{"train_loss": 2.0485665798187256, "global_step": 339283, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9896457195281982, "global_step": 339284, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1306514739990234, "global_step": 339285, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9753317832946777, "global_step": 339286, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.146599531173706, "global_step": 339287, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9777613878250122, "global_step": 339288, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9712414741516113, "global_step": 339289, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.098796844482422, "global_step": 339290, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0551505088806152, "global_step": 339291, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1010379791259766, "global_step": 339292, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1259922981262207, "global_step": 339293, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0202786922454834, "global_step": 339294, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.177194833755493, "global_step": 339295, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.113063335418701, "global_step": 339296, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0552680492401123, "global_step": 339297, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.064331293106079, "global_step": 339298, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0242364406585693, "global_step": 339299, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.067187786102295, "global_step": 339300, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075247049331665, "global_step": 339301, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0447983741760254, "global_step": 339302, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.036712884902954, "global_step": 339303, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0693023204803467, "global_step": 339304, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1720409393310547, "global_step": 339305, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1222972869873047, "global_step": 339306, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0278494358062744, "global_step": 339307, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0458266735076904, "global_step": 339308, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.042834997177124, "global_step": 339309, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0330867767333984, "global_step": 339310, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0796279907226562, "global_step": 339311, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0885708332061768, "global_step": 339312, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0023579597473145, "global_step": 339313, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0724706649780273, "global_step": 339314, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1229054927825928, "global_step": 339315, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1123874187469482, "global_step": 339316, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1108579635620117, "global_step": 339317, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1232521533966064, "global_step": 339318, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0176291465759277, "global_step": 339319, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0265941619873047, "global_step": 339320, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1252458095550537, "global_step": 339321, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0517961978912354, "global_step": 339322, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.061034917831421, "global_step": 339323, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.050644874572754, "global_step": 339324, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1539008617401123, "global_step": 339325, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.161879777908325, "global_step": 339326, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0878777503967285, "global_step": 339327, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045851230621338, "global_step": 339328, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0125837326049805, "global_step": 339329, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1199841499328613, "global_step": 339330, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08137583732605, "global_step": 339331, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.091998815536499, "global_step": 339332, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0689594745635986, "global_step": 339333, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1472465991973877, "global_step": 339334, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089404344558716, "global_step": 339335, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.004570960998535, "global_step": 339336, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0503439903259277, "global_step": 339337, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.197009563446045, "global_step": 339338, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.051396369934082, "global_step": 339339, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1106207370758057, "global_step": 339340, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0589489936828613, "global_step": 339341, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0819268226623535, "global_step": 339342, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108182430267334, "global_step": 339343, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1312613487243652, "global_step": 339344, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.081160545349121, "global_step": 339345, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0547678470611572, "global_step": 339346, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.034555673599243, "global_step": 339347, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.021831750869751, "global_step": 339348, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.093224048614502, "global_step": 339349, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1026487350463867, "global_step": 339350, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0690929889678955, "global_step": 339351, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0991690158843994, "global_step": 339352, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.078671455383301, "global_step": 339353, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.13881254196167, "global_step": 339354, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0740325450897217, "global_step": 339355, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108102321624756, "global_step": 339356, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.038004159927368, "global_step": 339357, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0827791690826416, "global_step": 339358, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0737717151641846, "global_step": 339359, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1641368865966797, "global_step": 339360, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0061583518981934, "global_step": 339361, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.083414077758789, "global_step": 339362, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9907913208007812, "global_step": 339363, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134685516357422, "global_step": 339364, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.087163209915161, "global_step": 339365, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.059094190597534, "global_step": 339366, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1213302612304688, "global_step": 339367, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.060152053833008, "global_step": 339368, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0554230213165283, "global_step": 339369, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0847933292388916, "global_step": 339370, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.007566213607788, "global_step": 339371, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1193389892578125, "global_step": 339372, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1504833698272705, "global_step": 339373, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.046856641769409, "global_step": 339374, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.171339988708496, "global_step": 339375, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.04328989982605, "global_step": 339376, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.025855541229248, "global_step": 339377, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1474859714508057, "global_step": 339378, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2419936656951904, "global_step": 339379, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.029259443283081, "global_step": 339380, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9974653720855713, "global_step": 339381, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085711717605591, "global_step": 339382, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.990231990814209, "global_step": 339383, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.025972843170166, "global_step": 339384, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0525028705596924, "global_step": 339385, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0981547832489014, "global_step": 339386, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0711817741394043, "global_step": 339387, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1375412940979004, "global_step": 339388, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1217362880706787, "global_step": 339389, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.128859519958496, "global_step": 339390, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.067574977874756, "global_step": 339391, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.103990077972412, "global_step": 339392, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.099390745162964, "global_step": 339393, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0723166465759277, "global_step": 339394, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0439395904541016, "global_step": 339395, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.031935214996338, "global_step": 339396, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.125248432159424, "global_step": 339397, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.231238842010498, "global_step": 339398, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2043771743774414, "global_step": 339399, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.048854351043701, "global_step": 339400, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0800676345825195, "global_step": 339401, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1789915561676025, "global_step": 339402, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1310079097747803, "global_step": 339403, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.14128041267395, "global_step": 339404, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1967477798461914, "global_step": 339405, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055788278579712, "global_step": 339406, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.144587278366089, "global_step": 339407, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0491185188293457, "global_step": 339408, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.03230881690979, "global_step": 339409, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072333574295044, "global_step": 339410, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.048292875289917, "global_step": 339411, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0333786010742188, "global_step": 339412, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1073787212371826, "global_step": 339413, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.146613359451294, "global_step": 339414, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1026272773742676, "global_step": 339415, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.065530300140381, "global_step": 339416, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0856611728668213, "global_step": 339417, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0683343410491943, "global_step": 339418, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044149160385132, "global_step": 339419, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0636186599731445, "global_step": 339420, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0524394512176514, "global_step": 339421, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.041060447692871, "global_step": 339422, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0868914127349854, "global_step": 339423, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0717718601226807, "global_step": 339424, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1369757652282715, "global_step": 339425, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1574480533599854, "global_step": 339426, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.088874340057373, "global_step": 339427, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0649054050445557, "global_step": 339428, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1427836418151855, "global_step": 339429, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.102733850479126, "global_step": 339430, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1402575969696045, "global_step": 339431, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1102294921875, "global_step": 339432, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0449562072753906, "global_step": 339433, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1107921600341797, "global_step": 339434, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.130204677581787, "global_step": 339435, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0562212467193604, "global_step": 339436, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123155117034912, "global_step": 339437, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1465885639190674, "global_step": 339438, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0942318439483643, "global_step": 339439, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.184781551361084, "global_step": 339440, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0534045696258545, "global_step": 339441, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084221124649048, "global_step": 339442, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.181774139404297, "global_step": 339443, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.00284743309021, "global_step": 339444, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0320122241973877, "global_step": 339445, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086679458618164, "global_step": 339446, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.027425527572632, "global_step": 339447, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.034241199493408, "global_step": 339448, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1353554725646973, "global_step": 339449, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1071739196777344, "global_step": 339450, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.102182388305664, "global_step": 339451, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.066983222961426, "global_step": 339452, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1243369579315186, "global_step": 339453, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9914228916168213, "global_step": 339454, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0595040321350098, "global_step": 339455, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075171947479248, "global_step": 339456, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.032179117202759, "global_step": 339457, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.039379835128784, "global_step": 339458, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0901079177856445, "global_step": 339459, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.008066177368164, "global_step": 339460, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1007089614868164, "global_step": 339461, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0698530673980713, "global_step": 339462, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0243446826934814, "global_step": 339463, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1292903423309326, "global_step": 339464, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1155943870544434, "global_step": 339465, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0780317783355713, "global_step": 339466, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0835583209991455, "global_step": 339467, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1083590984344482, "global_step": 339468, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.071031332015991, "global_step": 339469, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1217617988586426, "global_step": 339470, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1152968406677246, "global_step": 339471, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0693678855895996, "global_step": 339472, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2204535007476807, "global_step": 339473, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.021130084991455, "global_step": 339474, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1458826065063477, "global_step": 339475, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1479392051696777, "global_step": 339476, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.180551052093506, "global_step": 339477, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0577898025512695, "global_step": 339478, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1360387802124023, "global_step": 339479, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0463438034057617, "global_step": 339480, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1514458656311035, "global_step": 339481, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0557427406311035, "global_step": 339482, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.039802074432373, "global_step": 339483, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0992274284362793, "global_step": 339484, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0199663639068604, "global_step": 339485, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9466603994369507, "global_step": 339486, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0873899459838867, "global_step": 339487, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0579662322998047, "global_step": 339488, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0348594188690186, "global_step": 339489, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0568857192993164, "global_step": 339490, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0683462619781494, "global_step": 339491, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0281641483306885, "global_step": 339492, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9581019878387451, "global_step": 339493, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2120413780212402, "global_step": 339494, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1352345943450928, "global_step": 339495, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1530065536499023, "global_step": 339496, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0875566005706787, "global_step": 339497, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1332335472106934, "global_step": 339498, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119272232055664, "global_step": 339499, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0396230220794678, "global_step": 339500, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085543632507324, "global_step": 339501, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0638256072998047, "global_step": 339502, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110837936401367, "global_step": 339503, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119009256362915, "global_step": 339504, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0749454498291016, "global_step": 339505, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079287528991699, "global_step": 339506, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0830438137054443, "global_step": 339507, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0607354640960693, "global_step": 339508, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1270503997802734, "global_step": 339509, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1121463775634766, "global_step": 339510, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1443634033203125, "global_step": 339511, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.155923843383789, "global_step": 339512, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0907058715820312, "global_step": 339513, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.157423973083496, "global_step": 339514, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0834901332855225, "global_step": 339515, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08803129196167, "global_step": 339516, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0572378635406494, "global_step": 339517, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0751802921295166, "global_step": 339518, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079381227493286, "global_step": 339519, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0951201915740967, "global_step": 339520, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.118039608001709, "global_step": 339521, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0228049755096436, "global_step": 339522, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.111823797225952, "global_step": 339523, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.005990743637085, "global_step": 339524, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119229316711426, "global_step": 339525, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0724329948425293, "global_step": 339526, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.141737461090088, "global_step": 339527, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.126065731048584, "global_step": 339528, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1468827724456787, "global_step": 339529, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0743188858032227, "global_step": 339530, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.013768434524536, "global_step": 339531, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1286814212799072, "global_step": 339532, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1194515228271484, "global_step": 339533, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0736401081085205, "global_step": 339534, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.186391592025757, "global_step": 339535, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1264374256134033, "global_step": 339536, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0706052780151367, "global_step": 339537, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1522481441497803, "global_step": 339538, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0903308391571045, "global_step": 339539, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.125969886779785, "global_step": 339540, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.091367244720459, "global_step": 339541, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1084835529327393, "global_step": 339542, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.06274676322937, "global_step": 339543, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075059413909912, "global_step": 339544, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0967860221862793, "global_step": 339545, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9997007846832275, "global_step": 339546, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.099946975708008, "global_step": 339547, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.021249771118164, "global_step": 339548, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1075215339660645, "global_step": 339549, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1619250774383545, "global_step": 339550, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1286356449127197, "global_step": 339551, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055584669113159, "global_step": 339552, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0042378902435303, "global_step": 339553, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1101458072662354, "global_step": 339554, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0510029792785645, "global_step": 339555, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0554237365722656, "global_step": 339556, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0201354026794434, "global_step": 339557, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.088665008544922, "global_step": 339558, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.052496910095215, "global_step": 339559, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0513064861297607, "global_step": 339560, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.07590651512146, "global_step": 339561, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.142155408859253, "global_step": 339562, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1166832447052, "global_step": 339563, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.127322196960449, "global_step": 339564, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112863302230835, "global_step": 339565, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1378488540649414, "global_step": 339566, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.109661102294922, "global_step": 339567, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9981831312179565, "global_step": 339568, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1341843605041504, "global_step": 339569, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1683461666107178, "global_step": 339570, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1388509273529053, "global_step": 339571, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0990705490112305, "global_step": 339572, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.088620662689209, "global_step": 339573, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.106187343597412, "global_step": 339574, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1822052001953125, "global_step": 339575, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.024197578430176, "global_step": 339576, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0958008766174316, "global_step": 339577, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9885998964309692, "global_step": 339578, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9845483303070068, "global_step": 339579, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0528006553649902, "global_step": 339580, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.120534896850586, "global_step": 339581, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0619606971740723, "global_step": 339582, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1715657711029053, "global_step": 339583, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.128491163253784, "global_step": 339584, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0117974281311035, "global_step": 339585, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134183645248413, "global_step": 339586, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.080925703048706, "global_step": 339587, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.047260284423828, "global_step": 339588, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1079390048980713, "global_step": 339589, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0677335262298584, "global_step": 339590, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1314213275909424, "global_step": 339591, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0775206089019775, "global_step": 339592, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.116262674331665, "global_step": 339593, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.052745819091797, "global_step": 339594, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0137200355529785, "global_step": 339595, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0524048805236816, "global_step": 339596, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.111295461654663, "global_step": 339597, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0823276042938232, "global_step": 339598, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.034607172012329, "global_step": 339599, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0994744300842285, "global_step": 339600, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.146594285964966, "global_step": 339601, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1490790843963623, "global_step": 339602, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076195478439331, "global_step": 339603, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.144810676574707, "global_step": 339604, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.034801959991455, "global_step": 339605, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1038899421691895, "global_step": 339606, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0699713230133057, "global_step": 339607, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0701372623443604, "global_step": 339608, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0935447216033936, "global_step": 339609, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1063382625579834, "global_step": 339610, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0323081016540527, "global_step": 339611, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.066688060760498, "global_step": 339612, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0857441425323486, "global_step": 339613, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.060582399368286, "global_step": 339614, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0553975105285645, "global_step": 339615, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0981740951538086, "global_step": 339616, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1251003742218018, "global_step": 339617, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.018942356109619, "global_step": 339618, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045624256134033, "global_step": 339619, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1004486083984375, "global_step": 339620, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0988423824310303, "global_step": 339621, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0396740436553955, "global_step": 339622, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.109861373901367, "global_step": 339623, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1252198219299316, "global_step": 339624, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0894458293914795, "global_step": 339625, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.16856050491333, "global_step": 339626, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.11458683013916, "global_step": 339627, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.132735252380371, "global_step": 339628, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1289610862731934, "global_step": 339629, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.111891746520996, "global_step": 339630, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1238327026367188, "global_step": 339631, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1829912662506104, "global_step": 339632, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0760223865509033, "global_step": 339633, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08597469329834, "global_step": 339634, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.146791696548462, "global_step": 339635, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0978729724884033, "global_step": 339636, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.113710403442383, "global_step": 339637, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0576469898223877, "global_step": 339638, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0470850467681885, "global_step": 339639, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1392924785614014, "global_step": 339640, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1283516883850098, "global_step": 339641, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0013809204101562, "global_step": 339642, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108707904815674, "global_step": 339643, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.052870512008667, "global_step": 339644, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.155042886734009, "global_step": 339645, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.187729597091675, "global_step": 339646, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1772680282592773, "global_step": 339647, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0875048637390137, "global_step": 339648, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1785616874694824, "global_step": 339649, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.092334508895874, "global_step": 339650, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.124535322189331, "global_step": 339651, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.985260248184204, "global_step": 339652, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0639936923980713, "global_step": 339653, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0491371154785156, "global_step": 339654, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0590929985046387, "global_step": 339655, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0894761085510254, "global_step": 339656, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0372371673583984, "global_step": 339657, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1404740810394287, "global_step": 339658, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9547582864761353, "global_step": 339659, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108180284500122, "global_step": 339660, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0695743560791016, "global_step": 339661, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1279256343841553, "global_step": 339662, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0854876041412354, "global_step": 339663, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0405452251434326, "global_step": 339664, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1274425983428955, "global_step": 339665, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0651659965515137, "global_step": 339666, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1155126094818115, "global_step": 339667, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122316598892212, "global_step": 339668, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.195584297180176, "global_step": 339669, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0810835361480713, "global_step": 339670, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0396268367767334, "global_step": 339671, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1666641235351562, "global_step": 339672, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1347672939300537, "global_step": 339673, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1025772094726562, "global_step": 339674, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1899912357330322, "global_step": 339675, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0617012977600098, "global_step": 339676, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0839638710021973, "global_step": 339677, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.009150981903076, "global_step": 339678, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.04473614692688, "global_step": 339679, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1079249382019043, "global_step": 339680, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1403987407684326, "global_step": 339681, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0682482719421387, "global_step": 339682, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0550649166107178, "global_step": 339683, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.093470335006714, "global_step": 339684, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.111283302307129, "global_step": 339685, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110079526901245, "global_step": 339686, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1947808265686035, "global_step": 339687, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076491594314575, "global_step": 339688, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0564560890197754, "global_step": 339689, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0609185695648193, "global_step": 339690, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1351613998413086, "global_step": 339691, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.198913335800171, "global_step": 339692, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1155920028686523, "global_step": 339693, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.164952516555786, "global_step": 339694, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0041420459747314, "global_step": 339695, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0541765689849854, "global_step": 339696, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1362175941467285, "global_step": 339697, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1294240951538086, "global_step": 339698, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.111598014831543, "global_step": 339699, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.127464532852173, "global_step": 339700, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0539050102233887, "global_step": 339701, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0599355697631836, "global_step": 339702, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1389665603637695, "global_step": 339703, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0363779067993164, "global_step": 339704, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.07196307182312, "global_step": 339705, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1202940940856934, "global_step": 339706, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1023950576782227, "global_step": 339707, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.149820566177368, "global_step": 339708, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1158511638641357, "global_step": 339709, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1066718101501465, "global_step": 339710, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0879340171813965, "global_step": 339711, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0530261993408203, "global_step": 339712, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0555598735809326, "global_step": 339713, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9547581672668457, "global_step": 339714, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.080059051513672, "global_step": 339715, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.155877113342285, "global_step": 339716, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0362346172332764, "global_step": 339717, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1017017364501953, "global_step": 339718, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1254823207855225, "global_step": 339719, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0890698432922363, "global_step": 339720, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1609585285186768, "global_step": 339721, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072309732437134, "global_step": 339722, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.101447343826294, "global_step": 339723, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1086108684539795, "global_step": 339724, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.206519842147827, "global_step": 339725, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.226940393447876, "global_step": 339726, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0744104385375977, "global_step": 339727, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0083134174346924, "global_step": 339728, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.14442777633667, "global_step": 339729, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0567848682403564, "global_step": 339730, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0421862602233887, "global_step": 339731, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1307272911071777, "global_step": 339732, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079397678375244, "global_step": 339733, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0453529357910156, "global_step": 339734, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.064359188079834, "global_step": 339735, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.140345335006714, "global_step": 339736, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.048926591873169, "global_step": 339737, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0514910221099854, "global_step": 339738, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1360318660736084, "global_step": 339739, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1478569507598877, "global_step": 339740, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.12859845161438, "global_step": 339741, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1810379028320312, "global_step": 339742, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0280630588531494, "global_step": 339743, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1188440322875977, "global_step": 339744, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2038285732269287, "global_step": 339745, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123422622680664, "global_step": 339746, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1811959743499756, "global_step": 339747, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0543370246887207, "global_step": 339748, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0406112670898438, "global_step": 339749, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.062223196029663, "global_step": 339750, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.195490598678589, "global_step": 339751, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.109618663787842, "global_step": 339752, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.097945213317871, "global_step": 339753, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.117443084716797, "global_step": 339754, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1044938564300537, "global_step": 339755, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.05519700050354, "global_step": 339756, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0615410804748535, "global_step": 339757, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.078270196914673, "global_step": 339758, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.966105341911316, "global_step": 339759, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.115046501159668, "global_step": 339760, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0298972129821777, "global_step": 339761, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0834410190582275, "global_step": 339762, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0451292991638184, "global_step": 339763, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1300876140594482, "global_step": 339764, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1085941791534424, "global_step": 339765, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.947724461555481, "global_step": 339766, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0498461723327637, "global_step": 339767, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.050544500350952, "global_step": 339768, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.166818857192993, "global_step": 339769, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0507004261016846, "global_step": 339770, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.149684190750122, "global_step": 339771, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.101982831954956, "global_step": 339772, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134648323059082, "global_step": 339773, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.182171106338501, "global_step": 339774, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0870206356048584, "global_step": 339775, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1786670684814453, "global_step": 339776, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0596659183502197, "global_step": 339777, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1332967281341553, "global_step": 339778, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.082113027572632, "global_step": 339779, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.22417950630188, "global_step": 339780, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0712711811065674, "global_step": 339781, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.018134117126465, "global_step": 339782, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0521373748779297, "global_step": 339783, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.127659797668457, "global_step": 339784, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123067855834961, "global_step": 339785, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.039933204650879, "global_step": 339786, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1550960540771484, "global_step": 339787, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1160402297973633, "global_step": 339788, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.155811071395874, "global_step": 339789, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0901665687561035, "global_step": 339790, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0752384662628174, "global_step": 339791, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0355565547943115, "global_step": 339792, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1176676750183105, "global_step": 339793, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.091264009475708, "global_step": 339794, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1015803813934326, "global_step": 339795, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2125816345214844, "global_step": 339796, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0809898376464844, "global_step": 339797, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0903701782226562, "global_step": 339798, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0785696506500244, "global_step": 339799, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1024718284606934, "global_step": 339800, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.137448310852051, "global_step": 339801, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1104884147644043, "global_step": 339802, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.063922166824341, "global_step": 339803, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.162132740020752, "global_step": 339804, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0828914642333984, "global_step": 339805, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.053102493286133, "global_step": 339806, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.082821846008301, "global_step": 339807, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.178135395050049, "global_step": 339808, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0039007663726807, "global_step": 339809, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.080678701400757, "global_step": 339810, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9780409336090088, "global_step": 339811, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0718231201171875, "global_step": 339812, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100842237472534, "global_step": 339813, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0431106090545654, "global_step": 339814, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.141012668609619, "global_step": 339815, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086139440536499, "global_step": 339816, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.212308883666992, "global_step": 339817, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0786497592926025, "global_step": 339818, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0333633422851562, "global_step": 339819, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0823328495025635, "global_step": 339820, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1020379066467285, "global_step": 339821, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0183255672454834, "global_step": 339822, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1813278198242188, "global_step": 339823, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1774749755859375, "global_step": 339824, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.038628339767456, "global_step": 339825, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.172224521636963, "global_step": 339826, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.116797924041748, "global_step": 339827, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.141369342803955, "global_step": 339828, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1062543392181396, "global_step": 339829, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1500298976898193, "global_step": 339830, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.059779167175293, "global_step": 339831, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1897103786468506, "global_step": 339832, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9732415676116943, "global_step": 339833, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1581876277923584, "global_step": 339834, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.133899688720703, "global_step": 339835, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112673759460449, "global_step": 339836, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0469810962677, "global_step": 339837, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.168201208114624, "global_step": 339838, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0236244201660156, "global_step": 339839, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.171682596206665, "global_step": 339840, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0454676151275635, "global_step": 339841, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.057335138320923, "global_step": 339842, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9787276983261108, "global_step": 339843, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.077968120574951, "global_step": 339844, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1041247844696045, "global_step": 339845, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1139841079711914, "global_step": 339846, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1460440158843994, "global_step": 339847, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.024533271789551, "global_step": 339848, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.103067636489868, "global_step": 339849, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.102160930633545, "global_step": 339850, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0370426177978516, "global_step": 339851, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.102947950363159, "global_step": 339852, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.080066204071045, "global_step": 339853, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122943639755249, "global_step": 339854, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1243746280670166, "global_step": 339855, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1317360401153564, "global_step": 339856, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0680840015411377, "global_step": 339857, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0418930053710938, "global_step": 339858, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1579015254974365, "global_step": 339859, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0743727684020996, "global_step": 339860, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.073533058166504, "global_step": 339861, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2050750255584717, "global_step": 339862, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1496288776397705, "global_step": 339863, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0543875694274902, "global_step": 339864, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0026581287384033, "global_step": 339865, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1532793045043945, "global_step": 339866, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.117682456970215, "global_step": 339867, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10131573677063, "global_step": 339868, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.068692445755005, "global_step": 339869, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0749127864837646, "global_step": 339870, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0327460765838623, "global_step": 339871, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0909042358398438, "global_step": 339872, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.111090898513794, "global_step": 339873, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1465184688568115, "global_step": 339874, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1166577339172363, "global_step": 339875, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0799832344055176, "global_step": 339876, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.99876070022583, "global_step": 339877, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.136261224746704, "global_step": 339878, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1311850547790527, "global_step": 339879, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0626213550567627, "global_step": 339880, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9535330533981323, "global_step": 339881, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119222402572632, "global_step": 339882, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.152674436569214, "global_step": 339883, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1144821643829346, "global_step": 339884, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1753036975860596, "global_step": 339885, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1328837871551514, "global_step": 339886, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0712897777557373, "global_step": 339887, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1971020698547363, "global_step": 339888, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1190977096557617, "global_step": 339889, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0874457359313965, "global_step": 339890, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089323043823242, "global_step": 339891, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.091111660003662, "global_step": 339892, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.111478567123413, "global_step": 339893, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1369526386260986, "global_step": 339894, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084676504135132, "global_step": 339895, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.144643545150757, "global_step": 339896, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.023317575454712, "global_step": 339897, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.078953266143799, "global_step": 339898, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.186107635498047, "global_step": 339899, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.148850202560425, "global_step": 339900, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1523921489715576, "global_step": 339901, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1033077239990234, "global_step": 339902, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1339311599731445, "global_step": 339903, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1641693115234375, "global_step": 339904, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1041054725646973, "global_step": 339905, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0659279823303223, "global_step": 339906, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0278635025024414, "global_step": 339907, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055903911590576, "global_step": 339908, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1207025051116943, "global_step": 339909, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.077751636505127, "global_step": 339910, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1145708560943604, "global_step": 339911, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9783214330673218, "global_step": 339912, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.06394624710083, "global_step": 339913, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.062668800354004, "global_step": 339914, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.067028284072876, "global_step": 339915, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0652267932891846, "global_step": 339916, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.143608808517456, "global_step": 339917, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0400354862213135, "global_step": 339918, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0631356239318848, "global_step": 339919, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1940090656280518, "global_step": 339920, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0389230251312256, "global_step": 339921, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1232755184173584, "global_step": 339922, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.073579788208008, "global_step": 339923, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1597464084625244, "global_step": 339924, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0851993560791016, "global_step": 339925, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1380441188812256, "global_step": 339926, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1070492267608643, "global_step": 339927, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2011101245880127, "global_step": 339928, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0802676677703857, "global_step": 339929, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.09264874458313, "global_step": 339930, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2013328075408936, "global_step": 339931, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.13152813911438, "global_step": 339932, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.096987009048462, "global_step": 339933, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2412383556365967, "global_step": 339934, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0806238651275635, "global_step": 339935, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0467967987060547, "global_step": 339936, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0462253093719482, "global_step": 339937, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.063084125518799, "global_step": 339938, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.116121768951416, "global_step": 339939, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.14799165725708, "global_step": 339940, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.14434814453125, "global_step": 339941, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0844035148620605, "global_step": 339942, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1562747955322266, "global_step": 339943, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1202290058135986, "global_step": 339944, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0356063842773438, "global_step": 339945, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1209769248962402, "global_step": 339946, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.118739604949951, "global_step": 339947, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.14015531539917, "global_step": 339948, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1495449542999268, "global_step": 339949, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1490654945373535, "global_step": 339950, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.028526544570923, "global_step": 339951, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.125626564025879, "global_step": 339952, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1046907901763916, "global_step": 339953, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.144005298614502, "global_step": 339954, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1271536350250244, "global_step": 339955, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1719980239868164, "global_step": 339956, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1100900173187256, "global_step": 339957, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1217215061187744, "global_step": 339958, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1434783935546875, "global_step": 339959, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1473336219787598, "global_step": 339960, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1986334323883057, "global_step": 339961, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110501289367676, "global_step": 339962, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1340246200561523, "global_step": 339963, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.985634446144104, "global_step": 339964, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9965637922286987, "global_step": 339965, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1392405033111572, "global_step": 339966, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0976834297180176, "global_step": 339967, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1231160163879395, "global_step": 339968, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.117034435272217, "global_step": 339969, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1877763271331787, "global_step": 339970, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100764513015747, "global_step": 339971, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.101055383682251, "global_step": 339972, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0478339195251465, "global_step": 339973, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1287994384765625, "global_step": 339974, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0747830867767334, "global_step": 339975, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.114588737487793, "global_step": 339976, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1671831607818604, "global_step": 339977, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1636526584625244, "global_step": 339978, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.139781951904297, "global_step": 339979, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0901715755462646, "global_step": 339980, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0850257873535156, "global_step": 339981, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.168158531188965, "global_step": 339982, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2254292964935303, "global_step": 339983, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.11257266998291, "global_step": 339984, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.071951389312744, "global_step": 339985, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0223734378814697, "global_step": 339986, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1215717792510986, "global_step": 339987, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0791542530059814, "global_step": 339988, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.04034423828125, "global_step": 339989, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.127568006515503, "global_step": 339990, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0722920894622803, "global_step": 339991, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0874991416931152, "global_step": 339992, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1309990882873535, "global_step": 339993, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1291589736938477, "global_step": 339994, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.040658473968506, "global_step": 339995, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2626876831054688, "global_step": 339996, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10725474357605, "global_step": 339997, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.042760133743286, "global_step": 339998, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1475908756256104, "global_step": 339999, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1130409240722656, "global_step": 340000, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1228814125061035, "global_step": 340001, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.092634439468384, "global_step": 340002, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110097646713257, "global_step": 340003, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.030524253845215, "global_step": 340004, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0529263019561768, "global_step": 340005, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110107898712158, "global_step": 340006, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.163165807723999, "global_step": 340007, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1009397506713867, "global_step": 340008, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0147545337677, "global_step": 340009, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0700039863586426, "global_step": 340010, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.101780652999878, "global_step": 340011, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.146616220474243, "global_step": 340012, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1079440116882324, "global_step": 340013, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.189409017562866, "global_step": 340014, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0908055305480957, "global_step": 340015, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0027966499328613, "global_step": 340016, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.143800735473633, "global_step": 340017, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1775858402252197, "global_step": 340018, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0883829593658447, "global_step": 340019, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.090808391571045, "global_step": 340020, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112724781036377, "global_step": 340021, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.036449670791626, "global_step": 340022, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0588767528533936, "global_step": 340023, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0679399967193604, "global_step": 340024, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1111087799072266, "global_step": 340025, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.060441017150879, "global_step": 340026, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0378122329711914, "global_step": 340027, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.07310152053833, "global_step": 340028, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2092511653900146, "global_step": 340029, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.121849775314331, "global_step": 340030, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.019747734069824, "global_step": 340031, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1200685501098633, "global_step": 340032, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.145310878753662, "global_step": 340033, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1115050315856934, "global_step": 340034, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.094871759414673, "global_step": 340035, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0665016174316406, "global_step": 340036, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0967259407043457, "global_step": 340037, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.197704553604126, "global_step": 340038, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0531225204467773, "global_step": 340039, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.093968391418457, "global_step": 340040, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1284148693084717, "global_step": 340041, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.13327693939209, "global_step": 340042, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0797417163848877, "global_step": 340043, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0410099029541016, "global_step": 340044, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1597681045532227, "global_step": 340045, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100532054901123, "global_step": 340046, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0980920791625977, "global_step": 340047, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.081777334213257, "global_step": 340048, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0726895332336426, "global_step": 340049, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.987308144569397, "global_step": 340050, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.99490487575531, "global_step": 340051, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.152339220046997, "global_step": 340052, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.155513048171997, "global_step": 340053, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086808681488037, "global_step": 340054, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.105146884918213, "global_step": 340055, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0962958335876465, "global_step": 340056, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.176501750946045, "global_step": 340057, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1341652870178223, "global_step": 340058, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1030399799346924, "global_step": 340059, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0587809085845947, "global_step": 340060, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0766913890838623, "global_step": 340061, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.170966386795044, "global_step": 340062, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0893352031707764, "global_step": 340063, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1700165271759033, "global_step": 340064, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0419774055480957, "global_step": 340065, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.133666515350342, "global_step": 340066, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.117347002029419, "global_step": 340067, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.169538736343384, "global_step": 340068, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2353787422180176, "global_step": 340069, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.042861223220825, "global_step": 340070, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.114248752593994, "global_step": 340071, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1186742782592773, "global_step": 340072, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1118671894073486, "global_step": 340073, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.114199161529541, "global_step": 340074, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.128636121749878, "global_step": 340075, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0686347484588623, "global_step": 340076, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1013476848602295, "global_step": 340077, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0476784706115723, "global_step": 340078, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.151726484298706, "global_step": 340079, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1331231594085693, "global_step": 340080, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.128085136413574, "global_step": 340081, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1473610401153564, "global_step": 340082, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.088597536087036, "global_step": 340083, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0754947662353516, "global_step": 340084, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.115304470062256, "global_step": 340085, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0871522426605225, "global_step": 340086, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1633713245391846, "global_step": 340087, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1280670166015625, "global_step": 340088, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.061169385910034, "global_step": 340089, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.082118511199951, "global_step": 340090, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0775721073150635, "global_step": 340091, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1078786849975586, "global_step": 340092, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.035867929458618, "global_step": 340093, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1469991207122803, "global_step": 340094, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1500699520111084, "global_step": 340095, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0199859142303467, "global_step": 340096, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1698057651519775, "global_step": 340097, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.12335205078125, "global_step": 340098, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.091454029083252, "global_step": 340099, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1044304370880127, "global_step": 340100, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.195237874984741, "global_step": 340101, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1804039478302, "global_step": 340102, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084916114807129, "global_step": 340103, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1104893684387207, "global_step": 340104, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.162818670272827, "global_step": 340105, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1603407859802246, "global_step": 340106, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054931640625, "global_step": 340107, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.082362413406372, "global_step": 340108, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.032656192779541, "global_step": 340109, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.090352773666382, "global_step": 340110, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044710636138916, "global_step": 340111, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.047194719314575, "global_step": 340112, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0868124961853027, "global_step": 340113, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1074037551879883, "global_step": 340114, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0426185131073, "global_step": 340115, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.094567060470581, "global_step": 340116, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.157642364501953, "global_step": 340117, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.19467830657959, "global_step": 340118, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.157527446746826, "global_step": 340119, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0784547328948975, "global_step": 340120, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1096792221069336, "global_step": 340121, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1813254356384277, "global_step": 340122, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.106119155883789, "global_step": 340123, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0832276344299316, "global_step": 340124, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1063148975372314, "global_step": 340125, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086162805557251, "global_step": 340126, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1627659797668457, "global_step": 340127, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0939126014709473, "global_step": 340128, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.114341974258423, "global_step": 340129, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0741589069366455, "global_step": 340130, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1109237670898438, "global_step": 340131, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1523067951202393, "global_step": 340132, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1622767448425293, "global_step": 340133, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10908579826355, "global_step": 340134, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.167684316635132, "global_step": 340135, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1662580966949463, "global_step": 340136, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1750104427337646, "global_step": 340137, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1733343601226807, "global_step": 340138, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0698013305664062, "global_step": 340139, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0642757415771484, "global_step": 340140, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075862407684326, "global_step": 340141, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.074049234390259, "global_step": 340142, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0617494583129883, "global_step": 340143, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1948421001434326, "global_step": 340144, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0615832805633545, "global_step": 340145, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0725533962249756, "global_step": 340146, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1786508560180664, "global_step": 340147, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1819543838500977, "global_step": 340148, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1314940452575684, "global_step": 340149, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.070648670196533, "global_step": 340150, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.192598342895508, "global_step": 340151, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1382129192352295, "global_step": 340152, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085798740386963, "global_step": 340153, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0460093021392822, "global_step": 340154, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1145384311676025, "global_step": 340155, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1238536834716797, "global_step": 340156, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.064375877380371, "global_step": 340157, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1337687969207764, "global_step": 340158, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.096144676208496, "global_step": 340159, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.078258514404297, "global_step": 340160, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1462559700012207, "global_step": 340161, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1269938945770264, "global_step": 340162, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1012909412384033, "global_step": 340163, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0999929904937744, "global_step": 340164, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.074617624282837, "global_step": 340165, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1886470317840576, "global_step": 340166, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.150057554244995, "global_step": 340167, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10996150970459, "global_step": 340168, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.008758068084717, "global_step": 340169, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0861589908599854, "global_step": 340170, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1166272163391113, "global_step": 340171, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0383992195129395, "global_step": 340172, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1982667446136475, "global_step": 340173, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1300408840179443, "global_step": 340174, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.175140857696533, "global_step": 340175, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.015909194946289, "global_step": 340176, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.247546672821045, "global_step": 340177, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.160634994506836, "global_step": 340178, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0739645957946777, "global_step": 340179, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086397409439087, "global_step": 340180, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10105299949646, "global_step": 340181, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0381596088409424, "global_step": 340182, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1523563861846924, "global_step": 340183, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1879847049713135, "global_step": 340184, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1887612342834473, "global_step": 340185, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.015026092529297, "global_step": 340186, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1255435943603516, "global_step": 340187, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.200146198272705, "global_step": 340188, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.175462245941162, "global_step": 340189, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.104896068572998, "global_step": 340190, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.175433397293091, "global_step": 340191, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1446025371551514, "global_step": 340192, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1572883129119873, "global_step": 340193, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072481870651245, "global_step": 340194, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.099170207977295, "global_step": 340195, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1027681827545166, "global_step": 340196, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0978381633758545, "global_step": 340197, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1056160926818848, "global_step": 340198, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.012486696243286, "global_step": 340199, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0966668128967285, "global_step": 340200, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.046267509460449, "global_step": 340201, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2002334594726562, "global_step": 340202, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.115922451019287, "global_step": 340203, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0407423973083496, "global_step": 340204, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1833927631378174, "global_step": 340205, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.09714412689209, "global_step": 340206, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0749874114990234, "global_step": 340207, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0458180904388428, "global_step": 340208, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0861523151397705, "global_step": 340209, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.139455556869507, "global_step": 340210, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122441291809082, "global_step": 340211, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072916269302368, "global_step": 340212, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1407854557037354, "global_step": 340213, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1582589149475098, "global_step": 340214, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1911141872406006, "global_step": 340215, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.199951171875, "global_step": 340216, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0834484100341797, "global_step": 340217, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1687846183776855, "global_step": 340218, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0944483280181885, "global_step": 340219, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0686068534851074, "global_step": 340220, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1510725021362305, "global_step": 340221, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1547162532806396, "global_step": 340222, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.037564992904663, "global_step": 340223, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.081387519836426, "global_step": 340224, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069197416305542, "global_step": 340225, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0526175498962402, "global_step": 340226, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.186249256134033, "global_step": 340227, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0972177982330322, "global_step": 340228, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1171488761901855, "global_step": 340229, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.160874605178833, "global_step": 340230, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0814852714538574, "global_step": 340231, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1582844257354736, "global_step": 340232, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.121140718460083, "global_step": 340233, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1197826862335205, "global_step": 340234, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1581850051879883, "global_step": 340235, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2078354358673096, "global_step": 340236, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1665215492248535, "global_step": 340237, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.117130994796753, "global_step": 340238, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.171699047088623, "global_step": 340239, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0744292736053467, "global_step": 340240, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0809874534606934, "global_step": 340241, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.126291275024414, "global_step": 340242, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.041278600692749, "global_step": 340243, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.053910493850708, "global_step": 340244, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0788705348968506, "global_step": 340245, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0897364616394043, "global_step": 340246, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.199599027633667, "global_step": 340247, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0559937953948975, "global_step": 340248, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1462817192077637, "global_step": 340249, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1475062370300293, "global_step": 340250, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0485665798187256, "global_step": 339283, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9896459579467773, "global_step": 339284, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1306509971618652, "global_step": 339285, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.975332260131836, "global_step": 339286, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.146599769592285, "global_step": 339287, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9777570962905884, "global_step": 339288, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9712578058242798, "global_step": 339289, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.098815441131592, "global_step": 339290, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0551562309265137, "global_step": 339291, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1010215282440186, "global_step": 339292, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.125965118408203, "global_step": 339293, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.020303726196289, "global_step": 339294, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.177206039428711, "global_step": 339295, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1130785942077637, "global_step": 339296, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055267333984375, "global_step": 339297, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0644426345825195, "global_step": 339298, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.024233102798462, "global_step": 339299, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.067277193069458, "global_step": 339300, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075251579284668, "global_step": 339301, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044846773147583, "global_step": 339302, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0366744995117188, "global_step": 339303, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069258689880371, "global_step": 339304, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.171973705291748, "global_step": 339305, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1222732067108154, "global_step": 339306, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0276527404785156, "global_step": 339307, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0458853244781494, "global_step": 339308, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0427112579345703, "global_step": 339309, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0330913066864014, "global_step": 339310, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0799691677093506, "global_step": 339311, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0888943672180176, "global_step": 339312, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0024478435516357, "global_step": 339313, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072566270828247, "global_step": 339314, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122606039047241, "global_step": 339315, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1125645637512207, "global_step": 339316, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110395908355713, "global_step": 339317, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123303174972534, "global_step": 339318, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.017632007598877, "global_step": 339319, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0266270637512207, "global_step": 339320, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1255056858062744, "global_step": 339321, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0515520572662354, "global_step": 339322, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0609333515167236, "global_step": 339323, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.05118989944458, "global_step": 339324, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1540770530700684, "global_step": 339325, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.161661148071289, "global_step": 339326, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0874321460723877, "global_step": 339327, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.04565691947937, "global_step": 339328, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0132579803466797, "global_step": 339329, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1201140880584717, "global_step": 339330, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0818870067596436, "global_step": 339331, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0923244953155518, "global_step": 339332, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069246768951416, "global_step": 339333, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.146923303604126, "global_step": 339334, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08927845954895, "global_step": 339335, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0044336318969727, "global_step": 339336, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.049926996231079, "global_step": 339337, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.197262763977051, "global_step": 339338, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.05169415473938, "global_step": 339339, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1106786727905273, "global_step": 339340, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0590438842773438, "global_step": 339341, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0818324089050293, "global_step": 339342, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108281135559082, "global_step": 339343, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1310384273529053, "global_step": 339344, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0813558101654053, "global_step": 339345, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054675817489624, "global_step": 339346, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.034773826599121, "global_step": 339347, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.021649122238159, "global_step": 339348, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0934929847717285, "global_step": 339349, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1023800373077393, "global_step": 339350, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0694024562835693, "global_step": 339351, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0988190174102783, "global_step": 339352, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0785000324249268, "global_step": 339353, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.138463020324707, "global_step": 339354, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0744354724884033, "global_step": 339355, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1080684661865234, "global_step": 339356, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0380873680114746, "global_step": 339357, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.082821846008301, "global_step": 339358, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0740768909454346, "global_step": 339359, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1642305850982666, "global_step": 339360, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.006556272506714, "global_step": 339361, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0840978622436523, "global_step": 339362, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9908323287963867, "global_step": 339363, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1346044540405273, "global_step": 339364, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0879642963409424, "global_step": 339365, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0589003562927246, "global_step": 339366, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1217167377471924, "global_step": 339367, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0590128898620605, "global_step": 339368, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054389238357544, "global_step": 339369, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0850648880004883, "global_step": 339370, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.007723331451416, "global_step": 339371, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1194169521331787, "global_step": 339372, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.149704694747925, "global_step": 339373, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.047053098678589, "global_step": 339374, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1707584857940674, "global_step": 339375, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0427865982055664, "global_step": 339376, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.026087522506714, "global_step": 339377, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1470885276794434, "global_step": 339378, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.242429494857788, "global_step": 339379, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.030290126800537, "global_step": 339380, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9977103471755981, "global_step": 339381, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084934949874878, "global_step": 339382, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9893243312835693, "global_step": 339383, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.026717185974121, "global_step": 339384, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0523648262023926, "global_step": 339385, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.097806453704834, "global_step": 339386, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0714237689971924, "global_step": 339387, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1377296447753906, "global_step": 339388, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1212246417999268, "global_step": 339389, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.129565715789795, "global_step": 339390, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0673294067382812, "global_step": 339391, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1047921180725098, "global_step": 339392, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0990347862243652, "global_step": 339393, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.071856737136841, "global_step": 339394, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0433223247528076, "global_step": 339395, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0315771102905273, "global_step": 339396, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1247799396514893, "global_step": 339397, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2307493686676025, "global_step": 339398, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2050235271453857, "global_step": 339399, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0483431816101074, "global_step": 339400, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0795962810516357, "global_step": 339401, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1782338619232178, "global_step": 339402, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.130596160888672, "global_step": 339403, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1412301063537598, "global_step": 339404, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1961076259613037, "global_step": 339405, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055185079574585, "global_step": 339406, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1445491313934326, "global_step": 339407, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.04827880859375, "global_step": 339408, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.032759428024292, "global_step": 339409, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0704505443573, "global_step": 339410, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.047578811645508, "global_step": 339411, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0324783325195312, "global_step": 339412, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1086056232452393, "global_step": 339413, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1463656425476074, "global_step": 339414, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1039834022521973, "global_step": 339415, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0649032592773438, "global_step": 339416, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0856542587280273, "global_step": 339417, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.06779408454895, "global_step": 339418, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044546365737915, "global_step": 339419, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0636258125305176, "global_step": 339420, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0520694255828857, "global_step": 339421, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.040503978729248, "global_step": 339422, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085881233215332, "global_step": 339423, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.071629047393799, "global_step": 339424, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.136861801147461, "global_step": 339425, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.157130479812622, "global_step": 339426, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0886878967285156, "global_step": 339427, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0655386447906494, "global_step": 339428, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.143625020980835, "global_step": 339429, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.103459596633911, "global_step": 339430, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.140129327774048, "global_step": 339431, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110664129257202, "global_step": 339432, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045649290084839, "global_step": 339433, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1113922595977783, "global_step": 339434, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.129408359527588, "global_step": 339435, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0549988746643066, "global_step": 339436, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1230406761169434, "global_step": 339437, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1468238830566406, "global_step": 339438, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.093484401702881, "global_step": 339439, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1838479042053223, "global_step": 339440, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.053295135498047, "global_step": 339441, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085404396057129, "global_step": 339442, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1818275451660156, "global_step": 339443, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.003438949584961, "global_step": 339444, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0330734252929688, "global_step": 339445, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0873751640319824, "global_step": 339446, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0282037258148193, "global_step": 339447, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.03403902053833, "global_step": 339448, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134830951690674, "global_step": 339449, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.107621431350708, "global_step": 339450, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.102099895477295, "global_step": 339451, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0674736499786377, "global_step": 339452, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1242752075195312, "global_step": 339453, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9903223514556885, "global_step": 339454, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0585131645202637, "global_step": 339455, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0759711265563965, "global_step": 339456, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0334906578063965, "global_step": 339457, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0405049324035645, "global_step": 339458, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089914321899414, "global_step": 339459, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.008277177810669, "global_step": 339460, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1009411811828613, "global_step": 339461, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0694620609283447, "global_step": 339462, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.023699998855591, "global_step": 339463, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1297903060913086, "global_step": 339464, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1146860122680664, "global_step": 339465, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0778117179870605, "global_step": 339466, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084023952484131, "global_step": 339467, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1076862812042236, "global_step": 339468, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.070352077484131, "global_step": 339469, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1221492290496826, "global_step": 339470, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1161015033721924, "global_step": 339471, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0692548751831055, "global_step": 339472, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.219583511352539, "global_step": 339473, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.021893262863159, "global_step": 339474, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.146273612976074, "global_step": 339475, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1483941078186035, "global_step": 339476, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.179213285446167, "global_step": 339477, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.057821750640869, "global_step": 339478, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1367995738983154, "global_step": 339479, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.046785354614258, "global_step": 339480, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1521706581115723, "global_step": 339481, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0551600456237793, "global_step": 339482, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0395455360412598, "global_step": 339483, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0996694564819336, "global_step": 339484, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.018825054168701, "global_step": 339485, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9472756385803223, "global_step": 339486, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0882773399353027, "global_step": 339487, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0586986541748047, "global_step": 339488, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0346689224243164, "global_step": 339489, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.05791974067688, "global_step": 339490, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0686657428741455, "global_step": 339491, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.027445077896118, "global_step": 339492, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9574404954910278, "global_step": 339493, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2119812965393066, "global_step": 339494, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.135826587677002, "global_step": 339495, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.15124773979187, "global_step": 339496, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086334705352783, "global_step": 339497, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1329102516174316, "global_step": 339498, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1205785274505615, "global_step": 339499, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.038806438446045, "global_step": 339500, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0851125717163086, "global_step": 339501, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0646612644195557, "global_step": 339502, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110996723175049, "global_step": 339503, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1201066970825195, "global_step": 339504, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075533866882324, "global_step": 339505, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0805318355560303, "global_step": 339506, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0841641426086426, "global_step": 339507, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.061521291732788, "global_step": 339508, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1268606185913086, "global_step": 339509, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112940549850464, "global_step": 339510, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1462748050689697, "global_step": 339511, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1567606925964355, "global_step": 339512, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0902762413024902, "global_step": 339513, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.158043622970581, "global_step": 339514, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085249662399292, "global_step": 339515, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086663007736206, "global_step": 339516, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0541908740997314, "global_step": 339517, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0757861137390137, "global_step": 339518, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0796351432800293, "global_step": 339519, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0952296257019043, "global_step": 339520, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1170918941497803, "global_step": 339521, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0238349437713623, "global_step": 339522, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112003803253174, "global_step": 339523, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.003789186477661, "global_step": 339524, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.118227005004883, "global_step": 339525, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0719380378723145, "global_step": 339526, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.141058921813965, "global_step": 339527, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.125567674636841, "global_step": 339528, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147228479385376, "global_step": 339529, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.073664903640747, "global_step": 339530, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.014944553375244, "global_step": 339531, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.129161834716797, "global_step": 339532, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.120271921157837, "global_step": 339533, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.073922872543335, "global_step": 339534, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.186462879180908, "global_step": 339535, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1263656616210938, "global_step": 339536, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069899082183838, "global_step": 339537, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1497879028320312, "global_step": 339538, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0907349586486816, "global_step": 339539, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1243808269500732, "global_step": 339540, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.090723752975464, "global_step": 339541, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108074426651001, "global_step": 339542, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0635721683502197, "global_step": 339543, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0762572288513184, "global_step": 339544, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0957765579223633, "global_step": 339545, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.999245047569275, "global_step": 339546, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1008780002593994, "global_step": 339547, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0218095779418945, "global_step": 339548, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.106468677520752, "global_step": 339549, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1617538928985596, "global_step": 339550, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.127796173095703, "global_step": 339551, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054032325744629, "global_step": 339552, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0050148963928223, "global_step": 339553, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1087799072265625, "global_step": 339554, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0504894256591797, "global_step": 339555, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0545504093170166, "global_step": 339556, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0206775665283203, "global_step": 339557, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0890069007873535, "global_step": 339558, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0548086166381836, "global_step": 339559, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0503833293914795, "global_step": 339560, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0757315158843994, "global_step": 339561, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.141866683959961, "global_step": 339562, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.115887403488159, "global_step": 339563, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.12477445602417, "global_step": 339564, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1112427711486816, "global_step": 339565, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1393604278564453, "global_step": 339566, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1111717224121094, "global_step": 339567, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9997479915618896, "global_step": 339568, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134018898010254, "global_step": 339569, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.16861629486084, "global_step": 339570, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.138124942779541, "global_step": 339571, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0983448028564453, "global_step": 339572, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0883350372314453, "global_step": 339573, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1046857833862305, "global_step": 339574, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.183396339416504, "global_step": 339575, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.024833917617798, "global_step": 339576, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0951812267303467, "global_step": 339577, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9879435300827026, "global_step": 339578, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9838430881500244, "global_step": 339579, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0526044368743896, "global_step": 339580, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1202845573425293, "global_step": 339581, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0634207725524902, "global_step": 339582, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1716606616973877, "global_step": 339583, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.12917423248291, "global_step": 339584, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0118300914764404, "global_step": 339585, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.133662462234497, "global_step": 339586, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08073353767395, "global_step": 339587, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.046492576599121, "global_step": 339588, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.109428882598877, "global_step": 339589, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.070103645324707, "global_step": 339590, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1323044300079346, "global_step": 339591, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.077146291732788, "global_step": 339592, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1166906356811523, "global_step": 339593, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0510010719299316, "global_step": 339594, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0122830867767334, "global_step": 339595, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.052543878555298, "global_step": 339596, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1120502948760986, "global_step": 339597, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.082310438156128, "global_step": 339598, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.034022808074951, "global_step": 339599, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0987753868103027, "global_step": 339600, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1470961570739746, "global_step": 339601, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.150043249130249, "global_step": 339602, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.077125072479248, "global_step": 339603, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.145799398422241, "global_step": 339604, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0353949069976807, "global_step": 339605, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1022491455078125, "global_step": 339606, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0697083473205566, "global_step": 339607, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069918394088745, "global_step": 339608, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0936057567596436, "global_step": 339609, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.105496883392334, "global_step": 339610, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0323824882507324, "global_step": 339611, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.066950559616089, "global_step": 339612, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0843212604522705, "global_step": 339613, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0617012977600098, "global_step": 339614, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055704116821289, "global_step": 339615, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0979740619659424, "global_step": 339616, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1242451667785645, "global_step": 339617, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0185928344726562, "global_step": 339618, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044379949569702, "global_step": 339619, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1007094383239746, "global_step": 339620, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0988526344299316, "global_step": 339621, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.040170907974243, "global_step": 339622, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1114706993103027, "global_step": 339623, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.126401424407959, "global_step": 339624, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.090345859527588, "global_step": 339625, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.168442726135254, "global_step": 339626, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1139955520629883, "global_step": 339627, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.133263111114502, "global_step": 339628, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1291463375091553, "global_step": 339629, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112363576889038, "global_step": 339630, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1222782135009766, "global_step": 339631, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1833958625793457, "global_step": 339632, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075309991836548, "global_step": 339633, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08461332321167, "global_step": 339634, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1465795040130615, "global_step": 339635, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0977044105529785, "global_step": 339636, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.113374948501587, "global_step": 339637, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0566742420196533, "global_step": 339638, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0457804203033447, "global_step": 339639, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1397037506103516, "global_step": 339640, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.127213716506958, "global_step": 339641, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9994481801986694, "global_step": 339642, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1074507236480713, "global_step": 339643, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.051041841506958, "global_step": 339644, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1541450023651123, "global_step": 339645, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1868155002593994, "global_step": 339646, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1778292655944824, "global_step": 339647, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085442304611206, "global_step": 339648, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1773672103881836, "global_step": 339649, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0911970138549805, "global_step": 339650, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123375415802002, "global_step": 339651, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.985041856765747, "global_step": 339652, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.062709093093872, "global_step": 339653, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.049375057220459, "global_step": 339654, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0593929290771484, "global_step": 339655, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08833646774292, "global_step": 339656, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.037393808364868, "global_step": 339657, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1427130699157715, "global_step": 339658, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9542205333709717, "global_step": 339659, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1095657348632812, "global_step": 339660, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0701353549957275, "global_step": 339661, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.128798246383667, "global_step": 339662, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086900472640991, "global_step": 339663, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.03989577293396, "global_step": 339664, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1282262802124023, "global_step": 339665, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.065225839614868, "global_step": 339666, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.116184949874878, "global_step": 339667, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1221396923065186, "global_step": 339668, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1959381103515625, "global_step": 339669, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0802407264709473, "global_step": 339670, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.039428234100342, "global_step": 339671, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1666407585144043, "global_step": 339672, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1364102363586426, "global_step": 339673, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1027488708496094, "global_step": 339674, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1904585361480713, "global_step": 339675, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0603113174438477, "global_step": 339676, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0850565433502197, "global_step": 339677, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0118253231048584, "global_step": 339678, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0468645095825195, "global_step": 339679, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108105182647705, "global_step": 339680, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1396913528442383, "global_step": 339681, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069666624069214, "global_step": 339682, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0548391342163086, "global_step": 339683, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0926856994628906, "global_step": 339684, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1101016998291016, "global_step": 339685, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1098854541778564, "global_step": 339686, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.195342540740967, "global_step": 339687, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0765857696533203, "global_step": 339688, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0544095039367676, "global_step": 339689, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0618577003479004, "global_step": 339690, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1331350803375244, "global_step": 339691, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2007250785827637, "global_step": 339692, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.115546941757202, "global_step": 339693, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1652514934539795, "global_step": 339694, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0040533542633057, "global_step": 339695, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0555524826049805, "global_step": 339696, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.135962963104248, "global_step": 339697, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1291375160217285, "global_step": 339698, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.109875440597534, "global_step": 339699, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1260745525360107, "global_step": 339700, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0552926063537598, "global_step": 339701, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0581371784210205, "global_step": 339702, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1393635272979736, "global_step": 339703, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0367085933685303, "global_step": 339704, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0735394954681396, "global_step": 339705, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.120840549468994, "global_step": 339706, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.103759527206421, "global_step": 339707, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1482362747192383, "global_step": 339708, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119503974914551, "global_step": 339709, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108084201812744, "global_step": 339710, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0888748168945312, "global_step": 339711, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0532264709472656, "global_step": 339712, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.056657314300537, "global_step": 339713, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9539721012115479, "global_step": 339714, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.080550193786621, "global_step": 339715, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.154503107070923, "global_step": 339716, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0365490913391113, "global_step": 339717, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1013851165771484, "global_step": 339718, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123394250869751, "global_step": 339719, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0890347957611084, "global_step": 339720, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.161170244216919, "global_step": 339721, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.071666955947876, "global_step": 339722, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1011502742767334, "global_step": 339723, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.107503652572632, "global_step": 339724, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.20573353767395, "global_step": 339725, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.226564645767212, "global_step": 339726, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.074887752532959, "global_step": 339727, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.007277727127075, "global_step": 339728, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.14595103263855, "global_step": 339729, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.05436372756958, "global_step": 339730, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0414748191833496, "global_step": 339731, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1294310092926025, "global_step": 339732, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.078061819076538, "global_step": 339733, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045074224472046, "global_step": 339734, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0652389526367188, "global_step": 339735, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1400206089019775, "global_step": 339736, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.048460006713867, "global_step": 339737, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0516645908355713, "global_step": 339738, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1348416805267334, "global_step": 339739, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1476190090179443, "global_step": 339740, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.128732919692993, "global_step": 339741, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.177112102508545, "global_step": 339742, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.029831886291504, "global_step": 339743, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119201421737671, "global_step": 339744, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2050719261169434, "global_step": 339745, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123323440551758, "global_step": 339746, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1809940338134766, "global_step": 339747, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0537400245666504, "global_step": 339748, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0406336784362793, "global_step": 339749, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.064084053039551, "global_step": 339750, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1961593627929688, "global_step": 339751, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1094555854797363, "global_step": 339752, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.096160888671875, "global_step": 339753, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.114593744277954, "global_step": 339754, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1050925254821777, "global_step": 339755, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0552103519439697, "global_step": 339756, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.061445951461792, "global_step": 339757, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0769259929656982, "global_step": 339758, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.964682698249817, "global_step": 339759, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.114037036895752, "global_step": 339760, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0277740955352783, "global_step": 339761, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084421157836914, "global_step": 339762, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045527458190918, "global_step": 339763, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1280882358551025, "global_step": 339764, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1090521812438965, "global_step": 339765, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.949386477470398, "global_step": 339766, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0506415367126465, "global_step": 339767, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.05059814453125, "global_step": 339768, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1658692359924316, "global_step": 339769, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0507099628448486, "global_step": 339770, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.150812864303589, "global_step": 339771, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.103816270828247, "global_step": 339772, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1341068744659424, "global_step": 339773, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1849920749664307, "global_step": 339774, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086773633956909, "global_step": 339775, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.177161931991577, "global_step": 339776, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.059450387954712, "global_step": 339777, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134491205215454, "global_step": 339778, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0816876888275146, "global_step": 339779, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.225926399230957, "global_step": 339780, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0707504749298096, "global_step": 339781, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.019235610961914, "global_step": 339782, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.051936626434326, "global_step": 339783, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1292836666107178, "global_step": 339784, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1242074966430664, "global_step": 339785, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0419955253601074, "global_step": 339786, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.155888557434082, "global_step": 339787, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1142685413360596, "global_step": 339788, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1548960208892822, "global_step": 339789, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0906643867492676, "global_step": 339790, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0779013633728027, "global_step": 339791, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.035820722579956, "global_step": 339792, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.117429494857788, "global_step": 339793, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0905661582946777, "global_step": 339794, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1009156703948975, "global_step": 339795, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2136800289154053, "global_step": 339796, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.080683469772339, "global_step": 339797, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089569091796875, "global_step": 339798, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.077563524246216, "global_step": 339799, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1020243167877197, "global_step": 339800, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1361989974975586, "global_step": 339801, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110515832901001, "global_step": 339802, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.064332962036133, "global_step": 339803, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1622345447540283, "global_step": 339804, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0825254917144775, "global_step": 339805, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.052015542984009, "global_step": 339806, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.082759380340576, "global_step": 339807, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.176741361618042, "global_step": 339808, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.004227638244629, "global_step": 339809, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079210042953491, "global_step": 339810, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9767955541610718, "global_step": 339811, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.071810722351074, "global_step": 339812, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100615978240967, "global_step": 339813, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0431034564971924, "global_step": 339814, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1400911808013916, "global_step": 339815, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0846431255340576, "global_step": 339816, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2110769748687744, "global_step": 339817, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0813045501708984, "global_step": 339818, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0315961837768555, "global_step": 339819, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0843544006347656, "global_step": 339820, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1015241146087646, "global_step": 339821, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0163586139678955, "global_step": 339822, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1806344985961914, "global_step": 339823, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.177011728286743, "global_step": 339824, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.041210651397705, "global_step": 339825, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.172065019607544, "global_step": 339826, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119560480117798, "global_step": 339827, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.141425609588623, "global_step": 339828, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1067731380462646, "global_step": 339829, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1506118774414062, "global_step": 339830, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.058542490005493, "global_step": 339831, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1896965503692627, "global_step": 339832, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.971763253211975, "global_step": 339833, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1576833724975586, "global_step": 339834, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1335158348083496, "global_step": 339835, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1121509075164795, "global_step": 339836, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.047454357147217, "global_step": 339837, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1681008338928223, "global_step": 339838, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.021760940551758, "global_step": 339839, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.170511245727539, "global_step": 339840, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0448803901672363, "global_step": 339841, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.057368516921997, "global_step": 339842, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.97926926612854, "global_step": 339843, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0776591300964355, "global_step": 339844, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.104323148727417, "global_step": 339845, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1123454570770264, "global_step": 339846, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.143644332885742, "global_step": 339847, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0244381427764893, "global_step": 339848, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1030633449554443, "global_step": 339849, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1037237644195557, "global_step": 339850, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.038045883178711, "global_step": 339851, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1027259826660156, "global_step": 339852, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.077463150024414, "global_step": 339853, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1226797103881836, "global_step": 339854, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1236703395843506, "global_step": 339855, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1328656673431396, "global_step": 339856, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.06795072555542, "global_step": 339857, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0429112911224365, "global_step": 339858, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1575331687927246, "global_step": 339859, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0747230052948, "global_step": 339860, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072364568710327, "global_step": 339861, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.206943988800049, "global_step": 339862, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1492862701416016, "global_step": 339863, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0543289184570312, "global_step": 339864, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0044026374816895, "global_step": 339865, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1533281803131104, "global_step": 339866, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.116344928741455, "global_step": 339867, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1016407012939453, "global_step": 339868, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0699918270111084, "global_step": 339869, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076616048812866, "global_step": 339870, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0336573123931885, "global_step": 339871, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0883870124816895, "global_step": 339872, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1091220378875732, "global_step": 339873, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.145948886871338, "global_step": 339874, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1155362129211426, "global_step": 339875, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0794882774353027, "global_step": 339876, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9965758323669434, "global_step": 339877, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.136181354522705, "global_step": 339878, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.130131483078003, "global_step": 339879, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.063547372817993, "global_step": 339880, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9525277614593506, "global_step": 339881, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1193463802337646, "global_step": 339882, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1530401706695557, "global_step": 339883, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1147143840789795, "global_step": 339884, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1739516258239746, "global_step": 339885, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1329104900360107, "global_step": 339886, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.071943998336792, "global_step": 339887, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.198132276535034, "global_step": 339888, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1194894313812256, "global_step": 339889, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0883474349975586, "global_step": 339890, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0891478061676025, "global_step": 339891, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.090384006500244, "global_step": 339892, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.111269950866699, "global_step": 339893, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.13751482963562, "global_step": 339894, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0844597816467285, "global_step": 339895, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1431195735931396, "global_step": 339896, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0220091342926025, "global_step": 339897, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.078111171722412, "global_step": 339898, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1851425170898438, "global_step": 339899, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1495015621185303, "global_step": 339900, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1502315998077393, "global_step": 339901, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1020259857177734, "global_step": 339902, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.13370680809021, "global_step": 339903, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1638903617858887, "global_step": 339904, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.106828451156616, "global_step": 339905, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0672664642333984, "global_step": 339906, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0301032066345215, "global_step": 339907, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.05777907371521, "global_step": 339908, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.121047258377075, "global_step": 339909, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075551748275757, "global_step": 339910, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.115109920501709, "global_step": 339911, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9787287712097168, "global_step": 339912, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0632476806640625, "global_step": 339913, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.061438798904419, "global_step": 339914, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0677542686462402, "global_step": 339915, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.06585955619812, "global_step": 339916, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1429996490478516, "global_step": 339917, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0409858226776123, "global_step": 339918, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0616674423217773, "global_step": 339919, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.194365978240967, "global_step": 339920, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.040055513381958, "global_step": 339921, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.121504306793213, "global_step": 339922, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0738866329193115, "global_step": 339923, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.162086248397827, "global_step": 339924, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0861470699310303, "global_step": 339925, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.138474702835083, "global_step": 339926, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.103713035583496, "global_step": 339927, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.20105242729187, "global_step": 339928, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0801634788513184, "global_step": 339929, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.092489719390869, "global_step": 339930, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2027766704559326, "global_step": 339931, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1284940242767334, "global_step": 339932, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.098517417907715, "global_step": 339933, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2434234619140625, "global_step": 339934, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.080460786819458, "global_step": 339935, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0480802059173584, "global_step": 339936, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0471725463867188, "global_step": 339937, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0639724731445312, "global_step": 339938, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.116635799407959, "global_step": 339939, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.148481607437134, "global_step": 339940, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147887945175171, "global_step": 339941, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084864854812622, "global_step": 339942, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.156601667404175, "global_step": 339943, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1212308406829834, "global_step": 339944, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0358831882476807, "global_step": 339945, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119842052459717, "global_step": 339946, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.118269443511963, "global_step": 339947, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1421585083007812, "global_step": 339948, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1487679481506348, "global_step": 339949, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.150358200073242, "global_step": 339950, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.030062437057495, "global_step": 339951, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.126163959503174, "global_step": 339952, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.106907606124878, "global_step": 339953, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1450979709625244, "global_step": 339954, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1284217834472656, "global_step": 339955, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.17409348487854, "global_step": 339956, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110257387161255, "global_step": 339957, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1223185062408447, "global_step": 339958, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.144989252090454, "global_step": 339959, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1474196910858154, "global_step": 339960, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.198185682296753, "global_step": 339961, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110581159591675, "global_step": 339962, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1354782581329346, "global_step": 339963, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9857349395751953, "global_step": 339964, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9955768585205078, "global_step": 339965, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1405062675476074, "global_step": 339966, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0975499153137207, "global_step": 339967, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123946189880371, "global_step": 339968, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1151556968688965, "global_step": 339969, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.187011957168579, "global_step": 339970, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.099538564682007, "global_step": 339971, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.102384567260742, "global_step": 339972, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0460009574890137, "global_step": 339973, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1313326358795166, "global_step": 339974, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0788209438323975, "global_step": 339975, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1136345863342285, "global_step": 339976, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1680288314819336, "global_step": 339977, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.164216995239258, "global_step": 339978, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1403403282165527, "global_step": 339979, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089799642562866, "global_step": 339980, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0862045288085938, "global_step": 339981, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.168330192565918, "global_step": 339982, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2263028621673584, "global_step": 339983, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1123416423797607, "global_step": 339984, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0723416805267334, "global_step": 339985, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.023184299468994, "global_step": 339986, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.120271682739258, "global_step": 339987, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079416036605835, "global_step": 339988, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.038321018218994, "global_step": 339989, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1277964115142822, "global_step": 339990, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0726144313812256, "global_step": 339991, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0850491523742676, "global_step": 339992, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1307811737060547, "global_step": 339993, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.126723051071167, "global_step": 339994, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0384738445281982, "global_step": 339995, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.265005350112915, "global_step": 339996, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1056835651397705, "global_step": 339997, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.043860912322998, "global_step": 339998, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1481213569641113, "global_step": 339999, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1143434047698975, "global_step": 340000, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1254193782806396, "global_step": 340001, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0922553539276123, "global_step": 340002, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.109065294265747, "global_step": 340003, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0314018726348877, "global_step": 340004, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0534567832946777, "global_step": 340005, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112942934036255, "global_step": 340006, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1624155044555664, "global_step": 340007, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1053707599639893, "global_step": 340008, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.014249801635742, "global_step": 340009, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0704545974731445, "global_step": 340010, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.101776123046875, "global_step": 340011, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1483590602874756, "global_step": 340012, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108971118927002, "global_step": 340013, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1924567222595215, "global_step": 340014, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0907840728759766, "global_step": 340015, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0020813941955566, "global_step": 340016, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.142702341079712, "global_step": 340017, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1760380268096924, "global_step": 340018, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.090132474899292, "global_step": 340019, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0919601917266846, "global_step": 340020, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1117255687713623, "global_step": 340021, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0353336334228516, "global_step": 340022, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0595154762268066, "global_step": 340023, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069132089614868, "global_step": 340024, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1094560623168945, "global_step": 340025, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.061563730239868, "global_step": 340026, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.038835048675537, "global_step": 340027, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0712010860443115, "global_step": 340028, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.208530902862549, "global_step": 340029, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1225616931915283, "global_step": 340030, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.018799066543579, "global_step": 340031, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.12058424949646, "global_step": 340032, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.144874334335327, "global_step": 340033, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1101629734039307, "global_step": 340034, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.09521746635437, "global_step": 340035, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0655007362365723, "global_step": 340036, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0973424911499023, "global_step": 340037, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.197246551513672, "global_step": 340038, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0529098510742188, "global_step": 340039, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0920610427856445, "global_step": 340040, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.129932403564453, "global_step": 340041, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134321928024292, "global_step": 340042, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.077113628387451, "global_step": 340043, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0425524711608887, "global_step": 340044, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.158942937850952, "global_step": 340045, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1013314723968506, "global_step": 340046, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.095881938934326, "global_step": 340047, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0823006629943848, "global_step": 340048, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.070662498474121, "global_step": 340049, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9897531270980835, "global_step": 340050, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.994558572769165, "global_step": 340051, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1524250507354736, "global_step": 340052, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1542584896087646, "global_step": 340053, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0859897136688232, "global_step": 340054, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1071815490722656, "global_step": 340055, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0943195819854736, "global_step": 340056, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1756324768066406, "global_step": 340057, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1360039710998535, "global_step": 340058, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.102036952972412, "global_step": 340059, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0585310459136963, "global_step": 340060, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.074211597442627, "global_step": 340061, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.171161413192749, "global_step": 340062, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086587429046631, "global_step": 340063, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1691932678222656, "global_step": 340064, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.042147397994995, "global_step": 340065, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1326253414154053, "global_step": 340066, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1162497997283936, "global_step": 340067, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1664986610412598, "global_step": 340068, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2352352142333984, "global_step": 340069, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0427305698394775, "global_step": 340070, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.114179849624634, "global_step": 340071, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1170706748962402, "global_step": 340072, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1120028495788574, "global_step": 340073, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1134839057922363, "global_step": 340074, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1293399333953857, "global_step": 340075, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0697505474090576, "global_step": 340076, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.099489450454712, "global_step": 340077, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.048293113708496, "global_step": 340078, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1522929668426514, "global_step": 340079, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1342074871063232, "global_step": 340080, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1292998790740967, "global_step": 340081, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147771120071411, "global_step": 340082, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089444637298584, "global_step": 340083, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0755417346954346, "global_step": 340084, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1165051460266113, "global_step": 340085, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085533618927002, "global_step": 340086, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.162750482559204, "global_step": 340087, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1269795894622803, "global_step": 340088, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.061624526977539, "global_step": 340089, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0820515155792236, "global_step": 340090, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0781569480895996, "global_step": 340091, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.106232166290283, "global_step": 340092, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0358994007110596, "global_step": 340093, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1453049182891846, "global_step": 340094, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1478323936462402, "global_step": 340095, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0198516845703125, "global_step": 340096, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1706507205963135, "global_step": 340097, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1235616207122803, "global_step": 340098, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0893518924713135, "global_step": 340099, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1029460430145264, "global_step": 340100, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.194749355316162, "global_step": 340101, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1820497512817383, "global_step": 340102, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.087033271789551, "global_step": 340103, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.109403133392334, "global_step": 340104, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.163180112838745, "global_step": 340105, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.161194324493408, "global_step": 340106, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055253505706787, "global_step": 340107, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.082165002822876, "global_step": 340108, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0329298973083496, "global_step": 340109, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089709758758545, "global_step": 340110, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044773817062378, "global_step": 340111, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0451040267944336, "global_step": 340112, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.087928533554077, "global_step": 340113, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.103760242462158, "global_step": 340114, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.043309211730957, "global_step": 340115, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0966522693634033, "global_step": 340116, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.156020402908325, "global_step": 340117, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1951723098754883, "global_step": 340118, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1590423583984375, "global_step": 340119, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076486110687256, "global_step": 340120, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1067097187042236, "global_step": 340121, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.17934513092041, "global_step": 340122, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1072003841400146, "global_step": 340123, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0852699279785156, "global_step": 340124, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.109020233154297, "global_step": 340125, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0869922637939453, "global_step": 340126, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1619515419006348, "global_step": 340127, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0958118438720703, "global_step": 340128, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1131906509399414, "global_step": 340129, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.074291229248047, "global_step": 340130, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1093430519104004, "global_step": 340131, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1494076251983643, "global_step": 340132, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1636016368865967, "global_step": 340133, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1111459732055664, "global_step": 340134, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1697773933410645, "global_step": 340135, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1669044494628906, "global_step": 340136, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.175205707550049, "global_step": 340137, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.172481060028076, "global_step": 340138, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.066502571105957, "global_step": 340139, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0645956993103027, "global_step": 340140, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075519561767578, "global_step": 340141, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0749075412750244, "global_step": 340142, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.060703992843628, "global_step": 340143, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.198564291000366, "global_step": 340144, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0623362064361572, "global_step": 340145, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072012424468994, "global_step": 340146, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1796891689300537, "global_step": 340147, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1828298568725586, "global_step": 340148, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1304943561553955, "global_step": 340149, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.071291446685791, "global_step": 340150, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1904993057250977, "global_step": 340151, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.140336751937866, "global_step": 340152, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0856659412384033, "global_step": 340153, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.046710968017578, "global_step": 340154, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1158711910247803, "global_step": 340155, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1247401237487793, "global_step": 340156, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0655081272125244, "global_step": 340157, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1325900554656982, "global_step": 340158, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.097015857696533, "global_step": 340159, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.077993154525757, "global_step": 340160, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1472058296203613, "global_step": 340161, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.126309871673584, "global_step": 340162, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100224256515503, "global_step": 340163, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0997254848480225, "global_step": 340164, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075850248336792, "global_step": 340165, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.188002347946167, "global_step": 340166, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.149618625640869, "global_step": 340167, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1082868576049805, "global_step": 340168, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0056939125061035, "global_step": 340169, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085981845855713, "global_step": 340170, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1183173656463623, "global_step": 340171, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.039621591567993, "global_step": 340172, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.195033311843872, "global_step": 340173, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.129103422164917, "global_step": 340174, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1738317012786865, "global_step": 340175, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.01513934135437, "global_step": 340176, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2488389015197754, "global_step": 340177, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.160024642944336, "global_step": 340178, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0737802982330322, "global_step": 340179, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086731195449829, "global_step": 340180, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1006085872650146, "global_step": 340181, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0384061336517334, "global_step": 340182, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1514041423797607, "global_step": 340183, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1885859966278076, "global_step": 340184, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.187896728515625, "global_step": 340185, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0138912200927734, "global_step": 340186, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1256601810455322, "global_step": 340187, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.198260545730591, "global_step": 340188, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.176455497741699, "global_step": 340189, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1034631729125977, "global_step": 340190, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.177506446838379, "global_step": 340191, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1462597846984863, "global_step": 340192, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1586897373199463, "global_step": 340193, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0703516006469727, "global_step": 340194, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.09981107711792, "global_step": 340195, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1021170616149902, "global_step": 340196, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0971920490264893, "global_step": 340197, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108064889907837, "global_step": 340198, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0127155780792236, "global_step": 340199, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0968353748321533, "global_step": 340200, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0477709770202637, "global_step": 340201, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.200740337371826, "global_step": 340202, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.114609718322754, "global_step": 340203, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0400118827819824, "global_step": 340204, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.186535120010376, "global_step": 340205, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0985164642333984, "global_step": 340206, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0739688873291016, "global_step": 340207, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.043520927429199, "global_step": 340208, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0874416828155518, "global_step": 340209, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1384694576263428, "global_step": 340210, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1222405433654785, "global_step": 340211, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.073657989501953, "global_step": 340212, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.140693426132202, "global_step": 340213, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.161301612854004, "global_step": 340214, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1936628818511963, "global_step": 340215, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.202641248703003, "global_step": 340216, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.081395149230957, "global_step": 340217, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1671648025512695, "global_step": 340218, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.095418930053711, "global_step": 340219, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.070847511291504, "global_step": 340220, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1503779888153076, "global_step": 340221, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1582062244415283, "global_step": 340222, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0366339683532715, "global_step": 340223, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079745054244995, "global_step": 340224, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0701794624328613, "global_step": 340225, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.05342960357666, "global_step": 340226, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1880786418914795, "global_step": 340227, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.098447799682617, "global_step": 340228, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1167516708374023, "global_step": 340229, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1557936668395996, "global_step": 340230, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0788419246673584, "global_step": 340231, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1589677333831787, "global_step": 340232, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1227149963378906, "global_step": 340233, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.121647596359253, "global_step": 340234, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1585254669189453, "global_step": 340235, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2074379920959473, "global_step": 340236, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.168947458267212, "global_step": 340237, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.117112398147583, "global_step": 340238, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1747255325317383, "global_step": 340239, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0757551193237305, "global_step": 340240, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.083536386489868, "global_step": 340241, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123115062713623, "global_step": 340242, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0410444736480713, "global_step": 340243, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0512731075286865, "global_step": 340244, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0764222145080566, "global_step": 340245, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089337110519409, "global_step": 340246, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2058475017547607, "global_step": 340247, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0548739433288574, "global_step": 340248, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.14711594581604, "global_step": 340249, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.14823842048645, "global_step": 340250, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0485665798187256, "global_step": 339283, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9896458387374878, "global_step": 339284, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1306512355804443, "global_step": 339285, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9753319025039673, "global_step": 339286, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.146601676940918, "global_step": 339287, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9777568578720093, "global_step": 339288, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9712508916854858, "global_step": 339289, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.098803758621216, "global_step": 339290, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0551412105560303, "global_step": 339291, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1010289192199707, "global_step": 339292, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1259567737579346, "global_step": 339293, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.020310163497925, "global_step": 339294, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.177199602127075, "global_step": 339295, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1130659580230713, "global_step": 339296, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0552637577056885, "global_step": 339297, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0644094944000244, "global_step": 339298, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0241894721984863, "global_step": 339299, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0671935081481934, "global_step": 339300, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075198173522949, "global_step": 339301, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044772148132324, "global_step": 339302, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.036623954772949, "global_step": 339303, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0692331790924072, "global_step": 339304, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1719703674316406, "global_step": 339305, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1223843097686768, "global_step": 339306, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.027740716934204, "global_step": 339307, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0458407402038574, "global_step": 339308, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0427088737487793, "global_step": 339309, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0331408977508545, "global_step": 339310, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0796988010406494, "global_step": 339311, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08878755569458, "global_step": 339312, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0025370121002197, "global_step": 339313, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0725603103637695, "global_step": 339314, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122758388519287, "global_step": 339315, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112752914428711, "global_step": 339316, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1104633808135986, "global_step": 339317, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123229742050171, "global_step": 339318, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0178725719451904, "global_step": 339319, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0266528129577637, "global_step": 339320, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1254348754882812, "global_step": 339321, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0517990589141846, "global_step": 339322, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.060596227645874, "global_step": 339323, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.050619602203369, "global_step": 339324, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.154019832611084, "global_step": 339325, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1616809368133545, "global_step": 339326, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0878279209136963, "global_step": 339327, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045795440673828, "global_step": 339328, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0130813121795654, "global_step": 339329, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119952917098999, "global_step": 339330, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.081479549407959, "global_step": 339331, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0923409461975098, "global_step": 339332, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0692386627197266, "global_step": 339333, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147031545639038, "global_step": 339334, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0896191596984863, "global_step": 339335, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.005101442337036, "global_step": 339336, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.050035238265991, "global_step": 339337, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.197066068649292, "global_step": 339338, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.051330804824829, "global_step": 339339, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1107637882232666, "global_step": 339340, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.058177947998047, "global_step": 339341, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0813546180725098, "global_step": 339342, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108010768890381, "global_step": 339343, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1305935382843018, "global_step": 339344, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0816023349761963, "global_step": 339345, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054537773132324, "global_step": 339346, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.034611940383911, "global_step": 339347, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0216822624206543, "global_step": 339348, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.092921257019043, "global_step": 339349, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.102452039718628, "global_step": 339350, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069411039352417, "global_step": 339351, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.098616123199463, "global_step": 339352, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.078594923019409, "global_step": 339353, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1384377479553223, "global_step": 339354, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0742392539978027, "global_step": 339355, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.107682228088379, "global_step": 339356, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0384480953216553, "global_step": 339357, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0828139781951904, "global_step": 339358, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0737884044647217, "global_step": 339359, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1640284061431885, "global_step": 339360, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.006603956222534, "global_step": 339361, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084146738052368, "global_step": 339362, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.991001844406128, "global_step": 339363, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134162664413452, "global_step": 339364, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.087644338607788, "global_step": 339365, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.059250831604004, "global_step": 339366, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1218338012695312, "global_step": 339367, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0595550537109375, "global_step": 339368, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055328845977783, "global_step": 339369, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084895610809326, "global_step": 339370, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0079283714294434, "global_step": 339371, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1192355155944824, "global_step": 339372, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1503026485443115, "global_step": 339373, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0468039512634277, "global_step": 339374, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1718194484710693, "global_step": 339375, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.043174982070923, "global_step": 339376, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.025743007659912, "global_step": 339377, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147813320159912, "global_step": 339378, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.242877960205078, "global_step": 339379, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0296006202697754, "global_step": 339380, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.997869610786438, "global_step": 339381, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0848991870880127, "global_step": 339382, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9904084205627441, "global_step": 339383, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.025855779647827, "global_step": 339384, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.051657199859619, "global_step": 339385, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.098881721496582, "global_step": 339386, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.070688009262085, "global_step": 339387, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1367650032043457, "global_step": 339388, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.120727777481079, "global_step": 339389, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.129485607147217, "global_step": 339390, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.067549228668213, "global_step": 339391, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1038269996643066, "global_step": 339392, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0990216732025146, "global_step": 339393, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.07123064994812, "global_step": 339394, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0439975261688232, "global_step": 339395, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.031938314437866, "global_step": 339396, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.124903678894043, "global_step": 339397, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2306766510009766, "global_step": 339398, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2053091526031494, "global_step": 339399, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0494277477264404, "global_step": 339400, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0803751945495605, "global_step": 339401, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1778697967529297, "global_step": 339402, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.130413055419922, "global_step": 339403, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1416211128234863, "global_step": 339404, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1970551013946533, "global_step": 339405, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0560414791107178, "global_step": 339406, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1444530487060547, "global_step": 339407, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.048959970474243, "global_step": 339408, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.032095193862915, "global_step": 339409, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.071589231491089, "global_step": 339410, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0481834411621094, "global_step": 339411, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0326225757598877, "global_step": 339412, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.109119176864624, "global_step": 339413, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.146273612976074, "global_step": 339414, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10390567779541, "global_step": 339415, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0644948482513428, "global_step": 339416, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08474063873291, "global_step": 339417, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0680315494537354, "global_step": 339418, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0437941551208496, "global_step": 339419, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0639376640319824, "global_step": 339420, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0525259971618652, "global_step": 339421, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.040627956390381, "global_step": 339422, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085474967956543, "global_step": 339423, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072019577026367, "global_step": 339424, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1367154121398926, "global_step": 339425, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1577203273773193, "global_step": 339426, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089601516723633, "global_step": 339427, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.06522536277771, "global_step": 339428, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1450035572052, "global_step": 339429, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1031179428100586, "global_step": 339430, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1394710540771484, "global_step": 339431, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.11088228225708, "global_step": 339432, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0455245971679688, "global_step": 339433, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1109204292297363, "global_step": 339434, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1295058727264404, "global_step": 339435, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0551908016204834, "global_step": 339436, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1237499713897705, "global_step": 339437, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1469223499298096, "global_step": 339438, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0950942039489746, "global_step": 339439, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.184330701828003, "global_step": 339440, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0544116497039795, "global_step": 339441, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0843029022216797, "global_step": 339442, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1823959350585938, "global_step": 339443, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0034241676330566, "global_step": 339444, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.031815767288208, "global_step": 339445, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.087120771408081, "global_step": 339446, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0283234119415283, "global_step": 339447, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.03419828414917, "global_step": 339448, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134718894958496, "global_step": 339449, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.107712745666504, "global_step": 339450, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.102116584777832, "global_step": 339451, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0680878162384033, "global_step": 339452, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1234402656555176, "global_step": 339453, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.991292119026184, "global_step": 339454, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.059478282928467, "global_step": 339455, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0768046379089355, "global_step": 339456, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0336620807647705, "global_step": 339457, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.039504051208496, "global_step": 339458, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0890464782714844, "global_step": 339459, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0093135833740234, "global_step": 339460, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100799322128296, "global_step": 339461, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069654703140259, "global_step": 339462, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0244600772857666, "global_step": 339463, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1296050548553467, "global_step": 339464, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.115436315536499, "global_step": 339465, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0764541625976562, "global_step": 339466, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.083146810531616, "global_step": 339467, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1089398860931396, "global_step": 339468, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0698349475860596, "global_step": 339469, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.121417284011841, "global_step": 339470, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1152076721191406, "global_step": 339471, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0691583156585693, "global_step": 339472, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2196054458618164, "global_step": 339473, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.02197265625, "global_step": 339474, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1463701725006104, "global_step": 339475, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.148970127105713, "global_step": 339476, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.180803060531616, "global_step": 339477, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0570571422576904, "global_step": 339478, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.135819911956787, "global_step": 339479, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0465261936187744, "global_step": 339480, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1524627208709717, "global_step": 339481, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055452585220337, "global_step": 339482, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.040459156036377, "global_step": 339483, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1000969409942627, "global_step": 339484, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.019118547439575, "global_step": 339485, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.947082757949829, "global_step": 339486, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0886378288269043, "global_step": 339487, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0587658882141113, "global_step": 339488, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.034632921218872, "global_step": 339489, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.057481288909912, "global_step": 339490, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.068730592727661, "global_step": 339491, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.028764247894287, "global_step": 339492, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9578094482421875, "global_step": 339493, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.214016914367676, "global_step": 339494, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1351816654205322, "global_step": 339495, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1529715061187744, "global_step": 339496, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0871212482452393, "global_step": 339497, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.133809804916382, "global_step": 339498, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.120518922805786, "global_step": 339499, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0374324321746826, "global_step": 339500, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084465742111206, "global_step": 339501, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.062861204147339, "global_step": 339502, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1101667881011963, "global_step": 339503, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1206395626068115, "global_step": 339504, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075834035873413, "global_step": 339505, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.07973051071167, "global_step": 339506, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0827231407165527, "global_step": 339507, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0614013671875, "global_step": 339508, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1268765926361084, "global_step": 339509, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1111984252929688, "global_step": 339510, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.144256830215454, "global_step": 339511, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.156780958175659, "global_step": 339512, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0897088050842285, "global_step": 339513, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1580581665039062, "global_step": 339514, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084852933883667, "global_step": 339515, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086268424987793, "global_step": 339516, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0552310943603516, "global_step": 339517, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0750839710235596, "global_step": 339518, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0793464183807373, "global_step": 339519, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.095553159713745, "global_step": 339520, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.118307113647461, "global_step": 339521, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0236289501190186, "global_step": 339522, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.11318039894104, "global_step": 339523, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0063517093658447, "global_step": 339524, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.117347478866577, "global_step": 339525, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0718014240264893, "global_step": 339526, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1417574882507324, "global_step": 339527, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.125171661376953, "global_step": 339528, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.148524045944214, "global_step": 339529, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0734636783599854, "global_step": 339530, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.015357732772827, "global_step": 339531, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1296277046203613, "global_step": 339532, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1203482151031494, "global_step": 339533, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0751423835754395, "global_step": 339534, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1864206790924072, "global_step": 339535, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1261420249938965, "global_step": 339536, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0689797401428223, "global_step": 339537, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1505191326141357, "global_step": 339538, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0918009281158447, "global_step": 339539, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1244451999664307, "global_step": 339540, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089989185333252, "global_step": 339541, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1077816486358643, "global_step": 339542, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0632171630859375, "global_step": 339543, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075497627258301, "global_step": 339544, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0965025424957275, "global_step": 339545, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9977473020553589, "global_step": 339546, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.099965810775757, "global_step": 339547, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.020317316055298, "global_step": 339548, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.107213020324707, "global_step": 339549, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1629252433776855, "global_step": 339550, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.129657030105591, "global_step": 339551, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.057283639907837, "global_step": 339552, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0045783519744873, "global_step": 339553, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.109086513519287, "global_step": 339554, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0502028465270996, "global_step": 339555, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.05472469329834, "global_step": 339556, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.020657539367676, "global_step": 339557, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0893659591674805, "global_step": 339558, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0540213584899902, "global_step": 339559, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0500879287719727, "global_step": 339560, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0764663219451904, "global_step": 339561, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1418516635894775, "global_step": 339562, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1163649559020996, "global_step": 339563, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.125896453857422, "global_step": 339564, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1133837699890137, "global_step": 339565, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1379785537719727, "global_step": 339566, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110961675643921, "global_step": 339567, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.999484658241272, "global_step": 339568, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.133352041244507, "global_step": 339569, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1689040660858154, "global_step": 339570, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.140387773513794, "global_step": 339571, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.09844970703125, "global_step": 339572, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0893940925598145, "global_step": 339573, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1053311824798584, "global_step": 339574, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1824514865875244, "global_step": 339575, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.02339243888855, "global_step": 339576, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.095275640487671, "global_step": 339577, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9884119033813477, "global_step": 339578, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.984776258468628, "global_step": 339579, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0524353981018066, "global_step": 339580, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119025945663452, "global_step": 339581, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0625429153442383, "global_step": 339582, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1700239181518555, "global_step": 339583, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.128657579421997, "global_step": 339584, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0126147270202637, "global_step": 339585, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1355936527252197, "global_step": 339586, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0810351371765137, "global_step": 339587, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.047454833984375, "global_step": 339588, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108884811401367, "global_step": 339589, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0690948963165283, "global_step": 339590, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.12988018989563, "global_step": 339591, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076801061630249, "global_step": 339592, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1172988414764404, "global_step": 339593, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.051248550415039, "global_step": 339594, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0150837898254395, "global_step": 339595, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.053011178970337, "global_step": 339596, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1111345291137695, "global_step": 339597, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0823395252227783, "global_step": 339598, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.034916877746582, "global_step": 339599, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.098917245864868, "global_step": 339600, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.148355007171631, "global_step": 339601, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1503453254699707, "global_step": 339602, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0758256912231445, "global_step": 339603, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1438961029052734, "global_step": 339604, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.034142017364502, "global_step": 339605, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1025588512420654, "global_step": 339606, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.068620204925537, "global_step": 339607, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.068183183670044, "global_step": 339608, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.093909502029419, "global_step": 339609, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1060802936553955, "global_step": 339610, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.031770706176758, "global_step": 339611, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0668179988861084, "global_step": 339612, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0833261013031006, "global_step": 339613, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.061095714569092, "global_step": 339614, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0563950538635254, "global_step": 339615, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0970678329467773, "global_step": 339616, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1251847743988037, "global_step": 339617, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0181849002838135, "global_step": 339618, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044828176498413, "global_step": 339619, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100198984146118, "global_step": 339620, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.099397659301758, "global_step": 339621, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.03902530670166, "global_step": 339622, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1130194664001465, "global_step": 339623, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.124506950378418, "global_step": 339624, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0902371406555176, "global_step": 339625, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1678049564361572, "global_step": 339626, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1161046028137207, "global_step": 339627, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.133786916732788, "global_step": 339628, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.129605770111084, "global_step": 339629, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1109697818756104, "global_step": 339630, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1230251789093018, "global_step": 339631, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1845993995666504, "global_step": 339632, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075268268585205, "global_step": 339633, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085113525390625, "global_step": 339634, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1473140716552734, "global_step": 339635, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0976645946502686, "global_step": 339636, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1131656169891357, "global_step": 339637, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0568859577178955, "global_step": 339638, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.04662823677063, "global_step": 339639, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.140733003616333, "global_step": 339640, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1281046867370605, "global_step": 339641, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9987863302230835, "global_step": 339642, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108503580093384, "global_step": 339643, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.052192211151123, "global_step": 339644, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.153777599334717, "global_step": 339645, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.187645196914673, "global_step": 339646, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1767237186431885, "global_step": 339647, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0856597423553467, "global_step": 339648, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1792750358581543, "global_step": 339649, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0922820568084717, "global_step": 339650, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.125236749649048, "global_step": 339651, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9857841730117798, "global_step": 339652, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0624496936798096, "global_step": 339653, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0484602451324463, "global_step": 339654, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0598857402801514, "global_step": 339655, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.088911294937134, "global_step": 339656, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0373806953430176, "global_step": 339657, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.141651153564453, "global_step": 339658, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9532274007797241, "global_step": 339659, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1080727577209473, "global_step": 339660, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0714643001556396, "global_step": 339661, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.127490282058716, "global_step": 339662, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0851566791534424, "global_step": 339663, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.039112091064453, "global_step": 339664, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1265945434570312, "global_step": 339665, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0655570030212402, "global_step": 339666, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.115121841430664, "global_step": 339667, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1212923526763916, "global_step": 339668, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.197720527648926, "global_step": 339669, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.081055164337158, "global_step": 339670, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0394248962402344, "global_step": 339671, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1660244464874268, "global_step": 339672, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1367034912109375, "global_step": 339673, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1034722328186035, "global_step": 339674, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1892576217651367, "global_step": 339675, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.060114860534668, "global_step": 339676, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.083907127380371, "global_step": 339677, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0118021965026855, "global_step": 339678, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044445514678955, "global_step": 339679, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.107038974761963, "global_step": 339680, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.139747381210327, "global_step": 339681, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0689008235931396, "global_step": 339682, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0532586574554443, "global_step": 339683, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.092616558074951, "global_step": 339684, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1099212169647217, "global_step": 339685, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1085352897644043, "global_step": 339686, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1943471431732178, "global_step": 339687, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0776724815368652, "global_step": 339688, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.05656361579895, "global_step": 339689, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0609521865844727, "global_step": 339690, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1344549655914307, "global_step": 339691, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1999871730804443, "global_step": 339692, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1159088611602783, "global_step": 339693, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1667933464050293, "global_step": 339694, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.007155656814575, "global_step": 339695, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055121660232544, "global_step": 339696, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1375248432159424, "global_step": 339697, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1285412311553955, "global_step": 339698, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1122119426727295, "global_step": 339699, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.128927707672119, "global_step": 339700, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0568625926971436, "global_step": 339701, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0602965354919434, "global_step": 339702, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1421499252319336, "global_step": 339703, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0389113426208496, "global_step": 339704, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0718331336975098, "global_step": 339705, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122478485107422, "global_step": 339706, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.104069471359253, "global_step": 339707, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1505937576293945, "global_step": 339708, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.117828369140625, "global_step": 339709, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1080739498138428, "global_step": 339710, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0889437198638916, "global_step": 339711, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0519063472747803, "global_step": 339712, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0558888912200928, "global_step": 339713, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9533747434616089, "global_step": 339714, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0778889656066895, "global_step": 339715, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.155315637588501, "global_step": 339716, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.036059856414795, "global_step": 339717, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1022980213165283, "global_step": 339718, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.124948024749756, "global_step": 339719, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0885679721832275, "global_step": 339720, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.161891222000122, "global_step": 339721, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0714592933654785, "global_step": 339722, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10139799118042, "global_step": 339723, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.107780694961548, "global_step": 339724, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.205376148223877, "global_step": 339725, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.227297782897949, "global_step": 339726, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0730183124542236, "global_step": 339727, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0081589221954346, "global_step": 339728, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1451380252838135, "global_step": 339729, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055471420288086, "global_step": 339730, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0421359539031982, "global_step": 339731, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.13023042678833, "global_step": 339732, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.077303409576416, "global_step": 339733, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.046342372894287, "global_step": 339734, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0647482872009277, "global_step": 339735, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.141115188598633, "global_step": 339736, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.048959732055664, "global_step": 339737, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0497782230377197, "global_step": 339738, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.136558771133423, "global_step": 339739, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1478261947631836, "global_step": 339740, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1282732486724854, "global_step": 339741, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1787195205688477, "global_step": 339742, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0294363498687744, "global_step": 339743, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.118967294692993, "global_step": 339744, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2048423290252686, "global_step": 339745, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.124234437942505, "global_step": 339746, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1823172569274902, "global_step": 339747, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054257869720459, "global_step": 339748, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0401506423950195, "global_step": 339749, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0636861324310303, "global_step": 339750, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.196560859680176, "global_step": 339751, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1102492809295654, "global_step": 339752, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.09812593460083, "global_step": 339753, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1159143447875977, "global_step": 339754, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.104175567626953, "global_step": 339755, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0563743114471436, "global_step": 339756, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0613903999328613, "global_step": 339757, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0779542922973633, "global_step": 339758, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9644707441329956, "global_step": 339759, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1135120391845703, "global_step": 339760, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0287864208221436, "global_step": 339761, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.082446575164795, "global_step": 339762, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044560670852661, "global_step": 339763, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1305480003356934, "global_step": 339764, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1102042198181152, "global_step": 339765, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9478039741516113, "global_step": 339766, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.048921823501587, "global_step": 339767, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.050478458404541, "global_step": 339768, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.165152072906494, "global_step": 339769, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.050208330154419, "global_step": 339770, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.148362398147583, "global_step": 339771, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1015539169311523, "global_step": 339772, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.133319139480591, "global_step": 339773, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1829869747161865, "global_step": 339774, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086226463317871, "global_step": 339775, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1774911880493164, "global_step": 339776, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0603818893432617, "global_step": 339777, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134114980697632, "global_step": 339778, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.082029342651367, "global_step": 339779, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2250423431396484, "global_step": 339780, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0678274631500244, "global_step": 339781, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0195701122283936, "global_step": 339782, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0511226654052734, "global_step": 339783, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1271731853485107, "global_step": 339784, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1239662170410156, "global_step": 339785, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0410094261169434, "global_step": 339786, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1552436351776123, "global_step": 339787, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.116942882537842, "global_step": 339788, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.157374858856201, "global_step": 339789, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0892467498779297, "global_step": 339790, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.07598876953125, "global_step": 339791, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.036534547805786, "global_step": 339792, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.117009401321411, "global_step": 339793, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0916554927825928, "global_step": 339794, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1015028953552246, "global_step": 339795, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2121593952178955, "global_step": 339796, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0795340538024902, "global_step": 339797, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.091296672821045, "global_step": 339798, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.07688307762146, "global_step": 339799, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10239577293396, "global_step": 339800, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.136949300765991, "global_step": 339801, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1101267337799072, "global_step": 339802, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.065208911895752, "global_step": 339803, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1627070903778076, "global_step": 339804, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.083709716796875, "global_step": 339805, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0513265132904053, "global_step": 339806, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084045171737671, "global_step": 339807, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1793863773345947, "global_step": 339808, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.005387544631958, "global_step": 339809, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.080155372619629, "global_step": 339810, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9775416851043701, "global_step": 339811, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072458505630493, "global_step": 339812, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100231647491455, "global_step": 339813, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.043626546859741, "global_step": 339814, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.139643907546997, "global_step": 339815, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.083314895629883, "global_step": 339816, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2112739086151123, "global_step": 339817, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0817790031433105, "global_step": 339818, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0322136878967285, "global_step": 339819, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.083137035369873, "global_step": 339820, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1016788482666016, "global_step": 339821, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.016854763031006, "global_step": 339822, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.182049512863159, "global_step": 339823, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1783499717712402, "global_step": 339824, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0434153079986572, "global_step": 339825, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.173107147216797, "global_step": 339826, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1178171634674072, "global_step": 339827, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1412243843078613, "global_step": 339828, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1065900325775146, "global_step": 339829, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.151500940322876, "global_step": 339830, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.058636426925659, "global_step": 339831, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.189467668533325, "global_step": 339832, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.972243070602417, "global_step": 339833, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1583635807037354, "global_step": 339834, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.133455276489258, "global_step": 339835, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1111385822296143, "global_step": 339836, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0481719970703125, "global_step": 339837, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1669187545776367, "global_step": 339838, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0233426094055176, "global_step": 339839, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.171757936477661, "global_step": 339840, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.046027660369873, "global_step": 339841, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.05816650390625, "global_step": 339842, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9788888692855835, "global_step": 339843, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079594373703003, "global_step": 339844, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.105572462081909, "global_step": 339845, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1140642166137695, "global_step": 339846, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147190570831299, "global_step": 339847, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.023517370223999, "global_step": 339848, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1041603088378906, "global_step": 339849, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.101320743560791, "global_step": 339850, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.039161205291748, "global_step": 339851, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1016342639923096, "global_step": 339852, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0772972106933594, "global_step": 339853, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123621702194214, "global_step": 339854, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1235849857330322, "global_step": 339855, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1323320865631104, "global_step": 339856, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.067194938659668, "global_step": 339857, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0424580574035645, "global_step": 339858, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1609084606170654, "global_step": 339859, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0731189250946045, "global_step": 339860, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.073582887649536, "global_step": 339861, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2058262825012207, "global_step": 339862, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.149177074432373, "global_step": 339863, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.056081533432007, "global_step": 339864, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0046579837799072, "global_step": 339865, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1536452770233154, "global_step": 339866, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.118058204650879, "global_step": 339867, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10187029838562, "global_step": 339868, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069443941116333, "global_step": 339869, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076625347137451, "global_step": 339870, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0321640968322754, "global_step": 339871, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0911927223205566, "global_step": 339872, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.109804630279541, "global_step": 339873, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1469223499298096, "global_step": 339874, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.115246057510376, "global_step": 339875, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.080317258834839, "global_step": 339876, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9978890419006348, "global_step": 339877, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.136453866958618, "global_step": 339878, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.129441499710083, "global_step": 339879, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0636487007141113, "global_step": 339880, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9522545337677002, "global_step": 339881, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.120405435562134, "global_step": 339882, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1523029804229736, "global_step": 339883, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1136462688446045, "global_step": 339884, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.173215627670288, "global_step": 339885, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1319777965545654, "global_step": 339886, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.07035756111145, "global_step": 339887, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.197643518447876, "global_step": 339888, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.117720365524292, "global_step": 339889, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086507558822632, "global_step": 339890, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0901854038238525, "global_step": 339891, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0912258625030518, "global_step": 339892, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.11222243309021, "global_step": 339893, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1363606452941895, "global_step": 339894, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084613800048828, "global_step": 339895, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1436257362365723, "global_step": 339896, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.02323055267334, "global_step": 339897, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079785108566284, "global_step": 339898, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1874349117279053, "global_step": 339899, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147475004196167, "global_step": 339900, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.152583360671997, "global_step": 339901, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1023550033569336, "global_step": 339902, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1348392963409424, "global_step": 339903, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1642932891845703, "global_step": 339904, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1062984466552734, "global_step": 339905, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0657949447631836, "global_step": 339906, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0280609130859375, "global_step": 339907, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.058095693588257, "global_step": 339908, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1216843128204346, "global_step": 339909, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0769035816192627, "global_step": 339910, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.113340377807617, "global_step": 339911, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9790960550308228, "global_step": 339912, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.06428599357605, "global_step": 339913, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0623574256896973, "global_step": 339914, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0654945373535156, "global_step": 339915, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.064512014389038, "global_step": 339916, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1435399055480957, "global_step": 339917, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0402021408081055, "global_step": 339918, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0619237422943115, "global_step": 339919, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1935386657714844, "global_step": 339920, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0404229164123535, "global_step": 339921, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1226043701171875, "global_step": 339922, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.07353138923645, "global_step": 339923, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.159386396408081, "global_step": 339924, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0836410522460938, "global_step": 339925, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1392712593078613, "global_step": 339926, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1045572757720947, "global_step": 339927, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.199761390686035, "global_step": 339928, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079188108444214, "global_step": 339929, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0919604301452637, "global_step": 339930, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2024898529052734, "global_step": 339931, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.130228281021118, "global_step": 339932, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.096007823944092, "global_step": 339933, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.240600824356079, "global_step": 339934, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.080490827560425, "global_step": 339935, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0487961769104004, "global_step": 339936, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0468714237213135, "global_step": 339937, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.061655282974243, "global_step": 339938, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.116969585418701, "global_step": 339939, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147278070449829, "global_step": 339940, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.143256425857544, "global_step": 339941, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.083740234375, "global_step": 339942, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1551389694213867, "global_step": 339943, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1209139823913574, "global_step": 339944, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.035144090652466, "global_step": 339945, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119983673095703, "global_step": 339946, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1185858249664307, "global_step": 339947, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1424949169158936, "global_step": 339948, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.149749994277954, "global_step": 339949, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.149225950241089, "global_step": 339950, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.029738664627075, "global_step": 339951, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1242775917053223, "global_step": 339952, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1065945625305176, "global_step": 339953, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.143549919128418, "global_step": 339954, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1290855407714844, "global_step": 339955, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.173218011856079, "global_step": 339956, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110959529876709, "global_step": 339957, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.121741771697998, "global_step": 339958, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.14591908454895, "global_step": 339959, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1483592987060547, "global_step": 339960, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1993167400360107, "global_step": 339961, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1125950813293457, "global_step": 339962, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1342766284942627, "global_step": 339963, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9855455160140991, "global_step": 339964, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9978275299072266, "global_step": 339965, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.138245105743408, "global_step": 339966, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.096876382827759, "global_step": 339967, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1232569217681885, "global_step": 339968, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1165785789489746, "global_step": 339969, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1863763332366943, "global_step": 339970, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1016769409179688, "global_step": 339971, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1018524169921875, "global_step": 339972, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0467288494110107, "global_step": 339973, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.130396842956543, "global_step": 339974, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0768356323242188, "global_step": 339975, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.111901044845581, "global_step": 339976, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.16709566116333, "global_step": 339977, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.165217638015747, "global_step": 339978, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.139465808868408, "global_step": 339979, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0912530422210693, "global_step": 339980, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08535099029541, "global_step": 339981, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1686580181121826, "global_step": 339982, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2240748405456543, "global_step": 339983, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.111900806427002, "global_step": 339984, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0707690715789795, "global_step": 339985, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.024196147918701, "global_step": 339986, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1216540336608887, "global_step": 339987, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0789737701416016, "global_step": 339988, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.040886640548706, "global_step": 339989, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.127108335494995, "global_step": 339990, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.073514223098755, "global_step": 339991, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.087916374206543, "global_step": 339992, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.130434989929199, "global_step": 339993, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1271965503692627, "global_step": 339994, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0383493900299072, "global_step": 339995, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.263842821121216, "global_step": 339996, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.105311870574951, "global_step": 339997, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.04301381111145, "global_step": 339998, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.148499011993408, "global_step": 339999, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1136412620544434, "global_step": 340000, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123673439025879, "global_step": 340001, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0923409461975098, "global_step": 340002, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1078717708587646, "global_step": 340003, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.033092498779297, "global_step": 340004, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.052866220474243, "global_step": 340005, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1097617149353027, "global_step": 340006, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.162271022796631, "global_step": 340007, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1037545204162598, "global_step": 340008, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0153608322143555, "global_step": 340009, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0693459510803223, "global_step": 340010, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1014797687530518, "global_step": 340011, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.148409128189087, "global_step": 340012, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108074426651001, "global_step": 340013, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.192422866821289, "global_step": 340014, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.091506242752075, "global_step": 340015, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.002056360244751, "global_step": 340016, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.145049571990967, "global_step": 340017, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1764509677886963, "global_step": 340018, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0902388095855713, "global_step": 340019, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0911405086517334, "global_step": 340020, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.111733913421631, "global_step": 340021, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.037126302719116, "global_step": 340022, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.059542179107666, "global_step": 340023, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069180488586426, "global_step": 340024, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1105716228485107, "global_step": 340025, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0632638931274414, "global_step": 340026, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0373599529266357, "global_step": 340027, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072305917739868, "global_step": 340028, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.210211753845215, "global_step": 340029, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122127056121826, "global_step": 340030, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0209131240844727, "global_step": 340031, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.120697259902954, "global_step": 340032, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1447513103485107, "global_step": 340033, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1092171669006348, "global_step": 340034, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0954365730285645, "global_step": 340035, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0649056434631348, "global_step": 340036, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0974040031433105, "global_step": 340037, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1985678672790527, "global_step": 340038, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.053532361984253, "global_step": 340039, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0927622318267822, "global_step": 340040, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.128488779067993, "global_step": 340041, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.132554531097412, "global_step": 340042, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.077955484390259, "global_step": 340043, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.041044235229492, "global_step": 340044, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.159623861312866, "global_step": 340045, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1011838912963867, "global_step": 340046, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0943775177001953, "global_step": 340047, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084582567214966, "global_step": 340048, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.073406219482422, "global_step": 340049, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9893462657928467, "global_step": 340050, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9939796924591064, "global_step": 340051, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.150172472000122, "global_step": 340052, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.153444766998291, "global_step": 340053, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0874083042144775, "global_step": 340054, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.106651544570923, "global_step": 340055, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.096437931060791, "global_step": 340056, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.17631196975708, "global_step": 340057, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1332969665527344, "global_step": 340058, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.102468967437744, "global_step": 340059, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.057985544204712, "global_step": 340060, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0749857425689697, "global_step": 340061, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.169987440109253, "global_step": 340062, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08770751953125, "global_step": 340063, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.170194149017334, "global_step": 340064, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0419836044311523, "global_step": 340065, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.133680582046509, "global_step": 340066, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1188924312591553, "global_step": 340067, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1701016426086426, "global_step": 340068, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2342588901519775, "global_step": 340069, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0415539741516113, "global_step": 340070, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.113999605178833, "global_step": 340071, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.120121955871582, "global_step": 340072, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1137256622314453, "global_step": 340073, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.113953113555908, "global_step": 340074, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1318483352661133, "global_step": 340075, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0698935985565186, "global_step": 340076, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0995771884918213, "global_step": 340077, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0466911792755127, "global_step": 340078, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1498632431030273, "global_step": 340079, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1332006454467773, "global_step": 340080, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.128091812133789, "global_step": 340081, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.145782709121704, "global_step": 340082, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0876402854919434, "global_step": 340083, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0752642154693604, "global_step": 340084, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1165239810943604, "global_step": 340085, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08530592918396, "global_step": 340086, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1630091667175293, "global_step": 340087, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1268367767333984, "global_step": 340088, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.060593366622925, "global_step": 340089, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0798916816711426, "global_step": 340090, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079521417617798, "global_step": 340091, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.106083631515503, "global_step": 340092, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.036555767059326, "global_step": 340093, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.145564556121826, "global_step": 340094, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1486055850982666, "global_step": 340095, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.020448923110962, "global_step": 340096, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1724772453308105, "global_step": 340097, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.124009132385254, "global_step": 340098, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.092193603515625, "global_step": 340099, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.103393793106079, "global_step": 340100, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.193408966064453, "global_step": 340101, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1807870864868164, "global_step": 340102, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0836503505706787, "global_step": 340103, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1089224815368652, "global_step": 340104, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.162277936935425, "global_step": 340105, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.161468982696533, "global_step": 340106, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.053483724594116, "global_step": 340107, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0826494693756104, "global_step": 340108, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.032166004180908, "global_step": 340109, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0908398628234863, "global_step": 340110, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0446560382843018, "global_step": 340111, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.046006441116333, "global_step": 340112, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0865492820739746, "global_step": 340113, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1051604747772217, "global_step": 340114, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.042161226272583, "global_step": 340115, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.097227096557617, "global_step": 340116, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.15515398979187, "global_step": 340117, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.193998098373413, "global_step": 340118, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.159137725830078, "global_step": 340119, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0779244899749756, "global_step": 340120, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1070668697357178, "global_step": 340121, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.18039608001709, "global_step": 340122, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.107670545578003, "global_step": 340123, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0848548412323, "global_step": 340124, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1071643829345703, "global_step": 340125, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0876517295837402, "global_step": 340126, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1606273651123047, "global_step": 340127, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0948445796966553, "global_step": 340128, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1122426986694336, "global_step": 340129, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0734031200408936, "global_step": 340130, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108686685562134, "global_step": 340131, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1511263847351074, "global_step": 340132, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.163729667663574, "global_step": 340133, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110948324203491, "global_step": 340134, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1681761741638184, "global_step": 340135, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.166571855545044, "global_step": 340136, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1755924224853516, "global_step": 340137, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.175281524658203, "global_step": 340138, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0684328079223633, "global_step": 340139, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.065507173538208, "global_step": 340140, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0739588737487793, "global_step": 340141, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075709581375122, "global_step": 340142, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.062098264694214, "global_step": 340143, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1962199211120605, "global_step": 340144, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.061771869659424, "global_step": 340145, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0722086429595947, "global_step": 340146, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1775524616241455, "global_step": 340147, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1814727783203125, "global_step": 340148, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.131213426589966, "global_step": 340149, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0695109367370605, "global_step": 340150, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.189725875854492, "global_step": 340151, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1394948959350586, "global_step": 340152, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0858635902404785, "global_step": 340153, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0441391468048096, "global_step": 340154, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1152687072753906, "global_step": 340155, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1231772899627686, "global_step": 340156, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0644567012786865, "global_step": 340157, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1322848796844482, "global_step": 340158, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.098233222961426, "global_step": 340159, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0791749954223633, "global_step": 340160, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.148446559906006, "global_step": 340161, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1274149417877197, "global_step": 340162, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100663900375366, "global_step": 340163, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1022636890411377, "global_step": 340164, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0741708278656006, "global_step": 340165, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.188251495361328, "global_step": 340166, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1481802463531494, "global_step": 340167, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10925555229187, "global_step": 340168, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.006413221359253, "global_step": 340169, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084886312484741, "global_step": 340170, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.116380453109741, "global_step": 340171, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.035519599914551, "global_step": 340172, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.198289632797241, "global_step": 340173, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.131129503250122, "global_step": 340174, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.173910617828369, "global_step": 340175, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0138916969299316, "global_step": 340176, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.248364210128784, "global_step": 340177, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1619269847869873, "global_step": 340178, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.073383331298828, "global_step": 340179, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0865509510040283, "global_step": 340180, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100882053375244, "global_step": 340181, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.039222240447998, "global_step": 340182, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1522228717803955, "global_step": 340183, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1869213581085205, "global_step": 340184, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1907455921173096, "global_step": 340185, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.014028787612915, "global_step": 340186, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1277315616607666, "global_step": 340187, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.198967933654785, "global_step": 340188, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1752820014953613, "global_step": 340189, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1041078567504883, "global_step": 340190, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1761016845703125, "global_step": 340191, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1463894844055176, "global_step": 340192, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1577727794647217, "global_step": 340193, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.071084499359131, "global_step": 340194, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.098989963531494, "global_step": 340195, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.103238821029663, "global_step": 340196, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0975024700164795, "global_step": 340197, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1048574447631836, "global_step": 340198, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0113534927368164, "global_step": 340199, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.098823070526123, "global_step": 340200, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.046548843383789, "global_step": 340201, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2005577087402344, "global_step": 340202, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.11374831199646, "global_step": 340203, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0406341552734375, "global_step": 340204, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.186103343963623, "global_step": 340205, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.09724497795105, "global_step": 340206, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.074587106704712, "global_step": 340207, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045086145401001, "global_step": 340208, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086994171142578, "global_step": 340209, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1382739543914795, "global_step": 340210, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122830390930176, "global_step": 340211, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0729379653930664, "global_step": 340212, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1397345066070557, "global_step": 340213, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.160548448562622, "global_step": 340214, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1927506923675537, "global_step": 340215, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2011733055114746, "global_step": 340216, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0811877250671387, "global_step": 340217, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1706759929656982, "global_step": 340218, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.09519362449646, "global_step": 340219, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0682826042175293, "global_step": 340220, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.149864673614502, "global_step": 340221, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1541342735290527, "global_step": 340222, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.036576747894287, "global_step": 340223, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.07893443107605, "global_step": 340224, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.073111057281494, "global_step": 340225, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0512640476226807, "global_step": 340226, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.185959577560425, "global_step": 340227, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0973610877990723, "global_step": 340228, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1162264347076416, "global_step": 340229, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1563873291015625, "global_step": 340230, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0808780193328857, "global_step": 340231, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1581554412841797, "global_step": 340232, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1206769943237305, "global_step": 340233, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1196017265319824, "global_step": 340234, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1559176445007324, "global_step": 340235, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2064008712768555, "global_step": 340236, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.16378116607666, "global_step": 340237, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.113515853881836, "global_step": 340238, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1733038425445557, "global_step": 340239, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0726122856140137, "global_step": 340240, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.080347776412964, "global_step": 340241, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.124159097671509, "global_step": 340242, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0404224395751953, "global_step": 340243, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.053557872772217, "global_step": 340244, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0761191844940186, "global_step": 340245, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0899455547332764, "global_step": 340246, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.202810049057007, "global_step": 340247, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0546963214874268, "global_step": 340248, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1481146812438965, "global_step": 340249, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1482484340667725, "global_step": 340250, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0485665798187256, "global_step": 339283, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9896456003189087, "global_step": 339284, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1306514739990234, "global_step": 339285, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.975332498550415, "global_step": 339286, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1465985774993896, "global_step": 339287, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.977763056755066, "global_step": 339288, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9712311029434204, "global_step": 339289, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.098808526992798, "global_step": 339290, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055140256881714, "global_step": 339291, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10103702545166, "global_step": 339292, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1259829998016357, "global_step": 339293, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.020280361175537, "global_step": 339294, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.177151679992676, "global_step": 339295, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1130599975585938, "global_step": 339296, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0553033351898193, "global_step": 339297, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0643198490142822, "global_step": 339298, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.024282693862915, "global_step": 339299, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0672993659973145, "global_step": 339300, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075199604034424, "global_step": 339301, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044785976409912, "global_step": 339302, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0368263721466064, "global_step": 339303, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0693111419677734, "global_step": 339304, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1720690727233887, "global_step": 339305, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122357130050659, "global_step": 339306, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.027878999710083, "global_step": 339307, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045809745788574, "global_step": 339308, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0429046154022217, "global_step": 339309, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.03295636177063, "global_step": 339310, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0795681476593018, "global_step": 339311, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0889194011688232, "global_step": 339312, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.002389430999756, "global_step": 339313, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072662830352783, "global_step": 339314, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1226518154144287, "global_step": 339315, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112358331680298, "global_step": 339316, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1103579998016357, "global_step": 339317, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1230597496032715, "global_step": 339318, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.017810106277466, "global_step": 339319, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0264737606048584, "global_step": 339320, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.125293016433716, "global_step": 339321, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.051795721054077, "global_step": 339322, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.060809850692749, "global_step": 339323, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0508294105529785, "global_step": 339324, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1539931297302246, "global_step": 339325, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1617162227630615, "global_step": 339326, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0876779556274414, "global_step": 339327, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045722723007202, "global_step": 339328, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0129005908966064, "global_step": 339329, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119831085205078, "global_step": 339330, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0811429023742676, "global_step": 339331, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0922799110412598, "global_step": 339332, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0692665576934814, "global_step": 339333, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147341728210449, "global_step": 339334, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089986562728882, "global_step": 339335, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0046634674072266, "global_step": 339336, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.050037145614624, "global_step": 339337, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1975224018096924, "global_step": 339338, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0514183044433594, "global_step": 339339, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1104698181152344, "global_step": 339340, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.058363437652588, "global_step": 339341, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0820741653442383, "global_step": 339342, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108121156692505, "global_step": 339343, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.131223678588867, "global_step": 339344, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.081234931945801, "global_step": 339345, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0547165870666504, "global_step": 339346, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.034323215484619, "global_step": 339347, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.021878957748413, "global_step": 339348, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0930209159851074, "global_step": 339349, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1021244525909424, "global_step": 339350, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0692310333251953, "global_step": 339351, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.099386692047119, "global_step": 339352, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0788111686706543, "global_step": 339353, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1385486125946045, "global_step": 339354, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0747334957122803, "global_step": 339355, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.107851505279541, "global_step": 339356, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.038248062133789, "global_step": 339357, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0828664302825928, "global_step": 339358, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0734803676605225, "global_step": 339359, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1646296977996826, "global_step": 339360, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0063555240631104, "global_step": 339361, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0842552185058594, "global_step": 339362, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9911112785339355, "global_step": 339363, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134636163711548, "global_step": 339364, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.087768077850342, "global_step": 339365, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.058950424194336, "global_step": 339366, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1210968494415283, "global_step": 339367, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0595884323120117, "global_step": 339368, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055962324142456, "global_step": 339369, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0844485759735107, "global_step": 339370, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.007312536239624, "global_step": 339371, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1194076538085938, "global_step": 339372, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.149644374847412, "global_step": 339373, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045955181121826, "global_step": 339374, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.170922040939331, "global_step": 339375, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.043221950531006, "global_step": 339376, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0256237983703613, "global_step": 339377, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147061586380005, "global_step": 339378, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2428112030029297, "global_step": 339379, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.02901554107666, "global_step": 339380, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.997952938079834, "global_step": 339381, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0848753452301025, "global_step": 339382, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9895071983337402, "global_step": 339383, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0263121128082275, "global_step": 339384, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0519540309906006, "global_step": 339385, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0985138416290283, "global_step": 339386, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.071382761001587, "global_step": 339387, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1376235485076904, "global_step": 339388, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1210081577301025, "global_step": 339389, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1291568279266357, "global_step": 339390, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.06758451461792, "global_step": 339391, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1050238609313965, "global_step": 339392, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.099146604537964, "global_step": 339393, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0722270011901855, "global_step": 339394, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0439798831939697, "global_step": 339395, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0313587188720703, "global_step": 339396, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1249215602874756, "global_step": 339397, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.231457471847534, "global_step": 339398, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2040698528289795, "global_step": 339399, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.04939866065979, "global_step": 339400, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0797431468963623, "global_step": 339401, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.178959608078003, "global_step": 339402, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.131389617919922, "global_step": 339403, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1422414779663086, "global_step": 339404, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.196613073348999, "global_step": 339405, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055516481399536, "global_step": 339406, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1444289684295654, "global_step": 339407, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.04830265045166, "global_step": 339408, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0313222408294678, "global_step": 339409, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0704822540283203, "global_step": 339410, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0472428798675537, "global_step": 339411, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0336811542510986, "global_step": 339412, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.106459856033325, "global_step": 339413, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.14689564704895, "global_step": 339414, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.103304147720337, "global_step": 339415, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0655429363250732, "global_step": 339416, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085156202316284, "global_step": 339417, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.068990468978882, "global_step": 339418, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044498920440674, "global_step": 339419, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.064758539199829, "global_step": 339420, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0533432960510254, "global_step": 339421, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0410315990448, "global_step": 339422, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0853655338287354, "global_step": 339423, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072251796722412, "global_step": 339424, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.137279510498047, "global_step": 339425, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1573760509490967, "global_step": 339426, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0883853435516357, "global_step": 339427, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0646770000457764, "global_step": 339428, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1441266536712646, "global_step": 339429, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.103071928024292, "global_step": 339430, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.13979172706604, "global_step": 339431, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110126256942749, "global_step": 339432, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045780658721924, "global_step": 339433, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1111643314361572, "global_step": 339434, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.130310535430908, "global_step": 339435, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.056154251098633, "global_step": 339436, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122962713241577, "global_step": 339437, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1476492881774902, "global_step": 339438, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0957279205322266, "global_step": 339439, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1836647987365723, "global_step": 339440, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0541367530822754, "global_step": 339441, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0849266052246094, "global_step": 339442, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1817774772644043, "global_step": 339443, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.002220869064331, "global_step": 339444, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.032344341278076, "global_step": 339445, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086718797683716, "global_step": 339446, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0283381938934326, "global_step": 339447, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.03298020362854, "global_step": 339448, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1346049308776855, "global_step": 339449, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1080570220947266, "global_step": 339450, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1013011932373047, "global_step": 339451, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0668938159942627, "global_step": 339452, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1233227252960205, "global_step": 339453, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9908486604690552, "global_step": 339454, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.058551549911499, "global_step": 339455, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0771679878234863, "global_step": 339456, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0329689979553223, "global_step": 339457, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.039598226547241, "global_step": 339458, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0891246795654297, "global_step": 339459, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.008188247680664, "global_step": 339460, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1000194549560547, "global_step": 339461, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069397211074829, "global_step": 339462, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.024141311645508, "global_step": 339463, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1300227642059326, "global_step": 339464, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.115736961364746, "global_step": 339465, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0785105228424072, "global_step": 339466, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085075855255127, "global_step": 339467, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1080706119537354, "global_step": 339468, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069859027862549, "global_step": 339469, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.12198543548584, "global_step": 339470, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1148626804351807, "global_step": 339471, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0699825286865234, "global_step": 339472, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2190213203430176, "global_step": 339473, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0220937728881836, "global_step": 339474, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1467061042785645, "global_step": 339475, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.149143934249878, "global_step": 339476, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1803746223449707, "global_step": 339477, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.058163642883301, "global_step": 339478, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1365914344787598, "global_step": 339479, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.046506881713867, "global_step": 339480, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1517348289489746, "global_step": 339481, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0555129051208496, "global_step": 339482, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.039595365524292, "global_step": 339483, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1001102924346924, "global_step": 339484, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0192134380340576, "global_step": 339485, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9474436044692993, "global_step": 339486, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0878400802612305, "global_step": 339487, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.058119535446167, "global_step": 339488, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.034846067428589, "global_step": 339489, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0572898387908936, "global_step": 339490, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.068274736404419, "global_step": 339491, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.02963924407959, "global_step": 339492, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9584904909133911, "global_step": 339493, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2129127979278564, "global_step": 339494, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.136021375656128, "global_step": 339495, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.153822898864746, "global_step": 339496, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0873796939849854, "global_step": 339497, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1339244842529297, "global_step": 339498, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1214025020599365, "global_step": 339499, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0385525226593018, "global_step": 339500, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0841994285583496, "global_step": 339501, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0639686584472656, "global_step": 339502, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110968589782715, "global_step": 339503, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119927167892456, "global_step": 339504, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.074583053588867, "global_step": 339505, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0793614387512207, "global_step": 339506, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0838587284088135, "global_step": 339507, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0624189376831055, "global_step": 339508, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1253457069396973, "global_step": 339509, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.111443042755127, "global_step": 339510, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1448628902435303, "global_step": 339511, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.157137393951416, "global_step": 339512, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.090646982192993, "global_step": 339513, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.158302068710327, "global_step": 339514, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.082390069961548, "global_step": 339515, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086988925933838, "global_step": 339516, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055201530456543, "global_step": 339517, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0764713287353516, "global_step": 339518, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0793139934539795, "global_step": 339519, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0951857566833496, "global_step": 339520, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1166744232177734, "global_step": 339521, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.024528741836548, "global_step": 339522, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.113107204437256, "global_step": 339523, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0046541690826416, "global_step": 339524, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.117814779281616, "global_step": 339525, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0718679428100586, "global_step": 339526, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.141481637954712, "global_step": 339527, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.126500129699707, "global_step": 339528, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.148125648498535, "global_step": 339529, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0737876892089844, "global_step": 339530, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0145723819732666, "global_step": 339531, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1277902126312256, "global_step": 339532, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.120523452758789, "global_step": 339533, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.074171304702759, "global_step": 339534, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1866157054901123, "global_step": 339535, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1254489421844482, "global_step": 339536, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0702760219573975, "global_step": 339537, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1511290073394775, "global_step": 339538, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0915894508361816, "global_step": 339539, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1244497299194336, "global_step": 339540, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0904173851013184, "global_step": 339541, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108031749725342, "global_step": 339542, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0627267360687256, "global_step": 339543, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.07649302482605, "global_step": 339544, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0968434810638428, "global_step": 339545, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9985142946243286, "global_step": 339546, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1005218029022217, "global_step": 339547, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0208327770233154, "global_step": 339548, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10575008392334, "global_step": 339549, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1638734340667725, "global_step": 339550, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1284070014953613, "global_step": 339551, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0536599159240723, "global_step": 339552, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0050270557403564, "global_step": 339553, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1087398529052734, "global_step": 339554, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0512888431549072, "global_step": 339555, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054832696914673, "global_step": 339556, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0213098526000977, "global_step": 339557, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.090071201324463, "global_step": 339558, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0545248985290527, "global_step": 339559, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0502758026123047, "global_step": 339560, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076014280319214, "global_step": 339561, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1412034034729004, "global_step": 339562, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.114917278289795, "global_step": 339563, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1263322830200195, "global_step": 339564, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112724781036377, "global_step": 339565, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1381583213806152, "global_step": 339566, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1113202571868896, "global_step": 339567, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9984489679336548, "global_step": 339568, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134221076965332, "global_step": 339569, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1682517528533936, "global_step": 339570, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1386637687683105, "global_step": 339571, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0996315479278564, "global_step": 339572, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086712598800659, "global_step": 339573, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1058032512664795, "global_step": 339574, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.182267427444458, "global_step": 339575, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0258467197418213, "global_step": 339576, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0951547622680664, "global_step": 339577, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.988548755645752, "global_step": 339578, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9861303567886353, "global_step": 339579, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0521533489227295, "global_step": 339580, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119520902633667, "global_step": 339581, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0625720024108887, "global_step": 339582, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.171557664871216, "global_step": 339583, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.128702163696289, "global_step": 339584, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.012746572494507, "global_step": 339585, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.135237693786621, "global_step": 339586, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0812618732452393, "global_step": 339587, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0478978157043457, "global_step": 339588, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10837984085083, "global_step": 339589, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.070061683654785, "global_step": 339590, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1304757595062256, "global_step": 339591, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0757803916931152, "global_step": 339592, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1160147190093994, "global_step": 339593, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0514211654663086, "global_step": 339594, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.012645721435547, "global_step": 339595, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054269790649414, "global_step": 339596, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110381841659546, "global_step": 339597, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0829315185546875, "global_step": 339598, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0335617065429688, "global_step": 339599, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0992472171783447, "global_step": 339600, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147036075592041, "global_step": 339601, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1501083374023438, "global_step": 339602, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076464891433716, "global_step": 339603, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.144102096557617, "global_step": 339604, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0343410968780518, "global_step": 339605, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.101386308670044, "global_step": 339606, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.068260431289673, "global_step": 339607, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0694758892059326, "global_step": 339608, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0938920974731445, "global_step": 339609, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.107419490814209, "global_step": 339610, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0328547954559326, "global_step": 339611, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0669546127319336, "global_step": 339612, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0835201740264893, "global_step": 339613, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0621373653411865, "global_step": 339614, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055881977081299, "global_step": 339615, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.096778631210327, "global_step": 339616, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1252858638763428, "global_step": 339617, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0168988704681396, "global_step": 339618, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044600009918213, "global_step": 339619, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1012983322143555, "global_step": 339620, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100327730178833, "global_step": 339621, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0392003059387207, "global_step": 339622, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112091302871704, "global_step": 339623, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1256752014160156, "global_step": 339624, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0891952514648438, "global_step": 339625, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1685409545898438, "global_step": 339626, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.115827798843384, "global_step": 339627, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.13362979888916, "global_step": 339628, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.129189968109131, "global_step": 339629, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1128599643707275, "global_step": 339630, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1226871013641357, "global_step": 339631, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.18312931060791, "global_step": 339632, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0759522914886475, "global_step": 339633, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0846328735351562, "global_step": 339634, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1466941833496094, "global_step": 339635, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0981132984161377, "global_step": 339636, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1135480403900146, "global_step": 339637, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.057894229888916, "global_step": 339638, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.04647159576416, "global_step": 339639, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.138871431350708, "global_step": 339640, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.127653121948242, "global_step": 339641, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9994629621505737, "global_step": 339642, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.107426166534424, "global_step": 339643, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.051892042160034, "global_step": 339644, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1542720794677734, "global_step": 339645, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.188338041305542, "global_step": 339646, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1772894859313965, "global_step": 339647, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086507558822632, "global_step": 339648, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1767101287841797, "global_step": 339649, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0915756225585938, "global_step": 339650, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1232926845550537, "global_step": 339651, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9859895706176758, "global_step": 339652, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0626003742218018, "global_step": 339653, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.049423933029175, "global_step": 339654, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.058344841003418, "global_step": 339655, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.088681936264038, "global_step": 339656, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0363593101501465, "global_step": 339657, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.143293857574463, "global_step": 339658, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9540938138961792, "global_step": 339659, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1090190410614014, "global_step": 339660, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0700037479400635, "global_step": 339661, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.128021478652954, "global_step": 339662, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0854947566986084, "global_step": 339663, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0405514240264893, "global_step": 339664, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.128755807876587, "global_step": 339665, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0644774436950684, "global_step": 339666, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.115255832672119, "global_step": 339667, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1219687461853027, "global_step": 339668, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1970067024230957, "global_step": 339669, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0792675018310547, "global_step": 339670, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0393269062042236, "global_step": 339671, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1668570041656494, "global_step": 339672, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1355783939361572, "global_step": 339673, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1030406951904297, "global_step": 339674, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.189100742340088, "global_step": 339675, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.060847520828247, "global_step": 339676, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.083919048309326, "global_step": 339677, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.011049747467041, "global_step": 339678, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045419216156006, "global_step": 339679, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1075632572174072, "global_step": 339680, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1392788887023926, "global_step": 339681, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.06870698928833, "global_step": 339682, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055558681488037, "global_step": 339683, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0922040939331055, "global_step": 339684, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1116244792938232, "global_step": 339685, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1089072227478027, "global_step": 339686, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.194859504699707, "global_step": 339687, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0768611431121826, "global_step": 339688, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.056333541870117, "global_step": 339689, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.061474561691284, "global_step": 339690, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.133962392807007, "global_step": 339691, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2009201049804688, "global_step": 339692, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1151604652404785, "global_step": 339693, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1670966148376465, "global_step": 339694, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0051372051239014, "global_step": 339695, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0545079708099365, "global_step": 339696, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.135472536087036, "global_step": 339697, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1296000480651855, "global_step": 339698, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110427141189575, "global_step": 339699, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1265995502471924, "global_step": 339700, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055401563644409, "global_step": 339701, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0584731101989746, "global_step": 339702, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.141244888305664, "global_step": 339703, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.038475751876831, "global_step": 339704, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0741629600524902, "global_step": 339705, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122300386428833, "global_step": 339706, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1027143001556396, "global_step": 339707, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1513237953186035, "global_step": 339708, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1173717975616455, "global_step": 339709, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.106743335723877, "global_step": 339710, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089038848876953, "global_step": 339711, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.052912712097168, "global_step": 339712, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.057175397872925, "global_step": 339713, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9557591676712036, "global_step": 339714, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079054355621338, "global_step": 339715, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1548473834991455, "global_step": 339716, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0349411964416504, "global_step": 339717, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1010069847106934, "global_step": 339718, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1246306896209717, "global_step": 339719, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0893678665161133, "global_step": 339720, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1609296798706055, "global_step": 339721, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0709388256073, "global_step": 339722, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0997021198272705, "global_step": 339723, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1063437461853027, "global_step": 339724, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2066311836242676, "global_step": 339725, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2245028018951416, "global_step": 339726, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0726027488708496, "global_step": 339727, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0077507495880127, "global_step": 339728, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147102117538452, "global_step": 339729, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0567479133605957, "global_step": 339730, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0430636405944824, "global_step": 339731, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.130746603012085, "global_step": 339732, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.077033281326294, "global_step": 339733, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0463039875030518, "global_step": 339734, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0655744075775146, "global_step": 339735, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.141629695892334, "global_step": 339736, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.048628568649292, "global_step": 339737, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0506508350372314, "global_step": 339738, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1362087726593018, "global_step": 339739, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1473755836486816, "global_step": 339740, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1277945041656494, "global_step": 339741, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.178786516189575, "global_step": 339742, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0283589363098145, "global_step": 339743, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1181509494781494, "global_step": 339744, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.204979658126831, "global_step": 339745, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1225831508636475, "global_step": 339746, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1813859939575195, "global_step": 339747, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055464744567871, "global_step": 339748, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.04020619392395, "global_step": 339749, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0639383792877197, "global_step": 339750, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1969730854034424, "global_step": 339751, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1100544929504395, "global_step": 339752, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0973238945007324, "global_step": 339753, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1152639389038086, "global_step": 339754, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.103909969329834, "global_step": 339755, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0566773414611816, "global_step": 339756, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.060807943344116, "global_step": 339757, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.078718900680542, "global_step": 339758, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9656363725662231, "global_step": 339759, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1145713329315186, "global_step": 339760, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0284552574157715, "global_step": 339761, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0817923545837402, "global_step": 339762, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0449163913726807, "global_step": 339763, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1288681030273438, "global_step": 339764, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1087613105773926, "global_step": 339765, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9484832286834717, "global_step": 339766, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.050056219100952, "global_step": 339767, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.049211025238037, "global_step": 339768, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1653707027435303, "global_step": 339769, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0496041774749756, "global_step": 339770, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1498167514801025, "global_step": 339771, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.101851224899292, "global_step": 339772, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134434938430786, "global_step": 339773, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.183673620223999, "global_step": 339774, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086085081100464, "global_step": 339775, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1772775650024414, "global_step": 339776, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0607128143310547, "global_step": 339777, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1342391967773438, "global_step": 339778, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0817039012908936, "global_step": 339779, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2238707542419434, "global_step": 339780, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0684926509857178, "global_step": 339781, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.016117811203003, "global_step": 339782, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.052690029144287, "global_step": 339783, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1284687519073486, "global_step": 339784, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123494863510132, "global_step": 339785, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0415735244750977, "global_step": 339786, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.154942512512207, "global_step": 339787, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1156697273254395, "global_step": 339788, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1570212841033936, "global_step": 339789, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089297294616699, "global_step": 339790, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0762858390808105, "global_step": 339791, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0357625484466553, "global_step": 339792, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1174988746643066, "global_step": 339793, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0924572944641113, "global_step": 339794, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1009225845336914, "global_step": 339795, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.21156907081604, "global_step": 339796, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.078120231628418, "global_step": 339797, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.090704917907715, "global_step": 339798, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0767903327941895, "global_step": 339799, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10276198387146, "global_step": 339800, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1387076377868652, "global_step": 339801, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110370397567749, "global_step": 339802, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.065073251724243, "global_step": 339803, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.159627676010132, "global_step": 339804, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.082340955734253, "global_step": 339805, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0511417388916016, "global_step": 339806, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.083294153213501, "global_step": 339807, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.178154945373535, "global_step": 339808, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0041987895965576, "global_step": 339809, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0785651206970215, "global_step": 339810, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.977108359336853, "global_step": 339811, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.071605682373047, "global_step": 339812, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.099461078643799, "global_step": 339813, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0427684783935547, "global_step": 339814, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.141226291656494, "global_step": 339815, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0867462158203125, "global_step": 339816, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2113139629364014, "global_step": 339817, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0799648761749268, "global_step": 339818, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.03169846534729, "global_step": 339819, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084770679473877, "global_step": 339820, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1028857231140137, "global_step": 339821, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.016756057739258, "global_step": 339822, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.182504892349243, "global_step": 339823, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.177887201309204, "global_step": 339824, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0404553413391113, "global_step": 339825, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1721749305725098, "global_step": 339826, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119891405105591, "global_step": 339827, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.141940116882324, "global_step": 339828, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1054022312164307, "global_step": 339829, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.150984048843384, "global_step": 339830, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.059248447418213, "global_step": 339831, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1901626586914062, "global_step": 339832, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9723796844482422, "global_step": 339833, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1584811210632324, "global_step": 339834, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1337127685546875, "global_step": 339835, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.11084246635437, "global_step": 339836, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045477867126465, "global_step": 339837, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1675596237182617, "global_step": 339838, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0227713584899902, "global_step": 339839, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1705057621002197, "global_step": 339840, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0433404445648193, "global_step": 339841, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.056518793106079, "global_step": 339842, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.979108452796936, "global_step": 339843, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.078463554382324, "global_step": 339844, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.105609178543091, "global_step": 339845, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.113130569458008, "global_step": 339846, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1463983058929443, "global_step": 339847, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.025970935821533, "global_step": 339848, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1046111583709717, "global_step": 339849, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1024317741394043, "global_step": 339850, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0390284061431885, "global_step": 339851, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.102248191833496, "global_step": 339852, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0786101818084717, "global_step": 339853, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1237175464630127, "global_step": 339854, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123121976852417, "global_step": 339855, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.133246421813965, "global_step": 339856, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0675911903381348, "global_step": 339857, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044569730758667, "global_step": 339858, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1584582328796387, "global_step": 339859, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0750138759613037, "global_step": 339860, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0715534687042236, "global_step": 339861, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2054197788238525, "global_step": 339862, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1498875617980957, "global_step": 339863, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.053758382797241, "global_step": 339864, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.005229949951172, "global_step": 339865, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1548428535461426, "global_step": 339866, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1172773838043213, "global_step": 339867, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1033079624176025, "global_step": 339868, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.070361852645874, "global_step": 339869, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075186252593994, "global_step": 339870, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0338265895843506, "global_step": 339871, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0904316902160645, "global_step": 339872, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1095998287200928, "global_step": 339873, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.146981716156006, "global_step": 339874, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1154696941375732, "global_step": 339875, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0805583000183105, "global_step": 339876, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9969115257263184, "global_step": 339877, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1348965167999268, "global_step": 339878, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.130579948425293, "global_step": 339879, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0651140213012695, "global_step": 339880, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9517848491668701, "global_step": 339881, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1193206310272217, "global_step": 339882, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1517794132232666, "global_step": 339883, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.114107370376587, "global_step": 339884, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.176147937774658, "global_step": 339885, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1326756477355957, "global_step": 339886, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.070146322250366, "global_step": 339887, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.197622537612915, "global_step": 339888, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.11602520942688, "global_step": 339889, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0876705646514893, "global_step": 339890, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0900628566741943, "global_step": 339891, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08981990814209, "global_step": 339892, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1108896732330322, "global_step": 339893, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.138221263885498, "global_step": 339894, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08416748046875, "global_step": 339895, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1449007987976074, "global_step": 339896, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.024238348007202, "global_step": 339897, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0786421298980713, "global_step": 339898, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1858716011047363, "global_step": 339899, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1483445167541504, "global_step": 339900, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1510586738586426, "global_step": 339901, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100900650024414, "global_step": 339902, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1343071460723877, "global_step": 339903, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1628761291503906, "global_step": 339904, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.106243848800659, "global_step": 339905, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0655832290649414, "global_step": 339906, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0281851291656494, "global_step": 339907, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0569944381713867, "global_step": 339908, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1209588050842285, "global_step": 339909, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076961040496826, "global_step": 339910, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.113539218902588, "global_step": 339911, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.977612853050232, "global_step": 339912, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.064422607421875, "global_step": 339913, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0632576942443848, "global_step": 339914, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0655229091644287, "global_step": 339915, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0632402896881104, "global_step": 339916, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1428067684173584, "global_step": 339917, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0423402786254883, "global_step": 339918, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0637762546539307, "global_step": 339919, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1944873332977295, "global_step": 339920, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.040372848510742, "global_step": 339921, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1236319541931152, "global_step": 339922, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.074970006942749, "global_step": 339923, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.160112142562866, "global_step": 339924, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085737466812134, "global_step": 339925, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1400575637817383, "global_step": 339926, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1053314208984375, "global_step": 339927, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1991114616394043, "global_step": 339928, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0802736282348633, "global_step": 339929, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0914502143859863, "global_step": 339930, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.203096628189087, "global_step": 339931, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1292197704315186, "global_step": 339932, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.096015691757202, "global_step": 339933, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.240201234817505, "global_step": 339934, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08076548576355, "global_step": 339935, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0471622943878174, "global_step": 339936, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0465567111968994, "global_step": 339937, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0630807876586914, "global_step": 339938, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1147830486297607, "global_step": 339939, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147627830505371, "global_step": 339940, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1444568634033203, "global_step": 339941, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0846569538116455, "global_step": 339942, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.154515266418457, "global_step": 339943, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.120391607284546, "global_step": 339944, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.035597562789917, "global_step": 339945, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1177525520324707, "global_step": 339946, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119229316711426, "global_step": 339947, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1417365074157715, "global_step": 339948, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1479151248931885, "global_step": 339949, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.150101661682129, "global_step": 339950, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0290582180023193, "global_step": 339951, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.125460624694824, "global_step": 339952, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.105137586593628, "global_step": 339953, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.143763542175293, "global_step": 339954, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.127279281616211, "global_step": 339955, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.173346757888794, "global_step": 339956, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108980655670166, "global_step": 339957, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.120734453201294, "global_step": 339958, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.144423484802246, "global_step": 339959, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1462976932525635, "global_step": 339960, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2011618614196777, "global_step": 339961, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110692262649536, "global_step": 339962, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134331464767456, "global_step": 339963, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.985460877418518, "global_step": 339964, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.996282935142517, "global_step": 339965, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1389780044555664, "global_step": 339966, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0973353385925293, "global_step": 339967, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1236040592193604, "global_step": 339968, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.115474224090576, "global_step": 339969, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.18624210357666, "global_step": 339970, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0997776985168457, "global_step": 339971, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1020636558532715, "global_step": 339972, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044567584991455, "global_step": 339973, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.129859447479248, "global_step": 339974, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.077331066131592, "global_step": 339975, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.113044023513794, "global_step": 339976, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.167412281036377, "global_step": 339977, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1646623611450195, "global_step": 339978, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.141721725463867, "global_step": 339979, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0918643474578857, "global_step": 339980, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0859129428863525, "global_step": 339981, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1681911945343018, "global_step": 339982, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.225229024887085, "global_step": 339983, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112537384033203, "global_step": 339984, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0724105834960938, "global_step": 339985, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.024345636367798, "global_step": 339986, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.121878147125244, "global_step": 339987, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0778584480285645, "global_step": 339988, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0404694080352783, "global_step": 339989, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1278629302978516, "global_step": 339990, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.071134567260742, "global_step": 339991, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086760997772217, "global_step": 339992, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.129617929458618, "global_step": 339993, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.128512382507324, "global_step": 339994, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0396058559417725, "global_step": 339995, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2620315551757812, "global_step": 339996, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.103567600250244, "global_step": 339997, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0425238609313965, "global_step": 339998, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.150026798248291, "global_step": 339999, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.113712787628174, "global_step": 340000, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1229231357574463, "global_step": 340001, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0940310955047607, "global_step": 340002, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10868501663208, "global_step": 340003, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0303163528442383, "global_step": 340004, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0538158416748047, "global_step": 340005, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112708330154419, "global_step": 340006, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1641452312469482, "global_step": 340007, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1030161380767822, "global_step": 340008, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.015960931777954, "global_step": 340009, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.068997621536255, "global_step": 340010, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1018285751342773, "global_step": 340011, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1486568450927734, "global_step": 340012, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1075093746185303, "global_step": 340013, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1918108463287354, "global_step": 340014, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.090337038040161, "global_step": 340015, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.001499652862549, "global_step": 340016, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.144986629486084, "global_step": 340017, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1784040927886963, "global_step": 340018, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089179277420044, "global_step": 340019, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.091400146484375, "global_step": 340020, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1131513118743896, "global_step": 340021, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.036836624145508, "global_step": 340022, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.059020757675171, "global_step": 340023, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069068431854248, "global_step": 340024, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1107017993927, "global_step": 340025, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.060415267944336, "global_step": 340026, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0392396450042725, "global_step": 340027, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.07235050201416, "global_step": 340028, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.209526538848877, "global_step": 340029, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1223840713500977, "global_step": 340030, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0196781158447266, "global_step": 340031, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1197664737701416, "global_step": 340032, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.145537853240967, "global_step": 340033, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110222339630127, "global_step": 340034, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0956411361694336, "global_step": 340035, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.066722869873047, "global_step": 340036, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.097639560699463, "global_step": 340037, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1972908973693848, "global_step": 340038, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0526797771453857, "global_step": 340039, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.092245578765869, "global_step": 340040, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1289737224578857, "global_step": 340041, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1302969455718994, "global_step": 340042, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08023738861084, "global_step": 340043, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0405654907226562, "global_step": 340044, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1587305068969727, "global_step": 340045, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1014246940612793, "global_step": 340046, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0968194007873535, "global_step": 340047, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0841686725616455, "global_step": 340048, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0734293460845947, "global_step": 340049, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9876132011413574, "global_step": 340050, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9953498840332031, "global_step": 340051, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1503868103027344, "global_step": 340052, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1520678997039795, "global_step": 340053, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.087070941925049, "global_step": 340054, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.106022834777832, "global_step": 340055, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0947465896606445, "global_step": 340056, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.175877571105957, "global_step": 340057, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.133335590362549, "global_step": 340058, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1031062602996826, "global_step": 340059, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0589489936828613, "global_step": 340060, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075684070587158, "global_step": 340061, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1713128089904785, "global_step": 340062, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0882978439331055, "global_step": 340063, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1700196266174316, "global_step": 340064, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.040367841720581, "global_step": 340065, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1329948902130127, "global_step": 340066, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1166787147521973, "global_step": 340067, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1693460941314697, "global_step": 340068, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2339534759521484, "global_step": 340069, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0433733463287354, "global_step": 340070, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.114337205886841, "global_step": 340071, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.120426654815674, "global_step": 340072, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1127116680145264, "global_step": 340073, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1129515171051025, "global_step": 340074, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1282312870025635, "global_step": 340075, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069270610809326, "global_step": 340076, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100152015686035, "global_step": 340077, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0456464290618896, "global_step": 340078, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.15104079246521, "global_step": 340079, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.13481068611145, "global_step": 340080, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.129399538040161, "global_step": 340081, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.149815559387207, "global_step": 340082, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.088933229446411, "global_step": 340083, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0749874114990234, "global_step": 340084, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1167609691619873, "global_step": 340085, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0856523513793945, "global_step": 340086, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1628637313842773, "global_step": 340087, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.128127098083496, "global_step": 340088, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0593292713165283, "global_step": 340089, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0804052352905273, "global_step": 340090, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.078670024871826, "global_step": 340091, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1061792373657227, "global_step": 340092, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.03776216506958, "global_step": 340093, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1472020149230957, "global_step": 340094, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1496469974517822, "global_step": 340095, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.019944190979004, "global_step": 340096, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1711137294769287, "global_step": 340097, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1232151985168457, "global_step": 340098, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0900049209594727, "global_step": 340099, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10410475730896, "global_step": 340100, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1934967041015625, "global_step": 340101, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1812031269073486, "global_step": 340102, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085040330886841, "global_step": 340103, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.109309673309326, "global_step": 340104, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1639881134033203, "global_step": 340105, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1611850261688232, "global_step": 340106, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0536117553710938, "global_step": 340107, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.081826686859131, "global_step": 340108, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0331740379333496, "global_step": 340109, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0904743671417236, "global_step": 340110, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044039487838745, "global_step": 340111, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0467910766601562, "global_step": 340112, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0886340141296387, "global_step": 340113, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.103717565536499, "global_step": 340114, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.041475296020508, "global_step": 340115, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0959012508392334, "global_step": 340116, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1549599170684814, "global_step": 340117, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1951539516448975, "global_step": 340118, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1599459648132324, "global_step": 340119, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0765788555145264, "global_step": 340120, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1083760261535645, "global_step": 340121, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1803715229034424, "global_step": 340122, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108591318130493, "global_step": 340123, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085763931274414, "global_step": 340124, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.106363296508789, "global_step": 340125, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086535930633545, "global_step": 340126, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1596717834472656, "global_step": 340127, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0950357913970947, "global_step": 340128, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1129395961761475, "global_step": 340129, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.073523998260498, "global_step": 340130, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112277030944824, "global_step": 340131, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.151829719543457, "global_step": 340132, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1623501777648926, "global_step": 340133, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1097559928894043, "global_step": 340134, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1686573028564453, "global_step": 340135, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1674773693084717, "global_step": 340136, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.17529296875, "global_step": 340137, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.174828290939331, "global_step": 340138, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069232225418091, "global_step": 340139, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0642051696777344, "global_step": 340140, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0742154121398926, "global_step": 340141, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0731701850891113, "global_step": 340142, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.063225269317627, "global_step": 340143, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.19793701171875, "global_step": 340144, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0638365745544434, "global_step": 340145, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0746288299560547, "global_step": 340146, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.178892135620117, "global_step": 340147, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1847381591796875, "global_step": 340148, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.131913185119629, "global_step": 340149, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.068413019180298, "global_step": 340150, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.191481828689575, "global_step": 340151, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1385183334350586, "global_step": 340152, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0851614475250244, "global_step": 340153, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044557809829712, "global_step": 340154, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1154487133026123, "global_step": 340155, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123551607131958, "global_step": 340156, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0626678466796875, "global_step": 340157, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.131359100341797, "global_step": 340158, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0965821743011475, "global_step": 340159, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.078784465789795, "global_step": 340160, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147376537322998, "global_step": 340161, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1269965171813965, "global_step": 340162, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10038423538208, "global_step": 340163, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.099334716796875, "global_step": 340164, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075892925262451, "global_step": 340165, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1868178844451904, "global_step": 340166, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.146611213684082, "global_step": 340167, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1085424423217773, "global_step": 340168, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.009120225906372, "global_step": 340169, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086843729019165, "global_step": 340170, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.118447780609131, "global_step": 340171, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0373690128326416, "global_step": 340172, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1983964443206787, "global_step": 340173, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.130774736404419, "global_step": 340174, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.175384759902954, "global_step": 340175, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0147595405578613, "global_step": 340176, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2476022243499756, "global_step": 340177, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1612985134124756, "global_step": 340178, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076014995574951, "global_step": 340179, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0866427421569824, "global_step": 340180, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1006622314453125, "global_step": 340181, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.038616418838501, "global_step": 340182, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1520354747772217, "global_step": 340183, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.186446189880371, "global_step": 340184, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1893012523651123, "global_step": 340185, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.013957977294922, "global_step": 340186, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.127938985824585, "global_step": 340187, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1997263431549072, "global_step": 340188, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1761906147003174, "global_step": 340189, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1045336723327637, "global_step": 340190, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.17643666267395, "global_step": 340191, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.14569354057312, "global_step": 340192, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.159635543823242, "global_step": 340193, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0716402530670166, "global_step": 340194, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0985467433929443, "global_step": 340195, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.103337287902832, "global_step": 340196, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.09865665435791, "global_step": 340197, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1076321601867676, "global_step": 340198, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.01238751411438, "global_step": 340199, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.09576678276062, "global_step": 340200, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0452303886413574, "global_step": 340201, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1997246742248535, "global_step": 340202, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1155593395233154, "global_step": 340203, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.041262149810791, "global_step": 340204, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.184771776199341, "global_step": 340205, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.097421407699585, "global_step": 340206, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0738072395324707, "global_step": 340207, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0459396839141846, "global_step": 340208, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085390090942383, "global_step": 340209, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1380739212036133, "global_step": 340210, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1209139823913574, "global_step": 340211, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.073214054107666, "global_step": 340212, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1415741443634033, "global_step": 340213, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1574947834014893, "global_step": 340214, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1938974857330322, "global_step": 340215, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.197542905807495, "global_step": 340216, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0829899311065674, "global_step": 340217, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1685941219329834, "global_step": 340218, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0963006019592285, "global_step": 340219, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0709800720214844, "global_step": 340220, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1511943340301514, "global_step": 340221, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1557936668395996, "global_step": 340222, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.037397861480713, "global_step": 340223, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0791015625, "global_step": 340224, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.071099281311035, "global_step": 340225, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0522220134735107, "global_step": 340226, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.188523530960083, "global_step": 340227, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0967586040496826, "global_step": 340228, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.117201328277588, "global_step": 340229, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.158545970916748, "global_step": 340230, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0806119441986084, "global_step": 340231, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.159672975540161, "global_step": 340232, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.121307373046875, "global_step": 340233, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1219024658203125, "global_step": 340234, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.157783269882202, "global_step": 340235, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.208183765411377, "global_step": 340236, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1664888858795166, "global_step": 340237, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1171460151672363, "global_step": 340238, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.17398738861084, "global_step": 340239, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075313091278076, "global_step": 340240, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08247971534729, "global_step": 340241, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123220205307007, "global_step": 340242, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.038806915283203, "global_step": 340243, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0545976161956787, "global_step": 340244, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0781915187835693, "global_step": 340245, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0906598567962646, "global_step": 340246, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2034215927124023, "global_step": 340247, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055204153060913, "global_step": 340248, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147010087966919, "global_step": 340249, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147071361541748, "global_step": 340250, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0485665798187256, "global_step": 339283, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.98964524269104, "global_step": 339284, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.13065242767334, "global_step": 339285, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.975332498550415, "global_step": 339286, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1466000080108643, "global_step": 339287, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9777573347091675, "global_step": 339288, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9712461233139038, "global_step": 339289, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0988028049468994, "global_step": 339290, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0551400184631348, "global_step": 339291, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1010303497314453, "global_step": 339292, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.126014471054077, "global_step": 339293, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.020275354385376, "global_step": 339294, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.177225112915039, "global_step": 339295, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.113121747970581, "global_step": 339296, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055311441421509, "global_step": 339297, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0644052028656006, "global_step": 339298, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.024221897125244, "global_step": 339299, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0672860145568848, "global_step": 339300, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0752604007720947, "global_step": 339301, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0448625087738037, "global_step": 339302, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0366203784942627, "global_step": 339303, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069291353225708, "global_step": 339304, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1720831394195557, "global_step": 339305, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122223138809204, "global_step": 339306, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0278027057647705, "global_step": 339307, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0457382202148438, "global_step": 339308, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0426580905914307, "global_step": 339309, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0328874588012695, "global_step": 339310, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0797688961029053, "global_step": 339311, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.088836908340454, "global_step": 339312, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.002502918243408, "global_step": 339313, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0724618434906006, "global_step": 339314, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122771739959717, "global_step": 339315, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1124861240386963, "global_step": 339316, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1106948852539062, "global_step": 339317, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123131513595581, "global_step": 339318, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.017672538757324, "global_step": 339319, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.026608943939209, "global_step": 339320, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.125443935394287, "global_step": 339321, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0518958568573, "global_step": 339322, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0608971118927, "global_step": 339323, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.050724983215332, "global_step": 339324, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1540069580078125, "global_step": 339325, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.161930561065674, "global_step": 339326, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0875625610351562, "global_step": 339327, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045867919921875, "global_step": 339328, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.01279616355896, "global_step": 339329, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1200079917907715, "global_step": 339330, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.081266164779663, "global_step": 339331, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0920913219451904, "global_step": 339332, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069188356399536, "global_step": 339333, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147002935409546, "global_step": 339334, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0897111892700195, "global_step": 339335, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0046699047088623, "global_step": 339336, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0501320362091064, "global_step": 339337, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1969571113586426, "global_step": 339338, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.05107045173645, "global_step": 339339, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110273838043213, "global_step": 339340, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.058898687362671, "global_step": 339341, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0815298557281494, "global_step": 339342, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1080727577209473, "global_step": 339343, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1307501792907715, "global_step": 339344, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.081336736679077, "global_step": 339345, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0540809631347656, "global_step": 339346, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.034102439880371, "global_step": 339347, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.021962881088257, "global_step": 339348, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.093165397644043, "global_step": 339349, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1025514602661133, "global_step": 339350, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0694420337677, "global_step": 339351, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.099290132522583, "global_step": 339352, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.078557252883911, "global_step": 339353, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1388697624206543, "global_step": 339354, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0745561122894287, "global_step": 339355, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.107706069946289, "global_step": 339356, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0379087924957275, "global_step": 339357, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.082437515258789, "global_step": 339358, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0738837718963623, "global_step": 339359, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.164473056793213, "global_step": 339360, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0066168308258057, "global_step": 339361, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08388352394104, "global_step": 339362, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9911277294158936, "global_step": 339363, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1339075565338135, "global_step": 339364, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.087376832962036, "global_step": 339365, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.059159278869629, "global_step": 339366, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.121455669403076, "global_step": 339367, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.060149669647217, "global_step": 339368, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0559091567993164, "global_step": 339369, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0849852561950684, "global_step": 339370, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0075650215148926, "global_step": 339371, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1191389560699463, "global_step": 339372, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.149531364440918, "global_step": 339373, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.046929359436035, "global_step": 339374, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1718082427978516, "global_step": 339375, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0431485176086426, "global_step": 339376, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.025508403778076, "global_step": 339377, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147148609161377, "global_step": 339378, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2418365478515625, "global_step": 339379, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.029623031616211, "global_step": 339380, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9977458715438843, "global_step": 339381, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085476875305176, "global_step": 339382, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9897412061691284, "global_step": 339383, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.025923728942871, "global_step": 339384, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0523688793182373, "global_step": 339385, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0990588665008545, "global_step": 339386, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.071312189102173, "global_step": 339387, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.137760877609253, "global_step": 339388, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1210813522338867, "global_step": 339389, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1296205520629883, "global_step": 339390, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0667471885681152, "global_step": 339391, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1047005653381348, "global_step": 339392, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.098780870437622, "global_step": 339393, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.071948289871216, "global_step": 339394, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.04298734664917, "global_step": 339395, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.031198024749756, "global_step": 339396, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1251285076141357, "global_step": 339397, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2314321994781494, "global_step": 339398, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2054026126861572, "global_step": 339399, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0488407611846924, "global_step": 339400, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.080040693283081, "global_step": 339401, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1784002780914307, "global_step": 339402, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.13037371635437, "global_step": 339403, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1417274475097656, "global_step": 339404, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1970105171203613, "global_step": 339405, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055534839630127, "global_step": 339406, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.143531560897827, "global_step": 339407, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.048614978790283, "global_step": 339408, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.032045841217041, "global_step": 339409, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0707380771636963, "global_step": 339410, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.047088146209717, "global_step": 339411, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.032458782196045, "global_step": 339412, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1077980995178223, "global_step": 339413, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147005319595337, "global_step": 339414, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1036972999572754, "global_step": 339415, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0644969940185547, "global_step": 339416, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0849390029907227, "global_step": 339417, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0680344104766846, "global_step": 339418, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0445363521575928, "global_step": 339419, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.064419984817505, "global_step": 339420, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.05199933052063, "global_step": 339421, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0407400131225586, "global_step": 339422, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086209297180176, "global_step": 339423, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0719423294067383, "global_step": 339424, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.136335611343384, "global_step": 339425, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.157102108001709, "global_step": 339426, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0889604091644287, "global_step": 339427, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.06367564201355, "global_step": 339428, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.143380880355835, "global_step": 339429, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1027944087982178, "global_step": 339430, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1396842002868652, "global_step": 339431, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.109837770462036, "global_step": 339432, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045542001724243, "global_step": 339433, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1116716861724854, "global_step": 339434, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1295526027679443, "global_step": 339435, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055614948272705, "global_step": 339436, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123377799987793, "global_step": 339437, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147775173187256, "global_step": 339438, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0953164100646973, "global_step": 339439, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1834044456481934, "global_step": 339440, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0542163848876953, "global_step": 339441, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0846216678619385, "global_step": 339442, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.18203067779541, "global_step": 339443, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0021324157714844, "global_step": 339444, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.031487464904785, "global_step": 339445, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.087116003036499, "global_step": 339446, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0279228687286377, "global_step": 339447, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.034013509750366, "global_step": 339448, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.13379168510437, "global_step": 339449, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1074695587158203, "global_step": 339450, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1023783683776855, "global_step": 339451, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0673956871032715, "global_step": 339452, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123680353164673, "global_step": 339453, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9918614625930786, "global_step": 339454, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.059234380722046, "global_step": 339455, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075712203979492, "global_step": 339456, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.033968210220337, "global_step": 339457, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0390188694000244, "global_step": 339458, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0908169746398926, "global_step": 339459, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.009519338607788, "global_step": 339460, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100910186767578, "global_step": 339461, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0689120292663574, "global_step": 339462, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.023806571960449, "global_step": 339463, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1298577785491943, "global_step": 339464, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1157913208007812, "global_step": 339465, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0776491165161133, "global_step": 339466, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0845088958740234, "global_step": 339467, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1086578369140625, "global_step": 339468, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0693299770355225, "global_step": 339469, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1217501163482666, "global_step": 339470, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1157479286193848, "global_step": 339471, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0694868564605713, "global_step": 339472, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.219940423965454, "global_step": 339473, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0218679904937744, "global_step": 339474, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.146272897720337, "global_step": 339475, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.149465322494507, "global_step": 339476, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1821436882019043, "global_step": 339477, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.058314561843872, "global_step": 339478, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1366071701049805, "global_step": 339479, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0471177101135254, "global_step": 339480, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.152743339538574, "global_step": 339481, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0560801029205322, "global_step": 339482, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0389933586120605, "global_step": 339483, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.099283456802368, "global_step": 339484, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0195834636688232, "global_step": 339485, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9470287561416626, "global_step": 339486, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0884149074554443, "global_step": 339487, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.058450698852539, "global_step": 339488, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0343785285949707, "global_step": 339489, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.056852102279663, "global_step": 339490, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.068859815597534, "global_step": 339491, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.028733491897583, "global_step": 339492, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9594179391860962, "global_step": 339493, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2118663787841797, "global_step": 339494, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1366782188415527, "global_step": 339495, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1537680625915527, "global_step": 339496, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0875790119171143, "global_step": 339497, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.133437395095825, "global_step": 339498, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1214346885681152, "global_step": 339499, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.039339542388916, "global_step": 339500, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084958076477051, "global_step": 339501, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.064263343811035, "global_step": 339502, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110804557800293, "global_step": 339503, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1193172931671143, "global_step": 339504, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075120210647583, "global_step": 339505, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0791659355163574, "global_step": 339506, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084331512451172, "global_step": 339507, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.062584638595581, "global_step": 339508, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.126131057739258, "global_step": 339509, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1119492053985596, "global_step": 339510, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1444506645202637, "global_step": 339511, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1557912826538086, "global_step": 339512, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.090514659881592, "global_step": 339513, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.157194137573242, "global_step": 339514, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0847229957580566, "global_step": 339515, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0867109298706055, "global_step": 339516, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054935932159424, "global_step": 339517, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0760254859924316, "global_step": 339518, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079476833343506, "global_step": 339519, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.095285654067993, "global_step": 339520, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.116243839263916, "global_step": 339521, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0241243839263916, "global_step": 339522, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.111999988555908, "global_step": 339523, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.004606246948242, "global_step": 339524, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.117570161819458, "global_step": 339525, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.071259021759033, "global_step": 339526, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.140897512435913, "global_step": 339527, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.126507043838501, "global_step": 339528, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147352695465088, "global_step": 339529, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0754735469818115, "global_step": 339530, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.014543294906616, "global_step": 339531, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.127202033996582, "global_step": 339532, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1200685501098633, "global_step": 339533, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0746636390686035, "global_step": 339534, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.18613862991333, "global_step": 339535, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1274003982543945, "global_step": 339536, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0707764625549316, "global_step": 339537, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1513593196868896, "global_step": 339538, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0902864933013916, "global_step": 339539, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.126178741455078, "global_step": 339540, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.090195655822754, "global_step": 339541, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1076908111572266, "global_step": 339542, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0624260902404785, "global_step": 339543, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075958251953125, "global_step": 339544, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.096417188644409, "global_step": 339545, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9990856647491455, "global_step": 339546, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1011769771575928, "global_step": 339547, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0218818187713623, "global_step": 339548, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1071503162384033, "global_step": 339549, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.164245128631592, "global_step": 339550, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1276729106903076, "global_step": 339551, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054577589035034, "global_step": 339552, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.005070209503174, "global_step": 339553, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1081504821777344, "global_step": 339554, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0516176223754883, "global_step": 339555, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0539281368255615, "global_step": 339556, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.02034330368042, "global_step": 339557, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0899152755737305, "global_step": 339558, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054006814956665, "global_step": 339559, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.050502061843872, "global_step": 339560, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0759999752044678, "global_step": 339561, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.141961097717285, "global_step": 339562, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1162109375, "global_step": 339563, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1264216899871826, "global_step": 339564, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112401008605957, "global_step": 339565, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1397697925567627, "global_step": 339566, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.111710548400879, "global_step": 339567, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9986956119537354, "global_step": 339568, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1339340209960938, "global_step": 339569, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1680092811584473, "global_step": 339570, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.139580488204956, "global_step": 339571, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0997684001922607, "global_step": 339572, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0882134437561035, "global_step": 339573, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1054675579071045, "global_step": 339574, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1820666790008545, "global_step": 339575, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0235209465026855, "global_step": 339576, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0941364765167236, "global_step": 339577, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9886200428009033, "global_step": 339578, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9849246740341187, "global_step": 339579, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.053117513656616, "global_step": 339580, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1193673610687256, "global_step": 339581, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0635969638824463, "global_step": 339582, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.171967029571533, "global_step": 339583, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1287384033203125, "global_step": 339584, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.011474370956421, "global_step": 339585, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1345317363739014, "global_step": 339586, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0804836750030518, "global_step": 339587, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0471291542053223, "global_step": 339588, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.107706069946289, "global_step": 339589, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069561004638672, "global_step": 339590, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.130497455596924, "global_step": 339591, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0772781372070312, "global_step": 339592, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1178319454193115, "global_step": 339593, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.051044464111328, "global_step": 339594, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0134835243225098, "global_step": 339595, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.053760051727295, "global_step": 339596, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1111397743225098, "global_step": 339597, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084010362625122, "global_step": 339598, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.034027338027954, "global_step": 339599, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1011886596679688, "global_step": 339600, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147339105606079, "global_step": 339601, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.14888334274292, "global_step": 339602, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0756759643554688, "global_step": 339603, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.145475149154663, "global_step": 339604, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0338544845581055, "global_step": 339605, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1026999950408936, "global_step": 339606, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0700461864471436, "global_step": 339607, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0707530975341797, "global_step": 339608, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0931036472320557, "global_step": 339609, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.106459617614746, "global_step": 339610, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0324509143829346, "global_step": 339611, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0673482418060303, "global_step": 339612, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084104537963867, "global_step": 339613, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0598223209381104, "global_step": 339614, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0556397438049316, "global_step": 339615, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0979487895965576, "global_step": 339616, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1241724491119385, "global_step": 339617, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0181026458740234, "global_step": 339618, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044635057449341, "global_step": 339619, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100118398666382, "global_step": 339620, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100235939025879, "global_step": 339621, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.039377450942993, "global_step": 339622, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1116466522216797, "global_step": 339623, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.125793933868408, "global_step": 339624, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0907504558563232, "global_step": 339625, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1687703132629395, "global_step": 339626, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.115511655807495, "global_step": 339627, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.13301682472229, "global_step": 339628, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.130625009536743, "global_step": 339629, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112438201904297, "global_step": 339630, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122894763946533, "global_step": 339631, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1812989711761475, "global_step": 339632, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076256275177002, "global_step": 339633, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0853748321533203, "global_step": 339634, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1464006900787354, "global_step": 339635, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.096482276916504, "global_step": 339636, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1128342151641846, "global_step": 339637, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0565271377563477, "global_step": 339638, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0464508533477783, "global_step": 339639, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1408255100250244, "global_step": 339640, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.126826524734497, "global_step": 339641, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0030553340911865, "global_step": 339642, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.107326030731201, "global_step": 339643, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0521740913391113, "global_step": 339644, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.154245615005493, "global_step": 339645, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.187818765640259, "global_step": 339646, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1774492263793945, "global_step": 339647, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0844779014587402, "global_step": 339648, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1779963970184326, "global_step": 339649, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.092552661895752, "global_step": 339650, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.12306809425354, "global_step": 339651, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9860228300094604, "global_step": 339652, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0623939037323, "global_step": 339653, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.046686887741089, "global_step": 339654, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0595247745513916, "global_step": 339655, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089573621749878, "global_step": 339656, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0364952087402344, "global_step": 339657, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1415765285491943, "global_step": 339658, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9534401893615723, "global_step": 339659, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1087112426757812, "global_step": 339660, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072411298751831, "global_step": 339661, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.12911319732666, "global_step": 339662, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086789131164551, "global_step": 339663, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.041081190109253, "global_step": 339664, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.128204822540283, "global_step": 339665, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0657706260681152, "global_step": 339666, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.116807460784912, "global_step": 339667, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.121884822845459, "global_step": 339668, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1977343559265137, "global_step": 339669, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0799131393432617, "global_step": 339670, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.039320945739746, "global_step": 339671, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1656835079193115, "global_step": 339672, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.136632204055786, "global_step": 339673, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1027672290802, "global_step": 339674, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.189405679702759, "global_step": 339675, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.060335397720337, "global_step": 339676, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0850305557250977, "global_step": 339677, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.010723352432251, "global_step": 339678, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.04464054107666, "global_step": 339679, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1071157455444336, "global_step": 339680, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.141077756881714, "global_step": 339681, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.068537950515747, "global_step": 339682, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055105686187744, "global_step": 339683, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0915443897247314, "global_step": 339684, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1111819744110107, "global_step": 339685, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108079433441162, "global_step": 339686, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1931068897247314, "global_step": 339687, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0759925842285156, "global_step": 339688, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0552430152893066, "global_step": 339689, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.061549425125122, "global_step": 339690, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.13564133644104, "global_step": 339691, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.200779438018799, "global_step": 339692, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1152875423431396, "global_step": 339693, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.165519952774048, "global_step": 339694, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.005483865737915, "global_step": 339695, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054584264755249, "global_step": 339696, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1348886489868164, "global_step": 339697, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1282835006713867, "global_step": 339698, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1119039058685303, "global_step": 339699, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.12760329246521, "global_step": 339700, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0545103549957275, "global_step": 339701, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.058873176574707, "global_step": 339702, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1388449668884277, "global_step": 339703, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0362625122070312, "global_step": 339704, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.07267689704895, "global_step": 339705, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1213674545288086, "global_step": 339706, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1038780212402344, "global_step": 339707, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1492364406585693, "global_step": 339708, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.117499351501465, "global_step": 339709, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1074793338775635, "global_step": 339710, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0898385047912598, "global_step": 339711, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.053581953048706, "global_step": 339712, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054964780807495, "global_step": 339713, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9524827003479004, "global_step": 339714, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0785226821899414, "global_step": 339715, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1568307876586914, "global_step": 339716, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.033411741256714, "global_step": 339717, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100541830062866, "global_step": 339718, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1245930194854736, "global_step": 339719, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.088534116744995, "global_step": 339720, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1595871448516846, "global_step": 339721, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072354316711426, "global_step": 339722, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1010053157806396, "global_step": 339723, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108814001083374, "global_step": 339724, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2071614265441895, "global_step": 339725, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2267465591430664, "global_step": 339726, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0725364685058594, "global_step": 339727, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0083694458007812, "global_step": 339728, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.146113157272339, "global_step": 339729, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0558412075042725, "global_step": 339730, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0407707691192627, "global_step": 339731, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1303372383117676, "global_step": 339732, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.07806396484375, "global_step": 339733, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0450000762939453, "global_step": 339734, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0654420852661133, "global_step": 339735, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1396915912628174, "global_step": 339736, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.050184488296509, "global_step": 339737, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.051039457321167, "global_step": 339738, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1375017166137695, "global_step": 339739, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147956132888794, "global_step": 339740, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.127960205078125, "global_step": 339741, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.179354190826416, "global_step": 339742, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0293378829956055, "global_step": 339743, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1181178092956543, "global_step": 339744, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2043631076812744, "global_step": 339745, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1235764026641846, "global_step": 339746, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1804161071777344, "global_step": 339747, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054044485092163, "global_step": 339748, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.040661096572876, "global_step": 339749, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0632901191711426, "global_step": 339750, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1979176998138428, "global_step": 339751, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1097655296325684, "global_step": 339752, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.098651885986328, "global_step": 339753, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.116307258605957, "global_step": 339754, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1055963039398193, "global_step": 339755, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0549747943878174, "global_step": 339756, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.062086582183838, "global_step": 339757, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.077291965484619, "global_step": 339758, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9677135944366455, "global_step": 339759, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1131110191345215, "global_step": 339760, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0294876098632812, "global_step": 339761, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0812106132507324, "global_step": 339762, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0446383953094482, "global_step": 339763, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1294243335723877, "global_step": 339764, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1068625450134277, "global_step": 339765, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9477261304855347, "global_step": 339766, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0505995750427246, "global_step": 339767, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.048511028289795, "global_step": 339768, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1654868125915527, "global_step": 339769, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.050154685974121, "global_step": 339770, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1503074169158936, "global_step": 339771, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1036176681518555, "global_step": 339772, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.135155200958252, "global_step": 339773, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1833300590515137, "global_step": 339774, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086089611053467, "global_step": 339775, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1778578758239746, "global_step": 339776, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0588955879211426, "global_step": 339777, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1347925662994385, "global_step": 339778, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.082995653152466, "global_step": 339779, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2246854305267334, "global_step": 339780, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.070387601852417, "global_step": 339781, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.018054485321045, "global_step": 339782, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.051955223083496, "global_step": 339783, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1281728744506836, "global_step": 339784, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.125718355178833, "global_step": 339785, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0407512187957764, "global_step": 339786, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.156188488006592, "global_step": 339787, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1132349967956543, "global_step": 339788, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.156575918197632, "global_step": 339789, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0896356105804443, "global_step": 339790, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076885938644409, "global_step": 339791, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0352365970611572, "global_step": 339792, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1171677112579346, "global_step": 339793, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0902650356292725, "global_step": 339794, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1002283096313477, "global_step": 339795, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2126352787017822, "global_step": 339796, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0793116092681885, "global_step": 339797, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0906143188476562, "global_step": 339798, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0778894424438477, "global_step": 339799, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0996525287628174, "global_step": 339800, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.136575698852539, "global_step": 339801, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.111175298690796, "global_step": 339802, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0641720294952393, "global_step": 339803, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1621291637420654, "global_step": 339804, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0808799266815186, "global_step": 339805, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0521814823150635, "global_step": 339806, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0828864574432373, "global_step": 339807, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1778452396392822, "global_step": 339808, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.005603551864624, "global_step": 339809, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079458236694336, "global_step": 339810, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9789397716522217, "global_step": 339811, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072446823120117, "global_step": 339812, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.101339817047119, "global_step": 339813, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044013261795044, "global_step": 339814, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1407077312469482, "global_step": 339815, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08725643157959, "global_step": 339816, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2117772102355957, "global_step": 339817, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.080198287963867, "global_step": 339818, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0318973064422607, "global_step": 339819, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.083148717880249, "global_step": 339820, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1024985313415527, "global_step": 339821, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.016101598739624, "global_step": 339822, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.181391716003418, "global_step": 339823, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1779654026031494, "global_step": 339824, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.04071307182312, "global_step": 339825, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.172358989715576, "global_step": 339826, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1175568103790283, "global_step": 339827, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1422061920166016, "global_step": 339828, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108642578125, "global_step": 339829, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1510868072509766, "global_step": 339830, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0605762004852295, "global_step": 339831, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1902284622192383, "global_step": 339832, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9727691411972046, "global_step": 339833, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1594913005828857, "global_step": 339834, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1340954303741455, "global_step": 339835, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1116154193878174, "global_step": 339836, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.048858165740967, "global_step": 339837, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1683168411254883, "global_step": 339838, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0234713554382324, "global_step": 339839, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.170989751815796, "global_step": 339840, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045469045639038, "global_step": 339841, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0568268299102783, "global_step": 339842, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9792821407318115, "global_step": 339843, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.078498601913452, "global_step": 339844, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1048498153686523, "global_step": 339845, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.113004207611084, "global_step": 339846, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.146975517272949, "global_step": 339847, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.025890588760376, "global_step": 339848, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1058948040008545, "global_step": 339849, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1026768684387207, "global_step": 339850, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0370006561279297, "global_step": 339851, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1012401580810547, "global_step": 339852, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.078620195388794, "global_step": 339853, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1229617595672607, "global_step": 339854, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.124411106109619, "global_step": 339855, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.132568597793579, "global_step": 339856, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0660581588745117, "global_step": 339857, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.042287826538086, "global_step": 339858, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1587960720062256, "global_step": 339859, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072897434234619, "global_step": 339860, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0726988315582275, "global_step": 339861, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2060060501098633, "global_step": 339862, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.148069143295288, "global_step": 339863, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.053943395614624, "global_step": 339864, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.004366159439087, "global_step": 339865, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1551008224487305, "global_step": 339866, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.118474006652832, "global_step": 339867, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.101518392562866, "global_step": 339868, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.070901393890381, "global_step": 339869, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0769026279449463, "global_step": 339870, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0330519676208496, "global_step": 339871, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0912530422210693, "global_step": 339872, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1113083362579346, "global_step": 339873, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.146672010421753, "global_step": 339874, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.114751100540161, "global_step": 339875, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079957962036133, "global_step": 339876, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.998262643814087, "global_step": 339877, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.135410785675049, "global_step": 339878, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1312060356140137, "global_step": 339879, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0644402503967285, "global_step": 339880, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9517161846160889, "global_step": 339881, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1212806701660156, "global_step": 339882, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1523232460021973, "global_step": 339883, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1140730381011963, "global_step": 339884, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1760141849517822, "global_step": 339885, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1324329376220703, "global_step": 339886, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0705509185791016, "global_step": 339887, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1982779502868652, "global_step": 339888, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.116014003753662, "global_step": 339889, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086559772491455, "global_step": 339890, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0893216133117676, "global_step": 339891, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.091207981109619, "global_step": 339892, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110018491744995, "global_step": 339893, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1368906497955322, "global_step": 339894, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.083853006362915, "global_step": 339895, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1450648307800293, "global_step": 339896, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.023102283477783, "global_step": 339897, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0799460411071777, "global_step": 339898, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1858034133911133, "global_step": 339899, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1486945152282715, "global_step": 339900, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1532320976257324, "global_step": 339901, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.101172924041748, "global_step": 339902, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.13430118560791, "global_step": 339903, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.165045976638794, "global_step": 339904, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1039769649505615, "global_step": 339905, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0659449100494385, "global_step": 339906, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0289065837860107, "global_step": 339907, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0574095249176025, "global_step": 339908, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1215686798095703, "global_step": 339909, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075228452682495, "global_step": 339910, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.11315655708313, "global_step": 339911, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9796714782714844, "global_step": 339912, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0626959800720215, "global_step": 339913, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.063603401184082, "global_step": 339914, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0667121410369873, "global_step": 339915, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.065650463104248, "global_step": 339916, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1437089443206787, "global_step": 339917, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0416486263275146, "global_step": 339918, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.061566114425659, "global_step": 339919, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.194228410720825, "global_step": 339920, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0398504734039307, "global_step": 339921, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1243834495544434, "global_step": 339922, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0735464096069336, "global_step": 339923, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.159975051879883, "global_step": 339924, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084994316101074, "global_step": 339925, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.138671875, "global_step": 339926, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.104490041732788, "global_step": 339927, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2002623081207275, "global_step": 339928, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0815682411193848, "global_step": 339929, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0927250385284424, "global_step": 339930, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2017972469329834, "global_step": 339931, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.130156993865967, "global_step": 339932, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.098203659057617, "global_step": 339933, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.242919921875, "global_step": 339934, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079106330871582, "global_step": 339935, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.047626495361328, "global_step": 339936, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0458338260650635, "global_step": 339937, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0643470287323, "global_step": 339938, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1151833534240723, "global_step": 339939, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.14699387550354, "global_step": 339940, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1432697772979736, "global_step": 339941, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.083653211593628, "global_step": 339942, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1575961112976074, "global_step": 339943, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.120039701461792, "global_step": 339944, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0341832637786865, "global_step": 339945, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1191720962524414, "global_step": 339946, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1193132400512695, "global_step": 339947, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.142240285873413, "global_step": 339948, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.148545742034912, "global_step": 339949, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.150378942489624, "global_step": 339950, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.028701066970825, "global_step": 339951, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1265738010406494, "global_step": 339952, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1060683727264404, "global_step": 339953, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1448562145233154, "global_step": 339954, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1264350414276123, "global_step": 339955, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.174537181854248, "global_step": 339956, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1091830730438232, "global_step": 339957, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.121504306793213, "global_step": 339958, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1449217796325684, "global_step": 339959, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1479544639587402, "global_step": 339960, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1997320652008057, "global_step": 339961, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.109504461288452, "global_step": 339962, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1336264610290527, "global_step": 339963, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9850060939788818, "global_step": 339964, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.996524453163147, "global_step": 339965, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1385951042175293, "global_step": 339966, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0969834327697754, "global_step": 339967, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122532606124878, "global_step": 339968, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.116635799407959, "global_step": 339969, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.185063123703003, "global_step": 339970, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100712537765503, "global_step": 339971, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.101644992828369, "global_step": 339972, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0462307929992676, "global_step": 339973, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1276562213897705, "global_step": 339974, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075531244277954, "global_step": 339975, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.11281156539917, "global_step": 339976, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.167928457260132, "global_step": 339977, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.163994550704956, "global_step": 339978, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.139697551727295, "global_step": 339979, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0912458896636963, "global_step": 339980, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0849499702453613, "global_step": 339981, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1715428829193115, "global_step": 339982, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2256717681884766, "global_step": 339983, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1135408878326416, "global_step": 339984, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0708649158477783, "global_step": 339985, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.024528980255127, "global_step": 339986, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1209685802459717, "global_step": 339987, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0775976181030273, "global_step": 339988, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0410308837890625, "global_step": 339989, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1262214183807373, "global_step": 339990, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0730526447296143, "global_step": 339991, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0853617191314697, "global_step": 339992, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.131938934326172, "global_step": 339993, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.129662036895752, "global_step": 339994, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0379815101623535, "global_step": 339995, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.263875722885132, "global_step": 339996, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1054155826568604, "global_step": 339997, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0441319942474365, "global_step": 339998, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1479568481445312, "global_step": 339999, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.114959955215454, "global_step": 340000, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.124314069747925, "global_step": 340001, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0920748710632324, "global_step": 340002, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110435962677002, "global_step": 340003, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.032362461090088, "global_step": 340004, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0520639419555664, "global_step": 340005, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.111380100250244, "global_step": 340006, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1630642414093018, "global_step": 340007, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.103039026260376, "global_step": 340008, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.015896797180176, "global_step": 340009, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0694990158081055, "global_step": 340010, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.102989435195923, "global_step": 340011, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.148728847503662, "global_step": 340012, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1069600582122803, "global_step": 340013, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1930294036865234, "global_step": 340014, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.090254545211792, "global_step": 340015, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9999134540557861, "global_step": 340016, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.143627643585205, "global_step": 340017, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.177522897720337, "global_step": 340018, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0914196968078613, "global_step": 340019, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.090460777282715, "global_step": 340020, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.111536741256714, "global_step": 340021, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.037363290786743, "global_step": 340022, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.06026029586792, "global_step": 340023, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.067626714706421, "global_step": 340024, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1114377975463867, "global_step": 340025, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0620620250701904, "global_step": 340026, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.039327621459961, "global_step": 340027, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072371006011963, "global_step": 340028, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2101922035217285, "global_step": 340029, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1235597133636475, "global_step": 340030, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.019286870956421, "global_step": 340031, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.120587110519409, "global_step": 340032, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.145202398300171, "global_step": 340033, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1087465286254883, "global_step": 340034, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.093026638031006, "global_step": 340035, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.065227746963501, "global_step": 340036, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.097973585128784, "global_step": 340037, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.197082281112671, "global_step": 340038, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0505499839782715, "global_step": 340039, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.093317985534668, "global_step": 340040, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.13057017326355, "global_step": 340041, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1339995861053467, "global_step": 340042, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0786590576171875, "global_step": 340043, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0414013862609863, "global_step": 340044, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.159008741378784, "global_step": 340045, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100632429122925, "global_step": 340046, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0942139625549316, "global_step": 340047, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.083441734313965, "global_step": 340048, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.074453353881836, "global_step": 340049, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9885989427566528, "global_step": 340050, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9937506914138794, "global_step": 340051, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1513209342956543, "global_step": 340052, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1541876792907715, "global_step": 340053, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0870792865753174, "global_step": 340054, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.107759475708008, "global_step": 340055, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0978567600250244, "global_step": 340056, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1758651733398438, "global_step": 340057, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134221076965332, "global_step": 340058, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1024324893951416, "global_step": 340059, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0585741996765137, "global_step": 340060, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0754120349884033, "global_step": 340061, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.171482563018799, "global_step": 340062, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.088714122772217, "global_step": 340063, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.169358253479004, "global_step": 340064, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0410869121551514, "global_step": 340065, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1337876319885254, "global_step": 340066, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1183583736419678, "global_step": 340067, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.16859769821167, "global_step": 340068, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2350010871887207, "global_step": 340069, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.041541814804077, "global_step": 340070, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.113473415374756, "global_step": 340071, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119494915008545, "global_step": 340072, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.113898515701294, "global_step": 340073, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1133954524993896, "global_step": 340074, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1294524669647217, "global_step": 340075, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0691165924072266, "global_step": 340076, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1001853942871094, "global_step": 340077, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0456528663635254, "global_step": 340078, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1504132747650146, "global_step": 340079, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1342103481292725, "global_step": 340080, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1276910305023193, "global_step": 340081, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1491103172302246, "global_step": 340082, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0894501209259033, "global_step": 340083, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075827121734619, "global_step": 340084, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1158864498138428, "global_step": 340085, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0840775966644287, "global_step": 340086, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1631479263305664, "global_step": 340087, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.127408504486084, "global_step": 340088, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.061713933944702, "global_step": 340089, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.080768346786499, "global_step": 340090, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0780386924743652, "global_step": 340091, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1054646968841553, "global_step": 340092, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0360143184661865, "global_step": 340093, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1452205181121826, "global_step": 340094, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.150838851928711, "global_step": 340095, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0208899974823, "global_step": 340096, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1719541549682617, "global_step": 340097, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122195243835449, "global_step": 340098, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.091641902923584, "global_step": 340099, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.104219913482666, "global_step": 340100, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.196709394454956, "global_step": 340101, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.182345390319824, "global_step": 340102, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085012197494507, "global_step": 340103, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.111729383468628, "global_step": 340104, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.16349458694458, "global_step": 340105, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1620519161224365, "global_step": 340106, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0546562671661377, "global_step": 340107, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0820915699005127, "global_step": 340108, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0321388244628906, "global_step": 340109, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0889673233032227, "global_step": 340110, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.046321153640747, "global_step": 340111, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045452356338501, "global_step": 340112, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089045763015747, "global_step": 340113, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10625958442688, "global_step": 340114, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.043954849243164, "global_step": 340115, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0944557189941406, "global_step": 340116, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1549582481384277, "global_step": 340117, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.195701837539673, "global_step": 340118, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1580233573913574, "global_step": 340119, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.078033924102783, "global_step": 340120, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.105231285095215, "global_step": 340121, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1795706748962402, "global_step": 340122, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.106536626815796, "global_step": 340123, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086348295211792, "global_step": 340124, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1075081825256348, "global_step": 340125, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.087075710296631, "global_step": 340126, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1626384258270264, "global_step": 340127, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.094907760620117, "global_step": 340128, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1134631633758545, "global_step": 340129, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0738089084625244, "global_step": 340130, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1093482971191406, "global_step": 340131, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.153381824493408, "global_step": 340132, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.163034677505493, "global_step": 340133, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.109729528427124, "global_step": 340134, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.168874502182007, "global_step": 340135, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.166897773742676, "global_step": 340136, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.172327995300293, "global_step": 340137, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1754419803619385, "global_step": 340138, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.068938732147217, "global_step": 340139, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0643134117126465, "global_step": 340140, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.074774980545044, "global_step": 340141, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075181245803833, "global_step": 340142, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.059889078140259, "global_step": 340143, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1974008083343506, "global_step": 340144, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0633957386016846, "global_step": 340145, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0727312564849854, "global_step": 340146, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.177569627761841, "global_step": 340147, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1813061237335205, "global_step": 340148, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.131948471069336, "global_step": 340149, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.06984281539917, "global_step": 340150, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1912684440612793, "global_step": 340151, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1376709938049316, "global_step": 340152, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.087484359741211, "global_step": 340153, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0456206798553467, "global_step": 340154, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1151580810546875, "global_step": 340155, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122605800628662, "global_step": 340156, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.061790943145752, "global_step": 340157, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1320900917053223, "global_step": 340158, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0963101387023926, "global_step": 340159, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079317808151245, "global_step": 340160, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1475892066955566, "global_step": 340161, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.12575101852417, "global_step": 340162, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0994391441345215, "global_step": 340163, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.101109743118286, "global_step": 340164, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.07580828666687, "global_step": 340165, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.188410758972168, "global_step": 340166, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147970199584961, "global_step": 340167, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1094534397125244, "global_step": 340168, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.007000207901001, "global_step": 340169, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08565354347229, "global_step": 340170, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1190030574798584, "global_step": 340171, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.037501811981201, "global_step": 340172, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1961934566497803, "global_step": 340173, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.129570960998535, "global_step": 340174, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.174774408340454, "global_step": 340175, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0154919624328613, "global_step": 340176, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2494094371795654, "global_step": 340177, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1589510440826416, "global_step": 340178, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0744473934173584, "global_step": 340179, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085991859436035, "global_step": 340180, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1003363132476807, "global_step": 340181, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.039996862411499, "global_step": 340182, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.150268316268921, "global_step": 340183, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.188844919204712, "global_step": 340184, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1866374015808105, "global_step": 340185, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0129973888397217, "global_step": 340186, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.126882791519165, "global_step": 340187, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.200216293334961, "global_step": 340188, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.174859046936035, "global_step": 340189, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.105053663253784, "global_step": 340190, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1774039268493652, "global_step": 340191, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1472232341766357, "global_step": 340192, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1597564220428467, "global_step": 340193, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0703611373901367, "global_step": 340194, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1003832817077637, "global_step": 340195, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.101616621017456, "global_step": 340196, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0971250534057617, "global_step": 340197, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.104034662246704, "global_step": 340198, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0127639770507812, "global_step": 340199, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.095243215560913, "global_step": 340200, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.046459197998047, "global_step": 340201, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1999688148498535, "global_step": 340202, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.11554217338562, "global_step": 340203, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0378081798553467, "global_step": 340204, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1857430934906006, "global_step": 340205, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.098217487335205, "global_step": 340206, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0720603466033936, "global_step": 340207, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045380115509033, "global_step": 340208, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.087435007095337, "global_step": 340209, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.136676788330078, "global_step": 340210, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1217803955078125, "global_step": 340211, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.07342791557312, "global_step": 340212, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1421990394592285, "global_step": 340213, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1590182781219482, "global_step": 340214, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.194180965423584, "global_step": 340215, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.198674440383911, "global_step": 340216, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0812230110168457, "global_step": 340217, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.16965913772583, "global_step": 340218, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0948615074157715, "global_step": 340219, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069575786590576, "global_step": 340220, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1506426334381104, "global_step": 340221, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1545522212982178, "global_step": 340222, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.037092447280884, "global_step": 340223, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.081416130065918, "global_step": 340224, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0713086128234863, "global_step": 340225, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0501954555511475, "global_step": 340226, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.186413526535034, "global_step": 340227, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.09769868850708, "global_step": 340228, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1164252758026123, "global_step": 340229, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1586101055145264, "global_step": 340230, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0794222354888916, "global_step": 340231, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.159999132156372, "global_step": 340232, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.121436595916748, "global_step": 340233, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.120595693588257, "global_step": 340234, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1579031944274902, "global_step": 340235, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.20733380317688, "global_step": 340236, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.16640305519104, "global_step": 340237, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.116140365600586, "global_step": 340238, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.172945499420166, "global_step": 340239, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0763700008392334, "global_step": 340240, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.082024574279785, "global_step": 340241, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.125515937805176, "global_step": 340242, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.038928508758545, "global_step": 340243, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054380178451538, "global_step": 340244, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076328992843628, "global_step": 340245, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.087833881378174, "global_step": 340246, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2026207447052, "global_step": 340247, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.05673885345459, "global_step": 340248, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.146683931350708, "global_step": 340249, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1480984687805176, "global_step": 340250, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0485665798187256, "global_step": 339283, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9896453619003296, "global_step": 339284, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1306519508361816, "global_step": 339285, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9753321409225464, "global_step": 339286, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.146601915359497, "global_step": 339287, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9777610301971436, "global_step": 339288, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9712287187576294, "global_step": 339289, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.098813056945801, "global_step": 339290, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0551528930664062, "global_step": 339291, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1010398864746094, "global_step": 339292, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1259896755218506, "global_step": 339293, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0202717781066895, "global_step": 339294, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1771929264068604, "global_step": 339295, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1131210327148438, "global_step": 339296, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0553102493286133, "global_step": 339297, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.064401388168335, "global_step": 339298, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0242700576782227, "global_step": 339299, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.067237377166748, "global_step": 339300, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0751535892486572, "global_step": 339301, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0449259281158447, "global_step": 339302, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.036698341369629, "global_step": 339303, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0693373680114746, "global_step": 339304, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.172116756439209, "global_step": 339305, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122246265411377, "global_step": 339306, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0277678966522217, "global_step": 339307, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0457451343536377, "global_step": 339308, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.042569398880005, "global_step": 339309, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.03287410736084, "global_step": 339310, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079775094985962, "global_step": 339311, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.088555097579956, "global_step": 339312, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.002408742904663, "global_step": 339313, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0726540088653564, "global_step": 339314, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1228585243225098, "global_step": 339315, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1125316619873047, "global_step": 339316, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110628366470337, "global_step": 339317, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123108386993408, "global_step": 339318, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.017609119415283, "global_step": 339319, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.026709794998169, "global_step": 339320, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.125274419784546, "global_step": 339321, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0516316890716553, "global_step": 339322, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.060992479324341, "global_step": 339323, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.050985813140869, "global_step": 339324, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.154315948486328, "global_step": 339325, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1616439819335938, "global_step": 339326, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0879697799682617, "global_step": 339327, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045787811279297, "global_step": 339328, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0130302906036377, "global_step": 339329, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1199135780334473, "global_step": 339330, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0815770626068115, "global_step": 339331, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0924558639526367, "global_step": 339332, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069244861602783, "global_step": 339333, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147076368331909, "global_step": 339334, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0895752906799316, "global_step": 339335, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0043256282806396, "global_step": 339336, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.049968957901001, "global_step": 339337, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.197038412094116, "global_step": 339338, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.051194906234741, "global_step": 339339, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110083818435669, "global_step": 339340, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0590295791625977, "global_step": 339341, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.081517457962036, "global_step": 339342, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108527421951294, "global_step": 339343, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.131065845489502, "global_step": 339344, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0813651084899902, "global_step": 339345, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0546061992645264, "global_step": 339346, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0340070724487305, "global_step": 339347, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.021608829498291, "global_step": 339348, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.093010663986206, "global_step": 339349, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1022558212280273, "global_step": 339350, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0695786476135254, "global_step": 339351, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0993213653564453, "global_step": 339352, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0790114402770996, "global_step": 339353, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1382758617401123, "global_step": 339354, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0741593837738037, "global_step": 339355, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1077609062194824, "global_step": 339356, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0383315086364746, "global_step": 339357, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0826852321624756, "global_step": 339358, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0735373497009277, "global_step": 339359, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1648106575012207, "global_step": 339360, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.006643295288086, "global_step": 339361, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084385395050049, "global_step": 339362, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9908332824707031, "global_step": 339363, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1344807147979736, "global_step": 339364, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0872766971588135, "global_step": 339365, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0588810443878174, "global_step": 339366, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.121746301651001, "global_step": 339367, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0599212646484375, "global_step": 339368, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0555660724639893, "global_step": 339369, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0852344036102295, "global_step": 339370, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0074586868286133, "global_step": 339371, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119032144546509, "global_step": 339372, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1494803428649902, "global_step": 339373, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0464043617248535, "global_step": 339374, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1714909076690674, "global_step": 339375, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0429372787475586, "global_step": 339376, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.026092052459717, "global_step": 339377, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147245168685913, "global_step": 339378, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2425432205200195, "global_step": 339379, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.029243230819702, "global_step": 339380, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.99801504611969, "global_step": 339381, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085798501968384, "global_step": 339382, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.989738941192627, "global_step": 339383, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0267279148101807, "global_step": 339384, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0523006916046143, "global_step": 339385, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0992257595062256, "global_step": 339386, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.070779800415039, "global_step": 339387, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.138089179992676, "global_step": 339388, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1213505268096924, "global_step": 339389, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.129891872406006, "global_step": 339390, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0675888061523438, "global_step": 339391, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1041760444641113, "global_step": 339392, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.099273920059204, "global_step": 339393, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.07145094871521, "global_step": 339394, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0439107418060303, "global_step": 339395, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0326285362243652, "global_step": 339396, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1257717609405518, "global_step": 339397, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.230848550796509, "global_step": 339398, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.205181121826172, "global_step": 339399, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.048597812652588, "global_step": 339400, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0802149772644043, "global_step": 339401, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1783320903778076, "global_step": 339402, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1303369998931885, "global_step": 339403, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.140986442565918, "global_step": 339404, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.196638345718384, "global_step": 339405, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055729866027832, "global_step": 339406, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1447057723999023, "global_step": 339407, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0482025146484375, "global_step": 339408, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.031877040863037, "global_step": 339409, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0709187984466553, "global_step": 339410, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0471725463867188, "global_step": 339411, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0333776473999023, "global_step": 339412, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.107372522354126, "global_step": 339413, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1461663246154785, "global_step": 339414, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1025073528289795, "global_step": 339415, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0641794204711914, "global_step": 339416, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084399461746216, "global_step": 339417, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.06817626953125, "global_step": 339418, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.044386386871338, "global_step": 339419, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0636353492736816, "global_step": 339420, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0522706508636475, "global_step": 339421, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0410475730895996, "global_step": 339422, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0864810943603516, "global_step": 339423, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072129726409912, "global_step": 339424, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1355674266815186, "global_step": 339425, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.157041072845459, "global_step": 339426, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.087836503982544, "global_step": 339427, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0653491020202637, "global_step": 339428, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1435434818267822, "global_step": 339429, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1026968955993652, "global_step": 339430, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1398680210113525, "global_step": 339431, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1101696491241455, "global_step": 339432, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0454154014587402, "global_step": 339433, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.11139178276062, "global_step": 339434, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.130143165588379, "global_step": 339435, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0559144020080566, "global_step": 339436, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123532772064209, "global_step": 339437, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1473796367645264, "global_step": 339438, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.093691349029541, "global_step": 339439, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.183547258377075, "global_step": 339440, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.053838014602661, "global_step": 339441, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084892988204956, "global_step": 339442, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1826629638671875, "global_step": 339443, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.002544641494751, "global_step": 339444, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.03141713142395, "global_step": 339445, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0862083435058594, "global_step": 339446, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0269651412963867, "global_step": 339447, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.033581495285034, "global_step": 339448, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.135192394256592, "global_step": 339449, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1076464653015137, "global_step": 339450, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1016061305999756, "global_step": 339451, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0674288272857666, "global_step": 339452, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1245245933532715, "global_step": 339453, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9910166263580322, "global_step": 339454, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.059257745742798, "global_step": 339455, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0764243602752686, "global_step": 339456, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0331435203552246, "global_step": 339457, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.039558172225952, "global_step": 339458, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089806079864502, "global_step": 339459, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0091538429260254, "global_step": 339460, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1016337871551514, "global_step": 339461, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0695431232452393, "global_step": 339462, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0240564346313477, "global_step": 339463, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1291778087615967, "global_step": 339464, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1155107021331787, "global_step": 339465, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076627016067505, "global_step": 339466, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0833892822265625, "global_step": 339467, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108067274093628, "global_step": 339468, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.070803642272949, "global_step": 339469, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1213297843933105, "global_step": 339470, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1142590045928955, "global_step": 339471, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069223642349243, "global_step": 339472, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.219012975692749, "global_step": 339473, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.021557569503784, "global_step": 339474, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1450207233428955, "global_step": 339475, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.149589776992798, "global_step": 339476, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1812493801116943, "global_step": 339477, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0588016510009766, "global_step": 339478, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.136997938156128, "global_step": 339479, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0473146438598633, "global_step": 339480, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1527113914489746, "global_step": 339481, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0567426681518555, "global_step": 339482, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.040287494659424, "global_step": 339483, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0990097522735596, "global_step": 339484, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0194449424743652, "global_step": 339485, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9465601444244385, "global_step": 339486, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0875191688537598, "global_step": 339487, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0581774711608887, "global_step": 339488, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.034372329711914, "global_step": 339489, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.056462287902832, "global_step": 339490, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0687203407287598, "global_step": 339491, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.029169797897339, "global_step": 339492, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9585423469543457, "global_step": 339493, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.21401047706604, "global_step": 339494, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1346547603607178, "global_step": 339495, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.154468297958374, "global_step": 339496, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0878372192382812, "global_step": 339497, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134063959121704, "global_step": 339498, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.12080454826355, "global_step": 339499, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0397870540618896, "global_step": 339500, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0851736068725586, "global_step": 339501, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0641191005706787, "global_step": 339502, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1105093955993652, "global_step": 339503, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1198923587799072, "global_step": 339504, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0753531455993652, "global_step": 339505, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08048939704895, "global_step": 339506, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085064172744751, "global_step": 339507, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.061692237854004, "global_step": 339508, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.126394748687744, "global_step": 339509, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1123087406158447, "global_step": 339510, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1438498497009277, "global_step": 339511, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1569480895996094, "global_step": 339512, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0898427963256836, "global_step": 339513, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.155975818634033, "global_step": 339514, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.083529472351074, "global_step": 339515, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085796356201172, "global_step": 339516, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.05497407913208, "global_step": 339517, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076792001724243, "global_step": 339518, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0790345668792725, "global_step": 339519, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0954151153564453, "global_step": 339520, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1174235343933105, "global_step": 339521, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0247435569763184, "global_step": 339522, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1111361980438232, "global_step": 339523, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.00579833984375, "global_step": 339524, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119382858276367, "global_step": 339525, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0723555088043213, "global_step": 339526, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.141324520111084, "global_step": 339527, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.126145839691162, "global_step": 339528, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1465003490448, "global_step": 339529, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.074932098388672, "global_step": 339530, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0146806240081787, "global_step": 339531, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.129135847091675, "global_step": 339532, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.120091438293457, "global_step": 339533, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0738918781280518, "global_step": 339534, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1857223510742188, "global_step": 339535, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123591899871826, "global_step": 339536, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0689375400543213, "global_step": 339537, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.150670289993286, "global_step": 339538, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.088824510574341, "global_step": 339539, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1239426136016846, "global_step": 339540, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.090449571609497, "global_step": 339541, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.106989622116089, "global_step": 339542, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0635128021240234, "global_step": 339543, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075434684753418, "global_step": 339544, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0967652797698975, "global_step": 339545, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.997117519378662, "global_step": 339546, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0998177528381348, "global_step": 339547, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.022139549255371, "global_step": 339548, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10665225982666, "global_step": 339549, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1634414196014404, "global_step": 339550, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.127246141433716, "global_step": 339551, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0555810928344727, "global_step": 339552, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0052764415740967, "global_step": 339553, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108656167984009, "global_step": 339554, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.050708055496216, "global_step": 339555, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054189682006836, "global_step": 339556, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.020491123199463, "global_step": 339557, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.088172197341919, "global_step": 339558, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054149866104126, "global_step": 339559, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0498905181884766, "global_step": 339560, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0763230323791504, "global_step": 339561, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.142829656600952, "global_step": 339562, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1153171062469482, "global_step": 339563, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.125505208969116, "global_step": 339564, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112258195877075, "global_step": 339565, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.137686014175415, "global_step": 339566, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110692024230957, "global_step": 339567, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9993480443954468, "global_step": 339568, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1332128047943115, "global_step": 339569, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1688432693481445, "global_step": 339570, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.137629508972168, "global_step": 339571, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.099311113357544, "global_step": 339572, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0877883434295654, "global_step": 339573, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.103649377822876, "global_step": 339574, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1815764904022217, "global_step": 339575, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.024048089981079, "global_step": 339576, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.095240592956543, "global_step": 339577, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.989578366279602, "global_step": 339578, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9831387996673584, "global_step": 339579, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0540428161621094, "global_step": 339580, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119694232940674, "global_step": 339581, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0623204708099365, "global_step": 339582, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1710591316223145, "global_step": 339583, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1291158199310303, "global_step": 339584, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0130555629730225, "global_step": 339585, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.133582830429077, "global_step": 339586, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0795750617980957, "global_step": 339587, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.048013925552368, "global_step": 339588, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1085169315338135, "global_step": 339589, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.068467617034912, "global_step": 339590, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1296942234039307, "global_step": 339591, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0771517753601074, "global_step": 339592, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1168711185455322, "global_step": 339593, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0505924224853516, "global_step": 339594, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0132434368133545, "global_step": 339595, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0539724826812744, "global_step": 339596, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112279176712036, "global_step": 339597, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0827724933624268, "global_step": 339598, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0335538387298584, "global_step": 339599, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0996856689453125, "global_step": 339600, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1482772827148438, "global_step": 339601, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1492533683776855, "global_step": 339602, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075662851333618, "global_step": 339603, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.14447021484375, "global_step": 339604, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.034879684448242, "global_step": 339605, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.104017734527588, "global_step": 339606, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0701026916503906, "global_step": 339607, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0690340995788574, "global_step": 339608, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0935561656951904, "global_step": 339609, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1074891090393066, "global_step": 339610, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0321006774902344, "global_step": 339611, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.067195177078247, "global_step": 339612, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0843775272369385, "global_step": 339613, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0619566440582275, "global_step": 339614, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0566582679748535, "global_step": 339615, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.098073959350586, "global_step": 339616, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.124791145324707, "global_step": 339617, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.019007444381714, "global_step": 339618, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045833110809326, "global_step": 339619, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1006855964660645, "global_step": 339620, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100644111633301, "global_step": 339621, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.039341449737549, "global_step": 339622, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.111267328262329, "global_step": 339623, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1267969608306885, "global_step": 339624, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0917844772338867, "global_step": 339625, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.169525146484375, "global_step": 339626, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1172661781311035, "global_step": 339627, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1341826915740967, "global_step": 339628, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1310667991638184, "global_step": 339629, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1131179332733154, "global_step": 339630, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1239521503448486, "global_step": 339631, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.182922840118408, "global_step": 339632, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076230764389038, "global_step": 339633, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0852882862091064, "global_step": 339634, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.147129774093628, "global_step": 339635, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0955538749694824, "global_step": 339636, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1134252548217773, "global_step": 339637, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.056729793548584, "global_step": 339638, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.046225070953369, "global_step": 339639, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.138895273208618, "global_step": 339640, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1256773471832275, "global_step": 339641, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.000391960144043, "global_step": 339642, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.109711170196533, "global_step": 339643, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.052164077758789, "global_step": 339644, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.155641794204712, "global_step": 339645, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.188852548599243, "global_step": 339646, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.178612470626831, "global_step": 339647, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0894086360931396, "global_step": 339648, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.179809331893921, "global_step": 339649, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.092409133911133, "global_step": 339650, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1246988773345947, "global_step": 339651, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9843169450759888, "global_step": 339652, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0630664825439453, "global_step": 339653, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0484468936920166, "global_step": 339654, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.059002637863159, "global_step": 339655, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0871362686157227, "global_step": 339656, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.036432981491089, "global_step": 339657, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1410601139068604, "global_step": 339658, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9543544054031372, "global_step": 339659, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1082682609558105, "global_step": 339660, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0712478160858154, "global_step": 339661, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.128725290298462, "global_step": 339662, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0867700576782227, "global_step": 339663, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0399553775787354, "global_step": 339664, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.127596855163574, "global_step": 339665, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.065152645111084, "global_step": 339666, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1166305541992188, "global_step": 339667, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1222097873687744, "global_step": 339668, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.195507526397705, "global_step": 339669, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.081240653991699, "global_step": 339670, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0385420322418213, "global_step": 339671, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.163804292678833, "global_step": 339672, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1351823806762695, "global_step": 339673, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.103313446044922, "global_step": 339674, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1903235912323, "global_step": 339675, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.062513828277588, "global_step": 339676, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.083775043487549, "global_step": 339677, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0109057426452637, "global_step": 339678, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.046124219894409, "global_step": 339679, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108651638031006, "global_step": 339680, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1397392749786377, "global_step": 339681, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.068898916244507, "global_step": 339682, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0542993545532227, "global_step": 339683, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0916404724121094, "global_step": 339684, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1111955642700195, "global_step": 339685, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1095340251922607, "global_step": 339686, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.194915771484375, "global_step": 339687, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076383113861084, "global_step": 339688, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0564041137695312, "global_step": 339689, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0601305961608887, "global_step": 339690, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134697437286377, "global_step": 339691, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.198338270187378, "global_step": 339692, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1146585941314697, "global_step": 339693, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.16613507270813, "global_step": 339694, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.006901979446411, "global_step": 339695, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054980993270874, "global_step": 339696, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1339163780212402, "global_step": 339697, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1278915405273438, "global_step": 339698, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112245798110962, "global_step": 339699, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.127215623855591, "global_step": 339700, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054706573486328, "global_step": 339701, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0595712661743164, "global_step": 339702, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1398003101348877, "global_step": 339703, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0375473499298096, "global_step": 339704, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072927474975586, "global_step": 339705, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.121865749359131, "global_step": 339706, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1034059524536133, "global_step": 339707, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1492021083831787, "global_step": 339708, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.11879563331604, "global_step": 339709, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1078481674194336, "global_step": 339710, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089212417602539, "global_step": 339711, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.05145001411438, "global_step": 339712, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055046558380127, "global_step": 339713, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9545921087265015, "global_step": 339714, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0801570415496826, "global_step": 339715, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.155269145965576, "global_step": 339716, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.036699056625366, "global_step": 339717, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.101790189743042, "global_step": 339718, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1245079040527344, "global_step": 339719, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.08756947517395, "global_step": 339720, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.160527229309082, "global_step": 339721, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072676658630371, "global_step": 339722, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100698709487915, "global_step": 339723, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1075363159179688, "global_step": 339724, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.205770254135132, "global_step": 339725, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2274553775787354, "global_step": 339726, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.073636531829834, "global_step": 339727, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.008911609649658, "global_step": 339728, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.145789384841919, "global_step": 339729, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.055875539779663, "global_step": 339730, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0414278507232666, "global_step": 339731, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1304032802581787, "global_step": 339732, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.077721357345581, "global_step": 339733, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0458810329437256, "global_step": 339734, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0658671855926514, "global_step": 339735, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1404404640197754, "global_step": 339736, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0484724044799805, "global_step": 339737, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0492987632751465, "global_step": 339738, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1375763416290283, "global_step": 339739, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1487159729003906, "global_step": 339740, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.127962827682495, "global_step": 339741, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1796562671661377, "global_step": 339742, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0300369262695312, "global_step": 339743, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1189980506896973, "global_step": 339744, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2042579650878906, "global_step": 339745, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1231508255004883, "global_step": 339746, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.18034029006958, "global_step": 339747, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054569959640503, "global_step": 339748, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.040943145751953, "global_step": 339749, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0627074241638184, "global_step": 339750, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1977791786193848, "global_step": 339751, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1075000762939453, "global_step": 339752, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.099327325820923, "global_step": 339753, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1163158416748047, "global_step": 339754, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1054913997650146, "global_step": 339755, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.054309129714966, "global_step": 339756, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0622398853302, "global_step": 339757, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076209783554077, "global_step": 339758, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9646940231323242, "global_step": 339759, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.114593982696533, "global_step": 339760, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.028812885284424, "global_step": 339761, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.083115577697754, "global_step": 339762, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.04394793510437, "global_step": 339763, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1298983097076416, "global_step": 339764, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108213424682617, "global_step": 339765, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9478527307510376, "global_step": 339766, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0500576496124268, "global_step": 339767, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0505661964416504, "global_step": 339768, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.166813850402832, "global_step": 339769, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.050337314605713, "global_step": 339770, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.150481700897217, "global_step": 339771, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.100925922393799, "global_step": 339772, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134688138961792, "global_step": 339773, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.183410406112671, "global_step": 339774, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0863070487976074, "global_step": 339775, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1772546768188477, "global_step": 339776, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0604515075683594, "global_step": 339777, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1329755783081055, "global_step": 339778, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.081246852874756, "global_step": 339779, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2249958515167236, "global_step": 339780, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.069211483001709, "global_step": 339781, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0176384449005127, "global_step": 339782, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.051731586456299, "global_step": 339783, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1301746368408203, "global_step": 339784, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.12530779838562, "global_step": 339785, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.041745662689209, "global_step": 339786, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1554293632507324, "global_step": 339787, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1143460273742676, "global_step": 339788, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1541128158569336, "global_step": 339789, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0894854068756104, "global_step": 339790, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0744805335998535, "global_step": 339791, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0349183082580566, "global_step": 339792, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1185896396636963, "global_step": 339793, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0899171829223633, "global_step": 339794, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.101830005645752, "global_step": 339795, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2140727043151855, "global_step": 339796, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079876184463501, "global_step": 339797, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0870919227600098, "global_step": 339798, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079406976699829, "global_step": 339799, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1000022888183594, "global_step": 339800, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1358261108398438, "global_step": 339801, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1087961196899414, "global_step": 339802, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.064695119857788, "global_step": 339803, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1600775718688965, "global_step": 339804, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.081890344619751, "global_step": 339805, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.050717830657959, "global_step": 339806, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.083420753479004, "global_step": 339807, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.176460027694702, "global_step": 339808, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0031538009643555, "global_step": 339809, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0800554752349854, "global_step": 339810, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.976682186126709, "global_step": 339811, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.074118137359619, "global_step": 339812, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1004014015197754, "global_step": 339813, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.043318271636963, "global_step": 339814, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1418633460998535, "global_step": 339815, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085087299346924, "global_step": 339816, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.21148681640625, "global_step": 339817, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.080101728439331, "global_step": 339818, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0306029319763184, "global_step": 339819, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0827600955963135, "global_step": 339820, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1020054817199707, "global_step": 339821, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.017080068588257, "global_step": 339822, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.181633472442627, "global_step": 339823, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1757636070251465, "global_step": 339824, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0404791831970215, "global_step": 339825, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1740057468414307, "global_step": 339826, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.115401029586792, "global_step": 339827, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.141523838043213, "global_step": 339828, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.106321096420288, "global_step": 339829, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1501834392547607, "global_step": 339830, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0580246448516846, "global_step": 339831, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.188047170639038, "global_step": 339832, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9727100133895874, "global_step": 339833, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1581883430480957, "global_step": 339834, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134023904800415, "global_step": 339835, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1117944717407227, "global_step": 339836, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0489213466644287, "global_step": 339837, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.166741371154785, "global_step": 339838, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.02268385887146, "global_step": 339839, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1732046604156494, "global_step": 339840, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0470478534698486, "global_step": 339841, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0565719604492188, "global_step": 339842, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9790394306182861, "global_step": 339843, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0774621963500977, "global_step": 339844, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1039116382598877, "global_step": 339845, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.113091468811035, "global_step": 339846, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.145426034927368, "global_step": 339847, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0237231254577637, "global_step": 339848, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1044886112213135, "global_step": 339849, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1015546321868896, "global_step": 339850, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0375280380249023, "global_step": 339851, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1008834838867188, "global_step": 339852, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0780107975006104, "global_step": 339853, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1229941844940186, "global_step": 339854, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1240787506103516, "global_step": 339855, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134495735168457, "global_step": 339856, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0672662258148193, "global_step": 339857, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.04232120513916, "global_step": 339858, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.158222198486328, "global_step": 339859, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0722835063934326, "global_step": 339860, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0727171897888184, "global_step": 339861, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2037765979766846, "global_step": 339862, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1488723754882812, "global_step": 339863, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.053938150405884, "global_step": 339864, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0062782764434814, "global_step": 339865, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.153470993041992, "global_step": 339866, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1169209480285645, "global_step": 339867, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1019978523254395, "global_step": 339868, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0700156688690186, "global_step": 339869, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.07576584815979, "global_step": 339870, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0334017276763916, "global_step": 339871, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0899250507354736, "global_step": 339872, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1103758811950684, "global_step": 339873, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1479332447052, "global_step": 339874, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.114138126373291, "global_step": 339875, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0804483890533447, "global_step": 339876, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.998059630393982, "global_step": 339877, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.136500120162964, "global_step": 339878, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1300156116485596, "global_step": 339879, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0650715827941895, "global_step": 339880, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9537149667739868, "global_step": 339881, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1208791732788086, "global_step": 339882, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1544060707092285, "global_step": 339883, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.114290714263916, "global_step": 339884, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.174006938934326, "global_step": 339885, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.133420705795288, "global_step": 339886, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0704891681671143, "global_step": 339887, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1979312896728516, "global_step": 339888, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1179165840148926, "global_step": 339889, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0858094692230225, "global_step": 339890, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0878472328186035, "global_step": 339891, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089860677719116, "global_step": 339892, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110274314880371, "global_step": 339893, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.137803077697754, "global_step": 339894, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.085033893585205, "global_step": 339895, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1431291103363037, "global_step": 339896, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0225648880004883, "global_step": 339897, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.078099012374878, "global_step": 339898, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.187084913253784, "global_step": 339899, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.148524522781372, "global_step": 339900, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1513752937316895, "global_step": 339901, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1022400856018066, "global_step": 339902, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134436845779419, "global_step": 339903, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.165137529373169, "global_step": 339904, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1060662269592285, "global_step": 339905, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.065277099609375, "global_step": 339906, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0271213054656982, "global_step": 339907, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0580496788024902, "global_step": 339908, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.12216854095459, "global_step": 339909, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.079056739807129, "global_step": 339910, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1142611503601074, "global_step": 339911, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9791451692581177, "global_step": 339912, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0618882179260254, "global_step": 339913, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.064443349838257, "global_step": 339914, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0650110244750977, "global_step": 339915, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.065946102142334, "global_step": 339916, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1441597938537598, "global_step": 339917, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0408222675323486, "global_step": 339918, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.061724901199341, "global_step": 339919, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1931581497192383, "global_step": 339920, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.038923740386963, "global_step": 339921, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122833728790283, "global_step": 339922, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.074169635772705, "global_step": 339923, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1600120067596436, "global_step": 339924, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0852248668670654, "global_step": 339925, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1396780014038086, "global_step": 339926, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10488224029541, "global_step": 339927, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1996641159057617, "global_step": 339928, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0793237686157227, "global_step": 339929, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.093258857727051, "global_step": 339930, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2025465965270996, "global_step": 339931, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.129925012588501, "global_step": 339932, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0976688861846924, "global_step": 339933, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2409369945526123, "global_step": 339934, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.082155466079712, "global_step": 339935, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0473875999450684, "global_step": 339936, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0476503372192383, "global_step": 339937, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.062270402908325, "global_step": 339938, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1158623695373535, "global_step": 339939, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1472980976104736, "global_step": 339940, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1450881958007812, "global_step": 339941, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0858380794525146, "global_step": 339942, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.154977798461914, "global_step": 339943, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.12092924118042, "global_step": 339944, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.036396026611328, "global_step": 339945, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1224122047424316, "global_step": 339946, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1185152530670166, "global_step": 339947, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1416661739349365, "global_step": 339948, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.14921498298645, "global_step": 339949, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1479923725128174, "global_step": 339950, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0311806201934814, "global_step": 339951, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.126941442489624, "global_step": 339952, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1055619716644287, "global_step": 339953, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.143669366836548, "global_step": 339954, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1280977725982666, "global_step": 339955, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.172760486602783, "global_step": 339956, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1109845638275146, "global_step": 339957, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.123126983642578, "global_step": 339958, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1455626487731934, "global_step": 339959, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.148392915725708, "global_step": 339960, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.199328899383545, "global_step": 339961, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1114730834960938, "global_step": 339962, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.134486198425293, "global_step": 339963, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9860150814056396, "global_step": 339964, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.996095061302185, "global_step": 339965, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1391615867614746, "global_step": 339966, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.097658395767212, "global_step": 339967, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1228368282318115, "global_step": 339968, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.11721134185791, "global_step": 339969, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.185112714767456, "global_step": 339970, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.098625659942627, "global_step": 339971, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0999879837036133, "global_step": 339972, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045361042022705, "global_step": 339973, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1289222240448, "global_step": 339974, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076320171356201, "global_step": 339975, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1127219200134277, "global_step": 339976, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1678900718688965, "global_step": 339977, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.162637233734131, "global_step": 339978, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.140127420425415, "global_step": 339979, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.091132879257202, "global_step": 339980, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.087170124053955, "global_step": 339981, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1691136360168457, "global_step": 339982, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.225226402282715, "global_step": 339983, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112896203994751, "global_step": 339984, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0712907314300537, "global_step": 339985, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0232644081115723, "global_step": 339986, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.119709014892578, "global_step": 339987, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0783040523529053, "global_step": 339988, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0388023853302, "global_step": 339989, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.128081798553467, "global_step": 339990, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072852373123169, "global_step": 339991, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086945056915283, "global_step": 339992, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.130521535873413, "global_step": 339993, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1276776790618896, "global_step": 339994, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0401086807250977, "global_step": 339995, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2628707885742188, "global_step": 339996, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1042613983154297, "global_step": 339997, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.041666269302368, "global_step": 339998, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1484642028808594, "global_step": 339999, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1139988899230957, "global_step": 340000, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.12392258644104, "global_step": 340001, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0923895835876465, "global_step": 340002, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1097359657287598, "global_step": 340003, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.031911849975586, "global_step": 340004, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.052633762359619, "global_step": 340005, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.11091685295105, "global_step": 340006, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1638617515563965, "global_step": 340007, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1031267642974854, "global_step": 340008, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0133209228515625, "global_step": 340009, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0695629119873047, "global_step": 340010, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1024351119995117, "global_step": 340011, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1492562294006348, "global_step": 340012, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1083984375, "global_step": 340013, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.192354917526245, "global_step": 340014, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0913238525390625, "global_step": 340015, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0030517578125, "global_step": 340016, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.144364595413208, "global_step": 340017, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.175588369369507, "global_step": 340018, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0905025005340576, "global_step": 340019, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0906057357788086, "global_step": 340020, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1111247539520264, "global_step": 340021, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0387887954711914, "global_step": 340022, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0603041648864746, "global_step": 340023, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.068570613861084, "global_step": 340024, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110684394836426, "global_step": 340025, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0623061656951904, "global_step": 340026, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0379467010498047, "global_step": 340027, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.071274995803833, "global_step": 340028, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.210597515106201, "global_step": 340029, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.121551275253296, "global_step": 340030, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0190112590789795, "global_step": 340031, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.12076735496521, "global_step": 340032, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1447436809539795, "global_step": 340033, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.11079478263855, "global_step": 340034, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0951414108276367, "global_step": 340035, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0639772415161133, "global_step": 340036, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.096834897994995, "global_step": 340037, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.199483633041382, "global_step": 340038, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.053368091583252, "global_step": 340039, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0926480293273926, "global_step": 340040, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1302013397216797, "global_step": 340041, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.131042718887329, "global_step": 340042, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.078444004058838, "global_step": 340043, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0423014163970947, "global_step": 340044, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.158971071243286, "global_step": 340045, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1000993251800537, "global_step": 340046, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.094360589981079, "global_step": 340047, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0861284732818604, "global_step": 340048, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.072601556777954, "global_step": 340049, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9871153831481934, "global_step": 340050, "epoch": 700, "lr": 5e-05}
{"train_loss": 1.9948736429214478, "global_step": 340051, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.150813579559326, "global_step": 340052, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1543960571289062, "global_step": 340053, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.087554693222046, "global_step": 340054, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1080472469329834, "global_step": 340055, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0929830074310303, "global_step": 340056, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.174901247024536, "global_step": 340057, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1348578929901123, "global_step": 340058, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1036274433135986, "global_step": 340059, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0576670169830322, "global_step": 340060, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.074136734008789, "global_step": 340061, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1698062419891357, "global_step": 340062, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.087592601776123, "global_step": 340063, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.168208122253418, "global_step": 340064, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.042520523071289, "global_step": 340065, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.131998062133789, "global_step": 340066, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1180906295776367, "global_step": 340067, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1702303886413574, "global_step": 340068, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.233849048614502, "global_step": 340069, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0431745052337646, "global_step": 340070, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.113105297088623, "global_step": 340071, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1202797889709473, "global_step": 340072, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.110351800918579, "global_step": 340073, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.112480640411377, "global_step": 340074, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.129288911819458, "global_step": 340075, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0690836906433105, "global_step": 340076, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.099297046661377, "global_step": 340077, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.046823740005493, "global_step": 340078, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.152156352996826, "global_step": 340079, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1326301097869873, "global_step": 340080, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.128619432449341, "global_step": 340081, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1466009616851807, "global_step": 340082, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0891833305358887, "global_step": 340083, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.077402114868164, "global_step": 340084, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1181797981262207, "global_step": 340085, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0845863819122314, "global_step": 340086, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1647212505340576, "global_step": 340087, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1274495124816895, "global_step": 340088, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.061548948287964, "global_step": 340089, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0816617012023926, "global_step": 340090, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0777440071105957, "global_step": 340091, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1054744720458984, "global_step": 340092, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.037658452987671, "global_step": 340093, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1449053287506104, "global_step": 340094, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.148528575897217, "global_step": 340095, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0192363262176514, "global_step": 340096, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1707422733306885, "global_step": 340097, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1234006881713867, "global_step": 340098, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.089648962020874, "global_step": 340099, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1026699542999268, "global_step": 340100, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.194243907928467, "global_step": 340101, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.180453062057495, "global_step": 340102, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0845022201538086, "global_step": 340103, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.109426975250244, "global_step": 340104, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.163092851638794, "global_step": 340105, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.157878875732422, "global_step": 340106, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0541834831237793, "global_step": 340107, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0825254917144775, "global_step": 340108, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.032808303833008, "global_step": 340109, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0892882347106934, "global_step": 340110, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.045755386352539, "global_step": 340111, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0471339225769043, "global_step": 340112, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0888991355895996, "global_step": 340113, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10618257522583, "global_step": 340114, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0431888103485107, "global_step": 340115, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0950891971588135, "global_step": 340116, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.155576229095459, "global_step": 340117, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.194143772125244, "global_step": 340118, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1585159301757812, "global_step": 340119, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0762546062469482, "global_step": 340120, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1065919399261475, "global_step": 340121, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1801114082336426, "global_step": 340122, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1069207191467285, "global_step": 340123, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0842514038085938, "global_step": 340124, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.108351707458496, "global_step": 340125, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.084827184677124, "global_step": 340126, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1616477966308594, "global_step": 340127, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.094163417816162, "global_step": 340128, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1143958568573, "global_step": 340129, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0731451511383057, "global_step": 340130, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1101438999176025, "global_step": 340131, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1527228355407715, "global_step": 340132, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.164656639099121, "global_step": 340133, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.11091947555542, "global_step": 340134, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.167371988296509, "global_step": 340135, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.16741943359375, "global_step": 340136, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1735920906066895, "global_step": 340137, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1751415729522705, "global_step": 340138, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0712897777557373, "global_step": 340139, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0646862983703613, "global_step": 340140, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0760934352874756, "global_step": 340141, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0768344402313232, "global_step": 340142, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.061331033706665, "global_step": 340143, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1969079971313477, "global_step": 340144, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.063204526901245, "global_step": 340145, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.073228120803833, "global_step": 340146, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1774039268493652, "global_step": 340147, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.183516502380371, "global_step": 340148, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1299421787261963, "global_step": 340149, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.071201801300049, "global_step": 340150, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.193120002746582, "global_step": 340151, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1397409439086914, "global_step": 340152, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086801767349243, "global_step": 340153, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0460517406463623, "global_step": 340154, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1160776615142822, "global_step": 340155, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1256067752838135, "global_step": 340156, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.064544677734375, "global_step": 340157, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1324710845947266, "global_step": 340158, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.096012830734253, "global_step": 340159, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0777554512023926, "global_step": 340160, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1458849906921387, "global_step": 340161, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.12505841255188, "global_step": 340162, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1010220050811768, "global_step": 340163, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1003808975219727, "global_step": 340164, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.07479190826416, "global_step": 340165, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1884796619415283, "global_step": 340166, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1467444896698, "global_step": 340167, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1052138805389404, "global_step": 340168, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.006655216217041, "global_step": 340169, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.086092233657837, "global_step": 340170, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1168925762176514, "global_step": 340171, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0380125045776367, "global_step": 340172, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.199477195739746, "global_step": 340173, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1286919116973877, "global_step": 340174, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1733169555664062, "global_step": 340175, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0176010131835938, "global_step": 340176, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2486746311187744, "global_step": 340177, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.160630702972412, "global_step": 340178, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0739850997924805, "global_step": 340179, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.087158679962158, "global_step": 340180, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1012630462646484, "global_step": 340181, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.038419723510742, "global_step": 340182, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1524040699005127, "global_step": 340183, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.187258005142212, "global_step": 340184, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1898224353790283, "global_step": 340185, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0132713317871094, "global_step": 340186, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.125497817993164, "global_step": 340187, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2009167671203613, "global_step": 340188, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1758005619049072, "global_step": 340189, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1037492752075195, "global_step": 340190, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.175961971282959, "global_step": 340191, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.145709753036499, "global_step": 340192, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.157426595687866, "global_step": 340193, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0693657398223877, "global_step": 340194, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.099853515625, "global_step": 340195, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.102315902709961, "global_step": 340196, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0975189208984375, "global_step": 340197, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.10532808303833, "global_step": 340198, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.012981414794922, "global_step": 340199, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0964291095733643, "global_step": 340200, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0450258255004883, "global_step": 340201, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.199425220489502, "global_step": 340202, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1142663955688477, "global_step": 340203, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.03926682472229, "global_step": 340204, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1853761672973633, "global_step": 340205, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.094661235809326, "global_step": 340206, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.075681686401367, "global_step": 340207, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0445780754089355, "global_step": 340208, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0846915245056152, "global_step": 340209, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.137805461883545, "global_step": 340210, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.122400999069214, "global_step": 340211, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0746099948883057, "global_step": 340212, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1412606239318848, "global_step": 340213, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.158855438232422, "global_step": 340214, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.19339656829834, "global_step": 340215, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2019119262695312, "global_step": 340216, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.082080841064453, "global_step": 340217, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1710784435272217, "global_step": 340218, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0951595306396484, "global_step": 340219, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0712478160858154, "global_step": 340220, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1512162685394287, "global_step": 340221, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1580796241760254, "global_step": 340222, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.035771369934082, "global_step": 340223, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0802106857299805, "global_step": 340224, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0723938941955566, "global_step": 340225, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.053230047225952, "global_step": 340226, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.188873291015625, "global_step": 340227, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.09846568107605, "global_step": 340228, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.118386745452881, "global_step": 340229, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.158992290496826, "global_step": 340230, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.081099271774292, "global_step": 340231, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.160010576248169, "global_step": 340232, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.121016502380371, "global_step": 340233, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1200008392333984, "global_step": 340234, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1585991382598877, "global_step": 340235, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.2079718112945557, "global_step": 340236, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.168055772781372, "global_step": 340237, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1178927421569824, "global_step": 340238, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.174604654312134, "global_step": 340239, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.076807975769043, "global_step": 340240, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0828702449798584, "global_step": 340241, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1239774227142334, "global_step": 340242, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0413055419921875, "global_step": 340243, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0525894165039062, "global_step": 340244, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0787971019744873, "global_step": 340245, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0899136066436768, "global_step": 340246, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.20355486869812, "global_step": 340247, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0564470291137695, "global_step": 340248, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.148571252822876, "global_step": 340249, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.1491522789001465, "global_step": 340250, "epoch": 700, "lr": 5e-05}
{"train_loss": 2.0982589721679688, "global_step": 340251, "epoch": 700, "lr": 5e-05, "KITCHEN_SCENE6_put_the_yellow_and_white_mug_in_the_microwave_and_close_it/mean_success_rate": 0.7333333333333333, "LIVING_ROOM_SCENE2_put_both_the_alphabet_soup_and_the_tomato_sauce_in_the_basket/mean_success_rate": 0.0, "STUDY_SCENE1_pick_up_the_book_and_place_it_in_the_back_compartment_of_the_caddy/mean_success_rate": 0.5333333333333333, "KITCHEN_SCENE8_put_both_moka_pots_on_the_stove/mean_success_rate": 0.36666666666666664, "LIVING_ROOM_SCENE5_put_the_white_mug_on_the_left_plate_and_put_the_yellow_and_white_mug_on_the_right_plate/mean_success_rate": 0.43333333333333335, "LIVING_ROOM_SCENE6_put_the_white_mug_on_the_plate_and_put_the_chocolate_pudding_to_the_right_of_the_plate/mean_success_rate": 0.3333333333333333, "KITCHEN_SCENE4_put_the_black_bowl_in_the_bottom_drawer_of_the_cabinet_and_close_it/mean_success_rate": 0.9333333333333333, "LIVING_ROOM_SCENE2_put_both_the_cream_cheese_box_and_the_butter_in_the_basket/mean_success_rate": 0.43333333333333335, "LIVING_ROOM_SCENE1_put_both_the_alphabet_soup_and_the_cream_cheese_box_in_the_basket/mean_success_rate": 0.0, "KITCHEN_SCENE3_turn_on_the_stove_and_put_the_moka_pot_on_it/mean_success_rate": 0.7666666666666667, "mean_success_rate": 0.4533333333333333, "val_loss": 5.767025470733643, "test_reconst_mse": 0.07282733172178268}
{"train_loss": 2.0658621788024902, "global_step": 340252, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1264710426330566, "global_step": 340253, "epoch": 701, "lr": 5e-05}
{"train_loss": 1.9745686054229736, "global_step": 340254, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1302661895751953, "global_step": 340255, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.089512348175049, "global_step": 340256, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.03440260887146, "global_step": 340257, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.030841827392578, "global_step": 340258, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1965017318725586, "global_step": 340259, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0819168090820312, "global_step": 340260, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.131049871444702, "global_step": 340261, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0794548988342285, "global_step": 340262, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1476502418518066, "global_step": 340263, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.058983087539673, "global_step": 340264, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.10760498046875, "global_step": 340265, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0518434047698975, "global_step": 340266, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1102077960968018, "global_step": 340267, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.053380012512207, "global_step": 340268, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0930869579315186, "global_step": 340269, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0299630165100098, "global_step": 340270, "epoch": 701, "lr": 5e-05}
{"train_loss": 1.9762777090072632, "global_step": 340271, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.131443977355957, "global_step": 340272, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0693118572235107, "global_step": 340273, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1039013862609863, "global_step": 340274, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1408631801605225, "global_step": 340275, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1192948818206787, "global_step": 340276, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1425318717956543, "global_step": 340277, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.113072395324707, "global_step": 340278, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.089576482772827, "global_step": 340279, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.077481269836426, "global_step": 340280, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.004749298095703, "global_step": 340281, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.080230236053467, "global_step": 340282, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1601462364196777, "global_step": 340283, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1415538787841797, "global_step": 340284, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.023585319519043, "global_step": 340285, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0703704357147217, "global_step": 340286, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0817625522613525, "global_step": 340287, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0175797939300537, "global_step": 340288, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0737853050231934, "global_step": 340289, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1257731914520264, "global_step": 340290, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1404287815093994, "global_step": 340291, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0007028579711914, "global_step": 340292, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1639904975891113, "global_step": 340293, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.098224401473999, "global_step": 340294, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.053739070892334, "global_step": 340295, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0803306102752686, "global_step": 340296, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.057446002960205, "global_step": 340297, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0303804874420166, "global_step": 340298, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.119352340698242, "global_step": 340299, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0995657444000244, "global_step": 340300, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0312788486480713, "global_step": 340301, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1453819274902344, "global_step": 340302, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0595929622650146, "global_step": 340303, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.136803388595581, "global_step": 340304, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0804929733276367, "global_step": 340305, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1510443687438965, "global_step": 340306, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.028155565261841, "global_step": 340307, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.116884469985962, "global_step": 340308, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1517271995544434, "global_step": 340309, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0620765686035156, "global_step": 340310, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.055874824523926, "global_step": 340311, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.069875717163086, "global_step": 340312, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.062736749649048, "global_step": 340313, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.053658962249756, "global_step": 340314, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0620319843292236, "global_step": 340315, "epoch": 701, "lr": 5e-05}
{"train_loss": 1.9939433336257935, "global_step": 340316, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.058476209640503, "global_step": 340317, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1795544624328613, "global_step": 340318, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1211018562316895, "global_step": 340319, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1074113845825195, "global_step": 340320, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.107975959777832, "global_step": 340321, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.005120277404785, "global_step": 340322, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0557610988616943, "global_step": 340323, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.004031181335449, "global_step": 340324, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.069814682006836, "global_step": 340325, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1658811569213867, "global_step": 340326, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1192970275878906, "global_step": 340327, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1662166118621826, "global_step": 340328, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.223172187805176, "global_step": 340329, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.063032388687134, "global_step": 340330, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0205209255218506, "global_step": 340331, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.090149164199829, "global_step": 340332, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.163022994995117, "global_step": 340333, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0694549083709717, "global_step": 340334, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.071760892868042, "global_step": 340335, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.103386878967285, "global_step": 340336, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.064868211746216, "global_step": 340337, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.065098285675049, "global_step": 340338, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1280782222747803, "global_step": 340339, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0516743659973145, "global_step": 340340, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0832817554473877, "global_step": 340341, "epoch": 701, "lr": 5e-05}
{"train_loss": 1.9953289031982422, "global_step": 340342, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.018803119659424, "global_step": 340343, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.147461414337158, "global_step": 340344, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0671215057373047, "global_step": 340345, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0477240085601807, "global_step": 340346, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0686445236206055, "global_step": 340347, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1071860790252686, "global_step": 340348, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.055049419403076, "global_step": 340349, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.132084846496582, "global_step": 340350, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0863378047943115, "global_step": 340351, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1114649772644043, "global_step": 340352, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0244266986846924, "global_step": 340353, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1262054443359375, "global_step": 340354, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1468002796173096, "global_step": 340355, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0462138652801514, "global_step": 340356, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.109619140625, "global_step": 340357, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.123501777648926, "global_step": 340358, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0890092849731445, "global_step": 340359, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.125746488571167, "global_step": 340360, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0230369567871094, "global_step": 340361, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0630204677581787, "global_step": 340362, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.118107557296753, "global_step": 340363, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.074164628982544, "global_step": 340364, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.114290714263916, "global_step": 340365, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0975868701934814, "global_step": 340366, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0400314331054688, "global_step": 340367, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1002089977264404, "global_step": 340368, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.118971824645996, "global_step": 340369, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.213665246963501, "global_step": 340370, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1187644004821777, "global_step": 340371, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.063000202178955, "global_step": 340372, "epoch": 701, "lr": 5e-05}
{"train_loss": 1.9618051052093506, "global_step": 340373, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.116164207458496, "global_step": 340374, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0645241737365723, "global_step": 340375, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1120026111602783, "global_step": 340376, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1107239723205566, "global_step": 340377, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0981688499450684, "global_step": 340378, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.060624837875366, "global_step": 340379, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0234920978546143, "global_step": 340380, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1850931644439697, "global_step": 340381, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0994653701782227, "global_step": 340382, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.083812952041626, "global_step": 340383, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.117898941040039, "global_step": 340384, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1366775035858154, "global_step": 340385, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1278727054595947, "global_step": 340386, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.06689190864563, "global_step": 340387, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1018645763397217, "global_step": 340388, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1353940963745117, "global_step": 340389, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1046667098999023, "global_step": 340390, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.126321792602539, "global_step": 340391, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.112786293029785, "global_step": 340392, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0103836059570312, "global_step": 340393, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.041660785675049, "global_step": 340394, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0886824131011963, "global_step": 340395, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0958547592163086, "global_step": 340396, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0412774085998535, "global_step": 340397, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.040682792663574, "global_step": 340398, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1269471645355225, "global_step": 340399, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.081016778945923, "global_step": 340400, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.137176990509033, "global_step": 340401, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1303813457489014, "global_step": 340402, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.128565788269043, "global_step": 340403, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0641746520996094, "global_step": 340404, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1208608150482178, "global_step": 340405, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0570318698883057, "global_step": 340406, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0741188526153564, "global_step": 340407, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.114954710006714, "global_step": 340408, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.074876070022583, "global_step": 340409, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.100721597671509, "global_step": 340410, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.044309616088867, "global_step": 340411, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1364524364471436, "global_step": 340412, "epoch": 701, "lr": 5e-05}
{"train_loss": 1.9883601665496826, "global_step": 340413, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0921053886413574, "global_step": 340414, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1316864490509033, "global_step": 340415, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0950334072113037, "global_step": 340416, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1002793312072754, "global_step": 340417, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.093137502670288, "global_step": 340418, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.066497564315796, "global_step": 340419, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0740599632263184, "global_step": 340420, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0219383239746094, "global_step": 340421, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.182086706161499, "global_step": 340422, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.186469793319702, "global_step": 340423, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.080289602279663, "global_step": 340424, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.026251792907715, "global_step": 340425, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.2622618675231934, "global_step": 340426, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.090912342071533, "global_step": 340427, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.074506998062134, "global_step": 340428, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.119079351425171, "global_step": 340429, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.099392890930176, "global_step": 340430, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1705422401428223, "global_step": 340431, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.027001142501831, "global_step": 340432, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.043142795562744, "global_step": 340433, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1952455043792725, "global_step": 340434, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.125209331512451, "global_step": 340435, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0543015003204346, "global_step": 340436, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0686886310577393, "global_step": 340437, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.082698345184326, "global_step": 340438, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.157468795776367, "global_step": 340439, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.158494472503662, "global_step": 340440, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0681233406066895, "global_step": 340441, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0853469371795654, "global_step": 340442, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.064598798751831, "global_step": 340443, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1093485355377197, "global_step": 340444, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1105029582977295, "global_step": 340445, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.019500494003296, "global_step": 340446, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.067795515060425, "global_step": 340447, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.189565896987915, "global_step": 340448, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.140718698501587, "global_step": 340449, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1467835903167725, "global_step": 340450, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1196093559265137, "global_step": 340451, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.149812936782837, "global_step": 340452, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.126340627670288, "global_step": 340453, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0834736824035645, "global_step": 340454, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0688815116882324, "global_step": 340455, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.030256509780884, "global_step": 340456, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.107658624649048, "global_step": 340457, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1559596061706543, "global_step": 340458, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.137892246246338, "global_step": 340459, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.066709518432617, "global_step": 340460, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.089871883392334, "global_step": 340461, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.2049248218536377, "global_step": 340462, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.060434341430664, "global_step": 340463, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1356778144836426, "global_step": 340464, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1211204528808594, "global_step": 340465, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1378226280212402, "global_step": 340466, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0505778789520264, "global_step": 340467, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0701632499694824, "global_step": 340468, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1136701107025146, "global_step": 340469, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.08512020111084, "global_step": 340470, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1412851810455322, "global_step": 340471, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0915846824645996, "global_step": 340472, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0775673389434814, "global_step": 340473, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.096405029296875, "global_step": 340474, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0959584712982178, "global_step": 340475, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.006577253341675, "global_step": 340476, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1663851737976074, "global_step": 340477, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1513538360595703, "global_step": 340478, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.097905158996582, "global_step": 340479, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.17414927482605, "global_step": 340480, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0644116401672363, "global_step": 340481, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.129551649093628, "global_step": 340482, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.146477460861206, "global_step": 340483, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1495790481567383, "global_step": 340484, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.010308027267456, "global_step": 340485, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.093212127685547, "global_step": 340486, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.040548086166382, "global_step": 340487, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.182779312133789, "global_step": 340488, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.149366855621338, "global_step": 340489, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0787177085876465, "global_step": 340490, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1600818634033203, "global_step": 340491, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.01385235786438, "global_step": 340492, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.156839370727539, "global_step": 340493, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.158186435699463, "global_step": 340494, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.125485897064209, "global_step": 340495, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.099764108657837, "global_step": 340496, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.065547466278076, "global_step": 340497, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.031785011291504, "global_step": 340498, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.040407419204712, "global_step": 340499, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1548900604248047, "global_step": 340500, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1107077598571777, "global_step": 340501, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.15765118598938, "global_step": 340502, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.04085373878479, "global_step": 340503, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.071531057357788, "global_step": 340504, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0996651649475098, "global_step": 340505, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.074960947036743, "global_step": 340506, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.049764633178711, "global_step": 340507, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0193746089935303, "global_step": 340508, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0902886390686035, "global_step": 340509, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.126678228378296, "global_step": 340510, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1056392192840576, "global_step": 340511, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0705058574676514, "global_step": 340512, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0777394771575928, "global_step": 340513, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.074251651763916, "global_step": 340514, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1289920806884766, "global_step": 340515, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.021772623062134, "global_step": 340516, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0997912883758545, "global_step": 340517, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.108839750289917, "global_step": 340518, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.165660858154297, "global_step": 340519, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.037860631942749, "global_step": 340520, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.081954002380371, "global_step": 340521, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1639902591705322, "global_step": 340522, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.060678720474243, "global_step": 340523, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1103508472442627, "global_step": 340524, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.087549924850464, "global_step": 340525, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.147132158279419, "global_step": 340526, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.212942123413086, "global_step": 340527, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1353275775909424, "global_step": 340528, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.087050676345825, "global_step": 340529, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.086183547973633, "global_step": 340530, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.073627233505249, "global_step": 340531, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1244709491729736, "global_step": 340532, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0458807945251465, "global_step": 340533, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0284719467163086, "global_step": 340534, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1187021732330322, "global_step": 340535, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0903069972991943, "global_step": 340536, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1779427528381348, "global_step": 340537, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1665873527526855, "global_step": 340538, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1036243438720703, "global_step": 340539, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.2066831588745117, "global_step": 340540, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0800061225891113, "global_step": 340541, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0834531784057617, "global_step": 340542, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.101609468460083, "global_step": 340543, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.078495502471924, "global_step": 340544, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.108832359313965, "global_step": 340545, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.108596086502075, "global_step": 340546, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1113810539245605, "global_step": 340547, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1907386779785156, "global_step": 340548, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.091275691986084, "global_step": 340549, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.153822898864746, "global_step": 340550, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.077300786972046, "global_step": 340551, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.206284523010254, "global_step": 340552, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1413350105285645, "global_step": 340553, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0778799057006836, "global_step": 340554, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.133624315261841, "global_step": 340555, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1185050010681152, "global_step": 340556, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.050873041152954, "global_step": 340557, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.127676010131836, "global_step": 340558, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1467607021331787, "global_step": 340559, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1333556175231934, "global_step": 340560, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.192699432373047, "global_step": 340561, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.132911443710327, "global_step": 340562, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.130011558532715, "global_step": 340563, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.15889835357666, "global_step": 340564, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.183203935623169, "global_step": 340565, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.066915512084961, "global_step": 340566, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.123187780380249, "global_step": 340567, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.065403938293457, "global_step": 340568, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1641621589660645, "global_step": 340569, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0569779872894287, "global_step": 340570, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.066180467605591, "global_step": 340571, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.097296953201294, "global_step": 340572, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0846898555755615, "global_step": 340573, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1615540981292725, "global_step": 340574, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.048089027404785, "global_step": 340575, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.099132776260376, "global_step": 340576, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0955376625061035, "global_step": 340577, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0280423164367676, "global_step": 340578, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0849826335906982, "global_step": 340579, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0472066402435303, "global_step": 340580, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.036720037460327, "global_step": 340581, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.145315170288086, "global_step": 340582, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1097471714019775, "global_step": 340583, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.061567544937134, "global_step": 340584, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.135183334350586, "global_step": 340585, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0272042751312256, "global_step": 340586, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.134349822998047, "global_step": 340587, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.033559560775757, "global_step": 340588, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0705831050872803, "global_step": 340589, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.030965805053711, "global_step": 340590, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1612277030944824, "global_step": 340591, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.138209819793701, "global_step": 340592, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1651971340179443, "global_step": 340593, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0959439277648926, "global_step": 340594, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0375428199768066, "global_step": 340595, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.118349313735962, "global_step": 340596, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0058677196502686, "global_step": 340597, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1601710319519043, "global_step": 340598, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1365673542022705, "global_step": 340599, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1025383472442627, "global_step": 340600, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0527913570404053, "global_step": 340601, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0444841384887695, "global_step": 340602, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.043013334274292, "global_step": 340603, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.166393995285034, "global_step": 340604, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0576090812683105, "global_step": 340605, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.110349655151367, "global_step": 340606, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.088709831237793, "global_step": 340607, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.129194974899292, "global_step": 340608, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.043780565261841, "global_step": 340609, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.086667537689209, "global_step": 340610, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0439693927764893, "global_step": 340611, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0873844623565674, "global_step": 340612, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0901665687561035, "global_step": 340613, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.129265308380127, "global_step": 340614, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0725886821746826, "global_step": 340615, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.187218189239502, "global_step": 340616, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.111604928970337, "global_step": 340617, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.140018939971924, "global_step": 340618, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0668413639068604, "global_step": 340619, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1280062198638916, "global_step": 340620, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.076542615890503, "global_step": 340621, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.06868314743042, "global_step": 340622, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0471415519714355, "global_step": 340623, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1100125312805176, "global_step": 340624, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0560190677642822, "global_step": 340625, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0852222442626953, "global_step": 340626, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.096097230911255, "global_step": 340627, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.161262273788452, "global_step": 340628, "epoch": 701, "lr": 5e-05}
{"train_loss": 1.986513614654541, "global_step": 340629, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0976035594940186, "global_step": 340630, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.14644455909729, "global_step": 340631, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1525888442993164, "global_step": 340632, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.102806568145752, "global_step": 340633, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.149028778076172, "global_step": 340634, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0510034561157227, "global_step": 340635, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0409739017486572, "global_step": 340636, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.113929271697998, "global_step": 340637, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0800278186798096, "global_step": 340638, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1293249130249023, "global_step": 340639, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.084322929382324, "global_step": 340640, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.093458890914917, "global_step": 340641, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1424577236175537, "global_step": 340642, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.136207342147827, "global_step": 340643, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1273791790008545, "global_step": 340644, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1730852127075195, "global_step": 340645, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0653629302978516, "global_step": 340646, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.094449758529663, "global_step": 340647, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1240530014038086, "global_step": 340648, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.187700033187866, "global_step": 340649, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.124865770339966, "global_step": 340650, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.116129159927368, "global_step": 340651, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.212613582611084, "global_step": 340652, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0495524406433105, "global_step": 340653, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1572442054748535, "global_step": 340654, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.133033037185669, "global_step": 340655, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1064658164978027, "global_step": 340656, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1162421703338623, "global_step": 340657, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0734264850616455, "global_step": 340658, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1186938285827637, "global_step": 340659, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0145928859710693, "global_step": 340660, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1504039764404297, "global_step": 340661, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.2039902210235596, "global_step": 340662, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1016311645507812, "global_step": 340663, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1243109703063965, "global_step": 340664, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1079728603363037, "global_step": 340665, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0844554901123047, "global_step": 340666, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.146024703979492, "global_step": 340667, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1115994453430176, "global_step": 340668, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1038527488708496, "global_step": 340669, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.076139450073242, "global_step": 340670, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1261327266693115, "global_step": 340671, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.029080629348755, "global_step": 340672, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1374025344848633, "global_step": 340673, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0296401977539062, "global_step": 340674, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0752217769622803, "global_step": 340675, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0374596118927, "global_step": 340676, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.081489086151123, "global_step": 340677, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.052536725997925, "global_step": 340678, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1096978187561035, "global_step": 340679, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0300304889678955, "global_step": 340680, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.137643814086914, "global_step": 340681, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1853299140930176, "global_step": 340682, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.005891799926758, "global_step": 340683, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0574417114257812, "global_step": 340684, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0177693367004395, "global_step": 340685, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.126376152038574, "global_step": 340686, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0976133346557617, "global_step": 340687, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1591837406158447, "global_step": 340688, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0802388191223145, "global_step": 340689, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0615458488464355, "global_step": 340690, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.100027322769165, "global_step": 340691, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.169050693511963, "global_step": 340692, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0949008464813232, "global_step": 340693, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.084113121032715, "global_step": 340694, "epoch": 701, "lr": 5e-05}
{"train_loss": 1.9804209470748901, "global_step": 340695, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0995235443115234, "global_step": 340696, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1000173091888428, "global_step": 340697, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1310341358184814, "global_step": 340698, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0581793785095215, "global_step": 340699, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.050382375717163, "global_step": 340700, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0639305114746094, "global_step": 340701, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1793630123138428, "global_step": 340702, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.136183500289917, "global_step": 340703, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1812753677368164, "global_step": 340704, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0956029891967773, "global_step": 340705, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0969173908233643, "global_step": 340706, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.007253408432007, "global_step": 340707, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.147052526473999, "global_step": 340708, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.08300518989563, "global_step": 340709, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0650556087493896, "global_step": 340710, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.034075975418091, "global_step": 340711, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.004002571105957, "global_step": 340712, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.015469551086426, "global_step": 340713, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1655468940734863, "global_step": 340714, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0810322761535645, "global_step": 340715, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.056215286254883, "global_step": 340716, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.110889434814453, "global_step": 340717, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1850311756134033, "global_step": 340718, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0530238151550293, "global_step": 340719, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0226612091064453, "global_step": 340720, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0450048446655273, "global_step": 340721, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1286237239837646, "global_step": 340722, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1301825046539307, "global_step": 340723, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0659091472625732, "global_step": 340724, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1206977367401123, "global_step": 340725, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0592868328094482, "global_step": 340726, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.08893084526062, "global_step": 340727, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1253366470336914, "global_step": 340728, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0375893115997314, "global_step": 340729, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1284546852111816, "global_step": 340730, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1412055492401123, "global_step": 340731, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.103757381439209, "global_step": 340732, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0955779552459717, "global_step": 340733, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1022279262542725, "global_step": 340734, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0032806396484375, "global_step": 340735, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.014066457748413, "global_step": 340736, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0677847862243652, "global_step": 340737, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0415303707122803, "global_step": 340738, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.068675994873047, "global_step": 340739, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0771307945251465, "global_step": 340740, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0933024883270264, "global_step": 340741, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.006324052810669, "global_step": 340742, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.13421368598938, "global_step": 340743, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.107539176940918, "global_step": 340744, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.100337266921997, "global_step": 340745, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1167614459991455, "global_step": 340746, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0790212154388428, "global_step": 340747, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.2198686599731445, "global_step": 340748, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0919289588928223, "global_step": 340749, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1231775283813477, "global_step": 340750, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0833091735839844, "global_step": 340751, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.053816795349121, "global_step": 340752, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1299026012420654, "global_step": 340753, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.141796588897705, "global_step": 340754, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.060567855834961, "global_step": 340755, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.102883815765381, "global_step": 340756, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0018954277038574, "global_step": 340757, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1627249717712402, "global_step": 340758, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1712052822113037, "global_step": 340759, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.073814630508423, "global_step": 340760, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0903828144073486, "global_step": 340761, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.216914176940918, "global_step": 340762, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.127140760421753, "global_step": 340763, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.046438217163086, "global_step": 340764, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1001687049865723, "global_step": 340765, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.095562219619751, "global_step": 340766, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1122500896453857, "global_step": 340767, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1295299530029297, "global_step": 340768, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.064086437225342, "global_step": 340769, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.175534725189209, "global_step": 340770, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1527624130249023, "global_step": 340771, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1189358234405518, "global_step": 340772, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1246137619018555, "global_step": 340773, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.129695177078247, "global_step": 340774, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1137850284576416, "global_step": 340775, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.135453224182129, "global_step": 340776, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1672275066375732, "global_step": 340777, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.203455686569214, "global_step": 340778, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.090985059738159, "global_step": 340779, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.065972328186035, "global_step": 340780, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1387860774993896, "global_step": 340781, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.192873001098633, "global_step": 340782, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0461621284484863, "global_step": 340783, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1106410026550293, "global_step": 340784, "epoch": 701, "lr": 5e-05}
{"train_loss": 1.9885549545288086, "global_step": 340785, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0531551837921143, "global_step": 340786, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.2033979892730713, "global_step": 340787, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.142782688140869, "global_step": 340788, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.076500654220581, "global_step": 340789, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1359918117523193, "global_step": 340790, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.020688772201538, "global_step": 340791, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.05653977394104, "global_step": 340792, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0535740852355957, "global_step": 340793, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.122201442718506, "global_step": 340794, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.071719169616699, "global_step": 340795, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.102147102355957, "global_step": 340796, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0116078853607178, "global_step": 340797, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.09335994720459, "global_step": 340798, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.10189151763916, "global_step": 340799, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0846807956695557, "global_step": 340800, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.139432668685913, "global_step": 340801, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0916807651519775, "global_step": 340802, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1289005279541016, "global_step": 340803, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.158240556716919, "global_step": 340804, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.163179397583008, "global_step": 340805, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.066603660583496, "global_step": 340806, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.124952793121338, "global_step": 340807, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0486907958984375, "global_step": 340808, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.098947286605835, "global_step": 340809, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1774895191192627, "global_step": 340810, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.164778709411621, "global_step": 340811, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1421730518341064, "global_step": 340812, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.116000175476074, "global_step": 340813, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0997979640960693, "global_step": 340814, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.151987314224243, "global_step": 340815, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.03238844871521, "global_step": 340816, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1817731857299805, "global_step": 340817, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.174975633621216, "global_step": 340818, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.138425350189209, "global_step": 340819, "epoch": 701, "lr": 5e-05}
{"train_loss": 1.9941805601119995, "global_step": 340820, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1279327869415283, "global_step": 340821, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0666003227233887, "global_step": 340822, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.107910633087158, "global_step": 340823, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.090841054916382, "global_step": 340824, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.099487066268921, "global_step": 340825, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1870760917663574, "global_step": 340826, "epoch": 701, "lr": 5e-05}
{"train_loss": 1.9632906913757324, "global_step": 340827, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.035545587539673, "global_step": 340828, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.125560998916626, "global_step": 340829, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0820796489715576, "global_step": 340830, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.135878086090088, "global_step": 340831, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1002442836761475, "global_step": 340832, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0708508491516113, "global_step": 340833, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.094611644744873, "global_step": 340834, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1002931594848633, "global_step": 340835, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1110963821411133, "global_step": 340836, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1300320625305176, "global_step": 340837, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.04604172706604, "global_step": 340838, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.112302303314209, "global_step": 340839, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.028770923614502, "global_step": 340840, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1031107902526855, "global_step": 340841, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1105964183807373, "global_step": 340842, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1318321228027344, "global_step": 340843, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.107546091079712, "global_step": 340844, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.150602102279663, "global_step": 340845, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0269882678985596, "global_step": 340846, "epoch": 701, "lr": 5e-05}
{"train_loss": 1.9914194345474243, "global_step": 340847, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1125776767730713, "global_step": 340848, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0491344928741455, "global_step": 340849, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0956411361694336, "global_step": 340850, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1133649349212646, "global_step": 340851, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.136234760284424, "global_step": 340852, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0529286861419678, "global_step": 340853, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0429954528808594, "global_step": 340854, "epoch": 701, "lr": 5e-05}
{"train_loss": 1.9784939289093018, "global_step": 340855, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.123217821121216, "global_step": 340856, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1351006031036377, "global_step": 340857, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1813247203826904, "global_step": 340858, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.171004295349121, "global_step": 340859, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.233854055404663, "global_step": 340860, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.000952959060669, "global_step": 340861, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1561179161071777, "global_step": 340862, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0638651847839355, "global_step": 340863, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.120509624481201, "global_step": 340864, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.097421407699585, "global_step": 340865, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1613128185272217, "global_step": 340866, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.215197801589966, "global_step": 340867, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0215187072753906, "global_step": 340868, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1457128524780273, "global_step": 340869, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1697349548339844, "global_step": 340870, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.145805835723877, "global_step": 340871, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.132091522216797, "global_step": 340872, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1404120922088623, "global_step": 340873, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1169352531433105, "global_step": 340874, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.086693048477173, "global_step": 340875, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.114935874938965, "global_step": 340876, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.031393527984619, "global_step": 340877, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1225857734680176, "global_step": 340878, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0886082649230957, "global_step": 340879, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0633177757263184, "global_step": 340880, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1588268280029297, "global_step": 340881, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.083470344543457, "global_step": 340882, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1463260650634766, "global_step": 340883, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0530683994293213, "global_step": 340884, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0730319023132324, "global_step": 340885, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1284501552581787, "global_step": 340886, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.198897123336792, "global_step": 340887, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1375620365142822, "global_step": 340888, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.137742519378662, "global_step": 340889, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0775554180145264, "global_step": 340890, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.122633457183838, "global_step": 340891, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.143054246902466, "global_step": 340892, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.090008020401001, "global_step": 340893, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.178070545196533, "global_step": 340894, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1076462268829346, "global_step": 340895, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1150155067443848, "global_step": 340896, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1632509231567383, "global_step": 340897, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1101107597351074, "global_step": 340898, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.166595697402954, "global_step": 340899, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.144243001937866, "global_step": 340900, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1101667881011963, "global_step": 340901, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.098963499069214, "global_step": 340902, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1536598205566406, "global_step": 340903, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.147320508956909, "global_step": 340904, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0433857440948486, "global_step": 340905, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.2071750164031982, "global_step": 340906, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1401190757751465, "global_step": 340907, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.077197313308716, "global_step": 340908, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0697803497314453, "global_step": 340909, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.180558919906616, "global_step": 340910, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1602981090545654, "global_step": 340911, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.191600799560547, "global_step": 340912, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.066286087036133, "global_step": 340913, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1125645637512207, "global_step": 340914, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1012556552886963, "global_step": 340915, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1665313243865967, "global_step": 340916, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.131898880004883, "global_step": 340917, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1460611820220947, "global_step": 340918, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0802769660949707, "global_step": 340919, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1194121837615967, "global_step": 340920, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1141650676727295, "global_step": 340921, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.100980043411255, "global_step": 340922, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1270432472229004, "global_step": 340923, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1558468341827393, "global_step": 340924, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0840423107147217, "global_step": 340925, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.026447296142578, "global_step": 340926, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1014211177825928, "global_step": 340927, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0893595218658447, "global_step": 340928, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0834221839904785, "global_step": 340929, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0574183464050293, "global_step": 340930, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1789326667785645, "global_step": 340931, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0660951137542725, "global_step": 340932, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1067795753479004, "global_step": 340933, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.123084306716919, "global_step": 340934, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0785768032073975, "global_step": 340935, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0513808727264404, "global_step": 340936, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.24224591255188, "global_step": 340937, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.135140895843506, "global_step": 340938, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0803170204162598, "global_step": 340939, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0705039501190186, "global_step": 340940, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0626089572906494, "global_step": 340941, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.183147668838501, "global_step": 340942, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.122729778289795, "global_step": 340943, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.2257046699523926, "global_step": 340944, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1392714977264404, "global_step": 340945, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.096203565597534, "global_step": 340946, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.105088233947754, "global_step": 340947, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0213494300842285, "global_step": 340948, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.075528860092163, "global_step": 340949, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.10819149017334, "global_step": 340950, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.153637647628784, "global_step": 340951, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.135695695877075, "global_step": 340952, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.2325477600097656, "global_step": 340953, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.096085786819458, "global_step": 340954, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1645374298095703, "global_step": 340955, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1265041828155518, "global_step": 340956, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0248301029205322, "global_step": 340957, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0640337467193604, "global_step": 340958, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.109736680984497, "global_step": 340959, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1229538917541504, "global_step": 340960, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0990257263183594, "global_step": 340961, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1128954887390137, "global_step": 340962, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.2339963912963867, "global_step": 340963, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1078457832336426, "global_step": 340964, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1062214374542236, "global_step": 340965, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0886013507843018, "global_step": 340966, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1552734375, "global_step": 340967, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0913705825805664, "global_step": 340968, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1004931926727295, "global_step": 340969, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.079864263534546, "global_step": 340970, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.135531187057495, "global_step": 340971, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.086097478866577, "global_step": 340972, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.163525342941284, "global_step": 340973, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1145753860473633, "global_step": 340974, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.092714786529541, "global_step": 340975, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.132058620452881, "global_step": 340976, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.141857385635376, "global_step": 340977, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1140248775482178, "global_step": 340978, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.11950945854187, "global_step": 340979, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.161850929260254, "global_step": 340980, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1648108959198, "global_step": 340981, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0620265007019043, "global_step": 340982, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.085308313369751, "global_step": 340983, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.083406686782837, "global_step": 340984, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0214853286743164, "global_step": 340985, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0856800079345703, "global_step": 340986, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.114412784576416, "global_step": 340987, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0226919651031494, "global_step": 340988, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.113147735595703, "global_step": 340989, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0521955490112305, "global_step": 340990, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.082521438598633, "global_step": 340991, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1125829219818115, "global_step": 340992, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.070871591567993, "global_step": 340993, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1384737491607666, "global_step": 340994, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1255006790161133, "global_step": 340995, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1141273975372314, "global_step": 340996, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1732077598571777, "global_step": 340997, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1483750343322754, "global_step": 340998, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.2390995025634766, "global_step": 340999, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0239927768707275, "global_step": 341000, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.124781847000122, "global_step": 341001, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.089749336242676, "global_step": 341002, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1817545890808105, "global_step": 341003, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0907137393951416, "global_step": 341004, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.100163459777832, "global_step": 341005, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.051652431488037, "global_step": 341006, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.2237367630004883, "global_step": 341007, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1074655055999756, "global_step": 341008, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.116628646850586, "global_step": 341009, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1398253440856934, "global_step": 341010, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0755016803741455, "global_step": 341011, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.07310152053833, "global_step": 341012, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1120119094848633, "global_step": 341013, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0496773719787598, "global_step": 341014, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.169989585876465, "global_step": 341015, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1743381023406982, "global_step": 341016, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.151998281478882, "global_step": 341017, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0861589908599854, "global_step": 341018, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0672788619995117, "global_step": 341019, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0141918659210205, "global_step": 341020, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.114497184753418, "global_step": 341021, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.166318655014038, "global_step": 341022, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0886619091033936, "global_step": 341023, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1332345008850098, "global_step": 341024, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.126964807510376, "global_step": 341025, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0972800254821777, "global_step": 341026, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.018252372741699, "global_step": 341027, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0781726837158203, "global_step": 341028, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.081606864929199, "global_step": 341029, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.143543243408203, "global_step": 341030, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.043761730194092, "global_step": 341031, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0568323135375977, "global_step": 341032, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1624438762664795, "global_step": 341033, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0462875366210938, "global_step": 341034, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.102766275405884, "global_step": 341035, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1762351989746094, "global_step": 341036, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1273789405822754, "global_step": 341037, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.124008893966675, "global_step": 341038, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0392630100250244, "global_step": 341039, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.079848289489746, "global_step": 341040, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.090925931930542, "global_step": 341041, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.112400531768799, "global_step": 341042, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1595189571380615, "global_step": 341043, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.022251605987549, "global_step": 341044, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.089952230453491, "global_step": 341045, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0456113815307617, "global_step": 341046, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.174941301345825, "global_step": 341047, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.055147171020508, "global_step": 341048, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0668187141418457, "global_step": 341049, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0957248210906982, "global_step": 341050, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1284873485565186, "global_step": 341051, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1631946563720703, "global_step": 341052, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1828866004943848, "global_step": 341053, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1184427738189697, "global_step": 341054, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.069988489151001, "global_step": 341055, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.119014263153076, "global_step": 341056, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0208308696746826, "global_step": 341057, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.243715286254883, "global_step": 341058, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1514363288879395, "global_step": 341059, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0790657997131348, "global_step": 341060, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1724894046783447, "global_step": 341061, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.136817216873169, "global_step": 341062, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.091622829437256, "global_step": 341063, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0294201374053955, "global_step": 341064, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1103289127349854, "global_step": 341065, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0982398986816406, "global_step": 341066, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.118159294128418, "global_step": 341067, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1417815685272217, "global_step": 341068, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0843684673309326, "global_step": 341069, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.131376028060913, "global_step": 341070, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1239559650421143, "global_step": 341071, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.160602569580078, "global_step": 341072, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.195178270339966, "global_step": 341073, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.115784168243408, "global_step": 341074, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.169581174850464, "global_step": 341075, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0939788818359375, "global_step": 341076, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0870587825775146, "global_step": 341077, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.095019578933716, "global_step": 341078, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1012611389160156, "global_step": 341079, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.2552592754364014, "global_step": 341080, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0783376693725586, "global_step": 341081, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1314423084259033, "global_step": 341082, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.100087881088257, "global_step": 341083, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1342928409576416, "global_step": 341084, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.093088388442993, "global_step": 341085, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1494874954223633, "global_step": 341086, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0435049533843994, "global_step": 341087, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0235166549682617, "global_step": 341088, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.077785015106201, "global_step": 341089, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1007590293884277, "global_step": 341090, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.042649030685425, "global_step": 341091, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1449360847473145, "global_step": 341092, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.122479200363159, "global_step": 341093, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0931904315948486, "global_step": 341094, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1281118392944336, "global_step": 341095, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0796759128570557, "global_step": 341096, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.075735569000244, "global_step": 341097, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.203618049621582, "global_step": 341098, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.236567974090576, "global_step": 341099, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1202645301818848, "global_step": 341100, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1219797134399414, "global_step": 341101, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0944244861602783, "global_step": 341102, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1063849925994873, "global_step": 341103, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.159067153930664, "global_step": 341104, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0839197635650635, "global_step": 341105, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1354715824127197, "global_step": 341106, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.15189266204834, "global_step": 341107, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.093862771987915, "global_step": 341108, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.073052167892456, "global_step": 341109, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.009618043899536, "global_step": 341110, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.100106716156006, "global_step": 341111, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1558778285980225, "global_step": 341112, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.23477840423584, "global_step": 341113, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.04399037361145, "global_step": 341114, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1426589488983154, "global_step": 341115, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.122762441635132, "global_step": 341116, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.032745122909546, "global_step": 341117, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.049584150314331, "global_step": 341118, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.16009259223938, "global_step": 341119, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.2049221992492676, "global_step": 341120, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0987603664398193, "global_step": 341121, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.156651496887207, "global_step": 341122, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.120699644088745, "global_step": 341123, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.138432502746582, "global_step": 341124, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0685153007507324, "global_step": 341125, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.148139476776123, "global_step": 341126, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.113316059112549, "global_step": 341127, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.2357711791992188, "global_step": 341128, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0022616386413574, "global_step": 341129, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1069273948669434, "global_step": 341130, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.056408643722534, "global_step": 341131, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0826821327209473, "global_step": 341132, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1319825649261475, "global_step": 341133, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1347744464874268, "global_step": 341134, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.07893443107605, "global_step": 341135, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.103867769241333, "global_step": 341136, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1787524223327637, "global_step": 341137, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.045497179031372, "global_step": 341138, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.2085139751434326, "global_step": 341139, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0978429317474365, "global_step": 341140, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.130627155303955, "global_step": 341141, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0955348014831543, "global_step": 341142, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0852015018463135, "global_step": 341143, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1110379695892334, "global_step": 341144, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1342902183532715, "global_step": 341145, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.076063871383667, "global_step": 341146, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.085268974304199, "global_step": 341147, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.118394136428833, "global_step": 341148, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0040531158447266, "global_step": 341149, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1472575664520264, "global_step": 341150, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.168647050857544, "global_step": 341151, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.156306028366089, "global_step": 341152, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.101508140563965, "global_step": 341153, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.179016590118408, "global_step": 341154, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1715190410614014, "global_step": 341155, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.026412010192871, "global_step": 341156, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0627551078796387, "global_step": 341157, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.098973274230957, "global_step": 341158, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1235132217407227, "global_step": 341159, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.163055896759033, "global_step": 341160, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.212340831756592, "global_step": 341161, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1897711753845215, "global_step": 341162, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0817954540252686, "global_step": 341163, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0959436893463135, "global_step": 341164, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1525309085845947, "global_step": 341165, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.123962879180908, "global_step": 341166, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1327714920043945, "global_step": 341167, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.118159055709839, "global_step": 341168, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.119393825531006, "global_step": 341169, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.084123134613037, "global_step": 341170, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1325132846832275, "global_step": 341171, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.140552282333374, "global_step": 341172, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1194941997528076, "global_step": 341173, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.114657402038574, "global_step": 341174, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.089707612991333, "global_step": 341175, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.103144884109497, "global_step": 341176, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0713772773742676, "global_step": 341177, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.081864833831787, "global_step": 341178, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.036294460296631, "global_step": 341179, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1800596714019775, "global_step": 341180, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.200079917907715, "global_step": 341181, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1037914752960205, "global_step": 341182, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.136681318283081, "global_step": 341183, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1261062622070312, "global_step": 341184, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0857577323913574, "global_step": 341185, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0384950637817383, "global_step": 341186, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.2135236263275146, "global_step": 341187, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1402690410614014, "global_step": 341188, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1381618976593018, "global_step": 341189, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.118544816970825, "global_step": 341190, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.125666379928589, "global_step": 341191, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.102989435195923, "global_step": 341192, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.205341339111328, "global_step": 341193, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.076688766479492, "global_step": 341194, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1151063442230225, "global_step": 341195, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0797362327575684, "global_step": 341196, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1417298316955566, "global_step": 341197, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.156897783279419, "global_step": 341198, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0650386810302734, "global_step": 341199, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0534393787384033, "global_step": 341200, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.2038981914520264, "global_step": 341201, "epoch": 701, "lr": 5e-05}
{"train_loss": 1.9801487922668457, "global_step": 341202, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0816307067871094, "global_step": 341203, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1220061779022217, "global_step": 341204, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1075639724731445, "global_step": 341205, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0953261852264404, "global_step": 341206, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1344523429870605, "global_step": 341207, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.2152886390686035, "global_step": 341208, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.006199836730957, "global_step": 341209, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.125308036804199, "global_step": 341210, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.044975757598877, "global_step": 341211, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.110377550125122, "global_step": 341212, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0863118171691895, "global_step": 341213, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0562081336975098, "global_step": 341214, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1586902141571045, "global_step": 341215, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.073758840560913, "global_step": 341216, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.092841148376465, "global_step": 341217, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.0886073112487793, "global_step": 341218, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.055657386779785, "global_step": 341219, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1035897731781006, "global_step": 341220, "epoch": 701, "lr": 5e-05}
{"train_loss": 2.1804869174957275, "global_step": 341221, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.08508563041687, "global_step": 341222, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.146122932434082, "global_step": 341223, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1572368144989014, "global_step": 341224, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.149071216583252, "global_step": 341225, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.140885353088379, "global_step": 341226, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1155049800872803, "global_step": 341227, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1133694648742676, "global_step": 341228, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.186645984649658, "global_step": 341229, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.044870376586914, "global_step": 341230, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1517484188079834, "global_step": 341231, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.099558115005493, "global_step": 341232, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1463704109191895, "global_step": 341233, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.122431755065918, "global_step": 341234, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0688600540161133, "global_step": 341235, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0936200618743896, "global_step": 341236, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.116157293319702, "global_step": 341237, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1615378856658936, "global_step": 341238, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.094698905944824, "global_step": 341239, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.080702543258667, "global_step": 341240, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0881712436676025, "global_step": 341241, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.020270824432373, "global_step": 341242, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.095494270324707, "global_step": 341243, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.116337299346924, "global_step": 341244, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.143294095993042, "global_step": 341245, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0583207607269287, "global_step": 341246, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1682355403900146, "global_step": 341247, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0725557804107666, "global_step": 341248, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0432677268981934, "global_step": 341249, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.120130777359009, "global_step": 341250, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0706939697265625, "global_step": 341251, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0440309047698975, "global_step": 341252, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0778920650482178, "global_step": 341253, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.096764087677002, "global_step": 341254, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.128350019454956, "global_step": 341255, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.035278797149658, "global_step": 341256, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1101973056793213, "global_step": 341257, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.071460008621216, "global_step": 341258, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.2001895904541016, "global_step": 341259, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.07970929145813, "global_step": 341260, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.080099105834961, "global_step": 341261, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.042628049850464, "global_step": 341262, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0492441654205322, "global_step": 341263, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1168506145477295, "global_step": 341264, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0749294757843018, "global_step": 341265, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.145029067993164, "global_step": 341266, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1283133029937744, "global_step": 341267, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.139111042022705, "global_step": 341268, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1143369674682617, "global_step": 341269, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0923397541046143, "global_step": 341270, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.037813663482666, "global_step": 341271, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1609320640563965, "global_step": 341272, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.040036201477051, "global_step": 341273, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1281261444091797, "global_step": 341274, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.082724094390869, "global_step": 341275, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1445472240448, "global_step": 341276, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0457003116607666, "global_step": 341277, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.070513963699341, "global_step": 341278, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.141037940979004, "global_step": 341279, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1688320636749268, "global_step": 341280, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.084540843963623, "global_step": 341281, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1202735900878906, "global_step": 341282, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1147522926330566, "global_step": 341283, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0528204441070557, "global_step": 341284, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0753138065338135, "global_step": 341285, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1507530212402344, "global_step": 341286, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.088461399078369, "global_step": 341287, "epoch": 702, "lr": 5e-05}
{"train_loss": 1.965085506439209, "global_step": 341288, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1633918285369873, "global_step": 341289, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.125579357147217, "global_step": 341290, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.052520275115967, "global_step": 341291, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.187601089477539, "global_step": 341292, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1462955474853516, "global_step": 341293, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.072399377822876, "global_step": 341294, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0697391033172607, "global_step": 341295, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1168925762176514, "global_step": 341296, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.064056634902954, "global_step": 341297, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0805907249450684, "global_step": 341298, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1663873195648193, "global_step": 341299, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1495347023010254, "global_step": 341300, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0698347091674805, "global_step": 341301, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0334460735321045, "global_step": 341302, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1153135299682617, "global_step": 341303, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1334803104400635, "global_step": 341304, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0551979541778564, "global_step": 341305, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0527727603912354, "global_step": 341306, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.035161256790161, "global_step": 341307, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1323280334472656, "global_step": 341308, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0756912231445312, "global_step": 341309, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0307705402374268, "global_step": 341310, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0680580139160156, "global_step": 341311, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0331830978393555, "global_step": 341312, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.100975513458252, "global_step": 341313, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.047663927078247, "global_step": 341314, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0768940448760986, "global_step": 341315, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1164391040802, "global_step": 341316, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.053516149520874, "global_step": 341317, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1008081436157227, "global_step": 341318, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0378317832946777, "global_step": 341319, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0785562992095947, "global_step": 341320, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1276137828826904, "global_step": 341321, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0350582599639893, "global_step": 341322, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1272480487823486, "global_step": 341323, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1319072246551514, "global_step": 341324, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.091770887374878, "global_step": 341325, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0693068504333496, "global_step": 341326, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0838799476623535, "global_step": 341327, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0798051357269287, "global_step": 341328, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1031970977783203, "global_step": 341329, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1570048332214355, "global_step": 341330, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0576181411743164, "global_step": 341331, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1702611446380615, "global_step": 341332, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0801608562469482, "global_step": 341333, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0574963092803955, "global_step": 341334, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0364620685577393, "global_step": 341335, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1640028953552246, "global_step": 341336, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1046998500823975, "global_step": 341337, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.054593324661255, "global_step": 341338, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0964481830596924, "global_step": 341339, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.110072612762451, "global_step": 341340, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.134518623352051, "global_step": 341341, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.083833694458008, "global_step": 341342, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0775535106658936, "global_step": 341343, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.11285400390625, "global_step": 341344, "epoch": 702, "lr": 5e-05}
{"train_loss": 1.9940123558044434, "global_step": 341345, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.162551164627075, "global_step": 341346, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.166560649871826, "global_step": 341347, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1108832359313965, "global_step": 341348, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1047565937042236, "global_step": 341349, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.142434597015381, "global_step": 341350, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1055614948272705, "global_step": 341351, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0913312435150146, "global_step": 341352, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.051041603088379, "global_step": 341353, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0441935062408447, "global_step": 341354, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0995287895202637, "global_step": 341355, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1485490798950195, "global_step": 341356, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.121891736984253, "global_step": 341357, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.117666006088257, "global_step": 341358, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0555741786956787, "global_step": 341359, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.118009328842163, "global_step": 341360, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.167508363723755, "global_step": 341361, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.161404848098755, "global_step": 341362, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0679080486297607, "global_step": 341363, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1158173084259033, "global_step": 341364, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0333776473999023, "global_step": 341365, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0500566959381104, "global_step": 341366, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.131159543991089, "global_step": 341367, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.159247636795044, "global_step": 341368, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.100651264190674, "global_step": 341369, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0802581310272217, "global_step": 341370, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1275618076324463, "global_step": 341371, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.119872808456421, "global_step": 341372, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.147141218185425, "global_step": 341373, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.030773878097534, "global_step": 341374, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.136409282684326, "global_step": 341375, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.060544729232788, "global_step": 341376, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.158066987991333, "global_step": 341377, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.046298027038574, "global_step": 341378, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.135296583175659, "global_step": 341379, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.032280921936035, "global_step": 341380, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1355955600738525, "global_step": 341381, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.060932159423828, "global_step": 341382, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1634504795074463, "global_step": 341383, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1668832302093506, "global_step": 341384, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0899593830108643, "global_step": 341385, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1235110759735107, "global_step": 341386, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1042420864105225, "global_step": 341387, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0700109004974365, "global_step": 341388, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0376405715942383, "global_step": 341389, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.077083110809326, "global_step": 341390, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0799074172973633, "global_step": 341391, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.093935251235962, "global_step": 341392, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.2122154235839844, "global_step": 341393, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.077179193496704, "global_step": 341394, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.14487886428833, "global_step": 341395, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0886237621307373, "global_step": 341396, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0621113777160645, "global_step": 341397, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1245527267456055, "global_step": 341398, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.157550811767578, "global_step": 341399, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0649800300598145, "global_step": 341400, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.126375913619995, "global_step": 341401, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.13612699508667, "global_step": 341402, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1076338291168213, "global_step": 341403, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1379969120025635, "global_step": 341404, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.061544179916382, "global_step": 341405, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.022902011871338, "global_step": 341406, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.088625192642212, "global_step": 341407, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1574866771698, "global_step": 341408, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1740612983703613, "global_step": 341409, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1636526584625244, "global_step": 341410, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.130154609680176, "global_step": 341411, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1105363368988037, "global_step": 341412, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.2555768489837646, "global_step": 341413, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1967666149139404, "global_step": 341414, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1476964950561523, "global_step": 341415, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.097156286239624, "global_step": 341416, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0531787872314453, "global_step": 341417, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1045029163360596, "global_step": 341418, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1166470050811768, "global_step": 341419, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.106990337371826, "global_step": 341420, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0917012691497803, "global_step": 341421, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0606648921966553, "global_step": 341422, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1362147331237793, "global_step": 341423, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.059663772583008, "global_step": 341424, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.087080478668213, "global_step": 341425, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.053661823272705, "global_step": 341426, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.043409824371338, "global_step": 341427, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0734269618988037, "global_step": 341428, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.119610548019409, "global_step": 341429, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0741896629333496, "global_step": 341430, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.061605453491211, "global_step": 341431, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.120398998260498, "global_step": 341432, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0221455097198486, "global_step": 341433, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1089348793029785, "global_step": 341434, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1033873558044434, "global_step": 341435, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1021275520324707, "global_step": 341436, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1109001636505127, "global_step": 341437, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.099656581878662, "global_step": 341438, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.034367799758911, "global_step": 341439, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.093639612197876, "global_step": 341440, "epoch": 702, "lr": 5e-05}
{"train_loss": 1.9972161054611206, "global_step": 341441, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0356345176696777, "global_step": 341442, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1314802169799805, "global_step": 341443, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0632245540618896, "global_step": 341444, "epoch": 702, "lr": 5e-05}
{"train_loss": 1.9832310676574707, "global_step": 341445, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0897252559661865, "global_step": 341446, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0567188262939453, "global_step": 341447, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0873360633850098, "global_step": 341448, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.047194004058838, "global_step": 341449, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.113661050796509, "global_step": 341450, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.196037769317627, "global_step": 341451, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1204445362091064, "global_step": 341452, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.077284336090088, "global_step": 341453, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.095452070236206, "global_step": 341454, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1154491901397705, "global_step": 341455, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1435630321502686, "global_step": 341456, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1952710151672363, "global_step": 341457, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1343040466308594, "global_step": 341458, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1723124980926514, "global_step": 341459, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.2199747562408447, "global_step": 341460, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0860931873321533, "global_step": 341461, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1049251556396484, "global_step": 341462, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0704662799835205, "global_step": 341463, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0622620582580566, "global_step": 341464, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0826973915100098, "global_step": 341465, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1118946075439453, "global_step": 341466, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.135687828063965, "global_step": 341467, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0832526683807373, "global_step": 341468, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.13216495513916, "global_step": 341469, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0250496864318848, "global_step": 341470, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1001856327056885, "global_step": 341471, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0843889713287354, "global_step": 341472, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.052062511444092, "global_step": 341473, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0359554290771484, "global_step": 341474, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.2451014518737793, "global_step": 341475, "epoch": 702, "lr": 5e-05}
{"train_loss": 1.9860917329788208, "global_step": 341476, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.153818368911743, "global_step": 341477, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1724143028259277, "global_step": 341478, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.07812762260437, "global_step": 341479, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1187689304351807, "global_step": 341480, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.028003215789795, "global_step": 341481, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.063326835632324, "global_step": 341482, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1182515621185303, "global_step": 341483, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0507102012634277, "global_step": 341484, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.098249673843384, "global_step": 341485, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1432244777679443, "global_step": 341486, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.074153184890747, "global_step": 341487, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0821170806884766, "global_step": 341488, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0809004306793213, "global_step": 341489, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.134176015853882, "global_step": 341490, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0592234134674072, "global_step": 341491, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.111768960952759, "global_step": 341492, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.069803476333618, "global_step": 341493, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.011075258255005, "global_step": 341494, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.200293779373169, "global_step": 341495, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1181483268737793, "global_step": 341496, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0490434169769287, "global_step": 341497, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.110171318054199, "global_step": 341498, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.123750686645508, "global_step": 341499, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.086338996887207, "global_step": 341500, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0301690101623535, "global_step": 341501, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0251502990722656, "global_step": 341502, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.065091133117676, "global_step": 341503, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.089024305343628, "global_step": 341504, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.04693603515625, "global_step": 341505, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0417115688323975, "global_step": 341506, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1168551445007324, "global_step": 341507, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.058985710144043, "global_step": 341508, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0318634510040283, "global_step": 341509, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0605790615081787, "global_step": 341510, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.051154851913452, "global_step": 341511, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.130441904067993, "global_step": 341512, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0891714096069336, "global_step": 341513, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1746695041656494, "global_step": 341514, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.183454751968384, "global_step": 341515, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.084707260131836, "global_step": 341516, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.117610454559326, "global_step": 341517, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.13088321685791, "global_step": 341518, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0854997634887695, "global_step": 341519, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1710221767425537, "global_step": 341520, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.087852716445923, "global_step": 341521, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.083402156829834, "global_step": 341522, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0870821475982666, "global_step": 341523, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1116297245025635, "global_step": 341524, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1055784225463867, "global_step": 341525, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1481761932373047, "global_step": 341526, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1236917972564697, "global_step": 341527, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1060495376586914, "global_step": 341528, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1091742515563965, "global_step": 341529, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1423697471618652, "global_step": 341530, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1124603748321533, "global_step": 341531, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0822081565856934, "global_step": 341532, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.109133720397949, "global_step": 341533, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.046473741531372, "global_step": 341534, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.117013454437256, "global_step": 341535, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.056142807006836, "global_step": 341536, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.033977508544922, "global_step": 341537, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.177245855331421, "global_step": 341538, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0984840393066406, "global_step": 341539, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0766732692718506, "global_step": 341540, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1941750049591064, "global_step": 341541, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0864109992980957, "global_step": 341542, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.043652057647705, "global_step": 341543, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0939579010009766, "global_step": 341544, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1730313301086426, "global_step": 341545, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.15639066696167, "global_step": 341546, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.070918321609497, "global_step": 341547, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1439719200134277, "global_step": 341548, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.161247730255127, "global_step": 341549, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1182219982147217, "global_step": 341550, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0860860347747803, "global_step": 341551, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.006229877471924, "global_step": 341552, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1142754554748535, "global_step": 341553, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0915253162384033, "global_step": 341554, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.160687208175659, "global_step": 341555, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.142805576324463, "global_step": 341556, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.066941976547241, "global_step": 341557, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.140038013458252, "global_step": 341558, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0880024433135986, "global_step": 341559, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.037069797515869, "global_step": 341560, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0626652240753174, "global_step": 341561, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.128558397293091, "global_step": 341562, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0871570110321045, "global_step": 341563, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1004114151000977, "global_step": 341564, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.077754020690918, "global_step": 341565, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.003801107406616, "global_step": 341566, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0786452293395996, "global_step": 341567, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.071932792663574, "global_step": 341568, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.116903781890869, "global_step": 341569, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0249383449554443, "global_step": 341570, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.109931230545044, "global_step": 341571, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0014376640319824, "global_step": 341572, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.009897232055664, "global_step": 341573, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0535223484039307, "global_step": 341574, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0781972408294678, "global_step": 341575, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0185303688049316, "global_step": 341576, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0635602474212646, "global_step": 341577, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.121506452560425, "global_step": 341578, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.117746353149414, "global_step": 341579, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.005413770675659, "global_step": 341580, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.063131093978882, "global_step": 341581, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.070770025253296, "global_step": 341582, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0579235553741455, "global_step": 341583, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1413795948028564, "global_step": 341584, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.002082347869873, "global_step": 341585, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.053806781768799, "global_step": 341586, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1527061462402344, "global_step": 341587, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.096233606338501, "global_step": 341588, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.093644857406616, "global_step": 341589, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.116129159927368, "global_step": 341590, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.127877712249756, "global_step": 341591, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.147141695022583, "global_step": 341592, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0675668716430664, "global_step": 341593, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.086874485015869, "global_step": 341594, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0887057781219482, "global_step": 341595, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.114370346069336, "global_step": 341596, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1063573360443115, "global_step": 341597, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.05086088180542, "global_step": 341598, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1118004322052, "global_step": 341599, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.146378517150879, "global_step": 341600, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0870654582977295, "global_step": 341601, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1126787662506104, "global_step": 341602, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1260461807250977, "global_step": 341603, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.036729335784912, "global_step": 341604, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0981736183166504, "global_step": 341605, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0261411666870117, "global_step": 341606, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.007239580154419, "global_step": 341607, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.096184492111206, "global_step": 341608, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0948712825775146, "global_step": 341609, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1646945476531982, "global_step": 341610, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0176167488098145, "global_step": 341611, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0722031593322754, "global_step": 341612, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1850311756134033, "global_step": 341613, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1225225925445557, "global_step": 341614, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1481056213378906, "global_step": 341615, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.052877426147461, "global_step": 341616, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.076456308364868, "global_step": 341617, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0737342834472656, "global_step": 341618, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1329941749572754, "global_step": 341619, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.163783550262451, "global_step": 341620, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.060042142868042, "global_step": 341621, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1603569984436035, "global_step": 341622, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0624451637268066, "global_step": 341623, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.043184757232666, "global_step": 341624, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0620322227478027, "global_step": 341625, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0763752460479736, "global_step": 341626, "epoch": 702, "lr": 5e-05}
{"train_loss": 1.9947147369384766, "global_step": 341627, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.100992202758789, "global_step": 341628, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.025904893875122, "global_step": 341629, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1066596508026123, "global_step": 341630, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.102980613708496, "global_step": 341631, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.14941143989563, "global_step": 341632, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.107313871383667, "global_step": 341633, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0977365970611572, "global_step": 341634, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0915656089782715, "global_step": 341635, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.084439277648926, "global_step": 341636, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.172762632369995, "global_step": 341637, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0535032749176025, "global_step": 341638, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.126805067062378, "global_step": 341639, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.071990728378296, "global_step": 341640, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1222801208496094, "global_step": 341641, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0814223289489746, "global_step": 341642, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1148366928100586, "global_step": 341643, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.163100242614746, "global_step": 341644, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0472521781921387, "global_step": 341645, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.062751054763794, "global_step": 341646, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.135296583175659, "global_step": 341647, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0911924839019775, "global_step": 341648, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.145576238632202, "global_step": 341649, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1207621097564697, "global_step": 341650, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1956772804260254, "global_step": 341651, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0352277755737305, "global_step": 341652, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0957422256469727, "global_step": 341653, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.12819504737854, "global_step": 341654, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.090250015258789, "global_step": 341655, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.117490768432617, "global_step": 341656, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.082498788833618, "global_step": 341657, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.123035430908203, "global_step": 341658, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.031161069869995, "global_step": 341659, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.134258508682251, "global_step": 341660, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1378698348999023, "global_step": 341661, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.07609486579895, "global_step": 341662, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.104924440383911, "global_step": 341663, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0524604320526123, "global_step": 341664, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0805821418762207, "global_step": 341665, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0771913528442383, "global_step": 341666, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0369718074798584, "global_step": 341667, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1093075275421143, "global_step": 341668, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1186587810516357, "global_step": 341669, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.079204797744751, "global_step": 341670, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.099595546722412, "global_step": 341671, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0880630016326904, "global_step": 341672, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0750672817230225, "global_step": 341673, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.148245334625244, "global_step": 341674, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1311259269714355, "global_step": 341675, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.172701597213745, "global_step": 341676, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1489391326904297, "global_step": 341677, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.109027862548828, "global_step": 341678, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.086667776107788, "global_step": 341679, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.178128957748413, "global_step": 341680, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1218159198760986, "global_step": 341681, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.048426628112793, "global_step": 341682, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.111943006515503, "global_step": 341683, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.08396053314209, "global_step": 341684, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.144258975982666, "global_step": 341685, "epoch": 702, "lr": 5e-05}
{"train_loss": 1.999184250831604, "global_step": 341686, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.117075204849243, "global_step": 341687, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.156083345413208, "global_step": 341688, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.130070924758911, "global_step": 341689, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0623159408569336, "global_step": 341690, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.151165246963501, "global_step": 341691, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.151759624481201, "global_step": 341692, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0771923065185547, "global_step": 341693, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1014909744262695, "global_step": 341694, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.11735463142395, "global_step": 341695, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.167213201522827, "global_step": 341696, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.114680051803589, "global_step": 341697, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0712225437164307, "global_step": 341698, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.086024761199951, "global_step": 341699, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.082937479019165, "global_step": 341700, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1515564918518066, "global_step": 341701, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1700398921966553, "global_step": 341702, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0938315391540527, "global_step": 341703, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1640701293945312, "global_step": 341704, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.076101064682007, "global_step": 341705, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.105954170227051, "global_step": 341706, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0367088317871094, "global_step": 341707, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1089560985565186, "global_step": 341708, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0139319896698, "global_step": 341709, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.07466983795166, "global_step": 341710, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0137836933135986, "global_step": 341711, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.162940263748169, "global_step": 341712, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.093165874481201, "global_step": 341713, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1256730556488037, "global_step": 341714, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.039633274078369, "global_step": 341715, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.131176471710205, "global_step": 341716, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.163818836212158, "global_step": 341717, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0593411922454834, "global_step": 341718, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.029163122177124, "global_step": 341719, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1206440925598145, "global_step": 341720, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.07128643989563, "global_step": 341721, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1893632411956787, "global_step": 341722, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.140780448913574, "global_step": 341723, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.083428382873535, "global_step": 341724, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1156251430511475, "global_step": 341725, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0821869373321533, "global_step": 341726, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1243464946746826, "global_step": 341727, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0640716552734375, "global_step": 341728, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.132342576980591, "global_step": 341729, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1060004234313965, "global_step": 341730, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.112323760986328, "global_step": 341731, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.2405245304107666, "global_step": 341732, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1093156337738037, "global_step": 341733, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1249446868896484, "global_step": 341734, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1172890663146973, "global_step": 341735, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.085838556289673, "global_step": 341736, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.2003328800201416, "global_step": 341737, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.14229416847229, "global_step": 341738, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1773488521575928, "global_step": 341739, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1066160202026367, "global_step": 341740, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.047123908996582, "global_step": 341741, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0842080116271973, "global_step": 341742, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0793545246124268, "global_step": 341743, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1257882118225098, "global_step": 341744, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.086452007293701, "global_step": 341745, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.12507700920105, "global_step": 341746, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.096257448196411, "global_step": 341747, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.149791955947876, "global_step": 341748, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.151392936706543, "global_step": 341749, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.091905355453491, "global_step": 341750, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.10996675491333, "global_step": 341751, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1141514778137207, "global_step": 341752, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1073672771453857, "global_step": 341753, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.081172466278076, "global_step": 341754, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0942513942718506, "global_step": 341755, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1282174587249756, "global_step": 341756, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1699209213256836, "global_step": 341757, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0412840843200684, "global_step": 341758, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1047754287719727, "global_step": 341759, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1339879035949707, "global_step": 341760, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.000199556350708, "global_step": 341761, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.054166555404663, "global_step": 341762, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.07918643951416, "global_step": 341763, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.131696939468384, "global_step": 341764, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0948197841644287, "global_step": 341765, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.108712673187256, "global_step": 341766, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1832499504089355, "global_step": 341767, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.16097092628479, "global_step": 341768, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1366076469421387, "global_step": 341769, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.097597599029541, "global_step": 341770, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0264668464660645, "global_step": 341771, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.165386438369751, "global_step": 341772, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0935230255126953, "global_step": 341773, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.072673797607422, "global_step": 341774, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1919424533843994, "global_step": 341775, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.176809549331665, "global_step": 341776, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.143979072570801, "global_step": 341777, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.076817274093628, "global_step": 341778, "epoch": 702, "lr": 5e-05}
{"train_loss": 1.9594250917434692, "global_step": 341779, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.157045602798462, "global_step": 341780, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0432698726654053, "global_step": 341781, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.074000358581543, "global_step": 341782, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1111996173858643, "global_step": 341783, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0642194747924805, "global_step": 341784, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1044745445251465, "global_step": 341785, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1342148780822754, "global_step": 341786, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.016052484512329, "global_step": 341787, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.092696189880371, "global_step": 341788, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1431212425231934, "global_step": 341789, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.050480604171753, "global_step": 341790, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.119807004928589, "global_step": 341791, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.2580084800720215, "global_step": 341792, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.085221767425537, "global_step": 341793, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0276131629943848, "global_step": 341794, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.162856340408325, "global_step": 341795, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0916476249694824, "global_step": 341796, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1780967712402344, "global_step": 341797, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0984485149383545, "global_step": 341798, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1470694541931152, "global_step": 341799, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.13362193107605, "global_step": 341800, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1928296089172363, "global_step": 341801, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1183149814605713, "global_step": 341802, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1077394485473633, "global_step": 341803, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1551976203918457, "global_step": 341804, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1079957485198975, "global_step": 341805, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.108910322189331, "global_step": 341806, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0624475479125977, "global_step": 341807, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.042367935180664, "global_step": 341808, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.087571144104004, "global_step": 341809, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0861117839813232, "global_step": 341810, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.186100959777832, "global_step": 341811, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0361104011535645, "global_step": 341812, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0922603607177734, "global_step": 341813, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.112624168395996, "global_step": 341814, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.119296073913574, "global_step": 341815, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0703086853027344, "global_step": 341816, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.080087661743164, "global_step": 341817, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.13578462600708, "global_step": 341818, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1093380451202393, "global_step": 341819, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.115342617034912, "global_step": 341820, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0124058723449707, "global_step": 341821, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.133324146270752, "global_step": 341822, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.117082118988037, "global_step": 341823, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.05430006980896, "global_step": 341824, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1172187328338623, "global_step": 341825, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.102572441101074, "global_step": 341826, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1544008255004883, "global_step": 341827, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1212880611419678, "global_step": 341828, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1036453247070312, "global_step": 341829, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1300978660583496, "global_step": 341830, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0921106338500977, "global_step": 341831, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.07434344291687, "global_step": 341832, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0723698139190674, "global_step": 341833, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.068324327468872, "global_step": 341834, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.136995792388916, "global_step": 341835, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1098718643188477, "global_step": 341836, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1037163734436035, "global_step": 341837, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.093174457550049, "global_step": 341838, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1362502574920654, "global_step": 341839, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.13261342048645, "global_step": 341840, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.067854166030884, "global_step": 341841, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1531851291656494, "global_step": 341842, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.081709384918213, "global_step": 341843, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.049166679382324, "global_step": 341844, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.100034475326538, "global_step": 341845, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.102116346359253, "global_step": 341846, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.012746572494507, "global_step": 341847, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0631043910980225, "global_step": 341848, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.130938768386841, "global_step": 341849, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.124289035797119, "global_step": 341850, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0432920455932617, "global_step": 341851, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1206815242767334, "global_step": 341852, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.108379602432251, "global_step": 341853, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0968146324157715, "global_step": 341854, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.087409257888794, "global_step": 341855, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0907700061798096, "global_step": 341856, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.091811180114746, "global_step": 341857, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.053832769393921, "global_step": 341858, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1641008853912354, "global_step": 341859, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.22580623626709, "global_step": 341860, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0725560188293457, "global_step": 341861, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.079890251159668, "global_step": 341862, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.045273780822754, "global_step": 341863, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1475141048431396, "global_step": 341864, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0825321674346924, "global_step": 341865, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0932352542877197, "global_step": 341866, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0879106521606445, "global_step": 341867, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.115072727203369, "global_step": 341868, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.089630126953125, "global_step": 341869, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0576324462890625, "global_step": 341870, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.117798089981079, "global_step": 341871, "epoch": 702, "lr": 5e-05}
{"train_loss": 1.994236707687378, "global_step": 341872, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0580523014068604, "global_step": 341873, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0197300910949707, "global_step": 341874, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0709521770477295, "global_step": 341875, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.113316297531128, "global_step": 341876, "epoch": 702, "lr": 5e-05}
{"train_loss": 1.9806503057479858, "global_step": 341877, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.122624158859253, "global_step": 341878, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.075674533843994, "global_step": 341879, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1223087310791016, "global_step": 341880, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1914098262786865, "global_step": 341881, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.184220314025879, "global_step": 341882, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.166895627975464, "global_step": 341883, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.073335647583008, "global_step": 341884, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0942177772521973, "global_step": 341885, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.084662437438965, "global_step": 341886, "epoch": 702, "lr": 5e-05}
{"train_loss": 1.986693024635315, "global_step": 341887, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.119033098220825, "global_step": 341888, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1258885860443115, "global_step": 341889, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.142517328262329, "global_step": 341890, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1383841037750244, "global_step": 341891, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1130690574645996, "global_step": 341892, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.055690288543701, "global_step": 341893, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1321089267730713, "global_step": 341894, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.092582941055298, "global_step": 341895, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.14034366607666, "global_step": 341896, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.098888397216797, "global_step": 341897, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1125338077545166, "global_step": 341898, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0962016582489014, "global_step": 341899, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0372073650360107, "global_step": 341900, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.180872917175293, "global_step": 341901, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1684436798095703, "global_step": 341902, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1513075828552246, "global_step": 341903, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0414624214172363, "global_step": 341904, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1428771018981934, "global_step": 341905, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0549051761627197, "global_step": 341906, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1445329189300537, "global_step": 341907, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.137899398803711, "global_step": 341908, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.033106565475464, "global_step": 341909, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.2521438598632812, "global_step": 341910, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1730527877807617, "global_step": 341911, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1124868392944336, "global_step": 341912, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1464126110076904, "global_step": 341913, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1300132274627686, "global_step": 341914, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.176419734954834, "global_step": 341915, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.085702657699585, "global_step": 341916, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1077420711517334, "global_step": 341917, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1109516620635986, "global_step": 341918, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.050386428833008, "global_step": 341919, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.066760301589966, "global_step": 341920, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.135331153869629, "global_step": 341921, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.178438663482666, "global_step": 341922, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.12443470954895, "global_step": 341923, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.07150936126709, "global_step": 341924, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1500301361083984, "global_step": 341925, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1453824043273926, "global_step": 341926, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.096061944961548, "global_step": 341927, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.119938611984253, "global_step": 341928, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1254751682281494, "global_step": 341929, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.076253890991211, "global_step": 341930, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.139216423034668, "global_step": 341931, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.085014581680298, "global_step": 341932, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0718190670013428, "global_step": 341933, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1178476810455322, "global_step": 341934, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.190842628479004, "global_step": 341935, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1282742023468018, "global_step": 341936, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.141528844833374, "global_step": 341937, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0681445598602295, "global_step": 341938, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1515300273895264, "global_step": 341939, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.2375776767730713, "global_step": 341940, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.123506546020508, "global_step": 341941, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0419094562530518, "global_step": 341942, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1259217262268066, "global_step": 341943, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.05688214302063, "global_step": 341944, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.069986343383789, "global_step": 341945, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0660717487335205, "global_step": 341946, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.061866283416748, "global_step": 341947, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0739927291870117, "global_step": 341948, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1072378158569336, "global_step": 341949, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.142087697982788, "global_step": 341950, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.086061716079712, "global_step": 341951, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.096285820007324, "global_step": 341952, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0175468921661377, "global_step": 341953, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.198741912841797, "global_step": 341954, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1523897647857666, "global_step": 341955, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1259524822235107, "global_step": 341956, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.107374429702759, "global_step": 341957, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.020792007446289, "global_step": 341958, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.132734537124634, "global_step": 341959, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.107473611831665, "global_step": 341960, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.06961727142334, "global_step": 341961, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1761157512664795, "global_step": 341962, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.072727680206299, "global_step": 341963, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1386055946350098, "global_step": 341964, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.132960319519043, "global_step": 341965, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.2738707065582275, "global_step": 341966, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.085745334625244, "global_step": 341967, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.139214038848877, "global_step": 341968, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.146009683609009, "global_step": 341969, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0692663192749023, "global_step": 341970, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1520159244537354, "global_step": 341971, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1006414890289307, "global_step": 341972, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.150639057159424, "global_step": 341973, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1313681602478027, "global_step": 341974, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0664830207824707, "global_step": 341975, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.11855411529541, "global_step": 341976, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1034584045410156, "global_step": 341977, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1157588958740234, "global_step": 341978, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.148580551147461, "global_step": 341979, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.118579626083374, "global_step": 341980, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1107912063598633, "global_step": 341981, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.129704475402832, "global_step": 341982, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.180192708969116, "global_step": 341983, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.152730941772461, "global_step": 341984, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0405614376068115, "global_step": 341985, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.134089469909668, "global_step": 341986, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.004485607147217, "global_step": 341987, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1351091861724854, "global_step": 341988, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1075332164764404, "global_step": 341989, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0713114738464355, "global_step": 341990, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.129756212234497, "global_step": 341991, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1468665599823, "global_step": 341992, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0499675273895264, "global_step": 341993, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.090379238128662, "global_step": 341994, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1496846675872803, "global_step": 341995, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.2040727138519287, "global_step": 341996, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.114262819290161, "global_step": 341997, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1419715881347656, "global_step": 341998, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.087949752807617, "global_step": 341999, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1077849864959717, "global_step": 342000, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.065150260925293, "global_step": 342001, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1515414714813232, "global_step": 342002, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1122725009918213, "global_step": 342003, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1679530143737793, "global_step": 342004, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.145080089569092, "global_step": 342005, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.06961989402771, "global_step": 342006, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1815755367279053, "global_step": 342007, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1346275806427, "global_step": 342008, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1305601596832275, "global_step": 342009, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0635321140289307, "global_step": 342010, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.128671407699585, "global_step": 342011, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0770366191864014, "global_step": 342012, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1113483905792236, "global_step": 342013, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.07140851020813, "global_step": 342014, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0411534309387207, "global_step": 342015, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0862152576446533, "global_step": 342016, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1523563861846924, "global_step": 342017, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0613534450531006, "global_step": 342018, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.108246088027954, "global_step": 342019, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.155087471008301, "global_step": 342020, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1193900108337402, "global_step": 342021, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.149317502975464, "global_step": 342022, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.2013213634490967, "global_step": 342023, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.15077805519104, "global_step": 342024, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0680108070373535, "global_step": 342025, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.12184739112854, "global_step": 342026, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.062838077545166, "global_step": 342027, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.057123899459839, "global_step": 342028, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0866341590881348, "global_step": 342029, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.061053991317749, "global_step": 342030, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.272427558898926, "global_step": 342031, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0878093242645264, "global_step": 342032, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0942981243133545, "global_step": 342033, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1550557613372803, "global_step": 342034, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0515084266662598, "global_step": 342035, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0750162601470947, "global_step": 342036, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.10188364982605, "global_step": 342037, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.197953701019287, "global_step": 342038, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.094747304916382, "global_step": 342039, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0603787899017334, "global_step": 342040, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0294296741485596, "global_step": 342041, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0591280460357666, "global_step": 342042, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0404744148254395, "global_step": 342043, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0479419231414795, "global_step": 342044, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.165313959121704, "global_step": 342045, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.079357147216797, "global_step": 342046, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0851778984069824, "global_step": 342047, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.14009428024292, "global_step": 342048, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0275583267211914, "global_step": 342049, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.166504383087158, "global_step": 342050, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.062965154647827, "global_step": 342051, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.061265707015991, "global_step": 342052, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.2278060913085938, "global_step": 342053, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.095902681350708, "global_step": 342054, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1955316066741943, "global_step": 342055, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0913431644439697, "global_step": 342056, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1446893215179443, "global_step": 342057, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1058509349823, "global_step": 342058, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1215076446533203, "global_step": 342059, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.081178903579712, "global_step": 342060, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.047877550125122, "global_step": 342061, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.100332498550415, "global_step": 342062, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.030946969985962, "global_step": 342063, "epoch": 702, "lr": 5e-05}
{"train_loss": 1.9856014251708984, "global_step": 342064, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.113752603530884, "global_step": 342065, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.191509246826172, "global_step": 342066, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.119184732437134, "global_step": 342067, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1298463344573975, "global_step": 342068, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.129464864730835, "global_step": 342069, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0888280868530273, "global_step": 342070, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.148648738861084, "global_step": 342071, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.025674819946289, "global_step": 342072, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.103714942932129, "global_step": 342073, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.124683380126953, "global_step": 342074, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0181188583374023, "global_step": 342075, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1064107418060303, "global_step": 342076, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0848233699798584, "global_step": 342077, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1504383087158203, "global_step": 342078, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0397212505340576, "global_step": 342079, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.010197877883911, "global_step": 342080, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1731390953063965, "global_step": 342081, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.070683717727661, "global_step": 342082, "epoch": 702, "lr": 5e-05}
{"train_loss": 1.9929133653640747, "global_step": 342083, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0599236488342285, "global_step": 342084, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.2309155464172363, "global_step": 342085, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.025783061981201, "global_step": 342086, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0028975009918213, "global_step": 342087, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.16396427154541, "global_step": 342088, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.133664846420288, "global_step": 342089, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1451332569122314, "global_step": 342090, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0287671089172363, "global_step": 342091, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1126768589019775, "global_step": 342092, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1124720573425293, "global_step": 342093, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1810712814331055, "global_step": 342094, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.172201633453369, "global_step": 342095, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.130218029022217, "global_step": 342096, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.122779607772827, "global_step": 342097, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1032326221466064, "global_step": 342098, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.079843044281006, "global_step": 342099, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0436692237854004, "global_step": 342100, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1587204933166504, "global_step": 342101, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0872745513916016, "global_step": 342102, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1079227924346924, "global_step": 342103, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.180811643600464, "global_step": 342104, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1453709602355957, "global_step": 342105, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0710465908050537, "global_step": 342106, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.033276081085205, "global_step": 342107, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0786705017089844, "global_step": 342108, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1018362045288086, "global_step": 342109, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1454720497131348, "global_step": 342110, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0683796405792236, "global_step": 342111, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1064281463623047, "global_step": 342112, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.081608772277832, "global_step": 342113, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.118180274963379, "global_step": 342114, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.067452907562256, "global_step": 342115, "epoch": 702, "lr": 5e-05}
{"train_loss": 1.958177089691162, "global_step": 342116, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1405837535858154, "global_step": 342117, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1690025329589844, "global_step": 342118, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1699929237365723, "global_step": 342119, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.108365058898926, "global_step": 342120, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1740148067474365, "global_step": 342121, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0991406440734863, "global_step": 342122, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1658143997192383, "global_step": 342123, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.125067949295044, "global_step": 342124, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.018028974533081, "global_step": 342125, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0719237327575684, "global_step": 342126, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0998694896698, "global_step": 342127, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1064860820770264, "global_step": 342128, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.143256664276123, "global_step": 342129, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.100611686706543, "global_step": 342130, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0535624027252197, "global_step": 342131, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0695574283599854, "global_step": 342132, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0305798053741455, "global_step": 342133, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1035995483398438, "global_step": 342134, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0529661178588867, "global_step": 342135, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1745970249176025, "global_step": 342136, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0601847171783447, "global_step": 342137, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1021339893341064, "global_step": 342138, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.127309560775757, "global_step": 342139, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1996188163757324, "global_step": 342140, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1240551471710205, "global_step": 342141, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.143465757369995, "global_step": 342142, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0843758583068848, "global_step": 342143, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.117001533508301, "global_step": 342144, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.13728666305542, "global_step": 342145, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.039623260498047, "global_step": 342146, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.127549409866333, "global_step": 342147, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.132132053375244, "global_step": 342148, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1246337890625, "global_step": 342149, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0562102794647217, "global_step": 342150, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.156303882598877, "global_step": 342151, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0816750526428223, "global_step": 342152, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.042229413986206, "global_step": 342153, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0897860527038574, "global_step": 342154, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1595170497894287, "global_step": 342155, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1772756576538086, "global_step": 342156, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.079639196395874, "global_step": 342157, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1244983673095703, "global_step": 342158, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.05989933013916, "global_step": 342159, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1291885375976562, "global_step": 342160, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0234134197235107, "global_step": 342161, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.165391683578491, "global_step": 342162, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1132121086120605, "global_step": 342163, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.126765012741089, "global_step": 342164, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.192972421646118, "global_step": 342165, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.079662799835205, "global_step": 342166, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.085491180419922, "global_step": 342167, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.067823886871338, "global_step": 342168, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1108100414276123, "global_step": 342169, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.101961374282837, "global_step": 342170, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0860538482666016, "global_step": 342171, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0753777027130127, "global_step": 342172, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.113539457321167, "global_step": 342173, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0796451568603516, "global_step": 342174, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.045459747314453, "global_step": 342175, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.140667676925659, "global_step": 342176, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1206181049346924, "global_step": 342177, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1659700870513916, "global_step": 342178, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1617629528045654, "global_step": 342179, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.2122695446014404, "global_step": 342180, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1553618907928467, "global_step": 342181, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0240557193756104, "global_step": 342182, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1096134185791016, "global_step": 342183, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1605966091156006, "global_step": 342184, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.141981601715088, "global_step": 342185, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.175859212875366, "global_step": 342186, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0713112354278564, "global_step": 342187, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.0109896659851074, "global_step": 342188, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.1026995182037354, "global_step": 342189, "epoch": 702, "lr": 5e-05}
{"train_loss": 2.032208204269409, "global_step": 342190, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.134713649749756, "global_step": 342191, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0983591079711914, "global_step": 342192, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.086866855621338, "global_step": 342193, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9868563413619995, "global_step": 342194, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.138636589050293, "global_step": 342195, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1660139560699463, "global_step": 342196, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1433098316192627, "global_step": 342197, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1998629570007324, "global_step": 342198, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.034432888031006, "global_step": 342199, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.133024215698242, "global_step": 342200, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1298303604125977, "global_step": 342201, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9839813709259033, "global_step": 342202, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0883595943450928, "global_step": 342203, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.098099946975708, "global_step": 342204, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.138360023498535, "global_step": 342205, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.133455991744995, "global_step": 342206, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0250210762023926, "global_step": 342207, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.082502841949463, "global_step": 342208, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9831784963607788, "global_step": 342209, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.234243392944336, "global_step": 342210, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0643112659454346, "global_step": 342211, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1216397285461426, "global_step": 342212, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.094576120376587, "global_step": 342213, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.060912609100342, "global_step": 342214, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.073387384414673, "global_step": 342215, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.072683811187744, "global_step": 342216, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1672515869140625, "global_step": 342217, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.061192750930786, "global_step": 342218, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.092440366744995, "global_step": 342219, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0822062492370605, "global_step": 342220, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0909323692321777, "global_step": 342221, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0823042392730713, "global_step": 342222, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.144782304763794, "global_step": 342223, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.994619607925415, "global_step": 342224, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.162909507751465, "global_step": 342225, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.061265707015991, "global_step": 342226, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.094705104827881, "global_step": 342227, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0403358936309814, "global_step": 342228, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1405181884765625, "global_step": 342229, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.201725721359253, "global_step": 342230, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0204765796661377, "global_step": 342231, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.034757375717163, "global_step": 342232, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.073638439178467, "global_step": 342233, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.035703659057617, "global_step": 342234, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0744569301605225, "global_step": 342235, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0709664821624756, "global_step": 342236, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0054373741149902, "global_step": 342237, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0772945880889893, "global_step": 342238, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.177694320678711, "global_step": 342239, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1984519958496094, "global_step": 342240, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.030665636062622, "global_step": 342241, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.067225694656372, "global_step": 342242, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0962953567504883, "global_step": 342243, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.031177282333374, "global_step": 342244, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.11600661277771, "global_step": 342245, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.087047815322876, "global_step": 342246, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.072671890258789, "global_step": 342247, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.145970344543457, "global_step": 342248, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.093522310256958, "global_step": 342249, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0797908306121826, "global_step": 342250, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0870354175567627, "global_step": 342251, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.049626588821411, "global_step": 342252, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0278208255767822, "global_step": 342253, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1401751041412354, "global_step": 342254, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9707691669464111, "global_step": 342255, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1693408489227295, "global_step": 342256, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0456602573394775, "global_step": 342257, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0855929851531982, "global_step": 342258, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9942671060562134, "global_step": 342259, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0810465812683105, "global_step": 342260, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0590946674346924, "global_step": 342261, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1205155849456787, "global_step": 342262, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1031341552734375, "global_step": 342263, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.170593738555908, "global_step": 342264, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1227288246154785, "global_step": 342265, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1042423248291016, "global_step": 342266, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.114243984222412, "global_step": 342267, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1271958351135254, "global_step": 342268, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1361351013183594, "global_step": 342269, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1045141220092773, "global_step": 342270, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1295433044433594, "global_step": 342271, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1553945541381836, "global_step": 342272, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0758869647979736, "global_step": 342273, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1611404418945312, "global_step": 342274, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.151315450668335, "global_step": 342275, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.981189250946045, "global_step": 342276, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.152543306350708, "global_step": 342277, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.122360944747925, "global_step": 342278, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1024248600006104, "global_step": 342279, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1006433963775635, "global_step": 342280, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0535902976989746, "global_step": 342281, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0586585998535156, "global_step": 342282, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.128488540649414, "global_step": 342283, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0813112258911133, "global_step": 342284, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.040477991104126, "global_step": 342285, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.163661241531372, "global_step": 342286, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.115739345550537, "global_step": 342287, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.122046947479248, "global_step": 342288, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.147275924682617, "global_step": 342289, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0531928539276123, "global_step": 342290, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.095555067062378, "global_step": 342291, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.102543592453003, "global_step": 342292, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.148595094680786, "global_step": 342293, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.075775623321533, "global_step": 342294, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1267316341400146, "global_step": 342295, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1756272315979004, "global_step": 342296, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0892512798309326, "global_step": 342297, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0803589820861816, "global_step": 342298, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1208438873291016, "global_step": 342299, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1453769207000732, "global_step": 342300, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.010586977005005, "global_step": 342301, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1053662300109863, "global_step": 342302, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.034836530685425, "global_step": 342303, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0985820293426514, "global_step": 342304, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.123091459274292, "global_step": 342305, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.068729877471924, "global_step": 342306, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.082659959793091, "global_step": 342307, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.113375663757324, "global_step": 342308, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.156578302383423, "global_step": 342309, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1271774768829346, "global_step": 342310, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0758986473083496, "global_step": 342311, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9915225505828857, "global_step": 342312, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.122873067855835, "global_step": 342313, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.057863712310791, "global_step": 342314, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1072657108306885, "global_step": 342315, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.098257064819336, "global_step": 342316, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1282448768615723, "global_step": 342317, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.032113552093506, "global_step": 342318, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.06797194480896, "global_step": 342319, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0143752098083496, "global_step": 342320, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.2028439044952393, "global_step": 342321, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9027142524719238, "global_step": 342322, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.076183319091797, "global_step": 342323, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0705573558807373, "global_step": 342324, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0833370685577393, "global_step": 342325, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1329591274261475, "global_step": 342326, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.041752815246582, "global_step": 342327, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1024816036224365, "global_step": 342328, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.109807252883911, "global_step": 342329, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1291356086730957, "global_step": 342330, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.07600474357605, "global_step": 342331, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1815929412841797, "global_step": 342332, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1553714275360107, "global_step": 342333, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0311672687530518, "global_step": 342334, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0672383308410645, "global_step": 342335, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.09627366065979, "global_step": 342336, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0837085247039795, "global_step": 342337, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0792107582092285, "global_step": 342338, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0781302452087402, "global_step": 342339, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.177192449569702, "global_step": 342340, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0987796783447266, "global_step": 342341, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1468546390533447, "global_step": 342342, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1176419258117676, "global_step": 342343, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1797592639923096, "global_step": 342344, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1116933822631836, "global_step": 342345, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0861196517944336, "global_step": 342346, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.982557773590088, "global_step": 342347, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1677589416503906, "global_step": 342348, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.095283269882202, "global_step": 342349, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.07241153717041, "global_step": 342350, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.139003038406372, "global_step": 342351, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1529741287231445, "global_step": 342352, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.032680034637451, "global_step": 342353, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0894041061401367, "global_step": 342354, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1010658740997314, "global_step": 342355, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1106762886047363, "global_step": 342356, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.071687698364258, "global_step": 342357, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1977336406707764, "global_step": 342358, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.060356616973877, "global_step": 342359, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.152165651321411, "global_step": 342360, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.09196138381958, "global_step": 342361, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0838100910186768, "global_step": 342362, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0890066623687744, "global_step": 342363, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.066016435623169, "global_step": 342364, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.016845464706421, "global_step": 342365, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0805017948150635, "global_step": 342366, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.151432514190674, "global_step": 342367, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.130747079849243, "global_step": 342368, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1606953144073486, "global_step": 342369, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1638174057006836, "global_step": 342370, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.142137050628662, "global_step": 342371, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1353859901428223, "global_step": 342372, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.037172555923462, "global_step": 342373, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.133575201034546, "global_step": 342374, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.075622320175171, "global_step": 342375, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1586098670959473, "global_step": 342376, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0948119163513184, "global_step": 342377, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.104095220565796, "global_step": 342378, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0442917346954346, "global_step": 342379, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.09352445602417, "global_step": 342380, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0707263946533203, "global_step": 342381, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9943127632141113, "global_step": 342382, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.092712879180908, "global_step": 342383, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1422173976898193, "global_step": 342384, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.099722385406494, "global_step": 342385, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.104909658432007, "global_step": 342386, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0208683013916016, "global_step": 342387, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0860185623168945, "global_step": 342388, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.074277639389038, "global_step": 342389, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.096592664718628, "global_step": 342390, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.059119701385498, "global_step": 342391, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0439858436584473, "global_step": 342392, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.112656354904175, "global_step": 342393, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0626471042633057, "global_step": 342394, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0840697288513184, "global_step": 342395, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.092531204223633, "global_step": 342396, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0960628986358643, "global_step": 342397, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.115041971206665, "global_step": 342398, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0985751152038574, "global_step": 342399, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.107844591140747, "global_step": 342400, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1682698726654053, "global_step": 342401, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.206911087036133, "global_step": 342402, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.091257095336914, "global_step": 342403, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9954636096954346, "global_step": 342404, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0984017848968506, "global_step": 342405, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0771560668945312, "global_step": 342406, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.085590124130249, "global_step": 342407, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0768990516662598, "global_step": 342408, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.018984794616699, "global_step": 342409, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.2038440704345703, "global_step": 342410, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.044466018676758, "global_step": 342411, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1504018306732178, "global_step": 342412, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0870025157928467, "global_step": 342413, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0976951122283936, "global_step": 342414, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0781188011169434, "global_step": 342415, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1227288246154785, "global_step": 342416, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9870877265930176, "global_step": 342417, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.106628179550171, "global_step": 342418, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1475465297698975, "global_step": 342419, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.132996082305908, "global_step": 342420, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.126441478729248, "global_step": 342421, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1541295051574707, "global_step": 342422, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0466108322143555, "global_step": 342423, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1121397018432617, "global_step": 342424, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.109204053878784, "global_step": 342425, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.119419574737549, "global_step": 342426, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.053333044052124, "global_step": 342427, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.107285737991333, "global_step": 342428, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.168487310409546, "global_step": 342429, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0494656562805176, "global_step": 342430, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.132871389389038, "global_step": 342431, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.153968572616577, "global_step": 342432, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.066497564315796, "global_step": 342433, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1206932067871094, "global_step": 342434, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.948664665222168, "global_step": 342435, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.093153953552246, "global_step": 342436, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1093626022338867, "global_step": 342437, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0960967540740967, "global_step": 342438, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.139450788497925, "global_step": 342439, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0469353199005127, "global_step": 342440, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.173875093460083, "global_step": 342441, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0709753036499023, "global_step": 342442, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1680641174316406, "global_step": 342443, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0452029705047607, "global_step": 342444, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.033872365951538, "global_step": 342445, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1173317432403564, "global_step": 342446, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.060493230819702, "global_step": 342447, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.07330060005188, "global_step": 342448, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.090768814086914, "global_step": 342449, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0832080841064453, "global_step": 342450, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1071054935455322, "global_step": 342451, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9869427680969238, "global_step": 342452, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0401480197906494, "global_step": 342453, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1598854064941406, "global_step": 342454, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1674907207489014, "global_step": 342455, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.065232992172241, "global_step": 342456, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.179293394088745, "global_step": 342457, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0806820392608643, "global_step": 342458, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1481809616088867, "global_step": 342459, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.046510934829712, "global_step": 342460, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0949971675872803, "global_step": 342461, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1427130699157715, "global_step": 342462, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0964298248291016, "global_step": 342463, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.124176025390625, "global_step": 342464, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0990405082702637, "global_step": 342465, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0602986812591553, "global_step": 342466, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1451423168182373, "global_step": 342467, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.104529857635498, "global_step": 342468, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.14300537109375, "global_step": 342469, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.135427474975586, "global_step": 342470, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.100921392440796, "global_step": 342471, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.094224214553833, "global_step": 342472, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.016096830368042, "global_step": 342473, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1208879947662354, "global_step": 342474, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1390621662139893, "global_step": 342475, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1219115257263184, "global_step": 342476, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.006953716278076, "global_step": 342477, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1317453384399414, "global_step": 342478, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.010462522506714, "global_step": 342479, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.2490832805633545, "global_step": 342480, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0573880672454834, "global_step": 342481, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0783603191375732, "global_step": 342482, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.067251682281494, "global_step": 342483, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1534152030944824, "global_step": 342484, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1064062118530273, "global_step": 342485, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0621211528778076, "global_step": 342486, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.059260845184326, "global_step": 342487, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0719034671783447, "global_step": 342488, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.218034267425537, "global_step": 342489, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.11260724067688, "global_step": 342490, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.057516098022461, "global_step": 342491, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1537392139434814, "global_step": 342492, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0700130462646484, "global_step": 342493, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0980582237243652, "global_step": 342494, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0845441818237305, "global_step": 342495, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0545654296875, "global_step": 342496, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.131131887435913, "global_step": 342497, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1012680530548096, "global_step": 342498, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.166954278945923, "global_step": 342499, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.048166036605835, "global_step": 342500, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.137510061264038, "global_step": 342501, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.052358627319336, "global_step": 342502, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.138972520828247, "global_step": 342503, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0818426609039307, "global_step": 342504, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0663747787475586, "global_step": 342505, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1842610836029053, "global_step": 342506, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1088452339172363, "global_step": 342507, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0485315322875977, "global_step": 342508, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1313509941101074, "global_step": 342509, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0852677822113037, "global_step": 342510, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.099893569946289, "global_step": 342511, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.13727068901062, "global_step": 342512, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1654345989227295, "global_step": 342513, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.019195079803467, "global_step": 342514, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.129074811935425, "global_step": 342515, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0422985553741455, "global_step": 342516, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1446592807769775, "global_step": 342517, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1393232345581055, "global_step": 342518, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.074930429458618, "global_step": 342519, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1916885375976562, "global_step": 342520, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1307802200317383, "global_step": 342521, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0269174575805664, "global_step": 342522, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.079695701599121, "global_step": 342523, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1601855754852295, "global_step": 342524, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1019840240478516, "global_step": 342525, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.073394298553467, "global_step": 342526, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1124019622802734, "global_step": 342527, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0876569747924805, "global_step": 342528, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.145321846008301, "global_step": 342529, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.041454792022705, "global_step": 342530, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0202062129974365, "global_step": 342531, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.090341091156006, "global_step": 342532, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1640684604644775, "global_step": 342533, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0819363594055176, "global_step": 342534, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1044750213623047, "global_step": 342535, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.084336757659912, "global_step": 342536, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.156682252883911, "global_step": 342537, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.061258554458618, "global_step": 342538, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1116743087768555, "global_step": 342539, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.14795184135437, "global_step": 342540, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.13754940032959, "global_step": 342541, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0958456993103027, "global_step": 342542, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.107914447784424, "global_step": 342543, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1090588569641113, "global_step": 342544, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.082939386367798, "global_step": 342545, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.136256456375122, "global_step": 342546, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.047761917114258, "global_step": 342547, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0953216552734375, "global_step": 342548, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.138352155685425, "global_step": 342549, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0503883361816406, "global_step": 342550, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.012185573577881, "global_step": 342551, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1411333084106445, "global_step": 342552, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.052706003189087, "global_step": 342553, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0969297885894775, "global_step": 342554, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.105894088745117, "global_step": 342555, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1387417316436768, "global_step": 342556, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.085571765899658, "global_step": 342557, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.162099838256836, "global_step": 342558, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.095592737197876, "global_step": 342559, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.070258140563965, "global_step": 342560, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.203808307647705, "global_step": 342561, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.101745843887329, "global_step": 342562, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0700416564941406, "global_step": 342563, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0224897861480713, "global_step": 342564, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1109273433685303, "global_step": 342565, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0789942741394043, "global_step": 342566, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9891217947006226, "global_step": 342567, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.024857759475708, "global_step": 342568, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0732779502868652, "global_step": 342569, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1046833992004395, "global_step": 342570, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.100616931915283, "global_step": 342571, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1503639221191406, "global_step": 342572, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.971225380897522, "global_step": 342573, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.173675775527954, "global_step": 342574, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.137817859649658, "global_step": 342575, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1945383548736572, "global_step": 342576, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1354875564575195, "global_step": 342577, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1460773944854736, "global_step": 342578, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.120187997817993, "global_step": 342579, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1080269813537598, "global_step": 342580, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.2241721153259277, "global_step": 342581, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.079249143600464, "global_step": 342582, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0189480781555176, "global_step": 342583, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.124063491821289, "global_step": 342584, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0431883335113525, "global_step": 342585, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.102175712585449, "global_step": 342586, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.045466899871826, "global_step": 342587, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0083119869232178, "global_step": 342588, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.173198938369751, "global_step": 342589, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1247851848602295, "global_step": 342590, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.182279109954834, "global_step": 342591, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.087968349456787, "global_step": 342592, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.122953414916992, "global_step": 342593, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9851685762405396, "global_step": 342594, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.2014245986938477, "global_step": 342595, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1078743934631348, "global_step": 342596, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1082026958465576, "global_step": 342597, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.139347553253174, "global_step": 342598, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.001702308654785, "global_step": 342599, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.080526828765869, "global_step": 342600, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.230393409729004, "global_step": 342601, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0984928607940674, "global_step": 342602, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1869213581085205, "global_step": 342603, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.189811944961548, "global_step": 342604, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.125826358795166, "global_step": 342605, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.089665651321411, "global_step": 342606, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0933802127838135, "global_step": 342607, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1109721660614014, "global_step": 342608, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1308417320251465, "global_step": 342609, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1927430629730225, "global_step": 342610, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.157829761505127, "global_step": 342611, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0699493885040283, "global_step": 342612, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0638022422790527, "global_step": 342613, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1557416915893555, "global_step": 342614, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.024695634841919, "global_step": 342615, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0744543075561523, "global_step": 342616, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0817062854766846, "global_step": 342617, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.125398635864258, "global_step": 342618, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1410574913024902, "global_step": 342619, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.119453191757202, "global_step": 342620, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0601916313171387, "global_step": 342621, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1235787868499756, "global_step": 342622, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0717978477478027, "global_step": 342623, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1259937286376953, "global_step": 342624, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.109483480453491, "global_step": 342625, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1696789264678955, "global_step": 342626, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.2158474922180176, "global_step": 342627, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1093316078186035, "global_step": 342628, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0640151500701904, "global_step": 342629, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.09602952003479, "global_step": 342630, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.067054271697998, "global_step": 342631, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0844309329986572, "global_step": 342632, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0924904346466064, "global_step": 342633, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1102850437164307, "global_step": 342634, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1180777549743652, "global_step": 342635, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0110151767730713, "global_step": 342636, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0561869144439697, "global_step": 342637, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0319113731384277, "global_step": 342638, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1407129764556885, "global_step": 342639, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.205292224884033, "global_step": 342640, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.142009973526001, "global_step": 342641, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.042849063873291, "global_step": 342642, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.144186019897461, "global_step": 342643, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.2016124725341797, "global_step": 342644, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.032848596572876, "global_step": 342645, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1104233264923096, "global_step": 342646, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.054008722305298, "global_step": 342647, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0664422512054443, "global_step": 342648, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1724069118499756, "global_step": 342649, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.078159809112549, "global_step": 342650, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0249013900756836, "global_step": 342651, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.183912992477417, "global_step": 342652, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.027149200439453, "global_step": 342653, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.042750835418701, "global_step": 342654, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1135897636413574, "global_step": 342655, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0821802616119385, "global_step": 342656, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0568764209747314, "global_step": 342657, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0998804569244385, "global_step": 342658, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1090004444122314, "global_step": 342659, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.101666212081909, "global_step": 342660, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1451964378356934, "global_step": 342661, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1375935077667236, "global_step": 342662, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.063183069229126, "global_step": 342663, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1000311374664307, "global_step": 342664, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.118176221847534, "global_step": 342665, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1158249378204346, "global_step": 342666, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.085171937942505, "global_step": 342667, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.07460880279541, "global_step": 342668, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.2642085552215576, "global_step": 342669, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.151855945587158, "global_step": 342670, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1410326957702637, "global_step": 342671, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0649657249450684, "global_step": 342672, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0965912342071533, "global_step": 342673, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.083242416381836, "global_step": 342674, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.102632522583008, "global_step": 342675, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.080512762069702, "global_step": 342676, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.094731092453003, "global_step": 342677, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1684234142303467, "global_step": 342678, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0348644256591797, "global_step": 342679, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.128619432449341, "global_step": 342680, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0465383529663086, "global_step": 342681, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.100367784500122, "global_step": 342682, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.160970449447632, "global_step": 342683, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.082855463027954, "global_step": 342684, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.052574396133423, "global_step": 342685, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.12115478515625, "global_step": 342686, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1428606510162354, "global_step": 342687, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0874431133270264, "global_step": 342688, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0599191188812256, "global_step": 342689, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1458702087402344, "global_step": 342690, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1096103191375732, "global_step": 342691, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1057567596435547, "global_step": 342692, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0449838638305664, "global_step": 342693, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1215529441833496, "global_step": 342694, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.076050281524658, "global_step": 342695, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0667290687561035, "global_step": 342696, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.148104190826416, "global_step": 342697, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.125307083129883, "global_step": 342698, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1497299671173096, "global_step": 342699, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1402511596679688, "global_step": 342700, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.090790033340454, "global_step": 342701, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0941476821899414, "global_step": 342702, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1059823036193848, "global_step": 342703, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.082942485809326, "global_step": 342704, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.060701370239258, "global_step": 342705, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0379414558410645, "global_step": 342706, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0616538524627686, "global_step": 342707, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0494801998138428, "global_step": 342708, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1803905963897705, "global_step": 342709, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0547635555267334, "global_step": 342710, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0584163665771484, "global_step": 342711, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.220643997192383, "global_step": 342712, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.128894567489624, "global_step": 342713, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.153200149536133, "global_step": 342714, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0832443237304688, "global_step": 342715, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.186915874481201, "global_step": 342716, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.116501569747925, "global_step": 342717, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.110161542892456, "global_step": 342718, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1694552898406982, "global_step": 342719, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0656754970550537, "global_step": 342720, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.123548984527588, "global_step": 342721, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1163289546966553, "global_step": 342722, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0617759227752686, "global_step": 342723, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0814948081970215, "global_step": 342724, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.173579692840576, "global_step": 342725, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0352783203125, "global_step": 342726, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1337203979492188, "global_step": 342727, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.947723627090454, "global_step": 342728, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0818657875061035, "global_step": 342729, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1265993118286133, "global_step": 342730, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0457260608673096, "global_step": 342731, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0538740158081055, "global_step": 342732, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9797511100769043, "global_step": 342733, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.136476516723633, "global_step": 342734, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1313929557800293, "global_step": 342735, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1528584957122803, "global_step": 342736, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0814859867095947, "global_step": 342737, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1021602153778076, "global_step": 342738, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.151089906692505, "global_step": 342739, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1658942699432373, "global_step": 342740, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1142778396606445, "global_step": 342741, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0660693645477295, "global_step": 342742, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.133273124694824, "global_step": 342743, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.139662027359009, "global_step": 342744, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.2229745388031006, "global_step": 342745, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1511878967285156, "global_step": 342746, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1068897247314453, "global_step": 342747, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0211048126220703, "global_step": 342748, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.12567400932312, "global_step": 342749, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0447843074798584, "global_step": 342750, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0821006298065186, "global_step": 342751, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1631181240081787, "global_step": 342752, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1414682865142822, "global_step": 342753, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.018678903579712, "global_step": 342754, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1403372287750244, "global_step": 342755, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0778260231018066, "global_step": 342756, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1068944931030273, "global_step": 342757, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.163482904434204, "global_step": 342758, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.122920274734497, "global_step": 342759, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0745043754577637, "global_step": 342760, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0652637481689453, "global_step": 342761, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0515224933624268, "global_step": 342762, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0651097297668457, "global_step": 342763, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1160120964050293, "global_step": 342764, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.17431378364563, "global_step": 342765, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.988710880279541, "global_step": 342766, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.040722131729126, "global_step": 342767, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1541848182678223, "global_step": 342768, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1720035076141357, "global_step": 342769, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0709357261657715, "global_step": 342770, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.113830804824829, "global_step": 342771, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.099620819091797, "global_step": 342772, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.115417718887329, "global_step": 342773, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.162564516067505, "global_step": 342774, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.142749309539795, "global_step": 342775, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1588962078094482, "global_step": 342776, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9465519189834595, "global_step": 342777, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1349337100982666, "global_step": 342778, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.047137975692749, "global_step": 342779, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.005702018737793, "global_step": 342780, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.085200071334839, "global_step": 342781, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0446174144744873, "global_step": 342782, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.086313247680664, "global_step": 342783, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.055790901184082, "global_step": 342784, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.081707239151001, "global_step": 342785, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.045261859893799, "global_step": 342786, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.163238525390625, "global_step": 342787, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.051103115081787, "global_step": 342788, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.14066481590271, "global_step": 342789, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.109964370727539, "global_step": 342790, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0563063621520996, "global_step": 342791, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.2151200771331787, "global_step": 342792, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0625452995300293, "global_step": 342793, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0996646881103516, "global_step": 342794, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0416107177734375, "global_step": 342795, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1575543880462646, "global_step": 342796, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.160285711288452, "global_step": 342797, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.035999059677124, "global_step": 342798, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.162217855453491, "global_step": 342799, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.139617681503296, "global_step": 342800, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1523542404174805, "global_step": 342801, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.137362480163574, "global_step": 342802, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1678426265716553, "global_step": 342803, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0691139698028564, "global_step": 342804, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.013601303100586, "global_step": 342805, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1100895404815674, "global_step": 342806, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1599979400634766, "global_step": 342807, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.116630792617798, "global_step": 342808, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.15429949760437, "global_step": 342809, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1487982273101807, "global_step": 342810, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.144622325897217, "global_step": 342811, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.040480136871338, "global_step": 342812, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0912015438079834, "global_step": 342813, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.144681930541992, "global_step": 342814, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1875641345977783, "global_step": 342815, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.029212474822998, "global_step": 342816, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.067655086517334, "global_step": 342817, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1102945804595947, "global_step": 342818, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.132483959197998, "global_step": 342819, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.15956974029541, "global_step": 342820, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.138507127761841, "global_step": 342821, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.208071708679199, "global_step": 342822, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.2066450119018555, "global_step": 342823, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.047637701034546, "global_step": 342824, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.167701005935669, "global_step": 342825, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1550650596618652, "global_step": 342826, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1230993270874023, "global_step": 342827, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1276450157165527, "global_step": 342828, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.164130926132202, "global_step": 342829, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1180264949798584, "global_step": 342830, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1830599308013916, "global_step": 342831, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0095579624176025, "global_step": 342832, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.157177448272705, "global_step": 342833, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.2447235584259033, "global_step": 342834, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.089670419692993, "global_step": 342835, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1025524139404297, "global_step": 342836, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.186154842376709, "global_step": 342837, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0892393589019775, "global_step": 342838, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.142737627029419, "global_step": 342839, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1237659454345703, "global_step": 342840, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.096590518951416, "global_step": 342841, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.126774311065674, "global_step": 342842, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1199634075164795, "global_step": 342843, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.101045608520508, "global_step": 342844, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0664772987365723, "global_step": 342845, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.062234401702881, "global_step": 342846, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1018569469451904, "global_step": 342847, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.092500686645508, "global_step": 342848, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.101311445236206, "global_step": 342849, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1795434951782227, "global_step": 342850, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1351470947265625, "global_step": 342851, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1833531856536865, "global_step": 342852, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1416525840759277, "global_step": 342853, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9953306913375854, "global_step": 342854, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1731321811676025, "global_step": 342855, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.102828025817871, "global_step": 342856, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.107245922088623, "global_step": 342857, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1113829612731934, "global_step": 342858, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1389334201812744, "global_step": 342859, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.103243112564087, "global_step": 342860, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0891988277435303, "global_step": 342861, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.165148973464966, "global_step": 342862, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0759880542755127, "global_step": 342863, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0285019874572754, "global_step": 342864, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0858259201049805, "global_step": 342865, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1559805870056152, "global_step": 342866, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1380882263183594, "global_step": 342867, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1002254486083984, "global_step": 342868, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1599040031433105, "global_step": 342869, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.187700033187866, "global_step": 342870, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.077901840209961, "global_step": 342871, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.048848867416382, "global_step": 342872, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.106698513031006, "global_step": 342873, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.123293399810791, "global_step": 342874, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1501331329345703, "global_step": 342875, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1471898555755615, "global_step": 342876, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1293861865997314, "global_step": 342877, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1998729705810547, "global_step": 342878, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0347177982330322, "global_step": 342879, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0550897121429443, "global_step": 342880, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.11030912399292, "global_step": 342881, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.167348623275757, "global_step": 342882, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1066219806671143, "global_step": 342883, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1520042419433594, "global_step": 342884, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.100289821624756, "global_step": 342885, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.2264909744262695, "global_step": 342886, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.172590494155884, "global_step": 342887, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.085779905319214, "global_step": 342888, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1509952545166016, "global_step": 342889, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0898995399475098, "global_step": 342890, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1284067630767822, "global_step": 342891, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1726975440979004, "global_step": 342892, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.132388114929199, "global_step": 342893, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1607542037963867, "global_step": 342894, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1204988956451416, "global_step": 342895, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.223226547241211, "global_step": 342896, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1128411293029785, "global_step": 342897, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.041722297668457, "global_step": 342898, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.135573387145996, "global_step": 342899, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1814370155334473, "global_step": 342900, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0993330478668213, "global_step": 342901, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.164324998855591, "global_step": 342902, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.084512948989868, "global_step": 342903, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0450856685638428, "global_step": 342904, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0076231956481934, "global_step": 342905, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9883229732513428, "global_step": 342906, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.089015007019043, "global_step": 342907, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1093528270721436, "global_step": 342908, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.030388116836548, "global_step": 342909, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0768587589263916, "global_step": 342910, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1062796115875244, "global_step": 342911, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1304285526275635, "global_step": 342912, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.083101749420166, "global_step": 342913, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.147197961807251, "global_step": 342914, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1933083534240723, "global_step": 342915, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1547911167144775, "global_step": 342916, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0696146488189697, "global_step": 342917, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9938020706176758, "global_step": 342918, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0521249771118164, "global_step": 342919, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0541622638702393, "global_step": 342920, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.173983335494995, "global_step": 342921, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.174102544784546, "global_step": 342922, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0919318199157715, "global_step": 342923, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.115143060684204, "global_step": 342924, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.140443801879883, "global_step": 342925, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.143056631088257, "global_step": 342926, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.063781261444092, "global_step": 342927, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.093050956726074, "global_step": 342928, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0673935413360596, "global_step": 342929, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.072321891784668, "global_step": 342930, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1673429012298584, "global_step": 342931, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.082221031188965, "global_step": 342932, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.07944655418396, "global_step": 342933, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1001412868499756, "global_step": 342934, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1378393173217773, "global_step": 342935, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1225645542144775, "global_step": 342936, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1448657512664795, "global_step": 342937, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0945112705230713, "global_step": 342938, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1208157539367676, "global_step": 342939, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.157893419265747, "global_step": 342940, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1452243328094482, "global_step": 342941, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.124105453491211, "global_step": 342942, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.069208860397339, "global_step": 342943, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.104842185974121, "global_step": 342944, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1756033897399902, "global_step": 342945, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.053040027618408, "global_step": 342946, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0343685150146484, "global_step": 342947, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.094132423400879, "global_step": 342948, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.035080671310425, "global_step": 342949, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1268930435180664, "global_step": 342950, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0931389331817627, "global_step": 342951, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.08333683013916, "global_step": 342952, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1300981044769287, "global_step": 342953, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.102043628692627, "global_step": 342954, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0310652256011963, "global_step": 342955, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.063948392868042, "global_step": 342956, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0825908184051514, "global_step": 342957, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0742180347442627, "global_step": 342958, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.102396249771118, "global_step": 342959, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.114089012145996, "global_step": 342960, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9305380582809448, "global_step": 342961, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.143566846847534, "global_step": 342962, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.092984676361084, "global_step": 342963, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0987231731414795, "global_step": 342964, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.08914852142334, "global_step": 342965, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0591156482696533, "global_step": 342966, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.096991539001465, "global_step": 342967, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.058715581893921, "global_step": 342968, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.058579444885254, "global_step": 342969, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1244330406188965, "global_step": 342970, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1094772815704346, "global_step": 342971, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.19846510887146, "global_step": 342972, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.152883529663086, "global_step": 342973, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.157846689224243, "global_step": 342974, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1419992446899414, "global_step": 342975, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.083346366882324, "global_step": 342976, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0644068717956543, "global_step": 342977, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.137824058532715, "global_step": 342978, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.123964309692383, "global_step": 342979, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.163355588912964, "global_step": 342980, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.087480306625366, "global_step": 342981, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.086841583251953, "global_step": 342982, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9610035419464111, "global_step": 342983, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0727639198303223, "global_step": 342984, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0573909282684326, "global_step": 342985, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.036031723022461, "global_step": 342986, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.145362615585327, "global_step": 342987, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.041004180908203, "global_step": 342988, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1071937084198, "global_step": 342989, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0720386505126953, "global_step": 342990, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.13759446144104, "global_step": 342991, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.083432912826538, "global_step": 342992, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.145939588546753, "global_step": 342993, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0421338081359863, "global_step": 342994, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.131110668182373, "global_step": 342995, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1285581588745117, "global_step": 342996, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1174824237823486, "global_step": 342997, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.08825421333313, "global_step": 342998, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1884005069732666, "global_step": 342999, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.097167730331421, "global_step": 343000, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0620760917663574, "global_step": 343001, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.130150318145752, "global_step": 343002, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0662429332733154, "global_step": 343003, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.008312940597534, "global_step": 343004, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1186838150024414, "global_step": 343005, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.034954071044922, "global_step": 343006, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.058203935623169, "global_step": 343007, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0793018341064453, "global_step": 343008, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1623764038085938, "global_step": 343009, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0785534381866455, "global_step": 343010, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0768589973449707, "global_step": 343011, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1557979583740234, "global_step": 343012, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.126784086227417, "global_step": 343013, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1935784816741943, "global_step": 343014, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0507969856262207, "global_step": 343015, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0513722896575928, "global_step": 343016, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1536965370178223, "global_step": 343017, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1423020362854004, "global_step": 343018, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0711615085601807, "global_step": 343019, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0482535362243652, "global_step": 343020, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1593081951141357, "global_step": 343021, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1593480110168457, "global_step": 343022, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.100344657897949, "global_step": 343023, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1860148906707764, "global_step": 343024, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.161068916320801, "global_step": 343025, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.102695941925049, "global_step": 343026, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.096644639968872, "global_step": 343027, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.096647024154663, "global_step": 343028, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.012559413909912, "global_step": 343029, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.150360584259033, "global_step": 343030, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1435954570770264, "global_step": 343031, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1255481243133545, "global_step": 343032, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0650317668914795, "global_step": 343033, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.024871587753296, "global_step": 343034, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0286552906036377, "global_step": 343035, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.110698699951172, "global_step": 343036, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.096060037612915, "global_step": 343037, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0232033729553223, "global_step": 343038, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.149421453475952, "global_step": 343039, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0741257667541504, "global_step": 343040, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.04386830329895, "global_step": 343041, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.118147850036621, "global_step": 343042, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1419496536254883, "global_step": 343043, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.131614923477173, "global_step": 343044, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0866570472717285, "global_step": 343045, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.069307565689087, "global_step": 343046, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1855592727661133, "global_step": 343047, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9925252199172974, "global_step": 343048, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.114182233810425, "global_step": 343049, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.077867269515991, "global_step": 343050, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.183382749557495, "global_step": 343051, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9878686666488647, "global_step": 343052, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.113069534301758, "global_step": 343053, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.087297201156616, "global_step": 343054, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0049631595611572, "global_step": 343055, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1399009227752686, "global_step": 343056, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1765670776367188, "global_step": 343057, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1913974285125732, "global_step": 343058, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.075937271118164, "global_step": 343059, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.120285987854004, "global_step": 343060, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0803444385528564, "global_step": 343061, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0858142375946045, "global_step": 343062, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.004117250442505, "global_step": 343063, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.080519914627075, "global_step": 343064, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1056442260742188, "global_step": 343065, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.195213556289673, "global_step": 343066, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0758917331695557, "global_step": 343067, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0222065448760986, "global_step": 343068, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.060788869857788, "global_step": 343069, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.127720832824707, "global_step": 343070, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1267147064208984, "global_step": 343071, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1717238426208496, "global_step": 343072, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1403133869171143, "global_step": 343073, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.131287097930908, "global_step": 343074, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0960097312927246, "global_step": 343075, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1358187198638916, "global_step": 343076, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.072960376739502, "global_step": 343077, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.072490692138672, "global_step": 343078, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.156115770339966, "global_step": 343079, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0863735675811768, "global_step": 343080, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1133148670196533, "global_step": 343081, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1373777389526367, "global_step": 343082, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0914158821105957, "global_step": 343083, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1442830562591553, "global_step": 343084, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.086580991744995, "global_step": 343085, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0857720375061035, "global_step": 343086, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1842494010925293, "global_step": 343087, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.210078477859497, "global_step": 343088, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.081726551055908, "global_step": 343089, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1136088371276855, "global_step": 343090, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1264657974243164, "global_step": 343091, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.084991693496704, "global_step": 343092, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1403017044067383, "global_step": 343093, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1795575618743896, "global_step": 343094, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0899572372436523, "global_step": 343095, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.133248805999756, "global_step": 343096, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0710041522979736, "global_step": 343097, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0530710220336914, "global_step": 343098, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.088534116744995, "global_step": 343099, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0785341262817383, "global_step": 343100, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0277884006500244, "global_step": 343101, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.139284133911133, "global_step": 343102, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.002559185028076, "global_step": 343103, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.068018913269043, "global_step": 343104, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1226720809936523, "global_step": 343105, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.056709051132202, "global_step": 343106, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1630873680114746, "global_step": 343107, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.08597469329834, "global_step": 343108, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1801164150238037, "global_step": 343109, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.2122244834899902, "global_step": 343110, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0352985858917236, "global_step": 343111, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1361539363861084, "global_step": 343112, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.111248016357422, "global_step": 343113, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1212730407714844, "global_step": 343114, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.2103118896484375, "global_step": 343115, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1179254055023193, "global_step": 343116, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0796470642089844, "global_step": 343117, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.118605375289917, "global_step": 343118, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1035752296447754, "global_step": 343119, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.007779359817505, "global_step": 343120, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.055016279220581, "global_step": 343121, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.006693124771118, "global_step": 343122, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1302382946014404, "global_step": 343123, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.209122657775879, "global_step": 343124, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.109578847885132, "global_step": 343125, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.18135142326355, "global_step": 343126, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.226132392883301, "global_step": 343127, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.093332052230835, "global_step": 343128, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.063382148742676, "global_step": 343129, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1687655448913574, "global_step": 343130, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1137568950653076, "global_step": 343131, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0337183475494385, "global_step": 343132, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1080353260040283, "global_step": 343133, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1004111766815186, "global_step": 343134, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1428472995758057, "global_step": 343135, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0724141597747803, "global_step": 343136, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1586906909942627, "global_step": 343137, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1883771419525146, "global_step": 343138, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0691473484039307, "global_step": 343139, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1172232627868652, "global_step": 343140, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0842297077178955, "global_step": 343141, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0315041542053223, "global_step": 343142, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0767600536346436, "global_step": 343143, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0628063678741455, "global_step": 343144, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0654783248901367, "global_step": 343145, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.117375373840332, "global_step": 343146, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.2148194313049316, "global_step": 343147, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.032733678817749, "global_step": 343148, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1516928672790527, "global_step": 343149, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.064918041229248, "global_step": 343150, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1327760219573975, "global_step": 343151, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1219065189361572, "global_step": 343152, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1305618286132812, "global_step": 343153, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.241560697555542, "global_step": 343154, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.039543867111206, "global_step": 343155, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.0344228744506836, "global_step": 343156, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1460275650024414, "global_step": 343157, "epoch": 703, "lr": 5e-05}
{"train_loss": 2.1027603149414062, "global_step": 343158, "epoch": 703, "lr": 5e-05}
{"train_loss": 1.9712607860565186, "global_step": 343159, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1284358501434326, "global_step": 343160, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.070053815841675, "global_step": 343161, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.058703660964966, "global_step": 343162, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0922045707702637, "global_step": 343163, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.113372564315796, "global_step": 343164, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.142178773880005, "global_step": 343165, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0946662425994873, "global_step": 343166, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1101560592651367, "global_step": 343167, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0601577758789062, "global_step": 343168, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1245906352996826, "global_step": 343169, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.126478672027588, "global_step": 343170, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.081085681915283, "global_step": 343171, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1056010723114014, "global_step": 343172, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0940189361572266, "global_step": 343173, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.041138172149658, "global_step": 343174, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1050405502319336, "global_step": 343175, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0747292041778564, "global_step": 343176, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1169798374176025, "global_step": 343177, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.013596296310425, "global_step": 343178, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1028330326080322, "global_step": 343179, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0533463954925537, "global_step": 343180, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1188504695892334, "global_step": 343181, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.100546360015869, "global_step": 343182, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.077515125274658, "global_step": 343183, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.093982219696045, "global_step": 343184, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.109004020690918, "global_step": 343185, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.2012887001037598, "global_step": 343186, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.077186346054077, "global_step": 343187, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.073981285095215, "global_step": 343188, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1003832817077637, "global_step": 343189, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.113471269607544, "global_step": 343190, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0046005249023438, "global_step": 343191, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0822560787200928, "global_step": 343192, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.067020893096924, "global_step": 343193, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0542848110198975, "global_step": 343194, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0265116691589355, "global_step": 343195, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.069342851638794, "global_step": 343196, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0050737857818604, "global_step": 343197, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0260584354400635, "global_step": 343198, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1407716274261475, "global_step": 343199, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0744340419769287, "global_step": 343200, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.071645736694336, "global_step": 343201, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.092043876647949, "global_step": 343202, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1955273151397705, "global_step": 343203, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.042025089263916, "global_step": 343204, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0390992164611816, "global_step": 343205, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1150600910186768, "global_step": 343206, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1548337936401367, "global_step": 343207, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0782413482666016, "global_step": 343208, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.126620054244995, "global_step": 343209, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1244568824768066, "global_step": 343210, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.098202705383301, "global_step": 343211, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0576608180999756, "global_step": 343212, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0906059741973877, "global_step": 343213, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0331356525421143, "global_step": 343214, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.155451536178589, "global_step": 343215, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0999417304992676, "global_step": 343216, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.149275779724121, "global_step": 343217, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.155207395553589, "global_step": 343218, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1196742057800293, "global_step": 343219, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0984714031219482, "global_step": 343220, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.998576045036316, "global_step": 343221, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0258123874664307, "global_step": 343222, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.122413158416748, "global_step": 343223, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.119595766067505, "global_step": 343224, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0954506397247314, "global_step": 343225, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.045403480529785, "global_step": 343226, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.03251051902771, "global_step": 343227, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.008793592453003, "global_step": 343228, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.089233875274658, "global_step": 343229, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.107351541519165, "global_step": 343230, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1078457832336426, "global_step": 343231, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.076742172241211, "global_step": 343232, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.028445243835449, "global_step": 343233, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.112009286880493, "global_step": 343234, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0371623039245605, "global_step": 343235, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.111443519592285, "global_step": 343236, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1008424758911133, "global_step": 343237, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.053291082382202, "global_step": 343238, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.2003443241119385, "global_step": 343239, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.064955949783325, "global_step": 343240, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.9976003170013428, "global_step": 343241, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0831732749938965, "global_step": 343242, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.072535753250122, "global_step": 343243, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.135322332382202, "global_step": 343244, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1528377532958984, "global_step": 343245, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0537664890289307, "global_step": 343246, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1730008125305176, "global_step": 343247, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1112678050994873, "global_step": 343248, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.9789077043533325, "global_step": 343249, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.069411277770996, "global_step": 343250, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.133014678955078, "global_step": 343251, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1336848735809326, "global_step": 343252, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.056196928024292, "global_step": 343253, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.083841323852539, "global_step": 343254, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.032594919204712, "global_step": 343255, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1361424922943115, "global_step": 343256, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1224241256713867, "global_step": 343257, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1340208053588867, "global_step": 343258, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0702545642852783, "global_step": 343259, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.132606029510498, "global_step": 343260, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.252898693084717, "global_step": 343261, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.956689715385437, "global_step": 343262, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1306991577148438, "global_step": 343263, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.075639009475708, "global_step": 343264, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.174219846725464, "global_step": 343265, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1059458255767822, "global_step": 343266, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1512138843536377, "global_step": 343267, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.184974193572998, "global_step": 343268, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0921828746795654, "global_step": 343269, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.111665725708008, "global_step": 343270, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.025803804397583, "global_step": 343271, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1432013511657715, "global_step": 343272, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1622085571289062, "global_step": 343273, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1207423210144043, "global_step": 343274, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.093146800994873, "global_step": 343275, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.153731107711792, "global_step": 343276, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1224920749664307, "global_step": 343277, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.110203742980957, "global_step": 343278, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0808684825897217, "global_step": 343279, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.053217887878418, "global_step": 343280, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.070807933807373, "global_step": 343281, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.059875011444092, "global_step": 343282, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.138507604598999, "global_step": 343283, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.113203287124634, "global_step": 343284, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.122373104095459, "global_step": 343285, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0470423698425293, "global_step": 343286, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.09291672706604, "global_step": 343287, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0178017616271973, "global_step": 343288, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0952248573303223, "global_step": 343289, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1513655185699463, "global_step": 343290, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0824012756347656, "global_step": 343291, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.132406711578369, "global_step": 343292, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0662076473236084, "global_step": 343293, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.030402183532715, "global_step": 343294, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0413405895233154, "global_step": 343295, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.035104990005493, "global_step": 343296, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.9604209661483765, "global_step": 343297, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.121025323867798, "global_step": 343298, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0610663890838623, "global_step": 343299, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0721993446350098, "global_step": 343300, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.9423637390136719, "global_step": 343301, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0417397022247314, "global_step": 343302, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1085798740386963, "global_step": 343303, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.180922269821167, "global_step": 343304, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.096771478652954, "global_step": 343305, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.127211809158325, "global_step": 343306, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1908037662506104, "global_step": 343307, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0440380573272705, "global_step": 343308, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0480165481567383, "global_step": 343309, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.072375535964966, "global_step": 343310, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.05047345161438, "global_step": 343311, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0213217735290527, "global_step": 343312, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1347057819366455, "global_step": 343313, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0617291927337646, "global_step": 343314, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.092444896697998, "global_step": 343315, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.131803274154663, "global_step": 343316, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0661580562591553, "global_step": 343317, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1099307537078857, "global_step": 343318, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1240010261535645, "global_step": 343319, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0114290714263916, "global_step": 343320, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.096492052078247, "global_step": 343321, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0707409381866455, "global_step": 343322, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1562204360961914, "global_step": 343323, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1508891582489014, "global_step": 343324, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1654539108276367, "global_step": 343325, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0708534717559814, "global_step": 343326, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.080197811126709, "global_step": 343327, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.083730459213257, "global_step": 343328, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.9668432474136353, "global_step": 343329, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.2679078578948975, "global_step": 343330, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0404844284057617, "global_step": 343331, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.2135753631591797, "global_step": 343332, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.112894296646118, "global_step": 343333, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.00872802734375, "global_step": 343334, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1079514026641846, "global_step": 343335, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1347873210906982, "global_step": 343336, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0691490173339844, "global_step": 343337, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1302125453948975, "global_step": 343338, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1308271884918213, "global_step": 343339, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.080423593521118, "global_step": 343340, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.147742986679077, "global_step": 343341, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.069394826889038, "global_step": 343342, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1924123764038086, "global_step": 343343, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.103365421295166, "global_step": 343344, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1145403385162354, "global_step": 343345, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.106293201446533, "global_step": 343346, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.060567617416382, "global_step": 343347, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.056422710418701, "global_step": 343348, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1019113063812256, "global_step": 343349, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.176703929901123, "global_step": 343350, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.158897638320923, "global_step": 343351, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1060969829559326, "global_step": 343352, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1015748977661133, "global_step": 343353, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.096585988998413, "global_step": 343354, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0798161029815674, "global_step": 343355, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.079240083694458, "global_step": 343356, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1810109615325928, "global_step": 343357, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1506621837615967, "global_step": 343358, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0938220024108887, "global_step": 343359, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.012096643447876, "global_step": 343360, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.098691701889038, "global_step": 343361, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0841965675354004, "global_step": 343362, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.095906972885132, "global_step": 343363, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.018934965133667, "global_step": 343364, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.103224039077759, "global_step": 343365, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1252281665802, "global_step": 343366, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0291383266448975, "global_step": 343367, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.065403461456299, "global_step": 343368, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.2174324989318848, "global_step": 343369, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.136350154876709, "global_step": 343370, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1380836963653564, "global_step": 343371, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1337218284606934, "global_step": 343372, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.123417377471924, "global_step": 343373, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1353962421417236, "global_step": 343374, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0542917251586914, "global_step": 343375, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.155445098876953, "global_step": 343376, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1011130809783936, "global_step": 343377, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.037554979324341, "global_step": 343378, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.2141590118408203, "global_step": 343379, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1013100147247314, "global_step": 343380, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.09968638420105, "global_step": 343381, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.03933048248291, "global_step": 343382, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.067176342010498, "global_step": 343383, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.163167715072632, "global_step": 343384, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.065356731414795, "global_step": 343385, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0435357093811035, "global_step": 343386, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0983033180236816, "global_step": 343387, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.086477518081665, "global_step": 343388, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.04093074798584, "global_step": 343389, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.9967591762542725, "global_step": 343390, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0770115852355957, "global_step": 343391, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.190329074859619, "global_step": 343392, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.027808666229248, "global_step": 343393, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0241916179656982, "global_step": 343394, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.162980079650879, "global_step": 343395, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.05837345123291, "global_step": 343396, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.169421911239624, "global_step": 343397, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.094548463821411, "global_step": 343398, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1294968128204346, "global_step": 343399, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.163018226623535, "global_step": 343400, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1582982540130615, "global_step": 343401, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1950843334198, "global_step": 343402, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.072533130645752, "global_step": 343403, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1499476432800293, "global_step": 343404, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1583900451660156, "global_step": 343405, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0958027839660645, "global_step": 343406, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.9623466730117798, "global_step": 343407, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.038262367248535, "global_step": 343408, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0820553302764893, "global_step": 343409, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1366212368011475, "global_step": 343410, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0768792629241943, "global_step": 343411, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1050031185150146, "global_step": 343412, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1370606422424316, "global_step": 343413, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1016685962677, "global_step": 343414, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0388057231903076, "global_step": 343415, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.109837055206299, "global_step": 343416, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1235246658325195, "global_step": 343417, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1446590423583984, "global_step": 343418, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1436142921447754, "global_step": 343419, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.163655996322632, "global_step": 343420, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.044114351272583, "global_step": 343421, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1242644786834717, "global_step": 343422, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.151703357696533, "global_step": 343423, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.018479347229004, "global_step": 343424, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.105747699737549, "global_step": 343425, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1603384017944336, "global_step": 343426, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.120069742202759, "global_step": 343427, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1216776371002197, "global_step": 343428, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1472227573394775, "global_step": 343429, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1031441688537598, "global_step": 343430, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1521236896514893, "global_step": 343431, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1628715991973877, "global_step": 343432, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.215333938598633, "global_step": 343433, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1582720279693604, "global_step": 343434, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.119067907333374, "global_step": 343435, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0508618354797363, "global_step": 343436, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1391193866729736, "global_step": 343437, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.060122489929199, "global_step": 343438, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0441246032714844, "global_step": 343439, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0610194206237793, "global_step": 343440, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1442596912384033, "global_step": 343441, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1986587047576904, "global_step": 343442, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.12804913520813, "global_step": 343443, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1525464057922363, "global_step": 343444, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.096601724624634, "global_step": 343445, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.138685464859009, "global_step": 343446, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1442954540252686, "global_step": 343447, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0913398265838623, "global_step": 343448, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1950745582580566, "global_step": 343449, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0640084743499756, "global_step": 343450, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.2135133743286133, "global_step": 343451, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0802738666534424, "global_step": 343452, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0294923782348633, "global_step": 343453, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.171647787094116, "global_step": 343454, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1121137142181396, "global_step": 343455, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1023612022399902, "global_step": 343456, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0748424530029297, "global_step": 343457, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0052616596221924, "global_step": 343458, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.075143575668335, "global_step": 343459, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.082914113998413, "global_step": 343460, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.072272539138794, "global_step": 343461, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.133756399154663, "global_step": 343462, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.129730463027954, "global_step": 343463, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1383440494537354, "global_step": 343464, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.102149486541748, "global_step": 343465, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1289734840393066, "global_step": 343466, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0682506561279297, "global_step": 343467, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.139012098312378, "global_step": 343468, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0852444171905518, "global_step": 343469, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.099954843521118, "global_step": 343470, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.074990749359131, "global_step": 343471, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0592315196990967, "global_step": 343472, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.114743232727051, "global_step": 343473, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.087848424911499, "global_step": 343474, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1618430614471436, "global_step": 343475, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.122863531112671, "global_step": 343476, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.178941011428833, "global_step": 343477, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.130739450454712, "global_step": 343478, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1538660526275635, "global_step": 343479, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.139967441558838, "global_step": 343480, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.010403871536255, "global_step": 343481, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.139209747314453, "global_step": 343482, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.088996171951294, "global_step": 343483, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.11122727394104, "global_step": 343484, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1527299880981445, "global_step": 343485, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1379387378692627, "global_step": 343486, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1168205738067627, "global_step": 343487, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.065901517868042, "global_step": 343488, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1325523853302, "global_step": 343489, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0511744022369385, "global_step": 343490, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1063332557678223, "global_step": 343491, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0657362937927246, "global_step": 343492, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.076214551925659, "global_step": 343493, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.126875638961792, "global_step": 343494, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1088809967041016, "global_step": 343495, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.091636896133423, "global_step": 343496, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1721601486206055, "global_step": 343497, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.2507734298706055, "global_step": 343498, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0679943561553955, "global_step": 343499, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0522708892822266, "global_step": 343500, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.085127592086792, "global_step": 343501, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.2016000747680664, "global_step": 343502, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.097416639328003, "global_step": 343503, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0401198863983154, "global_step": 343504, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0957655906677246, "global_step": 343505, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.103174924850464, "global_step": 343506, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.102569580078125, "global_step": 343507, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0715348720550537, "global_step": 343508, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.052330493927002, "global_step": 343509, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.122854232788086, "global_step": 343510, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0953540802001953, "global_step": 343511, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.134913444519043, "global_step": 343512, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1287758350372314, "global_step": 343513, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.130746841430664, "global_step": 343514, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.058628797531128, "global_step": 343515, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.149080276489258, "global_step": 343516, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1127660274505615, "global_step": 343517, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0883865356445312, "global_step": 343518, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0937676429748535, "global_step": 343519, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1805648803710938, "global_step": 343520, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.9707859754562378, "global_step": 343521, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.170194387435913, "global_step": 343522, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0474658012390137, "global_step": 343523, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1165647506713867, "global_step": 343524, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0888350009918213, "global_step": 343525, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.144974708557129, "global_step": 343526, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.080507516860962, "global_step": 343527, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0608389377593994, "global_step": 343528, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.9506901502609253, "global_step": 343529, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.117671251296997, "global_step": 343530, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.188744068145752, "global_step": 343531, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0535452365875244, "global_step": 343532, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.120126724243164, "global_step": 343533, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.040036916732788, "global_step": 343534, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1493821144104004, "global_step": 343535, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1618969440460205, "global_step": 343536, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1813223361968994, "global_step": 343537, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0786101818084717, "global_step": 343538, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.143876314163208, "global_step": 343539, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1055197715759277, "global_step": 343540, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.090857982635498, "global_step": 343541, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0805084705352783, "global_step": 343542, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.125901222229004, "global_step": 343543, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1340506076812744, "global_step": 343544, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.167998790740967, "global_step": 343545, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.147745370864868, "global_step": 343546, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1810073852539062, "global_step": 343547, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.164310932159424, "global_step": 343548, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1451237201690674, "global_step": 343549, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0915613174438477, "global_step": 343550, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0966999530792236, "global_step": 343551, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.155945301055908, "global_step": 343552, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1247339248657227, "global_step": 343553, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1771130561828613, "global_step": 343554, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.241135835647583, "global_step": 343555, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1541707515716553, "global_step": 343556, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1620681285858154, "global_step": 343557, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1155285835266113, "global_step": 343558, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1268744468688965, "global_step": 343559, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.136732578277588, "global_step": 343560, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0900039672851562, "global_step": 343561, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0628769397735596, "global_step": 343562, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.08620285987854, "global_step": 343563, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.2027618885040283, "global_step": 343564, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0420217514038086, "global_step": 343565, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1316378116607666, "global_step": 343566, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.072972297668457, "global_step": 343567, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.006101608276367, "global_step": 343568, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1185221672058105, "global_step": 343569, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.149923086166382, "global_step": 343570, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.95729398727417, "global_step": 343571, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1158790588378906, "global_step": 343572, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.102546215057373, "global_step": 343573, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1137611865997314, "global_step": 343574, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.178830146789551, "global_step": 343575, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.141373634338379, "global_step": 343576, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1849653720855713, "global_step": 343577, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.139035224914551, "global_step": 343578, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1478071212768555, "global_step": 343579, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.115243911743164, "global_step": 343580, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.007049322128296, "global_step": 343581, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.182704448699951, "global_step": 343582, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.104896306991577, "global_step": 343583, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.11328125, "global_step": 343584, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1764273643493652, "global_step": 343585, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1008858680725098, "global_step": 343586, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.230088710784912, "global_step": 343587, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.053819417953491, "global_step": 343588, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1682686805725098, "global_step": 343589, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.060581684112549, "global_step": 343590, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1883997917175293, "global_step": 343591, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1426291465759277, "global_step": 343592, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0959279537200928, "global_step": 343593, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.189643383026123, "global_step": 343594, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0696723461151123, "global_step": 343595, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1669952869415283, "global_step": 343596, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.128021717071533, "global_step": 343597, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1855556964874268, "global_step": 343598, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.07077956199646, "global_step": 343599, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.053285837173462, "global_step": 343600, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.059654712677002, "global_step": 343601, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.245828151702881, "global_step": 343602, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0481903553009033, "global_step": 343603, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.162534236907959, "global_step": 343604, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1136701107025146, "global_step": 343605, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0889463424682617, "global_step": 343606, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1683032512664795, "global_step": 343607, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.15545392036438, "global_step": 343608, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0496292114257812, "global_step": 343609, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0314741134643555, "global_step": 343610, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0471534729003906, "global_step": 343611, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1193935871124268, "global_step": 343612, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.146744966506958, "global_step": 343613, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1561543941497803, "global_step": 343614, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.075493812561035, "global_step": 343615, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.10697340965271, "global_step": 343616, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1505157947540283, "global_step": 343617, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1011977195739746, "global_step": 343618, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1019511222839355, "global_step": 343619, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1625428199768066, "global_step": 343620, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0896217823028564, "global_step": 343621, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.089939594268799, "global_step": 343622, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.043668508529663, "global_step": 343623, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.061915159225464, "global_step": 343624, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0977985858917236, "global_step": 343625, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.179504632949829, "global_step": 343626, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0367918014526367, "global_step": 343627, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0896716117858887, "global_step": 343628, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1172313690185547, "global_step": 343629, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1221916675567627, "global_step": 343630, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0143918991088867, "global_step": 343631, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0805623531341553, "global_step": 343632, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1610419750213623, "global_step": 343633, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.115489959716797, "global_step": 343634, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.2195851802825928, "global_step": 343635, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.079051971435547, "global_step": 343636, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.130561351776123, "global_step": 343637, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.168264865875244, "global_step": 343638, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.119277000427246, "global_step": 343639, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.068516492843628, "global_step": 343640, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.105065107345581, "global_step": 343641, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.164583921432495, "global_step": 343642, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.138789415359497, "global_step": 343643, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.060239315032959, "global_step": 343644, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.2047808170318604, "global_step": 343645, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1591973304748535, "global_step": 343646, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0138916969299316, "global_step": 343647, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1072275638580322, "global_step": 343648, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.102707624435425, "global_step": 343649, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1360254287719727, "global_step": 343650, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1730570793151855, "global_step": 343651, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.147310733795166, "global_step": 343652, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1002538204193115, "global_step": 343653, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.175215244293213, "global_step": 343654, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.050624370574951, "global_step": 343655, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.9977730512619019, "global_step": 343656, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.107605218887329, "global_step": 343657, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0147624015808105, "global_step": 343658, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0629348754882812, "global_step": 343659, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.14453125, "global_step": 343660, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0621140003204346, "global_step": 343661, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.08766508102417, "global_step": 343662, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0449652671813965, "global_step": 343663, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1069204807281494, "global_step": 343664, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.091980218887329, "global_step": 343665, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.031558036804199, "global_step": 343666, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.100085496902466, "global_step": 343667, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0408084392547607, "global_step": 343668, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0120179653167725, "global_step": 343669, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.979433298110962, "global_step": 343670, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.089643955230713, "global_step": 343671, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1265223026275635, "global_step": 343672, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.020108699798584, "global_step": 343673, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.179499626159668, "global_step": 343674, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0840837955474854, "global_step": 343675, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1243629455566406, "global_step": 343676, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.2276039123535156, "global_step": 343677, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1101622581481934, "global_step": 343678, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.063831090927124, "global_step": 343679, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1431291103363037, "global_step": 343680, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.216930627822876, "global_step": 343681, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.127650260925293, "global_step": 343682, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.2012734413146973, "global_step": 343683, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1080827713012695, "global_step": 343684, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.999122142791748, "global_step": 343685, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.020003080368042, "global_step": 343686, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.132812976837158, "global_step": 343687, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1021201610565186, "global_step": 343688, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1340675354003906, "global_step": 343689, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1692287921905518, "global_step": 343690, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1384739875793457, "global_step": 343691, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.156592845916748, "global_step": 343692, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.080228090286255, "global_step": 343693, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0565783977508545, "global_step": 343694, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.079841375350952, "global_step": 343695, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1374521255493164, "global_step": 343696, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.116760730743408, "global_step": 343697, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1235978603363037, "global_step": 343698, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1055026054382324, "global_step": 343699, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.082075357437134, "global_step": 343700, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0194993019104004, "global_step": 343701, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1979494094848633, "global_step": 343702, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.242908000946045, "global_step": 343703, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.2018961906433105, "global_step": 343704, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0312395095825195, "global_step": 343705, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.150278091430664, "global_step": 343706, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1023571491241455, "global_step": 343707, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.033963203430176, "global_step": 343708, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1054866313934326, "global_step": 343709, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.150697708129883, "global_step": 343710, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1545279026031494, "global_step": 343711, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0482044219970703, "global_step": 343712, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1136698722839355, "global_step": 343713, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.127370595932007, "global_step": 343714, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.147608995437622, "global_step": 343715, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.046795129776001, "global_step": 343716, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.079530715942383, "global_step": 343717, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.068483352661133, "global_step": 343718, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0773098468780518, "global_step": 343719, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0775229930877686, "global_step": 343720, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0902137756347656, "global_step": 343721, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1836326122283936, "global_step": 343722, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.131201982498169, "global_step": 343723, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0498266220092773, "global_step": 343724, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0515942573547363, "global_step": 343725, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0885093212127686, "global_step": 343726, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1979053020477295, "global_step": 343727, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.093926429748535, "global_step": 343728, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0887768268585205, "global_step": 343729, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.076014280319214, "global_step": 343730, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.020827531814575, "global_step": 343731, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.059577226638794, "global_step": 343732, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.176985025405884, "global_step": 343733, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.059727430343628, "global_step": 343734, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0652706623077393, "global_step": 343735, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1218175888061523, "global_step": 343736, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.122403860092163, "global_step": 343737, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0538136959075928, "global_step": 343738, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.167726755142212, "global_step": 343739, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.133521795272827, "global_step": 343740, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.103867769241333, "global_step": 343741, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.142328977584839, "global_step": 343742, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.133056879043579, "global_step": 343743, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.081843137741089, "global_step": 343744, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.108346939086914, "global_step": 343745, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.073514938354492, "global_step": 343746, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.012265682220459, "global_step": 343747, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1457362174987793, "global_step": 343748, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1281237602233887, "global_step": 343749, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.192847490310669, "global_step": 343750, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.121631622314453, "global_step": 343751, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.067002534866333, "global_step": 343752, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0731372833251953, "global_step": 343753, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0695319175720215, "global_step": 343754, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1494007110595703, "global_step": 343755, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0790698528289795, "global_step": 343756, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.095804452896118, "global_step": 343757, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.088958501815796, "global_step": 343758, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0793163776397705, "global_step": 343759, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.149475336074829, "global_step": 343760, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0588924884796143, "global_step": 343761, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1727333068847656, "global_step": 343762, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1485815048217773, "global_step": 343763, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1272895336151123, "global_step": 343764, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.098358631134033, "global_step": 343765, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.015049695968628, "global_step": 343766, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1561553478240967, "global_step": 343767, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0437495708465576, "global_step": 343768, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1066484451293945, "global_step": 343769, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.137056589126587, "global_step": 343770, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0779645442962646, "global_step": 343771, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.11152982711792, "global_step": 343772, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1313486099243164, "global_step": 343773, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1192047595977783, "global_step": 343774, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.109858751296997, "global_step": 343775, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.092696189880371, "global_step": 343776, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.07875919342041, "global_step": 343777, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.135732889175415, "global_step": 343778, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1674535274505615, "global_step": 343779, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1423096656799316, "global_step": 343780, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.011715888977051, "global_step": 343781, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0936880111694336, "global_step": 343782, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.079596996307373, "global_step": 343783, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1047911643981934, "global_step": 343784, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.106567859649658, "global_step": 343785, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.038377523422241, "global_step": 343786, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.106499671936035, "global_step": 343787, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1867516040802, "global_step": 343788, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.134333610534668, "global_step": 343789, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1543455123901367, "global_step": 343790, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1172006130218506, "global_step": 343791, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.109875202178955, "global_step": 343792, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0642409324645996, "global_step": 343793, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.9896727800369263, "global_step": 343794, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0945186614990234, "global_step": 343795, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.204887866973877, "global_step": 343796, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1906299591064453, "global_step": 343797, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0988457202911377, "global_step": 343798, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0046825408935547, "global_step": 343799, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.065829038619995, "global_step": 343800, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.2251169681549072, "global_step": 343801, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.146383047103882, "global_step": 343802, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.085202217102051, "global_step": 343803, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1694633960723877, "global_step": 343804, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1186323165893555, "global_step": 343805, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.101940155029297, "global_step": 343806, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1137025356292725, "global_step": 343807, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1269257068634033, "global_step": 343808, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1095590591430664, "global_step": 343809, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.182666778564453, "global_step": 343810, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1983962059020996, "global_step": 343811, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0840158462524414, "global_step": 343812, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.11202335357666, "global_step": 343813, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.117361307144165, "global_step": 343814, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0934019088745117, "global_step": 343815, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.041161060333252, "global_step": 343816, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.137122392654419, "global_step": 343817, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0569820404052734, "global_step": 343818, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.014939069747925, "global_step": 343819, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.156130313873291, "global_step": 343820, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.107983112335205, "global_step": 343821, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0700860023498535, "global_step": 343822, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1259140968322754, "global_step": 343823, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.015479326248169, "global_step": 343824, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.066585063934326, "global_step": 343825, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.119508743286133, "global_step": 343826, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0700597763061523, "global_step": 343827, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.094452142715454, "global_step": 343828, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.040573835372925, "global_step": 343829, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.008563995361328, "global_step": 343830, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.065596342086792, "global_step": 343831, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1720681190490723, "global_step": 343832, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.142951011657715, "global_step": 343833, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1390130519866943, "global_step": 343834, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.163025140762329, "global_step": 343835, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.076232433319092, "global_step": 343836, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1679177284240723, "global_step": 343837, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0411336421966553, "global_step": 343838, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0486724376678467, "global_step": 343839, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1502256393432617, "global_step": 343840, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.163146495819092, "global_step": 343841, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.036592483520508, "global_step": 343842, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1374588012695312, "global_step": 343843, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0716378688812256, "global_step": 343844, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0720012187957764, "global_step": 343845, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1142966747283936, "global_step": 343846, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.125837802886963, "global_step": 343847, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.9832258224487305, "global_step": 343848, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0476841926574707, "global_step": 343849, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.159994602203369, "global_step": 343850, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0579380989074707, "global_step": 343851, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1084327697753906, "global_step": 343852, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.110840082168579, "global_step": 343853, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.099566698074341, "global_step": 343854, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0383551120758057, "global_step": 343855, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.088104724884033, "global_step": 343856, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.161940097808838, "global_step": 343857, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0754120349884033, "global_step": 343858, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.129138708114624, "global_step": 343859, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.133714437484741, "global_step": 343860, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.054914951324463, "global_step": 343861, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0481009483337402, "global_step": 343862, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1274595260620117, "global_step": 343863, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.170048952102661, "global_step": 343864, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0806796550750732, "global_step": 343865, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.122112512588501, "global_step": 343866, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0520222187042236, "global_step": 343867, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0590851306915283, "global_step": 343868, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0511460304260254, "global_step": 343869, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0746376514434814, "global_step": 343870, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.13685941696167, "global_step": 343871, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.032304286956787, "global_step": 343872, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1234495639801025, "global_step": 343873, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0589802265167236, "global_step": 343874, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1357579231262207, "global_step": 343875, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1403615474700928, "global_step": 343876, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0861544609069824, "global_step": 343877, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.040233850479126, "global_step": 343878, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1312923431396484, "global_step": 343879, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0999598503112793, "global_step": 343880, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0546083450317383, "global_step": 343881, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.083890438079834, "global_step": 343882, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1193459033966064, "global_step": 343883, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0627074241638184, "global_step": 343884, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0832948684692383, "global_step": 343885, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0608091354370117, "global_step": 343886, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0304648876190186, "global_step": 343887, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0422987937927246, "global_step": 343888, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.140667200088501, "global_step": 343889, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0547854900360107, "global_step": 343890, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.171093463897705, "global_step": 343891, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.162249803543091, "global_step": 343892, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.136029005050659, "global_step": 343893, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.141214370727539, "global_step": 343894, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.136122703552246, "global_step": 343895, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.090359687805176, "global_step": 343896, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0382752418518066, "global_step": 343897, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.11745023727417, "global_step": 343898, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0806353092193604, "global_step": 343899, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.026404619216919, "global_step": 343900, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0991265773773193, "global_step": 343901, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.9914849996566772, "global_step": 343902, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1223673820495605, "global_step": 343903, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1703708171844482, "global_step": 343904, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.144996404647827, "global_step": 343905, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0800294876098633, "global_step": 343906, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0667028427124023, "global_step": 343907, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.09110951423645, "global_step": 343908, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.2223267555236816, "global_step": 343909, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.13472843170166, "global_step": 343910, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.053694486618042, "global_step": 343911, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.171328544616699, "global_step": 343912, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1493782997131348, "global_step": 343913, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0495429039001465, "global_step": 343914, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0473742485046387, "global_step": 343915, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0282986164093018, "global_step": 343916, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1049885749816895, "global_step": 343917, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0587852001190186, "global_step": 343918, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1383824348449707, "global_step": 343919, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0670742988586426, "global_step": 343920, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1256513595581055, "global_step": 343921, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0923948287963867, "global_step": 343922, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1823666095733643, "global_step": 343923, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1628103256225586, "global_step": 343924, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.173574686050415, "global_step": 343925, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.072279214859009, "global_step": 343926, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1468417644500732, "global_step": 343927, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.9819586277008057, "global_step": 343928, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1067116260528564, "global_step": 343929, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0710182189941406, "global_step": 343930, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1104049682617188, "global_step": 343931, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1905517578125, "global_step": 343932, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.104456663131714, "global_step": 343933, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.104693651199341, "global_step": 343934, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1249053478240967, "global_step": 343935, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0568156242370605, "global_step": 343936, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1228091716766357, "global_step": 343937, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.136976957321167, "global_step": 343938, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.083693265914917, "global_step": 343939, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0781137943267822, "global_step": 343940, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.174294948577881, "global_step": 343941, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.106336832046509, "global_step": 343942, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.193895101547241, "global_step": 343943, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1331639289855957, "global_step": 343944, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1211085319519043, "global_step": 343945, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1090540885925293, "global_step": 343946, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.150716781616211, "global_step": 343947, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0910773277282715, "global_step": 343948, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1874208450317383, "global_step": 343949, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0388998985290527, "global_step": 343950, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.009394645690918, "global_step": 343951, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1251471042633057, "global_step": 343952, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1037843227386475, "global_step": 343953, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.05387544631958, "global_step": 343954, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1341912746429443, "global_step": 343955, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1069796085357666, "global_step": 343956, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.068368673324585, "global_step": 343957, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.122929096221924, "global_step": 343958, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0403571128845215, "global_step": 343959, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0748658180236816, "global_step": 343960, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.13254714012146, "global_step": 343961, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.042370557785034, "global_step": 343962, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.2106428146362305, "global_step": 343963, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1337525844573975, "global_step": 343964, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.109992027282715, "global_step": 343965, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.13177227973938, "global_step": 343966, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1322391033172607, "global_step": 343967, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.146825075149536, "global_step": 343968, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.156811237335205, "global_step": 343969, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1132047176361084, "global_step": 343970, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1714630126953125, "global_step": 343971, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0784757137298584, "global_step": 343972, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.120034694671631, "global_step": 343973, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.067201614379883, "global_step": 343974, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.022493362426758, "global_step": 343975, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0317559242248535, "global_step": 343976, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.089813470840454, "global_step": 343977, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.224923849105835, "global_step": 343978, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0693471431732178, "global_step": 343979, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1380844116210938, "global_step": 343980, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.049337387084961, "global_step": 343981, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1132428646087646, "global_step": 343982, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1595065593719482, "global_step": 343983, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1464061737060547, "global_step": 343984, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0908203125, "global_step": 343985, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.089752197265625, "global_step": 343986, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.083970069885254, "global_step": 343987, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1059367656707764, "global_step": 343988, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.091405153274536, "global_step": 343989, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0488319396972656, "global_step": 343990, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.164461612701416, "global_step": 343991, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.114910840988159, "global_step": 343992, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.096205234527588, "global_step": 343993, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1218957901000977, "global_step": 343994, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1108202934265137, "global_step": 343995, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1540746688842773, "global_step": 343996, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.074558973312378, "global_step": 343997, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.116471290588379, "global_step": 343998, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.150840997695923, "global_step": 343999, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.081636667251587, "global_step": 344000, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0325520038604736, "global_step": 344001, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1085493564605713, "global_step": 344002, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.157532215118408, "global_step": 344003, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.107008934020996, "global_step": 344004, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.159719467163086, "global_step": 344005, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.100822925567627, "global_step": 344006, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1423840522766113, "global_step": 344007, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.110123872756958, "global_step": 344008, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1282408237457275, "global_step": 344009, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0964596271514893, "global_step": 344010, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1486964225769043, "global_step": 344011, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.127305269241333, "global_step": 344012, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.135120153427124, "global_step": 344013, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.043473482131958, "global_step": 344014, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0938878059387207, "global_step": 344015, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.105532169342041, "global_step": 344016, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1351356506347656, "global_step": 344017, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1494455337524414, "global_step": 344018, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.117823600769043, "global_step": 344019, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.075016498565674, "global_step": 344020, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1540772914886475, "global_step": 344021, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.038391351699829, "global_step": 344022, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.197734832763672, "global_step": 344023, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0498621463775635, "global_step": 344024, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.276437997817993, "global_step": 344025, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.07829213142395, "global_step": 344026, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0493390560150146, "global_step": 344027, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.100487470626831, "global_step": 344028, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0644588470458984, "global_step": 344029, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0836069583892822, "global_step": 344030, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1224892139434814, "global_step": 344031, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1353514194488525, "global_step": 344032, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0719587802886963, "global_step": 344033, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.170072555541992, "global_step": 344034, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.090069055557251, "global_step": 344035, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.180453062057495, "global_step": 344036, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1681344509124756, "global_step": 344037, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.229555368423462, "global_step": 344038, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1061878204345703, "global_step": 344039, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0579888820648193, "global_step": 344040, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.198883533477783, "global_step": 344041, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.017665386199951, "global_step": 344042, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1996958255767822, "global_step": 344043, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.173919677734375, "global_step": 344044, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.125084638595581, "global_step": 344045, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.158675193786621, "global_step": 344046, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1822237968444824, "global_step": 344047, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1269114017486572, "global_step": 344048, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1308798789978027, "global_step": 344049, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0559329986572266, "global_step": 344050, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.087063789367676, "global_step": 344051, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.052025318145752, "global_step": 344052, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.2405660152435303, "global_step": 344053, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1234278678894043, "global_step": 344054, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.145080089569092, "global_step": 344055, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0874640941619873, "global_step": 344056, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0768144130706787, "global_step": 344057, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1419529914855957, "global_step": 344058, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1187288761138916, "global_step": 344059, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0893609523773193, "global_step": 344060, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.149629592895508, "global_step": 344061, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1734845638275146, "global_step": 344062, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1767051219940186, "global_step": 344063, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0496013164520264, "global_step": 344064, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0963125228881836, "global_step": 344065, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0338757038116455, "global_step": 344066, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1387686729431152, "global_step": 344067, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1719393730163574, "global_step": 344068, "epoch": 704, "lr": 5e-05}
{"train_loss": 1.980851173400879, "global_step": 344069, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.02396297454834, "global_step": 344070, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0865237712860107, "global_step": 344071, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0239245891571045, "global_step": 344072, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1422126293182373, "global_step": 344073, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0114784240722656, "global_step": 344074, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.01705002784729, "global_step": 344075, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.121797800064087, "global_step": 344076, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.149091958999634, "global_step": 344077, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.081449270248413, "global_step": 344078, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.136277437210083, "global_step": 344079, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.093818187713623, "global_step": 344080, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.059325933456421, "global_step": 344081, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.04134202003479, "global_step": 344082, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.166210174560547, "global_step": 344083, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1186556816101074, "global_step": 344084, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.179835557937622, "global_step": 344085, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.078350782394409, "global_step": 344086, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.134697914123535, "global_step": 344087, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1509265899658203, "global_step": 344088, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0861008167266846, "global_step": 344089, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1550803184509277, "global_step": 344090, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1581671237945557, "global_step": 344091, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0431935787200928, "global_step": 344092, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0443801879882812, "global_step": 344093, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0736184120178223, "global_step": 344094, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0768775939941406, "global_step": 344095, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0964431762695312, "global_step": 344096, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0836269855499268, "global_step": 344097, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1900265216827393, "global_step": 344098, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1390013694763184, "global_step": 344099, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1070542335510254, "global_step": 344100, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.028188943862915, "global_step": 344101, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0378074645996094, "global_step": 344102, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1670591831207275, "global_step": 344103, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.003458023071289, "global_step": 344104, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.157773017883301, "global_step": 344105, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.190431833267212, "global_step": 344106, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.076969623565674, "global_step": 344107, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.056387186050415, "global_step": 344108, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.09592342376709, "global_step": 344109, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.08241605758667, "global_step": 344110, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1762290000915527, "global_step": 344111, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.133479118347168, "global_step": 344112, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1505463123321533, "global_step": 344113, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.069742202758789, "global_step": 344114, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.074314594268799, "global_step": 344115, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1667044162750244, "global_step": 344116, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.007523536682129, "global_step": 344117, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0861544609069824, "global_step": 344118, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.086358070373535, "global_step": 344119, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.07814884185791, "global_step": 344120, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0511553287506104, "global_step": 344121, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1831812858581543, "global_step": 344122, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.093919277191162, "global_step": 344123, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1001486778259277, "global_step": 344124, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.095339298248291, "global_step": 344125, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1459450721740723, "global_step": 344126, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.1045639514923096, "global_step": 344127, "epoch": 704, "lr": 5e-05}
{"train_loss": 2.0534400939941406, "global_step": 344128, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.158552646636963, "global_step": 344129, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0679638385772705, "global_step": 344130, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.143383502960205, "global_step": 344131, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.116399049758911, "global_step": 344132, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0637636184692383, "global_step": 344133, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1618566513061523, "global_step": 344134, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.113859176635742, "global_step": 344135, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.037120819091797, "global_step": 344136, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.093177318572998, "global_step": 344137, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1432061195373535, "global_step": 344138, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0428552627563477, "global_step": 344139, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.09989595413208, "global_step": 344140, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.079955577850342, "global_step": 344141, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.025484800338745, "global_step": 344142, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.033440113067627, "global_step": 344143, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.09175968170166, "global_step": 344144, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.015652894973755, "global_step": 344145, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.120396137237549, "global_step": 344146, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9810503721237183, "global_step": 344147, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1228487491607666, "global_step": 344148, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.136977195739746, "global_step": 344149, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0879414081573486, "global_step": 344150, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1698732376098633, "global_step": 344151, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.100602865219116, "global_step": 344152, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.093822956085205, "global_step": 344153, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1330058574676514, "global_step": 344154, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0025904178619385, "global_step": 344155, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.133452892303467, "global_step": 344156, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.035583019256592, "global_step": 344157, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0471370220184326, "global_step": 344158, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.226605176925659, "global_step": 344159, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.097336530685425, "global_step": 344160, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.05375075340271, "global_step": 344161, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1078670024871826, "global_step": 344162, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.157186269760132, "global_step": 344163, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0944910049438477, "global_step": 344164, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0818066596984863, "global_step": 344165, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.141267776489258, "global_step": 344166, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1308062076568604, "global_step": 344167, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.160834312438965, "global_step": 344168, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0890872478485107, "global_step": 344169, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.148810625076294, "global_step": 344170, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1537539958953857, "global_step": 344171, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1163675785064697, "global_step": 344172, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1158909797668457, "global_step": 344173, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1244184970855713, "global_step": 344174, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.131322145462036, "global_step": 344175, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1954824924468994, "global_step": 344176, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0680482387542725, "global_step": 344177, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.112569808959961, "global_step": 344178, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0986411571502686, "global_step": 344179, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.065718412399292, "global_step": 344180, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9749032258987427, "global_step": 344181, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1278223991394043, "global_step": 344182, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.142223358154297, "global_step": 344183, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.094203472137451, "global_step": 344184, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0813369750976562, "global_step": 344185, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1355223655700684, "global_step": 344186, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1742234230041504, "global_step": 344187, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.135820150375366, "global_step": 344188, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9848542213439941, "global_step": 344189, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.059441089630127, "global_step": 344190, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0494461059570312, "global_step": 344191, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0689501762390137, "global_step": 344192, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0222699642181396, "global_step": 344193, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1184582710266113, "global_step": 344194, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1421713829040527, "global_step": 344195, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0759453773498535, "global_step": 344196, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1107232570648193, "global_step": 344197, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.151219129562378, "global_step": 344198, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.097350835800171, "global_step": 344199, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1240897178649902, "global_step": 344200, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0563321113586426, "global_step": 344201, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1422719955444336, "global_step": 344202, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1306798458099365, "global_step": 344203, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.024977445602417, "global_step": 344204, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0255982875823975, "global_step": 344205, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.143310070037842, "global_step": 344206, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.17024302482605, "global_step": 344207, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1060686111450195, "global_step": 344208, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0546298027038574, "global_step": 344209, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1772055625915527, "global_step": 344210, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1436188220977783, "global_step": 344211, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0734610557556152, "global_step": 344212, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.12491774559021, "global_step": 344213, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0065712928771973, "global_step": 344214, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.101649761199951, "global_step": 344215, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.066507339477539, "global_step": 344216, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0463473796844482, "global_step": 344217, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.111724853515625, "global_step": 344218, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.100712299346924, "global_step": 344219, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0570716857910156, "global_step": 344220, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0986955165863037, "global_step": 344221, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.104140520095825, "global_step": 344222, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.127023935317993, "global_step": 344223, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0413975715637207, "global_step": 344224, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1715898513793945, "global_step": 344225, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.135819911956787, "global_step": 344226, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.161911725997925, "global_step": 344227, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.040255546569824, "global_step": 344228, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1097676753997803, "global_step": 344229, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.129772663116455, "global_step": 344230, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1895360946655273, "global_step": 344231, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.250011444091797, "global_step": 344232, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.010833740234375, "global_step": 344233, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0697922706604004, "global_step": 344234, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.163728713989258, "global_step": 344235, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.131993532180786, "global_step": 344236, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0767829418182373, "global_step": 344237, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0817806720733643, "global_step": 344238, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.058290719985962, "global_step": 344239, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.062364339828491, "global_step": 344240, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.054701566696167, "global_step": 344241, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1235315799713135, "global_step": 344242, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.181527614593506, "global_step": 344243, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.080838441848755, "global_step": 344244, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1230950355529785, "global_step": 344245, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.066556215286255, "global_step": 344246, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.128565549850464, "global_step": 344247, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.005852699279785, "global_step": 344248, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.048445463180542, "global_step": 344249, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1118431091308594, "global_step": 344250, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.046417236328125, "global_step": 344251, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.128699541091919, "global_step": 344252, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0824084281921387, "global_step": 344253, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.057123899459839, "global_step": 344254, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.042619228363037, "global_step": 344255, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0225064754486084, "global_step": 344256, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0563061237335205, "global_step": 344257, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.142340898513794, "global_step": 344258, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0229945182800293, "global_step": 344259, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1516857147216797, "global_step": 344260, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1267035007476807, "global_step": 344261, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.076214075088501, "global_step": 344262, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0929646492004395, "global_step": 344263, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1039464473724365, "global_step": 344264, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.056957483291626, "global_step": 344265, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0976548194885254, "global_step": 344266, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1575467586517334, "global_step": 344267, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0390543937683105, "global_step": 344268, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.047677755355835, "global_step": 344269, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0927302837371826, "global_step": 344270, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.173720121383667, "global_step": 344271, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1678967475891113, "global_step": 344272, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.122093677520752, "global_step": 344273, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1218130588531494, "global_step": 344274, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.057234048843384, "global_step": 344275, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1187491416931152, "global_step": 344276, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1106061935424805, "global_step": 344277, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1290740966796875, "global_step": 344278, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0866003036499023, "global_step": 344279, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.080836534500122, "global_step": 344280, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0976924896240234, "global_step": 344281, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.146042823791504, "global_step": 344282, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.158245086669922, "global_step": 344283, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.104727268218994, "global_step": 344284, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0021822452545166, "global_step": 344285, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.10951566696167, "global_step": 344286, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1333141326904297, "global_step": 344287, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.164113759994507, "global_step": 344288, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1027934551239014, "global_step": 344289, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1368606090545654, "global_step": 344290, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.108891010284424, "global_step": 344291, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0304439067840576, "global_step": 344292, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.150885820388794, "global_step": 344293, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0337870121002197, "global_step": 344294, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.009990692138672, "global_step": 344295, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.158045530319214, "global_step": 344296, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0650014877319336, "global_step": 344297, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1275172233581543, "global_step": 344298, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1759705543518066, "global_step": 344299, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.083523750305176, "global_step": 344300, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.054612636566162, "global_step": 344301, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0562477111816406, "global_step": 344302, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0533504486083984, "global_step": 344303, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.086233377456665, "global_step": 344304, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.053812265396118, "global_step": 344305, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1073312759399414, "global_step": 344306, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.076752185821533, "global_step": 344307, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9809417724609375, "global_step": 344308, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0832290649414062, "global_step": 344309, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.024670124053955, "global_step": 344310, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0890846252441406, "global_step": 344311, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.093470573425293, "global_step": 344312, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.085984706878662, "global_step": 344313, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.2028439044952393, "global_step": 344314, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.201333522796631, "global_step": 344315, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.042943239212036, "global_step": 344316, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1372268199920654, "global_step": 344317, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1053085327148438, "global_step": 344318, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.092994451522827, "global_step": 344319, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.2306630611419678, "global_step": 344320, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0882155895233154, "global_step": 344321, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.077002763748169, "global_step": 344322, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0977938175201416, "global_step": 344323, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.123382806777954, "global_step": 344324, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0812950134277344, "global_step": 344325, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.105889081954956, "global_step": 344326, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1329071521759033, "global_step": 344327, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.118729591369629, "global_step": 344328, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9960615634918213, "global_step": 344329, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1310198307037354, "global_step": 344330, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0653316974639893, "global_step": 344331, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.100618839263916, "global_step": 344332, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0146541595458984, "global_step": 344333, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.078247547149658, "global_step": 344334, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1113500595092773, "global_step": 344335, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.126340866088867, "global_step": 344336, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.111093521118164, "global_step": 344337, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.994244933128357, "global_step": 344338, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.098193645477295, "global_step": 344339, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.117145538330078, "global_step": 344340, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.13503098487854, "global_step": 344341, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.201234817504883, "global_step": 344342, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.173231840133667, "global_step": 344343, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1512601375579834, "global_step": 344344, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0898382663726807, "global_step": 344345, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.14311146736145, "global_step": 344346, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1161906719207764, "global_step": 344347, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.109358549118042, "global_step": 344348, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0255191326141357, "global_step": 344349, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.013619899749756, "global_step": 344350, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.121938943862915, "global_step": 344351, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.035189390182495, "global_step": 344352, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.142634868621826, "global_step": 344353, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.054093360900879, "global_step": 344354, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.133112668991089, "global_step": 344355, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.092550754547119, "global_step": 344356, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1604466438293457, "global_step": 344357, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.118832588195801, "global_step": 344358, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1949193477630615, "global_step": 344359, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1458096504211426, "global_step": 344360, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1676924228668213, "global_step": 344361, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.132208824157715, "global_step": 344362, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0442121028900146, "global_step": 344363, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0883283615112305, "global_step": 344364, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1053717136383057, "global_step": 344365, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1531167030334473, "global_step": 344366, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.08919620513916, "global_step": 344367, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.149275064468384, "global_step": 344368, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1672046184539795, "global_step": 344369, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.109912633895874, "global_step": 344370, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1038424968719482, "global_step": 344371, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.147458076477051, "global_step": 344372, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.071207284927368, "global_step": 344373, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0584120750427246, "global_step": 344374, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1633079051971436, "global_step": 344375, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0794849395751953, "global_step": 344376, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1208107471466064, "global_step": 344377, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.042961359024048, "global_step": 344378, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1608633995056152, "global_step": 344379, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.11653208732605, "global_step": 344380, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0992956161499023, "global_step": 344381, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1628305912017822, "global_step": 344382, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1177473068237305, "global_step": 344383, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1156089305877686, "global_step": 344384, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0728886127471924, "global_step": 344385, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0558133125305176, "global_step": 344386, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.103074789047241, "global_step": 344387, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0933873653411865, "global_step": 344388, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.10119891166687, "global_step": 344389, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.120359182357788, "global_step": 344390, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0115442276000977, "global_step": 344391, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0494439601898193, "global_step": 344392, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0444068908691406, "global_step": 344393, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.15786075592041, "global_step": 344394, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9900641441345215, "global_step": 344395, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0531792640686035, "global_step": 344396, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.077937126159668, "global_step": 344397, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1792943477630615, "global_step": 344398, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0471014976501465, "global_step": 344399, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1153476238250732, "global_step": 344400, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9773067235946655, "global_step": 344401, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.027311086654663, "global_step": 344402, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.165461540222168, "global_step": 344403, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1034977436065674, "global_step": 344404, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1110610961914062, "global_step": 344405, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0615737438201904, "global_step": 344406, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0954020023345947, "global_step": 344407, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1542675495147705, "global_step": 344408, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1713130474090576, "global_step": 344409, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1859118938446045, "global_step": 344410, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0468666553497314, "global_step": 344411, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.018261432647705, "global_step": 344412, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1721432209014893, "global_step": 344413, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.125404119491577, "global_step": 344414, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1777305603027344, "global_step": 344415, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.099510669708252, "global_step": 344416, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.24743914604187, "global_step": 344417, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0506014823913574, "global_step": 344418, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.120420217514038, "global_step": 344419, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0786046981811523, "global_step": 344420, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1433498859405518, "global_step": 344421, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9423493146896362, "global_step": 344422, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1596567630767822, "global_step": 344423, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0168168544769287, "global_step": 344424, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0375149250030518, "global_step": 344425, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0646262168884277, "global_step": 344426, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0936574935913086, "global_step": 344427, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.084066152572632, "global_step": 344428, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.030518054962158, "global_step": 344429, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1021523475646973, "global_step": 344430, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0668880939483643, "global_step": 344431, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.155989408493042, "global_step": 344432, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.162766695022583, "global_step": 344433, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1829700469970703, "global_step": 344434, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1978447437286377, "global_step": 344435, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1149888038635254, "global_step": 344436, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0959794521331787, "global_step": 344437, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.010152578353882, "global_step": 344438, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.143646240234375, "global_step": 344439, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1259257793426514, "global_step": 344440, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.08986759185791, "global_step": 344441, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0849335193634033, "global_step": 344442, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0802206993103027, "global_step": 344443, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1059796810150146, "global_step": 344444, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.998677372932434, "global_step": 344445, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0917139053344727, "global_step": 344446, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.106109380722046, "global_step": 344447, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.053593158721924, "global_step": 344448, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.966766595840454, "global_step": 344449, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1116693019866943, "global_step": 344450, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1450490951538086, "global_step": 344451, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0991992950439453, "global_step": 344452, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1644625663757324, "global_step": 344453, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0671980381011963, "global_step": 344454, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.069439649581909, "global_step": 344455, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0843679904937744, "global_step": 344456, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1163856983184814, "global_step": 344457, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1389052867889404, "global_step": 344458, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.09443998336792, "global_step": 344459, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.071122407913208, "global_step": 344460, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0948574542999268, "global_step": 344461, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1030304431915283, "global_step": 344462, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1452383995056152, "global_step": 344463, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.117079734802246, "global_step": 344464, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.156627655029297, "global_step": 344465, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0815560817718506, "global_step": 344466, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.138734817504883, "global_step": 344467, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1075785160064697, "global_step": 344468, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1213903427124023, "global_step": 344469, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.155667781829834, "global_step": 344470, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.146822929382324, "global_step": 344471, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1279921531677246, "global_step": 344472, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.121464967727661, "global_step": 344473, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.106509208679199, "global_step": 344474, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.164144277572632, "global_step": 344475, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.092830181121826, "global_step": 344476, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1480090618133545, "global_step": 344477, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.04630708694458, "global_step": 344478, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.169156789779663, "global_step": 344479, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.125122547149658, "global_step": 344480, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.11484432220459, "global_step": 344481, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9893949031829834, "global_step": 344482, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0706417560577393, "global_step": 344483, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0465803146362305, "global_step": 344484, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1793198585510254, "global_step": 344485, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.142443895339966, "global_step": 344486, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1686806678771973, "global_step": 344487, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.089130401611328, "global_step": 344488, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.062056541442871, "global_step": 344489, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0546295642852783, "global_step": 344490, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.126676082611084, "global_step": 344491, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.168553352355957, "global_step": 344492, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1529643535614014, "global_step": 344493, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1831576824188232, "global_step": 344494, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.117931604385376, "global_step": 344495, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1747186183929443, "global_step": 344496, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.079753875732422, "global_step": 344497, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0775983333587646, "global_step": 344498, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.120298385620117, "global_step": 344499, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.049025774002075, "global_step": 344500, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.017669916152954, "global_step": 344501, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0899417400360107, "global_step": 344502, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.124448537826538, "global_step": 344503, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.089494228363037, "global_step": 344504, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1983892917633057, "global_step": 344505, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1288318634033203, "global_step": 344506, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.094341278076172, "global_step": 344507, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1420164108276367, "global_step": 344508, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0946755409240723, "global_step": 344509, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1126387119293213, "global_step": 344510, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1221041679382324, "global_step": 344511, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0979292392730713, "global_step": 344512, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.186030387878418, "global_step": 344513, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.107435941696167, "global_step": 344514, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1343188285827637, "global_step": 344515, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.028310775756836, "global_step": 344516, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1781253814697266, "global_step": 344517, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.115463972091675, "global_step": 344518, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.081261396408081, "global_step": 344519, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0746560096740723, "global_step": 344520, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1165237426757812, "global_step": 344521, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.013721466064453, "global_step": 344522, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.066272497177124, "global_step": 344523, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.091398000717163, "global_step": 344524, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0843982696533203, "global_step": 344525, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0158751010894775, "global_step": 344526, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.058736562728882, "global_step": 344527, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.171283721923828, "global_step": 344528, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.08955979347229, "global_step": 344529, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.133012294769287, "global_step": 344530, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1937270164489746, "global_step": 344531, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1299736499786377, "global_step": 344532, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.191258668899536, "global_step": 344533, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.096630096435547, "global_step": 344534, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9980859756469727, "global_step": 344535, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.081820487976074, "global_step": 344536, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0971665382385254, "global_step": 344537, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.08412504196167, "global_step": 344538, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9991525411605835, "global_step": 344539, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1159982681274414, "global_step": 344540, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1490097045898438, "global_step": 344541, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1293811798095703, "global_step": 344542, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.104276180267334, "global_step": 344543, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.09740948677063, "global_step": 344544, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.071359395980835, "global_step": 344545, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1629343032836914, "global_step": 344546, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.188223123550415, "global_step": 344547, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.088456630706787, "global_step": 344548, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.124385356903076, "global_step": 344549, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.043208360671997, "global_step": 344550, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1398444175720215, "global_step": 344551, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1825554370880127, "global_step": 344552, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.178407907485962, "global_step": 344553, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.086599588394165, "global_step": 344554, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0594441890716553, "global_step": 344555, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.080629587173462, "global_step": 344556, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0105679035186768, "global_step": 344557, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0605905055999756, "global_step": 344558, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.123538017272949, "global_step": 344559, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9689679145812988, "global_step": 344560, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0389773845672607, "global_step": 344561, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1267013549804688, "global_step": 344562, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.014908790588379, "global_step": 344563, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.060142993927002, "global_step": 344564, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0281174182891846, "global_step": 344565, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0516834259033203, "global_step": 344566, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.163050889968872, "global_step": 344567, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1369738578796387, "global_step": 344568, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.20489764213562, "global_step": 344569, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0266129970550537, "global_step": 344570, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1726081371307373, "global_step": 344571, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.074414014816284, "global_step": 344572, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.186735153198242, "global_step": 344573, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1071269512176514, "global_step": 344574, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.079071283340454, "global_step": 344575, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.132323741912842, "global_step": 344576, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.116612195968628, "global_step": 344577, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.078535556793213, "global_step": 344578, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0759081840515137, "global_step": 344579, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.151176691055298, "global_step": 344580, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1630489826202393, "global_step": 344581, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.021411180496216, "global_step": 344582, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.122504711151123, "global_step": 344583, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1929779052734375, "global_step": 344584, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0785937309265137, "global_step": 344585, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1013336181640625, "global_step": 344586, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.097975492477417, "global_step": 344587, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9652327299118042, "global_step": 344588, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0810017585754395, "global_step": 344589, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0831220149993896, "global_step": 344590, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1573193073272705, "global_step": 344591, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1675314903259277, "global_step": 344592, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.146017551422119, "global_step": 344593, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.138251543045044, "global_step": 344594, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.10201358795166, "global_step": 344595, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9945271015167236, "global_step": 344596, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0863752365112305, "global_step": 344597, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.073242425918579, "global_step": 344598, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1819655895233154, "global_step": 344599, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0819082260131836, "global_step": 344600, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.137113571166992, "global_step": 344601, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0508615970611572, "global_step": 344602, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.121791124343872, "global_step": 344603, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.105931043624878, "global_step": 344604, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.107866048812866, "global_step": 344605, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.081984519958496, "global_step": 344606, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.06807279586792, "global_step": 344607, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0882248878479004, "global_step": 344608, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.166109561920166, "global_step": 344609, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0754153728485107, "global_step": 344610, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0552263259887695, "global_step": 344611, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1225953102111816, "global_step": 344612, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9976439476013184, "global_step": 344613, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1028268337249756, "global_step": 344614, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0630531311035156, "global_step": 344615, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1964292526245117, "global_step": 344616, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0301458835601807, "global_step": 344617, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1488521099090576, "global_step": 344618, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0678694248199463, "global_step": 344619, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1190505027770996, "global_step": 344620, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0112452507019043, "global_step": 344621, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0836868286132812, "global_step": 344622, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1312601566314697, "global_step": 344623, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.138502836227417, "global_step": 344624, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.989982008934021, "global_step": 344625, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.117901086807251, "global_step": 344626, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1126341819763184, "global_step": 344627, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.180624008178711, "global_step": 344628, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0350341796875, "global_step": 344629, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0900685787200928, "global_step": 344630, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.127018928527832, "global_step": 344631, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.143409490585327, "global_step": 344632, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0517122745513916, "global_step": 344633, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.103527784347534, "global_step": 344634, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1560475826263428, "global_step": 344635, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.063107967376709, "global_step": 344636, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.066617012023926, "global_step": 344637, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1078596115112305, "global_step": 344638, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.072923421859741, "global_step": 344639, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.100947141647339, "global_step": 344640, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1366279125213623, "global_step": 344641, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0112342834472656, "global_step": 344642, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0803489685058594, "global_step": 344643, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.089146852493286, "global_step": 344644, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.088751792907715, "global_step": 344645, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0919361114501953, "global_step": 344646, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.054664373397827, "global_step": 344647, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0241539478302, "global_step": 344648, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.182068109512329, "global_step": 344649, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.020216226577759, "global_step": 344650, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0422627925872803, "global_step": 344651, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1553099155426025, "global_step": 344652, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1186068058013916, "global_step": 344653, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1129961013793945, "global_step": 344654, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.100844621658325, "global_step": 344655, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0892300605773926, "global_step": 344656, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1469566822052, "global_step": 344657, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1412978172302246, "global_step": 344658, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1133759021759033, "global_step": 344659, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1194722652435303, "global_step": 344660, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1009278297424316, "global_step": 344661, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.187455654144287, "global_step": 344662, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0560553073883057, "global_step": 344663, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.162963390350342, "global_step": 344664, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0832619667053223, "global_step": 344665, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.148432970046997, "global_step": 344666, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0815272331237793, "global_step": 344667, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0455284118652344, "global_step": 344668, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1277058124542236, "global_step": 344669, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.127357244491577, "global_step": 344670, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1397430896759033, "global_step": 344671, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1510825157165527, "global_step": 344672, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.096376895904541, "global_step": 344673, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.108614206314087, "global_step": 344674, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.2642221450805664, "global_step": 344675, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.111773729324341, "global_step": 344676, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1537368297576904, "global_step": 344677, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0520153045654297, "global_step": 344678, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0847909450531006, "global_step": 344679, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.185185432434082, "global_step": 344680, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1152358055114746, "global_step": 344681, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9569785594940186, "global_step": 344682, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.082174777984619, "global_step": 344683, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0564262866973877, "global_step": 344684, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.085733413696289, "global_step": 344685, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1221959590911865, "global_step": 344686, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0282740592956543, "global_step": 344687, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1272435188293457, "global_step": 344688, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1032216548919678, "global_step": 344689, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0184080600738525, "global_step": 344690, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1147372722625732, "global_step": 344691, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.141543388366699, "global_step": 344692, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1328492164611816, "global_step": 344693, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.110461950302124, "global_step": 344694, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1735517978668213, "global_step": 344695, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0427982807159424, "global_step": 344696, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1074845790863037, "global_step": 344697, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.07808780670166, "global_step": 344698, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0358314514160156, "global_step": 344699, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.168973684310913, "global_step": 344700, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0893149375915527, "global_step": 344701, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.104231357574463, "global_step": 344702, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0909500122070312, "global_step": 344703, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9880180358886719, "global_step": 344704, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0995934009552, "global_step": 344705, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.085721731185913, "global_step": 344706, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.135725259780884, "global_step": 344707, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.16880202293396, "global_step": 344708, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.148143768310547, "global_step": 344709, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1222474575042725, "global_step": 344710, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1165552139282227, "global_step": 344711, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1382107734680176, "global_step": 344712, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1230170726776123, "global_step": 344713, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.006523609161377, "global_step": 344714, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.191115379333496, "global_step": 344715, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1308367252349854, "global_step": 344716, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0818216800689697, "global_step": 344717, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.148038625717163, "global_step": 344718, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1340959072113037, "global_step": 344719, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1003878116607666, "global_step": 344720, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.131789207458496, "global_step": 344721, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1509850025177, "global_step": 344722, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.114013433456421, "global_step": 344723, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1294074058532715, "global_step": 344724, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1598024368286133, "global_step": 344725, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1053152084350586, "global_step": 344726, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1570708751678467, "global_step": 344727, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0765068531036377, "global_step": 344728, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.135483980178833, "global_step": 344729, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1070337295532227, "global_step": 344730, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.223682403564453, "global_step": 344731, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.134979248046875, "global_step": 344732, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0754246711730957, "global_step": 344733, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1157662868499756, "global_step": 344734, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.051831007003784, "global_step": 344735, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1047203540802, "global_step": 344736, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.126770257949829, "global_step": 344737, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.114945888519287, "global_step": 344738, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.11871075630188, "global_step": 344739, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.051513671875, "global_step": 344740, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1707987785339355, "global_step": 344741, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1380605697631836, "global_step": 344742, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1090073585510254, "global_step": 344743, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0400171279907227, "global_step": 344744, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.120897054672241, "global_step": 344745, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1186866760253906, "global_step": 344746, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0825023651123047, "global_step": 344747, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.090676784515381, "global_step": 344748, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.12748384475708, "global_step": 344749, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1662533283233643, "global_step": 344750, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0623321533203125, "global_step": 344751, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1582181453704834, "global_step": 344752, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0775444507598877, "global_step": 344753, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0338988304138184, "global_step": 344754, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.114156484603882, "global_step": 344755, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1095123291015625, "global_step": 344756, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1679930686950684, "global_step": 344757, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.133474349975586, "global_step": 344758, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.082503318786621, "global_step": 344759, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.146235466003418, "global_step": 344760, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1775124073028564, "global_step": 344761, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.192265272140503, "global_step": 344762, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1638996601104736, "global_step": 344763, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.118293285369873, "global_step": 344764, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1219546794891357, "global_step": 344765, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1152985095977783, "global_step": 344766, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1159987449645996, "global_step": 344767, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0428946018218994, "global_step": 344768, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.048595905303955, "global_step": 344769, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1065611839294434, "global_step": 344770, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.084622383117676, "global_step": 344771, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.172137498855591, "global_step": 344772, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.143110513687134, "global_step": 344773, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1391489505767822, "global_step": 344774, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1060664653778076, "global_step": 344775, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.094466209411621, "global_step": 344776, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.048710584640503, "global_step": 344777, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1576502323150635, "global_step": 344778, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.166706085205078, "global_step": 344779, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0852572917938232, "global_step": 344780, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.2292275428771973, "global_step": 344781, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.042897939682007, "global_step": 344782, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1788289546966553, "global_step": 344783, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1404902935028076, "global_step": 344784, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1616244316101074, "global_step": 344785, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0561792850494385, "global_step": 344786, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.173520088195801, "global_step": 344787, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1223833560943604, "global_step": 344788, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0772697925567627, "global_step": 344789, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0226149559020996, "global_step": 344790, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0852506160736084, "global_step": 344791, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.089998722076416, "global_step": 344792, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0994873046875, "global_step": 344793, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0751593112945557, "global_step": 344794, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1154799461364746, "global_step": 344795, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1253256797790527, "global_step": 344796, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.031193971633911, "global_step": 344797, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1251721382141113, "global_step": 344798, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1467223167419434, "global_step": 344799, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1320722103118896, "global_step": 344800, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.100588798522949, "global_step": 344801, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1070926189422607, "global_step": 344802, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0993165969848633, "global_step": 344803, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1366372108459473, "global_step": 344804, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0450518131256104, "global_step": 344805, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.100353479385376, "global_step": 344806, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.11615252494812, "global_step": 344807, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0548627376556396, "global_step": 344808, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1250240802764893, "global_step": 344809, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1545567512512207, "global_step": 344810, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.145254373550415, "global_step": 344811, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1578218936920166, "global_step": 344812, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1378023624420166, "global_step": 344813, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1372506618499756, "global_step": 344814, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0808520317077637, "global_step": 344815, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.22377347946167, "global_step": 344816, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0915873050689697, "global_step": 344817, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1944997310638428, "global_step": 344818, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.090315341949463, "global_step": 344819, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1221609115600586, "global_step": 344820, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.154874086380005, "global_step": 344821, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.2428476810455322, "global_step": 344822, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1456143856048584, "global_step": 344823, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.087883710861206, "global_step": 344824, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.077497720718384, "global_step": 344825, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0404388904571533, "global_step": 344826, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1653363704681396, "global_step": 344827, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1374778747558594, "global_step": 344828, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9870468378067017, "global_step": 344829, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.105837345123291, "global_step": 344830, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.2294161319732666, "global_step": 344831, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1712777614593506, "global_step": 344832, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1031694412231445, "global_step": 344833, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1622817516326904, "global_step": 344834, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1519784927368164, "global_step": 344835, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0969903469085693, "global_step": 344836, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1820926666259766, "global_step": 344837, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.112448215484619, "global_step": 344838, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1507577896118164, "global_step": 344839, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.182865858078003, "global_step": 344840, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.039440155029297, "global_step": 344841, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1056137084960938, "global_step": 344842, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1234753131866455, "global_step": 344843, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1209003925323486, "global_step": 344844, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.005127429962158, "global_step": 344845, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0759613513946533, "global_step": 344846, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1145734786987305, "global_step": 344847, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.120805501937866, "global_step": 344848, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0420639514923096, "global_step": 344849, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0881412029266357, "global_step": 344850, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1532187461853027, "global_step": 344851, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0831947326660156, "global_step": 344852, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.200566530227661, "global_step": 344853, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.122608184814453, "global_step": 344854, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.215512275695801, "global_step": 344855, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.099303722381592, "global_step": 344856, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.194155216217041, "global_step": 344857, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1015892028808594, "global_step": 344858, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.136258602142334, "global_step": 344859, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.042241334915161, "global_step": 344860, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1040689945220947, "global_step": 344861, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0606486797332764, "global_step": 344862, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1485674381256104, "global_step": 344863, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.066236734390259, "global_step": 344864, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0059926509857178, "global_step": 344865, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1051244735717773, "global_step": 344866, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1333577632904053, "global_step": 344867, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.120997667312622, "global_step": 344868, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.084054946899414, "global_step": 344869, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.157277822494507, "global_step": 344870, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1613755226135254, "global_step": 344871, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.155566930770874, "global_step": 344872, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.086566686630249, "global_step": 344873, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0673437118530273, "global_step": 344874, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.100480318069458, "global_step": 344875, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1223363876342773, "global_step": 344876, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0723774433135986, "global_step": 344877, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0479555130004883, "global_step": 344878, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1773388385772705, "global_step": 344879, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0779364109039307, "global_step": 344880, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0217678546905518, "global_step": 344881, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.060041666030884, "global_step": 344882, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0721755027770996, "global_step": 344883, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.138139486312866, "global_step": 344884, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.098721742630005, "global_step": 344885, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.104450225830078, "global_step": 344886, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1654305458068848, "global_step": 344887, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.241698741912842, "global_step": 344888, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1333043575286865, "global_step": 344889, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0651495456695557, "global_step": 344890, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1416354179382324, "global_step": 344891, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.120889663696289, "global_step": 344892, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.092694044113159, "global_step": 344893, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.2114930152893066, "global_step": 344894, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.145814895629883, "global_step": 344895, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0952234268188477, "global_step": 344896, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.157822847366333, "global_step": 344897, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1289823055267334, "global_step": 344898, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0905492305755615, "global_step": 344899, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.071603536605835, "global_step": 344900, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9807956218719482, "global_step": 344901, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0488717555999756, "global_step": 344902, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.08915114402771, "global_step": 344903, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.034201145172119, "global_step": 344904, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.164916753768921, "global_step": 344905, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1088757514953613, "global_step": 344906, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1140477657318115, "global_step": 344907, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9884788990020752, "global_step": 344908, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0813801288604736, "global_step": 344909, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1005570888519287, "global_step": 344910, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0232174396514893, "global_step": 344911, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1226747035980225, "global_step": 344912, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.052654981613159, "global_step": 344913, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.250483274459839, "global_step": 344914, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1329891681671143, "global_step": 344915, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1607210636138916, "global_step": 344916, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.047914505004883, "global_step": 344917, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0691397190093994, "global_step": 344918, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.2095999717712402, "global_step": 344919, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.146428346633911, "global_step": 344920, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.098479986190796, "global_step": 344921, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.156925916671753, "global_step": 344922, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.099849224090576, "global_step": 344923, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.156287431716919, "global_step": 344924, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1008481979370117, "global_step": 344925, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0944368839263916, "global_step": 344926, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1971123218536377, "global_step": 344927, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0336246490478516, "global_step": 344928, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.093226671218872, "global_step": 344929, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.073505401611328, "global_step": 344930, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.2053494453430176, "global_step": 344931, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1718387603759766, "global_step": 344932, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.10844349861145, "global_step": 344933, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.050826072692871, "global_step": 344934, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1677145957946777, "global_step": 344935, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0558910369873047, "global_step": 344936, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.175086736679077, "global_step": 344937, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0927252769470215, "global_step": 344938, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.031522512435913, "global_step": 344939, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0766665935516357, "global_step": 344940, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1587283611297607, "global_step": 344941, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1562576293945312, "global_step": 344942, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.082589864730835, "global_step": 344943, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.075695753097534, "global_step": 344944, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1647818088531494, "global_step": 344945, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1762585639953613, "global_step": 344946, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1197621822357178, "global_step": 344947, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.126716136932373, "global_step": 344948, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0944042205810547, "global_step": 344949, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.085496664047241, "global_step": 344950, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1456668376922607, "global_step": 344951, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.192559242248535, "global_step": 344952, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0934181213378906, "global_step": 344953, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.168377637863159, "global_step": 344954, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1110987663269043, "global_step": 344955, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.072845935821533, "global_step": 344956, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1014657020568848, "global_step": 344957, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1493682861328125, "global_step": 344958, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1076853275299072, "global_step": 344959, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0796072483062744, "global_step": 344960, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.214683771133423, "global_step": 344961, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.030834913253784, "global_step": 344962, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.124379873275757, "global_step": 344963, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0245447158813477, "global_step": 344964, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.117290735244751, "global_step": 344965, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.2025294303894043, "global_step": 344966, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.057389736175537, "global_step": 344967, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.096289873123169, "global_step": 344968, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1368799209594727, "global_step": 344969, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.149625539779663, "global_step": 344970, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1685404777526855, "global_step": 344971, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.969828486442566, "global_step": 344972, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1585702896118164, "global_step": 344973, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.143009662628174, "global_step": 344974, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0992982387542725, "global_step": 344975, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0975725650787354, "global_step": 344976, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0901308059692383, "global_step": 344977, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1044204235076904, "global_step": 344978, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1396822929382324, "global_step": 344979, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.160011053085327, "global_step": 344980, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.114469289779663, "global_step": 344981, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.107996702194214, "global_step": 344982, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.224951982498169, "global_step": 344983, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.006350517272949, "global_step": 344984, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.023890972137451, "global_step": 344985, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.059278964996338, "global_step": 344986, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1357946395874023, "global_step": 344987, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.105968713760376, "global_step": 344988, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.105321168899536, "global_step": 344989, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0839579105377197, "global_step": 344990, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1413164138793945, "global_step": 344991, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1740074157714844, "global_step": 344992, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.133242607116699, "global_step": 344993, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.11503005027771, "global_step": 344994, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.20291805267334, "global_step": 344995, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.200085163116455, "global_step": 344996, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1244494915008545, "global_step": 344997, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1058413982391357, "global_step": 344998, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.166104555130005, "global_step": 344999, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.2074315547943115, "global_step": 345000, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.134469985961914, "global_step": 345001, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1176364421844482, "global_step": 345002, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.124263048171997, "global_step": 345003, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.120518922805786, "global_step": 345004, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9785083532333374, "global_step": 345005, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0971460342407227, "global_step": 345006, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1644341945648193, "global_step": 345007, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0768868923187256, "global_step": 345008, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1723849773406982, "global_step": 345009, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.131256580352783, "global_step": 345010, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0620968341827393, "global_step": 345011, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.2229113578796387, "global_step": 345012, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.098940134048462, "global_step": 345013, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1566197872161865, "global_step": 345014, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.073923349380493, "global_step": 345015, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1669485569000244, "global_step": 345016, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.04463529586792, "global_step": 345017, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0119543075561523, "global_step": 345018, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.178140640258789, "global_step": 345019, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0323143005371094, "global_step": 345020, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0852737426757812, "global_step": 345021, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1836230754852295, "global_step": 345022, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.125899314880371, "global_step": 345023, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.2205286026000977, "global_step": 345024, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.999289870262146, "global_step": 345025, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.10604190826416, "global_step": 345026, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.144167900085449, "global_step": 345027, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.056061267852783, "global_step": 345028, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0606071949005127, "global_step": 345029, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1692287921905518, "global_step": 345030, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0810322761535645, "global_step": 345031, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0925798416137695, "global_step": 345032, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.087257146835327, "global_step": 345033, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1687169075012207, "global_step": 345034, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0904386043548584, "global_step": 345035, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0739388465881348, "global_step": 345036, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1411168575286865, "global_step": 345037, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1431989669799805, "global_step": 345038, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.247105360031128, "global_step": 345039, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1185414791107178, "global_step": 345040, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1153926849365234, "global_step": 345041, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.141211748123169, "global_step": 345042, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1186978816986084, "global_step": 345043, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.09842848777771, "global_step": 345044, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0862066745758057, "global_step": 345045, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.084343194961548, "global_step": 345046, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1639862060546875, "global_step": 345047, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.182577610015869, "global_step": 345048, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0853404998779297, "global_step": 345049, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0231823921203613, "global_step": 345050, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.126511812210083, "global_step": 345051, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.2048499584198, "global_step": 345052, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.072253465652466, "global_step": 345053, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.199415445327759, "global_step": 345054, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1423070430755615, "global_step": 345055, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.065295457839966, "global_step": 345056, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.056922674179077, "global_step": 345057, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.154087781906128, "global_step": 345058, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.099517822265625, "global_step": 345059, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0551388263702393, "global_step": 345060, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1392176151275635, "global_step": 345061, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0761046409606934, "global_step": 345062, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.153613805770874, "global_step": 345063, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.165228843688965, "global_step": 345064, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.065467119216919, "global_step": 345065, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1100807189941406, "global_step": 345066, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0830276012420654, "global_step": 345067, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0867974758148193, "global_step": 345068, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1091885566711426, "global_step": 345069, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.089928388595581, "global_step": 345070, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.2021446228027344, "global_step": 345071, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.17808198928833, "global_step": 345072, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.126169204711914, "global_step": 345073, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.079676628112793, "global_step": 345074, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.2045702934265137, "global_step": 345075, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0759191513061523, "global_step": 345076, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.148460626602173, "global_step": 345077, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0508062839508057, "global_step": 345078, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0661444664001465, "global_step": 345079, "epoch": 705, "lr": 5e-05}
{"train_loss": 1.9939106702804565, "global_step": 345080, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1206183433532715, "global_step": 345081, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0542235374450684, "global_step": 345082, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.067519187927246, "global_step": 345083, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.084308624267578, "global_step": 345084, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0583155155181885, "global_step": 345085, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0663270950317383, "global_step": 345086, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.10496187210083, "global_step": 345087, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1557862758636475, "global_step": 345088, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1320102214813232, "global_step": 345089, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0537760257720947, "global_step": 345090, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.125073194503784, "global_step": 345091, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.16528582572937, "global_step": 345092, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.073916435241699, "global_step": 345093, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.0759711265563965, "global_step": 345094, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1267895698547363, "global_step": 345095, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1065359115600586, "global_step": 345096, "epoch": 705, "lr": 5e-05}
{"train_loss": 2.1566104888916016, "global_step": 345097, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.047234058380127, "global_step": 345098, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.129093885421753, "global_step": 345099, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.072876453399658, "global_step": 345100, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1009366512298584, "global_step": 345101, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0802886486053467, "global_step": 345102, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0561602115631104, "global_step": 345103, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.109408140182495, "global_step": 345104, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0482892990112305, "global_step": 345105, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.097081184387207, "global_step": 345106, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1199567317962646, "global_step": 345107, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.097985029220581, "global_step": 345108, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0646133422851562, "global_step": 345109, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.077319622039795, "global_step": 345110, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.093946695327759, "global_step": 345111, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.037527561187744, "global_step": 345112, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.005622148513794, "global_step": 345113, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0515153408050537, "global_step": 345114, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0533952713012695, "global_step": 345115, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1197545528411865, "global_step": 345116, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1598944664001465, "global_step": 345117, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1097638607025146, "global_step": 345118, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0461978912353516, "global_step": 345119, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.194373607635498, "global_step": 345120, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0052168369293213, "global_step": 345121, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1022443771362305, "global_step": 345122, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0530800819396973, "global_step": 345123, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.126969814300537, "global_step": 345124, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.043151378631592, "global_step": 345125, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1066930294036865, "global_step": 345126, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0989341735839844, "global_step": 345127, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0687828063964844, "global_step": 345128, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0854804515838623, "global_step": 345129, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.076486587524414, "global_step": 345130, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.147127628326416, "global_step": 345131, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1101670265197754, "global_step": 345132, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.060702085494995, "global_step": 345133, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.083343505859375, "global_step": 345134, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.083988666534424, "global_step": 345135, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.064579486846924, "global_step": 345136, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0826144218444824, "global_step": 345137, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.053278684616089, "global_step": 345138, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.122849702835083, "global_step": 345139, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1119396686553955, "global_step": 345140, "epoch": 706, "lr": 5e-05}
{"train_loss": 1.950671911239624, "global_step": 345141, "epoch": 706, "lr": 5e-05}
{"train_loss": 1.994051456451416, "global_step": 345142, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1309890747070312, "global_step": 345143, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.070091962814331, "global_step": 345144, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1923773288726807, "global_step": 345145, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1437125205993652, "global_step": 345146, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1203227043151855, "global_step": 345147, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1604442596435547, "global_step": 345148, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.083333969116211, "global_step": 345149, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.085843801498413, "global_step": 345150, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.096140146255493, "global_step": 345151, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.154982328414917, "global_step": 345152, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.048109769821167, "global_step": 345153, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.047224283218384, "global_step": 345154, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2030203342437744, "global_step": 345155, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.094578742980957, "global_step": 345156, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0594425201416016, "global_step": 345157, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1844046115875244, "global_step": 345158, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0381295680999756, "global_step": 345159, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.080699920654297, "global_step": 345160, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.120863676071167, "global_step": 345161, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.075986385345459, "global_step": 345162, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0774619579315186, "global_step": 345163, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1270458698272705, "global_step": 345164, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.097174882888794, "global_step": 345165, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0963683128356934, "global_step": 345166, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.114389657974243, "global_step": 345167, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.058051586151123, "global_step": 345168, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.098496198654175, "global_step": 345169, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.089047908782959, "global_step": 345170, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.062837839126587, "global_step": 345171, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1422500610351562, "global_step": 345172, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0501902103424072, "global_step": 345173, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1321868896484375, "global_step": 345174, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0649044513702393, "global_step": 345175, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0928311347961426, "global_step": 345176, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0704197883605957, "global_step": 345177, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0544357299804688, "global_step": 345178, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.091141700744629, "global_step": 345179, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.133052110671997, "global_step": 345180, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.082066059112549, "global_step": 345181, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1464059352874756, "global_step": 345182, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1342084407806396, "global_step": 345183, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1062164306640625, "global_step": 345184, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.098008155822754, "global_step": 345185, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.00177001953125, "global_step": 345186, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1286165714263916, "global_step": 345187, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1272735595703125, "global_step": 345188, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0932841300964355, "global_step": 345189, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2106919288635254, "global_step": 345190, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1033222675323486, "global_step": 345191, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.054849863052368, "global_step": 345192, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.045038938522339, "global_step": 345193, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1191344261169434, "global_step": 345194, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.19892954826355, "global_step": 345195, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.080533266067505, "global_step": 345196, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0901334285736084, "global_step": 345197, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.025005340576172, "global_step": 345198, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.068986177444458, "global_step": 345199, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.150134325027466, "global_step": 345200, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0454580783843994, "global_step": 345201, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1194474697113037, "global_step": 345202, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0627670288085938, "global_step": 345203, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.201442003250122, "global_step": 345204, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0171947479248047, "global_step": 345205, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0409183502197266, "global_step": 345206, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0702435970306396, "global_step": 345207, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.038825511932373, "global_step": 345208, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.165550708770752, "global_step": 345209, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0436038970947266, "global_step": 345210, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.074871778488159, "global_step": 345211, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0163378715515137, "global_step": 345212, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0459179878234863, "global_step": 345213, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.108414649963379, "global_step": 345214, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.086369752883911, "global_step": 345215, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.119034767150879, "global_step": 345216, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.079883098602295, "global_step": 345217, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1004297733306885, "global_step": 345218, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.19124698638916, "global_step": 345219, "epoch": 706, "lr": 5e-05}
{"train_loss": 1.9828871488571167, "global_step": 345220, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1235125064849854, "global_step": 345221, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0700302124023438, "global_step": 345222, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1020309925079346, "global_step": 345223, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2075579166412354, "global_step": 345224, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1270530223846436, "global_step": 345225, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0910563468933105, "global_step": 345226, "epoch": 706, "lr": 5e-05}
{"train_loss": 1.9887545108795166, "global_step": 345227, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.159243583679199, "global_step": 345228, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0600790977478027, "global_step": 345229, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.049739122390747, "global_step": 345230, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.126066207885742, "global_step": 345231, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0797271728515625, "global_step": 345232, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1825578212738037, "global_step": 345233, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0684127807617188, "global_step": 345234, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.148956775665283, "global_step": 345235, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0615477561950684, "global_step": 345236, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.152153730392456, "global_step": 345237, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1701669692993164, "global_step": 345238, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.147392749786377, "global_step": 345239, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0607521533966064, "global_step": 345240, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0299925804138184, "global_step": 345241, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.022550582885742, "global_step": 345242, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0920608043670654, "global_step": 345243, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0997085571289062, "global_step": 345244, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0718772411346436, "global_step": 345245, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.100546360015869, "global_step": 345246, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1125104427337646, "global_step": 345247, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.079218626022339, "global_step": 345248, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1225664615631104, "global_step": 345249, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0630486011505127, "global_step": 345250, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.139578342437744, "global_step": 345251, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0991549491882324, "global_step": 345252, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.148958206176758, "global_step": 345253, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0620601177215576, "global_step": 345254, "epoch": 706, "lr": 5e-05}
{"train_loss": 1.9948557615280151, "global_step": 345255, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1554207801818848, "global_step": 345256, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.085069417953491, "global_step": 345257, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.102241277694702, "global_step": 345258, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0251340866088867, "global_step": 345259, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0957040786743164, "global_step": 345260, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1716744899749756, "global_step": 345261, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.116630792617798, "global_step": 345262, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1737682819366455, "global_step": 345263, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.074190139770508, "global_step": 345264, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0993831157684326, "global_step": 345265, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0471816062927246, "global_step": 345266, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1221601963043213, "global_step": 345267, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0821382999420166, "global_step": 345268, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0176620483398438, "global_step": 345269, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1908421516418457, "global_step": 345270, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.028201103210449, "global_step": 345271, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1358649730682373, "global_step": 345272, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0673584938049316, "global_step": 345273, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0990355014801025, "global_step": 345274, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1394848823547363, "global_step": 345275, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1800622940063477, "global_step": 345276, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1177167892456055, "global_step": 345277, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.086151361465454, "global_step": 345278, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.106773853302002, "global_step": 345279, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0972530841827393, "global_step": 345280, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1029481887817383, "global_step": 345281, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.149980068206787, "global_step": 345282, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0877532958984375, "global_step": 345283, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.097752571105957, "global_step": 345284, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.126786947250366, "global_step": 345285, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0269649028778076, "global_step": 345286, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1456820964813232, "global_step": 345287, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0676755905151367, "global_step": 345288, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.219801664352417, "global_step": 345289, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1209399700164795, "global_step": 345290, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0825300216674805, "global_step": 345291, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1500816345214844, "global_step": 345292, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.092017412185669, "global_step": 345293, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.150437593460083, "global_step": 345294, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0379698276519775, "global_step": 345295, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0479793548583984, "global_step": 345296, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.035656213760376, "global_step": 345297, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0429840087890625, "global_step": 345298, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1370134353637695, "global_step": 345299, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0413737297058105, "global_step": 345300, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.015552282333374, "global_step": 345301, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1344058513641357, "global_step": 345302, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2123477458953857, "global_step": 345303, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0645699501037598, "global_step": 345304, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.177294969558716, "global_step": 345305, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1477625370025635, "global_step": 345306, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.185117721557617, "global_step": 345307, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1571404933929443, "global_step": 345308, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1309268474578857, "global_step": 345309, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.136941909790039, "global_step": 345310, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.071359157562256, "global_step": 345311, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.049880266189575, "global_step": 345312, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.084411144256592, "global_step": 345313, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.002795934677124, "global_step": 345314, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1156539916992188, "global_step": 345315, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0808894634246826, "global_step": 345316, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.051194906234741, "global_step": 345317, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.023730516433716, "global_step": 345318, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.17045259475708, "global_step": 345319, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0845937728881836, "global_step": 345320, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1715962886810303, "global_step": 345321, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.098875045776367, "global_step": 345322, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1420087814331055, "global_step": 345323, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0857062339782715, "global_step": 345324, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.189415216445923, "global_step": 345325, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0612549781799316, "global_step": 345326, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1164233684539795, "global_step": 345327, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1609489917755127, "global_step": 345328, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1083984375, "global_step": 345329, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0556609630584717, "global_step": 345330, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.121641159057617, "global_step": 345331, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1387932300567627, "global_step": 345332, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1318767070770264, "global_step": 345333, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0110177993774414, "global_step": 345334, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1245415210723877, "global_step": 345335, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.052354097366333, "global_step": 345336, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.190314292907715, "global_step": 345337, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0775437355041504, "global_step": 345338, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0690629482269287, "global_step": 345339, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1011812686920166, "global_step": 345340, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.063005208969116, "global_step": 345341, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.095463275909424, "global_step": 345342, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0633206367492676, "global_step": 345343, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1324961185455322, "global_step": 345344, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1394519805908203, "global_step": 345345, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.102036476135254, "global_step": 345346, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1407148838043213, "global_step": 345347, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2385411262512207, "global_step": 345348, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.109149694442749, "global_step": 345349, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0217487812042236, "global_step": 345350, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.178269386291504, "global_step": 345351, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0235230922698975, "global_step": 345352, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0218632221221924, "global_step": 345353, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0711405277252197, "global_step": 345354, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0930769443511963, "global_step": 345355, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.117682695388794, "global_step": 345356, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0236809253692627, "global_step": 345357, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.022928476333618, "global_step": 345358, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1652958393096924, "global_step": 345359, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1521122455596924, "global_step": 345360, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0708916187286377, "global_step": 345361, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1056320667266846, "global_step": 345362, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1997804641723633, "global_step": 345363, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.121525526046753, "global_step": 345364, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1181068420410156, "global_step": 345365, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1376230716705322, "global_step": 345366, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1042070388793945, "global_step": 345367, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0237295627593994, "global_step": 345368, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.075779676437378, "global_step": 345369, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.188811779022217, "global_step": 345370, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.119431495666504, "global_step": 345371, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1290268898010254, "global_step": 345372, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.098477602005005, "global_step": 345373, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0165796279907227, "global_step": 345374, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1326539516448975, "global_step": 345375, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.140238046646118, "global_step": 345376, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.011413812637329, "global_step": 345377, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0527663230895996, "global_step": 345378, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.195711612701416, "global_step": 345379, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1724209785461426, "global_step": 345380, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.157122850418091, "global_step": 345381, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.200909376144409, "global_step": 345382, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.158195972442627, "global_step": 345383, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0390655994415283, "global_step": 345384, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0914738178253174, "global_step": 345385, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.17919659614563, "global_step": 345386, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.135411500930786, "global_step": 345387, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0623960494995117, "global_step": 345388, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1443161964416504, "global_step": 345389, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.145230293273926, "global_step": 345390, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1281180381774902, "global_step": 345391, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1565845012664795, "global_step": 345392, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1068167686462402, "global_step": 345393, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0490942001342773, "global_step": 345394, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.165933609008789, "global_step": 345395, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0369765758514404, "global_step": 345396, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.028163194656372, "global_step": 345397, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1087591648101807, "global_step": 345398, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.018336534500122, "global_step": 345399, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.193758487701416, "global_step": 345400, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1172330379486084, "global_step": 345401, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.082826614379883, "global_step": 345402, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0973987579345703, "global_step": 345403, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1088547706604004, "global_step": 345404, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0975685119628906, "global_step": 345405, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1618776321411133, "global_step": 345406, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1516449451446533, "global_step": 345407, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.153494119644165, "global_step": 345408, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0889148712158203, "global_step": 345409, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.024172306060791, "global_step": 345410, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1988131999969482, "global_step": 345411, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.06416916847229, "global_step": 345412, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.097714424133301, "global_step": 345413, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.14473032951355, "global_step": 345414, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.067763090133667, "global_step": 345415, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.040809154510498, "global_step": 345416, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1495378017425537, "global_step": 345417, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1125733852386475, "global_step": 345418, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1437768936157227, "global_step": 345419, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1223812103271484, "global_step": 345420, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.080244302749634, "global_step": 345421, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1360514163970947, "global_step": 345422, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1439754962921143, "global_step": 345423, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.043623685836792, "global_step": 345424, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.110873222351074, "global_step": 345425, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.04598331451416, "global_step": 345426, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.14414119720459, "global_step": 345427, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0775301456451416, "global_step": 345428, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1097583770751953, "global_step": 345429, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1073739528656006, "global_step": 345430, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.161726951599121, "global_step": 345431, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1795716285705566, "global_step": 345432, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.103896141052246, "global_step": 345433, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0196704864501953, "global_step": 345434, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1397347450256348, "global_step": 345435, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.07265043258667, "global_step": 345436, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0717415809631348, "global_step": 345437, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.066286087036133, "global_step": 345438, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.021115779876709, "global_step": 345439, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1779444217681885, "global_step": 345440, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0429718494415283, "global_step": 345441, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.08598256111145, "global_step": 345442, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1539790630340576, "global_step": 345443, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.184816598892212, "global_step": 345444, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1754941940307617, "global_step": 345445, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.157179594039917, "global_step": 345446, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0773158073425293, "global_step": 345447, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1136460304260254, "global_step": 345448, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0833795070648193, "global_step": 345449, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0788657665252686, "global_step": 345450, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0685415267944336, "global_step": 345451, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1455962657928467, "global_step": 345452, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.139514684677124, "global_step": 345453, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0141594409942627, "global_step": 345454, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.162095069885254, "global_step": 345455, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0883288383483887, "global_step": 345456, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.185237169265747, "global_step": 345457, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.102372169494629, "global_step": 345458, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.127350330352783, "global_step": 345459, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.052494525909424, "global_step": 345460, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0620172023773193, "global_step": 345461, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0857956409454346, "global_step": 345462, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1414148807525635, "global_step": 345463, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0928080081939697, "global_step": 345464, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1880269050598145, "global_step": 345465, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.124346971511841, "global_step": 345466, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0468263626098633, "global_step": 345467, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.098026990890503, "global_step": 345468, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1320416927337646, "global_step": 345469, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1048221588134766, "global_step": 345470, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.145820140838623, "global_step": 345471, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2142531871795654, "global_step": 345472, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.107372999191284, "global_step": 345473, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0648512840270996, "global_step": 345474, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.189493417739868, "global_step": 345475, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1184046268463135, "global_step": 345476, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.066054344177246, "global_step": 345477, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.019526720046997, "global_step": 345478, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2090115547180176, "global_step": 345479, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.205195665359497, "global_step": 345480, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.040675640106201, "global_step": 345481, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0262935161590576, "global_step": 345482, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.145050525665283, "global_step": 345483, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.073974609375, "global_step": 345484, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.138810873031616, "global_step": 345485, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0628163814544678, "global_step": 345486, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.222424268722534, "global_step": 345487, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.066704750061035, "global_step": 345488, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.09352970123291, "global_step": 345489, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.120344877243042, "global_step": 345490, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.111222505569458, "global_step": 345491, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0881783962249756, "global_step": 345492, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1375598907470703, "global_step": 345493, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1812744140625, "global_step": 345494, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1855907440185547, "global_step": 345495, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0816352367401123, "global_step": 345496, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1594326496124268, "global_step": 345497, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1442039012908936, "global_step": 345498, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1333024501800537, "global_step": 345499, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1218862533569336, "global_step": 345500, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.141819953918457, "global_step": 345501, "epoch": 706, "lr": 5e-05}
{"train_loss": 1.9941283464431763, "global_step": 345502, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.099350690841675, "global_step": 345503, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1374199390411377, "global_step": 345504, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0832955837249756, "global_step": 345505, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1008355617523193, "global_step": 345506, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.162302017211914, "global_step": 345507, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.112074375152588, "global_step": 345508, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0808324813842773, "global_step": 345509, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1527881622314453, "global_step": 345510, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0826871395111084, "global_step": 345511, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1733598709106445, "global_step": 345512, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1504106521606445, "global_step": 345513, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.132321834564209, "global_step": 345514, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.002835750579834, "global_step": 345515, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.186302661895752, "global_step": 345516, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1122138500213623, "global_step": 345517, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.13562273979187, "global_step": 345518, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1299242973327637, "global_step": 345519, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1409595012664795, "global_step": 345520, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.124807596206665, "global_step": 345521, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1057016849517822, "global_step": 345522, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.100811719894409, "global_step": 345523, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.119110107421875, "global_step": 345524, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.089698553085327, "global_step": 345525, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.11449933052063, "global_step": 345526, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.059652090072632, "global_step": 345527, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.131619691848755, "global_step": 345528, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.049086809158325, "global_step": 345529, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.091909885406494, "global_step": 345530, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.081059694290161, "global_step": 345531, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0110247135162354, "global_step": 345532, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.059701681137085, "global_step": 345533, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1544411182403564, "global_step": 345534, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0883562564849854, "global_step": 345535, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.087151288986206, "global_step": 345536, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1503517627716064, "global_step": 345537, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.188455581665039, "global_step": 345538, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.191438913345337, "global_step": 345539, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0414042472839355, "global_step": 345540, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1277241706848145, "global_step": 345541, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0790717601776123, "global_step": 345542, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0465846061706543, "global_step": 345543, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1257057189941406, "global_step": 345544, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0223634243011475, "global_step": 345545, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1089186668395996, "global_step": 345546, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1062991619110107, "global_step": 345547, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1213135719299316, "global_step": 345548, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1737632751464844, "global_step": 345549, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1291258335113525, "global_step": 345550, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0951623916625977, "global_step": 345551, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.155266046524048, "global_step": 345552, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.043886184692383, "global_step": 345553, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.057368516921997, "global_step": 345554, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.089521646499634, "global_step": 345555, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.092811107635498, "global_step": 345556, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0341453552246094, "global_step": 345557, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0956616401672363, "global_step": 345558, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1262147426605225, "global_step": 345559, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1323366165161133, "global_step": 345560, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0249617099761963, "global_step": 345561, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.133183717727661, "global_step": 345562, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1140708923339844, "global_step": 345563, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1406826972961426, "global_step": 345564, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0383670330047607, "global_step": 345565, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0746943950653076, "global_step": 345566, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0943665504455566, "global_step": 345567, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1026957035064697, "global_step": 345568, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0719144344329834, "global_step": 345569, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0987138748168945, "global_step": 345570, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1498537063598633, "global_step": 345571, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0430521965026855, "global_step": 345572, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1170458793640137, "global_step": 345573, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1254193782806396, "global_step": 345574, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.079832077026367, "global_step": 345575, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.13557505607605, "global_step": 345576, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.179598331451416, "global_step": 345577, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1659882068634033, "global_step": 345578, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.146923542022705, "global_step": 345579, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.16403865814209, "global_step": 345580, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.169860363006592, "global_step": 345581, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.091216802597046, "global_step": 345582, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1154916286468506, "global_step": 345583, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.142861843109131, "global_step": 345584, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2000176906585693, "global_step": 345585, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1160428524017334, "global_step": 345586, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.066746711730957, "global_step": 345587, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0309364795684814, "global_step": 345588, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1278064250946045, "global_step": 345589, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0787370204925537, "global_step": 345590, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1276803016662598, "global_step": 345591, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.175523281097412, "global_step": 345592, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.050520658493042, "global_step": 345593, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1917519569396973, "global_step": 345594, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.153423309326172, "global_step": 345595, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.113166093826294, "global_step": 345596, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1413443088531494, "global_step": 345597, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1298553943634033, "global_step": 345598, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1077003479003906, "global_step": 345599, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1022143363952637, "global_step": 345600, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1017374992370605, "global_step": 345601, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1182827949523926, "global_step": 345602, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1259005069732666, "global_step": 345603, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0734715461730957, "global_step": 345604, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0196409225463867, "global_step": 345605, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.105602502822876, "global_step": 345606, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.202266216278076, "global_step": 345607, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.122171401977539, "global_step": 345608, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0499866008758545, "global_step": 345609, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.109067678451538, "global_step": 345610, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0862836837768555, "global_step": 345611, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.098832607269287, "global_step": 345612, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.034672975540161, "global_step": 345613, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1486377716064453, "global_step": 345614, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0960543155670166, "global_step": 345615, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1021785736083984, "global_step": 345616, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1746253967285156, "global_step": 345617, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1095244884490967, "global_step": 345618, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.195781946182251, "global_step": 345619, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1223156452178955, "global_step": 345620, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.125235080718994, "global_step": 345621, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.153360366821289, "global_step": 345622, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.130077838897705, "global_step": 345623, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1552908420562744, "global_step": 345624, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.114492893218994, "global_step": 345625, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.053887367248535, "global_step": 345626, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1269454956054688, "global_step": 345627, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1691479682922363, "global_step": 345628, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1141276359558105, "global_step": 345629, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1219286918640137, "global_step": 345630, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.162498950958252, "global_step": 345631, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0614523887634277, "global_step": 345632, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2254703044891357, "global_step": 345633, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0538389682769775, "global_step": 345634, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1055831909179688, "global_step": 345635, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1409904956817627, "global_step": 345636, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2231385707855225, "global_step": 345637, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1954994201660156, "global_step": 345638, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1671981811523438, "global_step": 345639, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1590843200683594, "global_step": 345640, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1301891803741455, "global_step": 345641, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.156789779663086, "global_step": 345642, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1141157150268555, "global_step": 345643, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0697858333587646, "global_step": 345644, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.106117010116577, "global_step": 345645, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.068337917327881, "global_step": 345646, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1414999961853027, "global_step": 345647, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0866916179656982, "global_step": 345648, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0285418033599854, "global_step": 345649, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.098449945449829, "global_step": 345650, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1408705711364746, "global_step": 345651, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.071991443634033, "global_step": 345652, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1185033321380615, "global_step": 345653, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.115455150604248, "global_step": 345654, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1022913455963135, "global_step": 345655, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0286102294921875, "global_step": 345656, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1274948120117188, "global_step": 345657, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.111143112182617, "global_step": 345658, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.099260091781616, "global_step": 345659, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.127044677734375, "global_step": 345660, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.058046817779541, "global_step": 345661, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1586198806762695, "global_step": 345662, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1353673934936523, "global_step": 345663, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.139695882797241, "global_step": 345664, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0790138244628906, "global_step": 345665, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0843942165374756, "global_step": 345666, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0679585933685303, "global_step": 345667, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.168184280395508, "global_step": 345668, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.149289131164551, "global_step": 345669, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.071099042892456, "global_step": 345670, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.117737293243408, "global_step": 345671, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1774020195007324, "global_step": 345672, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1118905544281006, "global_step": 345673, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0726871490478516, "global_step": 345674, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1869213581085205, "global_step": 345675, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0696845054626465, "global_step": 345676, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.091637372970581, "global_step": 345677, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0410616397857666, "global_step": 345678, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.084401845932007, "global_step": 345679, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.136375904083252, "global_step": 345680, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1745903491973877, "global_step": 345681, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1315479278564453, "global_step": 345682, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.085219144821167, "global_step": 345683, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0360372066497803, "global_step": 345684, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1456282138824463, "global_step": 345685, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.085808515548706, "global_step": 345686, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.11415433883667, "global_step": 345687, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1935768127441406, "global_step": 345688, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.178321599960327, "global_step": 345689, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2037360668182373, "global_step": 345690, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1056923866271973, "global_step": 345691, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.176737070083618, "global_step": 345692, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0889790058135986, "global_step": 345693, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.138983726501465, "global_step": 345694, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.103882074356079, "global_step": 345695, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0767507553100586, "global_step": 345696, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1835973262786865, "global_step": 345697, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1186740398406982, "global_step": 345698, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1182000637054443, "global_step": 345699, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.218503713607788, "global_step": 345700, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.216252565383911, "global_step": 345701, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1214377880096436, "global_step": 345702, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.057628631591797, "global_step": 345703, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0447235107421875, "global_step": 345704, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0846216678619385, "global_step": 345705, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.193885326385498, "global_step": 345706, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.117835283279419, "global_step": 345707, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.130385398864746, "global_step": 345708, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.091675281524658, "global_step": 345709, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0347373485565186, "global_step": 345710, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.066948652267456, "global_step": 345711, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.146667003631592, "global_step": 345712, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.157405138015747, "global_step": 345713, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1362318992614746, "global_step": 345714, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0153892040252686, "global_step": 345715, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.103785991668701, "global_step": 345716, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.034149169921875, "global_step": 345717, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0781474113464355, "global_step": 345718, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.167391061782837, "global_step": 345719, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.127457618713379, "global_step": 345720, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1432268619537354, "global_step": 345721, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.100174903869629, "global_step": 345722, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.129176616668701, "global_step": 345723, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0966906547546387, "global_step": 345724, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.10134220123291, "global_step": 345725, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.068458318710327, "global_step": 345726, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.12945294380188, "global_step": 345727, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.079920530319214, "global_step": 345728, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1257636547088623, "global_step": 345729, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1683716773986816, "global_step": 345730, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1500306129455566, "global_step": 345731, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2010233402252197, "global_step": 345732, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.061100482940674, "global_step": 345733, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.086829662322998, "global_step": 345734, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.198976755142212, "global_step": 345735, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0338361263275146, "global_step": 345736, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.104585886001587, "global_step": 345737, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1445798873901367, "global_step": 345738, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0774741172790527, "global_step": 345739, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0731539726257324, "global_step": 345740, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1157026290893555, "global_step": 345741, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0710976123809814, "global_step": 345742, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1071906089782715, "global_step": 345743, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1985974311828613, "global_step": 345744, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0594241619110107, "global_step": 345745, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0490505695343018, "global_step": 345746, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.047023296356201, "global_step": 345747, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.058032512664795, "global_step": 345748, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1107852458953857, "global_step": 345749, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.039541482925415, "global_step": 345750, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0457193851470947, "global_step": 345751, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1459832191467285, "global_step": 345752, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1598575115203857, "global_step": 345753, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.195565700531006, "global_step": 345754, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1139512062072754, "global_step": 345755, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0981197357177734, "global_step": 345756, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1361687183380127, "global_step": 345757, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0579428672790527, "global_step": 345758, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0666561126708984, "global_step": 345759, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1129250526428223, "global_step": 345760, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0856175422668457, "global_step": 345761, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1664464473724365, "global_step": 345762, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0082521438598633, "global_step": 345763, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1261754035949707, "global_step": 345764, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.183793306350708, "global_step": 345765, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.078310251235962, "global_step": 345766, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.171259641647339, "global_step": 345767, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1311943531036377, "global_step": 345768, "epoch": 706, "lr": 5e-05}
{"train_loss": 1.9976561069488525, "global_step": 345769, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.085543394088745, "global_step": 345770, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.021068572998047, "global_step": 345771, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.118317127227783, "global_step": 345772, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1701948642730713, "global_step": 345773, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0760226249694824, "global_step": 345774, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2151095867156982, "global_step": 345775, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.082975149154663, "global_step": 345776, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0790507793426514, "global_step": 345777, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.049320697784424, "global_step": 345778, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.125333309173584, "global_step": 345779, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0867276191711426, "global_step": 345780, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1141953468322754, "global_step": 345781, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.118793249130249, "global_step": 345782, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2119193077087402, "global_step": 345783, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1360557079315186, "global_step": 345784, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0355277061462402, "global_step": 345785, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1606650352478027, "global_step": 345786, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.168431520462036, "global_step": 345787, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1264114379882812, "global_step": 345788, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1415576934814453, "global_step": 345789, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1186792850494385, "global_step": 345790, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.061897039413452, "global_step": 345791, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0732059478759766, "global_step": 345792, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.105445146560669, "global_step": 345793, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1120657920837402, "global_step": 345794, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.104797840118408, "global_step": 345795, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.170889139175415, "global_step": 345796, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0820212364196777, "global_step": 345797, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.163346290588379, "global_step": 345798, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1402697563171387, "global_step": 345799, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.138947010040283, "global_step": 345800, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.048959493637085, "global_step": 345801, "epoch": 706, "lr": 5e-05}
{"train_loss": 1.9830368757247925, "global_step": 345802, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.078929901123047, "global_step": 345803, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.126448631286621, "global_step": 345804, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.077000379562378, "global_step": 345805, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.142827033996582, "global_step": 345806, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.129295587539673, "global_step": 345807, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.115104913711548, "global_step": 345808, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1505963802337646, "global_step": 345809, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0705902576446533, "global_step": 345810, "epoch": 706, "lr": 5e-05}
{"train_loss": 1.997119665145874, "global_step": 345811, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.166132926940918, "global_step": 345812, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1022591590881348, "global_step": 345813, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.093427896499634, "global_step": 345814, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1029160022735596, "global_step": 345815, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.057743787765503, "global_step": 345816, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.037799119949341, "global_step": 345817, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1390395164489746, "global_step": 345818, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.082681894302368, "global_step": 345819, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.114607572555542, "global_step": 345820, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0907132625579834, "global_step": 345821, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.169994592666626, "global_step": 345822, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1571249961853027, "global_step": 345823, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.191474199295044, "global_step": 345824, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0925445556640625, "global_step": 345825, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.076483726501465, "global_step": 345826, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.17889142036438, "global_step": 345827, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1496105194091797, "global_step": 345828, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1169886589050293, "global_step": 345829, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.130333662033081, "global_step": 345830, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1561269760131836, "global_step": 345831, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1528613567352295, "global_step": 345832, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0969536304473877, "global_step": 345833, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0123183727264404, "global_step": 345834, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1156861782073975, "global_step": 345835, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0153114795684814, "global_step": 345836, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.113736391067505, "global_step": 345837, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1209816932678223, "global_step": 345838, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1050302982330322, "global_step": 345839, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.062027931213379, "global_step": 345840, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.120948553085327, "global_step": 345841, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.163356304168701, "global_step": 345842, "epoch": 706, "lr": 5e-05}
{"train_loss": 1.9809515476226807, "global_step": 345843, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1244099140167236, "global_step": 345844, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0630581378936768, "global_step": 345845, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.113175868988037, "global_step": 345846, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0731871128082275, "global_step": 345847, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0640833377838135, "global_step": 345848, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.109222888946533, "global_step": 345849, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.135624885559082, "global_step": 345850, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0796234607696533, "global_step": 345851, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1019480228424072, "global_step": 345852, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.038766860961914, "global_step": 345853, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1337356567382812, "global_step": 345854, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1599395275115967, "global_step": 345855, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.163966178894043, "global_step": 345856, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1781461238861084, "global_step": 345857, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.026139259338379, "global_step": 345858, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0979831218719482, "global_step": 345859, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.15796160697937, "global_step": 345860, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.081573486328125, "global_step": 345861, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1063456535339355, "global_step": 345862, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.048401117324829, "global_step": 345863, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1280431747436523, "global_step": 345864, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.235468626022339, "global_step": 345865, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1559321880340576, "global_step": 345866, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.11590576171875, "global_step": 345867, "epoch": 706, "lr": 5e-05}
{"train_loss": 1.961779236793518, "global_step": 345868, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.08144211769104, "global_step": 345869, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0559279918670654, "global_step": 345870, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.09844970703125, "global_step": 345871, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1062586307525635, "global_step": 345872, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0932328701019287, "global_step": 345873, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.121997594833374, "global_step": 345874, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1699633598327637, "global_step": 345875, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1698076725006104, "global_step": 345876, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1118876934051514, "global_step": 345877, "epoch": 706, "lr": 5e-05}
{"train_loss": 1.9741122722625732, "global_step": 345878, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1195809841156006, "global_step": 345879, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0296452045440674, "global_step": 345880, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.087571620941162, "global_step": 345881, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2097127437591553, "global_step": 345882, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1026933193206787, "global_step": 345883, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1210765838623047, "global_step": 345884, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.136229991912842, "global_step": 345885, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0892844200134277, "global_step": 345886, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1357386112213135, "global_step": 345887, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1232800483703613, "global_step": 345888, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1187760829925537, "global_step": 345889, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.113553524017334, "global_step": 345890, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0958549976348877, "global_step": 345891, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0766427516937256, "global_step": 345892, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.082432746887207, "global_step": 345893, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.096994161605835, "global_step": 345894, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.145164728164673, "global_step": 345895, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2265727519989014, "global_step": 345896, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0508573055267334, "global_step": 345897, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0620052814483643, "global_step": 345898, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.050875663757324, "global_step": 345899, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0614233016967773, "global_step": 345900, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.06514573097229, "global_step": 345901, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.064246654510498, "global_step": 345902, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1853246688842773, "global_step": 345903, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0697078704833984, "global_step": 345904, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0301594734191895, "global_step": 345905, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.154062032699585, "global_step": 345906, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.017092227935791, "global_step": 345907, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0847034454345703, "global_step": 345908, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1285152435302734, "global_step": 345909, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1242356300354004, "global_step": 345910, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.13277006149292, "global_step": 345911, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.171973466873169, "global_step": 345912, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.07863712310791, "global_step": 345913, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0627636909484863, "global_step": 345914, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1571638584136963, "global_step": 345915, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1142020225524902, "global_step": 345916, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.021801471710205, "global_step": 345917, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.134197235107422, "global_step": 345918, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1152069568634033, "global_step": 345919, "epoch": 706, "lr": 5e-05}
{"train_loss": 1.993289828300476, "global_step": 345920, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.093823194503784, "global_step": 345921, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1990089416503906, "global_step": 345922, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0762369632720947, "global_step": 345923, "epoch": 706, "lr": 5e-05}
{"train_loss": 1.9839948415756226, "global_step": 345924, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1751434803009033, "global_step": 345925, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0792036056518555, "global_step": 345926, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1274123191833496, "global_step": 345927, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0453808307647705, "global_step": 345928, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.088200807571411, "global_step": 345929, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1331684589385986, "global_step": 345930, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1001503467559814, "global_step": 345931, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.064742088317871, "global_step": 345932, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.133928060531616, "global_step": 345933, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1238272190093994, "global_step": 345934, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0103964805603027, "global_step": 345935, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.145045518875122, "global_step": 345936, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.127448320388794, "global_step": 345937, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0730645656585693, "global_step": 345938, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.175601005554199, "global_step": 345939, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.115238904953003, "global_step": 345940, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1187074184417725, "global_step": 345941, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1047651767730713, "global_step": 345942, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.104478359222412, "global_step": 345943, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0699074268341064, "global_step": 345944, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0482027530670166, "global_step": 345945, "epoch": 706, "lr": 5e-05}
{"train_loss": 1.9925493001937866, "global_step": 345946, "epoch": 706, "lr": 5e-05}
{"train_loss": 1.9932128190994263, "global_step": 345947, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1033895015716553, "global_step": 345948, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.219569683074951, "global_step": 345949, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.119910955429077, "global_step": 345950, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.080223321914673, "global_step": 345951, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.062192678451538, "global_step": 345952, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.109989643096924, "global_step": 345953, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0152478218078613, "global_step": 345954, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0991482734680176, "global_step": 345955, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.08388352394104, "global_step": 345956, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0930917263031006, "global_step": 345957, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2083065509796143, "global_step": 345958, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.05816912651062, "global_step": 345959, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.142383098602295, "global_step": 345960, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0371205806732178, "global_step": 345961, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.107252359390259, "global_step": 345962, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1636929512023926, "global_step": 345963, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0678436756134033, "global_step": 345964, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.251204490661621, "global_step": 345965, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0852909088134766, "global_step": 345966, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0674920082092285, "global_step": 345967, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0988998413085938, "global_step": 345968, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1093647480010986, "global_step": 345969, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.094646453857422, "global_step": 345970, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1348421573638916, "global_step": 345971, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1674916744232178, "global_step": 345972, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.102530002593994, "global_step": 345973, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.062391996383667, "global_step": 345974, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1491270065307617, "global_step": 345975, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0717830657958984, "global_step": 345976, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.070183277130127, "global_step": 345977, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.077404499053955, "global_step": 345978, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.155038833618164, "global_step": 345979, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.098773241043091, "global_step": 345980, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0838027000427246, "global_step": 345981, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.162437915802002, "global_step": 345982, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.188901662826538, "global_step": 345983, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.091827869415283, "global_step": 345984, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.086233139038086, "global_step": 345985, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.09177303314209, "global_step": 345986, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1144073009490967, "global_step": 345987, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1043508052825928, "global_step": 345988, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.072972297668457, "global_step": 345989, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.123758554458618, "global_step": 345990, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0833511352539062, "global_step": 345991, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.067861557006836, "global_step": 345992, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.15466046333313, "global_step": 345993, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.141857624053955, "global_step": 345994, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0544724464416504, "global_step": 345995, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.091921806335449, "global_step": 345996, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0977931022644043, "global_step": 345997, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.115478992462158, "global_step": 345998, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.116213321685791, "global_step": 345999, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.099928617477417, "global_step": 346000, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.123337745666504, "global_step": 346001, "epoch": 706, "lr": 5e-05}
{"train_loss": 1.980797290802002, "global_step": 346002, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1412627696990967, "global_step": 346003, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.148923635482788, "global_step": 346004, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0663578510284424, "global_step": 346005, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.124480724334717, "global_step": 346006, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.129448175430298, "global_step": 346007, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.117441177368164, "global_step": 346008, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0409486293792725, "global_step": 346009, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1028997898101807, "global_step": 346010, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.144425392150879, "global_step": 346011, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.174679756164551, "global_step": 346012, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.075063467025757, "global_step": 346013, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.116273880004883, "global_step": 346014, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.146765947341919, "global_step": 346015, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1267497539520264, "global_step": 346016, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.04058575630188, "global_step": 346017, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1826274394989014, "global_step": 346018, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.148010730743408, "global_step": 346019, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.196887969970703, "global_step": 346020, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.065777063369751, "global_step": 346021, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.041566848754883, "global_step": 346022, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.114799976348877, "global_step": 346023, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0979905128479004, "global_step": 346024, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0154848098754883, "global_step": 346025, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.053119421005249, "global_step": 346026, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.076533317565918, "global_step": 346027, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1766655445098877, "global_step": 346028, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1312203407287598, "global_step": 346029, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0673916339874268, "global_step": 346030, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.165231704711914, "global_step": 346031, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.125051975250244, "global_step": 346032, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0722622871398926, "global_step": 346033, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.12250018119812, "global_step": 346034, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0870699882507324, "global_step": 346035, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1481521129608154, "global_step": 346036, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1287131309509277, "global_step": 346037, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1439218521118164, "global_step": 346038, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0633881092071533, "global_step": 346039, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1516871452331543, "global_step": 346040, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.223512649536133, "global_step": 346041, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1106553077697754, "global_step": 346042, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2483808994293213, "global_step": 346043, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1653261184692383, "global_step": 346044, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1589622497558594, "global_step": 346045, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.170942544937134, "global_step": 346046, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.037498950958252, "global_step": 346047, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.150369644165039, "global_step": 346048, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.123516082763672, "global_step": 346049, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1561062335968018, "global_step": 346050, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1489689350128174, "global_step": 346051, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2552685737609863, "global_step": 346052, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1822946071624756, "global_step": 346053, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.2139713764190674, "global_step": 346054, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1810789108276367, "global_step": 346055, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1198716163635254, "global_step": 346056, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.10772967338562, "global_step": 346057, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1140196323394775, "global_step": 346058, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0999035835266113, "global_step": 346059, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1462979316711426, "global_step": 346060, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1585850715637207, "global_step": 346061, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0622684955596924, "global_step": 346062, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1609463691711426, "global_step": 346063, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0404224395751953, "global_step": 346064, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.1069018840789795, "global_step": 346065, "epoch": 706, "lr": 5e-05}
{"train_loss": 2.0108802318573, "global_step": 346066, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.160649061203003, "global_step": 346067, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0529048442840576, "global_step": 346068, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.098890542984009, "global_step": 346069, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.069359064102173, "global_step": 346070, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.112572431564331, "global_step": 346071, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1274094581604004, "global_step": 346072, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0378830432891846, "global_step": 346073, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.164820671081543, "global_step": 346074, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0725855827331543, "global_step": 346075, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1358089447021484, "global_step": 346076, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.104844331741333, "global_step": 346077, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.080505132675171, "global_step": 346078, "epoch": 707, "lr": 5e-05}
{"train_loss": 1.9972174167633057, "global_step": 346079, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.106581211090088, "global_step": 346080, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.096773862838745, "global_step": 346081, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.117172956466675, "global_step": 346082, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.102018356323242, "global_step": 346083, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.148876190185547, "global_step": 346084, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0893161296844482, "global_step": 346085, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.212496280670166, "global_step": 346086, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.053194284439087, "global_step": 346087, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1309189796447754, "global_step": 346088, "epoch": 707, "lr": 5e-05}
{"train_loss": 1.9890803098678589, "global_step": 346089, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1729073524475098, "global_step": 346090, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0772476196289062, "global_step": 346091, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.100001335144043, "global_step": 346092, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0916569232940674, "global_step": 346093, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0490872859954834, "global_step": 346094, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.067803382873535, "global_step": 346095, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.183824300765991, "global_step": 346096, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1694743633270264, "global_step": 346097, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0449788570404053, "global_step": 346098, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.13948392868042, "global_step": 346099, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0264945030212402, "global_step": 346100, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0885963439941406, "global_step": 346101, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0889077186584473, "global_step": 346102, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0867536067962646, "global_step": 346103, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.009645462036133, "global_step": 346104, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.065260648727417, "global_step": 346105, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0984885692596436, "global_step": 346106, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.151047706604004, "global_step": 346107, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0135891437530518, "global_step": 346108, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.054252862930298, "global_step": 346109, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1322500705718994, "global_step": 346110, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1348791122436523, "global_step": 346111, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1370930671691895, "global_step": 346112, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1266884803771973, "global_step": 346113, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0920708179473877, "global_step": 346114, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0521066188812256, "global_step": 346115, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.119013547897339, "global_step": 346116, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1117894649505615, "global_step": 346117, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1209945678710938, "global_step": 346118, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1498608589172363, "global_step": 346119, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0729732513427734, "global_step": 346120, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0790135860443115, "global_step": 346121, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.084681272506714, "global_step": 346122, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.048670768737793, "global_step": 346123, "epoch": 707, "lr": 5e-05}
{"train_loss": 1.971861720085144, "global_step": 346124, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.081162691116333, "global_step": 346125, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1620891094207764, "global_step": 346126, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0712690353393555, "global_step": 346127, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0955302715301514, "global_step": 346128, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1585819721221924, "global_step": 346129, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1071174144744873, "global_step": 346130, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1516811847686768, "global_step": 346131, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.128946542739868, "global_step": 346132, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1320509910583496, "global_step": 346133, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0491089820861816, "global_step": 346134, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0450596809387207, "global_step": 346135, "epoch": 707, "lr": 5e-05}
{"train_loss": 1.9861475229263306, "global_step": 346136, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.090850353240967, "global_step": 346137, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0462329387664795, "global_step": 346138, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0773019790649414, "global_step": 346139, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.120290756225586, "global_step": 346140, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0796127319335938, "global_step": 346141, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.066892147064209, "global_step": 346142, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.125041961669922, "global_step": 346143, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0993127822875977, "global_step": 346144, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1789333820343018, "global_step": 346145, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.104573965072632, "global_step": 346146, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0675086975097656, "global_step": 346147, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0626883506774902, "global_step": 346148, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1975622177124023, "global_step": 346149, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0482277870178223, "global_step": 346150, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0553712844848633, "global_step": 346151, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.080958127975464, "global_step": 346152, "epoch": 707, "lr": 5e-05}
{"train_loss": 1.9576528072357178, "global_step": 346153, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1093006134033203, "global_step": 346154, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.077385425567627, "global_step": 346155, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.047255039215088, "global_step": 346156, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1294498443603516, "global_step": 346157, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.07257342338562, "global_step": 346158, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1413416862487793, "global_step": 346159, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1221914291381836, "global_step": 346160, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.138408899307251, "global_step": 346161, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.124391794204712, "global_step": 346162, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.058060646057129, "global_step": 346163, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1063482761383057, "global_step": 346164, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0886569023132324, "global_step": 346165, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0891051292419434, "global_step": 346166, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1664018630981445, "global_step": 346167, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0676162242889404, "global_step": 346168, "epoch": 707, "lr": 5e-05}
{"train_loss": 1.9975250959396362, "global_step": 346169, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1597113609313965, "global_step": 346170, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0793888568878174, "global_step": 346171, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0512499809265137, "global_step": 346172, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1188104152679443, "global_step": 346173, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.168412208557129, "global_step": 346174, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0680811405181885, "global_step": 346175, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.129347562789917, "global_step": 346176, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1191272735595703, "global_step": 346177, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0646562576293945, "global_step": 346178, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.048208475112915, "global_step": 346179, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1742358207702637, "global_step": 346180, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1349663734436035, "global_step": 346181, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0757741928100586, "global_step": 346182, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1630730628967285, "global_step": 346183, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.027622699737549, "global_step": 346184, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.087249994277954, "global_step": 346185, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0774881839752197, "global_step": 346186, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0558509826660156, "global_step": 346187, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1298036575317383, "global_step": 346188, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.117821216583252, "global_step": 346189, "epoch": 707, "lr": 5e-05}
{"train_loss": 1.9934817552566528, "global_step": 346190, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0939090251922607, "global_step": 346191, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0607008934020996, "global_step": 346192, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1224374771118164, "global_step": 346193, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0269272327423096, "global_step": 346194, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.048191785812378, "global_step": 346195, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.123096227645874, "global_step": 346196, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0515525341033936, "global_step": 346197, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1055996417999268, "global_step": 346198, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1158976554870605, "global_step": 346199, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1053593158721924, "global_step": 346200, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0187084674835205, "global_step": 346201, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0053701400756836, "global_step": 346202, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0930511951446533, "global_step": 346203, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1305150985717773, "global_step": 346204, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1447651386260986, "global_step": 346205, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0910987854003906, "global_step": 346206, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1017632484436035, "global_step": 346207, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1269121170043945, "global_step": 346208, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0721189975738525, "global_step": 346209, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1328775882720947, "global_step": 346210, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0404491424560547, "global_step": 346211, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1609768867492676, "global_step": 346212, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0116400718688965, "global_step": 346213, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.173945426940918, "global_step": 346214, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.091926336288452, "global_step": 346215, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.135192632675171, "global_step": 346216, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0676329135894775, "global_step": 346217, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1206650733947754, "global_step": 346218, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1199381351470947, "global_step": 346219, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.083402633666992, "global_step": 346220, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.144594192504883, "global_step": 346221, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.2116105556488037, "global_step": 346222, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.086721181869507, "global_step": 346223, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0939886569976807, "global_step": 346224, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0754575729370117, "global_step": 346225, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0537025928497314, "global_step": 346226, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1178457736968994, "global_step": 346227, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1367080211639404, "global_step": 346228, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0544593334198, "global_step": 346229, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0655760765075684, "global_step": 346230, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.070523262023926, "global_step": 346231, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.117518901824951, "global_step": 346232, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0810012817382812, "global_step": 346233, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.084705114364624, "global_step": 346234, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.107029914855957, "global_step": 346235, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1717631816864014, "global_step": 346236, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.039316177368164, "global_step": 346237, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1553845405578613, "global_step": 346238, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0586938858032227, "global_step": 346239, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0662224292755127, "global_step": 346240, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1342153549194336, "global_step": 346241, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0289409160614014, "global_step": 346242, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.207598924636841, "global_step": 346243, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1018731594085693, "global_step": 346244, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0783374309539795, "global_step": 346245, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1194632053375244, "global_step": 346246, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1458683013916016, "global_step": 346247, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0084662437438965, "global_step": 346248, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1284308433532715, "global_step": 346249, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0882835388183594, "global_step": 346250, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.101702928543091, "global_step": 346251, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1190080642700195, "global_step": 346252, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0930776596069336, "global_step": 346253, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1667842864990234, "global_step": 346254, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1766293048858643, "global_step": 346255, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.138791799545288, "global_step": 346256, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0625696182250977, "global_step": 346257, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.066547393798828, "global_step": 346258, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.116560459136963, "global_step": 346259, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0844950675964355, "global_step": 346260, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.10616397857666, "global_step": 346261, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.073230266571045, "global_step": 346262, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.129456043243408, "global_step": 346263, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0071914196014404, "global_step": 346264, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1155385971069336, "global_step": 346265, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1231918334960938, "global_step": 346266, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1164286136627197, "global_step": 346267, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0748627185821533, "global_step": 346268, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1464414596557617, "global_step": 346269, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.055532217025757, "global_step": 346270, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.156003713607788, "global_step": 346271, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.180849075317383, "global_step": 346272, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.064379930496216, "global_step": 346273, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.032346725463867, "global_step": 346274, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.070584535598755, "global_step": 346275, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1176958084106445, "global_step": 346276, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1668288707733154, "global_step": 346277, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0911409854888916, "global_step": 346278, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.091855049133301, "global_step": 346279, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.059677839279175, "global_step": 346280, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0273540019989014, "global_step": 346281, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1142635345458984, "global_step": 346282, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.104001045227051, "global_step": 346283, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.05326247215271, "global_step": 346284, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1434249877929688, "global_step": 346285, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.125929117202759, "global_step": 346286, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1419076919555664, "global_step": 346287, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1507129669189453, "global_step": 346288, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.039398193359375, "global_step": 346289, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.11004376411438, "global_step": 346290, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1345837116241455, "global_step": 346291, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1449124813079834, "global_step": 346292, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.101057529449463, "global_step": 346293, "epoch": 707, "lr": 5e-05}
{"train_loss": 1.9822230339050293, "global_step": 346294, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1040945053100586, "global_step": 346295, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.159306764602661, "global_step": 346296, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0589535236358643, "global_step": 346297, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1142265796661377, "global_step": 346298, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0967631340026855, "global_step": 346299, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.082681179046631, "global_step": 346300, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.108205795288086, "global_step": 346301, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.055389642715454, "global_step": 346302, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0578079223632812, "global_step": 346303, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1068997383117676, "global_step": 346304, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1198976039886475, "global_step": 346305, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.030845880508423, "global_step": 346306, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.007697820663452, "global_step": 346307, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1546804904937744, "global_step": 346308, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0723824501037598, "global_step": 346309, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1452226638793945, "global_step": 346310, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.041590452194214, "global_step": 346311, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.111880302429199, "global_step": 346312, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0832877159118652, "global_step": 346313, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.2013907432556152, "global_step": 346314, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1170129776000977, "global_step": 346315, "epoch": 707, "lr": 5e-05}
{"train_loss": 1.9741899967193604, "global_step": 346316, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0493197441101074, "global_step": 346317, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0330231189727783, "global_step": 346318, "epoch": 707, "lr": 5e-05}
{"train_loss": 1.9892901182174683, "global_step": 346319, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.101485252380371, "global_step": 346320, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.145815372467041, "global_step": 346321, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.122819185256958, "global_step": 346322, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.082826614379883, "global_step": 346323, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1778078079223633, "global_step": 346324, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.019144296646118, "global_step": 346325, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1129114627838135, "global_step": 346326, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.064162254333496, "global_step": 346327, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0279486179351807, "global_step": 346328, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.086196184158325, "global_step": 346329, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.086244583129883, "global_step": 346330, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1327192783355713, "global_step": 346331, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1046688556671143, "global_step": 346332, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.117661714553833, "global_step": 346333, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0468404293060303, "global_step": 346334, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.061753749847412, "global_step": 346335, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0685224533081055, "global_step": 346336, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.108919620513916, "global_step": 346337, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.040628671646118, "global_step": 346338, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.09946608543396, "global_step": 346339, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1635940074920654, "global_step": 346340, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1868855953216553, "global_step": 346341, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0719141960144043, "global_step": 346342, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.148113965988159, "global_step": 346343, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.103506088256836, "global_step": 346344, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.132850408554077, "global_step": 346345, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1010565757751465, "global_step": 346346, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1923389434814453, "global_step": 346347, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.052325487136841, "global_step": 346348, "epoch": 707, "lr": 5e-05}
{"train_loss": 1.9972407817840576, "global_step": 346349, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1609153747558594, "global_step": 346350, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1250905990600586, "global_step": 346351, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.124962091445923, "global_step": 346352, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.056894540786743, "global_step": 346353, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.015155792236328, "global_step": 346354, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.096850633621216, "global_step": 346355, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1586837768554688, "global_step": 346356, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1877353191375732, "global_step": 346357, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1085283756256104, "global_step": 346358, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1223533153533936, "global_step": 346359, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.015369415283203, "global_step": 346360, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.17628812789917, "global_step": 346361, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.2026283740997314, "global_step": 346362, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0614726543426514, "global_step": 346363, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.159050703048706, "global_step": 346364, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.070253610610962, "global_step": 346365, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.082080841064453, "global_step": 346366, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.150331497192383, "global_step": 346367, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.090945243835449, "global_step": 346368, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0896172523498535, "global_step": 346369, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.136758327484131, "global_step": 346370, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.066521406173706, "global_step": 346371, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1032001972198486, "global_step": 346372, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.2392311096191406, "global_step": 346373, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.126376152038574, "global_step": 346374, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1542670726776123, "global_step": 346375, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0728561878204346, "global_step": 346376, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0735597610473633, "global_step": 346377, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0934853553771973, "global_step": 346378, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.052687406539917, "global_step": 346379, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0508179664611816, "global_step": 346380, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0878100395202637, "global_step": 346381, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0598936080932617, "global_step": 346382, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0423455238342285, "global_step": 346383, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1794607639312744, "global_step": 346384, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.059873580932617, "global_step": 346385, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.153510570526123, "global_step": 346386, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.120028257369995, "global_step": 346387, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0786116123199463, "global_step": 346388, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1015408039093018, "global_step": 346389, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.108210563659668, "global_step": 346390, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1482465267181396, "global_step": 346391, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1522018909454346, "global_step": 346392, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.050607442855835, "global_step": 346393, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.094431161880493, "global_step": 346394, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1380224227905273, "global_step": 346395, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1317100524902344, "global_step": 346396, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1301863193511963, "global_step": 346397, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0636496543884277, "global_step": 346398, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.217632293701172, "global_step": 346399, "epoch": 707, "lr": 5e-05}
{"train_loss": 1.9870331287384033, "global_step": 346400, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1223456859588623, "global_step": 346401, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1481359004974365, "global_step": 346402, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.122725486755371, "global_step": 346403, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.101099729537964, "global_step": 346404, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.105433702468872, "global_step": 346405, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1350257396698, "global_step": 346406, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.081965208053589, "global_step": 346407, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.128765106201172, "global_step": 346408, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.07515025138855, "global_step": 346409, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.112238645553589, "global_step": 346410, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.076854705810547, "global_step": 346411, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0033912658691406, "global_step": 346412, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1450448036193848, "global_step": 346413, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.088634967803955, "global_step": 346414, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.104707717895508, "global_step": 346415, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.056809186935425, "global_step": 346416, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.172095775604248, "global_step": 346417, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.077223300933838, "global_step": 346418, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.089235305786133, "global_step": 346419, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0608296394348145, "global_step": 346420, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1371374130249023, "global_step": 346421, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0505330562591553, "global_step": 346422, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1307201385498047, "global_step": 346423, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0334157943725586, "global_step": 346424, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.201178550720215, "global_step": 346425, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1133525371551514, "global_step": 346426, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0708415508270264, "global_step": 346427, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.172003984451294, "global_step": 346428, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0502068996429443, "global_step": 346429, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1480295658111572, "global_step": 346430, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0891759395599365, "global_step": 346431, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.085172176361084, "global_step": 346432, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1536178588867188, "global_step": 346433, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.098804473876953, "global_step": 346434, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0933239459991455, "global_step": 346435, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.15767240524292, "global_step": 346436, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.076665163040161, "global_step": 346437, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.155853033065796, "global_step": 346438, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.116243362426758, "global_step": 346439, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0479583740234375, "global_step": 346440, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.094926357269287, "global_step": 346441, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.161914587020874, "global_step": 346442, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1512038707733154, "global_step": 346443, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.077129364013672, "global_step": 346444, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1214756965637207, "global_step": 346445, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1543755531311035, "global_step": 346446, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.127254009246826, "global_step": 346447, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1658859252929688, "global_step": 346448, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0795421600341797, "global_step": 346449, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0998666286468506, "global_step": 346450, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.113138437271118, "global_step": 346451, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.12117600440979, "global_step": 346452, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1167407035827637, "global_step": 346453, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.170302391052246, "global_step": 346454, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1644957065582275, "global_step": 346455, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.143486499786377, "global_step": 346456, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0866172313690186, "global_step": 346457, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1233749389648438, "global_step": 346458, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0680782794952393, "global_step": 346459, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0965723991394043, "global_step": 346460, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1922495365142822, "global_step": 346461, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0755043029785156, "global_step": 346462, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0545871257781982, "global_step": 346463, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1868324279785156, "global_step": 346464, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.126616954803467, "global_step": 346465, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.076040506362915, "global_step": 346466, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0592586994171143, "global_step": 346467, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.103882312774658, "global_step": 346468, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0575475692749023, "global_step": 346469, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1880924701690674, "global_step": 346470, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1353423595428467, "global_step": 346471, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.09093976020813, "global_step": 346472, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0362985134124756, "global_step": 346473, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.155906915664673, "global_step": 346474, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1573760509490967, "global_step": 346475, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1312594413757324, "global_step": 346476, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0741238594055176, "global_step": 346477, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0853145122528076, "global_step": 346478, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.181968927383423, "global_step": 346479, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1028635501861572, "global_step": 346480, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1783652305603027, "global_step": 346481, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.136807680130005, "global_step": 346482, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.115889310836792, "global_step": 346483, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.057487964630127, "global_step": 346484, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.13966703414917, "global_step": 346485, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.090214967727661, "global_step": 346486, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.122607707977295, "global_step": 346487, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.089048147201538, "global_step": 346488, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1349990367889404, "global_step": 346489, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0889291763305664, "global_step": 346490, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1264162063598633, "global_step": 346491, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0103538036346436, "global_step": 346492, "epoch": 707, "lr": 5e-05}
{"train_loss": 1.9993903636932373, "global_step": 346493, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1671969890594482, "global_step": 346494, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0614840984344482, "global_step": 346495, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.011472463607788, "global_step": 346496, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.121914863586426, "global_step": 346497, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0870583057403564, "global_step": 346498, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1679883003234863, "global_step": 346499, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.036144733428955, "global_step": 346500, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.131438970565796, "global_step": 346501, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0658891201019287, "global_step": 346502, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1322460174560547, "global_step": 346503, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0890896320343018, "global_step": 346504, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0984585285186768, "global_step": 346505, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.084531784057617, "global_step": 346506, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.108888864517212, "global_step": 346507, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0112087726593018, "global_step": 346508, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1349353790283203, "global_step": 346509, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1084201335906982, "global_step": 346510, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.043286085128784, "global_step": 346511, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0952653884887695, "global_step": 346512, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.129244804382324, "global_step": 346513, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0476648807525635, "global_step": 346514, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.103924036026001, "global_step": 346515, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0499095916748047, "global_step": 346516, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.157022714614868, "global_step": 346517, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1910133361816406, "global_step": 346518, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.15716552734375, "global_step": 346519, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0833146572113037, "global_step": 346520, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0702931880950928, "global_step": 346521, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1724891662597656, "global_step": 346522, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.080610513687134, "global_step": 346523, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0799155235290527, "global_step": 346524, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.106485605239868, "global_step": 346525, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0741350650787354, "global_step": 346526, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1961348056793213, "global_step": 346527, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.181927442550659, "global_step": 346528, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.081303119659424, "global_step": 346529, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.174692392349243, "global_step": 346530, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0738770961761475, "global_step": 346531, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.153454065322876, "global_step": 346532, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0357542037963867, "global_step": 346533, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.21508526802063, "global_step": 346534, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.156566858291626, "global_step": 346535, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.163302421569824, "global_step": 346536, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.137927532196045, "global_step": 346537, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.162597179412842, "global_step": 346538, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.177281618118286, "global_step": 346539, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0999860763549805, "global_step": 346540, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.123494863510132, "global_step": 346541, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.049168586730957, "global_step": 346542, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0708062648773193, "global_step": 346543, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1752610206604004, "global_step": 346544, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1689822673797607, "global_step": 346545, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1278510093688965, "global_step": 346546, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.194286823272705, "global_step": 346547, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1172313690185547, "global_step": 346548, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1070430278778076, "global_step": 346549, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.075083017349243, "global_step": 346550, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1106908321380615, "global_step": 346551, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.065324068069458, "global_step": 346552, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0956180095672607, "global_step": 346553, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.159123182296753, "global_step": 346554, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.017113208770752, "global_step": 346555, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1351513862609863, "global_step": 346556, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1033735275268555, "global_step": 346557, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0458145141601562, "global_step": 346558, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.127521514892578, "global_step": 346559, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1629035472869873, "global_step": 346560, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.092957019805908, "global_step": 346561, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0909810066223145, "global_step": 346562, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.031111240386963, "global_step": 346563, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0681393146514893, "global_step": 346564, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1802995204925537, "global_step": 346565, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.088101863861084, "global_step": 346566, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0572118759155273, "global_step": 346567, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0957353115081787, "global_step": 346568, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1029815673828125, "global_step": 346569, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1553618907928467, "global_step": 346570, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1599791049957275, "global_step": 346571, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1097567081451416, "global_step": 346572, "epoch": 707, "lr": 5e-05}
{"train_loss": 1.9551525115966797, "global_step": 346573, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1220614910125732, "global_step": 346574, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.106724262237549, "global_step": 346575, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0348899364471436, "global_step": 346576, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.108027219772339, "global_step": 346577, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.102426528930664, "global_step": 346578, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1295952796936035, "global_step": 346579, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0359745025634766, "global_step": 346580, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.149439811706543, "global_step": 346581, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1597583293914795, "global_step": 346582, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.10859751701355, "global_step": 346583, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.186122179031372, "global_step": 346584, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.094583511352539, "global_step": 346585, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0896477699279785, "global_step": 346586, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1212496757507324, "global_step": 346587, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0930252075195312, "global_step": 346588, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1119494438171387, "global_step": 346589, "epoch": 707, "lr": 5e-05}
{"train_loss": 1.9364792108535767, "global_step": 346590, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0991787910461426, "global_step": 346591, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1281309127807617, "global_step": 346592, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.092268943786621, "global_step": 346593, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1529314517974854, "global_step": 346594, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0338261127471924, "global_step": 346595, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.119847536087036, "global_step": 346596, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.131606340408325, "global_step": 346597, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.144988775253296, "global_step": 346598, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0776569843292236, "global_step": 346599, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1219875812530518, "global_step": 346600, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0817697048187256, "global_step": 346601, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.162374973297119, "global_step": 346602, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0571887493133545, "global_step": 346603, "epoch": 707, "lr": 5e-05}
{"train_loss": 1.9868628978729248, "global_step": 346604, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0879712104797363, "global_step": 346605, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1861765384674072, "global_step": 346606, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1805355548858643, "global_step": 346607, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1069037914276123, "global_step": 346608, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.142376184463501, "global_step": 346609, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0534942150115967, "global_step": 346610, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1032192707061768, "global_step": 346611, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.105494499206543, "global_step": 346612, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1640796661376953, "global_step": 346613, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0658183097839355, "global_step": 346614, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.075749635696411, "global_step": 346615, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0795483589172363, "global_step": 346616, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.063959836959839, "global_step": 346617, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0879006385803223, "global_step": 346618, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.200681209564209, "global_step": 346619, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.057328701019287, "global_step": 346620, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.092862844467163, "global_step": 346621, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.127420663833618, "global_step": 346622, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0347909927368164, "global_step": 346623, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1464524269104004, "global_step": 346624, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.114609479904175, "global_step": 346625, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1488521099090576, "global_step": 346626, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1480066776275635, "global_step": 346627, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.179647922515869, "global_step": 346628, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1188504695892334, "global_step": 346629, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.033083200454712, "global_step": 346630, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0630619525909424, "global_step": 346631, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.110112190246582, "global_step": 346632, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1205079555511475, "global_step": 346633, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.085825204849243, "global_step": 346634, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1856839656829834, "global_step": 346635, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0564401149749756, "global_step": 346636, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0475432872772217, "global_step": 346637, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1119384765625, "global_step": 346638, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.10494327545166, "global_step": 346639, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0905847549438477, "global_step": 346640, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.225160837173462, "global_step": 346641, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.166828155517578, "global_step": 346642, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.034393787384033, "global_step": 346643, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.109959602355957, "global_step": 346644, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1057627201080322, "global_step": 346645, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1666147708892822, "global_step": 346646, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0479273796081543, "global_step": 346647, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1102750301361084, "global_step": 346648, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1061413288116455, "global_step": 346649, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0976834297180176, "global_step": 346650, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0495128631591797, "global_step": 346651, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0148348808288574, "global_step": 346652, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1956729888916016, "global_step": 346653, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.066225528717041, "global_step": 346654, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.100754499435425, "global_step": 346655, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1515655517578125, "global_step": 346656, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0914008617401123, "global_step": 346657, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1190052032470703, "global_step": 346658, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.2068095207214355, "global_step": 346659, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.127429246902466, "global_step": 346660, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1338398456573486, "global_step": 346661, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.150646448135376, "global_step": 346662, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.148837089538574, "global_step": 346663, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.150150775909424, "global_step": 346664, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1297199726104736, "global_step": 346665, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.146275520324707, "global_step": 346666, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0719568729400635, "global_step": 346667, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1697380542755127, "global_step": 346668, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.080324649810791, "global_step": 346669, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1439990997314453, "global_step": 346670, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.149836540222168, "global_step": 346671, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.02964448928833, "global_step": 346672, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1085596084594727, "global_step": 346673, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1493935585021973, "global_step": 346674, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1498806476593018, "global_step": 346675, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0387303829193115, "global_step": 346676, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1632535457611084, "global_step": 346677, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1159939765930176, "global_step": 346678, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0684313774108887, "global_step": 346679, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0075442790985107, "global_step": 346680, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.235727310180664, "global_step": 346681, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.073401927947998, "global_step": 346682, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1301541328430176, "global_step": 346683, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.13741397857666, "global_step": 346684, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0767951011657715, "global_step": 346685, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1385698318481445, "global_step": 346686, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0742790699005127, "global_step": 346687, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1168816089630127, "global_step": 346688, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.114217758178711, "global_step": 346689, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.099403142929077, "global_step": 346690, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.09462308883667, "global_step": 346691, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.068476438522339, "global_step": 346692, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1256072521209717, "global_step": 346693, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.065199136734009, "global_step": 346694, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.122185707092285, "global_step": 346695, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0976364612579346, "global_step": 346696, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1306815147399902, "global_step": 346697, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1892340183258057, "global_step": 346698, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.085009813308716, "global_step": 346699, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.096445083618164, "global_step": 346700, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0474181175231934, "global_step": 346701, "epoch": 707, "lr": 5e-05}
{"train_loss": 1.9749442338943481, "global_step": 346702, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.064302921295166, "global_step": 346703, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0818943977355957, "global_step": 346704, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1668856143951416, "global_step": 346705, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.184223175048828, "global_step": 346706, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1759555339813232, "global_step": 346707, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0556952953338623, "global_step": 346708, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1256487369537354, "global_step": 346709, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.106506586074829, "global_step": 346710, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.051018476486206, "global_step": 346711, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1258294582366943, "global_step": 346712, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1909303665161133, "global_step": 346713, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.080420732498169, "global_step": 346714, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0872747898101807, "global_step": 346715, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0684006214141846, "global_step": 346716, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.114190101623535, "global_step": 346717, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.152087450027466, "global_step": 346718, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0968360900878906, "global_step": 346719, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.21085524559021, "global_step": 346720, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.143691062927246, "global_step": 346721, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1178183555603027, "global_step": 346722, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.046428680419922, "global_step": 346723, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1582283973693848, "global_step": 346724, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0635323524475098, "global_step": 346725, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0996291637420654, "global_step": 346726, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.024716377258301, "global_step": 346727, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.118624687194824, "global_step": 346728, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.04632568359375, "global_step": 346729, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1497509479522705, "global_step": 346730, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.180687665939331, "global_step": 346731, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.053699254989624, "global_step": 346732, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.069366455078125, "global_step": 346733, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1131391525268555, "global_step": 346734, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0913608074188232, "global_step": 346735, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1052258014678955, "global_step": 346736, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1128273010253906, "global_step": 346737, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1834208965301514, "global_step": 346738, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1127336025238037, "global_step": 346739, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.024218797683716, "global_step": 346740, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.108776807785034, "global_step": 346741, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1632192134857178, "global_step": 346742, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1793246269226074, "global_step": 346743, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.183547258377075, "global_step": 346744, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.082726001739502, "global_step": 346745, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.102900981903076, "global_step": 346746, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1657793521881104, "global_step": 346747, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1538844108581543, "global_step": 346748, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.054241895675659, "global_step": 346749, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1901211738586426, "global_step": 346750, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0507454872131348, "global_step": 346751, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.169084072113037, "global_step": 346752, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1484322547912598, "global_step": 346753, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.117779493331909, "global_step": 346754, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1312406063079834, "global_step": 346755, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.074220657348633, "global_step": 346756, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1487038135528564, "global_step": 346757, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.068413496017456, "global_step": 346758, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.122610569000244, "global_step": 346759, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.136617660522461, "global_step": 346760, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1037838459014893, "global_step": 346761, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.105314016342163, "global_step": 346762, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1327385902404785, "global_step": 346763, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.124188184738159, "global_step": 346764, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1458933353424072, "global_step": 346765, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.173266887664795, "global_step": 346766, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1737849712371826, "global_step": 346767, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0892560482025146, "global_step": 346768, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0307776927948, "global_step": 346769, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1343343257904053, "global_step": 346770, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.044128894805908, "global_step": 346771, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.137007713317871, "global_step": 346772, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1611971855163574, "global_step": 346773, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.122530698776245, "global_step": 346774, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0710573196411133, "global_step": 346775, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.101358413696289, "global_step": 346776, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1149375438690186, "global_step": 346777, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.118224620819092, "global_step": 346778, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0682358741760254, "global_step": 346779, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1462039947509766, "global_step": 346780, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.106520652770996, "global_step": 346781, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1377644538879395, "global_step": 346782, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1105899810791016, "global_step": 346783, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.122551441192627, "global_step": 346784, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0816807746887207, "global_step": 346785, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.177377462387085, "global_step": 346786, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0798730850219727, "global_step": 346787, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.076972484588623, "global_step": 346788, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1454899311065674, "global_step": 346789, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0822196006774902, "global_step": 346790, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.046086549758911, "global_step": 346791, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1089107990264893, "global_step": 346792, "epoch": 707, "lr": 5e-05}
{"train_loss": 1.984843134880066, "global_step": 346793, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.107187509536743, "global_step": 346794, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.094651699066162, "global_step": 346795, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.11523699760437, "global_step": 346796, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.134054183959961, "global_step": 346797, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0963785648345947, "global_step": 346798, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0485527515411377, "global_step": 346799, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1061668395996094, "global_step": 346800, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1186370849609375, "global_step": 346801, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.122248649597168, "global_step": 346802, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1862878799438477, "global_step": 346803, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.137608528137207, "global_step": 346804, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1553006172180176, "global_step": 346805, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1065754890441895, "global_step": 346806, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.2749485969543457, "global_step": 346807, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1281561851501465, "global_step": 346808, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.15059232711792, "global_step": 346809, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1364283561706543, "global_step": 346810, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.097977638244629, "global_step": 346811, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0751655101776123, "global_step": 346812, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1053779125213623, "global_step": 346813, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.149827003479004, "global_step": 346814, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1232030391693115, "global_step": 346815, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1691417694091797, "global_step": 346816, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0722246170043945, "global_step": 346817, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.2243616580963135, "global_step": 346818, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.2002756595611572, "global_step": 346819, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.164515733718872, "global_step": 346820, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.145263433456421, "global_step": 346821, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.065068244934082, "global_step": 346822, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.059868574142456, "global_step": 346823, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0977096557617188, "global_step": 346824, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.092108726501465, "global_step": 346825, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0987548828125, "global_step": 346826, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.226573944091797, "global_step": 346827, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1658577919006348, "global_step": 346828, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0378220081329346, "global_step": 346829, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0670807361602783, "global_step": 346830, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1711299419403076, "global_step": 346831, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.101041078567505, "global_step": 346832, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1271538734436035, "global_step": 346833, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1364355087280273, "global_step": 346834, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0482990741729736, "global_step": 346835, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0392744541168213, "global_step": 346836, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1930882930755615, "global_step": 346837, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1354618072509766, "global_step": 346838, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0919642448425293, "global_step": 346839, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.162655830383301, "global_step": 346840, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.177051067352295, "global_step": 346841, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.049483060836792, "global_step": 346842, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0484187602996826, "global_step": 346843, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0892930030822754, "global_step": 346844, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0823135375976562, "global_step": 346845, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1416783332824707, "global_step": 346846, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0575623512268066, "global_step": 346847, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.15762996673584, "global_step": 346848, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1089982986450195, "global_step": 346849, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0416259765625, "global_step": 346850, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0746424198150635, "global_step": 346851, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.154330253601074, "global_step": 346852, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0683019161224365, "global_step": 346853, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.074779510498047, "global_step": 346854, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.052872896194458, "global_step": 346855, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.147351026535034, "global_step": 346856, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.2264018058776855, "global_step": 346857, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0888707637786865, "global_step": 346858, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.104343891143799, "global_step": 346859, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1747360229492188, "global_step": 346860, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.103241205215454, "global_step": 346861, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.049997329711914, "global_step": 346862, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.059483289718628, "global_step": 346863, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.091230869293213, "global_step": 346864, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.222824811935425, "global_step": 346865, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.086869478225708, "global_step": 346866, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.08925724029541, "global_step": 346867, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.016026258468628, "global_step": 346868, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0374021530151367, "global_step": 346869, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1090757846832275, "global_step": 346870, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1717188358306885, "global_step": 346871, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.177464723587036, "global_step": 346872, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1306965351104736, "global_step": 346873, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1693801879882812, "global_step": 346874, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.115082263946533, "global_step": 346875, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0367116928100586, "global_step": 346876, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1382172107696533, "global_step": 346877, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0922634601593018, "global_step": 346878, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.115450620651245, "global_step": 346879, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0638232231140137, "global_step": 346880, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0788307189941406, "global_step": 346881, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0681302547454834, "global_step": 346882, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.052016258239746, "global_step": 346883, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.005596399307251, "global_step": 346884, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.084709882736206, "global_step": 346885, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1410794258117676, "global_step": 346886, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0643293857574463, "global_step": 346887, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1921722888946533, "global_step": 346888, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1244561672210693, "global_step": 346889, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1043739318847656, "global_step": 346890, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1452505588531494, "global_step": 346891, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.098494529724121, "global_step": 346892, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1030232906341553, "global_step": 346893, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.018686532974243, "global_step": 346894, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1183717250823975, "global_step": 346895, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.139158010482788, "global_step": 346896, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.2419869899749756, "global_step": 346897, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0420913696289062, "global_step": 346898, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1055009365081787, "global_step": 346899, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.104841709136963, "global_step": 346900, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.153218984603882, "global_step": 346901, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1029231548309326, "global_step": 346902, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0978801250457764, "global_step": 346903, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1415722370147705, "global_step": 346904, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1178836822509766, "global_step": 346905, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.051515817642212, "global_step": 346906, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1664464473724365, "global_step": 346907, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.194829225540161, "global_step": 346908, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1453006267547607, "global_step": 346909, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0843353271484375, "global_step": 346910, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0300512313842773, "global_step": 346911, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1197850704193115, "global_step": 346912, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1584532260894775, "global_step": 346913, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1024653911590576, "global_step": 346914, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1263210773468018, "global_step": 346915, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0879011154174805, "global_step": 346916, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0897819995880127, "global_step": 346917, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.105774402618408, "global_step": 346918, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.073338747024536, "global_step": 346919, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.118060350418091, "global_step": 346920, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1507086753845215, "global_step": 346921, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1047523021698, "global_step": 346922, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.151303768157959, "global_step": 346923, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.042621374130249, "global_step": 346924, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.160215377807617, "global_step": 346925, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0884149074554443, "global_step": 346926, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.246201753616333, "global_step": 346927, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.109281063079834, "global_step": 346928, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.125009059906006, "global_step": 346929, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.134024143218994, "global_step": 346930, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0915887355804443, "global_step": 346931, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.093667507171631, "global_step": 346932, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1492514610290527, "global_step": 346933, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0651097297668457, "global_step": 346934, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1592676639556885, "global_step": 346935, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.21682071685791, "global_step": 346936, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.072206497192383, "global_step": 346937, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.02376651763916, "global_step": 346938, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1183393001556396, "global_step": 346939, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.089836835861206, "global_step": 346940, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1948635578155518, "global_step": 346941, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0521185398101807, "global_step": 346942, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0378780364990234, "global_step": 346943, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0884952545166016, "global_step": 346944, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.100043773651123, "global_step": 346945, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.107935905456543, "global_step": 346946, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.104874849319458, "global_step": 346947, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1591005325317383, "global_step": 346948, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.031548023223877, "global_step": 346949, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1545071601867676, "global_step": 346950, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1708872318267822, "global_step": 346951, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0963144302368164, "global_step": 346952, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0999956130981445, "global_step": 346953, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.143855333328247, "global_step": 346954, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0884270668029785, "global_step": 346955, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0975961685180664, "global_step": 346956, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1758861541748047, "global_step": 346957, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.169168472290039, "global_step": 346958, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.105978012084961, "global_step": 346959, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.069662570953369, "global_step": 346960, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1589596271514893, "global_step": 346961, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.05983304977417, "global_step": 346962, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0926387310028076, "global_step": 346963, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1436641216278076, "global_step": 346964, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0519886016845703, "global_step": 346965, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0194051265716553, "global_step": 346966, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.085268497467041, "global_step": 346967, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1155834197998047, "global_step": 346968, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.045119285583496, "global_step": 346969, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.128882884979248, "global_step": 346970, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0970284938812256, "global_step": 346971, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.065713405609131, "global_step": 346972, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.082699775695801, "global_step": 346973, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1389434337615967, "global_step": 346974, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.180079936981201, "global_step": 346975, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.073319911956787, "global_step": 346976, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0799267292022705, "global_step": 346977, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0847465991973877, "global_step": 346978, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0685524940490723, "global_step": 346979, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0788254737854004, "global_step": 346980, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.180758476257324, "global_step": 346981, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.132213830947876, "global_step": 346982, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0554490089416504, "global_step": 346983, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1636526584625244, "global_step": 346984, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1408934593200684, "global_step": 346985, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0808582305908203, "global_step": 346986, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1592535972595215, "global_step": 346987, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0997908115386963, "global_step": 346988, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.122535228729248, "global_step": 346989, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1237661838531494, "global_step": 346990, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0965259075164795, "global_step": 346991, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0573198795318604, "global_step": 346992, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1134395599365234, "global_step": 346993, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.200221538543701, "global_step": 346994, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.10146427154541, "global_step": 346995, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.148841381072998, "global_step": 346996, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1989848613739014, "global_step": 346997, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.15522837638855, "global_step": 346998, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1788666248321533, "global_step": 346999, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0983147621154785, "global_step": 347000, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1351730823516846, "global_step": 347001, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.078522205352783, "global_step": 347002, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1964304447174072, "global_step": 347003, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1547117233276367, "global_step": 347004, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.079550266265869, "global_step": 347005, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1612775325775146, "global_step": 347006, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.171306848526001, "global_step": 347007, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1168129444122314, "global_step": 347008, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.142216682434082, "global_step": 347009, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.197903633117676, "global_step": 347010, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.16677188873291, "global_step": 347011, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1723382472991943, "global_step": 347012, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1468262672424316, "global_step": 347013, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0504753589630127, "global_step": 347014, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0991482734680176, "global_step": 347015, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.112177610397339, "global_step": 347016, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.155632495880127, "global_step": 347017, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1297683715820312, "global_step": 347018, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.2063117027282715, "global_step": 347019, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.11141037940979, "global_step": 347020, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.087829113006592, "global_step": 347021, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0589065551757812, "global_step": 347022, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.083281993865967, "global_step": 347023, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1257338523864746, "global_step": 347024, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0254056453704834, "global_step": 347025, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.137251138687134, "global_step": 347026, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.107088804244995, "global_step": 347027, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.059671401977539, "global_step": 347028, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.2109498977661133, "global_step": 347029, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.106346607208252, "global_step": 347030, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0530734062194824, "global_step": 347031, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.086247444152832, "global_step": 347032, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.0496315956115723, "global_step": 347033, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.1064207553863525, "global_step": 347034, "epoch": 707, "lr": 5e-05}
{"train_loss": 2.150883197784424, "global_step": 347035, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.157113552093506, "global_step": 347036, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.133237361907959, "global_step": 347037, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.127718925476074, "global_step": 347038, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0740320682525635, "global_step": 347039, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0221755504608154, "global_step": 347040, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0260801315307617, "global_step": 347041, "epoch": 708, "lr": 5e-05}
{"train_loss": 1.9951260089874268, "global_step": 347042, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1041603088378906, "global_step": 347043, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0701563358306885, "global_step": 347044, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1872293949127197, "global_step": 347045, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.149613380432129, "global_step": 347046, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1739399433135986, "global_step": 347047, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1444814205169678, "global_step": 347048, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0996580123901367, "global_step": 347049, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0555858612060547, "global_step": 347050, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1388700008392334, "global_step": 347051, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0203239917755127, "global_step": 347052, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1096019744873047, "global_step": 347053, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1199629306793213, "global_step": 347054, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0322072505950928, "global_step": 347055, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1113381385803223, "global_step": 347056, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.082440137863159, "global_step": 347057, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.060465097427368, "global_step": 347058, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0698392391204834, "global_step": 347059, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2568836212158203, "global_step": 347060, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1236138343811035, "global_step": 347061, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.118886709213257, "global_step": 347062, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.098991632461548, "global_step": 347063, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1149556636810303, "global_step": 347064, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0853896141052246, "global_step": 347065, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.176460027694702, "global_step": 347066, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1691482067108154, "global_step": 347067, "epoch": 708, "lr": 5e-05}
{"train_loss": 1.99181067943573, "global_step": 347068, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0784876346588135, "global_step": 347069, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.080909490585327, "global_step": 347070, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0433197021484375, "global_step": 347071, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.022944211959839, "global_step": 347072, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1353039741516113, "global_step": 347073, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0503406524658203, "global_step": 347074, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0742528438568115, "global_step": 347075, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1197710037231445, "global_step": 347076, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1437129974365234, "global_step": 347077, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.123959541320801, "global_step": 347078, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0365853309631348, "global_step": 347079, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.086085557937622, "global_step": 347080, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0595450401306152, "global_step": 347081, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1129770278930664, "global_step": 347082, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.07824969291687, "global_step": 347083, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.114865303039551, "global_step": 347084, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.043353796005249, "global_step": 347085, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0552432537078857, "global_step": 347086, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1532886028289795, "global_step": 347087, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.130436658859253, "global_step": 347088, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0974175930023193, "global_step": 347089, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1172025203704834, "global_step": 347090, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0967843532562256, "global_step": 347091, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.055147647857666, "global_step": 347092, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.113858938217163, "global_step": 347093, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0612952709198, "global_step": 347094, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.074399948120117, "global_step": 347095, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.171664237976074, "global_step": 347096, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0342893600463867, "global_step": 347097, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1498875617980957, "global_step": 347098, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0525410175323486, "global_step": 347099, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1027097702026367, "global_step": 347100, "epoch": 708, "lr": 5e-05}
{"train_loss": 1.965146780014038, "global_step": 347101, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.172816276550293, "global_step": 347102, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.116370439529419, "global_step": 347103, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0496068000793457, "global_step": 347104, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.05936336517334, "global_step": 347105, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.168912410736084, "global_step": 347106, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1759836673736572, "global_step": 347107, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0525505542755127, "global_step": 347108, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0365052223205566, "global_step": 347109, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0791494846343994, "global_step": 347110, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0991132259368896, "global_step": 347111, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.122797966003418, "global_step": 347112, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0884861946105957, "global_step": 347113, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1623809337615967, "global_step": 347114, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.09254789352417, "global_step": 347115, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.051530361175537, "global_step": 347116, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0396924018859863, "global_step": 347117, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.108699321746826, "global_step": 347118, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.104184150695801, "global_step": 347119, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.072558641433716, "global_step": 347120, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0530755519866943, "global_step": 347121, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0982327461242676, "global_step": 347122, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.030123472213745, "global_step": 347123, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.071660280227661, "global_step": 347124, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1219680309295654, "global_step": 347125, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.165999412536621, "global_step": 347126, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.071730852127075, "global_step": 347127, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0921316146850586, "global_step": 347128, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0991876125335693, "global_step": 347129, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.146038055419922, "global_step": 347130, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0935637950897217, "global_step": 347131, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0569262504577637, "global_step": 347132, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.150251626968384, "global_step": 347133, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.074528694152832, "global_step": 347134, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.053086280822754, "global_step": 347135, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1040139198303223, "global_step": 347136, "epoch": 708, "lr": 5e-05}
{"train_loss": 1.9883008003234863, "global_step": 347137, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.07006573677063, "global_step": 347138, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.092691421508789, "global_step": 347139, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.075791835784912, "global_step": 347140, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1111223697662354, "global_step": 347141, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.065009593963623, "global_step": 347142, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.214470863342285, "global_step": 347143, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1142711639404297, "global_step": 347144, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0915536880493164, "global_step": 347145, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.046614646911621, "global_step": 347146, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0383493900299072, "global_step": 347147, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0976884365081787, "global_step": 347148, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.072657585144043, "global_step": 347149, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.060302972793579, "global_step": 347150, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.094238042831421, "global_step": 347151, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.209521532058716, "global_step": 347152, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1637377738952637, "global_step": 347153, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1279914379119873, "global_step": 347154, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1562511920928955, "global_step": 347155, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1303491592407227, "global_step": 347156, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1273531913757324, "global_step": 347157, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1632308959960938, "global_step": 347158, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.059969425201416, "global_step": 347159, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.137380599975586, "global_step": 347160, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1857919692993164, "global_step": 347161, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0366640090942383, "global_step": 347162, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1385269165039062, "global_step": 347163, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1207146644592285, "global_step": 347164, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1281564235687256, "global_step": 347165, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.192154884338379, "global_step": 347166, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.089073657989502, "global_step": 347167, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1222448348999023, "global_step": 347168, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.178457260131836, "global_step": 347169, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2332611083984375, "global_step": 347170, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.149897336959839, "global_step": 347171, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.073301315307617, "global_step": 347172, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1559321880340576, "global_step": 347173, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.116671085357666, "global_step": 347174, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.093594551086426, "global_step": 347175, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1306662559509277, "global_step": 347176, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1183459758758545, "global_step": 347177, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.114622116088867, "global_step": 347178, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.051734685897827, "global_step": 347179, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.076765775680542, "global_step": 347180, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1134986877441406, "global_step": 347181, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.170609712600708, "global_step": 347182, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.099701404571533, "global_step": 347183, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0369768142700195, "global_step": 347184, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.209523916244507, "global_step": 347185, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2080929279327393, "global_step": 347186, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.072448968887329, "global_step": 347187, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0867316722869873, "global_step": 347188, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.160585403442383, "global_step": 347189, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.12481689453125, "global_step": 347190, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1721551418304443, "global_step": 347191, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1018247604370117, "global_step": 347192, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1502788066864014, "global_step": 347193, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0925543308258057, "global_step": 347194, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.058110475540161, "global_step": 347195, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0871243476867676, "global_step": 347196, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1419527530670166, "global_step": 347197, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1460793018341064, "global_step": 347198, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.145185947418213, "global_step": 347199, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.045684814453125, "global_step": 347200, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2355661392211914, "global_step": 347201, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0678372383117676, "global_step": 347202, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0924031734466553, "global_step": 347203, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0605976581573486, "global_step": 347204, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0991458892822266, "global_step": 347205, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.195770263671875, "global_step": 347206, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1914191246032715, "global_step": 347207, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0289530754089355, "global_step": 347208, "epoch": 708, "lr": 5e-05}
{"train_loss": 1.9861109256744385, "global_step": 347209, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.078427791595459, "global_step": 347210, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0902626514434814, "global_step": 347211, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1105847358703613, "global_step": 347212, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1889569759368896, "global_step": 347213, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1443729400634766, "global_step": 347214, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.072627067565918, "global_step": 347215, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1611647605895996, "global_step": 347216, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.173494338989258, "global_step": 347217, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0886285305023193, "global_step": 347218, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1366124153137207, "global_step": 347219, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.051245927810669, "global_step": 347220, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0255019664764404, "global_step": 347221, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1298165321350098, "global_step": 347222, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0725669860839844, "global_step": 347223, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1153571605682373, "global_step": 347224, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.109733819961548, "global_step": 347225, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0989086627960205, "global_step": 347226, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2053606510162354, "global_step": 347227, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.190004587173462, "global_step": 347228, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1365065574645996, "global_step": 347229, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.13626766204834, "global_step": 347230, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.067540407180786, "global_step": 347231, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.100370168685913, "global_step": 347232, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.061401844024658, "global_step": 347233, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1034834384918213, "global_step": 347234, "epoch": 708, "lr": 5e-05}
{"train_loss": 1.9690600633621216, "global_step": 347235, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0597054958343506, "global_step": 347236, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.090711832046509, "global_step": 347237, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0993731021881104, "global_step": 347238, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0860776901245117, "global_step": 347239, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.091641902923584, "global_step": 347240, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.125082015991211, "global_step": 347241, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.102454423904419, "global_step": 347242, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.115325927734375, "global_step": 347243, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.137122392654419, "global_step": 347244, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.109846353530884, "global_step": 347245, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.097245216369629, "global_step": 347246, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.085649013519287, "global_step": 347247, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1330766677856445, "global_step": 347248, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.197465658187866, "global_step": 347249, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0268211364746094, "global_step": 347250, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0874545574188232, "global_step": 347251, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1199183464050293, "global_step": 347252, "epoch": 708, "lr": 5e-05}
{"train_loss": 1.9992446899414062, "global_step": 347253, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1288352012634277, "global_step": 347254, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.082766056060791, "global_step": 347255, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1832945346832275, "global_step": 347256, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0480284690856934, "global_step": 347257, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1471428871154785, "global_step": 347258, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.080874443054199, "global_step": 347259, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.111522912979126, "global_step": 347260, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1679654121398926, "global_step": 347261, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1052894592285156, "global_step": 347262, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1404638290405273, "global_step": 347263, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.131749153137207, "global_step": 347264, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1066384315490723, "global_step": 347265, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.129634141921997, "global_step": 347266, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1160764694213867, "global_step": 347267, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1244311332702637, "global_step": 347268, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.087972402572632, "global_step": 347269, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1385552883148193, "global_step": 347270, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0162880420684814, "global_step": 347271, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1302924156188965, "global_step": 347272, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.065415620803833, "global_step": 347273, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0977084636688232, "global_step": 347274, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1449382305145264, "global_step": 347275, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.190769672393799, "global_step": 347276, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.079641103744507, "global_step": 347277, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0910770893096924, "global_step": 347278, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.148479700088501, "global_step": 347279, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0210771560668945, "global_step": 347280, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.087998628616333, "global_step": 347281, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1413137912750244, "global_step": 347282, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0927419662475586, "global_step": 347283, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1699047088623047, "global_step": 347284, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1336405277252197, "global_step": 347285, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1402931213378906, "global_step": 347286, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1492438316345215, "global_step": 347287, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0686867237091064, "global_step": 347288, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.247523307800293, "global_step": 347289, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.145031690597534, "global_step": 347290, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1349563598632812, "global_step": 347291, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0389411449432373, "global_step": 347292, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0302093029022217, "global_step": 347293, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1245527267456055, "global_step": 347294, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.076624870300293, "global_step": 347295, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.150069236755371, "global_step": 347296, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0617527961730957, "global_step": 347297, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.078721523284912, "global_step": 347298, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.108833074569702, "global_step": 347299, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0696702003479004, "global_step": 347300, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1468822956085205, "global_step": 347301, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.165889263153076, "global_step": 347302, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.176936388015747, "global_step": 347303, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1531853675842285, "global_step": 347304, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.085632562637329, "global_step": 347305, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.136833906173706, "global_step": 347306, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1541593074798584, "global_step": 347307, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1406188011169434, "global_step": 347308, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1013410091400146, "global_step": 347309, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.137664318084717, "global_step": 347310, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1382622718811035, "global_step": 347311, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0705018043518066, "global_step": 347312, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0086865425109863, "global_step": 347313, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.055507183074951, "global_step": 347314, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.05330491065979, "global_step": 347315, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0759432315826416, "global_step": 347316, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.13134765625, "global_step": 347317, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0734310150146484, "global_step": 347318, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0288712978363037, "global_step": 347319, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.062687635421753, "global_step": 347320, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0824456214904785, "global_step": 347321, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0733234882354736, "global_step": 347322, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0936758518218994, "global_step": 347323, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0653560161590576, "global_step": 347324, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.189723253250122, "global_step": 347325, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1236276626586914, "global_step": 347326, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.101623773574829, "global_step": 347327, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0120701789855957, "global_step": 347328, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0498738288879395, "global_step": 347329, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.138066053390503, "global_step": 347330, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0952818393707275, "global_step": 347331, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0323925018310547, "global_step": 347332, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0380375385284424, "global_step": 347333, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.119600772857666, "global_step": 347334, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.123410940170288, "global_step": 347335, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2071032524108887, "global_step": 347336, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0989270210266113, "global_step": 347337, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1474993228912354, "global_step": 347338, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0603997707366943, "global_step": 347339, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1006650924682617, "global_step": 347340, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1527907848358154, "global_step": 347341, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.077594757080078, "global_step": 347342, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1260275840759277, "global_step": 347343, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.195152759552002, "global_step": 347344, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.027541160583496, "global_step": 347345, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1527633666992188, "global_step": 347346, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.107794761657715, "global_step": 347347, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.099437952041626, "global_step": 347348, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0141713619232178, "global_step": 347349, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0331733226776123, "global_step": 347350, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.120842218399048, "global_step": 347351, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0502209663391113, "global_step": 347352, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0654683113098145, "global_step": 347353, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.114776372909546, "global_step": 347354, "epoch": 708, "lr": 5e-05}
{"train_loss": 1.9818490743637085, "global_step": 347355, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1219537258148193, "global_step": 347356, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.126685857772827, "global_step": 347357, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.031409740447998, "global_step": 347358, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1030752658843994, "global_step": 347359, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0880062580108643, "global_step": 347360, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1358835697174072, "global_step": 347361, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.081516981124878, "global_step": 347362, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1052651405334473, "global_step": 347363, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0305492877960205, "global_step": 347364, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.160576820373535, "global_step": 347365, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.115373373031616, "global_step": 347366, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0227625370025635, "global_step": 347367, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0984714031219482, "global_step": 347368, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2223100662231445, "global_step": 347369, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1197307109832764, "global_step": 347370, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1423771381378174, "global_step": 347371, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0921919345855713, "global_step": 347372, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.051602840423584, "global_step": 347373, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.156160831451416, "global_step": 347374, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1127963066101074, "global_step": 347375, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.127943992614746, "global_step": 347376, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0776233673095703, "global_step": 347377, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.045370101928711, "global_step": 347378, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.055887222290039, "global_step": 347379, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.135526180267334, "global_step": 347380, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.084888458251953, "global_step": 347381, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.167529582977295, "global_step": 347382, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.036180257797241, "global_step": 347383, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0367350578308105, "global_step": 347384, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.155355930328369, "global_step": 347385, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.140429973602295, "global_step": 347386, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1043546199798584, "global_step": 347387, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0490102767944336, "global_step": 347388, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1017253398895264, "global_step": 347389, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.079627275466919, "global_step": 347390, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.059797763824463, "global_step": 347391, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1326069831848145, "global_step": 347392, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.058469772338867, "global_step": 347393, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.157003164291382, "global_step": 347394, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.050370216369629, "global_step": 347395, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0933454036712646, "global_step": 347396, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.062849283218384, "global_step": 347397, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0657148361206055, "global_step": 347398, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0749220848083496, "global_step": 347399, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.152384042739868, "global_step": 347400, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.094683885574341, "global_step": 347401, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.242368221282959, "global_step": 347402, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.193859577178955, "global_step": 347403, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1061532497406006, "global_step": 347404, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.049398183822632, "global_step": 347405, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1602346897125244, "global_step": 347406, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1630868911743164, "global_step": 347407, "epoch": 708, "lr": 5e-05}
{"train_loss": 1.9927617311477661, "global_step": 347408, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.050074577331543, "global_step": 347409, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.062376022338867, "global_step": 347410, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.000817060470581, "global_step": 347411, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.155867099761963, "global_step": 347412, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1547963619232178, "global_step": 347413, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.150444269180298, "global_step": 347414, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.226243734359741, "global_step": 347415, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1137194633483887, "global_step": 347416, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.062307596206665, "global_step": 347417, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.132916212081909, "global_step": 347418, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2034173011779785, "global_step": 347419, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1970510482788086, "global_step": 347420, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.164714813232422, "global_step": 347421, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1343579292297363, "global_step": 347422, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0680787563323975, "global_step": 347423, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.079132318496704, "global_step": 347424, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.086050271987915, "global_step": 347425, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.054572105407715, "global_step": 347426, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0318455696105957, "global_step": 347427, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.138584852218628, "global_step": 347428, "epoch": 708, "lr": 5e-05}
{"train_loss": 1.9835433959960938, "global_step": 347429, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1784067153930664, "global_step": 347430, "epoch": 708, "lr": 5e-05}
{"train_loss": 1.993640422821045, "global_step": 347431, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1140871047973633, "global_step": 347432, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.109562873840332, "global_step": 347433, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1527371406555176, "global_step": 347434, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.118001937866211, "global_step": 347435, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.153865337371826, "global_step": 347436, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0530385971069336, "global_step": 347437, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1615965366363525, "global_step": 347438, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.092069625854492, "global_step": 347439, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.104752779006958, "global_step": 347440, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1692707538604736, "global_step": 347441, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.067476272583008, "global_step": 347442, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0534050464630127, "global_step": 347443, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.110839366912842, "global_step": 347444, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.171354293823242, "global_step": 347445, "epoch": 708, "lr": 5e-05}
{"train_loss": 1.984916090965271, "global_step": 347446, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.061345100402832, "global_step": 347447, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1327877044677734, "global_step": 347448, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.158853769302368, "global_step": 347449, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0589966773986816, "global_step": 347450, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0141990184783936, "global_step": 347451, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.050013542175293, "global_step": 347452, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1676528453826904, "global_step": 347453, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1060574054718018, "global_step": 347454, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0480916500091553, "global_step": 347455, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1719870567321777, "global_step": 347456, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.184377908706665, "global_step": 347457, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1528306007385254, "global_step": 347458, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0888795852661133, "global_step": 347459, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.115452289581299, "global_step": 347460, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1493489742279053, "global_step": 347461, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1591248512268066, "global_step": 347462, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0935075283050537, "global_step": 347463, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.17500901222229, "global_step": 347464, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1703834533691406, "global_step": 347465, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0955512523651123, "global_step": 347466, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1032450199127197, "global_step": 347467, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0865671634674072, "global_step": 347468, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.04909348487854, "global_step": 347469, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1147403717041016, "global_step": 347470, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0869271755218506, "global_step": 347471, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0572378635406494, "global_step": 347472, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1212494373321533, "global_step": 347473, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.127631664276123, "global_step": 347474, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0339560508728027, "global_step": 347475, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1039228439331055, "global_step": 347476, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.107236623764038, "global_step": 347477, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2553610801696777, "global_step": 347478, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1707680225372314, "global_step": 347479, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.078592300415039, "global_step": 347480, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1336874961853027, "global_step": 347481, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.083477735519409, "global_step": 347482, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0333902835845947, "global_step": 347483, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.222090244293213, "global_step": 347484, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0845024585723877, "global_step": 347485, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0736496448516846, "global_step": 347486, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0961287021636963, "global_step": 347487, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.15166974067688, "global_step": 347488, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1021203994750977, "global_step": 347489, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0510153770446777, "global_step": 347490, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.139791965484619, "global_step": 347491, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1433253288269043, "global_step": 347492, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0784571170806885, "global_step": 347493, "epoch": 708, "lr": 5e-05}
{"train_loss": 1.9920448064804077, "global_step": 347494, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1286911964416504, "global_step": 347495, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0665738582611084, "global_step": 347496, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.156203031539917, "global_step": 347497, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.150380849838257, "global_step": 347498, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1956605911254883, "global_step": 347499, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1898131370544434, "global_step": 347500, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0952117443084717, "global_step": 347501, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.122093677520752, "global_step": 347502, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.071425437927246, "global_step": 347503, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1024670600891113, "global_step": 347504, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.096712350845337, "global_step": 347505, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0734803676605225, "global_step": 347506, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.171409845352173, "global_step": 347507, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0870485305786133, "global_step": 347508, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0503768920898438, "global_step": 347509, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0117976665496826, "global_step": 347510, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1354763507843018, "global_step": 347511, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0743861198425293, "global_step": 347512, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1458091735839844, "global_step": 347513, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0726518630981445, "global_step": 347514, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0877249240875244, "global_step": 347515, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1104774475097656, "global_step": 347516, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.115177631378174, "global_step": 347517, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1904239654541016, "global_step": 347518, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.214259386062622, "global_step": 347519, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.111392021179199, "global_step": 347520, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.104494333267212, "global_step": 347521, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0567917823791504, "global_step": 347522, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1617953777313232, "global_step": 347523, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0878024101257324, "global_step": 347524, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1091220378875732, "global_step": 347525, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0935521125793457, "global_step": 347526, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.237903594970703, "global_step": 347527, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1445422172546387, "global_step": 347528, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.057478904724121, "global_step": 347529, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.078664779663086, "global_step": 347530, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.125580310821533, "global_step": 347531, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1740221977233887, "global_step": 347532, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1166727542877197, "global_step": 347533, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.156670093536377, "global_step": 347534, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0654237270355225, "global_step": 347535, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0433077812194824, "global_step": 347536, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1408722400665283, "global_step": 347537, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0566370487213135, "global_step": 347538, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1277480125427246, "global_step": 347539, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0998613834381104, "global_step": 347540, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1346194744110107, "global_step": 347541, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.192450761795044, "global_step": 347542, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.119673490524292, "global_step": 347543, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1719017028808594, "global_step": 347544, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1444404125213623, "global_step": 347545, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1365890502929688, "global_step": 347546, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0899763107299805, "global_step": 347547, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.096621513366699, "global_step": 347548, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.095398426055908, "global_step": 347549, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0681943893432617, "global_step": 347550, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.066251039505005, "global_step": 347551, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.135590076446533, "global_step": 347552, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.076819896697998, "global_step": 347553, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1942057609558105, "global_step": 347554, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.085972309112549, "global_step": 347555, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1089389324188232, "global_step": 347556, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1430752277374268, "global_step": 347557, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.083022117614746, "global_step": 347558, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0559518337249756, "global_step": 347559, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1240100860595703, "global_step": 347560, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0852854251861572, "global_step": 347561, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.052624225616455, "global_step": 347562, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1481974124908447, "global_step": 347563, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1249313354492188, "global_step": 347564, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0795037746429443, "global_step": 347565, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0336837768554688, "global_step": 347566, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0469179153442383, "global_step": 347567, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.157486915588379, "global_step": 347568, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0828490257263184, "global_step": 347569, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0675649642944336, "global_step": 347570, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0400078296661377, "global_step": 347571, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.123155117034912, "global_step": 347572, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.116333246231079, "global_step": 347573, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.14674711227417, "global_step": 347574, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.088832378387451, "global_step": 347575, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1556196212768555, "global_step": 347576, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1424753665924072, "global_step": 347577, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.117375373840332, "global_step": 347578, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.197645664215088, "global_step": 347579, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.084221839904785, "global_step": 347580, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.065850019454956, "global_step": 347581, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1277990341186523, "global_step": 347582, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1622211933135986, "global_step": 347583, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0420074462890625, "global_step": 347584, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1265869140625, "global_step": 347585, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.048466920852661, "global_step": 347586, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0879688262939453, "global_step": 347587, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.164552927017212, "global_step": 347588, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0930891036987305, "global_step": 347589, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.087820291519165, "global_step": 347590, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1274735927581787, "global_step": 347591, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.093571662902832, "global_step": 347592, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0174291133880615, "global_step": 347593, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.241544008255005, "global_step": 347594, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0269529819488525, "global_step": 347595, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1098217964172363, "global_step": 347596, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1715898513793945, "global_step": 347597, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1640195846557617, "global_step": 347598, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.188161849975586, "global_step": 347599, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.228910207748413, "global_step": 347600, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0903232097625732, "global_step": 347601, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.109890937805176, "global_step": 347602, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2244374752044678, "global_step": 347603, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1285266876220703, "global_step": 347604, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.165489673614502, "global_step": 347605, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.173539638519287, "global_step": 347606, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.143293857574463, "global_step": 347607, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.138108491897583, "global_step": 347608, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1305439472198486, "global_step": 347609, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.114795684814453, "global_step": 347610, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.077293872833252, "global_step": 347611, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1276893615722656, "global_step": 347612, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.153650999069214, "global_step": 347613, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2153756618499756, "global_step": 347614, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1006829738616943, "global_step": 347615, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2031617164611816, "global_step": 347616, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.125739812850952, "global_step": 347617, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1704812049865723, "global_step": 347618, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1170079708099365, "global_step": 347619, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0770151615142822, "global_step": 347620, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.067113161087036, "global_step": 347621, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.133608102798462, "global_step": 347622, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.087885856628418, "global_step": 347623, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.153193235397339, "global_step": 347624, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0926101207733154, "global_step": 347625, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1058807373046875, "global_step": 347626, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1360297203063965, "global_step": 347627, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.023158311843872, "global_step": 347628, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0478484630584717, "global_step": 347629, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.168137550354004, "global_step": 347630, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1828277111053467, "global_step": 347631, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0725715160369873, "global_step": 347632, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.136565685272217, "global_step": 347633, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0719540119171143, "global_step": 347634, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0503814220428467, "global_step": 347635, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1081347465515137, "global_step": 347636, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1945302486419678, "global_step": 347637, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1016428470611572, "global_step": 347638, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.103261947631836, "global_step": 347639, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.033005952835083, "global_step": 347640, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.186298370361328, "global_step": 347641, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0773842334747314, "global_step": 347642, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0629899501800537, "global_step": 347643, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0633785724639893, "global_step": 347644, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0925421714782715, "global_step": 347645, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.078508138656616, "global_step": 347646, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1322615146636963, "global_step": 347647, "epoch": 708, "lr": 5e-05}
{"train_loss": 1.9943329095840454, "global_step": 347648, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.071660041809082, "global_step": 347649, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.245173215866089, "global_step": 347650, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1583943367004395, "global_step": 347651, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1846559047698975, "global_step": 347652, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.104081869125366, "global_step": 347653, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.152947187423706, "global_step": 347654, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1562955379486084, "global_step": 347655, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1505558490753174, "global_step": 347656, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.049487590789795, "global_step": 347657, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0371978282928467, "global_step": 347658, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1035103797912598, "global_step": 347659, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0997517108917236, "global_step": 347660, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.087407112121582, "global_step": 347661, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0798957347869873, "global_step": 347662, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.10973858833313, "global_step": 347663, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.098001480102539, "global_step": 347664, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1469509601593018, "global_step": 347665, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1343321800231934, "global_step": 347666, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.126965045928955, "global_step": 347667, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.104315996170044, "global_step": 347668, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.084291696548462, "global_step": 347669, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1536636352539062, "global_step": 347670, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2232112884521484, "global_step": 347671, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.179737091064453, "global_step": 347672, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0727121829986572, "global_step": 347673, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0930581092834473, "global_step": 347674, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.109428882598877, "global_step": 347675, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0463619232177734, "global_step": 347676, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.094601631164551, "global_step": 347677, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.248918294906616, "global_step": 347678, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.131824016571045, "global_step": 347679, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.067201614379883, "global_step": 347680, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0447654724121094, "global_step": 347681, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0539348125457764, "global_step": 347682, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1608808040618896, "global_step": 347683, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1148455142974854, "global_step": 347684, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.040410280227661, "global_step": 347685, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1768457889556885, "global_step": 347686, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1625850200653076, "global_step": 347687, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.124450922012329, "global_step": 347688, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0805504322052, "global_step": 347689, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0671799182891846, "global_step": 347690, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1025991439819336, "global_step": 347691, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0643656253814697, "global_step": 347692, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.118539333343506, "global_step": 347693, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1757771968841553, "global_step": 347694, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.143394947052002, "global_step": 347695, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1047022342681885, "global_step": 347696, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.161325454711914, "global_step": 347697, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.088754415512085, "global_step": 347698, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.084333896636963, "global_step": 347699, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.130557060241699, "global_step": 347700, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1606862545013428, "global_step": 347701, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0787861347198486, "global_step": 347702, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2287187576293945, "global_step": 347703, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.179006576538086, "global_step": 347704, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1506667137145996, "global_step": 347705, "epoch": 708, "lr": 5e-05}
{"train_loss": 1.9982248544692993, "global_step": 347706, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1461362838745117, "global_step": 347707, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1735129356384277, "global_step": 347708, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.142817974090576, "global_step": 347709, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0905611515045166, "global_step": 347710, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.108232021331787, "global_step": 347711, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1976490020751953, "global_step": 347712, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1220993995666504, "global_step": 347713, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1107044219970703, "global_step": 347714, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.087981939315796, "global_step": 347715, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0961718559265137, "global_step": 347716, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1887712478637695, "global_step": 347717, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1040313243865967, "global_step": 347718, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1075308322906494, "global_step": 347719, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1160390377044678, "global_step": 347720, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.222391366958618, "global_step": 347721, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1082255840301514, "global_step": 347722, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.090533494949341, "global_step": 347723, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.03893780708313, "global_step": 347724, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0826656818389893, "global_step": 347725, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0706844329833984, "global_step": 347726, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.101917028427124, "global_step": 347727, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0151546001434326, "global_step": 347728, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.056466579437256, "global_step": 347729, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0984365940093994, "global_step": 347730, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.196143388748169, "global_step": 347731, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1148085594177246, "global_step": 347732, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0405924320220947, "global_step": 347733, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1092562675476074, "global_step": 347734, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.104928731918335, "global_step": 347735, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2112467288970947, "global_step": 347736, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.205636739730835, "global_step": 347737, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1261630058288574, "global_step": 347738, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1232919692993164, "global_step": 347739, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0654633045196533, "global_step": 347740, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.067047119140625, "global_step": 347741, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.095510482788086, "global_step": 347742, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1910061836242676, "global_step": 347743, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0815255641937256, "global_step": 347744, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1148183345794678, "global_step": 347745, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1096880435943604, "global_step": 347746, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.081839084625244, "global_step": 347747, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.036949872970581, "global_step": 347748, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1268880367279053, "global_step": 347749, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1971042156219482, "global_step": 347750, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.103753089904785, "global_step": 347751, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2177350521087646, "global_step": 347752, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1077423095703125, "global_step": 347753, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1054797172546387, "global_step": 347754, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.01773738861084, "global_step": 347755, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1582212448120117, "global_step": 347756, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0531516075134277, "global_step": 347757, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1485934257507324, "global_step": 347758, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1219968795776367, "global_step": 347759, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1495134830474854, "global_step": 347760, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0991721153259277, "global_step": 347761, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1422314643859863, "global_step": 347762, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.103071689605713, "global_step": 347763, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1295294761657715, "global_step": 347764, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1527888774871826, "global_step": 347765, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0177173614501953, "global_step": 347766, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1512835025787354, "global_step": 347767, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0918123722076416, "global_step": 347768, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0686416625976562, "global_step": 347769, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.137855052947998, "global_step": 347770, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0182712078094482, "global_step": 347771, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.125955581665039, "global_step": 347772, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0938003063201904, "global_step": 347773, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1479084491729736, "global_step": 347774, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.227898359298706, "global_step": 347775, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1741385459899902, "global_step": 347776, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1457831859588623, "global_step": 347777, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.063084363937378, "global_step": 347778, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1417927742004395, "global_step": 347779, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1346426010131836, "global_step": 347780, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.11252760887146, "global_step": 347781, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1259653568267822, "global_step": 347782, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.120676279067993, "global_step": 347783, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0868592262268066, "global_step": 347784, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.249220848083496, "global_step": 347785, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1037442684173584, "global_step": 347786, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.073901414871216, "global_step": 347787, "epoch": 708, "lr": 5e-05}
{"train_loss": 1.9989877939224243, "global_step": 347788, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.163944721221924, "global_step": 347789, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1598522663116455, "global_step": 347790, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0206940174102783, "global_step": 347791, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1012120246887207, "global_step": 347792, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.243227958679199, "global_step": 347793, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0998730659484863, "global_step": 347794, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0994784832000732, "global_step": 347795, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1147427558898926, "global_step": 347796, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0857961177825928, "global_step": 347797, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.149616003036499, "global_step": 347798, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1212775707244873, "global_step": 347799, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1296744346618652, "global_step": 347800, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1466166973114014, "global_step": 347801, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1247782707214355, "global_step": 347802, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.126375436782837, "global_step": 347803, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1572744846343994, "global_step": 347804, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0779662132263184, "global_step": 347805, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0868301391601562, "global_step": 347806, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.170928478240967, "global_step": 347807, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.160297155380249, "global_step": 347808, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1339111328125, "global_step": 347809, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1563217639923096, "global_step": 347810, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.215467929840088, "global_step": 347811, "epoch": 708, "lr": 5e-05}
{"train_loss": 1.9701838493347168, "global_step": 347812, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0154459476470947, "global_step": 347813, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.101090908050537, "global_step": 347814, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.133287191390991, "global_step": 347815, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0844013690948486, "global_step": 347816, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2311320304870605, "global_step": 347817, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0818979740142822, "global_step": 347818, "epoch": 708, "lr": 5e-05}
{"train_loss": 1.9859338998794556, "global_step": 347819, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.155562400817871, "global_step": 347820, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1044273376464844, "global_step": 347821, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1317312717437744, "global_step": 347822, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1190590858459473, "global_step": 347823, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1043243408203125, "global_step": 347824, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.042506217956543, "global_step": 347825, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.11761212348938, "global_step": 347826, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.122688055038452, "global_step": 347827, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1081573963165283, "global_step": 347828, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0941832065582275, "global_step": 347829, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0753326416015625, "global_step": 347830, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1358137130737305, "global_step": 347831, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2092537879943848, "global_step": 347832, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.001224994659424, "global_step": 347833, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.033285140991211, "global_step": 347834, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1029040813446045, "global_step": 347835, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0925095081329346, "global_step": 347836, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.097628355026245, "global_step": 347837, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0933427810668945, "global_step": 347838, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1255812644958496, "global_step": 347839, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0660929679870605, "global_step": 347840, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.047727584838867, "global_step": 347841, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1516218185424805, "global_step": 347842, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.212782621383667, "global_step": 347843, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.084611654281616, "global_step": 347844, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.153738021850586, "global_step": 347845, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1685631275177, "global_step": 347846, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.124413013458252, "global_step": 347847, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1169443130493164, "global_step": 347848, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.049409866333008, "global_step": 347849, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.115469217300415, "global_step": 347850, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.169473648071289, "global_step": 347851, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.071682929992676, "global_step": 347852, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1889359951019287, "global_step": 347853, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1217472553253174, "global_step": 347854, "epoch": 708, "lr": 5e-05}
{"train_loss": 1.9900944232940674, "global_step": 347855, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2229163646698, "global_step": 347856, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2308425903320312, "global_step": 347857, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1000430583953857, "global_step": 347858, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.131422758102417, "global_step": 347859, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1188583374023438, "global_step": 347860, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0883901119232178, "global_step": 347861, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.073315382003784, "global_step": 347862, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1629512310028076, "global_step": 347863, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0040464401245117, "global_step": 347864, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.169867992401123, "global_step": 347865, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.179157018661499, "global_step": 347866, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.131852149963379, "global_step": 347867, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0999388694763184, "global_step": 347868, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.147346258163452, "global_step": 347869, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.156764030456543, "global_step": 347870, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.145732879638672, "global_step": 347871, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0274839401245117, "global_step": 347872, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1603615283966064, "global_step": 347873, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0846900939941406, "global_step": 347874, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0339431762695312, "global_step": 347875, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0710628032684326, "global_step": 347876, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.128836154937744, "global_step": 347877, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0611460208892822, "global_step": 347878, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1906275749206543, "global_step": 347879, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0585241317749023, "global_step": 347880, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1042115688323975, "global_step": 347881, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.186659097671509, "global_step": 347882, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1117448806762695, "global_step": 347883, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.080782890319824, "global_step": 347884, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1266934871673584, "global_step": 347885, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0672285556793213, "global_step": 347886, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.082446575164795, "global_step": 347887, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0362391471862793, "global_step": 347888, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.168670654296875, "global_step": 347889, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1751835346221924, "global_step": 347890, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.08486270904541, "global_step": 347891, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.154149055480957, "global_step": 347892, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.164731025695801, "global_step": 347893, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1316113471984863, "global_step": 347894, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.012094020843506, "global_step": 347895, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.146900177001953, "global_step": 347896, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.14461088180542, "global_step": 347897, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0646235942840576, "global_step": 347898, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.120150089263916, "global_step": 347899, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.097644567489624, "global_step": 347900, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1081418991088867, "global_step": 347901, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0599966049194336, "global_step": 347902, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1631152629852295, "global_step": 347903, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0532188415527344, "global_step": 347904, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.145108938217163, "global_step": 347905, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.108464479446411, "global_step": 347906, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2200493812561035, "global_step": 347907, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0695102214813232, "global_step": 347908, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0998141765594482, "global_step": 347909, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1707258224487305, "global_step": 347910, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.061962366104126, "global_step": 347911, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.168701171875, "global_step": 347912, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.08998703956604, "global_step": 347913, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1696083545684814, "global_step": 347914, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1673896312713623, "global_step": 347915, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.106947898864746, "global_step": 347916, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.140326976776123, "global_step": 347917, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.125420093536377, "global_step": 347918, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1295764446258545, "global_step": 347919, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1104655265808105, "global_step": 347920, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.091524362564087, "global_step": 347921, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.024742364883423, "global_step": 347922, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0566794872283936, "global_step": 347923, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.057687759399414, "global_step": 347924, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1153922080993652, "global_step": 347925, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.127635955810547, "global_step": 347926, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0813066959381104, "global_step": 347927, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0784950256347656, "global_step": 347928, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1349782943725586, "global_step": 347929, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.097710132598877, "global_step": 347930, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.113359212875366, "global_step": 347931, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1206889152526855, "global_step": 347932, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1187334060668945, "global_step": 347933, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.033234119415283, "global_step": 347934, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.135105848312378, "global_step": 347935, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1100664138793945, "global_step": 347936, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1244072914123535, "global_step": 347937, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1109769344329834, "global_step": 347938, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2322328090667725, "global_step": 347939, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.137223958969116, "global_step": 347940, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.063232898712158, "global_step": 347941, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.142991304397583, "global_step": 347942, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.080949544906616, "global_step": 347943, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.174241542816162, "global_step": 347944, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.110438585281372, "global_step": 347945, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.129263401031494, "global_step": 347946, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.014559268951416, "global_step": 347947, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0659399032592773, "global_step": 347948, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.171536445617676, "global_step": 347949, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0148849487304688, "global_step": 347950, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1676881313323975, "global_step": 347951, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.079878568649292, "global_step": 347952, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0738096237182617, "global_step": 347953, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.066211462020874, "global_step": 347954, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1702640056610107, "global_step": 347955, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1245555877685547, "global_step": 347956, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.173553228378296, "global_step": 347957, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1414899826049805, "global_step": 347958, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.177755832672119, "global_step": 347959, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0340752601623535, "global_step": 347960, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.166565179824829, "global_step": 347961, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1115071773529053, "global_step": 347962, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.108344316482544, "global_step": 347963, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.193215847015381, "global_step": 347964, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0600876808166504, "global_step": 347965, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1703286170959473, "global_step": 347966, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1248419284820557, "global_step": 347967, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0294411182403564, "global_step": 347968, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.199122905731201, "global_step": 347969, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.16314697265625, "global_step": 347970, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1958420276641846, "global_step": 347971, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1545543670654297, "global_step": 347972, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0741755962371826, "global_step": 347973, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.073108673095703, "global_step": 347974, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.042625665664673, "global_step": 347975, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.262248992919922, "global_step": 347976, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.131244659423828, "global_step": 347977, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1067731380462646, "global_step": 347978, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1987502574920654, "global_step": 347979, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1288464069366455, "global_step": 347980, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.143204927444458, "global_step": 347981, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1308352947235107, "global_step": 347982, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1121985912323, "global_step": 347983, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1135220527648926, "global_step": 347984, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.107736587524414, "global_step": 347985, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0615603923797607, "global_step": 347986, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1042239665985107, "global_step": 347987, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1577298641204834, "global_step": 347988, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.059556484222412, "global_step": 347989, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.132051944732666, "global_step": 347990, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.082155466079712, "global_step": 347991, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.0501551628112793, "global_step": 347992, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.110551118850708, "global_step": 347993, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.121624708175659, "global_step": 347994, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.132718086242676, "global_step": 347995, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.152695655822754, "global_step": 347996, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.032285451889038, "global_step": 347997, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1500117778778076, "global_step": 347998, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.2182886600494385, "global_step": 347999, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.104891300201416, "global_step": 348000, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.146475315093994, "global_step": 348001, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.1056439876556396, "global_step": 348002, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.110346555709839, "global_step": 348003, "epoch": 708, "lr": 5e-05}
{"train_loss": 2.084975242614746, "global_step": 348004, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.114804267883301, "global_step": 348005, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0692124366760254, "global_step": 348006, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1418545246124268, "global_step": 348007, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1422371864318848, "global_step": 348008, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1338679790496826, "global_step": 348009, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.072253704071045, "global_step": 348010, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0672528743743896, "global_step": 348011, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1505210399627686, "global_step": 348012, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0117502212524414, "global_step": 348013, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.133852958679199, "global_step": 348014, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1233932971954346, "global_step": 348015, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1345040798187256, "global_step": 348016, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1829020977020264, "global_step": 348017, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1680350303649902, "global_step": 348018, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.072681427001953, "global_step": 348019, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1304996013641357, "global_step": 348020, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.031358480453491, "global_step": 348021, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.060513496398926, "global_step": 348022, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.116292715072632, "global_step": 348023, "epoch": 709, "lr": 5e-05}
{"train_loss": 1.996316909790039, "global_step": 348024, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.136676549911499, "global_step": 348025, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0486161708831787, "global_step": 348026, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0913124084472656, "global_step": 348027, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.064602851867676, "global_step": 348028, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1063148975372314, "global_step": 348029, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1013827323913574, "global_step": 348030, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1064250469207764, "global_step": 348031, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.13606595993042, "global_step": 348032, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0795507431030273, "global_step": 348033, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1720008850097656, "global_step": 348034, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1482231616973877, "global_step": 348035, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0677011013031006, "global_step": 348036, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1737656593322754, "global_step": 348037, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.029745578765869, "global_step": 348038, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.088541269302368, "global_step": 348039, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0974745750427246, "global_step": 348040, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1314098834991455, "global_step": 348041, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.066812753677368, "global_step": 348042, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0839452743530273, "global_step": 348043, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1682209968566895, "global_step": 348044, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.065425157546997, "global_step": 348045, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.056664228439331, "global_step": 348046, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.097830057144165, "global_step": 348047, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0266330242156982, "global_step": 348048, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1409049034118652, "global_step": 348049, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.019590377807617, "global_step": 348050, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1386051177978516, "global_step": 348051, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.179290533065796, "global_step": 348052, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.134213447570801, "global_step": 348053, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.144590377807617, "global_step": 348054, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.126492738723755, "global_step": 348055, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1882991790771484, "global_step": 348056, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1314167976379395, "global_step": 348057, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1103925704956055, "global_step": 348058, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.125074863433838, "global_step": 348059, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0035033226013184, "global_step": 348060, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.01871919631958, "global_step": 348061, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.078932046890259, "global_step": 348062, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1734225749969482, "global_step": 348063, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.160144805908203, "global_step": 348064, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0884859561920166, "global_step": 348065, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0499627590179443, "global_step": 348066, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1988909244537354, "global_step": 348067, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1036007404327393, "global_step": 348068, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0100369453430176, "global_step": 348069, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.054283618927002, "global_step": 348070, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.059520721435547, "global_step": 348071, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.076141595840454, "global_step": 348072, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0373456478118896, "global_step": 348073, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.131526470184326, "global_step": 348074, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.08853816986084, "global_step": 348075, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0663955211639404, "global_step": 348076, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0330607891082764, "global_step": 348077, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1270434856414795, "global_step": 348078, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1581430435180664, "global_step": 348079, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.177424430847168, "global_step": 348080, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0977351665496826, "global_step": 348081, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0861470699310303, "global_step": 348082, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.131561040878296, "global_step": 348083, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0553834438323975, "global_step": 348084, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.099357843399048, "global_step": 348085, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.053123712539673, "global_step": 348086, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0378754138946533, "global_step": 348087, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.160762310028076, "global_step": 348088, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.017976999282837, "global_step": 348089, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1399619579315186, "global_step": 348090, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0861074924468994, "global_step": 348091, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1189956665039062, "global_step": 348092, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.168217182159424, "global_step": 348093, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.124311685562134, "global_step": 348094, "epoch": 709, "lr": 5e-05}
{"train_loss": 1.999161958694458, "global_step": 348095, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0405073165893555, "global_step": 348096, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1296896934509277, "global_step": 348097, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1395649909973145, "global_step": 348098, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0697593688964844, "global_step": 348099, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1235148906707764, "global_step": 348100, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.111417770385742, "global_step": 348101, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.09639048576355, "global_step": 348102, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.109916925430298, "global_step": 348103, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.14634370803833, "global_step": 348104, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1062896251678467, "global_step": 348105, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0774457454681396, "global_step": 348106, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1488852500915527, "global_step": 348107, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.13517165184021, "global_step": 348108, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0169777870178223, "global_step": 348109, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.14329195022583, "global_step": 348110, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.193794012069702, "global_step": 348111, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0748510360717773, "global_step": 348112, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.183967351913452, "global_step": 348113, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0770301818847656, "global_step": 348114, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.144331216812134, "global_step": 348115, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.106574535369873, "global_step": 348116, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0657896995544434, "global_step": 348117, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.037186622619629, "global_step": 348118, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1540675163269043, "global_step": 348119, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0924813747406006, "global_step": 348120, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0746312141418457, "global_step": 348121, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.045241594314575, "global_step": 348122, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0914156436920166, "global_step": 348123, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.138653039932251, "global_step": 348124, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.053659200668335, "global_step": 348125, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1080143451690674, "global_step": 348126, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0896413326263428, "global_step": 348127, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0767035484313965, "global_step": 348128, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0911965370178223, "global_step": 348129, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.089094877243042, "global_step": 348130, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.104445695877075, "global_step": 348131, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.114927291870117, "global_step": 348132, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1606194972991943, "global_step": 348133, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.036972761154175, "global_step": 348134, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.084381341934204, "global_step": 348135, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.089877128601074, "global_step": 348136, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0697269439697266, "global_step": 348137, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0983002185821533, "global_step": 348138, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.123337745666504, "global_step": 348139, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0185317993164062, "global_step": 348140, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0728907585144043, "global_step": 348141, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0714218616485596, "global_step": 348142, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.133273124694824, "global_step": 348143, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.118633985519409, "global_step": 348144, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1093544960021973, "global_step": 348145, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.2051138877868652, "global_step": 348146, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1007096767425537, "global_step": 348147, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.041085958480835, "global_step": 348148, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0986921787261963, "global_step": 348149, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1336491107940674, "global_step": 348150, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0695736408233643, "global_step": 348151, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0697081089019775, "global_step": 348152, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1042821407318115, "global_step": 348153, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1275670528411865, "global_step": 348154, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0235867500305176, "global_step": 348155, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.123182773590088, "global_step": 348156, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1218984127044678, "global_step": 348157, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.223639726638794, "global_step": 348158, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.155724048614502, "global_step": 348159, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.058835029602051, "global_step": 348160, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.104316473007202, "global_step": 348161, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.184138774871826, "global_step": 348162, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0465357303619385, "global_step": 348163, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.092092752456665, "global_step": 348164, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.043637990951538, "global_step": 348165, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.006010055541992, "global_step": 348166, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1110496520996094, "global_step": 348167, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.128631353378296, "global_step": 348168, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.049302101135254, "global_step": 348169, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.104071617126465, "global_step": 348170, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0742013454437256, "global_step": 348171, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0577406883239746, "global_step": 348172, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.062929630279541, "global_step": 348173, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.095256805419922, "global_step": 348174, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0930674076080322, "global_step": 348175, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0828821659088135, "global_step": 348176, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0996501445770264, "global_step": 348177, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.061049222946167, "global_step": 348178, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0855820178985596, "global_step": 348179, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0823233127593994, "global_step": 348180, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.144956111907959, "global_step": 348181, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0669310092926025, "global_step": 348182, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1737020015716553, "global_step": 348183, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1407816410064697, "global_step": 348184, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.085482358932495, "global_step": 348185, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.044731616973877, "global_step": 348186, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0540239810943604, "global_step": 348187, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1772258281707764, "global_step": 348188, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.13067364692688, "global_step": 348189, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.037341356277466, "global_step": 348190, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.093665599822998, "global_step": 348191, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.098165988922119, "global_step": 348192, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.133417844772339, "global_step": 348193, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.116820812225342, "global_step": 348194, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0781490802764893, "global_step": 348195, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.112825393676758, "global_step": 348196, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1374621391296387, "global_step": 348197, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0847578048706055, "global_step": 348198, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1605327129364014, "global_step": 348199, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0643410682678223, "global_step": 348200, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.162958860397339, "global_step": 348201, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.070197343826294, "global_step": 348202, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0323472023010254, "global_step": 348203, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1333906650543213, "global_step": 348204, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0824942588806152, "global_step": 348205, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1337575912475586, "global_step": 348206, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.078354835510254, "global_step": 348207, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1502037048339844, "global_step": 348208, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.167182207107544, "global_step": 348209, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.109121561050415, "global_step": 348210, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0728533267974854, "global_step": 348211, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1156678199768066, "global_step": 348212, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.092555522918701, "global_step": 348213, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.098012685775757, "global_step": 348214, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.080601930618286, "global_step": 348215, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0763070583343506, "global_step": 348216, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0880839824676514, "global_step": 348217, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0916552543640137, "global_step": 348218, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0836429595947266, "global_step": 348219, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0579895973205566, "global_step": 348220, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1676948070526123, "global_step": 348221, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.113619089126587, "global_step": 348222, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.047072410583496, "global_step": 348223, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.064495325088501, "global_step": 348224, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.188133716583252, "global_step": 348225, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1029727458953857, "global_step": 348226, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1074953079223633, "global_step": 348227, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.141576051712036, "global_step": 348228, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1112325191497803, "global_step": 348229, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.068380355834961, "global_step": 348230, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1394662857055664, "global_step": 348231, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1020824909210205, "global_step": 348232, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1451778411865234, "global_step": 348233, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0987021923065186, "global_step": 348234, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1020302772521973, "global_step": 348235, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.158087730407715, "global_step": 348236, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.139185905456543, "global_step": 348237, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1355741024017334, "global_step": 348238, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.072906970977783, "global_step": 348239, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1126973628997803, "global_step": 348240, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0688798427581787, "global_step": 348241, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0797197818756104, "global_step": 348242, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.077404022216797, "global_step": 348243, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.040179491043091, "global_step": 348244, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1371617317199707, "global_step": 348245, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1568901538848877, "global_step": 348246, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.110492467880249, "global_step": 348247, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0415947437286377, "global_step": 348248, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0328774452209473, "global_step": 348249, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.204108953475952, "global_step": 348250, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0736844539642334, "global_step": 348251, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0230469703674316, "global_step": 348252, "epoch": 709, "lr": 5e-05}
{"train_loss": 1.9868377447128296, "global_step": 348253, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0571093559265137, "global_step": 348254, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0544772148132324, "global_step": 348255, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1709702014923096, "global_step": 348256, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.119584083557129, "global_step": 348257, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1397652626037598, "global_step": 348258, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1273887157440186, "global_step": 348259, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0788280963897705, "global_step": 348260, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.176852226257324, "global_step": 348261, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1758370399475098, "global_step": 348262, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.071892261505127, "global_step": 348263, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.046149492263794, "global_step": 348264, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0400874614715576, "global_step": 348265, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1254281997680664, "global_step": 348266, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.093555450439453, "global_step": 348267, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.063749313354492, "global_step": 348268, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1780433654785156, "global_step": 348269, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.020401954650879, "global_step": 348270, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.037550449371338, "global_step": 348271, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1280555725097656, "global_step": 348272, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0858945846557617, "global_step": 348273, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1768898963928223, "global_step": 348274, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.2093703746795654, "global_step": 348275, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.059401512145996, "global_step": 348276, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.055710792541504, "global_step": 348277, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.128488063812256, "global_step": 348278, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0503833293914795, "global_step": 348279, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.2258782386779785, "global_step": 348280, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0864133834838867, "global_step": 348281, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1668317317962646, "global_step": 348282, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.118189573287964, "global_step": 348283, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.084812641143799, "global_step": 348284, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.108928918838501, "global_step": 348285, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1395363807678223, "global_step": 348286, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.148103713989258, "global_step": 348287, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1421937942504883, "global_step": 348288, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1439709663391113, "global_step": 348289, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.127243995666504, "global_step": 348290, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1754508018493652, "global_step": 348291, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1360647678375244, "global_step": 348292, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1408400535583496, "global_step": 348293, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0501294136047363, "global_step": 348294, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.12800669670105, "global_step": 348295, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.2048017978668213, "global_step": 348296, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.064958333969116, "global_step": 348297, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1679160594940186, "global_step": 348298, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1413261890411377, "global_step": 348299, "epoch": 709, "lr": 5e-05}
{"train_loss": 1.9901927709579468, "global_step": 348300, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0236656665802, "global_step": 348301, "epoch": 709, "lr": 5e-05}
{"train_loss": 1.9866126775741577, "global_step": 348302, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0626161098480225, "global_step": 348303, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0670218467712402, "global_step": 348304, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0538763999938965, "global_step": 348305, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.113722562789917, "global_step": 348306, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1118626594543457, "global_step": 348307, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1039786338806152, "global_step": 348308, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0121817588806152, "global_step": 348309, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.083214282989502, "global_step": 348310, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.2048559188842773, "global_step": 348311, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.123316526412964, "global_step": 348312, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.074085235595703, "global_step": 348313, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.179112672805786, "global_step": 348314, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0956640243530273, "global_step": 348315, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.076435089111328, "global_step": 348316, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1725356578826904, "global_step": 348317, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.097930908203125, "global_step": 348318, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.152696132659912, "global_step": 348319, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0822370052337646, "global_step": 348320, "epoch": 709, "lr": 5e-05}
{"train_loss": 1.998069167137146, "global_step": 348321, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0899479389190674, "global_step": 348322, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0723183155059814, "global_step": 348323, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1294164657592773, "global_step": 348324, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.190509080886841, "global_step": 348325, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.187918186187744, "global_step": 348326, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.109670877456665, "global_step": 348327, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0340027809143066, "global_step": 348328, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.2394614219665527, "global_step": 348329, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.029567003250122, "global_step": 348330, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.165590763092041, "global_step": 348331, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1350624561309814, "global_step": 348332, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0549073219299316, "global_step": 348333, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0741446018218994, "global_step": 348334, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0060970783233643, "global_step": 348335, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.103428363800049, "global_step": 348336, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.12634015083313, "global_step": 348337, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.079416513442993, "global_step": 348338, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.2110047340393066, "global_step": 348339, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0744807720184326, "global_step": 348340, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.125338077545166, "global_step": 348341, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.116579532623291, "global_step": 348342, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.119917869567871, "global_step": 348343, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1319656372070312, "global_step": 348344, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.121821403503418, "global_step": 348345, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1423251628875732, "global_step": 348346, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.088887929916382, "global_step": 348347, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1180999279022217, "global_step": 348348, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0774478912353516, "global_step": 348349, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.148798704147339, "global_step": 348350, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.044609546661377, "global_step": 348351, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.182978868484497, "global_step": 348352, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.169282913208008, "global_step": 348353, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1020708084106445, "global_step": 348354, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0808162689208984, "global_step": 348355, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.2040939331054688, "global_step": 348356, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.044551372528076, "global_step": 348357, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.044666290283203, "global_step": 348358, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.128627061843872, "global_step": 348359, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1279518604278564, "global_step": 348360, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1009435653686523, "global_step": 348361, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1567142009735107, "global_step": 348362, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.041161060333252, "global_step": 348363, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1441965103149414, "global_step": 348364, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.125751256942749, "global_step": 348365, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.249159336090088, "global_step": 348366, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.122089147567749, "global_step": 348367, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0835134983062744, "global_step": 348368, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0753531455993652, "global_step": 348369, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1159682273864746, "global_step": 348370, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.112861156463623, "global_step": 348371, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.079969882965088, "global_step": 348372, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.130093812942505, "global_step": 348373, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.142637014389038, "global_step": 348374, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.110801935195923, "global_step": 348375, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1021294593811035, "global_step": 348376, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.086212396621704, "global_step": 348377, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.128878593444824, "global_step": 348378, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0909433364868164, "global_step": 348379, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0770833492279053, "global_step": 348380, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1317667961120605, "global_step": 348381, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0507633686065674, "global_step": 348382, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1692700386047363, "global_step": 348383, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1330642700195312, "global_step": 348384, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.068591356277466, "global_step": 348385, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0645720958709717, "global_step": 348386, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1129846572875977, "global_step": 348387, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1125192642211914, "global_step": 348388, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.080153226852417, "global_step": 348389, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1032657623291016, "global_step": 348390, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.036746025085449, "global_step": 348391, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.051499843597412, "global_step": 348392, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.095567226409912, "global_step": 348393, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.059955596923828, "global_step": 348394, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1000452041625977, "global_step": 348395, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.02807879447937, "global_step": 348396, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1179561614990234, "global_step": 348397, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.090981960296631, "global_step": 348398, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1443655490875244, "global_step": 348399, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.067166566848755, "global_step": 348400, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1636602878570557, "global_step": 348401, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0529074668884277, "global_step": 348402, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.067363739013672, "global_step": 348403, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.057248592376709, "global_step": 348404, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.200972557067871, "global_step": 348405, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.114596366882324, "global_step": 348406, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.127894401550293, "global_step": 348407, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0937631130218506, "global_step": 348408, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0560669898986816, "global_step": 348409, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1276967525482178, "global_step": 348410, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.097870111465454, "global_step": 348411, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1220991611480713, "global_step": 348412, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1296567916870117, "global_step": 348413, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1675148010253906, "global_step": 348414, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.078493595123291, "global_step": 348415, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.025909662246704, "global_step": 348416, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0566959381103516, "global_step": 348417, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.028928756713867, "global_step": 348418, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.037903308868408, "global_step": 348419, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0932180881500244, "global_step": 348420, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1482441425323486, "global_step": 348421, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0930778980255127, "global_step": 348422, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.103398323059082, "global_step": 348423, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.00931978225708, "global_step": 348424, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0886709690093994, "global_step": 348425, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0910134315490723, "global_step": 348426, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0770459175109863, "global_step": 348427, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0972185134887695, "global_step": 348428, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1122055053710938, "global_step": 348429, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.092966318130493, "global_step": 348430, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1525871753692627, "global_step": 348431, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0834431648254395, "global_step": 348432, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.199268102645874, "global_step": 348433, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.045501470565796, "global_step": 348434, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0492424964904785, "global_step": 348435, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1108109951019287, "global_step": 348436, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.03022837638855, "global_step": 348437, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1290791034698486, "global_step": 348438, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0874249935150146, "global_step": 348439, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.115389823913574, "global_step": 348440, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.2299811840057373, "global_step": 348441, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0791797637939453, "global_step": 348442, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.037057399749756, "global_step": 348443, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0544545650482178, "global_step": 348444, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1650047302246094, "global_step": 348445, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1298394203186035, "global_step": 348446, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.123960494995117, "global_step": 348447, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.144998550415039, "global_step": 348448, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.052307605743408, "global_step": 348449, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.107287645339966, "global_step": 348450, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.197518825531006, "global_step": 348451, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.096039295196533, "global_step": 348452, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0072197914123535, "global_step": 348453, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.130326986312866, "global_step": 348454, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1558756828308105, "global_step": 348455, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.153996229171753, "global_step": 348456, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.065546751022339, "global_step": 348457, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1364948749542236, "global_step": 348458, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0775561332702637, "global_step": 348459, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.142674207687378, "global_step": 348460, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0753417015075684, "global_step": 348461, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1755223274230957, "global_step": 348462, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.107649803161621, "global_step": 348463, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1152548789978027, "global_step": 348464, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.116945505142212, "global_step": 348465, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1313769817352295, "global_step": 348466, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1153910160064697, "global_step": 348467, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.136704683303833, "global_step": 348468, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.184598207473755, "global_step": 348469, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.149444580078125, "global_step": 348470, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.06980037689209, "global_step": 348471, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1534948348999023, "global_step": 348472, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0902323722839355, "global_step": 348473, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.084770441055298, "global_step": 348474, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.077646493911743, "global_step": 348475, "epoch": 709, "lr": 5e-05}
{"train_loss": 1.9967361688613892, "global_step": 348476, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1431972980499268, "global_step": 348477, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.101776123046875, "global_step": 348478, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.154475450515747, "global_step": 348479, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1284916400909424, "global_step": 348480, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.088810443878174, "global_step": 348481, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.088181257247925, "global_step": 348482, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1219582557678223, "global_step": 348483, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0657811164855957, "global_step": 348484, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.136347532272339, "global_step": 348485, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0925912857055664, "global_step": 348486, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0449442863464355, "global_step": 348487, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.204634666442871, "global_step": 348488, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.023019552230835, "global_step": 348489, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1818482875823975, "global_step": 348490, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1791539192199707, "global_step": 348491, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.119004249572754, "global_step": 348492, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.12060284614563, "global_step": 348493, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.111034393310547, "global_step": 348494, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.121309518814087, "global_step": 348495, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.145983934402466, "global_step": 348496, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0597453117370605, "global_step": 348497, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.060166835784912, "global_step": 348498, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1419599056243896, "global_step": 348499, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1162667274475098, "global_step": 348500, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0979878902435303, "global_step": 348501, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1254756450653076, "global_step": 348502, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1596834659576416, "global_step": 348503, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1545934677124023, "global_step": 348504, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.112548351287842, "global_step": 348505, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.143688440322876, "global_step": 348506, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0650932788848877, "global_step": 348507, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.088688850402832, "global_step": 348508, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0280709266662598, "global_step": 348509, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0781450271606445, "global_step": 348510, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0022974014282227, "global_step": 348511, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.032947540283203, "global_step": 348512, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.10872220993042, "global_step": 348513, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1008541584014893, "global_step": 348514, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1157350540161133, "global_step": 348515, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.136638879776001, "global_step": 348516, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.155021905899048, "global_step": 348517, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0608177185058594, "global_step": 348518, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.098853349685669, "global_step": 348519, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.116905689239502, "global_step": 348520, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.095843553543091, "global_step": 348521, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.07705020904541, "global_step": 348522, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.14215350151062, "global_step": 348523, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.156208038330078, "global_step": 348524, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.2549736499786377, "global_step": 348525, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.097466468811035, "global_step": 348526, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1187121868133545, "global_step": 348527, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1173481941223145, "global_step": 348528, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0766868591308594, "global_step": 348529, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1542632579803467, "global_step": 348530, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.070542335510254, "global_step": 348531, "epoch": 709, "lr": 5e-05}
{"train_loss": 1.9745728969573975, "global_step": 348532, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.099944829940796, "global_step": 348533, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0874948501586914, "global_step": 348534, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0733954906463623, "global_step": 348535, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.052060604095459, "global_step": 348536, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1075215339660645, "global_step": 348537, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0663113594055176, "global_step": 348538, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.145725965499878, "global_step": 348539, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1789262294769287, "global_step": 348540, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0560073852539062, "global_step": 348541, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.055368185043335, "global_step": 348542, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1168179512023926, "global_step": 348543, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1534576416015625, "global_step": 348544, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.136955499649048, "global_step": 348545, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1658926010131836, "global_step": 348546, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.063875436782837, "global_step": 348547, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0559489727020264, "global_step": 348548, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1107125282287598, "global_step": 348549, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0078680515289307, "global_step": 348550, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.108715057373047, "global_step": 348551, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1738779544830322, "global_step": 348552, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.086350917816162, "global_step": 348553, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.157461166381836, "global_step": 348554, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.101602077484131, "global_step": 348555, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.21889591217041, "global_step": 348556, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.074528455734253, "global_step": 348557, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1168766021728516, "global_step": 348558, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0636205673217773, "global_step": 348559, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1308038234710693, "global_step": 348560, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1025846004486084, "global_step": 348561, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1061408519744873, "global_step": 348562, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.045816421508789, "global_step": 348563, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1115806102752686, "global_step": 348564, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.228501081466675, "global_step": 348565, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1667134761810303, "global_step": 348566, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1455912590026855, "global_step": 348567, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0844664573669434, "global_step": 348568, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0977799892425537, "global_step": 348569, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.128706932067871, "global_step": 348570, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1432831287384033, "global_step": 348571, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.063241720199585, "global_step": 348572, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0736544132232666, "global_step": 348573, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1113691329956055, "global_step": 348574, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.061206817626953, "global_step": 348575, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.105031967163086, "global_step": 348576, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.2271370887756348, "global_step": 348577, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.120304584503174, "global_step": 348578, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.2108333110809326, "global_step": 348579, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1191115379333496, "global_step": 348580, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1455111503601074, "global_step": 348581, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1287851333618164, "global_step": 348582, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1365675926208496, "global_step": 348583, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1666107177734375, "global_step": 348584, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1206674575805664, "global_step": 348585, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1617624759674072, "global_step": 348586, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.148998498916626, "global_step": 348587, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1089632511138916, "global_step": 348588, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.2516636848449707, "global_step": 348589, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.249483108520508, "global_step": 348590, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0958075523376465, "global_step": 348591, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0866472721099854, "global_step": 348592, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1415512561798096, "global_step": 348593, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.038806915283203, "global_step": 348594, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1167244911193848, "global_step": 348595, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1088502407073975, "global_step": 348596, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0865354537963867, "global_step": 348597, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1045985221862793, "global_step": 348598, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0568349361419678, "global_step": 348599, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.052485466003418, "global_step": 348600, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.057044267654419, "global_step": 348601, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.060688018798828, "global_step": 348602, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1079559326171875, "global_step": 348603, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.103269338607788, "global_step": 348604, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0904123783111572, "global_step": 348605, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.201042652130127, "global_step": 348606, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.074457883834839, "global_step": 348607, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.013770341873169, "global_step": 348608, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.088404655456543, "global_step": 348609, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.033529758453369, "global_step": 348610, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.226412534713745, "global_step": 348611, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0066752433776855, "global_step": 348612, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.125004768371582, "global_step": 348613, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0681471824645996, "global_step": 348614, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.07820987701416, "global_step": 348615, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.189958095550537, "global_step": 348616, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1511247158050537, "global_step": 348617, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.046128273010254, "global_step": 348618, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.08371639251709, "global_step": 348619, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.079470157623291, "global_step": 348620, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.204571008682251, "global_step": 348621, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1432690620422363, "global_step": 348622, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1656641960144043, "global_step": 348623, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.120241641998291, "global_step": 348624, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.153792142868042, "global_step": 348625, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.186906337738037, "global_step": 348626, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1188158988952637, "global_step": 348627, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0981976985931396, "global_step": 348628, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1513381004333496, "global_step": 348629, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0575621128082275, "global_step": 348630, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.065718650817871, "global_step": 348631, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.128065347671509, "global_step": 348632, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.058412551879883, "global_step": 348633, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1815357208251953, "global_step": 348634, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.084857702255249, "global_step": 348635, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.2008213996887207, "global_step": 348636, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0894174575805664, "global_step": 348637, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0582473278045654, "global_step": 348638, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1870644092559814, "global_step": 348639, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0143167972564697, "global_step": 348640, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.153369426727295, "global_step": 348641, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0680480003356934, "global_step": 348642, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0775718688964844, "global_step": 348643, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1483707427978516, "global_step": 348644, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.090092897415161, "global_step": 348645, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.142218828201294, "global_step": 348646, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.239494800567627, "global_step": 348647, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0698354244232178, "global_step": 348648, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0182032585144043, "global_step": 348649, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.097611904144287, "global_step": 348650, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1368417739868164, "global_step": 348651, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1732072830200195, "global_step": 348652, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.133007764816284, "global_step": 348653, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1974918842315674, "global_step": 348654, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.201124429702759, "global_step": 348655, "epoch": 709, "lr": 5e-05}
{"train_loss": 1.9934735298156738, "global_step": 348656, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1240923404693604, "global_step": 348657, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1286509037017822, "global_step": 348658, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1589434146881104, "global_step": 348659, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1270289421081543, "global_step": 348660, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0555930137634277, "global_step": 348661, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.073690414428711, "global_step": 348662, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0960853099823, "global_step": 348663, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1504454612731934, "global_step": 348664, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0558581352233887, "global_step": 348665, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0487208366394043, "global_step": 348666, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1099777221679688, "global_step": 348667, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0672848224639893, "global_step": 348668, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.114102363586426, "global_step": 348669, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.153923988342285, "global_step": 348670, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1883623600006104, "global_step": 348671, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1026484966278076, "global_step": 348672, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.086843490600586, "global_step": 348673, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.120058536529541, "global_step": 348674, "epoch": 709, "lr": 5e-05}
{"train_loss": 1.9938414096832275, "global_step": 348675, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1644816398620605, "global_step": 348676, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.109872817993164, "global_step": 348677, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.114555835723877, "global_step": 348678, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0855135917663574, "global_step": 348679, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1128594875335693, "global_step": 348680, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1583447456359863, "global_step": 348681, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1068692207336426, "global_step": 348682, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0711867809295654, "global_step": 348683, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.115198850631714, "global_step": 348684, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.099700450897217, "global_step": 348685, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0926754474639893, "global_step": 348686, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.178215980529785, "global_step": 348687, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1065921783447266, "global_step": 348688, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0717482566833496, "global_step": 348689, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1082420349121094, "global_step": 348690, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.187565565109253, "global_step": 348691, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1862776279449463, "global_step": 348692, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0701699256896973, "global_step": 348693, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0331108570098877, "global_step": 348694, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.181661605834961, "global_step": 348695, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1309428215026855, "global_step": 348696, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1062238216400146, "global_step": 348697, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1531245708465576, "global_step": 348698, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1242239475250244, "global_step": 348699, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1234798431396484, "global_step": 348700, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0980618000030518, "global_step": 348701, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0812413692474365, "global_step": 348702, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.14790415763855, "global_step": 348703, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.154022693634033, "global_step": 348704, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1333718299865723, "global_step": 348705, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.145811080932617, "global_step": 348706, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.116302728652954, "global_step": 348707, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1280267238616943, "global_step": 348708, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0759711265563965, "global_step": 348709, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0695135593414307, "global_step": 348710, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1059257984161377, "global_step": 348711, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.152895927429199, "global_step": 348712, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1169731616973877, "global_step": 348713, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0734894275665283, "global_step": 348714, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.113422393798828, "global_step": 348715, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1098453998565674, "global_step": 348716, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.101977825164795, "global_step": 348717, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.159939765930176, "global_step": 348718, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.083630323410034, "global_step": 348719, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.215423107147217, "global_step": 348720, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.087146043777466, "global_step": 348721, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.084737539291382, "global_step": 348722, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1529767513275146, "global_step": 348723, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1358320713043213, "global_step": 348724, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0539166927337646, "global_step": 348725, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1254332065582275, "global_step": 348726, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.180323362350464, "global_step": 348727, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.171595811843872, "global_step": 348728, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1266090869903564, "global_step": 348729, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0675809383392334, "global_step": 348730, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1224300861358643, "global_step": 348731, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.131749391555786, "global_step": 348732, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1708881855010986, "global_step": 348733, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1344735622406006, "global_step": 348734, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0012338161468506, "global_step": 348735, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.04085111618042, "global_step": 348736, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.094414710998535, "global_step": 348737, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0952253341674805, "global_step": 348738, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.116039752960205, "global_step": 348739, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0023610591888428, "global_step": 348740, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1114466190338135, "global_step": 348741, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.06815767288208, "global_step": 348742, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1217236518859863, "global_step": 348743, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.020301103591919, "global_step": 348744, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.068819046020508, "global_step": 348745, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0418577194213867, "global_step": 348746, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0116055011749268, "global_step": 348747, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.159054756164551, "global_step": 348748, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.088226556777954, "global_step": 348749, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0957305431365967, "global_step": 348750, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1964778900146484, "global_step": 348751, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0627264976501465, "global_step": 348752, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1446549892425537, "global_step": 348753, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.052943229675293, "global_step": 348754, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.107283592224121, "global_step": 348755, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.131054639816284, "global_step": 348756, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.161585807800293, "global_step": 348757, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1004438400268555, "global_step": 348758, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0764269828796387, "global_step": 348759, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0400850772857666, "global_step": 348760, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1385958194732666, "global_step": 348761, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.114905834197998, "global_step": 348762, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0392470359802246, "global_step": 348763, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.087878942489624, "global_step": 348764, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1514508724212646, "global_step": 348765, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1664624214172363, "global_step": 348766, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.036567449569702, "global_step": 348767, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.039824962615967, "global_step": 348768, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.076530694961548, "global_step": 348769, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.095521926879883, "global_step": 348770, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.136547088623047, "global_step": 348771, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1028501987457275, "global_step": 348772, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0895462036132812, "global_step": 348773, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1191611289978027, "global_step": 348774, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0990569591522217, "global_step": 348775, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1263155937194824, "global_step": 348776, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.11037015914917, "global_step": 348777, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.064113140106201, "global_step": 348778, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.2012832164764404, "global_step": 348779, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.038721799850464, "global_step": 348780, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.211038112640381, "global_step": 348781, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.098113775253296, "global_step": 348782, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.107447624206543, "global_step": 348783, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1426796913146973, "global_step": 348784, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1594643592834473, "global_step": 348785, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0298912525177, "global_step": 348786, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1086418628692627, "global_step": 348787, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0433924198150635, "global_step": 348788, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1066489219665527, "global_step": 348789, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0284438133239746, "global_step": 348790, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.075282096862793, "global_step": 348791, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0478031635284424, "global_step": 348792, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1666295528411865, "global_step": 348793, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.131244659423828, "global_step": 348794, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0818004608154297, "global_step": 348795, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.031827449798584, "global_step": 348796, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1067631244659424, "global_step": 348797, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.105055570602417, "global_step": 348798, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1340904235839844, "global_step": 348799, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0835671424865723, "global_step": 348800, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0532376766204834, "global_step": 348801, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1478822231292725, "global_step": 348802, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.118350028991699, "global_step": 348803, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.094212293624878, "global_step": 348804, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.184452772140503, "global_step": 348805, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.158177614212036, "global_step": 348806, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.149538516998291, "global_step": 348807, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.123401165008545, "global_step": 348808, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0757789611816406, "global_step": 348809, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1310603618621826, "global_step": 348810, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1085045337677, "global_step": 348811, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1192471981048584, "global_step": 348812, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1722190380096436, "global_step": 348813, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1222846508026123, "global_step": 348814, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0617716312408447, "global_step": 348815, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.065580368041992, "global_step": 348816, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1562886238098145, "global_step": 348817, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.102325439453125, "global_step": 348818, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1423158645629883, "global_step": 348819, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1455390453338623, "global_step": 348820, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0977184772491455, "global_step": 348821, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0565848350524902, "global_step": 348822, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1356635093688965, "global_step": 348823, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1409544944763184, "global_step": 348824, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.110032081604004, "global_step": 348825, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0878875255584717, "global_step": 348826, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0978612899780273, "global_step": 348827, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.084567070007324, "global_step": 348828, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0857813358306885, "global_step": 348829, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.094027042388916, "global_step": 348830, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0484492778778076, "global_step": 348831, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1334877014160156, "global_step": 348832, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.171048164367676, "global_step": 348833, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.089662551879883, "global_step": 348834, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0939109325408936, "global_step": 348835, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.124361991882324, "global_step": 348836, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.146984577178955, "global_step": 348837, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.079418182373047, "global_step": 348838, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0537056922912598, "global_step": 348839, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1051697731018066, "global_step": 348840, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.187100410461426, "global_step": 348841, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1409802436828613, "global_step": 348842, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1272506713867188, "global_step": 348843, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.115783929824829, "global_step": 348844, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.154308795928955, "global_step": 348845, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1991984844207764, "global_step": 348846, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.064833164215088, "global_step": 348847, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1268765926361084, "global_step": 348848, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.104999303817749, "global_step": 348849, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0284152030944824, "global_step": 348850, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1511709690093994, "global_step": 348851, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.07682204246521, "global_step": 348852, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1218583583831787, "global_step": 348853, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0853939056396484, "global_step": 348854, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.089198112487793, "global_step": 348855, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0814197063446045, "global_step": 348856, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.073256731033325, "global_step": 348857, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.105611801147461, "global_step": 348858, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.127708911895752, "global_step": 348859, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.061558723449707, "global_step": 348860, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1545257568359375, "global_step": 348861, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.113237142562866, "global_step": 348862, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1517791748046875, "global_step": 348863, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1682255268096924, "global_step": 348864, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1507461071014404, "global_step": 348865, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.159233570098877, "global_step": 348866, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0878710746765137, "global_step": 348867, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0385754108428955, "global_step": 348868, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.166548013687134, "global_step": 348869, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1113643646240234, "global_step": 348870, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.123777389526367, "global_step": 348871, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1658811569213867, "global_step": 348872, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1553330421447754, "global_step": 348873, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.129199504852295, "global_step": 348874, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1607370376586914, "global_step": 348875, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0869216918945312, "global_step": 348876, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.110058307647705, "global_step": 348877, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0699269771575928, "global_step": 348878, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.129103422164917, "global_step": 348879, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1663033962249756, "global_step": 348880, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.143944501876831, "global_step": 348881, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.103616952896118, "global_step": 348882, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.103794574737549, "global_step": 348883, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1081790924072266, "global_step": 348884, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0280017852783203, "global_step": 348885, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1791865825653076, "global_step": 348886, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.199782371520996, "global_step": 348887, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.12331223487854, "global_step": 348888, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1895675659179688, "global_step": 348889, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.048640489578247, "global_step": 348890, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.2208361625671387, "global_step": 348891, "epoch": 709, "lr": 5e-05}
{"train_loss": 1.9832403659820557, "global_step": 348892, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.077653169631958, "global_step": 348893, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.143627643585205, "global_step": 348894, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.091827154159546, "global_step": 348895, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1160924434661865, "global_step": 348896, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0584053993225098, "global_step": 348897, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0811219215393066, "global_step": 348898, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.044738531112671, "global_step": 348899, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1052212715148926, "global_step": 348900, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.135394334793091, "global_step": 348901, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0145108699798584, "global_step": 348902, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.197077989578247, "global_step": 348903, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.126574754714966, "global_step": 348904, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1594343185424805, "global_step": 348905, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.06880521774292, "global_step": 348906, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.145625114440918, "global_step": 348907, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1136956214904785, "global_step": 348908, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1265203952789307, "global_step": 348909, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1193695068359375, "global_step": 348910, "epoch": 709, "lr": 5e-05}
{"train_loss": 1.9851380586624146, "global_step": 348911, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0317564010620117, "global_step": 348912, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1084465980529785, "global_step": 348913, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1039133071899414, "global_step": 348914, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0947070121765137, "global_step": 348915, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.03196120262146, "global_step": 348916, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.103353977203369, "global_step": 348917, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1504921913146973, "global_step": 348918, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0250251293182373, "global_step": 348919, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1401166915893555, "global_step": 348920, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.048063039779663, "global_step": 348921, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.2005584239959717, "global_step": 348922, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1132290363311768, "global_step": 348923, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.140294313430786, "global_step": 348924, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1495275497436523, "global_step": 348925, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1871440410614014, "global_step": 348926, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0677192211151123, "global_step": 348927, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1834893226623535, "global_step": 348928, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1021087169647217, "global_step": 348929, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1042137145996094, "global_step": 348930, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1331565380096436, "global_step": 348931, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.065983295440674, "global_step": 348932, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1200122833251953, "global_step": 348933, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1492815017700195, "global_step": 348934, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.074476957321167, "global_step": 348935, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1023213863372803, "global_step": 348936, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.131380319595337, "global_step": 348937, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.114809989929199, "global_step": 348938, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.106734037399292, "global_step": 348939, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0927116870880127, "global_step": 348940, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1347031593322754, "global_step": 348941, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.041273355484009, "global_step": 348942, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.07401442527771, "global_step": 348943, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1084814071655273, "global_step": 348944, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1621291637420654, "global_step": 348945, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0800650119781494, "global_step": 348946, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1707851886749268, "global_step": 348947, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1192800998687744, "global_step": 348948, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.091313600540161, "global_step": 348949, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1504108905792236, "global_step": 348950, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1260759830474854, "global_step": 348951, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0659592151641846, "global_step": 348952, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.069827079772949, "global_step": 348953, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0618700981140137, "global_step": 348954, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.121561288833618, "global_step": 348955, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.061319589614868, "global_step": 348956, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1339309215545654, "global_step": 348957, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1537117958068848, "global_step": 348958, "epoch": 709, "lr": 5e-05}
{"train_loss": 1.9905633926391602, "global_step": 348959, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1380016803741455, "global_step": 348960, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0877983570098877, "global_step": 348961, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.224257230758667, "global_step": 348962, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.071301221847534, "global_step": 348963, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.132223606109619, "global_step": 348964, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1284048557281494, "global_step": 348965, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.119778633117676, "global_step": 348966, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1736061573028564, "global_step": 348967, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.0747616291046143, "global_step": 348968, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.144834518432617, "global_step": 348969, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.1309762001037598, "global_step": 348970, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.057180166244507, "global_step": 348971, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.106905460357666, "global_step": 348972, "epoch": 709, "lr": 5e-05}
{"train_loss": 2.053645372390747, "global_step": 348973, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0661120414733887, "global_step": 348974, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.082256555557251, "global_step": 348975, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1150035858154297, "global_step": 348976, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0934813022613525, "global_step": 348977, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0332586765289307, "global_step": 348978, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0718934535980225, "global_step": 348979, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.130431652069092, "global_step": 348980, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.111481189727783, "global_step": 348981, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.055638551712036, "global_step": 348982, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.06662654876709, "global_step": 348983, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.101161241531372, "global_step": 348984, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0619993209838867, "global_step": 348985, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.115110158920288, "global_step": 348986, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0875468254089355, "global_step": 348987, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.082909345626831, "global_step": 348988, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0652475357055664, "global_step": 348989, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0870399475097656, "global_step": 348990, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.102097511291504, "global_step": 348991, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1371428966522217, "global_step": 348992, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0890824794769287, "global_step": 348993, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1316170692443848, "global_step": 348994, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0852935314178467, "global_step": 348995, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.181293487548828, "global_step": 348996, "epoch": 710, "lr": 5e-05}
{"train_loss": 1.9724669456481934, "global_step": 348997, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1298391819000244, "global_step": 348998, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.102271556854248, "global_step": 348999, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0889692306518555, "global_step": 349000, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.082524299621582, "global_step": 349001, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1809301376342773, "global_step": 349002, "epoch": 710, "lr": 5e-05}
{"train_loss": 1.9715869426727295, "global_step": 349003, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1514697074890137, "global_step": 349004, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.190967559814453, "global_step": 349005, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0925259590148926, "global_step": 349006, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.081883192062378, "global_step": 349007, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0714316368103027, "global_step": 349008, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.055800676345825, "global_step": 349009, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.055060863494873, "global_step": 349010, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.149596929550171, "global_step": 349011, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.147965669631958, "global_step": 349012, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1175568103790283, "global_step": 349013, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1177256107330322, "global_step": 349014, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.110314130783081, "global_step": 349015, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0269079208374023, "global_step": 349016, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0219836235046387, "global_step": 349017, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.138705253601074, "global_step": 349018, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0492477416992188, "global_step": 349019, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1446330547332764, "global_step": 349020, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1601388454437256, "global_step": 349021, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.062917470932007, "global_step": 349022, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0633227825164795, "global_step": 349023, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1080093383789062, "global_step": 349024, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.042283773422241, "global_step": 349025, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0432698726654053, "global_step": 349026, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0545458793640137, "global_step": 349027, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.099717855453491, "global_step": 349028, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0358948707580566, "global_step": 349029, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.091193914413452, "global_step": 349030, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1594104766845703, "global_step": 349031, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1337785720825195, "global_step": 349032, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0275285243988037, "global_step": 349033, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1540300846099854, "global_step": 349034, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0406272411346436, "global_step": 349035, "epoch": 710, "lr": 5e-05}
{"train_loss": 1.9902544021606445, "global_step": 349036, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.129096746444702, "global_step": 349037, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1207125186920166, "global_step": 349038, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.074235677719116, "global_step": 349039, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.098271131515503, "global_step": 349040, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1842830181121826, "global_step": 349041, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1127166748046875, "global_step": 349042, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.075505495071411, "global_step": 349043, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0688517093658447, "global_step": 349044, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1160459518432617, "global_step": 349045, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1023640632629395, "global_step": 349046, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0531468391418457, "global_step": 349047, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0476250648498535, "global_step": 349048, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1096343994140625, "global_step": 349049, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.109074354171753, "global_step": 349050, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.15749192237854, "global_step": 349051, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1902899742126465, "global_step": 349052, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.069045066833496, "global_step": 349053, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.087451219558716, "global_step": 349054, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1704514026641846, "global_step": 349055, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1013269424438477, "global_step": 349056, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.203486204147339, "global_step": 349057, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1042072772979736, "global_step": 349058, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1455941200256348, "global_step": 349059, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1431307792663574, "global_step": 349060, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1332204341888428, "global_step": 349061, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.086354970932007, "global_step": 349062, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0544517040252686, "global_step": 349063, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1467738151550293, "global_step": 349064, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.077610492706299, "global_step": 349065, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1352486610412598, "global_step": 349066, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1594491004943848, "global_step": 349067, "epoch": 710, "lr": 5e-05}
{"train_loss": 1.990013599395752, "global_step": 349068, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.047006845474243, "global_step": 349069, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.132897138595581, "global_step": 349070, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.118911027908325, "global_step": 349071, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0767643451690674, "global_step": 349072, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1067099571228027, "global_step": 349073, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0532853603363037, "global_step": 349074, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0956575870513916, "global_step": 349075, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0181872844696045, "global_step": 349076, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.06535005569458, "global_step": 349077, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0732717514038086, "global_step": 349078, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1484949588775635, "global_step": 349079, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.197479724884033, "global_step": 349080, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.11694598197937, "global_step": 349081, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0973165035247803, "global_step": 349082, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.082181215286255, "global_step": 349083, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.084975481033325, "global_step": 349084, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.125711679458618, "global_step": 349085, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0944905281066895, "global_step": 349086, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.105192184448242, "global_step": 349087, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.032651662826538, "global_step": 349088, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.142951011657715, "global_step": 349089, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0911808013916016, "global_step": 349090, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.074348211288452, "global_step": 349091, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0296926498413086, "global_step": 349092, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.096665382385254, "global_step": 349093, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.171394109725952, "global_step": 349094, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.11639404296875, "global_step": 349095, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1089627742767334, "global_step": 349096, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.090745210647583, "global_step": 349097, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1166927814483643, "global_step": 349098, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.065335512161255, "global_step": 349099, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.141467332839966, "global_step": 349100, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.166735887527466, "global_step": 349101, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.146444320678711, "global_step": 349102, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0921967029571533, "global_step": 349103, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.087864637374878, "global_step": 349104, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.146775007247925, "global_step": 349105, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.060842990875244, "global_step": 349106, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0995118618011475, "global_step": 349107, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1300299167633057, "global_step": 349108, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1051886081695557, "global_step": 349109, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.085503101348877, "global_step": 349110, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.165562391281128, "global_step": 349111, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0370495319366455, "global_step": 349112, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0354371070861816, "global_step": 349113, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1555850505828857, "global_step": 349114, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.2350001335144043, "global_step": 349115, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.136106491088867, "global_step": 349116, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1901638507843018, "global_step": 349117, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1610662937164307, "global_step": 349118, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0780880451202393, "global_step": 349119, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0706894397735596, "global_step": 349120, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.065274715423584, "global_step": 349121, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1153149604797363, "global_step": 349122, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0699667930603027, "global_step": 349123, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0325584411621094, "global_step": 349124, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1117055416107178, "global_step": 349125, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1466143131256104, "global_step": 349126, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0026443004608154, "global_step": 349127, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.2392349243164062, "global_step": 349128, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.063326120376587, "global_step": 349129, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.097123146057129, "global_step": 349130, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0172648429870605, "global_step": 349131, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.156087875366211, "global_step": 349132, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0364911556243896, "global_step": 349133, "epoch": 710, "lr": 5e-05}
{"train_loss": 1.9993221759796143, "global_step": 349134, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.108898639678955, "global_step": 349135, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0912845134735107, "global_step": 349136, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.144151210784912, "global_step": 349137, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.131727933883667, "global_step": 349138, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1861870288848877, "global_step": 349139, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1035637855529785, "global_step": 349140, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0586097240448, "global_step": 349141, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1029884815216064, "global_step": 349142, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.042846918106079, "global_step": 349143, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0974578857421875, "global_step": 349144, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.123344659805298, "global_step": 349145, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.078556537628174, "global_step": 349146, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.045901298522949, "global_step": 349147, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0698390007019043, "global_step": 349148, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.030763626098633, "global_step": 349149, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0663115978240967, "global_step": 349150, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1679978370666504, "global_step": 349151, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.108426332473755, "global_step": 349152, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0565924644470215, "global_step": 349153, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1076552867889404, "global_step": 349154, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.148822069168091, "global_step": 349155, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1260499954223633, "global_step": 349156, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0419108867645264, "global_step": 349157, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1859323978424072, "global_step": 349158, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.117727518081665, "global_step": 349159, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0875627994537354, "global_step": 349160, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.135342597961426, "global_step": 349161, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.214573383331299, "global_step": 349162, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.111360549926758, "global_step": 349163, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0420000553131104, "global_step": 349164, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.151599884033203, "global_step": 349165, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.035675525665283, "global_step": 349166, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0463337898254395, "global_step": 349167, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0599987506866455, "global_step": 349168, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1425371170043945, "global_step": 349169, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.110607624053955, "global_step": 349170, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.046597957611084, "global_step": 349171, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.2041683197021484, "global_step": 349172, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1439735889434814, "global_step": 349173, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.149684429168701, "global_step": 349174, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.097156047821045, "global_step": 349175, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.130573272705078, "global_step": 349176, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.160036087036133, "global_step": 349177, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1367292404174805, "global_step": 349178, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.137669563293457, "global_step": 349179, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1545193195343018, "global_step": 349180, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1282052993774414, "global_step": 349181, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1103289127349854, "global_step": 349182, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0329718589782715, "global_step": 349183, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0822160243988037, "global_step": 349184, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.097193717956543, "global_step": 349185, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.046947717666626, "global_step": 349186, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.058772325515747, "global_step": 349187, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.08689546585083, "global_step": 349188, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0982227325439453, "global_step": 349189, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1645781993865967, "global_step": 349190, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0826642513275146, "global_step": 349191, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.095381498336792, "global_step": 349192, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0526480674743652, "global_step": 349193, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.08935546875, "global_step": 349194, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1153788566589355, "global_step": 349195, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.110790491104126, "global_step": 349196, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.114131450653076, "global_step": 349197, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.104609966278076, "global_step": 349198, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1146819591522217, "global_step": 349199, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0895142555236816, "global_step": 349200, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0556554794311523, "global_step": 349201, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0836987495422363, "global_step": 349202, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1556243896484375, "global_step": 349203, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.118685245513916, "global_step": 349204, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0623176097869873, "global_step": 349205, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.139380693435669, "global_step": 349206, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1158359050750732, "global_step": 349207, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.165332555770874, "global_step": 349208, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0893032550811768, "global_step": 349209, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.030911922454834, "global_step": 349210, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0893006324768066, "global_step": 349211, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1191632747650146, "global_step": 349212, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0931806564331055, "global_step": 349213, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1561806201934814, "global_step": 349214, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0840492248535156, "global_step": 349215, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0505523681640625, "global_step": 349216, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1059486865997314, "global_step": 349217, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.132513999938965, "global_step": 349218, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.068117618560791, "global_step": 349219, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.128061294555664, "global_step": 349220, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.073453903198242, "global_step": 349221, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1584572792053223, "global_step": 349222, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1285769939422607, "global_step": 349223, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1184237003326416, "global_step": 349224, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0629942417144775, "global_step": 349225, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0596067905426025, "global_step": 349226, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.113342046737671, "global_step": 349227, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0971744060516357, "global_step": 349228, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0918242931365967, "global_step": 349229, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0097978115081787, "global_step": 349230, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.100475311279297, "global_step": 349231, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.083932399749756, "global_step": 349232, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.2109506130218506, "global_step": 349233, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1303210258483887, "global_step": 349234, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1422767639160156, "global_step": 349235, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0947341918945312, "global_step": 349236, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.083045244216919, "global_step": 349237, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.108341932296753, "global_step": 349238, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1243364810943604, "global_step": 349239, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.149928331375122, "global_step": 349240, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1459238529205322, "global_step": 349241, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0446925163269043, "global_step": 349242, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.113981008529663, "global_step": 349243, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1206257343292236, "global_step": 349244, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1515185832977295, "global_step": 349245, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0758183002471924, "global_step": 349246, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.11739444732666, "global_step": 349247, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.233710527420044, "global_step": 349248, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.131326675415039, "global_step": 349249, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1404316425323486, "global_step": 349250, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.148383617401123, "global_step": 349251, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.043639659881592, "global_step": 349252, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0924530029296875, "global_step": 349253, "epoch": 710, "lr": 5e-05}
{"train_loss": 1.9909319877624512, "global_step": 349254, "epoch": 710, "lr": 5e-05}
{"train_loss": 1.995980143547058, "global_step": 349255, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.08561372756958, "global_step": 349256, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1330792903900146, "global_step": 349257, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.130675792694092, "global_step": 349258, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.10518479347229, "global_step": 349259, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1812217235565186, "global_step": 349260, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0896949768066406, "global_step": 349261, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1444475650787354, "global_step": 349262, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.09842586517334, "global_step": 349263, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.192662477493286, "global_step": 349264, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.051888942718506, "global_step": 349265, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1143250465393066, "global_step": 349266, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1836934089660645, "global_step": 349267, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.049337863922119, "global_step": 349268, "epoch": 710, "lr": 5e-05}
{"train_loss": 1.9914789199829102, "global_step": 349269, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.127335786819458, "global_step": 349270, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1482508182525635, "global_step": 349271, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.006610870361328, "global_step": 349272, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0921733379364014, "global_step": 349273, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.131180763244629, "global_step": 349274, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0148866176605225, "global_step": 349275, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.103076934814453, "global_step": 349276, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1202242374420166, "global_step": 349277, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.150618314743042, "global_step": 349278, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.110583543777466, "global_step": 349279, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.179690361022949, "global_step": 349280, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1308133602142334, "global_step": 349281, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.051396369934082, "global_step": 349282, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.139425039291382, "global_step": 349283, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1456897258758545, "global_step": 349284, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.053863048553467, "global_step": 349285, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.119722604751587, "global_step": 349286, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1568408012390137, "global_step": 349287, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.105635404586792, "global_step": 349288, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.099360704421997, "global_step": 349289, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.106839179992676, "global_step": 349290, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.081141471862793, "global_step": 349291, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1247549057006836, "global_step": 349292, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.220303773880005, "global_step": 349293, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0875329971313477, "global_step": 349294, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1112844944000244, "global_step": 349295, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.115798234939575, "global_step": 349296, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.016108512878418, "global_step": 349297, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0849812030792236, "global_step": 349298, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1522109508514404, "global_step": 349299, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.128923177719116, "global_step": 349300, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.165022373199463, "global_step": 349301, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0675251483917236, "global_step": 349302, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0697150230407715, "global_step": 349303, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0610857009887695, "global_step": 349304, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1108150482177734, "global_step": 349305, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.067251682281494, "global_step": 349306, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.116835594177246, "global_step": 349307, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1202378273010254, "global_step": 349308, "epoch": 710, "lr": 5e-05}
{"train_loss": 1.929629921913147, "global_step": 349309, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0752787590026855, "global_step": 349310, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1690399646759033, "global_step": 349311, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0525007247924805, "global_step": 349312, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1223843097686768, "global_step": 349313, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.121487617492676, "global_step": 349314, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1409075260162354, "global_step": 349315, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0623135566711426, "global_step": 349316, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0560660362243652, "global_step": 349317, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1440138816833496, "global_step": 349318, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.105642795562744, "global_step": 349319, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0958964824676514, "global_step": 349320, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0867724418640137, "global_step": 349321, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1514668464660645, "global_step": 349322, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.104480504989624, "global_step": 349323, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1236536502838135, "global_step": 349324, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1714694499969482, "global_step": 349325, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1444380283355713, "global_step": 349326, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.139037847518921, "global_step": 349327, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1731412410736084, "global_step": 349328, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1386070251464844, "global_step": 349329, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.114882707595825, "global_step": 349330, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0979926586151123, "global_step": 349331, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.2372665405273438, "global_step": 349332, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1226089000701904, "global_step": 349333, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1081581115722656, "global_step": 349334, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1073062419891357, "global_step": 349335, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.178941249847412, "global_step": 349336, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0809779167175293, "global_step": 349337, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.169018268585205, "global_step": 349338, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.070152521133423, "global_step": 349339, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.047759771347046, "global_step": 349340, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.041811943054199, "global_step": 349341, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.212409019470215, "global_step": 349342, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.09222412109375, "global_step": 349343, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.174396276473999, "global_step": 349344, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0875303745269775, "global_step": 349345, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.090261459350586, "global_step": 349346, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.144596815109253, "global_step": 349347, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1497764587402344, "global_step": 349348, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1304521560668945, "global_step": 349349, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0299794673919678, "global_step": 349350, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1825180053710938, "global_step": 349351, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1181209087371826, "global_step": 349352, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0958914756774902, "global_step": 349353, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0646543502807617, "global_step": 349354, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0591742992401123, "global_step": 349355, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.136017322540283, "global_step": 349356, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1128406524658203, "global_step": 349357, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.117595911026001, "global_step": 349358, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.133180856704712, "global_step": 349359, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1029930114746094, "global_step": 349360, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0419304370880127, "global_step": 349361, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1161949634552, "global_step": 349362, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0815443992614746, "global_step": 349363, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.112485885620117, "global_step": 349364, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.170381546020508, "global_step": 349365, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.056734323501587, "global_step": 349366, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.064199924468994, "global_step": 349367, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.045956611633301, "global_step": 349368, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0857248306274414, "global_step": 349369, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1271746158599854, "global_step": 349370, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.116969108581543, "global_step": 349371, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1371915340423584, "global_step": 349372, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1557655334472656, "global_step": 349373, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1216087341308594, "global_step": 349374, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.120159149169922, "global_step": 349375, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0902318954467773, "global_step": 349376, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1424384117126465, "global_step": 349377, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.126392126083374, "global_step": 349378, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1278233528137207, "global_step": 349379, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.085332155227661, "global_step": 349380, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1403512954711914, "global_step": 349381, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.065570116043091, "global_step": 349382, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1083197593688965, "global_step": 349383, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0219435691833496, "global_step": 349384, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.118143320083618, "global_step": 349385, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1082658767700195, "global_step": 349386, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0909509658813477, "global_step": 349387, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.089141607284546, "global_step": 349388, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.09264874458313, "global_step": 349389, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.160238742828369, "global_step": 349390, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1783361434936523, "global_step": 349391, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.172792434692383, "global_step": 349392, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1002233028411865, "global_step": 349393, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0998897552490234, "global_step": 349394, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0625967979431152, "global_step": 349395, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.132091999053955, "global_step": 349396, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0766091346740723, "global_step": 349397, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0907692909240723, "global_step": 349398, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.108401298522949, "global_step": 349399, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.03534197807312, "global_step": 349400, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0642879009246826, "global_step": 349401, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1110522747039795, "global_step": 349402, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1073131561279297, "global_step": 349403, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.117323398590088, "global_step": 349404, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0872814655303955, "global_step": 349405, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0288493633270264, "global_step": 349406, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.099839448928833, "global_step": 349407, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.15602970123291, "global_step": 349408, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0343825817108154, "global_step": 349409, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.080824851989746, "global_step": 349410, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.047398805618286, "global_step": 349411, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.110184669494629, "global_step": 349412, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1160476207733154, "global_step": 349413, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.132908821105957, "global_step": 349414, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1205365657806396, "global_step": 349415, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0784871578216553, "global_step": 349416, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.134490489959717, "global_step": 349417, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.145686149597168, "global_step": 349418, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1694624423980713, "global_step": 349419, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0915918350219727, "global_step": 349420, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0097105503082275, "global_step": 349421, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.141200304031372, "global_step": 349422, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0894432067871094, "global_step": 349423, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.069010019302368, "global_step": 349424, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.194565534591675, "global_step": 349425, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1620638370513916, "global_step": 349426, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1183457374572754, "global_step": 349427, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0977017879486084, "global_step": 349428, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.155928134918213, "global_step": 349429, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0001683235168457, "global_step": 349430, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1318647861480713, "global_step": 349431, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1600630283355713, "global_step": 349432, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1015243530273438, "global_step": 349433, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1237378120422363, "global_step": 349434, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1330678462982178, "global_step": 349435, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.118380546569824, "global_step": 349436, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0982422828674316, "global_step": 349437, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0750272274017334, "global_step": 349438, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.017127752304077, "global_step": 349439, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0148472785949707, "global_step": 349440, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.2061965465545654, "global_step": 349441, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1297407150268555, "global_step": 349442, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1030478477478027, "global_step": 349443, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1370019912719727, "global_step": 349444, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1029789447784424, "global_step": 349445, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.099330425262451, "global_step": 349446, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0538930892944336, "global_step": 349447, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0906295776367188, "global_step": 349448, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1214656829833984, "global_step": 349449, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1295852661132812, "global_step": 349450, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1349472999572754, "global_step": 349451, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0515902042388916, "global_step": 349452, "epoch": 710, "lr": 5e-05}
{"train_loss": 1.9896538257598877, "global_step": 349453, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0880823135375977, "global_step": 349454, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.122417449951172, "global_step": 349455, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1224358081817627, "global_step": 349456, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1348307132720947, "global_step": 349457, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1117420196533203, "global_step": 349458, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.135730504989624, "global_step": 349459, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0671606063842773, "global_step": 349460, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.20727801322937, "global_step": 349461, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1324057579040527, "global_step": 349462, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1120386123657227, "global_step": 349463, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0873184204101562, "global_step": 349464, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1098880767822266, "global_step": 349465, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0345194339752197, "global_step": 349466, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.167829990386963, "global_step": 349467, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0991928577423096, "global_step": 349468, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.081261157989502, "global_step": 349469, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.127635955810547, "global_step": 349470, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1262314319610596, "global_step": 349471, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.062195301055908, "global_step": 349472, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1393537521362305, "global_step": 349473, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.082603693008423, "global_step": 349474, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.030190944671631, "global_step": 349475, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.136047840118408, "global_step": 349476, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1312785148620605, "global_step": 349477, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0849335193634033, "global_step": 349478, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.015679121017456, "global_step": 349479, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0503406524658203, "global_step": 349480, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.085305690765381, "global_step": 349481, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1371686458587646, "global_step": 349482, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.2444841861724854, "global_step": 349483, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.170276165008545, "global_step": 349484, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.151594638824463, "global_step": 349485, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0838167667388916, "global_step": 349486, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1298205852508545, "global_step": 349487, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.175319194793701, "global_step": 349488, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.113589286804199, "global_step": 349489, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1585540771484375, "global_step": 349490, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0292084217071533, "global_step": 349491, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0134189128875732, "global_step": 349492, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1296708583831787, "global_step": 349493, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.139493227005005, "global_step": 349494, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.175816297531128, "global_step": 349495, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.131105899810791, "global_step": 349496, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1015007495880127, "global_step": 349497, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0582823753356934, "global_step": 349498, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.171450614929199, "global_step": 349499, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.032449722290039, "global_step": 349500, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.076392412185669, "global_step": 349501, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1403162479400635, "global_step": 349502, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.114659070968628, "global_step": 349503, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1192123889923096, "global_step": 349504, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.147052526473999, "global_step": 349505, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.117462396621704, "global_step": 349506, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0944535732269287, "global_step": 349507, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0454962253570557, "global_step": 349508, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0623769760131836, "global_step": 349509, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.160020112991333, "global_step": 349510, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1011569499969482, "global_step": 349511, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1839821338653564, "global_step": 349512, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.139636516571045, "global_step": 349513, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0877835750579834, "global_step": 349514, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.132474422454834, "global_step": 349515, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.174353837966919, "global_step": 349516, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1073241233825684, "global_step": 349517, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.122269868850708, "global_step": 349518, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0415828227996826, "global_step": 349519, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.20385479927063, "global_step": 349520, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.096771001815796, "global_step": 349521, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1989946365356445, "global_step": 349522, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0289406776428223, "global_step": 349523, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0561742782592773, "global_step": 349524, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.117366313934326, "global_step": 349525, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1084470748901367, "global_step": 349526, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1006827354431152, "global_step": 349527, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.162099599838257, "global_step": 349528, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.142719268798828, "global_step": 349529, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1680185794830322, "global_step": 349530, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.128830671310425, "global_step": 349531, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.186920166015625, "global_step": 349532, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0959882736206055, "global_step": 349533, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.100229024887085, "global_step": 349534, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.139993667602539, "global_step": 349535, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1620912551879883, "global_step": 349536, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0737385749816895, "global_step": 349537, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0486907958984375, "global_step": 349538, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.043242931365967, "global_step": 349539, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1471798419952393, "global_step": 349540, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.026087760925293, "global_step": 349541, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.136854410171509, "global_step": 349542, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.181997299194336, "global_step": 349543, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0641677379608154, "global_step": 349544, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.010974884033203, "global_step": 349545, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.118088483810425, "global_step": 349546, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1765620708465576, "global_step": 349547, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.199847936630249, "global_step": 349548, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.175750255584717, "global_step": 349549, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.232292652130127, "global_step": 349550, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1774184703826904, "global_step": 349551, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.062620162963867, "global_step": 349552, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1719441413879395, "global_step": 349553, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1681628227233887, "global_step": 349554, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.083871841430664, "global_step": 349555, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1109564304351807, "global_step": 349556, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1004889011383057, "global_step": 349557, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.140427827835083, "global_step": 349558, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1154139041900635, "global_step": 349559, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.011960029602051, "global_step": 349560, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.139439821243286, "global_step": 349561, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1575634479522705, "global_step": 349562, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0979323387145996, "global_step": 349563, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0552709102630615, "global_step": 349564, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0784261226654053, "global_step": 349565, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1881730556488037, "global_step": 349566, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1679933071136475, "global_step": 349567, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1190757751464844, "global_step": 349568, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0726754665374756, "global_step": 349569, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.071648597717285, "global_step": 349570, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.154160737991333, "global_step": 349571, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1283156871795654, "global_step": 349572, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.063999891281128, "global_step": 349573, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.075974464416504, "global_step": 349574, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.124006509780884, "global_step": 349575, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1167328357696533, "global_step": 349576, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0779917240142822, "global_step": 349577, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.100404739379883, "global_step": 349578, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.063612461090088, "global_step": 349579, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0811054706573486, "global_step": 349580, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0731308460235596, "global_step": 349581, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1248159408569336, "global_step": 349582, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1479568481445312, "global_step": 349583, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.114502429962158, "global_step": 349584, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0808358192443848, "global_step": 349585, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1469740867614746, "global_step": 349586, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0662147998809814, "global_step": 349587, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.153879165649414, "global_step": 349588, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.105612277984619, "global_step": 349589, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1770291328430176, "global_step": 349590, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0951120853424072, "global_step": 349591, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.150078058242798, "global_step": 349592, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1386501789093018, "global_step": 349593, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1767501831054688, "global_step": 349594, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1082122325897217, "global_step": 349595, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.174328088760376, "global_step": 349596, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0283966064453125, "global_step": 349597, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.142089605331421, "global_step": 349598, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.090820074081421, "global_step": 349599, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.162815570831299, "global_step": 349600, "epoch": 710, "lr": 5e-05}
{"train_loss": 1.9651352167129517, "global_step": 349601, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1466071605682373, "global_step": 349602, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.16331148147583, "global_step": 349603, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0723540782928467, "global_step": 349604, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1473445892333984, "global_step": 349605, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1190829277038574, "global_step": 349606, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.176300048828125, "global_step": 349607, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1242947578430176, "global_step": 349608, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1439733505249023, "global_step": 349609, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.195986270904541, "global_step": 349610, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1342477798461914, "global_step": 349611, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1671388149261475, "global_step": 349612, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1175084114074707, "global_step": 349613, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.132356643676758, "global_step": 349614, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0828773975372314, "global_step": 349615, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.123392105102539, "global_step": 349616, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.240220308303833, "global_step": 349617, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.105595588684082, "global_step": 349618, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0325896739959717, "global_step": 349619, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0939323902130127, "global_step": 349620, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.070523738861084, "global_step": 349621, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1380834579467773, "global_step": 349622, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0860209465026855, "global_step": 349623, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.102290630340576, "global_step": 349624, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.143137216567993, "global_step": 349625, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1696455478668213, "global_step": 349626, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1426804065704346, "global_step": 349627, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.17236328125, "global_step": 349628, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.105661153793335, "global_step": 349629, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.072373390197754, "global_step": 349630, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.135227918624878, "global_step": 349631, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1223249435424805, "global_step": 349632, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1353065967559814, "global_step": 349633, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.186584949493408, "global_step": 349634, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0996365547180176, "global_step": 349635, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1583526134490967, "global_step": 349636, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1047165393829346, "global_step": 349637, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.09993577003479, "global_step": 349638, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.175243616104126, "global_step": 349639, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1581289768218994, "global_step": 349640, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.032525062561035, "global_step": 349641, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1089532375335693, "global_step": 349642, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1255345344543457, "global_step": 349643, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.126220226287842, "global_step": 349644, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.146597146987915, "global_step": 349645, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0786945819854736, "global_step": 349646, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.067929267883301, "global_step": 349647, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0493345260620117, "global_step": 349648, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.036001443862915, "global_step": 349649, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0898690223693848, "global_step": 349650, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0231828689575195, "global_step": 349651, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.145810127258301, "global_step": 349652, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.118659496307373, "global_step": 349653, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1696317195892334, "global_step": 349654, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1243624687194824, "global_step": 349655, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1624951362609863, "global_step": 349656, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.104881763458252, "global_step": 349657, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.07082462310791, "global_step": 349658, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1376099586486816, "global_step": 349659, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1508519649505615, "global_step": 349660, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.068800449371338, "global_step": 349661, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.046999931335449, "global_step": 349662, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0682201385498047, "global_step": 349663, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.071436643600464, "global_step": 349664, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.153792381286621, "global_step": 349665, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1549429893493652, "global_step": 349666, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.213991403579712, "global_step": 349667, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1106674671173096, "global_step": 349668, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.055774450302124, "global_step": 349669, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0947065353393555, "global_step": 349670, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.081787109375, "global_step": 349671, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1882550716400146, "global_step": 349672, "epoch": 710, "lr": 5e-05}
{"train_loss": 1.9836658239364624, "global_step": 349673, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0876381397247314, "global_step": 349674, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.017669916152954, "global_step": 349675, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.162235975265503, "global_step": 349676, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.080458641052246, "global_step": 349677, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1616878509521484, "global_step": 349678, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.136312484741211, "global_step": 349679, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0063812732696533, "global_step": 349680, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0649144649505615, "global_step": 349681, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.184767723083496, "global_step": 349682, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.143336534500122, "global_step": 349683, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0640478134155273, "global_step": 349684, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.060451030731201, "global_step": 349685, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.151590347290039, "global_step": 349686, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.079026460647583, "global_step": 349687, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.088575601577759, "global_step": 349688, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1578259468078613, "global_step": 349689, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0439159870147705, "global_step": 349690, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0460474491119385, "global_step": 349691, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.107512950897217, "global_step": 349692, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0751311779022217, "global_step": 349693, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.046459913253784, "global_step": 349694, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0885660648345947, "global_step": 349695, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1305229663848877, "global_step": 349696, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0616509914398193, "global_step": 349697, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1151669025421143, "global_step": 349698, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1180219650268555, "global_step": 349699, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.087925910949707, "global_step": 349700, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.109273910522461, "global_step": 349701, "epoch": 710, "lr": 5e-05}
{"train_loss": 1.9872406721115112, "global_step": 349702, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.16135835647583, "global_step": 349703, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0868308544158936, "global_step": 349704, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1887433528900146, "global_step": 349705, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1152772903442383, "global_step": 349706, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0420689582824707, "global_step": 349707, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.2297275066375732, "global_step": 349708, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.110076665878296, "global_step": 349709, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1513850688934326, "global_step": 349710, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.158515214920044, "global_step": 349711, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.144441843032837, "global_step": 349712, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.093716621398926, "global_step": 349713, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1468265056610107, "global_step": 349714, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1720070838928223, "global_step": 349715, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0806946754455566, "global_step": 349716, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.098985195159912, "global_step": 349717, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.094923973083496, "global_step": 349718, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0984177589416504, "global_step": 349719, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1738228797912598, "global_step": 349720, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.2133309841156006, "global_step": 349721, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0447847843170166, "global_step": 349722, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0431957244873047, "global_step": 349723, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.151285171508789, "global_step": 349724, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0973846912384033, "global_step": 349725, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.111935615539551, "global_step": 349726, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1162197589874268, "global_step": 349727, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0451767444610596, "global_step": 349728, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.125894546508789, "global_step": 349729, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0470128059387207, "global_step": 349730, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1248013973236084, "global_step": 349731, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.075801134109497, "global_step": 349732, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1248044967651367, "global_step": 349733, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.122528314590454, "global_step": 349734, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.115123748779297, "global_step": 349735, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.148974895477295, "global_step": 349736, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1018786430358887, "global_step": 349737, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1260478496551514, "global_step": 349738, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1292238235473633, "global_step": 349739, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.076226234436035, "global_step": 349740, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0675015449523926, "global_step": 349741, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1114614009857178, "global_step": 349742, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.2360148429870605, "global_step": 349743, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.022332191467285, "global_step": 349744, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1190710067749023, "global_step": 349745, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1718502044677734, "global_step": 349746, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1056065559387207, "global_step": 349747, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1211419105529785, "global_step": 349748, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1489481925964355, "global_step": 349749, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.070718765258789, "global_step": 349750, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0635948181152344, "global_step": 349751, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.125521421432495, "global_step": 349752, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0920417308807373, "global_step": 349753, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.149146556854248, "global_step": 349754, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1640422344207764, "global_step": 349755, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.150118589401245, "global_step": 349756, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0322012901306152, "global_step": 349757, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1066925525665283, "global_step": 349758, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.109456777572632, "global_step": 349759, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1435084342956543, "global_step": 349760, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.195568561553955, "global_step": 349761, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1402933597564697, "global_step": 349762, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.127216339111328, "global_step": 349763, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.078688383102417, "global_step": 349764, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.040030002593994, "global_step": 349765, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1427063941955566, "global_step": 349766, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1738908290863037, "global_step": 349767, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.12831974029541, "global_step": 349768, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0793182849884033, "global_step": 349769, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.090895414352417, "global_step": 349770, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1421291828155518, "global_step": 349771, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1493446826934814, "global_step": 349772, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.104387044906616, "global_step": 349773, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0496463775634766, "global_step": 349774, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.057821035385132, "global_step": 349775, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1364705562591553, "global_step": 349776, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0917656421661377, "global_step": 349777, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1374709606170654, "global_step": 349778, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1679558753967285, "global_step": 349779, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0816662311553955, "global_step": 349780, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.199678897857666, "global_step": 349781, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0740599632263184, "global_step": 349782, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.19209885597229, "global_step": 349783, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.143864154815674, "global_step": 349784, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1666927337646484, "global_step": 349785, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1607251167297363, "global_step": 349786, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.115226984024048, "global_step": 349787, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1224448680877686, "global_step": 349788, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.100557565689087, "global_step": 349789, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.128816843032837, "global_step": 349790, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.168109893798828, "global_step": 349791, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1593527793884277, "global_step": 349792, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.233030319213867, "global_step": 349793, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.067830801010132, "global_step": 349794, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1482651233673096, "global_step": 349795, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1218507289886475, "global_step": 349796, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0751876831054688, "global_step": 349797, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.130403995513916, "global_step": 349798, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0375776290893555, "global_step": 349799, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0712735652923584, "global_step": 349800, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1212384700775146, "global_step": 349801, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.154653787612915, "global_step": 349802, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.109808921813965, "global_step": 349803, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.168414831161499, "global_step": 349804, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0368449687957764, "global_step": 349805, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1331989765167236, "global_step": 349806, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.084867000579834, "global_step": 349807, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.127570390701294, "global_step": 349808, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0414464473724365, "global_step": 349809, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0914130210876465, "global_step": 349810, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1201794147491455, "global_step": 349811, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0943117141723633, "global_step": 349812, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.238434314727783, "global_step": 349813, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1524691581726074, "global_step": 349814, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.131765604019165, "global_step": 349815, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1116526126861572, "global_step": 349816, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.160766124725342, "global_step": 349817, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1440467834472656, "global_step": 349818, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1454057693481445, "global_step": 349819, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0710933208465576, "global_step": 349820, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.03256893157959, "global_step": 349821, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.063889503479004, "global_step": 349822, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1421594619750977, "global_step": 349823, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.048231363296509, "global_step": 349824, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1043357849121094, "global_step": 349825, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1787354946136475, "global_step": 349826, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0882465839385986, "global_step": 349827, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.115680456161499, "global_step": 349828, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.119178295135498, "global_step": 349829, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1387453079223633, "global_step": 349830, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1777114868164062, "global_step": 349831, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1824381351470947, "global_step": 349832, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1733927726745605, "global_step": 349833, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.012899875640869, "global_step": 349834, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.142091989517212, "global_step": 349835, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0910990238189697, "global_step": 349836, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0610783100128174, "global_step": 349837, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1067111492156982, "global_step": 349838, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.065859079360962, "global_step": 349839, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.117372512817383, "global_step": 349840, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.16277813911438, "global_step": 349841, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0642943382263184, "global_step": 349842, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.14785099029541, "global_step": 349843, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.086970090866089, "global_step": 349844, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.056727886199951, "global_step": 349845, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0961337089538574, "global_step": 349846, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1034061908721924, "global_step": 349847, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.173401117324829, "global_step": 349848, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0972232818603516, "global_step": 349849, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.143522024154663, "global_step": 349850, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1026694774627686, "global_step": 349851, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.092663049697876, "global_step": 349852, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.082622766494751, "global_step": 349853, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0898830890655518, "global_step": 349854, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.17759370803833, "global_step": 349855, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0978450775146484, "global_step": 349856, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1459994316101074, "global_step": 349857, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1354012489318848, "global_step": 349858, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1052863597869873, "global_step": 349859, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.096552848815918, "global_step": 349860, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.124206066131592, "global_step": 349861, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.191883087158203, "global_step": 349862, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.079507827758789, "global_step": 349863, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0827651023864746, "global_step": 349864, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0704894065856934, "global_step": 349865, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.01639723777771, "global_step": 349866, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.188674211502075, "global_step": 349867, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1530933380126953, "global_step": 349868, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0924646854400635, "global_step": 349869, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1407811641693115, "global_step": 349870, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1345038414001465, "global_step": 349871, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0649940967559814, "global_step": 349872, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0634067058563232, "global_step": 349873, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.132657289505005, "global_step": 349874, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.196403980255127, "global_step": 349875, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1461448669433594, "global_step": 349876, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1016902923583984, "global_step": 349877, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1322805881500244, "global_step": 349878, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.113736629486084, "global_step": 349879, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.091019868850708, "global_step": 349880, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1347835063934326, "global_step": 349881, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.015745162963867, "global_step": 349882, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0209760665893555, "global_step": 349883, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1002583503723145, "global_step": 349884, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1003201007843018, "global_step": 349885, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.05629825592041, "global_step": 349886, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1450343132019043, "global_step": 349887, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0804123878479004, "global_step": 349888, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.185871124267578, "global_step": 349889, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0033326148986816, "global_step": 349890, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.20906138420105, "global_step": 349891, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.115266799926758, "global_step": 349892, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1511645317077637, "global_step": 349893, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.21109938621521, "global_step": 349894, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0616865158081055, "global_step": 349895, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0683162212371826, "global_step": 349896, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1534676551818848, "global_step": 349897, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0637385845184326, "global_step": 349898, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0751376152038574, "global_step": 349899, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0585522651672363, "global_step": 349900, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0767405033111572, "global_step": 349901, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.082980155944824, "global_step": 349902, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.142329216003418, "global_step": 349903, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1392531394958496, "global_step": 349904, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0838818550109863, "global_step": 349905, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.072582721710205, "global_step": 349906, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1466498374938965, "global_step": 349907, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.085690498352051, "global_step": 349908, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.2242701053619385, "global_step": 349909, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1525895595550537, "global_step": 349910, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1089699268341064, "global_step": 349911, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.135140895843506, "global_step": 349912, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0732948780059814, "global_step": 349913, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0639631748199463, "global_step": 349914, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.11993670463562, "global_step": 349915, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.2056424617767334, "global_step": 349916, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1020634174346924, "global_step": 349917, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.103025197982788, "global_step": 349918, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1488709449768066, "global_step": 349919, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.100689649581909, "global_step": 349920, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.2053956985473633, "global_step": 349921, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1237969398498535, "global_step": 349922, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1164145469665527, "global_step": 349923, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0653421878814697, "global_step": 349924, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0919530391693115, "global_step": 349925, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.091064691543579, "global_step": 349926, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.077223300933838, "global_step": 349927, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0128421783447266, "global_step": 349928, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1646218299865723, "global_step": 349929, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0805394649505615, "global_step": 349930, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.127692222595215, "global_step": 349931, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.087667226791382, "global_step": 349932, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.153311014175415, "global_step": 349933, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1327438354492188, "global_step": 349934, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1045539379119873, "global_step": 349935, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.035419225692749, "global_step": 349936, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1420400142669678, "global_step": 349937, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0844993591308594, "global_step": 349938, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.1039977073669434, "global_step": 349939, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.0996949672698975, "global_step": 349940, "epoch": 710, "lr": 5e-05}
{"train_loss": 2.10880970954895, "global_step": 349941, "epoch": 710, "lr": 5e-05, "val_loss": 5.661664009094238, "test_reconst_mse": 0.07383628189563751}
{"train_loss": 2.008568525314331, "global_step": 349942, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.032003402709961, "global_step": 349943, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.975938320159912, "global_step": 349944, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.18588924407959, "global_step": 349945, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.139622688293457, "global_step": 349946, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1178746223449707, "global_step": 349947, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.193067789077759, "global_step": 349948, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1291253566741943, "global_step": 349949, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1235806941986084, "global_step": 349950, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.047853946685791, "global_step": 349951, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.149049758911133, "global_step": 349952, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.062896251678467, "global_step": 349953, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.054147481918335, "global_step": 349954, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.094210386276245, "global_step": 349955, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.9741686582565308, "global_step": 349956, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0181989669799805, "global_step": 349957, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.105767011642456, "global_step": 349958, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.13219952583313, "global_step": 349959, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.998324990272522, "global_step": 349960, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.172391176223755, "global_step": 349961, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.008451223373413, "global_step": 349962, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.117074728012085, "global_step": 349963, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0811972618103027, "global_step": 349964, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.135411500930786, "global_step": 349965, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1112425327301025, "global_step": 349966, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1287360191345215, "global_step": 349967, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1255571842193604, "global_step": 349968, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.108963966369629, "global_step": 349969, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.087845802307129, "global_step": 349970, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.156536817550659, "global_step": 349971, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.119657039642334, "global_step": 349972, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0887398719787598, "global_step": 349973, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.047269582748413, "global_step": 349974, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0627036094665527, "global_step": 349975, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0687170028686523, "global_step": 349976, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.163896322250366, "global_step": 349977, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0617430210113525, "global_step": 349978, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2011525630950928, "global_step": 349979, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.094208002090454, "global_step": 349980, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.109093427658081, "global_step": 349981, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1672656536102295, "global_step": 349982, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1039180755615234, "global_step": 349983, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.196354627609253, "global_step": 349984, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0624969005584717, "global_step": 349985, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1487972736358643, "global_step": 349986, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.060127019882202, "global_step": 349987, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.134021043777466, "global_step": 349988, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.109142303466797, "global_step": 349989, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0644028186798096, "global_step": 349990, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1292672157287598, "global_step": 349991, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1432929039001465, "global_step": 349992, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1510279178619385, "global_step": 349993, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1687676906585693, "global_step": 349994, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.175039529800415, "global_step": 349995, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1090455055236816, "global_step": 349996, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1654953956604004, "global_step": 349997, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0863773822784424, "global_step": 349998, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1472153663635254, "global_step": 349999, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0679032802581787, "global_step": 350000, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0549278259277344, "global_step": 350001, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.097701072692871, "global_step": 350002, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.103012800216675, "global_step": 350003, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1683602333068848, "global_step": 350004, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1072347164154053, "global_step": 350005, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0910351276397705, "global_step": 350006, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0639710426330566, "global_step": 350007, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1483161449432373, "global_step": 350008, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.065134286880493, "global_step": 350009, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.9812026023864746, "global_step": 350010, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.08304500579834, "global_step": 350011, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1459314823150635, "global_step": 350012, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1472697257995605, "global_step": 350013, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0382611751556396, "global_step": 350014, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0258123874664307, "global_step": 350015, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0873610973358154, "global_step": 350016, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1203534603118896, "global_step": 350017, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.139047145843506, "global_step": 350018, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.100762367248535, "global_step": 350019, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0415961742401123, "global_step": 350020, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0180938243865967, "global_step": 350021, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.994826078414917, "global_step": 350022, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1385538578033447, "global_step": 350023, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1449437141418457, "global_step": 350024, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0301473140716553, "global_step": 350025, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0432238578796387, "global_step": 350026, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0013654232025146, "global_step": 350027, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0939111709594727, "global_step": 350028, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.9835125207901, "global_step": 350029, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1217188835144043, "global_step": 350030, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0316591262817383, "global_step": 350031, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0671799182891846, "global_step": 350032, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0875298976898193, "global_step": 350033, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1050782203674316, "global_step": 350034, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1224863529205322, "global_step": 350035, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.141636848449707, "global_step": 350036, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0639700889587402, "global_step": 350037, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.166991949081421, "global_step": 350038, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.039889097213745, "global_step": 350039, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0378313064575195, "global_step": 350040, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0856382846832275, "global_step": 350041, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.019788980484009, "global_step": 350042, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1095387935638428, "global_step": 350043, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1494195461273193, "global_step": 350044, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1124889850616455, "global_step": 350045, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.081789016723633, "global_step": 350046, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.094618320465088, "global_step": 350047, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0178325176239014, "global_step": 350048, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.105224609375, "global_step": 350049, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1057286262512207, "global_step": 350050, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0456416606903076, "global_step": 350051, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.131814479827881, "global_step": 350052, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0578978061676025, "global_step": 350053, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.072197675704956, "global_step": 350054, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0422632694244385, "global_step": 350055, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.169844388961792, "global_step": 350056, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.153001546859741, "global_step": 350057, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0866167545318604, "global_step": 350058, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.185344696044922, "global_step": 350059, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.9992152452468872, "global_step": 350060, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.089087724685669, "global_step": 350061, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0918405055999756, "global_step": 350062, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0368409156799316, "global_step": 350063, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0404703617095947, "global_step": 350064, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0961670875549316, "global_step": 350065, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1299338340759277, "global_step": 350066, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1065263748168945, "global_step": 350067, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.022876262664795, "global_step": 350068, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1215107440948486, "global_step": 350069, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1194956302642822, "global_step": 350070, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0539965629577637, "global_step": 350071, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1477861404418945, "global_step": 350072, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.087233543395996, "global_step": 350073, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.037379264831543, "global_step": 350074, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.9827631711959839, "global_step": 350075, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.157632827758789, "global_step": 350076, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.187112331390381, "global_step": 350077, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0834505558013916, "global_step": 350078, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1694021224975586, "global_step": 350079, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.174675226211548, "global_step": 350080, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.061232566833496, "global_step": 350081, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1544487476348877, "global_step": 350082, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.090653896331787, "global_step": 350083, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.161330461502075, "global_step": 350084, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.068089008331299, "global_step": 350085, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.104405403137207, "global_step": 350086, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1533193588256836, "global_step": 350087, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0763678550720215, "global_step": 350088, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0589983463287354, "global_step": 350089, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.117584466934204, "global_step": 350090, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0413577556610107, "global_step": 350091, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0497639179229736, "global_step": 350092, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1670963764190674, "global_step": 350093, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2613401412963867, "global_step": 350094, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0882225036621094, "global_step": 350095, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0252153873443604, "global_step": 350096, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.152143716812134, "global_step": 350097, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0352602005004883, "global_step": 350098, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1306779384613037, "global_step": 350099, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0041518211364746, "global_step": 350100, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.091153621673584, "global_step": 350101, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1157517433166504, "global_step": 350102, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0895299911499023, "global_step": 350103, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1975488662719727, "global_step": 350104, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.095228433609009, "global_step": 350105, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1536247730255127, "global_step": 350106, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.045815944671631, "global_step": 350107, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.210062265396118, "global_step": 350108, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0900156497955322, "global_step": 350109, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.127640962600708, "global_step": 350110, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0040957927703857, "global_step": 350111, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1255640983581543, "global_step": 350112, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1065168380737305, "global_step": 350113, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1367950439453125, "global_step": 350114, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0415680408477783, "global_step": 350115, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0923824310302734, "global_step": 350116, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0832061767578125, "global_step": 350117, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.079875946044922, "global_step": 350118, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0337443351745605, "global_step": 350119, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.06089448928833, "global_step": 350120, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1347062587738037, "global_step": 350121, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1491072177886963, "global_step": 350122, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.068721055984497, "global_step": 350123, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0270729064941406, "global_step": 350124, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0987954139709473, "global_step": 350125, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.182609796524048, "global_step": 350126, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1395456790924072, "global_step": 350127, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1087613105773926, "global_step": 350128, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.162362575531006, "global_step": 350129, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1271979808807373, "global_step": 350130, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0593323707580566, "global_step": 350131, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.074347496032715, "global_step": 350132, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0602915287017822, "global_step": 350133, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1236846446990967, "global_step": 350134, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.119464874267578, "global_step": 350135, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.088170051574707, "global_step": 350136, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.127769708633423, "global_step": 350137, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.124959707260132, "global_step": 350138, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.11700177192688, "global_step": 350139, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0866498947143555, "global_step": 350140, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0807580947875977, "global_step": 350141, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.120697498321533, "global_step": 350142, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1542320251464844, "global_step": 350143, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.026191473007202, "global_step": 350144, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.142125368118286, "global_step": 350145, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1380550861358643, "global_step": 350146, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0461463928222656, "global_step": 350147, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.130424737930298, "global_step": 350148, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1951725482940674, "global_step": 350149, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.03707218170166, "global_step": 350150, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1256814002990723, "global_step": 350151, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1492419242858887, "global_step": 350152, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0908026695251465, "global_step": 350153, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.133035659790039, "global_step": 350154, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.128265380859375, "global_step": 350155, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1007626056671143, "global_step": 350156, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.110445499420166, "global_step": 350157, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.195908784866333, "global_step": 350158, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.079813003540039, "global_step": 350159, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1636734008789062, "global_step": 350160, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0892932415008545, "global_step": 350161, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0799789428710938, "global_step": 350162, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0368120670318604, "global_step": 350163, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.174715518951416, "global_step": 350164, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0861995220184326, "global_step": 350165, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0410220623016357, "global_step": 350166, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.115143299102783, "global_step": 350167, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.102055788040161, "global_step": 350168, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0873513221740723, "global_step": 350169, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.02581524848938, "global_step": 350170, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1095428466796875, "global_step": 350171, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.13049578666687, "global_step": 350172, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.11559796333313, "global_step": 350173, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0281803607940674, "global_step": 350174, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1304452419281006, "global_step": 350175, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0817739963531494, "global_step": 350176, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0399203300476074, "global_step": 350177, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.089371919631958, "global_step": 350178, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.139206886291504, "global_step": 350179, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1148078441619873, "global_step": 350180, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.103311538696289, "global_step": 350181, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0252602100372314, "global_step": 350182, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1077613830566406, "global_step": 350183, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1035752296447754, "global_step": 350184, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.131406545639038, "global_step": 350185, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0808348655700684, "global_step": 350186, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1085622310638428, "global_step": 350187, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1257121562957764, "global_step": 350188, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.082825183868408, "global_step": 350189, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.115039348602295, "global_step": 350190, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.115288019180298, "global_step": 350191, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1796481609344482, "global_step": 350192, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.089825391769409, "global_step": 350193, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.103672981262207, "global_step": 350194, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0896897315979004, "global_step": 350195, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.149064779281616, "global_step": 350196, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0659825801849365, "global_step": 350197, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.140315055847168, "global_step": 350198, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0801007747650146, "global_step": 350199, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2001168727874756, "global_step": 350200, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1201577186584473, "global_step": 350201, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.073084831237793, "global_step": 350202, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.076080083847046, "global_step": 350203, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0755600929260254, "global_step": 350204, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1146862506866455, "global_step": 350205, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.034729480743408, "global_step": 350206, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1340718269348145, "global_step": 350207, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.088524341583252, "global_step": 350208, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1268436908721924, "global_step": 350209, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0851950645446777, "global_step": 350210, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.092287540435791, "global_step": 350211, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.119122266769409, "global_step": 350212, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.979759931564331, "global_step": 350213, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.055777072906494, "global_step": 350214, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.119624614715576, "global_step": 350215, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.155014991760254, "global_step": 350216, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2009646892547607, "global_step": 350217, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.105010747909546, "global_step": 350218, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0244109630584717, "global_step": 350219, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1122610569000244, "global_step": 350220, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0451889038085938, "global_step": 350221, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.102672815322876, "global_step": 350222, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1005101203918457, "global_step": 350223, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.113328695297241, "global_step": 350224, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1129117012023926, "global_step": 350225, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0430455207824707, "global_step": 350226, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.078235626220703, "global_step": 350227, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.073275327682495, "global_step": 350228, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.048161268234253, "global_step": 350229, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0074942111968994, "global_step": 350230, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1008403301239014, "global_step": 350231, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0876362323760986, "global_step": 350232, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1971538066864014, "global_step": 350233, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1021971702575684, "global_step": 350234, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.106276035308838, "global_step": 350235, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.109928607940674, "global_step": 350236, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.115007162094116, "global_step": 350237, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.178227186203003, "global_step": 350238, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.036848306655884, "global_step": 350239, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.129645824432373, "global_step": 350240, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.01397967338562, "global_step": 350241, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1098031997680664, "global_step": 350242, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1931278705596924, "global_step": 350243, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.9945532083511353, "global_step": 350244, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.158473014831543, "global_step": 350245, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.089111328125, "global_step": 350246, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.120701551437378, "global_step": 350247, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0607998371124268, "global_step": 350248, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.000802755355835, "global_step": 350249, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1295151710510254, "global_step": 350250, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.164905071258545, "global_step": 350251, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.9885187149047852, "global_step": 350252, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0702924728393555, "global_step": 350253, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.158140182495117, "global_step": 350254, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.072213649749756, "global_step": 350255, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.089108943939209, "global_step": 350256, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.174335479736328, "global_step": 350257, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.115455150604248, "global_step": 350258, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1428709030151367, "global_step": 350259, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.133334159851074, "global_step": 350260, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2550039291381836, "global_step": 350261, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.153674602508545, "global_step": 350262, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.226612091064453, "global_step": 350263, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.060389280319214, "global_step": 350264, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.177046775817871, "global_step": 350265, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.141007661819458, "global_step": 350266, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0801658630371094, "global_step": 350267, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.174586772918701, "global_step": 350268, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2149834632873535, "global_step": 350269, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.070385694503784, "global_step": 350270, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.142575979232788, "global_step": 350271, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2244057655334473, "global_step": 350272, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1022493839263916, "global_step": 350273, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1141817569732666, "global_step": 350274, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.182492733001709, "global_step": 350275, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0684335231781006, "global_step": 350276, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0731308460235596, "global_step": 350277, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.04020357131958, "global_step": 350278, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1859729290008545, "global_step": 350279, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1025009155273438, "global_step": 350280, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.098879337310791, "global_step": 350281, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.160740613937378, "global_step": 350282, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.121306896209717, "global_step": 350283, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0915658473968506, "global_step": 350284, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1058645248413086, "global_step": 350285, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1306512355804443, "global_step": 350286, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1299099922180176, "global_step": 350287, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.063236713409424, "global_step": 350288, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.08801531791687, "global_step": 350289, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0865495204925537, "global_step": 350290, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1389095783233643, "global_step": 350291, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.136274814605713, "global_step": 350292, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1467702388763428, "global_step": 350293, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1848154067993164, "global_step": 350294, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1295628547668457, "global_step": 350295, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1722891330718994, "global_step": 350296, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.076446771621704, "global_step": 350297, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1098792552948, "global_step": 350298, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1553432941436768, "global_step": 350299, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1031606197357178, "global_step": 350300, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.102130174636841, "global_step": 350301, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.209561824798584, "global_step": 350302, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.070587158203125, "global_step": 350303, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1016790866851807, "global_step": 350304, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.163361072540283, "global_step": 350305, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.120063066482544, "global_step": 350306, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.082106351852417, "global_step": 350307, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.034823179244995, "global_step": 350308, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0712320804595947, "global_step": 350309, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1063175201416016, "global_step": 350310, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.093461751937866, "global_step": 350311, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1025192737579346, "global_step": 350312, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1272287368774414, "global_step": 350313, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1290721893310547, "global_step": 350314, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.081761598587036, "global_step": 350315, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.068516254425049, "global_step": 350316, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0070641040802, "global_step": 350317, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0788486003875732, "global_step": 350318, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0815677642822266, "global_step": 350319, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.031348705291748, "global_step": 350320, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.064347982406616, "global_step": 350321, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.098113775253296, "global_step": 350322, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1416666507720947, "global_step": 350323, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0139124393463135, "global_step": 350324, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0716724395751953, "global_step": 350325, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0241873264312744, "global_step": 350326, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0982978343963623, "global_step": 350327, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0735926628112793, "global_step": 350328, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0957274436950684, "global_step": 350329, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1164603233337402, "global_step": 350330, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0684268474578857, "global_step": 350331, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1251943111419678, "global_step": 350332, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1175715923309326, "global_step": 350333, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0316672325134277, "global_step": 350334, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.063082456588745, "global_step": 350335, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.147763729095459, "global_step": 350336, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.195387840270996, "global_step": 350337, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.098646879196167, "global_step": 350338, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.187915325164795, "global_step": 350339, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1103951930999756, "global_step": 350340, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.121225595474243, "global_step": 350341, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.047518491744995, "global_step": 350342, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1341986656188965, "global_step": 350343, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1306371688842773, "global_step": 350344, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1330251693725586, "global_step": 350345, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.160508871078491, "global_step": 350346, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0393338203430176, "global_step": 350347, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1664464473724365, "global_step": 350348, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1595888137817383, "global_step": 350349, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.067587375640869, "global_step": 350350, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1628198623657227, "global_step": 350351, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1504995822906494, "global_step": 350352, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.138521194458008, "global_step": 350353, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.09012508392334, "global_step": 350354, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.179365634918213, "global_step": 350355, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.048752784729004, "global_step": 350356, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1242058277130127, "global_step": 350357, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.074124574661255, "global_step": 350358, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0454719066619873, "global_step": 350359, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0286076068878174, "global_step": 350360, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.135072946548462, "global_step": 350361, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0854506492614746, "global_step": 350362, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.035144567489624, "global_step": 350363, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0903544425964355, "global_step": 350364, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1109464168548584, "global_step": 350365, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1237034797668457, "global_step": 350366, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0727896690368652, "global_step": 350367, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.022109031677246, "global_step": 350368, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0679962635040283, "global_step": 350369, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1165390014648438, "global_step": 350370, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.203219413757324, "global_step": 350371, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.9894684553146362, "global_step": 350372, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.068991184234619, "global_step": 350373, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.055013418197632, "global_step": 350374, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0896925926208496, "global_step": 350375, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.120004177093506, "global_step": 350376, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.139495611190796, "global_step": 350377, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1106369495391846, "global_step": 350378, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1627047061920166, "global_step": 350379, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0863196849823, "global_step": 350380, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2048304080963135, "global_step": 350381, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1389811038970947, "global_step": 350382, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1440510749816895, "global_step": 350383, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1453819274902344, "global_step": 350384, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1387887001037598, "global_step": 350385, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.095024347305298, "global_step": 350386, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0846033096313477, "global_step": 350387, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1010191440582275, "global_step": 350388, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.097614288330078, "global_step": 350389, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.094329595565796, "global_step": 350390, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0721662044525146, "global_step": 350391, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1369574069976807, "global_step": 350392, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1068246364593506, "global_step": 350393, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.133549451828003, "global_step": 350394, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.134181261062622, "global_step": 350395, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0019431114196777, "global_step": 350396, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1298320293426514, "global_step": 350397, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1112260818481445, "global_step": 350398, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.045754909515381, "global_step": 350399, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.10090970993042, "global_step": 350400, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1358461380004883, "global_step": 350401, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.967711329460144, "global_step": 350402, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.049471855163574, "global_step": 350403, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0848608016967773, "global_step": 350404, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0847556591033936, "global_step": 350405, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1556718349456787, "global_step": 350406, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1358182430267334, "global_step": 350407, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.120695114135742, "global_step": 350408, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1224658489227295, "global_step": 350409, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1810147762298584, "global_step": 350410, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2150979042053223, "global_step": 350411, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0176379680633545, "global_step": 350412, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1689059734344482, "global_step": 350413, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1758227348327637, "global_step": 350414, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1437675952911377, "global_step": 350415, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1517415046691895, "global_step": 350416, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0586485862731934, "global_step": 350417, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.108854055404663, "global_step": 350418, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1943421363830566, "global_step": 350419, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.127560615539551, "global_step": 350420, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.16634464263916, "global_step": 350421, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.086855888366699, "global_step": 350422, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.096414089202881, "global_step": 350423, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.138275623321533, "global_step": 350424, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1265480518341064, "global_step": 350425, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1039199829101562, "global_step": 350426, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.091094732284546, "global_step": 350427, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.122551441192627, "global_step": 350428, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.095870018005371, "global_step": 350429, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1578946113586426, "global_step": 350430, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.046539306640625, "global_step": 350431, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0937206745147705, "global_step": 350432, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.136453151702881, "global_step": 350433, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.179527759552002, "global_step": 350434, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0879204273223877, "global_step": 350435, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.176835536956787, "global_step": 350436, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.146550416946411, "global_step": 350437, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0914902687072754, "global_step": 350438, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.211446762084961, "global_step": 350439, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.144219398498535, "global_step": 350440, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.198737144470215, "global_step": 350441, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0884408950805664, "global_step": 350442, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.094677209854126, "global_step": 350443, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.015932321548462, "global_step": 350444, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1724839210510254, "global_step": 350445, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.115523338317871, "global_step": 350446, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0887362957000732, "global_step": 350447, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.102660655975342, "global_step": 350448, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.126175880432129, "global_step": 350449, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0855085849761963, "global_step": 350450, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2264750003814697, "global_step": 350451, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1840720176696777, "global_step": 350452, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.07724928855896, "global_step": 350453, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0971715450286865, "global_step": 350454, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2173521518707275, "global_step": 350455, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0505971908569336, "global_step": 350456, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0413284301757812, "global_step": 350457, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.124574661254883, "global_step": 350458, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.147278308868408, "global_step": 350459, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.189927101135254, "global_step": 350460, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1151797771453857, "global_step": 350461, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1678357124328613, "global_step": 350462, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0954270362854004, "global_step": 350463, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1459274291992188, "global_step": 350464, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0623373985290527, "global_step": 350465, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.202977418899536, "global_step": 350466, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0362765789031982, "global_step": 350467, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.049548387527466, "global_step": 350468, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1649296283721924, "global_step": 350469, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0413756370544434, "global_step": 350470, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1593472957611084, "global_step": 350471, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.15887188911438, "global_step": 350472, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1538777351379395, "global_step": 350473, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.10387921333313, "global_step": 350474, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.087531805038452, "global_step": 350475, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.118942975997925, "global_step": 350476, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.064487934112549, "global_step": 350477, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.091977596282959, "global_step": 350478, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0580320358276367, "global_step": 350479, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.138695478439331, "global_step": 350480, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1015396118164062, "global_step": 350481, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.090888261795044, "global_step": 350482, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1033082008361816, "global_step": 350483, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1313087940216064, "global_step": 350484, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0323798656463623, "global_step": 350485, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.9942086935043335, "global_step": 350486, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.080721855163574, "global_step": 350487, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.127901077270508, "global_step": 350488, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0329039096832275, "global_step": 350489, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.17429780960083, "global_step": 350490, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.137831449508667, "global_step": 350491, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0983052253723145, "global_step": 350492, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.089010238647461, "global_step": 350493, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.109172821044922, "global_step": 350494, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.090590238571167, "global_step": 350495, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.9930096864700317, "global_step": 350496, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0909347534179688, "global_step": 350497, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0478482246398926, "global_step": 350498, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.963486909866333, "global_step": 350499, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1597068309783936, "global_step": 350500, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.150744676589966, "global_step": 350501, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.072969913482666, "global_step": 350502, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0675272941589355, "global_step": 350503, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.039605140686035, "global_step": 350504, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0704269409179688, "global_step": 350505, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.108332872390747, "global_step": 350506, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2106523513793945, "global_step": 350507, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0901906490325928, "global_step": 350508, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.175462007522583, "global_step": 350509, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1218338012695312, "global_step": 350510, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0706143379211426, "global_step": 350511, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.034465789794922, "global_step": 350512, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.084270715713501, "global_step": 350513, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1719188690185547, "global_step": 350514, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.111858606338501, "global_step": 350515, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1445913314819336, "global_step": 350516, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.084545135498047, "global_step": 350517, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1696255207061768, "global_step": 350518, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.219273328781128, "global_step": 350519, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.050755023956299, "global_step": 350520, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1238279342651367, "global_step": 350521, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0947558879852295, "global_step": 350522, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1742873191833496, "global_step": 350523, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.137007474899292, "global_step": 350524, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.112220287322998, "global_step": 350525, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1431424617767334, "global_step": 350526, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0656380653381348, "global_step": 350527, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1635940074920654, "global_step": 350528, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.109825372695923, "global_step": 350529, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.090907573699951, "global_step": 350530, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.083209753036499, "global_step": 350531, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.125349760055542, "global_step": 350532, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.052166223526001, "global_step": 350533, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.118546724319458, "global_step": 350534, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.053270101547241, "global_step": 350535, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0757839679718018, "global_step": 350536, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.038642168045044, "global_step": 350537, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1754307746887207, "global_step": 350538, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1978015899658203, "global_step": 350539, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.063908576965332, "global_step": 350540, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.125532865524292, "global_step": 350541, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.055974245071411, "global_step": 350542, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.206657648086548, "global_step": 350543, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1501195430755615, "global_step": 350544, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1600685119628906, "global_step": 350545, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1375088691711426, "global_step": 350546, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.152384042739868, "global_step": 350547, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.116741895675659, "global_step": 350548, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0646157264709473, "global_step": 350549, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1295056343078613, "global_step": 350550, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1807284355163574, "global_step": 350551, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.9959847927093506, "global_step": 350552, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.073843240737915, "global_step": 350553, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1352953910827637, "global_step": 350554, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.031132698059082, "global_step": 350555, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.073915958404541, "global_step": 350556, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.081441640853882, "global_step": 350557, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1623449325561523, "global_step": 350558, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1333014965057373, "global_step": 350559, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.106443166732788, "global_step": 350560, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1472136974334717, "global_step": 350561, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.037550926208496, "global_step": 350562, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1120193004608154, "global_step": 350563, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.117260456085205, "global_step": 350564, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.01522159576416, "global_step": 350565, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.038398027420044, "global_step": 350566, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.108975410461426, "global_step": 350567, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.178866386413574, "global_step": 350568, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1364824771881104, "global_step": 350569, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0977447032928467, "global_step": 350570, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1178641319274902, "global_step": 350571, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.122579574584961, "global_step": 350572, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0775887966156006, "global_step": 350573, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0835766792297363, "global_step": 350574, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.122222661972046, "global_step": 350575, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.121356725692749, "global_step": 350576, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0457510948181152, "global_step": 350577, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.14880633354187, "global_step": 350578, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.076011896133423, "global_step": 350579, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1142382621765137, "global_step": 350580, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1264216899871826, "global_step": 350581, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1831326484680176, "global_step": 350582, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1604831218719482, "global_step": 350583, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.159684896469116, "global_step": 350584, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.097686767578125, "global_step": 350585, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1253817081451416, "global_step": 350586, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.032405138015747, "global_step": 350587, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.096226453781128, "global_step": 350588, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.125474214553833, "global_step": 350589, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1244304180145264, "global_step": 350590, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1307520866394043, "global_step": 350591, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0965735912323, "global_step": 350592, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1443514823913574, "global_step": 350593, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1045570373535156, "global_step": 350594, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0510849952697754, "global_step": 350595, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.213257074356079, "global_step": 350596, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0408880710601807, "global_step": 350597, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.011194944381714, "global_step": 350598, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0679757595062256, "global_step": 350599, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.083564519882202, "global_step": 350600, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.100497245788574, "global_step": 350601, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1510097980499268, "global_step": 350602, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1285157203674316, "global_step": 350603, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.039278984069824, "global_step": 350604, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0832114219665527, "global_step": 350605, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0984175205230713, "global_step": 350606, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.110577344894409, "global_step": 350607, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2010254859924316, "global_step": 350608, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.062070608139038, "global_step": 350609, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1586267948150635, "global_step": 350610, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.05490779876709, "global_step": 350611, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.049769163131714, "global_step": 350612, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1615583896636963, "global_step": 350613, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0499119758605957, "global_step": 350614, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.138507843017578, "global_step": 350615, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.036695718765259, "global_step": 350616, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.150620937347412, "global_step": 350617, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1405067443847656, "global_step": 350618, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0456395149230957, "global_step": 350619, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0450150966644287, "global_step": 350620, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1878812313079834, "global_step": 350621, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.065093517303467, "global_step": 350622, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1091606616973877, "global_step": 350623, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.11869740486145, "global_step": 350624, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1440532207489014, "global_step": 350625, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1399402618408203, "global_step": 350626, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1184160709381104, "global_step": 350627, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.129883050918579, "global_step": 350628, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1558761596679688, "global_step": 350629, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0709707736968994, "global_step": 350630, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1484909057617188, "global_step": 350631, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.136749267578125, "global_step": 350632, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0604872703552246, "global_step": 350633, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.107079029083252, "global_step": 350634, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1371209621429443, "global_step": 350635, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0836524963378906, "global_step": 350636, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.047405481338501, "global_step": 350637, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.10174298286438, "global_step": 350638, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0655713081359863, "global_step": 350639, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0960850715637207, "global_step": 350640, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0677785873413086, "global_step": 350641, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.113070011138916, "global_step": 350642, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0410585403442383, "global_step": 350643, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.065471887588501, "global_step": 350644, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0737831592559814, "global_step": 350645, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1031742095947266, "global_step": 350646, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1898672580718994, "global_step": 350647, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.19757080078125, "global_step": 350648, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0785129070281982, "global_step": 350649, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1042754650115967, "global_step": 350650, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2389779090881348, "global_step": 350651, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.145223379135132, "global_step": 350652, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1570026874542236, "global_step": 350653, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0986666679382324, "global_step": 350654, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.145387649536133, "global_step": 350655, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1452114582061768, "global_step": 350656, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1731483936309814, "global_step": 350657, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2102081775665283, "global_step": 350658, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.045696973800659, "global_step": 350659, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0818674564361572, "global_step": 350660, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.229959011077881, "global_step": 350661, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1529242992401123, "global_step": 350662, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1526215076446533, "global_step": 350663, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0175681114196777, "global_step": 350664, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.147404193878174, "global_step": 350665, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0781362056732178, "global_step": 350666, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0262808799743652, "global_step": 350667, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1135826110839844, "global_step": 350668, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1292405128479004, "global_step": 350669, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0880749225616455, "global_step": 350670, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1519036293029785, "global_step": 350671, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1374824047088623, "global_step": 350672, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.156179428100586, "global_step": 350673, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2345025539398193, "global_step": 350674, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1327342987060547, "global_step": 350675, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0443623065948486, "global_step": 350676, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.127034902572632, "global_step": 350677, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.133704662322998, "global_step": 350678, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1133995056152344, "global_step": 350679, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1339550018310547, "global_step": 350680, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.15507435798645, "global_step": 350681, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1411421298980713, "global_step": 350682, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.110333204269409, "global_step": 350683, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1402573585510254, "global_step": 350684, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1221776008605957, "global_step": 350685, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0826103687286377, "global_step": 350686, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1550354957580566, "global_step": 350687, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1608951091766357, "global_step": 350688, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.146545648574829, "global_step": 350689, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1360249519348145, "global_step": 350690, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.137310743331909, "global_step": 350691, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0486583709716797, "global_step": 350692, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2303075790405273, "global_step": 350693, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.114088773727417, "global_step": 350694, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.140247106552124, "global_step": 350695, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.120638132095337, "global_step": 350696, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0606629848480225, "global_step": 350697, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1076624393463135, "global_step": 350698, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1103456020355225, "global_step": 350699, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.245419502258301, "global_step": 350700, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.9989417791366577, "global_step": 350701, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.988759994506836, "global_step": 350702, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0208823680877686, "global_step": 350703, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.105886936187744, "global_step": 350704, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1461081504821777, "global_step": 350705, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1277570724487305, "global_step": 350706, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1305928230285645, "global_step": 350707, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0438878536224365, "global_step": 350708, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0780539512634277, "global_step": 350709, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.145005941390991, "global_step": 350710, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1190128326416016, "global_step": 350711, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.158297300338745, "global_step": 350712, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.163893461227417, "global_step": 350713, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.069307565689087, "global_step": 350714, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0527772903442383, "global_step": 350715, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0730044841766357, "global_step": 350716, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0894877910614014, "global_step": 350717, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.136543035507202, "global_step": 350718, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.111315965652466, "global_step": 350719, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0831949710845947, "global_step": 350720, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.167588710784912, "global_step": 350721, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2646398544311523, "global_step": 350722, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0415244102478027, "global_step": 350723, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.06180739402771, "global_step": 350724, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.164409875869751, "global_step": 350725, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.118169069290161, "global_step": 350726, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0911457538604736, "global_step": 350727, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.098924160003662, "global_step": 350728, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0368103981018066, "global_step": 350729, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.067821979522705, "global_step": 350730, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.124030113220215, "global_step": 350731, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0777769088745117, "global_step": 350732, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0975165367126465, "global_step": 350733, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0667593479156494, "global_step": 350734, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.217883348464966, "global_step": 350735, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.08236026763916, "global_step": 350736, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.029231071472168, "global_step": 350737, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1135644912719727, "global_step": 350738, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1238834857940674, "global_step": 350739, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.108637571334839, "global_step": 350740, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.139005661010742, "global_step": 350741, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1435537338256836, "global_step": 350742, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.097177505493164, "global_step": 350743, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0933334827423096, "global_step": 350744, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.154425621032715, "global_step": 350745, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0881898403167725, "global_step": 350746, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.168553352355957, "global_step": 350747, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1542718410491943, "global_step": 350748, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.188992738723755, "global_step": 350749, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1028666496276855, "global_step": 350750, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1691884994506836, "global_step": 350751, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2093348503112793, "global_step": 350752, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1007747650146484, "global_step": 350753, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.094780921936035, "global_step": 350754, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.128178358078003, "global_step": 350755, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0964863300323486, "global_step": 350756, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1877269744873047, "global_step": 350757, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.09900164604187, "global_step": 350758, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1153719425201416, "global_step": 350759, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1707398891448975, "global_step": 350760, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.156424045562744, "global_step": 350761, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1608850955963135, "global_step": 350762, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.192589521408081, "global_step": 350763, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0838234424591064, "global_step": 350764, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0929911136627197, "global_step": 350765, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0910232067108154, "global_step": 350766, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0232460498809814, "global_step": 350767, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1456542015075684, "global_step": 350768, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2041711807250977, "global_step": 350769, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.103041887283325, "global_step": 350770, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0759758949279785, "global_step": 350771, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0779285430908203, "global_step": 350772, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1018404960632324, "global_step": 350773, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1342825889587402, "global_step": 350774, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.085148572921753, "global_step": 350775, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.086690664291382, "global_step": 350776, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1174466609954834, "global_step": 350777, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1453335285186768, "global_step": 350778, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.157464027404785, "global_step": 350779, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0526466369628906, "global_step": 350780, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.156667947769165, "global_step": 350781, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2504353523254395, "global_step": 350782, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1188676357269287, "global_step": 350783, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.154146194458008, "global_step": 350784, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.096853017807007, "global_step": 350785, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0627198219299316, "global_step": 350786, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.240311861038208, "global_step": 350787, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.171628475189209, "global_step": 350788, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.116436719894409, "global_step": 350789, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.124359607696533, "global_step": 350790, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1045162677764893, "global_step": 350791, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0853052139282227, "global_step": 350792, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.076444387435913, "global_step": 350793, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1568357944488525, "global_step": 350794, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.131742238998413, "global_step": 350795, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.086050271987915, "global_step": 350796, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.105999231338501, "global_step": 350797, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0992507934570312, "global_step": 350798, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2095773220062256, "global_step": 350799, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.134737730026245, "global_step": 350800, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0449280738830566, "global_step": 350801, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.09669828414917, "global_step": 350802, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0172576904296875, "global_step": 350803, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1848957538604736, "global_step": 350804, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1325860023498535, "global_step": 350805, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1203432083129883, "global_step": 350806, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.18611216545105, "global_step": 350807, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.119184732437134, "global_step": 350808, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.155726194381714, "global_step": 350809, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.089107036590576, "global_step": 350810, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.091062545776367, "global_step": 350811, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0732665061950684, "global_step": 350812, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.086589813232422, "global_step": 350813, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1550087928771973, "global_step": 350814, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1649329662323, "global_step": 350815, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1397907733917236, "global_step": 350816, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0272819995880127, "global_step": 350817, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.138441324234009, "global_step": 350818, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0697028636932373, "global_step": 350819, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0797011852264404, "global_step": 350820, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1119186878204346, "global_step": 350821, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1181416511535645, "global_step": 350822, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.098803758621216, "global_step": 350823, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0568997859954834, "global_step": 350824, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.126455068588257, "global_step": 350825, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.107499122619629, "global_step": 350826, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0799219608306885, "global_step": 350827, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.036748170852661, "global_step": 350828, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1218438148498535, "global_step": 350829, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1465797424316406, "global_step": 350830, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1121907234191895, "global_step": 350831, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.150513172149658, "global_step": 350832, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.164525032043457, "global_step": 350833, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1043245792388916, "global_step": 350834, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.045672655105591, "global_step": 350835, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.040710687637329, "global_step": 350836, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.126779794692993, "global_step": 350837, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.096670627593994, "global_step": 350838, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.162384510040283, "global_step": 350839, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.189401626586914, "global_step": 350840, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1038994789123535, "global_step": 350841, "epoch": 711, "lr": 5e-05}
{"train_loss": 1.9660531282424927, "global_step": 350842, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0972490310668945, "global_step": 350843, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.026761054992676, "global_step": 350844, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.054874897003174, "global_step": 350845, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.113294839859009, "global_step": 350846, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1307995319366455, "global_step": 350847, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1195738315582275, "global_step": 350848, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0789499282836914, "global_step": 350849, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.174880027770996, "global_step": 350850, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.17824387550354, "global_step": 350851, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1312496662139893, "global_step": 350852, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1193902492523193, "global_step": 350853, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1367344856262207, "global_step": 350854, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0495104789733887, "global_step": 350855, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1383278369903564, "global_step": 350856, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.164015531539917, "global_step": 350857, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0282280445098877, "global_step": 350858, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1366660594940186, "global_step": 350859, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1436607837677, "global_step": 350860, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.099968433380127, "global_step": 350861, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.164877414703369, "global_step": 350862, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.219456911087036, "global_step": 350863, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0994629859924316, "global_step": 350864, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.017589807510376, "global_step": 350865, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1102161407470703, "global_step": 350866, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0368597507476807, "global_step": 350867, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.103405475616455, "global_step": 350868, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1846463680267334, "global_step": 350869, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.238187789916992, "global_step": 350870, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.133120536804199, "global_step": 350871, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1246554851531982, "global_step": 350872, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0758986473083496, "global_step": 350873, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0056252479553223, "global_step": 350874, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0649776458740234, "global_step": 350875, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0452210903167725, "global_step": 350876, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0986900329589844, "global_step": 350877, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0709776878356934, "global_step": 350878, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1101813316345215, "global_step": 350879, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0886852741241455, "global_step": 350880, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0881574153900146, "global_step": 350881, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.142077684402466, "global_step": 350882, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1317853927612305, "global_step": 350883, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1200225353240967, "global_step": 350884, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.095459222793579, "global_step": 350885, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0584349632263184, "global_step": 350886, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0695815086364746, "global_step": 350887, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1665775775909424, "global_step": 350888, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2159786224365234, "global_step": 350889, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1490044593811035, "global_step": 350890, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1275734901428223, "global_step": 350891, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1349198818206787, "global_step": 350892, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1518890857696533, "global_step": 350893, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1088147163391113, "global_step": 350894, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0136470794677734, "global_step": 350895, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.098926067352295, "global_step": 350896, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1438546180725098, "global_step": 350897, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1635372638702393, "global_step": 350898, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1028401851654053, "global_step": 350899, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.076019763946533, "global_step": 350900, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0375800132751465, "global_step": 350901, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0822763442993164, "global_step": 350902, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.2080771923065186, "global_step": 350903, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1002423763275146, "global_step": 350904, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1891374588012695, "global_step": 350905, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0532805919647217, "global_step": 350906, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.121767520904541, "global_step": 350907, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1508243083953857, "global_step": 350908, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1346890926361084, "global_step": 350909, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.1079161167144775, "global_step": 350910, "epoch": 711, "lr": 5e-05}
{"train_loss": 2.0618362426757812, "global_step": 350911, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.038466453552246, "global_step": 350912, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.168020248413086, "global_step": 350913, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.09285044670105, "global_step": 350914, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0577657222747803, "global_step": 350915, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.169377088546753, "global_step": 350916, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.120654582977295, "global_step": 350917, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.075984477996826, "global_step": 350918, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.9832125902175903, "global_step": 350919, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.121610403060913, "global_step": 350920, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1268198490142822, "global_step": 350921, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0423247814178467, "global_step": 350922, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.069877862930298, "global_step": 350923, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.097834825515747, "global_step": 350924, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.133315324783325, "global_step": 350925, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.027743339538574, "global_step": 350926, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0501272678375244, "global_step": 350927, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0849180221557617, "global_step": 350928, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1007769107818604, "global_step": 350929, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.083820104598999, "global_step": 350930, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0830914974212646, "global_step": 350931, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1120786666870117, "global_step": 350932, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1106481552124023, "global_step": 350933, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0668423175811768, "global_step": 350934, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.115295886993408, "global_step": 350935, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.125910758972168, "global_step": 350936, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.066959857940674, "global_step": 350937, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.147397756576538, "global_step": 350938, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.011747360229492, "global_step": 350939, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0664167404174805, "global_step": 350940, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.158114194869995, "global_step": 350941, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0963547229766846, "global_step": 350942, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.9887174367904663, "global_step": 350943, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0922915935516357, "global_step": 350944, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.045025587081909, "global_step": 350945, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0445683002471924, "global_step": 350946, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.043142557144165, "global_step": 350947, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.051455020904541, "global_step": 350948, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1388580799102783, "global_step": 350949, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1379294395446777, "global_step": 350950, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.9967409372329712, "global_step": 350951, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.069185733795166, "global_step": 350952, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1166563034057617, "global_step": 350953, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.084285259246826, "global_step": 350954, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.9775663614273071, "global_step": 350955, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1529664993286133, "global_step": 350956, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.130842924118042, "global_step": 350957, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0666041374206543, "global_step": 350958, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1251060962677, "global_step": 350959, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0315356254577637, "global_step": 350960, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.9907070398330688, "global_step": 350961, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.114501953125, "global_step": 350962, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1687798500061035, "global_step": 350963, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.127995729446411, "global_step": 350964, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0377299785614014, "global_step": 350965, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.089202642440796, "global_step": 350966, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0449416637420654, "global_step": 350967, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1427149772644043, "global_step": 350968, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.062856674194336, "global_step": 350969, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.16092586517334, "global_step": 350970, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.017068386077881, "global_step": 350971, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.183939218521118, "global_step": 350972, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.121778964996338, "global_step": 350973, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.089266538619995, "global_step": 350974, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1835317611694336, "global_step": 350975, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.039839506149292, "global_step": 350976, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0434024333953857, "global_step": 350977, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.144766330718994, "global_step": 350978, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.059922695159912, "global_step": 350979, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0266942977905273, "global_step": 350980, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.070266008377075, "global_step": 350981, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1732029914855957, "global_step": 350982, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.15140700340271, "global_step": 350983, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1589293479919434, "global_step": 350984, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1779136657714844, "global_step": 350985, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.2249090671539307, "global_step": 350986, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1140317916870117, "global_step": 350987, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.095320463180542, "global_step": 350988, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0396459102630615, "global_step": 350989, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1413729190826416, "global_step": 350990, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.059143543243408, "global_step": 350991, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.058389663696289, "global_step": 350992, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.090007781982422, "global_step": 350993, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0996999740600586, "global_step": 350994, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0490970611572266, "global_step": 350995, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.014137029647827, "global_step": 350996, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.044894218444824, "global_step": 350997, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1810216903686523, "global_step": 350998, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.155940294265747, "global_step": 350999, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.049375295639038, "global_step": 351000, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1347265243530273, "global_step": 351001, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.14433217048645, "global_step": 351002, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0985143184661865, "global_step": 351003, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.136888027191162, "global_step": 351004, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.037033796310425, "global_step": 351005, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0636355876922607, "global_step": 351006, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.071061134338379, "global_step": 351007, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0543744564056396, "global_step": 351008, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0922348499298096, "global_step": 351009, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.122659683227539, "global_step": 351010, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.085458278656006, "global_step": 351011, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.091855764389038, "global_step": 351012, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1184487342834473, "global_step": 351013, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.112103223800659, "global_step": 351014, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.114703893661499, "global_step": 351015, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.070603370666504, "global_step": 351016, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0713882446289062, "global_step": 351017, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.111185073852539, "global_step": 351018, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0091936588287354, "global_step": 351019, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.120386838912964, "global_step": 351020, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.078676223754883, "global_step": 351021, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0725061893463135, "global_step": 351022, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0819287300109863, "global_step": 351023, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.084052801132202, "global_step": 351024, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1256625652313232, "global_step": 351025, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.032925844192505, "global_step": 351026, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.049217939376831, "global_step": 351027, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.064653158187866, "global_step": 351028, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.047231674194336, "global_step": 351029, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.103522539138794, "global_step": 351030, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1057136058807373, "global_step": 351031, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0954630374908447, "global_step": 351032, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0777878761291504, "global_step": 351033, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0970349311828613, "global_step": 351034, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.044281005859375, "global_step": 351035, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.138186454772949, "global_step": 351036, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0372543334960938, "global_step": 351037, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.2056310176849365, "global_step": 351038, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.113267660140991, "global_step": 351039, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.099512815475464, "global_step": 351040, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1181747913360596, "global_step": 351041, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1874594688415527, "global_step": 351042, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.158280611038208, "global_step": 351043, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.11749529838562, "global_step": 351044, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.10839581489563, "global_step": 351045, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.135960340499878, "global_step": 351046, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.122471570968628, "global_step": 351047, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0845139026641846, "global_step": 351048, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1292378902435303, "global_step": 351049, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1517856121063232, "global_step": 351050, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1386821269989014, "global_step": 351051, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.131476879119873, "global_step": 351052, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1656086444854736, "global_step": 351053, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0985193252563477, "global_step": 351054, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0922577381134033, "global_step": 351055, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.187272071838379, "global_step": 351056, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1263155937194824, "global_step": 351057, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0452444553375244, "global_step": 351058, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0696561336517334, "global_step": 351059, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0686402320861816, "global_step": 351060, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1092476844787598, "global_step": 351061, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.17299222946167, "global_step": 351062, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1218066215515137, "global_step": 351063, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.09059739112854, "global_step": 351064, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0259556770324707, "global_step": 351065, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.064521074295044, "global_step": 351066, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.188652753829956, "global_step": 351067, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1072864532470703, "global_step": 351068, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1070492267608643, "global_step": 351069, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.091984272003174, "global_step": 351070, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1197822093963623, "global_step": 351071, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.057858943939209, "global_step": 351072, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1646888256073, "global_step": 351073, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0481176376342773, "global_step": 351074, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.042820692062378, "global_step": 351075, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.193201780319214, "global_step": 351076, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.087191104888916, "global_step": 351077, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.137075424194336, "global_step": 351078, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.101665735244751, "global_step": 351079, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.174830913543701, "global_step": 351080, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.082645893096924, "global_step": 351081, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.116072177886963, "global_step": 351082, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.9438871145248413, "global_step": 351083, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0486814975738525, "global_step": 351084, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0263333320617676, "global_step": 351085, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.059100866317749, "global_step": 351086, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1401262283325195, "global_step": 351087, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0364608764648438, "global_step": 351088, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.071119785308838, "global_step": 351089, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.096893787384033, "global_step": 351090, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1172449588775635, "global_step": 351091, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1301684379577637, "global_step": 351092, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.124455690383911, "global_step": 351093, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1979522705078125, "global_step": 351094, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.107400417327881, "global_step": 351095, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.213834047317505, "global_step": 351096, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0683510303497314, "global_step": 351097, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.064601182937622, "global_step": 351098, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1626174449920654, "global_step": 351099, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0655112266540527, "global_step": 351100, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0866775512695312, "global_step": 351101, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1658616065979004, "global_step": 351102, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.052877426147461, "global_step": 351103, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.19960618019104, "global_step": 351104, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.9443883895874023, "global_step": 351105, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.148430824279785, "global_step": 351106, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1654632091522217, "global_step": 351107, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0884110927581787, "global_step": 351108, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.079951524734497, "global_step": 351109, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0644757747650146, "global_step": 351110, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1236400604248047, "global_step": 351111, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.071683406829834, "global_step": 351112, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0250704288482666, "global_step": 351113, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1071865558624268, "global_step": 351114, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.083631753921509, "global_step": 351115, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.2159297466278076, "global_step": 351116, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.112717390060425, "global_step": 351117, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.093799352645874, "global_step": 351118, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.9872655868530273, "global_step": 351119, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0988659858703613, "global_step": 351120, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1228880882263184, "global_step": 351121, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1030590534210205, "global_step": 351122, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1173245906829834, "global_step": 351123, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0930848121643066, "global_step": 351124, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0735883712768555, "global_step": 351125, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0604934692382812, "global_step": 351126, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.137282133102417, "global_step": 351127, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.074091911315918, "global_step": 351128, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.082273244857788, "global_step": 351129, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.177034378051758, "global_step": 351130, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.136129379272461, "global_step": 351131, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.107374429702759, "global_step": 351132, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.2050044536590576, "global_step": 351133, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.155893564224243, "global_step": 351134, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.192930221557617, "global_step": 351135, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1804988384246826, "global_step": 351136, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.131843328475952, "global_step": 351137, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.108351945877075, "global_step": 351138, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.093674898147583, "global_step": 351139, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1477530002593994, "global_step": 351140, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.2118053436279297, "global_step": 351141, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0856196880340576, "global_step": 351142, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.056342124938965, "global_step": 351143, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.032588481903076, "global_step": 351144, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.9981414079666138, "global_step": 351145, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0496480464935303, "global_step": 351146, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.064453601837158, "global_step": 351147, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1740105152130127, "global_step": 351148, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0506889820098877, "global_step": 351149, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.963672399520874, "global_step": 351150, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1795384883880615, "global_step": 351151, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0998029708862305, "global_step": 351152, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1485867500305176, "global_step": 351153, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1961610317230225, "global_step": 351154, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.966741919517517, "global_step": 351155, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.121638298034668, "global_step": 351156, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1442856788635254, "global_step": 351157, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1055715084075928, "global_step": 351158, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1329941749572754, "global_step": 351159, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0174317359924316, "global_step": 351160, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.081678867340088, "global_step": 351161, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1600775718688965, "global_step": 351162, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.2229678630828857, "global_step": 351163, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.120760202407837, "global_step": 351164, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1641130447387695, "global_step": 351165, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.077791452407837, "global_step": 351166, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.122809410095215, "global_step": 351167, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1642889976501465, "global_step": 351168, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0799202919006348, "global_step": 351169, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.075312614440918, "global_step": 351170, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1298625469207764, "global_step": 351171, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0668013095855713, "global_step": 351172, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.170316696166992, "global_step": 351173, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0969059467315674, "global_step": 351174, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1040074825286865, "global_step": 351175, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0687668323516846, "global_step": 351176, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.155970573425293, "global_step": 351177, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.112698554992676, "global_step": 351178, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1260361671447754, "global_step": 351179, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0825703144073486, "global_step": 351180, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.052879571914673, "global_step": 351181, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.057680368423462, "global_step": 351182, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.2337486743927, "global_step": 351183, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1149280071258545, "global_step": 351184, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.028559923171997, "global_step": 351185, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0612845420837402, "global_step": 351186, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.159132242202759, "global_step": 351187, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.129976511001587, "global_step": 351188, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.2172632217407227, "global_step": 351189, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.084872245788574, "global_step": 351190, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1477575302124023, "global_step": 351191, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1128053665161133, "global_step": 351192, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1132421493530273, "global_step": 351193, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1056251525878906, "global_step": 351194, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.141941547393799, "global_step": 351195, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1677796840667725, "global_step": 351196, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1490864753723145, "global_step": 351197, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0655205249786377, "global_step": 351198, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0646870136260986, "global_step": 351199, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1381542682647705, "global_step": 351200, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.15303373336792, "global_step": 351201, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.054630756378174, "global_step": 351202, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.145528554916382, "global_step": 351203, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.022322654724121, "global_step": 351204, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.07835054397583, "global_step": 351205, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.142608880996704, "global_step": 351206, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.120723009109497, "global_step": 351207, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1771860122680664, "global_step": 351208, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1509029865264893, "global_step": 351209, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1230709552764893, "global_step": 351210, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.106095314025879, "global_step": 351211, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.070373058319092, "global_step": 351212, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.103977680206299, "global_step": 351213, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1513946056365967, "global_step": 351214, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.18379545211792, "global_step": 351215, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.096031427383423, "global_step": 351216, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1589701175689697, "global_step": 351217, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0827982425689697, "global_step": 351218, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1384711265563965, "global_step": 351219, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.126049518585205, "global_step": 351220, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0821757316589355, "global_step": 351221, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1267309188842773, "global_step": 351222, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.059113025665283, "global_step": 351223, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.10587215423584, "global_step": 351224, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.126859426498413, "global_step": 351225, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.101506233215332, "global_step": 351226, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0534987449645996, "global_step": 351227, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0869393348693848, "global_step": 351228, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.086148500442505, "global_step": 351229, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0832931995391846, "global_step": 351230, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0857999324798584, "global_step": 351231, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1815779209136963, "global_step": 351232, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0668110847473145, "global_step": 351233, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1320652961730957, "global_step": 351234, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1236953735351562, "global_step": 351235, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1240651607513428, "global_step": 351236, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.092245101928711, "global_step": 351237, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.031097173690796, "global_step": 351238, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.156358003616333, "global_step": 351239, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1176822185516357, "global_step": 351240, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.142110586166382, "global_step": 351241, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1592609882354736, "global_step": 351242, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0999844074249268, "global_step": 351243, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0664777755737305, "global_step": 351244, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.060861349105835, "global_step": 351245, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.119978427886963, "global_step": 351246, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1719703674316406, "global_step": 351247, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0694491863250732, "global_step": 351248, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.132540464401245, "global_step": 351249, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0698814392089844, "global_step": 351250, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0598957538604736, "global_step": 351251, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0815322399139404, "global_step": 351252, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1865057945251465, "global_step": 351253, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.9967421293258667, "global_step": 351254, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0973904132843018, "global_step": 351255, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.101362943649292, "global_step": 351256, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1900384426116943, "global_step": 351257, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0154948234558105, "global_step": 351258, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0249738693237305, "global_step": 351259, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1221587657928467, "global_step": 351260, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1915807723999023, "global_step": 351261, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.100965738296509, "global_step": 351262, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.078665018081665, "global_step": 351263, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.177375316619873, "global_step": 351264, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1063647270202637, "global_step": 351265, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1435189247131348, "global_step": 351266, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1169166564941406, "global_step": 351267, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.030484914779663, "global_step": 351268, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1353046894073486, "global_step": 351269, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0490076541900635, "global_step": 351270, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1408660411834717, "global_step": 351271, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.035071611404419, "global_step": 351272, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1709139347076416, "global_step": 351273, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0798592567443848, "global_step": 351274, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.022892951965332, "global_step": 351275, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1252832412719727, "global_step": 351276, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.089660406112671, "global_step": 351277, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0968477725982666, "global_step": 351278, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1650619506835938, "global_step": 351279, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.112539291381836, "global_step": 351280, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.120037078857422, "global_step": 351281, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.133699417114258, "global_step": 351282, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1555514335632324, "global_step": 351283, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.196152925491333, "global_step": 351284, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.159754514694214, "global_step": 351285, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0681965351104736, "global_step": 351286, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.114968776702881, "global_step": 351287, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0639586448669434, "global_step": 351288, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0645384788513184, "global_step": 351289, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0539331436157227, "global_step": 351290, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0525879859924316, "global_step": 351291, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.168208122253418, "global_step": 351292, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1893234252929688, "global_step": 351293, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1767337322235107, "global_step": 351294, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.069777250289917, "global_step": 351295, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0772480964660645, "global_step": 351296, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0846407413482666, "global_step": 351297, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1437346935272217, "global_step": 351298, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0712990760803223, "global_step": 351299, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0700063705444336, "global_step": 351300, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1333210468292236, "global_step": 351301, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1288838386535645, "global_step": 351302, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.2022151947021484, "global_step": 351303, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.163386821746826, "global_step": 351304, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0941598415374756, "global_step": 351305, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.124953269958496, "global_step": 351306, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.091742515563965, "global_step": 351307, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1212666034698486, "global_step": 351308, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0694198608398438, "global_step": 351309, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.120378017425537, "global_step": 351310, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1206488609313965, "global_step": 351311, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.088456869125366, "global_step": 351312, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1090621948242188, "global_step": 351313, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.070038080215454, "global_step": 351314, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.171574592590332, "global_step": 351315, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1298375129699707, "global_step": 351316, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.223180055618286, "global_step": 351317, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0528721809387207, "global_step": 351318, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.062910318374634, "global_step": 351319, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1195456981658936, "global_step": 351320, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1024880409240723, "global_step": 351321, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.146091938018799, "global_step": 351322, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1041476726531982, "global_step": 351323, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.005497455596924, "global_step": 351324, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0526282787323, "global_step": 351325, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0543806552886963, "global_step": 351326, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1390187740325928, "global_step": 351327, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.086977958679199, "global_step": 351328, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.10253643989563, "global_step": 351329, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1344454288482666, "global_step": 351330, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0752007961273193, "global_step": 351331, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.206156015396118, "global_step": 351332, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1656293869018555, "global_step": 351333, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1279852390289307, "global_step": 351334, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1737923622131348, "global_step": 351335, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0067713260650635, "global_step": 351336, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1237399578094482, "global_step": 351337, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0796918869018555, "global_step": 351338, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.146519660949707, "global_step": 351339, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0821573734283447, "global_step": 351340, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.195523262023926, "global_step": 351341, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.151956558227539, "global_step": 351342, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0993518829345703, "global_step": 351343, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0888028144836426, "global_step": 351344, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.088287591934204, "global_step": 351345, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0798308849334717, "global_step": 351346, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.191955327987671, "global_step": 351347, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.16833233833313, "global_step": 351348, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.085446834564209, "global_step": 351349, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.047194719314575, "global_step": 351350, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.05049204826355, "global_step": 351351, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.082498788833618, "global_step": 351352, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1789915561676025, "global_step": 351353, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.166766881942749, "global_step": 351354, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1167683601379395, "global_step": 351355, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0079221725463867, "global_step": 351356, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1236095428466797, "global_step": 351357, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1030447483062744, "global_step": 351358, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.207364797592163, "global_step": 351359, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1389899253845215, "global_step": 351360, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0726871490478516, "global_step": 351361, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0404179096221924, "global_step": 351362, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.2004222869873047, "global_step": 351363, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.090247869491577, "global_step": 351364, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1611247062683105, "global_step": 351365, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.127119541168213, "global_step": 351366, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.189861297607422, "global_step": 351367, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.097539186477661, "global_step": 351368, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1058108806610107, "global_step": 351369, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1577515602111816, "global_step": 351370, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0700809955596924, "global_step": 351371, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.172454595565796, "global_step": 351372, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1095244884490967, "global_step": 351373, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.141580820083618, "global_step": 351374, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0151312351226807, "global_step": 351375, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.001755952835083, "global_step": 351376, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1043457984924316, "global_step": 351377, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1618731021881104, "global_step": 351378, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0699257850646973, "global_step": 351379, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.2155113220214844, "global_step": 351380, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.118975877761841, "global_step": 351381, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.9647945165634155, "global_step": 351382, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0893948078155518, "global_step": 351383, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0138144493103027, "global_step": 351384, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1418745517730713, "global_step": 351385, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0354115962982178, "global_step": 351386, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.038898468017578, "global_step": 351387, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.155057668685913, "global_step": 351388, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0771894454956055, "global_step": 351389, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0828866958618164, "global_step": 351390, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.113121747970581, "global_step": 351391, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.128527879714966, "global_step": 351392, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.12080454826355, "global_step": 351393, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0808260440826416, "global_step": 351394, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.115891695022583, "global_step": 351395, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0969343185424805, "global_step": 351396, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.077939510345459, "global_step": 351397, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.149113893508911, "global_step": 351398, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0896427631378174, "global_step": 351399, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.180945634841919, "global_step": 351400, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1030685901641846, "global_step": 351401, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0349555015563965, "global_step": 351402, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0846469402313232, "global_step": 351403, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.122779369354248, "global_step": 351404, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0085647106170654, "global_step": 351405, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1462392807006836, "global_step": 351406, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1984739303588867, "global_step": 351407, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1540937423706055, "global_step": 351408, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.065282106399536, "global_step": 351409, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.102830410003662, "global_step": 351410, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.127668857574463, "global_step": 351411, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.117220401763916, "global_step": 351412, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.9839922189712524, "global_step": 351413, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.064232349395752, "global_step": 351414, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1543643474578857, "global_step": 351415, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1758041381835938, "global_step": 351416, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0731170177459717, "global_step": 351417, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.070420265197754, "global_step": 351418, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1398849487304688, "global_step": 351419, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1419811248779297, "global_step": 351420, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.234034538269043, "global_step": 351421, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1283254623413086, "global_step": 351422, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.091809034347534, "global_step": 351423, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0732715129852295, "global_step": 351424, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1204166412353516, "global_step": 351425, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0892062187194824, "global_step": 351426, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.10827898979187, "global_step": 351427, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0692298412323, "global_step": 351428, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.123558521270752, "global_step": 351429, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.107161283493042, "global_step": 351430, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.114123821258545, "global_step": 351431, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1546120643615723, "global_step": 351432, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0924015045166016, "global_step": 351433, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1530442237854004, "global_step": 351434, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.09122633934021, "global_step": 351435, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.026075839996338, "global_step": 351436, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.12321138381958, "global_step": 351437, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1057705879211426, "global_step": 351438, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1228957176208496, "global_step": 351439, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1100196838378906, "global_step": 351440, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.081287384033203, "global_step": 351441, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1325509548187256, "global_step": 351442, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1161880493164062, "global_step": 351443, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.101262331008911, "global_step": 351444, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1214516162872314, "global_step": 351445, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1413397789001465, "global_step": 351446, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.151531219482422, "global_step": 351447, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1833372116088867, "global_step": 351448, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1515543460845947, "global_step": 351449, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.2353789806365967, "global_step": 351450, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1877377033233643, "global_step": 351451, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.078613042831421, "global_step": 351452, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.023519992828369, "global_step": 351453, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0113208293914795, "global_step": 351454, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0178213119506836, "global_step": 351455, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1692442893981934, "global_step": 351456, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.193396806716919, "global_step": 351457, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.052600860595703, "global_step": 351458, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0620806217193604, "global_step": 351459, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1792619228363037, "global_step": 351460, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1232283115386963, "global_step": 351461, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.117713212966919, "global_step": 351462, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.140340566635132, "global_step": 351463, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1346170902252197, "global_step": 351464, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.212723731994629, "global_step": 351465, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.9501410722732544, "global_step": 351466, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1083600521087646, "global_step": 351467, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.14473557472229, "global_step": 351468, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1486928462982178, "global_step": 351469, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.044171094894409, "global_step": 351470, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.018796920776367, "global_step": 351471, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.082625389099121, "global_step": 351472, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.100975275039673, "global_step": 351473, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.087672472000122, "global_step": 351474, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0787875652313232, "global_step": 351475, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1135151386260986, "global_step": 351476, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0227315425872803, "global_step": 351477, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0286309719085693, "global_step": 351478, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.083711624145508, "global_step": 351479, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.195859670639038, "global_step": 351480, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0380446910858154, "global_step": 351481, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.170832872390747, "global_step": 351482, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.095372200012207, "global_step": 351483, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0714635848999023, "global_step": 351484, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.114314317703247, "global_step": 351485, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.009706497192383, "global_step": 351486, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.19389271736145, "global_step": 351487, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.103315591812134, "global_step": 351488, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.021350383758545, "global_step": 351489, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.145892381668091, "global_step": 351490, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.119647979736328, "global_step": 351491, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.018195152282715, "global_step": 351492, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1765153408050537, "global_step": 351493, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1464178562164307, "global_step": 351494, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0998175144195557, "global_step": 351495, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.274402618408203, "global_step": 351496, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.068751096725464, "global_step": 351497, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0967507362365723, "global_step": 351498, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0533034801483154, "global_step": 351499, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.105067014694214, "global_step": 351500, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.21201491355896, "global_step": 351501, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.134692668914795, "global_step": 351502, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.024723529815674, "global_step": 351503, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1938769817352295, "global_step": 351504, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1415231227874756, "global_step": 351505, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.084249973297119, "global_step": 351506, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.167529821395874, "global_step": 351507, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1435060501098633, "global_step": 351508, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.100109100341797, "global_step": 351509, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0452842712402344, "global_step": 351510, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0490500926971436, "global_step": 351511, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1579651832580566, "global_step": 351512, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.110427141189575, "global_step": 351513, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0931105613708496, "global_step": 351514, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.142373561859131, "global_step": 351515, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0017478466033936, "global_step": 351516, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1262354850769043, "global_step": 351517, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.090121269226074, "global_step": 351518, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.094419240951538, "global_step": 351519, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1808252334594727, "global_step": 351520, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.033583402633667, "global_step": 351521, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.044447422027588, "global_step": 351522, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1104915142059326, "global_step": 351523, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1026387214660645, "global_step": 351524, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.071413993835449, "global_step": 351525, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0990545749664307, "global_step": 351526, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1396920680999756, "global_step": 351527, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.013881206512451, "global_step": 351528, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1056737899780273, "global_step": 351529, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1794445514678955, "global_step": 351530, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.184272050857544, "global_step": 351531, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1697998046875, "global_step": 351532, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.20352840423584, "global_step": 351533, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.119246006011963, "global_step": 351534, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.110320806503296, "global_step": 351535, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0214154720306396, "global_step": 351536, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0985608100891113, "global_step": 351537, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.244814872741699, "global_step": 351538, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.153718948364258, "global_step": 351539, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0079452991485596, "global_step": 351540, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1739461421966553, "global_step": 351541, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.038649082183838, "global_step": 351542, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1288294792175293, "global_step": 351543, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1723620891571045, "global_step": 351544, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.085029363632202, "global_step": 351545, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1369192600250244, "global_step": 351546, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.170724391937256, "global_step": 351547, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.138481616973877, "global_step": 351548, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1352648735046387, "global_step": 351549, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1196954250335693, "global_step": 351550, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0995419025421143, "global_step": 351551, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1198439598083496, "global_step": 351552, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1234939098358154, "global_step": 351553, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0827083587646484, "global_step": 351554, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1200220584869385, "global_step": 351555, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1563262939453125, "global_step": 351556, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1200923919677734, "global_step": 351557, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0929713249206543, "global_step": 351558, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0519165992736816, "global_step": 351559, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0829451084136963, "global_step": 351560, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.096949338912964, "global_step": 351561, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1471025943756104, "global_step": 351562, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0982818603515625, "global_step": 351563, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1002116203308105, "global_step": 351564, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0226495265960693, "global_step": 351565, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.105774164199829, "global_step": 351566, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.161804676055908, "global_step": 351567, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.113081216812134, "global_step": 351568, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1312990188598633, "global_step": 351569, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0923871994018555, "global_step": 351570, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.178633213043213, "global_step": 351571, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0943448543548584, "global_step": 351572, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1851091384887695, "global_step": 351573, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.113630771636963, "global_step": 351574, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1687405109405518, "global_step": 351575, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0894525051116943, "global_step": 351576, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.132819890975952, "global_step": 351577, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1230130195617676, "global_step": 351578, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1504316329956055, "global_step": 351579, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.040808916091919, "global_step": 351580, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0993432998657227, "global_step": 351581, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1103944778442383, "global_step": 351582, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0660083293914795, "global_step": 351583, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.151228666305542, "global_step": 351584, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1638596057891846, "global_step": 351585, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1150283813476562, "global_step": 351586, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1639599800109863, "global_step": 351587, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1921613216400146, "global_step": 351588, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.038888454437256, "global_step": 351589, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0638856887817383, "global_step": 351590, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.068561315536499, "global_step": 351591, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.146453380584717, "global_step": 351592, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.149960517883301, "global_step": 351593, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.2052083015441895, "global_step": 351594, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.2260239124298096, "global_step": 351595, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.111020088195801, "global_step": 351596, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1108345985412598, "global_step": 351597, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0319137573242188, "global_step": 351598, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.062870502471924, "global_step": 351599, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1798834800720215, "global_step": 351600, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.08615779876709, "global_step": 351601, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1140315532684326, "global_step": 351602, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.046748161315918, "global_step": 351603, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.101111650466919, "global_step": 351604, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.14713716506958, "global_step": 351605, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.121619939804077, "global_step": 351606, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1001548767089844, "global_step": 351607, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.123737096786499, "global_step": 351608, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.123969316482544, "global_step": 351609, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1551620960235596, "global_step": 351610, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.122868061065674, "global_step": 351611, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.112867593765259, "global_step": 351612, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1784844398498535, "global_step": 351613, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.128964424133301, "global_step": 351614, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0795164108276367, "global_step": 351615, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0849759578704834, "global_step": 351616, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.177321672439575, "global_step": 351617, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.166594982147217, "global_step": 351618, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.121579647064209, "global_step": 351619, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0671119689941406, "global_step": 351620, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.025935173034668, "global_step": 351621, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1279237270355225, "global_step": 351622, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1426520347595215, "global_step": 351623, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.03385329246521, "global_step": 351624, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1011030673980713, "global_step": 351625, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1569764614105225, "global_step": 351626, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1393651962280273, "global_step": 351627, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.062587022781372, "global_step": 351628, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1415438652038574, "global_step": 351629, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.082869291305542, "global_step": 351630, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0423145294189453, "global_step": 351631, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.081657648086548, "global_step": 351632, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0695855617523193, "global_step": 351633, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1606192588806152, "global_step": 351634, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.101511240005493, "global_step": 351635, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0815272331237793, "global_step": 351636, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.132951259613037, "global_step": 351637, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.2011044025421143, "global_step": 351638, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.15836238861084, "global_step": 351639, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1067800521850586, "global_step": 351640, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1729047298431396, "global_step": 351641, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.100372076034546, "global_step": 351642, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0989699363708496, "global_step": 351643, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0944647789001465, "global_step": 351644, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1038801670074463, "global_step": 351645, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.098078727722168, "global_step": 351646, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.047196865081787, "global_step": 351647, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1576132774353027, "global_step": 351648, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1603779792785645, "global_step": 351649, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0680456161499023, "global_step": 351650, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.071425437927246, "global_step": 351651, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1022584438323975, "global_step": 351652, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.185765266418457, "global_step": 351653, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.146005392074585, "global_step": 351654, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0797665119171143, "global_step": 351655, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0549981594085693, "global_step": 351656, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.023231267929077, "global_step": 351657, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0406529903411865, "global_step": 351658, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.096959352493286, "global_step": 351659, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.092871904373169, "global_step": 351660, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0551881790161133, "global_step": 351661, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0523483753204346, "global_step": 351662, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1438186168670654, "global_step": 351663, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.14217472076416, "global_step": 351664, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1118240356445312, "global_step": 351665, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0203020572662354, "global_step": 351666, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1692845821380615, "global_step": 351667, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.031163215637207, "global_step": 351668, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0774879455566406, "global_step": 351669, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.087407112121582, "global_step": 351670, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.093310832977295, "global_step": 351671, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0906012058258057, "global_step": 351672, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1118075847625732, "global_step": 351673, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1717703342437744, "global_step": 351674, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.089092493057251, "global_step": 351675, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1661996841430664, "global_step": 351676, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1256110668182373, "global_step": 351677, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.034125566482544, "global_step": 351678, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.097848892211914, "global_step": 351679, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.13358736038208, "global_step": 351680, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.11673641204834, "global_step": 351681, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0534496307373047, "global_step": 351682, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.187626361846924, "global_step": 351683, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0407230854034424, "global_step": 351684, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.084712505340576, "global_step": 351685, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.072370767593384, "global_step": 351686, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.073242664337158, "global_step": 351687, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.154449462890625, "global_step": 351688, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1466617584228516, "global_step": 351689, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1302390098571777, "global_step": 351690, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1711485385894775, "global_step": 351691, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.143165111541748, "global_step": 351692, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0367462635040283, "global_step": 351693, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1371023654937744, "global_step": 351694, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.089658498764038, "global_step": 351695, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1979901790618896, "global_step": 351696, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.152682065963745, "global_step": 351697, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1732497215270996, "global_step": 351698, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1864535808563232, "global_step": 351699, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.159045696258545, "global_step": 351700, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.050455093383789, "global_step": 351701, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1061019897460938, "global_step": 351702, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.123619794845581, "global_step": 351703, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1218559741973877, "global_step": 351704, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.129564046859741, "global_step": 351705, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0413150787353516, "global_step": 351706, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1085541248321533, "global_step": 351707, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0482494831085205, "global_step": 351708, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1064610481262207, "global_step": 351709, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1272504329681396, "global_step": 351710, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.085446357727051, "global_step": 351711, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0587525367736816, "global_step": 351712, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1274333000183105, "global_step": 351713, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0374505519866943, "global_step": 351714, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1328024864196777, "global_step": 351715, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.134751796722412, "global_step": 351716, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.2074368000030518, "global_step": 351717, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.082432985305786, "global_step": 351718, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.119866371154785, "global_step": 351719, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.065701961517334, "global_step": 351720, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.048910140991211, "global_step": 351721, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.2092702388763428, "global_step": 351722, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.107177972793579, "global_step": 351723, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0893402099609375, "global_step": 351724, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.11981201171875, "global_step": 351725, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1298105716705322, "global_step": 351726, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.113334894180298, "global_step": 351727, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.07249116897583, "global_step": 351728, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0776243209838867, "global_step": 351729, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0807855129241943, "global_step": 351730, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0158963203430176, "global_step": 351731, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.134960651397705, "global_step": 351732, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0381951332092285, "global_step": 351733, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.130986452102661, "global_step": 351734, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1809520721435547, "global_step": 351735, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0849084854125977, "global_step": 351736, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0987601280212402, "global_step": 351737, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0498385429382324, "global_step": 351738, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0425076484680176, "global_step": 351739, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1178882122039795, "global_step": 351740, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1226987838745117, "global_step": 351741, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1387569904327393, "global_step": 351742, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.2200095653533936, "global_step": 351743, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.201181650161743, "global_step": 351744, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.123356819152832, "global_step": 351745, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0598814487457275, "global_step": 351746, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.086637020111084, "global_step": 351747, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.225112199783325, "global_step": 351748, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0613903999328613, "global_step": 351749, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1044857501983643, "global_step": 351750, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0906822681427, "global_step": 351751, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0774986743927, "global_step": 351752, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1074113845825195, "global_step": 351753, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0563247203826904, "global_step": 351754, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1017160415649414, "global_step": 351755, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1275079250335693, "global_step": 351756, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1348676681518555, "global_step": 351757, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0535759925842285, "global_step": 351758, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1377413272857666, "global_step": 351759, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0852818489074707, "global_step": 351760, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1248414516448975, "global_step": 351761, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.053093910217285, "global_step": 351762, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.9682800769805908, "global_step": 351763, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.151001214981079, "global_step": 351764, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1137351989746094, "global_step": 351765, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0705177783966064, "global_step": 351766, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1388630867004395, "global_step": 351767, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0667669773101807, "global_step": 351768, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.005190849304199, "global_step": 351769, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.160919189453125, "global_step": 351770, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.11954402923584, "global_step": 351771, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1381216049194336, "global_step": 351772, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.176612615585327, "global_step": 351773, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0819292068481445, "global_step": 351774, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1319355964660645, "global_step": 351775, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1628878116607666, "global_step": 351776, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.238238573074341, "global_step": 351777, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0988621711730957, "global_step": 351778, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1996564865112305, "global_step": 351779, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0394551753997803, "global_step": 351780, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0683770179748535, "global_step": 351781, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1725616455078125, "global_step": 351782, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1240415573120117, "global_step": 351783, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0798556804656982, "global_step": 351784, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.102583646774292, "global_step": 351785, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.155083179473877, "global_step": 351786, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.095278263092041, "global_step": 351787, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1422886848449707, "global_step": 351788, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.116610288619995, "global_step": 351789, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.9839093685150146, "global_step": 351790, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.108604669570923, "global_step": 351791, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.158984422683716, "global_step": 351792, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0610649585723877, "global_step": 351793, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1816892623901367, "global_step": 351794, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1079792976379395, "global_step": 351795, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.112145185470581, "global_step": 351796, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.007629632949829, "global_step": 351797, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.170581579208374, "global_step": 351798, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1279070377349854, "global_step": 351799, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.11740779876709, "global_step": 351800, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.035144805908203, "global_step": 351801, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.174997568130493, "global_step": 351802, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.136075735092163, "global_step": 351803, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.019758701324463, "global_step": 351804, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0607106685638428, "global_step": 351805, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0865094661712646, "global_step": 351806, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1546690464019775, "global_step": 351807, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.181407928466797, "global_step": 351808, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0464742183685303, "global_step": 351809, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.118293523788452, "global_step": 351810, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.07602858543396, "global_step": 351811, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.137974977493286, "global_step": 351812, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0477049350738525, "global_step": 351813, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1097471714019775, "global_step": 351814, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0604097843170166, "global_step": 351815, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0652902126312256, "global_step": 351816, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0589826107025146, "global_step": 351817, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1644465923309326, "global_step": 351818, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.9329785108566284, "global_step": 351819, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.134148359298706, "global_step": 351820, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1216609477996826, "global_step": 351821, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.081327438354492, "global_step": 351822, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0869290828704834, "global_step": 351823, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.9610874652862549, "global_step": 351824, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1521291732788086, "global_step": 351825, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.095806360244751, "global_step": 351826, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1419711112976074, "global_step": 351827, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0983901023864746, "global_step": 351828, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.082826852798462, "global_step": 351829, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1219863891601562, "global_step": 351830, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1175334453582764, "global_step": 351831, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.089261770248413, "global_step": 351832, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0471973419189453, "global_step": 351833, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.117455244064331, "global_step": 351834, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1249196529388428, "global_step": 351835, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.070482015609741, "global_step": 351836, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0332696437835693, "global_step": 351837, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.112452745437622, "global_step": 351838, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1080660820007324, "global_step": 351839, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1379668712615967, "global_step": 351840, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.131330728530884, "global_step": 351841, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.160968065261841, "global_step": 351842, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.145556688308716, "global_step": 351843, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1434950828552246, "global_step": 351844, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.218864917755127, "global_step": 351845, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1258206367492676, "global_step": 351846, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.054036855697632, "global_step": 351847, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0638341903686523, "global_step": 351848, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0860579013824463, "global_step": 351849, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.128509759902954, "global_step": 351850, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0379815101623535, "global_step": 351851, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.171299695968628, "global_step": 351852, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1594598293304443, "global_step": 351853, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.138033628463745, "global_step": 351854, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.9907230138778687, "global_step": 351855, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0253586769104004, "global_step": 351856, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.060809373855591, "global_step": 351857, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.172407388687134, "global_step": 351858, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.142770767211914, "global_step": 351859, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1148195266723633, "global_step": 351860, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1068294048309326, "global_step": 351861, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.13020396232605, "global_step": 351862, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1021063327789307, "global_step": 351863, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1610777378082275, "global_step": 351864, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1547417640686035, "global_step": 351865, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.2375078201293945, "global_step": 351866, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1316449642181396, "global_step": 351867, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.0810163021087646, "global_step": 351868, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1539947986602783, "global_step": 351869, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1556811332702637, "global_step": 351870, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1260745525360107, "global_step": 351871, "epoch": 712, "lr": 5e-05}
{"train_loss": 1.9990500211715698, "global_step": 351872, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.142220973968506, "global_step": 351873, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.081968307495117, "global_step": 351874, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.106635332107544, "global_step": 351875, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1082870960235596, "global_step": 351876, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.119302988052368, "global_step": 351877, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.183302879333496, "global_step": 351878, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.1069273948669434, "global_step": 351879, "epoch": 712, "lr": 5e-05}
{"train_loss": 2.19299054145813, "global_step": 351880, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.090756893157959, "global_step": 351881, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.009273052215576, "global_step": 351882, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1076817512512207, "global_step": 351883, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.141810894012451, "global_step": 351884, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1368443965911865, "global_step": 351885, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1398494243621826, "global_step": 351886, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.107311487197876, "global_step": 351887, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1075856685638428, "global_step": 351888, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.014101028442383, "global_step": 351889, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1061244010925293, "global_step": 351890, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.145188570022583, "global_step": 351891, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0552473068237305, "global_step": 351892, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0555124282836914, "global_step": 351893, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.148174524307251, "global_step": 351894, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.084442615509033, "global_step": 351895, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.107977867126465, "global_step": 351896, "epoch": 713, "lr": 5e-05}
{"train_loss": 1.9962831735610962, "global_step": 351897, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1287765502929688, "global_step": 351898, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.090254068374634, "global_step": 351899, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.2148451805114746, "global_step": 351900, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0839810371398926, "global_step": 351901, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1070916652679443, "global_step": 351902, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.117581605911255, "global_step": 351903, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.199819803237915, "global_step": 351904, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.083799362182617, "global_step": 351905, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1261024475097656, "global_step": 351906, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.127802610397339, "global_step": 351907, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.148486614227295, "global_step": 351908, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.173859119415283, "global_step": 351909, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1110618114471436, "global_step": 351910, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.128692388534546, "global_step": 351911, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.154829502105713, "global_step": 351912, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.001863479614258, "global_step": 351913, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.060417413711548, "global_step": 351914, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.019134521484375, "global_step": 351915, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1676669120788574, "global_step": 351916, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1397597789764404, "global_step": 351917, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.190800666809082, "global_step": 351918, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.040947437286377, "global_step": 351919, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.079531669616699, "global_step": 351920, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0796525478363037, "global_step": 351921, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0642943382263184, "global_step": 351922, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.033994674682617, "global_step": 351923, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0261151790618896, "global_step": 351924, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1014564037323, "global_step": 351925, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1397781372070312, "global_step": 351926, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1147520542144775, "global_step": 351927, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.10780668258667, "global_step": 351928, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.084520101547241, "global_step": 351929, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0373759269714355, "global_step": 351930, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.068312406539917, "global_step": 351931, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.020247220993042, "global_step": 351932, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0690410137176514, "global_step": 351933, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.152401924133301, "global_step": 351934, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0917067527770996, "global_step": 351935, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1376073360443115, "global_step": 351936, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.152169942855835, "global_step": 351937, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.085869312286377, "global_step": 351938, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.048029661178589, "global_step": 351939, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0564873218536377, "global_step": 351940, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.067336082458496, "global_step": 351941, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1320009231567383, "global_step": 351942, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1457178592681885, "global_step": 351943, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.048063039779663, "global_step": 351944, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0510857105255127, "global_step": 351945, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.092052698135376, "global_step": 351946, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0791313648223877, "global_step": 351947, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.06820011138916, "global_step": 351948, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.069857597351074, "global_step": 351949, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.160101890563965, "global_step": 351950, "epoch": 713, "lr": 5e-05}
{"train_loss": 1.9895882606506348, "global_step": 351951, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.154172658920288, "global_step": 351952, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0161452293395996, "global_step": 351953, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.055098295211792, "global_step": 351954, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.098845958709717, "global_step": 351955, "epoch": 713, "lr": 5e-05}
{"train_loss": 1.9910727739334106, "global_step": 351956, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0874691009521484, "global_step": 351957, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1151089668273926, "global_step": 351958, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1298530101776123, "global_step": 351959, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.185370683670044, "global_step": 351960, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1388368606567383, "global_step": 351961, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0502822399139404, "global_step": 351962, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.14821720123291, "global_step": 351963, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.161203384399414, "global_step": 351964, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1085879802703857, "global_step": 351965, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.081325054168701, "global_step": 351966, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0348854064941406, "global_step": 351967, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0928938388824463, "global_step": 351968, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0808515548706055, "global_step": 351969, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0668976306915283, "global_step": 351970, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1013269424438477, "global_step": 351971, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.080354690551758, "global_step": 351972, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.170867443084717, "global_step": 351973, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1875076293945312, "global_step": 351974, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1684529781341553, "global_step": 351975, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1872472763061523, "global_step": 351976, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0432591438293457, "global_step": 351977, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.078892946243286, "global_step": 351978, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1569933891296387, "global_step": 351979, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1408514976501465, "global_step": 351980, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1447861194610596, "global_step": 351981, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0181307792663574, "global_step": 351982, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.077603340148926, "global_step": 351983, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1051433086395264, "global_step": 351984, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.19948673248291, "global_step": 351985, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1356470584869385, "global_step": 351986, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1171154975891113, "global_step": 351987, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0851190090179443, "global_step": 351988, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1226377487182617, "global_step": 351989, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.114429235458374, "global_step": 351990, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.130789279937744, "global_step": 351991, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1239235401153564, "global_step": 351992, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1180837154388428, "global_step": 351993, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.112170934677124, "global_step": 351994, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1060876846313477, "global_step": 351995, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.07907772064209, "global_step": 351996, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1391329765319824, "global_step": 351997, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1315133571624756, "global_step": 351998, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1180295944213867, "global_step": 351999, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.076798915863037, "global_step": 352000, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.092320680618286, "global_step": 352001, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.155951976776123, "global_step": 352002, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0511088371276855, "global_step": 352003, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.121990442276001, "global_step": 352004, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0668857097625732, "global_step": 352005, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.126556873321533, "global_step": 352006, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1331875324249268, "global_step": 352007, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1626670360565186, "global_step": 352008, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1801271438598633, "global_step": 352009, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1382203102111816, "global_step": 352010, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1343700885772705, "global_step": 352011, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1515660285949707, "global_step": 352012, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.19362735748291, "global_step": 352013, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0058014392852783, "global_step": 352014, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.132845878601074, "global_step": 352015, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1603503227233887, "global_step": 352016, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.100092649459839, "global_step": 352017, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.143911838531494, "global_step": 352018, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.07372784614563, "global_step": 352019, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1470396518707275, "global_step": 352020, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.106600761413574, "global_step": 352021, "epoch": 713, "lr": 5e-05}
{"train_loss": 1.994489312171936, "global_step": 352022, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0492305755615234, "global_step": 352023, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.166217088699341, "global_step": 352024, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0808169841766357, "global_step": 352025, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.130781650543213, "global_step": 352026, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.162336826324463, "global_step": 352027, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1368825435638428, "global_step": 352028, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1049442291259766, "global_step": 352029, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0741424560546875, "global_step": 352030, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0372538566589355, "global_step": 352031, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1359078884124756, "global_step": 352032, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.2458913326263428, "global_step": 352033, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.091118574142456, "global_step": 352034, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.011472702026367, "global_step": 352035, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0888805389404297, "global_step": 352036, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1055335998535156, "global_step": 352037, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.105536937713623, "global_step": 352038, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.124307155609131, "global_step": 352039, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.136711835861206, "global_step": 352040, "epoch": 713, "lr": 5e-05}
{"train_loss": 1.9867521524429321, "global_step": 352041, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0882279872894287, "global_step": 352042, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1976354122161865, "global_step": 352043, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.146608829498291, "global_step": 352044, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1555960178375244, "global_step": 352045, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1658177375793457, "global_step": 352046, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1847400665283203, "global_step": 352047, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1141326427459717, "global_step": 352048, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1071250438690186, "global_step": 352049, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0860135555267334, "global_step": 352050, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.12017560005188, "global_step": 352051, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0624091625213623, "global_step": 352052, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1237406730651855, "global_step": 352053, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1172919273376465, "global_step": 352054, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1810572147369385, "global_step": 352055, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.103576898574829, "global_step": 352056, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0637922286987305, "global_step": 352057, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.106961727142334, "global_step": 352058, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0802090167999268, "global_step": 352059, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.167125701904297, "global_step": 352060, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.143578052520752, "global_step": 352061, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.12308406829834, "global_step": 352062, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1264352798461914, "global_step": 352063, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.076498031616211, "global_step": 352064, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.098355770111084, "global_step": 352065, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.105929136276245, "global_step": 352066, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.159235954284668, "global_step": 352067, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.136474609375, "global_step": 352068, "epoch": 713, "lr": 5e-05}
{"train_loss": 1.9586018323898315, "global_step": 352069, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.056316614151001, "global_step": 352070, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1059563159942627, "global_step": 352071, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0169661045074463, "global_step": 352072, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1219968795776367, "global_step": 352073, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.084315061569214, "global_step": 352074, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1013824939727783, "global_step": 352075, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0331945419311523, "global_step": 352076, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0425310134887695, "global_step": 352077, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0799973011016846, "global_step": 352078, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.105433464050293, "global_step": 352079, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0571699142456055, "global_step": 352080, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1276774406433105, "global_step": 352081, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.075371265411377, "global_step": 352082, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1623964309692383, "global_step": 352083, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0840468406677246, "global_step": 352084, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.124770164489746, "global_step": 352085, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.10063099861145, "global_step": 352086, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.109238862991333, "global_step": 352087, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1405487060546875, "global_step": 352088, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.149202823638916, "global_step": 352089, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.094412088394165, "global_step": 352090, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.04695463180542, "global_step": 352091, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.05015230178833, "global_step": 352092, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0267724990844727, "global_step": 352093, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.157857894897461, "global_step": 352094, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.058415174484253, "global_step": 352095, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1461617946624756, "global_step": 352096, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.063110828399658, "global_step": 352097, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1129684448242188, "global_step": 352098, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0840444564819336, "global_step": 352099, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0358500480651855, "global_step": 352100, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0387892723083496, "global_step": 352101, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0951526165008545, "global_step": 352102, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.053807020187378, "global_step": 352103, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.087817430496216, "global_step": 352104, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.122192144393921, "global_step": 352105, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0779759883880615, "global_step": 352106, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1640074253082275, "global_step": 352107, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0867979526519775, "global_step": 352108, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.091808795928955, "global_step": 352109, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.09578275680542, "global_step": 352110, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.043402671813965, "global_step": 352111, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.143698215484619, "global_step": 352112, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.130573034286499, "global_step": 352113, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.089031934738159, "global_step": 352114, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.079486131668091, "global_step": 352115, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.153538465499878, "global_step": 352116, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.074450969696045, "global_step": 352117, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.119710922241211, "global_step": 352118, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.084299087524414, "global_step": 352119, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.191138982772827, "global_step": 352120, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.035175323486328, "global_step": 352121, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.122387170791626, "global_step": 352122, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.090477228164673, "global_step": 352123, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.089846134185791, "global_step": 352124, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0568687915802, "global_step": 352125, "epoch": 713, "lr": 5e-05}
{"train_loss": 1.9931538105010986, "global_step": 352126, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.166776657104492, "global_step": 352127, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.126220226287842, "global_step": 352128, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1189136505126953, "global_step": 352129, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0895233154296875, "global_step": 352130, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0252771377563477, "global_step": 352131, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1300337314605713, "global_step": 352132, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1691548824310303, "global_step": 352133, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0771210193634033, "global_step": 352134, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.114301919937134, "global_step": 352135, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.124249219894409, "global_step": 352136, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0343620777130127, "global_step": 352137, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1236379146575928, "global_step": 352138, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0575802326202393, "global_step": 352139, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.036508560180664, "global_step": 352140, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0980379581451416, "global_step": 352141, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.067352771759033, "global_step": 352142, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0384702682495117, "global_step": 352143, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.2034945487976074, "global_step": 352144, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.074537992477417, "global_step": 352145, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1911182403564453, "global_step": 352146, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0700559616088867, "global_step": 352147, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.126405954360962, "global_step": 352148, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1342685222625732, "global_step": 352149, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0898211002349854, "global_step": 352150, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0549676418304443, "global_step": 352151, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0445327758789062, "global_step": 352152, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0454721450805664, "global_step": 352153, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.191739082336426, "global_step": 352154, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.146378755569458, "global_step": 352155, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.100084066390991, "global_step": 352156, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.192554473876953, "global_step": 352157, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1045570373535156, "global_step": 352158, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.058316946029663, "global_step": 352159, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1054470539093018, "global_step": 352160, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1140406131744385, "global_step": 352161, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.114715337753296, "global_step": 352162, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1009278297424316, "global_step": 352163, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.146522283554077, "global_step": 352164, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.139617681503296, "global_step": 352165, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1504571437835693, "global_step": 352166, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1841535568237305, "global_step": 352167, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0509941577911377, "global_step": 352168, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1271121501922607, "global_step": 352169, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.116332769393921, "global_step": 352170, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.197939395904541, "global_step": 352171, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0912551879882812, "global_step": 352172, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0802419185638428, "global_step": 352173, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.148387908935547, "global_step": 352174, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0970652103424072, "global_step": 352175, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0810115337371826, "global_step": 352176, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0793755054473877, "global_step": 352177, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.04356050491333, "global_step": 352178, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.141716480255127, "global_step": 352179, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1364214420318604, "global_step": 352180, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1821792125701904, "global_step": 352181, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.140228509902954, "global_step": 352182, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0814008712768555, "global_step": 352183, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0973076820373535, "global_step": 352184, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0978662967681885, "global_step": 352185, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1132161617279053, "global_step": 352186, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.143745183944702, "global_step": 352187, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1609721183776855, "global_step": 352188, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.045119285583496, "global_step": 352189, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.11698317527771, "global_step": 352190, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0739428997039795, "global_step": 352191, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1415157318115234, "global_step": 352192, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.083794593811035, "global_step": 352193, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1103639602661133, "global_step": 352194, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0605173110961914, "global_step": 352195, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.089721202850342, "global_step": 352196, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.179687738418579, "global_step": 352197, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.2787270545959473, "global_step": 352198, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.052062749862671, "global_step": 352199, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.134214162826538, "global_step": 352200, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.149411678314209, "global_step": 352201, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0777955055236816, "global_step": 352202, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0578761100769043, "global_step": 352203, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.094383478164673, "global_step": 352204, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1403892040252686, "global_step": 352205, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.14695405960083, "global_step": 352206, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.11556077003479, "global_step": 352207, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0071158409118652, "global_step": 352208, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1905598640441895, "global_step": 352209, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.083066940307617, "global_step": 352210, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1028783321380615, "global_step": 352211, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.101252555847168, "global_step": 352212, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0362648963928223, "global_step": 352213, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.2101361751556396, "global_step": 352214, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.185311794281006, "global_step": 352215, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1033105850219727, "global_step": 352216, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.10799241065979, "global_step": 352217, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.058584451675415, "global_step": 352218, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0611815452575684, "global_step": 352219, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1171655654907227, "global_step": 352220, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1448802947998047, "global_step": 352221, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1105082035064697, "global_step": 352222, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.134880304336548, "global_step": 352223, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0418701171875, "global_step": 352224, "epoch": 713, "lr": 5e-05}
{"train_loss": 1.9962592124938965, "global_step": 352225, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.154866933822632, "global_step": 352226, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1479506492614746, "global_step": 352227, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.158639430999756, "global_step": 352228, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.092978000640869, "global_step": 352229, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0908119678497314, "global_step": 352230, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1062095165252686, "global_step": 352231, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.127685070037842, "global_step": 352232, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0653061866760254, "global_step": 352233, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.096550941467285, "global_step": 352234, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.07025408744812, "global_step": 352235, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0251529216766357, "global_step": 352236, "epoch": 713, "lr": 5e-05}
{"train_loss": 1.989182710647583, "global_step": 352237, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0704925060272217, "global_step": 352238, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0718679428100586, "global_step": 352239, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1190690994262695, "global_step": 352240, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.045966148376465, "global_step": 352241, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1018805503845215, "global_step": 352242, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.112394332885742, "global_step": 352243, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0506670475006104, "global_step": 352244, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1306827068328857, "global_step": 352245, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0889601707458496, "global_step": 352246, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.070835590362549, "global_step": 352247, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.153468132019043, "global_step": 352248, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0850369930267334, "global_step": 352249, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1184310913085938, "global_step": 352250, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0722427368164062, "global_step": 352251, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0206117630004883, "global_step": 352252, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.079547643661499, "global_step": 352253, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0285117626190186, "global_step": 352254, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0719361305236816, "global_step": 352255, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.071622610092163, "global_step": 352256, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1740498542785645, "global_step": 352257, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0824925899505615, "global_step": 352258, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0478086471557617, "global_step": 352259, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.061833620071411, "global_step": 352260, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.128973960876465, "global_step": 352261, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.149810552597046, "global_step": 352262, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.2021772861480713, "global_step": 352263, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.108187198638916, "global_step": 352264, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1386654376983643, "global_step": 352265, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.064124584197998, "global_step": 352266, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.086552381515503, "global_step": 352267, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1110150814056396, "global_step": 352268, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.125166177749634, "global_step": 352269, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1197378635406494, "global_step": 352270, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.068082809448242, "global_step": 352271, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1078388690948486, "global_step": 352272, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0521047115325928, "global_step": 352273, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.107302188873291, "global_step": 352274, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1247026920318604, "global_step": 352275, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.124643564224243, "global_step": 352276, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.147033452987671, "global_step": 352277, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.12019419670105, "global_step": 352278, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1242291927337646, "global_step": 352279, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.193472385406494, "global_step": 352280, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1380503177642822, "global_step": 352281, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0966122150421143, "global_step": 352282, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0940184593200684, "global_step": 352283, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1324188709259033, "global_step": 352284, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.173445224761963, "global_step": 352285, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1061787605285645, "global_step": 352286, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0897629261016846, "global_step": 352287, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.151455879211426, "global_step": 352288, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0180320739746094, "global_step": 352289, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1631791591644287, "global_step": 352290, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.091032028198242, "global_step": 352291, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.092859983444214, "global_step": 352292, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.143066644668579, "global_step": 352293, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.10899019241333, "global_step": 352294, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1095502376556396, "global_step": 352295, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1345701217651367, "global_step": 352296, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0512478351593018, "global_step": 352297, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.118427276611328, "global_step": 352298, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1200106143951416, "global_step": 352299, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.102856159210205, "global_step": 352300, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.186661958694458, "global_step": 352301, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1018476486206055, "global_step": 352302, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.100531816482544, "global_step": 352303, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1867730617523193, "global_step": 352304, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1591179370880127, "global_step": 352305, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.116024971008301, "global_step": 352306, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.113459825515747, "global_step": 352307, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0838816165924072, "global_step": 352308, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1226186752319336, "global_step": 352309, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1047580242156982, "global_step": 352310, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1156718730926514, "global_step": 352311, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1226541996002197, "global_step": 352312, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.186593532562256, "global_step": 352313, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.114658832550049, "global_step": 352314, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.070760726928711, "global_step": 352315, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1308910846710205, "global_step": 352316, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0905568599700928, "global_step": 352317, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1688392162323, "global_step": 352318, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1354260444641113, "global_step": 352319, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1193315982818604, "global_step": 352320, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0973012447357178, "global_step": 352321, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0560319423675537, "global_step": 352322, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0674402713775635, "global_step": 352323, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1322221755981445, "global_step": 352324, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.08254337310791, "global_step": 352325, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1750197410583496, "global_step": 352326, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1380550861358643, "global_step": 352327, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0063037872314453, "global_step": 352328, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.071828842163086, "global_step": 352329, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0944347381591797, "global_step": 352330, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.093653678894043, "global_step": 352331, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.116476058959961, "global_step": 352332, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1150705814361572, "global_step": 352333, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1674716472625732, "global_step": 352334, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0562682151794434, "global_step": 352335, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1344799995422363, "global_step": 352336, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.153430461883545, "global_step": 352337, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.084235429763794, "global_step": 352338, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.134491205215454, "global_step": 352339, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.097390651702881, "global_step": 352340, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.087306022644043, "global_step": 352341, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0793488025665283, "global_step": 352342, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.144529104232788, "global_step": 352343, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1863083839416504, "global_step": 352344, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.075594186782837, "global_step": 352345, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1788644790649414, "global_step": 352346, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.143296957015991, "global_step": 352347, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0958478450775146, "global_step": 352348, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1373069286346436, "global_step": 352349, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1211655139923096, "global_step": 352350, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1005859375, "global_step": 352351, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0680153369903564, "global_step": 352352, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.181504011154175, "global_step": 352353, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1238365173339844, "global_step": 352354, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0364012718200684, "global_step": 352355, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.130830764770508, "global_step": 352356, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.001924753189087, "global_step": 352357, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1425294876098633, "global_step": 352358, "epoch": 713, "lr": 5e-05}
{"train_loss": 1.987662434577942, "global_step": 352359, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0646963119506836, "global_step": 352360, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.161033868789673, "global_step": 352361, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1067450046539307, "global_step": 352362, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1235880851745605, "global_step": 352363, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1267411708831787, "global_step": 352364, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.210465908050537, "global_step": 352365, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.015092611312866, "global_step": 352366, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0761404037475586, "global_step": 352367, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.176259994506836, "global_step": 352368, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0568673610687256, "global_step": 352369, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.158587694168091, "global_step": 352370, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1796646118164062, "global_step": 352371, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.15108323097229, "global_step": 352372, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.137331008911133, "global_step": 352373, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.023181915283203, "global_step": 352374, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.032672166824341, "global_step": 352375, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1534454822540283, "global_step": 352376, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.084204912185669, "global_step": 352377, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.062731981277466, "global_step": 352378, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1293447017669678, "global_step": 352379, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0285050868988037, "global_step": 352380, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1775431632995605, "global_step": 352381, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.04533052444458, "global_step": 352382, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0807242393493652, "global_step": 352383, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.081160068511963, "global_step": 352384, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.2680962085723877, "global_step": 352385, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.154235363006592, "global_step": 352386, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0938878059387207, "global_step": 352387, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.145493507385254, "global_step": 352388, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.084129810333252, "global_step": 352389, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.116741418838501, "global_step": 352390, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.194457530975342, "global_step": 352391, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1436386108398438, "global_step": 352392, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0857913494110107, "global_step": 352393, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.129006862640381, "global_step": 352394, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.069669008255005, "global_step": 352395, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1025021076202393, "global_step": 352396, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.072617530822754, "global_step": 352397, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1899704933166504, "global_step": 352398, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.107316017150879, "global_step": 352399, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.082876443862915, "global_step": 352400, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.087343692779541, "global_step": 352401, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1561362743377686, "global_step": 352402, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0726687908172607, "global_step": 352403, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.111259698867798, "global_step": 352404, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.161863327026367, "global_step": 352405, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.077146530151367, "global_step": 352406, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.120006561279297, "global_step": 352407, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.116356611251831, "global_step": 352408, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1545979976654053, "global_step": 352409, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.058396339416504, "global_step": 352410, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0899691581726074, "global_step": 352411, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0823402404785156, "global_step": 352412, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1582188606262207, "global_step": 352413, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.170929193496704, "global_step": 352414, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.133223295211792, "global_step": 352415, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.160128116607666, "global_step": 352416, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1915996074676514, "global_step": 352417, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.189025402069092, "global_step": 352418, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1345462799072266, "global_step": 352419, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.079847574234009, "global_step": 352420, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0656089782714844, "global_step": 352421, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.081979513168335, "global_step": 352422, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.179015874862671, "global_step": 352423, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0272157192230225, "global_step": 352424, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1567800045013428, "global_step": 352425, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.096449613571167, "global_step": 352426, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.136812925338745, "global_step": 352427, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0482804775238037, "global_step": 352428, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.156007766723633, "global_step": 352429, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1613452434539795, "global_step": 352430, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.2126681804656982, "global_step": 352431, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0879275798797607, "global_step": 352432, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.070136070251465, "global_step": 352433, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.125837802886963, "global_step": 352434, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1176669597625732, "global_step": 352435, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.059849262237549, "global_step": 352436, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0795507431030273, "global_step": 352437, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1762759685516357, "global_step": 352438, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.065803289413452, "global_step": 352439, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.05938982963562, "global_step": 352440, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1975979804992676, "global_step": 352441, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.150486946105957, "global_step": 352442, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.114476442337036, "global_step": 352443, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0587732791900635, "global_step": 352444, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.195591688156128, "global_step": 352445, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0098345279693604, "global_step": 352446, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.18487548828125, "global_step": 352447, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.108165979385376, "global_step": 352448, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.144017457962036, "global_step": 352449, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1071937084198, "global_step": 352450, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.097475290298462, "global_step": 352451, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0957446098327637, "global_step": 352452, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0839877128601074, "global_step": 352453, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.01948881149292, "global_step": 352454, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.115131139755249, "global_step": 352455, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0729176998138428, "global_step": 352456, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1330151557922363, "global_step": 352457, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1483070850372314, "global_step": 352458, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0916364192962646, "global_step": 352459, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0475716590881348, "global_step": 352460, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.043789863586426, "global_step": 352461, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.030381202697754, "global_step": 352462, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1084187030792236, "global_step": 352463, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0154988765716553, "global_step": 352464, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.2448582649230957, "global_step": 352465, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.029360055923462, "global_step": 352466, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.106971025466919, "global_step": 352467, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0952959060668945, "global_step": 352468, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1233630180358887, "global_step": 352469, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1583669185638428, "global_step": 352470, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0524680614471436, "global_step": 352471, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.064098358154297, "global_step": 352472, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.091602087020874, "global_step": 352473, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0663845539093018, "global_step": 352474, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.2377185821533203, "global_step": 352475, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1243069171905518, "global_step": 352476, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1192193031311035, "global_step": 352477, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1682991981506348, "global_step": 352478, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1029059886932373, "global_step": 352479, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0806221961975098, "global_step": 352480, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1005523204803467, "global_step": 352481, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.167651653289795, "global_step": 352482, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0306403636932373, "global_step": 352483, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.167889356613159, "global_step": 352484, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.04887056350708, "global_step": 352485, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1258978843688965, "global_step": 352486, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0669519901275635, "global_step": 352487, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.056537628173828, "global_step": 352488, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1148698329925537, "global_step": 352489, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1022636890411377, "global_step": 352490, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.2139225006103516, "global_step": 352491, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.105402946472168, "global_step": 352492, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.133887529373169, "global_step": 352493, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0880792140960693, "global_step": 352494, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0475692749023438, "global_step": 352495, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0879364013671875, "global_step": 352496, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.127016305923462, "global_step": 352497, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.092661142349243, "global_step": 352498, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.146761178970337, "global_step": 352499, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1146328449249268, "global_step": 352500, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0848135948181152, "global_step": 352501, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0945355892181396, "global_step": 352502, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.005260705947876, "global_step": 352503, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1159989833831787, "global_step": 352504, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1286308765411377, "global_step": 352505, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0898139476776123, "global_step": 352506, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.104198932647705, "global_step": 352507, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1363413333892822, "global_step": 352508, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.102924108505249, "global_step": 352509, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1301448345184326, "global_step": 352510, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.028465509414673, "global_step": 352511, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0753774642944336, "global_step": 352512, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.03029727935791, "global_step": 352513, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0922253131866455, "global_step": 352514, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0805132389068604, "global_step": 352515, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.058136224746704, "global_step": 352516, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.091885566711426, "global_step": 352517, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1493585109710693, "global_step": 352518, "epoch": 713, "lr": 5e-05}
{"train_loss": 1.9918501377105713, "global_step": 352519, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.155694007873535, "global_step": 352520, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.14022159576416, "global_step": 352521, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.189542770385742, "global_step": 352522, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1392130851745605, "global_step": 352523, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.052294969558716, "global_step": 352524, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0045018196105957, "global_step": 352525, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.090571165084839, "global_step": 352526, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0580077171325684, "global_step": 352527, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0688555240631104, "global_step": 352528, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.04968523979187, "global_step": 352529, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0740599632263184, "global_step": 352530, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.2352564334869385, "global_step": 352531, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.121273994445801, "global_step": 352532, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.12725830078125, "global_step": 352533, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0439860820770264, "global_step": 352534, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1646177768707275, "global_step": 352535, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.072937250137329, "global_step": 352536, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.120189905166626, "global_step": 352537, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.093926191329956, "global_step": 352538, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0799612998962402, "global_step": 352539, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0798258781433105, "global_step": 352540, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.127131938934326, "global_step": 352541, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.186171531677246, "global_step": 352542, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1436684131622314, "global_step": 352543, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.109553575515747, "global_step": 352544, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0560991764068604, "global_step": 352545, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1078529357910156, "global_step": 352546, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.106302499771118, "global_step": 352547, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.117380380630493, "global_step": 352548, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1388232707977295, "global_step": 352549, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1079084873199463, "global_step": 352550, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.2077293395996094, "global_step": 352551, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.241347074508667, "global_step": 352552, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.228757381439209, "global_step": 352553, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.10878324508667, "global_step": 352554, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.158651351928711, "global_step": 352555, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0584845542907715, "global_step": 352556, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0693790912628174, "global_step": 352557, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1652536392211914, "global_step": 352558, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1391520500183105, "global_step": 352559, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.115229606628418, "global_step": 352560, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.13371205329895, "global_step": 352561, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0901808738708496, "global_step": 352562, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1759092807769775, "global_step": 352563, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1374318599700928, "global_step": 352564, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.148569345474243, "global_step": 352565, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.255749225616455, "global_step": 352566, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.126155138015747, "global_step": 352567, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0931079387664795, "global_step": 352568, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.182856798171997, "global_step": 352569, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.086902379989624, "global_step": 352570, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1998910903930664, "global_step": 352571, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1270031929016113, "global_step": 352572, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1099014282226562, "global_step": 352573, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0715854167938232, "global_step": 352574, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.024554967880249, "global_step": 352575, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1063880920410156, "global_step": 352576, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.10347056388855, "global_step": 352577, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.174459457397461, "global_step": 352578, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1640524864196777, "global_step": 352579, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0631868839263916, "global_step": 352580, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0815935134887695, "global_step": 352581, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.064648389816284, "global_step": 352582, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1859328746795654, "global_step": 352583, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.056283950805664, "global_step": 352584, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.012507200241089, "global_step": 352585, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.136370897293091, "global_step": 352586, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1140449047088623, "global_step": 352587, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0415899753570557, "global_step": 352588, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1740500926971436, "global_step": 352589, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1802027225494385, "global_step": 352590, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.073364019393921, "global_step": 352591, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.075066566467285, "global_step": 352592, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.111753463745117, "global_step": 352593, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.129074811935425, "global_step": 352594, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.086341142654419, "global_step": 352595, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.093351125717163, "global_step": 352596, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1139748096466064, "global_step": 352597, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.126143217086792, "global_step": 352598, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.140223503112793, "global_step": 352599, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0006935596466064, "global_step": 352600, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0833590030670166, "global_step": 352601, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.110823631286621, "global_step": 352602, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.076164722442627, "global_step": 352603, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1597025394439697, "global_step": 352604, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0989346504211426, "global_step": 352605, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.054517984390259, "global_step": 352606, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.186718463897705, "global_step": 352607, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.129202127456665, "global_step": 352608, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.070897340774536, "global_step": 352609, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.2252705097198486, "global_step": 352610, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1135873794555664, "global_step": 352611, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1147501468658447, "global_step": 352612, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.179849147796631, "global_step": 352613, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.11857271194458, "global_step": 352614, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1495442390441895, "global_step": 352615, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1130247116088867, "global_step": 352616, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0552306175231934, "global_step": 352617, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1654446125030518, "global_step": 352618, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0855765342712402, "global_step": 352619, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.141279458999634, "global_step": 352620, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.061558723449707, "global_step": 352621, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0951650142669678, "global_step": 352622, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.133054733276367, "global_step": 352623, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.164186716079712, "global_step": 352624, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0286166667938232, "global_step": 352625, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1304664611816406, "global_step": 352626, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.212831735610962, "global_step": 352627, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1597084999084473, "global_step": 352628, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.116215229034424, "global_step": 352629, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1018402576446533, "global_step": 352630, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1609365940093994, "global_step": 352631, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0444681644439697, "global_step": 352632, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1122841835021973, "global_step": 352633, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.176006555557251, "global_step": 352634, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1066291332244873, "global_step": 352635, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1585114002227783, "global_step": 352636, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1488330364227295, "global_step": 352637, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.11283278465271, "global_step": 352638, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.259661912918091, "global_step": 352639, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.096892833709717, "global_step": 352640, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1640913486480713, "global_step": 352641, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.094076633453369, "global_step": 352642, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.150972366333008, "global_step": 352643, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0954082012176514, "global_step": 352644, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0961899757385254, "global_step": 352645, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0353267192840576, "global_step": 352646, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0687124729156494, "global_step": 352647, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.095433235168457, "global_step": 352648, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.169741630554199, "global_step": 352649, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1095707416534424, "global_step": 352650, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.082894802093506, "global_step": 352651, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1752429008483887, "global_step": 352652, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.098895311355591, "global_step": 352653, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1261141300201416, "global_step": 352654, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.099972724914551, "global_step": 352655, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.027735471725464, "global_step": 352656, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1567580699920654, "global_step": 352657, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.03292179107666, "global_step": 352658, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.099534034729004, "global_step": 352659, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.175116777420044, "global_step": 352660, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1138389110565186, "global_step": 352661, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1151442527770996, "global_step": 352662, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0971109867095947, "global_step": 352663, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1367592811584473, "global_step": 352664, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.132565498352051, "global_step": 352665, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.009507179260254, "global_step": 352666, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0731043815612793, "global_step": 352667, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0504019260406494, "global_step": 352668, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0735902786254883, "global_step": 352669, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1456568241119385, "global_step": 352670, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.118028402328491, "global_step": 352671, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1769940853118896, "global_step": 352672, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.077702283859253, "global_step": 352673, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1123459339141846, "global_step": 352674, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1464738845825195, "global_step": 352675, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.115189790725708, "global_step": 352676, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.044994831085205, "global_step": 352677, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.2139127254486084, "global_step": 352678, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0931050777435303, "global_step": 352679, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0887131690979004, "global_step": 352680, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1161866188049316, "global_step": 352681, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0343387126922607, "global_step": 352682, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0593690872192383, "global_step": 352683, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.121866464614868, "global_step": 352684, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.124394416809082, "global_step": 352685, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.112053155899048, "global_step": 352686, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.139798402786255, "global_step": 352687, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1301016807556152, "global_step": 352688, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1448631286621094, "global_step": 352689, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.145779609680176, "global_step": 352690, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.137511968612671, "global_step": 352691, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0956501960754395, "global_step": 352692, "epoch": 713, "lr": 5e-05}
{"train_loss": 1.9616248607635498, "global_step": 352693, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1128296852111816, "global_step": 352694, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0359740257263184, "global_step": 352695, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.110405683517456, "global_step": 352696, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1062772274017334, "global_step": 352697, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.166703701019287, "global_step": 352698, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1682465076446533, "global_step": 352699, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.104186534881592, "global_step": 352700, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0171782970428467, "global_step": 352701, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.132032871246338, "global_step": 352702, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1317033767700195, "global_step": 352703, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.119624376296997, "global_step": 352704, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.083484172821045, "global_step": 352705, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.2031219005584717, "global_step": 352706, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.115856885910034, "global_step": 352707, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1147422790527344, "global_step": 352708, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1068551540374756, "global_step": 352709, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0383291244506836, "global_step": 352710, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0708298683166504, "global_step": 352711, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0452873706817627, "global_step": 352712, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.051912784576416, "global_step": 352713, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.072150468826294, "global_step": 352714, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.13075590133667, "global_step": 352715, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.078740119934082, "global_step": 352716, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.095020055770874, "global_step": 352717, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.03840708732605, "global_step": 352718, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.152172327041626, "global_step": 352719, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.15859055519104, "global_step": 352720, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0888724327087402, "global_step": 352721, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.01853609085083, "global_step": 352722, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.202146530151367, "global_step": 352723, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1089274883270264, "global_step": 352724, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.146929979324341, "global_step": 352725, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1255719661712646, "global_step": 352726, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1040499210357666, "global_step": 352727, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1873812675476074, "global_step": 352728, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0556154251098633, "global_step": 352729, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1701598167419434, "global_step": 352730, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0918493270874023, "global_step": 352731, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.061464786529541, "global_step": 352732, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.11933970451355, "global_step": 352733, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0981810092926025, "global_step": 352734, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.020735502243042, "global_step": 352735, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.152878522872925, "global_step": 352736, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1389358043670654, "global_step": 352737, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0723471641540527, "global_step": 352738, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0308401584625244, "global_step": 352739, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.177548408508301, "global_step": 352740, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1920316219329834, "global_step": 352741, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.055372953414917, "global_step": 352742, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.2014362812042236, "global_step": 352743, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1078014373779297, "global_step": 352744, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.067932367324829, "global_step": 352745, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1478078365325928, "global_step": 352746, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1111397743225098, "global_step": 352747, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0831491947174072, "global_step": 352748, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0122830867767334, "global_step": 352749, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1903135776519775, "global_step": 352750, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.115574598312378, "global_step": 352751, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1400363445281982, "global_step": 352752, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1474180221557617, "global_step": 352753, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.07038950920105, "global_step": 352754, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0958642959594727, "global_step": 352755, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1423470973968506, "global_step": 352756, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.167135000228882, "global_step": 352757, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0835225582122803, "global_step": 352758, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.175281047821045, "global_step": 352759, "epoch": 713, "lr": 5e-05}
{"train_loss": 1.9896081686019897, "global_step": 352760, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.10731840133667, "global_step": 352761, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.120499610900879, "global_step": 352762, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.103666305541992, "global_step": 352763, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1223442554473877, "global_step": 352764, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1739044189453125, "global_step": 352765, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1880691051483154, "global_step": 352766, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1238980293273926, "global_step": 352767, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1001718044281006, "global_step": 352768, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.139173746109009, "global_step": 352769, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1189537048339844, "global_step": 352770, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.099726438522339, "global_step": 352771, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.121821165084839, "global_step": 352772, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1190719604492188, "global_step": 352773, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.141188859939575, "global_step": 352774, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.138486385345459, "global_step": 352775, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.057694911956787, "global_step": 352776, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0959479808807373, "global_step": 352777, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1310534477233887, "global_step": 352778, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1262505054473877, "global_step": 352779, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.163396120071411, "global_step": 352780, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.095165252685547, "global_step": 352781, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.120739221572876, "global_step": 352782, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.212006092071533, "global_step": 352783, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1104533672332764, "global_step": 352784, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.205617904663086, "global_step": 352785, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.178356885910034, "global_step": 352786, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1158266067504883, "global_step": 352787, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0732367038726807, "global_step": 352788, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.12394118309021, "global_step": 352789, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0966637134552, "global_step": 352790, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0733718872070312, "global_step": 352791, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1594760417938232, "global_step": 352792, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1793172359466553, "global_step": 352793, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.157923698425293, "global_step": 352794, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0493218898773193, "global_step": 352795, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.185490846633911, "global_step": 352796, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.142306089401245, "global_step": 352797, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.059490203857422, "global_step": 352798, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.14978289604187, "global_step": 352799, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.173182964324951, "global_step": 352800, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0241012573242188, "global_step": 352801, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1141390800476074, "global_step": 352802, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.033151865005493, "global_step": 352803, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1598451137542725, "global_step": 352804, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.058622121810913, "global_step": 352805, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0553648471832275, "global_step": 352806, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0777974128723145, "global_step": 352807, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.065185546875, "global_step": 352808, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0900418758392334, "global_step": 352809, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0810203552246094, "global_step": 352810, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1014482975006104, "global_step": 352811, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1133460998535156, "global_step": 352812, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1663458347320557, "global_step": 352813, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.196956157684326, "global_step": 352814, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.138943672180176, "global_step": 352815, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.11362886428833, "global_step": 352816, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.112518310546875, "global_step": 352817, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.111698865890503, "global_step": 352818, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.064373016357422, "global_step": 352819, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0928375720977783, "global_step": 352820, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.165022134780884, "global_step": 352821, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0985748767852783, "global_step": 352822, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1675639152526855, "global_step": 352823, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.098557233810425, "global_step": 352824, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1422338485717773, "global_step": 352825, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.2044787406921387, "global_step": 352826, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1377556324005127, "global_step": 352827, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.10650634765625, "global_step": 352828, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.090181827545166, "global_step": 352829, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0802061557769775, "global_step": 352830, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.128729820251465, "global_step": 352831, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0110585689544678, "global_step": 352832, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.066254138946533, "global_step": 352833, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1021947860717773, "global_step": 352834, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1060783863067627, "global_step": 352835, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1286075115203857, "global_step": 352836, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1239004135131836, "global_step": 352837, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.089815855026245, "global_step": 352838, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0937137603759766, "global_step": 352839, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1230669021606445, "global_step": 352840, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1250619888305664, "global_step": 352841, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.13749098777771, "global_step": 352842, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1381425857543945, "global_step": 352843, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.118999719619751, "global_step": 352844, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1594367027282715, "global_step": 352845, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0342178344726562, "global_step": 352846, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0594537258148193, "global_step": 352847, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.1088030338287354, "global_step": 352848, "epoch": 713, "lr": 5e-05}
{"train_loss": 2.0822346210479736, "global_step": 352849, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0517711639404297, "global_step": 352850, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.071789503097534, "global_step": 352851, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1256489753723145, "global_step": 352852, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1196258068084717, "global_step": 352853, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0536062717437744, "global_step": 352854, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.126725912094116, "global_step": 352855, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.002824068069458, "global_step": 352856, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.030508518218994, "global_step": 352857, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.075925350189209, "global_step": 352858, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1250503063201904, "global_step": 352859, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1095850467681885, "global_step": 352860, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0877485275268555, "global_step": 352861, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2018022537231445, "global_step": 352862, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1037354469299316, "global_step": 352863, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.076833724975586, "global_step": 352864, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1389307975769043, "global_step": 352865, "epoch": 714, "lr": 5e-05}
{"train_loss": 1.9639637470245361, "global_step": 352866, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1424829959869385, "global_step": 352867, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.079009771347046, "global_step": 352868, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.04207444190979, "global_step": 352869, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0908706188201904, "global_step": 352870, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0652854442596436, "global_step": 352871, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2094902992248535, "global_step": 352872, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.113511323928833, "global_step": 352873, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1209962368011475, "global_step": 352874, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1177103519439697, "global_step": 352875, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0676324367523193, "global_step": 352876, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0933687686920166, "global_step": 352877, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.042429208755493, "global_step": 352878, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.122950792312622, "global_step": 352879, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.052539110183716, "global_step": 352880, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.120107889175415, "global_step": 352881, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.049589157104492, "global_step": 352882, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.06868577003479, "global_step": 352883, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1037092208862305, "global_step": 352884, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.16731858253479, "global_step": 352885, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1698176860809326, "global_step": 352886, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0778515338897705, "global_step": 352887, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.137434482574463, "global_step": 352888, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0468430519104004, "global_step": 352889, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0176241397857666, "global_step": 352890, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.104757785797119, "global_step": 352891, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.092719554901123, "global_step": 352892, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0484566688537598, "global_step": 352893, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0572450160980225, "global_step": 352894, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0937440395355225, "global_step": 352895, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1156606674194336, "global_step": 352896, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0970144271850586, "global_step": 352897, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.084359645843506, "global_step": 352898, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0889084339141846, "global_step": 352899, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0354204177856445, "global_step": 352900, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0417141914367676, "global_step": 352901, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1723074913024902, "global_step": 352902, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.079029083251953, "global_step": 352903, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0926706790924072, "global_step": 352904, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.089484691619873, "global_step": 352905, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.173074245452881, "global_step": 352906, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0765621662139893, "global_step": 352907, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.040226459503174, "global_step": 352908, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1700315475463867, "global_step": 352909, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.126357316970825, "global_step": 352910, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.189082384109497, "global_step": 352911, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.128755569458008, "global_step": 352912, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1030526161193848, "global_step": 352913, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0872044563293457, "global_step": 352914, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0815227031707764, "global_step": 352915, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.135061740875244, "global_step": 352916, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1417973041534424, "global_step": 352917, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.109724521636963, "global_step": 352918, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.07245135307312, "global_step": 352919, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.107396364212036, "global_step": 352920, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1765551567077637, "global_step": 352921, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.038118362426758, "global_step": 352922, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0921473503112793, "global_step": 352923, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.159667491912842, "global_step": 352924, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.054684638977051, "global_step": 352925, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0551061630249023, "global_step": 352926, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2139408588409424, "global_step": 352927, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.087965726852417, "global_step": 352928, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.118953227996826, "global_step": 352929, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1173996925354004, "global_step": 352930, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.064059257507324, "global_step": 352931, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.111147403717041, "global_step": 352932, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0956919193267822, "global_step": 352933, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0635738372802734, "global_step": 352934, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1367738246917725, "global_step": 352935, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.044801950454712, "global_step": 352936, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.11242413520813, "global_step": 352937, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1546103954315186, "global_step": 352938, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1061928272247314, "global_step": 352939, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.175537586212158, "global_step": 352940, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0439045429229736, "global_step": 352941, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.086934804916382, "global_step": 352942, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0907058715820312, "global_step": 352943, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.014901876449585, "global_step": 352944, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.116957187652588, "global_step": 352945, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.084282636642456, "global_step": 352946, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.109234571456909, "global_step": 352947, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.101855754852295, "global_step": 352948, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.087416410446167, "global_step": 352949, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1338255405426025, "global_step": 352950, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1766271591186523, "global_step": 352951, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.04620623588562, "global_step": 352952, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0666821002960205, "global_step": 352953, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0854156017303467, "global_step": 352954, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.072983503341675, "global_step": 352955, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0875234603881836, "global_step": 352956, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0586085319519043, "global_step": 352957, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.187509298324585, "global_step": 352958, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1960268020629883, "global_step": 352959, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1274642944335938, "global_step": 352960, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0654962062835693, "global_step": 352961, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1746156215667725, "global_step": 352962, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1515419483184814, "global_step": 352963, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0947022438049316, "global_step": 352964, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.080326557159424, "global_step": 352965, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0767483711242676, "global_step": 352966, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.087451696395874, "global_step": 352967, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.156158685684204, "global_step": 352968, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.116119146347046, "global_step": 352969, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0968379974365234, "global_step": 352970, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1023311614990234, "global_step": 352971, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.097292184829712, "global_step": 352972, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.139198064804077, "global_step": 352973, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0933732986450195, "global_step": 352974, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.146573543548584, "global_step": 352975, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.148261547088623, "global_step": 352976, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.104212522506714, "global_step": 352977, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.095376968383789, "global_step": 352978, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1062870025634766, "global_step": 352979, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0404913425445557, "global_step": 352980, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.097944498062134, "global_step": 352981, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.090876340866089, "global_step": 352982, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1408920288085938, "global_step": 352983, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1846704483032227, "global_step": 352984, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0486838817596436, "global_step": 352985, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1152281761169434, "global_step": 352986, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.080761194229126, "global_step": 352987, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.036792039871216, "global_step": 352988, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0711328983306885, "global_step": 352989, "epoch": 714, "lr": 5e-05}
{"train_loss": 1.9879570007324219, "global_step": 352990, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1195080280303955, "global_step": 352991, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1282052993774414, "global_step": 352992, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1295104026794434, "global_step": 352993, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.128430128097534, "global_step": 352994, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.095501184463501, "global_step": 352995, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.096727132797241, "global_step": 352996, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0706944465637207, "global_step": 352997, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1374857425689697, "global_step": 352998, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0686802864074707, "global_step": 352999, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1254959106445312, "global_step": 353000, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.211143970489502, "global_step": 353001, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0706377029418945, "global_step": 353002, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0572731494903564, "global_step": 353003, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0739095211029053, "global_step": 353004, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.118739604949951, "global_step": 353005, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0651907920837402, "global_step": 353006, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0920794010162354, "global_step": 353007, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.170468807220459, "global_step": 353008, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1023621559143066, "global_step": 353009, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.056583881378174, "global_step": 353010, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1531898975372314, "global_step": 353011, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0629074573516846, "global_step": 353012, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.108017921447754, "global_step": 353013, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1028401851654053, "global_step": 353014, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1565239429473877, "global_step": 353015, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.142575263977051, "global_step": 353016, "epoch": 714, "lr": 5e-05}
{"train_loss": 1.9628589153289795, "global_step": 353017, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1058309078216553, "global_step": 353018, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.080517530441284, "global_step": 353019, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.220024824142456, "global_step": 353020, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.102107286453247, "global_step": 353021, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.139786958694458, "global_step": 353022, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0723750591278076, "global_step": 353023, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.068168878555298, "global_step": 353024, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1407713890075684, "global_step": 353025, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1208486557006836, "global_step": 353026, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0701377391815186, "global_step": 353027, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1205499172210693, "global_step": 353028, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0956270694732666, "global_step": 353029, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0693771839141846, "global_step": 353030, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0976946353912354, "global_step": 353031, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1326208114624023, "global_step": 353032, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.157958745956421, "global_step": 353033, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.079523801803589, "global_step": 353034, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0991334915161133, "global_step": 353035, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0271871089935303, "global_step": 353036, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0140221118927, "global_step": 353037, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.017333745956421, "global_step": 353038, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.139420509338379, "global_step": 353039, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1091015338897705, "global_step": 353040, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1387431621551514, "global_step": 353041, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.111598491668701, "global_step": 353042, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1932106018066406, "global_step": 353043, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0355536937713623, "global_step": 353044, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.166287660598755, "global_step": 353045, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.173717975616455, "global_step": 353046, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.136098861694336, "global_step": 353047, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.141444444656372, "global_step": 353048, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.101043224334717, "global_step": 353049, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.087571859359741, "global_step": 353050, "epoch": 714, "lr": 5e-05}
{"train_loss": 1.9783588647842407, "global_step": 353051, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0862209796905518, "global_step": 353052, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.082946538925171, "global_step": 353053, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0930140018463135, "global_step": 353054, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.061264753341675, "global_step": 353055, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1329264640808105, "global_step": 353056, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0740678310394287, "global_step": 353057, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0988545417785645, "global_step": 353058, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.034043788909912, "global_step": 353059, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0651094913482666, "global_step": 353060, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0930817127227783, "global_step": 353061, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.062013626098633, "global_step": 353062, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1335432529449463, "global_step": 353063, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0661332607269287, "global_step": 353064, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1556780338287354, "global_step": 353065, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0864758491516113, "global_step": 353066, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.11340069770813, "global_step": 353067, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.073979616165161, "global_step": 353068, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1726486682891846, "global_step": 353069, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1037838459014893, "global_step": 353070, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.128253936767578, "global_step": 353071, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.085563898086548, "global_step": 353072, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0949487686157227, "global_step": 353073, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.134169101715088, "global_step": 353074, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0599825382232666, "global_step": 353075, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0768229961395264, "global_step": 353076, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.157021999359131, "global_step": 353077, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0434648990631104, "global_step": 353078, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0946645736694336, "global_step": 353079, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.187065601348877, "global_step": 353080, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0435755252838135, "global_step": 353081, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.054600238800049, "global_step": 353082, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0786712169647217, "global_step": 353083, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1115946769714355, "global_step": 353084, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.084430694580078, "global_step": 353085, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0627291202545166, "global_step": 353086, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.07619571685791, "global_step": 353087, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.201021432876587, "global_step": 353088, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.096388816833496, "global_step": 353089, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.120739459991455, "global_step": 353090, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.114755153656006, "global_step": 353091, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0115549564361572, "global_step": 353092, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1055796146392822, "global_step": 353093, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1217904090881348, "global_step": 353094, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.034834384918213, "global_step": 353095, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.06331729888916, "global_step": 353096, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.20648455619812, "global_step": 353097, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.075305223464966, "global_step": 353098, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.105072259902954, "global_step": 353099, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.086984395980835, "global_step": 353100, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.109126091003418, "global_step": 353101, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0576343536376953, "global_step": 353102, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1184475421905518, "global_step": 353103, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0351715087890625, "global_step": 353104, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1059346199035645, "global_step": 353105, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.193657875061035, "global_step": 353106, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.131424903869629, "global_step": 353107, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.158606767654419, "global_step": 353108, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.11110258102417, "global_step": 353109, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1200263500213623, "global_step": 353110, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.053382158279419, "global_step": 353111, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.130380153656006, "global_step": 353112, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.049237012863159, "global_step": 353113, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0800697803497314, "global_step": 353114, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0221803188323975, "global_step": 353115, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1306962966918945, "global_step": 353116, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0890309810638428, "global_step": 353117, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.116986036300659, "global_step": 353118, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0662217140197754, "global_step": 353119, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0962276458740234, "global_step": 353120, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.138136863708496, "global_step": 353121, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.224464178085327, "global_step": 353122, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.120033025741577, "global_step": 353123, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0591304302215576, "global_step": 353124, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.122424602508545, "global_step": 353125, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.005509376525879, "global_step": 353126, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0870654582977295, "global_step": 353127, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0694873332977295, "global_step": 353128, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.025648593902588, "global_step": 353129, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0518758296966553, "global_step": 353130, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.068586826324463, "global_step": 353131, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1313223838806152, "global_step": 353132, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.106020927429199, "global_step": 353133, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.096688747406006, "global_step": 353134, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1554017066955566, "global_step": 353135, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0303704738616943, "global_step": 353136, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0881295204162598, "global_step": 353137, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0969245433807373, "global_step": 353138, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1618080139160156, "global_step": 353139, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.110121488571167, "global_step": 353140, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.020258665084839, "global_step": 353141, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1676225662231445, "global_step": 353142, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.176865816116333, "global_step": 353143, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.208287239074707, "global_step": 353144, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.195394515991211, "global_step": 353145, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0897178649902344, "global_step": 353146, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1592602729797363, "global_step": 353147, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0835886001586914, "global_step": 353148, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.001512289047241, "global_step": 353149, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1199207305908203, "global_step": 353150, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0937676429748535, "global_step": 353151, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.126561403274536, "global_step": 353152, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1388723850250244, "global_step": 353153, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1147849559783936, "global_step": 353154, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1076548099517822, "global_step": 353155, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.123513698577881, "global_step": 353156, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0964455604553223, "global_step": 353157, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.068450689315796, "global_step": 353158, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.072910785675049, "global_step": 353159, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0832645893096924, "global_step": 353160, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.142153739929199, "global_step": 353161, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0643727779388428, "global_step": 353162, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.026454448699951, "global_step": 353163, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1213619709014893, "global_step": 353164, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1631364822387695, "global_step": 353165, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.139822006225586, "global_step": 353166, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0846970081329346, "global_step": 353167, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.13254451751709, "global_step": 353168, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.138930559158325, "global_step": 353169, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1146771907806396, "global_step": 353170, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.07358455657959, "global_step": 353171, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1223275661468506, "global_step": 353172, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1063265800476074, "global_step": 353173, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1121480464935303, "global_step": 353174, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1430060863494873, "global_step": 353175, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2199835777282715, "global_step": 353176, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1126961708068848, "global_step": 353177, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.100900411605835, "global_step": 353178, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0777688026428223, "global_step": 353179, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.243849277496338, "global_step": 353180, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0440707206726074, "global_step": 353181, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1023099422454834, "global_step": 353182, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0792579650878906, "global_step": 353183, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.051631450653076, "global_step": 353184, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.178227663040161, "global_step": 353185, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0629961490631104, "global_step": 353186, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.02734637260437, "global_step": 353187, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1885573863983154, "global_step": 353188, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.016566753387451, "global_step": 353189, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0538604259490967, "global_step": 353190, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0414481163024902, "global_step": 353191, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.142765522003174, "global_step": 353192, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1255977153778076, "global_step": 353193, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.093602418899536, "global_step": 353194, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1571710109710693, "global_step": 353195, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0078182220458984, "global_step": 353196, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.132103443145752, "global_step": 353197, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.097545623779297, "global_step": 353198, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0868685245513916, "global_step": 353199, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1653337478637695, "global_step": 353200, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1638193130493164, "global_step": 353201, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0425124168395996, "global_step": 353202, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1163241863250732, "global_step": 353203, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0653269290924072, "global_step": 353204, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1673171520233154, "global_step": 353205, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2318270206451416, "global_step": 353206, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.185868740081787, "global_step": 353207, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0989177227020264, "global_step": 353208, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0396878719329834, "global_step": 353209, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1405160427093506, "global_step": 353210, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0723142623901367, "global_step": 353211, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.063289165496826, "global_step": 353212, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1335062980651855, "global_step": 353213, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.16393780708313, "global_step": 353214, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1891777515411377, "global_step": 353215, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1091294288635254, "global_step": 353216, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.127102851867676, "global_step": 353217, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0847513675689697, "global_step": 353218, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.123328924179077, "global_step": 353219, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0265085697174072, "global_step": 353220, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0836429595947266, "global_step": 353221, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0605251789093018, "global_step": 353222, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.10798978805542, "global_step": 353223, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2290775775909424, "global_step": 353224, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1068081855773926, "global_step": 353225, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.083709716796875, "global_step": 353226, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1312663555145264, "global_step": 353227, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1004347801208496, "global_step": 353228, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2228641510009766, "global_step": 353229, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1948673725128174, "global_step": 353230, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1058874130249023, "global_step": 353231, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0423762798309326, "global_step": 353232, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1085827350616455, "global_step": 353233, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.054758310317993, "global_step": 353234, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1189725399017334, "global_step": 353235, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.109957218170166, "global_step": 353236, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1943817138671875, "global_step": 353237, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.098205804824829, "global_step": 353238, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0741302967071533, "global_step": 353239, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.173607587814331, "global_step": 353240, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1445324420928955, "global_step": 353241, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.130687952041626, "global_step": 353242, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1555371284484863, "global_step": 353243, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.107980966567993, "global_step": 353244, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1673247814178467, "global_step": 353245, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0298430919647217, "global_step": 353246, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.045306921005249, "global_step": 353247, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.177734136581421, "global_step": 353248, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.201594591140747, "global_step": 353249, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1034481525421143, "global_step": 353250, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1208438873291016, "global_step": 353251, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1099839210510254, "global_step": 353252, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.098191976547241, "global_step": 353253, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.207881450653076, "global_step": 353254, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.116374969482422, "global_step": 353255, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1982059478759766, "global_step": 353256, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.027538776397705, "global_step": 353257, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0531692504882812, "global_step": 353258, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0524847507476807, "global_step": 353259, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.05612850189209, "global_step": 353260, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1609046459198, "global_step": 353261, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0952224731445312, "global_step": 353262, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1389071941375732, "global_step": 353263, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0297839641571045, "global_step": 353264, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1230628490448, "global_step": 353265, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.127631664276123, "global_step": 353266, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0442140102386475, "global_step": 353267, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0593421459198, "global_step": 353268, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0617573261260986, "global_step": 353269, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1202564239501953, "global_step": 353270, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.151654005050659, "global_step": 353271, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1768627166748047, "global_step": 353272, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1334362030029297, "global_step": 353273, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.065394639968872, "global_step": 353274, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.14577317237854, "global_step": 353275, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0935165882110596, "global_step": 353276, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.129222869873047, "global_step": 353277, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.208181142807007, "global_step": 353278, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1897783279418945, "global_step": 353279, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0940849781036377, "global_step": 353280, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.003401279449463, "global_step": 353281, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1646413803100586, "global_step": 353282, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1494991779327393, "global_step": 353283, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1466786861419678, "global_step": 353284, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0966267585754395, "global_step": 353285, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1485533714294434, "global_step": 353286, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.056964159011841, "global_step": 353287, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1236722469329834, "global_step": 353288, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1398816108703613, "global_step": 353289, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.171358108520508, "global_step": 353290, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1476080417633057, "global_step": 353291, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.116499662399292, "global_step": 353292, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1744112968444824, "global_step": 353293, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1023709774017334, "global_step": 353294, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1409189701080322, "global_step": 353295, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0598533153533936, "global_step": 353296, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.097949266433716, "global_step": 353297, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0812180042266846, "global_step": 353298, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0868406295776367, "global_step": 353299, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.162720203399658, "global_step": 353300, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.071415424346924, "global_step": 353301, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.135448455810547, "global_step": 353302, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1377663612365723, "global_step": 353303, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.125178337097168, "global_step": 353304, "epoch": 714, "lr": 5e-05}
{"train_loss": 1.9857525825500488, "global_step": 353305, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0918309688568115, "global_step": 353306, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1288158893585205, "global_step": 353307, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.091764211654663, "global_step": 353308, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.179581642150879, "global_step": 353309, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.126197338104248, "global_step": 353310, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1271376609802246, "global_step": 353311, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1327812671661377, "global_step": 353312, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1135571002960205, "global_step": 353313, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0709259510040283, "global_step": 353314, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.06845760345459, "global_step": 353315, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1940412521362305, "global_step": 353316, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.096017837524414, "global_step": 353317, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1037793159484863, "global_step": 353318, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0708701610565186, "global_step": 353319, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.218531608581543, "global_step": 353320, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1350467205047607, "global_step": 353321, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.042145013809204, "global_step": 353322, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0893166065216064, "global_step": 353323, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.110145330429077, "global_step": 353324, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1255929470062256, "global_step": 353325, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.035274028778076, "global_step": 353326, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1851646900177, "global_step": 353327, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0995500087738037, "global_step": 353328, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.09340500831604, "global_step": 353329, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0540807247161865, "global_step": 353330, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.049427032470703, "global_step": 353331, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.11315655708313, "global_step": 353332, "epoch": 714, "lr": 5e-05}
{"train_loss": 1.9819459915161133, "global_step": 353333, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1276261806488037, "global_step": 353334, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.151171922683716, "global_step": 353335, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.043148994445801, "global_step": 353336, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0952491760253906, "global_step": 353337, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2112319469451904, "global_step": 353338, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.09364914894104, "global_step": 353339, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0897607803344727, "global_step": 353340, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0960693359375, "global_step": 353341, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0788114070892334, "global_step": 353342, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.070971965789795, "global_step": 353343, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.151681900024414, "global_step": 353344, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.146101474761963, "global_step": 353345, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1078124046325684, "global_step": 353346, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.174801826477051, "global_step": 353347, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.130032777786255, "global_step": 353348, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.133798122406006, "global_step": 353349, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.122983932495117, "global_step": 353350, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1563355922698975, "global_step": 353351, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.072070598602295, "global_step": 353352, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1077792644500732, "global_step": 353353, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1550049781799316, "global_step": 353354, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0657339096069336, "global_step": 353355, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1103806495666504, "global_step": 353356, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1145451068878174, "global_step": 353357, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.138857364654541, "global_step": 353358, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1371870040893555, "global_step": 353359, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0949387550354004, "global_step": 353360, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.071521282196045, "global_step": 353361, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.079334259033203, "global_step": 353362, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1479310989379883, "global_step": 353363, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.203775644302368, "global_step": 353364, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0691921710968018, "global_step": 353365, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2082014083862305, "global_step": 353366, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.034792423248291, "global_step": 353367, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.15901255607605, "global_step": 353368, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.185215473175049, "global_step": 353369, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.185041666030884, "global_step": 353370, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1936285495758057, "global_step": 353371, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0183615684509277, "global_step": 353372, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.076148509979248, "global_step": 353373, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0976927280426025, "global_step": 353374, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.059708833694458, "global_step": 353375, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.053335666656494, "global_step": 353376, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0933451652526855, "global_step": 353377, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1452713012695312, "global_step": 353378, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2104291915893555, "global_step": 353379, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1955106258392334, "global_step": 353380, "epoch": 714, "lr": 5e-05}
{"train_loss": 1.9784355163574219, "global_step": 353381, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.135446786880493, "global_step": 353382, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.183929204940796, "global_step": 353383, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0338823795318604, "global_step": 353384, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1669533252716064, "global_step": 353385, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0773894786834717, "global_step": 353386, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1616804599761963, "global_step": 353387, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.057680368423462, "global_step": 353388, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1200623512268066, "global_step": 353389, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2063910961151123, "global_step": 353390, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.122833013534546, "global_step": 353391, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.214801549911499, "global_step": 353392, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.136507034301758, "global_step": 353393, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0982463359832764, "global_step": 353394, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.119349956512451, "global_step": 353395, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.098416328430176, "global_step": 353396, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.031327486038208, "global_step": 353397, "epoch": 714, "lr": 5e-05}
{"train_loss": 1.9934513568878174, "global_step": 353398, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1304807662963867, "global_step": 353399, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.140763282775879, "global_step": 353400, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1233017444610596, "global_step": 353401, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.112628698348999, "global_step": 353402, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0266056060791016, "global_step": 353403, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0193076133728027, "global_step": 353404, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1090657711029053, "global_step": 353405, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0500314235687256, "global_step": 353406, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.036216974258423, "global_step": 353407, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1073124408721924, "global_step": 353408, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1491732597351074, "global_step": 353409, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0747697353363037, "global_step": 353410, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1076292991638184, "global_step": 353411, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0963385105133057, "global_step": 353412, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1344635486602783, "global_step": 353413, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.113281488418579, "global_step": 353414, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.126643180847168, "global_step": 353415, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0142672061920166, "global_step": 353416, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.056419610977173, "global_step": 353417, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0630719661712646, "global_step": 353418, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1145575046539307, "global_step": 353419, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.117434501647949, "global_step": 353420, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0809788703918457, "global_step": 353421, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.18662691116333, "global_step": 353422, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.06172776222229, "global_step": 353423, "epoch": 714, "lr": 5e-05}
{"train_loss": 1.9975709915161133, "global_step": 353424, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1642675399780273, "global_step": 353425, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1466245651245117, "global_step": 353426, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1652355194091797, "global_step": 353427, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.101393461227417, "global_step": 353428, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1771750450134277, "global_step": 353429, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0323734283447266, "global_step": 353430, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.142997980117798, "global_step": 353431, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1045732498168945, "global_step": 353432, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1626334190368652, "global_step": 353433, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0823538303375244, "global_step": 353434, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2200801372528076, "global_step": 353435, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1434786319732666, "global_step": 353436, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1433913707733154, "global_step": 353437, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.018223285675049, "global_step": 353438, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1075820922851562, "global_step": 353439, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1888184547424316, "global_step": 353440, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.131452798843384, "global_step": 353441, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.175980567932129, "global_step": 353442, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1502749919891357, "global_step": 353443, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1126251220703125, "global_step": 353444, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.081233024597168, "global_step": 353445, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2156739234924316, "global_step": 353446, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0282959938049316, "global_step": 353447, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.161961078643799, "global_step": 353448, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1548564434051514, "global_step": 353449, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.117032289505005, "global_step": 353450, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1045804023742676, "global_step": 353451, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0228333473205566, "global_step": 353452, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0874533653259277, "global_step": 353453, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.002650499343872, "global_step": 353454, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.187732219696045, "global_step": 353455, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1133229732513428, "global_step": 353456, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.035471200942993, "global_step": 353457, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1091198921203613, "global_step": 353458, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0509860515594482, "global_step": 353459, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0990195274353027, "global_step": 353460, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1445796489715576, "global_step": 353461, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.042013168334961, "global_step": 353462, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0948476791381836, "global_step": 353463, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.085583209991455, "global_step": 353464, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.15214204788208, "global_step": 353465, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1581363677978516, "global_step": 353466, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.128389358520508, "global_step": 353467, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.10215425491333, "global_step": 353468, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1416871547698975, "global_step": 353469, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0544919967651367, "global_step": 353470, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1196072101593018, "global_step": 353471, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.099367618560791, "global_step": 353472, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.075498342514038, "global_step": 353473, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1056129932403564, "global_step": 353474, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0661072731018066, "global_step": 353475, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.167778253555298, "global_step": 353476, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1272168159484863, "global_step": 353477, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.08298659324646, "global_step": 353478, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0607128143310547, "global_step": 353479, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.078795909881592, "global_step": 353480, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1088457107543945, "global_step": 353481, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.072598695755005, "global_step": 353482, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.056610107421875, "global_step": 353483, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.048558235168457, "global_step": 353484, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0527639389038086, "global_step": 353485, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.178035259246826, "global_step": 353486, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0848770141601562, "global_step": 353487, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1338043212890625, "global_step": 353488, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.08306884765625, "global_step": 353489, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.071510076522827, "global_step": 353490, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1166937351226807, "global_step": 353491, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1361916065216064, "global_step": 353492, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.066068172454834, "global_step": 353493, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0364794731140137, "global_step": 353494, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.115401268005371, "global_step": 353495, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0386815071105957, "global_step": 353496, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0974481105804443, "global_step": 353497, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0760297775268555, "global_step": 353498, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0141468048095703, "global_step": 353499, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.105699062347412, "global_step": 353500, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.112112283706665, "global_step": 353501, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.072251081466675, "global_step": 353502, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.119863510131836, "global_step": 353503, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.004345655441284, "global_step": 353504, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1689293384552, "global_step": 353505, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.187316417694092, "global_step": 353506, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.141505479812622, "global_step": 353507, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0651679039001465, "global_step": 353508, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0735950469970703, "global_step": 353509, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.089963674545288, "global_step": 353510, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0383787155151367, "global_step": 353511, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1134493350982666, "global_step": 353512, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.230269432067871, "global_step": 353513, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.018374443054199, "global_step": 353514, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0345120429992676, "global_step": 353515, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.071589708328247, "global_step": 353516, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.091014862060547, "global_step": 353517, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.162137746810913, "global_step": 353518, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.155221462249756, "global_step": 353519, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.13824200630188, "global_step": 353520, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.060351848602295, "global_step": 353521, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0013411045074463, "global_step": 353522, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0493710041046143, "global_step": 353523, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.056288003921509, "global_step": 353524, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0716795921325684, "global_step": 353525, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.160163640975952, "global_step": 353526, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.106905221939087, "global_step": 353527, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.145900249481201, "global_step": 353528, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.127570867538452, "global_step": 353529, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.100475788116455, "global_step": 353530, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1147754192352295, "global_step": 353531, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.107090711593628, "global_step": 353532, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.130502223968506, "global_step": 353533, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.130007266998291, "global_step": 353534, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1676344871520996, "global_step": 353535, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0936388969421387, "global_step": 353536, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.198225498199463, "global_step": 353537, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1031575202941895, "global_step": 353538, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0607783794403076, "global_step": 353539, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.061129570007324, "global_step": 353540, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.00137996673584, "global_step": 353541, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1341328620910645, "global_step": 353542, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1256840229034424, "global_step": 353543, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.094761848449707, "global_step": 353544, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2014355659484863, "global_step": 353545, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.028737783432007, "global_step": 353546, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.151195764541626, "global_step": 353547, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0919294357299805, "global_step": 353548, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.084059476852417, "global_step": 353549, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.113124370574951, "global_step": 353550, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1227409839630127, "global_step": 353551, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.047748327255249, "global_step": 353552, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.163311719894409, "global_step": 353553, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0750622749328613, "global_step": 353554, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0523312091827393, "global_step": 353555, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.054659843444824, "global_step": 353556, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.081164598464966, "global_step": 353557, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0773308277130127, "global_step": 353558, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1330347061157227, "global_step": 353559, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.120683193206787, "global_step": 353560, "epoch": 714, "lr": 5e-05}
{"train_loss": 1.9932104349136353, "global_step": 353561, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.075913906097412, "global_step": 353562, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.098551034927368, "global_step": 353563, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2094266414642334, "global_step": 353564, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.100104808807373, "global_step": 353565, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.150388479232788, "global_step": 353566, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1710329055786133, "global_step": 353567, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1401734352111816, "global_step": 353568, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0735158920288086, "global_step": 353569, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.120030164718628, "global_step": 353570, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.081537961959839, "global_step": 353571, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1450278759002686, "global_step": 353572, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2046618461608887, "global_step": 353573, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0594537258148193, "global_step": 353574, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1870064735412598, "global_step": 353575, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.157291889190674, "global_step": 353576, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1308305263519287, "global_step": 353577, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1056299209594727, "global_step": 353578, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.267329216003418, "global_step": 353579, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.075413703918457, "global_step": 353580, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1732187271118164, "global_step": 353581, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.207918405532837, "global_step": 353582, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1343564987182617, "global_step": 353583, "epoch": 714, "lr": 5e-05}
{"train_loss": 1.9921560287475586, "global_step": 353584, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.156961679458618, "global_step": 353585, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0272858142852783, "global_step": 353586, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1670851707458496, "global_step": 353587, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1132864952087402, "global_step": 353588, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.255781888961792, "global_step": 353589, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1311678886413574, "global_step": 353590, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1538310050964355, "global_step": 353591, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0896084308624268, "global_step": 353592, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.115662097930908, "global_step": 353593, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.002732753753662, "global_step": 353594, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.025569438934326, "global_step": 353595, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1263251304626465, "global_step": 353596, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0447754859924316, "global_step": 353597, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0432932376861572, "global_step": 353598, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0609912872314453, "global_step": 353599, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1437530517578125, "global_step": 353600, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.165349245071411, "global_step": 353601, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0893332958221436, "global_step": 353602, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.046034574508667, "global_step": 353603, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0787479877471924, "global_step": 353604, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0204174518585205, "global_step": 353605, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1192023754119873, "global_step": 353606, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1279237270355225, "global_step": 353607, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0259718894958496, "global_step": 353608, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.05204701423645, "global_step": 353609, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1071786880493164, "global_step": 353610, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.045454740524292, "global_step": 353611, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1614513397216797, "global_step": 353612, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.079951524734497, "global_step": 353613, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0962653160095215, "global_step": 353614, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1703498363494873, "global_step": 353615, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.189202070236206, "global_step": 353616, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1252264976501465, "global_step": 353617, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.123652696609497, "global_step": 353618, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.07199764251709, "global_step": 353619, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.166867256164551, "global_step": 353620, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.138547420501709, "global_step": 353621, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.125471353530884, "global_step": 353622, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.178278684616089, "global_step": 353623, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1163008213043213, "global_step": 353624, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0500636100769043, "global_step": 353625, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.114093780517578, "global_step": 353626, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1173059940338135, "global_step": 353627, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1170616149902344, "global_step": 353628, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.11826753616333, "global_step": 353629, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.124671459197998, "global_step": 353630, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1287386417388916, "global_step": 353631, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.211010456085205, "global_step": 353632, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1580004692077637, "global_step": 353633, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.123014211654663, "global_step": 353634, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0571720600128174, "global_step": 353635, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0649850368499756, "global_step": 353636, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0380465984344482, "global_step": 353637, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0779600143432617, "global_step": 353638, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.14786958694458, "global_step": 353639, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.135274887084961, "global_step": 353640, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1867122650146484, "global_step": 353641, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1172330379486084, "global_step": 353642, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1277685165405273, "global_step": 353643, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.179414987564087, "global_step": 353644, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.079835891723633, "global_step": 353645, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1973297595977783, "global_step": 353646, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.137333393096924, "global_step": 353647, "epoch": 714, "lr": 5e-05}
{"train_loss": 1.9995521306991577, "global_step": 353648, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1526331901550293, "global_step": 353649, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1274213790893555, "global_step": 353650, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0478432178497314, "global_step": 353651, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0587425231933594, "global_step": 353652, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.135063886642456, "global_step": 353653, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.107710599899292, "global_step": 353654, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.178363800048828, "global_step": 353655, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.15619158744812, "global_step": 353656, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.188401937484741, "global_step": 353657, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.181107759475708, "global_step": 353658, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0707273483276367, "global_step": 353659, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0920565128326416, "global_step": 353660, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0325474739074707, "global_step": 353661, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1142492294311523, "global_step": 353662, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1203300952911377, "global_step": 353663, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0990846157073975, "global_step": 353664, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0398130416870117, "global_step": 353665, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1841683387756348, "global_step": 353666, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0049304962158203, "global_step": 353667, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.107738733291626, "global_step": 353668, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0901215076446533, "global_step": 353669, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.028639316558838, "global_step": 353670, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.177619457244873, "global_step": 353671, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0546441078186035, "global_step": 353672, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.111219882965088, "global_step": 353673, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0816352367401123, "global_step": 353674, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1035807132720947, "global_step": 353675, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0771589279174805, "global_step": 353676, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0942134857177734, "global_step": 353677, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.099504232406616, "global_step": 353678, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.033506393432617, "global_step": 353679, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.176715135574341, "global_step": 353680, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1297786235809326, "global_step": 353681, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1354141235351562, "global_step": 353682, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1099655628204346, "global_step": 353683, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1810290813446045, "global_step": 353684, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.095400094985962, "global_step": 353685, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1175880432128906, "global_step": 353686, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.164365530014038, "global_step": 353687, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.067317008972168, "global_step": 353688, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.20763897895813, "global_step": 353689, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1842539310455322, "global_step": 353690, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0583720207214355, "global_step": 353691, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.140150308609009, "global_step": 353692, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.106585741043091, "global_step": 353693, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1319456100463867, "global_step": 353694, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.076188087463379, "global_step": 353695, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.161959171295166, "global_step": 353696, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0682966709136963, "global_step": 353697, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0736284255981445, "global_step": 353698, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1249358654022217, "global_step": 353699, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1130855083465576, "global_step": 353700, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0767743587493896, "global_step": 353701, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0610060691833496, "global_step": 353702, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1390464305877686, "global_step": 353703, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1041393280029297, "global_step": 353704, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1162073612213135, "global_step": 353705, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.043076515197754, "global_step": 353706, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0455708503723145, "global_step": 353707, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2045490741729736, "global_step": 353708, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0309154987335205, "global_step": 353709, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1406233310699463, "global_step": 353710, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1021790504455566, "global_step": 353711, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0590898990631104, "global_step": 353712, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1726303100585938, "global_step": 353713, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.124110698699951, "global_step": 353714, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0632216930389404, "global_step": 353715, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.133371353149414, "global_step": 353716, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0888304710388184, "global_step": 353717, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.147169351577759, "global_step": 353718, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1717631816864014, "global_step": 353719, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0680320262908936, "global_step": 353720, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.052583694458008, "global_step": 353721, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.058573007583618, "global_step": 353722, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.176557779312134, "global_step": 353723, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.120699644088745, "global_step": 353724, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.108551025390625, "global_step": 353725, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1504299640655518, "global_step": 353726, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.104903221130371, "global_step": 353727, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.158893585205078, "global_step": 353728, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1587066650390625, "global_step": 353729, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1544973850250244, "global_step": 353730, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.08837628364563, "global_step": 353731, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1524765491485596, "global_step": 353732, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0978517532348633, "global_step": 353733, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0792455673217773, "global_step": 353734, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.069801092147827, "global_step": 353735, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.207458019256592, "global_step": 353736, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0892605781555176, "global_step": 353737, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1219322681427, "global_step": 353738, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0574512481689453, "global_step": 353739, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.107827663421631, "global_step": 353740, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1252329349517822, "global_step": 353741, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.08994722366333, "global_step": 353742, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1672985553741455, "global_step": 353743, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0961644649505615, "global_step": 353744, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0636773109436035, "global_step": 353745, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.104862928390503, "global_step": 353746, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1492350101470947, "global_step": 353747, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1054599285125732, "global_step": 353748, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0843582153320312, "global_step": 353749, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0850577354431152, "global_step": 353750, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0519027709960938, "global_step": 353751, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.088193416595459, "global_step": 353752, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.084895610809326, "global_step": 353753, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.183173894882202, "global_step": 353754, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.144918918609619, "global_step": 353755, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1339378356933594, "global_step": 353756, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.054304361343384, "global_step": 353757, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0581188201904297, "global_step": 353758, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.111020088195801, "global_step": 353759, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0373826026916504, "global_step": 353760, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1041259765625, "global_step": 353761, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0363292694091797, "global_step": 353762, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1770684719085693, "global_step": 353763, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1466286182403564, "global_step": 353764, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1925830841064453, "global_step": 353765, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1513848304748535, "global_step": 353766, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.165306568145752, "global_step": 353767, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.188084125518799, "global_step": 353768, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.065162181854248, "global_step": 353769, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.162524700164795, "global_step": 353770, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.087820053100586, "global_step": 353771, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0692505836486816, "global_step": 353772, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1804230213165283, "global_step": 353773, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0682058334350586, "global_step": 353774, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0591492652893066, "global_step": 353775, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.115955352783203, "global_step": 353776, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1413726806640625, "global_step": 353777, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1531739234924316, "global_step": 353778, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1524882316589355, "global_step": 353779, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.182162046432495, "global_step": 353780, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1430068016052246, "global_step": 353781, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.148944854736328, "global_step": 353782, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.132080554962158, "global_step": 353783, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1742804050445557, "global_step": 353784, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.095275640487671, "global_step": 353785, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0938868522644043, "global_step": 353786, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.053280830383301, "global_step": 353787, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0932841300964355, "global_step": 353788, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2019622325897217, "global_step": 353789, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.050102710723877, "global_step": 353790, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.138552188873291, "global_step": 353791, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1677613258361816, "global_step": 353792, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2038607597351074, "global_step": 353793, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1375458240509033, "global_step": 353794, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.06817889213562, "global_step": 353795, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0426876544952393, "global_step": 353796, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.125697135925293, "global_step": 353797, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1417577266693115, "global_step": 353798, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.263878583908081, "global_step": 353799, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.232956886291504, "global_step": 353800, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1303293704986572, "global_step": 353801, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.191964864730835, "global_step": 353802, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.256551742553711, "global_step": 353803, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.110996961593628, "global_step": 353804, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.164912462234497, "global_step": 353805, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.224346876144409, "global_step": 353806, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.186920404434204, "global_step": 353807, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0910940170288086, "global_step": 353808, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.178846836090088, "global_step": 353809, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.2001585960388184, "global_step": 353810, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.0541491508483887, "global_step": 353811, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.031687021255493, "global_step": 353812, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.20558762550354, "global_step": 353813, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.051748514175415, "global_step": 353814, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.106417179107666, "global_step": 353815, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.091888189315796, "global_step": 353816, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1083123683929443, "global_step": 353817, "epoch": 714, "lr": 5e-05}
{"train_loss": 2.1174497604370117, "global_step": 353818, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1156787872314453, "global_step": 353819, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.108694076538086, "global_step": 353820, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1224524974823, "global_step": 353821, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0445079803466797, "global_step": 353822, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0315797328948975, "global_step": 353823, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0393898487091064, "global_step": 353824, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.103985548019409, "global_step": 353825, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.07529878616333, "global_step": 353826, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0487873554229736, "global_step": 353827, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0472984313964844, "global_step": 353828, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.087761163711548, "global_step": 353829, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0564215183258057, "global_step": 353830, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.108297824859619, "global_step": 353831, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.115377902984619, "global_step": 353832, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1575300693511963, "global_step": 353833, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0612308979034424, "global_step": 353834, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1176204681396484, "global_step": 353835, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.085245132446289, "global_step": 353836, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0506479740142822, "global_step": 353837, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.098806619644165, "global_step": 353838, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.064225912094116, "global_step": 353839, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0292346477508545, "global_step": 353840, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.186037540435791, "global_step": 353841, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.107581853866577, "global_step": 353842, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.119434356689453, "global_step": 353843, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.141697883605957, "global_step": 353844, "epoch": 715, "lr": 5e-05}
{"train_loss": 1.9992703199386597, "global_step": 353845, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.05465030670166, "global_step": 353846, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1622581481933594, "global_step": 353847, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1107263565063477, "global_step": 353848, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0055625438690186, "global_step": 353849, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1007702350616455, "global_step": 353850, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.123556613922119, "global_step": 353851, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0458719730377197, "global_step": 353852, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0314390659332275, "global_step": 353853, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.111278533935547, "global_step": 353854, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1169307231903076, "global_step": 353855, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.051683187484741, "global_step": 353856, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.117382049560547, "global_step": 353857, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.121227979660034, "global_step": 353858, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.109433889389038, "global_step": 353859, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0737624168395996, "global_step": 353860, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0738675594329834, "global_step": 353861, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0858209133148193, "global_step": 353862, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1171536445617676, "global_step": 353863, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.053548812866211, "global_step": 353864, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.088282585144043, "global_step": 353865, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.015786647796631, "global_step": 353866, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.112825870513916, "global_step": 353867, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1930413246154785, "global_step": 353868, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.121633529663086, "global_step": 353869, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2312676906585693, "global_step": 353870, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0549674034118652, "global_step": 353871, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.14499568939209, "global_step": 353872, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.099893808364868, "global_step": 353873, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0604758262634277, "global_step": 353874, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.081125497817993, "global_step": 353875, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1530838012695312, "global_step": 353876, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0682709217071533, "global_step": 353877, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.125701665878296, "global_step": 353878, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0354180335998535, "global_step": 353879, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.153045654296875, "global_step": 353880, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1558265686035156, "global_step": 353881, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0984578132629395, "global_step": 353882, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.050241708755493, "global_step": 353883, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0393311977386475, "global_step": 353884, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1685116291046143, "global_step": 353885, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1315672397613525, "global_step": 353886, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0521044731140137, "global_step": 353887, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2556235790252686, "global_step": 353888, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.116253614425659, "global_step": 353889, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0794005393981934, "global_step": 353890, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0944886207580566, "global_step": 353891, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1134285926818848, "global_step": 353892, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.096923351287842, "global_step": 353893, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.088711738586426, "global_step": 353894, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1076157093048096, "global_step": 353895, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.037403106689453, "global_step": 353896, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1967854499816895, "global_step": 353897, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1596672534942627, "global_step": 353898, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.090151786804199, "global_step": 353899, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0879099369049072, "global_step": 353900, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.060561418533325, "global_step": 353901, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1656076908111572, "global_step": 353902, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.196246862411499, "global_step": 353903, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1184234619140625, "global_step": 353904, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.07723331451416, "global_step": 353905, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.024686336517334, "global_step": 353906, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0937647819519043, "global_step": 353907, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0860531330108643, "global_step": 353908, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.188692092895508, "global_step": 353909, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.054704427719116, "global_step": 353910, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1164486408233643, "global_step": 353911, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1010899543762207, "global_step": 353912, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.097554922103882, "global_step": 353913, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0777623653411865, "global_step": 353914, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1683974266052246, "global_step": 353915, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0800535678863525, "global_step": 353916, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.092306137084961, "global_step": 353917, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1078710556030273, "global_step": 353918, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0559873580932617, "global_step": 353919, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.123185157775879, "global_step": 353920, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.142298698425293, "global_step": 353921, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.090801954269409, "global_step": 353922, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.132782220840454, "global_step": 353923, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.103686809539795, "global_step": 353924, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1614389419555664, "global_step": 353925, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0933327674865723, "global_step": 353926, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.063075304031372, "global_step": 353927, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0305581092834473, "global_step": 353928, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1376731395721436, "global_step": 353929, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0152580738067627, "global_step": 353930, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1185855865478516, "global_step": 353931, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1714978218078613, "global_step": 353932, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.114577054977417, "global_step": 353933, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.091294765472412, "global_step": 353934, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0503697395324707, "global_step": 353935, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1339614391326904, "global_step": 353936, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0305914878845215, "global_step": 353937, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0414559841156006, "global_step": 353938, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1386218070983887, "global_step": 353939, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0315988063812256, "global_step": 353940, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.158893346786499, "global_step": 353941, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.04203462600708, "global_step": 353942, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0909571647644043, "global_step": 353943, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.12007212638855, "global_step": 353944, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1350326538085938, "global_step": 353945, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1533865928649902, "global_step": 353946, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.111258029937744, "global_step": 353947, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.114419937133789, "global_step": 353948, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0796024799346924, "global_step": 353949, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0939948558807373, "global_step": 353950, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1506917476654053, "global_step": 353951, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0213892459869385, "global_step": 353952, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.09785795211792, "global_step": 353953, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.063777208328247, "global_step": 353954, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1311841011047363, "global_step": 353955, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1798484325408936, "global_step": 353956, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.046745777130127, "global_step": 353957, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1193182468414307, "global_step": 353958, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0857906341552734, "global_step": 353959, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.072178602218628, "global_step": 353960, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1065757274627686, "global_step": 353961, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0931053161621094, "global_step": 353962, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.144392967224121, "global_step": 353963, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0539472103118896, "global_step": 353964, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1353759765625, "global_step": 353965, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1772968769073486, "global_step": 353966, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.087007999420166, "global_step": 353967, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.064343214035034, "global_step": 353968, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1740784645080566, "global_step": 353969, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1047556400299072, "global_step": 353970, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.091071844100952, "global_step": 353971, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.180708885192871, "global_step": 353972, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.078967571258545, "global_step": 353973, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0545740127563477, "global_step": 353974, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1756911277770996, "global_step": 353975, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1000874042510986, "global_step": 353976, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.120887517929077, "global_step": 353977, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.087656021118164, "global_step": 353978, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.137655019760132, "global_step": 353979, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0931384563446045, "global_step": 353980, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1409900188446045, "global_step": 353981, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0887515544891357, "global_step": 353982, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1410107612609863, "global_step": 353983, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1034107208251953, "global_step": 353984, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1061623096466064, "global_step": 353985, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0789425373077393, "global_step": 353986, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.076826333999634, "global_step": 353987, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0979843139648438, "global_step": 353988, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2275407314300537, "global_step": 353989, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.085631847381592, "global_step": 353990, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.088447093963623, "global_step": 353991, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1113040447235107, "global_step": 353992, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1610028743743896, "global_step": 353993, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.003836154937744, "global_step": 353994, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1356656551361084, "global_step": 353995, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.100581169128418, "global_step": 353996, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1184113025665283, "global_step": 353997, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.013927459716797, "global_step": 353998, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0722203254699707, "global_step": 353999, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1131718158721924, "global_step": 354000, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1501903533935547, "global_step": 354001, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1286046504974365, "global_step": 354002, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.180177688598633, "global_step": 354003, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.047933578491211, "global_step": 354004, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.221924304962158, "global_step": 354005, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.114664077758789, "global_step": 354006, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0861856937408447, "global_step": 354007, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.090707540512085, "global_step": 354008, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0810487270355225, "global_step": 354009, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.16363787651062, "global_step": 354010, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.184837579727173, "global_step": 354011, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0364413261413574, "global_step": 354012, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1515164375305176, "global_step": 354013, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0507352352142334, "global_step": 354014, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0537729263305664, "global_step": 354015, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0811116695404053, "global_step": 354016, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2282323837280273, "global_step": 354017, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.154017925262451, "global_step": 354018, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0876522064208984, "global_step": 354019, "epoch": 715, "lr": 5e-05}
{"train_loss": 1.9956507682800293, "global_step": 354020, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2231178283691406, "global_step": 354021, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.045966386795044, "global_step": 354022, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.039977550506592, "global_step": 354023, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.120239496231079, "global_step": 354024, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0575733184814453, "global_step": 354025, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1013550758361816, "global_step": 354026, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0008535385131836, "global_step": 354027, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0607833862304688, "global_step": 354028, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1496384143829346, "global_step": 354029, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0893261432647705, "global_step": 354030, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.149632453918457, "global_step": 354031, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1400146484375, "global_step": 354032, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1067233085632324, "global_step": 354033, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1106278896331787, "global_step": 354034, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0359363555908203, "global_step": 354035, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1119959354400635, "global_step": 354036, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1355948448181152, "global_step": 354037, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.088536024093628, "global_step": 354038, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.12848162651062, "global_step": 354039, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0410873889923096, "global_step": 354040, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1169660091400146, "global_step": 354041, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1679747104644775, "global_step": 354042, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0059969425201416, "global_step": 354043, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.118203639984131, "global_step": 354044, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0704197883605957, "global_step": 354045, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.167487144470215, "global_step": 354046, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0819973945617676, "global_step": 354047, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.134153127670288, "global_step": 354048, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0555167198181152, "global_step": 354049, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.000894069671631, "global_step": 354050, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2234957218170166, "global_step": 354051, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.117401599884033, "global_step": 354052, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.114795446395874, "global_step": 354053, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1678314208984375, "global_step": 354054, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.083538293838501, "global_step": 354055, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.098360061645508, "global_step": 354056, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.024120330810547, "global_step": 354057, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0732266902923584, "global_step": 354058, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.086406946182251, "global_step": 354059, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1071510314941406, "global_step": 354060, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1620378494262695, "global_step": 354061, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.143489360809326, "global_step": 354062, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.152099609375, "global_step": 354063, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0115468502044678, "global_step": 354064, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.108290195465088, "global_step": 354065, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.145111560821533, "global_step": 354066, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0565128326416016, "global_step": 354067, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.183727741241455, "global_step": 354068, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1131093502044678, "global_step": 354069, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.020712375640869, "global_step": 354070, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1539127826690674, "global_step": 354071, "epoch": 715, "lr": 5e-05}
{"train_loss": 1.9773728847503662, "global_step": 354072, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.198939323425293, "global_step": 354073, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0914723873138428, "global_step": 354074, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1672916412353516, "global_step": 354075, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.206861734390259, "global_step": 354076, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0223922729492188, "global_step": 354077, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1162972450256348, "global_step": 354078, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.116292953491211, "global_step": 354079, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1249313354492188, "global_step": 354080, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.056429386138916, "global_step": 354081, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0920732021331787, "global_step": 354082, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.141601324081421, "global_step": 354083, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1767473220825195, "global_step": 354084, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0352180004119873, "global_step": 354085, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0477118492126465, "global_step": 354086, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0883524417877197, "global_step": 354087, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0140256881713867, "global_step": 354088, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1682958602905273, "global_step": 354089, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.113210916519165, "global_step": 354090, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.045989990234375, "global_step": 354091, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.036302089691162, "global_step": 354092, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.084354877471924, "global_step": 354093, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.155292272567749, "global_step": 354094, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.084304094314575, "global_step": 354095, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.103710889816284, "global_step": 354096, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1084046363830566, "global_step": 354097, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0893731117248535, "global_step": 354098, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1060950756073, "global_step": 354099, "epoch": 715, "lr": 5e-05}
{"train_loss": 1.9946463108062744, "global_step": 354100, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1010935306549072, "global_step": 354101, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.15311598777771, "global_step": 354102, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1557390689849854, "global_step": 354103, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0812277793884277, "global_step": 354104, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.058887243270874, "global_step": 354105, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.115478277206421, "global_step": 354106, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.061286211013794, "global_step": 354107, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1431901454925537, "global_step": 354108, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.10463809967041, "global_step": 354109, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.065864086151123, "global_step": 354110, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.251075029373169, "global_step": 354111, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0320165157318115, "global_step": 354112, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0832998752593994, "global_step": 354113, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0074853897094727, "global_step": 354114, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.062734365463257, "global_step": 354115, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.182950496673584, "global_step": 354116, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1054348945617676, "global_step": 354117, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0618553161621094, "global_step": 354118, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0095505714416504, "global_step": 354119, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0942060947418213, "global_step": 354120, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0854837894439697, "global_step": 354121, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.127178192138672, "global_step": 354122, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.158055543899536, "global_step": 354123, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.146059036254883, "global_step": 354124, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.113532066345215, "global_step": 354125, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1923716068267822, "global_step": 354126, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0577023029327393, "global_step": 354127, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.10414457321167, "global_step": 354128, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1139400005340576, "global_step": 354129, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1694836616516113, "global_step": 354130, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0463788509368896, "global_step": 354131, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1261792182922363, "global_step": 354132, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.167672634124756, "global_step": 354133, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.198765754699707, "global_step": 354134, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0705294609069824, "global_step": 354135, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.073648691177368, "global_step": 354136, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.106933832168579, "global_step": 354137, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1336848735809326, "global_step": 354138, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1000328063964844, "global_step": 354139, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.130643129348755, "global_step": 354140, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1125404834747314, "global_step": 354141, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.065640449523926, "global_step": 354142, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1148197650909424, "global_step": 354143, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.112015962600708, "global_step": 354144, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.079191207885742, "global_step": 354145, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0666933059692383, "global_step": 354146, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1424520015716553, "global_step": 354147, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1556785106658936, "global_step": 354148, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0636415481567383, "global_step": 354149, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.012810230255127, "global_step": 354150, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.164276123046875, "global_step": 354151, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.16096830368042, "global_step": 354152, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.184465169906616, "global_step": 354153, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1394736766815186, "global_step": 354154, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.129582643508911, "global_step": 354155, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0909080505371094, "global_step": 354156, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.157615900039673, "global_step": 354157, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.13997220993042, "global_step": 354158, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.009038209915161, "global_step": 354159, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1341946125030518, "global_step": 354160, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.146986484527588, "global_step": 354161, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.141085624694824, "global_step": 354162, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.084425687789917, "global_step": 354163, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0989139080047607, "global_step": 354164, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.070509672164917, "global_step": 354165, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.114100933074951, "global_step": 354166, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.077392578125, "global_step": 354167, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1884634494781494, "global_step": 354168, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.179349899291992, "global_step": 354169, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.201205253601074, "global_step": 354170, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.053161144256592, "global_step": 354171, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.077188491821289, "global_step": 354172, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.051358222961426, "global_step": 354173, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1810309886932373, "global_step": 354174, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.07063364982605, "global_step": 354175, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.142971992492676, "global_step": 354176, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1026737689971924, "global_step": 354177, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.162968158721924, "global_step": 354178, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1022770404815674, "global_step": 354179, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.170961618423462, "global_step": 354180, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0833516120910645, "global_step": 354181, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1085946559906006, "global_step": 354182, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.109964609146118, "global_step": 354183, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.096390962600708, "global_step": 354184, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.044896125793457, "global_step": 354185, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1677234172821045, "global_step": 354186, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0986108779907227, "global_step": 354187, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.071533203125, "global_step": 354188, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1771392822265625, "global_step": 354189, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2147207260131836, "global_step": 354190, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.069772243499756, "global_step": 354191, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.137535572052002, "global_step": 354192, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0869486331939697, "global_step": 354193, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.177807092666626, "global_step": 354194, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.083486795425415, "global_step": 354195, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.112863540649414, "global_step": 354196, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.171984910964966, "global_step": 354197, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.103647232055664, "global_step": 354198, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.121877908706665, "global_step": 354199, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0376806259155273, "global_step": 354200, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.089214324951172, "global_step": 354201, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.197835922241211, "global_step": 354202, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.135571241378784, "global_step": 354203, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.124225616455078, "global_step": 354204, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.056879997253418, "global_step": 354205, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.127070426940918, "global_step": 354206, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.054635763168335, "global_step": 354207, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.093639373779297, "global_step": 354208, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.121856689453125, "global_step": 354209, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.135756492614746, "global_step": 354210, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1109325885772705, "global_step": 354211, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.099853277206421, "global_step": 354212, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.01448655128479, "global_step": 354213, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0369317531585693, "global_step": 354214, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.151721477508545, "global_step": 354215, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1938071250915527, "global_step": 354216, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1759192943573, "global_step": 354217, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0333685874938965, "global_step": 354218, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1505117416381836, "global_step": 354219, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0629897117614746, "global_step": 354220, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0611653327941895, "global_step": 354221, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.127032518386841, "global_step": 354222, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0972964763641357, "global_step": 354223, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.121077299118042, "global_step": 354224, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1436495780944824, "global_step": 354225, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2030537128448486, "global_step": 354226, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0159783363342285, "global_step": 354227, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.15971302986145, "global_step": 354228, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.021496534347534, "global_step": 354229, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2331767082214355, "global_step": 354230, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.11759614944458, "global_step": 354231, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.03415584564209, "global_step": 354232, "epoch": 715, "lr": 5e-05}
{"train_loss": 1.957855463027954, "global_step": 354233, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0203237533569336, "global_step": 354234, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0507442951202393, "global_step": 354235, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.138366222381592, "global_step": 354236, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.091541290283203, "global_step": 354237, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0947110652923584, "global_step": 354238, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.10958194732666, "global_step": 354239, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0167458057403564, "global_step": 354240, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.011397361755371, "global_step": 354241, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.136444330215454, "global_step": 354242, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.135326385498047, "global_step": 354243, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1771903038024902, "global_step": 354244, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1080286502838135, "global_step": 354245, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1242120265960693, "global_step": 354246, "epoch": 715, "lr": 5e-05}
{"train_loss": 1.984076738357544, "global_step": 354247, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.195604085922241, "global_step": 354248, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1161420345306396, "global_step": 354249, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0228023529052734, "global_step": 354250, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.024522542953491, "global_step": 354251, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1917243003845215, "global_step": 354252, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1688709259033203, "global_step": 354253, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1570534706115723, "global_step": 354254, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.098301649093628, "global_step": 354255, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1226003170013428, "global_step": 354256, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.072399616241455, "global_step": 354257, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.107177257537842, "global_step": 354258, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.015284538269043, "global_step": 354259, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.196659564971924, "global_step": 354260, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0936620235443115, "global_step": 354261, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1081438064575195, "global_step": 354262, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0974843502044678, "global_step": 354263, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0005786418914795, "global_step": 354264, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0300614833831787, "global_step": 354265, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.067345142364502, "global_step": 354266, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0860540866851807, "global_step": 354267, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.164201259613037, "global_step": 354268, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1390676498413086, "global_step": 354269, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1317389011383057, "global_step": 354270, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0915796756744385, "global_step": 354271, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0811045169830322, "global_step": 354272, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.032846450805664, "global_step": 354273, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1130614280700684, "global_step": 354274, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0762760639190674, "global_step": 354275, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1421029567718506, "global_step": 354276, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.100078821182251, "global_step": 354277, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1376407146453857, "global_step": 354278, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.034224271774292, "global_step": 354279, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.094369411468506, "global_step": 354280, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0855674743652344, "global_step": 354281, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.111609935760498, "global_step": 354282, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.140082597732544, "global_step": 354283, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0662355422973633, "global_step": 354284, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0331308841705322, "global_step": 354285, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0442237854003906, "global_step": 354286, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.151273012161255, "global_step": 354287, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.144960403442383, "global_step": 354288, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1643903255462646, "global_step": 354289, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0417916774749756, "global_step": 354290, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1318795680999756, "global_step": 354291, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.059835433959961, "global_step": 354292, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.144329071044922, "global_step": 354293, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1271376609802246, "global_step": 354294, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1814868450164795, "global_step": 354295, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.228978395462036, "global_step": 354296, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.049968957901001, "global_step": 354297, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0434694290161133, "global_step": 354298, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.067378520965576, "global_step": 354299, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.136087417602539, "global_step": 354300, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1045870780944824, "global_step": 354301, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.158724308013916, "global_step": 354302, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.048837423324585, "global_step": 354303, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1617138385772705, "global_step": 354304, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1065640449523926, "global_step": 354305, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0793659687042236, "global_step": 354306, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1020216941833496, "global_step": 354307, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1081926822662354, "global_step": 354308, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0935170650482178, "global_step": 354309, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.155681610107422, "global_step": 354310, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0928874015808105, "global_step": 354311, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.128727912902832, "global_step": 354312, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0835518836975098, "global_step": 354313, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1897668838500977, "global_step": 354314, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1395277976989746, "global_step": 354315, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0954551696777344, "global_step": 354316, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0013444423675537, "global_step": 354317, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0632851123809814, "global_step": 354318, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1396870613098145, "global_step": 354319, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.076808214187622, "global_step": 354320, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1188912391662598, "global_step": 354321, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1541481018066406, "global_step": 354322, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1619536876678467, "global_step": 354323, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.172213554382324, "global_step": 354324, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0903432369232178, "global_step": 354325, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.032379388809204, "global_step": 354326, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1453614234924316, "global_step": 354327, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1748554706573486, "global_step": 354328, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.049379348754883, "global_step": 354329, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0795998573303223, "global_step": 354330, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.184796094894409, "global_step": 354331, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0817372798919678, "global_step": 354332, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1494553089141846, "global_step": 354333, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0998878479003906, "global_step": 354334, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.123347520828247, "global_step": 354335, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.064513921737671, "global_step": 354336, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.066265106201172, "global_step": 354337, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1790175437927246, "global_step": 354338, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1902244091033936, "global_step": 354339, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1135079860687256, "global_step": 354340, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1278629302978516, "global_step": 354341, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.142651319503784, "global_step": 354342, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.094404458999634, "global_step": 354343, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0343616008758545, "global_step": 354344, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1369545459747314, "global_step": 354345, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1458375453948975, "global_step": 354346, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1684412956237793, "global_step": 354347, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.215958833694458, "global_step": 354348, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0655112266540527, "global_step": 354349, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.140253782272339, "global_step": 354350, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0954501628875732, "global_step": 354351, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.139716148376465, "global_step": 354352, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1425883769989014, "global_step": 354353, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1084203720092773, "global_step": 354354, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.121880531311035, "global_step": 354355, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1766440868377686, "global_step": 354356, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0693957805633545, "global_step": 354357, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.052361011505127, "global_step": 354358, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.214446544647217, "global_step": 354359, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1211788654327393, "global_step": 354360, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.182081460952759, "global_step": 354361, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0938222408294678, "global_step": 354362, "epoch": 715, "lr": 5e-05}
{"train_loss": 1.9866819381713867, "global_step": 354363, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0974128246307373, "global_step": 354364, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0607237815856934, "global_step": 354365, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0641708374023438, "global_step": 354366, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1550607681274414, "global_step": 354367, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1413817405700684, "global_step": 354368, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.155487298965454, "global_step": 354369, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.092428684234619, "global_step": 354370, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.080322742462158, "global_step": 354371, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0575690269470215, "global_step": 354372, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1359968185424805, "global_step": 354373, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.059006452560425, "global_step": 354374, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1350440979003906, "global_step": 354375, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1616790294647217, "global_step": 354376, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1719815731048584, "global_step": 354377, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1855835914611816, "global_step": 354378, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.088721513748169, "global_step": 354379, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1434519290924072, "global_step": 354380, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1559340953826904, "global_step": 354381, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1172235012054443, "global_step": 354382, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1395106315612793, "global_step": 354383, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0741233825683594, "global_step": 354384, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.111088275909424, "global_step": 354385, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.089759588241577, "global_step": 354386, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0902111530303955, "global_step": 354387, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1696135997772217, "global_step": 354388, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0998101234436035, "global_step": 354389, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0255181789398193, "global_step": 354390, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1328506469726562, "global_step": 354391, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.125950813293457, "global_step": 354392, "epoch": 715, "lr": 5e-05}
{"train_loss": 1.9937214851379395, "global_step": 354393, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.069830894470215, "global_step": 354394, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.114821195602417, "global_step": 354395, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0850417613983154, "global_step": 354396, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1418721675872803, "global_step": 354397, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0902202129364014, "global_step": 354398, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0919458866119385, "global_step": 354399, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1002352237701416, "global_step": 354400, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1420674324035645, "global_step": 354401, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1685879230499268, "global_step": 354402, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.159674882888794, "global_step": 354403, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.04571533203125, "global_step": 354404, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.083181381225586, "global_step": 354405, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0998599529266357, "global_step": 354406, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.106398105621338, "global_step": 354407, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.204091787338257, "global_step": 354408, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.080573558807373, "global_step": 354409, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.11027193069458, "global_step": 354410, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0645382404327393, "global_step": 354411, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1379811763763428, "global_step": 354412, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.015076160430908, "global_step": 354413, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1354358196258545, "global_step": 354414, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.136099338531494, "global_step": 354415, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.141552686691284, "global_step": 354416, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.074385404586792, "global_step": 354417, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1922872066497803, "global_step": 354418, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1728036403656006, "global_step": 354419, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.058971643447876, "global_step": 354420, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.127803087234497, "global_step": 354421, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0894861221313477, "global_step": 354422, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.065990447998047, "global_step": 354423, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.100064516067505, "global_step": 354424, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1671102046966553, "global_step": 354425, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1754050254821777, "global_step": 354426, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2682154178619385, "global_step": 354427, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.060621500015259, "global_step": 354428, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.009772777557373, "global_step": 354429, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.056182861328125, "global_step": 354430, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0958030223846436, "global_step": 354431, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.036754608154297, "global_step": 354432, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2120180130004883, "global_step": 354433, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.113682985305786, "global_step": 354434, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0542967319488525, "global_step": 354435, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2345244884490967, "global_step": 354436, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1239914894104004, "global_step": 354437, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.035379409790039, "global_step": 354438, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1318321228027344, "global_step": 354439, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.048846483230591, "global_step": 354440, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.121610641479492, "global_step": 354441, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.13226318359375, "global_step": 354442, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0565192699432373, "global_step": 354443, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0281755924224854, "global_step": 354444, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.148449420928955, "global_step": 354445, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1335294246673584, "global_step": 354446, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0321972370147705, "global_step": 354447, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.048603057861328, "global_step": 354448, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.061102867126465, "global_step": 354449, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.112475633621216, "global_step": 354450, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0598232746124268, "global_step": 354451, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.061119318008423, "global_step": 354452, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.070537567138672, "global_step": 354453, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0833981037139893, "global_step": 354454, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.011735200881958, "global_step": 354455, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1061031818389893, "global_step": 354456, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1506845951080322, "global_step": 354457, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.122706174850464, "global_step": 354458, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2018520832061768, "global_step": 354459, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1426632404327393, "global_step": 354460, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0848841667175293, "global_step": 354461, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0701820850372314, "global_step": 354462, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.086885929107666, "global_step": 354463, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.267003059387207, "global_step": 354464, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.124361753463745, "global_step": 354465, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0533101558685303, "global_step": 354466, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.105862855911255, "global_step": 354467, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.150317907333374, "global_step": 354468, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0248262882232666, "global_step": 354469, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1569039821624756, "global_step": 354470, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.114341974258423, "global_step": 354471, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0823605060577393, "global_step": 354472, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.108153820037842, "global_step": 354473, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1217751502990723, "global_step": 354474, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0613272190093994, "global_step": 354475, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1962876319885254, "global_step": 354476, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0670487880706787, "global_step": 354477, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1199254989624023, "global_step": 354478, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.087463140487671, "global_step": 354479, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.171297311782837, "global_step": 354480, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0830795764923096, "global_step": 354481, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1115570068359375, "global_step": 354482, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0999951362609863, "global_step": 354483, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0494556427001953, "global_step": 354484, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0865674018859863, "global_step": 354485, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.052629232406616, "global_step": 354486, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.256046772003174, "global_step": 354487, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1360158920288086, "global_step": 354488, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0510075092315674, "global_step": 354489, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1386373043060303, "global_step": 354490, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0711100101470947, "global_step": 354491, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1030964851379395, "global_step": 354492, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.015244722366333, "global_step": 354493, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.105020046234131, "global_step": 354494, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.081602096557617, "global_step": 354495, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.186870574951172, "global_step": 354496, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.192399263381958, "global_step": 354497, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.106790542602539, "global_step": 354498, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.137852907180786, "global_step": 354499, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0971944332122803, "global_step": 354500, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1219828128814697, "global_step": 354501, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0975918769836426, "global_step": 354502, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.096243143081665, "global_step": 354503, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0815834999084473, "global_step": 354504, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.106816530227661, "global_step": 354505, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.150146484375, "global_step": 354506, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.061896324157715, "global_step": 354507, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1130383014678955, "global_step": 354508, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.065885066986084, "global_step": 354509, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.068829298019409, "global_step": 354510, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1131949424743652, "global_step": 354511, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.114191770553589, "global_step": 354512, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.086193323135376, "global_step": 354513, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.024101495742798, "global_step": 354514, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1411099433898926, "global_step": 354515, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1069066524505615, "global_step": 354516, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.127241849899292, "global_step": 354517, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0922603607177734, "global_step": 354518, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1283676624298096, "global_step": 354519, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1046507358551025, "global_step": 354520, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.131375551223755, "global_step": 354521, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1952016353607178, "global_step": 354522, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0789475440979004, "global_step": 354523, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.084193229675293, "global_step": 354524, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1554768085479736, "global_step": 354525, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1115052700042725, "global_step": 354526, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.058455467224121, "global_step": 354527, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.06581974029541, "global_step": 354528, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1263856887817383, "global_step": 354529, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.084890842437744, "global_step": 354530, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0957210063934326, "global_step": 354531, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0601017475128174, "global_step": 354532, "epoch": 715, "lr": 5e-05}
{"train_loss": 1.9933640956878662, "global_step": 354533, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.230785846710205, "global_step": 354534, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1686081886291504, "global_step": 354535, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.086857318878174, "global_step": 354536, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1132116317749023, "global_step": 354537, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.090261459350586, "global_step": 354538, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0834736824035645, "global_step": 354539, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1061787605285645, "global_step": 354540, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.058955669403076, "global_step": 354541, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.118896245956421, "global_step": 354542, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2238831520080566, "global_step": 354543, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1189680099487305, "global_step": 354544, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.111297845840454, "global_step": 354545, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0470216274261475, "global_step": 354546, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1336398124694824, "global_step": 354547, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0340750217437744, "global_step": 354548, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.134921073913574, "global_step": 354549, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1659679412841797, "global_step": 354550, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0825486183166504, "global_step": 354551, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0585031509399414, "global_step": 354552, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1324002742767334, "global_step": 354553, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2202484607696533, "global_step": 354554, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.068347215652466, "global_step": 354555, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.192497491836548, "global_step": 354556, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1244804859161377, "global_step": 354557, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1180834770202637, "global_step": 354558, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2293272018432617, "global_step": 354559, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.170698881149292, "global_step": 354560, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1502926349639893, "global_step": 354561, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.031858205795288, "global_step": 354562, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.050388813018799, "global_step": 354563, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1426548957824707, "global_step": 354564, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0833706855773926, "global_step": 354565, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1652772426605225, "global_step": 354566, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0805490016937256, "global_step": 354567, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1761484146118164, "global_step": 354568, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2178361415863037, "global_step": 354569, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.10931396484375, "global_step": 354570, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0641775131225586, "global_step": 354571, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.091289520263672, "global_step": 354572, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.131908893585205, "global_step": 354573, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0003340244293213, "global_step": 354574, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.110560655593872, "global_step": 354575, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.126580238342285, "global_step": 354576, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1327497959136963, "global_step": 354577, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1022145748138428, "global_step": 354578, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0326623916625977, "global_step": 354579, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.136249542236328, "global_step": 354580, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2135424613952637, "global_step": 354581, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.128849983215332, "global_step": 354582, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0074710845947266, "global_step": 354583, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1324219703674316, "global_step": 354584, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1138229370117188, "global_step": 354585, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.164238214492798, "global_step": 354586, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.155869483947754, "global_step": 354587, "epoch": 715, "lr": 5e-05}
{"train_loss": 1.994217872619629, "global_step": 354588, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1313841342926025, "global_step": 354589, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.008556365966797, "global_step": 354590, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.154430866241455, "global_step": 354591, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0949339866638184, "global_step": 354592, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1072423458099365, "global_step": 354593, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1172080039978027, "global_step": 354594, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1357240676879883, "global_step": 354595, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1381993293762207, "global_step": 354596, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.220447301864624, "global_step": 354597, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0991408824920654, "global_step": 354598, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.221557140350342, "global_step": 354599, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0327634811401367, "global_step": 354600, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1204233169555664, "global_step": 354601, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1265175342559814, "global_step": 354602, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1736488342285156, "global_step": 354603, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1849913597106934, "global_step": 354604, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.040839433670044, "global_step": 354605, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.074617624282837, "global_step": 354606, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0866739749908447, "global_step": 354607, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0905215740203857, "global_step": 354608, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0963895320892334, "global_step": 354609, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1287927627563477, "global_step": 354610, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1305134296417236, "global_step": 354611, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.097076416015625, "global_step": 354612, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.170201301574707, "global_step": 354613, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1946449279785156, "global_step": 354614, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.087719440460205, "global_step": 354615, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1600751876831055, "global_step": 354616, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.152829647064209, "global_step": 354617, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0820958614349365, "global_step": 354618, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.094940662384033, "global_step": 354619, "epoch": 715, "lr": 5e-05}
{"train_loss": 1.9853609800338745, "global_step": 354620, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.176741123199463, "global_step": 354621, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0749707221984863, "global_step": 354622, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.079927921295166, "global_step": 354623, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1199374198913574, "global_step": 354624, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.181630849838257, "global_step": 354625, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.133457899093628, "global_step": 354626, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.098508358001709, "global_step": 354627, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.23197865486145, "global_step": 354628, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.111582040786743, "global_step": 354629, "epoch": 715, "lr": 5e-05}
{"train_loss": 1.9991204738616943, "global_step": 354630, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0615339279174805, "global_step": 354631, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.119246482849121, "global_step": 354632, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1408262252807617, "global_step": 354633, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.133173942565918, "global_step": 354634, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.132498264312744, "global_step": 354635, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.055626630783081, "global_step": 354636, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.044477701187134, "global_step": 354637, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.100430488586426, "global_step": 354638, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0204548835754395, "global_step": 354639, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.121371269226074, "global_step": 354640, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1232082843780518, "global_step": 354641, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1024961471557617, "global_step": 354642, "epoch": 715, "lr": 5e-05}
{"train_loss": 1.9888496398925781, "global_step": 354643, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0590360164642334, "global_step": 354644, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.170775890350342, "global_step": 354645, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.07785964012146, "global_step": 354646, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2306792736053467, "global_step": 354647, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1343023777008057, "global_step": 354648, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.174997329711914, "global_step": 354649, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.089447021484375, "global_step": 354650, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1173081398010254, "global_step": 354651, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0858981609344482, "global_step": 354652, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.190412759780884, "global_step": 354653, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1357102394104004, "global_step": 354654, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.183856725692749, "global_step": 354655, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0300703048706055, "global_step": 354656, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1015567779541016, "global_step": 354657, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1047165393829346, "global_step": 354658, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.172255277633667, "global_step": 354659, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.049818992614746, "global_step": 354660, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1322336196899414, "global_step": 354661, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1175031661987305, "global_step": 354662, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.09883451461792, "global_step": 354663, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0934014320373535, "global_step": 354664, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.084611654281616, "global_step": 354665, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.093531847000122, "global_step": 354666, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1139636039733887, "global_step": 354667, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.155369758605957, "global_step": 354668, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.140782356262207, "global_step": 354669, "epoch": 715, "lr": 5e-05}
{"train_loss": 1.9927642345428467, "global_step": 354670, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1711325645446777, "global_step": 354671, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2518184185028076, "global_step": 354672, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.047330617904663, "global_step": 354673, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1807994842529297, "global_step": 354674, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2027747631073, "global_step": 354675, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0729687213897705, "global_step": 354676, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1133899688720703, "global_step": 354677, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0383551120758057, "global_step": 354678, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1371631622314453, "global_step": 354679, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.182572603225708, "global_step": 354680, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.10947322845459, "global_step": 354681, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0682575702667236, "global_step": 354682, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.113016366958618, "global_step": 354683, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.136859178543091, "global_step": 354684, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1186656951904297, "global_step": 354685, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.089538097381592, "global_step": 354686, "epoch": 715, "lr": 5e-05}
{"train_loss": 1.9872715473175049, "global_step": 354687, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.132835865020752, "global_step": 354688, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1955385208129883, "global_step": 354689, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.159055709838867, "global_step": 354690, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1568572521209717, "global_step": 354691, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.080381155014038, "global_step": 354692, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1409499645233154, "global_step": 354693, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2053894996643066, "global_step": 354694, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.102773666381836, "global_step": 354695, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0811924934387207, "global_step": 354696, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.128223419189453, "global_step": 354697, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.184459686279297, "global_step": 354698, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1180343627929688, "global_step": 354699, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.030496835708618, "global_step": 354700, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1106367111206055, "global_step": 354701, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.137576103210449, "global_step": 354702, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1273040771484375, "global_step": 354703, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0649657249450684, "global_step": 354704, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1438984870910645, "global_step": 354705, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.060565948486328, "global_step": 354706, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.077096462249756, "global_step": 354707, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0919079780578613, "global_step": 354708, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1337671279907227, "global_step": 354709, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1387150287628174, "global_step": 354710, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.149864912033081, "global_step": 354711, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1707706451416016, "global_step": 354712, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0681838989257812, "global_step": 354713, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.116122007369995, "global_step": 354714, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.168452024459839, "global_step": 354715, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.099705457687378, "global_step": 354716, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1275103092193604, "global_step": 354717, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.043541193008423, "global_step": 354718, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.113569974899292, "global_step": 354719, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.124427080154419, "global_step": 354720, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.142153739929199, "global_step": 354721, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.130189895629883, "global_step": 354722, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.122546672821045, "global_step": 354723, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.082552433013916, "global_step": 354724, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0957109928131104, "global_step": 354725, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0698275566101074, "global_step": 354726, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1808948516845703, "global_step": 354727, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0919058322906494, "global_step": 354728, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1008141040802, "global_step": 354729, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0975356101989746, "global_step": 354730, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1266369819641113, "global_step": 354731, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0949366092681885, "global_step": 354732, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1548354625701904, "global_step": 354733, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1001787185668945, "global_step": 354734, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.266098976135254, "global_step": 354735, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1005473136901855, "global_step": 354736, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0541350841522217, "global_step": 354737, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1041197776794434, "global_step": 354738, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0942347049713135, "global_step": 354739, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1446714401245117, "global_step": 354740, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.2113544940948486, "global_step": 354741, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1458492279052734, "global_step": 354742, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.161034107208252, "global_step": 354743, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.070906162261963, "global_step": 354744, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0705912113189697, "global_step": 354745, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.151317834854126, "global_step": 354746, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.088460922241211, "global_step": 354747, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1193087100982666, "global_step": 354748, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.111459255218506, "global_step": 354749, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1683385372161865, "global_step": 354750, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0290255546569824, "global_step": 354751, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.139716625213623, "global_step": 354752, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.169304132461548, "global_step": 354753, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0884172916412354, "global_step": 354754, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0518221855163574, "global_step": 354755, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0707333087921143, "global_step": 354756, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0666258335113525, "global_step": 354757, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1741061210632324, "global_step": 354758, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1204206943511963, "global_step": 354759, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.186549663543701, "global_step": 354760, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.104727268218994, "global_step": 354761, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.142914295196533, "global_step": 354762, "epoch": 715, "lr": 5e-05}
{"train_loss": 1.99647855758667, "global_step": 354763, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.032480001449585, "global_step": 354764, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.056720733642578, "global_step": 354765, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.110349178314209, "global_step": 354766, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1308417320251465, "global_step": 354767, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0995633602142334, "global_step": 354768, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0779712200164795, "global_step": 354769, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.145007371902466, "global_step": 354770, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1427438259124756, "global_step": 354771, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1525352001190186, "global_step": 354772, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.031609058380127, "global_step": 354773, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.164968729019165, "global_step": 354774, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0799803733825684, "global_step": 354775, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.082890748977661, "global_step": 354776, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0111255645751953, "global_step": 354777, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1453425884246826, "global_step": 354778, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.128944158554077, "global_step": 354779, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.09143328666687, "global_step": 354780, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1037163734436035, "global_step": 354781, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0581538677215576, "global_step": 354782, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0457725524902344, "global_step": 354783, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0964603424072266, "global_step": 354784, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.0597739219665527, "global_step": 354785, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.1077728271484375, "global_step": 354786, "epoch": 715, "lr": 5e-05}
{"train_loss": 2.087244987487793, "global_step": 354787, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.051691770553589, "global_step": 354788, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.083566188812256, "global_step": 354789, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.03481388092041, "global_step": 354790, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0958240032196045, "global_step": 354791, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.087690830230713, "global_step": 354792, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.170867919921875, "global_step": 354793, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0515847206115723, "global_step": 354794, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0580601692199707, "global_step": 354795, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.107295036315918, "global_step": 354796, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1139895915985107, "global_step": 354797, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.105640411376953, "global_step": 354798, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.157602310180664, "global_step": 354799, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.181833267211914, "global_step": 354800, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.141629934310913, "global_step": 354801, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0928595066070557, "global_step": 354802, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0925087928771973, "global_step": 354803, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.045016288757324, "global_step": 354804, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1116936206817627, "global_step": 354805, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1293623447418213, "global_step": 354806, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0301690101623535, "global_step": 354807, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1122283935546875, "global_step": 354808, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.153254270553589, "global_step": 354809, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.130246639251709, "global_step": 354810, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1453144550323486, "global_step": 354811, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0911130905151367, "global_step": 354812, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0246996879577637, "global_step": 354813, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.19840669631958, "global_step": 354814, "epoch": 716, "lr": 5e-05}
{"train_loss": 1.9888503551483154, "global_step": 354815, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1222012042999268, "global_step": 354816, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1376500129699707, "global_step": 354817, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.140160083770752, "global_step": 354818, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1358795166015625, "global_step": 354819, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.101116895675659, "global_step": 354820, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1359379291534424, "global_step": 354821, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.140254020690918, "global_step": 354822, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1067378520965576, "global_step": 354823, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.212839365005493, "global_step": 354824, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.146570920944214, "global_step": 354825, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.057978630065918, "global_step": 354826, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.148588180541992, "global_step": 354827, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1497859954833984, "global_step": 354828, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0343050956726074, "global_step": 354829, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0269229412078857, "global_step": 354830, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1591625213623047, "global_step": 354831, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2316622734069824, "global_step": 354832, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1583521366119385, "global_step": 354833, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.038357734680176, "global_step": 354834, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.022494316101074, "global_step": 354835, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.061572551727295, "global_step": 354836, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.10823917388916, "global_step": 354837, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.174823522567749, "global_step": 354838, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0568106174468994, "global_step": 354839, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1092004776000977, "global_step": 354840, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.055793523788452, "global_step": 354841, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.180215835571289, "global_step": 354842, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0988028049468994, "global_step": 354843, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1191246509552, "global_step": 354844, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.147599697113037, "global_step": 354845, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.090632915496826, "global_step": 354846, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1501121520996094, "global_step": 354847, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0650711059570312, "global_step": 354848, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1573688983917236, "global_step": 354849, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1671030521392822, "global_step": 354850, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2439537048339844, "global_step": 354851, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.115671157836914, "global_step": 354852, "epoch": 716, "lr": 5e-05}
{"train_loss": 1.9849553108215332, "global_step": 354853, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0374984741210938, "global_step": 354854, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.127155303955078, "global_step": 354855, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.110529661178589, "global_step": 354856, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.033647298812866, "global_step": 354857, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1157760620117188, "global_step": 354858, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.116302490234375, "global_step": 354859, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0688185691833496, "global_step": 354860, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.069821834564209, "global_step": 354861, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1077980995178223, "global_step": 354862, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.008044481277466, "global_step": 354863, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.071887493133545, "global_step": 354864, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.136328935623169, "global_step": 354865, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0919249057769775, "global_step": 354866, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1790549755096436, "global_step": 354867, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0996625423431396, "global_step": 354868, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.043506145477295, "global_step": 354869, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1604037284851074, "global_step": 354870, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0930747985839844, "global_step": 354871, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0958473682403564, "global_step": 354872, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.026052951812744, "global_step": 354873, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1842031478881836, "global_step": 354874, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.154588460922241, "global_step": 354875, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1195309162139893, "global_step": 354876, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.102961301803589, "global_step": 354877, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1091179847717285, "global_step": 354878, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.052530288696289, "global_step": 354879, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0941686630249023, "global_step": 354880, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0738604068756104, "global_step": 354881, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0867056846618652, "global_step": 354882, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.172804594039917, "global_step": 354883, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1077535152435303, "global_step": 354884, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.016186237335205, "global_step": 354885, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.152651786804199, "global_step": 354886, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0458273887634277, "global_step": 354887, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.060669422149658, "global_step": 354888, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.039324998855591, "global_step": 354889, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.126323699951172, "global_step": 354890, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.077718734741211, "global_step": 354891, "epoch": 716, "lr": 5e-05}
{"train_loss": 1.9924664497375488, "global_step": 354892, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1407554149627686, "global_step": 354893, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1346073150634766, "global_step": 354894, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.127592086791992, "global_step": 354895, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.090940237045288, "global_step": 354896, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.180039405822754, "global_step": 354897, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1153790950775146, "global_step": 354898, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.081829786300659, "global_step": 354899, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.193957567214966, "global_step": 354900, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1133604049682617, "global_step": 354901, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.050344228744507, "global_step": 354902, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1190884113311768, "global_step": 354903, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.140871047973633, "global_step": 354904, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0699973106384277, "global_step": 354905, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.046895742416382, "global_step": 354906, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.089463472366333, "global_step": 354907, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.093334197998047, "global_step": 354908, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.023191213607788, "global_step": 354909, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2159409523010254, "global_step": 354910, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.059530019760132, "global_step": 354911, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0568535327911377, "global_step": 354912, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.128883123397827, "global_step": 354913, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2106456756591797, "global_step": 354914, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0812458992004395, "global_step": 354915, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.121816635131836, "global_step": 354916, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1821556091308594, "global_step": 354917, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0734806060791016, "global_step": 354918, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.083014726638794, "global_step": 354919, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1013238430023193, "global_step": 354920, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0307517051696777, "global_step": 354921, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1353702545166016, "global_step": 354922, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0855178833007812, "global_step": 354923, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0584747791290283, "global_step": 354924, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0424485206604004, "global_step": 354925, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0829877853393555, "global_step": 354926, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.121708393096924, "global_step": 354927, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0022096633911133, "global_step": 354928, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.148064613342285, "global_step": 354929, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1806256771087646, "global_step": 354930, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.085444211959839, "global_step": 354931, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1002397537231445, "global_step": 354932, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.072758197784424, "global_step": 354933, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0544281005859375, "global_step": 354934, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.244077444076538, "global_step": 354935, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0841727256774902, "global_step": 354936, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.159555673599243, "global_step": 354937, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1202385425567627, "global_step": 354938, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.092494249343872, "global_step": 354939, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.062293291091919, "global_step": 354940, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1264426708221436, "global_step": 354941, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1274542808532715, "global_step": 354942, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2155518531799316, "global_step": 354943, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1465914249420166, "global_step": 354944, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.082805633544922, "global_step": 354945, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.199293851852417, "global_step": 354946, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.093315601348877, "global_step": 354947, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.193824052810669, "global_step": 354948, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0790648460388184, "global_step": 354949, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.059844493865967, "global_step": 354950, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0845227241516113, "global_step": 354951, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.22100830078125, "global_step": 354952, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.116486072540283, "global_step": 354953, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1379780769348145, "global_step": 354954, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1136701107025146, "global_step": 354955, "epoch": 716, "lr": 5e-05}
{"train_loss": 1.982053279876709, "global_step": 354956, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.168384075164795, "global_step": 354957, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0529587268829346, "global_step": 354958, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2088310718536377, "global_step": 354959, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.057659387588501, "global_step": 354960, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.050868511199951, "global_step": 354961, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1198554039001465, "global_step": 354962, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0658280849456787, "global_step": 354963, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0894296169281006, "global_step": 354964, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1073856353759766, "global_step": 354965, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.181196928024292, "global_step": 354966, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1149392127990723, "global_step": 354967, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.121056318283081, "global_step": 354968, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.095526695251465, "global_step": 354969, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0531911849975586, "global_step": 354970, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1418356895446777, "global_step": 354971, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0353169441223145, "global_step": 354972, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.024855375289917, "global_step": 354973, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0676088333129883, "global_step": 354974, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0981192588806152, "global_step": 354975, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0394091606140137, "global_step": 354976, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1132805347442627, "global_step": 354977, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1485419273376465, "global_step": 354978, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.060516834259033, "global_step": 354979, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1159279346466064, "global_step": 354980, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.105532646179199, "global_step": 354981, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1511669158935547, "global_step": 354982, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.026024341583252, "global_step": 354983, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1142754554748535, "global_step": 354984, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1965227127075195, "global_step": 354985, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1073641777038574, "global_step": 354986, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1121459007263184, "global_step": 354987, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.146209239959717, "global_step": 354988, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.143613338470459, "global_step": 354989, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0530576705932617, "global_step": 354990, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0836169719696045, "global_step": 354991, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0658020973205566, "global_step": 354992, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0905091762542725, "global_step": 354993, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0686028003692627, "global_step": 354994, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1220991611480713, "global_step": 354995, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1229934692382812, "global_step": 354996, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.158358097076416, "global_step": 354997, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.01589035987854, "global_step": 354998, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.164236068725586, "global_step": 354999, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0725502967834473, "global_step": 355000, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.056810140609741, "global_step": 355001, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0454845428466797, "global_step": 355002, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1018524169921875, "global_step": 355003, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1134915351867676, "global_step": 355004, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1746559143066406, "global_step": 355005, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1786999702453613, "global_step": 355006, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.075169324874878, "global_step": 355007, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.09550142288208, "global_step": 355008, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.12182354927063, "global_step": 355009, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1136152744293213, "global_step": 355010, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.031310796737671, "global_step": 355011, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1540937423706055, "global_step": 355012, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.137413501739502, "global_step": 355013, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.057384967803955, "global_step": 355014, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1087493896484375, "global_step": 355015, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.111050605773926, "global_step": 355016, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.114105463027954, "global_step": 355017, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.129664659500122, "global_step": 355018, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.097615957260132, "global_step": 355019, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.089726448059082, "global_step": 355020, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1089606285095215, "global_step": 355021, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1077356338500977, "global_step": 355022, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.140270233154297, "global_step": 355023, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1258704662323, "global_step": 355024, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.050940990447998, "global_step": 355025, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1696386337280273, "global_step": 355026, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.09783673286438, "global_step": 355027, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1174862384796143, "global_step": 355028, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1108224391937256, "global_step": 355029, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.123661994934082, "global_step": 355030, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.112752914428711, "global_step": 355031, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2206544876098633, "global_step": 355032, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0776329040527344, "global_step": 355033, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0802273750305176, "global_step": 355034, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0979645252227783, "global_step": 355035, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.272674083709717, "global_step": 355036, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1000914573669434, "global_step": 355037, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0818729400634766, "global_step": 355038, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.046231985092163, "global_step": 355039, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0879464149475098, "global_step": 355040, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1725587844848633, "global_step": 355041, "epoch": 716, "lr": 5e-05}
{"train_loss": 1.9870336055755615, "global_step": 355042, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0717451572418213, "global_step": 355043, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0904293060302734, "global_step": 355044, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.148000955581665, "global_step": 355045, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1229405403137207, "global_step": 355046, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2316205501556396, "global_step": 355047, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0715231895446777, "global_step": 355048, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1227822303771973, "global_step": 355049, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2490859031677246, "global_step": 355050, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.13466739654541, "global_step": 355051, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.103536367416382, "global_step": 355052, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.142054557800293, "global_step": 355053, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1594343185424805, "global_step": 355054, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.094660997390747, "global_step": 355055, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.133090019226074, "global_step": 355056, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.135058879852295, "global_step": 355057, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0741188526153564, "global_step": 355058, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.174534320831299, "global_step": 355059, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0083022117614746, "global_step": 355060, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0457472801208496, "global_step": 355061, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.129615306854248, "global_step": 355062, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1439478397369385, "global_step": 355063, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.134058713912964, "global_step": 355064, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.09232497215271, "global_step": 355065, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0903027057647705, "global_step": 355066, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1214587688446045, "global_step": 355067, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.172935962677002, "global_step": 355068, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1215896606445312, "global_step": 355069, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.111909866333008, "global_step": 355070, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1164565086364746, "global_step": 355071, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.092907428741455, "global_step": 355072, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.101304054260254, "global_step": 355073, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2190935611724854, "global_step": 355074, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1069910526275635, "global_step": 355075, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0757322311401367, "global_step": 355076, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1184141635894775, "global_step": 355077, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.168429374694824, "global_step": 355078, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.035963296890259, "global_step": 355079, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.02296781539917, "global_step": 355080, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.183029890060425, "global_step": 355081, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1287572383880615, "global_step": 355082, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0611777305603027, "global_step": 355083, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.105560779571533, "global_step": 355084, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1020774841308594, "global_step": 355085, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0654380321502686, "global_step": 355086, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.095823287963867, "global_step": 355087, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0975253582000732, "global_step": 355088, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1479787826538086, "global_step": 355089, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0359489917755127, "global_step": 355090, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0785415172576904, "global_step": 355091, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.149533987045288, "global_step": 355092, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0782265663146973, "global_step": 355093, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0601165294647217, "global_step": 355094, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1101138591766357, "global_step": 355095, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.119786024093628, "global_step": 355096, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0460894107818604, "global_step": 355097, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1536221504211426, "global_step": 355098, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0636544227600098, "global_step": 355099, "epoch": 716, "lr": 5e-05}
{"train_loss": 1.9825409650802612, "global_step": 355100, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.232072114944458, "global_step": 355101, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1519932746887207, "global_step": 355102, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0904476642608643, "global_step": 355103, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1738998889923096, "global_step": 355104, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.16890811920166, "global_step": 355105, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0336146354675293, "global_step": 355106, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.080080509185791, "global_step": 355107, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.080226182937622, "global_step": 355108, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0483179092407227, "global_step": 355109, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.161041736602783, "global_step": 355110, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1245057582855225, "global_step": 355111, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0468783378601074, "global_step": 355112, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0705463886260986, "global_step": 355113, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1646790504455566, "global_step": 355114, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.099459409713745, "global_step": 355115, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1476986408233643, "global_step": 355116, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.147658348083496, "global_step": 355117, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1586897373199463, "global_step": 355118, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1515870094299316, "global_step": 355119, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0571370124816895, "global_step": 355120, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.104022979736328, "global_step": 355121, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1040117740631104, "global_step": 355122, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1036999225616455, "global_step": 355123, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1722002029418945, "global_step": 355124, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.10786509513855, "global_step": 355125, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1124720573425293, "global_step": 355126, "epoch": 716, "lr": 5e-05}
{"train_loss": 1.981938362121582, "global_step": 355127, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1341822147369385, "global_step": 355128, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1046643257141113, "global_step": 355129, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.140578031539917, "global_step": 355130, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.142195224761963, "global_step": 355131, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.083728075027466, "global_step": 355132, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1834826469421387, "global_step": 355133, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0747995376586914, "global_step": 355134, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.11238956451416, "global_step": 355135, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.230241298675537, "global_step": 355136, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0749599933624268, "global_step": 355137, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.080656051635742, "global_step": 355138, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.124516487121582, "global_step": 355139, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1032583713531494, "global_step": 355140, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.100834369659424, "global_step": 355141, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1281402111053467, "global_step": 355142, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2086315155029297, "global_step": 355143, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0938661098480225, "global_step": 355144, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.092068672180176, "global_step": 355145, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1300418376922607, "global_step": 355146, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0849571228027344, "global_step": 355147, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.051574468612671, "global_step": 355148, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0698375701904297, "global_step": 355149, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.098801851272583, "global_step": 355150, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1105761528015137, "global_step": 355151, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1292877197265625, "global_step": 355152, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.113509178161621, "global_step": 355153, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.03641676902771, "global_step": 355154, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1053664684295654, "global_step": 355155, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1619484424591064, "global_step": 355156, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0702834129333496, "global_step": 355157, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1402721405029297, "global_step": 355158, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1300084590911865, "global_step": 355159, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0444564819335938, "global_step": 355160, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.185366153717041, "global_step": 355161, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.069575548171997, "global_step": 355162, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.037860870361328, "global_step": 355163, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.122807025909424, "global_step": 355164, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0723865032196045, "global_step": 355165, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.102599859237671, "global_step": 355166, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1476876735687256, "global_step": 355167, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.079923629760742, "global_step": 355168, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.061516761779785, "global_step": 355169, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0686230659484863, "global_step": 355170, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.112025737762451, "global_step": 355171, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1365225315093994, "global_step": 355172, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.148144483566284, "global_step": 355173, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1316401958465576, "global_step": 355174, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0339560508728027, "global_step": 355175, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0542266368865967, "global_step": 355176, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.107234001159668, "global_step": 355177, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0973398685455322, "global_step": 355178, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.076392412185669, "global_step": 355179, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0707356929779053, "global_step": 355180, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.071476936340332, "global_step": 355181, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.083805799484253, "global_step": 355182, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.007413864135742, "global_step": 355183, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1407759189605713, "global_step": 355184, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1038804054260254, "global_step": 355185, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1430206298828125, "global_step": 355186, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1255102157592773, "global_step": 355187, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1124300956726074, "global_step": 355188, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.082139015197754, "global_step": 355189, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.033626079559326, "global_step": 355190, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1191251277923584, "global_step": 355191, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.057720422744751, "global_step": 355192, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.112884759902954, "global_step": 355193, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.141869068145752, "global_step": 355194, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1606807708740234, "global_step": 355195, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1267292499542236, "global_step": 355196, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1100943088531494, "global_step": 355197, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.204822540283203, "global_step": 355198, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.13289737701416, "global_step": 355199, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.066530704498291, "global_step": 355200, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1683852672576904, "global_step": 355201, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1018028259277344, "global_step": 355202, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1352906227111816, "global_step": 355203, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1163289546966553, "global_step": 355204, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.090827703475952, "global_step": 355205, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0203914642333984, "global_step": 355206, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0297539234161377, "global_step": 355207, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.070546865463257, "global_step": 355208, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.066908597946167, "global_step": 355209, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.145552396774292, "global_step": 355210, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.141782522201538, "global_step": 355211, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1137213706970215, "global_step": 355212, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.131453275680542, "global_step": 355213, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.10921049118042, "global_step": 355214, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.007248878479004, "global_step": 355215, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1065776348114014, "global_step": 355216, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0365664958953857, "global_step": 355217, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1230788230895996, "global_step": 355218, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1023073196411133, "global_step": 355219, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0953471660614014, "global_step": 355220, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0524938106536865, "global_step": 355221, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1009294986724854, "global_step": 355222, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1213254928588867, "global_step": 355223, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.118011713027954, "global_step": 355224, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1085805892944336, "global_step": 355225, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0480644702911377, "global_step": 355226, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1366379261016846, "global_step": 355227, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.147852897644043, "global_step": 355228, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1467812061309814, "global_step": 355229, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.125256061553955, "global_step": 355230, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1823673248291016, "global_step": 355231, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0947861671447754, "global_step": 355232, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.093438148498535, "global_step": 355233, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0840022563934326, "global_step": 355234, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2473983764648438, "global_step": 355235, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0854856967926025, "global_step": 355236, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.131065607070923, "global_step": 355237, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1253840923309326, "global_step": 355238, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1159963607788086, "global_step": 355239, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1455512046813965, "global_step": 355240, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1637160778045654, "global_step": 355241, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0891056060791016, "global_step": 355242, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.082378387451172, "global_step": 355243, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1241233348846436, "global_step": 355244, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1016674041748047, "global_step": 355245, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1098532676696777, "global_step": 355246, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.076786518096924, "global_step": 355247, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1180317401885986, "global_step": 355248, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.033484935760498, "global_step": 355249, "epoch": 716, "lr": 5e-05}
{"train_loss": 1.9772231578826904, "global_step": 355250, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1398820877075195, "global_step": 355251, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1432509422302246, "global_step": 355252, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1653027534484863, "global_step": 355253, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.084988594055176, "global_step": 355254, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1100246906280518, "global_step": 355255, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1621718406677246, "global_step": 355256, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.127291202545166, "global_step": 355257, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.181023359298706, "global_step": 355258, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.031704902648926, "global_step": 355259, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.058053731918335, "global_step": 355260, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.193117141723633, "global_step": 355261, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.060723066329956, "global_step": 355262, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.147554636001587, "global_step": 355263, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.111624002456665, "global_step": 355264, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.079573154449463, "global_step": 355265, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.025707960128784, "global_step": 355266, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0296273231506348, "global_step": 355267, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2015042304992676, "global_step": 355268, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0666961669921875, "global_step": 355269, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.164400339126587, "global_step": 355270, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.122713565826416, "global_step": 355271, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.115055561065674, "global_step": 355272, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.076720714569092, "global_step": 355273, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0686466693878174, "global_step": 355274, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.156719207763672, "global_step": 355275, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1857919692993164, "global_step": 355276, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0232696533203125, "global_step": 355277, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.156700611114502, "global_step": 355278, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0321035385131836, "global_step": 355279, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1834917068481445, "global_step": 355280, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.091404676437378, "global_step": 355281, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0733420848846436, "global_step": 355282, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.10180401802063, "global_step": 355283, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.106844902038574, "global_step": 355284, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.209463596343994, "global_step": 355285, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1570940017700195, "global_step": 355286, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1800498962402344, "global_step": 355287, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0758090019226074, "global_step": 355288, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.036201000213623, "global_step": 355289, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.084516763687134, "global_step": 355290, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1302883625030518, "global_step": 355291, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.109773635864258, "global_step": 355292, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0815813541412354, "global_step": 355293, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0265824794769287, "global_step": 355294, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0998804569244385, "global_step": 355295, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0729024410247803, "global_step": 355296, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.121643304824829, "global_step": 355297, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1201953887939453, "global_step": 355298, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.11106538772583, "global_step": 355299, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1088995933532715, "global_step": 355300, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1338343620300293, "global_step": 355301, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1648151874542236, "global_step": 355302, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.026973009109497, "global_step": 355303, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1116881370544434, "global_step": 355304, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1360113620758057, "global_step": 355305, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1317996978759766, "global_step": 355306, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.063687801361084, "global_step": 355307, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.124673843383789, "global_step": 355308, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.048140048980713, "global_step": 355309, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0942797660827637, "global_step": 355310, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.006572723388672, "global_step": 355311, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0715506076812744, "global_step": 355312, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.158358335494995, "global_step": 355313, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1128716468811035, "global_step": 355314, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.167734146118164, "global_step": 355315, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.094195604324341, "global_step": 355316, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1534042358398438, "global_step": 355317, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.087977886199951, "global_step": 355318, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1660068035125732, "global_step": 355319, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.222956895828247, "global_step": 355320, "epoch": 716, "lr": 5e-05}
{"train_loss": 1.9997522830963135, "global_step": 355321, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2234373092651367, "global_step": 355322, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1861302852630615, "global_step": 355323, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.052111864089966, "global_step": 355324, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.184535026550293, "global_step": 355325, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0959277153015137, "global_step": 355326, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.089195728302002, "global_step": 355327, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.07315731048584, "global_step": 355328, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.055842638015747, "global_step": 355329, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.102686643600464, "global_step": 355330, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1328558921813965, "global_step": 355331, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.05884051322937, "global_step": 355332, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.160679340362549, "global_step": 355333, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.23468017578125, "global_step": 355334, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1369426250457764, "global_step": 355335, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.135162353515625, "global_step": 355336, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.138795852661133, "global_step": 355337, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1277883052825928, "global_step": 355338, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1450815200805664, "global_step": 355339, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1223573684692383, "global_step": 355340, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1424851417541504, "global_step": 355341, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0677263736724854, "global_step": 355342, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0982096195220947, "global_step": 355343, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.076326608657837, "global_step": 355344, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0885260105133057, "global_step": 355345, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1476151943206787, "global_step": 355346, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1558797359466553, "global_step": 355347, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1447815895080566, "global_step": 355348, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.189500570297241, "global_step": 355349, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0644371509552, "global_step": 355350, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0006985664367676, "global_step": 355351, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0814807415008545, "global_step": 355352, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1286110877990723, "global_step": 355353, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.138505220413208, "global_step": 355354, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2069759368896484, "global_step": 355355, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0878207683563232, "global_step": 355356, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.202650785446167, "global_step": 355357, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0848500728607178, "global_step": 355358, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1356403827667236, "global_step": 355359, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0304083824157715, "global_step": 355360, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.107666015625, "global_step": 355361, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0609185695648193, "global_step": 355362, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1318793296813965, "global_step": 355363, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.096281051635742, "global_step": 355364, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.168586492538452, "global_step": 355365, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1186516284942627, "global_step": 355366, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.093975067138672, "global_step": 355367, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.189988374710083, "global_step": 355368, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.075328826904297, "global_step": 355369, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.02421236038208, "global_step": 355370, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.150109052658081, "global_step": 355371, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0980377197265625, "global_step": 355372, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0242068767547607, "global_step": 355373, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.108863115310669, "global_step": 355374, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.07743239402771, "global_step": 355375, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.129880666732788, "global_step": 355376, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.142632484436035, "global_step": 355377, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1974072456359863, "global_step": 355378, "epoch": 716, "lr": 5e-05}
{"train_loss": 1.9976545572280884, "global_step": 355379, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.074197292327881, "global_step": 355380, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.123211145401001, "global_step": 355381, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.133629083633423, "global_step": 355382, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.103947401046753, "global_step": 355383, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0170555114746094, "global_step": 355384, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.152721881866455, "global_step": 355385, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0994479656219482, "global_step": 355386, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.145737409591675, "global_step": 355387, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0210227966308594, "global_step": 355388, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1061928272247314, "global_step": 355389, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.115388870239258, "global_step": 355390, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1914937496185303, "global_step": 355391, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0755996704101562, "global_step": 355392, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.107503890991211, "global_step": 355393, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1952617168426514, "global_step": 355394, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.06209135055542, "global_step": 355395, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.172152280807495, "global_step": 355396, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0605626106262207, "global_step": 355397, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0918784141540527, "global_step": 355398, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1416213512420654, "global_step": 355399, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0477218627929688, "global_step": 355400, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1063709259033203, "global_step": 355401, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.067575216293335, "global_step": 355402, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.120068311691284, "global_step": 355403, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0478358268737793, "global_step": 355404, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.093139171600342, "global_step": 355405, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.228161334991455, "global_step": 355406, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.081686019897461, "global_step": 355407, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.17010498046875, "global_step": 355408, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.053694248199463, "global_step": 355409, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1141762733459473, "global_step": 355410, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0820724964141846, "global_step": 355411, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.109459638595581, "global_step": 355412, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1335530281066895, "global_step": 355413, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.088728666305542, "global_step": 355414, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.074338436126709, "global_step": 355415, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1174111366271973, "global_step": 355416, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.145918846130371, "global_step": 355417, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0743274688720703, "global_step": 355418, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0986642837524414, "global_step": 355419, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1050281524658203, "global_step": 355420, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.094625234603882, "global_step": 355421, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.092695713043213, "global_step": 355422, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.224109172821045, "global_step": 355423, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1290605068206787, "global_step": 355424, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.02577805519104, "global_step": 355425, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.084259510040283, "global_step": 355426, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1309399604797363, "global_step": 355427, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.150622844696045, "global_step": 355428, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1375274658203125, "global_step": 355429, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.043299674987793, "global_step": 355430, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1231470108032227, "global_step": 355431, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0909619331359863, "global_step": 355432, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1559767723083496, "global_step": 355433, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.11777400970459, "global_step": 355434, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1251049041748047, "global_step": 355435, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.174614191055298, "global_step": 355436, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.067715883255005, "global_step": 355437, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1664350032806396, "global_step": 355438, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.017606258392334, "global_step": 355439, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.202944040298462, "global_step": 355440, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.061047077178955, "global_step": 355441, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1119048595428467, "global_step": 355442, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1814846992492676, "global_step": 355443, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1782851219177246, "global_step": 355444, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1017186641693115, "global_step": 355445, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.171870470046997, "global_step": 355446, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.145606756210327, "global_step": 355447, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.123197078704834, "global_step": 355448, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.18884015083313, "global_step": 355449, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1141316890716553, "global_step": 355450, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.051088809967041, "global_step": 355451, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.142085552215576, "global_step": 355452, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.160162925720215, "global_step": 355453, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2052814960479736, "global_step": 355454, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0765390396118164, "global_step": 355455, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.119412899017334, "global_step": 355456, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.161665439605713, "global_step": 355457, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0904879570007324, "global_step": 355458, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.116300582885742, "global_step": 355459, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1717100143432617, "global_step": 355460, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1139461994171143, "global_step": 355461, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.097473382949829, "global_step": 355462, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.072239398956299, "global_step": 355463, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.179206371307373, "global_step": 355464, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0490472316741943, "global_step": 355465, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.069389820098877, "global_step": 355466, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0528695583343506, "global_step": 355467, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.128467559814453, "global_step": 355468, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.146932363510132, "global_step": 355469, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.073596239089966, "global_step": 355470, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1429898738861084, "global_step": 355471, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0197229385375977, "global_step": 355472, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0816149711608887, "global_step": 355473, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.030827522277832, "global_step": 355474, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1369874477386475, "global_step": 355475, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.112091302871704, "global_step": 355476, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.038928985595703, "global_step": 355477, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.156978130340576, "global_step": 355478, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0714399814605713, "global_step": 355479, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1174142360687256, "global_step": 355480, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.083258867263794, "global_step": 355481, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1405367851257324, "global_step": 355482, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.082831859588623, "global_step": 355483, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.119178056716919, "global_step": 355484, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1628706455230713, "global_step": 355485, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1173717975616455, "global_step": 355486, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1942574977874756, "global_step": 355487, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.151301145553589, "global_step": 355488, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1016018390655518, "global_step": 355489, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1185102462768555, "global_step": 355490, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0974278450012207, "global_step": 355491, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.094440460205078, "global_step": 355492, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0259222984313965, "global_step": 355493, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1184234619140625, "global_step": 355494, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1635923385620117, "global_step": 355495, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.084088087081909, "global_step": 355496, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1625123023986816, "global_step": 355497, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.10955548286438, "global_step": 355498, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.157646894454956, "global_step": 355499, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1531567573547363, "global_step": 355500, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1745800971984863, "global_step": 355501, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.065676212310791, "global_step": 355502, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.101559638977051, "global_step": 355503, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0308303833007812, "global_step": 355504, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.096808433532715, "global_step": 355505, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.154197931289673, "global_step": 355506, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1596431732177734, "global_step": 355507, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2171382904052734, "global_step": 355508, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0426082611083984, "global_step": 355509, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.126771926879883, "global_step": 355510, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.107347011566162, "global_step": 355511, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.11311936378479, "global_step": 355512, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1138668060302734, "global_step": 355513, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1366918087005615, "global_step": 355514, "epoch": 716, "lr": 5e-05}
{"train_loss": 1.968617558479309, "global_step": 355515, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1973865032196045, "global_step": 355516, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0675618648529053, "global_step": 355517, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1037895679473877, "global_step": 355518, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1857292652130127, "global_step": 355519, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.168708324432373, "global_step": 355520, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1073813438415527, "global_step": 355521, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1288845539093018, "global_step": 355522, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0948705673217773, "global_step": 355523, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0828118324279785, "global_step": 355524, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1870059967041016, "global_step": 355525, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.162358045578003, "global_step": 355526, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.06807804107666, "global_step": 355527, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0990958213806152, "global_step": 355528, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0245397090911865, "global_step": 355529, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1550426483154297, "global_step": 355530, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0736074447631836, "global_step": 355531, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.102599859237671, "global_step": 355532, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1071317195892334, "global_step": 355533, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1191911697387695, "global_step": 355534, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0540239810943604, "global_step": 355535, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1290903091430664, "global_step": 355536, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1236014366149902, "global_step": 355537, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.082515239715576, "global_step": 355538, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1467299461364746, "global_step": 355539, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.113760232925415, "global_step": 355540, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.093646764755249, "global_step": 355541, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1458687782287598, "global_step": 355542, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1047635078430176, "global_step": 355543, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.044658899307251, "global_step": 355544, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0886404514312744, "global_step": 355545, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1063671112060547, "global_step": 355546, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1582069396972656, "global_step": 355547, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1096458435058594, "global_step": 355548, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.048353672027588, "global_step": 355549, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0578360557556152, "global_step": 355550, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.153298854827881, "global_step": 355551, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1055331230163574, "global_step": 355552, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0703632831573486, "global_step": 355553, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.156099319458008, "global_step": 355554, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1475472450256348, "global_step": 355555, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.100337028503418, "global_step": 355556, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2022697925567627, "global_step": 355557, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0560200214385986, "global_step": 355558, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1141598224639893, "global_step": 355559, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1006975173950195, "global_step": 355560, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.118736982345581, "global_step": 355561, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1131153106689453, "global_step": 355562, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.132492780685425, "global_step": 355563, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.189316749572754, "global_step": 355564, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1598238945007324, "global_step": 355565, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.088026523590088, "global_step": 355566, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0732905864715576, "global_step": 355567, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0700314044952393, "global_step": 355568, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.125459671020508, "global_step": 355569, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.119215488433838, "global_step": 355570, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.092764139175415, "global_step": 355571, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1187050342559814, "global_step": 355572, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1729400157928467, "global_step": 355573, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0780043601989746, "global_step": 355574, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1158077716827393, "global_step": 355575, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1416070461273193, "global_step": 355576, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.06866192817688, "global_step": 355577, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.113745927810669, "global_step": 355578, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.081808567047119, "global_step": 355579, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.027987480163574, "global_step": 355580, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2009880542755127, "global_step": 355581, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.090266227722168, "global_step": 355582, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1466948986053467, "global_step": 355583, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0511093139648438, "global_step": 355584, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1300578117370605, "global_step": 355585, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.190873861312866, "global_step": 355586, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0242655277252197, "global_step": 355587, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0220112800598145, "global_step": 355588, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.131967544555664, "global_step": 355589, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.203697681427002, "global_step": 355590, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.151951313018799, "global_step": 355591, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.055631637573242, "global_step": 355592, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0804941654205322, "global_step": 355593, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.135528326034546, "global_step": 355594, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.104780673980713, "global_step": 355595, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1946780681610107, "global_step": 355596, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.057926654815674, "global_step": 355597, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.056765079498291, "global_step": 355598, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1249165534973145, "global_step": 355599, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1552412509918213, "global_step": 355600, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1831252574920654, "global_step": 355601, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0723185539245605, "global_step": 355602, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.155561685562134, "global_step": 355603, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.13101863861084, "global_step": 355604, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.081266164779663, "global_step": 355605, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.173849582672119, "global_step": 355606, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.112264633178711, "global_step": 355607, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.07254695892334, "global_step": 355608, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.112436056137085, "global_step": 355609, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0709786415100098, "global_step": 355610, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0704970359802246, "global_step": 355611, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1836490631103516, "global_step": 355612, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1283586025238037, "global_step": 355613, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1072607040405273, "global_step": 355614, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1494927406311035, "global_step": 355615, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1301190853118896, "global_step": 355616, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1541552543640137, "global_step": 355617, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1402900218963623, "global_step": 355618, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1409263610839844, "global_step": 355619, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.067615509033203, "global_step": 355620, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1473677158355713, "global_step": 355621, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0992822647094727, "global_step": 355622, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.102497100830078, "global_step": 355623, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.122821807861328, "global_step": 355624, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.04134464263916, "global_step": 355625, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0845587253570557, "global_step": 355626, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1560277938842773, "global_step": 355627, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0034759044647217, "global_step": 355628, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1037673950195312, "global_step": 355629, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0972084999084473, "global_step": 355630, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1552505493164062, "global_step": 355631, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1376254558563232, "global_step": 355632, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1706247329711914, "global_step": 355633, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.083085536956787, "global_step": 355634, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.107605218887329, "global_step": 355635, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.090879201889038, "global_step": 355636, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.119969129562378, "global_step": 355637, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1062393188476562, "global_step": 355638, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1648995876312256, "global_step": 355639, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0945639610290527, "global_step": 355640, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0205867290496826, "global_step": 355641, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0640270709991455, "global_step": 355642, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.166750907897949, "global_step": 355643, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.076253652572632, "global_step": 355644, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0631484985351562, "global_step": 355645, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.133094072341919, "global_step": 355646, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0876872539520264, "global_step": 355647, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1335790157318115, "global_step": 355648, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2260632514953613, "global_step": 355649, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0622012615203857, "global_step": 355650, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1005845069885254, "global_step": 355651, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.076446533203125, "global_step": 355652, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0532174110412598, "global_step": 355653, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1106338500976562, "global_step": 355654, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1559245586395264, "global_step": 355655, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.04557466506958, "global_step": 355656, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.061514377593994, "global_step": 355657, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.172910690307617, "global_step": 355658, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2107224464416504, "global_step": 355659, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1377618312835693, "global_step": 355660, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.250981330871582, "global_step": 355661, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1794958114624023, "global_step": 355662, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.125349521636963, "global_step": 355663, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.088582754135132, "global_step": 355664, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.115330934524536, "global_step": 355665, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.112278461456299, "global_step": 355666, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0315439701080322, "global_step": 355667, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.109893321990967, "global_step": 355668, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0940299034118652, "global_step": 355669, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1361584663391113, "global_step": 355670, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1576180458068848, "global_step": 355671, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1541428565979004, "global_step": 355672, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1140434741973877, "global_step": 355673, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1329782009124756, "global_step": 355674, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0737318992614746, "global_step": 355675, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1775529384613037, "global_step": 355676, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.110055923461914, "global_step": 355677, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1445651054382324, "global_step": 355678, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.163989305496216, "global_step": 355679, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1532773971557617, "global_step": 355680, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.122082233428955, "global_step": 355681, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0217068195343018, "global_step": 355682, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1242637634277344, "global_step": 355683, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0990653038024902, "global_step": 355684, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0563721656799316, "global_step": 355685, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1253199577331543, "global_step": 355686, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.138230562210083, "global_step": 355687, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1282520294189453, "global_step": 355688, "epoch": 716, "lr": 5e-05}
{"train_loss": 1.9914090633392334, "global_step": 355689, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.163250684738159, "global_step": 355690, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1307764053344727, "global_step": 355691, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0866479873657227, "global_step": 355692, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.109485387802124, "global_step": 355693, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1438190937042236, "global_step": 355694, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0796427726745605, "global_step": 355695, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.144096612930298, "global_step": 355696, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.084977865219116, "global_step": 355697, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.081873893737793, "global_step": 355698, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0604491233825684, "global_step": 355699, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0929198265075684, "global_step": 355700, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1481258869171143, "global_step": 355701, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1596686840057373, "global_step": 355702, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1123557090759277, "global_step": 355703, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.130497932434082, "global_step": 355704, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.098945379257202, "global_step": 355705, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1784379482269287, "global_step": 355706, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.175027847290039, "global_step": 355707, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.129589557647705, "global_step": 355708, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1351242065429688, "global_step": 355709, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.110084295272827, "global_step": 355710, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.13632869720459, "global_step": 355711, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1710517406463623, "global_step": 355712, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1103885173797607, "global_step": 355713, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.102764844894409, "global_step": 355714, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1024224758148193, "global_step": 355715, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.180223226547241, "global_step": 355716, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0650460720062256, "global_step": 355717, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.122529983520508, "global_step": 355718, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0336220264434814, "global_step": 355719, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1257948875427246, "global_step": 355720, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.162309408187866, "global_step": 355721, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.139723300933838, "global_step": 355722, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1280291080474854, "global_step": 355723, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.148160934448242, "global_step": 355724, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.085359573364258, "global_step": 355725, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0875511169433594, "global_step": 355726, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0956132411956787, "global_step": 355727, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0264298915863037, "global_step": 355728, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.111912250518799, "global_step": 355729, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.067793130874634, "global_step": 355730, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.155353546142578, "global_step": 355731, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0404367446899414, "global_step": 355732, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.095815658569336, "global_step": 355733, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1582252979278564, "global_step": 355734, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0588502883911133, "global_step": 355735, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0743136405944824, "global_step": 355736, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1463241577148438, "global_step": 355737, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.181969165802002, "global_step": 355738, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0656325817108154, "global_step": 355739, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.123448610305786, "global_step": 355740, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0995383262634277, "global_step": 355741, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1263837814331055, "global_step": 355742, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.1847617626190186, "global_step": 355743, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0723419189453125, "global_step": 355744, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.152756690979004, "global_step": 355745, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2277626991271973, "global_step": 355746, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.0758678913116455, "global_step": 355747, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2097933292388916, "global_step": 355748, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.080831527709961, "global_step": 355749, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.150446891784668, "global_step": 355750, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.2188549041748047, "global_step": 355751, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.161163330078125, "global_step": 355752, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.084430694580078, "global_step": 355753, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.060803174972534, "global_step": 355754, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.110238552093506, "global_step": 355755, "epoch": 716, "lr": 5e-05}
{"train_loss": 2.103771448135376, "global_step": 355756, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.027312755584717, "global_step": 355757, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.09608793258667, "global_step": 355758, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1032915115356445, "global_step": 355759, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1034326553344727, "global_step": 355760, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.058056354522705, "global_step": 355761, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.068223714828491, "global_step": 355762, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0796737670898438, "global_step": 355763, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.039763927459717, "global_step": 355764, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.117917776107788, "global_step": 355765, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0503015518188477, "global_step": 355766, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.112891435623169, "global_step": 355767, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0697293281555176, "global_step": 355768, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.2047715187072754, "global_step": 355769, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.089045524597168, "global_step": 355770, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1244869232177734, "global_step": 355771, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.184722661972046, "global_step": 355772, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0525617599487305, "global_step": 355773, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1021525859832764, "global_step": 355774, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0898289680480957, "global_step": 355775, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.039792776107788, "global_step": 355776, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.055981159210205, "global_step": 355777, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1563608646392822, "global_step": 355778, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.096696138381958, "global_step": 355779, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1426122188568115, "global_step": 355780, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0271098613739014, "global_step": 355781, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0434603691101074, "global_step": 355782, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.146397829055786, "global_step": 355783, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1047146320343018, "global_step": 355784, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.140824794769287, "global_step": 355785, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1393702030181885, "global_step": 355786, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0928359031677246, "global_step": 355787, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.072828531265259, "global_step": 355788, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0787198543548584, "global_step": 355789, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0663387775421143, "global_step": 355790, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.072827100753784, "global_step": 355791, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0636532306671143, "global_step": 355792, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.098496198654175, "global_step": 355793, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.108246088027954, "global_step": 355794, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.15460467338562, "global_step": 355795, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0437350273132324, "global_step": 355796, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1345179080963135, "global_step": 355797, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1455466747283936, "global_step": 355798, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.255418062210083, "global_step": 355799, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.057116985321045, "global_step": 355800, "epoch": 717, "lr": 5e-05}
{"train_loss": 1.992071509361267, "global_step": 355801, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1784579753875732, "global_step": 355802, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0743675231933594, "global_step": 355803, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0310707092285156, "global_step": 355804, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.043736219406128, "global_step": 355805, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.172116279602051, "global_step": 355806, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.085437297821045, "global_step": 355807, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1511011123657227, "global_step": 355808, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1361684799194336, "global_step": 355809, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1187920570373535, "global_step": 355810, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1352739334106445, "global_step": 355811, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0997002124786377, "global_step": 355812, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.066260576248169, "global_step": 355813, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.014298677444458, "global_step": 355814, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.002765417098999, "global_step": 355815, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.101801872253418, "global_step": 355816, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.112076759338379, "global_step": 355817, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1747031211853027, "global_step": 355818, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1461029052734375, "global_step": 355819, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0692265033721924, "global_step": 355820, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1531286239624023, "global_step": 355821, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1344175338745117, "global_step": 355822, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1278133392333984, "global_step": 355823, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.200995922088623, "global_step": 355824, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.147625684738159, "global_step": 355825, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1152286529541016, "global_step": 355826, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0735955238342285, "global_step": 355827, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.056215286254883, "global_step": 355828, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.119077205657959, "global_step": 355829, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.15167236328125, "global_step": 355830, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.090116262435913, "global_step": 355831, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1337497234344482, "global_step": 355832, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0892391204833984, "global_step": 355833, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0610735416412354, "global_step": 355834, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1070683002471924, "global_step": 355835, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1990721225738525, "global_step": 355836, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.166499137878418, "global_step": 355837, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1505351066589355, "global_step": 355838, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0417490005493164, "global_step": 355839, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.065782070159912, "global_step": 355840, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0970935821533203, "global_step": 355841, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1740171909332275, "global_step": 355842, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0408458709716797, "global_step": 355843, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0699546337127686, "global_step": 355844, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1702685356140137, "global_step": 355845, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1508166790008545, "global_step": 355846, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0962164402008057, "global_step": 355847, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0007379055023193, "global_step": 355848, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1185014247894287, "global_step": 355849, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0692520141601562, "global_step": 355850, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1159534454345703, "global_step": 355851, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.140684127807617, "global_step": 355852, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.170806884765625, "global_step": 355853, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.024463653564453, "global_step": 355854, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1095218658447266, "global_step": 355855, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1281309127807617, "global_step": 355856, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.182864189147949, "global_step": 355857, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1477582454681396, "global_step": 355858, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.222465753555298, "global_step": 355859, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1043970584869385, "global_step": 355860, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.107834815979004, "global_step": 355861, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0880813598632812, "global_step": 355862, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0629920959472656, "global_step": 355863, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0909504890441895, "global_step": 355864, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1226983070373535, "global_step": 355865, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1918222904205322, "global_step": 355866, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.079850673675537, "global_step": 355867, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0807533264160156, "global_step": 355868, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.094547986984253, "global_step": 355869, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1535329818725586, "global_step": 355870, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1272146701812744, "global_step": 355871, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1663172245025635, "global_step": 355872, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0432002544403076, "global_step": 355873, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1559882164001465, "global_step": 355874, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1959664821624756, "global_step": 355875, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.067708730697632, "global_step": 355876, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.08950138092041, "global_step": 355877, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1654396057128906, "global_step": 355878, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0479495525360107, "global_step": 355879, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1469569206237793, "global_step": 355880, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1145598888397217, "global_step": 355881, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0364198684692383, "global_step": 355882, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1086366176605225, "global_step": 355883, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.119687080383301, "global_step": 355884, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0623695850372314, "global_step": 355885, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.126877784729004, "global_step": 355886, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.12001633644104, "global_step": 355887, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0715441703796387, "global_step": 355888, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1458728313446045, "global_step": 355889, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.011507511138916, "global_step": 355890, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.133863925933838, "global_step": 355891, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.175041675567627, "global_step": 355892, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0448620319366455, "global_step": 355893, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.2134578227996826, "global_step": 355894, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.138946533203125, "global_step": 355895, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.109363555908203, "global_step": 355896, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.094599485397339, "global_step": 355897, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.083954095840454, "global_step": 355898, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0231847763061523, "global_step": 355899, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.103719472885132, "global_step": 355900, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.139564275741577, "global_step": 355901, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1647093296051025, "global_step": 355902, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1819777488708496, "global_step": 355903, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0617668628692627, "global_step": 355904, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.115565776824951, "global_step": 355905, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1014065742492676, "global_step": 355906, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1641786098480225, "global_step": 355907, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0549123287200928, "global_step": 355908, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1418981552124023, "global_step": 355909, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.214378833770752, "global_step": 355910, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.111447811126709, "global_step": 355911, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.066089153289795, "global_step": 355912, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.127534866333008, "global_step": 355913, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1787776947021484, "global_step": 355914, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0604684352874756, "global_step": 355915, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1530959606170654, "global_step": 355916, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.158540964126587, "global_step": 355917, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.056629180908203, "global_step": 355918, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.119861602783203, "global_step": 355919, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1308140754699707, "global_step": 355920, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0477986335754395, "global_step": 355921, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0094377994537354, "global_step": 355922, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.109447479248047, "global_step": 355923, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1185789108276367, "global_step": 355924, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1057446002960205, "global_step": 355925, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.01340651512146, "global_step": 355926, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0585129261016846, "global_step": 355927, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0424654483795166, "global_step": 355928, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0968573093414307, "global_step": 355929, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1749112606048584, "global_step": 355930, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.150601625442505, "global_step": 355931, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.070272922515869, "global_step": 355932, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.050457239151001, "global_step": 355933, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.072638750076294, "global_step": 355934, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.096384286880493, "global_step": 355935, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1701011657714844, "global_step": 355936, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1683478355407715, "global_step": 355937, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1543993949890137, "global_step": 355938, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.124516248703003, "global_step": 355939, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.122823476791382, "global_step": 355940, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1636762619018555, "global_step": 355941, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1893057823181152, "global_step": 355942, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1200196743011475, "global_step": 355943, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.105506181716919, "global_step": 355944, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.072469472885132, "global_step": 355945, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.060983657836914, "global_step": 355946, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1076793670654297, "global_step": 355947, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0465939044952393, "global_step": 355948, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0898306369781494, "global_step": 355949, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.064509153366089, "global_step": 355950, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1891353130340576, "global_step": 355951, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.159177303314209, "global_step": 355952, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.168440341949463, "global_step": 355953, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1302499771118164, "global_step": 355954, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.090076446533203, "global_step": 355955, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.044373035430908, "global_step": 355956, "epoch": 717, "lr": 5e-05}
{"train_loss": 1.9617334604263306, "global_step": 355957, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1422183513641357, "global_step": 355958, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1371679306030273, "global_step": 355959, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1242172718048096, "global_step": 355960, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.050684928894043, "global_step": 355961, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.136741876602173, "global_step": 355962, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1006827354431152, "global_step": 355963, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1029441356658936, "global_step": 355964, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0353665351867676, "global_step": 355965, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1280739307403564, "global_step": 355966, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1747634410858154, "global_step": 355967, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0869572162628174, "global_step": 355968, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.151582956314087, "global_step": 355969, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0431783199310303, "global_step": 355970, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.097346305847168, "global_step": 355971, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.170977830886841, "global_step": 355972, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1551449298858643, "global_step": 355973, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0574612617492676, "global_step": 355974, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.148832321166992, "global_step": 355975, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.217996835708618, "global_step": 355976, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0595271587371826, "global_step": 355977, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1070737838745117, "global_step": 355978, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1512300968170166, "global_step": 355979, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0686678886413574, "global_step": 355980, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1017935276031494, "global_step": 355981, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0737438201904297, "global_step": 355982, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.105994939804077, "global_step": 355983, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.158141851425171, "global_step": 355984, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.2224628925323486, "global_step": 355985, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.141904354095459, "global_step": 355986, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0039021968841553, "global_step": 355987, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.15333890914917, "global_step": 355988, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.17913818359375, "global_step": 355989, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1545205116271973, "global_step": 355990, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1324429512023926, "global_step": 355991, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.03155517578125, "global_step": 355992, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.174717903137207, "global_step": 355993, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.010723829269409, "global_step": 355994, "epoch": 717, "lr": 5e-05}
{"train_loss": 1.9640824794769287, "global_step": 355995, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.088371992111206, "global_step": 355996, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1006276607513428, "global_step": 355997, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.061742067337036, "global_step": 355998, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.11720609664917, "global_step": 355999, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.056807041168213, "global_step": 356000, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1648976802825928, "global_step": 356001, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.122886896133423, "global_step": 356002, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.092883825302124, "global_step": 356003, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.111978054046631, "global_step": 356004, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1229264736175537, "global_step": 356005, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0125489234924316, "global_step": 356006, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.2321255207061768, "global_step": 356007, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.044945001602173, "global_step": 356008, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.097769021987915, "global_step": 356009, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.111381769180298, "global_step": 356010, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1800923347473145, "global_step": 356011, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1037330627441406, "global_step": 356012, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.138425827026367, "global_step": 356013, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.135087490081787, "global_step": 356014, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1272571086883545, "global_step": 356015, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.038144588470459, "global_step": 356016, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0601589679718018, "global_step": 356017, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1253366470336914, "global_step": 356018, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.053187131881714, "global_step": 356019, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.005465269088745, "global_step": 356020, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.122006893157959, "global_step": 356021, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.14945650100708, "global_step": 356022, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.138840675354004, "global_step": 356023, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0672738552093506, "global_step": 356024, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.120431900024414, "global_step": 356025, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0828654766082764, "global_step": 356026, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.072542190551758, "global_step": 356027, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1282122135162354, "global_step": 356028, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.126598358154297, "global_step": 356029, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0503311157226562, "global_step": 356030, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.210512161254883, "global_step": 356031, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1348159313201904, "global_step": 356032, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.197962522506714, "global_step": 356033, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0800468921661377, "global_step": 356034, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1480321884155273, "global_step": 356035, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0716941356658936, "global_step": 356036, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.172560214996338, "global_step": 356037, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1897518634796143, "global_step": 356038, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.054363489151001, "global_step": 356039, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0691118240356445, "global_step": 356040, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.072293519973755, "global_step": 356041, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1053130626678467, "global_step": 356042, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1544671058654785, "global_step": 356043, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0764105319976807, "global_step": 356044, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1284139156341553, "global_step": 356045, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0805253982543945, "global_step": 356046, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0692014694213867, "global_step": 356047, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0388379096984863, "global_step": 356048, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1231167316436768, "global_step": 356049, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.056795835494995, "global_step": 356050, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.2312350273132324, "global_step": 356051, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1110217571258545, "global_step": 356052, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.184222936630249, "global_step": 356053, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1137869358062744, "global_step": 356054, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.042368173599243, "global_step": 356055, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.2366929054260254, "global_step": 356056, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1000492572784424, "global_step": 356057, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.07698917388916, "global_step": 356058, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0645108222961426, "global_step": 356059, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1612682342529297, "global_step": 356060, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0841424465179443, "global_step": 356061, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.117239475250244, "global_step": 356062, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0927398204803467, "global_step": 356063, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0690083503723145, "global_step": 356064, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0592544078826904, "global_step": 356065, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0804038047790527, "global_step": 356066, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.09087872505188, "global_step": 356067, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.086998701095581, "global_step": 356068, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.116989850997925, "global_step": 356069, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.084105968475342, "global_step": 356070, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.165411949157715, "global_step": 356071, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.172816038131714, "global_step": 356072, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1548714637756348, "global_step": 356073, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0952565670013428, "global_step": 356074, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0853404998779297, "global_step": 356075, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.134830951690674, "global_step": 356076, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.053865909576416, "global_step": 356077, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.110342025756836, "global_step": 356078, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.068037271499634, "global_step": 356079, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0970771312713623, "global_step": 356080, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1383132934570312, "global_step": 356081, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1576826572418213, "global_step": 356082, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.171211004257202, "global_step": 356083, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1583383083343506, "global_step": 356084, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.029492139816284, "global_step": 356085, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0641329288482666, "global_step": 356086, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.089766263961792, "global_step": 356087, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1992740631103516, "global_step": 356088, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.142611265182495, "global_step": 356089, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0928382873535156, "global_step": 356090, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0797204971313477, "global_step": 356091, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1735010147094727, "global_step": 356092, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1091487407684326, "global_step": 356093, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.118074417114258, "global_step": 356094, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0862677097320557, "global_step": 356095, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1406009197235107, "global_step": 356096, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1595070362091064, "global_step": 356097, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.077219247817993, "global_step": 356098, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.110656976699829, "global_step": 356099, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.020369291305542, "global_step": 356100, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1107492446899414, "global_step": 356101, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.133423328399658, "global_step": 356102, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.135770797729492, "global_step": 356103, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.191394329071045, "global_step": 356104, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.101248025894165, "global_step": 356105, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1812264919281006, "global_step": 356106, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0921123027801514, "global_step": 356107, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.109755039215088, "global_step": 356108, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1151607036590576, "global_step": 356109, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1268954277038574, "global_step": 356110, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.189635992050171, "global_step": 356111, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1390151977539062, "global_step": 356112, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0635831356048584, "global_step": 356113, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.107980966567993, "global_step": 356114, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0528807640075684, "global_step": 356115, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1317996978759766, "global_step": 356116, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.135026216506958, "global_step": 356117, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.063567638397217, "global_step": 356118, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.116358995437622, "global_step": 356119, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.078829288482666, "global_step": 356120, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1260974407196045, "global_step": 356121, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0817224979400635, "global_step": 356122, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.124744415283203, "global_step": 356123, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1228158473968506, "global_step": 356124, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.09816837310791, "global_step": 356125, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0835442543029785, "global_step": 356126, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0407755374908447, "global_step": 356127, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.113651752471924, "global_step": 356128, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1934239864349365, "global_step": 356129, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1202564239501953, "global_step": 356130, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0841012001037598, "global_step": 356131, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.053776264190674, "global_step": 356132, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1429104804992676, "global_step": 356133, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.046609878540039, "global_step": 356134, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.114924669265747, "global_step": 356135, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.124891519546509, "global_step": 356136, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1708502769470215, "global_step": 356137, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1100239753723145, "global_step": 356138, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.12628173828125, "global_step": 356139, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1726057529449463, "global_step": 356140, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0790481567382812, "global_step": 356141, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.12967848777771, "global_step": 356142, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.107361316680908, "global_step": 356143, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.092390537261963, "global_step": 356144, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1435344219207764, "global_step": 356145, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.213158369064331, "global_step": 356146, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1751112937927246, "global_step": 356147, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.228003978729248, "global_step": 356148, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0793721675872803, "global_step": 356149, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0951948165893555, "global_step": 356150, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.145080804824829, "global_step": 356151, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.153132438659668, "global_step": 356152, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0690932273864746, "global_step": 356153, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.147252321243286, "global_step": 356154, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0660128593444824, "global_step": 356155, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1097137928009033, "global_step": 356156, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0854008197784424, "global_step": 356157, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1964111328125, "global_step": 356158, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.125380516052246, "global_step": 356159, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.185823678970337, "global_step": 356160, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0818543434143066, "global_step": 356161, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.094334840774536, "global_step": 356162, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.063443899154663, "global_step": 356163, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.149914264678955, "global_step": 356164, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.073765993118286, "global_step": 356165, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.08109974861145, "global_step": 356166, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0201354026794434, "global_step": 356167, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.19789719581604, "global_step": 356168, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1304492950439453, "global_step": 356169, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.114278793334961, "global_step": 356170, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1312813758850098, "global_step": 356171, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.2039291858673096, "global_step": 356172, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1128411293029785, "global_step": 356173, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1012868881225586, "global_step": 356174, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0126426219940186, "global_step": 356175, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.096811056137085, "global_step": 356176, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0982611179351807, "global_step": 356177, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1562845706939697, "global_step": 356178, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.042003870010376, "global_step": 356179, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0747554302215576, "global_step": 356180, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.158101797103882, "global_step": 356181, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0744869709014893, "global_step": 356182, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.07688570022583, "global_step": 356183, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.15346360206604, "global_step": 356184, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.220449209213257, "global_step": 356185, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.165933609008789, "global_step": 356186, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.141218900680542, "global_step": 356187, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1262784004211426, "global_step": 356188, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0540366172790527, "global_step": 356189, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0642991065979004, "global_step": 356190, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1018083095550537, "global_step": 356191, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.128657579421997, "global_step": 356192, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.120728015899658, "global_step": 356193, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1054575443267822, "global_step": 356194, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0949745178222656, "global_step": 356195, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.120570659637451, "global_step": 356196, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1045608520507812, "global_step": 356197, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0412983894348145, "global_step": 356198, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1848409175872803, "global_step": 356199, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1009373664855957, "global_step": 356200, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0625052452087402, "global_step": 356201, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.119431734085083, "global_step": 356202, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.078460454940796, "global_step": 356203, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1117570400238037, "global_step": 356204, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.148059129714966, "global_step": 356205, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1866209506988525, "global_step": 356206, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1234283447265625, "global_step": 356207, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.074315071105957, "global_step": 356208, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.026597738265991, "global_step": 356209, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.064572334289551, "global_step": 356210, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0986804962158203, "global_step": 356211, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.154369354248047, "global_step": 356212, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0514566898345947, "global_step": 356213, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0377702713012695, "global_step": 356214, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.125030040740967, "global_step": 356215, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0510311126708984, "global_step": 356216, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.208721399307251, "global_step": 356217, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0862646102905273, "global_step": 356218, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.118988275527954, "global_step": 356219, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0731735229492188, "global_step": 356220, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.029766321182251, "global_step": 356221, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0676286220550537, "global_step": 356222, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1205453872680664, "global_step": 356223, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.099668502807617, "global_step": 356224, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.109178304672241, "global_step": 356225, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0566744804382324, "global_step": 356226, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1113665103912354, "global_step": 356227, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0910513401031494, "global_step": 356228, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0980000495910645, "global_step": 356229, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.117356777191162, "global_step": 356230, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1543967723846436, "global_step": 356231, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.101942539215088, "global_step": 356232, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.208855628967285, "global_step": 356233, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0442962646484375, "global_step": 356234, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0723161697387695, "global_step": 356235, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1425342559814453, "global_step": 356236, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.156784772872925, "global_step": 356237, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0831422805786133, "global_step": 356238, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.102391242980957, "global_step": 356239, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0872063636779785, "global_step": 356240, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.133237361907959, "global_step": 356241, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1003315448760986, "global_step": 356242, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.121096611022949, "global_step": 356243, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1234076023101807, "global_step": 356244, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.092942714691162, "global_step": 356245, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1634764671325684, "global_step": 356246, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.134289026260376, "global_step": 356247, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1173770427703857, "global_step": 356248, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.010028600692749, "global_step": 356249, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1911802291870117, "global_step": 356250, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1481454372406006, "global_step": 356251, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.124260902404785, "global_step": 356252, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.118565797805786, "global_step": 356253, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.100468873977661, "global_step": 356254, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.108273983001709, "global_step": 356255, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.119014024734497, "global_step": 356256, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0995962619781494, "global_step": 356257, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0515494346618652, "global_step": 356258, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1728391647338867, "global_step": 356259, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0679855346679688, "global_step": 356260, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.189793586730957, "global_step": 356261, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0765154361724854, "global_step": 356262, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.091118574142456, "global_step": 356263, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.197075366973877, "global_step": 356264, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1823389530181885, "global_step": 356265, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0921802520751953, "global_step": 356266, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0920040607452393, "global_step": 356267, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1126315593719482, "global_step": 356268, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1117687225341797, "global_step": 356269, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.113715887069702, "global_step": 356270, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.135394334793091, "global_step": 356271, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.176753044128418, "global_step": 356272, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1205029487609863, "global_step": 356273, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.189007520675659, "global_step": 356274, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.129631757736206, "global_step": 356275, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0950608253479004, "global_step": 356276, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.160482406616211, "global_step": 356277, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0856239795684814, "global_step": 356278, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.090738534927368, "global_step": 356279, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1962661743164062, "global_step": 356280, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1126604080200195, "global_step": 356281, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1515934467315674, "global_step": 356282, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.09806489944458, "global_step": 356283, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.188589572906494, "global_step": 356284, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1201171875, "global_step": 356285, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.184570074081421, "global_step": 356286, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0266401767730713, "global_step": 356287, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.062230348587036, "global_step": 356288, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1258294582366943, "global_step": 356289, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1685431003570557, "global_step": 356290, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.153336524963379, "global_step": 356291, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.091689348220825, "global_step": 356292, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0551042556762695, "global_step": 356293, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0767107009887695, "global_step": 356294, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.121796131134033, "global_step": 356295, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1774380207061768, "global_step": 356296, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.2147819995880127, "global_step": 356297, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.084636926651001, "global_step": 356298, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.129889726638794, "global_step": 356299, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.030810832977295, "global_step": 356300, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1464016437530518, "global_step": 356301, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0962114334106445, "global_step": 356302, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0356221199035645, "global_step": 356303, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.094886302947998, "global_step": 356304, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1010210514068604, "global_step": 356305, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0366313457489014, "global_step": 356306, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0761003494262695, "global_step": 356307, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1288063526153564, "global_step": 356308, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0642409324645996, "global_step": 356309, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.10256028175354, "global_step": 356310, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0573809146881104, "global_step": 356311, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.087183713912964, "global_step": 356312, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1986515522003174, "global_step": 356313, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.079303741455078, "global_step": 356314, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0441579818725586, "global_step": 356315, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1124117374420166, "global_step": 356316, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.135551929473877, "global_step": 356317, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.100727081298828, "global_step": 356318, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.125910758972168, "global_step": 356319, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.032011032104492, "global_step": 356320, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.232341766357422, "global_step": 356321, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.087623119354248, "global_step": 356322, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1808300018310547, "global_step": 356323, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.125730276107788, "global_step": 356324, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1425740718841553, "global_step": 356325, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.075704336166382, "global_step": 356326, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0908236503601074, "global_step": 356327, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.073892831802368, "global_step": 356328, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.111175537109375, "global_step": 356329, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1155099868774414, "global_step": 356330, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.127997636795044, "global_step": 356331, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0801310539245605, "global_step": 356332, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.102146863937378, "global_step": 356333, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.12628436088562, "global_step": 356334, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.120288133621216, "global_step": 356335, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.157571792602539, "global_step": 356336, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0347189903259277, "global_step": 356337, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0655508041381836, "global_step": 356338, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0928878784179688, "global_step": 356339, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0906434059143066, "global_step": 356340, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1111130714416504, "global_step": 356341, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.157369613647461, "global_step": 356342, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.179250955581665, "global_step": 356343, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.136324644088745, "global_step": 356344, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.144304037094116, "global_step": 356345, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0765175819396973, "global_step": 356346, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1039974689483643, "global_step": 356347, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0610082149505615, "global_step": 356348, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.110903024673462, "global_step": 356349, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1995930671691895, "global_step": 356350, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1442270278930664, "global_step": 356351, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1285648345947266, "global_step": 356352, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.179273843765259, "global_step": 356353, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.039005756378174, "global_step": 356354, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.062526226043701, "global_step": 356355, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.111740827560425, "global_step": 356356, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.078462839126587, "global_step": 356357, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.124746561050415, "global_step": 356358, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.191298007965088, "global_step": 356359, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0499260425567627, "global_step": 356360, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0992088317871094, "global_step": 356361, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.108565092086792, "global_step": 356362, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0650107860565186, "global_step": 356363, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.084578514099121, "global_step": 356364, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.135007619857788, "global_step": 356365, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1681482791900635, "global_step": 356366, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1307754516601562, "global_step": 356367, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.156569480895996, "global_step": 356368, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.087895631790161, "global_step": 356369, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1719164848327637, "global_step": 356370, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0568535327911377, "global_step": 356371, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1233420372009277, "global_step": 356372, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.095078706741333, "global_step": 356373, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0153253078460693, "global_step": 356374, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.049103021621704, "global_step": 356375, "epoch": 717, "lr": 5e-05}
{"train_loss": 1.9980494976043701, "global_step": 356376, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.133216619491577, "global_step": 356377, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.122509241104126, "global_step": 356378, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0704128742218018, "global_step": 356379, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0706238746643066, "global_step": 356380, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.083117961883545, "global_step": 356381, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.121729850769043, "global_step": 356382, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.057065963745117, "global_step": 356383, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.035733938217163, "global_step": 356384, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.181432008743286, "global_step": 356385, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.151583433151245, "global_step": 356386, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.134862184524536, "global_step": 356387, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1384427547454834, "global_step": 356388, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1045989990234375, "global_step": 356389, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1140804290771484, "global_step": 356390, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.152928590774536, "global_step": 356391, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0317623615264893, "global_step": 356392, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1442301273345947, "global_step": 356393, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1212520599365234, "global_step": 356394, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.105452299118042, "global_step": 356395, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.034881830215454, "global_step": 356396, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0873827934265137, "global_step": 356397, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.2292723655700684, "global_step": 356398, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0926051139831543, "global_step": 356399, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.200847625732422, "global_step": 356400, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.027686834335327, "global_step": 356401, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.180396795272827, "global_step": 356402, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0980122089385986, "global_step": 356403, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0838265419006348, "global_step": 356404, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.06978440284729, "global_step": 356405, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0949923992156982, "global_step": 356406, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1467199325561523, "global_step": 356407, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1295993328094482, "global_step": 356408, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0849902629852295, "global_step": 356409, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1124699115753174, "global_step": 356410, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0317838191986084, "global_step": 356411, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1174192428588867, "global_step": 356412, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1890673637390137, "global_step": 356413, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0754201412200928, "global_step": 356414, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1309757232666016, "global_step": 356415, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0896823406219482, "global_step": 356416, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.119244337081909, "global_step": 356417, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1356632709503174, "global_step": 356418, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1151771545410156, "global_step": 356419, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.2336902618408203, "global_step": 356420, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.130812883377075, "global_step": 356421, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1974291801452637, "global_step": 356422, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.171433687210083, "global_step": 356423, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.119338035583496, "global_step": 356424, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1718454360961914, "global_step": 356425, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.116024971008301, "global_step": 356426, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.113959550857544, "global_step": 356427, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1811769008636475, "global_step": 356428, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.18035888671875, "global_step": 356429, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.034884452819824, "global_step": 356430, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0100018978118896, "global_step": 356431, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1540603637695312, "global_step": 356432, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.122061014175415, "global_step": 356433, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.145493507385254, "global_step": 356434, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.052365779876709, "global_step": 356435, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.136066436767578, "global_step": 356436, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.151423454284668, "global_step": 356437, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.090637445449829, "global_step": 356438, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.067868709564209, "global_step": 356439, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0835800170898438, "global_step": 356440, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.062546491622925, "global_step": 356441, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1928136348724365, "global_step": 356442, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1011593341827393, "global_step": 356443, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.002066135406494, "global_step": 356444, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.195495367050171, "global_step": 356445, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.032413959503174, "global_step": 356446, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.117457628250122, "global_step": 356447, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1580893993377686, "global_step": 356448, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1420888900756836, "global_step": 356449, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0452072620391846, "global_step": 356450, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.151592969894409, "global_step": 356451, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0744776725769043, "global_step": 356452, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1146862506866455, "global_step": 356453, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.087576389312744, "global_step": 356454, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.213829278945923, "global_step": 356455, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0914688110351562, "global_step": 356456, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0763955116271973, "global_step": 356457, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.089524030685425, "global_step": 356458, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0698859691619873, "global_step": 356459, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1163008213043213, "global_step": 356460, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0850906372070312, "global_step": 356461, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.150895118713379, "global_step": 356462, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0748488903045654, "global_step": 356463, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1302297115325928, "global_step": 356464, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.145738363265991, "global_step": 356465, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1335668563842773, "global_step": 356466, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1227147579193115, "global_step": 356467, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1564786434173584, "global_step": 356468, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0958027839660645, "global_step": 356469, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.083394765853882, "global_step": 356470, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0917258262634277, "global_step": 356471, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1341605186462402, "global_step": 356472, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1204190254211426, "global_step": 356473, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.083778142929077, "global_step": 356474, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0322108268737793, "global_step": 356475, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.010572671890259, "global_step": 356476, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1858341693878174, "global_step": 356477, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1069788932800293, "global_step": 356478, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0940306186676025, "global_step": 356479, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1487183570861816, "global_step": 356480, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.2529497146606445, "global_step": 356481, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1584224700927734, "global_step": 356482, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0325076580047607, "global_step": 356483, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.095329999923706, "global_step": 356484, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1024608612060547, "global_step": 356485, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1529674530029297, "global_step": 356486, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.162691354751587, "global_step": 356487, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0446579456329346, "global_step": 356488, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1364402770996094, "global_step": 356489, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.103541612625122, "global_step": 356490, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0997867584228516, "global_step": 356491, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.136711359024048, "global_step": 356492, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.111302614212036, "global_step": 356493, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1034159660339355, "global_step": 356494, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.12778902053833, "global_step": 356495, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.124386787414551, "global_step": 356496, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1416537761688232, "global_step": 356497, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1445019245147705, "global_step": 356498, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1535322666168213, "global_step": 356499, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0614993572235107, "global_step": 356500, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.126260757446289, "global_step": 356501, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1281087398529053, "global_step": 356502, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1566267013549805, "global_step": 356503, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.075650691986084, "global_step": 356504, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0560524463653564, "global_step": 356505, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1259891986846924, "global_step": 356506, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.165599822998047, "global_step": 356507, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0577926635742188, "global_step": 356508, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.145380973815918, "global_step": 356509, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0887043476104736, "global_step": 356510, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1034693717956543, "global_step": 356511, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1749134063720703, "global_step": 356512, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.057847499847412, "global_step": 356513, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1617908477783203, "global_step": 356514, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.049088716506958, "global_step": 356515, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.083582639694214, "global_step": 356516, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0948784351348877, "global_step": 356517, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.121964931488037, "global_step": 356518, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.098583221435547, "global_step": 356519, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.009373426437378, "global_step": 356520, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1824355125427246, "global_step": 356521, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0686798095703125, "global_step": 356522, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.030139923095703, "global_step": 356523, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0400373935699463, "global_step": 356524, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0136210918426514, "global_step": 356525, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1161410808563232, "global_step": 356526, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.111128091812134, "global_step": 356527, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1209166049957275, "global_step": 356528, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.199354648590088, "global_step": 356529, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.122479200363159, "global_step": 356530, "epoch": 717, "lr": 5e-05}
{"train_loss": 1.9850753545761108, "global_step": 356531, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.122769832611084, "global_step": 356532, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1113767623901367, "global_step": 356533, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.039721727371216, "global_step": 356534, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.133725643157959, "global_step": 356535, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.092613935470581, "global_step": 356536, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.152930736541748, "global_step": 356537, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0936076641082764, "global_step": 356538, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1224710941314697, "global_step": 356539, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0968282222747803, "global_step": 356540, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0372512340545654, "global_step": 356541, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1071081161499023, "global_step": 356542, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.070406675338745, "global_step": 356543, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0657246112823486, "global_step": 356544, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.149289131164551, "global_step": 356545, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.109896659851074, "global_step": 356546, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.207767963409424, "global_step": 356547, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0655035972595215, "global_step": 356548, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0917539596557617, "global_step": 356549, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.122685670852661, "global_step": 356550, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1254656314849854, "global_step": 356551, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1402292251586914, "global_step": 356552, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1078851222991943, "global_step": 356553, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1796414852142334, "global_step": 356554, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.152543544769287, "global_step": 356555, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.166640281677246, "global_step": 356556, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.03934645652771, "global_step": 356557, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0724527835845947, "global_step": 356558, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1455657482147217, "global_step": 356559, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.071488380432129, "global_step": 356560, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1642892360687256, "global_step": 356561, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0658676624298096, "global_step": 356562, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.17818546295166, "global_step": 356563, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.195952892303467, "global_step": 356564, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0540413856506348, "global_step": 356565, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0222373008728027, "global_step": 356566, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1251819133758545, "global_step": 356567, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.2056899070739746, "global_step": 356568, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.112922191619873, "global_step": 356569, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1100566387176514, "global_step": 356570, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0645062923431396, "global_step": 356571, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.2519583702087402, "global_step": 356572, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0873913764953613, "global_step": 356573, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1038084030151367, "global_step": 356574, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1061315536499023, "global_step": 356575, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.140872001647949, "global_step": 356576, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1544179916381836, "global_step": 356577, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.078198194503784, "global_step": 356578, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.153656005859375, "global_step": 356579, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1546506881713867, "global_step": 356580, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.06130313873291, "global_step": 356581, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0918819904327393, "global_step": 356582, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1178107261657715, "global_step": 356583, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1841533184051514, "global_step": 356584, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0708913803100586, "global_step": 356585, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.067871332168579, "global_step": 356586, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.087705135345459, "global_step": 356587, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.077242374420166, "global_step": 356588, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.140756845474243, "global_step": 356589, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.151459217071533, "global_step": 356590, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1501548290252686, "global_step": 356591, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1058719158172607, "global_step": 356592, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.136378526687622, "global_step": 356593, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0765738487243652, "global_step": 356594, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.048733949661255, "global_step": 356595, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0902907848358154, "global_step": 356596, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1097493171691895, "global_step": 356597, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.027761697769165, "global_step": 356598, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1533195972442627, "global_step": 356599, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1398017406463623, "global_step": 356600, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0657825469970703, "global_step": 356601, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1440773010253906, "global_step": 356602, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0966169834136963, "global_step": 356603, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1315040588378906, "global_step": 356604, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0853962898254395, "global_step": 356605, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0440123081207275, "global_step": 356606, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.075899362564087, "global_step": 356607, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1793811321258545, "global_step": 356608, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0836613178253174, "global_step": 356609, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1566598415374756, "global_step": 356610, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1717374324798584, "global_step": 356611, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.003380060195923, "global_step": 356612, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0768845081329346, "global_step": 356613, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.054044246673584, "global_step": 356614, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1006433963775635, "global_step": 356615, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1765329837799072, "global_step": 356616, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0601582527160645, "global_step": 356617, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1865015029907227, "global_step": 356618, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.106765031814575, "global_step": 356619, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1440367698669434, "global_step": 356620, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.188098907470703, "global_step": 356621, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1302640438079834, "global_step": 356622, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.09265398979187, "global_step": 356623, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.046239137649536, "global_step": 356624, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1561875343322754, "global_step": 356625, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1851370334625244, "global_step": 356626, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.154017686843872, "global_step": 356627, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0736773014068604, "global_step": 356628, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.092698097229004, "global_step": 356629, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.148838996887207, "global_step": 356630, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1651251316070557, "global_step": 356631, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.116454601287842, "global_step": 356632, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1528115272521973, "global_step": 356633, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0900356769561768, "global_step": 356634, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0961852073669434, "global_step": 356635, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.120115041732788, "global_step": 356636, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.168524742126465, "global_step": 356637, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.126108169555664, "global_step": 356638, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1234898567199707, "global_step": 356639, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1015231609344482, "global_step": 356640, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1108927726745605, "global_step": 356641, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.142801523208618, "global_step": 356642, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0436015129089355, "global_step": 356643, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0697717666625977, "global_step": 356644, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1132054328918457, "global_step": 356645, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1266252994537354, "global_step": 356646, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1809616088867188, "global_step": 356647, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0900044441223145, "global_step": 356648, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.093845844268799, "global_step": 356649, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0750770568847656, "global_step": 356650, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1812925338745117, "global_step": 356651, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1646928787231445, "global_step": 356652, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1201889514923096, "global_step": 356653, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.15163516998291, "global_step": 356654, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0803205966949463, "global_step": 356655, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1071102619171143, "global_step": 356656, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0225863456726074, "global_step": 356657, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.152644395828247, "global_step": 356658, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.155588388442993, "global_step": 356659, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0385866165161133, "global_step": 356660, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.073585033416748, "global_step": 356661, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1127052307128906, "global_step": 356662, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.187605381011963, "global_step": 356663, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1209044456481934, "global_step": 356664, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.117204427719116, "global_step": 356665, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1325912475585938, "global_step": 356666, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.142744541168213, "global_step": 356667, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0117647647857666, "global_step": 356668, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.095228910446167, "global_step": 356669, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.118910312652588, "global_step": 356670, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0670952796936035, "global_step": 356671, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1251773834228516, "global_step": 356672, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1035144329071045, "global_step": 356673, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1416001319885254, "global_step": 356674, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.144268035888672, "global_step": 356675, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1458423137664795, "global_step": 356676, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.121213912963867, "global_step": 356677, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.239997625350952, "global_step": 356678, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.113184690475464, "global_step": 356679, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.15455961227417, "global_step": 356680, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1973178386688232, "global_step": 356681, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.147277355194092, "global_step": 356682, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1726317405700684, "global_step": 356683, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.15447735786438, "global_step": 356684, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.183107614517212, "global_step": 356685, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0991921424865723, "global_step": 356686, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0942699909210205, "global_step": 356687, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.14729642868042, "global_step": 356688, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.110285758972168, "global_step": 356689, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.2371323108673096, "global_step": 356690, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0996994972229004, "global_step": 356691, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1058483123779297, "global_step": 356692, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1102964878082275, "global_step": 356693, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.088501214981079, "global_step": 356694, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1710364818573, "global_step": 356695, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1161608695983887, "global_step": 356696, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0100128650665283, "global_step": 356697, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1406610012054443, "global_step": 356698, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.12235689163208, "global_step": 356699, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1487419605255127, "global_step": 356700, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.059628486633301, "global_step": 356701, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.088132858276367, "global_step": 356702, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1746063232421875, "global_step": 356703, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0951004028320312, "global_step": 356704, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1677591800689697, "global_step": 356705, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0736262798309326, "global_step": 356706, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0679121017456055, "global_step": 356707, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1070096492767334, "global_step": 356708, "epoch": 717, "lr": 5e-05}
{"train_loss": 1.9782689809799194, "global_step": 356709, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1772775650024414, "global_step": 356710, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1196396350860596, "global_step": 356711, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.186244010925293, "global_step": 356712, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.188239812850952, "global_step": 356713, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0529191493988037, "global_step": 356714, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.096466302871704, "global_step": 356715, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.103050470352173, "global_step": 356716, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.128908395767212, "global_step": 356717, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0631847381591797, "global_step": 356718, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1997179985046387, "global_step": 356719, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.068246603012085, "global_step": 356720, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1553702354431152, "global_step": 356721, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.145695686340332, "global_step": 356722, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.1359546184539795, "global_step": 356723, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.111663818359375, "global_step": 356724, "epoch": 717, "lr": 5e-05}
{"train_loss": 2.0633065700531006, "global_step": 356725, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0895235538482666, "global_step": 356726, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1421515941619873, "global_step": 356727, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0535497665405273, "global_step": 356728, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.086822271347046, "global_step": 356729, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1226346492767334, "global_step": 356730, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.227311134338379, "global_step": 356731, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.093116044998169, "global_step": 356732, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1253209114074707, "global_step": 356733, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0725443363189697, "global_step": 356734, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.077240467071533, "global_step": 356735, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0032663345336914, "global_step": 356736, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0906457901000977, "global_step": 356737, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.12691593170166, "global_step": 356738, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0831737518310547, "global_step": 356739, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.128214120864868, "global_step": 356740, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1420373916625977, "global_step": 356741, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1455576419830322, "global_step": 356742, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.104600667953491, "global_step": 356743, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0725841522216797, "global_step": 356744, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0761799812316895, "global_step": 356745, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.164855480194092, "global_step": 356746, "epoch": 718, "lr": 5e-05}
{"train_loss": 1.9631142616271973, "global_step": 356747, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0680484771728516, "global_step": 356748, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1706666946411133, "global_step": 356749, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.148296594619751, "global_step": 356750, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1822667121887207, "global_step": 356751, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.109825611114502, "global_step": 356752, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1219139099121094, "global_step": 356753, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0834341049194336, "global_step": 356754, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.188502788543701, "global_step": 356755, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1176795959472656, "global_step": 356756, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0937867164611816, "global_step": 356757, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2302253246307373, "global_step": 356758, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0928735733032227, "global_step": 356759, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0601634979248047, "global_step": 356760, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1496846675872803, "global_step": 356761, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0188615322113037, "global_step": 356762, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.021148681640625, "global_step": 356763, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.106039524078369, "global_step": 356764, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.092388868331909, "global_step": 356765, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1662089824676514, "global_step": 356766, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1213581562042236, "global_step": 356767, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.061152935028076, "global_step": 356768, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1320700645446777, "global_step": 356769, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.079484224319458, "global_step": 356770, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1192526817321777, "global_step": 356771, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0674545764923096, "global_step": 356772, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0726466178894043, "global_step": 356773, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.135648012161255, "global_step": 356774, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.143372058868408, "global_step": 356775, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.093855142593384, "global_step": 356776, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.106623649597168, "global_step": 356777, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1521828174591064, "global_step": 356778, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.094304323196411, "global_step": 356779, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1347813606262207, "global_step": 356780, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.080402374267578, "global_step": 356781, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.105689525604248, "global_step": 356782, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.109257221221924, "global_step": 356783, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1507792472839355, "global_step": 356784, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.141113519668579, "global_step": 356785, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1484780311584473, "global_step": 356786, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1267611980438232, "global_step": 356787, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1038849353790283, "global_step": 356788, "epoch": 718, "lr": 5e-05}
{"train_loss": 1.9791598320007324, "global_step": 356789, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.072031021118164, "global_step": 356790, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.071942090988159, "global_step": 356791, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1420300006866455, "global_step": 356792, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.11234450340271, "global_step": 356793, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1601500511169434, "global_step": 356794, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0708181858062744, "global_step": 356795, "epoch": 718, "lr": 5e-05}
{"train_loss": 1.9692541360855103, "global_step": 356796, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1265766620635986, "global_step": 356797, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0942680835723877, "global_step": 356798, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1308295726776123, "global_step": 356799, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.085829257965088, "global_step": 356800, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1448187828063965, "global_step": 356801, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1903059482574463, "global_step": 356802, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1965153217315674, "global_step": 356803, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1611948013305664, "global_step": 356804, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.006126642227173, "global_step": 356805, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.06667423248291, "global_step": 356806, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.025733470916748, "global_step": 356807, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0220682621002197, "global_step": 356808, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0519261360168457, "global_step": 356809, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0380921363830566, "global_step": 356810, "epoch": 718, "lr": 5e-05}
{"train_loss": 1.969786286354065, "global_step": 356811, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0263915061950684, "global_step": 356812, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0676794052124023, "global_step": 356813, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0875093936920166, "global_step": 356814, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.081700086593628, "global_step": 356815, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0612058639526367, "global_step": 356816, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.136789560317993, "global_step": 356817, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0795161724090576, "global_step": 356818, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.062756061553955, "global_step": 356819, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.129814863204956, "global_step": 356820, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1783909797668457, "global_step": 356821, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0691580772399902, "global_step": 356822, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0584611892700195, "global_step": 356823, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.115504264831543, "global_step": 356824, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0498926639556885, "global_step": 356825, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0433971881866455, "global_step": 356826, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0846660137176514, "global_step": 356827, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.054213762283325, "global_step": 356828, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1724965572357178, "global_step": 356829, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0381052494049072, "global_step": 356830, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.117436408996582, "global_step": 356831, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0346150398254395, "global_step": 356832, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0861237049102783, "global_step": 356833, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.094858407974243, "global_step": 356834, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1276514530181885, "global_step": 356835, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.053057909011841, "global_step": 356836, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.105520486831665, "global_step": 356837, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.066314697265625, "global_step": 356838, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.158705472946167, "global_step": 356839, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1647002696990967, "global_step": 356840, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.077552556991577, "global_step": 356841, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.153714895248413, "global_step": 356842, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0744872093200684, "global_step": 356843, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1312191486358643, "global_step": 356844, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1008262634277344, "global_step": 356845, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1197760105133057, "global_step": 356846, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0775082111358643, "global_step": 356847, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.100397825241089, "global_step": 356848, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1619973182678223, "global_step": 356849, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1983330249786377, "global_step": 356850, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1089487075805664, "global_step": 356851, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1552655696868896, "global_step": 356852, "epoch": 718, "lr": 5e-05}
{"train_loss": 1.9841079711914062, "global_step": 356853, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.136033535003662, "global_step": 356854, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0993945598602295, "global_step": 356855, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.037099599838257, "global_step": 356856, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1670031547546387, "global_step": 356857, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.055911064147949, "global_step": 356858, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0721116065979004, "global_step": 356859, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.113264322280884, "global_step": 356860, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.089352607727051, "global_step": 356861, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.072533369064331, "global_step": 356862, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.123964309692383, "global_step": 356863, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.118612051010132, "global_step": 356864, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0830769538879395, "global_step": 356865, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0829646587371826, "global_step": 356866, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0923943519592285, "global_step": 356867, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0177738666534424, "global_step": 356868, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.151538372039795, "global_step": 356869, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0718657970428467, "global_step": 356870, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.060513973236084, "global_step": 356871, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.158200740814209, "global_step": 356872, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.116884469985962, "global_step": 356873, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1355679035186768, "global_step": 356874, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.078531503677368, "global_step": 356875, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0658814907073975, "global_step": 356876, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1418418884277344, "global_step": 356877, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1430909633636475, "global_step": 356878, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0793371200561523, "global_step": 356879, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.097839832305908, "global_step": 356880, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0486464500427246, "global_step": 356881, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.122483491897583, "global_step": 356882, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1224911212921143, "global_step": 356883, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0649540424346924, "global_step": 356884, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1365087032318115, "global_step": 356885, "epoch": 718, "lr": 5e-05}
{"train_loss": 1.9985501766204834, "global_step": 356886, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.137638568878174, "global_step": 356887, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1226680278778076, "global_step": 356888, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1338324546813965, "global_step": 356889, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.04972767829895, "global_step": 356890, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1855664253234863, "global_step": 356891, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0942282676696777, "global_step": 356892, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.099785089492798, "global_step": 356893, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0116920471191406, "global_step": 356894, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.137303352355957, "global_step": 356895, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1336822509765625, "global_step": 356896, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0797617435455322, "global_step": 356897, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.093423366546631, "global_step": 356898, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1012485027313232, "global_step": 356899, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1304337978363037, "global_step": 356900, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0648820400238037, "global_step": 356901, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.047166585922241, "global_step": 356902, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1117043495178223, "global_step": 356903, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.108328104019165, "global_step": 356904, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.119945764541626, "global_step": 356905, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1337664127349854, "global_step": 356906, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0245254039764404, "global_step": 356907, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0177371501922607, "global_step": 356908, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2120556831359863, "global_step": 356909, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0789248943328857, "global_step": 356910, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1339340209960938, "global_step": 356911, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1179745197296143, "global_step": 356912, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0529990196228027, "global_step": 356913, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.215859889984131, "global_step": 356914, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.106311559677124, "global_step": 356915, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1200480461120605, "global_step": 356916, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0336427688598633, "global_step": 356917, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0912346839904785, "global_step": 356918, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1054110527038574, "global_step": 356919, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.088059902191162, "global_step": 356920, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.169167995452881, "global_step": 356921, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1774027347564697, "global_step": 356922, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1453909873962402, "global_step": 356923, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1181886196136475, "global_step": 356924, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.011528253555298, "global_step": 356925, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1006386280059814, "global_step": 356926, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0881006717681885, "global_step": 356927, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0835347175598145, "global_step": 356928, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.094702959060669, "global_step": 356929, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1348180770874023, "global_step": 356930, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.081225633621216, "global_step": 356931, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1338391304016113, "global_step": 356932, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1307618618011475, "global_step": 356933, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.08469820022583, "global_step": 356934, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.153090000152588, "global_step": 356935, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.094407558441162, "global_step": 356936, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0801732540130615, "global_step": 356937, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.109963893890381, "global_step": 356938, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1150341033935547, "global_step": 356939, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0672719478607178, "global_step": 356940, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.153459310531616, "global_step": 356941, "epoch": 718, "lr": 5e-05}
{"train_loss": 1.9884920120239258, "global_step": 356942, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.079622983932495, "global_step": 356943, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.139274835586548, "global_step": 356944, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.068772077560425, "global_step": 356945, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2095513343811035, "global_step": 356946, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1160025596618652, "global_step": 356947, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1533312797546387, "global_step": 356948, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1872146129608154, "global_step": 356949, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1510040760040283, "global_step": 356950, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.091035842895508, "global_step": 356951, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.148242950439453, "global_step": 356952, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1575663089752197, "global_step": 356953, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.129730224609375, "global_step": 356954, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.046654462814331, "global_step": 356955, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1042044162750244, "global_step": 356956, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2066292762756348, "global_step": 356957, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.127230167388916, "global_step": 356958, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0895743370056152, "global_step": 356959, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1025919914245605, "global_step": 356960, "epoch": 718, "lr": 5e-05}
{"train_loss": 1.9822238683700562, "global_step": 356961, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.161339521408081, "global_step": 356962, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1358249187469482, "global_step": 356963, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1479146480560303, "global_step": 356964, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.07236385345459, "global_step": 356965, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.12296724319458, "global_step": 356966, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2227134704589844, "global_step": 356967, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0291645526885986, "global_step": 356968, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0591325759887695, "global_step": 356969, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.110546588897705, "global_step": 356970, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.104058027267456, "global_step": 356971, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.075545310974121, "global_step": 356972, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0214459896087646, "global_step": 356973, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0902280807495117, "global_step": 356974, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0987462997436523, "global_step": 356975, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1711626052856445, "global_step": 356976, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.149432420730591, "global_step": 356977, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.161304473876953, "global_step": 356978, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0318443775177, "global_step": 356979, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.13643217086792, "global_step": 356980, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0372869968414307, "global_step": 356981, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.207570791244507, "global_step": 356982, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.192723512649536, "global_step": 356983, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1198906898498535, "global_step": 356984, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.148493528366089, "global_step": 356985, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.111671209335327, "global_step": 356986, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0676400661468506, "global_step": 356987, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.132341146469116, "global_step": 356988, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1459548473358154, "global_step": 356989, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1583828926086426, "global_step": 356990, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1067631244659424, "global_step": 356991, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0461575984954834, "global_step": 356992, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.180528163909912, "global_step": 356993, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.050762891769409, "global_step": 356994, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0949528217315674, "global_step": 356995, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1568830013275146, "global_step": 356996, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1390421390533447, "global_step": 356997, "epoch": 718, "lr": 5e-05}
{"train_loss": 1.9808928966522217, "global_step": 356998, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1327457427978516, "global_step": 356999, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0979857444763184, "global_step": 357000, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.065194845199585, "global_step": 357001, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0914742946624756, "global_step": 357002, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.183051824569702, "global_step": 357003, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0291881561279297, "global_step": 357004, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1816298961639404, "global_step": 357005, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.029540538787842, "global_step": 357006, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.188523769378662, "global_step": 357007, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.105853319168091, "global_step": 357008, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0792369842529297, "global_step": 357009, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.096416711807251, "global_step": 357010, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.110560417175293, "global_step": 357011, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.082226037979126, "global_step": 357012, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.055838108062744, "global_step": 357013, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.065032482147217, "global_step": 357014, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1564619541168213, "global_step": 357015, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1472389698028564, "global_step": 357016, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.073556900024414, "global_step": 357017, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.128422737121582, "global_step": 357018, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0617902278900146, "global_step": 357019, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.069377899169922, "global_step": 357020, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1023523807525635, "global_step": 357021, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1160449981689453, "global_step": 357022, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.08953857421875, "global_step": 357023, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0655949115753174, "global_step": 357024, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1160361766815186, "global_step": 357025, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.098026752471924, "global_step": 357026, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0596797466278076, "global_step": 357027, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.119938611984253, "global_step": 357028, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0532782077789307, "global_step": 357029, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.112726926803589, "global_step": 357030, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1535463333129883, "global_step": 357031, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0803234577178955, "global_step": 357032, "epoch": 718, "lr": 5e-05}
{"train_loss": 1.988879680633545, "global_step": 357033, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0490074157714844, "global_step": 357034, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.105772018432617, "global_step": 357035, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.056689977645874, "global_step": 357036, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0901925563812256, "global_step": 357037, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1632773876190186, "global_step": 357038, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.137542963027954, "global_step": 357039, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1046059131622314, "global_step": 357040, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1410584449768066, "global_step": 357041, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1104884147644043, "global_step": 357042, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.040452480316162, "global_step": 357043, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0126118659973145, "global_step": 357044, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.123072862625122, "global_step": 357045, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.076998233795166, "global_step": 357046, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1422667503356934, "global_step": 357047, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.187263250350952, "global_step": 357048, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.176806688308716, "global_step": 357049, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.145972490310669, "global_step": 357050, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0532491207122803, "global_step": 357051, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1389527320861816, "global_step": 357052, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2290496826171875, "global_step": 357053, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0846269130706787, "global_step": 357054, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.094552755355835, "global_step": 357055, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0560951232910156, "global_step": 357056, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.157088041305542, "global_step": 357057, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0944583415985107, "global_step": 357058, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0822441577911377, "global_step": 357059, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0537312030792236, "global_step": 357060, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.081146240234375, "global_step": 357061, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.167551279067993, "global_step": 357062, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.059302806854248, "global_step": 357063, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2168445587158203, "global_step": 357064, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0983495712280273, "global_step": 357065, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0944061279296875, "global_step": 357066, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1301698684692383, "global_step": 357067, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0711171627044678, "global_step": 357068, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0755226612091064, "global_step": 357069, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0996406078338623, "global_step": 357070, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0242018699645996, "global_step": 357071, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1455068588256836, "global_step": 357072, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1543846130371094, "global_step": 357073, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1413748264312744, "global_step": 357074, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.078917980194092, "global_step": 357075, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.121126651763916, "global_step": 357076, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.077641248703003, "global_step": 357077, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0990960597991943, "global_step": 357078, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0356733798980713, "global_step": 357079, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.057465076446533, "global_step": 357080, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1478629112243652, "global_step": 357081, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0713653564453125, "global_step": 357082, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.205469846725464, "global_step": 357083, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2100839614868164, "global_step": 357084, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.073101758956909, "global_step": 357085, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.133756160736084, "global_step": 357086, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0898876190185547, "global_step": 357087, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.067908763885498, "global_step": 357088, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.18418288230896, "global_step": 357089, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0873029232025146, "global_step": 357090, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.117994785308838, "global_step": 357091, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1368234157562256, "global_step": 357092, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0433170795440674, "global_step": 357093, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.171473264694214, "global_step": 357094, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1301867961883545, "global_step": 357095, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.140909433364868, "global_step": 357096, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1003904342651367, "global_step": 357097, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1207337379455566, "global_step": 357098, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0832085609436035, "global_step": 357099, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1198601722717285, "global_step": 357100, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1338250637054443, "global_step": 357101, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1098971366882324, "global_step": 357102, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1232681274414062, "global_step": 357103, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1138010025024414, "global_step": 357104, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1107964515686035, "global_step": 357105, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1700398921966553, "global_step": 357106, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0688090324401855, "global_step": 357107, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1971638202667236, "global_step": 357108, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1044273376464844, "global_step": 357109, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1187667846679688, "global_step": 357110, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1114892959594727, "global_step": 357111, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1218724250793457, "global_step": 357112, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1234426498413086, "global_step": 357113, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1830265522003174, "global_step": 357114, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.172792911529541, "global_step": 357115, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.141475200653076, "global_step": 357116, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0884196758270264, "global_step": 357117, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0603599548339844, "global_step": 357118, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1151490211486816, "global_step": 357119, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0264077186584473, "global_step": 357120, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.169724464416504, "global_step": 357121, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1996116638183594, "global_step": 357122, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.125455379486084, "global_step": 357123, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.081634044647217, "global_step": 357124, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0381686687469482, "global_step": 357125, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1544718742370605, "global_step": 357126, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1099541187286377, "global_step": 357127, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0685982704162598, "global_step": 357128, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0924975872039795, "global_step": 357129, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1912238597869873, "global_step": 357130, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0830812454223633, "global_step": 357131, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.053220510482788, "global_step": 357132, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1550378799438477, "global_step": 357133, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1739704608917236, "global_step": 357134, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0182111263275146, "global_step": 357135, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.13285231590271, "global_step": 357136, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1100101470947266, "global_step": 357137, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1065990924835205, "global_step": 357138, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.121312379837036, "global_step": 357139, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1292450428009033, "global_step": 357140, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.126424789428711, "global_step": 357141, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1768417358398438, "global_step": 357142, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1414248943328857, "global_step": 357143, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0031983852386475, "global_step": 357144, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1078550815582275, "global_step": 357145, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.086235523223877, "global_step": 357146, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.22505784034729, "global_step": 357147, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.103416681289673, "global_step": 357148, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.061927556991577, "global_step": 357149, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1183881759643555, "global_step": 357150, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1132473945617676, "global_step": 357151, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.063206434249878, "global_step": 357152, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.091172456741333, "global_step": 357153, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1442642211914062, "global_step": 357154, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.133906841278076, "global_step": 357155, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2185609340667725, "global_step": 357156, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.084733009338379, "global_step": 357157, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1089587211608887, "global_step": 357158, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1773228645324707, "global_step": 357159, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0329437255859375, "global_step": 357160, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1221559047698975, "global_step": 357161, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1100656986236572, "global_step": 357162, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0982322692871094, "global_step": 357163, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.123029947280884, "global_step": 357164, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0981240272521973, "global_step": 357165, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1291446685791016, "global_step": 357166, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0565969944000244, "global_step": 357167, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0212841033935547, "global_step": 357168, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1864829063415527, "global_step": 357169, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0510809421539307, "global_step": 357170, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.139996290206909, "global_step": 357171, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0724754333496094, "global_step": 357172, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.068676471710205, "global_step": 357173, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1388185024261475, "global_step": 357174, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0921645164489746, "global_step": 357175, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1020712852478027, "global_step": 357176, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.13461971282959, "global_step": 357177, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.130638360977173, "global_step": 357178, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1216866970062256, "global_step": 357179, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1236257553100586, "global_step": 357180, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0884289741516113, "global_step": 357181, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.141916036605835, "global_step": 357182, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0640151500701904, "global_step": 357183, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.119859218597412, "global_step": 357184, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1219751834869385, "global_step": 357185, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.121647596359253, "global_step": 357186, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.034933090209961, "global_step": 357187, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0989139080047607, "global_step": 357188, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.135291576385498, "global_step": 357189, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.118725299835205, "global_step": 357190, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0660386085510254, "global_step": 357191, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.116682291030884, "global_step": 357192, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.035554885864258, "global_step": 357193, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.159308671951294, "global_step": 357194, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0467276573181152, "global_step": 357195, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1133105754852295, "global_step": 357196, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1502609252929688, "global_step": 357197, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.068561315536499, "global_step": 357198, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.08980655670166, "global_step": 357199, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0522286891937256, "global_step": 357200, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0793089866638184, "global_step": 357201, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.030024528503418, "global_step": 357202, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.091592311859131, "global_step": 357203, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1056838035583496, "global_step": 357204, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.149928331375122, "global_step": 357205, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.020310401916504, "global_step": 357206, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.124495267868042, "global_step": 357207, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.08937931060791, "global_step": 357208, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.069193124771118, "global_step": 357209, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0651495456695557, "global_step": 357210, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1346278190612793, "global_step": 357211, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.146841287612915, "global_step": 357212, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.092940092086792, "global_step": 357213, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1237621307373047, "global_step": 357214, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0089991092681885, "global_step": 357215, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.089946746826172, "global_step": 357216, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.04465913772583, "global_step": 357217, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.106954336166382, "global_step": 357218, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0603432655334473, "global_step": 357219, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.121018648147583, "global_step": 357220, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.047626256942749, "global_step": 357221, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0707476139068604, "global_step": 357222, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.20100998878479, "global_step": 357223, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0285720825195312, "global_step": 357224, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1241602897644043, "global_step": 357225, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1105005741119385, "global_step": 357226, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.154712677001953, "global_step": 357227, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2224953174591064, "global_step": 357228, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.205536127090454, "global_step": 357229, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1288394927978516, "global_step": 357230, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.13529896736145, "global_step": 357231, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.080167293548584, "global_step": 357232, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0877017974853516, "global_step": 357233, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.129751443862915, "global_step": 357234, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.175748348236084, "global_step": 357235, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1779422760009766, "global_step": 357236, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0894947052001953, "global_step": 357237, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.151299476623535, "global_step": 357238, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0657713413238525, "global_step": 357239, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.140904188156128, "global_step": 357240, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.104358673095703, "global_step": 357241, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0665128231048584, "global_step": 357242, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1508407592773438, "global_step": 357243, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0304720401763916, "global_step": 357244, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1879396438598633, "global_step": 357245, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1026031970977783, "global_step": 357246, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.101466655731201, "global_step": 357247, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.160444736480713, "global_step": 357248, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1215057373046875, "global_step": 357249, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.140683174133301, "global_step": 357250, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2629644870758057, "global_step": 357251, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.070455551147461, "global_step": 357252, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.130502939224243, "global_step": 357253, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.097172260284424, "global_step": 357254, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0664961338043213, "global_step": 357255, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0654115676879883, "global_step": 357256, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1307671070098877, "global_step": 357257, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.171733856201172, "global_step": 357258, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1252708435058594, "global_step": 357259, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.073460817337036, "global_step": 357260, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.072603464126587, "global_step": 357261, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.125370979309082, "global_step": 357262, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0562024116516113, "global_step": 357263, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.125838279724121, "global_step": 357264, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0499613285064697, "global_step": 357265, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.235063076019287, "global_step": 357266, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.133983612060547, "global_step": 357267, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.120408058166504, "global_step": 357268, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0540921688079834, "global_step": 357269, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0421142578125, "global_step": 357270, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.115600109100342, "global_step": 357271, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.13935923576355, "global_step": 357272, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.184190034866333, "global_step": 357273, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.203705310821533, "global_step": 357274, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0592424869537354, "global_step": 357275, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.211010694503784, "global_step": 357276, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.051624298095703, "global_step": 357277, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0307326316833496, "global_step": 357278, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1948955059051514, "global_step": 357279, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.165053367614746, "global_step": 357280, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1226913928985596, "global_step": 357281, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1263699531555176, "global_step": 357282, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0482006072998047, "global_step": 357283, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.181224822998047, "global_step": 357284, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.044579029083252, "global_step": 357285, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0912041664123535, "global_step": 357286, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.117135524749756, "global_step": 357287, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1081631183624268, "global_step": 357288, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.14508318901062, "global_step": 357289, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1133341789245605, "global_step": 357290, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0213544368743896, "global_step": 357291, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.112650156021118, "global_step": 357292, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.084524154663086, "global_step": 357293, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.085001230239868, "global_step": 357294, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0912680625915527, "global_step": 357295, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.078674793243408, "global_step": 357296, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.166378974914551, "global_step": 357297, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0824835300445557, "global_step": 357298, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1264989376068115, "global_step": 357299, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.051513195037842, "global_step": 357300, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.007894277572632, "global_step": 357301, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0859193801879883, "global_step": 357302, "epoch": 718, "lr": 5e-05}
{"train_loss": 1.9704797267913818, "global_step": 357303, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.182183027267456, "global_step": 357304, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0305330753326416, "global_step": 357305, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0096702575683594, "global_step": 357306, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.141681671142578, "global_step": 357307, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1565968990325928, "global_step": 357308, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.132874011993408, "global_step": 357309, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0402770042419434, "global_step": 357310, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.062575101852417, "global_step": 357311, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1184210777282715, "global_step": 357312, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0644288063049316, "global_step": 357313, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0536787509918213, "global_step": 357314, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1115920543670654, "global_step": 357315, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.12288761138916, "global_step": 357316, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1957786083221436, "global_step": 357317, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.090580940246582, "global_step": 357318, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.076953649520874, "global_step": 357319, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.102811336517334, "global_step": 357320, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1809988021850586, "global_step": 357321, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.107546329498291, "global_step": 357322, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1083498001098633, "global_step": 357323, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1270861625671387, "global_step": 357324, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.052363157272339, "global_step": 357325, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.081638813018799, "global_step": 357326, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.055999755859375, "global_step": 357327, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.090233325958252, "global_step": 357328, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.037839889526367, "global_step": 357329, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0640273094177246, "global_step": 357330, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.139192819595337, "global_step": 357331, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1762821674346924, "global_step": 357332, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.077446222305298, "global_step": 357333, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1561686992645264, "global_step": 357334, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.032989263534546, "global_step": 357335, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0671730041503906, "global_step": 357336, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1185266971588135, "global_step": 357337, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0520246028900146, "global_step": 357338, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.149653434753418, "global_step": 357339, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2171738147735596, "global_step": 357340, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1334569454193115, "global_step": 357341, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1280272006988525, "global_step": 357342, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.066685914993286, "global_step": 357343, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1771514415740967, "global_step": 357344, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.144045114517212, "global_step": 357345, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.074673891067505, "global_step": 357346, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.118411064147949, "global_step": 357347, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.167916774749756, "global_step": 357348, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1276485919952393, "global_step": 357349, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1041252613067627, "global_step": 357350, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.077871561050415, "global_step": 357351, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.130755662918091, "global_step": 357352, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.138390064239502, "global_step": 357353, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1231625080108643, "global_step": 357354, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1450533866882324, "global_step": 357355, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.08729887008667, "global_step": 357356, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.053760051727295, "global_step": 357357, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0819075107574463, "global_step": 357358, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2058684825897217, "global_step": 357359, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2475295066833496, "global_step": 357360, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0855324268341064, "global_step": 357361, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1082096099853516, "global_step": 357362, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0869874954223633, "global_step": 357363, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.047994613647461, "global_step": 357364, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1343679428100586, "global_step": 357365, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0671417713165283, "global_step": 357366, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1382553577423096, "global_step": 357367, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0994622707366943, "global_step": 357368, "epoch": 718, "lr": 5e-05}
{"train_loss": 1.9539735317230225, "global_step": 357369, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1372101306915283, "global_step": 357370, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2247583866119385, "global_step": 357371, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0933709144592285, "global_step": 357372, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.077831268310547, "global_step": 357373, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1822259426116943, "global_step": 357374, "epoch": 718, "lr": 5e-05}
{"train_loss": 1.9783536195755005, "global_step": 357375, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.124671459197998, "global_step": 357376, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1055400371551514, "global_step": 357377, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.079148292541504, "global_step": 357378, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.104036331176758, "global_step": 357379, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0846595764160156, "global_step": 357380, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.088121175765991, "global_step": 357381, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1079013347625732, "global_step": 357382, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.073099136352539, "global_step": 357383, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.171208620071411, "global_step": 357384, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1554267406463623, "global_step": 357385, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.04885196685791, "global_step": 357386, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1211955547332764, "global_step": 357387, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1351735591888428, "global_step": 357388, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0431289672851562, "global_step": 357389, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0242207050323486, "global_step": 357390, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0976059436798096, "global_step": 357391, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0526084899902344, "global_step": 357392, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0242583751678467, "global_step": 357393, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.125777006149292, "global_step": 357394, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0958926677703857, "global_step": 357395, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.114718198776245, "global_step": 357396, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1972270011901855, "global_step": 357397, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1378214359283447, "global_step": 357398, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1094601154327393, "global_step": 357399, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.10145902633667, "global_step": 357400, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.117173433303833, "global_step": 357401, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.107806444168091, "global_step": 357402, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2391226291656494, "global_step": 357403, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0358705520629883, "global_step": 357404, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.073284864425659, "global_step": 357405, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1411538124084473, "global_step": 357406, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0357654094696045, "global_step": 357407, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0366716384887695, "global_step": 357408, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.212284564971924, "global_step": 357409, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.16422438621521, "global_step": 357410, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.155708074569702, "global_step": 357411, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0919992923736572, "global_step": 357412, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0955464839935303, "global_step": 357413, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1166951656341553, "global_step": 357414, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.063915729522705, "global_step": 357415, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0388681888580322, "global_step": 357416, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2028276920318604, "global_step": 357417, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.131593704223633, "global_step": 357418, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1370084285736084, "global_step": 357419, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1563565731048584, "global_step": 357420, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.094945192337036, "global_step": 357421, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.052475929260254, "global_step": 357422, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1280720233917236, "global_step": 357423, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0595169067382812, "global_step": 357424, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0206353664398193, "global_step": 357425, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.112537384033203, "global_step": 357426, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.139352321624756, "global_step": 357427, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1524746417999268, "global_step": 357428, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1099870204925537, "global_step": 357429, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0837650299072266, "global_step": 357430, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0502915382385254, "global_step": 357431, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0945723056793213, "global_step": 357432, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1014485359191895, "global_step": 357433, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.261186361312866, "global_step": 357434, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1509435176849365, "global_step": 357435, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.121386766433716, "global_step": 357436, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1193199157714844, "global_step": 357437, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0270841121673584, "global_step": 357438, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0678763389587402, "global_step": 357439, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.050384521484375, "global_step": 357440, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0928256511688232, "global_step": 357441, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.198340654373169, "global_step": 357442, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.231801986694336, "global_step": 357443, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1358320713043213, "global_step": 357444, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0297584533691406, "global_step": 357445, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1126785278320312, "global_step": 357446, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2028040885925293, "global_step": 357447, "epoch": 718, "lr": 5e-05}
{"train_loss": 1.999652624130249, "global_step": 357448, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.139082908630371, "global_step": 357449, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.125049591064453, "global_step": 357450, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1688570976257324, "global_step": 357451, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.045180082321167, "global_step": 357452, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1038522720336914, "global_step": 357453, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.056857109069824, "global_step": 357454, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0913918018341064, "global_step": 357455, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0078773498535156, "global_step": 357456, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0597610473632812, "global_step": 357457, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0679311752319336, "global_step": 357458, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.119704246520996, "global_step": 357459, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.142965793609619, "global_step": 357460, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1201977729797363, "global_step": 357461, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0326921939849854, "global_step": 357462, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1710143089294434, "global_step": 357463, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.174290895462036, "global_step": 357464, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.224501371383667, "global_step": 357465, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1078667640686035, "global_step": 357466, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0822670459747314, "global_step": 357467, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0935866832733154, "global_step": 357468, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1118581295013428, "global_step": 357469, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1096994876861572, "global_step": 357470, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0520083904266357, "global_step": 357471, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1299235820770264, "global_step": 357472, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2454190254211426, "global_step": 357473, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.106339931488037, "global_step": 357474, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.148909330368042, "global_step": 357475, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.078587293624878, "global_step": 357476, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0966286659240723, "global_step": 357477, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0845420360565186, "global_step": 357478, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.173308849334717, "global_step": 357479, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.133835792541504, "global_step": 357480, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0288877487182617, "global_step": 357481, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0895395278930664, "global_step": 357482, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.182013511657715, "global_step": 357483, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0753426551818848, "global_step": 357484, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1072680950164795, "global_step": 357485, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1706206798553467, "global_step": 357486, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.141486883163452, "global_step": 357487, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.09940242767334, "global_step": 357488, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.11011004447937, "global_step": 357489, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2395215034484863, "global_step": 357490, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.073263645172119, "global_step": 357491, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1313529014587402, "global_step": 357492, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1219370365142822, "global_step": 357493, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0948171615600586, "global_step": 357494, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0981438159942627, "global_step": 357495, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1184515953063965, "global_step": 357496, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.151294231414795, "global_step": 357497, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.093276023864746, "global_step": 357498, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0493216514587402, "global_step": 357499, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1161863803863525, "global_step": 357500, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0829217433929443, "global_step": 357501, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1101322174072266, "global_step": 357502, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1381585597991943, "global_step": 357503, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1181352138519287, "global_step": 357504, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.117354154586792, "global_step": 357505, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.172712564468384, "global_step": 357506, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0984535217285156, "global_step": 357507, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.166808843612671, "global_step": 357508, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.152107000350952, "global_step": 357509, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.051069736480713, "global_step": 357510, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.078796863555908, "global_step": 357511, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.129375696182251, "global_step": 357512, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.112429618835449, "global_step": 357513, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1271541118621826, "global_step": 357514, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1183743476867676, "global_step": 357515, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1216046810150146, "global_step": 357516, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0889272689819336, "global_step": 357517, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0985026359558105, "global_step": 357518, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1532158851623535, "global_step": 357519, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0683987140655518, "global_step": 357520, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.148228168487549, "global_step": 357521, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1594886779785156, "global_step": 357522, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0614514350891113, "global_step": 357523, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0702929496765137, "global_step": 357524, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1265242099761963, "global_step": 357525, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2210044860839844, "global_step": 357526, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1095077991485596, "global_step": 357527, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1106984615325928, "global_step": 357528, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.058807849884033, "global_step": 357529, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1212379932403564, "global_step": 357530, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0260822772979736, "global_step": 357531, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0971739292144775, "global_step": 357532, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.051194906234741, "global_step": 357533, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1161725521087646, "global_step": 357534, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.101820707321167, "global_step": 357535, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.139802932739258, "global_step": 357536, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.107233762741089, "global_step": 357537, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.151064157485962, "global_step": 357538, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1152994632720947, "global_step": 357539, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1782217025756836, "global_step": 357540, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.059380292892456, "global_step": 357541, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.018948554992676, "global_step": 357542, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.087096691131592, "global_step": 357543, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2224581241607666, "global_step": 357544, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.080629825592041, "global_step": 357545, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1089468002319336, "global_step": 357546, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1455960273742676, "global_step": 357547, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.174485206604004, "global_step": 357548, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.07487416267395, "global_step": 357549, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1025712490081787, "global_step": 357550, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1853907108306885, "global_step": 357551, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0724422931671143, "global_step": 357552, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.090834856033325, "global_step": 357553, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.114079236984253, "global_step": 357554, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.134535789489746, "global_step": 357555, "epoch": 718, "lr": 5e-05}
{"train_loss": 1.9996116161346436, "global_step": 357556, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1712234020233154, "global_step": 357557, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.149679660797119, "global_step": 357558, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.09972882270813, "global_step": 357559, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.175021171569824, "global_step": 357560, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.15574049949646, "global_step": 357561, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0901589393615723, "global_step": 357562, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0626680850982666, "global_step": 357563, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1728291511535645, "global_step": 357564, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0894687175750732, "global_step": 357565, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0886502265930176, "global_step": 357566, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1186559200286865, "global_step": 357567, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0716631412506104, "global_step": 357568, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.112356185913086, "global_step": 357569, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1420958042144775, "global_step": 357570, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.159095048904419, "global_step": 357571, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1264355182647705, "global_step": 357572, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1174135208129883, "global_step": 357573, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.074296236038208, "global_step": 357574, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0922675132751465, "global_step": 357575, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.078084707260132, "global_step": 357576, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1886110305786133, "global_step": 357577, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1330511569976807, "global_step": 357578, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.125120162963867, "global_step": 357579, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1459593772888184, "global_step": 357580, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.131129026412964, "global_step": 357581, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1980111598968506, "global_step": 357582, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1073131561279297, "global_step": 357583, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.121997594833374, "global_step": 357584, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.086451530456543, "global_step": 357585, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1994144916534424, "global_step": 357586, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1296002864837646, "global_step": 357587, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1343581676483154, "global_step": 357588, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.076997995376587, "global_step": 357589, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.056871175765991, "global_step": 357590, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.150891065597534, "global_step": 357591, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1036274433135986, "global_step": 357592, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.194207191467285, "global_step": 357593, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0712172985076904, "global_step": 357594, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1838526725769043, "global_step": 357595, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0614125728607178, "global_step": 357596, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0952038764953613, "global_step": 357597, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0788302421569824, "global_step": 357598, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2644460201263428, "global_step": 357599, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.054588556289673, "global_step": 357600, "epoch": 718, "lr": 5e-05}
{"train_loss": 1.9592742919921875, "global_step": 357601, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.055246353149414, "global_step": 357602, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.110046148300171, "global_step": 357603, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.034633159637451, "global_step": 357604, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0787291526794434, "global_step": 357605, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1699531078338623, "global_step": 357606, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1522278785705566, "global_step": 357607, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.103114604949951, "global_step": 357608, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.118379592895508, "global_step": 357609, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0042080879211426, "global_step": 357610, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0573177337646484, "global_step": 357611, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0773215293884277, "global_step": 357612, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.070181369781494, "global_step": 357613, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1766295433044434, "global_step": 357614, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.177837371826172, "global_step": 357615, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1962714195251465, "global_step": 357616, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1467533111572266, "global_step": 357617, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1833431720733643, "global_step": 357618, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0573394298553467, "global_step": 357619, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.107565402984619, "global_step": 357620, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1612672805786133, "global_step": 357621, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1061220169067383, "global_step": 357622, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.043900489807129, "global_step": 357623, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1490180492401123, "global_step": 357624, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0983235836029053, "global_step": 357625, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.123875856399536, "global_step": 357626, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0524308681488037, "global_step": 357627, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.093756914138794, "global_step": 357628, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.107269763946533, "global_step": 357629, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0776798725128174, "global_step": 357630, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.167006015777588, "global_step": 357631, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0965590476989746, "global_step": 357632, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.173795461654663, "global_step": 357633, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.073315382003784, "global_step": 357634, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1537864208221436, "global_step": 357635, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1277761459350586, "global_step": 357636, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.151137351989746, "global_step": 357637, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.123579502105713, "global_step": 357638, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.067593812942505, "global_step": 357639, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1325292587280273, "global_step": 357640, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0653109550476074, "global_step": 357641, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0957860946655273, "global_step": 357642, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.054358959197998, "global_step": 357643, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.098602294921875, "global_step": 357644, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.100142002105713, "global_step": 357645, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2014546394348145, "global_step": 357646, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.081949234008789, "global_step": 357647, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.132160186767578, "global_step": 357648, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0323829650878906, "global_step": 357649, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1606428623199463, "global_step": 357650, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.141082763671875, "global_step": 357651, "epoch": 718, "lr": 5e-05}
{"train_loss": 1.9889070987701416, "global_step": 357652, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1253788471221924, "global_step": 357653, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1524434089660645, "global_step": 357654, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.024482011795044, "global_step": 357655, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0949652194976807, "global_step": 357656, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1975655555725098, "global_step": 357657, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1335723400115967, "global_step": 357658, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1808767318725586, "global_step": 357659, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1109678745269775, "global_step": 357660, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.119216203689575, "global_step": 357661, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0021486282348633, "global_step": 357662, "epoch": 718, "lr": 5e-05}
{"train_loss": 1.994555950164795, "global_step": 357663, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1068103313446045, "global_step": 357664, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1061673164367676, "global_step": 357665, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0980870723724365, "global_step": 357666, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.148451089859009, "global_step": 357667, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.18564510345459, "global_step": 357668, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.143235921859741, "global_step": 357669, "epoch": 718, "lr": 5e-05}
{"train_loss": 1.98014497756958, "global_step": 357670, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0640265941619873, "global_step": 357671, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.160900592803955, "global_step": 357672, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1565744876861572, "global_step": 357673, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1585798263549805, "global_step": 357674, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0566601753234863, "global_step": 357675, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.093756914138794, "global_step": 357676, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.2059264183044434, "global_step": 357677, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.102597713470459, "global_step": 357678, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.112440586090088, "global_step": 357679, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1166117191314697, "global_step": 357680, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.126577615737915, "global_step": 357681, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1130053997039795, "global_step": 357682, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1437265872955322, "global_step": 357683, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0953922271728516, "global_step": 357684, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0664258003234863, "global_step": 357685, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.152158260345459, "global_step": 357686, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.118691921234131, "global_step": 357687, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.178762435913086, "global_step": 357688, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1111626625061035, "global_step": 357689, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.099597454071045, "global_step": 357690, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.11867094039917, "global_step": 357691, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.0861051082611084, "global_step": 357692, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1079699993133545, "global_step": 357693, "epoch": 718, "lr": 5e-05}
{"train_loss": 2.1402976512908936, "global_step": 357694, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0645363330841064, "global_step": 357695, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0706191062927246, "global_step": 357696, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.235595941543579, "global_step": 357697, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0346126556396484, "global_step": 357698, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.135683536529541, "global_step": 357699, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.082334518432617, "global_step": 357700, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0917277336120605, "global_step": 357701, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.105781078338623, "global_step": 357702, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.108200788497925, "global_step": 357703, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.007033109664917, "global_step": 357704, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1677026748657227, "global_step": 357705, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.029944658279419, "global_step": 357706, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0949318408966064, "global_step": 357707, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.023233652114868, "global_step": 357708, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.081594705581665, "global_step": 357709, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.060037136077881, "global_step": 357710, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1287660598754883, "global_step": 357711, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.084289312362671, "global_step": 357712, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0161666870117188, "global_step": 357713, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.11189341545105, "global_step": 357714, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0834097862243652, "global_step": 357715, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.05661940574646, "global_step": 357716, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0390357971191406, "global_step": 357717, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0718812942504883, "global_step": 357718, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0868635177612305, "global_step": 357719, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1166396141052246, "global_step": 357720, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.027862548828125, "global_step": 357721, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0732779502868652, "global_step": 357722, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0368642807006836, "global_step": 357723, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0816421508789062, "global_step": 357724, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.040310859680176, "global_step": 357725, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.123971939086914, "global_step": 357726, "epoch": 719, "lr": 5e-05}
{"train_loss": 1.9948045015335083, "global_step": 357727, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.134956121444702, "global_step": 357728, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.165332317352295, "global_step": 357729, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0255017280578613, "global_step": 357730, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1175918579101562, "global_step": 357731, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.002392053604126, "global_step": 357732, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0599024295806885, "global_step": 357733, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1117162704467773, "global_step": 357734, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0908803939819336, "global_step": 357735, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.112060070037842, "global_step": 357736, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1208410263061523, "global_step": 357737, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0401320457458496, "global_step": 357738, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.073279857635498, "global_step": 357739, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1703879833221436, "global_step": 357740, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.080610513687134, "global_step": 357741, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.099647283554077, "global_step": 357742, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.046948194503784, "global_step": 357743, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0554442405700684, "global_step": 357744, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1226541996002197, "global_step": 357745, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.13435435295105, "global_step": 357746, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1763243675231934, "global_step": 357747, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0810368061065674, "global_step": 357748, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0443496704101562, "global_step": 357749, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.106444835662842, "global_step": 357750, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1447184085845947, "global_step": 357751, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.101799249649048, "global_step": 357752, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1640946865081787, "global_step": 357753, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.16648530960083, "global_step": 357754, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1549909114837646, "global_step": 357755, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0841946601867676, "global_step": 357756, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1272242069244385, "global_step": 357757, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1201794147491455, "global_step": 357758, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.114650249481201, "global_step": 357759, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0318591594696045, "global_step": 357760, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0290815830230713, "global_step": 357761, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.098428249359131, "global_step": 357762, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1308062076568604, "global_step": 357763, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.113067150115967, "global_step": 357764, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1079068183898926, "global_step": 357765, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1526803970336914, "global_step": 357766, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1322572231292725, "global_step": 357767, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.090113878250122, "global_step": 357768, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1414783000946045, "global_step": 357769, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1021134853363037, "global_step": 357770, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1519737243652344, "global_step": 357771, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.2479567527770996, "global_step": 357772, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1184773445129395, "global_step": 357773, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.098377227783203, "global_step": 357774, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.115710496902466, "global_step": 357775, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.037517786026001, "global_step": 357776, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0298011302948, "global_step": 357777, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.085955858230591, "global_step": 357778, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1759631633758545, "global_step": 357779, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0903570652008057, "global_step": 357780, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.088778018951416, "global_step": 357781, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0845730304718018, "global_step": 357782, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0469024181365967, "global_step": 357783, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1362876892089844, "global_step": 357784, "epoch": 719, "lr": 5e-05}
{"train_loss": 1.9995747804641724, "global_step": 357785, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.038783550262451, "global_step": 357786, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0995216369628906, "global_step": 357787, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0997188091278076, "global_step": 357788, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.114067792892456, "global_step": 357789, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0746078491210938, "global_step": 357790, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1853699684143066, "global_step": 357791, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0803158283233643, "global_step": 357792, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1185007095336914, "global_step": 357793, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.111595392227173, "global_step": 357794, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.082374334335327, "global_step": 357795, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1397476196289062, "global_step": 357796, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.081084966659546, "global_step": 357797, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1084837913513184, "global_step": 357798, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.15832781791687, "global_step": 357799, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.113734245300293, "global_step": 357800, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0393426418304443, "global_step": 357801, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.06355619430542, "global_step": 357802, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.099825382232666, "global_step": 357803, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0524888038635254, "global_step": 357804, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0700769424438477, "global_step": 357805, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.016503095626831, "global_step": 357806, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0616581439971924, "global_step": 357807, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.086879253387451, "global_step": 357808, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.130938768386841, "global_step": 357809, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.063838005065918, "global_step": 357810, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1602933406829834, "global_step": 357811, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0694901943206787, "global_step": 357812, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1692044734954834, "global_step": 357813, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.128082036972046, "global_step": 357814, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0212314128875732, "global_step": 357815, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.054516315460205, "global_step": 357816, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1133391857147217, "global_step": 357817, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1451148986816406, "global_step": 357818, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.132858991622925, "global_step": 357819, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.062727212905884, "global_step": 357820, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0733580589294434, "global_step": 357821, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0331907272338867, "global_step": 357822, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.066211462020874, "global_step": 357823, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.018660306930542, "global_step": 357824, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1430864334106445, "global_step": 357825, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.100020170211792, "global_step": 357826, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0924198627471924, "global_step": 357827, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0859689712524414, "global_step": 357828, "epoch": 719, "lr": 5e-05}
{"train_loss": 1.9681679010391235, "global_step": 357829, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.102717161178589, "global_step": 357830, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.071733236312866, "global_step": 357831, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0300683975219727, "global_step": 357832, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.101396083831787, "global_step": 357833, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.113981008529663, "global_step": 357834, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0788793563842773, "global_step": 357835, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1038873195648193, "global_step": 357836, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.113140344619751, "global_step": 357837, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0610766410827637, "global_step": 357838, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.00077223777771, "global_step": 357839, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.077065944671631, "global_step": 357840, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.137631893157959, "global_step": 357841, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.113124370574951, "global_step": 357842, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.131831645965576, "global_step": 357843, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1340768337249756, "global_step": 357844, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.082925319671631, "global_step": 357845, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.052699089050293, "global_step": 357846, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.035360097885132, "global_step": 357847, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0534958839416504, "global_step": 357848, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.2072620391845703, "global_step": 357849, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.097883701324463, "global_step": 357850, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1245529651641846, "global_step": 357851, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1833972930908203, "global_step": 357852, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.097303867340088, "global_step": 357853, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1097311973571777, "global_step": 357854, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.179117202758789, "global_step": 357855, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.156599283218384, "global_step": 357856, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.158270835876465, "global_step": 357857, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1252241134643555, "global_step": 357858, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.115635871887207, "global_step": 357859, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.164097547531128, "global_step": 357860, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.122640371322632, "global_step": 357861, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0856523513793945, "global_step": 357862, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0652973651885986, "global_step": 357863, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.121229887008667, "global_step": 357864, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.054529905319214, "global_step": 357865, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1221723556518555, "global_step": 357866, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1390328407287598, "global_step": 357867, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1047451496124268, "global_step": 357868, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0126116275787354, "global_step": 357869, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.07466197013855, "global_step": 357870, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.136803150177002, "global_step": 357871, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0719242095947266, "global_step": 357872, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.009709358215332, "global_step": 357873, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.086944580078125, "global_step": 357874, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0132193565368652, "global_step": 357875, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0964977741241455, "global_step": 357876, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0860812664031982, "global_step": 357877, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1117513179779053, "global_step": 357878, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.163376808166504, "global_step": 357879, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.114441156387329, "global_step": 357880, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.061622142791748, "global_step": 357881, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1263153553009033, "global_step": 357882, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0657060146331787, "global_step": 357883, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.153374195098877, "global_step": 357884, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.13374924659729, "global_step": 357885, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.088080644607544, "global_step": 357886, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1070027351379395, "global_step": 357887, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.149268865585327, "global_step": 357888, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1396596431732178, "global_step": 357889, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.105492353439331, "global_step": 357890, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.135967254638672, "global_step": 357891, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0373027324676514, "global_step": 357892, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.153831720352173, "global_step": 357893, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.103982448577881, "global_step": 357894, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.094473123550415, "global_step": 357895, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0707950592041016, "global_step": 357896, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0856945514678955, "global_step": 357897, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1090805530548096, "global_step": 357898, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0680487155914307, "global_step": 357899, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.086101531982422, "global_step": 357900, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0900611877441406, "global_step": 357901, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.263840913772583, "global_step": 357902, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.192861795425415, "global_step": 357903, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1120407581329346, "global_step": 357904, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1475579738616943, "global_step": 357905, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.132716178894043, "global_step": 357906, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.076439619064331, "global_step": 357907, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.142401695251465, "global_step": 357908, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0685176849365234, "global_step": 357909, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.141873598098755, "global_step": 357910, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0534543991088867, "global_step": 357911, "epoch": 719, "lr": 5e-05}
{"train_loss": 1.997114896774292, "global_step": 357912, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1116344928741455, "global_step": 357913, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.065028190612793, "global_step": 357914, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.104487895965576, "global_step": 357915, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.115635871887207, "global_step": 357916, "epoch": 719, "lr": 5e-05}
{"train_loss": 1.98701810836792, "global_step": 357917, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.183772087097168, "global_step": 357918, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0829896926879883, "global_step": 357919, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.085251569747925, "global_step": 357920, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1278903484344482, "global_step": 357921, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1180171966552734, "global_step": 357922, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.098626136779785, "global_step": 357923, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1311047077178955, "global_step": 357924, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.145958423614502, "global_step": 357925, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.058584213256836, "global_step": 357926, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.082437515258789, "global_step": 357927, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.172097682952881, "global_step": 357928, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.136765718460083, "global_step": 357929, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.062033176422119, "global_step": 357930, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1174087524414062, "global_step": 357931, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1173009872436523, "global_step": 357932, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1037611961364746, "global_step": 357933, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1693050861358643, "global_step": 357934, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0949041843414307, "global_step": 357935, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.047969102859497, "global_step": 357936, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.096583127975464, "global_step": 357937, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0510730743408203, "global_step": 357938, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.079055070877075, "global_step": 357939, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1290225982666016, "global_step": 357940, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.143460273742676, "global_step": 357941, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.124566078186035, "global_step": 357942, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1231536865234375, "global_step": 357943, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0747671127319336, "global_step": 357944, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0391552448272705, "global_step": 357945, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1489527225494385, "global_step": 357946, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0721347332000732, "global_step": 357947, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1553382873535156, "global_step": 357948, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.088794708251953, "global_step": 357949, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1766083240509033, "global_step": 357950, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.056265354156494, "global_step": 357951, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.191843032836914, "global_step": 357952, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.158259630203247, "global_step": 357953, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0991032123565674, "global_step": 357954, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1131808757781982, "global_step": 357955, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0576393604278564, "global_step": 357956, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.081493616104126, "global_step": 357957, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0748555660247803, "global_step": 357958, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.15334153175354, "global_step": 357959, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0882086753845215, "global_step": 357960, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.183997392654419, "global_step": 357961, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0713982582092285, "global_step": 357962, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1095387935638428, "global_step": 357963, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1401357650756836, "global_step": 357964, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0732882022857666, "global_step": 357965, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.160186290740967, "global_step": 357966, "epoch": 719, "lr": 5e-05}
{"train_loss": 1.975585699081421, "global_step": 357967, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1343119144439697, "global_step": 357968, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.117593765258789, "global_step": 357969, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.2596657276153564, "global_step": 357970, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.081557273864746, "global_step": 357971, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.074413776397705, "global_step": 357972, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0850369930267334, "global_step": 357973, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.135256052017212, "global_step": 357974, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1088485717773438, "global_step": 357975, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0269968509674072, "global_step": 357976, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0466136932373047, "global_step": 357977, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.054866313934326, "global_step": 357978, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0077853202819824, "global_step": 357979, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.089630126953125, "global_step": 357980, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0761020183563232, "global_step": 357981, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0693490505218506, "global_step": 357982, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0989255905151367, "global_step": 357983, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.045516014099121, "global_step": 357984, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1526718139648438, "global_step": 357985, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1070029735565186, "global_step": 357986, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0599582195281982, "global_step": 357987, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1607415676116943, "global_step": 357988, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1987032890319824, "global_step": 357989, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.073855400085449, "global_step": 357990, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.120880603790283, "global_step": 357991, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.100616693496704, "global_step": 357992, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0608201026916504, "global_step": 357993, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.127798318862915, "global_step": 357994, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1023292541503906, "global_step": 357995, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0794107913970947, "global_step": 357996, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1577887535095215, "global_step": 357997, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.220135450363159, "global_step": 357998, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.167318344116211, "global_step": 357999, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1104226112365723, "global_step": 358000, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0484073162078857, "global_step": 358001, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.100924015045166, "global_step": 358002, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.075063705444336, "global_step": 358003, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1252546310424805, "global_step": 358004, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1345393657684326, "global_step": 358005, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.130510091781616, "global_step": 358006, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.130772829055786, "global_step": 358007, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1116843223571777, "global_step": 358008, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0738232135772705, "global_step": 358009, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.069939613342285, "global_step": 358010, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1105661392211914, "global_step": 358011, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.042476177215576, "global_step": 358012, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0725293159484863, "global_step": 358013, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1536519527435303, "global_step": 358014, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0682425498962402, "global_step": 358015, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1047890186309814, "global_step": 358016, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1594769954681396, "global_step": 358017, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.161176919937134, "global_step": 358018, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0696029663085938, "global_step": 358019, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1271049976348877, "global_step": 358020, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1112210750579834, "global_step": 358021, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.155108690261841, "global_step": 358022, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.093919038772583, "global_step": 358023, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.122620105743408, "global_step": 358024, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.057065486907959, "global_step": 358025, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0861287117004395, "global_step": 358026, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.159533739089966, "global_step": 358027, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0345382690429688, "global_step": 358028, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1639842987060547, "global_step": 358029, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.148437261581421, "global_step": 358030, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0713233947753906, "global_step": 358031, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.177375555038452, "global_step": 358032, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.06668758392334, "global_step": 358033, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0914578437805176, "global_step": 358034, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.128009557723999, "global_step": 358035, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0252649784088135, "global_step": 358036, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1373441219329834, "global_step": 358037, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1472513675689697, "global_step": 358038, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0832929611206055, "global_step": 358039, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0680782794952393, "global_step": 358040, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.124560832977295, "global_step": 358041, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1130576133728027, "global_step": 358042, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0848336219787598, "global_step": 358043, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0575854778289795, "global_step": 358044, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1219542026519775, "global_step": 358045, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0310561656951904, "global_step": 358046, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0932466983795166, "global_step": 358047, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1214871406555176, "global_step": 358048, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1357903480529785, "global_step": 358049, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0282373428344727, "global_step": 358050, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.15191388130188, "global_step": 358051, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.142448663711548, "global_step": 358052, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.103823184967041, "global_step": 358053, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.080486297607422, "global_step": 358054, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1338179111480713, "global_step": 358055, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.054990768432617, "global_step": 358056, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1384904384613037, "global_step": 358057, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.118678331375122, "global_step": 358058, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0622775554656982, "global_step": 358059, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.09066104888916, "global_step": 358060, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.062300205230713, "global_step": 358061, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.082775354385376, "global_step": 358062, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.099616289138794, "global_step": 358063, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.187159776687622, "global_step": 358064, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0621745586395264, "global_step": 358065, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0929667949676514, "global_step": 358066, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1379761695861816, "global_step": 358067, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.081545352935791, "global_step": 358068, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0261924266815186, "global_step": 358069, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1171281337738037, "global_step": 358070, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.058413505554199, "global_step": 358071, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.093458652496338, "global_step": 358072, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1515204906463623, "global_step": 358073, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.05311918258667, "global_step": 358074, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.059314489364624, "global_step": 358075, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1446118354797363, "global_step": 358076, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0603103637695312, "global_step": 358077, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1877617835998535, "global_step": 358078, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1844048500061035, "global_step": 358079, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1364755630493164, "global_step": 358080, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.066084623336792, "global_step": 358081, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.059983015060425, "global_step": 358082, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0454964637756348, "global_step": 358083, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.068455696105957, "global_step": 358084, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.119598627090454, "global_step": 358085, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1255664825439453, "global_step": 358086, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1206297874450684, "global_step": 358087, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0654900074005127, "global_step": 358088, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1192829608917236, "global_step": 358089, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1621506214141846, "global_step": 358090, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1638948917388916, "global_step": 358091, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1225574016571045, "global_step": 358092, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.110612392425537, "global_step": 358093, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.101698637008667, "global_step": 358094, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1788461208343506, "global_step": 358095, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1378135681152344, "global_step": 358096, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0828890800476074, "global_step": 358097, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.182328462600708, "global_step": 358098, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0610387325286865, "global_step": 358099, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.116586923599243, "global_step": 358100, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.086510419845581, "global_step": 358101, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.115684747695923, "global_step": 358102, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.056541919708252, "global_step": 358103, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0440659523010254, "global_step": 358104, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.068480968475342, "global_step": 358105, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.078817844390869, "global_step": 358106, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1009974479675293, "global_step": 358107, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.046647071838379, "global_step": 358108, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0961151123046875, "global_step": 358109, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0849218368530273, "global_step": 358110, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0624442100524902, "global_step": 358111, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1303038597106934, "global_step": 358112, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.009141206741333, "global_step": 358113, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1372463703155518, "global_step": 358114, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.165870189666748, "global_step": 358115, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1552813053131104, "global_step": 358116, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1219210624694824, "global_step": 358117, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1092660427093506, "global_step": 358118, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.13836407661438, "global_step": 358119, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1071667671203613, "global_step": 358120, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.2024247646331787, "global_step": 358121, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0664093494415283, "global_step": 358122, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.165923833847046, "global_step": 358123, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1369552612304688, "global_step": 358124, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0153510570526123, "global_step": 358125, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.152740478515625, "global_step": 358126, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.070101022720337, "global_step": 358127, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0752103328704834, "global_step": 358128, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.126004457473755, "global_step": 358129, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.093099355697632, "global_step": 358130, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.111711025238037, "global_step": 358131, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0850610733032227, "global_step": 358132, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.091567039489746, "global_step": 358133, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.2476322650909424, "global_step": 358134, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0402421951293945, "global_step": 358135, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.141184091567993, "global_step": 358136, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.064553737640381, "global_step": 358137, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1180036067962646, "global_step": 358138, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.2195842266082764, "global_step": 358139, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.037543535232544, "global_step": 358140, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.121025562286377, "global_step": 358141, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0612990856170654, "global_step": 358142, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.096693754196167, "global_step": 358143, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.027116537094116, "global_step": 358144, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0413339138031006, "global_step": 358145, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0506677627563477, "global_step": 358146, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0865328311920166, "global_step": 358147, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0885684490203857, "global_step": 358148, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.097198247909546, "global_step": 358149, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.136190414428711, "global_step": 358150, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.05440616607666, "global_step": 358151, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.088550090789795, "global_step": 358152, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1626360416412354, "global_step": 358153, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0971744060516357, "global_step": 358154, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0895025730133057, "global_step": 358155, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0766658782958984, "global_step": 358156, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.062788963317871, "global_step": 358157, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.181429147720337, "global_step": 358158, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1044981479644775, "global_step": 358159, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0402915477752686, "global_step": 358160, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.113281011581421, "global_step": 358161, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0722951889038086, "global_step": 358162, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.191143274307251, "global_step": 358163, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1331686973571777, "global_step": 358164, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1193559169769287, "global_step": 358165, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1603140830993652, "global_step": 358166, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.080972671508789, "global_step": 358167, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0994389057159424, "global_step": 358168, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.146134614944458, "global_step": 358169, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1517174243927, "global_step": 358170, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0834615230560303, "global_step": 358171, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1201744079589844, "global_step": 358172, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1934525966644287, "global_step": 358173, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.2086241245269775, "global_step": 358174, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.126354217529297, "global_step": 358175, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1698062419891357, "global_step": 358176, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1581943035125732, "global_step": 358177, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1593406200408936, "global_step": 358178, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.2023673057556152, "global_step": 358179, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0959205627441406, "global_step": 358180, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1014082431793213, "global_step": 358181, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0602712631225586, "global_step": 358182, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.124204397201538, "global_step": 358183, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1160173416137695, "global_step": 358184, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.085153818130493, "global_step": 358185, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1087450981140137, "global_step": 358186, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0641708374023438, "global_step": 358187, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0429861545562744, "global_step": 358188, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0594542026519775, "global_step": 358189, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1056153774261475, "global_step": 358190, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1404261589050293, "global_step": 358191, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1027801036834717, "global_step": 358192, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.095597505569458, "global_step": 358193, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.167609930038452, "global_step": 358194, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1103334426879883, "global_step": 358195, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1632771492004395, "global_step": 358196, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.073866844177246, "global_step": 358197, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0835797786712646, "global_step": 358198, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1207334995269775, "global_step": 358199, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0456583499908447, "global_step": 358200, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.2059719562530518, "global_step": 358201, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0693671703338623, "global_step": 358202, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0905144214630127, "global_step": 358203, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0895488262176514, "global_step": 358204, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.043301820755005, "global_step": 358205, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1531734466552734, "global_step": 358206, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0855495929718018, "global_step": 358207, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.11596417427063, "global_step": 358208, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1160976886749268, "global_step": 358209, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1914405822753906, "global_step": 358210, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.038317918777466, "global_step": 358211, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1433181762695312, "global_step": 358212, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.120378255844116, "global_step": 358213, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1561927795410156, "global_step": 358214, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.160440683364868, "global_step": 358215, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.085939645767212, "global_step": 358216, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.167421579360962, "global_step": 358217, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.140285015106201, "global_step": 358218, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.104462146759033, "global_step": 358219, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.037097454071045, "global_step": 358220, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.124831438064575, "global_step": 358221, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1609692573547363, "global_step": 358222, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0715994834899902, "global_step": 358223, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0532937049865723, "global_step": 358224, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1744394302368164, "global_step": 358225, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.084988594055176, "global_step": 358226, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.125206232070923, "global_step": 358227, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1102535724639893, "global_step": 358228, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1286919116973877, "global_step": 358229, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0958499908447266, "global_step": 358230, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0013983249664307, "global_step": 358231, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0216870307922363, "global_step": 358232, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0477652549743652, "global_step": 358233, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1201765537261963, "global_step": 358234, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0892739295959473, "global_step": 358235, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.062509059906006, "global_step": 358236, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1178770065307617, "global_step": 358237, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0584824085235596, "global_step": 358238, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.142622947692871, "global_step": 358239, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.114732027053833, "global_step": 358240, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0753984451293945, "global_step": 358241, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.162813425064087, "global_step": 358242, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1353533267974854, "global_step": 358243, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.083621025085449, "global_step": 358244, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0799496173858643, "global_step": 358245, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0119571685791016, "global_step": 358246, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1064629554748535, "global_step": 358247, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.067197561264038, "global_step": 358248, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1711108684539795, "global_step": 358249, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1001322269439697, "global_step": 358250, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.191443681716919, "global_step": 358251, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.089707612991333, "global_step": 358252, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1722300052642822, "global_step": 358253, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1933422088623047, "global_step": 358254, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.093289852142334, "global_step": 358255, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.08553409576416, "global_step": 358256, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1196296215057373, "global_step": 358257, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1505346298217773, "global_step": 358258, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1236982345581055, "global_step": 358259, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0922040939331055, "global_step": 358260, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1312522888183594, "global_step": 358261, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.084088087081909, "global_step": 358262, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.155658006668091, "global_step": 358263, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.111584186553955, "global_step": 358264, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.04638934135437, "global_step": 358265, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0833911895751953, "global_step": 358266, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.187854766845703, "global_step": 358267, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0975050926208496, "global_step": 358268, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0814764499664307, "global_step": 358269, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0968518257141113, "global_step": 358270, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.106304168701172, "global_step": 358271, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1103456020355225, "global_step": 358272, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1768040657043457, "global_step": 358273, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.080294609069824, "global_step": 358274, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1337690353393555, "global_step": 358275, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1305954456329346, "global_step": 358276, "epoch": 719, "lr": 5e-05}
{"train_loss": 1.9957554340362549, "global_step": 358277, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1586837768554688, "global_step": 358278, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.155221939086914, "global_step": 358279, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.024937629699707, "global_step": 358280, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.157902240753174, "global_step": 358281, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1388344764709473, "global_step": 358282, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0520756244659424, "global_step": 358283, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.028172254562378, "global_step": 358284, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.042959451675415, "global_step": 358285, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0973026752471924, "global_step": 358286, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.112483501434326, "global_step": 358287, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0555617809295654, "global_step": 358288, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1360459327697754, "global_step": 358289, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0831637382507324, "global_step": 358290, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.085322380065918, "global_step": 358291, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0300204753875732, "global_step": 358292, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.16166090965271, "global_step": 358293, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1234235763549805, "global_step": 358294, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.13592791557312, "global_step": 358295, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1819586753845215, "global_step": 358296, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.167970895767212, "global_step": 358297, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1698646545410156, "global_step": 358298, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1469979286193848, "global_step": 358299, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.116209030151367, "global_step": 358300, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1860780715942383, "global_step": 358301, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0930395126342773, "global_step": 358302, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.046020269393921, "global_step": 358303, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.191251277923584, "global_step": 358304, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1572675704956055, "global_step": 358305, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.132314682006836, "global_step": 358306, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1181769371032715, "global_step": 358307, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.145794630050659, "global_step": 358308, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1467695236206055, "global_step": 358309, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.076594591140747, "global_step": 358310, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.179873466491699, "global_step": 358311, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.153837203979492, "global_step": 358312, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1535346508026123, "global_step": 358313, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1190268993377686, "global_step": 358314, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1443445682525635, "global_step": 358315, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1173346042633057, "global_step": 358316, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.120711088180542, "global_step": 358317, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0838980674743652, "global_step": 358318, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1440484523773193, "global_step": 358319, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.109052896499634, "global_step": 358320, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.070762872695923, "global_step": 358321, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1173861026763916, "global_step": 358322, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.073744297027588, "global_step": 358323, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0754780769348145, "global_step": 358324, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1300573348999023, "global_step": 358325, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.099346160888672, "global_step": 358326, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.220269203186035, "global_step": 358327, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1698105335235596, "global_step": 358328, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0804786682128906, "global_step": 358329, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.073211193084717, "global_step": 358330, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.145678997039795, "global_step": 358331, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0648646354675293, "global_step": 358332, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1281588077545166, "global_step": 358333, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0743567943573, "global_step": 358334, "epoch": 719, "lr": 5e-05}
{"train_loss": 1.9861805438995361, "global_step": 358335, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1184396743774414, "global_step": 358336, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1998448371887207, "global_step": 358337, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.135026454925537, "global_step": 358338, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.237804651260376, "global_step": 358339, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1339757442474365, "global_step": 358340, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0711119174957275, "global_step": 358341, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0869855880737305, "global_step": 358342, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.184866189956665, "global_step": 358343, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.069411039352417, "global_step": 358344, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1947824954986572, "global_step": 358345, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.099370241165161, "global_step": 358346, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1197071075439453, "global_step": 358347, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1068456172943115, "global_step": 358348, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.128171443939209, "global_step": 358349, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1373581886291504, "global_step": 358350, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1454174518585205, "global_step": 358351, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0853848457336426, "global_step": 358352, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0996854305267334, "global_step": 358353, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.024427890777588, "global_step": 358354, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.095094919204712, "global_step": 358355, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1600828170776367, "global_step": 358356, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1111984252929688, "global_step": 358357, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1144564151763916, "global_step": 358358, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1416170597076416, "global_step": 358359, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.018289566040039, "global_step": 358360, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.106281280517578, "global_step": 358361, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1376311779022217, "global_step": 358362, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1067545413970947, "global_step": 358363, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0230512619018555, "global_step": 358364, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.198838233947754, "global_step": 358365, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.122436761856079, "global_step": 358366, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.109185218811035, "global_step": 358367, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0457186698913574, "global_step": 358368, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.148010015487671, "global_step": 358369, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.098954439163208, "global_step": 358370, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1918351650238037, "global_step": 358371, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1229031085968018, "global_step": 358372, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.021482467651367, "global_step": 358373, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.050450086593628, "global_step": 358374, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.016683340072632, "global_step": 358375, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1401326656341553, "global_step": 358376, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.18241548538208, "global_step": 358377, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1370317935943604, "global_step": 358378, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.092160701751709, "global_step": 358379, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.139709234237671, "global_step": 358380, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.142965793609619, "global_step": 358381, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.138347864151001, "global_step": 358382, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.069086790084839, "global_step": 358383, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1489710807800293, "global_step": 358384, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.094635009765625, "global_step": 358385, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.063971757888794, "global_step": 358386, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.095266580581665, "global_step": 358387, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1065402030944824, "global_step": 358388, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.130429983139038, "global_step": 358389, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.131344795227051, "global_step": 358390, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1242313385009766, "global_step": 358391, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1004223823547363, "global_step": 358392, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0954935550689697, "global_step": 358393, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0853049755096436, "global_step": 358394, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1108882427215576, "global_step": 358395, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.154733896255493, "global_step": 358396, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1996304988861084, "global_step": 358397, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.2218337059020996, "global_step": 358398, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.126655101776123, "global_step": 358399, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.139780044555664, "global_step": 358400, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1104772090911865, "global_step": 358401, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0743556022644043, "global_step": 358402, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1430165767669678, "global_step": 358403, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1993319988250732, "global_step": 358404, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.137735366821289, "global_step": 358405, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.02986741065979, "global_step": 358406, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.112058162689209, "global_step": 358407, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.130614757537842, "global_step": 358408, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.179837942123413, "global_step": 358409, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.093167781829834, "global_step": 358410, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0933992862701416, "global_step": 358411, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.223376512527466, "global_step": 358412, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.083662986755371, "global_step": 358413, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1004557609558105, "global_step": 358414, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0800046920776367, "global_step": 358415, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.086801290512085, "global_step": 358416, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1517345905303955, "global_step": 358417, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.146714687347412, "global_step": 358418, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1387572288513184, "global_step": 358419, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0409982204437256, "global_step": 358420, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1223809719085693, "global_step": 358421, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1734118461608887, "global_step": 358422, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.122079372406006, "global_step": 358423, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0474586486816406, "global_step": 358424, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0998332500457764, "global_step": 358425, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.075815439224243, "global_step": 358426, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1069107055664062, "global_step": 358427, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.104696273803711, "global_step": 358428, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.2017226219177246, "global_step": 358429, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0756521224975586, "global_step": 358430, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1546785831451416, "global_step": 358431, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.116330146789551, "global_step": 358432, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1987524032592773, "global_step": 358433, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1123580932617188, "global_step": 358434, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.161512613296509, "global_step": 358435, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.2090535163879395, "global_step": 358436, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0028557777404785, "global_step": 358437, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0271852016448975, "global_step": 358438, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1382594108581543, "global_step": 358439, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1563658714294434, "global_step": 358440, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1373865604400635, "global_step": 358441, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.125460624694824, "global_step": 358442, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.142681837081909, "global_step": 358443, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.2109556198120117, "global_step": 358444, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1276397705078125, "global_step": 358445, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.164893388748169, "global_step": 358446, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.091667652130127, "global_step": 358447, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0651049613952637, "global_step": 358448, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.141587495803833, "global_step": 358449, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1449224948883057, "global_step": 358450, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1528079509735107, "global_step": 358451, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0446996688842773, "global_step": 358452, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0498459339141846, "global_step": 358453, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.065141201019287, "global_step": 358454, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1605074405670166, "global_step": 358455, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.148937225341797, "global_step": 358456, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0057666301727295, "global_step": 358457, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.174635410308838, "global_step": 358458, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1678569316864014, "global_step": 358459, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1192734241485596, "global_step": 358460, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1236815452575684, "global_step": 358461, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1728076934814453, "global_step": 358462, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0807836055755615, "global_step": 358463, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.104660987854004, "global_step": 358464, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.076598882675171, "global_step": 358465, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.135948419570923, "global_step": 358466, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.030533790588379, "global_step": 358467, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.134040594100952, "global_step": 358468, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0941426753997803, "global_step": 358469, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0293474197387695, "global_step": 358470, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0407347679138184, "global_step": 358471, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0931949615478516, "global_step": 358472, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0717575550079346, "global_step": 358473, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.086155891418457, "global_step": 358474, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.144573450088501, "global_step": 358475, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0966951847076416, "global_step": 358476, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.096200704574585, "global_step": 358477, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1292455196380615, "global_step": 358478, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.01686954498291, "global_step": 358479, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.17671275138855, "global_step": 358480, "epoch": 719, "lr": 5e-05}
{"train_loss": 1.9991273880004883, "global_step": 358481, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0853443145751953, "global_step": 358482, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.041696548461914, "global_step": 358483, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.067941188812256, "global_step": 358484, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.025059938430786, "global_step": 358485, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.157989501953125, "global_step": 358486, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.012012243270874, "global_step": 358487, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1212966442108154, "global_step": 358488, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0681281089782715, "global_step": 358489, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0039613246917725, "global_step": 358490, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0951435565948486, "global_step": 358491, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1131386756896973, "global_step": 358492, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.2647461891174316, "global_step": 358493, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.094539165496826, "global_step": 358494, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1244590282440186, "global_step": 358495, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0685479640960693, "global_step": 358496, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1933434009552, "global_step": 358497, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.105421543121338, "global_step": 358498, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1080434322357178, "global_step": 358499, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.172743320465088, "global_step": 358500, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.101064920425415, "global_step": 358501, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1927013397216797, "global_step": 358502, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.164250612258911, "global_step": 358503, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0979111194610596, "global_step": 358504, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.036888360977173, "global_step": 358505, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0112273693084717, "global_step": 358506, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1652350425720215, "global_step": 358507, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.04607892036438, "global_step": 358508, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.131641387939453, "global_step": 358509, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.030238628387451, "global_step": 358510, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.189969062805176, "global_step": 358511, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1458323001861572, "global_step": 358512, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1324515342712402, "global_step": 358513, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.115187406539917, "global_step": 358514, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.141040563583374, "global_step": 358515, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.139920473098755, "global_step": 358516, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1156883239746094, "global_step": 358517, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1116631031036377, "global_step": 358518, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0766191482543945, "global_step": 358519, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.092149019241333, "global_step": 358520, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.211298704147339, "global_step": 358521, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.061246395111084, "global_step": 358522, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.060256004333496, "global_step": 358523, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0469913482666016, "global_step": 358524, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.2395620346069336, "global_step": 358525, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1144492626190186, "global_step": 358526, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.159583568572998, "global_step": 358527, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1483020782470703, "global_step": 358528, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0405900478363037, "global_step": 358529, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.172818899154663, "global_step": 358530, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.156337261199951, "global_step": 358531, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.097996950149536, "global_step": 358532, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1629414558410645, "global_step": 358533, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.165963649749756, "global_step": 358534, "epoch": 719, "lr": 5e-05}
{"train_loss": 1.9900386333465576, "global_step": 358535, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.079026222229004, "global_step": 358536, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1222522258758545, "global_step": 358537, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1366074085235596, "global_step": 358538, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1085777282714844, "global_step": 358539, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.106868028640747, "global_step": 358540, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0632362365722656, "global_step": 358541, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0978808403015137, "global_step": 358542, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.191763401031494, "global_step": 358543, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.176197052001953, "global_step": 358544, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1182851791381836, "global_step": 358545, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0956315994262695, "global_step": 358546, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.090601921081543, "global_step": 358547, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1516895294189453, "global_step": 358548, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0872244834899902, "global_step": 358549, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.138145923614502, "global_step": 358550, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1739299297332764, "global_step": 358551, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1236562728881836, "global_step": 358552, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0810706615448, "global_step": 358553, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1449177265167236, "global_step": 358554, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0991032123565674, "global_step": 358555, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0615978240966797, "global_step": 358556, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.092585563659668, "global_step": 358557, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1173832416534424, "global_step": 358558, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1376919746398926, "global_step": 358559, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.081228256225586, "global_step": 358560, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.104158639907837, "global_step": 358561, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.2143068313598633, "global_step": 358562, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1280250549316406, "global_step": 358563, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.135768413543701, "global_step": 358564, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0887386798858643, "global_step": 358565, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0928633213043213, "global_step": 358566, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1575005054473877, "global_step": 358567, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1292123794555664, "global_step": 358568, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0716614723205566, "global_step": 358569, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.151841402053833, "global_step": 358570, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1201682090759277, "global_step": 358571, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.16587233543396, "global_step": 358572, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1097052097320557, "global_step": 358573, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.122704267501831, "global_step": 358574, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1036670207977295, "global_step": 358575, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.070462465286255, "global_step": 358576, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1579394340515137, "global_step": 358577, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.175205945968628, "global_step": 358578, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.081195116043091, "global_step": 358579, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.147000312805176, "global_step": 358580, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1503615379333496, "global_step": 358581, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.120441198348999, "global_step": 358582, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1609349250793457, "global_step": 358583, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.148451089859009, "global_step": 358584, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.08699893951416, "global_step": 358585, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.139432907104492, "global_step": 358586, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.122636079788208, "global_step": 358587, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0950212478637695, "global_step": 358588, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1071555614471436, "global_step": 358589, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1386959552764893, "global_step": 358590, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1225857734680176, "global_step": 358591, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.124364137649536, "global_step": 358592, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.137946367263794, "global_step": 358593, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.092097043991089, "global_step": 358594, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.087641477584839, "global_step": 358595, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1709489822387695, "global_step": 358596, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0662872791290283, "global_step": 358597, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1334927082061768, "global_step": 358598, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.086495876312256, "global_step": 358599, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.041593551635742, "global_step": 358600, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1574981212615967, "global_step": 358601, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1174967288970947, "global_step": 358602, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.118631362915039, "global_step": 358603, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.084136486053467, "global_step": 358604, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1094982624053955, "global_step": 358605, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1093075275421143, "global_step": 358606, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0833687782287598, "global_step": 358607, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1217992305755615, "global_step": 358608, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.115725517272949, "global_step": 358609, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.024421215057373, "global_step": 358610, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1137583255767822, "global_step": 358611, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1138641834259033, "global_step": 358612, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.12469744682312, "global_step": 358613, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.12565541267395, "global_step": 358614, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1293067932128906, "global_step": 358615, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1289236545562744, "global_step": 358616, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1170315742492676, "global_step": 358617, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1299970149993896, "global_step": 358618, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1068341732025146, "global_step": 358619, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0250766277313232, "global_step": 358620, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0456385612487793, "global_step": 358621, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.210596799850464, "global_step": 358622, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1890146732330322, "global_step": 358623, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1294305324554443, "global_step": 358624, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1398322582244873, "global_step": 358625, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1147921085357666, "global_step": 358626, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.126255750656128, "global_step": 358627, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.209383249282837, "global_step": 358628, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0615479946136475, "global_step": 358629, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1079859733581543, "global_step": 358630, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.011075973510742, "global_step": 358631, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.036971092224121, "global_step": 358632, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.052894115447998, "global_step": 358633, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1494522094726562, "global_step": 358634, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.139693260192871, "global_step": 358635, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1956872940063477, "global_step": 358636, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1079838275909424, "global_step": 358637, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1577048301696777, "global_step": 358638, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.092499017715454, "global_step": 358639, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1296231746673584, "global_step": 358640, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.070281982421875, "global_step": 358641, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.262188196182251, "global_step": 358642, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.096142053604126, "global_step": 358643, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.099032402038574, "global_step": 358644, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.024564743041992, "global_step": 358645, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.078010320663452, "global_step": 358646, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1867151260375977, "global_step": 358647, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.041923761367798, "global_step": 358648, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.185059070587158, "global_step": 358649, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.150639533996582, "global_step": 358650, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1538193225860596, "global_step": 358651, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.079899787902832, "global_step": 358652, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.096357822418213, "global_step": 358653, "epoch": 719, "lr": 5e-05}
{"train_loss": 1.9976829290390015, "global_step": 358654, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.087188959121704, "global_step": 358655, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0483944416046143, "global_step": 358656, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1277172565460205, "global_step": 358657, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.2083170413970947, "global_step": 358658, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0995514392852783, "global_step": 358659, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.13332462310791, "global_step": 358660, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.180577039718628, "global_step": 358661, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.1077113151550293, "global_step": 358662, "epoch": 719, "lr": 5e-05}
{"train_loss": 2.0607094764709473, "global_step": 358663, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.08963942527771, "global_step": 358664, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.068861246109009, "global_step": 358665, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.156233072280884, "global_step": 358666, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.093764543533325, "global_step": 358667, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.130754232406616, "global_step": 358668, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0634701251983643, "global_step": 358669, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0853962898254395, "global_step": 358670, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.130429267883301, "global_step": 358671, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.150911331176758, "global_step": 358672, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0564019680023193, "global_step": 358673, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1040260791778564, "global_step": 358674, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.055232524871826, "global_step": 358675, "epoch": 720, "lr": 5e-05}
{"train_loss": 1.9888297319412231, "global_step": 358676, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1416029930114746, "global_step": 358677, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.077866315841675, "global_step": 358678, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0543148517608643, "global_step": 358679, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0205399990081787, "global_step": 358680, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0708508491516113, "global_step": 358681, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0941221714019775, "global_step": 358682, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0950002670288086, "global_step": 358683, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0816657543182373, "global_step": 358684, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1508519649505615, "global_step": 358685, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1566176414489746, "global_step": 358686, "epoch": 720, "lr": 5e-05}
{"train_loss": 1.9943307638168335, "global_step": 358687, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0693347454071045, "global_step": 358688, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0777673721313477, "global_step": 358689, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0903406143188477, "global_step": 358690, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0901710987091064, "global_step": 358691, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.016517400741577, "global_step": 358692, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.162672281265259, "global_step": 358693, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0608651638031006, "global_step": 358694, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0474414825439453, "global_step": 358695, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.076726198196411, "global_step": 358696, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0383551120758057, "global_step": 358697, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1265180110931396, "global_step": 358698, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0867867469787598, "global_step": 358699, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.054192304611206, "global_step": 358700, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1439907550811768, "global_step": 358701, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0977087020874023, "global_step": 358702, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.061713218688965, "global_step": 358703, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.065662384033203, "global_step": 358704, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1127519607543945, "global_step": 358705, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1021029949188232, "global_step": 358706, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.14633846282959, "global_step": 358707, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.092994213104248, "global_step": 358708, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.053576707839966, "global_step": 358709, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0964057445526123, "global_step": 358710, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1079964637756348, "global_step": 358711, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.030691623687744, "global_step": 358712, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0921077728271484, "global_step": 358713, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1147196292877197, "global_step": 358714, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2409541606903076, "global_step": 358715, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1988298892974854, "global_step": 358716, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.122600555419922, "global_step": 358717, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.120572566986084, "global_step": 358718, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.115931749343872, "global_step": 358719, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1104896068573, "global_step": 358720, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1311285495758057, "global_step": 358721, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.05737042427063, "global_step": 358722, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.116044521331787, "global_step": 358723, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1390812397003174, "global_step": 358724, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.12742018699646, "global_step": 358725, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0688254833221436, "global_step": 358726, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1625120639801025, "global_step": 358727, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.054076671600342, "global_step": 358728, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0764241218566895, "global_step": 358729, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.068317413330078, "global_step": 358730, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.033353328704834, "global_step": 358731, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0553717613220215, "global_step": 358732, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0826406478881836, "global_step": 358733, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.144545078277588, "global_step": 358734, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1708791255950928, "global_step": 358735, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1359481811523438, "global_step": 358736, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.043330430984497, "global_step": 358737, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0985171794891357, "global_step": 358738, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.11358642578125, "global_step": 358739, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.038961172103882, "global_step": 358740, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0755414962768555, "global_step": 358741, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.080129861831665, "global_step": 358742, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0672078132629395, "global_step": 358743, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1077702045440674, "global_step": 358744, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.17337703704834, "global_step": 358745, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1239047050476074, "global_step": 358746, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0984373092651367, "global_step": 358747, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1146256923675537, "global_step": 358748, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.126485824584961, "global_step": 358749, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0989482402801514, "global_step": 358750, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.127417802810669, "global_step": 358751, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.096247673034668, "global_step": 358752, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1423914432525635, "global_step": 358753, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0088400840759277, "global_step": 358754, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1877596378326416, "global_step": 358755, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.079890251159668, "global_step": 358756, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0755884647369385, "global_step": 358757, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0872578620910645, "global_step": 358758, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.119638681411743, "global_step": 358759, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.140164852142334, "global_step": 358760, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.202770233154297, "global_step": 358761, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0319907665252686, "global_step": 358762, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.11346173286438, "global_step": 358763, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1017701625823975, "global_step": 358764, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1119349002838135, "global_step": 358765, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.111762285232544, "global_step": 358766, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.078113317489624, "global_step": 358767, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0274674892425537, "global_step": 358768, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0747063159942627, "global_step": 358769, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.060267925262451, "global_step": 358770, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0100796222686768, "global_step": 358771, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1071360111236572, "global_step": 358772, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.065495729446411, "global_step": 358773, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.028903007507324, "global_step": 358774, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.10945987701416, "global_step": 358775, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1507766246795654, "global_step": 358776, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0885660648345947, "global_step": 358777, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1898739337921143, "global_step": 358778, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0681488513946533, "global_step": 358779, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0093441009521484, "global_step": 358780, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.077519416809082, "global_step": 358781, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1363325119018555, "global_step": 358782, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.111377716064453, "global_step": 358783, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.071582555770874, "global_step": 358784, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.109996795654297, "global_step": 358785, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0688157081604004, "global_step": 358786, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1816701889038086, "global_step": 358787, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.094804525375366, "global_step": 358788, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.131706476211548, "global_step": 358789, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.070974111557007, "global_step": 358790, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.081972599029541, "global_step": 358791, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.039790153503418, "global_step": 358792, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.084287405014038, "global_step": 358793, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2030107975006104, "global_step": 358794, "epoch": 720, "lr": 5e-05}
{"train_loss": 1.994443416595459, "global_step": 358795, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1278791427612305, "global_step": 358796, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0401060581207275, "global_step": 358797, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.153912305831909, "global_step": 358798, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.096754550933838, "global_step": 358799, "epoch": 720, "lr": 5e-05}
{"train_loss": 1.9641587734222412, "global_step": 358800, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.051464557647705, "global_step": 358801, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1754837036132812, "global_step": 358802, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.036987781524658, "global_step": 358803, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.156285047531128, "global_step": 358804, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1162710189819336, "global_step": 358805, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.150789976119995, "global_step": 358806, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0481295585632324, "global_step": 358807, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.080667018890381, "global_step": 358808, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.266390562057495, "global_step": 358809, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0564982891082764, "global_step": 358810, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0390684604644775, "global_step": 358811, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.139371871948242, "global_step": 358812, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.122706413269043, "global_step": 358813, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1777873039245605, "global_step": 358814, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.031320810317993, "global_step": 358815, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1446378231048584, "global_step": 358816, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0189261436462402, "global_step": 358817, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0600357055664062, "global_step": 358818, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.134960412979126, "global_step": 358819, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2202863693237305, "global_step": 358820, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.110468626022339, "global_step": 358821, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.076469898223877, "global_step": 358822, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.166527271270752, "global_step": 358823, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.037153482437134, "global_step": 358824, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0306689739227295, "global_step": 358825, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.236382007598877, "global_step": 358826, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1447267532348633, "global_step": 358827, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.154325246810913, "global_step": 358828, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0326054096221924, "global_step": 358829, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1430952548980713, "global_step": 358830, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.113346815109253, "global_step": 358831, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.153484582901001, "global_step": 358832, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0551815032958984, "global_step": 358833, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1471214294433594, "global_step": 358834, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.116903781890869, "global_step": 358835, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.098443031311035, "global_step": 358836, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.057168483734131, "global_step": 358837, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1154050827026367, "global_step": 358838, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0618438720703125, "global_step": 358839, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.125218391418457, "global_step": 358840, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.148970365524292, "global_step": 358841, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.022521734237671, "global_step": 358842, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0998895168304443, "global_step": 358843, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1306915283203125, "global_step": 358844, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.083040475845337, "global_step": 358845, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.183713674545288, "global_step": 358846, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.090297222137451, "global_step": 358847, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.117469310760498, "global_step": 358848, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.095411777496338, "global_step": 358849, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.167442560195923, "global_step": 358850, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0932838916778564, "global_step": 358851, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1176226139068604, "global_step": 358852, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0304293632507324, "global_step": 358853, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0657269954681396, "global_step": 358854, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.132720470428467, "global_step": 358855, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.126132011413574, "global_step": 358856, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1344003677368164, "global_step": 358857, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1453328132629395, "global_step": 358858, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.080789089202881, "global_step": 358859, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1291050910949707, "global_step": 358860, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.151949644088745, "global_step": 358861, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1223835945129395, "global_step": 358862, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.142540216445923, "global_step": 358863, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.190610408782959, "global_step": 358864, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1765079498291016, "global_step": 358865, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0821573734283447, "global_step": 358866, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0631444454193115, "global_step": 358867, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0761213302612305, "global_step": 358868, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1615841388702393, "global_step": 358869, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.013136863708496, "global_step": 358870, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.119666814804077, "global_step": 358871, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.078610897064209, "global_step": 358872, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1097652912139893, "global_step": 358873, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.070059299468994, "global_step": 358874, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.072490930557251, "global_step": 358875, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.079796552658081, "global_step": 358876, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1114888191223145, "global_step": 358877, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.094508647918701, "global_step": 358878, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.080268621444702, "global_step": 358879, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1737449169158936, "global_step": 358880, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1411983966827393, "global_step": 358881, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.077531337738037, "global_step": 358882, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0894370079040527, "global_step": 358883, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1857831478118896, "global_step": 358884, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.154066801071167, "global_step": 358885, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.140732765197754, "global_step": 358886, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1302990913391113, "global_step": 358887, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.14306902885437, "global_step": 358888, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.065016984939575, "global_step": 358889, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0468790531158447, "global_step": 358890, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.184312582015991, "global_step": 358891, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.091596841812134, "global_step": 358892, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.208735704421997, "global_step": 358893, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.059868574142456, "global_step": 358894, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1352767944335938, "global_step": 358895, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0346243381500244, "global_step": 358896, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1279780864715576, "global_step": 358897, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.106384754180908, "global_step": 358898, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.087420701980591, "global_step": 358899, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.073395252227783, "global_step": 358900, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1389427185058594, "global_step": 358901, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.088139057159424, "global_step": 358902, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.103513240814209, "global_step": 358903, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0969133377075195, "global_step": 358904, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1258840560913086, "global_step": 358905, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0730443000793457, "global_step": 358906, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1580190658569336, "global_step": 358907, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.081315755844116, "global_step": 358908, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0919551849365234, "global_step": 358909, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.123650550842285, "global_step": 358910, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.048619508743286, "global_step": 358911, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1055960655212402, "global_step": 358912, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.168354034423828, "global_step": 358913, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.172201156616211, "global_step": 358914, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.056924343109131, "global_step": 358915, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0765531063079834, "global_step": 358916, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.081519365310669, "global_step": 358917, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.11478853225708, "global_step": 358918, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0790255069732666, "global_step": 358919, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0619356632232666, "global_step": 358920, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.060131549835205, "global_step": 358921, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.110062599182129, "global_step": 358922, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.109097480773926, "global_step": 358923, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0266213417053223, "global_step": 358924, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0459468364715576, "global_step": 358925, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1136958599090576, "global_step": 358926, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1120779514312744, "global_step": 358927, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.12241792678833, "global_step": 358928, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.020118236541748, "global_step": 358929, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.038393020629883, "global_step": 358930, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.079476833343506, "global_step": 358931, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1429684162139893, "global_step": 358932, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.111949920654297, "global_step": 358933, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.135495185852051, "global_step": 358934, "epoch": 720, "lr": 5e-05}
{"train_loss": 1.9809293746948242, "global_step": 358935, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.10275936126709, "global_step": 358936, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.156196355819702, "global_step": 358937, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1220736503601074, "global_step": 358938, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1122095584869385, "global_step": 358939, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1073825359344482, "global_step": 358940, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.133941888809204, "global_step": 358941, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1328656673431396, "global_step": 358942, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1253466606140137, "global_step": 358943, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.120774745941162, "global_step": 358944, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1185498237609863, "global_step": 358945, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0955424308776855, "global_step": 358946, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0784125328063965, "global_step": 358947, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.056442975997925, "global_step": 358948, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1049416065216064, "global_step": 358949, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.193312883377075, "global_step": 358950, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0640273094177246, "global_step": 358951, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0630226135253906, "global_step": 358952, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0528130531311035, "global_step": 358953, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.212480068206787, "global_step": 358954, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1315853595733643, "global_step": 358955, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.145643472671509, "global_step": 358956, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.095407247543335, "global_step": 358957, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1129274368286133, "global_step": 358958, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0332930088043213, "global_step": 358959, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1433041095733643, "global_step": 358960, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0679473876953125, "global_step": 358961, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.097813606262207, "global_step": 358962, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.172497034072876, "global_step": 358963, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0772125720977783, "global_step": 358964, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.136052131652832, "global_step": 358965, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1478145122528076, "global_step": 358966, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.161649703979492, "global_step": 358967, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.176340341567993, "global_step": 358968, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.107698678970337, "global_step": 358969, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1375715732574463, "global_step": 358970, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.14560604095459, "global_step": 358971, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.147334337234497, "global_step": 358972, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.132657289505005, "global_step": 358973, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0741465091705322, "global_step": 358974, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.157944679260254, "global_step": 358975, "epoch": 720, "lr": 5e-05}
{"train_loss": 1.9777003526687622, "global_step": 358976, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1048367023468018, "global_step": 358977, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.04056715965271, "global_step": 358978, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0706522464752197, "global_step": 358979, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0101537704467773, "global_step": 358980, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0879392623901367, "global_step": 358981, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.18430233001709, "global_step": 358982, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.088252305984497, "global_step": 358983, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0643134117126465, "global_step": 358984, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1744816303253174, "global_step": 358985, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0473318099975586, "global_step": 358986, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1042191982269287, "global_step": 358987, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1142210960388184, "global_step": 358988, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1091325283050537, "global_step": 358989, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1457228660583496, "global_step": 358990, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.053421974182129, "global_step": 358991, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.050839900970459, "global_step": 358992, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0690970420837402, "global_step": 358993, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.098088026046753, "global_step": 358994, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1425395011901855, "global_step": 358995, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.097327947616577, "global_step": 358996, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1004433631896973, "global_step": 358997, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0752878189086914, "global_step": 358998, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0657079219818115, "global_step": 358999, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.125617027282715, "global_step": 359000, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1457560062408447, "global_step": 359001, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0667974948883057, "global_step": 359002, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0585787296295166, "global_step": 359003, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.182480573654175, "global_step": 359004, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1108384132385254, "global_step": 359005, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.136490821838379, "global_step": 359006, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.144465446472168, "global_step": 359007, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0719704627990723, "global_step": 359008, "epoch": 720, "lr": 5e-05}
{"train_loss": 1.9762855768203735, "global_step": 359009, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0278406143188477, "global_step": 359010, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.029334545135498, "global_step": 359011, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.015674591064453, "global_step": 359012, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0565571784973145, "global_step": 359013, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1300599575042725, "global_step": 359014, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1089890003204346, "global_step": 359015, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.260317802429199, "global_step": 359016, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1292052268981934, "global_step": 359017, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1209840774536133, "global_step": 359018, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0999860763549805, "global_step": 359019, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1204559803009033, "global_step": 359020, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.100247859954834, "global_step": 359021, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.117461681365967, "global_step": 359022, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.095670461654663, "global_step": 359023, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.047844171524048, "global_step": 359024, "epoch": 720, "lr": 5e-05}
{"train_loss": 1.9893124103546143, "global_step": 359025, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1228888034820557, "global_step": 359026, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1323766708374023, "global_step": 359027, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.088918924331665, "global_step": 359028, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.103222370147705, "global_step": 359029, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0558061599731445, "global_step": 359030, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0379974842071533, "global_step": 359031, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1015703678131104, "global_step": 359032, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.003559112548828, "global_step": 359033, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1436097621917725, "global_step": 359034, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.070962905883789, "global_step": 359035, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.080744981765747, "global_step": 359036, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.070573329925537, "global_step": 359037, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0160439014434814, "global_step": 359038, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.127073287963867, "global_step": 359039, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1410715579986572, "global_step": 359040, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.149272918701172, "global_step": 359041, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.184271812438965, "global_step": 359042, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0889883041381836, "global_step": 359043, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1185736656188965, "global_step": 359044, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1350739002227783, "global_step": 359045, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1163442134857178, "global_step": 359046, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.157702684402466, "global_step": 359047, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1257901191711426, "global_step": 359048, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.184349298477173, "global_step": 359049, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1095635890960693, "global_step": 359050, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.161156415939331, "global_step": 359051, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.130727767944336, "global_step": 359052, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.07564115524292, "global_step": 359053, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2122573852539062, "global_step": 359054, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1296639442443848, "global_step": 359055, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.037034273147583, "global_step": 359056, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.100637912750244, "global_step": 359057, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.153369665145874, "global_step": 359058, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1023049354553223, "global_step": 359059, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1471948623657227, "global_step": 359060, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1780145168304443, "global_step": 359061, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1119630336761475, "global_step": 359062, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.166759729385376, "global_step": 359063, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.037992238998413, "global_step": 359064, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1163713932037354, "global_step": 359065, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0434422492980957, "global_step": 359066, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1679019927978516, "global_step": 359067, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.123192310333252, "global_step": 359068, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.062016010284424, "global_step": 359069, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1114420890808105, "global_step": 359070, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.190117835998535, "global_step": 359071, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1033501625061035, "global_step": 359072, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.060269355773926, "global_step": 359073, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0836572647094727, "global_step": 359074, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2101211547851562, "global_step": 359075, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.081634998321533, "global_step": 359076, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1811912059783936, "global_step": 359077, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.084660530090332, "global_step": 359078, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.137979030609131, "global_step": 359079, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.086293935775757, "global_step": 359080, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1399896144866943, "global_step": 359081, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.219715118408203, "global_step": 359082, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.203761100769043, "global_step": 359083, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.058323621749878, "global_step": 359084, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.129636526107788, "global_step": 359085, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0819690227508545, "global_step": 359086, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.124734878540039, "global_step": 359087, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0588841438293457, "global_step": 359088, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.111438512802124, "global_step": 359089, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0089399814605713, "global_step": 359090, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1141510009765625, "global_step": 359091, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0241506099700928, "global_step": 359092, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1644928455352783, "global_step": 359093, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0254557132720947, "global_step": 359094, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1641037464141846, "global_step": 359095, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1310317516326904, "global_step": 359096, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0913946628570557, "global_step": 359097, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1524085998535156, "global_step": 359098, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.167022943496704, "global_step": 359099, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.116711139678955, "global_step": 359100, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1436917781829834, "global_step": 359101, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0199790000915527, "global_step": 359102, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2172744274139404, "global_step": 359103, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1158769130706787, "global_step": 359104, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1852433681488037, "global_step": 359105, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.083115577697754, "global_step": 359106, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1432065963745117, "global_step": 359107, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.20146107673645, "global_step": 359108, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1558327674865723, "global_step": 359109, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.170391082763672, "global_step": 359110, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.094879150390625, "global_step": 359111, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0455455780029297, "global_step": 359112, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1060428619384766, "global_step": 359113, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1308634281158447, "global_step": 359114, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1066532135009766, "global_step": 359115, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.145555257797241, "global_step": 359116, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1173572540283203, "global_step": 359117, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.162079334259033, "global_step": 359118, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.089630603790283, "global_step": 359119, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0867273807525635, "global_step": 359120, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.114551067352295, "global_step": 359121, "epoch": 720, "lr": 5e-05}
{"train_loss": 1.9918493032455444, "global_step": 359122, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0195839405059814, "global_step": 359123, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.120969533920288, "global_step": 359124, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.123748540878296, "global_step": 359125, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.142888307571411, "global_step": 359126, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.091190814971924, "global_step": 359127, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0537476539611816, "global_step": 359128, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.06388258934021, "global_step": 359129, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.088252544403076, "global_step": 359130, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1353721618652344, "global_step": 359131, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.132772922515869, "global_step": 359132, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1374855041503906, "global_step": 359133, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0526678562164307, "global_step": 359134, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1507091522216797, "global_step": 359135, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.122502565383911, "global_step": 359136, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.139165163040161, "global_step": 359137, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0656626224517822, "global_step": 359138, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1633639335632324, "global_step": 359139, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.183084487915039, "global_step": 359140, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1568539142608643, "global_step": 359141, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.045701026916504, "global_step": 359142, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.112781524658203, "global_step": 359143, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.076256275177002, "global_step": 359144, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1569669246673584, "global_step": 359145, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0737476348876953, "global_step": 359146, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0786757469177246, "global_step": 359147, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0815911293029785, "global_step": 359148, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.06080961227417, "global_step": 359149, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.097715139389038, "global_step": 359150, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0926713943481445, "global_step": 359151, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0506997108459473, "global_step": 359152, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.141653299331665, "global_step": 359153, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1168510913848877, "global_step": 359154, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1205556392669678, "global_step": 359155, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.033573627471924, "global_step": 359156, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1076202392578125, "global_step": 359157, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0983755588531494, "global_step": 359158, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1138906478881836, "global_step": 359159, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.130518674850464, "global_step": 359160, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.121617317199707, "global_step": 359161, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.112515687942505, "global_step": 359162, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1314194202423096, "global_step": 359163, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0563111305236816, "global_step": 359164, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1700053215026855, "global_step": 359165, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.107783555984497, "global_step": 359166, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2117342948913574, "global_step": 359167, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1253883838653564, "global_step": 359168, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.166196346282959, "global_step": 359169, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.120774507522583, "global_step": 359170, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1601850986480713, "global_step": 359171, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.069070816040039, "global_step": 359172, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.125216484069824, "global_step": 359173, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.088611602783203, "global_step": 359174, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0655031204223633, "global_step": 359175, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0544776916503906, "global_step": 359176, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0920186042785645, "global_step": 359177, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1865947246551514, "global_step": 359178, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.057391881942749, "global_step": 359179, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0621745586395264, "global_step": 359180, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0928125381469727, "global_step": 359181, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1563453674316406, "global_step": 359182, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.091735363006592, "global_step": 359183, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0644381046295166, "global_step": 359184, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1310067176818848, "global_step": 359185, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1444122791290283, "global_step": 359186, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1555957794189453, "global_step": 359187, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0715906620025635, "global_step": 359188, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.168726921081543, "global_step": 359189, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.107508897781372, "global_step": 359190, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.109022617340088, "global_step": 359191, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2006516456604004, "global_step": 359192, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1521384716033936, "global_step": 359193, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1494884490966797, "global_step": 359194, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2302193641662598, "global_step": 359195, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1037206649780273, "global_step": 359196, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0881354808807373, "global_step": 359197, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0540945529937744, "global_step": 359198, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.139425277709961, "global_step": 359199, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.179136276245117, "global_step": 359200, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0952420234680176, "global_step": 359201, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.166325092315674, "global_step": 359202, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1370368003845215, "global_step": 359203, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.113600015640259, "global_step": 359204, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.098083734512329, "global_step": 359205, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1855266094207764, "global_step": 359206, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0469603538513184, "global_step": 359207, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.045478582382202, "global_step": 359208, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.087329626083374, "global_step": 359209, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.179743766784668, "global_step": 359210, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0526506900787354, "global_step": 359211, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.289998769760132, "global_step": 359212, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.112483501434326, "global_step": 359213, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1054482460021973, "global_step": 359214, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0691964626312256, "global_step": 359215, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.127798080444336, "global_step": 359216, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1088531017303467, "global_step": 359217, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0988497734069824, "global_step": 359218, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.104346990585327, "global_step": 359219, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.14951229095459, "global_step": 359220, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2122373580932617, "global_step": 359221, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0474255084991455, "global_step": 359222, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1106133460998535, "global_step": 359223, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.147256851196289, "global_step": 359224, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.143028736114502, "global_step": 359225, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.066533088684082, "global_step": 359226, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0920135974884033, "global_step": 359227, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.179028034210205, "global_step": 359228, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1872668266296387, "global_step": 359229, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0921263694763184, "global_step": 359230, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1343772411346436, "global_step": 359231, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.072387456893921, "global_step": 359232, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.015651226043701, "global_step": 359233, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.110586404800415, "global_step": 359234, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.250850200653076, "global_step": 359235, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1006295680999756, "global_step": 359236, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0968332290649414, "global_step": 359237, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1154606342315674, "global_step": 359238, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0239815711975098, "global_step": 359239, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1735641956329346, "global_step": 359240, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0306427478790283, "global_step": 359241, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.091167688369751, "global_step": 359242, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1298930644989014, "global_step": 359243, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1796181201934814, "global_step": 359244, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.129633903503418, "global_step": 359245, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0583832263946533, "global_step": 359246, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1137747764587402, "global_step": 359247, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0820465087890625, "global_step": 359248, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.116269111633301, "global_step": 359249, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.116523504257202, "global_step": 359250, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0681471824645996, "global_step": 359251, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1051604747772217, "global_step": 359252, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.080230236053467, "global_step": 359253, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.175596237182617, "global_step": 359254, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1021034717559814, "global_step": 359255, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0513060092926025, "global_step": 359256, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1114680767059326, "global_step": 359257, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.188467264175415, "global_step": 359258, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1135857105255127, "global_step": 359259, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.196467876434326, "global_step": 359260, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1557607650756836, "global_step": 359261, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0749893188476562, "global_step": 359262, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.067929983139038, "global_step": 359263, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.127329111099243, "global_step": 359264, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.232917308807373, "global_step": 359265, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0643508434295654, "global_step": 359266, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.161174774169922, "global_step": 359267, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.119861125946045, "global_step": 359268, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.122966766357422, "global_step": 359269, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0998456478118896, "global_step": 359270, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0958380699157715, "global_step": 359271, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0696985721588135, "global_step": 359272, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.065478563308716, "global_step": 359273, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0998682975769043, "global_step": 359274, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0982415676116943, "global_step": 359275, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.091063976287842, "global_step": 359276, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.213710308074951, "global_step": 359277, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.124210834503174, "global_step": 359278, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.131685733795166, "global_step": 359279, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.086786985397339, "global_step": 359280, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0330331325531006, "global_step": 359281, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2208805084228516, "global_step": 359282, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0993270874023438, "global_step": 359283, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.188894748687744, "global_step": 359284, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.077287197113037, "global_step": 359285, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1022207736968994, "global_step": 359286, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0591511726379395, "global_step": 359287, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.166689157485962, "global_step": 359288, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.139042377471924, "global_step": 359289, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1219327449798584, "global_step": 359290, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.178184747695923, "global_step": 359291, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1502797603607178, "global_step": 359292, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0354743003845215, "global_step": 359293, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0889201164245605, "global_step": 359294, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1309001445770264, "global_step": 359295, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.200568914413452, "global_step": 359296, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1652088165283203, "global_step": 359297, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.098088026046753, "global_step": 359298, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1578893661499023, "global_step": 359299, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.113658905029297, "global_step": 359300, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.211158514022827, "global_step": 359301, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0022361278533936, "global_step": 359302, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.100454568862915, "global_step": 359303, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.184401750564575, "global_step": 359304, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1610898971557617, "global_step": 359305, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1684365272521973, "global_step": 359306, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1764535903930664, "global_step": 359307, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.068904161453247, "global_step": 359308, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.123037099838257, "global_step": 359309, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0610101222991943, "global_step": 359310, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.094247341156006, "global_step": 359311, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2016775608062744, "global_step": 359312, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1262423992156982, "global_step": 359313, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1585731506347656, "global_step": 359314, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.029269218444824, "global_step": 359315, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.08992075920105, "global_step": 359316, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1332151889801025, "global_step": 359317, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.052753210067749, "global_step": 359318, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1109635829925537, "global_step": 359319, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.078619956970215, "global_step": 359320, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.095106363296509, "global_step": 359321, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.104771852493286, "global_step": 359322, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1426925659179688, "global_step": 359323, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1134390830993652, "global_step": 359324, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.131277322769165, "global_step": 359325, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.104008674621582, "global_step": 359326, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1160969734191895, "global_step": 359327, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.092637300491333, "global_step": 359328, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1554129123687744, "global_step": 359329, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.084516763687134, "global_step": 359330, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.11860990524292, "global_step": 359331, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0923473834991455, "global_step": 359332, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.137279987335205, "global_step": 359333, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.071450710296631, "global_step": 359334, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0275611877441406, "global_step": 359335, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1438441276550293, "global_step": 359336, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1285505294799805, "global_step": 359337, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.144106388092041, "global_step": 359338, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.072618007659912, "global_step": 359339, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1965041160583496, "global_step": 359340, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1539576053619385, "global_step": 359341, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.16698956489563, "global_step": 359342, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.208838701248169, "global_step": 359343, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0341989994049072, "global_step": 359344, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.096801519393921, "global_step": 359345, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1310458183288574, "global_step": 359346, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1147024631500244, "global_step": 359347, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1879634857177734, "global_step": 359348, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.057812213897705, "global_step": 359349, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.191753387451172, "global_step": 359350, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1496405601501465, "global_step": 359351, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.125838279724121, "global_step": 359352, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1743388175964355, "global_step": 359353, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.125920534133911, "global_step": 359354, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0478854179382324, "global_step": 359355, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1428117752075195, "global_step": 359356, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1198275089263916, "global_step": 359357, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0584089756011963, "global_step": 359358, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1789186000823975, "global_step": 359359, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.197885274887085, "global_step": 359360, "epoch": 720, "lr": 5e-05}
{"train_loss": 1.9999479055404663, "global_step": 359361, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0438547134399414, "global_step": 359362, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.170259475708008, "global_step": 359363, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.109699010848999, "global_step": 359364, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2295138835906982, "global_step": 359365, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.047759771347046, "global_step": 359366, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.079820156097412, "global_step": 359367, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1168925762176514, "global_step": 359368, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0460963249206543, "global_step": 359369, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0680909156799316, "global_step": 359370, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0932533740997314, "global_step": 359371, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.092315435409546, "global_step": 359372, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.122069835662842, "global_step": 359373, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1482365131378174, "global_step": 359374, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.031658411026001, "global_step": 359375, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.12371826171875, "global_step": 359376, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0880908966064453, "global_step": 359377, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.177541971206665, "global_step": 359378, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2096402645111084, "global_step": 359379, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0529446601867676, "global_step": 359380, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0965137481689453, "global_step": 359381, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1925723552703857, "global_step": 359382, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.073286533355713, "global_step": 359383, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.156639337539673, "global_step": 359384, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1087918281555176, "global_step": 359385, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1904287338256836, "global_step": 359386, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.122081756591797, "global_step": 359387, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.05055832862854, "global_step": 359388, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1304824352264404, "global_step": 359389, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.160677909851074, "global_step": 359390, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0933237075805664, "global_step": 359391, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1688849925994873, "global_step": 359392, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.118206739425659, "global_step": 359393, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1240463256835938, "global_step": 359394, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.093282461166382, "global_step": 359395, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1377246379852295, "global_step": 359396, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1692721843719482, "global_step": 359397, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1782078742980957, "global_step": 359398, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0888712406158447, "global_step": 359399, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.149759292602539, "global_step": 359400, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2008044719696045, "global_step": 359401, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0586068630218506, "global_step": 359402, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.151221513748169, "global_step": 359403, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.050076961517334, "global_step": 359404, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.201486587524414, "global_step": 359405, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1332449913024902, "global_step": 359406, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1591920852661133, "global_step": 359407, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.095937967300415, "global_step": 359408, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.112983465194702, "global_step": 359409, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0293853282928467, "global_step": 359410, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1669867038726807, "global_step": 359411, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1515283584594727, "global_step": 359412, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.112387180328369, "global_step": 359413, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1402153968811035, "global_step": 359414, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.112820863723755, "global_step": 359415, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.146885395050049, "global_step": 359416, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0888466835021973, "global_step": 359417, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.097292423248291, "global_step": 359418, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.180445432662964, "global_step": 359419, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1063663959503174, "global_step": 359420, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0627732276916504, "global_step": 359421, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1266391277313232, "global_step": 359422, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0540754795074463, "global_step": 359423, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.090486764907837, "global_step": 359424, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2152457237243652, "global_step": 359425, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.239475965499878, "global_step": 359426, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0486230850219727, "global_step": 359427, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.115271806716919, "global_step": 359428, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.16351580619812, "global_step": 359429, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0567080974578857, "global_step": 359430, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2028207778930664, "global_step": 359431, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.081864595413208, "global_step": 359432, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.053605318069458, "global_step": 359433, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1043457984924316, "global_step": 359434, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1294991970062256, "global_step": 359435, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1975150108337402, "global_step": 359436, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.139171838760376, "global_step": 359437, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.167316436767578, "global_step": 359438, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.187448263168335, "global_step": 359439, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.059575080871582, "global_step": 359440, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.230164051055908, "global_step": 359441, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1745359897613525, "global_step": 359442, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1504318714141846, "global_step": 359443, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0533559322357178, "global_step": 359444, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0762879848480225, "global_step": 359445, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.052511692047119, "global_step": 359446, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.074899196624756, "global_step": 359447, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0356106758117676, "global_step": 359448, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1033453941345215, "global_step": 359449, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.181652307510376, "global_step": 359450, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.105299472808838, "global_step": 359451, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1333510875701904, "global_step": 359452, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.168283462524414, "global_step": 359453, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.149501085281372, "global_step": 359454, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.150275230407715, "global_step": 359455, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.136833667755127, "global_step": 359456, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1257622241973877, "global_step": 359457, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1518025398254395, "global_step": 359458, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0351133346557617, "global_step": 359459, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.16892409324646, "global_step": 359460, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0988662242889404, "global_step": 359461, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.215581178665161, "global_step": 359462, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.142047643661499, "global_step": 359463, "epoch": 720, "lr": 5e-05}
{"train_loss": 1.9958049058914185, "global_step": 359464, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1323139667510986, "global_step": 359465, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.094696044921875, "global_step": 359466, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1792540550231934, "global_step": 359467, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1334335803985596, "global_step": 359468, "epoch": 720, "lr": 5e-05}
{"train_loss": 1.9981948137283325, "global_step": 359469, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1056599617004395, "global_step": 359470, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.091460704803467, "global_step": 359471, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.043792963027954, "global_step": 359472, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.053800582885742, "global_step": 359473, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.084493637084961, "global_step": 359474, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0980224609375, "global_step": 359475, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.117126226425171, "global_step": 359476, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1612207889556885, "global_step": 359477, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1821351051330566, "global_step": 359478, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.032236337661743, "global_step": 359479, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.125153064727783, "global_step": 359480, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1061172485351562, "global_step": 359481, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1900181770324707, "global_step": 359482, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.157134771347046, "global_step": 359483, "epoch": 720, "lr": 5e-05}
{"train_loss": 1.9747480154037476, "global_step": 359484, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.074385643005371, "global_step": 359485, "epoch": 720, "lr": 5e-05}
{"train_loss": 1.9840072393417358, "global_step": 359486, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0760459899902344, "global_step": 359487, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.158379077911377, "global_step": 359488, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.110863447189331, "global_step": 359489, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1020936965942383, "global_step": 359490, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1478209495544434, "global_step": 359491, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1152539253234863, "global_step": 359492, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.153165578842163, "global_step": 359493, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0806386470794678, "global_step": 359494, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0973949432373047, "global_step": 359495, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1497597694396973, "global_step": 359496, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1318976879119873, "global_step": 359497, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1481521129608154, "global_step": 359498, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1676738262176514, "global_step": 359499, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0925228595733643, "global_step": 359500, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.100877046585083, "global_step": 359501, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1471972465515137, "global_step": 359502, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1367900371551514, "global_step": 359503, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.102849245071411, "global_step": 359504, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.130648136138916, "global_step": 359505, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1847732067108154, "global_step": 359506, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2575154304504395, "global_step": 359507, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1517138481140137, "global_step": 359508, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1493611335754395, "global_step": 359509, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1537227630615234, "global_step": 359510, "epoch": 720, "lr": 5e-05}
{"train_loss": 1.9608074426651, "global_step": 359511, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.100321054458618, "global_step": 359512, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.048938512802124, "global_step": 359513, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2040839195251465, "global_step": 359514, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.188572645187378, "global_step": 359515, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0499255657196045, "global_step": 359516, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0668647289276123, "global_step": 359517, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.077732563018799, "global_step": 359518, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.089442729949951, "global_step": 359519, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.141482353210449, "global_step": 359520, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1071372032165527, "global_step": 359521, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.160425901412964, "global_step": 359522, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0560264587402344, "global_step": 359523, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1170151233673096, "global_step": 359524, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.243286371231079, "global_step": 359525, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.220808267593384, "global_step": 359526, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0961687564849854, "global_step": 359527, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.08498215675354, "global_step": 359528, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.182968854904175, "global_step": 359529, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1934146881103516, "global_step": 359530, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1709957122802734, "global_step": 359531, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.151965618133545, "global_step": 359532, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.096318006515503, "global_step": 359533, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0707874298095703, "global_step": 359534, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1456449031829834, "global_step": 359535, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0235533714294434, "global_step": 359536, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0592219829559326, "global_step": 359537, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1019527912139893, "global_step": 359538, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.105330228805542, "global_step": 359539, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.148913621902466, "global_step": 359540, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.095900774002075, "global_step": 359541, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1840853691101074, "global_step": 359542, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.071136713027954, "global_step": 359543, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.106923818588257, "global_step": 359544, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1052892208099365, "global_step": 359545, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0524256229400635, "global_step": 359546, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.149141550064087, "global_step": 359547, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.212811231613159, "global_step": 359548, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0780558586120605, "global_step": 359549, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1435134410858154, "global_step": 359550, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0621163845062256, "global_step": 359551, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.066432476043701, "global_step": 359552, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.134613275527954, "global_step": 359553, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2162222862243652, "global_step": 359554, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.134840726852417, "global_step": 359555, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1244332790374756, "global_step": 359556, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.128061056137085, "global_step": 359557, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1549315452575684, "global_step": 359558, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.072866201400757, "global_step": 359559, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.128563642501831, "global_step": 359560, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0825884342193604, "global_step": 359561, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0970675945281982, "global_step": 359562, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.139346122741699, "global_step": 359563, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1076557636260986, "global_step": 359564, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1743574142456055, "global_step": 359565, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.131563901901245, "global_step": 359566, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1525096893310547, "global_step": 359567, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.131392002105713, "global_step": 359568, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0488035678863525, "global_step": 359569, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.168139696121216, "global_step": 359570, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.184969186782837, "global_step": 359571, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.095466136932373, "global_step": 359572, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.060502767562866, "global_step": 359573, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1257951259613037, "global_step": 359574, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1909871101379395, "global_step": 359575, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.088423013687134, "global_step": 359576, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1276562213897705, "global_step": 359577, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0692076683044434, "global_step": 359578, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.085815906524658, "global_step": 359579, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.147379159927368, "global_step": 359580, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1541121006011963, "global_step": 359581, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.104506492614746, "global_step": 359582, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.16540789604187, "global_step": 359583, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.124803066253662, "global_step": 359584, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.174443483352661, "global_step": 359585, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.102047920227051, "global_step": 359586, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.2052652835845947, "global_step": 359587, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.130383253097534, "global_step": 359588, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1166932582855225, "global_step": 359589, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.157437324523926, "global_step": 359590, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.041954278945923, "global_step": 359591, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.223262310028076, "global_step": 359592, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.084210157394409, "global_step": 359593, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1091055870056152, "global_step": 359594, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.050013780593872, "global_step": 359595, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1397149562835693, "global_step": 359596, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1209003925323486, "global_step": 359597, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.153048515319824, "global_step": 359598, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1372032165527344, "global_step": 359599, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1747682094573975, "global_step": 359600, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.143158197402954, "global_step": 359601, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0806963443756104, "global_step": 359602, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0870513916015625, "global_step": 359603, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.254271984100342, "global_step": 359604, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0798285007476807, "global_step": 359605, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1350128650665283, "global_step": 359606, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.127699851989746, "global_step": 359607, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.111936092376709, "global_step": 359608, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.120187997817993, "global_step": 359609, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1159234046936035, "global_step": 359610, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1120998859405518, "global_step": 359611, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.175126314163208, "global_step": 359612, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.145458459854126, "global_step": 359613, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.067612886428833, "global_step": 359614, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.105527639389038, "global_step": 359615, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0755574703216553, "global_step": 359616, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1738617420196533, "global_step": 359617, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1030211448669434, "global_step": 359618, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1195127964019775, "global_step": 359619, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.182450532913208, "global_step": 359620, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1508452892303467, "global_step": 359621, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1530942916870117, "global_step": 359622, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.042741298675537, "global_step": 359623, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1301283836364746, "global_step": 359624, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1343820095062256, "global_step": 359625, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.168320894241333, "global_step": 359626, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.183337450027466, "global_step": 359627, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0802438259124756, "global_step": 359628, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.043196678161621, "global_step": 359629, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.0521366596221924, "global_step": 359630, "epoch": 720, "lr": 5e-05}
{"train_loss": 2.1118013858795166, "global_step": 359631, "epoch": 720, "lr": 5e-05, "val_loss": 5.641933441162109, "test_reconst_mse": 0.07325439155101776}
{"train_loss": 2.0411524772644043, "global_step": 359632, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1512210369110107, "global_step": 359633, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0243637561798096, "global_step": 359634, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1098904609680176, "global_step": 359635, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.067462682723999, "global_step": 359636, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1483538150787354, "global_step": 359637, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1268229484558105, "global_step": 359638, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1690173149108887, "global_step": 359639, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1698198318481445, "global_step": 359640, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0505576133728027, "global_step": 359641, "epoch": 721, "lr": 5e-05}
{"train_loss": 1.9808675050735474, "global_step": 359642, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.2408523559570312, "global_step": 359643, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.063253164291382, "global_step": 359644, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.110398292541504, "global_step": 359645, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.069408655166626, "global_step": 359646, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1610870361328125, "global_step": 359647, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.096266031265259, "global_step": 359648, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.181077480316162, "global_step": 359649, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.061250686645508, "global_step": 359650, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1193268299102783, "global_step": 359651, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.2152864933013916, "global_step": 359652, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.167473316192627, "global_step": 359653, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1032536029815674, "global_step": 359654, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.085697889328003, "global_step": 359655, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0765833854675293, "global_step": 359656, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1286041736602783, "global_step": 359657, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1106350421905518, "global_step": 359658, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1166975498199463, "global_step": 359659, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0728368759155273, "global_step": 359660, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0999300479888916, "global_step": 359661, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1749560832977295, "global_step": 359662, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1984634399414062, "global_step": 359663, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.029935836791992, "global_step": 359664, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1296303272247314, "global_step": 359665, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1747243404388428, "global_step": 359666, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.054933786392212, "global_step": 359667, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1552627086639404, "global_step": 359668, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.063377857208252, "global_step": 359669, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0475831031799316, "global_step": 359670, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.074040651321411, "global_step": 359671, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.07746958732605, "global_step": 359672, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1163642406463623, "global_step": 359673, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.054049015045166, "global_step": 359674, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.108262062072754, "global_step": 359675, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0797996520996094, "global_step": 359676, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.18436861038208, "global_step": 359677, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0499753952026367, "global_step": 359678, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.141737699508667, "global_step": 359679, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0739285945892334, "global_step": 359680, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0067522525787354, "global_step": 359681, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1543080806732178, "global_step": 359682, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.089054822921753, "global_step": 359683, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0722954273223877, "global_step": 359684, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.09535551071167, "global_step": 359685, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.15921950340271, "global_step": 359686, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0567638874053955, "global_step": 359687, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0852062702178955, "global_step": 359688, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.125845193862915, "global_step": 359689, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.064241409301758, "global_step": 359690, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1609723567962646, "global_step": 359691, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1226794719696045, "global_step": 359692, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1536667346954346, "global_step": 359693, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.055541753768921, "global_step": 359694, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1945295333862305, "global_step": 359695, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0911777019500732, "global_step": 359696, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.2334558963775635, "global_step": 359697, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1523518562316895, "global_step": 359698, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.151700973510742, "global_step": 359699, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.109386920928955, "global_step": 359700, "epoch": 721, "lr": 5e-05}
{"train_loss": 1.9856228828430176, "global_step": 359701, "epoch": 721, "lr": 5e-05}
{"train_loss": 1.999911904335022, "global_step": 359702, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.136314630508423, "global_step": 359703, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0622775554656982, "global_step": 359704, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.128500461578369, "global_step": 359705, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.118680953979492, "global_step": 359706, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.167922019958496, "global_step": 359707, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0733728408813477, "global_step": 359708, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1039979457855225, "global_step": 359709, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.138498306274414, "global_step": 359710, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0609188079833984, "global_step": 359711, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.099076986312866, "global_step": 359712, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.112473726272583, "global_step": 359713, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0424580574035645, "global_step": 359714, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.082535982131958, "global_step": 359715, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.099749803543091, "global_step": 359716, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1356897354125977, "global_step": 359717, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0552093982696533, "global_step": 359718, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1525566577911377, "global_step": 359719, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.045869827270508, "global_step": 359720, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.090980291366577, "global_step": 359721, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1135218143463135, "global_step": 359722, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.120820999145508, "global_step": 359723, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0591094493865967, "global_step": 359724, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1152124404907227, "global_step": 359725, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1424143314361572, "global_step": 359726, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0536839962005615, "global_step": 359727, "epoch": 721, "lr": 5e-05}
{"train_loss": 1.9799177646636963, "global_step": 359728, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0713958740234375, "global_step": 359729, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1559274196624756, "global_step": 359730, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0866775512695312, "global_step": 359731, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1710405349731445, "global_step": 359732, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.102208375930786, "global_step": 359733, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.105571985244751, "global_step": 359734, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.208770275115967, "global_step": 359735, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1113717555999756, "global_step": 359736, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0729706287384033, "global_step": 359737, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.034489631652832, "global_step": 359738, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0506880283355713, "global_step": 359739, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.121957302093506, "global_step": 359740, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1114578247070312, "global_step": 359741, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.075038433074951, "global_step": 359742, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0979952812194824, "global_step": 359743, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0184192657470703, "global_step": 359744, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0810961723327637, "global_step": 359745, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1149861812591553, "global_step": 359746, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.150237798690796, "global_step": 359747, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.2175018787384033, "global_step": 359748, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1470470428466797, "global_step": 359749, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1105260848999023, "global_step": 359750, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.137493848800659, "global_step": 359751, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0814149379730225, "global_step": 359752, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.188509225845337, "global_step": 359753, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.065497875213623, "global_step": 359754, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.101475477218628, "global_step": 359755, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0339114665985107, "global_step": 359756, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1115381717681885, "global_step": 359757, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1564528942108154, "global_step": 359758, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0831804275512695, "global_step": 359759, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.107020378112793, "global_step": 359760, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.133680820465088, "global_step": 359761, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.086001396179199, "global_step": 359762, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.191189765930176, "global_step": 359763, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0618715286254883, "global_step": 359764, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0280063152313232, "global_step": 359765, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1047112941741943, "global_step": 359766, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1066207885742188, "global_step": 359767, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0682308673858643, "global_step": 359768, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.191124439239502, "global_step": 359769, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1297976970672607, "global_step": 359770, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.095153570175171, "global_step": 359771, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1643478870391846, "global_step": 359772, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.114078998565674, "global_step": 359773, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1781835556030273, "global_step": 359774, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.046251058578491, "global_step": 359775, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.054389476776123, "global_step": 359776, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1132867336273193, "global_step": 359777, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0567097663879395, "global_step": 359778, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1300556659698486, "global_step": 359779, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1278202533721924, "global_step": 359780, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.17387318611145, "global_step": 359781, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.06012225151062, "global_step": 359782, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1688156127929688, "global_step": 359783, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0516350269317627, "global_step": 359784, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.155808448791504, "global_step": 359785, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1324403285980225, "global_step": 359786, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0636258125305176, "global_step": 359787, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0894551277160645, "global_step": 359788, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.111492872238159, "global_step": 359789, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.068221092224121, "global_step": 359790, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.036212921142578, "global_step": 359791, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1762282848358154, "global_step": 359792, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1281213760375977, "global_step": 359793, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.116457223892212, "global_step": 359794, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.010843276977539, "global_step": 359795, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0800092220306396, "global_step": 359796, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.075770616531372, "global_step": 359797, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.170701026916504, "global_step": 359798, "epoch": 721, "lr": 5e-05}
{"train_loss": 1.9824963808059692, "global_step": 359799, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1000730991363525, "global_step": 359800, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0768983364105225, "global_step": 359801, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1167192459106445, "global_step": 359802, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.12617826461792, "global_step": 359803, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1015923023223877, "global_step": 359804, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.141388177871704, "global_step": 359805, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0919480323791504, "global_step": 359806, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.2001774311065674, "global_step": 359807, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.105187177658081, "global_step": 359808, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.090012550354004, "global_step": 359809, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.104320526123047, "global_step": 359810, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.139627456665039, "global_step": 359811, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.079432964324951, "global_step": 359812, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.05216908454895, "global_step": 359813, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1396853923797607, "global_step": 359814, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.103074789047241, "global_step": 359815, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1086819171905518, "global_step": 359816, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.01067852973938, "global_step": 359817, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1165671348571777, "global_step": 359818, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0926482677459717, "global_step": 359819, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.125450611114502, "global_step": 359820, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1727848052978516, "global_step": 359821, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.104722738265991, "global_step": 359822, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.062415838241577, "global_step": 359823, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1061973571777344, "global_step": 359824, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1077404022216797, "global_step": 359825, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.137502431869507, "global_step": 359826, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1409387588500977, "global_step": 359827, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1004042625427246, "global_step": 359828, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.169720411300659, "global_step": 359829, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1491870880126953, "global_step": 359830, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0874156951904297, "global_step": 359831, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.07639741897583, "global_step": 359832, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1727418899536133, "global_step": 359833, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0665104389190674, "global_step": 359834, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0889761447906494, "global_step": 359835, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.106562852859497, "global_step": 359836, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.107032060623169, "global_step": 359837, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.113860607147217, "global_step": 359838, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1020545959472656, "global_step": 359839, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.106189012527466, "global_step": 359840, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1555135250091553, "global_step": 359841, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.118983507156372, "global_step": 359842, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.067898750305176, "global_step": 359843, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0742294788360596, "global_step": 359844, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1305363178253174, "global_step": 359845, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1122944355010986, "global_step": 359846, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.108412027359009, "global_step": 359847, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0639302730560303, "global_step": 359848, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1157140731811523, "global_step": 359849, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.088737964630127, "global_step": 359850, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.140728235244751, "global_step": 359851, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.177344799041748, "global_step": 359852, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1014957427978516, "global_step": 359853, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1285922527313232, "global_step": 359854, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.152085304260254, "global_step": 359855, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1295573711395264, "global_step": 359856, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0589449405670166, "global_step": 359857, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0469868183135986, "global_step": 359858, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.151744842529297, "global_step": 359859, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1098239421844482, "global_step": 359860, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.110841989517212, "global_step": 359861, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0395665168762207, "global_step": 359862, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.119529962539673, "global_step": 359863, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.020212173461914, "global_step": 359864, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.186746835708618, "global_step": 359865, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1176767349243164, "global_step": 359866, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0988991260528564, "global_step": 359867, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0252463817596436, "global_step": 359868, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0852794647216797, "global_step": 359869, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.053962230682373, "global_step": 359870, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0757484436035156, "global_step": 359871, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.04659104347229, "global_step": 359872, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0889699459075928, "global_step": 359873, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.135152816772461, "global_step": 359874, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0997681617736816, "global_step": 359875, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0591983795166016, "global_step": 359876, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1244661808013916, "global_step": 359877, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.027705192565918, "global_step": 359878, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.115037679672241, "global_step": 359879, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0750644207000732, "global_step": 359880, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.11055850982666, "global_step": 359881, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.059890031814575, "global_step": 359882, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1196837425231934, "global_step": 359883, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1197669506073, "global_step": 359884, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1432137489318848, "global_step": 359885, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.145637035369873, "global_step": 359886, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.079862117767334, "global_step": 359887, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1280713081359863, "global_step": 359888, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0978527069091797, "global_step": 359889, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1150732040405273, "global_step": 359890, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.20100736618042, "global_step": 359891, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1174728870391846, "global_step": 359892, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.224130153656006, "global_step": 359893, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.057133674621582, "global_step": 359894, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.134162664413452, "global_step": 359895, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.14850115776062, "global_step": 359896, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1635074615478516, "global_step": 359897, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1395864486694336, "global_step": 359898, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.137150526046753, "global_step": 359899, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1346845626831055, "global_step": 359900, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1029648780822754, "global_step": 359901, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.085320234298706, "global_step": 359902, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0801472663879395, "global_step": 359903, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0496411323547363, "global_step": 359904, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.085463047027588, "global_step": 359905, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.056105375289917, "global_step": 359906, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.031503200531006, "global_step": 359907, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.169356346130371, "global_step": 359908, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0508484840393066, "global_step": 359909, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1282591819763184, "global_step": 359910, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.095978021621704, "global_step": 359911, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0923781394958496, "global_step": 359912, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.114133834838867, "global_step": 359913, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1127700805664062, "global_step": 359914, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1558728218078613, "global_step": 359915, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.128350257873535, "global_step": 359916, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0655972957611084, "global_step": 359917, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.159802198410034, "global_step": 359918, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1321818828582764, "global_step": 359919, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1011412143707275, "global_step": 359920, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.118549346923828, "global_step": 359921, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1400258541107178, "global_step": 359922, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.109318256378174, "global_step": 359923, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0362701416015625, "global_step": 359924, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1900851726531982, "global_step": 359925, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1170873641967773, "global_step": 359926, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0411365032196045, "global_step": 359927, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0419602394104004, "global_step": 359928, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.032055616378784, "global_step": 359929, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1038870811462402, "global_step": 359930, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.063154697418213, "global_step": 359931, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0344204902648926, "global_step": 359932, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0999820232391357, "global_step": 359933, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1230316162109375, "global_step": 359934, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.068615436553955, "global_step": 359935, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.032357931137085, "global_step": 359936, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1059603691101074, "global_step": 359937, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1638362407684326, "global_step": 359938, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1484761238098145, "global_step": 359939, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0215930938720703, "global_step": 359940, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1354329586029053, "global_step": 359941, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1263504028320312, "global_step": 359942, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0872418880462646, "global_step": 359943, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.065274953842163, "global_step": 359944, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.092527151107788, "global_step": 359945, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.115811586380005, "global_step": 359946, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.052726984024048, "global_step": 359947, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1279234886169434, "global_step": 359948, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1303820610046387, "global_step": 359949, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1308841705322266, "global_step": 359950, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.156438112258911, "global_step": 359951, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.14839506149292, "global_step": 359952, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0957884788513184, "global_step": 359953, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.086448907852173, "global_step": 359954, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1394734382629395, "global_step": 359955, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1379482746124268, "global_step": 359956, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.125176429748535, "global_step": 359957, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0072126388549805, "global_step": 359958, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0665504932403564, "global_step": 359959, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.147270679473877, "global_step": 359960, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0084574222564697, "global_step": 359961, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0605382919311523, "global_step": 359962, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.079864978790283, "global_step": 359963, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0620760917663574, "global_step": 359964, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0955958366394043, "global_step": 359965, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.212477445602417, "global_step": 359966, "epoch": 721, "lr": 5e-05}
{"train_loss": 1.982022762298584, "global_step": 359967, "epoch": 721, "lr": 5e-05}
{"train_loss": 1.9691561460494995, "global_step": 359968, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1336498260498047, "global_step": 359969, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.019970655441284, "global_step": 359970, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1247451305389404, "global_step": 359971, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.121899127960205, "global_step": 359972, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.097355365753174, "global_step": 359973, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0671496391296387, "global_step": 359974, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0702247619628906, "global_step": 359975, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.148164749145508, "global_step": 359976, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.223191499710083, "global_step": 359977, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1547060012817383, "global_step": 359978, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1396446228027344, "global_step": 359979, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0767295360565186, "global_step": 359980, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.039827823638916, "global_step": 359981, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.2117583751678467, "global_step": 359982, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1632370948791504, "global_step": 359983, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0000932216644287, "global_step": 359984, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1889150142669678, "global_step": 359985, "epoch": 721, "lr": 5e-05}
{"train_loss": 1.9730744361877441, "global_step": 359986, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.137535810470581, "global_step": 359987, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0513765811920166, "global_step": 359988, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0637269020080566, "global_step": 359989, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1010804176330566, "global_step": 359990, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.115640640258789, "global_step": 359991, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.075148582458496, "global_step": 359992, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1324360370635986, "global_step": 359993, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0954363346099854, "global_step": 359994, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.161959409713745, "global_step": 359995, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1136372089385986, "global_step": 359996, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0484933853149414, "global_step": 359997, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.177736759185791, "global_step": 359998, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.051450729370117, "global_step": 359999, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1231348514556885, "global_step": 360000, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0998482704162598, "global_step": 360001, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.152695655822754, "global_step": 360002, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0917282104492188, "global_step": 360003, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.072911024093628, "global_step": 360004, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0562734603881836, "global_step": 360005, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.105210304260254, "global_step": 360006, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1201953887939453, "global_step": 360007, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.146801471710205, "global_step": 360008, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.150778293609619, "global_step": 360009, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0590970516204834, "global_step": 360010, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.141202211380005, "global_step": 360011, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.076486110687256, "global_step": 360012, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.056596279144287, "global_step": 360013, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0913639068603516, "global_step": 360014, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0772786140441895, "global_step": 360015, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1972405910491943, "global_step": 360016, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.096133232116699, "global_step": 360017, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.136667013168335, "global_step": 360018, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1643176078796387, "global_step": 360019, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1514995098114014, "global_step": 360020, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1579275131225586, "global_step": 360021, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0473759174346924, "global_step": 360022, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.121490240097046, "global_step": 360023, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0989198684692383, "global_step": 360024, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.117548942565918, "global_step": 360025, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0923240184783936, "global_step": 360026, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.096055746078491, "global_step": 360027, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0988826751708984, "global_step": 360028, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0910708904266357, "global_step": 360029, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0692014694213867, "global_step": 360030, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0486416816711426, "global_step": 360031, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.125065565109253, "global_step": 360032, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1464452743530273, "global_step": 360033, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1299209594726562, "global_step": 360034, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.131558656692505, "global_step": 360035, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.084672689437866, "global_step": 360036, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1517908573150635, "global_step": 360037, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.089012384414673, "global_step": 360038, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0227103233337402, "global_step": 360039, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.074573516845703, "global_step": 360040, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.11356520652771, "global_step": 360041, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0052337646484375, "global_step": 360042, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1195366382598877, "global_step": 360043, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.052206516265869, "global_step": 360044, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.174920082092285, "global_step": 360045, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.047293186187744, "global_step": 360046, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.124053478240967, "global_step": 360047, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0607776641845703, "global_step": 360048, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.152296781539917, "global_step": 360049, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0107405185699463, "global_step": 360050, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.231232166290283, "global_step": 360051, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.102604389190674, "global_step": 360052, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.057742118835449, "global_step": 360053, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.102980375289917, "global_step": 360054, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.04978346824646, "global_step": 360055, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0893642902374268, "global_step": 360056, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.121633291244507, "global_step": 360057, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.056992292404175, "global_step": 360058, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1482467651367188, "global_step": 360059, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1082117557525635, "global_step": 360060, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0753021240234375, "global_step": 360061, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1002631187438965, "global_step": 360062, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0928399562835693, "global_step": 360063, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1007802486419678, "global_step": 360064, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.135854721069336, "global_step": 360065, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0622334480285645, "global_step": 360066, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0796642303466797, "global_step": 360067, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.115628480911255, "global_step": 360068, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0950493812561035, "global_step": 360069, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1483206748962402, "global_step": 360070, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.107736587524414, "global_step": 360071, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1050448417663574, "global_step": 360072, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1826517581939697, "global_step": 360073, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.130126714706421, "global_step": 360074, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1900010108947754, "global_step": 360075, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0510125160217285, "global_step": 360076, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.069493532180786, "global_step": 360077, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1062581539154053, "global_step": 360078, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0830047130584717, "global_step": 360079, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.21502685546875, "global_step": 360080, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1045689582824707, "global_step": 360081, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1474790573120117, "global_step": 360082, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.17136812210083, "global_step": 360083, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0688107013702393, "global_step": 360084, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.022458076477051, "global_step": 360085, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.037020683288574, "global_step": 360086, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.167018413543701, "global_step": 360087, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1463241577148438, "global_step": 360088, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.092069387435913, "global_step": 360089, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0810704231262207, "global_step": 360090, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.198776960372925, "global_step": 360091, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.006040573120117, "global_step": 360092, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.13824725151062, "global_step": 360093, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0767080783843994, "global_step": 360094, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.174663543701172, "global_step": 360095, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.138414144515991, "global_step": 360096, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0958774089813232, "global_step": 360097, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.043846845626831, "global_step": 360098, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1484076976776123, "global_step": 360099, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0641438961029053, "global_step": 360100, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0723283290863037, "global_step": 360101, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.15140438079834, "global_step": 360102, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.103689670562744, "global_step": 360103, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.074225902557373, "global_step": 360104, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0934014320373535, "global_step": 360105, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.090977191925049, "global_step": 360106, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.090034008026123, "global_step": 360107, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.050665855407715, "global_step": 360108, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0521748065948486, "global_step": 360109, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1635046005249023, "global_step": 360110, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0461597442626953, "global_step": 360111, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.184478998184204, "global_step": 360112, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.054642915725708, "global_step": 360113, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.118316173553467, "global_step": 360114, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.107010841369629, "global_step": 360115, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1200428009033203, "global_step": 360116, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0501253604888916, "global_step": 360117, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.114985704421997, "global_step": 360118, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0370373725891113, "global_step": 360119, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.073227643966675, "global_step": 360120, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1149682998657227, "global_step": 360121, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.179546356201172, "global_step": 360122, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1401588916778564, "global_step": 360123, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.157686710357666, "global_step": 360124, "epoch": 721, "lr": 5e-05}
{"train_loss": 1.9905627965927124, "global_step": 360125, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1743712425231934, "global_step": 360126, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.089289665222168, "global_step": 360127, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1801609992980957, "global_step": 360128, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.075853109359741, "global_step": 360129, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1293282508850098, "global_step": 360130, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1147491931915283, "global_step": 360131, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.072645425796509, "global_step": 360132, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0570878982543945, "global_step": 360133, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.053574800491333, "global_step": 360134, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.124410629272461, "global_step": 360135, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1075944900512695, "global_step": 360136, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0015251636505127, "global_step": 360137, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.2280516624450684, "global_step": 360138, "epoch": 721, "lr": 5e-05}
{"train_loss": 1.997205138206482, "global_step": 360139, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1028852462768555, "global_step": 360140, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1036736965179443, "global_step": 360141, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.178515911102295, "global_step": 360142, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.111236333847046, "global_step": 360143, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.079440116882324, "global_step": 360144, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1291897296905518, "global_step": 360145, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.053262710571289, "global_step": 360146, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1094155311584473, "global_step": 360147, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.062199354171753, "global_step": 360148, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.056460380554199, "global_step": 360149, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1805331707000732, "global_step": 360150, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.082226276397705, "global_step": 360151, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.093677043914795, "global_step": 360152, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.129598379135132, "global_step": 360153, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1072819232940674, "global_step": 360154, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1401853561401367, "global_step": 360155, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.136167526245117, "global_step": 360156, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0913760662078857, "global_step": 360157, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0531558990478516, "global_step": 360158, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.114367723464966, "global_step": 360159, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1405067443847656, "global_step": 360160, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.033292055130005, "global_step": 360161, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.117995023727417, "global_step": 360162, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0998148918151855, "global_step": 360163, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.073392152786255, "global_step": 360164, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0338432788848877, "global_step": 360165, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.032287120819092, "global_step": 360166, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.037000894546509, "global_step": 360167, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0832157135009766, "global_step": 360168, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1417107582092285, "global_step": 360169, "epoch": 721, "lr": 5e-05}
{"train_loss": 1.9982455968856812, "global_step": 360170, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1124823093414307, "global_step": 360171, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0606882572174072, "global_step": 360172, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1327316761016846, "global_step": 360173, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.043161630630493, "global_step": 360174, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.169243812561035, "global_step": 360175, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1727049350738525, "global_step": 360176, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0750222206115723, "global_step": 360177, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.088087558746338, "global_step": 360178, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1377339363098145, "global_step": 360179, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1232433319091797, "global_step": 360180, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.220925807952881, "global_step": 360181, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1171162128448486, "global_step": 360182, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1273560523986816, "global_step": 360183, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.091585397720337, "global_step": 360184, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.140033721923828, "global_step": 360185, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1015565395355225, "global_step": 360186, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.081211566925049, "global_step": 360187, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.174861192703247, "global_step": 360188, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1481986045837402, "global_step": 360189, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0874338150024414, "global_step": 360190, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.075751543045044, "global_step": 360191, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0978381633758545, "global_step": 360192, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.143989086151123, "global_step": 360193, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1311378479003906, "global_step": 360194, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0855422019958496, "global_step": 360195, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.115901231765747, "global_step": 360196, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0687434673309326, "global_step": 360197, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1043899059295654, "global_step": 360198, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1269819736480713, "global_step": 360199, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0618364810943604, "global_step": 360200, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.110492467880249, "global_step": 360201, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1394083499908447, "global_step": 360202, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.105705738067627, "global_step": 360203, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0821547508239746, "global_step": 360204, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1139168739318848, "global_step": 360205, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.123826026916504, "global_step": 360206, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.062185525894165, "global_step": 360207, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1339714527130127, "global_step": 360208, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.149670362472534, "global_step": 360209, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.141993284225464, "global_step": 360210, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1214089393615723, "global_step": 360211, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1315953731536865, "global_step": 360212, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.058633804321289, "global_step": 360213, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1114814281463623, "global_step": 360214, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.042081356048584, "global_step": 360215, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.091162919998169, "global_step": 360216, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1099348068237305, "global_step": 360217, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0940968990325928, "global_step": 360218, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.116464853286743, "global_step": 360219, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.038525104522705, "global_step": 360220, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1035408973693848, "global_step": 360221, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.139092206954956, "global_step": 360222, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.154155731201172, "global_step": 360223, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.195596218109131, "global_step": 360224, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1401724815368652, "global_step": 360225, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1431872844696045, "global_step": 360226, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0617239475250244, "global_step": 360227, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0728135108947754, "global_step": 360228, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0767722129821777, "global_step": 360229, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.025899887084961, "global_step": 360230, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0608482360839844, "global_step": 360231, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.054816246032715, "global_step": 360232, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1941511631011963, "global_step": 360233, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0746638774871826, "global_step": 360234, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.17883038520813, "global_step": 360235, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1276612281799316, "global_step": 360236, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.155625104904175, "global_step": 360237, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1430437564849854, "global_step": 360238, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.147885799407959, "global_step": 360239, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0578694343566895, "global_step": 360240, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.126357316970825, "global_step": 360241, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.059948205947876, "global_step": 360242, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.123378038406372, "global_step": 360243, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.118757724761963, "global_step": 360244, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1269750595092773, "global_step": 360245, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1192476749420166, "global_step": 360246, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.19907808303833, "global_step": 360247, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1714296340942383, "global_step": 360248, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0568344593048096, "global_step": 360249, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.186370611190796, "global_step": 360250, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0401275157928467, "global_step": 360251, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.132078170776367, "global_step": 360252, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.095332145690918, "global_step": 360253, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.117492914199829, "global_step": 360254, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0594120025634766, "global_step": 360255, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1516964435577393, "global_step": 360256, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1118738651275635, "global_step": 360257, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1468498706817627, "global_step": 360258, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.129401445388794, "global_step": 360259, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.144359827041626, "global_step": 360260, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1777567863464355, "global_step": 360261, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.111386775970459, "global_step": 360262, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1816534996032715, "global_step": 360263, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1319990158081055, "global_step": 360264, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.054394245147705, "global_step": 360265, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.10318660736084, "global_step": 360266, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0404698848724365, "global_step": 360267, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0905630588531494, "global_step": 360268, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1208338737487793, "global_step": 360269, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1506056785583496, "global_step": 360270, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.137535810470581, "global_step": 360271, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1424269676208496, "global_step": 360272, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.132863998413086, "global_step": 360273, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.111848831176758, "global_step": 360274, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1667799949645996, "global_step": 360275, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0758440494537354, "global_step": 360276, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.132295608520508, "global_step": 360277, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.074252128601074, "global_step": 360278, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1172218322753906, "global_step": 360279, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1481237411499023, "global_step": 360280, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.035536289215088, "global_step": 360281, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.07820200920105, "global_step": 360282, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.152771472930908, "global_step": 360283, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.194838523864746, "global_step": 360284, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.161590099334717, "global_step": 360285, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1148250102996826, "global_step": 360286, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0702083110809326, "global_step": 360287, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1264383792877197, "global_step": 360288, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0440096855163574, "global_step": 360289, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1461141109466553, "global_step": 360290, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1488170623779297, "global_step": 360291, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.205496311187744, "global_step": 360292, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0692875385284424, "global_step": 360293, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.033351421356201, "global_step": 360294, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1409192085266113, "global_step": 360295, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1592414379119873, "global_step": 360296, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1003682613372803, "global_step": 360297, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0691781044006348, "global_step": 360298, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.05446457862854, "global_step": 360299, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0976858139038086, "global_step": 360300, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.141939640045166, "global_step": 360301, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1682121753692627, "global_step": 360302, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1592178344726562, "global_step": 360303, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1381936073303223, "global_step": 360304, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.2170112133026123, "global_step": 360305, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0678462982177734, "global_step": 360306, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1048901081085205, "global_step": 360307, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.180847406387329, "global_step": 360308, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.107750177383423, "global_step": 360309, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0722057819366455, "global_step": 360310, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1534228324890137, "global_step": 360311, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.150282382965088, "global_step": 360312, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.2185301780700684, "global_step": 360313, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0825002193450928, "global_step": 360314, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.15807843208313, "global_step": 360315, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.143174648284912, "global_step": 360316, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.018575429916382, "global_step": 360317, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.144289255142212, "global_step": 360318, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.123664617538452, "global_step": 360319, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.121380567550659, "global_step": 360320, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0928380489349365, "global_step": 360321, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0682976245880127, "global_step": 360322, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.014005661010742, "global_step": 360323, "epoch": 721, "lr": 5e-05}
{"train_loss": 1.985435962677002, "global_step": 360324, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1641221046447754, "global_step": 360325, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.074176073074341, "global_step": 360326, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.121056318283081, "global_step": 360327, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.2037031650543213, "global_step": 360328, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0620877742767334, "global_step": 360329, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.095836639404297, "global_step": 360330, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.069936513900757, "global_step": 360331, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.085644006729126, "global_step": 360332, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0683114528656006, "global_step": 360333, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1030032634735107, "global_step": 360334, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.2121236324310303, "global_step": 360335, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0996668338775635, "global_step": 360336, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.108814239501953, "global_step": 360337, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.012188673019409, "global_step": 360338, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.161078691482544, "global_step": 360339, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1143200397491455, "global_step": 360340, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1063311100006104, "global_step": 360341, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.056821346282959, "global_step": 360342, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.16038179397583, "global_step": 360343, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1707451343536377, "global_step": 360344, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1661338806152344, "global_step": 360345, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0696351528167725, "global_step": 360346, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1217472553253174, "global_step": 360347, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1880714893341064, "global_step": 360348, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1445701122283936, "global_step": 360349, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0735087394714355, "global_step": 360350, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0268826484680176, "global_step": 360351, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1812233924865723, "global_step": 360352, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.258638381958008, "global_step": 360353, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.121025323867798, "global_step": 360354, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1664011478424072, "global_step": 360355, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1139638423919678, "global_step": 360356, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0424435138702393, "global_step": 360357, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.193953037261963, "global_step": 360358, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1898138523101807, "global_step": 360359, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1417129039764404, "global_step": 360360, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0960004329681396, "global_step": 360361, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1049914360046387, "global_step": 360362, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.146496295928955, "global_step": 360363, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0603439807891846, "global_step": 360364, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.035116195678711, "global_step": 360365, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1881494522094727, "global_step": 360366, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1600182056427, "global_step": 360367, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1277287006378174, "global_step": 360368, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1243574619293213, "global_step": 360369, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0957095623016357, "global_step": 360370, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.066556930541992, "global_step": 360371, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1160266399383545, "global_step": 360372, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.032834529876709, "global_step": 360373, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0618321895599365, "global_step": 360374, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1878621578216553, "global_step": 360375, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.047267436981201, "global_step": 360376, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0636117458343506, "global_step": 360377, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0848922729492188, "global_step": 360378, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.2424967288970947, "global_step": 360379, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.081911087036133, "global_step": 360380, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0845019817352295, "global_step": 360381, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1806368827819824, "global_step": 360382, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1158738136291504, "global_step": 360383, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0991392135620117, "global_step": 360384, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0597376823425293, "global_step": 360385, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0795047283172607, "global_step": 360386, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.113788366317749, "global_step": 360387, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.124238967895508, "global_step": 360388, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0556037425994873, "global_step": 360389, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0472519397735596, "global_step": 360390, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.110652446746826, "global_step": 360391, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0747671127319336, "global_step": 360392, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.089578628540039, "global_step": 360393, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.054452419281006, "global_step": 360394, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1024701595306396, "global_step": 360395, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0664947032928467, "global_step": 360396, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1331288814544678, "global_step": 360397, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0958545207977295, "global_step": 360398, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.082979440689087, "global_step": 360399, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0930542945861816, "global_step": 360400, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.050497055053711, "global_step": 360401, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1489739418029785, "global_step": 360402, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.067208766937256, "global_step": 360403, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.126711845397949, "global_step": 360404, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1298575401306152, "global_step": 360405, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1250040531158447, "global_step": 360406, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.120224952697754, "global_step": 360407, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1062440872192383, "global_step": 360408, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.013979196548462, "global_step": 360409, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1521594524383545, "global_step": 360410, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0406508445739746, "global_step": 360411, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.149143695831299, "global_step": 360412, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.200723171234131, "global_step": 360413, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1942169666290283, "global_step": 360414, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.126024007797241, "global_step": 360415, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1463844776153564, "global_step": 360416, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0854358673095703, "global_step": 360417, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1373393535614014, "global_step": 360418, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0424587726593018, "global_step": 360419, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1513781547546387, "global_step": 360420, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.062631607055664, "global_step": 360421, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.081772804260254, "global_step": 360422, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.114332675933838, "global_step": 360423, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0060033798217773, "global_step": 360424, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1197397708892822, "global_step": 360425, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.140714406967163, "global_step": 360426, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0555989742279053, "global_step": 360427, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.115718126296997, "global_step": 360428, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.105565309524536, "global_step": 360429, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.076983690261841, "global_step": 360430, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0435824394226074, "global_step": 360431, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0426013469696045, "global_step": 360432, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.024487257003784, "global_step": 360433, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1041293144226074, "global_step": 360434, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.101846933364868, "global_step": 360435, "epoch": 721, "lr": 5e-05}
{"train_loss": 1.9617621898651123, "global_step": 360436, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.089167356491089, "global_step": 360437, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0825421810150146, "global_step": 360438, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1722230911254883, "global_step": 360439, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0503971576690674, "global_step": 360440, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0605082511901855, "global_step": 360441, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.093151807785034, "global_step": 360442, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.06662654876709, "global_step": 360443, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0884416103363037, "global_step": 360444, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1903250217437744, "global_step": 360445, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0603506565093994, "global_step": 360446, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0739009380340576, "global_step": 360447, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.104933261871338, "global_step": 360448, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1020545959472656, "global_step": 360449, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.130228281021118, "global_step": 360450, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1381375789642334, "global_step": 360451, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.131216526031494, "global_step": 360452, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.111727237701416, "global_step": 360453, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0719571113586426, "global_step": 360454, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.165278434753418, "global_step": 360455, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1699612140655518, "global_step": 360456, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.054567575454712, "global_step": 360457, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.156996726989746, "global_step": 360458, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0914175510406494, "global_step": 360459, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1339125633239746, "global_step": 360460, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0874505043029785, "global_step": 360461, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.14440655708313, "global_step": 360462, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1446356773376465, "global_step": 360463, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0732431411743164, "global_step": 360464, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1784746646881104, "global_step": 360465, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.084343433380127, "global_step": 360466, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1201720237731934, "global_step": 360467, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1268160343170166, "global_step": 360468, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1586806774139404, "global_step": 360469, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.189751625061035, "global_step": 360470, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1531622409820557, "global_step": 360471, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1508612632751465, "global_step": 360472, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1473190784454346, "global_step": 360473, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1803197860717773, "global_step": 360474, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1223971843719482, "global_step": 360475, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.114089012145996, "global_step": 360476, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.128868579864502, "global_step": 360477, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0812807083129883, "global_step": 360478, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1197636127471924, "global_step": 360479, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.05743670463562, "global_step": 360480, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0915639400482178, "global_step": 360481, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0917060375213623, "global_step": 360482, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.101578950881958, "global_step": 360483, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.168224811553955, "global_step": 360484, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.133103609085083, "global_step": 360485, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1083929538726807, "global_step": 360486, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.078592538833618, "global_step": 360487, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1370508670806885, "global_step": 360488, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.129298210144043, "global_step": 360489, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.112340211868286, "global_step": 360490, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.143207311630249, "global_step": 360491, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1384503841400146, "global_step": 360492, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.144085645675659, "global_step": 360493, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.14452862739563, "global_step": 360494, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.107740640640259, "global_step": 360495, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.125912666320801, "global_step": 360496, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0831503868103027, "global_step": 360497, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.099992036819458, "global_step": 360498, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1643154621124268, "global_step": 360499, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1052474975585938, "global_step": 360500, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0473220348358154, "global_step": 360501, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.037071466445923, "global_step": 360502, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.115685224533081, "global_step": 360503, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1079905033111572, "global_step": 360504, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.137153148651123, "global_step": 360505, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0834035873413086, "global_step": 360506, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1348681449890137, "global_step": 360507, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.224487543106079, "global_step": 360508, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.105156898498535, "global_step": 360509, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.036841630935669, "global_step": 360510, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1738460063934326, "global_step": 360511, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0126686096191406, "global_step": 360512, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1101503372192383, "global_step": 360513, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.102786064147949, "global_step": 360514, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1549949645996094, "global_step": 360515, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.137526035308838, "global_step": 360516, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.156175136566162, "global_step": 360517, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1237003803253174, "global_step": 360518, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.062979221343994, "global_step": 360519, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0881195068359375, "global_step": 360520, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1269350051879883, "global_step": 360521, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.070760488510132, "global_step": 360522, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1041431427001953, "global_step": 360523, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1474497318267822, "global_step": 360524, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.04347562789917, "global_step": 360525, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0851645469665527, "global_step": 360526, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.073946714401245, "global_step": 360527, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1190149784088135, "global_step": 360528, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1281018257141113, "global_step": 360529, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.102759838104248, "global_step": 360530, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1468100547790527, "global_step": 360531, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0811002254486084, "global_step": 360532, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.096374750137329, "global_step": 360533, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1201772689819336, "global_step": 360534, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0474061965942383, "global_step": 360535, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1267776489257812, "global_step": 360536, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.159693717956543, "global_step": 360537, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.134215831756592, "global_step": 360538, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.056842565536499, "global_step": 360539, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.114194869995117, "global_step": 360540, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.155078411102295, "global_step": 360541, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1168951988220215, "global_step": 360542, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1777353286743164, "global_step": 360543, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.125030994415283, "global_step": 360544, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1212637424468994, "global_step": 360545, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.148251533508301, "global_step": 360546, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0956437587738037, "global_step": 360547, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0896973609924316, "global_step": 360548, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.16001558303833, "global_step": 360549, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0961763858795166, "global_step": 360550, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.164064645767212, "global_step": 360551, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.036022186279297, "global_step": 360552, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.12568998336792, "global_step": 360553, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.102522850036621, "global_step": 360554, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1229465007781982, "global_step": 360555, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.065319776535034, "global_step": 360556, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1698713302612305, "global_step": 360557, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1770641803741455, "global_step": 360558, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1127777099609375, "global_step": 360559, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.08823823928833, "global_step": 360560, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1694116592407227, "global_step": 360561, "epoch": 721, "lr": 5e-05}
{"train_loss": 1.9584470987319946, "global_step": 360562, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1031460762023926, "global_step": 360563, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1142523288726807, "global_step": 360564, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.131267786026001, "global_step": 360565, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1039183139801025, "global_step": 360566, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.089250326156616, "global_step": 360567, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1265153884887695, "global_step": 360568, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1203789710998535, "global_step": 360569, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1791656017303467, "global_step": 360570, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1273269653320312, "global_step": 360571, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.173102855682373, "global_step": 360572, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1119778156280518, "global_step": 360573, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.067861557006836, "global_step": 360574, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.057006359100342, "global_step": 360575, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1291909217834473, "global_step": 360576, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.143289089202881, "global_step": 360577, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1128644943237305, "global_step": 360578, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0542914867401123, "global_step": 360579, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.124800205230713, "global_step": 360580, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.127372980117798, "global_step": 360581, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0679054260253906, "global_step": 360582, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1529321670532227, "global_step": 360583, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.22578501701355, "global_step": 360584, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0818305015563965, "global_step": 360585, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1534345149993896, "global_step": 360586, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.063532829284668, "global_step": 360587, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1258199214935303, "global_step": 360588, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.134634256362915, "global_step": 360589, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.069976568222046, "global_step": 360590, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.145807981491089, "global_step": 360591, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.062561511993408, "global_step": 360592, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1644296646118164, "global_step": 360593, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.110161066055298, "global_step": 360594, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1896166801452637, "global_step": 360595, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.050045967102051, "global_step": 360596, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0293641090393066, "global_step": 360597, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.099412202835083, "global_step": 360598, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0476033687591553, "global_step": 360599, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.1072194576263428, "global_step": 360600, "epoch": 721, "lr": 5e-05}
{"train_loss": 2.0838518142700195, "global_step": 360601, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1089653968811035, "global_step": 360602, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.13364315032959, "global_step": 360603, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.116382360458374, "global_step": 360604, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1096644401550293, "global_step": 360605, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0688891410827637, "global_step": 360606, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1800687313079834, "global_step": 360607, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1199464797973633, "global_step": 360608, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.026185989379883, "global_step": 360609, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.186729669570923, "global_step": 360610, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1132516860961914, "global_step": 360611, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0631697177886963, "global_step": 360612, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0877394676208496, "global_step": 360613, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1247832775115967, "global_step": 360614, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2018539905548096, "global_step": 360615, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1251718997955322, "global_step": 360616, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.130244016647339, "global_step": 360617, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.134963035583496, "global_step": 360618, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0768420696258545, "global_step": 360619, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1392171382904053, "global_step": 360620, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.082547903060913, "global_step": 360621, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.066657781600952, "global_step": 360622, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.069655656814575, "global_step": 360623, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.055471658706665, "global_step": 360624, "epoch": 722, "lr": 5e-05}
{"train_loss": 1.9858217239379883, "global_step": 360625, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1439411640167236, "global_step": 360626, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.140049457550049, "global_step": 360627, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0256187915802, "global_step": 360628, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1194205284118652, "global_step": 360629, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.047097682952881, "global_step": 360630, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.095877170562744, "global_step": 360631, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.134927749633789, "global_step": 360632, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.113645315170288, "global_step": 360633, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.032679557800293, "global_step": 360634, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0525119304656982, "global_step": 360635, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0407228469848633, "global_step": 360636, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1160202026367188, "global_step": 360637, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1502482891082764, "global_step": 360638, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0708227157592773, "global_step": 360639, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0974934101104736, "global_step": 360640, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.129387140274048, "global_step": 360641, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.050017833709717, "global_step": 360642, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0494630336761475, "global_step": 360643, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0633246898651123, "global_step": 360644, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.163613796234131, "global_step": 360645, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0278513431549072, "global_step": 360646, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0680313110351562, "global_step": 360647, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0918304920196533, "global_step": 360648, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1193044185638428, "global_step": 360649, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.009342670440674, "global_step": 360650, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0478029251098633, "global_step": 360651, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1401784420013428, "global_step": 360652, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.083556652069092, "global_step": 360653, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.14304518699646, "global_step": 360654, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1578588485717773, "global_step": 360655, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1134989261627197, "global_step": 360656, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0446650981903076, "global_step": 360657, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.090247631072998, "global_step": 360658, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1681909561157227, "global_step": 360659, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.107252597808838, "global_step": 360660, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.155054807662964, "global_step": 360661, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.073500156402588, "global_step": 360662, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1811249256134033, "global_step": 360663, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.109745979309082, "global_step": 360664, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.211113929748535, "global_step": 360665, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.149632453918457, "global_step": 360666, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1303634643554688, "global_step": 360667, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.123347759246826, "global_step": 360668, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0767228603363037, "global_step": 360669, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.111635208129883, "global_step": 360670, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.106933116912842, "global_step": 360671, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.034507989883423, "global_step": 360672, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0945942401885986, "global_step": 360673, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1518335342407227, "global_step": 360674, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0763723850250244, "global_step": 360675, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0970542430877686, "global_step": 360676, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0375847816467285, "global_step": 360677, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0613629817962646, "global_step": 360678, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1431326866149902, "global_step": 360679, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.086629629135132, "global_step": 360680, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0949442386627197, "global_step": 360681, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0406644344329834, "global_step": 360682, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1251728534698486, "global_step": 360683, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1171576976776123, "global_step": 360684, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0872857570648193, "global_step": 360685, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0796384811401367, "global_step": 360686, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.04311203956604, "global_step": 360687, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.276820182800293, "global_step": 360688, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1779844760894775, "global_step": 360689, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1537718772888184, "global_step": 360690, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.175105094909668, "global_step": 360691, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.037121057510376, "global_step": 360692, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1221506595611572, "global_step": 360693, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1781442165374756, "global_step": 360694, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.098846197128296, "global_step": 360695, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.131884813308716, "global_step": 360696, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.120490550994873, "global_step": 360697, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.081082820892334, "global_step": 360698, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0900158882141113, "global_step": 360699, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.174543857574463, "global_step": 360700, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0084495544433594, "global_step": 360701, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1203465461730957, "global_step": 360702, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.061213731765747, "global_step": 360703, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.072312593460083, "global_step": 360704, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.088972330093384, "global_step": 360705, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.080172300338745, "global_step": 360706, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0300025939941406, "global_step": 360707, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1500942707061768, "global_step": 360708, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1215059757232666, "global_step": 360709, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.088745594024658, "global_step": 360710, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.022490978240967, "global_step": 360711, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0524110794067383, "global_step": 360712, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1697943210601807, "global_step": 360713, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0349974632263184, "global_step": 360714, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.071021556854248, "global_step": 360715, "epoch": 722, "lr": 5e-05}
{"train_loss": 1.9505332708358765, "global_step": 360716, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1899075508117676, "global_step": 360717, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1910147666931152, "global_step": 360718, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1700267791748047, "global_step": 360719, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1922128200531006, "global_step": 360720, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1256062984466553, "global_step": 360721, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.102834701538086, "global_step": 360722, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1064977645874023, "global_step": 360723, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.129124641418457, "global_step": 360724, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.169740676879883, "global_step": 360725, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1585030555725098, "global_step": 360726, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0827736854553223, "global_step": 360727, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.081812858581543, "global_step": 360728, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0793344974517822, "global_step": 360729, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.141258716583252, "global_step": 360730, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.02309250831604, "global_step": 360731, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0498549938201904, "global_step": 360732, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0339090824127197, "global_step": 360733, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2195918560028076, "global_step": 360734, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0936319828033447, "global_step": 360735, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0911242961883545, "global_step": 360736, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0649502277374268, "global_step": 360737, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0431976318359375, "global_step": 360738, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.112600803375244, "global_step": 360739, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.064506769180298, "global_step": 360740, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.101696014404297, "global_step": 360741, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.057772636413574, "global_step": 360742, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.206542491912842, "global_step": 360743, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0707664489746094, "global_step": 360744, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0853939056396484, "global_step": 360745, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0442044734954834, "global_step": 360746, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0693519115448, "global_step": 360747, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0743112564086914, "global_step": 360748, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.102483034133911, "global_step": 360749, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.174915075302124, "global_step": 360750, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.10422945022583, "global_step": 360751, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1331264972686768, "global_step": 360752, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0892269611358643, "global_step": 360753, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.097808361053467, "global_step": 360754, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.077820062637329, "global_step": 360755, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0481302738189697, "global_step": 360756, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1450397968292236, "global_step": 360757, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.021132469177246, "global_step": 360758, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1253724098205566, "global_step": 360759, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.141871929168701, "global_step": 360760, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1384308338165283, "global_step": 360761, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1448330879211426, "global_step": 360762, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.076007604598999, "global_step": 360763, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.137016773223877, "global_step": 360764, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1358864307403564, "global_step": 360765, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1319010257720947, "global_step": 360766, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0854787826538086, "global_step": 360767, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.090668201446533, "global_step": 360768, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.120209217071533, "global_step": 360769, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.175380229949951, "global_step": 360770, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.148461103439331, "global_step": 360771, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0493950843811035, "global_step": 360772, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1598222255706787, "global_step": 360773, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.008514881134033, "global_step": 360774, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0753066539764404, "global_step": 360775, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.100982189178467, "global_step": 360776, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.132401466369629, "global_step": 360777, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1668953895568848, "global_step": 360778, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.15511155128479, "global_step": 360779, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0837161540985107, "global_step": 360780, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0185577869415283, "global_step": 360781, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0963051319122314, "global_step": 360782, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0797579288482666, "global_step": 360783, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.095376491546631, "global_step": 360784, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.059213161468506, "global_step": 360785, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.043182611465454, "global_step": 360786, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1561784744262695, "global_step": 360787, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0468239784240723, "global_step": 360788, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.266608715057373, "global_step": 360789, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0908753871917725, "global_step": 360790, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0966782569885254, "global_step": 360791, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0722477436065674, "global_step": 360792, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1233513355255127, "global_step": 360793, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0908474922180176, "global_step": 360794, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1163086891174316, "global_step": 360795, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.064723253250122, "global_step": 360796, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1079325675964355, "global_step": 360797, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.099783420562744, "global_step": 360798, "epoch": 722, "lr": 5e-05}
{"train_loss": 1.9714914560317993, "global_step": 360799, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.074554204940796, "global_step": 360800, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.106955051422119, "global_step": 360801, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.100146770477295, "global_step": 360802, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.048187017440796, "global_step": 360803, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.174243927001953, "global_step": 360804, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0966796875, "global_step": 360805, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.124605178833008, "global_step": 360806, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.197665214538574, "global_step": 360807, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1409623622894287, "global_step": 360808, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.074097156524658, "global_step": 360809, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0899817943573, "global_step": 360810, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.041886329650879, "global_step": 360811, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.094933271408081, "global_step": 360812, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1125869750976562, "global_step": 360813, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.117231607437134, "global_step": 360814, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0311148166656494, "global_step": 360815, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1441690921783447, "global_step": 360816, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1286137104034424, "global_step": 360817, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1101620197296143, "global_step": 360818, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1659955978393555, "global_step": 360819, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.020986795425415, "global_step": 360820, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0684566497802734, "global_step": 360821, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.078605890274048, "global_step": 360822, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.111999273300171, "global_step": 360823, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.161355972290039, "global_step": 360824, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0260794162750244, "global_step": 360825, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1568658351898193, "global_step": 360826, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0805323123931885, "global_step": 360827, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1303210258483887, "global_step": 360828, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.135026454925537, "global_step": 360829, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.012849807739258, "global_step": 360830, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0109519958496094, "global_step": 360831, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0621323585510254, "global_step": 360832, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0703389644622803, "global_step": 360833, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0490899085998535, "global_step": 360834, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1448771953582764, "global_step": 360835, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0728232860565186, "global_step": 360836, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.06538987159729, "global_step": 360837, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1391472816467285, "global_step": 360838, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.022289514541626, "global_step": 360839, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.055154800415039, "global_step": 360840, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.133284568786621, "global_step": 360841, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1707749366760254, "global_step": 360842, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0631790161132812, "global_step": 360843, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.061800956726074, "global_step": 360844, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.091569662094116, "global_step": 360845, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.038504123687744, "global_step": 360846, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0886881351470947, "global_step": 360847, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.094804286956787, "global_step": 360848, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.05692195892334, "global_step": 360849, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.132701873779297, "global_step": 360850, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0575778484344482, "global_step": 360851, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.136209487915039, "global_step": 360852, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.049503803253174, "global_step": 360853, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1110570430755615, "global_step": 360854, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.057295560836792, "global_step": 360855, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.127234697341919, "global_step": 360856, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1263720989227295, "global_step": 360857, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0795702934265137, "global_step": 360858, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.12300705909729, "global_step": 360859, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0539371967315674, "global_step": 360860, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2399604320526123, "global_step": 360861, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1406102180480957, "global_step": 360862, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.101607322692871, "global_step": 360863, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.117339611053467, "global_step": 360864, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1330058574676514, "global_step": 360865, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.082690715789795, "global_step": 360866, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.180744171142578, "global_step": 360867, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1071109771728516, "global_step": 360868, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.243213415145874, "global_step": 360869, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1365668773651123, "global_step": 360870, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.176556348800659, "global_step": 360871, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1210625171661377, "global_step": 360872, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.010702610015869, "global_step": 360873, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0484817028045654, "global_step": 360874, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.104114294052124, "global_step": 360875, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1982991695404053, "global_step": 360876, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.177025556564331, "global_step": 360877, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.056893825531006, "global_step": 360878, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.12176775932312, "global_step": 360879, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.154611825942993, "global_step": 360880, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0981318950653076, "global_step": 360881, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0309696197509766, "global_step": 360882, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0167462825775146, "global_step": 360883, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0729007720947266, "global_step": 360884, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.080782413482666, "global_step": 360885, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1477456092834473, "global_step": 360886, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2250816822052, "global_step": 360887, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.127869129180908, "global_step": 360888, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1658573150634766, "global_step": 360889, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.024395704269409, "global_step": 360890, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1489384174346924, "global_step": 360891, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.120260715484619, "global_step": 360892, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.091886281967163, "global_step": 360893, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.039123773574829, "global_step": 360894, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0793302059173584, "global_step": 360895, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.060577154159546, "global_step": 360896, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1401829719543457, "global_step": 360897, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1812033653259277, "global_step": 360898, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.040666341781616, "global_step": 360899, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1169371604919434, "global_step": 360900, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.109363317489624, "global_step": 360901, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1331615447998047, "global_step": 360902, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.19638991355896, "global_step": 360903, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1588144302368164, "global_step": 360904, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0382330417633057, "global_step": 360905, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.171562910079956, "global_step": 360906, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0690269470214844, "global_step": 360907, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0267410278320312, "global_step": 360908, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0953595638275146, "global_step": 360909, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0531771183013916, "global_step": 360910, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.065263271331787, "global_step": 360911, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1232879161834717, "global_step": 360912, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1158201694488525, "global_step": 360913, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1324422359466553, "global_step": 360914, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.124223470687866, "global_step": 360915, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1450862884521484, "global_step": 360916, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0903239250183105, "global_step": 360917, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.094332456588745, "global_step": 360918, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.181041717529297, "global_step": 360919, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0678741931915283, "global_step": 360920, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1302170753479004, "global_step": 360921, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0916149616241455, "global_step": 360922, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.213639259338379, "global_step": 360923, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1653029918670654, "global_step": 360924, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0737974643707275, "global_step": 360925, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.149442434310913, "global_step": 360926, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0887176990509033, "global_step": 360927, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.114502429962158, "global_step": 360928, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1136136054992676, "global_step": 360929, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.132537603378296, "global_step": 360930, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.082695245742798, "global_step": 360931, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0384533405303955, "global_step": 360932, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1059160232543945, "global_step": 360933, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.061669111251831, "global_step": 360934, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.081570625305176, "global_step": 360935, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.11649489402771, "global_step": 360936, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.159615993499756, "global_step": 360937, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0179033279418945, "global_step": 360938, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.141895055770874, "global_step": 360939, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1512370109558105, "global_step": 360940, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0524604320526123, "global_step": 360941, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.176791191101074, "global_step": 360942, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1187853813171387, "global_step": 360943, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1094043254852295, "global_step": 360944, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.114388942718506, "global_step": 360945, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.075124979019165, "global_step": 360946, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.053314685821533, "global_step": 360947, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.07194447517395, "global_step": 360948, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1968469619750977, "global_step": 360949, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0388360023498535, "global_step": 360950, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.181013345718384, "global_step": 360951, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2059473991394043, "global_step": 360952, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.088650703430176, "global_step": 360953, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1334409713745117, "global_step": 360954, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0952134132385254, "global_step": 360955, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1031033992767334, "global_step": 360956, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0401201248168945, "global_step": 360957, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1475989818573, "global_step": 360958, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.084663152694702, "global_step": 360959, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1234865188598633, "global_step": 360960, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1194629669189453, "global_step": 360961, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1165661811828613, "global_step": 360962, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0391392707824707, "global_step": 360963, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0949745178222656, "global_step": 360964, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1023526191711426, "global_step": 360965, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.113849639892578, "global_step": 360966, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0311217308044434, "global_step": 360967, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1057779788970947, "global_step": 360968, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.084970712661743, "global_step": 360969, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.082819938659668, "global_step": 360970, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.070580005645752, "global_step": 360971, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.068917989730835, "global_step": 360972, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0932657718658447, "global_step": 360973, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1203701496124268, "global_step": 360974, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.086700677871704, "global_step": 360975, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.135150194168091, "global_step": 360976, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.091153860092163, "global_step": 360977, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.014583110809326, "global_step": 360978, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1197726726531982, "global_step": 360979, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1479172706604004, "global_step": 360980, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.103485107421875, "global_step": 360981, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1189634799957275, "global_step": 360982, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.123387336730957, "global_step": 360983, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1206893920898438, "global_step": 360984, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2808456420898438, "global_step": 360985, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.182288408279419, "global_step": 360986, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.210453748703003, "global_step": 360987, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.111163854598999, "global_step": 360988, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0811121463775635, "global_step": 360989, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.131871223449707, "global_step": 360990, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0379555225372314, "global_step": 360991, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1556379795074463, "global_step": 360992, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0900516510009766, "global_step": 360993, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1619691848754883, "global_step": 360994, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.093494176864624, "global_step": 360995, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1271073818206787, "global_step": 360996, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1170904636383057, "global_step": 360997, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1502280235290527, "global_step": 360998, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0344741344451904, "global_step": 360999, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.144944429397583, "global_step": 361000, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.11624813079834, "global_step": 361001, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.061870574951172, "global_step": 361002, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1343955993652344, "global_step": 361003, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0786194801330566, "global_step": 361004, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1491031646728516, "global_step": 361005, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.045121431350708, "global_step": 361006, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.115088701248169, "global_step": 361007, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.012941360473633, "global_step": 361008, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0408051013946533, "global_step": 361009, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.087307929992676, "global_step": 361010, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1244466304779053, "global_step": 361011, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0426435470581055, "global_step": 361012, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.191452741622925, "global_step": 361013, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1216020584106445, "global_step": 361014, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0668160915374756, "global_step": 361015, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1332623958587646, "global_step": 361016, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1941592693328857, "global_step": 361017, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.14113450050354, "global_step": 361018, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.178560972213745, "global_step": 361019, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2181777954101562, "global_step": 361020, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.15165638923645, "global_step": 361021, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1107633113861084, "global_step": 361022, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.101193428039551, "global_step": 361023, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.21856689453125, "global_step": 361024, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1004865169525146, "global_step": 361025, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.082634687423706, "global_step": 361026, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1741745471954346, "global_step": 361027, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0819616317749023, "global_step": 361028, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1161324977874756, "global_step": 361029, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0435144901275635, "global_step": 361030, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.090378522872925, "global_step": 361031, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.094027519226074, "global_step": 361032, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.094451665878296, "global_step": 361033, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1290383338928223, "global_step": 361034, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0189852714538574, "global_step": 361035, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0690202713012695, "global_step": 361036, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.066448211669922, "global_step": 361037, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.138359546661377, "global_step": 361038, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1326417922973633, "global_step": 361039, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.171505928039551, "global_step": 361040, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0564470291137695, "global_step": 361041, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.023013114929199, "global_step": 361042, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.039280652999878, "global_step": 361043, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.096949577331543, "global_step": 361044, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.070061683654785, "global_step": 361045, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0633351802825928, "global_step": 361046, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1568939685821533, "global_step": 361047, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.108196258544922, "global_step": 361048, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.095954418182373, "global_step": 361049, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1137795448303223, "global_step": 361050, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1395256519317627, "global_step": 361051, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1744792461395264, "global_step": 361052, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.104626178741455, "global_step": 361053, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1362829208374023, "global_step": 361054, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0304949283599854, "global_step": 361055, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.151916742324829, "global_step": 361056, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.175144672393799, "global_step": 361057, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.112382650375366, "global_step": 361058, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1233069896698, "global_step": 361059, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.111868143081665, "global_step": 361060, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.115424394607544, "global_step": 361061, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1721386909484863, "global_step": 361062, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.116284132003784, "global_step": 361063, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1072568893432617, "global_step": 361064, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.141914129257202, "global_step": 361065, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1927144527435303, "global_step": 361066, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0327186584472656, "global_step": 361067, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1481475830078125, "global_step": 361068, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1005284786224365, "global_step": 361069, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0936238765716553, "global_step": 361070, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0572659969329834, "global_step": 361071, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0258073806762695, "global_step": 361072, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.094571828842163, "global_step": 361073, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0916309356689453, "global_step": 361074, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2099761962890625, "global_step": 361075, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0904123783111572, "global_step": 361076, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1034634113311768, "global_step": 361077, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.119169235229492, "global_step": 361078, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0961878299713135, "global_step": 361079, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.140995740890503, "global_step": 361080, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.118002414703369, "global_step": 361081, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.101430654525757, "global_step": 361082, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1189866065979004, "global_step": 361083, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0715980529785156, "global_step": 361084, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.164093494415283, "global_step": 361085, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0954723358154297, "global_step": 361086, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0996079444885254, "global_step": 361087, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.164027690887451, "global_step": 361088, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1317880153656006, "global_step": 361089, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.082958698272705, "global_step": 361090, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1347789764404297, "global_step": 361091, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.116865873336792, "global_step": 361092, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.168292760848999, "global_step": 361093, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0528910160064697, "global_step": 361094, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.137091636657715, "global_step": 361095, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1163835525512695, "global_step": 361096, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1011717319488525, "global_step": 361097, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1291213035583496, "global_step": 361098, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2404675483703613, "global_step": 361099, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.10538387298584, "global_step": 361100, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.147522449493408, "global_step": 361101, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1462109088897705, "global_step": 361102, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.071565628051758, "global_step": 361103, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0372138023376465, "global_step": 361104, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1998236179351807, "global_step": 361105, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2168710231781006, "global_step": 361106, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.116966724395752, "global_step": 361107, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0232093334198, "global_step": 361108, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0272469520568848, "global_step": 361109, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1433372497558594, "global_step": 361110, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1511802673339844, "global_step": 361111, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.097428560256958, "global_step": 361112, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.208326816558838, "global_step": 361113, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1975061893463135, "global_step": 361114, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1198370456695557, "global_step": 361115, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1816225051879883, "global_step": 361116, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1013736724853516, "global_step": 361117, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.051351547241211, "global_step": 361118, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.139265298843384, "global_step": 361119, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0383598804473877, "global_step": 361120, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0753934383392334, "global_step": 361121, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1378040313720703, "global_step": 361122, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.036078691482544, "global_step": 361123, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1115972995758057, "global_step": 361124, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0772929191589355, "global_step": 361125, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1153757572174072, "global_step": 361126, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.030362606048584, "global_step": 361127, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.108306646347046, "global_step": 361128, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.148684024810791, "global_step": 361129, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1235220432281494, "global_step": 361130, "epoch": 722, "lr": 5e-05}
{"train_loss": 1.9773529767990112, "global_step": 361131, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0213046073913574, "global_step": 361132, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.093142509460449, "global_step": 361133, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0392019748687744, "global_step": 361134, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0657882690429688, "global_step": 361135, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.108377456665039, "global_step": 361136, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.140110731124878, "global_step": 361137, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0805211067199707, "global_step": 361138, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1282689571380615, "global_step": 361139, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.138622522354126, "global_step": 361140, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.060704231262207, "global_step": 361141, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.176128625869751, "global_step": 361142, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.119473934173584, "global_step": 361143, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0620975494384766, "global_step": 361144, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.107470989227295, "global_step": 361145, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0188381671905518, "global_step": 361146, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1394846439361572, "global_step": 361147, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.14892578125, "global_step": 361148, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.139007806777954, "global_step": 361149, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0854978561401367, "global_step": 361150, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1723129749298096, "global_step": 361151, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1250898838043213, "global_step": 361152, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0956780910491943, "global_step": 361153, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.027649164199829, "global_step": 361154, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1330363750457764, "global_step": 361155, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0971450805664062, "global_step": 361156, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.030033588409424, "global_step": 361157, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.092761278152466, "global_step": 361158, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1267733573913574, "global_step": 361159, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.109095811843872, "global_step": 361160, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1885488033294678, "global_step": 361161, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1230788230895996, "global_step": 361162, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2575278282165527, "global_step": 361163, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1136791706085205, "global_step": 361164, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1958231925964355, "global_step": 361165, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1043150424957275, "global_step": 361166, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.150949239730835, "global_step": 361167, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1402652263641357, "global_step": 361168, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.107612371444702, "global_step": 361169, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1425652503967285, "global_step": 361170, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.180270195007324, "global_step": 361171, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.147907018661499, "global_step": 361172, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0312347412109375, "global_step": 361173, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.121445894241333, "global_step": 361174, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1952481269836426, "global_step": 361175, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.188953161239624, "global_step": 361176, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.092133045196533, "global_step": 361177, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1430015563964844, "global_step": 361178, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.095404863357544, "global_step": 361179, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1057329177856445, "global_step": 361180, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.06791615486145, "global_step": 361181, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.123720645904541, "global_step": 361182, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.140132188796997, "global_step": 361183, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0792198181152344, "global_step": 361184, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2556755542755127, "global_step": 361185, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.078596591949463, "global_step": 361186, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.054332733154297, "global_step": 361187, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0358376502990723, "global_step": 361188, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.178743600845337, "global_step": 361189, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.06382155418396, "global_step": 361190, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0038297176361084, "global_step": 361191, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0739917755126953, "global_step": 361192, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1786553859710693, "global_step": 361193, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1090846061706543, "global_step": 361194, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1524758338928223, "global_step": 361195, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0694072246551514, "global_step": 361196, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0418756008148193, "global_step": 361197, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0421969890594482, "global_step": 361198, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.060608386993408, "global_step": 361199, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0513110160827637, "global_step": 361200, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.073415756225586, "global_step": 361201, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1255381107330322, "global_step": 361202, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1314733028411865, "global_step": 361203, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.190917491912842, "global_step": 361204, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.056908369064331, "global_step": 361205, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.119847297668457, "global_step": 361206, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.100861072540283, "global_step": 361207, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.146696090698242, "global_step": 361208, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.102238893508911, "global_step": 361209, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0887081623077393, "global_step": 361210, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.199387550354004, "global_step": 361211, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.150665760040283, "global_step": 361212, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.065077304840088, "global_step": 361213, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0610203742980957, "global_step": 361214, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.032254695892334, "global_step": 361215, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1682634353637695, "global_step": 361216, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0878775119781494, "global_step": 361217, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0391151905059814, "global_step": 361218, "epoch": 722, "lr": 5e-05}
{"train_loss": 1.9772796630859375, "global_step": 361219, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.193380117416382, "global_step": 361220, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0786025524139404, "global_step": 361221, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1407902240753174, "global_step": 361222, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0799005031585693, "global_step": 361223, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0677218437194824, "global_step": 361224, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.123687505722046, "global_step": 361225, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1155035495758057, "global_step": 361226, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1259098052978516, "global_step": 361227, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.074420928955078, "global_step": 361228, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1151175498962402, "global_step": 361229, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.169005870819092, "global_step": 361230, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0851690769195557, "global_step": 361231, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.067859649658203, "global_step": 361232, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.125084161758423, "global_step": 361233, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1589667797088623, "global_step": 361234, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1113429069519043, "global_step": 361235, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.18034029006958, "global_step": 361236, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0863637924194336, "global_step": 361237, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.066272020339966, "global_step": 361238, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.112036943435669, "global_step": 361239, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1733624935150146, "global_step": 361240, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0937891006469727, "global_step": 361241, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0676772594451904, "global_step": 361242, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.119668483734131, "global_step": 361243, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1180648803710938, "global_step": 361244, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0725364685058594, "global_step": 361245, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.029648542404175, "global_step": 361246, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0564982891082764, "global_step": 361247, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.101846218109131, "global_step": 361248, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.131786823272705, "global_step": 361249, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.096057415008545, "global_step": 361250, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.138768434524536, "global_step": 361251, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.06006121635437, "global_step": 361252, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1634249687194824, "global_step": 361253, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.147118091583252, "global_step": 361254, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0561277866363525, "global_step": 361255, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0801241397857666, "global_step": 361256, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.147310972213745, "global_step": 361257, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0251002311706543, "global_step": 361258, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1206490993499756, "global_step": 361259, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0966978073120117, "global_step": 361260, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.123422861099243, "global_step": 361261, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0547335147857666, "global_step": 361262, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1516647338867188, "global_step": 361263, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1140012741088867, "global_step": 361264, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.01271653175354, "global_step": 361265, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0971226692199707, "global_step": 361266, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1780483722686768, "global_step": 361267, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1653106212615967, "global_step": 361268, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.138328790664673, "global_step": 361269, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.101757049560547, "global_step": 361270, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.17177677154541, "global_step": 361271, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1564977169036865, "global_step": 361272, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1297178268432617, "global_step": 361273, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1189205646514893, "global_step": 361274, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0997366905212402, "global_step": 361275, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.106998920440674, "global_step": 361276, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0980708599090576, "global_step": 361277, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2016024589538574, "global_step": 361278, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1039509773254395, "global_step": 361279, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.124547243118286, "global_step": 361280, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1088929176330566, "global_step": 361281, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1116106510162354, "global_step": 361282, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1388885974884033, "global_step": 361283, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.148190975189209, "global_step": 361284, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.013627052307129, "global_step": 361285, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1487183570861816, "global_step": 361286, "epoch": 722, "lr": 5e-05}
{"train_loss": 1.9732006788253784, "global_step": 361287, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2089359760284424, "global_step": 361288, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2983920574188232, "global_step": 361289, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1203649044036865, "global_step": 361290, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1183769702911377, "global_step": 361291, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1683144569396973, "global_step": 361292, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0997471809387207, "global_step": 361293, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.102538585662842, "global_step": 361294, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1716926097869873, "global_step": 361295, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.105659246444702, "global_step": 361296, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2158749103546143, "global_step": 361297, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0979185104370117, "global_step": 361298, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.185072183609009, "global_step": 361299, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.171586036682129, "global_step": 361300, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.091611623764038, "global_step": 361301, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.155241012573242, "global_step": 361302, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1071953773498535, "global_step": 361303, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.104810953140259, "global_step": 361304, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.098388910293579, "global_step": 361305, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1726455688476562, "global_step": 361306, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.146416664123535, "global_step": 361307, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1238133907318115, "global_step": 361308, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.179656744003296, "global_step": 361309, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0647614002227783, "global_step": 361310, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.079798698425293, "global_step": 361311, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.140061855316162, "global_step": 361312, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1201131343841553, "global_step": 361313, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.009878158569336, "global_step": 361314, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0907535552978516, "global_step": 361315, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0673446655273438, "global_step": 361316, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.12363600730896, "global_step": 361317, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.082371473312378, "global_step": 361318, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0518641471862793, "global_step": 361319, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.15478777885437, "global_step": 361320, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1801860332489014, "global_step": 361321, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1763439178466797, "global_step": 361322, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1030986309051514, "global_step": 361323, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.029076337814331, "global_step": 361324, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.100234031677246, "global_step": 361325, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0898866653442383, "global_step": 361326, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.12321400642395, "global_step": 361327, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.149080991744995, "global_step": 361328, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.061408281326294, "global_step": 361329, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.09312105178833, "global_step": 361330, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.093351125717163, "global_step": 361331, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0593767166137695, "global_step": 361332, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0364294052124023, "global_step": 361333, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1206653118133545, "global_step": 361334, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.135760545730591, "global_step": 361335, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0838868618011475, "global_step": 361336, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1552700996398926, "global_step": 361337, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.168785333633423, "global_step": 361338, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.090017080307007, "global_step": 361339, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.028562307357788, "global_step": 361340, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.128413438796997, "global_step": 361341, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1648330688476562, "global_step": 361342, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.144714832305908, "global_step": 361343, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0993733406066895, "global_step": 361344, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0368924140930176, "global_step": 361345, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.130427837371826, "global_step": 361346, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.191965103149414, "global_step": 361347, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.106165885925293, "global_step": 361348, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1344752311706543, "global_step": 361349, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0970942974090576, "global_step": 361350, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0505385398864746, "global_step": 361351, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2489306926727295, "global_step": 361352, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.168180227279663, "global_step": 361353, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.089092493057251, "global_step": 361354, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.118678569793701, "global_step": 361355, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1117136478424072, "global_step": 361356, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.04839825630188, "global_step": 361357, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0654845237731934, "global_step": 361358, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0946357250213623, "global_step": 361359, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1268489360809326, "global_step": 361360, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1045453548431396, "global_step": 361361, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0831985473632812, "global_step": 361362, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1449997425079346, "global_step": 361363, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.213510036468506, "global_step": 361364, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1737864017486572, "global_step": 361365, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1719155311584473, "global_step": 361366, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.038222312927246, "global_step": 361367, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.137726306915283, "global_step": 361368, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2125403881073, "global_step": 361369, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0639169216156006, "global_step": 361370, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1542489528656006, "global_step": 361371, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1316442489624023, "global_step": 361372, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0081677436828613, "global_step": 361373, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.044854164123535, "global_step": 361374, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.206415891647339, "global_step": 361375, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.20973539352417, "global_step": 361376, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.144937038421631, "global_step": 361377, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.114121198654175, "global_step": 361378, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0733413696289062, "global_step": 361379, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.137834072113037, "global_step": 361380, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1166558265686035, "global_step": 361381, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1143991947174072, "global_step": 361382, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.088996171951294, "global_step": 361383, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.161428213119507, "global_step": 361384, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0693955421447754, "global_step": 361385, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0645337104797363, "global_step": 361386, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.062494993209839, "global_step": 361387, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1011977195739746, "global_step": 361388, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.195775270462036, "global_step": 361389, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.096121311187744, "global_step": 361390, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1176187992095947, "global_step": 361391, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.10461163520813, "global_step": 361392, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.089399576187134, "global_step": 361393, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0380847454071045, "global_step": 361394, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1025338172912598, "global_step": 361395, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0741701126098633, "global_step": 361396, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1499035358428955, "global_step": 361397, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.085510730743408, "global_step": 361398, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0499954223632812, "global_step": 361399, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0873866081237793, "global_step": 361400, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1437807083129883, "global_step": 361401, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.060563087463379, "global_step": 361402, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1701178550720215, "global_step": 361403, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1177849769592285, "global_step": 361404, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0543928146362305, "global_step": 361405, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.129854917526245, "global_step": 361406, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1290934085845947, "global_step": 361407, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1589303016662598, "global_step": 361408, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.162024736404419, "global_step": 361409, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.189460039138794, "global_step": 361410, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1653339862823486, "global_step": 361411, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0897200107574463, "global_step": 361412, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1422653198242188, "global_step": 361413, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.181798219680786, "global_step": 361414, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.126678466796875, "global_step": 361415, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0951766967773438, "global_step": 361416, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.031619071960449, "global_step": 361417, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.173191547393799, "global_step": 361418, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0304086208343506, "global_step": 361419, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.192356824874878, "global_step": 361420, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.11834979057312, "global_step": 361421, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1295599937438965, "global_step": 361422, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.09891939163208, "global_step": 361423, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.171682834625244, "global_step": 361424, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0642659664154053, "global_step": 361425, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0137410163879395, "global_step": 361426, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1652159690856934, "global_step": 361427, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1551661491394043, "global_step": 361428, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0547261238098145, "global_step": 361429, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1456875801086426, "global_step": 361430, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.113694906234741, "global_step": 361431, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1003847122192383, "global_step": 361432, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.104782819747925, "global_step": 361433, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.13057279586792, "global_step": 361434, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1342430114746094, "global_step": 361435, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1604185104370117, "global_step": 361436, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.062248706817627, "global_step": 361437, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1096479892730713, "global_step": 361438, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.149348020553589, "global_step": 361439, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1493759155273438, "global_step": 361440, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0586469173431396, "global_step": 361441, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.116888999938965, "global_step": 361442, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0536062717437744, "global_step": 361443, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.050314426422119, "global_step": 361444, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1095497608184814, "global_step": 361445, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1320042610168457, "global_step": 361446, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1496148109436035, "global_step": 361447, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2216172218322754, "global_step": 361448, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1135504245758057, "global_step": 361449, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0392420291900635, "global_step": 361450, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1337811946868896, "global_step": 361451, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.134044885635376, "global_step": 361452, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.049889326095581, "global_step": 361453, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1257476806640625, "global_step": 361454, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.177891492843628, "global_step": 361455, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1623175144195557, "global_step": 361456, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.145681858062744, "global_step": 361457, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1687660217285156, "global_step": 361458, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1069676876068115, "global_step": 361459, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2065093517303467, "global_step": 361460, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.144535779953003, "global_step": 361461, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1263132095336914, "global_step": 361462, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0473663806915283, "global_step": 361463, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1660995483398438, "global_step": 361464, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.107935905456543, "global_step": 361465, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1731185913085938, "global_step": 361466, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1059348583221436, "global_step": 361467, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1923024654388428, "global_step": 361468, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.124593734741211, "global_step": 361469, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1180267333984375, "global_step": 361470, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.074126958847046, "global_step": 361471, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1034388542175293, "global_step": 361472, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.049499034881592, "global_step": 361473, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.016674280166626, "global_step": 361474, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.10565447807312, "global_step": 361475, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.170687675476074, "global_step": 361476, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0787103176116943, "global_step": 361477, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0658044815063477, "global_step": 361478, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1133296489715576, "global_step": 361479, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0403552055358887, "global_step": 361480, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.151468276977539, "global_step": 361481, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.138716697692871, "global_step": 361482, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.109529972076416, "global_step": 361483, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1180977821350098, "global_step": 361484, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.084941864013672, "global_step": 361485, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.094311237335205, "global_step": 361486, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0896730422973633, "global_step": 361487, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.125873565673828, "global_step": 361488, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1047000885009766, "global_step": 361489, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.052788496017456, "global_step": 361490, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1511809825897217, "global_step": 361491, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0931246280670166, "global_step": 361492, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1583147048950195, "global_step": 361493, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1341662406921387, "global_step": 361494, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1181416511535645, "global_step": 361495, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0710997581481934, "global_step": 361496, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.174403667449951, "global_step": 361497, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1326005458831787, "global_step": 361498, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1715660095214844, "global_step": 361499, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1284515857696533, "global_step": 361500, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.152923822402954, "global_step": 361501, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.110950469970703, "global_step": 361502, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.125784158706665, "global_step": 361503, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1584625244140625, "global_step": 361504, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1424553394317627, "global_step": 361505, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.117215156555176, "global_step": 361506, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.124328374862671, "global_step": 361507, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0480027198791504, "global_step": 361508, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0854716300964355, "global_step": 361509, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.086343765258789, "global_step": 361510, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.112781047821045, "global_step": 361511, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.143519401550293, "global_step": 361512, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.157335042953491, "global_step": 361513, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1345343589782715, "global_step": 361514, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1205921173095703, "global_step": 361515, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.05625581741333, "global_step": 361516, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1053965091705322, "global_step": 361517, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0430543422698975, "global_step": 361518, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1679933071136475, "global_step": 361519, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0905065536499023, "global_step": 361520, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.125199794769287, "global_step": 361521, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.115504026412964, "global_step": 361522, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.041205406188965, "global_step": 361523, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0728654861450195, "global_step": 361524, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.070620536804199, "global_step": 361525, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0991628170013428, "global_step": 361526, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.127161979675293, "global_step": 361527, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1071410179138184, "global_step": 361528, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0625808238983154, "global_step": 361529, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1500227451324463, "global_step": 361530, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2739787101745605, "global_step": 361531, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.090528964996338, "global_step": 361532, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.166485071182251, "global_step": 361533, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0628652572631836, "global_step": 361534, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.118826389312744, "global_step": 361535, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1557555198669434, "global_step": 361536, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1490283012390137, "global_step": 361537, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.171886444091797, "global_step": 361538, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1109464168548584, "global_step": 361539, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.2180705070495605, "global_step": 361540, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0297210216522217, "global_step": 361541, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1252501010894775, "global_step": 361542, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1461181640625, "global_step": 361543, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.075286865234375, "global_step": 361544, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1161389350891113, "global_step": 361545, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.055131196975708, "global_step": 361546, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.175553321838379, "global_step": 361547, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.066612720489502, "global_step": 361548, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1273794174194336, "global_step": 361549, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1569392681121826, "global_step": 361550, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0262904167175293, "global_step": 361551, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.172380208969116, "global_step": 361552, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.128720283508301, "global_step": 361553, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.062671184539795, "global_step": 361554, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.040235996246338, "global_step": 361555, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.052966356277466, "global_step": 361556, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1268129348754883, "global_step": 361557, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1119742393493652, "global_step": 361558, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.042153835296631, "global_step": 361559, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.045125961303711, "global_step": 361560, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0915374755859375, "global_step": 361561, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0526890754699707, "global_step": 361562, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.250730514526367, "global_step": 361563, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.074950695037842, "global_step": 361564, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.113757848739624, "global_step": 361565, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1573238372802734, "global_step": 361566, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.074047565460205, "global_step": 361567, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0055243968963623, "global_step": 361568, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.1092851161956787, "global_step": 361569, "epoch": 722, "lr": 5e-05}
{"train_loss": 2.0557546615600586, "global_step": 361570, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0693540573120117, "global_step": 361571, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1263904571533203, "global_step": 361572, "epoch": 723, "lr": 5e-05}
{"train_loss": 1.982965111732483, "global_step": 361573, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.2020816802978516, "global_step": 361574, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0331482887268066, "global_step": 361575, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0098795890808105, "global_step": 361576, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0756494998931885, "global_step": 361577, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.158877372741699, "global_step": 361578, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.057349443435669, "global_step": 361579, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.169283628463745, "global_step": 361580, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.096925973892212, "global_step": 361581, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1528122425079346, "global_step": 361582, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0938796997070312, "global_step": 361583, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.051313877105713, "global_step": 361584, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.052403688430786, "global_step": 361585, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0994904041290283, "global_step": 361586, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0413267612457275, "global_step": 361587, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0044665336608887, "global_step": 361588, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0272350311279297, "global_step": 361589, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.060338258743286, "global_step": 361590, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.138753890991211, "global_step": 361591, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.085437774658203, "global_step": 361592, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.162562370300293, "global_step": 361593, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1030187606811523, "global_step": 361594, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0920116901397705, "global_step": 361595, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.126420497894287, "global_step": 361596, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1027333736419678, "global_step": 361597, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0825061798095703, "global_step": 361598, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0946080684661865, "global_step": 361599, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0642995834350586, "global_step": 361600, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1349258422851562, "global_step": 361601, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.2022225856781006, "global_step": 361602, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.119915723800659, "global_step": 361603, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1066627502441406, "global_step": 361604, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0886895656585693, "global_step": 361605, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1064062118530273, "global_step": 361606, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.156306028366089, "global_step": 361607, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1511011123657227, "global_step": 361608, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0677483081817627, "global_step": 361609, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.168958902359009, "global_step": 361610, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.103057384490967, "global_step": 361611, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0814785957336426, "global_step": 361612, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.093940258026123, "global_step": 361613, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.083191394805908, "global_step": 361614, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0901901721954346, "global_step": 361615, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0161232948303223, "global_step": 361616, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.096831798553467, "global_step": 361617, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.163367986679077, "global_step": 361618, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1052446365356445, "global_step": 361619, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0441226959228516, "global_step": 361620, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1552577018737793, "global_step": 361621, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.162290096282959, "global_step": 361622, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.09679913520813, "global_step": 361623, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.046452522277832, "global_step": 361624, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0129544734954834, "global_step": 361625, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0596978664398193, "global_step": 361626, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0522947311401367, "global_step": 361627, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0827059745788574, "global_step": 361628, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0772898197174072, "global_step": 361629, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.015623092651367, "global_step": 361630, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0487372875213623, "global_step": 361631, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0473875999450684, "global_step": 361632, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.089491128921509, "global_step": 361633, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0637311935424805, "global_step": 361634, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0992512702941895, "global_step": 361635, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0620317459106445, "global_step": 361636, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1515371799468994, "global_step": 361637, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.2036685943603516, "global_step": 361638, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.062760591506958, "global_step": 361639, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1416430473327637, "global_step": 361640, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.066956043243408, "global_step": 361641, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1457130908966064, "global_step": 361642, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.038393497467041, "global_step": 361643, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1082987785339355, "global_step": 361644, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.049858808517456, "global_step": 361645, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0716538429260254, "global_step": 361646, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0424253940582275, "global_step": 361647, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.058687686920166, "global_step": 361648, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.099137783050537, "global_step": 361649, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0053024291992188, "global_step": 361650, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1079037189483643, "global_step": 361651, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0646770000457764, "global_step": 361652, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1489055156707764, "global_step": 361653, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.104865074157715, "global_step": 361654, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.164323091506958, "global_step": 361655, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1518452167510986, "global_step": 361656, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0550544261932373, "global_step": 361657, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0501461029052734, "global_step": 361658, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.072115182876587, "global_step": 361659, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1099302768707275, "global_step": 361660, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0502984523773193, "global_step": 361661, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.176452398300171, "global_step": 361662, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.082371473312378, "global_step": 361663, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.058445453643799, "global_step": 361664, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.122018575668335, "global_step": 361665, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.098787307739258, "global_step": 361666, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.050694465637207, "global_step": 361667, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.117075204849243, "global_step": 361668, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0673983097076416, "global_step": 361669, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1349241733551025, "global_step": 361670, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0985310077667236, "global_step": 361671, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1722259521484375, "global_step": 361672, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.097271680831909, "global_step": 361673, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1607325077056885, "global_step": 361674, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1240079402923584, "global_step": 361675, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.181718111038208, "global_step": 361676, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.144017219543457, "global_step": 361677, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1478188037872314, "global_step": 361678, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0852646827697754, "global_step": 361679, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1153411865234375, "global_step": 361680, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.227921962738037, "global_step": 361681, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1636180877685547, "global_step": 361682, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1513938903808594, "global_step": 361683, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1852235794067383, "global_step": 361684, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0576529502868652, "global_step": 361685, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.119626522064209, "global_step": 361686, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1431407928466797, "global_step": 361687, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0248820781707764, "global_step": 361688, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0078353881835938, "global_step": 361689, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.096890449523926, "global_step": 361690, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0922799110412598, "global_step": 361691, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0768604278564453, "global_step": 361692, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.107050895690918, "global_step": 361693, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1513876914978027, "global_step": 361694, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.143507480621338, "global_step": 361695, "epoch": 723, "lr": 5e-05}
{"train_loss": 1.9966647624969482, "global_step": 361696, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0269579887390137, "global_step": 361697, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.105499267578125, "global_step": 361698, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.119112014770508, "global_step": 361699, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.005586624145508, "global_step": 361700, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.041147232055664, "global_step": 361701, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.123588800430298, "global_step": 361702, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.112130880355835, "global_step": 361703, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.102339267730713, "global_step": 361704, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.112210750579834, "global_step": 361705, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0181310176849365, "global_step": 361706, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1041462421417236, "global_step": 361707, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0587449073791504, "global_step": 361708, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.067880630493164, "global_step": 361709, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.152655839920044, "global_step": 361710, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.036625385284424, "global_step": 361711, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.2427480220794678, "global_step": 361712, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.089818000793457, "global_step": 361713, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0893335342407227, "global_step": 361714, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0964274406433105, "global_step": 361715, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.159289598464966, "global_step": 361716, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0802412033081055, "global_step": 361717, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1329381465911865, "global_step": 361718, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0264170169830322, "global_step": 361719, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0536274909973145, "global_step": 361720, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.21610426902771, "global_step": 361721, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.148205041885376, "global_step": 361722, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0371172428131104, "global_step": 361723, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0949418544769287, "global_step": 361724, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.129222869873047, "global_step": 361725, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.043372869491577, "global_step": 361726, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0489888191223145, "global_step": 361727, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.060577869415283, "global_step": 361728, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0939698219299316, "global_step": 361729, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1269843578338623, "global_step": 361730, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0787463188171387, "global_step": 361731, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1663224697113037, "global_step": 361732, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.2298941612243652, "global_step": 361733, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.153451442718506, "global_step": 361734, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.116250991821289, "global_step": 361735, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.193080186843872, "global_step": 361736, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0675570964813232, "global_step": 361737, "epoch": 723, "lr": 5e-05}
{"train_loss": 1.984273076057434, "global_step": 361738, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0812857151031494, "global_step": 361739, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.137357473373413, "global_step": 361740, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1156585216522217, "global_step": 361741, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1689248085021973, "global_step": 361742, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1791558265686035, "global_step": 361743, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1026885509490967, "global_step": 361744, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1702396869659424, "global_step": 361745, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0580854415893555, "global_step": 361746, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1294870376586914, "global_step": 361747, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0536177158355713, "global_step": 361748, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0270256996154785, "global_step": 361749, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.130387544631958, "global_step": 361750, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.099144697189331, "global_step": 361751, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1809303760528564, "global_step": 361752, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1523873805999756, "global_step": 361753, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0462286472320557, "global_step": 361754, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.092308521270752, "global_step": 361755, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0442068576812744, "global_step": 361756, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0647480487823486, "global_step": 361757, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.150725841522217, "global_step": 361758, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1010308265686035, "global_step": 361759, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.137657642364502, "global_step": 361760, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.222527265548706, "global_step": 361761, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1232106685638428, "global_step": 361762, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1428542137145996, "global_step": 361763, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.058166980743408, "global_step": 361764, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.215075969696045, "global_step": 361765, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1879067420959473, "global_step": 361766, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.105578899383545, "global_step": 361767, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0694167613983154, "global_step": 361768, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.074227809906006, "global_step": 361769, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1008191108703613, "global_step": 361770, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0934979915618896, "global_step": 361771, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1087183952331543, "global_step": 361772, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1595330238342285, "global_step": 361773, "epoch": 723, "lr": 5e-05}
{"train_loss": 1.9611424207687378, "global_step": 361774, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.110213041305542, "global_step": 361775, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1240737438201904, "global_step": 361776, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.123589038848877, "global_step": 361777, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.065335273742676, "global_step": 361778, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.043654680252075, "global_step": 361779, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0798144340515137, "global_step": 361780, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.099079132080078, "global_step": 361781, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0712711811065674, "global_step": 361782, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.220668077468872, "global_step": 361783, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1929237842559814, "global_step": 361784, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1465864181518555, "global_step": 361785, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1471030712127686, "global_step": 361786, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.087470531463623, "global_step": 361787, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1911559104919434, "global_step": 361788, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.091845750808716, "global_step": 361789, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.169652223587036, "global_step": 361790, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.2030770778656006, "global_step": 361791, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0482447147369385, "global_step": 361792, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1793363094329834, "global_step": 361793, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.184921979904175, "global_step": 361794, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0475573539733887, "global_step": 361795, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.066936731338501, "global_step": 361796, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0956332683563232, "global_step": 361797, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.217303514480591, "global_step": 361798, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.130648612976074, "global_step": 361799, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1480553150177, "global_step": 361800, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.12052059173584, "global_step": 361801, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.135481834411621, "global_step": 361802, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.105393171310425, "global_step": 361803, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.089155435562134, "global_step": 361804, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0827176570892334, "global_step": 361805, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0342495441436768, "global_step": 361806, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1242642402648926, "global_step": 361807, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.115913152694702, "global_step": 361808, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1229772567749023, "global_step": 361809, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0447897911071777, "global_step": 361810, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0259249210357666, "global_step": 361811, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.053514242172241, "global_step": 361812, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0726306438446045, "global_step": 361813, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.095168113708496, "global_step": 361814, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.118091106414795, "global_step": 361815, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.2027251720428467, "global_step": 361816, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1768648624420166, "global_step": 361817, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.096635580062866, "global_step": 361818, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.056020736694336, "global_step": 361819, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1383755207061768, "global_step": 361820, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1023998260498047, "global_step": 361821, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.146678924560547, "global_step": 361822, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.146054983139038, "global_step": 361823, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0577759742736816, "global_step": 361824, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.09553861618042, "global_step": 361825, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.158339500427246, "global_step": 361826, "epoch": 723, "lr": 5e-05}
{"train_loss": 1.9825458526611328, "global_step": 361827, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1404712200164795, "global_step": 361828, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0427844524383545, "global_step": 361829, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1643452644348145, "global_step": 361830, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.10648512840271, "global_step": 361831, "epoch": 723, "lr": 5e-05}
{"train_loss": 1.983813762664795, "global_step": 361832, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1211984157562256, "global_step": 361833, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0725369453430176, "global_step": 361834, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.138936996459961, "global_step": 361835, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1178717613220215, "global_step": 361836, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1450018882751465, "global_step": 361837, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1947309970855713, "global_step": 361838, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0653505325317383, "global_step": 361839, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1351470947265625, "global_step": 361840, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1725175380706787, "global_step": 361841, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0885324478149414, "global_step": 361842, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0595037937164307, "global_step": 361843, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1764755249023438, "global_step": 361844, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0714774131774902, "global_step": 361845, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0730538368225098, "global_step": 361846, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0637879371643066, "global_step": 361847, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0230281352996826, "global_step": 361848, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1812469959259033, "global_step": 361849, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.049532651901245, "global_step": 361850, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.074493169784546, "global_step": 361851, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0059993267059326, "global_step": 361852, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.13828182220459, "global_step": 361853, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.133845806121826, "global_step": 361854, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0967905521392822, "global_step": 361855, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0922985076904297, "global_step": 361856, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1272571086883545, "global_step": 361857, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.140246868133545, "global_step": 361858, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.113399028778076, "global_step": 361859, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1546061038970947, "global_step": 361860, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.176694393157959, "global_step": 361861, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.055140733718872, "global_step": 361862, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.040985107421875, "global_step": 361863, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0876989364624023, "global_step": 361864, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.054274559020996, "global_step": 361865, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1480486392974854, "global_step": 361866, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0327649116516113, "global_step": 361867, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0849223136901855, "global_step": 361868, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.170541763305664, "global_step": 361869, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0953640937805176, "global_step": 361870, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.092662811279297, "global_step": 361871, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.069389581680298, "global_step": 361872, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1274220943450928, "global_step": 361873, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.082190752029419, "global_step": 361874, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.212495803833008, "global_step": 361875, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1944518089294434, "global_step": 361876, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1335973739624023, "global_step": 361877, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.021188259124756, "global_step": 361878, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1304824352264404, "global_step": 361879, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0365750789642334, "global_step": 361880, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.070664882659912, "global_step": 361881, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.029726982116699, "global_step": 361882, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.144718885421753, "global_step": 361883, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0525286197662354, "global_step": 361884, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0864386558532715, "global_step": 361885, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1031079292297363, "global_step": 361886, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0500223636627197, "global_step": 361887, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0404107570648193, "global_step": 361888, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.144127130508423, "global_step": 361889, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1123244762420654, "global_step": 361890, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.173340320587158, "global_step": 361891, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.215142250061035, "global_step": 361892, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0544512271881104, "global_step": 361893, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0438075065612793, "global_step": 361894, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1827707290649414, "global_step": 361895, "epoch": 723, "lr": 5e-05}
{"train_loss": 1.984702706336975, "global_step": 361896, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1219866275787354, "global_step": 361897, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.078704595565796, "global_step": 361898, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1200454235076904, "global_step": 361899, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.087747812271118, "global_step": 361900, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.057551622390747, "global_step": 361901, "epoch": 723, "lr": 5e-05}
{"train_loss": 1.9993489980697632, "global_step": 361902, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.030745506286621, "global_step": 361903, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1678287982940674, "global_step": 361904, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1253936290740967, "global_step": 361905, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.152602195739746, "global_step": 361906, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1667115688323975, "global_step": 361907, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1807875633239746, "global_step": 361908, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.155831813812256, "global_step": 361909, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.117344856262207, "global_step": 361910, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0615339279174805, "global_step": 361911, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1616275310516357, "global_step": 361912, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.121453285217285, "global_step": 361913, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.093424081802368, "global_step": 361914, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1178557872772217, "global_step": 361915, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1382787227630615, "global_step": 361916, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0262038707733154, "global_step": 361917, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.12608003616333, "global_step": 361918, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0149142742156982, "global_step": 361919, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0972113609313965, "global_step": 361920, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.11991548538208, "global_step": 361921, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.107758045196533, "global_step": 361922, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.201160192489624, "global_step": 361923, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.152956962585449, "global_step": 361924, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.112545967102051, "global_step": 361925, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0923995971679688, "global_step": 361926, "epoch": 723, "lr": 5e-05}
{"train_loss": 1.9941567182540894, "global_step": 361927, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.180036783218384, "global_step": 361928, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1460959911346436, "global_step": 361929, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.076972246170044, "global_step": 361930, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.185818910598755, "global_step": 361931, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1571693420410156, "global_step": 361932, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.044835329055786, "global_step": 361933, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.075993299484253, "global_step": 361934, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1177170276641846, "global_step": 361935, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1332578659057617, "global_step": 361936, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0648672580718994, "global_step": 361937, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.075275182723999, "global_step": 361938, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0548176765441895, "global_step": 361939, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0306577682495117, "global_step": 361940, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.174917221069336, "global_step": 361941, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.137685775756836, "global_step": 361942, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1562256813049316, "global_step": 361943, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.092818021774292, "global_step": 361944, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.084233283996582, "global_step": 361945, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.031809091567993, "global_step": 361946, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.028984546661377, "global_step": 361947, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.135941982269287, "global_step": 361948, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1111721992492676, "global_step": 361949, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.108504056930542, "global_step": 361950, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.104306697845459, "global_step": 361951, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1452789306640625, "global_step": 361952, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0770583152770996, "global_step": 361953, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1493680477142334, "global_step": 361954, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.064283847808838, "global_step": 361955, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.102860689163208, "global_step": 361956, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0533344745635986, "global_step": 361957, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0994880199432373, "global_step": 361958, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1723408699035645, "global_step": 361959, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.153045415878296, "global_step": 361960, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1229119300842285, "global_step": 361961, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1316850185394287, "global_step": 361962, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0712313652038574, "global_step": 361963, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.103196620941162, "global_step": 361964, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.109780788421631, "global_step": 361965, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.123950481414795, "global_step": 361966, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1054930686950684, "global_step": 361967, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.16259503364563, "global_step": 361968, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1265549659729004, "global_step": 361969, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1652567386627197, "global_step": 361970, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.059818744659424, "global_step": 361971, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1089296340942383, "global_step": 361972, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0161070823669434, "global_step": 361973, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0992796421051025, "global_step": 361974, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.059452772140503, "global_step": 361975, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0930469036102295, "global_step": 361976, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0963287353515625, "global_step": 361977, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.120194911956787, "global_step": 361978, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.143584728240967, "global_step": 361979, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.130685567855835, "global_step": 361980, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1375067234039307, "global_step": 361981, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0949831008911133, "global_step": 361982, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.145719528198242, "global_step": 361983, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0898520946502686, "global_step": 361984, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1461548805236816, "global_step": 361985, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.131371259689331, "global_step": 361986, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.133427381515503, "global_step": 361987, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0744271278381348, "global_step": 361988, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0857603549957275, "global_step": 361989, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.121788740158081, "global_step": 361990, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.178558588027954, "global_step": 361991, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0510098934173584, "global_step": 361992, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.05421781539917, "global_step": 361993, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.127938985824585, "global_step": 361994, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0898633003234863, "global_step": 361995, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.172813653945923, "global_step": 361996, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.139549493789673, "global_step": 361997, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.050910472869873, "global_step": 361998, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1413955688476562, "global_step": 361999, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1099908351898193, "global_step": 362000, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0727269649505615, "global_step": 362001, "epoch": 723, "lr": 5e-05}
{"train_loss": 1.9955952167510986, "global_step": 362002, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.174182891845703, "global_step": 362003, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.089465856552124, "global_step": 362004, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.121572732925415, "global_step": 362005, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1418888568878174, "global_step": 362006, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0925443172454834, "global_step": 362007, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.163991689682007, "global_step": 362008, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0427284240722656, "global_step": 362009, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.011247158050537, "global_step": 362010, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.116572618484497, "global_step": 362011, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1956119537353516, "global_step": 362012, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.111304998397827, "global_step": 362013, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.072794198989868, "global_step": 362014, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.146810531616211, "global_step": 362015, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1857471466064453, "global_step": 362016, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1035659313201904, "global_step": 362017, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.152510166168213, "global_step": 362018, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.075348138809204, "global_step": 362019, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1487629413604736, "global_step": 362020, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.106322765350342, "global_step": 362021, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0763258934020996, "global_step": 362022, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.158057689666748, "global_step": 362023, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0319032669067383, "global_step": 362024, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.2070813179016113, "global_step": 362025, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.07304310798645, "global_step": 362026, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0530829429626465, "global_step": 362027, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1090939044952393, "global_step": 362028, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1065304279327393, "global_step": 362029, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0966169834136963, "global_step": 362030, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1181085109710693, "global_step": 362031, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1186647415161133, "global_step": 362032, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.166799783706665, "global_step": 362033, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.132239818572998, "global_step": 362034, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1256041526794434, "global_step": 362035, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.132841110229492, "global_step": 362036, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.097182512283325, "global_step": 362037, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1720073223114014, "global_step": 362038, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.2052409648895264, "global_step": 362039, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.068028211593628, "global_step": 362040, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0702505111694336, "global_step": 362041, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.198782205581665, "global_step": 362042, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.2024943828582764, "global_step": 362043, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0988574028015137, "global_step": 362044, "epoch": 723, "lr": 5e-05}
{"train_loss": 1.9988620281219482, "global_step": 362045, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1718430519104004, "global_step": 362046, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.103170394897461, "global_step": 362047, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.14768648147583, "global_step": 362048, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.077260732650757, "global_step": 362049, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.166759967803955, "global_step": 362050, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1358327865600586, "global_step": 362051, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.182934045791626, "global_step": 362052, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.057574510574341, "global_step": 362053, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.039630651473999, "global_step": 362054, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1052298545837402, "global_step": 362055, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0893845558166504, "global_step": 362056, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0665442943573, "global_step": 362057, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1668267250061035, "global_step": 362058, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.059741735458374, "global_step": 362059, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.124333143234253, "global_step": 362060, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0711569786071777, "global_step": 362061, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0546765327453613, "global_step": 362062, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0295424461364746, "global_step": 362063, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1119110584259033, "global_step": 362064, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.164490222930908, "global_step": 362065, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1384077072143555, "global_step": 362066, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1839396953582764, "global_step": 362067, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0766890048980713, "global_step": 362068, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0011703968048096, "global_step": 362069, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1786415576934814, "global_step": 362070, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.18507981300354, "global_step": 362071, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1331191062927246, "global_step": 362072, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0759222507476807, "global_step": 362073, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.11929988861084, "global_step": 362074, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.076382875442505, "global_step": 362075, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.057241678237915, "global_step": 362076, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.081455707550049, "global_step": 362077, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0801773071289062, "global_step": 362078, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.065357208251953, "global_step": 362079, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.009996175765991, "global_step": 362080, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1259069442749023, "global_step": 362081, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.095960855484009, "global_step": 362082, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.18275785446167, "global_step": 362083, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.129957675933838, "global_step": 362084, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0781941413879395, "global_step": 362085, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0908970832824707, "global_step": 362086, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.072110414505005, "global_step": 362087, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.080472946166992, "global_step": 362088, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1366126537323, "global_step": 362089, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0509564876556396, "global_step": 362090, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1535019874572754, "global_step": 362091, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.078317403793335, "global_step": 362092, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1317756175994873, "global_step": 362093, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.139425039291382, "global_step": 362094, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1413233280181885, "global_step": 362095, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1328511238098145, "global_step": 362096, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.172578811645508, "global_step": 362097, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0703670978546143, "global_step": 362098, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0715084075927734, "global_step": 362099, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.099687337875366, "global_step": 362100, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.183152437210083, "global_step": 362101, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.021547555923462, "global_step": 362102, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1037511825561523, "global_step": 362103, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.084406852722168, "global_step": 362104, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1083993911743164, "global_step": 362105, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1683497428894043, "global_step": 362106, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0961172580718994, "global_step": 362107, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0186619758605957, "global_step": 362108, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1436519622802734, "global_step": 362109, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1358132362365723, "global_step": 362110, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.105585813522339, "global_step": 362111, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1294448375701904, "global_step": 362112, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0008771419525146, "global_step": 362113, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.027130126953125, "global_step": 362114, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.083936929702759, "global_step": 362115, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1469929218292236, "global_step": 362116, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0459115505218506, "global_step": 362117, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0801916122436523, "global_step": 362118, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0797908306121826, "global_step": 362119, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1863462924957275, "global_step": 362120, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1555957794189453, "global_step": 362121, "epoch": 723, "lr": 5e-05}
{"train_loss": 1.9741640090942383, "global_step": 362122, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0724880695343018, "global_step": 362123, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.047104835510254, "global_step": 362124, "epoch": 723, "lr": 5e-05}
{"train_loss": 1.9541573524475098, "global_step": 362125, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0606911182403564, "global_step": 362126, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.05550217628479, "global_step": 362127, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.003208875656128, "global_step": 362128, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0685410499572754, "global_step": 362129, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.070185422897339, "global_step": 362130, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.207723379135132, "global_step": 362131, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.133903980255127, "global_step": 362132, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1675801277160645, "global_step": 362133, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1514358520507812, "global_step": 362134, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.116877317428589, "global_step": 362135, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1077282428741455, "global_step": 362136, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1103413105010986, "global_step": 362137, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.149369955062866, "global_step": 362138, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.102583646774292, "global_step": 362139, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1114277839660645, "global_step": 362140, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1752359867095947, "global_step": 362141, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.138824462890625, "global_step": 362142, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.158768892288208, "global_step": 362143, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.128261089324951, "global_step": 362144, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1115617752075195, "global_step": 362145, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1138017177581787, "global_step": 362146, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1539430618286133, "global_step": 362147, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.080080032348633, "global_step": 362148, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0987741947174072, "global_step": 362149, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.055267095565796, "global_step": 362150, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.132272958755493, "global_step": 362151, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0219860076904297, "global_step": 362152, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1241753101348877, "global_step": 362153, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.2157998085021973, "global_step": 362154, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0814950466156006, "global_step": 362155, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1134955883026123, "global_step": 362156, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0875589847564697, "global_step": 362157, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0523526668548584, "global_step": 362158, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1320695877075195, "global_step": 362159, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.17646861076355, "global_step": 362160, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.137796401977539, "global_step": 362161, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.082141876220703, "global_step": 362162, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1526477336883545, "global_step": 362163, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0581040382385254, "global_step": 362164, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.146785259246826, "global_step": 362165, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.107612133026123, "global_step": 362166, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.075504779815674, "global_step": 362167, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.088677167892456, "global_step": 362168, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0906500816345215, "global_step": 362169, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0877513885498047, "global_step": 362170, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.176079034805298, "global_step": 362171, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0544633865356445, "global_step": 362172, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.120152473449707, "global_step": 362173, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.175380229949951, "global_step": 362174, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1057565212249756, "global_step": 362175, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0614778995513916, "global_step": 362176, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0669291019439697, "global_step": 362177, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.050318479537964, "global_step": 362178, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.21549916267395, "global_step": 362179, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.11667537689209, "global_step": 362180, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.113582134246826, "global_step": 362181, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.156825542449951, "global_step": 362182, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1310133934020996, "global_step": 362183, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1346118450164795, "global_step": 362184, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0337228775024414, "global_step": 362185, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1280105113983154, "global_step": 362186, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.182997465133667, "global_step": 362187, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0775656700134277, "global_step": 362188, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0599472522735596, "global_step": 362189, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1032180786132812, "global_step": 362190, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.015836000442505, "global_step": 362191, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1075894832611084, "global_step": 362192, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1157636642456055, "global_step": 362193, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.134577512741089, "global_step": 362194, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.103344440460205, "global_step": 362195, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0689423084259033, "global_step": 362196, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0581772327423096, "global_step": 362197, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.142490863800049, "global_step": 362198, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.118933916091919, "global_step": 362199, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1060659885406494, "global_step": 362200, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1336240768432617, "global_step": 362201, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.101928234100342, "global_step": 362202, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0646238327026367, "global_step": 362203, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0722851753234863, "global_step": 362204, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.111677646636963, "global_step": 362205, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.10603666305542, "global_step": 362206, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0459632873535156, "global_step": 362207, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1482317447662354, "global_step": 362208, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.225693941116333, "global_step": 362209, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.10539174079895, "global_step": 362210, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.121530771255493, "global_step": 362211, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1407370567321777, "global_step": 362212, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1051905155181885, "global_step": 362213, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1194417476654053, "global_step": 362214, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1489007472991943, "global_step": 362215, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0764639377593994, "global_step": 362216, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.161700487136841, "global_step": 362217, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1420981884002686, "global_step": 362218, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.123558282852173, "global_step": 362219, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.203814744949341, "global_step": 362220, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.143584966659546, "global_step": 362221, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1100878715515137, "global_step": 362222, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0601272583007812, "global_step": 362223, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0922882556915283, "global_step": 362224, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0745809078216553, "global_step": 362225, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1551461219787598, "global_step": 362226, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.044633388519287, "global_step": 362227, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.073594093322754, "global_step": 362228, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1190004348754883, "global_step": 362229, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1413400173187256, "global_step": 362230, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.156863212585449, "global_step": 362231, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1303248405456543, "global_step": 362232, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1503539085388184, "global_step": 362233, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1573903560638428, "global_step": 362234, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.086026430130005, "global_step": 362235, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0358362197875977, "global_step": 362236, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0413694381713867, "global_step": 362237, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.099733352661133, "global_step": 362238, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1178805828094482, "global_step": 362239, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.108588933944702, "global_step": 362240, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.108128547668457, "global_step": 362241, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.059170722961426, "global_step": 362242, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.185868501663208, "global_step": 362243, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0636541843414307, "global_step": 362244, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1187055110931396, "global_step": 362245, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1125316619873047, "global_step": 362246, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1073248386383057, "global_step": 362247, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.075226306915283, "global_step": 362248, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.144329309463501, "global_step": 362249, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1497204303741455, "global_step": 362250, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0908288955688477, "global_step": 362251, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0421078205108643, "global_step": 362252, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0509889125823975, "global_step": 362253, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1604926586151123, "global_step": 362254, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1594035625457764, "global_step": 362255, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0227222442626953, "global_step": 362256, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.163645029067993, "global_step": 362257, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.140573501586914, "global_step": 362258, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1346499919891357, "global_step": 362259, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.127507209777832, "global_step": 362260, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.118312358856201, "global_step": 362261, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0157694816589355, "global_step": 362262, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0397791862487793, "global_step": 362263, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.136958599090576, "global_step": 362264, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.172203540802002, "global_step": 362265, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0831611156463623, "global_step": 362266, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1112349033355713, "global_step": 362267, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0616848468780518, "global_step": 362268, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0540101528167725, "global_step": 362269, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.078702449798584, "global_step": 362270, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0520823001861572, "global_step": 362271, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1620001792907715, "global_step": 362272, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1747796535491943, "global_step": 362273, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.087195634841919, "global_step": 362274, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1847455501556396, "global_step": 362275, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1346731185913086, "global_step": 362276, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.159830331802368, "global_step": 362277, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0893430709838867, "global_step": 362278, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1581225395202637, "global_step": 362279, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0843374729156494, "global_step": 362280, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1579434871673584, "global_step": 362281, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1346802711486816, "global_step": 362282, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0660078525543213, "global_step": 362283, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.089890480041504, "global_step": 362284, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0467700958251953, "global_step": 362285, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0595128536224365, "global_step": 362286, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1172964572906494, "global_step": 362287, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.153747320175171, "global_step": 362288, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.080582857131958, "global_step": 362289, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0776865482330322, "global_step": 362290, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1695823669433594, "global_step": 362291, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1321537494659424, "global_step": 362292, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.068096160888672, "global_step": 362293, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.07254958152771, "global_step": 362294, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.110198974609375, "global_step": 362295, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1224124431610107, "global_step": 362296, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.212482213973999, "global_step": 362297, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1443285942077637, "global_step": 362298, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0982346534729004, "global_step": 362299, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.156022071838379, "global_step": 362300, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0749003887176514, "global_step": 362301, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.126243829727173, "global_step": 362302, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.132491111755371, "global_step": 362303, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1214406490325928, "global_step": 362304, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.079375743865967, "global_step": 362305, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0791006088256836, "global_step": 362306, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1423721313476562, "global_step": 362307, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.134678840637207, "global_step": 362308, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.111621141433716, "global_step": 362309, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1078195571899414, "global_step": 362310, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.109995126724243, "global_step": 362311, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.147343635559082, "global_step": 362312, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.181277275085449, "global_step": 362313, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1435654163360596, "global_step": 362314, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1275086402893066, "global_step": 362315, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.101426362991333, "global_step": 362316, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.092510223388672, "global_step": 362317, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0318174362182617, "global_step": 362318, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.2305455207824707, "global_step": 362319, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.072235107421875, "global_step": 362320, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0473732948303223, "global_step": 362321, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0343170166015625, "global_step": 362322, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.253967761993408, "global_step": 362323, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0489678382873535, "global_step": 362324, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.082171678543091, "global_step": 362325, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.07501220703125, "global_step": 362326, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1650402545928955, "global_step": 362327, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1496427059173584, "global_step": 362328, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1515793800354004, "global_step": 362329, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.225942373275757, "global_step": 362330, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.056008815765381, "global_step": 362331, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1875877380371094, "global_step": 362332, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.179147720336914, "global_step": 362333, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.108442783355713, "global_step": 362334, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.075190782546997, "global_step": 362335, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1948249340057373, "global_step": 362336, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0920968055725098, "global_step": 362337, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1212964057922363, "global_step": 362338, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1170756816864014, "global_step": 362339, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.069122791290283, "global_step": 362340, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1628830432891846, "global_step": 362341, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.137491464614868, "global_step": 362342, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1284570693969727, "global_step": 362343, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0888466835021973, "global_step": 362344, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1505722999572754, "global_step": 362345, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.124713182449341, "global_step": 362346, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0575480461120605, "global_step": 362347, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0769309997558594, "global_step": 362348, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.111781120300293, "global_step": 362349, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.054220676422119, "global_step": 362350, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1533172130584717, "global_step": 362351, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.124507188796997, "global_step": 362352, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0844709873199463, "global_step": 362353, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.125441789627075, "global_step": 362354, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.173212766647339, "global_step": 362355, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.093214273452759, "global_step": 362356, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0647950172424316, "global_step": 362357, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1622426509857178, "global_step": 362358, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.102224111557007, "global_step": 362359, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0810441970825195, "global_step": 362360, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0705482959747314, "global_step": 362361, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.115032196044922, "global_step": 362362, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1566593647003174, "global_step": 362363, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0576910972595215, "global_step": 362364, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.110523223876953, "global_step": 362365, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.055933713912964, "global_step": 362366, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.142406940460205, "global_step": 362367, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1810176372528076, "global_step": 362368, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1262450218200684, "global_step": 362369, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.125415563583374, "global_step": 362370, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.16910982131958, "global_step": 362371, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0822572708129883, "global_step": 362372, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0481669902801514, "global_step": 362373, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.2386436462402344, "global_step": 362374, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1253950595855713, "global_step": 362375, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0638391971588135, "global_step": 362376, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.131222724914551, "global_step": 362377, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1178061962127686, "global_step": 362378, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1186883449554443, "global_step": 362379, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.213899612426758, "global_step": 362380, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.081829786300659, "global_step": 362381, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1826183795928955, "global_step": 362382, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.122091770172119, "global_step": 362383, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.2027907371520996, "global_step": 362384, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.130202531814575, "global_step": 362385, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.13728928565979, "global_step": 362386, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0667006969451904, "global_step": 362387, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1008620262145996, "global_step": 362388, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.106701374053955, "global_step": 362389, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0942482948303223, "global_step": 362390, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.112234115600586, "global_step": 362391, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0987775325775146, "global_step": 362392, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.043623208999634, "global_step": 362393, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.053603410720825, "global_step": 362394, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1136248111724854, "global_step": 362395, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1240546703338623, "global_step": 362396, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.10627818107605, "global_step": 362397, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1330952644348145, "global_step": 362398, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1240627765655518, "global_step": 362399, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.137152910232544, "global_step": 362400, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1125080585479736, "global_step": 362401, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.037101984024048, "global_step": 362402, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1318578720092773, "global_step": 362403, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1791770458221436, "global_step": 362404, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1317408084869385, "global_step": 362405, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1019833087921143, "global_step": 362406, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1753082275390625, "global_step": 362407, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0608856678009033, "global_step": 362408, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.211186408996582, "global_step": 362409, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0047483444213867, "global_step": 362410, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.060605049133301, "global_step": 362411, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.043717384338379, "global_step": 362412, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.204242467880249, "global_step": 362413, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.093562602996826, "global_step": 362414, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0809991359710693, "global_step": 362415, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0278117656707764, "global_step": 362416, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.163670063018799, "global_step": 362417, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.094770669937134, "global_step": 362418, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0324981212615967, "global_step": 362419, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1698122024536133, "global_step": 362420, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.137751340866089, "global_step": 362421, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.13014817237854, "global_step": 362422, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.144148349761963, "global_step": 362423, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0937764644622803, "global_step": 362424, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0990493297576904, "global_step": 362425, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.173994541168213, "global_step": 362426, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.169891834259033, "global_step": 362427, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.158828020095825, "global_step": 362428, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0565948486328125, "global_step": 362429, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1207048892974854, "global_step": 362430, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.164945363998413, "global_step": 362431, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0988943576812744, "global_step": 362432, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.01804256439209, "global_step": 362433, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1860554218292236, "global_step": 362434, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.130748987197876, "global_step": 362435, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0429282188415527, "global_step": 362436, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.083892583847046, "global_step": 362437, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1562659740448, "global_step": 362438, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.161597967147827, "global_step": 362439, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1175496578216553, "global_step": 362440, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1266140937805176, "global_step": 362441, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.128727436065674, "global_step": 362442, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1042850017547607, "global_step": 362443, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.2010936737060547, "global_step": 362444, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1122400760650635, "global_step": 362445, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0761494636535645, "global_step": 362446, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.093744993209839, "global_step": 362447, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1132237911224365, "global_step": 362448, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1647591590881348, "global_step": 362449, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0880377292633057, "global_step": 362450, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.09397554397583, "global_step": 362451, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.11272931098938, "global_step": 362452, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.096937894821167, "global_step": 362453, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0844063758850098, "global_step": 362454, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.113802194595337, "global_step": 362455, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1606338024139404, "global_step": 362456, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0658135414123535, "global_step": 362457, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1049187183380127, "global_step": 362458, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1346280574798584, "global_step": 362459, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.094407081604004, "global_step": 362460, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1356825828552246, "global_step": 362461, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.102958917617798, "global_step": 362462, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.166618585586548, "global_step": 362463, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.060926914215088, "global_step": 362464, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1547510623931885, "global_step": 362465, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.080080509185791, "global_step": 362466, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.113520622253418, "global_step": 362467, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1120309829711914, "global_step": 362468, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.098658323287964, "global_step": 362469, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1003148555755615, "global_step": 362470, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0604326725006104, "global_step": 362471, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1103439331054688, "global_step": 362472, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.076333522796631, "global_step": 362473, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.172076463699341, "global_step": 362474, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0931649208068848, "global_step": 362475, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.099374294281006, "global_step": 362476, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.192842483520508, "global_step": 362477, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1810154914855957, "global_step": 362478, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0581583976745605, "global_step": 362479, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1808156967163086, "global_step": 362480, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0434603691101074, "global_step": 362481, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0163044929504395, "global_step": 362482, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.04373836517334, "global_step": 362483, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.113819122314453, "global_step": 362484, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.2169125080108643, "global_step": 362485, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1441125869750977, "global_step": 362486, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0498106479644775, "global_step": 362487, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1363959312438965, "global_step": 362488, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1388933658599854, "global_step": 362489, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1585962772369385, "global_step": 362490, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1229095458984375, "global_step": 362491, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.113701581954956, "global_step": 362492, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1074860095977783, "global_step": 362493, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0751540660858154, "global_step": 362494, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.242042064666748, "global_step": 362495, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1360785961151123, "global_step": 362496, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0784049034118652, "global_step": 362497, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1138806343078613, "global_step": 362498, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1706223487854004, "global_step": 362499, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0574240684509277, "global_step": 362500, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1418259143829346, "global_step": 362501, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1424427032470703, "global_step": 362502, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1302311420440674, "global_step": 362503, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1215474605560303, "global_step": 362504, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.057896137237549, "global_step": 362505, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0570273399353027, "global_step": 362506, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.071629524230957, "global_step": 362507, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.092334270477295, "global_step": 362508, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0823986530303955, "global_step": 362509, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.03566312789917, "global_step": 362510, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.171757698059082, "global_step": 362511, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1079471111297607, "global_step": 362512, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.116072416305542, "global_step": 362513, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.132476568222046, "global_step": 362514, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1558098793029785, "global_step": 362515, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.203056573867798, "global_step": 362516, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0758142471313477, "global_step": 362517, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.109273672103882, "global_step": 362518, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0318477153778076, "global_step": 362519, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1387593746185303, "global_step": 362520, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.040424346923828, "global_step": 362521, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1611037254333496, "global_step": 362522, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.016143321990967, "global_step": 362523, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0252163410186768, "global_step": 362524, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1486778259277344, "global_step": 362525, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1685380935668945, "global_step": 362526, "epoch": 723, "lr": 5e-05}
{"train_loss": 1.9731088876724243, "global_step": 362527, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.173055648803711, "global_step": 362528, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.121906042098999, "global_step": 362529, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.186098098754883, "global_step": 362530, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.015638828277588, "global_step": 362531, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.116812229156494, "global_step": 362532, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0976722240448, "global_step": 362533, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.1654815673828125, "global_step": 362534, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.214843511581421, "global_step": 362535, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.085648536682129, "global_step": 362536, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0641932487487793, "global_step": 362537, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.107912540435791, "global_step": 362538, "epoch": 723, "lr": 5e-05}
{"train_loss": 2.0920965671539307, "global_step": 362539, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.116853952407837, "global_step": 362540, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0607752799987793, "global_step": 362541, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.113286256790161, "global_step": 362542, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.179304599761963, "global_step": 362543, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1099884510040283, "global_step": 362544, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1098899841308594, "global_step": 362545, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1146886348724365, "global_step": 362546, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0624680519104004, "global_step": 362547, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0598154067993164, "global_step": 362548, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0289595127105713, "global_step": 362549, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1130478382110596, "global_step": 362550, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0273358821868896, "global_step": 362551, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.145206928253174, "global_step": 362552, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1254940032958984, "global_step": 362553, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.076298236846924, "global_step": 362554, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.108139991760254, "global_step": 362555, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.069849729537964, "global_step": 362556, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0839145183563232, "global_step": 362557, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.117934226989746, "global_step": 362558, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.03200626373291, "global_step": 362559, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0740718841552734, "global_step": 362560, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1222822666168213, "global_step": 362561, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0694944858551025, "global_step": 362562, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0343313217163086, "global_step": 362563, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1179471015930176, "global_step": 362564, "epoch": 724, "lr": 5e-05}
{"train_loss": 1.995545744895935, "global_step": 362565, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.103403329849243, "global_step": 362566, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.131334066390991, "global_step": 362567, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.098372220993042, "global_step": 362568, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2985999584198, "global_step": 362569, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1049952507019043, "global_step": 362570, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.069286823272705, "global_step": 362571, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.103912115097046, "global_step": 362572, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.159024715423584, "global_step": 362573, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.183323383331299, "global_step": 362574, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0464320182800293, "global_step": 362575, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.011798620223999, "global_step": 362576, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.163639545440674, "global_step": 362577, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.088373899459839, "global_step": 362578, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.074796199798584, "global_step": 362579, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.145190477371216, "global_step": 362580, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0978658199310303, "global_step": 362581, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.16344952583313, "global_step": 362582, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.143187999725342, "global_step": 362583, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0898616313934326, "global_step": 362584, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1127514839172363, "global_step": 362585, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.143421173095703, "global_step": 362586, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1867570877075195, "global_step": 362587, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.100027561187744, "global_step": 362588, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0382778644561768, "global_step": 362589, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.022740125656128, "global_step": 362590, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.060751438140869, "global_step": 362591, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.135620355606079, "global_step": 362592, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.077418565750122, "global_step": 362593, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0816009044647217, "global_step": 362594, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.102508068084717, "global_step": 362595, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1341683864593506, "global_step": 362596, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0224015712738037, "global_step": 362597, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0364372730255127, "global_step": 362598, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.124858856201172, "global_step": 362599, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0886800289154053, "global_step": 362600, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.017655611038208, "global_step": 362601, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.132617473602295, "global_step": 362602, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0959272384643555, "global_step": 362603, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.092064142227173, "global_step": 362604, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1485750675201416, "global_step": 362605, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.191425323486328, "global_step": 362606, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1175384521484375, "global_step": 362607, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.107728958129883, "global_step": 362608, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.108179807662964, "global_step": 362609, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.142958164215088, "global_step": 362610, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.146480083465576, "global_step": 362611, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.082268714904785, "global_step": 362612, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1317384243011475, "global_step": 362613, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.130702495574951, "global_step": 362614, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.092015504837036, "global_step": 362615, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.01511549949646, "global_step": 362616, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0960609912872314, "global_step": 362617, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.069499969482422, "global_step": 362618, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1137404441833496, "global_step": 362619, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.033139228820801, "global_step": 362620, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1041438579559326, "global_step": 362621, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.088778257369995, "global_step": 362622, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.105073928833008, "global_step": 362623, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0279922485351562, "global_step": 362624, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.09175181388855, "global_step": 362625, "epoch": 724, "lr": 5e-05}
{"train_loss": 1.9802320003509521, "global_step": 362626, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0832359790802, "global_step": 362627, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0942726135253906, "global_step": 362628, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1428747177124023, "global_step": 362629, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1673240661621094, "global_step": 362630, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.108470916748047, "global_step": 362631, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0256335735321045, "global_step": 362632, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0579779148101807, "global_step": 362633, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1947731971740723, "global_step": 362634, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1672873497009277, "global_step": 362635, "epoch": 724, "lr": 5e-05}
{"train_loss": 1.9627050161361694, "global_step": 362636, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1439309120178223, "global_step": 362637, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0094757080078125, "global_step": 362638, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1704511642456055, "global_step": 362639, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.197277069091797, "global_step": 362640, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0394351482391357, "global_step": 362641, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.122368812561035, "global_step": 362642, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1522440910339355, "global_step": 362643, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.162327766418457, "global_step": 362644, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.108201265335083, "global_step": 362645, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.037078380584717, "global_step": 362646, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.146071672439575, "global_step": 362647, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1813461780548096, "global_step": 362648, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.138000011444092, "global_step": 362649, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.065735101699829, "global_step": 362650, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.110914468765259, "global_step": 362651, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1821706295013428, "global_step": 362652, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.100726366043091, "global_step": 362653, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0402326583862305, "global_step": 362654, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1226518154144287, "global_step": 362655, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0549404621124268, "global_step": 362656, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.163106918334961, "global_step": 362657, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0769600868225098, "global_step": 362658, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.150879144668579, "global_step": 362659, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.032402276992798, "global_step": 362660, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1532697677612305, "global_step": 362661, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.094451904296875, "global_step": 362662, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.083739757537842, "global_step": 362663, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1320455074310303, "global_step": 362664, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.116302728652954, "global_step": 362665, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.099924087524414, "global_step": 362666, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1722497940063477, "global_step": 362667, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.170022964477539, "global_step": 362668, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.140280246734619, "global_step": 362669, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.095959424972534, "global_step": 362670, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.114794969558716, "global_step": 362671, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1035685539245605, "global_step": 362672, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1465201377868652, "global_step": 362673, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.133478879928589, "global_step": 362674, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1378042697906494, "global_step": 362675, "epoch": 724, "lr": 5e-05}
{"train_loss": 1.991514801979065, "global_step": 362676, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.128099203109741, "global_step": 362677, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1248133182525635, "global_step": 362678, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.074005365371704, "global_step": 362679, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.106109619140625, "global_step": 362680, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0567798614501953, "global_step": 362681, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1270172595977783, "global_step": 362682, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1074371337890625, "global_step": 362683, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.10412859916687, "global_step": 362684, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.097883701324463, "global_step": 362685, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.112236738204956, "global_step": 362686, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0801751613616943, "global_step": 362687, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.061265230178833, "global_step": 362688, "epoch": 724, "lr": 5e-05}
{"train_loss": 1.985588788986206, "global_step": 362689, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1266069412231445, "global_step": 362690, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.203195333480835, "global_step": 362691, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.10688853263855, "global_step": 362692, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.048924446105957, "global_step": 362693, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1501474380493164, "global_step": 362694, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1147165298461914, "global_step": 362695, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1201047897338867, "global_step": 362696, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1754040718078613, "global_step": 362697, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.070415496826172, "global_step": 362698, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1392428874969482, "global_step": 362699, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.130411386489868, "global_step": 362700, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.289109706878662, "global_step": 362701, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1233904361724854, "global_step": 362702, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.123753547668457, "global_step": 362703, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.104402542114258, "global_step": 362704, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0924761295318604, "global_step": 362705, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.212153911590576, "global_step": 362706, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0805611610412598, "global_step": 362707, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0963337421417236, "global_step": 362708, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.065030813217163, "global_step": 362709, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1434781551361084, "global_step": 362710, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1240720748901367, "global_step": 362711, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0792460441589355, "global_step": 362712, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0794029235839844, "global_step": 362713, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1379802227020264, "global_step": 362714, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.127582311630249, "global_step": 362715, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0660195350646973, "global_step": 362716, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.001220226287842, "global_step": 362717, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.025014638900757, "global_step": 362718, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0956943035125732, "global_step": 362719, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1039915084838867, "global_step": 362720, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0565037727355957, "global_step": 362721, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.068936347961426, "global_step": 362722, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.086287498474121, "global_step": 362723, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.130246162414551, "global_step": 362724, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0604970455169678, "global_step": 362725, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1457626819610596, "global_step": 362726, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.121260166168213, "global_step": 362727, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1491026878356934, "global_step": 362728, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1487796306610107, "global_step": 362729, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0736405849456787, "global_step": 362730, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1029491424560547, "global_step": 362731, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.104194402694702, "global_step": 362732, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1041712760925293, "global_step": 362733, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1373629570007324, "global_step": 362734, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0950329303741455, "global_step": 362735, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0368831157684326, "global_step": 362736, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0722110271453857, "global_step": 362737, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0486249923706055, "global_step": 362738, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1988534927368164, "global_step": 362739, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.117161750793457, "global_step": 362740, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0950777530670166, "global_step": 362741, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0552849769592285, "global_step": 362742, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0879476070404053, "global_step": 362743, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0290417671203613, "global_step": 362744, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1001322269439697, "global_step": 362745, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1197447776794434, "global_step": 362746, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1388823986053467, "global_step": 362747, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0686259269714355, "global_step": 362748, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2023262977600098, "global_step": 362749, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.101531744003296, "global_step": 362750, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0707311630249023, "global_step": 362751, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.150768756866455, "global_step": 362752, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.062581777572632, "global_step": 362753, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1027486324310303, "global_step": 362754, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.057966709136963, "global_step": 362755, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1194419860839844, "global_step": 362756, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0350725650787354, "global_step": 362757, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1237611770629883, "global_step": 362758, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.146984577178955, "global_step": 362759, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1038668155670166, "global_step": 362760, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.108363628387451, "global_step": 362761, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1197268962860107, "global_step": 362762, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1775381565093994, "global_step": 362763, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0941529273986816, "global_step": 362764, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1014387607574463, "global_step": 362765, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0538599491119385, "global_step": 362766, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.056821823120117, "global_step": 362767, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.143364191055298, "global_step": 362768, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1297054290771484, "global_step": 362769, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1327505111694336, "global_step": 362770, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1266417503356934, "global_step": 362771, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1363935470581055, "global_step": 362772, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1075942516326904, "global_step": 362773, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0997977256774902, "global_step": 362774, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1651296615600586, "global_step": 362775, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.272449016571045, "global_step": 362776, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.118804931640625, "global_step": 362777, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0201468467712402, "global_step": 362778, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.121067523956299, "global_step": 362779, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.095883846282959, "global_step": 362780, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0320167541503906, "global_step": 362781, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1092841625213623, "global_step": 362782, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1589410305023193, "global_step": 362783, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.233426809310913, "global_step": 362784, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1035287380218506, "global_step": 362785, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1456613540649414, "global_step": 362786, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0672924518585205, "global_step": 362787, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1279337406158447, "global_step": 362788, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0668294429779053, "global_step": 362789, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.088034152984619, "global_step": 362790, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.084221601486206, "global_step": 362791, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1159379482269287, "global_step": 362792, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0714151859283447, "global_step": 362793, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.093703031539917, "global_step": 362794, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.087965250015259, "global_step": 362795, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.049628973007202, "global_step": 362796, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.019993305206299, "global_step": 362797, "epoch": 724, "lr": 5e-05}
{"train_loss": 1.9934031963348389, "global_step": 362798, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.142502784729004, "global_step": 362799, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1083767414093018, "global_step": 362800, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.059809446334839, "global_step": 362801, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.035003423690796, "global_step": 362802, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0694265365600586, "global_step": 362803, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0230658054351807, "global_step": 362804, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0624284744262695, "global_step": 362805, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0704102516174316, "global_step": 362806, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.070361375808716, "global_step": 362807, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0313527584075928, "global_step": 362808, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1263909339904785, "global_step": 362809, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.106344699859619, "global_step": 362810, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1303813457489014, "global_step": 362811, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.174013614654541, "global_step": 362812, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.137871026992798, "global_step": 362813, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.107732057571411, "global_step": 362814, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1025373935699463, "global_step": 362815, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0245261192321777, "global_step": 362816, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0476737022399902, "global_step": 362817, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.159576892852783, "global_step": 362818, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.027010679244995, "global_step": 362819, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1017308235168457, "global_step": 362820, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1410367488861084, "global_step": 362821, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.049670934677124, "global_step": 362822, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.070010185241699, "global_step": 362823, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1140880584716797, "global_step": 362824, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.114733934402466, "global_step": 362825, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2185986042022705, "global_step": 362826, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.079404354095459, "global_step": 362827, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0728600025177, "global_step": 362828, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1075382232666016, "global_step": 362829, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.072127103805542, "global_step": 362830, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.079336643218994, "global_step": 362831, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0329525470733643, "global_step": 362832, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.194749593734741, "global_step": 362833, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.101264715194702, "global_step": 362834, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1158676147460938, "global_step": 362835, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.220067024230957, "global_step": 362836, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.084301471710205, "global_step": 362837, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1186439990997314, "global_step": 362838, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0564017295837402, "global_step": 362839, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.179851770401001, "global_step": 362840, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.079124927520752, "global_step": 362841, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.131911516189575, "global_step": 362842, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.110292673110962, "global_step": 362843, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0307652950286865, "global_step": 362844, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2014904022216797, "global_step": 362845, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.082742929458618, "global_step": 362846, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.159217119216919, "global_step": 362847, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2100560665130615, "global_step": 362848, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.130207061767578, "global_step": 362849, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.083559513092041, "global_step": 362850, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0323984622955322, "global_step": 362851, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1457998752593994, "global_step": 362852, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0391526222229004, "global_step": 362853, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1875226497650146, "global_step": 362854, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1166794300079346, "global_step": 362855, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1794703006744385, "global_step": 362856, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1500210762023926, "global_step": 362857, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1541693210601807, "global_step": 362858, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.084369421005249, "global_step": 362859, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1017353534698486, "global_step": 362860, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1512179374694824, "global_step": 362861, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0915374755859375, "global_step": 362862, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0980277061462402, "global_step": 362863, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.170030355453491, "global_step": 362864, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1160504817962646, "global_step": 362865, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.162097454071045, "global_step": 362866, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0930778980255127, "global_step": 362867, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1090822219848633, "global_step": 362868, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.110682725906372, "global_step": 362869, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1929755210876465, "global_step": 362870, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.191131591796875, "global_step": 362871, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.023744821548462, "global_step": 362872, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1836297512054443, "global_step": 362873, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.127732276916504, "global_step": 362874, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.14512038230896, "global_step": 362875, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0780606269836426, "global_step": 362876, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0940544605255127, "global_step": 362877, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.151313304901123, "global_step": 362878, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.142284870147705, "global_step": 362879, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.143211603164673, "global_step": 362880, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.073993682861328, "global_step": 362881, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1038262844085693, "global_step": 362882, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.063077926635742, "global_step": 362883, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1195051670074463, "global_step": 362884, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.102055788040161, "global_step": 362885, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0735514163970947, "global_step": 362886, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1395199298858643, "global_step": 362887, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2076613903045654, "global_step": 362888, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1469995975494385, "global_step": 362889, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1839945316314697, "global_step": 362890, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1329543590545654, "global_step": 362891, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.073636293411255, "global_step": 362892, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1482608318328857, "global_step": 362893, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1420822143554688, "global_step": 362894, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1098740100860596, "global_step": 362895, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1878373622894287, "global_step": 362896, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0758349895477295, "global_step": 362897, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1105213165283203, "global_step": 362898, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.077880859375, "global_step": 362899, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1088051795959473, "global_step": 362900, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.093008518218994, "global_step": 362901, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.171928644180298, "global_step": 362902, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.027106523513794, "global_step": 362903, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0596487522125244, "global_step": 362904, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1413910388946533, "global_step": 362905, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.149549961090088, "global_step": 362906, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1164352893829346, "global_step": 362907, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.093229055404663, "global_step": 362908, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.089210271835327, "global_step": 362909, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.101480007171631, "global_step": 362910, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1295011043548584, "global_step": 362911, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.062737464904785, "global_step": 362912, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.139064073562622, "global_step": 362913, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1183786392211914, "global_step": 362914, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.076026439666748, "global_step": 362915, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1011595726013184, "global_step": 362916, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.023608684539795, "global_step": 362917, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1282105445861816, "global_step": 362918, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.091387987136841, "global_step": 362919, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.105945348739624, "global_step": 362920, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1291890144348145, "global_step": 362921, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1082041263580322, "global_step": 362922, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0801126956939697, "global_step": 362923, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0954806804656982, "global_step": 362924, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0998620986938477, "global_step": 362925, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.041771411895752, "global_step": 362926, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1843316555023193, "global_step": 362927, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0881543159484863, "global_step": 362928, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.017056941986084, "global_step": 362929, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.159987449645996, "global_step": 362930, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0775086879730225, "global_step": 362931, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.165611505508423, "global_step": 362932, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1964991092681885, "global_step": 362933, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.105725049972534, "global_step": 362934, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2025654315948486, "global_step": 362935, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.168949842453003, "global_step": 362936, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0716350078582764, "global_step": 362937, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.111943244934082, "global_step": 362938, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.120889663696289, "global_step": 362939, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0799779891967773, "global_step": 362940, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1061179637908936, "global_step": 362941, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1927576065063477, "global_step": 362942, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.089287281036377, "global_step": 362943, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0872814655303955, "global_step": 362944, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.103882074356079, "global_step": 362945, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0561769008636475, "global_step": 362946, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1682724952697754, "global_step": 362947, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1335628032684326, "global_step": 362948, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2163631916046143, "global_step": 362949, "epoch": 724, "lr": 5e-05}
{"train_loss": 1.9968994855880737, "global_step": 362950, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0688865184783936, "global_step": 362951, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1381778717041016, "global_step": 362952, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.147559881210327, "global_step": 362953, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1343719959259033, "global_step": 362954, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1497387886047363, "global_step": 362955, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0383005142211914, "global_step": 362956, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.092439651489258, "global_step": 362957, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1236629486083984, "global_step": 362958, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1157238483428955, "global_step": 362959, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.044644832611084, "global_step": 362960, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0717086791992188, "global_step": 362961, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.146433115005493, "global_step": 362962, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0730719566345215, "global_step": 362963, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0779380798339844, "global_step": 362964, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1341311931610107, "global_step": 362965, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2037675380706787, "global_step": 362966, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.082160472869873, "global_step": 362967, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1479504108428955, "global_step": 362968, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.12045955657959, "global_step": 362969, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.021639585494995, "global_step": 362970, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1420071125030518, "global_step": 362971, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.125169515609741, "global_step": 362972, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0130677223205566, "global_step": 362973, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.131066083908081, "global_step": 362974, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0995540618896484, "global_step": 362975, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0244929790496826, "global_step": 362976, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.112776279449463, "global_step": 362977, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.199939489364624, "global_step": 362978, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0889675617218018, "global_step": 362979, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.053755521774292, "global_step": 362980, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.217775821685791, "global_step": 362981, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.154325008392334, "global_step": 362982, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.113976001739502, "global_step": 362983, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.15226674079895, "global_step": 362984, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1132001876831055, "global_step": 362985, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1342720985412598, "global_step": 362986, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1437582969665527, "global_step": 362987, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.079014778137207, "global_step": 362988, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0033514499664307, "global_step": 362989, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.156902551651001, "global_step": 362990, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.122478485107422, "global_step": 362991, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.07804012298584, "global_step": 362992, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.054624319076538, "global_step": 362993, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1385648250579834, "global_step": 362994, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1475300788879395, "global_step": 362995, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.158552885055542, "global_step": 362996, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0252628326416016, "global_step": 362997, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.144362449645996, "global_step": 362998, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0926108360290527, "global_step": 362999, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0142600536346436, "global_step": 363000, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1369550228118896, "global_step": 363001, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2062573432922363, "global_step": 363002, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0868031978607178, "global_step": 363003, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0898501873016357, "global_step": 363004, "epoch": 724, "lr": 5e-05}
{"train_loss": 1.9396718740463257, "global_step": 363005, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0843005180358887, "global_step": 363006, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.215667247772217, "global_step": 363007, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1011102199554443, "global_step": 363008, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.145940065383911, "global_step": 363009, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.121908664703369, "global_step": 363010, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.21409010887146, "global_step": 363011, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1626193523406982, "global_step": 363012, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.05775785446167, "global_step": 363013, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.094015598297119, "global_step": 363014, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.223518133163452, "global_step": 363015, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1161422729492188, "global_step": 363016, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.146327018737793, "global_step": 363017, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.114485263824463, "global_step": 363018, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.20871639251709, "global_step": 363019, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1148300170898438, "global_step": 363020, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1491081714630127, "global_step": 363021, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.06410551071167, "global_step": 363022, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.152074098587036, "global_step": 363023, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.160395383834839, "global_step": 363024, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0200040340423584, "global_step": 363025, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0369508266448975, "global_step": 363026, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1385250091552734, "global_step": 363027, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0861589908599854, "global_step": 363028, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0702600479125977, "global_step": 363029, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0958926677703857, "global_step": 363030, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.11548113822937, "global_step": 363031, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0396151542663574, "global_step": 363032, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.235232353210449, "global_step": 363033, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1563429832458496, "global_step": 363034, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1509077548980713, "global_step": 363035, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.016765594482422, "global_step": 363036, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1396799087524414, "global_step": 363037, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.094104290008545, "global_step": 363038, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0590381622314453, "global_step": 363039, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1009609699249268, "global_step": 363040, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.044574737548828, "global_step": 363041, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1125149726867676, "global_step": 363042, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0481743812561035, "global_step": 363043, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0909066200256348, "global_step": 363044, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.166661500930786, "global_step": 363045, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0624027252197266, "global_step": 363046, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.062404155731201, "global_step": 363047, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1316187381744385, "global_step": 363048, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.160653591156006, "global_step": 363049, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.015261173248291, "global_step": 363050, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1477785110473633, "global_step": 363051, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1273295879364014, "global_step": 363052, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0676429271698, "global_step": 363053, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.081281900405884, "global_step": 363054, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.023948907852173, "global_step": 363055, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1673948764801025, "global_step": 363056, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0445616245269775, "global_step": 363057, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0814385414123535, "global_step": 363058, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.045086622238159, "global_step": 363059, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0648677349090576, "global_step": 363060, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.117953062057495, "global_step": 363061, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1719207763671875, "global_step": 363062, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.157924175262451, "global_step": 363063, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.063699245452881, "global_step": 363064, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.118269443511963, "global_step": 363065, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.132164716720581, "global_step": 363066, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1713364124298096, "global_step": 363067, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0891661643981934, "global_step": 363068, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1610634326934814, "global_step": 363069, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1375436782836914, "global_step": 363070, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.059309959411621, "global_step": 363071, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1928086280822754, "global_step": 363072, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1259143352508545, "global_step": 363073, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0159964561462402, "global_step": 363074, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1522057056427, "global_step": 363075, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.136324882507324, "global_step": 363076, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.01435923576355, "global_step": 363077, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1314377784729004, "global_step": 363078, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0346572399139404, "global_step": 363079, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.103346347808838, "global_step": 363080, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0073020458221436, "global_step": 363081, "epoch": 724, "lr": 5e-05}
{"train_loss": 1.9758250713348389, "global_step": 363082, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1339962482452393, "global_step": 363083, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2754018306732178, "global_step": 363084, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.055109977722168, "global_step": 363085, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.095358371734619, "global_step": 363086, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.189943790435791, "global_step": 363087, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1568222045898438, "global_step": 363088, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.104835033416748, "global_step": 363089, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.095856189727783, "global_step": 363090, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.053868293762207, "global_step": 363091, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1946587562561035, "global_step": 363092, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2225677967071533, "global_step": 363093, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1462044715881348, "global_step": 363094, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.198944568634033, "global_step": 363095, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.162602424621582, "global_step": 363096, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1484453678131104, "global_step": 363097, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.094820261001587, "global_step": 363098, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0329060554504395, "global_step": 363099, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.146099805831909, "global_step": 363100, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1605324745178223, "global_step": 363101, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.083019495010376, "global_step": 363102, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.035949945449829, "global_step": 363103, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.105901002883911, "global_step": 363104, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0984206199645996, "global_step": 363105, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.130561590194702, "global_step": 363106, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.115751028060913, "global_step": 363107, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0960192680358887, "global_step": 363108, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1494410037994385, "global_step": 363109, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.13875412940979, "global_step": 363110, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.122197389602661, "global_step": 363111, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.116250514984131, "global_step": 363112, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1296589374542236, "global_step": 363113, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0587007999420166, "global_step": 363114, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1634626388549805, "global_step": 363115, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.097269296646118, "global_step": 363116, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.165714979171753, "global_step": 363117, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.025651693344116, "global_step": 363118, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.031048536300659, "global_step": 363119, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.080732822418213, "global_step": 363120, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1011219024658203, "global_step": 363121, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0476622581481934, "global_step": 363122, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0546607971191406, "global_step": 363123, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.128988027572632, "global_step": 363124, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.099350929260254, "global_step": 363125, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.196366310119629, "global_step": 363126, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.110612630844116, "global_step": 363127, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0460946559906006, "global_step": 363128, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0871315002441406, "global_step": 363129, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.06410551071167, "global_step": 363130, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1395316123962402, "global_step": 363131, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1249356269836426, "global_step": 363132, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0437817573547363, "global_step": 363133, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.047780752182007, "global_step": 363134, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0998122692108154, "global_step": 363135, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1246912479400635, "global_step": 363136, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.180532932281494, "global_step": 363137, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1015396118164062, "global_step": 363138, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0951831340789795, "global_step": 363139, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0656604766845703, "global_step": 363140, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0283000469207764, "global_step": 363141, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1226766109466553, "global_step": 363142, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0709664821624756, "global_step": 363143, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0887529850006104, "global_step": 363144, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1129262447357178, "global_step": 363145, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1067919731140137, "global_step": 363146, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.052262306213379, "global_step": 363147, "epoch": 724, "lr": 5e-05}
{"train_loss": 1.9935437440872192, "global_step": 363148, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1312150955200195, "global_step": 363149, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0420546531677246, "global_step": 363150, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.107022523880005, "global_step": 363151, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.119887590408325, "global_step": 363152, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.098048448562622, "global_step": 363153, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1754353046417236, "global_step": 363154, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.156012535095215, "global_step": 363155, "epoch": 724, "lr": 5e-05}
{"train_loss": 1.9743001461029053, "global_step": 363156, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1185142993927, "global_step": 363157, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0858144760131836, "global_step": 363158, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.062187433242798, "global_step": 363159, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1453070640563965, "global_step": 363160, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0628232955932617, "global_step": 363161, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0819149017333984, "global_step": 363162, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1021311283111572, "global_step": 363163, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.093940019607544, "global_step": 363164, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1110193729400635, "global_step": 363165, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.112696409225464, "global_step": 363166, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.157687187194824, "global_step": 363167, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1262903213500977, "global_step": 363168, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.083749294281006, "global_step": 363169, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0010244846343994, "global_step": 363170, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.111520290374756, "global_step": 363171, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1754097938537598, "global_step": 363172, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1495819091796875, "global_step": 363173, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.088066577911377, "global_step": 363174, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1019644737243652, "global_step": 363175, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.08823823928833, "global_step": 363176, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1584980487823486, "global_step": 363177, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.029031991958618, "global_step": 363178, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.079787254333496, "global_step": 363179, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0678482055664062, "global_step": 363180, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0870819091796875, "global_step": 363181, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.121422529220581, "global_step": 363182, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1557090282440186, "global_step": 363183, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.198803663253784, "global_step": 363184, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1734912395477295, "global_step": 363185, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.028560161590576, "global_step": 363186, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.084397077560425, "global_step": 363187, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1570186614990234, "global_step": 363188, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.06760573387146, "global_step": 363189, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.213071584701538, "global_step": 363190, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0796303749084473, "global_step": 363191, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1203129291534424, "global_step": 363192, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1336820125579834, "global_step": 363193, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1378045082092285, "global_step": 363194, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0735230445861816, "global_step": 363195, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1388437747955322, "global_step": 363196, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1210670471191406, "global_step": 363197, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.119136333465576, "global_step": 363198, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.175863265991211, "global_step": 363199, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1224453449249268, "global_step": 363200, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.016575813293457, "global_step": 363201, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0797007083892822, "global_step": 363202, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.048513889312744, "global_step": 363203, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1395885944366455, "global_step": 363204, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1474461555480957, "global_step": 363205, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.179081916809082, "global_step": 363206, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1676175594329834, "global_step": 363207, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.158846616744995, "global_step": 363208, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.057379722595215, "global_step": 363209, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0955119132995605, "global_step": 363210, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1021013259887695, "global_step": 363211, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1442723274230957, "global_step": 363212, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0619401931762695, "global_step": 363213, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1196930408477783, "global_step": 363214, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1439523696899414, "global_step": 363215, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1627883911132812, "global_step": 363216, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.165731191635132, "global_step": 363217, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2407913208007812, "global_step": 363218, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.140742063522339, "global_step": 363219, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.082430839538574, "global_step": 363220, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1149370670318604, "global_step": 363221, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.09377121925354, "global_step": 363222, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.070347785949707, "global_step": 363223, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1145527362823486, "global_step": 363224, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0898501873016357, "global_step": 363225, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0454673767089844, "global_step": 363226, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.066535234451294, "global_step": 363227, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.131770372390747, "global_step": 363228, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0692477226257324, "global_step": 363229, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.150911331176758, "global_step": 363230, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.139808416366577, "global_step": 363231, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1997275352478027, "global_step": 363232, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1393632888793945, "global_step": 363233, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.119511604309082, "global_step": 363234, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.199955940246582, "global_step": 363235, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0752761363983154, "global_step": 363236, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.158139944076538, "global_step": 363237, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.135908365249634, "global_step": 363238, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.056570053100586, "global_step": 363239, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0965733528137207, "global_step": 363240, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0661025047302246, "global_step": 363241, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.072521924972534, "global_step": 363242, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.125368595123291, "global_step": 363243, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0983195304870605, "global_step": 363244, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.123870849609375, "global_step": 363245, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0952370166778564, "global_step": 363246, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.064540147781372, "global_step": 363247, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0484557151794434, "global_step": 363248, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1448616981506348, "global_step": 363249, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1439950466156006, "global_step": 363250, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0412425994873047, "global_step": 363251, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0330419540405273, "global_step": 363252, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0594210624694824, "global_step": 363253, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.270372152328491, "global_step": 363254, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.096498727798462, "global_step": 363255, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.077434778213501, "global_step": 363256, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.129500150680542, "global_step": 363257, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1401007175445557, "global_step": 363258, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0857067108154297, "global_step": 363259, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.235416889190674, "global_step": 363260, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.090822696685791, "global_step": 363261, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0706026554107666, "global_step": 363262, "epoch": 724, "lr": 5e-05}
{"train_loss": 1.998441457748413, "global_step": 363263, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.196843147277832, "global_step": 363264, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1213910579681396, "global_step": 363265, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.125304698944092, "global_step": 363266, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.130683660507202, "global_step": 363267, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1765172481536865, "global_step": 363268, "epoch": 724, "lr": 5e-05}
{"train_loss": 1.9980717897415161, "global_step": 363269, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.072922468185425, "global_step": 363270, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.096359968185425, "global_step": 363271, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.073493242263794, "global_step": 363272, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1682205200195312, "global_step": 363273, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0803093910217285, "global_step": 363274, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0774152278900146, "global_step": 363275, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1863913536071777, "global_step": 363276, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1210808753967285, "global_step": 363277, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.149888515472412, "global_step": 363278, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.018638849258423, "global_step": 363279, "epoch": 724, "lr": 5e-05}
{"train_loss": 1.9844882488250732, "global_step": 363280, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1385200023651123, "global_step": 363281, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0662004947662354, "global_step": 363282, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0980992317199707, "global_step": 363283, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1235392093658447, "global_step": 363284, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.175163507461548, "global_step": 363285, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1143455505371094, "global_step": 363286, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.05188250541687, "global_step": 363287, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.083484649658203, "global_step": 363288, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0624985694885254, "global_step": 363289, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1681861877441406, "global_step": 363290, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.068472146987915, "global_step": 363291, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.077043056488037, "global_step": 363292, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.128978729248047, "global_step": 363293, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1439480781555176, "global_step": 363294, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.13360857963562, "global_step": 363295, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.075958251953125, "global_step": 363296, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1559197902679443, "global_step": 363297, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.097352981567383, "global_step": 363298, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.148690938949585, "global_step": 363299, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.059941291809082, "global_step": 363300, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1437385082244873, "global_step": 363301, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1237475872039795, "global_step": 363302, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1333086490631104, "global_step": 363303, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.063647985458374, "global_step": 363304, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.08528995513916, "global_step": 363305, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.20701265335083, "global_step": 363306, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2272284030914307, "global_step": 363307, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0923542976379395, "global_step": 363308, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1123814582824707, "global_step": 363309, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1206624507904053, "global_step": 363310, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.008166551589966, "global_step": 363311, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0311472415924072, "global_step": 363312, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.10664963722229, "global_step": 363313, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.101790189743042, "global_step": 363314, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.028263568878174, "global_step": 363315, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1567771434783936, "global_step": 363316, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0756478309631348, "global_step": 363317, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1458470821380615, "global_step": 363318, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.17159104347229, "global_step": 363319, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.186450481414795, "global_step": 363320, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.193293809890747, "global_step": 363321, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0021286010742188, "global_step": 363322, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1141700744628906, "global_step": 363323, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.077491044998169, "global_step": 363324, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.197676658630371, "global_step": 363325, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.081394672393799, "global_step": 363326, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.146348714828491, "global_step": 363327, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.078073501586914, "global_step": 363328, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.058243751525879, "global_step": 363329, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.072925567626953, "global_step": 363330, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.081535577774048, "global_step": 363331, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.162111759185791, "global_step": 363332, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.117173910140991, "global_step": 363333, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0894429683685303, "global_step": 363334, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1351633071899414, "global_step": 363335, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.098308801651001, "global_step": 363336, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1380984783172607, "global_step": 363337, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0954275131225586, "global_step": 363338, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.227595806121826, "global_step": 363339, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.093689203262329, "global_step": 363340, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0749781131744385, "global_step": 363341, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1263365745544434, "global_step": 363342, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2243263721466064, "global_step": 363343, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.19175124168396, "global_step": 363344, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0802202224731445, "global_step": 363345, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1190743446350098, "global_step": 363346, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0683162212371826, "global_step": 363347, "epoch": 724, "lr": 5e-05}
{"train_loss": 1.9920597076416016, "global_step": 363348, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.076756238937378, "global_step": 363349, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0330638885498047, "global_step": 363350, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.131284475326538, "global_step": 363351, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1615383625030518, "global_step": 363352, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1025421619415283, "global_step": 363353, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1483800411224365, "global_step": 363354, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2211058139801025, "global_step": 363355, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.100813150405884, "global_step": 363356, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0313634872436523, "global_step": 363357, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.07318115234375, "global_step": 363358, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0804738998413086, "global_step": 363359, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0646893978118896, "global_step": 363360, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1345691680908203, "global_step": 363361, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.090583324432373, "global_step": 363362, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2194039821624756, "global_step": 363363, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.137563705444336, "global_step": 363364, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1236116886138916, "global_step": 363365, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1766409873962402, "global_step": 363366, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1109507083892822, "global_step": 363367, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1187357902526855, "global_step": 363368, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1433258056640625, "global_step": 363369, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0992591381073, "global_step": 363370, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1573052406311035, "global_step": 363371, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0660390853881836, "global_step": 363372, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.066983461380005, "global_step": 363373, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1312685012817383, "global_step": 363374, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.171764850616455, "global_step": 363375, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1370532512664795, "global_step": 363376, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0758399963378906, "global_step": 363377, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.068288564682007, "global_step": 363378, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.124790906906128, "global_step": 363379, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.114509105682373, "global_step": 363380, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.100738048553467, "global_step": 363381, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1174662113189697, "global_step": 363382, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.142890691757202, "global_step": 363383, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1182258129119873, "global_step": 363384, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.101142406463623, "global_step": 363385, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.065121650695801, "global_step": 363386, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.126542568206787, "global_step": 363387, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2173449993133545, "global_step": 363388, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1178736686706543, "global_step": 363389, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1117701530456543, "global_step": 363390, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.108546257019043, "global_step": 363391, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.117574691772461, "global_step": 363392, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2218990325927734, "global_step": 363393, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0305919647216797, "global_step": 363394, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0686795711517334, "global_step": 363395, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.074331045150757, "global_step": 363396, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1209654808044434, "global_step": 363397, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1493000984191895, "global_step": 363398, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1597962379455566, "global_step": 363399, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1518561840057373, "global_step": 363400, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.053673505783081, "global_step": 363401, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1959164142608643, "global_step": 363402, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.127819776535034, "global_step": 363403, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1764872074127197, "global_step": 363404, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.074610471725464, "global_step": 363405, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.114225149154663, "global_step": 363406, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.217264175415039, "global_step": 363407, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.140413999557495, "global_step": 363408, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.167917013168335, "global_step": 363409, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2025418281555176, "global_step": 363410, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1150104999542236, "global_step": 363411, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.067182779312134, "global_step": 363412, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1649177074432373, "global_step": 363413, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.090959072113037, "global_step": 363414, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.120424270629883, "global_step": 363415, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1161880493164062, "global_step": 363416, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.125143527984619, "global_step": 363417, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0868983268737793, "global_step": 363418, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.058767557144165, "global_step": 363419, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1770591735839844, "global_step": 363420, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1730239391326904, "global_step": 363421, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1059138774871826, "global_step": 363422, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.115722894668579, "global_step": 363423, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.099464178085327, "global_step": 363424, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.107147216796875, "global_step": 363425, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.093306064605713, "global_step": 363426, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.142436981201172, "global_step": 363427, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1590588092803955, "global_step": 363428, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1820647716522217, "global_step": 363429, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.098926305770874, "global_step": 363430, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.148336172103882, "global_step": 363431, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1174001693725586, "global_step": 363432, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1534852981567383, "global_step": 363433, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0696628093719482, "global_step": 363434, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.11862850189209, "global_step": 363435, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0787932872772217, "global_step": 363436, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.132080316543579, "global_step": 363437, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.119601249694824, "global_step": 363438, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.077688694000244, "global_step": 363439, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1706461906433105, "global_step": 363440, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.083656072616577, "global_step": 363441, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.101081371307373, "global_step": 363442, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1648426055908203, "global_step": 363443, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.225595235824585, "global_step": 363444, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.230980157852173, "global_step": 363445, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1779658794403076, "global_step": 363446, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1149203777313232, "global_step": 363447, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1208252906799316, "global_step": 363448, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.081904888153076, "global_step": 363449, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.150050640106201, "global_step": 363450, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0323715209960938, "global_step": 363451, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1054270267486572, "global_step": 363452, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.089895725250244, "global_step": 363453, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1556177139282227, "global_step": 363454, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0978047847747803, "global_step": 363455, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.072640895843506, "global_step": 363456, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.188181161880493, "global_step": 363457, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.086317777633667, "global_step": 363458, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.144815444946289, "global_step": 363459, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1182239055633545, "global_step": 363460, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0780270099639893, "global_step": 363461, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0348453521728516, "global_step": 363462, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.148324728012085, "global_step": 363463, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.021876811981201, "global_step": 363464, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1162426471710205, "global_step": 363465, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0760183334350586, "global_step": 363466, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2055487632751465, "global_step": 363467, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1323204040527344, "global_step": 363468, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.17173433303833, "global_step": 363469, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.101616382598877, "global_step": 363470, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.138965606689453, "global_step": 363471, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1307156085968018, "global_step": 363472, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0773751735687256, "global_step": 363473, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.123983860015869, "global_step": 363474, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0697765350341797, "global_step": 363475, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.174794912338257, "global_step": 363476, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2067737579345703, "global_step": 363477, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1359457969665527, "global_step": 363478, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1351869106292725, "global_step": 363479, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.119121551513672, "global_step": 363480, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1333322525024414, "global_step": 363481, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.165163278579712, "global_step": 363482, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0963456630706787, "global_step": 363483, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0558133125305176, "global_step": 363484, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0654447078704834, "global_step": 363485, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.086332082748413, "global_step": 363486, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.194756507873535, "global_step": 363487, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1967341899871826, "global_step": 363488, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1016931533813477, "global_step": 363489, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.124103307723999, "global_step": 363490, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.195584774017334, "global_step": 363491, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1336069107055664, "global_step": 363492, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1510393619537354, "global_step": 363493, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0749027729034424, "global_step": 363494, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1262221336364746, "global_step": 363495, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.038240909576416, "global_step": 363496, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1074819564819336, "global_step": 363497, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.0135715007781982, "global_step": 363498, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.057133436203003, "global_step": 363499, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1038646697998047, "global_step": 363500, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1975901126861572, "global_step": 363501, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.142367362976074, "global_step": 363502, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.2115468978881836, "global_step": 363503, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.021871328353882, "global_step": 363504, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.075606346130371, "global_step": 363505, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.105091094970703, "global_step": 363506, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.1099021434783936, "global_step": 363507, "epoch": 724, "lr": 5e-05}
{"train_loss": 2.149946928024292, "global_step": 363508, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1163060665130615, "global_step": 363509, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.02352237701416, "global_step": 363510, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1448237895965576, "global_step": 363511, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.057591199874878, "global_step": 363512, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0123209953308105, "global_step": 363513, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.058945894241333, "global_step": 363514, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0512876510620117, "global_step": 363515, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0121939182281494, "global_step": 363516, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.12140154838562, "global_step": 363517, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2505340576171875, "global_step": 363518, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1464641094207764, "global_step": 363519, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.068350315093994, "global_step": 363520, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0594098567962646, "global_step": 363521, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.211334466934204, "global_step": 363522, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.115607738494873, "global_step": 363523, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.106599807739258, "global_step": 363524, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.075732946395874, "global_step": 363525, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.062527894973755, "global_step": 363526, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0808165073394775, "global_step": 363527, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.215240716934204, "global_step": 363528, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.120055913925171, "global_step": 363529, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0704386234283447, "global_step": 363530, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.102701425552368, "global_step": 363531, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2079625129699707, "global_step": 363532, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0701215267181396, "global_step": 363533, "epoch": 725, "lr": 5e-05}
{"train_loss": 1.9931228160858154, "global_step": 363534, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.106489658355713, "global_step": 363535, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1386938095092773, "global_step": 363536, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.185786247253418, "global_step": 363537, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.108896255493164, "global_step": 363538, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0956947803497314, "global_step": 363539, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.114638566970825, "global_step": 363540, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.144699811935425, "global_step": 363541, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1510894298553467, "global_step": 363542, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1293487548828125, "global_step": 363543, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1332037448883057, "global_step": 363544, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1701791286468506, "global_step": 363545, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1357173919677734, "global_step": 363546, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0607054233551025, "global_step": 363547, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1037521362304688, "global_step": 363548, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.12917160987854, "global_step": 363549, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0699758529663086, "global_step": 363550, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.030588388442993, "global_step": 363551, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.148944854736328, "global_step": 363552, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1266794204711914, "global_step": 363553, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.152312755584717, "global_step": 363554, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.108027935028076, "global_step": 363555, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0337836742401123, "global_step": 363556, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0624587535858154, "global_step": 363557, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0903372764587402, "global_step": 363558, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1213490962982178, "global_step": 363559, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.072892427444458, "global_step": 363560, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0406739711761475, "global_step": 363561, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.096679449081421, "global_step": 363562, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0422327518463135, "global_step": 363563, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1086490154266357, "global_step": 363564, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.137564182281494, "global_step": 363565, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0564091205596924, "global_step": 363566, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.131823778152466, "global_step": 363567, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.131734609603882, "global_step": 363568, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.050494432449341, "global_step": 363569, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1033575534820557, "global_step": 363570, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.140442132949829, "global_step": 363571, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.104926824569702, "global_step": 363572, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1047158241271973, "global_step": 363573, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.190565824508667, "global_step": 363574, "epoch": 725, "lr": 5e-05}
{"train_loss": 1.9907959699630737, "global_step": 363575, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0874760150909424, "global_step": 363576, "epoch": 725, "lr": 5e-05}
{"train_loss": 1.9831032752990723, "global_step": 363577, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0505692958831787, "global_step": 363578, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0993926525115967, "global_step": 363579, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.053988456726074, "global_step": 363580, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0563833713531494, "global_step": 363581, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.160156011581421, "global_step": 363582, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1120312213897705, "global_step": 363583, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0852553844451904, "global_step": 363584, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.154177665710449, "global_step": 363585, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.08540940284729, "global_step": 363586, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1277804374694824, "global_step": 363587, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1444103717803955, "global_step": 363588, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.209031105041504, "global_step": 363589, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1586766242980957, "global_step": 363590, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.094424247741699, "global_step": 363591, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0991408824920654, "global_step": 363592, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1138739585876465, "global_step": 363593, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1556317806243896, "global_step": 363594, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.127887487411499, "global_step": 363595, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0634708404541016, "global_step": 363596, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.04148006439209, "global_step": 363597, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.160444974899292, "global_step": 363598, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.063817262649536, "global_step": 363599, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.148160457611084, "global_step": 363600, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.126030206680298, "global_step": 363601, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1553707122802734, "global_step": 363602, "epoch": 725, "lr": 5e-05}
{"train_loss": 1.9914436340332031, "global_step": 363603, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0182459354400635, "global_step": 363604, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.064753293991089, "global_step": 363605, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.128727436065674, "global_step": 363606, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1454918384552, "global_step": 363607, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1391329765319824, "global_step": 363608, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0257790088653564, "global_step": 363609, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2609457969665527, "global_step": 363610, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0565314292907715, "global_step": 363611, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.056138038635254, "global_step": 363612, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.134892225265503, "global_step": 363613, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.237476348876953, "global_step": 363614, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0861220359802246, "global_step": 363615, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.124128818511963, "global_step": 363616, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1673123836517334, "global_step": 363617, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.137721538543701, "global_step": 363618, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0546319484710693, "global_step": 363619, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.104321241378784, "global_step": 363620, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1971161365509033, "global_step": 363621, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0914738178253174, "global_step": 363622, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.137812376022339, "global_step": 363623, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0820562839508057, "global_step": 363624, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.056579828262329, "global_step": 363625, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.089414119720459, "global_step": 363626, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.112473726272583, "global_step": 363627, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1895911693573, "global_step": 363628, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1303229331970215, "global_step": 363629, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.107297658920288, "global_step": 363630, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0769224166870117, "global_step": 363631, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0797393321990967, "global_step": 363632, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0204479694366455, "global_step": 363633, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0944876670837402, "global_step": 363634, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.091097593307495, "global_step": 363635, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0719571113586426, "global_step": 363636, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1280927658081055, "global_step": 363637, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0978024005889893, "global_step": 363638, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.149244785308838, "global_step": 363639, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1101279258728027, "global_step": 363640, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1565968990325928, "global_step": 363641, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.129070281982422, "global_step": 363642, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0918798446655273, "global_step": 363643, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.09462571144104, "global_step": 363644, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0351202487945557, "global_step": 363645, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0255274772644043, "global_step": 363646, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.157209634780884, "global_step": 363647, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.134188175201416, "global_step": 363648, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0878376960754395, "global_step": 363649, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.049877643585205, "global_step": 363650, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.086231231689453, "global_step": 363651, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.156726360321045, "global_step": 363652, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1066975593566895, "global_step": 363653, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1761186122894287, "global_step": 363654, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.116706609725952, "global_step": 363655, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.086642026901245, "global_step": 363656, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1108734607696533, "global_step": 363657, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0942368507385254, "global_step": 363658, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.216002941131592, "global_step": 363659, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1290981769561768, "global_step": 363660, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1649208068847656, "global_step": 363661, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1087775230407715, "global_step": 363662, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0579004287719727, "global_step": 363663, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0904436111450195, "global_step": 363664, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.146711587905884, "global_step": 363665, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.18999981880188, "global_step": 363666, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0685274600982666, "global_step": 363667, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.058629274368286, "global_step": 363668, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0688624382019043, "global_step": 363669, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1462249755859375, "global_step": 363670, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0333657264709473, "global_step": 363671, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.062947988510132, "global_step": 363672, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1819546222686768, "global_step": 363673, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0827901363372803, "global_step": 363674, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0937464237213135, "global_step": 363675, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.087740659713745, "global_step": 363676, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0717899799346924, "global_step": 363677, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0979440212249756, "global_step": 363678, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.180417060852051, "global_step": 363679, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0745348930358887, "global_step": 363680, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.104081153869629, "global_step": 363681, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.131863594055176, "global_step": 363682, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1530489921569824, "global_step": 363683, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.054082155227661, "global_step": 363684, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0157456398010254, "global_step": 363685, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1262848377227783, "global_step": 363686, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0904440879821777, "global_step": 363687, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0395684242248535, "global_step": 363688, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0261549949645996, "global_step": 363689, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1055898666381836, "global_step": 363690, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0271153450012207, "global_step": 363691, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.116370439529419, "global_step": 363692, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.114661931991577, "global_step": 363693, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1529343128204346, "global_step": 363694, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1088879108428955, "global_step": 363695, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.219787359237671, "global_step": 363696, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.157170295715332, "global_step": 363697, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.20127272605896, "global_step": 363698, "epoch": 725, "lr": 5e-05}
{"train_loss": 1.9910509586334229, "global_step": 363699, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.123645305633545, "global_step": 363700, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1042063236236572, "global_step": 363701, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0683140754699707, "global_step": 363702, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.065142869949341, "global_step": 363703, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.154977321624756, "global_step": 363704, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1344172954559326, "global_step": 363705, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1071674823760986, "global_step": 363706, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1387417316436768, "global_step": 363707, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.122387170791626, "global_step": 363708, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0597193241119385, "global_step": 363709, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.108119010925293, "global_step": 363710, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.096012592315674, "global_step": 363711, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.097578763961792, "global_step": 363712, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1484017372131348, "global_step": 363713, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1729869842529297, "global_step": 363714, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1016087532043457, "global_step": 363715, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1639039516448975, "global_step": 363716, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0284695625305176, "global_step": 363717, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.095078468322754, "global_step": 363718, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.06426739692688, "global_step": 363719, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1589667797088623, "global_step": 363720, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1596155166625977, "global_step": 363721, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1344552040100098, "global_step": 363722, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.055992603302002, "global_step": 363723, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.141836166381836, "global_step": 363724, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1509714126586914, "global_step": 363725, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1894538402557373, "global_step": 363726, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.03002667427063, "global_step": 363727, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0089197158813477, "global_step": 363728, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0151255130767822, "global_step": 363729, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.049870252609253, "global_step": 363730, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.199946641921997, "global_step": 363731, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1258814334869385, "global_step": 363732, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0988805294036865, "global_step": 363733, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.12131929397583, "global_step": 363734, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0376687049865723, "global_step": 363735, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.159590721130371, "global_step": 363736, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.125441074371338, "global_step": 363737, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.191404342651367, "global_step": 363738, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1089248657226562, "global_step": 363739, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1054887771606445, "global_step": 363740, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1662232875823975, "global_step": 363741, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0313193798065186, "global_step": 363742, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0985171794891357, "global_step": 363743, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1308460235595703, "global_step": 363744, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1094837188720703, "global_step": 363745, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1948893070220947, "global_step": 363746, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1786398887634277, "global_step": 363747, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.074204206466675, "global_step": 363748, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.186958074569702, "global_step": 363749, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.07852840423584, "global_step": 363750, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1450061798095703, "global_step": 363751, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1223220825195312, "global_step": 363752, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0815720558166504, "global_step": 363753, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1140623092651367, "global_step": 363754, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1302123069763184, "global_step": 363755, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.176116704940796, "global_step": 363756, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0967681407928467, "global_step": 363757, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.160975933074951, "global_step": 363758, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0237607955932617, "global_step": 363759, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.088322162628174, "global_step": 363760, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1057684421539307, "global_step": 363761, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1139488220214844, "global_step": 363762, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.164332389831543, "global_step": 363763, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0431737899780273, "global_step": 363764, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0896542072296143, "global_step": 363765, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.121338367462158, "global_step": 363766, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2019710540771484, "global_step": 363767, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0845766067504883, "global_step": 363768, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.053753137588501, "global_step": 363769, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.179262161254883, "global_step": 363770, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1719515323638916, "global_step": 363771, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0505051612854004, "global_step": 363772, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0810482501983643, "global_step": 363773, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.135277271270752, "global_step": 363774, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.092824697494507, "global_step": 363775, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0505595207214355, "global_step": 363776, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.129549264907837, "global_step": 363777, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0923380851745605, "global_step": 363778, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.077324151992798, "global_step": 363779, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0868537425994873, "global_step": 363780, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.114323139190674, "global_step": 363781, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0948328971862793, "global_step": 363782, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0300395488739014, "global_step": 363783, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.130798101425171, "global_step": 363784, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.081026315689087, "global_step": 363785, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1083364486694336, "global_step": 363786, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.063138484954834, "global_step": 363787, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.108988046646118, "global_step": 363788, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0706746578216553, "global_step": 363789, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0888144969940186, "global_step": 363790, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.071596622467041, "global_step": 363791, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0630407333374023, "global_step": 363792, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.075587749481201, "global_step": 363793, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0851924419403076, "global_step": 363794, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.12580943107605, "global_step": 363795, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1019744873046875, "global_step": 363796, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2032763957977295, "global_step": 363797, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0436758995056152, "global_step": 363798, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.047239065170288, "global_step": 363799, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.088230848312378, "global_step": 363800, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1674110889434814, "global_step": 363801, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.095182180404663, "global_step": 363802, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0344321727752686, "global_step": 363803, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1216044425964355, "global_step": 363804, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1006906032562256, "global_step": 363805, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.02534818649292, "global_step": 363806, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.106905698776245, "global_step": 363807, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.120486259460449, "global_step": 363808, "epoch": 725, "lr": 5e-05}
{"train_loss": 1.9883811473846436, "global_step": 363809, "epoch": 725, "lr": 5e-05}
{"train_loss": 1.9973716735839844, "global_step": 363810, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.170351982116699, "global_step": 363811, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.07312273979187, "global_step": 363812, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1426572799682617, "global_step": 363813, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.069566249847412, "global_step": 363814, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.038004159927368, "global_step": 363815, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.130880355834961, "global_step": 363816, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1177713871002197, "global_step": 363817, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0972907543182373, "global_step": 363818, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2181038856506348, "global_step": 363819, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1321911811828613, "global_step": 363820, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1253082752227783, "global_step": 363821, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.065324306488037, "global_step": 363822, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1527483463287354, "global_step": 363823, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.098813056945801, "global_step": 363824, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.008409261703491, "global_step": 363825, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.116121530532837, "global_step": 363826, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0529251098632812, "global_step": 363827, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1508703231811523, "global_step": 363828, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.155226945877075, "global_step": 363829, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1576528549194336, "global_step": 363830, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0442214012145996, "global_step": 363831, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1185812950134277, "global_step": 363832, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1057326793670654, "global_step": 363833, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.12276291847229, "global_step": 363834, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.044119358062744, "global_step": 363835, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1391570568084717, "global_step": 363836, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.126905918121338, "global_step": 363837, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1176977157592773, "global_step": 363838, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1544082164764404, "global_step": 363839, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1014935970306396, "global_step": 363840, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2182765007019043, "global_step": 363841, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0763344764709473, "global_step": 363842, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1382622718811035, "global_step": 363843, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0854034423828125, "global_step": 363844, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0568759441375732, "global_step": 363845, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.180911064147949, "global_step": 363846, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0504672527313232, "global_step": 363847, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.056806802749634, "global_step": 363848, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.185751438140869, "global_step": 363849, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.093247175216675, "global_step": 363850, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0522303581237793, "global_step": 363851, "epoch": 725, "lr": 5e-05}
{"train_loss": 1.9775965213775635, "global_step": 363852, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1906869411468506, "global_step": 363853, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.059384822845459, "global_step": 363854, "epoch": 725, "lr": 5e-05}
{"train_loss": 1.998137354850769, "global_step": 363855, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.070988416671753, "global_step": 363856, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0869529247283936, "global_step": 363857, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.121192455291748, "global_step": 363858, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0784969329833984, "global_step": 363859, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.126710891723633, "global_step": 363860, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.139613389968872, "global_step": 363861, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0535309314727783, "global_step": 363862, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.080488920211792, "global_step": 363863, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1640961170196533, "global_step": 363864, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.105087995529175, "global_step": 363865, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.197477102279663, "global_step": 363866, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.109539270401001, "global_step": 363867, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1178886890411377, "global_step": 363868, "epoch": 725, "lr": 5e-05}
{"train_loss": 1.9874670505523682, "global_step": 363869, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.034714460372925, "global_step": 363870, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.098759889602661, "global_step": 363871, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.074453592300415, "global_step": 363872, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1109368801116943, "global_step": 363873, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.07317852973938, "global_step": 363874, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.053812026977539, "global_step": 363875, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0520284175872803, "global_step": 363876, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.154123067855835, "global_step": 363877, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.079620122909546, "global_step": 363878, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.113023281097412, "global_step": 363879, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.178339958190918, "global_step": 363880, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.095090627670288, "global_step": 363881, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.093827962875366, "global_step": 363882, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.143397331237793, "global_step": 363883, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.049309492111206, "global_step": 363884, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1548218727111816, "global_step": 363885, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.075148105621338, "global_step": 363886, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1993367671966553, "global_step": 363887, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1173272132873535, "global_step": 363888, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1149113178253174, "global_step": 363889, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1686227321624756, "global_step": 363890, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.177027702331543, "global_step": 363891, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0782196521759033, "global_step": 363892, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0799155235290527, "global_step": 363893, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.132138252258301, "global_step": 363894, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1187379360198975, "global_step": 363895, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0536293983459473, "global_step": 363896, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.091188669204712, "global_step": 363897, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0811877250671387, "global_step": 363898, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0915982723236084, "global_step": 363899, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.080660104751587, "global_step": 363900, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.073945999145508, "global_step": 363901, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0419912338256836, "global_step": 363902, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.061983585357666, "global_step": 363903, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.105149745941162, "global_step": 363904, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0807743072509766, "global_step": 363905, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.089905261993408, "global_step": 363906, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1621501445770264, "global_step": 363907, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.064314365386963, "global_step": 363908, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1605100631713867, "global_step": 363909, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.140153408050537, "global_step": 363910, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.044187307357788, "global_step": 363911, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.070685863494873, "global_step": 363912, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0240931510925293, "global_step": 363913, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0282726287841797, "global_step": 363914, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0799365043640137, "global_step": 363915, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.096121311187744, "global_step": 363916, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0420258045196533, "global_step": 363917, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.136617422103882, "global_step": 363918, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0917935371398926, "global_step": 363919, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.064734935760498, "global_step": 363920, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1697494983673096, "global_step": 363921, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.12307071685791, "global_step": 363922, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.040099859237671, "global_step": 363923, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.116028070449829, "global_step": 363924, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.057892322540283, "global_step": 363925, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1423864364624023, "global_step": 363926, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.090869188308716, "global_step": 363927, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0807785987854004, "global_step": 363928, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.089282274246216, "global_step": 363929, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.001174211502075, "global_step": 363930, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1681342124938965, "global_step": 363931, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0556180477142334, "global_step": 363932, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1270546913146973, "global_step": 363933, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0998916625976562, "global_step": 363934, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1218831539154053, "global_step": 363935, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1043763160705566, "global_step": 363936, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.095942735671997, "global_step": 363937, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.085829496383667, "global_step": 363938, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.162222385406494, "global_step": 363939, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.104337453842163, "global_step": 363940, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.067363739013672, "global_step": 363941, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0666935443878174, "global_step": 363942, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2063212394714355, "global_step": 363943, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0338995456695557, "global_step": 363944, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.137519598007202, "global_step": 363945, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1108601093292236, "global_step": 363946, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.157672166824341, "global_step": 363947, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.111882448196411, "global_step": 363948, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1358113288879395, "global_step": 363949, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.126890182495117, "global_step": 363950, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0833046436309814, "global_step": 363951, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.169275999069214, "global_step": 363952, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.126925468444824, "global_step": 363953, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1511788368225098, "global_step": 363954, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2216761112213135, "global_step": 363955, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.122870683670044, "global_step": 363956, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1046767234802246, "global_step": 363957, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.088423252105713, "global_step": 363958, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.128190755844116, "global_step": 363959, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.079975128173828, "global_step": 363960, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.062419891357422, "global_step": 363961, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0621109008789062, "global_step": 363962, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.093295097351074, "global_step": 363963, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0398077964782715, "global_step": 363964, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.076014757156372, "global_step": 363965, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.104724168777466, "global_step": 363966, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1797983646392822, "global_step": 363967, "epoch": 725, "lr": 5e-05}
{"train_loss": 1.9862946271896362, "global_step": 363968, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1836938858032227, "global_step": 363969, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.109267473220825, "global_step": 363970, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2039389610290527, "global_step": 363971, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1252646446228027, "global_step": 363972, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1366212368011475, "global_step": 363973, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.153944730758667, "global_step": 363974, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1540050506591797, "global_step": 363975, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0638442039489746, "global_step": 363976, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.016634702682495, "global_step": 363977, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.081779718399048, "global_step": 363978, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.068955659866333, "global_step": 363979, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.054924964904785, "global_step": 363980, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.145677089691162, "global_step": 363981, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.118499279022217, "global_step": 363982, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.024094343185425, "global_step": 363983, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.17948055267334, "global_step": 363984, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.135497808456421, "global_step": 363985, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0940797328948975, "global_step": 363986, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1199796199798584, "global_step": 363987, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.147960662841797, "global_step": 363988, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0910720825195312, "global_step": 363989, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.135016441345215, "global_step": 363990, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0496456623077393, "global_step": 363991, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1360514163970947, "global_step": 363992, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0936732292175293, "global_step": 363993, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.173762559890747, "global_step": 363994, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.111290216445923, "global_step": 363995, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.123317003250122, "global_step": 363996, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0339128971099854, "global_step": 363997, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2410740852355957, "global_step": 363998, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0602030754089355, "global_step": 363999, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1198456287384033, "global_step": 364000, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0089352130889893, "global_step": 364001, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1481006145477295, "global_step": 364002, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1058058738708496, "global_step": 364003, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1203413009643555, "global_step": 364004, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.103261947631836, "global_step": 364005, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.090379238128662, "global_step": 364006, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.256089210510254, "global_step": 364007, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.090024471282959, "global_step": 364008, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.15773344039917, "global_step": 364009, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.093400239944458, "global_step": 364010, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.055359363555908, "global_step": 364011, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0368640422821045, "global_step": 364012, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.11079740524292, "global_step": 364013, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0882341861724854, "global_step": 364014, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1162400245666504, "global_step": 364015, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1138439178466797, "global_step": 364016, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.170947790145874, "global_step": 364017, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1141517162323, "global_step": 364018, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.147268056869507, "global_step": 364019, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2221477031707764, "global_step": 364020, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1058590412139893, "global_step": 364021, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.086472988128662, "global_step": 364022, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1238012313842773, "global_step": 364023, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.134016990661621, "global_step": 364024, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.169302463531494, "global_step": 364025, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0922465324401855, "global_step": 364026, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1173181533813477, "global_step": 364027, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0400636196136475, "global_step": 364028, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.110293388366699, "global_step": 364029, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.067136287689209, "global_step": 364030, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1025097370147705, "global_step": 364031, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1426000595092773, "global_step": 364032, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.110208511352539, "global_step": 364033, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.155148506164551, "global_step": 364034, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.079254627227783, "global_step": 364035, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.107623815536499, "global_step": 364036, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1119191646575928, "global_step": 364037, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1458542346954346, "global_step": 364038, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1648154258728027, "global_step": 364039, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0870864391326904, "global_step": 364040, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.116617441177368, "global_step": 364041, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1216092109680176, "global_step": 364042, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1148288249969482, "global_step": 364043, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1996655464172363, "global_step": 364044, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.06378436088562, "global_step": 364045, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0920000076293945, "global_step": 364046, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2056078910827637, "global_step": 364047, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.009577989578247, "global_step": 364048, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1355299949645996, "global_step": 364049, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1256906986236572, "global_step": 364050, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.162950038909912, "global_step": 364051, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1350109577178955, "global_step": 364052, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.092907190322876, "global_step": 364053, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1519839763641357, "global_step": 364054, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1544394493103027, "global_step": 364055, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1062400341033936, "global_step": 364056, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1262550354003906, "global_step": 364057, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.170793294906616, "global_step": 364058, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.192234754562378, "global_step": 364059, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0877296924591064, "global_step": 364060, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.169835090637207, "global_step": 364061, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0418643951416016, "global_step": 364062, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0758779048919678, "global_step": 364063, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0979623794555664, "global_step": 364064, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.114412307739258, "global_step": 364065, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0962753295898438, "global_step": 364066, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.113415002822876, "global_step": 364067, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1464736461639404, "global_step": 364068, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0925378799438477, "global_step": 364069, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1323082447052, "global_step": 364070, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0889334678649902, "global_step": 364071, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.126555919647217, "global_step": 364072, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.113922119140625, "global_step": 364073, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1146838665008545, "global_step": 364074, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1066596508026123, "global_step": 364075, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.046377658843994, "global_step": 364076, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0370686054229736, "global_step": 364077, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1145660877227783, "global_step": 364078, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.115896701812744, "global_step": 364079, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1369900703430176, "global_step": 364080, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.119190216064453, "global_step": 364081, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1126315593719482, "global_step": 364082, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0384671688079834, "global_step": 364083, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.141231060028076, "global_step": 364084, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0874006748199463, "global_step": 364085, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.096226930618286, "global_step": 364086, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1080737113952637, "global_step": 364087, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1063435077667236, "global_step": 364088, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.07816481590271, "global_step": 364089, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1143243312835693, "global_step": 364090, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.118227958679199, "global_step": 364091, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0929315090179443, "global_step": 364092, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.165473699569702, "global_step": 364093, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.118201732635498, "global_step": 364094, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.174440860748291, "global_step": 364095, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0779690742492676, "global_step": 364096, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.059046983718872, "global_step": 364097, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1051371097564697, "global_step": 364098, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0250391960144043, "global_step": 364099, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.113619565963745, "global_step": 364100, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0709829330444336, "global_step": 364101, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0933735370635986, "global_step": 364102, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0693836212158203, "global_step": 364103, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0699310302734375, "global_step": 364104, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0660109519958496, "global_step": 364105, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.150547742843628, "global_step": 364106, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0825867652893066, "global_step": 364107, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.108522891998291, "global_step": 364108, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0759568214416504, "global_step": 364109, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1758511066436768, "global_step": 364110, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.086683511734009, "global_step": 364111, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.108538866043091, "global_step": 364112, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2194314002990723, "global_step": 364113, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.107738494873047, "global_step": 364114, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.021432638168335, "global_step": 364115, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.015687942504883, "global_step": 364116, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1093764305114746, "global_step": 364117, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.146913766860962, "global_step": 364118, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0785744190216064, "global_step": 364119, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.244572162628174, "global_step": 364120, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1446573734283447, "global_step": 364121, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2030372619628906, "global_step": 364122, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0631446838378906, "global_step": 364123, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1403536796569824, "global_step": 364124, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.087312936782837, "global_step": 364125, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.079798936843872, "global_step": 364126, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.159395217895508, "global_step": 364127, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.116220235824585, "global_step": 364128, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.07094144821167, "global_step": 364129, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.099061965942383, "global_step": 364130, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1828885078430176, "global_step": 364131, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1129653453826904, "global_step": 364132, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.124494791030884, "global_step": 364133, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1746034622192383, "global_step": 364134, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1115171909332275, "global_step": 364135, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0586326122283936, "global_step": 364136, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.104276180267334, "global_step": 364137, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.173532009124756, "global_step": 364138, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0936923027038574, "global_step": 364139, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1439096927642822, "global_step": 364140, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.142749071121216, "global_step": 364141, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.153878927230835, "global_step": 364142, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.11804461479187, "global_step": 364143, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0958478450775146, "global_step": 364144, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1632957458496094, "global_step": 364145, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0517966747283936, "global_step": 364146, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1520514488220215, "global_step": 364147, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.142674684524536, "global_step": 364148, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.015406608581543, "global_step": 364149, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0380449295043945, "global_step": 364150, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1681041717529297, "global_step": 364151, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.137091875076294, "global_step": 364152, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1040844917297363, "global_step": 364153, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0618975162506104, "global_step": 364154, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0897092819213867, "global_step": 364155, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1036040782928467, "global_step": 364156, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1728506088256836, "global_step": 364157, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1795310974121094, "global_step": 364158, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.122368097305298, "global_step": 364159, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1013166904449463, "global_step": 364160, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1832313537597656, "global_step": 364161, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.200927972793579, "global_step": 364162, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.153634548187256, "global_step": 364163, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.10214900970459, "global_step": 364164, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0668256282806396, "global_step": 364165, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2256221771240234, "global_step": 364166, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.004040002822876, "global_step": 364167, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0956923961639404, "global_step": 364168, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.111685276031494, "global_step": 364169, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.028160333633423, "global_step": 364170, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1095447540283203, "global_step": 364171, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0779712200164795, "global_step": 364172, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.147486925125122, "global_step": 364173, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1424732208251953, "global_step": 364174, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0267069339752197, "global_step": 364175, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.122462749481201, "global_step": 364176, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.103390693664551, "global_step": 364177, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0585243701934814, "global_step": 364178, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1139817237854004, "global_step": 364179, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.226825714111328, "global_step": 364180, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1072733402252197, "global_step": 364181, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.143928289413452, "global_step": 364182, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1522562503814697, "global_step": 364183, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.052671432495117, "global_step": 364184, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.06412410736084, "global_step": 364185, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1105005741119385, "global_step": 364186, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.104274272918701, "global_step": 364187, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1218481063842773, "global_step": 364188, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1867921352386475, "global_step": 364189, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1233694553375244, "global_step": 364190, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1838533878326416, "global_step": 364191, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0930373668670654, "global_step": 364192, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0563533306121826, "global_step": 364193, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1058967113494873, "global_step": 364194, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1673741340637207, "global_step": 364195, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0002710819244385, "global_step": 364196, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.174910068511963, "global_step": 364197, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0424234867095947, "global_step": 364198, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.150770664215088, "global_step": 364199, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0593791007995605, "global_step": 364200, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1228275299072266, "global_step": 364201, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0975959300994873, "global_step": 364202, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1619672775268555, "global_step": 364203, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.13668155670166, "global_step": 364204, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1626007556915283, "global_step": 364205, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0825791358947754, "global_step": 364206, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0680158138275146, "global_step": 364207, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.090843439102173, "global_step": 364208, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2033419609069824, "global_step": 364209, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1076436042785645, "global_step": 364210, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.092254638671875, "global_step": 364211, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.105513572692871, "global_step": 364212, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.086031436920166, "global_step": 364213, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0844688415527344, "global_step": 364214, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.150350570678711, "global_step": 364215, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1183266639709473, "global_step": 364216, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.088813066482544, "global_step": 364217, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1901168823242188, "global_step": 364218, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0666310787200928, "global_step": 364219, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.214423418045044, "global_step": 364220, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.198622703552246, "global_step": 364221, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.129246234893799, "global_step": 364222, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1256837844848633, "global_step": 364223, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.235560655593872, "global_step": 364224, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1205687522888184, "global_step": 364225, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.12333345413208, "global_step": 364226, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0890955924987793, "global_step": 364227, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.174748182296753, "global_step": 364228, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0848543643951416, "global_step": 364229, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.082608699798584, "global_step": 364230, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1123762130737305, "global_step": 364231, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0875771045684814, "global_step": 364232, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.11507248878479, "global_step": 364233, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1904518604278564, "global_step": 364234, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.16789174079895, "global_step": 364235, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2000732421875, "global_step": 364236, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.120084285736084, "global_step": 364237, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2184324264526367, "global_step": 364238, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0811264514923096, "global_step": 364239, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0877699851989746, "global_step": 364240, "epoch": 725, "lr": 5e-05}
{"train_loss": 1.9904922246932983, "global_step": 364241, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1021924018859863, "global_step": 364242, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.125910758972168, "global_step": 364243, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.121748924255371, "global_step": 364244, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0594396591186523, "global_step": 364245, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1309876441955566, "global_step": 364246, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0839805603027344, "global_step": 364247, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2522225379943848, "global_step": 364248, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.164574146270752, "global_step": 364249, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.201578378677368, "global_step": 364250, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0212011337280273, "global_step": 364251, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.095763921737671, "global_step": 364252, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.098921537399292, "global_step": 364253, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0952134132385254, "global_step": 364254, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.05983829498291, "global_step": 364255, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.126584529876709, "global_step": 364256, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0863466262817383, "global_step": 364257, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0448668003082275, "global_step": 364258, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.144901990890503, "global_step": 364259, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1679983139038086, "global_step": 364260, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1518185138702393, "global_step": 364261, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.072108268737793, "global_step": 364262, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1011300086975098, "global_step": 364263, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1037235260009766, "global_step": 364264, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.110966444015503, "global_step": 364265, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.214354991912842, "global_step": 364266, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1002602577209473, "global_step": 364267, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1068482398986816, "global_step": 364268, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.062774896621704, "global_step": 364269, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2032668590545654, "global_step": 364270, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.188575506210327, "global_step": 364271, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.161613702774048, "global_step": 364272, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1080644130706787, "global_step": 364273, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1825368404388428, "global_step": 364274, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0641443729400635, "global_step": 364275, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1450512409210205, "global_step": 364276, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.09731388092041, "global_step": 364277, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0928688049316406, "global_step": 364278, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.124084234237671, "global_step": 364279, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.227614402770996, "global_step": 364280, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.048344135284424, "global_step": 364281, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1593759059906006, "global_step": 364282, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1208841800689697, "global_step": 364283, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1346988677978516, "global_step": 364284, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.085402727127075, "global_step": 364285, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.096904754638672, "global_step": 364286, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.061936378479004, "global_step": 364287, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0638508796691895, "global_step": 364288, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1264491081237793, "global_step": 364289, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1479332447052, "global_step": 364290, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1699395179748535, "global_step": 364291, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1016342639923096, "global_step": 364292, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1189167499542236, "global_step": 364293, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1411726474761963, "global_step": 364294, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.116607904434204, "global_step": 364295, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.108161449432373, "global_step": 364296, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0815067291259766, "global_step": 364297, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.172178268432617, "global_step": 364298, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0253782272338867, "global_step": 364299, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.167065382003784, "global_step": 364300, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.154181957244873, "global_step": 364301, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0899744033813477, "global_step": 364302, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.087888240814209, "global_step": 364303, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0177738666534424, "global_step": 364304, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1462557315826416, "global_step": 364305, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0808017253875732, "global_step": 364306, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.047290563583374, "global_step": 364307, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0459606647491455, "global_step": 364308, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.167907238006592, "global_step": 364309, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.090571403503418, "global_step": 364310, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0701377391815186, "global_step": 364311, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.105726480484009, "global_step": 364312, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2255935668945312, "global_step": 364313, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.092402935028076, "global_step": 364314, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.02107572555542, "global_step": 364315, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.048114538192749, "global_step": 364316, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1007330417633057, "global_step": 364317, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.019481897354126, "global_step": 364318, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1068079471588135, "global_step": 364319, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0903773307800293, "global_step": 364320, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0871422290802, "global_step": 364321, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.165135145187378, "global_step": 364322, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1606605052948, "global_step": 364323, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.041332483291626, "global_step": 364324, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0249295234680176, "global_step": 364325, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.113973379135132, "global_step": 364326, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.197866916656494, "global_step": 364327, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0913290977478027, "global_step": 364328, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1083810329437256, "global_step": 364329, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.029742479324341, "global_step": 364330, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.125136613845825, "global_step": 364331, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.181936025619507, "global_step": 364332, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1231274604797363, "global_step": 364333, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.111274480819702, "global_step": 364334, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1186013221740723, "global_step": 364335, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.154387950897217, "global_step": 364336, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.114645004272461, "global_step": 364337, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.113852024078369, "global_step": 364338, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.05829119682312, "global_step": 364339, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1002213954925537, "global_step": 364340, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.029385805130005, "global_step": 364341, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0599348545074463, "global_step": 364342, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.018235683441162, "global_step": 364343, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.030970811843872, "global_step": 364344, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.077829360961914, "global_step": 364345, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1462059020996094, "global_step": 364346, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0929107666015625, "global_step": 364347, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.087322235107422, "global_step": 364348, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1801106929779053, "global_step": 364349, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0796139240264893, "global_step": 364350, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.18709397315979, "global_step": 364351, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1019980907440186, "global_step": 364352, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0820116996765137, "global_step": 364353, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1816604137420654, "global_step": 364354, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0223217010498047, "global_step": 364355, "epoch": 725, "lr": 5e-05}
{"train_loss": 1.96318519115448, "global_step": 364356, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1520638465881348, "global_step": 364357, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0805728435516357, "global_step": 364358, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.118014097213745, "global_step": 364359, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1164603233337402, "global_step": 364360, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.053774356842041, "global_step": 364361, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.193213701248169, "global_step": 364362, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.086724281311035, "global_step": 364363, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.141291856765747, "global_step": 364364, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1589295864105225, "global_step": 364365, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.011504888534546, "global_step": 364366, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.055691957473755, "global_step": 364367, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1046884059906006, "global_step": 364368, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.235365867614746, "global_step": 364369, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.081641674041748, "global_step": 364370, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1292545795440674, "global_step": 364371, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1863861083984375, "global_step": 364372, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0765225887298584, "global_step": 364373, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0251410007476807, "global_step": 364374, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.021193742752075, "global_step": 364375, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0835142135620117, "global_step": 364376, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.032057762145996, "global_step": 364377, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1228182315826416, "global_step": 364378, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.045091390609741, "global_step": 364379, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0751209259033203, "global_step": 364380, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.099421977996826, "global_step": 364381, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.154172658920288, "global_step": 364382, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.149710178375244, "global_step": 364383, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1576106548309326, "global_step": 364384, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.130666971206665, "global_step": 364385, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.078451156616211, "global_step": 364386, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.081141948699951, "global_step": 364387, "epoch": 725, "lr": 5e-05}
{"train_loss": 1.9880536794662476, "global_step": 364388, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1016111373901367, "global_step": 364389, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.165984630584717, "global_step": 364390, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.084531545639038, "global_step": 364391, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0777740478515625, "global_step": 364392, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0926730632781982, "global_step": 364393, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1720733642578125, "global_step": 364394, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.087877035140991, "global_step": 364395, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0649874210357666, "global_step": 364396, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.120266914367676, "global_step": 364397, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0582807064056396, "global_step": 364398, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0623698234558105, "global_step": 364399, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.109790563583374, "global_step": 364400, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.097238779067993, "global_step": 364401, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.118608236312866, "global_step": 364402, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1086862087249756, "global_step": 364403, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.08750057220459, "global_step": 364404, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.117941379547119, "global_step": 364405, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1087818145751953, "global_step": 364406, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1256632804870605, "global_step": 364407, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1009130477905273, "global_step": 364408, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1405222415924072, "global_step": 364409, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0626678466796875, "global_step": 364410, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1496410369873047, "global_step": 364411, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2276973724365234, "global_step": 364412, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.198909044265747, "global_step": 364413, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.037006139755249, "global_step": 364414, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1330695152282715, "global_step": 364415, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1798646450042725, "global_step": 364416, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.136345148086548, "global_step": 364417, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1479523181915283, "global_step": 364418, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.122735023498535, "global_step": 364419, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.037149667739868, "global_step": 364420, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.089951515197754, "global_step": 364421, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.18070125579834, "global_step": 364422, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1404714584350586, "global_step": 364423, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.191502809524536, "global_step": 364424, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1448042392730713, "global_step": 364425, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0879478454589844, "global_step": 364426, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.147066593170166, "global_step": 364427, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0616800785064697, "global_step": 364428, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1521995067596436, "global_step": 364429, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.106565237045288, "global_step": 364430, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2086243629455566, "global_step": 364431, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0635738372802734, "global_step": 364432, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1322107315063477, "global_step": 364433, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.05393648147583, "global_step": 364434, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.147905111312866, "global_step": 364435, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.10471248626709, "global_step": 364436, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1776814460754395, "global_step": 364437, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1862337589263916, "global_step": 364438, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.183939218521118, "global_step": 364439, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0708651542663574, "global_step": 364440, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.124717950820923, "global_step": 364441, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1017162799835205, "global_step": 364442, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1032958030700684, "global_step": 364443, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1417181491851807, "global_step": 364444, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0629050731658936, "global_step": 364445, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.092752456665039, "global_step": 364446, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.2088184356689453, "global_step": 364447, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.121398448944092, "global_step": 364448, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1259877681732178, "global_step": 364449, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.153318166732788, "global_step": 364450, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0528857707977295, "global_step": 364451, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.066169023513794, "global_step": 364452, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1086621284484863, "global_step": 364453, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.159008026123047, "global_step": 364454, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0678436756134033, "global_step": 364455, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.124748468399048, "global_step": 364456, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.136648416519165, "global_step": 364457, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1071739196777344, "global_step": 364458, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0661847591400146, "global_step": 364459, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1351234912872314, "global_step": 364460, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1535439491271973, "global_step": 364461, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.154897928237915, "global_step": 364462, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.140106439590454, "global_step": 364463, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.156937837600708, "global_step": 364464, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.022874116897583, "global_step": 364465, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.102062225341797, "global_step": 364466, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1179590225219727, "global_step": 364467, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.1118099689483643, "global_step": 364468, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0715112686157227, "global_step": 364469, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.120345115661621, "global_step": 364470, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.136927843093872, "global_step": 364471, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.164630651473999, "global_step": 364472, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.146416187286377, "global_step": 364473, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.107937812805176, "global_step": 364474, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.202517032623291, "global_step": 364475, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.109078884124756, "global_step": 364476, "epoch": 725, "lr": 5e-05}
{"train_loss": 2.0200138092041016, "global_step": 364477, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.07890248298645, "global_step": 364478, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1195809841156006, "global_step": 364479, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1121084690093994, "global_step": 364480, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0827584266662598, "global_step": 364481, "epoch": 726, "lr": 5e-05}
{"train_loss": 1.9837363958358765, "global_step": 364482, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0899417400360107, "global_step": 364483, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1689724922180176, "global_step": 364484, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.063915252685547, "global_step": 364485, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.092363119125366, "global_step": 364486, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1501379013061523, "global_step": 364487, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.066448926925659, "global_step": 364488, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0820610523223877, "global_step": 364489, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.183917760848999, "global_step": 364490, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.045170783996582, "global_step": 364491, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.123385190963745, "global_step": 364492, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0965499877929688, "global_step": 364493, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.053049087524414, "global_step": 364494, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0826611518859863, "global_step": 364495, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.147796392440796, "global_step": 364496, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.082610607147217, "global_step": 364497, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.185460090637207, "global_step": 364498, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.066002607345581, "global_step": 364499, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.111452579498291, "global_step": 364500, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1256401538848877, "global_step": 364501, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1768958568573, "global_step": 364502, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.125086784362793, "global_step": 364503, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1013691425323486, "global_step": 364504, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.152608871459961, "global_step": 364505, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1687562465667725, "global_step": 364506, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0998191833496094, "global_step": 364507, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.114180564880371, "global_step": 364508, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0012617111206055, "global_step": 364509, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0920567512512207, "global_step": 364510, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0773818492889404, "global_step": 364511, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0972256660461426, "global_step": 364512, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1095590591430664, "global_step": 364513, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1121299266815186, "global_step": 364514, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1267590522766113, "global_step": 364515, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0125033855438232, "global_step": 364516, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0630242824554443, "global_step": 364517, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0622169971466064, "global_step": 364518, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1405117511749268, "global_step": 364519, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.006300926208496, "global_step": 364520, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.098034143447876, "global_step": 364521, "epoch": 726, "lr": 5e-05}
{"train_loss": 1.9812617301940918, "global_step": 364522, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.088287115097046, "global_step": 364523, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.141594886779785, "global_step": 364524, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.054361581802368, "global_step": 364525, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1284468173980713, "global_step": 364526, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.173630952835083, "global_step": 364527, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.050774335861206, "global_step": 364528, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.142388343811035, "global_step": 364529, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0522031784057617, "global_step": 364530, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0618205070495605, "global_step": 364531, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0943233966827393, "global_step": 364532, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0955262184143066, "global_step": 364533, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.180020809173584, "global_step": 364534, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1368062496185303, "global_step": 364535, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0056052207946777, "global_step": 364536, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.103421211242676, "global_step": 364537, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1350362300872803, "global_step": 364538, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0468013286590576, "global_step": 364539, "epoch": 726, "lr": 5e-05}
{"train_loss": 1.986031174659729, "global_step": 364540, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1243019104003906, "global_step": 364541, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1400246620178223, "global_step": 364542, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1767499446868896, "global_step": 364543, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1416304111480713, "global_step": 364544, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.097688913345337, "global_step": 364545, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.082350492477417, "global_step": 364546, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.104518413543701, "global_step": 364547, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1544787883758545, "global_step": 364548, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.070411205291748, "global_step": 364549, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0953147411346436, "global_step": 364550, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0797836780548096, "global_step": 364551, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.087392807006836, "global_step": 364552, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0608301162719727, "global_step": 364553, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.161729574203491, "global_step": 364554, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1247506141662598, "global_step": 364555, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.12461519241333, "global_step": 364556, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.125657558441162, "global_step": 364557, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1012048721313477, "global_step": 364558, "epoch": 726, "lr": 5e-05}
{"train_loss": 1.992608666419983, "global_step": 364559, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1839916706085205, "global_step": 364560, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1647255420684814, "global_step": 364561, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0776588916778564, "global_step": 364562, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0547845363616943, "global_step": 364563, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.148455858230591, "global_step": 364564, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.020772933959961, "global_step": 364565, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1305618286132812, "global_step": 364566, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.099022150039673, "global_step": 364567, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.069620370864868, "global_step": 364568, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0997066497802734, "global_step": 364569, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.172302722930908, "global_step": 364570, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.05110764503479, "global_step": 364571, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1831324100494385, "global_step": 364572, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0746657848358154, "global_step": 364573, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.074674606323242, "global_step": 364574, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.116547107696533, "global_step": 364575, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.035939931869507, "global_step": 364576, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1161251068115234, "global_step": 364577, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.09482741355896, "global_step": 364578, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1452951431274414, "global_step": 364579, "epoch": 726, "lr": 5e-05}
{"train_loss": 1.9975720643997192, "global_step": 364580, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0775225162506104, "global_step": 364581, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.008131980895996, "global_step": 364582, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0916435718536377, "global_step": 364583, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.07594633102417, "global_step": 364584, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.096992015838623, "global_step": 364585, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2416269779205322, "global_step": 364586, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.168832778930664, "global_step": 364587, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.117037057876587, "global_step": 364588, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0298514366149902, "global_step": 364589, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0253872871398926, "global_step": 364590, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.089242458343506, "global_step": 364591, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1838555335998535, "global_step": 364592, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0032453536987305, "global_step": 364593, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1350536346435547, "global_step": 364594, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1119303703308105, "global_step": 364595, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1225597858428955, "global_step": 364596, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.035663604736328, "global_step": 364597, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0036869049072266, "global_step": 364598, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.068880558013916, "global_step": 364599, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.185335636138916, "global_step": 364600, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.104815721511841, "global_step": 364601, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1898996829986572, "global_step": 364602, "epoch": 726, "lr": 5e-05}
{"train_loss": 1.9873830080032349, "global_step": 364603, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.073991537094116, "global_step": 364604, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.097952127456665, "global_step": 364605, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0576393604278564, "global_step": 364606, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.104671001434326, "global_step": 364607, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1958861351013184, "global_step": 364608, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.065551996231079, "global_step": 364609, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.133517265319824, "global_step": 364610, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0952372550964355, "global_step": 364611, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.062241792678833, "global_step": 364612, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1172709465026855, "global_step": 364613, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0115842819213867, "global_step": 364614, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.078157663345337, "global_step": 364615, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0812363624572754, "global_step": 364616, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.119576930999756, "global_step": 364617, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0482399463653564, "global_step": 364618, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.125643730163574, "global_step": 364619, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1493983268737793, "global_step": 364620, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.118358612060547, "global_step": 364621, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1283507347106934, "global_step": 364622, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0478098392486572, "global_step": 364623, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0676662921905518, "global_step": 364624, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0703604221343994, "global_step": 364625, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1784400939941406, "global_step": 364626, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1012396812438965, "global_step": 364627, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.182797431945801, "global_step": 364628, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1026418209075928, "global_step": 364629, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1189708709716797, "global_step": 364630, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.118758201599121, "global_step": 364631, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0500094890594482, "global_step": 364632, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1402933597564697, "global_step": 364633, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.131239175796509, "global_step": 364634, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.192450523376465, "global_step": 364635, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.100292921066284, "global_step": 364636, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1534149646759033, "global_step": 364637, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.090897798538208, "global_step": 364638, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2423269748687744, "global_step": 364639, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.099841833114624, "global_step": 364640, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0374224185943604, "global_step": 364641, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.176234006881714, "global_step": 364642, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.151787519454956, "global_step": 364643, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.169157028198242, "global_step": 364644, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.090040683746338, "global_step": 364645, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.080012559890747, "global_step": 364646, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1697349548339844, "global_step": 364647, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1402814388275146, "global_step": 364648, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1291089057922363, "global_step": 364649, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1132147312164307, "global_step": 364650, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2078633308410645, "global_step": 364651, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0265729427337646, "global_step": 364652, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.06831431388855, "global_step": 364653, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.07782244682312, "global_step": 364654, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.132982015609741, "global_step": 364655, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1374781131744385, "global_step": 364656, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0656967163085938, "global_step": 364657, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1534664630889893, "global_step": 364658, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.086676597595215, "global_step": 364659, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.079298257827759, "global_step": 364660, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1012556552886963, "global_step": 364661, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1332504749298096, "global_step": 364662, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.195047378540039, "global_step": 364663, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0111420154571533, "global_step": 364664, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1592769622802734, "global_step": 364665, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1516153812408447, "global_step": 364666, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.059541940689087, "global_step": 364667, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.116891622543335, "global_step": 364668, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.128675699234009, "global_step": 364669, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1434359550476074, "global_step": 364670, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.104597806930542, "global_step": 364671, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.125523090362549, "global_step": 364672, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1236519813537598, "global_step": 364673, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1263129711151123, "global_step": 364674, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1262760162353516, "global_step": 364675, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2065296173095703, "global_step": 364676, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1205861568450928, "global_step": 364677, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0988311767578125, "global_step": 364678, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0805234909057617, "global_step": 364679, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.073256731033325, "global_step": 364680, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0809686183929443, "global_step": 364681, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0936155319213867, "global_step": 364682, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0526208877563477, "global_step": 364683, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1161131858825684, "global_step": 364684, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.132263422012329, "global_step": 364685, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.152632474899292, "global_step": 364686, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.146127223968506, "global_step": 364687, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0449864864349365, "global_step": 364688, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1794962882995605, "global_step": 364689, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0996124744415283, "global_step": 364690, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.097116708755493, "global_step": 364691, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.067246913909912, "global_step": 364692, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.088989734649658, "global_step": 364693, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.07829213142395, "global_step": 364694, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1152138710021973, "global_step": 364695, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.128305435180664, "global_step": 364696, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1253716945648193, "global_step": 364697, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1672630310058594, "global_step": 364698, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.062727451324463, "global_step": 364699, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0829102993011475, "global_step": 364700, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0943801403045654, "global_step": 364701, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0915913581848145, "global_step": 364702, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.10359263420105, "global_step": 364703, "epoch": 726, "lr": 5e-05}
{"train_loss": 1.9858438968658447, "global_step": 364704, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.101762294769287, "global_step": 364705, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.16145396232605, "global_step": 364706, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0587198734283447, "global_step": 364707, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0231690406799316, "global_step": 364708, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0945143699645996, "global_step": 364709, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1073429584503174, "global_step": 364710, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1679306030273438, "global_step": 364711, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.068809747695923, "global_step": 364712, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0716803073883057, "global_step": 364713, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0886566638946533, "global_step": 364714, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0742247104644775, "global_step": 364715, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1682286262512207, "global_step": 364716, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0592517852783203, "global_step": 364717, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1055521965026855, "global_step": 364718, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.07948637008667, "global_step": 364719, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.067627429962158, "global_step": 364720, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1099112033843994, "global_step": 364721, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.063065767288208, "global_step": 364722, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.12104868888855, "global_step": 364723, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1460824012756348, "global_step": 364724, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.153090715408325, "global_step": 364725, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.127293586730957, "global_step": 364726, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1410043239593506, "global_step": 364727, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.176539897918701, "global_step": 364728, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0574657917022705, "global_step": 364729, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.095667600631714, "global_step": 364730, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1388630867004395, "global_step": 364731, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.066894769668579, "global_step": 364732, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.142334222793579, "global_step": 364733, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.10941481590271, "global_step": 364734, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0030534267425537, "global_step": 364735, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.104058027267456, "global_step": 364736, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0359439849853516, "global_step": 364737, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.038393020629883, "global_step": 364738, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0795974731445312, "global_step": 364739, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.083313465118408, "global_step": 364740, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1545088291168213, "global_step": 364741, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0969698429107666, "global_step": 364742, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1252174377441406, "global_step": 364743, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0755362510681152, "global_step": 364744, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.126958131790161, "global_step": 364745, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0649685859680176, "global_step": 364746, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.118072032928467, "global_step": 364747, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.196336030960083, "global_step": 364748, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0638365745544434, "global_step": 364749, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1720967292785645, "global_step": 364750, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.126352071762085, "global_step": 364751, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0887136459350586, "global_step": 364752, "epoch": 726, "lr": 5e-05}
{"train_loss": 1.9572092294692993, "global_step": 364753, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.208756446838379, "global_step": 364754, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1113476753234863, "global_step": 364755, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1030936241149902, "global_step": 364756, "epoch": 726, "lr": 5e-05}
{"train_loss": 1.9776861667633057, "global_step": 364757, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1341302394866943, "global_step": 364758, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2022993564605713, "global_step": 364759, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.105475664138794, "global_step": 364760, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.026508331298828, "global_step": 364761, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1116907596588135, "global_step": 364762, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1445000171661377, "global_step": 364763, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.163724422454834, "global_step": 364764, "epoch": 726, "lr": 5e-05}
{"train_loss": 1.977178931236267, "global_step": 364765, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.131479501724243, "global_step": 364766, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1506855487823486, "global_step": 364767, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.108123540878296, "global_step": 364768, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.101593017578125, "global_step": 364769, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.106116771697998, "global_step": 364770, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.07655930519104, "global_step": 364771, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0814554691314697, "global_step": 364772, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1091346740722656, "global_step": 364773, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.140843391418457, "global_step": 364774, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.05800461769104, "global_step": 364775, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.104870319366455, "global_step": 364776, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.063802480697632, "global_step": 364777, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0985429286956787, "global_step": 364778, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.088726282119751, "global_step": 364779, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.054868698120117, "global_step": 364780, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1305489540100098, "global_step": 364781, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0623512268066406, "global_step": 364782, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0951032638549805, "global_step": 364783, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.137579917907715, "global_step": 364784, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.132932662963867, "global_step": 364785, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0491597652435303, "global_step": 364786, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.093454360961914, "global_step": 364787, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.129030227661133, "global_step": 364788, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1382479667663574, "global_step": 364789, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1970603466033936, "global_step": 364790, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1382763385772705, "global_step": 364791, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.052659511566162, "global_step": 364792, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1403086185455322, "global_step": 364793, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1049582958221436, "global_step": 364794, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.102491617202759, "global_step": 364795, "epoch": 726, "lr": 5e-05}
{"train_loss": 1.989236831665039, "global_step": 364796, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0340516567230225, "global_step": 364797, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1833503246307373, "global_step": 364798, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0796115398406982, "global_step": 364799, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.097752332687378, "global_step": 364800, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0765159130096436, "global_step": 364801, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1085970401763916, "global_step": 364802, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1189050674438477, "global_step": 364803, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1051928997039795, "global_step": 364804, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.046724557876587, "global_step": 364805, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0567991733551025, "global_step": 364806, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.122659206390381, "global_step": 364807, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1088337898254395, "global_step": 364808, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.089534282684326, "global_step": 364809, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.065385580062866, "global_step": 364810, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1394267082214355, "global_step": 364811, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0289230346679688, "global_step": 364812, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0648069381713867, "global_step": 364813, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.119351387023926, "global_step": 364814, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1065285205841064, "global_step": 364815, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1081626415252686, "global_step": 364816, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0885818004608154, "global_step": 364817, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0989744663238525, "global_step": 364818, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0881524085998535, "global_step": 364819, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0645296573638916, "global_step": 364820, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.136549711227417, "global_step": 364821, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.125145196914673, "global_step": 364822, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.006248712539673, "global_step": 364823, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.122629165649414, "global_step": 364824, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1519274711608887, "global_step": 364825, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1503779888153076, "global_step": 364826, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0888359546661377, "global_step": 364827, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.141462564468384, "global_step": 364828, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0757429599761963, "global_step": 364829, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.087785482406616, "global_step": 364830, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.072650671005249, "global_step": 364831, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0995378494262695, "global_step": 364832, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.179680347442627, "global_step": 364833, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.170819044113159, "global_step": 364834, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0196213722229004, "global_step": 364835, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1153576374053955, "global_step": 364836, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0816595554351807, "global_step": 364837, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1406736373901367, "global_step": 364838, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1340291500091553, "global_step": 364839, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0730512142181396, "global_step": 364840, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.009833335876465, "global_step": 364841, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.059861421585083, "global_step": 364842, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.149059772491455, "global_step": 364843, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0345048904418945, "global_step": 364844, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.085146427154541, "global_step": 364845, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.057164192199707, "global_step": 364846, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1656157970428467, "global_step": 364847, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.087200164794922, "global_step": 364848, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1302990913391113, "global_step": 364849, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0796680450439453, "global_step": 364850, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1420047283172607, "global_step": 364851, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1270885467529297, "global_step": 364852, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1215953826904297, "global_step": 364853, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1540584564208984, "global_step": 364854, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1412954330444336, "global_step": 364855, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0787668228149414, "global_step": 364856, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1172072887420654, "global_step": 364857, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0788891315460205, "global_step": 364858, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1386542320251465, "global_step": 364859, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1671433448791504, "global_step": 364860, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.108283042907715, "global_step": 364861, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1387133598327637, "global_step": 364862, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.075991153717041, "global_step": 364863, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1641845703125, "global_step": 364864, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1123709678649902, "global_step": 364865, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1679046154022217, "global_step": 364866, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0673656463623047, "global_step": 364867, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.151744842529297, "global_step": 364868, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1208622455596924, "global_step": 364869, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1315157413482666, "global_step": 364870, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1689319610595703, "global_step": 364871, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.087949275970459, "global_step": 364872, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0518240928649902, "global_step": 364873, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0474693775177, "global_step": 364874, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1868016719818115, "global_step": 364875, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1002111434936523, "global_step": 364876, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0030932426452637, "global_step": 364877, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.046097755432129, "global_step": 364878, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1372084617614746, "global_step": 364879, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0724594593048096, "global_step": 364880, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.167388677597046, "global_step": 364881, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1549713611602783, "global_step": 364882, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.128852605819702, "global_step": 364883, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.012446165084839, "global_step": 364884, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.15720796585083, "global_step": 364885, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.125138998031616, "global_step": 364886, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.087371826171875, "global_step": 364887, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.122974395751953, "global_step": 364888, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.21921706199646, "global_step": 364889, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1320266723632812, "global_step": 364890, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0653417110443115, "global_step": 364891, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1591413021087646, "global_step": 364892, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2321290969848633, "global_step": 364893, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1535425186157227, "global_step": 364894, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1116271018981934, "global_step": 364895, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.146650791168213, "global_step": 364896, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.133873701095581, "global_step": 364897, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0297014713287354, "global_step": 364898, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0960757732391357, "global_step": 364899, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.014976739883423, "global_step": 364900, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0619940757751465, "global_step": 364901, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.130321741104126, "global_step": 364902, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.132251739501953, "global_step": 364903, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0907912254333496, "global_step": 364904, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1093263626098633, "global_step": 364905, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.075819492340088, "global_step": 364906, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0081374645233154, "global_step": 364907, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.130946636199951, "global_step": 364908, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.143963575363159, "global_step": 364909, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.171088695526123, "global_step": 364910, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1598007678985596, "global_step": 364911, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0608506202697754, "global_step": 364912, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0943994522094727, "global_step": 364913, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.127470016479492, "global_step": 364914, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0889949798583984, "global_step": 364915, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0809223651885986, "global_step": 364916, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1492936611175537, "global_step": 364917, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.124389410018921, "global_step": 364918, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1590070724487305, "global_step": 364919, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1289122104644775, "global_step": 364920, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1272575855255127, "global_step": 364921, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1008851528167725, "global_step": 364922, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0445423126220703, "global_step": 364923, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1172499656677246, "global_step": 364924, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.176452398300171, "global_step": 364925, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1507604122161865, "global_step": 364926, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.09112286567688, "global_step": 364927, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1213746070861816, "global_step": 364928, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.086663246154785, "global_step": 364929, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0430357456207275, "global_step": 364930, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1124491691589355, "global_step": 364931, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0971243381500244, "global_step": 364932, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.130246162414551, "global_step": 364933, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.172750234603882, "global_step": 364934, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.018188953399658, "global_step": 364935, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.134697437286377, "global_step": 364936, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.112673044204712, "global_step": 364937, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.184684991836548, "global_step": 364938, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.185807466506958, "global_step": 364939, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.113426923751831, "global_step": 364940, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.090543031692505, "global_step": 364941, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0771267414093018, "global_step": 364942, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.171217203140259, "global_step": 364943, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0885941982269287, "global_step": 364944, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0971899032592773, "global_step": 364945, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1145153045654297, "global_step": 364946, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1425418853759766, "global_step": 364947, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1607351303100586, "global_step": 364948, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0750324726104736, "global_step": 364949, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.164790153503418, "global_step": 364950, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1106505393981934, "global_step": 364951, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.28385853767395, "global_step": 364952, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1045947074890137, "global_step": 364953, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.129505157470703, "global_step": 364954, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.062683343887329, "global_step": 364955, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1441867351531982, "global_step": 364956, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.232499361038208, "global_step": 364957, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.098708152770996, "global_step": 364958, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0735886096954346, "global_step": 364959, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2057440280914307, "global_step": 364960, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0968124866485596, "global_step": 364961, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1477596759796143, "global_step": 364962, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0723307132720947, "global_step": 364963, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0820090770721436, "global_step": 364964, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1690735816955566, "global_step": 364965, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0745270252227783, "global_step": 364966, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0936453342437744, "global_step": 364967, "epoch": 726, "lr": 5e-05}
{"train_loss": 1.998787522315979, "global_step": 364968, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2595953941345215, "global_step": 364969, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0957486629486084, "global_step": 364970, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.102200746536255, "global_step": 364971, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.116687297821045, "global_step": 364972, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1217896938323975, "global_step": 364973, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.172607183456421, "global_step": 364974, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.026474952697754, "global_step": 364975, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.068796157836914, "global_step": 364976, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1685709953308105, "global_step": 364977, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.140674591064453, "global_step": 364978, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.039505958557129, "global_step": 364979, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1611201763153076, "global_step": 364980, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0754308700561523, "global_step": 364981, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.005615711212158, "global_step": 364982, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1446170806884766, "global_step": 364983, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0912063121795654, "global_step": 364984, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.110806941986084, "global_step": 364985, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.112041711807251, "global_step": 364986, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1471385955810547, "global_step": 364987, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.08786940574646, "global_step": 364988, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.09165358543396, "global_step": 364989, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.165844202041626, "global_step": 364990, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.075485944747925, "global_step": 364991, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1656370162963867, "global_step": 364992, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0855679512023926, "global_step": 364993, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1574268341064453, "global_step": 364994, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.022437572479248, "global_step": 364995, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1253397464752197, "global_step": 364996, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.138530969619751, "global_step": 364997, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.213820457458496, "global_step": 364998, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0935139656066895, "global_step": 364999, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.172779083251953, "global_step": 365000, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0650668144226074, "global_step": 365001, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1035938262939453, "global_step": 365002, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0890917778015137, "global_step": 365003, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.118340253829956, "global_step": 365004, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0598554611206055, "global_step": 365005, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0408644676208496, "global_step": 365006, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.143872022628784, "global_step": 365007, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1315038204193115, "global_step": 365008, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.117819309234619, "global_step": 365009, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.049311637878418, "global_step": 365010, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.084994316101074, "global_step": 365011, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.105576276779175, "global_step": 365012, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0418403148651123, "global_step": 365013, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1244640350341797, "global_step": 365014, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.05216646194458, "global_step": 365015, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.018378734588623, "global_step": 365016, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0944483280181885, "global_step": 365017, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.027047634124756, "global_step": 365018, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0476131439208984, "global_step": 365019, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0916221141815186, "global_step": 365020, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.052589178085327, "global_step": 365021, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0929853916168213, "global_step": 365022, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.080535888671875, "global_step": 365023, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1781764030456543, "global_step": 365024, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1018803119659424, "global_step": 365025, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.185107469558716, "global_step": 365026, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.051398754119873, "global_step": 365027, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1250181198120117, "global_step": 365028, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1312878131866455, "global_step": 365029, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.139802932739258, "global_step": 365030, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.140774965286255, "global_step": 365031, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0779170989990234, "global_step": 365032, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.080259084701538, "global_step": 365033, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.17657470703125, "global_step": 365034, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1143221855163574, "global_step": 365035, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0144944190979004, "global_step": 365036, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0674328804016113, "global_step": 365037, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0584230422973633, "global_step": 365038, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1478700637817383, "global_step": 365039, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1604232788085938, "global_step": 365040, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1118416786193848, "global_step": 365041, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1810569763183594, "global_step": 365042, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.194601535797119, "global_step": 365043, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0740771293640137, "global_step": 365044, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0972588062286377, "global_step": 365045, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.116892099380493, "global_step": 365046, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1465983390808105, "global_step": 365047, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1441071033477783, "global_step": 365048, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.174267530441284, "global_step": 365049, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2029306888580322, "global_step": 365050, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.12398362159729, "global_step": 365051, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.196678876876831, "global_step": 365052, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.173863410949707, "global_step": 365053, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0183918476104736, "global_step": 365054, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.157712697982788, "global_step": 365055, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.174150228500366, "global_step": 365056, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0633978843688965, "global_step": 365057, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1166279315948486, "global_step": 365058, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.114625930786133, "global_step": 365059, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0319385528564453, "global_step": 365060, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1177895069122314, "global_step": 365061, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1539134979248047, "global_step": 365062, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1292569637298584, "global_step": 365063, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0577571392059326, "global_step": 365064, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0938546657562256, "global_step": 365065, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.111506938934326, "global_step": 365066, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.095996379852295, "global_step": 365067, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.161966562271118, "global_step": 365068, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.099731683731079, "global_step": 365069, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.107276678085327, "global_step": 365070, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0894713401794434, "global_step": 365071, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0838232040405273, "global_step": 365072, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1340136528015137, "global_step": 365073, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.163292407989502, "global_step": 365074, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.097614288330078, "global_step": 365075, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1611852645874023, "global_step": 365076, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0758419036865234, "global_step": 365077, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.074390172958374, "global_step": 365078, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1908464431762695, "global_step": 365079, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0876882076263428, "global_step": 365080, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.058636426925659, "global_step": 365081, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0461349487304688, "global_step": 365082, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1058170795440674, "global_step": 365083, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0124213695526123, "global_step": 365084, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.13071608543396, "global_step": 365085, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.143094301223755, "global_step": 365086, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1747844219207764, "global_step": 365087, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0992484092712402, "global_step": 365088, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1329684257507324, "global_step": 365089, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0532400608062744, "global_step": 365090, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0142014026641846, "global_step": 365091, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.08958101272583, "global_step": 365092, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.123213529586792, "global_step": 365093, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1147854328155518, "global_step": 365094, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1020641326904297, "global_step": 365095, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0834035873413086, "global_step": 365096, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0890257358551025, "global_step": 365097, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.043442726135254, "global_step": 365098, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.132739782333374, "global_step": 365099, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1145050525665283, "global_step": 365100, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.169285297393799, "global_step": 365101, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.151794195175171, "global_step": 365102, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1225814819335938, "global_step": 365103, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1491663455963135, "global_step": 365104, "epoch": 726, "lr": 5e-05}
{"train_loss": 1.9851996898651123, "global_step": 365105, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1176483631134033, "global_step": 365106, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0717530250549316, "global_step": 365107, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2262814044952393, "global_step": 365108, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.095959186553955, "global_step": 365109, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.076963424682617, "global_step": 365110, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.157052516937256, "global_step": 365111, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1538684368133545, "global_step": 365112, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.113999605178833, "global_step": 365113, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1556577682495117, "global_step": 365114, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.094378709793091, "global_step": 365115, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.217005491256714, "global_step": 365116, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1108434200286865, "global_step": 365117, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1457457542419434, "global_step": 365118, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0024795532226562, "global_step": 365119, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.097100257873535, "global_step": 365120, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1116180419921875, "global_step": 365121, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0629565715789795, "global_step": 365122, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.123067855834961, "global_step": 365123, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1059415340423584, "global_step": 365124, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0906341075897217, "global_step": 365125, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0900473594665527, "global_step": 365126, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0873937606811523, "global_step": 365127, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2138121128082275, "global_step": 365128, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1291089057922363, "global_step": 365129, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.064406156539917, "global_step": 365130, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.155824661254883, "global_step": 365131, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0844242572784424, "global_step": 365132, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.122896671295166, "global_step": 365133, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1505343914031982, "global_step": 365134, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1399776935577393, "global_step": 365135, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.100668430328369, "global_step": 365136, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.046795606613159, "global_step": 365137, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.048668384552002, "global_step": 365138, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.17215633392334, "global_step": 365139, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0944840908050537, "global_step": 365140, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.113413095474243, "global_step": 365141, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.093574285507202, "global_step": 365142, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.066584587097168, "global_step": 365143, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.111276626586914, "global_step": 365144, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.140819787979126, "global_step": 365145, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.126322031021118, "global_step": 365146, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0418453216552734, "global_step": 365147, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0980937480926514, "global_step": 365148, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1148996353149414, "global_step": 365149, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2121567726135254, "global_step": 365150, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0524802207946777, "global_step": 365151, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0293610095977783, "global_step": 365152, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.033693790435791, "global_step": 365153, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.171994924545288, "global_step": 365154, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.203186511993408, "global_step": 365155, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0110511779785156, "global_step": 365156, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2069334983825684, "global_step": 365157, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0754878520965576, "global_step": 365158, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.144763946533203, "global_step": 365159, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0526158809661865, "global_step": 365160, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.137251138687134, "global_step": 365161, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.144477605819702, "global_step": 365162, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.052309274673462, "global_step": 365163, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.135223865509033, "global_step": 365164, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1109583377838135, "global_step": 365165, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.145998239517212, "global_step": 365166, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1920554637908936, "global_step": 365167, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1907804012298584, "global_step": 365168, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1469926834106445, "global_step": 365169, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.142799139022827, "global_step": 365170, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0728964805603027, "global_step": 365171, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.169650077819824, "global_step": 365172, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.116102933883667, "global_step": 365173, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.158856153488159, "global_step": 365174, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.028441905975342, "global_step": 365175, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0594167709350586, "global_step": 365176, "epoch": 726, "lr": 5e-05}
{"train_loss": 1.9885905981063843, "global_step": 365177, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0438926219940186, "global_step": 365178, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0551788806915283, "global_step": 365179, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0992417335510254, "global_step": 365180, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.085622549057007, "global_step": 365181, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1672513484954834, "global_step": 365182, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1080551147460938, "global_step": 365183, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1144003868103027, "global_step": 365184, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1312551498413086, "global_step": 365185, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.134192705154419, "global_step": 365186, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.08988356590271, "global_step": 365187, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.088022232055664, "global_step": 365188, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0268442630767822, "global_step": 365189, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1819875240325928, "global_step": 365190, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.05466890335083, "global_step": 365191, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1270575523376465, "global_step": 365192, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0468204021453857, "global_step": 365193, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1084043979644775, "global_step": 365194, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1191818714141846, "global_step": 365195, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1191577911376953, "global_step": 365196, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1004271507263184, "global_step": 365197, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.157355785369873, "global_step": 365198, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.019946336746216, "global_step": 365199, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0757205486297607, "global_step": 365200, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.059602975845337, "global_step": 365201, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0755205154418945, "global_step": 365202, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.150601387023926, "global_step": 365203, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1310696601867676, "global_step": 365204, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.061917781829834, "global_step": 365205, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.077530860900879, "global_step": 365206, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.197941303253174, "global_step": 365207, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1180880069732666, "global_step": 365208, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0529823303222656, "global_step": 365209, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.070666551589966, "global_step": 365210, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.04404354095459, "global_step": 365211, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.212984085083008, "global_step": 365212, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.10737681388855, "global_step": 365213, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1841518878936768, "global_step": 365214, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0482373237609863, "global_step": 365215, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0694830417633057, "global_step": 365216, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0416371822357178, "global_step": 365217, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0299715995788574, "global_step": 365218, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.028388023376465, "global_step": 365219, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.168428421020508, "global_step": 365220, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1137285232543945, "global_step": 365221, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1258938312530518, "global_step": 365222, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.083491325378418, "global_step": 365223, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0730419158935547, "global_step": 365224, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.093991279602051, "global_step": 365225, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0965309143066406, "global_step": 365226, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1342098712921143, "global_step": 365227, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1220247745513916, "global_step": 365228, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.162019729614258, "global_step": 365229, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1670048236846924, "global_step": 365230, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.096693515777588, "global_step": 365231, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1453607082366943, "global_step": 365232, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0773961544036865, "global_step": 365233, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1136183738708496, "global_step": 365234, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0752110481262207, "global_step": 365235, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1185672283172607, "global_step": 365236, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.127317428588867, "global_step": 365237, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0705525875091553, "global_step": 365238, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0614402294158936, "global_step": 365239, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1470401287078857, "global_step": 365240, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.125084161758423, "global_step": 365241, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.157320737838745, "global_step": 365242, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1556105613708496, "global_step": 365243, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1687073707580566, "global_step": 365244, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.077765703201294, "global_step": 365245, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.099565267562866, "global_step": 365246, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0352635383605957, "global_step": 365247, "epoch": 726, "lr": 5e-05}
{"train_loss": 1.9632766246795654, "global_step": 365248, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1472890377044678, "global_step": 365249, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0615804195404053, "global_step": 365250, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0505096912384033, "global_step": 365251, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0990397930145264, "global_step": 365252, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1968467235565186, "global_step": 365253, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1256163120269775, "global_step": 365254, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0808370113372803, "global_step": 365255, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1996288299560547, "global_step": 365256, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1438989639282227, "global_step": 365257, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.060171127319336, "global_step": 365258, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1750175952911377, "global_step": 365259, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.140324592590332, "global_step": 365260, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1795802116394043, "global_step": 365261, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.126512289047241, "global_step": 365262, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0918521881103516, "global_step": 365263, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.182316780090332, "global_step": 365264, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.082775592803955, "global_step": 365265, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.249725580215454, "global_step": 365266, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0919029712677, "global_step": 365267, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0893490314483643, "global_step": 365268, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0570459365844727, "global_step": 365269, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.15639328956604, "global_step": 365270, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1638736724853516, "global_step": 365271, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1367897987365723, "global_step": 365272, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0630669593811035, "global_step": 365273, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1419625282287598, "global_step": 365274, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1662485599517822, "global_step": 365275, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0707333087921143, "global_step": 365276, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.095205068588257, "global_step": 365277, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0733823776245117, "global_step": 365278, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1014575958251953, "global_step": 365279, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1722588539123535, "global_step": 365280, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.094355821609497, "global_step": 365281, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1544342041015625, "global_step": 365282, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2021446228027344, "global_step": 365283, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1308395862579346, "global_step": 365284, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2066776752471924, "global_step": 365285, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1229350566864014, "global_step": 365286, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1011343002319336, "global_step": 365287, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.208829402923584, "global_step": 365288, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.084571599960327, "global_step": 365289, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.043384075164795, "global_step": 365290, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.147050619125366, "global_step": 365291, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1319215297698975, "global_step": 365292, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.183462142944336, "global_step": 365293, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.060368299484253, "global_step": 365294, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.159127950668335, "global_step": 365295, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0848729610443115, "global_step": 365296, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0975148677825928, "global_step": 365297, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1950080394744873, "global_step": 365298, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.119338274002075, "global_step": 365299, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1091268062591553, "global_step": 365300, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0661227703094482, "global_step": 365301, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0205626487731934, "global_step": 365302, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1476621627807617, "global_step": 365303, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.175025463104248, "global_step": 365304, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1283421516418457, "global_step": 365305, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.110870122909546, "global_step": 365306, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.070317029953003, "global_step": 365307, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.090087413787842, "global_step": 365308, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.123915433883667, "global_step": 365309, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.110398769378662, "global_step": 365310, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.116584062576294, "global_step": 365311, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1003453731536865, "global_step": 365312, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.131748676300049, "global_step": 365313, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.134599447250366, "global_step": 365314, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0652318000793457, "global_step": 365315, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1145455837249756, "global_step": 365316, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1196675300598145, "global_step": 365317, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1343584060668945, "global_step": 365318, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1672322750091553, "global_step": 365319, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0861828327178955, "global_step": 365320, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1482436656951904, "global_step": 365321, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.090423583984375, "global_step": 365322, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.159058094024658, "global_step": 365323, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.063615083694458, "global_step": 365324, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.115285634994507, "global_step": 365325, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.089156150817871, "global_step": 365326, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.128809690475464, "global_step": 365327, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.173903226852417, "global_step": 365328, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0759549140930176, "global_step": 365329, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.134152412414551, "global_step": 365330, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.191801071166992, "global_step": 365331, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1356046199798584, "global_step": 365332, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0256009101867676, "global_step": 365333, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1068832874298096, "global_step": 365334, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1673424243927, "global_step": 365335, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0753002166748047, "global_step": 365336, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1654720306396484, "global_step": 365337, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.144650459289551, "global_step": 365338, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1754748821258545, "global_step": 365339, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1000702381134033, "global_step": 365340, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.191981554031372, "global_step": 365341, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1163132190704346, "global_step": 365342, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0561270713806152, "global_step": 365343, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0819389820098877, "global_step": 365344, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.184202194213867, "global_step": 365345, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.091644287109375, "global_step": 365346, "epoch": 726, "lr": 5e-05}
{"train_loss": 1.9758723974227905, "global_step": 365347, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.112255334854126, "global_step": 365348, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.12907338142395, "global_step": 365349, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.131547689437866, "global_step": 365350, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1079506874084473, "global_step": 365351, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.088073253631592, "global_step": 365352, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0918006896972656, "global_step": 365353, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.066293239593506, "global_step": 365354, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1655960083007812, "global_step": 365355, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0180163383483887, "global_step": 365356, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0481719970703125, "global_step": 365357, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1311588287353516, "global_step": 365358, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.159395933151245, "global_step": 365359, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1243975162506104, "global_step": 365360, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.139794111251831, "global_step": 365361, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1242220401763916, "global_step": 365362, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1284189224243164, "global_step": 365363, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.05904221534729, "global_step": 365364, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0919442176818848, "global_step": 365365, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1174042224884033, "global_step": 365366, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.164844512939453, "global_step": 365367, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2019214630126953, "global_step": 365368, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.072983980178833, "global_step": 365369, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1708948612213135, "global_step": 365370, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1221485137939453, "global_step": 365371, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.116255044937134, "global_step": 365372, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.134850263595581, "global_step": 365373, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1942243576049805, "global_step": 365374, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.012739658355713, "global_step": 365375, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1925461292266846, "global_step": 365376, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0971410274505615, "global_step": 365377, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1662962436676025, "global_step": 365378, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2008304595947266, "global_step": 365379, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.048018217086792, "global_step": 365380, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1221230030059814, "global_step": 365381, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1620795726776123, "global_step": 365382, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0748746395111084, "global_step": 365383, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1102778911590576, "global_step": 365384, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0932061672210693, "global_step": 365385, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1088387966156006, "global_step": 365386, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.047180652618408, "global_step": 365387, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.079679012298584, "global_step": 365388, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0535762310028076, "global_step": 365389, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2124669551849365, "global_step": 365390, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.161107301712036, "global_step": 365391, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1893351078033447, "global_step": 365392, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.163874864578247, "global_step": 365393, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.136279344558716, "global_step": 365394, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0557734966278076, "global_step": 365395, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0856924057006836, "global_step": 365396, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0346412658691406, "global_step": 365397, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0781636238098145, "global_step": 365398, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0326924324035645, "global_step": 365399, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1546053886413574, "global_step": 365400, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1466166973114014, "global_step": 365401, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1136395931243896, "global_step": 365402, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1417016983032227, "global_step": 365403, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.13396954536438, "global_step": 365404, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1419477462768555, "global_step": 365405, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1442389488220215, "global_step": 365406, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1433706283569336, "global_step": 365407, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0929133892059326, "global_step": 365408, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1341307163238525, "global_step": 365409, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.089953660964966, "global_step": 365410, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0693228244781494, "global_step": 365411, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0861363410949707, "global_step": 365412, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1775848865509033, "global_step": 365413, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.085179328918457, "global_step": 365414, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0313405990600586, "global_step": 365415, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1344006061553955, "global_step": 365416, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.065721273422241, "global_step": 365417, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0752620697021484, "global_step": 365418, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0752062797546387, "global_step": 365419, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1401617527008057, "global_step": 365420, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2054271697998047, "global_step": 365421, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1592938899993896, "global_step": 365422, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1162827014923096, "global_step": 365423, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1610119342803955, "global_step": 365424, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.097292900085449, "global_step": 365425, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1028106212615967, "global_step": 365426, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.2206249237060547, "global_step": 365427, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0451316833496094, "global_step": 365428, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.094514846801758, "global_step": 365429, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.07659649848938, "global_step": 365430, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.171355724334717, "global_step": 365431, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.122481107711792, "global_step": 365432, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1073436737060547, "global_step": 365433, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.146705389022827, "global_step": 365434, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1751253604888916, "global_step": 365435, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.124051332473755, "global_step": 365436, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.063868999481201, "global_step": 365437, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1010611057281494, "global_step": 365438, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.200507640838623, "global_step": 365439, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1168532371520996, "global_step": 365440, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.109090805053711, "global_step": 365441, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1318447589874268, "global_step": 365442, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.06465744972229, "global_step": 365443, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.0359647274017334, "global_step": 365444, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1086153984069824, "global_step": 365445, "epoch": 726, "lr": 5e-05}
{"train_loss": 2.1071722507476807, "global_step": 365446, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.033112049102783, "global_step": 365447, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1450183391571045, "global_step": 365448, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0448174476623535, "global_step": 365449, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.197378158569336, "global_step": 365450, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0715548992156982, "global_step": 365451, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0821077823638916, "global_step": 365452, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.090468645095825, "global_step": 365453, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.087831735610962, "global_step": 365454, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0303902626037598, "global_step": 365455, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.155688762664795, "global_step": 365456, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1496622562408447, "global_step": 365457, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.208925724029541, "global_step": 365458, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.134906768798828, "global_step": 365459, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0729100704193115, "global_step": 365460, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.079071521759033, "global_step": 365461, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.067389726638794, "global_step": 365462, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.118725299835205, "global_step": 365463, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0975706577301025, "global_step": 365464, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0963540077209473, "global_step": 365465, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.2216217517852783, "global_step": 365466, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1165826320648193, "global_step": 365467, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0965497493743896, "global_step": 365468, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.083536148071289, "global_step": 365469, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.104074239730835, "global_step": 365470, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1156468391418457, "global_step": 365471, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0308945178985596, "global_step": 365472, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1093292236328125, "global_step": 365473, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.130099058151245, "global_step": 365474, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.110661029815674, "global_step": 365475, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0803866386413574, "global_step": 365476, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.154470682144165, "global_step": 365477, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.088759660720825, "global_step": 365478, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.175734281539917, "global_step": 365479, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0911967754364014, "global_step": 365480, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1206846237182617, "global_step": 365481, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.2406201362609863, "global_step": 365482, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0768492221832275, "global_step": 365483, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0883419513702393, "global_step": 365484, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1702752113342285, "global_step": 365485, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1349399089813232, "global_step": 365486, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1591055393218994, "global_step": 365487, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1497559547424316, "global_step": 365488, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0557727813720703, "global_step": 365489, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0661253929138184, "global_step": 365490, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0611045360565186, "global_step": 365491, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.061763286590576, "global_step": 365492, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0228991508483887, "global_step": 365493, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0607473850250244, "global_step": 365494, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1523492336273193, "global_step": 365495, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.09293794631958, "global_step": 365496, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.009295701980591, "global_step": 365497, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.157562494277954, "global_step": 365498, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1612348556518555, "global_step": 365499, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1148672103881836, "global_step": 365500, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1629202365875244, "global_step": 365501, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1555604934692383, "global_step": 365502, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.02286434173584, "global_step": 365503, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.036127805709839, "global_step": 365504, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1827733516693115, "global_step": 365505, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.109811782836914, "global_step": 365506, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0309572219848633, "global_step": 365507, "epoch": 727, "lr": 5e-05}
{"train_loss": 1.9880744218826294, "global_step": 365508, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.082627534866333, "global_step": 365509, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1838815212249756, "global_step": 365510, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1660807132720947, "global_step": 365511, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0918426513671875, "global_step": 365512, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.061136484146118, "global_step": 365513, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1090526580810547, "global_step": 365514, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.189690351486206, "global_step": 365515, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.161470890045166, "global_step": 365516, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.103750705718994, "global_step": 365517, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.2090539932250977, "global_step": 365518, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0778253078460693, "global_step": 365519, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.109285354614258, "global_step": 365520, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.035794973373413, "global_step": 365521, "epoch": 727, "lr": 5e-05}
{"train_loss": 1.956856369972229, "global_step": 365522, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.062528610229492, "global_step": 365523, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1605844497680664, "global_step": 365524, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.001239776611328, "global_step": 365525, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0941762924194336, "global_step": 365526, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0783567428588867, "global_step": 365527, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1696982383728027, "global_step": 365528, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1851394176483154, "global_step": 365529, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1559455394744873, "global_step": 365530, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.181871175765991, "global_step": 365531, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.102386713027954, "global_step": 365532, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0553088188171387, "global_step": 365533, "epoch": 727, "lr": 5e-05}
{"train_loss": 1.9890050888061523, "global_step": 365534, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.110532522201538, "global_step": 365535, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1728217601776123, "global_step": 365536, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1846702098846436, "global_step": 365537, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.108431816101074, "global_step": 365538, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1022157669067383, "global_step": 365539, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.130582094192505, "global_step": 365540, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1770145893096924, "global_step": 365541, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.18681263923645, "global_step": 365542, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.096301555633545, "global_step": 365543, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0943470001220703, "global_step": 365544, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.178851842880249, "global_step": 365545, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.062896490097046, "global_step": 365546, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1004271507263184, "global_step": 365547, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0957465171813965, "global_step": 365548, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0850961208343506, "global_step": 365549, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0945076942443848, "global_step": 365550, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.166623115539551, "global_step": 365551, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1480696201324463, "global_step": 365552, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.140197277069092, "global_step": 365553, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1350910663604736, "global_step": 365554, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.069824695587158, "global_step": 365555, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0557806491851807, "global_step": 365556, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.082552194595337, "global_step": 365557, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0366034507751465, "global_step": 365558, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.152254104614258, "global_step": 365559, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0646920204162598, "global_step": 365560, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0899577140808105, "global_step": 365561, "epoch": 727, "lr": 5e-05}
{"train_loss": 1.9941251277923584, "global_step": 365562, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.093721628189087, "global_step": 365563, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.136094331741333, "global_step": 365564, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0775063037872314, "global_step": 365565, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1517233848571777, "global_step": 365566, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0191457271575928, "global_step": 365567, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0254275798797607, "global_step": 365568, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1733620166778564, "global_step": 365569, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1903865337371826, "global_step": 365570, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1151630878448486, "global_step": 365571, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.115919589996338, "global_step": 365572, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.04899263381958, "global_step": 365573, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1625094413757324, "global_step": 365574, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0779929161071777, "global_step": 365575, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0975422859191895, "global_step": 365576, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0593228340148926, "global_step": 365577, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.078805923461914, "global_step": 365578, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1086771488189697, "global_step": 365579, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0811498165130615, "global_step": 365580, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1272904872894287, "global_step": 365581, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1675329208374023, "global_step": 365582, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.2075703144073486, "global_step": 365583, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0985910892486572, "global_step": 365584, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.050701379776001, "global_step": 365585, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.096045970916748, "global_step": 365586, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0027081966400146, "global_step": 365587, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1416163444519043, "global_step": 365588, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.052419662475586, "global_step": 365589, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.155353546142578, "global_step": 365590, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.158632516860962, "global_step": 365591, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.18035626411438, "global_step": 365592, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.083925485610962, "global_step": 365593, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1086995601654053, "global_step": 365594, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.136265993118286, "global_step": 365595, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.061427593231201, "global_step": 365596, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.149310827255249, "global_step": 365597, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.060910940170288, "global_step": 365598, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.136683940887451, "global_step": 365599, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0516164302825928, "global_step": 365600, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1238927841186523, "global_step": 365601, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.112931251525879, "global_step": 365602, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0776307582855225, "global_step": 365603, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1099607944488525, "global_step": 365604, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.094022274017334, "global_step": 365605, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0909295082092285, "global_step": 365606, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0810084342956543, "global_step": 365607, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0932509899139404, "global_step": 365608, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0106496810913086, "global_step": 365609, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1675736904144287, "global_step": 365610, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.114821195602417, "global_step": 365611, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.125943660736084, "global_step": 365612, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.207042694091797, "global_step": 365613, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0854175090789795, "global_step": 365614, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.091961145401001, "global_step": 365615, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1863763332366943, "global_step": 365616, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1264894008636475, "global_step": 365617, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1135683059692383, "global_step": 365618, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0414247512817383, "global_step": 365619, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.157872438430786, "global_step": 365620, "epoch": 727, "lr": 5e-05}
{"train_loss": 1.989464521408081, "global_step": 365621, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1730198860168457, "global_step": 365622, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.143869400024414, "global_step": 365623, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.060581684112549, "global_step": 365624, "epoch": 727, "lr": 5e-05}
{"train_loss": 1.9928852319717407, "global_step": 365625, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.099196434020996, "global_step": 365626, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1800475120544434, "global_step": 365627, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.110858678817749, "global_step": 365628, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.156954288482666, "global_step": 365629, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.235309600830078, "global_step": 365630, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.2288119792938232, "global_step": 365631, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.133237361907959, "global_step": 365632, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0805153846740723, "global_step": 365633, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1115882396698, "global_step": 365634, "epoch": 727, "lr": 5e-05}
{"train_loss": 1.976883053779602, "global_step": 365635, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.098487615585327, "global_step": 365636, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.132944345474243, "global_step": 365637, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1843390464782715, "global_step": 365638, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.151552438735962, "global_step": 365639, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0651257038116455, "global_step": 365640, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0819363594055176, "global_step": 365641, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.081519603729248, "global_step": 365642, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0186007022857666, "global_step": 365643, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1085376739501953, "global_step": 365644, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1807329654693604, "global_step": 365645, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0948758125305176, "global_step": 365646, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.104567527770996, "global_step": 365647, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.054466724395752, "global_step": 365648, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0268874168395996, "global_step": 365649, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1040163040161133, "global_step": 365650, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0888054370880127, "global_step": 365651, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.073805570602417, "global_step": 365652, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1116015911102295, "global_step": 365653, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.154454231262207, "global_step": 365654, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.051936626434326, "global_step": 365655, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.136378526687622, "global_step": 365656, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1238675117492676, "global_step": 365657, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0689897537231445, "global_step": 365658, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.100588798522949, "global_step": 365659, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.082751512527466, "global_step": 365660, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1045761108398438, "global_step": 365661, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.093104362487793, "global_step": 365662, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1970412731170654, "global_step": 365663, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0434107780456543, "global_step": 365664, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.13889479637146, "global_step": 365665, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0777180194854736, "global_step": 365666, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1219558715820312, "global_step": 365667, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.148749351501465, "global_step": 365668, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.2014787197113037, "global_step": 365669, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1544790267944336, "global_step": 365670, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.076184034347534, "global_step": 365671, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0648021697998047, "global_step": 365672, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0547890663146973, "global_step": 365673, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.185825824737549, "global_step": 365674, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.022329092025757, "global_step": 365675, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0998339653015137, "global_step": 365676, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.084088087081909, "global_step": 365677, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.112931251525879, "global_step": 365678, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1687581539154053, "global_step": 365679, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.143934726715088, "global_step": 365680, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.091623544692993, "global_step": 365681, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.170307159423828, "global_step": 365682, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.021300792694092, "global_step": 365683, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.122082471847534, "global_step": 365684, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1456410884857178, "global_step": 365685, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.178838014602661, "global_step": 365686, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1862497329711914, "global_step": 365687, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1546058654785156, "global_step": 365688, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0961859226226807, "global_step": 365689, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0817270278930664, "global_step": 365690, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0673956871032715, "global_step": 365691, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1530919075012207, "global_step": 365692, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1818313598632812, "global_step": 365693, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.142038106918335, "global_step": 365694, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1280500888824463, "global_step": 365695, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1285972595214844, "global_step": 365696, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1376216411590576, "global_step": 365697, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0894267559051514, "global_step": 365698, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.014037609100342, "global_step": 365699, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.166046619415283, "global_step": 365700, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0157129764556885, "global_step": 365701, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0841922760009766, "global_step": 365702, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1019954681396484, "global_step": 365703, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0698177814483643, "global_step": 365704, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0191593170166016, "global_step": 365705, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1157591342926025, "global_step": 365706, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0873191356658936, "global_step": 365707, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.146519184112549, "global_step": 365708, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.112617254257202, "global_step": 365709, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.067624807357788, "global_step": 365710, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.140712261199951, "global_step": 365711, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1150102615356445, "global_step": 365712, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.048151731491089, "global_step": 365713, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.029555320739746, "global_step": 365714, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.2069854736328125, "global_step": 365715, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1258819103240967, "global_step": 365716, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1107864379882812, "global_step": 365717, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1213014125823975, "global_step": 365718, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.100152015686035, "global_step": 365719, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1258718967437744, "global_step": 365720, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0612828731536865, "global_step": 365721, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0755977630615234, "global_step": 365722, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1423215866088867, "global_step": 365723, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0400567054748535, "global_step": 365724, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1586217880249023, "global_step": 365725, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.038726568222046, "global_step": 365726, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.082300901412964, "global_step": 365727, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.175485134124756, "global_step": 365728, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.189879894256592, "global_step": 365729, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.10321044921875, "global_step": 365730, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.113926887512207, "global_step": 365731, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.08899188041687, "global_step": 365732, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1237611770629883, "global_step": 365733, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1158597469329834, "global_step": 365734, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1067261695861816, "global_step": 365735, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1012721061706543, "global_step": 365736, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.101797580718994, "global_step": 365737, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0984866619110107, "global_step": 365738, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.042875051498413, "global_step": 365739, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0247390270233154, "global_step": 365740, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0635945796966553, "global_step": 365741, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1121816635131836, "global_step": 365742, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.157228469848633, "global_step": 365743, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0833096504211426, "global_step": 365744, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1243534088134766, "global_step": 365745, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0651614665985107, "global_step": 365746, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.112776517868042, "global_step": 365747, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1678106784820557, "global_step": 365748, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.055166244506836, "global_step": 365749, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1195037364959717, "global_step": 365750, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1378610134124756, "global_step": 365751, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.078432559967041, "global_step": 365752, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0981223583221436, "global_step": 365753, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0646746158599854, "global_step": 365754, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.123128890991211, "global_step": 365755, "epoch": 727, "lr": 5e-05}
{"train_loss": 1.9718244075775146, "global_step": 365756, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1737887859344482, "global_step": 365757, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.108391284942627, "global_step": 365758, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0558009147644043, "global_step": 365759, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.148160934448242, "global_step": 365760, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1154446601867676, "global_step": 365761, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.07177734375, "global_step": 365762, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1154773235321045, "global_step": 365763, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1458468437194824, "global_step": 365764, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.131963014602661, "global_step": 365765, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.110053539276123, "global_step": 365766, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0745792388916016, "global_step": 365767, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0179896354675293, "global_step": 365768, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0066733360290527, "global_step": 365769, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0292723178863525, "global_step": 365770, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.086519718170166, "global_step": 365771, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.044003963470459, "global_step": 365772, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.146348476409912, "global_step": 365773, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1098575592041016, "global_step": 365774, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.178579568862915, "global_step": 365775, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0917065143585205, "global_step": 365776, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0966060161590576, "global_step": 365777, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0712497234344482, "global_step": 365778, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0796680450439453, "global_step": 365779, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1493942737579346, "global_step": 365780, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0574145317077637, "global_step": 365781, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1124353408813477, "global_step": 365782, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.073148250579834, "global_step": 365783, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.148819923400879, "global_step": 365784, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.056769371032715, "global_step": 365785, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.011504650115967, "global_step": 365786, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.081125259399414, "global_step": 365787, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.128075361251831, "global_step": 365788, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1077888011932373, "global_step": 365789, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.095892906188965, "global_step": 365790, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1067869663238525, "global_step": 365791, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.068467140197754, "global_step": 365792, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1067583560943604, "global_step": 365793, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.142702102661133, "global_step": 365794, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0463855266571045, "global_step": 365795, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1446142196655273, "global_step": 365796, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1108484268188477, "global_step": 365797, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0238852500915527, "global_step": 365798, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0310890674591064, "global_step": 365799, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1215920448303223, "global_step": 365800, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.112276077270508, "global_step": 365801, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.042064905166626, "global_step": 365802, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.157207489013672, "global_step": 365803, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1385574340820312, "global_step": 365804, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0807743072509766, "global_step": 365805, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.147336483001709, "global_step": 365806, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.140070676803589, "global_step": 365807, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1068122386932373, "global_step": 365808, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0757174491882324, "global_step": 365809, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1209192276000977, "global_step": 365810, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1186797618865967, "global_step": 365811, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1696619987487793, "global_step": 365812, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.123398780822754, "global_step": 365813, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0408568382263184, "global_step": 365814, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.028419256210327, "global_step": 365815, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0979409217834473, "global_step": 365816, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1542725563049316, "global_step": 365817, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1965322494506836, "global_step": 365818, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.122906446456909, "global_step": 365819, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.07735538482666, "global_step": 365820, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0045039653778076, "global_step": 365821, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.185537815093994, "global_step": 365822, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.217318058013916, "global_step": 365823, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.135181427001953, "global_step": 365824, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.132100820541382, "global_step": 365825, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0731914043426514, "global_step": 365826, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0819759368896484, "global_step": 365827, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1013498306274414, "global_step": 365828, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1416497230529785, "global_step": 365829, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.180262327194214, "global_step": 365830, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.023207664489746, "global_step": 365831, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.006990432739258, "global_step": 365832, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.160085916519165, "global_step": 365833, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.139089345932007, "global_step": 365834, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1040849685668945, "global_step": 365835, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.102137804031372, "global_step": 365836, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.068171739578247, "global_step": 365837, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.001955986022949, "global_step": 365838, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.04495906829834, "global_step": 365839, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.15128493309021, "global_step": 365840, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0816287994384766, "global_step": 365841, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0824313163757324, "global_step": 365842, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.053987979888916, "global_step": 365843, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1073200702667236, "global_step": 365844, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.225796937942505, "global_step": 365845, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.111602306365967, "global_step": 365846, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.143854856491089, "global_step": 365847, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1937172412872314, "global_step": 365848, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.077425956726074, "global_step": 365849, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1231281757354736, "global_step": 365850, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.123093605041504, "global_step": 365851, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1180365085601807, "global_step": 365852, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.08711576461792, "global_step": 365853, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0287344455718994, "global_step": 365854, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.2362008094787598, "global_step": 365855, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0665292739868164, "global_step": 365856, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1301233768463135, "global_step": 365857, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0661590099334717, "global_step": 365858, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1142003536224365, "global_step": 365859, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.089574098587036, "global_step": 365860, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.11845064163208, "global_step": 365861, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.117906332015991, "global_step": 365862, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1198463439941406, "global_step": 365863, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.09765362739563, "global_step": 365864, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0771145820617676, "global_step": 365865, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1351497173309326, "global_step": 365866, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.2553911209106445, "global_step": 365867, "epoch": 727, "lr": 5e-05}
{"train_loss": 1.984097957611084, "global_step": 365868, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.05481219291687, "global_step": 365869, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.130337953567505, "global_step": 365870, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0946738719940186, "global_step": 365871, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.068129539489746, "global_step": 365872, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1453685760498047, "global_step": 365873, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1307196617126465, "global_step": 365874, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.040440320968628, "global_step": 365875, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.066152811050415, "global_step": 365876, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1036970615386963, "global_step": 365877, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.102254629135132, "global_step": 365878, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.060241222381592, "global_step": 365879, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0236825942993164, "global_step": 365880, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0530903339385986, "global_step": 365881, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1710164546966553, "global_step": 365882, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1506712436676025, "global_step": 365883, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1319077014923096, "global_step": 365884, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0669517517089844, "global_step": 365885, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.141160011291504, "global_step": 365886, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.090803861618042, "global_step": 365887, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0869927406311035, "global_step": 365888, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1417412757873535, "global_step": 365889, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0502796173095703, "global_step": 365890, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1183741092681885, "global_step": 365891, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1193885803222656, "global_step": 365892, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0899579524993896, "global_step": 365893, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.172118663787842, "global_step": 365894, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.082390785217285, "global_step": 365895, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.181178092956543, "global_step": 365896, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1870105266571045, "global_step": 365897, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.125647783279419, "global_step": 365898, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0731210708618164, "global_step": 365899, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.085416793823242, "global_step": 365900, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1994659900665283, "global_step": 365901, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1332170963287354, "global_step": 365902, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.133251428604126, "global_step": 365903, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.021923303604126, "global_step": 365904, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.144096851348877, "global_step": 365905, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1397836208343506, "global_step": 365906, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1161539554595947, "global_step": 365907, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0724871158599854, "global_step": 365908, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.10902738571167, "global_step": 365909, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.179960012435913, "global_step": 365910, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.039067029953003, "global_step": 365911, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.098367929458618, "global_step": 365912, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1239638328552246, "global_step": 365913, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0434770584106445, "global_step": 365914, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0511550903320312, "global_step": 365915, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0870964527130127, "global_step": 365916, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.164484739303589, "global_step": 365917, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0938947200775146, "global_step": 365918, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1866884231567383, "global_step": 365919, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1124491691589355, "global_step": 365920, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.147360324859619, "global_step": 365921, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1178815364837646, "global_step": 365922, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0295512676239014, "global_step": 365923, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.152179479598999, "global_step": 365924, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0727672576904297, "global_step": 365925, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.183471202850342, "global_step": 365926, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.2107229232788086, "global_step": 365927, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1429989337921143, "global_step": 365928, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.022026538848877, "global_step": 365929, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.100328207015991, "global_step": 365930, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0970098972320557, "global_step": 365931, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1256906986236572, "global_step": 365932, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1931450366973877, "global_step": 365933, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0666749477386475, "global_step": 365934, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1189470291137695, "global_step": 365935, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.073485851287842, "global_step": 365936, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0368118286132812, "global_step": 365937, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.065441608428955, "global_step": 365938, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.055884599685669, "global_step": 365939, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.113701820373535, "global_step": 365940, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.065901279449463, "global_step": 365941, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1823787689208984, "global_step": 365942, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.117896318435669, "global_step": 365943, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1151819229125977, "global_step": 365944, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0265798568725586, "global_step": 365945, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1853880882263184, "global_step": 365946, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1371707916259766, "global_step": 365947, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1359524726867676, "global_step": 365948, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1854987144470215, "global_step": 365949, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1205456256866455, "global_step": 365950, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0496513843536377, "global_step": 365951, "epoch": 727, "lr": 5e-05}
{"train_loss": 1.9765974283218384, "global_step": 365952, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.091917037963867, "global_step": 365953, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1905813217163086, "global_step": 365954, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1592049598693848, "global_step": 365955, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1219422817230225, "global_step": 365956, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1386559009552, "global_step": 365957, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.098233461380005, "global_step": 365958, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1002931594848633, "global_step": 365959, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0936639308929443, "global_step": 365960, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1796159744262695, "global_step": 365961, "epoch": 727, "lr": 5e-05}
{"train_loss": 1.9665319919586182, "global_step": 365962, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1019644737243652, "global_step": 365963, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.084538459777832, "global_step": 365964, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.053555727005005, "global_step": 365965, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.14388108253479, "global_step": 365966, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.060396432876587, "global_step": 365967, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.170436382293701, "global_step": 365968, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.2054691314697266, "global_step": 365969, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.15065598487854, "global_step": 365970, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1786530017852783, "global_step": 365971, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1651177406311035, "global_step": 365972, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.192456007003784, "global_step": 365973, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1009573936462402, "global_step": 365974, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0655739307403564, "global_step": 365975, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0587375164031982, "global_step": 365976, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.105550765991211, "global_step": 365977, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.066053628921509, "global_step": 365978, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.18757963180542, "global_step": 365979, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.122274875640869, "global_step": 365980, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1116533279418945, "global_step": 365981, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.076453685760498, "global_step": 365982, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0927798748016357, "global_step": 365983, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1270318031311035, "global_step": 365984, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1877808570861816, "global_step": 365985, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0870676040649414, "global_step": 365986, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1024250984191895, "global_step": 365987, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0823636054992676, "global_step": 365988, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1378204822540283, "global_step": 365989, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0637130737304688, "global_step": 365990, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0577969551086426, "global_step": 365991, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0133473873138428, "global_step": 365992, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1522905826568604, "global_step": 365993, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.121196985244751, "global_step": 365994, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0860848426818848, "global_step": 365995, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0261454582214355, "global_step": 365996, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0533483028411865, "global_step": 365997, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0352373123168945, "global_step": 365998, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1104016304016113, "global_step": 365999, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.088135242462158, "global_step": 366000, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1023364067077637, "global_step": 366001, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0976624488830566, "global_step": 366002, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1349313259124756, "global_step": 366003, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0422232151031494, "global_step": 366004, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1494452953338623, "global_step": 366005, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1663942337036133, "global_step": 366006, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.149341583251953, "global_step": 366007, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.131192445755005, "global_step": 366008, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1194770336151123, "global_step": 366009, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.2143492698669434, "global_step": 366010, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.136465072631836, "global_step": 366011, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0708935260772705, "global_step": 366012, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1381280422210693, "global_step": 366013, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0744361877441406, "global_step": 366014, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.2192792892456055, "global_step": 366015, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1345598697662354, "global_step": 366016, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.125025987625122, "global_step": 366017, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.184114933013916, "global_step": 366018, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.152567148208618, "global_step": 366019, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1152546405792236, "global_step": 366020, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0559825897216797, "global_step": 366021, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0721435546875, "global_step": 366022, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1002087593078613, "global_step": 366023, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0339767932891846, "global_step": 366024, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0384774208068848, "global_step": 366025, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1726670265197754, "global_step": 366026, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0730397701263428, "global_step": 366027, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.023205041885376, "global_step": 366028, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1311588287353516, "global_step": 366029, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1651902198791504, "global_step": 366030, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.085914373397827, "global_step": 366031, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.086465358734131, "global_step": 366032, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.077836751937866, "global_step": 366033, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.119032621383667, "global_step": 366034, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0250563621520996, "global_step": 366035, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0787353515625, "global_step": 366036, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.096906900405884, "global_step": 366037, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.128209352493286, "global_step": 366038, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.129869222640991, "global_step": 366039, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0802974700927734, "global_step": 366040, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.128446578979492, "global_step": 366041, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0814998149871826, "global_step": 366042, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0181121826171875, "global_step": 366043, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1327733993530273, "global_step": 366044, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.117771625518799, "global_step": 366045, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.135082483291626, "global_step": 366046, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0577402114868164, "global_step": 366047, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.258148193359375, "global_step": 366048, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.126171112060547, "global_step": 366049, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0865209102630615, "global_step": 366050, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1052799224853516, "global_step": 366051, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.129744052886963, "global_step": 366052, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0778002738952637, "global_step": 366053, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1084086894989014, "global_step": 366054, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.149629831314087, "global_step": 366055, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0345191955566406, "global_step": 366056, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.113729953765869, "global_step": 366057, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1521222591400146, "global_step": 366058, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.179206132888794, "global_step": 366059, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1359703540802, "global_step": 366060, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.071882963180542, "global_step": 366061, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.06491756439209, "global_step": 366062, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.065922260284424, "global_step": 366063, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.13553524017334, "global_step": 366064, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1223926544189453, "global_step": 366065, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0952818393707275, "global_step": 366066, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.119645595550537, "global_step": 366067, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1631686687469482, "global_step": 366068, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.187302827835083, "global_step": 366069, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.126427173614502, "global_step": 366070, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.163600444793701, "global_step": 366071, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.136728048324585, "global_step": 366072, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1392312049865723, "global_step": 366073, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1422338485717773, "global_step": 366074, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.031700611114502, "global_step": 366075, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0885229110717773, "global_step": 366076, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.11733078956604, "global_step": 366077, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1747922897338867, "global_step": 366078, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.122441530227661, "global_step": 366079, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1349334716796875, "global_step": 366080, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.13749361038208, "global_step": 366081, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1029412746429443, "global_step": 366082, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1268837451934814, "global_step": 366083, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.113956928253174, "global_step": 366084, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1461994647979736, "global_step": 366085, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0841267108917236, "global_step": 366086, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0853254795074463, "global_step": 366087, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1177103519439697, "global_step": 366088, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.116621494293213, "global_step": 366089, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.087437391281128, "global_step": 366090, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1294877529144287, "global_step": 366091, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1176114082336426, "global_step": 366092, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.146303415298462, "global_step": 366093, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1038904190063477, "global_step": 366094, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.121349811553955, "global_step": 366095, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.078836679458618, "global_step": 366096, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.126767873764038, "global_step": 366097, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.065335512161255, "global_step": 366098, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1346824169158936, "global_step": 366099, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0849997997283936, "global_step": 366100, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.106018543243408, "global_step": 366101, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1511731147766113, "global_step": 366102, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.172032117843628, "global_step": 366103, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0889344215393066, "global_step": 366104, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.022437572479248, "global_step": 366105, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.135728597640991, "global_step": 366106, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.120922088623047, "global_step": 366107, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.124711751937866, "global_step": 366108, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.103630304336548, "global_step": 366109, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.112710952758789, "global_step": 366110, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.063016653060913, "global_step": 366111, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0698461532592773, "global_step": 366112, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.121605396270752, "global_step": 366113, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1054532527923584, "global_step": 366114, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0646023750305176, "global_step": 366115, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.104362726211548, "global_step": 366116, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1677849292755127, "global_step": 366117, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.144378423690796, "global_step": 366118, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1519041061401367, "global_step": 366119, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0771677494049072, "global_step": 366120, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1009480953216553, "global_step": 366121, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1791036128997803, "global_step": 366122, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1721644401550293, "global_step": 366123, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1627814769744873, "global_step": 366124, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0487868785858154, "global_step": 366125, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1372339725494385, "global_step": 366126, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.037623405456543, "global_step": 366127, "epoch": 727, "lr": 5e-05}
{"train_loss": 1.9830199480056763, "global_step": 366128, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.072547435760498, "global_step": 366129, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1402816772460938, "global_step": 366130, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.147639036178589, "global_step": 366131, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0825865268707275, "global_step": 366132, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.135314464569092, "global_step": 366133, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0804290771484375, "global_step": 366134, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.091761589050293, "global_step": 366135, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0679924488067627, "global_step": 366136, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.147334098815918, "global_step": 366137, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1128270626068115, "global_step": 366138, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.130141496658325, "global_step": 366139, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0026767253875732, "global_step": 366140, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.102234363555908, "global_step": 366141, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.074450731277466, "global_step": 366142, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0388193130493164, "global_step": 366143, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1068129539489746, "global_step": 366144, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.094458818435669, "global_step": 366145, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0451552867889404, "global_step": 366146, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1348609924316406, "global_step": 366147, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0558958053588867, "global_step": 366148, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.011368751525879, "global_step": 366149, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0621442794799805, "global_step": 366150, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1295206546783447, "global_step": 366151, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1105213165283203, "global_step": 366152, "epoch": 727, "lr": 5e-05}
{"train_loss": 1.9566627740859985, "global_step": 366153, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0869405269622803, "global_step": 366154, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.113190174102783, "global_step": 366155, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.064424753189087, "global_step": 366156, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1090593338012695, "global_step": 366157, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1335110664367676, "global_step": 366158, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0790464878082275, "global_step": 366159, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.163520336151123, "global_step": 366160, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0707740783691406, "global_step": 366161, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.141646146774292, "global_step": 366162, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0312490463256836, "global_step": 366163, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0492353439331055, "global_step": 366164, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1196091175079346, "global_step": 366165, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.139293670654297, "global_step": 366166, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1453499794006348, "global_step": 366167, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.132373332977295, "global_step": 366168, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.107734203338623, "global_step": 366169, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1318166255950928, "global_step": 366170, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.044543981552124, "global_step": 366171, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.088787078857422, "global_step": 366172, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1250159740448, "global_step": 366173, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.030801773071289, "global_step": 366174, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.037696123123169, "global_step": 366175, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0611772537231445, "global_step": 366176, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0098037719726562, "global_step": 366177, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.09195613861084, "global_step": 366178, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1032018661499023, "global_step": 366179, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.070416212081909, "global_step": 366180, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0318081378936768, "global_step": 366181, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.097712993621826, "global_step": 366182, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.049103260040283, "global_step": 366183, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.132645845413208, "global_step": 366184, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.117769718170166, "global_step": 366185, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.182124376296997, "global_step": 366186, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.2143895626068115, "global_step": 366187, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.139082193374634, "global_step": 366188, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.106459140777588, "global_step": 366189, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1340603828430176, "global_step": 366190, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.128344774246216, "global_step": 366191, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0900251865386963, "global_step": 366192, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1024203300476074, "global_step": 366193, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.23181414604187, "global_step": 366194, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.081425189971924, "global_step": 366195, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1796798706054688, "global_step": 366196, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1741461753845215, "global_step": 366197, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.067141532897949, "global_step": 366198, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0754098892211914, "global_step": 366199, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1218831539154053, "global_step": 366200, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1865336894989014, "global_step": 366201, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.095846652984619, "global_step": 366202, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1500635147094727, "global_step": 366203, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.076573610305786, "global_step": 366204, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.187922477722168, "global_step": 366205, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0635459423065186, "global_step": 366206, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1091432571411133, "global_step": 366207, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.100632429122925, "global_step": 366208, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0546700954437256, "global_step": 366209, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.137094020843506, "global_step": 366210, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.181896209716797, "global_step": 366211, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0862932205200195, "global_step": 366212, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0664219856262207, "global_step": 366213, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1318230628967285, "global_step": 366214, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0330026149749756, "global_step": 366215, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0695247650146484, "global_step": 366216, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.12724232673645, "global_step": 366217, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.064460277557373, "global_step": 366218, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0912368297576904, "global_step": 366219, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0505194664001465, "global_step": 366220, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0999059677124023, "global_step": 366221, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1438002586364746, "global_step": 366222, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0515406131744385, "global_step": 366223, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0164246559143066, "global_step": 366224, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1226706504821777, "global_step": 366225, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.07391095161438, "global_step": 366226, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0186281204223633, "global_step": 366227, "epoch": 727, "lr": 5e-05}
{"train_loss": 1.9786808490753174, "global_step": 366228, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.044067144393921, "global_step": 366229, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.080714702606201, "global_step": 366230, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.103037118911743, "global_step": 366231, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0926990509033203, "global_step": 366232, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0538556575775146, "global_step": 366233, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.081583023071289, "global_step": 366234, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.032853603363037, "global_step": 366235, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.224358320236206, "global_step": 366236, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1032590866088867, "global_step": 366237, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.108375072479248, "global_step": 366238, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.163811206817627, "global_step": 366239, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.127377986907959, "global_step": 366240, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.028801202774048, "global_step": 366241, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1838324069976807, "global_step": 366242, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.062058210372925, "global_step": 366243, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.120117664337158, "global_step": 366244, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.140089988708496, "global_step": 366245, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0656063556671143, "global_step": 366246, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.076672315597534, "global_step": 366247, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.156660795211792, "global_step": 366248, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1563491821289062, "global_step": 366249, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1273140907287598, "global_step": 366250, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.161465883255005, "global_step": 366251, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.04258394241333, "global_step": 366252, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1046459674835205, "global_step": 366253, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.096484422683716, "global_step": 366254, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.067270278930664, "global_step": 366255, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.080200433731079, "global_step": 366256, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1124069690704346, "global_step": 366257, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0816476345062256, "global_step": 366258, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.186218738555908, "global_step": 366259, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1892712116241455, "global_step": 366260, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1039319038391113, "global_step": 366261, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0945398807525635, "global_step": 366262, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.113137722015381, "global_step": 366263, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.196319103240967, "global_step": 366264, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0207648277282715, "global_step": 366265, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.070986747741699, "global_step": 366266, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1046700477600098, "global_step": 366267, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0289993286132812, "global_step": 366268, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0441102981567383, "global_step": 366269, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1515047550201416, "global_step": 366270, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.075624704360962, "global_step": 366271, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.046858787536621, "global_step": 366272, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1867730617523193, "global_step": 366273, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0753824710845947, "global_step": 366274, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.101963996887207, "global_step": 366275, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1047260761260986, "global_step": 366276, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1022257804870605, "global_step": 366277, "epoch": 727, "lr": 5e-05}
{"train_loss": 1.9965680837631226, "global_step": 366278, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.11212420463562, "global_step": 366279, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0524213314056396, "global_step": 366280, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1178181171417236, "global_step": 366281, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0820860862731934, "global_step": 366282, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.109238386154175, "global_step": 366283, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.208923578262329, "global_step": 366284, "epoch": 727, "lr": 5e-05}
{"train_loss": 1.983906626701355, "global_step": 366285, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.126765727996826, "global_step": 366286, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0939927101135254, "global_step": 366287, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.084178924560547, "global_step": 366288, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.090468406677246, "global_step": 366289, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0159265995025635, "global_step": 366290, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0525920391082764, "global_step": 366291, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.247225522994995, "global_step": 366292, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1251778602600098, "global_step": 366293, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0616021156311035, "global_step": 366294, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0790743827819824, "global_step": 366295, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.08575177192688, "global_step": 366296, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1330554485321045, "global_step": 366297, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1937096118927, "global_step": 366298, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1536829471588135, "global_step": 366299, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.17741322517395, "global_step": 366300, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1448049545288086, "global_step": 366301, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.09883975982666, "global_step": 366302, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0617852210998535, "global_step": 366303, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1952457427978516, "global_step": 366304, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1065378189086914, "global_step": 366305, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.140904664993286, "global_step": 366306, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1312873363494873, "global_step": 366307, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.120488405227661, "global_step": 366308, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1577200889587402, "global_step": 366309, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.204741954803467, "global_step": 366310, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.092334032058716, "global_step": 366311, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1580727100372314, "global_step": 366312, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.098755121231079, "global_step": 366313, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1598877906799316, "global_step": 366314, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0979223251342773, "global_step": 366315, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1006991863250732, "global_step": 366316, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.097188711166382, "global_step": 366317, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0818872451782227, "global_step": 366318, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.131593704223633, "global_step": 366319, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1328389644622803, "global_step": 366320, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.197385787963867, "global_step": 366321, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.066192865371704, "global_step": 366322, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.159360408782959, "global_step": 366323, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0762810707092285, "global_step": 366324, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.168436288833618, "global_step": 366325, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1276731491088867, "global_step": 366326, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.150235891342163, "global_step": 366327, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.149890661239624, "global_step": 366328, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1870155334472656, "global_step": 366329, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.089663028717041, "global_step": 366330, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0518712997436523, "global_step": 366331, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.036348581314087, "global_step": 366332, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1268861293792725, "global_step": 366333, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.070024013519287, "global_step": 366334, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.177049160003662, "global_step": 366335, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0555481910705566, "global_step": 366336, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.097899913787842, "global_step": 366337, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1039698123931885, "global_step": 366338, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0742228031158447, "global_step": 366339, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.11906099319458, "global_step": 366340, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.128811836242676, "global_step": 366341, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.113535165786743, "global_step": 366342, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.182421922683716, "global_step": 366343, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1820452213287354, "global_step": 366344, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.05547833442688, "global_step": 366345, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0505919456481934, "global_step": 366346, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0801873207092285, "global_step": 366347, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.152641773223877, "global_step": 366348, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1881532669067383, "global_step": 366349, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.129189968109131, "global_step": 366350, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.110064744949341, "global_step": 366351, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0599029064178467, "global_step": 366352, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.141474723815918, "global_step": 366353, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1435558795928955, "global_step": 366354, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0501961708068848, "global_step": 366355, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1417758464813232, "global_step": 366356, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1113834381103516, "global_step": 366357, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.188765048980713, "global_step": 366358, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1224117279052734, "global_step": 366359, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.224330425262451, "global_step": 366360, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0587546825408936, "global_step": 366361, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.138232946395874, "global_step": 366362, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1915431022644043, "global_step": 366363, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0970420837402344, "global_step": 366364, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.015767812728882, "global_step": 366365, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.148489475250244, "global_step": 366366, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.147629499435425, "global_step": 366367, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.114982843399048, "global_step": 366368, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.059096574783325, "global_step": 366369, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1695075035095215, "global_step": 366370, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1571877002716064, "global_step": 366371, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0766777992248535, "global_step": 366372, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0631158351898193, "global_step": 366373, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.206817626953125, "global_step": 366374, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1463844776153564, "global_step": 366375, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0333893299102783, "global_step": 366376, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.151017904281616, "global_step": 366377, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0203216075897217, "global_step": 366378, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1222312450408936, "global_step": 366379, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0894551277160645, "global_step": 366380, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0803401470184326, "global_step": 366381, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0680384635925293, "global_step": 366382, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1627273559570312, "global_step": 366383, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.166379690170288, "global_step": 366384, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.177602529525757, "global_step": 366385, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0634231567382812, "global_step": 366386, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1324682235717773, "global_step": 366387, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.15110445022583, "global_step": 366388, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.169340133666992, "global_step": 366389, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.12984299659729, "global_step": 366390, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1071133613586426, "global_step": 366391, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1171061992645264, "global_step": 366392, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0736358165740967, "global_step": 366393, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1732230186462402, "global_step": 366394, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1351163387298584, "global_step": 366395, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0796196460723877, "global_step": 366396, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.026055097579956, "global_step": 366397, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0736546516418457, "global_step": 366398, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.051194906234741, "global_step": 366399, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0716500282287598, "global_step": 366400, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.058532476425171, "global_step": 366401, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.2031309604644775, "global_step": 366402, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.0792484283447266, "global_step": 366403, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1024394035339355, "global_step": 366404, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.113591432571411, "global_step": 366405, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.2271692752838135, "global_step": 366406, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.070629119873047, "global_step": 366407, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1342508792877197, "global_step": 366408, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.047067165374756, "global_step": 366409, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.097902774810791, "global_step": 366410, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.169344902038574, "global_step": 366411, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.1245501041412354, "global_step": 366412, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.119896411895752, "global_step": 366413, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.107213020324707, "global_step": 366414, "epoch": 727, "lr": 5e-05}
{"train_loss": 2.116150140762329, "global_step": 366415, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0949478149414062, "global_step": 366416, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0765316486358643, "global_step": 366417, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.138620376586914, "global_step": 366418, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0799753665924072, "global_step": 366419, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0580599308013916, "global_step": 366420, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.141453981399536, "global_step": 366421, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.03743839263916, "global_step": 366422, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.09454083442688, "global_step": 366423, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1197102069854736, "global_step": 366424, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1244235038757324, "global_step": 366425, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.149653673171997, "global_step": 366426, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1754753589630127, "global_step": 366427, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.097052574157715, "global_step": 366428, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.020362615585327, "global_step": 366429, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1680188179016113, "global_step": 366430, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.050776243209839, "global_step": 366431, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.05535888671875, "global_step": 366432, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1736650466918945, "global_step": 366433, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.103936195373535, "global_step": 366434, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1157679557800293, "global_step": 366435, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.107480764389038, "global_step": 366436, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.11724591255188, "global_step": 366437, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.017650842666626, "global_step": 366438, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.123195171356201, "global_step": 366439, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.040313482284546, "global_step": 366440, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1717803478240967, "global_step": 366441, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0705113410949707, "global_step": 366442, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1027708053588867, "global_step": 366443, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0772602558135986, "global_step": 366444, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.039340019226074, "global_step": 366445, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.187730550765991, "global_step": 366446, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0994739532470703, "global_step": 366447, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.135467052459717, "global_step": 366448, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1510143280029297, "global_step": 366449, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0827338695526123, "global_step": 366450, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1075356006622314, "global_step": 366451, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0785422325134277, "global_step": 366452, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1718990802764893, "global_step": 366453, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.104249954223633, "global_step": 366454, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1170480251312256, "global_step": 366455, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.048086166381836, "global_step": 366456, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1456754207611084, "global_step": 366457, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1407084465026855, "global_step": 366458, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.063396453857422, "global_step": 366459, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.098273515701294, "global_step": 366460, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1341402530670166, "global_step": 366461, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.204317092895508, "global_step": 366462, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.056236505508423, "global_step": 366463, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.043520927429199, "global_step": 366464, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0428543090820312, "global_step": 366465, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.086761474609375, "global_step": 366466, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.095825433731079, "global_step": 366467, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0651748180389404, "global_step": 366468, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1150355339050293, "global_step": 366469, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0662670135498047, "global_step": 366470, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1014106273651123, "global_step": 366471, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.120819330215454, "global_step": 366472, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.156329393386841, "global_step": 366473, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0331478118896484, "global_step": 366474, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.079096794128418, "global_step": 366475, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.084376573562622, "global_step": 366476, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1168696880340576, "global_step": 366477, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0329270362854004, "global_step": 366478, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0478620529174805, "global_step": 366479, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.080266237258911, "global_step": 366480, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1493608951568604, "global_step": 366481, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.072380304336548, "global_step": 366482, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.166414737701416, "global_step": 366483, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.095320701599121, "global_step": 366484, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.035247325897217, "global_step": 366485, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0767757892608643, "global_step": 366486, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0924947261810303, "global_step": 366487, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.137566328048706, "global_step": 366488, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.158026933670044, "global_step": 366489, "epoch": 728, "lr": 5e-05}
{"train_loss": 1.9873846769332886, "global_step": 366490, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1192405223846436, "global_step": 366491, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2338263988494873, "global_step": 366492, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.063929796218872, "global_step": 366493, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.086886405944824, "global_step": 366494, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.105440139770508, "global_step": 366495, "epoch": 728, "lr": 5e-05}
{"train_loss": 1.9779566526412964, "global_step": 366496, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.208855628967285, "global_step": 366497, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1358814239501953, "global_step": 366498, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0993428230285645, "global_step": 366499, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0546653270721436, "global_step": 366500, "epoch": 728, "lr": 5e-05}
{"train_loss": 1.9999878406524658, "global_step": 366501, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1286778450012207, "global_step": 366502, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1553754806518555, "global_step": 366503, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.066075563430786, "global_step": 366504, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.174133062362671, "global_step": 366505, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.187814950942993, "global_step": 366506, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.022596597671509, "global_step": 366507, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.130162477493286, "global_step": 366508, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.049121379852295, "global_step": 366509, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.157626152038574, "global_step": 366510, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0123376846313477, "global_step": 366511, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.099797248840332, "global_step": 366512, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.085310697555542, "global_step": 366513, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.113229274749756, "global_step": 366514, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.142528533935547, "global_step": 366515, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.096508502960205, "global_step": 366516, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1760692596435547, "global_step": 366517, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1034138202667236, "global_step": 366518, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.058403968811035, "global_step": 366519, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.126309633255005, "global_step": 366520, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0764081478118896, "global_step": 366521, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2187395095825195, "global_step": 366522, "epoch": 728, "lr": 5e-05}
{"train_loss": 1.9952281713485718, "global_step": 366523, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1050002574920654, "global_step": 366524, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.12841796875, "global_step": 366525, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.062213897705078, "global_step": 366526, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.123548984527588, "global_step": 366527, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.157327890396118, "global_step": 366528, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0906600952148438, "global_step": 366529, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0468802452087402, "global_step": 366530, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.029268503189087, "global_step": 366531, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.089664936065674, "global_step": 366532, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0186808109283447, "global_step": 366533, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0765273571014404, "global_step": 366534, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.088181257247925, "global_step": 366535, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1574361324310303, "global_step": 366536, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1340062618255615, "global_step": 366537, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.135471820831299, "global_step": 366538, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.071495294570923, "global_step": 366539, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0715901851654053, "global_step": 366540, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0861029624938965, "global_step": 366541, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0717484951019287, "global_step": 366542, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2216460704803467, "global_step": 366543, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1375985145568848, "global_step": 366544, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1242663860321045, "global_step": 366545, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0249016284942627, "global_step": 366546, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.118389368057251, "global_step": 366547, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1544225215911865, "global_step": 366548, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.097752809524536, "global_step": 366549, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.26948881149292, "global_step": 366550, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.179203748703003, "global_step": 366551, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.049316167831421, "global_step": 366552, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.11486554145813, "global_step": 366553, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.03606915473938, "global_step": 366554, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.062995195388794, "global_step": 366555, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1495778560638428, "global_step": 366556, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1142642498016357, "global_step": 366557, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0949511528015137, "global_step": 366558, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.04046368598938, "global_step": 366559, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0922656059265137, "global_step": 366560, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.176525592803955, "global_step": 366561, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0600192546844482, "global_step": 366562, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.099982500076294, "global_step": 366563, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.163860321044922, "global_step": 366564, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0212697982788086, "global_step": 366565, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1726343631744385, "global_step": 366566, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0220754146575928, "global_step": 366567, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.052321672439575, "global_step": 366568, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.07989501953125, "global_step": 366569, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0889172554016113, "global_step": 366570, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0703930854797363, "global_step": 366571, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1835405826568604, "global_step": 366572, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0596675872802734, "global_step": 366573, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0050110816955566, "global_step": 366574, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1330435276031494, "global_step": 366575, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1133594512939453, "global_step": 366576, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1896252632141113, "global_step": 366577, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0630996227264404, "global_step": 366578, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1581344604492188, "global_step": 366579, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0863585472106934, "global_step": 366580, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0425937175750732, "global_step": 366581, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.088893175125122, "global_step": 366582, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0616555213928223, "global_step": 366583, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.155956268310547, "global_step": 366584, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0419487953186035, "global_step": 366585, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.050787925720215, "global_step": 366586, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.086488723754883, "global_step": 366587, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1779630184173584, "global_step": 366588, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0701284408569336, "global_step": 366589, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0850069522857666, "global_step": 366590, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0644984245300293, "global_step": 366591, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1285669803619385, "global_step": 366592, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.170811176300049, "global_step": 366593, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0085031986236572, "global_step": 366594, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1540396213531494, "global_step": 366595, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.148475408554077, "global_step": 366596, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1353907585144043, "global_step": 366597, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1260859966278076, "global_step": 366598, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.077998161315918, "global_step": 366599, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0405876636505127, "global_step": 366600, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.117891550064087, "global_step": 366601, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.127408742904663, "global_step": 366602, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1832923889160156, "global_step": 366603, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1166181564331055, "global_step": 366604, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1622934341430664, "global_step": 366605, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1625757217407227, "global_step": 366606, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0440220832824707, "global_step": 366607, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1554324626922607, "global_step": 366608, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.176889419555664, "global_step": 366609, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1583669185638428, "global_step": 366610, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0633583068847656, "global_step": 366611, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0728816986083984, "global_step": 366612, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2070324420928955, "global_step": 366613, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1675612926483154, "global_step": 366614, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.167958974838257, "global_step": 366615, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0022096633911133, "global_step": 366616, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.080007553100586, "global_step": 366617, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0682015419006348, "global_step": 366618, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0488035678863525, "global_step": 366619, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0588455200195312, "global_step": 366620, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.108342409133911, "global_step": 366621, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0160930156707764, "global_step": 366622, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1231701374053955, "global_step": 366623, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.092698812484741, "global_step": 366624, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0541625022888184, "global_step": 366625, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1536176204681396, "global_step": 366626, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0550551414489746, "global_step": 366627, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.10481595993042, "global_step": 366628, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0717685222625732, "global_step": 366629, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1264588832855225, "global_step": 366630, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1332991123199463, "global_step": 366631, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.108363628387451, "global_step": 366632, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.006012201309204, "global_step": 366633, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1009609699249268, "global_step": 366634, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0975754261016846, "global_step": 366635, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.009211540222168, "global_step": 366636, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.043630361557007, "global_step": 366637, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1099348068237305, "global_step": 366638, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1723825931549072, "global_step": 366639, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.11360764503479, "global_step": 366640, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.059495449066162, "global_step": 366641, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.136324644088745, "global_step": 366642, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1419105529785156, "global_step": 366643, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1068172454833984, "global_step": 366644, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1544430255889893, "global_step": 366645, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0819156169891357, "global_step": 366646, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1915407180786133, "global_step": 366647, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1470706462860107, "global_step": 366648, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0937514305114746, "global_step": 366649, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1299796104431152, "global_step": 366650, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.075911045074463, "global_step": 366651, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1116371154785156, "global_step": 366652, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0897269248962402, "global_step": 366653, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0743982791900635, "global_step": 366654, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0967066287994385, "global_step": 366655, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0962233543395996, "global_step": 366656, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0356736183166504, "global_step": 366657, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.015021562576294, "global_step": 366658, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1440210342407227, "global_step": 366659, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1158573627471924, "global_step": 366660, "epoch": 728, "lr": 5e-05}
{"train_loss": 1.9834620952606201, "global_step": 366661, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.042304039001465, "global_step": 366662, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1438915729522705, "global_step": 366663, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1061630249023438, "global_step": 366664, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0971322059631348, "global_step": 366665, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.059103012084961, "global_step": 366666, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.160346031188965, "global_step": 366667, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.188068389892578, "global_step": 366668, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1057662963867188, "global_step": 366669, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1274476051330566, "global_step": 366670, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1006360054016113, "global_step": 366671, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0800201892852783, "global_step": 366672, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0687313079833984, "global_step": 366673, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1806347370147705, "global_step": 366674, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.054212808609009, "global_step": 366675, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.030773639678955, "global_step": 366676, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0911166667938232, "global_step": 366677, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0731256008148193, "global_step": 366678, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1229796409606934, "global_step": 366679, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0894277095794678, "global_step": 366680, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.074838161468506, "global_step": 366681, "epoch": 728, "lr": 5e-05}
{"train_loss": 1.9883090257644653, "global_step": 366682, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1545987129211426, "global_step": 366683, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0822594165802, "global_step": 366684, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0665111541748047, "global_step": 366685, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1867966651916504, "global_step": 366686, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1148178577423096, "global_step": 366687, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.097031831741333, "global_step": 366688, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0481557846069336, "global_step": 366689, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.112834930419922, "global_step": 366690, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0782978534698486, "global_step": 366691, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.061399221420288, "global_step": 366692, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.174370288848877, "global_step": 366693, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1434268951416016, "global_step": 366694, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.110856056213379, "global_step": 366695, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.111029624938965, "global_step": 366696, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.105678081512451, "global_step": 366697, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0779876708984375, "global_step": 366698, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.082512378692627, "global_step": 366699, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0643630027770996, "global_step": 366700, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0358033180236816, "global_step": 366701, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0694580078125, "global_step": 366702, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.030240774154663, "global_step": 366703, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1503384113311768, "global_step": 366704, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0690996646881104, "global_step": 366705, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1276869773864746, "global_step": 366706, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.064046859741211, "global_step": 366707, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1367247104644775, "global_step": 366708, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0712761878967285, "global_step": 366709, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1381020545959473, "global_step": 366710, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0303263664245605, "global_step": 366711, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.059413194656372, "global_step": 366712, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.126180410385132, "global_step": 366713, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.011672258377075, "global_step": 366714, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0544779300689697, "global_step": 366715, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0337424278259277, "global_step": 366716, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.150860071182251, "global_step": 366717, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0839381217956543, "global_step": 366718, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2476742267608643, "global_step": 366719, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.151808738708496, "global_step": 366720, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.089202642440796, "global_step": 366721, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0800678730010986, "global_step": 366722, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0903217792510986, "global_step": 366723, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0833230018615723, "global_step": 366724, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.145932912826538, "global_step": 366725, "epoch": 728, "lr": 5e-05}
{"train_loss": 1.968018651008606, "global_step": 366726, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1081058979034424, "global_step": 366727, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.14193058013916, "global_step": 366728, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.071039915084839, "global_step": 366729, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2225191593170166, "global_step": 366730, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1017956733703613, "global_step": 366731, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.094362258911133, "global_step": 366732, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.072070598602295, "global_step": 366733, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2413077354431152, "global_step": 366734, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1393630504608154, "global_step": 366735, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2360029220581055, "global_step": 366736, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.102590799331665, "global_step": 366737, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1506645679473877, "global_step": 366738, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0945489406585693, "global_step": 366739, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.132977247238159, "global_step": 366740, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.162233352661133, "global_step": 366741, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1069862842559814, "global_step": 366742, "epoch": 728, "lr": 5e-05}
{"train_loss": 1.9904638528823853, "global_step": 366743, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1474924087524414, "global_step": 366744, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.067521572113037, "global_step": 366745, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0721380710601807, "global_step": 366746, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.107311248779297, "global_step": 366747, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.078138828277588, "global_step": 366748, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0539586544036865, "global_step": 366749, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.17106294631958, "global_step": 366750, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.150395154953003, "global_step": 366751, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1564154624938965, "global_step": 366752, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.028200387954712, "global_step": 366753, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.096864700317383, "global_step": 366754, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0685439109802246, "global_step": 366755, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.118953227996826, "global_step": 366756, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1179709434509277, "global_step": 366757, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.064981698989868, "global_step": 366758, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0657341480255127, "global_step": 366759, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0847721099853516, "global_step": 366760, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2182366847991943, "global_step": 366761, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0731234550476074, "global_step": 366762, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1347548961639404, "global_step": 366763, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.05963397026062, "global_step": 366764, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0819404125213623, "global_step": 366765, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0316720008850098, "global_step": 366766, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1422412395477295, "global_step": 366767, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.044161319732666, "global_step": 366768, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.06291127204895, "global_step": 366769, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.114328145980835, "global_step": 366770, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1044459342956543, "global_step": 366771, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0161116123199463, "global_step": 366772, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.070922374725342, "global_step": 366773, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2145519256591797, "global_step": 366774, "epoch": 728, "lr": 5e-05}
{"train_loss": 1.9563647508621216, "global_step": 366775, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1321489810943604, "global_step": 366776, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1061391830444336, "global_step": 366777, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1205663681030273, "global_step": 366778, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.133934497833252, "global_step": 366779, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.124551296234131, "global_step": 366780, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0048887729644775, "global_step": 366781, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0946428775787354, "global_step": 366782, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.188347339630127, "global_step": 366783, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1220691204071045, "global_step": 366784, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.109748125076294, "global_step": 366785, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.04469633102417, "global_step": 366786, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.107466459274292, "global_step": 366787, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.172657012939453, "global_step": 366788, "epoch": 728, "lr": 5e-05}
{"train_loss": 1.9996964931488037, "global_step": 366789, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.153245210647583, "global_step": 366790, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1467652320861816, "global_step": 366791, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.163811206817627, "global_step": 366792, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0658769607543945, "global_step": 366793, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.106170415878296, "global_step": 366794, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1796324253082275, "global_step": 366795, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0494441986083984, "global_step": 366796, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.121539831161499, "global_step": 366797, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0152533054351807, "global_step": 366798, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0864992141723633, "global_step": 366799, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1118147373199463, "global_step": 366800, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1449878215789795, "global_step": 366801, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0309410095214844, "global_step": 366802, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1373002529144287, "global_step": 366803, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0453197956085205, "global_step": 366804, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.002857208251953, "global_step": 366805, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0146279335021973, "global_step": 366806, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1000289916992188, "global_step": 366807, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.117396354675293, "global_step": 366808, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0682241916656494, "global_step": 366809, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.112605094909668, "global_step": 366810, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.157440185546875, "global_step": 366811, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1101067066192627, "global_step": 366812, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.113229274749756, "global_step": 366813, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0842318534851074, "global_step": 366814, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.14577579498291, "global_step": 366815, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1133296489715576, "global_step": 366816, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.168635606765747, "global_step": 366817, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.187307834625244, "global_step": 366818, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1678476333618164, "global_step": 366819, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1156833171844482, "global_step": 366820, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0910329818725586, "global_step": 366821, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1265265941619873, "global_step": 366822, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1367080211639404, "global_step": 366823, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.103658437728882, "global_step": 366824, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0753703117370605, "global_step": 366825, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1306679248809814, "global_step": 366826, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0767979621887207, "global_step": 366827, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0340471267700195, "global_step": 366828, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.00764536857605, "global_step": 366829, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.136960506439209, "global_step": 366830, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.076478958129883, "global_step": 366831, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.149327278137207, "global_step": 366832, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.08483624458313, "global_step": 366833, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0041143894195557, "global_step": 366834, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0989248752593994, "global_step": 366835, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.165384531021118, "global_step": 366836, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.109471082687378, "global_step": 366837, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1665284633636475, "global_step": 366838, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1566660404205322, "global_step": 366839, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.142453908920288, "global_step": 366840, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0958871841430664, "global_step": 366841, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1176347732543945, "global_step": 366842, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.120565891265869, "global_step": 366843, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0599405765533447, "global_step": 366844, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0854969024658203, "global_step": 366845, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.101970911026001, "global_step": 366846, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1191914081573486, "global_step": 366847, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.126368284225464, "global_step": 366848, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0776870250701904, "global_step": 366849, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0954813957214355, "global_step": 366850, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0749599933624268, "global_step": 366851, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.120659351348877, "global_step": 366852, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1644279956817627, "global_step": 366853, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1613667011260986, "global_step": 366854, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1672651767730713, "global_step": 366855, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.083406686782837, "global_step": 366856, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.141815423965454, "global_step": 366857, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.126154899597168, "global_step": 366858, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0584096908569336, "global_step": 366859, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.094179391860962, "global_step": 366860, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.164153575897217, "global_step": 366861, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.135866641998291, "global_step": 366862, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1180264949798584, "global_step": 366863, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0529348850250244, "global_step": 366864, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0629677772521973, "global_step": 366865, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.122734308242798, "global_step": 366866, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1111419200897217, "global_step": 366867, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.149573802947998, "global_step": 366868, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0835137367248535, "global_step": 366869, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1863279342651367, "global_step": 366870, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.060981273651123, "global_step": 366871, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0661544799804688, "global_step": 366872, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.083033323287964, "global_step": 366873, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1130268573760986, "global_step": 366874, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.057917594909668, "global_step": 366875, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1019577980041504, "global_step": 366876, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.143721342086792, "global_step": 366877, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.022679090499878, "global_step": 366878, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.04795241355896, "global_step": 366879, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1151225566864014, "global_step": 366880, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1396117210388184, "global_step": 366881, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1183066368103027, "global_step": 366882, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0283572673797607, "global_step": 366883, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.072300910949707, "global_step": 366884, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.046172618865967, "global_step": 366885, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1465182304382324, "global_step": 366886, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.074613094329834, "global_step": 366887, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.126858949661255, "global_step": 366888, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2111728191375732, "global_step": 366889, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.041576862335205, "global_step": 366890, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.014404535293579, "global_step": 366891, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.125598907470703, "global_step": 366892, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.047558307647705, "global_step": 366893, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.096402883529663, "global_step": 366894, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.139932632446289, "global_step": 366895, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0818393230438232, "global_step": 366896, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1305713653564453, "global_step": 366897, "epoch": 728, "lr": 5e-05}
{"train_loss": 1.9728742837905884, "global_step": 366898, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.127274513244629, "global_step": 366899, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.047797441482544, "global_step": 366900, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0909388065338135, "global_step": 366901, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.199022054672241, "global_step": 366902, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.068284749984741, "global_step": 366903, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1132848262786865, "global_step": 366904, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.033064842224121, "global_step": 366905, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0227341651916504, "global_step": 366906, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.075648546218872, "global_step": 366907, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.106473684310913, "global_step": 366908, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.151611566543579, "global_step": 366909, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.122911214828491, "global_step": 366910, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2069811820983887, "global_step": 366911, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.074392795562744, "global_step": 366912, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0627310276031494, "global_step": 366913, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.147277355194092, "global_step": 366914, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1196322441101074, "global_step": 366915, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0241758823394775, "global_step": 366916, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1778218746185303, "global_step": 366917, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1780712604522705, "global_step": 366918, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0963664054870605, "global_step": 366919, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.104703903198242, "global_step": 366920, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0764520168304443, "global_step": 366921, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1805577278137207, "global_step": 366922, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0677497386932373, "global_step": 366923, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.09702205657959, "global_step": 366924, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1018688678741455, "global_step": 366925, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.021494150161743, "global_step": 366926, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.102123737335205, "global_step": 366927, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1073124408721924, "global_step": 366928, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0869956016540527, "global_step": 366929, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.274033546447754, "global_step": 366930, "epoch": 728, "lr": 5e-05}
{"train_loss": 1.998227834701538, "global_step": 366931, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.065826177597046, "global_step": 366932, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.140347957611084, "global_step": 366933, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1217963695526123, "global_step": 366934, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0391910076141357, "global_step": 366935, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.019505023956299, "global_step": 366936, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0365540981292725, "global_step": 366937, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0636911392211914, "global_step": 366938, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.209564447402954, "global_step": 366939, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.079862594604492, "global_step": 366940, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1060922145843506, "global_step": 366941, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1535868644714355, "global_step": 366942, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.108959436416626, "global_step": 366943, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.080631732940674, "global_step": 366944, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0950398445129395, "global_step": 366945, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1175537109375, "global_step": 366946, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1807758808135986, "global_step": 366947, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.127446174621582, "global_step": 366948, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2695975303649902, "global_step": 366949, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0750808715820312, "global_step": 366950, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0960984230041504, "global_step": 366951, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1254465579986572, "global_step": 366952, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.124795436859131, "global_step": 366953, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.135190486907959, "global_step": 366954, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0939013957977295, "global_step": 366955, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.116713285446167, "global_step": 366956, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1103572845458984, "global_step": 366957, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1764297485351562, "global_step": 366958, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.104879856109619, "global_step": 366959, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0499773025512695, "global_step": 366960, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1020450592041016, "global_step": 366961, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1330225467681885, "global_step": 366962, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.128004550933838, "global_step": 366963, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.200338125228882, "global_step": 366964, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0805702209472656, "global_step": 366965, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.168667793273926, "global_step": 366966, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.085184097290039, "global_step": 366967, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0588316917419434, "global_step": 366968, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0712623596191406, "global_step": 366969, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0289134979248047, "global_step": 366970, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0463054180145264, "global_step": 366971, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.056684970855713, "global_step": 366972, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.121999979019165, "global_step": 366973, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1397640705108643, "global_step": 366974, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.132561683654785, "global_step": 366975, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.108908176422119, "global_step": 366976, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.095224618911743, "global_step": 366977, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.137096405029297, "global_step": 366978, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1188461780548096, "global_step": 366979, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.133446216583252, "global_step": 366980, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1342170238494873, "global_step": 366981, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2041072845458984, "global_step": 366982, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.110330104827881, "global_step": 366983, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.191499948501587, "global_step": 366984, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0364015102386475, "global_step": 366985, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.125507354736328, "global_step": 366986, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0944771766662598, "global_step": 366987, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0807945728302, "global_step": 366988, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.139677047729492, "global_step": 366989, "epoch": 728, "lr": 5e-05}
{"train_loss": 1.9939497709274292, "global_step": 366990, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.102827310562134, "global_step": 366991, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2208712100982666, "global_step": 366992, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.095179557800293, "global_step": 366993, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1011252403259277, "global_step": 366994, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1259548664093018, "global_step": 366995, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1269381046295166, "global_step": 366996, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0865437984466553, "global_step": 366997, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.023616075515747, "global_step": 366998, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1608355045318604, "global_step": 366999, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.094862699508667, "global_step": 367000, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1142492294311523, "global_step": 367001, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1994173526763916, "global_step": 367002, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.101898193359375, "global_step": 367003, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0968496799468994, "global_step": 367004, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.112656831741333, "global_step": 367005, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1156890392303467, "global_step": 367006, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.045398712158203, "global_step": 367007, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1599066257476807, "global_step": 367008, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0785183906555176, "global_step": 367009, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.125033378601074, "global_step": 367010, "epoch": 728, "lr": 5e-05}
{"train_loss": 1.9504040479660034, "global_step": 367011, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0940475463867188, "global_step": 367012, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1318931579589844, "global_step": 367013, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0841071605682373, "global_step": 367014, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1587820053100586, "global_step": 367015, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.121922254562378, "global_step": 367016, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.045304298400879, "global_step": 367017, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0840647220611572, "global_step": 367018, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.11037278175354, "global_step": 367019, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.073439598083496, "global_step": 367020, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1082587242126465, "global_step": 367021, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.03218150138855, "global_step": 367022, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1465837955474854, "global_step": 367023, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1903746128082275, "global_step": 367024, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1487553119659424, "global_step": 367025, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0899434089660645, "global_step": 367026, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1006548404693604, "global_step": 367027, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.130728244781494, "global_step": 367028, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1810030937194824, "global_step": 367029, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1463654041290283, "global_step": 367030, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0765302181243896, "global_step": 367031, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1132619380950928, "global_step": 367032, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.081650972366333, "global_step": 367033, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1745502948760986, "global_step": 367034, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1736505031585693, "global_step": 367035, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0457262992858887, "global_step": 367036, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1161019802093506, "global_step": 367037, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.084929943084717, "global_step": 367038, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1213321685791016, "global_step": 367039, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0312647819519043, "global_step": 367040, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.11421537399292, "global_step": 367041, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.133953332901001, "global_step": 367042, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1421093940734863, "global_step": 367043, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.094149112701416, "global_step": 367044, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1716246604919434, "global_step": 367045, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.163949966430664, "global_step": 367046, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.10298752784729, "global_step": 367047, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.134249448776245, "global_step": 367048, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.113849639892578, "global_step": 367049, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1059727668762207, "global_step": 367050, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1434175968170166, "global_step": 367051, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1005282402038574, "global_step": 367052, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.074939012527466, "global_step": 367053, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0872466564178467, "global_step": 367054, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0878984928131104, "global_step": 367055, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.077263116836548, "global_step": 367056, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0664398670196533, "global_step": 367057, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1260950565338135, "global_step": 367058, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1396045684814453, "global_step": 367059, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.146177053451538, "global_step": 367060, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0861220359802246, "global_step": 367061, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2001211643218994, "global_step": 367062, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.133223533630371, "global_step": 367063, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1599478721618652, "global_step": 367064, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1211180686950684, "global_step": 367065, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1589057445526123, "global_step": 367066, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.165747880935669, "global_step": 367067, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.117385149002075, "global_step": 367068, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2165462970733643, "global_step": 367069, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.064244031906128, "global_step": 367070, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0152652263641357, "global_step": 367071, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1749298572540283, "global_step": 367072, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1013221740722656, "global_step": 367073, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0746841430664062, "global_step": 367074, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.140960216522217, "global_step": 367075, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.063810110092163, "global_step": 367076, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1254684925079346, "global_step": 367077, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0372257232666016, "global_step": 367078, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1356921195983887, "global_step": 367079, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.134941816329956, "global_step": 367080, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.170285701751709, "global_step": 367081, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0336925983428955, "global_step": 367082, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1135478019714355, "global_step": 367083, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2288334369659424, "global_step": 367084, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1021838188171387, "global_step": 367085, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1341466903686523, "global_step": 367086, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.080306053161621, "global_step": 367087, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0975024700164795, "global_step": 367088, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1086440086364746, "global_step": 367089, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.074089765548706, "global_step": 367090, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0913496017456055, "global_step": 367091, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1597988605499268, "global_step": 367092, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.066373348236084, "global_step": 367093, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.156242609024048, "global_step": 367094, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1795642375946045, "global_step": 367095, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.136589288711548, "global_step": 367096, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.11077880859375, "global_step": 367097, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.073051929473877, "global_step": 367098, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.128882884979248, "global_step": 367099, "epoch": 728, "lr": 5e-05}
{"train_loss": 1.9857087135314941, "global_step": 367100, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1054201126098633, "global_step": 367101, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.067500591278076, "global_step": 367102, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.071495294570923, "global_step": 367103, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.072871446609497, "global_step": 367104, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.207472085952759, "global_step": 367105, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1216189861297607, "global_step": 367106, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.071453094482422, "global_step": 367107, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1290781497955322, "global_step": 367108, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0227386951446533, "global_step": 367109, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1641178131103516, "global_step": 367110, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1069705486297607, "global_step": 367111, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0872867107391357, "global_step": 367112, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0875186920166016, "global_step": 367113, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0517401695251465, "global_step": 367114, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0748417377471924, "global_step": 367115, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1187996864318848, "global_step": 367116, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.152667284011841, "global_step": 367117, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1038401126861572, "global_step": 367118, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.054008722305298, "global_step": 367119, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1115152835845947, "global_step": 367120, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.109989643096924, "global_step": 367121, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0709381103515625, "global_step": 367122, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0914061069488525, "global_step": 367123, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.071674346923828, "global_step": 367124, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1268742084503174, "global_step": 367125, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1730024814605713, "global_step": 367126, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1006710529327393, "global_step": 367127, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.098026990890503, "global_step": 367128, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0945539474487305, "global_step": 367129, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0490188598632812, "global_step": 367130, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1199724674224854, "global_step": 367131, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0227255821228027, "global_step": 367132, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.081472158432007, "global_step": 367133, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1969680786132812, "global_step": 367134, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0827012062072754, "global_step": 367135, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.102475643157959, "global_step": 367136, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.046801805496216, "global_step": 367137, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.13454008102417, "global_step": 367138, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.102396249771118, "global_step": 367139, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.139512777328491, "global_step": 367140, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.169431686401367, "global_step": 367141, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.042785882949829, "global_step": 367142, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.167672872543335, "global_step": 367143, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.136866807937622, "global_step": 367144, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0995490550994873, "global_step": 367145, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1347496509552, "global_step": 367146, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.138047218322754, "global_step": 367147, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.127480983734131, "global_step": 367148, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1302244663238525, "global_step": 367149, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1201086044311523, "global_step": 367150, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.18942928314209, "global_step": 367151, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0852267742156982, "global_step": 367152, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0875461101531982, "global_step": 367153, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1328916549682617, "global_step": 367154, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.065844774246216, "global_step": 367155, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1650102138519287, "global_step": 367156, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0943384170532227, "global_step": 367157, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0831968784332275, "global_step": 367158, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1119000911712646, "global_step": 367159, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.084346055984497, "global_step": 367160, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1692564487457275, "global_step": 367161, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.00762939453125, "global_step": 367162, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.174004316329956, "global_step": 367163, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1648802757263184, "global_step": 367164, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0761218070983887, "global_step": 367165, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0634870529174805, "global_step": 367166, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.095560073852539, "global_step": 367167, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1729867458343506, "global_step": 367168, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1020750999450684, "global_step": 367169, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0781307220458984, "global_step": 367170, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.12640118598938, "global_step": 367171, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2399826049804688, "global_step": 367172, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0545237064361572, "global_step": 367173, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1014156341552734, "global_step": 367174, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.10508394241333, "global_step": 367175, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0962142944335938, "global_step": 367176, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1820387840270996, "global_step": 367177, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0074777603149414, "global_step": 367178, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0696017742156982, "global_step": 367179, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0996334552764893, "global_step": 367180, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.007028818130493, "global_step": 367181, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2047839164733887, "global_step": 367182, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.019690990447998, "global_step": 367183, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0507395267486572, "global_step": 367184, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1405327320098877, "global_step": 367185, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.127164602279663, "global_step": 367186, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0892722606658936, "global_step": 367187, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.102168083190918, "global_step": 367188, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.103245973587036, "global_step": 367189, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1324963569641113, "global_step": 367190, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1137804985046387, "global_step": 367191, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.120558738708496, "global_step": 367192, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.087942600250244, "global_step": 367193, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1691524982452393, "global_step": 367194, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1376407146453857, "global_step": 367195, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.071230888366699, "global_step": 367196, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.101597785949707, "global_step": 367197, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0994694232940674, "global_step": 367198, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0995707511901855, "global_step": 367199, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1242828369140625, "global_step": 367200, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.130253791809082, "global_step": 367201, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1027305126190186, "global_step": 367202, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.150554895401001, "global_step": 367203, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0679242610931396, "global_step": 367204, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1330525875091553, "global_step": 367205, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0871336460113525, "global_step": 367206, "epoch": 728, "lr": 5e-05}
{"train_loss": 1.9980113506317139, "global_step": 367207, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1203126907348633, "global_step": 367208, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0940871238708496, "global_step": 367209, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1908233165740967, "global_step": 367210, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.063927412033081, "global_step": 367211, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1615538597106934, "global_step": 367212, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1318743228912354, "global_step": 367213, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.131455898284912, "global_step": 367214, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1169400215148926, "global_step": 367215, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.091700553894043, "global_step": 367216, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.091480016708374, "global_step": 367217, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.06927490234375, "global_step": 367218, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.192460060119629, "global_step": 367219, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.110255002975464, "global_step": 367220, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.223159074783325, "global_step": 367221, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.126162528991699, "global_step": 367222, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.093355417251587, "global_step": 367223, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0980005264282227, "global_step": 367224, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0949742794036865, "global_step": 367225, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1479406356811523, "global_step": 367226, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.107393503189087, "global_step": 367227, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.075453042984009, "global_step": 367228, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.113297700881958, "global_step": 367229, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1563048362731934, "global_step": 367230, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.10017728805542, "global_step": 367231, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.068110942840576, "global_step": 367232, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.141498565673828, "global_step": 367233, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.089348554611206, "global_step": 367234, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0705275535583496, "global_step": 367235, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1850156784057617, "global_step": 367236, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0986266136169434, "global_step": 367237, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.117262125015259, "global_step": 367238, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.11273455619812, "global_step": 367239, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.119795799255371, "global_step": 367240, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.081855535507202, "global_step": 367241, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.125295639038086, "global_step": 367242, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.20597243309021, "global_step": 367243, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1826891899108887, "global_step": 367244, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.015679359436035, "global_step": 367245, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.158374309539795, "global_step": 367246, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0913279056549072, "global_step": 367247, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.103163242340088, "global_step": 367248, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1273694038391113, "global_step": 367249, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1066458225250244, "global_step": 367250, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.117499351501465, "global_step": 367251, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0962324142456055, "global_step": 367252, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.159806489944458, "global_step": 367253, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0826265811920166, "global_step": 367254, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.061767339706421, "global_step": 367255, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.102130174636841, "global_step": 367256, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.102735757827759, "global_step": 367257, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1288888454437256, "global_step": 367258, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.156320810317993, "global_step": 367259, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.02767276763916, "global_step": 367260, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0779783725738525, "global_step": 367261, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0902225971221924, "global_step": 367262, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.126880645751953, "global_step": 367263, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1192150115966797, "global_step": 367264, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1676394939422607, "global_step": 367265, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.154566764831543, "global_step": 367266, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.114455223083496, "global_step": 367267, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.12931752204895, "global_step": 367268, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.126741647720337, "global_step": 367269, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1389200687408447, "global_step": 367270, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0838799476623535, "global_step": 367271, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.061189889907837, "global_step": 367272, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1257381439208984, "global_step": 367273, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0614919662475586, "global_step": 367274, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1241025924682617, "global_step": 367275, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1329290866851807, "global_step": 367276, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1260409355163574, "global_step": 367277, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1840646266937256, "global_step": 367278, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.150211811065674, "global_step": 367279, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0639960765838623, "global_step": 367280, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.159719228744507, "global_step": 367281, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.027570962905884, "global_step": 367282, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1138575077056885, "global_step": 367283, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1160573959350586, "global_step": 367284, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1132493019104004, "global_step": 367285, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2433505058288574, "global_step": 367286, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.120199203491211, "global_step": 367287, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0888636112213135, "global_step": 367288, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0121116638183594, "global_step": 367289, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1595003604888916, "global_step": 367290, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1238436698913574, "global_step": 367291, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.10713791847229, "global_step": 367292, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.070370674133301, "global_step": 367293, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1054155826568604, "global_step": 367294, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1515891551971436, "global_step": 367295, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.181925058364868, "global_step": 367296, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.072040319442749, "global_step": 367297, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.149101495742798, "global_step": 367298, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0557262897491455, "global_step": 367299, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.102954149246216, "global_step": 367300, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0111920833587646, "global_step": 367301, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.146704912185669, "global_step": 367302, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.17732572555542, "global_step": 367303, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.172071695327759, "global_step": 367304, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.092146635055542, "global_step": 367305, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0796942710876465, "global_step": 367306, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0960214138031006, "global_step": 367307, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.156506299972534, "global_step": 367308, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1284139156341553, "global_step": 367309, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.092682361602783, "global_step": 367310, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.11568546295166, "global_step": 367311, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.085164785385132, "global_step": 367312, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1447975635528564, "global_step": 367313, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0577051639556885, "global_step": 367314, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0876359939575195, "global_step": 367315, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.130730390548706, "global_step": 367316, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0627949237823486, "global_step": 367317, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.055203437805176, "global_step": 367318, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1028804779052734, "global_step": 367319, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.125516891479492, "global_step": 367320, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1957924365997314, "global_step": 367321, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1348791122436523, "global_step": 367322, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0972137451171875, "global_step": 367323, "epoch": 728, "lr": 5e-05}
{"train_loss": 1.9939072132110596, "global_step": 367324, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.222036838531494, "global_step": 367325, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.145747184753418, "global_step": 367326, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1344780921936035, "global_step": 367327, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0778346061706543, "global_step": 367328, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0867600440979004, "global_step": 367329, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.15802001953125, "global_step": 367330, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0543525218963623, "global_step": 367331, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1770784854888916, "global_step": 367332, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.111165761947632, "global_step": 367333, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.191465377807617, "global_step": 367334, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.048646926879883, "global_step": 367335, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2268948554992676, "global_step": 367336, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0773890018463135, "global_step": 367337, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1358675956726074, "global_step": 367338, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.036296844482422, "global_step": 367339, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.140730619430542, "global_step": 367340, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.13681960105896, "global_step": 367341, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.147158622741699, "global_step": 367342, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.121002197265625, "global_step": 367343, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0782859325408936, "global_step": 367344, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.209817886352539, "global_step": 367345, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1098568439483643, "global_step": 367346, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.048813819885254, "global_step": 367347, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1089937686920166, "global_step": 367348, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.104318141937256, "global_step": 367349, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.2854762077331543, "global_step": 367350, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.117037296295166, "global_step": 367351, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.090707778930664, "global_step": 367352, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1129090785980225, "global_step": 367353, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.188079357147217, "global_step": 367354, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.084472179412842, "global_step": 367355, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1571414470672607, "global_step": 367356, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1510231494903564, "global_step": 367357, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.129197835922241, "global_step": 367358, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0535404682159424, "global_step": 367359, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1510064601898193, "global_step": 367360, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1745340824127197, "global_step": 367361, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.106440305709839, "global_step": 367362, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1266086101531982, "global_step": 367363, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.152982473373413, "global_step": 367364, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.042424440383911, "global_step": 367365, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.094505548477173, "global_step": 367366, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.058176040649414, "global_step": 367367, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.104527711868286, "global_step": 367368, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0770866870880127, "global_step": 367369, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.047619581222534, "global_step": 367370, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.083268880844116, "global_step": 367371, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.061920404434204, "global_step": 367372, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.094463586807251, "global_step": 367373, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.061683177947998, "global_step": 367374, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1398470401763916, "global_step": 367375, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1657750606536865, "global_step": 367376, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.19873046875, "global_step": 367377, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.153125524520874, "global_step": 367378, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1319687366485596, "global_step": 367379, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.070496082305908, "global_step": 367380, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.092076301574707, "global_step": 367381, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.0606942176818848, "global_step": 367382, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1062307357788086, "global_step": 367383, "epoch": 728, "lr": 5e-05}
{"train_loss": 2.1255555152893066, "global_step": 367384, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.064751625061035, "global_step": 367385, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.055253505706787, "global_step": 367386, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0258519649505615, "global_step": 367387, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.117856979370117, "global_step": 367388, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.139375925064087, "global_step": 367389, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1144089698791504, "global_step": 367390, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.092264175415039, "global_step": 367391, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.144662380218506, "global_step": 367392, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.041248083114624, "global_step": 367393, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1985278129577637, "global_step": 367394, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.015371322631836, "global_step": 367395, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.04927659034729, "global_step": 367396, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0619869232177734, "global_step": 367397, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0408358573913574, "global_step": 367398, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.124950647354126, "global_step": 367399, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0910773277282715, "global_step": 367400, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0953869819641113, "global_step": 367401, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1156768798828125, "global_step": 367402, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.190610408782959, "global_step": 367403, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0982248783111572, "global_step": 367404, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0554144382476807, "global_step": 367405, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.088696241378784, "global_step": 367406, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1223857402801514, "global_step": 367407, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0010576248168945, "global_step": 367408, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1469061374664307, "global_step": 367409, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1090810298919678, "global_step": 367410, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1370508670806885, "global_step": 367411, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1290597915649414, "global_step": 367412, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.061445474624634, "global_step": 367413, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0486302375793457, "global_step": 367414, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0645062923431396, "global_step": 367415, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.160968542098999, "global_step": 367416, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0965471267700195, "global_step": 367417, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.103503465652466, "global_step": 367418, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0270490646362305, "global_step": 367419, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.123750925064087, "global_step": 367420, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0898447036743164, "global_step": 367421, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1251184940338135, "global_step": 367422, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.095564842224121, "global_step": 367423, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0543766021728516, "global_step": 367424, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1643404960632324, "global_step": 367425, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0948729515075684, "global_step": 367426, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.101891040802002, "global_step": 367427, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0626158714294434, "global_step": 367428, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.02160382270813, "global_step": 367429, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1182634830474854, "global_step": 367430, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.020815134048462, "global_step": 367431, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0359277725219727, "global_step": 367432, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1862428188323975, "global_step": 367433, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.098496198654175, "global_step": 367434, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0985100269317627, "global_step": 367435, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1163489818573, "global_step": 367436, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1201374530792236, "global_step": 367437, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.019674062728882, "global_step": 367438, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.122189521789551, "global_step": 367439, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.101797342300415, "global_step": 367440, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1016976833343506, "global_step": 367441, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1568007469177246, "global_step": 367442, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1317436695098877, "global_step": 367443, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.020540237426758, "global_step": 367444, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.173935651779175, "global_step": 367445, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1529386043548584, "global_step": 367446, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.100321054458618, "global_step": 367447, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.117234468460083, "global_step": 367448, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1186394691467285, "global_step": 367449, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.161505699157715, "global_step": 367450, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1969780921936035, "global_step": 367451, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0342023372650146, "global_step": 367452, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.145132064819336, "global_step": 367453, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.119560480117798, "global_step": 367454, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1400790214538574, "global_step": 367455, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1249332427978516, "global_step": 367456, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1884026527404785, "global_step": 367457, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.106713056564331, "global_step": 367458, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.167377471923828, "global_step": 367459, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0944697856903076, "global_step": 367460, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.122789144515991, "global_step": 367461, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.087829828262329, "global_step": 367462, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0899648666381836, "global_step": 367463, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1113762855529785, "global_step": 367464, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0849668979644775, "global_step": 367465, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0887720584869385, "global_step": 367466, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.11617374420166, "global_step": 367467, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1621289253234863, "global_step": 367468, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.019683361053467, "global_step": 367469, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0670387744903564, "global_step": 367470, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.072354793548584, "global_step": 367471, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1304733753204346, "global_step": 367472, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0978739261627197, "global_step": 367473, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0602786540985107, "global_step": 367474, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.046562910079956, "global_step": 367475, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1283421516418457, "global_step": 367476, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1094024181365967, "global_step": 367477, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.083692789077759, "global_step": 367478, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1049485206604004, "global_step": 367479, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0677287578582764, "global_step": 367480, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1327133178710938, "global_step": 367481, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0866782665252686, "global_step": 367482, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0938756465911865, "global_step": 367483, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1554720401763916, "global_step": 367484, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1739401817321777, "global_step": 367485, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.069615364074707, "global_step": 367486, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0943820476531982, "global_step": 367487, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0409932136535645, "global_step": 367488, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.093188524246216, "global_step": 367489, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0972089767456055, "global_step": 367490, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.154848098754883, "global_step": 367491, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0711286067962646, "global_step": 367492, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.157820701599121, "global_step": 367493, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1570231914520264, "global_step": 367494, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.992701768875122, "global_step": 367495, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.143000364303589, "global_step": 367496, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0949652194976807, "global_step": 367497, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.055454730987549, "global_step": 367498, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0402798652648926, "global_step": 367499, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.082885980606079, "global_step": 367500, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.127042770385742, "global_step": 367501, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1509344577789307, "global_step": 367502, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.149087905883789, "global_step": 367503, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.086960554122925, "global_step": 367504, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.119830846786499, "global_step": 367505, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0865604877471924, "global_step": 367506, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0619850158691406, "global_step": 367507, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0433151721954346, "global_step": 367508, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.154362440109253, "global_step": 367509, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0850419998168945, "global_step": 367510, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.017880439758301, "global_step": 367511, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.135568380355835, "global_step": 367512, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1879146099090576, "global_step": 367513, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0957834720611572, "global_step": 367514, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.089933156967163, "global_step": 367515, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.114778757095337, "global_step": 367516, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.134539842605591, "global_step": 367517, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.093949317932129, "global_step": 367518, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.034271717071533, "global_step": 367519, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1029887199401855, "global_step": 367520, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.116868019104004, "global_step": 367521, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.2022550106048584, "global_step": 367522, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.9623287916183472, "global_step": 367523, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1204545497894287, "global_step": 367524, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1455981731414795, "global_step": 367525, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1282708644866943, "global_step": 367526, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1155152320861816, "global_step": 367527, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1498188972473145, "global_step": 367528, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0942115783691406, "global_step": 367529, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0921270847320557, "global_step": 367530, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1054766178131104, "global_step": 367531, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1228864192962646, "global_step": 367532, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1432647705078125, "global_step": 367533, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0430748462677, "global_step": 367534, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1171975135803223, "global_step": 367535, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0553174018859863, "global_step": 367536, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.102442741394043, "global_step": 367537, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1866202354431152, "global_step": 367538, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.142515182495117, "global_step": 367539, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1441824436187744, "global_step": 367540, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.142157793045044, "global_step": 367541, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.176246404647827, "global_step": 367542, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.035283327102661, "global_step": 367543, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.138103485107422, "global_step": 367544, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1795589923858643, "global_step": 367545, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1051647663116455, "global_step": 367546, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1603281497955322, "global_step": 367547, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.148041009902954, "global_step": 367548, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.141559362411499, "global_step": 367549, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0304853916168213, "global_step": 367550, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.977251410484314, "global_step": 367551, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1885504722595215, "global_step": 367552, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0472965240478516, "global_step": 367553, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.042090892791748, "global_step": 367554, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.110166549682617, "global_step": 367555, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0867135524749756, "global_step": 367556, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0514392852783203, "global_step": 367557, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0793888568878174, "global_step": 367558, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0878114700317383, "global_step": 367559, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0926640033721924, "global_step": 367560, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1187639236450195, "global_step": 367561, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1268422603607178, "global_step": 367562, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0826404094696045, "global_step": 367563, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.072502613067627, "global_step": 367564, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0518453121185303, "global_step": 367565, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0980546474456787, "global_step": 367566, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.049075126647949, "global_step": 367567, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0883097648620605, "global_step": 367568, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.05241322517395, "global_step": 367569, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.126258373260498, "global_step": 367570, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1536190509796143, "global_step": 367571, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1787831783294678, "global_step": 367572, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0851101875305176, "global_step": 367573, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0153377056121826, "global_step": 367574, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1100754737854004, "global_step": 367575, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0501716136932373, "global_step": 367576, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.176959276199341, "global_step": 367577, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.178084135055542, "global_step": 367578, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1264688968658447, "global_step": 367579, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.12550950050354, "global_step": 367580, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0257785320281982, "global_step": 367581, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1176280975341797, "global_step": 367582, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.074059247970581, "global_step": 367583, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.106781005859375, "global_step": 367584, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1964199542999268, "global_step": 367585, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.154965400695801, "global_step": 367586, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1550309658050537, "global_step": 367587, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.138366222381592, "global_step": 367588, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.045759916305542, "global_step": 367589, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0993356704711914, "global_step": 367590, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0090725421905518, "global_step": 367591, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0771193504333496, "global_step": 367592, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0964231491088867, "global_step": 367593, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.095104455947876, "global_step": 367594, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0354397296905518, "global_step": 367595, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0769805908203125, "global_step": 367596, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1478471755981445, "global_step": 367597, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1049256324768066, "global_step": 367598, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.113912343978882, "global_step": 367599, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1120283603668213, "global_step": 367600, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0997707843780518, "global_step": 367601, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1739320755004883, "global_step": 367602, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0667150020599365, "global_step": 367603, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.157538890838623, "global_step": 367604, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.062472105026245, "global_step": 367605, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0360641479492188, "global_step": 367606, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0873401165008545, "global_step": 367607, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.081730604171753, "global_step": 367608, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1863765716552734, "global_step": 367609, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1389379501342773, "global_step": 367610, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.095085859298706, "global_step": 367611, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.092957019805908, "global_step": 367612, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.16725754737854, "global_step": 367613, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1355433464050293, "global_step": 367614, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0216407775878906, "global_step": 367615, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.113783836364746, "global_step": 367616, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1035025119781494, "global_step": 367617, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.110778570175171, "global_step": 367618, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.161999225616455, "global_step": 367619, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.061521530151367, "global_step": 367620, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0665249824523926, "global_step": 367621, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0547611713409424, "global_step": 367622, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1083145141601562, "global_step": 367623, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1530685424804688, "global_step": 367624, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0765504837036133, "global_step": 367625, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1207876205444336, "global_step": 367626, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0557589530944824, "global_step": 367627, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0817716121673584, "global_step": 367628, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0782947540283203, "global_step": 367629, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.042980909347534, "global_step": 367630, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1869494915008545, "global_step": 367631, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1428496837615967, "global_step": 367632, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0093727111816406, "global_step": 367633, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.127098560333252, "global_step": 367634, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.075230598449707, "global_step": 367635, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1185717582702637, "global_step": 367636, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.033998966217041, "global_step": 367637, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1755404472351074, "global_step": 367638, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.153761863708496, "global_step": 367639, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.089660882949829, "global_step": 367640, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1180403232574463, "global_step": 367641, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.123807191848755, "global_step": 367642, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.142746686935425, "global_step": 367643, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0640995502471924, "global_step": 367644, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0603034496307373, "global_step": 367645, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0430150032043457, "global_step": 367646, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0744454860687256, "global_step": 367647, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.14288067817688, "global_step": 367648, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0317249298095703, "global_step": 367649, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.024221658706665, "global_step": 367650, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1407902240753174, "global_step": 367651, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.048283576965332, "global_step": 367652, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1674721240997314, "global_step": 367653, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1672401428222656, "global_step": 367654, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.113717555999756, "global_step": 367655, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0280840396881104, "global_step": 367656, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1492087841033936, "global_step": 367657, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0729010105133057, "global_step": 367658, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0870797634124756, "global_step": 367659, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.078491449356079, "global_step": 367660, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.2468864917755127, "global_step": 367661, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.079129695892334, "global_step": 367662, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.179452896118164, "global_step": 367663, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.161705255508423, "global_step": 367664, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.112342119216919, "global_step": 367665, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.088596820831299, "global_step": 367666, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0940606594085693, "global_step": 367667, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.110206127166748, "global_step": 367668, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.096766233444214, "global_step": 367669, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.103443145751953, "global_step": 367670, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1497159004211426, "global_step": 367671, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.110106945037842, "global_step": 367672, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.082702159881592, "global_step": 367673, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1531240940093994, "global_step": 367674, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.089428424835205, "global_step": 367675, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1971540451049805, "global_step": 367676, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0017595291137695, "global_step": 367677, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.073638439178467, "global_step": 367678, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.022219657897949, "global_step": 367679, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.135611057281494, "global_step": 367680, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1343271732330322, "global_step": 367681, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.177903652191162, "global_step": 367682, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1274325847625732, "global_step": 367683, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.2073330879211426, "global_step": 367684, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0737874507904053, "global_step": 367685, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.9992852210998535, "global_step": 367686, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1585168838500977, "global_step": 367687, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.131418228149414, "global_step": 367688, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1524641513824463, "global_step": 367689, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.140117645263672, "global_step": 367690, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0687289237976074, "global_step": 367691, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1669628620147705, "global_step": 367692, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.026836395263672, "global_step": 367693, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.139986038208008, "global_step": 367694, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0594592094421387, "global_step": 367695, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1315300464630127, "global_step": 367696, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1727116107940674, "global_step": 367697, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1198184490203857, "global_step": 367698, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1036570072174072, "global_step": 367699, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.059738874435425, "global_step": 367700, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.042299270629883, "global_step": 367701, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.201850652694702, "global_step": 367702, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0852980613708496, "global_step": 367703, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.057030200958252, "global_step": 367704, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.07761812210083, "global_step": 367705, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1055986881256104, "global_step": 367706, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0747756958007812, "global_step": 367707, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.072699546813965, "global_step": 367708, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0297369956970215, "global_step": 367709, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.027815818786621, "global_step": 367710, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0796613693237305, "global_step": 367711, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.049246072769165, "global_step": 367712, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.098444700241089, "global_step": 367713, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.075185775756836, "global_step": 367714, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.077779531478882, "global_step": 367715, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1303627490997314, "global_step": 367716, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1249916553497314, "global_step": 367717, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.096679210662842, "global_step": 367718, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1338469982147217, "global_step": 367719, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1439433097839355, "global_step": 367720, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1817028522491455, "global_step": 367721, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.128558874130249, "global_step": 367722, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0969903469085693, "global_step": 367723, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.080446243286133, "global_step": 367724, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1895368099212646, "global_step": 367725, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.032597541809082, "global_step": 367726, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.190549373626709, "global_step": 367727, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0747809410095215, "global_step": 367728, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.084683895111084, "global_step": 367729, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1481881141662598, "global_step": 367730, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0303518772125244, "global_step": 367731, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.140169620513916, "global_step": 367732, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1028268337249756, "global_step": 367733, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0787153244018555, "global_step": 367734, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.2123734951019287, "global_step": 367735, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.135486602783203, "global_step": 367736, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.013683319091797, "global_step": 367737, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0945913791656494, "global_step": 367738, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1081461906433105, "global_step": 367739, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.9797176122665405, "global_step": 367740, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0379538536071777, "global_step": 367741, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.088552713394165, "global_step": 367742, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1142075061798096, "global_step": 367743, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.055866241455078, "global_step": 367744, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1243646144866943, "global_step": 367745, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0739898681640625, "global_step": 367746, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0989701747894287, "global_step": 367747, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0620546340942383, "global_step": 367748, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1243643760681152, "global_step": 367749, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.105513334274292, "global_step": 367750, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0973517894744873, "global_step": 367751, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1323351860046387, "global_step": 367752, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1862337589263916, "global_step": 367753, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0702812671661377, "global_step": 367754, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0320730209350586, "global_step": 367755, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.135674238204956, "global_step": 367756, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.9546138048171997, "global_step": 367757, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0775787830352783, "global_step": 367758, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0979886054992676, "global_step": 367759, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0701348781585693, "global_step": 367760, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0574729442596436, "global_step": 367761, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.139302968978882, "global_step": 367762, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0182063579559326, "global_step": 367763, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.123436212539673, "global_step": 367764, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.042360782623291, "global_step": 367765, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0702507495880127, "global_step": 367766, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.065323829650879, "global_step": 367767, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.272927761077881, "global_step": 367768, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.068056106567383, "global_step": 367769, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0916223526000977, "global_step": 367770, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0713539123535156, "global_step": 367771, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0422446727752686, "global_step": 367772, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.06549072265625, "global_step": 367773, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.095548152923584, "global_step": 367774, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.117615222930908, "global_step": 367775, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0692639350891113, "global_step": 367776, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0558993816375732, "global_step": 367777, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1076011657714844, "global_step": 367778, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.093745708465576, "global_step": 367779, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.2004945278167725, "global_step": 367780, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1108334064483643, "global_step": 367781, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1663427352905273, "global_step": 367782, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1291792392730713, "global_step": 367783, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1211814880371094, "global_step": 367784, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0706565380096436, "global_step": 367785, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1989879608154297, "global_step": 367786, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.02707839012146, "global_step": 367787, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1590545177459717, "global_step": 367788, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1235265731811523, "global_step": 367789, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.139256477355957, "global_step": 367790, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.157888650894165, "global_step": 367791, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.084193468093872, "global_step": 367792, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1636788845062256, "global_step": 367793, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.027651786804199, "global_step": 367794, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1066906452178955, "global_step": 367795, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.066227436065674, "global_step": 367796, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1648178100585938, "global_step": 367797, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1371710300445557, "global_step": 367798, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0831873416900635, "global_step": 367799, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0672874450683594, "global_step": 367800, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.161186695098877, "global_step": 367801, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1380295753479004, "global_step": 367802, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1818180084228516, "global_step": 367803, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.073782444000244, "global_step": 367804, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1144192218780518, "global_step": 367805, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.123056650161743, "global_step": 367806, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.185868263244629, "global_step": 367807, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.9985812902450562, "global_step": 367808, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.9995832443237305, "global_step": 367809, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.065925121307373, "global_step": 367810, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0926718711853027, "global_step": 367811, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.032758951187134, "global_step": 367812, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.178489923477173, "global_step": 367813, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.071863889694214, "global_step": 367814, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.09891676902771, "global_step": 367815, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.07961106300354, "global_step": 367816, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0679116249084473, "global_step": 367817, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1026759147644043, "global_step": 367818, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.157996654510498, "global_step": 367819, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.076815366744995, "global_step": 367820, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.054990291595459, "global_step": 367821, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0185446739196777, "global_step": 367822, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1013457775115967, "global_step": 367823, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0642027854919434, "global_step": 367824, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1174216270446777, "global_step": 367825, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.025076150894165, "global_step": 367826, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0971665382385254, "global_step": 367827, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1992595195770264, "global_step": 367828, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0539181232452393, "global_step": 367829, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0973427295684814, "global_step": 367830, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1789462566375732, "global_step": 367831, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.058000326156616, "global_step": 367832, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1088509559631348, "global_step": 367833, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0635719299316406, "global_step": 367834, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1347053050994873, "global_step": 367835, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1332340240478516, "global_step": 367836, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0683112144470215, "global_step": 367837, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.196591377258301, "global_step": 367838, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1499290466308594, "global_step": 367839, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1049249172210693, "global_step": 367840, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.119727611541748, "global_step": 367841, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1053478717803955, "global_step": 367842, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0858688354492188, "global_step": 367843, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0964772701263428, "global_step": 367844, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1555075645446777, "global_step": 367845, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0379743576049805, "global_step": 367846, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.088228940963745, "global_step": 367847, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0907387733459473, "global_step": 367848, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1340341567993164, "global_step": 367849, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.039754867553711, "global_step": 367850, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.031858444213867, "global_step": 367851, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1010959148406982, "global_step": 367852, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.158277988433838, "global_step": 367853, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1280486583709717, "global_step": 367854, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1430137157440186, "global_step": 367855, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.058889389038086, "global_step": 367856, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.154787540435791, "global_step": 367857, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.161163806915283, "global_step": 367858, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.141620635986328, "global_step": 367859, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0802674293518066, "global_step": 367860, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1184380054473877, "global_step": 367861, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0871903896331787, "global_step": 367862, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.163522481918335, "global_step": 367863, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0402073860168457, "global_step": 367864, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.042698621749878, "global_step": 367865, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1068665981292725, "global_step": 367866, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.006782054901123, "global_step": 367867, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1132869720458984, "global_step": 367868, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.236870527267456, "global_step": 367869, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.19425106048584, "global_step": 367870, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.085777521133423, "global_step": 367871, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0722784996032715, "global_step": 367872, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.099742889404297, "global_step": 367873, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0602705478668213, "global_step": 367874, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.094895601272583, "global_step": 367875, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1975953578948975, "global_step": 367876, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1044681072235107, "global_step": 367877, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.04824161529541, "global_step": 367878, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.09502911567688, "global_step": 367879, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1331961154937744, "global_step": 367880, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1082193851470947, "global_step": 367881, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.086228847503662, "global_step": 367882, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.157480478286743, "global_step": 367883, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.139995574951172, "global_step": 367884, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1324119567871094, "global_step": 367885, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0990781784057617, "global_step": 367886, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1309609413146973, "global_step": 367887, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0830931663513184, "global_step": 367888, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.070749521255493, "global_step": 367889, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0744264125823975, "global_step": 367890, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1388673782348633, "global_step": 367891, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0919718742370605, "global_step": 367892, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0267996788024902, "global_step": 367893, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.182678461074829, "global_step": 367894, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.9884674549102783, "global_step": 367895, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1877028942108154, "global_step": 367896, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.2017147541046143, "global_step": 367897, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1193227767944336, "global_step": 367898, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.147326946258545, "global_step": 367899, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.100301742553711, "global_step": 367900, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.066918134689331, "global_step": 367901, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1184933185577393, "global_step": 367902, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1556458473205566, "global_step": 367903, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1256771087646484, "global_step": 367904, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.12271785736084, "global_step": 367905, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.128129005432129, "global_step": 367906, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.156386375427246, "global_step": 367907, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1820366382598877, "global_step": 367908, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1546008586883545, "global_step": 367909, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.133512258529663, "global_step": 367910, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0898690223693848, "global_step": 367911, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.077275276184082, "global_step": 367912, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.119208812713623, "global_step": 367913, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.07196307182312, "global_step": 367914, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0954113006591797, "global_step": 367915, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.178283929824829, "global_step": 367916, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1980109214782715, "global_step": 367917, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1830270290374756, "global_step": 367918, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.083864212036133, "global_step": 367919, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.175307273864746, "global_step": 367920, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0390868186950684, "global_step": 367921, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1288058757781982, "global_step": 367922, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1269266605377197, "global_step": 367923, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1346967220306396, "global_step": 367924, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0822269916534424, "global_step": 367925, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0708513259887695, "global_step": 367926, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.120734214782715, "global_step": 367927, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1520938873291016, "global_step": 367928, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.078855514526367, "global_step": 367929, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1568081378936768, "global_step": 367930, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1283090114593506, "global_step": 367931, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0861592292785645, "global_step": 367932, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0964903831481934, "global_step": 367933, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0978870391845703, "global_step": 367934, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1299781799316406, "global_step": 367935, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.163038969039917, "global_step": 367936, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1027746200561523, "global_step": 367937, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.9351272583007812, "global_step": 367938, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1734700202941895, "global_step": 367939, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.144089937210083, "global_step": 367940, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.107733726501465, "global_step": 367941, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0405161380767822, "global_step": 367942, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0646142959594727, "global_step": 367943, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1056151390075684, "global_step": 367944, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.04014253616333, "global_step": 367945, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0795094966888428, "global_step": 367946, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0487923622131348, "global_step": 367947, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.9970171451568604, "global_step": 367948, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0701048374176025, "global_step": 367949, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1093943119049072, "global_step": 367950, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1302618980407715, "global_step": 367951, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.140528917312622, "global_step": 367952, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0770277976989746, "global_step": 367953, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1552329063415527, "global_step": 367954, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1203362941741943, "global_step": 367955, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.101886749267578, "global_step": 367956, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1859145164489746, "global_step": 367957, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.091061592102051, "global_step": 367958, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0736241340637207, "global_step": 367959, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1315417289733887, "global_step": 367960, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.135627031326294, "global_step": 367961, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0640170574188232, "global_step": 367962, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0004100799560547, "global_step": 367963, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.106445789337158, "global_step": 367964, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1247787475585938, "global_step": 367965, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1643519401550293, "global_step": 367966, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0925378799438477, "global_step": 367967, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.131716251373291, "global_step": 367968, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1158549785614014, "global_step": 367969, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1089251041412354, "global_step": 367970, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0868771076202393, "global_step": 367971, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.088437080383301, "global_step": 367972, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1178767681121826, "global_step": 367973, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0476059913635254, "global_step": 367974, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1382827758789062, "global_step": 367975, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.9730043411254883, "global_step": 367976, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1342954635620117, "global_step": 367977, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.021167755126953, "global_step": 367978, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.112273931503296, "global_step": 367979, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.101151943206787, "global_step": 367980, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.179286241531372, "global_step": 367981, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.9984668493270874, "global_step": 367982, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0863466262817383, "global_step": 367983, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1073474884033203, "global_step": 367984, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1685240268707275, "global_step": 367985, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.079974889755249, "global_step": 367986, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.153273582458496, "global_step": 367987, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0188679695129395, "global_step": 367988, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.122377395629883, "global_step": 367989, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0702145099639893, "global_step": 367990, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.057502508163452, "global_step": 367991, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0632050037384033, "global_step": 367992, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.072744131088257, "global_step": 367993, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1341629028320312, "global_step": 367994, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.142570734024048, "global_step": 367995, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1410350799560547, "global_step": 367996, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0620532035827637, "global_step": 367997, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1392300128936768, "global_step": 367998, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0693576335906982, "global_step": 367999, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1773154735565186, "global_step": 368000, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.106232166290283, "global_step": 368001, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0957114696502686, "global_step": 368002, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.9942830801010132, "global_step": 368003, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1697731018066406, "global_step": 368004, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.110753297805786, "global_step": 368005, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1107211112976074, "global_step": 368006, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.112061023712158, "global_step": 368007, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.131809711456299, "global_step": 368008, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.11785626411438, "global_step": 368009, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1411561965942383, "global_step": 368010, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.106227159500122, "global_step": 368011, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1352217197418213, "global_step": 368012, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.157257080078125, "global_step": 368013, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1782946586608887, "global_step": 368014, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.120668411254883, "global_step": 368015, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1480071544647217, "global_step": 368016, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1093826293945312, "global_step": 368017, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.032996654510498, "global_step": 368018, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.168377161026001, "global_step": 368019, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.131199836730957, "global_step": 368020, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1284019947052, "global_step": 368021, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.111799955368042, "global_step": 368022, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.06162428855896, "global_step": 368023, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.118817090988159, "global_step": 368024, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1468379497528076, "global_step": 368025, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1131534576416016, "global_step": 368026, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0392117500305176, "global_step": 368027, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1736385822296143, "global_step": 368028, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1267588138580322, "global_step": 368029, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.076127529144287, "global_step": 368030, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.050936222076416, "global_step": 368031, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0673818588256836, "global_step": 368032, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.114598512649536, "global_step": 368033, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1734981536865234, "global_step": 368034, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0639429092407227, "global_step": 368035, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1932778358459473, "global_step": 368036, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.135063648223877, "global_step": 368037, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.172060012817383, "global_step": 368038, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.129733085632324, "global_step": 368039, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0677177906036377, "global_step": 368040, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1271445751190186, "global_step": 368041, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.147777795791626, "global_step": 368042, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.089794397354126, "global_step": 368043, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.163895606994629, "global_step": 368044, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.04778790473938, "global_step": 368045, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.109104633331299, "global_step": 368046, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1474294662475586, "global_step": 368047, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.148212432861328, "global_step": 368048, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1204376220703125, "global_step": 368049, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.145813465118408, "global_step": 368050, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1904609203338623, "global_step": 368051, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.118945598602295, "global_step": 368052, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0824825763702393, "global_step": 368053, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0955967903137207, "global_step": 368054, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0809712409973145, "global_step": 368055, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1088216304779053, "global_step": 368056, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0077803134918213, "global_step": 368057, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.153111696243286, "global_step": 368058, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1275172233581543, "global_step": 368059, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.08892560005188, "global_step": 368060, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.017139434814453, "global_step": 368061, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.2011966705322266, "global_step": 368062, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.118739604949951, "global_step": 368063, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.152618885040283, "global_step": 368064, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1652140617370605, "global_step": 368065, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.123688220977783, "global_step": 368066, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.136460781097412, "global_step": 368067, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.995549201965332, "global_step": 368068, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0955235958099365, "global_step": 368069, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.052377223968506, "global_step": 368070, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1110105514526367, "global_step": 368071, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0359575748443604, "global_step": 368072, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.081047773361206, "global_step": 368073, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.043684244155884, "global_step": 368074, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.199559450149536, "global_step": 368075, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.2047317028045654, "global_step": 368076, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.2286646366119385, "global_step": 368077, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1662724018096924, "global_step": 368078, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1295247077941895, "global_step": 368079, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1253416538238525, "global_step": 368080, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.264003038406372, "global_step": 368081, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0774660110473633, "global_step": 368082, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1213698387145996, "global_step": 368083, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.160846710205078, "global_step": 368084, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.059722423553467, "global_step": 368085, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.140228748321533, "global_step": 368086, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.150540351867676, "global_step": 368087, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.035374402999878, "global_step": 368088, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.065185070037842, "global_step": 368089, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.112515926361084, "global_step": 368090, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0733304023742676, "global_step": 368091, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1568453311920166, "global_step": 368092, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.9856867790222168, "global_step": 368093, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0570127964019775, "global_step": 368094, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.088736057281494, "global_step": 368095, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.122368097305298, "global_step": 368096, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.173462152481079, "global_step": 368097, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.106280565261841, "global_step": 368098, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1787264347076416, "global_step": 368099, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1120095252990723, "global_step": 368100, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.163363218307495, "global_step": 368101, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.081178665161133, "global_step": 368102, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.170443058013916, "global_step": 368103, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.203275203704834, "global_step": 368104, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.166423797607422, "global_step": 368105, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1168370246887207, "global_step": 368106, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.106213092803955, "global_step": 368107, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.9951717853546143, "global_step": 368108, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1520493030548096, "global_step": 368109, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1225244998931885, "global_step": 368110, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1278960704803467, "global_step": 368111, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0867462158203125, "global_step": 368112, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.066060781478882, "global_step": 368113, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.996543288230896, "global_step": 368114, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0709352493286133, "global_step": 368115, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.074413299560547, "global_step": 368116, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.068659782409668, "global_step": 368117, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.038013458251953, "global_step": 368118, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.111417293548584, "global_step": 368119, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1110379695892334, "global_step": 368120, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.114945650100708, "global_step": 368121, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.158027172088623, "global_step": 368122, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0776524543762207, "global_step": 368123, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.970922827720642, "global_step": 368124, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.148996114730835, "global_step": 368125, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0809950828552246, "global_step": 368126, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0849907398223877, "global_step": 368127, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.124884843826294, "global_step": 368128, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.087559700012207, "global_step": 368129, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0912210941314697, "global_step": 368130, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.065959930419922, "global_step": 368131, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0455191135406494, "global_step": 368132, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.994149088859558, "global_step": 368133, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0768823623657227, "global_step": 368134, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.101057767868042, "global_step": 368135, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0752339363098145, "global_step": 368136, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.024813413619995, "global_step": 368137, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1305527687072754, "global_step": 368138, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0623812675476074, "global_step": 368139, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.149498462677002, "global_step": 368140, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.130643606185913, "global_step": 368141, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1407032012939453, "global_step": 368142, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.141010046005249, "global_step": 368143, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1486165523529053, "global_step": 368144, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.120347261428833, "global_step": 368145, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.107947826385498, "global_step": 368146, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1635522842407227, "global_step": 368147, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0980896949768066, "global_step": 368148, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1846797466278076, "global_step": 368149, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1005191802978516, "global_step": 368150, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.061265468597412, "global_step": 368151, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1043357849121094, "global_step": 368152, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1518666744232178, "global_step": 368153, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.16924786567688, "global_step": 368154, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1139700412750244, "global_step": 368155, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.06351375579834, "global_step": 368156, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1992266178131104, "global_step": 368157, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0814201831817627, "global_step": 368158, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.07010817527771, "global_step": 368159, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0383801460266113, "global_step": 368160, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.145332098007202, "global_step": 368161, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.121026039123535, "global_step": 368162, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1487059593200684, "global_step": 368163, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1526038646698, "global_step": 368164, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.187899589538574, "global_step": 368165, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.067026376724243, "global_step": 368166, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0586178302764893, "global_step": 368167, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1516053676605225, "global_step": 368168, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.123713254928589, "global_step": 368169, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0259134769439697, "global_step": 368170, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1242215633392334, "global_step": 368171, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1311817169189453, "global_step": 368172, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1918272972106934, "global_step": 368173, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.03913950920105, "global_step": 368174, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.042785882949829, "global_step": 368175, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1888554096221924, "global_step": 368176, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.051682233810425, "global_step": 368177, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.056898593902588, "global_step": 368178, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1234281063079834, "global_step": 368179, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0563178062438965, "global_step": 368180, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1978394985198975, "global_step": 368181, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.142063617706299, "global_step": 368182, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.183116912841797, "global_step": 368183, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.104625940322876, "global_step": 368184, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0772545337677, "global_step": 368185, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.102724075317383, "global_step": 368186, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1347014904022217, "global_step": 368187, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.135457992553711, "global_step": 368188, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1084749698638916, "global_step": 368189, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1077775955200195, "global_step": 368190, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.118720054626465, "global_step": 368191, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0645370483398438, "global_step": 368192, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1186108589172363, "global_step": 368193, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0793936252593994, "global_step": 368194, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.121607780456543, "global_step": 368195, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0537033081054688, "global_step": 368196, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1349129676818848, "global_step": 368197, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.021664619445801, "global_step": 368198, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0954644680023193, "global_step": 368199, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.01816725730896, "global_step": 368200, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.219510793685913, "global_step": 368201, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0997276306152344, "global_step": 368202, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.123375654220581, "global_step": 368203, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1122212409973145, "global_step": 368204, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.022368907928467, "global_step": 368205, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.095860242843628, "global_step": 368206, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0862765312194824, "global_step": 368207, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0911223888397217, "global_step": 368208, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.130178213119507, "global_step": 368209, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.106109619140625, "global_step": 368210, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.075712203979492, "global_step": 368211, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.206218957901001, "global_step": 368212, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0771355628967285, "global_step": 368213, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0617260932922363, "global_step": 368214, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1171693801879883, "global_step": 368215, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.118096351623535, "global_step": 368216, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1496262550354004, "global_step": 368217, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0768370628356934, "global_step": 368218, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1037607192993164, "global_step": 368219, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.061187744140625, "global_step": 368220, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0595192909240723, "global_step": 368221, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1433892250061035, "global_step": 368222, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.100146770477295, "global_step": 368223, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.097658395767212, "global_step": 368224, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.174727201461792, "global_step": 368225, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.101822853088379, "global_step": 368226, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0397655963897705, "global_step": 368227, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1539058685302734, "global_step": 368228, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0974738597869873, "global_step": 368229, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.183234453201294, "global_step": 368230, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1088030338287354, "global_step": 368231, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.055178165435791, "global_step": 368232, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1346139907836914, "global_step": 368233, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1087636947631836, "global_step": 368234, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.166110038757324, "global_step": 368235, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.115192174911499, "global_step": 368236, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1834964752197266, "global_step": 368237, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1254074573516846, "global_step": 368238, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0859525203704834, "global_step": 368239, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.098947286605835, "global_step": 368240, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.030195713043213, "global_step": 368241, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.186464548110962, "global_step": 368242, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0690431594848633, "global_step": 368243, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.2025537490844727, "global_step": 368244, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0788514614105225, "global_step": 368245, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.170854091644287, "global_step": 368246, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.095553398132324, "global_step": 368247, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.2176191806793213, "global_step": 368248, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.091606378555298, "global_step": 368249, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0815322399139404, "global_step": 368250, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0801749229431152, "global_step": 368251, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0242207050323486, "global_step": 368252, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1825714111328125, "global_step": 368253, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0625388622283936, "global_step": 368254, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.184959888458252, "global_step": 368255, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0511600971221924, "global_step": 368256, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1821446418762207, "global_step": 368257, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.06486439704895, "global_step": 368258, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0984671115875244, "global_step": 368259, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0937728881835938, "global_step": 368260, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1086151599884033, "global_step": 368261, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0460422039031982, "global_step": 368262, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1705434322357178, "global_step": 368263, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.12147855758667, "global_step": 368264, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1002721786499023, "global_step": 368265, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.204655647277832, "global_step": 368266, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.202440023422241, "global_step": 368267, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0783181190490723, "global_step": 368268, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1234028339385986, "global_step": 368269, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1590893268585205, "global_step": 368270, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.153581142425537, "global_step": 368271, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.072955846786499, "global_step": 368272, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.094170570373535, "global_step": 368273, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.086841344833374, "global_step": 368274, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1113202571868896, "global_step": 368275, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.143028736114502, "global_step": 368276, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.166795492172241, "global_step": 368277, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.096616744995117, "global_step": 368278, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1184096336364746, "global_step": 368279, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0871522426605225, "global_step": 368280, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.05765438079834, "global_step": 368281, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1242599487304688, "global_step": 368282, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1082756519317627, "global_step": 368283, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.110902786254883, "global_step": 368284, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1931674480438232, "global_step": 368285, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0885980129241943, "global_step": 368286, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.10547137260437, "global_step": 368287, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.072389602661133, "global_step": 368288, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.034266710281372, "global_step": 368289, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0644030570983887, "global_step": 368290, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.159268856048584, "global_step": 368291, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1165969371795654, "global_step": 368292, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0797226428985596, "global_step": 368293, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0363218784332275, "global_step": 368294, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1881537437438965, "global_step": 368295, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0590858459472656, "global_step": 368296, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.154662609100342, "global_step": 368297, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.072220802307129, "global_step": 368298, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.098137855529785, "global_step": 368299, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.131150722503662, "global_step": 368300, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.120121479034424, "global_step": 368301, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.133117198944092, "global_step": 368302, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.094782829284668, "global_step": 368303, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.085916757583618, "global_step": 368304, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.198648452758789, "global_step": 368305, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0810749530792236, "global_step": 368306, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0278127193450928, "global_step": 368307, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.13722562789917, "global_step": 368308, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1061248779296875, "global_step": 368309, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1451528072357178, "global_step": 368310, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1517491340637207, "global_step": 368311, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.092928886413574, "global_step": 368312, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.069960594177246, "global_step": 368313, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1303417682647705, "global_step": 368314, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1041600704193115, "global_step": 368315, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0859477519989014, "global_step": 368316, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.150824546813965, "global_step": 368317, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.112997531890869, "global_step": 368318, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0830302238464355, "global_step": 368319, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1142373085021973, "global_step": 368320, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.054046630859375, "global_step": 368321, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.004035472869873, "global_step": 368322, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.152132034301758, "global_step": 368323, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1016499996185303, "global_step": 368324, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.049980401992798, "global_step": 368325, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.073537588119507, "global_step": 368326, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.067471981048584, "global_step": 368327, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.091165065765381, "global_step": 368328, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1017532348632812, "global_step": 368329, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.149860382080078, "global_step": 368330, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1161935329437256, "global_step": 368331, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.025190830230713, "global_step": 368332, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.073439598083496, "global_step": 368333, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0798652172088623, "global_step": 368334, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1020727157592773, "global_step": 368335, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.172830820083618, "global_step": 368336, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.087148666381836, "global_step": 368337, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.219757080078125, "global_step": 368338, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1019701957702637, "global_step": 368339, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0627551078796387, "global_step": 368340, "epoch": 729, "lr": 5e-05}
{"train_loss": 1.976773977279663, "global_step": 368341, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0451529026031494, "global_step": 368342, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1487369537353516, "global_step": 368343, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.110475778579712, "global_step": 368344, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.18426251411438, "global_step": 368345, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.104320526123047, "global_step": 368346, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.152259111404419, "global_step": 368347, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1354823112487793, "global_step": 368348, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.0091097354888916, "global_step": 368349, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.133754253387451, "global_step": 368350, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.154653549194336, "global_step": 368351, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.1054742336273193, "global_step": 368352, "epoch": 729, "lr": 5e-05}
{"train_loss": 2.056553840637207, "global_step": 368353, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0602917671203613, "global_step": 368354, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.102642774581909, "global_step": 368355, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2190911769866943, "global_step": 368356, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0645523071289062, "global_step": 368357, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.093902111053467, "global_step": 368358, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.004748821258545, "global_step": 368359, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.145814895629883, "global_step": 368360, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0606191158294678, "global_step": 368361, "epoch": 730, "lr": 5e-05}
{"train_loss": 1.9819109439849854, "global_step": 368362, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2511539459228516, "global_step": 368363, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0022521018981934, "global_step": 368364, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0217537879943848, "global_step": 368365, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.005070686340332, "global_step": 368366, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0784101486206055, "global_step": 368367, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.118116617202759, "global_step": 368368, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0606579780578613, "global_step": 368369, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0959060192108154, "global_step": 368370, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1101150512695312, "global_step": 368371, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0432512760162354, "global_step": 368372, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.082035541534424, "global_step": 368373, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1595571041107178, "global_step": 368374, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1428487300872803, "global_step": 368375, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0989151000976562, "global_step": 368376, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.169787883758545, "global_step": 368377, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0685625076293945, "global_step": 368378, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.077467441558838, "global_step": 368379, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.139920711517334, "global_step": 368380, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1836016178131104, "global_step": 368381, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0399816036224365, "global_step": 368382, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0978662967681885, "global_step": 368383, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1774942874908447, "global_step": 368384, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.048853874206543, "global_step": 368385, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0691800117492676, "global_step": 368386, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.098597288131714, "global_step": 368387, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1166434288024902, "global_step": 368388, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.071300983428955, "global_step": 368389, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0683560371398926, "global_step": 368390, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.103975296020508, "global_step": 368391, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.096086025238037, "global_step": 368392, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.027785062789917, "global_step": 368393, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.085512638092041, "global_step": 368394, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0817811489105225, "global_step": 368395, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0647130012512207, "global_step": 368396, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.093055009841919, "global_step": 368397, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.079587936401367, "global_step": 368398, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.213982343673706, "global_step": 368399, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.065272808074951, "global_step": 368400, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.135448455810547, "global_step": 368401, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.096081018447876, "global_step": 368402, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.142022132873535, "global_step": 368403, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0788276195526123, "global_step": 368404, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0719923973083496, "global_step": 368405, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2187414169311523, "global_step": 368406, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.081949472427368, "global_step": 368407, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1194190979003906, "global_step": 368408, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.060673236846924, "global_step": 368409, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1368441581726074, "global_step": 368410, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1618895530700684, "global_step": 368411, "epoch": 730, "lr": 5e-05}
{"train_loss": 1.9771384000778198, "global_step": 368412, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0373620986938477, "global_step": 368413, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1631882190704346, "global_step": 368414, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0230326652526855, "global_step": 368415, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0598576068878174, "global_step": 368416, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.107086181640625, "global_step": 368417, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.090486526489258, "global_step": 368418, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1307191848754883, "global_step": 368419, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.065635919570923, "global_step": 368420, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0678465366363525, "global_step": 368421, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.064678430557251, "global_step": 368422, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.072911024093628, "global_step": 368423, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0214338302612305, "global_step": 368424, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0496397018432617, "global_step": 368425, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.068573236465454, "global_step": 368426, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0040664672851562, "global_step": 368427, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0866119861602783, "global_step": 368428, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1089158058166504, "global_step": 368429, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1588923931121826, "global_step": 368430, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1039345264434814, "global_step": 368431, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1125166416168213, "global_step": 368432, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1415486335754395, "global_step": 368433, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.093501567840576, "global_step": 368434, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.139476776123047, "global_step": 368435, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.122917413711548, "global_step": 368436, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.169478178024292, "global_step": 368437, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.029712677001953, "global_step": 368438, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.166623592376709, "global_step": 368439, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.143454074859619, "global_step": 368440, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.137326717376709, "global_step": 368441, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1540164947509766, "global_step": 368442, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.098588705062866, "global_step": 368443, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.07173752784729, "global_step": 368444, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0626778602600098, "global_step": 368445, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.051600694656372, "global_step": 368446, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0958828926086426, "global_step": 368447, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.093907117843628, "global_step": 368448, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1113240718841553, "global_step": 368449, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1574466228485107, "global_step": 368450, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0531578063964844, "global_step": 368451, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.066973924636841, "global_step": 368452, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1021347045898438, "global_step": 368453, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.101013660430908, "global_step": 368454, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0962443351745605, "global_step": 368455, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0304014682769775, "global_step": 368456, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1167938709259033, "global_step": 368457, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.061460018157959, "global_step": 368458, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.116460084915161, "global_step": 368459, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1064577102661133, "global_step": 368460, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0925486087799072, "global_step": 368461, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1013400554656982, "global_step": 368462, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1634764671325684, "global_step": 368463, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1229231357574463, "global_step": 368464, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.161963701248169, "global_step": 368465, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1288187503814697, "global_step": 368466, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1620795726776123, "global_step": 368467, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.086824655532837, "global_step": 368468, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0737359523773193, "global_step": 368469, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.075340747833252, "global_step": 368470, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.188868999481201, "global_step": 368471, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0055747032165527, "global_step": 368472, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1453025341033936, "global_step": 368473, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.093907117843628, "global_step": 368474, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.109661340713501, "global_step": 368475, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0769944190979004, "global_step": 368476, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1825716495513916, "global_step": 368477, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.106508255004883, "global_step": 368478, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.094313383102417, "global_step": 368479, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1343843936920166, "global_step": 368480, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1017420291900635, "global_step": 368481, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0669374465942383, "global_step": 368482, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.059507369995117, "global_step": 368483, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.172192335128784, "global_step": 368484, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.075580596923828, "global_step": 368485, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.186142683029175, "global_step": 368486, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0866336822509766, "global_step": 368487, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1312522888183594, "global_step": 368488, "epoch": 730, "lr": 5e-05}
{"train_loss": 1.9640611410140991, "global_step": 368489, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1593618392944336, "global_step": 368490, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1223204135894775, "global_step": 368491, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1664934158325195, "global_step": 368492, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.084929943084717, "global_step": 368493, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1395106315612793, "global_step": 368494, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1495909690856934, "global_step": 368495, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0964231491088867, "global_step": 368496, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.119746208190918, "global_step": 368497, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.051706314086914, "global_step": 368498, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1138319969177246, "global_step": 368499, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.149204969406128, "global_step": 368500, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1748454570770264, "global_step": 368501, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1403942108154297, "global_step": 368502, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1689870357513428, "global_step": 368503, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.128211736679077, "global_step": 368504, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.139202833175659, "global_step": 368505, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.110018730163574, "global_step": 368506, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.146653175354004, "global_step": 368507, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.067141532897949, "global_step": 368508, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.084853410720825, "global_step": 368509, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.169712543487549, "global_step": 368510, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0227291584014893, "global_step": 368511, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2097628116607666, "global_step": 368512, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0850837230682373, "global_step": 368513, "epoch": 730, "lr": 5e-05}
{"train_loss": 1.940004587173462, "global_step": 368514, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1018123626708984, "global_step": 368515, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0830636024475098, "global_step": 368516, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1375234127044678, "global_step": 368517, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0559194087982178, "global_step": 368518, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1053531169891357, "global_step": 368519, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.109455108642578, "global_step": 368520, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1425867080688477, "global_step": 368521, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1158270835876465, "global_step": 368522, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.042104721069336, "global_step": 368523, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1434667110443115, "global_step": 368524, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.088606357574463, "global_step": 368525, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.037135362625122, "global_step": 368526, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.083554983139038, "global_step": 368527, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1580238342285156, "global_step": 368528, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1638100147247314, "global_step": 368529, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.121471643447876, "global_step": 368530, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.067586660385132, "global_step": 368531, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1598763465881348, "global_step": 368532, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.123725414276123, "global_step": 368533, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.112653970718384, "global_step": 368534, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.036569833755493, "global_step": 368535, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.051204204559326, "global_step": 368536, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.169929265975952, "global_step": 368537, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.155439615249634, "global_step": 368538, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1763947010040283, "global_step": 368539, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1255524158477783, "global_step": 368540, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.130948305130005, "global_step": 368541, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1867494583129883, "global_step": 368542, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.08379864692688, "global_step": 368543, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.199422836303711, "global_step": 368544, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1702351570129395, "global_step": 368545, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0595693588256836, "global_step": 368546, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0785574913024902, "global_step": 368547, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.134824752807617, "global_step": 368548, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0401721000671387, "global_step": 368549, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.090926170349121, "global_step": 368550, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.124018430709839, "global_step": 368551, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.06223201751709, "global_step": 368552, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1921193599700928, "global_step": 368553, "epoch": 730, "lr": 5e-05}
{"train_loss": 1.996336817741394, "global_step": 368554, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.051467180252075, "global_step": 368555, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0536742210388184, "global_step": 368556, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.062220335006714, "global_step": 368557, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.134284019470215, "global_step": 368558, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0479350090026855, "global_step": 368559, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1352992057800293, "global_step": 368560, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.14156174659729, "global_step": 368561, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.051715612411499, "global_step": 368562, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1153335571289062, "global_step": 368563, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.12613844871521, "global_step": 368564, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.026569366455078, "global_step": 368565, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0955374240875244, "global_step": 368566, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.07515287399292, "global_step": 368567, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.136622667312622, "global_step": 368568, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.110668182373047, "global_step": 368569, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0567009449005127, "global_step": 368570, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0675315856933594, "global_step": 368571, "epoch": 730, "lr": 5e-05}
{"train_loss": 1.9985077381134033, "global_step": 368572, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0292201042175293, "global_step": 368573, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.11350154876709, "global_step": 368574, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0603761672973633, "global_step": 368575, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.085970640182495, "global_step": 368576, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.126847267150879, "global_step": 368577, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0620014667510986, "global_step": 368578, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1589295864105225, "global_step": 368579, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.171466588973999, "global_step": 368580, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.13645339012146, "global_step": 368581, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.146121025085449, "global_step": 368582, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1912357807159424, "global_step": 368583, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.102456569671631, "global_step": 368584, "epoch": 730, "lr": 5e-05}
{"train_loss": 1.997241735458374, "global_step": 368585, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1402876377105713, "global_step": 368586, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.097102642059326, "global_step": 368587, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2559287548065186, "global_step": 368588, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1519808769226074, "global_step": 368589, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.019944667816162, "global_step": 368590, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.01204252243042, "global_step": 368591, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0079433917999268, "global_step": 368592, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0812137126922607, "global_step": 368593, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1197094917297363, "global_step": 368594, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0639960765838623, "global_step": 368595, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.102480411529541, "global_step": 368596, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.01188063621521, "global_step": 368597, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0616095066070557, "global_step": 368598, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.096466302871704, "global_step": 368599, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1095163822174072, "global_step": 368600, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.146315574645996, "global_step": 368601, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0810139179229736, "global_step": 368602, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1622345447540283, "global_step": 368603, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0960066318511963, "global_step": 368604, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0436410903930664, "global_step": 368605, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.123131513595581, "global_step": 368606, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1024603843688965, "global_step": 368607, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0208590030670166, "global_step": 368608, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0884671211242676, "global_step": 368609, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1006643772125244, "global_step": 368610, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.119314193725586, "global_step": 368611, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1174583435058594, "global_step": 368612, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1404356956481934, "global_step": 368613, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0443813800811768, "global_step": 368614, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1519837379455566, "global_step": 368615, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.005859613418579, "global_step": 368616, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1649067401885986, "global_step": 368617, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.150407075881958, "global_step": 368618, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.054489850997925, "global_step": 368619, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1384401321411133, "global_step": 368620, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0501210689544678, "global_step": 368621, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1434860229492188, "global_step": 368622, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.059178590774536, "global_step": 368623, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0470688343048096, "global_step": 368624, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0864484310150146, "global_step": 368625, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.063608407974243, "global_step": 368626, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1136116981506348, "global_step": 368627, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0326247215270996, "global_step": 368628, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.061753511428833, "global_step": 368629, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1686370372772217, "global_step": 368630, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.136676073074341, "global_step": 368631, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.240438938140869, "global_step": 368632, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.078355312347412, "global_step": 368633, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0558767318725586, "global_step": 368634, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1149957180023193, "global_step": 368635, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1371395587921143, "global_step": 368636, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.185899257659912, "global_step": 368637, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.001307964324951, "global_step": 368638, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.028202533721924, "global_step": 368639, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1443545818328857, "global_step": 368640, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.068493604660034, "global_step": 368641, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.170793056488037, "global_step": 368642, "epoch": 730, "lr": 5e-05}
{"train_loss": 1.9581047296524048, "global_step": 368643, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.212104082107544, "global_step": 368644, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.122502088546753, "global_step": 368645, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0987071990966797, "global_step": 368646, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1456432342529297, "global_step": 368647, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.136105537414551, "global_step": 368648, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1697864532470703, "global_step": 368649, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.111618757247925, "global_step": 368650, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.150615930557251, "global_step": 368651, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1115822792053223, "global_step": 368652, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0798981189727783, "global_step": 368653, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0960171222686768, "global_step": 368654, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1371912956237793, "global_step": 368655, "epoch": 730, "lr": 5e-05}
{"train_loss": 1.988461971282959, "global_step": 368656, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.028459310531616, "global_step": 368657, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1288864612579346, "global_step": 368658, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.051919937133789, "global_step": 368659, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.064044237136841, "global_step": 368660, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.024639129638672, "global_step": 368661, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1461939811706543, "global_step": 368662, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0815224647521973, "global_step": 368663, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.132211208343506, "global_step": 368664, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0647873878479004, "global_step": 368665, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.107369899749756, "global_step": 368666, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.087617874145508, "global_step": 368667, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0916757583618164, "global_step": 368668, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.139955520629883, "global_step": 368669, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.054734706878662, "global_step": 368670, "epoch": 730, "lr": 5e-05}
{"train_loss": 1.9797887802124023, "global_step": 368671, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.044186592102051, "global_step": 368672, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.118809461593628, "global_step": 368673, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1557750701904297, "global_step": 368674, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.080746650695801, "global_step": 368675, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1233503818511963, "global_step": 368676, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.083665370941162, "global_step": 368677, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0516724586486816, "global_step": 368678, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.100818634033203, "global_step": 368679, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0227317810058594, "global_step": 368680, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.18123722076416, "global_step": 368681, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1125574111938477, "global_step": 368682, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1602165699005127, "global_step": 368683, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0771732330322266, "global_step": 368684, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0684871673583984, "global_step": 368685, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0623254776000977, "global_step": 368686, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.092898368835449, "global_step": 368687, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0777854919433594, "global_step": 368688, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.02959942817688, "global_step": 368689, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.127056121826172, "global_step": 368690, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.085752487182617, "global_step": 368691, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.141477584838867, "global_step": 368692, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.09836483001709, "global_step": 368693, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2118279933929443, "global_step": 368694, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.074446201324463, "global_step": 368695, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.134826183319092, "global_step": 368696, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.090883731842041, "global_step": 368697, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.088035821914673, "global_step": 368698, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.145141363143921, "global_step": 368699, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1451566219329834, "global_step": 368700, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0379467010498047, "global_step": 368701, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.112149477005005, "global_step": 368702, "epoch": 730, "lr": 5e-05}
{"train_loss": 1.9660265445709229, "global_step": 368703, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1593708992004395, "global_step": 368704, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0663859844207764, "global_step": 368705, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.095208168029785, "global_step": 368706, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0759758949279785, "global_step": 368707, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.086420774459839, "global_step": 368708, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.003767728805542, "global_step": 368709, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0993404388427734, "global_step": 368710, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2228853702545166, "global_step": 368711, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.071110725402832, "global_step": 368712, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.17639422416687, "global_step": 368713, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.125236988067627, "global_step": 368714, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.061918020248413, "global_step": 368715, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.097707509994507, "global_step": 368716, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.096003293991089, "global_step": 368717, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1693153381347656, "global_step": 368718, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.072152614593506, "global_step": 368719, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1510000228881836, "global_step": 368720, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1357200145721436, "global_step": 368721, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1034133434295654, "global_step": 368722, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1279308795928955, "global_step": 368723, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0667033195495605, "global_step": 368724, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0148892402648926, "global_step": 368725, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0960936546325684, "global_step": 368726, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.172858476638794, "global_step": 368727, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.138516426086426, "global_step": 368728, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.112386703491211, "global_step": 368729, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.102071762084961, "global_step": 368730, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1187970638275146, "global_step": 368731, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.181126356124878, "global_step": 368732, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.09800386428833, "global_step": 368733, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.096527099609375, "global_step": 368734, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.120642900466919, "global_step": 368735, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.061690092086792, "global_step": 368736, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1034646034240723, "global_step": 368737, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.112370252609253, "global_step": 368738, "epoch": 730, "lr": 5e-05}
{"train_loss": 1.9797509908676147, "global_step": 368739, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.024513006210327, "global_step": 368740, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.118966817855835, "global_step": 368741, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2432055473327637, "global_step": 368742, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.082986831665039, "global_step": 368743, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2219858169555664, "global_step": 368744, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1120524406433105, "global_step": 368745, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0778698921203613, "global_step": 368746, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0396666526794434, "global_step": 368747, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0727427005767822, "global_step": 368748, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.098796844482422, "global_step": 368749, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0473556518554688, "global_step": 368750, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.093123197555542, "global_step": 368751, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1225833892822266, "global_step": 368752, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.086524724960327, "global_step": 368753, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2516815662384033, "global_step": 368754, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.072114944458008, "global_step": 368755, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2049062252044678, "global_step": 368756, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1632137298583984, "global_step": 368757, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.067063093185425, "global_step": 368758, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0676515102386475, "global_step": 368759, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.043376922607422, "global_step": 368760, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0991876125335693, "global_step": 368761, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.118790626525879, "global_step": 368762, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1466832160949707, "global_step": 368763, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.125270366668701, "global_step": 368764, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1559531688690186, "global_step": 368765, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.084951877593994, "global_step": 368766, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0381429195404053, "global_step": 368767, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.160344123840332, "global_step": 368768, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0334668159484863, "global_step": 368769, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0025665760040283, "global_step": 368770, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.199714422225952, "global_step": 368771, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0471746921539307, "global_step": 368772, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1110775470733643, "global_step": 368773, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.167799472808838, "global_step": 368774, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0668153762817383, "global_step": 368775, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.081239938735962, "global_step": 368776, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1393356323242188, "global_step": 368777, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.13301157951355, "global_step": 368778, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0769758224487305, "global_step": 368779, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0961132049560547, "global_step": 368780, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.047025203704834, "global_step": 368781, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.101067304611206, "global_step": 368782, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.057854413986206, "global_step": 368783, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1780307292938232, "global_step": 368784, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.132582187652588, "global_step": 368785, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1530117988586426, "global_step": 368786, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.086681842803955, "global_step": 368787, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.095759630203247, "global_step": 368788, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1168899536132812, "global_step": 368789, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.141944646835327, "global_step": 368790, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.149329662322998, "global_step": 368791, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1211395263671875, "global_step": 368792, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0106184482574463, "global_step": 368793, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.113065004348755, "global_step": 368794, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.033243417739868, "global_step": 368795, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0715620517730713, "global_step": 368796, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.189424514770508, "global_step": 368797, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.022705078125, "global_step": 368798, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.192020893096924, "global_step": 368799, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0857834815979004, "global_step": 368800, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.057708501815796, "global_step": 368801, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.078542470932007, "global_step": 368802, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0310492515563965, "global_step": 368803, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.041574478149414, "global_step": 368804, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.135385274887085, "global_step": 368805, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1465277671813965, "global_step": 368806, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0714306831359863, "global_step": 368807, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.075284242630005, "global_step": 368808, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.067563533782959, "global_step": 368809, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0454981327056885, "global_step": 368810, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.10304594039917, "global_step": 368811, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.013054132461548, "global_step": 368812, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0711259841918945, "global_step": 368813, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1209609508514404, "global_step": 368814, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1619017124176025, "global_step": 368815, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0889804363250732, "global_step": 368816, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1011717319488525, "global_step": 368817, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.161717176437378, "global_step": 368818, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.16782808303833, "global_step": 368819, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.174252510070801, "global_step": 368820, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1434075832366943, "global_step": 368821, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1093251705169678, "global_step": 368822, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1513946056365967, "global_step": 368823, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.107412338256836, "global_step": 368824, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.130004405975342, "global_step": 368825, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.099581718444824, "global_step": 368826, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.071538209915161, "global_step": 368827, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.11141037940979, "global_step": 368828, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1965887546539307, "global_step": 368829, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.094917058944702, "global_step": 368830, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.059502124786377, "global_step": 368831, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.047729015350342, "global_step": 368832, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.155332326889038, "global_step": 368833, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0988309383392334, "global_step": 368834, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0652658939361572, "global_step": 368835, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1839704513549805, "global_step": 368836, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.153700113296509, "global_step": 368837, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.066979169845581, "global_step": 368838, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1472272872924805, "global_step": 368839, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0595858097076416, "global_step": 368840, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0904083251953125, "global_step": 368841, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1659700870513916, "global_step": 368842, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1251657009124756, "global_step": 368843, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.141026496887207, "global_step": 368844, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0899224281311035, "global_step": 368845, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1415517330169678, "global_step": 368846, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.056530714035034, "global_step": 368847, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1927080154418945, "global_step": 368848, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0219972133636475, "global_step": 368849, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0511116981506348, "global_step": 368850, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.09991455078125, "global_step": 368851, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2235989570617676, "global_step": 368852, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1093878746032715, "global_step": 368853, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1008808612823486, "global_step": 368854, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1413800716400146, "global_step": 368855, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.109870433807373, "global_step": 368856, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.042980909347534, "global_step": 368857, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1587798595428467, "global_step": 368858, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0887374877929688, "global_step": 368859, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1536858081817627, "global_step": 368860, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.067831516265869, "global_step": 368861, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.091527223587036, "global_step": 368862, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0467119216918945, "global_step": 368863, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1093389987945557, "global_step": 368864, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.084526538848877, "global_step": 368865, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.17867112159729, "global_step": 368866, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0050787925720215, "global_step": 368867, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.077537775039673, "global_step": 368868, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1075174808502197, "global_step": 368869, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1190662384033203, "global_step": 368870, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.142374277114868, "global_step": 368871, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.133800745010376, "global_step": 368872, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1052536964416504, "global_step": 368873, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1219961643218994, "global_step": 368874, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1305460929870605, "global_step": 368875, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0579257011413574, "global_step": 368876, "epoch": 730, "lr": 5e-05}
{"train_loss": 1.9967849254608154, "global_step": 368877, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1579694747924805, "global_step": 368878, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0558269023895264, "global_step": 368879, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1900343894958496, "global_step": 368880, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.051110029220581, "global_step": 368881, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.104842185974121, "global_step": 368882, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.051476240158081, "global_step": 368883, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.092099666595459, "global_step": 368884, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1298344135284424, "global_step": 368885, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0919179916381836, "global_step": 368886, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0907773971557617, "global_step": 368887, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0793886184692383, "global_step": 368888, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1263933181762695, "global_step": 368889, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.09303879737854, "global_step": 368890, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0932931900024414, "global_step": 368891, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0866687297821045, "global_step": 368892, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1534109115600586, "global_step": 368893, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0770645141601562, "global_step": 368894, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0634937286376953, "global_step": 368895, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.061347484588623, "global_step": 368896, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.089102029800415, "global_step": 368897, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.208883047103882, "global_step": 368898, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.126567840576172, "global_step": 368899, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1529927253723145, "global_step": 368900, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1442744731903076, "global_step": 368901, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.082545042037964, "global_step": 368902, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1460909843444824, "global_step": 368903, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0416769981384277, "global_step": 368904, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1132187843322754, "global_step": 368905, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1057939529418945, "global_step": 368906, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.130542755126953, "global_step": 368907, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.124767780303955, "global_step": 368908, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1282553672790527, "global_step": 368909, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.095409870147705, "global_step": 368910, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.098228931427002, "global_step": 368911, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.161731719970703, "global_step": 368912, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.198514699935913, "global_step": 368913, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1053965091705322, "global_step": 368914, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.126276731491089, "global_step": 368915, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1168742179870605, "global_step": 368916, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0450122356414795, "global_step": 368917, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1476640701293945, "global_step": 368918, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1138103008270264, "global_step": 368919, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.141411066055298, "global_step": 368920, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1541519165039062, "global_step": 368921, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1740362644195557, "global_step": 368922, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0313172340393066, "global_step": 368923, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1157076358795166, "global_step": 368924, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.032005786895752, "global_step": 368925, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1301279067993164, "global_step": 368926, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1708669662475586, "global_step": 368927, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1162121295928955, "global_step": 368928, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1439661979675293, "global_step": 368929, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1365838050842285, "global_step": 368930, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.153777599334717, "global_step": 368931, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1553537845611572, "global_step": 368932, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.09088397026062, "global_step": 368933, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0516648292541504, "global_step": 368934, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1301798820495605, "global_step": 368935, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.158794641494751, "global_step": 368936, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.177060604095459, "global_step": 368937, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.069366693496704, "global_step": 368938, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1218695640563965, "global_step": 368939, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1398677825927734, "global_step": 368940, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.065310478210449, "global_step": 368941, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.114173650741577, "global_step": 368942, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0667572021484375, "global_step": 368943, "epoch": 730, "lr": 5e-05}
{"train_loss": 1.9416078329086304, "global_step": 368944, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0045032501220703, "global_step": 368945, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.067939519882202, "global_step": 368946, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0547070503234863, "global_step": 368947, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.169940948486328, "global_step": 368948, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0780744552612305, "global_step": 368949, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.18585205078125, "global_step": 368950, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1017143726348877, "global_step": 368951, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.078625440597534, "global_step": 368952, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.122755527496338, "global_step": 368953, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1191155910491943, "global_step": 368954, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1121444702148438, "global_step": 368955, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.239305257797241, "global_step": 368956, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.071639060974121, "global_step": 368957, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0428147315979004, "global_step": 368958, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0863914489746094, "global_step": 368959, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1134650707244873, "global_step": 368960, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1176865100860596, "global_step": 368961, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.137953758239746, "global_step": 368962, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0491673946380615, "global_step": 368963, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0902011394500732, "global_step": 368964, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.011037588119507, "global_step": 368965, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0437240600585938, "global_step": 368966, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.159320592880249, "global_step": 368967, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.141254425048828, "global_step": 368968, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1051394939422607, "global_step": 368969, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0681803226470947, "global_step": 368970, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0829830169677734, "global_step": 368971, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.068405866622925, "global_step": 368972, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0888755321502686, "global_step": 368973, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.140082359313965, "global_step": 368974, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.121849536895752, "global_step": 368975, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.101367712020874, "global_step": 368976, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.198425054550171, "global_step": 368977, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0976781845092773, "global_step": 368978, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.084319829940796, "global_step": 368979, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1122543811798096, "global_step": 368980, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1704201698303223, "global_step": 368981, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0935070514678955, "global_step": 368982, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.101430654525757, "global_step": 368983, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.140580892562866, "global_step": 368984, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.136796712875366, "global_step": 368985, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1777215003967285, "global_step": 368986, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0245978832244873, "global_step": 368987, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.068084239959717, "global_step": 368988, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1018383502960205, "global_step": 368989, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.100003719329834, "global_step": 368990, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1520752906799316, "global_step": 368991, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1706924438476562, "global_step": 368992, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1723251342773438, "global_step": 368993, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1017649173736572, "global_step": 368994, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.162712335586548, "global_step": 368995, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0754575729370117, "global_step": 368996, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.120957851409912, "global_step": 368997, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0870108604431152, "global_step": 368998, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.108431816101074, "global_step": 368999, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1133785247802734, "global_step": 369000, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1401724815368652, "global_step": 369001, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.14190411567688, "global_step": 369002, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.135176181793213, "global_step": 369003, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.129667043685913, "global_step": 369004, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1212244033813477, "global_step": 369005, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0960378646850586, "global_step": 369006, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.174509048461914, "global_step": 369007, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.21779727935791, "global_step": 369008, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.070469856262207, "global_step": 369009, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0258288383483887, "global_step": 369010, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0933191776275635, "global_step": 369011, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.127279281616211, "global_step": 369012, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.094590425491333, "global_step": 369013, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.135558605194092, "global_step": 369014, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0324840545654297, "global_step": 369015, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0618886947631836, "global_step": 369016, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.116415023803711, "global_step": 369017, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1946280002593994, "global_step": 369018, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.113715887069702, "global_step": 369019, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0846617221832275, "global_step": 369020, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0653188228607178, "global_step": 369021, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.143597364425659, "global_step": 369022, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0948331356048584, "global_step": 369023, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.111660957336426, "global_step": 369024, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1427600383758545, "global_step": 369025, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0683395862579346, "global_step": 369026, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.091526508331299, "global_step": 369027, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.28701114654541, "global_step": 369028, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1826460361480713, "global_step": 369029, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1321117877960205, "global_step": 369030, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1198625564575195, "global_step": 369031, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0844171047210693, "global_step": 369032, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.183664321899414, "global_step": 369033, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.135754346847534, "global_step": 369034, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.076808214187622, "global_step": 369035, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.120743751525879, "global_step": 369036, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.177917718887329, "global_step": 369037, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.100891351699829, "global_step": 369038, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1771240234375, "global_step": 369039, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.063312530517578, "global_step": 369040, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1253035068511963, "global_step": 369041, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.17079758644104, "global_step": 369042, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2487475872039795, "global_step": 369043, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.160261392593384, "global_step": 369044, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0350894927978516, "global_step": 369045, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.167565107345581, "global_step": 369046, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.085756301879883, "global_step": 369047, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.12630295753479, "global_step": 369048, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1382949352264404, "global_step": 369049, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.163619041442871, "global_step": 369050, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1235294342041016, "global_step": 369051, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0722343921661377, "global_step": 369052, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.143381118774414, "global_step": 369053, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.063891887664795, "global_step": 369054, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.091215133666992, "global_step": 369055, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.092869520187378, "global_step": 369056, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.12524676322937, "global_step": 369057, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.112179756164551, "global_step": 369058, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0923945903778076, "global_step": 369059, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.012178897857666, "global_step": 369060, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1923680305480957, "global_step": 369061, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1209728717803955, "global_step": 369062, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1856634616851807, "global_step": 369063, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1139042377471924, "global_step": 369064, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1380186080932617, "global_step": 369065, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0368733406066895, "global_step": 369066, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.080057144165039, "global_step": 369067, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2001307010650635, "global_step": 369068, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2032504081726074, "global_step": 369069, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1761741638183594, "global_step": 369070, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2038071155548096, "global_step": 369071, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0855677127838135, "global_step": 369072, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1249241828918457, "global_step": 369073, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0899553298950195, "global_step": 369074, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.150052785873413, "global_step": 369075, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2424235343933105, "global_step": 369076, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.144742727279663, "global_step": 369077, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.126741647720337, "global_step": 369078, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.028567314147949, "global_step": 369079, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1282527446746826, "global_step": 369080, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1242105960845947, "global_step": 369081, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.077280044555664, "global_step": 369082, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.096410036087036, "global_step": 369083, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1257596015930176, "global_step": 369084, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.092392683029175, "global_step": 369085, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0189571380615234, "global_step": 369086, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1455917358398438, "global_step": 369087, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0364835262298584, "global_step": 369088, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2030043601989746, "global_step": 369089, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.060375690460205, "global_step": 369090, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0961568355560303, "global_step": 369091, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.079303503036499, "global_step": 369092, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0975217819213867, "global_step": 369093, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1142802238464355, "global_step": 369094, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0956103801727295, "global_step": 369095, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0800769329071045, "global_step": 369096, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.163133144378662, "global_step": 369097, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.157111167907715, "global_step": 369098, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1264774799346924, "global_step": 369099, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1757609844207764, "global_step": 369100, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.054136276245117, "global_step": 369101, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.07010817527771, "global_step": 369102, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.073528289794922, "global_step": 369103, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1142101287841797, "global_step": 369104, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1776998043060303, "global_step": 369105, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.075537919998169, "global_step": 369106, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1068854331970215, "global_step": 369107, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1260714530944824, "global_step": 369108, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.022979974746704, "global_step": 369109, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.20570707321167, "global_step": 369110, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.135850667953491, "global_step": 369111, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.062805652618408, "global_step": 369112, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1141340732574463, "global_step": 369113, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.146566390991211, "global_step": 369114, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0491864681243896, "global_step": 369115, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1223011016845703, "global_step": 369116, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.113593339920044, "global_step": 369117, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.177513599395752, "global_step": 369118, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2168147563934326, "global_step": 369119, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.154995918273926, "global_step": 369120, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.045975923538208, "global_step": 369121, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0858726501464844, "global_step": 369122, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1432299613952637, "global_step": 369123, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.162317991256714, "global_step": 369124, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1062936782836914, "global_step": 369125, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1060149669647217, "global_step": 369126, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0715625286102295, "global_step": 369127, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0218515396118164, "global_step": 369128, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.261223316192627, "global_step": 369129, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1613430976867676, "global_step": 369130, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1311168670654297, "global_step": 369131, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.019461154937744, "global_step": 369132, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.010077953338623, "global_step": 369133, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.164034843444824, "global_step": 369134, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1290225982666016, "global_step": 369135, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.095813274383545, "global_step": 369136, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1427407264709473, "global_step": 369137, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.058469295501709, "global_step": 369138, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.209867000579834, "global_step": 369139, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1389825344085693, "global_step": 369140, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.036639451980591, "global_step": 369141, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1062393188476562, "global_step": 369142, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.115013599395752, "global_step": 369143, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0705082416534424, "global_step": 369144, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1011645793914795, "global_step": 369145, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.050813913345337, "global_step": 369146, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1202070713043213, "global_step": 369147, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.047084093093872, "global_step": 369148, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0327553749084473, "global_step": 369149, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.117398500442505, "global_step": 369150, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1866519451141357, "global_step": 369151, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.050065517425537, "global_step": 369152, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0370595455169678, "global_step": 369153, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.103381633758545, "global_step": 369154, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.163144111633301, "global_step": 369155, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.125027656555176, "global_step": 369156, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.117831230163574, "global_step": 369157, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.093400001525879, "global_step": 369158, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1237001419067383, "global_step": 369159, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0871453285217285, "global_step": 369160, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.165355682373047, "global_step": 369161, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.144649028778076, "global_step": 369162, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1226649284362793, "global_step": 369163, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.063950777053833, "global_step": 369164, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.061760663986206, "global_step": 369165, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1254611015319824, "global_step": 369166, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1056246757507324, "global_step": 369167, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.045179605484009, "global_step": 369168, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0885369777679443, "global_step": 369169, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.21470308303833, "global_step": 369170, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.088561773300171, "global_step": 369171, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1364400386810303, "global_step": 369172, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0561347007751465, "global_step": 369173, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.057706117630005, "global_step": 369174, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.097933530807495, "global_step": 369175, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.149425983428955, "global_step": 369176, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1978464126586914, "global_step": 369177, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1241283416748047, "global_step": 369178, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.121283769607544, "global_step": 369179, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0814642906188965, "global_step": 369180, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.095026731491089, "global_step": 369181, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1260268688201904, "global_step": 369182, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0653328895568848, "global_step": 369183, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1811630725860596, "global_step": 369184, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0633621215820312, "global_step": 369185, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0837111473083496, "global_step": 369186, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0538456439971924, "global_step": 369187, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1108803749084473, "global_step": 369188, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1330466270446777, "global_step": 369189, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.130342960357666, "global_step": 369190, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0548179149627686, "global_step": 369191, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.157092571258545, "global_step": 369192, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.153390645980835, "global_step": 369193, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.081577777862549, "global_step": 369194, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1358022689819336, "global_step": 369195, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.074080467224121, "global_step": 369196, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0862655639648438, "global_step": 369197, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1185061931610107, "global_step": 369198, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.134765148162842, "global_step": 369199, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.178286075592041, "global_step": 369200, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1517179012298584, "global_step": 369201, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1249687671661377, "global_step": 369202, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0653624534606934, "global_step": 369203, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.105731725692749, "global_step": 369204, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.155677080154419, "global_step": 369205, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1116087436676025, "global_step": 369206, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.097313642501831, "global_step": 369207, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1790177822113037, "global_step": 369208, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.207111358642578, "global_step": 369209, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.113878011703491, "global_step": 369210, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1695327758789062, "global_step": 369211, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.120140790939331, "global_step": 369212, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1334996223449707, "global_step": 369213, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0504543781280518, "global_step": 369214, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1106996536254883, "global_step": 369215, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.143145799636841, "global_step": 369216, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0114598274230957, "global_step": 369217, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.237034559249878, "global_step": 369218, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0473883152008057, "global_step": 369219, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.159916400909424, "global_step": 369220, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.06655216217041, "global_step": 369221, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.162240505218506, "global_step": 369222, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.119939088821411, "global_step": 369223, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1106815338134766, "global_step": 369224, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1554789543151855, "global_step": 369225, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0902507305145264, "global_step": 369226, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.145937919616699, "global_step": 369227, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1230924129486084, "global_step": 369228, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0987908840179443, "global_step": 369229, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.058781147003174, "global_step": 369230, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0490777492523193, "global_step": 369231, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.092453956604004, "global_step": 369232, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1441729068756104, "global_step": 369233, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.115213632583618, "global_step": 369234, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0295755863189697, "global_step": 369235, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0296313762664795, "global_step": 369236, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1665287017822266, "global_step": 369237, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.135347843170166, "global_step": 369238, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1209139823913574, "global_step": 369239, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0922205448150635, "global_step": 369240, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1964547634124756, "global_step": 369241, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.123652219772339, "global_step": 369242, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.100125312805176, "global_step": 369243, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0942881107330322, "global_step": 369244, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.040524482727051, "global_step": 369245, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0975124835968018, "global_step": 369246, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.136791229248047, "global_step": 369247, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.085775375366211, "global_step": 369248, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0786142349243164, "global_step": 369249, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1981940269470215, "global_step": 369250, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1486246585845947, "global_step": 369251, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.09464168548584, "global_step": 369252, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1018717288970947, "global_step": 369253, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.167496681213379, "global_step": 369254, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0990312099456787, "global_step": 369255, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2064404487609863, "global_step": 369256, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1104443073272705, "global_step": 369257, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1615068912506104, "global_step": 369258, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1686503887176514, "global_step": 369259, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.11126971244812, "global_step": 369260, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1503288745880127, "global_step": 369261, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1053519248962402, "global_step": 369262, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0946223735809326, "global_step": 369263, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.136183500289917, "global_step": 369264, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1825129985809326, "global_step": 369265, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2117156982421875, "global_step": 369266, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1674304008483887, "global_step": 369267, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1562371253967285, "global_step": 369268, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.071239948272705, "global_step": 369269, "epoch": 730, "lr": 5e-05}
{"train_loss": 1.9984763860702515, "global_step": 369270, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1121315956115723, "global_step": 369271, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0706140995025635, "global_step": 369272, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1521682739257812, "global_step": 369273, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.046917200088501, "global_step": 369274, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.141782522201538, "global_step": 369275, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.134092092514038, "global_step": 369276, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2416725158691406, "global_step": 369277, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0859460830688477, "global_step": 369278, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0506818294525146, "global_step": 369279, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.061500072479248, "global_step": 369280, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.104402542114258, "global_step": 369281, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.117114782333374, "global_step": 369282, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.158832311630249, "global_step": 369283, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1360514163970947, "global_step": 369284, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1199111938476562, "global_step": 369285, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1526927947998047, "global_step": 369286, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1025705337524414, "global_step": 369287, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.2018563747406006, "global_step": 369288, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1782267093658447, "global_step": 369289, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1083059310913086, "global_step": 369290, "epoch": 730, "lr": 5e-05}
{"train_loss": 1.9762136936187744, "global_step": 369291, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.06832218170166, "global_step": 369292, "epoch": 730, "lr": 5e-05}
{"train_loss": 1.919776439666748, "global_step": 369293, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1511805057525635, "global_step": 369294, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0567402839660645, "global_step": 369295, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1004600524902344, "global_step": 369296, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.134615898132324, "global_step": 369297, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1285219192504883, "global_step": 369298, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.135434627532959, "global_step": 369299, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.108548879623413, "global_step": 369300, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1012589931488037, "global_step": 369301, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.134974956512451, "global_step": 369302, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.146742582321167, "global_step": 369303, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.110783338546753, "global_step": 369304, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.12925124168396, "global_step": 369305, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.095306873321533, "global_step": 369306, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1690621376037598, "global_step": 369307, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.06006121635437, "global_step": 369308, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1079587936401367, "global_step": 369309, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0807788372039795, "global_step": 369310, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0990898609161377, "global_step": 369311, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1295759677886963, "global_step": 369312, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0970444679260254, "global_step": 369313, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.089402437210083, "global_step": 369314, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.1457974910736084, "global_step": 369315, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0403735637664795, "global_step": 369316, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.0671002864837646, "global_step": 369317, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.184091329574585, "global_step": 369318, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.127499580383301, "global_step": 369319, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.115201234817505, "global_step": 369320, "epoch": 730, "lr": 5e-05}
{"train_loss": 2.107168674468994, "global_step": 369321, "epoch": 730, "lr": 5e-05, "val_loss": 5.634252548217773, "test_reconst_mse": 0.07252591848373413}
{"train_loss": 2.1963629722595215, "global_step": 369322, "epoch": 731, "lr": 5e-05}
{"train_loss": 1.996148705482483, "global_step": 369323, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.036146640777588, "global_step": 369324, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.108804702758789, "global_step": 369325, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1447513103485107, "global_step": 369326, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0764992237091064, "global_step": 369327, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0802042484283447, "global_step": 369328, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1168689727783203, "global_step": 369329, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0431509017944336, "global_step": 369330, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.095473051071167, "global_step": 369331, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.136644124984741, "global_step": 369332, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0166027545928955, "global_step": 369333, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1558680534362793, "global_step": 369334, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.081052303314209, "global_step": 369335, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0627071857452393, "global_step": 369336, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.126193046569824, "global_step": 369337, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0907347202301025, "global_step": 369338, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0737252235412598, "global_step": 369339, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.071384906768799, "global_step": 369340, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.2179648876190186, "global_step": 369341, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.101740598678589, "global_step": 369342, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.105485677719116, "global_step": 369343, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.179792881011963, "global_step": 369344, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0981953144073486, "global_step": 369345, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.018540620803833, "global_step": 369346, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.044372081756592, "global_step": 369347, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0932235717773438, "global_step": 369348, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0834102630615234, "global_step": 369349, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.117905855178833, "global_step": 369350, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0213241577148438, "global_step": 369351, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.073927164077759, "global_step": 369352, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.153848648071289, "global_step": 369353, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.115440845489502, "global_step": 369354, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0475573539733887, "global_step": 369355, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0685577392578125, "global_step": 369356, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.164020538330078, "global_step": 369357, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1025960445404053, "global_step": 369358, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0444958209991455, "global_step": 369359, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0866925716400146, "global_step": 369360, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0818800926208496, "global_step": 369361, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1320154666900635, "global_step": 369362, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0947444438934326, "global_step": 369363, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.111199378967285, "global_step": 369364, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.2244911193847656, "global_step": 369365, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0865159034729004, "global_step": 369366, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.241358518600464, "global_step": 369367, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.124101161956787, "global_step": 369368, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0917389392852783, "global_step": 369369, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.161309242248535, "global_step": 369370, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1070542335510254, "global_step": 369371, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.069636821746826, "global_step": 369372, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.169605255126953, "global_step": 369373, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1034350395202637, "global_step": 369374, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1416101455688477, "global_step": 369375, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0595264434814453, "global_step": 369376, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1704652309417725, "global_step": 369377, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0753862857818604, "global_step": 369378, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0699262619018555, "global_step": 369379, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1005656719207764, "global_step": 369380, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.096850872039795, "global_step": 369381, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.150564670562744, "global_step": 369382, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1328413486480713, "global_step": 369383, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.166971445083618, "global_step": 369384, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.113034248352051, "global_step": 369385, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.026414394378662, "global_step": 369386, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.171114683151245, "global_step": 369387, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0444295406341553, "global_step": 369388, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0889813899993896, "global_step": 369389, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.068894624710083, "global_step": 369390, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1123290061950684, "global_step": 369391, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1661124229431152, "global_step": 369392, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0507514476776123, "global_step": 369393, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0852081775665283, "global_step": 369394, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.010082721710205, "global_step": 369395, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1202967166900635, "global_step": 369396, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.115246057510376, "global_step": 369397, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.072166919708252, "global_step": 369398, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.085611581802368, "global_step": 369399, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.081613540649414, "global_step": 369400, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1618802547454834, "global_step": 369401, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1485583782196045, "global_step": 369402, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.068000555038452, "global_step": 369403, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0786306858062744, "global_step": 369404, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1200854778289795, "global_step": 369405, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.068228006362915, "global_step": 369406, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.011162519454956, "global_step": 369407, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0498485565185547, "global_step": 369408, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1838269233703613, "global_step": 369409, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1073038578033447, "global_step": 369410, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.090287923812866, "global_step": 369411, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.085845470428467, "global_step": 369412, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.053812265396118, "global_step": 369413, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0707874298095703, "global_step": 369414, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1327950954437256, "global_step": 369415, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.109023094177246, "global_step": 369416, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.133697748184204, "global_step": 369417, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.079362154006958, "global_step": 369418, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.129106283187866, "global_step": 369419, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1414554119110107, "global_step": 369420, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.082334518432617, "global_step": 369421, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.045353889465332, "global_step": 369422, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1758763790130615, "global_step": 369423, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.153900623321533, "global_step": 369424, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0911452770233154, "global_step": 369425, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0918869972229004, "global_step": 369426, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1251823902130127, "global_step": 369427, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.037379741668701, "global_step": 369428, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.091688632965088, "global_step": 369429, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1521337032318115, "global_step": 369430, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1875126361846924, "global_step": 369431, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.094197988510132, "global_step": 369432, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.185473918914795, "global_step": 369433, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1820836067199707, "global_step": 369434, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1212592124938965, "global_step": 369435, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1281564235687256, "global_step": 369436, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.071200370788574, "global_step": 369437, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1018218994140625, "global_step": 369438, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.078345537185669, "global_step": 369439, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1483631134033203, "global_step": 369440, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.052417516708374, "global_step": 369441, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.07643985748291, "global_step": 369442, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.150240659713745, "global_step": 369443, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.203472852706909, "global_step": 369444, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1272313594818115, "global_step": 369445, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1692776679992676, "global_step": 369446, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.189215898513794, "global_step": 369447, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.222100019454956, "global_step": 369448, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.165036678314209, "global_step": 369449, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1571319103240967, "global_step": 369450, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.100825309753418, "global_step": 369451, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1267597675323486, "global_step": 369452, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.081751823425293, "global_step": 369453, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1817786693573, "global_step": 369454, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0213780403137207, "global_step": 369455, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.101732015609741, "global_step": 369456, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0767321586608887, "global_step": 369457, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.05475115776062, "global_step": 369458, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.097503900527954, "global_step": 369459, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0427284240722656, "global_step": 369460, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.167820930480957, "global_step": 369461, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.081204414367676, "global_step": 369462, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0927810668945312, "global_step": 369463, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.152920722961426, "global_step": 369464, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0861077308654785, "global_step": 369465, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.190920114517212, "global_step": 369466, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.09032940864563, "global_step": 369467, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1003222465515137, "global_step": 369468, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0875861644744873, "global_step": 369469, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.123962640762329, "global_step": 369470, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1141631603240967, "global_step": 369471, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.134092092514038, "global_step": 369472, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.06819748878479, "global_step": 369473, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0677850246429443, "global_step": 369474, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.064706325531006, "global_step": 369475, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1659088134765625, "global_step": 369476, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1501128673553467, "global_step": 369477, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.12958025932312, "global_step": 369478, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.112873077392578, "global_step": 369479, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1444849967956543, "global_step": 369480, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1973471641540527, "global_step": 369481, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1664252281188965, "global_step": 369482, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.087761402130127, "global_step": 369483, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1191885471343994, "global_step": 369484, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0717344284057617, "global_step": 369485, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0790464878082275, "global_step": 369486, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0988609790802, "global_step": 369487, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.129817485809326, "global_step": 369488, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.104887008666992, "global_step": 369489, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.05501389503479, "global_step": 369490, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1021437644958496, "global_step": 369491, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1294000148773193, "global_step": 369492, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.000847578048706, "global_step": 369493, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.052286386489868, "global_step": 369494, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1599020957946777, "global_step": 369495, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.144120454788208, "global_step": 369496, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0808444023132324, "global_step": 369497, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.025676965713501, "global_step": 369498, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1783714294433594, "global_step": 369499, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.011984348297119, "global_step": 369500, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.152752161026001, "global_step": 369501, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.056771993637085, "global_step": 369502, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1361937522888184, "global_step": 369503, "epoch": 731, "lr": 5e-05}
{"train_loss": 1.96637761592865, "global_step": 369504, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.105921983718872, "global_step": 369505, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1610631942749023, "global_step": 369506, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.159210205078125, "global_step": 369507, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0913360118865967, "global_step": 369508, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1530303955078125, "global_step": 369509, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1601500511169434, "global_step": 369510, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.058152914047241, "global_step": 369511, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0722734928131104, "global_step": 369512, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0802950859069824, "global_step": 369513, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.096323013305664, "global_step": 369514, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0267460346221924, "global_step": 369515, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.110769271850586, "global_step": 369516, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1223366260528564, "global_step": 369517, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0819125175476074, "global_step": 369518, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0828683376312256, "global_step": 369519, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0310287475585938, "global_step": 369520, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1186959743499756, "global_step": 369521, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1126697063446045, "global_step": 369522, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.2027428150177, "global_step": 369523, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.200145721435547, "global_step": 369524, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1018640995025635, "global_step": 369525, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1213903427124023, "global_step": 369526, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1338250637054443, "global_step": 369527, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.094968318939209, "global_step": 369528, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1329727172851562, "global_step": 369529, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.087139368057251, "global_step": 369530, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.114743232727051, "global_step": 369531, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.092825174331665, "global_step": 369532, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1127283573150635, "global_step": 369533, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1093239784240723, "global_step": 369534, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0918054580688477, "global_step": 369535, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.147972822189331, "global_step": 369536, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.096318244934082, "global_step": 369537, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1562066078186035, "global_step": 369538, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1826817989349365, "global_step": 369539, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0555760860443115, "global_step": 369540, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0465500354766846, "global_step": 369541, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0412065982818604, "global_step": 369542, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.092365026473999, "global_step": 369543, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.18345308303833, "global_step": 369544, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.155456066131592, "global_step": 369545, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0528645515441895, "global_step": 369546, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0910284519195557, "global_step": 369547, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0668745040893555, "global_step": 369548, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0378780364990234, "global_step": 369549, "epoch": 731, "lr": 5e-05}
{"train_loss": 1.985411286354065, "global_step": 369550, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0938074588775635, "global_step": 369551, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1099119186401367, "global_step": 369552, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.181110143661499, "global_step": 369553, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.2023253440856934, "global_step": 369554, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.157099485397339, "global_step": 369555, "epoch": 731, "lr": 5e-05}
{"train_loss": 1.9552431106567383, "global_step": 369556, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.095177173614502, "global_step": 369557, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.045544385910034, "global_step": 369558, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0651803016662598, "global_step": 369559, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0527517795562744, "global_step": 369560, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.074211359024048, "global_step": 369561, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.040393590927124, "global_step": 369562, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.136492967605591, "global_step": 369563, "epoch": 731, "lr": 5e-05}
{"train_loss": 1.9708260297775269, "global_step": 369564, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.049548625946045, "global_step": 369565, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.104055166244507, "global_step": 369566, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.126539468765259, "global_step": 369567, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.14993953704834, "global_step": 369568, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0832321643829346, "global_step": 369569, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.2212839126586914, "global_step": 369570, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1347293853759766, "global_step": 369571, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0626220703125, "global_step": 369572, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0671277046203613, "global_step": 369573, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0874929428100586, "global_step": 369574, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1573941707611084, "global_step": 369575, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0048930644989014, "global_step": 369576, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.055075168609619, "global_step": 369577, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.074191093444824, "global_step": 369578, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1373729705810547, "global_step": 369579, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0275681018829346, "global_step": 369580, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0786447525024414, "global_step": 369581, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1976826190948486, "global_step": 369582, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1114907264709473, "global_step": 369583, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1245296001434326, "global_step": 369584, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1390540599823, "global_step": 369585, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.050942897796631, "global_step": 369586, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1020214557647705, "global_step": 369587, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.136370897293091, "global_step": 369588, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.081169366836548, "global_step": 369589, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.108147382736206, "global_step": 369590, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1830477714538574, "global_step": 369591, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.070246934890747, "global_step": 369592, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1652424335479736, "global_step": 369593, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.138826370239258, "global_step": 369594, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.090101718902588, "global_step": 369595, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1422998905181885, "global_step": 369596, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.083993911743164, "global_step": 369597, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1077589988708496, "global_step": 369598, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0965492725372314, "global_step": 369599, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0612199306488037, "global_step": 369600, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1146929264068604, "global_step": 369601, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.126410722732544, "global_step": 369602, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.154834508895874, "global_step": 369603, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0432655811309814, "global_step": 369604, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0792670249938965, "global_step": 369605, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.014267921447754, "global_step": 369606, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1188266277313232, "global_step": 369607, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0582048892974854, "global_step": 369608, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.17197847366333, "global_step": 369609, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.085222005844116, "global_step": 369610, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.099548101425171, "global_step": 369611, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1176364421844482, "global_step": 369612, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.058593273162842, "global_step": 369613, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1318037509918213, "global_step": 369614, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.151918411254883, "global_step": 369615, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1285011768341064, "global_step": 369616, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.223390817642212, "global_step": 369617, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.167856454849243, "global_step": 369618, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.084430694580078, "global_step": 369619, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0652761459350586, "global_step": 369620, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0444233417510986, "global_step": 369621, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.070075035095215, "global_step": 369622, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.2067670822143555, "global_step": 369623, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0838558673858643, "global_step": 369624, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1098456382751465, "global_step": 369625, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.149484634399414, "global_step": 369626, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0766663551330566, "global_step": 369627, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0552449226379395, "global_step": 369628, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0738253593444824, "global_step": 369629, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.079853057861328, "global_step": 369630, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.054556131362915, "global_step": 369631, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.151719331741333, "global_step": 369632, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1310689449310303, "global_step": 369633, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1738545894622803, "global_step": 369634, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.161687135696411, "global_step": 369635, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.092984676361084, "global_step": 369636, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.147554397583008, "global_step": 369637, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.128260374069214, "global_step": 369638, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1493420600891113, "global_step": 369639, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0947208404541016, "global_step": 369640, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1063170433044434, "global_step": 369641, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0645110607147217, "global_step": 369642, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.201937198638916, "global_step": 369643, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1176161766052246, "global_step": 369644, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.124695062637329, "global_step": 369645, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1678245067596436, "global_step": 369646, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.122291326522827, "global_step": 369647, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.07212495803833, "global_step": 369648, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1271309852600098, "global_step": 369649, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.043344736099243, "global_step": 369650, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1168787479400635, "global_step": 369651, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1452789306640625, "global_step": 369652, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.120347261428833, "global_step": 369653, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0090322494506836, "global_step": 369654, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0406832695007324, "global_step": 369655, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1801869869232178, "global_step": 369656, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1304540634155273, "global_step": 369657, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.177098035812378, "global_step": 369658, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.097116231918335, "global_step": 369659, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0999839305877686, "global_step": 369660, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.091979742050171, "global_step": 369661, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.068159580230713, "global_step": 369662, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1220200061798096, "global_step": 369663, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1516244411468506, "global_step": 369664, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.087764263153076, "global_step": 369665, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.090094566345215, "global_step": 369666, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0431888103485107, "global_step": 369667, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.083791971206665, "global_step": 369668, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0467147827148438, "global_step": 369669, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1396617889404297, "global_step": 369670, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0935142040252686, "global_step": 369671, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1056814193725586, "global_step": 369672, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.207763195037842, "global_step": 369673, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.117157459259033, "global_step": 369674, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.119764804840088, "global_step": 369675, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0759904384613037, "global_step": 369676, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.129225492477417, "global_step": 369677, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.153510570526123, "global_step": 369678, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1317338943481445, "global_step": 369679, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.078470230102539, "global_step": 369680, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1905996799468994, "global_step": 369681, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.092712640762329, "global_step": 369682, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0982487201690674, "global_step": 369683, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.124037742614746, "global_step": 369684, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1271321773529053, "global_step": 369685, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1484434604644775, "global_step": 369686, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.155489444732666, "global_step": 369687, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0985286235809326, "global_step": 369688, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1300559043884277, "global_step": 369689, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1815836429595947, "global_step": 369690, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.052882671356201, "global_step": 369691, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.2016711235046387, "global_step": 369692, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.075648546218872, "global_step": 369693, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1240386962890625, "global_step": 369694, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0750010013580322, "global_step": 369695, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.06683611869812, "global_step": 369696, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.119631767272949, "global_step": 369697, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0834126472473145, "global_step": 369698, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.036705732345581, "global_step": 369699, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1205954551696777, "global_step": 369700, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0514302253723145, "global_step": 369701, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.100114345550537, "global_step": 369702, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.173877239227295, "global_step": 369703, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.170731782913208, "global_step": 369704, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0505013465881348, "global_step": 369705, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.195230484008789, "global_step": 369706, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0146844387054443, "global_step": 369707, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1354777812957764, "global_step": 369708, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1107370853424072, "global_step": 369709, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0451700687408447, "global_step": 369710, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0891053676605225, "global_step": 369711, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1477243900299072, "global_step": 369712, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.063664674758911, "global_step": 369713, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0863983631134033, "global_step": 369714, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.164138078689575, "global_step": 369715, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.149413585662842, "global_step": 369716, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1623270511627197, "global_step": 369717, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1295671463012695, "global_step": 369718, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.114964723587036, "global_step": 369719, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.115525722503662, "global_step": 369720, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.081148862838745, "global_step": 369721, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.115738868713379, "global_step": 369722, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1378066539764404, "global_step": 369723, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0186150074005127, "global_step": 369724, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.034177780151367, "global_step": 369725, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1280322074890137, "global_step": 369726, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0946574211120605, "global_step": 369727, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.097198486328125, "global_step": 369728, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.082578659057617, "global_step": 369729, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1776530742645264, "global_step": 369730, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.060926675796509, "global_step": 369731, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1556944847106934, "global_step": 369732, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1903417110443115, "global_step": 369733, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1102328300476074, "global_step": 369734, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.158881664276123, "global_step": 369735, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.162048816680908, "global_step": 369736, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.112286329269409, "global_step": 369737, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0497560501098633, "global_step": 369738, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.112924814224243, "global_step": 369739, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.03195858001709, "global_step": 369740, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1240756511688232, "global_step": 369741, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.109638214111328, "global_step": 369742, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.073033332824707, "global_step": 369743, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.081693649291992, "global_step": 369744, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1108639240264893, "global_step": 369745, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0296733379364014, "global_step": 369746, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.134565830230713, "global_step": 369747, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0851502418518066, "global_step": 369748, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0654706954956055, "global_step": 369749, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0913798809051514, "global_step": 369750, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1247384548187256, "global_step": 369751, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.076742649078369, "global_step": 369752, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.00028920173645, "global_step": 369753, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.038383722305298, "global_step": 369754, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.105071544647217, "global_step": 369755, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1270785331726074, "global_step": 369756, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.148569107055664, "global_step": 369757, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.086782932281494, "global_step": 369758, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0982589721679688, "global_step": 369759, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0691659450531006, "global_step": 369760, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0481956005096436, "global_step": 369761, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1317644119262695, "global_step": 369762, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.147223711013794, "global_step": 369763, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0286245346069336, "global_step": 369764, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1131715774536133, "global_step": 369765, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.2172086238861084, "global_step": 369766, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0751681327819824, "global_step": 369767, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0829110145568848, "global_step": 369768, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.134909152984619, "global_step": 369769, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1897594928741455, "global_step": 369770, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.128791093826294, "global_step": 369771, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.20450496673584, "global_step": 369772, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1355857849121094, "global_step": 369773, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1469614505767822, "global_step": 369774, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1091582775115967, "global_step": 369775, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1144566535949707, "global_step": 369776, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.151569366455078, "global_step": 369777, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1336352825164795, "global_step": 369778, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1211259365081787, "global_step": 369779, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.075878381729126, "global_step": 369780, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1900291442871094, "global_step": 369781, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0217251777648926, "global_step": 369782, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1214709281921387, "global_step": 369783, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0810792446136475, "global_step": 369784, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1119930744171143, "global_step": 369785, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.113816738128662, "global_step": 369786, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1424477100372314, "global_step": 369787, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0809476375579834, "global_step": 369788, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0840375423431396, "global_step": 369789, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1452364921569824, "global_step": 369790, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0703718662261963, "global_step": 369791, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.082643508911133, "global_step": 369792, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0312962532043457, "global_step": 369793, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1038870811462402, "global_step": 369794, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.098975658416748, "global_step": 369795, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1362195014953613, "global_step": 369796, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.108034372329712, "global_step": 369797, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0453577041625977, "global_step": 369798, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.098857879638672, "global_step": 369799, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.086668014526367, "global_step": 369800, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.026872396469116, "global_step": 369801, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.134009838104248, "global_step": 369802, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.015231132507324, "global_step": 369803, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0884506702423096, "global_step": 369804, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0436718463897705, "global_step": 369805, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.19818377494812, "global_step": 369806, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.11112642288208, "global_step": 369807, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0293734073638916, "global_step": 369808, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.13037371635437, "global_step": 369809, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0957720279693604, "global_step": 369810, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1252059936523438, "global_step": 369811, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.009092092514038, "global_step": 369812, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.075212240219116, "global_step": 369813, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1696014404296875, "global_step": 369814, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0843684673309326, "global_step": 369815, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.141871690750122, "global_step": 369816, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1177000999450684, "global_step": 369817, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0491018295288086, "global_step": 369818, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.080845355987549, "global_step": 369819, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0599939823150635, "global_step": 369820, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0655829906463623, "global_step": 369821, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1725292205810547, "global_step": 369822, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.2195804119110107, "global_step": 369823, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.191535472869873, "global_step": 369824, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.033940076828003, "global_step": 369825, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.076840877532959, "global_step": 369826, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.072221279144287, "global_step": 369827, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0811879634857178, "global_step": 369828, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0567216873168945, "global_step": 369829, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1233041286468506, "global_step": 369830, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1497292518615723, "global_step": 369831, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1054844856262207, "global_step": 369832, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1158807277679443, "global_step": 369833, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1490638256073, "global_step": 369834, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.176872968673706, "global_step": 369835, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.165438652038574, "global_step": 369836, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1251213550567627, "global_step": 369837, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.048694610595703, "global_step": 369838, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.050306797027588, "global_step": 369839, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.193138599395752, "global_step": 369840, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0509121417999268, "global_step": 369841, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1207873821258545, "global_step": 369842, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.124748706817627, "global_step": 369843, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.089261531829834, "global_step": 369844, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1461148262023926, "global_step": 369845, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0888760089874268, "global_step": 369846, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1246721744537354, "global_step": 369847, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1033496856689453, "global_step": 369848, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.132941722869873, "global_step": 369849, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1185247898101807, "global_step": 369850, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1140401363372803, "global_step": 369851, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1417980194091797, "global_step": 369852, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1679201126098633, "global_step": 369853, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1912429332733154, "global_step": 369854, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.052278995513916, "global_step": 369855, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0694022178649902, "global_step": 369856, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.169248104095459, "global_step": 369857, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.110924005508423, "global_step": 369858, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1046340465545654, "global_step": 369859, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.099553108215332, "global_step": 369860, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1711316108703613, "global_step": 369861, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1845920085906982, "global_step": 369862, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0724306106567383, "global_step": 369863, "epoch": 731, "lr": 5e-05}
{"train_loss": 1.9957554340362549, "global_step": 369864, "epoch": 731, "lr": 5e-05}
{"train_loss": 1.9944593906402588, "global_step": 369865, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.083408832550049, "global_step": 369866, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1128854751586914, "global_step": 369867, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.110138416290283, "global_step": 369868, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.169590711593628, "global_step": 369869, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.157618522644043, "global_step": 369870, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1060051918029785, "global_step": 369871, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.172633171081543, "global_step": 369872, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.18119215965271, "global_step": 369873, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1880555152893066, "global_step": 369874, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1319117546081543, "global_step": 369875, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.083317756652832, "global_step": 369876, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1977391242980957, "global_step": 369877, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.128631830215454, "global_step": 369878, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0506465435028076, "global_step": 369879, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.098151445388794, "global_step": 369880, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.181863784790039, "global_step": 369881, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.080963373184204, "global_step": 369882, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0203053951263428, "global_step": 369883, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.109137535095215, "global_step": 369884, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1321728229522705, "global_step": 369885, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.155266761779785, "global_step": 369886, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.135293960571289, "global_step": 369887, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.149946689605713, "global_step": 369888, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0487215518951416, "global_step": 369889, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.155797243118286, "global_step": 369890, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.057391881942749, "global_step": 369891, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.058018445968628, "global_step": 369892, "epoch": 731, "lr": 5e-05}
{"train_loss": 1.9630038738250732, "global_step": 369893, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.103253126144409, "global_step": 369894, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0801849365234375, "global_step": 369895, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.163473606109619, "global_step": 369896, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1406702995300293, "global_step": 369897, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0786635875701904, "global_step": 369898, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1548075675964355, "global_step": 369899, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.171449661254883, "global_step": 369900, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.218806505203247, "global_step": 369901, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.129257917404175, "global_step": 369902, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0164966583251953, "global_step": 369903, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1112987995147705, "global_step": 369904, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.073756694793701, "global_step": 369905, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.103773593902588, "global_step": 369906, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.178978681564331, "global_step": 369907, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1584510803222656, "global_step": 369908, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1094725131988525, "global_step": 369909, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.13645339012146, "global_step": 369910, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.15569806098938, "global_step": 369911, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.032202959060669, "global_step": 369912, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.064324378967285, "global_step": 369913, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.083047389984131, "global_step": 369914, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1210124492645264, "global_step": 369915, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1172122955322266, "global_step": 369916, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.116820812225342, "global_step": 369917, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0723021030426025, "global_step": 369918, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1139843463897705, "global_step": 369919, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0752382278442383, "global_step": 369920, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0864498615264893, "global_step": 369921, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.013259172439575, "global_step": 369922, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0864999294281006, "global_step": 369923, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.119400978088379, "global_step": 369924, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1837375164031982, "global_step": 369925, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.096914768218994, "global_step": 369926, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1521530151367188, "global_step": 369927, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.053070306777954, "global_step": 369928, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0985169410705566, "global_step": 369929, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.085344076156616, "global_step": 369930, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0885915756225586, "global_step": 369931, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.2468764781951904, "global_step": 369932, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1187779903411865, "global_step": 369933, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.2571310997009277, "global_step": 369934, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.101809501647949, "global_step": 369935, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1118264198303223, "global_step": 369936, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.069854259490967, "global_step": 369937, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.182842969894409, "global_step": 369938, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.084883213043213, "global_step": 369939, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.13158917427063, "global_step": 369940, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.160963296890259, "global_step": 369941, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0788075923919678, "global_step": 369942, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1582419872283936, "global_step": 369943, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.084442615509033, "global_step": 369944, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1259615421295166, "global_step": 369945, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1014647483825684, "global_step": 369946, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1274912357330322, "global_step": 369947, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.154060125350952, "global_step": 369948, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.052816390991211, "global_step": 369949, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1282808780670166, "global_step": 369950, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.096261978149414, "global_step": 369951, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1493489742279053, "global_step": 369952, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.147526741027832, "global_step": 369953, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.105329990386963, "global_step": 369954, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1460635662078857, "global_step": 369955, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1084256172180176, "global_step": 369956, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1430933475494385, "global_step": 369957, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.107473134994507, "global_step": 369958, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1193501949310303, "global_step": 369959, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1146492958068848, "global_step": 369960, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1691460609436035, "global_step": 369961, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.032306432723999, "global_step": 369962, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0994489192962646, "global_step": 369963, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0804190635681152, "global_step": 369964, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.12841534614563, "global_step": 369965, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.132319450378418, "global_step": 369966, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1187102794647217, "global_step": 369967, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1334362030029297, "global_step": 369968, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.148552894592285, "global_step": 369969, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.065781354904175, "global_step": 369970, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.083958148956299, "global_step": 369971, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0677411556243896, "global_step": 369972, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.066986322402954, "global_step": 369973, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.170952796936035, "global_step": 369974, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1088926792144775, "global_step": 369975, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1680493354797363, "global_step": 369976, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1533448696136475, "global_step": 369977, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.103095054626465, "global_step": 369978, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0601487159729004, "global_step": 369979, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0769784450531006, "global_step": 369980, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1531074047088623, "global_step": 369981, "epoch": 731, "lr": 5e-05}
{"train_loss": 1.9902349710464478, "global_step": 369982, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.08836030960083, "global_step": 369983, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0272910594940186, "global_step": 369984, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1476879119873047, "global_step": 369985, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0861215591430664, "global_step": 369986, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.07759165763855, "global_step": 369987, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1382088661193848, "global_step": 369988, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.210697650909424, "global_step": 369989, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0880558490753174, "global_step": 369990, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1475143432617188, "global_step": 369991, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0967350006103516, "global_step": 369992, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1780154705047607, "global_step": 369993, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.058497428894043, "global_step": 369994, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.154531478881836, "global_step": 369995, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.209365129470825, "global_step": 369996, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.059624671936035, "global_step": 369997, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.099060297012329, "global_step": 369998, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0586750507354736, "global_step": 369999, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1077160835266113, "global_step": 370000, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.233635902404785, "global_step": 370001, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0493597984313965, "global_step": 370002, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.161989212036133, "global_step": 370003, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0802080631256104, "global_step": 370004, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0826637744903564, "global_step": 370005, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.128239631652832, "global_step": 370006, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0803494453430176, "global_step": 370007, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.122727632522583, "global_step": 370008, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0127787590026855, "global_step": 370009, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.082322120666504, "global_step": 370010, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.162351608276367, "global_step": 370011, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1324470043182373, "global_step": 370012, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.114993095397949, "global_step": 370013, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0647048950195312, "global_step": 370014, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.053093194961548, "global_step": 370015, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1494247913360596, "global_step": 370016, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.235048294067383, "global_step": 370017, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.062807559967041, "global_step": 370018, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1145753860473633, "global_step": 370019, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1677353382110596, "global_step": 370020, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1363189220428467, "global_step": 370021, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0367515087127686, "global_step": 370022, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.003746271133423, "global_step": 370023, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.161484479904175, "global_step": 370024, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.108637809753418, "global_step": 370025, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0709261894226074, "global_step": 370026, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.14487886428833, "global_step": 370027, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0868148803710938, "global_step": 370028, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.134772539138794, "global_step": 370029, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1451594829559326, "global_step": 370030, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.081439733505249, "global_step": 370031, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1186578273773193, "global_step": 370032, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.115817070007324, "global_step": 370033, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.157663106918335, "global_step": 370034, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.165009021759033, "global_step": 370035, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1778955459594727, "global_step": 370036, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1151185035705566, "global_step": 370037, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0731098651885986, "global_step": 370038, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.086031198501587, "global_step": 370039, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.099997043609619, "global_step": 370040, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1686439514160156, "global_step": 370041, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.158586025238037, "global_step": 370042, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.134193181991577, "global_step": 370043, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1934616565704346, "global_step": 370044, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1528518199920654, "global_step": 370045, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.128812551498413, "global_step": 370046, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.113865613937378, "global_step": 370047, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1269171237945557, "global_step": 370048, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0916895866394043, "global_step": 370049, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.158724784851074, "global_step": 370050, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1051230430603027, "global_step": 370051, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.066138505935669, "global_step": 370052, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0834031105041504, "global_step": 370053, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1314167976379395, "global_step": 370054, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.131399631500244, "global_step": 370055, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1220898628234863, "global_step": 370056, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.085861921310425, "global_step": 370057, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0660362243652344, "global_step": 370058, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.018585681915283, "global_step": 370059, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0890467166900635, "global_step": 370060, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1021440029144287, "global_step": 370061, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1957175731658936, "global_step": 370062, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.2020928859710693, "global_step": 370063, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1212105751037598, "global_step": 370064, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0374655723571777, "global_step": 370065, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.055323362350464, "global_step": 370066, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.144533634185791, "global_step": 370067, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1307692527770996, "global_step": 370068, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.169222593307495, "global_step": 370069, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.213277578353882, "global_step": 370070, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.169252872467041, "global_step": 370071, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0494227409362793, "global_step": 370072, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1051013469696045, "global_step": 370073, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.2167656421661377, "global_step": 370074, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1159138679504395, "global_step": 370075, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.065988779067993, "global_step": 370076, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0931015014648438, "global_step": 370077, "epoch": 731, "lr": 5e-05}
{"train_loss": 1.9878244400024414, "global_step": 370078, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1490097045898438, "global_step": 370079, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0511484146118164, "global_step": 370080, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1153008937835693, "global_step": 370081, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0832674503326416, "global_step": 370082, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0348238945007324, "global_step": 370083, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0582339763641357, "global_step": 370084, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.164391040802002, "global_step": 370085, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0699379444122314, "global_step": 370086, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1223905086517334, "global_step": 370087, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0909104347229004, "global_step": 370088, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.161835193634033, "global_step": 370089, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1856131553649902, "global_step": 370090, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.077430486679077, "global_step": 370091, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1151461601257324, "global_step": 370092, "epoch": 731, "lr": 5e-05}
{"train_loss": 1.9882100820541382, "global_step": 370093, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.029691457748413, "global_step": 370094, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.096928596496582, "global_step": 370095, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.085489273071289, "global_step": 370096, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.142430067062378, "global_step": 370097, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0098354816436768, "global_step": 370098, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.164456844329834, "global_step": 370099, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1640074253082275, "global_step": 370100, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.080156087875366, "global_step": 370101, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.088034152984619, "global_step": 370102, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1933555603027344, "global_step": 370103, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.086106538772583, "global_step": 370104, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.153538942337036, "global_step": 370105, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.010213851928711, "global_step": 370106, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.05157208442688, "global_step": 370107, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0395562648773193, "global_step": 370108, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1647703647613525, "global_step": 370109, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.108142375946045, "global_step": 370110, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0948400497436523, "global_step": 370111, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.083575963973999, "global_step": 370112, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1931190490722656, "global_step": 370113, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.2101941108703613, "global_step": 370114, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.064296245574951, "global_step": 370115, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0694544315338135, "global_step": 370116, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1241228580474854, "global_step": 370117, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0942087173461914, "global_step": 370118, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.153593063354492, "global_step": 370119, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.2031776905059814, "global_step": 370120, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.136296510696411, "global_step": 370121, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.033634901046753, "global_step": 370122, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.148488998413086, "global_step": 370123, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1149470806121826, "global_step": 370124, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1523640155792236, "global_step": 370125, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.164605140686035, "global_step": 370126, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.105031728744507, "global_step": 370127, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1191935539245605, "global_step": 370128, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1304588317871094, "global_step": 370129, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.128109931945801, "global_step": 370130, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0803260803222656, "global_step": 370131, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.10908579826355, "global_step": 370132, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0830910205841064, "global_step": 370133, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0926430225372314, "global_step": 370134, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.116212844848633, "global_step": 370135, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.105482578277588, "global_step": 370136, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1190552711486816, "global_step": 370137, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1485064029693604, "global_step": 370138, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0362422466278076, "global_step": 370139, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.05981707572937, "global_step": 370140, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1259875297546387, "global_step": 370141, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.2378597259521484, "global_step": 370142, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1476945877075195, "global_step": 370143, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.117554187774658, "global_step": 370144, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1413323879241943, "global_step": 370145, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1137547492980957, "global_step": 370146, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1608264446258545, "global_step": 370147, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.07633376121521, "global_step": 370148, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1619179248809814, "global_step": 370149, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.178954601287842, "global_step": 370150, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1359994411468506, "global_step": 370151, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.169642448425293, "global_step": 370152, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.150881052017212, "global_step": 370153, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.124380350112915, "global_step": 370154, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1339101791381836, "global_step": 370155, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.196664333343506, "global_step": 370156, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1569972038269043, "global_step": 370157, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0760738849639893, "global_step": 370158, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.151078462600708, "global_step": 370159, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.19830060005188, "global_step": 370160, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1397547721862793, "global_step": 370161, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.143918752670288, "global_step": 370162, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.2146265506744385, "global_step": 370163, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.131067991256714, "global_step": 370164, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.111361265182495, "global_step": 370165, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0412347316741943, "global_step": 370166, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1140530109405518, "global_step": 370167, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.126983642578125, "global_step": 370168, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.2274370193481445, "global_step": 370169, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.079610586166382, "global_step": 370170, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1153745651245117, "global_step": 370171, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.089946746826172, "global_step": 370172, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0905022621154785, "global_step": 370173, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1252682209014893, "global_step": 370174, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.178454875946045, "global_step": 370175, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0699520111083984, "global_step": 370176, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0433952808380127, "global_step": 370177, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.088270664215088, "global_step": 370178, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1389904022216797, "global_step": 370179, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.141611337661743, "global_step": 370180, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0609357357025146, "global_step": 370181, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.069817066192627, "global_step": 370182, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1498255729675293, "global_step": 370183, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.193133592605591, "global_step": 370184, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0342752933502197, "global_step": 370185, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.159616231918335, "global_step": 370186, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.026959180831909, "global_step": 370187, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1189072132110596, "global_step": 370188, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.113132953643799, "global_step": 370189, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1003921031951904, "global_step": 370190, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1014955043792725, "global_step": 370191, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1145036220550537, "global_step": 370192, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.003692150115967, "global_step": 370193, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0760016441345215, "global_step": 370194, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.119842052459717, "global_step": 370195, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1743569374084473, "global_step": 370196, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0894641876220703, "global_step": 370197, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1238982677459717, "global_step": 370198, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.150010108947754, "global_step": 370199, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.191358804702759, "global_step": 370200, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0814993381500244, "global_step": 370201, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1522672176361084, "global_step": 370202, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.06813645362854, "global_step": 370203, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.088235378265381, "global_step": 370204, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.100252151489258, "global_step": 370205, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0812151432037354, "global_step": 370206, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.2082157135009766, "global_step": 370207, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0483555793762207, "global_step": 370208, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0623438358306885, "global_step": 370209, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.129244327545166, "global_step": 370210, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.180527448654175, "global_step": 370211, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.107140302658081, "global_step": 370212, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0120346546173096, "global_step": 370213, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.185842275619507, "global_step": 370214, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1715567111968994, "global_step": 370215, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.085251808166504, "global_step": 370216, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.094810962677002, "global_step": 370217, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.094196081161499, "global_step": 370218, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1448585987091064, "global_step": 370219, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0610897541046143, "global_step": 370220, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1277894973754883, "global_step": 370221, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1499123573303223, "global_step": 370222, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0999691486358643, "global_step": 370223, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.131479501724243, "global_step": 370224, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.109821081161499, "global_step": 370225, "epoch": 731, "lr": 5e-05}
{"train_loss": 1.9878777265548706, "global_step": 370226, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1664421558380127, "global_step": 370227, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.159411907196045, "global_step": 370228, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.08402681350708, "global_step": 370229, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1477913856506348, "global_step": 370230, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1449806690216064, "global_step": 370231, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.051593065261841, "global_step": 370232, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0075573921203613, "global_step": 370233, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.013002395629883, "global_step": 370234, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1390132904052734, "global_step": 370235, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0389580726623535, "global_step": 370236, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1116459369659424, "global_step": 370237, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.101694345474243, "global_step": 370238, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0609540939331055, "global_step": 370239, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1513662338256836, "global_step": 370240, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0536718368530273, "global_step": 370241, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.140820026397705, "global_step": 370242, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1064717769622803, "global_step": 370243, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.044038772583008, "global_step": 370244, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1367781162261963, "global_step": 370245, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1588261127471924, "global_step": 370246, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1197350025177, "global_step": 370247, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1103224754333496, "global_step": 370248, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1086325645446777, "global_step": 370249, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.186086416244507, "global_step": 370250, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.132880210876465, "global_step": 370251, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1381022930145264, "global_step": 370252, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1096432209014893, "global_step": 370253, "epoch": 731, "lr": 5e-05}
{"train_loss": 1.9704170227050781, "global_step": 370254, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1565780639648438, "global_step": 370255, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.137080192565918, "global_step": 370256, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0637290477752686, "global_step": 370257, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.114408493041992, "global_step": 370258, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1294198036193848, "global_step": 370259, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1417653560638428, "global_step": 370260, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1187021732330322, "global_step": 370261, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.139829158782959, "global_step": 370262, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1006062030792236, "global_step": 370263, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1433887481689453, "global_step": 370264, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0302884578704834, "global_step": 370265, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1264216899871826, "global_step": 370266, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1650025844573975, "global_step": 370267, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0851149559020996, "global_step": 370268, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0862603187561035, "global_step": 370269, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1212480068206787, "global_step": 370270, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0234737396240234, "global_step": 370271, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.100698709487915, "global_step": 370272, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.137258291244507, "global_step": 370273, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.206151247024536, "global_step": 370274, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.0929770469665527, "global_step": 370275, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1377179622650146, "global_step": 370276, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1036298274993896, "global_step": 370277, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.168778896331787, "global_step": 370278, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1032354831695557, "global_step": 370279, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.068690776824951, "global_step": 370280, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.132667064666748, "global_step": 370281, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1322414875030518, "global_step": 370282, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1649832725524902, "global_step": 370283, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1299469470977783, "global_step": 370284, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.042006492614746, "global_step": 370285, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.181776285171509, "global_step": 370286, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.240788459777832, "global_step": 370287, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.013298511505127, "global_step": 370288, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1672699451446533, "global_step": 370289, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.109823226928711, "global_step": 370290, "epoch": 731, "lr": 5e-05}
{"train_loss": 2.1458253860473633, "global_step": 370291, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.119260311126709, "global_step": 370292, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0621135234832764, "global_step": 370293, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0621888637542725, "global_step": 370294, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0934784412384033, "global_step": 370295, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0130105018615723, "global_step": 370296, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0870320796966553, "global_step": 370297, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0958969593048096, "global_step": 370298, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.9729653596878052, "global_step": 370299, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.052934408187866, "global_step": 370300, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.113494634628296, "global_step": 370301, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.055497169494629, "global_step": 370302, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.160482168197632, "global_step": 370303, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1580581665039062, "global_step": 370304, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1085119247436523, "global_step": 370305, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.104050874710083, "global_step": 370306, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0901246070861816, "global_step": 370307, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0750415325164795, "global_step": 370308, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.071044921875, "global_step": 370309, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.088498115539551, "global_step": 370310, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.075261354446411, "global_step": 370311, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0132241249084473, "global_step": 370312, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1751644611358643, "global_step": 370313, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.042080879211426, "global_step": 370314, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.2002363204956055, "global_step": 370315, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1281003952026367, "global_step": 370316, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0945916175842285, "global_step": 370317, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.9806491136550903, "global_step": 370318, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.11122989654541, "global_step": 370319, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1196744441986084, "global_step": 370320, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.075076103210449, "global_step": 370321, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0784409046173096, "global_step": 370322, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.152919292449951, "global_step": 370323, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0214037895202637, "global_step": 370324, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0796680450439453, "global_step": 370325, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0232131481170654, "global_step": 370326, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.069258451461792, "global_step": 370327, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.081098794937134, "global_step": 370328, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1196579933166504, "global_step": 370329, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.091484308242798, "global_step": 370330, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.111387252807617, "global_step": 370331, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1985082626342773, "global_step": 370332, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0230343341827393, "global_step": 370333, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1422321796417236, "global_step": 370334, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1145706176757812, "global_step": 370335, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1180331707000732, "global_step": 370336, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.145906448364258, "global_step": 370337, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.212641477584839, "global_step": 370338, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0619962215423584, "global_step": 370339, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.124436616897583, "global_step": 370340, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.126225233078003, "global_step": 370341, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1814277172088623, "global_step": 370342, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.083672046661377, "global_step": 370343, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.094240188598633, "global_step": 370344, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1111011505126953, "global_step": 370345, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1287617683410645, "global_step": 370346, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0989489555358887, "global_step": 370347, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.114731788635254, "global_step": 370348, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.064568042755127, "global_step": 370349, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1683332920074463, "global_step": 370350, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1041157245635986, "global_step": 370351, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1304683685302734, "global_step": 370352, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0677847862243652, "global_step": 370353, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.089700698852539, "global_step": 370354, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0938732624053955, "global_step": 370355, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.008723735809326, "global_step": 370356, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.051954507827759, "global_step": 370357, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1184909343719482, "global_step": 370358, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0819966793060303, "global_step": 370359, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.2112185955047607, "global_step": 370360, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.089508533477783, "global_step": 370361, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0881149768829346, "global_step": 370362, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.11710786819458, "global_step": 370363, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1278560161590576, "global_step": 370364, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0825774669647217, "global_step": 370365, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1132278442382812, "global_step": 370366, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1117665767669678, "global_step": 370367, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.2215847969055176, "global_step": 370368, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.9994349479675293, "global_step": 370369, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.079829454421997, "global_step": 370370, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.032118082046509, "global_step": 370371, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1496474742889404, "global_step": 370372, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.073071002960205, "global_step": 370373, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.131629467010498, "global_step": 370374, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1121082305908203, "global_step": 370375, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1094751358032227, "global_step": 370376, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0905699729919434, "global_step": 370377, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.041426181793213, "global_step": 370378, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.11599063873291, "global_step": 370379, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.204859972000122, "global_step": 370380, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1005141735076904, "global_step": 370381, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.097599506378174, "global_step": 370382, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0379912853240967, "global_step": 370383, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0710527896881104, "global_step": 370384, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0806190967559814, "global_step": 370385, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.052177667617798, "global_step": 370386, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1020302772521973, "global_step": 370387, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.207122802734375, "global_step": 370388, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.018327236175537, "global_step": 370389, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.074699640274048, "global_step": 370390, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0858314037323, "global_step": 370391, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.039613723754883, "global_step": 370392, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.9956609010696411, "global_step": 370393, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.17960262298584, "global_step": 370394, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0762124061584473, "global_step": 370395, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0515503883361816, "global_step": 370396, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0711464881896973, "global_step": 370397, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.086721420288086, "global_step": 370398, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.116062879562378, "global_step": 370399, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0555057525634766, "global_step": 370400, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.064316987991333, "global_step": 370401, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.05492901802063, "global_step": 370402, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.088205575942993, "global_step": 370403, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.114833354949951, "global_step": 370404, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.218780994415283, "global_step": 370405, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1931838989257812, "global_step": 370406, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.102848529815674, "global_step": 370407, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.100144863128662, "global_step": 370408, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.105186939239502, "global_step": 370409, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1222996711730957, "global_step": 370410, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.161161184310913, "global_step": 370411, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0917294025421143, "global_step": 370412, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.114362955093384, "global_step": 370413, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1263587474823, "global_step": 370414, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.126469850540161, "global_step": 370415, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0839052200317383, "global_step": 370416, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1365602016448975, "global_step": 370417, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0536017417907715, "global_step": 370418, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.05110239982605, "global_step": 370419, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0598080158233643, "global_step": 370420, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1234130859375, "global_step": 370421, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.10210919380188, "global_step": 370422, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1681299209594727, "global_step": 370423, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.9759576320648193, "global_step": 370424, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0618720054626465, "global_step": 370425, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.058685064315796, "global_step": 370426, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.09224009513855, "global_step": 370427, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0493531227111816, "global_step": 370428, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.021028995513916, "global_step": 370429, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.2081034183502197, "global_step": 370430, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0911147594451904, "global_step": 370431, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.077150583267212, "global_step": 370432, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1559886932373047, "global_step": 370433, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0185439586639404, "global_step": 370434, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.043440818786621, "global_step": 370435, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.17667555809021, "global_step": 370436, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0759503841400146, "global_step": 370437, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.125727653503418, "global_step": 370438, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.046987533569336, "global_step": 370439, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1408607959747314, "global_step": 370440, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0327751636505127, "global_step": 370441, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.181892156600952, "global_step": 370442, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.2103922367095947, "global_step": 370443, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.077375650405884, "global_step": 370444, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.064802408218384, "global_step": 370445, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.141955852508545, "global_step": 370446, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0864949226379395, "global_step": 370447, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.114036798477173, "global_step": 370448, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.123950242996216, "global_step": 370449, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0949795246124268, "global_step": 370450, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1519782543182373, "global_step": 370451, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.14389705657959, "global_step": 370452, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1468255519866943, "global_step": 370453, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.050097942352295, "global_step": 370454, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.132593870162964, "global_step": 370455, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0340447425842285, "global_step": 370456, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1330583095550537, "global_step": 370457, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1148276329040527, "global_step": 370458, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0346884727478027, "global_step": 370459, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.039578437805176, "global_step": 370460, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.094074249267578, "global_step": 370461, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.947542428970337, "global_step": 370462, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.129791498184204, "global_step": 370463, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.9954557418823242, "global_step": 370464, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.103978395462036, "global_step": 370465, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.06445050239563, "global_step": 370466, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.147773265838623, "global_step": 370467, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0478856563568115, "global_step": 370468, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0136501789093018, "global_step": 370469, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.9861924648284912, "global_step": 370470, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.089169502258301, "global_step": 370471, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1144070625305176, "global_step": 370472, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1203250885009766, "global_step": 370473, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1044065952301025, "global_step": 370474, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.085545063018799, "global_step": 370475, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0969161987304688, "global_step": 370476, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.052896022796631, "global_step": 370477, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0763096809387207, "global_step": 370478, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1110572814941406, "global_step": 370479, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1567718982696533, "global_step": 370480, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0595598220825195, "global_step": 370481, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1257550716400146, "global_step": 370482, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0560972690582275, "global_step": 370483, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1934006214141846, "global_step": 370484, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.130246877670288, "global_step": 370485, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1384308338165283, "global_step": 370486, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.009953260421753, "global_step": 370487, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0865397453308105, "global_step": 370488, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.040750026702881, "global_step": 370489, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1029999256134033, "global_step": 370490, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.081202268600464, "global_step": 370491, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.108290433883667, "global_step": 370492, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.099943161010742, "global_step": 370493, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.121286392211914, "global_step": 370494, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0386576652526855, "global_step": 370495, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0501322746276855, "global_step": 370496, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.102800130844116, "global_step": 370497, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.2081518173217773, "global_step": 370498, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.135336399078369, "global_step": 370499, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.11507248878479, "global_step": 370500, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.091900587081909, "global_step": 370501, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0914523601531982, "global_step": 370502, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1264681816101074, "global_step": 370503, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1678884029388428, "global_step": 370504, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.12776517868042, "global_step": 370505, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1219279766082764, "global_step": 370506, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.007467031478882, "global_step": 370507, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.03843092918396, "global_step": 370508, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.2098169326782227, "global_step": 370509, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0728063583374023, "global_step": 370510, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1292269229888916, "global_step": 370511, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0924644470214844, "global_step": 370512, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1146857738494873, "global_step": 370513, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.152014970779419, "global_step": 370514, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0802512168884277, "global_step": 370515, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1775245666503906, "global_step": 370516, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.122002601623535, "global_step": 370517, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.9944655895233154, "global_step": 370518, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.9833906888961792, "global_step": 370519, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1387040615081787, "global_step": 370520, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.072962760925293, "global_step": 370521, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0530781745910645, "global_step": 370522, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1592063903808594, "global_step": 370523, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.120293617248535, "global_step": 370524, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.160303831100464, "global_step": 370525, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0113492012023926, "global_step": 370526, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1499884128570557, "global_step": 370527, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.070171356201172, "global_step": 370528, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1409711837768555, "global_step": 370529, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.062802314758301, "global_step": 370530, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.177992820739746, "global_step": 370531, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.026517152786255, "global_step": 370532, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1012473106384277, "global_step": 370533, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.239980697631836, "global_step": 370534, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0729012489318848, "global_step": 370535, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1402993202209473, "global_step": 370536, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.069692850112915, "global_step": 370537, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1222333908081055, "global_step": 370538, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0986037254333496, "global_step": 370539, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0931053161621094, "global_step": 370540, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0834834575653076, "global_step": 370541, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.9907872676849365, "global_step": 370542, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1120827198028564, "global_step": 370543, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1876087188720703, "global_step": 370544, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.155900716781616, "global_step": 370545, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.016446828842163, "global_step": 370546, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0352532863616943, "global_step": 370547, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0900967121124268, "global_step": 370548, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0571448802948, "global_step": 370549, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.135432243347168, "global_step": 370550, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.129626512527466, "global_step": 370551, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.049586772918701, "global_step": 370552, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.082765579223633, "global_step": 370553, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0875844955444336, "global_step": 370554, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1080336570739746, "global_step": 370555, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0802159309387207, "global_step": 370556, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.117459535598755, "global_step": 370557, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.9879835844039917, "global_step": 370558, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0276925563812256, "global_step": 370559, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1570470333099365, "global_step": 370560, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1203222274780273, "global_step": 370561, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1550755500793457, "global_step": 370562, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1199967861175537, "global_step": 370563, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1286847591400146, "global_step": 370564, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.171229124069214, "global_step": 370565, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.084564685821533, "global_step": 370566, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0827138423919678, "global_step": 370567, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0964343547821045, "global_step": 370568, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0618832111358643, "global_step": 370569, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.135601043701172, "global_step": 370570, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1067326068878174, "global_step": 370571, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1238553524017334, "global_step": 370572, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0709850788116455, "global_step": 370573, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0674867630004883, "global_step": 370574, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1479549407958984, "global_step": 370575, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1991617679595947, "global_step": 370576, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0633671283721924, "global_step": 370577, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1971442699432373, "global_step": 370578, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0220580101013184, "global_step": 370579, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0564053058624268, "global_step": 370580, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1970374584198, "global_step": 370581, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1738908290863037, "global_step": 370582, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.070819616317749, "global_step": 370583, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.134561061859131, "global_step": 370584, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.9675648212432861, "global_step": 370585, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.088599443435669, "global_step": 370586, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.2256767749786377, "global_step": 370587, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.2149264812469482, "global_step": 370588, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1000256538391113, "global_step": 370589, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1755001544952393, "global_step": 370590, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1212403774261475, "global_step": 370591, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.14190673828125, "global_step": 370592, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1020469665527344, "global_step": 370593, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.100625514984131, "global_step": 370594, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0457265377044678, "global_step": 370595, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0678462982177734, "global_step": 370596, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0553603172302246, "global_step": 370597, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1627588272094727, "global_step": 370598, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.109656572341919, "global_step": 370599, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0670711994171143, "global_step": 370600, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.121610641479492, "global_step": 370601, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.199512004852295, "global_step": 370602, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0666725635528564, "global_step": 370603, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.140505313873291, "global_step": 370604, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.043020248413086, "global_step": 370605, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.124202251434326, "global_step": 370606, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.102860689163208, "global_step": 370607, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.142455816268921, "global_step": 370608, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.132422924041748, "global_step": 370609, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1524534225463867, "global_step": 370610, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0908212661743164, "global_step": 370611, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1581504344940186, "global_step": 370612, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.12458872795105, "global_step": 370613, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1583032608032227, "global_step": 370614, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.066833257675171, "global_step": 370615, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.060716152191162, "global_step": 370616, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1407737731933594, "global_step": 370617, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.07991623878479, "global_step": 370618, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.115882158279419, "global_step": 370619, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0682451725006104, "global_step": 370620, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1088039875030518, "global_step": 370621, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1714935302734375, "global_step": 370622, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.080543279647827, "global_step": 370623, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.09041690826416, "global_step": 370624, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.080873966217041, "global_step": 370625, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1897318363189697, "global_step": 370626, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.059666872024536, "global_step": 370627, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.091568946838379, "global_step": 370628, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.097803831100464, "global_step": 370629, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.065983533859253, "global_step": 370630, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0988590717315674, "global_step": 370631, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1212992668151855, "global_step": 370632, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.14048171043396, "global_step": 370633, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.076972007751465, "global_step": 370634, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0509729385375977, "global_step": 370635, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0359110832214355, "global_step": 370636, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1397228240966797, "global_step": 370637, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1301820278167725, "global_step": 370638, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.109297513961792, "global_step": 370639, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.079634666442871, "global_step": 370640, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.037599802017212, "global_step": 370641, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.090982437133789, "global_step": 370642, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0634186267852783, "global_step": 370643, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0573251247406006, "global_step": 370644, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1530981063842773, "global_step": 370645, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.034282922744751, "global_step": 370646, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.192680835723877, "global_step": 370647, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0964391231536865, "global_step": 370648, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1034610271453857, "global_step": 370649, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.175442934036255, "global_step": 370650, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1017820835113525, "global_step": 370651, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.127962112426758, "global_step": 370652, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1516923904418945, "global_step": 370653, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0486392974853516, "global_step": 370654, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.098989725112915, "global_step": 370655, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1427605152130127, "global_step": 370656, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0910627841949463, "global_step": 370657, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1283304691314697, "global_step": 370658, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.032600164413452, "global_step": 370659, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.129338026046753, "global_step": 370660, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1815743446350098, "global_step": 370661, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0619359016418457, "global_step": 370662, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1549885272979736, "global_step": 370663, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.088477611541748, "global_step": 370664, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.103036403656006, "global_step": 370665, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.127106189727783, "global_step": 370666, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1371097564697266, "global_step": 370667, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.020313024520874, "global_step": 370668, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1183512210845947, "global_step": 370669, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.086156129837036, "global_step": 370670, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0631368160247803, "global_step": 370671, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.147327184677124, "global_step": 370672, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.163600206375122, "global_step": 370673, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.067138195037842, "global_step": 370674, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1017887592315674, "global_step": 370675, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.122954845428467, "global_step": 370676, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.168381929397583, "global_step": 370677, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.077092170715332, "global_step": 370678, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.194585084915161, "global_step": 370679, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.091641902923584, "global_step": 370680, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0927610397338867, "global_step": 370681, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.024332284927368, "global_step": 370682, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1071090698242188, "global_step": 370683, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0882151126861572, "global_step": 370684, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1865627765655518, "global_step": 370685, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1005265712738037, "global_step": 370686, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0405807495117188, "global_step": 370687, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.187103271484375, "global_step": 370688, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0975446701049805, "global_step": 370689, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1166350841522217, "global_step": 370690, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1773910522460938, "global_step": 370691, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.2469840049743652, "global_step": 370692, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.072330951690674, "global_step": 370693, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.118896007537842, "global_step": 370694, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.098562717437744, "global_step": 370695, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0828166007995605, "global_step": 370696, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.122641086578369, "global_step": 370697, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.071176052093506, "global_step": 370698, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.149174928665161, "global_step": 370699, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.088059902191162, "global_step": 370700, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0862324237823486, "global_step": 370701, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.064149856567383, "global_step": 370702, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1326756477355957, "global_step": 370703, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.144697666168213, "global_step": 370704, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.074542760848999, "global_step": 370705, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.151338577270508, "global_step": 370706, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0276103019714355, "global_step": 370707, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1327064037323, "global_step": 370708, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.188931465148926, "global_step": 370709, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1309733390808105, "global_step": 370710, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.160121440887451, "global_step": 370711, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.105952024459839, "global_step": 370712, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.136230707168579, "global_step": 370713, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.15252423286438, "global_step": 370714, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1576874256134033, "global_step": 370715, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.090073347091675, "global_step": 370716, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1048765182495117, "global_step": 370717, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.075120210647583, "global_step": 370718, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.083439350128174, "global_step": 370719, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.030118703842163, "global_step": 370720, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.131882667541504, "global_step": 370721, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1195225715637207, "global_step": 370722, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1495609283447266, "global_step": 370723, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.108966827392578, "global_step": 370724, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.2112815380096436, "global_step": 370725, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0817744731903076, "global_step": 370726, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.092841386795044, "global_step": 370727, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.128267288208008, "global_step": 370728, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.115685224533081, "global_step": 370729, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0161690711975098, "global_step": 370730, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.112957000732422, "global_step": 370731, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.141239881515503, "global_step": 370732, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.162724733352661, "global_step": 370733, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.117107391357422, "global_step": 370734, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0183353424072266, "global_step": 370735, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0369956493377686, "global_step": 370736, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1287829875946045, "global_step": 370737, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.157728672027588, "global_step": 370738, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0571584701538086, "global_step": 370739, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1183390617370605, "global_step": 370740, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1790530681610107, "global_step": 370741, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.146549701690674, "global_step": 370742, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1514651775360107, "global_step": 370743, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0542755126953125, "global_step": 370744, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0493133068084717, "global_step": 370745, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.142857789993286, "global_step": 370746, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.163393974304199, "global_step": 370747, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.12258243560791, "global_step": 370748, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.007009506225586, "global_step": 370749, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0549850463867188, "global_step": 370750, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1369824409484863, "global_step": 370751, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.096339464187622, "global_step": 370752, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0404350757598877, "global_step": 370753, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.172335624694824, "global_step": 370754, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.116447687149048, "global_step": 370755, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1030635833740234, "global_step": 370756, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0668840408325195, "global_step": 370757, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0986790657043457, "global_step": 370758, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.051602602005005, "global_step": 370759, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.090402603149414, "global_step": 370760, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1398367881774902, "global_step": 370761, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.079432725906372, "global_step": 370762, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1172518730163574, "global_step": 370763, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0553245544433594, "global_step": 370764, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1317152976989746, "global_step": 370765, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.232433795928955, "global_step": 370766, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1173558235168457, "global_step": 370767, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0299057960510254, "global_step": 370768, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.133681297302246, "global_step": 370769, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.109113931655884, "global_step": 370770, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0875070095062256, "global_step": 370771, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0894241333007812, "global_step": 370772, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.175232410430908, "global_step": 370773, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.144235610961914, "global_step": 370774, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.109076738357544, "global_step": 370775, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1825380325317383, "global_step": 370776, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1103413105010986, "global_step": 370777, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1478865146636963, "global_step": 370778, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.150066614151001, "global_step": 370779, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.083031177520752, "global_step": 370780, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1329731941223145, "global_step": 370781, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.095116138458252, "global_step": 370782, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0662055015563965, "global_step": 370783, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1691887378692627, "global_step": 370784, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.145029306411743, "global_step": 370785, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0873301029205322, "global_step": 370786, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.147157907485962, "global_step": 370787, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.018937349319458, "global_step": 370788, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0447072982788086, "global_step": 370789, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.098205327987671, "global_step": 370790, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0703518390655518, "global_step": 370791, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0499696731567383, "global_step": 370792, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.061387062072754, "global_step": 370793, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1526405811309814, "global_step": 370794, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0708394050598145, "global_step": 370795, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.038628339767456, "global_step": 370796, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1329891681671143, "global_step": 370797, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0435688495635986, "global_step": 370798, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.084956407546997, "global_step": 370799, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.128002166748047, "global_step": 370800, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.097970485687256, "global_step": 370801, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0989701747894287, "global_step": 370802, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.048215389251709, "global_step": 370803, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.047420024871826, "global_step": 370804, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0560190677642822, "global_step": 370805, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.150284767150879, "global_step": 370806, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.080944776535034, "global_step": 370807, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1141252517700195, "global_step": 370808, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.14785099029541, "global_step": 370809, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1324503421783447, "global_step": 370810, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1667962074279785, "global_step": 370811, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.064728021621704, "global_step": 370812, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.127760410308838, "global_step": 370813, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0705718994140625, "global_step": 370814, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0619921684265137, "global_step": 370815, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.197540521621704, "global_step": 370816, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.222721576690674, "global_step": 370817, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1618492603302, "global_step": 370818, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1042165756225586, "global_step": 370819, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.15051531791687, "global_step": 370820, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0071842670440674, "global_step": 370821, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.063845634460449, "global_step": 370822, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.171496629714966, "global_step": 370823, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.198702573776245, "global_step": 370824, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1280853748321533, "global_step": 370825, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.103513717651367, "global_step": 370826, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0535950660705566, "global_step": 370827, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0953924655914307, "global_step": 370828, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1396312713623047, "global_step": 370829, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0069127082824707, "global_step": 370830, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.103792428970337, "global_step": 370831, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.119260549545288, "global_step": 370832, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1353390216827393, "global_step": 370833, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0658445358276367, "global_step": 370834, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.996738314628601, "global_step": 370835, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1804983615875244, "global_step": 370836, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0312275886535645, "global_step": 370837, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.15584135055542, "global_step": 370838, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1076929569244385, "global_step": 370839, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.142124891281128, "global_step": 370840, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0670242309570312, "global_step": 370841, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.2004318237304688, "global_step": 370842, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1418838500976562, "global_step": 370843, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.22310471534729, "global_step": 370844, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1985323429107666, "global_step": 370845, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1291184425354004, "global_step": 370846, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.057837724685669, "global_step": 370847, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1418919563293457, "global_step": 370848, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.054628610610962, "global_step": 370849, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1111114025115967, "global_step": 370850, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.051304340362549, "global_step": 370851, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0798985958099365, "global_step": 370852, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.186953067779541, "global_step": 370853, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0989575386047363, "global_step": 370854, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1340980529785156, "global_step": 370855, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0914101600646973, "global_step": 370856, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0897130966186523, "global_step": 370857, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.149782419204712, "global_step": 370858, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0628762245178223, "global_step": 370859, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.040682554244995, "global_step": 370860, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1330909729003906, "global_step": 370861, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1626007556915283, "global_step": 370862, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.9998605251312256, "global_step": 370863, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1971635818481445, "global_step": 370864, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.126943826675415, "global_step": 370865, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.14011812210083, "global_step": 370866, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.025906562805176, "global_step": 370867, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.071664571762085, "global_step": 370868, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.051497220993042, "global_step": 370869, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.10587477684021, "global_step": 370870, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1265692710876465, "global_step": 370871, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1428463459014893, "global_step": 370872, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0921738147735596, "global_step": 370873, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1297168731689453, "global_step": 370874, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.060307025909424, "global_step": 370875, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.144094705581665, "global_step": 370876, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1221094131469727, "global_step": 370877, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.088679075241089, "global_step": 370878, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.107800245285034, "global_step": 370879, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1496798992156982, "global_step": 370880, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1465964317321777, "global_step": 370881, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0917375087738037, "global_step": 370882, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0981557369232178, "global_step": 370883, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0573618412017822, "global_step": 370884, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.038550615310669, "global_step": 370885, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0914700031280518, "global_step": 370886, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0330357551574707, "global_step": 370887, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1234397888183594, "global_step": 370888, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.068622350692749, "global_step": 370889, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0859291553497314, "global_step": 370890, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.093294858932495, "global_step": 370891, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.089984655380249, "global_step": 370892, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1886982917785645, "global_step": 370893, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.014798402786255, "global_step": 370894, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1961560249328613, "global_step": 370895, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0966122150421143, "global_step": 370896, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.027987241744995, "global_step": 370897, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.042983055114746, "global_step": 370898, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1347498893737793, "global_step": 370899, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.094531774520874, "global_step": 370900, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0562551021575928, "global_step": 370901, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1525771617889404, "global_step": 370902, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1320693492889404, "global_step": 370903, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.128469944000244, "global_step": 370904, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.130519390106201, "global_step": 370905, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.084831476211548, "global_step": 370906, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0599215030670166, "global_step": 370907, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1346383094787598, "global_step": 370908, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0380680561065674, "global_step": 370909, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1314077377319336, "global_step": 370910, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0377402305603027, "global_step": 370911, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.094998598098755, "global_step": 370912, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.090475559234619, "global_step": 370913, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0205047130584717, "global_step": 370914, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0882019996643066, "global_step": 370915, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1046841144561768, "global_step": 370916, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0832102298736572, "global_step": 370917, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1004409790039062, "global_step": 370918, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1396327018737793, "global_step": 370919, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1697840690612793, "global_step": 370920, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.041170358657837, "global_step": 370921, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.156480073928833, "global_step": 370922, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.177090883255005, "global_step": 370923, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1218574047088623, "global_step": 370924, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.161135673522949, "global_step": 370925, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1098978519439697, "global_step": 370926, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0982673168182373, "global_step": 370927, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.089244842529297, "global_step": 370928, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.122770309448242, "global_step": 370929, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0374484062194824, "global_step": 370930, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1855931282043457, "global_step": 370931, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0927610397338867, "global_step": 370932, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.172943353652954, "global_step": 370933, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0944230556488037, "global_step": 370934, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.11535382270813, "global_step": 370935, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.062877893447876, "global_step": 370936, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.9517135620117188, "global_step": 370937, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0976459980010986, "global_step": 370938, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0910327434539795, "global_step": 370939, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0824108123779297, "global_step": 370940, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.183199644088745, "global_step": 370941, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.136291980743408, "global_step": 370942, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0196714401245117, "global_step": 370943, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0405144691467285, "global_step": 370944, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.079744577407837, "global_step": 370945, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.148092746734619, "global_step": 370946, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.071897268295288, "global_step": 370947, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0573973655700684, "global_step": 370948, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1473793983459473, "global_step": 370949, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.147925853729248, "global_step": 370950, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.108860731124878, "global_step": 370951, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.094393253326416, "global_step": 370952, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1176717281341553, "global_step": 370953, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.185127019882202, "global_step": 370954, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1020150184631348, "global_step": 370955, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.170192003250122, "global_step": 370956, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0669407844543457, "global_step": 370957, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0699267387390137, "global_step": 370958, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1053478717803955, "global_step": 370959, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.152148723602295, "global_step": 370960, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.2066891193389893, "global_step": 370961, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.085184097290039, "global_step": 370962, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.110654830932617, "global_step": 370963, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1256697177886963, "global_step": 370964, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1282544136047363, "global_step": 370965, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0981552600860596, "global_step": 370966, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1340126991271973, "global_step": 370967, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1468019485473633, "global_step": 370968, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1029183864593506, "global_step": 370969, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0809223651885986, "global_step": 370970, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0793533325195312, "global_step": 370971, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1368231773376465, "global_step": 370972, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.074108123779297, "global_step": 370973, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0497496128082275, "global_step": 370974, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0848851203918457, "global_step": 370975, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.069326877593994, "global_step": 370976, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.113152027130127, "global_step": 370977, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1036999225616455, "global_step": 370978, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1963694095611572, "global_step": 370979, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1623289585113525, "global_step": 370980, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.2267370223999023, "global_step": 370981, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1333258152008057, "global_step": 370982, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.069178819656372, "global_step": 370983, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1709299087524414, "global_step": 370984, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1516401767730713, "global_step": 370985, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.054877758026123, "global_step": 370986, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.116957426071167, "global_step": 370987, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.042386054992676, "global_step": 370988, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0884430408477783, "global_step": 370989, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.180023431777954, "global_step": 370990, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0908336639404297, "global_step": 370991, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1212198734283447, "global_step": 370992, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.090801477432251, "global_step": 370993, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.170034646987915, "global_step": 370994, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0842483043670654, "global_step": 370995, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.09383225440979, "global_step": 370996, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0535166263580322, "global_step": 370997, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0758919715881348, "global_step": 370998, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.00036358833313, "global_step": 370999, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.156414270401001, "global_step": 371000, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.066704273223877, "global_step": 371001, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.146191120147705, "global_step": 371002, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0475776195526123, "global_step": 371003, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0763752460479736, "global_step": 371004, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1805877685546875, "global_step": 371005, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0492570400238037, "global_step": 371006, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0617148876190186, "global_step": 371007, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0440280437469482, "global_step": 371008, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1979143619537354, "global_step": 371009, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1966238021850586, "global_step": 371010, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1282436847686768, "global_step": 371011, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1259212493896484, "global_step": 371012, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0596909523010254, "global_step": 371013, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1291074752807617, "global_step": 371014, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1114509105682373, "global_step": 371015, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1242003440856934, "global_step": 371016, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0283732414245605, "global_step": 371017, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0836000442504883, "global_step": 371018, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.212068796157837, "global_step": 371019, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0888848304748535, "global_step": 371020, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.162459135055542, "global_step": 371021, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1226260662078857, "global_step": 371022, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1418044567108154, "global_step": 371023, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0785024166107178, "global_step": 371024, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1544251441955566, "global_step": 371025, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.094223737716675, "global_step": 371026, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0568017959594727, "global_step": 371027, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1635255813598633, "global_step": 371028, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1313138008117676, "global_step": 371029, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.013207197189331, "global_step": 371030, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1145925521850586, "global_step": 371031, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1678075790405273, "global_step": 371032, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.103410482406616, "global_step": 371033, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0392181873321533, "global_step": 371034, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.079481601715088, "global_step": 371035, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.185779333114624, "global_step": 371036, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.056112051010132, "global_step": 371037, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.058401584625244, "global_step": 371038, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.15710186958313, "global_step": 371039, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0991594791412354, "global_step": 371040, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.093820095062256, "global_step": 371041, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.130472421646118, "global_step": 371042, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.144425868988037, "global_step": 371043, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1021792888641357, "global_step": 371044, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1215169429779053, "global_step": 371045, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1157591342926025, "global_step": 371046, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.195199966430664, "global_step": 371047, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0859556198120117, "global_step": 371048, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1175448894500732, "global_step": 371049, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.2284445762634277, "global_step": 371050, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1734089851379395, "global_step": 371051, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.19753098487854, "global_step": 371052, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.991374135017395, "global_step": 371053, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1915111541748047, "global_step": 371054, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1172938346862793, "global_step": 371055, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.160212993621826, "global_step": 371056, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0342822074890137, "global_step": 371057, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.12265682220459, "global_step": 371058, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.2081491947174072, "global_step": 371059, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.255403995513916, "global_step": 371060, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0102787017822266, "global_step": 371061, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1543221473693848, "global_step": 371062, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.156221628189087, "global_step": 371063, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.063610792160034, "global_step": 371064, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.07454514503479, "global_step": 371065, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.254910469055176, "global_step": 371066, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0898537635803223, "global_step": 371067, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1507742404937744, "global_step": 371068, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1635735034942627, "global_step": 371069, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0694897174835205, "global_step": 371070, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.07606840133667, "global_step": 371071, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.038663148880005, "global_step": 371072, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0533981323242188, "global_step": 371073, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1150035858154297, "global_step": 371074, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1397268772125244, "global_step": 371075, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1301426887512207, "global_step": 371076, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.039538621902466, "global_step": 371077, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1128616333007812, "global_step": 371078, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.112527370452881, "global_step": 371079, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1654858589172363, "global_step": 371080, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1292335987091064, "global_step": 371081, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.076446533203125, "global_step": 371082, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.004591226577759, "global_step": 371083, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1089651584625244, "global_step": 371084, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1040215492248535, "global_step": 371085, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.09405255317688, "global_step": 371086, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.2221570014953613, "global_step": 371087, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.142432928085327, "global_step": 371088, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0625600814819336, "global_step": 371089, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1655304431915283, "global_step": 371090, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0993411540985107, "global_step": 371091, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0850188732147217, "global_step": 371092, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.11753511428833, "global_step": 371093, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1032276153564453, "global_step": 371094, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0391783714294434, "global_step": 371095, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.081836462020874, "global_step": 371096, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1984918117523193, "global_step": 371097, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.085145950317383, "global_step": 371098, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0446197986602783, "global_step": 371099, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.159205436706543, "global_step": 371100, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1954195499420166, "global_step": 371101, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.137920618057251, "global_step": 371102, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.9828228950500488, "global_step": 371103, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.098268747329712, "global_step": 371104, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1168830394744873, "global_step": 371105, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1661078929901123, "global_step": 371106, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.110297679901123, "global_step": 371107, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0580520629882812, "global_step": 371108, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.073474168777466, "global_step": 371109, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.057677984237671, "global_step": 371110, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.050553798675537, "global_step": 371111, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0998473167419434, "global_step": 371112, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1274752616882324, "global_step": 371113, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1342227458953857, "global_step": 371114, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0466811656951904, "global_step": 371115, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.106661319732666, "global_step": 371116, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1006832122802734, "global_step": 371117, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.033764600753784, "global_step": 371118, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0868163108825684, "global_step": 371119, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.177332878112793, "global_step": 371120, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.2080986499786377, "global_step": 371121, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.097236156463623, "global_step": 371122, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.074395179748535, "global_step": 371123, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.2178642749786377, "global_step": 371124, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1227355003356934, "global_step": 371125, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0254852771759033, "global_step": 371126, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.079204559326172, "global_step": 371127, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1036479473114014, "global_step": 371128, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.178375244140625, "global_step": 371129, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1770734786987305, "global_step": 371130, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.106282949447632, "global_step": 371131, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0754904747009277, "global_step": 371132, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1394007205963135, "global_step": 371133, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0100669860839844, "global_step": 371134, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0670666694641113, "global_step": 371135, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.147329807281494, "global_step": 371136, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.107431650161743, "global_step": 371137, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.180600166320801, "global_step": 371138, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1035003662109375, "global_step": 371139, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1032471656799316, "global_step": 371140, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.06007719039917, "global_step": 371141, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0838868618011475, "global_step": 371142, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.199881076812744, "global_step": 371143, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.035006523132324, "global_step": 371144, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.097428798675537, "global_step": 371145, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.204218864440918, "global_step": 371146, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1905391216278076, "global_step": 371147, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.063499689102173, "global_step": 371148, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.094679355621338, "global_step": 371149, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.130281925201416, "global_step": 371150, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1184823513031006, "global_step": 371151, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1394639015197754, "global_step": 371152, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0779104232788086, "global_step": 371153, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.19204044342041, "global_step": 371154, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1098484992980957, "global_step": 371155, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1139559745788574, "global_step": 371156, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1320250034332275, "global_step": 371157, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.153170347213745, "global_step": 371158, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.134430170059204, "global_step": 371159, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.122438669204712, "global_step": 371160, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.07088041305542, "global_step": 371161, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1204802989959717, "global_step": 371162, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0460641384124756, "global_step": 371163, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.194234609603882, "global_step": 371164, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1070914268493652, "global_step": 371165, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.06087064743042, "global_step": 371166, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1417603492736816, "global_step": 371167, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.173157215118408, "global_step": 371168, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1777243614196777, "global_step": 371169, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.074317216873169, "global_step": 371170, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.085561990737915, "global_step": 371171, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1018073558807373, "global_step": 371172, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0226340293884277, "global_step": 371173, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1354780197143555, "global_step": 371174, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0720112323760986, "global_step": 371175, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0764479637145996, "global_step": 371176, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.090773105621338, "global_step": 371177, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1979191303253174, "global_step": 371178, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.170335054397583, "global_step": 371179, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.025115728378296, "global_step": 371180, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1701560020446777, "global_step": 371181, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.072108507156372, "global_step": 371182, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.133690357208252, "global_step": 371183, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.085452079772949, "global_step": 371184, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1455423831939697, "global_step": 371185, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.9748345613479614, "global_step": 371186, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.155278205871582, "global_step": 371187, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1186141967773438, "global_step": 371188, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1693649291992188, "global_step": 371189, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.187333822250366, "global_step": 371190, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.162930965423584, "global_step": 371191, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1211016178131104, "global_step": 371192, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1481194496154785, "global_step": 371193, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0754244327545166, "global_step": 371194, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0824472904205322, "global_step": 371195, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.14734148979187, "global_step": 371196, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.123650074005127, "global_step": 371197, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.136721611022949, "global_step": 371198, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.968298077583313, "global_step": 371199, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1411375999450684, "global_step": 371200, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1327402591705322, "global_step": 371201, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1129939556121826, "global_step": 371202, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0952343940734863, "global_step": 371203, "epoch": 732, "lr": 5e-05}
{"train_loss": 1.9880222082138062, "global_step": 371204, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.133035182952881, "global_step": 371205, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0583062171936035, "global_step": 371206, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.207561492919922, "global_step": 371207, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1071743965148926, "global_step": 371208, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.100168228149414, "global_step": 371209, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1171367168426514, "global_step": 371210, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.109980821609497, "global_step": 371211, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1170201301574707, "global_step": 371212, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.019582748413086, "global_step": 371213, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1562418937683105, "global_step": 371214, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1023619174957275, "global_step": 371215, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.127289056777954, "global_step": 371216, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1364481449127197, "global_step": 371217, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.034369468688965, "global_step": 371218, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1842212677001953, "global_step": 371219, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.157447576522827, "global_step": 371220, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.061843156814575, "global_step": 371221, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.124738931655884, "global_step": 371222, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1429362297058105, "global_step": 371223, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1143100261688232, "global_step": 371224, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1637485027313232, "global_step": 371225, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.154778003692627, "global_step": 371226, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.087663412094116, "global_step": 371227, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.164949893951416, "global_step": 371228, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1449759006500244, "global_step": 371229, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0906574726104736, "global_step": 371230, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1470558643341064, "global_step": 371231, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.195803642272949, "global_step": 371232, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.077204465866089, "global_step": 371233, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.152632713317871, "global_step": 371234, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1267573833465576, "global_step": 371235, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.237823724746704, "global_step": 371236, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1640465259552, "global_step": 371237, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.119936227798462, "global_step": 371238, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1591689586639404, "global_step": 371239, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.115452289581299, "global_step": 371240, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.120403289794922, "global_step": 371241, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0342421531677246, "global_step": 371242, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.093763589859009, "global_step": 371243, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.16896653175354, "global_step": 371244, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.118187665939331, "global_step": 371245, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0892410278320312, "global_step": 371246, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1336183547973633, "global_step": 371247, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.08052134513855, "global_step": 371248, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0783779621124268, "global_step": 371249, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1069753170013428, "global_step": 371250, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.117694139480591, "global_step": 371251, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.151008367538452, "global_step": 371252, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1235499382019043, "global_step": 371253, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0742344856262207, "global_step": 371254, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1275699138641357, "global_step": 371255, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.0759685039520264, "global_step": 371256, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1199238300323486, "global_step": 371257, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.07470703125, "global_step": 371258, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1064090728759766, "global_step": 371259, "epoch": 732, "lr": 5e-05}
{"train_loss": 2.1887898445129395, "global_step": 371260, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.046236276626587, "global_step": 371261, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0325992107391357, "global_step": 371262, "epoch": 733, "lr": 5e-05}
{"train_loss": 1.9869884252548218, "global_step": 371263, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1318247318267822, "global_step": 371264, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1099178791046143, "global_step": 371265, "epoch": 733, "lr": 5e-05}
{"train_loss": 1.9873661994934082, "global_step": 371266, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.079002618789673, "global_step": 371267, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.174788475036621, "global_step": 371268, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0938663482666016, "global_step": 371269, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.131423234939575, "global_step": 371270, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.10217022895813, "global_step": 371271, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.028728485107422, "global_step": 371272, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1071598529815674, "global_step": 371273, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.172786235809326, "global_step": 371274, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.041861057281494, "global_step": 371275, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.175508499145508, "global_step": 371276, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0817246437072754, "global_step": 371277, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0707106590270996, "global_step": 371278, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.081392765045166, "global_step": 371279, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1468522548675537, "global_step": 371280, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.146143674850464, "global_step": 371281, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0955395698547363, "global_step": 371282, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.134690284729004, "global_step": 371283, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0856244564056396, "global_step": 371284, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.154249906539917, "global_step": 371285, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0715484619140625, "global_step": 371286, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0960354804992676, "global_step": 371287, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1193861961364746, "global_step": 371288, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.091953754425049, "global_step": 371289, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0678722858428955, "global_step": 371290, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.049299716949463, "global_step": 371291, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1634914875030518, "global_step": 371292, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.179246187210083, "global_step": 371293, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.00681734085083, "global_step": 371294, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.050060510635376, "global_step": 371295, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.019582986831665, "global_step": 371296, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1335809230804443, "global_step": 371297, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1435368061065674, "global_step": 371298, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0213520526885986, "global_step": 371299, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0940372943878174, "global_step": 371300, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0871379375457764, "global_step": 371301, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.06722354888916, "global_step": 371302, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.121350049972534, "global_step": 371303, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.061767816543579, "global_step": 371304, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0507450103759766, "global_step": 371305, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0567779541015625, "global_step": 371306, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.086712121963501, "global_step": 371307, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.074554204940796, "global_step": 371308, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1635730266571045, "global_step": 371309, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.151658535003662, "global_step": 371310, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.196582794189453, "global_step": 371311, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0295920372009277, "global_step": 371312, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1344213485717773, "global_step": 371313, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1493301391601562, "global_step": 371314, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1170525550842285, "global_step": 371315, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1449670791625977, "global_step": 371316, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.005103349685669, "global_step": 371317, "epoch": 733, "lr": 5e-05}
{"train_loss": 1.9920475482940674, "global_step": 371318, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1242055892944336, "global_step": 371319, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0910191535949707, "global_step": 371320, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1312122344970703, "global_step": 371321, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.162400245666504, "global_step": 371322, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1067981719970703, "global_step": 371323, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2278025150299072, "global_step": 371324, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.12522292137146, "global_step": 371325, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1041510105133057, "global_step": 371326, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.079402446746826, "global_step": 371327, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.137343168258667, "global_step": 371328, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1279184818267822, "global_step": 371329, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0914857387542725, "global_step": 371330, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0381662845611572, "global_step": 371331, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0701777935028076, "global_step": 371332, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.111168384552002, "global_step": 371333, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1304402351379395, "global_step": 371334, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0394036769866943, "global_step": 371335, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0339910984039307, "global_step": 371336, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0973517894744873, "global_step": 371337, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0458641052246094, "global_step": 371338, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0526199340820312, "global_step": 371339, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.069477081298828, "global_step": 371340, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0385727882385254, "global_step": 371341, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0714569091796875, "global_step": 371342, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.133718252182007, "global_step": 371343, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1428825855255127, "global_step": 371344, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.089418888092041, "global_step": 371345, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0867395401000977, "global_step": 371346, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.074904441833496, "global_step": 371347, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.141949415206909, "global_step": 371348, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.166116714477539, "global_step": 371349, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1531002521514893, "global_step": 371350, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1059787273406982, "global_step": 371351, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0156426429748535, "global_step": 371352, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1319401264190674, "global_step": 371353, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1101460456848145, "global_step": 371354, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.075401782989502, "global_step": 371355, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.106152057647705, "global_step": 371356, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.175855875015259, "global_step": 371357, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0770881175994873, "global_step": 371358, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.148667573928833, "global_step": 371359, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.091535806655884, "global_step": 371360, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.148146867752075, "global_step": 371361, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.087533473968506, "global_step": 371362, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0591766834259033, "global_step": 371363, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.110219717025757, "global_step": 371364, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1495676040649414, "global_step": 371365, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0640463829040527, "global_step": 371366, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0782878398895264, "global_step": 371367, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0441243648529053, "global_step": 371368, "epoch": 733, "lr": 5e-05}
{"train_loss": 1.9775753021240234, "global_step": 371369, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0434114933013916, "global_step": 371370, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.122157335281372, "global_step": 371371, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0937588214874268, "global_step": 371372, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.147172689437866, "global_step": 371373, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1177875995635986, "global_step": 371374, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1319470405578613, "global_step": 371375, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.017408847808838, "global_step": 371376, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.088245153427124, "global_step": 371377, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.11114501953125, "global_step": 371378, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.117142915725708, "global_step": 371379, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1267807483673096, "global_step": 371380, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1205475330352783, "global_step": 371381, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.096494674682617, "global_step": 371382, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.157041072845459, "global_step": 371383, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.080073833465576, "global_step": 371384, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0958855152130127, "global_step": 371385, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0852808952331543, "global_step": 371386, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0863454341888428, "global_step": 371387, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1462459564208984, "global_step": 371388, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.139195442199707, "global_step": 371389, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0733675956726074, "global_step": 371390, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.052992105484009, "global_step": 371391, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.139033079147339, "global_step": 371392, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1093528270721436, "global_step": 371393, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.029538869857788, "global_step": 371394, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0944364070892334, "global_step": 371395, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0938634872436523, "global_step": 371396, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0989420413970947, "global_step": 371397, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.06313419342041, "global_step": 371398, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.162095308303833, "global_step": 371399, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.094493865966797, "global_step": 371400, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.122351884841919, "global_step": 371401, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1028690338134766, "global_step": 371402, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0950753688812256, "global_step": 371403, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0650906562805176, "global_step": 371404, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1419739723205566, "global_step": 371405, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0798611640930176, "global_step": 371406, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.211852788925171, "global_step": 371407, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.079716205596924, "global_step": 371408, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0689942836761475, "global_step": 371409, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0470058917999268, "global_step": 371410, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0787370204925537, "global_step": 371411, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.034461259841919, "global_step": 371412, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.200186014175415, "global_step": 371413, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.130258560180664, "global_step": 371414, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1662261486053467, "global_step": 371415, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.094832420349121, "global_step": 371416, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.062946319580078, "global_step": 371417, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0739824771881104, "global_step": 371418, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.218698740005493, "global_step": 371419, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1763663291931152, "global_step": 371420, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.108201503753662, "global_step": 371421, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1983022689819336, "global_step": 371422, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1609275341033936, "global_step": 371423, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1633307933807373, "global_step": 371424, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1035847663879395, "global_step": 371425, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1108672618865967, "global_step": 371426, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.114067792892456, "global_step": 371427, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.148862600326538, "global_step": 371428, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.116812229156494, "global_step": 371429, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1089296340942383, "global_step": 371430, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1118810176849365, "global_step": 371431, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0231401920318604, "global_step": 371432, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.063227653503418, "global_step": 371433, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.065768241882324, "global_step": 371434, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.049347400665283, "global_step": 371435, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1249756813049316, "global_step": 371436, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.087263345718384, "global_step": 371437, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.065511703491211, "global_step": 371438, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0392396450042725, "global_step": 371439, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.035247802734375, "global_step": 371440, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0916738510131836, "global_step": 371441, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0791966915130615, "global_step": 371442, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0497028827667236, "global_step": 371443, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0807089805603027, "global_step": 371444, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.069185495376587, "global_step": 371445, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.077302932739258, "global_step": 371446, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.085171699523926, "global_step": 371447, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1785364151000977, "global_step": 371448, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1053478717803955, "global_step": 371449, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2065935134887695, "global_step": 371450, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0645902156829834, "global_step": 371451, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.14681339263916, "global_step": 371452, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1252379417419434, "global_step": 371453, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.099637746810913, "global_step": 371454, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.039511203765869, "global_step": 371455, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.117717981338501, "global_step": 371456, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0026490688323975, "global_step": 371457, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1720685958862305, "global_step": 371458, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1341540813446045, "global_step": 371459, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.081961154937744, "global_step": 371460, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1905674934387207, "global_step": 371461, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.104107618331909, "global_step": 371462, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.176901340484619, "global_step": 371463, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0592193603515625, "global_step": 371464, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0821757316589355, "global_step": 371465, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1651926040649414, "global_step": 371466, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1431775093078613, "global_step": 371467, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1482553482055664, "global_step": 371468, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.119838237762451, "global_step": 371469, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0745017528533936, "global_step": 371470, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2000863552093506, "global_step": 371471, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.079979419708252, "global_step": 371472, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.045003652572632, "global_step": 371473, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.040360927581787, "global_step": 371474, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1417949199676514, "global_step": 371475, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.014664888381958, "global_step": 371476, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1073157787323, "global_step": 371477, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1238973140716553, "global_step": 371478, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2156612873077393, "global_step": 371479, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.049705743789673, "global_step": 371480, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0519540309906006, "global_step": 371481, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.078321933746338, "global_step": 371482, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1355085372924805, "global_step": 371483, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.173391819000244, "global_step": 371484, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.119860887527466, "global_step": 371485, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.213127613067627, "global_step": 371486, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.080580711364746, "global_step": 371487, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1129372119903564, "global_step": 371488, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0584757328033447, "global_step": 371489, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.070000171661377, "global_step": 371490, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0899875164031982, "global_step": 371491, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.139866352081299, "global_step": 371492, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1296370029449463, "global_step": 371493, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.05924391746521, "global_step": 371494, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.106698989868164, "global_step": 371495, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0982205867767334, "global_step": 371496, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1011524200439453, "global_step": 371497, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.075284957885742, "global_step": 371498, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1368801593780518, "global_step": 371499, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.138207197189331, "global_step": 371500, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.016298770904541, "global_step": 371501, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1127994060516357, "global_step": 371502, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.111098289489746, "global_step": 371503, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0390985012054443, "global_step": 371504, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0863542556762695, "global_step": 371505, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.127580404281616, "global_step": 371506, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1342697143554688, "global_step": 371507, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2111246585845947, "global_step": 371508, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1997621059417725, "global_step": 371509, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1439595222473145, "global_step": 371510, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0100674629211426, "global_step": 371511, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0345618724823, "global_step": 371512, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1347508430480957, "global_step": 371513, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1869258880615234, "global_step": 371514, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1718814373016357, "global_step": 371515, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0965256690979004, "global_step": 371516, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0957894325256348, "global_step": 371517, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.085477352142334, "global_step": 371518, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0501155853271484, "global_step": 371519, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.049764633178711, "global_step": 371520, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.055798053741455, "global_step": 371521, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.132272481918335, "global_step": 371522, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0409014225006104, "global_step": 371523, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.101724863052368, "global_step": 371524, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1615500450134277, "global_step": 371525, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0466859340667725, "global_step": 371526, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.151716947555542, "global_step": 371527, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.117014169692993, "global_step": 371528, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.16074538230896, "global_step": 371529, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0811426639556885, "global_step": 371530, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1292123794555664, "global_step": 371531, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.138624668121338, "global_step": 371532, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.152275323867798, "global_step": 371533, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.117445468902588, "global_step": 371534, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1333203315734863, "global_step": 371535, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.239856481552124, "global_step": 371536, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.167562961578369, "global_step": 371537, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0486724376678467, "global_step": 371538, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.155194044113159, "global_step": 371539, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.107583522796631, "global_step": 371540, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0940301418304443, "global_step": 371541, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1525025367736816, "global_step": 371542, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.132866859436035, "global_step": 371543, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0927155017852783, "global_step": 371544, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1382150650024414, "global_step": 371545, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.092825174331665, "global_step": 371546, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1149022579193115, "global_step": 371547, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.018954038619995, "global_step": 371548, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.155566930770874, "global_step": 371549, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.010096788406372, "global_step": 371550, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.091139078140259, "global_step": 371551, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1127233505249023, "global_step": 371552, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0990660190582275, "global_step": 371553, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1441831588745117, "global_step": 371554, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1176998615264893, "global_step": 371555, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.019813060760498, "global_step": 371556, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0060713291168213, "global_step": 371557, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.160731077194214, "global_step": 371558, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0450263023376465, "global_step": 371559, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1053473949432373, "global_step": 371560, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.081439256668091, "global_step": 371561, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.071444511413574, "global_step": 371562, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0898003578186035, "global_step": 371563, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.138887882232666, "global_step": 371564, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.193398952484131, "global_step": 371565, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.036055088043213, "global_step": 371566, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0892810821533203, "global_step": 371567, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0915119647979736, "global_step": 371568, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0623481273651123, "global_step": 371569, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.131601572036743, "global_step": 371570, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0086417198181152, "global_step": 371571, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0639405250549316, "global_step": 371572, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1546075344085693, "global_step": 371573, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.215630531311035, "global_step": 371574, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1295711994171143, "global_step": 371575, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1071279048919678, "global_step": 371576, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1732661724090576, "global_step": 371577, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.053971290588379, "global_step": 371578, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.066838502883911, "global_step": 371579, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0564987659454346, "global_step": 371580, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.012470006942749, "global_step": 371581, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0184030532836914, "global_step": 371582, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.074991226196289, "global_step": 371583, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.180931806564331, "global_step": 371584, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1901936531066895, "global_step": 371585, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.085562229156494, "global_step": 371586, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0799384117126465, "global_step": 371587, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0732314586639404, "global_step": 371588, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.049189329147339, "global_step": 371589, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1234493255615234, "global_step": 371590, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2071187496185303, "global_step": 371591, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.23061466217041, "global_step": 371592, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.063570499420166, "global_step": 371593, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1901190280914307, "global_step": 371594, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1066324710845947, "global_step": 371595, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0901057720184326, "global_step": 371596, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0786142349243164, "global_step": 371597, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1320290565490723, "global_step": 371598, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1776912212371826, "global_step": 371599, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1668574810028076, "global_step": 371600, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0896060466766357, "global_step": 371601, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1561248302459717, "global_step": 371602, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.113708257675171, "global_step": 371603, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0955822467803955, "global_step": 371604, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.101840019226074, "global_step": 371605, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2052948474884033, "global_step": 371606, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0798511505126953, "global_step": 371607, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2026381492614746, "global_step": 371608, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1732280254364014, "global_step": 371609, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.045124053955078, "global_step": 371610, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1366395950317383, "global_step": 371611, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.057051420211792, "global_step": 371612, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.143350601196289, "global_step": 371613, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0972304344177246, "global_step": 371614, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.024296998977661, "global_step": 371615, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0844082832336426, "global_step": 371616, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0991313457489014, "global_step": 371617, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1554410457611084, "global_step": 371618, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.160814046859741, "global_step": 371619, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0929369926452637, "global_step": 371620, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1301794052124023, "global_step": 371621, "epoch": 733, "lr": 5e-05}
{"train_loss": 1.962555170059204, "global_step": 371622, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.116015672683716, "global_step": 371623, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1132757663726807, "global_step": 371624, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.125839948654175, "global_step": 371625, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.120795249938965, "global_step": 371626, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0565059185028076, "global_step": 371627, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.096013307571411, "global_step": 371628, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1517090797424316, "global_step": 371629, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.103046178817749, "global_step": 371630, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0713837146759033, "global_step": 371631, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0556344985961914, "global_step": 371632, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.011136293411255, "global_step": 371633, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.114689350128174, "global_step": 371634, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.156728506088257, "global_step": 371635, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.072831869125366, "global_step": 371636, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0568041801452637, "global_step": 371637, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.01409649848938, "global_step": 371638, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.156893730163574, "global_step": 371639, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1729788780212402, "global_step": 371640, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.137676239013672, "global_step": 371641, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1759538650512695, "global_step": 371642, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.118107795715332, "global_step": 371643, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.05755877494812, "global_step": 371644, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1024057865142822, "global_step": 371645, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0892951488494873, "global_step": 371646, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.103217840194702, "global_step": 371647, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0617871284484863, "global_step": 371648, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0780303478240967, "global_step": 371649, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0981805324554443, "global_step": 371650, "epoch": 733, "lr": 5e-05}
{"train_loss": 1.9815846681594849, "global_step": 371651, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1965301036834717, "global_step": 371652, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1104891300201416, "global_step": 371653, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0795581340789795, "global_step": 371654, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1596271991729736, "global_step": 371655, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.078047037124634, "global_step": 371656, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0229246616363525, "global_step": 371657, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0955798625946045, "global_step": 371658, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.166450023651123, "global_step": 371659, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.186464786529541, "global_step": 371660, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.095428705215454, "global_step": 371661, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.181840658187866, "global_step": 371662, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1080641746520996, "global_step": 371663, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.033071994781494, "global_step": 371664, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0007166862487793, "global_step": 371665, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.060420036315918, "global_step": 371666, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0669357776641846, "global_step": 371667, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1085398197174072, "global_step": 371668, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1047911643981934, "global_step": 371669, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.099687099456787, "global_step": 371670, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1328930854797363, "global_step": 371671, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1182429790496826, "global_step": 371672, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.132364511489868, "global_step": 371673, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.116706371307373, "global_step": 371674, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1812407970428467, "global_step": 371675, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.029423952102661, "global_step": 371676, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1571130752563477, "global_step": 371677, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0389814376831055, "global_step": 371678, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1384897232055664, "global_step": 371679, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1442689895629883, "global_step": 371680, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1820647716522217, "global_step": 371681, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0959692001342773, "global_step": 371682, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.185788631439209, "global_step": 371683, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.187690496444702, "global_step": 371684, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.026376247406006, "global_step": 371685, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0769803524017334, "global_step": 371686, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.09305477142334, "global_step": 371687, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0475268363952637, "global_step": 371688, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.02406907081604, "global_step": 371689, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.097109794616699, "global_step": 371690, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0596024990081787, "global_step": 371691, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.170612096786499, "global_step": 371692, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.067819595336914, "global_step": 371693, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.081631660461426, "global_step": 371694, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1144800186157227, "global_step": 371695, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.093419313430786, "global_step": 371696, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1516497135162354, "global_step": 371697, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.213531017303467, "global_step": 371698, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1072826385498047, "global_step": 371699, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0921876430511475, "global_step": 371700, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0197949409484863, "global_step": 371701, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.087540626525879, "global_step": 371702, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1192238330841064, "global_step": 371703, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0094707012176514, "global_step": 371704, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0529074668884277, "global_step": 371705, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1976675987243652, "global_step": 371706, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.144460439682007, "global_step": 371707, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.001004219055176, "global_step": 371708, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.21651291847229, "global_step": 371709, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.168658971786499, "global_step": 371710, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1064870357513428, "global_step": 371711, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.082929849624634, "global_step": 371712, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0979974269866943, "global_step": 371713, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0557539463043213, "global_step": 371714, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1507973670959473, "global_step": 371715, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.064727544784546, "global_step": 371716, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1638526916503906, "global_step": 371717, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.005783796310425, "global_step": 371718, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1474111080169678, "global_step": 371719, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1687119007110596, "global_step": 371720, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0687546730041504, "global_step": 371721, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1322929859161377, "global_step": 371722, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0944340229034424, "global_step": 371723, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1099133491516113, "global_step": 371724, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2076339721679688, "global_step": 371725, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1081998348236084, "global_step": 371726, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.139207363128662, "global_step": 371727, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2052643299102783, "global_step": 371728, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.172330141067505, "global_step": 371729, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0461137294769287, "global_step": 371730, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1117172241210938, "global_step": 371731, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0860002040863037, "global_step": 371732, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1350390911102295, "global_step": 371733, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1915156841278076, "global_step": 371734, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.111661672592163, "global_step": 371735, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.073859930038452, "global_step": 371736, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2124550342559814, "global_step": 371737, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0792791843414307, "global_step": 371738, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.087002754211426, "global_step": 371739, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1131794452667236, "global_step": 371740, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0860328674316406, "global_step": 371741, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2195727825164795, "global_step": 371742, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.022538423538208, "global_step": 371743, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.097233295440674, "global_step": 371744, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.058659315109253, "global_step": 371745, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.127794027328491, "global_step": 371746, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0726377964019775, "global_step": 371747, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.167339324951172, "global_step": 371748, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0866103172302246, "global_step": 371749, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.015483856201172, "global_step": 371750, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.070737838745117, "global_step": 371751, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1268396377563477, "global_step": 371752, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.101018190383911, "global_step": 371753, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1414084434509277, "global_step": 371754, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.023775339126587, "global_step": 371755, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.094616174697876, "global_step": 371756, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1368494033813477, "global_step": 371757, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.047924280166626, "global_step": 371758, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1572866439819336, "global_step": 371759, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.068021774291992, "global_step": 371760, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.028266191482544, "global_step": 371761, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.144758462905884, "global_step": 371762, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1041178703308105, "global_step": 371763, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.177805185317993, "global_step": 371764, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1042990684509277, "global_step": 371765, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.108947992324829, "global_step": 371766, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1129252910614014, "global_step": 371767, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1537349224090576, "global_step": 371768, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.248136520385742, "global_step": 371769, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.133544683456421, "global_step": 371770, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.065021514892578, "global_step": 371771, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.154383420944214, "global_step": 371772, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.148084878921509, "global_step": 371773, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1029272079467773, "global_step": 371774, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.087118148803711, "global_step": 371775, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0765798091888428, "global_step": 371776, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1424083709716797, "global_step": 371777, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.192883014678955, "global_step": 371778, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.056347131729126, "global_step": 371779, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0896682739257812, "global_step": 371780, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0660619735717773, "global_step": 371781, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0983517169952393, "global_step": 371782, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0627002716064453, "global_step": 371783, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.080712080001831, "global_step": 371784, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0760204792022705, "global_step": 371785, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1719167232513428, "global_step": 371786, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1451001167297363, "global_step": 371787, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1204676628112793, "global_step": 371788, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.195108652114868, "global_step": 371789, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1361517906188965, "global_step": 371790, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.135110855102539, "global_step": 371791, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1027913093566895, "global_step": 371792, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.058493137359619, "global_step": 371793, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0292179584503174, "global_step": 371794, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1530840396881104, "global_step": 371795, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.104623556137085, "global_step": 371796, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1025571823120117, "global_step": 371797, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1885323524475098, "global_step": 371798, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.113302707672119, "global_step": 371799, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.073378801345825, "global_step": 371800, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1363437175750732, "global_step": 371801, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1482298374176025, "global_step": 371802, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1523213386535645, "global_step": 371803, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.060072660446167, "global_step": 371804, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0517122745513916, "global_step": 371805, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1358330249786377, "global_step": 371806, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.150505542755127, "global_step": 371807, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1818912029266357, "global_step": 371808, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1586596965789795, "global_step": 371809, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1246957778930664, "global_step": 371810, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.162926197052002, "global_step": 371811, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.071002721786499, "global_step": 371812, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0738582611083984, "global_step": 371813, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.130598783493042, "global_step": 371814, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.076197624206543, "global_step": 371815, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1230244636535645, "global_step": 371816, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.106738328933716, "global_step": 371817, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.130155086517334, "global_step": 371818, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1388425827026367, "global_step": 371819, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1018552780151367, "global_step": 371820, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0483546257019043, "global_step": 371821, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.060612201690674, "global_step": 371822, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.14031720161438, "global_step": 371823, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.099010467529297, "global_step": 371824, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0827128887176514, "global_step": 371825, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.118196964263916, "global_step": 371826, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1029388904571533, "global_step": 371827, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1163830757141113, "global_step": 371828, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.138806104660034, "global_step": 371829, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.154500722885132, "global_step": 371830, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0596837997436523, "global_step": 371831, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1315791606903076, "global_step": 371832, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1944782733917236, "global_step": 371833, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.042830228805542, "global_step": 371834, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0787479877471924, "global_step": 371835, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.109858274459839, "global_step": 371836, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1639046669006348, "global_step": 371837, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.204906702041626, "global_step": 371838, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.035175085067749, "global_step": 371839, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.146177291870117, "global_step": 371840, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0256261825561523, "global_step": 371841, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1516518592834473, "global_step": 371842, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.041145086288452, "global_step": 371843, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.119236707687378, "global_step": 371844, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1368048191070557, "global_step": 371845, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1696178913116455, "global_step": 371846, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.150972843170166, "global_step": 371847, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.072476625442505, "global_step": 371848, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.178091526031494, "global_step": 371849, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0598578453063965, "global_step": 371850, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.082706928253174, "global_step": 371851, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0844309329986572, "global_step": 371852, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.088230609893799, "global_step": 371853, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0217831134796143, "global_step": 371854, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1688148975372314, "global_step": 371855, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0588290691375732, "global_step": 371856, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1285669803619385, "global_step": 371857, "epoch": 733, "lr": 5e-05}
{"train_loss": 1.9919085502624512, "global_step": 371858, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.064342498779297, "global_step": 371859, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.032153844833374, "global_step": 371860, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.019892692565918, "global_step": 371861, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0329320430755615, "global_step": 371862, "epoch": 733, "lr": 5e-05}
{"train_loss": 1.9916189908981323, "global_step": 371863, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1390838623046875, "global_step": 371864, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0924553871154785, "global_step": 371865, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.091987133026123, "global_step": 371866, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.116978406906128, "global_step": 371867, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1156904697418213, "global_step": 371868, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0511693954467773, "global_step": 371869, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1003761291503906, "global_step": 371870, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0890614986419678, "global_step": 371871, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.163386344909668, "global_step": 371872, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0428037643432617, "global_step": 371873, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0815727710723877, "global_step": 371874, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1646316051483154, "global_step": 371875, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.105483293533325, "global_step": 371876, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.075310707092285, "global_step": 371877, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.030755043029785, "global_step": 371878, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1669743061065674, "global_step": 371879, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1122193336486816, "global_step": 371880, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.125828266143799, "global_step": 371881, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.089012861251831, "global_step": 371882, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.082420587539673, "global_step": 371883, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0750837326049805, "global_step": 371884, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.021522045135498, "global_step": 371885, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.12664794921875, "global_step": 371886, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0741636753082275, "global_step": 371887, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0961661338806152, "global_step": 371888, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1166093349456787, "global_step": 371889, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.12227201461792, "global_step": 371890, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.062408447265625, "global_step": 371891, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1292264461517334, "global_step": 371892, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0549991130828857, "global_step": 371893, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.07904052734375, "global_step": 371894, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.03395676612854, "global_step": 371895, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1125876903533936, "global_step": 371896, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.091292381286621, "global_step": 371897, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.094874382019043, "global_step": 371898, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1087570190429688, "global_step": 371899, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1943063735961914, "global_step": 371900, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1114840507507324, "global_step": 371901, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.037393808364868, "global_step": 371902, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0836598873138428, "global_step": 371903, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.203392744064331, "global_step": 371904, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1360538005828857, "global_step": 371905, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.141655445098877, "global_step": 371906, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1231768131256104, "global_step": 371907, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.063952922821045, "global_step": 371908, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0920045375823975, "global_step": 371909, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.100209951400757, "global_step": 371910, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.080228805541992, "global_step": 371911, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.092203140258789, "global_step": 371912, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.118597984313965, "global_step": 371913, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.11645245552063, "global_step": 371914, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1764097213745117, "global_step": 371915, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0862224102020264, "global_step": 371916, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1090571880340576, "global_step": 371917, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2061941623687744, "global_step": 371918, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.094268798828125, "global_step": 371919, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.088153600692749, "global_step": 371920, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0802040100097656, "global_step": 371921, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0842385292053223, "global_step": 371922, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1275272369384766, "global_step": 371923, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.080807685852051, "global_step": 371924, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.099235773086548, "global_step": 371925, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.141728639602661, "global_step": 371926, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.074047327041626, "global_step": 371927, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.143770456314087, "global_step": 371928, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.067471981048584, "global_step": 371929, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.149155855178833, "global_step": 371930, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.026954412460327, "global_step": 371931, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.15619158744812, "global_step": 371932, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.071937084197998, "global_step": 371933, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.124499559402466, "global_step": 371934, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.061599016189575, "global_step": 371935, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.150552749633789, "global_step": 371936, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.109558582305908, "global_step": 371937, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.048825263977051, "global_step": 371938, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0541813373565674, "global_step": 371939, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0445382595062256, "global_step": 371940, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1408276557922363, "global_step": 371941, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2349019050598145, "global_step": 371942, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1033220291137695, "global_step": 371943, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1530418395996094, "global_step": 371944, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.191014289855957, "global_step": 371945, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0895259380340576, "global_step": 371946, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1212587356567383, "global_step": 371947, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2047579288482666, "global_step": 371948, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.106882333755493, "global_step": 371949, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0211544036865234, "global_step": 371950, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1018755435943604, "global_step": 371951, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0735385417938232, "global_step": 371952, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0950734615325928, "global_step": 371953, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1771228313446045, "global_step": 371954, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1064465045928955, "global_step": 371955, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.122494697570801, "global_step": 371956, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.187941074371338, "global_step": 371957, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1260087490081787, "global_step": 371958, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1375527381896973, "global_step": 371959, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1046669483184814, "global_step": 371960, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0736093521118164, "global_step": 371961, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1023921966552734, "global_step": 371962, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.216514825820923, "global_step": 371963, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1604421138763428, "global_step": 371964, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0919227600097656, "global_step": 371965, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.076742649078369, "global_step": 371966, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.118868112564087, "global_step": 371967, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1063120365142822, "global_step": 371968, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0593552589416504, "global_step": 371969, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1175265312194824, "global_step": 371970, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1861860752105713, "global_step": 371971, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1266891956329346, "global_step": 371972, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.104200601577759, "global_step": 371973, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0607428550720215, "global_step": 371974, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1515045166015625, "global_step": 371975, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.149738311767578, "global_step": 371976, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1151986122131348, "global_step": 371977, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1169686317443848, "global_step": 371978, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0278608798980713, "global_step": 371979, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.167855978012085, "global_step": 371980, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2318308353424072, "global_step": 371981, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0914697647094727, "global_step": 371982, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0314509868621826, "global_step": 371983, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.088669538497925, "global_step": 371984, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1378629207611084, "global_step": 371985, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1288270950317383, "global_step": 371986, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1440682411193848, "global_step": 371987, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1089954376220703, "global_step": 371988, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1356003284454346, "global_step": 371989, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1341264247894287, "global_step": 371990, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.121952772140503, "global_step": 371991, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0932796001434326, "global_step": 371992, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.093355178833008, "global_step": 371993, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.171271324157715, "global_step": 371994, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.128321647644043, "global_step": 371995, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.123702049255371, "global_step": 371996, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.160240650177002, "global_step": 371997, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.097874402999878, "global_step": 371998, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0547847747802734, "global_step": 371999, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.108288288116455, "global_step": 372000, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1978201866149902, "global_step": 372001, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1560027599334717, "global_step": 372002, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.122206687927246, "global_step": 372003, "epoch": 733, "lr": 5e-05}
{"train_loss": 1.9887698888778687, "global_step": 372004, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0491433143615723, "global_step": 372005, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0548055171966553, "global_step": 372006, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0859179496765137, "global_step": 372007, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.175910711288452, "global_step": 372008, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.102825164794922, "global_step": 372009, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0438480377197266, "global_step": 372010, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.173884868621826, "global_step": 372011, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.078413724899292, "global_step": 372012, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.157000780105591, "global_step": 372013, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.092775583267212, "global_step": 372014, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1673333644866943, "global_step": 372015, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.165020227432251, "global_step": 372016, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1109507083892822, "global_step": 372017, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.159939765930176, "global_step": 372018, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1451447010040283, "global_step": 372019, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.152369499206543, "global_step": 372020, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1815340518951416, "global_step": 372021, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1443920135498047, "global_step": 372022, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0607926845550537, "global_step": 372023, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0977516174316406, "global_step": 372024, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.143331527709961, "global_step": 372025, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1864585876464844, "global_step": 372026, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.119208335876465, "global_step": 372027, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1774392127990723, "global_step": 372028, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1672096252441406, "global_step": 372029, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1619017124176025, "global_step": 372030, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1111652851104736, "global_step": 372031, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0233187675476074, "global_step": 372032, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1412930488586426, "global_step": 372033, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1184868812561035, "global_step": 372034, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1249735355377197, "global_step": 372035, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1512746810913086, "global_step": 372036, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.067923069000244, "global_step": 372037, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1462342739105225, "global_step": 372038, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2060658931732178, "global_step": 372039, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1099367141723633, "global_step": 372040, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1767046451568604, "global_step": 372041, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1307449340820312, "global_step": 372042, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0293221473693848, "global_step": 372043, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.063535451889038, "global_step": 372044, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1938230991363525, "global_step": 372045, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0498464107513428, "global_step": 372046, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.18111252784729, "global_step": 372047, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0825469493865967, "global_step": 372048, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1234235763549805, "global_step": 372049, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1268463134765625, "global_step": 372050, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1048030853271484, "global_step": 372051, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.135859727859497, "global_step": 372052, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1286261081695557, "global_step": 372053, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0508670806884766, "global_step": 372054, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.096801280975342, "global_step": 372055, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.205728054046631, "global_step": 372056, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.072155475616455, "global_step": 372057, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1747729778289795, "global_step": 372058, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.142883062362671, "global_step": 372059, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1449453830718994, "global_step": 372060, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1297786235809326, "global_step": 372061, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.076077938079834, "global_step": 372062, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.099625587463379, "global_step": 372063, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1592092514038086, "global_step": 372064, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.165919542312622, "global_step": 372065, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0774378776550293, "global_step": 372066, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0895254611968994, "global_step": 372067, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.059670925140381, "global_step": 372068, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1299281120300293, "global_step": 372069, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1659586429595947, "global_step": 372070, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.21830415725708, "global_step": 372071, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1211681365966797, "global_step": 372072, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.076620578765869, "global_step": 372073, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.093940258026123, "global_step": 372074, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.113967180252075, "global_step": 372075, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.010232448577881, "global_step": 372076, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0564653873443604, "global_step": 372077, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1155388355255127, "global_step": 372078, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.120070219039917, "global_step": 372079, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.192842483520508, "global_step": 372080, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.127121686935425, "global_step": 372081, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0439867973327637, "global_step": 372082, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.089137077331543, "global_step": 372083, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1315414905548096, "global_step": 372084, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0707144737243652, "global_step": 372085, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0522937774658203, "global_step": 372086, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.167308807373047, "global_step": 372087, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1332669258117676, "global_step": 372088, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.084383964538574, "global_step": 372089, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.116983413696289, "global_step": 372090, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.094402551651001, "global_step": 372091, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.138780355453491, "global_step": 372092, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.064617395401001, "global_step": 372093, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0947163105010986, "global_step": 372094, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1159138679504395, "global_step": 372095, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0545687675476074, "global_step": 372096, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0689125061035156, "global_step": 372097, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.103286027908325, "global_step": 372098, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.189056873321533, "global_step": 372099, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0578229427337646, "global_step": 372100, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.146742105484009, "global_step": 372101, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1285789012908936, "global_step": 372102, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.03945255279541, "global_step": 372103, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.117964744567871, "global_step": 372104, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.080373764038086, "global_step": 372105, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.130048990249634, "global_step": 372106, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1872599124908447, "global_step": 372107, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1495676040649414, "global_step": 372108, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1119329929351807, "global_step": 372109, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.086606979370117, "global_step": 372110, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1537697315216064, "global_step": 372111, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1403584480285645, "global_step": 372112, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.124377965927124, "global_step": 372113, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0853397846221924, "global_step": 372114, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.060094118118286, "global_step": 372115, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.162046432495117, "global_step": 372116, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0726494789123535, "global_step": 372117, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1044201850891113, "global_step": 372118, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.08868408203125, "global_step": 372119, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1266682147979736, "global_step": 372120, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.065518617630005, "global_step": 372121, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0881495475769043, "global_step": 372122, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0186562538146973, "global_step": 372123, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.074695348739624, "global_step": 372124, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.091912269592285, "global_step": 372125, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.067513942718506, "global_step": 372126, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1696407794952393, "global_step": 372127, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0332212448120117, "global_step": 372128, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.143367290496826, "global_step": 372129, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1216728687286377, "global_step": 372130, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.050816774368286, "global_step": 372131, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.195626974105835, "global_step": 372132, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1171369552612305, "global_step": 372133, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.160660743713379, "global_step": 372134, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1698977947235107, "global_step": 372135, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0853476524353027, "global_step": 372136, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1392898559570312, "global_step": 372137, "epoch": 733, "lr": 5e-05}
{"train_loss": 1.992588758468628, "global_step": 372138, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0640902519226074, "global_step": 372139, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.115434408187866, "global_step": 372140, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.191681385040283, "global_step": 372141, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1260926723480225, "global_step": 372142, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1269636154174805, "global_step": 372143, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.164566993713379, "global_step": 372144, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.104315996170044, "global_step": 372145, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.106982469558716, "global_step": 372146, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.142705202102661, "global_step": 372147, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0588512420654297, "global_step": 372148, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1493539810180664, "global_step": 372149, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1772360801696777, "global_step": 372150, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2009992599487305, "global_step": 372151, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1550824642181396, "global_step": 372152, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.083425283432007, "global_step": 372153, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2451565265655518, "global_step": 372154, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.11967396736145, "global_step": 372155, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.084211826324463, "global_step": 372156, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1399333477020264, "global_step": 372157, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.144556999206543, "global_step": 372158, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1080219745635986, "global_step": 372159, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.118889808654785, "global_step": 372160, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.043680429458618, "global_step": 372161, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.207080364227295, "global_step": 372162, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.127932548522949, "global_step": 372163, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.149125576019287, "global_step": 372164, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1228888034820557, "global_step": 372165, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.115638256072998, "global_step": 372166, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.174143075942993, "global_step": 372167, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1094629764556885, "global_step": 372168, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1704442501068115, "global_step": 372169, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0299365520477295, "global_step": 372170, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0336358547210693, "global_step": 372171, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1083006858825684, "global_step": 372172, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.073472261428833, "global_step": 372173, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0204904079437256, "global_step": 372174, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1074557304382324, "global_step": 372175, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.059086322784424, "global_step": 372176, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1921122074127197, "global_step": 372177, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0706632137298584, "global_step": 372178, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0940370559692383, "global_step": 372179, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.103991985321045, "global_step": 372180, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.108311653137207, "global_step": 372181, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0390005111694336, "global_step": 372182, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.180957078933716, "global_step": 372183, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1287574768066406, "global_step": 372184, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1221823692321777, "global_step": 372185, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.230574369430542, "global_step": 372186, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1340978145599365, "global_step": 372187, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.115654468536377, "global_step": 372188, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1090292930603027, "global_step": 372189, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.144284725189209, "global_step": 372190, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.098937749862671, "global_step": 372191, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1111385822296143, "global_step": 372192, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.099360704421997, "global_step": 372193, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.09161376953125, "global_step": 372194, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.093245506286621, "global_step": 372195, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.280367136001587, "global_step": 372196, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1800734996795654, "global_step": 372197, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.066251277923584, "global_step": 372198, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0871684551239014, "global_step": 372199, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0845284461975098, "global_step": 372200, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1846675872802734, "global_step": 372201, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0420241355895996, "global_step": 372202, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1903889179229736, "global_step": 372203, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.128708600997925, "global_step": 372204, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0800859928131104, "global_step": 372205, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0925509929656982, "global_step": 372206, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.08713436126709, "global_step": 372207, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0888266563415527, "global_step": 372208, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.096525192260742, "global_step": 372209, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.147209644317627, "global_step": 372210, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.036792039871216, "global_step": 372211, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1087377071380615, "global_step": 372212, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1762266159057617, "global_step": 372213, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.139261245727539, "global_step": 372214, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1208786964416504, "global_step": 372215, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.119209051132202, "global_step": 372216, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0828206539154053, "global_step": 372217, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.096964120864868, "global_step": 372218, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1761062145233154, "global_step": 372219, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.079091787338257, "global_step": 372220, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0497570037841797, "global_step": 372221, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.082239866256714, "global_step": 372222, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.0232772827148438, "global_step": 372223, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2194154262542725, "global_step": 372224, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1010236740112305, "global_step": 372225, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.2003469467163086, "global_step": 372226, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.180992841720581, "global_step": 372227, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1084420680999756, "global_step": 372228, "epoch": 733, "lr": 5e-05}
{"train_loss": 2.1290507316589355, "global_step": 372229, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1352269649505615, "global_step": 372230, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.102001190185547, "global_step": 372231, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0834567546844482, "global_step": 372232, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1793997287750244, "global_step": 372233, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1573822498321533, "global_step": 372234, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0383195877075195, "global_step": 372235, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0657989978790283, "global_step": 372236, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0699210166931152, "global_step": 372237, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.095977544784546, "global_step": 372238, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0957281589508057, "global_step": 372239, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1346302032470703, "global_step": 372240, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0742886066436768, "global_step": 372241, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.038642168045044, "global_step": 372242, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.057945728302002, "global_step": 372243, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.122502565383911, "global_step": 372244, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1649129390716553, "global_step": 372245, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.217550277709961, "global_step": 372246, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.045034170150757, "global_step": 372247, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1396234035491943, "global_step": 372248, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0351974964141846, "global_step": 372249, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1178717613220215, "global_step": 372250, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1110527515411377, "global_step": 372251, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1352765560150146, "global_step": 372252, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0680482387542725, "global_step": 372253, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.096066951751709, "global_step": 372254, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1215503215789795, "global_step": 372255, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.070432662963867, "global_step": 372256, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0598032474517822, "global_step": 372257, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1032874584198, "global_step": 372258, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.089033365249634, "global_step": 372259, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1473236083984375, "global_step": 372260, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1257102489471436, "global_step": 372261, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1813089847564697, "global_step": 372262, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.055799722671509, "global_step": 372263, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.104079246520996, "global_step": 372264, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.095857858657837, "global_step": 372265, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.054990530014038, "global_step": 372266, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1196610927581787, "global_step": 372267, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0957634449005127, "global_step": 372268, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.107160806655884, "global_step": 372269, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0424633026123047, "global_step": 372270, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1737864017486572, "global_step": 372271, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0141537189483643, "global_step": 372272, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1445672512054443, "global_step": 372273, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1069748401641846, "global_step": 372274, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0470614433288574, "global_step": 372275, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.07527494430542, "global_step": 372276, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.03857684135437, "global_step": 372277, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1725728511810303, "global_step": 372278, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.148909091949463, "global_step": 372279, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0632967948913574, "global_step": 372280, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2491915225982666, "global_step": 372281, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0654072761535645, "global_step": 372282, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.090397834777832, "global_step": 372283, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1372034549713135, "global_step": 372284, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.119910955429077, "global_step": 372285, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0732641220092773, "global_step": 372286, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0041987895965576, "global_step": 372287, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.078951120376587, "global_step": 372288, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1019153594970703, "global_step": 372289, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2092111110687256, "global_step": 372290, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1269078254699707, "global_step": 372291, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.087965488433838, "global_step": 372292, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.13484263420105, "global_step": 372293, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1651482582092285, "global_step": 372294, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.067772626876831, "global_step": 372295, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1480631828308105, "global_step": 372296, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.140169143676758, "global_step": 372297, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1237258911132812, "global_step": 372298, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1124420166015625, "global_step": 372299, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0538384914398193, "global_step": 372300, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0997533798217773, "global_step": 372301, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0973739624023438, "global_step": 372302, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.130138874053955, "global_step": 372303, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.068126678466797, "global_step": 372304, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1139326095581055, "global_step": 372305, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.078338384628296, "global_step": 372306, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.106231212615967, "global_step": 372307, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.145308494567871, "global_step": 372308, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.046022891998291, "global_step": 372309, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0544116497039795, "global_step": 372310, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1403706073760986, "global_step": 372311, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0827479362487793, "global_step": 372312, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2304978370666504, "global_step": 372313, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.09623122215271, "global_step": 372314, "epoch": 734, "lr": 5e-05}
{"train_loss": 1.9995920658111572, "global_step": 372315, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.039207696914673, "global_step": 372316, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.034761905670166, "global_step": 372317, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.086653470993042, "global_step": 372318, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.035311698913574, "global_step": 372319, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.157580614089966, "global_step": 372320, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1643528938293457, "global_step": 372321, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.173987865447998, "global_step": 372322, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0735790729522705, "global_step": 372323, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.190351724624634, "global_step": 372324, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0916638374328613, "global_step": 372325, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.104522705078125, "global_step": 372326, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0667805671691895, "global_step": 372327, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.04917573928833, "global_step": 372328, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1113431453704834, "global_step": 372329, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.095550060272217, "global_step": 372330, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.141847610473633, "global_step": 372331, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.136950969696045, "global_step": 372332, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1158559322357178, "global_step": 372333, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1095170974731445, "global_step": 372334, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.142639398574829, "global_step": 372335, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.011094570159912, "global_step": 372336, "epoch": 734, "lr": 5e-05}
{"train_loss": 1.9591326713562012, "global_step": 372337, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.075057029724121, "global_step": 372338, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.136539936065674, "global_step": 372339, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.120788812637329, "global_step": 372340, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0730040073394775, "global_step": 372341, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0429816246032715, "global_step": 372342, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0192925930023193, "global_step": 372343, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0930230617523193, "global_step": 372344, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.066049098968506, "global_step": 372345, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2002687454223633, "global_step": 372346, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.078036069869995, "global_step": 372347, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.127056837081909, "global_step": 372348, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1338324546813965, "global_step": 372349, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.096468448638916, "global_step": 372350, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.134139060974121, "global_step": 372351, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.093620538711548, "global_step": 372352, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1684091091156006, "global_step": 372353, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1068737506866455, "global_step": 372354, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.162170171737671, "global_step": 372355, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0356557369232178, "global_step": 372356, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.120450019836426, "global_step": 372357, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1219682693481445, "global_step": 372358, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1706345081329346, "global_step": 372359, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.157072067260742, "global_step": 372360, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0287187099456787, "global_step": 372361, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0310678482055664, "global_step": 372362, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0756800174713135, "global_step": 372363, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0695395469665527, "global_step": 372364, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.061005115509033, "global_step": 372365, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1316263675689697, "global_step": 372366, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.056180953979492, "global_step": 372367, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.127392292022705, "global_step": 372368, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1727538108825684, "global_step": 372369, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.106868028640747, "global_step": 372370, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.11807918548584, "global_step": 372371, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1424601078033447, "global_step": 372372, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.045538902282715, "global_step": 372373, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.099762201309204, "global_step": 372374, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1880264282226562, "global_step": 372375, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.073957920074463, "global_step": 372376, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.085292100906372, "global_step": 372377, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.083841562271118, "global_step": 372378, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.121577739715576, "global_step": 372379, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.213792562484741, "global_step": 372380, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.14152455329895, "global_step": 372381, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1429033279418945, "global_step": 372382, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0962777137756348, "global_step": 372383, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.164560079574585, "global_step": 372384, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.069211959838867, "global_step": 372385, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.206496238708496, "global_step": 372386, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1506168842315674, "global_step": 372387, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1147706508636475, "global_step": 372388, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0507283210754395, "global_step": 372389, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1234593391418457, "global_step": 372390, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1055731773376465, "global_step": 372391, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.124021530151367, "global_step": 372392, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1066811084747314, "global_step": 372393, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.135051965713501, "global_step": 372394, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1145246028900146, "global_step": 372395, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1227543354034424, "global_step": 372396, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1183419227600098, "global_step": 372397, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0787031650543213, "global_step": 372398, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.083235025405884, "global_step": 372399, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0875492095947266, "global_step": 372400, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1417014598846436, "global_step": 372401, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.023880958557129, "global_step": 372402, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1194400787353516, "global_step": 372403, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.121377468109131, "global_step": 372404, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.107893228530884, "global_step": 372405, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1037094593048096, "global_step": 372406, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1616363525390625, "global_step": 372407, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1796822547912598, "global_step": 372408, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0907318592071533, "global_step": 372409, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.212045669555664, "global_step": 372410, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.090188980102539, "global_step": 372411, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1344285011291504, "global_step": 372412, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0851097106933594, "global_step": 372413, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.116144895553589, "global_step": 372414, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.156036853790283, "global_step": 372415, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.124052047729492, "global_step": 372416, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1095082759857178, "global_step": 372417, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.199039936065674, "global_step": 372418, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0809497833251953, "global_step": 372419, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.063349962234497, "global_step": 372420, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.101809501647949, "global_step": 372421, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1436688899993896, "global_step": 372422, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1045985221862793, "global_step": 372423, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0837230682373047, "global_step": 372424, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0645229816436768, "global_step": 372425, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.085136651992798, "global_step": 372426, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.084444284439087, "global_step": 372427, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1645123958587646, "global_step": 372428, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1559181213378906, "global_step": 372429, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0664379596710205, "global_step": 372430, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0703606605529785, "global_step": 372431, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2125589847564697, "global_step": 372432, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2047653198242188, "global_step": 372433, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1479856967926025, "global_step": 372434, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.094416379928589, "global_step": 372435, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.046504259109497, "global_step": 372436, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.051281690597534, "global_step": 372437, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0999598503112793, "global_step": 372438, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.147437810897827, "global_step": 372439, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1658198833465576, "global_step": 372440, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2149178981781006, "global_step": 372441, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.170559883117676, "global_step": 372442, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0856711864471436, "global_step": 372443, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0635299682617188, "global_step": 372444, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1494150161743164, "global_step": 372445, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0503878593444824, "global_step": 372446, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0718419551849365, "global_step": 372447, "epoch": 734, "lr": 5e-05}
{"train_loss": 1.9564497470855713, "global_step": 372448, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0017240047454834, "global_step": 372449, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0752692222595215, "global_step": 372450, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1059045791625977, "global_step": 372451, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0503132343292236, "global_step": 372452, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0769996643066406, "global_step": 372453, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1783156394958496, "global_step": 372454, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.100461483001709, "global_step": 372455, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.027933120727539, "global_step": 372456, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.097691297531128, "global_step": 372457, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1194005012512207, "global_step": 372458, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0824027061462402, "global_step": 372459, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.038905382156372, "global_step": 372460, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.032076120376587, "global_step": 372461, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.067913293838501, "global_step": 372462, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1577656269073486, "global_step": 372463, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.116852283477783, "global_step": 372464, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0152788162231445, "global_step": 372465, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0876588821411133, "global_step": 372466, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0865695476531982, "global_step": 372467, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1476330757141113, "global_step": 372468, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.14652681350708, "global_step": 372469, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0824873447418213, "global_step": 372470, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.029052257537842, "global_step": 372471, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.083521842956543, "global_step": 372472, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0873165130615234, "global_step": 372473, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1528804302215576, "global_step": 372474, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0391366481781006, "global_step": 372475, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0431623458862305, "global_step": 372476, "epoch": 734, "lr": 5e-05}
{"train_loss": 1.9948019981384277, "global_step": 372477, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1431353092193604, "global_step": 372478, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.095503568649292, "global_step": 372479, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1789209842681885, "global_step": 372480, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1697497367858887, "global_step": 372481, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.161810874938965, "global_step": 372482, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.095109224319458, "global_step": 372483, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1479525566101074, "global_step": 372484, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.082355499267578, "global_step": 372485, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.057636022567749, "global_step": 372486, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.069216251373291, "global_step": 372487, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.139519214630127, "global_step": 372488, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0864295959472656, "global_step": 372489, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0661702156066895, "global_step": 372490, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1024131774902344, "global_step": 372491, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1143836975097656, "global_step": 372492, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0656025409698486, "global_step": 372493, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0904266834259033, "global_step": 372494, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0911478996276855, "global_step": 372495, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1016056537628174, "global_step": 372496, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.169774055480957, "global_step": 372497, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0650551319122314, "global_step": 372498, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0726077556610107, "global_step": 372499, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1241793632507324, "global_step": 372500, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1722891330718994, "global_step": 372501, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1526832580566406, "global_step": 372502, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.072122573852539, "global_step": 372503, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.010770559310913, "global_step": 372504, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1169662475585938, "global_step": 372505, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.105957269668579, "global_step": 372506, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0574851036071777, "global_step": 372507, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0590381622314453, "global_step": 372508, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0491750240325928, "global_step": 372509, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1265416145324707, "global_step": 372510, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0348892211914062, "global_step": 372511, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.07820725440979, "global_step": 372512, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.169651746749878, "global_step": 372513, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.142622709274292, "global_step": 372514, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.099562168121338, "global_step": 372515, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.15189266204834, "global_step": 372516, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.142275333404541, "global_step": 372517, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1269893646240234, "global_step": 372518, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.121873140335083, "global_step": 372519, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1253302097320557, "global_step": 372520, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1567041873931885, "global_step": 372521, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1552417278289795, "global_step": 372522, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0982766151428223, "global_step": 372523, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1573824882507324, "global_step": 372524, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0254037380218506, "global_step": 372525, "epoch": 734, "lr": 5e-05}
{"train_loss": 1.9892120361328125, "global_step": 372526, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1170132160186768, "global_step": 372527, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.134289264678955, "global_step": 372528, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1166036128997803, "global_step": 372529, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.008297920227051, "global_step": 372530, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1191587448120117, "global_step": 372531, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.041288375854492, "global_step": 372532, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.137890100479126, "global_step": 372533, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1112403869628906, "global_step": 372534, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0619184970855713, "global_step": 372535, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1596527099609375, "global_step": 372536, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.081651210784912, "global_step": 372537, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1063992977142334, "global_step": 372538, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1391961574554443, "global_step": 372539, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0566935539245605, "global_step": 372540, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1379501819610596, "global_step": 372541, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.101879358291626, "global_step": 372542, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.042177200317383, "global_step": 372543, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1333372592926025, "global_step": 372544, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.084541082382202, "global_step": 372545, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0569400787353516, "global_step": 372546, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1598587036132812, "global_step": 372547, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0584728717803955, "global_step": 372548, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1073050498962402, "global_step": 372549, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.166024684906006, "global_step": 372550, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1617298126220703, "global_step": 372551, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0360329151153564, "global_step": 372552, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1427600383758545, "global_step": 372553, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0871174335479736, "global_step": 372554, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1831603050231934, "global_step": 372555, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0500261783599854, "global_step": 372556, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1472721099853516, "global_step": 372557, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.168187379837036, "global_step": 372558, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1111819744110107, "global_step": 372559, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0372653007507324, "global_step": 372560, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1071038246154785, "global_step": 372561, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1721112728118896, "global_step": 372562, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1349740028381348, "global_step": 372563, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.099860429763794, "global_step": 372564, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0557632446289062, "global_step": 372565, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1041111946105957, "global_step": 372566, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.080573797225952, "global_step": 372567, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1134002208709717, "global_step": 372568, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.004563808441162, "global_step": 372569, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.083066463470459, "global_step": 372570, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.05863618850708, "global_step": 372571, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.153067111968994, "global_step": 372572, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0545527935028076, "global_step": 372573, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1048049926757812, "global_step": 372574, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0821173191070557, "global_step": 372575, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.09907603263855, "global_step": 372576, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0769999027252197, "global_step": 372577, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.034660816192627, "global_step": 372578, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0608866214752197, "global_step": 372579, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1082892417907715, "global_step": 372580, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.029827356338501, "global_step": 372581, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1470558643341064, "global_step": 372582, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0666048526763916, "global_step": 372583, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0830421447753906, "global_step": 372584, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0453200340270996, "global_step": 372585, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0994620323181152, "global_step": 372586, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1525161266326904, "global_step": 372587, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0752570629119873, "global_step": 372588, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.127342462539673, "global_step": 372589, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.178105592727661, "global_step": 372590, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.074174165725708, "global_step": 372591, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1154873371124268, "global_step": 372592, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.110206365585327, "global_step": 372593, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.067150592803955, "global_step": 372594, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0601956844329834, "global_step": 372595, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0589823722839355, "global_step": 372596, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1297924518585205, "global_step": 372597, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.102341413497925, "global_step": 372598, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0465357303619385, "global_step": 372599, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1518542766571045, "global_step": 372600, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.148362398147583, "global_step": 372601, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0793397426605225, "global_step": 372602, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.067692756652832, "global_step": 372603, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.198474168777466, "global_step": 372604, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1372835636138916, "global_step": 372605, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0795483589172363, "global_step": 372606, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.095221519470215, "global_step": 372607, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.08609676361084, "global_step": 372608, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0858888626098633, "global_step": 372609, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.107640027999878, "global_step": 372610, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.182349443435669, "global_step": 372611, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1474175453186035, "global_step": 372612, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.136394500732422, "global_step": 372613, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.106515407562256, "global_step": 372614, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.152312755584717, "global_step": 372615, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0764143466949463, "global_step": 372616, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1593172550201416, "global_step": 372617, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1356098651885986, "global_step": 372618, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.110307216644287, "global_step": 372619, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.127664804458618, "global_step": 372620, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.073637008666992, "global_step": 372621, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.052042007446289, "global_step": 372622, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.081753969192505, "global_step": 372623, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1955647468566895, "global_step": 372624, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1030454635620117, "global_step": 372625, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.101956844329834, "global_step": 372626, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1819279193878174, "global_step": 372627, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.150604486465454, "global_step": 372628, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0381813049316406, "global_step": 372629, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.142503023147583, "global_step": 372630, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.078557014465332, "global_step": 372631, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.120110511779785, "global_step": 372632, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1099257469177246, "global_step": 372633, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0988736152648926, "global_step": 372634, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.109889268875122, "global_step": 372635, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1519317626953125, "global_step": 372636, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1380679607391357, "global_step": 372637, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.118908643722534, "global_step": 372638, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.079840898513794, "global_step": 372639, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.004814624786377, "global_step": 372640, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1068882942199707, "global_step": 372641, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1163110733032227, "global_step": 372642, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1766254901885986, "global_step": 372643, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0991969108581543, "global_step": 372644, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1198997497558594, "global_step": 372645, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1357226371765137, "global_step": 372646, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1604485511779785, "global_step": 372647, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0737483501434326, "global_step": 372648, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0839481353759766, "global_step": 372649, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0929102897644043, "global_step": 372650, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.06034517288208, "global_step": 372651, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.191826820373535, "global_step": 372652, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.165400981903076, "global_step": 372653, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1451003551483154, "global_step": 372654, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.075810432434082, "global_step": 372655, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.104635000228882, "global_step": 372656, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0987870693206787, "global_step": 372657, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0651347637176514, "global_step": 372658, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0981125831604004, "global_step": 372659, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1481871604919434, "global_step": 372660, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1171016693115234, "global_step": 372661, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.072216510772705, "global_step": 372662, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.077951431274414, "global_step": 372663, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.111823797225952, "global_step": 372664, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.057657480239868, "global_step": 372665, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1003730297088623, "global_step": 372666, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1020665168762207, "global_step": 372667, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.134108781814575, "global_step": 372668, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2068586349487305, "global_step": 372669, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.13250470161438, "global_step": 372670, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.126389265060425, "global_step": 372671, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0629053115844727, "global_step": 372672, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.046935796737671, "global_step": 372673, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1638848781585693, "global_step": 372674, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1116697788238525, "global_step": 372675, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.067972183227539, "global_step": 372676, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1532812118530273, "global_step": 372677, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.160173177719116, "global_step": 372678, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.115161418914795, "global_step": 372679, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0201685428619385, "global_step": 372680, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1372978687286377, "global_step": 372681, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0914790630340576, "global_step": 372682, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0829102993011475, "global_step": 372683, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1795217990875244, "global_step": 372684, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.166480541229248, "global_step": 372685, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.080781936645508, "global_step": 372686, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.144237995147705, "global_step": 372687, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1451985836029053, "global_step": 372688, "epoch": 734, "lr": 5e-05}
{"train_loss": 1.9759474992752075, "global_step": 372689, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2002148628234863, "global_step": 372690, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1983582973480225, "global_step": 372691, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.107285499572754, "global_step": 372692, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0817441940307617, "global_step": 372693, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1007323265075684, "global_step": 372694, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0415306091308594, "global_step": 372695, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1272528171539307, "global_step": 372696, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.08796763420105, "global_step": 372697, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1442792415618896, "global_step": 372698, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1520979404449463, "global_step": 372699, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0642313957214355, "global_step": 372700, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.059190273284912, "global_step": 372701, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0305380821228027, "global_step": 372702, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1734557151794434, "global_step": 372703, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1270270347595215, "global_step": 372704, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1421875953674316, "global_step": 372705, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1254160404205322, "global_step": 372706, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1035006046295166, "global_step": 372707, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.095162868499756, "global_step": 372708, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.068559169769287, "global_step": 372709, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.13228440284729, "global_step": 372710, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1931064128875732, "global_step": 372711, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.042273998260498, "global_step": 372712, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1832187175750732, "global_step": 372713, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.06951904296875, "global_step": 372714, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1392476558685303, "global_step": 372715, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0787456035614014, "global_step": 372716, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1384217739105225, "global_step": 372717, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1752095222473145, "global_step": 372718, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0985026359558105, "global_step": 372719, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0044171810150146, "global_step": 372720, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.096555709838867, "global_step": 372721, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.139554023742676, "global_step": 372722, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0212323665618896, "global_step": 372723, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0082967281341553, "global_step": 372724, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1503148078918457, "global_step": 372725, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.12465763092041, "global_step": 372726, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0373668670654297, "global_step": 372727, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1292190551757812, "global_step": 372728, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1172165870666504, "global_step": 372729, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0829193592071533, "global_step": 372730, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.068258047103882, "global_step": 372731, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0411999225616455, "global_step": 372732, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1361207962036133, "global_step": 372733, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.125011920928955, "global_step": 372734, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.220594882965088, "global_step": 372735, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.119029998779297, "global_step": 372736, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1416079998016357, "global_step": 372737, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1123883724212646, "global_step": 372738, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.086402416229248, "global_step": 372739, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1158738136291504, "global_step": 372740, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1838133335113525, "global_step": 372741, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0921740531921387, "global_step": 372742, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.098296880722046, "global_step": 372743, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1641879081726074, "global_step": 372744, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1713316440582275, "global_step": 372745, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0921947956085205, "global_step": 372746, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.111362934112549, "global_step": 372747, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.196920871734619, "global_step": 372748, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.100806713104248, "global_step": 372749, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.168732166290283, "global_step": 372750, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1697463989257812, "global_step": 372751, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.106621026992798, "global_step": 372752, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1536033153533936, "global_step": 372753, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.112759590148926, "global_step": 372754, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2332277297973633, "global_step": 372755, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0365374088287354, "global_step": 372756, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1857075691223145, "global_step": 372757, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.108646869659424, "global_step": 372758, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1368844509124756, "global_step": 372759, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2378458976745605, "global_step": 372760, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.141066312789917, "global_step": 372761, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1147043704986572, "global_step": 372762, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2294509410858154, "global_step": 372763, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0073318481445312, "global_step": 372764, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.187427282333374, "global_step": 372765, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.124004602432251, "global_step": 372766, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.059303045272827, "global_step": 372767, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0830538272857666, "global_step": 372768, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0406036376953125, "global_step": 372769, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.077202320098877, "global_step": 372770, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.080622673034668, "global_step": 372771, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2021262645721436, "global_step": 372772, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.133010149002075, "global_step": 372773, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.102053642272949, "global_step": 372774, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.13826584815979, "global_step": 372775, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1036698818206787, "global_step": 372776, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.160120964050293, "global_step": 372777, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0773942470550537, "global_step": 372778, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2495415210723877, "global_step": 372779, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0661256313323975, "global_step": 372780, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1228229999542236, "global_step": 372781, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1935906410217285, "global_step": 372782, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0643441677093506, "global_step": 372783, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.097195625305176, "global_step": 372784, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.048999309539795, "global_step": 372785, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0648443698883057, "global_step": 372786, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0940449237823486, "global_step": 372787, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0934011936187744, "global_step": 372788, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0792505741119385, "global_step": 372789, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1197328567504883, "global_step": 372790, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0944530963897705, "global_step": 372791, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1036829948425293, "global_step": 372792, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.117666721343994, "global_step": 372793, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0373945236206055, "global_step": 372794, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1143813133239746, "global_step": 372795, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.059037685394287, "global_step": 372796, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.111257791519165, "global_step": 372797, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0950043201446533, "global_step": 372798, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1339035034179688, "global_step": 372799, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.078282356262207, "global_step": 372800, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.060884952545166, "global_step": 372801, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.137127161026001, "global_step": 372802, "epoch": 734, "lr": 5e-05}
{"train_loss": 1.9944536685943604, "global_step": 372803, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.110663890838623, "global_step": 372804, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.056830406188965, "global_step": 372805, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1354222297668457, "global_step": 372806, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1064565181732178, "global_step": 372807, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0098776817321777, "global_step": 372808, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.136032819747925, "global_step": 372809, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1012368202209473, "global_step": 372810, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1340513229370117, "global_step": 372811, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1132895946502686, "global_step": 372812, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0962183475494385, "global_step": 372813, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.041378974914551, "global_step": 372814, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1526856422424316, "global_step": 372815, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0559844970703125, "global_step": 372816, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.09100079536438, "global_step": 372817, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1941254138946533, "global_step": 372818, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0218684673309326, "global_step": 372819, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.222235918045044, "global_step": 372820, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1487832069396973, "global_step": 372821, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0976290702819824, "global_step": 372822, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0969948768615723, "global_step": 372823, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.163985252380371, "global_step": 372824, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0576577186584473, "global_step": 372825, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0940990447998047, "global_step": 372826, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.154285192489624, "global_step": 372827, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0696861743927, "global_step": 372828, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1176373958587646, "global_step": 372829, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.169055461883545, "global_step": 372830, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.143986940383911, "global_step": 372831, "epoch": 734, "lr": 5e-05}
{"train_loss": 1.9963207244873047, "global_step": 372832, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1286826133728027, "global_step": 372833, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1177375316619873, "global_step": 372834, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0926413536071777, "global_step": 372835, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.037040948867798, "global_step": 372836, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0700812339782715, "global_step": 372837, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.048659563064575, "global_step": 372838, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.041917085647583, "global_step": 372839, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0580875873565674, "global_step": 372840, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.17464017868042, "global_step": 372841, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.164273977279663, "global_step": 372842, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.183980941772461, "global_step": 372843, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.077354669570923, "global_step": 372844, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0945627689361572, "global_step": 372845, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1568620204925537, "global_step": 372846, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.09818959236145, "global_step": 372847, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0809743404388428, "global_step": 372848, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.073789119720459, "global_step": 372849, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.078026294708252, "global_step": 372850, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.043131113052368, "global_step": 372851, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.030428886413574, "global_step": 372852, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1157419681549072, "global_step": 372853, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1155428886413574, "global_step": 372854, "epoch": 734, "lr": 5e-05}
{"train_loss": 1.9916973114013672, "global_step": 372855, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.090409994125366, "global_step": 372856, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1880228519439697, "global_step": 372857, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1150760650634766, "global_step": 372858, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1207613945007324, "global_step": 372859, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1535189151763916, "global_step": 372860, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1261465549468994, "global_step": 372861, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.122687339782715, "global_step": 372862, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0144073963165283, "global_step": 372863, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.088447093963623, "global_step": 372864, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.075100898742676, "global_step": 372865, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.103696823120117, "global_step": 372866, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.037830352783203, "global_step": 372867, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1526827812194824, "global_step": 372868, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1314172744750977, "global_step": 372869, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0887861251831055, "global_step": 372870, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.11277437210083, "global_step": 372871, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0963826179504395, "global_step": 372872, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2189881801605225, "global_step": 372873, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1270251274108887, "global_step": 372874, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.085346221923828, "global_step": 372875, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.087123394012451, "global_step": 372876, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.087785243988037, "global_step": 372877, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1431729793548584, "global_step": 372878, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0989205837249756, "global_step": 372879, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1861720085144043, "global_step": 372880, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.037416696548462, "global_step": 372881, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0902531147003174, "global_step": 372882, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0562260150909424, "global_step": 372883, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0072569847106934, "global_step": 372884, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.016815423965454, "global_step": 372885, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1787729263305664, "global_step": 372886, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1016831398010254, "global_step": 372887, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0792176723480225, "global_step": 372888, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1071152687072754, "global_step": 372889, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1995415687561035, "global_step": 372890, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1140716075897217, "global_step": 372891, "epoch": 734, "lr": 5e-05}
{"train_loss": 1.9865319728851318, "global_step": 372892, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.092695951461792, "global_step": 372893, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.155562400817871, "global_step": 372894, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.090406894683838, "global_step": 372895, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1947484016418457, "global_step": 372896, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.14805269241333, "global_step": 372897, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0839388370513916, "global_step": 372898, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.048374652862549, "global_step": 372899, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.066312551498413, "global_step": 372900, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2100369930267334, "global_step": 372901, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1616220474243164, "global_step": 372902, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.166321039199829, "global_step": 372903, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0541138648986816, "global_step": 372904, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.138124465942383, "global_step": 372905, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.160614252090454, "global_step": 372906, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.105266809463501, "global_step": 372907, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0340635776519775, "global_step": 372908, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1382436752319336, "global_step": 372909, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.114880084991455, "global_step": 372910, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.103813886642456, "global_step": 372911, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1955323219299316, "global_step": 372912, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.152517318725586, "global_step": 372913, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0317320823669434, "global_step": 372914, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.054384708404541, "global_step": 372915, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0328383445739746, "global_step": 372916, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.074228048324585, "global_step": 372917, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1887810230255127, "global_step": 372918, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.062791109085083, "global_step": 372919, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1839029788970947, "global_step": 372920, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1582858562469482, "global_step": 372921, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1121537685394287, "global_step": 372922, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.034705638885498, "global_step": 372923, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.109567165374756, "global_step": 372924, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.045621633529663, "global_step": 372925, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0867724418640137, "global_step": 372926, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.212503671646118, "global_step": 372927, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0750536918640137, "global_step": 372928, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0813567638397217, "global_step": 372929, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0972721576690674, "global_step": 372930, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0995147228240967, "global_step": 372931, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.150599479675293, "global_step": 372932, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1249873638153076, "global_step": 372933, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.049672842025757, "global_step": 372934, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1006686687469482, "global_step": 372935, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.064319133758545, "global_step": 372936, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1160881519317627, "global_step": 372937, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0880002975463867, "global_step": 372938, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1621456146240234, "global_step": 372939, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1293222904205322, "global_step": 372940, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1972062587738037, "global_step": 372941, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1650030612945557, "global_step": 372942, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.146989583969116, "global_step": 372943, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1016323566436768, "global_step": 372944, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1487350463867188, "global_step": 372945, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.144404172897339, "global_step": 372946, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.078474283218384, "global_step": 372947, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.129181146621704, "global_step": 372948, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0400912761688232, "global_step": 372949, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.122258186340332, "global_step": 372950, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.203716278076172, "global_step": 372951, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.113659143447876, "global_step": 372952, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.096499443054199, "global_step": 372953, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2039132118225098, "global_step": 372954, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1299774646759033, "global_step": 372955, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.020656108856201, "global_step": 372956, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0268545150756836, "global_step": 372957, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.094440460205078, "global_step": 372958, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2002668380737305, "global_step": 372959, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.02557373046875, "global_step": 372960, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0868678092956543, "global_step": 372961, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1323792934417725, "global_step": 372962, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0804226398468018, "global_step": 372963, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.081371545791626, "global_step": 372964, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0454845428466797, "global_step": 372965, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.117868661880493, "global_step": 372966, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0807323455810547, "global_step": 372967, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0823748111724854, "global_step": 372968, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.107301950454712, "global_step": 372969, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1993956565856934, "global_step": 372970, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.047734022140503, "global_step": 372971, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0960164070129395, "global_step": 372972, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.101236343383789, "global_step": 372973, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1029908657073975, "global_step": 372974, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1362662315368652, "global_step": 372975, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1364519596099854, "global_step": 372976, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0149073600769043, "global_step": 372977, "epoch": 734, "lr": 5e-05}
{"train_loss": 1.999241828918457, "global_step": 372978, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.080117702484131, "global_step": 372979, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1124649047851562, "global_step": 372980, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.020613670349121, "global_step": 372981, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.148426055908203, "global_step": 372982, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0364022254943848, "global_step": 372983, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0835371017456055, "global_step": 372984, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0587854385375977, "global_step": 372985, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0953991413116455, "global_step": 372986, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.112103223800659, "global_step": 372987, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.073352336883545, "global_step": 372988, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.112356662750244, "global_step": 372989, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0837435722351074, "global_step": 372990, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0604212284088135, "global_step": 372991, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1234607696533203, "global_step": 372992, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0604279041290283, "global_step": 372993, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0544323921203613, "global_step": 372994, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1767187118530273, "global_step": 372995, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.101078510284424, "global_step": 372996, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1454381942749023, "global_step": 372997, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.140554428100586, "global_step": 372998, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1181747913360596, "global_step": 372999, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.070621967315674, "global_step": 373000, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1520798206329346, "global_step": 373001, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1527695655822754, "global_step": 373002, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.138904094696045, "global_step": 373003, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1041910648345947, "global_step": 373004, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.151236057281494, "global_step": 373005, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.152055263519287, "global_step": 373006, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.158597946166992, "global_step": 373007, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0877745151519775, "global_step": 373008, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.075631856918335, "global_step": 373009, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.139582633972168, "global_step": 373010, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.101092576980591, "global_step": 373011, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.055234670639038, "global_step": 373012, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1232454776763916, "global_step": 373013, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.134371280670166, "global_step": 373014, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.121182680130005, "global_step": 373015, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.157238006591797, "global_step": 373016, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1170167922973633, "global_step": 373017, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.101982593536377, "global_step": 373018, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.10967755317688, "global_step": 373019, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1342949867248535, "global_step": 373020, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.132819652557373, "global_step": 373021, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.143859624862671, "global_step": 373022, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1355931758880615, "global_step": 373023, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.102069854736328, "global_step": 373024, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1088714599609375, "global_step": 373025, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.108896255493164, "global_step": 373026, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0930938720703125, "global_step": 373027, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0929179191589355, "global_step": 373028, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.106013059616089, "global_step": 373029, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1219451427459717, "global_step": 373030, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.102123498916626, "global_step": 373031, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1611826419830322, "global_step": 373032, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2058935165405273, "global_step": 373033, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1537744998931885, "global_step": 373034, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.111224412918091, "global_step": 373035, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.148371934890747, "global_step": 373036, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.025758981704712, "global_step": 373037, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.06254506111145, "global_step": 373038, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.194620370864868, "global_step": 373039, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1996026039123535, "global_step": 373040, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1062865257263184, "global_step": 373041, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2120304107666016, "global_step": 373042, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1964950561523438, "global_step": 373043, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2012016773223877, "global_step": 373044, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2007312774658203, "global_step": 373045, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1128032207489014, "global_step": 373046, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0954928398132324, "global_step": 373047, "epoch": 734, "lr": 5e-05}
{"train_loss": 1.978579044342041, "global_step": 373048, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.18231463432312, "global_step": 373049, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.078052043914795, "global_step": 373050, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1100611686706543, "global_step": 373051, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.193753719329834, "global_step": 373052, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1523191928863525, "global_step": 373053, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2030556201934814, "global_step": 373054, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.061228036880493, "global_step": 373055, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1127822399139404, "global_step": 373056, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.12819504737854, "global_step": 373057, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1004528999328613, "global_step": 373058, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.113049268722534, "global_step": 373059, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1084537506103516, "global_step": 373060, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1112983226776123, "global_step": 373061, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1602399349212646, "global_step": 373062, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.144207715988159, "global_step": 373063, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.14272403717041, "global_step": 373064, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.119335412979126, "global_step": 373065, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1188039779663086, "global_step": 373066, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.09139084815979, "global_step": 373067, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0785601139068604, "global_step": 373068, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1425650119781494, "global_step": 373069, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.082033395767212, "global_step": 373070, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.112842321395874, "global_step": 373071, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1326143741607666, "global_step": 373072, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1801137924194336, "global_step": 373073, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0968661308288574, "global_step": 373074, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1409924030303955, "global_step": 373075, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.013859748840332, "global_step": 373076, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.143918752670288, "global_step": 373077, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1400771141052246, "global_step": 373078, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1705658435821533, "global_step": 373079, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1412644386291504, "global_step": 373080, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.091789484024048, "global_step": 373081, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1094000339508057, "global_step": 373082, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.135575294494629, "global_step": 373083, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.129011869430542, "global_step": 373084, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.08463716506958, "global_step": 373085, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.154165506362915, "global_step": 373086, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.117830753326416, "global_step": 373087, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1871087551116943, "global_step": 373088, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.094836950302124, "global_step": 373089, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.128526449203491, "global_step": 373090, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0771193504333496, "global_step": 373091, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1356468200683594, "global_step": 373092, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.015468120574951, "global_step": 373093, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0172746181488037, "global_step": 373094, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1085054874420166, "global_step": 373095, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2379090785980225, "global_step": 373096, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1730542182922363, "global_step": 373097, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.186691999435425, "global_step": 373098, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0708014965057373, "global_step": 373099, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.178501844406128, "global_step": 373100, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.069596767425537, "global_step": 373101, "epoch": 734, "lr": 5e-05}
{"train_loss": 1.982179880142212, "global_step": 373102, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.114302158355713, "global_step": 373103, "epoch": 734, "lr": 5e-05}
{"train_loss": 1.9929983615875244, "global_step": 373104, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0996451377868652, "global_step": 373105, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.170022487640381, "global_step": 373106, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1431241035461426, "global_step": 373107, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1543638706207275, "global_step": 373108, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.119994640350342, "global_step": 373109, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1225485801696777, "global_step": 373110, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0931737422943115, "global_step": 373111, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0378000736236572, "global_step": 373112, "epoch": 734, "lr": 5e-05}
{"train_loss": 1.9799994230270386, "global_step": 373113, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0608367919921875, "global_step": 373114, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1246087551116943, "global_step": 373115, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0976758003234863, "global_step": 373116, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0646328926086426, "global_step": 373117, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0797433853149414, "global_step": 373118, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1082956790924072, "global_step": 373119, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1178817749023438, "global_step": 373120, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0804665088653564, "global_step": 373121, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1202619075775146, "global_step": 373122, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1488521099090576, "global_step": 373123, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.131521701812744, "global_step": 373124, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.161323070526123, "global_step": 373125, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0554749965667725, "global_step": 373126, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1134934425354004, "global_step": 373127, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.181666374206543, "global_step": 373128, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.06498384475708, "global_step": 373129, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1414501667022705, "global_step": 373130, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.054515838623047, "global_step": 373131, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.114105224609375, "global_step": 373132, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1761410236358643, "global_step": 373133, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.039349317550659, "global_step": 373134, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.162137985229492, "global_step": 373135, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.111997365951538, "global_step": 373136, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.033414840698242, "global_step": 373137, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1702184677124023, "global_step": 373138, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1302685737609863, "global_step": 373139, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.093607187271118, "global_step": 373140, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1204967498779297, "global_step": 373141, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0737955570220947, "global_step": 373142, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0585319995880127, "global_step": 373143, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1713099479675293, "global_step": 373144, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.175031900405884, "global_step": 373145, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1963205337524414, "global_step": 373146, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1034746170043945, "global_step": 373147, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0921778678894043, "global_step": 373148, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.058798313140869, "global_step": 373149, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.179222583770752, "global_step": 373150, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.161540985107422, "global_step": 373151, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0623767375946045, "global_step": 373152, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1394636631011963, "global_step": 373153, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1061456203460693, "global_step": 373154, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.155127763748169, "global_step": 373155, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2353017330169678, "global_step": 373156, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1197397708892822, "global_step": 373157, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.043769598007202, "global_step": 373158, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.070070743560791, "global_step": 373159, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1113500595092773, "global_step": 373160, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.041069507598877, "global_step": 373161, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1392617225646973, "global_step": 373162, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1385228633880615, "global_step": 373163, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0844454765319824, "global_step": 373164, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2272346019744873, "global_step": 373165, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.165457248687744, "global_step": 373166, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0721452236175537, "global_step": 373167, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.156649351119995, "global_step": 373168, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0571956634521484, "global_step": 373169, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.050060749053955, "global_step": 373170, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1359047889709473, "global_step": 373171, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1181721687316895, "global_step": 373172, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.2028565406799316, "global_step": 373173, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1683506965637207, "global_step": 373174, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1569180488586426, "global_step": 373175, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.128080368041992, "global_step": 373176, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.066300868988037, "global_step": 373177, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.202063798904419, "global_step": 373178, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0140249729156494, "global_step": 373179, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1918270587921143, "global_step": 373180, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1434481143951416, "global_step": 373181, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.08050799369812, "global_step": 373182, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.072230339050293, "global_step": 373183, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.127419948577881, "global_step": 373184, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.040572166442871, "global_step": 373185, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0520708560943604, "global_step": 373186, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0079433917999268, "global_step": 373187, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1060688495635986, "global_step": 373188, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.168015480041504, "global_step": 373189, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.03157639503479, "global_step": 373190, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0877857208251953, "global_step": 373191, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0873899459838867, "global_step": 373192, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1039791107177734, "global_step": 373193, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.0885777473449707, "global_step": 373194, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.159898519515991, "global_step": 373195, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.1478922367095947, "global_step": 373196, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.108213424682617, "global_step": 373197, "epoch": 734, "lr": 5e-05}
{"train_loss": 2.107546329498291, "global_step": 373198, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1349849700927734, "global_step": 373199, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.089432716369629, "global_step": 373200, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.12164568901062, "global_step": 373201, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0349817276000977, "global_step": 373202, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0148797035217285, "global_step": 373203, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.097604751586914, "global_step": 373204, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.074497938156128, "global_step": 373205, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1018593311309814, "global_step": 373206, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.124122142791748, "global_step": 373207, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1167075634002686, "global_step": 373208, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.132405996322632, "global_step": 373209, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.065408945083618, "global_step": 373210, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.123448610305786, "global_step": 373211, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.10324764251709, "global_step": 373212, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1127548217773438, "global_step": 373213, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1439106464385986, "global_step": 373214, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.158618211746216, "global_step": 373215, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.181417942047119, "global_step": 373216, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0881922245025635, "global_step": 373217, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1868441104888916, "global_step": 373218, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1064867973327637, "global_step": 373219, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.2129316329956055, "global_step": 373220, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0876734256744385, "global_step": 373221, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.128788471221924, "global_step": 373222, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0978972911834717, "global_step": 373223, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1262192726135254, "global_step": 373224, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1883158683776855, "global_step": 373225, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1147541999816895, "global_step": 373226, "epoch": 735, "lr": 5e-05}
{"train_loss": 1.9892010688781738, "global_step": 373227, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1311185359954834, "global_step": 373228, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0605409145355225, "global_step": 373229, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.091374635696411, "global_step": 373230, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.167466878890991, "global_step": 373231, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.016879081726074, "global_step": 373232, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1151082515716553, "global_step": 373233, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.043910503387451, "global_step": 373234, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0892136096954346, "global_step": 373235, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1454036235809326, "global_step": 373236, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1352503299713135, "global_step": 373237, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1702377796173096, "global_step": 373238, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0017130374908447, "global_step": 373239, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0612399578094482, "global_step": 373240, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1707723140716553, "global_step": 373241, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0163769721984863, "global_step": 373242, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.194392204284668, "global_step": 373243, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0854740142822266, "global_step": 373244, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0428414344787598, "global_step": 373245, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.118971586227417, "global_step": 373246, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.115795850753784, "global_step": 373247, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.112311840057373, "global_step": 373248, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0425829887390137, "global_step": 373249, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.084599494934082, "global_step": 373250, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0946877002716064, "global_step": 373251, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.072796106338501, "global_step": 373252, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1240406036376953, "global_step": 373253, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0867080688476562, "global_step": 373254, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0636110305786133, "global_step": 373255, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0998523235321045, "global_step": 373256, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1475117206573486, "global_step": 373257, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.192155599594116, "global_step": 373258, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.082822561264038, "global_step": 373259, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1406099796295166, "global_step": 373260, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0640554428100586, "global_step": 373261, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.180388927459717, "global_step": 373262, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1022162437438965, "global_step": 373263, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1661734580993652, "global_step": 373264, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1502673625946045, "global_step": 373265, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0910451412200928, "global_step": 373266, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0924718379974365, "global_step": 373267, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0460751056671143, "global_step": 373268, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.08603572845459, "global_step": 373269, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1473073959350586, "global_step": 373270, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.163545608520508, "global_step": 373271, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1104578971862793, "global_step": 373272, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.073251485824585, "global_step": 373273, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.066039800643921, "global_step": 373274, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0538580417633057, "global_step": 373275, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0311830043792725, "global_step": 373276, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.2040152549743652, "global_step": 373277, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.126985788345337, "global_step": 373278, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.073286771774292, "global_step": 373279, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.118180274963379, "global_step": 373280, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.071821928024292, "global_step": 373281, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1139683723449707, "global_step": 373282, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0267748832702637, "global_step": 373283, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.144714832305908, "global_step": 373284, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0704216957092285, "global_step": 373285, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.126585006713867, "global_step": 373286, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0497891902923584, "global_step": 373287, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.107628345489502, "global_step": 373288, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0791549682617188, "global_step": 373289, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.203906536102295, "global_step": 373290, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1164464950561523, "global_step": 373291, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0852785110473633, "global_step": 373292, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0898377895355225, "global_step": 373293, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.12400484085083, "global_step": 373294, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1543784141540527, "global_step": 373295, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.019718647003174, "global_step": 373296, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0804312229156494, "global_step": 373297, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.152653694152832, "global_step": 373298, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.177680253982544, "global_step": 373299, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1787781715393066, "global_step": 373300, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.13669490814209, "global_step": 373301, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0572094917297363, "global_step": 373302, "epoch": 735, "lr": 5e-05}
{"train_loss": 1.975139856338501, "global_step": 373303, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.108532190322876, "global_step": 373304, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1153361797332764, "global_step": 373305, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.079542636871338, "global_step": 373306, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.108499765396118, "global_step": 373307, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0827934741973877, "global_step": 373308, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0750648975372314, "global_step": 373309, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1060545444488525, "global_step": 373310, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.084272861480713, "global_step": 373311, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0906982421875, "global_step": 373312, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0407683849334717, "global_step": 373313, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1190083026885986, "global_step": 373314, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1149802207946777, "global_step": 373315, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.191290855407715, "global_step": 373316, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.114807605743408, "global_step": 373317, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0306406021118164, "global_step": 373318, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0591046810150146, "global_step": 373319, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0308477878570557, "global_step": 373320, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.053227186203003, "global_step": 373321, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.103095293045044, "global_step": 373322, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0887577533721924, "global_step": 373323, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0875601768493652, "global_step": 373324, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.090834140777588, "global_step": 373325, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.044745683670044, "global_step": 373326, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1667590141296387, "global_step": 373327, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.052253484725952, "global_step": 373328, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0920896530151367, "global_step": 373329, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0321056842803955, "global_step": 373330, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0788896083831787, "global_step": 373331, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1749377250671387, "global_step": 373332, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.099724292755127, "global_step": 373333, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1457440853118896, "global_step": 373334, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.077702045440674, "global_step": 373335, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0636911392211914, "global_step": 373336, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1387691497802734, "global_step": 373337, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.048755168914795, "global_step": 373338, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0706942081451416, "global_step": 373339, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0379388332366943, "global_step": 373340, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0790016651153564, "global_step": 373341, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.049044132232666, "global_step": 373342, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.073634386062622, "global_step": 373343, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.083606719970703, "global_step": 373344, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.11529803276062, "global_step": 373345, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1957244873046875, "global_step": 373346, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1338295936584473, "global_step": 373347, "epoch": 735, "lr": 5e-05}
{"train_loss": 1.9684867858886719, "global_step": 373348, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1010892391204834, "global_step": 373349, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0887043476104736, "global_step": 373350, "epoch": 735, "lr": 5e-05}
{"train_loss": 1.9757230281829834, "global_step": 373351, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0648412704467773, "global_step": 373352, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0862889289855957, "global_step": 373353, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.032068967819214, "global_step": 373354, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.029771327972412, "global_step": 373355, "epoch": 735, "lr": 5e-05}
{"train_loss": 1.994057297706604, "global_step": 373356, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.111511468887329, "global_step": 373357, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.066523551940918, "global_step": 373358, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.093817710876465, "global_step": 373359, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0756919384002686, "global_step": 373360, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.090303897857666, "global_step": 373361, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0849790573120117, "global_step": 373362, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0852482318878174, "global_step": 373363, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.048713445663452, "global_step": 373364, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1562159061431885, "global_step": 373365, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0650737285614014, "global_step": 373366, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0842740535736084, "global_step": 373367, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1319425106048584, "global_step": 373368, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1535162925720215, "global_step": 373369, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1660492420196533, "global_step": 373370, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1880807876586914, "global_step": 373371, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0946102142333984, "global_step": 373372, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.060542106628418, "global_step": 373373, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0920464992523193, "global_step": 373374, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.117049217224121, "global_step": 373375, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.125744342803955, "global_step": 373376, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1497817039489746, "global_step": 373377, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.100436210632324, "global_step": 373378, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.020395278930664, "global_step": 373379, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1534583568573, "global_step": 373380, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0537478923797607, "global_step": 373381, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.044464111328125, "global_step": 373382, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.044564962387085, "global_step": 373383, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0441620349884033, "global_step": 373384, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1187052726745605, "global_step": 373385, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.129910707473755, "global_step": 373386, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.133596658706665, "global_step": 373387, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1092050075531006, "global_step": 373388, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0768537521362305, "global_step": 373389, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0099258422851562, "global_step": 373390, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1807711124420166, "global_step": 373391, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.113588333129883, "global_step": 373392, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.2458202838897705, "global_step": 373393, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1471102237701416, "global_step": 373394, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.055634021759033, "global_step": 373395, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.136620283126831, "global_step": 373396, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.084806203842163, "global_step": 373397, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.076303482055664, "global_step": 373398, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.024273633956909, "global_step": 373399, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.114919900894165, "global_step": 373400, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0839955806732178, "global_step": 373401, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1110615730285645, "global_step": 373402, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1104326248168945, "global_step": 373403, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0461440086364746, "global_step": 373404, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.196380138397217, "global_step": 373405, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.142897129058838, "global_step": 373406, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.047464609146118, "global_step": 373407, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.10042142868042, "global_step": 373408, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.215996503829956, "global_step": 373409, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.128556251525879, "global_step": 373410, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.089599132537842, "global_step": 373411, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.165483236312866, "global_step": 373412, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1548144817352295, "global_step": 373413, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0866634845733643, "global_step": 373414, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0625245571136475, "global_step": 373415, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1109588146209717, "global_step": 373416, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0879788398742676, "global_step": 373417, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1043059825897217, "global_step": 373418, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.141075372695923, "global_step": 373419, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0730059146881104, "global_step": 373420, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1363677978515625, "global_step": 373421, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1558661460876465, "global_step": 373422, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.135969400405884, "global_step": 373423, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.2318050861358643, "global_step": 373424, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0801124572753906, "global_step": 373425, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.060689926147461, "global_step": 373426, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0355653762817383, "global_step": 373427, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0819249153137207, "global_step": 373428, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1447513103485107, "global_step": 373429, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1179277896881104, "global_step": 373430, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1656417846679688, "global_step": 373431, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.101922035217285, "global_step": 373432, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.099229097366333, "global_step": 373433, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.130981206893921, "global_step": 373434, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1308846473693848, "global_step": 373435, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1187527179718018, "global_step": 373436, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1584343910217285, "global_step": 373437, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1919424533843994, "global_step": 373438, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1187498569488525, "global_step": 373439, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0982649326324463, "global_step": 373440, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1119930744171143, "global_step": 373441, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0780091285705566, "global_step": 373442, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1093859672546387, "global_step": 373443, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0110156536102295, "global_step": 373444, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0726499557495117, "global_step": 373445, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.115678310394287, "global_step": 373446, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.061429262161255, "global_step": 373447, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.074328899383545, "global_step": 373448, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.02901291847229, "global_step": 373449, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.107741594314575, "global_step": 373450, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.090826988220215, "global_step": 373451, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1151089668273926, "global_step": 373452, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.080667018890381, "global_step": 373453, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.092461109161377, "global_step": 373454, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.039685010910034, "global_step": 373455, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0535247325897217, "global_step": 373456, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0576484203338623, "global_step": 373457, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1224679946899414, "global_step": 373458, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0594561100006104, "global_step": 373459, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.125869035720825, "global_step": 373460, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1157684326171875, "global_step": 373461, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1791720390319824, "global_step": 373462, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1342453956604004, "global_step": 373463, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.085022449493408, "global_step": 373464, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.09637713432312, "global_step": 373465, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1709792613983154, "global_step": 373466, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.197627305984497, "global_step": 373467, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0850069522857666, "global_step": 373468, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.089224100112915, "global_step": 373469, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0985612869262695, "global_step": 373470, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.112185001373291, "global_step": 373471, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0739293098449707, "global_step": 373472, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1154582500457764, "global_step": 373473, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1116294860839844, "global_step": 373474, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.114912509918213, "global_step": 373475, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.014375925064087, "global_step": 373476, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1024069786071777, "global_step": 373477, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.104672908782959, "global_step": 373478, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1194348335266113, "global_step": 373479, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.143760919570923, "global_step": 373480, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0419440269470215, "global_step": 373481, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0555596351623535, "global_step": 373482, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1452178955078125, "global_step": 373483, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0261390209198, "global_step": 373484, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0567004680633545, "global_step": 373485, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1112406253814697, "global_step": 373486, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1283152103424072, "global_step": 373487, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.145177125930786, "global_step": 373488, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.2305991649627686, "global_step": 373489, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1115834712982178, "global_step": 373490, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.083559036254883, "global_step": 373491, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1344196796417236, "global_step": 373492, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.153486490249634, "global_step": 373493, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.142470359802246, "global_step": 373494, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0945992469787598, "global_step": 373495, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.208451509475708, "global_step": 373496, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.043797731399536, "global_step": 373497, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0647597312927246, "global_step": 373498, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.134150743484497, "global_step": 373499, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.070160150527954, "global_step": 373500, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0530993938446045, "global_step": 373501, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1078104972839355, "global_step": 373502, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1096248626708984, "global_step": 373503, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.116299629211426, "global_step": 373504, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1813979148864746, "global_step": 373505, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0851786136627197, "global_step": 373506, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.127210855484009, "global_step": 373507, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1494462490081787, "global_step": 373508, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.136721134185791, "global_step": 373509, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.062840700149536, "global_step": 373510, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1291544437408447, "global_step": 373511, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1202268600463867, "global_step": 373512, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0532431602478027, "global_step": 373513, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0639660358428955, "global_step": 373514, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0547866821289062, "global_step": 373515, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.14428448677063, "global_step": 373516, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.2270758152008057, "global_step": 373517, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1222469806671143, "global_step": 373518, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.127201557159424, "global_step": 373519, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.16467547416687, "global_step": 373520, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.086719512939453, "global_step": 373521, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1103124618530273, "global_step": 373522, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1679840087890625, "global_step": 373523, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.093334197998047, "global_step": 373524, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.016835927963257, "global_step": 373525, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0669946670532227, "global_step": 373526, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1290712356567383, "global_step": 373527, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.149566650390625, "global_step": 373528, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.111482858657837, "global_step": 373529, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.2158961296081543, "global_step": 373530, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.144425630569458, "global_step": 373531, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1518588066101074, "global_step": 373532, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.170832633972168, "global_step": 373533, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0776937007904053, "global_step": 373534, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1706159114837646, "global_step": 373535, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1576037406921387, "global_step": 373536, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0683400630950928, "global_step": 373537, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.066054344177246, "global_step": 373538, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1974287033081055, "global_step": 373539, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0706675052642822, "global_step": 373540, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1561739444732666, "global_step": 373541, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1365652084350586, "global_step": 373542, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.071686029434204, "global_step": 373543, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0751638412475586, "global_step": 373544, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0499355792999268, "global_step": 373545, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.11671781539917, "global_step": 373546, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1753156185150146, "global_step": 373547, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.160531997680664, "global_step": 373548, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1742265224456787, "global_step": 373549, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.098973035812378, "global_step": 373550, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.212174415588379, "global_step": 373551, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.08426833152771, "global_step": 373552, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.158205986022949, "global_step": 373553, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.06945538520813, "global_step": 373554, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.131387233734131, "global_step": 373555, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.177624464035034, "global_step": 373556, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.2318015098571777, "global_step": 373557, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.107037305831909, "global_step": 373558, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.162961006164551, "global_step": 373559, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0804507732391357, "global_step": 373560, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.161165475845337, "global_step": 373561, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1339290142059326, "global_step": 373562, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0817618370056152, "global_step": 373563, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.054405927658081, "global_step": 373564, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.147665500640869, "global_step": 373565, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.087615966796875, "global_step": 373566, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0343151092529297, "global_step": 373567, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1373815536499023, "global_step": 373568, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.142972946166992, "global_step": 373569, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0229761600494385, "global_step": 373570, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.055324077606201, "global_step": 373571, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.206300735473633, "global_step": 373572, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1422011852264404, "global_step": 373573, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.033240795135498, "global_step": 373574, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.140239715576172, "global_step": 373575, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0649373531341553, "global_step": 373576, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0582435131073, "global_step": 373577, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.069337844848633, "global_step": 373578, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0503039360046387, "global_step": 373579, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.077130079269409, "global_step": 373580, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0869834423065186, "global_step": 373581, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.13350248336792, "global_step": 373582, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.168980360031128, "global_step": 373583, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0255255699157715, "global_step": 373584, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0895280838012695, "global_step": 373585, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0436325073242188, "global_step": 373586, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1282570362091064, "global_step": 373587, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1670584678649902, "global_step": 373588, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0995142459869385, "global_step": 373589, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1183619499206543, "global_step": 373590, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.081780433654785, "global_step": 373591, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.032071590423584, "global_step": 373592, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0948214530944824, "global_step": 373593, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.138314962387085, "global_step": 373594, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.126248836517334, "global_step": 373595, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1163196563720703, "global_step": 373596, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.127462387084961, "global_step": 373597, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1164464950561523, "global_step": 373598, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0604395866394043, "global_step": 373599, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0308902263641357, "global_step": 373600, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.14532732963562, "global_step": 373601, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.057692766189575, "global_step": 373602, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0832886695861816, "global_step": 373603, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.098010778427124, "global_step": 373604, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.036444664001465, "global_step": 373605, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1009867191314697, "global_step": 373606, "epoch": 735, "lr": 5e-05}
{"train_loss": 1.995751976966858, "global_step": 373607, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1333019733428955, "global_step": 373608, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0414693355560303, "global_step": 373609, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1802353858947754, "global_step": 373610, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.044849395751953, "global_step": 373611, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1858127117156982, "global_step": 373612, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1385788917541504, "global_step": 373613, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0856118202209473, "global_step": 373614, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0570642948150635, "global_step": 373615, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.123671293258667, "global_step": 373616, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.068591833114624, "global_step": 373617, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1727476119995117, "global_step": 373618, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.081923007965088, "global_step": 373619, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0200283527374268, "global_step": 373620, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0850648880004883, "global_step": 373621, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1220130920410156, "global_step": 373622, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0582666397094727, "global_step": 373623, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0999398231506348, "global_step": 373624, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1285407543182373, "global_step": 373625, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.071906089782715, "global_step": 373626, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0709917545318604, "global_step": 373627, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.167853355407715, "global_step": 373628, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0900607109069824, "global_step": 373629, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.149110794067383, "global_step": 373630, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1611833572387695, "global_step": 373631, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1531529426574707, "global_step": 373632, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0859858989715576, "global_step": 373633, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.119840621948242, "global_step": 373634, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0746452808380127, "global_step": 373635, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.062640905380249, "global_step": 373636, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.064605474472046, "global_step": 373637, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.101260185241699, "global_step": 373638, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.103850841522217, "global_step": 373639, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0967345237731934, "global_step": 373640, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1272776126861572, "global_step": 373641, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.160773515701294, "global_step": 373642, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.172123908996582, "global_step": 373643, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1187381744384766, "global_step": 373644, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.190061092376709, "global_step": 373645, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0776405334472656, "global_step": 373646, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0810706615448, "global_step": 373647, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1062445640563965, "global_step": 373648, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.084573984146118, "global_step": 373649, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.097712755203247, "global_step": 373650, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1562139987945557, "global_step": 373651, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0057828426361084, "global_step": 373652, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.150074005126953, "global_step": 373653, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0428528785705566, "global_step": 373654, "epoch": 735, "lr": 5e-05}
{"train_loss": 1.9910540580749512, "global_step": 373655, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0784380435943604, "global_step": 373656, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.130504608154297, "global_step": 373657, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.12066388130188, "global_step": 373658, "epoch": 735, "lr": 5e-05}
{"train_loss": 1.98036789894104, "global_step": 373659, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0827343463897705, "global_step": 373660, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.111255407333374, "global_step": 373661, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.203693389892578, "global_step": 373662, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1215875148773193, "global_step": 373663, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0802812576293945, "global_step": 373664, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.12197208404541, "global_step": 373665, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0714616775512695, "global_step": 373666, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1015307903289795, "global_step": 373667, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0997228622436523, "global_step": 373668, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.079667568206787, "global_step": 373669, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.131587266921997, "global_step": 373670, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.075230360031128, "global_step": 373671, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.088160991668701, "global_step": 373672, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.163728713989258, "global_step": 373673, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1145334243774414, "global_step": 373674, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1322619915008545, "global_step": 373675, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1842353343963623, "global_step": 373676, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1748907566070557, "global_step": 373677, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0811424255371094, "global_step": 373678, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.248342752456665, "global_step": 373679, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.088308572769165, "global_step": 373680, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1428747177124023, "global_step": 373681, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1459271907806396, "global_step": 373682, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1871390342712402, "global_step": 373683, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.159057140350342, "global_step": 373684, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1452407836914062, "global_step": 373685, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.053217887878418, "global_step": 373686, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1081602573394775, "global_step": 373687, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1335113048553467, "global_step": 373688, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.032953977584839, "global_step": 373689, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1014790534973145, "global_step": 373690, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.060335874557495, "global_step": 373691, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.179410457611084, "global_step": 373692, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1365838050842285, "global_step": 373693, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.089233875274658, "global_step": 373694, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0511226654052734, "global_step": 373695, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1496517658233643, "global_step": 373696, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0449604988098145, "global_step": 373697, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0874454975128174, "global_step": 373698, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.072136878967285, "global_step": 373699, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.106546401977539, "global_step": 373700, "epoch": 735, "lr": 5e-05}
{"train_loss": 1.9734598398208618, "global_step": 373701, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.163390874862671, "global_step": 373702, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0781240463256836, "global_step": 373703, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.122323513031006, "global_step": 373704, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1147212982177734, "global_step": 373705, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.112215042114258, "global_step": 373706, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1525769233703613, "global_step": 373707, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1414084434509277, "global_step": 373708, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1657516956329346, "global_step": 373709, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.136692523956299, "global_step": 373710, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.104172468185425, "global_step": 373711, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.12562894821167, "global_step": 373712, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1095688343048096, "global_step": 373713, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1560795307159424, "global_step": 373714, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1937766075134277, "global_step": 373715, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0496015548706055, "global_step": 373716, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1834933757781982, "global_step": 373717, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0858988761901855, "global_step": 373718, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.161875009536743, "global_step": 373719, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0850963592529297, "global_step": 373720, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1841282844543457, "global_step": 373721, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1541287899017334, "global_step": 373722, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.118104934692383, "global_step": 373723, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.144869804382324, "global_step": 373724, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1837518215179443, "global_step": 373725, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.154237747192383, "global_step": 373726, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0928595066070557, "global_step": 373727, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.050081968307495, "global_step": 373728, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0357377529144287, "global_step": 373729, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.084071397781372, "global_step": 373730, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1288039684295654, "global_step": 373731, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.089590311050415, "global_step": 373732, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.054821491241455, "global_step": 373733, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.08801007270813, "global_step": 373734, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1605167388916016, "global_step": 373735, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1168811321258545, "global_step": 373736, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1593525409698486, "global_step": 373737, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1236112117767334, "global_step": 373738, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.096395492553711, "global_step": 373739, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0365452766418457, "global_step": 373740, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.047173500061035, "global_step": 373741, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.055485486984253, "global_step": 373742, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.105520486831665, "global_step": 373743, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0571131706237793, "global_step": 373744, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.129585027694702, "global_step": 373745, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1013660430908203, "global_step": 373746, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.10868239402771, "global_step": 373747, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.184720754623413, "global_step": 373748, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0355443954467773, "global_step": 373749, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1315202713012695, "global_step": 373750, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.06750750541687, "global_step": 373751, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1963865756988525, "global_step": 373752, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.049009084701538, "global_step": 373753, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1855485439300537, "global_step": 373754, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.106355905532837, "global_step": 373755, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1655116081237793, "global_step": 373756, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.225119113922119, "global_step": 373757, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0309414863586426, "global_step": 373758, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.101616382598877, "global_step": 373759, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0415937900543213, "global_step": 373760, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.144470691680908, "global_step": 373761, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.115522623062134, "global_step": 373762, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.082428216934204, "global_step": 373763, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.080437660217285, "global_step": 373764, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.035006523132324, "global_step": 373765, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1096761226654053, "global_step": 373766, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.105741024017334, "global_step": 373767, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.08671236038208, "global_step": 373768, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1368894577026367, "global_step": 373769, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.093427896499634, "global_step": 373770, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.119659900665283, "global_step": 373771, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0890471935272217, "global_step": 373772, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.17683482170105, "global_step": 373773, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.010498523712158, "global_step": 373774, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.14253306388855, "global_step": 373775, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.19103741645813, "global_step": 373776, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.107992172241211, "global_step": 373777, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.132317304611206, "global_step": 373778, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.124668836593628, "global_step": 373779, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.07104754447937, "global_step": 373780, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1172330379486084, "global_step": 373781, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0511674880981445, "global_step": 373782, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.155353546142578, "global_step": 373783, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.2052149772644043, "global_step": 373784, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1343681812286377, "global_step": 373785, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.050163984298706, "global_step": 373786, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1012566089630127, "global_step": 373787, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1158392429351807, "global_step": 373788, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.031179666519165, "global_step": 373789, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.093038320541382, "global_step": 373790, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1254796981811523, "global_step": 373791, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.118455410003662, "global_step": 373792, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1471734046936035, "global_step": 373793, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.2060365676879883, "global_step": 373794, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1536920070648193, "global_step": 373795, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1290676593780518, "global_step": 373796, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.152796506881714, "global_step": 373797, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.064603567123413, "global_step": 373798, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1882081031799316, "global_step": 373799, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1436710357666016, "global_step": 373800, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.114654064178467, "global_step": 373801, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0223991870880127, "global_step": 373802, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.139817476272583, "global_step": 373803, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0292158126831055, "global_step": 373804, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0285422801971436, "global_step": 373805, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.043438673019409, "global_step": 373806, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.096381664276123, "global_step": 373807, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.122249126434326, "global_step": 373808, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.087519645690918, "global_step": 373809, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.2002453804016113, "global_step": 373810, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0837574005126953, "global_step": 373811, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0756044387817383, "global_step": 373812, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0579113960266113, "global_step": 373813, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1454367637634277, "global_step": 373814, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0112061500549316, "global_step": 373815, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.100398302078247, "global_step": 373816, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.078632116317749, "global_step": 373817, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1842284202575684, "global_step": 373818, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0870485305786133, "global_step": 373819, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1457104682922363, "global_step": 373820, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.2120540142059326, "global_step": 373821, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0641746520996094, "global_step": 373822, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0651137828826904, "global_step": 373823, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.171588659286499, "global_step": 373824, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.123383045196533, "global_step": 373825, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.075076103210449, "global_step": 373826, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.031635284423828, "global_step": 373827, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0885517597198486, "global_step": 373828, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.040116548538208, "global_step": 373829, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.128211498260498, "global_step": 373830, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1503102779388428, "global_step": 373831, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0846664905548096, "global_step": 373832, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1572988033294678, "global_step": 373833, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.062528610229492, "global_step": 373834, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.02579927444458, "global_step": 373835, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0236029624938965, "global_step": 373836, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.00262713432312, "global_step": 373837, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0919814109802246, "global_step": 373838, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1544899940490723, "global_step": 373839, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.022986888885498, "global_step": 373840, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1633756160736084, "global_step": 373841, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.126004934310913, "global_step": 373842, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1072750091552734, "global_step": 373843, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.165536642074585, "global_step": 373844, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1124260425567627, "global_step": 373845, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0727760791778564, "global_step": 373846, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.033883571624756, "global_step": 373847, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1198456287384033, "global_step": 373848, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0388689041137695, "global_step": 373849, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.148353338241577, "global_step": 373850, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1189658641815186, "global_step": 373851, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.145984411239624, "global_step": 373852, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1039319038391113, "global_step": 373853, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1063365936279297, "global_step": 373854, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1495089530944824, "global_step": 373855, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.117157220840454, "global_step": 373856, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1329634189605713, "global_step": 373857, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1859750747680664, "global_step": 373858, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1491498947143555, "global_step": 373859, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0730247497558594, "global_step": 373860, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0694096088409424, "global_step": 373861, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1014201641082764, "global_step": 373862, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.203861951828003, "global_step": 373863, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0676748752593994, "global_step": 373864, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0698184967041016, "global_step": 373865, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1530985832214355, "global_step": 373866, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.114124298095703, "global_step": 373867, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.162597417831421, "global_step": 373868, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0846784114837646, "global_step": 373869, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.10254168510437, "global_step": 373870, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.093076467514038, "global_step": 373871, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.081277370452881, "global_step": 373872, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.179267168045044, "global_step": 373873, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1531505584716797, "global_step": 373874, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0956923961639404, "global_step": 373875, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.232041120529175, "global_step": 373876, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.151667594909668, "global_step": 373877, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.10541033744812, "global_step": 373878, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.163145065307617, "global_step": 373879, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1069765090942383, "global_step": 373880, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0219032764434814, "global_step": 373881, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.179386854171753, "global_step": 373882, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1024863719940186, "global_step": 373883, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.046839952468872, "global_step": 373884, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0677828788757324, "global_step": 373885, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0764901638031006, "global_step": 373886, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.146733522415161, "global_step": 373887, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.09084153175354, "global_step": 373888, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.040560245513916, "global_step": 373889, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1057324409484863, "global_step": 373890, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.104012966156006, "global_step": 373891, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1302168369293213, "global_step": 373892, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0687761306762695, "global_step": 373893, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.16335391998291, "global_step": 373894, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1183018684387207, "global_step": 373895, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.133676290512085, "global_step": 373896, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1937248706817627, "global_step": 373897, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0798165798187256, "global_step": 373898, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1040823459625244, "global_step": 373899, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0951218605041504, "global_step": 373900, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0873403549194336, "global_step": 373901, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0622410774230957, "global_step": 373902, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0868923664093018, "global_step": 373903, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1286513805389404, "global_step": 373904, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0947060585021973, "global_step": 373905, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1007587909698486, "global_step": 373906, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0882439613342285, "global_step": 373907, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1097426414489746, "global_step": 373908, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1923673152923584, "global_step": 373909, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1391761302948, "global_step": 373910, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1092300415039062, "global_step": 373911, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1563844680786133, "global_step": 373912, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.084296941757202, "global_step": 373913, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1406173706054688, "global_step": 373914, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1016135215759277, "global_step": 373915, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0810818672180176, "global_step": 373916, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0785539150238037, "global_step": 373917, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.027745485305786, "global_step": 373918, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.097423791885376, "global_step": 373919, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.09870982170105, "global_step": 373920, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.037982225418091, "global_step": 373921, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0776805877685547, "global_step": 373922, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.008671522140503, "global_step": 373923, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.111392021179199, "global_step": 373924, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1852924823760986, "global_step": 373925, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.109428644180298, "global_step": 373926, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0844836235046387, "global_step": 373927, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.10068678855896, "global_step": 373928, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.118523359298706, "global_step": 373929, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.076054096221924, "global_step": 373930, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1278786659240723, "global_step": 373931, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.059800386428833, "global_step": 373932, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.265597105026245, "global_step": 373933, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.124760389328003, "global_step": 373934, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.109734058380127, "global_step": 373935, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1144607067108154, "global_step": 373936, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1695728302001953, "global_step": 373937, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.159904956817627, "global_step": 373938, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1543684005737305, "global_step": 373939, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0166947841644287, "global_step": 373940, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0248172283172607, "global_step": 373941, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1632022857666016, "global_step": 373942, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.095280170440674, "global_step": 373943, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0675065517425537, "global_step": 373944, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1743826866149902, "global_step": 373945, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1526501178741455, "global_step": 373946, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0634164810180664, "global_step": 373947, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.131749391555786, "global_step": 373948, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.074134588241577, "global_step": 373949, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.136862277984619, "global_step": 373950, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1792218685150146, "global_step": 373951, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0507004261016846, "global_step": 373952, "epoch": 735, "lr": 5e-05}
{"train_loss": 1.9916776418685913, "global_step": 373953, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.050386667251587, "global_step": 373954, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.062011957168579, "global_step": 373955, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1667160987854004, "global_step": 373956, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.053182363510132, "global_step": 373957, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1602067947387695, "global_step": 373958, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1303553581237793, "global_step": 373959, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1132519245147705, "global_step": 373960, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.07658314704895, "global_step": 373961, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.110949993133545, "global_step": 373962, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.117955446243286, "global_step": 373963, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.040487766265869, "global_step": 373964, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1592204570770264, "global_step": 373965, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.152780055999756, "global_step": 373966, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0232632160186768, "global_step": 373967, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1008787155151367, "global_step": 373968, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0730040073394775, "global_step": 373969, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.046931028366089, "global_step": 373970, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1310994625091553, "global_step": 373971, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0637686252593994, "global_step": 373972, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0741658210754395, "global_step": 373973, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.157604694366455, "global_step": 373974, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1468029022216797, "global_step": 373975, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0620930194854736, "global_step": 373976, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.148941993713379, "global_step": 373977, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.123847246170044, "global_step": 373978, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1530404090881348, "global_step": 373979, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1041650772094727, "global_step": 373980, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0769965648651123, "global_step": 373981, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.125892400741577, "global_step": 373982, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.107395648956299, "global_step": 373983, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.186878204345703, "global_step": 373984, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.145315408706665, "global_step": 373985, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.098410129547119, "global_step": 373986, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.075512409210205, "global_step": 373987, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1440541744232178, "global_step": 373988, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.073073387145996, "global_step": 373989, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1074633598327637, "global_step": 373990, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.113412380218506, "global_step": 373991, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.042469024658203, "global_step": 373992, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0987162590026855, "global_step": 373993, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0502774715423584, "global_step": 373994, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.083432674407959, "global_step": 373995, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.135352373123169, "global_step": 373996, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1355786323547363, "global_step": 373997, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1263198852539062, "global_step": 373998, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.2340550422668457, "global_step": 373999, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1234896183013916, "global_step": 374000, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0948374271392822, "global_step": 374001, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.110926389694214, "global_step": 374002, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0812952518463135, "global_step": 374003, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1018142700195312, "global_step": 374004, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.142669439315796, "global_step": 374005, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1747443675994873, "global_step": 374006, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1503875255584717, "global_step": 374007, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0160458087921143, "global_step": 374008, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1296579837799072, "global_step": 374009, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.060598134994507, "global_step": 374010, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.031946897506714, "global_step": 374011, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1001179218292236, "global_step": 374012, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0171146392822266, "global_step": 374013, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0660455226898193, "global_step": 374014, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1637325286865234, "global_step": 374015, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.131204605102539, "global_step": 374016, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.120267868041992, "global_step": 374017, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0987987518310547, "global_step": 374018, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0913026332855225, "global_step": 374019, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.098829984664917, "global_step": 374020, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.112611770629883, "global_step": 374021, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.108246088027954, "global_step": 374022, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0844030380249023, "global_step": 374023, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1460773944854736, "global_step": 374024, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1645867824554443, "global_step": 374025, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.08423113822937, "global_step": 374026, "epoch": 735, "lr": 5e-05}
{"train_loss": 1.9988021850585938, "global_step": 374027, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.115551710128784, "global_step": 374028, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.12798810005188, "global_step": 374029, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0930347442626953, "global_step": 374030, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0957367420196533, "global_step": 374031, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.182323694229126, "global_step": 374032, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0357706546783447, "global_step": 374033, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1888134479522705, "global_step": 374034, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0803825855255127, "global_step": 374035, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.070176601409912, "global_step": 374036, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.143671989440918, "global_step": 374037, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1344571113586426, "global_step": 374038, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1797409057617188, "global_step": 374039, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0684592723846436, "global_step": 374040, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0179851055145264, "global_step": 374041, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.198817491531372, "global_step": 374042, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.2055938243865967, "global_step": 374043, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.127092123031616, "global_step": 374044, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.032656669616699, "global_step": 374045, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.103771448135376, "global_step": 374046, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.066580057144165, "global_step": 374047, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.11030912399292, "global_step": 374048, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0884759426116943, "global_step": 374049, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.136200189590454, "global_step": 374050, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.121488332748413, "global_step": 374051, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0982096195220947, "global_step": 374052, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.082324743270874, "global_step": 374053, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1867740154266357, "global_step": 374054, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.05845308303833, "global_step": 374055, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0589652061462402, "global_step": 374056, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1718928813934326, "global_step": 374057, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.074976921081543, "global_step": 374058, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0754921436309814, "global_step": 374059, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1154074668884277, "global_step": 374060, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1219704151153564, "global_step": 374061, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.063026189804077, "global_step": 374062, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.076427459716797, "global_step": 374063, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.148003578186035, "global_step": 374064, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.037154197692871, "global_step": 374065, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.009180784225464, "global_step": 374066, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1020867824554443, "global_step": 374067, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1310009956359863, "global_step": 374068, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0555267333984375, "global_step": 374069, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0433404445648193, "global_step": 374070, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1145904064178467, "global_step": 374071, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.050307273864746, "global_step": 374072, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0667202472686768, "global_step": 374073, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.2280991077423096, "global_step": 374074, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1103899478912354, "global_step": 374075, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.107849359512329, "global_step": 374076, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.177762985229492, "global_step": 374077, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0790529251098633, "global_step": 374078, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.230647563934326, "global_step": 374079, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0869858264923096, "global_step": 374080, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1141843795776367, "global_step": 374081, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.131558895111084, "global_step": 374082, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.131073236465454, "global_step": 374083, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0814871788024902, "global_step": 374084, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.007335662841797, "global_step": 374085, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.08668851852417, "global_step": 374086, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.090435743331909, "global_step": 374087, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1632673740386963, "global_step": 374088, "epoch": 735, "lr": 5e-05}
{"train_loss": 1.9883068799972534, "global_step": 374089, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1852848529815674, "global_step": 374090, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.099470376968384, "global_step": 374091, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.091826915740967, "global_step": 374092, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.15771484375, "global_step": 374093, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.199097156524658, "global_step": 374094, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.175157308578491, "global_step": 374095, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0878608226776123, "global_step": 374096, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.135477066040039, "global_step": 374097, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.058448553085327, "global_step": 374098, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.161576271057129, "global_step": 374099, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.137533187866211, "global_step": 374100, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.07759165763855, "global_step": 374101, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.167604684829712, "global_step": 374102, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0623929500579834, "global_step": 374103, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.119460344314575, "global_step": 374104, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.143404960632324, "global_step": 374105, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.205261468887329, "global_step": 374106, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1144065856933594, "global_step": 374107, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.138335704803467, "global_step": 374108, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0725417137145996, "global_step": 374109, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0939321517944336, "global_step": 374110, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.096212863922119, "global_step": 374111, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1333227157592773, "global_step": 374112, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0808441638946533, "global_step": 374113, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.094137668609619, "global_step": 374114, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.2166576385498047, "global_step": 374115, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0696868896484375, "global_step": 374116, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.08809494972229, "global_step": 374117, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0283889770507812, "global_step": 374118, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.020841360092163, "global_step": 374119, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0751049518585205, "global_step": 374120, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1060104370117188, "global_step": 374121, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0956645011901855, "global_step": 374122, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0796875953674316, "global_step": 374123, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.042757511138916, "global_step": 374124, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.088632822036743, "global_step": 374125, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.184445858001709, "global_step": 374126, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.172243595123291, "global_step": 374127, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1379804611206055, "global_step": 374128, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.060863971710205, "global_step": 374129, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.078890800476074, "global_step": 374130, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.074990749359131, "global_step": 374131, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.139545202255249, "global_step": 374132, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1205174922943115, "global_step": 374133, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0619657039642334, "global_step": 374134, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1833271980285645, "global_step": 374135, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.187803268432617, "global_step": 374136, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0775954723358154, "global_step": 374137, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0920281410217285, "global_step": 374138, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0746922492980957, "global_step": 374139, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1030306816101074, "global_step": 374140, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.0915215015411377, "global_step": 374141, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1779253482818604, "global_step": 374142, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.153989315032959, "global_step": 374143, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.2120630741119385, "global_step": 374144, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1642353534698486, "global_step": 374145, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.233691692352295, "global_step": 374146, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1293442249298096, "global_step": 374147, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.060547351837158, "global_step": 374148, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1558635234832764, "global_step": 374149, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1230294704437256, "global_step": 374150, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.053452730178833, "global_step": 374151, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.065729856491089, "global_step": 374152, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1152291297912598, "global_step": 374153, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1026649475097656, "global_step": 374154, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1221892833709717, "global_step": 374155, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1037518978118896, "global_step": 374156, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1080923080444336, "global_step": 374157, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.153733730316162, "global_step": 374158, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1287152767181396, "global_step": 374159, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.217237710952759, "global_step": 374160, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.055358409881592, "global_step": 374161, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1752684116363525, "global_step": 374162, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.125662326812744, "global_step": 374163, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.135979175567627, "global_step": 374164, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.2095839977264404, "global_step": 374165, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.1070568561553955, "global_step": 374166, "epoch": 735, "lr": 5e-05}
{"train_loss": 2.052905559539795, "global_step": 374167, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0243773460388184, "global_step": 374168, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.065539836883545, "global_step": 374169, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1476080417633057, "global_step": 374170, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1279499530792236, "global_step": 374171, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1229052543640137, "global_step": 374172, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0608761310577393, "global_step": 374173, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.003776788711548, "global_step": 374174, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1598434448242188, "global_step": 374175, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.142232656478882, "global_step": 374176, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.066880702972412, "global_step": 374177, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.132951021194458, "global_step": 374178, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.117295503616333, "global_step": 374179, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.132375717163086, "global_step": 374180, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.048741340637207, "global_step": 374181, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.058889150619507, "global_step": 374182, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.068852424621582, "global_step": 374183, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0240190029144287, "global_step": 374184, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0605249404907227, "global_step": 374185, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.079702377319336, "global_step": 374186, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0703649520874023, "global_step": 374187, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0305135250091553, "global_step": 374188, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0237362384796143, "global_step": 374189, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.042006015777588, "global_step": 374190, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.077915906906128, "global_step": 374191, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.074882745742798, "global_step": 374192, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1209776401519775, "global_step": 374193, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0564944744110107, "global_step": 374194, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1191036701202393, "global_step": 374195, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.131586790084839, "global_step": 374196, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1436805725097656, "global_step": 374197, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.157228469848633, "global_step": 374198, "epoch": 736, "lr": 5e-05}
{"train_loss": 1.9956541061401367, "global_step": 374199, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.140361785888672, "global_step": 374200, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.178201675415039, "global_step": 374201, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.061086654663086, "global_step": 374202, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.107175827026367, "global_step": 374203, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0098068714141846, "global_step": 374204, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1275179386138916, "global_step": 374205, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.13128662109375, "global_step": 374206, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.056159734725952, "global_step": 374207, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.034566640853882, "global_step": 374208, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0922884941101074, "global_step": 374209, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0626327991485596, "global_step": 374210, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.160064220428467, "global_step": 374211, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0438520908355713, "global_step": 374212, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.029778480529785, "global_step": 374213, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.149458169937134, "global_step": 374214, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1485722064971924, "global_step": 374215, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0379064083099365, "global_step": 374216, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0430519580841064, "global_step": 374217, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.100665807723999, "global_step": 374218, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1181883811950684, "global_step": 374219, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.087759256362915, "global_step": 374220, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.2071685791015625, "global_step": 374221, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1241519451141357, "global_step": 374222, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.171553373336792, "global_step": 374223, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1336722373962402, "global_step": 374224, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0964584350585938, "global_step": 374225, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1277763843536377, "global_step": 374226, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.080375909805298, "global_step": 374227, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0878896713256836, "global_step": 374228, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.06486439704895, "global_step": 374229, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0529556274414062, "global_step": 374230, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.129660129547119, "global_step": 374231, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1055908203125, "global_step": 374232, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1466917991638184, "global_step": 374233, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.06156063079834, "global_step": 374234, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1331892013549805, "global_step": 374235, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0579628944396973, "global_step": 374236, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.128230094909668, "global_step": 374237, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1356396675109863, "global_step": 374238, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.186671018600464, "global_step": 374239, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.093782663345337, "global_step": 374240, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1578738689422607, "global_step": 374241, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.147984266281128, "global_step": 374242, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1012661457061768, "global_step": 374243, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.139552354812622, "global_step": 374244, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0972297191619873, "global_step": 374245, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.129931688308716, "global_step": 374246, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.067382335662842, "global_step": 374247, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1229324340820312, "global_step": 374248, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.002988338470459, "global_step": 374249, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.173164129257202, "global_step": 374250, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0144782066345215, "global_step": 374251, "epoch": 736, "lr": 5e-05}
{"train_loss": 1.9982192516326904, "global_step": 374252, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.052309513092041, "global_step": 374253, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0915725231170654, "global_step": 374254, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.014263391494751, "global_step": 374255, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1190249919891357, "global_step": 374256, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1516289710998535, "global_step": 374257, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.088822364807129, "global_step": 374258, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1557140350341797, "global_step": 374259, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1104557514190674, "global_step": 374260, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.04780912399292, "global_step": 374261, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0903208255767822, "global_step": 374262, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.061250686645508, "global_step": 374263, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.177417039871216, "global_step": 374264, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1434433460235596, "global_step": 374265, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.128434896469116, "global_step": 374266, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1204473972320557, "global_step": 374267, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0845072269439697, "global_step": 374268, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.03834867477417, "global_step": 374269, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1114745140075684, "global_step": 374270, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1789326667785645, "global_step": 374271, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1508615016937256, "global_step": 374272, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.057468891143799, "global_step": 374273, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.10915470123291, "global_step": 374274, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1634979248046875, "global_step": 374275, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.139029026031494, "global_step": 374276, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1339356899261475, "global_step": 374277, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1483137607574463, "global_step": 374278, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1057608127593994, "global_step": 374279, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.075279474258423, "global_step": 374280, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0390608310699463, "global_step": 374281, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1440412998199463, "global_step": 374282, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1254560947418213, "global_step": 374283, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1811981201171875, "global_step": 374284, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.051914691925049, "global_step": 374285, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.070495128631592, "global_step": 374286, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.015068769454956, "global_step": 374287, "epoch": 736, "lr": 5e-05}
{"train_loss": 1.999779224395752, "global_step": 374288, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.132631301879883, "global_step": 374289, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0384373664855957, "global_step": 374290, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.124455690383911, "global_step": 374291, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.059725522994995, "global_step": 374292, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1463072299957275, "global_step": 374293, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.187152862548828, "global_step": 374294, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.074721336364746, "global_step": 374295, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.113495111465454, "global_step": 374296, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.118288278579712, "global_step": 374297, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.127211570739746, "global_step": 374298, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1241397857666016, "global_step": 374299, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.038087844848633, "global_step": 374300, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1332602500915527, "global_step": 374301, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.06669282913208, "global_step": 374302, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.062843084335327, "global_step": 374303, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1230151653289795, "global_step": 374304, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0415120124816895, "global_step": 374305, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.111358404159546, "global_step": 374306, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.069532871246338, "global_step": 374307, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.061663866043091, "global_step": 374308, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.100290536880493, "global_step": 374309, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0403971672058105, "global_step": 374310, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.074866771697998, "global_step": 374311, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1070356369018555, "global_step": 374312, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0911765098571777, "global_step": 374313, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.023240804672241, "global_step": 374314, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.093353509902954, "global_step": 374315, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1080801486968994, "global_step": 374316, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.056252956390381, "global_step": 374317, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1077165603637695, "global_step": 374318, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.031989574432373, "global_step": 374319, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.041707754135132, "global_step": 374320, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.123286485671997, "global_step": 374321, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.140019655227661, "global_step": 374322, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1885712146759033, "global_step": 374323, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.087736129760742, "global_step": 374324, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.148695707321167, "global_step": 374325, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.113994836807251, "global_step": 374326, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.072178840637207, "global_step": 374327, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0706536769866943, "global_step": 374328, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0717291831970215, "global_step": 374329, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0666322708129883, "global_step": 374330, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0815398693084717, "global_step": 374331, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0935797691345215, "global_step": 374332, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.138314723968506, "global_step": 374333, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.089277982711792, "global_step": 374334, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1278443336486816, "global_step": 374335, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.077653408050537, "global_step": 374336, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0682804584503174, "global_step": 374337, "epoch": 736, "lr": 5e-05}
{"train_loss": 1.959957480430603, "global_step": 374338, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.084796905517578, "global_step": 374339, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.12898588180542, "global_step": 374340, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.067476511001587, "global_step": 374341, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.153158664703369, "global_step": 374342, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0774309635162354, "global_step": 374343, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0075182914733887, "global_step": 374344, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.208089828491211, "global_step": 374345, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.09932804107666, "global_step": 374346, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.039597272872925, "global_step": 374347, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1255581378936768, "global_step": 374348, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0852813720703125, "global_step": 374349, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1192519664764404, "global_step": 374350, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0699732303619385, "global_step": 374351, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0517544746398926, "global_step": 374352, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.102186918258667, "global_step": 374353, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1127023696899414, "global_step": 374354, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.123602867126465, "global_step": 374355, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.149738073348999, "global_step": 374356, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.049715757369995, "global_step": 374357, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1233315467834473, "global_step": 374358, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1511435508728027, "global_step": 374359, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0146782398223877, "global_step": 374360, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0831196308135986, "global_step": 374361, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.118879795074463, "global_step": 374362, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.195850372314453, "global_step": 374363, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1357979774475098, "global_step": 374364, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1881072521209717, "global_step": 374365, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0130653381347656, "global_step": 374366, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.06488037109375, "global_step": 374367, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.077854633331299, "global_step": 374368, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.08286190032959, "global_step": 374369, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.057075023651123, "global_step": 374370, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1568052768707275, "global_step": 374371, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.125234365463257, "global_step": 374372, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.067561388015747, "global_step": 374373, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.069659948348999, "global_step": 374374, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1273317337036133, "global_step": 374375, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1450376510620117, "global_step": 374376, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1972527503967285, "global_step": 374377, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1131696701049805, "global_step": 374378, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.074953556060791, "global_step": 374379, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0232770442962646, "global_step": 374380, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.107297420501709, "global_step": 374381, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1378166675567627, "global_step": 374382, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0866692066192627, "global_step": 374383, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0972838401794434, "global_step": 374384, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1188805103302, "global_step": 374385, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.173478603363037, "global_step": 374386, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0199060440063477, "global_step": 374387, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.136814832687378, "global_step": 374388, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.057586908340454, "global_step": 374389, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0838048458099365, "global_step": 374390, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1787803173065186, "global_step": 374391, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0365445613861084, "global_step": 374392, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.053140163421631, "global_step": 374393, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.108971118927002, "global_step": 374394, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1232056617736816, "global_step": 374395, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.005627393722534, "global_step": 374396, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.152256488800049, "global_step": 374397, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.104779005050659, "global_step": 374398, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0532679557800293, "global_step": 374399, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1315741539001465, "global_step": 374400, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.200629234313965, "global_step": 374401, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.087031364440918, "global_step": 374402, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1569502353668213, "global_step": 374403, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1035006046295166, "global_step": 374404, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.112199306488037, "global_step": 374405, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.003451347351074, "global_step": 374406, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.082685947418213, "global_step": 374407, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.126694917678833, "global_step": 374408, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0964295864105225, "global_step": 374409, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.116144895553589, "global_step": 374410, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0380771160125732, "global_step": 374411, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1246418952941895, "global_step": 374412, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.142848014831543, "global_step": 374413, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.08235502243042, "global_step": 374414, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1583776473999023, "global_step": 374415, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.051326274871826, "global_step": 374416, "epoch": 736, "lr": 5e-05}
{"train_loss": 1.9996436834335327, "global_step": 374417, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.127854347229004, "global_step": 374418, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.068844795227051, "global_step": 374419, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.085024118423462, "global_step": 374420, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.107962131500244, "global_step": 374421, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.203911542892456, "global_step": 374422, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0819814205169678, "global_step": 374423, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1602859497070312, "global_step": 374424, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0634078979492188, "global_step": 374425, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.112569570541382, "global_step": 374426, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.184014320373535, "global_step": 374427, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.087963819503784, "global_step": 374428, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.077360153198242, "global_step": 374429, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1591053009033203, "global_step": 374430, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.16064453125, "global_step": 374431, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0887043476104736, "global_step": 374432, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1336376667022705, "global_step": 374433, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.146637201309204, "global_step": 374434, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1153924465179443, "global_step": 374435, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1171162128448486, "global_step": 374436, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0540590286254883, "global_step": 374437, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1264772415161133, "global_step": 374438, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.070493459701538, "global_step": 374439, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.068591594696045, "global_step": 374440, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.185483455657959, "global_step": 374441, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0787672996520996, "global_step": 374442, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.051234245300293, "global_step": 374443, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1235594749450684, "global_step": 374444, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1122710704803467, "global_step": 374445, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.110403299331665, "global_step": 374446, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1449215412139893, "global_step": 374447, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1112148761749268, "global_step": 374448, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.150125503540039, "global_step": 374449, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1661715507507324, "global_step": 374450, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1052513122558594, "global_step": 374451, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1144962310791016, "global_step": 374452, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1665823459625244, "global_step": 374453, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.086970806121826, "global_step": 374454, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.097904920578003, "global_step": 374455, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.188096046447754, "global_step": 374456, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1258385181427, "global_step": 374457, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.03411602973938, "global_step": 374458, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.175227165222168, "global_step": 374459, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1251132488250732, "global_step": 374460, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.148918867111206, "global_step": 374461, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0662918090820312, "global_step": 374462, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.096210241317749, "global_step": 374463, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.154340982437134, "global_step": 374464, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1057801246643066, "global_step": 374465, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1082146167755127, "global_step": 374466, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.157358407974243, "global_step": 374467, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0961050987243652, "global_step": 374468, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1255431175231934, "global_step": 374469, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0880866050720215, "global_step": 374470, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.205139636993408, "global_step": 374471, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.059962034225464, "global_step": 374472, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.11438250541687, "global_step": 374473, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0024406909942627, "global_step": 374474, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.100080728530884, "global_step": 374475, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1984658241271973, "global_step": 374476, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0299761295318604, "global_step": 374477, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.105109453201294, "global_step": 374478, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.052722215652466, "global_step": 374479, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1449084281921387, "global_step": 374480, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0814452171325684, "global_step": 374481, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.077620506286621, "global_step": 374482, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1407721042633057, "global_step": 374483, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0647826194763184, "global_step": 374484, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.143080472946167, "global_step": 374485, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.124000072479248, "global_step": 374486, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.194573163986206, "global_step": 374487, "epoch": 736, "lr": 5e-05}
{"train_loss": 1.9941649436950684, "global_step": 374488, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0860447883605957, "global_step": 374489, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1538076400756836, "global_step": 374490, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0801010131835938, "global_step": 374491, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0748744010925293, "global_step": 374492, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0268466472625732, "global_step": 374493, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1028494834899902, "global_step": 374494, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.126344680786133, "global_step": 374495, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.076387882232666, "global_step": 374496, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0526607036590576, "global_step": 374497, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.151010036468506, "global_step": 374498, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.130603313446045, "global_step": 374499, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.181755542755127, "global_step": 374500, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1236751079559326, "global_step": 374501, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.083209753036499, "global_step": 374502, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1830079555511475, "global_step": 374503, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.072761058807373, "global_step": 374504, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0269532203674316, "global_step": 374505, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1376595497131348, "global_step": 374506, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.042173385620117, "global_step": 374507, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.046795129776001, "global_step": 374508, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.089003324508667, "global_step": 374509, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0502030849456787, "global_step": 374510, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1760716438293457, "global_step": 374511, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.09540057182312, "global_step": 374512, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.041172981262207, "global_step": 374513, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0864038467407227, "global_step": 374514, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0933496952056885, "global_step": 374515, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.093682289123535, "global_step": 374516, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.162522077560425, "global_step": 374517, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0648529529571533, "global_step": 374518, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.022648811340332, "global_step": 374519, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.176694393157959, "global_step": 374520, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1064791679382324, "global_step": 374521, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.112290382385254, "global_step": 374522, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.2357938289642334, "global_step": 374523, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1737043857574463, "global_step": 374524, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.107840061187744, "global_step": 374525, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.115640163421631, "global_step": 374526, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.084871530532837, "global_step": 374527, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.205629348754883, "global_step": 374528, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0997819900512695, "global_step": 374529, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0738115310668945, "global_step": 374530, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.065206289291382, "global_step": 374531, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.072141647338867, "global_step": 374532, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1864964962005615, "global_step": 374533, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.032543420791626, "global_step": 374534, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.166537284851074, "global_step": 374535, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1187374591827393, "global_step": 374536, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.041135787963867, "global_step": 374537, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0977041721343994, "global_step": 374538, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1302108764648438, "global_step": 374539, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.132688522338867, "global_step": 374540, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.030402898788452, "global_step": 374541, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0748510360717773, "global_step": 374542, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.104323625564575, "global_step": 374543, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.017793655395508, "global_step": 374544, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1447060108184814, "global_step": 374545, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.057363986968994, "global_step": 374546, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1022374629974365, "global_step": 374547, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.17108154296875, "global_step": 374548, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1101181507110596, "global_step": 374549, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1535379886627197, "global_step": 374550, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0204474925994873, "global_step": 374551, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1622250080108643, "global_step": 374552, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.052781105041504, "global_step": 374553, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1492269039154053, "global_step": 374554, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.021812915802002, "global_step": 374555, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.114633321762085, "global_step": 374556, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.034273147583008, "global_step": 374557, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1522915363311768, "global_step": 374558, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1728639602661133, "global_step": 374559, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.05924391746521, "global_step": 374560, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1023149490356445, "global_step": 374561, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.080611228942871, "global_step": 374562, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.254375696182251, "global_step": 374563, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0291290283203125, "global_step": 374564, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0895884037017822, "global_step": 374565, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.139866352081299, "global_step": 374566, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1159536838531494, "global_step": 374567, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.2081222534179688, "global_step": 374568, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1201443672180176, "global_step": 374569, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1188082695007324, "global_step": 374570, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.119889497756958, "global_step": 374571, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.15142560005188, "global_step": 374572, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.060530662536621, "global_step": 374573, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.13252854347229, "global_step": 374574, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0481412410736084, "global_step": 374575, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.110124111175537, "global_step": 374576, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0651848316192627, "global_step": 374577, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.115859270095825, "global_step": 374578, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0532102584838867, "global_step": 374579, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.093919277191162, "global_step": 374580, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1179490089416504, "global_step": 374581, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.108419895172119, "global_step": 374582, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.12044620513916, "global_step": 374583, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.042126178741455, "global_step": 374584, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0793263912200928, "global_step": 374585, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0366580486297607, "global_step": 374586, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1548941135406494, "global_step": 374587, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1726431846618652, "global_step": 374588, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.140568733215332, "global_step": 374589, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0875632762908936, "global_step": 374590, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1498777866363525, "global_step": 374591, "epoch": 736, "lr": 5e-05}
{"train_loss": 1.9926966428756714, "global_step": 374592, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1193058490753174, "global_step": 374593, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0903990268707275, "global_step": 374594, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.082629680633545, "global_step": 374595, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0944957733154297, "global_step": 374596, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1034886837005615, "global_step": 374597, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1928560733795166, "global_step": 374598, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.173830509185791, "global_step": 374599, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.16923451423645, "global_step": 374600, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1694555282592773, "global_step": 374601, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.055767059326172, "global_step": 374602, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0911762714385986, "global_step": 374603, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1438112258911133, "global_step": 374604, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.087207078933716, "global_step": 374605, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.067737340927124, "global_step": 374606, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.155069351196289, "global_step": 374607, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.079824447631836, "global_step": 374608, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1317243576049805, "global_step": 374609, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1692042350769043, "global_step": 374610, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1610069274902344, "global_step": 374611, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.13647198677063, "global_step": 374612, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1078834533691406, "global_step": 374613, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1435134410858154, "global_step": 374614, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.171938419342041, "global_step": 374615, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1414225101470947, "global_step": 374616, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.073031425476074, "global_step": 374617, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1579623222351074, "global_step": 374618, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.048403739929199, "global_step": 374619, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1467509269714355, "global_step": 374620, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.146747350692749, "global_step": 374621, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0574333667755127, "global_step": 374622, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0864059925079346, "global_step": 374623, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1478195190429688, "global_step": 374624, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.008530378341675, "global_step": 374625, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.126897096633911, "global_step": 374626, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0771358013153076, "global_step": 374627, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.107516288757324, "global_step": 374628, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.149888277053833, "global_step": 374629, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1306657791137695, "global_step": 374630, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.115731954574585, "global_step": 374631, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1198654174804688, "global_step": 374632, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.12609601020813, "global_step": 374633, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0823159217834473, "global_step": 374634, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0417449474334717, "global_step": 374635, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0416486263275146, "global_step": 374636, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.078657865524292, "global_step": 374637, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0960938930511475, "global_step": 374638, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.063093662261963, "global_step": 374639, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1325249671936035, "global_step": 374640, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1102242469787598, "global_step": 374641, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.173457622528076, "global_step": 374642, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.056849241256714, "global_step": 374643, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.099871873855591, "global_step": 374644, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1556732654571533, "global_step": 374645, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1173195838928223, "global_step": 374646, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0583512783050537, "global_step": 374647, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1484298706054688, "global_step": 374648, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0827770233154297, "global_step": 374649, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.160074234008789, "global_step": 374650, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.07039737701416, "global_step": 374651, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1217072010040283, "global_step": 374652, "epoch": 736, "lr": 5e-05}
{"train_loss": 1.9953739643096924, "global_step": 374653, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.062562942504883, "global_step": 374654, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.124269485473633, "global_step": 374655, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0355679988861084, "global_step": 374656, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.131014347076416, "global_step": 374657, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0081825256347656, "global_step": 374658, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.028648614883423, "global_step": 374659, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0306220054626465, "global_step": 374660, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1391854286193848, "global_step": 374661, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0972700119018555, "global_step": 374662, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1820359230041504, "global_step": 374663, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0555522441864014, "global_step": 374664, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0833396911621094, "global_step": 374665, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.102513074874878, "global_step": 374666, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1256229877471924, "global_step": 374667, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1005918979644775, "global_step": 374668, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.17209529876709, "global_step": 374669, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1789679527282715, "global_step": 374670, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1349122524261475, "global_step": 374671, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1699745655059814, "global_step": 374672, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1181540489196777, "global_step": 374673, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.174748420715332, "global_step": 374674, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0842630863189697, "global_step": 374675, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1427202224731445, "global_step": 374676, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.062203884124756, "global_step": 374677, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0363757610321045, "global_step": 374678, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.193256378173828, "global_step": 374679, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1471197605133057, "global_step": 374680, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0204737186431885, "global_step": 374681, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0901730060577393, "global_step": 374682, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0483806133270264, "global_step": 374683, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1389708518981934, "global_step": 374684, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0592761039733887, "global_step": 374685, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0882322788238525, "global_step": 374686, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.102299213409424, "global_step": 374687, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0980451107025146, "global_step": 374688, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.163473129272461, "global_step": 374689, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.147982597351074, "global_step": 374690, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.072434425354004, "global_step": 374691, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1367506980895996, "global_step": 374692, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.048020124435425, "global_step": 374693, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.092906951904297, "global_step": 374694, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.043093204498291, "global_step": 374695, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0955007076263428, "global_step": 374696, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.2259902954101562, "global_step": 374697, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.140465497970581, "global_step": 374698, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.161121368408203, "global_step": 374699, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0490188598632812, "global_step": 374700, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1551930904388428, "global_step": 374701, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1379377841949463, "global_step": 374702, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0373313426971436, "global_step": 374703, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1450116634368896, "global_step": 374704, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1937477588653564, "global_step": 374705, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.145585775375366, "global_step": 374706, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1539013385772705, "global_step": 374707, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0650177001953125, "global_step": 374708, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.12583589553833, "global_step": 374709, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1567888259887695, "global_step": 374710, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1936185359954834, "global_step": 374711, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1041481494903564, "global_step": 374712, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1445634365081787, "global_step": 374713, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.089322566986084, "global_step": 374714, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.055938959121704, "global_step": 374715, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0367612838745117, "global_step": 374716, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0724451541900635, "global_step": 374717, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.128969669342041, "global_step": 374718, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1330370903015137, "global_step": 374719, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.128187656402588, "global_step": 374720, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.097461223602295, "global_step": 374721, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.09853458404541, "global_step": 374722, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1327004432678223, "global_step": 374723, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1051416397094727, "global_step": 374724, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.20950984954834, "global_step": 374725, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0982635021209717, "global_step": 374726, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.2020912170410156, "global_step": 374727, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0731687545776367, "global_step": 374728, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.116004467010498, "global_step": 374729, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.141615152359009, "global_step": 374730, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.104294776916504, "global_step": 374731, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.134153366088867, "global_step": 374732, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0792016983032227, "global_step": 374733, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.10895037651062, "global_step": 374734, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.125972032546997, "global_step": 374735, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.114091634750366, "global_step": 374736, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0667827129364014, "global_step": 374737, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1058595180511475, "global_step": 374738, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.138584852218628, "global_step": 374739, "epoch": 736, "lr": 5e-05}
{"train_loss": 1.9779008626937866, "global_step": 374740, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1019437313079834, "global_step": 374741, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.100224494934082, "global_step": 374742, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1381282806396484, "global_step": 374743, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0890660285949707, "global_step": 374744, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.065610408782959, "global_step": 374745, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1021223068237305, "global_step": 374746, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0455172061920166, "global_step": 374747, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.096179485321045, "global_step": 374748, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.15289306640625, "global_step": 374749, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1430766582489014, "global_step": 374750, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1305596828460693, "global_step": 374751, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.031254768371582, "global_step": 374752, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1195755004882812, "global_step": 374753, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.089301824569702, "global_step": 374754, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.127676486968994, "global_step": 374755, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0609445571899414, "global_step": 374756, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1039180755615234, "global_step": 374757, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0950984954833984, "global_step": 374758, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.177898406982422, "global_step": 374759, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1259889602661133, "global_step": 374760, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0657715797424316, "global_step": 374761, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1718437671661377, "global_step": 374762, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.217768669128418, "global_step": 374763, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1556005477905273, "global_step": 374764, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1977715492248535, "global_step": 374765, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.081584930419922, "global_step": 374766, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1457934379577637, "global_step": 374767, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.049922227859497, "global_step": 374768, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1794161796569824, "global_step": 374769, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.075908660888672, "global_step": 374770, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.130873441696167, "global_step": 374771, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.049105167388916, "global_step": 374772, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1858572959899902, "global_step": 374773, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.022212505340576, "global_step": 374774, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.070533037185669, "global_step": 374775, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1293678283691406, "global_step": 374776, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.064948081970215, "global_step": 374777, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0898845195770264, "global_step": 374778, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1556882858276367, "global_step": 374779, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0107152462005615, "global_step": 374780, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.088022470474243, "global_step": 374781, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.110837697982788, "global_step": 374782, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1440675258636475, "global_step": 374783, "epoch": 736, "lr": 5e-05}
{"train_loss": 1.980486512184143, "global_step": 374784, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1642820835113525, "global_step": 374785, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.081585168838501, "global_step": 374786, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0774855613708496, "global_step": 374787, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.208422899246216, "global_step": 374788, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0631542205810547, "global_step": 374789, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0992767810821533, "global_step": 374790, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1190106868743896, "global_step": 374791, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.153639078140259, "global_step": 374792, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.089378595352173, "global_step": 374793, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1790783405303955, "global_step": 374794, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.094313621520996, "global_step": 374795, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.2215733528137207, "global_step": 374796, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0577094554901123, "global_step": 374797, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.029517650604248, "global_step": 374798, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1247897148132324, "global_step": 374799, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1268625259399414, "global_step": 374800, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1667168140411377, "global_step": 374801, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.145435094833374, "global_step": 374802, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.104156494140625, "global_step": 374803, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1209449768066406, "global_step": 374804, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0308005809783936, "global_step": 374805, "epoch": 736, "lr": 5e-05}
{"train_loss": 1.988935112953186, "global_step": 374806, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.164451837539673, "global_step": 374807, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0890798568725586, "global_step": 374808, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.071805477142334, "global_step": 374809, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.09043025970459, "global_step": 374810, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.12518048286438, "global_step": 374811, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.063769578933716, "global_step": 374812, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.113642454147339, "global_step": 374813, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1130385398864746, "global_step": 374814, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.11580228805542, "global_step": 374815, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1478195190429688, "global_step": 374816, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1434717178344727, "global_step": 374817, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.165724039077759, "global_step": 374818, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.127129554748535, "global_step": 374819, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1142866611480713, "global_step": 374820, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0416488647460938, "global_step": 374821, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.200021266937256, "global_step": 374822, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.12017822265625, "global_step": 374823, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.069932460784912, "global_step": 374824, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.161907196044922, "global_step": 374825, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1803998947143555, "global_step": 374826, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1732871532440186, "global_step": 374827, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.08594012260437, "global_step": 374828, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.165428876876831, "global_step": 374829, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1054623126983643, "global_step": 374830, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1659209728240967, "global_step": 374831, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.096282720565796, "global_step": 374832, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1067190170288086, "global_step": 374833, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1828649044036865, "global_step": 374834, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.135254144668579, "global_step": 374835, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0761377811431885, "global_step": 374836, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0621228218078613, "global_step": 374837, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0641610622406006, "global_step": 374838, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.173043727874756, "global_step": 374839, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0923361778259277, "global_step": 374840, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.189647912979126, "global_step": 374841, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.220862865447998, "global_step": 374842, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1713802814483643, "global_step": 374843, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1793155670166016, "global_step": 374844, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.150022029876709, "global_step": 374845, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0062851905822754, "global_step": 374846, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1730880737304688, "global_step": 374847, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.124042510986328, "global_step": 374848, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0426321029663086, "global_step": 374849, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1854915618896484, "global_step": 374850, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1812803745269775, "global_step": 374851, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.060772657394409, "global_step": 374852, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0826687812805176, "global_step": 374853, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0682356357574463, "global_step": 374854, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1230838298797607, "global_step": 374855, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0238351821899414, "global_step": 374856, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.136593818664551, "global_step": 374857, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0975759029388428, "global_step": 374858, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1245083808898926, "global_step": 374859, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1129400730133057, "global_step": 374860, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1372294425964355, "global_step": 374861, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1841301918029785, "global_step": 374862, "epoch": 736, "lr": 5e-05}
{"train_loss": 1.9416992664337158, "global_step": 374863, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1701507568359375, "global_step": 374864, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1182825565338135, "global_step": 374865, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.097834587097168, "global_step": 374866, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.063890218734741, "global_step": 374867, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0563790798187256, "global_step": 374868, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0622315406799316, "global_step": 374869, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1637611389160156, "global_step": 374870, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1318514347076416, "global_step": 374871, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0200693607330322, "global_step": 374872, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1090166568756104, "global_step": 374873, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1738505363464355, "global_step": 374874, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1498959064483643, "global_step": 374875, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.11834979057312, "global_step": 374876, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.202213764190674, "global_step": 374877, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.039997100830078, "global_step": 374878, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.074826717376709, "global_step": 374879, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0647132396698, "global_step": 374880, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1571707725524902, "global_step": 374881, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.090041399002075, "global_step": 374882, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1124603748321533, "global_step": 374883, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.065140724182129, "global_step": 374884, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0351827144622803, "global_step": 374885, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0738418102264404, "global_step": 374886, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1372122764587402, "global_step": 374887, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.103085517883301, "global_step": 374888, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1595652103424072, "global_step": 374889, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.060810089111328, "global_step": 374890, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0243828296661377, "global_step": 374891, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.164663314819336, "global_step": 374892, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.056349277496338, "global_step": 374893, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.047057867050171, "global_step": 374894, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0934412479400635, "global_step": 374895, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0499343872070312, "global_step": 374896, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1392600536346436, "global_step": 374897, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0666682720184326, "global_step": 374898, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.059917688369751, "global_step": 374899, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.127821207046509, "global_step": 374900, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.148284673690796, "global_step": 374901, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.10025691986084, "global_step": 374902, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.144012689590454, "global_step": 374903, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0934762954711914, "global_step": 374904, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.2212870121002197, "global_step": 374905, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.145547389984131, "global_step": 374906, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.143311023712158, "global_step": 374907, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.150137424468994, "global_step": 374908, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0294787883758545, "global_step": 374909, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.032104969024658, "global_step": 374910, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.2944579124450684, "global_step": 374911, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.193695306777954, "global_step": 374912, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.124925374984741, "global_step": 374913, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1416211128234863, "global_step": 374914, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0738117694854736, "global_step": 374915, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.091888666152954, "global_step": 374916, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.089064121246338, "global_step": 374917, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.194474220275879, "global_step": 374918, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.104586362838745, "global_step": 374919, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.103567600250244, "global_step": 374920, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1214842796325684, "global_step": 374921, "epoch": 736, "lr": 5e-05}
{"train_loss": 1.9844914674758911, "global_step": 374922, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0051679611206055, "global_step": 374923, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1249420642852783, "global_step": 374924, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0964810848236084, "global_step": 374925, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.112056016921997, "global_step": 374926, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0979208946228027, "global_step": 374927, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.147763252258301, "global_step": 374928, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0958547592163086, "global_step": 374929, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.076124429702759, "global_step": 374930, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1309432983398438, "global_step": 374931, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0040934085845947, "global_step": 374932, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1076273918151855, "global_step": 374933, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1193149089813232, "global_step": 374934, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.035722017288208, "global_step": 374935, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.2069075107574463, "global_step": 374936, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.228276252746582, "global_step": 374937, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1196439266204834, "global_step": 374938, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1546404361724854, "global_step": 374939, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.123673677444458, "global_step": 374940, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0425140857696533, "global_step": 374941, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.164668083190918, "global_step": 374942, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1038239002227783, "global_step": 374943, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.107913017272949, "global_step": 374944, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.189662456512451, "global_step": 374945, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.111107110977173, "global_step": 374946, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.054661273956299, "global_step": 374947, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.151488780975342, "global_step": 374948, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1848721504211426, "global_step": 374949, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.013737201690674, "global_step": 374950, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.060208797454834, "global_step": 374951, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.162036895751953, "global_step": 374952, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0417089462280273, "global_step": 374953, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.078676700592041, "global_step": 374954, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0490663051605225, "global_step": 374955, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0876529216766357, "global_step": 374956, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.128190279006958, "global_step": 374957, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0239617824554443, "global_step": 374958, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0988855361938477, "global_step": 374959, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1691367626190186, "global_step": 374960, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0598413944244385, "global_step": 374961, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1275177001953125, "global_step": 374962, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.172576665878296, "global_step": 374963, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.132117986679077, "global_step": 374964, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.084885597229004, "global_step": 374965, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0960514545440674, "global_step": 374966, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1349713802337646, "global_step": 374967, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.190915584564209, "global_step": 374968, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1319422721862793, "global_step": 374969, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.034137010574341, "global_step": 374970, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1259043216705322, "global_step": 374971, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.089465379714966, "global_step": 374972, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1162121295928955, "global_step": 374973, "epoch": 736, "lr": 5e-05}
{"train_loss": 1.970881700515747, "global_step": 374974, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1617026329040527, "global_step": 374975, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.170332431793213, "global_step": 374976, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0954854488372803, "global_step": 374977, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.126960039138794, "global_step": 374978, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.07643985748291, "global_step": 374979, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1276605129241943, "global_step": 374980, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1928179264068604, "global_step": 374981, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1096668243408203, "global_step": 374982, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.197035551071167, "global_step": 374983, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.210278034210205, "global_step": 374984, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.158987522125244, "global_step": 374985, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1023714542388916, "global_step": 374986, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1236181259155273, "global_step": 374987, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.098043203353882, "global_step": 374988, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.121251106262207, "global_step": 374989, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1385319232940674, "global_step": 374990, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.130453586578369, "global_step": 374991, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.119236946105957, "global_step": 374992, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0932114124298096, "global_step": 374993, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.110072612762451, "global_step": 374994, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.004190683364868, "global_step": 374995, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1650922298431396, "global_step": 374996, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.045753002166748, "global_step": 374997, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1374330520629883, "global_step": 374998, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0965895652770996, "global_step": 374999, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0928845405578613, "global_step": 375000, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.089629888534546, "global_step": 375001, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1293437480926514, "global_step": 375002, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0928025245666504, "global_step": 375003, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.063375234603882, "global_step": 375004, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.055264711380005, "global_step": 375005, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0886497497558594, "global_step": 375006, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.153912305831909, "global_step": 375007, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.166480779647827, "global_step": 375008, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.117680549621582, "global_step": 375009, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1581225395202637, "global_step": 375010, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0922133922576904, "global_step": 375011, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0855278968811035, "global_step": 375012, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0576844215393066, "global_step": 375013, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.065272808074951, "global_step": 375014, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1213905811309814, "global_step": 375015, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.121800422668457, "global_step": 375016, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0807344913482666, "global_step": 375017, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0397002696990967, "global_step": 375018, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0758233070373535, "global_step": 375019, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0881733894348145, "global_step": 375020, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1346583366394043, "global_step": 375021, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.12275767326355, "global_step": 375022, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0805118083953857, "global_step": 375023, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1918869018554688, "global_step": 375024, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.110252618789673, "global_step": 375025, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1760478019714355, "global_step": 375026, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.058015823364258, "global_step": 375027, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.021599292755127, "global_step": 375028, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1061551570892334, "global_step": 375029, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1580233573913574, "global_step": 375030, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1064372062683105, "global_step": 375031, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0983853340148926, "global_step": 375032, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1860427856445312, "global_step": 375033, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.085897922515869, "global_step": 375034, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1118478775024414, "global_step": 375035, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.145939350128174, "global_step": 375036, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.048696517944336, "global_step": 375037, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.066138505935669, "global_step": 375038, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.147900104522705, "global_step": 375039, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.059542179107666, "global_step": 375040, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1225745677948, "global_step": 375041, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1601524353027344, "global_step": 375042, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1039774417877197, "global_step": 375043, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1280300617218018, "global_step": 375044, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.183769702911377, "global_step": 375045, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0616493225097656, "global_step": 375046, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.2104363441467285, "global_step": 375047, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1168251037597656, "global_step": 375048, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1793017387390137, "global_step": 375049, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0298099517822266, "global_step": 375050, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0904901027679443, "global_step": 375051, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1624462604522705, "global_step": 375052, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0806405544281006, "global_step": 375053, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.082831382751465, "global_step": 375054, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0889596939086914, "global_step": 375055, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.127492904663086, "global_step": 375056, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0851705074310303, "global_step": 375057, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.070614814758301, "global_step": 375058, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1836585998535156, "global_step": 375059, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.155280351638794, "global_step": 375060, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.128199577331543, "global_step": 375061, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.130948066711426, "global_step": 375062, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1036500930786133, "global_step": 375063, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1030261516571045, "global_step": 375064, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.134783983230591, "global_step": 375065, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1311213970184326, "global_step": 375066, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.146223783493042, "global_step": 375067, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0780961513519287, "global_step": 375068, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0966238975524902, "global_step": 375069, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.114548444747925, "global_step": 375070, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1390628814697266, "global_step": 375071, "epoch": 736, "lr": 5e-05}
{"train_loss": 1.9981825351715088, "global_step": 375072, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1527724266052246, "global_step": 375073, "epoch": 736, "lr": 5e-05}
{"train_loss": 1.978345513343811, "global_step": 375074, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.075704574584961, "global_step": 375075, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0979349613189697, "global_step": 375076, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1406633853912354, "global_step": 375077, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1393141746520996, "global_step": 375078, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1359376907348633, "global_step": 375079, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1095333099365234, "global_step": 375080, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.089629650115967, "global_step": 375081, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1219687461853027, "global_step": 375082, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1104230880737305, "global_step": 375083, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0918188095092773, "global_step": 375084, "epoch": 736, "lr": 5e-05}
{"train_loss": 1.984628677368164, "global_step": 375085, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1374518871307373, "global_step": 375086, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1459739208221436, "global_step": 375087, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0940959453582764, "global_step": 375088, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0456724166870117, "global_step": 375089, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0386664867401123, "global_step": 375090, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.20017671585083, "global_step": 375091, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1378092765808105, "global_step": 375092, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.104962110519409, "global_step": 375093, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1763296127319336, "global_step": 375094, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.251742124557495, "global_step": 375095, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1073319911956787, "global_step": 375096, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1876392364501953, "global_step": 375097, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0478837490081787, "global_step": 375098, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0436220169067383, "global_step": 375099, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.184666872024536, "global_step": 375100, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.12827205657959, "global_step": 375101, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.097949743270874, "global_step": 375102, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0623555183410645, "global_step": 375103, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.010382890701294, "global_step": 375104, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.028827428817749, "global_step": 375105, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.06984806060791, "global_step": 375106, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1110000610351562, "global_step": 375107, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1080081462860107, "global_step": 375108, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1507744789123535, "global_step": 375109, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1308367252349854, "global_step": 375110, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.175354480743408, "global_step": 375111, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.11997652053833, "global_step": 375112, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.154665231704712, "global_step": 375113, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.124009132385254, "global_step": 375114, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1583337783813477, "global_step": 375115, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.072098970413208, "global_step": 375116, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0925676822662354, "global_step": 375117, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1265993118286133, "global_step": 375118, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0881035327911377, "global_step": 375119, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.137050151824951, "global_step": 375120, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0869693756103516, "global_step": 375121, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.129852056503296, "global_step": 375122, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1399052143096924, "global_step": 375123, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1484525203704834, "global_step": 375124, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.114654779434204, "global_step": 375125, "epoch": 736, "lr": 5e-05}
{"train_loss": 1.9878954887390137, "global_step": 375126, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1858205795288086, "global_step": 375127, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1193065643310547, "global_step": 375128, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.060565710067749, "global_step": 375129, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.0847420692443848, "global_step": 375130, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.138422727584839, "global_step": 375131, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1344432830810547, "global_step": 375132, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.064218044281006, "global_step": 375133, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1371936798095703, "global_step": 375134, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1065728664398193, "global_step": 375135, "epoch": 736, "lr": 5e-05}
{"train_loss": 2.1685688495635986, "global_step": 375136, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0835492610931396, "global_step": 375137, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.08327317237854, "global_step": 375138, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.175891160964966, "global_step": 375139, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1446404457092285, "global_step": 375140, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1400909423828125, "global_step": 375141, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1342110633850098, "global_step": 375142, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1810145378112793, "global_step": 375143, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1740546226501465, "global_step": 375144, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.136889696121216, "global_step": 375145, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.193774700164795, "global_step": 375146, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.2012455463409424, "global_step": 375147, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.132969856262207, "global_step": 375148, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.097241163253784, "global_step": 375149, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.087341785430908, "global_step": 375150, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.122615337371826, "global_step": 375151, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.192694664001465, "global_step": 375152, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.03940749168396, "global_step": 375153, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0083112716674805, "global_step": 375154, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1460351943969727, "global_step": 375155, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0873327255249023, "global_step": 375156, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1168437004089355, "global_step": 375157, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0320777893066406, "global_step": 375158, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.154482364654541, "global_step": 375159, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.082469940185547, "global_step": 375160, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.037139892578125, "global_step": 375161, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.080960273742676, "global_step": 375162, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1196811199188232, "global_step": 375163, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1446852684020996, "global_step": 375164, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0102481842041016, "global_step": 375165, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.004523754119873, "global_step": 375166, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0502469539642334, "global_step": 375167, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0531904697418213, "global_step": 375168, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0911734104156494, "global_step": 375169, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0852699279785156, "global_step": 375170, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1197943687438965, "global_step": 375171, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0462143421173096, "global_step": 375172, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0304172039031982, "global_step": 375173, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0994925498962402, "global_step": 375174, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1589162349700928, "global_step": 375175, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.068885087966919, "global_step": 375176, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.084080934524536, "global_step": 375177, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.097639322280884, "global_step": 375178, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.019083261489868, "global_step": 375179, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1520562171936035, "global_step": 375180, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1040022373199463, "global_step": 375181, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.135277509689331, "global_step": 375182, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.198333501815796, "global_step": 375183, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.154409646987915, "global_step": 375184, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0426106452941895, "global_step": 375185, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0053789615631104, "global_step": 375186, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.081749200820923, "global_step": 375187, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0662853717803955, "global_step": 375188, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1026885509490967, "global_step": 375189, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.190577983856201, "global_step": 375190, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.165407419204712, "global_step": 375191, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1386911869049072, "global_step": 375192, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1218769550323486, "global_step": 375193, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1066439151763916, "global_step": 375194, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.083796262741089, "global_step": 375195, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.181795597076416, "global_step": 375196, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.077024459838867, "global_step": 375197, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.090297222137451, "global_step": 375198, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.166079044342041, "global_step": 375199, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.116025686264038, "global_step": 375200, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1375091075897217, "global_step": 375201, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.061689615249634, "global_step": 375202, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1076457500457764, "global_step": 375203, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1487748622894287, "global_step": 375204, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0959150791168213, "global_step": 375205, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1801822185516357, "global_step": 375206, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.203141927719116, "global_step": 375207, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.07456111907959, "global_step": 375208, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0521252155303955, "global_step": 375209, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.095749855041504, "global_step": 375210, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.136744976043701, "global_step": 375211, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1253530979156494, "global_step": 375212, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1092634201049805, "global_step": 375213, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.134981632232666, "global_step": 375214, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.169348955154419, "global_step": 375215, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1007635593414307, "global_step": 375216, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0369675159454346, "global_step": 375217, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1410629749298096, "global_step": 375218, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.134817600250244, "global_step": 375219, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1828789710998535, "global_step": 375220, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.205444574356079, "global_step": 375221, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0342564582824707, "global_step": 375222, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1734442710876465, "global_step": 375223, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0712106227874756, "global_step": 375224, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0985357761383057, "global_step": 375225, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0254600048065186, "global_step": 375226, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0627245903015137, "global_step": 375227, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0736231803894043, "global_step": 375228, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.137890577316284, "global_step": 375229, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.07327938079834, "global_step": 375230, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.077190399169922, "global_step": 375231, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0983734130859375, "global_step": 375232, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.039825677871704, "global_step": 375233, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.9658809900283813, "global_step": 375234, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1260147094726562, "global_step": 375235, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.063734292984009, "global_step": 375236, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.107963800430298, "global_step": 375237, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.093597650527954, "global_step": 375238, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0882105827331543, "global_step": 375239, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.115264892578125, "global_step": 375240, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1548526287078857, "global_step": 375241, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.9665131568908691, "global_step": 375242, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1537551879882812, "global_step": 375243, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0632331371307373, "global_step": 375244, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0589449405670166, "global_step": 375245, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.070671558380127, "global_step": 375246, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1345221996307373, "global_step": 375247, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.110531806945801, "global_step": 375248, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.032938241958618, "global_step": 375249, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0645182132720947, "global_step": 375250, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0903239250183105, "global_step": 375251, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1955084800720215, "global_step": 375252, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1444883346557617, "global_step": 375253, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.056854724884033, "global_step": 375254, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.133664608001709, "global_step": 375255, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.02673077583313, "global_step": 375256, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0034990310668945, "global_step": 375257, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0906729698181152, "global_step": 375258, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.119074821472168, "global_step": 375259, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.055309772491455, "global_step": 375260, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.023171901702881, "global_step": 375261, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.2011477947235107, "global_step": 375262, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.038156509399414, "global_step": 375263, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1180880069732666, "global_step": 375264, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.061805248260498, "global_step": 375265, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.088207960128784, "global_step": 375266, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1384122371673584, "global_step": 375267, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.169954776763916, "global_step": 375268, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.093775749206543, "global_step": 375269, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.143782138824463, "global_step": 375270, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1208906173706055, "global_step": 375271, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.040022373199463, "global_step": 375272, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1376609802246094, "global_step": 375273, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0285353660583496, "global_step": 375274, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.007727861404419, "global_step": 375275, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.116459608078003, "global_step": 375276, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1424670219421387, "global_step": 375277, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.147029161453247, "global_step": 375278, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0934882164001465, "global_step": 375279, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0879056453704834, "global_step": 375280, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.095308303833008, "global_step": 375281, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0846216678619385, "global_step": 375282, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.079925060272217, "global_step": 375283, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.173820734024048, "global_step": 375284, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0770082473754883, "global_step": 375285, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1091349124908447, "global_step": 375286, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.081425428390503, "global_step": 375287, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1247572898864746, "global_step": 375288, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1033644676208496, "global_step": 375289, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1360585689544678, "global_step": 375290, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.118253231048584, "global_step": 375291, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0983991622924805, "global_step": 375292, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.148005962371826, "global_step": 375293, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1238620281219482, "global_step": 375294, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1022679805755615, "global_step": 375295, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0192503929138184, "global_step": 375296, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.028172492980957, "global_step": 375297, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1491429805755615, "global_step": 375298, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.2523794174194336, "global_step": 375299, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.057307720184326, "global_step": 375300, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0679168701171875, "global_step": 375301, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0993824005126953, "global_step": 375302, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0422444343566895, "global_step": 375303, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0370333194732666, "global_step": 375304, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.174617052078247, "global_step": 375305, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.094597816467285, "global_step": 375306, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1729798316955566, "global_step": 375307, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1227834224700928, "global_step": 375308, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0649166107177734, "global_step": 375309, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1213481426239014, "global_step": 375310, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.047457456588745, "global_step": 375311, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.139606475830078, "global_step": 375312, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.126950740814209, "global_step": 375313, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0317487716674805, "global_step": 375314, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1738038063049316, "global_step": 375315, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1139402389526367, "global_step": 375316, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0521137714385986, "global_step": 375317, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.135066032409668, "global_step": 375318, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.06730318069458, "global_step": 375319, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0611703395843506, "global_step": 375320, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0436899662017822, "global_step": 375321, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1027793884277344, "global_step": 375322, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.219675064086914, "global_step": 375323, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1205756664276123, "global_step": 375324, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1348156929016113, "global_step": 375325, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1117663383483887, "global_step": 375326, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.148803234100342, "global_step": 375327, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1622843742370605, "global_step": 375328, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.099910020828247, "global_step": 375329, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1286356449127197, "global_step": 375330, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1453816890716553, "global_step": 375331, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.041569232940674, "global_step": 375332, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0520753860473633, "global_step": 375333, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.229872941970825, "global_step": 375334, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0689101219177246, "global_step": 375335, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.139888048171997, "global_step": 375336, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.014744997024536, "global_step": 375337, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1362404823303223, "global_step": 375338, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.075373649597168, "global_step": 375339, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.102390766143799, "global_step": 375340, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0766985416412354, "global_step": 375341, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0599398612976074, "global_step": 375342, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1319050788879395, "global_step": 375343, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1134209632873535, "global_step": 375344, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0917441844940186, "global_step": 375345, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.088456869125366, "global_step": 375346, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0599496364593506, "global_step": 375347, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0835983753204346, "global_step": 375348, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0889029502868652, "global_step": 375349, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.159308433532715, "global_step": 375350, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1316843032836914, "global_step": 375351, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0688235759735107, "global_step": 375352, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0835556983947754, "global_step": 375353, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.127188205718994, "global_step": 375354, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.211899757385254, "global_step": 375355, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1351125240325928, "global_step": 375356, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.117182493209839, "global_step": 375357, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.083552360534668, "global_step": 375358, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.064178466796875, "global_step": 375359, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.057340621948242, "global_step": 375360, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.091602087020874, "global_step": 375361, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0949623584747314, "global_step": 375362, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.113543748855591, "global_step": 375363, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.103537082672119, "global_step": 375364, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.123300790786743, "global_step": 375365, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.156736373901367, "global_step": 375366, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.048896551132202, "global_step": 375367, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0882227420806885, "global_step": 375368, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0213875770568848, "global_step": 375369, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1911792755126953, "global_step": 375370, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1202471256256104, "global_step": 375371, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1754791736602783, "global_step": 375372, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.9801870584487915, "global_step": 375373, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1101222038269043, "global_step": 375374, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0679755210876465, "global_step": 375375, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0590264797210693, "global_step": 375376, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.068840742111206, "global_step": 375377, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.122546911239624, "global_step": 375378, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.123887062072754, "global_step": 375379, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1760716438293457, "global_step": 375380, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1646728515625, "global_step": 375381, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0998411178588867, "global_step": 375382, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1495542526245117, "global_step": 375383, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0763185024261475, "global_step": 375384, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.9934196472167969, "global_step": 375385, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.084606885910034, "global_step": 375386, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.062110424041748, "global_step": 375387, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.025336980819702, "global_step": 375388, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.064290761947632, "global_step": 375389, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.082195997238159, "global_step": 375390, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1220791339874268, "global_step": 375391, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1375303268432617, "global_step": 375392, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.133059501647949, "global_step": 375393, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.202609062194824, "global_step": 375394, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.041285514831543, "global_step": 375395, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.980652928352356, "global_step": 375396, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0436453819274902, "global_step": 375397, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1820828914642334, "global_step": 375398, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.099046468734741, "global_step": 375399, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.126429319381714, "global_step": 375400, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.151928663253784, "global_step": 375401, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.2532196044921875, "global_step": 375402, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.168255567550659, "global_step": 375403, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0670058727264404, "global_step": 375404, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.065186023712158, "global_step": 375405, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.161656379699707, "global_step": 375406, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.9542090892791748, "global_step": 375407, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0848655700683594, "global_step": 375408, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0973541736602783, "global_step": 375409, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0943055152893066, "global_step": 375410, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0221924781799316, "global_step": 375411, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1408612728118896, "global_step": 375412, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.120687961578369, "global_step": 375413, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.11240553855896, "global_step": 375414, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.097822666168213, "global_step": 375415, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.058138370513916, "global_step": 375416, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.057469606399536, "global_step": 375417, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.001250743865967, "global_step": 375418, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0869383811950684, "global_step": 375419, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1879518032073975, "global_step": 375420, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1133739948272705, "global_step": 375421, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.165095567703247, "global_step": 375422, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1054158210754395, "global_step": 375423, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0817291736602783, "global_step": 375424, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1674859523773193, "global_step": 375425, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.098085403442383, "global_step": 375426, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.07673978805542, "global_step": 375427, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.047633647918701, "global_step": 375428, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.051295518875122, "global_step": 375429, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0378787517547607, "global_step": 375430, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.042280912399292, "global_step": 375431, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.06278920173645, "global_step": 375432, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1012794971466064, "global_step": 375433, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.2039859294891357, "global_step": 375434, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.076108932495117, "global_step": 375435, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.157986640930176, "global_step": 375436, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.106069326400757, "global_step": 375437, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1632187366485596, "global_step": 375438, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1075565814971924, "global_step": 375439, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.131701707839966, "global_step": 375440, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.2039976119995117, "global_step": 375441, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.135868787765503, "global_step": 375442, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.048398733139038, "global_step": 375443, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.087263584136963, "global_step": 375444, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0591213703155518, "global_step": 375445, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.08500599861145, "global_step": 375446, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0896008014678955, "global_step": 375447, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.172049045562744, "global_step": 375448, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0570175647735596, "global_step": 375449, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.117271900177002, "global_step": 375450, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.133248805999756, "global_step": 375451, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.023221969604492, "global_step": 375452, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.003988265991211, "global_step": 375453, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.090547800064087, "global_step": 375454, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0824060440063477, "global_step": 375455, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1639177799224854, "global_step": 375456, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.153010845184326, "global_step": 375457, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.099381685256958, "global_step": 375458, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.163158416748047, "global_step": 375459, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1035406589508057, "global_step": 375460, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1190428733825684, "global_step": 375461, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0031373500823975, "global_step": 375462, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1141653060913086, "global_step": 375463, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.05964994430542, "global_step": 375464, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1321494579315186, "global_step": 375465, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1544430255889893, "global_step": 375466, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0571043491363525, "global_step": 375467, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.136282205581665, "global_step": 375468, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0201940536499023, "global_step": 375469, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.121481418609619, "global_step": 375470, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0413589477539062, "global_step": 375471, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1167705059051514, "global_step": 375472, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1796042919158936, "global_step": 375473, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1221752166748047, "global_step": 375474, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.065249443054199, "global_step": 375475, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0850677490234375, "global_step": 375476, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1452796459198, "global_step": 375477, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1120073795318604, "global_step": 375478, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.019298553466797, "global_step": 375479, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1120822429656982, "global_step": 375480, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.047250986099243, "global_step": 375481, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0929346084594727, "global_step": 375482, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1517951488494873, "global_step": 375483, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0619559288024902, "global_step": 375484, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1203558444976807, "global_step": 375485, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0780272483825684, "global_step": 375486, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.078010320663452, "global_step": 375487, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1738691329956055, "global_step": 375488, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0791831016540527, "global_step": 375489, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.9901673793792725, "global_step": 375490, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0875511169433594, "global_step": 375491, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.100846529006958, "global_step": 375492, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0084049701690674, "global_step": 375493, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1634151935577393, "global_step": 375494, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.097383737564087, "global_step": 375495, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1170544624328613, "global_step": 375496, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.178760528564453, "global_step": 375497, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.047882556915283, "global_step": 375498, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1312689781188965, "global_step": 375499, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0329947471618652, "global_step": 375500, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0868825912475586, "global_step": 375501, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1322031021118164, "global_step": 375502, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0853636264801025, "global_step": 375503, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.157719850540161, "global_step": 375504, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0707929134368896, "global_step": 375505, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0467708110809326, "global_step": 375506, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.099759817123413, "global_step": 375507, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0925135612487793, "global_step": 375508, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0775251388549805, "global_step": 375509, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.09330677986145, "global_step": 375510, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.091505765914917, "global_step": 375511, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1162850856781006, "global_step": 375512, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0849812030792236, "global_step": 375513, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.151015043258667, "global_step": 375514, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1063828468322754, "global_step": 375515, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.053795099258423, "global_step": 375516, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.15590500831604, "global_step": 375517, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0138819217681885, "global_step": 375518, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1252689361572266, "global_step": 375519, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0963618755340576, "global_step": 375520, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0864877700805664, "global_step": 375521, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.109706163406372, "global_step": 375522, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0380098819732666, "global_step": 375523, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.177311897277832, "global_step": 375524, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1054210662841797, "global_step": 375525, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.094562292098999, "global_step": 375526, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0576987266540527, "global_step": 375527, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0271496772766113, "global_step": 375528, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1404869556427, "global_step": 375529, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.152310609817505, "global_step": 375530, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.134720802307129, "global_step": 375531, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.2132794857025146, "global_step": 375532, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.030207633972168, "global_step": 375533, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.227864980697632, "global_step": 375534, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.099320650100708, "global_step": 375535, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1882681846618652, "global_step": 375536, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0254006385803223, "global_step": 375537, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.093982696533203, "global_step": 375538, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0532307624816895, "global_step": 375539, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0673868656158447, "global_step": 375540, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1116597652435303, "global_step": 375541, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0989840030670166, "global_step": 375542, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0583314895629883, "global_step": 375543, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0651490688323975, "global_step": 375544, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1178481578826904, "global_step": 375545, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.114000082015991, "global_step": 375546, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1159355640411377, "global_step": 375547, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.143475294113159, "global_step": 375548, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.157604217529297, "global_step": 375549, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.091596841812134, "global_step": 375550, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.003086566925049, "global_step": 375551, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1491951942443848, "global_step": 375552, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0903496742248535, "global_step": 375553, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1057136058807373, "global_step": 375554, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.114947557449341, "global_step": 375555, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1374363899230957, "global_step": 375556, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1858952045440674, "global_step": 375557, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.150376796722412, "global_step": 375558, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0520479679107666, "global_step": 375559, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.143200635910034, "global_step": 375560, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.134058713912964, "global_step": 375561, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.220841646194458, "global_step": 375562, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.098984956741333, "global_step": 375563, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.183311700820923, "global_step": 375564, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1165127754211426, "global_step": 375565, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1834146976470947, "global_step": 375566, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1598832607269287, "global_step": 375567, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.059312582015991, "global_step": 375568, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1644811630249023, "global_step": 375569, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1023499965667725, "global_step": 375570, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.9632985591888428, "global_step": 375571, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0852701663970947, "global_step": 375572, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.14414644241333, "global_step": 375573, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.00547194480896, "global_step": 375574, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.067368745803833, "global_step": 375575, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1467270851135254, "global_step": 375576, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.077068328857422, "global_step": 375577, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.025369644165039, "global_step": 375578, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.160423755645752, "global_step": 375579, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.105966806411743, "global_step": 375580, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.028653621673584, "global_step": 375581, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1156601905822754, "global_step": 375582, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0577287673950195, "global_step": 375583, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.2091002464294434, "global_step": 375584, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1203079223632812, "global_step": 375585, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0850179195404053, "global_step": 375586, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0981392860412598, "global_step": 375587, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.137467384338379, "global_step": 375588, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.12670636177063, "global_step": 375589, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.107222557067871, "global_step": 375590, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0805861949920654, "global_step": 375591, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1628570556640625, "global_step": 375592, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1341450214385986, "global_step": 375593, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0570549964904785, "global_step": 375594, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1070351600646973, "global_step": 375595, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.9815164804458618, "global_step": 375596, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0436196327209473, "global_step": 375597, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.095871686935425, "global_step": 375598, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.105565309524536, "global_step": 375599, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0918073654174805, "global_step": 375600, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1298813819885254, "global_step": 375601, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1623592376708984, "global_step": 375602, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.141003370285034, "global_step": 375603, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.161555290222168, "global_step": 375604, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1549489498138428, "global_step": 375605, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0073165893554688, "global_step": 375606, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1918601989746094, "global_step": 375607, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1171061992645264, "global_step": 375608, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1686463356018066, "global_step": 375609, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1167941093444824, "global_step": 375610, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0506296157836914, "global_step": 375611, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.061814546585083, "global_step": 375612, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.049513101577759, "global_step": 375613, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.134319305419922, "global_step": 375614, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0252022743225098, "global_step": 375615, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.117370843887329, "global_step": 375616, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0253777503967285, "global_step": 375617, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1229588985443115, "global_step": 375618, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.046555995941162, "global_step": 375619, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.955026388168335, "global_step": 375620, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1325018405914307, "global_step": 375621, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.026822328567505, "global_step": 375622, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.125783681869507, "global_step": 375623, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.068939208984375, "global_step": 375624, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.101426362991333, "global_step": 375625, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1332945823669434, "global_step": 375626, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0394203662872314, "global_step": 375627, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0474042892456055, "global_step": 375628, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1490519046783447, "global_step": 375629, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1340343952178955, "global_step": 375630, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.133296012878418, "global_step": 375631, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1504018306732178, "global_step": 375632, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1035351753234863, "global_step": 375633, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.070833444595337, "global_step": 375634, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0695853233337402, "global_step": 375635, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.081956148147583, "global_step": 375636, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.083042621612549, "global_step": 375637, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.084066152572632, "global_step": 375638, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0997836589813232, "global_step": 375639, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0360822677612305, "global_step": 375640, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0855796337127686, "global_step": 375641, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1339187622070312, "global_step": 375642, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.131641387939453, "global_step": 375643, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.10396671295166, "global_step": 375644, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.071641683578491, "global_step": 375645, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.123551607131958, "global_step": 375646, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.9868139028549194, "global_step": 375647, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.15621018409729, "global_step": 375648, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.075173854827881, "global_step": 375649, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.050605297088623, "global_step": 375650, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.133676767349243, "global_step": 375651, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0851492881774902, "global_step": 375652, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.082778215408325, "global_step": 375653, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.116835832595825, "global_step": 375654, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.038079023361206, "global_step": 375655, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.2298929691314697, "global_step": 375656, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0332653522491455, "global_step": 375657, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0244758129119873, "global_step": 375658, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1160876750946045, "global_step": 375659, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.134010076522827, "global_step": 375660, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1331558227539062, "global_step": 375661, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1670730113983154, "global_step": 375662, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.2193517684936523, "global_step": 375663, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0963220596313477, "global_step": 375664, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.171375036239624, "global_step": 375665, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.115020751953125, "global_step": 375666, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.9637575149536133, "global_step": 375667, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.065488815307617, "global_step": 375668, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1469175815582275, "global_step": 375669, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.159727096557617, "global_step": 375670, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1976563930511475, "global_step": 375671, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.082512140274048, "global_step": 375672, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0322329998016357, "global_step": 375673, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.059401750564575, "global_step": 375674, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1905856132507324, "global_step": 375675, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0528311729431152, "global_step": 375676, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0959064960479736, "global_step": 375677, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0641419887542725, "global_step": 375678, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.2186479568481445, "global_step": 375679, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.125974655151367, "global_step": 375680, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.121997594833374, "global_step": 375681, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1598010063171387, "global_step": 375682, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0866286754608154, "global_step": 375683, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1553995609283447, "global_step": 375684, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.096266746520996, "global_step": 375685, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.11069917678833, "global_step": 375686, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.052736520767212, "global_step": 375687, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1608264446258545, "global_step": 375688, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0974819660186768, "global_step": 375689, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0641465187072754, "global_step": 375690, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1320834159851074, "global_step": 375691, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.9727121591567993, "global_step": 375692, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0904128551483154, "global_step": 375693, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0483310222625732, "global_step": 375694, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0993549823760986, "global_step": 375695, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1713109016418457, "global_step": 375696, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0457611083984375, "global_step": 375697, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.088376760482788, "global_step": 375698, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.126380443572998, "global_step": 375699, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1777913570404053, "global_step": 375700, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0498294830322266, "global_step": 375701, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.9916317462921143, "global_step": 375702, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1768388748168945, "global_step": 375703, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.100454807281494, "global_step": 375704, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.090895891189575, "global_step": 375705, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1460635662078857, "global_step": 375706, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0599653720855713, "global_step": 375707, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.034583806991577, "global_step": 375708, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0993635654449463, "global_step": 375709, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1622977256774902, "global_step": 375710, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.129946231842041, "global_step": 375711, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.137669801712036, "global_step": 375712, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.156972885131836, "global_step": 375713, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.15623140335083, "global_step": 375714, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0731709003448486, "global_step": 375715, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1260056495666504, "global_step": 375716, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0996429920196533, "global_step": 375717, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0337722301483154, "global_step": 375718, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1877593994140625, "global_step": 375719, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0791752338409424, "global_step": 375720, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1212408542633057, "global_step": 375721, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.2378389835357666, "global_step": 375722, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.039332628250122, "global_step": 375723, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1292245388031006, "global_step": 375724, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.199389934539795, "global_step": 375725, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1571731567382812, "global_step": 375726, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.061476945877075, "global_step": 375727, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1053218841552734, "global_step": 375728, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.169222116470337, "global_step": 375729, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1438910961151123, "global_step": 375730, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.143986463546753, "global_step": 375731, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.161878824234009, "global_step": 375732, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.082679271697998, "global_step": 375733, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1361429691314697, "global_step": 375734, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.08485746383667, "global_step": 375735, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.099607229232788, "global_step": 375736, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.095008611679077, "global_step": 375737, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1151387691497803, "global_step": 375738, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1477766036987305, "global_step": 375739, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1484293937683105, "global_step": 375740, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0931153297424316, "global_step": 375741, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0922060012817383, "global_step": 375742, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.199127674102783, "global_step": 375743, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1976983547210693, "global_step": 375744, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.139822483062744, "global_step": 375745, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.061927080154419, "global_step": 375746, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1630427837371826, "global_step": 375747, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0611279010772705, "global_step": 375748, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1690988540649414, "global_step": 375749, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0895283222198486, "global_step": 375750, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1276674270629883, "global_step": 375751, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.068049430847168, "global_step": 375752, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1058123111724854, "global_step": 375753, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.9803087711334229, "global_step": 375754, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.151291847229004, "global_step": 375755, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.159623622894287, "global_step": 375756, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.146411418914795, "global_step": 375757, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.110257387161255, "global_step": 375758, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0684001445770264, "global_step": 375759, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.101841449737549, "global_step": 375760, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0618460178375244, "global_step": 375761, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.215217351913452, "global_step": 375762, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1178486347198486, "global_step": 375763, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1302337646484375, "global_step": 375764, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1279664039611816, "global_step": 375765, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0588862895965576, "global_step": 375766, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.070594310760498, "global_step": 375767, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.9783707857131958, "global_step": 375768, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0775375366210938, "global_step": 375769, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.030313730239868, "global_step": 375770, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.117086410522461, "global_step": 375771, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0989670753479004, "global_step": 375772, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1402761936187744, "global_step": 375773, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.100177049636841, "global_step": 375774, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.983233094215393, "global_step": 375775, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0423240661621094, "global_step": 375776, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.17305326461792, "global_step": 375777, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.141481637954712, "global_step": 375778, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1250228881835938, "global_step": 375779, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1406967639923096, "global_step": 375780, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1808927059173584, "global_step": 375781, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.098999261856079, "global_step": 375782, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.080730438232422, "global_step": 375783, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1203062534332275, "global_step": 375784, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0591344833374023, "global_step": 375785, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.150676727294922, "global_step": 375786, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.073411703109741, "global_step": 375787, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1065833568573, "global_step": 375788, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1178512573242188, "global_step": 375789, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1033716201782227, "global_step": 375790, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1176555156707764, "global_step": 375791, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1070404052734375, "global_step": 375792, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1510848999023438, "global_step": 375793, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.083542585372925, "global_step": 375794, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.083948850631714, "global_step": 375795, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0949156284332275, "global_step": 375796, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1409199237823486, "global_step": 375797, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.103213310241699, "global_step": 375798, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.032369375228882, "global_step": 375799, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.009212017059326, "global_step": 375800, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0552499294281006, "global_step": 375801, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1603686809539795, "global_step": 375802, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.088594436645508, "global_step": 375803, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0316100120544434, "global_step": 375804, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.155984878540039, "global_step": 375805, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.159437656402588, "global_step": 375806, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.075593948364258, "global_step": 375807, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1232118606567383, "global_step": 375808, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0565009117126465, "global_step": 375809, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.166067123413086, "global_step": 375810, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.098919630050659, "global_step": 375811, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0828301906585693, "global_step": 375812, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1207332611083984, "global_step": 375813, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.084996223449707, "global_step": 375814, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.121523857116699, "global_step": 375815, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.140146255493164, "global_step": 375816, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.050208568572998, "global_step": 375817, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1210625171661377, "global_step": 375818, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1582844257354736, "global_step": 375819, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.074070930480957, "global_step": 375820, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.141139268875122, "global_step": 375821, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.143202781677246, "global_step": 375822, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1182281970977783, "global_step": 375823, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.069284200668335, "global_step": 375824, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.131819486618042, "global_step": 375825, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0776333808898926, "global_step": 375826, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.015155792236328, "global_step": 375827, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.04172420501709, "global_step": 375828, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.9788228273391724, "global_step": 375829, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.2379863262176514, "global_step": 375830, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0850014686584473, "global_step": 375831, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1055591106414795, "global_step": 375832, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1145458221435547, "global_step": 375833, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.191094160079956, "global_step": 375834, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.128282308578491, "global_step": 375835, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.049863815307617, "global_step": 375836, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.063361883163452, "global_step": 375837, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.098996162414551, "global_step": 375838, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.156860828399658, "global_step": 375839, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.018184185028076, "global_step": 375840, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1098196506500244, "global_step": 375841, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.102297306060791, "global_step": 375842, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1992900371551514, "global_step": 375843, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.202423095703125, "global_step": 375844, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.201277494430542, "global_step": 375845, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0676729679107666, "global_step": 375846, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.138756036758423, "global_step": 375847, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1892170906066895, "global_step": 375848, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0831243991851807, "global_step": 375849, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.145399332046509, "global_step": 375850, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.090902090072632, "global_step": 375851, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.105555772781372, "global_step": 375852, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1136820316314697, "global_step": 375853, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.058415651321411, "global_step": 375854, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1291112899780273, "global_step": 375855, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1910834312438965, "global_step": 375856, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1044981479644775, "global_step": 375857, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1147444248199463, "global_step": 375858, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.126305103302002, "global_step": 375859, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1186962127685547, "global_step": 375860, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.132671356201172, "global_step": 375861, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1586050987243652, "global_step": 375862, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.107152223587036, "global_step": 375863, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.211167335510254, "global_step": 375864, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0933847427368164, "global_step": 375865, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.172699451446533, "global_step": 375866, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.136323928833008, "global_step": 375867, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1612110137939453, "global_step": 375868, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.024949789047241, "global_step": 375869, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1276419162750244, "global_step": 375870, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.03928542137146, "global_step": 375871, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.122776985168457, "global_step": 375872, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.077416181564331, "global_step": 375873, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.061845541000366, "global_step": 375874, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.162825584411621, "global_step": 375875, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1587250232696533, "global_step": 375876, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.08119797706604, "global_step": 375877, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.050954818725586, "global_step": 375878, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0887866020202637, "global_step": 375879, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0758161544799805, "global_step": 375880, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1314165592193604, "global_step": 375881, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.114743947982788, "global_step": 375882, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.097916841506958, "global_step": 375883, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0722405910491943, "global_step": 375884, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0308358669281006, "global_step": 375885, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.082334518432617, "global_step": 375886, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.2188615798950195, "global_step": 375887, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1193747520446777, "global_step": 375888, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1332359313964844, "global_step": 375889, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.095869302749634, "global_step": 375890, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.178813934326172, "global_step": 375891, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0418810844421387, "global_step": 375892, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1238350868225098, "global_step": 375893, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.049423933029175, "global_step": 375894, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.132024049758911, "global_step": 375895, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0914711952209473, "global_step": 375896, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1567273139953613, "global_step": 375897, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1586270332336426, "global_step": 375898, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.2016544342041016, "global_step": 375899, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.180314302444458, "global_step": 375900, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1422812938690186, "global_step": 375901, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.200822114944458, "global_step": 375902, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1145331859588623, "global_step": 375903, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.125662326812744, "global_step": 375904, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.082840919494629, "global_step": 375905, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1808040142059326, "global_step": 375906, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.136754035949707, "global_step": 375907, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0685949325561523, "global_step": 375908, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.092711925506592, "global_step": 375909, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.2142493724823, "global_step": 375910, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.161637306213379, "global_step": 375911, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1585440635681152, "global_step": 375912, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.086627721786499, "global_step": 375913, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.075014114379883, "global_step": 375914, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.111341953277588, "global_step": 375915, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0344715118408203, "global_step": 375916, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.108246326446533, "global_step": 375917, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0907130241394043, "global_step": 375918, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0939781665802, "global_step": 375919, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0325100421905518, "global_step": 375920, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.105010986328125, "global_step": 375921, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.166111469268799, "global_step": 375922, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1428332328796387, "global_step": 375923, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.007131338119507, "global_step": 375924, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.057117462158203, "global_step": 375925, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.118986129760742, "global_step": 375926, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1587576866149902, "global_step": 375927, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0787038803100586, "global_step": 375928, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1284799575805664, "global_step": 375929, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.132908582687378, "global_step": 375930, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1327807903289795, "global_step": 375931, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.061420202255249, "global_step": 375932, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1488616466522217, "global_step": 375933, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.060232162475586, "global_step": 375934, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.127901554107666, "global_step": 375935, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.17708420753479, "global_step": 375936, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.073366641998291, "global_step": 375937, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.124903917312622, "global_step": 375938, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.082180976867676, "global_step": 375939, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1303696632385254, "global_step": 375940, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.153850793838501, "global_step": 375941, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.090616226196289, "global_step": 375942, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1178104877471924, "global_step": 375943, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0689117908477783, "global_step": 375944, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1461234092712402, "global_step": 375945, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.06996488571167, "global_step": 375946, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1525325775146484, "global_step": 375947, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.129032611846924, "global_step": 375948, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.041177988052368, "global_step": 375949, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0865018367767334, "global_step": 375950, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0646860599517822, "global_step": 375951, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.045957326889038, "global_step": 375952, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.2210898399353027, "global_step": 375953, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.167863607406616, "global_step": 375954, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.206726551055908, "global_step": 375955, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.139646291732788, "global_step": 375956, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0633962154388428, "global_step": 375957, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.117295026779175, "global_step": 375958, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1202359199523926, "global_step": 375959, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.08292293548584, "global_step": 375960, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.097623109817505, "global_step": 375961, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1692726612091064, "global_step": 375962, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1246726512908936, "global_step": 375963, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1426336765289307, "global_step": 375964, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.9998977184295654, "global_step": 375965, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.154508113861084, "global_step": 375966, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0953519344329834, "global_step": 375967, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.098606586456299, "global_step": 375968, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1163339614868164, "global_step": 375969, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1205251216888428, "global_step": 375970, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.108201265335083, "global_step": 375971, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.108680248260498, "global_step": 375972, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.102046012878418, "global_step": 375973, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0371530055999756, "global_step": 375974, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1035256385803223, "global_step": 375975, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1898746490478516, "global_step": 375976, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.083745241165161, "global_step": 375977, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1025187969207764, "global_step": 375978, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.090068817138672, "global_step": 375979, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.9969367980957031, "global_step": 375980, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0947811603546143, "global_step": 375981, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1379387378692627, "global_step": 375982, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0862045288085938, "global_step": 375983, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.141050100326538, "global_step": 375984, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0734493732452393, "global_step": 375985, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1077053546905518, "global_step": 375986, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0554308891296387, "global_step": 375987, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1077306270599365, "global_step": 375988, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.104895830154419, "global_step": 375989, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0948915481567383, "global_step": 375990, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1824538707733154, "global_step": 375991, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0553553104400635, "global_step": 375992, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.129244089126587, "global_step": 375993, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0778584480285645, "global_step": 375994, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.076493978500366, "global_step": 375995, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.213531017303467, "global_step": 375996, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.120620012283325, "global_step": 375997, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1051530838012695, "global_step": 375998, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.057863712310791, "global_step": 375999, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1671605110168457, "global_step": 376000, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.02036452293396, "global_step": 376001, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1069984436035156, "global_step": 376002, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0961556434631348, "global_step": 376003, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1451923847198486, "global_step": 376004, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1228554248809814, "global_step": 376005, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1521518230438232, "global_step": 376006, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0357308387756348, "global_step": 376007, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1202690601348877, "global_step": 376008, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0847208499908447, "global_step": 376009, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.107815742492676, "global_step": 376010, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.119279146194458, "global_step": 376011, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.146789073944092, "global_step": 376012, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.142749547958374, "global_step": 376013, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1229755878448486, "global_step": 376014, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.153963804244995, "global_step": 376015, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.061898946762085, "global_step": 376016, "epoch": 737, "lr": 5e-05}
{"train_loss": 1.997449278831482, "global_step": 376017, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1104729175567627, "global_step": 376018, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.070772171020508, "global_step": 376019, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1600377559661865, "global_step": 376020, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.18684458732605, "global_step": 376021, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0454213619232178, "global_step": 376022, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0751290321350098, "global_step": 376023, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.164644479751587, "global_step": 376024, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.146580219268799, "global_step": 376025, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.115556478500366, "global_step": 376026, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0956809520721436, "global_step": 376027, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0900986194610596, "global_step": 376028, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.12996244430542, "global_step": 376029, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.112297773361206, "global_step": 376030, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.055603504180908, "global_step": 376031, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.112794876098633, "global_step": 376032, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.05104923248291, "global_step": 376033, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.099635601043701, "global_step": 376034, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0917282104492188, "global_step": 376035, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1175222396850586, "global_step": 376036, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0548501014709473, "global_step": 376037, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0549325942993164, "global_step": 376038, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1828866004943848, "global_step": 376039, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1718411445617676, "global_step": 376040, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.093799114227295, "global_step": 376041, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1286537647247314, "global_step": 376042, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.140726327896118, "global_step": 376043, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1240768432617188, "global_step": 376044, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.006113052368164, "global_step": 376045, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.07452654838562, "global_step": 376046, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.091024875640869, "global_step": 376047, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.121750593185425, "global_step": 376048, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1360042095184326, "global_step": 376049, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1279964447021484, "global_step": 376050, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0938191413879395, "global_step": 376051, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1333365440368652, "global_step": 376052, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.143303632736206, "global_step": 376053, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0240116119384766, "global_step": 376054, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.18961763381958, "global_step": 376055, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0266101360321045, "global_step": 376056, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.161592483520508, "global_step": 376057, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.151954412460327, "global_step": 376058, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.084994077682495, "global_step": 376059, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1409356594085693, "global_step": 376060, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0259859561920166, "global_step": 376061, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.202253580093384, "global_step": 376062, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1728932857513428, "global_step": 376063, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1650331020355225, "global_step": 376064, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.117438554763794, "global_step": 376065, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0534536838531494, "global_step": 376066, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1790215969085693, "global_step": 376067, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1688928604125977, "global_step": 376068, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.118964672088623, "global_step": 376069, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.117293119430542, "global_step": 376070, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.058218240737915, "global_step": 376071, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.107602119445801, "global_step": 376072, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1706366539001465, "global_step": 376073, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1272804737091064, "global_step": 376074, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1711509227752686, "global_step": 376075, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0598771572113037, "global_step": 376076, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0179519653320312, "global_step": 376077, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1511054039001465, "global_step": 376078, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.128505229949951, "global_step": 376079, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.135746717453003, "global_step": 376080, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0698342323303223, "global_step": 376081, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1473581790924072, "global_step": 376082, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1529788970947266, "global_step": 376083, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.18698787689209, "global_step": 376084, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0248351097106934, "global_step": 376085, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.095482110977173, "global_step": 376086, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1083486080169678, "global_step": 376087, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0369579792022705, "global_step": 376088, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.081794261932373, "global_step": 376089, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.170405864715576, "global_step": 376090, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.067014217376709, "global_step": 376091, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.2089526653289795, "global_step": 376092, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.131314277648926, "global_step": 376093, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.13486909866333, "global_step": 376094, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1516740322113037, "global_step": 376095, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1663200855255127, "global_step": 376096, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1550545692443848, "global_step": 376097, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.085108757019043, "global_step": 376098, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1296164989471436, "global_step": 376099, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0844550132751465, "global_step": 376100, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.058248519897461, "global_step": 376101, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.102419137954712, "global_step": 376102, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.1043753623962402, "global_step": 376103, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.105980157852173, "global_step": 376104, "epoch": 737, "lr": 5e-05}
{"train_loss": 2.0265684127807617, "global_step": 376105, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1635382175445557, "global_step": 376106, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0505051612854004, "global_step": 376107, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0486936569213867, "global_step": 376108, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0961008071899414, "global_step": 376109, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0628974437713623, "global_step": 376110, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0613741874694824, "global_step": 376111, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0620431900024414, "global_step": 376112, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0861406326293945, "global_step": 376113, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1445581912994385, "global_step": 376114, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1156561374664307, "global_step": 376115, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1970934867858887, "global_step": 376116, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1546308994293213, "global_step": 376117, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.162769317626953, "global_step": 376118, "epoch": 738, "lr": 5e-05}
{"train_loss": 1.950618863105774, "global_step": 376119, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.088989019393921, "global_step": 376120, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0859975814819336, "global_step": 376121, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1803746223449707, "global_step": 376122, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0269124507904053, "global_step": 376123, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1904709339141846, "global_step": 376124, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0685040950775146, "global_step": 376125, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1808083057403564, "global_step": 376126, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0925803184509277, "global_step": 376127, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.107740879058838, "global_step": 376128, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1473641395568848, "global_step": 376129, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.022688388824463, "global_step": 376130, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1607439517974854, "global_step": 376131, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1220862865448, "global_step": 376132, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.015463352203369, "global_step": 376133, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.138367176055908, "global_step": 376134, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.019800901412964, "global_step": 376135, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0790741443634033, "global_step": 376136, "epoch": 738, "lr": 5e-05}
{"train_loss": 1.9930814504623413, "global_step": 376137, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.083251476287842, "global_step": 376138, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.078747034072876, "global_step": 376139, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1251649856567383, "global_step": 376140, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0730202198028564, "global_step": 376141, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.130075454711914, "global_step": 376142, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0421833992004395, "global_step": 376143, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.042466640472412, "global_step": 376144, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0808956623077393, "global_step": 376145, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1138954162597656, "global_step": 376146, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0635459423065186, "global_step": 376147, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0534398555755615, "global_step": 376148, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0323469638824463, "global_step": 376149, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0616536140441895, "global_step": 376150, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0233964920043945, "global_step": 376151, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1966559886932373, "global_step": 376152, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1226911544799805, "global_step": 376153, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.10585355758667, "global_step": 376154, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.162644863128662, "global_step": 376155, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0890238285064697, "global_step": 376156, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.144425630569458, "global_step": 376157, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1529455184936523, "global_step": 376158, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0764083862304688, "global_step": 376159, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0487520694732666, "global_step": 376160, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0832359790802, "global_step": 376161, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1498332023620605, "global_step": 376162, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.059650421142578, "global_step": 376163, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.097378969192505, "global_step": 376164, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1217072010040283, "global_step": 376165, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1810498237609863, "global_step": 376166, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.089109182357788, "global_step": 376167, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0381453037261963, "global_step": 376168, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0605602264404297, "global_step": 376169, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.127384901046753, "global_step": 376170, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1471657752990723, "global_step": 376171, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0457708835601807, "global_step": 376172, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0817129611968994, "global_step": 376173, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.12256121635437, "global_step": 376174, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1237072944641113, "global_step": 376175, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.214383602142334, "global_step": 376176, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.120534658432007, "global_step": 376177, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.047849416732788, "global_step": 376178, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.05086612701416, "global_step": 376179, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1561856269836426, "global_step": 376180, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.120474338531494, "global_step": 376181, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0882086753845215, "global_step": 376182, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1472299098968506, "global_step": 376183, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.011884927749634, "global_step": 376184, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.117464065551758, "global_step": 376185, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1200430393218994, "global_step": 376186, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1154613494873047, "global_step": 376187, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.265873908996582, "global_step": 376188, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0173561573028564, "global_step": 376189, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.018542766571045, "global_step": 376190, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.17763090133667, "global_step": 376191, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0953407287597656, "global_step": 376192, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.07670259475708, "global_step": 376193, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0460205078125, "global_step": 376194, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0880043506622314, "global_step": 376195, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.141289710998535, "global_step": 376196, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0364739894866943, "global_step": 376197, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.09371018409729, "global_step": 376198, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.092921733856201, "global_step": 376199, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.2284867763519287, "global_step": 376200, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.112361431121826, "global_step": 376201, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.075366735458374, "global_step": 376202, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0930871963500977, "global_step": 376203, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1861579418182373, "global_step": 376204, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.121516704559326, "global_step": 376205, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.088125228881836, "global_step": 376206, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.201396942138672, "global_step": 376207, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.132399082183838, "global_step": 376208, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1329500675201416, "global_step": 376209, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0664191246032715, "global_step": 376210, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1865274906158447, "global_step": 376211, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.048002243041992, "global_step": 376212, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.158921957015991, "global_step": 376213, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1055798530578613, "global_step": 376214, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1147701740264893, "global_step": 376215, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0429587364196777, "global_step": 376216, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1249587535858154, "global_step": 376217, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0862791538238525, "global_step": 376218, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0810539722442627, "global_step": 376219, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0714309215545654, "global_step": 376220, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.169001579284668, "global_step": 376221, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.119295358657837, "global_step": 376222, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.203352212905884, "global_step": 376223, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.069655656814575, "global_step": 376224, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0873327255249023, "global_step": 376225, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.089651107788086, "global_step": 376226, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1167469024658203, "global_step": 376227, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.092834711074829, "global_step": 376228, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.068758487701416, "global_step": 376229, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.051628828048706, "global_step": 376230, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.037177801132202, "global_step": 376231, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.067112922668457, "global_step": 376232, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1187057495117188, "global_step": 376233, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1401941776275635, "global_step": 376234, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0986762046813965, "global_step": 376235, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0801756381988525, "global_step": 376236, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.17893123626709, "global_step": 376237, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.077040433883667, "global_step": 376238, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.055567502975464, "global_step": 376239, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0796427726745605, "global_step": 376240, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.102418899536133, "global_step": 376241, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0578927993774414, "global_step": 376242, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.12123966217041, "global_step": 376243, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0838475227355957, "global_step": 376244, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0068891048431396, "global_step": 376245, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1090378761291504, "global_step": 376246, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.140367031097412, "global_step": 376247, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.093709707260132, "global_step": 376248, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.065230131149292, "global_step": 376249, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0833590030670166, "global_step": 376250, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0551047325134277, "global_step": 376251, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.03106689453125, "global_step": 376252, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.085435628890991, "global_step": 376253, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0987236499786377, "global_step": 376254, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1540791988372803, "global_step": 376255, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1137897968292236, "global_step": 376256, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0576729774475098, "global_step": 376257, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1651084423065186, "global_step": 376258, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.168771505355835, "global_step": 376259, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.145660400390625, "global_step": 376260, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.149951696395874, "global_step": 376261, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.126803398132324, "global_step": 376262, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.104494094848633, "global_step": 376263, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.061326742172241, "global_step": 376264, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1443519592285156, "global_step": 376265, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1565117835998535, "global_step": 376266, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0666589736938477, "global_step": 376267, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1024792194366455, "global_step": 376268, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1729633808135986, "global_step": 376269, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.041759729385376, "global_step": 376270, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1335129737854004, "global_step": 376271, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0694243907928467, "global_step": 376272, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1167094707489014, "global_step": 376273, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.095592498779297, "global_step": 376274, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1424880027770996, "global_step": 376275, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1138389110565186, "global_step": 376276, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1829116344451904, "global_step": 376277, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.144375801086426, "global_step": 376278, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0906851291656494, "global_step": 376279, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.056865692138672, "global_step": 376280, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.017472743988037, "global_step": 376281, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.165982484817505, "global_step": 376282, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0596232414245605, "global_step": 376283, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.113725185394287, "global_step": 376284, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0545811653137207, "global_step": 376285, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0776045322418213, "global_step": 376286, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.141209125518799, "global_step": 376287, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1676251888275146, "global_step": 376288, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1169657707214355, "global_step": 376289, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1599714756011963, "global_step": 376290, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0922491550445557, "global_step": 376291, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1079108715057373, "global_step": 376292, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1679818630218506, "global_step": 376293, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.160874366760254, "global_step": 376294, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0835955142974854, "global_step": 376295, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1744253635406494, "global_step": 376296, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.064936637878418, "global_step": 376297, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1389851570129395, "global_step": 376298, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.045926094055176, "global_step": 376299, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1566410064697266, "global_step": 376300, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.111276388168335, "global_step": 376301, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.222485065460205, "global_step": 376302, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.162442445755005, "global_step": 376303, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0299718379974365, "global_step": 376304, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.129345417022705, "global_step": 376305, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0618579387664795, "global_step": 376306, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0821125507354736, "global_step": 376307, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.131229877471924, "global_step": 376308, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1346662044525146, "global_step": 376309, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0580146312713623, "global_step": 376310, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.006283760070801, "global_step": 376311, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.104642629623413, "global_step": 376312, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1264021396636963, "global_step": 376313, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.167036771774292, "global_step": 376314, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.166365623474121, "global_step": 376315, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.2280542850494385, "global_step": 376316, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.094426155090332, "global_step": 376317, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.043673515319824, "global_step": 376318, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0709800720214844, "global_step": 376319, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.135385513305664, "global_step": 376320, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1243512630462646, "global_step": 376321, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.053757429122925, "global_step": 376322, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1320807933807373, "global_step": 376323, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.187425374984741, "global_step": 376324, "epoch": 738, "lr": 5e-05}
{"train_loss": 1.982913613319397, "global_step": 376325, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.2111408710479736, "global_step": 376326, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0489261150360107, "global_step": 376327, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1256914138793945, "global_step": 376328, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1552369594573975, "global_step": 376329, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1180551052093506, "global_step": 376330, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1040358543395996, "global_step": 376331, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.05194091796875, "global_step": 376332, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0741050243377686, "global_step": 376333, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.196833372116089, "global_step": 376334, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.119767427444458, "global_step": 376335, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1733005046844482, "global_step": 376336, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0962960720062256, "global_step": 376337, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0823311805725098, "global_step": 376338, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0788607597351074, "global_step": 376339, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0976455211639404, "global_step": 376340, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.138132095336914, "global_step": 376341, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.110253095626831, "global_step": 376342, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.191779851913452, "global_step": 376343, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.177142381668091, "global_step": 376344, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0082509517669678, "global_step": 376345, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0417304039001465, "global_step": 376346, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.174886465072632, "global_step": 376347, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1549317836761475, "global_step": 376348, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.069444417953491, "global_step": 376349, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.074202537536621, "global_step": 376350, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0810775756835938, "global_step": 376351, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1040873527526855, "global_step": 376352, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1592602729797363, "global_step": 376353, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0664310455322266, "global_step": 376354, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.091902017593384, "global_step": 376355, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.026163339614868, "global_step": 376356, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1333653926849365, "global_step": 376357, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.133859634399414, "global_step": 376358, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0269718170166016, "global_step": 376359, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0763652324676514, "global_step": 376360, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0511481761932373, "global_step": 376361, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1702728271484375, "global_step": 376362, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.077650547027588, "global_step": 376363, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0859572887420654, "global_step": 376364, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0300543308258057, "global_step": 376365, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.133058547973633, "global_step": 376366, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0985946655273438, "global_step": 376367, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.051201820373535, "global_step": 376368, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.04396915435791, "global_step": 376369, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0341005325317383, "global_step": 376370, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.045877695083618, "global_step": 376371, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1362457275390625, "global_step": 376372, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1280357837677, "global_step": 376373, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.173123359680176, "global_step": 376374, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0979487895965576, "global_step": 376375, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1458301544189453, "global_step": 376376, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1045825481414795, "global_step": 376377, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1497890949249268, "global_step": 376378, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.131272315979004, "global_step": 376379, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1946561336517334, "global_step": 376380, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1501541137695312, "global_step": 376381, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1380715370178223, "global_step": 376382, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.026625633239746, "global_step": 376383, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.183462381362915, "global_step": 376384, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.023070812225342, "global_step": 376385, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0539376735687256, "global_step": 376386, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0511374473571777, "global_step": 376387, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0857226848602295, "global_step": 376388, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0648045539855957, "global_step": 376389, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0176632404327393, "global_step": 376390, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.138368606567383, "global_step": 376391, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.169248580932617, "global_step": 376392, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.050096273422241, "global_step": 376393, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.099299669265747, "global_step": 376394, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.052302598953247, "global_step": 376395, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.059152126312256, "global_step": 376396, "epoch": 738, "lr": 5e-05}
{"train_loss": 1.9916003942489624, "global_step": 376397, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.071258783340454, "global_step": 376398, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0447802543640137, "global_step": 376399, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.170509099960327, "global_step": 376400, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.129389524459839, "global_step": 376401, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.107830286026001, "global_step": 376402, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.094020128250122, "global_step": 376403, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0671615600585938, "global_step": 376404, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.02530837059021, "global_step": 376405, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.09333872795105, "global_step": 376406, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.136514663696289, "global_step": 376407, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1125552654266357, "global_step": 376408, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.078599214553833, "global_step": 376409, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.096484661102295, "global_step": 376410, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.124558448791504, "global_step": 376411, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.111856460571289, "global_step": 376412, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.09574031829834, "global_step": 376413, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0789012908935547, "global_step": 376414, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1837644577026367, "global_step": 376415, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0713796615600586, "global_step": 376416, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.130732536315918, "global_step": 376417, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1351611614227295, "global_step": 376418, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.10710072517395, "global_step": 376419, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.082113265991211, "global_step": 376420, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.109886884689331, "global_step": 376421, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.054713726043701, "global_step": 376422, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.097257375717163, "global_step": 376423, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.123889207839966, "global_step": 376424, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1234970092773438, "global_step": 376425, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.086923360824585, "global_step": 376426, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.167145013809204, "global_step": 376427, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1495091915130615, "global_step": 376428, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0941147804260254, "global_step": 376429, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.038052558898926, "global_step": 376430, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1504790782928467, "global_step": 376431, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.058993339538574, "global_step": 376432, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.131373167037964, "global_step": 376433, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.083735942840576, "global_step": 376434, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0016608238220215, "global_step": 376435, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1775736808776855, "global_step": 376436, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.105189800262451, "global_step": 376437, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1056089401245117, "global_step": 376438, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1098461151123047, "global_step": 376439, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.141446828842163, "global_step": 376440, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0963284969329834, "global_step": 376441, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.087519884109497, "global_step": 376442, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1348578929901123, "global_step": 376443, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.082524299621582, "global_step": 376444, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.060681104660034, "global_step": 376445, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0452566146850586, "global_step": 376446, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.071152687072754, "global_step": 376447, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.143817663192749, "global_step": 376448, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1550347805023193, "global_step": 376449, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0985183715820312, "global_step": 376450, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.092984676361084, "global_step": 376451, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0467021465301514, "global_step": 376452, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.109147548675537, "global_step": 376453, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.061760425567627, "global_step": 376454, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0644242763519287, "global_step": 376455, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1965343952178955, "global_step": 376456, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.143134117126465, "global_step": 376457, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0463287830352783, "global_step": 376458, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.124560832977295, "global_step": 376459, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.066181182861328, "global_step": 376460, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1256234645843506, "global_step": 376461, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0862200260162354, "global_step": 376462, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1459968090057373, "global_step": 376463, "epoch": 738, "lr": 5e-05}
{"train_loss": 1.9689363241195679, "global_step": 376464, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1934516429901123, "global_step": 376465, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0713469982147217, "global_step": 376466, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0861074924468994, "global_step": 376467, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.082703113555908, "global_step": 376468, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.025725841522217, "global_step": 376469, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0701370239257812, "global_step": 376470, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.123697280883789, "global_step": 376471, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1772117614746094, "global_step": 376472, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.182082414627075, "global_step": 376473, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.062983989715576, "global_step": 376474, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.118971586227417, "global_step": 376475, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1177399158477783, "global_step": 376476, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0976884365081787, "global_step": 376477, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.127187967300415, "global_step": 376478, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1473567485809326, "global_step": 376479, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0602047443389893, "global_step": 376480, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1695544719696045, "global_step": 376481, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.167933225631714, "global_step": 376482, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.2023565769195557, "global_step": 376483, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.120190382003784, "global_step": 376484, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1559154987335205, "global_step": 376485, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.03344988822937, "global_step": 376486, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.203084945678711, "global_step": 376487, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.12715220451355, "global_step": 376488, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.17645001411438, "global_step": 376489, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0598340034484863, "global_step": 376490, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.20230770111084, "global_step": 376491, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1846749782562256, "global_step": 376492, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.213331699371338, "global_step": 376493, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.192180871963501, "global_step": 376494, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1356239318847656, "global_step": 376495, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.088129997253418, "global_step": 376496, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1313772201538086, "global_step": 376497, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.092914581298828, "global_step": 376498, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0728001594543457, "global_step": 376499, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1625518798828125, "global_step": 376500, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1726980209350586, "global_step": 376501, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1302707195281982, "global_step": 376502, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.145280361175537, "global_step": 376503, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.114348888397217, "global_step": 376504, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0297625064849854, "global_step": 376505, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.17231822013855, "global_step": 376506, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.088291883468628, "global_step": 376507, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0779268741607666, "global_step": 376508, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.131161689758301, "global_step": 376509, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1021957397460938, "global_step": 376510, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.094721794128418, "global_step": 376511, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.155146837234497, "global_step": 376512, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0658249855041504, "global_step": 376513, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.064298152923584, "global_step": 376514, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0758838653564453, "global_step": 376515, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.098909616470337, "global_step": 376516, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1537160873413086, "global_step": 376517, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0483884811401367, "global_step": 376518, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1151371002197266, "global_step": 376519, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1674652099609375, "global_step": 376520, "epoch": 738, "lr": 5e-05}
{"train_loss": 1.9956111907958984, "global_step": 376521, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0513758659362793, "global_step": 376522, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1020331382751465, "global_step": 376523, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.042464017868042, "global_step": 376524, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0547854900360107, "global_step": 376525, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1295082569122314, "global_step": 376526, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1007163524627686, "global_step": 376527, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0959105491638184, "global_step": 376528, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1604387760162354, "global_step": 376529, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0817861557006836, "global_step": 376530, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1036601066589355, "global_step": 376531, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.128983497619629, "global_step": 376532, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.059828996658325, "global_step": 376533, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.166058301925659, "global_step": 376534, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.157949924468994, "global_step": 376535, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.064879894256592, "global_step": 376536, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.073887586593628, "global_step": 376537, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1648266315460205, "global_step": 376538, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.105231761932373, "global_step": 376539, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.131071090698242, "global_step": 376540, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1400091648101807, "global_step": 376541, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0823044776916504, "global_step": 376542, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1282191276550293, "global_step": 376543, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1228044033050537, "global_step": 376544, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.080554246902466, "global_step": 376545, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.083381175994873, "global_step": 376546, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.149061679840088, "global_step": 376547, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0381879806518555, "global_step": 376548, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.084167003631592, "global_step": 376549, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1123783588409424, "global_step": 376550, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1834518909454346, "global_step": 376551, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1239256858825684, "global_step": 376552, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.253127336502075, "global_step": 376553, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0429935455322266, "global_step": 376554, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1016101837158203, "global_step": 376555, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0866916179656982, "global_step": 376556, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.073417901992798, "global_step": 376557, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0668039321899414, "global_step": 376558, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.101227045059204, "global_step": 376559, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.182739019393921, "global_step": 376560, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1542110443115234, "global_step": 376561, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1637516021728516, "global_step": 376562, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1490719318389893, "global_step": 376563, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1498119831085205, "global_step": 376564, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.074080228805542, "global_step": 376565, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1484932899475098, "global_step": 376566, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.057795763015747, "global_step": 376567, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.117276906967163, "global_step": 376568, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1557443141937256, "global_step": 376569, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.113394021987915, "global_step": 376570, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0155467987060547, "global_step": 376571, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.065002918243408, "global_step": 376572, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.2004988193511963, "global_step": 376573, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0927646160125732, "global_step": 376574, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1100969314575195, "global_step": 376575, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.171088218688965, "global_step": 376576, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.122793197631836, "global_step": 376577, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1304173469543457, "global_step": 376578, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.107823610305786, "global_step": 376579, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1908390522003174, "global_step": 376580, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.221632957458496, "global_step": 376581, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.119791269302368, "global_step": 376582, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1326165199279785, "global_step": 376583, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1663899421691895, "global_step": 376584, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.102828025817871, "global_step": 376585, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1908257007598877, "global_step": 376586, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1223554611206055, "global_step": 376587, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0224592685699463, "global_step": 376588, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.127525806427002, "global_step": 376589, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1075198650360107, "global_step": 376590, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0830929279327393, "global_step": 376591, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0737104415893555, "global_step": 376592, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1666362285614014, "global_step": 376593, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.162119150161743, "global_step": 376594, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.089871644973755, "global_step": 376595, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.136655807495117, "global_step": 376596, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1227927207946777, "global_step": 376597, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.079071044921875, "global_step": 376598, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0676677227020264, "global_step": 376599, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.085844039916992, "global_step": 376600, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1025428771972656, "global_step": 376601, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.094851016998291, "global_step": 376602, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0763232707977295, "global_step": 376603, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.076550006866455, "global_step": 376604, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0574803352355957, "global_step": 376605, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1634507179260254, "global_step": 376606, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.128863573074341, "global_step": 376607, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1125385761260986, "global_step": 376608, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.025526762008667, "global_step": 376609, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0707085132598877, "global_step": 376610, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1255972385406494, "global_step": 376611, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1660337448120117, "global_step": 376612, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0714688301086426, "global_step": 376613, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.2005720138549805, "global_step": 376614, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.044053554534912, "global_step": 376615, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.115943193435669, "global_step": 376616, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.2533648014068604, "global_step": 376617, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0603814125061035, "global_step": 376618, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.02427339553833, "global_step": 376619, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1916098594665527, "global_step": 376620, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0351433753967285, "global_step": 376621, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.129565954208374, "global_step": 376622, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1148898601531982, "global_step": 376623, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.132112503051758, "global_step": 376624, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.005211114883423, "global_step": 376625, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.109344959259033, "global_step": 376626, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.163804531097412, "global_step": 376627, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0496885776519775, "global_step": 376628, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0577943325042725, "global_step": 376629, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.081535577774048, "global_step": 376630, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.120107889175415, "global_step": 376631, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.160067081451416, "global_step": 376632, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.14729905128479, "global_step": 376633, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.111671209335327, "global_step": 376634, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0672786235809326, "global_step": 376635, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.103045701980591, "global_step": 376636, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.125349760055542, "global_step": 376637, "epoch": 738, "lr": 5e-05}
{"train_loss": 1.9538511037826538, "global_step": 376638, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.2469210624694824, "global_step": 376639, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.140383720397949, "global_step": 376640, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1439781188964844, "global_step": 376641, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.110389232635498, "global_step": 376642, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.02457594871521, "global_step": 376643, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.096130609512329, "global_step": 376644, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.141983985900879, "global_step": 376645, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.114781379699707, "global_step": 376646, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1364288330078125, "global_step": 376647, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1696481704711914, "global_step": 376648, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1006579399108887, "global_step": 376649, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.084597110748291, "global_step": 376650, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.099059820175171, "global_step": 376651, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.037019729614258, "global_step": 376652, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0393967628479004, "global_step": 376653, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0621488094329834, "global_step": 376654, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0663232803344727, "global_step": 376655, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.195749044418335, "global_step": 376656, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0732827186584473, "global_step": 376657, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0923523902893066, "global_step": 376658, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1417057514190674, "global_step": 376659, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1220786571502686, "global_step": 376660, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1069905757904053, "global_step": 376661, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1045310497283936, "global_step": 376662, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1009609699249268, "global_step": 376663, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1568288803100586, "global_step": 376664, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1081531047821045, "global_step": 376665, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.001328945159912, "global_step": 376666, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.063480854034424, "global_step": 376667, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1251842975616455, "global_step": 376668, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0864734649658203, "global_step": 376669, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.020779848098755, "global_step": 376670, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0965139865875244, "global_step": 376671, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0741465091705322, "global_step": 376672, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1431777477264404, "global_step": 376673, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.091188669204712, "global_step": 376674, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.036909580230713, "global_step": 376675, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.075653314590454, "global_step": 376676, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.106049060821533, "global_step": 376677, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1245460510253906, "global_step": 376678, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0552923679351807, "global_step": 376679, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.132537364959717, "global_step": 376680, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1062402725219727, "global_step": 376681, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.107767343521118, "global_step": 376682, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.093412160873413, "global_step": 376683, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1340088844299316, "global_step": 376684, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1022419929504395, "global_step": 376685, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0209479331970215, "global_step": 376686, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.209197521209717, "global_step": 376687, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1505625247955322, "global_step": 376688, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0233614444732666, "global_step": 376689, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.147761344909668, "global_step": 376690, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.137411594390869, "global_step": 376691, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1564228534698486, "global_step": 376692, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.088336706161499, "global_step": 376693, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.040497064590454, "global_step": 376694, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.145458221435547, "global_step": 376695, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.074899196624756, "global_step": 376696, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1385440826416016, "global_step": 376697, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1264235973358154, "global_step": 376698, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.063992738723755, "global_step": 376699, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1684792041778564, "global_step": 376700, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.114947557449341, "global_step": 376701, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.089919090270996, "global_step": 376702, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1451146602630615, "global_step": 376703, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.110424041748047, "global_step": 376704, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.157660722732544, "global_step": 376705, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1159629821777344, "global_step": 376706, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.116488218307495, "global_step": 376707, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0766539573669434, "global_step": 376708, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1513354778289795, "global_step": 376709, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.075094699859619, "global_step": 376710, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1271743774414062, "global_step": 376711, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.038569688796997, "global_step": 376712, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.090749502182007, "global_step": 376713, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0573854446411133, "global_step": 376714, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1499381065368652, "global_step": 376715, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0974159240722656, "global_step": 376716, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0588839054107666, "global_step": 376717, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.155467987060547, "global_step": 376718, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0398552417755127, "global_step": 376719, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1061670780181885, "global_step": 376720, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0957467555999756, "global_step": 376721, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.152515411376953, "global_step": 376722, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1521358489990234, "global_step": 376723, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1601402759552, "global_step": 376724, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.076961040496826, "global_step": 376725, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1435446739196777, "global_step": 376726, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1298460960388184, "global_step": 376727, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0687217712402344, "global_step": 376728, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1603500843048096, "global_step": 376729, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0853500366210938, "global_step": 376730, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1666438579559326, "global_step": 376731, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.05767560005188, "global_step": 376732, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.098998546600342, "global_step": 376733, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.105072259902954, "global_step": 376734, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.103895664215088, "global_step": 376735, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.145371198654175, "global_step": 376736, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1244654655456543, "global_step": 376737, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.145728588104248, "global_step": 376738, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1750147342681885, "global_step": 376739, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1069772243499756, "global_step": 376740, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.072232723236084, "global_step": 376741, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.076103687286377, "global_step": 376742, "epoch": 738, "lr": 5e-05}
{"train_loss": 1.9927963018417358, "global_step": 376743, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.07243275642395, "global_step": 376744, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1121020317077637, "global_step": 376745, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.122694492340088, "global_step": 376746, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1734535694122314, "global_step": 376747, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.115992307662964, "global_step": 376748, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.184202194213867, "global_step": 376749, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1430842876434326, "global_step": 376750, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.026939630508423, "global_step": 376751, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.107435703277588, "global_step": 376752, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0063230991363525, "global_step": 376753, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1927037239074707, "global_step": 376754, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1010096073150635, "global_step": 376755, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.17470383644104, "global_step": 376756, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0788474082946777, "global_step": 376757, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.2059247493743896, "global_step": 376758, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1292803287506104, "global_step": 376759, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1129112243652344, "global_step": 376760, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1417922973632812, "global_step": 376761, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.092923641204834, "global_step": 376762, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1266894340515137, "global_step": 376763, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.082460403442383, "global_step": 376764, "epoch": 738, "lr": 5e-05}
{"train_loss": 1.9892957210540771, "global_step": 376765, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0345544815063477, "global_step": 376766, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.080399990081787, "global_step": 376767, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1926417350769043, "global_step": 376768, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0768632888793945, "global_step": 376769, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.065718650817871, "global_step": 376770, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1302287578582764, "global_step": 376771, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.103142499923706, "global_step": 376772, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1410648822784424, "global_step": 376773, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0232303142547607, "global_step": 376774, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0691545009613037, "global_step": 376775, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.044067859649658, "global_step": 376776, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.097841739654541, "global_step": 376777, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0612568855285645, "global_step": 376778, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1101255416870117, "global_step": 376779, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1631975173950195, "global_step": 376780, "epoch": 738, "lr": 5e-05}
{"train_loss": 1.9993972778320312, "global_step": 376781, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0702905654907227, "global_step": 376782, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.128505229949951, "global_step": 376783, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1000053882598877, "global_step": 376784, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0987045764923096, "global_step": 376785, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0775372982025146, "global_step": 376786, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.047274112701416, "global_step": 376787, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1129093170166016, "global_step": 376788, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1193528175354004, "global_step": 376789, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.152103900909424, "global_step": 376790, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0411996841430664, "global_step": 376791, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.077643632888794, "global_step": 376792, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.092555046081543, "global_step": 376793, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.059415340423584, "global_step": 376794, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1343636512756348, "global_step": 376795, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.190687894821167, "global_step": 376796, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0854547023773193, "global_step": 376797, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1090142726898193, "global_step": 376798, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0727648735046387, "global_step": 376799, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1255245208740234, "global_step": 376800, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.035468816757202, "global_step": 376801, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0413129329681396, "global_step": 376802, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0979909896850586, "global_step": 376803, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.054175853729248, "global_step": 376804, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.060764789581299, "global_step": 376805, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1594903469085693, "global_step": 376806, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1360435485839844, "global_step": 376807, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.113048791885376, "global_step": 376808, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.093963384628296, "global_step": 376809, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0690500736236572, "global_step": 376810, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.201547384262085, "global_step": 376811, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.183332920074463, "global_step": 376812, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0756266117095947, "global_step": 376813, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1258389949798584, "global_step": 376814, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.158867835998535, "global_step": 376815, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1532580852508545, "global_step": 376816, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.019171714782715, "global_step": 376817, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.112271547317505, "global_step": 376818, "epoch": 738, "lr": 5e-05}
{"train_loss": 1.9977947473526, "global_step": 376819, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1325016021728516, "global_step": 376820, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.161724090576172, "global_step": 376821, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.160616874694824, "global_step": 376822, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.021275043487549, "global_step": 376823, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1014602184295654, "global_step": 376824, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.06939959526062, "global_step": 376825, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.047835111618042, "global_step": 376826, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1320271492004395, "global_step": 376827, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.183218002319336, "global_step": 376828, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.138683319091797, "global_step": 376829, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.187711238861084, "global_step": 376830, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0799009799957275, "global_step": 376831, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.137045383453369, "global_step": 376832, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0740227699279785, "global_step": 376833, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1550426483154297, "global_step": 376834, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1834962368011475, "global_step": 376835, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1788511276245117, "global_step": 376836, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1436452865600586, "global_step": 376837, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.096160411834717, "global_step": 376838, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1300902366638184, "global_step": 376839, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.127802848815918, "global_step": 376840, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1092331409454346, "global_step": 376841, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.2249691486358643, "global_step": 376842, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0310003757476807, "global_step": 376843, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1623055934906006, "global_step": 376844, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.104555130004883, "global_step": 376845, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.2393059730529785, "global_step": 376846, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0406291484832764, "global_step": 376847, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.134107828140259, "global_step": 376848, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1041131019592285, "global_step": 376849, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0657598972320557, "global_step": 376850, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1586997509002686, "global_step": 376851, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.2242510318756104, "global_step": 376852, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0642693042755127, "global_step": 376853, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0818533897399902, "global_step": 376854, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.088559627532959, "global_step": 376855, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.183651924133301, "global_step": 376856, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.153782844543457, "global_step": 376857, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0508620738983154, "global_step": 376858, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.042743444442749, "global_step": 376859, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1578550338745117, "global_step": 376860, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1474223136901855, "global_step": 376861, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0847854614257812, "global_step": 376862, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.129601001739502, "global_step": 376863, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.135840654373169, "global_step": 376864, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1491639614105225, "global_step": 376865, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.2318594455718994, "global_step": 376866, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1499805450439453, "global_step": 376867, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.043524742126465, "global_step": 376868, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1202855110168457, "global_step": 376869, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.157571792602539, "global_step": 376870, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1349332332611084, "global_step": 376871, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1016182899475098, "global_step": 376872, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.2192466259002686, "global_step": 376873, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.139854669570923, "global_step": 376874, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.032862424850464, "global_step": 376875, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1337997913360596, "global_step": 376876, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0821492671966553, "global_step": 376877, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.104872465133667, "global_step": 376878, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.036343574523926, "global_step": 376879, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1193795204162598, "global_step": 376880, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0544991493225098, "global_step": 376881, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0270044803619385, "global_step": 376882, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.174811363220215, "global_step": 376883, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.056431770324707, "global_step": 376884, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.179419994354248, "global_step": 376885, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1081228256225586, "global_step": 376886, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1342649459838867, "global_step": 376887, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0015435218811035, "global_step": 376888, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0471408367156982, "global_step": 376889, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.099214553833008, "global_step": 376890, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1482701301574707, "global_step": 376891, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.042677879333496, "global_step": 376892, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.137228488922119, "global_step": 376893, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0553982257843018, "global_step": 376894, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0889933109283447, "global_step": 376895, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0596976280212402, "global_step": 376896, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0427262783050537, "global_step": 376897, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1534218788146973, "global_step": 376898, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.163022518157959, "global_step": 376899, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.137049436569214, "global_step": 376900, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.118648052215576, "global_step": 376901, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1457443237304688, "global_step": 376902, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0097503662109375, "global_step": 376903, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1291890144348145, "global_step": 376904, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0603187084198, "global_step": 376905, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0438506603240967, "global_step": 376906, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1860196590423584, "global_step": 376907, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0978987216949463, "global_step": 376908, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1499147415161133, "global_step": 376909, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0702669620513916, "global_step": 376910, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.2266881465911865, "global_step": 376911, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.095858573913574, "global_step": 376912, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.119727611541748, "global_step": 376913, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1114754676818848, "global_step": 376914, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.136040210723877, "global_step": 376915, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.108048915863037, "global_step": 376916, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.115330696105957, "global_step": 376917, "epoch": 738, "lr": 5e-05}
{"train_loss": 1.974638819694519, "global_step": 376918, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1623916625976562, "global_step": 376919, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.2165322303771973, "global_step": 376920, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1343188285827637, "global_step": 376921, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0719316005706787, "global_step": 376922, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.167783737182617, "global_step": 376923, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.049556016921997, "global_step": 376924, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0309886932373047, "global_step": 376925, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.110140562057495, "global_step": 376926, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1448733806610107, "global_step": 376927, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1590230464935303, "global_step": 376928, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.123188018798828, "global_step": 376929, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0466997623443604, "global_step": 376930, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1170461177825928, "global_step": 376931, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.143949270248413, "global_step": 376932, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.040189504623413, "global_step": 376933, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.015378475189209, "global_step": 376934, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.230393409729004, "global_step": 376935, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.074125289916992, "global_step": 376936, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0872108936309814, "global_step": 376937, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1426408290863037, "global_step": 376938, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.156928539276123, "global_step": 376939, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.028075695037842, "global_step": 376940, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1595633029937744, "global_step": 376941, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.149503231048584, "global_step": 376942, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1257519721984863, "global_step": 376943, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.084291696548462, "global_step": 376944, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.095088005065918, "global_step": 376945, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.115427017211914, "global_step": 376946, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0646603107452393, "global_step": 376947, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.209383249282837, "global_step": 376948, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.151930570602417, "global_step": 376949, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1882519721984863, "global_step": 376950, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.17261004447937, "global_step": 376951, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.2017571926116943, "global_step": 376952, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1450324058532715, "global_step": 376953, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0958359241485596, "global_step": 376954, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.032668352127075, "global_step": 376955, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0818471908569336, "global_step": 376956, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.060159683227539, "global_step": 376957, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.076744556427002, "global_step": 376958, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.104325771331787, "global_step": 376959, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.085747241973877, "global_step": 376960, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1053285598754883, "global_step": 376961, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.208714485168457, "global_step": 376962, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.085010528564453, "global_step": 376963, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1711935997009277, "global_step": 376964, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1424779891967773, "global_step": 376965, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0455093383789062, "global_step": 376966, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1299526691436768, "global_step": 376967, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0499117374420166, "global_step": 376968, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0667355060577393, "global_step": 376969, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1412839889526367, "global_step": 376970, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.059323787689209, "global_step": 376971, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.139230251312256, "global_step": 376972, "epoch": 738, "lr": 5e-05}
{"train_loss": 1.9639326333999634, "global_step": 376973, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.208216428756714, "global_step": 376974, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.152053117752075, "global_step": 376975, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.174088716506958, "global_step": 376976, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.2123472690582275, "global_step": 376977, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1303775310516357, "global_step": 376978, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.122692346572876, "global_step": 376979, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1593542098999023, "global_step": 376980, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.128298759460449, "global_step": 376981, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0262746810913086, "global_step": 376982, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.118119955062866, "global_step": 376983, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1157102584838867, "global_step": 376984, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.097256660461426, "global_step": 376985, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1229662895202637, "global_step": 376986, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0886781215667725, "global_step": 376987, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1871442794799805, "global_step": 376988, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1225650310516357, "global_step": 376989, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1513073444366455, "global_step": 376990, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.17045521736145, "global_step": 376991, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1041758060455322, "global_step": 376992, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.107520580291748, "global_step": 376993, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.110152244567871, "global_step": 376994, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0826966762542725, "global_step": 376995, "epoch": 738, "lr": 5e-05}
{"train_loss": 1.9917335510253906, "global_step": 376996, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.09114933013916, "global_step": 376997, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.142329692840576, "global_step": 376998, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0722084045410156, "global_step": 376999, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1207363605499268, "global_step": 377000, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.163912773132324, "global_step": 377001, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0714287757873535, "global_step": 377002, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0733821392059326, "global_step": 377003, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0560951232910156, "global_step": 377004, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1161282062530518, "global_step": 377005, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.06943416595459, "global_step": 377006, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0763747692108154, "global_step": 377007, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0583176612854004, "global_step": 377008, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1213343143463135, "global_step": 377009, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.17976713180542, "global_step": 377010, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.027636766433716, "global_step": 377011, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1250767707824707, "global_step": 377012, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.085684299468994, "global_step": 377013, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0851759910583496, "global_step": 377014, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0590150356292725, "global_step": 377015, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0857207775115967, "global_step": 377016, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0477147102355957, "global_step": 377017, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1135528087615967, "global_step": 377018, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1533620357513428, "global_step": 377019, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0998125076293945, "global_step": 377020, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.159933090209961, "global_step": 377021, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1288578510284424, "global_step": 377022, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0567383766174316, "global_step": 377023, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0300073623657227, "global_step": 377024, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.136535167694092, "global_step": 377025, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0912117958068848, "global_step": 377026, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0871708393096924, "global_step": 377027, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0786850452423096, "global_step": 377028, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.246699094772339, "global_step": 377029, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1824212074279785, "global_step": 377030, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1341681480407715, "global_step": 377031, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1364850997924805, "global_step": 377032, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1415226459503174, "global_step": 377033, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.090710401535034, "global_step": 377034, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.12138295173645, "global_step": 377035, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1251916885375977, "global_step": 377036, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.185499668121338, "global_step": 377037, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.031046152114868, "global_step": 377038, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1128041744232178, "global_step": 377039, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0663299560546875, "global_step": 377040, "epoch": 738, "lr": 5e-05}
{"train_loss": 1.9646567106246948, "global_step": 377041, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.140164375305176, "global_step": 377042, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.09014892578125, "global_step": 377043, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0449416637420654, "global_step": 377044, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1859982013702393, "global_step": 377045, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.056004047393799, "global_step": 377046, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0702731609344482, "global_step": 377047, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1246376037597656, "global_step": 377048, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.094879627227783, "global_step": 377049, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.085523843765259, "global_step": 377050, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.228137254714966, "global_step": 377051, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.154212236404419, "global_step": 377052, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0725257396698, "global_step": 377053, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0817267894744873, "global_step": 377054, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1202611923217773, "global_step": 377055, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1108736991882324, "global_step": 377056, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.11338472366333, "global_step": 377057, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0994439125061035, "global_step": 377058, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.12290620803833, "global_step": 377059, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.104950189590454, "global_step": 377060, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1259562969207764, "global_step": 377061, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1857826709747314, "global_step": 377062, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1428544521331787, "global_step": 377063, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0706100463867188, "global_step": 377064, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1070122718811035, "global_step": 377065, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0192110538482666, "global_step": 377066, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.181581735610962, "global_step": 377067, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1251354217529297, "global_step": 377068, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.0885872840881348, "global_step": 377069, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.090535879135132, "global_step": 377070, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.15143084526062, "global_step": 377071, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.103954792022705, "global_step": 377072, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.107325792312622, "global_step": 377073, "epoch": 738, "lr": 5e-05}
{"train_loss": 2.1143527030944824, "global_step": 377074, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.077180862426758, "global_step": 377075, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.085232973098755, "global_step": 377076, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1558403968811035, "global_step": 377077, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.112431764602661, "global_step": 377078, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0547196865081787, "global_step": 377079, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1330454349517822, "global_step": 377080, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1518213748931885, "global_step": 377081, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1065993309020996, "global_step": 377082, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.085573434829712, "global_step": 377083, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.047175407409668, "global_step": 377084, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.115558624267578, "global_step": 377085, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1644222736358643, "global_step": 377086, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.046250581741333, "global_step": 377087, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.044595241546631, "global_step": 377088, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1037423610687256, "global_step": 377089, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1045424938201904, "global_step": 377090, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0390121936798096, "global_step": 377091, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.020240545272827, "global_step": 377092, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1092398166656494, "global_step": 377093, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.092649221420288, "global_step": 377094, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1142125129699707, "global_step": 377095, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.08522891998291, "global_step": 377096, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.08901309967041, "global_step": 377097, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1818935871124268, "global_step": 377098, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.154679775238037, "global_step": 377099, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1292786598205566, "global_step": 377100, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1802046298980713, "global_step": 377101, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.109010696411133, "global_step": 377102, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.055851459503174, "global_step": 377103, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.137493371963501, "global_step": 377104, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.088512420654297, "global_step": 377105, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.078662157058716, "global_step": 377106, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0858302116394043, "global_step": 377107, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1031088829040527, "global_step": 377108, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1068437099456787, "global_step": 377109, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.09529709815979, "global_step": 377110, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1153244972229004, "global_step": 377111, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.044595956802368, "global_step": 377112, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1208038330078125, "global_step": 377113, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0865983963012695, "global_step": 377114, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.017791271209717, "global_step": 377115, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.137510061264038, "global_step": 377116, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.036283493041992, "global_step": 377117, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0585436820983887, "global_step": 377118, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0565390586853027, "global_step": 377119, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.141345739364624, "global_step": 377120, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1374616622924805, "global_step": 377121, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0478627681732178, "global_step": 377122, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1163864135742188, "global_step": 377123, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0490453243255615, "global_step": 377124, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.208470582962036, "global_step": 377125, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.048184871673584, "global_step": 377126, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0284671783447266, "global_step": 377127, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.069551467895508, "global_step": 377128, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0123395919799805, "global_step": 377129, "epoch": 739, "lr": 5e-05}
{"train_loss": 1.9806699752807617, "global_step": 377130, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.142176866531372, "global_step": 377131, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.080134868621826, "global_step": 377132, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.101820468902588, "global_step": 377133, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1205899715423584, "global_step": 377134, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1225502490997314, "global_step": 377135, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.237426519393921, "global_step": 377136, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1464133262634277, "global_step": 377137, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0974507331848145, "global_step": 377138, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1218674182891846, "global_step": 377139, "epoch": 739, "lr": 5e-05}
{"train_loss": 1.9797024726867676, "global_step": 377140, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0363457202911377, "global_step": 377141, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1189820766448975, "global_step": 377142, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.103388786315918, "global_step": 377143, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.059023141860962, "global_step": 377144, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0350565910339355, "global_step": 377145, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.139704942703247, "global_step": 377146, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0994207859039307, "global_step": 377147, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1530654430389404, "global_step": 377148, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.205684185028076, "global_step": 377149, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0925824642181396, "global_step": 377150, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.085545063018799, "global_step": 377151, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.158712863922119, "global_step": 377152, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.053617238998413, "global_step": 377153, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0841550827026367, "global_step": 377154, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1398653984069824, "global_step": 377155, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.011530876159668, "global_step": 377156, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.161693572998047, "global_step": 377157, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1265640258789062, "global_step": 377158, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.116421937942505, "global_step": 377159, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0350921154022217, "global_step": 377160, "epoch": 739, "lr": 5e-05}
{"train_loss": 1.9715293645858765, "global_step": 377161, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0642244815826416, "global_step": 377162, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.128002882003784, "global_step": 377163, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0496058464050293, "global_step": 377164, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.128150701522827, "global_step": 377165, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0981504917144775, "global_step": 377166, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1471669673919678, "global_step": 377167, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.182192087173462, "global_step": 377168, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0485262870788574, "global_step": 377169, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.13415265083313, "global_step": 377170, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.16666579246521, "global_step": 377171, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0824551582336426, "global_step": 377172, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1772801876068115, "global_step": 377173, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.083634376525879, "global_step": 377174, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.090324640274048, "global_step": 377175, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.010603427886963, "global_step": 377176, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0821704864501953, "global_step": 377177, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.126451253890991, "global_step": 377178, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.138042449951172, "global_step": 377179, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0249648094177246, "global_step": 377180, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1137349605560303, "global_step": 377181, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1574764251708984, "global_step": 377182, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0970351696014404, "global_step": 377183, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0118181705474854, "global_step": 377184, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.035362720489502, "global_step": 377185, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0982673168182373, "global_step": 377186, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.087362051010132, "global_step": 377187, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0475878715515137, "global_step": 377188, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0679991245269775, "global_step": 377189, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.15006685256958, "global_step": 377190, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0727570056915283, "global_step": 377191, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.136634349822998, "global_step": 377192, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.063359260559082, "global_step": 377193, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1469826698303223, "global_step": 377194, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.231569528579712, "global_step": 377195, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.108837127685547, "global_step": 377196, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.05399227142334, "global_step": 377197, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.06662917137146, "global_step": 377198, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.05950927734375, "global_step": 377199, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0157203674316406, "global_step": 377200, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0375263690948486, "global_step": 377201, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.014479398727417, "global_step": 377202, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0414116382598877, "global_step": 377203, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0731053352355957, "global_step": 377204, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.102437734603882, "global_step": 377205, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0794575214385986, "global_step": 377206, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.14304518699646, "global_step": 377207, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1046640872955322, "global_step": 377208, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1757073402404785, "global_step": 377209, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1410815715789795, "global_step": 377210, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1673643589019775, "global_step": 377211, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.115767002105713, "global_step": 377212, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.056464195251465, "global_step": 377213, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1264262199401855, "global_step": 377214, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0775582790374756, "global_step": 377215, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0960588455200195, "global_step": 377216, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.2410194873809814, "global_step": 377217, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.100358724594116, "global_step": 377218, "epoch": 739, "lr": 5e-05}
{"train_loss": 1.9184523820877075, "global_step": 377219, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.111367702484131, "global_step": 377220, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.131822109222412, "global_step": 377221, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.050459384918213, "global_step": 377222, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1411542892456055, "global_step": 377223, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1139109134674072, "global_step": 377224, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.106151819229126, "global_step": 377225, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.139533042907715, "global_step": 377226, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.070258140563965, "global_step": 377227, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0483250617980957, "global_step": 377228, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.160396099090576, "global_step": 377229, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.047482967376709, "global_step": 377230, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.121469736099243, "global_step": 377231, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.106382131576538, "global_step": 377232, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.139224052429199, "global_step": 377233, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0607590675354004, "global_step": 377234, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.097716808319092, "global_step": 377235, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.179778814315796, "global_step": 377236, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.077883243560791, "global_step": 377237, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0852017402648926, "global_step": 377238, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1158695220947266, "global_step": 377239, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.233914613723755, "global_step": 377240, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0696659088134766, "global_step": 377241, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.062230110168457, "global_step": 377242, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0665578842163086, "global_step": 377243, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.131913661956787, "global_step": 377244, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.121593475341797, "global_step": 377245, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.117537021636963, "global_step": 377246, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1391537189483643, "global_step": 377247, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.094838857650757, "global_step": 377248, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1531312465667725, "global_step": 377249, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0522611141204834, "global_step": 377250, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.137221336364746, "global_step": 377251, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1097629070281982, "global_step": 377252, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1406311988830566, "global_step": 377253, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0580146312713623, "global_step": 377254, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.139585256576538, "global_step": 377255, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.171509265899658, "global_step": 377256, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.083430290222168, "global_step": 377257, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0899875164031982, "global_step": 377258, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1607038974761963, "global_step": 377259, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.107001543045044, "global_step": 377260, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1446456909179688, "global_step": 377261, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.087092399597168, "global_step": 377262, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.135495185852051, "global_step": 377263, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.184220552444458, "global_step": 377264, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1125216484069824, "global_step": 377265, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0730457305908203, "global_step": 377266, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1190133094787598, "global_step": 377267, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0465126037597656, "global_step": 377268, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0603883266448975, "global_step": 377269, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1305346488952637, "global_step": 377270, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0982532501220703, "global_step": 377271, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1259548664093018, "global_step": 377272, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.2133491039276123, "global_step": 377273, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1290411949157715, "global_step": 377274, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.097625732421875, "global_step": 377275, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.119349956512451, "global_step": 377276, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.157942533493042, "global_step": 377277, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0851893424987793, "global_step": 377278, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.094674587249756, "global_step": 377279, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1325089931488037, "global_step": 377280, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.002758741378784, "global_step": 377281, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0944314002990723, "global_step": 377282, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1656203269958496, "global_step": 377283, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0383946895599365, "global_step": 377284, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1047046184539795, "global_step": 377285, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.09702467918396, "global_step": 377286, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.031932830810547, "global_step": 377287, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1268770694732666, "global_step": 377288, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1355361938476562, "global_step": 377289, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.162348747253418, "global_step": 377290, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.177865982055664, "global_step": 377291, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0745491981506348, "global_step": 377292, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0761334896087646, "global_step": 377293, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.108356237411499, "global_step": 377294, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.002291679382324, "global_step": 377295, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1436173915863037, "global_step": 377296, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.182436943054199, "global_step": 377297, "epoch": 739, "lr": 5e-05}
{"train_loss": 1.9533573389053345, "global_step": 377298, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1249778270721436, "global_step": 377299, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1506576538085938, "global_step": 377300, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.170734405517578, "global_step": 377301, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0750491619110107, "global_step": 377302, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.140514373779297, "global_step": 377303, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.087158679962158, "global_step": 377304, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0635790824890137, "global_step": 377305, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.091043472290039, "global_step": 377306, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0178301334381104, "global_step": 377307, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.115846633911133, "global_step": 377308, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1506831645965576, "global_step": 377309, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1431334018707275, "global_step": 377310, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.148308277130127, "global_step": 377311, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.047096014022827, "global_step": 377312, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.143526077270508, "global_step": 377313, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0703210830688477, "global_step": 377314, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0848090648651123, "global_step": 377315, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0648603439331055, "global_step": 377316, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1123504638671875, "global_step": 377317, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.023677349090576, "global_step": 377318, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0750205516815186, "global_step": 377319, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.125129222869873, "global_step": 377320, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.079324722290039, "global_step": 377321, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.033623218536377, "global_step": 377322, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.115645408630371, "global_step": 377323, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1053121089935303, "global_step": 377324, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1200544834136963, "global_step": 377325, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0937983989715576, "global_step": 377326, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0794129371643066, "global_step": 377327, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.055896520614624, "global_step": 377328, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.038719892501831, "global_step": 377329, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1577608585357666, "global_step": 377330, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0911667346954346, "global_step": 377331, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.145752429962158, "global_step": 377332, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1647913455963135, "global_step": 377333, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0095629692077637, "global_step": 377334, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1619346141815186, "global_step": 377335, "epoch": 739, "lr": 5e-05}
{"train_loss": 1.9934591054916382, "global_step": 377336, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0455284118652344, "global_step": 377337, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1396234035491943, "global_step": 377338, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1052446365356445, "global_step": 377339, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0639150142669678, "global_step": 377340, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.215988874435425, "global_step": 377341, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0270915031433105, "global_step": 377342, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0704073905944824, "global_step": 377343, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0396151542663574, "global_step": 377344, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.113468885421753, "global_step": 377345, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0657074451446533, "global_step": 377346, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0546374320983887, "global_step": 377347, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0977330207824707, "global_step": 377348, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.097233533859253, "global_step": 377349, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0961365699768066, "global_step": 377350, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0656869411468506, "global_step": 377351, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.134383201599121, "global_step": 377352, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0949161052703857, "global_step": 377353, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.094653367996216, "global_step": 377354, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1252243518829346, "global_step": 377355, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.04504656791687, "global_step": 377356, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1648600101470947, "global_step": 377357, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0687448978424072, "global_step": 377358, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0863590240478516, "global_step": 377359, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0931155681610107, "global_step": 377360, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0495855808258057, "global_step": 377361, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.180603504180908, "global_step": 377362, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1575655937194824, "global_step": 377363, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0837600231170654, "global_step": 377364, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.016724109649658, "global_step": 377365, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0690653324127197, "global_step": 377366, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1725013256073, "global_step": 377367, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1102051734924316, "global_step": 377368, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.083240509033203, "global_step": 377369, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1463069915771484, "global_step": 377370, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1992743015289307, "global_step": 377371, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1953694820404053, "global_step": 377372, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0528881549835205, "global_step": 377373, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1104331016540527, "global_step": 377374, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.164039134979248, "global_step": 377375, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.071275472640991, "global_step": 377376, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1561176776885986, "global_step": 377377, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1192824840545654, "global_step": 377378, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1053264141082764, "global_step": 377379, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1576099395751953, "global_step": 377380, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1878654956817627, "global_step": 377381, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.078608512878418, "global_step": 377382, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.07430100440979, "global_step": 377383, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1237072944641113, "global_step": 377384, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0351133346557617, "global_step": 377385, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0929486751556396, "global_step": 377386, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1424574851989746, "global_step": 377387, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0778555870056152, "global_step": 377388, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1128287315368652, "global_step": 377389, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0733230113983154, "global_step": 377390, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1646642684936523, "global_step": 377391, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.13188099861145, "global_step": 377392, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.026709794998169, "global_step": 377393, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.2620553970336914, "global_step": 377394, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.105376720428467, "global_step": 377395, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.17746901512146, "global_step": 377396, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.11198353767395, "global_step": 377397, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1827502250671387, "global_step": 377398, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.125958204269409, "global_step": 377399, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0314559936523438, "global_step": 377400, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0919201374053955, "global_step": 377401, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.117709159851074, "global_step": 377402, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1592869758605957, "global_step": 377403, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0851147174835205, "global_step": 377404, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1700057983398438, "global_step": 377405, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1114389896392822, "global_step": 377406, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.107922077178955, "global_step": 377407, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1077585220336914, "global_step": 377408, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0348598957061768, "global_step": 377409, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.089163064956665, "global_step": 377410, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1518149375915527, "global_step": 377411, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.2429921627044678, "global_step": 377412, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.04113507270813, "global_step": 377413, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.082592487335205, "global_step": 377414, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0132477283477783, "global_step": 377415, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0330448150634766, "global_step": 377416, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0880422592163086, "global_step": 377417, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0987486839294434, "global_step": 377418, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.108522653579712, "global_step": 377419, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1216225624084473, "global_step": 377420, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.048396110534668, "global_step": 377421, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0848968029022217, "global_step": 377422, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0626657009124756, "global_step": 377423, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1267402172088623, "global_step": 377424, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.03391695022583, "global_step": 377425, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1181423664093018, "global_step": 377426, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0264875888824463, "global_step": 377427, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1401290893554688, "global_step": 377428, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1030404567718506, "global_step": 377429, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.149596929550171, "global_step": 377430, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.166515827178955, "global_step": 377431, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0239853858947754, "global_step": 377432, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0863938331604004, "global_step": 377433, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0773465633392334, "global_step": 377434, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0940890312194824, "global_step": 377435, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0338001251220703, "global_step": 377436, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0383074283599854, "global_step": 377437, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.128070831298828, "global_step": 377438, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.095017910003662, "global_step": 377439, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1525254249572754, "global_step": 377440, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0246565341949463, "global_step": 377441, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.081681728363037, "global_step": 377442, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0804243087768555, "global_step": 377443, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0322797298431396, "global_step": 377444, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0433878898620605, "global_step": 377445, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.07358455657959, "global_step": 377446, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.042297840118408, "global_step": 377447, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1354498863220215, "global_step": 377448, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.137631893157959, "global_step": 377449, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0618138313293457, "global_step": 377450, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0402345657348633, "global_step": 377451, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.179424285888672, "global_step": 377452, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0928146839141846, "global_step": 377453, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1872198581695557, "global_step": 377454, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.066417694091797, "global_step": 377455, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1504321098327637, "global_step": 377456, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1034793853759766, "global_step": 377457, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.079009771347046, "global_step": 377458, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.105173110961914, "global_step": 377459, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1212568283081055, "global_step": 377460, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1158108711242676, "global_step": 377461, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1584134101867676, "global_step": 377462, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.139634132385254, "global_step": 377463, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0989022254943848, "global_step": 377464, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.073208808898926, "global_step": 377465, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1141557693481445, "global_step": 377466, "epoch": 739, "lr": 5e-05}
{"train_loss": 1.9781007766723633, "global_step": 377467, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1306912899017334, "global_step": 377468, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.208195686340332, "global_step": 377469, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1121814250946045, "global_step": 377470, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1457157135009766, "global_step": 377471, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.132045269012451, "global_step": 377472, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0718326568603516, "global_step": 377473, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.089726686477661, "global_step": 377474, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0952415466308594, "global_step": 377475, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0698001384735107, "global_step": 377476, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1524264812469482, "global_step": 377477, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.069038152694702, "global_step": 377478, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0635011196136475, "global_step": 377479, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.083461046218872, "global_step": 377480, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1667640209198, "global_step": 377481, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0593128204345703, "global_step": 377482, "epoch": 739, "lr": 5e-05}
{"train_loss": 1.9470758438110352, "global_step": 377483, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1437082290649414, "global_step": 377484, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1015193462371826, "global_step": 377485, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0255112648010254, "global_step": 377486, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1799051761627197, "global_step": 377487, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1689887046813965, "global_step": 377488, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0336432456970215, "global_step": 377489, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.175413131713867, "global_step": 377490, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0758581161499023, "global_step": 377491, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.11954927444458, "global_step": 377492, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0883989334106445, "global_step": 377493, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.144601583480835, "global_step": 377494, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0367796421051025, "global_step": 377495, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1129069328308105, "global_step": 377496, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0933244228363037, "global_step": 377497, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1501877307891846, "global_step": 377498, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0906364917755127, "global_step": 377499, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0770022869110107, "global_step": 377500, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.068474292755127, "global_step": 377501, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1198487281799316, "global_step": 377502, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.076930522918701, "global_step": 377503, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.110140562057495, "global_step": 377504, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1584980487823486, "global_step": 377505, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.146221399307251, "global_step": 377506, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.171447992324829, "global_step": 377507, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1492886543273926, "global_step": 377508, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1051266193389893, "global_step": 377509, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1307694911956787, "global_step": 377510, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1761460304260254, "global_step": 377511, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0705349445343018, "global_step": 377512, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.170969247817993, "global_step": 377513, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.123056173324585, "global_step": 377514, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.068229913711548, "global_step": 377515, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.107985496520996, "global_step": 377516, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1538965702056885, "global_step": 377517, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.077205181121826, "global_step": 377518, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.128924608230591, "global_step": 377519, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0923781394958496, "global_step": 377520, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1020030975341797, "global_step": 377521, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.06204891204834, "global_step": 377522, "epoch": 739, "lr": 5e-05}
{"train_loss": 1.952924370765686, "global_step": 377523, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1865663528442383, "global_step": 377524, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.054260730743408, "global_step": 377525, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1649465560913086, "global_step": 377526, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1236867904663086, "global_step": 377527, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1521356105804443, "global_step": 377528, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0902421474456787, "global_step": 377529, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1563620567321777, "global_step": 377530, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.048548698425293, "global_step": 377531, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0365383625030518, "global_step": 377532, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.243422269821167, "global_step": 377533, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1397647857666016, "global_step": 377534, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.20324444770813, "global_step": 377535, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0161325931549072, "global_step": 377536, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0615756511688232, "global_step": 377537, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0717952251434326, "global_step": 377538, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1777777671813965, "global_step": 377539, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0943527221679688, "global_step": 377540, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.063983678817749, "global_step": 377541, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1142759323120117, "global_step": 377542, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0179126262664795, "global_step": 377543, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.099730968475342, "global_step": 377544, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.056015729904175, "global_step": 377545, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.2080817222595215, "global_step": 377546, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.115493059158325, "global_step": 377547, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.153203248977661, "global_step": 377548, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1833183765411377, "global_step": 377549, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.182845115661621, "global_step": 377550, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1120285987854004, "global_step": 377551, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.069944381713867, "global_step": 377552, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.11621356010437, "global_step": 377553, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0857648849487305, "global_step": 377554, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.2184274196624756, "global_step": 377555, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1488521099090576, "global_step": 377556, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.063344717025757, "global_step": 377557, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1254284381866455, "global_step": 377558, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.110901355743408, "global_step": 377559, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.2134058475494385, "global_step": 377560, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1603875160217285, "global_step": 377561, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0608904361724854, "global_step": 377562, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.123593807220459, "global_step": 377563, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1323118209838867, "global_step": 377564, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1475696563720703, "global_step": 377565, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.153013229370117, "global_step": 377566, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1400368213653564, "global_step": 377567, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0919013023376465, "global_step": 377568, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.168055534362793, "global_step": 377569, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1502957344055176, "global_step": 377570, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1314239501953125, "global_step": 377571, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0839006900787354, "global_step": 377572, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.148409366607666, "global_step": 377573, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.163435220718384, "global_step": 377574, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1094939708709717, "global_step": 377575, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.139435052871704, "global_step": 377576, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.099973678588867, "global_step": 377577, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.138554573059082, "global_step": 377578, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.14609956741333, "global_step": 377579, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.101036787033081, "global_step": 377580, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.023195505142212, "global_step": 377581, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.131378650665283, "global_step": 377582, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.067725658416748, "global_step": 377583, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1763558387756348, "global_step": 377584, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.094431161880493, "global_step": 377585, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1330857276916504, "global_step": 377586, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1492209434509277, "global_step": 377587, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.124854326248169, "global_step": 377588, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.187159299850464, "global_step": 377589, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1170244216918945, "global_step": 377590, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0484418869018555, "global_step": 377591, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0376334190368652, "global_step": 377592, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1081833839416504, "global_step": 377593, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1506292819976807, "global_step": 377594, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.064923048019409, "global_step": 377595, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.082777976989746, "global_step": 377596, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0148813724517822, "global_step": 377597, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0972273349761963, "global_step": 377598, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.202366828918457, "global_step": 377599, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1304750442504883, "global_step": 377600, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1357333660125732, "global_step": 377601, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.100102663040161, "global_step": 377602, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.089750051498413, "global_step": 377603, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1221354007720947, "global_step": 377604, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0911648273468018, "global_step": 377605, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.063905954360962, "global_step": 377606, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0799975395202637, "global_step": 377607, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.030569553375244, "global_step": 377608, "epoch": 739, "lr": 5e-05}
{"train_loss": 1.9915125370025635, "global_step": 377609, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1084938049316406, "global_step": 377610, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.081824779510498, "global_step": 377611, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0845978260040283, "global_step": 377612, "epoch": 739, "lr": 5e-05}
{"train_loss": 1.9839333295822144, "global_step": 377613, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1067700386047363, "global_step": 377614, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.098996877670288, "global_step": 377615, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.12907338142395, "global_step": 377616, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1258158683776855, "global_step": 377617, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1702208518981934, "global_step": 377618, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0273020267486572, "global_step": 377619, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.101402997970581, "global_step": 377620, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.097555160522461, "global_step": 377621, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.216461181640625, "global_step": 377622, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.129167318344116, "global_step": 377623, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.179072141647339, "global_step": 377624, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1478111743927, "global_step": 377625, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0575733184814453, "global_step": 377626, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1145782470703125, "global_step": 377627, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.161696672439575, "global_step": 377628, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.09324312210083, "global_step": 377629, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.17240047454834, "global_step": 377630, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1042027473449707, "global_step": 377631, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1307592391967773, "global_step": 377632, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1090524196624756, "global_step": 377633, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0939202308654785, "global_step": 377634, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0805225372314453, "global_step": 377635, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0019350051879883, "global_step": 377636, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.078420400619507, "global_step": 377637, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1440980434417725, "global_step": 377638, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1587066650390625, "global_step": 377639, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1213035583496094, "global_step": 377640, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0364630222320557, "global_step": 377641, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1482889652252197, "global_step": 377642, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0015618801116943, "global_step": 377643, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.047288656234741, "global_step": 377644, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.160804033279419, "global_step": 377645, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0712311267852783, "global_step": 377646, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.094052791595459, "global_step": 377647, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.134509563446045, "global_step": 377648, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.052943229675293, "global_step": 377649, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1467721462249756, "global_step": 377650, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.120652914047241, "global_step": 377651, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0590553283691406, "global_step": 377652, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.154884099960327, "global_step": 377653, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1082868576049805, "global_step": 377654, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.082028865814209, "global_step": 377655, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.11063551902771, "global_step": 377656, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.142775297164917, "global_step": 377657, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0656182765960693, "global_step": 377658, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1522300243377686, "global_step": 377659, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.18133544921875, "global_step": 377660, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.078160047531128, "global_step": 377661, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0745978355407715, "global_step": 377662, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0690529346466064, "global_step": 377663, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0354604721069336, "global_step": 377664, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.2475364208221436, "global_step": 377665, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.103853702545166, "global_step": 377666, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.028536081314087, "global_step": 377667, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1351099014282227, "global_step": 377668, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.083040714263916, "global_step": 377669, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.116021156311035, "global_step": 377670, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1825265884399414, "global_step": 377671, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0900046825408936, "global_step": 377672, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.178981304168701, "global_step": 377673, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0580344200134277, "global_step": 377674, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0612270832061768, "global_step": 377675, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1351921558380127, "global_step": 377676, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.133126974105835, "global_step": 377677, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1064813137054443, "global_step": 377678, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.154973030090332, "global_step": 377679, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0935614109039307, "global_step": 377680, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.022193193435669, "global_step": 377681, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1326797008514404, "global_step": 377682, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0960965156555176, "global_step": 377683, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.10990834236145, "global_step": 377684, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1106536388397217, "global_step": 377685, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0737040042877197, "global_step": 377686, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0478334426879883, "global_step": 377687, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.046701192855835, "global_step": 377688, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1282551288604736, "global_step": 377689, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0927250385284424, "global_step": 377690, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.094815969467163, "global_step": 377691, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.029949188232422, "global_step": 377692, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0399341583251953, "global_step": 377693, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1223104000091553, "global_step": 377694, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.110639810562134, "global_step": 377695, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.078500986099243, "global_step": 377696, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1773126125335693, "global_step": 377697, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1497342586517334, "global_step": 377698, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.096000909805298, "global_step": 377699, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0549471378326416, "global_step": 377700, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.083878517150879, "global_step": 377701, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.036384105682373, "global_step": 377702, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.079754114151001, "global_step": 377703, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.034928321838379, "global_step": 377704, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0695347785949707, "global_step": 377705, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0986053943634033, "global_step": 377706, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0633347034454346, "global_step": 377707, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1050338745117188, "global_step": 377708, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0264437198638916, "global_step": 377709, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1800899505615234, "global_step": 377710, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.072817802429199, "global_step": 377711, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1310198307037354, "global_step": 377712, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0528903007507324, "global_step": 377713, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.07539701461792, "global_step": 377714, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0956344604492188, "global_step": 377715, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.055760145187378, "global_step": 377716, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.13210129737854, "global_step": 377717, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1103386878967285, "global_step": 377718, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.133840322494507, "global_step": 377719, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0985186100006104, "global_step": 377720, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.014270544052124, "global_step": 377721, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.088050603866577, "global_step": 377722, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.060316801071167, "global_step": 377723, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.074315309524536, "global_step": 377724, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1047537326812744, "global_step": 377725, "epoch": 739, "lr": 5e-05}
{"train_loss": 1.9958422183990479, "global_step": 377726, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0220675468444824, "global_step": 377727, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0830271244049072, "global_step": 377728, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.070828437805176, "global_step": 377729, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.116873264312744, "global_step": 377730, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1652183532714844, "global_step": 377731, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0858144760131836, "global_step": 377732, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.126675844192505, "global_step": 377733, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1005442142486572, "global_step": 377734, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1175317764282227, "global_step": 377735, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1709563732147217, "global_step": 377736, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0932631492614746, "global_step": 377737, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1149184703826904, "global_step": 377738, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0745394229888916, "global_step": 377739, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.12770938873291, "global_step": 377740, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.114072561264038, "global_step": 377741, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.045724391937256, "global_step": 377742, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.134523868560791, "global_step": 377743, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.06095814704895, "global_step": 377744, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.2278494834899902, "global_step": 377745, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.077928066253662, "global_step": 377746, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1431994438171387, "global_step": 377747, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0934460163116455, "global_step": 377748, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.141479253768921, "global_step": 377749, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1483187675476074, "global_step": 377750, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.000816583633423, "global_step": 377751, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.185307741165161, "global_step": 377752, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1268081665039062, "global_step": 377753, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.075627326965332, "global_step": 377754, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1117939949035645, "global_step": 377755, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0465776920318604, "global_step": 377756, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.105679988861084, "global_step": 377757, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.033602237701416, "global_step": 377758, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.138559103012085, "global_step": 377759, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0254247188568115, "global_step": 377760, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1335809230804443, "global_step": 377761, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1690828800201416, "global_step": 377762, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.080357313156128, "global_step": 377763, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1420552730560303, "global_step": 377764, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1520190238952637, "global_step": 377765, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0785789489746094, "global_step": 377766, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.186048746109009, "global_step": 377767, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1543080806732178, "global_step": 377768, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1017346382141113, "global_step": 377769, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.139965295791626, "global_step": 377770, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0666439533233643, "global_step": 377771, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.135744571685791, "global_step": 377772, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0502851009368896, "global_step": 377773, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1003618240356445, "global_step": 377774, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.142115831375122, "global_step": 377775, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1109325885772705, "global_step": 377776, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.119028091430664, "global_step": 377777, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.078795909881592, "global_step": 377778, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0819454193115234, "global_step": 377779, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0933194160461426, "global_step": 377780, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.124882221221924, "global_step": 377781, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0224294662475586, "global_step": 377782, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0511398315429688, "global_step": 377783, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1657209396362305, "global_step": 377784, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.071913957595825, "global_step": 377785, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.18617582321167, "global_step": 377786, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1611168384552, "global_step": 377787, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0301766395568848, "global_step": 377788, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.121286153793335, "global_step": 377789, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1028499603271484, "global_step": 377790, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.056778907775879, "global_step": 377791, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.090460777282715, "global_step": 377792, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0952112674713135, "global_step": 377793, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0676722526550293, "global_step": 377794, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1479225158691406, "global_step": 377795, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0999691486358643, "global_step": 377796, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1748976707458496, "global_step": 377797, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0679304599761963, "global_step": 377798, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.07486891746521, "global_step": 377799, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0722391605377197, "global_step": 377800, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0560836791992188, "global_step": 377801, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.099260091781616, "global_step": 377802, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.101167917251587, "global_step": 377803, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1197023391723633, "global_step": 377804, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.070996046066284, "global_step": 377805, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1173086166381836, "global_step": 377806, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0650789737701416, "global_step": 377807, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1255710124969482, "global_step": 377808, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0739471912384033, "global_step": 377809, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.124518394470215, "global_step": 377810, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.122237205505371, "global_step": 377811, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.118997812271118, "global_step": 377812, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1346476078033447, "global_step": 377813, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.022578001022339, "global_step": 377814, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.074634075164795, "global_step": 377815, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0636777877807617, "global_step": 377816, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.045370578765869, "global_step": 377817, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.039583921432495, "global_step": 377818, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.101508378982544, "global_step": 377819, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.077277660369873, "global_step": 377820, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0362420082092285, "global_step": 377821, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.106584310531616, "global_step": 377822, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.099327325820923, "global_step": 377823, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.136681079864502, "global_step": 377824, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1095693111419678, "global_step": 377825, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1614491939544678, "global_step": 377826, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.107203960418701, "global_step": 377827, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.084151268005371, "global_step": 377828, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.068359136581421, "global_step": 377829, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.139350652694702, "global_step": 377830, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.178152084350586, "global_step": 377831, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1239991188049316, "global_step": 377832, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1714422702789307, "global_step": 377833, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1124541759490967, "global_step": 377834, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1291370391845703, "global_step": 377835, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0665955543518066, "global_step": 377836, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0809969902038574, "global_step": 377837, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0866148471832275, "global_step": 377838, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1444661617279053, "global_step": 377839, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.06746506690979, "global_step": 377840, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1341543197631836, "global_step": 377841, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.101882219314575, "global_step": 377842, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0902292728424072, "global_step": 377843, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0846304893493652, "global_step": 377844, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.096097230911255, "global_step": 377845, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.061931848526001, "global_step": 377846, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1967945098876953, "global_step": 377847, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.088848829269409, "global_step": 377848, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1243674755096436, "global_step": 377849, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1045982837677, "global_step": 377850, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1176836490631104, "global_step": 377851, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0447428226470947, "global_step": 377852, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1564667224884033, "global_step": 377853, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0470693111419678, "global_step": 377854, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1655502319335938, "global_step": 377855, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.002887487411499, "global_step": 377856, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0937116146087646, "global_step": 377857, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1101784706115723, "global_step": 377858, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.062744379043579, "global_step": 377859, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1520183086395264, "global_step": 377860, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.184007167816162, "global_step": 377861, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1196794509887695, "global_step": 377862, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.162003755569458, "global_step": 377863, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1107594966888428, "global_step": 377864, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.077207326889038, "global_step": 377865, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.114743232727051, "global_step": 377866, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1154520511627197, "global_step": 377867, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1082112789154053, "global_step": 377868, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.206359624862671, "global_step": 377869, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.192107915878296, "global_step": 377870, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1647067070007324, "global_step": 377871, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.037583112716675, "global_step": 377872, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.181136131286621, "global_step": 377873, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.156226634979248, "global_step": 377874, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0972299575805664, "global_step": 377875, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1162681579589844, "global_step": 377876, "epoch": 739, "lr": 5e-05}
{"train_loss": 1.9581313133239746, "global_step": 377877, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.113642692565918, "global_step": 377878, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.120117664337158, "global_step": 377879, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0943222045898438, "global_step": 377880, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.101330041885376, "global_step": 377881, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.112658977508545, "global_step": 377882, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0928993225097656, "global_step": 377883, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1200857162475586, "global_step": 377884, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1165847778320312, "global_step": 377885, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.2256269454956055, "global_step": 377886, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1166744232177734, "global_step": 377887, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0369956493377686, "global_step": 377888, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.080049514770508, "global_step": 377889, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0327436923980713, "global_step": 377890, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.057860851287842, "global_step": 377891, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.068565845489502, "global_step": 377892, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0778043270111084, "global_step": 377893, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1650819778442383, "global_step": 377894, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.134807586669922, "global_step": 377895, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1255123615264893, "global_step": 377896, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.016270160675049, "global_step": 377897, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0573647022247314, "global_step": 377898, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1160471439361572, "global_step": 377899, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.164450168609619, "global_step": 377900, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.055405378341675, "global_step": 377901, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0615901947021484, "global_step": 377902, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1645681858062744, "global_step": 377903, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.137925863265991, "global_step": 377904, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0813589096069336, "global_step": 377905, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0675013065338135, "global_step": 377906, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1290862560272217, "global_step": 377907, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0823254585266113, "global_step": 377908, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1917147636413574, "global_step": 377909, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0452346801757812, "global_step": 377910, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1575539112091064, "global_step": 377911, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.131836175918579, "global_step": 377912, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.073258638381958, "global_step": 377913, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1042304039001465, "global_step": 377914, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.053238868713379, "global_step": 377915, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.164116382598877, "global_step": 377916, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.143961191177368, "global_step": 377917, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1190412044525146, "global_step": 377918, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0871059894561768, "global_step": 377919, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1110684871673584, "global_step": 377920, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1190741062164307, "global_step": 377921, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.117811918258667, "global_step": 377922, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.071134090423584, "global_step": 377923, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.106539487838745, "global_step": 377924, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0886547565460205, "global_step": 377925, "epoch": 739, "lr": 5e-05}
{"train_loss": 1.9922969341278076, "global_step": 377926, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1140170097351074, "global_step": 377927, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0788114070892334, "global_step": 377928, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.104403257369995, "global_step": 377929, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.040539503097534, "global_step": 377930, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.2088160514831543, "global_step": 377931, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0959532260894775, "global_step": 377932, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1638317108154297, "global_step": 377933, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.141632080078125, "global_step": 377934, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1627213954925537, "global_step": 377935, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0363056659698486, "global_step": 377936, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.180877685546875, "global_step": 377937, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1270461082458496, "global_step": 377938, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0984203815460205, "global_step": 377939, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1648781299591064, "global_step": 377940, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.077143907546997, "global_step": 377941, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0911154747009277, "global_step": 377942, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0312161445617676, "global_step": 377943, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.110801935195923, "global_step": 377944, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.060619592666626, "global_step": 377945, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.231671094894409, "global_step": 377946, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.085360050201416, "global_step": 377947, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1038596630096436, "global_step": 377948, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0930488109588623, "global_step": 377949, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.089264392852783, "global_step": 377950, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1998767852783203, "global_step": 377951, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.130314350128174, "global_step": 377952, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0273232460021973, "global_step": 377953, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.088240623474121, "global_step": 377954, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.108785629272461, "global_step": 377955, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1998815536499023, "global_step": 377956, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0870048999786377, "global_step": 377957, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.145603656768799, "global_step": 377958, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1177096366882324, "global_step": 377959, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.070739507675171, "global_step": 377960, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.14570689201355, "global_step": 377961, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.126474142074585, "global_step": 377962, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1431045532226562, "global_step": 377963, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.056858777999878, "global_step": 377964, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.139432907104492, "global_step": 377965, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.061279535293579, "global_step": 377966, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.102116107940674, "global_step": 377967, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.061710834503174, "global_step": 377968, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1601779460906982, "global_step": 377969, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0534653663635254, "global_step": 377970, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1893043518066406, "global_step": 377971, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1328537464141846, "global_step": 377972, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0930752754211426, "global_step": 377973, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0194108486175537, "global_step": 377974, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0520551204681396, "global_step": 377975, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1744089126586914, "global_step": 377976, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.049945116043091, "global_step": 377977, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.14971923828125, "global_step": 377978, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.129628896713257, "global_step": 377979, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.117213487625122, "global_step": 377980, "epoch": 739, "lr": 5e-05}
{"train_loss": 1.9801344871520996, "global_step": 377981, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1376771926879883, "global_step": 377982, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.142174005508423, "global_step": 377983, "epoch": 739, "lr": 5e-05}
{"train_loss": 1.9863381385803223, "global_step": 377984, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1419856548309326, "global_step": 377985, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.108721971511841, "global_step": 377986, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0302681922912598, "global_step": 377987, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.2009997367858887, "global_step": 377988, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0970287322998047, "global_step": 377989, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.146928548812866, "global_step": 377990, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.126511335372925, "global_step": 377991, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.12601900100708, "global_step": 377992, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1518406867980957, "global_step": 377993, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0832507610321045, "global_step": 377994, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1007144451141357, "global_step": 377995, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1108450889587402, "global_step": 377996, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0606977939605713, "global_step": 377997, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.109187364578247, "global_step": 377998, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0236775875091553, "global_step": 377999, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1434943675994873, "global_step": 378000, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.127986431121826, "global_step": 378001, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.2361886501312256, "global_step": 378002, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.158463954925537, "global_step": 378003, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1375882625579834, "global_step": 378004, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0690431594848633, "global_step": 378005, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.120412588119507, "global_step": 378006, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0115134716033936, "global_step": 378007, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0819573402404785, "global_step": 378008, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0328149795532227, "global_step": 378009, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.2351582050323486, "global_step": 378010, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0946638584136963, "global_step": 378011, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0188848972320557, "global_step": 378012, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0882108211517334, "global_step": 378013, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1241776943206787, "global_step": 378014, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0649571418762207, "global_step": 378015, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1228673458099365, "global_step": 378016, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0727944374084473, "global_step": 378017, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.180262565612793, "global_step": 378018, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1072676181793213, "global_step": 378019, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1246533393859863, "global_step": 378020, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0772387981414795, "global_step": 378021, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1063449382781982, "global_step": 378022, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.088641881942749, "global_step": 378023, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.2174112796783447, "global_step": 378024, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.141711711883545, "global_step": 378025, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0592856407165527, "global_step": 378026, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.089364767074585, "global_step": 378027, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.110456705093384, "global_step": 378028, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.073631525039673, "global_step": 378029, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.114490270614624, "global_step": 378030, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.076141834259033, "global_step": 378031, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1379504203796387, "global_step": 378032, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.118196725845337, "global_step": 378033, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.03930401802063, "global_step": 378034, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.140815496444702, "global_step": 378035, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.086641788482666, "global_step": 378036, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1164653301239014, "global_step": 378037, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.158646821975708, "global_step": 378038, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0749423503875732, "global_step": 378039, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.137167453765869, "global_step": 378040, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.145336389541626, "global_step": 378041, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.1037533283233643, "global_step": 378042, "epoch": 739, "lr": 5e-05}
{"train_loss": 2.0755388736724854, "global_step": 378043, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1281111240386963, "global_step": 378044, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1006624698638916, "global_step": 378045, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.112436532974243, "global_step": 378046, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0270986557006836, "global_step": 378047, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0685150623321533, "global_step": 378048, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1359052658081055, "global_step": 378049, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0895702838897705, "global_step": 378050, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.12583327293396, "global_step": 378051, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.133802890777588, "global_step": 378052, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0786616802215576, "global_step": 378053, "epoch": 740, "lr": 5e-05}
{"train_loss": 1.9931031465530396, "global_step": 378054, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.072558879852295, "global_step": 378055, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0842092037200928, "global_step": 378056, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.2013206481933594, "global_step": 378057, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.126035451889038, "global_step": 378058, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0150909423828125, "global_step": 378059, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.177264451980591, "global_step": 378060, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1170740127563477, "global_step": 378061, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.138504981994629, "global_step": 378062, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0489466190338135, "global_step": 378063, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.036167860031128, "global_step": 378064, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.093362808227539, "global_step": 378065, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1198883056640625, "global_step": 378066, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0669124126434326, "global_step": 378067, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0986669063568115, "global_step": 378068, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0788815021514893, "global_step": 378069, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.123596668243408, "global_step": 378070, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1323461532592773, "global_step": 378071, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0901660919189453, "global_step": 378072, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.141920566558838, "global_step": 378073, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.00981068611145, "global_step": 378074, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.082838773727417, "global_step": 378075, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.00961971282959, "global_step": 378076, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0437049865722656, "global_step": 378077, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.165229558944702, "global_step": 378078, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0202884674072266, "global_step": 378079, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0868804454803467, "global_step": 378080, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.132600784301758, "global_step": 378081, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1566359996795654, "global_step": 378082, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0638749599456787, "global_step": 378083, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.094017267227173, "global_step": 378084, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.063631534576416, "global_step": 378085, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0537054538726807, "global_step": 378086, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1147332191467285, "global_step": 378087, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1288504600524902, "global_step": 378088, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1561834812164307, "global_step": 378089, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1907012462615967, "global_step": 378090, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0649945735931396, "global_step": 378091, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0871422290802, "global_step": 378092, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.102046489715576, "global_step": 378093, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1478238105773926, "global_step": 378094, "epoch": 740, "lr": 5e-05}
{"train_loss": 1.9994540214538574, "global_step": 378095, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.144552230834961, "global_step": 378096, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.147401809692383, "global_step": 378097, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1471803188323975, "global_step": 378098, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1923067569732666, "global_step": 378099, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.040400981903076, "global_step": 378100, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.178365707397461, "global_step": 378101, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.164303779602051, "global_step": 378102, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.119882106781006, "global_step": 378103, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.124934196472168, "global_step": 378104, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.024251699447632, "global_step": 378105, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0555055141448975, "global_step": 378106, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1224560737609863, "global_step": 378107, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.103013515472412, "global_step": 378108, "epoch": 740, "lr": 5e-05}
{"train_loss": 1.9890536069869995, "global_step": 378109, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.164191961288452, "global_step": 378110, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0592334270477295, "global_step": 378111, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.103707790374756, "global_step": 378112, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1234588623046875, "global_step": 378113, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1311898231506348, "global_step": 378114, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0206046104431152, "global_step": 378115, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.225015163421631, "global_step": 378116, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0727744102478027, "global_step": 378117, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0371546745300293, "global_step": 378118, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0479588508605957, "global_step": 378119, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1261634826660156, "global_step": 378120, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.112651824951172, "global_step": 378121, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.025273084640503, "global_step": 378122, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1435647010803223, "global_step": 378123, "epoch": 740, "lr": 5e-05}
{"train_loss": 1.9929907321929932, "global_step": 378124, "epoch": 740, "lr": 5e-05}
{"train_loss": 1.9835124015808105, "global_step": 378125, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.078321933746338, "global_step": 378126, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.129415988922119, "global_step": 378127, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0677261352539062, "global_step": 378128, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0920770168304443, "global_step": 378129, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.106069803237915, "global_step": 378130, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0513596534729004, "global_step": 378131, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0642876625061035, "global_step": 378132, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1162309646606445, "global_step": 378133, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0564701557159424, "global_step": 378134, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.069544553756714, "global_step": 378135, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.087799310684204, "global_step": 378136, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.075322389602661, "global_step": 378137, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.174489736557007, "global_step": 378138, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0470259189605713, "global_step": 378139, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.2144081592559814, "global_step": 378140, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1655826568603516, "global_step": 378141, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0986809730529785, "global_step": 378142, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.132439613342285, "global_step": 378143, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0926787853240967, "global_step": 378144, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1302359104156494, "global_step": 378145, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0882174968719482, "global_step": 378146, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.083683490753174, "global_step": 378147, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1582109928131104, "global_step": 378148, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1660141944885254, "global_step": 378149, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0395150184631348, "global_step": 378150, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.032198190689087, "global_step": 378151, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.151566505432129, "global_step": 378152, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1449520587921143, "global_step": 378153, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.054297685623169, "global_step": 378154, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1331207752227783, "global_step": 378155, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.2537286281585693, "global_step": 378156, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.124509334564209, "global_step": 378157, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.083406448364258, "global_step": 378158, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.058173418045044, "global_step": 378159, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1067168712615967, "global_step": 378160, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.021718978881836, "global_step": 378161, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0294439792633057, "global_step": 378162, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1006178855895996, "global_step": 378163, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1233606338500977, "global_step": 378164, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0482757091522217, "global_step": 378165, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0326292514801025, "global_step": 378166, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0510072708129883, "global_step": 378167, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1139352321624756, "global_step": 378168, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1823127269744873, "global_step": 378169, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0385501384735107, "global_step": 378170, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.10823130607605, "global_step": 378171, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0928707122802734, "global_step": 378172, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.083780527114868, "global_step": 378173, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.013028383255005, "global_step": 378174, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.098568916320801, "global_step": 378175, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1273980140686035, "global_step": 378176, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1469249725341797, "global_step": 378177, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.117037296295166, "global_step": 378178, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0931761264801025, "global_step": 378179, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1579673290252686, "global_step": 378180, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1379055976867676, "global_step": 378181, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.127943754196167, "global_step": 378182, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1463441848754883, "global_step": 378183, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1531319618225098, "global_step": 378184, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1557087898254395, "global_step": 378185, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0613222122192383, "global_step": 378186, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.04024600982666, "global_step": 378187, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0872042179107666, "global_step": 378188, "epoch": 740, "lr": 5e-05}
{"train_loss": 1.971274733543396, "global_step": 378189, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0929300785064697, "global_step": 378190, "epoch": 740, "lr": 5e-05}
{"train_loss": 1.9941083192825317, "global_step": 378191, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0486109256744385, "global_step": 378192, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0983622074127197, "global_step": 378193, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.081982374191284, "global_step": 378194, "epoch": 740, "lr": 5e-05}
{"train_loss": 1.9909757375717163, "global_step": 378195, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.096560001373291, "global_step": 378196, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1110739707946777, "global_step": 378197, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1322295665740967, "global_step": 378198, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1047956943511963, "global_step": 378199, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.213270664215088, "global_step": 378200, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0835611820220947, "global_step": 378201, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1227850914001465, "global_step": 378202, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1493356227874756, "global_step": 378203, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.138627290725708, "global_step": 378204, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0301215648651123, "global_step": 378205, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.131035089492798, "global_step": 378206, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.08276104927063, "global_step": 378207, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1385719776153564, "global_step": 378208, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1832363605499268, "global_step": 378209, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1139323711395264, "global_step": 378210, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.022010564804077, "global_step": 378211, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.061171054840088, "global_step": 378212, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0532679557800293, "global_step": 378213, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.104689359664917, "global_step": 378214, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1817917823791504, "global_step": 378215, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0411505699157715, "global_step": 378216, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.128600597381592, "global_step": 378217, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0569119453430176, "global_step": 378218, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0730347633361816, "global_step": 378219, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0627641677856445, "global_step": 378220, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1834475994110107, "global_step": 378221, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0900163650512695, "global_step": 378222, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0779385566711426, "global_step": 378223, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.03912615776062, "global_step": 378224, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0887928009033203, "global_step": 378225, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1179354190826416, "global_step": 378226, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.136930465698242, "global_step": 378227, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.077805280685425, "global_step": 378228, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.112461805343628, "global_step": 378229, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.19504976272583, "global_step": 378230, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.049731492996216, "global_step": 378231, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0785775184631348, "global_step": 378232, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.054652452468872, "global_step": 378233, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.110213041305542, "global_step": 378234, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0911574363708496, "global_step": 378235, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0857200622558594, "global_step": 378236, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1866912841796875, "global_step": 378237, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1273694038391113, "global_step": 378238, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.04714035987854, "global_step": 378239, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1749186515808105, "global_step": 378240, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1167967319488525, "global_step": 378241, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1209540367126465, "global_step": 378242, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.163130521774292, "global_step": 378243, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1392874717712402, "global_step": 378244, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.136669635772705, "global_step": 378245, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1018548011779785, "global_step": 378246, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.13919997215271, "global_step": 378247, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1183857917785645, "global_step": 378248, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1289024353027344, "global_step": 378249, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0221714973449707, "global_step": 378250, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0450689792633057, "global_step": 378251, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0864784717559814, "global_step": 378252, "epoch": 740, "lr": 5e-05}
{"train_loss": 1.9984550476074219, "global_step": 378253, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1669979095458984, "global_step": 378254, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0599303245544434, "global_step": 378255, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.110189437866211, "global_step": 378256, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.142524003982544, "global_step": 378257, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1151700019836426, "global_step": 378258, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.219370126724243, "global_step": 378259, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.15647292137146, "global_step": 378260, "epoch": 740, "lr": 5e-05}
{"train_loss": 1.9979493618011475, "global_step": 378261, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.085876941680908, "global_step": 378262, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.122858762741089, "global_step": 378263, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0673482418060303, "global_step": 378264, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0105700492858887, "global_step": 378265, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.139983892440796, "global_step": 378266, "epoch": 740, "lr": 5e-05}
{"train_loss": 1.9767519235610962, "global_step": 378267, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0964608192443848, "global_step": 378268, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0748181343078613, "global_step": 378269, "epoch": 740, "lr": 5e-05}
{"train_loss": 1.9959667921066284, "global_step": 378270, "epoch": 740, "lr": 5e-05}
{"train_loss": 1.9967122077941895, "global_step": 378271, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.029592275619507, "global_step": 378272, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1013541221618652, "global_step": 378273, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.097294330596924, "global_step": 378274, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0659406185150146, "global_step": 378275, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0661094188690186, "global_step": 378276, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1363000869750977, "global_step": 378277, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0716514587402344, "global_step": 378278, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.073167324066162, "global_step": 378279, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0844414234161377, "global_step": 378280, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.005101442337036, "global_step": 378281, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1731622219085693, "global_step": 378282, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0711259841918945, "global_step": 378283, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.076124668121338, "global_step": 378284, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.096031427383423, "global_step": 378285, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1363525390625, "global_step": 378286, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.049996852874756, "global_step": 378287, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.07724666595459, "global_step": 378288, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.032349109649658, "global_step": 378289, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1278157234191895, "global_step": 378290, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.075319766998291, "global_step": 378291, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0749571323394775, "global_step": 378292, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.220919609069824, "global_step": 378293, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.10101318359375, "global_step": 378294, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.193695545196533, "global_step": 378295, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.201165199279785, "global_step": 378296, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0469608306884766, "global_step": 378297, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1371195316314697, "global_step": 378298, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.147279739379883, "global_step": 378299, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.136596202850342, "global_step": 378300, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0581002235412598, "global_step": 378301, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.07245135307312, "global_step": 378302, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.141968250274658, "global_step": 378303, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1246848106384277, "global_step": 378304, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.155060052871704, "global_step": 378305, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0430901050567627, "global_step": 378306, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1052331924438477, "global_step": 378307, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1011385917663574, "global_step": 378308, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.141709566116333, "global_step": 378309, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.171048402786255, "global_step": 378310, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0621609687805176, "global_step": 378311, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.044276475906372, "global_step": 378312, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0635528564453125, "global_step": 378313, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.070786237716675, "global_step": 378314, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1242899894714355, "global_step": 378315, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0798139572143555, "global_step": 378316, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1047632694244385, "global_step": 378317, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1937479972839355, "global_step": 378318, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0802712440490723, "global_step": 378319, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.13826847076416, "global_step": 378320, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.069979190826416, "global_step": 378321, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0246598720550537, "global_step": 378322, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.11446475982666, "global_step": 378323, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1442832946777344, "global_step": 378324, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1089112758636475, "global_step": 378325, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.052020311355591, "global_step": 378326, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1649458408355713, "global_step": 378327, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1339120864868164, "global_step": 378328, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.088869333267212, "global_step": 378329, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.2015929222106934, "global_step": 378330, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0936696529388428, "global_step": 378331, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0980474948883057, "global_step": 378332, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.031317949295044, "global_step": 378333, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.110718011856079, "global_step": 378334, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.109278440475464, "global_step": 378335, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.142599582672119, "global_step": 378336, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1283109188079834, "global_step": 378337, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1022963523864746, "global_step": 378338, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1294243335723877, "global_step": 378339, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.027520179748535, "global_step": 378340, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0524635314941406, "global_step": 378341, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0741727352142334, "global_step": 378342, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0922346115112305, "global_step": 378343, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.049630880355835, "global_step": 378344, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0762269496917725, "global_step": 378345, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.110208034515381, "global_step": 378346, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.089047908782959, "global_step": 378347, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.098879814147949, "global_step": 378348, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.100877046585083, "global_step": 378349, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0886619091033936, "global_step": 378350, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.111945629119873, "global_step": 378351, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0819666385650635, "global_step": 378352, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.144214630126953, "global_step": 378353, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0831081867218018, "global_step": 378354, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0026228427886963, "global_step": 378355, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.099963426589966, "global_step": 378356, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0743441581726074, "global_step": 378357, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.126121997833252, "global_step": 378358, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.115466833114624, "global_step": 378359, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0427727699279785, "global_step": 378360, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.138648509979248, "global_step": 378361, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1285247802734375, "global_step": 378362, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1275389194488525, "global_step": 378363, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0928542613983154, "global_step": 378364, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1478822231292725, "global_step": 378365, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1234142780303955, "global_step": 378366, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.122898578643799, "global_step": 378367, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0594403743743896, "global_step": 378368, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1307873725891113, "global_step": 378369, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0524420738220215, "global_step": 378370, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1379036903381348, "global_step": 378371, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0998191833496094, "global_step": 378372, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0604381561279297, "global_step": 378373, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.116185426712036, "global_step": 378374, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.109407663345337, "global_step": 378375, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0481317043304443, "global_step": 378376, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1320669651031494, "global_step": 378377, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1767406463623047, "global_step": 378378, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0644125938415527, "global_step": 378379, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1650993824005127, "global_step": 378380, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0470941066741943, "global_step": 378381, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.054833173751831, "global_step": 378382, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.002605676651001, "global_step": 378383, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.11492657661438, "global_step": 378384, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0395331382751465, "global_step": 378385, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0867583751678467, "global_step": 378386, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0653374195098877, "global_step": 378387, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.2442328929901123, "global_step": 378388, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.169868230819702, "global_step": 378389, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.055009126663208, "global_step": 378390, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.23576021194458, "global_step": 378391, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.122127056121826, "global_step": 378392, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0281529426574707, "global_step": 378393, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.06644344329834, "global_step": 378394, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.017514705657959, "global_step": 378395, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.194056987762451, "global_step": 378396, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.155665397644043, "global_step": 378397, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1090643405914307, "global_step": 378398, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0082590579986572, "global_step": 378399, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1371569633483887, "global_step": 378400, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0726382732391357, "global_step": 378401, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.066641330718994, "global_step": 378402, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.126162052154541, "global_step": 378403, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0750508308410645, "global_step": 378404, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.138002395629883, "global_step": 378405, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.162820339202881, "global_step": 378406, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.046696186065674, "global_step": 378407, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.135289192199707, "global_step": 378408, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0660767555236816, "global_step": 378409, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1144330501556396, "global_step": 378410, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.063608169555664, "global_step": 378411, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.187392234802246, "global_step": 378412, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0995187759399414, "global_step": 378413, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1312155723571777, "global_step": 378414, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.2020480632781982, "global_step": 378415, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1052017211914062, "global_step": 378416, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.136573553085327, "global_step": 378417, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.105071544647217, "global_step": 378418, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1689951419830322, "global_step": 378419, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.066408395767212, "global_step": 378420, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0981051921844482, "global_step": 378421, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1993353366851807, "global_step": 378422, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.192495822906494, "global_step": 378423, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.165569543838501, "global_step": 378424, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.125600814819336, "global_step": 378425, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.103116512298584, "global_step": 378426, "epoch": 740, "lr": 5e-05}
{"train_loss": 1.9891849756240845, "global_step": 378427, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0667917728424072, "global_step": 378428, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.104914903640747, "global_step": 378429, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.052212715148926, "global_step": 378430, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1209757328033447, "global_step": 378431, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.115511894226074, "global_step": 378432, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0423169136047363, "global_step": 378433, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1597323417663574, "global_step": 378434, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1226110458374023, "global_step": 378435, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.12347149848938, "global_step": 378436, "epoch": 740, "lr": 5e-05}
{"train_loss": 1.9905961751937866, "global_step": 378437, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.083115577697754, "global_step": 378438, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1066627502441406, "global_step": 378439, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.2054500579833984, "global_step": 378440, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0236170291900635, "global_step": 378441, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1763052940368652, "global_step": 378442, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0825586318969727, "global_step": 378443, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.04365873336792, "global_step": 378444, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.10380220413208, "global_step": 378445, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0945234298706055, "global_step": 378446, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.143615484237671, "global_step": 378447, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.043844699859619, "global_step": 378448, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1198527812957764, "global_step": 378449, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1420376300811768, "global_step": 378450, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.119412899017334, "global_step": 378451, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0794105529785156, "global_step": 378452, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1000523567199707, "global_step": 378453, "epoch": 740, "lr": 5e-05}
{"train_loss": 1.9534170627593994, "global_step": 378454, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.078904628753662, "global_step": 378455, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.145676612854004, "global_step": 378456, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1401591300964355, "global_step": 378457, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1250414848327637, "global_step": 378458, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1180684566497803, "global_step": 378459, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.210491180419922, "global_step": 378460, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0493152141571045, "global_step": 378461, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.073896884918213, "global_step": 378462, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0953567028045654, "global_step": 378463, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.049879789352417, "global_step": 378464, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0814812183380127, "global_step": 378465, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.134253740310669, "global_step": 378466, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.082010269165039, "global_step": 378467, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1488120555877686, "global_step": 378468, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1615161895751953, "global_step": 378469, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0777833461761475, "global_step": 378470, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1834261417388916, "global_step": 378471, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.159846544265747, "global_step": 378472, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.109539747238159, "global_step": 378473, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1336793899536133, "global_step": 378474, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.090974807739258, "global_step": 378475, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0823099613189697, "global_step": 378476, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0301382541656494, "global_step": 378477, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0420539379119873, "global_step": 378478, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1293845176696777, "global_step": 378479, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.113650321960449, "global_step": 378480, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.078691005706787, "global_step": 378481, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1404221057891846, "global_step": 378482, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1019093990325928, "global_step": 378483, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1326546669006348, "global_step": 378484, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.106384754180908, "global_step": 378485, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1426305770874023, "global_step": 378486, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.179131031036377, "global_step": 378487, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0644640922546387, "global_step": 378488, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1511552333831787, "global_step": 378489, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1342883110046387, "global_step": 378490, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.069248676300049, "global_step": 378491, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1178131103515625, "global_step": 378492, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.123248338699341, "global_step": 378493, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0881316661834717, "global_step": 378494, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0686542987823486, "global_step": 378495, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0883007049560547, "global_step": 378496, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1124579906463623, "global_step": 378497, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1261167526245117, "global_step": 378498, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0431060791015625, "global_step": 378499, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1791720390319824, "global_step": 378500, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0393426418304443, "global_step": 378501, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.114132881164551, "global_step": 378502, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0518410205841064, "global_step": 378503, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.160656452178955, "global_step": 378504, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.136321783065796, "global_step": 378505, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0941293239593506, "global_step": 378506, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0377655029296875, "global_step": 378507, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.099156618118286, "global_step": 378508, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1990549564361572, "global_step": 378509, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0135269165039062, "global_step": 378510, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1127495765686035, "global_step": 378511, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.081390857696533, "global_step": 378512, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0889716148376465, "global_step": 378513, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1556546688079834, "global_step": 378514, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.137985944747925, "global_step": 378515, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.027132511138916, "global_step": 378516, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1301729679107666, "global_step": 378517, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.196199893951416, "global_step": 378518, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0640196800231934, "global_step": 378519, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.14493727684021, "global_step": 378520, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0592141151428223, "global_step": 378521, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1958818435668945, "global_step": 378522, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0860676765441895, "global_step": 378523, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.124521493911743, "global_step": 378524, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.082406759262085, "global_step": 378525, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1962485313415527, "global_step": 378526, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1151394844055176, "global_step": 378527, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1973612308502197, "global_step": 378528, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.150627613067627, "global_step": 378529, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.153569459915161, "global_step": 378530, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.11427903175354, "global_step": 378531, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.095339775085449, "global_step": 378532, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1280078887939453, "global_step": 378533, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.09751033782959, "global_step": 378534, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1333935260772705, "global_step": 378535, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1407551765441895, "global_step": 378536, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1774868965148926, "global_step": 378537, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.062274217605591, "global_step": 378538, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0915915966033936, "global_step": 378539, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.056022882461548, "global_step": 378540, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0275347232818604, "global_step": 378541, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0998458862304688, "global_step": 378542, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0782229900360107, "global_step": 378543, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.041574239730835, "global_step": 378544, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1256279945373535, "global_step": 378545, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.152277708053589, "global_step": 378546, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0647714138031006, "global_step": 378547, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1113786697387695, "global_step": 378548, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.108328104019165, "global_step": 378549, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1041195392608643, "global_step": 378550, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.050989866256714, "global_step": 378551, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.056379795074463, "global_step": 378552, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.163516044616699, "global_step": 378553, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.073310136795044, "global_step": 378554, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.09527587890625, "global_step": 378555, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.143573522567749, "global_step": 378556, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.065222978591919, "global_step": 378557, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.10791277885437, "global_step": 378558, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.07832932472229, "global_step": 378559, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.165426731109619, "global_step": 378560, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.154650926589966, "global_step": 378561, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.094896078109741, "global_step": 378562, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.107266902923584, "global_step": 378563, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1652538776397705, "global_step": 378564, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0645835399627686, "global_step": 378565, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1252424716949463, "global_step": 378566, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.113391160964966, "global_step": 378567, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1679797172546387, "global_step": 378568, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.092590808868408, "global_step": 378569, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1323254108428955, "global_step": 378570, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0841362476348877, "global_step": 378571, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1006486415863037, "global_step": 378572, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0532617568969727, "global_step": 378573, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1484758853912354, "global_step": 378574, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.08378005027771, "global_step": 378575, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0420188903808594, "global_step": 378576, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0343544483184814, "global_step": 378577, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.060962200164795, "global_step": 378578, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0543432235717773, "global_step": 378579, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0955312252044678, "global_step": 378580, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1078646183013916, "global_step": 378581, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.15842342376709, "global_step": 378582, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.162722110748291, "global_step": 378583, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.133286714553833, "global_step": 378584, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0766940116882324, "global_step": 378585, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1426377296447754, "global_step": 378586, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0395607948303223, "global_step": 378587, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0801098346710205, "global_step": 378588, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0687601566314697, "global_step": 378589, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.173156976699829, "global_step": 378590, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.074488878250122, "global_step": 378591, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1385140419006348, "global_step": 378592, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.066272735595703, "global_step": 378593, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1199240684509277, "global_step": 378594, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.205822467803955, "global_step": 378595, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0750439167022705, "global_step": 378596, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1270487308502197, "global_step": 378597, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1285648345947266, "global_step": 378598, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0815892219543457, "global_step": 378599, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1092545986175537, "global_step": 378600, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.099931478500366, "global_step": 378601, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.121535539627075, "global_step": 378602, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.059950351715088, "global_step": 378603, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.124457359313965, "global_step": 378604, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.180931329727173, "global_step": 378605, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.142378330230713, "global_step": 378606, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.101557731628418, "global_step": 378607, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0788652896881104, "global_step": 378608, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.168058156967163, "global_step": 378609, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.065950632095337, "global_step": 378610, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1616716384887695, "global_step": 378611, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1592941284179688, "global_step": 378612, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.094653844833374, "global_step": 378613, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1222736835479736, "global_step": 378614, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1622486114501953, "global_step": 378615, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0853328704833984, "global_step": 378616, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.118581533432007, "global_step": 378617, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0750598907470703, "global_step": 378618, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0605123043060303, "global_step": 378619, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.093113422393799, "global_step": 378620, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.2320504188537598, "global_step": 378621, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0749425888061523, "global_step": 378622, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0514206886291504, "global_step": 378623, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.16266131401062, "global_step": 378624, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.147202968597412, "global_step": 378625, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0326051712036133, "global_step": 378626, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1511359214782715, "global_step": 378627, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0590591430664062, "global_step": 378628, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1029491424560547, "global_step": 378629, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.220245599746704, "global_step": 378630, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.093942880630493, "global_step": 378631, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.081331253051758, "global_step": 378632, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.052934408187866, "global_step": 378633, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1248390674591064, "global_step": 378634, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0763444900512695, "global_step": 378635, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.118974447250366, "global_step": 378636, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1112115383148193, "global_step": 378637, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.068916082382202, "global_step": 378638, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1008527278900146, "global_step": 378639, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.102719783782959, "global_step": 378640, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0386264324188232, "global_step": 378641, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.125903367996216, "global_step": 378642, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.093733787536621, "global_step": 378643, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.140489339828491, "global_step": 378644, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.188102960586548, "global_step": 378645, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.101532459259033, "global_step": 378646, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0911898612976074, "global_step": 378647, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0763230323791504, "global_step": 378648, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.099766492843628, "global_step": 378649, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.11604642868042, "global_step": 378650, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1285629272460938, "global_step": 378651, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1261720657348633, "global_step": 378652, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1118814945220947, "global_step": 378653, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1227235794067383, "global_step": 378654, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0982494354248047, "global_step": 378655, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.10300874710083, "global_step": 378656, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.125476360321045, "global_step": 378657, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1249070167541504, "global_step": 378658, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1646525859832764, "global_step": 378659, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.089855670928955, "global_step": 378660, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0567963123321533, "global_step": 378661, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1359505653381348, "global_step": 378662, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1530256271362305, "global_step": 378663, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.117328405380249, "global_step": 378664, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.116597890853882, "global_step": 378665, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1122777462005615, "global_step": 378666, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1002984046936035, "global_step": 378667, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0943241119384766, "global_step": 378668, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1430504322052, "global_step": 378669, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.081472158432007, "global_step": 378670, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.083340644836426, "global_step": 378671, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1164278984069824, "global_step": 378672, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.144171953201294, "global_step": 378673, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.142223358154297, "global_step": 378674, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.110602617263794, "global_step": 378675, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.161682605743408, "global_step": 378676, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.038389205932617, "global_step": 378677, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.144937515258789, "global_step": 378678, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.112445831298828, "global_step": 378679, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1050922870635986, "global_step": 378680, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0810739994049072, "global_step": 378681, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1210646629333496, "global_step": 378682, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0737533569335938, "global_step": 378683, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1090824604034424, "global_step": 378684, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1226015090942383, "global_step": 378685, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.11803936958313, "global_step": 378686, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.079261302947998, "global_step": 378687, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.087894916534424, "global_step": 378688, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1470274925231934, "global_step": 378689, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.082104206085205, "global_step": 378690, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.076284885406494, "global_step": 378691, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0294229984283447, "global_step": 378692, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.191011667251587, "global_step": 378693, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.145482301712036, "global_step": 378694, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0753843784332275, "global_step": 378695, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.084658145904541, "global_step": 378696, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1114859580993652, "global_step": 378697, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.172687292098999, "global_step": 378698, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.054962635040283, "global_step": 378699, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.033296823501587, "global_step": 378700, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1142842769622803, "global_step": 378701, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0729639530181885, "global_step": 378702, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0472888946533203, "global_step": 378703, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.14846134185791, "global_step": 378704, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0756688117980957, "global_step": 378705, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.058436393737793, "global_step": 378706, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.186140537261963, "global_step": 378707, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0430426597595215, "global_step": 378708, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1248552799224854, "global_step": 378709, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.158862352371216, "global_step": 378710, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1314661502838135, "global_step": 378711, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.093505620956421, "global_step": 378712, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1070544719696045, "global_step": 378713, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1231613159179688, "global_step": 378714, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.15742564201355, "global_step": 378715, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1194748878479004, "global_step": 378716, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0890729427337646, "global_step": 378717, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1135478019714355, "global_step": 378718, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0438473224639893, "global_step": 378719, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0850703716278076, "global_step": 378720, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0086779594421387, "global_step": 378721, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0200464725494385, "global_step": 378722, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0471537113189697, "global_step": 378723, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1236772537231445, "global_step": 378724, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.16023850440979, "global_step": 378725, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1145286560058594, "global_step": 378726, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1133220195770264, "global_step": 378727, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0308263301849365, "global_step": 378728, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.101376533508301, "global_step": 378729, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1664443016052246, "global_step": 378730, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1154661178588867, "global_step": 378731, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.109177589416504, "global_step": 378732, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.153193235397339, "global_step": 378733, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.059107780456543, "global_step": 378734, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.137342929840088, "global_step": 378735, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.12827205657959, "global_step": 378736, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1224467754364014, "global_step": 378737, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.101090669631958, "global_step": 378738, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1517560482025146, "global_step": 378739, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.067192792892456, "global_step": 378740, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0792205333709717, "global_step": 378741, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.063314914703369, "global_step": 378742, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.2109761238098145, "global_step": 378743, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.083893060684204, "global_step": 378744, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.084599733352661, "global_step": 378745, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.129488468170166, "global_step": 378746, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.166585683822632, "global_step": 378747, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1530942916870117, "global_step": 378748, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1267268657684326, "global_step": 378749, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.105468988418579, "global_step": 378750, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.03248929977417, "global_step": 378751, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.098177433013916, "global_step": 378752, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.081071138381958, "global_step": 378753, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0892014503479004, "global_step": 378754, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.036914825439453, "global_step": 378755, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0827040672302246, "global_step": 378756, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.124483585357666, "global_step": 378757, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1769044399261475, "global_step": 378758, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1149868965148926, "global_step": 378759, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.068244218826294, "global_step": 378760, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1668272018432617, "global_step": 378761, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.058288335800171, "global_step": 378762, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1369428634643555, "global_step": 378763, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.034973382949829, "global_step": 378764, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.151200532913208, "global_step": 378765, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1577816009521484, "global_step": 378766, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0660455226898193, "global_step": 378767, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0843920707702637, "global_step": 378768, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1023011207580566, "global_step": 378769, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.157531976699829, "global_step": 378770, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1194722652435303, "global_step": 378771, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1371653079986572, "global_step": 378772, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1634137630462646, "global_step": 378773, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1690423488616943, "global_step": 378774, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.10762095451355, "global_step": 378775, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1277294158935547, "global_step": 378776, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0792856216430664, "global_step": 378777, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.165008068084717, "global_step": 378778, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1106646060943604, "global_step": 378779, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0353126525878906, "global_step": 378780, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.092740297317505, "global_step": 378781, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.069817543029785, "global_step": 378782, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0723042488098145, "global_step": 378783, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1836540699005127, "global_step": 378784, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0551021099090576, "global_step": 378785, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1119213104248047, "global_step": 378786, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.067242383956909, "global_step": 378787, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1071012020111084, "global_step": 378788, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1215708255767822, "global_step": 378789, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1377978324890137, "global_step": 378790, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.035041570663452, "global_step": 378791, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1548831462860107, "global_step": 378792, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0863471031188965, "global_step": 378793, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.117201089859009, "global_step": 378794, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0992634296417236, "global_step": 378795, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.2241580486297607, "global_step": 378796, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.164019823074341, "global_step": 378797, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0215723514556885, "global_step": 378798, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.127346992492676, "global_step": 378799, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.125710964202881, "global_step": 378800, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.071272134780884, "global_step": 378801, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0588252544403076, "global_step": 378802, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.125732660293579, "global_step": 378803, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.086725950241089, "global_step": 378804, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1330795288085938, "global_step": 378805, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1663224697113037, "global_step": 378806, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.075395345687866, "global_step": 378807, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.118572950363159, "global_step": 378808, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.098545789718628, "global_step": 378809, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.140132427215576, "global_step": 378810, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1324081420898438, "global_step": 378811, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.076456308364868, "global_step": 378812, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1732070446014404, "global_step": 378813, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1508326530456543, "global_step": 378814, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1097524166107178, "global_step": 378815, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.090991497039795, "global_step": 378816, "epoch": 740, "lr": 5e-05}
{"train_loss": 1.949583888053894, "global_step": 378817, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.096184730529785, "global_step": 378818, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.08732533454895, "global_step": 378819, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.23660945892334, "global_step": 378820, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1488335132598877, "global_step": 378821, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.087479591369629, "global_step": 378822, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1238787174224854, "global_step": 378823, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1486799716949463, "global_step": 378824, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.08070969581604, "global_step": 378825, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1574912071228027, "global_step": 378826, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.04748797416687, "global_step": 378827, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0512924194335938, "global_step": 378828, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.103924512863159, "global_step": 378829, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1030023097991943, "global_step": 378830, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.015906572341919, "global_step": 378831, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1037826538085938, "global_step": 378832, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.12325382232666, "global_step": 378833, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1624526977539062, "global_step": 378834, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1596882343292236, "global_step": 378835, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1600382328033447, "global_step": 378836, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1335642337799072, "global_step": 378837, "epoch": 740, "lr": 5e-05}
{"train_loss": 1.994665503501892, "global_step": 378838, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1076953411102295, "global_step": 378839, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1132521629333496, "global_step": 378840, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1212265491485596, "global_step": 378841, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0717356204986572, "global_step": 378842, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0713951587677, "global_step": 378843, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.098939895629883, "global_step": 378844, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1733815670013428, "global_step": 378845, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0969207286834717, "global_step": 378846, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.210491418838501, "global_step": 378847, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0968034267425537, "global_step": 378848, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0527844429016113, "global_step": 378849, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.083561420440674, "global_step": 378850, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1337778568267822, "global_step": 378851, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.121309518814087, "global_step": 378852, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.110492467880249, "global_step": 378853, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.146829605102539, "global_step": 378854, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.140082359313965, "global_step": 378855, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.126033067703247, "global_step": 378856, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.062321901321411, "global_step": 378857, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.098100423812866, "global_step": 378858, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0748298168182373, "global_step": 378859, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1695024967193604, "global_step": 378860, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.208638906478882, "global_step": 378861, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.075594663619995, "global_step": 378862, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1054892539978027, "global_step": 378863, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0439462661743164, "global_step": 378864, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1061058044433594, "global_step": 378865, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.111264944076538, "global_step": 378866, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.102020502090454, "global_step": 378867, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0684704780578613, "global_step": 378868, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0232274532318115, "global_step": 378869, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.190063953399658, "global_step": 378870, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1005711555480957, "global_step": 378871, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0701918601989746, "global_step": 378872, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1207380294799805, "global_step": 378873, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.024477481842041, "global_step": 378874, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.2075586318969727, "global_step": 378875, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1351327896118164, "global_step": 378876, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0450150966644287, "global_step": 378877, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.176835775375366, "global_step": 378878, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.047456741333008, "global_step": 378879, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.133523941040039, "global_step": 378880, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1012020111083984, "global_step": 378881, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0255508422851562, "global_step": 378882, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.089965343475342, "global_step": 378883, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.2002367973327637, "global_step": 378884, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.044248342514038, "global_step": 378885, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.082686185836792, "global_step": 378886, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1317949295043945, "global_step": 378887, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.2331292629241943, "global_step": 378888, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.087583065032959, "global_step": 378889, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.142961263656616, "global_step": 378890, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0952677726745605, "global_step": 378891, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1272776126861572, "global_step": 378892, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0263314247131348, "global_step": 378893, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.179856777191162, "global_step": 378894, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.046863079071045, "global_step": 378895, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1622581481933594, "global_step": 378896, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1006288528442383, "global_step": 378897, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.175147771835327, "global_step": 378898, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.166626214981079, "global_step": 378899, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0986998081207275, "global_step": 378900, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0848236083984375, "global_step": 378901, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0053837299346924, "global_step": 378902, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.055626630783081, "global_step": 378903, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1410727500915527, "global_step": 378904, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.194232225418091, "global_step": 378905, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0397353172302246, "global_step": 378906, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1218578815460205, "global_step": 378907, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0518124103546143, "global_step": 378908, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.124654769897461, "global_step": 378909, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.166344404220581, "global_step": 378910, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1255016326904297, "global_step": 378911, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.043652057647705, "global_step": 378912, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.129305839538574, "global_step": 378913, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1034440994262695, "global_step": 378914, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.082930326461792, "global_step": 378915, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.130160093307495, "global_step": 378916, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0309414863586426, "global_step": 378917, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1352388858795166, "global_step": 378918, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1156704425811768, "global_step": 378919, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1953089237213135, "global_step": 378920, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0699963569641113, "global_step": 378921, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1185426712036133, "global_step": 378922, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.164757490158081, "global_step": 378923, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0619144439697266, "global_step": 378924, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0900208950042725, "global_step": 378925, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0540215969085693, "global_step": 378926, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.078566312789917, "global_step": 378927, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0882279872894287, "global_step": 378928, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.162677526473999, "global_step": 378929, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.159980058670044, "global_step": 378930, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1202094554901123, "global_step": 378931, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1422555446624756, "global_step": 378932, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.2463316917419434, "global_step": 378933, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0986878871917725, "global_step": 378934, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1048009395599365, "global_step": 378935, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.224971294403076, "global_step": 378936, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.2503812313079834, "global_step": 378937, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0696935653686523, "global_step": 378938, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.15582537651062, "global_step": 378939, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.111206531524658, "global_step": 378940, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.114724636077881, "global_step": 378941, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0773308277130127, "global_step": 378942, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.131798028945923, "global_step": 378943, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1230530738830566, "global_step": 378944, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.154723882675171, "global_step": 378945, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.109030246734619, "global_step": 378946, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.064070701599121, "global_step": 378947, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.181837558746338, "global_step": 378948, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.124382257461548, "global_step": 378949, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1008172035217285, "global_step": 378950, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.112436532974243, "global_step": 378951, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.15290904045105, "global_step": 378952, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0953354835510254, "global_step": 378953, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1277995109558105, "global_step": 378954, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.007488965988159, "global_step": 378955, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1033453941345215, "global_step": 378956, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1871657371520996, "global_step": 378957, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.204681634902954, "global_step": 378958, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.100346088409424, "global_step": 378959, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1162164211273193, "global_step": 378960, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0435914993286133, "global_step": 378961, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0275321006774902, "global_step": 378962, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.112426519393921, "global_step": 378963, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.136225461959839, "global_step": 378964, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0963199138641357, "global_step": 378965, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.066603422164917, "global_step": 378966, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.188319206237793, "global_step": 378967, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.150620937347412, "global_step": 378968, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1446521282196045, "global_step": 378969, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.181682825088501, "global_step": 378970, "epoch": 740, "lr": 5e-05}
{"train_loss": 1.9852535724639893, "global_step": 378971, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1052069664001465, "global_step": 378972, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0872530937194824, "global_step": 378973, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.072349786758423, "global_step": 378974, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.178344964981079, "global_step": 378975, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.095768690109253, "global_step": 378976, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0618515014648438, "global_step": 378977, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.11826229095459, "global_step": 378978, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.110360860824585, "global_step": 378979, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.15411114692688, "global_step": 378980, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.095487356185913, "global_step": 378981, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.149491310119629, "global_step": 378982, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1362686157226562, "global_step": 378983, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.080855131149292, "global_step": 378984, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1077024936676025, "global_step": 378985, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.099973678588867, "global_step": 378986, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.2056210041046143, "global_step": 378987, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.036545753479004, "global_step": 378988, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1064858436584473, "global_step": 378989, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0954508781433105, "global_step": 378990, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.074904680252075, "global_step": 378991, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0571601390838623, "global_step": 378992, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0918519496917725, "global_step": 378993, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.079533100128174, "global_step": 378994, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1212961673736572, "global_step": 378995, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0930888652801514, "global_step": 378996, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0758581161499023, "global_step": 378997, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.046280860900879, "global_step": 378998, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0977296829223633, "global_step": 378999, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.0860447883605957, "global_step": 379000, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1484529972076416, "global_step": 379001, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.086430788040161, "global_step": 379002, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1027750968933105, "global_step": 379003, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.134969472885132, "global_step": 379004, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1530866622924805, "global_step": 379005, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1148014068603516, "global_step": 379006, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.05096435546875, "global_step": 379007, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.060180187225342, "global_step": 379008, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.1240084171295166, "global_step": 379009, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.061490774154663, "global_step": 379010, "epoch": 740, "lr": 5e-05}
{"train_loss": 2.104842185974121, "global_step": 379011, "epoch": 740, "lr": 5e-05, "val_loss": 5.632317543029785, "test_reconst_mse": 0.07343845814466476}
{"train_loss": 2.022895574569702, "global_step": 379012, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0241200923919678, "global_step": 379013, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1241934299468994, "global_step": 379014, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.007753849029541, "global_step": 379015, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1181421279907227, "global_step": 379016, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.097350835800171, "global_step": 379017, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.086170196533203, "global_step": 379018, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.136662244796753, "global_step": 379019, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.08294677734375, "global_step": 379020, "epoch": 741, "lr": 5e-05}
{"train_loss": 1.9838144779205322, "global_step": 379021, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1096081733703613, "global_step": 379022, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.014960527420044, "global_step": 379023, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.030172348022461, "global_step": 379024, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0544795989990234, "global_step": 379025, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.2424378395080566, "global_step": 379026, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0368998050689697, "global_step": 379027, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.077995777130127, "global_step": 379028, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0821144580841064, "global_step": 379029, "epoch": 741, "lr": 5e-05}
{"train_loss": 1.9939850568771362, "global_step": 379030, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1119444370269775, "global_step": 379031, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.152251958847046, "global_step": 379032, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.065065622329712, "global_step": 379033, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.065830945968628, "global_step": 379034, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.050595760345459, "global_step": 379035, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.079420566558838, "global_step": 379036, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0583715438842773, "global_step": 379037, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0470707416534424, "global_step": 379038, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0568034648895264, "global_step": 379039, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.048703908920288, "global_step": 379040, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.111128091812134, "global_step": 379041, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1725423336029053, "global_step": 379042, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0577991008758545, "global_step": 379043, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0554935932159424, "global_step": 379044, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1142938137054443, "global_step": 379045, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.076599597930908, "global_step": 379046, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.016981840133667, "global_step": 379047, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1521975994110107, "global_step": 379048, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.116556167602539, "global_step": 379049, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.054823637008667, "global_step": 379050, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1635215282440186, "global_step": 379051, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.118964433670044, "global_step": 379052, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0324788093566895, "global_step": 379053, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1608071327209473, "global_step": 379054, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.045900821685791, "global_step": 379055, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0905981063842773, "global_step": 379056, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.108445405960083, "global_step": 379057, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.204413890838623, "global_step": 379058, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1409809589385986, "global_step": 379059, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.121217966079712, "global_step": 379060, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.145768642425537, "global_step": 379061, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.072330951690674, "global_step": 379062, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1601102352142334, "global_step": 379063, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.10752010345459, "global_step": 379064, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.078458547592163, "global_step": 379065, "epoch": 741, "lr": 5e-05}
{"train_loss": 1.9824551343917847, "global_step": 379066, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0349104404449463, "global_step": 379067, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1418914794921875, "global_step": 379068, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0370728969573975, "global_step": 379069, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0550622940063477, "global_step": 379070, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1098523139953613, "global_step": 379071, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0941970348358154, "global_step": 379072, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.19097638130188, "global_step": 379073, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.164515256881714, "global_step": 379074, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0373082160949707, "global_step": 379075, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0248639583587646, "global_step": 379076, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.095921754837036, "global_step": 379077, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.022578001022339, "global_step": 379078, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0139713287353516, "global_step": 379079, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.076528787612915, "global_step": 379080, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.112560987472534, "global_step": 379081, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1650257110595703, "global_step": 379082, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0279459953308105, "global_step": 379083, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0456268787384033, "global_step": 379084, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0875043869018555, "global_step": 379085, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0763697624206543, "global_step": 379086, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0594329833984375, "global_step": 379087, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.074991226196289, "global_step": 379088, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1059956550598145, "global_step": 379089, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1538565158843994, "global_step": 379090, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1536476612091064, "global_step": 379091, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0717971324920654, "global_step": 379092, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.084935188293457, "global_step": 379093, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.075105905532837, "global_step": 379094, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.011200428009033, "global_step": 379095, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.159343719482422, "global_step": 379096, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.2010769844055176, "global_step": 379097, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1174662113189697, "global_step": 379098, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.139378547668457, "global_step": 379099, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0959792137145996, "global_step": 379100, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.230886697769165, "global_step": 379101, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.050032138824463, "global_step": 379102, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1242544651031494, "global_step": 379103, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.111276865005493, "global_step": 379104, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0715463161468506, "global_step": 379105, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.2064285278320312, "global_step": 379106, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.120913505554199, "global_step": 379107, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0892434120178223, "global_step": 379108, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.115048885345459, "global_step": 379109, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1060569286346436, "global_step": 379110, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.090294361114502, "global_step": 379111, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.121441125869751, "global_step": 379112, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.181277275085449, "global_step": 379113, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.125156879425049, "global_step": 379114, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.110957384109497, "global_step": 379115, "epoch": 741, "lr": 5e-05}
{"train_loss": 1.991148829460144, "global_step": 379116, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.12358021736145, "global_step": 379117, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0804479122161865, "global_step": 379118, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1176583766937256, "global_step": 379119, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1475183963775635, "global_step": 379120, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0971477031707764, "global_step": 379121, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.09645414352417, "global_step": 379122, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.081329345703125, "global_step": 379123, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.064835786819458, "global_step": 379124, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1123807430267334, "global_step": 379125, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1072897911071777, "global_step": 379126, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.03548526763916, "global_step": 379127, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.091811418533325, "global_step": 379128, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.107296943664551, "global_step": 379129, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.060004472732544, "global_step": 379130, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0485963821411133, "global_step": 379131, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1339950561523438, "global_step": 379132, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1755762100219727, "global_step": 379133, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1750237941741943, "global_step": 379134, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0606367588043213, "global_step": 379135, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0222201347351074, "global_step": 379136, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0321550369262695, "global_step": 379137, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.098646402359009, "global_step": 379138, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.115602493286133, "global_step": 379139, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1063458919525146, "global_step": 379140, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.111320734024048, "global_step": 379141, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0827012062072754, "global_step": 379142, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0479602813720703, "global_step": 379143, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.06899356842041, "global_step": 379144, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1363627910614014, "global_step": 379145, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0554661750793457, "global_step": 379146, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.237361192703247, "global_step": 379147, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1965818405151367, "global_step": 379148, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.117997646331787, "global_step": 379149, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1271464824676514, "global_step": 379150, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1282238960266113, "global_step": 379151, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.087867498397827, "global_step": 379152, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1224212646484375, "global_step": 379153, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.141631603240967, "global_step": 379154, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.101280689239502, "global_step": 379155, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0665969848632812, "global_step": 379156, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.08974289894104, "global_step": 379157, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.141702651977539, "global_step": 379158, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.101879835128784, "global_step": 379159, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1285367012023926, "global_step": 379160, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0275137424468994, "global_step": 379161, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.183699131011963, "global_step": 379162, "epoch": 741, "lr": 5e-05}
{"train_loss": 1.9412461519241333, "global_step": 379163, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0730531215667725, "global_step": 379164, "epoch": 741, "lr": 5e-05}
{"train_loss": 1.9804000854492188, "global_step": 379165, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.044983148574829, "global_step": 379166, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0291101932525635, "global_step": 379167, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.070113182067871, "global_step": 379168, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1271615028381348, "global_step": 379169, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0387094020843506, "global_step": 379170, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0994489192962646, "global_step": 379171, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0825695991516113, "global_step": 379172, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0771448612213135, "global_step": 379173, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1206722259521484, "global_step": 379174, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1275949478149414, "global_step": 379175, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0233304500579834, "global_step": 379176, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.066251039505005, "global_step": 379177, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.083951711654663, "global_step": 379178, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.081528902053833, "global_step": 379179, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.133922576904297, "global_step": 379180, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.095550298690796, "global_step": 379181, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.047245979309082, "global_step": 379182, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0968949794769287, "global_step": 379183, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.086775064468384, "global_step": 379184, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1073362827301025, "global_step": 379185, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.098475933074951, "global_step": 379186, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0813517570495605, "global_step": 379187, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.047440767288208, "global_step": 379188, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.072566032409668, "global_step": 379189, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0936594009399414, "global_step": 379190, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0726423263549805, "global_step": 379191, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.090399980545044, "global_step": 379192, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.151177406311035, "global_step": 379193, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0682530403137207, "global_step": 379194, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.115257978439331, "global_step": 379195, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0926387310028076, "global_step": 379196, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.152477979660034, "global_step": 379197, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1492648124694824, "global_step": 379198, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0596537590026855, "global_step": 379199, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1704888343811035, "global_step": 379200, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.078752279281616, "global_step": 379201, "epoch": 741, "lr": 5e-05}
{"train_loss": 1.9260700941085815, "global_step": 379202, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.053710460662842, "global_step": 379203, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1197738647460938, "global_step": 379204, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.047619342803955, "global_step": 379205, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.104936122894287, "global_step": 379206, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.112546920776367, "global_step": 379207, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0580761432647705, "global_step": 379208, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.077056407928467, "global_step": 379209, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.066847801208496, "global_step": 379210, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.077194929122925, "global_step": 379211, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1188578605651855, "global_step": 379212, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1151719093322754, "global_step": 379213, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.096527576446533, "global_step": 379214, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.118678569793701, "global_step": 379215, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.088336944580078, "global_step": 379216, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0174379348754883, "global_step": 379217, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0386455059051514, "global_step": 379218, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.2152462005615234, "global_step": 379219, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1055164337158203, "global_step": 379220, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.04232120513916, "global_step": 379221, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1076242923736572, "global_step": 379222, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1097328662872314, "global_step": 379223, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1240711212158203, "global_step": 379224, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1306843757629395, "global_step": 379225, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.057605028152466, "global_step": 379226, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.159898281097412, "global_step": 379227, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0460667610168457, "global_step": 379228, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.094125270843506, "global_step": 379229, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1668622493743896, "global_step": 379230, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.171767234802246, "global_step": 379231, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1373708248138428, "global_step": 379232, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.144881248474121, "global_step": 379233, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1002938747406006, "global_step": 379234, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.032050132751465, "global_step": 379235, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0856919288635254, "global_step": 379236, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.135784387588501, "global_step": 379237, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1903064250946045, "global_step": 379238, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.194424629211426, "global_step": 379239, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0136847496032715, "global_step": 379240, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0942020416259766, "global_step": 379241, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.067211151123047, "global_step": 379242, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0695371627807617, "global_step": 379243, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.107828140258789, "global_step": 379244, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.124107837677002, "global_step": 379245, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0669031143188477, "global_step": 379246, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.113361358642578, "global_step": 379247, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.081075429916382, "global_step": 379248, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.196814775466919, "global_step": 379249, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0743610858917236, "global_step": 379250, "epoch": 741, "lr": 5e-05}
{"train_loss": 1.978163242340088, "global_step": 379251, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0137546062469482, "global_step": 379252, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1286776065826416, "global_step": 379253, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.056586503982544, "global_step": 379254, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0356836318969727, "global_step": 379255, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1554741859436035, "global_step": 379256, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0745275020599365, "global_step": 379257, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1048738956451416, "global_step": 379258, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0227036476135254, "global_step": 379259, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1077208518981934, "global_step": 379260, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.043700933456421, "global_step": 379261, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.041165590286255, "global_step": 379262, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.151912212371826, "global_step": 379263, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1572561264038086, "global_step": 379264, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.019258737564087, "global_step": 379265, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.134194850921631, "global_step": 379266, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.042141914367676, "global_step": 379267, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.170205593109131, "global_step": 379268, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1309456825256348, "global_step": 379269, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.066895008087158, "global_step": 379270, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0761678218841553, "global_step": 379271, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1180782318115234, "global_step": 379272, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0966873168945312, "global_step": 379273, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1534290313720703, "global_step": 379274, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.063605308532715, "global_step": 379275, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.112725019454956, "global_step": 379276, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.031566619873047, "global_step": 379277, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.003861904144287, "global_step": 379278, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.096787691116333, "global_step": 379279, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0645880699157715, "global_step": 379280, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.055157423019409, "global_step": 379281, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1232943534851074, "global_step": 379282, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1634864807128906, "global_step": 379283, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1346659660339355, "global_step": 379284, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0668509006500244, "global_step": 379285, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.057629346847534, "global_step": 379286, "epoch": 741, "lr": 5e-05}
{"train_loss": 1.9952654838562012, "global_step": 379287, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0913238525390625, "global_step": 379288, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1917059421539307, "global_step": 379289, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.2274081707000732, "global_step": 379290, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1228861808776855, "global_step": 379291, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0452070236206055, "global_step": 379292, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1126997470855713, "global_step": 379293, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0541629791259766, "global_step": 379294, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0878472328186035, "global_step": 379295, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.105752468109131, "global_step": 379296, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.106480360031128, "global_step": 379297, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0754637718200684, "global_step": 379298, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.14044451713562, "global_step": 379299, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0330288410186768, "global_step": 379300, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0993595123291016, "global_step": 379301, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.16554594039917, "global_step": 379302, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.09279203414917, "global_step": 379303, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1003971099853516, "global_step": 379304, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.099752426147461, "global_step": 379305, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.088027000427246, "global_step": 379306, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1176376342773438, "global_step": 379307, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.040050983428955, "global_step": 379308, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.04306697845459, "global_step": 379309, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1310524940490723, "global_step": 379310, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1030619144439697, "global_step": 379311, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1176905632019043, "global_step": 379312, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.124812602996826, "global_step": 379313, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1581904888153076, "global_step": 379314, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1388087272644043, "global_step": 379315, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.149143695831299, "global_step": 379316, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0364627838134766, "global_step": 379317, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0208518505096436, "global_step": 379318, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0500588417053223, "global_step": 379319, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1542773246765137, "global_step": 379320, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.12953782081604, "global_step": 379321, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.09263277053833, "global_step": 379322, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0674619674682617, "global_step": 379323, "epoch": 741, "lr": 5e-05}
{"train_loss": 1.9912397861480713, "global_step": 379324, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1444268226623535, "global_step": 379325, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.072335958480835, "global_step": 379326, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0853464603424072, "global_step": 379327, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.176386833190918, "global_step": 379328, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1130359172821045, "global_step": 379329, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1207783222198486, "global_step": 379330, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.153881072998047, "global_step": 379331, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.057873010635376, "global_step": 379332, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0713236331939697, "global_step": 379333, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0991263389587402, "global_step": 379334, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0701091289520264, "global_step": 379335, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.206843852996826, "global_step": 379336, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.123429298400879, "global_step": 379337, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0153000354766846, "global_step": 379338, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.038957357406616, "global_step": 379339, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1063292026519775, "global_step": 379340, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1275813579559326, "global_step": 379341, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.2162463665008545, "global_step": 379342, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0151286125183105, "global_step": 379343, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1378633975982666, "global_step": 379344, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.115293025970459, "global_step": 379345, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.044072389602661, "global_step": 379346, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0616612434387207, "global_step": 379347, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.032588243484497, "global_step": 379348, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0489578247070312, "global_step": 379349, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.054957866668701, "global_step": 379350, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1019585132598877, "global_step": 379351, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1563196182250977, "global_step": 379352, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.110804796218872, "global_step": 379353, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0629239082336426, "global_step": 379354, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0381882190704346, "global_step": 379355, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0771026611328125, "global_step": 379356, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.151803493499756, "global_step": 379357, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.127302646636963, "global_step": 379358, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1443278789520264, "global_step": 379359, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.18489670753479, "global_step": 379360, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0758299827575684, "global_step": 379361, "epoch": 741, "lr": 5e-05}
{"train_loss": 1.9975329637527466, "global_step": 379362, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0260238647460938, "global_step": 379363, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1220102310180664, "global_step": 379364, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1244301795959473, "global_step": 379365, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1012778282165527, "global_step": 379366, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1595866680145264, "global_step": 379367, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0909759998321533, "global_step": 379368, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.2267684936523438, "global_step": 379369, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.192225933074951, "global_step": 379370, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.2101633548736572, "global_step": 379371, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0634920597076416, "global_step": 379372, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1258490085601807, "global_step": 379373, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.140902042388916, "global_step": 379374, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1345696449279785, "global_step": 379375, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0399060249328613, "global_step": 379376, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.030143976211548, "global_step": 379377, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0418126583099365, "global_step": 379378, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.15500545501709, "global_step": 379379, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.123039484024048, "global_step": 379380, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1032378673553467, "global_step": 379381, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0551466941833496, "global_step": 379382, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1625733375549316, "global_step": 379383, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1346826553344727, "global_step": 379384, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.05731463432312, "global_step": 379385, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0785205364227295, "global_step": 379386, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0132577419281006, "global_step": 379387, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0877819061279297, "global_step": 379388, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1545376777648926, "global_step": 379389, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0993261337280273, "global_step": 379390, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.117361307144165, "global_step": 379391, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.127535104751587, "global_step": 379392, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.2048583030700684, "global_step": 379393, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.05418062210083, "global_step": 379394, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0428056716918945, "global_step": 379395, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.146454334259033, "global_step": 379396, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.07662034034729, "global_step": 379397, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.017334222793579, "global_step": 379398, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.144160747528076, "global_step": 379399, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0953245162963867, "global_step": 379400, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1644279956817627, "global_step": 379401, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.213993549346924, "global_step": 379402, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0641562938690186, "global_step": 379403, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.150198459625244, "global_step": 379404, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0747008323669434, "global_step": 379405, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1095428466796875, "global_step": 379406, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1049306392669678, "global_step": 379407, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.04154896736145, "global_step": 379408, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1562142372131348, "global_step": 379409, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.208186149597168, "global_step": 379410, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1577980518341064, "global_step": 379411, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1039278507232666, "global_step": 379412, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1790387630462646, "global_step": 379413, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1018950939178467, "global_step": 379414, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0378575325012207, "global_step": 379415, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.109203338623047, "global_step": 379416, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.101534128189087, "global_step": 379417, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.112656354904175, "global_step": 379418, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.136535882949829, "global_step": 379419, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.224259614944458, "global_step": 379420, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.121171474456787, "global_step": 379421, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0695457458496094, "global_step": 379422, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0447635650634766, "global_step": 379423, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.135566234588623, "global_step": 379424, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1165354251861572, "global_step": 379425, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.063981294631958, "global_step": 379426, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1297507286071777, "global_step": 379427, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0725135803222656, "global_step": 379428, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.149778127670288, "global_step": 379429, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.112161874771118, "global_step": 379430, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0657801628112793, "global_step": 379431, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0744469165802, "global_step": 379432, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.011033773422241, "global_step": 379433, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0459673404693604, "global_step": 379434, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0958783626556396, "global_step": 379435, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1138272285461426, "global_step": 379436, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.144144058227539, "global_step": 379437, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.086700677871704, "global_step": 379438, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.012788772583008, "global_step": 379439, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0922176837921143, "global_step": 379440, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1024839878082275, "global_step": 379441, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1582038402557373, "global_step": 379442, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.056574583053589, "global_step": 379443, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1098599433898926, "global_step": 379444, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1439719200134277, "global_step": 379445, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0195329189300537, "global_step": 379446, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1524720191955566, "global_step": 379447, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0689334869384766, "global_step": 379448, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1483614444732666, "global_step": 379449, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.180464744567871, "global_step": 379450, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0990982055664062, "global_step": 379451, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.154989719390869, "global_step": 379452, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0933287143707275, "global_step": 379453, "epoch": 741, "lr": 5e-05}
{"train_loss": 1.992124080657959, "global_step": 379454, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1113078594207764, "global_step": 379455, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.135333776473999, "global_step": 379456, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1022980213165283, "global_step": 379457, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.02860164642334, "global_step": 379458, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1712710857391357, "global_step": 379459, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0367209911346436, "global_step": 379460, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1464462280273438, "global_step": 379461, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0848333835601807, "global_step": 379462, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.057910919189453, "global_step": 379463, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0550801753997803, "global_step": 379464, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0850563049316406, "global_step": 379465, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.150238275527954, "global_step": 379466, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.106933832168579, "global_step": 379467, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1002728939056396, "global_step": 379468, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1199052333831787, "global_step": 379469, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0892183780670166, "global_step": 379470, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1099355220794678, "global_step": 379471, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1154680252075195, "global_step": 379472, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1484506130218506, "global_step": 379473, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.2143633365631104, "global_step": 379474, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1798057556152344, "global_step": 379475, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.176372766494751, "global_step": 379476, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.121387481689453, "global_step": 379477, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0734801292419434, "global_step": 379478, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1244654655456543, "global_step": 379479, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0772817134857178, "global_step": 379480, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1241259574890137, "global_step": 379481, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.100024938583374, "global_step": 379482, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.080725908279419, "global_step": 379483, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.032362699508667, "global_step": 379484, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0158329010009766, "global_step": 379485, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1575372219085693, "global_step": 379486, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.102707862854004, "global_step": 379487, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1291825771331787, "global_step": 379488, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.037358522415161, "global_step": 379489, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0365548133850098, "global_step": 379490, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.122542381286621, "global_step": 379491, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0426557064056396, "global_step": 379492, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1120758056640625, "global_step": 379493, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0444202423095703, "global_step": 379494, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0585551261901855, "global_step": 379495, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0315942764282227, "global_step": 379496, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1048407554626465, "global_step": 379497, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.127779722213745, "global_step": 379498, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1175382137298584, "global_step": 379499, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.149163007736206, "global_step": 379500, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1278321743011475, "global_step": 379501, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.033705234527588, "global_step": 379502, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.13379168510437, "global_step": 379503, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0003321170806885, "global_step": 379504, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1132354736328125, "global_step": 379505, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.015859365463257, "global_step": 379506, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0470798015594482, "global_step": 379507, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.084207534790039, "global_step": 379508, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.053530693054199, "global_step": 379509, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0539543628692627, "global_step": 379510, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1735734939575195, "global_step": 379511, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0744922161102295, "global_step": 379512, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1838088035583496, "global_step": 379513, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.145659923553467, "global_step": 379514, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.014616012573242, "global_step": 379515, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1137795448303223, "global_step": 379516, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1415836811065674, "global_step": 379517, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.14077091217041, "global_step": 379518, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0753798484802246, "global_step": 379519, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.113828659057617, "global_step": 379520, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0654985904693604, "global_step": 379521, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0842037200927734, "global_step": 379522, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1108429431915283, "global_step": 379523, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.188354730606079, "global_step": 379524, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.215416669845581, "global_step": 379525, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0992424488067627, "global_step": 379526, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1799566745758057, "global_step": 379527, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1571125984191895, "global_step": 379528, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1101651191711426, "global_step": 379529, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.027862548828125, "global_step": 379530, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0045220851898193, "global_step": 379531, "epoch": 741, "lr": 5e-05}
{"train_loss": 1.9872510433197021, "global_step": 379532, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0160326957702637, "global_step": 379533, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0747647285461426, "global_step": 379534, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0544941425323486, "global_step": 379535, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0928075313568115, "global_step": 379536, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1320807933807373, "global_step": 379537, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1028454303741455, "global_step": 379538, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.073058843612671, "global_step": 379539, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.137800455093384, "global_step": 379540, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.150636911392212, "global_step": 379541, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0522875785827637, "global_step": 379542, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.213129997253418, "global_step": 379543, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.123321294784546, "global_step": 379544, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1123623847961426, "global_step": 379545, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0871119499206543, "global_step": 379546, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1166799068450928, "global_step": 379547, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.036606550216675, "global_step": 379548, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0654115676879883, "global_step": 379549, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.043560266494751, "global_step": 379550, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1168453693389893, "global_step": 379551, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.099806308746338, "global_step": 379552, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.171456813812256, "global_step": 379553, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.147078514099121, "global_step": 379554, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0859243869781494, "global_step": 379555, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1116514205932617, "global_step": 379556, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0742368698120117, "global_step": 379557, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.096825361251831, "global_step": 379558, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1343882083892822, "global_step": 379559, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1953632831573486, "global_step": 379560, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1084094047546387, "global_step": 379561, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0982255935668945, "global_step": 379562, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.119840145111084, "global_step": 379563, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.01076078414917, "global_step": 379564, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1090197563171387, "global_step": 379565, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0400984287261963, "global_step": 379566, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0595216751098633, "global_step": 379567, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.069446563720703, "global_step": 379568, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.181460380554199, "global_step": 379569, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1041085720062256, "global_step": 379570, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1319363117218018, "global_step": 379571, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.146278142929077, "global_step": 379572, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.145139217376709, "global_step": 379573, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1161584854125977, "global_step": 379574, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.110889434814453, "global_step": 379575, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.048734188079834, "global_step": 379576, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0295798778533936, "global_step": 379577, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1483311653137207, "global_step": 379578, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1329731941223145, "global_step": 379579, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1500461101531982, "global_step": 379580, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0163145065307617, "global_step": 379581, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1220862865448, "global_step": 379582, "epoch": 741, "lr": 5e-05}
{"train_loss": 1.9624767303466797, "global_step": 379583, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1000077724456787, "global_step": 379584, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.106841802597046, "global_step": 379585, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.104499101638794, "global_step": 379586, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.076589822769165, "global_step": 379587, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1168324947357178, "global_step": 379588, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0562729835510254, "global_step": 379589, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.085785388946533, "global_step": 379590, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.204301595687866, "global_step": 379591, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.156839370727539, "global_step": 379592, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0315089225769043, "global_step": 379593, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.167511224746704, "global_step": 379594, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.121483564376831, "global_step": 379595, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.092742443084717, "global_step": 379596, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.050765037536621, "global_step": 379597, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.15559720993042, "global_step": 379598, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1978261470794678, "global_step": 379599, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0977892875671387, "global_step": 379600, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1342053413391113, "global_step": 379601, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.12186598777771, "global_step": 379602, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0976052284240723, "global_step": 379603, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0838372707366943, "global_step": 379604, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.122504711151123, "global_step": 379605, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.114002227783203, "global_step": 379606, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.143887996673584, "global_step": 379607, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.067150592803955, "global_step": 379608, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1355903148651123, "global_step": 379609, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.104494571685791, "global_step": 379610, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1349706649780273, "global_step": 379611, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0632262229919434, "global_step": 379612, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.165797233581543, "global_step": 379613, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1461493968963623, "global_step": 379614, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.127927303314209, "global_step": 379615, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0897324085235596, "global_step": 379616, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.099738121032715, "global_step": 379617, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.118415117263794, "global_step": 379618, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0569519996643066, "global_step": 379619, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1595451831817627, "global_step": 379620, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.067790985107422, "global_step": 379621, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.104959726333618, "global_step": 379622, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.104464530944824, "global_step": 379623, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.114335060119629, "global_step": 379624, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0935370922088623, "global_step": 379625, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0847508907318115, "global_step": 379626, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.031156063079834, "global_step": 379627, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1858127117156982, "global_step": 379628, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.042876958847046, "global_step": 379629, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.087383985519409, "global_step": 379630, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1095898151397705, "global_step": 379631, "epoch": 741, "lr": 5e-05}
{"train_loss": 1.9865666627883911, "global_step": 379632, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1512372493743896, "global_step": 379633, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1035642623901367, "global_step": 379634, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1423380374908447, "global_step": 379635, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0597312450408936, "global_step": 379636, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.085678815841675, "global_step": 379637, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.159266471862793, "global_step": 379638, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.115321636199951, "global_step": 379639, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.035414457321167, "global_step": 379640, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1176555156707764, "global_step": 379641, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1555283069610596, "global_step": 379642, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.164579391479492, "global_step": 379643, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1722280979156494, "global_step": 379644, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.071781873703003, "global_step": 379645, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0797600746154785, "global_step": 379646, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0879974365234375, "global_step": 379647, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.064415216445923, "global_step": 379648, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.069924831390381, "global_step": 379649, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0978963375091553, "global_step": 379650, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1211605072021484, "global_step": 379651, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0978100299835205, "global_step": 379652, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0992953777313232, "global_step": 379653, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1048974990844727, "global_step": 379654, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.096160888671875, "global_step": 379655, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0575616359710693, "global_step": 379656, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0424413681030273, "global_step": 379657, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.054913282394409, "global_step": 379658, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1326239109039307, "global_step": 379659, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1621041297912598, "global_step": 379660, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.161752223968506, "global_step": 379661, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.104501485824585, "global_step": 379662, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.091763496398926, "global_step": 379663, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0954160690307617, "global_step": 379664, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.096407175064087, "global_step": 379665, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0962905883789062, "global_step": 379666, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.042482852935791, "global_step": 379667, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.076355457305908, "global_step": 379668, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1707959175109863, "global_step": 379669, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1294374465942383, "global_step": 379670, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.208735466003418, "global_step": 379671, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.237936019897461, "global_step": 379672, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0622050762176514, "global_step": 379673, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1589534282684326, "global_step": 379674, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0869054794311523, "global_step": 379675, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.075474500656128, "global_step": 379676, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0555052757263184, "global_step": 379677, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.185025215148926, "global_step": 379678, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1629910469055176, "global_step": 379679, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1740076541900635, "global_step": 379680, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.063508987426758, "global_step": 379681, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1743409633636475, "global_step": 379682, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.154062509536743, "global_step": 379683, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.058110475540161, "global_step": 379684, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0872151851654053, "global_step": 379685, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1195931434631348, "global_step": 379686, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.120590925216675, "global_step": 379687, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.080993890762329, "global_step": 379688, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.134892463684082, "global_step": 379689, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0817313194274902, "global_step": 379690, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0052437782287598, "global_step": 379691, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1436243057250977, "global_step": 379692, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.122298240661621, "global_step": 379693, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.168968439102173, "global_step": 379694, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1717796325683594, "global_step": 379695, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1362104415893555, "global_step": 379696, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0632169246673584, "global_step": 379697, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1112136840820312, "global_step": 379698, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.157287120819092, "global_step": 379699, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1937594413757324, "global_step": 379700, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1096081733703613, "global_step": 379701, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0868802070617676, "global_step": 379702, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.188781976699829, "global_step": 379703, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.143714666366577, "global_step": 379704, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1704390048980713, "global_step": 379705, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.134582757949829, "global_step": 379706, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0891239643096924, "global_step": 379707, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0483384132385254, "global_step": 379708, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.084674835205078, "global_step": 379709, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0833215713500977, "global_step": 379710, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1449670791625977, "global_step": 379711, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.116304636001587, "global_step": 379712, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1048781871795654, "global_step": 379713, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.024597644805908, "global_step": 379714, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1089653968811035, "global_step": 379715, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.146665334701538, "global_step": 379716, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.097827672958374, "global_step": 379717, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1587061882019043, "global_step": 379718, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.054830312728882, "global_step": 379719, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.084763288497925, "global_step": 379720, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.097400665283203, "global_step": 379721, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1181888580322266, "global_step": 379722, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1063480377197266, "global_step": 379723, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0962469577789307, "global_step": 379724, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1116435527801514, "global_step": 379725, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.124446392059326, "global_step": 379726, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1098225116729736, "global_step": 379727, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.040865898132324, "global_step": 379728, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.156454563140869, "global_step": 379729, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.102970838546753, "global_step": 379730, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0919430255889893, "global_step": 379731, "epoch": 741, "lr": 5e-05}
{"train_loss": 1.9850666522979736, "global_step": 379732, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.069439172744751, "global_step": 379733, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.122767686843872, "global_step": 379734, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.140859603881836, "global_step": 379735, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1196138858795166, "global_step": 379736, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.071317434310913, "global_step": 379737, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0836079120635986, "global_step": 379738, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.2008368968963623, "global_step": 379739, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1216518878936768, "global_step": 379740, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.029118299484253, "global_step": 379741, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.111609697341919, "global_step": 379742, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1050243377685547, "global_step": 379743, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0646145343780518, "global_step": 379744, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0687661170959473, "global_step": 379745, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.078346014022827, "global_step": 379746, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.209012985229492, "global_step": 379747, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0754554271698, "global_step": 379748, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1817307472229004, "global_step": 379749, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0978758335113525, "global_step": 379750, "epoch": 741, "lr": 5e-05}
{"train_loss": 1.9796805381774902, "global_step": 379751, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0749926567077637, "global_step": 379752, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.169306516647339, "global_step": 379753, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1197826862335205, "global_step": 379754, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1188135147094727, "global_step": 379755, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0767014026641846, "global_step": 379756, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0649893283843994, "global_step": 379757, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1287901401519775, "global_step": 379758, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0886974334716797, "global_step": 379759, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.081731081008911, "global_step": 379760, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1105778217315674, "global_step": 379761, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.227600336074829, "global_step": 379762, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.182154655456543, "global_step": 379763, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.048943042755127, "global_step": 379764, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1726491451263428, "global_step": 379765, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1090168952941895, "global_step": 379766, "epoch": 741, "lr": 5e-05}
{"train_loss": 1.9768081903457642, "global_step": 379767, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.167597770690918, "global_step": 379768, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.129723310470581, "global_step": 379769, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0664219856262207, "global_step": 379770, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.154494524002075, "global_step": 379771, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1008808612823486, "global_step": 379772, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0407025814056396, "global_step": 379773, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.139714479446411, "global_step": 379774, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.142153024673462, "global_step": 379775, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.095099925994873, "global_step": 379776, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.094190835952759, "global_step": 379777, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.140157699584961, "global_step": 379778, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1300008296966553, "global_step": 379779, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0591278076171875, "global_step": 379780, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1035091876983643, "global_step": 379781, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.104370355606079, "global_step": 379782, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1142823696136475, "global_step": 379783, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.093600273132324, "global_step": 379784, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1447842121124268, "global_step": 379785, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.2008368968963623, "global_step": 379786, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.083979845046997, "global_step": 379787, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.091114044189453, "global_step": 379788, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.084658622741699, "global_step": 379789, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.170247793197632, "global_step": 379790, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0150208473205566, "global_step": 379791, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.048123359680176, "global_step": 379792, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.077765703201294, "global_step": 379793, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.11643385887146, "global_step": 379794, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.056706428527832, "global_step": 379795, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1071202754974365, "global_step": 379796, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.129889726638794, "global_step": 379797, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1372387409210205, "global_step": 379798, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1048026084899902, "global_step": 379799, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.05838680267334, "global_step": 379800, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.128330945968628, "global_step": 379801, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0497689247131348, "global_step": 379802, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0625176429748535, "global_step": 379803, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.110422372817993, "global_step": 379804, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.091627359390259, "global_step": 379805, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.13065242767334, "global_step": 379806, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.104931354522705, "global_step": 379807, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.026435375213623, "global_step": 379808, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1710522174835205, "global_step": 379809, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0517847537994385, "global_step": 379810, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.202036142349243, "global_step": 379811, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.119503974914551, "global_step": 379812, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.107290744781494, "global_step": 379813, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1672298908233643, "global_step": 379814, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.055300712585449, "global_step": 379815, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1785879135131836, "global_step": 379816, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1652517318725586, "global_step": 379817, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.111819267272949, "global_step": 379818, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.122372627258301, "global_step": 379819, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0763964653015137, "global_step": 379820, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.145805597305298, "global_step": 379821, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1908931732177734, "global_step": 379822, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.044373035430908, "global_step": 379823, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0537145137786865, "global_step": 379824, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0825281143188477, "global_step": 379825, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0564780235290527, "global_step": 379826, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.187591314315796, "global_step": 379827, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1840195655822754, "global_step": 379828, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0934088230133057, "global_step": 379829, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.089533567428589, "global_step": 379830, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1428394317626953, "global_step": 379831, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1150057315826416, "global_step": 379832, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.071500301361084, "global_step": 379833, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.20419979095459, "global_step": 379834, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.052903413772583, "global_step": 379835, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.116194725036621, "global_step": 379836, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0760467052459717, "global_step": 379837, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.198786735534668, "global_step": 379838, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0343880653381348, "global_step": 379839, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0821971893310547, "global_step": 379840, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.08756947517395, "global_step": 379841, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.072155475616455, "global_step": 379842, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.135993003845215, "global_step": 379843, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.118406295776367, "global_step": 379844, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1700308322906494, "global_step": 379845, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.148597240447998, "global_step": 379846, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1344969272613525, "global_step": 379847, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0784270763397217, "global_step": 379848, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1792232990264893, "global_step": 379849, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0749106407165527, "global_step": 379850, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0949254035949707, "global_step": 379851, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.102942943572998, "global_step": 379852, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.124803304672241, "global_step": 379853, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.041964292526245, "global_step": 379854, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1221847534179688, "global_step": 379855, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0716402530670166, "global_step": 379856, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0686838626861572, "global_step": 379857, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.214062213897705, "global_step": 379858, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1341311931610107, "global_step": 379859, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1209981441497803, "global_step": 379860, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1374728679656982, "global_step": 379861, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.178887367248535, "global_step": 379862, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.101154327392578, "global_step": 379863, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0504672527313232, "global_step": 379864, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.178887128829956, "global_step": 379865, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.144075870513916, "global_step": 379866, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.070612907409668, "global_step": 379867, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.157078742980957, "global_step": 379868, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1062870025634766, "global_step": 379869, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.145577907562256, "global_step": 379870, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0483479499816895, "global_step": 379871, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.139564037322998, "global_step": 379872, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.06632137298584, "global_step": 379873, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1154444217681885, "global_step": 379874, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0878798961639404, "global_step": 379875, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1092276573181152, "global_step": 379876, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0396347045898438, "global_step": 379877, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0738470554351807, "global_step": 379878, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.167696952819824, "global_step": 379879, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1523122787475586, "global_step": 379880, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0893332958221436, "global_step": 379881, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.259335994720459, "global_step": 379882, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1337454319000244, "global_step": 379883, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.161176919937134, "global_step": 379884, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.059046506881714, "global_step": 379885, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0742950439453125, "global_step": 379886, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0851995944976807, "global_step": 379887, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1675796508789062, "global_step": 379888, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0719947814941406, "global_step": 379889, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1122469902038574, "global_step": 379890, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0017027854919434, "global_step": 379891, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0730912685394287, "global_step": 379892, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.060472249984741, "global_step": 379893, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.155287742614746, "global_step": 379894, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.134155750274658, "global_step": 379895, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1238958835601807, "global_step": 379896, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.156695604324341, "global_step": 379897, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.145503520965576, "global_step": 379898, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0981287956237793, "global_step": 379899, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0497634410858154, "global_step": 379900, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.083172559738159, "global_step": 379901, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1490602493286133, "global_step": 379902, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0933821201324463, "global_step": 379903, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.140791177749634, "global_step": 379904, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1418068408966064, "global_step": 379905, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.115344285964966, "global_step": 379906, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1051201820373535, "global_step": 379907, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.048693895339966, "global_step": 379908, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0328543186187744, "global_step": 379909, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1060030460357666, "global_step": 379910, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.228935956954956, "global_step": 379911, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.160053253173828, "global_step": 379912, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1050875186920166, "global_step": 379913, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.124696969985962, "global_step": 379914, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0565483570098877, "global_step": 379915, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.142838478088379, "global_step": 379916, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1937787532806396, "global_step": 379917, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1425483226776123, "global_step": 379918, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.026719808578491, "global_step": 379919, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.123816967010498, "global_step": 379920, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.202211618423462, "global_step": 379921, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1040854454040527, "global_step": 379922, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1572039127349854, "global_step": 379923, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.122070550918579, "global_step": 379924, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0778565406799316, "global_step": 379925, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.146280288696289, "global_step": 379926, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1729390621185303, "global_step": 379927, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1053566932678223, "global_step": 379928, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.068176507949829, "global_step": 379929, "epoch": 741, "lr": 5e-05}
{"train_loss": 1.9821147918701172, "global_step": 379930, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.108848810195923, "global_step": 379931, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0518758296966553, "global_step": 379932, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.041079521179199, "global_step": 379933, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0905046463012695, "global_step": 379934, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1445958614349365, "global_step": 379935, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0415492057800293, "global_step": 379936, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.2009575366973877, "global_step": 379937, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1721153259277344, "global_step": 379938, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1262149810791016, "global_step": 379939, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0927059650421143, "global_step": 379940, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0848281383514404, "global_step": 379941, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.036717653274536, "global_step": 379942, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.07191801071167, "global_step": 379943, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.087399482727051, "global_step": 379944, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1353983879089355, "global_step": 379945, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1102070808410645, "global_step": 379946, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.200024127960205, "global_step": 379947, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0922796726226807, "global_step": 379948, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0480430126190186, "global_step": 379949, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.132106065750122, "global_step": 379950, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.10571026802063, "global_step": 379951, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0956244468688965, "global_step": 379952, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.05029034614563, "global_step": 379953, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1620945930480957, "global_step": 379954, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0586097240448, "global_step": 379955, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.10402774810791, "global_step": 379956, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.056307792663574, "global_step": 379957, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.142087697982788, "global_step": 379958, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0546720027923584, "global_step": 379959, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.090404510498047, "global_step": 379960, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1054697036743164, "global_step": 379961, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0417840480804443, "global_step": 379962, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1198959350585938, "global_step": 379963, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0886263847351074, "global_step": 379964, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1210460662841797, "global_step": 379965, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0774881839752197, "global_step": 379966, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.116313934326172, "global_step": 379967, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1156392097473145, "global_step": 379968, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0126953125, "global_step": 379969, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0244839191436768, "global_step": 379970, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.1129729747772217, "global_step": 379971, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.174684524536133, "global_step": 379972, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.090777635574341, "global_step": 379973, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.013951301574707, "global_step": 379974, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.102616548538208, "global_step": 379975, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.078310966491699, "global_step": 379976, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0452041625976562, "global_step": 379977, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.0990755558013916, "global_step": 379978, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.175264835357666, "global_step": 379979, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.101829767227173, "global_step": 379980, "epoch": 741, "lr": 5e-05}
{"train_loss": 2.044578790664673, "global_step": 379981, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0547029972076416, "global_step": 379982, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.125863790512085, "global_step": 379983, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1035728454589844, "global_step": 379984, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0855634212493896, "global_step": 379985, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1397247314453125, "global_step": 379986, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1198649406433105, "global_step": 379987, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.087836265563965, "global_step": 379988, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.086275339126587, "global_step": 379989, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1128809452056885, "global_step": 379990, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.202744483947754, "global_step": 379991, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0994386672973633, "global_step": 379992, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1083831787109375, "global_step": 379993, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.154615640640259, "global_step": 379994, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.9945257902145386, "global_step": 379995, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1355338096618652, "global_step": 379996, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1896142959594727, "global_step": 379997, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1445517539978027, "global_step": 379998, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.114495277404785, "global_step": 379999, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.116865873336792, "global_step": 380000, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1027519702911377, "global_step": 380001, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.9845335483551025, "global_step": 380002, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0968546867370605, "global_step": 380003, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0739991664886475, "global_step": 380004, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.168870210647583, "global_step": 380005, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1108317375183105, "global_step": 380006, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.9490684270858765, "global_step": 380007, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.111189842224121, "global_step": 380008, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.172252655029297, "global_step": 380009, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.123826503753662, "global_step": 380010, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.090723991394043, "global_step": 380011, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.071262836456299, "global_step": 380012, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.080096960067749, "global_step": 380013, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1066291332244873, "global_step": 380014, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.177347183227539, "global_step": 380015, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0509908199310303, "global_step": 380016, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.053077459335327, "global_step": 380017, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1470186710357666, "global_step": 380018, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.084089994430542, "global_step": 380019, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1032893657684326, "global_step": 380020, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.150937080383301, "global_step": 380021, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0303144454956055, "global_step": 380022, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0650405883789062, "global_step": 380023, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0676777362823486, "global_step": 380024, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0772392749786377, "global_step": 380025, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0450940132141113, "global_step": 380026, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0826032161712646, "global_step": 380027, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.067152500152588, "global_step": 380028, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0365073680877686, "global_step": 380029, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.075477361679077, "global_step": 380030, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.088883399963379, "global_step": 380031, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.028606653213501, "global_step": 380032, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0683789253234863, "global_step": 380033, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.109822988510132, "global_step": 380034, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0680911540985107, "global_step": 380035, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.108818531036377, "global_step": 380036, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.05741024017334, "global_step": 380037, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0830235481262207, "global_step": 380038, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.974304437637329, "global_step": 380039, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.074908494949341, "global_step": 380040, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.150257110595703, "global_step": 380041, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0877225399017334, "global_step": 380042, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.104179620742798, "global_step": 380043, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1969563961029053, "global_step": 380044, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.041199207305908, "global_step": 380045, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0392677783966064, "global_step": 380046, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0099265575408936, "global_step": 380047, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.071678638458252, "global_step": 380048, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.082653045654297, "global_step": 380049, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.078850507736206, "global_step": 380050, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1858410835266113, "global_step": 380051, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.006884813308716, "global_step": 380052, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.178392171859741, "global_step": 380053, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.089750051498413, "global_step": 380054, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1570496559143066, "global_step": 380055, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.079188108444214, "global_step": 380056, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.060683250427246, "global_step": 380057, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0698628425598145, "global_step": 380058, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0442349910736084, "global_step": 380059, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.046504020690918, "global_step": 380060, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.184767007827759, "global_step": 380061, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0241434574127197, "global_step": 380062, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0922818183898926, "global_step": 380063, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.120784282684326, "global_step": 380064, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.015329360961914, "global_step": 380065, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.083217144012451, "global_step": 380066, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.067894220352173, "global_step": 380067, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1555421352386475, "global_step": 380068, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0989115238189697, "global_step": 380069, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.9681744575500488, "global_step": 380070, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0947420597076416, "global_step": 380071, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.150338888168335, "global_step": 380072, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.087068557739258, "global_step": 380073, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1797447204589844, "global_step": 380074, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0823757648468018, "global_step": 380075, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.060180902481079, "global_step": 380076, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1986677646636963, "global_step": 380077, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.096130132675171, "global_step": 380078, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1427667140960693, "global_step": 380079, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.137263298034668, "global_step": 380080, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.055844306945801, "global_step": 380081, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1372225284576416, "global_step": 380082, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.054354667663574, "global_step": 380083, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1357483863830566, "global_step": 380084, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.099990129470825, "global_step": 380085, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.039149522781372, "global_step": 380086, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1356325149536133, "global_step": 380087, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0480782985687256, "global_step": 380088, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.127392530441284, "global_step": 380089, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1351981163024902, "global_step": 380090, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1497621536254883, "global_step": 380091, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1795694828033447, "global_step": 380092, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0512192249298096, "global_step": 380093, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.017713785171509, "global_step": 380094, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.112562656402588, "global_step": 380095, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0917859077453613, "global_step": 380096, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.162839651107788, "global_step": 380097, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1122498512268066, "global_step": 380098, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0925979614257812, "global_step": 380099, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.127927780151367, "global_step": 380100, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.076284646987915, "global_step": 380101, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.098442554473877, "global_step": 380102, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0594539642333984, "global_step": 380103, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0558836460113525, "global_step": 380104, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.213338851928711, "global_step": 380105, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.15561842918396, "global_step": 380106, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0260400772094727, "global_step": 380107, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.133570671081543, "global_step": 380108, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0285844802856445, "global_step": 380109, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1105270385742188, "global_step": 380110, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.134742498397827, "global_step": 380111, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1167709827423096, "global_step": 380112, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.125673770904541, "global_step": 380113, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.146566152572632, "global_step": 380114, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.088695526123047, "global_step": 380115, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0760252475738525, "global_step": 380116, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1365859508514404, "global_step": 380117, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.099271059036255, "global_step": 380118, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0806362628936768, "global_step": 380119, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.02896785736084, "global_step": 380120, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.9726015329360962, "global_step": 380121, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1039538383483887, "global_step": 380122, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1794402599334717, "global_step": 380123, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0552802085876465, "global_step": 380124, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1189022064208984, "global_step": 380125, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1118202209472656, "global_step": 380126, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.069516897201538, "global_step": 380127, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0982513427734375, "global_step": 380128, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1319661140441895, "global_step": 380129, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.097428560256958, "global_step": 380130, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.093510150909424, "global_step": 380131, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1336798667907715, "global_step": 380132, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.2347218990325928, "global_step": 380133, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.12326717376709, "global_step": 380134, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0295608043670654, "global_step": 380135, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.010782480239868, "global_step": 380136, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1113719940185547, "global_step": 380137, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1254966259002686, "global_step": 380138, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.087298631668091, "global_step": 380139, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0170373916625977, "global_step": 380140, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.138401746749878, "global_step": 380141, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0246472358703613, "global_step": 380142, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1114540100097656, "global_step": 380143, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0411124229431152, "global_step": 380144, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.090946912765503, "global_step": 380145, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0623865127563477, "global_step": 380146, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0752384662628174, "global_step": 380147, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0010883808135986, "global_step": 380148, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0323421955108643, "global_step": 380149, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0699520111083984, "global_step": 380150, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.09245228767395, "global_step": 380151, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1350274085998535, "global_step": 380152, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.044776201248169, "global_step": 380153, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0390563011169434, "global_step": 380154, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.158693313598633, "global_step": 380155, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0661704540252686, "global_step": 380156, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.033109426498413, "global_step": 380157, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0597074031829834, "global_step": 380158, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1318740844726562, "global_step": 380159, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.100221633911133, "global_step": 380160, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1085333824157715, "global_step": 380161, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0995776653289795, "global_step": 380162, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1329445838928223, "global_step": 380163, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.119732141494751, "global_step": 380164, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.050001621246338, "global_step": 380165, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1291418075561523, "global_step": 380166, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0952072143554688, "global_step": 380167, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.155146598815918, "global_step": 380168, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0369179248809814, "global_step": 380169, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.150613784790039, "global_step": 380170, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1315128803253174, "global_step": 380171, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1318609714508057, "global_step": 380172, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.125211000442505, "global_step": 380173, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1679494380950928, "global_step": 380174, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.053570508956909, "global_step": 380175, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.084841012954712, "global_step": 380176, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1012685298919678, "global_step": 380177, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1158175468444824, "global_step": 380178, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0647385120391846, "global_step": 380179, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.128427028656006, "global_step": 380180, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.018155813217163, "global_step": 380181, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1151020526885986, "global_step": 380182, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0199239253997803, "global_step": 380183, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0637195110321045, "global_step": 380184, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.012040376663208, "global_step": 380185, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.00994610786438, "global_step": 380186, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.047792434692383, "global_step": 380187, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0444211959838867, "global_step": 380188, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1128690242767334, "global_step": 380189, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.067988395690918, "global_step": 380190, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.129213333129883, "global_step": 380191, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1493003368377686, "global_step": 380192, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0286455154418945, "global_step": 380193, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1387786865234375, "global_step": 380194, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0994269847869873, "global_step": 380195, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0651891231536865, "global_step": 380196, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1584417819976807, "global_step": 380197, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.098146438598633, "global_step": 380198, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1494052410125732, "global_step": 380199, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0761044025421143, "global_step": 380200, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.065804958343506, "global_step": 380201, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.115057945251465, "global_step": 380202, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.072887420654297, "global_step": 380203, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1383297443389893, "global_step": 380204, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.088902473449707, "global_step": 380205, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1402199268341064, "global_step": 380206, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1454837322235107, "global_step": 380207, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.111989736557007, "global_step": 380208, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.154963970184326, "global_step": 380209, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0750434398651123, "global_step": 380210, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.024367332458496, "global_step": 380211, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0868585109710693, "global_step": 380212, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.109498977661133, "global_step": 380213, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0938761234283447, "global_step": 380214, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1110787391662598, "global_step": 380215, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1093196868896484, "global_step": 380216, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1020288467407227, "global_step": 380217, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.084259033203125, "global_step": 380218, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.035565137863159, "global_step": 380219, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.082429885864258, "global_step": 380220, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0795912742614746, "global_step": 380221, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1892333030700684, "global_step": 380222, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.147233724594116, "global_step": 380223, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1324992179870605, "global_step": 380224, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1324050426483154, "global_step": 380225, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.998111367225647, "global_step": 380226, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.945380687713623, "global_step": 380227, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1641714572906494, "global_step": 380228, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.9669443368911743, "global_step": 380229, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.040699005126953, "global_step": 380230, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0612406730651855, "global_step": 380231, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.067462205886841, "global_step": 380232, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.071995735168457, "global_step": 380233, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.108614921569824, "global_step": 380234, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.013303518295288, "global_step": 380235, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.9943753480911255, "global_step": 380236, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.076484203338623, "global_step": 380237, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.088941812515259, "global_step": 380238, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.087857484817505, "global_step": 380239, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0493431091308594, "global_step": 380240, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0805165767669678, "global_step": 380241, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1108381748199463, "global_step": 380242, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1101975440979004, "global_step": 380243, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.157109022140503, "global_step": 380244, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.089538335800171, "global_step": 380245, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0973057746887207, "global_step": 380246, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.068218946456909, "global_step": 380247, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1249303817749023, "global_step": 380248, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0848591327667236, "global_step": 380249, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1164629459381104, "global_step": 380250, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0052318572998047, "global_step": 380251, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.074115037918091, "global_step": 380252, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1309008598327637, "global_step": 380253, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1295764446258545, "global_step": 380254, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0892579555511475, "global_step": 380255, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0431113243103027, "global_step": 380256, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1317386627197266, "global_step": 380257, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0748207569122314, "global_step": 380258, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0990822315216064, "global_step": 380259, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.171459913253784, "global_step": 380260, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1075098514556885, "global_step": 380261, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.027358055114746, "global_step": 380262, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0751888751983643, "global_step": 380263, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1324009895324707, "global_step": 380264, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0605838298797607, "global_step": 380265, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1063032150268555, "global_step": 380266, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.026434898376465, "global_step": 380267, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1472151279449463, "global_step": 380268, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.195375919342041, "global_step": 380269, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0803983211517334, "global_step": 380270, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0488264560699463, "global_step": 380271, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0350046157836914, "global_step": 380272, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.164109468460083, "global_step": 380273, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.160006284713745, "global_step": 380274, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1420164108276367, "global_step": 380275, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0067601203918457, "global_step": 380276, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1488492488861084, "global_step": 380277, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.134779453277588, "global_step": 380278, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.163510322570801, "global_step": 380279, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0908894538879395, "global_step": 380280, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.136569023132324, "global_step": 380281, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.147167444229126, "global_step": 380282, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0624709129333496, "global_step": 380283, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0217719078063965, "global_step": 380284, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0364091396331787, "global_step": 380285, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0798428058624268, "global_step": 380286, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1081595420837402, "global_step": 380287, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.060945987701416, "global_step": 380288, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.116295576095581, "global_step": 380289, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.099787473678589, "global_step": 380290, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.039090633392334, "global_step": 380291, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.062377452850342, "global_step": 380292, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1228561401367188, "global_step": 380293, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1628315448760986, "global_step": 380294, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.105224370956421, "global_step": 380295, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1419694423675537, "global_step": 380296, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.157869338989258, "global_step": 380297, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.141453266143799, "global_step": 380298, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1116864681243896, "global_step": 380299, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0692098140716553, "global_step": 380300, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.081094741821289, "global_step": 380301, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1052680015563965, "global_step": 380302, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.086320400238037, "global_step": 380303, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1378729343414307, "global_step": 380304, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1232614517211914, "global_step": 380305, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.219358205795288, "global_step": 380306, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0683116912841797, "global_step": 380307, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.135643482208252, "global_step": 380308, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1101913452148438, "global_step": 380309, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.162412166595459, "global_step": 380310, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0512893199920654, "global_step": 380311, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.123952627182007, "global_step": 380312, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.143150806427002, "global_step": 380313, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.158947706222534, "global_step": 380314, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1241402626037598, "global_step": 380315, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0856924057006836, "global_step": 380316, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1030232906341553, "global_step": 380317, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0099289417266846, "global_step": 380318, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.122894287109375, "global_step": 380319, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.9987034797668457, "global_step": 380320, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.104797840118408, "global_step": 380321, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.134359359741211, "global_step": 380322, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0260119438171387, "global_step": 380323, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.142652750015259, "global_step": 380324, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1000852584838867, "global_step": 380325, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.038412570953369, "global_step": 380326, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1385741233825684, "global_step": 380327, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.025743246078491, "global_step": 380328, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.09911847114563, "global_step": 380329, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.080129623413086, "global_step": 380330, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0698814392089844, "global_step": 380331, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1435673236846924, "global_step": 380332, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0630645751953125, "global_step": 380333, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.143934488296509, "global_step": 380334, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.026442766189575, "global_step": 380335, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0047411918640137, "global_step": 380336, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.163484811782837, "global_step": 380337, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1028101444244385, "global_step": 380338, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.079237461090088, "global_step": 380339, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.111025094985962, "global_step": 380340, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1418368816375732, "global_step": 380341, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.093104124069214, "global_step": 380342, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0147600173950195, "global_step": 380343, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0600247383117676, "global_step": 380344, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.064824342727661, "global_step": 380345, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1297130584716797, "global_step": 380346, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1012158393859863, "global_step": 380347, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.152428388595581, "global_step": 380348, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.9917020797729492, "global_step": 380349, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1271934509277344, "global_step": 380350, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.115774393081665, "global_step": 380351, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.075408458709717, "global_step": 380352, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.065835475921631, "global_step": 380353, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1359102725982666, "global_step": 380354, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.027554512023926, "global_step": 380355, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0317835807800293, "global_step": 380356, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.094043493270874, "global_step": 380357, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.9814321994781494, "global_step": 380358, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.161371946334839, "global_step": 380359, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.09500789642334, "global_step": 380360, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1988489627838135, "global_step": 380361, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.05401349067688, "global_step": 380362, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.169304370880127, "global_step": 380363, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.057500123977661, "global_step": 380364, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0612845420837402, "global_step": 380365, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0082671642303467, "global_step": 380366, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1242449283599854, "global_step": 380367, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.170539617538452, "global_step": 380368, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0488476753234863, "global_step": 380369, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.107667922973633, "global_step": 380370, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0280325412750244, "global_step": 380371, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.132359266281128, "global_step": 380372, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1052768230438232, "global_step": 380373, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1234729290008545, "global_step": 380374, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.14951753616333, "global_step": 380375, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1723275184631348, "global_step": 380376, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.9762777090072632, "global_step": 380377, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.157823085784912, "global_step": 380378, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.148620843887329, "global_step": 380379, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1149322986602783, "global_step": 380380, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0431289672851562, "global_step": 380381, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.103053092956543, "global_step": 380382, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.058335542678833, "global_step": 380383, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0718915462493896, "global_step": 380384, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.107708692550659, "global_step": 380385, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.066319227218628, "global_step": 380386, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0849761962890625, "global_step": 380387, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1693572998046875, "global_step": 380388, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0537478923797607, "global_step": 380389, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.053250312805176, "global_step": 380390, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.091493606567383, "global_step": 380391, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1673777103424072, "global_step": 380392, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.2175283432006836, "global_step": 380393, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1124391555786133, "global_step": 380394, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1337339878082275, "global_step": 380395, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.010751962661743, "global_step": 380396, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0941555500030518, "global_step": 380397, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.110372304916382, "global_step": 380398, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.12914776802063, "global_step": 380399, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.081184148788452, "global_step": 380400, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.005707263946533, "global_step": 380401, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.180992603302002, "global_step": 380402, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1556942462921143, "global_step": 380403, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.098830223083496, "global_step": 380404, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0874240398406982, "global_step": 380405, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0691986083984375, "global_step": 380406, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.125612258911133, "global_step": 380407, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1698808670043945, "global_step": 380408, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.183502435684204, "global_step": 380409, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.176358222961426, "global_step": 380410, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.107438802719116, "global_step": 380411, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1080331802368164, "global_step": 380412, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.141653060913086, "global_step": 380413, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.152991771697998, "global_step": 380414, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0988171100616455, "global_step": 380415, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.133368968963623, "global_step": 380416, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1077330112457275, "global_step": 380417, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1667826175689697, "global_step": 380418, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1556849479675293, "global_step": 380419, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0868115425109863, "global_step": 380420, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.075561761856079, "global_step": 380421, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.140986204147339, "global_step": 380422, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.9417643547058105, "global_step": 380423, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0577616691589355, "global_step": 380424, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.169692039489746, "global_step": 380425, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1092946529388428, "global_step": 380426, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1511640548706055, "global_step": 380427, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0400853157043457, "global_step": 380428, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0877842903137207, "global_step": 380429, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0947585105895996, "global_step": 380430, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.121330738067627, "global_step": 380431, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1732373237609863, "global_step": 380432, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1302237510681152, "global_step": 380433, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1170458793640137, "global_step": 380434, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.056706428527832, "global_step": 380435, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.064862012863159, "global_step": 380436, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1501259803771973, "global_step": 380437, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.128542900085449, "global_step": 380438, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1104822158813477, "global_step": 380439, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.091503858566284, "global_step": 380440, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.154381275177002, "global_step": 380441, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.112755298614502, "global_step": 380442, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.094435691833496, "global_step": 380443, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0899581909179688, "global_step": 380444, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.076809883117676, "global_step": 380445, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.080875873565674, "global_step": 380446, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.162330150604248, "global_step": 380447, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1170432567596436, "global_step": 380448, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.194096326828003, "global_step": 380449, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1213126182556152, "global_step": 380450, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1211698055267334, "global_step": 380451, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1421103477478027, "global_step": 380452, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.027637481689453, "global_step": 380453, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0471909046173096, "global_step": 380454, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0615479946136475, "global_step": 380455, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0538675785064697, "global_step": 380456, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.054605007171631, "global_step": 380457, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0929176807403564, "global_step": 380458, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0176031589508057, "global_step": 380459, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0527689456939697, "global_step": 380460, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0915279388427734, "global_step": 380461, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.093129873275757, "global_step": 380462, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1270980834960938, "global_step": 380463, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1522321701049805, "global_step": 380464, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1282670497894287, "global_step": 380465, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.152686834335327, "global_step": 380466, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.149718999862671, "global_step": 380467, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1518561840057373, "global_step": 380468, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1576924324035645, "global_step": 380469, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.083738088607788, "global_step": 380470, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.137409210205078, "global_step": 380471, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.108121633529663, "global_step": 380472, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.037526845932007, "global_step": 380473, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0389444828033447, "global_step": 380474, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.257847309112549, "global_step": 380475, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.112584114074707, "global_step": 380476, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0724172592163086, "global_step": 380477, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.130250930786133, "global_step": 380478, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1051018238067627, "global_step": 380479, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0927536487579346, "global_step": 380480, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1251442432403564, "global_step": 380481, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0835814476013184, "global_step": 380482, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.169293165206909, "global_step": 380483, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.132678747177124, "global_step": 380484, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1245224475860596, "global_step": 380485, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.9779621362686157, "global_step": 380486, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.085742950439453, "global_step": 380487, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0861175060272217, "global_step": 380488, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0505361557006836, "global_step": 380489, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.009972333908081, "global_step": 380490, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0883901119232178, "global_step": 380491, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1284215450286865, "global_step": 380492, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1441822052001953, "global_step": 380493, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.178452968597412, "global_step": 380494, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.185654640197754, "global_step": 380495, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.159367322921753, "global_step": 380496, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1018991470336914, "global_step": 380497, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1588146686553955, "global_step": 380498, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0614898204803467, "global_step": 380499, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0744738578796387, "global_step": 380500, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0865726470947266, "global_step": 380501, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1450836658477783, "global_step": 380502, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0672943592071533, "global_step": 380503, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1782515048980713, "global_step": 380504, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.9975190162658691, "global_step": 380505, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1113362312316895, "global_step": 380506, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1239590644836426, "global_step": 380507, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0960233211517334, "global_step": 380508, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.141873598098755, "global_step": 380509, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.2140567302703857, "global_step": 380510, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0453274250030518, "global_step": 380511, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.022129774093628, "global_step": 380512, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.142509698867798, "global_step": 380513, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.106825828552246, "global_step": 380514, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.096858024597168, "global_step": 380515, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.108597755432129, "global_step": 380516, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0576274394989014, "global_step": 380517, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1364693641662598, "global_step": 380518, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1763343811035156, "global_step": 380519, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1849379539489746, "global_step": 380520, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0831198692321777, "global_step": 380521, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1223597526550293, "global_step": 380522, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.087372064590454, "global_step": 380523, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1601481437683105, "global_step": 380524, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.149688720703125, "global_step": 380525, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.106586217880249, "global_step": 380526, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.147028684616089, "global_step": 380527, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.167436122894287, "global_step": 380528, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.086676597595215, "global_step": 380529, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.065725326538086, "global_step": 380530, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.125, "global_step": 380531, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0810699462890625, "global_step": 380532, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.105250120162964, "global_step": 380533, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.094383955001831, "global_step": 380534, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.2128307819366455, "global_step": 380535, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0652949810028076, "global_step": 380536, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.031655788421631, "global_step": 380537, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1052653789520264, "global_step": 380538, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.162830114364624, "global_step": 380539, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0866522789001465, "global_step": 380540, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.13271427154541, "global_step": 380541, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.107032537460327, "global_step": 380542, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.10524845123291, "global_step": 380543, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0386440753936768, "global_step": 380544, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.007431745529175, "global_step": 380545, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.090151786804199, "global_step": 380546, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.047407388687134, "global_step": 380547, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.098992347717285, "global_step": 380548, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.067310333251953, "global_step": 380549, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0451366901397705, "global_step": 380550, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.101841688156128, "global_step": 380551, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1199088096618652, "global_step": 380552, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.119770050048828, "global_step": 380553, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1581504344940186, "global_step": 380554, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.107255458831787, "global_step": 380555, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.108429193496704, "global_step": 380556, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0878474712371826, "global_step": 380557, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.165940046310425, "global_step": 380558, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.10917329788208, "global_step": 380559, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1360604763031006, "global_step": 380560, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.105423927307129, "global_step": 380561, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.117384910583496, "global_step": 380562, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.203505039215088, "global_step": 380563, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.064995050430298, "global_step": 380564, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.052220582962036, "global_step": 380565, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0835447311401367, "global_step": 380566, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0575530529022217, "global_step": 380567, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1677663326263428, "global_step": 380568, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.093825340270996, "global_step": 380569, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.055755853652954, "global_step": 380570, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1174867153167725, "global_step": 380571, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0896289348602295, "global_step": 380572, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1496779918670654, "global_step": 380573, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0603511333465576, "global_step": 380574, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1949260234832764, "global_step": 380575, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0747556686401367, "global_step": 380576, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1869616508483887, "global_step": 380577, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.114946126937866, "global_step": 380578, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0797598361968994, "global_step": 380579, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.095658540725708, "global_step": 380580, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0510077476501465, "global_step": 380581, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1430304050445557, "global_step": 380582, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0555739402770996, "global_step": 380583, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0423858165740967, "global_step": 380584, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0523674488067627, "global_step": 380585, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.107470750808716, "global_step": 380586, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.188058376312256, "global_step": 380587, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.095921277999878, "global_step": 380588, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.074599027633667, "global_step": 380589, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1866977214813232, "global_step": 380590, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0886638164520264, "global_step": 380591, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.016394853591919, "global_step": 380592, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.088463068008423, "global_step": 380593, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0832648277282715, "global_step": 380594, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0948896408081055, "global_step": 380595, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.098762273788452, "global_step": 380596, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.2101521492004395, "global_step": 380597, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0571627616882324, "global_step": 380598, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.061448574066162, "global_step": 380599, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.045264482498169, "global_step": 380600, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.171297073364258, "global_step": 380601, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0131278038024902, "global_step": 380602, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.131080389022827, "global_step": 380603, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.103412628173828, "global_step": 380604, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0813562870025635, "global_step": 380605, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.109910249710083, "global_step": 380606, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1324901580810547, "global_step": 380607, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1044182777404785, "global_step": 380608, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1595091819763184, "global_step": 380609, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.089730739593506, "global_step": 380610, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1214680671691895, "global_step": 380611, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1614878177642822, "global_step": 380612, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1539502143859863, "global_step": 380613, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0208241939544678, "global_step": 380614, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.07887864112854, "global_step": 380615, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.150470733642578, "global_step": 380616, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1737418174743652, "global_step": 380617, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0697262287139893, "global_step": 380618, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.048182249069214, "global_step": 380619, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0799643993377686, "global_step": 380620, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.07206654548645, "global_step": 380621, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.196061134338379, "global_step": 380622, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1251039505004883, "global_step": 380623, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.140137195587158, "global_step": 380624, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1277055740356445, "global_step": 380625, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0175700187683105, "global_step": 380626, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0962283611297607, "global_step": 380627, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1546547412872314, "global_step": 380628, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0310416221618652, "global_step": 380629, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1887154579162598, "global_step": 380630, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1362648010253906, "global_step": 380631, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0981714725494385, "global_step": 380632, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.10591721534729, "global_step": 380633, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.2325706481933594, "global_step": 380634, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0885815620422363, "global_step": 380635, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0119776725769043, "global_step": 380636, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.106558322906494, "global_step": 380637, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.018979549407959, "global_step": 380638, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1199402809143066, "global_step": 380639, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.099830389022827, "global_step": 380640, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1527416706085205, "global_step": 380641, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1324117183685303, "global_step": 380642, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1162593364715576, "global_step": 380643, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.138303518295288, "global_step": 380644, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.156426429748535, "global_step": 380645, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1942687034606934, "global_step": 380646, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.091862440109253, "global_step": 380647, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.101118803024292, "global_step": 380648, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.077535629272461, "global_step": 380649, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.168675661087036, "global_step": 380650, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1557703018188477, "global_step": 380651, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.060853958129883, "global_step": 380652, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0829310417175293, "global_step": 380653, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1367287635803223, "global_step": 380654, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.137941360473633, "global_step": 380655, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1292974948883057, "global_step": 380656, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0932252407073975, "global_step": 380657, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.054417371749878, "global_step": 380658, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0726068019866943, "global_step": 380659, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.13588547706604, "global_step": 380660, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.157745361328125, "global_step": 380661, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0460946559906006, "global_step": 380662, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0524356365203857, "global_step": 380663, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.162551164627075, "global_step": 380664, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0917961597442627, "global_step": 380665, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1827666759490967, "global_step": 380666, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.127117156982422, "global_step": 380667, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1159212589263916, "global_step": 380668, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0908560752868652, "global_step": 380669, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.9739487171173096, "global_step": 380670, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1346137523651123, "global_step": 380671, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1502938270568848, "global_step": 380672, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.100715160369873, "global_step": 380673, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.118255138397217, "global_step": 380674, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.187182664871216, "global_step": 380675, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.118931293487549, "global_step": 380676, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.101874828338623, "global_step": 380677, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.063657522201538, "global_step": 380678, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.081010580062866, "global_step": 380679, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0635697841644287, "global_step": 380680, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.111870765686035, "global_step": 380681, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.094775676727295, "global_step": 380682, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0779268741607666, "global_step": 380683, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1492059230804443, "global_step": 380684, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1459875106811523, "global_step": 380685, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1096386909484863, "global_step": 380686, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1177661418914795, "global_step": 380687, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1752843856811523, "global_step": 380688, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1395108699798584, "global_step": 380689, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0700523853302, "global_step": 380690, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.147322416305542, "global_step": 380691, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.06260347366333, "global_step": 380692, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.146322727203369, "global_step": 380693, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1588664054870605, "global_step": 380694, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.134359359741211, "global_step": 380695, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.111359119415283, "global_step": 380696, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1503493785858154, "global_step": 380697, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1009104251861572, "global_step": 380698, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0510456562042236, "global_step": 380699, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0987446308135986, "global_step": 380700, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.023268222808838, "global_step": 380701, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.029308795928955, "global_step": 380702, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1526894569396973, "global_step": 380703, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1781938076019287, "global_step": 380704, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.082279682159424, "global_step": 380705, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.158324956893921, "global_step": 380706, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0673539638519287, "global_step": 380707, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0453855991363525, "global_step": 380708, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1462478637695312, "global_step": 380709, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.162224769592285, "global_step": 380710, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.080657482147217, "global_step": 380711, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1983728408813477, "global_step": 380712, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.15061616897583, "global_step": 380713, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0421550273895264, "global_step": 380714, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1048078536987305, "global_step": 380715, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1493582725524902, "global_step": 380716, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0945262908935547, "global_step": 380717, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.100550413131714, "global_step": 380718, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.080975294113159, "global_step": 380719, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.9901278018951416, "global_step": 380720, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1426398754119873, "global_step": 380721, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1011219024658203, "global_step": 380722, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.130784034729004, "global_step": 380723, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1829841136932373, "global_step": 380724, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.080512046813965, "global_step": 380725, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.055781841278076, "global_step": 380726, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.089143753051758, "global_step": 380727, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1263821125030518, "global_step": 380728, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1106128692626953, "global_step": 380729, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0665066242218018, "global_step": 380730, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.043984889984131, "global_step": 380731, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1237337589263916, "global_step": 380732, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.082864284515381, "global_step": 380733, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0995125770568848, "global_step": 380734, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1047897338867188, "global_step": 380735, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1825027465820312, "global_step": 380736, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.077770709991455, "global_step": 380737, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.127742290496826, "global_step": 380738, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.060196876525879, "global_step": 380739, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1121790409088135, "global_step": 380740, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.059650421142578, "global_step": 380741, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.116612434387207, "global_step": 380742, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1335010528564453, "global_step": 380743, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1600089073181152, "global_step": 380744, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1327037811279297, "global_step": 380745, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1132559776306152, "global_step": 380746, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.085906982421875, "global_step": 380747, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.111628293991089, "global_step": 380748, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.108989953994751, "global_step": 380749, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.118797779083252, "global_step": 380750, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.098407745361328, "global_step": 380751, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.14736008644104, "global_step": 380752, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0635488033294678, "global_step": 380753, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.189483404159546, "global_step": 380754, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1404387950897217, "global_step": 380755, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.12014102935791, "global_step": 380756, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.068934440612793, "global_step": 380757, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1329562664031982, "global_step": 380758, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1687521934509277, "global_step": 380759, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1014657020568848, "global_step": 380760, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0786328315734863, "global_step": 380761, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0732357501983643, "global_step": 380762, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.055234670639038, "global_step": 380763, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1099843978881836, "global_step": 380764, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.2039623260498047, "global_step": 380765, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.064419984817505, "global_step": 380766, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.140155792236328, "global_step": 380767, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.153231382369995, "global_step": 380768, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.049941062927246, "global_step": 380769, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.166123390197754, "global_step": 380770, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0638182163238525, "global_step": 380771, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1226754188537598, "global_step": 380772, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0750603675842285, "global_step": 380773, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0369441509246826, "global_step": 380774, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.124145746231079, "global_step": 380775, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0402352809906006, "global_step": 380776, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1097588539123535, "global_step": 380777, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1203808784484863, "global_step": 380778, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1148672103881836, "global_step": 380779, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.182871103286743, "global_step": 380780, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0922861099243164, "global_step": 380781, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0358424186706543, "global_step": 380782, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.164400577545166, "global_step": 380783, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0962159633636475, "global_step": 380784, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0643765926361084, "global_step": 380785, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1757636070251465, "global_step": 380786, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1111598014831543, "global_step": 380787, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1897287368774414, "global_step": 380788, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.07192325592041, "global_step": 380789, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1508548259735107, "global_step": 380790, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.129762887954712, "global_step": 380791, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0789284706115723, "global_step": 380792, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.036168098449707, "global_step": 380793, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.088705539703369, "global_step": 380794, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.153233289718628, "global_step": 380795, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.13154935836792, "global_step": 380796, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1487040519714355, "global_step": 380797, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.112992763519287, "global_step": 380798, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.071761131286621, "global_step": 380799, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1300015449523926, "global_step": 380800, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1357386112213135, "global_step": 380801, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1657145023345947, "global_step": 380802, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.139270305633545, "global_step": 380803, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0540378093719482, "global_step": 380804, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0968291759490967, "global_step": 380805, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1083920001983643, "global_step": 380806, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.105463743209839, "global_step": 380807, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1725404262542725, "global_step": 380808, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.127568483352661, "global_step": 380809, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1844863891601562, "global_step": 380810, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1531805992126465, "global_step": 380811, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.084703207015991, "global_step": 380812, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.173729419708252, "global_step": 380813, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1432435512542725, "global_step": 380814, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.187309980392456, "global_step": 380815, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1252808570861816, "global_step": 380816, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0614209175109863, "global_step": 380817, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.121758222579956, "global_step": 380818, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1892242431640625, "global_step": 380819, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1297388076782227, "global_step": 380820, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1483309268951416, "global_step": 380821, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.206099510192871, "global_step": 380822, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.067570209503174, "global_step": 380823, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.083900213241577, "global_step": 380824, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.198092460632324, "global_step": 380825, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.251948118209839, "global_step": 380826, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.148040771484375, "global_step": 380827, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1003079414367676, "global_step": 380828, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.092729091644287, "global_step": 380829, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0758705139160156, "global_step": 380830, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0631277561187744, "global_step": 380831, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1585726737976074, "global_step": 380832, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.17153263092041, "global_step": 380833, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0999033451080322, "global_step": 380834, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.223519802093506, "global_step": 380835, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0626585483551025, "global_step": 380836, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0245397090911865, "global_step": 380837, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.2367963790893555, "global_step": 380838, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1007423400878906, "global_step": 380839, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1280384063720703, "global_step": 380840, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1368534564971924, "global_step": 380841, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.103177070617676, "global_step": 380842, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1351499557495117, "global_step": 380843, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1688263416290283, "global_step": 380844, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1014556884765625, "global_step": 380845, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1042370796203613, "global_step": 380846, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1745877265930176, "global_step": 380847, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0973305702209473, "global_step": 380848, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.161438226699829, "global_step": 380849, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.106187582015991, "global_step": 380850, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1094918251037598, "global_step": 380851, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1150054931640625, "global_step": 380852, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1061363220214844, "global_step": 380853, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1152708530426025, "global_step": 380854, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.039583921432495, "global_step": 380855, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.084989547729492, "global_step": 380856, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.194871425628662, "global_step": 380857, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0844130516052246, "global_step": 380858, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1314265727996826, "global_step": 380859, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.130793809890747, "global_step": 380860, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1021292209625244, "global_step": 380861, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.123286724090576, "global_step": 380862, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1021502017974854, "global_step": 380863, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.126760959625244, "global_step": 380864, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.103179931640625, "global_step": 380865, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0271694660186768, "global_step": 380866, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.197498083114624, "global_step": 380867, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1441683769226074, "global_step": 380868, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1288042068481445, "global_step": 380869, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.191357135772705, "global_step": 380870, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1066339015960693, "global_step": 380871, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0160927772521973, "global_step": 380872, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1024765968322754, "global_step": 380873, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.08626389503479, "global_step": 380874, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0874686241149902, "global_step": 380875, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.088494300842285, "global_step": 380876, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.200773239135742, "global_step": 380877, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.111166477203369, "global_step": 380878, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0805678367614746, "global_step": 380879, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.2450454235076904, "global_step": 380880, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1360549926757812, "global_step": 380881, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.107996940612793, "global_step": 380882, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.196254253387451, "global_step": 380883, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.2272355556488037, "global_step": 380884, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.183175802230835, "global_step": 380885, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1866214275360107, "global_step": 380886, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1264398097991943, "global_step": 380887, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1135640144348145, "global_step": 380888, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1680121421813965, "global_step": 380889, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.118184804916382, "global_step": 380890, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.086867332458496, "global_step": 380891, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1240031719207764, "global_step": 380892, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0805137157440186, "global_step": 380893, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.131422996520996, "global_step": 380894, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.997943639755249, "global_step": 380895, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.04408597946167, "global_step": 380896, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0789618492126465, "global_step": 380897, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1406984329223633, "global_step": 380898, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0923683643341064, "global_step": 380899, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.142495632171631, "global_step": 380900, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.064166307449341, "global_step": 380901, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.027951240539551, "global_step": 380902, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.12788462638855, "global_step": 380903, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1526994705200195, "global_step": 380904, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.155518054962158, "global_step": 380905, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0196821689605713, "global_step": 380906, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0803098678588867, "global_step": 380907, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.088805675506592, "global_step": 380908, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.062717914581299, "global_step": 380909, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.170109748840332, "global_step": 380910, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.110684633255005, "global_step": 380911, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1299736499786377, "global_step": 380912, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.02204966545105, "global_step": 380913, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.118189573287964, "global_step": 380914, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0437259674072266, "global_step": 380915, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.9898483753204346, "global_step": 380916, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1450743675231934, "global_step": 380917, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.184542417526245, "global_step": 380918, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.124481678009033, "global_step": 380919, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1660549640655518, "global_step": 380920, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1346917152404785, "global_step": 380921, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.9987661838531494, "global_step": 380922, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0839381217956543, "global_step": 380923, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1098110675811768, "global_step": 380924, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.153733253479004, "global_step": 380925, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.036287307739258, "global_step": 380926, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1166164875030518, "global_step": 380927, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1900699138641357, "global_step": 380928, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.2100846767425537, "global_step": 380929, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1698663234710693, "global_step": 380930, "epoch": 742, "lr": 5e-05}
{"train_loss": 1.9959369897842407, "global_step": 380931, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1174709796905518, "global_step": 380932, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0323779582977295, "global_step": 380933, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.098047971725464, "global_step": 380934, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.2736029624938965, "global_step": 380935, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1249802112579346, "global_step": 380936, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.103914260864258, "global_step": 380937, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.109931230545044, "global_step": 380938, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1258819103240967, "global_step": 380939, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.081472635269165, "global_step": 380940, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.163511037826538, "global_step": 380941, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.0905027389526367, "global_step": 380942, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.081380605697632, "global_step": 380943, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1544973850250244, "global_step": 380944, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.113215446472168, "global_step": 380945, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.16557240486145, "global_step": 380946, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.288189172744751, "global_step": 380947, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1535627841949463, "global_step": 380948, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1043825149536133, "global_step": 380949, "epoch": 742, "lr": 5e-05}
{"train_loss": 2.1361467838287354, "global_step": 380950, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.079097032546997, "global_step": 380951, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1500484943389893, "global_step": 380952, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0936896800994873, "global_step": 380953, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.2219831943511963, "global_step": 380954, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1040375232696533, "global_step": 380955, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.104822874069214, "global_step": 380956, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.047243595123291, "global_step": 380957, "epoch": 743, "lr": 5e-05}
{"train_loss": 1.9827998876571655, "global_step": 380958, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.058812379837036, "global_step": 380959, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1204421520233154, "global_step": 380960, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0252768993377686, "global_step": 380961, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1666455268859863, "global_step": 380962, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0938732624053955, "global_step": 380963, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1045265197753906, "global_step": 380964, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.070342540740967, "global_step": 380965, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.106426477432251, "global_step": 380966, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1157519817352295, "global_step": 380967, "epoch": 743, "lr": 5e-05}
{"train_loss": 1.9916436672210693, "global_step": 380968, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.097376823425293, "global_step": 380969, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.170959949493408, "global_step": 380970, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0775699615478516, "global_step": 380971, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.097712516784668, "global_step": 380972, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1789426803588867, "global_step": 380973, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.136899948120117, "global_step": 380974, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1305644512176514, "global_step": 380975, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.033994674682617, "global_step": 380976, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.097123146057129, "global_step": 380977, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.085466146469116, "global_step": 380978, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.085475444793701, "global_step": 380979, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0444581508636475, "global_step": 380980, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.162428855895996, "global_step": 380981, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.152031660079956, "global_step": 380982, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.123579978942871, "global_step": 380983, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.127454996109009, "global_step": 380984, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0870110988616943, "global_step": 380985, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.077984571456909, "global_step": 380986, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0845417976379395, "global_step": 380987, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.013923168182373, "global_step": 380988, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.158916473388672, "global_step": 380989, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1408820152282715, "global_step": 380990, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1264536380767822, "global_step": 380991, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.100836992263794, "global_step": 380992, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0433263778686523, "global_step": 380993, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0395946502685547, "global_step": 380994, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.114577531814575, "global_step": 380995, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.129657506942749, "global_step": 380996, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1105828285217285, "global_step": 380997, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0708987712860107, "global_step": 380998, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1230576038360596, "global_step": 380999, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0231611728668213, "global_step": 381000, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0785374641418457, "global_step": 381001, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.012547016143799, "global_step": 381002, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.093085765838623, "global_step": 381003, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1267025470733643, "global_step": 381004, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1338346004486084, "global_step": 381005, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1210310459136963, "global_step": 381006, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.138784885406494, "global_step": 381007, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.044032573699951, "global_step": 381008, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.052668809890747, "global_step": 381009, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.034764289855957, "global_step": 381010, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1066863536834717, "global_step": 381011, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0665814876556396, "global_step": 381012, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.143942356109619, "global_step": 381013, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0773398876190186, "global_step": 381014, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1080710887908936, "global_step": 381015, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0214037895202637, "global_step": 381016, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.003390073776245, "global_step": 381017, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.13327693939209, "global_step": 381018, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0953636169433594, "global_step": 381019, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1172101497650146, "global_step": 381020, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.012014865875244, "global_step": 381021, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.09263014793396, "global_step": 381022, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0741517543792725, "global_step": 381023, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0823521614074707, "global_step": 381024, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1177191734313965, "global_step": 381025, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.03361177444458, "global_step": 381026, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0946669578552246, "global_step": 381027, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0212807655334473, "global_step": 381028, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0602974891662598, "global_step": 381029, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.156303644180298, "global_step": 381030, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0413691997528076, "global_step": 381031, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1584904193878174, "global_step": 381032, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.062227487564087, "global_step": 381033, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0886027812957764, "global_step": 381034, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.075042486190796, "global_step": 381035, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.126055955886841, "global_step": 381036, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.14966082572937, "global_step": 381037, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0721821784973145, "global_step": 381038, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0834224224090576, "global_step": 381039, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1259632110595703, "global_step": 381040, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0483970642089844, "global_step": 381041, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0962612628936768, "global_step": 381042, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0227880477905273, "global_step": 381043, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1417737007141113, "global_step": 381044, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0157220363616943, "global_step": 381045, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0082497596740723, "global_step": 381046, "epoch": 743, "lr": 5e-05}
{"train_loss": 1.9276937246322632, "global_step": 381047, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.142817974090576, "global_step": 381048, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.140103578567505, "global_step": 381049, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1504478454589844, "global_step": 381050, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1203792095184326, "global_step": 381051, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.066723585128784, "global_step": 381052, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1615662574768066, "global_step": 381053, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1309256553649902, "global_step": 381054, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1263999938964844, "global_step": 381055, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.125426769256592, "global_step": 381056, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.179212808609009, "global_step": 381057, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.200165271759033, "global_step": 381058, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0917577743530273, "global_step": 381059, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.045879364013672, "global_step": 381060, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.110274076461792, "global_step": 381061, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0761969089508057, "global_step": 381062, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0627224445343018, "global_step": 381063, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.004225254058838, "global_step": 381064, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0987792015075684, "global_step": 381065, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1420888900756836, "global_step": 381066, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0230162143707275, "global_step": 381067, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.095707893371582, "global_step": 381068, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0811145305633545, "global_step": 381069, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.08772349357605, "global_step": 381070, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.067065954208374, "global_step": 381071, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0393881797790527, "global_step": 381072, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0548369884490967, "global_step": 381073, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1087911128997803, "global_step": 381074, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.148420572280884, "global_step": 381075, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.086543560028076, "global_step": 381076, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0626699924468994, "global_step": 381077, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.20194935798645, "global_step": 381078, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.050894021987915, "global_step": 381079, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.048039674758911, "global_step": 381080, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1374199390411377, "global_step": 381081, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1827638149261475, "global_step": 381082, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.137979745864868, "global_step": 381083, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.197437286376953, "global_step": 381084, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0966384410858154, "global_step": 381085, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1224379539489746, "global_step": 381086, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.059535264968872, "global_step": 381087, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0854997634887695, "global_step": 381088, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0940182209014893, "global_step": 381089, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.090313196182251, "global_step": 381090, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.17887806892395, "global_step": 381091, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.040541410446167, "global_step": 381092, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1259665489196777, "global_step": 381093, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1008780002593994, "global_step": 381094, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1073105335235596, "global_step": 381095, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.107081413269043, "global_step": 381096, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.139697790145874, "global_step": 381097, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1087229251861572, "global_step": 381098, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.117316722869873, "global_step": 381099, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1012723445892334, "global_step": 381100, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.017076253890991, "global_step": 381101, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.105785608291626, "global_step": 381102, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.102464437484741, "global_step": 381103, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.08677339553833, "global_step": 381104, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1256043910980225, "global_step": 381105, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.030362129211426, "global_step": 381106, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.095311403274536, "global_step": 381107, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.027160406112671, "global_step": 381108, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.029366970062256, "global_step": 381109, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1027796268463135, "global_step": 381110, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.067655563354492, "global_step": 381111, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0984485149383545, "global_step": 381112, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.086719512939453, "global_step": 381113, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0792789459228516, "global_step": 381114, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0946877002716064, "global_step": 381115, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0825986862182617, "global_step": 381116, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.110043525695801, "global_step": 381117, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1487698554992676, "global_step": 381118, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1185872554779053, "global_step": 381119, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.115158796310425, "global_step": 381120, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0841588973999023, "global_step": 381121, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0984458923339844, "global_step": 381122, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.101741075515747, "global_step": 381123, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0410990715026855, "global_step": 381124, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1246204376220703, "global_step": 381125, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1150403022766113, "global_step": 381126, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1558449268341064, "global_step": 381127, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.060380697250366, "global_step": 381128, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1259543895721436, "global_step": 381129, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.080515146255493, "global_step": 381130, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.068049430847168, "global_step": 381131, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.120628833770752, "global_step": 381132, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.109266519546509, "global_step": 381133, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0559747219085693, "global_step": 381134, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.05153751373291, "global_step": 381135, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1496224403381348, "global_step": 381136, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1634905338287354, "global_step": 381137, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.14316463470459, "global_step": 381138, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1118578910827637, "global_step": 381139, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.00307559967041, "global_step": 381140, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0299134254455566, "global_step": 381141, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.084897041320801, "global_step": 381142, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.122894763946533, "global_step": 381143, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1181042194366455, "global_step": 381144, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0898311138153076, "global_step": 381145, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.058652639389038, "global_step": 381146, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0694692134857178, "global_step": 381147, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.069060802459717, "global_step": 381148, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.085724353790283, "global_step": 381149, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1687605381011963, "global_step": 381150, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.12195086479187, "global_step": 381151, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.201185464859009, "global_step": 381152, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.192868709564209, "global_step": 381153, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.141657829284668, "global_step": 381154, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0413739681243896, "global_step": 381155, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.098545789718628, "global_step": 381156, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1236023902893066, "global_step": 381157, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.103091239929199, "global_step": 381158, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1422576904296875, "global_step": 381159, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.096296787261963, "global_step": 381160, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0116002559661865, "global_step": 381161, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.094728469848633, "global_step": 381162, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.008591651916504, "global_step": 381163, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1887128353118896, "global_step": 381164, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1423251628875732, "global_step": 381165, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1255619525909424, "global_step": 381166, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0712127685546875, "global_step": 381167, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.079439878463745, "global_step": 381168, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.2091140747070312, "global_step": 381169, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1053378582000732, "global_step": 381170, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0727856159210205, "global_step": 381171, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1704325675964355, "global_step": 381172, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.135072946548462, "global_step": 381173, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1356875896453857, "global_step": 381174, "epoch": 743, "lr": 5e-05}
{"train_loss": 1.9760898351669312, "global_step": 381175, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1839091777801514, "global_step": 381176, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0418453216552734, "global_step": 381177, "epoch": 743, "lr": 5e-05}
{"train_loss": 1.9908664226531982, "global_step": 381178, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.145601511001587, "global_step": 381179, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.195765256881714, "global_step": 381180, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.078437328338623, "global_step": 381181, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0742571353912354, "global_step": 381182, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.038630723953247, "global_step": 381183, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0665385723114014, "global_step": 381184, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1278843879699707, "global_step": 381185, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0148305892944336, "global_step": 381186, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0507795810699463, "global_step": 381187, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0781781673431396, "global_step": 381188, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.154695510864258, "global_step": 381189, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.046159505844116, "global_step": 381190, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1662745475769043, "global_step": 381191, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.085599899291992, "global_step": 381192, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0793304443359375, "global_step": 381193, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.033602714538574, "global_step": 381194, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.118762731552124, "global_step": 381195, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1079132556915283, "global_step": 381196, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1124775409698486, "global_step": 381197, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.084399938583374, "global_step": 381198, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.066817045211792, "global_step": 381199, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.126436471939087, "global_step": 381200, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1173136234283447, "global_step": 381201, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.032337188720703, "global_step": 381202, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.134606122970581, "global_step": 381203, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.091902494430542, "global_step": 381204, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.135666608810425, "global_step": 381205, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0338423252105713, "global_step": 381206, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.167985439300537, "global_step": 381207, "epoch": 743, "lr": 5e-05}
{"train_loss": 1.9448497295379639, "global_step": 381208, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.136401891708374, "global_step": 381209, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.069401264190674, "global_step": 381210, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0976662635803223, "global_step": 381211, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.111609697341919, "global_step": 381212, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0340735912323, "global_step": 381213, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.049370288848877, "global_step": 381214, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0611870288848877, "global_step": 381215, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0917325019836426, "global_step": 381216, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0859501361846924, "global_step": 381217, "epoch": 743, "lr": 5e-05}
{"train_loss": 1.9671590328216553, "global_step": 381218, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.128594160079956, "global_step": 381219, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1991097927093506, "global_step": 381220, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.048581838607788, "global_step": 381221, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0790188312530518, "global_step": 381222, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.133099317550659, "global_step": 381223, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.119492530822754, "global_step": 381224, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.064577102661133, "global_step": 381225, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.066431999206543, "global_step": 381226, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0368189811706543, "global_step": 381227, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0332584381103516, "global_step": 381228, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1358284950256348, "global_step": 381229, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.109461784362793, "global_step": 381230, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0125980377197266, "global_step": 381231, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1002347469329834, "global_step": 381232, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1359212398529053, "global_step": 381233, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.228163957595825, "global_step": 381234, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.099775791168213, "global_step": 381235, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1998283863067627, "global_step": 381236, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1185247898101807, "global_step": 381237, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.090477705001831, "global_step": 381238, "epoch": 743, "lr": 5e-05}
{"train_loss": 1.991806149482727, "global_step": 381239, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0759940147399902, "global_step": 381240, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1777896881103516, "global_step": 381241, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0871312618255615, "global_step": 381242, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.18609881401062, "global_step": 381243, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1513898372650146, "global_step": 381244, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0971322059631348, "global_step": 381245, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.07901930809021, "global_step": 381246, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0901734828948975, "global_step": 381247, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.100579261779785, "global_step": 381248, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.041687250137329, "global_step": 381249, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.076042413711548, "global_step": 381250, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.043586015701294, "global_step": 381251, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0807411670684814, "global_step": 381252, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.130882978439331, "global_step": 381253, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0686752796173096, "global_step": 381254, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0491228103637695, "global_step": 381255, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.2142930030822754, "global_step": 381256, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1605136394500732, "global_step": 381257, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0619564056396484, "global_step": 381258, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0974960327148438, "global_step": 381259, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1924421787261963, "global_step": 381260, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1345620155334473, "global_step": 381261, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1468148231506348, "global_step": 381262, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.100236177444458, "global_step": 381263, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.117159128189087, "global_step": 381264, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.110809564590454, "global_step": 381265, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.087736129760742, "global_step": 381266, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1091203689575195, "global_step": 381267, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.103701591491699, "global_step": 381268, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.03887677192688, "global_step": 381269, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.096545696258545, "global_step": 381270, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.114392042160034, "global_step": 381271, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.110140085220337, "global_step": 381272, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0902113914489746, "global_step": 381273, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0596179962158203, "global_step": 381274, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0524425506591797, "global_step": 381275, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0416219234466553, "global_step": 381276, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.086775302886963, "global_step": 381277, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0702338218688965, "global_step": 381278, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0377447605133057, "global_step": 381279, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.079035520553589, "global_step": 381280, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.119580030441284, "global_step": 381281, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.100576877593994, "global_step": 381282, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.065772533416748, "global_step": 381283, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.137889862060547, "global_step": 381284, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1730992794036865, "global_step": 381285, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0916011333465576, "global_step": 381286, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0318310260772705, "global_step": 381287, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0574440956115723, "global_step": 381288, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1295204162597656, "global_step": 381289, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.053696632385254, "global_step": 381290, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.067284345626831, "global_step": 381291, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1070590019226074, "global_step": 381292, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1521408557891846, "global_step": 381293, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0961573123931885, "global_step": 381294, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0468924045562744, "global_step": 381295, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.093989133834839, "global_step": 381296, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1317837238311768, "global_step": 381297, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0717310905456543, "global_step": 381298, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.143407106399536, "global_step": 381299, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1006600856781006, "global_step": 381300, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.144376039505005, "global_step": 381301, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1205999851226807, "global_step": 381302, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0523643493652344, "global_step": 381303, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1103367805480957, "global_step": 381304, "epoch": 743, "lr": 5e-05}
{"train_loss": 1.9765563011169434, "global_step": 381305, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0496530532836914, "global_step": 381306, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.121121883392334, "global_step": 381307, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1647427082061768, "global_step": 381308, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.053321599960327, "global_step": 381309, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.237630605697632, "global_step": 381310, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0943918228149414, "global_step": 381311, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.060380220413208, "global_step": 381312, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1179983615875244, "global_step": 381313, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1139566898345947, "global_step": 381314, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1166727542877197, "global_step": 381315, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.153069257736206, "global_step": 381316, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0570411682128906, "global_step": 381317, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1066036224365234, "global_step": 381318, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1251237392425537, "global_step": 381319, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.105056047439575, "global_step": 381320, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.140091896057129, "global_step": 381321, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0750277042388916, "global_step": 381322, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.122317314147949, "global_step": 381323, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1313891410827637, "global_step": 381324, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.109254837036133, "global_step": 381325, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.009125232696533, "global_step": 381326, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.130021810531616, "global_step": 381327, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0322864055633545, "global_step": 381328, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.100916862487793, "global_step": 381329, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.088926315307617, "global_step": 381330, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0510306358337402, "global_step": 381331, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0346481800079346, "global_step": 381332, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.155625581741333, "global_step": 381333, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.126763105392456, "global_step": 381334, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0461504459381104, "global_step": 381335, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1312758922576904, "global_step": 381336, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1208066940307617, "global_step": 381337, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.2056021690368652, "global_step": 381338, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1438095569610596, "global_step": 381339, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.154003620147705, "global_step": 381340, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.193941831588745, "global_step": 381341, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.144549608230591, "global_step": 381342, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.112382411956787, "global_step": 381343, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0429608821868896, "global_step": 381344, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.066199779510498, "global_step": 381345, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1251742839813232, "global_step": 381346, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.117572784423828, "global_step": 381347, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0255112648010254, "global_step": 381348, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.141519546508789, "global_step": 381349, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1473796367645264, "global_step": 381350, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.09378981590271, "global_step": 381351, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1164042949676514, "global_step": 381352, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1512484550476074, "global_step": 381353, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1108670234680176, "global_step": 381354, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.079318046569824, "global_step": 381355, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1651012897491455, "global_step": 381356, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0673110485076904, "global_step": 381357, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0898232460021973, "global_step": 381358, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0815439224243164, "global_step": 381359, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0767822265625, "global_step": 381360, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0957610607147217, "global_step": 381361, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0683085918426514, "global_step": 381362, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.120072603225708, "global_step": 381363, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.2013096809387207, "global_step": 381364, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.137592077255249, "global_step": 381365, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0824708938598633, "global_step": 381366, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0920372009277344, "global_step": 381367, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1018552780151367, "global_step": 381368, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0403547286987305, "global_step": 381369, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0416290760040283, "global_step": 381370, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1270976066589355, "global_step": 381371, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.118668794631958, "global_step": 381372, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1555542945861816, "global_step": 381373, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0802698135375977, "global_step": 381374, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0654690265655518, "global_step": 381375, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1379220485687256, "global_step": 381376, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.080507516860962, "global_step": 381377, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1415929794311523, "global_step": 381378, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.149991989135742, "global_step": 381379, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.101367712020874, "global_step": 381380, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.044283151626587, "global_step": 381381, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0979862213134766, "global_step": 381382, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0267252922058105, "global_step": 381383, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.2212893962860107, "global_step": 381384, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.104971408843994, "global_step": 381385, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.018606185913086, "global_step": 381386, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.051331043243408, "global_step": 381387, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0970458984375, "global_step": 381388, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.096224308013916, "global_step": 381389, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0413098335266113, "global_step": 381390, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0550990104675293, "global_step": 381391, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.15429949760437, "global_step": 381392, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1455721855163574, "global_step": 381393, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1024887561798096, "global_step": 381394, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.107936382293701, "global_step": 381395, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.15757417678833, "global_step": 381396, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1199567317962646, "global_step": 381397, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1738452911376953, "global_step": 381398, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1369991302490234, "global_step": 381399, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.087730884552002, "global_step": 381400, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0859813690185547, "global_step": 381401, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.166499137878418, "global_step": 381402, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0588066577911377, "global_step": 381403, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.069624662399292, "global_step": 381404, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1628623008728027, "global_step": 381405, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0987226963043213, "global_step": 381406, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0819873809814453, "global_step": 381407, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.087944984436035, "global_step": 381408, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1623499393463135, "global_step": 381409, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0775656700134277, "global_step": 381410, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.158268451690674, "global_step": 381411, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.010641574859619, "global_step": 381412, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1033005714416504, "global_step": 381413, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1508281230926514, "global_step": 381414, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.053534507751465, "global_step": 381415, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1364927291870117, "global_step": 381416, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1497607231140137, "global_step": 381417, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.035412549972534, "global_step": 381418, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0205271244049072, "global_step": 381419, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0562667846679688, "global_step": 381420, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1178743839263916, "global_step": 381421, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0249199867248535, "global_step": 381422, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.152780532836914, "global_step": 381423, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1586506366729736, "global_step": 381424, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.102834701538086, "global_step": 381425, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1326236724853516, "global_step": 381426, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.12662410736084, "global_step": 381427, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.096497058868408, "global_step": 381428, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.186960220336914, "global_step": 381429, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.134707450866699, "global_step": 381430, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1272711753845215, "global_step": 381431, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0802972316741943, "global_step": 381432, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1444082260131836, "global_step": 381433, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0604000091552734, "global_step": 381434, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.2117834091186523, "global_step": 381435, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.117373466491699, "global_step": 381436, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.118828058242798, "global_step": 381437, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1350960731506348, "global_step": 381438, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0633983612060547, "global_step": 381439, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.113725185394287, "global_step": 381440, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.147306442260742, "global_step": 381441, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0944864749908447, "global_step": 381442, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.193730354309082, "global_step": 381443, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.162177324295044, "global_step": 381444, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.115790367126465, "global_step": 381445, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0387182235717773, "global_step": 381446, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1683197021484375, "global_step": 381447, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.140063524246216, "global_step": 381448, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0809290409088135, "global_step": 381449, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1195337772369385, "global_step": 381450, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.115976095199585, "global_step": 381451, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1301794052124023, "global_step": 381452, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1308493614196777, "global_step": 381453, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.125156879425049, "global_step": 381454, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0361063480377197, "global_step": 381455, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0838565826416016, "global_step": 381456, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.103243589401245, "global_step": 381457, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0485668182373047, "global_step": 381458, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.146611452102661, "global_step": 381459, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.078875780105591, "global_step": 381460, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1501529216766357, "global_step": 381461, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.126551866531372, "global_step": 381462, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0575928688049316, "global_step": 381463, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1042301654815674, "global_step": 381464, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.129730701446533, "global_step": 381465, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1930673122406006, "global_step": 381466, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.091826915740967, "global_step": 381467, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.148015022277832, "global_step": 381468, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.156244993209839, "global_step": 381469, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.113354444503784, "global_step": 381470, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1823737621307373, "global_step": 381471, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.079361915588379, "global_step": 381472, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0670759677886963, "global_step": 381473, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1216835975646973, "global_step": 381474, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.092135190963745, "global_step": 381475, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0464026927948, "global_step": 381476, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1309711933135986, "global_step": 381477, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0517208576202393, "global_step": 381478, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1310787200927734, "global_step": 381479, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0599210262298584, "global_step": 381480, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.200608968734741, "global_step": 381481, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.149683952331543, "global_step": 381482, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1218044757843018, "global_step": 381483, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.09930419921875, "global_step": 381484, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0554118156433105, "global_step": 381485, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.066223621368408, "global_step": 381486, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1172232627868652, "global_step": 381487, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0681562423706055, "global_step": 381488, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0966265201568604, "global_step": 381489, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0631039142608643, "global_step": 381490, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.112792730331421, "global_step": 381491, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0972836017608643, "global_step": 381492, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1242334842681885, "global_step": 381493, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0900654792785645, "global_step": 381494, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.2333877086639404, "global_step": 381495, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1437737941741943, "global_step": 381496, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.085808038711548, "global_step": 381497, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.2261228561401367, "global_step": 381498, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0865135192871094, "global_step": 381499, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1326968669891357, "global_step": 381500, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1337177753448486, "global_step": 381501, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1983134746551514, "global_step": 381502, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.104259967803955, "global_step": 381503, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.106485366821289, "global_step": 381504, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1481757164001465, "global_step": 381505, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0801358222961426, "global_step": 381506, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1549034118652344, "global_step": 381507, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.076228618621826, "global_step": 381508, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0544350147247314, "global_step": 381509, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.219829559326172, "global_step": 381510, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.178537368774414, "global_step": 381511, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0277700424194336, "global_step": 381512, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.049037218093872, "global_step": 381513, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.2069084644317627, "global_step": 381514, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.2315473556518555, "global_step": 381515, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0748443603515625, "global_step": 381516, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1012074947357178, "global_step": 381517, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1635327339172363, "global_step": 381518, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0886003971099854, "global_step": 381519, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.123476266860962, "global_step": 381520, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0654468536376953, "global_step": 381521, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1032323837280273, "global_step": 381522, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.131418228149414, "global_step": 381523, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0778183937072754, "global_step": 381524, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.048151969909668, "global_step": 381525, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0971364974975586, "global_step": 381526, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0938267707824707, "global_step": 381527, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.087193489074707, "global_step": 381528, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0196475982666016, "global_step": 381529, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.079378843307495, "global_step": 381530, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.061426877975464, "global_step": 381531, "epoch": 743, "lr": 5e-05}
{"train_loss": 1.9904236793518066, "global_step": 381532, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0975160598754883, "global_step": 381533, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0750012397766113, "global_step": 381534, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.089566707611084, "global_step": 381535, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.090106964111328, "global_step": 381536, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0693202018737793, "global_step": 381537, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1102633476257324, "global_step": 381538, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.129556655883789, "global_step": 381539, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1094040870666504, "global_step": 381540, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0501351356506348, "global_step": 381541, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1874258518218994, "global_step": 381542, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.218564033508301, "global_step": 381543, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1185145378112793, "global_step": 381544, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1057193279266357, "global_step": 381545, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1041760444641113, "global_step": 381546, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.140167474746704, "global_step": 381547, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.061575174331665, "global_step": 381548, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.133420705795288, "global_step": 381549, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.125444173812866, "global_step": 381550, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1216208934783936, "global_step": 381551, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1561906337738037, "global_step": 381552, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1998190879821777, "global_step": 381553, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.175262212753296, "global_step": 381554, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.106536626815796, "global_step": 381555, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.130880832672119, "global_step": 381556, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0839524269104004, "global_step": 381557, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1466472148895264, "global_step": 381558, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1176302433013916, "global_step": 381559, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1549594402313232, "global_step": 381560, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.144437074661255, "global_step": 381561, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0792200565338135, "global_step": 381562, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1165761947631836, "global_step": 381563, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.057111978530884, "global_step": 381564, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1324498653411865, "global_step": 381565, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0604896545410156, "global_step": 381566, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.097917079925537, "global_step": 381567, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.120579957962036, "global_step": 381568, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1777853965759277, "global_step": 381569, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.126403331756592, "global_step": 381570, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.100691080093384, "global_step": 381571, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.2342441082000732, "global_step": 381572, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1114115715026855, "global_step": 381573, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.090029716491699, "global_step": 381574, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0376741886138916, "global_step": 381575, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.170755624771118, "global_step": 381576, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1744723320007324, "global_step": 381577, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1301639080047607, "global_step": 381578, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0901036262512207, "global_step": 381579, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1990792751312256, "global_step": 381580, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.089906930923462, "global_step": 381581, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.084737539291382, "global_step": 381582, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.058016777038574, "global_step": 381583, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0635077953338623, "global_step": 381584, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.148926019668579, "global_step": 381585, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0509321689605713, "global_step": 381586, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1296191215515137, "global_step": 381587, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.068018674850464, "global_step": 381588, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.092974901199341, "global_step": 381589, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1506540775299072, "global_step": 381590, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1719913482666016, "global_step": 381591, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1009089946746826, "global_step": 381592, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.141671657562256, "global_step": 381593, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.056612968444824, "global_step": 381594, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.100151538848877, "global_step": 381595, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.093146562576294, "global_step": 381596, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.156924247741699, "global_step": 381597, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0784406661987305, "global_step": 381598, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.051302671432495, "global_step": 381599, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0614335536956787, "global_step": 381600, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1175339221954346, "global_step": 381601, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.139099597930908, "global_step": 381602, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1345653533935547, "global_step": 381603, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1988768577575684, "global_step": 381604, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0710642337799072, "global_step": 381605, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.075286865234375, "global_step": 381606, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0349931716918945, "global_step": 381607, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.131197690963745, "global_step": 381608, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0225577354431152, "global_step": 381609, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1041407585144043, "global_step": 381610, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0589234828948975, "global_step": 381611, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1727795600891113, "global_step": 381612, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0825774669647217, "global_step": 381613, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1158297061920166, "global_step": 381614, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.19439435005188, "global_step": 381615, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0541043281555176, "global_step": 381616, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.017104148864746, "global_step": 381617, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.183676242828369, "global_step": 381618, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1644821166992188, "global_step": 381619, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.172719717025757, "global_step": 381620, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.062342643737793, "global_step": 381621, "epoch": 743, "lr": 5e-05}
{"train_loss": 1.9527941942214966, "global_step": 381622, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1258394718170166, "global_step": 381623, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.057377576828003, "global_step": 381624, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.108989953994751, "global_step": 381625, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.099860429763794, "global_step": 381626, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0611860752105713, "global_step": 381627, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0998106002807617, "global_step": 381628, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.142676591873169, "global_step": 381629, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.2414655685424805, "global_step": 381630, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.143612861633301, "global_step": 381631, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0616209506988525, "global_step": 381632, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.18056321144104, "global_step": 381633, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.164896249771118, "global_step": 381634, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0144007205963135, "global_step": 381635, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.119417905807495, "global_step": 381636, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1791508197784424, "global_step": 381637, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.035839557647705, "global_step": 381638, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0371851921081543, "global_step": 381639, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0615715980529785, "global_step": 381640, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.059385061264038, "global_step": 381641, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.106886386871338, "global_step": 381642, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.105595827102661, "global_step": 381643, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.239682197570801, "global_step": 381644, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1510422229766846, "global_step": 381645, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1094377040863037, "global_step": 381646, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0505306720733643, "global_step": 381647, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.011075019836426, "global_step": 381648, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0805013179779053, "global_step": 381649, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.087085723876953, "global_step": 381650, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.122607469558716, "global_step": 381651, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0576512813568115, "global_step": 381652, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1284608840942383, "global_step": 381653, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.078742027282715, "global_step": 381654, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0263490676879883, "global_step": 381655, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1151435375213623, "global_step": 381656, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.103123426437378, "global_step": 381657, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.078324794769287, "global_step": 381658, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.043281078338623, "global_step": 381659, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.040674924850464, "global_step": 381660, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.04249906539917, "global_step": 381661, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.129138946533203, "global_step": 381662, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.057417869567871, "global_step": 381663, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1280128955841064, "global_step": 381664, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1272058486938477, "global_step": 381665, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1420047283172607, "global_step": 381666, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0787570476531982, "global_step": 381667, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1093780994415283, "global_step": 381668, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1467175483703613, "global_step": 381669, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.139510154724121, "global_step": 381670, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.090975761413574, "global_step": 381671, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0014865398406982, "global_step": 381672, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.157731294631958, "global_step": 381673, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.044304847717285, "global_step": 381674, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.169827699661255, "global_step": 381675, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0239808559417725, "global_step": 381676, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.136976957321167, "global_step": 381677, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1455020904541016, "global_step": 381678, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1972222328186035, "global_step": 381679, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1330440044403076, "global_step": 381680, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.111586332321167, "global_step": 381681, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0617051124572754, "global_step": 381682, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0327610969543457, "global_step": 381683, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.040802478790283, "global_step": 381684, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0891997814178467, "global_step": 381685, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.172226905822754, "global_step": 381686, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0745558738708496, "global_step": 381687, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.083057403564453, "global_step": 381688, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1076135635375977, "global_step": 381689, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.115755081176758, "global_step": 381690, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.114527702331543, "global_step": 381691, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0770697593688965, "global_step": 381692, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0594305992126465, "global_step": 381693, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.104578971862793, "global_step": 381694, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.022199869155884, "global_step": 381695, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0901741981506348, "global_step": 381696, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0105507373809814, "global_step": 381697, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.114032030105591, "global_step": 381698, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0822126865386963, "global_step": 381699, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1212263107299805, "global_step": 381700, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1843178272247314, "global_step": 381701, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.066084384918213, "global_step": 381702, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.119675636291504, "global_step": 381703, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0826470851898193, "global_step": 381704, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.170569658279419, "global_step": 381705, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0941245555877686, "global_step": 381706, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1036195755004883, "global_step": 381707, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.052079677581787, "global_step": 381708, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.035170555114746, "global_step": 381709, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1730120182037354, "global_step": 381710, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.020368814468384, "global_step": 381711, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.2098467350006104, "global_step": 381712, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0759365558624268, "global_step": 381713, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1531753540039062, "global_step": 381714, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1618218421936035, "global_step": 381715, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0995051860809326, "global_step": 381716, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0450360774993896, "global_step": 381717, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.057598114013672, "global_step": 381718, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.10453724861145, "global_step": 381719, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.111304521560669, "global_step": 381720, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0439891815185547, "global_step": 381721, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.125509023666382, "global_step": 381722, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.119075059890747, "global_step": 381723, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1545474529266357, "global_step": 381724, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1223020553588867, "global_step": 381725, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0506300926208496, "global_step": 381726, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.13875675201416, "global_step": 381727, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1084144115448, "global_step": 381728, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.149379253387451, "global_step": 381729, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0446712970733643, "global_step": 381730, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0638678073883057, "global_step": 381731, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0650548934936523, "global_step": 381732, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.128727436065674, "global_step": 381733, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1166062355041504, "global_step": 381734, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.083918809890747, "global_step": 381735, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0982766151428223, "global_step": 381736, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1370491981506348, "global_step": 381737, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1785385608673096, "global_step": 381738, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1266989707946777, "global_step": 381739, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.263535499572754, "global_step": 381740, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1451194286346436, "global_step": 381741, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0837385654449463, "global_step": 381742, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.130767822265625, "global_step": 381743, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.138505697250366, "global_step": 381744, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.147979497909546, "global_step": 381745, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.078461170196533, "global_step": 381746, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.195427179336548, "global_step": 381747, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0487003326416016, "global_step": 381748, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0515010356903076, "global_step": 381749, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.181147575378418, "global_step": 381750, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.150679111480713, "global_step": 381751, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1205220222473145, "global_step": 381752, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.076090097427368, "global_step": 381753, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.037466287612915, "global_step": 381754, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1716902256011963, "global_step": 381755, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1158788204193115, "global_step": 381756, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.111788272857666, "global_step": 381757, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1845006942749023, "global_step": 381758, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0973739624023438, "global_step": 381759, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0878169536590576, "global_step": 381760, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.170565605163574, "global_step": 381761, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0495333671569824, "global_step": 381762, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.05356764793396, "global_step": 381763, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.147048234939575, "global_step": 381764, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.207336902618408, "global_step": 381765, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1638412475585938, "global_step": 381766, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0787951946258545, "global_step": 381767, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1756598949432373, "global_step": 381768, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0268735885620117, "global_step": 381769, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1234171390533447, "global_step": 381770, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.093564033508301, "global_step": 381771, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.192058563232422, "global_step": 381772, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0545847415924072, "global_step": 381773, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0615227222442627, "global_step": 381774, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1231837272644043, "global_step": 381775, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1057443618774414, "global_step": 381776, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.109585762023926, "global_step": 381777, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0397050380706787, "global_step": 381778, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.094799757003784, "global_step": 381779, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.181804656982422, "global_step": 381780, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.134667158126831, "global_step": 381781, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1303365230560303, "global_step": 381782, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.108297824859619, "global_step": 381783, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.093302011489868, "global_step": 381784, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.040623903274536, "global_step": 381785, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.102287769317627, "global_step": 381786, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.119007110595703, "global_step": 381787, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1914050579071045, "global_step": 381788, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.106071710586548, "global_step": 381789, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1350018978118896, "global_step": 381790, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.119586706161499, "global_step": 381791, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1545419692993164, "global_step": 381792, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0509891510009766, "global_step": 381793, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1550590991973877, "global_step": 381794, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0895628929138184, "global_step": 381795, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1726369857788086, "global_step": 381796, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1143038272857666, "global_step": 381797, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1266379356384277, "global_step": 381798, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0008292198181152, "global_step": 381799, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.120857000350952, "global_step": 381800, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0890984535217285, "global_step": 381801, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0906665325164795, "global_step": 381802, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1398653984069824, "global_step": 381803, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.110786199569702, "global_step": 381804, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1200528144836426, "global_step": 381805, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.056260824203491, "global_step": 381806, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0967118740081787, "global_step": 381807, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1240036487579346, "global_step": 381808, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1141626834869385, "global_step": 381809, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.084535598754883, "global_step": 381810, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0665650367736816, "global_step": 381811, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0500917434692383, "global_step": 381812, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1712536811828613, "global_step": 381813, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.055912733078003, "global_step": 381814, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0518994331359863, "global_step": 381815, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.162651538848877, "global_step": 381816, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0886995792388916, "global_step": 381817, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1664247512817383, "global_step": 381818, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.154878616333008, "global_step": 381819, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1385812759399414, "global_step": 381820, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.121466875076294, "global_step": 381821, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.143484354019165, "global_step": 381822, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.152735710144043, "global_step": 381823, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.045341968536377, "global_step": 381824, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.071911334991455, "global_step": 381825, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0557308197021484, "global_step": 381826, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.083944082260132, "global_step": 381827, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0744125843048096, "global_step": 381828, "epoch": 743, "lr": 5e-05}
{"train_loss": 1.9799724817276, "global_step": 381829, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1522364616394043, "global_step": 381830, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.071530818939209, "global_step": 381831, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.16025710105896, "global_step": 381832, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1200308799743652, "global_step": 381833, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.169826030731201, "global_step": 381834, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1920177936553955, "global_step": 381835, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.132929801940918, "global_step": 381836, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.096724271774292, "global_step": 381837, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0993335247039795, "global_step": 381838, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1743123531341553, "global_step": 381839, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.104721784591675, "global_step": 381840, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1411633491516113, "global_step": 381841, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1022865772247314, "global_step": 381842, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1431987285614014, "global_step": 381843, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1167826652526855, "global_step": 381844, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1791322231292725, "global_step": 381845, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1071271896362305, "global_step": 381846, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1526598930358887, "global_step": 381847, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0258255004882812, "global_step": 381848, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1168158054351807, "global_step": 381849, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0905704498291016, "global_step": 381850, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1026110649108887, "global_step": 381851, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.089979410171509, "global_step": 381852, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0997867584228516, "global_step": 381853, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1400082111358643, "global_step": 381854, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.219712495803833, "global_step": 381855, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0837082862854004, "global_step": 381856, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.2139058113098145, "global_step": 381857, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.146249294281006, "global_step": 381858, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0362908840179443, "global_step": 381859, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.2192156314849854, "global_step": 381860, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.120453357696533, "global_step": 381861, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.136934995651245, "global_step": 381862, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1495068073272705, "global_step": 381863, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1155614852905273, "global_step": 381864, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.162132740020752, "global_step": 381865, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1068499088287354, "global_step": 381866, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0953547954559326, "global_step": 381867, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.134711742401123, "global_step": 381868, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0521419048309326, "global_step": 381869, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0295920372009277, "global_step": 381870, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1916286945343018, "global_step": 381871, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0945444107055664, "global_step": 381872, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.23455810546875, "global_step": 381873, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0422580242156982, "global_step": 381874, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.07957124710083, "global_step": 381875, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1102631092071533, "global_step": 381876, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.096048593521118, "global_step": 381877, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0609917640686035, "global_step": 381878, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.102806806564331, "global_step": 381879, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.155092716217041, "global_step": 381880, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1433985233306885, "global_step": 381881, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1316349506378174, "global_step": 381882, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1145877838134766, "global_step": 381883, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1464388370513916, "global_step": 381884, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.108783483505249, "global_step": 381885, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0320401191711426, "global_step": 381886, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.216963052749634, "global_step": 381887, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1348142623901367, "global_step": 381888, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.213319778442383, "global_step": 381889, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0429229736328125, "global_step": 381890, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.2105906009674072, "global_step": 381891, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.05761456489563, "global_step": 381892, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0309455394744873, "global_step": 381893, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.083164930343628, "global_step": 381894, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.144416570663452, "global_step": 381895, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.040773868560791, "global_step": 381896, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1742193698883057, "global_step": 381897, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.20491623878479, "global_step": 381898, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.026090145111084, "global_step": 381899, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1026451587677, "global_step": 381900, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0513534545898438, "global_step": 381901, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.101935625076294, "global_step": 381902, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1615829467773438, "global_step": 381903, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0189619064331055, "global_step": 381904, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.136876344680786, "global_step": 381905, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1421399116516113, "global_step": 381906, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1272242069244385, "global_step": 381907, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0968713760375977, "global_step": 381908, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1290390491485596, "global_step": 381909, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1297600269317627, "global_step": 381910, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1305723190307617, "global_step": 381911, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0604491233825684, "global_step": 381912, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1332056522369385, "global_step": 381913, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.040900707244873, "global_step": 381914, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1212356090545654, "global_step": 381915, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.0600600242614746, "global_step": 381916, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1581361293792725, "global_step": 381917, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1043248176574707, "global_step": 381918, "epoch": 743, "lr": 5e-05}
{"train_loss": 2.1625711917877197, "global_step": 381919, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1082887649536133, "global_step": 381920, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.060307025909424, "global_step": 381921, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1274492740631104, "global_step": 381922, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0497331619262695, "global_step": 381923, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.003141164779663, "global_step": 381924, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.203740119934082, "global_step": 381925, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.100226640701294, "global_step": 381926, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1038358211517334, "global_step": 381927, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.080902576446533, "global_step": 381928, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0749127864837646, "global_step": 381929, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0979535579681396, "global_step": 381930, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1059861183166504, "global_step": 381931, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.041069269180298, "global_step": 381932, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.018787384033203, "global_step": 381933, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0455081462860107, "global_step": 381934, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1787192821502686, "global_step": 381935, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1428582668304443, "global_step": 381936, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0735456943511963, "global_step": 381937, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.04059100151062, "global_step": 381938, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.121030807495117, "global_step": 381939, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.046462297439575, "global_step": 381940, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.156074047088623, "global_step": 381941, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2177324295043945, "global_step": 381942, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0179214477539062, "global_step": 381943, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1503260135650635, "global_step": 381944, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.039182186126709, "global_step": 381945, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.031226873397827, "global_step": 381946, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.064241409301758, "global_step": 381947, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1670567989349365, "global_step": 381948, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.222501277923584, "global_step": 381949, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0599589347839355, "global_step": 381950, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1151785850524902, "global_step": 381951, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.073850154876709, "global_step": 381952, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0849339962005615, "global_step": 381953, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.179123640060425, "global_step": 381954, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.089350938796997, "global_step": 381955, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.101875066757202, "global_step": 381956, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.083867073059082, "global_step": 381957, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.106174945831299, "global_step": 381958, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1062746047973633, "global_step": 381959, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1531271934509277, "global_step": 381960, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.017961025238037, "global_step": 381961, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.015127182006836, "global_step": 381962, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.009828805923462, "global_step": 381963, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.071089029312134, "global_step": 381964, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1828389167785645, "global_step": 381965, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0623886585235596, "global_step": 381966, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.004201889038086, "global_step": 381967, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1156773567199707, "global_step": 381968, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.078937292098999, "global_step": 381969, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0992331504821777, "global_step": 381970, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0614609718322754, "global_step": 381971, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1083784103393555, "global_step": 381972, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.118227958679199, "global_step": 381973, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0794332027435303, "global_step": 381974, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.055115222930908, "global_step": 381975, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1498360633850098, "global_step": 381976, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.073108673095703, "global_step": 381977, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.039626121520996, "global_step": 381978, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.141310214996338, "global_step": 381979, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.04815411567688, "global_step": 381980, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1032936573028564, "global_step": 381981, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1030333042144775, "global_step": 381982, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.068276882171631, "global_step": 381983, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1326515674591064, "global_step": 381984, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.096151351928711, "global_step": 381985, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.108877182006836, "global_step": 381986, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.044790029525757, "global_step": 381987, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.104304313659668, "global_step": 381988, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1539835929870605, "global_step": 381989, "epoch": 744, "lr": 5e-05}
{"train_loss": 1.9965978860855103, "global_step": 381990, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0703771114349365, "global_step": 381991, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.269155740737915, "global_step": 381992, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1006455421447754, "global_step": 381993, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.144167184829712, "global_step": 381994, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0855929851531982, "global_step": 381995, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.07421612739563, "global_step": 381996, "epoch": 744, "lr": 5e-05}
{"train_loss": 1.9516322612762451, "global_step": 381997, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1286919116973877, "global_step": 381998, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.060875177383423, "global_step": 381999, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1878926753997803, "global_step": 382000, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.12644624710083, "global_step": 382001, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.054213285446167, "global_step": 382002, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1627187728881836, "global_step": 382003, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.052738904953003, "global_step": 382004, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1120145320892334, "global_step": 382005, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0519025325775146, "global_step": 382006, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2032716274261475, "global_step": 382007, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.100435495376587, "global_step": 382008, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.106299877166748, "global_step": 382009, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0596392154693604, "global_step": 382010, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.052978754043579, "global_step": 382011, "epoch": 744, "lr": 5e-05}
{"train_loss": 1.998227834701538, "global_step": 382012, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.140787363052368, "global_step": 382013, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.117267370223999, "global_step": 382014, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0841996669769287, "global_step": 382015, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1743996143341064, "global_step": 382016, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0605950355529785, "global_step": 382017, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1438703536987305, "global_step": 382018, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1221652030944824, "global_step": 382019, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1728148460388184, "global_step": 382020, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0827925205230713, "global_step": 382021, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1034069061279297, "global_step": 382022, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.132396697998047, "global_step": 382023, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.058042287826538, "global_step": 382024, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.097447395324707, "global_step": 382025, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.089077949523926, "global_step": 382026, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0988049507141113, "global_step": 382027, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.089402675628662, "global_step": 382028, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0994300842285156, "global_step": 382029, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0899271965026855, "global_step": 382030, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.144484281539917, "global_step": 382031, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.181225299835205, "global_step": 382032, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2105929851531982, "global_step": 382033, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.146944522857666, "global_step": 382034, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.01790452003479, "global_step": 382035, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.095289468765259, "global_step": 382036, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.045612096786499, "global_step": 382037, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.047098159790039, "global_step": 382038, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0626587867736816, "global_step": 382039, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0563249588012695, "global_step": 382040, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1301684379577637, "global_step": 382041, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.066392421722412, "global_step": 382042, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0871405601501465, "global_step": 382043, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0608625411987305, "global_step": 382044, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.051954984664917, "global_step": 382045, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.143592119216919, "global_step": 382046, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.059809923171997, "global_step": 382047, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1623988151550293, "global_step": 382048, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1725056171417236, "global_step": 382049, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.132991075515747, "global_step": 382050, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1156845092773438, "global_step": 382051, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0269935131073, "global_step": 382052, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.171058177947998, "global_step": 382053, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.051736831665039, "global_step": 382054, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1178908348083496, "global_step": 382055, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0818543434143066, "global_step": 382056, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0977110862731934, "global_step": 382057, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.136242628097534, "global_step": 382058, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1300346851348877, "global_step": 382059, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1836798191070557, "global_step": 382060, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0809645652770996, "global_step": 382061, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2381579875946045, "global_step": 382062, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0570223331451416, "global_step": 382063, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0971760749816895, "global_step": 382064, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0359954833984375, "global_step": 382065, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.081989049911499, "global_step": 382066, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0473601818084717, "global_step": 382067, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1479692459106445, "global_step": 382068, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.007610559463501, "global_step": 382069, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.094635486602783, "global_step": 382070, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0550808906555176, "global_step": 382071, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0640718936920166, "global_step": 382072, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1114919185638428, "global_step": 382073, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.148956537246704, "global_step": 382074, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1443965435028076, "global_step": 382075, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0744595527648926, "global_step": 382076, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.034684181213379, "global_step": 382077, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0547730922698975, "global_step": 382078, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1419670581817627, "global_step": 382079, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0821070671081543, "global_step": 382080, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1672451496124268, "global_step": 382081, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.111135721206665, "global_step": 382082, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1209044456481934, "global_step": 382083, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1370584964752197, "global_step": 382084, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.06752872467041, "global_step": 382085, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.152681350708008, "global_step": 382086, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.067284345626831, "global_step": 382087, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.078286647796631, "global_step": 382088, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.124270439147949, "global_step": 382089, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.105125665664673, "global_step": 382090, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0744757652282715, "global_step": 382091, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.009690284729004, "global_step": 382092, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0784027576446533, "global_step": 382093, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.146036148071289, "global_step": 382094, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.100294828414917, "global_step": 382095, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1471760272979736, "global_step": 382096, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.099163293838501, "global_step": 382097, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0909411907196045, "global_step": 382098, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1136937141418457, "global_step": 382099, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0564916133880615, "global_step": 382100, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1089277267456055, "global_step": 382101, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.095588207244873, "global_step": 382102, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.086076259613037, "global_step": 382103, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1105456352233887, "global_step": 382104, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1472666263580322, "global_step": 382105, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0797486305236816, "global_step": 382106, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0353147983551025, "global_step": 382107, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.124386787414551, "global_step": 382108, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0393223762512207, "global_step": 382109, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0899264812469482, "global_step": 382110, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0828301906585693, "global_step": 382111, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1654882431030273, "global_step": 382112, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.087570905685425, "global_step": 382113, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.057249069213867, "global_step": 382114, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0950634479522705, "global_step": 382115, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.21169114112854, "global_step": 382116, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.129688262939453, "global_step": 382117, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0882246494293213, "global_step": 382118, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.085836172103882, "global_step": 382119, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0930871963500977, "global_step": 382120, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0914721488952637, "global_step": 382121, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.09993052482605, "global_step": 382122, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1055710315704346, "global_step": 382123, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1653730869293213, "global_step": 382124, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.041546106338501, "global_step": 382125, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1554207801818848, "global_step": 382126, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0964648723602295, "global_step": 382127, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.048102855682373, "global_step": 382128, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.085871458053589, "global_step": 382129, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.107790470123291, "global_step": 382130, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0633068084716797, "global_step": 382131, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0157454013824463, "global_step": 382132, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.055392026901245, "global_step": 382133, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1170613765716553, "global_step": 382134, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0883874893188477, "global_step": 382135, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1054887771606445, "global_step": 382136, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0780279636383057, "global_step": 382137, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0168895721435547, "global_step": 382138, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.140385627746582, "global_step": 382139, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.223487615585327, "global_step": 382140, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1690449714660645, "global_step": 382141, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0992109775543213, "global_step": 382142, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.069065570831299, "global_step": 382143, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1465163230895996, "global_step": 382144, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0855181217193604, "global_step": 382145, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.151992082595825, "global_step": 382146, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1177165508270264, "global_step": 382147, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.151510715484619, "global_step": 382148, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0754685401916504, "global_step": 382149, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1686644554138184, "global_step": 382150, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1515932083129883, "global_step": 382151, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.064704656600952, "global_step": 382152, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2416465282440186, "global_step": 382153, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1359684467315674, "global_step": 382154, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.083223342895508, "global_step": 382155, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.077084541320801, "global_step": 382156, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.129347324371338, "global_step": 382157, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1368038654327393, "global_step": 382158, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1450164318084717, "global_step": 382159, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0703907012939453, "global_step": 382160, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.162118434906006, "global_step": 382161, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.124255657196045, "global_step": 382162, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0289649963378906, "global_step": 382163, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0674662590026855, "global_step": 382164, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.162705659866333, "global_step": 382165, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1154186725616455, "global_step": 382166, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1446595191955566, "global_step": 382167, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0176024436950684, "global_step": 382168, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.03375244140625, "global_step": 382169, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0973751544952393, "global_step": 382170, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0744802951812744, "global_step": 382171, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.143010377883911, "global_step": 382172, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.131542682647705, "global_step": 382173, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0754575729370117, "global_step": 382174, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.148010730743408, "global_step": 382175, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.158773899078369, "global_step": 382176, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0450589656829834, "global_step": 382177, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0689594745635986, "global_step": 382178, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.203566551208496, "global_step": 382179, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0502119064331055, "global_step": 382180, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0598349571228027, "global_step": 382181, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1417200565338135, "global_step": 382182, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.074326276779175, "global_step": 382183, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1179757118225098, "global_step": 382184, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.056648015975952, "global_step": 382185, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1519739627838135, "global_step": 382186, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0781939029693604, "global_step": 382187, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0188541412353516, "global_step": 382188, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0977842807769775, "global_step": 382189, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1019601821899414, "global_step": 382190, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.088348865509033, "global_step": 382191, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0896620750427246, "global_step": 382192, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0184249877929688, "global_step": 382193, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0776889324188232, "global_step": 382194, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.07163667678833, "global_step": 382195, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0794849395751953, "global_step": 382196, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.053102493286133, "global_step": 382197, "epoch": 744, "lr": 5e-05}
{"train_loss": 1.992904543876648, "global_step": 382198, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0755598545074463, "global_step": 382199, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0502138137817383, "global_step": 382200, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0555570125579834, "global_step": 382201, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.159855842590332, "global_step": 382202, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1698105335235596, "global_step": 382203, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0585756301879883, "global_step": 382204, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0756304264068604, "global_step": 382205, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0875182151794434, "global_step": 382206, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1609110832214355, "global_step": 382207, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0831031799316406, "global_step": 382208, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2291767597198486, "global_step": 382209, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.061542272567749, "global_step": 382210, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1945013999938965, "global_step": 382211, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.162365436553955, "global_step": 382212, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1102375984191895, "global_step": 382213, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2138352394104004, "global_step": 382214, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.004732370376587, "global_step": 382215, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.085716485977173, "global_step": 382216, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.051072835922241, "global_step": 382217, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.067716121673584, "global_step": 382218, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.091001272201538, "global_step": 382219, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1168019771575928, "global_step": 382220, "epoch": 744, "lr": 5e-05}
{"train_loss": 1.9360430240631104, "global_step": 382221, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0738532543182373, "global_step": 382222, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1894025802612305, "global_step": 382223, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1184465885162354, "global_step": 382224, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0753729343414307, "global_step": 382225, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2053451538085938, "global_step": 382226, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1412711143493652, "global_step": 382227, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.032423496246338, "global_step": 382228, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1684064865112305, "global_step": 382229, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0799694061279297, "global_step": 382230, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0584189891815186, "global_step": 382231, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1283628940582275, "global_step": 382232, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1237998008728027, "global_step": 382233, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.112748146057129, "global_step": 382234, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.079190492630005, "global_step": 382235, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0696709156036377, "global_step": 382236, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1128435134887695, "global_step": 382237, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.024782419204712, "global_step": 382238, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.116353750228882, "global_step": 382239, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1076724529266357, "global_step": 382240, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.145576000213623, "global_step": 382241, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.185497999191284, "global_step": 382242, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.082918167114258, "global_step": 382243, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1069297790527344, "global_step": 382244, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.203808546066284, "global_step": 382245, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0569956302642822, "global_step": 382246, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.088909149169922, "global_step": 382247, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0882022380828857, "global_step": 382248, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.125013589859009, "global_step": 382249, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.037583112716675, "global_step": 382250, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0951426029205322, "global_step": 382251, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0674326419830322, "global_step": 382252, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.19351863861084, "global_step": 382253, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.142606258392334, "global_step": 382254, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0726706981658936, "global_step": 382255, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0406334400177, "global_step": 382256, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.079303503036499, "global_step": 382257, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0916764736175537, "global_step": 382258, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2267377376556396, "global_step": 382259, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.03254771232605, "global_step": 382260, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0273876190185547, "global_step": 382261, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.067014694213867, "global_step": 382262, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.125594139099121, "global_step": 382263, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.139007091522217, "global_step": 382264, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0516209602355957, "global_step": 382265, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1345324516296387, "global_step": 382266, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0453407764434814, "global_step": 382267, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.069624423980713, "global_step": 382268, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1645963191986084, "global_step": 382269, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.130162000656128, "global_step": 382270, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.145324468612671, "global_step": 382271, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.139749765396118, "global_step": 382272, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.092435121536255, "global_step": 382273, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1749956607818604, "global_step": 382274, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2378344535827637, "global_step": 382275, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1962332725524902, "global_step": 382276, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0595014095306396, "global_step": 382277, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0778415203094482, "global_step": 382278, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.089740514755249, "global_step": 382279, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2065021991729736, "global_step": 382280, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0843310356140137, "global_step": 382281, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0763068199157715, "global_step": 382282, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0545952320098877, "global_step": 382283, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.015270471572876, "global_step": 382284, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0304954051971436, "global_step": 382285, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0973832607269287, "global_step": 382286, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0854785442352295, "global_step": 382287, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1440188884735107, "global_step": 382288, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.067049264907837, "global_step": 382289, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0933878421783447, "global_step": 382290, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0755791664123535, "global_step": 382291, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.21765398979187, "global_step": 382292, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.081251859664917, "global_step": 382293, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.072328567504883, "global_step": 382294, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0486409664154053, "global_step": 382295, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1172659397125244, "global_step": 382296, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.205386161804199, "global_step": 382297, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.05308198928833, "global_step": 382298, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0020627975463867, "global_step": 382299, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1229124069213867, "global_step": 382300, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0965652465820312, "global_step": 382301, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1162800788879395, "global_step": 382302, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0702569484710693, "global_step": 382303, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.162181854248047, "global_step": 382304, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0972952842712402, "global_step": 382305, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0764572620391846, "global_step": 382306, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1198408603668213, "global_step": 382307, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0799241065979004, "global_step": 382308, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.066603660583496, "global_step": 382309, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0283689498901367, "global_step": 382310, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.083594560623169, "global_step": 382311, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.043224334716797, "global_step": 382312, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0961270332336426, "global_step": 382313, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1047239303588867, "global_step": 382314, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.041569948196411, "global_step": 382315, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1373469829559326, "global_step": 382316, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1170294284820557, "global_step": 382317, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.176687717437744, "global_step": 382318, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0880651473999023, "global_step": 382319, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1301615238189697, "global_step": 382320, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.078317403793335, "global_step": 382321, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1491894721984863, "global_step": 382322, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.11488676071167, "global_step": 382323, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.150251626968384, "global_step": 382324, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.165005922317505, "global_step": 382325, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1221230030059814, "global_step": 382326, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0401742458343506, "global_step": 382327, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.195714235305786, "global_step": 382328, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.050575017929077, "global_step": 382329, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.033552885055542, "global_step": 382330, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1321887969970703, "global_step": 382331, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.104102373123169, "global_step": 382332, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.035661220550537, "global_step": 382333, "epoch": 744, "lr": 5e-05}
{"train_loss": 1.993699073791504, "global_step": 382334, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.138845443725586, "global_step": 382335, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.091611623764038, "global_step": 382336, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.150355339050293, "global_step": 382337, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.167689085006714, "global_step": 382338, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1279163360595703, "global_step": 382339, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.062182664871216, "global_step": 382340, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.126258611679077, "global_step": 382341, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0787110328674316, "global_step": 382342, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0282020568847656, "global_step": 382343, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0162830352783203, "global_step": 382344, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0474071502685547, "global_step": 382345, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1261091232299805, "global_step": 382346, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.116926908493042, "global_step": 382347, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0643937587738037, "global_step": 382348, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.142641544342041, "global_step": 382349, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0457465648651123, "global_step": 382350, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0314552783966064, "global_step": 382351, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.116807460784912, "global_step": 382352, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.068222999572754, "global_step": 382353, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1516623497009277, "global_step": 382354, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.15155029296875, "global_step": 382355, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.024561882019043, "global_step": 382356, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.225464344024658, "global_step": 382357, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1611075401306152, "global_step": 382358, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.121497392654419, "global_step": 382359, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.00138783454895, "global_step": 382360, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.121803045272827, "global_step": 382361, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1461360454559326, "global_step": 382362, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0863871574401855, "global_step": 382363, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1654303073883057, "global_step": 382364, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.138460397720337, "global_step": 382365, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.059035539627075, "global_step": 382366, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0877201557159424, "global_step": 382367, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1091675758361816, "global_step": 382368, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1464269161224365, "global_step": 382369, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.140955924987793, "global_step": 382370, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0808558464050293, "global_step": 382371, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1756391525268555, "global_step": 382372, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.052748680114746, "global_step": 382373, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.133568525314331, "global_step": 382374, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0162103176116943, "global_step": 382375, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0636613368988037, "global_step": 382376, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1097970008850098, "global_step": 382377, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.243556499481201, "global_step": 382378, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.078430414199829, "global_step": 382379, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1369597911834717, "global_step": 382380, "epoch": 744, "lr": 5e-05}
{"train_loss": 1.9801852703094482, "global_step": 382381, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1768743991851807, "global_step": 382382, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.043851852416992, "global_step": 382383, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0405099391937256, "global_step": 382384, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.127150058746338, "global_step": 382385, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.015096664428711, "global_step": 382386, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0974433422088623, "global_step": 382387, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0732808113098145, "global_step": 382388, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0686373710632324, "global_step": 382389, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0675735473632812, "global_step": 382390, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1768555641174316, "global_step": 382391, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.14925479888916, "global_step": 382392, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.034832239151001, "global_step": 382393, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1024017333984375, "global_step": 382394, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0812785625457764, "global_step": 382395, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0137336254119873, "global_step": 382396, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0697381496429443, "global_step": 382397, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.132983684539795, "global_step": 382398, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0796759128570557, "global_step": 382399, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0337910652160645, "global_step": 382400, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0428130626678467, "global_step": 382401, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.05542254447937, "global_step": 382402, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1320440769195557, "global_step": 382403, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0595903396606445, "global_step": 382404, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0834877490997314, "global_step": 382405, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0071969032287598, "global_step": 382406, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.078293561935425, "global_step": 382407, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1471352577209473, "global_step": 382408, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.132521867752075, "global_step": 382409, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1968564987182617, "global_step": 382410, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.152064323425293, "global_step": 382411, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.085113048553467, "global_step": 382412, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.087869167327881, "global_step": 382413, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.135247230529785, "global_step": 382414, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.096802234649658, "global_step": 382415, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1011290550231934, "global_step": 382416, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.189962148666382, "global_step": 382417, "epoch": 744, "lr": 5e-05}
{"train_loss": 1.9856961965560913, "global_step": 382418, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1886022090911865, "global_step": 382419, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0973949432373047, "global_step": 382420, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.070098638534546, "global_step": 382421, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.151486873626709, "global_step": 382422, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1246674060821533, "global_step": 382423, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.096264123916626, "global_step": 382424, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1305787563323975, "global_step": 382425, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1286044120788574, "global_step": 382426, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.054814577102661, "global_step": 382427, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0887162685394287, "global_step": 382428, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.108229398727417, "global_step": 382429, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1812102794647217, "global_step": 382430, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1616249084472656, "global_step": 382431, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1133627891540527, "global_step": 382432, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.161850690841675, "global_step": 382433, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.163360595703125, "global_step": 382434, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0949432849884033, "global_step": 382435, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.116560459136963, "global_step": 382436, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0565714836120605, "global_step": 382437, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.071826457977295, "global_step": 382438, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1739532947540283, "global_step": 382439, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1190357208251953, "global_step": 382440, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.149160623550415, "global_step": 382441, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.091442823410034, "global_step": 382442, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1440892219543457, "global_step": 382443, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.002556562423706, "global_step": 382444, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1773650646209717, "global_step": 382445, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0603291988372803, "global_step": 382446, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.094930410385132, "global_step": 382447, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1078991889953613, "global_step": 382448, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1655757427215576, "global_step": 382449, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.048884153366089, "global_step": 382450, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.171027898788452, "global_step": 382451, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1298530101776123, "global_step": 382452, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1248133182525635, "global_step": 382453, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0945513248443604, "global_step": 382454, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.111084461212158, "global_step": 382455, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1324965953826904, "global_step": 382456, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.035789966583252, "global_step": 382457, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0833137035369873, "global_step": 382458, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.04001784324646, "global_step": 382459, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1184873580932617, "global_step": 382460, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.138063669204712, "global_step": 382461, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1674861907958984, "global_step": 382462, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1081900596618652, "global_step": 382463, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0060877799987793, "global_step": 382464, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1265957355499268, "global_step": 382465, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.144742250442505, "global_step": 382466, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.193807601928711, "global_step": 382467, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.016991138458252, "global_step": 382468, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1276895999908447, "global_step": 382469, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.078939437866211, "global_step": 382470, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1514205932617188, "global_step": 382471, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1962311267852783, "global_step": 382472, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.160332679748535, "global_step": 382473, "epoch": 744, "lr": 5e-05}
{"train_loss": 1.9644583463668823, "global_step": 382474, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0587565898895264, "global_step": 382475, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.156137228012085, "global_step": 382476, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.121516466140747, "global_step": 382477, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0314507484436035, "global_step": 382478, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.17084002494812, "global_step": 382479, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.077960252761841, "global_step": 382480, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.076960563659668, "global_step": 382481, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.048847198486328, "global_step": 382482, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.113823890686035, "global_step": 382483, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1157331466674805, "global_step": 382484, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0918755531311035, "global_step": 382485, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.111196756362915, "global_step": 382486, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.122401475906372, "global_step": 382487, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0854103565216064, "global_step": 382488, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.084214210510254, "global_step": 382489, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1671719551086426, "global_step": 382490, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.148629665374756, "global_step": 382491, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.02500581741333, "global_step": 382492, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.076425075531006, "global_step": 382493, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0814833641052246, "global_step": 382494, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1403815746307373, "global_step": 382495, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.062331199645996, "global_step": 382496, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1787023544311523, "global_step": 382497, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1485705375671387, "global_step": 382498, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0973904132843018, "global_step": 382499, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1358251571655273, "global_step": 382500, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0127780437469482, "global_step": 382501, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0741007328033447, "global_step": 382502, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1157548427581787, "global_step": 382503, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0989766120910645, "global_step": 382504, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1243784427642822, "global_step": 382505, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.186955213546753, "global_step": 382506, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1457467079162598, "global_step": 382507, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.030447483062744, "global_step": 382508, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.03944993019104, "global_step": 382509, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0726258754730225, "global_step": 382510, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1762583255767822, "global_step": 382511, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.081008195877075, "global_step": 382512, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1486265659332275, "global_step": 382513, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1064536571502686, "global_step": 382514, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1090595722198486, "global_step": 382515, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1934282779693604, "global_step": 382516, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1216928958892822, "global_step": 382517, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1396379470825195, "global_step": 382518, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1212966442108154, "global_step": 382519, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.16507887840271, "global_step": 382520, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.118755578994751, "global_step": 382521, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.117417097091675, "global_step": 382522, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0886034965515137, "global_step": 382523, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1808245182037354, "global_step": 382524, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.125317096710205, "global_step": 382525, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.122653007507324, "global_step": 382526, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1039533615112305, "global_step": 382527, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.067091226577759, "global_step": 382528, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.086824417114258, "global_step": 382529, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1478774547576904, "global_step": 382530, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.07865309715271, "global_step": 382531, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1397829055786133, "global_step": 382532, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0948288440704346, "global_step": 382533, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0302698612213135, "global_step": 382534, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0825259685516357, "global_step": 382535, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0403125286102295, "global_step": 382536, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.157360792160034, "global_step": 382537, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2084085941314697, "global_step": 382538, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1155354976654053, "global_step": 382539, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0298941135406494, "global_step": 382540, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0959980487823486, "global_step": 382541, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0588717460632324, "global_step": 382542, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1484286785125732, "global_step": 382543, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0942928791046143, "global_step": 382544, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2288978099823, "global_step": 382545, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.086301565170288, "global_step": 382546, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1106152534484863, "global_step": 382547, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.060858726501465, "global_step": 382548, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1547815799713135, "global_step": 382549, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.211777448654175, "global_step": 382550, "epoch": 744, "lr": 5e-05}
{"train_loss": 1.9750242233276367, "global_step": 382551, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.047319173812866, "global_step": 382552, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.141950845718384, "global_step": 382553, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0810916423797607, "global_step": 382554, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.074651002883911, "global_step": 382555, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1932170391082764, "global_step": 382556, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1873674392700195, "global_step": 382557, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.135223865509033, "global_step": 382558, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0775392055511475, "global_step": 382559, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1274969577789307, "global_step": 382560, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1309871673583984, "global_step": 382561, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2124505043029785, "global_step": 382562, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.036923885345459, "global_step": 382563, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.138014554977417, "global_step": 382564, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0859427452087402, "global_step": 382565, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.123546838760376, "global_step": 382566, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.047445058822632, "global_step": 382567, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0942397117614746, "global_step": 382568, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0720365047454834, "global_step": 382569, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.123455286026001, "global_step": 382570, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0148754119873047, "global_step": 382571, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.131107807159424, "global_step": 382572, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.008732557296753, "global_step": 382573, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.169081449508667, "global_step": 382574, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0669167041778564, "global_step": 382575, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1141738891601562, "global_step": 382576, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1253247261047363, "global_step": 382577, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.057969093322754, "global_step": 382578, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.115816831588745, "global_step": 382579, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0569779872894287, "global_step": 382580, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.115734338760376, "global_step": 382581, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.116175889968872, "global_step": 382582, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.115760326385498, "global_step": 382583, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1835310459136963, "global_step": 382584, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0996646881103516, "global_step": 382585, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.130969762802124, "global_step": 382586, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.151238203048706, "global_step": 382587, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1074910163879395, "global_step": 382588, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.099571466445923, "global_step": 382589, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1124649047851562, "global_step": 382590, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.152099609375, "global_step": 382591, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0461935997009277, "global_step": 382592, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.139237403869629, "global_step": 382593, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.083278179168701, "global_step": 382594, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.157785654067993, "global_step": 382595, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1385838985443115, "global_step": 382596, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.184601306915283, "global_step": 382597, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1403510570526123, "global_step": 382598, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.068692922592163, "global_step": 382599, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.120126247406006, "global_step": 382600, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0860795974731445, "global_step": 382601, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.123204469680786, "global_step": 382602, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0299134254455566, "global_step": 382603, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1864891052246094, "global_step": 382604, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.102997303009033, "global_step": 382605, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.200495719909668, "global_step": 382606, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.117107391357422, "global_step": 382607, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0139520168304443, "global_step": 382608, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1547656059265137, "global_step": 382609, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.060291290283203, "global_step": 382610, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.06461238861084, "global_step": 382611, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1363539695739746, "global_step": 382612, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.072354316711426, "global_step": 382613, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.144376754760742, "global_step": 382614, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.171548366546631, "global_step": 382615, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0976855754852295, "global_step": 382616, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1559700965881348, "global_step": 382617, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1156628131866455, "global_step": 382618, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.211705207824707, "global_step": 382619, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.131711006164551, "global_step": 382620, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.156845808029175, "global_step": 382621, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1846184730529785, "global_step": 382622, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.143782138824463, "global_step": 382623, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0862958431243896, "global_step": 382624, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0986642837524414, "global_step": 382625, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1326868534088135, "global_step": 382626, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.134385347366333, "global_step": 382627, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1018948554992676, "global_step": 382628, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0311810970306396, "global_step": 382629, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0643177032470703, "global_step": 382630, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1124887466430664, "global_step": 382631, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2052197456359863, "global_step": 382632, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1184957027435303, "global_step": 382633, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0960946083068848, "global_step": 382634, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0588526725769043, "global_step": 382635, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0992965698242188, "global_step": 382636, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0778419971466064, "global_step": 382637, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.143742322921753, "global_step": 382638, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0504043102264404, "global_step": 382639, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.009263753890991, "global_step": 382640, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.072375535964966, "global_step": 382641, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.147991418838501, "global_step": 382642, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0866687297821045, "global_step": 382643, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.101710796356201, "global_step": 382644, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.156090259552002, "global_step": 382645, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.158980131149292, "global_step": 382646, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1404144763946533, "global_step": 382647, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.160576105117798, "global_step": 382648, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0616157054901123, "global_step": 382649, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0730178356170654, "global_step": 382650, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1332857608795166, "global_step": 382651, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0809998512268066, "global_step": 382652, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0935354232788086, "global_step": 382653, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1358301639556885, "global_step": 382654, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1223278045654297, "global_step": 382655, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0406033992767334, "global_step": 382656, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2172749042510986, "global_step": 382657, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0249457359313965, "global_step": 382658, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2023909091949463, "global_step": 382659, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.098997116088867, "global_step": 382660, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.119961738586426, "global_step": 382661, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.065601110458374, "global_step": 382662, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0825164318084717, "global_step": 382663, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.048200845718384, "global_step": 382664, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2282462120056152, "global_step": 382665, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.122451066970825, "global_step": 382666, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.034191131591797, "global_step": 382667, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.042593002319336, "global_step": 382668, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1375391483306885, "global_step": 382669, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.155780792236328, "global_step": 382670, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.107323408126831, "global_step": 382671, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1851024627685547, "global_step": 382672, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.118631362915039, "global_step": 382673, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0630509853363037, "global_step": 382674, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.095733642578125, "global_step": 382675, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.107034206390381, "global_step": 382676, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0958545207977295, "global_step": 382677, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.139003038406372, "global_step": 382678, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0885980129241943, "global_step": 382679, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.165700912475586, "global_step": 382680, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.033433675765991, "global_step": 382681, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.055976152420044, "global_step": 382682, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1089179515838623, "global_step": 382683, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1092116832733154, "global_step": 382684, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.247577667236328, "global_step": 382685, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0845413208007812, "global_step": 382686, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.151289463043213, "global_step": 382687, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.133303642272949, "global_step": 382688, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1601760387420654, "global_step": 382689, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1028246879577637, "global_step": 382690, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0712080001831055, "global_step": 382691, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.17439341545105, "global_step": 382692, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.07541561126709, "global_step": 382693, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.011244297027588, "global_step": 382694, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.075068235397339, "global_step": 382695, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1203651428222656, "global_step": 382696, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.063511610031128, "global_step": 382697, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0575191974639893, "global_step": 382698, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.080554723739624, "global_step": 382699, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.134664297103882, "global_step": 382700, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1507744789123535, "global_step": 382701, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.135030508041382, "global_step": 382702, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.151716709136963, "global_step": 382703, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1869447231292725, "global_step": 382704, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0993332862854004, "global_step": 382705, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.152331590652466, "global_step": 382706, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1152985095977783, "global_step": 382707, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1196866035461426, "global_step": 382708, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0498785972595215, "global_step": 382709, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.088836669921875, "global_step": 382710, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0335917472839355, "global_step": 382711, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1605043411254883, "global_step": 382712, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1479897499084473, "global_step": 382713, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1102306842803955, "global_step": 382714, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1010403633117676, "global_step": 382715, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.066617727279663, "global_step": 382716, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.130838394165039, "global_step": 382717, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1037511825561523, "global_step": 382718, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.032717227935791, "global_step": 382719, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0461859703063965, "global_step": 382720, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2223660945892334, "global_step": 382721, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.095522880554199, "global_step": 382722, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1407501697540283, "global_step": 382723, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0824809074401855, "global_step": 382724, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1630048751831055, "global_step": 382725, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1712183952331543, "global_step": 382726, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0885379314422607, "global_step": 382727, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.062398910522461, "global_step": 382728, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1418955326080322, "global_step": 382729, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0832653045654297, "global_step": 382730, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0721333026885986, "global_step": 382731, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.178744077682495, "global_step": 382732, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.099529981613159, "global_step": 382733, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.159133195877075, "global_step": 382734, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1399340629577637, "global_step": 382735, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1160123348236084, "global_step": 382736, "epoch": 744, "lr": 5e-05}
{"train_loss": 1.9716991186141968, "global_step": 382737, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2207372188568115, "global_step": 382738, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.14387845993042, "global_step": 382739, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.152721881866455, "global_step": 382740, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.049332618713379, "global_step": 382741, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1170692443847656, "global_step": 382742, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.125241756439209, "global_step": 382743, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1346402168273926, "global_step": 382744, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.198134660720825, "global_step": 382745, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.045236825942993, "global_step": 382746, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.058763027191162, "global_step": 382747, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0745644569396973, "global_step": 382748, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.157536506652832, "global_step": 382749, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.114349126815796, "global_step": 382750, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0816054344177246, "global_step": 382751, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1597447395324707, "global_step": 382752, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1614058017730713, "global_step": 382753, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.05423903465271, "global_step": 382754, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1057233810424805, "global_step": 382755, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1466124057769775, "global_step": 382756, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0975890159606934, "global_step": 382757, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1594438552856445, "global_step": 382758, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.157025098800659, "global_step": 382759, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1281723976135254, "global_step": 382760, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0964372158050537, "global_step": 382761, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.169982671737671, "global_step": 382762, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.109952926635742, "global_step": 382763, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0621376037597656, "global_step": 382764, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1440935134887695, "global_step": 382765, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0219290256500244, "global_step": 382766, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0696945190429688, "global_step": 382767, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.056070327758789, "global_step": 382768, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2279927730560303, "global_step": 382769, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1824700832366943, "global_step": 382770, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1739652156829834, "global_step": 382771, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1257314682006836, "global_step": 382772, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0501601696014404, "global_step": 382773, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.100884437561035, "global_step": 382774, "epoch": 744, "lr": 5e-05}
{"train_loss": 1.9893300533294678, "global_step": 382775, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1055984497070312, "global_step": 382776, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1520256996154785, "global_step": 382777, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1111509799957275, "global_step": 382778, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1018388271331787, "global_step": 382779, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.070157051086426, "global_step": 382780, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1579930782318115, "global_step": 382781, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0646867752075195, "global_step": 382782, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1485838890075684, "global_step": 382783, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0780980587005615, "global_step": 382784, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.11769962310791, "global_step": 382785, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2057666778564453, "global_step": 382786, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1514151096343994, "global_step": 382787, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.174809694290161, "global_step": 382788, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0650224685668945, "global_step": 382789, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.167633295059204, "global_step": 382790, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.121901035308838, "global_step": 382791, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1057422161102295, "global_step": 382792, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1173255443573, "global_step": 382793, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.066577196121216, "global_step": 382794, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0835745334625244, "global_step": 382795, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.140638828277588, "global_step": 382796, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.050264835357666, "global_step": 382797, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2181572914123535, "global_step": 382798, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.064398765563965, "global_step": 382799, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.206538438796997, "global_step": 382800, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1282458305358887, "global_step": 382801, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0668630599975586, "global_step": 382802, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.011727809906006, "global_step": 382803, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.140136957168579, "global_step": 382804, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.091165065765381, "global_step": 382805, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.220759391784668, "global_step": 382806, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1549909114837646, "global_step": 382807, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1123430728912354, "global_step": 382808, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.045941114425659, "global_step": 382809, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.056746482849121, "global_step": 382810, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.2147865295410156, "global_step": 382811, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.168417453765869, "global_step": 382812, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1219406127929688, "global_step": 382813, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1678316593170166, "global_step": 382814, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0665764808654785, "global_step": 382815, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1375958919525146, "global_step": 382816, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.129826068878174, "global_step": 382817, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0980257987976074, "global_step": 382818, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.052349805831909, "global_step": 382819, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0826964378356934, "global_step": 382820, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.165144443511963, "global_step": 382821, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.173262119293213, "global_step": 382822, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1100544929504395, "global_step": 382823, "epoch": 744, "lr": 5e-05}
{"train_loss": 1.9948475360870361, "global_step": 382824, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1109213829040527, "global_step": 382825, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0081944465637207, "global_step": 382826, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1274728775024414, "global_step": 382827, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0940937995910645, "global_step": 382828, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.117457866668701, "global_step": 382829, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1327707767486572, "global_step": 382830, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.055755615234375, "global_step": 382831, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0822675228118896, "global_step": 382832, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1072731018066406, "global_step": 382833, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0585076808929443, "global_step": 382834, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0998120307922363, "global_step": 382835, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1725692749023438, "global_step": 382836, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0630369186401367, "global_step": 382837, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.093817949295044, "global_step": 382838, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1831703186035156, "global_step": 382839, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.06242036819458, "global_step": 382840, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.164693832397461, "global_step": 382841, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.087223529815674, "global_step": 382842, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1707396507263184, "global_step": 382843, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.173541307449341, "global_step": 382844, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.057480573654175, "global_step": 382845, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.061767339706421, "global_step": 382846, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.071150779724121, "global_step": 382847, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0306355953216553, "global_step": 382848, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1301918029785156, "global_step": 382849, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1893439292907715, "global_step": 382850, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.166706085205078, "global_step": 382851, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.14431095123291, "global_step": 382852, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.062678813934326, "global_step": 382853, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1296916007995605, "global_step": 382854, "epoch": 744, "lr": 5e-05}
{"train_loss": 1.9515492916107178, "global_step": 382855, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.134126663208008, "global_step": 382856, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1471896171569824, "global_step": 382857, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1336562633514404, "global_step": 382858, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1181724071502686, "global_step": 382859, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.050947427749634, "global_step": 382860, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.057600498199463, "global_step": 382861, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0927186012268066, "global_step": 382862, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.078432559967041, "global_step": 382863, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1095612049102783, "global_step": 382864, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0882840156555176, "global_step": 382865, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1086864471435547, "global_step": 382866, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.091578722000122, "global_step": 382867, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1690125465393066, "global_step": 382868, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1721649169921875, "global_step": 382869, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.130337715148926, "global_step": 382870, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1284914016723633, "global_step": 382871, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.115858793258667, "global_step": 382872, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1349453926086426, "global_step": 382873, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.148275375366211, "global_step": 382874, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.051304817199707, "global_step": 382875, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1547389030456543, "global_step": 382876, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1261181831359863, "global_step": 382877, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1183102130889893, "global_step": 382878, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.135772228240967, "global_step": 382879, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0435855388641357, "global_step": 382880, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1510109901428223, "global_step": 382881, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0359816551208496, "global_step": 382882, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.124537229537964, "global_step": 382883, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1182570457458496, "global_step": 382884, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.097038984298706, "global_step": 382885, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0828921794891357, "global_step": 382886, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.1051595211029053, "global_step": 382887, "epoch": 744, "lr": 5e-05}
{"train_loss": 2.0727310180664062, "global_step": 382888, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.107595443725586, "global_step": 382889, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.022022008895874, "global_step": 382890, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0982348918914795, "global_step": 382891, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.086533784866333, "global_step": 382892, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.087172508239746, "global_step": 382893, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0199081897735596, "global_step": 382894, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0720009803771973, "global_step": 382895, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0520365238189697, "global_step": 382896, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.123227119445801, "global_step": 382897, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0869805812835693, "global_step": 382898, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0477652549743652, "global_step": 382899, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.055668592453003, "global_step": 382900, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0768251419067383, "global_step": 382901, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1323511600494385, "global_step": 382902, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1322765350341797, "global_step": 382903, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.093179702758789, "global_step": 382904, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.102114677429199, "global_step": 382905, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1742403507232666, "global_step": 382906, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.225454092025757, "global_step": 382907, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1194684505462646, "global_step": 382908, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.13505482673645, "global_step": 382909, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0836689472198486, "global_step": 382910, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.139495611190796, "global_step": 382911, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.032114267349243, "global_step": 382912, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1447811126708984, "global_step": 382913, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.127769708633423, "global_step": 382914, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.089517116546631, "global_step": 382915, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1515259742736816, "global_step": 382916, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.18835186958313, "global_step": 382917, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0459651947021484, "global_step": 382918, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0231380462646484, "global_step": 382919, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.9820646047592163, "global_step": 382920, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0616464614868164, "global_step": 382921, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.038710355758667, "global_step": 382922, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.110872745513916, "global_step": 382923, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.107632637023926, "global_step": 382924, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1262197494506836, "global_step": 382925, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1338937282562256, "global_step": 382926, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.082554340362549, "global_step": 382927, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.105475425720215, "global_step": 382928, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.057508707046509, "global_step": 382929, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0868442058563232, "global_step": 382930, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0426535606384277, "global_step": 382931, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0940358638763428, "global_step": 382932, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0737175941467285, "global_step": 382933, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.154222249984741, "global_step": 382934, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.056871175765991, "global_step": 382935, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.075246572494507, "global_step": 382936, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.105968952178955, "global_step": 382937, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.993220329284668, "global_step": 382938, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.122337818145752, "global_step": 382939, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0017940998077393, "global_step": 382940, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.143002510070801, "global_step": 382941, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1083950996398926, "global_step": 382942, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.13822603225708, "global_step": 382943, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0806665420532227, "global_step": 382944, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0365967750549316, "global_step": 382945, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.112682819366455, "global_step": 382946, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0947728157043457, "global_step": 382947, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0898427963256836, "global_step": 382948, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0708367824554443, "global_step": 382949, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0988738536834717, "global_step": 382950, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.107078790664673, "global_step": 382951, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1358113288879395, "global_step": 382952, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.9964606761932373, "global_step": 382953, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0298264026641846, "global_step": 382954, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1660642623901367, "global_step": 382955, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.048851490020752, "global_step": 382956, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0207080841064453, "global_step": 382957, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.109036684036255, "global_step": 382958, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.08036732673645, "global_step": 382959, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0163321495056152, "global_step": 382960, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.172088861465454, "global_step": 382961, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.029446601867676, "global_step": 382962, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1375932693481445, "global_step": 382963, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0462839603424072, "global_step": 382964, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0898854732513428, "global_step": 382965, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1407999992370605, "global_step": 382966, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.9943684339523315, "global_step": 382967, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.094454050064087, "global_step": 382968, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.089672803878784, "global_step": 382969, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.938380241394043, "global_step": 382970, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1472041606903076, "global_step": 382971, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0394222736358643, "global_step": 382972, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.085782051086426, "global_step": 382973, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0718424320220947, "global_step": 382974, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1119449138641357, "global_step": 382975, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.127849817276001, "global_step": 382976, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0698330402374268, "global_step": 382977, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0993692874908447, "global_step": 382978, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0618176460266113, "global_step": 382979, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.10233736038208, "global_step": 382980, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1535065174102783, "global_step": 382981, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0722603797912598, "global_step": 382982, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0672504901885986, "global_step": 382983, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0483853816986084, "global_step": 382984, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.136225938796997, "global_step": 382985, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.10933256149292, "global_step": 382986, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.074702024459839, "global_step": 382987, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.060302495956421, "global_step": 382988, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0584559440612793, "global_step": 382989, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1854333877563477, "global_step": 382990, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0493154525756836, "global_step": 382991, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.109971761703491, "global_step": 382992, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1379475593566895, "global_step": 382993, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.117729663848877, "global_step": 382994, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2154531478881836, "global_step": 382995, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0675973892211914, "global_step": 382996, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0364785194396973, "global_step": 382997, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.174159049987793, "global_step": 382998, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0214412212371826, "global_step": 382999, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.111677408218384, "global_step": 383000, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2045910358428955, "global_step": 383001, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.095043182373047, "global_step": 383002, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1389245986938477, "global_step": 383003, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.187821865081787, "global_step": 383004, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.056537628173828, "global_step": 383005, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0008187294006348, "global_step": 383006, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.133375406265259, "global_step": 383007, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1243200302124023, "global_step": 383008, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.160247325897217, "global_step": 383009, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.12377667427063, "global_step": 383010, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.073899507522583, "global_step": 383011, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.098780393600464, "global_step": 383012, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0669243335723877, "global_step": 383013, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0951383113861084, "global_step": 383014, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1654186248779297, "global_step": 383015, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.055727481842041, "global_step": 383016, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1526811122894287, "global_step": 383017, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0808866024017334, "global_step": 383018, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.075453281402588, "global_step": 383019, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.086604118347168, "global_step": 383020, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2074134349823, "global_step": 383021, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.106065511703491, "global_step": 383022, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.078017234802246, "global_step": 383023, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.9551160335540771, "global_step": 383024, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.040994644165039, "global_step": 383025, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1664133071899414, "global_step": 383026, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0857412815093994, "global_step": 383027, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1400015354156494, "global_step": 383028, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.087486743927002, "global_step": 383029, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0344443321228027, "global_step": 383030, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0421371459960938, "global_step": 383031, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.128368616104126, "global_step": 383032, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1109986305236816, "global_step": 383033, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1280248165130615, "global_step": 383034, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1606764793395996, "global_step": 383035, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.03584885597229, "global_step": 383036, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.116649627685547, "global_step": 383037, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0832765102386475, "global_step": 383038, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.091965675354004, "global_step": 383039, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1247410774230957, "global_step": 383040, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1042404174804688, "global_step": 383041, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1341302394866943, "global_step": 383042, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1690115928649902, "global_step": 383043, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1161811351776123, "global_step": 383044, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1713831424713135, "global_step": 383045, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1680679321289062, "global_step": 383046, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1210343837738037, "global_step": 383047, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1014530658721924, "global_step": 383048, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.116426944732666, "global_step": 383049, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.043651819229126, "global_step": 383050, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.109926700592041, "global_step": 383051, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.9992731809616089, "global_step": 383052, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.053459405899048, "global_step": 383053, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1135048866271973, "global_step": 383054, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1734509468078613, "global_step": 383055, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.084352493286133, "global_step": 383056, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1031765937805176, "global_step": 383057, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.145533800125122, "global_step": 383058, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.10284686088562, "global_step": 383059, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1404170989990234, "global_step": 383060, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0809037685394287, "global_step": 383061, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0852246284484863, "global_step": 383062, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.095500946044922, "global_step": 383063, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0477941036224365, "global_step": 383064, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0840964317321777, "global_step": 383065, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.018388271331787, "global_step": 383066, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0645804405212402, "global_step": 383067, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0116806030273438, "global_step": 383068, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0731430053710938, "global_step": 383069, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.154301166534424, "global_step": 383070, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0214290618896484, "global_step": 383071, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0819239616394043, "global_step": 383072, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.116990327835083, "global_step": 383073, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0908658504486084, "global_step": 383074, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.097723960876465, "global_step": 383075, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.064159631729126, "global_step": 383076, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.064415454864502, "global_step": 383077, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0584850311279297, "global_step": 383078, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.045356273651123, "global_step": 383079, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.9973938465118408, "global_step": 383080, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0796165466308594, "global_step": 383081, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1323189735412598, "global_step": 383082, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1205673217773438, "global_step": 383083, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.03861141204834, "global_step": 383084, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1027324199676514, "global_step": 383085, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1362786293029785, "global_step": 383086, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.096417188644409, "global_step": 383087, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0373363494873047, "global_step": 383088, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.185885190963745, "global_step": 383089, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.139784097671509, "global_step": 383090, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0643460750579834, "global_step": 383091, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.13521409034729, "global_step": 383092, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1056506633758545, "global_step": 383093, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.176807165145874, "global_step": 383094, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0915892124176025, "global_step": 383095, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0375919342041016, "global_step": 383096, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.174112558364868, "global_step": 383097, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.102658748626709, "global_step": 383098, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.086732864379883, "global_step": 383099, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.107386589050293, "global_step": 383100, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.104391098022461, "global_step": 383101, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.124091863632202, "global_step": 383102, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.106503963470459, "global_step": 383103, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1078243255615234, "global_step": 383104, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1129863262176514, "global_step": 383105, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1616265773773193, "global_step": 383106, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.163357973098755, "global_step": 383107, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.091193914413452, "global_step": 383108, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.153684377670288, "global_step": 383109, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0542914867401123, "global_step": 383110, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0421178340911865, "global_step": 383111, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0332093238830566, "global_step": 383112, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1166906356811523, "global_step": 383113, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0929129123687744, "global_step": 383114, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.09885835647583, "global_step": 383115, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.130092144012451, "global_step": 383116, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0670032501220703, "global_step": 383117, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1224186420440674, "global_step": 383118, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.110511541366577, "global_step": 383119, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0892505645751953, "global_step": 383120, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1034340858459473, "global_step": 383121, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1295695304870605, "global_step": 383122, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0899505615234375, "global_step": 383123, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1424448490142822, "global_step": 383124, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.158881664276123, "global_step": 383125, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.103961944580078, "global_step": 383126, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1215977668762207, "global_step": 383127, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1329874992370605, "global_step": 383128, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.035735845565796, "global_step": 383129, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.094905138015747, "global_step": 383130, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1511425971984863, "global_step": 383131, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1110363006591797, "global_step": 383132, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.146357297897339, "global_step": 383133, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1086854934692383, "global_step": 383134, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1228232383728027, "global_step": 383135, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.117863416671753, "global_step": 383136, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.9908561706542969, "global_step": 383137, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.150973081588745, "global_step": 383138, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1118757724761963, "global_step": 383139, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1237614154815674, "global_step": 383140, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.098676919937134, "global_step": 383141, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.133960723876953, "global_step": 383142, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0328102111816406, "global_step": 383143, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1253836154937744, "global_step": 383144, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.109060764312744, "global_step": 383145, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1199347972869873, "global_step": 383146, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.064368724822998, "global_step": 383147, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.076416492462158, "global_step": 383148, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.152750015258789, "global_step": 383149, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.095367431640625, "global_step": 383150, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.04233717918396, "global_step": 383151, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.131985902786255, "global_step": 383152, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.038539409637451, "global_step": 383153, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0907251834869385, "global_step": 383154, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0814168453216553, "global_step": 383155, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.155916452407837, "global_step": 383156, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.084876298904419, "global_step": 383157, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0591516494750977, "global_step": 383158, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.104746103286743, "global_step": 383159, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0565574169158936, "global_step": 383160, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.12800931930542, "global_step": 383161, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1494133472442627, "global_step": 383162, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0586748123168945, "global_step": 383163, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1149990558624268, "global_step": 383164, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1135687828063965, "global_step": 383165, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.114100933074951, "global_step": 383166, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0962331295013428, "global_step": 383167, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0378031730651855, "global_step": 383168, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0779664516448975, "global_step": 383169, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.079421281814575, "global_step": 383170, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1611504554748535, "global_step": 383171, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0906734466552734, "global_step": 383172, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1079752445220947, "global_step": 383173, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.9870896339416504, "global_step": 383174, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.995439887046814, "global_step": 383175, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0683865547180176, "global_step": 383176, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0687255859375, "global_step": 383177, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.02435564994812, "global_step": 383178, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0803258419036865, "global_step": 383179, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0927789211273193, "global_step": 383180, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.092179536819458, "global_step": 383181, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1433804035186768, "global_step": 383182, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1004648208618164, "global_step": 383183, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.124940872192383, "global_step": 383184, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.081146240234375, "global_step": 383185, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0255186557769775, "global_step": 383186, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1699016094207764, "global_step": 383187, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1027262210845947, "global_step": 383188, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0943994522094727, "global_step": 383189, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1347920894622803, "global_step": 383190, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0954487323760986, "global_step": 383191, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2097413539886475, "global_step": 383192, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.096431255340576, "global_step": 383193, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1359713077545166, "global_step": 383194, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.115586757659912, "global_step": 383195, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0782854557037354, "global_step": 383196, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1507346630096436, "global_step": 383197, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.126854419708252, "global_step": 383198, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.01851749420166, "global_step": 383199, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.098879098892212, "global_step": 383200, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0308291912078857, "global_step": 383201, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1056370735168457, "global_step": 383202, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.142239809036255, "global_step": 383203, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0735859870910645, "global_step": 383204, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0636816024780273, "global_step": 383205, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1284804344177246, "global_step": 383206, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0217766761779785, "global_step": 383207, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0480377674102783, "global_step": 383208, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0818073749542236, "global_step": 383209, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1168618202209473, "global_step": 383210, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1482949256896973, "global_step": 383211, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1387672424316406, "global_step": 383212, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.115687131881714, "global_step": 383213, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1205875873565674, "global_step": 383214, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.038943290710449, "global_step": 383215, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1314260959625244, "global_step": 383216, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.152791738510132, "global_step": 383217, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.10233736038208, "global_step": 383218, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1874256134033203, "global_step": 383219, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0877649784088135, "global_step": 383220, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.122063636779785, "global_step": 383221, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.065493583679199, "global_step": 383222, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0898783206939697, "global_step": 383223, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1573681831359863, "global_step": 383224, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0786659717559814, "global_step": 383225, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1156516075134277, "global_step": 383226, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.109586715698242, "global_step": 383227, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1170873641967773, "global_step": 383228, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0155396461486816, "global_step": 383229, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.117116928100586, "global_step": 383230, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0405800342559814, "global_step": 383231, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.049069404602051, "global_step": 383232, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1301560401916504, "global_step": 383233, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.11828351020813, "global_step": 383234, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.216691255569458, "global_step": 383235, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0648953914642334, "global_step": 383236, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1671719551086426, "global_step": 383237, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1014370918273926, "global_step": 383238, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.076991319656372, "global_step": 383239, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.170499086380005, "global_step": 383240, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1451199054718018, "global_step": 383241, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0382649898529053, "global_step": 383242, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.103914499282837, "global_step": 383243, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0512678623199463, "global_step": 383244, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1269145011901855, "global_step": 383245, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.037175416946411, "global_step": 383246, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1132442951202393, "global_step": 383247, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1102662086486816, "global_step": 383248, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0241124629974365, "global_step": 383249, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1350927352905273, "global_step": 383250, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.135967254638672, "global_step": 383251, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0513641834259033, "global_step": 383252, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.132720470428467, "global_step": 383253, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0012083053588867, "global_step": 383254, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0844578742980957, "global_step": 383255, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0946903228759766, "global_step": 383256, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.07236909866333, "global_step": 383257, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0803027153015137, "global_step": 383258, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.196917772293091, "global_step": 383259, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.144637107849121, "global_step": 383260, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.968560814857483, "global_step": 383261, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0922489166259766, "global_step": 383262, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0831615924835205, "global_step": 383263, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1316933631896973, "global_step": 383264, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0808634757995605, "global_step": 383265, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2296934127807617, "global_step": 383266, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.073018789291382, "global_step": 383267, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0600318908691406, "global_step": 383268, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.10127329826355, "global_step": 383269, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1154303550720215, "global_step": 383270, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0406293869018555, "global_step": 383271, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2090091705322266, "global_step": 383272, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1580162048339844, "global_step": 383273, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.109544515609741, "global_step": 383274, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0913987159729004, "global_step": 383275, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.111222267150879, "global_step": 383276, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1329455375671387, "global_step": 383277, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0498995780944824, "global_step": 383278, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1429452896118164, "global_step": 383279, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1069250106811523, "global_step": 383280, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.9866352081298828, "global_step": 383281, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.180509090423584, "global_step": 383282, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.032994508743286, "global_step": 383283, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2250804901123047, "global_step": 383284, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0450141429901123, "global_step": 383285, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.037158727645874, "global_step": 383286, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0808262825012207, "global_step": 383287, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.090606212615967, "global_step": 383288, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1023342609405518, "global_step": 383289, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0513782501220703, "global_step": 383290, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.066575765609741, "global_step": 383291, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.145698308944702, "global_step": 383292, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.200709819793701, "global_step": 383293, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.05781888961792, "global_step": 383294, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.109752655029297, "global_step": 383295, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0474119186401367, "global_step": 383296, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.180983066558838, "global_step": 383297, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1284282207489014, "global_step": 383298, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1840078830718994, "global_step": 383299, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0475518703460693, "global_step": 383300, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.102701187133789, "global_step": 383301, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1598238945007324, "global_step": 383302, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.105679512023926, "global_step": 383303, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0996897220611572, "global_step": 383304, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1150565147399902, "global_step": 383305, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1211304664611816, "global_step": 383306, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.122069835662842, "global_step": 383307, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0384440422058105, "global_step": 383308, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0554909706115723, "global_step": 383309, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0768706798553467, "global_step": 383310, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0689175128936768, "global_step": 383311, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.118455648422241, "global_step": 383312, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0855700969696045, "global_step": 383313, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.119490623474121, "global_step": 383314, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.068296432495117, "global_step": 383315, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.063889503479004, "global_step": 383316, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0969319343566895, "global_step": 383317, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.172455072402954, "global_step": 383318, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1540002822875977, "global_step": 383319, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1799724102020264, "global_step": 383320, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1369049549102783, "global_step": 383321, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0489253997802734, "global_step": 383322, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0428967475891113, "global_step": 383323, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.180903196334839, "global_step": 383324, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.115687608718872, "global_step": 383325, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0946366786956787, "global_step": 383326, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.15661883354187, "global_step": 383327, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1299386024475098, "global_step": 383328, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.068129539489746, "global_step": 383329, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0416009426116943, "global_step": 383330, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1391854286193848, "global_step": 383331, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.176412582397461, "global_step": 383332, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.9892560243606567, "global_step": 383333, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.102761745452881, "global_step": 383334, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0214009284973145, "global_step": 383335, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.216378927230835, "global_step": 383336, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.102372646331787, "global_step": 383337, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0782976150512695, "global_step": 383338, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0917322635650635, "global_step": 383339, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1545679569244385, "global_step": 383340, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1864287853240967, "global_step": 383341, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.059407949447632, "global_step": 383342, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0827207565307617, "global_step": 383343, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0830249786376953, "global_step": 383344, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.039335250854492, "global_step": 383345, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.082808494567871, "global_step": 383346, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.956727147102356, "global_step": 383347, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.020798683166504, "global_step": 383348, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.118036985397339, "global_step": 383349, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1872289180755615, "global_step": 383350, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0659825801849365, "global_step": 383351, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1404011249542236, "global_step": 383352, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.072852611541748, "global_step": 383353, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.047870635986328, "global_step": 383354, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1121294498443604, "global_step": 383355, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1205718517303467, "global_step": 383356, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0952935218811035, "global_step": 383357, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.103269577026367, "global_step": 383358, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1450793743133545, "global_step": 383359, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.120699405670166, "global_step": 383360, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.06835675239563, "global_step": 383361, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.195568323135376, "global_step": 383362, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.092785358428955, "global_step": 383363, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.127797842025757, "global_step": 383364, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.976313591003418, "global_step": 383365, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1229641437530518, "global_step": 383366, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1199254989624023, "global_step": 383367, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.025531053543091, "global_step": 383368, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.043379783630371, "global_step": 383369, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.037862539291382, "global_step": 383370, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0251595973968506, "global_step": 383371, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0712621212005615, "global_step": 383372, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.159884452819824, "global_step": 383373, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.024887800216675, "global_step": 383374, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.163240671157837, "global_step": 383375, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0793168544769287, "global_step": 383376, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.9662343263626099, "global_step": 383377, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0620837211608887, "global_step": 383378, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1288163661956787, "global_step": 383379, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2072019577026367, "global_step": 383380, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1449105739593506, "global_step": 383381, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.04314923286438, "global_step": 383382, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.138432264328003, "global_step": 383383, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.231032609939575, "global_step": 383384, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.122253179550171, "global_step": 383385, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.253443479537964, "global_step": 383386, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1048271656036377, "global_step": 383387, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.023668050765991, "global_step": 383388, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1393399238586426, "global_step": 383389, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1457414627075195, "global_step": 383390, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0667190551757812, "global_step": 383391, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.04276967048645, "global_step": 383392, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.008554458618164, "global_step": 383393, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.069342613220215, "global_step": 383394, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.048828601837158, "global_step": 383395, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.18849515914917, "global_step": 383396, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.172041893005371, "global_step": 383397, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0840845108032227, "global_step": 383398, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0599417686462402, "global_step": 383399, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0818581581115723, "global_step": 383400, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.21024227142334, "global_step": 383401, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0954959392547607, "global_step": 383402, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1447157859802246, "global_step": 383403, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.157167911529541, "global_step": 383404, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.107966423034668, "global_step": 383405, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1167521476745605, "global_step": 383406, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.181690216064453, "global_step": 383407, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0483317375183105, "global_step": 383408, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.213615894317627, "global_step": 383409, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.159421682357788, "global_step": 383410, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.150247573852539, "global_step": 383411, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0878119468688965, "global_step": 383412, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2104930877685547, "global_step": 383413, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1501846313476562, "global_step": 383414, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0406978130340576, "global_step": 383415, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1150174140930176, "global_step": 383416, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.105530023574829, "global_step": 383417, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.033975839614868, "global_step": 383418, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.06904935836792, "global_step": 383419, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0871875286102295, "global_step": 383420, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.122241973876953, "global_step": 383421, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.184138298034668, "global_step": 383422, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.118095874786377, "global_step": 383423, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1187307834625244, "global_step": 383424, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.004272222518921, "global_step": 383425, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.130120277404785, "global_step": 383426, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.146122694015503, "global_step": 383427, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.03200101852417, "global_step": 383428, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2495765686035156, "global_step": 383429, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.050058603286743, "global_step": 383430, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.084988832473755, "global_step": 383431, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.047410011291504, "global_step": 383432, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.135279417037964, "global_step": 383433, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.076364040374756, "global_step": 383434, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0913639068603516, "global_step": 383435, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.152459144592285, "global_step": 383436, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1537036895751953, "global_step": 383437, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.128131151199341, "global_step": 383438, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.070683002471924, "global_step": 383439, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1199636459350586, "global_step": 383440, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0536048412323, "global_step": 383441, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.170677900314331, "global_step": 383442, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0687966346740723, "global_step": 383443, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.085418462753296, "global_step": 383444, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.077399969100952, "global_step": 383445, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1140990257263184, "global_step": 383446, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1309566497802734, "global_step": 383447, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1550843715667725, "global_step": 383448, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1796114444732666, "global_step": 383449, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.072531223297119, "global_step": 383450, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.163856029510498, "global_step": 383451, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0962109565734863, "global_step": 383452, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1896002292633057, "global_step": 383453, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.9963490962982178, "global_step": 383454, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1179466247558594, "global_step": 383455, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0663256645202637, "global_step": 383456, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0987327098846436, "global_step": 383457, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.122239351272583, "global_step": 383458, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1171247959136963, "global_step": 383459, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.9534590244293213, "global_step": 383460, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1405692100524902, "global_step": 383461, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.149512767791748, "global_step": 383462, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.176349639892578, "global_step": 383463, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.9992485046386719, "global_step": 383464, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0609424114227295, "global_step": 383465, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.094836711883545, "global_step": 383466, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0396676063537598, "global_step": 383467, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0971808433532715, "global_step": 383468, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0830180644989014, "global_step": 383469, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1472818851470947, "global_step": 383470, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.04953932762146, "global_step": 383471, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1029419898986816, "global_step": 383472, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0760602951049805, "global_step": 383473, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1149439811706543, "global_step": 383474, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1070518493652344, "global_step": 383475, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.106614112854004, "global_step": 383476, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1025311946868896, "global_step": 383477, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1448147296905518, "global_step": 383478, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.102766752243042, "global_step": 383479, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1305408477783203, "global_step": 383480, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.161224603652954, "global_step": 383481, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.155430555343628, "global_step": 383482, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0588297843933105, "global_step": 383483, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1185567378997803, "global_step": 383484, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0053184032440186, "global_step": 383485, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0692126750946045, "global_step": 383486, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.128460168838501, "global_step": 383487, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2213735580444336, "global_step": 383488, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.115133762359619, "global_step": 383489, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0743789672851562, "global_step": 383490, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.253661632537842, "global_step": 383491, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0842020511627197, "global_step": 383492, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1144659519195557, "global_step": 383493, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.068786382675171, "global_step": 383494, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0403904914855957, "global_step": 383495, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.109687566757202, "global_step": 383496, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0978076457977295, "global_step": 383497, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0607783794403076, "global_step": 383498, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0282726287841797, "global_step": 383499, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1013779640197754, "global_step": 383500, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1734976768493652, "global_step": 383501, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0171709060668945, "global_step": 383502, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1386005878448486, "global_step": 383503, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1296985149383545, "global_step": 383504, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.068328857421875, "global_step": 383505, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.209336042404175, "global_step": 383506, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.163506031036377, "global_step": 383507, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.9957913160324097, "global_step": 383508, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1610355377197266, "global_step": 383509, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1489720344543457, "global_step": 383510, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.043984889984131, "global_step": 383511, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1456799507141113, "global_step": 383512, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.117103099822998, "global_step": 383513, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.160418748855591, "global_step": 383514, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0703532695770264, "global_step": 383515, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0919387340545654, "global_step": 383516, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.127107858657837, "global_step": 383517, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1605007648468018, "global_step": 383518, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.136777877807617, "global_step": 383519, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.063464879989624, "global_step": 383520, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.107912063598633, "global_step": 383521, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.065878391265869, "global_step": 383522, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1300153732299805, "global_step": 383523, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.057446002960205, "global_step": 383524, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.140629768371582, "global_step": 383525, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.156151294708252, "global_step": 383526, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.113349437713623, "global_step": 383527, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.079838275909424, "global_step": 383528, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1880431175231934, "global_step": 383529, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.117522954940796, "global_step": 383530, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.141409397125244, "global_step": 383531, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1027252674102783, "global_step": 383532, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.074470043182373, "global_step": 383533, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.145885705947876, "global_step": 383534, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0611109733581543, "global_step": 383535, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1461634635925293, "global_step": 383536, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1440072059631348, "global_step": 383537, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0149388313293457, "global_step": 383538, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0997660160064697, "global_step": 383539, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0960938930511475, "global_step": 383540, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.067229747772217, "global_step": 383541, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1727564334869385, "global_step": 383542, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.081118583679199, "global_step": 383543, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1805996894836426, "global_step": 383544, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.037099599838257, "global_step": 383545, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0353641510009766, "global_step": 383546, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1373414993286133, "global_step": 383547, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0278899669647217, "global_step": 383548, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1881749629974365, "global_step": 383549, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.99005925655365, "global_step": 383550, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.180889368057251, "global_step": 383551, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1522576808929443, "global_step": 383552, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0518558025360107, "global_step": 383553, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1118288040161133, "global_step": 383554, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.093336582183838, "global_step": 383555, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.03523850440979, "global_step": 383556, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.093628406524658, "global_step": 383557, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1014254093170166, "global_step": 383558, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1839306354522705, "global_step": 383559, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2024295330047607, "global_step": 383560, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.063706159591675, "global_step": 383561, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1189043521881104, "global_step": 383562, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0758893489837646, "global_step": 383563, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1521222591400146, "global_step": 383564, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1018080711364746, "global_step": 383565, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0612266063690186, "global_step": 383566, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1523289680480957, "global_step": 383567, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1639187335968018, "global_step": 383568, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.153109312057495, "global_step": 383569, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0479681491851807, "global_step": 383570, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.128746271133423, "global_step": 383571, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0755083560943604, "global_step": 383572, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1007943153381348, "global_step": 383573, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.079975128173828, "global_step": 383574, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2027082443237305, "global_step": 383575, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.043199062347412, "global_step": 383576, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0580263137817383, "global_step": 383577, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.101314067840576, "global_step": 383578, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.104191303253174, "global_step": 383579, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0466794967651367, "global_step": 383580, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0679328441619873, "global_step": 383581, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.093170166015625, "global_step": 383582, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0183417797088623, "global_step": 383583, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.216313123703003, "global_step": 383584, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.10714054107666, "global_step": 383585, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.078113555908203, "global_step": 383586, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1130433082580566, "global_step": 383587, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1047658920288086, "global_step": 383588, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.063593864440918, "global_step": 383589, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0944247245788574, "global_step": 383590, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0978126525878906, "global_step": 383591, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1262259483337402, "global_step": 383592, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0893192291259766, "global_step": 383593, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1506311893463135, "global_step": 383594, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1846108436584473, "global_step": 383595, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.058431386947632, "global_step": 383596, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1379706859588623, "global_step": 383597, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1196258068084717, "global_step": 383598, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0975499153137207, "global_step": 383599, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0631511211395264, "global_step": 383600, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0232656002044678, "global_step": 383601, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.12738037109375, "global_step": 383602, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.106365442276001, "global_step": 383603, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.168980836868286, "global_step": 383604, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1457083225250244, "global_step": 383605, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.030998468399048, "global_step": 383606, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.163238286972046, "global_step": 383607, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.113588571548462, "global_step": 383608, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.162783145904541, "global_step": 383609, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.105604410171509, "global_step": 383610, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0741021633148193, "global_step": 383611, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.142864942550659, "global_step": 383612, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0909831523895264, "global_step": 383613, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.124936103820801, "global_step": 383614, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0723419189453125, "global_step": 383615, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.115151882171631, "global_step": 383616, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0667693614959717, "global_step": 383617, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.08323073387146, "global_step": 383618, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1475844383239746, "global_step": 383619, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.047722578048706, "global_step": 383620, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.153848648071289, "global_step": 383621, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.105268716812134, "global_step": 383622, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0474987030029297, "global_step": 383623, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1848442554473877, "global_step": 383624, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0901896953582764, "global_step": 383625, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.095447301864624, "global_step": 383626, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2198233604431152, "global_step": 383627, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.115657329559326, "global_step": 383628, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0576515197753906, "global_step": 383629, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.01601243019104, "global_step": 383630, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1276450157165527, "global_step": 383631, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0942397117614746, "global_step": 383632, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1353261470794678, "global_step": 383633, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.173834800720215, "global_step": 383634, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0817196369171143, "global_step": 383635, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.050312042236328, "global_step": 383636, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.17952561378479, "global_step": 383637, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.181652784347534, "global_step": 383638, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1614162921905518, "global_step": 383639, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1579506397247314, "global_step": 383640, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.054013967514038, "global_step": 383641, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.115389347076416, "global_step": 383642, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.109739065170288, "global_step": 383643, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0237200260162354, "global_step": 383644, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.094431161880493, "global_step": 383645, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0651402473449707, "global_step": 383646, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0158333778381348, "global_step": 383647, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1667678356170654, "global_step": 383648, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.076895236968994, "global_step": 383649, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.06697940826416, "global_step": 383650, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0741946697235107, "global_step": 383651, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1709351539611816, "global_step": 383652, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.110398769378662, "global_step": 383653, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.111983299255371, "global_step": 383654, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1167807579040527, "global_step": 383655, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1477792263031006, "global_step": 383656, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.156040906906128, "global_step": 383657, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.022385358810425, "global_step": 383658, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2255265712738037, "global_step": 383659, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1246325969696045, "global_step": 383660, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.082911252975464, "global_step": 383661, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.144775629043579, "global_step": 383662, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1251304149627686, "global_step": 383663, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1137452125549316, "global_step": 383664, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1040635108947754, "global_step": 383665, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.145296096801758, "global_step": 383666, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1206705570220947, "global_step": 383667, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1057708263397217, "global_step": 383668, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1481621265411377, "global_step": 383669, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.154839277267456, "global_step": 383670, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.095308542251587, "global_step": 383671, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.132002115249634, "global_step": 383672, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.167163610458374, "global_step": 383673, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0834484100341797, "global_step": 383674, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.036818504333496, "global_step": 383675, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.025559902191162, "global_step": 383676, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2001349925994873, "global_step": 383677, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1709165573120117, "global_step": 383678, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.082488536834717, "global_step": 383679, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.103832483291626, "global_step": 383680, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.119304895401001, "global_step": 383681, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1756069660186768, "global_step": 383682, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1517555713653564, "global_step": 383683, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.091494560241699, "global_step": 383684, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1461780071258545, "global_step": 383685, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0983119010925293, "global_step": 383686, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2268919944763184, "global_step": 383687, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0711793899536133, "global_step": 383688, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.144803285598755, "global_step": 383689, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.150890350341797, "global_step": 383690, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.097990036010742, "global_step": 383691, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1118409633636475, "global_step": 383692, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1187779903411865, "global_step": 383693, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.113581657409668, "global_step": 383694, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.125044584274292, "global_step": 383695, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1470987796783447, "global_step": 383696, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0923991203308105, "global_step": 383697, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.085085868835449, "global_step": 383698, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1744396686553955, "global_step": 383699, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.087845802307129, "global_step": 383700, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0592572689056396, "global_step": 383701, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0800418853759766, "global_step": 383702, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.08369779586792, "global_step": 383703, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.107198476791382, "global_step": 383704, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1732232570648193, "global_step": 383705, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0872464179992676, "global_step": 383706, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1173174381256104, "global_step": 383707, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0880603790283203, "global_step": 383708, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.050482749938965, "global_step": 383709, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.092345952987671, "global_step": 383710, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1342227458953857, "global_step": 383711, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.065117835998535, "global_step": 383712, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.059220314025879, "global_step": 383713, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0813276767730713, "global_step": 383714, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1026620864868164, "global_step": 383715, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.090153455734253, "global_step": 383716, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.153398036956787, "global_step": 383717, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1303114891052246, "global_step": 383718, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.062265157699585, "global_step": 383719, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1442136764526367, "global_step": 383720, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1470558643341064, "global_step": 383721, "epoch": 745, "lr": 5e-05}
{"train_loss": 1.9593406915664673, "global_step": 383722, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.066098690032959, "global_step": 383723, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1031832695007324, "global_step": 383724, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2181763648986816, "global_step": 383725, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.10274076461792, "global_step": 383726, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.107389450073242, "global_step": 383727, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.112194299697876, "global_step": 383728, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0578927993774414, "global_step": 383729, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.127901554107666, "global_step": 383730, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.096867799758911, "global_step": 383731, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.10176157951355, "global_step": 383732, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.113658905029297, "global_step": 383733, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0433382987976074, "global_step": 383734, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.082054853439331, "global_step": 383735, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.069939136505127, "global_step": 383736, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.067765712738037, "global_step": 383737, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1938037872314453, "global_step": 383738, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.052935838699341, "global_step": 383739, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.081789970397949, "global_step": 383740, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0471487045288086, "global_step": 383741, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1328999996185303, "global_step": 383742, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1028451919555664, "global_step": 383743, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.065945863723755, "global_step": 383744, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1091928482055664, "global_step": 383745, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.072983741760254, "global_step": 383746, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1369333267211914, "global_step": 383747, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.128459930419922, "global_step": 383748, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0532710552215576, "global_step": 383749, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1609561443328857, "global_step": 383750, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1267740726470947, "global_step": 383751, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0001211166381836, "global_step": 383752, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.149714469909668, "global_step": 383753, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.074211597442627, "global_step": 383754, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0965590476989746, "global_step": 383755, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0479443073272705, "global_step": 383756, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1102454662323, "global_step": 383757, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1299972534179688, "global_step": 383758, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.138413667678833, "global_step": 383759, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.120375156402588, "global_step": 383760, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0506107807159424, "global_step": 383761, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0938236713409424, "global_step": 383762, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1268110275268555, "global_step": 383763, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0529329776763916, "global_step": 383764, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1167056560516357, "global_step": 383765, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.187237024307251, "global_step": 383766, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.139868974685669, "global_step": 383767, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0948805809020996, "global_step": 383768, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.080292224884033, "global_step": 383769, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.153325080871582, "global_step": 383770, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.067413091659546, "global_step": 383771, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0559799671173096, "global_step": 383772, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.141763210296631, "global_step": 383773, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2301254272460938, "global_step": 383774, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.114536762237549, "global_step": 383775, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.138080596923828, "global_step": 383776, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0834810733795166, "global_step": 383777, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.107712507247925, "global_step": 383778, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.099492311477661, "global_step": 383779, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0916950702667236, "global_step": 383780, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1300039291381836, "global_step": 383781, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1625561714172363, "global_step": 383782, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0602450370788574, "global_step": 383783, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.102602481842041, "global_step": 383784, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1112112998962402, "global_step": 383785, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.15787410736084, "global_step": 383786, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.024193525314331, "global_step": 383787, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0541694164276123, "global_step": 383788, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.129434823989868, "global_step": 383789, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1156458854675293, "global_step": 383790, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1639814376831055, "global_step": 383791, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1272754669189453, "global_step": 383792, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.192005157470703, "global_step": 383793, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1168107986450195, "global_step": 383794, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0801894664764404, "global_step": 383795, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.15502667427063, "global_step": 383796, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.107712984085083, "global_step": 383797, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0635032653808594, "global_step": 383798, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0473461151123047, "global_step": 383799, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1310744285583496, "global_step": 383800, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1433494091033936, "global_step": 383801, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.129150867462158, "global_step": 383802, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1518967151641846, "global_step": 383803, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.226425886154175, "global_step": 383804, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1549301147460938, "global_step": 383805, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0880398750305176, "global_step": 383806, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1439008712768555, "global_step": 383807, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0777060985565186, "global_step": 383808, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.191650152206421, "global_step": 383809, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.001072406768799, "global_step": 383810, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.073779344558716, "global_step": 383811, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0459022521972656, "global_step": 383812, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.103888988494873, "global_step": 383813, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.10432767868042, "global_step": 383814, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1767139434814453, "global_step": 383815, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1881585121154785, "global_step": 383816, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.188190221786499, "global_step": 383817, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1718547344207764, "global_step": 383818, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0768702030181885, "global_step": 383819, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.050814390182495, "global_step": 383820, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0659286975860596, "global_step": 383821, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1140058040618896, "global_step": 383822, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0900325775146484, "global_step": 383823, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1710097789764404, "global_step": 383824, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0806219577789307, "global_step": 383825, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.067082166671753, "global_step": 383826, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.144103527069092, "global_step": 383827, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.112239122390747, "global_step": 383828, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1040101051330566, "global_step": 383829, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.043304681777954, "global_step": 383830, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.152697801589966, "global_step": 383831, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.103311777114868, "global_step": 383832, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.077608823776245, "global_step": 383833, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.13374662399292, "global_step": 383834, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0930824279785156, "global_step": 383835, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1407647132873535, "global_step": 383836, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0498366355895996, "global_step": 383837, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1359236240386963, "global_step": 383838, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.06523060798645, "global_step": 383839, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.179029941558838, "global_step": 383840, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1691200733184814, "global_step": 383841, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.2322189807891846, "global_step": 383842, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0654377937316895, "global_step": 383843, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1187212467193604, "global_step": 383844, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0894863605499268, "global_step": 383845, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0615897178649902, "global_step": 383846, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0806472301483154, "global_step": 383847, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.146646738052368, "global_step": 383848, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0327906608581543, "global_step": 383849, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1299474239349365, "global_step": 383850, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.0451223850250244, "global_step": 383851, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.03011155128479, "global_step": 383852, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.161646604537964, "global_step": 383853, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1169655323028564, "global_step": 383854, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1548311710357666, "global_step": 383855, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.1029739379882812, "global_step": 383856, "epoch": 745, "lr": 5e-05}
{"train_loss": 2.090049982070923, "global_step": 383857, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.037032127380371, "global_step": 383858, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0110063552856445, "global_step": 383859, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0754380226135254, "global_step": 383860, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1799118518829346, "global_step": 383861, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.034501552581787, "global_step": 383862, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0961415767669678, "global_step": 383863, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.003117561340332, "global_step": 383864, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.2045207023620605, "global_step": 383865, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0386226177215576, "global_step": 383866, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0328450202941895, "global_step": 383867, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1616873741149902, "global_step": 383868, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1598236560821533, "global_step": 383869, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1688454151153564, "global_step": 383870, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0470523834228516, "global_step": 383871, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1843101978302, "global_step": 383872, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1211934089660645, "global_step": 383873, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0912561416625977, "global_step": 383874, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.130215883255005, "global_step": 383875, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1034910678863525, "global_step": 383876, "epoch": 746, "lr": 5e-05}
{"train_loss": 1.9828667640686035, "global_step": 383877, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1472458839416504, "global_step": 383878, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0707204341888428, "global_step": 383879, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0467946529388428, "global_step": 383880, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.097935676574707, "global_step": 383881, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1108155250549316, "global_step": 383882, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.081629991531372, "global_step": 383883, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1217916011810303, "global_step": 383884, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.00131893157959, "global_step": 383885, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1275129318237305, "global_step": 383886, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.084852933883667, "global_step": 383887, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1223909854888916, "global_step": 383888, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0156116485595703, "global_step": 383889, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.084097385406494, "global_step": 383890, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.031235456466675, "global_step": 383891, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0618534088134766, "global_step": 383892, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0360708236694336, "global_step": 383893, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.085956335067749, "global_step": 383894, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0490875244140625, "global_step": 383895, "epoch": 746, "lr": 5e-05}
{"train_loss": 1.9880644083023071, "global_step": 383896, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.090756893157959, "global_step": 383897, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.024247407913208, "global_step": 383898, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.003504753112793, "global_step": 383899, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0635647773742676, "global_step": 383900, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.127511739730835, "global_step": 383901, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1454010009765625, "global_step": 383902, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1585519313812256, "global_step": 383903, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0793776512145996, "global_step": 383904, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.032719850540161, "global_step": 383905, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0536367893218994, "global_step": 383906, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.137155294418335, "global_step": 383907, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0681161880493164, "global_step": 383908, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0386738777160645, "global_step": 383909, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1487746238708496, "global_step": 383910, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.195582151412964, "global_step": 383911, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1437933444976807, "global_step": 383912, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0984458923339844, "global_step": 383913, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.086700201034546, "global_step": 383914, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1535990238189697, "global_step": 383915, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1415786743164062, "global_step": 383916, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.126279354095459, "global_step": 383917, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.15427303314209, "global_step": 383918, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.103639841079712, "global_step": 383919, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.089202880859375, "global_step": 383920, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.20418643951416, "global_step": 383921, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1349434852600098, "global_step": 383922, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1880176067352295, "global_step": 383923, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0981876850128174, "global_step": 383924, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1310179233551025, "global_step": 383925, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1005494594573975, "global_step": 383926, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0947182178497314, "global_step": 383927, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.168569803237915, "global_step": 383928, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1043059825897217, "global_step": 383929, "epoch": 746, "lr": 5e-05}
{"train_loss": 1.9925637245178223, "global_step": 383930, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.161956548690796, "global_step": 383931, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.072950839996338, "global_step": 383932, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0637142658233643, "global_step": 383933, "epoch": 746, "lr": 5e-05}
{"train_loss": 1.9592558145523071, "global_step": 383934, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0904483795166016, "global_step": 383935, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.11761474609375, "global_step": 383936, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.101367712020874, "global_step": 383937, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0333163738250732, "global_step": 383938, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0383243560791016, "global_step": 383939, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0476603507995605, "global_step": 383940, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.167548179626465, "global_step": 383941, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1809308528900146, "global_step": 383942, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.196399688720703, "global_step": 383943, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.076184034347534, "global_step": 383944, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0851027965545654, "global_step": 383945, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.052382469177246, "global_step": 383946, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.111309051513672, "global_step": 383947, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1234290599823, "global_step": 383948, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0771634578704834, "global_step": 383949, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0643556118011475, "global_step": 383950, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1713497638702393, "global_step": 383951, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.130281925201416, "global_step": 383952, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.135568857192993, "global_step": 383953, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1701698303222656, "global_step": 383954, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.146662950515747, "global_step": 383955, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.138253688812256, "global_step": 383956, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.111424207687378, "global_step": 383957, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0209786891937256, "global_step": 383958, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.097238302230835, "global_step": 383959, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.081728458404541, "global_step": 383960, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.106280565261841, "global_step": 383961, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.063417434692383, "global_step": 383962, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0989222526550293, "global_step": 383963, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1600849628448486, "global_step": 383964, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0665297508239746, "global_step": 383965, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0042145252227783, "global_step": 383966, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.085261583328247, "global_step": 383967, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.040724277496338, "global_step": 383968, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.089686393737793, "global_step": 383969, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.04207706451416, "global_step": 383970, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.111074924468994, "global_step": 383971, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0934560298919678, "global_step": 383972, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0883026123046875, "global_step": 383973, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0794472694396973, "global_step": 383974, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.062267780303955, "global_step": 383975, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.120302438735962, "global_step": 383976, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0824294090270996, "global_step": 383977, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.119368076324463, "global_step": 383978, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.161975383758545, "global_step": 383979, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.05721378326416, "global_step": 383980, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.190042734146118, "global_step": 383981, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0074126720428467, "global_step": 383982, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.169839382171631, "global_step": 383983, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.094961404800415, "global_step": 383984, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1823484897613525, "global_step": 383985, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.017608880996704, "global_step": 383986, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0851149559020996, "global_step": 383987, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0081846714019775, "global_step": 383988, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1038897037506104, "global_step": 383989, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0705313682556152, "global_step": 383990, "epoch": 746, "lr": 5e-05}
{"train_loss": 1.98063325881958, "global_step": 383991, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1266908645629883, "global_step": 383992, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1855883598327637, "global_step": 383993, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1917920112609863, "global_step": 383994, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.12656569480896, "global_step": 383995, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1426451206207275, "global_step": 383996, "epoch": 746, "lr": 5e-05}
{"train_loss": 1.9996464252471924, "global_step": 383997, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.105189323425293, "global_step": 383998, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0484142303466797, "global_step": 383999, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.058380365371704, "global_step": 384000, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.135460376739502, "global_step": 384001, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.135463237762451, "global_step": 384002, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1534900665283203, "global_step": 384003, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0783870220184326, "global_step": 384004, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1138198375701904, "global_step": 384005, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1022393703460693, "global_step": 384006, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.075258493423462, "global_step": 384007, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.155667543411255, "global_step": 384008, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.072803020477295, "global_step": 384009, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.149305820465088, "global_step": 384010, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.093520402908325, "global_step": 384011, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1176939010620117, "global_step": 384012, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1033236980438232, "global_step": 384013, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0887348651885986, "global_step": 384014, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.058417320251465, "global_step": 384015, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.15520977973938, "global_step": 384016, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.061063051223755, "global_step": 384017, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.181884288787842, "global_step": 384018, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.072985887527466, "global_step": 384019, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0508713722229004, "global_step": 384020, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0998284816741943, "global_step": 384021, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0505378246307373, "global_step": 384022, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.049692153930664, "global_step": 384023, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1367597579956055, "global_step": 384024, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1174299716949463, "global_step": 384025, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.106637716293335, "global_step": 384026, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0999577045440674, "global_step": 384027, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.15444278717041, "global_step": 384028, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1024296283721924, "global_step": 384029, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0757410526275635, "global_step": 384030, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1478612422943115, "global_step": 384031, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1281678676605225, "global_step": 384032, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1028406620025635, "global_step": 384033, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0979950428009033, "global_step": 384034, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.128664255142212, "global_step": 384035, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.048691987991333, "global_step": 384036, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0936355590820312, "global_step": 384037, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.047039031982422, "global_step": 384038, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.144713878631592, "global_step": 384039, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.000079393386841, "global_step": 384040, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0823214054107666, "global_step": 384041, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.111825466156006, "global_step": 384042, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1207096576690674, "global_step": 384043, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.260601758956909, "global_step": 384044, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.084350109100342, "global_step": 384045, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1040029525756836, "global_step": 384046, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.032536029815674, "global_step": 384047, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.019242525100708, "global_step": 384048, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0968310832977295, "global_step": 384049, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0793426036834717, "global_step": 384050, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1272432804107666, "global_step": 384051, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0801644325256348, "global_step": 384052, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.069692850112915, "global_step": 384053, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0566341876983643, "global_step": 384054, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1229398250579834, "global_step": 384055, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.01912260055542, "global_step": 384056, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0599730014801025, "global_step": 384057, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1472201347351074, "global_step": 384058, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0115878582000732, "global_step": 384059, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.093038558959961, "global_step": 384060, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0964365005493164, "global_step": 384061, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.056081533432007, "global_step": 384062, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1704211235046387, "global_step": 384063, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0329298973083496, "global_step": 384064, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0920722484588623, "global_step": 384065, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.108753204345703, "global_step": 384066, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.080383777618408, "global_step": 384067, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1323611736297607, "global_step": 384068, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.032466173171997, "global_step": 384069, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0491302013397217, "global_step": 384070, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.016178846359253, "global_step": 384071, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1002070903778076, "global_step": 384072, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.073942184448242, "global_step": 384073, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.075748920440674, "global_step": 384074, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.095541477203369, "global_step": 384075, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.080618381500244, "global_step": 384076, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0850749015808105, "global_step": 384077, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1215007305145264, "global_step": 384078, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.119196891784668, "global_step": 384079, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0728847980499268, "global_step": 384080, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0973520278930664, "global_step": 384081, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0476202964782715, "global_step": 384082, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.083845853805542, "global_step": 384083, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1402881145477295, "global_step": 384084, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.190974712371826, "global_step": 384085, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.073265314102173, "global_step": 384086, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1399083137512207, "global_step": 384087, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0667829513549805, "global_step": 384088, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0592989921569824, "global_step": 384089, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.12381911277771, "global_step": 384090, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.04013991355896, "global_step": 384091, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0619735717773438, "global_step": 384092, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.103947401046753, "global_step": 384093, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.084153413772583, "global_step": 384094, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.102346420288086, "global_step": 384095, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.054783821105957, "global_step": 384096, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0362677574157715, "global_step": 384097, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0685291290283203, "global_step": 384098, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.091790199279785, "global_step": 384099, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0912411212921143, "global_step": 384100, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0500404834747314, "global_step": 384101, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.109773635864258, "global_step": 384102, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0344128608703613, "global_step": 384103, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0569605827331543, "global_step": 384104, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.074988603591919, "global_step": 384105, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.075728178024292, "global_step": 384106, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.149808168411255, "global_step": 384107, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0995688438415527, "global_step": 384108, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.05277943611145, "global_step": 384109, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1263182163238525, "global_step": 384110, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1585402488708496, "global_step": 384111, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.08854341506958, "global_step": 384112, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1399569511413574, "global_step": 384113, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.10040283203125, "global_step": 384114, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0743331909179688, "global_step": 384115, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.06758975982666, "global_step": 384116, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.099673271179199, "global_step": 384117, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.175685167312622, "global_step": 384118, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0505259037017822, "global_step": 384119, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1052024364471436, "global_step": 384120, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0857458114624023, "global_step": 384121, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0245072841644287, "global_step": 384122, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0990524291992188, "global_step": 384123, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.071000814437866, "global_step": 384124, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0061376094818115, "global_step": 384125, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1626646518707275, "global_step": 384126, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.071767568588257, "global_step": 384127, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1469497680664062, "global_step": 384128, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1675069332122803, "global_step": 384129, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0701401233673096, "global_step": 384130, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.04367733001709, "global_step": 384131, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.121992826461792, "global_step": 384132, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.20859956741333, "global_step": 384133, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.158781051635742, "global_step": 384134, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0767509937286377, "global_step": 384135, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1013660430908203, "global_step": 384136, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1682229042053223, "global_step": 384137, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.020151138305664, "global_step": 384138, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.094527244567871, "global_step": 384139, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0970046520233154, "global_step": 384140, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1234700679779053, "global_step": 384141, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0630264282226562, "global_step": 384142, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1156246662139893, "global_step": 384143, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1229753494262695, "global_step": 384144, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1287682056427, "global_step": 384145, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.067549705505371, "global_step": 384146, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.091193675994873, "global_step": 384147, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1177573204040527, "global_step": 384148, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.191788673400879, "global_step": 384149, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.167182445526123, "global_step": 384150, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.160665512084961, "global_step": 384151, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1702263355255127, "global_step": 384152, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.021602153778076, "global_step": 384153, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.190460443496704, "global_step": 384154, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.033310651779175, "global_step": 384155, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1326828002929688, "global_step": 384156, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.147879123687744, "global_step": 384157, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.173729419708252, "global_step": 384158, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1050362586975098, "global_step": 384159, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.07381010055542, "global_step": 384160, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0858421325683594, "global_step": 384161, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1340997219085693, "global_step": 384162, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.046588659286499, "global_step": 384163, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.107267379760742, "global_step": 384164, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0105695724487305, "global_step": 384165, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0810070037841797, "global_step": 384166, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.098217725753784, "global_step": 384167, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.062530994415283, "global_step": 384168, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.165375232696533, "global_step": 384169, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.039609909057617, "global_step": 384170, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0185725688934326, "global_step": 384171, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.061479330062866, "global_step": 384172, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0747287273406982, "global_step": 384173, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1368699073791504, "global_step": 384174, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0099103450775146, "global_step": 384175, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0595955848693848, "global_step": 384176, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0538041591644287, "global_step": 384177, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0717852115631104, "global_step": 384178, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.116018533706665, "global_step": 384179, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.065922737121582, "global_step": 384180, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0413968563079834, "global_step": 384181, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.141895055770874, "global_step": 384182, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0904059410095215, "global_step": 384183, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1357173919677734, "global_step": 384184, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.102996349334717, "global_step": 384185, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.106879949569702, "global_step": 384186, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1701548099517822, "global_step": 384187, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1014511585235596, "global_step": 384188, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1303319931030273, "global_step": 384189, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0795540809631348, "global_step": 384190, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1102476119995117, "global_step": 384191, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1574606895446777, "global_step": 384192, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.09414005279541, "global_step": 384193, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1308412551879883, "global_step": 384194, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.097999095916748, "global_step": 384195, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.237300157546997, "global_step": 384196, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1146469116210938, "global_step": 384197, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1900835037231445, "global_step": 384198, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.090095281600952, "global_step": 384199, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.162890911102295, "global_step": 384200, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1031320095062256, "global_step": 384201, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.043632984161377, "global_step": 384202, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.169914722442627, "global_step": 384203, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.083869218826294, "global_step": 384204, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0518548488616943, "global_step": 384205, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1268651485443115, "global_step": 384206, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1611549854278564, "global_step": 384207, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0815188884735107, "global_step": 384208, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.037536144256592, "global_step": 384209, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.12587571144104, "global_step": 384210, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.167158603668213, "global_step": 384211, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0573925971984863, "global_step": 384212, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.079333782196045, "global_step": 384213, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1640071868896484, "global_step": 384214, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1351470947265625, "global_step": 384215, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1144280433654785, "global_step": 384216, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1454811096191406, "global_step": 384217, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0309932231903076, "global_step": 384218, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0951316356658936, "global_step": 384219, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1771442890167236, "global_step": 384220, "epoch": 746, "lr": 5e-05}
{"train_loss": 1.9908275604248047, "global_step": 384221, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.096874952316284, "global_step": 384222, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0863871574401855, "global_step": 384223, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0109174251556396, "global_step": 384224, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0826351642608643, "global_step": 384225, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0762786865234375, "global_step": 384226, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1077778339385986, "global_step": 384227, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.152634859085083, "global_step": 384228, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0378358364105225, "global_step": 384229, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.156928300857544, "global_step": 384230, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.154815435409546, "global_step": 384231, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1082265377044678, "global_step": 384232, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1932387351989746, "global_step": 384233, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1458804607391357, "global_step": 384234, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1423070430755615, "global_step": 384235, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.113537549972534, "global_step": 384236, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.046719789505005, "global_step": 384237, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.052229166030884, "global_step": 384238, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1038780212402344, "global_step": 384239, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1428208351135254, "global_step": 384240, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.164437770843506, "global_step": 384241, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0997114181518555, "global_step": 384242, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.165055751800537, "global_step": 384243, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1104044914245605, "global_step": 384244, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1452908515930176, "global_step": 384245, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1220879554748535, "global_step": 384246, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0748674869537354, "global_step": 384247, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1556684970855713, "global_step": 384248, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.12202525138855, "global_step": 384249, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.08355450630188, "global_step": 384250, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0340518951416016, "global_step": 384251, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.094740152359009, "global_step": 384252, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0650479793548584, "global_step": 384253, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.003490447998047, "global_step": 384254, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.094778537750244, "global_step": 384255, "epoch": 746, "lr": 5e-05}
{"train_loss": 1.9467544555664062, "global_step": 384256, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.091723918914795, "global_step": 384257, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1827585697174072, "global_step": 384258, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1197969913482666, "global_step": 384259, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.05051851272583, "global_step": 384260, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1005258560180664, "global_step": 384261, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0985090732574463, "global_step": 384262, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1089375019073486, "global_step": 384263, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1385440826416016, "global_step": 384264, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1663951873779297, "global_step": 384265, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1314046382904053, "global_step": 384266, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1503264904022217, "global_step": 384267, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.067614793777466, "global_step": 384268, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0854172706604004, "global_step": 384269, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0687694549560547, "global_step": 384270, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.081987142562866, "global_step": 384271, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.151175022125244, "global_step": 384272, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0953991413116455, "global_step": 384273, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1549065113067627, "global_step": 384274, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1174590587615967, "global_step": 384275, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0803024768829346, "global_step": 384276, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1148033142089844, "global_step": 384277, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0657756328582764, "global_step": 384278, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.166428804397583, "global_step": 384279, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0721278190612793, "global_step": 384280, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1128337383270264, "global_step": 384281, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1375346183776855, "global_step": 384282, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1248888969421387, "global_step": 384283, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0467233657836914, "global_step": 384284, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1271824836730957, "global_step": 384285, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.061643362045288, "global_step": 384286, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.183180332183838, "global_step": 384287, "epoch": 746, "lr": 5e-05}
{"train_loss": 1.990291953086853, "global_step": 384288, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.116543769836426, "global_step": 384289, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1130638122558594, "global_step": 384290, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.220686912536621, "global_step": 384291, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.2068939208984375, "global_step": 384292, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0843446254730225, "global_step": 384293, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0371532440185547, "global_step": 384294, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1108953952789307, "global_step": 384295, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.111839532852173, "global_step": 384296, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.037965774536133, "global_step": 384297, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.138425350189209, "global_step": 384298, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.181779146194458, "global_step": 384299, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0651957988739014, "global_step": 384300, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1095387935638428, "global_step": 384301, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1733758449554443, "global_step": 384302, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1144793033599854, "global_step": 384303, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1518518924713135, "global_step": 384304, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1847405433654785, "global_step": 384305, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1220617294311523, "global_step": 384306, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1643965244293213, "global_step": 384307, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1506543159484863, "global_step": 384308, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.218005895614624, "global_step": 384309, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.186246395111084, "global_step": 384310, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1307382583618164, "global_step": 384311, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1258387565612793, "global_step": 384312, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1049892902374268, "global_step": 384313, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.085740327835083, "global_step": 384314, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1132380962371826, "global_step": 384315, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.062894582748413, "global_step": 384316, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.114227533340454, "global_step": 384317, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.018247127532959, "global_step": 384318, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.09537935256958, "global_step": 384319, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0652921199798584, "global_step": 384320, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1428534984588623, "global_step": 384321, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.085376739501953, "global_step": 384322, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.077409505844116, "global_step": 384323, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.066696882247925, "global_step": 384324, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.128627061843872, "global_step": 384325, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.17569637298584, "global_step": 384326, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1442103385925293, "global_step": 384327, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.116037607192993, "global_step": 384328, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0602915287017822, "global_step": 384329, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1615383625030518, "global_step": 384330, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.127392530441284, "global_step": 384331, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0752294063568115, "global_step": 384332, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1384494304656982, "global_step": 384333, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0444374084472656, "global_step": 384334, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.123417615890503, "global_step": 384335, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.137430429458618, "global_step": 384336, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0318405628204346, "global_step": 384337, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.207291603088379, "global_step": 384338, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.11993145942688, "global_step": 384339, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.015016555786133, "global_step": 384340, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0978777408599854, "global_step": 384341, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.094632625579834, "global_step": 384342, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0392394065856934, "global_step": 384343, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.113358974456787, "global_step": 384344, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.09192156791687, "global_step": 384345, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.032219886779785, "global_step": 384346, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0561609268188477, "global_step": 384347, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.07108211517334, "global_step": 384348, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1009063720703125, "global_step": 384349, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.15437650680542, "global_step": 384350, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.112274646759033, "global_step": 384351, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0874831676483154, "global_step": 384352, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.105548143386841, "global_step": 384353, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1327834129333496, "global_step": 384354, "epoch": 746, "lr": 5e-05}
{"train_loss": 1.9820530414581299, "global_step": 384355, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1430344581604004, "global_step": 384356, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1347289085388184, "global_step": 384357, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.193467378616333, "global_step": 384358, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.096142530441284, "global_step": 384359, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0921146869659424, "global_step": 384360, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1338655948638916, "global_step": 384361, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.109060049057007, "global_step": 384362, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.150817632675171, "global_step": 384363, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0848705768585205, "global_step": 384364, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.147176504135132, "global_step": 384365, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.070373773574829, "global_step": 384366, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0969672203063965, "global_step": 384367, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.159304618835449, "global_step": 384368, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1320996284484863, "global_step": 384369, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.138124704360962, "global_step": 384370, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.097329616546631, "global_step": 384371, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1430773735046387, "global_step": 384372, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.108375310897827, "global_step": 384373, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.110157012939453, "global_step": 384374, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.119718313217163, "global_step": 384375, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.084368944168091, "global_step": 384376, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.070894479751587, "global_step": 384377, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0883724689483643, "global_step": 384378, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1965084075927734, "global_step": 384379, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.124671459197998, "global_step": 384380, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.045440196990967, "global_step": 384381, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0547330379486084, "global_step": 384382, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0800628662109375, "global_step": 384383, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.170260429382324, "global_step": 384384, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.057234287261963, "global_step": 384385, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.04447865486145, "global_step": 384386, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.083033800125122, "global_step": 384387, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0652687549591064, "global_step": 384388, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.089144706726074, "global_step": 384389, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0818915367126465, "global_step": 384390, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0912036895751953, "global_step": 384391, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1345415115356445, "global_step": 384392, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.102909564971924, "global_step": 384393, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.173065423965454, "global_step": 384394, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.069025993347168, "global_step": 384395, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.051785707473755, "global_step": 384396, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.128861427307129, "global_step": 384397, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1206014156341553, "global_step": 384398, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.085040807723999, "global_step": 384399, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.085116386413574, "global_step": 384400, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.2583529949188232, "global_step": 384401, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1843414306640625, "global_step": 384402, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1175081729888916, "global_step": 384403, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.2147328853607178, "global_step": 384404, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0694074630737305, "global_step": 384405, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0400075912475586, "global_step": 384406, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1254281997680664, "global_step": 384407, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.010300636291504, "global_step": 384408, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0734710693359375, "global_step": 384409, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1110177040100098, "global_step": 384410, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1382763385772705, "global_step": 384411, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.139890670776367, "global_step": 384412, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.095019578933716, "global_step": 384413, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.029728889465332, "global_step": 384414, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.155409812927246, "global_step": 384415, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1101880073547363, "global_step": 384416, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.13016939163208, "global_step": 384417, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.063556432723999, "global_step": 384418, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1649725437164307, "global_step": 384419, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0773627758026123, "global_step": 384420, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.111274242401123, "global_step": 384421, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.048072099685669, "global_step": 384422, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.075098991394043, "global_step": 384423, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.076444149017334, "global_step": 384424, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1205177307128906, "global_step": 384425, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1391396522521973, "global_step": 384426, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1238694190979004, "global_step": 384427, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1497833728790283, "global_step": 384428, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0456314086914062, "global_step": 384429, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.12766170501709, "global_step": 384430, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.065537452697754, "global_step": 384431, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.168839693069458, "global_step": 384432, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1453394889831543, "global_step": 384433, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1233038902282715, "global_step": 384434, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1769840717315674, "global_step": 384435, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.137510299682617, "global_step": 384436, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0551235675811768, "global_step": 384437, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1545450687408447, "global_step": 384438, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.103539228439331, "global_step": 384439, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1143136024475098, "global_step": 384440, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1543097496032715, "global_step": 384441, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0485520362854004, "global_step": 384442, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0726475715637207, "global_step": 384443, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.100944757461548, "global_step": 384444, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0413973331451416, "global_step": 384445, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1843626499176025, "global_step": 384446, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1264240741729736, "global_step": 384447, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0943310260772705, "global_step": 384448, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0763354301452637, "global_step": 384449, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.097142457962036, "global_step": 384450, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0926051139831543, "global_step": 384451, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1376736164093018, "global_step": 384452, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0998165607452393, "global_step": 384453, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1092488765716553, "global_step": 384454, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.064079999923706, "global_step": 384455, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.105348825454712, "global_step": 384456, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.089665174484253, "global_step": 384457, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.2150096893310547, "global_step": 384458, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.117192268371582, "global_step": 384459, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0936875343322754, "global_step": 384460, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1388278007507324, "global_step": 384461, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1124672889709473, "global_step": 384462, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1100454330444336, "global_step": 384463, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.09675931930542, "global_step": 384464, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.054555654525757, "global_step": 384465, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.178846597671509, "global_step": 384466, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0382351875305176, "global_step": 384467, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1046600341796875, "global_step": 384468, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1428849697113037, "global_step": 384469, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.062736988067627, "global_step": 384470, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.102036952972412, "global_step": 384471, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.126893997192383, "global_step": 384472, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1065497398376465, "global_step": 384473, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.050816297531128, "global_step": 384474, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.091503143310547, "global_step": 384475, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1192049980163574, "global_step": 384476, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.087085008621216, "global_step": 384477, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1268720626831055, "global_step": 384478, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1200428009033203, "global_step": 384479, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.091916084289551, "global_step": 384480, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.199875593185425, "global_step": 384481, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1276462078094482, "global_step": 384482, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0701498985290527, "global_step": 384483, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1073412895202637, "global_step": 384484, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0503029823303223, "global_step": 384485, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.016148805618286, "global_step": 384486, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0736536979675293, "global_step": 384487, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.159898519515991, "global_step": 384488, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1133928298950195, "global_step": 384489, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.107588291168213, "global_step": 384490, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1129813194274902, "global_step": 384491, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1695165634155273, "global_step": 384492, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1781651973724365, "global_step": 384493, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.10894513130188, "global_step": 384494, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.146979570388794, "global_step": 384495, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.117927312850952, "global_step": 384496, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1687772274017334, "global_step": 384497, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1143534183502197, "global_step": 384498, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0999510288238525, "global_step": 384499, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0183560848236084, "global_step": 384500, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1854405403137207, "global_step": 384501, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.173797845840454, "global_step": 384502, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.181514024734497, "global_step": 384503, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0107204914093018, "global_step": 384504, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0715527534484863, "global_step": 384505, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.141650915145874, "global_step": 384506, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.157818078994751, "global_step": 384507, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.174154043197632, "global_step": 384508, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.112114906311035, "global_step": 384509, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1024746894836426, "global_step": 384510, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1764800548553467, "global_step": 384511, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1620497703552246, "global_step": 384512, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0574848651885986, "global_step": 384513, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0592126846313477, "global_step": 384514, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0874903202056885, "global_step": 384515, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0808794498443604, "global_step": 384516, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1189942359924316, "global_step": 384517, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.15504789352417, "global_step": 384518, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.117187738418579, "global_step": 384519, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1272740364074707, "global_step": 384520, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1536061763763428, "global_step": 384521, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.105607271194458, "global_step": 384522, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.140263080596924, "global_step": 384523, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1744463443756104, "global_step": 384524, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.10650372505188, "global_step": 384525, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0363852977752686, "global_step": 384526, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.2503857612609863, "global_step": 384527, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1246023178100586, "global_step": 384528, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1478991508483887, "global_step": 384529, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0841681957244873, "global_step": 384530, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.146533727645874, "global_step": 384531, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.063786745071411, "global_step": 384532, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0601298809051514, "global_step": 384533, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.174839496612549, "global_step": 384534, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0572304725646973, "global_step": 384535, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.115297555923462, "global_step": 384536, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1474733352661133, "global_step": 384537, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1110172271728516, "global_step": 384538, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.15775728225708, "global_step": 384539, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.2025434970855713, "global_step": 384540, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.058439254760742, "global_step": 384541, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1022231578826904, "global_step": 384542, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1227638721466064, "global_step": 384543, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1363167762756348, "global_step": 384544, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0484139919281006, "global_step": 384545, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0910561084747314, "global_step": 384546, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0565242767333984, "global_step": 384547, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.03200626373291, "global_step": 384548, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.157503843307495, "global_step": 384549, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.037834882736206, "global_step": 384550, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.075108766555786, "global_step": 384551, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0762810707092285, "global_step": 384552, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1194944381713867, "global_step": 384553, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.104855537414551, "global_step": 384554, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0377657413482666, "global_step": 384555, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0470476150512695, "global_step": 384556, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.13504695892334, "global_step": 384557, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1431925296783447, "global_step": 384558, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.087449550628662, "global_step": 384559, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1530065536499023, "global_step": 384560, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.085900068283081, "global_step": 384561, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1229567527770996, "global_step": 384562, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.208627939224243, "global_step": 384563, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.101740598678589, "global_step": 384564, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0960090160369873, "global_step": 384565, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.106663227081299, "global_step": 384566, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.113060474395752, "global_step": 384567, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1074488162994385, "global_step": 384568, "epoch": 746, "lr": 5e-05}
{"train_loss": 1.9968687295913696, "global_step": 384569, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1007182598114014, "global_step": 384570, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1450257301330566, "global_step": 384571, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.095463514328003, "global_step": 384572, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.065840244293213, "global_step": 384573, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.089942455291748, "global_step": 384574, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.125933885574341, "global_step": 384575, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.077052593231201, "global_step": 384576, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0347683429718018, "global_step": 384577, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.156721830368042, "global_step": 384578, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1086935997009277, "global_step": 384579, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.150697946548462, "global_step": 384580, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.087374448776245, "global_step": 384581, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1260409355163574, "global_step": 384582, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.111875057220459, "global_step": 384583, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0824196338653564, "global_step": 384584, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1458685398101807, "global_step": 384585, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.12381911277771, "global_step": 384586, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.054051160812378, "global_step": 384587, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.093717098236084, "global_step": 384588, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.151353359222412, "global_step": 384589, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1605968475341797, "global_step": 384590, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.067939519882202, "global_step": 384591, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.145548105239868, "global_step": 384592, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1340787410736084, "global_step": 384593, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.09509539604187, "global_step": 384594, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.149568796157837, "global_step": 384595, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0566256046295166, "global_step": 384596, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1487464904785156, "global_step": 384597, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.116472005844116, "global_step": 384598, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0168724060058594, "global_step": 384599, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.033337354660034, "global_step": 384600, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.064779043197632, "global_step": 384601, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.032137870788574, "global_step": 384602, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1406314373016357, "global_step": 384603, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.074888229370117, "global_step": 384604, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0903830528259277, "global_step": 384605, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.120171546936035, "global_step": 384606, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1521456241607666, "global_step": 384607, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.010084390640259, "global_step": 384608, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1775095462799072, "global_step": 384609, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0916929244995117, "global_step": 384610, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1063730716705322, "global_step": 384611, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0307979583740234, "global_step": 384612, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.166551113128662, "global_step": 384613, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.136439800262451, "global_step": 384614, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.181447744369507, "global_step": 384615, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.239028215408325, "global_step": 384616, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.157442569732666, "global_step": 384617, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.058643341064453, "global_step": 384618, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.20882511138916, "global_step": 384619, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.009950637817383, "global_step": 384620, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0716521739959717, "global_step": 384621, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1473898887634277, "global_step": 384622, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1644246578216553, "global_step": 384623, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.132046699523926, "global_step": 384624, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.085907220840454, "global_step": 384625, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.095717430114746, "global_step": 384626, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1641998291015625, "global_step": 384627, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0154128074645996, "global_step": 384628, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.131096363067627, "global_step": 384629, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.092921495437622, "global_step": 384630, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1302857398986816, "global_step": 384631, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1003921031951904, "global_step": 384632, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1166718006134033, "global_step": 384633, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.083245038986206, "global_step": 384634, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.024404525756836, "global_step": 384635, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.081040382385254, "global_step": 384636, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1032333374023438, "global_step": 384637, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.124037504196167, "global_step": 384638, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.122102737426758, "global_step": 384639, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0775489807128906, "global_step": 384640, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.085326671600342, "global_step": 384641, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.181731939315796, "global_step": 384642, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.126166343688965, "global_step": 384643, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.065523386001587, "global_step": 384644, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0237789154052734, "global_step": 384645, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1045217514038086, "global_step": 384646, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0855517387390137, "global_step": 384647, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.072007417678833, "global_step": 384648, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.113218307495117, "global_step": 384649, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0222463607788086, "global_step": 384650, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0754716396331787, "global_step": 384651, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.088165521621704, "global_step": 384652, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.13600754737854, "global_step": 384653, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0763940811157227, "global_step": 384654, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1530933380126953, "global_step": 384655, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1555659770965576, "global_step": 384656, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0813968181610107, "global_step": 384657, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.097529649734497, "global_step": 384658, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.140141248703003, "global_step": 384659, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.119943380355835, "global_step": 384660, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.2045674324035645, "global_step": 384661, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.12246036529541, "global_step": 384662, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0213546752929688, "global_step": 384663, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1234967708587646, "global_step": 384664, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.068344831466675, "global_step": 384665, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.099782943725586, "global_step": 384666, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0520124435424805, "global_step": 384667, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0846595764160156, "global_step": 384668, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.057844877243042, "global_step": 384669, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.058077335357666, "global_step": 384670, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1740806102752686, "global_step": 384671, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.059541940689087, "global_step": 384672, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0670008659362793, "global_step": 384673, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0918731689453125, "global_step": 384674, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.039423942565918, "global_step": 384675, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.068495750427246, "global_step": 384676, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.11796236038208, "global_step": 384677, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0821375846862793, "global_step": 384678, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.131910562515259, "global_step": 384679, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1141183376312256, "global_step": 384680, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1113226413726807, "global_step": 384681, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0417520999908447, "global_step": 384682, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.12252140045166, "global_step": 384683, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1474409103393555, "global_step": 384684, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1354355812072754, "global_step": 384685, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.050077199935913, "global_step": 384686, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1003217697143555, "global_step": 384687, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1095874309539795, "global_step": 384688, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1902830600738525, "global_step": 384689, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.02716326713562, "global_step": 384690, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1139883995056152, "global_step": 384691, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.045301914215088, "global_step": 384692, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0800912380218506, "global_step": 384693, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1273348331451416, "global_step": 384694, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0889487266540527, "global_step": 384695, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0958895683288574, "global_step": 384696, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1920571327209473, "global_step": 384697, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.182114601135254, "global_step": 384698, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0902984142303467, "global_step": 384699, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0749850273132324, "global_step": 384700, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0065388679504395, "global_step": 384701, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.15114164352417, "global_step": 384702, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1277105808258057, "global_step": 384703, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1950416564941406, "global_step": 384704, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.131910800933838, "global_step": 384705, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.109828472137451, "global_step": 384706, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.07890248298645, "global_step": 384707, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0552570819854736, "global_step": 384708, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.039994716644287, "global_step": 384709, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0619287490844727, "global_step": 384710, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1180033683776855, "global_step": 384711, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.115677833557129, "global_step": 384712, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0672547817230225, "global_step": 384713, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1268467903137207, "global_step": 384714, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.054401397705078, "global_step": 384715, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0859622955322266, "global_step": 384716, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1009011268615723, "global_step": 384717, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.033782958984375, "global_step": 384718, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.119173288345337, "global_step": 384719, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1531193256378174, "global_step": 384720, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.133991003036499, "global_step": 384721, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.149015188217163, "global_step": 384722, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.124363899230957, "global_step": 384723, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0495431423187256, "global_step": 384724, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1289525032043457, "global_step": 384725, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1316189765930176, "global_step": 384726, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.156081438064575, "global_step": 384727, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.156895637512207, "global_step": 384728, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0809485912323, "global_step": 384729, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1190967559814453, "global_step": 384730, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1400434970855713, "global_step": 384731, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.090240716934204, "global_step": 384732, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.123028039932251, "global_step": 384733, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0940608978271484, "global_step": 384734, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.169100761413574, "global_step": 384735, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1386234760284424, "global_step": 384736, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.097996473312378, "global_step": 384737, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.091628313064575, "global_step": 384738, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1512451171875, "global_step": 384739, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0371367931365967, "global_step": 384740, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.077472448348999, "global_step": 384741, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.203458786010742, "global_step": 384742, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1664130687713623, "global_step": 384743, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1297760009765625, "global_step": 384744, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.099513292312622, "global_step": 384745, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1355173587799072, "global_step": 384746, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.094951629638672, "global_step": 384747, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1425516605377197, "global_step": 384748, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.086106061935425, "global_step": 384749, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.2071735858917236, "global_step": 384750, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.2173893451690674, "global_step": 384751, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0366501808166504, "global_step": 384752, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0734264850616455, "global_step": 384753, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0511460304260254, "global_step": 384754, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1349520683288574, "global_step": 384755, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0611186027526855, "global_step": 384756, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1871867179870605, "global_step": 384757, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.083791971206665, "global_step": 384758, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.09781813621521, "global_step": 384759, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.096578598022461, "global_step": 384760, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0690643787384033, "global_step": 384761, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.092662811279297, "global_step": 384762, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.159700632095337, "global_step": 384763, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.11932635307312, "global_step": 384764, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.077765703201294, "global_step": 384765, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0549230575561523, "global_step": 384766, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1662378311157227, "global_step": 384767, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0716965198516846, "global_step": 384768, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.174103260040283, "global_step": 384769, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1539688110351562, "global_step": 384770, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1085762977600098, "global_step": 384771, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.085418701171875, "global_step": 384772, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0616586208343506, "global_step": 384773, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0056910514831543, "global_step": 384774, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.053711175918579, "global_step": 384775, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1242470741271973, "global_step": 384776, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1139326095581055, "global_step": 384777, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0962769985198975, "global_step": 384778, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.039486885070801, "global_step": 384779, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.054424285888672, "global_step": 384780, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.100996255874634, "global_step": 384781, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.2662100791931152, "global_step": 384782, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.11527681350708, "global_step": 384783, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1847586631774902, "global_step": 384784, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.2165467739105225, "global_step": 384785, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.090975522994995, "global_step": 384786, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.073967456817627, "global_step": 384787, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1624886989593506, "global_step": 384788, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1474130153656006, "global_step": 384789, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0779619216918945, "global_step": 384790, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0814549922943115, "global_step": 384791, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1215901374816895, "global_step": 384792, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1512820720672607, "global_step": 384793, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0788702964782715, "global_step": 384794, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1447479724884033, "global_step": 384795, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0712053775787354, "global_step": 384796, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.073944568634033, "global_step": 384797, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1248769760131836, "global_step": 384798, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.145494222640991, "global_step": 384799, "epoch": 746, "lr": 5e-05}
{"train_loss": 1.994505524635315, "global_step": 384800, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0581533908843994, "global_step": 384801, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0569403171539307, "global_step": 384802, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0636630058288574, "global_step": 384803, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1026337146759033, "global_step": 384804, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0701820850372314, "global_step": 384805, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.197293281555176, "global_step": 384806, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1446962356567383, "global_step": 384807, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1533141136169434, "global_step": 384808, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.113987445831299, "global_step": 384809, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.154757499694824, "global_step": 384810, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.078411102294922, "global_step": 384811, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1066553592681885, "global_step": 384812, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1662511825561523, "global_step": 384813, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.101755142211914, "global_step": 384814, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.082751750946045, "global_step": 384815, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0575921535491943, "global_step": 384816, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0706570148468018, "global_step": 384817, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0937657356262207, "global_step": 384818, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0303637981414795, "global_step": 384819, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.04827618598938, "global_step": 384820, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1156198978424072, "global_step": 384821, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.065887689590454, "global_step": 384822, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1026039123535156, "global_step": 384823, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1068363189697266, "global_step": 384824, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.1034672260284424, "global_step": 384825, "epoch": 746, "lr": 5e-05}
{"train_loss": 2.0453996658325195, "global_step": 384826, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0831403732299805, "global_step": 384827, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.146937608718872, "global_step": 384828, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.055359363555908, "global_step": 384829, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.09832501411438, "global_step": 384830, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1134538650512695, "global_step": 384831, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.104020595550537, "global_step": 384832, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.069349765777588, "global_step": 384833, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.042680025100708, "global_step": 384834, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0871224403381348, "global_step": 384835, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0492472648620605, "global_step": 384836, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.142629861831665, "global_step": 384837, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.183854818344116, "global_step": 384838, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.058699369430542, "global_step": 384839, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1130361557006836, "global_step": 384840, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0833864212036133, "global_step": 384841, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.066819190979004, "global_step": 384842, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0594258308410645, "global_step": 384843, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1326351165771484, "global_step": 384844, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.043846845626831, "global_step": 384845, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.17952299118042, "global_step": 384846, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.071962356567383, "global_step": 384847, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.092994213104248, "global_step": 384848, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1201858520507812, "global_step": 384849, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2004904747009277, "global_step": 384850, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.9725902080535889, "global_step": 384851, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.104372978210449, "global_step": 384852, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.028219223022461, "global_step": 384853, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0665674209594727, "global_step": 384854, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0912017822265625, "global_step": 384855, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.111633062362671, "global_step": 384856, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.033846616744995, "global_step": 384857, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.111196517944336, "global_step": 384858, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.070436477661133, "global_step": 384859, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0433332920074463, "global_step": 384860, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.047881603240967, "global_step": 384861, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0882413387298584, "global_step": 384862, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1045777797698975, "global_step": 384863, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0727760791778564, "global_step": 384864, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.134336471557617, "global_step": 384865, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.122598648071289, "global_step": 384866, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0580968856811523, "global_step": 384867, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0286340713500977, "global_step": 384868, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.044847249984741, "global_step": 384869, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0019168853759766, "global_step": 384870, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.127434730529785, "global_step": 384871, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0871689319610596, "global_step": 384872, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0851523876190186, "global_step": 384873, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0942726135253906, "global_step": 384874, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0395517349243164, "global_step": 384875, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.9883867502212524, "global_step": 384876, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.191534996032715, "global_step": 384877, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.096858501434326, "global_step": 384878, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.066854238510132, "global_step": 384879, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.041243314743042, "global_step": 384880, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1311261653900146, "global_step": 384881, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0782899856567383, "global_step": 384882, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0734362602233887, "global_step": 384883, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0632221698760986, "global_step": 384884, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0375053882598877, "global_step": 384885, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.048269748687744, "global_step": 384886, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2060160636901855, "global_step": 384887, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2390096187591553, "global_step": 384888, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0960185527801514, "global_step": 384889, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0915822982788086, "global_step": 384890, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.167651414871216, "global_step": 384891, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.140089273452759, "global_step": 384892, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.079644203186035, "global_step": 384893, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0288901329040527, "global_step": 384894, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1000213623046875, "global_step": 384895, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.181020975112915, "global_step": 384896, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.078080892562866, "global_step": 384897, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0451819896698, "global_step": 384898, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.01920223236084, "global_step": 384899, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.048640489578247, "global_step": 384900, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.156947612762451, "global_step": 384901, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.9731299877166748, "global_step": 384902, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.002457618713379, "global_step": 384903, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0399181842803955, "global_step": 384904, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.078404426574707, "global_step": 384905, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.077885866165161, "global_step": 384906, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0453343391418457, "global_step": 384907, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0865142345428467, "global_step": 384908, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.170607805252075, "global_step": 384909, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0815343856811523, "global_step": 384910, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1420187950134277, "global_step": 384911, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.020112991333008, "global_step": 384912, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.042402982711792, "global_step": 384913, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1147000789642334, "global_step": 384914, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1423070430755615, "global_step": 384915, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.168158531188965, "global_step": 384916, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.068786144256592, "global_step": 384917, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.173452615737915, "global_step": 384918, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0613505840301514, "global_step": 384919, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0874242782592773, "global_step": 384920, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1014244556427, "global_step": 384921, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1275885105133057, "global_step": 384922, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.075937032699585, "global_step": 384923, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0214643478393555, "global_step": 384924, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1600425243377686, "global_step": 384925, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0228688716888428, "global_step": 384926, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1527371406555176, "global_step": 384927, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0639102458953857, "global_step": 384928, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0290205478668213, "global_step": 384929, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0800464153289795, "global_step": 384930, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0504376888275146, "global_step": 384931, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0367982387542725, "global_step": 384932, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1719131469726562, "global_step": 384933, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0452473163604736, "global_step": 384934, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.100092649459839, "global_step": 384935, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0303051471710205, "global_step": 384936, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0964131355285645, "global_step": 384937, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1862239837646484, "global_step": 384938, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0882863998413086, "global_step": 384939, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0704708099365234, "global_step": 384940, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1597254276275635, "global_step": 384941, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.146495819091797, "global_step": 384942, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0806102752685547, "global_step": 384943, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1732935905456543, "global_step": 384944, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1879382133483887, "global_step": 384945, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0701732635498047, "global_step": 384946, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0642249584198, "global_step": 384947, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0889482498168945, "global_step": 384948, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0664517879486084, "global_step": 384949, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.071809768676758, "global_step": 384950, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0513031482696533, "global_step": 384951, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.163170099258423, "global_step": 384952, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0457074642181396, "global_step": 384953, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0501532554626465, "global_step": 384954, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.064643621444702, "global_step": 384955, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1302638053894043, "global_step": 384956, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1066176891326904, "global_step": 384957, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0744729042053223, "global_step": 384958, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0415992736816406, "global_step": 384959, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.041459560394287, "global_step": 384960, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0417304039001465, "global_step": 384961, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.163109302520752, "global_step": 384962, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.079319715499878, "global_step": 384963, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1017544269561768, "global_step": 384964, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.9768142700195312, "global_step": 384965, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.116384983062744, "global_step": 384966, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1638381481170654, "global_step": 384967, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1771488189697266, "global_step": 384968, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1047444343566895, "global_step": 384969, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.148721218109131, "global_step": 384970, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.031954288482666, "global_step": 384971, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2400779724121094, "global_step": 384972, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1608355045318604, "global_step": 384973, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.120857000350952, "global_step": 384974, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.223952293395996, "global_step": 384975, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1490633487701416, "global_step": 384976, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.127470016479492, "global_step": 384977, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0678389072418213, "global_step": 384978, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0537641048431396, "global_step": 384979, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1456046104431152, "global_step": 384980, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.200507879257202, "global_step": 384981, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.117452621459961, "global_step": 384982, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0722756385803223, "global_step": 384983, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0930731296539307, "global_step": 384984, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1533920764923096, "global_step": 384985, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0634047985076904, "global_step": 384986, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0978987216949463, "global_step": 384987, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1048059463500977, "global_step": 384988, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.082967519760132, "global_step": 384989, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.101724624633789, "global_step": 384990, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.209975004196167, "global_step": 384991, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1037187576293945, "global_step": 384992, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1811208724975586, "global_step": 384993, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.197591543197632, "global_step": 384994, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1523094177246094, "global_step": 384995, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.030306816101074, "global_step": 384996, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.055966854095459, "global_step": 384997, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1344234943389893, "global_step": 384998, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.053117513656616, "global_step": 384999, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0765724182128906, "global_step": 385000, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.108349084854126, "global_step": 385001, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.10703706741333, "global_step": 385002, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1915085315704346, "global_step": 385003, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1505284309387207, "global_step": 385004, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0979998111724854, "global_step": 385005, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0644824504852295, "global_step": 385006, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.147348165512085, "global_step": 385007, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1287434101104736, "global_step": 385008, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1040456295013428, "global_step": 385009, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.037240982055664, "global_step": 385010, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.086181640625, "global_step": 385011, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0865602493286133, "global_step": 385012, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.122408151626587, "global_step": 385013, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.163846015930176, "global_step": 385014, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.066786527633667, "global_step": 385015, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.185792922973633, "global_step": 385016, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.146275281906128, "global_step": 385017, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0509750843048096, "global_step": 385018, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1502199172973633, "global_step": 385019, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.057656764984131, "global_step": 385020, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1623754501342773, "global_step": 385021, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0844385623931885, "global_step": 385022, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.171349048614502, "global_step": 385023, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.150838851928711, "global_step": 385024, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1926331520080566, "global_step": 385025, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0623831748962402, "global_step": 385026, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0675156116485596, "global_step": 385027, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0716114044189453, "global_step": 385028, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1018455028533936, "global_step": 385029, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.05271053314209, "global_step": 385030, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0979843139648438, "global_step": 385031, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1059348583221436, "global_step": 385032, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1454997062683105, "global_step": 385033, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.124318838119507, "global_step": 385034, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0552401542663574, "global_step": 385035, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1061391830444336, "global_step": 385036, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0663068294525146, "global_step": 385037, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1822962760925293, "global_step": 385038, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.223783493041992, "global_step": 385039, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0245304107666016, "global_step": 385040, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0980615615844727, "global_step": 385041, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0227468013763428, "global_step": 385042, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1281025409698486, "global_step": 385043, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.184927463531494, "global_step": 385044, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0775108337402344, "global_step": 385045, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0848493576049805, "global_step": 385046, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.146555185317993, "global_step": 385047, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0915355682373047, "global_step": 385048, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.045997142791748, "global_step": 385049, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0990872383117676, "global_step": 385050, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0562753677368164, "global_step": 385051, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.087383985519409, "global_step": 385052, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.05482816696167, "global_step": 385053, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.057429552078247, "global_step": 385054, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1768901348114014, "global_step": 385055, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.147015333175659, "global_step": 385056, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0923285484313965, "global_step": 385057, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.097005605697632, "global_step": 385058, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1439242362976074, "global_step": 385059, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0895588397979736, "global_step": 385060, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.124986171722412, "global_step": 385061, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.125718832015991, "global_step": 385062, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.082202672958374, "global_step": 385063, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1227989196777344, "global_step": 385064, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1417980194091797, "global_step": 385065, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0741188526153564, "global_step": 385066, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0544934272766113, "global_step": 385067, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0646262168884277, "global_step": 385068, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.037346363067627, "global_step": 385069, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.9947395324707031, "global_step": 385070, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1104371547698975, "global_step": 385071, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1386494636535645, "global_step": 385072, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0499117374420166, "global_step": 385073, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1580474376678467, "global_step": 385074, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1052825450897217, "global_step": 385075, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.196235418319702, "global_step": 385076, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.037482976913452, "global_step": 385077, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.082101345062256, "global_step": 385078, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.027117967605591, "global_step": 385079, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0278279781341553, "global_step": 385080, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1705434322357178, "global_step": 385081, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.059109926223755, "global_step": 385082, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0959110260009766, "global_step": 385083, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1997711658477783, "global_step": 385084, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.098436117172241, "global_step": 385085, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0201220512390137, "global_step": 385086, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.122934579849243, "global_step": 385087, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.9881271123886108, "global_step": 385088, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.095107316970825, "global_step": 385089, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.114999294281006, "global_step": 385090, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1385488510131836, "global_step": 385091, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0589687824249268, "global_step": 385092, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1143600940704346, "global_step": 385093, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0745739936828613, "global_step": 385094, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.076218366622925, "global_step": 385095, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.100517749786377, "global_step": 385096, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.057241678237915, "global_step": 385097, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.119509220123291, "global_step": 385098, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0062804222106934, "global_step": 385099, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1205861568450928, "global_step": 385100, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.078300952911377, "global_step": 385101, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1116299629211426, "global_step": 385102, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1013875007629395, "global_step": 385103, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0998013019561768, "global_step": 385104, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.057370901107788, "global_step": 385105, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.084670066833496, "global_step": 385106, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1927199363708496, "global_step": 385107, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0763649940490723, "global_step": 385108, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.110373020172119, "global_step": 385109, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0600829124450684, "global_step": 385110, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.121527671813965, "global_step": 385111, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.047987699508667, "global_step": 385112, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.056995391845703, "global_step": 385113, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1503372192382812, "global_step": 385114, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0941643714904785, "global_step": 385115, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1159207820892334, "global_step": 385116, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1294007301330566, "global_step": 385117, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.180854082107544, "global_step": 385118, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.071819305419922, "global_step": 385119, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1241648197174072, "global_step": 385120, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.9875414371490479, "global_step": 385121, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0922534465789795, "global_step": 385122, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1422054767608643, "global_step": 385123, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0631258487701416, "global_step": 385124, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0783467292785645, "global_step": 385125, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.117744207382202, "global_step": 385126, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0234344005584717, "global_step": 385127, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0294244289398193, "global_step": 385128, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1738970279693604, "global_step": 385129, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1165573596954346, "global_step": 385130, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1655385494232178, "global_step": 385131, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.9464728832244873, "global_step": 385132, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.101572036743164, "global_step": 385133, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0415282249450684, "global_step": 385134, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0791542530059814, "global_step": 385135, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.072936534881592, "global_step": 385136, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1664726734161377, "global_step": 385137, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.007911443710327, "global_step": 385138, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1410531997680664, "global_step": 385139, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1567490100860596, "global_step": 385140, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0803592205047607, "global_step": 385141, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.145738124847412, "global_step": 385142, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.123844623565674, "global_step": 385143, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.043114185333252, "global_step": 385144, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.149409532546997, "global_step": 385145, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1157186031341553, "global_step": 385146, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1277382373809814, "global_step": 385147, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.158439874649048, "global_step": 385148, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0922389030456543, "global_step": 385149, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1104423999786377, "global_step": 385150, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.105161190032959, "global_step": 385151, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.099013090133667, "global_step": 385152, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.126807928085327, "global_step": 385153, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.083662748336792, "global_step": 385154, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1634674072265625, "global_step": 385155, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.103808879852295, "global_step": 385156, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0645883083343506, "global_step": 385157, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.017798900604248, "global_step": 385158, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.022839307785034, "global_step": 385159, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.116884708404541, "global_step": 385160, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.041161060333252, "global_step": 385161, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.11490797996521, "global_step": 385162, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1488656997680664, "global_step": 385163, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.135247230529785, "global_step": 385164, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.9612014293670654, "global_step": 385165, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1286096572875977, "global_step": 385166, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0259501934051514, "global_step": 385167, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2093119621276855, "global_step": 385168, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0883066654205322, "global_step": 385169, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.076284170150757, "global_step": 385170, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0380914211273193, "global_step": 385171, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.065321445465088, "global_step": 385172, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.096451759338379, "global_step": 385173, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1312007904052734, "global_step": 385174, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.108079195022583, "global_step": 385175, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.076052188873291, "global_step": 385176, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0585012435913086, "global_step": 385177, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.092123031616211, "global_step": 385178, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.090827703475952, "global_step": 385179, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.180912971496582, "global_step": 385180, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.053921699523926, "global_step": 385181, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1511974334716797, "global_step": 385182, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.141270160675049, "global_step": 385183, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.058561325073242, "global_step": 385184, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.17647385597229, "global_step": 385185, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0953686237335205, "global_step": 385186, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1207356452941895, "global_step": 385187, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1244120597839355, "global_step": 385188, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.995355486869812, "global_step": 385189, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0591232776641846, "global_step": 385190, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.041923761367798, "global_step": 385191, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.078963041305542, "global_step": 385192, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1204700469970703, "global_step": 385193, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0058367252349854, "global_step": 385194, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.077873945236206, "global_step": 385195, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0744218826293945, "global_step": 385196, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.065962314605713, "global_step": 385197, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.192542552947998, "global_step": 385198, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.127516269683838, "global_step": 385199, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1129310131073, "global_step": 385200, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1547014713287354, "global_step": 385201, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.135157823562622, "global_step": 385202, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.9792789220809937, "global_step": 385203, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0976054668426514, "global_step": 385204, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0315449237823486, "global_step": 385205, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1155970096588135, "global_step": 385206, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.014847755432129, "global_step": 385207, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0638113021850586, "global_step": 385208, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.186556339263916, "global_step": 385209, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.115828037261963, "global_step": 385210, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.051337242126465, "global_step": 385211, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2137856483459473, "global_step": 385212, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1828205585479736, "global_step": 385213, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.105236053466797, "global_step": 385214, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.103426694869995, "global_step": 385215, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.9586288928985596, "global_step": 385216, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.090398073196411, "global_step": 385217, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.045557737350464, "global_step": 385218, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.12428617477417, "global_step": 385219, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.112999677658081, "global_step": 385220, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.039335012435913, "global_step": 385221, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1580352783203125, "global_step": 385222, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0819592475891113, "global_step": 385223, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0846309661865234, "global_step": 385224, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0880706310272217, "global_step": 385225, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1520614624023438, "global_step": 385226, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.134023904800415, "global_step": 385227, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.029820442199707, "global_step": 385228, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1198983192443848, "global_step": 385229, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.108698844909668, "global_step": 385230, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.024141788482666, "global_step": 385231, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1221179962158203, "global_step": 385232, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1535375118255615, "global_step": 385233, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0943849086761475, "global_step": 385234, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0023233890533447, "global_step": 385235, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1485676765441895, "global_step": 385236, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0767171382904053, "global_step": 385237, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0518085956573486, "global_step": 385238, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.090052604675293, "global_step": 385239, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1381783485412598, "global_step": 385240, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.034782648086548, "global_step": 385241, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.074583053588867, "global_step": 385242, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1396660804748535, "global_step": 385243, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0560905933380127, "global_step": 385244, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.140488624572754, "global_step": 385245, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0815889835357666, "global_step": 385246, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1277754306793213, "global_step": 385247, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1338067054748535, "global_step": 385248, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.144423007965088, "global_step": 385249, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1469104290008545, "global_step": 385250, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1917810440063477, "global_step": 385251, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.11153244972229, "global_step": 385252, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.169862985610962, "global_step": 385253, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1259853839874268, "global_step": 385254, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.076761245727539, "global_step": 385255, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0194787979125977, "global_step": 385256, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1146891117095947, "global_step": 385257, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0986125469207764, "global_step": 385258, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0943076610565186, "global_step": 385259, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0965771675109863, "global_step": 385260, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0337533950805664, "global_step": 385261, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.144257068634033, "global_step": 385262, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2198824882507324, "global_step": 385263, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0443685054779053, "global_step": 385264, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1280014514923096, "global_step": 385265, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0784730911254883, "global_step": 385266, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0017905235290527, "global_step": 385267, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1946535110473633, "global_step": 385268, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1069726943969727, "global_step": 385269, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0333681106567383, "global_step": 385270, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.153491973876953, "global_step": 385271, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.140042304992676, "global_step": 385272, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.142578601837158, "global_step": 385273, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0808887481689453, "global_step": 385274, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1173202991485596, "global_step": 385275, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.134753704071045, "global_step": 385276, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.074354648590088, "global_step": 385277, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.10908579826355, "global_step": 385278, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1451094150543213, "global_step": 385279, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.125333547592163, "global_step": 385280, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1451289653778076, "global_step": 385281, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.063112735748291, "global_step": 385282, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1467080116271973, "global_step": 385283, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1681392192840576, "global_step": 385284, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1283700466156006, "global_step": 385285, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0882678031921387, "global_step": 385286, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0525999069213867, "global_step": 385287, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.047072410583496, "global_step": 385288, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2043967247009277, "global_step": 385289, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.033125162124634, "global_step": 385290, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.045818567276001, "global_step": 385291, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1668004989624023, "global_step": 385292, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.172050714492798, "global_step": 385293, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1983561515808105, "global_step": 385294, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.099884033203125, "global_step": 385295, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1226696968078613, "global_step": 385296, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1481847763061523, "global_step": 385297, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.129079580307007, "global_step": 385298, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0949087142944336, "global_step": 385299, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1587324142456055, "global_step": 385300, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1622278690338135, "global_step": 385301, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0604124069213867, "global_step": 385302, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1141393184661865, "global_step": 385303, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.254357099533081, "global_step": 385304, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0792148113250732, "global_step": 385305, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.123692512512207, "global_step": 385306, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.076880931854248, "global_step": 385307, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1494874954223633, "global_step": 385308, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1210227012634277, "global_step": 385309, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0856878757476807, "global_step": 385310, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.042470932006836, "global_step": 385311, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.007293224334717, "global_step": 385312, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0963406562805176, "global_step": 385313, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.144047260284424, "global_step": 385314, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1021625995635986, "global_step": 385315, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0903682708740234, "global_step": 385316, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.049102544784546, "global_step": 385317, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.162867784500122, "global_step": 385318, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.052518367767334, "global_step": 385319, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.152329444885254, "global_step": 385320, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.096327066421509, "global_step": 385321, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1218209266662598, "global_step": 385322, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.010143756866455, "global_step": 385323, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1555614471435547, "global_step": 385324, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.092686176300049, "global_step": 385325, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1057746410369873, "global_step": 385326, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0758988857269287, "global_step": 385327, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.07808518409729, "global_step": 385328, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1434786319732666, "global_step": 385329, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.032878875732422, "global_step": 385330, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.148681163787842, "global_step": 385331, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.103703498840332, "global_step": 385332, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1232011318206787, "global_step": 385333, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1445834636688232, "global_step": 385334, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0720431804656982, "global_step": 385335, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.058969020843506, "global_step": 385336, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1947197914123535, "global_step": 385337, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.070686101913452, "global_step": 385338, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.109992504119873, "global_step": 385339, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.089963674545288, "global_step": 385340, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2215354442596436, "global_step": 385341, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.052811622619629, "global_step": 385342, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.081190347671509, "global_step": 385343, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1173486709594727, "global_step": 385344, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.139594793319702, "global_step": 385345, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1143267154693604, "global_step": 385346, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1382181644439697, "global_step": 385347, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.154491424560547, "global_step": 385348, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.9957520961761475, "global_step": 385349, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1417646408081055, "global_step": 385350, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.00549578666687, "global_step": 385351, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.163208484649658, "global_step": 385352, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0714242458343506, "global_step": 385353, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.060822010040283, "global_step": 385354, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0381321907043457, "global_step": 385355, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1124324798583984, "global_step": 385356, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0028786659240723, "global_step": 385357, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.05769681930542, "global_step": 385358, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.077677011489868, "global_step": 385359, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.131810426712036, "global_step": 385360, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.110945701599121, "global_step": 385361, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0435521602630615, "global_step": 385362, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0336077213287354, "global_step": 385363, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1505706310272217, "global_step": 385364, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.151287317276001, "global_step": 385365, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1258249282836914, "global_step": 385366, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1716091632843018, "global_step": 385367, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0850486755371094, "global_step": 385368, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.119288682937622, "global_step": 385369, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1889431476593018, "global_step": 385370, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.148498058319092, "global_step": 385371, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.04081654548645, "global_step": 385372, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0708420276641846, "global_step": 385373, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0902483463287354, "global_step": 385374, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1211585998535156, "global_step": 385375, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.165175676345825, "global_step": 385376, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1056406497955322, "global_step": 385377, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.061363458633423, "global_step": 385378, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0964386463165283, "global_step": 385379, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.10302734375, "global_step": 385380, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.080686092376709, "global_step": 385381, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.072796583175659, "global_step": 385382, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0753421783447266, "global_step": 385383, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.06050968170166, "global_step": 385384, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0856926441192627, "global_step": 385385, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.093352794647217, "global_step": 385386, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1041793823242188, "global_step": 385387, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1506247520446777, "global_step": 385388, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1588025093078613, "global_step": 385389, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0948774814605713, "global_step": 385390, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0795814990997314, "global_step": 385391, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.094437599182129, "global_step": 385392, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1477997303009033, "global_step": 385393, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.124716281890869, "global_step": 385394, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2320473194122314, "global_step": 385395, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1175644397735596, "global_step": 385396, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.9756627082824707, "global_step": 385397, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0911355018615723, "global_step": 385398, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2179911136627197, "global_step": 385399, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0606071949005127, "global_step": 385400, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0708301067352295, "global_step": 385401, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0303633213043213, "global_step": 385402, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.029392957687378, "global_step": 385403, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.065048933029175, "global_step": 385404, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1492042541503906, "global_step": 385405, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1201364994049072, "global_step": 385406, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1120779514312744, "global_step": 385407, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.121628761291504, "global_step": 385408, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.016587972640991, "global_step": 385409, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.095960855484009, "global_step": 385410, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0768187046051025, "global_step": 385411, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.113483428955078, "global_step": 385412, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.086604595184326, "global_step": 385413, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.065398693084717, "global_step": 385414, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1611223220825195, "global_step": 385415, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2084290981292725, "global_step": 385416, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0755419731140137, "global_step": 385417, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.073258399963379, "global_step": 385418, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0518059730529785, "global_step": 385419, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1639292240142822, "global_step": 385420, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0629098415374756, "global_step": 385421, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.100703716278076, "global_step": 385422, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.059457778930664, "global_step": 385423, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1455955505371094, "global_step": 385424, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.02410888671875, "global_step": 385425, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.062321662902832, "global_step": 385426, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1100425720214844, "global_step": 385427, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1383042335510254, "global_step": 385428, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.036646604537964, "global_step": 385429, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.095808744430542, "global_step": 385430, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.106764793395996, "global_step": 385431, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0883867740631104, "global_step": 385432, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.035536289215088, "global_step": 385433, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.121717929840088, "global_step": 385434, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2102043628692627, "global_step": 385435, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.106600761413574, "global_step": 385436, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1338672637939453, "global_step": 385437, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.121190071105957, "global_step": 385438, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1409354209899902, "global_step": 385439, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0658202171325684, "global_step": 385440, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1375973224639893, "global_step": 385441, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.140251398086548, "global_step": 385442, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.063088893890381, "global_step": 385443, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0417115688323975, "global_step": 385444, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.068488836288452, "global_step": 385445, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.066100835800171, "global_step": 385446, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1085193157196045, "global_step": 385447, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0810837745666504, "global_step": 385448, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.081085205078125, "global_step": 385449, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.129133701324463, "global_step": 385450, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1786515712738037, "global_step": 385451, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2054190635681152, "global_step": 385452, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.196955442428589, "global_step": 385453, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.143941879272461, "global_step": 385454, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.042344570159912, "global_step": 385455, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1098809242248535, "global_step": 385456, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.214301347732544, "global_step": 385457, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0621962547302246, "global_step": 385458, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0546441078186035, "global_step": 385459, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2102882862091064, "global_step": 385460, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.079498291015625, "global_step": 385461, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.141871452331543, "global_step": 385462, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.016507625579834, "global_step": 385463, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.129438638687134, "global_step": 385464, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0714027881622314, "global_step": 385465, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.97878098487854, "global_step": 385466, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0924277305603027, "global_step": 385467, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1560869216918945, "global_step": 385468, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1896867752075195, "global_step": 385469, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0291614532470703, "global_step": 385470, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0959670543670654, "global_step": 385471, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.091765880584717, "global_step": 385472, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0845415592193604, "global_step": 385473, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.175902843475342, "global_step": 385474, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0522148609161377, "global_step": 385475, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1682920455932617, "global_step": 385476, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.170893430709839, "global_step": 385477, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1138241291046143, "global_step": 385478, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0949742794036865, "global_step": 385479, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.037191390991211, "global_step": 385480, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.068890333175659, "global_step": 385481, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1188831329345703, "global_step": 385482, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1547586917877197, "global_step": 385483, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1478922367095947, "global_step": 385484, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1596646308898926, "global_step": 385485, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1309523582458496, "global_step": 385486, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1340885162353516, "global_step": 385487, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.173586130142212, "global_step": 385488, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0658860206604004, "global_step": 385489, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.127340316772461, "global_step": 385490, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.146864414215088, "global_step": 385491, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.068254232406616, "global_step": 385492, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0280117988586426, "global_step": 385493, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.111078977584839, "global_step": 385494, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0545918941497803, "global_step": 385495, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1999621391296387, "global_step": 385496, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0605833530426025, "global_step": 385497, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0813140869140625, "global_step": 385498, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.122523784637451, "global_step": 385499, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.158102512359619, "global_step": 385500, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.034363031387329, "global_step": 385501, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.095578193664551, "global_step": 385502, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.076575756072998, "global_step": 385503, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2145400047302246, "global_step": 385504, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.079873561859131, "global_step": 385505, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0573999881744385, "global_step": 385506, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2079527378082275, "global_step": 385507, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0904927253723145, "global_step": 385508, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.080336093902588, "global_step": 385509, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.122481346130371, "global_step": 385510, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1887032985687256, "global_step": 385511, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.072262763977051, "global_step": 385512, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.125547170639038, "global_step": 385513, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.122361660003662, "global_step": 385514, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0675344467163086, "global_step": 385515, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1440370082855225, "global_step": 385516, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1505074501037598, "global_step": 385517, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0566985607147217, "global_step": 385518, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0407931804656982, "global_step": 385519, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2129063606262207, "global_step": 385520, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1086790561676025, "global_step": 385521, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1013906002044678, "global_step": 385522, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.166313648223877, "global_step": 385523, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.132550001144409, "global_step": 385524, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.082284450531006, "global_step": 385525, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.087615966796875, "global_step": 385526, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.055047035217285, "global_step": 385527, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.121763229370117, "global_step": 385528, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.075711488723755, "global_step": 385529, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.129861831665039, "global_step": 385530, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.163832187652588, "global_step": 385531, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0812551975250244, "global_step": 385532, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.113529682159424, "global_step": 385533, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.121521234512329, "global_step": 385534, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0843608379364014, "global_step": 385535, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.077021598815918, "global_step": 385536, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.048560380935669, "global_step": 385537, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0838592052459717, "global_step": 385538, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1302554607391357, "global_step": 385539, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0319042205810547, "global_step": 385540, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0475974082946777, "global_step": 385541, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.066011667251587, "global_step": 385542, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.201207399368286, "global_step": 385543, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0865819454193115, "global_step": 385544, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1033148765563965, "global_step": 385545, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.020512819290161, "global_step": 385546, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.165519952774048, "global_step": 385547, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0727787017822266, "global_step": 385548, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.149106740951538, "global_step": 385549, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0934367179870605, "global_step": 385550, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0813732147216797, "global_step": 385551, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1170332431793213, "global_step": 385552, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2361807823181152, "global_step": 385553, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2066822052001953, "global_step": 385554, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1348960399627686, "global_step": 385555, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0712766647338867, "global_step": 385556, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0149338245391846, "global_step": 385557, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.073829412460327, "global_step": 385558, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.9973828792572021, "global_step": 385559, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1440539360046387, "global_step": 385560, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.150477409362793, "global_step": 385561, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1057748794555664, "global_step": 385562, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.036945343017578, "global_step": 385563, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0821635723114014, "global_step": 385564, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.094527244567871, "global_step": 385565, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.169466733932495, "global_step": 385566, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.113309383392334, "global_step": 385567, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.149954080581665, "global_step": 385568, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0906906127929688, "global_step": 385569, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.116429090499878, "global_step": 385570, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.174820899963379, "global_step": 385571, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.9844776391983032, "global_step": 385572, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1345009803771973, "global_step": 385573, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0750036239624023, "global_step": 385574, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1570587158203125, "global_step": 385575, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.172884702682495, "global_step": 385576, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.154437780380249, "global_step": 385577, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.071209192276001, "global_step": 385578, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.9748038053512573, "global_step": 385579, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1017394065856934, "global_step": 385580, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2138590812683105, "global_step": 385581, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.082890510559082, "global_step": 385582, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1012802124023438, "global_step": 385583, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1050026416778564, "global_step": 385584, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0369203090667725, "global_step": 385585, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0283408164978027, "global_step": 385586, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0277457237243652, "global_step": 385587, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.088141918182373, "global_step": 385588, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0465197563171387, "global_step": 385589, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.082679271697998, "global_step": 385590, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.115586042404175, "global_step": 385591, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.084747076034546, "global_step": 385592, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.091566324234009, "global_step": 385593, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.205984592437744, "global_step": 385594, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0746657848358154, "global_step": 385595, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.182511568069458, "global_step": 385596, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.091708183288574, "global_step": 385597, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.116961717605591, "global_step": 385598, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1280272006988525, "global_step": 385599, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.090367555618286, "global_step": 385600, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1815409660339355, "global_step": 385601, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.117089033126831, "global_step": 385602, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1139445304870605, "global_step": 385603, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.061476707458496, "global_step": 385604, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0968382358551025, "global_step": 385605, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1346445083618164, "global_step": 385606, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.093714952468872, "global_step": 385607, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0672764778137207, "global_step": 385608, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.035515308380127, "global_step": 385609, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0552093982696533, "global_step": 385610, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0503506660461426, "global_step": 385611, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1053199768066406, "global_step": 385612, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.074645757675171, "global_step": 385613, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.084031343460083, "global_step": 385614, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.044140338897705, "global_step": 385615, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.9812228679656982, "global_step": 385616, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1220054626464844, "global_step": 385617, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0577619075775146, "global_step": 385618, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.103715181350708, "global_step": 385619, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2131762504577637, "global_step": 385620, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1288933753967285, "global_step": 385621, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1284592151641846, "global_step": 385622, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1320834159851074, "global_step": 385623, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0913937091827393, "global_step": 385624, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.06864857673645, "global_step": 385625, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.153209924697876, "global_step": 385626, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.094951629638672, "global_step": 385627, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1323764324188232, "global_step": 385628, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.093766689300537, "global_step": 385629, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1271636486053467, "global_step": 385630, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0526721477508545, "global_step": 385631, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.067657709121704, "global_step": 385632, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0948565006256104, "global_step": 385633, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.070976972579956, "global_step": 385634, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.218240261077881, "global_step": 385635, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0812416076660156, "global_step": 385636, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1100258827209473, "global_step": 385637, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.048442840576172, "global_step": 385638, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.130922794342041, "global_step": 385639, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1711268424987793, "global_step": 385640, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1213607788085938, "global_step": 385641, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.109851598739624, "global_step": 385642, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.076549530029297, "global_step": 385643, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.050389528274536, "global_step": 385644, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0864555835723877, "global_step": 385645, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0618762969970703, "global_step": 385646, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0739493370056152, "global_step": 385647, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.157240629196167, "global_step": 385648, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.115246057510376, "global_step": 385649, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.079575300216675, "global_step": 385650, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0929346084594727, "global_step": 385651, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0347068309783936, "global_step": 385652, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.102167844772339, "global_step": 385653, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.005201816558838, "global_step": 385654, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.131702423095703, "global_step": 385655, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1479763984680176, "global_step": 385656, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.101273775100708, "global_step": 385657, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.125492811203003, "global_step": 385658, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1729578971862793, "global_step": 385659, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.174260139465332, "global_step": 385660, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1211187839508057, "global_step": 385661, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.089606523513794, "global_step": 385662, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.185460090637207, "global_step": 385663, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.067871332168579, "global_step": 385664, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1157031059265137, "global_step": 385665, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1302404403686523, "global_step": 385666, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0510740280151367, "global_step": 385667, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1454803943634033, "global_step": 385668, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1554903984069824, "global_step": 385669, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1087870597839355, "global_step": 385670, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.168306589126587, "global_step": 385671, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1535840034484863, "global_step": 385672, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1829254627227783, "global_step": 385673, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0754053592681885, "global_step": 385674, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0637829303741455, "global_step": 385675, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.165766716003418, "global_step": 385676, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.155329942703247, "global_step": 385677, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1886096000671387, "global_step": 385678, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1491239070892334, "global_step": 385679, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1516335010528564, "global_step": 385680, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.158371686935425, "global_step": 385681, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.14050555229187, "global_step": 385682, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.148352861404419, "global_step": 385683, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1416900157928467, "global_step": 385684, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1163148880004883, "global_step": 385685, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.194755792617798, "global_step": 385686, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.110182046890259, "global_step": 385687, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0404019355773926, "global_step": 385688, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1414122581481934, "global_step": 385689, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.156567096710205, "global_step": 385690, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0577456951141357, "global_step": 385691, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1058242321014404, "global_step": 385692, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.120695114135742, "global_step": 385693, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1339097023010254, "global_step": 385694, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.192467212677002, "global_step": 385695, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0719869136810303, "global_step": 385696, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0089643001556396, "global_step": 385697, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1295433044433594, "global_step": 385698, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1428937911987305, "global_step": 385699, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1124074459075928, "global_step": 385700, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1443915367126465, "global_step": 385701, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0487263202667236, "global_step": 385702, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.150399684906006, "global_step": 385703, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1080620288848877, "global_step": 385704, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.038318395614624, "global_step": 385705, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.137753963470459, "global_step": 385706, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0684823989868164, "global_step": 385707, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.172667980194092, "global_step": 385708, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.066953182220459, "global_step": 385709, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0250329971313477, "global_step": 385710, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.091912269592285, "global_step": 385711, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1324405670166016, "global_step": 385712, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.141453742980957, "global_step": 385713, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.070112943649292, "global_step": 385714, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.183586835861206, "global_step": 385715, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1070873737335205, "global_step": 385716, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1960394382476807, "global_step": 385717, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.165933132171631, "global_step": 385718, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.065122127532959, "global_step": 385719, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.136486053466797, "global_step": 385720, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.16060209274292, "global_step": 385721, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1343770027160645, "global_step": 385722, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0598113536834717, "global_step": 385723, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1184256076812744, "global_step": 385724, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.054614543914795, "global_step": 385725, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0576863288879395, "global_step": 385726, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.098022222518921, "global_step": 385727, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1132616996765137, "global_step": 385728, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.162187099456787, "global_step": 385729, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.108670711517334, "global_step": 385730, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1389122009277344, "global_step": 385731, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0357911586761475, "global_step": 385732, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1300275325775146, "global_step": 385733, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.073878049850464, "global_step": 385734, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1267762184143066, "global_step": 385735, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0965986251831055, "global_step": 385736, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.209632158279419, "global_step": 385737, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0684397220611572, "global_step": 385738, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.105691909790039, "global_step": 385739, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.034783363342285, "global_step": 385740, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0964951515197754, "global_step": 385741, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.153512954711914, "global_step": 385742, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0277445316314697, "global_step": 385743, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2192108631134033, "global_step": 385744, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.156813144683838, "global_step": 385745, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.028454065322876, "global_step": 385746, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.065814733505249, "global_step": 385747, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1233091354370117, "global_step": 385748, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1738228797912598, "global_step": 385749, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0470316410064697, "global_step": 385750, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0527124404907227, "global_step": 385751, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0564653873443604, "global_step": 385752, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0519895553588867, "global_step": 385753, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.00473690032959, "global_step": 385754, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1308064460754395, "global_step": 385755, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1029813289642334, "global_step": 385756, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1603379249572754, "global_step": 385757, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.058690071105957, "global_step": 385758, "epoch": 747, "lr": 5e-05}
{"train_loss": 1.9670578241348267, "global_step": 385759, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.09259033203125, "global_step": 385760, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0225818157196045, "global_step": 385761, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0840985774993896, "global_step": 385762, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.114603281021118, "global_step": 385763, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1171176433563232, "global_step": 385764, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.101790428161621, "global_step": 385765, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1222355365753174, "global_step": 385766, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1241650581359863, "global_step": 385767, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1319239139556885, "global_step": 385768, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0695955753326416, "global_step": 385769, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.068215847015381, "global_step": 385770, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.141132116317749, "global_step": 385771, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1309444904327393, "global_step": 385772, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1123485565185547, "global_step": 385773, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.166923999786377, "global_step": 385774, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.016474962234497, "global_step": 385775, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1259512901306152, "global_step": 385776, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.117917776107788, "global_step": 385777, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.087906837463379, "global_step": 385778, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0984854698181152, "global_step": 385779, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.001438856124878, "global_step": 385780, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1275572776794434, "global_step": 385781, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1797213554382324, "global_step": 385782, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.134110927581787, "global_step": 385783, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.004826068878174, "global_step": 385784, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0059750080108643, "global_step": 385785, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.0219576358795166, "global_step": 385786, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1340177059173584, "global_step": 385787, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.2693636417388916, "global_step": 385788, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.106140613555908, "global_step": 385789, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.030925989151001, "global_step": 385790, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.1982696056365967, "global_step": 385791, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.113276720046997, "global_step": 385792, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.151752233505249, "global_step": 385793, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.101898670196533, "global_step": 385794, "epoch": 747, "lr": 5e-05}
{"train_loss": 2.091463088989258, "global_step": 385795, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1080739498138428, "global_step": 385796, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.14886474609375, "global_step": 385797, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.08908748626709, "global_step": 385798, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.146784543991089, "global_step": 385799, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0826921463012695, "global_step": 385800, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.041001558303833, "global_step": 385801, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.9948201179504395, "global_step": 385802, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1376450061798096, "global_step": 385803, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0864570140838623, "global_step": 385804, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0648763179779053, "global_step": 385805, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0719070434570312, "global_step": 385806, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1083638668060303, "global_step": 385807, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.009352207183838, "global_step": 385808, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.100890636444092, "global_step": 385809, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.137514591217041, "global_step": 385810, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.159047842025757, "global_step": 385811, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.2040021419525146, "global_step": 385812, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.075470209121704, "global_step": 385813, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1219115257263184, "global_step": 385814, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1215076446533203, "global_step": 385815, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0777080059051514, "global_step": 385816, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1647469997406006, "global_step": 385817, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0740232467651367, "global_step": 385818, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.038200855255127, "global_step": 385819, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0842950344085693, "global_step": 385820, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1731646060943604, "global_step": 385821, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0629496574401855, "global_step": 385822, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0077874660491943, "global_step": 385823, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.085890531539917, "global_step": 385824, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0817487239837646, "global_step": 385825, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.099217176437378, "global_step": 385826, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.095099687576294, "global_step": 385827, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.15468168258667, "global_step": 385828, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.005875587463379, "global_step": 385829, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0115339756011963, "global_step": 385830, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1425435543060303, "global_step": 385831, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1178672313690186, "global_step": 385832, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.102397918701172, "global_step": 385833, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.9870061874389648, "global_step": 385834, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0214996337890625, "global_step": 385835, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0879645347595215, "global_step": 385836, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.156013011932373, "global_step": 385837, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.126218318939209, "global_step": 385838, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1261560916900635, "global_step": 385839, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.127195358276367, "global_step": 385840, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1594464778900146, "global_step": 385841, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1466691493988037, "global_step": 385842, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.057544708251953, "global_step": 385843, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.9999784231185913, "global_step": 385844, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0506417751312256, "global_step": 385845, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0970399379730225, "global_step": 385846, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.08524751663208, "global_step": 385847, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.134793996810913, "global_step": 385848, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1682252883911133, "global_step": 385849, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1294896602630615, "global_step": 385850, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.185380220413208, "global_step": 385851, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1288206577301025, "global_step": 385852, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0585286617279053, "global_step": 385853, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1138577461242676, "global_step": 385854, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0844314098358154, "global_step": 385855, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0152997970581055, "global_step": 385856, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.057286500930786, "global_step": 385857, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1054651737213135, "global_step": 385858, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1293389797210693, "global_step": 385859, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1560845375061035, "global_step": 385860, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0159316062927246, "global_step": 385861, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1500046253204346, "global_step": 385862, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1115522384643555, "global_step": 385863, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1195037364959717, "global_step": 385864, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.126800775527954, "global_step": 385865, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.02752423286438, "global_step": 385866, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.043588399887085, "global_step": 385867, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0890538692474365, "global_step": 385868, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.174105405807495, "global_step": 385869, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1165006160736084, "global_step": 385870, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.092364549636841, "global_step": 385871, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.9719257354736328, "global_step": 385872, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.9811524152755737, "global_step": 385873, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0727694034576416, "global_step": 385874, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.178018808364868, "global_step": 385875, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.113234519958496, "global_step": 385876, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0683863162994385, "global_step": 385877, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1843581199645996, "global_step": 385878, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.030233144760132, "global_step": 385879, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.04118275642395, "global_step": 385880, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.095634937286377, "global_step": 385881, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0240049362182617, "global_step": 385882, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1629393100738525, "global_step": 385883, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.2016775608062744, "global_step": 385884, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0220694541931152, "global_step": 385885, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.127838373184204, "global_step": 385886, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.102475643157959, "global_step": 385887, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1675450801849365, "global_step": 385888, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.126413583755493, "global_step": 385889, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.082868814468384, "global_step": 385890, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.020423412322998, "global_step": 385891, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.080868721008301, "global_step": 385892, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0412144660949707, "global_step": 385893, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.089322805404663, "global_step": 385894, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.136721611022949, "global_step": 385895, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.123899459838867, "global_step": 385896, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.9948474168777466, "global_step": 385897, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1028027534484863, "global_step": 385898, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0525691509246826, "global_step": 385899, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1216604709625244, "global_step": 385900, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0588009357452393, "global_step": 385901, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1059346199035645, "global_step": 385902, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1327579021453857, "global_step": 385903, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.107983112335205, "global_step": 385904, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1591646671295166, "global_step": 385905, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1368296146392822, "global_step": 385906, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1538963317871094, "global_step": 385907, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1344215869903564, "global_step": 385908, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.183896064758301, "global_step": 385909, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.099557876586914, "global_step": 385910, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1246237754821777, "global_step": 385911, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0968871116638184, "global_step": 385912, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.085343360900879, "global_step": 385913, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0044186115264893, "global_step": 385914, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1109354496002197, "global_step": 385915, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.142850160598755, "global_step": 385916, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.067681312561035, "global_step": 385917, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0383126735687256, "global_step": 385918, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.2003722190856934, "global_step": 385919, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.080410957336426, "global_step": 385920, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0224363803863525, "global_step": 385921, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.103498697280884, "global_step": 385922, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1802561283111572, "global_step": 385923, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1310880184173584, "global_step": 385924, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.085306406021118, "global_step": 385925, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0854897499084473, "global_step": 385926, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0442259311676025, "global_step": 385927, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1109886169433594, "global_step": 385928, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0774431228637695, "global_step": 385929, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1321308612823486, "global_step": 385930, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.036804437637329, "global_step": 385931, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.057313919067383, "global_step": 385932, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.133260726928711, "global_step": 385933, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0378103256225586, "global_step": 385934, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.072141647338867, "global_step": 385935, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.096529006958008, "global_step": 385936, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.034735679626465, "global_step": 385937, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.144441604614258, "global_step": 385938, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0641751289367676, "global_step": 385939, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0949134826660156, "global_step": 385940, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0690536499023438, "global_step": 385941, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.089566707611084, "global_step": 385942, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0611021518707275, "global_step": 385943, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.040010452270508, "global_step": 385944, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0901687145233154, "global_step": 385945, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.9910985231399536, "global_step": 385946, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0793681144714355, "global_step": 385947, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0018765926361084, "global_step": 385948, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0659615993499756, "global_step": 385949, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1382908821105957, "global_step": 385950, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0629303455352783, "global_step": 385951, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1179614067077637, "global_step": 385952, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.017216205596924, "global_step": 385953, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1180903911590576, "global_step": 385954, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.13802170753479, "global_step": 385955, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.149778127670288, "global_step": 385956, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.064988136291504, "global_step": 385957, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.173276424407959, "global_step": 385958, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.113865375518799, "global_step": 385959, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.180522918701172, "global_step": 385960, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0623090267181396, "global_step": 385961, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0533242225646973, "global_step": 385962, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1090033054351807, "global_step": 385963, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.195138692855835, "global_step": 385964, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.11954665184021, "global_step": 385965, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1079916954040527, "global_step": 385966, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1862294673919678, "global_step": 385967, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0633625984191895, "global_step": 385968, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.9912077188491821, "global_step": 385969, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.164051055908203, "global_step": 385970, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0642874240875244, "global_step": 385971, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1045260429382324, "global_step": 385972, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.043825626373291, "global_step": 385973, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1540520191192627, "global_step": 385974, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.172218084335327, "global_step": 385975, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.094143867492676, "global_step": 385976, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0559139251708984, "global_step": 385977, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.128110408782959, "global_step": 385978, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0975260734558105, "global_step": 385979, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.022691249847412, "global_step": 385980, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.109876871109009, "global_step": 385981, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.07470440864563, "global_step": 385982, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.089379072189331, "global_step": 385983, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0831093788146973, "global_step": 385984, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.05833101272583, "global_step": 385985, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.150068759918213, "global_step": 385986, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0551016330718994, "global_step": 385987, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.147686004638672, "global_step": 385988, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.095724582672119, "global_step": 385989, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0940909385681152, "global_step": 385990, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.109189748764038, "global_step": 385991, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.022799491882324, "global_step": 385992, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1196022033691406, "global_step": 385993, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.094876527786255, "global_step": 385994, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.131359577178955, "global_step": 385995, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0806000232696533, "global_step": 385996, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0319087505340576, "global_step": 385997, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1043858528137207, "global_step": 385998, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0586652755737305, "global_step": 385999, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.062725067138672, "global_step": 386000, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1650731563568115, "global_step": 386001, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.099029064178467, "global_step": 386002, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0858640670776367, "global_step": 386003, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1710832118988037, "global_step": 386004, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0897631645202637, "global_step": 386005, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.137119770050049, "global_step": 386006, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.06142520904541, "global_step": 386007, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1062867641448975, "global_step": 386008, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0738818645477295, "global_step": 386009, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.086642026901245, "global_step": 386010, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.053719997406006, "global_step": 386011, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1861655712127686, "global_step": 386012, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.125812292098999, "global_step": 386013, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.058847188949585, "global_step": 386014, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.013148546218872, "global_step": 386015, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.130601167678833, "global_step": 386016, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0891740322113037, "global_step": 386017, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.043229579925537, "global_step": 386018, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.131441831588745, "global_step": 386019, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0891127586364746, "global_step": 386020, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1351029872894287, "global_step": 386021, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.07481050491333, "global_step": 386022, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1051440238952637, "global_step": 386023, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1524367332458496, "global_step": 386024, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0521252155303955, "global_step": 386025, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1681978702545166, "global_step": 386026, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1056911945343018, "global_step": 386027, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.171182155609131, "global_step": 386028, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1476848125457764, "global_step": 386029, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0736913681030273, "global_step": 386030, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.060556650161743, "global_step": 386031, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.998046636581421, "global_step": 386032, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.190455675125122, "global_step": 386033, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.134550094604492, "global_step": 386034, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.077946901321411, "global_step": 386035, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.098179340362549, "global_step": 386036, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.081066608428955, "global_step": 386037, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1112685203552246, "global_step": 386038, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.116490364074707, "global_step": 386039, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.082462787628174, "global_step": 386040, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1061477661132812, "global_step": 386041, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0572996139526367, "global_step": 386042, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0601608753204346, "global_step": 386043, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.194277286529541, "global_step": 386044, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.08647084236145, "global_step": 386045, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.137814521789551, "global_step": 386046, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.047384262084961, "global_step": 386047, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1254684925079346, "global_step": 386048, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0119574069976807, "global_step": 386049, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1075422763824463, "global_step": 386050, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1571035385131836, "global_step": 386051, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.07883620262146, "global_step": 386052, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.098773956298828, "global_step": 386053, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1452479362487793, "global_step": 386054, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.107116222381592, "global_step": 386055, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1714394092559814, "global_step": 386056, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0431323051452637, "global_step": 386057, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0969345569610596, "global_step": 386058, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1051526069641113, "global_step": 386059, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.065031051635742, "global_step": 386060, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.074880838394165, "global_step": 386061, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.105588436126709, "global_step": 386062, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1064717769622803, "global_step": 386063, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.133173704147339, "global_step": 386064, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1274023056030273, "global_step": 386065, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.102546453475952, "global_step": 386066, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1328799724578857, "global_step": 386067, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1013569831848145, "global_step": 386068, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0106618404388428, "global_step": 386069, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.9877970218658447, "global_step": 386070, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1294708251953125, "global_step": 386071, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.060692071914673, "global_step": 386072, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.182926654815674, "global_step": 386073, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.099512815475464, "global_step": 386074, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1519315242767334, "global_step": 386075, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1038386821746826, "global_step": 386076, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1455273628234863, "global_step": 386077, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0920674800872803, "global_step": 386078, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0495686531066895, "global_step": 386079, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1019444465637207, "global_step": 386080, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.2146031856536865, "global_step": 386081, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.087054491043091, "global_step": 386082, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1114752292633057, "global_step": 386083, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1104698181152344, "global_step": 386084, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1682703495025635, "global_step": 386085, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0097618103027344, "global_step": 386086, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.151308298110962, "global_step": 386087, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.095369815826416, "global_step": 386088, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1202034950256348, "global_step": 386089, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.035207748413086, "global_step": 386090, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1672728061676025, "global_step": 386091, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1160237789154053, "global_step": 386092, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1197266578674316, "global_step": 386093, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1489787101745605, "global_step": 386094, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1120731830596924, "global_step": 386095, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1813652515411377, "global_step": 386096, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.077545166015625, "global_step": 386097, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0372283458709717, "global_step": 386098, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.059983253479004, "global_step": 386099, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0631918907165527, "global_step": 386100, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.162882089614868, "global_step": 386101, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1258907318115234, "global_step": 386102, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.151245355606079, "global_step": 386103, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0844359397888184, "global_step": 386104, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0554840564727783, "global_step": 386105, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.132167100906372, "global_step": 386106, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0459890365600586, "global_step": 386107, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.9874120950698853, "global_step": 386108, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0581212043762207, "global_step": 386109, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.199380397796631, "global_step": 386110, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0462357997894287, "global_step": 386111, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1264071464538574, "global_step": 386112, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.139328956604004, "global_step": 386113, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1174347400665283, "global_step": 386114, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0761826038360596, "global_step": 386115, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1190433502197266, "global_step": 386116, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.082890510559082, "global_step": 386117, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.160263776779175, "global_step": 386118, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0570311546325684, "global_step": 386119, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0812432765960693, "global_step": 386120, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1284823417663574, "global_step": 386121, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1040854454040527, "global_step": 386122, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1502206325531006, "global_step": 386123, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1045424938201904, "global_step": 386124, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.172121286392212, "global_step": 386125, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0938916206359863, "global_step": 386126, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.099229335784912, "global_step": 386127, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1785390377044678, "global_step": 386128, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.124628782272339, "global_step": 386129, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0532007217407227, "global_step": 386130, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.080033779144287, "global_step": 386131, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0022404193878174, "global_step": 386132, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.005495071411133, "global_step": 386133, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0844225883483887, "global_step": 386134, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0953192710876465, "global_step": 386135, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.022524833679199, "global_step": 386136, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1535449028015137, "global_step": 386137, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.088890552520752, "global_step": 386138, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1256637573242188, "global_step": 386139, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1370038986206055, "global_step": 386140, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1149723529815674, "global_step": 386141, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0576798915863037, "global_step": 386142, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1207540035247803, "global_step": 386143, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.065631866455078, "global_step": 386144, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1508193016052246, "global_step": 386145, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0459911823272705, "global_step": 386146, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.014972686767578, "global_step": 386147, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0574791431427, "global_step": 386148, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0683183670043945, "global_step": 386149, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0872621536254883, "global_step": 386150, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0454516410827637, "global_step": 386151, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0971126556396484, "global_step": 386152, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1114935874938965, "global_step": 386153, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.2219278812408447, "global_step": 386154, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.186516046524048, "global_step": 386155, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0008816719055176, "global_step": 386156, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1627895832061768, "global_step": 386157, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0249931812286377, "global_step": 386158, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0968029499053955, "global_step": 386159, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0527384281158447, "global_step": 386160, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0510940551757812, "global_step": 386161, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.9967339038848877, "global_step": 386162, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0112102031707764, "global_step": 386163, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0601353645324707, "global_step": 386164, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0685722827911377, "global_step": 386165, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.161475896835327, "global_step": 386166, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.119412660598755, "global_step": 386167, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.090602397918701, "global_step": 386168, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0606226921081543, "global_step": 386169, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.093201160430908, "global_step": 386170, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.074086904525757, "global_step": 386171, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.9956978559494019, "global_step": 386172, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.101001739501953, "global_step": 386173, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.119708776473999, "global_step": 386174, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1394715309143066, "global_step": 386175, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0067825317382812, "global_step": 386176, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1066832542419434, "global_step": 386177, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1413891315460205, "global_step": 386178, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0821189880371094, "global_step": 386179, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0797863006591797, "global_step": 386180, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0818493366241455, "global_step": 386181, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0335981845855713, "global_step": 386182, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0548975467681885, "global_step": 386183, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.137761354446411, "global_step": 386184, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0423202514648438, "global_step": 386185, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0587546825408936, "global_step": 386186, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0468556880950928, "global_step": 386187, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.051004648208618, "global_step": 386188, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.092580795288086, "global_step": 386189, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.050041913986206, "global_step": 386190, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1265039443969727, "global_step": 386191, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0838382244110107, "global_step": 386192, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0833046436309814, "global_step": 386193, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.095510959625244, "global_step": 386194, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.169191360473633, "global_step": 386195, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.038755416870117, "global_step": 386196, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.152310848236084, "global_step": 386197, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1589579582214355, "global_step": 386198, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1423587799072266, "global_step": 386199, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.2252886295318604, "global_step": 386200, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.106201648712158, "global_step": 386201, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.172729730606079, "global_step": 386202, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1940906047821045, "global_step": 386203, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1368749141693115, "global_step": 386204, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.105879783630371, "global_step": 386205, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1355652809143066, "global_step": 386206, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0741167068481445, "global_step": 386207, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1005868911743164, "global_step": 386208, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.19858980178833, "global_step": 386209, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.093223810195923, "global_step": 386210, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.167682409286499, "global_step": 386211, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.094424247741699, "global_step": 386212, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1658976078033447, "global_step": 386213, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0943450927734375, "global_step": 386214, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1001710891723633, "global_step": 386215, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.00636887550354, "global_step": 386216, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1137843132019043, "global_step": 386217, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.143423318862915, "global_step": 386218, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1141419410705566, "global_step": 386219, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.120048999786377, "global_step": 386220, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1081430912017822, "global_step": 386221, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.133554220199585, "global_step": 386222, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.041748046875, "global_step": 386223, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.118807554244995, "global_step": 386224, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0974302291870117, "global_step": 386225, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.091230869293213, "global_step": 386226, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0917789936065674, "global_step": 386227, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.112053155899048, "global_step": 386228, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.157602310180664, "global_step": 386229, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0875494480133057, "global_step": 386230, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.01704478263855, "global_step": 386231, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1723639965057373, "global_step": 386232, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1081271171569824, "global_step": 386233, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.089799165725708, "global_step": 386234, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.151132345199585, "global_step": 386235, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1947221755981445, "global_step": 386236, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.124732255935669, "global_step": 386237, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.154632568359375, "global_step": 386238, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0062079429626465, "global_step": 386239, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1433873176574707, "global_step": 386240, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.081757068634033, "global_step": 386241, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1651322841644287, "global_step": 386242, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1540331840515137, "global_step": 386243, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0654141902923584, "global_step": 386244, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1625499725341797, "global_step": 386245, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.109808921813965, "global_step": 386246, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1121931076049805, "global_step": 386247, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1759941577911377, "global_step": 386248, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.004830837249756, "global_step": 386249, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1185131072998047, "global_step": 386250, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1375327110290527, "global_step": 386251, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0912675857543945, "global_step": 386252, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0629570484161377, "global_step": 386253, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.142345905303955, "global_step": 386254, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.132265329360962, "global_step": 386255, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.08195161819458, "global_step": 386256, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0932977199554443, "global_step": 386257, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1594412326812744, "global_step": 386258, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1084728240966797, "global_step": 386259, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.036287546157837, "global_step": 386260, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.178466558456421, "global_step": 386261, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.095224618911743, "global_step": 386262, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0904743671417236, "global_step": 386263, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.137366771697998, "global_step": 386264, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0923006534576416, "global_step": 386265, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.135714530944824, "global_step": 386266, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0350263118743896, "global_step": 386267, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0170812606811523, "global_step": 386268, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.21073055267334, "global_step": 386269, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.11991810798645, "global_step": 386270, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.2049362659454346, "global_step": 386271, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.063883066177368, "global_step": 386272, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.106398344039917, "global_step": 386273, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1104931831359863, "global_step": 386274, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0438544750213623, "global_step": 386275, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.061889886856079, "global_step": 386276, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.129335641860962, "global_step": 386277, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0084645748138428, "global_step": 386278, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0344419479370117, "global_step": 386279, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0847043991088867, "global_step": 386280, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.065074920654297, "global_step": 386281, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1633799076080322, "global_step": 386282, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0876102447509766, "global_step": 386283, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0586092472076416, "global_step": 386284, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1042306423187256, "global_step": 386285, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1406826972961426, "global_step": 386286, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1621861457824707, "global_step": 386287, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.055600881576538, "global_step": 386288, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.083369016647339, "global_step": 386289, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.175511598587036, "global_step": 386290, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.116903781890869, "global_step": 386291, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.131709575653076, "global_step": 386292, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1037065982818604, "global_step": 386293, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.152876138687134, "global_step": 386294, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.154153347015381, "global_step": 386295, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.181812286376953, "global_step": 386296, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1191022396087646, "global_step": 386297, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1734814643859863, "global_step": 386298, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.079918384552002, "global_step": 386299, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.183776378631592, "global_step": 386300, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.184147596359253, "global_step": 386301, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.017601728439331, "global_step": 386302, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.9976211786270142, "global_step": 386303, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0030782222747803, "global_step": 386304, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.126757860183716, "global_step": 386305, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.12298321723938, "global_step": 386306, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.2343673706054688, "global_step": 386307, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1392972469329834, "global_step": 386308, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.173563241958618, "global_step": 386309, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1586570739746094, "global_step": 386310, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1937265396118164, "global_step": 386311, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1279752254486084, "global_step": 386312, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.194805145263672, "global_step": 386313, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1217665672302246, "global_step": 386314, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.134382963180542, "global_step": 386315, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1702206134796143, "global_step": 386316, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.03436541557312, "global_step": 386317, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.111704111099243, "global_step": 386318, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.155099630355835, "global_step": 386319, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0667500495910645, "global_step": 386320, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.057070255279541, "global_step": 386321, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1792900562286377, "global_step": 386322, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.042262077331543, "global_step": 386323, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1172308921813965, "global_step": 386324, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.054760694503784, "global_step": 386325, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1354153156280518, "global_step": 386326, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.124143362045288, "global_step": 386327, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1379308700561523, "global_step": 386328, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1453964710235596, "global_step": 386329, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.995553970336914, "global_step": 386330, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1293509006500244, "global_step": 386331, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1192214488983154, "global_step": 386332, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1641297340393066, "global_step": 386333, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0075414180755615, "global_step": 386334, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1580328941345215, "global_step": 386335, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0797195434570312, "global_step": 386336, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.107928514480591, "global_step": 386337, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1887972354888916, "global_step": 386338, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0810952186584473, "global_step": 386339, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1506669521331787, "global_step": 386340, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1631388664245605, "global_step": 386341, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.093155860900879, "global_step": 386342, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.102447986602783, "global_step": 386343, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.127959728240967, "global_step": 386344, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.074232816696167, "global_step": 386345, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.092850685119629, "global_step": 386346, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0420467853546143, "global_step": 386347, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1152420043945312, "global_step": 386348, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.082998752593994, "global_step": 386349, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.076097011566162, "global_step": 386350, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.113260507583618, "global_step": 386351, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0846269130706787, "global_step": 386352, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.147588014602661, "global_step": 386353, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.075822114944458, "global_step": 386354, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.050527572631836, "global_step": 386355, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0868992805480957, "global_step": 386356, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0448267459869385, "global_step": 386357, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.141202926635742, "global_step": 386358, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.024925470352173, "global_step": 386359, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.131571054458618, "global_step": 386360, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.063695192337036, "global_step": 386361, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.036301374435425, "global_step": 386362, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.077279806137085, "global_step": 386363, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1153409481048584, "global_step": 386364, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.138782262802124, "global_step": 386365, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1108946800231934, "global_step": 386366, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.085202693939209, "global_step": 386367, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0526437759399414, "global_step": 386368, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0596415996551514, "global_step": 386369, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.073805570602417, "global_step": 386370, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.2222988605499268, "global_step": 386371, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1214585304260254, "global_step": 386372, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0615692138671875, "global_step": 386373, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.132413625717163, "global_step": 386374, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0864791870117188, "global_step": 386375, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.103461265563965, "global_step": 386376, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0321872234344482, "global_step": 386377, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.022786855697632, "global_step": 386378, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.162492513656616, "global_step": 386379, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1164631843566895, "global_step": 386380, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0921359062194824, "global_step": 386381, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.074981451034546, "global_step": 386382, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.153561592102051, "global_step": 386383, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0487587451934814, "global_step": 386384, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.037039279937744, "global_step": 386385, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1129000186920166, "global_step": 386386, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.121826648712158, "global_step": 386387, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.195614814758301, "global_step": 386388, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.083570718765259, "global_step": 386389, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1126537322998047, "global_step": 386390, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.175015449523926, "global_step": 386391, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1045660972595215, "global_step": 386392, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.138474464416504, "global_step": 386393, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1964094638824463, "global_step": 386394, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.060530662536621, "global_step": 386395, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1372251510620117, "global_step": 386396, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0654284954071045, "global_step": 386397, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1546990871429443, "global_step": 386398, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.083573579788208, "global_step": 386399, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.096728801727295, "global_step": 386400, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1627461910247803, "global_step": 386401, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.031384229660034, "global_step": 386402, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1410107612609863, "global_step": 386403, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1198437213897705, "global_step": 386404, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1433966159820557, "global_step": 386405, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.006101608276367, "global_step": 386406, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.038897752761841, "global_step": 386407, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.112121343612671, "global_step": 386408, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1411030292510986, "global_step": 386409, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1395106315612793, "global_step": 386410, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.067866563796997, "global_step": 386411, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0991499423980713, "global_step": 386412, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1197071075439453, "global_step": 386413, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.9973609447479248, "global_step": 386414, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0584418773651123, "global_step": 386415, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1267447471618652, "global_step": 386416, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1011364459991455, "global_step": 386417, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1617910861968994, "global_step": 386418, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1104204654693604, "global_step": 386419, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.100938081741333, "global_step": 386420, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1617202758789062, "global_step": 386421, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1108710765838623, "global_step": 386422, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1149914264678955, "global_step": 386423, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1432273387908936, "global_step": 386424, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1362502574920654, "global_step": 386425, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1066646575927734, "global_step": 386426, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.99852454662323, "global_step": 386427, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0809168815612793, "global_step": 386428, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.089028835296631, "global_step": 386429, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.9847077131271362, "global_step": 386430, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0845611095428467, "global_step": 386431, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.186393976211548, "global_step": 386432, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.177924156188965, "global_step": 386433, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1068875789642334, "global_step": 386434, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1146135330200195, "global_step": 386435, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0005881786346436, "global_step": 386436, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0491039752960205, "global_step": 386437, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1250808238983154, "global_step": 386438, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0718672275543213, "global_step": 386439, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.031226873397827, "global_step": 386440, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1095287799835205, "global_step": 386441, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.081965684890747, "global_step": 386442, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0920028686523438, "global_step": 386443, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.034259796142578, "global_step": 386444, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1109514236450195, "global_step": 386445, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0932185649871826, "global_step": 386446, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0743770599365234, "global_step": 386447, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.11769700050354, "global_step": 386448, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1276042461395264, "global_step": 386449, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1119890213012695, "global_step": 386450, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.030158519744873, "global_step": 386451, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.129619598388672, "global_step": 386452, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.093597650527954, "global_step": 386453, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.101621389389038, "global_step": 386454, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.152054786682129, "global_step": 386455, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1136741638183594, "global_step": 386456, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.204104423522949, "global_step": 386457, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.108875036239624, "global_step": 386458, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0044782161712646, "global_step": 386459, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0758485794067383, "global_step": 386460, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1076278686523438, "global_step": 386461, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.005563735961914, "global_step": 386462, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0006661415100098, "global_step": 386463, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1237382888793945, "global_step": 386464, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.094907283782959, "global_step": 386465, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0795738697052, "global_step": 386466, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0176827907562256, "global_step": 386467, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.004103183746338, "global_step": 386468, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.083653211593628, "global_step": 386469, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.065577507019043, "global_step": 386470, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.080094337463379, "global_step": 386471, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1365749835968018, "global_step": 386472, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1124484539031982, "global_step": 386473, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.090777635574341, "global_step": 386474, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0635387897491455, "global_step": 386475, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.130476713180542, "global_step": 386476, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.076773166656494, "global_step": 386477, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.201059579849243, "global_step": 386478, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0268685817718506, "global_step": 386479, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0936832427978516, "global_step": 386480, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0824034214019775, "global_step": 386481, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0841307640075684, "global_step": 386482, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1241722106933594, "global_step": 386483, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0825653076171875, "global_step": 386484, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.190865993499756, "global_step": 386485, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0773980617523193, "global_step": 386486, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.091456413269043, "global_step": 386487, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.142099380493164, "global_step": 386488, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0881576538085938, "global_step": 386489, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.133845329284668, "global_step": 386490, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1510019302368164, "global_step": 386491, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1135034561157227, "global_step": 386492, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.128601551055908, "global_step": 386493, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0703608989715576, "global_step": 386494, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1017298698425293, "global_step": 386495, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.104851245880127, "global_step": 386496, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0663199424743652, "global_step": 386497, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0247483253479004, "global_step": 386498, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.057586669921875, "global_step": 386499, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0842857360839844, "global_step": 386500, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0663297176361084, "global_step": 386501, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1625783443450928, "global_step": 386502, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.064178943634033, "global_step": 386503, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.191671371459961, "global_step": 386504, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.094843626022339, "global_step": 386505, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.121568202972412, "global_step": 386506, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.081320285797119, "global_step": 386507, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1433048248291016, "global_step": 386508, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.160676956176758, "global_step": 386509, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.168518304824829, "global_step": 386510, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1079037189483643, "global_step": 386511, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1431751251220703, "global_step": 386512, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.021697998046875, "global_step": 386513, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0515635013580322, "global_step": 386514, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.092433214187622, "global_step": 386515, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0705745220184326, "global_step": 386516, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1904189586639404, "global_step": 386517, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0672600269317627, "global_step": 386518, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.078646421432495, "global_step": 386519, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1540205478668213, "global_step": 386520, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0798795223236084, "global_step": 386521, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1328632831573486, "global_step": 386522, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0642447471618652, "global_step": 386523, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.087648868560791, "global_step": 386524, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0673248767852783, "global_step": 386525, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0919554233551025, "global_step": 386526, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.2053496837615967, "global_step": 386527, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0598504543304443, "global_step": 386528, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0898444652557373, "global_step": 386529, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1099116802215576, "global_step": 386530, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.109109401702881, "global_step": 386531, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.209636688232422, "global_step": 386532, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1458852291107178, "global_step": 386533, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0684871673583984, "global_step": 386534, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1403651237487793, "global_step": 386535, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0597317218780518, "global_step": 386536, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1494979858398438, "global_step": 386537, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0947601795196533, "global_step": 386538, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0957822799682617, "global_step": 386539, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1918625831604004, "global_step": 386540, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.012160301208496, "global_step": 386541, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.111772060394287, "global_step": 386542, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0887625217437744, "global_step": 386543, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1633758544921875, "global_step": 386544, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0927228927612305, "global_step": 386545, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0805368423461914, "global_step": 386546, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0768494606018066, "global_step": 386547, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1282875537872314, "global_step": 386548, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0470800399780273, "global_step": 386549, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.159100294113159, "global_step": 386550, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1235122680664062, "global_step": 386551, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.011289119720459, "global_step": 386552, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1456403732299805, "global_step": 386553, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1301722526550293, "global_step": 386554, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.034841299057007, "global_step": 386555, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1263742446899414, "global_step": 386556, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0377063751220703, "global_step": 386557, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.127157211303711, "global_step": 386558, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1398446559906006, "global_step": 386559, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1375041007995605, "global_step": 386560, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1170668601989746, "global_step": 386561, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1556522846221924, "global_step": 386562, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.122678518295288, "global_step": 386563, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1808643341064453, "global_step": 386564, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0422701835632324, "global_step": 386565, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.11484694480896, "global_step": 386566, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.087419033050537, "global_step": 386567, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1847915649414062, "global_step": 386568, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.185291290283203, "global_step": 386569, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1065776348114014, "global_step": 386570, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0520966053009033, "global_step": 386571, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1162374019622803, "global_step": 386572, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.173947334289551, "global_step": 386573, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.184109687805176, "global_step": 386574, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.082136392593384, "global_step": 386575, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.153047800064087, "global_step": 386576, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.107761859893799, "global_step": 386577, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1135129928588867, "global_step": 386578, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.9287900924682617, "global_step": 386579, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.089669942855835, "global_step": 386580, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.041515350341797, "global_step": 386581, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0915398597717285, "global_step": 386582, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.19815731048584, "global_step": 386583, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1172866821289062, "global_step": 386584, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.142810344696045, "global_step": 386585, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.111433267593384, "global_step": 386586, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.139784336090088, "global_step": 386587, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.114459753036499, "global_step": 386588, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1260616779327393, "global_step": 386589, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.143404245376587, "global_step": 386590, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.114443778991699, "global_step": 386591, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0805552005767822, "global_step": 386592, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.12027907371521, "global_step": 386593, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1741583347320557, "global_step": 386594, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0627925395965576, "global_step": 386595, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.160975217819214, "global_step": 386596, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0640969276428223, "global_step": 386597, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0795986652374268, "global_step": 386598, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0592293739318848, "global_step": 386599, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0773425102233887, "global_step": 386600, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.145113945007324, "global_step": 386601, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0894908905029297, "global_step": 386602, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.168336868286133, "global_step": 386603, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1509673595428467, "global_step": 386604, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1725738048553467, "global_step": 386605, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.114546775817871, "global_step": 386606, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0598220825195312, "global_step": 386607, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.9965691566467285, "global_step": 386608, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1766748428344727, "global_step": 386609, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.135702610015869, "global_step": 386610, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0785186290740967, "global_step": 386611, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.051727771759033, "global_step": 386612, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1660001277923584, "global_step": 386613, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.079270124435425, "global_step": 386614, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0793190002441406, "global_step": 386615, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.172931671142578, "global_step": 386616, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0529775619506836, "global_step": 386617, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0922634601593018, "global_step": 386618, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1346852779388428, "global_step": 386619, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1334450244903564, "global_step": 386620, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.120232105255127, "global_step": 386621, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.175036907196045, "global_step": 386622, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.067404270172119, "global_step": 386623, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.154374837875366, "global_step": 386624, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1101114749908447, "global_step": 386625, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.161912679672241, "global_step": 386626, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.130819320678711, "global_step": 386627, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1195521354675293, "global_step": 386628, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0665674209594727, "global_step": 386629, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0881638526916504, "global_step": 386630, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0173587799072266, "global_step": 386631, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.04188871383667, "global_step": 386632, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1251542568206787, "global_step": 386633, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1101694107055664, "global_step": 386634, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.026878595352173, "global_step": 386635, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.217268466949463, "global_step": 386636, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.187825918197632, "global_step": 386637, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1694743633270264, "global_step": 386638, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1659977436065674, "global_step": 386639, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.192608594894409, "global_step": 386640, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1611061096191406, "global_step": 386641, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1140923500061035, "global_step": 386642, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.057136297225952, "global_step": 386643, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1509556770324707, "global_step": 386644, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1822948455810547, "global_step": 386645, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0692312717437744, "global_step": 386646, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1744589805603027, "global_step": 386647, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0522401332855225, "global_step": 386648, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1230685710906982, "global_step": 386649, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1208910942077637, "global_step": 386650, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0542469024658203, "global_step": 386651, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.049470901489258, "global_step": 386652, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0947530269622803, "global_step": 386653, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.142042875289917, "global_step": 386654, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1836390495300293, "global_step": 386655, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1652588844299316, "global_step": 386656, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0778653621673584, "global_step": 386657, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.061851978302002, "global_step": 386658, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.095021963119507, "global_step": 386659, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0607690811157227, "global_step": 386660, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.168722152709961, "global_step": 386661, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.138763427734375, "global_step": 386662, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.144984006881714, "global_step": 386663, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0381534099578857, "global_step": 386664, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1004679203033447, "global_step": 386665, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.024127960205078, "global_step": 386666, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0751538276672363, "global_step": 386667, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0168228149414062, "global_step": 386668, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.182222604751587, "global_step": 386669, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.2278027534484863, "global_step": 386670, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1518712043762207, "global_step": 386671, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1374478340148926, "global_step": 386672, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.14133882522583, "global_step": 386673, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0729925632476807, "global_step": 386674, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.108698844909668, "global_step": 386675, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.143625020980835, "global_step": 386676, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.138654947280884, "global_step": 386677, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1709814071655273, "global_step": 386678, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0930166244506836, "global_step": 386679, "epoch": 748, "lr": 5e-05}
{"train_loss": 1.9953322410583496, "global_step": 386680, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1560678482055664, "global_step": 386681, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.085298538208008, "global_step": 386682, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1326801776885986, "global_step": 386683, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0948312282562256, "global_step": 386684, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.136730670928955, "global_step": 386685, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0151939392089844, "global_step": 386686, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.052135467529297, "global_step": 386687, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.051262378692627, "global_step": 386688, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1316239833831787, "global_step": 386689, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.15854549407959, "global_step": 386690, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0797805786132812, "global_step": 386691, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0937163829803467, "global_step": 386692, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.125213384628296, "global_step": 386693, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0426676273345947, "global_step": 386694, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1676037311553955, "global_step": 386695, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.2130277156829834, "global_step": 386696, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0376548767089844, "global_step": 386697, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.067683458328247, "global_step": 386698, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.141072988510132, "global_step": 386699, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.071617841720581, "global_step": 386700, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1716291904449463, "global_step": 386701, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0640995502471924, "global_step": 386702, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0237977504730225, "global_step": 386703, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1227011680603027, "global_step": 386704, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.173853635787964, "global_step": 386705, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0890045166015625, "global_step": 386706, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1718010902404785, "global_step": 386707, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.2166106700897217, "global_step": 386708, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.121403217315674, "global_step": 386709, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0257301330566406, "global_step": 386710, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1464309692382812, "global_step": 386711, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.105957508087158, "global_step": 386712, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0288429260253906, "global_step": 386713, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0553810596466064, "global_step": 386714, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1640312671661377, "global_step": 386715, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.184328079223633, "global_step": 386716, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1454014778137207, "global_step": 386717, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.120199680328369, "global_step": 386718, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1107959747314453, "global_step": 386719, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0892174243927, "global_step": 386720, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.091289758682251, "global_step": 386721, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.072962760925293, "global_step": 386722, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1571578979492188, "global_step": 386723, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.091214895248413, "global_step": 386724, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.129727840423584, "global_step": 386725, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0792014598846436, "global_step": 386726, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0819754600524902, "global_step": 386727, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0718448162078857, "global_step": 386728, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.191767930984497, "global_step": 386729, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1712734699249268, "global_step": 386730, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.18050479888916, "global_step": 386731, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0248637199401855, "global_step": 386732, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.041252851486206, "global_step": 386733, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.102916717529297, "global_step": 386734, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1203372478485107, "global_step": 386735, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0624399185180664, "global_step": 386736, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1242196559906006, "global_step": 386737, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1049177646636963, "global_step": 386738, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.138230800628662, "global_step": 386739, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.112839937210083, "global_step": 386740, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1934266090393066, "global_step": 386741, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1126482486724854, "global_step": 386742, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0415754318237305, "global_step": 386743, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1269257068634033, "global_step": 386744, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.072219133377075, "global_step": 386745, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.13346266746521, "global_step": 386746, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.2343227863311768, "global_step": 386747, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1214959621429443, "global_step": 386748, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.101562023162842, "global_step": 386749, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1160924434661865, "global_step": 386750, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0712826251983643, "global_step": 386751, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0896027088165283, "global_step": 386752, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.082075595855713, "global_step": 386753, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1068315505981445, "global_step": 386754, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.142245292663574, "global_step": 386755, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1054720878601074, "global_step": 386756, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0764496326446533, "global_step": 386757, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1007003784179688, "global_step": 386758, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1180291175842285, "global_step": 386759, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0373971462249756, "global_step": 386760, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.0430338382720947, "global_step": 386761, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1270134449005127, "global_step": 386762, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.1026360988616943, "global_step": 386763, "epoch": 748, "lr": 5e-05}
{"train_loss": 2.063605546951294, "global_step": 386764, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.088055372238159, "global_step": 386765, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.156096935272217, "global_step": 386766, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1040360927581787, "global_step": 386767, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.232351303100586, "global_step": 386768, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0949437618255615, "global_step": 386769, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1082115173339844, "global_step": 386770, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.077197790145874, "global_step": 386771, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1440372467041016, "global_step": 386772, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.04471492767334, "global_step": 386773, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.062901258468628, "global_step": 386774, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.160236120223999, "global_step": 386775, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0407800674438477, "global_step": 386776, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.085705280303955, "global_step": 386777, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0161030292510986, "global_step": 386778, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1772470474243164, "global_step": 386779, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1008293628692627, "global_step": 386780, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0759942531585693, "global_step": 386781, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.164644241333008, "global_step": 386782, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0605013370513916, "global_step": 386783, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1098639965057373, "global_step": 386784, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.127584934234619, "global_step": 386785, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.213226318359375, "global_step": 386786, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.2009878158569336, "global_step": 386787, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0754573345184326, "global_step": 386788, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0991780757904053, "global_step": 386789, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0644421577453613, "global_step": 386790, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1790847778320312, "global_step": 386791, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0518932342529297, "global_step": 386792, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.118947744369507, "global_step": 386793, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.986741304397583, "global_step": 386794, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1068997383117676, "global_step": 386795, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.036421775817871, "global_step": 386796, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0826268196105957, "global_step": 386797, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1006667613983154, "global_step": 386798, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0936810970306396, "global_step": 386799, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0799202919006348, "global_step": 386800, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1767239570617676, "global_step": 386801, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1081817150115967, "global_step": 386802, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1037206649780273, "global_step": 386803, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.043074131011963, "global_step": 386804, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1079649925231934, "global_step": 386805, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.111022472381592, "global_step": 386806, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1167550086975098, "global_step": 386807, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0134494304656982, "global_step": 386808, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0085291862487793, "global_step": 386809, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.095797061920166, "global_step": 386810, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0970194339752197, "global_step": 386811, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0433619022369385, "global_step": 386812, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.144213914871216, "global_step": 386813, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.033318281173706, "global_step": 386814, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.069784164428711, "global_step": 386815, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0794665813446045, "global_step": 386816, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1651978492736816, "global_step": 386817, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1851561069488525, "global_step": 386818, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1307897567749023, "global_step": 386819, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.056912899017334, "global_step": 386820, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.058751106262207, "global_step": 386821, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0526342391967773, "global_step": 386822, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.067798137664795, "global_step": 386823, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1014981269836426, "global_step": 386824, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.142162561416626, "global_step": 386825, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1408004760742188, "global_step": 386826, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.057706117630005, "global_step": 386827, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.19824481010437, "global_step": 386828, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0653347969055176, "global_step": 386829, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.074633836746216, "global_step": 386830, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1050338745117188, "global_step": 386831, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.114443778991699, "global_step": 386832, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0833899974823, "global_step": 386833, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.022871971130371, "global_step": 386834, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0733301639556885, "global_step": 386835, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0783097743988037, "global_step": 386836, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1682536602020264, "global_step": 386837, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.084064245223999, "global_step": 386838, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.102315902709961, "global_step": 386839, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.00266170501709, "global_step": 386840, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.135296106338501, "global_step": 386841, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0545694828033447, "global_step": 386842, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1567728519439697, "global_step": 386843, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1814064979553223, "global_step": 386844, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.069885492324829, "global_step": 386845, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.045114517211914, "global_step": 386846, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1237268447875977, "global_step": 386847, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.064758777618408, "global_step": 386848, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.087465524673462, "global_step": 386849, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.067816972732544, "global_step": 386850, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1698410511016846, "global_step": 386851, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.016197443008423, "global_step": 386852, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.000150203704834, "global_step": 386853, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1117353439331055, "global_step": 386854, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1619882583618164, "global_step": 386855, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.173175811767578, "global_step": 386856, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.097905158996582, "global_step": 386857, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.16589093208313, "global_step": 386858, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1006836891174316, "global_step": 386859, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0321590900421143, "global_step": 386860, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.11053729057312, "global_step": 386861, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.09788179397583, "global_step": 386862, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1417574882507324, "global_step": 386863, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.160413980484009, "global_step": 386864, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.160411834716797, "global_step": 386865, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0465705394744873, "global_step": 386866, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0814898014068604, "global_step": 386867, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.045717239379883, "global_step": 386868, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0861282348632812, "global_step": 386869, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.150561571121216, "global_step": 386870, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0802979469299316, "global_step": 386871, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1528117656707764, "global_step": 386872, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.105526924133301, "global_step": 386873, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.147982120513916, "global_step": 386874, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.025209665298462, "global_step": 386875, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0797736644744873, "global_step": 386876, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0719239711761475, "global_step": 386877, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1068413257598877, "global_step": 386878, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1750741004943848, "global_step": 386879, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1366100311279297, "global_step": 386880, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.016975164413452, "global_step": 386881, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.056421995162964, "global_step": 386882, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1436076164245605, "global_step": 386883, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1682567596435547, "global_step": 386884, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.042714834213257, "global_step": 386885, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0384602546691895, "global_step": 386886, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1784541606903076, "global_step": 386887, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.053912878036499, "global_step": 386888, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1212575435638428, "global_step": 386889, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.20542311668396, "global_step": 386890, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.176368236541748, "global_step": 386891, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.127258777618408, "global_step": 386892, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.095032215118408, "global_step": 386893, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.047790288925171, "global_step": 386894, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1433234214782715, "global_step": 386895, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1064159870147705, "global_step": 386896, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.083136796951294, "global_step": 386897, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0713038444519043, "global_step": 386898, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1228458881378174, "global_step": 386899, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0973541736602783, "global_step": 386900, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0147950649261475, "global_step": 386901, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.179635524749756, "global_step": 386902, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.040675401687622, "global_step": 386903, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.23337984085083, "global_step": 386904, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1039834022521973, "global_step": 386905, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0438289642333984, "global_step": 386906, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0534753799438477, "global_step": 386907, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.055020570755005, "global_step": 386908, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.155884265899658, "global_step": 386909, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0959463119506836, "global_step": 386910, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.10099720954895, "global_step": 386911, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0015225410461426, "global_step": 386912, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1294097900390625, "global_step": 386913, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.13130259513855, "global_step": 386914, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.057234764099121, "global_step": 386915, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.120983839035034, "global_step": 386916, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.069624900817871, "global_step": 386917, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.17836332321167, "global_step": 386918, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0787830352783203, "global_step": 386919, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.038411855697632, "global_step": 386920, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0591232776641846, "global_step": 386921, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.124859571456909, "global_step": 386922, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0155751705169678, "global_step": 386923, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0858585834503174, "global_step": 386924, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1285338401794434, "global_step": 386925, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.094534158706665, "global_step": 386926, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.096646308898926, "global_step": 386927, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1014914512634277, "global_step": 386928, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0431931018829346, "global_step": 386929, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.105717420578003, "global_step": 386930, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0866007804870605, "global_step": 386931, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.066880226135254, "global_step": 386932, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.032452344894409, "global_step": 386933, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.085881471633911, "global_step": 386934, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.977831244468689, "global_step": 386935, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.053720235824585, "global_step": 386936, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.144447088241577, "global_step": 386937, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1602489948272705, "global_step": 386938, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.005148410797119, "global_step": 386939, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.089416742324829, "global_step": 386940, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0927395820617676, "global_step": 386941, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0580077171325684, "global_step": 386942, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1052632331848145, "global_step": 386943, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1320648193359375, "global_step": 386944, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1328437328338623, "global_step": 386945, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0149459838867188, "global_step": 386946, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.079286813735962, "global_step": 386947, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0726089477539062, "global_step": 386948, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1119256019592285, "global_step": 386949, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0967442989349365, "global_step": 386950, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0537848472595215, "global_step": 386951, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.175952672958374, "global_step": 386952, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1680080890655518, "global_step": 386953, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.20135760307312, "global_step": 386954, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0477755069732666, "global_step": 386955, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0826079845428467, "global_step": 386956, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0607101917266846, "global_step": 386957, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.143981456756592, "global_step": 386958, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.047774076461792, "global_step": 386959, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0346062183380127, "global_step": 386960, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1240599155426025, "global_step": 386961, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0963263511657715, "global_step": 386962, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1053640842437744, "global_step": 386963, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0620765686035156, "global_step": 386964, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0630807876586914, "global_step": 386965, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0905463695526123, "global_step": 386966, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0874056816101074, "global_step": 386967, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.9965901374816895, "global_step": 386968, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1325979232788086, "global_step": 386969, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1422533988952637, "global_step": 386970, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.190483808517456, "global_step": 386971, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0499870777130127, "global_step": 386972, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0879404544830322, "global_step": 386973, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.06132435798645, "global_step": 386974, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.098696231842041, "global_step": 386975, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.180065393447876, "global_step": 386976, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.134519338607788, "global_step": 386977, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.9618301391601562, "global_step": 386978, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.157503843307495, "global_step": 386979, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0319457054138184, "global_step": 386980, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0778634548187256, "global_step": 386981, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0735983848571777, "global_step": 386982, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.135225772857666, "global_step": 386983, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.071195602416992, "global_step": 386984, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0039238929748535, "global_step": 386985, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1179401874542236, "global_step": 386986, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.986419916152954, "global_step": 386987, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.083578109741211, "global_step": 386988, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1623764038085938, "global_step": 386989, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0541768074035645, "global_step": 386990, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.108994960784912, "global_step": 386991, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.108927011489868, "global_step": 386992, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1368024349212646, "global_step": 386993, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.028472900390625, "global_step": 386994, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1328210830688477, "global_step": 386995, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.045762300491333, "global_step": 386996, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1382596492767334, "global_step": 386997, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1350150108337402, "global_step": 386998, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0394127368927, "global_step": 386999, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0718326568603516, "global_step": 387000, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.129863739013672, "global_step": 387001, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.174273729324341, "global_step": 387002, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.129089117050171, "global_step": 387003, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0883779525756836, "global_step": 387004, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1007437705993652, "global_step": 387005, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.135105609893799, "global_step": 387006, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.048247814178467, "global_step": 387007, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.093970775604248, "global_step": 387008, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1142916679382324, "global_step": 387009, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0880677700042725, "global_step": 387010, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.2637317180633545, "global_step": 387011, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.128652334213257, "global_step": 387012, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1504666805267334, "global_step": 387013, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1305196285247803, "global_step": 387014, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.037442684173584, "global_step": 387015, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.135542154312134, "global_step": 387016, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0895493030548096, "global_step": 387017, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1221494674682617, "global_step": 387018, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.065863609313965, "global_step": 387019, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.085261106491089, "global_step": 387020, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1296563148498535, "global_step": 387021, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0993475914001465, "global_step": 387022, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.160240888595581, "global_step": 387023, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1052563190460205, "global_step": 387024, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0915603637695312, "global_step": 387025, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0341570377349854, "global_step": 387026, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.091646671295166, "global_step": 387027, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1264727115631104, "global_step": 387028, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1289479732513428, "global_step": 387029, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.057960271835327, "global_step": 387030, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.9977988004684448, "global_step": 387031, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.059727907180786, "global_step": 387032, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.117738962173462, "global_step": 387033, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1334004402160645, "global_step": 387034, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.073352575302124, "global_step": 387035, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1339778900146484, "global_step": 387036, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.102463960647583, "global_step": 387037, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0712673664093018, "global_step": 387038, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.145998001098633, "global_step": 387039, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.028383493423462, "global_step": 387040, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0827572345733643, "global_step": 387041, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0770792961120605, "global_step": 387042, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0585384368896484, "global_step": 387043, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.994957447052002, "global_step": 387044, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0934741497039795, "global_step": 387045, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.082784414291382, "global_step": 387046, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0550971031188965, "global_step": 387047, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.178421974182129, "global_step": 387048, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.9900168180465698, "global_step": 387049, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.162853956222534, "global_step": 387050, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1222283840179443, "global_step": 387051, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.157959461212158, "global_step": 387052, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.180346965789795, "global_step": 387053, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.08126163482666, "global_step": 387054, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0381484031677246, "global_step": 387055, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.096712589263916, "global_step": 387056, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.08223557472229, "global_step": 387057, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0579397678375244, "global_step": 387058, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.040998935699463, "global_step": 387059, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1105027198791504, "global_step": 387060, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.14017653465271, "global_step": 387061, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.091954469680786, "global_step": 387062, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.044360637664795, "global_step": 387063, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.11871600151062, "global_step": 387064, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.046144485473633, "global_step": 387065, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.075373649597168, "global_step": 387066, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.178821563720703, "global_step": 387067, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1399474143981934, "global_step": 387068, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0940279960632324, "global_step": 387069, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0695130825042725, "global_step": 387070, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.216005325317383, "global_step": 387071, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1684184074401855, "global_step": 387072, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0823757648468018, "global_step": 387073, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1537253856658936, "global_step": 387074, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1129910945892334, "global_step": 387075, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1118764877319336, "global_step": 387076, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0628037452697754, "global_step": 387077, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1237475872039795, "global_step": 387078, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1276302337646484, "global_step": 387079, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.000276803970337, "global_step": 387080, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.046576738357544, "global_step": 387081, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.175520658493042, "global_step": 387082, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.133042335510254, "global_step": 387083, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.019944190979004, "global_step": 387084, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.9804203510284424, "global_step": 387085, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.141446828842163, "global_step": 387086, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1078720092773438, "global_step": 387087, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.9912470579147339, "global_step": 387088, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0990991592407227, "global_step": 387089, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1524851322174072, "global_step": 387090, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.086106777191162, "global_step": 387091, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.098637104034424, "global_step": 387092, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.05914044380188, "global_step": 387093, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1077733039855957, "global_step": 387094, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0434131622314453, "global_step": 387095, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1165661811828613, "global_step": 387096, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.9623889923095703, "global_step": 387097, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.101895332336426, "global_step": 387098, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0942893028259277, "global_step": 387099, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.110593318939209, "global_step": 387100, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1329262256622314, "global_step": 387101, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.117609977722168, "global_step": 387102, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1157422065734863, "global_step": 387103, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0275704860687256, "global_step": 387104, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.980934739112854, "global_step": 387105, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1584908962249756, "global_step": 387106, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0990257263183594, "global_step": 387107, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0525131225585938, "global_step": 387108, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0999436378479004, "global_step": 387109, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.085167407989502, "global_step": 387110, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1288652420043945, "global_step": 387111, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1723341941833496, "global_step": 387112, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0230939388275146, "global_step": 387113, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0808472633361816, "global_step": 387114, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.135784149169922, "global_step": 387115, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0844709873199463, "global_step": 387116, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.158067464828491, "global_step": 387117, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.221683979034424, "global_step": 387118, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1449978351593018, "global_step": 387119, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0060954093933105, "global_step": 387120, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.114381790161133, "global_step": 387121, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.031407117843628, "global_step": 387122, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1371238231658936, "global_step": 387123, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.150019884109497, "global_step": 387124, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0612075328826904, "global_step": 387125, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.037081480026245, "global_step": 387126, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1130096912384033, "global_step": 387127, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1691670417785645, "global_step": 387128, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.074157238006592, "global_step": 387129, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.160615921020508, "global_step": 387130, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.045652151107788, "global_step": 387131, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.068049430847168, "global_step": 387132, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.092010498046875, "global_step": 387133, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1798222064971924, "global_step": 387134, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.13409686088562, "global_step": 387135, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.078885793685913, "global_step": 387136, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1470787525177, "global_step": 387137, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.018115520477295, "global_step": 387138, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.077003240585327, "global_step": 387139, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.097724676132202, "global_step": 387140, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.061023235321045, "global_step": 387141, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.184931516647339, "global_step": 387142, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0806007385253906, "global_step": 387143, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1194632053375244, "global_step": 387144, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.128476619720459, "global_step": 387145, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.079655170440674, "global_step": 387146, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0862605571746826, "global_step": 387147, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.095749616622925, "global_step": 387148, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.15456485748291, "global_step": 387149, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0479071140289307, "global_step": 387150, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0995261669158936, "global_step": 387151, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1249637603759766, "global_step": 387152, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.097907066345215, "global_step": 387153, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.9930744171142578, "global_step": 387154, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.9733346700668335, "global_step": 387155, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.067681312561035, "global_step": 387156, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1770033836364746, "global_step": 387157, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0973923206329346, "global_step": 387158, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0801403522491455, "global_step": 387159, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.084913492202759, "global_step": 387160, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1949622631073, "global_step": 387161, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.130317211151123, "global_step": 387162, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1776857376098633, "global_step": 387163, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.053466558456421, "global_step": 387164, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0861475467681885, "global_step": 387165, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.044121265411377, "global_step": 387166, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0821032524108887, "global_step": 387167, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1338744163513184, "global_step": 387168, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0414040088653564, "global_step": 387169, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0954861640930176, "global_step": 387170, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.037475347518921, "global_step": 387171, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.057339906692505, "global_step": 387172, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1113929748535156, "global_step": 387173, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.076936960220337, "global_step": 387174, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1688177585601807, "global_step": 387175, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1739180088043213, "global_step": 387176, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0328598022460938, "global_step": 387177, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.088878870010376, "global_step": 387178, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.063978433609009, "global_step": 387179, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.2327423095703125, "global_step": 387180, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0698676109313965, "global_step": 387181, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.9965438842773438, "global_step": 387182, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.112696647644043, "global_step": 387183, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0496273040771484, "global_step": 387184, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0003833770751953, "global_step": 387185, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1808016300201416, "global_step": 387186, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1468446254730225, "global_step": 387187, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1321492195129395, "global_step": 387188, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1704800128936768, "global_step": 387189, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.042872905731201, "global_step": 387190, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1146082878112793, "global_step": 387191, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0714340209960938, "global_step": 387192, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1606318950653076, "global_step": 387193, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.146132230758667, "global_step": 387194, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1290602684020996, "global_step": 387195, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.145493507385254, "global_step": 387196, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0687406063079834, "global_step": 387197, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.079132318496704, "global_step": 387198, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.091231107711792, "global_step": 387199, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0397462844848633, "global_step": 387200, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.203732967376709, "global_step": 387201, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0312047004699707, "global_step": 387202, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1327106952667236, "global_step": 387203, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0658459663391113, "global_step": 387204, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1560630798339844, "global_step": 387205, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1011509895324707, "global_step": 387206, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.050105094909668, "global_step": 387207, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.099557876586914, "global_step": 387208, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1351161003112793, "global_step": 387209, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.091606378555298, "global_step": 387210, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.049769163131714, "global_step": 387211, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.065018653869629, "global_step": 387212, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.059603452682495, "global_step": 387213, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.027940511703491, "global_step": 387214, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1496052742004395, "global_step": 387215, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.095813512802124, "global_step": 387216, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0815861225128174, "global_step": 387217, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.132845163345337, "global_step": 387218, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1122043132781982, "global_step": 387219, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1773760318756104, "global_step": 387220, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0296194553375244, "global_step": 387221, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1489827632904053, "global_step": 387222, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1004891395568848, "global_step": 387223, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.093008279800415, "global_step": 387224, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0906670093536377, "global_step": 387225, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1240079402923584, "global_step": 387226, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.101928949356079, "global_step": 387227, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1585137844085693, "global_step": 387228, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1187760829925537, "global_step": 387229, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1559839248657227, "global_step": 387230, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0581400394439697, "global_step": 387231, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.06036639213562, "global_step": 387232, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0886001586914062, "global_step": 387233, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.068617582321167, "global_step": 387234, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.063204526901245, "global_step": 387235, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0389246940612793, "global_step": 387236, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.178313732147217, "global_step": 387237, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0414772033691406, "global_step": 387238, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1222116947174072, "global_step": 387239, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1204023361206055, "global_step": 387240, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.106196403503418, "global_step": 387241, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1846425533294678, "global_step": 387242, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0992674827575684, "global_step": 387243, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1769843101501465, "global_step": 387244, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1812849044799805, "global_step": 387245, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.092350959777832, "global_step": 387246, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.113248825073242, "global_step": 387247, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1565732955932617, "global_step": 387248, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.038525342941284, "global_step": 387249, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0888795852661133, "global_step": 387250, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0213470458984375, "global_step": 387251, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0843751430511475, "global_step": 387252, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.042055606842041, "global_step": 387253, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.130636692047119, "global_step": 387254, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1709277629852295, "global_step": 387255, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0887720584869385, "global_step": 387256, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.139207601547241, "global_step": 387257, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.2158217430114746, "global_step": 387258, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1304545402526855, "global_step": 387259, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.013857841491699, "global_step": 387260, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0218286514282227, "global_step": 387261, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.081101417541504, "global_step": 387262, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0661253929138184, "global_step": 387263, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1051185131073, "global_step": 387264, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1061859130859375, "global_step": 387265, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.178539514541626, "global_step": 387266, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1201248168945312, "global_step": 387267, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1438488960266113, "global_step": 387268, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0680654048919678, "global_step": 387269, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.103922128677368, "global_step": 387270, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0894432067871094, "global_step": 387271, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.162044048309326, "global_step": 387272, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.116856098175049, "global_step": 387273, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1085240840911865, "global_step": 387274, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0788819789886475, "global_step": 387275, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.177896022796631, "global_step": 387276, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1635043621063232, "global_step": 387277, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1213347911834717, "global_step": 387278, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.198270797729492, "global_step": 387279, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1189558506011963, "global_step": 387280, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1557531356811523, "global_step": 387281, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.087444543838501, "global_step": 387282, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.14334774017334, "global_step": 387283, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1272385120391846, "global_step": 387284, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1067965030670166, "global_step": 387285, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0300374031066895, "global_step": 387286, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1101772785186768, "global_step": 387287, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.107520818710327, "global_step": 387288, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0709197521209717, "global_step": 387289, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1230721473693848, "global_step": 387290, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1590607166290283, "global_step": 387291, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0634734630584717, "global_step": 387292, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.143789052963257, "global_step": 387293, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.148188829421997, "global_step": 387294, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.177682638168335, "global_step": 387295, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.051539897918701, "global_step": 387296, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.2475881576538086, "global_step": 387297, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0033082962036133, "global_step": 387298, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1538174152374268, "global_step": 387299, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.058112621307373, "global_step": 387300, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1841862201690674, "global_step": 387301, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0834147930145264, "global_step": 387302, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1151771545410156, "global_step": 387303, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.041720390319824, "global_step": 387304, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0759036540985107, "global_step": 387305, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0895817279815674, "global_step": 387306, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.9819886684417725, "global_step": 387307, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.154278039932251, "global_step": 387308, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1304104328155518, "global_step": 387309, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.107788562774658, "global_step": 387310, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.092491626739502, "global_step": 387311, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.118122100830078, "global_step": 387312, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1440584659576416, "global_step": 387313, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.076752185821533, "global_step": 387314, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0528783798217773, "global_step": 387315, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.132446765899658, "global_step": 387316, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.00673770904541, "global_step": 387317, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1417348384857178, "global_step": 387318, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.133225202560425, "global_step": 387319, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0842196941375732, "global_step": 387320, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1009609699249268, "global_step": 387321, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0880215167999268, "global_step": 387322, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1261038780212402, "global_step": 387323, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.168833017349243, "global_step": 387324, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.070807456970215, "global_step": 387325, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0198633670806885, "global_step": 387326, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0934131145477295, "global_step": 387327, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.066920757293701, "global_step": 387328, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.096869707107544, "global_step": 387329, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1468496322631836, "global_step": 387330, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.986339807510376, "global_step": 387331, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.101717948913574, "global_step": 387332, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0745842456817627, "global_step": 387333, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.165862560272217, "global_step": 387334, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1902692317962646, "global_step": 387335, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0301685333251953, "global_step": 387336, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1669905185699463, "global_step": 387337, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.131804943084717, "global_step": 387338, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0514190196990967, "global_step": 387339, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.125528573989868, "global_step": 387340, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0893993377685547, "global_step": 387341, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0959420204162598, "global_step": 387342, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1700522899627686, "global_step": 387343, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1013505458831787, "global_step": 387344, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0645008087158203, "global_step": 387345, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1307172775268555, "global_step": 387346, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0756218433380127, "global_step": 387347, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.133039951324463, "global_step": 387348, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1062426567077637, "global_step": 387349, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.10103178024292, "global_step": 387350, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.146282911300659, "global_step": 387351, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.015712022781372, "global_step": 387352, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.174623727798462, "global_step": 387353, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0333383083343506, "global_step": 387354, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1387081146240234, "global_step": 387355, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.118044137954712, "global_step": 387356, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0414206981658936, "global_step": 387357, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0779449939727783, "global_step": 387358, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.11391544342041, "global_step": 387359, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.085317611694336, "global_step": 387360, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0716423988342285, "global_step": 387361, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.142470121383667, "global_step": 387362, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1241447925567627, "global_step": 387363, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1198196411132812, "global_step": 387364, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.150470018386841, "global_step": 387365, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1233906745910645, "global_step": 387366, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.119812488555908, "global_step": 387367, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.060392379760742, "global_step": 387368, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.08732533454895, "global_step": 387369, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1058499813079834, "global_step": 387370, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.10587215423584, "global_step": 387371, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.130945920944214, "global_step": 387372, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1043124198913574, "global_step": 387373, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1082255840301514, "global_step": 387374, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.073460340499878, "global_step": 387375, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1827664375305176, "global_step": 387376, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.045584201812744, "global_step": 387377, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1228115558624268, "global_step": 387378, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.134774923324585, "global_step": 387379, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1090128421783447, "global_step": 387380, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.108966827392578, "global_step": 387381, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0344533920288086, "global_step": 387382, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1284773349761963, "global_step": 387383, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0889394283294678, "global_step": 387384, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.088290214538574, "global_step": 387385, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.087383508682251, "global_step": 387386, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.163410186767578, "global_step": 387387, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1469967365264893, "global_step": 387388, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.079380512237549, "global_step": 387389, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.15057635307312, "global_step": 387390, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.088008165359497, "global_step": 387391, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1678576469421387, "global_step": 387392, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.13388729095459, "global_step": 387393, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1396403312683105, "global_step": 387394, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.112396240234375, "global_step": 387395, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0871341228485107, "global_step": 387396, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1768243312835693, "global_step": 387397, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.213886022567749, "global_step": 387398, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.136301279067993, "global_step": 387399, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.024730920791626, "global_step": 387400, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.013625144958496, "global_step": 387401, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1131539344787598, "global_step": 387402, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.025299310684204, "global_step": 387403, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.077202796936035, "global_step": 387404, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1282155513763428, "global_step": 387405, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1296322345733643, "global_step": 387406, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.106783390045166, "global_step": 387407, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0555429458618164, "global_step": 387408, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.126906394958496, "global_step": 387409, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.036059856414795, "global_step": 387410, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0995798110961914, "global_step": 387411, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.104066848754883, "global_step": 387412, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.21541690826416, "global_step": 387413, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0903429985046387, "global_step": 387414, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1256184577941895, "global_step": 387415, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1206562519073486, "global_step": 387416, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.063392162322998, "global_step": 387417, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.101656675338745, "global_step": 387418, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0770092010498047, "global_step": 387419, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0500786304473877, "global_step": 387420, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1248252391815186, "global_step": 387421, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1503474712371826, "global_step": 387422, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.09790301322937, "global_step": 387423, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1178810596466064, "global_step": 387424, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.138554334640503, "global_step": 387425, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.105836868286133, "global_step": 387426, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1312646865844727, "global_step": 387427, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0570571422576904, "global_step": 387428, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1172640323638916, "global_step": 387429, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0724825859069824, "global_step": 387430, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.08634614944458, "global_step": 387431, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0915236473083496, "global_step": 387432, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.192735433578491, "global_step": 387433, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.112987756729126, "global_step": 387434, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0732452869415283, "global_step": 387435, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0799143314361572, "global_step": 387436, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0571601390838623, "global_step": 387437, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.194828748703003, "global_step": 387438, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.052217721939087, "global_step": 387439, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1013448238372803, "global_step": 387440, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0322952270507812, "global_step": 387441, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0329880714416504, "global_step": 387442, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1348514556884766, "global_step": 387443, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.073824882507324, "global_step": 387444, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1038858890533447, "global_step": 387445, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0932483673095703, "global_step": 387446, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1406357288360596, "global_step": 387447, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1107215881347656, "global_step": 387448, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1954545974731445, "global_step": 387449, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.004465103149414, "global_step": 387450, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.03518009185791, "global_step": 387451, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.135732412338257, "global_step": 387452, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0979812145233154, "global_step": 387453, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1425247192382812, "global_step": 387454, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1793882846832275, "global_step": 387455, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0586724281311035, "global_step": 387456, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.155993700027466, "global_step": 387457, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.102200508117676, "global_step": 387458, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0909667015075684, "global_step": 387459, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0899338722229004, "global_step": 387460, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0040171146392822, "global_step": 387461, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0951898097991943, "global_step": 387462, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1141462326049805, "global_step": 387463, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.028132677078247, "global_step": 387464, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.152139186859131, "global_step": 387465, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0418193340301514, "global_step": 387466, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.091012477874756, "global_step": 387467, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.212993860244751, "global_step": 387468, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1066954135894775, "global_step": 387469, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0799639225006104, "global_step": 387470, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1398398876190186, "global_step": 387471, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1312785148620605, "global_step": 387472, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.2195193767547607, "global_step": 387473, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.19325590133667, "global_step": 387474, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1347923278808594, "global_step": 387475, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.066669225692749, "global_step": 387476, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.030919313430786, "global_step": 387477, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1567811965942383, "global_step": 387478, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.035872220993042, "global_step": 387479, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.9770549535751343, "global_step": 387480, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0966103076934814, "global_step": 387481, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.136361598968506, "global_step": 387482, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.009342908859253, "global_step": 387483, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1181070804595947, "global_step": 387484, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.074982166290283, "global_step": 387485, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0973334312438965, "global_step": 387486, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0658130645751953, "global_step": 387487, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1185803413391113, "global_step": 387488, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1343188285827637, "global_step": 387489, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.119217872619629, "global_step": 387490, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0513598918914795, "global_step": 387491, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.120137929916382, "global_step": 387492, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.034757375717163, "global_step": 387493, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1508705615997314, "global_step": 387494, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.199387311935425, "global_step": 387495, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1535770893096924, "global_step": 387496, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1510586738586426, "global_step": 387497, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.041145086288452, "global_step": 387498, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1029231548309326, "global_step": 387499, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.10872745513916, "global_step": 387500, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.117201566696167, "global_step": 387501, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1111340522766113, "global_step": 387502, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.120288133621216, "global_step": 387503, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1354117393493652, "global_step": 387504, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1619815826416016, "global_step": 387505, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.137437343597412, "global_step": 387506, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1327075958251953, "global_step": 387507, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1212854385375977, "global_step": 387508, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.093345880508423, "global_step": 387509, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.12150502204895, "global_step": 387510, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.184826135635376, "global_step": 387511, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0901520252227783, "global_step": 387512, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0851292610168457, "global_step": 387513, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1071279048919678, "global_step": 387514, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0509727001190186, "global_step": 387515, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.110598087310791, "global_step": 387516, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.195176601409912, "global_step": 387517, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1455190181732178, "global_step": 387518, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.077792167663574, "global_step": 387519, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1039061546325684, "global_step": 387520, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0974555015563965, "global_step": 387521, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1125762462615967, "global_step": 387522, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0651772022247314, "global_step": 387523, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.164705991744995, "global_step": 387524, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0713672637939453, "global_step": 387525, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1106274127960205, "global_step": 387526, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1761486530303955, "global_step": 387527, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1200997829437256, "global_step": 387528, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0439374446868896, "global_step": 387529, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.15150785446167, "global_step": 387530, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0988526344299316, "global_step": 387531, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.042313575744629, "global_step": 387532, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.089387893676758, "global_step": 387533, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.056817054748535, "global_step": 387534, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1554393768310547, "global_step": 387535, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1409478187561035, "global_step": 387536, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1570146083831787, "global_step": 387537, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1523783206939697, "global_step": 387538, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1781678199768066, "global_step": 387539, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.064471483230591, "global_step": 387540, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1364192962646484, "global_step": 387541, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1789751052856445, "global_step": 387542, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1233510971069336, "global_step": 387543, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.075951099395752, "global_step": 387544, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1206741333007812, "global_step": 387545, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.053992509841919, "global_step": 387546, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0024971961975098, "global_step": 387547, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1153554916381836, "global_step": 387548, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0901618003845215, "global_step": 387549, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0586907863616943, "global_step": 387550, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.209378480911255, "global_step": 387551, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.151707410812378, "global_step": 387552, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1715784072875977, "global_step": 387553, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.076704740524292, "global_step": 387554, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1077516078948975, "global_step": 387555, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1084446907043457, "global_step": 387556, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1530520915985107, "global_step": 387557, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0938515663146973, "global_step": 387558, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.108691930770874, "global_step": 387559, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1150190830230713, "global_step": 387560, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.176952362060547, "global_step": 387561, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.2072432041168213, "global_step": 387562, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.139186143875122, "global_step": 387563, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1524314880371094, "global_step": 387564, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1065921783447266, "global_step": 387565, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1181178092956543, "global_step": 387566, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.193061113357544, "global_step": 387567, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1613941192626953, "global_step": 387568, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.027498245239258, "global_step": 387569, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.140746831893921, "global_step": 387570, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0840752124786377, "global_step": 387571, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1348297595977783, "global_step": 387572, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.157454490661621, "global_step": 387573, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0953428745269775, "global_step": 387574, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0595874786376953, "global_step": 387575, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.9986474514007568, "global_step": 387576, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.066438674926758, "global_step": 387577, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0621793270111084, "global_step": 387578, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0946357250213623, "global_step": 387579, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.153965711593628, "global_step": 387580, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.116687297821045, "global_step": 387581, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0957369804382324, "global_step": 387582, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1622660160064697, "global_step": 387583, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.9985873699188232, "global_step": 387584, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1783463954925537, "global_step": 387585, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1135001182556152, "global_step": 387586, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.203531503677368, "global_step": 387587, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1467339992523193, "global_step": 387588, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1137804985046387, "global_step": 387589, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.149909257888794, "global_step": 387590, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.011178493499756, "global_step": 387591, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.182490110397339, "global_step": 387592, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1617164611816406, "global_step": 387593, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.136244297027588, "global_step": 387594, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.054863691329956, "global_step": 387595, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0801687240600586, "global_step": 387596, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.085008382797241, "global_step": 387597, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.13295578956604, "global_step": 387598, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0517194271087646, "global_step": 387599, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0255544185638428, "global_step": 387600, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0510902404785156, "global_step": 387601, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0331032276153564, "global_step": 387602, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.2105748653411865, "global_step": 387603, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.09342885017395, "global_step": 387604, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1093199253082275, "global_step": 387605, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.002645492553711, "global_step": 387606, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1084482669830322, "global_step": 387607, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0757458209991455, "global_step": 387608, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1191999912261963, "global_step": 387609, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.167588233947754, "global_step": 387610, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1363894939422607, "global_step": 387611, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1807758808135986, "global_step": 387612, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1682722568511963, "global_step": 387613, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1609835624694824, "global_step": 387614, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.067657709121704, "global_step": 387615, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0842790603637695, "global_step": 387616, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1669423580169678, "global_step": 387617, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.174112558364868, "global_step": 387618, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.06606388092041, "global_step": 387619, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1068034172058105, "global_step": 387620, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1123785972595215, "global_step": 387621, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0133283138275146, "global_step": 387622, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.230250358581543, "global_step": 387623, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.17048716545105, "global_step": 387624, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1042089462280273, "global_step": 387625, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.06486177444458, "global_step": 387626, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.016301155090332, "global_step": 387627, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.138605833053589, "global_step": 387628, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0746383666992188, "global_step": 387629, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.06196928024292, "global_step": 387630, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0890274047851562, "global_step": 387631, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.093958854675293, "global_step": 387632, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.159147262573242, "global_step": 387633, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0985066890716553, "global_step": 387634, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.039689779281616, "global_step": 387635, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1354176998138428, "global_step": 387636, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0733020305633545, "global_step": 387637, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0508852005004883, "global_step": 387638, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0426831245422363, "global_step": 387639, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1763253211975098, "global_step": 387640, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1852822303771973, "global_step": 387641, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0634474754333496, "global_step": 387642, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1044466495513916, "global_step": 387643, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0634913444519043, "global_step": 387644, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0958614349365234, "global_step": 387645, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.173068046569824, "global_step": 387646, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1373372077941895, "global_step": 387647, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.164055347442627, "global_step": 387648, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0832717418670654, "global_step": 387649, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.095795154571533, "global_step": 387650, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.129570245742798, "global_step": 387651, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1743431091308594, "global_step": 387652, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.129321336746216, "global_step": 387653, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.115624189376831, "global_step": 387654, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0648910999298096, "global_step": 387655, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.08836030960083, "global_step": 387656, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0079312324523926, "global_step": 387657, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1710808277130127, "global_step": 387658, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.103559970855713, "global_step": 387659, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0499532222747803, "global_step": 387660, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.043248414993286, "global_step": 387661, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.056663751602173, "global_step": 387662, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1159250736236572, "global_step": 387663, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.11380934715271, "global_step": 387664, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.19053053855896, "global_step": 387665, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1051442623138428, "global_step": 387666, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1481964588165283, "global_step": 387667, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.098158597946167, "global_step": 387668, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.105548143386841, "global_step": 387669, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1731486320495605, "global_step": 387670, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0679595470428467, "global_step": 387671, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1070468425750732, "global_step": 387672, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.160038709640503, "global_step": 387673, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.164519786834717, "global_step": 387674, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.9766974449157715, "global_step": 387675, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1124420166015625, "global_step": 387676, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.111070156097412, "global_step": 387677, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.144566059112549, "global_step": 387678, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.140580415725708, "global_step": 387679, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.060934543609619, "global_step": 387680, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0971519947052, "global_step": 387681, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.176821231842041, "global_step": 387682, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.117356300354004, "global_step": 387683, "epoch": 749, "lr": 5e-05}
{"train_loss": 1.997090220451355, "global_step": 387684, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.08687162399292, "global_step": 387685, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0620713233947754, "global_step": 387686, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1368789672851562, "global_step": 387687, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1048669815063477, "global_step": 387688, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.125272274017334, "global_step": 387689, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0546579360961914, "global_step": 387690, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0464224815368652, "global_step": 387691, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.121783494949341, "global_step": 387692, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.123145580291748, "global_step": 387693, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.2901644706726074, "global_step": 387694, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.032935380935669, "global_step": 387695, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1100449562072754, "global_step": 387696, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.126554012298584, "global_step": 387697, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1272599697113037, "global_step": 387698, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.125149726867676, "global_step": 387699, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0735812187194824, "global_step": 387700, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0588786602020264, "global_step": 387701, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0123376846313477, "global_step": 387702, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1221652030944824, "global_step": 387703, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1296372413635254, "global_step": 387704, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.044210910797119, "global_step": 387705, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1276581287384033, "global_step": 387706, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0595481395721436, "global_step": 387707, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0816879272460938, "global_step": 387708, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0713281631469727, "global_step": 387709, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.11738920211792, "global_step": 387710, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.127249002456665, "global_step": 387711, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0881242752075195, "global_step": 387712, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.2329423427581787, "global_step": 387713, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1025378704071045, "global_step": 387714, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0752995014190674, "global_step": 387715, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.16414213180542, "global_step": 387716, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0966625213623047, "global_step": 387717, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.039717435836792, "global_step": 387718, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0038981437683105, "global_step": 387719, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.11153507232666, "global_step": 387720, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.108945846557617, "global_step": 387721, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0856220722198486, "global_step": 387722, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0758860111236572, "global_step": 387723, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1857059001922607, "global_step": 387724, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0899534225463867, "global_step": 387725, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1558518409729004, "global_step": 387726, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0873358249664307, "global_step": 387727, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1761701107025146, "global_step": 387728, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.1003987789154053, "global_step": 387729, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.152039051055908, "global_step": 387730, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.143895149230957, "global_step": 387731, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.102572202682495, "global_step": 387732, "epoch": 749, "lr": 5e-05}
{"train_loss": 2.0447275638580322, "global_step": 387733, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.111739158630371, "global_step": 387734, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0642874240875244, "global_step": 387735, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0459206104278564, "global_step": 387736, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1310932636260986, "global_step": 387737, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1459720134735107, "global_step": 387738, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.053839683532715, "global_step": 387739, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0549044609069824, "global_step": 387740, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0621461868286133, "global_step": 387741, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1488914489746094, "global_step": 387742, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.075561046600342, "global_step": 387743, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.06828236579895, "global_step": 387744, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.088693618774414, "global_step": 387745, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.119112014770508, "global_step": 387746, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.097290515899658, "global_step": 387747, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0725717544555664, "global_step": 387748, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0650017261505127, "global_step": 387749, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0966780185699463, "global_step": 387750, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0055534839630127, "global_step": 387751, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1225831508636475, "global_step": 387752, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1584551334381104, "global_step": 387753, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.100151300430298, "global_step": 387754, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0531885623931885, "global_step": 387755, "epoch": 750, "lr": 5e-05}
{"train_loss": 1.995477557182312, "global_step": 387756, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.091980218887329, "global_step": 387757, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1622066497802734, "global_step": 387758, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0697083473205566, "global_step": 387759, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0914454460144043, "global_step": 387760, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.135551691055298, "global_step": 387761, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0373377799987793, "global_step": 387762, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1600089073181152, "global_step": 387763, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0876731872558594, "global_step": 387764, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.063829183578491, "global_step": 387765, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1254944801330566, "global_step": 387766, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.119525909423828, "global_step": 387767, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0977814197540283, "global_step": 387768, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1391921043395996, "global_step": 387769, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1455888748168945, "global_step": 387770, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.075805902481079, "global_step": 387771, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0766124725341797, "global_step": 387772, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0831456184387207, "global_step": 387773, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0881741046905518, "global_step": 387774, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.163217782974243, "global_step": 387775, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0695900917053223, "global_step": 387776, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1036572456359863, "global_step": 387777, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0334153175354004, "global_step": 387778, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0823512077331543, "global_step": 387779, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1034646034240723, "global_step": 387780, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.155959129333496, "global_step": 387781, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1199774742126465, "global_step": 387782, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0738584995269775, "global_step": 387783, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0366671085357666, "global_step": 387784, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.003473997116089, "global_step": 387785, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.011934995651245, "global_step": 387786, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1639533042907715, "global_step": 387787, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0804433822631836, "global_step": 387788, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.020867109298706, "global_step": 387789, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0544331073760986, "global_step": 387790, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0796215534210205, "global_step": 387791, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0394229888916016, "global_step": 387792, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1477878093719482, "global_step": 387793, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.05822491645813, "global_step": 387794, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0526556968688965, "global_step": 387795, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.158730983734131, "global_step": 387796, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.094404935836792, "global_step": 387797, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1037964820861816, "global_step": 387798, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0740416049957275, "global_step": 387799, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1046440601348877, "global_step": 387800, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0650670528411865, "global_step": 387801, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1426892280578613, "global_step": 387802, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.031219959259033, "global_step": 387803, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.114790678024292, "global_step": 387804, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.082258462905884, "global_step": 387805, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0428128242492676, "global_step": 387806, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1783595085144043, "global_step": 387807, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.173790216445923, "global_step": 387808, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.08092999458313, "global_step": 387809, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.06758189201355, "global_step": 387810, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0523130893707275, "global_step": 387811, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1967544555664062, "global_step": 387812, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.057192325592041, "global_step": 387813, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1441714763641357, "global_step": 387814, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.146217107772827, "global_step": 387815, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1171045303344727, "global_step": 387816, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.060333013534546, "global_step": 387817, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1239585876464844, "global_step": 387818, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1649727821350098, "global_step": 387819, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1238393783569336, "global_step": 387820, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1607415676116943, "global_step": 387821, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1013023853302, "global_step": 387822, "epoch": 750, "lr": 5e-05}
{"train_loss": 1.967453956604004, "global_step": 387823, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.114980459213257, "global_step": 387824, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.124603033065796, "global_step": 387825, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.068286895751953, "global_step": 387826, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1183524131774902, "global_step": 387827, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1098101139068604, "global_step": 387828, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1769051551818848, "global_step": 387829, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0789988040924072, "global_step": 387830, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.066251039505005, "global_step": 387831, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0822808742523193, "global_step": 387832, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.143831253051758, "global_step": 387833, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.147625207901001, "global_step": 387834, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1935253143310547, "global_step": 387835, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1125168800354004, "global_step": 387836, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0487613677978516, "global_step": 387837, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1174750328063965, "global_step": 387838, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.063952922821045, "global_step": 387839, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.193744421005249, "global_step": 387840, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0082428455352783, "global_step": 387841, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1024374961853027, "global_step": 387842, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0257720947265625, "global_step": 387843, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0721583366394043, "global_step": 387844, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0656304359436035, "global_step": 387845, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0777926445007324, "global_step": 387846, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.116211414337158, "global_step": 387847, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.053075075149536, "global_step": 387848, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.072486400604248, "global_step": 387849, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0959041118621826, "global_step": 387850, "epoch": 750, "lr": 5e-05}
{"train_loss": 1.990020513534546, "global_step": 387851, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1848204135894775, "global_step": 387852, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.137011766433716, "global_step": 387853, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.088358163833618, "global_step": 387854, "epoch": 750, "lr": 5e-05}
{"train_loss": 1.9911712408065796, "global_step": 387855, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.028866767883301, "global_step": 387856, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0653114318847656, "global_step": 387857, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0937395095825195, "global_step": 387858, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0155739784240723, "global_step": 387859, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1842265129089355, "global_step": 387860, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.119239091873169, "global_step": 387861, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.023031711578369, "global_step": 387862, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0823159217834473, "global_step": 387863, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.101303815841675, "global_step": 387864, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0663483142852783, "global_step": 387865, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.120635986328125, "global_step": 387866, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1519012451171875, "global_step": 387867, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1036136150360107, "global_step": 387868, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.106872320175171, "global_step": 387869, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.093201160430908, "global_step": 387870, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1650302410125732, "global_step": 387871, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.073404312133789, "global_step": 387872, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.158385753631592, "global_step": 387873, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.037620782852173, "global_step": 387874, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0644400119781494, "global_step": 387875, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1720752716064453, "global_step": 387876, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1478099822998047, "global_step": 387877, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.17864727973938, "global_step": 387878, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.085883855819702, "global_step": 387879, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.17988920211792, "global_step": 387880, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0947165489196777, "global_step": 387881, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0537056922912598, "global_step": 387882, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0359206199645996, "global_step": 387883, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0147359371185303, "global_step": 387884, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0354065895080566, "global_step": 387885, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.201855182647705, "global_step": 387886, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1228525638580322, "global_step": 387887, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0583841800689697, "global_step": 387888, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0950980186462402, "global_step": 387889, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.02766489982605, "global_step": 387890, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1480212211608887, "global_step": 387891, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1907756328582764, "global_step": 387892, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1781158447265625, "global_step": 387893, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0768463611602783, "global_step": 387894, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0946478843688965, "global_step": 387895, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0850205421447754, "global_step": 387896, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0882506370544434, "global_step": 387897, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1404459476470947, "global_step": 387898, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0761165618896484, "global_step": 387899, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.087228775024414, "global_step": 387900, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.2058351039886475, "global_step": 387901, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.003934860229492, "global_step": 387902, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0521810054779053, "global_step": 387903, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.194606065750122, "global_step": 387904, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.14292049407959, "global_step": 387905, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.054631233215332, "global_step": 387906, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.018731117248535, "global_step": 387907, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1602630615234375, "global_step": 387908, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0716309547424316, "global_step": 387909, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0925586223602295, "global_step": 387910, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0784783363342285, "global_step": 387911, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1167986392974854, "global_step": 387912, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.143813133239746, "global_step": 387913, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1153371334075928, "global_step": 387914, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.160309314727783, "global_step": 387915, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.136519193649292, "global_step": 387916, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0471293926239014, "global_step": 387917, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0848031044006348, "global_step": 387918, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1678812503814697, "global_step": 387919, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.112816333770752, "global_step": 387920, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.070158004760742, "global_step": 387921, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0988926887512207, "global_step": 387922, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.038158416748047, "global_step": 387923, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.149078130722046, "global_step": 387924, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1227409839630127, "global_step": 387925, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.2223474979400635, "global_step": 387926, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1110098361968994, "global_step": 387927, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.091231107711792, "global_step": 387928, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.124183177947998, "global_step": 387929, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.133279800415039, "global_step": 387930, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1496808528900146, "global_step": 387931, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.146216869354248, "global_step": 387932, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.178046226501465, "global_step": 387933, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.110107421875, "global_step": 387934, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.032200336456299, "global_step": 387935, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1859922409057617, "global_step": 387936, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.101444721221924, "global_step": 387937, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.051656723022461, "global_step": 387938, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1839303970336914, "global_step": 387939, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0592217445373535, "global_step": 387940, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0064218044281006, "global_step": 387941, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1260788440704346, "global_step": 387942, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.055018901824951, "global_step": 387943, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.124474048614502, "global_step": 387944, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.02030873298645, "global_step": 387945, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.078817844390869, "global_step": 387946, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.111417770385742, "global_step": 387947, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1166532039642334, "global_step": 387948, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0935075283050537, "global_step": 387949, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.108473539352417, "global_step": 387950, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1650285720825195, "global_step": 387951, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0236356258392334, "global_step": 387952, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1992547512054443, "global_step": 387953, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1088929176330566, "global_step": 387954, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.116501569747925, "global_step": 387955, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1255946159362793, "global_step": 387956, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1144793033599854, "global_step": 387957, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0696568489074707, "global_step": 387958, "epoch": 750, "lr": 5e-05}
{"train_loss": 1.9958993196487427, "global_step": 387959, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0416455268859863, "global_step": 387960, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.052427291870117, "global_step": 387961, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0118978023529053, "global_step": 387962, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1056175231933594, "global_step": 387963, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0528056621551514, "global_step": 387964, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1601929664611816, "global_step": 387965, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1008617877960205, "global_step": 387966, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.176100254058838, "global_step": 387967, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1236884593963623, "global_step": 387968, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0296859741210938, "global_step": 387969, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0185635089874268, "global_step": 387970, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1643784046173096, "global_step": 387971, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0435361862182617, "global_step": 387972, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.067469596862793, "global_step": 387973, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1527984142303467, "global_step": 387974, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.111755609512329, "global_step": 387975, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1200695037841797, "global_step": 387976, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0593457221984863, "global_step": 387977, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1477878093719482, "global_step": 387978, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.000842332839966, "global_step": 387979, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1235320568084717, "global_step": 387980, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0926012992858887, "global_step": 387981, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.038456678390503, "global_step": 387982, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.123303174972534, "global_step": 387983, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0663444995880127, "global_step": 387984, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.15313982963562, "global_step": 387985, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.184197425842285, "global_step": 387986, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0965096950531006, "global_step": 387987, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.147770881652832, "global_step": 387988, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.156831979751587, "global_step": 387989, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.192227363586426, "global_step": 387990, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.096778154373169, "global_step": 387991, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0941903591156006, "global_step": 387992, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0391576290130615, "global_step": 387993, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.159738779067993, "global_step": 387994, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0458571910858154, "global_step": 387995, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.138111114501953, "global_step": 387996, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.2088122367858887, "global_step": 387997, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.031700849533081, "global_step": 387998, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1079437732696533, "global_step": 387999, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.103458881378174, "global_step": 388000, "epoch": 750, "lr": 5e-05}
{"train_loss": 1.9988229274749756, "global_step": 388001, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.161783456802368, "global_step": 388002, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.053544521331787, "global_step": 388003, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0961360931396484, "global_step": 388004, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1201040744781494, "global_step": 388005, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0863447189331055, "global_step": 388006, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.141749858856201, "global_step": 388007, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.203935146331787, "global_step": 388008, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0342862606048584, "global_step": 388009, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1034297943115234, "global_step": 388010, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1246466636657715, "global_step": 388011, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0727407932281494, "global_step": 388012, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1152408123016357, "global_step": 388013, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1447274684906006, "global_step": 388014, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1027069091796875, "global_step": 388015, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0343260765075684, "global_step": 388016, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.170107364654541, "global_step": 388017, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1287670135498047, "global_step": 388018, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.105733871459961, "global_step": 388019, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.045499324798584, "global_step": 388020, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.061509609222412, "global_step": 388021, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1342520713806152, "global_step": 388022, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1326780319213867, "global_step": 388023, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0382914543151855, "global_step": 388024, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1621415615081787, "global_step": 388025, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.048288106918335, "global_step": 388026, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0630156993865967, "global_step": 388027, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.02217173576355, "global_step": 388028, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.087679862976074, "global_step": 388029, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1172802448272705, "global_step": 388030, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1685550212860107, "global_step": 388031, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0819058418273926, "global_step": 388032, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.13360857963562, "global_step": 388033, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.194230794906616, "global_step": 388034, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.065822124481201, "global_step": 388035, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.031057596206665, "global_step": 388036, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1408438682556152, "global_step": 388037, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1834633350372314, "global_step": 388038, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.160402297973633, "global_step": 388039, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.021766185760498, "global_step": 388040, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0803136825561523, "global_step": 388041, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.111438035964966, "global_step": 388042, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.111193895339966, "global_step": 388043, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1292154788970947, "global_step": 388044, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0339114665985107, "global_step": 388045, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1047487258911133, "global_step": 388046, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.086059093475342, "global_step": 388047, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0984034538269043, "global_step": 388048, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1350269317626953, "global_step": 388049, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.126230239868164, "global_step": 388050, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0950794219970703, "global_step": 388051, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0215423107147217, "global_step": 388052, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.077597141265869, "global_step": 388053, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.102755308151245, "global_step": 388054, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0933916568756104, "global_step": 388055, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0910756587982178, "global_step": 388056, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.017483949661255, "global_step": 388057, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.192316770553589, "global_step": 388058, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.090754508972168, "global_step": 388059, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0876996517181396, "global_step": 388060, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1703438758850098, "global_step": 388061, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0742552280426025, "global_step": 388062, "epoch": 750, "lr": 5e-05}
{"train_loss": 1.9937994480133057, "global_step": 388063, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0344650745391846, "global_step": 388064, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0207197666168213, "global_step": 388065, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1142547130584717, "global_step": 388066, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0774760246276855, "global_step": 388067, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0869333744049072, "global_step": 388068, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.077718496322632, "global_step": 388069, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.078861713409424, "global_step": 388070, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1072142124176025, "global_step": 388071, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.099024534225464, "global_step": 388072, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1315712928771973, "global_step": 388073, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.105902671813965, "global_step": 388074, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.106295347213745, "global_step": 388075, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.10091233253479, "global_step": 388076, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.061122417449951, "global_step": 388077, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.152069091796875, "global_step": 388078, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0528604984283447, "global_step": 388079, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.106694459915161, "global_step": 388080, "epoch": 750, "lr": 5e-05}
{"train_loss": 1.9982504844665527, "global_step": 388081, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1225883960723877, "global_step": 388082, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1231749057769775, "global_step": 388083, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.110781192779541, "global_step": 388084, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1017258167266846, "global_step": 388085, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.039475679397583, "global_step": 388086, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.09492826461792, "global_step": 388087, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1338717937469482, "global_step": 388088, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.153794527053833, "global_step": 388089, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.11965274810791, "global_step": 388090, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0785109996795654, "global_step": 388091, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.090932607650757, "global_step": 388092, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0499253273010254, "global_step": 388093, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0706300735473633, "global_step": 388094, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.079582929611206, "global_step": 388095, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1611506938934326, "global_step": 388096, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0632922649383545, "global_step": 388097, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0630948543548584, "global_step": 388098, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.041571617126465, "global_step": 388099, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.110107421875, "global_step": 388100, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.134061813354492, "global_step": 388101, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.2143380641937256, "global_step": 388102, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0919456481933594, "global_step": 388103, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0683553218841553, "global_step": 388104, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.144329071044922, "global_step": 388105, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0504188537597656, "global_step": 388106, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1101744174957275, "global_step": 388107, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0960264205932617, "global_step": 388108, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0028319358825684, "global_step": 388109, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.2412052154541016, "global_step": 388110, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0325191020965576, "global_step": 388111, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0572850704193115, "global_step": 388112, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.022176742553711, "global_step": 388113, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.039665460586548, "global_step": 388114, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1141552925109863, "global_step": 388115, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.056600332260132, "global_step": 388116, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1575162410736084, "global_step": 388117, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0859196186065674, "global_step": 388118, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.013944625854492, "global_step": 388119, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1227543354034424, "global_step": 388120, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.198930025100708, "global_step": 388121, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.149667978286743, "global_step": 388122, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1693153381347656, "global_step": 388123, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.126410722732544, "global_step": 388124, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1176083087921143, "global_step": 388125, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1788487434387207, "global_step": 388126, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0503897666931152, "global_step": 388127, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.139911413192749, "global_step": 388128, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.137911558151245, "global_step": 388129, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1615893840789795, "global_step": 388130, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0539755821228027, "global_step": 388131, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0887699127197266, "global_step": 388132, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0700266361236572, "global_step": 388133, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.128812074661255, "global_step": 388134, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.089592218399048, "global_step": 388135, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0898470878601074, "global_step": 388136, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.051140069961548, "global_step": 388137, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0310897827148438, "global_step": 388138, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0933823585510254, "global_step": 388139, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1346564292907715, "global_step": 388140, "epoch": 750, "lr": 5e-05}
{"train_loss": 1.9697492122650146, "global_step": 388141, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.098865270614624, "global_step": 388142, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.113994598388672, "global_step": 388143, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0549123287200928, "global_step": 388144, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.094233751296997, "global_step": 388145, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1905906200408936, "global_step": 388146, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.111828565597534, "global_step": 388147, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0648906230926514, "global_step": 388148, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0349929332733154, "global_step": 388149, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1021525859832764, "global_step": 388150, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.130009174346924, "global_step": 388151, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.046926259994507, "global_step": 388152, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1085572242736816, "global_step": 388153, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0734362602233887, "global_step": 388154, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1315858364105225, "global_step": 388155, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.088745355606079, "global_step": 388156, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1016640663146973, "global_step": 388157, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1759896278381348, "global_step": 388158, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.104118824005127, "global_step": 388159, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1009724140167236, "global_step": 388160, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1376075744628906, "global_step": 388161, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.051863431930542, "global_step": 388162, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0487380027770996, "global_step": 388163, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.036785840988159, "global_step": 388164, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0574951171875, "global_step": 388165, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0139074325561523, "global_step": 388166, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0887253284454346, "global_step": 388167, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.242868185043335, "global_step": 388168, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1156694889068604, "global_step": 388169, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.029428243637085, "global_step": 388170, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0890331268310547, "global_step": 388171, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.087372064590454, "global_step": 388172, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.088770627975464, "global_step": 388173, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1076927185058594, "global_step": 388174, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.04168963432312, "global_step": 388175, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.017241954803467, "global_step": 388176, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0710017681121826, "global_step": 388177, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.10111403465271, "global_step": 388178, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0695412158966064, "global_step": 388179, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0717012882232666, "global_step": 388180, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.129495859146118, "global_step": 388181, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1244630813598633, "global_step": 388182, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0450782775878906, "global_step": 388183, "epoch": 750, "lr": 5e-05}
{"train_loss": 1.9830635786056519, "global_step": 388184, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.094998359680176, "global_step": 388185, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.146512746810913, "global_step": 388186, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.105895519256592, "global_step": 388187, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0654313564300537, "global_step": 388188, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0766711235046387, "global_step": 388189, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.115624189376831, "global_step": 388190, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.089775562286377, "global_step": 388191, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1115012168884277, "global_step": 388192, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1258227825164795, "global_step": 388193, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.222193479537964, "global_step": 388194, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0428340435028076, "global_step": 388195, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0368480682373047, "global_step": 388196, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1413002014160156, "global_step": 388197, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.134692430496216, "global_step": 388198, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.110208511352539, "global_step": 388199, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.088447093963623, "global_step": 388200, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0461254119873047, "global_step": 388201, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0708208084106445, "global_step": 388202, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.077777624130249, "global_step": 388203, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.053251028060913, "global_step": 388204, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0765185356140137, "global_step": 388205, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1697003841400146, "global_step": 388206, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.179079294204712, "global_step": 388207, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.086421012878418, "global_step": 388208, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.090496301651001, "global_step": 388209, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1888184547424316, "global_step": 388210, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.180525064468384, "global_step": 388211, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.120959997177124, "global_step": 388212, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.094665050506592, "global_step": 388213, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0039496421813965, "global_step": 388214, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1248574256896973, "global_step": 388215, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1646676063537598, "global_step": 388216, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.192499876022339, "global_step": 388217, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0946128368377686, "global_step": 388218, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1323177814483643, "global_step": 388219, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1249351501464844, "global_step": 388220, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.131493330001831, "global_step": 388221, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0597074031829834, "global_step": 388222, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.122490167617798, "global_step": 388223, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.085925340652466, "global_step": 388224, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0117578506469727, "global_step": 388225, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.12554931640625, "global_step": 388226, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.133934497833252, "global_step": 388227, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0921950340270996, "global_step": 388228, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1288554668426514, "global_step": 388229, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0670549869537354, "global_step": 388230, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0325565338134766, "global_step": 388231, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.165374279022217, "global_step": 388232, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.18056321144104, "global_step": 388233, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.099637508392334, "global_step": 388234, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1103248596191406, "global_step": 388235, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.100487470626831, "global_step": 388236, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1560492515563965, "global_step": 388237, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.078700304031372, "global_step": 388238, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1406331062316895, "global_step": 388239, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.129323720932007, "global_step": 388240, "epoch": 750, "lr": 5e-05}
{"train_loss": 1.9835808277130127, "global_step": 388241, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0741448402404785, "global_step": 388242, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1262035369873047, "global_step": 388243, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.045281410217285, "global_step": 388244, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1647276878356934, "global_step": 388245, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.140115976333618, "global_step": 388246, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1054046154022217, "global_step": 388247, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0668206214904785, "global_step": 388248, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1463847160339355, "global_step": 388249, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1151211261749268, "global_step": 388250, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0430479049682617, "global_step": 388251, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.107250928878784, "global_step": 388252, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1358563899993896, "global_step": 388253, "epoch": 750, "lr": 5e-05}
{"train_loss": 1.9920246601104736, "global_step": 388254, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.102447032928467, "global_step": 388255, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0530617237091064, "global_step": 388256, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1327433586120605, "global_step": 388257, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1131579875946045, "global_step": 388258, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.222109317779541, "global_step": 388259, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.121088743209839, "global_step": 388260, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0670299530029297, "global_step": 388261, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.093052625656128, "global_step": 388262, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.146272897720337, "global_step": 388263, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1593847274780273, "global_step": 388264, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1359598636627197, "global_step": 388265, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1389341354370117, "global_step": 388266, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0490431785583496, "global_step": 388267, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.097235918045044, "global_step": 388268, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0843770503997803, "global_step": 388269, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.180971384048462, "global_step": 388270, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.168750524520874, "global_step": 388271, "epoch": 750, "lr": 5e-05}
{"train_loss": 1.9988988637924194, "global_step": 388272, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0916576385498047, "global_step": 388273, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1584126949310303, "global_step": 388274, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0966379642486572, "global_step": 388275, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.138127565383911, "global_step": 388276, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.049659490585327, "global_step": 388277, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1017637252807617, "global_step": 388278, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0330896377563477, "global_step": 388279, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.2119765281677246, "global_step": 388280, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0255813598632812, "global_step": 388281, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0314276218414307, "global_step": 388282, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1241953372955322, "global_step": 388283, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.152757167816162, "global_step": 388284, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0997962951660156, "global_step": 388285, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.126368284225464, "global_step": 388286, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.093520402908325, "global_step": 388287, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.122593402862549, "global_step": 388288, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.005286455154419, "global_step": 388289, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.110301971435547, "global_step": 388290, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0312387943267822, "global_step": 388291, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0780532360076904, "global_step": 388292, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.07297420501709, "global_step": 388293, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.198850631713867, "global_step": 388294, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.140031099319458, "global_step": 388295, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.149996757507324, "global_step": 388296, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.112332582473755, "global_step": 388297, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.076268196105957, "global_step": 388298, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.072319984436035, "global_step": 388299, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.101677417755127, "global_step": 388300, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0251336097717285, "global_step": 388301, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.183356285095215, "global_step": 388302, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1544854640960693, "global_step": 388303, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.200314998626709, "global_step": 388304, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1332848072052, "global_step": 388305, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0529303550720215, "global_step": 388306, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.135730028152466, "global_step": 388307, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.087693452835083, "global_step": 388308, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.075047731399536, "global_step": 388309, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.116989850997925, "global_step": 388310, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0522141456604004, "global_step": 388311, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0871691703796387, "global_step": 388312, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0252137184143066, "global_step": 388313, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0297281742095947, "global_step": 388314, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.132009267807007, "global_step": 388315, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.015578031539917, "global_step": 388316, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.092690944671631, "global_step": 388317, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0974671840667725, "global_step": 388318, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.129204273223877, "global_step": 388319, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0627849102020264, "global_step": 388320, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1111764907836914, "global_step": 388321, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1517348289489746, "global_step": 388322, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.110907793045044, "global_step": 388323, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0571322441101074, "global_step": 388324, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1910581588745117, "global_step": 388325, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1123733520507812, "global_step": 388326, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0747833251953125, "global_step": 388327, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0738816261291504, "global_step": 388328, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0947723388671875, "global_step": 388329, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.132662296295166, "global_step": 388330, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.109879732131958, "global_step": 388331, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.137078285217285, "global_step": 388332, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0779995918273926, "global_step": 388333, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.070924758911133, "global_step": 388334, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.098566770553589, "global_step": 388335, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1330440044403076, "global_step": 388336, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1649107933044434, "global_step": 388337, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0816071033477783, "global_step": 388338, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0736148357391357, "global_step": 388339, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1167683601379395, "global_step": 388340, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.102842092514038, "global_step": 388341, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1106648445129395, "global_step": 388342, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0838849544525146, "global_step": 388343, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.099031686782837, "global_step": 388344, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.179582357406616, "global_step": 388345, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.133162498474121, "global_step": 388346, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.108806610107422, "global_step": 388347, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0818960666656494, "global_step": 388348, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.143726348876953, "global_step": 388349, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1139957904815674, "global_step": 388350, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0679407119750977, "global_step": 388351, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.174502372741699, "global_step": 388352, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1011507511138916, "global_step": 388353, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1116340160369873, "global_step": 388354, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0464630126953125, "global_step": 388355, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0766308307647705, "global_step": 388356, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.094957113265991, "global_step": 388357, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.090975761413574, "global_step": 388358, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0360805988311768, "global_step": 388359, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.168551206588745, "global_step": 388360, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0622904300689697, "global_step": 388361, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.201354503631592, "global_step": 388362, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.13020920753479, "global_step": 388363, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0875189304351807, "global_step": 388364, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0797696113586426, "global_step": 388365, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0635416507720947, "global_step": 388366, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0963551998138428, "global_step": 388367, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.065373659133911, "global_step": 388368, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1409785747528076, "global_step": 388369, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1550536155700684, "global_step": 388370, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1623172760009766, "global_step": 388371, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1287755966186523, "global_step": 388372, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1026999950408936, "global_step": 388373, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1581132411956787, "global_step": 388374, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.083221673965454, "global_step": 388375, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.162935256958008, "global_step": 388376, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.2163453102111816, "global_step": 388377, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1363258361816406, "global_step": 388378, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.168968915939331, "global_step": 388379, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1282243728637695, "global_step": 388380, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.08840012550354, "global_step": 388381, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.098146677017212, "global_step": 388382, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0514774322509766, "global_step": 388383, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0570766925811768, "global_step": 388384, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.033507823944092, "global_step": 388385, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.058210849761963, "global_step": 388386, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.115389347076416, "global_step": 388387, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0489580631256104, "global_step": 388388, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.094843864440918, "global_step": 388389, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0962936878204346, "global_step": 388390, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1250498294830322, "global_step": 388391, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.209960699081421, "global_step": 388392, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1360929012298584, "global_step": 388393, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.163564682006836, "global_step": 388394, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1018893718719482, "global_step": 388395, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.088569164276123, "global_step": 388396, "epoch": 750, "lr": 5e-05}
{"train_loss": 1.9963818788528442, "global_step": 388397, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.049675941467285, "global_step": 388398, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0790178775787354, "global_step": 388399, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.038841962814331, "global_step": 388400, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1424381732940674, "global_step": 388401, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.07196044921875, "global_step": 388402, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0888993740081787, "global_step": 388403, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0991666316986084, "global_step": 388404, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1233744621276855, "global_step": 388405, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.072758197784424, "global_step": 388406, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.20796275138855, "global_step": 388407, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.072833776473999, "global_step": 388408, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0933427810668945, "global_step": 388409, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.114677906036377, "global_step": 388410, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.04399037361145, "global_step": 388411, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0448524951934814, "global_step": 388412, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0009243488311768, "global_step": 388413, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.039675235748291, "global_step": 388414, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.121048927307129, "global_step": 388415, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1164307594299316, "global_step": 388416, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.064563035964966, "global_step": 388417, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1264235973358154, "global_step": 388418, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.121574640274048, "global_step": 388419, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0557360649108887, "global_step": 388420, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1580793857574463, "global_step": 388421, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.23769211769104, "global_step": 388422, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.126542329788208, "global_step": 388423, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0818097591400146, "global_step": 388424, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0841140747070312, "global_step": 388425, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0269615650177, "global_step": 388426, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.100979804992676, "global_step": 388427, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0749852657318115, "global_step": 388428, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.023003101348877, "global_step": 388429, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.116030693054199, "global_step": 388430, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0963058471679688, "global_step": 388431, "epoch": 750, "lr": 5e-05}
{"train_loss": 1.99539053440094, "global_step": 388432, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1192595958709717, "global_step": 388433, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0917351245880127, "global_step": 388434, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1880290508270264, "global_step": 388435, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1446712017059326, "global_step": 388436, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1401586532592773, "global_step": 388437, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1589770317077637, "global_step": 388438, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0673646926879883, "global_step": 388439, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1104283332824707, "global_step": 388440, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.069774866104126, "global_step": 388441, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.058161973953247, "global_step": 388442, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0453453063964844, "global_step": 388443, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1601154804229736, "global_step": 388444, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.113913059234619, "global_step": 388445, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1963882446289062, "global_step": 388446, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1066551208496094, "global_step": 388447, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.020413875579834, "global_step": 388448, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1260879039764404, "global_step": 388449, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0854618549346924, "global_step": 388450, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0353729724884033, "global_step": 388451, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.090660810470581, "global_step": 388452, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0427212715148926, "global_step": 388453, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.077965021133423, "global_step": 388454, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.114708423614502, "global_step": 388455, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1513569355010986, "global_step": 388456, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1390585899353027, "global_step": 388457, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0953617095947266, "global_step": 388458, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.022759199142456, "global_step": 388459, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.18735933303833, "global_step": 388460, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1077635288238525, "global_step": 388461, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.074957847595215, "global_step": 388462, "epoch": 750, "lr": 5e-05}
{"train_loss": 1.9995479583740234, "global_step": 388463, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1314291954040527, "global_step": 388464, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.089207410812378, "global_step": 388465, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.051178455352783, "global_step": 388466, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.204465627670288, "global_step": 388467, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.065033197402954, "global_step": 388468, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.112278461456299, "global_step": 388469, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.109346389770508, "global_step": 388470, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.049799919128418, "global_step": 388471, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0731332302093506, "global_step": 388472, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.144324779510498, "global_step": 388473, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.129232883453369, "global_step": 388474, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.177257776260376, "global_step": 388475, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.047741174697876, "global_step": 388476, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.06723952293396, "global_step": 388477, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.151419162750244, "global_step": 388478, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1409714221954346, "global_step": 388479, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.181960344314575, "global_step": 388480, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.095127582550049, "global_step": 388481, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.158447742462158, "global_step": 388482, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.017021417617798, "global_step": 388483, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1596648693084717, "global_step": 388484, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.097623586654663, "global_step": 388485, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0727498531341553, "global_step": 388486, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0114340782165527, "global_step": 388487, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0551774501800537, "global_step": 388488, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.090074062347412, "global_step": 388489, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0542330741882324, "global_step": 388490, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.2136855125427246, "global_step": 388491, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.124323844909668, "global_step": 388492, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.2426598072052, "global_step": 388493, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.05867600440979, "global_step": 388494, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.104512929916382, "global_step": 388495, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.128408908843994, "global_step": 388496, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0190629959106445, "global_step": 388497, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.161738395690918, "global_step": 388498, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0313503742218018, "global_step": 388499, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.073479175567627, "global_step": 388500, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.238595724105835, "global_step": 388501, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0925002098083496, "global_step": 388502, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0523486137390137, "global_step": 388503, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.097522497177124, "global_step": 388504, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.028019666671753, "global_step": 388505, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.124368667602539, "global_step": 388506, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0853192806243896, "global_step": 388507, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.128485679626465, "global_step": 388508, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.121185541152954, "global_step": 388509, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1710119247436523, "global_step": 388510, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.108506679534912, "global_step": 388511, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.064441442489624, "global_step": 388512, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.13858699798584, "global_step": 388513, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.17128849029541, "global_step": 388514, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.091759443283081, "global_step": 388515, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.099921941757202, "global_step": 388516, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.073118209838867, "global_step": 388517, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.068225860595703, "global_step": 388518, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1298301219940186, "global_step": 388519, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0117881298065186, "global_step": 388520, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0540871620178223, "global_step": 388521, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.104539394378662, "global_step": 388522, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.19925594329834, "global_step": 388523, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0852108001708984, "global_step": 388524, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.063901424407959, "global_step": 388525, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.090458869934082, "global_step": 388526, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.126105785369873, "global_step": 388527, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1284308433532715, "global_step": 388528, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.124454975128174, "global_step": 388529, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.141953945159912, "global_step": 388530, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.039186716079712, "global_step": 388531, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.118870973587036, "global_step": 388532, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0716733932495117, "global_step": 388533, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.087233066558838, "global_step": 388534, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1312026977539062, "global_step": 388535, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0695760250091553, "global_step": 388536, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.119391918182373, "global_step": 388537, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.10589861869812, "global_step": 388538, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0950968265533447, "global_step": 388539, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1859793663024902, "global_step": 388540, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0880870819091797, "global_step": 388541, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1174614429473877, "global_step": 388542, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.089905261993408, "global_step": 388543, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0899789333343506, "global_step": 388544, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1471309661865234, "global_step": 388545, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.103361129760742, "global_step": 388546, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0992884635925293, "global_step": 388547, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1307425498962402, "global_step": 388548, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0531270503997803, "global_step": 388549, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1071319580078125, "global_step": 388550, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0658457279205322, "global_step": 388551, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.064911127090454, "global_step": 388552, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.150217294692993, "global_step": 388553, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1823842525482178, "global_step": 388554, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.030479669570923, "global_step": 388555, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.136176109313965, "global_step": 388556, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0612235069274902, "global_step": 388557, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.241410493850708, "global_step": 388558, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.134204387664795, "global_step": 388559, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.071192979812622, "global_step": 388560, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0909228324890137, "global_step": 388561, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0102648735046387, "global_step": 388562, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.071349620819092, "global_step": 388563, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.106842041015625, "global_step": 388564, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0620391368865967, "global_step": 388565, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.132310390472412, "global_step": 388566, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1109979152679443, "global_step": 388567, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0945706367492676, "global_step": 388568, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1214041709899902, "global_step": 388569, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.084787607192993, "global_step": 388570, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1041290760040283, "global_step": 388571, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.130559206008911, "global_step": 388572, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1061601638793945, "global_step": 388573, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.045252799987793, "global_step": 388574, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0780675411224365, "global_step": 388575, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1782643795013428, "global_step": 388576, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.101938247680664, "global_step": 388577, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.173999547958374, "global_step": 388578, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0727698802948, "global_step": 388579, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1807525157928467, "global_step": 388580, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0939528942108154, "global_step": 388581, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0303897857666016, "global_step": 388582, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0656228065490723, "global_step": 388583, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.054624080657959, "global_step": 388584, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1351070404052734, "global_step": 388585, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0933070182800293, "global_step": 388586, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0974209308624268, "global_step": 388587, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1799654960632324, "global_step": 388588, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.12408447265625, "global_step": 388589, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0986592769622803, "global_step": 388590, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1356637477874756, "global_step": 388591, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0738701820373535, "global_step": 388592, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0672240257263184, "global_step": 388593, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.117121934890747, "global_step": 388594, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.093353509902954, "global_step": 388595, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.135148048400879, "global_step": 388596, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.144951105117798, "global_step": 388597, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.116731882095337, "global_step": 388598, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.188573122024536, "global_step": 388599, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1583995819091797, "global_step": 388600, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1360013484954834, "global_step": 388601, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.255126714706421, "global_step": 388602, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1091606616973877, "global_step": 388603, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.076683759689331, "global_step": 388604, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.156240224838257, "global_step": 388605, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1084020137786865, "global_step": 388606, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.066901922225952, "global_step": 388607, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.107670307159424, "global_step": 388608, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.090456485748291, "global_step": 388609, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0775606632232666, "global_step": 388610, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.118473529815674, "global_step": 388611, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.180997848510742, "global_step": 388612, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1033778190612793, "global_step": 388613, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1252663135528564, "global_step": 388614, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0931997299194336, "global_step": 388615, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1219499111175537, "global_step": 388616, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.121406078338623, "global_step": 388617, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.10329008102417, "global_step": 388618, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.180877923965454, "global_step": 388619, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.083575963973999, "global_step": 388620, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1583566665649414, "global_step": 388621, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0491228103637695, "global_step": 388622, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0154225826263428, "global_step": 388623, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.046790599822998, "global_step": 388624, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.024616241455078, "global_step": 388625, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.116713047027588, "global_step": 388626, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.013827323913574, "global_step": 388627, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1104869842529297, "global_step": 388628, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0901947021484375, "global_step": 388629, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0623302459716797, "global_step": 388630, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1230297088623047, "global_step": 388631, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0645384788513184, "global_step": 388632, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1491613388061523, "global_step": 388633, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.118504524230957, "global_step": 388634, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.037731409072876, "global_step": 388635, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.036489963531494, "global_step": 388636, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0767266750335693, "global_step": 388637, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0462217330932617, "global_step": 388638, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1054649353027344, "global_step": 388639, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1067681312561035, "global_step": 388640, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1332039833068848, "global_step": 388641, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1954002380371094, "global_step": 388642, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.078460454940796, "global_step": 388643, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1429696083068848, "global_step": 388644, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.104464530944824, "global_step": 388645, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1055920124053955, "global_step": 388646, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0340778827667236, "global_step": 388647, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.012904167175293, "global_step": 388648, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1713852882385254, "global_step": 388649, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1727700233459473, "global_step": 388650, "epoch": 750, "lr": 5e-05}
{"train_loss": 1.9927600622177124, "global_step": 388651, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.193988800048828, "global_step": 388652, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1050219535827637, "global_step": 388653, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1399848461151123, "global_step": 388654, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1541588306427, "global_step": 388655, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.153332233428955, "global_step": 388656, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.2000882625579834, "global_step": 388657, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.078005313873291, "global_step": 388658, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.110602617263794, "global_step": 388659, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.122000217437744, "global_step": 388660, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0601351261138916, "global_step": 388661, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0495553016662598, "global_step": 388662, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0666892528533936, "global_step": 388663, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1594226360321045, "global_step": 388664, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.044665813446045, "global_step": 388665, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1528050899505615, "global_step": 388666, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0494890213012695, "global_step": 388667, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0867135524749756, "global_step": 388668, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0342986583709717, "global_step": 388669, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.149003267288208, "global_step": 388670, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1518704891204834, "global_step": 388671, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1534409523010254, "global_step": 388672, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0661916732788086, "global_step": 388673, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.106274366378784, "global_step": 388674, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1838014125823975, "global_step": 388675, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.087456464767456, "global_step": 388676, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.084974527359009, "global_step": 388677, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.177624464035034, "global_step": 388678, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1234986782073975, "global_step": 388679, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.082488536834717, "global_step": 388680, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.068553924560547, "global_step": 388681, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0264434814453125, "global_step": 388682, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1187009811401367, "global_step": 388683, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.2176904678344727, "global_step": 388684, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0146243572235107, "global_step": 388685, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1773617267608643, "global_step": 388686, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.123218536376953, "global_step": 388687, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1850833892822266, "global_step": 388688, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0669448375701904, "global_step": 388689, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1053643226623535, "global_step": 388690, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.125197410583496, "global_step": 388691, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.0675909519195557, "global_step": 388692, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.081860303878784, "global_step": 388693, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1472489833831787, "global_step": 388694, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1531026363372803, "global_step": 388695, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.169903039932251, "global_step": 388696, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.142000436782837, "global_step": 388697, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.074928045272827, "global_step": 388698, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.11725115776062, "global_step": 388699, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.1249873638153076, "global_step": 388700, "epoch": 750, "lr": 5e-05}
{"train_loss": 2.101219654083252, "global_step": 388701, "epoch": 750, "lr": 5e-05, "KITCHEN_SCENE6_put_the_yellow_and_white_mug_in_the_microwave_and_close_it/mean_success_rate": 0.6333333333333333, "LIVING_ROOM_SCENE2_put_both_the_alphabet_soup_and_the_tomato_sauce_in_the_basket/mean_success_rate": 0.0, "STUDY_SCENE1_pick_up_the_book_and_place_it_in_the_back_compartment_of_the_caddy/mean_success_rate": 0.5666666666666667, "KITCHEN_SCENE8_put_both_moka_pots_on_the_stove/mean_success_rate": 0.26666666666666666, "LIVING_ROOM_SCENE5_put_the_white_mug_on_the_left_plate_and_put_the_yellow_and_white_mug_on_the_right_plate/mean_success_rate": 0.5333333333333333, "LIVING_ROOM_SCENE6_put_the_white_mug_on_the_plate_and_put_the_chocolate_pudding_to_the_right_of_the_plate/mean_success_rate": 0.36666666666666664, "KITCHEN_SCENE4_put_the_black_bowl_in_the_bottom_drawer_of_the_cabinet_and_close_it/mean_success_rate": 0.9333333333333333, "LIVING_ROOM_SCENE2_put_both_the_cream_cheese_box_and_the_butter_in_the_basket/mean_success_rate": 0.5, "LIVING_ROOM_SCENE1_put_both_the_alphabet_soup_and_the_cream_cheese_box_in_the_basket/mean_success_rate": 0.0, "KITCHEN_SCENE3_turn_on_the_stove_and_put_the_moka_pot_on_it/mean_success_rate": 0.9666666666666667, "mean_success_rate": 0.4766666666666667, "val_loss": 5.636320114135742, "test_reconst_mse": 0.07375873625278473}
{"train_loss": 2.1056289672851562, "global_step": 388702, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0870935916900635, "global_step": 388703, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.04201340675354, "global_step": 388704, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1271719932556152, "global_step": 388705, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1203091144561768, "global_step": 388706, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0377349853515625, "global_step": 388707, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1393086910247803, "global_step": 388708, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0429046154022217, "global_step": 388709, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.128178358078003, "global_step": 388710, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0998992919921875, "global_step": 388711, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1307525634765625, "global_step": 388712, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1037113666534424, "global_step": 388713, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9929701089859009, "global_step": 388714, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.099066972732544, "global_step": 388715, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.178212881088257, "global_step": 388716, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0765023231506348, "global_step": 388717, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0888078212738037, "global_step": 388718, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1421141624450684, "global_step": 388719, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0336382389068604, "global_step": 388720, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.105726480484009, "global_step": 388721, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0974438190460205, "global_step": 388722, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.125291585922241, "global_step": 388723, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1401734352111816, "global_step": 388724, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9908756017684937, "global_step": 388725, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.114985704421997, "global_step": 388726, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1176717281341553, "global_step": 388727, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1088082790374756, "global_step": 388728, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.028409004211426, "global_step": 388729, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.100252628326416, "global_step": 388730, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0958571434020996, "global_step": 388731, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1419928073883057, "global_step": 388732, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0783894062042236, "global_step": 388733, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.149125814437866, "global_step": 388734, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.039113759994507, "global_step": 388735, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0438950061798096, "global_step": 388736, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1817572116851807, "global_step": 388737, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.073754072189331, "global_step": 388738, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0457959175109863, "global_step": 388739, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0445590019226074, "global_step": 388740, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1238605976104736, "global_step": 388741, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.962926983833313, "global_step": 388742, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.10282826423645, "global_step": 388743, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.076730966567993, "global_step": 388744, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0633585453033447, "global_step": 388745, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1735119819641113, "global_step": 388746, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9714385271072388, "global_step": 388747, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.013101100921631, "global_step": 388748, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1784820556640625, "global_step": 388749, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.146930456161499, "global_step": 388750, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1192126274108887, "global_step": 388751, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1914613246917725, "global_step": 388752, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1327097415924072, "global_step": 388753, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0821011066436768, "global_step": 388754, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0265185832977295, "global_step": 388755, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1867854595184326, "global_step": 388756, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0937042236328125, "global_step": 388757, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.131221055984497, "global_step": 388758, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1075212955474854, "global_step": 388759, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1656556129455566, "global_step": 388760, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.044771432876587, "global_step": 388761, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0672152042388916, "global_step": 388762, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1585917472839355, "global_step": 388763, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.119203805923462, "global_step": 388764, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1633102893829346, "global_step": 388765, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.029092311859131, "global_step": 388766, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.143695116043091, "global_step": 388767, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0396032333374023, "global_step": 388768, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1429715156555176, "global_step": 388769, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.074063301086426, "global_step": 388770, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.070960283279419, "global_step": 388771, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0088558197021484, "global_step": 388772, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0114078521728516, "global_step": 388773, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.056119918823242, "global_step": 388774, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1138339042663574, "global_step": 388775, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1093087196350098, "global_step": 388776, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0964250564575195, "global_step": 388777, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.041823387145996, "global_step": 388778, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1143798828125, "global_step": 388779, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.161696672439575, "global_step": 388780, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1490731239318848, "global_step": 388781, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0551977157592773, "global_step": 388782, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1335909366607666, "global_step": 388783, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.139568328857422, "global_step": 388784, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.129279136657715, "global_step": 388785, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0988616943359375, "global_step": 388786, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0616087913513184, "global_step": 388787, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.087681293487549, "global_step": 388788, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.065272331237793, "global_step": 388789, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.089369535446167, "global_step": 388790, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.03440523147583, "global_step": 388791, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1130571365356445, "global_step": 388792, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.119150400161743, "global_step": 388793, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1023030281066895, "global_step": 388794, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.014679431915283, "global_step": 388795, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1076531410217285, "global_step": 388796, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.135828733444214, "global_step": 388797, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.048879861831665, "global_step": 388798, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1074142456054688, "global_step": 388799, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.102592945098877, "global_step": 388800, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1377062797546387, "global_step": 388801, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0795373916625977, "global_step": 388802, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1597912311553955, "global_step": 388803, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0792579650878906, "global_step": 388804, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0548744201660156, "global_step": 388805, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0988597869873047, "global_step": 388806, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.135141134262085, "global_step": 388807, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.2055282592773438, "global_step": 388808, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.118394136428833, "global_step": 388809, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.976883888244629, "global_step": 388810, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.066977024078369, "global_step": 388811, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1225039958953857, "global_step": 388812, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.153571844100952, "global_step": 388813, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.112095594406128, "global_step": 388814, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.123473882675171, "global_step": 388815, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.149869441986084, "global_step": 388816, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1380927562713623, "global_step": 388817, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.009725332260132, "global_step": 388818, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0558316707611084, "global_step": 388819, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0856833457946777, "global_step": 388820, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0531086921691895, "global_step": 388821, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0969600677490234, "global_step": 388822, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0061299800872803, "global_step": 388823, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0740842819213867, "global_step": 388824, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1136293411254883, "global_step": 388825, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.109368324279785, "global_step": 388826, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.013052225112915, "global_step": 388827, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.113325357437134, "global_step": 388828, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.956282138824463, "global_step": 388829, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.086221218109131, "global_step": 388830, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.073580026626587, "global_step": 388831, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1700284481048584, "global_step": 388832, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0705463886260986, "global_step": 388833, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0589547157287598, "global_step": 388834, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0395619869232178, "global_step": 388835, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.067096471786499, "global_step": 388836, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0373494625091553, "global_step": 388837, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0524487495422363, "global_step": 388838, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1604464054107666, "global_step": 388839, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1317617893218994, "global_step": 388840, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1085104942321777, "global_step": 388841, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.099102020263672, "global_step": 388842, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1133055686950684, "global_step": 388843, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.089151620864868, "global_step": 388844, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0561723709106445, "global_step": 388845, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.094015121459961, "global_step": 388846, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.094616174697876, "global_step": 388847, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1459085941314697, "global_step": 388848, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9790279865264893, "global_step": 388849, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1717798709869385, "global_step": 388850, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0991568565368652, "global_step": 388851, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.130108118057251, "global_step": 388852, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0580976009368896, "global_step": 388853, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1199748516082764, "global_step": 388854, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0837721824645996, "global_step": 388855, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.107222557067871, "global_step": 388856, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.040757894515991, "global_step": 388857, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.096036911010742, "global_step": 388858, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.091064453125, "global_step": 388859, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0860254764556885, "global_step": 388860, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1634304523468018, "global_step": 388861, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.128063678741455, "global_step": 388862, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1839137077331543, "global_step": 388863, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.157463550567627, "global_step": 388864, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1753504276275635, "global_step": 388865, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1437015533447266, "global_step": 388866, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.02821946144104, "global_step": 388867, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1119351387023926, "global_step": 388868, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.139559268951416, "global_step": 388869, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.012174367904663, "global_step": 388870, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.049135446548462, "global_step": 388871, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1015846729278564, "global_step": 388872, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9573171138763428, "global_step": 388873, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0793933868408203, "global_step": 388874, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0868167877197266, "global_step": 388875, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0976693630218506, "global_step": 388876, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1336495876312256, "global_step": 388877, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.127495288848877, "global_step": 388878, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.111990451812744, "global_step": 388879, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1062607765197754, "global_step": 388880, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.104135274887085, "global_step": 388881, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.139301061630249, "global_step": 388882, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.11962628364563, "global_step": 388883, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.133730888366699, "global_step": 388884, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.116525411605835, "global_step": 388885, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0008461475372314, "global_step": 388886, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0674805641174316, "global_step": 388887, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1424617767333984, "global_step": 388888, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1235830783843994, "global_step": 388889, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.029716968536377, "global_step": 388890, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0376663208007812, "global_step": 388891, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1634888648986816, "global_step": 388892, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0787854194641113, "global_step": 388893, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0844948291778564, "global_step": 388894, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.2239491939544678, "global_step": 388895, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.055837631225586, "global_step": 388896, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.067415475845337, "global_step": 388897, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.013859510421753, "global_step": 388898, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1281750202178955, "global_step": 388899, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.143009901046753, "global_step": 388900, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1250739097595215, "global_step": 388901, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.068725109100342, "global_step": 388902, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1505820751190186, "global_step": 388903, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1332931518554688, "global_step": 388904, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.217916250228882, "global_step": 388905, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9939006567001343, "global_step": 388906, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.041921615600586, "global_step": 388907, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.116461992263794, "global_step": 388908, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1300370693206787, "global_step": 388909, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.048797845840454, "global_step": 388910, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1027543544769287, "global_step": 388911, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0348329544067383, "global_step": 388912, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.134343385696411, "global_step": 388913, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.084444999694824, "global_step": 388914, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.069950819015503, "global_step": 388915, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.057183265686035, "global_step": 388916, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1116185188293457, "global_step": 388917, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1118133068084717, "global_step": 388918, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.099198579788208, "global_step": 388919, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0589101314544678, "global_step": 388920, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.079763174057007, "global_step": 388921, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.129004955291748, "global_step": 388922, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1230461597442627, "global_step": 388923, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.060432195663452, "global_step": 388924, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1358301639556885, "global_step": 388925, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0784175395965576, "global_step": 388926, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.140615224838257, "global_step": 388927, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1231536865234375, "global_step": 388928, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1284735202789307, "global_step": 388929, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.070007562637329, "global_step": 388930, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0283029079437256, "global_step": 388931, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.116743564605713, "global_step": 388932, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.163144826889038, "global_step": 388933, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1429543495178223, "global_step": 388934, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0609874725341797, "global_step": 388935, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.994539499282837, "global_step": 388936, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1030123233795166, "global_step": 388937, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0100409984588623, "global_step": 388938, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.041991949081421, "global_step": 388939, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.037700653076172, "global_step": 388940, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.11775541305542, "global_step": 388941, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0608205795288086, "global_step": 388942, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0418615341186523, "global_step": 388943, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0964136123657227, "global_step": 388944, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0385754108428955, "global_step": 388945, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0661308765411377, "global_step": 388946, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.076418161392212, "global_step": 388947, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.102466344833374, "global_step": 388948, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0571815967559814, "global_step": 388949, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0981647968292236, "global_step": 388950, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1392862796783447, "global_step": 388951, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0478897094726562, "global_step": 388952, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.05946946144104, "global_step": 388953, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.103846788406372, "global_step": 388954, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1751859188079834, "global_step": 388955, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.197360038757324, "global_step": 388956, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.141733169555664, "global_step": 388957, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0637052059173584, "global_step": 388958, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0877320766448975, "global_step": 388959, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0277130603790283, "global_step": 388960, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.040806293487549, "global_step": 388961, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.049795627593994, "global_step": 388962, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.140408515930176, "global_step": 388963, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0674374103546143, "global_step": 388964, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9904444217681885, "global_step": 388965, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.10227370262146, "global_step": 388966, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.080305576324463, "global_step": 388967, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.074216604232788, "global_step": 388968, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.130685806274414, "global_step": 388969, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0451509952545166, "global_step": 388970, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1694302558898926, "global_step": 388971, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9691131114959717, "global_step": 388972, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0387187004089355, "global_step": 388973, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0899240970611572, "global_step": 388974, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0554721355438232, "global_step": 388975, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.088069438934326, "global_step": 388976, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.047664165496826, "global_step": 388977, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0988104343414307, "global_step": 388978, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.095061779022217, "global_step": 388979, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.110266923904419, "global_step": 388980, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0087082386016846, "global_step": 388981, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.121716260910034, "global_step": 388982, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1288886070251465, "global_step": 388983, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.050902843475342, "global_step": 388984, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0959365367889404, "global_step": 388985, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.03961443901062, "global_step": 388986, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0358173847198486, "global_step": 388987, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.070993423461914, "global_step": 388988, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1070165634155273, "global_step": 388989, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0808663368225098, "global_step": 388990, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.096576452255249, "global_step": 388991, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0789732933044434, "global_step": 388992, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.087778091430664, "global_step": 388993, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1228771209716797, "global_step": 388994, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.110131025314331, "global_step": 388995, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.042248010635376, "global_step": 388996, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0727715492248535, "global_step": 388997, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1424877643585205, "global_step": 388998, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0675086975097656, "global_step": 388999, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1231791973114014, "global_step": 389000, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9869413375854492, "global_step": 389001, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.179687261581421, "global_step": 389002, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.052116870880127, "global_step": 389003, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0380125045776367, "global_step": 389004, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.116659641265869, "global_step": 389005, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.097597599029541, "global_step": 389006, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0280215740203857, "global_step": 389007, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1302907466888428, "global_step": 389008, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0951437950134277, "global_step": 389009, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.139827251434326, "global_step": 389010, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1178252696990967, "global_step": 389011, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.096691846847534, "global_step": 389012, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0924315452575684, "global_step": 389013, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.130373477935791, "global_step": 389014, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.13950777053833, "global_step": 389015, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0574445724487305, "global_step": 389016, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.071587085723877, "global_step": 389017, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.059649705886841, "global_step": 389018, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.03169322013855, "global_step": 389019, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.11106014251709, "global_step": 389020, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1147620677948, "global_step": 389021, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1166906356811523, "global_step": 389022, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.091193914413452, "global_step": 389023, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1129648685455322, "global_step": 389024, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1087779998779297, "global_step": 389025, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0723090171813965, "global_step": 389026, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1255862712860107, "global_step": 389027, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1164445877075195, "global_step": 389028, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.118044853210449, "global_step": 389029, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.095978260040283, "global_step": 389030, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.094167947769165, "global_step": 389031, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.028999090194702, "global_step": 389032, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1152894496917725, "global_step": 389033, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0279645919799805, "global_step": 389034, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0795724391937256, "global_step": 389035, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1460604667663574, "global_step": 389036, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0751442909240723, "global_step": 389037, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1585230827331543, "global_step": 389038, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1546385288238525, "global_step": 389039, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.061772346496582, "global_step": 389040, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1458349227905273, "global_step": 389041, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1200919151306152, "global_step": 389042, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.14623761177063, "global_step": 389043, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1683695316314697, "global_step": 389044, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.104177236557007, "global_step": 389045, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1275644302368164, "global_step": 389046, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0848419666290283, "global_step": 389047, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0940191745758057, "global_step": 389048, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.06874418258667, "global_step": 389049, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0300769805908203, "global_step": 389050, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.066098690032959, "global_step": 389051, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1359333992004395, "global_step": 389052, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.096261978149414, "global_step": 389053, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0489635467529297, "global_step": 389054, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.2259466648101807, "global_step": 389055, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.113083839416504, "global_step": 389056, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1320762634277344, "global_step": 389057, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.224337577819824, "global_step": 389058, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.152827262878418, "global_step": 389059, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1029164791107178, "global_step": 389060, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.203953742980957, "global_step": 389061, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0386266708374023, "global_step": 389062, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1292178630828857, "global_step": 389063, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0352110862731934, "global_step": 389064, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.059283971786499, "global_step": 389065, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0630545616149902, "global_step": 389066, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.221930980682373, "global_step": 389067, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.094874620437622, "global_step": 389068, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1263740062713623, "global_step": 389069, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.048734664916992, "global_step": 389070, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0903937816619873, "global_step": 389071, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1723105907440186, "global_step": 389072, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.03548002243042, "global_step": 389073, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1190834045410156, "global_step": 389074, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0964722633361816, "global_step": 389075, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0936059951782227, "global_step": 389076, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.105710983276367, "global_step": 389077, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.138751745223999, "global_step": 389078, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.137171983718872, "global_step": 389079, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1083366870880127, "global_step": 389080, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1382737159729004, "global_step": 389081, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0419974327087402, "global_step": 389082, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.073185920715332, "global_step": 389083, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.09506893157959, "global_step": 389084, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0682952404022217, "global_step": 389085, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0196027755737305, "global_step": 389086, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1476964950561523, "global_step": 389087, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0899877548217773, "global_step": 389088, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1430249214172363, "global_step": 389089, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1572346687316895, "global_step": 389090, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1369850635528564, "global_step": 389091, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1070475578308105, "global_step": 389092, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1092422008514404, "global_step": 389093, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0921263694763184, "global_step": 389094, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1174986362457275, "global_step": 389095, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1814792156219482, "global_step": 389096, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1718480587005615, "global_step": 389097, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.015589714050293, "global_step": 389098, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0677754878997803, "global_step": 389099, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.085325241088867, "global_step": 389100, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.161590576171875, "global_step": 389101, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0902671813964844, "global_step": 389102, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.176417589187622, "global_step": 389103, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1576452255249023, "global_step": 389104, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1532270908355713, "global_step": 389105, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0083765983581543, "global_step": 389106, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1436471939086914, "global_step": 389107, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.158586263656616, "global_step": 389108, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9874584674835205, "global_step": 389109, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1081314086914062, "global_step": 389110, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9844084978103638, "global_step": 389111, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.085901975631714, "global_step": 389112, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.043808698654175, "global_step": 389113, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.038374423980713, "global_step": 389114, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1640496253967285, "global_step": 389115, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.058870315551758, "global_step": 389116, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0819451808929443, "global_step": 389117, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9611434936523438, "global_step": 389118, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.114255905151367, "global_step": 389119, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0468411445617676, "global_step": 389120, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0421149730682373, "global_step": 389121, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.073280096054077, "global_step": 389122, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.167095184326172, "global_step": 389123, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.084482192993164, "global_step": 389124, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.244734764099121, "global_step": 389125, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0204267501831055, "global_step": 389126, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0824756622314453, "global_step": 389127, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.144963502883911, "global_step": 389128, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0987792015075684, "global_step": 389129, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1096110343933105, "global_step": 389130, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1136512756347656, "global_step": 389131, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1532044410705566, "global_step": 389132, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1841299533843994, "global_step": 389133, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0735466480255127, "global_step": 389134, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.188805103302002, "global_step": 389135, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.069807291030884, "global_step": 389136, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.14835262298584, "global_step": 389137, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.076763153076172, "global_step": 389138, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1328251361846924, "global_step": 389139, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1320292949676514, "global_step": 389140, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1640982627868652, "global_step": 389141, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.18892502784729, "global_step": 389142, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.141427755355835, "global_step": 389143, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1009061336517334, "global_step": 389144, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.051046133041382, "global_step": 389145, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1376657485961914, "global_step": 389146, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0905568599700928, "global_step": 389147, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.180778741836548, "global_step": 389148, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0933210849761963, "global_step": 389149, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1007370948791504, "global_step": 389150, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.137974977493286, "global_step": 389151, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0972275733947754, "global_step": 389152, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.072438955307007, "global_step": 389153, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0906341075897217, "global_step": 389154, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.12945556640625, "global_step": 389155, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1571788787841797, "global_step": 389156, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.024719715118408, "global_step": 389157, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.151723623275757, "global_step": 389158, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1590709686279297, "global_step": 389159, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0967295169830322, "global_step": 389160, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0282907485961914, "global_step": 389161, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1537301540374756, "global_step": 389162, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.05108380317688, "global_step": 389163, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.182178020477295, "global_step": 389164, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.10599422454834, "global_step": 389165, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.017630100250244, "global_step": 389166, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.040860176086426, "global_step": 389167, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.067922592163086, "global_step": 389168, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.157695770263672, "global_step": 389169, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.164884567260742, "global_step": 389170, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.04742693901062, "global_step": 389171, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.069709539413452, "global_step": 389172, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.142669439315796, "global_step": 389173, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1138973236083984, "global_step": 389174, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0710790157318115, "global_step": 389175, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1661264896392822, "global_step": 389176, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1331892013549805, "global_step": 389177, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0482044219970703, "global_step": 389178, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.10636305809021, "global_step": 389179, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.113492488861084, "global_step": 389180, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1288676261901855, "global_step": 389181, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1555941104888916, "global_step": 389182, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.133622169494629, "global_step": 389183, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.110628366470337, "global_step": 389184, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1134161949157715, "global_step": 389185, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.090723991394043, "global_step": 389186, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1303017139434814, "global_step": 389187, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0896809101104736, "global_step": 389188, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.115264654159546, "global_step": 389189, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0036022663116455, "global_step": 389190, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0773940086364746, "global_step": 389191, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9970978498458862, "global_step": 389192, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.10548996925354, "global_step": 389193, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1293368339538574, "global_step": 389194, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9986631870269775, "global_step": 389195, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0981976985931396, "global_step": 389196, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9857653379440308, "global_step": 389197, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.034769058227539, "global_step": 389198, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1787936687469482, "global_step": 389199, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0892248153686523, "global_step": 389200, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.058436632156372, "global_step": 389201, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1107587814331055, "global_step": 389202, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.105186939239502, "global_step": 389203, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.125098466873169, "global_step": 389204, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9968167543411255, "global_step": 389205, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0908515453338623, "global_step": 389206, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.060868263244629, "global_step": 389207, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0942957401275635, "global_step": 389208, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1114983558654785, "global_step": 389209, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1830976009368896, "global_step": 389210, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.06838059425354, "global_step": 389211, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1721384525299072, "global_step": 389212, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.076052188873291, "global_step": 389213, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0528066158294678, "global_step": 389214, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0503597259521484, "global_step": 389215, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.146657705307007, "global_step": 389216, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1895809173583984, "global_step": 389217, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0943539142608643, "global_step": 389218, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0503621101379395, "global_step": 389219, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0233280658721924, "global_step": 389220, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.018385648727417, "global_step": 389221, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.116424798965454, "global_step": 389222, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1165997982025146, "global_step": 389223, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.099022626876831, "global_step": 389224, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0764126777648926, "global_step": 389225, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0730040073394775, "global_step": 389226, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.098726511001587, "global_step": 389227, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0963354110717773, "global_step": 389228, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.104071617126465, "global_step": 389229, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0325095653533936, "global_step": 389230, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1673152446746826, "global_step": 389231, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.070444345474243, "global_step": 389232, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.087920904159546, "global_step": 389233, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0440170764923096, "global_step": 389234, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.108210802078247, "global_step": 389235, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.159493923187256, "global_step": 389236, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0940401554107666, "global_step": 389237, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.125775098800659, "global_step": 389238, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.092210531234741, "global_step": 389239, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.06402850151062, "global_step": 389240, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1585683822631836, "global_step": 389241, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.103368043899536, "global_step": 389242, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.04984188079834, "global_step": 389243, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1126110553741455, "global_step": 389244, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.161205768585205, "global_step": 389245, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1371078491210938, "global_step": 389246, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.190737247467041, "global_step": 389247, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1777758598327637, "global_step": 389248, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1266186237335205, "global_step": 389249, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1914875507354736, "global_step": 389250, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0329885482788086, "global_step": 389251, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.076631784439087, "global_step": 389252, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.170780658721924, "global_step": 389253, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1075544357299805, "global_step": 389254, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.064769983291626, "global_step": 389255, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0993428230285645, "global_step": 389256, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1360137462615967, "global_step": 389257, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0967395305633545, "global_step": 389258, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1067802906036377, "global_step": 389259, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1302578449249268, "global_step": 389260, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0902955532073975, "global_step": 389261, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1282243728637695, "global_step": 389262, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.2057769298553467, "global_step": 389263, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0986711978912354, "global_step": 389264, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1001598834991455, "global_step": 389265, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.115631103515625, "global_step": 389266, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1094021797180176, "global_step": 389267, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9796748161315918, "global_step": 389268, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.017726182937622, "global_step": 389269, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1579782962799072, "global_step": 389270, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.067390203475952, "global_step": 389271, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0859458446502686, "global_step": 389272, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.121917247772217, "global_step": 389273, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1109142303466797, "global_step": 389274, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.019015073776245, "global_step": 389275, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.114488363265991, "global_step": 389276, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1624691486358643, "global_step": 389277, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.995976448059082, "global_step": 389278, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.158132314682007, "global_step": 389279, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.102722644805908, "global_step": 389280, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0005245208740234, "global_step": 389281, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.113016366958618, "global_step": 389282, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0494141578674316, "global_step": 389283, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0672554969787598, "global_step": 389284, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.129016399383545, "global_step": 389285, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0553417205810547, "global_step": 389286, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.12138032913208, "global_step": 389287, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.121098279953003, "global_step": 389288, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.051345109939575, "global_step": 389289, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1176016330718994, "global_step": 389290, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0441620349884033, "global_step": 389291, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0999269485473633, "global_step": 389292, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.094972848892212, "global_step": 389293, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.110774517059326, "global_step": 389294, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0667402744293213, "global_step": 389295, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.161674737930298, "global_step": 389296, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0982465744018555, "global_step": 389297, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.176255702972412, "global_step": 389298, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1420133113861084, "global_step": 389299, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0878026485443115, "global_step": 389300, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.057499408721924, "global_step": 389301, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1121742725372314, "global_step": 389302, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0211713314056396, "global_step": 389303, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1229257583618164, "global_step": 389304, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0381433963775635, "global_step": 389305, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1142423152923584, "global_step": 389306, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.100095272064209, "global_step": 389307, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.134531021118164, "global_step": 389308, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.106318712234497, "global_step": 389309, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.123891830444336, "global_step": 389310, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.059990167617798, "global_step": 389311, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.093231678009033, "global_step": 389312, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0205130577087402, "global_step": 389313, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.2155191898345947, "global_step": 389314, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0787460803985596, "global_step": 389315, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0836098194122314, "global_step": 389316, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.141477108001709, "global_step": 389317, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1337199211120605, "global_step": 389318, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0586068630218506, "global_step": 389319, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.138826370239258, "global_step": 389320, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0083861351013184, "global_step": 389321, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0411298274993896, "global_step": 389322, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.203446626663208, "global_step": 389323, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0104782581329346, "global_step": 389324, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0098533630371094, "global_step": 389325, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1755752563476562, "global_step": 389326, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.213930606842041, "global_step": 389327, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1015448570251465, "global_step": 389328, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.120218515396118, "global_step": 389329, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.148658275604248, "global_step": 389330, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1697733402252197, "global_step": 389331, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0410945415496826, "global_step": 389332, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.130328893661499, "global_step": 389333, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0500175952911377, "global_step": 389334, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.186110496520996, "global_step": 389335, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0213463306427, "global_step": 389336, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.042060613632202, "global_step": 389337, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.131680727005005, "global_step": 389338, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.083432674407959, "global_step": 389339, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0376999378204346, "global_step": 389340, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.238020181655884, "global_step": 389341, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1314470767974854, "global_step": 389342, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1380083560943604, "global_step": 389343, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.039971351623535, "global_step": 389344, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.084599733352661, "global_step": 389345, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1485533714294434, "global_step": 389346, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.12253475189209, "global_step": 389347, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1122782230377197, "global_step": 389348, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0874226093292236, "global_step": 389349, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.183469772338867, "global_step": 389350, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0842626094818115, "global_step": 389351, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1179356575012207, "global_step": 389352, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0812582969665527, "global_step": 389353, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0590240955352783, "global_step": 389354, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1247313022613525, "global_step": 389355, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1205272674560547, "global_step": 389356, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1227622032165527, "global_step": 389357, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0932109355926514, "global_step": 389358, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.112171173095703, "global_step": 389359, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.128251552581787, "global_step": 389360, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0804128646850586, "global_step": 389361, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0710666179656982, "global_step": 389362, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1396737098693848, "global_step": 389363, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1296451091766357, "global_step": 389364, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1716203689575195, "global_step": 389365, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.098346710205078, "global_step": 389366, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.00195050239563, "global_step": 389367, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1175098419189453, "global_step": 389368, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0640482902526855, "global_step": 389369, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0938987731933594, "global_step": 389370, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.2616806030273438, "global_step": 389371, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0983121395111084, "global_step": 389372, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0327250957489014, "global_step": 389373, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.073540210723877, "global_step": 389374, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0602076053619385, "global_step": 389375, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.207155466079712, "global_step": 389376, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0417191982269287, "global_step": 389377, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.072474956512451, "global_step": 389378, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1250786781311035, "global_step": 389379, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0716211795806885, "global_step": 389380, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0928735733032227, "global_step": 389381, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1244096755981445, "global_step": 389382, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0687477588653564, "global_step": 389383, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1717545986175537, "global_step": 389384, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.099776029586792, "global_step": 389385, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1384191513061523, "global_step": 389386, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.087937831878662, "global_step": 389387, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.139962911605835, "global_step": 389388, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1439874172210693, "global_step": 389389, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0849664211273193, "global_step": 389390, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.061659574508667, "global_step": 389391, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0296409130096436, "global_step": 389392, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.065305471420288, "global_step": 389393, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0844829082489014, "global_step": 389394, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1040196418762207, "global_step": 389395, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0393009185791016, "global_step": 389396, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.113649606704712, "global_step": 389397, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.180202007293701, "global_step": 389398, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.098842144012451, "global_step": 389399, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.077439069747925, "global_step": 389400, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1413347721099854, "global_step": 389401, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1569483280181885, "global_step": 389402, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.087282180786133, "global_step": 389403, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.070925235748291, "global_step": 389404, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.10457444190979, "global_step": 389405, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9970048666000366, "global_step": 389406, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.124394416809082, "global_step": 389407, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.005291223526001, "global_step": 389408, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.12485933303833, "global_step": 389409, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1734211444854736, "global_step": 389410, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.147475004196167, "global_step": 389411, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0721378326416016, "global_step": 389412, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1086223125457764, "global_step": 389413, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.125622510910034, "global_step": 389414, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0522260665893555, "global_step": 389415, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0610342025756836, "global_step": 389416, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.173769235610962, "global_step": 389417, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1660006046295166, "global_step": 389418, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.091891288757324, "global_step": 389419, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1300477981567383, "global_step": 389420, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.068697214126587, "global_step": 389421, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0438220500946045, "global_step": 389422, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.146310329437256, "global_step": 389423, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1137027740478516, "global_step": 389424, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.097168207168579, "global_step": 389425, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1262879371643066, "global_step": 389426, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0516836643218994, "global_step": 389427, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.083833932876587, "global_step": 389428, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1743547916412354, "global_step": 389429, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.103835344314575, "global_step": 389430, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1243088245391846, "global_step": 389431, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0388240814208984, "global_step": 389432, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1544995307922363, "global_step": 389433, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.088829755783081, "global_step": 389434, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.146894931793213, "global_step": 389435, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.152287244796753, "global_step": 389436, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.120546817779541, "global_step": 389437, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0935182571411133, "global_step": 389438, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0905354022979736, "global_step": 389439, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.060371160507202, "global_step": 389440, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0910794734954834, "global_step": 389441, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1465976238250732, "global_step": 389442, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.131197452545166, "global_step": 389443, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1570019721984863, "global_step": 389444, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1259777545928955, "global_step": 389445, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.2125980854034424, "global_step": 389446, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.063249349594116, "global_step": 389447, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9964338541030884, "global_step": 389448, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0805444717407227, "global_step": 389449, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.100677728652954, "global_step": 389450, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1165931224823, "global_step": 389451, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9944939613342285, "global_step": 389452, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1269896030426025, "global_step": 389453, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.109895944595337, "global_step": 389454, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9945294857025146, "global_step": 389455, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0933260917663574, "global_step": 389456, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.125375270843506, "global_step": 389457, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1532561779022217, "global_step": 389458, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.103553295135498, "global_step": 389459, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.076569080352783, "global_step": 389460, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0734853744506836, "global_step": 389461, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.078075647354126, "global_step": 389462, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1116111278533936, "global_step": 389463, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.222368001937866, "global_step": 389464, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.017930507659912, "global_step": 389465, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9834835529327393, "global_step": 389466, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0668585300445557, "global_step": 389467, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0690653324127197, "global_step": 389468, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0907559394836426, "global_step": 389469, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.084057569503784, "global_step": 389470, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.126589059829712, "global_step": 389471, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.162912607192993, "global_step": 389472, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.149325370788574, "global_step": 389473, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1939501762390137, "global_step": 389474, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1405396461486816, "global_step": 389475, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0868022441864014, "global_step": 389476, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.2196903228759766, "global_step": 389477, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1017403602600098, "global_step": 389478, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.087944746017456, "global_step": 389479, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1129913330078125, "global_step": 389480, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1522881984710693, "global_step": 389481, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1220483779907227, "global_step": 389482, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.075749635696411, "global_step": 389483, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0640640258789062, "global_step": 389484, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0449676513671875, "global_step": 389485, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1945555210113525, "global_step": 389486, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1417338848114014, "global_step": 389487, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1111254692077637, "global_step": 389488, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.165343761444092, "global_step": 389489, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1568775177001953, "global_step": 389490, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.047684907913208, "global_step": 389491, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1232855319976807, "global_step": 389492, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0837037563323975, "global_step": 389493, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1499183177948, "global_step": 389494, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.078612804412842, "global_step": 389495, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.05279541015625, "global_step": 389496, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.070453405380249, "global_step": 389497, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0597705841064453, "global_step": 389498, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1017956733703613, "global_step": 389499, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.102705717086792, "global_step": 389500, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0565974712371826, "global_step": 389501, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.169485092163086, "global_step": 389502, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.060622215270996, "global_step": 389503, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.098921775817871, "global_step": 389504, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.071009874343872, "global_step": 389505, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.043886184692383, "global_step": 389506, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1109533309936523, "global_step": 389507, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0148813724517822, "global_step": 389508, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.146867036819458, "global_step": 389509, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.025172472000122, "global_step": 389510, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.157137870788574, "global_step": 389511, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.219334602355957, "global_step": 389512, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.086729049682617, "global_step": 389513, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0609400272369385, "global_step": 389514, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1844701766967773, "global_step": 389515, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0645790100097656, "global_step": 389516, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.044466495513916, "global_step": 389517, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1635446548461914, "global_step": 389518, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.199103832244873, "global_step": 389519, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.071413993835449, "global_step": 389520, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.053957462310791, "global_step": 389521, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1237940788269043, "global_step": 389522, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.057522773742676, "global_step": 389523, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1148793697357178, "global_step": 389524, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1387317180633545, "global_step": 389525, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.158100128173828, "global_step": 389526, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.099599599838257, "global_step": 389527, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.11283278465271, "global_step": 389528, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.141423225402832, "global_step": 389529, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0824437141418457, "global_step": 389530, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.160425901412964, "global_step": 389531, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1386868953704834, "global_step": 389532, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9966622591018677, "global_step": 389533, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0599722862243652, "global_step": 389534, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1883275508880615, "global_step": 389535, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.154757022857666, "global_step": 389536, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.162935733795166, "global_step": 389537, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0523128509521484, "global_step": 389538, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0786924362182617, "global_step": 389539, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.062377691268921, "global_step": 389540, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.135873556137085, "global_step": 389541, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.110750913619995, "global_step": 389542, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.091953992843628, "global_step": 389543, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0523993968963623, "global_step": 389544, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.156712532043457, "global_step": 389545, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.204793691635132, "global_step": 389546, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.119575023651123, "global_step": 389547, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.079517126083374, "global_step": 389548, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.140561819076538, "global_step": 389549, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1149942874908447, "global_step": 389550, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0798590183258057, "global_step": 389551, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1395323276519775, "global_step": 389552, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.150486469268799, "global_step": 389553, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1031980514526367, "global_step": 389554, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.000598430633545, "global_step": 389555, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.069164752960205, "global_step": 389556, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.2244174480438232, "global_step": 389557, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1173553466796875, "global_step": 389558, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0214591026306152, "global_step": 389559, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.073793649673462, "global_step": 389560, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.080780506134033, "global_step": 389561, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.2116332054138184, "global_step": 389562, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1219916343688965, "global_step": 389563, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.064610242843628, "global_step": 389564, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.065721035003662, "global_step": 389565, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.120756149291992, "global_step": 389566, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.118788242340088, "global_step": 389567, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.165759563446045, "global_step": 389568, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.102306604385376, "global_step": 389569, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1569392681121826, "global_step": 389570, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.171935558319092, "global_step": 389571, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1022846698760986, "global_step": 389572, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.984480857849121, "global_step": 389573, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0932483673095703, "global_step": 389574, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9909199476242065, "global_step": 389575, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.089301586151123, "global_step": 389576, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1057984828948975, "global_step": 389577, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0494701862335205, "global_step": 389578, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.158405303955078, "global_step": 389579, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1371541023254395, "global_step": 389580, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1379916667938232, "global_step": 389581, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9876681566238403, "global_step": 389582, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1355032920837402, "global_step": 389583, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.2500829696655273, "global_step": 389584, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0390305519104004, "global_step": 389585, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0633175373077393, "global_step": 389586, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0277082920074463, "global_step": 389587, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0956270694732666, "global_step": 389588, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1068882942199707, "global_step": 389589, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0838871002197266, "global_step": 389590, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0289976596832275, "global_step": 389591, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.124901056289673, "global_step": 389592, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1172635555267334, "global_step": 389593, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0398671627044678, "global_step": 389594, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.135089874267578, "global_step": 389595, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1516501903533936, "global_step": 389596, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1223409175872803, "global_step": 389597, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1607871055603027, "global_step": 389598, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.257551431655884, "global_step": 389599, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1312594413757324, "global_step": 389600, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0419762134552, "global_step": 389601, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.099959373474121, "global_step": 389602, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0916965007781982, "global_step": 389603, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1264359951019287, "global_step": 389604, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.2061469554901123, "global_step": 389605, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1554858684539795, "global_step": 389606, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.062756299972534, "global_step": 389607, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.9935262203216553, "global_step": 389608, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0141944885253906, "global_step": 389609, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0621252059936523, "global_step": 389610, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.18565034866333, "global_step": 389611, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0659749507904053, "global_step": 389612, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.109811305999756, "global_step": 389613, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.082618236541748, "global_step": 389614, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0914082527160645, "global_step": 389615, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0555436611175537, "global_step": 389616, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.155385732650757, "global_step": 389617, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1112709045410156, "global_step": 389618, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0936050415039062, "global_step": 389619, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0904159545898438, "global_step": 389620, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1211366653442383, "global_step": 389621, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.034010171890259, "global_step": 389622, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.092879056930542, "global_step": 389623, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.108332395553589, "global_step": 389624, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.107672691345215, "global_step": 389625, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.042081594467163, "global_step": 389626, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1637380123138428, "global_step": 389627, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.079824209213257, "global_step": 389628, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.104235887527466, "global_step": 389629, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1415834426879883, "global_step": 389630, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1431310176849365, "global_step": 389631, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.11313796043396, "global_step": 389632, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.088203191757202, "global_step": 389633, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1319265365600586, "global_step": 389634, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0206398963928223, "global_step": 389635, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1119720935821533, "global_step": 389636, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.117565155029297, "global_step": 389637, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0586137771606445, "global_step": 389638, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1108882427215576, "global_step": 389639, "epoch": 751, "lr": 5e-05}
{"train_loss": 1.98448646068573, "global_step": 389640, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1324431896209717, "global_step": 389641, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1287081241607666, "global_step": 389642, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0779919624328613, "global_step": 389643, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.145214319229126, "global_step": 389644, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0966732501983643, "global_step": 389645, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.065943717956543, "global_step": 389646, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.2184557914733887, "global_step": 389647, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0334675312042236, "global_step": 389648, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1646604537963867, "global_step": 389649, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.008770704269409, "global_step": 389650, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1171350479125977, "global_step": 389651, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0755116939544678, "global_step": 389652, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0997917652130127, "global_step": 389653, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0880770683288574, "global_step": 389654, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0764811038970947, "global_step": 389655, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1413650512695312, "global_step": 389656, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.061307191848755, "global_step": 389657, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0945520401000977, "global_step": 389658, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.086259603500366, "global_step": 389659, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1055774688720703, "global_step": 389660, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.03779673576355, "global_step": 389661, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.104449987411499, "global_step": 389662, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1499288082122803, "global_step": 389663, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.04990291595459, "global_step": 389664, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.098548412322998, "global_step": 389665, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.0598137378692627, "global_step": 389666, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.158454656600952, "global_step": 389667, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.137803554534912, "global_step": 389668, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.042280912399292, "global_step": 389669, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.099064826965332, "global_step": 389670, "epoch": 751, "lr": 5e-05}
{"train_loss": 2.1677448749542236, "global_step": 389671, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0168378353118896, "global_step": 389672, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.117685556411743, "global_step": 389673, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0965898036956787, "global_step": 389674, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1389286518096924, "global_step": 389675, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0442957878112793, "global_step": 389676, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1247482299804688, "global_step": 389677, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.123335123062134, "global_step": 389678, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.081166982650757, "global_step": 389679, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0876998901367188, "global_step": 389680, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.140432596206665, "global_step": 389681, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.092622995376587, "global_step": 389682, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.100773572921753, "global_step": 389683, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1369690895080566, "global_step": 389684, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.157221555709839, "global_step": 389685, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.094132900238037, "global_step": 389686, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1052746772766113, "global_step": 389687, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1191494464874268, "global_step": 389688, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.090475082397461, "global_step": 389689, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1350769996643066, "global_step": 389690, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1142563819885254, "global_step": 389691, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0781497955322266, "global_step": 389692, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.083387851715088, "global_step": 389693, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1051273345947266, "global_step": 389694, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.097505807876587, "global_step": 389695, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0388402938842773, "global_step": 389696, "epoch": 752, "lr": 5e-05}
{"train_loss": 1.999985933303833, "global_step": 389697, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.117684841156006, "global_step": 389698, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1151082515716553, "global_step": 389699, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0145602226257324, "global_step": 389700, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1874489784240723, "global_step": 389701, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1012961864471436, "global_step": 389702, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.080531597137451, "global_step": 389703, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.177408456802368, "global_step": 389704, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.106971025466919, "global_step": 389705, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.109586238861084, "global_step": 389706, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0356032848358154, "global_step": 389707, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.046177864074707, "global_step": 389708, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.04656720161438, "global_step": 389709, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0785973072052, "global_step": 389710, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.026421070098877, "global_step": 389711, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.109833002090454, "global_step": 389712, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0542097091674805, "global_step": 389713, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.085482597351074, "global_step": 389714, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0825395584106445, "global_step": 389715, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0700926780700684, "global_step": 389716, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.091881275177002, "global_step": 389717, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.064375877380371, "global_step": 389718, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.119363784790039, "global_step": 389719, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.128657341003418, "global_step": 389720, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.025623083114624, "global_step": 389721, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0153894424438477, "global_step": 389722, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1547629833221436, "global_step": 389723, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1299736499786377, "global_step": 389724, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0389628410339355, "global_step": 389725, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1487057209014893, "global_step": 389726, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0809850692749023, "global_step": 389727, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.073352575302124, "global_step": 389728, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0927839279174805, "global_step": 389729, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1658568382263184, "global_step": 389730, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.021963119506836, "global_step": 389731, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1331257820129395, "global_step": 389732, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0498998165130615, "global_step": 389733, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0924072265625, "global_step": 389734, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1510918140411377, "global_step": 389735, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.054863452911377, "global_step": 389736, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1129934787750244, "global_step": 389737, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1205427646636963, "global_step": 389738, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.050464630126953, "global_step": 389739, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0478994846343994, "global_step": 389740, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.05008602142334, "global_step": 389741, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1435470581054688, "global_step": 389742, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0111937522888184, "global_step": 389743, "epoch": 752, "lr": 5e-05}
{"train_loss": 1.9460667371749878, "global_step": 389744, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0818772315979004, "global_step": 389745, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.2087206840515137, "global_step": 389746, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0406851768493652, "global_step": 389747, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1466152667999268, "global_step": 389748, "epoch": 752, "lr": 5e-05}
{"train_loss": 1.998726725578308, "global_step": 389749, "epoch": 752, "lr": 5e-05}
{"train_loss": 1.9574997425079346, "global_step": 389750, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.079936981201172, "global_step": 389751, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0752341747283936, "global_step": 389752, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0612902641296387, "global_step": 389753, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.12998628616333, "global_step": 389754, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.144700288772583, "global_step": 389755, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.107008695602417, "global_step": 389756, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1306324005126953, "global_step": 389757, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1416704654693604, "global_step": 389758, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0279552936553955, "global_step": 389759, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.145820379257202, "global_step": 389760, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1325266361236572, "global_step": 389761, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.087681531906128, "global_step": 389762, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.128958225250244, "global_step": 389763, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1218948364257812, "global_step": 389764, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1170783042907715, "global_step": 389765, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.056550979614258, "global_step": 389766, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0611720085144043, "global_step": 389767, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.085280418395996, "global_step": 389768, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.06695818901062, "global_step": 389769, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.08608078956604, "global_step": 389770, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0631697177886963, "global_step": 389771, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.048933982849121, "global_step": 389772, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0781867504119873, "global_step": 389773, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.155585765838623, "global_step": 389774, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1064534187316895, "global_step": 389775, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0763726234436035, "global_step": 389776, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0876100063323975, "global_step": 389777, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.055804491043091, "global_step": 389778, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0878498554229736, "global_step": 389779, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.10697603225708, "global_step": 389780, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.10921573638916, "global_step": 389781, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1057333946228027, "global_step": 389782, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1077139377593994, "global_step": 389783, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0701355934143066, "global_step": 389784, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0367379188537598, "global_step": 389785, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0813004970550537, "global_step": 389786, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.14247727394104, "global_step": 389787, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.149317741394043, "global_step": 389788, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.133415460586548, "global_step": 389789, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0668294429779053, "global_step": 389790, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1860454082489014, "global_step": 389791, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0615758895874023, "global_step": 389792, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.079233407974243, "global_step": 389793, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.174889087677002, "global_step": 389794, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0935115814208984, "global_step": 389795, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1304941177368164, "global_step": 389796, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.006706714630127, "global_step": 389797, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1442325115203857, "global_step": 389798, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1072216033935547, "global_step": 389799, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.15889048576355, "global_step": 389800, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1004979610443115, "global_step": 389801, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1556098461151123, "global_step": 389802, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0618605613708496, "global_step": 389803, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.06134033203125, "global_step": 389804, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1796507835388184, "global_step": 389805, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.133960008621216, "global_step": 389806, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.123075008392334, "global_step": 389807, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1179182529449463, "global_step": 389808, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.135622262954712, "global_step": 389809, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.144259214401245, "global_step": 389810, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.085231304168701, "global_step": 389811, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1310293674468994, "global_step": 389812, "epoch": 752, "lr": 5e-05}
{"train_loss": 1.9869132041931152, "global_step": 389813, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1163134574890137, "global_step": 389814, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.000945806503296, "global_step": 389815, "epoch": 752, "lr": 5e-05}
{"train_loss": 1.9819772243499756, "global_step": 389816, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0766615867614746, "global_step": 389817, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0103771686553955, "global_step": 389818, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0576012134552, "global_step": 389819, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0412356853485107, "global_step": 389820, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.09808087348938, "global_step": 389821, "epoch": 752, "lr": 5e-05}
{"train_loss": 1.973425269126892, "global_step": 389822, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0770325660705566, "global_step": 389823, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.088526487350464, "global_step": 389824, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.15580677986145, "global_step": 389825, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1396145820617676, "global_step": 389826, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0519118309020996, "global_step": 389827, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.009699821472168, "global_step": 389828, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0374643802642822, "global_step": 389829, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0323948860168457, "global_step": 389830, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.169599771499634, "global_step": 389831, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.121595621109009, "global_step": 389832, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0765228271484375, "global_step": 389833, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.102975845336914, "global_step": 389834, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.075803279876709, "global_step": 389835, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.155975341796875, "global_step": 389836, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1295955181121826, "global_step": 389837, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1283090114593506, "global_step": 389838, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.021733045578003, "global_step": 389839, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.133408546447754, "global_step": 389840, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1645331382751465, "global_step": 389841, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0726568698883057, "global_step": 389842, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.108513832092285, "global_step": 389843, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0767157077789307, "global_step": 389844, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0706307888031006, "global_step": 389845, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1287622451782227, "global_step": 389846, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.150608539581299, "global_step": 389847, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0530004501342773, "global_step": 389848, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.022942304611206, "global_step": 389849, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1474199295043945, "global_step": 389850, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.046527862548828, "global_step": 389851, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0989792346954346, "global_step": 389852, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0882434844970703, "global_step": 389853, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.048635482788086, "global_step": 389854, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.04457688331604, "global_step": 389855, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.088963747024536, "global_step": 389856, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0719220638275146, "global_step": 389857, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.088451862335205, "global_step": 389858, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.2233638763427734, "global_step": 389859, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0268921852111816, "global_step": 389860, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.115623950958252, "global_step": 389861, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1085455417633057, "global_step": 389862, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.126721143722534, "global_step": 389863, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0685691833496094, "global_step": 389864, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1060428619384766, "global_step": 389865, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0210180282592773, "global_step": 389866, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0956525802612305, "global_step": 389867, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.12164306640625, "global_step": 389868, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0099520683288574, "global_step": 389869, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.114908218383789, "global_step": 389870, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0751535892486572, "global_step": 389871, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0221853256225586, "global_step": 389872, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0322375297546387, "global_step": 389873, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1262621879577637, "global_step": 389874, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1641292572021484, "global_step": 389875, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.119738817214966, "global_step": 389876, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1673295497894287, "global_step": 389877, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.072923183441162, "global_step": 389878, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.142688035964966, "global_step": 389879, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.058441400527954, "global_step": 389880, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1129775047302246, "global_step": 389881, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1144399642944336, "global_step": 389882, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1027309894561768, "global_step": 389883, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.115539789199829, "global_step": 389884, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.175291061401367, "global_step": 389885, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0672214031219482, "global_step": 389886, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0578906536102295, "global_step": 389887, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0112290382385254, "global_step": 389888, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0389435291290283, "global_step": 389889, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.066190719604492, "global_step": 389890, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0506131649017334, "global_step": 389891, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1326870918273926, "global_step": 389892, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.147427558898926, "global_step": 389893, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.077799081802368, "global_step": 389894, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.128811836242676, "global_step": 389895, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0503616333007812, "global_step": 389896, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.055048942565918, "global_step": 389897, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.100419044494629, "global_step": 389898, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.150787353515625, "global_step": 389899, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0498428344726562, "global_step": 389900, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.134164571762085, "global_step": 389901, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.079603672027588, "global_step": 389902, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.105384111404419, "global_step": 389903, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.121678113937378, "global_step": 389904, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0680935382843018, "global_step": 389905, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.2220752239227295, "global_step": 389906, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1071417331695557, "global_step": 389907, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1556830406188965, "global_step": 389908, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.075979709625244, "global_step": 389909, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.103426456451416, "global_step": 389910, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0500411987304688, "global_step": 389911, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0722389221191406, "global_step": 389912, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0630669593811035, "global_step": 389913, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0648763179779053, "global_step": 389914, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.097975730895996, "global_step": 389915, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.137126922607422, "global_step": 389916, "epoch": 752, "lr": 5e-05}
{"train_loss": 1.9847182035446167, "global_step": 389917, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.096130847930908, "global_step": 389918, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.083475112915039, "global_step": 389919, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1333417892456055, "global_step": 389920, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0954208374023438, "global_step": 389921, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1665027141571045, "global_step": 389922, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.21370792388916, "global_step": 389923, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1057212352752686, "global_step": 389924, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.118314266204834, "global_step": 389925, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.090991258621216, "global_step": 389926, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0461015701293945, "global_step": 389927, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1588501930236816, "global_step": 389928, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0446951389312744, "global_step": 389929, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1752538681030273, "global_step": 389930, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.078742742538452, "global_step": 389931, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.10959529876709, "global_step": 389932, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.014176368713379, "global_step": 389933, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.052278518676758, "global_step": 389934, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1269500255584717, "global_step": 389935, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0876052379608154, "global_step": 389936, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.096128225326538, "global_step": 389937, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.091979503631592, "global_step": 389938, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.155186414718628, "global_step": 389939, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.111008882522583, "global_step": 389940, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1253292560577393, "global_step": 389941, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.126180410385132, "global_step": 389942, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.208203077316284, "global_step": 389943, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1299033164978027, "global_step": 389944, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1232657432556152, "global_step": 389945, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0734736919403076, "global_step": 389946, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1714067459106445, "global_step": 389947, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0177133083343506, "global_step": 389948, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0220601558685303, "global_step": 389949, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.150397300720215, "global_step": 389950, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.039959192276001, "global_step": 389951, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.067701578140259, "global_step": 389952, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1384100914001465, "global_step": 389953, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1361420154571533, "global_step": 389954, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.128307819366455, "global_step": 389955, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.104802370071411, "global_step": 389956, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0816662311553955, "global_step": 389957, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.087477922439575, "global_step": 389958, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0436513423919678, "global_step": 389959, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1748158931732178, "global_step": 389960, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.142362117767334, "global_step": 389961, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.091933250427246, "global_step": 389962, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1240270137786865, "global_step": 389963, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1027016639709473, "global_step": 389964, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.149264335632324, "global_step": 389965, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0388216972351074, "global_step": 389966, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.152055263519287, "global_step": 389967, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0299482345581055, "global_step": 389968, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.120591640472412, "global_step": 389969, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0201337337493896, "global_step": 389970, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0942609310150146, "global_step": 389971, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0929696559906006, "global_step": 389972, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.116942882537842, "global_step": 389973, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0506556034088135, "global_step": 389974, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.072263717651367, "global_step": 389975, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0438780784606934, "global_step": 389976, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0381288528442383, "global_step": 389977, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1037073135375977, "global_step": 389978, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.14290714263916, "global_step": 389979, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1473684310913086, "global_step": 389980, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0308945178985596, "global_step": 389981, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.057673692703247, "global_step": 389982, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.167940855026245, "global_step": 389983, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0687026977539062, "global_step": 389984, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1236066818237305, "global_step": 389985, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1441054344177246, "global_step": 389986, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0679476261138916, "global_step": 389987, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.147094964981079, "global_step": 389988, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.133646249771118, "global_step": 389989, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1535110473632812, "global_step": 389990, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0704855918884277, "global_step": 389991, "epoch": 752, "lr": 5e-05}
{"train_loss": 1.9839462041854858, "global_step": 389992, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1051173210144043, "global_step": 389993, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1217105388641357, "global_step": 389994, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.136112928390503, "global_step": 389995, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.065418243408203, "global_step": 389996, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.083913803100586, "global_step": 389997, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1435749530792236, "global_step": 389998, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0036354064941406, "global_step": 389999, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1084980964660645, "global_step": 390000, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0820672512054443, "global_step": 390001, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1409945487976074, "global_step": 390002, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1435675621032715, "global_step": 390003, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.11964750289917, "global_step": 390004, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1202518939971924, "global_step": 390005, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.084927797317505, "global_step": 390006, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1527700424194336, "global_step": 390007, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1345059871673584, "global_step": 390008, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1366283893585205, "global_step": 390009, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1360528469085693, "global_step": 390010, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1473686695098877, "global_step": 390011, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.087146759033203, "global_step": 390012, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0854146480560303, "global_step": 390013, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0832931995391846, "global_step": 390014, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.065516233444214, "global_step": 390015, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0535812377929688, "global_step": 390016, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1913681030273438, "global_step": 390017, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1403002738952637, "global_step": 390018, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.058504104614258, "global_step": 390019, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.117677927017212, "global_step": 390020, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1443896293640137, "global_step": 390021, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.037309169769287, "global_step": 390022, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0756261348724365, "global_step": 390023, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.162339448928833, "global_step": 390024, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1444430351257324, "global_step": 390025, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.095590591430664, "global_step": 390026, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.110846996307373, "global_step": 390027, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.2096471786499023, "global_step": 390028, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.138495922088623, "global_step": 390029, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0405962467193604, "global_step": 390030, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.160285711288452, "global_step": 390031, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.077580690383911, "global_step": 390032, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.153350353240967, "global_step": 390033, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.045842170715332, "global_step": 390034, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0574138164520264, "global_step": 390035, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0649800300598145, "global_step": 390036, "epoch": 752, "lr": 5e-05}
{"train_loss": 1.9902387857437134, "global_step": 390037, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1450250148773193, "global_step": 390038, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0917258262634277, "global_step": 390039, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.096906900405884, "global_step": 390040, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1359262466430664, "global_step": 390041, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.084073543548584, "global_step": 390042, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.035372257232666, "global_step": 390043, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.127655506134033, "global_step": 390044, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1885600090026855, "global_step": 390045, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.075253486633301, "global_step": 390046, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0793285369873047, "global_step": 390047, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.118016481399536, "global_step": 390048, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.020979404449463, "global_step": 390049, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.113644599914551, "global_step": 390050, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.061258554458618, "global_step": 390051, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0405590534210205, "global_step": 390052, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0862088203430176, "global_step": 390053, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.124535322189331, "global_step": 390054, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0346484184265137, "global_step": 390055, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0516843795776367, "global_step": 390056, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1090972423553467, "global_step": 390057, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.09006404876709, "global_step": 390058, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.136052370071411, "global_step": 390059, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0740108489990234, "global_step": 390060, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1653707027435303, "global_step": 390061, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.159559726715088, "global_step": 390062, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0872199535369873, "global_step": 390063, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.079582929611206, "global_step": 390064, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0673506259918213, "global_step": 390065, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1166882514953613, "global_step": 390066, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1282687187194824, "global_step": 390067, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0427629947662354, "global_step": 390068, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.102743148803711, "global_step": 390069, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0635182857513428, "global_step": 390070, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0121188163757324, "global_step": 390071, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.130415678024292, "global_step": 390072, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1550230979919434, "global_step": 390073, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.12528395652771, "global_step": 390074, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0759694576263428, "global_step": 390075, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1743831634521484, "global_step": 390076, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0674362182617188, "global_step": 390077, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.099536657333374, "global_step": 390078, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0715672969818115, "global_step": 390079, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.125922203063965, "global_step": 390080, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1459100246429443, "global_step": 390081, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.110631227493286, "global_step": 390082, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.048215389251709, "global_step": 390083, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0702764987945557, "global_step": 390084, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1817193031311035, "global_step": 390085, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1180262565612793, "global_step": 390086, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.119720697402954, "global_step": 390087, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1174991130828857, "global_step": 390088, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1362624168395996, "global_step": 390089, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.077313184738159, "global_step": 390090, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1076738834381104, "global_step": 390091, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0582406520843506, "global_step": 390092, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.05171275138855, "global_step": 390093, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.154200792312622, "global_step": 390094, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1346423625946045, "global_step": 390095, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.098782539367676, "global_step": 390096, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.035515069961548, "global_step": 390097, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1456263065338135, "global_step": 390098, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0745437145233154, "global_step": 390099, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0474181175231934, "global_step": 390100, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0841715335845947, "global_step": 390101, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1018919944763184, "global_step": 390102, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1654295921325684, "global_step": 390103, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0424132347106934, "global_step": 390104, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0831971168518066, "global_step": 390105, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0430054664611816, "global_step": 390106, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0919625759124756, "global_step": 390107, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.040830135345459, "global_step": 390108, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1014726161956787, "global_step": 390109, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0316314697265625, "global_step": 390110, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.019355535507202, "global_step": 390111, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0923526287078857, "global_step": 390112, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.127863645553589, "global_step": 390113, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0786921977996826, "global_step": 390114, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.061269760131836, "global_step": 390115, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1556038856506348, "global_step": 390116, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.012929677963257, "global_step": 390117, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.2055633068084717, "global_step": 390118, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.02071213722229, "global_step": 390119, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.043860912322998, "global_step": 390120, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.053194046020508, "global_step": 390121, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0948116779327393, "global_step": 390122, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0732240676879883, "global_step": 390123, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1150803565979004, "global_step": 390124, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.087679147720337, "global_step": 390125, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.074378728866577, "global_step": 390126, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0981805324554443, "global_step": 390127, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1269893646240234, "global_step": 390128, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1072468757629395, "global_step": 390129, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0161688327789307, "global_step": 390130, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1267995834350586, "global_step": 390131, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1677820682525635, "global_step": 390132, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0324907302856445, "global_step": 390133, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.105909585952759, "global_step": 390134, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0766687393188477, "global_step": 390135, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.088301658630371, "global_step": 390136, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.101402759552002, "global_step": 390137, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1987648010253906, "global_step": 390138, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.035306692123413, "global_step": 390139, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1977784633636475, "global_step": 390140, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.144925355911255, "global_step": 390141, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1188955307006836, "global_step": 390142, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.130340337753296, "global_step": 390143, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.097294569015503, "global_step": 390144, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1703577041625977, "global_step": 390145, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.108689308166504, "global_step": 390146, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.141977310180664, "global_step": 390147, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.079791784286499, "global_step": 390148, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.123675584793091, "global_step": 390149, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.069488525390625, "global_step": 390150, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1334474086761475, "global_step": 390151, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.018165111541748, "global_step": 390152, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1866061687469482, "global_step": 390153, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1205506324768066, "global_step": 390154, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.058450698852539, "global_step": 390155, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.034315824508667, "global_step": 390156, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.001490354537964, "global_step": 390157, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.083336114883423, "global_step": 390158, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1063833236694336, "global_step": 390159, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.032069444656372, "global_step": 390160, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.013082981109619, "global_step": 390161, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.172966718673706, "global_step": 390162, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1947450637817383, "global_step": 390163, "epoch": 752, "lr": 5e-05}
{"train_loss": 1.9537312984466553, "global_step": 390164, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.100099563598633, "global_step": 390165, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.073371648788452, "global_step": 390166, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.064152956008911, "global_step": 390167, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.040497303009033, "global_step": 390168, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.105689525604248, "global_step": 390169, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0921483039855957, "global_step": 390170, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.118236780166626, "global_step": 390171, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0933926105499268, "global_step": 390172, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.054771661758423, "global_step": 390173, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1098272800445557, "global_step": 390174, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0818240642547607, "global_step": 390175, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0870563983917236, "global_step": 390176, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1028594970703125, "global_step": 390177, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.119081974029541, "global_step": 390178, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1880156993865967, "global_step": 390179, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1475415229797363, "global_step": 390180, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.002084970474243, "global_step": 390181, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0937376022338867, "global_step": 390182, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1371142864227295, "global_step": 390183, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0535945892333984, "global_step": 390184, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1691782474517822, "global_step": 390185, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.004138708114624, "global_step": 390186, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.045506238937378, "global_step": 390187, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1039669513702393, "global_step": 390188, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0833921432495117, "global_step": 390189, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.10886549949646, "global_step": 390190, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1016032695770264, "global_step": 390191, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.108412027359009, "global_step": 390192, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1232352256774902, "global_step": 390193, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.151641368865967, "global_step": 390194, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0641555786132812, "global_step": 390195, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0929126739501953, "global_step": 390196, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.103208065032959, "global_step": 390197, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.131906270980835, "global_step": 390198, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1083872318267822, "global_step": 390199, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.129772424697876, "global_step": 390200, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1137874126434326, "global_step": 390201, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.119121789932251, "global_step": 390202, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.132305860519409, "global_step": 390203, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.077244520187378, "global_step": 390204, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1010193824768066, "global_step": 390205, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1119470596313477, "global_step": 390206, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1268234252929688, "global_step": 390207, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0465469360351562, "global_step": 390208, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1316184997558594, "global_step": 390209, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0227277278900146, "global_step": 390210, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1338906288146973, "global_step": 390211, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.065157890319824, "global_step": 390212, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.100273609161377, "global_step": 390213, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.150458335876465, "global_step": 390214, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1319692134857178, "global_step": 390215, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.042492151260376, "global_step": 390216, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1312901973724365, "global_step": 390217, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1371378898620605, "global_step": 390218, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1699728965759277, "global_step": 390219, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.066513776779175, "global_step": 390220, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0307044982910156, "global_step": 390221, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0679893493652344, "global_step": 390222, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.050037145614624, "global_step": 390223, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0889928340911865, "global_step": 390224, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0259482860565186, "global_step": 390225, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.128361940383911, "global_step": 390226, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1720454692840576, "global_step": 390227, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1805613040924072, "global_step": 390228, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1051387786865234, "global_step": 390229, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0569162368774414, "global_step": 390230, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1807074546813965, "global_step": 390231, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1427621841430664, "global_step": 390232, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.2297604084014893, "global_step": 390233, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1486785411834717, "global_step": 390234, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.10687255859375, "global_step": 390235, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0786051750183105, "global_step": 390236, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0873894691467285, "global_step": 390237, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1173572540283203, "global_step": 390238, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0994696617126465, "global_step": 390239, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.123995780944824, "global_step": 390240, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1422371864318848, "global_step": 390241, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0636088848114014, "global_step": 390242, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0836963653564453, "global_step": 390243, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1476168632507324, "global_step": 390244, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0940511226654053, "global_step": 390245, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0804898738861084, "global_step": 390246, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.157634735107422, "global_step": 390247, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.134796380996704, "global_step": 390248, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0967040061950684, "global_step": 390249, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1689517498016357, "global_step": 390250, "epoch": 752, "lr": 5e-05}
{"train_loss": 1.9709038734436035, "global_step": 390251, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1553473472595215, "global_step": 390252, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1530323028564453, "global_step": 390253, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.08209490776062, "global_step": 390254, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.110222339630127, "global_step": 390255, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0622055530548096, "global_step": 390256, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.174013614654541, "global_step": 390257, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1706671714782715, "global_step": 390258, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.126944065093994, "global_step": 390259, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0785696506500244, "global_step": 390260, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0752103328704834, "global_step": 390261, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.085418462753296, "global_step": 390262, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0271100997924805, "global_step": 390263, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.057783365249634, "global_step": 390264, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.131448745727539, "global_step": 390265, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.134145498275757, "global_step": 390266, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1515707969665527, "global_step": 390267, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.155071258544922, "global_step": 390268, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1582207679748535, "global_step": 390269, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0331289768218994, "global_step": 390270, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1835110187530518, "global_step": 390271, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.098252534866333, "global_step": 390272, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.130174398422241, "global_step": 390273, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.105968713760376, "global_step": 390274, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0515823364257812, "global_step": 390275, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.11592960357666, "global_step": 390276, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1758110523223877, "global_step": 390277, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.065025568008423, "global_step": 390278, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1897311210632324, "global_step": 390279, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.051723003387451, "global_step": 390280, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.045889377593994, "global_step": 390281, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1503119468688965, "global_step": 390282, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1203949451446533, "global_step": 390283, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1316113471984863, "global_step": 390284, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1204934120178223, "global_step": 390285, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.110776901245117, "global_step": 390286, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.075961112976074, "global_step": 390287, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.042729616165161, "global_step": 390288, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1285178661346436, "global_step": 390289, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.03999924659729, "global_step": 390290, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.072732925415039, "global_step": 390291, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0197227001190186, "global_step": 390292, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.017409086227417, "global_step": 390293, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1544063091278076, "global_step": 390294, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1551616191864014, "global_step": 390295, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0767695903778076, "global_step": 390296, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1088597774505615, "global_step": 390297, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.076509952545166, "global_step": 390298, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.017055034637451, "global_step": 390299, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.137010097503662, "global_step": 390300, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.077566146850586, "global_step": 390301, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0249083042144775, "global_step": 390302, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1370224952697754, "global_step": 390303, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0386834144592285, "global_step": 390304, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1238553524017334, "global_step": 390305, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.07191801071167, "global_step": 390306, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.130849838256836, "global_step": 390307, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.2094578742980957, "global_step": 390308, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.077091693878174, "global_step": 390309, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1474080085754395, "global_step": 390310, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1011595726013184, "global_step": 390311, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1002087593078613, "global_step": 390312, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.172297477722168, "global_step": 390313, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.116773843765259, "global_step": 390314, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.041262626647949, "global_step": 390315, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1234917640686035, "global_step": 390316, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1317663192749023, "global_step": 390317, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.153533697128296, "global_step": 390318, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1011009216308594, "global_step": 390319, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1801364421844482, "global_step": 390320, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1800739765167236, "global_step": 390321, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.134874105453491, "global_step": 390322, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.051337480545044, "global_step": 390323, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1112804412841797, "global_step": 390324, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.117767095565796, "global_step": 390325, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0744991302490234, "global_step": 390326, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0950279235839844, "global_step": 390327, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1023848056793213, "global_step": 390328, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.106299877166748, "global_step": 390329, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0675439834594727, "global_step": 390330, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.127972364425659, "global_step": 390331, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1228041648864746, "global_step": 390332, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0364983081817627, "global_step": 390333, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.091059923171997, "global_step": 390334, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0851616859436035, "global_step": 390335, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.11252760887146, "global_step": 390336, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0308480262756348, "global_step": 390337, "epoch": 752, "lr": 5e-05}
{"train_loss": 1.994429349899292, "global_step": 390338, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1418635845184326, "global_step": 390339, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.140854597091675, "global_step": 390340, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.116091728210449, "global_step": 390341, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0646486282348633, "global_step": 390342, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.171576976776123, "global_step": 390343, "epoch": 752, "lr": 5e-05}
{"train_loss": 1.9771713018417358, "global_step": 390344, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.178274631500244, "global_step": 390345, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1048378944396973, "global_step": 390346, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1579158306121826, "global_step": 390347, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1289501190185547, "global_step": 390348, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.120140314102173, "global_step": 390349, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.153620958328247, "global_step": 390350, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0715487003326416, "global_step": 390351, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.184950113296509, "global_step": 390352, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0321788787841797, "global_step": 390353, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1106984615325928, "global_step": 390354, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.183716058731079, "global_step": 390355, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.167475700378418, "global_step": 390356, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.118051290512085, "global_step": 390357, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.043433904647827, "global_step": 390358, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.163334369659424, "global_step": 390359, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1023294925689697, "global_step": 390360, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1204986572265625, "global_step": 390361, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0211405754089355, "global_step": 390362, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1320769786834717, "global_step": 390363, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1081290245056152, "global_step": 390364, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0722978115081787, "global_step": 390365, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.110020160675049, "global_step": 390366, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.149224281311035, "global_step": 390367, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1604270935058594, "global_step": 390368, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.13022780418396, "global_step": 390369, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.187107801437378, "global_step": 390370, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1069130897521973, "global_step": 390371, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.048916816711426, "global_step": 390372, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.127469301223755, "global_step": 390373, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.135922908782959, "global_step": 390374, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0712687969207764, "global_step": 390375, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1446549892425537, "global_step": 390376, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0835554599761963, "global_step": 390377, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0748212337493896, "global_step": 390378, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.103233575820923, "global_step": 390379, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0835041999816895, "global_step": 390380, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.095607042312622, "global_step": 390381, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.164461612701416, "global_step": 390382, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.063441276550293, "global_step": 390383, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0598719120025635, "global_step": 390384, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0422847270965576, "global_step": 390385, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1399412155151367, "global_step": 390386, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.111384391784668, "global_step": 390387, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.197190999984741, "global_step": 390388, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1164710521698, "global_step": 390389, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0772476196289062, "global_step": 390390, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.11795711517334, "global_step": 390391, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1105618476867676, "global_step": 390392, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1174063682556152, "global_step": 390393, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0350847244262695, "global_step": 390394, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.104358434677124, "global_step": 390395, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.19572114944458, "global_step": 390396, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0285792350769043, "global_step": 390397, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1552889347076416, "global_step": 390398, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1081697940826416, "global_step": 390399, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.069988250732422, "global_step": 390400, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0898380279541016, "global_step": 390401, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.128777503967285, "global_step": 390402, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0648324489593506, "global_step": 390403, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1238632202148438, "global_step": 390404, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0995304584503174, "global_step": 390405, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0967612266540527, "global_step": 390406, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0810155868530273, "global_step": 390407, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.098910331726074, "global_step": 390408, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.294626474380493, "global_step": 390409, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.047795295715332, "global_step": 390410, "epoch": 752, "lr": 5e-05}
{"train_loss": 1.9672821760177612, "global_step": 390411, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.180129289627075, "global_step": 390412, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0358998775482178, "global_step": 390413, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.150074005126953, "global_step": 390414, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.172447681427002, "global_step": 390415, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.193082094192505, "global_step": 390416, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0941145420074463, "global_step": 390417, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1676876544952393, "global_step": 390418, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.031784772872925, "global_step": 390419, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.2343060970306396, "global_step": 390420, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1547014713287354, "global_step": 390421, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.130521535873413, "global_step": 390422, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1163411140441895, "global_step": 390423, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1199839115142822, "global_step": 390424, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0815236568450928, "global_step": 390425, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0748496055603027, "global_step": 390426, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.116638660430908, "global_step": 390427, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1815011501312256, "global_step": 390428, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.11112117767334, "global_step": 390429, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.18156099319458, "global_step": 390430, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0925004482269287, "global_step": 390431, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0488696098327637, "global_step": 390432, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.042625665664673, "global_step": 390433, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0042808055877686, "global_step": 390434, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.100874423980713, "global_step": 390435, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.093031167984009, "global_step": 390436, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.052983045578003, "global_step": 390437, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.09916353225708, "global_step": 390438, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.051278829574585, "global_step": 390439, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.098822593688965, "global_step": 390440, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.12662672996521, "global_step": 390441, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0917439460754395, "global_step": 390442, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.169969081878662, "global_step": 390443, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.061574935913086, "global_step": 390444, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1119496822357178, "global_step": 390445, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1040024757385254, "global_step": 390446, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0134334564208984, "global_step": 390447, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0527496337890625, "global_step": 390448, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.064457893371582, "global_step": 390449, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.051191568374634, "global_step": 390450, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.145216703414917, "global_step": 390451, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0465736389160156, "global_step": 390452, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1529622077941895, "global_step": 390453, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.096862316131592, "global_step": 390454, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1117966175079346, "global_step": 390455, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.113118886947632, "global_step": 390456, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1508290767669678, "global_step": 390457, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.085855722427368, "global_step": 390458, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1583900451660156, "global_step": 390459, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.047039747238159, "global_step": 390460, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1835248470306396, "global_step": 390461, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0532870292663574, "global_step": 390462, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.096693754196167, "global_step": 390463, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1200718879699707, "global_step": 390464, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0356051921844482, "global_step": 390465, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1541824340820312, "global_step": 390466, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1940207481384277, "global_step": 390467, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.103593349456787, "global_step": 390468, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.050873279571533, "global_step": 390469, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.162942409515381, "global_step": 390470, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0818088054656982, "global_step": 390471, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.10524582862854, "global_step": 390472, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0746278762817383, "global_step": 390473, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.126990795135498, "global_step": 390474, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0557761192321777, "global_step": 390475, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.095813751220703, "global_step": 390476, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.129369020462036, "global_step": 390477, "epoch": 752, "lr": 5e-05}
{"train_loss": 1.98383629322052, "global_step": 390478, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.2033560276031494, "global_step": 390479, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.079425811767578, "global_step": 390480, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1638946533203125, "global_step": 390481, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.139796018600464, "global_step": 390482, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.028738021850586, "global_step": 390483, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.071305513381958, "global_step": 390484, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.178640842437744, "global_step": 390485, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.101654052734375, "global_step": 390486, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1713204383850098, "global_step": 390487, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.097838878631592, "global_step": 390488, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1224911212921143, "global_step": 390489, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.111754894256592, "global_step": 390490, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.150747537612915, "global_step": 390491, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.221813440322876, "global_step": 390492, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1378273963928223, "global_step": 390493, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0045595169067383, "global_step": 390494, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.101780414581299, "global_step": 390495, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.056097984313965, "global_step": 390496, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0699868202209473, "global_step": 390497, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1728124618530273, "global_step": 390498, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.038782835006714, "global_step": 390499, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.034790515899658, "global_step": 390500, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0017142295837402, "global_step": 390501, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1881654262542725, "global_step": 390502, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.019251823425293, "global_step": 390503, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0692059993743896, "global_step": 390504, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.130852222442627, "global_step": 390505, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.098935842514038, "global_step": 390506, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.059093475341797, "global_step": 390507, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1321332454681396, "global_step": 390508, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.095029592514038, "global_step": 390509, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1190216541290283, "global_step": 390510, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.162764310836792, "global_step": 390511, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0846781730651855, "global_step": 390512, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.096794366836548, "global_step": 390513, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.073153257369995, "global_step": 390514, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.114431142807007, "global_step": 390515, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0400924682617188, "global_step": 390516, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.090527057647705, "global_step": 390517, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0172274112701416, "global_step": 390518, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.173691749572754, "global_step": 390519, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1818625926971436, "global_step": 390520, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.16017746925354, "global_step": 390521, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.150472640991211, "global_step": 390522, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.073115825653076, "global_step": 390523, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.072598457336426, "global_step": 390524, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.03963565826416, "global_step": 390525, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.053022623062134, "global_step": 390526, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1518399715423584, "global_step": 390527, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.094654083251953, "global_step": 390528, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.165623426437378, "global_step": 390529, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1376030445098877, "global_step": 390530, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0047225952148438, "global_step": 390531, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.103048324584961, "global_step": 390532, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.090334177017212, "global_step": 390533, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1515872478485107, "global_step": 390534, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.168734073638916, "global_step": 390535, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.092494487762451, "global_step": 390536, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.103248357772827, "global_step": 390537, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.054100751876831, "global_step": 390538, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.178166627883911, "global_step": 390539, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1337764263153076, "global_step": 390540, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0538082122802734, "global_step": 390541, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0756914615631104, "global_step": 390542, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0815677642822266, "global_step": 390543, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.079984664916992, "global_step": 390544, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1434881687164307, "global_step": 390545, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0395889282226562, "global_step": 390546, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.063750743865967, "global_step": 390547, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.060145854949951, "global_step": 390548, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.063380718231201, "global_step": 390549, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0790534019470215, "global_step": 390550, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.123039722442627, "global_step": 390551, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0567634105682373, "global_step": 390552, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0614781379699707, "global_step": 390553, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.051776170730591, "global_step": 390554, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0677270889282227, "global_step": 390555, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0159265995025635, "global_step": 390556, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.184248685836792, "global_step": 390557, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.078895330429077, "global_step": 390558, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.035019636154175, "global_step": 390559, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.210054874420166, "global_step": 390560, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1212234497070312, "global_step": 390561, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1217129230499268, "global_step": 390562, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0375475883483887, "global_step": 390563, "epoch": 752, "lr": 5e-05}
{"train_loss": 1.994171142578125, "global_step": 390564, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1533050537109375, "global_step": 390565, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.122406005859375, "global_step": 390566, "epoch": 752, "lr": 5e-05}
{"train_loss": 1.9725499153137207, "global_step": 390567, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.020005464553833, "global_step": 390568, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1521589756011963, "global_step": 390569, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1498289108276367, "global_step": 390570, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0447394847869873, "global_step": 390571, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.137037992477417, "global_step": 390572, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1456265449523926, "global_step": 390573, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0933194160461426, "global_step": 390574, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.045734167098999, "global_step": 390575, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1129672527313232, "global_step": 390576, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.115492820739746, "global_step": 390577, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.041377067565918, "global_step": 390578, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.187804937362671, "global_step": 390579, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.117199182510376, "global_step": 390580, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.054492712020874, "global_step": 390581, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1640493869781494, "global_step": 390582, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1355061531066895, "global_step": 390583, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.059629201889038, "global_step": 390584, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.113483428955078, "global_step": 390585, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1294655799865723, "global_step": 390586, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0768351554870605, "global_step": 390587, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.085002899169922, "global_step": 390588, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.127072334289551, "global_step": 390589, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0608363151550293, "global_step": 390590, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.2107677459716797, "global_step": 390591, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.054128646850586, "global_step": 390592, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0961875915527344, "global_step": 390593, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.126662015914917, "global_step": 390594, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1189098358154297, "global_step": 390595, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.2012951374053955, "global_step": 390596, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1201376914978027, "global_step": 390597, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0493714809417725, "global_step": 390598, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1189751625061035, "global_step": 390599, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.150820016860962, "global_step": 390600, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1662678718566895, "global_step": 390601, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0762362480163574, "global_step": 390602, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1059978008270264, "global_step": 390603, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.063244342803955, "global_step": 390604, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.077003240585327, "global_step": 390605, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0596258640289307, "global_step": 390606, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1407763957977295, "global_step": 390607, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.112895965576172, "global_step": 390608, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.034613609313965, "global_step": 390609, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.107407808303833, "global_step": 390610, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1009037494659424, "global_step": 390611, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1294336318969727, "global_step": 390612, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1311452388763428, "global_step": 390613, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1037425994873047, "global_step": 390614, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0023322105407715, "global_step": 390615, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1041266918182373, "global_step": 390616, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1643776893615723, "global_step": 390617, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0712945461273193, "global_step": 390618, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.084868907928467, "global_step": 390619, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1215386390686035, "global_step": 390620, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.129587411880493, "global_step": 390621, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1185507774353027, "global_step": 390622, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.116772174835205, "global_step": 390623, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1572422981262207, "global_step": 390624, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0416388511657715, "global_step": 390625, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1461052894592285, "global_step": 390626, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0734128952026367, "global_step": 390627, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.125173330307007, "global_step": 390628, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.178826332092285, "global_step": 390629, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1503379344940186, "global_step": 390630, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1820068359375, "global_step": 390631, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.133016586303711, "global_step": 390632, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1624839305877686, "global_step": 390633, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.113978862762451, "global_step": 390634, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.070969820022583, "global_step": 390635, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0956850051879883, "global_step": 390636, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.1795589923858643, "global_step": 390637, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0661895275115967, "global_step": 390638, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.0999038219451904, "global_step": 390639, "epoch": 752, "lr": 5e-05}
{"train_loss": 2.064065456390381, "global_step": 390640, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1297197341918945, "global_step": 390641, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0550549030303955, "global_step": 390642, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.071881055831909, "global_step": 390643, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.09578013420105, "global_step": 390644, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0455172061920166, "global_step": 390645, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0594940185546875, "global_step": 390646, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.119856834411621, "global_step": 390647, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.057453155517578, "global_step": 390648, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.047100782394409, "global_step": 390649, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0856733322143555, "global_step": 390650, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.144918203353882, "global_step": 390651, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1526832580566406, "global_step": 390652, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.05938458442688, "global_step": 390653, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0202813148498535, "global_step": 390654, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.156430244445801, "global_step": 390655, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0271875858306885, "global_step": 390656, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1219301223754883, "global_step": 390657, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0851898193359375, "global_step": 390658, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0441856384277344, "global_step": 390659, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.019526958465576, "global_step": 390660, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.115041971206665, "global_step": 390661, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.065270185470581, "global_step": 390662, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.143629789352417, "global_step": 390663, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0338833332061768, "global_step": 390664, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.013542890548706, "global_step": 390665, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0498239994049072, "global_step": 390666, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1701903343200684, "global_step": 390667, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0867934226989746, "global_step": 390668, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1165013313293457, "global_step": 390669, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0735843181610107, "global_step": 390670, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1185343265533447, "global_step": 390671, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0858283042907715, "global_step": 390672, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0827877521514893, "global_step": 390673, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2205777168273926, "global_step": 390674, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1654276847839355, "global_step": 390675, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.050450086593628, "global_step": 390676, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0532844066619873, "global_step": 390677, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0939531326293945, "global_step": 390678, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1062583923339844, "global_step": 390679, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.107513904571533, "global_step": 390680, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.113067626953125, "global_step": 390681, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0838541984558105, "global_step": 390682, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.112903118133545, "global_step": 390683, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1666131019592285, "global_step": 390684, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1682522296905518, "global_step": 390685, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.092982053756714, "global_step": 390686, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.110619306564331, "global_step": 390687, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0739548206329346, "global_step": 390688, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0326733589172363, "global_step": 390689, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.011556625366211, "global_step": 390690, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0472424030303955, "global_step": 390691, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2279908657073975, "global_step": 390692, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.09287428855896, "global_step": 390693, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.084111213684082, "global_step": 390694, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.093264579772949, "global_step": 390695, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1262741088867188, "global_step": 390696, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1907453536987305, "global_step": 390697, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.089735984802246, "global_step": 390698, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.006913900375366, "global_step": 390699, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0742111206054688, "global_step": 390700, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1090779304504395, "global_step": 390701, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1130645275115967, "global_step": 390702, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0892324447631836, "global_step": 390703, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.144274950027466, "global_step": 390704, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1127755641937256, "global_step": 390705, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1192545890808105, "global_step": 390706, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0357015132904053, "global_step": 390707, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0286364555358887, "global_step": 390708, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0418808460235596, "global_step": 390709, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0832033157348633, "global_step": 390710, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.036238431930542, "global_step": 390711, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1181111335754395, "global_step": 390712, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0803589820861816, "global_step": 390713, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0711076259613037, "global_step": 390714, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.9872362613677979, "global_step": 390715, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1008687019348145, "global_step": 390716, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.084338426589966, "global_step": 390717, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1295113563537598, "global_step": 390718, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.079488515853882, "global_step": 390719, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0999655723571777, "global_step": 390720, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0747945308685303, "global_step": 390721, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.057708978652954, "global_step": 390722, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0684709548950195, "global_step": 390723, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.13315486907959, "global_step": 390724, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0252885818481445, "global_step": 390725, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0892584323883057, "global_step": 390726, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.128458261489868, "global_step": 390727, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1243693828582764, "global_step": 390728, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.05648136138916, "global_step": 390729, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.078559637069702, "global_step": 390730, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.096067428588867, "global_step": 390731, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0556764602661133, "global_step": 390732, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.083599090576172, "global_step": 390733, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0945725440979004, "global_step": 390734, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.084881067276001, "global_step": 390735, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0486795902252197, "global_step": 390736, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0371270179748535, "global_step": 390737, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.061175584793091, "global_step": 390738, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1237213611602783, "global_step": 390739, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.09416127204895, "global_step": 390740, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.063140630722046, "global_step": 390741, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.081132173538208, "global_step": 390742, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1750144958496094, "global_step": 390743, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0972983837127686, "global_step": 390744, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1428275108337402, "global_step": 390745, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1010289192199707, "global_step": 390746, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.13303804397583, "global_step": 390747, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1434166431427, "global_step": 390748, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0974085330963135, "global_step": 390749, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.158994436264038, "global_step": 390750, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.075389862060547, "global_step": 390751, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0415995121002197, "global_step": 390752, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.133427858352661, "global_step": 390753, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.089869499206543, "global_step": 390754, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1621346473693848, "global_step": 390755, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1219522953033447, "global_step": 390756, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.090959072113037, "global_step": 390757, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0836355686187744, "global_step": 390758, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.041689395904541, "global_step": 390759, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.031323194503784, "global_step": 390760, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2029976844787598, "global_step": 390761, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.169382095336914, "global_step": 390762, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1450295448303223, "global_step": 390763, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.11889386177063, "global_step": 390764, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0388612747192383, "global_step": 390765, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1429455280303955, "global_step": 390766, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1040143966674805, "global_step": 390767, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0086829662323, "global_step": 390768, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1861367225646973, "global_step": 390769, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.112520456314087, "global_step": 390770, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.976230263710022, "global_step": 390771, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0704853534698486, "global_step": 390772, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0927574634552, "global_step": 390773, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0542521476745605, "global_step": 390774, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.153874158859253, "global_step": 390775, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1412909030914307, "global_step": 390776, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.045051097869873, "global_step": 390777, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1278536319732666, "global_step": 390778, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0165607929229736, "global_step": 390779, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1742990016937256, "global_step": 390780, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.038635492324829, "global_step": 390781, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.043030023574829, "global_step": 390782, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.046143054962158, "global_step": 390783, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.079277753829956, "global_step": 390784, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1010756492614746, "global_step": 390785, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.046429395675659, "global_step": 390786, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.113105297088623, "global_step": 390787, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.063915252685547, "global_step": 390788, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0683934688568115, "global_step": 390789, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.115403890609741, "global_step": 390790, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1092758178710938, "global_step": 390791, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.006822109222412, "global_step": 390792, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2254221439361572, "global_step": 390793, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0768282413482666, "global_step": 390794, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1565864086151123, "global_step": 390795, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0941450595855713, "global_step": 390796, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.03513765335083, "global_step": 390797, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1176795959472656, "global_step": 390798, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0581538677215576, "global_step": 390799, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1282856464385986, "global_step": 390800, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0236988067626953, "global_step": 390801, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1031391620635986, "global_step": 390802, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1483137607574463, "global_step": 390803, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0767016410827637, "global_step": 390804, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1282379627227783, "global_step": 390805, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.032928466796875, "global_step": 390806, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.091867685317993, "global_step": 390807, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1098053455352783, "global_step": 390808, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.148557424545288, "global_step": 390809, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1302361488342285, "global_step": 390810, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0813026428222656, "global_step": 390811, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.138010025024414, "global_step": 390812, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.032740592956543, "global_step": 390813, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0057079792022705, "global_step": 390814, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0864181518554688, "global_step": 390815, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0446460247039795, "global_step": 390816, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1627297401428223, "global_step": 390817, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.159646511077881, "global_step": 390818, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.071847438812256, "global_step": 390819, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1400644779205322, "global_step": 390820, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1676392555236816, "global_step": 390821, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0552961826324463, "global_step": 390822, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1115732192993164, "global_step": 390823, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1485087871551514, "global_step": 390824, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.055941581726074, "global_step": 390825, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.091057538986206, "global_step": 390826, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.166259527206421, "global_step": 390827, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.11649751663208, "global_step": 390828, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1003692150115967, "global_step": 390829, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.027017116546631, "global_step": 390830, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1211814880371094, "global_step": 390831, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0732221603393555, "global_step": 390832, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.014488458633423, "global_step": 390833, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.103902816772461, "global_step": 390834, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.9741259813308716, "global_step": 390835, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.186788558959961, "global_step": 390836, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1066269874572754, "global_step": 390837, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.114936113357544, "global_step": 390838, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1270172595977783, "global_step": 390839, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0049827098846436, "global_step": 390840, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.046193838119507, "global_step": 390841, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0433990955352783, "global_step": 390842, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1296658515930176, "global_step": 390843, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1022112369537354, "global_step": 390844, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1042215824127197, "global_step": 390845, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0259063243865967, "global_step": 390846, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0959293842315674, "global_step": 390847, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1168527603149414, "global_step": 390848, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.16996169090271, "global_step": 390849, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1257271766662598, "global_step": 390850, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0619726181030273, "global_step": 390851, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1273107528686523, "global_step": 390852, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.018662214279175, "global_step": 390853, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0624747276306152, "global_step": 390854, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1542932987213135, "global_step": 390855, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1243340969085693, "global_step": 390856, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1439499855041504, "global_step": 390857, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.102776050567627, "global_step": 390858, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1130590438842773, "global_step": 390859, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2124998569488525, "global_step": 390860, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.079165458679199, "global_step": 390861, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.056149959564209, "global_step": 390862, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0737719535827637, "global_step": 390863, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0641603469848633, "global_step": 390864, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.137394666671753, "global_step": 390865, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.9983805418014526, "global_step": 390866, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0929534435272217, "global_step": 390867, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1202831268310547, "global_step": 390868, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.042037010192871, "global_step": 390869, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.072286367416382, "global_step": 390870, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0389766693115234, "global_step": 390871, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1265933513641357, "global_step": 390872, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0386593341827393, "global_step": 390873, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1412065029144287, "global_step": 390874, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0401651859283447, "global_step": 390875, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.089425802230835, "global_step": 390876, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.025275707244873, "global_step": 390877, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.042849063873291, "global_step": 390878, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1308226585388184, "global_step": 390879, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1351892948150635, "global_step": 390880, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0663864612579346, "global_step": 390881, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0714824199676514, "global_step": 390882, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1146740913391113, "global_step": 390883, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.088970899581909, "global_step": 390884, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.025738477706909, "global_step": 390885, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.097271203994751, "global_step": 390886, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.096510410308838, "global_step": 390887, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.040972948074341, "global_step": 390888, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.9769566059112549, "global_step": 390889, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.015475273132324, "global_step": 390890, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0893735885620117, "global_step": 390891, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0962307453155518, "global_step": 390892, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.176633596420288, "global_step": 390893, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1176302433013916, "global_step": 390894, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.211670398712158, "global_step": 390895, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.077972412109375, "global_step": 390896, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.118703842163086, "global_step": 390897, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.074598550796509, "global_step": 390898, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.00203537940979, "global_step": 390899, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0875463485717773, "global_step": 390900, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.025590181350708, "global_step": 390901, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.065068006515503, "global_step": 390902, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.168508291244507, "global_step": 390903, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1221423149108887, "global_step": 390904, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.039156913757324, "global_step": 390905, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1156091690063477, "global_step": 390906, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0298516750335693, "global_step": 390907, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0583555698394775, "global_step": 390908, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.043562412261963, "global_step": 390909, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0703213214874268, "global_step": 390910, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1024813652038574, "global_step": 390911, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1853036880493164, "global_step": 390912, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.16865873336792, "global_step": 390913, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1496002674102783, "global_step": 390914, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1105732917785645, "global_step": 390915, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.07607102394104, "global_step": 390916, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.102339506149292, "global_step": 390917, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0702099800109863, "global_step": 390918, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1830732822418213, "global_step": 390919, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.111741781234741, "global_step": 390920, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.200512409210205, "global_step": 390921, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0731277465820312, "global_step": 390922, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.104856252670288, "global_step": 390923, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.071125030517578, "global_step": 390924, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.052216053009033, "global_step": 390925, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.073214292526245, "global_step": 390926, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.064896583557129, "global_step": 390927, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.06005597114563, "global_step": 390928, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0874714851379395, "global_step": 390929, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0991904735565186, "global_step": 390930, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1697161197662354, "global_step": 390931, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1034140586853027, "global_step": 390932, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0903289318084717, "global_step": 390933, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1399645805358887, "global_step": 390934, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1318295001983643, "global_step": 390935, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1120107173919678, "global_step": 390936, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0902340412139893, "global_step": 390937, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.964369773864746, "global_step": 390938, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1519691944122314, "global_step": 390939, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.998565673828125, "global_step": 390940, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.123749017715454, "global_step": 390941, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1854710578918457, "global_step": 390942, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0985093116760254, "global_step": 390943, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1830458641052246, "global_step": 390944, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.098154306411743, "global_step": 390945, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.05527400970459, "global_step": 390946, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.088613271713257, "global_step": 390947, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1135377883911133, "global_step": 390948, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0884716510772705, "global_step": 390949, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.9936304092407227, "global_step": 390950, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.083646297454834, "global_step": 390951, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1258704662323, "global_step": 390952, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.075937271118164, "global_step": 390953, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.084420919418335, "global_step": 390954, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0761964321136475, "global_step": 390955, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0937323570251465, "global_step": 390956, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1178107261657715, "global_step": 390957, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0458858013153076, "global_step": 390958, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0647265911102295, "global_step": 390959, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.054457187652588, "global_step": 390960, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1663553714752197, "global_step": 390961, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.197115898132324, "global_step": 390962, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.136221170425415, "global_step": 390963, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0633187294006348, "global_step": 390964, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0985934734344482, "global_step": 390965, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0990307331085205, "global_step": 390966, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.022007465362549, "global_step": 390967, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.043269395828247, "global_step": 390968, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.094320774078369, "global_step": 390969, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.069974184036255, "global_step": 390970, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0425970554351807, "global_step": 390971, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1743175983428955, "global_step": 390972, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0254809856414795, "global_step": 390973, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.994279146194458, "global_step": 390974, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.106606960296631, "global_step": 390975, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.067415952682495, "global_step": 390976, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1082491874694824, "global_step": 390977, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0869438648223877, "global_step": 390978, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.165515422821045, "global_step": 390979, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.084733247756958, "global_step": 390980, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0455098152160645, "global_step": 390981, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.111549139022827, "global_step": 390982, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.050295352935791, "global_step": 390983, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0180301666259766, "global_step": 390984, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1023380756378174, "global_step": 390985, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1151983737945557, "global_step": 390986, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.169889450073242, "global_step": 390987, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1430013179779053, "global_step": 390988, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.069751024246216, "global_step": 390989, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.089585542678833, "global_step": 390990, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1296286582946777, "global_step": 390991, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0898120403289795, "global_step": 390992, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0114898681640625, "global_step": 390993, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1310946941375732, "global_step": 390994, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.140805244445801, "global_step": 390995, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0913844108581543, "global_step": 390996, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1325345039367676, "global_step": 390997, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1886401176452637, "global_step": 390998, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1188724040985107, "global_step": 390999, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0478405952453613, "global_step": 391000, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0860183238983154, "global_step": 391001, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0847129821777344, "global_step": 391002, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.104804277420044, "global_step": 391003, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1715641021728516, "global_step": 391004, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.096196413040161, "global_step": 391005, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.136451244354248, "global_step": 391006, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.084524393081665, "global_step": 391007, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0675055980682373, "global_step": 391008, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.062053680419922, "global_step": 391009, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1561968326568604, "global_step": 391010, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1356632709503174, "global_step": 391011, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0565223693847656, "global_step": 391012, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0207672119140625, "global_step": 391013, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2007362842559814, "global_step": 391014, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1292617321014404, "global_step": 391015, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0232956409454346, "global_step": 391016, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0232093334198, "global_step": 391017, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.074615001678467, "global_step": 391018, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.140549898147583, "global_step": 391019, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.054593324661255, "global_step": 391020, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0750045776367188, "global_step": 391021, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0977814197540283, "global_step": 391022, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1062419414520264, "global_step": 391023, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0589654445648193, "global_step": 391024, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.161193370819092, "global_step": 391025, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2165110111236572, "global_step": 391026, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.050293207168579, "global_step": 391027, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0806894302368164, "global_step": 391028, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0240156650543213, "global_step": 391029, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.107720375061035, "global_step": 391030, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0400848388671875, "global_step": 391031, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2229254245758057, "global_step": 391032, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.117530345916748, "global_step": 391033, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0655558109283447, "global_step": 391034, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1267359256744385, "global_step": 391035, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0752110481262207, "global_step": 391036, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1106972694396973, "global_step": 391037, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.105346202850342, "global_step": 391038, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0950210094451904, "global_step": 391039, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.084059000015259, "global_step": 391040, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0606231689453125, "global_step": 391041, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0372607707977295, "global_step": 391042, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0903656482696533, "global_step": 391043, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.9810768365859985, "global_step": 391044, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.070435047149658, "global_step": 391045, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1099495887756348, "global_step": 391046, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1971254348754883, "global_step": 391047, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.03572678565979, "global_step": 391048, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.124607563018799, "global_step": 391049, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0933573246002197, "global_step": 391050, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0413780212402344, "global_step": 391051, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0620203018188477, "global_step": 391052, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0146450996398926, "global_step": 391053, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0293877124786377, "global_step": 391054, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.076765775680542, "global_step": 391055, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1389849185943604, "global_step": 391056, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.058851718902588, "global_step": 391057, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.090269088745117, "global_step": 391058, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.021920680999756, "global_step": 391059, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.095418691635132, "global_step": 391060, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0906238555908203, "global_step": 391061, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1237435340881348, "global_step": 391062, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.044966697692871, "global_step": 391063, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.030529737472534, "global_step": 391064, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0583431720733643, "global_step": 391065, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0845978260040283, "global_step": 391066, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1015257835388184, "global_step": 391067, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0328636169433594, "global_step": 391068, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1388795375823975, "global_step": 391069, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1096444129943848, "global_step": 391070, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.091904640197754, "global_step": 391071, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0089762210845947, "global_step": 391072, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0931708812713623, "global_step": 391073, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0282788276672363, "global_step": 391074, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.089634895324707, "global_step": 391075, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.146893262863159, "global_step": 391076, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0250463485717773, "global_step": 391077, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.051438808441162, "global_step": 391078, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1009862422943115, "global_step": 391079, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1150124073028564, "global_step": 391080, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0933737754821777, "global_step": 391081, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.167632579803467, "global_step": 391082, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1570372581481934, "global_step": 391083, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.127223491668701, "global_step": 391084, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0989232063293457, "global_step": 391085, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0072338581085205, "global_step": 391086, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0941765308380127, "global_step": 391087, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.039191722869873, "global_step": 391088, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1394269466400146, "global_step": 391089, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1751644611358643, "global_step": 391090, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.12933611869812, "global_step": 391091, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1853442192077637, "global_step": 391092, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.014233350753784, "global_step": 391093, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0703539848327637, "global_step": 391094, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.085468292236328, "global_step": 391095, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.133382558822632, "global_step": 391096, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.032640218734741, "global_step": 391097, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.114943027496338, "global_step": 391098, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.14591646194458, "global_step": 391099, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.136871814727783, "global_step": 391100, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.033159017562866, "global_step": 391101, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.142843008041382, "global_step": 391102, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1696298122406006, "global_step": 391103, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0461580753326416, "global_step": 391104, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.098426342010498, "global_step": 391105, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1293270587921143, "global_step": 391106, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1267435550689697, "global_step": 391107, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.180229902267456, "global_step": 391108, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1778814792633057, "global_step": 391109, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.046349287033081, "global_step": 391110, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0938799381256104, "global_step": 391111, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0375325679779053, "global_step": 391112, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.016434907913208, "global_step": 391113, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.150449752807617, "global_step": 391114, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1090614795684814, "global_step": 391115, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.11403751373291, "global_step": 391116, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0364058017730713, "global_step": 391117, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.096328020095825, "global_step": 391118, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0921850204467773, "global_step": 391119, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.144158363342285, "global_step": 391120, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.183429479598999, "global_step": 391121, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.03427791595459, "global_step": 391122, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0939712524414062, "global_step": 391123, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0776805877685547, "global_step": 391124, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1381399631500244, "global_step": 391125, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1474850177764893, "global_step": 391126, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.012443780899048, "global_step": 391127, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0756404399871826, "global_step": 391128, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1116480827331543, "global_step": 391129, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.118321180343628, "global_step": 391130, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1489579677581787, "global_step": 391131, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0803210735321045, "global_step": 391132, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.131427049636841, "global_step": 391133, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.100818157196045, "global_step": 391134, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.211495876312256, "global_step": 391135, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.09944748878479, "global_step": 391136, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0592403411865234, "global_step": 391137, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0969152450561523, "global_step": 391138, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1536011695861816, "global_step": 391139, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.123065948486328, "global_step": 391140, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0902552604675293, "global_step": 391141, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0287723541259766, "global_step": 391142, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2155027389526367, "global_step": 391143, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0798044204711914, "global_step": 391144, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1596057415008545, "global_step": 391145, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.024142265319824, "global_step": 391146, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.130369186401367, "global_step": 391147, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0592052936553955, "global_step": 391148, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.9334664344787598, "global_step": 391149, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1565589904785156, "global_step": 391150, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0817224979400635, "global_step": 391151, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.087604284286499, "global_step": 391152, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.064058303833008, "global_step": 391153, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1622729301452637, "global_step": 391154, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1453115940093994, "global_step": 391155, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.09504771232605, "global_step": 391156, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.023894786834717, "global_step": 391157, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.074507236480713, "global_step": 391158, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.154062271118164, "global_step": 391159, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0468075275421143, "global_step": 391160, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.059257984161377, "global_step": 391161, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0174357891082764, "global_step": 391162, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.194904327392578, "global_step": 391163, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.13682222366333, "global_step": 391164, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1168572902679443, "global_step": 391165, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0643157958984375, "global_step": 391166, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1401686668395996, "global_step": 391167, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.138956069946289, "global_step": 391168, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0818276405334473, "global_step": 391169, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.148740291595459, "global_step": 391170, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.028721809387207, "global_step": 391171, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.01232647895813, "global_step": 391172, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.089012384414673, "global_step": 391173, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.169114112854004, "global_step": 391174, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1658687591552734, "global_step": 391175, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1454882621765137, "global_step": 391176, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2063486576080322, "global_step": 391177, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.166161060333252, "global_step": 391178, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.152250051498413, "global_step": 391179, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1323084831237793, "global_step": 391180, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.036262273788452, "global_step": 391181, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0570712089538574, "global_step": 391182, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.095214605331421, "global_step": 391183, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.162846088409424, "global_step": 391184, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0310490131378174, "global_step": 391185, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.059720277786255, "global_step": 391186, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.171480894088745, "global_step": 391187, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.100466728210449, "global_step": 391188, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1170551776885986, "global_step": 391189, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1202385425567627, "global_step": 391190, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.12623929977417, "global_step": 391191, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.071249485015869, "global_step": 391192, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0502400398254395, "global_step": 391193, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0664894580841064, "global_step": 391194, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0711355209350586, "global_step": 391195, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0880706310272217, "global_step": 391196, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0682544708251953, "global_step": 391197, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1195216178894043, "global_step": 391198, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.062703847885132, "global_step": 391199, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.051941394805908, "global_step": 391200, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0549349784851074, "global_step": 391201, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.9850378036499023, "global_step": 391202, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0946576595306396, "global_step": 391203, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1761507987976074, "global_step": 391204, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.056013345718384, "global_step": 391205, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1896183490753174, "global_step": 391206, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1612348556518555, "global_step": 391207, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1243889331817627, "global_step": 391208, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.074007511138916, "global_step": 391209, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.12650465965271, "global_step": 391210, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.199169635772705, "global_step": 391211, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.977363109588623, "global_step": 391212, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2179043292999268, "global_step": 391213, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1073904037475586, "global_step": 391214, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.172929525375366, "global_step": 391215, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0473766326904297, "global_step": 391216, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.158282518386841, "global_step": 391217, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.022247552871704, "global_step": 391218, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1313562393188477, "global_step": 391219, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0444321632385254, "global_step": 391220, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.116590976715088, "global_step": 391221, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0557267665863037, "global_step": 391222, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0901880264282227, "global_step": 391223, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0288987159729004, "global_step": 391224, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.056461811065674, "global_step": 391225, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2199058532714844, "global_step": 391226, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.030939817428589, "global_step": 391227, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.14312744140625, "global_step": 391228, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1639978885650635, "global_step": 391229, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.089479446411133, "global_step": 391230, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.080425500869751, "global_step": 391231, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.153660297393799, "global_step": 391232, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.151580572128296, "global_step": 391233, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0256779193878174, "global_step": 391234, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.080333709716797, "global_step": 391235, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0430006980895996, "global_step": 391236, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2034225463867188, "global_step": 391237, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.093006134033203, "global_step": 391238, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1652653217315674, "global_step": 391239, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1395978927612305, "global_step": 391240, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1277177333831787, "global_step": 391241, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0986483097076416, "global_step": 391242, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0452823638916016, "global_step": 391243, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0782458782196045, "global_step": 391244, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.099670886993408, "global_step": 391245, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.199843645095825, "global_step": 391246, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.090245008468628, "global_step": 391247, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.133596181869507, "global_step": 391248, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.153107166290283, "global_step": 391249, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.073119640350342, "global_step": 391250, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1174068450927734, "global_step": 391251, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0729546546936035, "global_step": 391252, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0851123332977295, "global_step": 391253, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.137359619140625, "global_step": 391254, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0694050788879395, "global_step": 391255, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0335896015167236, "global_step": 391256, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1656713485717773, "global_step": 391257, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.112238883972168, "global_step": 391258, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0724494457244873, "global_step": 391259, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1874377727508545, "global_step": 391260, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0658180713653564, "global_step": 391261, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0572242736816406, "global_step": 391262, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.09509539604187, "global_step": 391263, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1578004360198975, "global_step": 391264, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.136554479598999, "global_step": 391265, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1251513957977295, "global_step": 391266, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.071061134338379, "global_step": 391267, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1454155445098877, "global_step": 391268, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.155418872833252, "global_step": 391269, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1418838500976562, "global_step": 391270, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1017489433288574, "global_step": 391271, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1114413738250732, "global_step": 391272, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1263341903686523, "global_step": 391273, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.053060293197632, "global_step": 391274, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.106266975402832, "global_step": 391275, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.107266426086426, "global_step": 391276, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.095564842224121, "global_step": 391277, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0931782722473145, "global_step": 391278, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.064135789871216, "global_step": 391279, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0917162895202637, "global_step": 391280, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.156972885131836, "global_step": 391281, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1398768424987793, "global_step": 391282, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.052361249923706, "global_step": 391283, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0303235054016113, "global_step": 391284, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1192374229431152, "global_step": 391285, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2077345848083496, "global_step": 391286, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1149282455444336, "global_step": 391287, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.213636875152588, "global_step": 391288, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.122511863708496, "global_step": 391289, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0665457248687744, "global_step": 391290, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.187666654586792, "global_step": 391291, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.077453136444092, "global_step": 391292, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.232363224029541, "global_step": 391293, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.089304208755493, "global_step": 391294, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2318902015686035, "global_step": 391295, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.060335636138916, "global_step": 391296, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1636412143707275, "global_step": 391297, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0738227367401123, "global_step": 391298, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1202521324157715, "global_step": 391299, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1719970703125, "global_step": 391300, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.09006404876709, "global_step": 391301, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.073352575302124, "global_step": 391302, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1153833866119385, "global_step": 391303, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.129634141921997, "global_step": 391304, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.105621814727783, "global_step": 391305, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.120028495788574, "global_step": 391306, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1653037071228027, "global_step": 391307, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.123430013656616, "global_step": 391308, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0947723388671875, "global_step": 391309, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.148792266845703, "global_step": 391310, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0953378677368164, "global_step": 391311, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.091294288635254, "global_step": 391312, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1879959106445312, "global_step": 391313, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.013871192932129, "global_step": 391314, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.155359983444214, "global_step": 391315, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0456721782684326, "global_step": 391316, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1285831928253174, "global_step": 391317, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.072970151901245, "global_step": 391318, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1053407192230225, "global_step": 391319, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.058922052383423, "global_step": 391320, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0049896240234375, "global_step": 391321, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1082041263580322, "global_step": 391322, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.062260866165161, "global_step": 391323, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.139296770095825, "global_step": 391324, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1299965381622314, "global_step": 391325, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.098444700241089, "global_step": 391326, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1099300384521484, "global_step": 391327, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2299551963806152, "global_step": 391328, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1071224212646484, "global_step": 391329, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0782394409179688, "global_step": 391330, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0942392349243164, "global_step": 391331, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1683173179626465, "global_step": 391332, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.066615581512451, "global_step": 391333, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.053210973739624, "global_step": 391334, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.107795000076294, "global_step": 391335, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0909371376037598, "global_step": 391336, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2646982669830322, "global_step": 391337, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2007930278778076, "global_step": 391338, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1208980083465576, "global_step": 391339, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0507736206054688, "global_step": 391340, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.130225658416748, "global_step": 391341, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.108786106109619, "global_step": 391342, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1151888370513916, "global_step": 391343, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1015379428863525, "global_step": 391344, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1316442489624023, "global_step": 391345, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.123833656311035, "global_step": 391346, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0378196239471436, "global_step": 391347, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.064572811126709, "global_step": 391348, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.078115463256836, "global_step": 391349, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.044445037841797, "global_step": 391350, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1086995601654053, "global_step": 391351, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.111332416534424, "global_step": 391352, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0894505977630615, "global_step": 391353, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.003355026245117, "global_step": 391354, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0735766887664795, "global_step": 391355, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1032748222351074, "global_step": 391356, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0579614639282227, "global_step": 391357, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.133143901824951, "global_step": 391358, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.089651107788086, "global_step": 391359, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0247018337249756, "global_step": 391360, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.092463731765747, "global_step": 391361, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1283721923828125, "global_step": 391362, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.210347890853882, "global_step": 391363, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.9954674243927002, "global_step": 391364, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1846916675567627, "global_step": 391365, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1329874992370605, "global_step": 391366, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.122663974761963, "global_step": 391367, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.9710060358047485, "global_step": 391368, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0999226570129395, "global_step": 391369, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.037078619003296, "global_step": 391370, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1784257888793945, "global_step": 391371, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1488986015319824, "global_step": 391372, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1287829875946045, "global_step": 391373, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0807294845581055, "global_step": 391374, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2258667945861816, "global_step": 391375, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0979628562927246, "global_step": 391376, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.125303268432617, "global_step": 391377, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.123729944229126, "global_step": 391378, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0643389225006104, "global_step": 391379, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1189017295837402, "global_step": 391380, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0841119289398193, "global_step": 391381, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.153974771499634, "global_step": 391382, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.06384539604187, "global_step": 391383, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.10856294631958, "global_step": 391384, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0895650386810303, "global_step": 391385, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1615052223205566, "global_step": 391386, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0986361503601074, "global_step": 391387, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0798702239990234, "global_step": 391388, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0601112842559814, "global_step": 391389, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.116436243057251, "global_step": 391390, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.145977020263672, "global_step": 391391, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2098355293273926, "global_step": 391392, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.073570489883423, "global_step": 391393, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1191959381103516, "global_step": 391394, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0781705379486084, "global_step": 391395, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.129082679748535, "global_step": 391396, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.06243896484375, "global_step": 391397, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.100116014480591, "global_step": 391398, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0884876251220703, "global_step": 391399, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0378506183624268, "global_step": 391400, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2188050746917725, "global_step": 391401, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.088911771774292, "global_step": 391402, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.232805013656616, "global_step": 391403, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.075417995452881, "global_step": 391404, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.025383949279785, "global_step": 391405, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.097583055496216, "global_step": 391406, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.039505958557129, "global_step": 391407, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1749725341796875, "global_step": 391408, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1390531063079834, "global_step": 391409, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1665408611297607, "global_step": 391410, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0732994079589844, "global_step": 391411, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.071016788482666, "global_step": 391412, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2361669540405273, "global_step": 391413, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0999531745910645, "global_step": 391414, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.098679780960083, "global_step": 391415, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.056133508682251, "global_step": 391416, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.116225481033325, "global_step": 391417, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.18338680267334, "global_step": 391418, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.103990316390991, "global_step": 391419, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.049471139907837, "global_step": 391420, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1772942543029785, "global_step": 391421, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0270931720733643, "global_step": 391422, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0632483959198, "global_step": 391423, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.099095582962036, "global_step": 391424, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.199873924255371, "global_step": 391425, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.029799222946167, "global_step": 391426, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0968856811523438, "global_step": 391427, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0942723751068115, "global_step": 391428, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.086668014526367, "global_step": 391429, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0245795249938965, "global_step": 391430, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1563596725463867, "global_step": 391431, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1363308429718018, "global_step": 391432, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.117980480194092, "global_step": 391433, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.097853660583496, "global_step": 391434, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.9818992614746094, "global_step": 391435, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1310207843780518, "global_step": 391436, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1403398513793945, "global_step": 391437, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0198769569396973, "global_step": 391438, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.027723550796509, "global_step": 391439, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1693756580352783, "global_step": 391440, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2044403553009033, "global_step": 391441, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1230263710021973, "global_step": 391442, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1386122703552246, "global_step": 391443, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.15866756439209, "global_step": 391444, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0772595405578613, "global_step": 391445, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0439634323120117, "global_step": 391446, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1369621753692627, "global_step": 391447, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1321706771850586, "global_step": 391448, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.105241060256958, "global_step": 391449, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0839009284973145, "global_step": 391450, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.230811834335327, "global_step": 391451, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.108093738555908, "global_step": 391452, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0452258586883545, "global_step": 391453, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0915181636810303, "global_step": 391454, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1810104846954346, "global_step": 391455, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0999605655670166, "global_step": 391456, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.024080514907837, "global_step": 391457, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.167940855026245, "global_step": 391458, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.117851495742798, "global_step": 391459, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.091721773147583, "global_step": 391460, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.136939525604248, "global_step": 391461, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0991225242614746, "global_step": 391462, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0824947357177734, "global_step": 391463, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.989730954170227, "global_step": 391464, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.095186948776245, "global_step": 391465, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.114485740661621, "global_step": 391466, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1940786838531494, "global_step": 391467, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.091421127319336, "global_step": 391468, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0734758377075195, "global_step": 391469, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0938663482666016, "global_step": 391470, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.9890903234481812, "global_step": 391471, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.097398519515991, "global_step": 391472, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.094872236251831, "global_step": 391473, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0814812183380127, "global_step": 391474, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.133206605911255, "global_step": 391475, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1361589431762695, "global_step": 391476, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.07432222366333, "global_step": 391477, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.170742988586426, "global_step": 391478, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1448748111724854, "global_step": 391479, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0416548252105713, "global_step": 391480, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1143240928649902, "global_step": 391481, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.026764154434204, "global_step": 391482, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0449607372283936, "global_step": 391483, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0387887954711914, "global_step": 391484, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0778074264526367, "global_step": 391485, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1010384559631348, "global_step": 391486, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.088696241378784, "global_step": 391487, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.176929473876953, "global_step": 391488, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.073639392852783, "global_step": 391489, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.182556629180908, "global_step": 391490, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.132405996322632, "global_step": 391491, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1950879096984863, "global_step": 391492, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.100590467453003, "global_step": 391493, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1340887546539307, "global_step": 391494, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.114025115966797, "global_step": 391495, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.106638193130493, "global_step": 391496, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.101820230484009, "global_step": 391497, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1992316246032715, "global_step": 391498, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1781668663024902, "global_step": 391499, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0237793922424316, "global_step": 391500, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.112619638442993, "global_step": 391501, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0966084003448486, "global_step": 391502, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.149383544921875, "global_step": 391503, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2050323486328125, "global_step": 391504, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1137964725494385, "global_step": 391505, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1271610260009766, "global_step": 391506, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1430249214172363, "global_step": 391507, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.091163396835327, "global_step": 391508, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0439987182617188, "global_step": 391509, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0774178504943848, "global_step": 391510, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0574569702148438, "global_step": 391511, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0609350204467773, "global_step": 391512, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.111980676651001, "global_step": 391513, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.123070001602173, "global_step": 391514, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.99547278881073, "global_step": 391515, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.080162763595581, "global_step": 391516, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1088006496429443, "global_step": 391517, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.066127300262451, "global_step": 391518, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.054750680923462, "global_step": 391519, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.154588460922241, "global_step": 391520, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.152953624725342, "global_step": 391521, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1948776245117188, "global_step": 391522, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1852498054504395, "global_step": 391523, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.080209732055664, "global_step": 391524, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.05918550491333, "global_step": 391525, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0906362533569336, "global_step": 391526, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.146545171737671, "global_step": 391527, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1600053310394287, "global_step": 391528, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.066610336303711, "global_step": 391529, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.142850637435913, "global_step": 391530, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.061819553375244, "global_step": 391531, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.14582896232605, "global_step": 391532, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.090247631072998, "global_step": 391533, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.059581995010376, "global_step": 391534, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0518746376037598, "global_step": 391535, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.120757818222046, "global_step": 391536, "epoch": 753, "lr": 5e-05}
{"train_loss": 1.967234492301941, "global_step": 391537, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.083112955093384, "global_step": 391538, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1472976207733154, "global_step": 391539, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0957024097442627, "global_step": 391540, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0645430088043213, "global_step": 391541, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0739314556121826, "global_step": 391542, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.091660737991333, "global_step": 391543, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0363755226135254, "global_step": 391544, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.101720094680786, "global_step": 391545, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0723800659179688, "global_step": 391546, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2273526191711426, "global_step": 391547, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0867085456848145, "global_step": 391548, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.156503915786743, "global_step": 391549, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.118537187576294, "global_step": 391550, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1121134757995605, "global_step": 391551, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1469953060150146, "global_step": 391552, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1032941341400146, "global_step": 391553, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.111745834350586, "global_step": 391554, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1446287631988525, "global_step": 391555, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.021446943283081, "global_step": 391556, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1308095455169678, "global_step": 391557, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.17781925201416, "global_step": 391558, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.01615309715271, "global_step": 391559, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0938215255737305, "global_step": 391560, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.08615779876709, "global_step": 391561, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.165330410003662, "global_step": 391562, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.04850697517395, "global_step": 391563, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.099382162094116, "global_step": 391564, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1114375591278076, "global_step": 391565, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1737825870513916, "global_step": 391566, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.063356399536133, "global_step": 391567, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.193946123123169, "global_step": 391568, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1407997608184814, "global_step": 391569, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.007856607437134, "global_step": 391570, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.045320987701416, "global_step": 391571, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0543370246887207, "global_step": 391572, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0775983333587646, "global_step": 391573, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.054605484008789, "global_step": 391574, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.113804817199707, "global_step": 391575, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.054358959197998, "global_step": 391576, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.119982957839966, "global_step": 391577, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.147556781768799, "global_step": 391578, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.141453266143799, "global_step": 391579, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.024616241455078, "global_step": 391580, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0824949741363525, "global_step": 391581, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1015477180480957, "global_step": 391582, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.057492733001709, "global_step": 391583, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1644256114959717, "global_step": 391584, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.032066822052002, "global_step": 391585, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0524790287017822, "global_step": 391586, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1353471279144287, "global_step": 391587, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1023097038269043, "global_step": 391588, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1565675735473633, "global_step": 391589, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.156076431274414, "global_step": 391590, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0920522212982178, "global_step": 391591, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0867600440979004, "global_step": 391592, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1719541549682617, "global_step": 391593, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0159192085266113, "global_step": 391594, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0955724716186523, "global_step": 391595, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0440726280212402, "global_step": 391596, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0637471675872803, "global_step": 391597, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0532829761505127, "global_step": 391598, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.181293487548828, "global_step": 391599, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0770680904388428, "global_step": 391600, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1094751358032227, "global_step": 391601, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.113402843475342, "global_step": 391602, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.098728656768799, "global_step": 391603, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.2166988849639893, "global_step": 391604, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.123237133026123, "global_step": 391605, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.1158552169799805, "global_step": 391606, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.094369649887085, "global_step": 391607, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.098947763442993, "global_step": 391608, "epoch": 753, "lr": 5e-05}
{"train_loss": 2.0361242294311523, "global_step": 391609, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0773820877075195, "global_step": 391610, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.082754135131836, "global_step": 391611, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.055799722671509, "global_step": 391612, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1836068630218506, "global_step": 391613, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0682015419006348, "global_step": 391614, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.109092950820923, "global_step": 391615, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.205697536468506, "global_step": 391616, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.092176914215088, "global_step": 391617, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.065373182296753, "global_step": 391618, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.062851905822754, "global_step": 391619, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0651981830596924, "global_step": 391620, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0906484127044678, "global_step": 391621, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0244219303131104, "global_step": 391622, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.062213659286499, "global_step": 391623, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0894596576690674, "global_step": 391624, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0287132263183594, "global_step": 391625, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.036857843399048, "global_step": 391626, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1360509395599365, "global_step": 391627, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.125108242034912, "global_step": 391628, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.051560401916504, "global_step": 391629, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.092923879623413, "global_step": 391630, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.13419771194458, "global_step": 391631, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0804805755615234, "global_step": 391632, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.073230028152466, "global_step": 391633, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.158342123031616, "global_step": 391634, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.084672212600708, "global_step": 391635, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0736637115478516, "global_step": 391636, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.158566474914551, "global_step": 391637, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0700817108154297, "global_step": 391638, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1223340034484863, "global_step": 391639, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.072035551071167, "global_step": 391640, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1055490970611572, "global_step": 391641, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.110801935195923, "global_step": 391642, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.06550669670105, "global_step": 391643, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.119457483291626, "global_step": 391644, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.067594289779663, "global_step": 391645, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.050354480743408, "global_step": 391646, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0715813636779785, "global_step": 391647, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.150073289871216, "global_step": 391648, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.088973045349121, "global_step": 391649, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.058997631072998, "global_step": 391650, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0691332817077637, "global_step": 391651, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.098562479019165, "global_step": 391652, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0870988368988037, "global_step": 391653, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1176536083221436, "global_step": 391654, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0982792377471924, "global_step": 391655, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.088602304458618, "global_step": 391656, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.091871738433838, "global_step": 391657, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1000816822052, "global_step": 391658, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.084395408630371, "global_step": 391659, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.086367130279541, "global_step": 391660, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1529510021209717, "global_step": 391661, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0826761722564697, "global_step": 391662, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0028059482574463, "global_step": 391663, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0309040546417236, "global_step": 391664, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1653788089752197, "global_step": 391665, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1301629543304443, "global_step": 391666, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0067853927612305, "global_step": 391667, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.122535467147827, "global_step": 391668, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0672531127929688, "global_step": 391669, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0650033950805664, "global_step": 391670, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.053084135055542, "global_step": 391671, "epoch": 754, "lr": 5e-05}
{"train_loss": 1.9634548425674438, "global_step": 391672, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0435566902160645, "global_step": 391673, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.100632667541504, "global_step": 391674, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0587918758392334, "global_step": 391675, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0147995948791504, "global_step": 391676, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1342711448669434, "global_step": 391677, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0909290313720703, "global_step": 391678, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.115293264389038, "global_step": 391679, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.102029800415039, "global_step": 391680, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0679101943969727, "global_step": 391681, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.153625726699829, "global_step": 391682, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.054110527038574, "global_step": 391683, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1088430881500244, "global_step": 391684, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0880656242370605, "global_step": 391685, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0961403846740723, "global_step": 391686, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1477653980255127, "global_step": 391687, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1048009395599365, "global_step": 391688, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.116868257522583, "global_step": 391689, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.040717840194702, "global_step": 391690, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1220808029174805, "global_step": 391691, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.083508014678955, "global_step": 391692, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1393187046051025, "global_step": 391693, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0561912059783936, "global_step": 391694, "epoch": 754, "lr": 5e-05}
{"train_loss": 1.9864665269851685, "global_step": 391695, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0146944522857666, "global_step": 391696, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0937676429748535, "global_step": 391697, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.009833574295044, "global_step": 391698, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.152283191680908, "global_step": 391699, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0406887531280518, "global_step": 391700, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.134077548980713, "global_step": 391701, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0902676582336426, "global_step": 391702, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.2000832557678223, "global_step": 391703, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.147345542907715, "global_step": 391704, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0428621768951416, "global_step": 391705, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.014087200164795, "global_step": 391706, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.082789897918701, "global_step": 391707, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.087540864944458, "global_step": 391708, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1375749111175537, "global_step": 391709, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.120622396469116, "global_step": 391710, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0834403038024902, "global_step": 391711, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.035529375076294, "global_step": 391712, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1277716159820557, "global_step": 391713, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.081285238265991, "global_step": 391714, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1636147499084473, "global_step": 391715, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0870184898376465, "global_step": 391716, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.053402900695801, "global_step": 391717, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0143799781799316, "global_step": 391718, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0950803756713867, "global_step": 391719, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0299606323242188, "global_step": 391720, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.055082321166992, "global_step": 391721, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.118316888809204, "global_step": 391722, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0997931957244873, "global_step": 391723, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.2306056022644043, "global_step": 391724, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1274774074554443, "global_step": 391725, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.078688621520996, "global_step": 391726, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.092830181121826, "global_step": 391727, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.194730281829834, "global_step": 391728, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.082597494125366, "global_step": 391729, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.046583890914917, "global_step": 391730, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1224162578582764, "global_step": 391731, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1005284786224365, "global_step": 391732, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0542004108428955, "global_step": 391733, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1138899326324463, "global_step": 391734, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0841121673583984, "global_step": 391735, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.110682249069214, "global_step": 391736, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.073209047317505, "global_step": 391737, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.030712604522705, "global_step": 391738, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.108415365219116, "global_step": 391739, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0445055961608887, "global_step": 391740, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0309031009674072, "global_step": 391741, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0628573894500732, "global_step": 391742, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.047694683074951, "global_step": 391743, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.102548599243164, "global_step": 391744, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.109623432159424, "global_step": 391745, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.13023042678833, "global_step": 391746, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.003549098968506, "global_step": 391747, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.114975929260254, "global_step": 391748, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1064462661743164, "global_step": 391749, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0857460498809814, "global_step": 391750, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.123434066772461, "global_step": 391751, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0617523193359375, "global_step": 391752, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0792558193206787, "global_step": 391753, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.013242721557617, "global_step": 391754, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1134214401245117, "global_step": 391755, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.045182228088379, "global_step": 391756, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.184988498687744, "global_step": 391757, "epoch": 754, "lr": 5e-05}
{"train_loss": 1.9729399681091309, "global_step": 391758, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0673253536224365, "global_step": 391759, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.079568386077881, "global_step": 391760, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.104829788208008, "global_step": 391761, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.13919997215271, "global_step": 391762, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.091198444366455, "global_step": 391763, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.163151502609253, "global_step": 391764, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0859639644622803, "global_step": 391765, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1010189056396484, "global_step": 391766, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.120939254760742, "global_step": 391767, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.061101198196411, "global_step": 391768, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.111588954925537, "global_step": 391769, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.179344415664673, "global_step": 391770, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0574259757995605, "global_step": 391771, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0545284748077393, "global_step": 391772, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0265417098999023, "global_step": 391773, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.073535680770874, "global_step": 391774, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.08627986907959, "global_step": 391775, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0290122032165527, "global_step": 391776, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1492786407470703, "global_step": 391777, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1672098636627197, "global_step": 391778, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.070791721343994, "global_step": 391779, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.132190465927124, "global_step": 391780, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0274291038513184, "global_step": 391781, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1330668926239014, "global_step": 391782, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0789239406585693, "global_step": 391783, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.053649663925171, "global_step": 391784, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0894365310668945, "global_step": 391785, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.167113780975342, "global_step": 391786, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.067080497741699, "global_step": 391787, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0562286376953125, "global_step": 391788, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1015422344207764, "global_step": 391789, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0357625484466553, "global_step": 391790, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0962140560150146, "global_step": 391791, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0477006435394287, "global_step": 391792, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.171940565109253, "global_step": 391793, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.063650131225586, "global_step": 391794, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0622453689575195, "global_step": 391795, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.127880573272705, "global_step": 391796, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.150635242462158, "global_step": 391797, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.09505558013916, "global_step": 391798, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.119429349899292, "global_step": 391799, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0910027027130127, "global_step": 391800, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.071993827819824, "global_step": 391801, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0552000999450684, "global_step": 391802, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.083775520324707, "global_step": 391803, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0618808269500732, "global_step": 391804, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1088643074035645, "global_step": 391805, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.052056074142456, "global_step": 391806, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0682637691497803, "global_step": 391807, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.08837628364563, "global_step": 391808, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.122307538986206, "global_step": 391809, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0018129348754883, "global_step": 391810, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.10660719871521, "global_step": 391811, "epoch": 754, "lr": 5e-05}
{"train_loss": 1.967468500137329, "global_step": 391812, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.058246374130249, "global_step": 391813, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.084678888320923, "global_step": 391814, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1979894638061523, "global_step": 391815, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1506519317626953, "global_step": 391816, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.189732551574707, "global_step": 391817, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1248278617858887, "global_step": 391818, "epoch": 754, "lr": 5e-05}
{"train_loss": 1.9894670248031616, "global_step": 391819, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1559088230133057, "global_step": 391820, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.228043794631958, "global_step": 391821, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1390562057495117, "global_step": 391822, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.080648422241211, "global_step": 391823, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.013376235961914, "global_step": 391824, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.190330743789673, "global_step": 391825, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0358541011810303, "global_step": 391826, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.10770845413208, "global_step": 391827, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.037492275238037, "global_step": 391828, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1182568073272705, "global_step": 391829, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0566110610961914, "global_step": 391830, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.063323974609375, "global_step": 391831, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0584053993225098, "global_step": 391832, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1382102966308594, "global_step": 391833, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.070199489593506, "global_step": 391834, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.185917377471924, "global_step": 391835, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.10976243019104, "global_step": 391836, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.110387086868286, "global_step": 391837, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.060136079788208, "global_step": 391838, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.093430280685425, "global_step": 391839, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.033594846725464, "global_step": 391840, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0912632942199707, "global_step": 391841, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0909860134124756, "global_step": 391842, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.051156759262085, "global_step": 391843, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.195261240005493, "global_step": 391844, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.127216100692749, "global_step": 391845, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1613008975982666, "global_step": 391846, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1163158416748047, "global_step": 391847, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1173057556152344, "global_step": 391848, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.024657964706421, "global_step": 391849, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1418848037719727, "global_step": 391850, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.146939992904663, "global_step": 391851, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.103569984436035, "global_step": 391852, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1225130558013916, "global_step": 391853, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0549144744873047, "global_step": 391854, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0363247394561768, "global_step": 391855, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1008121967315674, "global_step": 391856, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.147325038909912, "global_step": 391857, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.100637912750244, "global_step": 391858, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.092224597930908, "global_step": 391859, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.17795467376709, "global_step": 391860, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.144092559814453, "global_step": 391861, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.087559223175049, "global_step": 391862, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1087989807128906, "global_step": 391863, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.145430326461792, "global_step": 391864, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.12276291847229, "global_step": 391865, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0389139652252197, "global_step": 391866, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.145840644836426, "global_step": 391867, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.2098264694213867, "global_step": 391868, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.066082715988159, "global_step": 391869, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0736589431762695, "global_step": 391870, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.071194648742676, "global_step": 391871, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.152150869369507, "global_step": 391872, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0986216068267822, "global_step": 391873, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0912487506866455, "global_step": 391874, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1113743782043457, "global_step": 391875, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0860936641693115, "global_step": 391876, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.057098865509033, "global_step": 391877, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1281116008758545, "global_step": 391878, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1685590744018555, "global_step": 391879, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0406813621520996, "global_step": 391880, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.077792167663574, "global_step": 391881, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.081670045852661, "global_step": 391882, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.123349189758301, "global_step": 391883, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.159372568130493, "global_step": 391884, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.165283203125, "global_step": 391885, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0265135765075684, "global_step": 391886, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.144737482070923, "global_step": 391887, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.074939012527466, "global_step": 391888, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0829155445098877, "global_step": 391889, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0610146522521973, "global_step": 391890, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.2090134620666504, "global_step": 391891, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.057103395462036, "global_step": 391892, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.101027727127075, "global_step": 391893, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0438058376312256, "global_step": 391894, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.14229679107666, "global_step": 391895, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1522443294525146, "global_step": 391896, "epoch": 754, "lr": 5e-05}
{"train_loss": 1.9715864658355713, "global_step": 391897, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1399340629577637, "global_step": 391898, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0715138912200928, "global_step": 391899, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.089095115661621, "global_step": 391900, "epoch": 754, "lr": 5e-05}
{"train_loss": 1.9986838102340698, "global_step": 391901, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1254796981811523, "global_step": 391902, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1432392597198486, "global_step": 391903, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.070329189300537, "global_step": 391904, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1314358711242676, "global_step": 391905, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.156921625137329, "global_step": 391906, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.140977382659912, "global_step": 391907, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1737563610076904, "global_step": 391908, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.108994245529175, "global_step": 391909, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1250572204589844, "global_step": 391910, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1128430366516113, "global_step": 391911, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1345081329345703, "global_step": 391912, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0942277908325195, "global_step": 391913, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.194547653198242, "global_step": 391914, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0740630626678467, "global_step": 391915, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0260772705078125, "global_step": 391916, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0263710021972656, "global_step": 391917, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0334835052490234, "global_step": 391918, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.091986894607544, "global_step": 391919, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1098735332489014, "global_step": 391920, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0570945739746094, "global_step": 391921, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0636844635009766, "global_step": 391922, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.005133867263794, "global_step": 391923, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1502723693847656, "global_step": 391924, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1839847564697266, "global_step": 391925, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.093679428100586, "global_step": 391926, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1311964988708496, "global_step": 391927, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.048182487487793, "global_step": 391928, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1000468730926514, "global_step": 391929, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1525895595550537, "global_step": 391930, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1580207347869873, "global_step": 391931, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.084573984146118, "global_step": 391932, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.150081157684326, "global_step": 391933, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1689741611480713, "global_step": 391934, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.166348457336426, "global_step": 391935, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0883846282958984, "global_step": 391936, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.093179225921631, "global_step": 391937, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0427744388580322, "global_step": 391938, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.146967649459839, "global_step": 391939, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0866599082946777, "global_step": 391940, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.110969066619873, "global_step": 391941, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.033277750015259, "global_step": 391942, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.136859655380249, "global_step": 391943, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1230525970458984, "global_step": 391944, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1022706031799316, "global_step": 391945, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.142552137374878, "global_step": 391946, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.125185251235962, "global_step": 391947, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1350486278533936, "global_step": 391948, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.066748857498169, "global_step": 391949, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1171915531158447, "global_step": 391950, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.004837989807129, "global_step": 391951, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.124159336090088, "global_step": 391952, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.142817735671997, "global_step": 391953, "epoch": 754, "lr": 5e-05}
{"train_loss": 1.9969971179962158, "global_step": 391954, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.061718702316284, "global_step": 391955, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0222232341766357, "global_step": 391956, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.108323574066162, "global_step": 391957, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1704607009887695, "global_step": 391958, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.143709182739258, "global_step": 391959, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1925463676452637, "global_step": 391960, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0682249069213867, "global_step": 391961, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1266658306121826, "global_step": 391962, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1269006729125977, "global_step": 391963, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.04963755607605, "global_step": 391964, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.103329658508301, "global_step": 391965, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0664849281311035, "global_step": 391966, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.159358263015747, "global_step": 391967, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.208120822906494, "global_step": 391968, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.08225154876709, "global_step": 391969, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1048998832702637, "global_step": 391970, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0956614017486572, "global_step": 391971, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.074016809463501, "global_step": 391972, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0248172283172607, "global_step": 391973, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0629544258117676, "global_step": 391974, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.13993501663208, "global_step": 391975, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.110913038253784, "global_step": 391976, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0929818153381348, "global_step": 391977, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0628786087036133, "global_step": 391978, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1521389484405518, "global_step": 391979, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.073969841003418, "global_step": 391980, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.007481813430786, "global_step": 391981, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0610647201538086, "global_step": 391982, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.094550132751465, "global_step": 391983, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0921928882598877, "global_step": 391984, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.170764446258545, "global_step": 391985, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.128953695297241, "global_step": 391986, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0201220512390137, "global_step": 391987, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0884196758270264, "global_step": 391988, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.051121473312378, "global_step": 391989, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0604124069213867, "global_step": 391990, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1558010578155518, "global_step": 391991, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0619964599609375, "global_step": 391992, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.102665424346924, "global_step": 391993, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1505863666534424, "global_step": 391994, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.141873359680176, "global_step": 391995, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.160550117492676, "global_step": 391996, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0365729331970215, "global_step": 391997, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1330623626708984, "global_step": 391998, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.137613296508789, "global_step": 391999, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0128328800201416, "global_step": 392000, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.053100824356079, "global_step": 392001, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1092331409454346, "global_step": 392002, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0738401412963867, "global_step": 392003, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.079869270324707, "global_step": 392004, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0859763622283936, "global_step": 392005, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.061445474624634, "global_step": 392006, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.086418390274048, "global_step": 392007, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1517341136932373, "global_step": 392008, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1695053577423096, "global_step": 392009, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1852424144744873, "global_step": 392010, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.048402786254883, "global_step": 392011, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.077094078063965, "global_step": 392012, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.061393976211548, "global_step": 392013, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.151449203491211, "global_step": 392014, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.105388641357422, "global_step": 392015, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.021284580230713, "global_step": 392016, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0773515701293945, "global_step": 392017, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.055886745452881, "global_step": 392018, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0989139080047607, "global_step": 392019, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.082343578338623, "global_step": 392020, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0139076709747314, "global_step": 392021, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.111114740371704, "global_step": 392022, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.154353380203247, "global_step": 392023, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1536014080047607, "global_step": 392024, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1589488983154297, "global_step": 392025, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.127688407897949, "global_step": 392026, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0723037719726562, "global_step": 392027, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0543200969696045, "global_step": 392028, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0762503147125244, "global_step": 392029, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1418328285217285, "global_step": 392030, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1101675033569336, "global_step": 392031, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.140995979309082, "global_step": 392032, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1657485961914062, "global_step": 392033, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.068336248397827, "global_step": 392034, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0963172912597656, "global_step": 392035, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.112241506576538, "global_step": 392036, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1718082427978516, "global_step": 392037, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.091500759124756, "global_step": 392038, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0943872928619385, "global_step": 392039, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1358325481414795, "global_step": 392040, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1376700401306152, "global_step": 392041, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1502485275268555, "global_step": 392042, "epoch": 754, "lr": 5e-05}
{"train_loss": 1.9898324012756348, "global_step": 392043, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.151381492614746, "global_step": 392044, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1053831577301025, "global_step": 392045, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1227476596832275, "global_step": 392046, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.160831928253174, "global_step": 392047, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.027705669403076, "global_step": 392048, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.105276346206665, "global_step": 392049, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1303255558013916, "global_step": 392050, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.095442056655884, "global_step": 392051, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0292317867279053, "global_step": 392052, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.033736228942871, "global_step": 392053, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1079134941101074, "global_step": 392054, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0663249492645264, "global_step": 392055, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1100058555603027, "global_step": 392056, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0874810218811035, "global_step": 392057, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0979464054107666, "global_step": 392058, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0882556438446045, "global_step": 392059, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0910723209381104, "global_step": 392060, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.163376569747925, "global_step": 392061, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.205095052719116, "global_step": 392062, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.065192937850952, "global_step": 392063, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1124746799468994, "global_step": 392064, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.108164072036743, "global_step": 392065, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1072144508361816, "global_step": 392066, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.034868001937866, "global_step": 392067, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0712924003601074, "global_step": 392068, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0580220222473145, "global_step": 392069, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0509588718414307, "global_step": 392070, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0749869346618652, "global_step": 392071, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.088083505630493, "global_step": 392072, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0907933712005615, "global_step": 392073, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0727014541625977, "global_step": 392074, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1178030967712402, "global_step": 392075, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.088174819946289, "global_step": 392076, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.118803024291992, "global_step": 392077, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0656657218933105, "global_step": 392078, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0371594429016113, "global_step": 392079, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.012995958328247, "global_step": 392080, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1679179668426514, "global_step": 392081, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1065049171447754, "global_step": 392082, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1389427185058594, "global_step": 392083, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1088855266571045, "global_step": 392084, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1970224380493164, "global_step": 392085, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.157931327819824, "global_step": 392086, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0375616550445557, "global_step": 392087, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.095963478088379, "global_step": 392088, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.112373113632202, "global_step": 392089, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.094252109527588, "global_step": 392090, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.198373317718506, "global_step": 392091, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1205990314483643, "global_step": 392092, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.054640531539917, "global_step": 392093, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0173962116241455, "global_step": 392094, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1478583812713623, "global_step": 392095, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.048501491546631, "global_step": 392096, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.141482353210449, "global_step": 392097, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.12772274017334, "global_step": 392098, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0703091621398926, "global_step": 392099, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.036116123199463, "global_step": 392100, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.147412061691284, "global_step": 392101, "epoch": 754, "lr": 5e-05}
{"train_loss": 1.9925103187561035, "global_step": 392102, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0193703174591064, "global_step": 392103, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.126891613006592, "global_step": 392104, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.093283176422119, "global_step": 392105, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1015515327453613, "global_step": 392106, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.170111894607544, "global_step": 392107, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1538891792297363, "global_step": 392108, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1829442977905273, "global_step": 392109, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1298413276672363, "global_step": 392110, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1424806118011475, "global_step": 392111, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1086509227752686, "global_step": 392112, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1113522052764893, "global_step": 392113, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1262292861938477, "global_step": 392114, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0459089279174805, "global_step": 392115, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0416204929351807, "global_step": 392116, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.075916051864624, "global_step": 392117, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1109747886657715, "global_step": 392118, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1436686515808105, "global_step": 392119, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.035964250564575, "global_step": 392120, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1566014289855957, "global_step": 392121, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.163297176361084, "global_step": 392122, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.103393793106079, "global_step": 392123, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0378527641296387, "global_step": 392124, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1078364849090576, "global_step": 392125, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.072141408920288, "global_step": 392126, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1298036575317383, "global_step": 392127, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0627589225769043, "global_step": 392128, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.114259958267212, "global_step": 392129, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.143904447555542, "global_step": 392130, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.156809091567993, "global_step": 392131, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1765224933624268, "global_step": 392132, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1998438835144043, "global_step": 392133, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.142735719680786, "global_step": 392134, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1297144889831543, "global_step": 392135, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1070921421051025, "global_step": 392136, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.129401445388794, "global_step": 392137, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1199073791503906, "global_step": 392138, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.078075408935547, "global_step": 392139, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0156102180480957, "global_step": 392140, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.135831832885742, "global_step": 392141, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.033432960510254, "global_step": 392142, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0247433185577393, "global_step": 392143, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.106823205947876, "global_step": 392144, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.161756992340088, "global_step": 392145, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.039827346801758, "global_step": 392146, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1175506114959717, "global_step": 392147, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.093939781188965, "global_step": 392148, "epoch": 754, "lr": 5e-05}
{"train_loss": 1.9844887256622314, "global_step": 392149, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.17409086227417, "global_step": 392150, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.039275884628296, "global_step": 392151, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1647987365722656, "global_step": 392152, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.064114570617676, "global_step": 392153, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.07015061378479, "global_step": 392154, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1288843154907227, "global_step": 392155, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1270179748535156, "global_step": 392156, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0954904556274414, "global_step": 392157, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0644125938415527, "global_step": 392158, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0938963890075684, "global_step": 392159, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0656681060791016, "global_step": 392160, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1194868087768555, "global_step": 392161, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1689343452453613, "global_step": 392162, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0096776485443115, "global_step": 392163, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1103591918945312, "global_step": 392164, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.057858467102051, "global_step": 392165, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1144793033599854, "global_step": 392166, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.112029552459717, "global_step": 392167, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.004864454269409, "global_step": 392168, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.2054333686828613, "global_step": 392169, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.164269208908081, "global_step": 392170, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.169339895248413, "global_step": 392171, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.132049798965454, "global_step": 392172, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1415562629699707, "global_step": 392173, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0279481410980225, "global_step": 392174, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0947418212890625, "global_step": 392175, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.067532539367676, "global_step": 392176, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1090078353881836, "global_step": 392177, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.078573703765869, "global_step": 392178, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0766148567199707, "global_step": 392179, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0882976055145264, "global_step": 392180, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.041666030883789, "global_step": 392181, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.122504949569702, "global_step": 392182, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0951337814331055, "global_step": 392183, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.072690486907959, "global_step": 392184, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.107619047164917, "global_step": 392185, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0724995136260986, "global_step": 392186, "epoch": 754, "lr": 5e-05}
{"train_loss": 1.9904595613479614, "global_step": 392187, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.083664894104004, "global_step": 392188, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.145975351333618, "global_step": 392189, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.042670249938965, "global_step": 392190, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1239616870880127, "global_step": 392191, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.08060884475708, "global_step": 392192, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1177892684936523, "global_step": 392193, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1155340671539307, "global_step": 392194, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.09159517288208, "global_step": 392195, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1934707164764404, "global_step": 392196, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.113828659057617, "global_step": 392197, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1816115379333496, "global_step": 392198, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.108464002609253, "global_step": 392199, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1256844997406006, "global_step": 392200, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0593481063842773, "global_step": 392201, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1202304363250732, "global_step": 392202, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1314477920532227, "global_step": 392203, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1126060485839844, "global_step": 392204, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.085500478744507, "global_step": 392205, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.118934154510498, "global_step": 392206, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1789474487304688, "global_step": 392207, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1281511783599854, "global_step": 392208, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.098346471786499, "global_step": 392209, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.03842830657959, "global_step": 392210, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0818254947662354, "global_step": 392211, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.167026996612549, "global_step": 392212, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1208670139312744, "global_step": 392213, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1506495475769043, "global_step": 392214, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1174213886260986, "global_step": 392215, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0812790393829346, "global_step": 392216, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.122149705886841, "global_step": 392217, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.142289638519287, "global_step": 392218, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.147841453552246, "global_step": 392219, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0501933097839355, "global_step": 392220, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.085981845855713, "global_step": 392221, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0820162296295166, "global_step": 392222, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1327064037323, "global_step": 392223, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.122332811355591, "global_step": 392224, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.113856077194214, "global_step": 392225, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1529476642608643, "global_step": 392226, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.105712413787842, "global_step": 392227, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0580251216888428, "global_step": 392228, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.146754264831543, "global_step": 392229, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0669145584106445, "global_step": 392230, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0409510135650635, "global_step": 392231, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0202956199645996, "global_step": 392232, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0554442405700684, "global_step": 392233, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.076615333557129, "global_step": 392234, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0991268157958984, "global_step": 392235, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.076694965362549, "global_step": 392236, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1014816761016846, "global_step": 392237, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.063836097717285, "global_step": 392238, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.062561511993408, "global_step": 392239, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0485973358154297, "global_step": 392240, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.186180353164673, "global_step": 392241, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0763638019561768, "global_step": 392242, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1122243404388428, "global_step": 392243, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.172003984451294, "global_step": 392244, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0624046325683594, "global_step": 392245, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1752288341522217, "global_step": 392246, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.048048257827759, "global_step": 392247, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.096954584121704, "global_step": 392248, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0620505809783936, "global_step": 392249, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1753976345062256, "global_step": 392250, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1066040992736816, "global_step": 392251, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0049564838409424, "global_step": 392252, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.176149368286133, "global_step": 392253, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.148037910461426, "global_step": 392254, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0671935081481934, "global_step": 392255, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1205387115478516, "global_step": 392256, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1239213943481445, "global_step": 392257, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0320088863372803, "global_step": 392258, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.109217882156372, "global_step": 392259, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.136474847793579, "global_step": 392260, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0845487117767334, "global_step": 392261, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.090718984603882, "global_step": 392262, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0677497386932373, "global_step": 392263, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1131484508514404, "global_step": 392264, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.032782554626465, "global_step": 392265, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0196709632873535, "global_step": 392266, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.01725172996521, "global_step": 392267, "epoch": 754, "lr": 5e-05}
{"train_loss": 1.9874106645584106, "global_step": 392268, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.091911792755127, "global_step": 392269, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0012094974517822, "global_step": 392270, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0517971515655518, "global_step": 392271, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.107137441635132, "global_step": 392272, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1070549488067627, "global_step": 392273, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.077998638153076, "global_step": 392274, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.025730609893799, "global_step": 392275, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0928499698638916, "global_step": 392276, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.119049549102783, "global_step": 392277, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.114349842071533, "global_step": 392278, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.150442123413086, "global_step": 392279, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.096184015274048, "global_step": 392280, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.189836263656616, "global_step": 392281, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.121185302734375, "global_step": 392282, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0824804306030273, "global_step": 392283, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.055155038833618, "global_step": 392284, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1306827068328857, "global_step": 392285, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.035074472427368, "global_step": 392286, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.148088216781616, "global_step": 392287, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.099823474884033, "global_step": 392288, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.078773260116577, "global_step": 392289, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1414408683776855, "global_step": 392290, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1919243335723877, "global_step": 392291, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1390602588653564, "global_step": 392292, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1008081436157227, "global_step": 392293, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0887324810028076, "global_step": 392294, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1078810691833496, "global_step": 392295, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0472726821899414, "global_step": 392296, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.009430170059204, "global_step": 392297, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.123804807662964, "global_step": 392298, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.13662052154541, "global_step": 392299, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1508302688598633, "global_step": 392300, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.064192295074463, "global_step": 392301, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.165274143218994, "global_step": 392302, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0765187740325928, "global_step": 392303, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1662795543670654, "global_step": 392304, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.200927972793579, "global_step": 392305, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.038335084915161, "global_step": 392306, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.037416934967041, "global_step": 392307, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0894031524658203, "global_step": 392308, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1055965423583984, "global_step": 392309, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1214241981506348, "global_step": 392310, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0801432132720947, "global_step": 392311, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.103874921798706, "global_step": 392312, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.094146966934204, "global_step": 392313, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0677742958068848, "global_step": 392314, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.145050048828125, "global_step": 392315, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0576813220977783, "global_step": 392316, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0860462188720703, "global_step": 392317, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.042867422103882, "global_step": 392318, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0865843296051025, "global_step": 392319, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0772109031677246, "global_step": 392320, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.079996347427368, "global_step": 392321, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0659728050231934, "global_step": 392322, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.06109356880188, "global_step": 392323, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.17933988571167, "global_step": 392324, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1194586753845215, "global_step": 392325, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0093486309051514, "global_step": 392326, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.13667368888855, "global_step": 392327, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.082374095916748, "global_step": 392328, "epoch": 754, "lr": 5e-05}
{"train_loss": 1.9879852533340454, "global_step": 392329, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.085007905960083, "global_step": 392330, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1363484859466553, "global_step": 392331, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.074906349182129, "global_step": 392332, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1257376670837402, "global_step": 392333, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1262052059173584, "global_step": 392334, "epoch": 754, "lr": 5e-05}
{"train_loss": 1.9751994609832764, "global_step": 392335, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.098869800567627, "global_step": 392336, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1406033039093018, "global_step": 392337, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0750460624694824, "global_step": 392338, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.126105785369873, "global_step": 392339, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0576272010803223, "global_step": 392340, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.077951431274414, "global_step": 392341, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0756118297576904, "global_step": 392342, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.075824737548828, "global_step": 392343, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1250226497650146, "global_step": 392344, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1394147872924805, "global_step": 392345, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0872766971588135, "global_step": 392346, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.041011333465576, "global_step": 392347, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.079552173614502, "global_step": 392348, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.137151002883911, "global_step": 392349, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.084669828414917, "global_step": 392350, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.130632162094116, "global_step": 392351, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0930731296539307, "global_step": 392352, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.2197258472442627, "global_step": 392353, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1000778675079346, "global_step": 392354, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.067476272583008, "global_step": 392355, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.100187063217163, "global_step": 392356, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0994443893432617, "global_step": 392357, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1844992637634277, "global_step": 392358, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0235631465911865, "global_step": 392359, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.092979907989502, "global_step": 392360, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1751856803894043, "global_step": 392361, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.074812889099121, "global_step": 392362, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.153456926345825, "global_step": 392363, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0120668411254883, "global_step": 392364, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.056391716003418, "global_step": 392365, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0296707153320312, "global_step": 392366, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1382884979248047, "global_step": 392367, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.174546241760254, "global_step": 392368, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0491573810577393, "global_step": 392369, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.067354202270508, "global_step": 392370, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.08294939994812, "global_step": 392371, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0996201038360596, "global_step": 392372, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1014397144317627, "global_step": 392373, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0434277057647705, "global_step": 392374, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0961053371429443, "global_step": 392375, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.168508768081665, "global_step": 392376, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.109907865524292, "global_step": 392377, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1193790435791016, "global_step": 392378, "epoch": 754, "lr": 5e-05}
{"train_loss": 1.9987093210220337, "global_step": 392379, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1248703002929688, "global_step": 392380, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.101872205734253, "global_step": 392381, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.197103500366211, "global_step": 392382, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.08031964302063, "global_step": 392383, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1056599617004395, "global_step": 392384, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0134198665618896, "global_step": 392385, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.196537494659424, "global_step": 392386, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0261638164520264, "global_step": 392387, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.069223165512085, "global_step": 392388, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1121363639831543, "global_step": 392389, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.083418607711792, "global_step": 392390, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0923051834106445, "global_step": 392391, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.120694398880005, "global_step": 392392, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0344207286834717, "global_step": 392393, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.090035915374756, "global_step": 392394, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0746586322784424, "global_step": 392395, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.082508087158203, "global_step": 392396, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0786516666412354, "global_step": 392397, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.103316068649292, "global_step": 392398, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0285286903381348, "global_step": 392399, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.173892021179199, "global_step": 392400, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1118102073669434, "global_step": 392401, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1406867504119873, "global_step": 392402, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.111370801925659, "global_step": 392403, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.098033905029297, "global_step": 392404, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0905697345733643, "global_step": 392405, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.035939931869507, "global_step": 392406, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0536117553710938, "global_step": 392407, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.059887170791626, "global_step": 392408, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1294915676116943, "global_step": 392409, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.099207878112793, "global_step": 392410, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.098057746887207, "global_step": 392411, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.14333176612854, "global_step": 392412, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.2053191661834717, "global_step": 392413, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1245861053466797, "global_step": 392414, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.148268699645996, "global_step": 392415, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.061258554458618, "global_step": 392416, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0965089797973633, "global_step": 392417, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.088348388671875, "global_step": 392418, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1307170391082764, "global_step": 392419, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.125915288925171, "global_step": 392420, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.121309280395508, "global_step": 392421, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.045977830886841, "global_step": 392422, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.083045482635498, "global_step": 392423, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1532468795776367, "global_step": 392424, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1059160232543945, "global_step": 392425, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1019561290740967, "global_step": 392426, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0216164588928223, "global_step": 392427, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.12213134765625, "global_step": 392428, "epoch": 754, "lr": 5e-05}
{"train_loss": 1.976726770401001, "global_step": 392429, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0871810913085938, "global_step": 392430, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1375198364257812, "global_step": 392431, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.070327043533325, "global_step": 392432, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.155689001083374, "global_step": 392433, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1213552951812744, "global_step": 392434, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1648828983306885, "global_step": 392435, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.122619867324829, "global_step": 392436, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1322922706604004, "global_step": 392437, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1328959465026855, "global_step": 392438, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.105269193649292, "global_step": 392439, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.116067886352539, "global_step": 392440, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.091154098510742, "global_step": 392441, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0680737495422363, "global_step": 392442, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.14150333404541, "global_step": 392443, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1327521800994873, "global_step": 392444, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1328048706054688, "global_step": 392445, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.099863052368164, "global_step": 392446, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.152817487716675, "global_step": 392447, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0360419750213623, "global_step": 392448, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.125725746154785, "global_step": 392449, "epoch": 754, "lr": 5e-05}
{"train_loss": 1.9662333726882935, "global_step": 392450, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.108095407485962, "global_step": 392451, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0782718658447266, "global_step": 392452, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.167922258377075, "global_step": 392453, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0034234523773193, "global_step": 392454, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1173038482666016, "global_step": 392455, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0963966846466064, "global_step": 392456, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1864285469055176, "global_step": 392457, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.031341552734375, "global_step": 392458, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.062324285507202, "global_step": 392459, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1664986610412598, "global_step": 392460, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.165179967880249, "global_step": 392461, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.097416639328003, "global_step": 392462, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1571767330169678, "global_step": 392463, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1512935161590576, "global_step": 392464, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1619369983673096, "global_step": 392465, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0744857788085938, "global_step": 392466, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.196718692779541, "global_step": 392467, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.097632884979248, "global_step": 392468, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0750372409820557, "global_step": 392469, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.080059289932251, "global_step": 392470, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1001179218292236, "global_step": 392471, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.175568103790283, "global_step": 392472, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0364391803741455, "global_step": 392473, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.089811086654663, "global_step": 392474, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1581015586853027, "global_step": 392475, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.08662486076355, "global_step": 392476, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.040931224822998, "global_step": 392477, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.082601308822632, "global_step": 392478, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.139652967453003, "global_step": 392479, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0870938301086426, "global_step": 392480, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1045100688934326, "global_step": 392481, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.098712205886841, "global_step": 392482, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.094069004058838, "global_step": 392483, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0887110233306885, "global_step": 392484, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.030074119567871, "global_step": 392485, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.081157922744751, "global_step": 392486, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0529606342315674, "global_step": 392487, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.147005796432495, "global_step": 392488, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.091843843460083, "global_step": 392489, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.078995704650879, "global_step": 392490, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.161060333251953, "global_step": 392491, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.171194314956665, "global_step": 392492, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.069369316101074, "global_step": 392493, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1257200241088867, "global_step": 392494, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.097594738006592, "global_step": 392495, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.090630531311035, "global_step": 392496, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.2194621562957764, "global_step": 392497, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.139753818511963, "global_step": 392498, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.152686595916748, "global_step": 392499, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1244189739227295, "global_step": 392500, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.133542776107788, "global_step": 392501, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0608630180358887, "global_step": 392502, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.128018856048584, "global_step": 392503, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.102318048477173, "global_step": 392504, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0614233016967773, "global_step": 392505, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0546469688415527, "global_step": 392506, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1445798873901367, "global_step": 392507, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1209874153137207, "global_step": 392508, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.024862051010132, "global_step": 392509, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.209219455718994, "global_step": 392510, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.086742639541626, "global_step": 392511, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.137092351913452, "global_step": 392512, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.139396905899048, "global_step": 392513, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.141623020172119, "global_step": 392514, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0497257709503174, "global_step": 392515, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1024391651153564, "global_step": 392516, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.155282497406006, "global_step": 392517, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0769150257110596, "global_step": 392518, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0740456581115723, "global_step": 392519, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1116573810577393, "global_step": 392520, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1571617126464844, "global_step": 392521, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.050845146179199, "global_step": 392522, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.178889513015747, "global_step": 392523, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.040907144546509, "global_step": 392524, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1484644412994385, "global_step": 392525, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1294562816619873, "global_step": 392526, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.070329427719116, "global_step": 392527, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1937906742095947, "global_step": 392528, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1026949882507324, "global_step": 392529, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.136183261871338, "global_step": 392530, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.049830198287964, "global_step": 392531, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.220318078994751, "global_step": 392532, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0988171100616455, "global_step": 392533, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1211681365966797, "global_step": 392534, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.104365110397339, "global_step": 392535, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1600470542907715, "global_step": 392536, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.045379877090454, "global_step": 392537, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0732455253601074, "global_step": 392538, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.125007390975952, "global_step": 392539, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0486302375793457, "global_step": 392540, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0759878158569336, "global_step": 392541, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0563857555389404, "global_step": 392542, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.04252552986145, "global_step": 392543, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1619927883148193, "global_step": 392544, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0646755695343018, "global_step": 392545, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0511252880096436, "global_step": 392546, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.136953115463257, "global_step": 392547, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.045868396759033, "global_step": 392548, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1774234771728516, "global_step": 392549, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0387580394744873, "global_step": 392550, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0807230472564697, "global_step": 392551, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1002731323242188, "global_step": 392552, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.058117389678955, "global_step": 392553, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1283628940582275, "global_step": 392554, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0976104736328125, "global_step": 392555, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0801990032196045, "global_step": 392556, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1335830688476562, "global_step": 392557, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.077378273010254, "global_step": 392558, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.166572332382202, "global_step": 392559, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.118527412414551, "global_step": 392560, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1165785789489746, "global_step": 392561, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1869213581085205, "global_step": 392562, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0780820846557617, "global_step": 392563, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1312179565429688, "global_step": 392564, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.081876754760742, "global_step": 392565, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1170895099639893, "global_step": 392566, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1814916133880615, "global_step": 392567, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0253942012786865, "global_step": 392568, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1666319370269775, "global_step": 392569, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.147822618484497, "global_step": 392570, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.101515293121338, "global_step": 392571, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.1103265285491943, "global_step": 392572, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0508439540863037, "global_step": 392573, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0709660053253174, "global_step": 392574, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.106780529022217, "global_step": 392575, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.097569465637207, "global_step": 392576, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0984816551208496, "global_step": 392577, "epoch": 754, "lr": 5e-05}
{"train_loss": 2.0563621520996094, "global_step": 392578, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.2202837467193604, "global_step": 392579, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.038177013397217, "global_step": 392580, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.9960089921951294, "global_step": 392581, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1729559898376465, "global_step": 392582, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0857787132263184, "global_step": 392583, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1334824562072754, "global_step": 392584, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.173602819442749, "global_step": 392585, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.159451723098755, "global_step": 392586, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0868663787841797, "global_step": 392587, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.110614061355591, "global_step": 392588, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0727171897888184, "global_step": 392589, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1070897579193115, "global_step": 392590, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.100813865661621, "global_step": 392591, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0363759994506836, "global_step": 392592, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.020326614379883, "global_step": 392593, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.163599967956543, "global_step": 392594, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1419410705566406, "global_step": 392595, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.063570976257324, "global_step": 392596, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.063930034637451, "global_step": 392597, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1225297451019287, "global_step": 392598, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.110565423965454, "global_step": 392599, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1136374473571777, "global_step": 392600, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1156201362609863, "global_step": 392601, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1078310012817383, "global_step": 392602, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1051390171051025, "global_step": 392603, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.05448842048645, "global_step": 392604, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1652393341064453, "global_step": 392605, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1876718997955322, "global_step": 392606, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.117105722427368, "global_step": 392607, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.2197022438049316, "global_step": 392608, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1078436374664307, "global_step": 392609, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1402509212493896, "global_step": 392610, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.023390769958496, "global_step": 392611, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1265389919281006, "global_step": 392612, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1012496948242188, "global_step": 392613, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.068730354309082, "global_step": 392614, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1064178943634033, "global_step": 392615, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1301002502441406, "global_step": 392616, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0644052028656006, "global_step": 392617, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.117264747619629, "global_step": 392618, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.9822793006896973, "global_step": 392619, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1911213397979736, "global_step": 392620, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1029622554779053, "global_step": 392621, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1003191471099854, "global_step": 392622, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1836066246032715, "global_step": 392623, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.095029354095459, "global_step": 392624, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.022710084915161, "global_step": 392625, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.126321315765381, "global_step": 392626, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1274380683898926, "global_step": 392627, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.2181591987609863, "global_step": 392628, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0380802154541016, "global_step": 392629, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.988606333732605, "global_step": 392630, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1010947227478027, "global_step": 392631, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0759658813476562, "global_step": 392632, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0727663040161133, "global_step": 392633, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.050421953201294, "global_step": 392634, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0052456855773926, "global_step": 392635, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.153803825378418, "global_step": 392636, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0775561332702637, "global_step": 392637, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.175145387649536, "global_step": 392638, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0015323162078857, "global_step": 392639, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1969125270843506, "global_step": 392640, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1303093433380127, "global_step": 392641, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1476364135742188, "global_step": 392642, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.9926259517669678, "global_step": 392643, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.097773551940918, "global_step": 392644, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1442673206329346, "global_step": 392645, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.087045431137085, "global_step": 392646, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.213172435760498, "global_step": 392647, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.087876558303833, "global_step": 392648, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.2539591789245605, "global_step": 392649, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.090259552001953, "global_step": 392650, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0652120113372803, "global_step": 392651, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1054396629333496, "global_step": 392652, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.072126865386963, "global_step": 392653, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.178112268447876, "global_step": 392654, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0685040950775146, "global_step": 392655, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0320968627929688, "global_step": 392656, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.067816734313965, "global_step": 392657, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1498494148254395, "global_step": 392658, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1003787517547607, "global_step": 392659, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0697996616363525, "global_step": 392660, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0334532260894775, "global_step": 392661, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0761327743530273, "global_step": 392662, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0412697792053223, "global_step": 392663, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0596694946289062, "global_step": 392664, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.158184289932251, "global_step": 392665, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0830132961273193, "global_step": 392666, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.145918369293213, "global_step": 392667, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.078890562057495, "global_step": 392668, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.043839931488037, "global_step": 392669, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1045594215393066, "global_step": 392670, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1600069999694824, "global_step": 392671, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.2155373096466064, "global_step": 392672, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.054518222808838, "global_step": 392673, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1660823822021484, "global_step": 392674, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.08974027633667, "global_step": 392675, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0759804248809814, "global_step": 392676, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.126000165939331, "global_step": 392677, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1082959175109863, "global_step": 392678, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1360228061676025, "global_step": 392679, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1702873706817627, "global_step": 392680, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0660603046417236, "global_step": 392681, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0357391834259033, "global_step": 392682, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.05240797996521, "global_step": 392683, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.14076566696167, "global_step": 392684, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0820674896240234, "global_step": 392685, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1756513118743896, "global_step": 392686, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.124352216720581, "global_step": 392687, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0430967807769775, "global_step": 392688, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1463818550109863, "global_step": 392689, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0979909896850586, "global_step": 392690, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.104849100112915, "global_step": 392691, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0754575729370117, "global_step": 392692, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.07637882232666, "global_step": 392693, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.104933023452759, "global_step": 392694, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.079624652862549, "global_step": 392695, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.9495664834976196, "global_step": 392696, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.09768009185791, "global_step": 392697, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.102756977081299, "global_step": 392698, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0130088329315186, "global_step": 392699, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1100831031799316, "global_step": 392700, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0233314037323, "global_step": 392701, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1018126010894775, "global_step": 392702, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0101990699768066, "global_step": 392703, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.027996063232422, "global_step": 392704, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.18735671043396, "global_step": 392705, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.057175874710083, "global_step": 392706, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.029538869857788, "global_step": 392707, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0871384143829346, "global_step": 392708, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.9979629516601562, "global_step": 392709, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1482107639312744, "global_step": 392710, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0534799098968506, "global_step": 392711, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.149678945541382, "global_step": 392712, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1022253036499023, "global_step": 392713, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.053131103515625, "global_step": 392714, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0802340507507324, "global_step": 392715, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1475181579589844, "global_step": 392716, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.121410846710205, "global_step": 392717, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.073124885559082, "global_step": 392718, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.133039712905884, "global_step": 392719, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1493544578552246, "global_step": 392720, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0526509284973145, "global_step": 392721, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0085976123809814, "global_step": 392722, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.015334129333496, "global_step": 392723, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1689443588256836, "global_step": 392724, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0344555377960205, "global_step": 392725, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.133960723876953, "global_step": 392726, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1243770122528076, "global_step": 392727, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.128549814224243, "global_step": 392728, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1524338722229004, "global_step": 392729, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0186328887939453, "global_step": 392730, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.118894338607788, "global_step": 392731, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0615193843841553, "global_step": 392732, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0833117961883545, "global_step": 392733, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0759503841400146, "global_step": 392734, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0600953102111816, "global_step": 392735, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1399054527282715, "global_step": 392736, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.021409034729004, "global_step": 392737, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0327837467193604, "global_step": 392738, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.9957177639007568, "global_step": 392739, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0524370670318604, "global_step": 392740, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.121786117553711, "global_step": 392741, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.060666561126709, "global_step": 392742, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0697522163391113, "global_step": 392743, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0110626220703125, "global_step": 392744, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1419711112976074, "global_step": 392745, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.072777271270752, "global_step": 392746, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0799195766448975, "global_step": 392747, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0098588466644287, "global_step": 392748, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1009361743927, "global_step": 392749, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0775845050811768, "global_step": 392750, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1034839153289795, "global_step": 392751, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.034245491027832, "global_step": 392752, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1122090816497803, "global_step": 392753, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.079068899154663, "global_step": 392754, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.116056203842163, "global_step": 392755, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.020758628845215, "global_step": 392756, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0779175758361816, "global_step": 392757, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1390700340270996, "global_step": 392758, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1619696617126465, "global_step": 392759, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.140688896179199, "global_step": 392760, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1160895824432373, "global_step": 392761, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.146613121032715, "global_step": 392762, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.083052396774292, "global_step": 392763, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1047182083129883, "global_step": 392764, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1471638679504395, "global_step": 392765, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.077502489089966, "global_step": 392766, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.043379783630371, "global_step": 392767, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0649352073669434, "global_step": 392768, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.10402774810791, "global_step": 392769, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0894339084625244, "global_step": 392770, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0505800247192383, "global_step": 392771, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.118818521499634, "global_step": 392772, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.076240062713623, "global_step": 392773, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1467466354370117, "global_step": 392774, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.058736801147461, "global_step": 392775, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1243598461151123, "global_step": 392776, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.974382758140564, "global_step": 392777, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0467703342437744, "global_step": 392778, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.20908784866333, "global_step": 392779, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.008605718612671, "global_step": 392780, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1180007457733154, "global_step": 392781, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1756324768066406, "global_step": 392782, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.024801254272461, "global_step": 392783, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1286404132843018, "global_step": 392784, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1508712768554688, "global_step": 392785, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.111405849456787, "global_step": 392786, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.051539897918701, "global_step": 392787, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1452643871307373, "global_step": 392788, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1470091342926025, "global_step": 392789, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0617964267730713, "global_step": 392790, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1231095790863037, "global_step": 392791, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.241401195526123, "global_step": 392792, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0674221515655518, "global_step": 392793, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0516085624694824, "global_step": 392794, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.096194267272949, "global_step": 392795, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1860077381134033, "global_step": 392796, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1445367336273193, "global_step": 392797, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.095747232437134, "global_step": 392798, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0382893085479736, "global_step": 392799, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.021497964859009, "global_step": 392800, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0590670108795166, "global_step": 392801, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0629513263702393, "global_step": 392802, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.283198356628418, "global_step": 392803, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.13556170463562, "global_step": 392804, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0878348350524902, "global_step": 392805, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1355679035186768, "global_step": 392806, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0809438228607178, "global_step": 392807, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.174252986907959, "global_step": 392808, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.163766384124756, "global_step": 392809, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0996253490448, "global_step": 392810, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1168203353881836, "global_step": 392811, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1463100910186768, "global_step": 392812, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0647530555725098, "global_step": 392813, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1204769611358643, "global_step": 392814, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.144169807434082, "global_step": 392815, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1392428874969482, "global_step": 392816, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0863146781921387, "global_step": 392817, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1470491886138916, "global_step": 392818, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1909244060516357, "global_step": 392819, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1238975524902344, "global_step": 392820, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.2193005084991455, "global_step": 392821, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.118342876434326, "global_step": 392822, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.045661211013794, "global_step": 392823, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.147653341293335, "global_step": 392824, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0970396995544434, "global_step": 392825, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.948184847831726, "global_step": 392826, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.023144006729126, "global_step": 392827, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1625850200653076, "global_step": 392828, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.029099225997925, "global_step": 392829, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1850504875183105, "global_step": 392830, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.116323232650757, "global_step": 392831, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1245484352111816, "global_step": 392832, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0944697856903076, "global_step": 392833, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.013254404067993, "global_step": 392834, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.012244939804077, "global_step": 392835, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1081979274749756, "global_step": 392836, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0555410385131836, "global_step": 392837, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0791690349578857, "global_step": 392838, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1212220191955566, "global_step": 392839, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.076484203338623, "global_step": 392840, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.066336154937744, "global_step": 392841, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1059908866882324, "global_step": 392842, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1405413150787354, "global_step": 392843, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.07659912109375, "global_step": 392844, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1656036376953125, "global_step": 392845, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1497223377227783, "global_step": 392846, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.139291286468506, "global_step": 392847, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1401422023773193, "global_step": 392848, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.032996654510498, "global_step": 392849, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.062539577484131, "global_step": 392850, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.076911211013794, "global_step": 392851, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0396456718444824, "global_step": 392852, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.157392740249634, "global_step": 392853, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1471428871154785, "global_step": 392854, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0945065021514893, "global_step": 392855, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1012589931488037, "global_step": 392856, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.040083169937134, "global_step": 392857, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1801557540893555, "global_step": 392858, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.08062744140625, "global_step": 392859, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.140697956085205, "global_step": 392860, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.071424961090088, "global_step": 392861, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.111027479171753, "global_step": 392862, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.061852216720581, "global_step": 392863, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.052847385406494, "global_step": 392864, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0269854068756104, "global_step": 392865, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.010215997695923, "global_step": 392866, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.14821720123291, "global_step": 392867, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.030566453933716, "global_step": 392868, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.997039794921875, "global_step": 392869, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0219461917877197, "global_step": 392870, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1167783737182617, "global_step": 392871, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1231045722961426, "global_step": 392872, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.045224189758301, "global_step": 392873, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0190210342407227, "global_step": 392874, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.137603521347046, "global_step": 392875, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.075666666030884, "global_step": 392876, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.061617851257324, "global_step": 392877, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.052995204925537, "global_step": 392878, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.042163372039795, "global_step": 392879, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.067021608352661, "global_step": 392880, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.083528995513916, "global_step": 392881, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.083061933517456, "global_step": 392882, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1223127841949463, "global_step": 392883, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0363030433654785, "global_step": 392884, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.071270704269409, "global_step": 392885, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0574660301208496, "global_step": 392886, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1408631801605225, "global_step": 392887, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.108649969100952, "global_step": 392888, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1442294120788574, "global_step": 392889, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.041126012802124, "global_step": 392890, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0444321632385254, "global_step": 392891, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1745595932006836, "global_step": 392892, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.116670846939087, "global_step": 392893, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.110046148300171, "global_step": 392894, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.183901309967041, "global_step": 392895, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.099379301071167, "global_step": 392896, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1626596450805664, "global_step": 392897, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.2167956829071045, "global_step": 392898, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0965940952301025, "global_step": 392899, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.18200945854187, "global_step": 392900, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0624752044677734, "global_step": 392901, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0711545944213867, "global_step": 392902, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.139127254486084, "global_step": 392903, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.142749071121216, "global_step": 392904, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0474681854248047, "global_step": 392905, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.076974868774414, "global_step": 392906, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0970380306243896, "global_step": 392907, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.144709348678589, "global_step": 392908, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.141855001449585, "global_step": 392909, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0189197063446045, "global_step": 392910, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1599624156951904, "global_step": 392911, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1169164180755615, "global_step": 392912, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1002769470214844, "global_step": 392913, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0602340698242188, "global_step": 392914, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0572330951690674, "global_step": 392915, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0453522205352783, "global_step": 392916, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1263020038604736, "global_step": 392917, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.167449951171875, "global_step": 392918, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.099351167678833, "global_step": 392919, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.053727865219116, "global_step": 392920, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0330147743225098, "global_step": 392921, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1190686225891113, "global_step": 392922, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.069714069366455, "global_step": 392923, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0792336463928223, "global_step": 392924, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0735971927642822, "global_step": 392925, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0967118740081787, "global_step": 392926, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.08726167678833, "global_step": 392927, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.078342914581299, "global_step": 392928, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1731419563293457, "global_step": 392929, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1093480587005615, "global_step": 392930, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0661725997924805, "global_step": 392931, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1690945625305176, "global_step": 392932, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.039278030395508, "global_step": 392933, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0758042335510254, "global_step": 392934, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.138641595840454, "global_step": 392935, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.202125072479248, "global_step": 392936, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0489702224731445, "global_step": 392937, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.141688585281372, "global_step": 392938, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.057654619216919, "global_step": 392939, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0445032119750977, "global_step": 392940, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.095095157623291, "global_step": 392941, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1601109504699707, "global_step": 392942, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0953309535980225, "global_step": 392943, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1377251148223877, "global_step": 392944, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0448105335235596, "global_step": 392945, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1064279079437256, "global_step": 392946, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0792319774627686, "global_step": 392947, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.121060848236084, "global_step": 392948, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.115504026412964, "global_step": 392949, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0645651817321777, "global_step": 392950, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0563650131225586, "global_step": 392951, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1350064277648926, "global_step": 392952, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.191530227661133, "global_step": 392953, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1390910148620605, "global_step": 392954, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.9952739477157593, "global_step": 392955, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0008342266082764, "global_step": 392956, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1002376079559326, "global_step": 392957, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1085941791534424, "global_step": 392958, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0573599338531494, "global_step": 392959, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.065438747406006, "global_step": 392960, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1401748657226562, "global_step": 392961, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0889763832092285, "global_step": 392962, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0931971073150635, "global_step": 392963, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.100879192352295, "global_step": 392964, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0737152099609375, "global_step": 392965, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1246001720428467, "global_step": 392966, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0600039958953857, "global_step": 392967, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0734810829162598, "global_step": 392968, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1684768199920654, "global_step": 392969, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0257620811462402, "global_step": 392970, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1473801136016846, "global_step": 392971, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.099245309829712, "global_step": 392972, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.064734697341919, "global_step": 392973, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0722668170928955, "global_step": 392974, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.041191577911377, "global_step": 392975, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.109112024307251, "global_step": 392976, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0076897144317627, "global_step": 392977, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0174083709716797, "global_step": 392978, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.087803602218628, "global_step": 392979, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.035060167312622, "global_step": 392980, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.107159376144409, "global_step": 392981, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.078322410583496, "global_step": 392982, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0657999515533447, "global_step": 392983, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0743842124938965, "global_step": 392984, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.106780529022217, "global_step": 392985, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1177995204925537, "global_step": 392986, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.097163677215576, "global_step": 392987, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.027818202972412, "global_step": 392988, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0152652263641357, "global_step": 392989, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.129913091659546, "global_step": 392990, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0986156463623047, "global_step": 392991, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.9677150249481201, "global_step": 392992, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.088956594467163, "global_step": 392993, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0626220703125, "global_step": 392994, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.105893850326538, "global_step": 392995, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1327974796295166, "global_step": 392996, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1289525032043457, "global_step": 392997, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0750792026519775, "global_step": 392998, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.047752618789673, "global_step": 392999, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.073026657104492, "global_step": 393000, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0502748489379883, "global_step": 393001, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.053295850753784, "global_step": 393002, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0443248748779297, "global_step": 393003, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1637470722198486, "global_step": 393004, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0319597721099854, "global_step": 393005, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1284148693084717, "global_step": 393006, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.149898052215576, "global_step": 393007, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0884177684783936, "global_step": 393008, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1185495853424072, "global_step": 393009, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1172027587890625, "global_step": 393010, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1289594173431396, "global_step": 393011, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.088839054107666, "global_step": 393012, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.111905574798584, "global_step": 393013, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0297086238861084, "global_step": 393014, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0501437187194824, "global_step": 393015, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.074247121810913, "global_step": 393016, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.079730749130249, "global_step": 393017, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0392816066741943, "global_step": 393018, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.066706418991089, "global_step": 393019, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.963508129119873, "global_step": 393020, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0555927753448486, "global_step": 393021, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0232090950012207, "global_step": 393022, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.150357246398926, "global_step": 393023, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1040899753570557, "global_step": 393024, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0808050632476807, "global_step": 393025, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0782551765441895, "global_step": 393026, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.02632999420166, "global_step": 393027, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.022818088531494, "global_step": 393028, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1179559230804443, "global_step": 393029, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.042607307434082, "global_step": 393030, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.027569532394409, "global_step": 393031, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1301262378692627, "global_step": 393032, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1037027835845947, "global_step": 393033, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.083751916885376, "global_step": 393034, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.138413429260254, "global_step": 393035, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.150524139404297, "global_step": 393036, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.072524309158325, "global_step": 393037, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.145571231842041, "global_step": 393038, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.073791980743408, "global_step": 393039, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.136009693145752, "global_step": 393040, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1116347312927246, "global_step": 393041, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0166826248168945, "global_step": 393042, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.091963052749634, "global_step": 393043, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.198758602142334, "global_step": 393044, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1285908222198486, "global_step": 393045, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.007208824157715, "global_step": 393046, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.134768486022949, "global_step": 393047, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0594639778137207, "global_step": 393048, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0858750343322754, "global_step": 393049, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0480332374572754, "global_step": 393050, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1419615745544434, "global_step": 393051, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0891573429107666, "global_step": 393052, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.039520025253296, "global_step": 393053, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1009604930877686, "global_step": 393054, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0938456058502197, "global_step": 393055, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1194264888763428, "global_step": 393056, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1841495037078857, "global_step": 393057, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.044402837753296, "global_step": 393058, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.013828992843628, "global_step": 393059, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.100024700164795, "global_step": 393060, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1270828247070312, "global_step": 393061, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.091780662536621, "global_step": 393062, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0741541385650635, "global_step": 393063, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1139931678771973, "global_step": 393064, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1705527305603027, "global_step": 393065, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0292725563049316, "global_step": 393066, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.063275098800659, "global_step": 393067, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.085890531539917, "global_step": 393068, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0276706218719482, "global_step": 393069, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1847078800201416, "global_step": 393070, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1042823791503906, "global_step": 393071, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0757358074188232, "global_step": 393072, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1811208724975586, "global_step": 393073, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1052157878875732, "global_step": 393074, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0807483196258545, "global_step": 393075, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1319289207458496, "global_step": 393076, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.126758098602295, "global_step": 393077, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0267932415008545, "global_step": 393078, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1120378971099854, "global_step": 393079, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1866514682769775, "global_step": 393080, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1681935787200928, "global_step": 393081, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0722033977508545, "global_step": 393082, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0842368602752686, "global_step": 393083, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1539242267608643, "global_step": 393084, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.129279851913452, "global_step": 393085, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.099310874938965, "global_step": 393086, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1214067935943604, "global_step": 393087, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0703158378601074, "global_step": 393088, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1664693355560303, "global_step": 393089, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0777859687805176, "global_step": 393090, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0889625549316406, "global_step": 393091, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1414706707000732, "global_step": 393092, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.103520393371582, "global_step": 393093, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.14227032661438, "global_step": 393094, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.9895964860916138, "global_step": 393095, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0648820400238037, "global_step": 393096, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.104426622390747, "global_step": 393097, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1045620441436768, "global_step": 393098, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.114712715148926, "global_step": 393099, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.144710063934326, "global_step": 393100, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1323177814483643, "global_step": 393101, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0153322219848633, "global_step": 393102, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0581119060516357, "global_step": 393103, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1088130474090576, "global_step": 393104, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.068530321121216, "global_step": 393105, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1110193729400635, "global_step": 393106, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1437838077545166, "global_step": 393107, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1689634323120117, "global_step": 393108, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1238062381744385, "global_step": 393109, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0403528213500977, "global_step": 393110, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.98684561252594, "global_step": 393111, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.059190511703491, "global_step": 393112, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.049211025238037, "global_step": 393113, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1565191745758057, "global_step": 393114, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.065910577774048, "global_step": 393115, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0675411224365234, "global_step": 393116, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0277342796325684, "global_step": 393117, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.086660861968994, "global_step": 393118, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.123220920562744, "global_step": 393119, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.153960943222046, "global_step": 393120, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.013152599334717, "global_step": 393121, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1224122047424316, "global_step": 393122, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.131415605545044, "global_step": 393123, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0694315433502197, "global_step": 393124, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.9867223501205444, "global_step": 393125, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0225961208343506, "global_step": 393126, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.173252820968628, "global_step": 393127, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1341230869293213, "global_step": 393128, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0020034313201904, "global_step": 393129, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1383466720581055, "global_step": 393130, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0889673233032227, "global_step": 393131, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1166839599609375, "global_step": 393132, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.9725091457366943, "global_step": 393133, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.094356060028076, "global_step": 393134, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.098219394683838, "global_step": 393135, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1617588996887207, "global_step": 393136, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.141775369644165, "global_step": 393137, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.111632823944092, "global_step": 393138, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1431312561035156, "global_step": 393139, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.069636821746826, "global_step": 393140, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1671483516693115, "global_step": 393141, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.057662010192871, "global_step": 393142, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1822750568389893, "global_step": 393143, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1424999237060547, "global_step": 393144, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0647237300872803, "global_step": 393145, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.138367176055908, "global_step": 393146, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0068612098693848, "global_step": 393147, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.131277561187744, "global_step": 393148, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.041189193725586, "global_step": 393149, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1586740016937256, "global_step": 393150, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0666866302490234, "global_step": 393151, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.084850788116455, "global_step": 393152, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0561554431915283, "global_step": 393153, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.111180067062378, "global_step": 393154, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.070983409881592, "global_step": 393155, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1244237422943115, "global_step": 393156, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.160935401916504, "global_step": 393157, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.161938428878784, "global_step": 393158, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1374151706695557, "global_step": 393159, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1178269386291504, "global_step": 393160, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1182034015655518, "global_step": 393161, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1305737495422363, "global_step": 393162, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1359992027282715, "global_step": 393163, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0795578956604004, "global_step": 393164, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.070605754852295, "global_step": 393165, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0779926776885986, "global_step": 393166, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.166666030883789, "global_step": 393167, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1916887760162354, "global_step": 393168, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.056544780731201, "global_step": 393169, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1295382976531982, "global_step": 393170, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.037949562072754, "global_step": 393171, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1223435401916504, "global_step": 393172, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0803728103637695, "global_step": 393173, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.047517776489258, "global_step": 393174, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1340246200561523, "global_step": 393175, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1341803073883057, "global_step": 393176, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0323615074157715, "global_step": 393177, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.031163454055786, "global_step": 393178, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.2067253589630127, "global_step": 393179, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.086418628692627, "global_step": 393180, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.141152858734131, "global_step": 393181, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0438473224639893, "global_step": 393182, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.143484354019165, "global_step": 393183, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.084834098815918, "global_step": 393184, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0908265113830566, "global_step": 393185, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0514729022979736, "global_step": 393186, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0400302410125732, "global_step": 393187, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0866732597351074, "global_step": 393188, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0887961387634277, "global_step": 393189, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1342475414276123, "global_step": 393190, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0498223304748535, "global_step": 393191, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1054747104644775, "global_step": 393192, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1114890575408936, "global_step": 393193, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.092663288116455, "global_step": 393194, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.116177558898926, "global_step": 393195, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1008453369140625, "global_step": 393196, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.071026563644409, "global_step": 393197, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.115570068359375, "global_step": 393198, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1238162517547607, "global_step": 393199, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0581583976745605, "global_step": 393200, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1221771240234375, "global_step": 393201, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.035794973373413, "global_step": 393202, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1984665393829346, "global_step": 393203, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1182169914245605, "global_step": 393204, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0869247913360596, "global_step": 393205, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.07830548286438, "global_step": 393206, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.088172197341919, "global_step": 393207, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.9932798147201538, "global_step": 393208, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.177976131439209, "global_step": 393209, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1207590103149414, "global_step": 393210, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1472277641296387, "global_step": 393211, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1192104816436768, "global_step": 393212, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0854060649871826, "global_step": 393213, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0587971210479736, "global_step": 393214, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1700024604797363, "global_step": 393215, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1382317543029785, "global_step": 393216, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.148667573928833, "global_step": 393217, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.216728687286377, "global_step": 393218, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1515402793884277, "global_step": 393219, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1326475143432617, "global_step": 393220, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1226463317871094, "global_step": 393221, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1776270866394043, "global_step": 393222, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.042311668395996, "global_step": 393223, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1355152130126953, "global_step": 393224, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.071450710296631, "global_step": 393225, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.2025978565216064, "global_step": 393226, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.124171495437622, "global_step": 393227, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.138110876083374, "global_step": 393228, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.161363363265991, "global_step": 393229, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.2251763343811035, "global_step": 393230, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1007189750671387, "global_step": 393231, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.103912115097046, "global_step": 393232, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1089444160461426, "global_step": 393233, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0599377155303955, "global_step": 393234, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.090338706970215, "global_step": 393235, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0819008350372314, "global_step": 393236, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1296629905700684, "global_step": 393237, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0898869037628174, "global_step": 393238, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0925328731536865, "global_step": 393239, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0428667068481445, "global_step": 393240, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.9826571941375732, "global_step": 393241, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1019721031188965, "global_step": 393242, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.085109233856201, "global_step": 393243, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0827927589416504, "global_step": 393244, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.08063006401062, "global_step": 393245, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.08960223197937, "global_step": 393246, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.085322618484497, "global_step": 393247, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0411596298217773, "global_step": 393248, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.079292058944702, "global_step": 393249, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.079390525817871, "global_step": 393250, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.106147289276123, "global_step": 393251, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0915775299072266, "global_step": 393252, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.101033926010132, "global_step": 393253, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1377880573272705, "global_step": 393254, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.090813398361206, "global_step": 393255, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1022236347198486, "global_step": 393256, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1249911785125732, "global_step": 393257, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1062839031219482, "global_step": 393258, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.067470073699951, "global_step": 393259, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0202229022979736, "global_step": 393260, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1365396976470947, "global_step": 393261, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.9932761192321777, "global_step": 393262, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.131709337234497, "global_step": 393263, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0414323806762695, "global_step": 393264, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1461617946624756, "global_step": 393265, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.137641191482544, "global_step": 393266, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1392018795013428, "global_step": 393267, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0739827156066895, "global_step": 393268, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.167835235595703, "global_step": 393269, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1357295513153076, "global_step": 393270, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0799012184143066, "global_step": 393271, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0712199211120605, "global_step": 393272, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1877496242523193, "global_step": 393273, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.078572988510132, "global_step": 393274, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1511971950531006, "global_step": 393275, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1066057682037354, "global_step": 393276, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.012930393218994, "global_step": 393277, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1290602684020996, "global_step": 393278, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0340020656585693, "global_step": 393279, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.115607738494873, "global_step": 393280, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0540590286254883, "global_step": 393281, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.160170078277588, "global_step": 393282, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1230127811431885, "global_step": 393283, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.082188606262207, "global_step": 393284, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.090294361114502, "global_step": 393285, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1976006031036377, "global_step": 393286, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.133500814437866, "global_step": 393287, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0153260231018066, "global_step": 393288, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.079725503921509, "global_step": 393289, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0874485969543457, "global_step": 393290, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.135132312774658, "global_step": 393291, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1422038078308105, "global_step": 393292, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1160402297973633, "global_step": 393293, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0630106925964355, "global_step": 393294, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.043269157409668, "global_step": 393295, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0977327823638916, "global_step": 393296, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1256401538848877, "global_step": 393297, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0956013202667236, "global_step": 393298, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0778422355651855, "global_step": 393299, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.089937210083008, "global_step": 393300, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.10021710395813, "global_step": 393301, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0729427337646484, "global_step": 393302, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.105318069458008, "global_step": 393303, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0854790210723877, "global_step": 393304, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.092522621154785, "global_step": 393305, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1984610557556152, "global_step": 393306, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0741536617279053, "global_step": 393307, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.120094060897827, "global_step": 393308, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1292154788970947, "global_step": 393309, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0959839820861816, "global_step": 393310, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1730551719665527, "global_step": 393311, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1649599075317383, "global_step": 393312, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.049650192260742, "global_step": 393313, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1648521423339844, "global_step": 393314, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1159942150115967, "global_step": 393315, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.098391056060791, "global_step": 393316, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1829047203063965, "global_step": 393317, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0936899185180664, "global_step": 393318, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0588083267211914, "global_step": 393319, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1185269355773926, "global_step": 393320, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1279900074005127, "global_step": 393321, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.9963041543960571, "global_step": 393322, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0907459259033203, "global_step": 393323, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.158153533935547, "global_step": 393324, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0997180938720703, "global_step": 393325, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0287301540374756, "global_step": 393326, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1809000968933105, "global_step": 393327, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.9895740747451782, "global_step": 393328, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.127800226211548, "global_step": 393329, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1827189922332764, "global_step": 393330, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0474836826324463, "global_step": 393331, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1560068130493164, "global_step": 393332, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1411359310150146, "global_step": 393333, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.102001905441284, "global_step": 393334, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.071704864501953, "global_step": 393335, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0929031372070312, "global_step": 393336, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1207048892974854, "global_step": 393337, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0293331146240234, "global_step": 393338, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0686686038970947, "global_step": 393339, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.056511640548706, "global_step": 393340, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1048293113708496, "global_step": 393341, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.157073736190796, "global_step": 393342, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1028575897216797, "global_step": 393343, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.117810010910034, "global_step": 393344, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0440077781677246, "global_step": 393345, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1285009384155273, "global_step": 393346, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0484962463378906, "global_step": 393347, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.029123544692993, "global_step": 393348, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1178183555603027, "global_step": 393349, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0793166160583496, "global_step": 393350, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0428032875061035, "global_step": 393351, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.108963966369629, "global_step": 393352, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0770180225372314, "global_step": 393353, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.170039653778076, "global_step": 393354, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1634740829467773, "global_step": 393355, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0937564373016357, "global_step": 393356, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.179278612136841, "global_step": 393357, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1023640632629395, "global_step": 393358, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1189422607421875, "global_step": 393359, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1986019611358643, "global_step": 393360, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.188547134399414, "global_step": 393361, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.101799249649048, "global_step": 393362, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.106315851211548, "global_step": 393363, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.160062074661255, "global_step": 393364, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0918385982513428, "global_step": 393365, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0444648265838623, "global_step": 393366, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.082939386367798, "global_step": 393367, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.161407947540283, "global_step": 393368, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.089359760284424, "global_step": 393369, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.121316432952881, "global_step": 393370, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.059176445007324, "global_step": 393371, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.065781354904175, "global_step": 393372, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0342917442321777, "global_step": 393373, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.111297369003296, "global_step": 393374, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.040534257888794, "global_step": 393375, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1161341667175293, "global_step": 393376, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.094362258911133, "global_step": 393377, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0579590797424316, "global_step": 393378, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1558902263641357, "global_step": 393379, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1146490573883057, "global_step": 393380, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.105985403060913, "global_step": 393381, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.048036575317383, "global_step": 393382, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.075711488723755, "global_step": 393383, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.050891399383545, "global_step": 393384, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.095093250274658, "global_step": 393385, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1285316944122314, "global_step": 393386, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1221909523010254, "global_step": 393387, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.2297306060791016, "global_step": 393388, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.111509084701538, "global_step": 393389, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.097134828567505, "global_step": 393390, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1822760105133057, "global_step": 393391, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1479313373565674, "global_step": 393392, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0761656761169434, "global_step": 393393, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.060943603515625, "global_step": 393394, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.008451461791992, "global_step": 393395, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1214189529418945, "global_step": 393396, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.089362144470215, "global_step": 393397, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.111340284347534, "global_step": 393398, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.13230037689209, "global_step": 393399, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.16361927986145, "global_step": 393400, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1364963054656982, "global_step": 393401, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.039661407470703, "global_step": 393402, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0896620750427246, "global_step": 393403, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.131147623062134, "global_step": 393404, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1338162422180176, "global_step": 393405, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1491153240203857, "global_step": 393406, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0868146419525146, "global_step": 393407, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.027797222137451, "global_step": 393408, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.161316394805908, "global_step": 393409, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.079437255859375, "global_step": 393410, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.053447961807251, "global_step": 393411, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0272552967071533, "global_step": 393412, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.9824304580688477, "global_step": 393413, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1100423336029053, "global_step": 393414, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1770997047424316, "global_step": 393415, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.182011842727661, "global_step": 393416, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.029261589050293, "global_step": 393417, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.227302312850952, "global_step": 393418, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.076470375061035, "global_step": 393419, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0973358154296875, "global_step": 393420, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1701395511627197, "global_step": 393421, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1258456707000732, "global_step": 393422, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0631916522979736, "global_step": 393423, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1302783489227295, "global_step": 393424, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.075563907623291, "global_step": 393425, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.167769432067871, "global_step": 393426, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1908042430877686, "global_step": 393427, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.014118194580078, "global_step": 393428, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1161258220672607, "global_step": 393429, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1362717151641846, "global_step": 393430, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.121614694595337, "global_step": 393431, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1352639198303223, "global_step": 393432, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1376376152038574, "global_step": 393433, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0890040397644043, "global_step": 393434, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.088279962539673, "global_step": 393435, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1262853145599365, "global_step": 393436, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.127656936645508, "global_step": 393437, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0573811531066895, "global_step": 393438, "epoch": 755, "lr": 5e-05}
{"train_loss": 1.9825270175933838, "global_step": 393439, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.017573118209839, "global_step": 393440, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1579489707946777, "global_step": 393441, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1142191886901855, "global_step": 393442, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1141207218170166, "global_step": 393443, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1663262844085693, "global_step": 393444, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.105828285217285, "global_step": 393445, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.144016742706299, "global_step": 393446, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1363110542297363, "global_step": 393447, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.103285312652588, "global_step": 393448, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1119420528411865, "global_step": 393449, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.121455669403076, "global_step": 393450, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1552553176879883, "global_step": 393451, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1779043674468994, "global_step": 393452, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0729806423187256, "global_step": 393453, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.021380662918091, "global_step": 393454, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.115361452102661, "global_step": 393455, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.115107536315918, "global_step": 393456, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.005176305770874, "global_step": 393457, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1679434776306152, "global_step": 393458, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1215133666992188, "global_step": 393459, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.136683940887451, "global_step": 393460, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.08026123046875, "global_step": 393461, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.08784556388855, "global_step": 393462, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.121129035949707, "global_step": 393463, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1744508743286133, "global_step": 393464, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.044869899749756, "global_step": 393465, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1236624717712402, "global_step": 393466, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.132580280303955, "global_step": 393467, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0558693408966064, "global_step": 393468, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0477206707000732, "global_step": 393469, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0877084732055664, "global_step": 393470, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.058745861053467, "global_step": 393471, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1289687156677246, "global_step": 393472, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.083502769470215, "global_step": 393473, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1629319190979004, "global_step": 393474, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0286149978637695, "global_step": 393475, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.050323009490967, "global_step": 393476, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.060379981994629, "global_step": 393477, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1953744888305664, "global_step": 393478, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0580227375030518, "global_step": 393479, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1102025508880615, "global_step": 393480, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.046661615371704, "global_step": 393481, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.091656446456909, "global_step": 393482, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.137878894805908, "global_step": 393483, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.080552816390991, "global_step": 393484, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.057231903076172, "global_step": 393485, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.085003614425659, "global_step": 393486, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1273410320281982, "global_step": 393487, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0853073596954346, "global_step": 393488, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1148886680603027, "global_step": 393489, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1406021118164062, "global_step": 393490, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1843454837799072, "global_step": 393491, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0941216945648193, "global_step": 393492, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0359199047088623, "global_step": 393493, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.189312219619751, "global_step": 393494, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.2143638134002686, "global_step": 393495, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.162750244140625, "global_step": 393496, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1171867847442627, "global_step": 393497, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0998568534851074, "global_step": 393498, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.144619941711426, "global_step": 393499, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1055562496185303, "global_step": 393500, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1013059616088867, "global_step": 393501, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.162592887878418, "global_step": 393502, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0890445709228516, "global_step": 393503, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0922200679779053, "global_step": 393504, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0604777336120605, "global_step": 393505, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.143666982650757, "global_step": 393506, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1253206729888916, "global_step": 393507, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1493098735809326, "global_step": 393508, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1294755935668945, "global_step": 393509, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0913491249084473, "global_step": 393510, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1580910682678223, "global_step": 393511, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0908727645874023, "global_step": 393512, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.108872413635254, "global_step": 393513, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0939583778381348, "global_step": 393514, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.091357946395874, "global_step": 393515, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0381574630737305, "global_step": 393516, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1701853275299072, "global_step": 393517, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0311412811279297, "global_step": 393518, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0897722244262695, "global_step": 393519, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0688841342926025, "global_step": 393520, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.156027317047119, "global_step": 393521, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.138000249862671, "global_step": 393522, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.091005563735962, "global_step": 393523, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0133414268493652, "global_step": 393524, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0583362579345703, "global_step": 393525, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.03757905960083, "global_step": 393526, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1606082916259766, "global_step": 393527, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.2306745052337646, "global_step": 393528, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.087177038192749, "global_step": 393529, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.011556386947632, "global_step": 393530, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.030853271484375, "global_step": 393531, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1620593070983887, "global_step": 393532, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1201417446136475, "global_step": 393533, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.105591058731079, "global_step": 393534, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.110400438308716, "global_step": 393535, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0724003314971924, "global_step": 393536, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.193880558013916, "global_step": 393537, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1985092163085938, "global_step": 393538, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.060943841934204, "global_step": 393539, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1487340927124023, "global_step": 393540, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0894665718078613, "global_step": 393541, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1093556880950928, "global_step": 393542, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.085014820098877, "global_step": 393543, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0650861263275146, "global_step": 393544, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.1140859127044678, "global_step": 393545, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0987794399261475, "global_step": 393546, "epoch": 755, "lr": 5e-05}
{"train_loss": 2.0372276306152344, "global_step": 393547, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1649694442749023, "global_step": 393548, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.040689468383789, "global_step": 393549, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.064152717590332, "global_step": 393550, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0848379135131836, "global_step": 393551, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.105023145675659, "global_step": 393552, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.187107563018799, "global_step": 393553, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.9983057975769043, "global_step": 393554, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0502305030822754, "global_step": 393555, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.017998695373535, "global_step": 393556, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1578011512756348, "global_step": 393557, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1257619857788086, "global_step": 393558, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1497440338134766, "global_step": 393559, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1300265789031982, "global_step": 393560, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0801069736480713, "global_step": 393561, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.063675880432129, "global_step": 393562, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0054242610931396, "global_step": 393563, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.039412260055542, "global_step": 393564, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0985324382781982, "global_step": 393565, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1454830169677734, "global_step": 393566, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.127650499343872, "global_step": 393567, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0554749965667725, "global_step": 393568, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.137087106704712, "global_step": 393569, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0425171852111816, "global_step": 393570, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1657063961029053, "global_step": 393571, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.030963659286499, "global_step": 393572, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1058104038238525, "global_step": 393573, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.055044412612915, "global_step": 393574, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0632171630859375, "global_step": 393575, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.028143882751465, "global_step": 393576, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.154794931411743, "global_step": 393577, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.071831226348877, "global_step": 393578, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.154233932495117, "global_step": 393579, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.185166358947754, "global_step": 393580, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1239657402038574, "global_step": 393581, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.139763832092285, "global_step": 393582, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0559041500091553, "global_step": 393583, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1293177604675293, "global_step": 393584, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1503143310546875, "global_step": 393585, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.064911365509033, "global_step": 393586, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1067163944244385, "global_step": 393587, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.114694118499756, "global_step": 393588, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1562373638153076, "global_step": 393589, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1634092330932617, "global_step": 393590, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.121084451675415, "global_step": 393591, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.109715700149536, "global_step": 393592, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.9916067123413086, "global_step": 393593, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.031036853790283, "global_step": 393594, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.08721661567688, "global_step": 393595, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1974005699157715, "global_step": 393596, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1464171409606934, "global_step": 393597, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0987651348114014, "global_step": 393598, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1459832191467285, "global_step": 393599, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0859084129333496, "global_step": 393600, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.134092330932617, "global_step": 393601, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1092681884765625, "global_step": 393602, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1296544075012207, "global_step": 393603, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1355152130126953, "global_step": 393604, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.043485641479492, "global_step": 393605, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1068265438079834, "global_step": 393606, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1043972969055176, "global_step": 393607, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.028754949569702, "global_step": 393608, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1069116592407227, "global_step": 393609, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.064943552017212, "global_step": 393610, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0727415084838867, "global_step": 393611, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.111778497695923, "global_step": 393612, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.062311887741089, "global_step": 393613, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0983994007110596, "global_step": 393614, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.176637887954712, "global_step": 393615, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.02532958984375, "global_step": 393616, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.109076738357544, "global_step": 393617, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.087937831878662, "global_step": 393618, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0878183841705322, "global_step": 393619, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1389737129211426, "global_step": 393620, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.071394681930542, "global_step": 393621, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0725975036621094, "global_step": 393622, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1079697608947754, "global_step": 393623, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.00378680229187, "global_step": 393624, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.097243309020996, "global_step": 393625, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.087649345397949, "global_step": 393626, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0721356868743896, "global_step": 393627, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.16721773147583, "global_step": 393628, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0762996673583984, "global_step": 393629, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0841526985168457, "global_step": 393630, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1058781147003174, "global_step": 393631, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.128967761993408, "global_step": 393632, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0499889850616455, "global_step": 393633, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1160802841186523, "global_step": 393634, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1483616828918457, "global_step": 393635, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.141773223876953, "global_step": 393636, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.046592950820923, "global_step": 393637, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.062972068786621, "global_step": 393638, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0945043563842773, "global_step": 393639, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.078887701034546, "global_step": 393640, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0421042442321777, "global_step": 393641, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1326546669006348, "global_step": 393642, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.069068193435669, "global_step": 393643, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.9554779529571533, "global_step": 393644, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.2148962020874023, "global_step": 393645, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0672781467437744, "global_step": 393646, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.079820156097412, "global_step": 393647, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1466891765594482, "global_step": 393648, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.102088451385498, "global_step": 393649, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.014223337173462, "global_step": 393650, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.2212882041931152, "global_step": 393651, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0947930812835693, "global_step": 393652, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1015872955322266, "global_step": 393653, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.067739248275757, "global_step": 393654, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.996242880821228, "global_step": 393655, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0896503925323486, "global_step": 393656, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.165092945098877, "global_step": 393657, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.021604061126709, "global_step": 393658, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0637707710266113, "global_step": 393659, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.054718494415283, "global_step": 393660, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.111278772354126, "global_step": 393661, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.028679847717285, "global_step": 393662, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.107762098312378, "global_step": 393663, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.969176173210144, "global_step": 393664, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.085747241973877, "global_step": 393665, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1200380325317383, "global_step": 393666, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0704450607299805, "global_step": 393667, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.087012529373169, "global_step": 393668, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0677857398986816, "global_step": 393669, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.9841639995574951, "global_step": 393670, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1243584156036377, "global_step": 393671, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0405185222625732, "global_step": 393672, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0863606929779053, "global_step": 393673, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.083789825439453, "global_step": 393674, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0658819675445557, "global_step": 393675, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.08160138130188, "global_step": 393676, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.104518413543701, "global_step": 393677, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1278278827667236, "global_step": 393678, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1311638355255127, "global_step": 393679, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0724053382873535, "global_step": 393680, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0774214267730713, "global_step": 393681, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0715062618255615, "global_step": 393682, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1006643772125244, "global_step": 393683, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0772476196289062, "global_step": 393684, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1180872917175293, "global_step": 393685, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.059565544128418, "global_step": 393686, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.077486991882324, "global_step": 393687, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.091655969619751, "global_step": 393688, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.078842878341675, "global_step": 393689, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.166710138320923, "global_step": 393690, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.169771671295166, "global_step": 393691, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.12880802154541, "global_step": 393692, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0776209831237793, "global_step": 393693, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1663753986358643, "global_step": 393694, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.084101915359497, "global_step": 393695, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1738765239715576, "global_step": 393696, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.012470006942749, "global_step": 393697, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0207924842834473, "global_step": 393698, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.9555232524871826, "global_step": 393699, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.079531669616699, "global_step": 393700, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.055158853530884, "global_step": 393701, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1102216243743896, "global_step": 393702, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1000723838806152, "global_step": 393703, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.171802520751953, "global_step": 393704, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.040213108062744, "global_step": 393705, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.212310791015625, "global_step": 393706, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.2067923545837402, "global_step": 393707, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1091699600219727, "global_step": 393708, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.104863405227661, "global_step": 393709, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.121412992477417, "global_step": 393710, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1926541328430176, "global_step": 393711, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.21360182762146, "global_step": 393712, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.068016529083252, "global_step": 393713, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1187920570373535, "global_step": 393714, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1464362144470215, "global_step": 393715, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0950491428375244, "global_step": 393716, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.093423366546631, "global_step": 393717, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1317176818847656, "global_step": 393718, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1057560443878174, "global_step": 393719, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1484780311584473, "global_step": 393720, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.094377040863037, "global_step": 393721, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1002159118652344, "global_step": 393722, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1633691787719727, "global_step": 393723, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0248258113861084, "global_step": 393724, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.095338821411133, "global_step": 393725, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1135473251342773, "global_step": 393726, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1322460174560547, "global_step": 393727, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0935897827148438, "global_step": 393728, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0734946727752686, "global_step": 393729, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.084397077560425, "global_step": 393730, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1004464626312256, "global_step": 393731, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.189211130142212, "global_step": 393732, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.064692735671997, "global_step": 393733, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.143162488937378, "global_step": 393734, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1002118587493896, "global_step": 393735, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1102497577667236, "global_step": 393736, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.120755195617676, "global_step": 393737, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1037886142730713, "global_step": 393738, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.119068145751953, "global_step": 393739, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.2332465648651123, "global_step": 393740, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0549709796905518, "global_step": 393741, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.082648992538452, "global_step": 393742, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1313962936401367, "global_step": 393743, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.081223249435425, "global_step": 393744, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.089621067047119, "global_step": 393745, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1176788806915283, "global_step": 393746, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1363537311553955, "global_step": 393747, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1350059509277344, "global_step": 393748, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1328794956207275, "global_step": 393749, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0953187942504883, "global_step": 393750, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.101520299911499, "global_step": 393751, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.087475299835205, "global_step": 393752, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0297560691833496, "global_step": 393753, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1522319316864014, "global_step": 393754, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.112128734588623, "global_step": 393755, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1914989948272705, "global_step": 393756, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.077937602996826, "global_step": 393757, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0989973545074463, "global_step": 393758, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.9795504808425903, "global_step": 393759, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1564738750457764, "global_step": 393760, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.03143048286438, "global_step": 393761, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.084961175918579, "global_step": 393762, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.128812313079834, "global_step": 393763, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0510306358337402, "global_step": 393764, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.090175151824951, "global_step": 393765, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.029226779937744, "global_step": 393766, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.045518398284912, "global_step": 393767, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0551719665527344, "global_step": 393768, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.120731830596924, "global_step": 393769, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0748798847198486, "global_step": 393770, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.9980231523513794, "global_step": 393771, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.194688558578491, "global_step": 393772, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.060131072998047, "global_step": 393773, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1011416912078857, "global_step": 393774, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.187932252883911, "global_step": 393775, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.112764358520508, "global_step": 393776, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.090208053588867, "global_step": 393777, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1007888317108154, "global_step": 393778, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.166865587234497, "global_step": 393779, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.151071310043335, "global_step": 393780, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1169536113739014, "global_step": 393781, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0723772048950195, "global_step": 393782, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0973987579345703, "global_step": 393783, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1726443767547607, "global_step": 393784, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.049253463745117, "global_step": 393785, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.068190813064575, "global_step": 393786, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0739500522613525, "global_step": 393787, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0195817947387695, "global_step": 393788, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0751795768737793, "global_step": 393789, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1126675605773926, "global_step": 393790, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1668169498443604, "global_step": 393791, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1036384105682373, "global_step": 393792, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1568689346313477, "global_step": 393793, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1284332275390625, "global_step": 393794, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.123950958251953, "global_step": 393795, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.174468994140625, "global_step": 393796, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0975542068481445, "global_step": 393797, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1093404293060303, "global_step": 393798, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1047637462615967, "global_step": 393799, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.9880746603012085, "global_step": 393800, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0759341716766357, "global_step": 393801, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1293952465057373, "global_step": 393802, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.149500846862793, "global_step": 393803, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0783753395080566, "global_step": 393804, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1701173782348633, "global_step": 393805, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0933291912078857, "global_step": 393806, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.101433277130127, "global_step": 393807, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.105452537536621, "global_step": 393808, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.153290271759033, "global_step": 393809, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0762219429016113, "global_step": 393810, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0095489025115967, "global_step": 393811, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.986383080482483, "global_step": 393812, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0707740783691406, "global_step": 393813, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0526716709136963, "global_step": 393814, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.170147180557251, "global_step": 393815, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1147537231445312, "global_step": 393816, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.103632926940918, "global_step": 393817, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0399703979492188, "global_step": 393818, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1817288398742676, "global_step": 393819, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1471896171569824, "global_step": 393820, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.155174732208252, "global_step": 393821, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0872671604156494, "global_step": 393822, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0903642177581787, "global_step": 393823, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0886237621307373, "global_step": 393824, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.048527717590332, "global_step": 393825, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.043794870376587, "global_step": 393826, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.042775869369507, "global_step": 393827, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0589730739593506, "global_step": 393828, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1445610523223877, "global_step": 393829, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1653943061828613, "global_step": 393830, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.101073741912842, "global_step": 393831, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0672805309295654, "global_step": 393832, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.032524347305298, "global_step": 393833, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1154794692993164, "global_step": 393834, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.117368221282959, "global_step": 393835, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0227537155151367, "global_step": 393836, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.159902572631836, "global_step": 393837, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0388894081115723, "global_step": 393838, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.16105318069458, "global_step": 393839, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0592780113220215, "global_step": 393840, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.070862054824829, "global_step": 393841, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1184988021850586, "global_step": 393842, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1135940551757812, "global_step": 393843, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.090158462524414, "global_step": 393844, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1247994899749756, "global_step": 393845, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1206884384155273, "global_step": 393846, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1140942573547363, "global_step": 393847, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0050315856933594, "global_step": 393848, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.033780336380005, "global_step": 393849, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.127880811691284, "global_step": 393850, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0789544582366943, "global_step": 393851, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0186638832092285, "global_step": 393852, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1045942306518555, "global_step": 393853, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0073533058166504, "global_step": 393854, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1057324409484863, "global_step": 393855, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.130035638809204, "global_step": 393856, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.050110340118408, "global_step": 393857, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1166746616363525, "global_step": 393858, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1992006301879883, "global_step": 393859, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1536219120025635, "global_step": 393860, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0483405590057373, "global_step": 393861, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.132607936859131, "global_step": 393862, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0331320762634277, "global_step": 393863, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1024043560028076, "global_step": 393864, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.109154224395752, "global_step": 393865, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0257198810577393, "global_step": 393866, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1673176288604736, "global_step": 393867, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1254115104675293, "global_step": 393868, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1046388149261475, "global_step": 393869, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0449514389038086, "global_step": 393870, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.095376968383789, "global_step": 393871, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.015754222869873, "global_step": 393872, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.9898083209991455, "global_step": 393873, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.078307628631592, "global_step": 393874, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0585274696350098, "global_step": 393875, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0217883586883545, "global_step": 393876, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.960438847541809, "global_step": 393877, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.090336322784424, "global_step": 393878, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.144794225692749, "global_step": 393879, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.085749387741089, "global_step": 393880, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.140444040298462, "global_step": 393881, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.136002779006958, "global_step": 393882, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1335997581481934, "global_step": 393883, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0114693641662598, "global_step": 393884, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.090614080429077, "global_step": 393885, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.05747652053833, "global_step": 393886, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.060544490814209, "global_step": 393887, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.156460762023926, "global_step": 393888, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0767288208007812, "global_step": 393889, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.070544481277466, "global_step": 393890, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0513041019439697, "global_step": 393891, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1251320838928223, "global_step": 393892, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.132474184036255, "global_step": 393893, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0779614448547363, "global_step": 393894, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.114647150039673, "global_step": 393895, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1556496620178223, "global_step": 393896, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1325995922088623, "global_step": 393897, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.204420328140259, "global_step": 393898, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.040127992630005, "global_step": 393899, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1431000232696533, "global_step": 393900, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0033183097839355, "global_step": 393901, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1529412269592285, "global_step": 393902, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.163590908050537, "global_step": 393903, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1778929233551025, "global_step": 393904, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0664706230163574, "global_step": 393905, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.029259443283081, "global_step": 393906, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.20851731300354, "global_step": 393907, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.123364210128784, "global_step": 393908, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.083674669265747, "global_step": 393909, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.114243507385254, "global_step": 393910, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.000330686569214, "global_step": 393911, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1031861305236816, "global_step": 393912, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.090688467025757, "global_step": 393913, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0887317657470703, "global_step": 393914, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1222026348114014, "global_step": 393915, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.107665538787842, "global_step": 393916, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0620789527893066, "global_step": 393917, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0978174209594727, "global_step": 393918, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1178090572357178, "global_step": 393919, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.055776357650757, "global_step": 393920, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1224942207336426, "global_step": 393921, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0350327491760254, "global_step": 393922, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1772422790527344, "global_step": 393923, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.123852491378784, "global_step": 393924, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0182504653930664, "global_step": 393925, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1565394401550293, "global_step": 393926, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.115220069885254, "global_step": 393927, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.059468984603882, "global_step": 393928, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.138923406600952, "global_step": 393929, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1017637252807617, "global_step": 393930, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0898754596710205, "global_step": 393931, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.073657512664795, "global_step": 393932, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0639617443084717, "global_step": 393933, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0633254051208496, "global_step": 393934, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0487513542175293, "global_step": 393935, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.163226366043091, "global_step": 393936, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0871803760528564, "global_step": 393937, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.2130367755889893, "global_step": 393938, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0910205841064453, "global_step": 393939, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1094343662261963, "global_step": 393940, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.030252456665039, "global_step": 393941, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.054795980453491, "global_step": 393942, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.127368927001953, "global_step": 393943, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.07706618309021, "global_step": 393944, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0946877002716064, "global_step": 393945, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.092482089996338, "global_step": 393946, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.163229465484619, "global_step": 393947, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0678677558898926, "global_step": 393948, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1542444229125977, "global_step": 393949, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0343410968780518, "global_step": 393950, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.085819721221924, "global_step": 393951, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.058152675628662, "global_step": 393952, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.139094114303589, "global_step": 393953, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.082653522491455, "global_step": 393954, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.12013840675354, "global_step": 393955, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.072944164276123, "global_step": 393956, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.09440279006958, "global_step": 393957, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0675127506256104, "global_step": 393958, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1023499965667725, "global_step": 393959, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1662137508392334, "global_step": 393960, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0468177795410156, "global_step": 393961, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0711517333984375, "global_step": 393962, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.09313702583313, "global_step": 393963, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0931684970855713, "global_step": 393964, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0132675170898438, "global_step": 393965, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.039433002471924, "global_step": 393966, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.03175950050354, "global_step": 393967, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.102099895477295, "global_step": 393968, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0849175453186035, "global_step": 393969, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.172610282897949, "global_step": 393970, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.028001546859741, "global_step": 393971, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1196093559265137, "global_step": 393972, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.157602071762085, "global_step": 393973, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.092334270477295, "global_step": 393974, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1198811531066895, "global_step": 393975, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1255059242248535, "global_step": 393976, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0809171199798584, "global_step": 393977, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0898289680480957, "global_step": 393978, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.11696195602417, "global_step": 393979, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0853846073150635, "global_step": 393980, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.101881980895996, "global_step": 393981, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1331024169921875, "global_step": 393982, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0622317790985107, "global_step": 393983, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0335564613342285, "global_step": 393984, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0932679176330566, "global_step": 393985, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0674493312835693, "global_step": 393986, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1158878803253174, "global_step": 393987, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0799570083618164, "global_step": 393988, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.083749294281006, "global_step": 393989, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.120994806289673, "global_step": 393990, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1561200618743896, "global_step": 393991, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1025140285491943, "global_step": 393992, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.030547857284546, "global_step": 393993, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0989816188812256, "global_step": 393994, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.050516366958618, "global_step": 393995, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0961098670959473, "global_step": 393996, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.102639675140381, "global_step": 393997, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.096400737762451, "global_step": 393998, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.134763717651367, "global_step": 393999, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.2290492057800293, "global_step": 394000, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.040776491165161, "global_step": 394001, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.107513189315796, "global_step": 394002, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1103177070617676, "global_step": 394003, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1241278648376465, "global_step": 394004, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.149219036102295, "global_step": 394005, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.096024751663208, "global_step": 394006, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1961092948913574, "global_step": 394007, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0609471797943115, "global_step": 394008, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.17392897605896, "global_step": 394009, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.017526865005493, "global_step": 394010, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0462119579315186, "global_step": 394011, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0879132747650146, "global_step": 394012, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.130859136581421, "global_step": 394013, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.126269578933716, "global_step": 394014, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.142305612564087, "global_step": 394015, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0411481857299805, "global_step": 394016, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.089693069458008, "global_step": 394017, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0614333152770996, "global_step": 394018, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1269052028656006, "global_step": 394019, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.172416925430298, "global_step": 394020, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.17063045501709, "global_step": 394021, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0645077228546143, "global_step": 394022, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.024442195892334, "global_step": 394023, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0770678520202637, "global_step": 394024, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.132824420928955, "global_step": 394025, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0927767753601074, "global_step": 394026, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0336732864379883, "global_step": 394027, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.191547155380249, "global_step": 394028, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0521247386932373, "global_step": 394029, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0804972648620605, "global_step": 394030, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.097534418106079, "global_step": 394031, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.060535192489624, "global_step": 394032, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.042445182800293, "global_step": 394033, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.148343563079834, "global_step": 394034, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1825366020202637, "global_step": 394035, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0619208812713623, "global_step": 394036, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.012601137161255, "global_step": 394037, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.141108989715576, "global_step": 394038, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0372068881988525, "global_step": 394039, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.085360527038574, "global_step": 394040, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0943117141723633, "global_step": 394041, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0152087211608887, "global_step": 394042, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1703174114227295, "global_step": 394043, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0914058685302734, "global_step": 394044, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1539907455444336, "global_step": 394045, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1424975395202637, "global_step": 394046, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1055169105529785, "global_step": 394047, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0923776626586914, "global_step": 394048, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.025240659713745, "global_step": 394049, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.216277599334717, "global_step": 394050, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1029763221740723, "global_step": 394051, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.130307197570801, "global_step": 394052, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.122605323791504, "global_step": 394053, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0994014739990234, "global_step": 394054, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.046546459197998, "global_step": 394055, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.099900722503662, "global_step": 394056, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0619494915008545, "global_step": 394057, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1601929664611816, "global_step": 394058, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1266214847564697, "global_step": 394059, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0330891609191895, "global_step": 394060, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.110924482345581, "global_step": 394061, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.116248369216919, "global_step": 394062, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.120088815689087, "global_step": 394063, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.16387939453125, "global_step": 394064, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.040139675140381, "global_step": 394065, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0251238346099854, "global_step": 394066, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0436758995056152, "global_step": 394067, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.169442653656006, "global_step": 394068, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.131791591644287, "global_step": 394069, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.073681116104126, "global_step": 394070, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1095592975616455, "global_step": 394071, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0757930278778076, "global_step": 394072, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1658685207366943, "global_step": 394073, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.080838680267334, "global_step": 394074, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.095935106277466, "global_step": 394075, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.062696695327759, "global_step": 394076, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.2063934803009033, "global_step": 394077, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0568645000457764, "global_step": 394078, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0265321731567383, "global_step": 394079, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1130173206329346, "global_step": 394080, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1681010723114014, "global_step": 394081, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.038614273071289, "global_step": 394082, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.101283073425293, "global_step": 394083, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1390984058380127, "global_step": 394084, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.123992919921875, "global_step": 394085, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0396554470062256, "global_step": 394086, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.089232921600342, "global_step": 394087, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.118603467941284, "global_step": 394088, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.2474019527435303, "global_step": 394089, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1594772338867188, "global_step": 394090, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0599911212921143, "global_step": 394091, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1254780292510986, "global_step": 394092, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1159279346466064, "global_step": 394093, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.145303964614868, "global_step": 394094, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0661163330078125, "global_step": 394095, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1275432109832764, "global_step": 394096, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.172626256942749, "global_step": 394097, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.112570285797119, "global_step": 394098, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.140179395675659, "global_step": 394099, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1049652099609375, "global_step": 394100, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.051201343536377, "global_step": 394101, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.129328489303589, "global_step": 394102, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.119039535522461, "global_step": 394103, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.03598690032959, "global_step": 394104, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0699729919433594, "global_step": 394105, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0995116233825684, "global_step": 394106, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1052427291870117, "global_step": 394107, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.161787271499634, "global_step": 394108, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0745232105255127, "global_step": 394109, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1130475997924805, "global_step": 394110, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1152725219726562, "global_step": 394111, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.058438539505005, "global_step": 394112, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.127061605453491, "global_step": 394113, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0993781089782715, "global_step": 394114, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0612621307373047, "global_step": 394115, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1812663078308105, "global_step": 394116, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1127421855926514, "global_step": 394117, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.134366512298584, "global_step": 394118, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0849175453186035, "global_step": 394119, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0895776748657227, "global_step": 394120, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0977232456207275, "global_step": 394121, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.126908540725708, "global_step": 394122, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1589267253875732, "global_step": 394123, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0829732418060303, "global_step": 394124, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0613906383514404, "global_step": 394125, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.135658025741577, "global_step": 394126, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0478391647338867, "global_step": 394127, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0987601280212402, "global_step": 394128, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1079070568084717, "global_step": 394129, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0089781284332275, "global_step": 394130, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0850577354431152, "global_step": 394131, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1139352321624756, "global_step": 394132, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1889026165008545, "global_step": 394133, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0683400630950928, "global_step": 394134, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0469284057617188, "global_step": 394135, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1488261222839355, "global_step": 394136, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.152174711227417, "global_step": 394137, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.040384531021118, "global_step": 394138, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.2131268978118896, "global_step": 394139, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0806374549865723, "global_step": 394140, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1382033824920654, "global_step": 394141, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1841766834259033, "global_step": 394142, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1131787300109863, "global_step": 394143, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0839908123016357, "global_step": 394144, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.157371759414673, "global_step": 394145, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.153855085372925, "global_step": 394146, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0998237133026123, "global_step": 394147, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.088083028793335, "global_step": 394148, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.18754243850708, "global_step": 394149, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.255080223083496, "global_step": 394150, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.198765754699707, "global_step": 394151, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.060468912124634, "global_step": 394152, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.106712579727173, "global_step": 394153, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0787179470062256, "global_step": 394154, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0521230697631836, "global_step": 394155, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0790979862213135, "global_step": 394156, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1315155029296875, "global_step": 394157, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.999609112739563, "global_step": 394158, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.142116069793701, "global_step": 394159, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0613062381744385, "global_step": 394160, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.053377151489258, "global_step": 394161, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1532609462738037, "global_step": 394162, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0128049850463867, "global_step": 394163, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.075071334838867, "global_step": 394164, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.12123966217041, "global_step": 394165, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0412909984588623, "global_step": 394166, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.047731399536133, "global_step": 394167, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0679593086242676, "global_step": 394168, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.125476837158203, "global_step": 394169, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1339809894561768, "global_step": 394170, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.086427927017212, "global_step": 394171, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0863852500915527, "global_step": 394172, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.136746406555176, "global_step": 394173, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1342315673828125, "global_step": 394174, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1031806468963623, "global_step": 394175, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.098679780960083, "global_step": 394176, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1341068744659424, "global_step": 394177, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1807591915130615, "global_step": 394178, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.118844747543335, "global_step": 394179, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0626118183135986, "global_step": 394180, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1012089252471924, "global_step": 394181, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.019017219543457, "global_step": 394182, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.060039520263672, "global_step": 394183, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1340458393096924, "global_step": 394184, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1474387645721436, "global_step": 394185, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1309947967529297, "global_step": 394186, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1650583744049072, "global_step": 394187, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1212410926818848, "global_step": 394188, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1648943424224854, "global_step": 394189, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0988967418670654, "global_step": 394190, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.093891143798828, "global_step": 394191, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.023115634918213, "global_step": 394192, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1077022552490234, "global_step": 394193, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0046725273132324, "global_step": 394194, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1308188438415527, "global_step": 394195, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1446444988250732, "global_step": 394196, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0878713130950928, "global_step": 394197, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0553929805755615, "global_step": 394198, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0891542434692383, "global_step": 394199, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0996689796447754, "global_step": 394200, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0827560424804688, "global_step": 394201, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0313448905944824, "global_step": 394202, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.9792397022247314, "global_step": 394203, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1014323234558105, "global_step": 394204, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1002893447875977, "global_step": 394205, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.159193515777588, "global_step": 394206, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.139838695526123, "global_step": 394207, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1116623878479004, "global_step": 394208, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1219327449798584, "global_step": 394209, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.044973134994507, "global_step": 394210, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1573750972747803, "global_step": 394211, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0052309036254883, "global_step": 394212, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.054358959197998, "global_step": 394213, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0579466819763184, "global_step": 394214, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0176782608032227, "global_step": 394215, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0428788661956787, "global_step": 394216, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0470993518829346, "global_step": 394217, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0941057205200195, "global_step": 394218, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1903693675994873, "global_step": 394219, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.11458420753479, "global_step": 394220, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.059001922607422, "global_step": 394221, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.130967855453491, "global_step": 394222, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.120488166809082, "global_step": 394223, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.114452600479126, "global_step": 394224, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0749213695526123, "global_step": 394225, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.112344980239868, "global_step": 394226, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.102480173110962, "global_step": 394227, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.201695442199707, "global_step": 394228, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1333494186401367, "global_step": 394229, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0888278484344482, "global_step": 394230, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.105509042739868, "global_step": 394231, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.059889078140259, "global_step": 394232, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.047184944152832, "global_step": 394233, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.137462615966797, "global_step": 394234, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1534812450408936, "global_step": 394235, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1390058994293213, "global_step": 394236, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.08500337600708, "global_step": 394237, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.2310564517974854, "global_step": 394238, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.126523494720459, "global_step": 394239, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0171709060668945, "global_step": 394240, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0630736351013184, "global_step": 394241, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.026700973510742, "global_step": 394242, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.137963056564331, "global_step": 394243, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0890626907348633, "global_step": 394244, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.092963695526123, "global_step": 394245, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0321402549743652, "global_step": 394246, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.150083065032959, "global_step": 394247, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.095026731491089, "global_step": 394248, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.117042064666748, "global_step": 394249, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.091062545776367, "global_step": 394250, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.9550703763961792, "global_step": 394251, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.123832941055298, "global_step": 394252, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1365551948547363, "global_step": 394253, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0405335426330566, "global_step": 394254, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.103093385696411, "global_step": 394255, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1355772018432617, "global_step": 394256, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.157119035720825, "global_step": 394257, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0670485496520996, "global_step": 394258, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1497223377227783, "global_step": 394259, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.036158561706543, "global_step": 394260, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1872200965881348, "global_step": 394261, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0003621578216553, "global_step": 394262, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0772757530212402, "global_step": 394263, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1898250579833984, "global_step": 394264, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0961735248565674, "global_step": 394265, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.15779972076416, "global_step": 394266, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0525689125061035, "global_step": 394267, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.085404872894287, "global_step": 394268, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.09600830078125, "global_step": 394269, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.066110610961914, "global_step": 394270, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0761680603027344, "global_step": 394271, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1021292209625244, "global_step": 394272, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1423609256744385, "global_step": 394273, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.079413652420044, "global_step": 394274, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1805200576782227, "global_step": 394275, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.083812713623047, "global_step": 394276, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0977110862731934, "global_step": 394277, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0895681381225586, "global_step": 394278, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.105531930923462, "global_step": 394279, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.137629985809326, "global_step": 394280, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1321208477020264, "global_step": 394281, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.135756015777588, "global_step": 394282, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.151089668273926, "global_step": 394283, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.069542407989502, "global_step": 394284, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.01374888420105, "global_step": 394285, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0886454582214355, "global_step": 394286, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1104745864868164, "global_step": 394287, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.108123540878296, "global_step": 394288, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.076125383377075, "global_step": 394289, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0247247219085693, "global_step": 394290, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.131779909133911, "global_step": 394291, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0882623195648193, "global_step": 394292, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1101186275482178, "global_step": 394293, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.127878427505493, "global_step": 394294, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.024359941482544, "global_step": 394295, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0841193199157715, "global_step": 394296, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1335787773132324, "global_step": 394297, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.12357234954834, "global_step": 394298, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1172728538513184, "global_step": 394299, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.094008207321167, "global_step": 394300, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1384334564208984, "global_step": 394301, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1638669967651367, "global_step": 394302, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.086373805999756, "global_step": 394303, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0965592861175537, "global_step": 394304, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.116457939147949, "global_step": 394305, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0646393299102783, "global_step": 394306, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0557751655578613, "global_step": 394307, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.099496841430664, "global_step": 394308, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.072235345840454, "global_step": 394309, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.085157871246338, "global_step": 394310, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.9931910037994385, "global_step": 394311, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.177442789077759, "global_step": 394312, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0743157863616943, "global_step": 394313, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.139899492263794, "global_step": 394314, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0878398418426514, "global_step": 394315, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0665366649627686, "global_step": 394316, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.135922908782959, "global_step": 394317, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.133639097213745, "global_step": 394318, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0681114196777344, "global_step": 394319, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1363306045532227, "global_step": 394320, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1222658157348633, "global_step": 394321, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0896213054656982, "global_step": 394322, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.034179925918579, "global_step": 394323, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1066277027130127, "global_step": 394324, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.070483446121216, "global_step": 394325, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0642623901367188, "global_step": 394326, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.020754814147949, "global_step": 394327, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0435783863067627, "global_step": 394328, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.080376386642456, "global_step": 394329, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.137838125228882, "global_step": 394330, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.115583896636963, "global_step": 394331, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0650861263275146, "global_step": 394332, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.2395670413970947, "global_step": 394333, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1230576038360596, "global_step": 394334, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0507631301879883, "global_step": 394335, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1099472045898438, "global_step": 394336, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.201242446899414, "global_step": 394337, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1001603603363037, "global_step": 394338, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.115473508834839, "global_step": 394339, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.041114091873169, "global_step": 394340, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1576080322265625, "global_step": 394341, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.20808482170105, "global_step": 394342, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.054517984390259, "global_step": 394343, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1383042335510254, "global_step": 394344, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0342330932617188, "global_step": 394345, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1135094165802, "global_step": 394346, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0937399864196777, "global_step": 394347, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0345571041107178, "global_step": 394348, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0305275917053223, "global_step": 394349, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.148390054702759, "global_step": 394350, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0642764568328857, "global_step": 394351, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1318256855010986, "global_step": 394352, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1984314918518066, "global_step": 394353, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.090142250061035, "global_step": 394354, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.143113136291504, "global_step": 394355, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.153744697570801, "global_step": 394356, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.111727714538574, "global_step": 394357, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.047532796859741, "global_step": 394358, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1377525329589844, "global_step": 394359, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1604421138763428, "global_step": 394360, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.069204568862915, "global_step": 394361, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0859837532043457, "global_step": 394362, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1249892711639404, "global_step": 394363, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0619571208953857, "global_step": 394364, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.056307077407837, "global_step": 394365, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.17708683013916, "global_step": 394366, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1733665466308594, "global_step": 394367, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.088264226913452, "global_step": 394368, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.013000011444092, "global_step": 394369, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1093146800994873, "global_step": 394370, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.144570827484131, "global_step": 394371, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.133777141571045, "global_step": 394372, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.100576877593994, "global_step": 394373, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.108372926712036, "global_step": 394374, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0920028686523438, "global_step": 394375, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.047243118286133, "global_step": 394376, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1367385387420654, "global_step": 394377, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.107689380645752, "global_step": 394378, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.102391242980957, "global_step": 394379, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0202829837799072, "global_step": 394380, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1003472805023193, "global_step": 394381, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0709102153778076, "global_step": 394382, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0710947513580322, "global_step": 394383, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.044088125228882, "global_step": 394384, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1164016723632812, "global_step": 394385, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.192528247833252, "global_step": 394386, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0538995265960693, "global_step": 394387, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.091456413269043, "global_step": 394388, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0127980709075928, "global_step": 394389, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0203347206115723, "global_step": 394390, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.104799270629883, "global_step": 394391, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.055170774459839, "global_step": 394392, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0849292278289795, "global_step": 394393, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.068488597869873, "global_step": 394394, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.051800489425659, "global_step": 394395, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.094120979309082, "global_step": 394396, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.261308193206787, "global_step": 394397, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.142322540283203, "global_step": 394398, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.131115436553955, "global_step": 394399, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.072266101837158, "global_step": 394400, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1348235607147217, "global_step": 394401, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0514276027679443, "global_step": 394402, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1467695236206055, "global_step": 394403, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.123823642730713, "global_step": 394404, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0393970012664795, "global_step": 394405, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0547354221343994, "global_step": 394406, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0573933124542236, "global_step": 394407, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.9871329069137573, "global_step": 394408, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1369059085845947, "global_step": 394409, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0062923431396484, "global_step": 394410, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.044328212738037, "global_step": 394411, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0540010929107666, "global_step": 394412, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.100217342376709, "global_step": 394413, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1527962684631348, "global_step": 394414, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.059692144393921, "global_step": 394415, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.112781286239624, "global_step": 394416, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.069645404815674, "global_step": 394417, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0902979373931885, "global_step": 394418, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.121641159057617, "global_step": 394419, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.9955811500549316, "global_step": 394420, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.21531081199646, "global_step": 394421, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.122544050216675, "global_step": 394422, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1996090412139893, "global_step": 394423, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.089134454727173, "global_step": 394424, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.090486764907837, "global_step": 394425, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.148209571838379, "global_step": 394426, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1232216358184814, "global_step": 394427, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1431775093078613, "global_step": 394428, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.03637433052063, "global_step": 394429, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.149883270263672, "global_step": 394430, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0484695434570312, "global_step": 394431, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.022453546524048, "global_step": 394432, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0651514530181885, "global_step": 394433, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.097809314727783, "global_step": 394434, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0535035133361816, "global_step": 394435, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.110698699951172, "global_step": 394436, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.05373477935791, "global_step": 394437, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0947225093841553, "global_step": 394438, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1279261112213135, "global_step": 394439, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.091641426086426, "global_step": 394440, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.9864944219589233, "global_step": 394441, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1449315547943115, "global_step": 394442, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0728237628936768, "global_step": 394443, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.019598960876465, "global_step": 394444, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0801632404327393, "global_step": 394445, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1340889930725098, "global_step": 394446, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1692636013031006, "global_step": 394447, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1298506259918213, "global_step": 394448, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1139934062957764, "global_step": 394449, "epoch": 756, "lr": 5e-05}
{"train_loss": 1.9744360446929932, "global_step": 394450, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0628511905670166, "global_step": 394451, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.077155351638794, "global_step": 394452, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0566437244415283, "global_step": 394453, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0454492568969727, "global_step": 394454, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.097501277923584, "global_step": 394455, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.181915760040283, "global_step": 394456, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0690855979919434, "global_step": 394457, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1218173503875732, "global_step": 394458, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0935394763946533, "global_step": 394459, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.2027924060821533, "global_step": 394460, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0944736003875732, "global_step": 394461, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1070356369018555, "global_step": 394462, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0421154499053955, "global_step": 394463, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.145045757293701, "global_step": 394464, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0073699951171875, "global_step": 394465, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1358423233032227, "global_step": 394466, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1835548877716064, "global_step": 394467, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1458852291107178, "global_step": 394468, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.103161096572876, "global_step": 394469, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.112321615219116, "global_step": 394470, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1725714206695557, "global_step": 394471, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.144120693206787, "global_step": 394472, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1054482460021973, "global_step": 394473, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.115577220916748, "global_step": 394474, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.11169695854187, "global_step": 394475, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.104525089263916, "global_step": 394476, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0847206115722656, "global_step": 394477, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1393635272979736, "global_step": 394478, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.085806369781494, "global_step": 394479, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1452295780181885, "global_step": 394480, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0860090255737305, "global_step": 394481, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0661447048187256, "global_step": 394482, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.01267671585083, "global_step": 394483, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0490195751190186, "global_step": 394484, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.086113214492798, "global_step": 394485, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.125427722930908, "global_step": 394486, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.038695812225342, "global_step": 394487, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.045790195465088, "global_step": 394488, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.050615072250366, "global_step": 394489, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1347174644470215, "global_step": 394490, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0920627117156982, "global_step": 394491, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1377882957458496, "global_step": 394492, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0973308086395264, "global_step": 394493, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1125783920288086, "global_step": 394494, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1893866062164307, "global_step": 394495, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0414910316467285, "global_step": 394496, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.107880115509033, "global_step": 394497, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0793302059173584, "global_step": 394498, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0268194675445557, "global_step": 394499, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0461349487304688, "global_step": 394500, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0696284770965576, "global_step": 394501, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1089589595794678, "global_step": 394502, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0908284187316895, "global_step": 394503, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1512961387634277, "global_step": 394504, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1760189533233643, "global_step": 394505, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.055208206176758, "global_step": 394506, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.033430814743042, "global_step": 394507, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.187835454940796, "global_step": 394508, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.112732172012329, "global_step": 394509, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.157670497894287, "global_step": 394510, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1059186458587646, "global_step": 394511, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.110546112060547, "global_step": 394512, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0644564628601074, "global_step": 394513, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.1226634979248047, "global_step": 394514, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.0983736515045166, "global_step": 394515, "epoch": 756, "lr": 5e-05}
{"train_loss": 2.177281379699707, "global_step": 394516, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0787904262542725, "global_step": 394517, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0848355293273926, "global_step": 394518, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.131873607635498, "global_step": 394519, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.047527551651001, "global_step": 394520, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0674209594726562, "global_step": 394521, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.102642059326172, "global_step": 394522, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1558921337127686, "global_step": 394523, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.082076072692871, "global_step": 394524, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.053769111633301, "global_step": 394525, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.021091938018799, "global_step": 394526, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1233320236206055, "global_step": 394527, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1609222888946533, "global_step": 394528, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0866494178771973, "global_step": 394529, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0360679626464844, "global_step": 394530, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0380523204803467, "global_step": 394531, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1064295768737793, "global_step": 394532, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.002636432647705, "global_step": 394533, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.099586248397827, "global_step": 394534, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.140822172164917, "global_step": 394535, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0610439777374268, "global_step": 394536, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.05861759185791, "global_step": 394537, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0973386764526367, "global_step": 394538, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1486706733703613, "global_step": 394539, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.107570171356201, "global_step": 394540, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.11147403717041, "global_step": 394541, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1793978214263916, "global_step": 394542, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9894829988479614, "global_step": 394543, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.035979986190796, "global_step": 394544, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.107342004776001, "global_step": 394545, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.2015221118927, "global_step": 394546, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.096261739730835, "global_step": 394547, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0804708003997803, "global_step": 394548, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1123125553131104, "global_step": 394549, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1396563053131104, "global_step": 394550, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.117931604385376, "global_step": 394551, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0225729942321777, "global_step": 394552, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.115506410598755, "global_step": 394553, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.166457414627075, "global_step": 394554, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1030430793762207, "global_step": 394555, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.105600118637085, "global_step": 394556, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1985225677490234, "global_step": 394557, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.066676616668701, "global_step": 394558, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.055680990219116, "global_step": 394559, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1258978843688965, "global_step": 394560, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.063404083251953, "global_step": 394561, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1145944595336914, "global_step": 394562, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0494959354400635, "global_step": 394563, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1025326251983643, "global_step": 394564, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0697438716888428, "global_step": 394565, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0539450645446777, "global_step": 394566, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1420342922210693, "global_step": 394567, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.041018486022949, "global_step": 394568, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.2666594982147217, "global_step": 394569, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0957963466644287, "global_step": 394570, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0273549556732178, "global_step": 394571, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1158313751220703, "global_step": 394572, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0987443923950195, "global_step": 394573, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9808348417282104, "global_step": 394574, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.136382579803467, "global_step": 394575, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.013364553451538, "global_step": 394576, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0550906658172607, "global_step": 394577, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0307865142822266, "global_step": 394578, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1053428649902344, "global_step": 394579, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0685977935791016, "global_step": 394580, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.035879373550415, "global_step": 394581, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1923975944519043, "global_step": 394582, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.092622756958008, "global_step": 394583, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.155463457107544, "global_step": 394584, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.062676429748535, "global_step": 394585, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.05564284324646, "global_step": 394586, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1005539894104004, "global_step": 394587, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1266565322875977, "global_step": 394588, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0394890308380127, "global_step": 394589, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0218563079833984, "global_step": 394590, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.018882989883423, "global_step": 394591, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1968486309051514, "global_step": 394592, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.079618453979492, "global_step": 394593, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.088303804397583, "global_step": 394594, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.080105781555176, "global_step": 394595, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1068248748779297, "global_step": 394596, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.101301431655884, "global_step": 394597, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0829319953918457, "global_step": 394598, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0689857006073, "global_step": 394599, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1136491298675537, "global_step": 394600, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0425028800964355, "global_step": 394601, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.12265682220459, "global_step": 394602, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.082103967666626, "global_step": 394603, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.088874578475952, "global_step": 394604, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.059755325317383, "global_step": 394605, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0983049869537354, "global_step": 394606, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0897817611694336, "global_step": 394607, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.106276512145996, "global_step": 394608, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1525533199310303, "global_step": 394609, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.071800708770752, "global_step": 394610, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1814475059509277, "global_step": 394611, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.161405563354492, "global_step": 394612, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9954659938812256, "global_step": 394613, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.100456953048706, "global_step": 394614, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0154144763946533, "global_step": 394615, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.017470121383667, "global_step": 394616, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1370511054992676, "global_step": 394617, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.065253257751465, "global_step": 394618, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0842843055725098, "global_step": 394619, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.036574125289917, "global_step": 394620, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.025477170944214, "global_step": 394621, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.05920672416687, "global_step": 394622, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.068861961364746, "global_step": 394623, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.144827127456665, "global_step": 394624, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0467467308044434, "global_step": 394625, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1675593852996826, "global_step": 394626, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9873278141021729, "global_step": 394627, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.030683755874634, "global_step": 394628, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.199202537536621, "global_step": 394629, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.054760456085205, "global_step": 394630, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.044656753540039, "global_step": 394631, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1006650924682617, "global_step": 394632, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.059919595718384, "global_step": 394633, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.114921808242798, "global_step": 394634, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.102219343185425, "global_step": 394635, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.14115047454834, "global_step": 394636, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0812788009643555, "global_step": 394637, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1523540019989014, "global_step": 394638, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.07323956489563, "global_step": 394639, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.075510263442993, "global_step": 394640, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.111393690109253, "global_step": 394641, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1177146434783936, "global_step": 394642, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.089667797088623, "global_step": 394643, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0646395683288574, "global_step": 394644, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.131340980529785, "global_step": 394645, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.082726001739502, "global_step": 394646, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0726590156555176, "global_step": 394647, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0646958351135254, "global_step": 394648, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0787436962127686, "global_step": 394649, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.125920057296753, "global_step": 394650, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.052103042602539, "global_step": 394651, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0173180103302, "global_step": 394652, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.138655185699463, "global_step": 394653, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0648043155670166, "global_step": 394654, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1254026889801025, "global_step": 394655, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.09395694732666, "global_step": 394656, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0853657722473145, "global_step": 394657, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1100165843963623, "global_step": 394658, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.163931131362915, "global_step": 394659, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0375313758850098, "global_step": 394660, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9867827892303467, "global_step": 394661, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1311118602752686, "global_step": 394662, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.162865400314331, "global_step": 394663, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0714335441589355, "global_step": 394664, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.117305040359497, "global_step": 394665, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0968542098999023, "global_step": 394666, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0785322189331055, "global_step": 394667, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.155130386352539, "global_step": 394668, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1742982864379883, "global_step": 394669, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.008164644241333, "global_step": 394670, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0808920860290527, "global_step": 394671, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.167786121368408, "global_step": 394672, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.097842216491699, "global_step": 394673, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1006927490234375, "global_step": 394674, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.032139778137207, "global_step": 394675, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1584126949310303, "global_step": 394676, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1126270294189453, "global_step": 394677, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.104189395904541, "global_step": 394678, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0467119216918945, "global_step": 394679, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1709792613983154, "global_step": 394680, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0889077186584473, "global_step": 394681, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1445956230163574, "global_step": 394682, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.112004280090332, "global_step": 394683, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0405056476593018, "global_step": 394684, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1714749336242676, "global_step": 394685, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.074047803878784, "global_step": 394686, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.086496353149414, "global_step": 394687, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.040313482284546, "global_step": 394688, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.100229263305664, "global_step": 394689, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0801713466644287, "global_step": 394690, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0971789360046387, "global_step": 394691, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.057589054107666, "global_step": 394692, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.003314256668091, "global_step": 394693, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0871541500091553, "global_step": 394694, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1143853664398193, "global_step": 394695, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1231849193573, "global_step": 394696, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0984010696411133, "global_step": 394697, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.2070565223693848, "global_step": 394698, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1364386081695557, "global_step": 394699, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1480355262756348, "global_step": 394700, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0652945041656494, "global_step": 394701, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.153261661529541, "global_step": 394702, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0555343627929688, "global_step": 394703, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.096461057662964, "global_step": 394704, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0554304122924805, "global_step": 394705, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0196304321289062, "global_step": 394706, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1381282806396484, "global_step": 394707, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.081815242767334, "global_step": 394708, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.2069852352142334, "global_step": 394709, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.117363452911377, "global_step": 394710, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0080726146698, "global_step": 394711, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1169726848602295, "global_step": 394712, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0166168212890625, "global_step": 394713, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.048701524734497, "global_step": 394714, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.12095046043396, "global_step": 394715, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.086106061935425, "global_step": 394716, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.144613742828369, "global_step": 394717, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.089679718017578, "global_step": 394718, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9950580596923828, "global_step": 394719, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.080198049545288, "global_step": 394720, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0377464294433594, "global_step": 394721, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0620665550231934, "global_step": 394722, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0921106338500977, "global_step": 394723, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1708526611328125, "global_step": 394724, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.005514144897461, "global_step": 394725, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.108060836791992, "global_step": 394726, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.182997941970825, "global_step": 394727, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0344865322113037, "global_step": 394728, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0449132919311523, "global_step": 394729, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.121359348297119, "global_step": 394730, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1533148288726807, "global_step": 394731, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1811766624450684, "global_step": 394732, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0833654403686523, "global_step": 394733, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1053807735443115, "global_step": 394734, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.051175355911255, "global_step": 394735, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1683309078216553, "global_step": 394736, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.12255859375, "global_step": 394737, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.095263957977295, "global_step": 394738, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.187835693359375, "global_step": 394739, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0571610927581787, "global_step": 394740, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0596654415130615, "global_step": 394741, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0800082683563232, "global_step": 394742, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0676488876342773, "global_step": 394743, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0325868129730225, "global_step": 394744, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.102118968963623, "global_step": 394745, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1391594409942627, "global_step": 394746, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1619110107421875, "global_step": 394747, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0028634071350098, "global_step": 394748, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0577452182769775, "global_step": 394749, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0836315155029297, "global_step": 394750, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1351544857025146, "global_step": 394751, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.059208631515503, "global_step": 394752, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1195225715637207, "global_step": 394753, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.109261989593506, "global_step": 394754, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1973843574523926, "global_step": 394755, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.121124267578125, "global_step": 394756, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0756702423095703, "global_step": 394757, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0786592960357666, "global_step": 394758, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.180039882659912, "global_step": 394759, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1486427783966064, "global_step": 394760, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0914580821990967, "global_step": 394761, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0923149585723877, "global_step": 394762, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0434420108795166, "global_step": 394763, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0360307693481445, "global_step": 394764, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.101430654525757, "global_step": 394765, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.169858694076538, "global_step": 394766, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.116140127182007, "global_step": 394767, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.081934690475464, "global_step": 394768, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.119778633117676, "global_step": 394769, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0631940364837646, "global_step": 394770, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.082951545715332, "global_step": 394771, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.164928913116455, "global_step": 394772, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.025273323059082, "global_step": 394773, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1001572608947754, "global_step": 394774, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.049431085586548, "global_step": 394775, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1239306926727295, "global_step": 394776, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0345559120178223, "global_step": 394777, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1853036880493164, "global_step": 394778, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.14705753326416, "global_step": 394779, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1040396690368652, "global_step": 394780, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1259660720825195, "global_step": 394781, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1403286457061768, "global_step": 394782, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.114713430404663, "global_step": 394783, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.127930164337158, "global_step": 394784, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0817272663116455, "global_step": 394785, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.07245135307312, "global_step": 394786, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1454670429229736, "global_step": 394787, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0917201042175293, "global_step": 394788, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0630669593811035, "global_step": 394789, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.111452579498291, "global_step": 394790, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0723657608032227, "global_step": 394791, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0419015884399414, "global_step": 394792, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1411263942718506, "global_step": 394793, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.074475049972534, "global_step": 394794, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.2320406436920166, "global_step": 394795, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.120591640472412, "global_step": 394796, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.062509536743164, "global_step": 394797, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1676416397094727, "global_step": 394798, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1097612380981445, "global_step": 394799, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.034219980239868, "global_step": 394800, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.082400321960449, "global_step": 394801, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.008272886276245, "global_step": 394802, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9924933910369873, "global_step": 394803, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1228599548339844, "global_step": 394804, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0577614307403564, "global_step": 394805, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.001741886138916, "global_step": 394806, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1111669540405273, "global_step": 394807, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.017347812652588, "global_step": 394808, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.155179738998413, "global_step": 394809, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9992319345474243, "global_step": 394810, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.034459114074707, "global_step": 394811, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0753300189971924, "global_step": 394812, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.136652946472168, "global_step": 394813, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.098323106765747, "global_step": 394814, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.13061785697937, "global_step": 394815, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0855352878570557, "global_step": 394816, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.041841745376587, "global_step": 394817, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.993598461151123, "global_step": 394818, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1502692699432373, "global_step": 394819, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.057000160217285, "global_step": 394820, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.097843885421753, "global_step": 394821, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0364468097686768, "global_step": 394822, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.073185920715332, "global_step": 394823, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0670459270477295, "global_step": 394824, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1300723552703857, "global_step": 394825, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0903735160827637, "global_step": 394826, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0882980823516846, "global_step": 394827, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1128294467926025, "global_step": 394828, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.125401020050049, "global_step": 394829, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1638548374176025, "global_step": 394830, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1119470596313477, "global_step": 394831, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1312687397003174, "global_step": 394832, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1253559589385986, "global_step": 394833, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.135716199874878, "global_step": 394834, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0922722816467285, "global_step": 394835, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1199452877044678, "global_step": 394836, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0707454681396484, "global_step": 394837, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.033965587615967, "global_step": 394838, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.246624708175659, "global_step": 394839, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.096313714981079, "global_step": 394840, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.190803050994873, "global_step": 394841, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.17572283744812, "global_step": 394842, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0779523849487305, "global_step": 394843, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9920767545700073, "global_step": 394844, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.99469792842865, "global_step": 394845, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.108806610107422, "global_step": 394846, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.122457265853882, "global_step": 394847, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0850346088409424, "global_step": 394848, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.078200340270996, "global_step": 394849, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1951904296875, "global_step": 394850, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1295642852783203, "global_step": 394851, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0797696113586426, "global_step": 394852, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.102316379547119, "global_step": 394853, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.118657112121582, "global_step": 394854, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.173783779144287, "global_step": 394855, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1310553550720215, "global_step": 394856, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0514676570892334, "global_step": 394857, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0197815895080566, "global_step": 394858, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.131695032119751, "global_step": 394859, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0854127407073975, "global_step": 394860, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0407626628875732, "global_step": 394861, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.110959529876709, "global_step": 394862, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.087449550628662, "global_step": 394863, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.024108648300171, "global_step": 394864, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.093414545059204, "global_step": 394865, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1647822856903076, "global_step": 394866, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0139853954315186, "global_step": 394867, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.093905448913574, "global_step": 394868, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.065425395965576, "global_step": 394869, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0233163833618164, "global_step": 394870, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.057218313217163, "global_step": 394871, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1640625, "global_step": 394872, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1418392658233643, "global_step": 394873, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1845273971557617, "global_step": 394874, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.120173215866089, "global_step": 394875, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1085147857666016, "global_step": 394876, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.147162437438965, "global_step": 394877, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1325531005859375, "global_step": 394878, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0425891876220703, "global_step": 394879, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0261335372924805, "global_step": 394880, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1326067447662354, "global_step": 394881, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1289966106414795, "global_step": 394882, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9825031757354736, "global_step": 394883, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1239724159240723, "global_step": 394884, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.113250255584717, "global_step": 394885, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0897552967071533, "global_step": 394886, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.100001811981201, "global_step": 394887, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.137637138366699, "global_step": 394888, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0988030433654785, "global_step": 394889, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.078587770462036, "global_step": 394890, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.072289228439331, "global_step": 394891, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.064030408859253, "global_step": 394892, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.082504987716675, "global_step": 394893, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0927369594573975, "global_step": 394894, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9727426767349243, "global_step": 394895, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1062755584716797, "global_step": 394896, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.060966730117798, "global_step": 394897, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.057859182357788, "global_step": 394898, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1225578784942627, "global_step": 394899, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.124537467956543, "global_step": 394900, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0837247371673584, "global_step": 394901, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.079406499862671, "global_step": 394902, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.063936471939087, "global_step": 394903, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0833418369293213, "global_step": 394904, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.074981212615967, "global_step": 394905, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1248819828033447, "global_step": 394906, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0594866275787354, "global_step": 394907, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.209179401397705, "global_step": 394908, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1783101558685303, "global_step": 394909, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1402573585510254, "global_step": 394910, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1106956005096436, "global_step": 394911, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.142487049102783, "global_step": 394912, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.13980770111084, "global_step": 394913, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0511250495910645, "global_step": 394914, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0973775386810303, "global_step": 394915, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.072988748550415, "global_step": 394916, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0849528312683105, "global_step": 394917, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.108541488647461, "global_step": 394918, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.005223274230957, "global_step": 394919, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.153909206390381, "global_step": 394920, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.147156000137329, "global_step": 394921, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.188861846923828, "global_step": 394922, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0707788467407227, "global_step": 394923, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.065683603286743, "global_step": 394924, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.012988328933716, "global_step": 394925, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0157525539398193, "global_step": 394926, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.216543674468994, "global_step": 394927, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.043365716934204, "global_step": 394928, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1096408367156982, "global_step": 394929, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0624773502349854, "global_step": 394930, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1238021850585938, "global_step": 394931, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.134385347366333, "global_step": 394932, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.120248317718506, "global_step": 394933, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0721216201782227, "global_step": 394934, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.167560577392578, "global_step": 394935, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0281386375427246, "global_step": 394936, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.071938991546631, "global_step": 394937, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.138737201690674, "global_step": 394938, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1166534423828125, "global_step": 394939, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0556087493896484, "global_step": 394940, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.039848566055298, "global_step": 394941, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0636796951293945, "global_step": 394942, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0750467777252197, "global_step": 394943, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0886011123657227, "global_step": 394944, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0804684162139893, "global_step": 394945, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1053647994995117, "global_step": 394946, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.128631114959717, "global_step": 394947, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.056335687637329, "global_step": 394948, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0680911540985107, "global_step": 394949, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.108762502670288, "global_step": 394950, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.121410846710205, "global_step": 394951, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0644850730895996, "global_step": 394952, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.117603302001953, "global_step": 394953, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1493303775787354, "global_step": 394954, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.105929136276245, "global_step": 394955, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1379129886627197, "global_step": 394956, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1572513580322266, "global_step": 394957, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0752058029174805, "global_step": 394958, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1100518703460693, "global_step": 394959, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.118638753890991, "global_step": 394960, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.074605941772461, "global_step": 394961, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0576930046081543, "global_step": 394962, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0712170600891113, "global_step": 394963, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.146616220474243, "global_step": 394964, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0908491611480713, "global_step": 394965, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.003141403198242, "global_step": 394966, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0479390621185303, "global_step": 394967, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.034851312637329, "global_step": 394968, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0019142627716064, "global_step": 394969, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.078918933868408, "global_step": 394970, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1748239994049072, "global_step": 394971, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1484572887420654, "global_step": 394972, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9652178287506104, "global_step": 394973, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1147797107696533, "global_step": 394974, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.04769229888916, "global_step": 394975, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.158888816833496, "global_step": 394976, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0412354469299316, "global_step": 394977, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.107081890106201, "global_step": 394978, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1489803791046143, "global_step": 394979, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0697357654571533, "global_step": 394980, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.123563051223755, "global_step": 394981, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0353190898895264, "global_step": 394982, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0780487060546875, "global_step": 394983, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.094285249710083, "global_step": 394984, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.095308542251587, "global_step": 394985, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.2315173149108887, "global_step": 394986, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0445919036865234, "global_step": 394987, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.053161382675171, "global_step": 394988, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.155775547027588, "global_step": 394989, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0994679927825928, "global_step": 394990, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1404361724853516, "global_step": 394991, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.113054037094116, "global_step": 394992, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.953080415725708, "global_step": 394993, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.111105442047119, "global_step": 394994, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.135164737701416, "global_step": 394995, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0408718585968018, "global_step": 394996, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.084207534790039, "global_step": 394997, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0970282554626465, "global_step": 394998, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.094914197921753, "global_step": 394999, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.063485860824585, "global_step": 395000, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.105095386505127, "global_step": 395001, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0967018604278564, "global_step": 395002, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9875986576080322, "global_step": 395003, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0862340927124023, "global_step": 395004, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0706727504730225, "global_step": 395005, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.095277786254883, "global_step": 395006, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.093433141708374, "global_step": 395007, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.079228162765503, "global_step": 395008, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.998510479927063, "global_step": 395009, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1344246864318848, "global_step": 395010, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1355159282684326, "global_step": 395011, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1139049530029297, "global_step": 395012, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1305949687957764, "global_step": 395013, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.118969202041626, "global_step": 395014, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0752413272857666, "global_step": 395015, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0684871673583984, "global_step": 395016, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1220672130584717, "global_step": 395017, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.116386890411377, "global_step": 395018, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0704076290130615, "global_step": 395019, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0442612171173096, "global_step": 395020, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.18536639213562, "global_step": 395021, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0700724124908447, "global_step": 395022, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.119925022125244, "global_step": 395023, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0963711738586426, "global_step": 395024, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.062966823577881, "global_step": 395025, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0757896900177, "global_step": 395026, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1762514114379883, "global_step": 395027, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9961397647857666, "global_step": 395028, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.111833333969116, "global_step": 395029, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.070352077484131, "global_step": 395030, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.084503650665283, "global_step": 395031, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1428160667419434, "global_step": 395032, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.157008171081543, "global_step": 395033, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.103727340698242, "global_step": 395034, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.058378219604492, "global_step": 395035, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1218976974487305, "global_step": 395036, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.064307451248169, "global_step": 395037, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1050987243652344, "global_step": 395038, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1600492000579834, "global_step": 395039, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0811638832092285, "global_step": 395040, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0755724906921387, "global_step": 395041, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.065288543701172, "global_step": 395042, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.097080707550049, "global_step": 395043, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0993640422821045, "global_step": 395044, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1896135807037354, "global_step": 395045, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.158508539199829, "global_step": 395046, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1330363750457764, "global_step": 395047, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0663583278656006, "global_step": 395048, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.069000482559204, "global_step": 395049, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0538506507873535, "global_step": 395050, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0787086486816406, "global_step": 395051, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1676580905914307, "global_step": 395052, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.155294179916382, "global_step": 395053, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1051647663116455, "global_step": 395054, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0756993293762207, "global_step": 395055, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.2157630920410156, "global_step": 395056, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.111123561859131, "global_step": 395057, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0943918228149414, "global_step": 395058, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1517560482025146, "global_step": 395059, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.11977481842041, "global_step": 395060, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.034571647644043, "global_step": 395061, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.148705244064331, "global_step": 395062, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0960984230041504, "global_step": 395063, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.12740159034729, "global_step": 395064, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1606905460357666, "global_step": 395065, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0520572662353516, "global_step": 395066, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9834825992584229, "global_step": 395067, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0551764965057373, "global_step": 395068, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1126816272735596, "global_step": 395069, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1709606647491455, "global_step": 395070, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.141800880432129, "global_step": 395071, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.064208507537842, "global_step": 395072, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9950389862060547, "global_step": 395073, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.101360559463501, "global_step": 395074, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1392078399658203, "global_step": 395075, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.103736162185669, "global_step": 395076, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.134012460708618, "global_step": 395077, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.080395221710205, "global_step": 395078, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0806097984313965, "global_step": 395079, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.120333194732666, "global_step": 395080, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0936193466186523, "global_step": 395081, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1457555294036865, "global_step": 395082, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.208385705947876, "global_step": 395083, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1482934951782227, "global_step": 395084, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1474978923797607, "global_step": 395085, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.082883834838867, "global_step": 395086, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.109961748123169, "global_step": 395087, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1377079486846924, "global_step": 395088, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0505590438842773, "global_step": 395089, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.132507801055908, "global_step": 395090, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.163534164428711, "global_step": 395091, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.101759195327759, "global_step": 395092, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0944697856903076, "global_step": 395093, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0619912147521973, "global_step": 395094, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1583566665649414, "global_step": 395095, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.097381830215454, "global_step": 395096, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.151860237121582, "global_step": 395097, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.990982174873352, "global_step": 395098, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.089329242706299, "global_step": 395099, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1065571308135986, "global_step": 395100, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.137162446975708, "global_step": 395101, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1061770915985107, "global_step": 395102, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.076349973678589, "global_step": 395103, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.060136318206787, "global_step": 395104, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1943984031677246, "global_step": 395105, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1255226135253906, "global_step": 395106, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.101733684539795, "global_step": 395107, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1002068519592285, "global_step": 395108, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0711755752563477, "global_step": 395109, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9474209547042847, "global_step": 395110, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1808717250823975, "global_step": 395111, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.060412883758545, "global_step": 395112, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.079484462738037, "global_step": 395113, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.09194016456604, "global_step": 395114, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0957953929901123, "global_step": 395115, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0304489135742188, "global_step": 395116, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.069044828414917, "global_step": 395117, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0330398082733154, "global_step": 395118, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.2569823265075684, "global_step": 395119, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1699888706207275, "global_step": 395120, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1576640605926514, "global_step": 395121, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1566851139068604, "global_step": 395122, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.127627372741699, "global_step": 395123, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0900347232818604, "global_step": 395124, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1807870864868164, "global_step": 395125, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.102832555770874, "global_step": 395126, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.138974189758301, "global_step": 395127, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0957539081573486, "global_step": 395128, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.086981773376465, "global_step": 395129, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.14132022857666, "global_step": 395130, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.2024521827697754, "global_step": 395131, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.093923807144165, "global_step": 395132, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0844690799713135, "global_step": 395133, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1155166625976562, "global_step": 395134, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0937061309814453, "global_step": 395135, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9849796295166016, "global_step": 395136, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0692508220672607, "global_step": 395137, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.075770854949951, "global_step": 395138, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0702195167541504, "global_step": 395139, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.057528257369995, "global_step": 395140, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0398752689361572, "global_step": 395141, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0772652626037598, "global_step": 395142, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1322154998779297, "global_step": 395143, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0728161334991455, "global_step": 395144, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.140126943588257, "global_step": 395145, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.101811647415161, "global_step": 395146, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.091330051422119, "global_step": 395147, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.138976573944092, "global_step": 395148, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1057844161987305, "global_step": 395149, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0806427001953125, "global_step": 395150, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1775240898132324, "global_step": 395151, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.148592710494995, "global_step": 395152, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1185290813446045, "global_step": 395153, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.174135684967041, "global_step": 395154, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1106417179107666, "global_step": 395155, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.111205577850342, "global_step": 395156, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0975165367126465, "global_step": 395157, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.059333324432373, "global_step": 395158, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1052987575531006, "global_step": 395159, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.067336082458496, "global_step": 395160, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0946974754333496, "global_step": 395161, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1356029510498047, "global_step": 395162, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.062350034713745, "global_step": 395163, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.163322687149048, "global_step": 395164, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0360496044158936, "global_step": 395165, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.115408182144165, "global_step": 395166, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1491103172302246, "global_step": 395167, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1017425060272217, "global_step": 395168, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.092031717300415, "global_step": 395169, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1518962383270264, "global_step": 395170, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0836284160614014, "global_step": 395171, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0182502269744873, "global_step": 395172, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0681958198547363, "global_step": 395173, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1974875926971436, "global_step": 395174, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0295042991638184, "global_step": 395175, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.06071138381958, "global_step": 395176, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1523916721343994, "global_step": 395177, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0815327167510986, "global_step": 395178, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.083054780960083, "global_step": 395179, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0679590702056885, "global_step": 395180, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0403690338134766, "global_step": 395181, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.116684675216675, "global_step": 395182, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1300413608551025, "global_step": 395183, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.041126012802124, "global_step": 395184, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.132406234741211, "global_step": 395185, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.118500232696533, "global_step": 395186, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0473265647888184, "global_step": 395187, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0757627487182617, "global_step": 395188, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.08589243888855, "global_step": 395189, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.084998607635498, "global_step": 395190, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0744988918304443, "global_step": 395191, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1127569675445557, "global_step": 395192, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.040374755859375, "global_step": 395193, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.090451717376709, "global_step": 395194, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.17960524559021, "global_step": 395195, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0546457767486572, "global_step": 395196, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.052156448364258, "global_step": 395197, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9989876747131348, "global_step": 395198, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0688376426696777, "global_step": 395199, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.019199848175049, "global_step": 395200, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1350557804107666, "global_step": 395201, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0698611736297607, "global_step": 395202, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.099897861480713, "global_step": 395203, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0925984382629395, "global_step": 395204, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.174574375152588, "global_step": 395205, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.069519519805908, "global_step": 395206, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1379411220550537, "global_step": 395207, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.100306987762451, "global_step": 395208, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.053215980529785, "global_step": 395209, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1044211387634277, "global_step": 395210, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0378034114837646, "global_step": 395211, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.105756998062134, "global_step": 395212, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1336214542388916, "global_step": 395213, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1416172981262207, "global_step": 395214, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.180389642715454, "global_step": 395215, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.158118486404419, "global_step": 395216, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0975425243377686, "global_step": 395217, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.108097553253174, "global_step": 395218, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1651060581207275, "global_step": 395219, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0780394077301025, "global_step": 395220, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0517687797546387, "global_step": 395221, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1411821842193604, "global_step": 395222, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.126020669937134, "global_step": 395223, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.145939350128174, "global_step": 395224, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.01582407951355, "global_step": 395225, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.078955888748169, "global_step": 395226, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1415867805480957, "global_step": 395227, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1092731952667236, "global_step": 395228, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0983521938323975, "global_step": 395229, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.082695484161377, "global_step": 395230, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1767122745513916, "global_step": 395231, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0970234870910645, "global_step": 395232, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.124751329421997, "global_step": 395233, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.098360538482666, "global_step": 395234, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1060919761657715, "global_step": 395235, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.034910202026367, "global_step": 395236, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.073422908782959, "global_step": 395237, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1130619049072266, "global_step": 395238, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1004414558410645, "global_step": 395239, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1051509380340576, "global_step": 395240, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.130028247833252, "global_step": 395241, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1536924839019775, "global_step": 395242, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9989380836486816, "global_step": 395243, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0189969539642334, "global_step": 395244, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.144904375076294, "global_step": 395245, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1079297065734863, "global_step": 395246, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.153808116912842, "global_step": 395247, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.118666172027588, "global_step": 395248, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.10031795501709, "global_step": 395249, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.162278175354004, "global_step": 395250, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0828161239624023, "global_step": 395251, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0556421279907227, "global_step": 395252, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.161820650100708, "global_step": 395253, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1234073638916016, "global_step": 395254, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0760889053344727, "global_step": 395255, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.133429527282715, "global_step": 395256, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.112088203430176, "global_step": 395257, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0818278789520264, "global_step": 395258, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.069319248199463, "global_step": 395259, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.083946704864502, "global_step": 395260, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.047316551208496, "global_step": 395261, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.114494800567627, "global_step": 395262, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1613364219665527, "global_step": 395263, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0451295375823975, "global_step": 395264, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1618056297302246, "global_step": 395265, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1600074768066406, "global_step": 395266, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1018192768096924, "global_step": 395267, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.163175106048584, "global_step": 395268, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.097266912460327, "global_step": 395269, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.176224946975708, "global_step": 395270, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.117114782333374, "global_step": 395271, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1339216232299805, "global_step": 395272, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1000890731811523, "global_step": 395273, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1058833599090576, "global_step": 395274, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0795798301696777, "global_step": 395275, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1276168823242188, "global_step": 395276, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1410062313079834, "global_step": 395277, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.022287368774414, "global_step": 395278, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.107323408126831, "global_step": 395279, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0845541954040527, "global_step": 395280, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0942726135253906, "global_step": 395281, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0510032176971436, "global_step": 395282, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.059441566467285, "global_step": 395283, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0506346225738525, "global_step": 395284, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1395576000213623, "global_step": 395285, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0653188228607178, "global_step": 395286, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.114473342895508, "global_step": 395287, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.065131664276123, "global_step": 395288, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0983214378356934, "global_step": 395289, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1022558212280273, "global_step": 395290, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.11047625541687, "global_step": 395291, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0996029376983643, "global_step": 395292, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0885376930236816, "global_step": 395293, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1693854331970215, "global_step": 395294, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0765926837921143, "global_step": 395295, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1284399032592773, "global_step": 395296, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.084456205368042, "global_step": 395297, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1292262077331543, "global_step": 395298, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0766777992248535, "global_step": 395299, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1515252590179443, "global_step": 395300, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1019201278686523, "global_step": 395301, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1123480796813965, "global_step": 395302, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1097190380096436, "global_step": 395303, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.063847064971924, "global_step": 395304, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1156961917877197, "global_step": 395305, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.093933343887329, "global_step": 395306, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0068228244781494, "global_step": 395307, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1938729286193848, "global_step": 395308, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.124474048614502, "global_step": 395309, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0819895267486572, "global_step": 395310, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9706987142562866, "global_step": 395311, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0936028957366943, "global_step": 395312, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.107161521911621, "global_step": 395313, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1570675373077393, "global_step": 395314, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0744919776916504, "global_step": 395315, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.04301118850708, "global_step": 395316, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0509684085845947, "global_step": 395317, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.100257158279419, "global_step": 395318, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0753777027130127, "global_step": 395319, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1095385551452637, "global_step": 395320, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0847253799438477, "global_step": 395321, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.127397060394287, "global_step": 395322, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0252208709716797, "global_step": 395323, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.140516757965088, "global_step": 395324, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.2060649394989014, "global_step": 395325, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0648534297943115, "global_step": 395326, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.070373296737671, "global_step": 395327, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0046863555908203, "global_step": 395328, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0430960655212402, "global_step": 395329, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.098350763320923, "global_step": 395330, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.021306276321411, "global_step": 395331, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.153290033340454, "global_step": 395332, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.178889274597168, "global_step": 395333, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.160306692123413, "global_step": 395334, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0687410831451416, "global_step": 395335, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.076004981994629, "global_step": 395336, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9355930089950562, "global_step": 395337, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0842671394348145, "global_step": 395338, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1598265171051025, "global_step": 395339, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.125749349594116, "global_step": 395340, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.092738151550293, "global_step": 395341, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1659529209136963, "global_step": 395342, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.134134292602539, "global_step": 395343, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.116668939590454, "global_step": 395344, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0445661544799805, "global_step": 395345, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1180362701416016, "global_step": 395346, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1065289974212646, "global_step": 395347, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0916640758514404, "global_step": 395348, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.052675485610962, "global_step": 395349, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.097994089126587, "global_step": 395350, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.077134132385254, "global_step": 395351, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0557267665863037, "global_step": 395352, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.095531702041626, "global_step": 395353, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1765992641448975, "global_step": 395354, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.109715223312378, "global_step": 395355, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.105854034423828, "global_step": 395356, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1044881343841553, "global_step": 395357, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0724058151245117, "global_step": 395358, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1684513092041016, "global_step": 395359, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0998263359069824, "global_step": 395360, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.105437755584717, "global_step": 395361, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0938851833343506, "global_step": 395362, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.097693681716919, "global_step": 395363, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1177399158477783, "global_step": 395364, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.069549083709717, "global_step": 395365, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0649311542510986, "global_step": 395366, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1045055389404297, "global_step": 395367, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0955207347869873, "global_step": 395368, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.2075181007385254, "global_step": 395369, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.163865804672241, "global_step": 395370, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.128767251968384, "global_step": 395371, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1528329849243164, "global_step": 395372, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1447064876556396, "global_step": 395373, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.09763503074646, "global_step": 395374, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1056926250457764, "global_step": 395375, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0916388034820557, "global_step": 395376, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.087904691696167, "global_step": 395377, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0740694999694824, "global_step": 395378, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0673325061798096, "global_step": 395379, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0945377349853516, "global_step": 395380, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0539112091064453, "global_step": 395381, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0611541271209717, "global_step": 395382, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1424617767333984, "global_step": 395383, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.091887950897217, "global_step": 395384, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.2187445163726807, "global_step": 395385, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1113805770874023, "global_step": 395386, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.060317039489746, "global_step": 395387, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.10917329788208, "global_step": 395388, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.034449338912964, "global_step": 395389, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.136293411254883, "global_step": 395390, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1259524822235107, "global_step": 395391, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1514840126037598, "global_step": 395392, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.079784393310547, "global_step": 395393, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.14019775390625, "global_step": 395394, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.190566301345825, "global_step": 395395, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0669736862182617, "global_step": 395396, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1520371437072754, "global_step": 395397, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0975449085235596, "global_step": 395398, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0921456813812256, "global_step": 395399, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9551500082015991, "global_step": 395400, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.114253044128418, "global_step": 395401, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0734381675720215, "global_step": 395402, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1796319484710693, "global_step": 395403, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1387698650360107, "global_step": 395404, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0880417823791504, "global_step": 395405, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1364634037017822, "global_step": 395406, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.098517894744873, "global_step": 395407, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.044208526611328, "global_step": 395408, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.156815528869629, "global_step": 395409, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.12914776802063, "global_step": 395410, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1674227714538574, "global_step": 395411, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1352531909942627, "global_step": 395412, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.074385404586792, "global_step": 395413, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1833691596984863, "global_step": 395414, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.059183120727539, "global_step": 395415, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0808053016662598, "global_step": 395416, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1687204837799072, "global_step": 395417, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1255414485931396, "global_step": 395418, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1176981925964355, "global_step": 395419, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0166914463043213, "global_step": 395420, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.126490592956543, "global_step": 395421, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.112441062927246, "global_step": 395422, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0855612754821777, "global_step": 395423, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0902352333068848, "global_step": 395424, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1197896003723145, "global_step": 395425, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.088783025741577, "global_step": 395426, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.047053337097168, "global_step": 395427, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1633989810943604, "global_step": 395428, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1043097972869873, "global_step": 395429, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.2331016063690186, "global_step": 395430, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1082170009613037, "global_step": 395431, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1198577880859375, "global_step": 395432, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0733320713043213, "global_step": 395433, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1726224422454834, "global_step": 395434, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0564000606536865, "global_step": 395435, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0221400260925293, "global_step": 395436, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1475672721862793, "global_step": 395437, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0927751064300537, "global_step": 395438, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1605963706970215, "global_step": 395439, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.185140609741211, "global_step": 395440, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.109642744064331, "global_step": 395441, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.105149030685425, "global_step": 395442, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0973289012908936, "global_step": 395443, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.2018308639526367, "global_step": 395444, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.106358528137207, "global_step": 395445, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.080814838409424, "global_step": 395446, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1071767807006836, "global_step": 395447, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0855705738067627, "global_step": 395448, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.123894214630127, "global_step": 395449, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.2061100006103516, "global_step": 395450, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1076736450195312, "global_step": 395451, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.156271457672119, "global_step": 395452, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.142223834991455, "global_step": 395453, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.183196783065796, "global_step": 395454, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.099457025527954, "global_step": 395455, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.143984794616699, "global_step": 395456, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0889840126037598, "global_step": 395457, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0103025436401367, "global_step": 395458, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1103708744049072, "global_step": 395459, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0714902877807617, "global_step": 395460, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1820311546325684, "global_step": 395461, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0914595127105713, "global_step": 395462, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0715739727020264, "global_step": 395463, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.098764419555664, "global_step": 395464, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.12965726852417, "global_step": 395465, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1467130184173584, "global_step": 395466, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0998737812042236, "global_step": 395467, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.2014760971069336, "global_step": 395468, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1054775714874268, "global_step": 395469, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1428844928741455, "global_step": 395470, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0774312019348145, "global_step": 395471, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.086810827255249, "global_step": 395472, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1209845542907715, "global_step": 395473, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.10666561126709, "global_step": 395474, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1113672256469727, "global_step": 395475, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1002941131591797, "global_step": 395476, "epoch": 757, "lr": 5e-05}
{"train_loss": 1.9926906824111938, "global_step": 395477, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.136078357696533, "global_step": 395478, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0359697341918945, "global_step": 395479, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0866858959198, "global_step": 395480, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0750646591186523, "global_step": 395481, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.1000571250915527, "global_step": 395482, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0723330974578857, "global_step": 395483, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.098554849624634, "global_step": 395484, "epoch": 757, "lr": 5e-05}
{"train_loss": 2.0846779346466064, "global_step": 395485, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1224069595336914, "global_step": 395486, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0802130699157715, "global_step": 395487, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.053868532180786, "global_step": 395488, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1448097229003906, "global_step": 395489, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1613142490386963, "global_step": 395490, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0750107765197754, "global_step": 395491, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0341415405273438, "global_step": 395492, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1098134517669678, "global_step": 395493, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0302841663360596, "global_step": 395494, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.179103136062622, "global_step": 395495, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1481316089630127, "global_step": 395496, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.136110782623291, "global_step": 395497, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1582353115081787, "global_step": 395498, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.066997528076172, "global_step": 395499, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0635626316070557, "global_step": 395500, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.121955633163452, "global_step": 395501, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.081035852432251, "global_step": 395502, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1000256538391113, "global_step": 395503, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0092740058898926, "global_step": 395504, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.04666805267334, "global_step": 395505, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0398788452148438, "global_step": 395506, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.008356809616089, "global_step": 395507, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0326223373413086, "global_step": 395508, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.090644359588623, "global_step": 395509, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1694860458374023, "global_step": 395510, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1153783798217773, "global_step": 395511, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.151122570037842, "global_step": 395512, "epoch": 758, "lr": 5e-05}
{"train_loss": 1.9941474199295044, "global_step": 395513, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0957844257354736, "global_step": 395514, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0978662967681885, "global_step": 395515, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.083372116088867, "global_step": 395516, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0859861373901367, "global_step": 395517, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0903120040893555, "global_step": 395518, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0273196697235107, "global_step": 395519, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0008721351623535, "global_step": 395520, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.099712610244751, "global_step": 395521, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.042344331741333, "global_step": 395522, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0858685970306396, "global_step": 395523, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0507447719573975, "global_step": 395524, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0185511112213135, "global_step": 395525, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0609161853790283, "global_step": 395526, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0851502418518066, "global_step": 395527, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.182760715484619, "global_step": 395528, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0146374702453613, "global_step": 395529, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0442984104156494, "global_step": 395530, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1032803058624268, "global_step": 395531, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1748709678649902, "global_step": 395532, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1507651805877686, "global_step": 395533, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1265056133270264, "global_step": 395534, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0676584243774414, "global_step": 395535, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.122904062271118, "global_step": 395536, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.048532724380493, "global_step": 395537, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0888962745666504, "global_step": 395538, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.075756549835205, "global_step": 395539, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.036656379699707, "global_step": 395540, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.057187080383301, "global_step": 395541, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0835142135620117, "global_step": 395542, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1086153984069824, "global_step": 395543, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0438902378082275, "global_step": 395544, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0632476806640625, "global_step": 395545, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1023430824279785, "global_step": 395546, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0741806030273438, "global_step": 395547, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0797436237335205, "global_step": 395548, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0150458812713623, "global_step": 395549, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1372764110565186, "global_step": 395550, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.061222791671753, "global_step": 395551, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0979607105255127, "global_step": 395552, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0800020694732666, "global_step": 395553, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.073239803314209, "global_step": 395554, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.085336923599243, "global_step": 395555, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1342382431030273, "global_step": 395556, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0232126712799072, "global_step": 395557, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1840267181396484, "global_step": 395558, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1412315368652344, "global_step": 395559, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1385929584503174, "global_step": 395560, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.139122724533081, "global_step": 395561, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.127427816390991, "global_step": 395562, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.097701072692871, "global_step": 395563, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1584901809692383, "global_step": 395564, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.029974937438965, "global_step": 395565, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.122483730316162, "global_step": 395566, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0503687858581543, "global_step": 395567, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.143951177597046, "global_step": 395568, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0078318119049072, "global_step": 395569, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1099321842193604, "global_step": 395570, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.114974021911621, "global_step": 395571, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.090578317642212, "global_step": 395572, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.076235055923462, "global_step": 395573, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1978161334991455, "global_step": 395574, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0363268852233887, "global_step": 395575, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1450095176696777, "global_step": 395576, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0428643226623535, "global_step": 395577, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1275815963745117, "global_step": 395578, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.09873366355896, "global_step": 395579, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.130615711212158, "global_step": 395580, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0879464149475098, "global_step": 395581, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0847890377044678, "global_step": 395582, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1263797283172607, "global_step": 395583, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0852701663970947, "global_step": 395584, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.111764907836914, "global_step": 395585, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0521204471588135, "global_step": 395586, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.108307123184204, "global_step": 395587, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1178669929504395, "global_step": 395588, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.076935291290283, "global_step": 395589, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.060157299041748, "global_step": 395590, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0681941509246826, "global_step": 395591, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.121054172515869, "global_step": 395592, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1249208450317383, "global_step": 395593, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1263086795806885, "global_step": 395594, "epoch": 758, "lr": 5e-05}
{"train_loss": 1.9984146356582642, "global_step": 395595, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1507768630981445, "global_step": 395596, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.036418914794922, "global_step": 395597, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0358052253723145, "global_step": 395598, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0224061012268066, "global_step": 395599, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1911211013793945, "global_step": 395600, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1036574840545654, "global_step": 395601, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.152620792388916, "global_step": 395602, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0740439891815186, "global_step": 395603, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1148838996887207, "global_step": 395604, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1241230964660645, "global_step": 395605, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1364221572875977, "global_step": 395606, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0661380290985107, "global_step": 395607, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1010258197784424, "global_step": 395608, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.087432622909546, "global_step": 395609, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0260093212127686, "global_step": 395610, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.123861074447632, "global_step": 395611, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0787885189056396, "global_step": 395612, "epoch": 758, "lr": 5e-05}
{"train_loss": 1.9796624183654785, "global_step": 395613, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0811517238616943, "global_step": 395614, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.082160472869873, "global_step": 395615, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1257290840148926, "global_step": 395616, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.055485248565674, "global_step": 395617, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.072660446166992, "global_step": 395618, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0905139446258545, "global_step": 395619, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.069596290588379, "global_step": 395620, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.144167423248291, "global_step": 395621, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0704338550567627, "global_step": 395622, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0921554565429688, "global_step": 395623, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0721561908721924, "global_step": 395624, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.107262134552002, "global_step": 395625, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1554203033447266, "global_step": 395626, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0952506065368652, "global_step": 395627, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1199159622192383, "global_step": 395628, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0991578102111816, "global_step": 395629, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0986030101776123, "global_step": 395630, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.15958571434021, "global_step": 395631, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.116504192352295, "global_step": 395632, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.156705856323242, "global_step": 395633, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0793726444244385, "global_step": 395634, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.155869960784912, "global_step": 395635, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.084887981414795, "global_step": 395636, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.093632698059082, "global_step": 395637, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.117424726486206, "global_step": 395638, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0376250743865967, "global_step": 395639, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.036477565765381, "global_step": 395640, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.062696695327759, "global_step": 395641, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0838754177093506, "global_step": 395642, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.104668378829956, "global_step": 395643, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.180588722229004, "global_step": 395644, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0409395694732666, "global_step": 395645, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0606184005737305, "global_step": 395646, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.03658127784729, "global_step": 395647, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0799388885498047, "global_step": 395648, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1102845668792725, "global_step": 395649, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0897409915924072, "global_step": 395650, "epoch": 758, "lr": 5e-05}
{"train_loss": 1.9754222631454468, "global_step": 395651, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0282719135284424, "global_step": 395652, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0482757091522217, "global_step": 395653, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.111703872680664, "global_step": 395654, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0229623317718506, "global_step": 395655, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.149606466293335, "global_step": 395656, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1134512424468994, "global_step": 395657, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.046067476272583, "global_step": 395658, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0578317642211914, "global_step": 395659, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.037442922592163, "global_step": 395660, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1238317489624023, "global_step": 395661, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0872442722320557, "global_step": 395662, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.096088409423828, "global_step": 395663, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1067299842834473, "global_step": 395664, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1248068809509277, "global_step": 395665, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1242964267730713, "global_step": 395666, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1152243614196777, "global_step": 395667, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1301918029785156, "global_step": 395668, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0802180767059326, "global_step": 395669, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.053359031677246, "global_step": 395670, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.049522876739502, "global_step": 395671, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.102452278137207, "global_step": 395672, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0686142444610596, "global_step": 395673, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.084468126296997, "global_step": 395674, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.050572633743286, "global_step": 395675, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.173760175704956, "global_step": 395676, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0434579849243164, "global_step": 395677, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.091135025024414, "global_step": 395678, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1122841835021973, "global_step": 395679, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.069291114807129, "global_step": 395680, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0854997634887695, "global_step": 395681, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0378849506378174, "global_step": 395682, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.123514413833618, "global_step": 395683, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.163203001022339, "global_step": 395684, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.10347580909729, "global_step": 395685, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0969009399414062, "global_step": 395686, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.064427137374878, "global_step": 395687, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.094482898712158, "global_step": 395688, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0552656650543213, "global_step": 395689, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.132418632507324, "global_step": 395690, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0495359897613525, "global_step": 395691, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.142801284790039, "global_step": 395692, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0821924209594727, "global_step": 395693, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1139798164367676, "global_step": 395694, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0459189414978027, "global_step": 395695, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.084205389022827, "global_step": 395696, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1114206314086914, "global_step": 395697, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0824294090270996, "global_step": 395698, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.159454822540283, "global_step": 395699, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1279711723327637, "global_step": 395700, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.097463846206665, "global_step": 395701, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.123749017715454, "global_step": 395702, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0679800510406494, "global_step": 395703, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1253106594085693, "global_step": 395704, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0579822063446045, "global_step": 395705, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.069514036178589, "global_step": 395706, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1265292167663574, "global_step": 395707, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.058682441711426, "global_step": 395708, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.099140167236328, "global_step": 395709, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0706193447113037, "global_step": 395710, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0966527462005615, "global_step": 395711, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.159273624420166, "global_step": 395712, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1517648696899414, "global_step": 395713, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.115044593811035, "global_step": 395714, "epoch": 758, "lr": 5e-05}
{"train_loss": 1.979511022567749, "global_step": 395715, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0141794681549072, "global_step": 395716, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.161923885345459, "global_step": 395717, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.144106149673462, "global_step": 395718, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1725807189941406, "global_step": 395719, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0618081092834473, "global_step": 395720, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.041501522064209, "global_step": 395721, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.048161745071411, "global_step": 395722, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.137052059173584, "global_step": 395723, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0371603965759277, "global_step": 395724, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0744636058807373, "global_step": 395725, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1397464275360107, "global_step": 395726, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0177714824676514, "global_step": 395727, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0626087188720703, "global_step": 395728, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0770180225372314, "global_step": 395729, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1968703269958496, "global_step": 395730, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.116201639175415, "global_step": 395731, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.196732521057129, "global_step": 395732, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1354570388793945, "global_step": 395733, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0668060779571533, "global_step": 395734, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1356406211853027, "global_step": 395735, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1620140075683594, "global_step": 395736, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0726795196533203, "global_step": 395737, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1186583042144775, "global_step": 395738, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0607259273529053, "global_step": 395739, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0259156227111816, "global_step": 395740, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.048631191253662, "global_step": 395741, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.069706678390503, "global_step": 395742, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1523044109344482, "global_step": 395743, "epoch": 758, "lr": 5e-05}
{"train_loss": 1.9728882312774658, "global_step": 395744, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.078803300857544, "global_step": 395745, "epoch": 758, "lr": 5e-05}
{"train_loss": 1.9675143957138062, "global_step": 395746, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0072426795959473, "global_step": 395747, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1650028228759766, "global_step": 395748, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0688316822052, "global_step": 395749, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0312283039093018, "global_step": 395750, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.2209348678588867, "global_step": 395751, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.059981346130371, "global_step": 395752, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.002119779586792, "global_step": 395753, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1013734340667725, "global_step": 395754, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1564559936523438, "global_step": 395755, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.111117362976074, "global_step": 395756, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.017625331878662, "global_step": 395757, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0477681159973145, "global_step": 395758, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1663613319396973, "global_step": 395759, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.031071901321411, "global_step": 395760, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.128253698348999, "global_step": 395761, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1001369953155518, "global_step": 395762, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0340921878814697, "global_step": 395763, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1017682552337646, "global_step": 395764, "epoch": 758, "lr": 5e-05}
{"train_loss": 1.9825890064239502, "global_step": 395765, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1079580783843994, "global_step": 395766, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1331770420074463, "global_step": 395767, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1891074180603027, "global_step": 395768, "epoch": 758, "lr": 5e-05}
{"train_loss": 1.994908094406128, "global_step": 395769, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0673575401306152, "global_step": 395770, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0758426189422607, "global_step": 395771, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.114017963409424, "global_step": 395772, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.103463649749756, "global_step": 395773, "epoch": 758, "lr": 5e-05}
{"train_loss": 1.9607139825820923, "global_step": 395774, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.115285634994507, "global_step": 395775, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1234538555145264, "global_step": 395776, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1139132976531982, "global_step": 395777, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1982483863830566, "global_step": 395778, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.139859437942505, "global_step": 395779, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.144273519515991, "global_step": 395780, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1085174083709717, "global_step": 395781, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0693342685699463, "global_step": 395782, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.131601572036743, "global_step": 395783, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0924289226531982, "global_step": 395784, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0624356269836426, "global_step": 395785, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0579886436462402, "global_step": 395786, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.072190284729004, "global_step": 395787, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.130805015563965, "global_step": 395788, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.057803153991699, "global_step": 395789, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.055677890777588, "global_step": 395790, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1429078578948975, "global_step": 395791, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1018126010894775, "global_step": 395792, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1281042098999023, "global_step": 395793, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1687867641448975, "global_step": 395794, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.071828842163086, "global_step": 395795, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0110251903533936, "global_step": 395796, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0572593212127686, "global_step": 395797, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.055607795715332, "global_step": 395798, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.12656831741333, "global_step": 395799, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.058260917663574, "global_step": 395800, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1094069480895996, "global_step": 395801, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.141277313232422, "global_step": 395802, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0677883625030518, "global_step": 395803, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0555524826049805, "global_step": 395804, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.111567497253418, "global_step": 395805, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.019444227218628, "global_step": 395806, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0223116874694824, "global_step": 395807, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.161464214324951, "global_step": 395808, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.200622797012329, "global_step": 395809, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.081491708755493, "global_step": 395810, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.035534381866455, "global_step": 395811, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.15708065032959, "global_step": 395812, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.144246816635132, "global_step": 395813, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.05252742767334, "global_step": 395814, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.103931427001953, "global_step": 395815, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.17899751663208, "global_step": 395816, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0763163566589355, "global_step": 395817, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0375301837921143, "global_step": 395818, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.074291229248047, "global_step": 395819, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1948342323303223, "global_step": 395820, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.016139030456543, "global_step": 395821, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.2309930324554443, "global_step": 395822, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0497188568115234, "global_step": 395823, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1244149208068848, "global_step": 395824, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.080066680908203, "global_step": 395825, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.055172920227051, "global_step": 395826, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0487663745880127, "global_step": 395827, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0771477222442627, "global_step": 395828, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.083185911178589, "global_step": 395829, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.069044828414917, "global_step": 395830, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.186340093612671, "global_step": 395831, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0718021392822266, "global_step": 395832, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.129592180252075, "global_step": 395833, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.122523784637451, "global_step": 395834, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0663137435913086, "global_step": 395835, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.045557975769043, "global_step": 395836, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1026628017425537, "global_step": 395837, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0541563034057617, "global_step": 395838, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1094205379486084, "global_step": 395839, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1052279472351074, "global_step": 395840, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1414990425109863, "global_step": 395841, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0295627117156982, "global_step": 395842, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0689845085144043, "global_step": 395843, "epoch": 758, "lr": 5e-05}
{"train_loss": 1.9913665056228638, "global_step": 395844, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.160050868988037, "global_step": 395845, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0975821018218994, "global_step": 395846, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0283665657043457, "global_step": 395847, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.092362403869629, "global_step": 395848, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.068910598754883, "global_step": 395849, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1451363563537598, "global_step": 395850, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1565685272216797, "global_step": 395851, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0166537761688232, "global_step": 395852, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0951974391937256, "global_step": 395853, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1059699058532715, "global_step": 395854, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0889499187469482, "global_step": 395855, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0790064334869385, "global_step": 395856, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1235153675079346, "global_step": 395857, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.051500082015991, "global_step": 395858, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.09305739402771, "global_step": 395859, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1115517616271973, "global_step": 395860, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0938591957092285, "global_step": 395861, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.085991144180298, "global_step": 395862, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.133469343185425, "global_step": 395863, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0272674560546875, "global_step": 395864, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0925729274749756, "global_step": 395865, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1054515838623047, "global_step": 395866, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.129951000213623, "global_step": 395867, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.038511037826538, "global_step": 395868, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.066659688949585, "global_step": 395869, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1645050048828125, "global_step": 395870, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1620326042175293, "global_step": 395871, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.124967336654663, "global_step": 395872, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.148733377456665, "global_step": 395873, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0147509574890137, "global_step": 395874, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1779181957244873, "global_step": 395875, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1225974559783936, "global_step": 395876, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0634586811065674, "global_step": 395877, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.13358998298645, "global_step": 395878, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1586945056915283, "global_step": 395879, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1088671684265137, "global_step": 395880, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1185660362243652, "global_step": 395881, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.075167417526245, "global_step": 395882, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.05332612991333, "global_step": 395883, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1683549880981445, "global_step": 395884, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.076374053955078, "global_step": 395885, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.05503249168396, "global_step": 395886, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.124330759048462, "global_step": 395887, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.184631824493408, "global_step": 395888, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1193995475769043, "global_step": 395889, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.040896415710449, "global_step": 395890, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0515494346618652, "global_step": 395891, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.112107515335083, "global_step": 395892, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.055628776550293, "global_step": 395893, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.2075657844543457, "global_step": 395894, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1973299980163574, "global_step": 395895, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0515074729919434, "global_step": 395896, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0442495346069336, "global_step": 395897, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1894993782043457, "global_step": 395898, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0860395431518555, "global_step": 395899, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1008055210113525, "global_step": 395900, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0884008407592773, "global_step": 395901, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0550642013549805, "global_step": 395902, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.10111665725708, "global_step": 395903, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.209136724472046, "global_step": 395904, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0265088081359863, "global_step": 395905, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.070388078689575, "global_step": 395906, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1797192096710205, "global_step": 395907, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0883307456970215, "global_step": 395908, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1156723499298096, "global_step": 395909, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0279242992401123, "global_step": 395910, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.083533525466919, "global_step": 395911, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.090897798538208, "global_step": 395912, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.117460012435913, "global_step": 395913, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0414860248565674, "global_step": 395914, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1000499725341797, "global_step": 395915, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0460972785949707, "global_step": 395916, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.099567413330078, "global_step": 395917, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1612930297851562, "global_step": 395918, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.074202537536621, "global_step": 395919, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.139835834503174, "global_step": 395920, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.010730266571045, "global_step": 395921, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1432576179504395, "global_step": 395922, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.068615436553955, "global_step": 395923, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0496861934661865, "global_step": 395924, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.104631185531616, "global_step": 395925, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.082967519760132, "global_step": 395926, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1035051345825195, "global_step": 395927, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.110889434814453, "global_step": 395928, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.167386293411255, "global_step": 395929, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.059112310409546, "global_step": 395930, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.077282667160034, "global_step": 395931, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0301907062530518, "global_step": 395932, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0336503982543945, "global_step": 395933, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0520179271698, "global_step": 395934, "epoch": 758, "lr": 5e-05}
{"train_loss": 1.998026967048645, "global_step": 395935, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0639078617095947, "global_step": 395936, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.191241979598999, "global_step": 395937, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0728728771209717, "global_step": 395938, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1359825134277344, "global_step": 395939, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.103936195373535, "global_step": 395940, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.107179641723633, "global_step": 395941, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1101436614990234, "global_step": 395942, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1553847789764404, "global_step": 395943, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.055936098098755, "global_step": 395944, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.175354480743408, "global_step": 395945, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.112133741378784, "global_step": 395946, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.160008192062378, "global_step": 395947, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1874794960021973, "global_step": 395948, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0640852451324463, "global_step": 395949, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0589632987976074, "global_step": 395950, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0057263374328613, "global_step": 395951, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.046069383621216, "global_step": 395952, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0735247135162354, "global_step": 395953, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0714962482452393, "global_step": 395954, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.097123861312866, "global_step": 395955, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0992980003356934, "global_step": 395956, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1044180393218994, "global_step": 395957, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1222567558288574, "global_step": 395958, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0144922733306885, "global_step": 395959, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1233410835266113, "global_step": 395960, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1532745361328125, "global_step": 395961, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0364954471588135, "global_step": 395962, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.109590530395508, "global_step": 395963, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1132092475891113, "global_step": 395964, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.047926664352417, "global_step": 395965, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.039726495742798, "global_step": 395966, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.218858003616333, "global_step": 395967, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.082563877105713, "global_step": 395968, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0585505962371826, "global_step": 395969, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.108229637145996, "global_step": 395970, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.078233242034912, "global_step": 395971, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1518445014953613, "global_step": 395972, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.076631546020508, "global_step": 395973, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.051920175552368, "global_step": 395974, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.160513162612915, "global_step": 395975, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1388723850250244, "global_step": 395976, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.060455560684204, "global_step": 395977, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0917131900787354, "global_step": 395978, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0788183212280273, "global_step": 395979, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.208303689956665, "global_step": 395980, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.113597869873047, "global_step": 395981, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1496431827545166, "global_step": 395982, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1159720420837402, "global_step": 395983, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0818581581115723, "global_step": 395984, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0142557621002197, "global_step": 395985, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.2173314094543457, "global_step": 395986, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1113698482513428, "global_step": 395987, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1105895042419434, "global_step": 395988, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0495405197143555, "global_step": 395989, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1416854858398438, "global_step": 395990, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.03202223777771, "global_step": 395991, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.157893180847168, "global_step": 395992, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0625667572021484, "global_step": 395993, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.026243209838867, "global_step": 395994, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.191377878189087, "global_step": 395995, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.102823495864868, "global_step": 395996, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0846939086914062, "global_step": 395997, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0717923641204834, "global_step": 395998, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.155501365661621, "global_step": 395999, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.167417049407959, "global_step": 396000, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1229419708251953, "global_step": 396001, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.069363832473755, "global_step": 396002, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0428075790405273, "global_step": 396003, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1295952796936035, "global_step": 396004, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.131290912628174, "global_step": 396005, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1497721672058105, "global_step": 396006, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0537710189819336, "global_step": 396007, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.203964948654175, "global_step": 396008, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1367626190185547, "global_step": 396009, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.20611572265625, "global_step": 396010, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0876047611236572, "global_step": 396011, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.148024320602417, "global_step": 396012, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0722882747650146, "global_step": 396013, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1307015419006348, "global_step": 396014, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1749789714813232, "global_step": 396015, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.035271167755127, "global_step": 396016, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.08009672164917, "global_step": 396017, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.056624412536621, "global_step": 396018, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0818588733673096, "global_step": 396019, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.023442029953003, "global_step": 396020, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1340208053588867, "global_step": 396021, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.086132049560547, "global_step": 396022, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1053407192230225, "global_step": 396023, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1294913291931152, "global_step": 396024, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1168179512023926, "global_step": 396025, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.107853412628174, "global_step": 396026, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.201120615005493, "global_step": 396027, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0694704055786133, "global_step": 396028, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.074822425842285, "global_step": 396029, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1017374992370605, "global_step": 396030, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.008607864379883, "global_step": 396031, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0236544609069824, "global_step": 396032, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.140021800994873, "global_step": 396033, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.148207664489746, "global_step": 396034, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.147373676300049, "global_step": 396035, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0544707775115967, "global_step": 396036, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.156494379043579, "global_step": 396037, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.086888074874878, "global_step": 396038, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1137847900390625, "global_step": 396039, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.09462308883667, "global_step": 396040, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.179964065551758, "global_step": 396041, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.106999158859253, "global_step": 396042, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1236770153045654, "global_step": 396043, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.113914966583252, "global_step": 396044, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1548914909362793, "global_step": 396045, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1323063373565674, "global_step": 396046, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1553831100463867, "global_step": 396047, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.115175485610962, "global_step": 396048, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1407835483551025, "global_step": 396049, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1637229919433594, "global_step": 396050, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.072232723236084, "global_step": 396051, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.088801145553589, "global_step": 396052, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.238352060317993, "global_step": 396053, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1648001670837402, "global_step": 396054, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0843734741210938, "global_step": 396055, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1524412631988525, "global_step": 396056, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.089629650115967, "global_step": 396057, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.140245199203491, "global_step": 396058, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0223355293273926, "global_step": 396059, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.051578998565674, "global_step": 396060, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1555137634277344, "global_step": 396061, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.214052677154541, "global_step": 396062, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.078216791152954, "global_step": 396063, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1354517936706543, "global_step": 396064, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1126604080200195, "global_step": 396065, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1847832202911377, "global_step": 396066, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.074403762817383, "global_step": 396067, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.194404363632202, "global_step": 396068, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.066521644592285, "global_step": 396069, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1522886753082275, "global_step": 396070, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0577268600463867, "global_step": 396071, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1273443698883057, "global_step": 396072, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0965728759765625, "global_step": 396073, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1539394855499268, "global_step": 396074, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.183225631713867, "global_step": 396075, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.058936834335327, "global_step": 396076, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1339616775512695, "global_step": 396077, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.033818483352661, "global_step": 396078, "epoch": 758, "lr": 5e-05}
{"train_loss": 1.999061107635498, "global_step": 396079, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.090435743331909, "global_step": 396080, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.064295768737793, "global_step": 396081, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.095273733139038, "global_step": 396082, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.125105619430542, "global_step": 396083, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1459505558013916, "global_step": 396084, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1000773906707764, "global_step": 396085, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0990474224090576, "global_step": 396086, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0484867095947266, "global_step": 396087, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1239142417907715, "global_step": 396088, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1741554737091064, "global_step": 396089, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1963603496551514, "global_step": 396090, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.109286308288574, "global_step": 396091, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0748579502105713, "global_step": 396092, "epoch": 758, "lr": 5e-05}
{"train_loss": 1.967271089553833, "global_step": 396093, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.119473695755005, "global_step": 396094, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.128202199935913, "global_step": 396095, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.119870901107788, "global_step": 396096, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.014453649520874, "global_step": 396097, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.094106912612915, "global_step": 396098, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.097564697265625, "global_step": 396099, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.102083444595337, "global_step": 396100, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.115736484527588, "global_step": 396101, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.052739381790161, "global_step": 396102, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.094364881515503, "global_step": 396103, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.030683994293213, "global_step": 396104, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.122326135635376, "global_step": 396105, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0958974361419678, "global_step": 396106, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1541948318481445, "global_step": 396107, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0378005504608154, "global_step": 396108, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1256887912750244, "global_step": 396109, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0052809715270996, "global_step": 396110, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.075718879699707, "global_step": 396111, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1758105754852295, "global_step": 396112, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.162790298461914, "global_step": 396113, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.144428014755249, "global_step": 396114, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.074702501296997, "global_step": 396115, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1154427528381348, "global_step": 396116, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0215859413146973, "global_step": 396117, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.18245530128479, "global_step": 396118, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1059300899505615, "global_step": 396119, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1446163654327393, "global_step": 396120, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1576335430145264, "global_step": 396121, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1569600105285645, "global_step": 396122, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0751874446868896, "global_step": 396123, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.097156047821045, "global_step": 396124, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.149710178375244, "global_step": 396125, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.099008083343506, "global_step": 396126, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.073251724243164, "global_step": 396127, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1986923217773438, "global_step": 396128, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0593674182891846, "global_step": 396129, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1012744903564453, "global_step": 396130, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0325229167938232, "global_step": 396131, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0916097164154053, "global_step": 396132, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0822322368621826, "global_step": 396133, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1553122997283936, "global_step": 396134, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.111454725265503, "global_step": 396135, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.068669080734253, "global_step": 396136, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1208503246307373, "global_step": 396137, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0996317863464355, "global_step": 396138, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0810205936431885, "global_step": 396139, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.075845718383789, "global_step": 396140, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.064098834991455, "global_step": 396141, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0938377380371094, "global_step": 396142, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0706136226654053, "global_step": 396143, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.034531831741333, "global_step": 396144, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.030350685119629, "global_step": 396145, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.122448444366455, "global_step": 396146, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1643669605255127, "global_step": 396147, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0778753757476807, "global_step": 396148, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0464162826538086, "global_step": 396149, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0786304473876953, "global_step": 396150, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1287670135498047, "global_step": 396151, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0673835277557373, "global_step": 396152, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1437182426452637, "global_step": 396153, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0844244956970215, "global_step": 396154, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.072093963623047, "global_step": 396155, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.075171709060669, "global_step": 396156, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.095345973968506, "global_step": 396157, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.117283344268799, "global_step": 396158, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.037282943725586, "global_step": 396159, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0856986045837402, "global_step": 396160, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1229541301727295, "global_step": 396161, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1331262588500977, "global_step": 396162, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0860555171966553, "global_step": 396163, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1372148990631104, "global_step": 396164, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.104783296585083, "global_step": 396165, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0709116458892822, "global_step": 396166, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.090574026107788, "global_step": 396167, "epoch": 758, "lr": 5e-05}
{"train_loss": 1.9975581169128418, "global_step": 396168, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1198666095733643, "global_step": 396169, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.103299379348755, "global_step": 396170, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0545718669891357, "global_step": 396171, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.111281156539917, "global_step": 396172, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0658016204833984, "global_step": 396173, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0192935466766357, "global_step": 396174, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1503329277038574, "global_step": 396175, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1073050498962402, "global_step": 396176, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0420665740966797, "global_step": 396177, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0672574043273926, "global_step": 396178, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.089402198791504, "global_step": 396179, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0336334705352783, "global_step": 396180, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.083967924118042, "global_step": 396181, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0648486614227295, "global_step": 396182, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0963029861450195, "global_step": 396183, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.081707715988159, "global_step": 396184, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0816280841827393, "global_step": 396185, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.2032265663146973, "global_step": 396186, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0519580841064453, "global_step": 396187, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.118427276611328, "global_step": 396188, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1506989002227783, "global_step": 396189, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1179022789001465, "global_step": 396190, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.101468324661255, "global_step": 396191, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.110799551010132, "global_step": 396192, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.091531753540039, "global_step": 396193, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1601057052612305, "global_step": 396194, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1441378593444824, "global_step": 396195, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0800974369049072, "global_step": 396196, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0429513454437256, "global_step": 396197, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.011035203933716, "global_step": 396198, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0433428287506104, "global_step": 396199, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1072661876678467, "global_step": 396200, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0959341526031494, "global_step": 396201, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1511385440826416, "global_step": 396202, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0957462787628174, "global_step": 396203, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1135175228118896, "global_step": 396204, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0732197761535645, "global_step": 396205, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.102442741394043, "global_step": 396206, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.033007860183716, "global_step": 396207, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1217520236968994, "global_step": 396208, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1974401473999023, "global_step": 396209, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.036195755004883, "global_step": 396210, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1420693397521973, "global_step": 396211, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.042262077331543, "global_step": 396212, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.063765525817871, "global_step": 396213, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.130180597305298, "global_step": 396214, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0567715167999268, "global_step": 396215, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0544614791870117, "global_step": 396216, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1853232383728027, "global_step": 396217, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0074806213378906, "global_step": 396218, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1524548530578613, "global_step": 396219, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1954867839813232, "global_step": 396220, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1316099166870117, "global_step": 396221, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.087151050567627, "global_step": 396222, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1406922340393066, "global_step": 396223, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1379120349884033, "global_step": 396224, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.091343879699707, "global_step": 396225, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0183517932891846, "global_step": 396226, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.083512544631958, "global_step": 396227, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.090407133102417, "global_step": 396228, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.141695976257324, "global_step": 396229, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.103808879852295, "global_step": 396230, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1103460788726807, "global_step": 396231, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.139631986618042, "global_step": 396232, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1331887245178223, "global_step": 396233, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.140014886856079, "global_step": 396234, "epoch": 758, "lr": 5e-05}
{"train_loss": 1.9989861249923706, "global_step": 396235, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0827176570892334, "global_step": 396236, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.102257251739502, "global_step": 396237, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.140636444091797, "global_step": 396238, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.132805824279785, "global_step": 396239, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.106682062149048, "global_step": 396240, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0732762813568115, "global_step": 396241, "epoch": 758, "lr": 5e-05}
{"train_loss": 1.9898436069488525, "global_step": 396242, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0759267807006836, "global_step": 396243, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.069075584411621, "global_step": 396244, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1615490913391113, "global_step": 396245, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.159538507461548, "global_step": 396246, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1216673851013184, "global_step": 396247, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1326680183410645, "global_step": 396248, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1269848346710205, "global_step": 396249, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0659196376800537, "global_step": 396250, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1485068798065186, "global_step": 396251, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.080296277999878, "global_step": 396252, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0723323822021484, "global_step": 396253, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0619888305664062, "global_step": 396254, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.101912498474121, "global_step": 396255, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.127937078475952, "global_step": 396256, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.114509105682373, "global_step": 396257, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0296730995178223, "global_step": 396258, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1081669330596924, "global_step": 396259, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.121901512145996, "global_step": 396260, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.171748399734497, "global_step": 396261, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0583651065826416, "global_step": 396262, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1278512477874756, "global_step": 396263, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.094426155090332, "global_step": 396264, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.091198205947876, "global_step": 396265, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1103808879852295, "global_step": 396266, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0498602390289307, "global_step": 396267, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.079514980316162, "global_step": 396268, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0654356479644775, "global_step": 396269, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1917030811309814, "global_step": 396270, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0956223011016846, "global_step": 396271, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0776278972625732, "global_step": 396272, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.192986249923706, "global_step": 396273, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.052600622177124, "global_step": 396274, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.141021251678467, "global_step": 396275, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.163717031478882, "global_step": 396276, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.111025810241699, "global_step": 396277, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.113804578781128, "global_step": 396278, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.118110179901123, "global_step": 396279, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.030531644821167, "global_step": 396280, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0778000354766846, "global_step": 396281, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0584707260131836, "global_step": 396282, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.186218738555908, "global_step": 396283, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.043297290802002, "global_step": 396284, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0054643154144287, "global_step": 396285, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0318195819854736, "global_step": 396286, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0804760456085205, "global_step": 396287, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.068812608718872, "global_step": 396288, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.045215606689453, "global_step": 396289, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1654860973358154, "global_step": 396290, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.085723876953125, "global_step": 396291, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0782957077026367, "global_step": 396292, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0929453372955322, "global_step": 396293, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.113604784011841, "global_step": 396294, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.155653476715088, "global_step": 396295, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1376090049743652, "global_step": 396296, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0927534103393555, "global_step": 396297, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1952641010284424, "global_step": 396298, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.060309648513794, "global_step": 396299, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1459171772003174, "global_step": 396300, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.2148914337158203, "global_step": 396301, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.056983232498169, "global_step": 396302, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.121506452560425, "global_step": 396303, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1469290256500244, "global_step": 396304, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.077474594116211, "global_step": 396305, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.094127655029297, "global_step": 396306, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0825369358062744, "global_step": 396307, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.115523099899292, "global_step": 396308, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1682631969451904, "global_step": 396309, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1075987815856934, "global_step": 396310, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1125316619873047, "global_step": 396311, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0962090492248535, "global_step": 396312, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.030531644821167, "global_step": 396313, "epoch": 758, "lr": 5e-05}
{"train_loss": 1.9887070655822754, "global_step": 396314, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1392581462860107, "global_step": 396315, "epoch": 758, "lr": 5e-05}
{"train_loss": 1.9668604135513306, "global_step": 396316, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.145521402359009, "global_step": 396317, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0835378170013428, "global_step": 396318, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.116053819656372, "global_step": 396319, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1841583251953125, "global_step": 396320, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0661725997924805, "global_step": 396321, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1634624004364014, "global_step": 396322, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.091019868850708, "global_step": 396323, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.13419508934021, "global_step": 396324, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.095714569091797, "global_step": 396325, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.05533504486084, "global_step": 396326, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1055562496185303, "global_step": 396327, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0450875759124756, "global_step": 396328, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0654139518737793, "global_step": 396329, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.222569227218628, "global_step": 396330, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.109834671020508, "global_step": 396331, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0756425857543945, "global_step": 396332, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.121241807937622, "global_step": 396333, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.130647659301758, "global_step": 396334, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1219680309295654, "global_step": 396335, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.070610523223877, "global_step": 396336, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1697254180908203, "global_step": 396337, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0986430644989014, "global_step": 396338, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1965830326080322, "global_step": 396339, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1338212490081787, "global_step": 396340, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.134326696395874, "global_step": 396341, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1716115474700928, "global_step": 396342, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.041483163833618, "global_step": 396343, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0766866207122803, "global_step": 396344, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.197246789932251, "global_step": 396345, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.045274257659912, "global_step": 396346, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.053776741027832, "global_step": 396347, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0538270473480225, "global_step": 396348, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.067394495010376, "global_step": 396349, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0916786193847656, "global_step": 396350, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.018287420272827, "global_step": 396351, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.118183135986328, "global_step": 396352, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.124699115753174, "global_step": 396353, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.147840738296509, "global_step": 396354, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.065561294555664, "global_step": 396355, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1195244789123535, "global_step": 396356, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1163299083709717, "global_step": 396357, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.078619956970215, "global_step": 396358, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.062410354614258, "global_step": 396359, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1453959941864014, "global_step": 396360, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0860230922698975, "global_step": 396361, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1324265003204346, "global_step": 396362, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0754170417785645, "global_step": 396363, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0293478965759277, "global_step": 396364, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.097370147705078, "global_step": 396365, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.12882399559021, "global_step": 396366, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.062164545059204, "global_step": 396367, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.156198740005493, "global_step": 396368, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0963103771209717, "global_step": 396369, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.164402961730957, "global_step": 396370, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0750508308410645, "global_step": 396371, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1280996799468994, "global_step": 396372, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1679253578186035, "global_step": 396373, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.116872549057007, "global_step": 396374, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0322601795196533, "global_step": 396375, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.145258903503418, "global_step": 396376, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.017791748046875, "global_step": 396377, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.142162799835205, "global_step": 396378, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.114238739013672, "global_step": 396379, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.150913953781128, "global_step": 396380, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1336846351623535, "global_step": 396381, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0938169956207275, "global_step": 396382, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1239309310913086, "global_step": 396383, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.127220869064331, "global_step": 396384, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0990216732025146, "global_step": 396385, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.161787748336792, "global_step": 396386, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.085826873779297, "global_step": 396387, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1517527103424072, "global_step": 396388, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0037262439727783, "global_step": 396389, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0520081520080566, "global_step": 396390, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.190880298614502, "global_step": 396391, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1281120777130127, "global_step": 396392, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0540289878845215, "global_step": 396393, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1100337505340576, "global_step": 396394, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1982147693634033, "global_step": 396395, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0488851070404053, "global_step": 396396, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1520588397979736, "global_step": 396397, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.190199851989746, "global_step": 396398, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.125535011291504, "global_step": 396399, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.131032705307007, "global_step": 396400, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1863369941711426, "global_step": 396401, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0753157138824463, "global_step": 396402, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.2282681465148926, "global_step": 396403, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1391143798828125, "global_step": 396404, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.192335844039917, "global_step": 396405, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1380505561828613, "global_step": 396406, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1124696731567383, "global_step": 396407, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1179168224334717, "global_step": 396408, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0299556255340576, "global_step": 396409, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.103238344192505, "global_step": 396410, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.070512294769287, "global_step": 396411, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0964303016662598, "global_step": 396412, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.030376434326172, "global_step": 396413, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1301469802856445, "global_step": 396414, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.120499849319458, "global_step": 396415, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0954318046569824, "global_step": 396416, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0778121948242188, "global_step": 396417, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.027231216430664, "global_step": 396418, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0619165897369385, "global_step": 396419, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1784145832061768, "global_step": 396420, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.10150408744812, "global_step": 396421, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1574583053588867, "global_step": 396422, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0934510231018066, "global_step": 396423, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1727676391601562, "global_step": 396424, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.055541515350342, "global_step": 396425, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0530002117156982, "global_step": 396426, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1359598636627197, "global_step": 396427, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.078660726547241, "global_step": 396428, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1224350929260254, "global_step": 396429, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.039276599884033, "global_step": 396430, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0797202587127686, "global_step": 396431, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0081264972686768, "global_step": 396432, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.158724308013916, "global_step": 396433, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1490583419799805, "global_step": 396434, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.08683180809021, "global_step": 396435, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.099578857421875, "global_step": 396436, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.234661102294922, "global_step": 396437, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1224660873413086, "global_step": 396438, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.153627634048462, "global_step": 396439, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.054997205734253, "global_step": 396440, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.12347149848938, "global_step": 396441, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0302374362945557, "global_step": 396442, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.063123941421509, "global_step": 396443, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.100691080093384, "global_step": 396444, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.164834976196289, "global_step": 396445, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.142418146133423, "global_step": 396446, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.069756269454956, "global_step": 396447, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0757367610931396, "global_step": 396448, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.048685312271118, "global_step": 396449, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1010138988494873, "global_step": 396450, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0603880882263184, "global_step": 396451, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.060347557067871, "global_step": 396452, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.0981152057647705, "global_step": 396453, "epoch": 758, "lr": 5e-05}
{"train_loss": 2.1141750812530518, "global_step": 396454, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1667888164520264, "global_step": 396455, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0959877967834473, "global_step": 396456, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0434467792510986, "global_step": 396457, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.062324285507202, "global_step": 396458, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.105797052383423, "global_step": 396459, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1035385131835938, "global_step": 396460, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0700838565826416, "global_step": 396461, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1265792846679688, "global_step": 396462, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.054940700531006, "global_step": 396463, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.068410634994507, "global_step": 396464, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1257550716400146, "global_step": 396465, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.175710439682007, "global_step": 396466, "epoch": 759, "lr": 5e-05}
{"train_loss": 1.989877462387085, "global_step": 396467, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0879178047180176, "global_step": 396468, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1146280765533447, "global_step": 396469, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.086697816848755, "global_step": 396470, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1319525241851807, "global_step": 396471, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.068699598312378, "global_step": 396472, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0705738067626953, "global_step": 396473, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.098573684692383, "global_step": 396474, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0258164405822754, "global_step": 396475, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0578789710998535, "global_step": 396476, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.092705011367798, "global_step": 396477, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1255617141723633, "global_step": 396478, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0358335971832275, "global_step": 396479, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0352656841278076, "global_step": 396480, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.086054801940918, "global_step": 396481, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.073326826095581, "global_step": 396482, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0401971340179443, "global_step": 396483, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1307246685028076, "global_step": 396484, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1276214122772217, "global_step": 396485, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1128647327423096, "global_step": 396486, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.010683536529541, "global_step": 396487, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.027204990386963, "global_step": 396488, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.068756580352783, "global_step": 396489, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1497132778167725, "global_step": 396490, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0485682487487793, "global_step": 396491, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.072889804840088, "global_step": 396492, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0047566890716553, "global_step": 396493, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.042762041091919, "global_step": 396494, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0391900539398193, "global_step": 396495, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0844006538391113, "global_step": 396496, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1168477535247803, "global_step": 396497, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1518003940582275, "global_step": 396498, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1505212783813477, "global_step": 396499, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0225558280944824, "global_step": 396500, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1321887969970703, "global_step": 396501, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1486263275146484, "global_step": 396502, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0652387142181396, "global_step": 396503, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1000373363494873, "global_step": 396504, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.062601327896118, "global_step": 396505, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.071363925933838, "global_step": 396506, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1380672454833984, "global_step": 396507, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1106255054473877, "global_step": 396508, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.08853816986084, "global_step": 396509, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1216259002685547, "global_step": 396510, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0869555473327637, "global_step": 396511, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.060492753982544, "global_step": 396512, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.123718738555908, "global_step": 396513, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.082094669342041, "global_step": 396514, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0897889137268066, "global_step": 396515, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.143439769744873, "global_step": 396516, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.142798662185669, "global_step": 396517, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.107412338256836, "global_step": 396518, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1123220920562744, "global_step": 396519, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.151163101196289, "global_step": 396520, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1530280113220215, "global_step": 396521, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1880617141723633, "global_step": 396522, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.203066825866699, "global_step": 396523, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.162961721420288, "global_step": 396524, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.121129035949707, "global_step": 396525, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.134899616241455, "global_step": 396526, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0436501502990723, "global_step": 396527, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1171417236328125, "global_step": 396528, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0431394577026367, "global_step": 396529, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1209707260131836, "global_step": 396530, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0524802207946777, "global_step": 396531, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1586484909057617, "global_step": 396532, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.006807327270508, "global_step": 396533, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.088747024536133, "global_step": 396534, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.095107316970825, "global_step": 396535, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1262526512145996, "global_step": 396536, "epoch": 759, "lr": 5e-05}
{"train_loss": 1.97719144821167, "global_step": 396537, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.048208475112915, "global_step": 396538, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0932507514953613, "global_step": 396539, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.006286144256592, "global_step": 396540, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0999295711517334, "global_step": 396541, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.076796293258667, "global_step": 396542, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0700738430023193, "global_step": 396543, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1809158325195312, "global_step": 396544, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.098879814147949, "global_step": 396545, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.179307699203491, "global_step": 396546, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.052313804626465, "global_step": 396547, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0563907623291016, "global_step": 396548, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.053584337234497, "global_step": 396549, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1083784103393555, "global_step": 396550, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.101186513900757, "global_step": 396551, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0618255138397217, "global_step": 396552, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1110002994537354, "global_step": 396553, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1151256561279297, "global_step": 396554, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.165940523147583, "global_step": 396555, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0814809799194336, "global_step": 396556, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1338634490966797, "global_step": 396557, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0841903686523438, "global_step": 396558, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.15289306640625, "global_step": 396559, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.12776517868042, "global_step": 396560, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0232627391815186, "global_step": 396561, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0134096145629883, "global_step": 396562, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.101975202560425, "global_step": 396563, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0135059356689453, "global_step": 396564, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.023329496383667, "global_step": 396565, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0009987354278564, "global_step": 396566, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0873374938964844, "global_step": 396567, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0783486366271973, "global_step": 396568, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0928454399108887, "global_step": 396569, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0902516841888428, "global_step": 396570, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.105567216873169, "global_step": 396571, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0671277046203613, "global_step": 396572, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.091179132461548, "global_step": 396573, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.095022201538086, "global_step": 396574, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1148388385772705, "global_step": 396575, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1173043251037598, "global_step": 396576, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0544073581695557, "global_step": 396577, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1242761611938477, "global_step": 396578, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0768377780914307, "global_step": 396579, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.136704206466675, "global_step": 396580, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1081647872924805, "global_step": 396581, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.062797784805298, "global_step": 396582, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0208892822265625, "global_step": 396583, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.018625020980835, "global_step": 396584, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1258604526519775, "global_step": 396585, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.164687395095825, "global_step": 396586, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.190640449523926, "global_step": 396587, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.041564464569092, "global_step": 396588, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1442298889160156, "global_step": 396589, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1489298343658447, "global_step": 396590, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.090109348297119, "global_step": 396591, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1671929359436035, "global_step": 396592, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1834771633148193, "global_step": 396593, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.101114511489868, "global_step": 396594, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0357208251953125, "global_step": 396595, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.061464786529541, "global_step": 396596, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.012418746948242, "global_step": 396597, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.128990650177002, "global_step": 396598, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.02982497215271, "global_step": 396599, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1166958808898926, "global_step": 396600, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1181676387786865, "global_step": 396601, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.08927583694458, "global_step": 396602, "epoch": 759, "lr": 5e-05}
{"train_loss": 1.9976418018341064, "global_step": 396603, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.113152265548706, "global_step": 396604, "epoch": 759, "lr": 5e-05}
{"train_loss": 1.9891891479492188, "global_step": 396605, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1512255668640137, "global_step": 396606, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1308932304382324, "global_step": 396607, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.073432207107544, "global_step": 396608, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0317602157592773, "global_step": 396609, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.18266224861145, "global_step": 396610, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0826058387756348, "global_step": 396611, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.047931432723999, "global_step": 396612, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0900328159332275, "global_step": 396613, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0539495944976807, "global_step": 396614, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.100839614868164, "global_step": 396615, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.063220977783203, "global_step": 396616, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.080841541290283, "global_step": 396617, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.226552724838257, "global_step": 396618, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.09970760345459, "global_step": 396619, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0644547939300537, "global_step": 396620, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1030642986297607, "global_step": 396621, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0260307788848877, "global_step": 396622, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0758631229400635, "global_step": 396623, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0696961879730225, "global_step": 396624, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0539138317108154, "global_step": 396625, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0374863147735596, "global_step": 396626, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.080223321914673, "global_step": 396627, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.07684326171875, "global_step": 396628, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.024970531463623, "global_step": 396629, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1633362770080566, "global_step": 396630, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.055830717086792, "global_step": 396631, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1688601970672607, "global_step": 396632, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.034097909927368, "global_step": 396633, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0984530448913574, "global_step": 396634, "epoch": 759, "lr": 5e-05}
{"train_loss": 1.957811713218689, "global_step": 396635, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.048053741455078, "global_step": 396636, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.13796329498291, "global_step": 396637, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.086690902709961, "global_step": 396638, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.048035144805908, "global_step": 396639, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0441946983337402, "global_step": 396640, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.141146421432495, "global_step": 396641, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.097498893737793, "global_step": 396642, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0644547939300537, "global_step": 396643, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1314971446990967, "global_step": 396644, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.188986301422119, "global_step": 396645, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.074705123901367, "global_step": 396646, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1150763034820557, "global_step": 396647, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0871779918670654, "global_step": 396648, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0802977085113525, "global_step": 396649, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0752766132354736, "global_step": 396650, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.036088705062866, "global_step": 396651, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1426310539245605, "global_step": 396652, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1681792736053467, "global_step": 396653, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.144639253616333, "global_step": 396654, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0714919567108154, "global_step": 396655, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.019836187362671, "global_step": 396656, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0974724292755127, "global_step": 396657, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.114849805831909, "global_step": 396658, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1009790897369385, "global_step": 396659, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0849733352661133, "global_step": 396660, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.123047351837158, "global_step": 396661, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0371994972229004, "global_step": 396662, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.145669937133789, "global_step": 396663, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.021916389465332, "global_step": 396664, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1160669326782227, "global_step": 396665, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0867762565612793, "global_step": 396666, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1005570888519287, "global_step": 396667, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.092280387878418, "global_step": 396668, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0690135955810547, "global_step": 396669, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0676114559173584, "global_step": 396670, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0539987087249756, "global_step": 396671, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1018593311309814, "global_step": 396672, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.093290090560913, "global_step": 396673, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0428991317749023, "global_step": 396674, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1465399265289307, "global_step": 396675, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1380038261413574, "global_step": 396676, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.114351987838745, "global_step": 396677, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1035261154174805, "global_step": 396678, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.05159330368042, "global_step": 396679, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.10200572013855, "global_step": 396680, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1180038452148438, "global_step": 396681, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0304031372070312, "global_step": 396682, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.126885414123535, "global_step": 396683, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.055697202682495, "global_step": 396684, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.106137275695801, "global_step": 396685, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0708327293395996, "global_step": 396686, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0940353870391846, "global_step": 396687, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0618374347686768, "global_step": 396688, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.133180856704712, "global_step": 396689, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0952248573303223, "global_step": 396690, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.126673698425293, "global_step": 396691, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.139824867248535, "global_step": 396692, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0816564559936523, "global_step": 396693, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1238577365875244, "global_step": 396694, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.131671667098999, "global_step": 396695, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1404240131378174, "global_step": 396696, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1050853729248047, "global_step": 396697, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.160722017288208, "global_step": 396698, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.173069477081299, "global_step": 396699, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1048519611358643, "global_step": 396700, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.080691337585449, "global_step": 396701, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.062634229660034, "global_step": 396702, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0018460750579834, "global_step": 396703, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.07804012298584, "global_step": 396704, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.156700372695923, "global_step": 396705, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.154426097869873, "global_step": 396706, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.104008436203003, "global_step": 396707, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1019232273101807, "global_step": 396708, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.071439027786255, "global_step": 396709, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.095656156539917, "global_step": 396710, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0750536918640137, "global_step": 396711, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0514628887176514, "global_step": 396712, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.044691562652588, "global_step": 396713, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.119919538497925, "global_step": 396714, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1050784587860107, "global_step": 396715, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0965640544891357, "global_step": 396716, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.090635061264038, "global_step": 396717, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1625757217407227, "global_step": 396718, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1407103538513184, "global_step": 396719, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.000816583633423, "global_step": 396720, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.058952808380127, "global_step": 396721, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.145113706588745, "global_step": 396722, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0606393814086914, "global_step": 396723, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1729373931884766, "global_step": 396724, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0876896381378174, "global_step": 396725, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1238746643066406, "global_step": 396726, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0957374572753906, "global_step": 396727, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.087521553039551, "global_step": 396728, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0857841968536377, "global_step": 396729, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.136693000793457, "global_step": 396730, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0735721588134766, "global_step": 396731, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0572097301483154, "global_step": 396732, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.121426820755005, "global_step": 396733, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1804425716400146, "global_step": 396734, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.150722026824951, "global_step": 396735, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1074459552764893, "global_step": 396736, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1186342239379883, "global_step": 396737, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.134371280670166, "global_step": 396738, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0491700172424316, "global_step": 396739, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.025179147720337, "global_step": 396740, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0660037994384766, "global_step": 396741, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0250284671783447, "global_step": 396742, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.131664276123047, "global_step": 396743, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1413216590881348, "global_step": 396744, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0902931690216064, "global_step": 396745, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.080728769302368, "global_step": 396746, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.113481283187866, "global_step": 396747, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0465803146362305, "global_step": 396748, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1435046195983887, "global_step": 396749, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0370826721191406, "global_step": 396750, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1314423084259033, "global_step": 396751, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1349425315856934, "global_step": 396752, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0718650817871094, "global_step": 396753, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0338995456695557, "global_step": 396754, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.115506649017334, "global_step": 396755, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.026108980178833, "global_step": 396756, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.086418867111206, "global_step": 396757, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1194608211517334, "global_step": 396758, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.228046417236328, "global_step": 396759, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.098773717880249, "global_step": 396760, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.096869707107544, "global_step": 396761, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1082091331481934, "global_step": 396762, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.04170560836792, "global_step": 396763, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1123738288879395, "global_step": 396764, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1434249877929688, "global_step": 396765, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.2020480632781982, "global_step": 396766, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1122448444366455, "global_step": 396767, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0295326709747314, "global_step": 396768, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0626862049102783, "global_step": 396769, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1486175060272217, "global_step": 396770, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.041914224624634, "global_step": 396771, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.055250644683838, "global_step": 396772, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0896761417388916, "global_step": 396773, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.17221736907959, "global_step": 396774, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0666565895080566, "global_step": 396775, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0511372089385986, "global_step": 396776, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.144425392150879, "global_step": 396777, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0764355659484863, "global_step": 396778, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0305237770080566, "global_step": 396779, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0776655673980713, "global_step": 396780, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1174378395080566, "global_step": 396781, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0886850357055664, "global_step": 396782, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.083059787750244, "global_step": 396783, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.010075569152832, "global_step": 396784, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1850357055664062, "global_step": 396785, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.076073169708252, "global_step": 396786, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0932886600494385, "global_step": 396787, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0355234146118164, "global_step": 396788, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.156817674636841, "global_step": 396789, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.023632764816284, "global_step": 396790, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.100872278213501, "global_step": 396791, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.176006317138672, "global_step": 396792, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.04791522026062, "global_step": 396793, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1160318851470947, "global_step": 396794, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0269227027893066, "global_step": 396795, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.030038356781006, "global_step": 396796, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.037701368331909, "global_step": 396797, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.077623128890991, "global_step": 396798, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.2065930366516113, "global_step": 396799, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1316893100738525, "global_step": 396800, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1418190002441406, "global_step": 396801, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.10536789894104, "global_step": 396802, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.145256996154785, "global_step": 396803, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0385382175445557, "global_step": 396804, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1026771068573, "global_step": 396805, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0466508865356445, "global_step": 396806, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1429266929626465, "global_step": 396807, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0987322330474854, "global_step": 396808, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0960588455200195, "global_step": 396809, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.163461208343506, "global_step": 396810, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.029920816421509, "global_step": 396811, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.098581552505493, "global_step": 396812, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0693747997283936, "global_step": 396813, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0642361640930176, "global_step": 396814, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0995945930480957, "global_step": 396815, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.111715793609619, "global_step": 396816, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.07401180267334, "global_step": 396817, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1181392669677734, "global_step": 396818, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.098820209503174, "global_step": 396819, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0432262420654297, "global_step": 396820, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1018850803375244, "global_step": 396821, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1067087650299072, "global_step": 396822, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.050529956817627, "global_step": 396823, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1219325065612793, "global_step": 396824, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.097017288208008, "global_step": 396825, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1320643424987793, "global_step": 396826, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1074469089508057, "global_step": 396827, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1055381298065186, "global_step": 396828, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0751776695251465, "global_step": 396829, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0921614170074463, "global_step": 396830, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.057342290878296, "global_step": 396831, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.104707717895508, "global_step": 396832, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0918447971343994, "global_step": 396833, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1244959831237793, "global_step": 396834, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1032915115356445, "global_step": 396835, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.120694875717163, "global_step": 396836, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1132373809814453, "global_step": 396837, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.03031587600708, "global_step": 396838, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.06518292427063, "global_step": 396839, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0720465183258057, "global_step": 396840, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.111025094985962, "global_step": 396841, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1079816818237305, "global_step": 396842, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.036236047744751, "global_step": 396843, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.044247627258301, "global_step": 396844, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.104679822921753, "global_step": 396845, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1260509490966797, "global_step": 396846, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1714835166931152, "global_step": 396847, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1719043254852295, "global_step": 396848, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.14510178565979, "global_step": 396849, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0559802055358887, "global_step": 396850, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.111021041870117, "global_step": 396851, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0501623153686523, "global_step": 396852, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1523725986480713, "global_step": 396853, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.086404323577881, "global_step": 396854, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0746848583221436, "global_step": 396855, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.177072286605835, "global_step": 396856, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.032979965209961, "global_step": 396857, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.122427225112915, "global_step": 396858, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.089280128479004, "global_step": 396859, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1810660362243652, "global_step": 396860, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1368048191070557, "global_step": 396861, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1074109077453613, "global_step": 396862, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.131830930709839, "global_step": 396863, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1138129234313965, "global_step": 396864, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.11423659324646, "global_step": 396865, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.114027261734009, "global_step": 396866, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.164752721786499, "global_step": 396867, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.107043981552124, "global_step": 396868, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.2163949012756348, "global_step": 396869, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1171064376831055, "global_step": 396870, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1423933506011963, "global_step": 396871, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.11691951751709, "global_step": 396872, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1099326610565186, "global_step": 396873, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0236096382141113, "global_step": 396874, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.123588800430298, "global_step": 396875, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.093871831893921, "global_step": 396876, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.05135440826416, "global_step": 396877, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0003204345703125, "global_step": 396878, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.10211181640625, "global_step": 396879, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.037907838821411, "global_step": 396880, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1176013946533203, "global_step": 396881, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1107897758483887, "global_step": 396882, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1133060455322266, "global_step": 396883, "epoch": 759, "lr": 5e-05}
{"train_loss": 1.964671015739441, "global_step": 396884, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1575703620910645, "global_step": 396885, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1062939167022705, "global_step": 396886, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.087279796600342, "global_step": 396887, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.123453378677368, "global_step": 396888, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0287749767303467, "global_step": 396889, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1501100063323975, "global_step": 396890, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0376088619232178, "global_step": 396891, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.086874008178711, "global_step": 396892, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.10630202293396, "global_step": 396893, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1366631984710693, "global_step": 396894, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0914623737335205, "global_step": 396895, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0923948287963867, "global_step": 396896, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.065079927444458, "global_step": 396897, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.2112722396850586, "global_step": 396898, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.035936117172241, "global_step": 396899, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.174562931060791, "global_step": 396900, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1117444038391113, "global_step": 396901, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1564531326293945, "global_step": 396902, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.089153528213501, "global_step": 396903, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0414023399353027, "global_step": 396904, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1189985275268555, "global_step": 396905, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.119122266769409, "global_step": 396906, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0355491638183594, "global_step": 396907, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.138127326965332, "global_step": 396908, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1249125003814697, "global_step": 396909, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1137161254882812, "global_step": 396910, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0496015548706055, "global_step": 396911, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.130293846130371, "global_step": 396912, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0759754180908203, "global_step": 396913, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.070082664489746, "global_step": 396914, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1256163120269775, "global_step": 396915, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.185966730117798, "global_step": 396916, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1286826133728027, "global_step": 396917, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.066135883331299, "global_step": 396918, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1090760231018066, "global_step": 396919, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1924591064453125, "global_step": 396920, "epoch": 759, "lr": 5e-05}
{"train_loss": 1.9962190389633179, "global_step": 396921, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1774048805236816, "global_step": 396922, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.039341449737549, "global_step": 396923, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.148050546646118, "global_step": 396924, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1178393363952637, "global_step": 396925, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1439502239227295, "global_step": 396926, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1628544330596924, "global_step": 396927, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.115750312805176, "global_step": 396928, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1318302154541016, "global_step": 396929, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1536693572998047, "global_step": 396930, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.095130205154419, "global_step": 396931, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0536961555480957, "global_step": 396932, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.232886552810669, "global_step": 396933, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.043041944503784, "global_step": 396934, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0841360092163086, "global_step": 396935, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.089953660964966, "global_step": 396936, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.084733247756958, "global_step": 396937, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1616897583007812, "global_step": 396938, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1480653285980225, "global_step": 396939, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0304458141326904, "global_step": 396940, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.10036301612854, "global_step": 396941, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0689010620117188, "global_step": 396942, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.072253704071045, "global_step": 396943, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1280696392059326, "global_step": 396944, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0459485054016113, "global_step": 396945, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1148316860198975, "global_step": 396946, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.065958023071289, "global_step": 396947, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.072815418243408, "global_step": 396948, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1703524589538574, "global_step": 396949, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.135392189025879, "global_step": 396950, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.084080457687378, "global_step": 396951, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0716700553894043, "global_step": 396952, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1353085041046143, "global_step": 396953, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1530911922454834, "global_step": 396954, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.191391944885254, "global_step": 396955, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0925369262695312, "global_step": 396956, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.01912522315979, "global_step": 396957, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.155242443084717, "global_step": 396958, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.095623731613159, "global_step": 396959, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1556994915008545, "global_step": 396960, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.073857545852661, "global_step": 396961, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.071979522705078, "global_step": 396962, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0927021503448486, "global_step": 396963, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1085073947906494, "global_step": 396964, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0293540954589844, "global_step": 396965, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.090452194213867, "global_step": 396966, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.076432704925537, "global_step": 396967, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.014343023300171, "global_step": 396968, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1240010261535645, "global_step": 396969, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.194786787033081, "global_step": 396970, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1006362438201904, "global_step": 396971, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1970231533050537, "global_step": 396972, "epoch": 759, "lr": 5e-05}
{"train_loss": 1.9822144508361816, "global_step": 396973, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0711216926574707, "global_step": 396974, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0396361351013184, "global_step": 396975, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.106112003326416, "global_step": 396976, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0898420810699463, "global_step": 396977, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0248982906341553, "global_step": 396978, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1369757652282715, "global_step": 396979, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1202659606933594, "global_step": 396980, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0139098167419434, "global_step": 396981, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0708279609680176, "global_step": 396982, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.069390296936035, "global_step": 396983, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0883045196533203, "global_step": 396984, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.143153190612793, "global_step": 396985, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0466485023498535, "global_step": 396986, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.186201810836792, "global_step": 396987, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.106250762939453, "global_step": 396988, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0717475414276123, "global_step": 396989, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.093813896179199, "global_step": 396990, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0978713035583496, "global_step": 396991, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.013923168182373, "global_step": 396992, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1406941413879395, "global_step": 396993, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.00761079788208, "global_step": 396994, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.044407844543457, "global_step": 396995, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1184041500091553, "global_step": 396996, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.083491086959839, "global_step": 396997, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1067826747894287, "global_step": 396998, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1179070472717285, "global_step": 396999, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.053487777709961, "global_step": 397000, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0911943912506104, "global_step": 397001, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0235249996185303, "global_step": 397002, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1192026138305664, "global_step": 397003, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0861713886260986, "global_step": 397004, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.15986704826355, "global_step": 397005, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.185020923614502, "global_step": 397006, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0382862091064453, "global_step": 397007, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0756397247314453, "global_step": 397008, "epoch": 759, "lr": 5e-05}
{"train_loss": 1.9839611053466797, "global_step": 397009, "epoch": 759, "lr": 5e-05}
{"train_loss": 1.9941954612731934, "global_step": 397010, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1345839500427246, "global_step": 397011, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.009586811065674, "global_step": 397012, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0426623821258545, "global_step": 397013, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.111332893371582, "global_step": 397014, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0644609928131104, "global_step": 397015, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1302924156188965, "global_step": 397016, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0801873207092285, "global_step": 397017, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0932023525238037, "global_step": 397018, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.109280824661255, "global_step": 397019, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1845815181732178, "global_step": 397020, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.2156360149383545, "global_step": 397021, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1544556617736816, "global_step": 397022, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1504385471343994, "global_step": 397023, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1650099754333496, "global_step": 397024, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.076817274093628, "global_step": 397025, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1788599491119385, "global_step": 397026, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.2158966064453125, "global_step": 397027, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.146944761276245, "global_step": 397028, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.090423583984375, "global_step": 397029, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.017439842224121, "global_step": 397030, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1878294944763184, "global_step": 397031, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.100872755050659, "global_step": 397032, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0671844482421875, "global_step": 397033, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.084951162338257, "global_step": 397034, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1006228923797607, "global_step": 397035, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1147077083587646, "global_step": 397036, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.129767894744873, "global_step": 397037, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0950589179992676, "global_step": 397038, "epoch": 759, "lr": 5e-05}
{"train_loss": 1.9959381818771362, "global_step": 397039, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.2771894931793213, "global_step": 397040, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0685055255889893, "global_step": 397041, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0290403366088867, "global_step": 397042, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.299131393432617, "global_step": 397043, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1414175033569336, "global_step": 397044, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.064284563064575, "global_step": 397045, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0933337211608887, "global_step": 397046, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.093916177749634, "global_step": 397047, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.076277017593384, "global_step": 397048, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0777251720428467, "global_step": 397049, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0561864376068115, "global_step": 397050, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.106038808822632, "global_step": 397051, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0725247859954834, "global_step": 397052, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1032028198242188, "global_step": 397053, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1676881313323975, "global_step": 397054, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0591583251953125, "global_step": 397055, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.037156581878662, "global_step": 397056, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.099313974380493, "global_step": 397057, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0970518589019775, "global_step": 397058, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0297999382019043, "global_step": 397059, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.003533363342285, "global_step": 397060, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.085314989089966, "global_step": 397061, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0749154090881348, "global_step": 397062, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.105940580368042, "global_step": 397063, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1549384593963623, "global_step": 397064, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1536786556243896, "global_step": 397065, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.115403413772583, "global_step": 397066, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1029279232025146, "global_step": 397067, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.18166184425354, "global_step": 397068, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0066981315612793, "global_step": 397069, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0784413814544678, "global_step": 397070, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1393165588378906, "global_step": 397071, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.111908197402954, "global_step": 397072, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1524760723114014, "global_step": 397073, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0662102699279785, "global_step": 397074, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.160139322280884, "global_step": 397075, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.095613479614258, "global_step": 397076, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0752415657043457, "global_step": 397077, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.048283100128174, "global_step": 397078, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.089895486831665, "global_step": 397079, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0908641815185547, "global_step": 397080, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.14058256149292, "global_step": 397081, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.080132007598877, "global_step": 397082, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0333433151245117, "global_step": 397083, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0078165531158447, "global_step": 397084, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1777470111846924, "global_step": 397085, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.098177194595337, "global_step": 397086, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.153632164001465, "global_step": 397087, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0292062759399414, "global_step": 397088, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.071898937225342, "global_step": 397089, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1189792156219482, "global_step": 397090, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0748069286346436, "global_step": 397091, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1551320552825928, "global_step": 397092, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.054965019226074, "global_step": 397093, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1291346549987793, "global_step": 397094, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.200572967529297, "global_step": 397095, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.112978458404541, "global_step": 397096, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.2043614387512207, "global_step": 397097, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1328558921813965, "global_step": 397098, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0765371322631836, "global_step": 397099, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.071653366088867, "global_step": 397100, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1263232231140137, "global_step": 397101, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.123521089553833, "global_step": 397102, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1364858150482178, "global_step": 397103, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.067650079727173, "global_step": 397104, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.113762140274048, "global_step": 397105, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0611493587493896, "global_step": 397106, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1823487281799316, "global_step": 397107, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.137924909591675, "global_step": 397108, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.035477638244629, "global_step": 397109, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.144183397293091, "global_step": 397110, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.092270851135254, "global_step": 397111, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.133044719696045, "global_step": 397112, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1136586666107178, "global_step": 397113, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.084684371948242, "global_step": 397114, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0326735973358154, "global_step": 397115, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1537036895751953, "global_step": 397116, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0546205043792725, "global_step": 397117, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.12011456489563, "global_step": 397118, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.100630283355713, "global_step": 397119, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0373806953430176, "global_step": 397120, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0767762660980225, "global_step": 397121, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1023449897766113, "global_step": 397122, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.189603090286255, "global_step": 397123, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1600587368011475, "global_step": 397124, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0960934162139893, "global_step": 397125, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0109341144561768, "global_step": 397126, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.128476619720459, "global_step": 397127, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.115840435028076, "global_step": 397128, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.116205930709839, "global_step": 397129, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0944833755493164, "global_step": 397130, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0984010696411133, "global_step": 397131, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0751137733459473, "global_step": 397132, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0566232204437256, "global_step": 397133, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.158930540084839, "global_step": 397134, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.095886468887329, "global_step": 397135, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.094635248184204, "global_step": 397136, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.062363624572754, "global_step": 397137, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1818346977233887, "global_step": 397138, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.161639928817749, "global_step": 397139, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.10290789604187, "global_step": 397140, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.111543655395508, "global_step": 397141, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.136873483657837, "global_step": 397142, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.126551628112793, "global_step": 397143, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.192171573638916, "global_step": 397144, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.15968918800354, "global_step": 397145, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.113194227218628, "global_step": 397146, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1255762577056885, "global_step": 397147, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.158045530319214, "global_step": 397148, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0753962993621826, "global_step": 397149, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.007460117340088, "global_step": 397150, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0411577224731445, "global_step": 397151, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.143419027328491, "global_step": 397152, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0540366172790527, "global_step": 397153, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.120795726776123, "global_step": 397154, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.144131660461426, "global_step": 397155, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.074349880218506, "global_step": 397156, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.085970878601074, "global_step": 397157, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0681684017181396, "global_step": 397158, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0662052631378174, "global_step": 397159, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0698082447052, "global_step": 397160, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0723912715911865, "global_step": 397161, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.179764747619629, "global_step": 397162, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.108342170715332, "global_step": 397163, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1208696365356445, "global_step": 397164, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.001444101333618, "global_step": 397165, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1837382316589355, "global_step": 397166, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1771798133850098, "global_step": 397167, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0622951984405518, "global_step": 397168, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0809576511383057, "global_step": 397169, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1607470512390137, "global_step": 397170, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1332573890686035, "global_step": 397171, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.021524667739868, "global_step": 397172, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1751692295074463, "global_step": 397173, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.076716899871826, "global_step": 397174, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.188641309738159, "global_step": 397175, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.164501905441284, "global_step": 397176, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.118223190307617, "global_step": 397177, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.2086024284362793, "global_step": 397178, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0390572547912598, "global_step": 397179, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.065183401107788, "global_step": 397180, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.048898935317993, "global_step": 397181, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.077594518661499, "global_step": 397182, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.049314260482788, "global_step": 397183, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.096994161605835, "global_step": 397184, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1791183948516846, "global_step": 397185, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.143892765045166, "global_step": 397186, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.053391933441162, "global_step": 397187, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0459976196289062, "global_step": 397188, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0866363048553467, "global_step": 397189, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0596487522125244, "global_step": 397190, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0008745193481445, "global_step": 397191, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0966219902038574, "global_step": 397192, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.081336498260498, "global_step": 397193, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.048405408859253, "global_step": 397194, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0802314281463623, "global_step": 397195, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0289247035980225, "global_step": 397196, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0788729190826416, "global_step": 397197, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.100569009780884, "global_step": 397198, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.077993869781494, "global_step": 397199, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0929410457611084, "global_step": 397200, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1463396549224854, "global_step": 397201, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0945630073547363, "global_step": 397202, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0938973426818848, "global_step": 397203, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1340298652648926, "global_step": 397204, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1006863117218018, "global_step": 397205, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.155975341796875, "global_step": 397206, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0608811378479004, "global_step": 397207, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.088974714279175, "global_step": 397208, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0996897220611572, "global_step": 397209, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1264898777008057, "global_step": 397210, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0006747245788574, "global_step": 397211, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.114041805267334, "global_step": 397212, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0369651317596436, "global_step": 397213, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.103761911392212, "global_step": 397214, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0935351848602295, "global_step": 397215, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1313729286193848, "global_step": 397216, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1221108436584473, "global_step": 397217, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1186306476593018, "global_step": 397218, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.098963499069214, "global_step": 397219, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1150996685028076, "global_step": 397220, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0633604526519775, "global_step": 397221, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1320695877075195, "global_step": 397222, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1229074001312256, "global_step": 397223, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.134282350540161, "global_step": 397224, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.077286958694458, "global_step": 397225, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0704219341278076, "global_step": 397226, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0293993949890137, "global_step": 397227, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0739712715148926, "global_step": 397228, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.103724956512451, "global_step": 397229, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.116344928741455, "global_step": 397230, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0788681507110596, "global_step": 397231, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1050162315368652, "global_step": 397232, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1117429733276367, "global_step": 397233, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1133651733398438, "global_step": 397234, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0985918045043945, "global_step": 397235, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1791961193084717, "global_step": 397236, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.095106601715088, "global_step": 397237, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1391217708587646, "global_step": 397238, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.023196220397949, "global_step": 397239, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0939247608184814, "global_step": 397240, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0818607807159424, "global_step": 397241, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0475664138793945, "global_step": 397242, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1311213970184326, "global_step": 397243, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.096520185470581, "global_step": 397244, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.080331802368164, "global_step": 397245, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0529119968414307, "global_step": 397246, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.200880289077759, "global_step": 397247, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0684542655944824, "global_step": 397248, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.055776596069336, "global_step": 397249, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1317496299743652, "global_step": 397250, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.041884183883667, "global_step": 397251, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1536688804626465, "global_step": 397252, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0761358737945557, "global_step": 397253, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1344127655029297, "global_step": 397254, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1019842624664307, "global_step": 397255, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1223838329315186, "global_step": 397256, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0765469074249268, "global_step": 397257, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.083414077758789, "global_step": 397258, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.117157220840454, "global_step": 397259, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.165475368499756, "global_step": 397260, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1125524044036865, "global_step": 397261, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0857558250427246, "global_step": 397262, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.077146530151367, "global_step": 397263, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0558011531829834, "global_step": 397264, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.048673629760742, "global_step": 397265, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.114474296569824, "global_step": 397266, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1109907627105713, "global_step": 397267, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.222529411315918, "global_step": 397268, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.080674648284912, "global_step": 397269, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1253702640533447, "global_step": 397270, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.091402053833008, "global_step": 397271, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1018428802490234, "global_step": 397272, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0967907905578613, "global_step": 397273, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1265676021575928, "global_step": 397274, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.19309401512146, "global_step": 397275, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1506507396698, "global_step": 397276, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.142794132232666, "global_step": 397277, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.113288164138794, "global_step": 397278, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.084423065185547, "global_step": 397279, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.167975425720215, "global_step": 397280, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.185234785079956, "global_step": 397281, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0207862854003906, "global_step": 397282, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.111501455307007, "global_step": 397283, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.072746992111206, "global_step": 397284, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1276638507843018, "global_step": 397285, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1183369159698486, "global_step": 397286, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0746946334838867, "global_step": 397287, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.168363332748413, "global_step": 397288, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.044435977935791, "global_step": 397289, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0473244190216064, "global_step": 397290, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.172229528427124, "global_step": 397291, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.202308416366577, "global_step": 397292, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.140925168991089, "global_step": 397293, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1803669929504395, "global_step": 397294, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.076892614364624, "global_step": 397295, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.048630714416504, "global_step": 397296, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0934059619903564, "global_step": 397297, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0581412315368652, "global_step": 397298, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1161396503448486, "global_step": 397299, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.195901393890381, "global_step": 397300, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.040599822998047, "global_step": 397301, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0467913150787354, "global_step": 397302, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.051952838897705, "global_step": 397303, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.142636299133301, "global_step": 397304, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.102785348892212, "global_step": 397305, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.042707681655884, "global_step": 397306, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1470160484313965, "global_step": 397307, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0499684810638428, "global_step": 397308, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1631321907043457, "global_step": 397309, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0420193672180176, "global_step": 397310, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1629152297973633, "global_step": 397311, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1198437213897705, "global_step": 397312, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1437058448791504, "global_step": 397313, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0407052040100098, "global_step": 397314, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.085651397705078, "global_step": 397315, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1051909923553467, "global_step": 397316, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.109588623046875, "global_step": 397317, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.2035763263702393, "global_step": 397318, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0934319496154785, "global_step": 397319, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0838818550109863, "global_step": 397320, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.103940963745117, "global_step": 397321, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1684184074401855, "global_step": 397322, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0435900688171387, "global_step": 397323, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0397133827209473, "global_step": 397324, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1064059734344482, "global_step": 397325, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0821533203125, "global_step": 397326, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0276691913604736, "global_step": 397327, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.176978588104248, "global_step": 397328, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0605931282043457, "global_step": 397329, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1239118576049805, "global_step": 397330, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1794803142547607, "global_step": 397331, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.148249864578247, "global_step": 397332, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1201212406158447, "global_step": 397333, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.142561197280884, "global_step": 397334, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.119675397872925, "global_step": 397335, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0279273986816406, "global_step": 397336, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0757243633270264, "global_step": 397337, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0625059604644775, "global_step": 397338, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0471277236938477, "global_step": 397339, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1061387062072754, "global_step": 397340, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0945122241973877, "global_step": 397341, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1714749336242676, "global_step": 397342, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.150441884994507, "global_step": 397343, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.102220058441162, "global_step": 397344, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0656723976135254, "global_step": 397345, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.110741376876831, "global_step": 397346, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.160111904144287, "global_step": 397347, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0274949073791504, "global_step": 397348, "epoch": 759, "lr": 5e-05}
{"train_loss": 1.9985088109970093, "global_step": 397349, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0445375442504883, "global_step": 397350, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1205315589904785, "global_step": 397351, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.078460216522217, "global_step": 397352, "epoch": 759, "lr": 5e-05}
{"train_loss": 1.9609675407409668, "global_step": 397353, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0656774044036865, "global_step": 397354, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.138402223587036, "global_step": 397355, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.03635311126709, "global_step": 397356, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.061480760574341, "global_step": 397357, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0536508560180664, "global_step": 397358, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1342222690582275, "global_step": 397359, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0751209259033203, "global_step": 397360, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0908701419830322, "global_step": 397361, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0778191089630127, "global_step": 397362, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.001816511154175, "global_step": 397363, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.083893060684204, "global_step": 397364, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.2101969718933105, "global_step": 397365, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.074920415878296, "global_step": 397366, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1332337856292725, "global_step": 397367, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0943186283111572, "global_step": 397368, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.044250011444092, "global_step": 397369, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1580448150634766, "global_step": 397370, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0851268768310547, "global_step": 397371, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.136240243911743, "global_step": 397372, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0742506980895996, "global_step": 397373, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1760151386260986, "global_step": 397374, "epoch": 759, "lr": 5e-05}
{"train_loss": 1.9940581321716309, "global_step": 397375, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0815021991729736, "global_step": 397376, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1862857341766357, "global_step": 397377, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1395795345306396, "global_step": 397378, "epoch": 759, "lr": 5e-05}
{"train_loss": 1.9963798522949219, "global_step": 397379, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1296567916870117, "global_step": 397380, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1318717002868652, "global_step": 397381, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.149782180786133, "global_step": 397382, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.033949851989746, "global_step": 397383, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0350003242492676, "global_step": 397384, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.031966209411621, "global_step": 397385, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1058969497680664, "global_step": 397386, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0714025497436523, "global_step": 397387, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.170149803161621, "global_step": 397388, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.162597417831421, "global_step": 397389, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0264012813568115, "global_step": 397390, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1261229515075684, "global_step": 397391, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.009821653366089, "global_step": 397392, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.11426043510437, "global_step": 397393, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1722819805145264, "global_step": 397394, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.043637990951538, "global_step": 397395, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1238584518432617, "global_step": 397396, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.062375545501709, "global_step": 397397, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0828969478607178, "global_step": 397398, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.17173433303833, "global_step": 397399, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.178461790084839, "global_step": 397400, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.131326913833618, "global_step": 397401, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.188912868499756, "global_step": 397402, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.132420301437378, "global_step": 397403, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0491514205932617, "global_step": 397404, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.040156364440918, "global_step": 397405, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.106675148010254, "global_step": 397406, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1506786346435547, "global_step": 397407, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0367913246154785, "global_step": 397408, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1059458255767822, "global_step": 397409, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1275272369384766, "global_step": 397410, "epoch": 759, "lr": 5e-05}
{"train_loss": 1.9986828565597534, "global_step": 397411, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.172527551651001, "global_step": 397412, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.138024091720581, "global_step": 397413, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.076948642730713, "global_step": 397414, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0788047313690186, "global_step": 397415, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0923404693603516, "global_step": 397416, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.0752153396606445, "global_step": 397417, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.129457712173462, "global_step": 397418, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.1855504512786865, "global_step": 397419, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.179863452911377, "global_step": 397420, "epoch": 759, "lr": 5e-05}
{"train_loss": 1.9998431205749512, "global_step": 397421, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.097987413406372, "global_step": 397422, "epoch": 759, "lr": 5e-05}
{"train_loss": 2.110051155090332, "global_step": 397423, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0871458053588867, "global_step": 397424, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.05060076713562, "global_step": 397425, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0594468116760254, "global_step": 397426, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.2323427200317383, "global_step": 397427, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.056582450866699, "global_step": 397428, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.027327060699463, "global_step": 397429, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1425957679748535, "global_step": 397430, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.052234411239624, "global_step": 397431, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9783073663711548, "global_step": 397432, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0215959548950195, "global_step": 397433, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1128716468811035, "global_step": 397434, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.128791332244873, "global_step": 397435, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0629656314849854, "global_step": 397436, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0225210189819336, "global_step": 397437, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0581092834472656, "global_step": 397438, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1347458362579346, "global_step": 397439, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.134943723678589, "global_step": 397440, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0521066188812256, "global_step": 397441, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1028642654418945, "global_step": 397442, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.977500319480896, "global_step": 397443, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0834383964538574, "global_step": 397444, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0983517169952393, "global_step": 397445, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0719246864318848, "global_step": 397446, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0832221508026123, "global_step": 397447, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1623897552490234, "global_step": 397448, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1288959980010986, "global_step": 397449, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1104772090911865, "global_step": 397450, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1784942150115967, "global_step": 397451, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.135681390762329, "global_step": 397452, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0993340015411377, "global_step": 397453, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.137507438659668, "global_step": 397454, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.122248411178589, "global_step": 397455, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0395500659942627, "global_step": 397456, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.094252824783325, "global_step": 397457, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0638604164123535, "global_step": 397458, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0604403018951416, "global_step": 397459, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.148472309112549, "global_step": 397460, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0699894428253174, "global_step": 397461, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0514793395996094, "global_step": 397462, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0189921855926514, "global_step": 397463, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1326253414154053, "global_step": 397464, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1468136310577393, "global_step": 397465, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.128810167312622, "global_step": 397466, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.066776990890503, "global_step": 397467, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.158247470855713, "global_step": 397468, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.080540895462036, "global_step": 397469, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0898663997650146, "global_step": 397470, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.06640625, "global_step": 397471, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1136889457702637, "global_step": 397472, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1400160789489746, "global_step": 397473, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1023566722869873, "global_step": 397474, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0892789363861084, "global_step": 397475, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0770699977874756, "global_step": 397476, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.022517204284668, "global_step": 397477, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.090341091156006, "global_step": 397478, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0759103298187256, "global_step": 397479, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.071335554122925, "global_step": 397480, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0591068267822266, "global_step": 397481, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.063777208328247, "global_step": 397482, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1853227615356445, "global_step": 397483, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.032942056655884, "global_step": 397484, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.148256301879883, "global_step": 397485, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1166231632232666, "global_step": 397486, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0810904502868652, "global_step": 397487, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0923144817352295, "global_step": 397488, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.117034912109375, "global_step": 397489, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1112968921661377, "global_step": 397490, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0977776050567627, "global_step": 397491, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0737009048461914, "global_step": 397492, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.161266326904297, "global_step": 397493, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.090317487716675, "global_step": 397494, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.080631732940674, "global_step": 397495, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0825257301330566, "global_step": 397496, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.083397626876831, "global_step": 397497, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.173008441925049, "global_step": 397498, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9879021644592285, "global_step": 397499, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0227749347686768, "global_step": 397500, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0212438106536865, "global_step": 397501, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.086355209350586, "global_step": 397502, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.117452621459961, "global_step": 397503, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0368406772613525, "global_step": 397504, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0891988277435303, "global_step": 397505, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0413153171539307, "global_step": 397506, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.023059129714966, "global_step": 397507, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.25272536277771, "global_step": 397508, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.107419013977051, "global_step": 397509, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.191620111465454, "global_step": 397510, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0993216037750244, "global_step": 397511, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1085031032562256, "global_step": 397512, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0581278800964355, "global_step": 397513, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1514084339141846, "global_step": 397514, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.097944736480713, "global_step": 397515, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.146629571914673, "global_step": 397516, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0461575984954834, "global_step": 397517, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1016554832458496, "global_step": 397518, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0724916458129883, "global_step": 397519, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.148158073425293, "global_step": 397520, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.048156499862671, "global_step": 397521, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0438919067382812, "global_step": 397522, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0221121311187744, "global_step": 397523, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.117828607559204, "global_step": 397524, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0602304935455322, "global_step": 397525, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1488523483276367, "global_step": 397526, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.976867437362671, "global_step": 397527, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0806407928466797, "global_step": 397528, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1673243045806885, "global_step": 397529, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.068368911743164, "global_step": 397530, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0266153812408447, "global_step": 397531, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.028254985809326, "global_step": 397532, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1112422943115234, "global_step": 397533, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.112560749053955, "global_step": 397534, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0736358165740967, "global_step": 397535, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1299855709075928, "global_step": 397536, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.025838613510132, "global_step": 397537, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.032013416290283, "global_step": 397538, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0775387287139893, "global_step": 397539, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.101022243499756, "global_step": 397540, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.14479398727417, "global_step": 397541, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0799200534820557, "global_step": 397542, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.038865566253662, "global_step": 397543, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0315966606140137, "global_step": 397544, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.13856840133667, "global_step": 397545, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.128484010696411, "global_step": 397546, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.040989637374878, "global_step": 397547, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0607619285583496, "global_step": 397548, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0048372745513916, "global_step": 397549, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.054036855697632, "global_step": 397550, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.147355079650879, "global_step": 397551, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.10717511177063, "global_step": 397552, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1096084117889404, "global_step": 397553, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0398435592651367, "global_step": 397554, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.042252779006958, "global_step": 397555, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0324909687042236, "global_step": 397556, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.086806535720825, "global_step": 397557, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.100930690765381, "global_step": 397558, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0859954357147217, "global_step": 397559, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.063817262649536, "global_step": 397560, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0497243404388428, "global_step": 397561, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0567588806152344, "global_step": 397562, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1518280506134033, "global_step": 397563, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1816952228546143, "global_step": 397564, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.140416383743286, "global_step": 397565, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.06545090675354, "global_step": 397566, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1177926063537598, "global_step": 397567, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.121638774871826, "global_step": 397568, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1302831172943115, "global_step": 397569, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0744786262512207, "global_step": 397570, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0952136516571045, "global_step": 397571, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.107288360595703, "global_step": 397572, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.108811616897583, "global_step": 397573, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.227478265762329, "global_step": 397574, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0731513500213623, "global_step": 397575, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1234121322631836, "global_step": 397576, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0733678340911865, "global_step": 397577, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9946942329406738, "global_step": 397578, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.023106575012207, "global_step": 397579, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0421018600463867, "global_step": 397580, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.101044178009033, "global_step": 397581, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1032967567443848, "global_step": 397582, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.165286064147949, "global_step": 397583, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1049935817718506, "global_step": 397584, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1318891048431396, "global_step": 397585, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.094228744506836, "global_step": 397586, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1467795372009277, "global_step": 397587, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0605697631835938, "global_step": 397588, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.104111433029175, "global_step": 397589, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.053529977798462, "global_step": 397590, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.084820032119751, "global_step": 397591, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0531654357910156, "global_step": 397592, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.16582989692688, "global_step": 397593, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.13415789604187, "global_step": 397594, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0920374393463135, "global_step": 397595, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0849456787109375, "global_step": 397596, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.088986396789551, "global_step": 397597, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0587377548217773, "global_step": 397598, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.131708860397339, "global_step": 397599, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0509490966796875, "global_step": 397600, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1080167293548584, "global_step": 397601, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0178911685943604, "global_step": 397602, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0906126499176025, "global_step": 397603, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0626745223999023, "global_step": 397604, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.086160898208618, "global_step": 397605, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9827566146850586, "global_step": 397606, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.031616449356079, "global_step": 397607, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0105717182159424, "global_step": 397608, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0827558040618896, "global_step": 397609, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1431756019592285, "global_step": 397610, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.134394884109497, "global_step": 397611, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.118824005126953, "global_step": 397612, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.115323543548584, "global_step": 397613, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1683294773101807, "global_step": 397614, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0883119106292725, "global_step": 397615, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1603505611419678, "global_step": 397616, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1639013290405273, "global_step": 397617, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0974621772766113, "global_step": 397618, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.100278377532959, "global_step": 397619, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1556811332702637, "global_step": 397620, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.049306631088257, "global_step": 397621, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.018211603164673, "global_step": 397622, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1128063201904297, "global_step": 397623, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.126570224761963, "global_step": 397624, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.082345724105835, "global_step": 397625, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.07582950592041, "global_step": 397626, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.123784065246582, "global_step": 397627, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0971832275390625, "global_step": 397628, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0865771770477295, "global_step": 397629, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0301764011383057, "global_step": 397630, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9882895946502686, "global_step": 397631, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.088223934173584, "global_step": 397632, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.062817335128784, "global_step": 397633, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0733983516693115, "global_step": 397634, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1259512901306152, "global_step": 397635, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.186880350112915, "global_step": 397636, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1007943153381348, "global_step": 397637, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0842785835266113, "global_step": 397638, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0624067783355713, "global_step": 397639, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.089712619781494, "global_step": 397640, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.997816562652588, "global_step": 397641, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.153874158859253, "global_step": 397642, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0857739448547363, "global_step": 397643, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1292169094085693, "global_step": 397644, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.095766544342041, "global_step": 397645, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1479053497314453, "global_step": 397646, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.090427875518799, "global_step": 397647, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0379481315612793, "global_step": 397648, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0500388145446777, "global_step": 397649, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.099876642227173, "global_step": 397650, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.167877674102783, "global_step": 397651, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.117584466934204, "global_step": 397652, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.209866762161255, "global_step": 397653, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1640737056732178, "global_step": 397654, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0671627521514893, "global_step": 397655, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1162562370300293, "global_step": 397656, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.074708938598633, "global_step": 397657, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.150388240814209, "global_step": 397658, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1697635650634766, "global_step": 397659, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1600379943847656, "global_step": 397660, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1019885540008545, "global_step": 397661, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1347415447235107, "global_step": 397662, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1092512607574463, "global_step": 397663, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1267905235290527, "global_step": 397664, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.2334892749786377, "global_step": 397665, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1725077629089355, "global_step": 397666, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.111795425415039, "global_step": 397667, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1467323303222656, "global_step": 397668, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.049517869949341, "global_step": 397669, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0460286140441895, "global_step": 397670, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.063124179840088, "global_step": 397671, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1283276081085205, "global_step": 397672, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1679751873016357, "global_step": 397673, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.052396535873413, "global_step": 397674, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1311943531036377, "global_step": 397675, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1639442443847656, "global_step": 397676, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.02984619140625, "global_step": 397677, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0540831089019775, "global_step": 397678, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.063521385192871, "global_step": 397679, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1180458068847656, "global_step": 397680, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0135200023651123, "global_step": 397681, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.102325916290283, "global_step": 397682, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.138921022415161, "global_step": 397683, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.145479679107666, "global_step": 397684, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1711344718933105, "global_step": 397685, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0883147716522217, "global_step": 397686, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.071439266204834, "global_step": 397687, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1267166137695312, "global_step": 397688, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0526232719421387, "global_step": 397689, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1151342391967773, "global_step": 397690, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0076305866241455, "global_step": 397691, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1252329349517822, "global_step": 397692, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.16571044921875, "global_step": 397693, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1025519371032715, "global_step": 397694, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.179358959197998, "global_step": 397695, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0758957862854004, "global_step": 397696, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.026383638381958, "global_step": 397697, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.101001501083374, "global_step": 397698, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0093512535095215, "global_step": 397699, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1160645484924316, "global_step": 397700, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1331772804260254, "global_step": 397701, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9405741691589355, "global_step": 397702, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1170902252197266, "global_step": 397703, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.106895685195923, "global_step": 397704, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.144918203353882, "global_step": 397705, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1045899391174316, "global_step": 397706, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1175193786621094, "global_step": 397707, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0822274684906006, "global_step": 397708, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.095799684524536, "global_step": 397709, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.088697910308838, "global_step": 397710, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.2393171787261963, "global_step": 397711, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0124192237854004, "global_step": 397712, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1355695724487305, "global_step": 397713, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0696640014648438, "global_step": 397714, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0840067863464355, "global_step": 397715, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1374688148498535, "global_step": 397716, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0971219539642334, "global_step": 397717, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0855886936187744, "global_step": 397718, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1399028301239014, "global_step": 397719, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.005866289138794, "global_step": 397720, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.064575433731079, "global_step": 397721, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9737862348556519, "global_step": 397722, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0425782203674316, "global_step": 397723, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0034804344177246, "global_step": 397724, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1495254039764404, "global_step": 397725, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0427818298339844, "global_step": 397726, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0749874114990234, "global_step": 397727, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0996618270874023, "global_step": 397728, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.103747844696045, "global_step": 397729, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9847407341003418, "global_step": 397730, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0602521896362305, "global_step": 397731, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9838268756866455, "global_step": 397732, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.081745147705078, "global_step": 397733, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0629868507385254, "global_step": 397734, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.158193826675415, "global_step": 397735, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1451687812805176, "global_step": 397736, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.094153642654419, "global_step": 397737, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.089554786682129, "global_step": 397738, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0546324253082275, "global_step": 397739, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1080474853515625, "global_step": 397740, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.054957866668701, "global_step": 397741, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0380046367645264, "global_step": 397742, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.111813545227051, "global_step": 397743, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1068007946014404, "global_step": 397744, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1239330768585205, "global_step": 397745, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1385743618011475, "global_step": 397746, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.111405372619629, "global_step": 397747, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0667197704315186, "global_step": 397748, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1558635234832764, "global_step": 397749, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.087108612060547, "global_step": 397750, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1809322834014893, "global_step": 397751, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.029060125350952, "global_step": 397752, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.124945878982544, "global_step": 397753, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0603628158569336, "global_step": 397754, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.113056182861328, "global_step": 397755, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0458388328552246, "global_step": 397756, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1218576431274414, "global_step": 397757, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1993722915649414, "global_step": 397758, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0597736835479736, "global_step": 397759, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0992634296417236, "global_step": 397760, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9951494932174683, "global_step": 397761, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0754029750823975, "global_step": 397762, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.03538179397583, "global_step": 397763, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1566109657287598, "global_step": 397764, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.013375997543335, "global_step": 397765, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1188395023345947, "global_step": 397766, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.061999559402466, "global_step": 397767, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1182215213775635, "global_step": 397768, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.188979148864746, "global_step": 397769, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0377888679504395, "global_step": 397770, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1020443439483643, "global_step": 397771, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1357028484344482, "global_step": 397772, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.091094970703125, "global_step": 397773, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0823922157287598, "global_step": 397774, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0736207962036133, "global_step": 397775, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1245102882385254, "global_step": 397776, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.076016664505005, "global_step": 397777, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1239702701568604, "global_step": 397778, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0372202396392822, "global_step": 397779, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.128716468811035, "global_step": 397780, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0731236934661865, "global_step": 397781, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.160351037979126, "global_step": 397782, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0862743854522705, "global_step": 397783, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0837037563323975, "global_step": 397784, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1737444400787354, "global_step": 397785, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0934345722198486, "global_step": 397786, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0701820850372314, "global_step": 397787, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.050403118133545, "global_step": 397788, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0957553386688232, "global_step": 397789, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1696531772613525, "global_step": 397790, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.077065944671631, "global_step": 397791, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0882503986358643, "global_step": 397792, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1017415523529053, "global_step": 397793, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.125825881958008, "global_step": 397794, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1567654609680176, "global_step": 397795, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0478713512420654, "global_step": 397796, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0496065616607666, "global_step": 397797, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.122091770172119, "global_step": 397798, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1106863021850586, "global_step": 397799, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.056471824645996, "global_step": 397800, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1274118423461914, "global_step": 397801, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.024113655090332, "global_step": 397802, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.132084369659424, "global_step": 397803, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0394439697265625, "global_step": 397804, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1048197746276855, "global_step": 397805, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0585575103759766, "global_step": 397806, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1221683025360107, "global_step": 397807, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0962653160095215, "global_step": 397808, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.091144323348999, "global_step": 397809, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1581225395202637, "global_step": 397810, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.08732533454895, "global_step": 397811, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1033835411071777, "global_step": 397812, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.090899705886841, "global_step": 397813, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0803427696228027, "global_step": 397814, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.052102565765381, "global_step": 397815, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0720090866088867, "global_step": 397816, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.045036792755127, "global_step": 397817, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0591259002685547, "global_step": 397818, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.102813959121704, "global_step": 397819, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.135108232498169, "global_step": 397820, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1528611183166504, "global_step": 397821, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.06636118888855, "global_step": 397822, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.013373851776123, "global_step": 397823, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.068946123123169, "global_step": 397824, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.170962333679199, "global_step": 397825, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.066497325897217, "global_step": 397826, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.125215530395508, "global_step": 397827, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1643528938293457, "global_step": 397828, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.112100601196289, "global_step": 397829, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.157597064971924, "global_step": 397830, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.2115957736968994, "global_step": 397831, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.110102415084839, "global_step": 397832, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.131023406982422, "global_step": 397833, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.194735527038574, "global_step": 397834, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.123844623565674, "global_step": 397835, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1042113304138184, "global_step": 397836, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1657354831695557, "global_step": 397837, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.111518621444702, "global_step": 397838, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.083566665649414, "global_step": 397839, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1194095611572266, "global_step": 397840, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0769355297088623, "global_step": 397841, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.087280750274658, "global_step": 397842, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0472350120544434, "global_step": 397843, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.097562789916992, "global_step": 397844, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.029090404510498, "global_step": 397845, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1013848781585693, "global_step": 397846, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.057887077331543, "global_step": 397847, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0469677448272705, "global_step": 397848, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.106985569000244, "global_step": 397849, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1168267726898193, "global_step": 397850, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0619070529937744, "global_step": 397851, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.10967755317688, "global_step": 397852, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0916919708251953, "global_step": 397853, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9750348329544067, "global_step": 397854, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1526362895965576, "global_step": 397855, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1820285320281982, "global_step": 397856, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.178642511367798, "global_step": 397857, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.117626667022705, "global_step": 397858, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.089509963989258, "global_step": 397859, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1288483142852783, "global_step": 397860, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1101841926574707, "global_step": 397861, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.108264684677124, "global_step": 397862, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1065456867218018, "global_step": 397863, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1069231033325195, "global_step": 397864, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0773580074310303, "global_step": 397865, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1931469440460205, "global_step": 397866, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9870134592056274, "global_step": 397867, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0593509674072266, "global_step": 397868, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.159177303314209, "global_step": 397869, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0927436351776123, "global_step": 397870, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.200883626937866, "global_step": 397871, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0493385791778564, "global_step": 397872, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.051798105239868, "global_step": 397873, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.095716714859009, "global_step": 397874, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.016200542449951, "global_step": 397875, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0688631534576416, "global_step": 397876, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.069729804992676, "global_step": 397877, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1189825534820557, "global_step": 397878, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0810983180999756, "global_step": 397879, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.062657356262207, "global_step": 397880, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9671894311904907, "global_step": 397881, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.196554183959961, "global_step": 397882, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.07441782951355, "global_step": 397883, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.102797746658325, "global_step": 397884, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1080169677734375, "global_step": 397885, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1101317405700684, "global_step": 397886, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.007807493209839, "global_step": 397887, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.164243459701538, "global_step": 397888, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.118401288986206, "global_step": 397889, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0834107398986816, "global_step": 397890, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.118544340133667, "global_step": 397891, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.087846279144287, "global_step": 397892, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0796518325805664, "global_step": 397893, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0826168060302734, "global_step": 397894, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.044647455215454, "global_step": 397895, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.073005199432373, "global_step": 397896, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1556551456451416, "global_step": 397897, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.074208974838257, "global_step": 397898, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0477302074432373, "global_step": 397899, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1276214122772217, "global_step": 397900, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.11350154876709, "global_step": 397901, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0285842418670654, "global_step": 397902, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1090614795684814, "global_step": 397903, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1419146060943604, "global_step": 397904, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.131650447845459, "global_step": 397905, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.068115711212158, "global_step": 397906, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1216464042663574, "global_step": 397907, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.151050090789795, "global_step": 397908, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.094034194946289, "global_step": 397909, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1287922859191895, "global_step": 397910, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.14219069480896, "global_step": 397911, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.074281692504883, "global_step": 397912, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0857136249542236, "global_step": 397913, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1348493099212646, "global_step": 397914, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0859451293945312, "global_step": 397915, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.153238296508789, "global_step": 397916, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1172502040863037, "global_step": 397917, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.119530200958252, "global_step": 397918, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0786969661712646, "global_step": 397919, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.032508134841919, "global_step": 397920, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1124839782714844, "global_step": 397921, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0569353103637695, "global_step": 397922, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1474368572235107, "global_step": 397923, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.081827163696289, "global_step": 397924, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.15759015083313, "global_step": 397925, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.04468035697937, "global_step": 397926, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0875720977783203, "global_step": 397927, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0447356700897217, "global_step": 397928, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9483758211135864, "global_step": 397929, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.036808729171753, "global_step": 397930, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0690078735351562, "global_step": 397931, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0860354900360107, "global_step": 397932, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1081864833831787, "global_step": 397933, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.112093448638916, "global_step": 397934, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.027698278427124, "global_step": 397935, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0182673931121826, "global_step": 397936, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1135730743408203, "global_step": 397937, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9962666034698486, "global_step": 397938, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0214297771453857, "global_step": 397939, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1188101768493652, "global_step": 397940, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.178227424621582, "global_step": 397941, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0628292560577393, "global_step": 397942, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.135848045349121, "global_step": 397943, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1015307903289795, "global_step": 397944, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0656583309173584, "global_step": 397945, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.06803560256958, "global_step": 397946, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.15277361869812, "global_step": 397947, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0956966876983643, "global_step": 397948, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0986132621765137, "global_step": 397949, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1642098426818848, "global_step": 397950, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1978840827941895, "global_step": 397951, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.128520965576172, "global_step": 397952, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1213552951812744, "global_step": 397953, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0388906002044678, "global_step": 397954, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1197495460510254, "global_step": 397955, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9569307565689087, "global_step": 397956, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.039759397506714, "global_step": 397957, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.05940842628479, "global_step": 397958, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.107267379760742, "global_step": 397959, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.137049436569214, "global_step": 397960, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1228952407836914, "global_step": 397961, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1782073974609375, "global_step": 397962, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0461924076080322, "global_step": 397963, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1003916263580322, "global_step": 397964, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.982772707939148, "global_step": 397965, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1192262172698975, "global_step": 397966, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0733373165130615, "global_step": 397967, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.140216112136841, "global_step": 397968, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1709582805633545, "global_step": 397969, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0451412200927734, "global_step": 397970, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0511534214019775, "global_step": 397971, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0708603858947754, "global_step": 397972, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.119133949279785, "global_step": 397973, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.192286729812622, "global_step": 397974, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0983023643493652, "global_step": 397975, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0856170654296875, "global_step": 397976, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.021704912185669, "global_step": 397977, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.144479751586914, "global_step": 397978, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.047980308532715, "global_step": 397979, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0672948360443115, "global_step": 397980, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1437296867370605, "global_step": 397981, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0645017623901367, "global_step": 397982, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0844905376434326, "global_step": 397983, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.14650559425354, "global_step": 397984, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1095073223114014, "global_step": 397985, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.141286849975586, "global_step": 397986, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.012742280960083, "global_step": 397987, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.012465238571167, "global_step": 397988, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0968616008758545, "global_step": 397989, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.058220863342285, "global_step": 397990, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0734994411468506, "global_step": 397991, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1982407569885254, "global_step": 397992, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0997843742370605, "global_step": 397993, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.009977102279663, "global_step": 397994, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1090447902679443, "global_step": 397995, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.095551013946533, "global_step": 397996, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1177568435668945, "global_step": 397997, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0402793884277344, "global_step": 397998, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.136812210083008, "global_step": 397999, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1240644454956055, "global_step": 398000, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1740193367004395, "global_step": 398001, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0509727001190186, "global_step": 398002, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.114630937576294, "global_step": 398003, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1321675777435303, "global_step": 398004, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.080723524093628, "global_step": 398005, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0973033905029297, "global_step": 398006, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1721034049987793, "global_step": 398007, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1057982444763184, "global_step": 398008, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.202352523803711, "global_step": 398009, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1881840229034424, "global_step": 398010, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.092059373855591, "global_step": 398011, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.042438507080078, "global_step": 398012, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.10504412651062, "global_step": 398013, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.132201910018921, "global_step": 398014, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1324267387390137, "global_step": 398015, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0489416122436523, "global_step": 398016, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.160588264465332, "global_step": 398017, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.116518974304199, "global_step": 398018, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.077465772628784, "global_step": 398019, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0720226764678955, "global_step": 398020, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.107738971710205, "global_step": 398021, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.174718141555786, "global_step": 398022, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0572211742401123, "global_step": 398023, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1205062866210938, "global_step": 398024, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.159353256225586, "global_step": 398025, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1363790035247803, "global_step": 398026, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.140245199203491, "global_step": 398027, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.08211612701416, "global_step": 398028, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1191532611846924, "global_step": 398029, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.109642744064331, "global_step": 398030, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.151085615158081, "global_step": 398031, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0341997146606445, "global_step": 398032, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.137951374053955, "global_step": 398033, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1814913749694824, "global_step": 398034, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0550477504730225, "global_step": 398035, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1240110397338867, "global_step": 398036, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1032650470733643, "global_step": 398037, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0718448162078857, "global_step": 398038, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.133913278579712, "global_step": 398039, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.019554376602173, "global_step": 398040, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1162638664245605, "global_step": 398041, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.126235246658325, "global_step": 398042, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0471434593200684, "global_step": 398043, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.027275800704956, "global_step": 398044, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.107794761657715, "global_step": 398045, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.11383318901062, "global_step": 398046, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.029287099838257, "global_step": 398047, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.052351236343384, "global_step": 398048, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.140005111694336, "global_step": 398049, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0131077766418457, "global_step": 398050, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1820485591888428, "global_step": 398051, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1724565029144287, "global_step": 398052, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9773719310760498, "global_step": 398053, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1471316814422607, "global_step": 398054, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.028425931930542, "global_step": 398055, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1488301753997803, "global_step": 398056, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1741936206817627, "global_step": 398057, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0817043781280518, "global_step": 398058, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1055099964141846, "global_step": 398059, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.07944917678833, "global_step": 398060, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1118788719177246, "global_step": 398061, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1058740615844727, "global_step": 398062, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0461649894714355, "global_step": 398063, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1703708171844482, "global_step": 398064, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0930535793304443, "global_step": 398065, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1487200260162354, "global_step": 398066, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.10811448097229, "global_step": 398067, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.123783826828003, "global_step": 398068, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.165879249572754, "global_step": 398069, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0731048583984375, "global_step": 398070, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0735971927642822, "global_step": 398071, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.089545249938965, "global_step": 398072, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1080644130706787, "global_step": 398073, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.06587815284729, "global_step": 398074, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1411280632019043, "global_step": 398075, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.120882272720337, "global_step": 398076, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1124043464660645, "global_step": 398077, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1038105487823486, "global_step": 398078, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.083972215652466, "global_step": 398079, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1414029598236084, "global_step": 398080, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0780999660491943, "global_step": 398081, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.140462875366211, "global_step": 398082, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1295855045318604, "global_step": 398083, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0793471336364746, "global_step": 398084, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.092500686645508, "global_step": 398085, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1332342624664307, "global_step": 398086, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.081167221069336, "global_step": 398087, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.992270588874817, "global_step": 398088, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.101485013961792, "global_step": 398089, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.147939682006836, "global_step": 398090, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0548317432403564, "global_step": 398091, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0582945346832275, "global_step": 398092, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.165184259414673, "global_step": 398093, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0461220741271973, "global_step": 398094, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.026956081390381, "global_step": 398095, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0445446968078613, "global_step": 398096, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0907347202301025, "global_step": 398097, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9880608320236206, "global_step": 398098, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.095996379852295, "global_step": 398099, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1451966762542725, "global_step": 398100, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.093686103820801, "global_step": 398101, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1647136211395264, "global_step": 398102, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1902685165405273, "global_step": 398103, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1470065116882324, "global_step": 398104, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.147559642791748, "global_step": 398105, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.12104868888855, "global_step": 398106, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9588292837142944, "global_step": 398107, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0518150329589844, "global_step": 398108, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1088290214538574, "global_step": 398109, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.049887180328369, "global_step": 398110, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1073906421661377, "global_step": 398111, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1461946964263916, "global_step": 398112, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1723885536193848, "global_step": 398113, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0620663166046143, "global_step": 398114, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.159844398498535, "global_step": 398115, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0833394527435303, "global_step": 398116, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0216591358184814, "global_step": 398117, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1854376792907715, "global_step": 398118, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1123015880584717, "global_step": 398119, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0495810508728027, "global_step": 398120, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0803418159484863, "global_step": 398121, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0341994762420654, "global_step": 398122, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1099393367767334, "global_step": 398123, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1495487689971924, "global_step": 398124, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.039669990539551, "global_step": 398125, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0659024715423584, "global_step": 398126, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.040355920791626, "global_step": 398127, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.098766565322876, "global_step": 398128, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.104335069656372, "global_step": 398129, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0037641525268555, "global_step": 398130, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0325961112976074, "global_step": 398131, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.2249770164489746, "global_step": 398132, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0966100692749023, "global_step": 398133, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0875449180603027, "global_step": 398134, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.094820261001587, "global_step": 398135, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1554696559906006, "global_step": 398136, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1019928455352783, "global_step": 398137, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1191463470458984, "global_step": 398138, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.061490774154663, "global_step": 398139, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1067073345184326, "global_step": 398140, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1310224533081055, "global_step": 398141, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.103938341140747, "global_step": 398142, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1708834171295166, "global_step": 398143, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0580403804779053, "global_step": 398144, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1979310512542725, "global_step": 398145, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.094027042388916, "global_step": 398146, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0542235374450684, "global_step": 398147, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1274235248565674, "global_step": 398148, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.050898551940918, "global_step": 398149, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.101757764816284, "global_step": 398150, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0657694339752197, "global_step": 398151, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0886759757995605, "global_step": 398152, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0641021728515625, "global_step": 398153, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1354451179504395, "global_step": 398154, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.040609359741211, "global_step": 398155, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.056725263595581, "global_step": 398156, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.074132204055786, "global_step": 398157, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.099818229675293, "global_step": 398158, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1671648025512695, "global_step": 398159, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1553127765655518, "global_step": 398160, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0625429153442383, "global_step": 398161, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0838191509246826, "global_step": 398162, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.109961986541748, "global_step": 398163, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1054527759552, "global_step": 398164, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0987629890441895, "global_step": 398165, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1744329929351807, "global_step": 398166, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1248939037323, "global_step": 398167, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.168562889099121, "global_step": 398168, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.127910614013672, "global_step": 398169, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.08200740814209, "global_step": 398170, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0768513679504395, "global_step": 398171, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1400198936462402, "global_step": 398172, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.015284538269043, "global_step": 398173, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.132197856903076, "global_step": 398174, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.032147169113159, "global_step": 398175, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0868260860443115, "global_step": 398176, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1073641777038574, "global_step": 398177, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1190788745880127, "global_step": 398178, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.069831371307373, "global_step": 398179, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0664408206939697, "global_step": 398180, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1092824935913086, "global_step": 398181, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.111077070236206, "global_step": 398182, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.103839159011841, "global_step": 398183, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.167379856109619, "global_step": 398184, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.041015863418579, "global_step": 398185, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1254920959472656, "global_step": 398186, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0171146392822266, "global_step": 398187, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.099518060684204, "global_step": 398188, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.103936195373535, "global_step": 398189, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1129894256591797, "global_step": 398190, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.085024356842041, "global_step": 398191, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.103846311569214, "global_step": 398192, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.207493782043457, "global_step": 398193, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.123046875, "global_step": 398194, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1309995651245117, "global_step": 398195, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1612207889556885, "global_step": 398196, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1613144874572754, "global_step": 398197, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.148799180984497, "global_step": 398198, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.161431074142456, "global_step": 398199, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0985803604125977, "global_step": 398200, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.124131441116333, "global_step": 398201, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1047847270965576, "global_step": 398202, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.187814712524414, "global_step": 398203, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1256699562072754, "global_step": 398204, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1128978729248047, "global_step": 398205, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.224905014038086, "global_step": 398206, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.092456102371216, "global_step": 398207, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0380115509033203, "global_step": 398208, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.167335033416748, "global_step": 398209, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1469268798828125, "global_step": 398210, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.057033061981201, "global_step": 398211, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.089275360107422, "global_step": 398212, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.15170955657959, "global_step": 398213, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0431785583496094, "global_step": 398214, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1351356506347656, "global_step": 398215, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1439743041992188, "global_step": 398216, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0277583599090576, "global_step": 398217, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.110093593597412, "global_step": 398218, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.111851692199707, "global_step": 398219, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.072122097015381, "global_step": 398220, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.053098201751709, "global_step": 398221, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.177259683609009, "global_step": 398222, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.117610216140747, "global_step": 398223, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.075148105621338, "global_step": 398224, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0212807655334473, "global_step": 398225, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.148831844329834, "global_step": 398226, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0864017009735107, "global_step": 398227, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0282785892486572, "global_step": 398228, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.05997371673584, "global_step": 398229, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.140601634979248, "global_step": 398230, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.025560140609741, "global_step": 398231, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0296988487243652, "global_step": 398232, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1412384510040283, "global_step": 398233, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0664453506469727, "global_step": 398234, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.099578857421875, "global_step": 398235, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0594160556793213, "global_step": 398236, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.039067506790161, "global_step": 398237, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0796546936035156, "global_step": 398238, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0422840118408203, "global_step": 398239, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1472909450531006, "global_step": 398240, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.088071823120117, "global_step": 398241, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.115614175796509, "global_step": 398242, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.087806224822998, "global_step": 398243, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.040830612182617, "global_step": 398244, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.17984676361084, "global_step": 398245, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1444520950317383, "global_step": 398246, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0608747005462646, "global_step": 398247, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0532126426696777, "global_step": 398248, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.093812942504883, "global_step": 398249, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0757977962493896, "global_step": 398250, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0927791595458984, "global_step": 398251, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.169337749481201, "global_step": 398252, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0808703899383545, "global_step": 398253, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.128382682800293, "global_step": 398254, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1044933795928955, "global_step": 398255, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1573121547698975, "global_step": 398256, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1253714561462402, "global_step": 398257, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1288795471191406, "global_step": 398258, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.003180742263794, "global_step": 398259, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0224599838256836, "global_step": 398260, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0366873741149902, "global_step": 398261, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.160745143890381, "global_step": 398262, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0733466148376465, "global_step": 398263, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.074512481689453, "global_step": 398264, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.099668264389038, "global_step": 398265, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.138197183609009, "global_step": 398266, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1873550415039062, "global_step": 398267, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.027221918106079, "global_step": 398268, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0902369022369385, "global_step": 398269, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0632200241088867, "global_step": 398270, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.113321542739868, "global_step": 398271, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1140360832214355, "global_step": 398272, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1214425563812256, "global_step": 398273, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.110339403152466, "global_step": 398274, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1470062732696533, "global_step": 398275, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.082818031311035, "global_step": 398276, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.150631904602051, "global_step": 398277, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.079432487487793, "global_step": 398278, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1900599002838135, "global_step": 398279, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.106626033782959, "global_step": 398280, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.111732006072998, "global_step": 398281, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.069645404815674, "global_step": 398282, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1194231510162354, "global_step": 398283, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1331682205200195, "global_step": 398284, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1425275802612305, "global_step": 398285, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.15966796875, "global_step": 398286, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0881919860839844, "global_step": 398287, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1536450386047363, "global_step": 398288, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.15201997756958, "global_step": 398289, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.148392677307129, "global_step": 398290, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0139875411987305, "global_step": 398291, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0875916481018066, "global_step": 398292, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1870157718658447, "global_step": 398293, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1623942852020264, "global_step": 398294, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.097081184387207, "global_step": 398295, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1620614528656006, "global_step": 398296, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0642688274383545, "global_step": 398297, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.218111991882324, "global_step": 398298, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1219804286956787, "global_step": 398299, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1255009174346924, "global_step": 398300, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.981326937675476, "global_step": 398301, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.2103090286254883, "global_step": 398302, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0318446159362793, "global_step": 398303, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.119581937789917, "global_step": 398304, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.086568832397461, "global_step": 398305, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0849480628967285, "global_step": 398306, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.129507541656494, "global_step": 398307, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.109161615371704, "global_step": 398308, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0203638076782227, "global_step": 398309, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1442465782165527, "global_step": 398310, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.140867233276367, "global_step": 398311, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.094993829727173, "global_step": 398312, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1520192623138428, "global_step": 398313, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.133342981338501, "global_step": 398314, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.08400297164917, "global_step": 398315, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.086026430130005, "global_step": 398316, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1087377071380615, "global_step": 398317, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0697402954101562, "global_step": 398318, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.043529510498047, "global_step": 398319, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0331904888153076, "global_step": 398320, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.076509714126587, "global_step": 398321, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1178996562957764, "global_step": 398322, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.049384832382202, "global_step": 398323, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1353342533111572, "global_step": 398324, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.03490948677063, "global_step": 398325, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1152777671813965, "global_step": 398326, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.169473648071289, "global_step": 398327, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.260822057723999, "global_step": 398328, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0809597969055176, "global_step": 398329, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1297402381896973, "global_step": 398330, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.087524175643921, "global_step": 398331, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0910732746124268, "global_step": 398332, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.029439926147461, "global_step": 398333, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1241230964660645, "global_step": 398334, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.122411012649536, "global_step": 398335, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.109842538833618, "global_step": 398336, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.128255844116211, "global_step": 398337, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.084517002105713, "global_step": 398338, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.107626438140869, "global_step": 398339, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0601768493652344, "global_step": 398340, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.042370319366455, "global_step": 398341, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.057013988494873, "global_step": 398342, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0572433471679688, "global_step": 398343, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.084465265274048, "global_step": 398344, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.137428045272827, "global_step": 398345, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0364131927490234, "global_step": 398346, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1001060009002686, "global_step": 398347, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.085097312927246, "global_step": 398348, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.057021379470825, "global_step": 398349, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.121673345565796, "global_step": 398350, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1250622272491455, "global_step": 398351, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1076440811157227, "global_step": 398352, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.085597276687622, "global_step": 398353, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1627817153930664, "global_step": 398354, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0688233375549316, "global_step": 398355, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.2151830196380615, "global_step": 398356, "epoch": 760, "lr": 5e-05}
{"train_loss": 1.9859693050384521, "global_step": 398357, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0997073650360107, "global_step": 398358, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0725414752960205, "global_step": 398359, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0341882705688477, "global_step": 398360, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0491738319396973, "global_step": 398361, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1446762084960938, "global_step": 398362, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1479902267456055, "global_step": 398363, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.109933614730835, "global_step": 398364, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0474774837493896, "global_step": 398365, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1750364303588867, "global_step": 398366, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0735855102539062, "global_step": 398367, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.042551279067993, "global_step": 398368, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.039267063140869, "global_step": 398369, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.100642204284668, "global_step": 398370, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1011133193969727, "global_step": 398371, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0629711151123047, "global_step": 398372, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.012204170227051, "global_step": 398373, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.081789255142212, "global_step": 398374, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1006293296813965, "global_step": 398375, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.107064723968506, "global_step": 398376, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.091569423675537, "global_step": 398377, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1110634803771973, "global_step": 398378, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.063344955444336, "global_step": 398379, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0568478107452393, "global_step": 398380, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.169933557510376, "global_step": 398381, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0801494121551514, "global_step": 398382, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.085578680038452, "global_step": 398383, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.079286813735962, "global_step": 398384, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1090469360351562, "global_step": 398385, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1082661151885986, "global_step": 398386, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0816328525543213, "global_step": 398387, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0957183837890625, "global_step": 398388, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.1025495529174805, "global_step": 398389, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.0953571796417236, "global_step": 398390, "epoch": 760, "lr": 5e-05}
{"train_loss": 2.096843719482422, "global_step": 398391, "epoch": 760, "lr": 5e-05, "val_loss": 5.631248950958252, "test_reconst_mse": 0.0734533816576004}
{"train_loss": 2.0118167400360107, "global_step": 398392, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1105170249938965, "global_step": 398393, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1325817108154297, "global_step": 398394, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0238990783691406, "global_step": 398395, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0125088691711426, "global_step": 398396, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.066420316696167, "global_step": 398397, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0785083770751953, "global_step": 398398, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.118109703063965, "global_step": 398399, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0873241424560547, "global_step": 398400, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.110912322998047, "global_step": 398401, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0543768405914307, "global_step": 398402, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0600249767303467, "global_step": 398403, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0978176593780518, "global_step": 398404, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0558290481567383, "global_step": 398405, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0621042251586914, "global_step": 398406, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1012449264526367, "global_step": 398407, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0775701999664307, "global_step": 398408, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.146874189376831, "global_step": 398409, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0594165325164795, "global_step": 398410, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0546188354492188, "global_step": 398411, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.076251268386841, "global_step": 398412, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.020430088043213, "global_step": 398413, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1862192153930664, "global_step": 398414, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0593931674957275, "global_step": 398415, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.06518816947937, "global_step": 398416, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1087753772735596, "global_step": 398417, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.172287702560425, "global_step": 398418, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1632137298583984, "global_step": 398419, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1555867195129395, "global_step": 398420, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.094137191772461, "global_step": 398421, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.112046957015991, "global_step": 398422, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.9769136905670166, "global_step": 398423, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.032637596130371, "global_step": 398424, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.152674436569214, "global_step": 398425, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.137439012527466, "global_step": 398426, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0768213272094727, "global_step": 398427, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0030248165130615, "global_step": 398428, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1377599239349365, "global_step": 398429, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.990732192993164, "global_step": 398430, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.086531400680542, "global_step": 398431, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1424407958984375, "global_step": 398432, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.155083656311035, "global_step": 398433, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.079275608062744, "global_step": 398434, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0875773429870605, "global_step": 398435, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.040226697921753, "global_step": 398436, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0840344429016113, "global_step": 398437, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0950751304626465, "global_step": 398438, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0027339458465576, "global_step": 398439, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.115990161895752, "global_step": 398440, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0634937286376953, "global_step": 398441, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1753947734832764, "global_step": 398442, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1273880004882812, "global_step": 398443, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0563411712646484, "global_step": 398444, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.088134527206421, "global_step": 398445, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.099468946456909, "global_step": 398446, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.082183361053467, "global_step": 398447, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1033549308776855, "global_step": 398448, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.130215883255005, "global_step": 398449, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.122403860092163, "global_step": 398450, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1166012287139893, "global_step": 398451, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0905773639678955, "global_step": 398452, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1542458534240723, "global_step": 398453, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1423237323760986, "global_step": 398454, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0978286266326904, "global_step": 398455, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0759658813476562, "global_step": 398456, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1153855323791504, "global_step": 398457, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0900754928588867, "global_step": 398458, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.042219877243042, "global_step": 398459, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.070807695388794, "global_step": 398460, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0331778526306152, "global_step": 398461, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.140019416809082, "global_step": 398462, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1366164684295654, "global_step": 398463, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0756776332855225, "global_step": 398464, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0149402618408203, "global_step": 398465, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.088857889175415, "global_step": 398466, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1396660804748535, "global_step": 398467, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0916659832000732, "global_step": 398468, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.127025604248047, "global_step": 398469, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1225762367248535, "global_step": 398470, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0665602684020996, "global_step": 398471, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.174858570098877, "global_step": 398472, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.04925799369812, "global_step": 398473, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1571693420410156, "global_step": 398474, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.094000816345215, "global_step": 398475, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1102747917175293, "global_step": 398476, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.028512954711914, "global_step": 398477, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.093935966491699, "global_step": 398478, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.090867757797241, "global_step": 398479, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.102116823196411, "global_step": 398480, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.119933605194092, "global_step": 398481, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0147182941436768, "global_step": 398482, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.089488983154297, "global_step": 398483, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.050896644592285, "global_step": 398484, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.080617666244507, "global_step": 398485, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.041022777557373, "global_step": 398486, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.107327938079834, "global_step": 398487, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1057982444763184, "global_step": 398488, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.104801893234253, "global_step": 398489, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0461857318878174, "global_step": 398490, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.007513999938965, "global_step": 398491, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.099445104598999, "global_step": 398492, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.098424196243286, "global_step": 398493, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0821449756622314, "global_step": 398494, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.099463939666748, "global_step": 398495, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.948935627937317, "global_step": 398496, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0379154682159424, "global_step": 398497, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1087372303009033, "global_step": 398498, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1044418811798096, "global_step": 398499, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1358096599578857, "global_step": 398500, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0501832962036133, "global_step": 398501, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0888512134552, "global_step": 398502, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1183836460113525, "global_step": 398503, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.165832996368408, "global_step": 398504, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0786972045898438, "global_step": 398505, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0614309310913086, "global_step": 398506, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0399749279022217, "global_step": 398507, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.135089159011841, "global_step": 398508, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.12154483795166, "global_step": 398509, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.108344078063965, "global_step": 398510, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1200382709503174, "global_step": 398511, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.081127405166626, "global_step": 398512, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0894834995269775, "global_step": 398513, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1234145164489746, "global_step": 398514, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.074577569961548, "global_step": 398515, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.167926788330078, "global_step": 398516, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.058345317840576, "global_step": 398517, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.101257085800171, "global_step": 398518, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.103102207183838, "global_step": 398519, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1116209030151367, "global_step": 398520, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.106330394744873, "global_step": 398521, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.077619791030884, "global_step": 398522, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0376405715942383, "global_step": 398523, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0391364097595215, "global_step": 398524, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0465924739837646, "global_step": 398525, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.051455497741699, "global_step": 398526, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0888147354125977, "global_step": 398527, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1363883018493652, "global_step": 398528, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1532814502716064, "global_step": 398529, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0347900390625, "global_step": 398530, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0343775749206543, "global_step": 398531, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.096886157989502, "global_step": 398532, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.114391565322876, "global_step": 398533, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0887532234191895, "global_step": 398534, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.096467971801758, "global_step": 398535, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.110269546508789, "global_step": 398536, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0570759773254395, "global_step": 398537, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1305556297302246, "global_step": 398538, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.185643196105957, "global_step": 398539, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.053170680999756, "global_step": 398540, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.13608980178833, "global_step": 398541, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0768487453460693, "global_step": 398542, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0777244567871094, "global_step": 398543, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0952534675598145, "global_step": 398544, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.084301710128784, "global_step": 398545, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.187917470932007, "global_step": 398546, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0653555393218994, "global_step": 398547, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.031503438949585, "global_step": 398548, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.150139570236206, "global_step": 398549, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1447243690490723, "global_step": 398550, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.161799669265747, "global_step": 398551, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.103883981704712, "global_step": 398552, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0875349044799805, "global_step": 398553, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.057222843170166, "global_step": 398554, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.092710494995117, "global_step": 398555, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.071852922439575, "global_step": 398556, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.067729949951172, "global_step": 398557, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1218607425689697, "global_step": 398558, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0813605785369873, "global_step": 398559, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0180416107177734, "global_step": 398560, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0261247158050537, "global_step": 398561, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1993143558502197, "global_step": 398562, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.070582866668701, "global_step": 398563, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1465373039245605, "global_step": 398564, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0739219188690186, "global_step": 398565, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0824625492095947, "global_step": 398566, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0912208557128906, "global_step": 398567, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0548057556152344, "global_step": 398568, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.094637393951416, "global_step": 398569, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1060054302215576, "global_step": 398570, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.120911121368408, "global_step": 398571, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0404438972473145, "global_step": 398572, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1300907135009766, "global_step": 398573, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.100999116897583, "global_step": 398574, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0666913986206055, "global_step": 398575, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.178044319152832, "global_step": 398576, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.166512966156006, "global_step": 398577, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1397507190704346, "global_step": 398578, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0736682415008545, "global_step": 398579, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1218957901000977, "global_step": 398580, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0654501914978027, "global_step": 398581, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0715315341949463, "global_step": 398582, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.030177593231201, "global_step": 398583, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1250417232513428, "global_step": 398584, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.045170783996582, "global_step": 398585, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.101862668991089, "global_step": 398586, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1499266624450684, "global_step": 398587, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0846335887908936, "global_step": 398588, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.137408494949341, "global_step": 398589, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.056995391845703, "global_step": 398590, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.151050090789795, "global_step": 398591, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.061746120452881, "global_step": 398592, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.125452756881714, "global_step": 398593, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.05519437789917, "global_step": 398594, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.059281349182129, "global_step": 398595, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0702452659606934, "global_step": 398596, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0680980682373047, "global_step": 398597, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0839145183563232, "global_step": 398598, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.122588634490967, "global_step": 398599, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0601561069488525, "global_step": 398600, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.025743007659912, "global_step": 398601, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0695886611938477, "global_step": 398602, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.074798345565796, "global_step": 398603, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0066628456115723, "global_step": 398604, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.051358461380005, "global_step": 398605, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.033506155014038, "global_step": 398606, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.029682159423828, "global_step": 398607, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.094607353210449, "global_step": 398608, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0324480533599854, "global_step": 398609, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0977115631103516, "global_step": 398610, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.119971752166748, "global_step": 398611, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0877137184143066, "global_step": 398612, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.036357879638672, "global_step": 398613, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.069558620452881, "global_step": 398614, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.075948715209961, "global_step": 398615, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.114518880844116, "global_step": 398616, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1231281757354736, "global_step": 398617, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1040000915527344, "global_step": 398618, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.002639055252075, "global_step": 398619, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1359591484069824, "global_step": 398620, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1203393936157227, "global_step": 398621, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.070007085800171, "global_step": 398622, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1167235374450684, "global_step": 398623, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.106349229812622, "global_step": 398624, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1357200145721436, "global_step": 398625, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.136805534362793, "global_step": 398626, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0783512592315674, "global_step": 398627, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.067272663116455, "global_step": 398628, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0924904346466064, "global_step": 398629, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.062598943710327, "global_step": 398630, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0951833724975586, "global_step": 398631, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.168480157852173, "global_step": 398632, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0455448627471924, "global_step": 398633, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1475741863250732, "global_step": 398634, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1245007514953613, "global_step": 398635, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0522830486297607, "global_step": 398636, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0600717067718506, "global_step": 398637, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1115643978118896, "global_step": 398638, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.13877534866333, "global_step": 398639, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.059063673019409, "global_step": 398640, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1255483627319336, "global_step": 398641, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0893056392669678, "global_step": 398642, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1056230068206787, "global_step": 398643, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.113250494003296, "global_step": 398644, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.070007562637329, "global_step": 398645, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.08003306388855, "global_step": 398646, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1054179668426514, "global_step": 398647, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1147899627685547, "global_step": 398648, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1022746562957764, "global_step": 398649, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0924808979034424, "global_step": 398650, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1095900535583496, "global_step": 398651, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.073241949081421, "global_step": 398652, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.109614372253418, "global_step": 398653, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.044276237487793, "global_step": 398654, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.08797287940979, "global_step": 398655, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.004179000854492, "global_step": 398656, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0608768463134766, "global_step": 398657, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1055712699890137, "global_step": 398658, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.061431646347046, "global_step": 398659, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.019507646560669, "global_step": 398660, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.140292167663574, "global_step": 398661, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.025017499923706, "global_step": 398662, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0671894550323486, "global_step": 398663, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0732786655426025, "global_step": 398664, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.065480947494507, "global_step": 398665, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0753469467163086, "global_step": 398666, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.090381622314453, "global_step": 398667, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0637643337249756, "global_step": 398668, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1045188903808594, "global_step": 398669, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0981500148773193, "global_step": 398670, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1243295669555664, "global_step": 398671, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.079240560531616, "global_step": 398672, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0735538005828857, "global_step": 398673, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1098992824554443, "global_step": 398674, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.090970039367676, "global_step": 398675, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.987900972366333, "global_step": 398676, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1181118488311768, "global_step": 398677, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1896088123321533, "global_step": 398678, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.116584062576294, "global_step": 398679, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.184598684310913, "global_step": 398680, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1485323905944824, "global_step": 398681, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1663572788238525, "global_step": 398682, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.049100637435913, "global_step": 398683, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.109708309173584, "global_step": 398684, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.082836389541626, "global_step": 398685, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.144683837890625, "global_step": 398686, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0333783626556396, "global_step": 398687, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.024826765060425, "global_step": 398688, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.082488775253296, "global_step": 398689, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.089902639389038, "global_step": 398690, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.053953170776367, "global_step": 398691, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.9499804973602295, "global_step": 398692, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.9820476770401, "global_step": 398693, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.118115186691284, "global_step": 398694, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0336594581604004, "global_step": 398695, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.10577130317688, "global_step": 398696, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1258463859558105, "global_step": 398697, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0173237323760986, "global_step": 398698, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.059023857116699, "global_step": 398699, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1463115215301514, "global_step": 398700, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0554401874542236, "global_step": 398701, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.088391065597534, "global_step": 398702, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1328625679016113, "global_step": 398703, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0412445068359375, "global_step": 398704, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.2053897380828857, "global_step": 398705, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1391687393188477, "global_step": 398706, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.090665340423584, "global_step": 398707, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.132617712020874, "global_step": 398708, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1226038932800293, "global_step": 398709, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.122903347015381, "global_step": 398710, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.130491018295288, "global_step": 398711, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1861941814422607, "global_step": 398712, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1076762676239014, "global_step": 398713, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1233229637145996, "global_step": 398714, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.046102523803711, "global_step": 398715, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0705549716949463, "global_step": 398716, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.033143997192383, "global_step": 398717, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1749041080474854, "global_step": 398718, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.2141504287719727, "global_step": 398719, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0951199531555176, "global_step": 398720, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1085400581359863, "global_step": 398721, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1432979106903076, "global_step": 398722, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0709707736968994, "global_step": 398723, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.050788640975952, "global_step": 398724, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1513445377349854, "global_step": 398725, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.121741771697998, "global_step": 398726, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.124485731124878, "global_step": 398727, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.9928900003433228, "global_step": 398728, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.124494791030884, "global_step": 398729, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0157690048217773, "global_step": 398730, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1023573875427246, "global_step": 398731, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1321945190429688, "global_step": 398732, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.149803638458252, "global_step": 398733, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0885040760040283, "global_step": 398734, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0429880619049072, "global_step": 398735, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1303510665893555, "global_step": 398736, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1741302013397217, "global_step": 398737, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.07912540435791, "global_step": 398738, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1421616077423096, "global_step": 398739, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.051342725753784, "global_step": 398740, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0798840522766113, "global_step": 398741, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.176610231399536, "global_step": 398742, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.163637638092041, "global_step": 398743, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0412328243255615, "global_step": 398744, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.104032039642334, "global_step": 398745, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.17832088470459, "global_step": 398746, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0604891777038574, "global_step": 398747, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.147556781768799, "global_step": 398748, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.090620517730713, "global_step": 398749, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.006317138671875, "global_step": 398750, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.100044012069702, "global_step": 398751, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.101628065109253, "global_step": 398752, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0662734508514404, "global_step": 398753, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0947656631469727, "global_step": 398754, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.043264865875244, "global_step": 398755, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0996971130371094, "global_step": 398756, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1339614391326904, "global_step": 398757, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1419970989227295, "global_step": 398758, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.156949758529663, "global_step": 398759, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0577855110168457, "global_step": 398760, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1734185218811035, "global_step": 398761, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1738929748535156, "global_step": 398762, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0433433055877686, "global_step": 398763, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.114494800567627, "global_step": 398764, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.104746103286743, "global_step": 398765, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.134460687637329, "global_step": 398766, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1268858909606934, "global_step": 398767, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1519839763641357, "global_step": 398768, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.078526735305786, "global_step": 398769, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.119950532913208, "global_step": 398770, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.078786849975586, "global_step": 398771, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0788803100585938, "global_step": 398772, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.2141685485839844, "global_step": 398773, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.089674234390259, "global_step": 398774, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1536247730255127, "global_step": 398775, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1229770183563232, "global_step": 398776, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0756313800811768, "global_step": 398777, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1738712787628174, "global_step": 398778, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.146191120147705, "global_step": 398779, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.01184344291687, "global_step": 398780, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0443055629730225, "global_step": 398781, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.012200117111206, "global_step": 398782, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0381839275360107, "global_step": 398783, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.064785957336426, "global_step": 398784, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0748016834259033, "global_step": 398785, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.160184860229492, "global_step": 398786, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1276743412017822, "global_step": 398787, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0719211101531982, "global_step": 398788, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.14410662651062, "global_step": 398789, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.151695728302002, "global_step": 398790, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1390042304992676, "global_step": 398791, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1318585872650146, "global_step": 398792, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1031265258789062, "global_step": 398793, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0322699546813965, "global_step": 398794, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0634021759033203, "global_step": 398795, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.9873770475387573, "global_step": 398796, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.07041335105896, "global_step": 398797, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.141979694366455, "global_step": 398798, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.2082180976867676, "global_step": 398799, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0989952087402344, "global_step": 398800, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1327853202819824, "global_step": 398801, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.130125045776367, "global_step": 398802, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0044589042663574, "global_step": 398803, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.048494577407837, "global_step": 398804, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0910274982452393, "global_step": 398805, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.116136312484741, "global_step": 398806, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0802981853485107, "global_step": 398807, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.071160316467285, "global_step": 398808, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.130533218383789, "global_step": 398809, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.145789623260498, "global_step": 398810, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0807149410247803, "global_step": 398811, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.180802822113037, "global_step": 398812, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0398921966552734, "global_step": 398813, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.185607671737671, "global_step": 398814, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.183903694152832, "global_step": 398815, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.056180000305176, "global_step": 398816, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0812971591949463, "global_step": 398817, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.189992904663086, "global_step": 398818, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.119084358215332, "global_step": 398819, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1013271808624268, "global_step": 398820, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.996886134147644, "global_step": 398821, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.173025369644165, "global_step": 398822, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.180443286895752, "global_step": 398823, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1756813526153564, "global_step": 398824, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.097254514694214, "global_step": 398825, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0351040363311768, "global_step": 398826, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1191937923431396, "global_step": 398827, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0265769958496094, "global_step": 398828, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.095647096633911, "global_step": 398829, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.131237268447876, "global_step": 398830, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1105618476867676, "global_step": 398831, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.2055134773254395, "global_step": 398832, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0669283866882324, "global_step": 398833, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0635035037994385, "global_step": 398834, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.2101056575775146, "global_step": 398835, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.133680582046509, "global_step": 398836, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.106156587600708, "global_step": 398837, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1089656352996826, "global_step": 398838, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.091761589050293, "global_step": 398839, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0850846767425537, "global_step": 398840, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0919363498687744, "global_step": 398841, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1300835609436035, "global_step": 398842, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1346330642700195, "global_step": 398843, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.035674810409546, "global_step": 398844, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1049869060516357, "global_step": 398845, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.086606502532959, "global_step": 398846, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0596814155578613, "global_step": 398847, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.144747734069824, "global_step": 398848, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.9938381910324097, "global_step": 398849, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1524603366851807, "global_step": 398850, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.086761474609375, "global_step": 398851, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0955615043640137, "global_step": 398852, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.110757827758789, "global_step": 398853, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.166085720062256, "global_step": 398854, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.129149913787842, "global_step": 398855, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.012044668197632, "global_step": 398856, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1075050830841064, "global_step": 398857, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.089773178100586, "global_step": 398858, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.018380641937256, "global_step": 398859, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0064337253570557, "global_step": 398860, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1561267375946045, "global_step": 398861, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.9463326930999756, "global_step": 398862, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.082496166229248, "global_step": 398863, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0548245906829834, "global_step": 398864, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.161806106567383, "global_step": 398865, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.093327283859253, "global_step": 398866, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.091665267944336, "global_step": 398867, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.032578945159912, "global_step": 398868, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.113567352294922, "global_step": 398869, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.9919768571853638, "global_step": 398870, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.085296869277954, "global_step": 398871, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.106240749359131, "global_step": 398872, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0317845344543457, "global_step": 398873, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.9972025156021118, "global_step": 398874, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1255176067352295, "global_step": 398875, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0766119956970215, "global_step": 398876, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.068413257598877, "global_step": 398877, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0446231365203857, "global_step": 398878, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1698737144470215, "global_step": 398879, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.2075397968292236, "global_step": 398880, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.228416681289673, "global_step": 398881, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.139385223388672, "global_step": 398882, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1869664192199707, "global_step": 398883, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.147343158721924, "global_step": 398884, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.179938316345215, "global_step": 398885, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.074890375137329, "global_step": 398886, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1221141815185547, "global_step": 398887, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0732533931732178, "global_step": 398888, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.10683536529541, "global_step": 398889, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1028823852539062, "global_step": 398890, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.093947649002075, "global_step": 398891, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1361496448516846, "global_step": 398892, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1750786304473877, "global_step": 398893, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.121422052383423, "global_step": 398894, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.093444585800171, "global_step": 398895, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0983152389526367, "global_step": 398896, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.122912883758545, "global_step": 398897, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1102535724639893, "global_step": 398898, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.070343494415283, "global_step": 398899, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.026939630508423, "global_step": 398900, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.069591522216797, "global_step": 398901, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0509886741638184, "global_step": 398902, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0779664516448975, "global_step": 398903, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.053081512451172, "global_step": 398904, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.06034517288208, "global_step": 398905, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.124501943588257, "global_step": 398906, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0465965270996094, "global_step": 398907, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0871777534484863, "global_step": 398908, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.9987154006958008, "global_step": 398909, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.118680000305176, "global_step": 398910, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.064162254333496, "global_step": 398911, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1227962970733643, "global_step": 398912, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1600427627563477, "global_step": 398913, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.089625835418701, "global_step": 398914, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.026216506958008, "global_step": 398915, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0715525150299072, "global_step": 398916, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.074901580810547, "global_step": 398917, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0934696197509766, "global_step": 398918, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0579798221588135, "global_step": 398919, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.130690336227417, "global_step": 398920, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.057061195373535, "global_step": 398921, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.106552839279175, "global_step": 398922, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0527968406677246, "global_step": 398923, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1533713340759277, "global_step": 398924, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.079251527786255, "global_step": 398925, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.124008893966675, "global_step": 398926, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1935153007507324, "global_step": 398927, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.196655750274658, "global_step": 398928, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0272860527038574, "global_step": 398929, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.089736223220825, "global_step": 398930, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1122984886169434, "global_step": 398931, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.087465763092041, "global_step": 398932, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.027402400970459, "global_step": 398933, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.136326313018799, "global_step": 398934, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.037031412124634, "global_step": 398935, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.107686758041382, "global_step": 398936, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0950920581817627, "global_step": 398937, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0002334117889404, "global_step": 398938, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0552785396575928, "global_step": 398939, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0190064907073975, "global_step": 398940, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1026690006256104, "global_step": 398941, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1655595302581787, "global_step": 398942, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1661572456359863, "global_step": 398943, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1972501277923584, "global_step": 398944, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.970921277999878, "global_step": 398945, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.049771547317505, "global_step": 398946, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0347745418548584, "global_step": 398947, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1759283542633057, "global_step": 398948, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1021523475646973, "global_step": 398949, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0180797576904297, "global_step": 398950, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1326913833618164, "global_step": 398951, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1246891021728516, "global_step": 398952, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.9857667684555054, "global_step": 398953, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.11035418510437, "global_step": 398954, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1155683994293213, "global_step": 398955, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0217275619506836, "global_step": 398956, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0537595748901367, "global_step": 398957, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.116316556930542, "global_step": 398958, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1383888721466064, "global_step": 398959, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.081195116043091, "global_step": 398960, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.096966028213501, "global_step": 398961, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.123889446258545, "global_step": 398962, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.084718942642212, "global_step": 398963, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.147068977355957, "global_step": 398964, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0775976181030273, "global_step": 398965, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.109184503555298, "global_step": 398966, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0838735103607178, "global_step": 398967, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.11759090423584, "global_step": 398968, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0893070697784424, "global_step": 398969, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.021115303039551, "global_step": 398970, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1566684246063232, "global_step": 398971, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1795661449432373, "global_step": 398972, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.101156234741211, "global_step": 398973, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.053739547729492, "global_step": 398974, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.152836799621582, "global_step": 398975, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.155825138092041, "global_step": 398976, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1181485652923584, "global_step": 398977, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.143127918243408, "global_step": 398978, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0954861640930176, "global_step": 398979, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.016637086868286, "global_step": 398980, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1436052322387695, "global_step": 398981, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1367621421813965, "global_step": 398982, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.2275571823120117, "global_step": 398983, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.086284637451172, "global_step": 398984, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.035125970840454, "global_step": 398985, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0757217407226562, "global_step": 398986, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.109546661376953, "global_step": 398987, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.194735050201416, "global_step": 398988, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1083412170410156, "global_step": 398989, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.096985340118408, "global_step": 398990, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.102787494659424, "global_step": 398991, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1647095680236816, "global_step": 398992, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.068788528442383, "global_step": 398993, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.109139919281006, "global_step": 398994, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.116616725921631, "global_step": 398995, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.079406499862671, "global_step": 398996, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.112150192260742, "global_step": 398997, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.057840585708618, "global_step": 398998, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.172244071960449, "global_step": 398999, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.10151743888855, "global_step": 399000, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.126500368118286, "global_step": 399001, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0973410606384277, "global_step": 399002, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0609421730041504, "global_step": 399003, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.03464674949646, "global_step": 399004, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0465762615203857, "global_step": 399005, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.072359323501587, "global_step": 399006, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.005871295928955, "global_step": 399007, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1081795692443848, "global_step": 399008, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.085977792739868, "global_step": 399009, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1572751998901367, "global_step": 399010, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.140815019607544, "global_step": 399011, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1495659351348877, "global_step": 399012, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1632702350616455, "global_step": 399013, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.061659097671509, "global_step": 399014, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1973206996917725, "global_step": 399015, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0402917861938477, "global_step": 399016, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0999696254730225, "global_step": 399017, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1399266719818115, "global_step": 399018, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.056922435760498, "global_step": 399019, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0519070625305176, "global_step": 399020, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1004092693328857, "global_step": 399021, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1195974349975586, "global_step": 399022, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.033712387084961, "global_step": 399023, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0577781200408936, "global_step": 399024, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.208298683166504, "global_step": 399025, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.123084783554077, "global_step": 399026, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0719704627990723, "global_step": 399027, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0703728199005127, "global_step": 399028, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1156811714172363, "global_step": 399029, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0821776390075684, "global_step": 399030, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0152194499969482, "global_step": 399031, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0297679901123047, "global_step": 399032, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1325297355651855, "global_step": 399033, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.003084659576416, "global_step": 399034, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.107882499694824, "global_step": 399035, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1820809841156006, "global_step": 399036, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.191063165664673, "global_step": 399037, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.123333692550659, "global_step": 399038, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.078726053237915, "global_step": 399039, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.050413131713867, "global_step": 399040, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.077378511428833, "global_step": 399041, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1494851112365723, "global_step": 399042, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0877573490142822, "global_step": 399043, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.098358154296875, "global_step": 399044, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1382288932800293, "global_step": 399045, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0335805416107178, "global_step": 399046, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.101175546646118, "global_step": 399047, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1180579662323, "global_step": 399048, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.064584255218506, "global_step": 399049, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0774261951446533, "global_step": 399050, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.138979434967041, "global_step": 399051, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.096261501312256, "global_step": 399052, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.068667411804199, "global_step": 399053, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0833005905151367, "global_step": 399054, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1499786376953125, "global_step": 399055, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1212058067321777, "global_step": 399056, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.052882432937622, "global_step": 399057, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0832455158233643, "global_step": 399058, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.081990957260132, "global_step": 399059, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.162914276123047, "global_step": 399060, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1468615531921387, "global_step": 399061, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.050541639328003, "global_step": 399062, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0185585021972656, "global_step": 399063, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.122844696044922, "global_step": 399064, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.117809534072876, "global_step": 399065, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1513314247131348, "global_step": 399066, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1134490966796875, "global_step": 399067, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.086536169052124, "global_step": 399068, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.16693115234375, "global_step": 399069, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1029984951019287, "global_step": 399070, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.015554666519165, "global_step": 399071, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0820014476776123, "global_step": 399072, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0495097637176514, "global_step": 399073, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0202996730804443, "global_step": 399074, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.131065607070923, "global_step": 399075, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1195101737976074, "global_step": 399076, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.102539300918579, "global_step": 399077, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.09375262260437, "global_step": 399078, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.098094940185547, "global_step": 399079, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1078522205352783, "global_step": 399080, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.054858446121216, "global_step": 399081, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.116781711578369, "global_step": 399082, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0526390075683594, "global_step": 399083, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0476484298706055, "global_step": 399084, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.119281053543091, "global_step": 399085, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1171700954437256, "global_step": 399086, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.091470718383789, "global_step": 399087, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1295571327209473, "global_step": 399088, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.052154302597046, "global_step": 399089, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0106377601623535, "global_step": 399090, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0841188430786133, "global_step": 399091, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.116896867752075, "global_step": 399092, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1724836826324463, "global_step": 399093, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0282626152038574, "global_step": 399094, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0573673248291016, "global_step": 399095, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.042351245880127, "global_step": 399096, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0735697746276855, "global_step": 399097, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1098148822784424, "global_step": 399098, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1447508335113525, "global_step": 399099, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0380613803863525, "global_step": 399100, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0605082511901855, "global_step": 399101, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1146645545959473, "global_step": 399102, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1218812465667725, "global_step": 399103, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.152050733566284, "global_step": 399104, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1108641624450684, "global_step": 399105, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0959787368774414, "global_step": 399106, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1021370887756348, "global_step": 399107, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0173516273498535, "global_step": 399108, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.089782476425171, "global_step": 399109, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.185326099395752, "global_step": 399110, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.074488639831543, "global_step": 399111, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.161790609359741, "global_step": 399112, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.088717222213745, "global_step": 399113, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.032534599304199, "global_step": 399114, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.192382335662842, "global_step": 399115, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.112750768661499, "global_step": 399116, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.103604793548584, "global_step": 399117, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1475770473480225, "global_step": 399118, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.130593776702881, "global_step": 399119, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0245258808135986, "global_step": 399120, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.171963691711426, "global_step": 399121, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.034818649291992, "global_step": 399122, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1041111946105957, "global_step": 399123, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0773656368255615, "global_step": 399124, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1150314807891846, "global_step": 399125, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1153573989868164, "global_step": 399126, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.108135938644409, "global_step": 399127, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1435201168060303, "global_step": 399128, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0865139961242676, "global_step": 399129, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0769896507263184, "global_step": 399130, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.106729507446289, "global_step": 399131, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0485198497772217, "global_step": 399132, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.071502923965454, "global_step": 399133, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.063107490539551, "global_step": 399134, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1299891471862793, "global_step": 399135, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.132211208343506, "global_step": 399136, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.132390022277832, "global_step": 399137, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.2201638221740723, "global_step": 399138, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.204580783843994, "global_step": 399139, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.166588306427002, "global_step": 399140, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1369245052337646, "global_step": 399141, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1257882118225098, "global_step": 399142, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0977487564086914, "global_step": 399143, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1731138229370117, "global_step": 399144, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.134505271911621, "global_step": 399145, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1031694412231445, "global_step": 399146, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.005950927734375, "global_step": 399147, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0622262954711914, "global_step": 399148, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.102465867996216, "global_step": 399149, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1830341815948486, "global_step": 399150, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0588927268981934, "global_step": 399151, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1000277996063232, "global_step": 399152, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.081387996673584, "global_step": 399153, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1667237281799316, "global_step": 399154, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0215203762054443, "global_step": 399155, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1240365505218506, "global_step": 399156, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1163811683654785, "global_step": 399157, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.118309736251831, "global_step": 399158, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.137498140335083, "global_step": 399159, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.137876510620117, "global_step": 399160, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0293240547180176, "global_step": 399161, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.157271146774292, "global_step": 399162, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.124488115310669, "global_step": 399163, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.015608787536621, "global_step": 399164, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.9812403917312622, "global_step": 399165, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0971004962921143, "global_step": 399166, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1720290184020996, "global_step": 399167, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0766959190368652, "global_step": 399168, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.05153489112854, "global_step": 399169, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1324851512908936, "global_step": 399170, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1367645263671875, "global_step": 399171, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0495445728302, "global_step": 399172, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1446354389190674, "global_step": 399173, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1149587631225586, "global_step": 399174, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1687204837799072, "global_step": 399175, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.099416732788086, "global_step": 399176, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.053114891052246, "global_step": 399177, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0338943004608154, "global_step": 399178, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0769407749176025, "global_step": 399179, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1197757720947266, "global_step": 399180, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.103976011276245, "global_step": 399181, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.107639789581299, "global_step": 399182, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.038909912109375, "global_step": 399183, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.058253765106201, "global_step": 399184, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1724746227264404, "global_step": 399185, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.9964325428009033, "global_step": 399186, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.145885467529297, "global_step": 399187, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1141440868377686, "global_step": 399188, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.103902816772461, "global_step": 399189, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1064350605010986, "global_step": 399190, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1318600177764893, "global_step": 399191, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0913214683532715, "global_step": 399192, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0529062747955322, "global_step": 399193, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0523359775543213, "global_step": 399194, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1390857696533203, "global_step": 399195, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1663708686828613, "global_step": 399196, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.139204263687134, "global_step": 399197, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.018965721130371, "global_step": 399198, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1138172149658203, "global_step": 399199, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1954915523529053, "global_step": 399200, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0659682750701904, "global_step": 399201, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1102590560913086, "global_step": 399202, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1226439476013184, "global_step": 399203, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0609312057495117, "global_step": 399204, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.072047710418701, "global_step": 399205, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.125457763671875, "global_step": 399206, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.10615873336792, "global_step": 399207, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0620226860046387, "global_step": 399208, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0985536575317383, "global_step": 399209, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.127335786819458, "global_step": 399210, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.113140106201172, "global_step": 399211, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0917460918426514, "global_step": 399212, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0938544273376465, "global_step": 399213, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1458561420440674, "global_step": 399214, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.093484878540039, "global_step": 399215, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1848528385162354, "global_step": 399216, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.045778274536133, "global_step": 399217, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.121924877166748, "global_step": 399218, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.08475923538208, "global_step": 399219, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.115764617919922, "global_step": 399220, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0355491638183594, "global_step": 399221, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.078111171722412, "global_step": 399222, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1024363040924072, "global_step": 399223, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1208176612854004, "global_step": 399224, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.043790340423584, "global_step": 399225, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.190005302429199, "global_step": 399226, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0652036666870117, "global_step": 399227, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1543006896972656, "global_step": 399228, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.977948784828186, "global_step": 399229, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1335251331329346, "global_step": 399230, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0576815605163574, "global_step": 399231, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0515847206115723, "global_step": 399232, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.2049875259399414, "global_step": 399233, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1206021308898926, "global_step": 399234, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0991485118865967, "global_step": 399235, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1039347648620605, "global_step": 399236, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.13997745513916, "global_step": 399237, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.152719259262085, "global_step": 399238, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1349096298217773, "global_step": 399239, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.16603684425354, "global_step": 399240, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0731911659240723, "global_step": 399241, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1440927982330322, "global_step": 399242, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.9387314319610596, "global_step": 399243, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.028916358947754, "global_step": 399244, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.009765148162842, "global_step": 399245, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0190696716308594, "global_step": 399246, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0957436561584473, "global_step": 399247, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.118372678756714, "global_step": 399248, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1327874660491943, "global_step": 399249, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.226170301437378, "global_step": 399250, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.136505603790283, "global_step": 399251, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.095390558242798, "global_step": 399252, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.162533760070801, "global_step": 399253, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1119492053985596, "global_step": 399254, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1146528720855713, "global_step": 399255, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.060584783554077, "global_step": 399256, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.087113380432129, "global_step": 399257, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.163090229034424, "global_step": 399258, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.114760637283325, "global_step": 399259, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0591955184936523, "global_step": 399260, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.144221544265747, "global_step": 399261, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0113885402679443, "global_step": 399262, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0867414474487305, "global_step": 399263, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1227142810821533, "global_step": 399264, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.136613607406616, "global_step": 399265, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.110135078430176, "global_step": 399266, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1136763095855713, "global_step": 399267, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.159379243850708, "global_step": 399268, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.171002149581909, "global_step": 399269, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.132578134536743, "global_step": 399270, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1188693046569824, "global_step": 399271, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.196631669998169, "global_step": 399272, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1017961502075195, "global_step": 399273, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.072065591812134, "global_step": 399274, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.2193403244018555, "global_step": 399275, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0710434913635254, "global_step": 399276, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.107597827911377, "global_step": 399277, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.106137752532959, "global_step": 399278, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.2078452110290527, "global_step": 399279, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.113457441329956, "global_step": 399280, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0841715335845947, "global_step": 399281, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.180476427078247, "global_step": 399282, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.099848747253418, "global_step": 399283, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.056185245513916, "global_step": 399284, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1038193702697754, "global_step": 399285, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1355392932891846, "global_step": 399286, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.142582893371582, "global_step": 399287, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.053781509399414, "global_step": 399288, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1501028537750244, "global_step": 399289, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1070735454559326, "global_step": 399290, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1284801959991455, "global_step": 399291, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.096435546875, "global_step": 399292, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.081254243850708, "global_step": 399293, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.138550281524658, "global_step": 399294, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1066930294036865, "global_step": 399295, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.16851544380188, "global_step": 399296, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1031768321990967, "global_step": 399297, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0711917877197266, "global_step": 399298, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0980050563812256, "global_step": 399299, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.123945951461792, "global_step": 399300, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.109038829803467, "global_step": 399301, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1371097564697266, "global_step": 399302, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.124002456665039, "global_step": 399303, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0179314613342285, "global_step": 399304, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0843665599823, "global_step": 399305, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.123133420944214, "global_step": 399306, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.054995536804199, "global_step": 399307, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.144033193588257, "global_step": 399308, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.054614305496216, "global_step": 399309, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.130491018295288, "global_step": 399310, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.072303056716919, "global_step": 399311, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0793139934539795, "global_step": 399312, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.10688853263855, "global_step": 399313, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.241091251373291, "global_step": 399314, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.140043258666992, "global_step": 399315, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.188218593597412, "global_step": 399316, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1269359588623047, "global_step": 399317, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0675692558288574, "global_step": 399318, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.08624267578125, "global_step": 399319, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0792901515960693, "global_step": 399320, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1662285327911377, "global_step": 399321, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.108102798461914, "global_step": 399322, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.115389585494995, "global_step": 399323, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1010982990264893, "global_step": 399324, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.9979497194290161, "global_step": 399325, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.045193672180176, "global_step": 399326, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0215232372283936, "global_step": 399327, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.044271469116211, "global_step": 399328, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.160614013671875, "global_step": 399329, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1526310443878174, "global_step": 399330, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.02813982963562, "global_step": 399331, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.109696388244629, "global_step": 399332, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1067683696746826, "global_step": 399333, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1928749084472656, "global_step": 399334, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1018483638763428, "global_step": 399335, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1149158477783203, "global_step": 399336, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.17461895942688, "global_step": 399337, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0973291397094727, "global_step": 399338, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.039285659790039, "global_step": 399339, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1243622303009033, "global_step": 399340, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0572593212127686, "global_step": 399341, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.179077386856079, "global_step": 399342, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.123589277267456, "global_step": 399343, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.110356330871582, "global_step": 399344, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1230251789093018, "global_step": 399345, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1342525482177734, "global_step": 399346, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1499834060668945, "global_step": 399347, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1096370220184326, "global_step": 399348, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1895315647125244, "global_step": 399349, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0955731868743896, "global_step": 399350, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.123922824859619, "global_step": 399351, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1168088912963867, "global_step": 399352, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.044153928756714, "global_step": 399353, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0544230937957764, "global_step": 399354, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1502797603607178, "global_step": 399355, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.083491325378418, "global_step": 399356, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0518877506256104, "global_step": 399357, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.1424458026885986, "global_step": 399358, "epoch": 761, "lr": 5e-05}
{"train_loss": 1.9807860851287842, "global_step": 399359, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.0977554321289062, "global_step": 399360, "epoch": 761, "lr": 5e-05}
{"train_loss": 2.065974235534668, "global_step": 399361, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1085221767425537, "global_step": 399362, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0854172706604004, "global_step": 399363, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0021750926971436, "global_step": 399364, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0260543823242188, "global_step": 399365, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.005901336669922, "global_step": 399366, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0487096309661865, "global_step": 399367, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1029210090637207, "global_step": 399368, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1493327617645264, "global_step": 399369, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.19437837600708, "global_step": 399370, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1547763347625732, "global_step": 399371, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.9995362758636475, "global_step": 399372, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1386044025421143, "global_step": 399373, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0957677364349365, "global_step": 399374, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.085875988006592, "global_step": 399375, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.176083564758301, "global_step": 399376, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.101095676422119, "global_step": 399377, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.054600715637207, "global_step": 399378, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1541473865509033, "global_step": 399379, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.9933321475982666, "global_step": 399380, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.086397409439087, "global_step": 399381, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.120661497116089, "global_step": 399382, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.053331136703491, "global_step": 399383, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.113468885421753, "global_step": 399384, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1348862648010254, "global_step": 399385, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0693600177764893, "global_step": 399386, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.061215400695801, "global_step": 399387, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.120262622833252, "global_step": 399388, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0325138568878174, "global_step": 399389, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.096144437789917, "global_step": 399390, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0109095573425293, "global_step": 399391, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0294852256774902, "global_step": 399392, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0550544261932373, "global_step": 399393, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0398268699645996, "global_step": 399394, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1054441928863525, "global_step": 399395, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0105092525482178, "global_step": 399396, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.201972007751465, "global_step": 399397, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.9932070970535278, "global_step": 399398, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0279533863067627, "global_step": 399399, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0935611724853516, "global_step": 399400, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.043923854827881, "global_step": 399401, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0502190589904785, "global_step": 399402, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0492188930511475, "global_step": 399403, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1006882190704346, "global_step": 399404, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.105257987976074, "global_step": 399405, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0532009601593018, "global_step": 399406, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.043541669845581, "global_step": 399407, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0921406745910645, "global_step": 399408, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1316754817962646, "global_step": 399409, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.080487012863159, "global_step": 399410, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.102504253387451, "global_step": 399411, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.124159574508667, "global_step": 399412, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.058361768722534, "global_step": 399413, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1009066104888916, "global_step": 399414, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0706913471221924, "global_step": 399415, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0251736640930176, "global_step": 399416, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1458852291107178, "global_step": 399417, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1833622455596924, "global_step": 399418, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.149707317352295, "global_step": 399419, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.158917188644409, "global_step": 399420, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.086042642593384, "global_step": 399421, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1391544342041016, "global_step": 399422, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.067293167114258, "global_step": 399423, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.171592950820923, "global_step": 399424, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.136199951171875, "global_step": 399425, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0366973876953125, "global_step": 399426, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1360011100769043, "global_step": 399427, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1218385696411133, "global_step": 399428, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0839595794677734, "global_step": 399429, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0855700969696045, "global_step": 399430, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0872342586517334, "global_step": 399431, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.166867256164551, "global_step": 399432, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.133821487426758, "global_step": 399433, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.101339340209961, "global_step": 399434, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.9983799457550049, "global_step": 399435, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.120713472366333, "global_step": 399436, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0814554691314697, "global_step": 399437, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.068601131439209, "global_step": 399438, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.104466438293457, "global_step": 399439, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1391701698303223, "global_step": 399440, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0864529609680176, "global_step": 399441, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.103355884552002, "global_step": 399442, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.034043073654175, "global_step": 399443, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.075463056564331, "global_step": 399444, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.080613374710083, "global_step": 399445, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1425280570983887, "global_step": 399446, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1089251041412354, "global_step": 399447, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1033904552459717, "global_step": 399448, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.9804630279541016, "global_step": 399449, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1582398414611816, "global_step": 399450, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.042102098464966, "global_step": 399451, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0808701515197754, "global_step": 399452, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0129270553588867, "global_step": 399453, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0531880855560303, "global_step": 399454, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.088719367980957, "global_step": 399455, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.074230432510376, "global_step": 399456, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.000168561935425, "global_step": 399457, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0891339778900146, "global_step": 399458, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.9701147079467773, "global_step": 399459, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0953457355499268, "global_step": 399460, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0895824432373047, "global_step": 399461, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.068411111831665, "global_step": 399462, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1019859313964844, "global_step": 399463, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.07958984375, "global_step": 399464, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0738227367401123, "global_step": 399465, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1285650730133057, "global_step": 399466, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.076874256134033, "global_step": 399467, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.094285488128662, "global_step": 399468, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1919891834259033, "global_step": 399469, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1058478355407715, "global_step": 399470, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.140423536300659, "global_step": 399471, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.049825429916382, "global_step": 399472, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.187911033630371, "global_step": 399473, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0456392765045166, "global_step": 399474, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0370664596557617, "global_step": 399475, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.092912435531616, "global_step": 399476, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0927302837371826, "global_step": 399477, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.111870527267456, "global_step": 399478, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0709102153778076, "global_step": 399479, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0693137645721436, "global_step": 399480, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0285043716430664, "global_step": 399481, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0793519020080566, "global_step": 399482, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.129964828491211, "global_step": 399483, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0915422439575195, "global_step": 399484, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1345202922821045, "global_step": 399485, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1127724647521973, "global_step": 399486, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.133920669555664, "global_step": 399487, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0568928718566895, "global_step": 399488, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0547921657562256, "global_step": 399489, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.065324068069458, "global_step": 399490, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0629143714904785, "global_step": 399491, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.137331962585449, "global_step": 399492, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0130910873413086, "global_step": 399493, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0110061168670654, "global_step": 399494, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.088557243347168, "global_step": 399495, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.042283535003662, "global_step": 399496, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0505058765411377, "global_step": 399497, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.122138500213623, "global_step": 399498, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.093761920928955, "global_step": 399499, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0394887924194336, "global_step": 399500, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0917108058929443, "global_step": 399501, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0695276260375977, "global_step": 399502, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.084827184677124, "global_step": 399503, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.9676930904388428, "global_step": 399504, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0941238403320312, "global_step": 399505, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.103259325027466, "global_step": 399506, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.158738613128662, "global_step": 399507, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1307055950164795, "global_step": 399508, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.11181640625, "global_step": 399509, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0261800289154053, "global_step": 399510, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.026409149169922, "global_step": 399511, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0145325660705566, "global_step": 399512, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.129082679748535, "global_step": 399513, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0687499046325684, "global_step": 399514, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1391048431396484, "global_step": 399515, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.151980400085449, "global_step": 399516, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.064406394958496, "global_step": 399517, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1355185508728027, "global_step": 399518, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0865862369537354, "global_step": 399519, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1059162616729736, "global_step": 399520, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.060544490814209, "global_step": 399521, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.116849184036255, "global_step": 399522, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0831985473632812, "global_step": 399523, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0851476192474365, "global_step": 399524, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0334112644195557, "global_step": 399525, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.060488224029541, "global_step": 399526, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.12678861618042, "global_step": 399527, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.033663511276245, "global_step": 399528, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0014915466308594, "global_step": 399529, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.166959047317505, "global_step": 399530, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0800647735595703, "global_step": 399531, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.170482873916626, "global_step": 399532, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.064695358276367, "global_step": 399533, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1835227012634277, "global_step": 399534, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1740684509277344, "global_step": 399535, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.089597463607788, "global_step": 399536, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.146519660949707, "global_step": 399537, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.159623861312866, "global_step": 399538, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.9869649410247803, "global_step": 399539, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.009162425994873, "global_step": 399540, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.044039726257324, "global_step": 399541, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1478912830352783, "global_step": 399542, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0595273971557617, "global_step": 399543, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.152942419052124, "global_step": 399544, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0838050842285156, "global_step": 399545, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.139812707901001, "global_step": 399546, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0541155338287354, "global_step": 399547, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.133516550064087, "global_step": 399548, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.074432849884033, "global_step": 399549, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0974748134613037, "global_step": 399550, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1779627799987793, "global_step": 399551, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0485479831695557, "global_step": 399552, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.027109146118164, "global_step": 399553, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1050920486450195, "global_step": 399554, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.2022781372070312, "global_step": 399555, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.917502999305725, "global_step": 399556, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1281039714813232, "global_step": 399557, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1466212272644043, "global_step": 399558, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.074009656906128, "global_step": 399559, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1275458335876465, "global_step": 399560, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0944130420684814, "global_step": 399561, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0854740142822266, "global_step": 399562, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0925331115722656, "global_step": 399563, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0532596111297607, "global_step": 399564, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.144108295440674, "global_step": 399565, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1750435829162598, "global_step": 399566, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.017296552658081, "global_step": 399567, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0544371604919434, "global_step": 399568, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1474075317382812, "global_step": 399569, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.094693422317505, "global_step": 399570, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0656943321228027, "global_step": 399571, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0868046283721924, "global_step": 399572, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.190703868865967, "global_step": 399573, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0303735733032227, "global_step": 399574, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1225850582122803, "global_step": 399575, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.128509521484375, "global_step": 399576, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.141395330429077, "global_step": 399577, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0596609115600586, "global_step": 399578, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.13318133354187, "global_step": 399579, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.129404306411743, "global_step": 399580, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1395325660705566, "global_step": 399581, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.070345163345337, "global_step": 399582, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.063096284866333, "global_step": 399583, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.048656463623047, "global_step": 399584, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.14786958694458, "global_step": 399585, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.03778338432312, "global_step": 399586, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0871684551239014, "global_step": 399587, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1792078018188477, "global_step": 399588, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1348156929016113, "global_step": 399589, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.119940996170044, "global_step": 399590, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.9906998872756958, "global_step": 399591, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.066941738128662, "global_step": 399592, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0984902381896973, "global_step": 399593, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.129180908203125, "global_step": 399594, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.049182891845703, "global_step": 399595, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0649242401123047, "global_step": 399596, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.2306582927703857, "global_step": 399597, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0956969261169434, "global_step": 399598, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1045565605163574, "global_step": 399599, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.219118595123291, "global_step": 399600, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1261253356933594, "global_step": 399601, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.095595121383667, "global_step": 399602, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.2195262908935547, "global_step": 399603, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.117784023284912, "global_step": 399604, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1161367893218994, "global_step": 399605, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.125366687774658, "global_step": 399606, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1429781913757324, "global_step": 399607, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1338326930999756, "global_step": 399608, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1270861625671387, "global_step": 399609, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.154082775115967, "global_step": 399610, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.094434976577759, "global_step": 399611, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.043004035949707, "global_step": 399612, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1298205852508545, "global_step": 399613, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0949513912200928, "global_step": 399614, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0320146083831787, "global_step": 399615, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.17277193069458, "global_step": 399616, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.066160202026367, "global_step": 399617, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.059051275253296, "global_step": 399618, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1550796031951904, "global_step": 399619, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.126887083053589, "global_step": 399620, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1006600856781006, "global_step": 399621, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.077805280685425, "global_step": 399622, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1592459678649902, "global_step": 399623, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.044696092605591, "global_step": 399624, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1332082748413086, "global_step": 399625, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0775179862976074, "global_step": 399626, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.149620294570923, "global_step": 399627, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0996856689453125, "global_step": 399628, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1302764415740967, "global_step": 399629, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.08009934425354, "global_step": 399630, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0607495307922363, "global_step": 399631, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0894076824188232, "global_step": 399632, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1114423274993896, "global_step": 399633, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0737030506134033, "global_step": 399634, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.092916965484619, "global_step": 399635, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0706896781921387, "global_step": 399636, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.12843918800354, "global_step": 399637, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1237242221832275, "global_step": 399638, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.121131181716919, "global_step": 399639, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0740296840667725, "global_step": 399640, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.084007501602173, "global_step": 399641, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1068716049194336, "global_step": 399642, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0979480743408203, "global_step": 399643, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0659923553466797, "global_step": 399644, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.012500524520874, "global_step": 399645, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0962576866149902, "global_step": 399646, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.065467357635498, "global_step": 399647, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0899486541748047, "global_step": 399648, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.158600330352783, "global_step": 399649, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.068584442138672, "global_step": 399650, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1629085540771484, "global_step": 399651, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.150355339050293, "global_step": 399652, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.9966282844543457, "global_step": 399653, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0108418464660645, "global_step": 399654, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1856529712677, "global_step": 399655, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0272104740142822, "global_step": 399656, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.063420295715332, "global_step": 399657, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.149021863937378, "global_step": 399658, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.118408679962158, "global_step": 399659, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1345410346984863, "global_step": 399660, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0257294178009033, "global_step": 399661, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.10115647315979, "global_step": 399662, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.088561534881592, "global_step": 399663, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0035502910614014, "global_step": 399664, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.162510871887207, "global_step": 399665, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.121570110321045, "global_step": 399666, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.073806047439575, "global_step": 399667, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0738298892974854, "global_step": 399668, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1314992904663086, "global_step": 399669, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0680463314056396, "global_step": 399670, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.088365077972412, "global_step": 399671, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1236703395843506, "global_step": 399672, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1433513164520264, "global_step": 399673, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1568527221679688, "global_step": 399674, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0535075664520264, "global_step": 399675, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0003468990325928, "global_step": 399676, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.156397819519043, "global_step": 399677, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.141669988632202, "global_step": 399678, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1174819469451904, "global_step": 399679, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.11808443069458, "global_step": 399680, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0583817958831787, "global_step": 399681, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.145439386367798, "global_step": 399682, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1268868446350098, "global_step": 399683, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.050076961517334, "global_step": 399684, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1611831188201904, "global_step": 399685, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.062298059463501, "global_step": 399686, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.074979305267334, "global_step": 399687, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.155208110809326, "global_step": 399688, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.133423328399658, "global_step": 399689, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.134876012802124, "global_step": 399690, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0701944828033447, "global_step": 399691, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.116844892501831, "global_step": 399692, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1409316062927246, "global_step": 399693, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0515618324279785, "global_step": 399694, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1086785793304443, "global_step": 399695, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.090473175048828, "global_step": 399696, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1772329807281494, "global_step": 399697, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.9987540245056152, "global_step": 399698, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1020987033843994, "global_step": 399699, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.035176992416382, "global_step": 399700, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0574097633361816, "global_step": 399701, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0967509746551514, "global_step": 399702, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.989424228668213, "global_step": 399703, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1114633083343506, "global_step": 399704, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.077507734298706, "global_step": 399705, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0455856323242188, "global_step": 399706, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.2027063369750977, "global_step": 399707, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1411337852478027, "global_step": 399708, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.12166166305542, "global_step": 399709, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0261144638061523, "global_step": 399710, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.046208620071411, "global_step": 399711, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0974838733673096, "global_step": 399712, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0663156509399414, "global_step": 399713, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1919872760772705, "global_step": 399714, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0906410217285156, "global_step": 399715, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.090743064880371, "global_step": 399716, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1180074214935303, "global_step": 399717, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1208629608154297, "global_step": 399718, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0440523624420166, "global_step": 399719, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1120781898498535, "global_step": 399720, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0616002082824707, "global_step": 399721, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1006393432617188, "global_step": 399722, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0569775104522705, "global_step": 399723, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.066755771636963, "global_step": 399724, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1574649810791016, "global_step": 399725, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1150429248809814, "global_step": 399726, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1935219764709473, "global_step": 399727, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1096675395965576, "global_step": 399728, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.9987225532531738, "global_step": 399729, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1042959690093994, "global_step": 399730, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1497559547424316, "global_step": 399731, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1529903411865234, "global_step": 399732, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.056424379348755, "global_step": 399733, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0930378437042236, "global_step": 399734, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0923681259155273, "global_step": 399735, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1440622806549072, "global_step": 399736, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1512582302093506, "global_step": 399737, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.082632064819336, "global_step": 399738, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.015258550643921, "global_step": 399739, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1502301692962646, "global_step": 399740, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1018190383911133, "global_step": 399741, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1538808345794678, "global_step": 399742, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.127127170562744, "global_step": 399743, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1334609985351562, "global_step": 399744, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.067755699157715, "global_step": 399745, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0654571056365967, "global_step": 399746, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0279593467712402, "global_step": 399747, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0896055698394775, "global_step": 399748, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0705177783966064, "global_step": 399749, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.148010492324829, "global_step": 399750, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1316304206848145, "global_step": 399751, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.018045663833618, "global_step": 399752, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1066956520080566, "global_step": 399753, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0204687118530273, "global_step": 399754, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0901012420654297, "global_step": 399755, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0635409355163574, "global_step": 399756, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0258727073669434, "global_step": 399757, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.104616165161133, "global_step": 399758, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.059074878692627, "global_step": 399759, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0403525829315186, "global_step": 399760, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.126121997833252, "global_step": 399761, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.000504970550537, "global_step": 399762, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.125173568725586, "global_step": 399763, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.094116449356079, "global_step": 399764, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1024506092071533, "global_step": 399765, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.054433584213257, "global_step": 399766, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1098151206970215, "global_step": 399767, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.9975626468658447, "global_step": 399768, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1397719383239746, "global_step": 399769, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1976470947265625, "global_step": 399770, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.126828193664551, "global_step": 399771, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.09283185005188, "global_step": 399772, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1036016941070557, "global_step": 399773, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0914711952209473, "global_step": 399774, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0395164489746094, "global_step": 399775, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.10418438911438, "global_step": 399776, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.023077964782715, "global_step": 399777, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.045116901397705, "global_step": 399778, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1242945194244385, "global_step": 399779, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.065753936767578, "global_step": 399780, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0955684185028076, "global_step": 399781, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1994597911834717, "global_step": 399782, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.119234561920166, "global_step": 399783, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.08217191696167, "global_step": 399784, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.10817813873291, "global_step": 399785, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.232501745223999, "global_step": 399786, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.02689528465271, "global_step": 399787, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.16450834274292, "global_step": 399788, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.047203540802002, "global_step": 399789, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1740803718566895, "global_step": 399790, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.2175090312957764, "global_step": 399791, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0586392879486084, "global_step": 399792, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0498080253601074, "global_step": 399793, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1490070819854736, "global_step": 399794, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1437933444976807, "global_step": 399795, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1080126762390137, "global_step": 399796, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.096721887588501, "global_step": 399797, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1765990257263184, "global_step": 399798, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1371147632598877, "global_step": 399799, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.085653066635132, "global_step": 399800, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.9995113611221313, "global_step": 399801, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1691839694976807, "global_step": 399802, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1732559204101562, "global_step": 399803, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.078312873840332, "global_step": 399804, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1752631664276123, "global_step": 399805, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1338489055633545, "global_step": 399806, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.076586961746216, "global_step": 399807, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.074197292327881, "global_step": 399808, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0757765769958496, "global_step": 399809, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1091737747192383, "global_step": 399810, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.110956907272339, "global_step": 399811, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1287970542907715, "global_step": 399812, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.117645502090454, "global_step": 399813, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1581053733825684, "global_step": 399814, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.151928424835205, "global_step": 399815, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.075915575027466, "global_step": 399816, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.9884164333343506, "global_step": 399817, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0178048610687256, "global_step": 399818, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.201704978942871, "global_step": 399819, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.20919132232666, "global_step": 399820, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.09065580368042, "global_step": 399821, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.216785192489624, "global_step": 399822, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1161882877349854, "global_step": 399823, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1667096614837646, "global_step": 399824, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.015920877456665, "global_step": 399825, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.023146867752075, "global_step": 399826, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.067221164703369, "global_step": 399827, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.096015691757202, "global_step": 399828, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.083446502685547, "global_step": 399829, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0626003742218018, "global_step": 399830, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1678707599639893, "global_step": 399831, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1761057376861572, "global_step": 399832, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.176138401031494, "global_step": 399833, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.063565969467163, "global_step": 399834, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1930315494537354, "global_step": 399835, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.056448459625244, "global_step": 399836, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0770325660705566, "global_step": 399837, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.053104877471924, "global_step": 399838, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0839481353759766, "global_step": 399839, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.069434404373169, "global_step": 399840, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.107334613800049, "global_step": 399841, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.129085063934326, "global_step": 399842, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.072718381881714, "global_step": 399843, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.098660707473755, "global_step": 399844, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.044279098510742, "global_step": 399845, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1062839031219482, "global_step": 399846, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1474881172180176, "global_step": 399847, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1973419189453125, "global_step": 399848, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.21683931350708, "global_step": 399849, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1569623947143555, "global_step": 399850, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.080021619796753, "global_step": 399851, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1303446292877197, "global_step": 399852, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0763089656829834, "global_step": 399853, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.180036783218384, "global_step": 399854, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.130434274673462, "global_step": 399855, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0521652698516846, "global_step": 399856, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0390079021453857, "global_step": 399857, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0895819664001465, "global_step": 399858, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.063762664794922, "global_step": 399859, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0800397396087646, "global_step": 399860, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.202272891998291, "global_step": 399861, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1269102096557617, "global_step": 399862, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1197125911712646, "global_step": 399863, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.135239362716675, "global_step": 399864, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.072340726852417, "global_step": 399865, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1527538299560547, "global_step": 399866, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1509616374969482, "global_step": 399867, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.080624580383301, "global_step": 399868, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0787160396575928, "global_step": 399869, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0395233631134033, "global_step": 399870, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.076934576034546, "global_step": 399871, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.2070653438568115, "global_step": 399872, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1723344326019287, "global_step": 399873, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0857837200164795, "global_step": 399874, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1530585289001465, "global_step": 399875, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0956597328186035, "global_step": 399876, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.097843647003174, "global_step": 399877, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.149195671081543, "global_step": 399878, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0433385372161865, "global_step": 399879, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1017322540283203, "global_step": 399880, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1045119762420654, "global_step": 399881, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0761334896087646, "global_step": 399882, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0646424293518066, "global_step": 399883, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0961554050445557, "global_step": 399884, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.175415515899658, "global_step": 399885, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1600828170776367, "global_step": 399886, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0612165927886963, "global_step": 399887, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1585187911987305, "global_step": 399888, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.019740104675293, "global_step": 399889, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.19282865524292, "global_step": 399890, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0612614154815674, "global_step": 399891, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.09806227684021, "global_step": 399892, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.098341226577759, "global_step": 399893, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.082063674926758, "global_step": 399894, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.149928092956543, "global_step": 399895, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.072012424468994, "global_step": 399896, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0284295082092285, "global_step": 399897, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0649912357330322, "global_step": 399898, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.112450122833252, "global_step": 399899, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1080198287963867, "global_step": 399900, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.121077299118042, "global_step": 399901, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.116530656814575, "global_step": 399902, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1488187313079834, "global_step": 399903, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0993361473083496, "global_step": 399904, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.211987018585205, "global_step": 399905, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0997400283813477, "global_step": 399906, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0558626651763916, "global_step": 399907, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1510612964630127, "global_step": 399908, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0712978839874268, "global_step": 399909, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0507097244262695, "global_step": 399910, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.073572874069214, "global_step": 399911, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0658178329467773, "global_step": 399912, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.085352659225464, "global_step": 399913, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.085622787475586, "global_step": 399914, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0911383628845215, "global_step": 399915, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0638256072998047, "global_step": 399916, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1218819618225098, "global_step": 399917, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0769941806793213, "global_step": 399918, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1324565410614014, "global_step": 399919, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1026194095611572, "global_step": 399920, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0720365047454834, "global_step": 399921, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.077723741531372, "global_step": 399922, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.065408706665039, "global_step": 399923, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.150355100631714, "global_step": 399924, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1769356727600098, "global_step": 399925, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1553566455841064, "global_step": 399926, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.150475263595581, "global_step": 399927, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0844366550445557, "global_step": 399928, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0620644092559814, "global_step": 399929, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.145066976547241, "global_step": 399930, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1541218757629395, "global_step": 399931, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.112377882003784, "global_step": 399932, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0661141872406006, "global_step": 399933, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0561811923980713, "global_step": 399934, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0806243419647217, "global_step": 399935, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.137637138366699, "global_step": 399936, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0875909328460693, "global_step": 399937, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.116391181945801, "global_step": 399938, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0733084678649902, "global_step": 399939, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0786304473876953, "global_step": 399940, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.993870496749878, "global_step": 399941, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.104426145553589, "global_step": 399942, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.058427572250366, "global_step": 399943, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1023402214050293, "global_step": 399944, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0836358070373535, "global_step": 399945, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.9561271667480469, "global_step": 399946, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.079488754272461, "global_step": 399947, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.168395757675171, "global_step": 399948, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.076434373855591, "global_step": 399949, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1182708740234375, "global_step": 399950, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1003377437591553, "global_step": 399951, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1538002490997314, "global_step": 399952, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.036330461502075, "global_step": 399953, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1010653972625732, "global_step": 399954, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.116781234741211, "global_step": 399955, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.113102674484253, "global_step": 399956, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0740573406219482, "global_step": 399957, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0544846057891846, "global_step": 399958, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.090587854385376, "global_step": 399959, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0342042446136475, "global_step": 399960, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1429250240325928, "global_step": 399961, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0899012088775635, "global_step": 399962, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0446627140045166, "global_step": 399963, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0683722496032715, "global_step": 399964, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1156868934631348, "global_step": 399965, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1391751766204834, "global_step": 399966, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0407702922821045, "global_step": 399967, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0791101455688477, "global_step": 399968, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1045491695404053, "global_step": 399969, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1038506031036377, "global_step": 399970, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.061875581741333, "global_step": 399971, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1135048866271973, "global_step": 399972, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1080925464630127, "global_step": 399973, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0882725715637207, "global_step": 399974, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0867373943328857, "global_step": 399975, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.062559127807617, "global_step": 399976, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0361838340759277, "global_step": 399977, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1008777618408203, "global_step": 399978, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.126852512359619, "global_step": 399979, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.083775043487549, "global_step": 399980, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0946457386016846, "global_step": 399981, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.041417360305786, "global_step": 399982, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.109891653060913, "global_step": 399983, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.102524757385254, "global_step": 399984, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1531805992126465, "global_step": 399985, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.054696798324585, "global_step": 399986, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.050168037414551, "global_step": 399987, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.15210223197937, "global_step": 399988, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.139087677001953, "global_step": 399989, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1119565963745117, "global_step": 399990, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1278910636901855, "global_step": 399991, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1364967823028564, "global_step": 399992, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.084033966064453, "global_step": 399993, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0822505950927734, "global_step": 399994, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.083594799041748, "global_step": 399995, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1498560905456543, "global_step": 399996, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.147822618484497, "global_step": 399997, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1515235900878906, "global_step": 399998, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1454224586486816, "global_step": 399999, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0833096504211426, "global_step": 400000, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.067967176437378, "global_step": 400001, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.128056764602661, "global_step": 400002, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.084303617477417, "global_step": 400003, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.105557441711426, "global_step": 400004, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0708842277526855, "global_step": 400005, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0519187450408936, "global_step": 400006, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1129467487335205, "global_step": 400007, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.092097043991089, "global_step": 400008, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.112107515335083, "global_step": 400009, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.083423137664795, "global_step": 400010, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1366474628448486, "global_step": 400011, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0172481536865234, "global_step": 400012, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.098418712615967, "global_step": 400013, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.09014892578125, "global_step": 400014, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.056119441986084, "global_step": 400015, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.061086654663086, "global_step": 400016, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1845765113830566, "global_step": 400017, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0596063137054443, "global_step": 400018, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.098574638366699, "global_step": 400019, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.090094804763794, "global_step": 400020, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.077890634536743, "global_step": 400021, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0218324661254883, "global_step": 400022, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0396265983581543, "global_step": 400023, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.010868787765503, "global_step": 400024, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0647008419036865, "global_step": 400025, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.9865654706954956, "global_step": 400026, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1849377155303955, "global_step": 400027, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1059210300445557, "global_step": 400028, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.140393018722534, "global_step": 400029, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.024811267852783, "global_step": 400030, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1688029766082764, "global_step": 400031, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0651957988739014, "global_step": 400032, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.123904228210449, "global_step": 400033, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0787746906280518, "global_step": 400034, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0218966007232666, "global_step": 400035, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.2280361652374268, "global_step": 400036, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1185333728790283, "global_step": 400037, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0503668785095215, "global_step": 400038, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.093257188796997, "global_step": 400039, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1303153038024902, "global_step": 400040, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1263468265533447, "global_step": 400041, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0582003593444824, "global_step": 400042, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.970115303993225, "global_step": 400043, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1148548126220703, "global_step": 400044, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.054936647415161, "global_step": 400045, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1066088676452637, "global_step": 400046, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.136345148086548, "global_step": 400047, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1509361267089844, "global_step": 400048, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1071324348449707, "global_step": 400049, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.075718402862549, "global_step": 400050, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.130098581314087, "global_step": 400051, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1262166500091553, "global_step": 400052, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1542696952819824, "global_step": 400053, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.064409017562866, "global_step": 400054, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1537513732910156, "global_step": 400055, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.09027361869812, "global_step": 400056, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1108486652374268, "global_step": 400057, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.9809668064117432, "global_step": 400058, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0652213096618652, "global_step": 400059, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0479626655578613, "global_step": 400060, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.045335531234741, "global_step": 400061, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0322203636169434, "global_step": 400062, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0712783336639404, "global_step": 400063, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1296465396881104, "global_step": 400064, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0525808334350586, "global_step": 400065, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0358614921569824, "global_step": 400066, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.092695713043213, "global_step": 400067, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.145231246948242, "global_step": 400068, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0419118404388428, "global_step": 400069, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.166691541671753, "global_step": 400070, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1331021785736084, "global_step": 400071, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1641159057617188, "global_step": 400072, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.109278440475464, "global_step": 400073, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1182713508605957, "global_step": 400074, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0649638175964355, "global_step": 400075, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.056218385696411, "global_step": 400076, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0670971870422363, "global_step": 400077, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1903250217437744, "global_step": 400078, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.103181838989258, "global_step": 400079, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0377707481384277, "global_step": 400080, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0725204944610596, "global_step": 400081, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.104656219482422, "global_step": 400082, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0362648963928223, "global_step": 400083, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.169199228286743, "global_step": 400084, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1000497341156006, "global_step": 400085, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.061863422393799, "global_step": 400086, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1397390365600586, "global_step": 400087, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1418821811676025, "global_step": 400088, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0822720527648926, "global_step": 400089, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.034116268157959, "global_step": 400090, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.111147880554199, "global_step": 400091, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.121403455734253, "global_step": 400092, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.039872884750366, "global_step": 400093, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0551645755767822, "global_step": 400094, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1409690380096436, "global_step": 400095, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0839273929595947, "global_step": 400096, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0933146476745605, "global_step": 400097, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.116856336593628, "global_step": 400098, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0875000953674316, "global_step": 400099, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.074056386947632, "global_step": 400100, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.037385940551758, "global_step": 400101, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.069551467895508, "global_step": 400102, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0712218284606934, "global_step": 400103, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1093125343322754, "global_step": 400104, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1074085235595703, "global_step": 400105, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.080972194671631, "global_step": 400106, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0682287216186523, "global_step": 400107, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0581631660461426, "global_step": 400108, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1076252460479736, "global_step": 400109, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0899274349212646, "global_step": 400110, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0703511238098145, "global_step": 400111, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.15690279006958, "global_step": 400112, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.072962760925293, "global_step": 400113, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1218671798706055, "global_step": 400114, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.161700487136841, "global_step": 400115, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.979904055595398, "global_step": 400116, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1223702430725098, "global_step": 400117, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1876466274261475, "global_step": 400118, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.10217022895813, "global_step": 400119, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.160616636276245, "global_step": 400120, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0876848697662354, "global_step": 400121, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.009645462036133, "global_step": 400122, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.045551061630249, "global_step": 400123, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0498764514923096, "global_step": 400124, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0777294635772705, "global_step": 400125, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0168609619140625, "global_step": 400126, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1106603145599365, "global_step": 400127, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1184558868408203, "global_step": 400128, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.113548517227173, "global_step": 400129, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0692107677459717, "global_step": 400130, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.084434747695923, "global_step": 400131, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1233766078948975, "global_step": 400132, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1835901737213135, "global_step": 400133, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0452330112457275, "global_step": 400134, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0662190914154053, "global_step": 400135, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0414247512817383, "global_step": 400136, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0609967708587646, "global_step": 400137, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0181972980499268, "global_step": 400138, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.056528329849243, "global_step": 400139, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.151313066482544, "global_step": 400140, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.098503351211548, "global_step": 400141, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.143345832824707, "global_step": 400142, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1034345626831055, "global_step": 400143, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.153710126876831, "global_step": 400144, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.106656789779663, "global_step": 400145, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0606064796447754, "global_step": 400146, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.100694417953491, "global_step": 400147, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0544605255126953, "global_step": 400148, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0220272541046143, "global_step": 400149, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1797406673431396, "global_step": 400150, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1800172328948975, "global_step": 400151, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1735196113586426, "global_step": 400152, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1413166522979736, "global_step": 400153, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0657758712768555, "global_step": 400154, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.14798641204834, "global_step": 400155, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0632803440093994, "global_step": 400156, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.144623279571533, "global_step": 400157, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0523626804351807, "global_step": 400158, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.146604537963867, "global_step": 400159, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.08195424079895, "global_step": 400160, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1151928901672363, "global_step": 400161, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.110929250717163, "global_step": 400162, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.140118360519409, "global_step": 400163, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.17836594581604, "global_step": 400164, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1343393325805664, "global_step": 400165, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0653622150421143, "global_step": 400166, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.153280019760132, "global_step": 400167, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.064716339111328, "global_step": 400168, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0206148624420166, "global_step": 400169, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.14747953414917, "global_step": 400170, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1363985538482666, "global_step": 400171, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0594005584716797, "global_step": 400172, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.076978921890259, "global_step": 400173, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.072394847869873, "global_step": 400174, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1290323734283447, "global_step": 400175, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.12211012840271, "global_step": 400176, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.087254762649536, "global_step": 400177, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.100593328475952, "global_step": 400178, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.06189227104187, "global_step": 400179, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.125962018966675, "global_step": 400180, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.11350679397583, "global_step": 400181, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1402807235717773, "global_step": 400182, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.061570167541504, "global_step": 400183, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1777634620666504, "global_step": 400184, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.12772274017334, "global_step": 400185, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1649115085601807, "global_step": 400186, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1304314136505127, "global_step": 400187, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0541903972625732, "global_step": 400188, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0893054008483887, "global_step": 400189, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.103290557861328, "global_step": 400190, "epoch": 762, "lr": 5e-05}
{"train_loss": 1.976306438446045, "global_step": 400191, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0245413780212402, "global_step": 400192, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.164163827896118, "global_step": 400193, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0269484519958496, "global_step": 400194, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1306333541870117, "global_step": 400195, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1230733394622803, "global_step": 400196, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1012892723083496, "global_step": 400197, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.125654697418213, "global_step": 400198, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0528147220611572, "global_step": 400199, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0755505561828613, "global_step": 400200, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1697521209716797, "global_step": 400201, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0856990814208984, "global_step": 400202, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0872879028320312, "global_step": 400203, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1701314449310303, "global_step": 400204, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0957694053649902, "global_step": 400205, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.059885263442993, "global_step": 400206, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1294655799865723, "global_step": 400207, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.044365882873535, "global_step": 400208, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1039156913757324, "global_step": 400209, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.071768045425415, "global_step": 400210, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0553598403930664, "global_step": 400211, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0551271438598633, "global_step": 400212, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0581910610198975, "global_step": 400213, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1134045124053955, "global_step": 400214, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.123103618621826, "global_step": 400215, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0443203449249268, "global_step": 400216, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1191322803497314, "global_step": 400217, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.163789749145508, "global_step": 400218, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.078900098800659, "global_step": 400219, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.087200164794922, "global_step": 400220, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0773026943206787, "global_step": 400221, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0784687995910645, "global_step": 400222, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.136380910873413, "global_step": 400223, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0757527351379395, "global_step": 400224, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0724239349365234, "global_step": 400225, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.15423583984375, "global_step": 400226, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0962769985198975, "global_step": 400227, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0997726917266846, "global_step": 400228, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0353786945343018, "global_step": 400229, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0421032905578613, "global_step": 400230, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0892372131347656, "global_step": 400231, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.136497974395752, "global_step": 400232, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0643177032470703, "global_step": 400233, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.158883571624756, "global_step": 400234, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1080474853515625, "global_step": 400235, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.170595169067383, "global_step": 400236, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1413888931274414, "global_step": 400237, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.058340072631836, "global_step": 400238, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.200422763824463, "global_step": 400239, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0817599296569824, "global_step": 400240, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.077847957611084, "global_step": 400241, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1719746589660645, "global_step": 400242, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1319663524627686, "global_step": 400243, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1257011890411377, "global_step": 400244, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1080360412597656, "global_step": 400245, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0626444816589355, "global_step": 400246, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1282546520233154, "global_step": 400247, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1299729347229004, "global_step": 400248, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1012203693389893, "global_step": 400249, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0748438835144043, "global_step": 400250, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.253347158432007, "global_step": 400251, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.113510847091675, "global_step": 400252, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1510508060455322, "global_step": 400253, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.094778537750244, "global_step": 400254, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.032188653945923, "global_step": 400255, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1003401279449463, "global_step": 400256, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1598353385925293, "global_step": 400257, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0771427154541016, "global_step": 400258, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0835812091827393, "global_step": 400259, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1103625297546387, "global_step": 400260, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1617698669433594, "global_step": 400261, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1118030548095703, "global_step": 400262, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.151759386062622, "global_step": 400263, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.165640354156494, "global_step": 400264, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.084195613861084, "global_step": 400265, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1207973957061768, "global_step": 400266, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0444743633270264, "global_step": 400267, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1604533195495605, "global_step": 400268, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0924856662750244, "global_step": 400269, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0726876258850098, "global_step": 400270, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.210261821746826, "global_step": 400271, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1673989295959473, "global_step": 400272, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.125297784805298, "global_step": 400273, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0672683715820312, "global_step": 400274, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0580296516418457, "global_step": 400275, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.139843225479126, "global_step": 400276, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.158966064453125, "global_step": 400277, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0191938877105713, "global_step": 400278, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1035726070404053, "global_step": 400279, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0941879749298096, "global_step": 400280, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1471307277679443, "global_step": 400281, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1334259510040283, "global_step": 400282, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1116511821746826, "global_step": 400283, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.116274356842041, "global_step": 400284, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1227681636810303, "global_step": 400285, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0725014209747314, "global_step": 400286, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.100764513015747, "global_step": 400287, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.2012665271759033, "global_step": 400288, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.146286964416504, "global_step": 400289, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1127190589904785, "global_step": 400290, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0516886711120605, "global_step": 400291, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1148719787597656, "global_step": 400292, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.2008588314056396, "global_step": 400293, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.126814126968384, "global_step": 400294, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0861711502075195, "global_step": 400295, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.044273853302002, "global_step": 400296, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1276159286499023, "global_step": 400297, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.121028184890747, "global_step": 400298, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1029741764068604, "global_step": 400299, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1260104179382324, "global_step": 400300, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1008641719818115, "global_step": 400301, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.15750789642334, "global_step": 400302, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0428013801574707, "global_step": 400303, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1405296325683594, "global_step": 400304, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.149479627609253, "global_step": 400305, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0972437858581543, "global_step": 400306, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.105654001235962, "global_step": 400307, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.115736722946167, "global_step": 400308, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1495361328125, "global_step": 400309, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1361076831817627, "global_step": 400310, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0255603790283203, "global_step": 400311, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.125727415084839, "global_step": 400312, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.185401201248169, "global_step": 400313, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1743650436401367, "global_step": 400314, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1559150218963623, "global_step": 400315, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0889077186584473, "global_step": 400316, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.15759539604187, "global_step": 400317, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0842018127441406, "global_step": 400318, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.057703971862793, "global_step": 400319, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1088578701019287, "global_step": 400320, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.2190654277801514, "global_step": 400321, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0974924564361572, "global_step": 400322, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.0433409214019775, "global_step": 400323, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.098902702331543, "global_step": 400324, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.138645887374878, "global_step": 400325, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.109909772872925, "global_step": 400326, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.1190474033355713, "global_step": 400327, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.135089635848999, "global_step": 400328, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.098337173461914, "global_step": 400329, "epoch": 762, "lr": 5e-05}
{"train_loss": 2.138519048690796, "global_step": 400330, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.031282901763916, "global_step": 400331, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0891661643981934, "global_step": 400332, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0368757247924805, "global_step": 400333, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0638842582702637, "global_step": 400334, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.046684980392456, "global_step": 400335, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.946855902671814, "global_step": 400336, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1093521118164062, "global_step": 400337, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.21354341506958, "global_step": 400338, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.063889265060425, "global_step": 400339, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0973989963531494, "global_step": 400340, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.096055507659912, "global_step": 400341, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.99966561794281, "global_step": 400342, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.134047508239746, "global_step": 400343, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.124998092651367, "global_step": 400344, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0744922161102295, "global_step": 400345, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0704586505889893, "global_step": 400346, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1312410831451416, "global_step": 400347, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1333956718444824, "global_step": 400348, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.152348041534424, "global_step": 400349, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.031834363937378, "global_step": 400350, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.114264726638794, "global_step": 400351, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.05522084236145, "global_step": 400352, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.020813226699829, "global_step": 400353, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1158344745635986, "global_step": 400354, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.025682210922241, "global_step": 400355, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.153402090072632, "global_step": 400356, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0171778202056885, "global_step": 400357, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.125257968902588, "global_step": 400358, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.2050795555114746, "global_step": 400359, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0656020641326904, "global_step": 400360, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1368329524993896, "global_step": 400361, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.070091485977173, "global_step": 400362, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0971341133117676, "global_step": 400363, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.190500259399414, "global_step": 400364, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.081082820892334, "global_step": 400365, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1462888717651367, "global_step": 400366, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1031901836395264, "global_step": 400367, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0241360664367676, "global_step": 400368, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.084238052368164, "global_step": 400369, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0638427734375, "global_step": 400370, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1213362216949463, "global_step": 400371, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0635414123535156, "global_step": 400372, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1052958965301514, "global_step": 400373, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.9948426485061646, "global_step": 400374, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1751203536987305, "global_step": 400375, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0944769382476807, "global_step": 400376, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.036677598953247, "global_step": 400377, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1002867221832275, "global_step": 400378, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.00063157081604, "global_step": 400379, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0603866577148438, "global_step": 400380, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1000595092773438, "global_step": 400381, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0897748470306396, "global_step": 400382, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.124560832977295, "global_step": 400383, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.189293146133423, "global_step": 400384, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.047316789627075, "global_step": 400385, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0837113857269287, "global_step": 400386, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0085086822509766, "global_step": 400387, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.087635040283203, "global_step": 400388, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0924181938171387, "global_step": 400389, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.112765312194824, "global_step": 400390, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0989058017730713, "global_step": 400391, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.153797149658203, "global_step": 400392, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.9957400560379028, "global_step": 400393, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.054828405380249, "global_step": 400394, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0436599254608154, "global_step": 400395, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0970473289489746, "global_step": 400396, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.130782127380371, "global_step": 400397, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1060068607330322, "global_step": 400398, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0855419635772705, "global_step": 400399, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.123495578765869, "global_step": 400400, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.089334011077881, "global_step": 400401, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.094417095184326, "global_step": 400402, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0386409759521484, "global_step": 400403, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1121292114257812, "global_step": 400404, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.196979284286499, "global_step": 400405, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.105618953704834, "global_step": 400406, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.115617513656616, "global_step": 400407, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.9768637418746948, "global_step": 400408, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1345467567443848, "global_step": 400409, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1783676147460938, "global_step": 400410, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0858352184295654, "global_step": 400411, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0761306285858154, "global_step": 400412, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.175522804260254, "global_step": 400413, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.103780746459961, "global_step": 400414, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1495308876037598, "global_step": 400415, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1276581287384033, "global_step": 400416, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.028376579284668, "global_step": 400417, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.046281337738037, "global_step": 400418, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.025103807449341, "global_step": 400419, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.065704822540283, "global_step": 400420, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.127439260482788, "global_step": 400421, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.084721803665161, "global_step": 400422, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0879669189453125, "global_step": 400423, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1768643856048584, "global_step": 400424, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1208395957946777, "global_step": 400425, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0599613189697266, "global_step": 400426, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.122685432434082, "global_step": 400427, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0553793907165527, "global_step": 400428, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1389641761779785, "global_step": 400429, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1323273181915283, "global_step": 400430, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.158780813217163, "global_step": 400431, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.137876272201538, "global_step": 400432, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1031665802001953, "global_step": 400433, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.033783197402954, "global_step": 400434, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0876545906066895, "global_step": 400435, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.074633836746216, "global_step": 400436, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.081880807876587, "global_step": 400437, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.9761197566986084, "global_step": 400438, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.071319341659546, "global_step": 400439, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.114366292953491, "global_step": 400440, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0686113834381104, "global_step": 400441, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0318105220794678, "global_step": 400442, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1516449451446533, "global_step": 400443, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.076846122741699, "global_step": 400444, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.100977659225464, "global_step": 400445, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0834007263183594, "global_step": 400446, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1227500438690186, "global_step": 400447, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1496284008026123, "global_step": 400448, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0967156887054443, "global_step": 400449, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.2244911193847656, "global_step": 400450, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.005282402038574, "global_step": 400451, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0618369579315186, "global_step": 400452, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.136483907699585, "global_step": 400453, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0632011890411377, "global_step": 400454, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1071746349334717, "global_step": 400455, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.065391778945923, "global_step": 400456, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0269548892974854, "global_step": 400457, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.079993486404419, "global_step": 400458, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1003103256225586, "global_step": 400459, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.9672976732254028, "global_step": 400460, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0849130153656006, "global_step": 400461, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0689167976379395, "global_step": 400462, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.173434257507324, "global_step": 400463, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.019814968109131, "global_step": 400464, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0366833209991455, "global_step": 400465, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.2257845401763916, "global_step": 400466, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0929672718048096, "global_step": 400467, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.9473029375076294, "global_step": 400468, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.037506341934204, "global_step": 400469, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.179905652999878, "global_step": 400470, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.2198598384857178, "global_step": 400471, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1145944595336914, "global_step": 400472, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.127732276916504, "global_step": 400473, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0997445583343506, "global_step": 400474, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.049957275390625, "global_step": 400475, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.093277931213379, "global_step": 400476, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.121006488800049, "global_step": 400477, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.022048234939575, "global_step": 400478, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1304173469543457, "global_step": 400479, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.017267942428589, "global_step": 400480, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1683242321014404, "global_step": 400481, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0895376205444336, "global_step": 400482, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1384572982788086, "global_step": 400483, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.135380983352661, "global_step": 400484, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0264463424682617, "global_step": 400485, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.134737730026245, "global_step": 400486, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0190441608428955, "global_step": 400487, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0836987495422363, "global_step": 400488, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1385443210601807, "global_step": 400489, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.144761085510254, "global_step": 400490, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.119924306869507, "global_step": 400491, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.2534732818603516, "global_step": 400492, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.076833486557007, "global_step": 400493, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.108234405517578, "global_step": 400494, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0521910190582275, "global_step": 400495, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.038402557373047, "global_step": 400496, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.107942581176758, "global_step": 400497, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.03531551361084, "global_step": 400498, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.05502986907959, "global_step": 400499, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.093008041381836, "global_step": 400500, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1115188598632812, "global_step": 400501, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.111314296722412, "global_step": 400502, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.00193452835083, "global_step": 400503, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.2115278244018555, "global_step": 400504, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.071063756942749, "global_step": 400505, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0930516719818115, "global_step": 400506, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.120615005493164, "global_step": 400507, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1384823322296143, "global_step": 400508, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1191563606262207, "global_step": 400509, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.05352783203125, "global_step": 400510, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.055070638656616, "global_step": 400511, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.09226655960083, "global_step": 400512, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0557408332824707, "global_step": 400513, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.054497480392456, "global_step": 400514, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.128821611404419, "global_step": 400515, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1345975399017334, "global_step": 400516, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.993175745010376, "global_step": 400517, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.11445689201355, "global_step": 400518, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.14426326751709, "global_step": 400519, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0925371646881104, "global_step": 400520, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0119166374206543, "global_step": 400521, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.101975202560425, "global_step": 400522, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.156599998474121, "global_step": 400523, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0851690769195557, "global_step": 400524, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.187401294708252, "global_step": 400525, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.205530881881714, "global_step": 400526, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1099038124084473, "global_step": 400527, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.112389087677002, "global_step": 400528, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1066060066223145, "global_step": 400529, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1066293716430664, "global_step": 400530, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0661275386810303, "global_step": 400531, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.148265838623047, "global_step": 400532, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0596764087677, "global_step": 400533, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.104100227355957, "global_step": 400534, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1471526622772217, "global_step": 400535, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1084322929382324, "global_step": 400536, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1183176040649414, "global_step": 400537, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0279464721679688, "global_step": 400538, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.9973199367523193, "global_step": 400539, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1883227825164795, "global_step": 400540, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1172802448272705, "global_step": 400541, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1441965103149414, "global_step": 400542, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0221059322357178, "global_step": 400543, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0341084003448486, "global_step": 400544, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.132586717605591, "global_step": 400545, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.006783962249756, "global_step": 400546, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1034159660339355, "global_step": 400547, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1766796112060547, "global_step": 400548, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1003522872924805, "global_step": 400549, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0439846515655518, "global_step": 400550, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.212019920349121, "global_step": 400551, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0575313568115234, "global_step": 400552, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.138216972351074, "global_step": 400553, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0552310943603516, "global_step": 400554, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0981295108795166, "global_step": 400555, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.142148494720459, "global_step": 400556, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0707902908325195, "global_step": 400557, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0441956520080566, "global_step": 400558, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1487772464752197, "global_step": 400559, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.129655599594116, "global_step": 400560, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1332671642303467, "global_step": 400561, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0451645851135254, "global_step": 400562, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1230525970458984, "global_step": 400563, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1698668003082275, "global_step": 400564, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.06801700592041, "global_step": 400565, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.194038152694702, "global_step": 400566, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.08040452003479, "global_step": 400567, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0118637084960938, "global_step": 400568, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1203408241271973, "global_step": 400569, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.136509656906128, "global_step": 400570, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.123600721359253, "global_step": 400571, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1111602783203125, "global_step": 400572, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.087036371231079, "global_step": 400573, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.125208616256714, "global_step": 400574, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.9647377729415894, "global_step": 400575, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1269969940185547, "global_step": 400576, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.214846134185791, "global_step": 400577, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1376283168792725, "global_step": 400578, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.124274730682373, "global_step": 400579, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.107712984085083, "global_step": 400580, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1149277687072754, "global_step": 400581, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.063817024230957, "global_step": 400582, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.137925386428833, "global_step": 400583, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0361382961273193, "global_step": 400584, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0875890254974365, "global_step": 400585, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.031935930252075, "global_step": 400586, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0431830883026123, "global_step": 400587, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.031010389328003, "global_step": 400588, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.125556468963623, "global_step": 400589, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1240599155426025, "global_step": 400590, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0067391395568848, "global_step": 400591, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.076052188873291, "global_step": 400592, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.167257785797119, "global_step": 400593, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0827183723449707, "global_step": 400594, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0431902408599854, "global_step": 400595, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1379330158233643, "global_step": 400596, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.037027597427368, "global_step": 400597, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.132232189178467, "global_step": 400598, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0666980743408203, "global_step": 400599, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0696353912353516, "global_step": 400600, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.137934446334839, "global_step": 400601, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.085442543029785, "global_step": 400602, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.068594455718994, "global_step": 400603, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.110531806945801, "global_step": 400604, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0741305351257324, "global_step": 400605, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0550143718719482, "global_step": 400606, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0298118591308594, "global_step": 400607, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1435859203338623, "global_step": 400608, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.9871799945831299, "global_step": 400609, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1813557147979736, "global_step": 400610, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0854718685150146, "global_step": 400611, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.115736961364746, "global_step": 400612, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.178804397583008, "global_step": 400613, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.064987897872925, "global_step": 400614, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0715720653533936, "global_step": 400615, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.049971103668213, "global_step": 400616, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0882821083068848, "global_step": 400617, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.087083578109741, "global_step": 400618, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0861740112304688, "global_step": 400619, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.095571756362915, "global_step": 400620, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.039924144744873, "global_step": 400621, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1261658668518066, "global_step": 400622, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0517868995666504, "global_step": 400623, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0911741256713867, "global_step": 400624, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0702147483825684, "global_step": 400625, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0408551692962646, "global_step": 400626, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.08858323097229, "global_step": 400627, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1022908687591553, "global_step": 400628, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1076390743255615, "global_step": 400629, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.171121597290039, "global_step": 400630, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1649272441864014, "global_step": 400631, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0893945693969727, "global_step": 400632, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.075775384902954, "global_step": 400633, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1576461791992188, "global_step": 400634, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.184053897857666, "global_step": 400635, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0229082107543945, "global_step": 400636, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.080050468444824, "global_step": 400637, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0490269660949707, "global_step": 400638, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.2300052642822266, "global_step": 400639, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.033738136291504, "global_step": 400640, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0325207710266113, "global_step": 400641, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.15484619140625, "global_step": 400642, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1132254600524902, "global_step": 400643, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1929826736450195, "global_step": 400644, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1804211139678955, "global_step": 400645, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0955212116241455, "global_step": 400646, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1677725315093994, "global_step": 400647, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.091549873352051, "global_step": 400648, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1401355266571045, "global_step": 400649, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.064345359802246, "global_step": 400650, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.103689670562744, "global_step": 400651, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1105892658233643, "global_step": 400652, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.107103109359741, "global_step": 400653, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1853444576263428, "global_step": 400654, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0487611293792725, "global_step": 400655, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0032002925872803, "global_step": 400656, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.101048707962036, "global_step": 400657, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.118661880493164, "global_step": 400658, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0758249759674072, "global_step": 400659, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1451196670532227, "global_step": 400660, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0578601360321045, "global_step": 400661, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.029933214187622, "global_step": 400662, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.038551092147827, "global_step": 400663, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1094233989715576, "global_step": 400664, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.9665179252624512, "global_step": 400665, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.057764768600464, "global_step": 400666, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1369271278381348, "global_step": 400667, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.136324644088745, "global_step": 400668, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.202338218688965, "global_step": 400669, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.141956090927124, "global_step": 400670, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0984017848968506, "global_step": 400671, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.079894781112671, "global_step": 400672, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.9708032608032227, "global_step": 400673, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0960261821746826, "global_step": 400674, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.2268238067626953, "global_step": 400675, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.123579502105713, "global_step": 400676, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1498029232025146, "global_step": 400677, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.115097761154175, "global_step": 400678, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1476705074310303, "global_step": 400679, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.125300884246826, "global_step": 400680, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0393223762512207, "global_step": 400681, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0722548961639404, "global_step": 400682, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.126418113708496, "global_step": 400683, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0316696166992188, "global_step": 400684, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1026058197021484, "global_step": 400685, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1565771102905273, "global_step": 400686, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1068596839904785, "global_step": 400687, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0786030292510986, "global_step": 400688, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.077202081680298, "global_step": 400689, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.165161371231079, "global_step": 400690, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1531479358673096, "global_step": 400691, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.088787317276001, "global_step": 400692, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.156870126724243, "global_step": 400693, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1747210025787354, "global_step": 400694, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0833210945129395, "global_step": 400695, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1432411670684814, "global_step": 400696, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.144554615020752, "global_step": 400697, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1194281578063965, "global_step": 400698, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.131524085998535, "global_step": 400699, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1221821308135986, "global_step": 400700, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0817551612854004, "global_step": 400701, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.051300287246704, "global_step": 400702, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.000001907348633, "global_step": 400703, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0765023231506348, "global_step": 400704, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0765902996063232, "global_step": 400705, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1013457775115967, "global_step": 400706, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0441644191741943, "global_step": 400707, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.114000082015991, "global_step": 400708, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.108912229537964, "global_step": 400709, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1263303756713867, "global_step": 400710, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0463786125183105, "global_step": 400711, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.084857702255249, "global_step": 400712, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1272120475769043, "global_step": 400713, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0454776287078857, "global_step": 400714, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.074779748916626, "global_step": 400715, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1247735023498535, "global_step": 400716, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0893990993499756, "global_step": 400717, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.138920307159424, "global_step": 400718, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1324551105499268, "global_step": 400719, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.178396463394165, "global_step": 400720, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0768942832946777, "global_step": 400721, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0969107151031494, "global_step": 400722, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1096441745758057, "global_step": 400723, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1112308502197266, "global_step": 400724, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0942022800445557, "global_step": 400725, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0154120922088623, "global_step": 400726, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.113191604614258, "global_step": 400727, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0826525688171387, "global_step": 400728, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.045377016067505, "global_step": 400729, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0814270973205566, "global_step": 400730, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0893454551696777, "global_step": 400731, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.122738838195801, "global_step": 400732, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.012747049331665, "global_step": 400733, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0752017498016357, "global_step": 400734, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0738749504089355, "global_step": 400735, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1152729988098145, "global_step": 400736, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.09299373626709, "global_step": 400737, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0315282344818115, "global_step": 400738, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.120194673538208, "global_step": 400739, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.111654281616211, "global_step": 400740, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.100452184677124, "global_step": 400741, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.084899663925171, "global_step": 400742, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0820391178131104, "global_step": 400743, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0800211429595947, "global_step": 400744, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.08343768119812, "global_step": 400745, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1497488021850586, "global_step": 400746, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.094496250152588, "global_step": 400747, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.116821050643921, "global_step": 400748, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.139622211456299, "global_step": 400749, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0354437828063965, "global_step": 400750, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1358225345611572, "global_step": 400751, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0975747108459473, "global_step": 400752, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0809028148651123, "global_step": 400753, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1516740322113037, "global_step": 400754, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0803732872009277, "global_step": 400755, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.10646915435791, "global_step": 400756, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0122227668762207, "global_step": 400757, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.05269455909729, "global_step": 400758, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1799137592315674, "global_step": 400759, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.07320237159729, "global_step": 400760, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1422617435455322, "global_step": 400761, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0416526794433594, "global_step": 400762, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.03411602973938, "global_step": 400763, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1170501708984375, "global_step": 400764, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.092952251434326, "global_step": 400765, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1536450386047363, "global_step": 400766, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.072472095489502, "global_step": 400767, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.144810438156128, "global_step": 400768, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1252875328063965, "global_step": 400769, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0937306880950928, "global_step": 400770, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.136364698410034, "global_step": 400771, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.088571310043335, "global_step": 400772, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0697519779205322, "global_step": 400773, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1028130054473877, "global_step": 400774, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0500545501708984, "global_step": 400775, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.120108127593994, "global_step": 400776, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.02252459526062, "global_step": 400777, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0980963706970215, "global_step": 400778, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.099440574645996, "global_step": 400779, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.130723476409912, "global_step": 400780, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.126863479614258, "global_step": 400781, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0530953407287598, "global_step": 400782, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.105057954788208, "global_step": 400783, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1243255138397217, "global_step": 400784, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.147401809692383, "global_step": 400785, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1344985961914062, "global_step": 400786, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1058053970336914, "global_step": 400787, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0935704708099365, "global_step": 400788, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0824248790740967, "global_step": 400789, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0057175159454346, "global_step": 400790, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.091416358947754, "global_step": 400791, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0345458984375, "global_step": 400792, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.9922734498977661, "global_step": 400793, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1595096588134766, "global_step": 400794, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.069988965988159, "global_step": 400795, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1569511890411377, "global_step": 400796, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1092591285705566, "global_step": 400797, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.062642812728882, "global_step": 400798, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1332528591156006, "global_step": 400799, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.200575351715088, "global_step": 400800, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.140421152114868, "global_step": 400801, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.12317156791687, "global_step": 400802, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0788731575012207, "global_step": 400803, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1394059658050537, "global_step": 400804, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0491533279418945, "global_step": 400805, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.10504412651062, "global_step": 400806, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1620965003967285, "global_step": 400807, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0855562686920166, "global_step": 400808, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.045746326446533, "global_step": 400809, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.047436475753784, "global_step": 400810, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1306142807006836, "global_step": 400811, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0844054222106934, "global_step": 400812, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0796260833740234, "global_step": 400813, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1453850269317627, "global_step": 400814, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.067626953125, "global_step": 400815, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1403651237487793, "global_step": 400816, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1609745025634766, "global_step": 400817, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1570334434509277, "global_step": 400818, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.110253095626831, "global_step": 400819, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.136350154876709, "global_step": 400820, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0655393600463867, "global_step": 400821, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1082983016967773, "global_step": 400822, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.040024995803833, "global_step": 400823, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.092846155166626, "global_step": 400824, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0451037883758545, "global_step": 400825, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0913162231445312, "global_step": 400826, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.004068374633789, "global_step": 400827, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.045295476913452, "global_step": 400828, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1053993701934814, "global_step": 400829, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0779950618743896, "global_step": 400830, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.055673122406006, "global_step": 400831, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.9807829856872559, "global_step": 400832, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1654140949249268, "global_step": 400833, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0398709774017334, "global_step": 400834, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0719990730285645, "global_step": 400835, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.074906587600708, "global_step": 400836, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0484437942504883, "global_step": 400837, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0949034690856934, "global_step": 400838, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0314533710479736, "global_step": 400839, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.159939765930176, "global_step": 400840, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0903637409210205, "global_step": 400841, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.020185708999634, "global_step": 400842, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1404974460601807, "global_step": 400843, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0848326683044434, "global_step": 400844, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.132676601409912, "global_step": 400845, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.039353370666504, "global_step": 400846, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.090489625930786, "global_step": 400847, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.094532012939453, "global_step": 400848, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.053192138671875, "global_step": 400849, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.174751043319702, "global_step": 400850, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.111513376235962, "global_step": 400851, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.086379051208496, "global_step": 400852, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1217880249023438, "global_step": 400853, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0641205310821533, "global_step": 400854, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1188952922821045, "global_step": 400855, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.105156898498535, "global_step": 400856, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.017991542816162, "global_step": 400857, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1506898403167725, "global_step": 400858, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1209397315979004, "global_step": 400859, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1817662715911865, "global_step": 400860, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.101372480392456, "global_step": 400861, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1401822566986084, "global_step": 400862, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.17919659614563, "global_step": 400863, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.078580856323242, "global_step": 400864, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1181821823120117, "global_step": 400865, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.119258403778076, "global_step": 400866, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0122926235198975, "global_step": 400867, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.156796455383301, "global_step": 400868, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.062084913253784, "global_step": 400869, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0650336742401123, "global_step": 400870, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0263314247131348, "global_step": 400871, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.140930652618408, "global_step": 400872, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.197904348373413, "global_step": 400873, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1303443908691406, "global_step": 400874, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.997273564338684, "global_step": 400875, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1208174228668213, "global_step": 400876, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0694313049316406, "global_step": 400877, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0528817176818848, "global_step": 400878, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1138854026794434, "global_step": 400879, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.045579195022583, "global_step": 400880, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0960302352905273, "global_step": 400881, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.03969669342041, "global_step": 400882, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0932435989379883, "global_step": 400883, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.185734272003174, "global_step": 400884, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.120875358581543, "global_step": 400885, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0880327224731445, "global_step": 400886, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0106804370880127, "global_step": 400887, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.089769124984741, "global_step": 400888, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0961177349090576, "global_step": 400889, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.033952236175537, "global_step": 400890, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.064446449279785, "global_step": 400891, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.134643316268921, "global_step": 400892, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1776070594787598, "global_step": 400893, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.087387800216675, "global_step": 400894, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1507961750030518, "global_step": 400895, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1258277893066406, "global_step": 400896, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.043942451477051, "global_step": 400897, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1018426418304443, "global_step": 400898, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.2140285968780518, "global_step": 400899, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0614020824432373, "global_step": 400900, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.14448881149292, "global_step": 400901, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.058075428009033, "global_step": 400902, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1721699237823486, "global_step": 400903, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1873888969421387, "global_step": 400904, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1061694622039795, "global_step": 400905, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1245861053466797, "global_step": 400906, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0945749282836914, "global_step": 400907, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0920116901397705, "global_step": 400908, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1754939556121826, "global_step": 400909, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0578455924987793, "global_step": 400910, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0177221298217773, "global_step": 400911, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1461427211761475, "global_step": 400912, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.118290424346924, "global_step": 400913, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0819365978240967, "global_step": 400914, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1453301906585693, "global_step": 400915, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.147080421447754, "global_step": 400916, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0767712593078613, "global_step": 400917, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1644818782806396, "global_step": 400918, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1445140838623047, "global_step": 400919, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.065159559249878, "global_step": 400920, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1466617584228516, "global_step": 400921, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.100611448287964, "global_step": 400922, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.080781936645508, "global_step": 400923, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0823264122009277, "global_step": 400924, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.160554885864258, "global_step": 400925, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.14493989944458, "global_step": 400926, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.044276475906372, "global_step": 400927, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0694332122802734, "global_step": 400928, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0555062294006348, "global_step": 400929, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.985177755355835, "global_step": 400930, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1881542205810547, "global_step": 400931, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0706589221954346, "global_step": 400932, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1536645889282227, "global_step": 400933, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.9619996547698975, "global_step": 400934, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0434205532073975, "global_step": 400935, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.011194944381714, "global_step": 400936, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.059776782989502, "global_step": 400937, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.127204418182373, "global_step": 400938, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.188167095184326, "global_step": 400939, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1104214191436768, "global_step": 400940, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.002157688140869, "global_step": 400941, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.115565776824951, "global_step": 400942, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.064878225326538, "global_step": 400943, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0798511505126953, "global_step": 400944, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.053309440612793, "global_step": 400945, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1446661949157715, "global_step": 400946, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0959396362304688, "global_step": 400947, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1146345138549805, "global_step": 400948, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0908591747283936, "global_step": 400949, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1582934856414795, "global_step": 400950, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0800418853759766, "global_step": 400951, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.030684232711792, "global_step": 400952, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.137413501739502, "global_step": 400953, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.9798955917358398, "global_step": 400954, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1087119579315186, "global_step": 400955, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0788867473602295, "global_step": 400956, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1128811836242676, "global_step": 400957, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0308961868286133, "global_step": 400958, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1440114974975586, "global_step": 400959, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.073377847671509, "global_step": 400960, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.109525680541992, "global_step": 400961, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0383102893829346, "global_step": 400962, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.069704294204712, "global_step": 400963, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.038743019104004, "global_step": 400964, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1141016483306885, "global_step": 400965, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.106837511062622, "global_step": 400966, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.124267578125, "global_step": 400967, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.066941738128662, "global_step": 400968, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0536246299743652, "global_step": 400969, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.149806022644043, "global_step": 400970, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.006579875946045, "global_step": 400971, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.200615882873535, "global_step": 400972, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.2327513694763184, "global_step": 400973, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0679972171783447, "global_step": 400974, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0740175247192383, "global_step": 400975, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0023720264434814, "global_step": 400976, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0379207134246826, "global_step": 400977, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.176255226135254, "global_step": 400978, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.107034921646118, "global_step": 400979, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0816221237182617, "global_step": 400980, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.120882749557495, "global_step": 400981, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.111778497695923, "global_step": 400982, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0383732318878174, "global_step": 400983, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.193384885787964, "global_step": 400984, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.160816192626953, "global_step": 400985, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.19113826751709, "global_step": 400986, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.094416379928589, "global_step": 400987, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0840420722961426, "global_step": 400988, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1784300804138184, "global_step": 400989, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0933871269226074, "global_step": 400990, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.142551898956299, "global_step": 400991, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1151578426361084, "global_step": 400992, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.119342803955078, "global_step": 400993, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0546720027923584, "global_step": 400994, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.111992120742798, "global_step": 400995, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.068660259246826, "global_step": 400996, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0282068252563477, "global_step": 400997, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.129525661468506, "global_step": 400998, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.100330352783203, "global_step": 400999, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1308200359344482, "global_step": 401000, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1169769763946533, "global_step": 401001, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0497171878814697, "global_step": 401002, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.038604974746704, "global_step": 401003, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.113243579864502, "global_step": 401004, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0768706798553467, "global_step": 401005, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1166481971740723, "global_step": 401006, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1377065181732178, "global_step": 401007, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0528242588043213, "global_step": 401008, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.11102032661438, "global_step": 401009, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0928499698638916, "global_step": 401010, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0833282470703125, "global_step": 401011, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1143624782562256, "global_step": 401012, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0906052589416504, "global_step": 401013, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1461338996887207, "global_step": 401014, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0893442630767822, "global_step": 401015, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0761942863464355, "global_step": 401016, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.240222454071045, "global_step": 401017, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.031238317489624, "global_step": 401018, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.985836148262024, "global_step": 401019, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0842316150665283, "global_step": 401020, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.116152286529541, "global_step": 401021, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1139681339263916, "global_step": 401022, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0996761322021484, "global_step": 401023, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0730738639831543, "global_step": 401024, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1550450325012207, "global_step": 401025, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.092317819595337, "global_step": 401026, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1021671295166016, "global_step": 401027, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.193049192428589, "global_step": 401028, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.110884428024292, "global_step": 401029, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0502591133117676, "global_step": 401030, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.224470853805542, "global_step": 401031, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.099616289138794, "global_step": 401032, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.076897144317627, "global_step": 401033, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1807358264923096, "global_step": 401034, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.126940965652466, "global_step": 401035, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.114189386367798, "global_step": 401036, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0899152755737305, "global_step": 401037, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.107450008392334, "global_step": 401038, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.094050407409668, "global_step": 401039, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1696181297302246, "global_step": 401040, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1517395973205566, "global_step": 401041, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0992770195007324, "global_step": 401042, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1524715423583984, "global_step": 401043, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.016301155090332, "global_step": 401044, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.06554913520813, "global_step": 401045, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1217403411865234, "global_step": 401046, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.138695240020752, "global_step": 401047, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1357274055480957, "global_step": 401048, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1019742488861084, "global_step": 401049, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1606338024139404, "global_step": 401050, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.052415609359741, "global_step": 401051, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0482754707336426, "global_step": 401052, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.12371563911438, "global_step": 401053, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1629092693328857, "global_step": 401054, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0749521255493164, "global_step": 401055, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1746082305908203, "global_step": 401056, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.042764902114868, "global_step": 401057, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0841948986053467, "global_step": 401058, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0154261589050293, "global_step": 401059, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.038642168045044, "global_step": 401060, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.186671733856201, "global_step": 401061, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.030219078063965, "global_step": 401062, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1202569007873535, "global_step": 401063, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0675675868988037, "global_step": 401064, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.089749813079834, "global_step": 401065, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0817975997924805, "global_step": 401066, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1994895935058594, "global_step": 401067, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1184234619140625, "global_step": 401068, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1669118404388428, "global_step": 401069, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1081647872924805, "global_step": 401070, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1750364303588867, "global_step": 401071, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1102235317230225, "global_step": 401072, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0633180141448975, "global_step": 401073, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1111695766448975, "global_step": 401074, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1281967163085938, "global_step": 401075, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0343375205993652, "global_step": 401076, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.080263137817383, "global_step": 401077, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1415815353393555, "global_step": 401078, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.094087839126587, "global_step": 401079, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.096388816833496, "global_step": 401080, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1181771755218506, "global_step": 401081, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0931038856506348, "global_step": 401082, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0911152362823486, "global_step": 401083, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.115154504776001, "global_step": 401084, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1391801834106445, "global_step": 401085, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1698079109191895, "global_step": 401086, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1242358684539795, "global_step": 401087, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1523494720458984, "global_step": 401088, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0712473392486572, "global_step": 401089, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0579349994659424, "global_step": 401090, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0604283809661865, "global_step": 401091, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.121609687805176, "global_step": 401092, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1566998958587646, "global_step": 401093, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1693027019500732, "global_step": 401094, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1644082069396973, "global_step": 401095, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0965731143951416, "global_step": 401096, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1551358699798584, "global_step": 401097, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1059813499450684, "global_step": 401098, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.072308301925659, "global_step": 401099, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0989506244659424, "global_step": 401100, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1361396312713623, "global_step": 401101, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0325193405151367, "global_step": 401102, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.135190725326538, "global_step": 401103, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1291115283966064, "global_step": 401104, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1124234199523926, "global_step": 401105, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0749285221099854, "global_step": 401106, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.019310712814331, "global_step": 401107, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0685253143310547, "global_step": 401108, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0669283866882324, "global_step": 401109, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0765044689178467, "global_step": 401110, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0996007919311523, "global_step": 401111, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1545631885528564, "global_step": 401112, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0640745162963867, "global_step": 401113, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.044792890548706, "global_step": 401114, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.14094614982605, "global_step": 401115, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1185221672058105, "global_step": 401116, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0567595958709717, "global_step": 401117, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1176090240478516, "global_step": 401118, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0631461143493652, "global_step": 401119, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.076235771179199, "global_step": 401120, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0539889335632324, "global_step": 401121, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0607004165649414, "global_step": 401122, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.9908815622329712, "global_step": 401123, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.101407766342163, "global_step": 401124, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.108752965927124, "global_step": 401125, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0899784564971924, "global_step": 401126, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0923361778259277, "global_step": 401127, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1670429706573486, "global_step": 401128, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0921859741210938, "global_step": 401129, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.030486583709717, "global_step": 401130, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0224995613098145, "global_step": 401131, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.149484395980835, "global_step": 401132, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1861422061920166, "global_step": 401133, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1076440811157227, "global_step": 401134, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.09688663482666, "global_step": 401135, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.099618434906006, "global_step": 401136, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0394222736358643, "global_step": 401137, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1174633502960205, "global_step": 401138, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1572113037109375, "global_step": 401139, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.116103172302246, "global_step": 401140, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.091022491455078, "global_step": 401141, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1066884994506836, "global_step": 401142, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.2211966514587402, "global_step": 401143, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1452689170837402, "global_step": 401144, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.182126045227051, "global_step": 401145, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.014638900756836, "global_step": 401146, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0055923461914062, "global_step": 401147, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.181568145751953, "global_step": 401148, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.025090456008911, "global_step": 401149, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.085275888442993, "global_step": 401150, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.148115634918213, "global_step": 401151, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1290438175201416, "global_step": 401152, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.038144826889038, "global_step": 401153, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.069275379180908, "global_step": 401154, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.164130210876465, "global_step": 401155, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.127333164215088, "global_step": 401156, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.076979875564575, "global_step": 401157, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0314619541168213, "global_step": 401158, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.081320285797119, "global_step": 401159, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.169468641281128, "global_step": 401160, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.147228956222534, "global_step": 401161, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1109657287597656, "global_step": 401162, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.138990640640259, "global_step": 401163, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.13815975189209, "global_step": 401164, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1158382892608643, "global_step": 401165, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1954495906829834, "global_step": 401166, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.137629270553589, "global_step": 401167, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.2336056232452393, "global_step": 401168, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.058018684387207, "global_step": 401169, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0424814224243164, "global_step": 401170, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.085991144180298, "global_step": 401171, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.013298749923706, "global_step": 401172, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.134549856185913, "global_step": 401173, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.158932685852051, "global_step": 401174, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1218440532684326, "global_step": 401175, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.033682107925415, "global_step": 401176, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.129077911376953, "global_step": 401177, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.113649606704712, "global_step": 401178, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.144622325897217, "global_step": 401179, "epoch": 763, "lr": 5e-05}
{"train_loss": 1.9939002990722656, "global_step": 401180, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.169172763824463, "global_step": 401181, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0786612033843994, "global_step": 401182, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0322442054748535, "global_step": 401183, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.164191722869873, "global_step": 401184, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.079530715942383, "global_step": 401185, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.086456060409546, "global_step": 401186, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1049296855926514, "global_step": 401187, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1689202785491943, "global_step": 401188, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.186732053756714, "global_step": 401189, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.101477861404419, "global_step": 401190, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0283477306365967, "global_step": 401191, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0430328845977783, "global_step": 401192, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0726053714752197, "global_step": 401193, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.110100269317627, "global_step": 401194, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0966055393218994, "global_step": 401195, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1251072883605957, "global_step": 401196, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0912623405456543, "global_step": 401197, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0861403942108154, "global_step": 401198, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.12426495552063, "global_step": 401199, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.113751173019409, "global_step": 401200, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.044086456298828, "global_step": 401201, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.069455862045288, "global_step": 401202, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0963521003723145, "global_step": 401203, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0775513648986816, "global_step": 401204, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.13472843170166, "global_step": 401205, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0358428955078125, "global_step": 401206, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.2040579319000244, "global_step": 401207, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1135172843933105, "global_step": 401208, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.062108039855957, "global_step": 401209, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0642549991607666, "global_step": 401210, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1475985050201416, "global_step": 401211, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.152801513671875, "global_step": 401212, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0398521423339844, "global_step": 401213, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1104397773742676, "global_step": 401214, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0847766399383545, "global_step": 401215, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.079540252685547, "global_step": 401216, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1579904556274414, "global_step": 401217, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1153085231781006, "global_step": 401218, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0758070945739746, "global_step": 401219, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0828158855438232, "global_step": 401220, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0290842056274414, "global_step": 401221, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.085996627807617, "global_step": 401222, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.054872751235962, "global_step": 401223, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0301342010498047, "global_step": 401224, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0792365074157715, "global_step": 401225, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0704336166381836, "global_step": 401226, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0805718898773193, "global_step": 401227, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.101628541946411, "global_step": 401228, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0757181644439697, "global_step": 401229, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.099789619445801, "global_step": 401230, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.136127471923828, "global_step": 401231, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1392343044281006, "global_step": 401232, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0354857444763184, "global_step": 401233, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.149146556854248, "global_step": 401234, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.093207359313965, "global_step": 401235, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.180417537689209, "global_step": 401236, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0849032402038574, "global_step": 401237, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.114140510559082, "global_step": 401238, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1566202640533447, "global_step": 401239, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0417640209198, "global_step": 401240, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0763914585113525, "global_step": 401241, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.084282398223877, "global_step": 401242, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.116570472717285, "global_step": 401243, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.086840867996216, "global_step": 401244, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.111231803894043, "global_step": 401245, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1253066062927246, "global_step": 401246, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0488154888153076, "global_step": 401247, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.110055923461914, "global_step": 401248, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.091784954071045, "global_step": 401249, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.189206838607788, "global_step": 401250, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.062666893005371, "global_step": 401251, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.138542413711548, "global_step": 401252, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1611359119415283, "global_step": 401253, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.222620964050293, "global_step": 401254, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.2101807594299316, "global_step": 401255, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.088289499282837, "global_step": 401256, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1151275634765625, "global_step": 401257, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.09515643119812, "global_step": 401258, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0855331420898438, "global_step": 401259, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0508296489715576, "global_step": 401260, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.102355718612671, "global_step": 401261, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1038193702697754, "global_step": 401262, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0687594413757324, "global_step": 401263, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1577203273773193, "global_step": 401264, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1151115894317627, "global_step": 401265, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.119248867034912, "global_step": 401266, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.084707021713257, "global_step": 401267, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1041011810302734, "global_step": 401268, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.097083568572998, "global_step": 401269, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.182953357696533, "global_step": 401270, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.080536365509033, "global_step": 401271, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.036039113998413, "global_step": 401272, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.095611333847046, "global_step": 401273, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1691434383392334, "global_step": 401274, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1130311489105225, "global_step": 401275, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1441917419433594, "global_step": 401276, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.06420636177063, "global_step": 401277, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0983433723449707, "global_step": 401278, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0339884757995605, "global_step": 401279, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.058537483215332, "global_step": 401280, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.123990535736084, "global_step": 401281, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1014158725738525, "global_step": 401282, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.173696517944336, "global_step": 401283, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1317343711853027, "global_step": 401284, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1340675354003906, "global_step": 401285, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.087961196899414, "global_step": 401286, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1232120990753174, "global_step": 401287, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0385618209838867, "global_step": 401288, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.137880802154541, "global_step": 401289, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1833128929138184, "global_step": 401290, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.1568634510040283, "global_step": 401291, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0725972652435303, "global_step": 401292, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.032158613204956, "global_step": 401293, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0903704166412354, "global_step": 401294, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0732131004333496, "global_step": 401295, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.2156708240509033, "global_step": 401296, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.0190534591674805, "global_step": 401297, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.098707675933838, "global_step": 401298, "epoch": 763, "lr": 5e-05}
{"train_loss": 2.121267795562744, "global_step": 401299, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.017198324203491, "global_step": 401300, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.188018321990967, "global_step": 401301, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0597128868103027, "global_step": 401302, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1646499633789062, "global_step": 401303, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1933624744415283, "global_step": 401304, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.152172565460205, "global_step": 401305, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.033024787902832, "global_step": 401306, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.163398265838623, "global_step": 401307, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1262333393096924, "global_step": 401308, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0527725219726562, "global_step": 401309, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.046557664871216, "global_step": 401310, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.105036497116089, "global_step": 401311, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0942673683166504, "global_step": 401312, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.15472674369812, "global_step": 401313, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0572526454925537, "global_step": 401314, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.124260902404785, "global_step": 401315, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0010852813720703, "global_step": 401316, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.090132236480713, "global_step": 401317, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0533647537231445, "global_step": 401318, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.044123888015747, "global_step": 401319, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.139465093612671, "global_step": 401320, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.9964357614517212, "global_step": 401321, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0437381267547607, "global_step": 401322, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1323657035827637, "global_step": 401323, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0592150688171387, "global_step": 401324, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1126158237457275, "global_step": 401325, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0529420375823975, "global_step": 401326, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.121670722961426, "global_step": 401327, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.067655563354492, "global_step": 401328, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1281964778900146, "global_step": 401329, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0594632625579834, "global_step": 401330, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1102242469787598, "global_step": 401331, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0223286151885986, "global_step": 401332, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1123406887054443, "global_step": 401333, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0275721549987793, "global_step": 401334, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.123753309249878, "global_step": 401335, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.071343183517456, "global_step": 401336, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0858423709869385, "global_step": 401337, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1079916954040527, "global_step": 401338, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0458314418792725, "global_step": 401339, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1160359382629395, "global_step": 401340, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1121208667755127, "global_step": 401341, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0297346115112305, "global_step": 401342, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.126288890838623, "global_step": 401343, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1265480518341064, "global_step": 401344, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.126420021057129, "global_step": 401345, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.055058717727661, "global_step": 401346, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0140345096588135, "global_step": 401347, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0870656967163086, "global_step": 401348, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0541367530822754, "global_step": 401349, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0816214084625244, "global_step": 401350, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.097276449203491, "global_step": 401351, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0107147693634033, "global_step": 401352, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0932912826538086, "global_step": 401353, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.080352544784546, "global_step": 401354, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.067915678024292, "global_step": 401355, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.124655246734619, "global_step": 401356, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.149433135986328, "global_step": 401357, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.038538932800293, "global_step": 401358, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.996293544769287, "global_step": 401359, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1088502407073975, "global_step": 401360, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1646127700805664, "global_step": 401361, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.150601387023926, "global_step": 401362, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.057860851287842, "global_step": 401363, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.073336362838745, "global_step": 401364, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.11875057220459, "global_step": 401365, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.130070686340332, "global_step": 401366, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0835723876953125, "global_step": 401367, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.166425943374634, "global_step": 401368, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.9861838817596436, "global_step": 401369, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.023932933807373, "global_step": 401370, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.116504430770874, "global_step": 401371, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.133406639099121, "global_step": 401372, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1140847206115723, "global_step": 401373, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.175825595855713, "global_step": 401374, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0367064476013184, "global_step": 401375, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1425647735595703, "global_step": 401376, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.097163677215576, "global_step": 401377, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1514792442321777, "global_step": 401378, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.003113269805908, "global_step": 401379, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.060561418533325, "global_step": 401380, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0871946811676025, "global_step": 401381, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.115736484527588, "global_step": 401382, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.050105333328247, "global_step": 401383, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0652880668640137, "global_step": 401384, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.072256326675415, "global_step": 401385, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1190743446350098, "global_step": 401386, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0382938385009766, "global_step": 401387, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.11665678024292, "global_step": 401388, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.038482427597046, "global_step": 401389, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0912561416625977, "global_step": 401390, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.127586841583252, "global_step": 401391, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.024592638015747, "global_step": 401392, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1162781715393066, "global_step": 401393, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.2321786880493164, "global_step": 401394, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0496654510498047, "global_step": 401395, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0730018615722656, "global_step": 401396, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1222188472747803, "global_step": 401397, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1665191650390625, "global_step": 401398, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.088918924331665, "global_step": 401399, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.182387113571167, "global_step": 401400, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.121774911880493, "global_step": 401401, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.068713903427124, "global_step": 401402, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0573644638061523, "global_step": 401403, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.11043643951416, "global_step": 401404, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.12176513671875, "global_step": 401405, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.043853759765625, "global_step": 401406, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.117114305496216, "global_step": 401407, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.09017014503479, "global_step": 401408, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.088136911392212, "global_step": 401409, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.087912082672119, "global_step": 401410, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.113164186477661, "global_step": 401411, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.071462392807007, "global_step": 401412, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.041522979736328, "global_step": 401413, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1315503120422363, "global_step": 401414, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.079171657562256, "global_step": 401415, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.086503505706787, "global_step": 401416, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.042914390563965, "global_step": 401417, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.036409378051758, "global_step": 401418, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1275949478149414, "global_step": 401419, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.122182607650757, "global_step": 401420, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.114699363708496, "global_step": 401421, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.2049779891967773, "global_step": 401422, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.048736572265625, "global_step": 401423, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0905613899230957, "global_step": 401424, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.05437970161438, "global_step": 401425, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1113526821136475, "global_step": 401426, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1020443439483643, "global_step": 401427, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.9782936573028564, "global_step": 401428, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0375521183013916, "global_step": 401429, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.112572431564331, "global_step": 401430, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1518337726593018, "global_step": 401431, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.025709629058838, "global_step": 401432, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1060009002685547, "global_step": 401433, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.085994243621826, "global_step": 401434, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1465301513671875, "global_step": 401435, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1131420135498047, "global_step": 401436, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1205685138702393, "global_step": 401437, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1387805938720703, "global_step": 401438, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1112289428710938, "global_step": 401439, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.139777898788452, "global_step": 401440, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.07330060005188, "global_step": 401441, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0123777389526367, "global_step": 401442, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.120384454727173, "global_step": 401443, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.176114559173584, "global_step": 401444, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.025646209716797, "global_step": 401445, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.072457790374756, "global_step": 401446, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0951781272888184, "global_step": 401447, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1098926067352295, "global_step": 401448, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.076115131378174, "global_step": 401449, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1210317611694336, "global_step": 401450, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.088905096054077, "global_step": 401451, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0808417797088623, "global_step": 401452, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0778491497039795, "global_step": 401453, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.11967134475708, "global_step": 401454, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.035569906234741, "global_step": 401455, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0504257678985596, "global_step": 401456, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.9689252376556396, "global_step": 401457, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.12203049659729, "global_step": 401458, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1363773345947266, "global_step": 401459, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0184459686279297, "global_step": 401460, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0765292644500732, "global_step": 401461, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.126835823059082, "global_step": 401462, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0488297939300537, "global_step": 401463, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1013784408569336, "global_step": 401464, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0949010848999023, "global_step": 401465, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.9778351783752441, "global_step": 401466, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.091698169708252, "global_step": 401467, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1048789024353027, "global_step": 401468, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.107483386993408, "global_step": 401469, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.055471897125244, "global_step": 401470, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.074333429336548, "global_step": 401471, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.053805112838745, "global_step": 401472, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0679266452789307, "global_step": 401473, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0569071769714355, "global_step": 401474, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1123483180999756, "global_step": 401475, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0567805767059326, "global_step": 401476, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0908358097076416, "global_step": 401477, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1470232009887695, "global_step": 401478, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.9932243824005127, "global_step": 401479, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.099065065383911, "global_step": 401480, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1390163898468018, "global_step": 401481, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.017331123352051, "global_step": 401482, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.110039234161377, "global_step": 401483, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1346821784973145, "global_step": 401484, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.069223165512085, "global_step": 401485, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1701161861419678, "global_step": 401486, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0174648761749268, "global_step": 401487, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1121535301208496, "global_step": 401488, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.064068078994751, "global_step": 401489, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0942881107330322, "global_step": 401490, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0834383964538574, "global_step": 401491, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.072309970855713, "global_step": 401492, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1001951694488525, "global_step": 401493, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0212695598602295, "global_step": 401494, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0515332221984863, "global_step": 401495, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1215789318084717, "global_step": 401496, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0612692832946777, "global_step": 401497, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1184544563293457, "global_step": 401498, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0402536392211914, "global_step": 401499, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1117780208587646, "global_step": 401500, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1367952823638916, "global_step": 401501, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.105496883392334, "global_step": 401502, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0012383460998535, "global_step": 401503, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0254082679748535, "global_step": 401504, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.034477472305298, "global_step": 401505, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0620899200439453, "global_step": 401506, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.182706832885742, "global_step": 401507, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1619865894317627, "global_step": 401508, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0583457946777344, "global_step": 401509, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1130223274230957, "global_step": 401510, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0645909309387207, "global_step": 401511, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.067793607711792, "global_step": 401512, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.130500316619873, "global_step": 401513, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.997782826423645, "global_step": 401514, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0420594215393066, "global_step": 401515, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1388092041015625, "global_step": 401516, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0103402137756348, "global_step": 401517, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1111249923706055, "global_step": 401518, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1161913871765137, "global_step": 401519, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.083937644958496, "global_step": 401520, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.14278507232666, "global_step": 401521, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0738606452941895, "global_step": 401522, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.089569091796875, "global_step": 401523, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0193090438842773, "global_step": 401524, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.200136184692383, "global_step": 401525, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.033682107925415, "global_step": 401526, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.046417474746704, "global_step": 401527, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.127568244934082, "global_step": 401528, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0568652153015137, "global_step": 401529, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0207300186157227, "global_step": 401530, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0612552165985107, "global_step": 401531, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.067567825317383, "global_step": 401532, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.077420711517334, "global_step": 401533, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.079399347305298, "global_step": 401534, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.13859224319458, "global_step": 401535, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.127145767211914, "global_step": 401536, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.188007116317749, "global_step": 401537, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0586180686950684, "global_step": 401538, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.100611448287964, "global_step": 401539, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0392892360687256, "global_step": 401540, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1741108894348145, "global_step": 401541, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1587014198303223, "global_step": 401542, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0624876022338867, "global_step": 401543, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.020185708999634, "global_step": 401544, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.121025562286377, "global_step": 401545, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0530405044555664, "global_step": 401546, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0585787296295166, "global_step": 401547, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1374263763427734, "global_step": 401548, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.162648916244507, "global_step": 401549, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0945746898651123, "global_step": 401550, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.108090877532959, "global_step": 401551, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.067535638809204, "global_step": 401552, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.9759236574172974, "global_step": 401553, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.016213893890381, "global_step": 401554, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1097583770751953, "global_step": 401555, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0747134685516357, "global_step": 401556, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.193376302719116, "global_step": 401557, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0432958602905273, "global_step": 401558, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.067760467529297, "global_step": 401559, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0849742889404297, "global_step": 401560, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.134258985519409, "global_step": 401561, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1746206283569336, "global_step": 401562, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1164839267730713, "global_step": 401563, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.987144112586975, "global_step": 401564, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0497682094573975, "global_step": 401565, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.116753101348877, "global_step": 401566, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0593910217285156, "global_step": 401567, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.2167465686798096, "global_step": 401568, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0579357147216797, "global_step": 401569, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0785865783691406, "global_step": 401570, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0846762657165527, "global_step": 401571, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.060549259185791, "global_step": 401572, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.124027729034424, "global_step": 401573, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1256117820739746, "global_step": 401574, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0733931064605713, "global_step": 401575, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.091374635696411, "global_step": 401576, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0478501319885254, "global_step": 401577, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.036168098449707, "global_step": 401578, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0757274627685547, "global_step": 401579, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.120305061340332, "global_step": 401580, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1429107189178467, "global_step": 401581, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0575037002563477, "global_step": 401582, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0957143306732178, "global_step": 401583, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0878944396972656, "global_step": 401584, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0244150161743164, "global_step": 401585, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.173851728439331, "global_step": 401586, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.064113140106201, "global_step": 401587, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.089387893676758, "global_step": 401588, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1442434787750244, "global_step": 401589, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.982100248336792, "global_step": 401590, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0766682624816895, "global_step": 401591, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1196980476379395, "global_step": 401592, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1191294193267822, "global_step": 401593, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.148102283477783, "global_step": 401594, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.015338897705078, "global_step": 401595, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.03171443939209, "global_step": 401596, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.2770872116088867, "global_step": 401597, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.116729259490967, "global_step": 401598, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.997436285018921, "global_step": 401599, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0716474056243896, "global_step": 401600, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.086108684539795, "global_step": 401601, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0976600646972656, "global_step": 401602, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.050967216491699, "global_step": 401603, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1482064723968506, "global_step": 401604, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1192853450775146, "global_step": 401605, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0418403148651123, "global_step": 401606, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0767505168914795, "global_step": 401607, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.093902349472046, "global_step": 401608, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.08862042427063, "global_step": 401609, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0922608375549316, "global_step": 401610, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.005608558654785, "global_step": 401611, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.135331630706787, "global_step": 401612, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.129692554473877, "global_step": 401613, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0937860012054443, "global_step": 401614, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0197389125823975, "global_step": 401615, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0605311393737793, "global_step": 401616, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.124307870864868, "global_step": 401617, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1649749279022217, "global_step": 401618, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1002213954925537, "global_step": 401619, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0707812309265137, "global_step": 401620, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0927321910858154, "global_step": 401621, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.095767021179199, "global_step": 401622, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1762845516204834, "global_step": 401623, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.05938720703125, "global_step": 401624, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0708796977996826, "global_step": 401625, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.07843279838562, "global_step": 401626, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0759620666503906, "global_step": 401627, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.049348831176758, "global_step": 401628, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.070084810256958, "global_step": 401629, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1338582038879395, "global_step": 401630, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0388872623443604, "global_step": 401631, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.051699638366699, "global_step": 401632, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0933635234832764, "global_step": 401633, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.058699369430542, "global_step": 401634, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0651447772979736, "global_step": 401635, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1128079891204834, "global_step": 401636, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.167060375213623, "global_step": 401637, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0751452445983887, "global_step": 401638, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0858421325683594, "global_step": 401639, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1104137897491455, "global_step": 401640, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.2126431465148926, "global_step": 401641, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1062304973602295, "global_step": 401642, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.127948045730591, "global_step": 401643, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0933501720428467, "global_step": 401644, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.121729850769043, "global_step": 401645, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.167194128036499, "global_step": 401646, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.02535080909729, "global_step": 401647, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.017799139022827, "global_step": 401648, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.00984787940979, "global_step": 401649, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0953493118286133, "global_step": 401650, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.053455352783203, "global_step": 401651, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0569663047790527, "global_step": 401652, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.149935245513916, "global_step": 401653, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.090833902359009, "global_step": 401654, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.110611915588379, "global_step": 401655, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1560699939727783, "global_step": 401656, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.146246910095215, "global_step": 401657, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.060274124145508, "global_step": 401658, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1330721378326416, "global_step": 401659, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0792019367218018, "global_step": 401660, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0780036449432373, "global_step": 401661, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0990045070648193, "global_step": 401662, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.059451103210449, "global_step": 401663, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0684258937835693, "global_step": 401664, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0748562812805176, "global_step": 401665, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.068354368209839, "global_step": 401666, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.097662925720215, "global_step": 401667, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.041294813156128, "global_step": 401668, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1097958087921143, "global_step": 401669, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.998178482055664, "global_step": 401670, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0879876613616943, "global_step": 401671, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0453412532806396, "global_step": 401672, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0514731407165527, "global_step": 401673, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.113050937652588, "global_step": 401674, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.137388229370117, "global_step": 401675, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.179560661315918, "global_step": 401676, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0912930965423584, "global_step": 401677, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.158714771270752, "global_step": 401678, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.9808924198150635, "global_step": 401679, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1522719860076904, "global_step": 401680, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1593925952911377, "global_step": 401681, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0953052043914795, "global_step": 401682, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.970955491065979, "global_step": 401683, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1285998821258545, "global_step": 401684, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1119070053100586, "global_step": 401685, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0646517276763916, "global_step": 401686, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.188441038131714, "global_step": 401687, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1511459350585938, "global_step": 401688, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1266236305236816, "global_step": 401689, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0719246864318848, "global_step": 401690, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.113805055618286, "global_step": 401691, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0644948482513428, "global_step": 401692, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1787471771240234, "global_step": 401693, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.072784423828125, "global_step": 401694, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0603079795837402, "global_step": 401695, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0714635848999023, "global_step": 401696, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.146588087081909, "global_step": 401697, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.139291286468506, "global_step": 401698, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0877127647399902, "global_step": 401699, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.173995018005371, "global_step": 401700, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.2191147804260254, "global_step": 401701, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1503360271453857, "global_step": 401702, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0162549018859863, "global_step": 401703, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.138244390487671, "global_step": 401704, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0649218559265137, "global_step": 401705, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0299081802368164, "global_step": 401706, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.128755807876587, "global_step": 401707, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1000819206237793, "global_step": 401708, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0953633785247803, "global_step": 401709, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0889744758605957, "global_step": 401710, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0606017112731934, "global_step": 401711, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0392849445343018, "global_step": 401712, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1297590732574463, "global_step": 401713, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.104417324066162, "global_step": 401714, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1168973445892334, "global_step": 401715, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.139662027359009, "global_step": 401716, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.107165813446045, "global_step": 401717, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0771868228912354, "global_step": 401718, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0067501068115234, "global_step": 401719, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0967698097229004, "global_step": 401720, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1765220165252686, "global_step": 401721, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0753228664398193, "global_step": 401722, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.078110694885254, "global_step": 401723, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0412909984588623, "global_step": 401724, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1733109951019287, "global_step": 401725, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.108368158340454, "global_step": 401726, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1123664379119873, "global_step": 401727, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1315293312072754, "global_step": 401728, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1799991130828857, "global_step": 401729, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.149967670440674, "global_step": 401730, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1498987674713135, "global_step": 401731, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.132742166519165, "global_step": 401732, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.018951654434204, "global_step": 401733, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1259100437164307, "global_step": 401734, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1224560737609863, "global_step": 401735, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.120363235473633, "global_step": 401736, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1366260051727295, "global_step": 401737, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.053438186645508, "global_step": 401738, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1301193237304688, "global_step": 401739, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.157501697540283, "global_step": 401740, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0142722129821777, "global_step": 401741, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1802611351013184, "global_step": 401742, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.137550115585327, "global_step": 401743, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1235437393188477, "global_step": 401744, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0726635456085205, "global_step": 401745, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.084817886352539, "global_step": 401746, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0876450538635254, "global_step": 401747, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0107569694519043, "global_step": 401748, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.092921257019043, "global_step": 401749, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.080272674560547, "global_step": 401750, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1485042572021484, "global_step": 401751, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.142247200012207, "global_step": 401752, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.203195810317993, "global_step": 401753, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.025893211364746, "global_step": 401754, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.095852851867676, "global_step": 401755, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.011526584625244, "global_step": 401756, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1448028087615967, "global_step": 401757, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0279855728149414, "global_step": 401758, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0770153999328613, "global_step": 401759, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0562002658843994, "global_step": 401760, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0998752117156982, "global_step": 401761, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.090131998062134, "global_step": 401762, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.069983720779419, "global_step": 401763, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.136700391769409, "global_step": 401764, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.179636001586914, "global_step": 401765, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.137505292892456, "global_step": 401766, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1137077808380127, "global_step": 401767, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1534910202026367, "global_step": 401768, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1272590160369873, "global_step": 401769, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0680644512176514, "global_step": 401770, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0958147048950195, "global_step": 401771, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0629982948303223, "global_step": 401772, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0389816761016846, "global_step": 401773, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.064185857772827, "global_step": 401774, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0991082191467285, "global_step": 401775, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0573673248291016, "global_step": 401776, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.104889154434204, "global_step": 401777, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1121485233306885, "global_step": 401778, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1495418548583984, "global_step": 401779, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.088253974914551, "global_step": 401780, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.095614433288574, "global_step": 401781, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0965428352355957, "global_step": 401782, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0892956256866455, "global_step": 401783, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.042233943939209, "global_step": 401784, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0292766094207764, "global_step": 401785, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.143832206726074, "global_step": 401786, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1464500427246094, "global_step": 401787, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0709946155548096, "global_step": 401788, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1875438690185547, "global_step": 401789, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1221261024475098, "global_step": 401790, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0891950130462646, "global_step": 401791, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.078667402267456, "global_step": 401792, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1119749546051025, "global_step": 401793, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1788136959075928, "global_step": 401794, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0514609813690186, "global_step": 401795, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0458643436431885, "global_step": 401796, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0211942195892334, "global_step": 401797, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.107891321182251, "global_step": 401798, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1120800971984863, "global_step": 401799, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1358964443206787, "global_step": 401800, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.126987934112549, "global_step": 401801, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.098397731781006, "global_step": 401802, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0309107303619385, "global_step": 401803, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1345462799072266, "global_step": 401804, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.024123430252075, "global_step": 401805, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1251845359802246, "global_step": 401806, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.006783962249756, "global_step": 401807, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0405585765838623, "global_step": 401808, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1344308853149414, "global_step": 401809, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0770909786224365, "global_step": 401810, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.070976495742798, "global_step": 401811, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.9970494508743286, "global_step": 401812, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0677731037139893, "global_step": 401813, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.08744478225708, "global_step": 401814, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.132567882537842, "global_step": 401815, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.119844913482666, "global_step": 401816, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0809295177459717, "global_step": 401817, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.158811330795288, "global_step": 401818, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1268789768218994, "global_step": 401819, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.092402219772339, "global_step": 401820, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.9936602115631104, "global_step": 401821, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.043525218963623, "global_step": 401822, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.138427734375, "global_step": 401823, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0662920475006104, "global_step": 401824, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.155291795730591, "global_step": 401825, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1516120433807373, "global_step": 401826, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.2690300941467285, "global_step": 401827, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.10398530960083, "global_step": 401828, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0715532302856445, "global_step": 401829, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.159766674041748, "global_step": 401830, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.9566826820373535, "global_step": 401831, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.055685520172119, "global_step": 401832, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0720245838165283, "global_step": 401833, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.039724826812744, "global_step": 401834, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.095386505126953, "global_step": 401835, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0751707553863525, "global_step": 401836, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0893030166625977, "global_step": 401837, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.02154541015625, "global_step": 401838, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1192471981048584, "global_step": 401839, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.104714870452881, "global_step": 401840, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.104527473449707, "global_step": 401841, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0673716068267822, "global_step": 401842, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0343377590179443, "global_step": 401843, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.126985549926758, "global_step": 401844, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1025028228759766, "global_step": 401845, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1840009689331055, "global_step": 401846, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0500755310058594, "global_step": 401847, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0692481994628906, "global_step": 401848, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.2257466316223145, "global_step": 401849, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.221097946166992, "global_step": 401850, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.159268617630005, "global_step": 401851, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.141934871673584, "global_step": 401852, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.12042236328125, "global_step": 401853, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.057422399520874, "global_step": 401854, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.09033203125, "global_step": 401855, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.122121810913086, "global_step": 401856, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0517849922180176, "global_step": 401857, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0361247062683105, "global_step": 401858, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.2393534183502197, "global_step": 401859, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.097161054611206, "global_step": 401860, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.116150379180908, "global_step": 401861, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1726107597351074, "global_step": 401862, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0904648303985596, "global_step": 401863, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.170994758605957, "global_step": 401864, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0378928184509277, "global_step": 401865, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0614025592803955, "global_step": 401866, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.057656764984131, "global_step": 401867, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.023486375808716, "global_step": 401868, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.095250368118286, "global_step": 401869, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.074941873550415, "global_step": 401870, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0500340461730957, "global_step": 401871, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.067159652709961, "global_step": 401872, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0451488494873047, "global_step": 401873, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1761133670806885, "global_step": 401874, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1201300621032715, "global_step": 401875, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.125795602798462, "global_step": 401876, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1368260383605957, "global_step": 401877, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1017720699310303, "global_step": 401878, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0586445331573486, "global_step": 401879, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1180310249328613, "global_step": 401880, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.023383378982544, "global_step": 401881, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.9804065227508545, "global_step": 401882, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0579280853271484, "global_step": 401883, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.120682954788208, "global_step": 401884, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.044161319732666, "global_step": 401885, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0317580699920654, "global_step": 401886, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1144018173217773, "global_step": 401887, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0911731719970703, "global_step": 401888, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.082970142364502, "global_step": 401889, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.9829031229019165, "global_step": 401890, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.081886053085327, "global_step": 401891, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1716623306274414, "global_step": 401892, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1385607719421387, "global_step": 401893, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0864176750183105, "global_step": 401894, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.113187789916992, "global_step": 401895, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0931236743927, "global_step": 401896, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1492972373962402, "global_step": 401897, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1006715297698975, "global_step": 401898, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1096622943878174, "global_step": 401899, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0471529960632324, "global_step": 401900, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0957682132720947, "global_step": 401901, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.076035261154175, "global_step": 401902, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1520960330963135, "global_step": 401903, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.112502098083496, "global_step": 401904, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0825133323669434, "global_step": 401905, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1074390411376953, "global_step": 401906, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.16945219039917, "global_step": 401907, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1037991046905518, "global_step": 401908, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.12273907661438, "global_step": 401909, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1620795726776123, "global_step": 401910, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.114349365234375, "global_step": 401911, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1136507987976074, "global_step": 401912, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.08728289604187, "global_step": 401913, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0954580307006836, "global_step": 401914, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.144820213317871, "global_step": 401915, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0565648078918457, "global_step": 401916, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1532187461853027, "global_step": 401917, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.118478775024414, "global_step": 401918, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0335726737976074, "global_step": 401919, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.140303611755371, "global_step": 401920, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.006340265274048, "global_step": 401921, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1014785766601562, "global_step": 401922, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.076129913330078, "global_step": 401923, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0455684661865234, "global_step": 401924, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0336318016052246, "global_step": 401925, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1307222843170166, "global_step": 401926, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.139378547668457, "global_step": 401927, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1107211112976074, "global_step": 401928, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1035830974578857, "global_step": 401929, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.111888885498047, "global_step": 401930, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.035616159439087, "global_step": 401931, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.042833089828491, "global_step": 401932, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1125051975250244, "global_step": 401933, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.066131591796875, "global_step": 401934, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.096781015396118, "global_step": 401935, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.154498815536499, "global_step": 401936, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.055699110031128, "global_step": 401937, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.136828660964966, "global_step": 401938, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0667829513549805, "global_step": 401939, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0681533813476562, "global_step": 401940, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1472461223602295, "global_step": 401941, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.095895767211914, "global_step": 401942, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.107635974884033, "global_step": 401943, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1496024131774902, "global_step": 401944, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1328914165496826, "global_step": 401945, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0571906566619873, "global_step": 401946, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.118237257003784, "global_step": 401947, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.019531726837158, "global_step": 401948, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0884177684783936, "global_step": 401949, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.004321336746216, "global_step": 401950, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0146141052246094, "global_step": 401951, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1939852237701416, "global_step": 401952, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0614516735076904, "global_step": 401953, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0665390491485596, "global_step": 401954, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0973896980285645, "global_step": 401955, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.033853054046631, "global_step": 401956, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.046689033508301, "global_step": 401957, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0605666637420654, "global_step": 401958, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.165759563446045, "global_step": 401959, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0402352809906006, "global_step": 401960, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.9857267141342163, "global_step": 401961, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.158971071243286, "global_step": 401962, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.099412202835083, "global_step": 401963, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.202026605606079, "global_step": 401964, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1085219383239746, "global_step": 401965, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.112229108810425, "global_step": 401966, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.103612184524536, "global_step": 401967, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1464931964874268, "global_step": 401968, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.087233304977417, "global_step": 401969, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.078402042388916, "global_step": 401970, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.055628538131714, "global_step": 401971, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.072352886199951, "global_step": 401972, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1668410301208496, "global_step": 401973, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.161438226699829, "global_step": 401974, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0583975315093994, "global_step": 401975, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1703312397003174, "global_step": 401976, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1103060245513916, "global_step": 401977, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0661048889160156, "global_step": 401978, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.043881416320801, "global_step": 401979, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0239858627319336, "global_step": 401980, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1267917156219482, "global_step": 401981, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.022989273071289, "global_step": 401982, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0920209884643555, "global_step": 401983, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.088338851928711, "global_step": 401984, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.097048282623291, "global_step": 401985, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.186624526977539, "global_step": 401986, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0907506942749023, "global_step": 401987, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.039153814315796, "global_step": 401988, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1382384300231934, "global_step": 401989, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.17134165763855, "global_step": 401990, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1296162605285645, "global_step": 401991, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.130488395690918, "global_step": 401992, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1104300022125244, "global_step": 401993, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1379804611206055, "global_step": 401994, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.13659930229187, "global_step": 401995, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1133861541748047, "global_step": 401996, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1483113765716553, "global_step": 401997, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1436288356781006, "global_step": 401998, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.063538074493408, "global_step": 401999, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1218292713165283, "global_step": 402000, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0780081748962402, "global_step": 402001, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1552577018737793, "global_step": 402002, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0930795669555664, "global_step": 402003, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.067042112350464, "global_step": 402004, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0884768962860107, "global_step": 402005, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.033902168273926, "global_step": 402006, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0823922157287598, "global_step": 402007, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.112344741821289, "global_step": 402008, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0705575942993164, "global_step": 402009, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1730222702026367, "global_step": 402010, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1379945278167725, "global_step": 402011, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0824453830718994, "global_step": 402012, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0547447204589844, "global_step": 402013, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1102311611175537, "global_step": 402014, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.142939567565918, "global_step": 402015, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.9829298257827759, "global_step": 402016, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0567400455474854, "global_step": 402017, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0618557929992676, "global_step": 402018, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0909171104431152, "global_step": 402019, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.100675106048584, "global_step": 402020, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1286842823028564, "global_step": 402021, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1496987342834473, "global_step": 402022, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0856688022613525, "global_step": 402023, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.21396803855896, "global_step": 402024, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.961877465248108, "global_step": 402025, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.036534309387207, "global_step": 402026, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1651079654693604, "global_step": 402027, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.024174690246582, "global_step": 402028, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1032986640930176, "global_step": 402029, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.051578998565674, "global_step": 402030, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0388476848602295, "global_step": 402031, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0934133529663086, "global_step": 402032, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1660263538360596, "global_step": 402033, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.046555757522583, "global_step": 402034, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0845274925231934, "global_step": 402035, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.135138988494873, "global_step": 402036, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0574209690093994, "global_step": 402037, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.116373062133789, "global_step": 402038, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0580697059631348, "global_step": 402039, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.098787784576416, "global_step": 402040, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0617165565490723, "global_step": 402041, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0647244453430176, "global_step": 402042, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.066488027572632, "global_step": 402043, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.067563772201538, "global_step": 402044, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.130141496658325, "global_step": 402045, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.081265449523926, "global_step": 402046, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.057859420776367, "global_step": 402047, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.111189365386963, "global_step": 402048, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.10319185256958, "global_step": 402049, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1041247844696045, "global_step": 402050, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.157582998275757, "global_step": 402051, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.12308406829834, "global_step": 402052, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.092796802520752, "global_step": 402053, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.062013864517212, "global_step": 402054, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1389970779418945, "global_step": 402055, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1396541595458984, "global_step": 402056, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1264076232910156, "global_step": 402057, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.2058682441711426, "global_step": 402058, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.079026937484741, "global_step": 402059, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.053781509399414, "global_step": 402060, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0968246459960938, "global_step": 402061, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.2020068168640137, "global_step": 402062, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.047229766845703, "global_step": 402063, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.090081214904785, "global_step": 402064, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0475189685821533, "global_step": 402065, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1041131019592285, "global_step": 402066, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.052532434463501, "global_step": 402067, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1234519481658936, "global_step": 402068, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.11069917678833, "global_step": 402069, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1766486167907715, "global_step": 402070, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0934770107269287, "global_step": 402071, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1806869506835938, "global_step": 402072, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1072494983673096, "global_step": 402073, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.109457015991211, "global_step": 402074, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1203536987304688, "global_step": 402075, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.004373073577881, "global_step": 402076, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0955779552459717, "global_step": 402077, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1158926486968994, "global_step": 402078, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0535030364990234, "global_step": 402079, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.061525344848633, "global_step": 402080, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.106198310852051, "global_step": 402081, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1637063026428223, "global_step": 402082, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1405880451202393, "global_step": 402083, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0172767639160156, "global_step": 402084, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1439857482910156, "global_step": 402085, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.119250774383545, "global_step": 402086, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.103353500366211, "global_step": 402087, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.162597417831421, "global_step": 402088, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0402474403381348, "global_step": 402089, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1011040210723877, "global_step": 402090, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.067141532897949, "global_step": 402091, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.9761600494384766, "global_step": 402092, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.089390993118286, "global_step": 402093, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1189939975738525, "global_step": 402094, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.047478675842285, "global_step": 402095, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0580389499664307, "global_step": 402096, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.110991954803467, "global_step": 402097, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.132441759109497, "global_step": 402098, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0771641731262207, "global_step": 402099, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0621795654296875, "global_step": 402100, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.08149790763855, "global_step": 402101, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0696754455566406, "global_step": 402102, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1045045852661133, "global_step": 402103, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.088557004928589, "global_step": 402104, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0231800079345703, "global_step": 402105, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.042595863342285, "global_step": 402106, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.133538007736206, "global_step": 402107, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.9882327318191528, "global_step": 402108, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.103710174560547, "global_step": 402109, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1357340812683105, "global_step": 402110, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0660853385925293, "global_step": 402111, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.043301820755005, "global_step": 402112, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.147245168685913, "global_step": 402113, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.118486166000366, "global_step": 402114, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.137859344482422, "global_step": 402115, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.175605535507202, "global_step": 402116, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1048264503479004, "global_step": 402117, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1028945446014404, "global_step": 402118, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0490663051605225, "global_step": 402119, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.127204418182373, "global_step": 402120, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0941312313079834, "global_step": 402121, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.073817014694214, "global_step": 402122, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.097632646560669, "global_step": 402123, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1088812351226807, "global_step": 402124, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.139545202255249, "global_step": 402125, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1175220012664795, "global_step": 402126, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1478631496429443, "global_step": 402127, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.036970853805542, "global_step": 402128, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0136382579803467, "global_step": 402129, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.140855073928833, "global_step": 402130, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0139052867889404, "global_step": 402131, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.053905963897705, "global_step": 402132, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.001746416091919, "global_step": 402133, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.151609420776367, "global_step": 402134, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.031243085861206, "global_step": 402135, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0887012481689453, "global_step": 402136, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1133265495300293, "global_step": 402137, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1617326736450195, "global_step": 402138, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.143792152404785, "global_step": 402139, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0506656169891357, "global_step": 402140, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.086604595184326, "global_step": 402141, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1202232837677, "global_step": 402142, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.084639310836792, "global_step": 402143, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0925724506378174, "global_step": 402144, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.122891664505005, "global_step": 402145, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.047532081604004, "global_step": 402146, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1125149726867676, "global_step": 402147, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0713603496551514, "global_step": 402148, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0527310371398926, "global_step": 402149, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.166769504547119, "global_step": 402150, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.145679473876953, "global_step": 402151, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1020312309265137, "global_step": 402152, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.01892352104187, "global_step": 402153, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1402549743652344, "global_step": 402154, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0198168754577637, "global_step": 402155, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1839303970336914, "global_step": 402156, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.031456470489502, "global_step": 402157, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.061307668685913, "global_step": 402158, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.125582695007324, "global_step": 402159, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.091569185256958, "global_step": 402160, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.144259452819824, "global_step": 402161, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0906243324279785, "global_step": 402162, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.093949794769287, "global_step": 402163, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.2278079986572266, "global_step": 402164, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.113792657852173, "global_step": 402165, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0496716499328613, "global_step": 402166, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0919442176818848, "global_step": 402167, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0362911224365234, "global_step": 402168, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0328006744384766, "global_step": 402169, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.105065107345581, "global_step": 402170, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1569576263427734, "global_step": 402171, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0547492504119873, "global_step": 402172, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.098834276199341, "global_step": 402173, "epoch": 764, "lr": 5e-05}
{"train_loss": 1.9994064569473267, "global_step": 402174, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0915987491607666, "global_step": 402175, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.124976396560669, "global_step": 402176, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.170898199081421, "global_step": 402177, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0707647800445557, "global_step": 402178, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.112337350845337, "global_step": 402179, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0402567386627197, "global_step": 402180, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1510019302368164, "global_step": 402181, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.138512372970581, "global_step": 402182, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0269527435302734, "global_step": 402183, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.100003957748413, "global_step": 402184, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.120668411254883, "global_step": 402185, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1028432846069336, "global_step": 402186, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1351888179779053, "global_step": 402187, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.162978172302246, "global_step": 402188, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1094610691070557, "global_step": 402189, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.106616497039795, "global_step": 402190, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.038022756576538, "global_step": 402191, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.192394733428955, "global_step": 402192, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.206787586212158, "global_step": 402193, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.081721067428589, "global_step": 402194, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0687692165374756, "global_step": 402195, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.067410469055176, "global_step": 402196, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.045583486557007, "global_step": 402197, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.128230333328247, "global_step": 402198, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1891891956329346, "global_step": 402199, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.121295690536499, "global_step": 402200, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.07049298286438, "global_step": 402201, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1152310371398926, "global_step": 402202, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.036750555038452, "global_step": 402203, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0114738941192627, "global_step": 402204, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0486302375793457, "global_step": 402205, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0071775913238525, "global_step": 402206, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.070378065109253, "global_step": 402207, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0689125061035156, "global_step": 402208, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1333940029144287, "global_step": 402209, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0582451820373535, "global_step": 402210, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0711405277252197, "global_step": 402211, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1342175006866455, "global_step": 402212, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1149327754974365, "global_step": 402213, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1297619342803955, "global_step": 402214, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.180548667907715, "global_step": 402215, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.2153103351593018, "global_step": 402216, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.078104019165039, "global_step": 402217, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1202564239501953, "global_step": 402218, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.053640365600586, "global_step": 402219, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.097935676574707, "global_step": 402220, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.108027458190918, "global_step": 402221, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0468924045562744, "global_step": 402222, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.099865198135376, "global_step": 402223, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.074768304824829, "global_step": 402224, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.073756694793701, "global_step": 402225, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0761120319366455, "global_step": 402226, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.150538921356201, "global_step": 402227, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1439321041107178, "global_step": 402228, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1707706451416016, "global_step": 402229, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.14890456199646, "global_step": 402230, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1004018783569336, "global_step": 402231, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1057229042053223, "global_step": 402232, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0208582878112793, "global_step": 402233, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.055786609649658, "global_step": 402234, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0937249660491943, "global_step": 402235, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0754451751708984, "global_step": 402236, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.078834056854248, "global_step": 402237, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0432705879211426, "global_step": 402238, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.085965394973755, "global_step": 402239, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.029700994491577, "global_step": 402240, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1731269359588623, "global_step": 402241, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.107150077819824, "global_step": 402242, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1186978816986084, "global_step": 402243, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0242819786071777, "global_step": 402244, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1324150562286377, "global_step": 402245, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.089121103286743, "global_step": 402246, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.204084634780884, "global_step": 402247, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0767157077789307, "global_step": 402248, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1722705364227295, "global_step": 402249, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0330052375793457, "global_step": 402250, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.180636167526245, "global_step": 402251, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0205836296081543, "global_step": 402252, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1357860565185547, "global_step": 402253, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0274288654327393, "global_step": 402254, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0712473392486572, "global_step": 402255, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1290135383605957, "global_step": 402256, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0581328868865967, "global_step": 402257, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.216458320617676, "global_step": 402258, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.070061206817627, "global_step": 402259, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.0998334884643555, "global_step": 402260, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1428918838500977, "global_step": 402261, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1562209129333496, "global_step": 402262, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1455190181732178, "global_step": 402263, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.1254591941833496, "global_step": 402264, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.094367027282715, "global_step": 402265, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.013575315475464, "global_step": 402266, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.094127893447876, "global_step": 402267, "epoch": 764, "lr": 5e-05}
{"train_loss": 2.051989793777466, "global_step": 402268, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1402273178100586, "global_step": 402269, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1059067249298096, "global_step": 402270, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0228989124298096, "global_step": 402271, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1118106842041016, "global_step": 402272, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0415077209472656, "global_step": 402273, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1395139694213867, "global_step": 402274, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0888991355895996, "global_step": 402275, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0399880409240723, "global_step": 402276, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.029733419418335, "global_step": 402277, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.013702392578125, "global_step": 402278, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1053478717803955, "global_step": 402279, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.026081085205078, "global_step": 402280, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0489566326141357, "global_step": 402281, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1109719276428223, "global_step": 402282, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1252553462982178, "global_step": 402283, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.056320905685425, "global_step": 402284, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.041048288345337, "global_step": 402285, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0538835525512695, "global_step": 402286, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0207128524780273, "global_step": 402287, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0178568363189697, "global_step": 402288, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0922446250915527, "global_step": 402289, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0597903728485107, "global_step": 402290, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.076702117919922, "global_step": 402291, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.213838577270508, "global_step": 402292, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.089458703994751, "global_step": 402293, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.002257823944092, "global_step": 402294, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.2060205936431885, "global_step": 402295, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.107779026031494, "global_step": 402296, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0481972694396973, "global_step": 402297, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.089306354522705, "global_step": 402298, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.128664970397949, "global_step": 402299, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0391600131988525, "global_step": 402300, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1249377727508545, "global_step": 402301, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0751900672912598, "global_step": 402302, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0565543174743652, "global_step": 402303, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0563364028930664, "global_step": 402304, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0423099994659424, "global_step": 402305, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.125818967819214, "global_step": 402306, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1570780277252197, "global_step": 402307, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0871148109436035, "global_step": 402308, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9472507238388062, "global_step": 402309, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9948172569274902, "global_step": 402310, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.144669532775879, "global_step": 402311, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1068384647369385, "global_step": 402312, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.04468035697937, "global_step": 402313, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0294837951660156, "global_step": 402314, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9975225925445557, "global_step": 402315, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1500837802886963, "global_step": 402316, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1300041675567627, "global_step": 402317, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.151470184326172, "global_step": 402318, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.044968843460083, "global_step": 402319, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0735299587249756, "global_step": 402320, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0562424659729004, "global_step": 402321, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1611874103546143, "global_step": 402322, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0461585521698, "global_step": 402323, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0290212631225586, "global_step": 402324, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.080134153366089, "global_step": 402325, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1232211589813232, "global_step": 402326, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.061737060546875, "global_step": 402327, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0813655853271484, "global_step": 402328, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.105400323867798, "global_step": 402329, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.146361827850342, "global_step": 402330, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1058781147003174, "global_step": 402331, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.105769157409668, "global_step": 402332, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0381808280944824, "global_step": 402333, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9685962200164795, "global_step": 402334, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0426015853881836, "global_step": 402335, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.039527654647827, "global_step": 402336, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0953495502471924, "global_step": 402337, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1002981662750244, "global_step": 402338, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1685051918029785, "global_step": 402339, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0317842960357666, "global_step": 402340, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.089552640914917, "global_step": 402341, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.039835214614868, "global_step": 402342, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0337629318237305, "global_step": 402343, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0777087211608887, "global_step": 402344, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0405094623565674, "global_step": 402345, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0858938694000244, "global_step": 402346, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0822627544403076, "global_step": 402347, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.075120687484741, "global_step": 402348, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.078418493270874, "global_step": 402349, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.98514723777771, "global_step": 402350, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1278350353240967, "global_step": 402351, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0749874114990234, "global_step": 402352, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.156484842300415, "global_step": 402353, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0714311599731445, "global_step": 402354, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0017037391662598, "global_step": 402355, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.047445297241211, "global_step": 402356, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0176713466644287, "global_step": 402357, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.038632392883301, "global_step": 402358, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.091824531555176, "global_step": 402359, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.063370943069458, "global_step": 402360, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.113431930541992, "global_step": 402361, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.069361686706543, "global_step": 402362, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1236696243286133, "global_step": 402363, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.127169370651245, "global_step": 402364, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0837624073028564, "global_step": 402365, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.16109299659729, "global_step": 402366, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.111809492111206, "global_step": 402367, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1031839847564697, "global_step": 402368, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.044365644454956, "global_step": 402369, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1454434394836426, "global_step": 402370, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0286831855773926, "global_step": 402371, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1538469791412354, "global_step": 402372, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1035234928131104, "global_step": 402373, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.056568145751953, "global_step": 402374, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0754103660583496, "global_step": 402375, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1594278812408447, "global_step": 402376, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1598775386810303, "global_step": 402377, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0465641021728516, "global_step": 402378, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0814812183380127, "global_step": 402379, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.135596513748169, "global_step": 402380, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1554629802703857, "global_step": 402381, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.037330389022827, "global_step": 402382, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.017787456512451, "global_step": 402383, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0025975704193115, "global_step": 402384, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1278176307678223, "global_step": 402385, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.999121069908142, "global_step": 402386, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1472442150115967, "global_step": 402387, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1464450359344482, "global_step": 402388, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1009531021118164, "global_step": 402389, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.068944215774536, "global_step": 402390, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1169636249542236, "global_step": 402391, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.079427480697632, "global_step": 402392, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.016388177871704, "global_step": 402393, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1394565105438232, "global_step": 402394, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1678264141082764, "global_step": 402395, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.058098316192627, "global_step": 402396, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.087249279022217, "global_step": 402397, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1757054328918457, "global_step": 402398, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.143139362335205, "global_step": 402399, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1285269260406494, "global_step": 402400, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.054941415786743, "global_step": 402401, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0463333129882812, "global_step": 402402, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1244847774505615, "global_step": 402403, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0507354736328125, "global_step": 402404, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0693674087524414, "global_step": 402405, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1511850357055664, "global_step": 402406, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0268383026123047, "global_step": 402407, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1119179725646973, "global_step": 402408, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0740649700164795, "global_step": 402409, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.158543586730957, "global_step": 402410, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.098538398742676, "global_step": 402411, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.043998956680298, "global_step": 402412, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.126246213912964, "global_step": 402413, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.046139717102051, "global_step": 402414, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0418553352355957, "global_step": 402415, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.026228189468384, "global_step": 402416, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1033670902252197, "global_step": 402417, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0689656734466553, "global_step": 402418, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1253628730773926, "global_step": 402419, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.134589433670044, "global_step": 402420, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.037841320037842, "global_step": 402421, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.083444356918335, "global_step": 402422, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0770413875579834, "global_step": 402423, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.032172441482544, "global_step": 402424, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.980135202407837, "global_step": 402425, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.094320058822632, "global_step": 402426, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0934624671936035, "global_step": 402427, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.017181873321533, "global_step": 402428, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1035470962524414, "global_step": 402429, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1182262897491455, "global_step": 402430, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9904439449310303, "global_step": 402431, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9988889694213867, "global_step": 402432, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0998799800872803, "global_step": 402433, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.084139347076416, "global_step": 402434, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0925400257110596, "global_step": 402435, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.05938720703125, "global_step": 402436, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0684473514556885, "global_step": 402437, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0708115100860596, "global_step": 402438, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0790677070617676, "global_step": 402439, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1189956665039062, "global_step": 402440, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1596288681030273, "global_step": 402441, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1670608520507812, "global_step": 402442, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.075622081756592, "global_step": 402443, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.038667678833008, "global_step": 402444, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1917552947998047, "global_step": 402445, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0722732543945312, "global_step": 402446, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.090113878250122, "global_step": 402447, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.020932912826538, "global_step": 402448, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0316238403320312, "global_step": 402449, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0629143714904785, "global_step": 402450, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.020237684249878, "global_step": 402451, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1387035846710205, "global_step": 402452, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.113201141357422, "global_step": 402453, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0363032817840576, "global_step": 402454, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.129671812057495, "global_step": 402455, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0055909156799316, "global_step": 402456, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.020636558532715, "global_step": 402457, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0731565952301025, "global_step": 402458, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.094597578048706, "global_step": 402459, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.14469838142395, "global_step": 402460, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0710268020629883, "global_step": 402461, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0940239429473877, "global_step": 402462, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.193068742752075, "global_step": 402463, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.11076283454895, "global_step": 402464, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.051419258117676, "global_step": 402465, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1396119594573975, "global_step": 402466, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.12803053855896, "global_step": 402467, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.016225814819336, "global_step": 402468, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0208041667938232, "global_step": 402469, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.059211492538452, "global_step": 402470, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0688865184783936, "global_step": 402471, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.156435489654541, "global_step": 402472, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.045708179473877, "global_step": 402473, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.094078302383423, "global_step": 402474, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.071852922439575, "global_step": 402475, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.072329044342041, "global_step": 402476, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0777249336242676, "global_step": 402477, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.104253053665161, "global_step": 402478, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1693081855773926, "global_step": 402479, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.066650629043579, "global_step": 402480, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1469032764434814, "global_step": 402481, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.053596019744873, "global_step": 402482, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0463614463806152, "global_step": 402483, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.133937120437622, "global_step": 402484, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.035993814468384, "global_step": 402485, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.060413360595703, "global_step": 402486, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0836236476898193, "global_step": 402487, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.12017822265625, "global_step": 402488, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.066328525543213, "global_step": 402489, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.116694688796997, "global_step": 402490, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1531898975372314, "global_step": 402491, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.09906005859375, "global_step": 402492, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1505749225616455, "global_step": 402493, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.082728385925293, "global_step": 402494, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0620503425598145, "global_step": 402495, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0054497718811035, "global_step": 402496, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.111219644546509, "global_step": 402497, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0872135162353516, "global_step": 402498, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1208016872406006, "global_step": 402499, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1160223484039307, "global_step": 402500, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.120741367340088, "global_step": 402501, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0084424018859863, "global_step": 402502, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9978537559509277, "global_step": 402503, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1910970211029053, "global_step": 402504, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1170454025268555, "global_step": 402505, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0387091636657715, "global_step": 402506, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9984992742538452, "global_step": 402507, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.18026065826416, "global_step": 402508, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0690152645111084, "global_step": 402509, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.112936019897461, "global_step": 402510, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0704474449157715, "global_step": 402511, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.089385509490967, "global_step": 402512, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.057438373565674, "global_step": 402513, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1656839847564697, "global_step": 402514, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.074390411376953, "global_step": 402515, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0873453617095947, "global_step": 402516, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1379101276397705, "global_step": 402517, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.095160484313965, "global_step": 402518, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.040118932723999, "global_step": 402519, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1348876953125, "global_step": 402520, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1083922386169434, "global_step": 402521, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0697007179260254, "global_step": 402522, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1001875400543213, "global_step": 402523, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1077446937561035, "global_step": 402524, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1175591945648193, "global_step": 402525, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1896955966949463, "global_step": 402526, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.04640531539917, "global_step": 402527, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0894947052001953, "global_step": 402528, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0598649978637695, "global_step": 402529, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1426994800567627, "global_step": 402530, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0323574542999268, "global_step": 402531, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.040308952331543, "global_step": 402532, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.071141242980957, "global_step": 402533, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.00425386428833, "global_step": 402534, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1321170330047607, "global_step": 402535, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1315195560455322, "global_step": 402536, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0253031253814697, "global_step": 402537, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1356403827667236, "global_step": 402538, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.005927801132202, "global_step": 402539, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.066237211227417, "global_step": 402540, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1347622871398926, "global_step": 402541, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.116934299468994, "global_step": 402542, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.127225875854492, "global_step": 402543, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.035203456878662, "global_step": 402544, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.030043363571167, "global_step": 402545, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.106276512145996, "global_step": 402546, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.028541088104248, "global_step": 402547, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.090381383895874, "global_step": 402548, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1030924320220947, "global_step": 402549, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.004828929901123, "global_step": 402550, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1041760444641113, "global_step": 402551, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0695056915283203, "global_step": 402552, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.153686046600342, "global_step": 402553, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1130523681640625, "global_step": 402554, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1572482585906982, "global_step": 402555, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.072981357574463, "global_step": 402556, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.023505449295044, "global_step": 402557, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.115257978439331, "global_step": 402558, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.17264461517334, "global_step": 402559, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0364315509796143, "global_step": 402560, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.152330160140991, "global_step": 402561, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0384249687194824, "global_step": 402562, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.024404525756836, "global_step": 402563, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0665056705474854, "global_step": 402564, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0817480087280273, "global_step": 402565, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1072819232940674, "global_step": 402566, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.049544095993042, "global_step": 402567, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0146868228912354, "global_step": 402568, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0916032791137695, "global_step": 402569, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1162872314453125, "global_step": 402570, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.125208616256714, "global_step": 402571, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0897037982940674, "global_step": 402572, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0314691066741943, "global_step": 402573, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.127066135406494, "global_step": 402574, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.174821138381958, "global_step": 402575, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.110055446624756, "global_step": 402576, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1185083389282227, "global_step": 402577, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.05808162689209, "global_step": 402578, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1012449264526367, "global_step": 402579, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.135873556137085, "global_step": 402580, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.106459140777588, "global_step": 402581, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.166360378265381, "global_step": 402582, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1023669242858887, "global_step": 402583, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0370936393737793, "global_step": 402584, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.039485454559326, "global_step": 402585, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.069023609161377, "global_step": 402586, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.107426881790161, "global_step": 402587, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.175532817840576, "global_step": 402588, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0396993160247803, "global_step": 402589, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0563106536865234, "global_step": 402590, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0782599449157715, "global_step": 402591, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1504688262939453, "global_step": 402592, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0725395679473877, "global_step": 402593, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1140332221984863, "global_step": 402594, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.026052236557007, "global_step": 402595, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.040987014770508, "global_step": 402596, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.065154552459717, "global_step": 402597, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.088442325592041, "global_step": 402598, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.150902032852173, "global_step": 402599, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.120043992996216, "global_step": 402600, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0906970500946045, "global_step": 402601, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.134918212890625, "global_step": 402602, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.133962392807007, "global_step": 402603, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.149601936340332, "global_step": 402604, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0830624103546143, "global_step": 402605, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.107501983642578, "global_step": 402606, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.064236640930176, "global_step": 402607, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.071788787841797, "global_step": 402608, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.145280361175537, "global_step": 402609, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.184981107711792, "global_step": 402610, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0702500343322754, "global_step": 402611, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1382224559783936, "global_step": 402612, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.095283031463623, "global_step": 402613, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1967263221740723, "global_step": 402614, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.107365131378174, "global_step": 402615, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0621867179870605, "global_step": 402616, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0257558822631836, "global_step": 402617, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.088670253753662, "global_step": 402618, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.104734420776367, "global_step": 402619, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1386444568634033, "global_step": 402620, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.101328134536743, "global_step": 402621, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.047520875930786, "global_step": 402622, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0915167331695557, "global_step": 402623, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.090564727783203, "global_step": 402624, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.049246311187744, "global_step": 402625, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1266884803771973, "global_step": 402626, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1311943531036377, "global_step": 402627, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0806021690368652, "global_step": 402628, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0992307662963867, "global_step": 402629, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1106009483337402, "global_step": 402630, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1190595626831055, "global_step": 402631, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.055537462234497, "global_step": 402632, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0660953521728516, "global_step": 402633, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0211234092712402, "global_step": 402634, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1519827842712402, "global_step": 402635, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0212714672088623, "global_step": 402636, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.129777669906616, "global_step": 402637, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0646767616271973, "global_step": 402638, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0241897106170654, "global_step": 402639, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.051802158355713, "global_step": 402640, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0831682682037354, "global_step": 402641, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.971125602722168, "global_step": 402642, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0661089420318604, "global_step": 402643, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0845611095428467, "global_step": 402644, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.077383279800415, "global_step": 402645, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9827003479003906, "global_step": 402646, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0810489654541016, "global_step": 402647, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0751235485076904, "global_step": 402648, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1147732734680176, "global_step": 402649, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1205737590789795, "global_step": 402650, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.103698492050171, "global_step": 402651, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.153561592102051, "global_step": 402652, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1124186515808105, "global_step": 402653, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1290574073791504, "global_step": 402654, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0684399604797363, "global_step": 402655, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1308302879333496, "global_step": 402656, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.120495319366455, "global_step": 402657, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.064026117324829, "global_step": 402658, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0041048526763916, "global_step": 402659, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0350630283355713, "global_step": 402660, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.031430959701538, "global_step": 402661, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1469156742095947, "global_step": 402662, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.073305130004883, "global_step": 402663, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1617281436920166, "global_step": 402664, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0341570377349854, "global_step": 402665, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0902481079101562, "global_step": 402666, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0520758628845215, "global_step": 402667, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.119551420211792, "global_step": 402668, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1287314891815186, "global_step": 402669, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1864943504333496, "global_step": 402670, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.045279026031494, "global_step": 402671, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0495951175689697, "global_step": 402672, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0973947048187256, "global_step": 402673, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.968062400817871, "global_step": 402674, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1502208709716797, "global_step": 402675, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.116243600845337, "global_step": 402676, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1049861907958984, "global_step": 402677, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.144986867904663, "global_step": 402678, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.188310146331787, "global_step": 402679, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.016594886779785, "global_step": 402680, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0961625576019287, "global_step": 402681, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1968307495117188, "global_step": 402682, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9954252243041992, "global_step": 402683, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1467082500457764, "global_step": 402684, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.085838794708252, "global_step": 402685, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9122514724731445, "global_step": 402686, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.091738224029541, "global_step": 402687, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0742921829223633, "global_step": 402688, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1845180988311768, "global_step": 402689, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1462790966033936, "global_step": 402690, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.203584671020508, "global_step": 402691, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.118114471435547, "global_step": 402692, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1096551418304443, "global_step": 402693, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.088228464126587, "global_step": 402694, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1637468338012695, "global_step": 402695, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.177785873413086, "global_step": 402696, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.120868682861328, "global_step": 402697, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0880134105682373, "global_step": 402698, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0860540866851807, "global_step": 402699, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.054391622543335, "global_step": 402700, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.112257957458496, "global_step": 402701, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1357059478759766, "global_step": 402702, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1423354148864746, "global_step": 402703, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1472508907318115, "global_step": 402704, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1987879276275635, "global_step": 402705, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0196328163146973, "global_step": 402706, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.092841863632202, "global_step": 402707, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.141867160797119, "global_step": 402708, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.096726417541504, "global_step": 402709, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.095165729522705, "global_step": 402710, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.096004009246826, "global_step": 402711, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9984631538391113, "global_step": 402712, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.122070074081421, "global_step": 402713, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1096386909484863, "global_step": 402714, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.091888904571533, "global_step": 402715, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1224329471588135, "global_step": 402716, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0664479732513428, "global_step": 402717, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1035571098327637, "global_step": 402718, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.109164237976074, "global_step": 402719, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0854334831237793, "global_step": 402720, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.109161138534546, "global_step": 402721, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.018188714981079, "global_step": 402722, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.096299886703491, "global_step": 402723, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1264495849609375, "global_step": 402724, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1274333000183105, "global_step": 402725, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.091111898422241, "global_step": 402726, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.083014965057373, "global_step": 402727, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.081085205078125, "global_step": 402728, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0812184810638428, "global_step": 402729, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.214007616043091, "global_step": 402730, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0700740814208984, "global_step": 402731, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.105470895767212, "global_step": 402732, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0861785411834717, "global_step": 402733, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.171597957611084, "global_step": 402734, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1871957778930664, "global_step": 402735, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0862905979156494, "global_step": 402736, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1745784282684326, "global_step": 402737, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.055300235748291, "global_step": 402738, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0908195972442627, "global_step": 402739, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.074512004852295, "global_step": 402740, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9794765710830688, "global_step": 402741, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1297667026519775, "global_step": 402742, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1242802143096924, "global_step": 402743, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0496256351470947, "global_step": 402744, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.100022315979004, "global_step": 402745, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.117455244064331, "global_step": 402746, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1620140075683594, "global_step": 402747, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.107938766479492, "global_step": 402748, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.090817928314209, "global_step": 402749, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.117029905319214, "global_step": 402750, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1240761280059814, "global_step": 402751, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0393450260162354, "global_step": 402752, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0512187480926514, "global_step": 402753, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9948792457580566, "global_step": 402754, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.097240686416626, "global_step": 402755, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.170538902282715, "global_step": 402756, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0540201663970947, "global_step": 402757, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1242148876190186, "global_step": 402758, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0250093936920166, "global_step": 402759, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.071443796157837, "global_step": 402760, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1042897701263428, "global_step": 402761, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0580692291259766, "global_step": 402762, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0452895164489746, "global_step": 402763, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.991114854812622, "global_step": 402764, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0806057453155518, "global_step": 402765, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0943334102630615, "global_step": 402766, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.131972551345825, "global_step": 402767, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.2507073879241943, "global_step": 402768, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.180691719055176, "global_step": 402769, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.104633331298828, "global_step": 402770, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1149344444274902, "global_step": 402771, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1051650047302246, "global_step": 402772, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.108351230621338, "global_step": 402773, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.106748342514038, "global_step": 402774, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0873682498931885, "global_step": 402775, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1352107524871826, "global_step": 402776, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0409274101257324, "global_step": 402777, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0998425483703613, "global_step": 402778, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0523629188537598, "global_step": 402779, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.064239025115967, "global_step": 402780, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1435842514038086, "global_step": 402781, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1012237071990967, "global_step": 402782, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1647727489471436, "global_step": 402783, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1547751426696777, "global_step": 402784, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.122116804122925, "global_step": 402785, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.009911298751831, "global_step": 402786, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.096944808959961, "global_step": 402787, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0551981925964355, "global_step": 402788, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1121537685394287, "global_step": 402789, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0349857807159424, "global_step": 402790, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.161770820617676, "global_step": 402791, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1143531799316406, "global_step": 402792, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.142160415649414, "global_step": 402793, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1340785026550293, "global_step": 402794, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1383988857269287, "global_step": 402795, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.087914228439331, "global_step": 402796, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1023879051208496, "global_step": 402797, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1620309352874756, "global_step": 402798, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.111581325531006, "global_step": 402799, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.083653450012207, "global_step": 402800, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.136960744857788, "global_step": 402801, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0225627422332764, "global_step": 402802, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0933525562286377, "global_step": 402803, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0723302364349365, "global_step": 402804, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1119563579559326, "global_step": 402805, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0859153270721436, "global_step": 402806, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.100818634033203, "global_step": 402807, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0869407653808594, "global_step": 402808, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.081127643585205, "global_step": 402809, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.109290361404419, "global_step": 402810, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0778682231903076, "global_step": 402811, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.195363759994507, "global_step": 402812, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0693366527557373, "global_step": 402813, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.206390380859375, "global_step": 402814, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0469157695770264, "global_step": 402815, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1403751373291016, "global_step": 402816, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1264939308166504, "global_step": 402817, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.176729440689087, "global_step": 402818, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.145530939102173, "global_step": 402819, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1585757732391357, "global_step": 402820, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.131169557571411, "global_step": 402821, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.026559591293335, "global_step": 402822, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.124782085418701, "global_step": 402823, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.129016160964966, "global_step": 402824, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.054076910018921, "global_step": 402825, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.031545400619507, "global_step": 402826, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0568649768829346, "global_step": 402827, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1760034561157227, "global_step": 402828, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.153045892715454, "global_step": 402829, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0609893798828125, "global_step": 402830, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0628764629364014, "global_step": 402831, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0596048831939697, "global_step": 402832, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0855510234832764, "global_step": 402833, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1913533210754395, "global_step": 402834, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0591931343078613, "global_step": 402835, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.001555919647217, "global_step": 402836, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.127394676208496, "global_step": 402837, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1799252033233643, "global_step": 402838, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1122124195098877, "global_step": 402839, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0869321823120117, "global_step": 402840, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1264877319335938, "global_step": 402841, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.155221939086914, "global_step": 402842, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.092243194580078, "global_step": 402843, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.03806471824646, "global_step": 402844, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.083393096923828, "global_step": 402845, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1354081630706787, "global_step": 402846, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0709455013275146, "global_step": 402847, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0940418243408203, "global_step": 402848, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1839091777801514, "global_step": 402849, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1417479515075684, "global_step": 402850, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1590919494628906, "global_step": 402851, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.057936668395996, "global_step": 402852, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1418235301971436, "global_step": 402853, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.138075113296509, "global_step": 402854, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0919349193573, "global_step": 402855, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1430256366729736, "global_step": 402856, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1251025199890137, "global_step": 402857, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.105412721633911, "global_step": 402858, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.113966703414917, "global_step": 402859, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1426331996917725, "global_step": 402860, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.101027488708496, "global_step": 402861, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0632662773132324, "global_step": 402862, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.103980541229248, "global_step": 402863, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.151200294494629, "global_step": 402864, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.149322748184204, "global_step": 402865, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0977375507354736, "global_step": 402866, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.042255163192749, "global_step": 402867, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1071994304656982, "global_step": 402868, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1506881713867188, "global_step": 402869, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1088883876800537, "global_step": 402870, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1625707149505615, "global_step": 402871, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.010392189025879, "global_step": 402872, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1023852825164795, "global_step": 402873, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0758912563323975, "global_step": 402874, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1312966346740723, "global_step": 402875, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0860908031463623, "global_step": 402876, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.083096504211426, "global_step": 402877, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.127330780029297, "global_step": 402878, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9759628772735596, "global_step": 402879, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.071160316467285, "global_step": 402880, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1271281242370605, "global_step": 402881, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.077871799468994, "global_step": 402882, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1725921630859375, "global_step": 402883, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.070934534072876, "global_step": 402884, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.036505937576294, "global_step": 402885, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1335723400115967, "global_step": 402886, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1605405807495117, "global_step": 402887, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.162788152694702, "global_step": 402888, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.084404468536377, "global_step": 402889, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0540273189544678, "global_step": 402890, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1588850021362305, "global_step": 402891, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.098921775817871, "global_step": 402892, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0821549892425537, "global_step": 402893, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.124725341796875, "global_step": 402894, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.099623441696167, "global_step": 402895, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0673348903656006, "global_step": 402896, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0984368324279785, "global_step": 402897, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1192831993103027, "global_step": 402898, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1199541091918945, "global_step": 402899, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.027533531188965, "global_step": 402900, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.133498191833496, "global_step": 402901, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.095388174057007, "global_step": 402902, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.12549090385437, "global_step": 402903, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0960116386413574, "global_step": 402904, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0754523277282715, "global_step": 402905, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0702435970306396, "global_step": 402906, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0524792671203613, "global_step": 402907, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.07629132270813, "global_step": 402908, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0673937797546387, "global_step": 402909, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.170886993408203, "global_step": 402910, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1557276248931885, "global_step": 402911, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0624537467956543, "global_step": 402912, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.090287923812866, "global_step": 402913, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0858542919158936, "global_step": 402914, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0887880325317383, "global_step": 402915, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.098926067352295, "global_step": 402916, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.162975311279297, "global_step": 402917, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0981006622314453, "global_step": 402918, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.056788444519043, "global_step": 402919, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0272672176361084, "global_step": 402920, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0607361793518066, "global_step": 402921, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0622212886810303, "global_step": 402922, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1638827323913574, "global_step": 402923, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.08461856842041, "global_step": 402924, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0753910541534424, "global_step": 402925, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.027926445007324, "global_step": 402926, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1403138637542725, "global_step": 402927, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0783629417419434, "global_step": 402928, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.124784469604492, "global_step": 402929, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1911590099334717, "global_step": 402930, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1246585845947266, "global_step": 402931, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0513651371002197, "global_step": 402932, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0360233783721924, "global_step": 402933, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0919594764709473, "global_step": 402934, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.025294542312622, "global_step": 402935, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1671154499053955, "global_step": 402936, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0359139442443848, "global_step": 402937, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0856995582580566, "global_step": 402938, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.052896022796631, "global_step": 402939, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0272748470306396, "global_step": 402940, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.171085834503174, "global_step": 402941, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1438941955566406, "global_step": 402942, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.167024612426758, "global_step": 402943, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.080998420715332, "global_step": 402944, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1244373321533203, "global_step": 402945, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.090866804122925, "global_step": 402946, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1432485580444336, "global_step": 402947, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1133615970611572, "global_step": 402948, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.083712100982666, "global_step": 402949, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0191972255706787, "global_step": 402950, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.024044990539551, "global_step": 402951, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1255006790161133, "global_step": 402952, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1265087127685547, "global_step": 402953, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1078829765319824, "global_step": 402954, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.135204315185547, "global_step": 402955, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.094383716583252, "global_step": 402956, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.081360101699829, "global_step": 402957, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1374330520629883, "global_step": 402958, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1455650329589844, "global_step": 402959, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1329543590545654, "global_step": 402960, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9539659023284912, "global_step": 402961, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0971829891204834, "global_step": 402962, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.142207622528076, "global_step": 402963, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.174384117126465, "global_step": 402964, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.161978244781494, "global_step": 402965, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0897746086120605, "global_step": 402966, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.088862657546997, "global_step": 402967, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.039198875427246, "global_step": 402968, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.021209955215454, "global_step": 402969, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1356537342071533, "global_step": 402970, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0699429512023926, "global_step": 402971, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1042964458465576, "global_step": 402972, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0932812690734863, "global_step": 402973, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0989317893981934, "global_step": 402974, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.224545955657959, "global_step": 402975, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1284103393554688, "global_step": 402976, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0715126991271973, "global_step": 402977, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1029372215270996, "global_step": 402978, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0537514686584473, "global_step": 402979, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.09309720993042, "global_step": 402980, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.081275224685669, "global_step": 402981, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.2064056396484375, "global_step": 402982, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1350579261779785, "global_step": 402983, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1014065742492676, "global_step": 402984, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.189666271209717, "global_step": 402985, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1211013793945312, "global_step": 402986, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0294814109802246, "global_step": 402987, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1288435459136963, "global_step": 402988, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.066481113433838, "global_step": 402989, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.077608585357666, "global_step": 402990, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.179965019226074, "global_step": 402991, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0398929119110107, "global_step": 402992, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1517491340637207, "global_step": 402993, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0394301414489746, "global_step": 402994, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0820488929748535, "global_step": 402995, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.131153106689453, "global_step": 402996, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.054903268814087, "global_step": 402997, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.166358470916748, "global_step": 402998, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0630288124084473, "global_step": 402999, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.105909585952759, "global_step": 403000, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.103813886642456, "global_step": 403001, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9954168796539307, "global_step": 403002, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0920372009277344, "global_step": 403003, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0928547382354736, "global_step": 403004, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0755703449249268, "global_step": 403005, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1175994873046875, "global_step": 403006, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.252171754837036, "global_step": 403007, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.16339111328125, "global_step": 403008, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.090708017349243, "global_step": 403009, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.177246570587158, "global_step": 403010, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.073437213897705, "global_step": 403011, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1255390644073486, "global_step": 403012, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.036691427230835, "global_step": 403013, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1011674404144287, "global_step": 403014, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0947694778442383, "global_step": 403015, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.087251663208008, "global_step": 403016, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0122854709625244, "global_step": 403017, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0355968475341797, "global_step": 403018, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0965218544006348, "global_step": 403019, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0917134284973145, "global_step": 403020, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1730735301971436, "global_step": 403021, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.069988250732422, "global_step": 403022, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.067328691482544, "global_step": 403023, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1114211082458496, "global_step": 403024, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.155735969543457, "global_step": 403025, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1799306869506836, "global_step": 403026, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1004257202148438, "global_step": 403027, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1891930103302, "global_step": 403028, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.094865083694458, "global_step": 403029, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1195671558380127, "global_step": 403030, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.062285900115967, "global_step": 403031, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.102299213409424, "global_step": 403032, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.115867853164673, "global_step": 403033, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.140522003173828, "global_step": 403034, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1154966354370117, "global_step": 403035, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1375656127929688, "global_step": 403036, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.103167772293091, "global_step": 403037, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.13675594329834, "global_step": 403038, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0861847400665283, "global_step": 403039, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.179654121398926, "global_step": 403040, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1519112586975098, "global_step": 403041, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0504937171936035, "global_step": 403042, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.105393648147583, "global_step": 403043, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0700840950012207, "global_step": 403044, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0193593502044678, "global_step": 403045, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.171933889389038, "global_step": 403046, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1424574851989746, "global_step": 403047, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.032545566558838, "global_step": 403048, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0469913482666016, "global_step": 403049, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.079735040664673, "global_step": 403050, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1155574321746826, "global_step": 403051, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.156668186187744, "global_step": 403052, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0551412105560303, "global_step": 403053, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1099600791931152, "global_step": 403054, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.068934202194214, "global_step": 403055, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.212299346923828, "global_step": 403056, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0908374786376953, "global_step": 403057, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1713204383850098, "global_step": 403058, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1795310974121094, "global_step": 403059, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.095863103866577, "global_step": 403060, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.024310350418091, "global_step": 403061, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0523862838745117, "global_step": 403062, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0359456539154053, "global_step": 403063, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.145871877670288, "global_step": 403064, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1381113529205322, "global_step": 403065, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.045250654220581, "global_step": 403066, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0673532485961914, "global_step": 403067, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0601847171783447, "global_step": 403068, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.175180196762085, "global_step": 403069, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1355462074279785, "global_step": 403070, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.069772481918335, "global_step": 403071, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.071648597717285, "global_step": 403072, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.134404182434082, "global_step": 403073, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.204911708831787, "global_step": 403074, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1012418270111084, "global_step": 403075, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0646920204162598, "global_step": 403076, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1168971061706543, "global_step": 403077, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1874632835388184, "global_step": 403078, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0691840648651123, "global_step": 403079, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.099370241165161, "global_step": 403080, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.08848237991333, "global_step": 403081, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0611469745635986, "global_step": 403082, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.038421392440796, "global_step": 403083, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0429463386535645, "global_step": 403084, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0596909523010254, "global_step": 403085, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.078873634338379, "global_step": 403086, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1423323154449463, "global_step": 403087, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0984437465667725, "global_step": 403088, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.052051305770874, "global_step": 403089, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0688364505767822, "global_step": 403090, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1168019771575928, "global_step": 403091, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1085896492004395, "global_step": 403092, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1411125659942627, "global_step": 403093, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1095221042633057, "global_step": 403094, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.178892135620117, "global_step": 403095, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1314635276794434, "global_step": 403096, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1312968730926514, "global_step": 403097, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1779062747955322, "global_step": 403098, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.073251247406006, "global_step": 403099, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0747337341308594, "global_step": 403100, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1492555141448975, "global_step": 403101, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.019481897354126, "global_step": 403102, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0196690559387207, "global_step": 403103, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0239899158477783, "global_step": 403104, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0291786193847656, "global_step": 403105, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0763983726501465, "global_step": 403106, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0811822414398193, "global_step": 403107, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0991554260253906, "global_step": 403108, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.2103865146636963, "global_step": 403109, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0305216312408447, "global_step": 403110, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1657025814056396, "global_step": 403111, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1268680095672607, "global_step": 403112, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.075108051300049, "global_step": 403113, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9691197872161865, "global_step": 403114, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1218769550323486, "global_step": 403115, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.07027006149292, "global_step": 403116, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1368050575256348, "global_step": 403117, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.2194902896881104, "global_step": 403118, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.087226390838623, "global_step": 403119, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.069913148880005, "global_step": 403120, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0849578380584717, "global_step": 403121, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.060328960418701, "global_step": 403122, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0810728073120117, "global_step": 403123, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0714077949523926, "global_step": 403124, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0154714584350586, "global_step": 403125, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.068136692047119, "global_step": 403126, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0085175037384033, "global_step": 403127, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1325924396514893, "global_step": 403128, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.12125301361084, "global_step": 403129, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.089529275894165, "global_step": 403130, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.108020067214966, "global_step": 403131, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.084538221359253, "global_step": 403132, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.098731279373169, "global_step": 403133, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0546090602874756, "global_step": 403134, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.151318311691284, "global_step": 403135, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1738739013671875, "global_step": 403136, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1340441703796387, "global_step": 403137, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1100046634674072, "global_step": 403138, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0786046981811523, "global_step": 403139, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0956790447235107, "global_step": 403140, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.128664970397949, "global_step": 403141, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0300607681274414, "global_step": 403142, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.074533700942993, "global_step": 403143, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0486955642700195, "global_step": 403144, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1146762371063232, "global_step": 403145, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9795790910720825, "global_step": 403146, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0775482654571533, "global_step": 403147, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.095456123352051, "global_step": 403148, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1306514739990234, "global_step": 403149, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.101651430130005, "global_step": 403150, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1044528484344482, "global_step": 403151, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.162038803100586, "global_step": 403152, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1651952266693115, "global_step": 403153, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0710527896881104, "global_step": 403154, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0630974769592285, "global_step": 403155, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0923397541046143, "global_step": 403156, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.102212905883789, "global_step": 403157, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.105621814727783, "global_step": 403158, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.039036512374878, "global_step": 403159, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.111128568649292, "global_step": 403160, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.046931266784668, "global_step": 403161, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.112480878829956, "global_step": 403162, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0576772689819336, "global_step": 403163, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0829997062683105, "global_step": 403164, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0050907135009766, "global_step": 403165, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0945918560028076, "global_step": 403166, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.090500593185425, "global_step": 403167, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1283068656921387, "global_step": 403168, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1635122299194336, "global_step": 403169, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1502184867858887, "global_step": 403170, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1086478233337402, "global_step": 403171, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9394502639770508, "global_step": 403172, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0117640495300293, "global_step": 403173, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0640430450439453, "global_step": 403174, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.119507312774658, "global_step": 403175, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0876450538635254, "global_step": 403176, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.116276741027832, "global_step": 403177, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1342287063598633, "global_step": 403178, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1612653732299805, "global_step": 403179, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.126311779022217, "global_step": 403180, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.100404739379883, "global_step": 403181, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1178295612335205, "global_step": 403182, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.102321147918701, "global_step": 403183, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.093111038208008, "global_step": 403184, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0526907444000244, "global_step": 403185, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0471911430358887, "global_step": 403186, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1586787700653076, "global_step": 403187, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0719103813171387, "global_step": 403188, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.145514726638794, "global_step": 403189, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1963469982147217, "global_step": 403190, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.081683397293091, "global_step": 403191, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0282509326934814, "global_step": 403192, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.173450231552124, "global_step": 403193, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0917115211486816, "global_step": 403194, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0670297145843506, "global_step": 403195, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.113870859146118, "global_step": 403196, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.977270483970642, "global_step": 403197, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1560709476470947, "global_step": 403198, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1407546997070312, "global_step": 403199, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.064342737197876, "global_step": 403200, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1155929565429688, "global_step": 403201, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1335365772247314, "global_step": 403202, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0553767681121826, "global_step": 403203, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.9908462762832642, "global_step": 403204, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1699182987213135, "global_step": 403205, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.059175968170166, "global_step": 403206, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0677521228790283, "global_step": 403207, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.048353672027588, "global_step": 403208, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.150064706802368, "global_step": 403209, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.161486864089966, "global_step": 403210, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1350131034851074, "global_step": 403211, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.108497381210327, "global_step": 403212, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1391303539276123, "global_step": 403213, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1287450790405273, "global_step": 403214, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1283791065216064, "global_step": 403215, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.117771863937378, "global_step": 403216, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1263020038604736, "global_step": 403217, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0502519607543945, "global_step": 403218, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.065958023071289, "global_step": 403219, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1562459468841553, "global_step": 403220, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0765933990478516, "global_step": 403221, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.096672773361206, "global_step": 403222, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1022491455078125, "global_step": 403223, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1012351512908936, "global_step": 403224, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1444575786590576, "global_step": 403225, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1163368225097656, "global_step": 403226, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.050506114959717, "global_step": 403227, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0860414505004883, "global_step": 403228, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0713155269622803, "global_step": 403229, "epoch": 765, "lr": 5e-05}
{"train_loss": 1.973548173904419, "global_step": 403230, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0868945121765137, "global_step": 403231, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0323734283447266, "global_step": 403232, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.024738311767578, "global_step": 403233, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.1028411388397217, "global_step": 403234, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0596048831939697, "global_step": 403235, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.094022035598755, "global_step": 403236, "epoch": 765, "lr": 5e-05}
{"train_loss": 2.0900912284851074, "global_step": 403237, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0532784461975098, "global_step": 403238, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1331167221069336, "global_step": 403239, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1758217811584473, "global_step": 403240, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0584168434143066, "global_step": 403241, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.136887311935425, "global_step": 403242, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0625782012939453, "global_step": 403243, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0536065101623535, "global_step": 403244, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1057448387145996, "global_step": 403245, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0336785316467285, "global_step": 403246, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.090731620788574, "global_step": 403247, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.107501268386841, "global_step": 403248, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0595974922180176, "global_step": 403249, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1212925910949707, "global_step": 403250, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0783166885375977, "global_step": 403251, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1779751777648926, "global_step": 403252, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0934956073760986, "global_step": 403253, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.069608449935913, "global_step": 403254, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.063260316848755, "global_step": 403255, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1682450771331787, "global_step": 403256, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.13261079788208, "global_step": 403257, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.053227186203003, "global_step": 403258, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.062922477722168, "global_step": 403259, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0668067932128906, "global_step": 403260, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1648995876312256, "global_step": 403261, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.030106544494629, "global_step": 403262, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.127784013748169, "global_step": 403263, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.076616048812866, "global_step": 403264, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0735132694244385, "global_step": 403265, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1257483959198, "global_step": 403266, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0973105430603027, "global_step": 403267, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.024031639099121, "global_step": 403268, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9690272808074951, "global_step": 403269, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.149869680404663, "global_step": 403270, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0254719257354736, "global_step": 403271, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.118274211883545, "global_step": 403272, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.06807541847229, "global_step": 403273, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.078233480453491, "global_step": 403274, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1180315017700195, "global_step": 403275, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.029898166656494, "global_step": 403276, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.006927490234375, "global_step": 403277, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.057321310043335, "global_step": 403278, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0709996223449707, "global_step": 403279, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1497373580932617, "global_step": 403280, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1154866218566895, "global_step": 403281, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.060657262802124, "global_step": 403282, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0955402851104736, "global_step": 403283, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.107163906097412, "global_step": 403284, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1603055000305176, "global_step": 403285, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1760690212249756, "global_step": 403286, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0877199172973633, "global_step": 403287, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9813400506973267, "global_step": 403288, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0552492141723633, "global_step": 403289, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.117387056350708, "global_step": 403290, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0010664463043213, "global_step": 403291, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0862460136413574, "global_step": 403292, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1501293182373047, "global_step": 403293, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.01593017578125, "global_step": 403294, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.090287685394287, "global_step": 403295, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0729520320892334, "global_step": 403296, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1060757637023926, "global_step": 403297, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0705788135528564, "global_step": 403298, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1011226177215576, "global_step": 403299, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9949991703033447, "global_step": 403300, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.095742702484131, "global_step": 403301, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9782577753067017, "global_step": 403302, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0501272678375244, "global_step": 403303, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0565075874328613, "global_step": 403304, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0029022693634033, "global_step": 403305, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0607917308807373, "global_step": 403306, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.034444570541382, "global_step": 403307, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1411850452423096, "global_step": 403308, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.055438280105591, "global_step": 403309, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0550143718719482, "global_step": 403310, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.003746747970581, "global_step": 403311, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1106069087982178, "global_step": 403312, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0552902221679688, "global_step": 403313, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0919697284698486, "global_step": 403314, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.086109161376953, "global_step": 403315, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.168550729751587, "global_step": 403316, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0846054553985596, "global_step": 403317, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.050165891647339, "global_step": 403318, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1032259464263916, "global_step": 403319, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0795798301696777, "global_step": 403320, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0438315868377686, "global_step": 403321, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.048596143722534, "global_step": 403322, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1191792488098145, "global_step": 403323, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0755655765533447, "global_step": 403324, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0758159160614014, "global_step": 403325, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0923681259155273, "global_step": 403326, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0582380294799805, "global_step": 403327, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.006512403488159, "global_step": 403328, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1249747276306152, "global_step": 403329, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.176711082458496, "global_step": 403330, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0409507751464844, "global_step": 403331, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1099042892456055, "global_step": 403332, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1041853427886963, "global_step": 403333, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1171529293060303, "global_step": 403334, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0885226726531982, "global_step": 403335, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0795669555664062, "global_step": 403336, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.173278570175171, "global_step": 403337, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1361453533172607, "global_step": 403338, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0654590129852295, "global_step": 403339, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9544577598571777, "global_step": 403340, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.072080612182617, "global_step": 403341, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.182783365249634, "global_step": 403342, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0992519855499268, "global_step": 403343, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.067812442779541, "global_step": 403344, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.151604413986206, "global_step": 403345, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0573956966400146, "global_step": 403346, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0884995460510254, "global_step": 403347, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0651988983154297, "global_step": 403348, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0721797943115234, "global_step": 403349, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.162696361541748, "global_step": 403350, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.020120143890381, "global_step": 403351, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9863102436065674, "global_step": 403352, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0649707317352295, "global_step": 403353, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1260640621185303, "global_step": 403354, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.096021890640259, "global_step": 403355, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.052530527114868, "global_step": 403356, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.094722032546997, "global_step": 403357, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1527748107910156, "global_step": 403358, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0574209690093994, "global_step": 403359, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.037684679031372, "global_step": 403360, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.06484055519104, "global_step": 403361, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1197140216827393, "global_step": 403362, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1938087940216064, "global_step": 403363, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.054344415664673, "global_step": 403364, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.026884078979492, "global_step": 403365, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.150134325027466, "global_step": 403366, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0382080078125, "global_step": 403367, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.147963047027588, "global_step": 403368, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1661839485168457, "global_step": 403369, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0641977787017822, "global_step": 403370, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0902669429779053, "global_step": 403371, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0760583877563477, "global_step": 403372, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.045166015625, "global_step": 403373, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1266653537750244, "global_step": 403374, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.059431552886963, "global_step": 403375, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0934112071990967, "global_step": 403376, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0644283294677734, "global_step": 403377, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.087214708328247, "global_step": 403378, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.083595037460327, "global_step": 403379, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.143430233001709, "global_step": 403380, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.204059362411499, "global_step": 403381, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.106459140777588, "global_step": 403382, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0802762508392334, "global_step": 403383, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.122729778289795, "global_step": 403384, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.133178949356079, "global_step": 403385, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1952197551727295, "global_step": 403386, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.141132116317749, "global_step": 403387, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.180042028427124, "global_step": 403388, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0545685291290283, "global_step": 403389, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1040751934051514, "global_step": 403390, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.106201648712158, "global_step": 403391, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.140929698944092, "global_step": 403392, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.083812952041626, "global_step": 403393, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0906729698181152, "global_step": 403394, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0608952045440674, "global_step": 403395, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1370038986206055, "global_step": 403396, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.03660249710083, "global_step": 403397, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.100269079208374, "global_step": 403398, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1998422145843506, "global_step": 403399, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.114281177520752, "global_step": 403400, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0623319149017334, "global_step": 403401, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0973005294799805, "global_step": 403402, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.119602918624878, "global_step": 403403, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.090435743331909, "global_step": 403404, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.121964454650879, "global_step": 403405, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0027716159820557, "global_step": 403406, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.108198404312134, "global_step": 403407, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1183598041534424, "global_step": 403408, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0341246128082275, "global_step": 403409, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.027576446533203, "global_step": 403410, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1014864444732666, "global_step": 403411, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1253623962402344, "global_step": 403412, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.152205228805542, "global_step": 403413, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.026864528656006, "global_step": 403414, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1015281677246094, "global_step": 403415, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.067957639694214, "global_step": 403416, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1185929775238037, "global_step": 403417, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0709896087646484, "global_step": 403418, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.078357458114624, "global_step": 403419, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0209648609161377, "global_step": 403420, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.048846483230591, "global_step": 403421, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0407938957214355, "global_step": 403422, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0748066902160645, "global_step": 403423, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1370458602905273, "global_step": 403424, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1057066917419434, "global_step": 403425, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0918638706207275, "global_step": 403426, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0313384532928467, "global_step": 403427, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1267755031585693, "global_step": 403428, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1127755641937256, "global_step": 403429, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0536210536956787, "global_step": 403430, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.092198133468628, "global_step": 403431, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.093244791030884, "global_step": 403432, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1054279804229736, "global_step": 403433, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0707967281341553, "global_step": 403434, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.037882089614868, "global_step": 403435, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9937232732772827, "global_step": 403436, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1467177867889404, "global_step": 403437, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.089003324508667, "global_step": 403438, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0853495597839355, "global_step": 403439, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0639796257019043, "global_step": 403440, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.029022693634033, "global_step": 403441, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0682320594787598, "global_step": 403442, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1060564517974854, "global_step": 403443, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1020376682281494, "global_step": 403444, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0471906661987305, "global_step": 403445, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1822993755340576, "global_step": 403446, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1346182823181152, "global_step": 403447, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.124636650085449, "global_step": 403448, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0605950355529785, "global_step": 403449, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0080933570861816, "global_step": 403450, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0617222785949707, "global_step": 403451, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.074822425842285, "global_step": 403452, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1540987491607666, "global_step": 403453, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.098810911178589, "global_step": 403454, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0323867797851562, "global_step": 403455, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1161179542541504, "global_step": 403456, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.125494956970215, "global_step": 403457, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1139214038848877, "global_step": 403458, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0600264072418213, "global_step": 403459, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.102389335632324, "global_step": 403460, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.075517177581787, "global_step": 403461, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1461472511291504, "global_step": 403462, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0273072719573975, "global_step": 403463, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1537671089172363, "global_step": 403464, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.062058925628662, "global_step": 403465, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0851688385009766, "global_step": 403466, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1352670192718506, "global_step": 403467, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1169607639312744, "global_step": 403468, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0967886447906494, "global_step": 403469, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.043781280517578, "global_step": 403470, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.151829242706299, "global_step": 403471, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1022896766662598, "global_step": 403472, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.102236032485962, "global_step": 403473, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9840221405029297, "global_step": 403474, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.036465883255005, "global_step": 403475, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.108182430267334, "global_step": 403476, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.106135129928589, "global_step": 403477, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9817520380020142, "global_step": 403478, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.061246633529663, "global_step": 403479, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1165599822998047, "global_step": 403480, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.132880687713623, "global_step": 403481, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.089585781097412, "global_step": 403482, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1676557064056396, "global_step": 403483, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1207611560821533, "global_step": 403484, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0569608211517334, "global_step": 403485, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.086549997329712, "global_step": 403486, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.079289674758911, "global_step": 403487, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1524035930633545, "global_step": 403488, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1617932319641113, "global_step": 403489, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0654070377349854, "global_step": 403490, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0359885692596436, "global_step": 403491, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0590903759002686, "global_step": 403492, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1754376888275146, "global_step": 403493, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1548662185668945, "global_step": 403494, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0047616958618164, "global_step": 403495, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.081449508666992, "global_step": 403496, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.091427803039551, "global_step": 403497, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.2177646160125732, "global_step": 403498, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1187098026275635, "global_step": 403499, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.094313859939575, "global_step": 403500, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0583205223083496, "global_step": 403501, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0778887271881104, "global_step": 403502, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.140648603439331, "global_step": 403503, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0803580284118652, "global_step": 403504, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9887539148330688, "global_step": 403505, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0417232513427734, "global_step": 403506, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1452715396881104, "global_step": 403507, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.164607048034668, "global_step": 403508, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0968761444091797, "global_step": 403509, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1123805046081543, "global_step": 403510, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.084650993347168, "global_step": 403511, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1438934803009033, "global_step": 403512, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.188663959503174, "global_step": 403513, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.066110849380493, "global_step": 403514, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.059343099594116, "global_step": 403515, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0707509517669678, "global_step": 403516, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0634169578552246, "global_step": 403517, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.005368947982788, "global_step": 403518, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0971803665161133, "global_step": 403519, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0184340476989746, "global_step": 403520, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.114107847213745, "global_step": 403521, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1451776027679443, "global_step": 403522, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1353201866149902, "global_step": 403523, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0962748527526855, "global_step": 403524, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0765597820281982, "global_step": 403525, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0842597484588623, "global_step": 403526, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.108745574951172, "global_step": 403527, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.145434617996216, "global_step": 403528, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.146068572998047, "global_step": 403529, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.053583860397339, "global_step": 403530, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.038857936859131, "global_step": 403531, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1042184829711914, "global_step": 403532, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0051491260528564, "global_step": 403533, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0709314346313477, "global_step": 403534, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0472803115844727, "global_step": 403535, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0009653568267822, "global_step": 403536, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.09346866607666, "global_step": 403537, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0702459812164307, "global_step": 403538, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1841073036193848, "global_step": 403539, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.010864734649658, "global_step": 403540, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.139829397201538, "global_step": 403541, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.09840989112854, "global_step": 403542, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.086714267730713, "global_step": 403543, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0431439876556396, "global_step": 403544, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.091635227203369, "global_step": 403545, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.119962692260742, "global_step": 403546, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.102288007736206, "global_step": 403547, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0829591751098633, "global_step": 403548, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0587053298950195, "global_step": 403549, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1530165672302246, "global_step": 403550, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9650206565856934, "global_step": 403551, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0611073970794678, "global_step": 403552, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0565810203552246, "global_step": 403553, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.167975425720215, "global_step": 403554, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0838160514831543, "global_step": 403555, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1336636543273926, "global_step": 403556, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.123627185821533, "global_step": 403557, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.053682327270508, "global_step": 403558, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1567440032958984, "global_step": 403559, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0693211555480957, "global_step": 403560, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1973977088928223, "global_step": 403561, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0499210357666016, "global_step": 403562, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1538710594177246, "global_step": 403563, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.056001901626587, "global_step": 403564, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1294851303100586, "global_step": 403565, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0613815784454346, "global_step": 403566, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.160656452178955, "global_step": 403567, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0647430419921875, "global_step": 403568, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1995339393615723, "global_step": 403569, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0637407302856445, "global_step": 403570, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1765248775482178, "global_step": 403571, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9679049253463745, "global_step": 403572, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.080536365509033, "global_step": 403573, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.128823757171631, "global_step": 403574, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1094343662261963, "global_step": 403575, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0646893978118896, "global_step": 403576, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0788092613220215, "global_step": 403577, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0708601474761963, "global_step": 403578, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.035109519958496, "global_step": 403579, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0796947479248047, "global_step": 403580, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1346499919891357, "global_step": 403581, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.2025105953216553, "global_step": 403582, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.14499831199646, "global_step": 403583, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.002445936203003, "global_step": 403584, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1855902671813965, "global_step": 403585, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.056507110595703, "global_step": 403586, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.050926446914673, "global_step": 403587, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1760284900665283, "global_step": 403588, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.10357403755188, "global_step": 403589, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.038464307785034, "global_step": 403590, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9999520778656006, "global_step": 403591, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1632397174835205, "global_step": 403592, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.086822748184204, "global_step": 403593, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1343064308166504, "global_step": 403594, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1530489921569824, "global_step": 403595, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0328831672668457, "global_step": 403596, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0552926063537598, "global_step": 403597, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0447254180908203, "global_step": 403598, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.12493634223938, "global_step": 403599, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.123215913772583, "global_step": 403600, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.183382749557495, "global_step": 403601, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0634374618530273, "global_step": 403602, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1066887378692627, "global_step": 403603, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1213743686676025, "global_step": 403604, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.133641242980957, "global_step": 403605, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1308212280273438, "global_step": 403606, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0863826274871826, "global_step": 403607, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1458985805511475, "global_step": 403608, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.092153310775757, "global_step": 403609, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.17136287689209, "global_step": 403610, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.104741096496582, "global_step": 403611, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.094101905822754, "global_step": 403612, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.143889904022217, "global_step": 403613, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.108315944671631, "global_step": 403614, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0884084701538086, "global_step": 403615, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0387284755706787, "global_step": 403616, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.003586530685425, "global_step": 403617, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1355090141296387, "global_step": 403618, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1831209659576416, "global_step": 403619, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0964789390563965, "global_step": 403620, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.108656406402588, "global_step": 403621, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0396881103515625, "global_step": 403622, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.089193344116211, "global_step": 403623, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.053734302520752, "global_step": 403624, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.092114210128784, "global_step": 403625, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9839364290237427, "global_step": 403626, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9620815515518188, "global_step": 403627, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.063023090362549, "global_step": 403628, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.063249111175537, "global_step": 403629, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.071920394897461, "global_step": 403630, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.087172031402588, "global_step": 403631, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0915234088897705, "global_step": 403632, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.074509382247925, "global_step": 403633, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.202314853668213, "global_step": 403634, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.102591037750244, "global_step": 403635, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0824060440063477, "global_step": 403636, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.144045352935791, "global_step": 403637, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0854408740997314, "global_step": 403638, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0457608699798584, "global_step": 403639, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0432114601135254, "global_step": 403640, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0862185955047607, "global_step": 403641, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0777831077575684, "global_step": 403642, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1027233600616455, "global_step": 403643, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.2178165912628174, "global_step": 403644, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.067476272583008, "global_step": 403645, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.104590892791748, "global_step": 403646, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0958151817321777, "global_step": 403647, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.108304977416992, "global_step": 403648, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.147066116333008, "global_step": 403649, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.065582275390625, "global_step": 403650, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0490963459014893, "global_step": 403651, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.049341917037964, "global_step": 403652, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1079177856445312, "global_step": 403653, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1049625873565674, "global_step": 403654, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0787487030029297, "global_step": 403655, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1078591346740723, "global_step": 403656, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0505785942077637, "global_step": 403657, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.201723575592041, "global_step": 403658, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0827362537384033, "global_step": 403659, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.16157865524292, "global_step": 403660, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9996585845947266, "global_step": 403661, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0164315700531006, "global_step": 403662, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9510648250579834, "global_step": 403663, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.048844575881958, "global_step": 403664, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0879204273223877, "global_step": 403665, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.057748794555664, "global_step": 403666, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1086316108703613, "global_step": 403667, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0353264808654785, "global_step": 403668, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0925369262695312, "global_step": 403669, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1024675369262695, "global_step": 403670, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.030121088027954, "global_step": 403671, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0156028270721436, "global_step": 403672, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1768128871917725, "global_step": 403673, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.116179943084717, "global_step": 403674, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.105545997619629, "global_step": 403675, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1206023693084717, "global_step": 403676, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.08251953125, "global_step": 403677, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0752954483032227, "global_step": 403678, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1356523036956787, "global_step": 403679, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0450472831726074, "global_step": 403680, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.069000720977783, "global_step": 403681, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.094184637069702, "global_step": 403682, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0976920127868652, "global_step": 403683, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1127548217773438, "global_step": 403684, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0806477069854736, "global_step": 403685, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0675642490386963, "global_step": 403686, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.166527032852173, "global_step": 403687, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1488394737243652, "global_step": 403688, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0201807022094727, "global_step": 403689, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1790215969085693, "global_step": 403690, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0874125957489014, "global_step": 403691, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.162527561187744, "global_step": 403692, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0524394512176514, "global_step": 403693, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1926310062408447, "global_step": 403694, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0644702911376953, "global_step": 403695, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1088674068450928, "global_step": 403696, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.126016855239868, "global_step": 403697, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1625850200653076, "global_step": 403698, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.10322642326355, "global_step": 403699, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.069575309753418, "global_step": 403700, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.2075603008270264, "global_step": 403701, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.003430128097534, "global_step": 403702, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.150580644607544, "global_step": 403703, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.180588483810425, "global_step": 403704, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.029280185699463, "global_step": 403705, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.106480121612549, "global_step": 403706, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0487637519836426, "global_step": 403707, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0067970752716064, "global_step": 403708, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1530604362487793, "global_step": 403709, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0267276763916016, "global_step": 403710, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0564253330230713, "global_step": 403711, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.184434413909912, "global_step": 403712, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.022073268890381, "global_step": 403713, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1140453815460205, "global_step": 403714, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0968854427337646, "global_step": 403715, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0591864585876465, "global_step": 403716, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0997583866119385, "global_step": 403717, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.066124439239502, "global_step": 403718, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.07795786857605, "global_step": 403719, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0337040424346924, "global_step": 403720, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.125580072402954, "global_step": 403721, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.104957103729248, "global_step": 403722, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0897183418273926, "global_step": 403723, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.019763469696045, "global_step": 403724, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1197383403778076, "global_step": 403725, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1249067783355713, "global_step": 403726, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0284688472747803, "global_step": 403727, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.120565414428711, "global_step": 403728, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.125755548477173, "global_step": 403729, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1361091136932373, "global_step": 403730, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0207161903381348, "global_step": 403731, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1374592781066895, "global_step": 403732, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.126920461654663, "global_step": 403733, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1163527965545654, "global_step": 403734, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.107870578765869, "global_step": 403735, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0910911560058594, "global_step": 403736, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1891510486602783, "global_step": 403737, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.139671564102173, "global_step": 403738, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9893349409103394, "global_step": 403739, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1084508895874023, "global_step": 403740, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0470387935638428, "global_step": 403741, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1694447994232178, "global_step": 403742, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1273083686828613, "global_step": 403743, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1392815113067627, "global_step": 403744, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.039597749710083, "global_step": 403745, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1127874851226807, "global_step": 403746, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0832724571228027, "global_step": 403747, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0133421421051025, "global_step": 403748, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1638965606689453, "global_step": 403749, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.121166467666626, "global_step": 403750, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.128765821456909, "global_step": 403751, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9636179208755493, "global_step": 403752, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0052976608276367, "global_step": 403753, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0829319953918457, "global_step": 403754, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.029508113861084, "global_step": 403755, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.091259002685547, "global_step": 403756, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1621100902557373, "global_step": 403757, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.070068359375, "global_step": 403758, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1629607677459717, "global_step": 403759, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0792529582977295, "global_step": 403760, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1067633628845215, "global_step": 403761, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0194923877716064, "global_step": 403762, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1511447429656982, "global_step": 403763, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0229430198669434, "global_step": 403764, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.09499454498291, "global_step": 403765, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1263208389282227, "global_step": 403766, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.09944486618042, "global_step": 403767, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0234129428863525, "global_step": 403768, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.132868528366089, "global_step": 403769, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0019052028656006, "global_step": 403770, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.104403257369995, "global_step": 403771, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0492563247680664, "global_step": 403772, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.118004322052002, "global_step": 403773, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.147657632827759, "global_step": 403774, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1302435398101807, "global_step": 403775, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1134254932403564, "global_step": 403776, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0852742195129395, "global_step": 403777, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1409194469451904, "global_step": 403778, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.140617609024048, "global_step": 403779, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1100125312805176, "global_step": 403780, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0988008975982666, "global_step": 403781, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.096112012863159, "global_step": 403782, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1010096073150635, "global_step": 403783, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1670451164245605, "global_step": 403784, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1399714946746826, "global_step": 403785, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1680710315704346, "global_step": 403786, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0990512371063232, "global_step": 403787, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.039968490600586, "global_step": 403788, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1022422313690186, "global_step": 403789, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9983489513397217, "global_step": 403790, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.012488842010498, "global_step": 403791, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1157898902893066, "global_step": 403792, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1271491050720215, "global_step": 403793, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1690618991851807, "global_step": 403794, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1491661071777344, "global_step": 403795, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1971352100372314, "global_step": 403796, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.041111707687378, "global_step": 403797, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0699048042297363, "global_step": 403798, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1883316040039062, "global_step": 403799, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.108572006225586, "global_step": 403800, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0955772399902344, "global_step": 403801, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1004726886749268, "global_step": 403802, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.2057414054870605, "global_step": 403803, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1483545303344727, "global_step": 403804, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.117924451828003, "global_step": 403805, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.16378116607666, "global_step": 403806, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1856579780578613, "global_step": 403807, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.031228542327881, "global_step": 403808, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.030195474624634, "global_step": 403809, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.052363157272339, "global_step": 403810, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0778307914733887, "global_step": 403811, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0103185176849365, "global_step": 403812, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.144624710083008, "global_step": 403813, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1534812450408936, "global_step": 403814, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.002347230911255, "global_step": 403815, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0929648876190186, "global_step": 403816, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1115028858184814, "global_step": 403817, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0774343013763428, "global_step": 403818, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.011606216430664, "global_step": 403819, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0733530521392822, "global_step": 403820, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1603775024414062, "global_step": 403821, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0505056381225586, "global_step": 403822, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.991446614265442, "global_step": 403823, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.129121780395508, "global_step": 403824, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.14835786819458, "global_step": 403825, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0317769050598145, "global_step": 403826, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1241109371185303, "global_step": 403827, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1054656505584717, "global_step": 403828, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.139713764190674, "global_step": 403829, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1295626163482666, "global_step": 403830, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.093336820602417, "global_step": 403831, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1059134006500244, "global_step": 403832, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0350043773651123, "global_step": 403833, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.008857488632202, "global_step": 403834, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.046074867248535, "global_step": 403835, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.037449598312378, "global_step": 403836, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1583542823791504, "global_step": 403837, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1133949756622314, "global_step": 403838, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.136301040649414, "global_step": 403839, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1420183181762695, "global_step": 403840, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1845462322235107, "global_step": 403841, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1172704696655273, "global_step": 403842, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0705389976501465, "global_step": 403843, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.129582643508911, "global_step": 403844, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.098358631134033, "global_step": 403845, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.158865213394165, "global_step": 403846, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.014381170272827, "global_step": 403847, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0753846168518066, "global_step": 403848, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0742602348327637, "global_step": 403849, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1381571292877197, "global_step": 403850, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0464115142822266, "global_step": 403851, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1485514640808105, "global_step": 403852, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0390748977661133, "global_step": 403853, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1240432262420654, "global_step": 403854, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.074941873550415, "global_step": 403855, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.07053279876709, "global_step": 403856, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1308562755584717, "global_step": 403857, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0675911903381348, "global_step": 403858, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.074437141418457, "global_step": 403859, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.14178729057312, "global_step": 403860, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1303818225860596, "global_step": 403861, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.120776653289795, "global_step": 403862, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.064474105834961, "global_step": 403863, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0874979496002197, "global_step": 403864, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.084796905517578, "global_step": 403865, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0816962718963623, "global_step": 403866, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1044325828552246, "global_step": 403867, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1043548583984375, "global_step": 403868, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0956196784973145, "global_step": 403869, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.086925506591797, "global_step": 403870, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0722389221191406, "global_step": 403871, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0415287017822266, "global_step": 403872, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.065718173980713, "global_step": 403873, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0513155460357666, "global_step": 403874, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1634140014648438, "global_step": 403875, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.091775894165039, "global_step": 403876, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1238646507263184, "global_step": 403877, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1036458015441895, "global_step": 403878, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.155620813369751, "global_step": 403879, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.146237850189209, "global_step": 403880, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0606138706207275, "global_step": 403881, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0952374935150146, "global_step": 403882, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.076590061187744, "global_step": 403883, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0674965381622314, "global_step": 403884, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.086804151535034, "global_step": 403885, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0775043964385986, "global_step": 403886, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1565074920654297, "global_step": 403887, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0208981037139893, "global_step": 403888, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.144662380218506, "global_step": 403889, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1796042919158936, "global_step": 403890, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.154240846633911, "global_step": 403891, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0358147621154785, "global_step": 403892, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.083685874938965, "global_step": 403893, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0840346813201904, "global_step": 403894, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0916123390197754, "global_step": 403895, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0177853107452393, "global_step": 403896, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1039481163024902, "global_step": 403897, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0073015689849854, "global_step": 403898, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.165713310241699, "global_step": 403899, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1074326038360596, "global_step": 403900, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.139439582824707, "global_step": 403901, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.074538230895996, "global_step": 403902, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0911905765533447, "global_step": 403903, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.07100248336792, "global_step": 403904, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.986505150794983, "global_step": 403905, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0539424419403076, "global_step": 403906, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.133970022201538, "global_step": 403907, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.182569980621338, "global_step": 403908, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1161985397338867, "global_step": 403909, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0587055683135986, "global_step": 403910, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.148984670639038, "global_step": 403911, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.162148952484131, "global_step": 403912, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.158607244491577, "global_step": 403913, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.074195384979248, "global_step": 403914, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0666964054107666, "global_step": 403915, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.058786392211914, "global_step": 403916, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0584943294525146, "global_step": 403917, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.112731695175171, "global_step": 403918, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1298727989196777, "global_step": 403919, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.10341215133667, "global_step": 403920, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1485395431518555, "global_step": 403921, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0773961544036865, "global_step": 403922, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0711750984191895, "global_step": 403923, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.11650013923645, "global_step": 403924, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1800835132598877, "global_step": 403925, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.162550210952759, "global_step": 403926, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0687448978424072, "global_step": 403927, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1310620307922363, "global_step": 403928, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0558853149414062, "global_step": 403929, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0133490562438965, "global_step": 403930, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.095897674560547, "global_step": 403931, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1492223739624023, "global_step": 403932, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1059329509735107, "global_step": 403933, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.044093608856201, "global_step": 403934, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0907790660858154, "global_step": 403935, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.137334108352661, "global_step": 403936, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1505541801452637, "global_step": 403937, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1494791507720947, "global_step": 403938, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.102466106414795, "global_step": 403939, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0388362407684326, "global_step": 403940, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0538227558135986, "global_step": 403941, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.02978515625, "global_step": 403942, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.176609754562378, "global_step": 403943, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.056344985961914, "global_step": 403944, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0943031311035156, "global_step": 403945, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1080057621002197, "global_step": 403946, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1198692321777344, "global_step": 403947, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.047058582305908, "global_step": 403948, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0738184452056885, "global_step": 403949, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.044276475906372, "global_step": 403950, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.2189865112304688, "global_step": 403951, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0712313652038574, "global_step": 403952, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0601048469543457, "global_step": 403953, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0342860221862793, "global_step": 403954, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.077643871307373, "global_step": 403955, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1073267459869385, "global_step": 403956, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0814013481140137, "global_step": 403957, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.123598575592041, "global_step": 403958, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0331809520721436, "global_step": 403959, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.115572929382324, "global_step": 403960, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1143529415130615, "global_step": 403961, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9923079013824463, "global_step": 403962, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0404458045959473, "global_step": 403963, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.018658399581909, "global_step": 403964, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.186870813369751, "global_step": 403965, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.18393611907959, "global_step": 403966, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0594277381896973, "global_step": 403967, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.055365800857544, "global_step": 403968, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.065070629119873, "global_step": 403969, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1677215099334717, "global_step": 403970, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1474390029907227, "global_step": 403971, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.101763963699341, "global_step": 403972, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.077493667602539, "global_step": 403973, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0653021335601807, "global_step": 403974, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.09641170501709, "global_step": 403975, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.070631742477417, "global_step": 403976, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0830507278442383, "global_step": 403977, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1310598850250244, "global_step": 403978, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0412747859954834, "global_step": 403979, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0918760299682617, "global_step": 403980, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1186046600341797, "global_step": 403981, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.066743850708008, "global_step": 403982, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0842833518981934, "global_step": 403983, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.181199312210083, "global_step": 403984, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.142836332321167, "global_step": 403985, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1757278442382812, "global_step": 403986, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0526490211486816, "global_step": 403987, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.136420249938965, "global_step": 403988, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0251264572143555, "global_step": 403989, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0881145000457764, "global_step": 403990, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1648311614990234, "global_step": 403991, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0160741806030273, "global_step": 403992, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.10400390625, "global_step": 403993, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.096039295196533, "global_step": 403994, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0070505142211914, "global_step": 403995, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1062092781066895, "global_step": 403996, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0371317863464355, "global_step": 403997, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.166550874710083, "global_step": 403998, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0741140842437744, "global_step": 403999, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.130965232849121, "global_step": 404000, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.983715295791626, "global_step": 404001, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1247270107269287, "global_step": 404002, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0484180450439453, "global_step": 404003, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.2088687419891357, "global_step": 404004, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.079134702682495, "global_step": 404005, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1038944721221924, "global_step": 404006, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.099083423614502, "global_step": 404007, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0635688304901123, "global_step": 404008, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0590782165527344, "global_step": 404009, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1039228439331055, "global_step": 404010, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1149022579193115, "global_step": 404011, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.139458656311035, "global_step": 404012, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1352481842041016, "global_step": 404013, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.095465898513794, "global_step": 404014, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0786092281341553, "global_step": 404015, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.2297980785369873, "global_step": 404016, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.090243339538574, "global_step": 404017, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0407118797302246, "global_step": 404018, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0748274326324463, "global_step": 404019, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0780739784240723, "global_step": 404020, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.129751205444336, "global_step": 404021, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1358792781829834, "global_step": 404022, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0901901721954346, "global_step": 404023, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1316213607788086, "global_step": 404024, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0570735931396484, "global_step": 404025, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0924246311187744, "global_step": 404026, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1208736896514893, "global_step": 404027, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.112898111343384, "global_step": 404028, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0942344665527344, "global_step": 404029, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0872433185577393, "global_step": 404030, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.130387783050537, "global_step": 404031, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1518654823303223, "global_step": 404032, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0572099685668945, "global_step": 404033, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.349299192428589, "global_step": 404034, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0679423809051514, "global_step": 404035, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.063809394836426, "global_step": 404036, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.079627752304077, "global_step": 404037, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9913196563720703, "global_step": 404038, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0960445404052734, "global_step": 404039, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0313174724578857, "global_step": 404040, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0675339698791504, "global_step": 404041, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1094603538513184, "global_step": 404042, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.122091054916382, "global_step": 404043, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0652847290039062, "global_step": 404044, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0841805934906006, "global_step": 404045, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0897724628448486, "global_step": 404046, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1124603748321533, "global_step": 404047, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0210587978363037, "global_step": 404048, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.110065221786499, "global_step": 404049, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.113751173019409, "global_step": 404050, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.090935707092285, "global_step": 404051, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.021587610244751, "global_step": 404052, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0563509464263916, "global_step": 404053, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0745766162872314, "global_step": 404054, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1840076446533203, "global_step": 404055, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1472835540771484, "global_step": 404056, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.099544048309326, "global_step": 404057, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.064840316772461, "global_step": 404058, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.137096643447876, "global_step": 404059, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.142946481704712, "global_step": 404060, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1217782497406006, "global_step": 404061, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.149916887283325, "global_step": 404062, "epoch": 766, "lr": 5e-05}
{"train_loss": 1.9573886394500732, "global_step": 404063, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.153566837310791, "global_step": 404064, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0541908740997314, "global_step": 404065, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.2460367679595947, "global_step": 404066, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.063656806945801, "global_step": 404067, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.126202344894409, "global_step": 404068, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.052856206893921, "global_step": 404069, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.096151828765869, "global_step": 404070, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1723577976226807, "global_step": 404071, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1418099403381348, "global_step": 404072, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.146202802658081, "global_step": 404073, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.129647970199585, "global_step": 404074, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1194753646850586, "global_step": 404075, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0779569149017334, "global_step": 404076, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1437013149261475, "global_step": 404077, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.167405843734741, "global_step": 404078, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.184913396835327, "global_step": 404079, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0985770225524902, "global_step": 404080, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.105619192123413, "global_step": 404081, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1135056018829346, "global_step": 404082, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0241591930389404, "global_step": 404083, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.229640007019043, "global_step": 404084, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0928869247436523, "global_step": 404085, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.149616241455078, "global_step": 404086, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.2214529514312744, "global_step": 404087, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0283877849578857, "global_step": 404088, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1625118255615234, "global_step": 404089, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1616668701171875, "global_step": 404090, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1106395721435547, "global_step": 404091, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.106342077255249, "global_step": 404092, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0644774436950684, "global_step": 404093, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.10145902633667, "global_step": 404094, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0899925231933594, "global_step": 404095, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1152968406677246, "global_step": 404096, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.157238483428955, "global_step": 404097, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.086710214614868, "global_step": 404098, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0839614868164062, "global_step": 404099, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1022748947143555, "global_step": 404100, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1388115882873535, "global_step": 404101, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1160264015197754, "global_step": 404102, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0391480922698975, "global_step": 404103, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1003639698028564, "global_step": 404104, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.147082805633545, "global_step": 404105, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.085965156555176, "global_step": 404106, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0677666664123535, "global_step": 404107, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0726511478424072, "global_step": 404108, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.071366310119629, "global_step": 404109, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1120047569274902, "global_step": 404110, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1153972148895264, "global_step": 404111, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.097954034805298, "global_step": 404112, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0979058742523193, "global_step": 404113, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.106450319290161, "global_step": 404114, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0641396045684814, "global_step": 404115, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.100630044937134, "global_step": 404116, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.105959892272949, "global_step": 404117, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.111464262008667, "global_step": 404118, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1297247409820557, "global_step": 404119, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1315395832061768, "global_step": 404120, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.160337448120117, "global_step": 404121, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.069288492202759, "global_step": 404122, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0926127433776855, "global_step": 404123, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0980262756347656, "global_step": 404124, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0931100845336914, "global_step": 404125, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1398351192474365, "global_step": 404126, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.11594820022583, "global_step": 404127, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1076858043670654, "global_step": 404128, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1180806159973145, "global_step": 404129, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1565301418304443, "global_step": 404130, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1057286262512207, "global_step": 404131, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0935468673706055, "global_step": 404132, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0770750045776367, "global_step": 404133, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.017320394515991, "global_step": 404134, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0867700576782227, "global_step": 404135, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1016104221343994, "global_step": 404136, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0303404331207275, "global_step": 404137, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1071317195892334, "global_step": 404138, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1959080696105957, "global_step": 404139, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.075547695159912, "global_step": 404140, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1268346309661865, "global_step": 404141, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.133570432662964, "global_step": 404142, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.095952033996582, "global_step": 404143, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1193931102752686, "global_step": 404144, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1055119037628174, "global_step": 404145, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.082252264022827, "global_step": 404146, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.128969669342041, "global_step": 404147, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.158414602279663, "global_step": 404148, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.155644416809082, "global_step": 404149, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1673102378845215, "global_step": 404150, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0875227451324463, "global_step": 404151, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1621897220611572, "global_step": 404152, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.2045950889587402, "global_step": 404153, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0559425354003906, "global_step": 404154, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0789120197296143, "global_step": 404155, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1284995079040527, "global_step": 404156, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0468175411224365, "global_step": 404157, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0805633068084717, "global_step": 404158, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1548848152160645, "global_step": 404159, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.053346633911133, "global_step": 404160, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1908559799194336, "global_step": 404161, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.059772253036499, "global_step": 404162, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1131112575531006, "global_step": 404163, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.195098400115967, "global_step": 404164, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1935720443725586, "global_step": 404165, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0935490131378174, "global_step": 404166, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.062417984008789, "global_step": 404167, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0639119148254395, "global_step": 404168, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.147624969482422, "global_step": 404169, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1361300945281982, "global_step": 404170, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.128638982772827, "global_step": 404171, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1117050647735596, "global_step": 404172, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0834836959838867, "global_step": 404173, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1488192081451416, "global_step": 404174, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.036001205444336, "global_step": 404175, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.10136342048645, "global_step": 404176, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1825404167175293, "global_step": 404177, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0628042221069336, "global_step": 404178, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.12261700630188, "global_step": 404179, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.038987874984741, "global_step": 404180, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.055516242980957, "global_step": 404181, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.024142265319824, "global_step": 404182, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1384596824645996, "global_step": 404183, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0906856060028076, "global_step": 404184, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0100035667419434, "global_step": 404185, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1101841926574707, "global_step": 404186, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.027966022491455, "global_step": 404187, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.060281753540039, "global_step": 404188, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0760552883148193, "global_step": 404189, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.120119333267212, "global_step": 404190, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0704398155212402, "global_step": 404191, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.079759120941162, "global_step": 404192, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0603349208831787, "global_step": 404193, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.079817533493042, "global_step": 404194, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0562992095947266, "global_step": 404195, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.143195629119873, "global_step": 404196, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.111701726913452, "global_step": 404197, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1265881061553955, "global_step": 404198, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.008983612060547, "global_step": 404199, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.1453588008880615, "global_step": 404200, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.0685160160064697, "global_step": 404201, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.076131820678711, "global_step": 404202, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.122828722000122, "global_step": 404203, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.161468267440796, "global_step": 404204, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.095061779022217, "global_step": 404205, "epoch": 766, "lr": 5e-05}
{"train_loss": 2.101736068725586, "global_step": 404206, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.066394567489624, "global_step": 404207, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.02805233001709, "global_step": 404208, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.010286331176758, "global_step": 404209, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0675411224365234, "global_step": 404210, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.096820116043091, "global_step": 404211, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.063387155532837, "global_step": 404212, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9931511878967285, "global_step": 404213, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0731942653656006, "global_step": 404214, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.108048677444458, "global_step": 404215, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9279496669769287, "global_step": 404216, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1050593852996826, "global_step": 404217, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.068723440170288, "global_step": 404218, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1101694107055664, "global_step": 404219, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1479105949401855, "global_step": 404220, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1160731315612793, "global_step": 404221, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.115117311477661, "global_step": 404222, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.163203239440918, "global_step": 404223, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0913121700286865, "global_step": 404224, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0837552547454834, "global_step": 404225, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1095998287200928, "global_step": 404226, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0317318439483643, "global_step": 404227, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.070650815963745, "global_step": 404228, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0857067108154297, "global_step": 404229, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.099226236343384, "global_step": 404230, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1234889030456543, "global_step": 404231, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0651283264160156, "global_step": 404232, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.115736961364746, "global_step": 404233, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.047224760055542, "global_step": 404234, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.127209186553955, "global_step": 404235, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0200631618499756, "global_step": 404236, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0964200496673584, "global_step": 404237, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0509397983551025, "global_step": 404238, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0818841457366943, "global_step": 404239, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.004812717437744, "global_step": 404240, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0997672080993652, "global_step": 404241, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9764846563339233, "global_step": 404242, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9778398275375366, "global_step": 404243, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0860955715179443, "global_step": 404244, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.076164960861206, "global_step": 404245, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.153076648712158, "global_step": 404246, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.085909605026245, "global_step": 404247, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1340572834014893, "global_step": 404248, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0292935371398926, "global_step": 404249, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1206488609313965, "global_step": 404250, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1529176235198975, "global_step": 404251, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0052669048309326, "global_step": 404252, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1441798210144043, "global_step": 404253, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0782663822174072, "global_step": 404254, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1779983043670654, "global_step": 404255, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0551295280456543, "global_step": 404256, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.160876512527466, "global_step": 404257, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0513298511505127, "global_step": 404258, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.095801591873169, "global_step": 404259, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0623459815979004, "global_step": 404260, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0835583209991455, "global_step": 404261, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.115631580352783, "global_step": 404262, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.040891170501709, "global_step": 404263, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0546987056732178, "global_step": 404264, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1050214767456055, "global_step": 404265, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0903878211975098, "global_step": 404266, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0148868560791016, "global_step": 404267, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1356277465820312, "global_step": 404268, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1033682823181152, "global_step": 404269, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1728804111480713, "global_step": 404270, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.148334503173828, "global_step": 404271, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0960309505462646, "global_step": 404272, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.046776056289673, "global_step": 404273, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.091918706893921, "global_step": 404274, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0719213485717773, "global_step": 404275, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.185488700866699, "global_step": 404276, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0768883228302, "global_step": 404277, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0637617111206055, "global_step": 404278, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0069446563720703, "global_step": 404279, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1288411617279053, "global_step": 404280, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1062088012695312, "global_step": 404281, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1246464252471924, "global_step": 404282, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0678861141204834, "global_step": 404283, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1483683586120605, "global_step": 404284, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.965140461921692, "global_step": 404285, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1219120025634766, "global_step": 404286, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1240663528442383, "global_step": 404287, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.110645055770874, "global_step": 404288, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0737392902374268, "global_step": 404289, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1149187088012695, "global_step": 404290, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.077620267868042, "global_step": 404291, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1474690437316895, "global_step": 404292, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.058669090270996, "global_step": 404293, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9791592359542847, "global_step": 404294, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0907201766967773, "global_step": 404295, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1039350032806396, "global_step": 404296, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1044111251831055, "global_step": 404297, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1746795177459717, "global_step": 404298, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.090050220489502, "global_step": 404299, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.065237522125244, "global_step": 404300, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.069542407989502, "global_step": 404301, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.204099655151367, "global_step": 404302, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0665555000305176, "global_step": 404303, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.987680196762085, "global_step": 404304, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.021092176437378, "global_step": 404305, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0291805267333984, "global_step": 404306, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1096463203430176, "global_step": 404307, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.165581703186035, "global_step": 404308, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.088637113571167, "global_step": 404309, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1319034099578857, "global_step": 404310, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0908732414245605, "global_step": 404311, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0972113609313965, "global_step": 404312, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0969796180725098, "global_step": 404313, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1506237983703613, "global_step": 404314, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.085927963256836, "global_step": 404315, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1172971725463867, "global_step": 404316, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.129622220993042, "global_step": 404317, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1104471683502197, "global_step": 404318, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.114778757095337, "global_step": 404319, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1480891704559326, "global_step": 404320, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1008050441741943, "global_step": 404321, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1143996715545654, "global_step": 404322, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.074953079223633, "global_step": 404323, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1014397144317627, "global_step": 404324, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0623347759246826, "global_step": 404325, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.040557622909546, "global_step": 404326, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0283079147338867, "global_step": 404327, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.058514356613159, "global_step": 404328, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0155129432678223, "global_step": 404329, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.106476306915283, "global_step": 404330, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0489611625671387, "global_step": 404331, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1077821254730225, "global_step": 404332, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.107593297958374, "global_step": 404333, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.14077091217041, "global_step": 404334, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0859320163726807, "global_step": 404335, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1227831840515137, "global_step": 404336, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0353965759277344, "global_step": 404337, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.15058970451355, "global_step": 404338, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0283970832824707, "global_step": 404339, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.149336814880371, "global_step": 404340, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.184528350830078, "global_step": 404341, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0256235599517822, "global_step": 404342, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.065783977508545, "global_step": 404343, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.2265985012054443, "global_step": 404344, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.099482297897339, "global_step": 404345, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0854828357696533, "global_step": 404346, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0786826610565186, "global_step": 404347, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0051214694976807, "global_step": 404348, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.121722459793091, "global_step": 404349, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1009199619293213, "global_step": 404350, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.167306423187256, "global_step": 404351, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1389319896698, "global_step": 404352, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.062563419342041, "global_step": 404353, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0779387950897217, "global_step": 404354, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9784197807312012, "global_step": 404355, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1326217651367188, "global_step": 404356, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1233675479888916, "global_step": 404357, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1157355308532715, "global_step": 404358, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.074908971786499, "global_step": 404359, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0275943279266357, "global_step": 404360, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9933642148971558, "global_step": 404361, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1419146060943604, "global_step": 404362, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0055110454559326, "global_step": 404363, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.149576187133789, "global_step": 404364, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0270378589630127, "global_step": 404365, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0289387702941895, "global_step": 404366, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.060326337814331, "global_step": 404367, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0417399406433105, "global_step": 404368, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0716264247894287, "global_step": 404369, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0115785598754883, "global_step": 404370, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1768710613250732, "global_step": 404371, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1770150661468506, "global_step": 404372, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.155351161956787, "global_step": 404373, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1252553462982178, "global_step": 404374, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.157241106033325, "global_step": 404375, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9878336191177368, "global_step": 404376, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.150805950164795, "global_step": 404377, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.078726053237915, "global_step": 404378, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9802258014678955, "global_step": 404379, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1288516521453857, "global_step": 404380, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0948123931884766, "global_step": 404381, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.067991256713867, "global_step": 404382, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0340309143066406, "global_step": 404383, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1330819129943848, "global_step": 404384, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1314308643341064, "global_step": 404385, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.01042103767395, "global_step": 404386, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0695250034332275, "global_step": 404387, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0115103721618652, "global_step": 404388, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0947697162628174, "global_step": 404389, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.007735252380371, "global_step": 404390, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.087545394897461, "global_step": 404391, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1949455738067627, "global_step": 404392, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0730209350585938, "global_step": 404393, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1059415340423584, "global_step": 404394, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0969979763031006, "global_step": 404395, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1356797218322754, "global_step": 404396, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.174135446548462, "global_step": 404397, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1609902381896973, "global_step": 404398, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.013758659362793, "global_step": 404399, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.041792631149292, "global_step": 404400, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0315866470336914, "global_step": 404401, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1231751441955566, "global_step": 404402, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0680205821990967, "global_step": 404403, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0796306133270264, "global_step": 404404, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.122891664505005, "global_step": 404405, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0741357803344727, "global_step": 404406, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1358132362365723, "global_step": 404407, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1301932334899902, "global_step": 404408, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1056478023529053, "global_step": 404409, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.090623617172241, "global_step": 404410, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0886220932006836, "global_step": 404411, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0049757957458496, "global_step": 404412, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.142699956893921, "global_step": 404413, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.129816770553589, "global_step": 404414, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.100855827331543, "global_step": 404415, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.10211181640625, "global_step": 404416, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.158749580383301, "global_step": 404417, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.030764579772949, "global_step": 404418, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0484344959259033, "global_step": 404419, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.085702896118164, "global_step": 404420, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.090994358062744, "global_step": 404421, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.103853464126587, "global_step": 404422, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.096346139907837, "global_step": 404423, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1870439052581787, "global_step": 404424, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.2362072467803955, "global_step": 404425, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.088818311691284, "global_step": 404426, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0945165157318115, "global_step": 404427, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1236395835876465, "global_step": 404428, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0938878059387207, "global_step": 404429, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0948688983917236, "global_step": 404430, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0805418491363525, "global_step": 404431, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.111276388168335, "global_step": 404432, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0597903728485107, "global_step": 404433, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.058519124984741, "global_step": 404434, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.2087221145629883, "global_step": 404435, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1367762088775635, "global_step": 404436, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.077272653579712, "global_step": 404437, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0165247917175293, "global_step": 404438, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.135408639907837, "global_step": 404439, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1232690811157227, "global_step": 404440, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0395379066467285, "global_step": 404441, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.024235725402832, "global_step": 404442, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.117093086242676, "global_step": 404443, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0889670848846436, "global_step": 404444, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0913848876953125, "global_step": 404445, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.109661340713501, "global_step": 404446, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.078460931777954, "global_step": 404447, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.035897970199585, "global_step": 404448, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1346614360809326, "global_step": 404449, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.101187229156494, "global_step": 404450, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.100154399871826, "global_step": 404451, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.137392997741699, "global_step": 404452, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0524394512176514, "global_step": 404453, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1044089794158936, "global_step": 404454, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.13042950630188, "global_step": 404455, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1406800746917725, "global_step": 404456, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.13381290435791, "global_step": 404457, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1195712089538574, "global_step": 404458, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0853638648986816, "global_step": 404459, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.105142593383789, "global_step": 404460, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0826754570007324, "global_step": 404461, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1115686893463135, "global_step": 404462, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.119424343109131, "global_step": 404463, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.053544521331787, "global_step": 404464, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9648313522338867, "global_step": 404465, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.103001117706299, "global_step": 404466, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.01599383354187, "global_step": 404467, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.059199094772339, "global_step": 404468, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1207523345947266, "global_step": 404469, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.105969190597534, "global_step": 404470, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.077014446258545, "global_step": 404471, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0654125213623047, "global_step": 404472, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0975000858306885, "global_step": 404473, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.076819896697998, "global_step": 404474, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0345730781555176, "global_step": 404475, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0771334171295166, "global_step": 404476, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0759451389312744, "global_step": 404477, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1142101287841797, "global_step": 404478, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0878310203552246, "global_step": 404479, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.067859172821045, "global_step": 404480, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0235490798950195, "global_step": 404481, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.084602117538452, "global_step": 404482, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.142019033432007, "global_step": 404483, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.114570140838623, "global_step": 404484, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.127689838409424, "global_step": 404485, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1468451023101807, "global_step": 404486, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.110896587371826, "global_step": 404487, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1077699661254883, "global_step": 404488, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.09389066696167, "global_step": 404489, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.110419988632202, "global_step": 404490, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.076164484024048, "global_step": 404491, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.150789499282837, "global_step": 404492, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.044522285461426, "global_step": 404493, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.044692277908325, "global_step": 404494, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1746349334716797, "global_step": 404495, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.059574604034424, "global_step": 404496, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0911107063293457, "global_step": 404497, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1528990268707275, "global_step": 404498, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0523765087127686, "global_step": 404499, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.221688747406006, "global_step": 404500, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.077453374862671, "global_step": 404501, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.13187313079834, "global_step": 404502, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0878918170928955, "global_step": 404503, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.004727363586426, "global_step": 404504, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9942357540130615, "global_step": 404505, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.128185749053955, "global_step": 404506, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.081620216369629, "global_step": 404507, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1058695316314697, "global_step": 404508, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0457823276519775, "global_step": 404509, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.071521282196045, "global_step": 404510, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1457252502441406, "global_step": 404511, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.094848394393921, "global_step": 404512, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.197458028793335, "global_step": 404513, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.078467845916748, "global_step": 404514, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1153881549835205, "global_step": 404515, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1468441486358643, "global_step": 404516, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1125736236572266, "global_step": 404517, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.015317440032959, "global_step": 404518, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.096113681793213, "global_step": 404519, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.22318696975708, "global_step": 404520, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.066378593444824, "global_step": 404521, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.168590545654297, "global_step": 404522, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.12498140335083, "global_step": 404523, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1009597778320312, "global_step": 404524, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.030996561050415, "global_step": 404525, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0101726055145264, "global_step": 404526, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1225056648254395, "global_step": 404527, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0944716930389404, "global_step": 404528, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.039022922515869, "global_step": 404529, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.073976516723633, "global_step": 404530, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.075249195098877, "global_step": 404531, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.035027265548706, "global_step": 404532, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1026804447174072, "global_step": 404533, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1134374141693115, "global_step": 404534, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.105518102645874, "global_step": 404535, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0229735374450684, "global_step": 404536, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.095890998840332, "global_step": 404537, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.03855037689209, "global_step": 404538, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.067985773086548, "global_step": 404539, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.105304718017578, "global_step": 404540, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1138672828674316, "global_step": 404541, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0894906520843506, "global_step": 404542, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1447384357452393, "global_step": 404543, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.034947395324707, "global_step": 404544, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.068974256515503, "global_step": 404545, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0822317600250244, "global_step": 404546, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.014617443084717, "global_step": 404547, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.118367910385132, "global_step": 404548, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.115215301513672, "global_step": 404549, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0961906909942627, "global_step": 404550, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0946385860443115, "global_step": 404551, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1712265014648438, "global_step": 404552, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.13830304145813, "global_step": 404553, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.053471326828003, "global_step": 404554, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.138160467147827, "global_step": 404555, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0747530460357666, "global_step": 404556, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0571866035461426, "global_step": 404557, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0929114818573, "global_step": 404558, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1468842029571533, "global_step": 404559, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.117079019546509, "global_step": 404560, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0537984371185303, "global_step": 404561, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.047653913497925, "global_step": 404562, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0904271602630615, "global_step": 404563, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0864782333374023, "global_step": 404564, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.038778781890869, "global_step": 404565, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.081467866897583, "global_step": 404566, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.082486629486084, "global_step": 404567, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1519696712493896, "global_step": 404568, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1249232292175293, "global_step": 404569, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.2183306217193604, "global_step": 404570, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.095759868621826, "global_step": 404571, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0801730155944824, "global_step": 404572, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.2054548263549805, "global_step": 404573, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0911452770233154, "global_step": 404574, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1583380699157715, "global_step": 404575, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.127394676208496, "global_step": 404576, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0566325187683105, "global_step": 404577, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0116543769836426, "global_step": 404578, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.002574920654297, "global_step": 404579, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.061655044555664, "global_step": 404580, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0030927658081055, "global_step": 404581, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.042538642883301, "global_step": 404582, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1093862056732178, "global_step": 404583, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.158031463623047, "global_step": 404584, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.028186321258545, "global_step": 404585, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.164311408996582, "global_step": 404586, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0878989696502686, "global_step": 404587, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0944268703460693, "global_step": 404588, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1388299465179443, "global_step": 404589, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1191458702087402, "global_step": 404590, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0302252769470215, "global_step": 404591, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0727622509002686, "global_step": 404592, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.104321241378784, "global_step": 404593, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.05316162109375, "global_step": 404594, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1025354862213135, "global_step": 404595, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.029994249343872, "global_step": 404596, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0791170597076416, "global_step": 404597, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0592217445373535, "global_step": 404598, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.101438522338867, "global_step": 404599, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0792717933654785, "global_step": 404600, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.155390501022339, "global_step": 404601, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1329004764556885, "global_step": 404602, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.001875877380371, "global_step": 404603, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.2039928436279297, "global_step": 404604, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0887060165405273, "global_step": 404605, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9977537393569946, "global_step": 404606, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.164219379425049, "global_step": 404607, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.079256296157837, "global_step": 404608, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.147007465362549, "global_step": 404609, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0378308296203613, "global_step": 404610, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.066570997238159, "global_step": 404611, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9589704275131226, "global_step": 404612, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0527145862579346, "global_step": 404613, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.112959146499634, "global_step": 404614, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0641465187072754, "global_step": 404615, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0909860134124756, "global_step": 404616, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1089329719543457, "global_step": 404617, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.118748188018799, "global_step": 404618, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1778197288513184, "global_step": 404619, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.106492757797241, "global_step": 404620, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9504766464233398, "global_step": 404621, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.136657238006592, "global_step": 404622, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.070773124694824, "global_step": 404623, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.088195323944092, "global_step": 404624, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1248507499694824, "global_step": 404625, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.057103395462036, "global_step": 404626, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1259472370147705, "global_step": 404627, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.142510175704956, "global_step": 404628, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1582272052764893, "global_step": 404629, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0738179683685303, "global_step": 404630, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0922625064849854, "global_step": 404631, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.01971173286438, "global_step": 404632, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0828959941864014, "global_step": 404633, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.121518611907959, "global_step": 404634, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.053760528564453, "global_step": 404635, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1193606853485107, "global_step": 404636, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0897815227508545, "global_step": 404637, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.049527406692505, "global_step": 404638, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0437369346618652, "global_step": 404639, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.039924144744873, "global_step": 404640, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1113498210906982, "global_step": 404641, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0222156047821045, "global_step": 404642, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.110697031021118, "global_step": 404643, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1842498779296875, "global_step": 404644, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1158034801483154, "global_step": 404645, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.080873489379883, "global_step": 404646, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.068004846572876, "global_step": 404647, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1633899211883545, "global_step": 404648, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.029926300048828, "global_step": 404649, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.035184144973755, "global_step": 404650, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.156644582748413, "global_step": 404651, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.062286376953125, "global_step": 404652, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0403220653533936, "global_step": 404653, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1071646213531494, "global_step": 404654, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.011448383331299, "global_step": 404655, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.083569288253784, "global_step": 404656, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1684908866882324, "global_step": 404657, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.121093511581421, "global_step": 404658, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1552233695983887, "global_step": 404659, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0983457565307617, "global_step": 404660, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0936520099639893, "global_step": 404661, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.05850887298584, "global_step": 404662, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0645763874053955, "global_step": 404663, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0253372192382812, "global_step": 404664, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.155292510986328, "global_step": 404665, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.008810043334961, "global_step": 404666, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1063387393951416, "global_step": 404667, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9909732341766357, "global_step": 404668, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0643999576568604, "global_step": 404669, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0804977416992188, "global_step": 404670, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0488243103027344, "global_step": 404671, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9788086414337158, "global_step": 404672, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0244626998901367, "global_step": 404673, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.150064706802368, "global_step": 404674, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1121668815612793, "global_step": 404675, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1685714721679688, "global_step": 404676, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.085869789123535, "global_step": 404677, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1675639152526855, "global_step": 404678, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1032910346984863, "global_step": 404679, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0827016830444336, "global_step": 404680, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0095322132110596, "global_step": 404681, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.058562994003296, "global_step": 404682, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1122894287109375, "global_step": 404683, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0246100425720215, "global_step": 404684, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0743942260742188, "global_step": 404685, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0090160369873047, "global_step": 404686, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0170416831970215, "global_step": 404687, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0566670894622803, "global_step": 404688, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.07446026802063, "global_step": 404689, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1468377113342285, "global_step": 404690, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.042619466781616, "global_step": 404691, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.102787733078003, "global_step": 404692, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1629486083984375, "global_step": 404693, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.191692590713501, "global_step": 404694, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1055541038513184, "global_step": 404695, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1399619579315186, "global_step": 404696, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.100127696990967, "global_step": 404697, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.111633777618408, "global_step": 404698, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.060816526412964, "global_step": 404699, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.010420322418213, "global_step": 404700, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.084198236465454, "global_step": 404701, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1219284534454346, "global_step": 404702, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.066852569580078, "global_step": 404703, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1159234046936035, "global_step": 404704, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0382468700408936, "global_step": 404705, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.05724835395813, "global_step": 404706, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.197746992111206, "global_step": 404707, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.151822090148926, "global_step": 404708, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0748374462127686, "global_step": 404709, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.154702663421631, "global_step": 404710, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0624096393585205, "global_step": 404711, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.094320058822632, "global_step": 404712, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.973692774772644, "global_step": 404713, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.105090856552124, "global_step": 404714, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.164820432662964, "global_step": 404715, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.13928484916687, "global_step": 404716, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.038212299346924, "global_step": 404717, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.065991163253784, "global_step": 404718, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.088107109069824, "global_step": 404719, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1442203521728516, "global_step": 404720, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.111660957336426, "global_step": 404721, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1189632415771484, "global_step": 404722, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0779306888580322, "global_step": 404723, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.143974542617798, "global_step": 404724, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0075418949127197, "global_step": 404725, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0325214862823486, "global_step": 404726, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0282442569732666, "global_step": 404727, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.08874773979187, "global_step": 404728, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.11912202835083, "global_step": 404729, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0464227199554443, "global_step": 404730, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1478137969970703, "global_step": 404731, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0319297313690186, "global_step": 404732, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.153287172317505, "global_step": 404733, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.089989423751831, "global_step": 404734, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.015449047088623, "global_step": 404735, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1102778911590576, "global_step": 404736, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.111752986907959, "global_step": 404737, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0561141967773438, "global_step": 404738, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1291167736053467, "global_step": 404739, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.005887031555176, "global_step": 404740, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.061245918273926, "global_step": 404741, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0676939487457275, "global_step": 404742, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.005262613296509, "global_step": 404743, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.130847692489624, "global_step": 404744, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1438872814178467, "global_step": 404745, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0943570137023926, "global_step": 404746, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.139414072036743, "global_step": 404747, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0251736640930176, "global_step": 404748, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.07393741607666, "global_step": 404749, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1123363971710205, "global_step": 404750, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0209851264953613, "global_step": 404751, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.072085380554199, "global_step": 404752, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.036447048187256, "global_step": 404753, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1794495582580566, "global_step": 404754, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1272823810577393, "global_step": 404755, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.143892765045166, "global_step": 404756, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0902719497680664, "global_step": 404757, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1652708053588867, "global_step": 404758, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.039067268371582, "global_step": 404759, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.037602424621582, "global_step": 404760, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0830302238464355, "global_step": 404761, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.091862678527832, "global_step": 404762, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1093358993530273, "global_step": 404763, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1487107276916504, "global_step": 404764, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.085535764694214, "global_step": 404765, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1177175045013428, "global_step": 404766, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0777719020843506, "global_step": 404767, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0807266235351562, "global_step": 404768, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.028740167617798, "global_step": 404769, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0838139057159424, "global_step": 404770, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9707432985305786, "global_step": 404771, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0605039596557617, "global_step": 404772, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.092198133468628, "global_step": 404773, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1666855812072754, "global_step": 404774, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0866239070892334, "global_step": 404775, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1470837593078613, "global_step": 404776, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.121136426925659, "global_step": 404777, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0932793617248535, "global_step": 404778, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.009871006011963, "global_step": 404779, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0626730918884277, "global_step": 404780, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1164286136627197, "global_step": 404781, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.063053607940674, "global_step": 404782, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.161608934402466, "global_step": 404783, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0215206146240234, "global_step": 404784, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.141221761703491, "global_step": 404785, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0664122104644775, "global_step": 404786, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.127211093902588, "global_step": 404787, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.098775863647461, "global_step": 404788, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.122436761856079, "global_step": 404789, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.063990831375122, "global_step": 404790, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0509755611419678, "global_step": 404791, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0999484062194824, "global_step": 404792, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.2016148567199707, "global_step": 404793, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0903379917144775, "global_step": 404794, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.10506010055542, "global_step": 404795, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0945143699645996, "global_step": 404796, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1040494441986084, "global_step": 404797, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9771066904067993, "global_step": 404798, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.18152117729187, "global_step": 404799, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1232798099517822, "global_step": 404800, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.165588140487671, "global_step": 404801, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0921525955200195, "global_step": 404802, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.018099308013916, "global_step": 404803, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0960540771484375, "global_step": 404804, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.044959783554077, "global_step": 404805, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1170756816864014, "global_step": 404806, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0443389415740967, "global_step": 404807, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.073880434036255, "global_step": 404808, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0746450424194336, "global_step": 404809, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.094606876373291, "global_step": 404810, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.155734062194824, "global_step": 404811, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.111997604370117, "global_step": 404812, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.08632230758667, "global_step": 404813, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0587921142578125, "global_step": 404814, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1080124378204346, "global_step": 404815, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0911877155303955, "global_step": 404816, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1712141036987305, "global_step": 404817, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1173830032348633, "global_step": 404818, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.120069742202759, "global_step": 404819, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0761682987213135, "global_step": 404820, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0822715759277344, "global_step": 404821, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1258246898651123, "global_step": 404822, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1276955604553223, "global_step": 404823, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0136325359344482, "global_step": 404824, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.218637704849243, "global_step": 404825, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.088665723800659, "global_step": 404826, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1103761196136475, "global_step": 404827, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0698187351226807, "global_step": 404828, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1136224269866943, "global_step": 404829, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1800410747528076, "global_step": 404830, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0963587760925293, "global_step": 404831, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0957682132720947, "global_step": 404832, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.05017352104187, "global_step": 404833, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1187379360198975, "global_step": 404834, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.140540599822998, "global_step": 404835, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1441762447357178, "global_step": 404836, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.087754249572754, "global_step": 404837, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0210540294647217, "global_step": 404838, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.028855085372925, "global_step": 404839, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.01005482673645, "global_step": 404840, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.223694324493408, "global_step": 404841, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.131629228591919, "global_step": 404842, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1638107299804688, "global_step": 404843, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.100416421890259, "global_step": 404844, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.2012875080108643, "global_step": 404845, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0384328365325928, "global_step": 404846, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1051948070526123, "global_step": 404847, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.089280843734741, "global_step": 404848, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0485289096832275, "global_step": 404849, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0120694637298584, "global_step": 404850, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.088672399520874, "global_step": 404851, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1275277137756348, "global_step": 404852, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.089169979095459, "global_step": 404853, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.128937244415283, "global_step": 404854, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1138412952423096, "global_step": 404855, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0327491760253906, "global_step": 404856, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.088629961013794, "global_step": 404857, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.124847888946533, "global_step": 404858, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0163631439208984, "global_step": 404859, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.012026786804199, "global_step": 404860, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.142749309539795, "global_step": 404861, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0770814418792725, "global_step": 404862, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.070376396179199, "global_step": 404863, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1398415565490723, "global_step": 404864, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.083123207092285, "global_step": 404865, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1049935817718506, "global_step": 404866, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1700077056884766, "global_step": 404867, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.125819206237793, "global_step": 404868, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0917038917541504, "global_step": 404869, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0042202472686768, "global_step": 404870, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.994055986404419, "global_step": 404871, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.079197883605957, "global_step": 404872, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.113363027572632, "global_step": 404873, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.090775728225708, "global_step": 404874, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.074620008468628, "global_step": 404875, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1165568828582764, "global_step": 404876, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0859320163726807, "global_step": 404877, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1061768531799316, "global_step": 404878, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1268489360809326, "global_step": 404879, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0316455364227295, "global_step": 404880, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.155521869659424, "global_step": 404881, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1441149711608887, "global_step": 404882, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.03769850730896, "global_step": 404883, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.008018732070923, "global_step": 404884, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0842907428741455, "global_step": 404885, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0498931407928467, "global_step": 404886, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0547256469726562, "global_step": 404887, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1197850704193115, "global_step": 404888, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1421165466308594, "global_step": 404889, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.148550271987915, "global_step": 404890, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.084801197052002, "global_step": 404891, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9999427795410156, "global_step": 404892, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1698696613311768, "global_step": 404893, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0578653812408447, "global_step": 404894, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1906239986419678, "global_step": 404895, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.030308246612549, "global_step": 404896, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0922024250030518, "global_step": 404897, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.078068494796753, "global_step": 404898, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.146150827407837, "global_step": 404899, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1417219638824463, "global_step": 404900, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1413965225219727, "global_step": 404901, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0429372787475586, "global_step": 404902, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0442097187042236, "global_step": 404903, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0812833309173584, "global_step": 404904, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0239739418029785, "global_step": 404905, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.13114070892334, "global_step": 404906, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0649025440216064, "global_step": 404907, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.048654317855835, "global_step": 404908, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0814085006713867, "global_step": 404909, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.146801471710205, "global_step": 404910, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0704736709594727, "global_step": 404911, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.123906135559082, "global_step": 404912, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1572682857513428, "global_step": 404913, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.067720651626587, "global_step": 404914, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.07957124710083, "global_step": 404915, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.050347089767456, "global_step": 404916, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.135089159011841, "global_step": 404917, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.083498954772949, "global_step": 404918, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.063133478164673, "global_step": 404919, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1257050037384033, "global_step": 404920, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.107330322265625, "global_step": 404921, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0793120861053467, "global_step": 404922, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0720903873443604, "global_step": 404923, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1020593643188477, "global_step": 404924, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.094059705734253, "global_step": 404925, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0562734603881836, "global_step": 404926, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.026963949203491, "global_step": 404927, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.012120008468628, "global_step": 404928, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0114822387695312, "global_step": 404929, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1324830055236816, "global_step": 404930, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0802557468414307, "global_step": 404931, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0480828285217285, "global_step": 404932, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.093381643295288, "global_step": 404933, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0575144290924072, "global_step": 404934, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0626907348632812, "global_step": 404935, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0612127780914307, "global_step": 404936, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.091468572616577, "global_step": 404937, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0066821575164795, "global_step": 404938, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.216486930847168, "global_step": 404939, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1202497482299805, "global_step": 404940, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0479395389556885, "global_step": 404941, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.104231595993042, "global_step": 404942, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1121318340301514, "global_step": 404943, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.100749969482422, "global_step": 404944, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.150388479232788, "global_step": 404945, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.13010573387146, "global_step": 404946, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1498165130615234, "global_step": 404947, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.145286798477173, "global_step": 404948, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0565946102142334, "global_step": 404949, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.103963613510132, "global_step": 404950, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1058948040008545, "global_step": 404951, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.102943181991577, "global_step": 404952, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.173100233078003, "global_step": 404953, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0938222408294678, "global_step": 404954, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.043930768966675, "global_step": 404955, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1078264713287354, "global_step": 404956, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9913122653961182, "global_step": 404957, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0646183490753174, "global_step": 404958, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1341617107391357, "global_step": 404959, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0733814239501953, "global_step": 404960, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.156527280807495, "global_step": 404961, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1656265258789062, "global_step": 404962, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.134647846221924, "global_step": 404963, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.064814329147339, "global_step": 404964, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.031195878982544, "global_step": 404965, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.044818162918091, "global_step": 404966, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1442861557006836, "global_step": 404967, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.048055410385132, "global_step": 404968, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.063206195831299, "global_step": 404969, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0282676219940186, "global_step": 404970, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0012731552124023, "global_step": 404971, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1475181579589844, "global_step": 404972, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0744643211364746, "global_step": 404973, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0476553440093994, "global_step": 404974, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.096238374710083, "global_step": 404975, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1774544715881348, "global_step": 404976, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.057521343231201, "global_step": 404977, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.114008665084839, "global_step": 404978, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.024411678314209, "global_step": 404979, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1464333534240723, "global_step": 404980, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0933802127838135, "global_step": 404981, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.097618579864502, "global_step": 404982, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.138561248779297, "global_step": 404983, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.077967882156372, "global_step": 404984, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.120485782623291, "global_step": 404985, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.085690498352051, "global_step": 404986, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0973587036132812, "global_step": 404987, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.117361068725586, "global_step": 404988, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.104952573776245, "global_step": 404989, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0923244953155518, "global_step": 404990, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0895402431488037, "global_step": 404991, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0697696208953857, "global_step": 404992, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.125091791152954, "global_step": 404993, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.115844488143921, "global_step": 404994, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.15474009513855, "global_step": 404995, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.165444850921631, "global_step": 404996, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0261988639831543, "global_step": 404997, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0682780742645264, "global_step": 404998, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.285804033279419, "global_step": 404999, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.11848783493042, "global_step": 405000, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.036447525024414, "global_step": 405001, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1532154083251953, "global_step": 405002, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1533608436584473, "global_step": 405003, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0746684074401855, "global_step": 405004, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.060105085372925, "global_step": 405005, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.054671287536621, "global_step": 405006, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1443958282470703, "global_step": 405007, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.144496202468872, "global_step": 405008, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.102708578109741, "global_step": 405009, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.012641668319702, "global_step": 405010, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.109299659729004, "global_step": 405011, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1078341007232666, "global_step": 405012, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.136547565460205, "global_step": 405013, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0531725883483887, "global_step": 405014, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0702574253082275, "global_step": 405015, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.042344331741333, "global_step": 405016, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.109022617340088, "global_step": 405017, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.052708864212036, "global_step": 405018, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0891683101654053, "global_step": 405019, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0938546657562256, "global_step": 405020, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0587821006774902, "global_step": 405021, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0515248775482178, "global_step": 405022, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1060829162597656, "global_step": 405023, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1306912899017334, "global_step": 405024, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1230103969573975, "global_step": 405025, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.097600221633911, "global_step": 405026, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.00321102142334, "global_step": 405027, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.088615655899048, "global_step": 405028, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0894734859466553, "global_step": 405029, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0390660762786865, "global_step": 405030, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.030038356781006, "global_step": 405031, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0614442825317383, "global_step": 405032, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.159348964691162, "global_step": 405033, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.189605474472046, "global_step": 405034, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0127713680267334, "global_step": 405035, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0523505210876465, "global_step": 405036, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1433610916137695, "global_step": 405037, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0965256690979004, "global_step": 405038, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.085808753967285, "global_step": 405039, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0756924152374268, "global_step": 405040, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1043131351470947, "global_step": 405041, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1039252281188965, "global_step": 405042, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.088872194290161, "global_step": 405043, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.06337571144104, "global_step": 405044, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1068952083587646, "global_step": 405045, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.119089126586914, "global_step": 405046, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.138411521911621, "global_step": 405047, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1424760818481445, "global_step": 405048, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0541305541992188, "global_step": 405049, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.110567808151245, "global_step": 405050, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.129075765609741, "global_step": 405051, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1028120517730713, "global_step": 405052, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0801143646240234, "global_step": 405053, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0614914894104004, "global_step": 405054, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.078385829925537, "global_step": 405055, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1011946201324463, "global_step": 405056, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.060472011566162, "global_step": 405057, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0350067615509033, "global_step": 405058, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.093278408050537, "global_step": 405059, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.044442892074585, "global_step": 405060, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0853335857391357, "global_step": 405061, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.09865140914917, "global_step": 405062, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.023965835571289, "global_step": 405063, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1220085620880127, "global_step": 405064, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1498923301696777, "global_step": 405065, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0782251358032227, "global_step": 405066, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1233291625976562, "global_step": 405067, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0292410850524902, "global_step": 405068, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.2038209438323975, "global_step": 405069, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0785481929779053, "global_step": 405070, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1352035999298096, "global_step": 405071, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.157851219177246, "global_step": 405072, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.181943893432617, "global_step": 405073, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.122159719467163, "global_step": 405074, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.139153003692627, "global_step": 405075, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0642800331115723, "global_step": 405076, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1081533432006836, "global_step": 405077, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.137688398361206, "global_step": 405078, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.076648473739624, "global_step": 405079, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0921578407287598, "global_step": 405080, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0737922191619873, "global_step": 405081, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0794060230255127, "global_step": 405082, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.147804021835327, "global_step": 405083, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0866363048553467, "global_step": 405084, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0822629928588867, "global_step": 405085, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.022043228149414, "global_step": 405086, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1330974102020264, "global_step": 405087, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.136033773422241, "global_step": 405088, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.2141213417053223, "global_step": 405089, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0606303215026855, "global_step": 405090, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.033240556716919, "global_step": 405091, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.103104591369629, "global_step": 405092, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.109571933746338, "global_step": 405093, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.14398455619812, "global_step": 405094, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1362786293029785, "global_step": 405095, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.129666566848755, "global_step": 405096, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1237473487854004, "global_step": 405097, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.102705717086792, "global_step": 405098, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0120296478271484, "global_step": 405099, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0668272972106934, "global_step": 405100, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.138943910598755, "global_step": 405101, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0695505142211914, "global_step": 405102, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1258909702301025, "global_step": 405103, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.134709596633911, "global_step": 405104, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1580750942230225, "global_step": 405105, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0705506801605225, "global_step": 405106, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0530288219451904, "global_step": 405107, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.159217119216919, "global_step": 405108, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.061396598815918, "global_step": 405109, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0735437870025635, "global_step": 405110, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.067349672317505, "global_step": 405111, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.034768581390381, "global_step": 405112, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0928492546081543, "global_step": 405113, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1231606006622314, "global_step": 405114, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1590137481689453, "global_step": 405115, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0708632469177246, "global_step": 405116, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1454241275787354, "global_step": 405117, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1245272159576416, "global_step": 405118, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.138317823410034, "global_step": 405119, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.029047727584839, "global_step": 405120, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1117818355560303, "global_step": 405121, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1038413047790527, "global_step": 405122, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1040396690368652, "global_step": 405123, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0879080295562744, "global_step": 405124, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0665152072906494, "global_step": 405125, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0467569828033447, "global_step": 405126, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.107591152191162, "global_step": 405127, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.169516086578369, "global_step": 405128, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.123636484146118, "global_step": 405129, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1154613494873047, "global_step": 405130, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.12910532951355, "global_step": 405131, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1278257369995117, "global_step": 405132, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9830021858215332, "global_step": 405133, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0956850051879883, "global_step": 405134, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.204557180404663, "global_step": 405135, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1114108562469482, "global_step": 405136, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.970989465713501, "global_step": 405137, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1183578968048096, "global_step": 405138, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0848326683044434, "global_step": 405139, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1336793899536133, "global_step": 405140, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.097374677658081, "global_step": 405141, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.102769613265991, "global_step": 405142, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1887154579162598, "global_step": 405143, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1077826023101807, "global_step": 405144, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1687960624694824, "global_step": 405145, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0509793758392334, "global_step": 405146, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0524067878723145, "global_step": 405147, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0960495471954346, "global_step": 405148, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.05468487739563, "global_step": 405149, "epoch": 767, "lr": 5e-05}
{"train_loss": 1.9877468347549438, "global_step": 405150, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0476186275482178, "global_step": 405151, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1299877166748047, "global_step": 405152, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.030109405517578, "global_step": 405153, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.095975875854492, "global_step": 405154, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1265132427215576, "global_step": 405155, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.081740617752075, "global_step": 405156, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0660436153411865, "global_step": 405157, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.018864154815674, "global_step": 405158, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.2223944664001465, "global_step": 405159, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1140542030334473, "global_step": 405160, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.11422061920166, "global_step": 405161, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.143810749053955, "global_step": 405162, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.1287097930908203, "global_step": 405163, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.143832206726074, "global_step": 405164, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0709095001220703, "global_step": 405165, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.075183868408203, "global_step": 405166, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0527684688568115, "global_step": 405167, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.140106439590454, "global_step": 405168, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.184577226638794, "global_step": 405169, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.037526845932007, "global_step": 405170, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0524559020996094, "global_step": 405171, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0682055950164795, "global_step": 405172, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0281825065612793, "global_step": 405173, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.091733694076538, "global_step": 405174, "epoch": 767, "lr": 5e-05}
{"train_loss": 2.0469744205474854, "global_step": 405175, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1282546520233154, "global_step": 405176, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1112897396087646, "global_step": 405177, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0438339710235596, "global_step": 405178, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.093444347381592, "global_step": 405179, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.044661521911621, "global_step": 405180, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.124958038330078, "global_step": 405181, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1034135818481445, "global_step": 405182, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0145750045776367, "global_step": 405183, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0514700412750244, "global_step": 405184, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1099581718444824, "global_step": 405185, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.125999689102173, "global_step": 405186, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.096458911895752, "global_step": 405187, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.028163194656372, "global_step": 405188, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1797285079956055, "global_step": 405189, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.059591293334961, "global_step": 405190, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0310776233673096, "global_step": 405191, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1381561756134033, "global_step": 405192, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.091567039489746, "global_step": 405193, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0903193950653076, "global_step": 405194, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.055023193359375, "global_step": 405195, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.01324725151062, "global_step": 405196, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.103801965713501, "global_step": 405197, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1788530349731445, "global_step": 405198, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.168006420135498, "global_step": 405199, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1015677452087402, "global_step": 405200, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1448445320129395, "global_step": 405201, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.071193218231201, "global_step": 405202, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.063890218734741, "global_step": 405203, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.03478741645813, "global_step": 405204, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.102121114730835, "global_step": 405205, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.096757173538208, "global_step": 405206, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.086726427078247, "global_step": 405207, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0655150413513184, "global_step": 405208, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0930798053741455, "global_step": 405209, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.126455307006836, "global_step": 405210, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.999456763267517, "global_step": 405211, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0351457595825195, "global_step": 405212, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.063401699066162, "global_step": 405213, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1208059787750244, "global_step": 405214, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.07810640335083, "global_step": 405215, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.051607131958008, "global_step": 405216, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.130038022994995, "global_step": 405217, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.054131507873535, "global_step": 405218, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.99764084815979, "global_step": 405219, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0198888778686523, "global_step": 405220, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0646634101867676, "global_step": 405221, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.149982213973999, "global_step": 405222, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1525967121124268, "global_step": 405223, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.126120090484619, "global_step": 405224, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.033186197280884, "global_step": 405225, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.034743547439575, "global_step": 405226, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9969432353973389, "global_step": 405227, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0126819610595703, "global_step": 405228, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.182040214538574, "global_step": 405229, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.145073413848877, "global_step": 405230, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.121318817138672, "global_step": 405231, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.137347459793091, "global_step": 405232, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.12088942527771, "global_step": 405233, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.111330270767212, "global_step": 405234, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.022800922393799, "global_step": 405235, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1455860137939453, "global_step": 405236, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.146883726119995, "global_step": 405237, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.043707847595215, "global_step": 405238, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0650534629821777, "global_step": 405239, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0207743644714355, "global_step": 405240, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0376577377319336, "global_step": 405241, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0998363494873047, "global_step": 405242, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.023408889770508, "global_step": 405243, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0464842319488525, "global_step": 405244, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0029101371765137, "global_step": 405245, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.085862874984741, "global_step": 405246, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.04297137260437, "global_step": 405247, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0832033157348633, "global_step": 405248, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0784833431243896, "global_step": 405249, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0332045555114746, "global_step": 405250, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.096266746520996, "global_step": 405251, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.029719114303589, "global_step": 405252, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1319828033447266, "global_step": 405253, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0693633556365967, "global_step": 405254, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0425209999084473, "global_step": 405255, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1313722133636475, "global_step": 405256, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.976662278175354, "global_step": 405257, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.084581136703491, "global_step": 405258, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.108123302459717, "global_step": 405259, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.019306182861328, "global_step": 405260, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.2155182361602783, "global_step": 405261, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.104288101196289, "global_step": 405262, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1075921058654785, "global_step": 405263, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.15329909324646, "global_step": 405264, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1124699115753174, "global_step": 405265, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0835039615631104, "global_step": 405266, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0247933864593506, "global_step": 405267, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0502517223358154, "global_step": 405268, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.076200246810913, "global_step": 405269, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.135814905166626, "global_step": 405270, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0313899517059326, "global_step": 405271, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0666680335998535, "global_step": 405272, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0396885871887207, "global_step": 405273, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0549325942993164, "global_step": 405274, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0490572452545166, "global_step": 405275, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.152735471725464, "global_step": 405276, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1218671798706055, "global_step": 405277, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.130965232849121, "global_step": 405278, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.057330369949341, "global_step": 405279, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0627481937408447, "global_step": 405280, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1344757080078125, "global_step": 405281, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.136901378631592, "global_step": 405282, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0258212089538574, "global_step": 405283, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.087019205093384, "global_step": 405284, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1432106494903564, "global_step": 405285, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1641905307769775, "global_step": 405286, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1005892753601074, "global_step": 405287, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.048076868057251, "global_step": 405288, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1112074851989746, "global_step": 405289, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1302719116210938, "global_step": 405290, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.000663995742798, "global_step": 405291, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1327319145202637, "global_step": 405292, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1043341159820557, "global_step": 405293, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.084953546524048, "global_step": 405294, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0632026195526123, "global_step": 405295, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0870397090911865, "global_step": 405296, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.026118755340576, "global_step": 405297, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0910284519195557, "global_step": 405298, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.105198621749878, "global_step": 405299, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.105988025665283, "global_step": 405300, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0504300594329834, "global_step": 405301, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0691006183624268, "global_step": 405302, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.113375425338745, "global_step": 405303, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0751240253448486, "global_step": 405304, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0960376262664795, "global_step": 405305, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0780961513519287, "global_step": 405306, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.076936721801758, "global_step": 405307, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.115614891052246, "global_step": 405308, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0898380279541016, "global_step": 405309, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0775673389434814, "global_step": 405310, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0503628253936768, "global_step": 405311, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0326383113861084, "global_step": 405312, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.2016561031341553, "global_step": 405313, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.012592315673828, "global_step": 405314, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.124894142150879, "global_step": 405315, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0535073280334473, "global_step": 405316, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9844379425048828, "global_step": 405317, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.082073211669922, "global_step": 405318, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1155598163604736, "global_step": 405319, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.154386520385742, "global_step": 405320, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.027831792831421, "global_step": 405321, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.085224151611328, "global_step": 405322, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.048335313796997, "global_step": 405323, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0414316654205322, "global_step": 405324, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0614583492279053, "global_step": 405325, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0669994354248047, "global_step": 405326, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.070614814758301, "global_step": 405327, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.045074224472046, "global_step": 405328, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.131415605545044, "global_step": 405329, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.052314043045044, "global_step": 405330, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.055974245071411, "global_step": 405331, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0818397998809814, "global_step": 405332, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.144697427749634, "global_step": 405333, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0964415073394775, "global_step": 405334, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1256799697875977, "global_step": 405335, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1135830879211426, "global_step": 405336, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.076751232147217, "global_step": 405337, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.01798677444458, "global_step": 405338, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0662765502929688, "global_step": 405339, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.040889024734497, "global_step": 405340, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0755903720855713, "global_step": 405341, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.071342945098877, "global_step": 405342, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9796087741851807, "global_step": 405343, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1151111125946045, "global_step": 405344, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.119250774383545, "global_step": 405345, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.065624475479126, "global_step": 405346, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.041672706604004, "global_step": 405347, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.051279067993164, "global_step": 405348, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.197817802429199, "global_step": 405349, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.2302749156951904, "global_step": 405350, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0642149448394775, "global_step": 405351, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0792248249053955, "global_step": 405352, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0939724445343018, "global_step": 405353, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.058577299118042, "global_step": 405354, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.114675521850586, "global_step": 405355, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.150195360183716, "global_step": 405356, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.111738681793213, "global_step": 405357, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1186716556549072, "global_step": 405358, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1704821586608887, "global_step": 405359, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0302534103393555, "global_step": 405360, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1520578861236572, "global_step": 405361, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.027188539505005, "global_step": 405362, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.037830114364624, "global_step": 405363, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.041348695755005, "global_step": 405364, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.141934394836426, "global_step": 405365, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1460278034210205, "global_step": 405366, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0714006423950195, "global_step": 405367, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.102597951889038, "global_step": 405368, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1104345321655273, "global_step": 405369, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1194705963134766, "global_step": 405370, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.116184949874878, "global_step": 405371, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0489399433135986, "global_step": 405372, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.045431613922119, "global_step": 405373, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1608006954193115, "global_step": 405374, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.082296133041382, "global_step": 405375, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.152048349380493, "global_step": 405376, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0915184020996094, "global_step": 405377, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0320730209350586, "global_step": 405378, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.048722743988037, "global_step": 405379, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.081836462020874, "global_step": 405380, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.077636957168579, "global_step": 405381, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.117121696472168, "global_step": 405382, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.068909168243408, "global_step": 405383, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.07519268989563, "global_step": 405384, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0778439044952393, "global_step": 405385, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.06189227104187, "global_step": 405386, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.118530035018921, "global_step": 405387, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9958019256591797, "global_step": 405388, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0817017555236816, "global_step": 405389, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.057371139526367, "global_step": 405390, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0867292881011963, "global_step": 405391, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.116408109664917, "global_step": 405392, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.087441921234131, "global_step": 405393, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0857038497924805, "global_step": 405394, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0869226455688477, "global_step": 405395, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0322322845458984, "global_step": 405396, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9800944328308105, "global_step": 405397, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.227466106414795, "global_step": 405398, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0553693771362305, "global_step": 405399, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.103900909423828, "global_step": 405400, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.135387659072876, "global_step": 405401, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0482068061828613, "global_step": 405402, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1190688610076904, "global_step": 405403, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.08774471282959, "global_step": 405404, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1244094371795654, "global_step": 405405, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1117894649505615, "global_step": 405406, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1644604206085205, "global_step": 405407, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0873513221740723, "global_step": 405408, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.079789400100708, "global_step": 405409, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0546882152557373, "global_step": 405410, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.120978355407715, "global_step": 405411, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.011784076690674, "global_step": 405412, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0487873554229736, "global_step": 405413, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.01824688911438, "global_step": 405414, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0929603576660156, "global_step": 405415, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1210484504699707, "global_step": 405416, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1161649227142334, "global_step": 405417, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1319527626037598, "global_step": 405418, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0224547386169434, "global_step": 405419, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1754281520843506, "global_step": 405420, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1018970012664795, "global_step": 405421, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1086249351501465, "global_step": 405422, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0279054641723633, "global_step": 405423, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0700314044952393, "global_step": 405424, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.032419204711914, "global_step": 405425, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.015486717224121, "global_step": 405426, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.2561447620391846, "global_step": 405427, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1227643489837646, "global_step": 405428, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0900356769561768, "global_step": 405429, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.145298719406128, "global_step": 405430, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9974552392959595, "global_step": 405431, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1423447132110596, "global_step": 405432, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1745145320892334, "global_step": 405433, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0417463779449463, "global_step": 405434, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0948569774627686, "global_step": 405435, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1362297534942627, "global_step": 405436, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1028835773468018, "global_step": 405437, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.140134811401367, "global_step": 405438, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1115031242370605, "global_step": 405439, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1714136600494385, "global_step": 405440, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1473734378814697, "global_step": 405441, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.157472610473633, "global_step": 405442, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9943972826004028, "global_step": 405443, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0864737033843994, "global_step": 405444, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.2317540645599365, "global_step": 405445, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0541443824768066, "global_step": 405446, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0291976928710938, "global_step": 405447, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.091853380203247, "global_step": 405448, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1060006618499756, "global_step": 405449, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.073331356048584, "global_step": 405450, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.140113353729248, "global_step": 405451, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0835022926330566, "global_step": 405452, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0788426399230957, "global_step": 405453, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1088340282440186, "global_step": 405454, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0700411796569824, "global_step": 405455, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.073814868927002, "global_step": 405456, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.075531482696533, "global_step": 405457, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1241531372070312, "global_step": 405458, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1266512870788574, "global_step": 405459, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.020250082015991, "global_step": 405460, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.2273263931274414, "global_step": 405461, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1492996215820312, "global_step": 405462, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0155396461486816, "global_step": 405463, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.042773962020874, "global_step": 405464, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1276206970214844, "global_step": 405465, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1023459434509277, "global_step": 405466, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.063338041305542, "global_step": 405467, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.006143808364868, "global_step": 405468, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.117391586303711, "global_step": 405469, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.170138120651245, "global_step": 405470, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.059319019317627, "global_step": 405471, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0918874740600586, "global_step": 405472, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1453824043273926, "global_step": 405473, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1787662506103516, "global_step": 405474, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0581750869750977, "global_step": 405475, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0394785404205322, "global_step": 405476, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.147287130355835, "global_step": 405477, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1399085521698, "global_step": 405478, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.045671224594116, "global_step": 405479, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0552635192871094, "global_step": 405480, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0969340801239014, "global_step": 405481, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0897490978240967, "global_step": 405482, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.056006908416748, "global_step": 405483, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.114563465118408, "global_step": 405484, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1386125087738037, "global_step": 405485, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1514337062835693, "global_step": 405486, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1544206142425537, "global_step": 405487, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0199825763702393, "global_step": 405488, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.065969944000244, "global_step": 405489, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.147104263305664, "global_step": 405490, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.167234420776367, "global_step": 405491, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.977603554725647, "global_step": 405492, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.032778024673462, "global_step": 405493, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.954458475112915, "global_step": 405494, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1251556873321533, "global_step": 405495, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.097893714904785, "global_step": 405496, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.046550989151001, "global_step": 405497, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.110828399658203, "global_step": 405498, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0632104873657227, "global_step": 405499, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0913796424865723, "global_step": 405500, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.08320951461792, "global_step": 405501, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0689730644226074, "global_step": 405502, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.032811164855957, "global_step": 405503, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1219751834869385, "global_step": 405504, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.033149480819702, "global_step": 405505, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.110339879989624, "global_step": 405506, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1412410736083984, "global_step": 405507, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.181328773498535, "global_step": 405508, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0547571182250977, "global_step": 405509, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9860392808914185, "global_step": 405510, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0765225887298584, "global_step": 405511, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0602214336395264, "global_step": 405512, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0894784927368164, "global_step": 405513, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.120069980621338, "global_step": 405514, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.032357692718506, "global_step": 405515, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.107623815536499, "global_step": 405516, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.164613962173462, "global_step": 405517, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.058173418045044, "global_step": 405518, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1352553367614746, "global_step": 405519, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0426549911499023, "global_step": 405520, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0783894062042236, "global_step": 405521, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0450241565704346, "global_step": 405522, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1936607360839844, "global_step": 405523, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1574349403381348, "global_step": 405524, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0140631198883057, "global_step": 405525, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1174278259277344, "global_step": 405526, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0596389770507812, "global_step": 405527, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1116654872894287, "global_step": 405528, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.063689947128296, "global_step": 405529, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1888222694396973, "global_step": 405530, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0578179359436035, "global_step": 405531, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.153844118118286, "global_step": 405532, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.099503517150879, "global_step": 405533, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1703989505767822, "global_step": 405534, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.082737445831299, "global_step": 405535, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1391661167144775, "global_step": 405536, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.110673666000366, "global_step": 405537, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.148451089859009, "global_step": 405538, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1658225059509277, "global_step": 405539, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1398367881774902, "global_step": 405540, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.138561964035034, "global_step": 405541, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.091200828552246, "global_step": 405542, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.143187999725342, "global_step": 405543, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1201913356781006, "global_step": 405544, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1473259925842285, "global_step": 405545, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.103464126586914, "global_step": 405546, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1147725582122803, "global_step": 405547, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9819453954696655, "global_step": 405548, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.133552312850952, "global_step": 405549, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0753798484802246, "global_step": 405550, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0473945140838623, "global_step": 405551, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.000725507736206, "global_step": 405552, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.060392379760742, "global_step": 405553, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.026503086090088, "global_step": 405554, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0835940837860107, "global_step": 405555, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.125386953353882, "global_step": 405556, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0580387115478516, "global_step": 405557, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.245929479598999, "global_step": 405558, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.086909294128418, "global_step": 405559, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0235981941223145, "global_step": 405560, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0829012393951416, "global_step": 405561, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.007750988006592, "global_step": 405562, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.008432626724243, "global_step": 405563, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.079662799835205, "global_step": 405564, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9916092157363892, "global_step": 405565, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.08156681060791, "global_step": 405566, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0993764400482178, "global_step": 405567, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1105000972747803, "global_step": 405568, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1156697273254395, "global_step": 405569, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.066166877746582, "global_step": 405570, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0550320148468018, "global_step": 405571, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.075981616973877, "global_step": 405572, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1185402870178223, "global_step": 405573, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0460731983184814, "global_step": 405574, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.074124574661255, "global_step": 405575, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.123347759246826, "global_step": 405576, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0451087951660156, "global_step": 405577, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.179776668548584, "global_step": 405578, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0983331203460693, "global_step": 405579, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.155444383621216, "global_step": 405580, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1209731101989746, "global_step": 405581, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0963428020477295, "global_step": 405582, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.087388515472412, "global_step": 405583, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0459420680999756, "global_step": 405584, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.047229290008545, "global_step": 405585, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.034653663635254, "global_step": 405586, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.098179578781128, "global_step": 405587, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0738461017608643, "global_step": 405588, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0725109577178955, "global_step": 405589, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.194324493408203, "global_step": 405590, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.068990468978882, "global_step": 405591, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.01995849609375, "global_step": 405592, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.137726068496704, "global_step": 405593, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0579190254211426, "global_step": 405594, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0650691986083984, "global_step": 405595, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0150392055511475, "global_step": 405596, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1754322052001953, "global_step": 405597, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1276838779449463, "global_step": 405598, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.166982412338257, "global_step": 405599, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.065882444381714, "global_step": 405600, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.082430124282837, "global_step": 405601, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0212514400482178, "global_step": 405602, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.996864676475525, "global_step": 405603, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.104254722595215, "global_step": 405604, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0170247554779053, "global_step": 405605, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.192326068878174, "global_step": 405606, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1202943325042725, "global_step": 405607, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.041569471359253, "global_step": 405608, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1173436641693115, "global_step": 405609, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.035942554473877, "global_step": 405610, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.127413034439087, "global_step": 405611, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.080592155456543, "global_step": 405612, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0370428562164307, "global_step": 405613, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0708611011505127, "global_step": 405614, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0466108322143555, "global_step": 405615, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0213894844055176, "global_step": 405616, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0902328491210938, "global_step": 405617, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0056257247924805, "global_step": 405618, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.087749481201172, "global_step": 405619, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0849578380584717, "global_step": 405620, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.114786148071289, "global_step": 405621, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0676255226135254, "global_step": 405622, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0999090671539307, "global_step": 405623, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.145153522491455, "global_step": 405624, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0458154678344727, "global_step": 405625, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.170870304107666, "global_step": 405626, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0867092609405518, "global_step": 405627, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1135172843933105, "global_step": 405628, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.077723741531372, "global_step": 405629, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0438904762268066, "global_step": 405630, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.048981189727783, "global_step": 405631, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1184167861938477, "global_step": 405632, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1342525482177734, "global_step": 405633, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1173908710479736, "global_step": 405634, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0588507652282715, "global_step": 405635, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1155807971954346, "global_step": 405636, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1015820503234863, "global_step": 405637, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0153188705444336, "global_step": 405638, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1839334964752197, "global_step": 405639, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0397613048553467, "global_step": 405640, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1580722332000732, "global_step": 405641, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1490893363952637, "global_step": 405642, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9574275016784668, "global_step": 405643, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0889787673950195, "global_step": 405644, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.154895067214966, "global_step": 405645, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1198654174804688, "global_step": 405646, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0724432468414307, "global_step": 405647, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.143787384033203, "global_step": 405648, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0717692375183105, "global_step": 405649, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0923867225646973, "global_step": 405650, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9764585494995117, "global_step": 405651, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0654311180114746, "global_step": 405652, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0658481121063232, "global_step": 405653, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0742108821868896, "global_step": 405654, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0401463508605957, "global_step": 405655, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.144083261489868, "global_step": 405656, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1779088973999023, "global_step": 405657, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1306967735290527, "global_step": 405658, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0721940994262695, "global_step": 405659, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.107495069503784, "global_step": 405660, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.120391845703125, "global_step": 405661, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.128641366958618, "global_step": 405662, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1229422092437744, "global_step": 405663, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.004585027694702, "global_step": 405664, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0836639404296875, "global_step": 405665, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0688400268554688, "global_step": 405666, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0896294116973877, "global_step": 405667, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0536153316497803, "global_step": 405668, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.113908529281616, "global_step": 405669, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0936853885650635, "global_step": 405670, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.2016828060150146, "global_step": 405671, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1374852657318115, "global_step": 405672, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1416022777557373, "global_step": 405673, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.08685564994812, "global_step": 405674, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.008014440536499, "global_step": 405675, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.102635383605957, "global_step": 405676, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.2022347450256348, "global_step": 405677, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1452906131744385, "global_step": 405678, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.045851707458496, "global_step": 405679, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.061290979385376, "global_step": 405680, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0520505905151367, "global_step": 405681, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.125278949737549, "global_step": 405682, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.087886333465576, "global_step": 405683, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.190521240234375, "global_step": 405684, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.109760284423828, "global_step": 405685, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0675926208496094, "global_step": 405686, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.104945421218872, "global_step": 405687, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1088342666625977, "global_step": 405688, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.097874879837036, "global_step": 405689, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0474741458892822, "global_step": 405690, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.130260705947876, "global_step": 405691, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0611166954040527, "global_step": 405692, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0737757682800293, "global_step": 405693, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0418965816497803, "global_step": 405694, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.151628255844116, "global_step": 405695, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.109844923019409, "global_step": 405696, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.098210096359253, "global_step": 405697, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1740448474884033, "global_step": 405698, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.034369468688965, "global_step": 405699, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0701191425323486, "global_step": 405700, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1563148498535156, "global_step": 405701, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0112783908843994, "global_step": 405702, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0826210975646973, "global_step": 405703, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1201539039611816, "global_step": 405704, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1395115852355957, "global_step": 405705, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1339104175567627, "global_step": 405706, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1142213344573975, "global_step": 405707, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9855583906173706, "global_step": 405708, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.094369888305664, "global_step": 405709, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1427972316741943, "global_step": 405710, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.201502799987793, "global_step": 405711, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1540093421936035, "global_step": 405712, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.131246566772461, "global_step": 405713, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0745747089385986, "global_step": 405714, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0711541175842285, "global_step": 405715, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.075208902359009, "global_step": 405716, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0736093521118164, "global_step": 405717, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0650882720947266, "global_step": 405718, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.063678503036499, "global_step": 405719, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1041719913482666, "global_step": 405720, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.098886489868164, "global_step": 405721, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0264947414398193, "global_step": 405722, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.180922746658325, "global_step": 405723, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1056766510009766, "global_step": 405724, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.012208938598633, "global_step": 405725, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0187618732452393, "global_step": 405726, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0599594116210938, "global_step": 405727, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.094247817993164, "global_step": 405728, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0814263820648193, "global_step": 405729, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0833652019500732, "global_step": 405730, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.093950033187866, "global_step": 405731, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9599742889404297, "global_step": 405732, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0566024780273438, "global_step": 405733, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1179661750793457, "global_step": 405734, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1275105476379395, "global_step": 405735, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.087778091430664, "global_step": 405736, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0683486461639404, "global_step": 405737, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.146186113357544, "global_step": 405738, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1457042694091797, "global_step": 405739, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.157771348953247, "global_step": 405740, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.2295920848846436, "global_step": 405741, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.04559588432312, "global_step": 405742, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0915324687957764, "global_step": 405743, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.158233880996704, "global_step": 405744, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.099135637283325, "global_step": 405745, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.220146417617798, "global_step": 405746, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.086425304412842, "global_step": 405747, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1062989234924316, "global_step": 405748, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1322946548461914, "global_step": 405749, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.011547088623047, "global_step": 405750, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1306557655334473, "global_step": 405751, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0564255714416504, "global_step": 405752, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.093226909637451, "global_step": 405753, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.01029372215271, "global_step": 405754, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0181868076324463, "global_step": 405755, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.993190050125122, "global_step": 405756, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0877459049224854, "global_step": 405757, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1421146392822266, "global_step": 405758, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.104245662689209, "global_step": 405759, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.08239483833313, "global_step": 405760, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9961904287338257, "global_step": 405761, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1248724460601807, "global_step": 405762, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1315109729766846, "global_step": 405763, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.111342430114746, "global_step": 405764, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.090491771697998, "global_step": 405765, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.181706666946411, "global_step": 405766, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1500742435455322, "global_step": 405767, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1198208332061768, "global_step": 405768, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.141023874282837, "global_step": 405769, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0133168697357178, "global_step": 405770, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.145761013031006, "global_step": 405771, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1186442375183105, "global_step": 405772, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.151879072189331, "global_step": 405773, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0603771209716797, "global_step": 405774, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0676937103271484, "global_step": 405775, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1678144931793213, "global_step": 405776, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.088623046875, "global_step": 405777, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0616848468780518, "global_step": 405778, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1095988750457764, "global_step": 405779, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.2157344818115234, "global_step": 405780, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.135455369949341, "global_step": 405781, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.166013479232788, "global_step": 405782, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.052180290222168, "global_step": 405783, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.167832612991333, "global_step": 405784, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1686923503875732, "global_step": 405785, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0714941024780273, "global_step": 405786, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.053644895553589, "global_step": 405787, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.108090400695801, "global_step": 405788, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1096181869506836, "global_step": 405789, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.109368324279785, "global_step": 405790, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.088998556137085, "global_step": 405791, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0641016960144043, "global_step": 405792, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0750632286071777, "global_step": 405793, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.097740411758423, "global_step": 405794, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.130326986312866, "global_step": 405795, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0574092864990234, "global_step": 405796, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.148513078689575, "global_step": 405797, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.085484504699707, "global_step": 405798, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1590025424957275, "global_step": 405799, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0960330963134766, "global_step": 405800, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0809879302978516, "global_step": 405801, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.061168909072876, "global_step": 405802, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1340858936309814, "global_step": 405803, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9755706787109375, "global_step": 405804, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.073883295059204, "global_step": 405805, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0326778888702393, "global_step": 405806, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0959768295288086, "global_step": 405807, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1221561431884766, "global_step": 405808, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9805784225463867, "global_step": 405809, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1374430656433105, "global_step": 405810, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.171633243560791, "global_step": 405811, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0256738662719727, "global_step": 405812, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0452816486358643, "global_step": 405813, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.093379020690918, "global_step": 405814, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1584460735321045, "global_step": 405815, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0781807899475098, "global_step": 405816, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1492998600006104, "global_step": 405817, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0627214908599854, "global_step": 405818, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1318953037261963, "global_step": 405819, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0329203605651855, "global_step": 405820, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1047897338867188, "global_step": 405821, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0637309551239014, "global_step": 405822, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1608359813690186, "global_step": 405823, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.148362398147583, "global_step": 405824, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0262489318847656, "global_step": 405825, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0938894748687744, "global_step": 405826, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0907750129699707, "global_step": 405827, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0370032787323, "global_step": 405828, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1532962322235107, "global_step": 405829, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.127581834793091, "global_step": 405830, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.160198926925659, "global_step": 405831, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0884201526641846, "global_step": 405832, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0977935791015625, "global_step": 405833, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0539753437042236, "global_step": 405834, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.09649658203125, "global_step": 405835, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0996079444885254, "global_step": 405836, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0688576698303223, "global_step": 405837, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0587072372436523, "global_step": 405838, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0976359844207764, "global_step": 405839, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0470714569091797, "global_step": 405840, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.107065200805664, "global_step": 405841, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.065460681915283, "global_step": 405842, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.094527006149292, "global_step": 405843, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.095337152481079, "global_step": 405844, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.134044885635376, "global_step": 405845, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1254332065582275, "global_step": 405846, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0159480571746826, "global_step": 405847, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.123054265975952, "global_step": 405848, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0730931758880615, "global_step": 405849, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0312626361846924, "global_step": 405850, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1382312774658203, "global_step": 405851, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1834022998809814, "global_step": 405852, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0612664222717285, "global_step": 405853, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0633420944213867, "global_step": 405854, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1518852710723877, "global_step": 405855, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.135662078857422, "global_step": 405856, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9947870969772339, "global_step": 405857, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1009268760681152, "global_step": 405858, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0692319869995117, "global_step": 405859, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.119840145111084, "global_step": 405860, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.120229482650757, "global_step": 405861, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.138798475265503, "global_step": 405862, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.162485122680664, "global_step": 405863, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.058551788330078, "global_step": 405864, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1485068798065186, "global_step": 405865, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1387381553649902, "global_step": 405866, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.163469076156616, "global_step": 405867, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.183175563812256, "global_step": 405868, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.063699245452881, "global_step": 405869, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.062751293182373, "global_step": 405870, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9878407716751099, "global_step": 405871, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1735610961914062, "global_step": 405872, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.149597644805908, "global_step": 405873, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.145838737487793, "global_step": 405874, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.088759422302246, "global_step": 405875, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1414999961853027, "global_step": 405876, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.104051113128662, "global_step": 405877, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0634307861328125, "global_step": 405878, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.119060516357422, "global_step": 405879, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.059436798095703, "global_step": 405880, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0793471336364746, "global_step": 405881, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.071298360824585, "global_step": 405882, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0681090354919434, "global_step": 405883, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.130347728729248, "global_step": 405884, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1142935752868652, "global_step": 405885, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0727951526641846, "global_step": 405886, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0471811294555664, "global_step": 405887, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0783612728118896, "global_step": 405888, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9765359163284302, "global_step": 405889, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1220600605010986, "global_step": 405890, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.104668140411377, "global_step": 405891, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1438980102539062, "global_step": 405892, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.166130304336548, "global_step": 405893, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.101491928100586, "global_step": 405894, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1697745323181152, "global_step": 405895, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0919814109802246, "global_step": 405896, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0621235370635986, "global_step": 405897, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.045285701751709, "global_step": 405898, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.018416404724121, "global_step": 405899, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0751078128814697, "global_step": 405900, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1324782371520996, "global_step": 405901, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0741629600524902, "global_step": 405902, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.154468059539795, "global_step": 405903, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.153749465942383, "global_step": 405904, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.080036163330078, "global_step": 405905, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0739026069641113, "global_step": 405906, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.06904935836792, "global_step": 405907, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0999958515167236, "global_step": 405908, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0487043857574463, "global_step": 405909, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0082850456237793, "global_step": 405910, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1233303546905518, "global_step": 405911, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0316109657287598, "global_step": 405912, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9953997135162354, "global_step": 405913, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.067509174346924, "global_step": 405914, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0613203048706055, "global_step": 405915, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.072626829147339, "global_step": 405916, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0813820362091064, "global_step": 405917, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0951428413391113, "global_step": 405918, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1240546703338623, "global_step": 405919, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0761184692382812, "global_step": 405920, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1770782470703125, "global_step": 405921, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.12766695022583, "global_step": 405922, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.156853199005127, "global_step": 405923, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.021111488342285, "global_step": 405924, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1005258560180664, "global_step": 405925, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0100045204162598, "global_step": 405926, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0916926860809326, "global_step": 405927, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0814926624298096, "global_step": 405928, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0533576011657715, "global_step": 405929, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.142131805419922, "global_step": 405930, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1119091510772705, "global_step": 405931, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.098994016647339, "global_step": 405932, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0200278759002686, "global_step": 405933, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0863382816314697, "global_step": 405934, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0422911643981934, "global_step": 405935, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.102782964706421, "global_step": 405936, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.087935209274292, "global_step": 405937, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1932218074798584, "global_step": 405938, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.077820301055908, "global_step": 405939, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.085350751876831, "global_step": 405940, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.067326068878174, "global_step": 405941, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0931012630462646, "global_step": 405942, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.150946855545044, "global_step": 405943, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1259989738464355, "global_step": 405944, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0536270141601562, "global_step": 405945, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.107707977294922, "global_step": 405946, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.103886604309082, "global_step": 405947, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.104788064956665, "global_step": 405948, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.103635311126709, "global_step": 405949, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1522674560546875, "global_step": 405950, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0892751216888428, "global_step": 405951, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1091420650482178, "global_step": 405952, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.037429094314575, "global_step": 405953, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0915205478668213, "global_step": 405954, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.020352363586426, "global_step": 405955, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0457024574279785, "global_step": 405956, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0560879707336426, "global_step": 405957, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.085193634033203, "global_step": 405958, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.12424898147583, "global_step": 405959, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.077387809753418, "global_step": 405960, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1069865226745605, "global_step": 405961, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.148937940597534, "global_step": 405962, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.079935073852539, "global_step": 405963, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.124783992767334, "global_step": 405964, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.157036066055298, "global_step": 405965, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.133002758026123, "global_step": 405966, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1088428497314453, "global_step": 405967, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1157937049865723, "global_step": 405968, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.086766481399536, "global_step": 405969, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1164543628692627, "global_step": 405970, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0561139583587646, "global_step": 405971, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1994082927703857, "global_step": 405972, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.121347427368164, "global_step": 405973, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1300394535064697, "global_step": 405974, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.122526168823242, "global_step": 405975, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.093029737472534, "global_step": 405976, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0827829837799072, "global_step": 405977, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0952670574188232, "global_step": 405978, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.157954454421997, "global_step": 405979, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0741219520568848, "global_step": 405980, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.181098461151123, "global_step": 405981, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1817805767059326, "global_step": 405982, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.057513475418091, "global_step": 405983, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0662996768951416, "global_step": 405984, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0734736919403076, "global_step": 405985, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.116335153579712, "global_step": 405986, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0552265644073486, "global_step": 405987, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1532132625579834, "global_step": 405988, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0725650787353516, "global_step": 405989, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.086604356765747, "global_step": 405990, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.035433053970337, "global_step": 405991, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.06343674659729, "global_step": 405992, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1031527519226074, "global_step": 405993, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.047978401184082, "global_step": 405994, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.048788547515869, "global_step": 405995, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0469970703125, "global_step": 405996, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.123002767562866, "global_step": 405997, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0736188888549805, "global_step": 405998, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0744194984436035, "global_step": 405999, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.076390266418457, "global_step": 406000, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.039299964904785, "global_step": 406001, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1353394985198975, "global_step": 406002, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0676755905151367, "global_step": 406003, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1183598041534424, "global_step": 406004, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.047478675842285, "global_step": 406005, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.078944206237793, "global_step": 406006, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1394641399383545, "global_step": 406007, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0883548259735107, "global_step": 406008, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1600630283355713, "global_step": 406009, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0702390670776367, "global_step": 406010, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0502572059631348, "global_step": 406011, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0938310623168945, "global_step": 406012, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0909719467163086, "global_step": 406013, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9872546195983887, "global_step": 406014, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.087404727935791, "global_step": 406015, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.044654130935669, "global_step": 406016, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1188299655914307, "global_step": 406017, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.057830333709717, "global_step": 406018, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0982184410095215, "global_step": 406019, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.124011754989624, "global_step": 406020, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1742348670959473, "global_step": 406021, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1022350788116455, "global_step": 406022, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.029395818710327, "global_step": 406023, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0582566261291504, "global_step": 406024, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.109942674636841, "global_step": 406025, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0422611236572266, "global_step": 406026, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.039682149887085, "global_step": 406027, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1105165481567383, "global_step": 406028, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.092561721801758, "global_step": 406029, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.046600818634033, "global_step": 406030, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1003220081329346, "global_step": 406031, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0744287967681885, "global_step": 406032, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1137053966522217, "global_step": 406033, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0095019340515137, "global_step": 406034, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.150390625, "global_step": 406035, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0837950706481934, "global_step": 406036, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1726908683776855, "global_step": 406037, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.030296802520752, "global_step": 406038, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.072601318359375, "global_step": 406039, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.059896945953369, "global_step": 406040, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.067657947540283, "global_step": 406041, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0425467491149902, "global_step": 406042, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.06404972076416, "global_step": 406043, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.109307050704956, "global_step": 406044, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1453375816345215, "global_step": 406045, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0795469284057617, "global_step": 406046, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.148348331451416, "global_step": 406047, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1711533069610596, "global_step": 406048, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.098064422607422, "global_step": 406049, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1139047145843506, "global_step": 406050, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.097029685974121, "global_step": 406051, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1654739379882812, "global_step": 406052, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0604493618011475, "global_step": 406053, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.100642442703247, "global_step": 406054, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.081380844116211, "global_step": 406055, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.096369504928589, "global_step": 406056, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0970234870910645, "global_step": 406057, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0601840019226074, "global_step": 406058, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0319409370422363, "global_step": 406059, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.102576971054077, "global_step": 406060, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1004936695098877, "global_step": 406061, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0591542720794678, "global_step": 406062, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1296894550323486, "global_step": 406063, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1390881538391113, "global_step": 406064, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0698652267456055, "global_step": 406065, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.15695858001709, "global_step": 406066, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1170766353607178, "global_step": 406067, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1067683696746826, "global_step": 406068, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0718491077423096, "global_step": 406069, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1471855640411377, "global_step": 406070, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1155893802642822, "global_step": 406071, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1425158977508545, "global_step": 406072, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.104231834411621, "global_step": 406073, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.106783628463745, "global_step": 406074, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.087690591812134, "global_step": 406075, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.086038589477539, "global_step": 406076, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1464381217956543, "global_step": 406077, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.126795530319214, "global_step": 406078, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1081032752990723, "global_step": 406079, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.048736333847046, "global_step": 406080, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0998034477233887, "global_step": 406081, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1722917556762695, "global_step": 406082, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.074601411819458, "global_step": 406083, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0431573390960693, "global_step": 406084, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0953447818756104, "global_step": 406085, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.042473077774048, "global_step": 406086, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.046534538269043, "global_step": 406087, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.096644163131714, "global_step": 406088, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.158770799636841, "global_step": 406089, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.123749017715454, "global_step": 406090, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1840929985046387, "global_step": 406091, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1039984226226807, "global_step": 406092, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1117424964904785, "global_step": 406093, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1056442260742188, "global_step": 406094, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.177978038787842, "global_step": 406095, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0815346240997314, "global_step": 406096, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.023024320602417, "global_step": 406097, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.06496000289917, "global_step": 406098, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.112046957015991, "global_step": 406099, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.100155830383301, "global_step": 406100, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.129131317138672, "global_step": 406101, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1602351665496826, "global_step": 406102, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1595420837402344, "global_step": 406103, "epoch": 768, "lr": 5e-05}
{"train_loss": 1.9611601829528809, "global_step": 406104, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0385513305664062, "global_step": 406105, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1251187324523926, "global_step": 406106, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1656930446624756, "global_step": 406107, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.064547061920166, "global_step": 406108, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.118333578109741, "global_step": 406109, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.065535306930542, "global_step": 406110, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0536553859710693, "global_step": 406111, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0109851360321045, "global_step": 406112, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1751110553741455, "global_step": 406113, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1579463481903076, "global_step": 406114, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0040171146392822, "global_step": 406115, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.014378547668457, "global_step": 406116, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.131913423538208, "global_step": 406117, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0977323055267334, "global_step": 406118, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1482763290405273, "global_step": 406119, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.117722272872925, "global_step": 406120, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1263203620910645, "global_step": 406121, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0907654762268066, "global_step": 406122, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0463688373565674, "global_step": 406123, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0895233154296875, "global_step": 406124, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1337761878967285, "global_step": 406125, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.191174268722534, "global_step": 406126, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.081676721572876, "global_step": 406127, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1621100902557373, "global_step": 406128, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.18742299079895, "global_step": 406129, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0981099605560303, "global_step": 406130, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0945446491241455, "global_step": 406131, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1019387245178223, "global_step": 406132, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.2112107276916504, "global_step": 406133, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.103955030441284, "global_step": 406134, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1046879291534424, "global_step": 406135, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.0876553058624268, "global_step": 406136, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.153202533721924, "global_step": 406137, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.2223949432373047, "global_step": 406138, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.104666233062744, "global_step": 406139, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1778106689453125, "global_step": 406140, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.087374448776245, "global_step": 406141, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.10857892036438, "global_step": 406142, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.092789888381958, "global_step": 406143, "epoch": 768, "lr": 5e-05}
{"train_loss": 2.1585123538970947, "global_step": 406144, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0943145751953125, "global_step": 406145, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0659291744232178, "global_step": 406146, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1241703033447266, "global_step": 406147, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.069319486618042, "global_step": 406148, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0796303749084473, "global_step": 406149, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.9853688478469849, "global_step": 406150, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0718014240264893, "global_step": 406151, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.068603992462158, "global_step": 406152, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.055957317352295, "global_step": 406153, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0404367446899414, "global_step": 406154, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1510632038116455, "global_step": 406155, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1578822135925293, "global_step": 406156, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.094548463821411, "global_step": 406157, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.066281795501709, "global_step": 406158, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.9997339248657227, "global_step": 406159, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.06168794631958, "global_step": 406160, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.073533535003662, "global_step": 406161, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0406687259674072, "global_step": 406162, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0014586448669434, "global_step": 406163, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1076552867889404, "global_step": 406164, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.079819440841675, "global_step": 406165, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.05355167388916, "global_step": 406166, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.163097620010376, "global_step": 406167, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0987820625305176, "global_step": 406168, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.111487865447998, "global_step": 406169, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0425643920898438, "global_step": 406170, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0258524417877197, "global_step": 406171, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1583096981048584, "global_step": 406172, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0580244064331055, "global_step": 406173, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0754222869873047, "global_step": 406174, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0761845111846924, "global_step": 406175, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.040764331817627, "global_step": 406176, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.164954662322998, "global_step": 406177, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.079332113265991, "global_step": 406178, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.10072922706604, "global_step": 406179, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.072366714477539, "global_step": 406180, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0695786476135254, "global_step": 406181, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0807688236236572, "global_step": 406182, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.13267183303833, "global_step": 406183, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.147064685821533, "global_step": 406184, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1054747104644775, "global_step": 406185, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0712316036224365, "global_step": 406186, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0532844066619873, "global_step": 406187, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0222012996673584, "global_step": 406188, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.117414951324463, "global_step": 406189, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.110623836517334, "global_step": 406190, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0860512256622314, "global_step": 406191, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0900564193725586, "global_step": 406192, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0092294216156006, "global_step": 406193, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0707991123199463, "global_step": 406194, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.073613405227661, "global_step": 406195, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0495996475219727, "global_step": 406196, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1473004817962646, "global_step": 406197, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0464375019073486, "global_step": 406198, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.062499761581421, "global_step": 406199, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.064016342163086, "global_step": 406200, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1219704151153564, "global_step": 406201, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0208024978637695, "global_step": 406202, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.005239963531494, "global_step": 406203, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.174886465072632, "global_step": 406204, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0590810775756836, "global_step": 406205, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.164543867111206, "global_step": 406206, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.157033681869507, "global_step": 406207, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1862006187438965, "global_step": 406208, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1250791549682617, "global_step": 406209, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.03842830657959, "global_step": 406210, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.09304141998291, "global_step": 406211, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.9984750747680664, "global_step": 406212, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.029590368270874, "global_step": 406213, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.040323495864868, "global_step": 406214, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0653700828552246, "global_step": 406215, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.074270725250244, "global_step": 406216, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0457072257995605, "global_step": 406217, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.129446268081665, "global_step": 406218, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.053905963897705, "global_step": 406219, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.113563060760498, "global_step": 406220, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0750036239624023, "global_step": 406221, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.070570230484009, "global_step": 406222, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1209471225738525, "global_step": 406223, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.9708592891693115, "global_step": 406224, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0236105918884277, "global_step": 406225, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.093719959259033, "global_step": 406226, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1083009243011475, "global_step": 406227, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0832812786102295, "global_step": 406228, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1301989555358887, "global_step": 406229, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0990378856658936, "global_step": 406230, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0385074615478516, "global_step": 406231, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.049515724182129, "global_step": 406232, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.045346736907959, "global_step": 406233, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.033858299255371, "global_step": 406234, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0367534160614014, "global_step": 406235, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0404131412506104, "global_step": 406236, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1278140544891357, "global_step": 406237, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1022562980651855, "global_step": 406238, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.981247067451477, "global_step": 406239, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.102081537246704, "global_step": 406240, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.064366579055786, "global_step": 406241, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.104492664337158, "global_step": 406242, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1479711532592773, "global_step": 406243, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.127791404724121, "global_step": 406244, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.098762035369873, "global_step": 406245, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0925920009613037, "global_step": 406246, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0596923828125, "global_step": 406247, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.11771297454834, "global_step": 406248, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.123676061630249, "global_step": 406249, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1228184700012207, "global_step": 406250, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.11515474319458, "global_step": 406251, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0035226345062256, "global_step": 406252, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0873019695281982, "global_step": 406253, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1050620079040527, "global_step": 406254, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1591522693634033, "global_step": 406255, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.117805242538452, "global_step": 406256, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1315267086029053, "global_step": 406257, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.999529242515564, "global_step": 406258, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.987457036972046, "global_step": 406259, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.05940842628479, "global_step": 406260, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0733492374420166, "global_step": 406261, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1736490726470947, "global_step": 406262, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1204020977020264, "global_step": 406263, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0715384483337402, "global_step": 406264, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1263086795806885, "global_step": 406265, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.041248321533203, "global_step": 406266, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0705533027648926, "global_step": 406267, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.090573310852051, "global_step": 406268, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0394325256347656, "global_step": 406269, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.088376998901367, "global_step": 406270, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.07736873626709, "global_step": 406271, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0254995822906494, "global_step": 406272, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0915303230285645, "global_step": 406273, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.070143938064575, "global_step": 406274, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0945000648498535, "global_step": 406275, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.041774272918701, "global_step": 406276, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0648515224456787, "global_step": 406277, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.078273296356201, "global_step": 406278, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.127161979675293, "global_step": 406279, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0473389625549316, "global_step": 406280, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.011232614517212, "global_step": 406281, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.144758462905884, "global_step": 406282, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1934337615966797, "global_step": 406283, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1062986850738525, "global_step": 406284, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1198570728302, "global_step": 406285, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1552529335021973, "global_step": 406286, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1503875255584717, "global_step": 406287, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.155764579772949, "global_step": 406288, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0701985359191895, "global_step": 406289, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.056581974029541, "global_step": 406290, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1136484146118164, "global_step": 406291, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.144685745239258, "global_step": 406292, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1580214500427246, "global_step": 406293, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1210999488830566, "global_step": 406294, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.089000940322876, "global_step": 406295, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1292619705200195, "global_step": 406296, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.099317789077759, "global_step": 406297, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.2411048412323, "global_step": 406298, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.061950445175171, "global_step": 406299, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.106276750564575, "global_step": 406300, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0989489555358887, "global_step": 406301, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1386218070983887, "global_step": 406302, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1038267612457275, "global_step": 406303, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.087339401245117, "global_step": 406304, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.09281849861145, "global_step": 406305, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0342676639556885, "global_step": 406306, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.046076774597168, "global_step": 406307, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.151221990585327, "global_step": 406308, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1207449436187744, "global_step": 406309, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.064563512802124, "global_step": 406310, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.098414659500122, "global_step": 406311, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.155334234237671, "global_step": 406312, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.158168077468872, "global_step": 406313, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.068390130996704, "global_step": 406314, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1642885208129883, "global_step": 406315, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1289470195770264, "global_step": 406316, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.143920660018921, "global_step": 406317, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0648608207702637, "global_step": 406318, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0013229846954346, "global_step": 406319, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0206730365753174, "global_step": 406320, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.110551118850708, "global_step": 406321, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.049633026123047, "global_step": 406322, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.113067388534546, "global_step": 406323, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0537586212158203, "global_step": 406324, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0970842838287354, "global_step": 406325, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.112191677093506, "global_step": 406326, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.018238067626953, "global_step": 406327, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0430397987365723, "global_step": 406328, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0170109272003174, "global_step": 406329, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1246914863586426, "global_step": 406330, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.053509473800659, "global_step": 406331, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.11081600189209, "global_step": 406332, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1478419303894043, "global_step": 406333, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0993967056274414, "global_step": 406334, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.025435447692871, "global_step": 406335, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.066819667816162, "global_step": 406336, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0226969718933105, "global_step": 406337, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.112826347351074, "global_step": 406338, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0715715885162354, "global_step": 406339, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1260933876037598, "global_step": 406340, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.172943353652954, "global_step": 406341, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0779268741607666, "global_step": 406342, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1817808151245117, "global_step": 406343, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.9975121021270752, "global_step": 406344, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0786354541778564, "global_step": 406345, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1112236976623535, "global_step": 406346, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.074366331100464, "global_step": 406347, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0460941791534424, "global_step": 406348, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1553657054901123, "global_step": 406349, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1045315265655518, "global_step": 406350, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0589182376861572, "global_step": 406351, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.082329750061035, "global_step": 406352, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.123650312423706, "global_step": 406353, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1391448974609375, "global_step": 406354, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.131875991821289, "global_step": 406355, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.062861442565918, "global_step": 406356, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.059953212738037, "global_step": 406357, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0875368118286133, "global_step": 406358, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.091888904571533, "global_step": 406359, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.013903856277466, "global_step": 406360, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0158207416534424, "global_step": 406361, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.033330202102661, "global_step": 406362, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0784637928009033, "global_step": 406363, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.135070323944092, "global_step": 406364, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.084486722946167, "global_step": 406365, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0712084770202637, "global_step": 406366, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0179643630981445, "global_step": 406367, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0596044063568115, "global_step": 406368, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.133535146713257, "global_step": 406369, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1796340942382812, "global_step": 406370, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1052117347717285, "global_step": 406371, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0445375442504883, "global_step": 406372, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.057600975036621, "global_step": 406373, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1067442893981934, "global_step": 406374, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1043128967285156, "global_step": 406375, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0876076221466064, "global_step": 406376, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1358959674835205, "global_step": 406377, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.052117109298706, "global_step": 406378, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1573212146759033, "global_step": 406379, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.140436887741089, "global_step": 406380, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0441739559173584, "global_step": 406381, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0408265590667725, "global_step": 406382, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.019190549850464, "global_step": 406383, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.118112325668335, "global_step": 406384, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0861005783081055, "global_step": 406385, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0618069171905518, "global_step": 406386, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0063748359680176, "global_step": 406387, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1104466915130615, "global_step": 406388, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0839169025421143, "global_step": 406389, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.107450008392334, "global_step": 406390, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.040229320526123, "global_step": 406391, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.035188913345337, "global_step": 406392, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.162323236465454, "global_step": 406393, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.045851707458496, "global_step": 406394, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1117944717407227, "global_step": 406395, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.189270496368408, "global_step": 406396, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.2013468742370605, "global_step": 406397, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.010301351547241, "global_step": 406398, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.043330192565918, "global_step": 406399, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.036971092224121, "global_step": 406400, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1144680976867676, "global_step": 406401, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1114492416381836, "global_step": 406402, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1048903465270996, "global_step": 406403, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.090406656265259, "global_step": 406404, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0621378421783447, "global_step": 406405, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.12438702583313, "global_step": 406406, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.9228945970535278, "global_step": 406407, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1025896072387695, "global_step": 406408, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.959739327430725, "global_step": 406409, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0701639652252197, "global_step": 406410, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.102839469909668, "global_step": 406411, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1098570823669434, "global_step": 406412, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0211446285247803, "global_step": 406413, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.147892475128174, "global_step": 406414, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0741281509399414, "global_step": 406415, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0435585975646973, "global_step": 406416, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0738487243652344, "global_step": 406417, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.095447540283203, "global_step": 406418, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.082693099975586, "global_step": 406419, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1679024696350098, "global_step": 406420, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0475118160247803, "global_step": 406421, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1557440757751465, "global_step": 406422, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0191285610198975, "global_step": 406423, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.093015670776367, "global_step": 406424, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.08660626411438, "global_step": 406425, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0546884536743164, "global_step": 406426, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.184037208557129, "global_step": 406427, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.019181728363037, "global_step": 406428, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.077707529067993, "global_step": 406429, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0226852893829346, "global_step": 406430, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1285805702209473, "global_step": 406431, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.161118984222412, "global_step": 406432, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0211501121520996, "global_step": 406433, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.124852180480957, "global_step": 406434, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.141833782196045, "global_step": 406435, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.075502634048462, "global_step": 406436, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.094733476638794, "global_step": 406437, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1275906562805176, "global_step": 406438, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.086082696914673, "global_step": 406439, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1296637058258057, "global_step": 406440, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0797433853149414, "global_step": 406441, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1128792762756348, "global_step": 406442, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1224710941314697, "global_step": 406443, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.05536150932312, "global_step": 406444, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0539603233337402, "global_step": 406445, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.143062114715576, "global_step": 406446, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1217894554138184, "global_step": 406447, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0886330604553223, "global_step": 406448, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1101510524749756, "global_step": 406449, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1439731121063232, "global_step": 406450, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.9966903924942017, "global_step": 406451, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0457675457000732, "global_step": 406452, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0437707901000977, "global_step": 406453, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1964917182922363, "global_step": 406454, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.088226079940796, "global_step": 406455, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1268534660339355, "global_step": 406456, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1687633991241455, "global_step": 406457, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.041403293609619, "global_step": 406458, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.133908271789551, "global_step": 406459, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1139395236968994, "global_step": 406460, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.103571891784668, "global_step": 406461, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1513876914978027, "global_step": 406462, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.07463002204895, "global_step": 406463, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.062033176422119, "global_step": 406464, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.140517473220825, "global_step": 406465, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.089775800704956, "global_step": 406466, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0520517826080322, "global_step": 406467, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0791966915130615, "global_step": 406468, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1384904384613037, "global_step": 406469, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0663561820983887, "global_step": 406470, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.011561870574951, "global_step": 406471, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0768661499023438, "global_step": 406472, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.123985767364502, "global_step": 406473, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.058213949203491, "global_step": 406474, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.9822310209274292, "global_step": 406475, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.114130973815918, "global_step": 406476, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0757997035980225, "global_step": 406477, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1200873851776123, "global_step": 406478, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.13578200340271, "global_step": 406479, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0882625579833984, "global_step": 406480, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0654282569885254, "global_step": 406481, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.122983932495117, "global_step": 406482, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.166055202484131, "global_step": 406483, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0982539653778076, "global_step": 406484, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.021731376647949, "global_step": 406485, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.146700620651245, "global_step": 406486, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0115036964416504, "global_step": 406487, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0551321506500244, "global_step": 406488, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0686309337615967, "global_step": 406489, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0285892486572266, "global_step": 406490, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.2082412242889404, "global_step": 406491, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1358492374420166, "global_step": 406492, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.057957649230957, "global_step": 406493, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0336196422576904, "global_step": 406494, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1361618041992188, "global_step": 406495, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0592200756073, "global_step": 406496, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.088744640350342, "global_step": 406497, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.181594133377075, "global_step": 406498, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1422464847564697, "global_step": 406499, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.045685291290283, "global_step": 406500, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.064222812652588, "global_step": 406501, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0650877952575684, "global_step": 406502, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.079540729522705, "global_step": 406503, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1018166542053223, "global_step": 406504, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0668420791625977, "global_step": 406505, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1722779273986816, "global_step": 406506, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.037883758544922, "global_step": 406507, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1571359634399414, "global_step": 406508, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.117176055908203, "global_step": 406509, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.166701078414917, "global_step": 406510, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0528266429901123, "global_step": 406511, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.021389961242676, "global_step": 406512, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0975472927093506, "global_step": 406513, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1381256580352783, "global_step": 406514, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.113252878189087, "global_step": 406515, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1055636405944824, "global_step": 406516, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.131101608276367, "global_step": 406517, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0698046684265137, "global_step": 406518, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.162224292755127, "global_step": 406519, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1051924228668213, "global_step": 406520, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.109448194503784, "global_step": 406521, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1197140216827393, "global_step": 406522, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0292892456054688, "global_step": 406523, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1305134296417236, "global_step": 406524, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.9837398529052734, "global_step": 406525, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1823761463165283, "global_step": 406526, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.035633087158203, "global_step": 406527, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1066830158233643, "global_step": 406528, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0556206703186035, "global_step": 406529, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.003272533416748, "global_step": 406530, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1114819049835205, "global_step": 406531, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0552456378936768, "global_step": 406532, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1037793159484863, "global_step": 406533, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.074431896209717, "global_step": 406534, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1075074672698975, "global_step": 406535, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.122220993041992, "global_step": 406536, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0930848121643066, "global_step": 406537, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.026695728302002, "global_step": 406538, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.113283395767212, "global_step": 406539, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0325663089752197, "global_step": 406540, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0932819843292236, "global_step": 406541, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0678768157958984, "global_step": 406542, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.076587677001953, "global_step": 406543, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1483263969421387, "global_step": 406544, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.069552421569824, "global_step": 406545, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.019087314605713, "global_step": 406546, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.072479248046875, "global_step": 406547, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.158541440963745, "global_step": 406548, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0851857662200928, "global_step": 406549, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0643656253814697, "global_step": 406550, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.010450601577759, "global_step": 406551, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0710396766662598, "global_step": 406552, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0897157192230225, "global_step": 406553, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.131443738937378, "global_step": 406554, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.180764675140381, "global_step": 406555, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1563942432403564, "global_step": 406556, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0986404418945312, "global_step": 406557, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1284897327423096, "global_step": 406558, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0987539291381836, "global_step": 406559, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.015380382537842, "global_step": 406560, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1586389541625977, "global_step": 406561, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.089961051940918, "global_step": 406562, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.08744215965271, "global_step": 406563, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0229785442352295, "global_step": 406564, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1075048446655273, "global_step": 406565, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.032470703125, "global_step": 406566, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1222007274627686, "global_step": 406567, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0393874645233154, "global_step": 406568, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.058580160140991, "global_step": 406569, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1759212017059326, "global_step": 406570, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.071918487548828, "global_step": 406571, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.000765323638916, "global_step": 406572, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.176342487335205, "global_step": 406573, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1354193687438965, "global_step": 406574, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.054095983505249, "global_step": 406575, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1947622299194336, "global_step": 406576, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.103174924850464, "global_step": 406577, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.090322971343994, "global_step": 406578, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0116677284240723, "global_step": 406579, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.066793441772461, "global_step": 406580, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1730146408081055, "global_step": 406581, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.02423095703125, "global_step": 406582, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.074374198913574, "global_step": 406583, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.066054105758667, "global_step": 406584, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0121946334838867, "global_step": 406585, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.113124132156372, "global_step": 406586, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1253502368927, "global_step": 406587, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1365911960601807, "global_step": 406588, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0996992588043213, "global_step": 406589, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0766189098358154, "global_step": 406590, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0650887489318848, "global_step": 406591, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1385767459869385, "global_step": 406592, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0248124599456787, "global_step": 406593, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1883487701416016, "global_step": 406594, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.117384672164917, "global_step": 406595, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1391055583953857, "global_step": 406596, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1936042308807373, "global_step": 406597, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0164077281951904, "global_step": 406598, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.115989923477173, "global_step": 406599, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.13297963142395, "global_step": 406600, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.110424518585205, "global_step": 406601, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1124110221862793, "global_step": 406602, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1361775398254395, "global_step": 406603, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.091334581375122, "global_step": 406604, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.993647813796997, "global_step": 406605, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1184322834014893, "global_step": 406606, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0792365074157715, "global_step": 406607, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0357613563537598, "global_step": 406608, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.134779214859009, "global_step": 406609, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.043205738067627, "global_step": 406610, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.074934244155884, "global_step": 406611, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.066706418991089, "global_step": 406612, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.04699969291687, "global_step": 406613, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1047098636627197, "global_step": 406614, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1136600971221924, "global_step": 406615, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0220253467559814, "global_step": 406616, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0056393146514893, "global_step": 406617, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.033987283706665, "global_step": 406618, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.9755494594573975, "global_step": 406619, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0997185707092285, "global_step": 406620, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.051896095275879, "global_step": 406621, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0563387870788574, "global_step": 406622, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.026615858078003, "global_step": 406623, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1392908096313477, "global_step": 406624, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.2929162979125977, "global_step": 406625, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0529072284698486, "global_step": 406626, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.042867422103882, "global_step": 406627, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1160454750061035, "global_step": 406628, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1214330196380615, "global_step": 406629, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1472432613372803, "global_step": 406630, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1252832412719727, "global_step": 406631, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.106665849685669, "global_step": 406632, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.120227336883545, "global_step": 406633, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0555524826049805, "global_step": 406634, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1115918159484863, "global_step": 406635, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.110607385635376, "global_step": 406636, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.9937729835510254, "global_step": 406637, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1473934650421143, "global_step": 406638, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0235273838043213, "global_step": 406639, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0557754039764404, "global_step": 406640, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.143979549407959, "global_step": 406641, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0799174308776855, "global_step": 406642, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0491538047790527, "global_step": 406643, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.158068895339966, "global_step": 406644, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0790274143218994, "global_step": 406645, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0480661392211914, "global_step": 406646, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.9876190423965454, "global_step": 406647, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1263346672058105, "global_step": 406648, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.008768320083618, "global_step": 406649, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.2108500003814697, "global_step": 406650, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.088566780090332, "global_step": 406651, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0698468685150146, "global_step": 406652, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.066519021987915, "global_step": 406653, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.124589443206787, "global_step": 406654, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.057948350906372, "global_step": 406655, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.097750663757324, "global_step": 406656, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1288113594055176, "global_step": 406657, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0750246047973633, "global_step": 406658, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1293225288391113, "global_step": 406659, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0037734508514404, "global_step": 406660, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.087179660797119, "global_step": 406661, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.136897563934326, "global_step": 406662, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.167297840118408, "global_step": 406663, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.086132049560547, "global_step": 406664, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.146923065185547, "global_step": 406665, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1355416774749756, "global_step": 406666, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1378254890441895, "global_step": 406667, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1316885948181152, "global_step": 406668, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.11104154586792, "global_step": 406669, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1229894161224365, "global_step": 406670, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.136882781982422, "global_step": 406671, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.096623182296753, "global_step": 406672, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.143167018890381, "global_step": 406673, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1307456493377686, "global_step": 406674, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.142577648162842, "global_step": 406675, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.075599193572998, "global_step": 406676, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0998411178588867, "global_step": 406677, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.053619146347046, "global_step": 406678, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0344150066375732, "global_step": 406679, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.158114194869995, "global_step": 406680, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0779824256896973, "global_step": 406681, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1517717838287354, "global_step": 406682, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1527493000030518, "global_step": 406683, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.9658713340759277, "global_step": 406684, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1235530376434326, "global_step": 406685, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.050584077835083, "global_step": 406686, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0987958908081055, "global_step": 406687, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0622148513793945, "global_step": 406688, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.093770980834961, "global_step": 406689, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0230865478515625, "global_step": 406690, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1301052570343018, "global_step": 406691, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0962307453155518, "global_step": 406692, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.079575777053833, "global_step": 406693, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0498173236846924, "global_step": 406694, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0970945358276367, "global_step": 406695, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1324660778045654, "global_step": 406696, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0398318767547607, "global_step": 406697, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.168715476989746, "global_step": 406698, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0839684009552, "global_step": 406699, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.119847297668457, "global_step": 406700, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.127570867538452, "global_step": 406701, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1388816833496094, "global_step": 406702, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.207324504852295, "global_step": 406703, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0788145065307617, "global_step": 406704, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.202579975128174, "global_step": 406705, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0935842990875244, "global_step": 406706, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1697471141815186, "global_step": 406707, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.092839002609253, "global_step": 406708, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0108418464660645, "global_step": 406709, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.068556308746338, "global_step": 406710, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0747363567352295, "global_step": 406711, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1233768463134766, "global_step": 406712, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0939273834228516, "global_step": 406713, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.158270835876465, "global_step": 406714, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.135066509246826, "global_step": 406715, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.125908613204956, "global_step": 406716, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.188713312149048, "global_step": 406717, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.059654712677002, "global_step": 406718, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.07403826713562, "global_step": 406719, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0701937675476074, "global_step": 406720, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1223065853118896, "global_step": 406721, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0265188217163086, "global_step": 406722, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.127556562423706, "global_step": 406723, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.019191026687622, "global_step": 406724, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1547930240631104, "global_step": 406725, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0971763134002686, "global_step": 406726, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.085432767868042, "global_step": 406727, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0973734855651855, "global_step": 406728, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1354787349700928, "global_step": 406729, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.095613718032837, "global_step": 406730, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0616228580474854, "global_step": 406731, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.087874412536621, "global_step": 406732, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0908608436584473, "global_step": 406733, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.090205192565918, "global_step": 406734, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0811831951141357, "global_step": 406735, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1148555278778076, "global_step": 406736, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1736667156219482, "global_step": 406737, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.086247682571411, "global_step": 406738, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1347243785858154, "global_step": 406739, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.060112953186035, "global_step": 406740, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.143710136413574, "global_step": 406741, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1137704849243164, "global_step": 406742, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0512235164642334, "global_step": 406743, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0650556087493896, "global_step": 406744, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1437010765075684, "global_step": 406745, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.085385799407959, "global_step": 406746, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0977346897125244, "global_step": 406747, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1008689403533936, "global_step": 406748, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1000049114227295, "global_step": 406749, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0833191871643066, "global_step": 406750, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0951156616210938, "global_step": 406751, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1029560565948486, "global_step": 406752, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0641307830810547, "global_step": 406753, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.168360948562622, "global_step": 406754, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.100087881088257, "global_step": 406755, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.186635971069336, "global_step": 406756, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.051388740539551, "global_step": 406757, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1315059661865234, "global_step": 406758, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1144814491271973, "global_step": 406759, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1613988876342773, "global_step": 406760, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0504024028778076, "global_step": 406761, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.072998285293579, "global_step": 406762, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.095083475112915, "global_step": 406763, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0748136043548584, "global_step": 406764, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0740468502044678, "global_step": 406765, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.131840229034424, "global_step": 406766, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0739033222198486, "global_step": 406767, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0704116821289062, "global_step": 406768, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0600426197052, "global_step": 406769, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0747663974761963, "global_step": 406770, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1446239948272705, "global_step": 406771, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.051811456680298, "global_step": 406772, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0694029331207275, "global_step": 406773, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.104243516921997, "global_step": 406774, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1306939125061035, "global_step": 406775, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.100412607192993, "global_step": 406776, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.104923725128174, "global_step": 406777, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0851449966430664, "global_step": 406778, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.14370059967041, "global_step": 406779, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1806235313415527, "global_step": 406780, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.2321231365203857, "global_step": 406781, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.002534866333008, "global_step": 406782, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1569347381591797, "global_step": 406783, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.099848508834839, "global_step": 406784, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.119142532348633, "global_step": 406785, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.056748390197754, "global_step": 406786, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1008148193359375, "global_step": 406787, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1103010177612305, "global_step": 406788, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1043286323547363, "global_step": 406789, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0820109844207764, "global_step": 406790, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1828083992004395, "global_step": 406791, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1502578258514404, "global_step": 406792, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.117213249206543, "global_step": 406793, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0505287647247314, "global_step": 406794, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1464507579803467, "global_step": 406795, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.062889814376831, "global_step": 406796, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0899970531463623, "global_step": 406797, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.077943801879883, "global_step": 406798, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1000545024871826, "global_step": 406799, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1962382793426514, "global_step": 406800, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.087097644805908, "global_step": 406801, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0797107219696045, "global_step": 406802, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1830952167510986, "global_step": 406803, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1460118293762207, "global_step": 406804, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1307272911071777, "global_step": 406805, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1347718238830566, "global_step": 406806, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.152874231338501, "global_step": 406807, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1315784454345703, "global_step": 406808, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1868138313293457, "global_step": 406809, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.116879940032959, "global_step": 406810, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.083106279373169, "global_step": 406811, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1302249431610107, "global_step": 406812, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0614795684814453, "global_step": 406813, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.097707748413086, "global_step": 406814, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0943641662597656, "global_step": 406815, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.105219602584839, "global_step": 406816, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0929441452026367, "global_step": 406817, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0575661659240723, "global_step": 406818, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0221989154815674, "global_step": 406819, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.104870557785034, "global_step": 406820, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1140713691711426, "global_step": 406821, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.11852765083313, "global_step": 406822, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1813385486602783, "global_step": 406823, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0302600860595703, "global_step": 406824, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0756077766418457, "global_step": 406825, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0458269119262695, "global_step": 406826, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.090742826461792, "global_step": 406827, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.166905641555786, "global_step": 406828, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.154911994934082, "global_step": 406829, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.160808563232422, "global_step": 406830, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0187532901763916, "global_step": 406831, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.137439727783203, "global_step": 406832, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1736464500427246, "global_step": 406833, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.180279016494751, "global_step": 406834, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.070666790008545, "global_step": 406835, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.9628658294677734, "global_step": 406836, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0921132564544678, "global_step": 406837, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1010124683380127, "global_step": 406838, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1575510501861572, "global_step": 406839, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1086437702178955, "global_step": 406840, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0011889934539795, "global_step": 406841, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0564284324645996, "global_step": 406842, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.147204637527466, "global_step": 406843, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1384472846984863, "global_step": 406844, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.029726505279541, "global_step": 406845, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.050759792327881, "global_step": 406846, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.103828191757202, "global_step": 406847, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0561158657073975, "global_step": 406848, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0513758659362793, "global_step": 406849, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0787506103515625, "global_step": 406850, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1296422481536865, "global_step": 406851, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0720388889312744, "global_step": 406852, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0542726516723633, "global_step": 406853, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.090944290161133, "global_step": 406854, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.041445016860962, "global_step": 406855, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1433775424957275, "global_step": 406856, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1155176162719727, "global_step": 406857, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1335225105285645, "global_step": 406858, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1409385204315186, "global_step": 406859, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0631141662597656, "global_step": 406860, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1162054538726807, "global_step": 406861, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1731648445129395, "global_step": 406862, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0728044509887695, "global_step": 406863, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.151585578918457, "global_step": 406864, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.178384780883789, "global_step": 406865, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.042224645614624, "global_step": 406866, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.073345422744751, "global_step": 406867, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0841031074523926, "global_step": 406868, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.078104257583618, "global_step": 406869, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0914368629455566, "global_step": 406870, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0977725982666016, "global_step": 406871, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.067647695541382, "global_step": 406872, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1730406284332275, "global_step": 406873, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.048402786254883, "global_step": 406874, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0890934467315674, "global_step": 406875, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.062596082687378, "global_step": 406876, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0812487602233887, "global_step": 406877, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1304032802581787, "global_step": 406878, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.089998245239258, "global_step": 406879, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.111407995223999, "global_step": 406880, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0639686584472656, "global_step": 406881, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.081613779067993, "global_step": 406882, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1056249141693115, "global_step": 406883, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.091322183609009, "global_step": 406884, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0929055213928223, "global_step": 406885, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.138702154159546, "global_step": 406886, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0706207752227783, "global_step": 406887, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.145700216293335, "global_step": 406888, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.089688301086426, "global_step": 406889, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1117255687713623, "global_step": 406890, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1309022903442383, "global_step": 406891, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.029686212539673, "global_step": 406892, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1037983894348145, "global_step": 406893, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.067411422729492, "global_step": 406894, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1608169078826904, "global_step": 406895, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.163770914077759, "global_step": 406896, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.091607093811035, "global_step": 406897, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1589787006378174, "global_step": 406898, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1197240352630615, "global_step": 406899, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0932507514953613, "global_step": 406900, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0926685333251953, "global_step": 406901, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1181640625, "global_step": 406902, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.036576747894287, "global_step": 406903, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1360645294189453, "global_step": 406904, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.060415029525757, "global_step": 406905, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0755577087402344, "global_step": 406906, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.078428030014038, "global_step": 406907, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1387088298797607, "global_step": 406908, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0811924934387207, "global_step": 406909, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0775558948516846, "global_step": 406910, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0643019676208496, "global_step": 406911, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.083919048309326, "global_step": 406912, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.062368631362915, "global_step": 406913, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.059473752975464, "global_step": 406914, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0877251625061035, "global_step": 406915, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.129223346710205, "global_step": 406916, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1477959156036377, "global_step": 406917, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.9603190422058105, "global_step": 406918, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.050391912460327, "global_step": 406919, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0521702766418457, "global_step": 406920, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.9912729263305664, "global_step": 406921, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0497541427612305, "global_step": 406922, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.992417812347412, "global_step": 406923, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.06689715385437, "global_step": 406924, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0243866443634033, "global_step": 406925, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0555689334869385, "global_step": 406926, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.101992130279541, "global_step": 406927, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1688427925109863, "global_step": 406928, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0480527877807617, "global_step": 406929, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.084658622741699, "global_step": 406930, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.042020320892334, "global_step": 406931, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.198753833770752, "global_step": 406932, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.988242745399475, "global_step": 406933, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0480868816375732, "global_step": 406934, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.030165910720825, "global_step": 406935, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1745221614837646, "global_step": 406936, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0295519828796387, "global_step": 406937, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1010472774505615, "global_step": 406938, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0483062267303467, "global_step": 406939, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1577627658843994, "global_step": 406940, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.065417766571045, "global_step": 406941, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.084503412246704, "global_step": 406942, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.085836172103882, "global_step": 406943, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.176832675933838, "global_step": 406944, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0996663570404053, "global_step": 406945, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.2030370235443115, "global_step": 406946, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1667234897613525, "global_step": 406947, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0374255180358887, "global_step": 406948, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.067267656326294, "global_step": 406949, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0840442180633545, "global_step": 406950, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.138047456741333, "global_step": 406951, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.032076120376587, "global_step": 406952, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.158761501312256, "global_step": 406953, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1118547916412354, "global_step": 406954, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.057731866836548, "global_step": 406955, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1930642127990723, "global_step": 406956, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.030249834060669, "global_step": 406957, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.138233184814453, "global_step": 406958, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0265772342681885, "global_step": 406959, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1090307235717773, "global_step": 406960, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.988620400428772, "global_step": 406961, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0971248149871826, "global_step": 406962, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0953891277313232, "global_step": 406963, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.05244517326355, "global_step": 406964, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0948915481567383, "global_step": 406965, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.144153356552124, "global_step": 406966, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.084308624267578, "global_step": 406967, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.028107166290283, "global_step": 406968, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.138096570968628, "global_step": 406969, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1284756660461426, "global_step": 406970, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0479869842529297, "global_step": 406971, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1601366996765137, "global_step": 406972, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1461002826690674, "global_step": 406973, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.149876594543457, "global_step": 406974, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.055988073348999, "global_step": 406975, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.116959810256958, "global_step": 406976, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0486249923706055, "global_step": 406977, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0791995525360107, "global_step": 406978, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.148446559906006, "global_step": 406979, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0522029399871826, "global_step": 406980, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.082853078842163, "global_step": 406981, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.077219247817993, "global_step": 406982, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1182737350463867, "global_step": 406983, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.154811382293701, "global_step": 406984, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0367696285247803, "global_step": 406985, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0836284160614014, "global_step": 406986, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.131671667098999, "global_step": 406987, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1266415119171143, "global_step": 406988, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0397160053253174, "global_step": 406989, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0799343585968018, "global_step": 406990, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.135014533996582, "global_step": 406991, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1490299701690674, "global_step": 406992, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1146321296691895, "global_step": 406993, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1539387702941895, "global_step": 406994, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0754361152648926, "global_step": 406995, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1485540866851807, "global_step": 406996, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.030221462249756, "global_step": 406997, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.106623888015747, "global_step": 406998, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.161547899246216, "global_step": 406999, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0951485633850098, "global_step": 407000, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.085629940032959, "global_step": 407001, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1011250019073486, "global_step": 407002, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0992839336395264, "global_step": 407003, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.9994240999221802, "global_step": 407004, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1148104667663574, "global_step": 407005, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0605876445770264, "global_step": 407006, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1516923904418945, "global_step": 407007, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.108686923980713, "global_step": 407008, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1792194843292236, "global_step": 407009, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.091906785964966, "global_step": 407010, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1525485515594482, "global_step": 407011, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1486449241638184, "global_step": 407012, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.111980438232422, "global_step": 407013, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0677897930145264, "global_step": 407014, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.126157760620117, "global_step": 407015, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0657081604003906, "global_step": 407016, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.160165786743164, "global_step": 407017, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0965118408203125, "global_step": 407018, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.149235725402832, "global_step": 407019, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0124878883361816, "global_step": 407020, "epoch": 769, "lr": 5e-05}
{"train_loss": 1.9825739860534668, "global_step": 407021, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.116917133331299, "global_step": 407022, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1366958618164062, "global_step": 407023, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.133862018585205, "global_step": 407024, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0325331687927246, "global_step": 407025, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0997653007507324, "global_step": 407026, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0203676223754883, "global_step": 407027, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0384647846221924, "global_step": 407028, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0723464488983154, "global_step": 407029, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1690096855163574, "global_step": 407030, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.091695547103882, "global_step": 407031, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1125826835632324, "global_step": 407032, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0913186073303223, "global_step": 407033, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1544318199157715, "global_step": 407034, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.12589168548584, "global_step": 407035, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0574002265930176, "global_step": 407036, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.037445306777954, "global_step": 407037, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1548402309417725, "global_step": 407038, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1162917613983154, "global_step": 407039, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.141773223876953, "global_step": 407040, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0943076610565186, "global_step": 407041, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.13271164894104, "global_step": 407042, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.133615732192993, "global_step": 407043, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0743467807769775, "global_step": 407044, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0866594314575195, "global_step": 407045, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.053882598876953, "global_step": 407046, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0464248657226562, "global_step": 407047, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0216257572174072, "global_step": 407048, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.076158285140991, "global_step": 407049, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.081348180770874, "global_step": 407050, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0817713737487793, "global_step": 407051, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1301987171173096, "global_step": 407052, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1961584091186523, "global_step": 407053, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.096864700317383, "global_step": 407054, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.087069034576416, "global_step": 407055, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0260491371154785, "global_step": 407056, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1320226192474365, "global_step": 407057, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1012399196624756, "global_step": 407058, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0570712089538574, "global_step": 407059, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0374722480773926, "global_step": 407060, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1619787216186523, "global_step": 407061, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.128356695175171, "global_step": 407062, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1784257888793945, "global_step": 407063, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.059396743774414, "global_step": 407064, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1032140254974365, "global_step": 407065, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.193424940109253, "global_step": 407066, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.09903883934021, "global_step": 407067, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.007195234298706, "global_step": 407068, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0660998821258545, "global_step": 407069, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1713032722473145, "global_step": 407070, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.156095504760742, "global_step": 407071, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.128730535507202, "global_step": 407072, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0771310329437256, "global_step": 407073, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0431206226348877, "global_step": 407074, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0920658111572266, "global_step": 407075, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.04565691947937, "global_step": 407076, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.159757137298584, "global_step": 407077, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1112263202667236, "global_step": 407078, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0207579135894775, "global_step": 407079, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1606600284576416, "global_step": 407080, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.091256856918335, "global_step": 407081, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1476762294769287, "global_step": 407082, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.19867205619812, "global_step": 407083, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1085431575775146, "global_step": 407084, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1438581943511963, "global_step": 407085, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1753933429718018, "global_step": 407086, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.086249828338623, "global_step": 407087, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1387288570404053, "global_step": 407088, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0459139347076416, "global_step": 407089, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.035839080810547, "global_step": 407090, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0547823905944824, "global_step": 407091, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.125839948654175, "global_step": 407092, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.107159376144409, "global_step": 407093, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0923852920532227, "global_step": 407094, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.161597728729248, "global_step": 407095, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1108767986297607, "global_step": 407096, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1364200115203857, "global_step": 407097, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.070134162902832, "global_step": 407098, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.175736427307129, "global_step": 407099, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0161805152893066, "global_step": 407100, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.133831262588501, "global_step": 407101, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1378722190856934, "global_step": 407102, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.089390277862549, "global_step": 407103, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0658485889434814, "global_step": 407104, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0400350093841553, "global_step": 407105, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.125366687774658, "global_step": 407106, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1069395542144775, "global_step": 407107, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.1856045722961426, "global_step": 407108, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.033844232559204, "global_step": 407109, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.118997097015381, "global_step": 407110, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.194310426712036, "global_step": 407111, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0937438011169434, "global_step": 407112, "epoch": 769, "lr": 5e-05}
{"train_loss": 2.0892727375030518, "global_step": 407113, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.167120933532715, "global_step": 407114, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0312507152557373, "global_step": 407115, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.035656690597534, "global_step": 407116, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.070470094680786, "global_step": 407117, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0988945960998535, "global_step": 407118, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1081936359405518, "global_step": 407119, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0601487159729004, "global_step": 407120, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0361735820770264, "global_step": 407121, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1541333198547363, "global_step": 407122, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0530495643615723, "global_step": 407123, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0130701065063477, "global_step": 407124, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.074051856994629, "global_step": 407125, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9973920583724976, "global_step": 407126, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.05527663230896, "global_step": 407127, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0579774379730225, "global_step": 407128, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.099102020263672, "global_step": 407129, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0305585861206055, "global_step": 407130, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0834598541259766, "global_step": 407131, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1083357334136963, "global_step": 407132, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.087035894393921, "global_step": 407133, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9682811498641968, "global_step": 407134, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0451455116271973, "global_step": 407135, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.063917398452759, "global_step": 407136, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.163416624069214, "global_step": 407137, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1466355323791504, "global_step": 407138, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0908336639404297, "global_step": 407139, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.025588274002075, "global_step": 407140, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0058770179748535, "global_step": 407141, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0964434146881104, "global_step": 407142, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0449509620666504, "global_step": 407143, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1332664489746094, "global_step": 407144, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0007712841033936, "global_step": 407145, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0821316242218018, "global_step": 407146, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0827300548553467, "global_step": 407147, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0687527656555176, "global_step": 407148, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0285937786102295, "global_step": 407149, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.021505355834961, "global_step": 407150, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.097160577774048, "global_step": 407151, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.170830011367798, "global_step": 407152, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.026989221572876, "global_step": 407153, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0376434326171875, "global_step": 407154, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.155993938446045, "global_step": 407155, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.102076530456543, "global_step": 407156, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.031033754348755, "global_step": 407157, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9681589603424072, "global_step": 407158, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0570967197418213, "global_step": 407159, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1411609649658203, "global_step": 407160, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1910181045532227, "global_step": 407161, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.066195249557495, "global_step": 407162, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1253297328948975, "global_step": 407163, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.157587766647339, "global_step": 407164, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.070619583129883, "global_step": 407165, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0371971130371094, "global_step": 407166, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1260406970977783, "global_step": 407167, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.078260660171509, "global_step": 407168, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9725638628005981, "global_step": 407169, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0266289710998535, "global_step": 407170, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.083932876586914, "global_step": 407171, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.043278455734253, "global_step": 407172, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0873842239379883, "global_step": 407173, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1077890396118164, "global_step": 407174, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1232450008392334, "global_step": 407175, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.142529249191284, "global_step": 407176, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.034815549850464, "global_step": 407177, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0081140995025635, "global_step": 407178, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.191763162612915, "global_step": 407179, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0740725994110107, "global_step": 407180, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.100175142288208, "global_step": 407181, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0596911907196045, "global_step": 407182, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.095560312271118, "global_step": 407183, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.127107620239258, "global_step": 407184, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0747737884521484, "global_step": 407185, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1251089572906494, "global_step": 407186, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1078548431396484, "global_step": 407187, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.077552318572998, "global_step": 407188, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1040165424346924, "global_step": 407189, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1408679485321045, "global_step": 407190, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1058506965637207, "global_step": 407191, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.053593397140503, "global_step": 407192, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0518107414245605, "global_step": 407193, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.042849063873291, "global_step": 407194, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1006972789764404, "global_step": 407195, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0347564220428467, "global_step": 407196, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1314423084259033, "global_step": 407197, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.121245861053467, "global_step": 407198, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0541725158691406, "global_step": 407199, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1092848777770996, "global_step": 407200, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0669891834259033, "global_step": 407201, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.064181327819824, "global_step": 407202, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9770790338516235, "global_step": 407203, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1967415809631348, "global_step": 407204, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0087227821350098, "global_step": 407205, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1333558559417725, "global_step": 407206, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1555161476135254, "global_step": 407207, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.013596296310425, "global_step": 407208, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.078706741333008, "global_step": 407209, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.191333293914795, "global_step": 407210, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.090873956680298, "global_step": 407211, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1157784461975098, "global_step": 407212, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1361498832702637, "global_step": 407213, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.190652847290039, "global_step": 407214, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.069312572479248, "global_step": 407215, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.145888328552246, "global_step": 407216, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1347458362579346, "global_step": 407217, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1913864612579346, "global_step": 407218, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.06298828125, "global_step": 407219, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1738851070404053, "global_step": 407220, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.170926570892334, "global_step": 407221, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9841591119766235, "global_step": 407222, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0780115127563477, "global_step": 407223, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0796823501586914, "global_step": 407224, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0347061157226562, "global_step": 407225, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.093116521835327, "global_step": 407226, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.111489772796631, "global_step": 407227, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.100090503692627, "global_step": 407228, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0325982570648193, "global_step": 407229, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1309714317321777, "global_step": 407230, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0809547901153564, "global_step": 407231, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1280136108398438, "global_step": 407232, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.063753128051758, "global_step": 407233, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1694817543029785, "global_step": 407234, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0837128162384033, "global_step": 407235, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.135350465774536, "global_step": 407236, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1174027919769287, "global_step": 407237, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1797022819519043, "global_step": 407238, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.089901924133301, "global_step": 407239, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0653140544891357, "global_step": 407240, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1124653816223145, "global_step": 407241, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1010780334472656, "global_step": 407242, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.148707866668701, "global_step": 407243, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.087599515914917, "global_step": 407244, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.158273220062256, "global_step": 407245, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1113548278808594, "global_step": 407246, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.128056526184082, "global_step": 407247, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.071138858795166, "global_step": 407248, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1078033447265625, "global_step": 407249, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.169046401977539, "global_step": 407250, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.056642532348633, "global_step": 407251, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0208194255828857, "global_step": 407252, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.146925210952759, "global_step": 407253, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1369516849517822, "global_step": 407254, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9991315603256226, "global_step": 407255, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0972399711608887, "global_step": 407256, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0396969318389893, "global_step": 407257, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1181535720825195, "global_step": 407258, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0852792263031006, "global_step": 407259, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.004371404647827, "global_step": 407260, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1488571166992188, "global_step": 407261, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.120509147644043, "global_step": 407262, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1015915870666504, "global_step": 407263, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0967905521392822, "global_step": 407264, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.073528289794922, "global_step": 407265, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.067153215408325, "global_step": 407266, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1066300868988037, "global_step": 407267, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.039313316345215, "global_step": 407268, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0631771087646484, "global_step": 407269, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.079335927963257, "global_step": 407270, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0607595443725586, "global_step": 407271, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0691230297088623, "global_step": 407272, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0594325065612793, "global_step": 407273, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1156280040740967, "global_step": 407274, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0336389541625977, "global_step": 407275, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1247153282165527, "global_step": 407276, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.048689365386963, "global_step": 407277, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.044296979904175, "global_step": 407278, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1875972747802734, "global_step": 407279, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0793049335479736, "global_step": 407280, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1513733863830566, "global_step": 407281, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1062731742858887, "global_step": 407282, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1030471324920654, "global_step": 407283, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9895812273025513, "global_step": 407284, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1815237998962402, "global_step": 407285, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1142048835754395, "global_step": 407286, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.055344343185425, "global_step": 407287, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1581783294677734, "global_step": 407288, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.062472343444824, "global_step": 407289, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.166069984436035, "global_step": 407290, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0359902381896973, "global_step": 407291, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0353333950042725, "global_step": 407292, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0081841945648193, "global_step": 407293, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1460304260253906, "global_step": 407294, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.02374005317688, "global_step": 407295, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.118933916091919, "global_step": 407296, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0670318603515625, "global_step": 407297, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1794393062591553, "global_step": 407298, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.053055763244629, "global_step": 407299, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1061172485351562, "global_step": 407300, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1420044898986816, "global_step": 407301, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0489816665649414, "global_step": 407302, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.987424373626709, "global_step": 407303, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.100477695465088, "global_step": 407304, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.19104266166687, "global_step": 407305, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.129646062850952, "global_step": 407306, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0974349975585938, "global_step": 407307, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.020223617553711, "global_step": 407308, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.00338077545166, "global_step": 407309, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.026970148086548, "global_step": 407310, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.011636257171631, "global_step": 407311, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.106997013092041, "global_step": 407312, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1033151149749756, "global_step": 407313, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0963969230651855, "global_step": 407314, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.067970037460327, "global_step": 407315, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.024272918701172, "global_step": 407316, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0767111778259277, "global_step": 407317, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0752274990081787, "global_step": 407318, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1246135234832764, "global_step": 407319, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0862650871276855, "global_step": 407320, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1020126342773438, "global_step": 407321, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1172266006469727, "global_step": 407322, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.077867269515991, "global_step": 407323, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.102229595184326, "global_step": 407324, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.103654146194458, "global_step": 407325, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0716753005981445, "global_step": 407326, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0679361820220947, "global_step": 407327, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1494760513305664, "global_step": 407328, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.141087055206299, "global_step": 407329, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1381609439849854, "global_step": 407330, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.026656150817871, "global_step": 407331, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1308605670928955, "global_step": 407332, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1277859210968018, "global_step": 407333, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0886917114257812, "global_step": 407334, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.972034215927124, "global_step": 407335, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9890683889389038, "global_step": 407336, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.10225248336792, "global_step": 407337, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1326255798339844, "global_step": 407338, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.153202772140503, "global_step": 407339, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.032282829284668, "global_step": 407340, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.149791717529297, "global_step": 407341, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1385982036590576, "global_step": 407342, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1019484996795654, "global_step": 407343, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.078401803970337, "global_step": 407344, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1629366874694824, "global_step": 407345, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0349302291870117, "global_step": 407346, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0587682723999023, "global_step": 407347, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.168701171875, "global_step": 407348, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0267887115478516, "global_step": 407349, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0700204372406006, "global_step": 407350, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0078256130218506, "global_step": 407351, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.212679147720337, "global_step": 407352, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.056647777557373, "global_step": 407353, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1150898933410645, "global_step": 407354, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1227028369903564, "global_step": 407355, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0405287742614746, "global_step": 407356, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1160824298858643, "global_step": 407357, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0973575115203857, "global_step": 407358, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1387763023376465, "global_step": 407359, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.09515643119812, "global_step": 407360, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0740983486175537, "global_step": 407361, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.053396463394165, "global_step": 407362, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.116586208343506, "global_step": 407363, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1444005966186523, "global_step": 407364, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.012570381164551, "global_step": 407365, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0561540126800537, "global_step": 407366, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0969479084014893, "global_step": 407367, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1114752292633057, "global_step": 407368, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0000126361846924, "global_step": 407369, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0808515548706055, "global_step": 407370, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.082090139389038, "global_step": 407371, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0281591415405273, "global_step": 407372, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0795505046844482, "global_step": 407373, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.168529510498047, "global_step": 407374, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0750670433044434, "global_step": 407375, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1093475818634033, "global_step": 407376, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.044330596923828, "global_step": 407377, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.128829002380371, "global_step": 407378, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.080343246459961, "global_step": 407379, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.139478921890259, "global_step": 407380, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.16318941116333, "global_step": 407381, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1410350799560547, "global_step": 407382, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1262896060943604, "global_step": 407383, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1134567260742188, "global_step": 407384, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.113151788711548, "global_step": 407385, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.144477367401123, "global_step": 407386, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0798449516296387, "global_step": 407387, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1428189277648926, "global_step": 407388, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1258223056793213, "global_step": 407389, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.052875280380249, "global_step": 407390, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.184370279312134, "global_step": 407391, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.128357410430908, "global_step": 407392, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1744117736816406, "global_step": 407393, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.080440044403076, "global_step": 407394, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0970656871795654, "global_step": 407395, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.215749979019165, "global_step": 407396, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0123744010925293, "global_step": 407397, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.052704095840454, "global_step": 407398, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0302035808563232, "global_step": 407399, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1299238204956055, "global_step": 407400, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.172973871231079, "global_step": 407401, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0581538677215576, "global_step": 407402, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.099433660507202, "global_step": 407403, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9924702644348145, "global_step": 407404, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.072753429412842, "global_step": 407405, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1344454288482666, "global_step": 407406, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.059711217880249, "global_step": 407407, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0814034938812256, "global_step": 407408, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0878710746765137, "global_step": 407409, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1235291957855225, "global_step": 407410, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0353167057037354, "global_step": 407411, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.074758529663086, "global_step": 407412, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9708869457244873, "global_step": 407413, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0811398029327393, "global_step": 407414, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.057461738586426, "global_step": 407415, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.095513343811035, "global_step": 407416, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0341100692749023, "global_step": 407417, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0302622318267822, "global_step": 407418, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9649567604064941, "global_step": 407419, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1467854976654053, "global_step": 407420, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.154080629348755, "global_step": 407421, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1170313358306885, "global_step": 407422, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0319764614105225, "global_step": 407423, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.127392530441284, "global_step": 407424, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0845179557800293, "global_step": 407425, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.096503257751465, "global_step": 407426, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1351675987243652, "global_step": 407427, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0375008583068848, "global_step": 407428, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1649858951568604, "global_step": 407429, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0249812602996826, "global_step": 407430, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1324028968811035, "global_step": 407431, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0345516204833984, "global_step": 407432, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0894134044647217, "global_step": 407433, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.139326810836792, "global_step": 407434, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1649065017700195, "global_step": 407435, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.085686206817627, "global_step": 407436, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.159086227416992, "global_step": 407437, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.089477062225342, "global_step": 407438, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1189889907836914, "global_step": 407439, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0443904399871826, "global_step": 407440, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1031241416931152, "global_step": 407441, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.10002064704895, "global_step": 407442, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1138384342193604, "global_step": 407443, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.057814598083496, "global_step": 407444, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0961334705352783, "global_step": 407445, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.112492799758911, "global_step": 407446, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1170401573181152, "global_step": 407447, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.039872884750366, "global_step": 407448, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.056973457336426, "global_step": 407449, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.026245355606079, "global_step": 407450, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.117478370666504, "global_step": 407451, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0722665786743164, "global_step": 407452, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.029489755630493, "global_step": 407453, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1590309143066406, "global_step": 407454, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0571811199188232, "global_step": 407455, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.058891534805298, "global_step": 407456, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1300876140594482, "global_step": 407457, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.118756055831909, "global_step": 407458, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1579482555389404, "global_step": 407459, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1564247608184814, "global_step": 407460, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.034916639328003, "global_step": 407461, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0944559574127197, "global_step": 407462, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0935239791870117, "global_step": 407463, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1552419662475586, "global_step": 407464, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1569414138793945, "global_step": 407465, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1015121936798096, "global_step": 407466, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0904879570007324, "global_step": 407467, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.214031219482422, "global_step": 407468, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1481220722198486, "global_step": 407469, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.15022873878479, "global_step": 407470, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.120234727859497, "global_step": 407471, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0634970664978027, "global_step": 407472, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0824527740478516, "global_step": 407473, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.074267625808716, "global_step": 407474, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0697004795074463, "global_step": 407475, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.078918695449829, "global_step": 407476, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0386037826538086, "global_step": 407477, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0557525157928467, "global_step": 407478, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.058324098587036, "global_step": 407479, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.207019567489624, "global_step": 407480, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.15281081199646, "global_step": 407481, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.074059009552002, "global_step": 407482, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.2095820903778076, "global_step": 407483, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.119342088699341, "global_step": 407484, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.081596851348877, "global_step": 407485, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.127892255783081, "global_step": 407486, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0878565311431885, "global_step": 407487, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0990803241729736, "global_step": 407488, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1008570194244385, "global_step": 407489, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.024902105331421, "global_step": 407490, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.084376811981201, "global_step": 407491, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1227636337280273, "global_step": 407492, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1620943546295166, "global_step": 407493, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.2130606174468994, "global_step": 407494, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1064367294311523, "global_step": 407495, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0348987579345703, "global_step": 407496, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.053589344024658, "global_step": 407497, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0662472248077393, "global_step": 407498, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.047938346862793, "global_step": 407499, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0970733165740967, "global_step": 407500, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0457262992858887, "global_step": 407501, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.044961452484131, "global_step": 407502, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.082813262939453, "global_step": 407503, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0624337196350098, "global_step": 407504, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0195348262786865, "global_step": 407505, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0540854930877686, "global_step": 407506, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.026416778564453, "global_step": 407507, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.159569263458252, "global_step": 407508, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.199690818786621, "global_step": 407509, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0734360218048096, "global_step": 407510, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.040281295776367, "global_step": 407511, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.097472667694092, "global_step": 407512, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0498998165130615, "global_step": 407513, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.109266519546509, "global_step": 407514, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0681326389312744, "global_step": 407515, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1471641063690186, "global_step": 407516, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.159440040588379, "global_step": 407517, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1114449501037598, "global_step": 407518, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.2119369506835938, "global_step": 407519, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0764076709747314, "global_step": 407520, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.042165994644165, "global_step": 407521, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1454005241394043, "global_step": 407522, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.119422674179077, "global_step": 407523, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1607630252838135, "global_step": 407524, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.13478422164917, "global_step": 407525, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.119128465652466, "global_step": 407526, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.177870988845825, "global_step": 407527, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9498099088668823, "global_step": 407528, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.071892261505127, "global_step": 407529, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0819637775421143, "global_step": 407530, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0674355030059814, "global_step": 407531, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.061800956726074, "global_step": 407532, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.012061357498169, "global_step": 407533, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0300943851470947, "global_step": 407534, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0808563232421875, "global_step": 407535, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1508214473724365, "global_step": 407536, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1045634746551514, "global_step": 407537, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1057357788085938, "global_step": 407538, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.153777599334717, "global_step": 407539, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.113525390625, "global_step": 407540, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0969810485839844, "global_step": 407541, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.15032958984375, "global_step": 407542, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1040589809417725, "global_step": 407543, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.122875452041626, "global_step": 407544, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0955801010131836, "global_step": 407545, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.059443950653076, "global_step": 407546, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.186574697494507, "global_step": 407547, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0327954292297363, "global_step": 407548, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.135782241821289, "global_step": 407549, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.062863826751709, "global_step": 407550, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.096190929412842, "global_step": 407551, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.037451982498169, "global_step": 407552, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0855214595794678, "global_step": 407553, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.057586431503296, "global_step": 407554, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1210598945617676, "global_step": 407555, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1108102798461914, "global_step": 407556, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1085283756256104, "global_step": 407557, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0893449783325195, "global_step": 407558, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0964930057525635, "global_step": 407559, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1387264728546143, "global_step": 407560, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9504677057266235, "global_step": 407561, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.049567937850952, "global_step": 407562, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.141880989074707, "global_step": 407563, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0466089248657227, "global_step": 407564, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0734012126922607, "global_step": 407565, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1085667610168457, "global_step": 407566, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.054025888442993, "global_step": 407567, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.075744152069092, "global_step": 407568, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.120840072631836, "global_step": 407569, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0742225646972656, "global_step": 407570, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1548783779144287, "global_step": 407571, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.089508295059204, "global_step": 407572, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.026068687438965, "global_step": 407573, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.041940927505493, "global_step": 407574, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9940950870513916, "global_step": 407575, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.053375482559204, "global_step": 407576, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.144468307495117, "global_step": 407577, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.105903148651123, "global_step": 407578, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.180556058883667, "global_step": 407579, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.056083917617798, "global_step": 407580, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1743850708007812, "global_step": 407581, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.065511465072632, "global_step": 407582, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.057246208190918, "global_step": 407583, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1276533603668213, "global_step": 407584, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0557379722595215, "global_step": 407585, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1467843055725098, "global_step": 407586, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.097242593765259, "global_step": 407587, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0869247913360596, "global_step": 407588, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1516335010528564, "global_step": 407589, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0697977542877197, "global_step": 407590, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.081394910812378, "global_step": 407591, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.173125982284546, "global_step": 407592, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.049388885498047, "global_step": 407593, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1249053478240967, "global_step": 407594, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.044234037399292, "global_step": 407595, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.114454507827759, "global_step": 407596, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.07818341255188, "global_step": 407597, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0325396060943604, "global_step": 407598, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0225958824157715, "global_step": 407599, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1791489124298096, "global_step": 407600, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1659862995147705, "global_step": 407601, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0250909328460693, "global_step": 407602, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0962910652160645, "global_step": 407603, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.073742151260376, "global_step": 407604, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0768167972564697, "global_step": 407605, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1621925830841064, "global_step": 407606, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1880757808685303, "global_step": 407607, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1037845611572266, "global_step": 407608, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1459004878997803, "global_step": 407609, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1942665576934814, "global_step": 407610, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.147801160812378, "global_step": 407611, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.050252914428711, "global_step": 407612, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1187632083892822, "global_step": 407613, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1133675575256348, "global_step": 407614, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1259543895721436, "global_step": 407615, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0895910263061523, "global_step": 407616, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.109908103942871, "global_step": 407617, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0713984966278076, "global_step": 407618, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.080855131149292, "global_step": 407619, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.106619358062744, "global_step": 407620, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.052917957305908, "global_step": 407621, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1281027793884277, "global_step": 407622, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.092059373855591, "global_step": 407623, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0812487602233887, "global_step": 407624, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1349732875823975, "global_step": 407625, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.046970844268799, "global_step": 407626, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1565518379211426, "global_step": 407627, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.060342788696289, "global_step": 407628, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0578348636627197, "global_step": 407629, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.131617307662964, "global_step": 407630, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0158071517944336, "global_step": 407631, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0739147663116455, "global_step": 407632, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.141470193862915, "global_step": 407633, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1772427558898926, "global_step": 407634, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0463318824768066, "global_step": 407635, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.173482656478882, "global_step": 407636, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.158276319503784, "global_step": 407637, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0937697887420654, "global_step": 407638, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1069324016571045, "global_step": 407639, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1234638690948486, "global_step": 407640, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.158684730529785, "global_step": 407641, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.14082670211792, "global_step": 407642, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.070249557495117, "global_step": 407643, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.020298719406128, "global_step": 407644, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0844976902008057, "global_step": 407645, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.095193386077881, "global_step": 407646, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1239991188049316, "global_step": 407647, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0662920475006104, "global_step": 407648, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.145709753036499, "global_step": 407649, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.081167697906494, "global_step": 407650, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.115511894226074, "global_step": 407651, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1343157291412354, "global_step": 407652, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.146151065826416, "global_step": 407653, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0981860160827637, "global_step": 407654, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.127460479736328, "global_step": 407655, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0974807739257812, "global_step": 407656, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1039323806762695, "global_step": 407657, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1853151321411133, "global_step": 407658, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1052086353302, "global_step": 407659, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1216981410980225, "global_step": 407660, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.140745162963867, "global_step": 407661, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1193699836730957, "global_step": 407662, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.079580068588257, "global_step": 407663, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.019814968109131, "global_step": 407664, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.208601713180542, "global_step": 407665, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.2140724658966064, "global_step": 407666, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.118612051010132, "global_step": 407667, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0530712604522705, "global_step": 407668, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.079824447631836, "global_step": 407669, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9845243692398071, "global_step": 407670, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.170469045639038, "global_step": 407671, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.107832193374634, "global_step": 407672, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0598366260528564, "global_step": 407673, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.020847797393799, "global_step": 407674, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0631484985351562, "global_step": 407675, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1779706478118896, "global_step": 407676, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.000769853591919, "global_step": 407677, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.144155263900757, "global_step": 407678, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.073033571243286, "global_step": 407679, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0892550945281982, "global_step": 407680, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1541690826416016, "global_step": 407681, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.150269031524658, "global_step": 407682, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.092801570892334, "global_step": 407683, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1463255882263184, "global_step": 407684, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.075989246368408, "global_step": 407685, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.169224739074707, "global_step": 407686, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.112330913543701, "global_step": 407687, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.131948471069336, "global_step": 407688, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1302905082702637, "global_step": 407689, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1926677227020264, "global_step": 407690, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.108618974685669, "global_step": 407691, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1207096576690674, "global_step": 407692, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.097468614578247, "global_step": 407693, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1527833938598633, "global_step": 407694, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0227818489074707, "global_step": 407695, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.975083589553833, "global_step": 407696, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1890833377838135, "global_step": 407697, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0252888202667236, "global_step": 407698, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0589261054992676, "global_step": 407699, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1252427101135254, "global_step": 407700, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.062027931213379, "global_step": 407701, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0008039474487305, "global_step": 407702, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0542397499084473, "global_step": 407703, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.133323907852173, "global_step": 407704, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.107879877090454, "global_step": 407705, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.043269157409668, "global_step": 407706, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0333030223846436, "global_step": 407707, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.106656312942505, "global_step": 407708, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.089979410171509, "global_step": 407709, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0843076705932617, "global_step": 407710, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1056625843048096, "global_step": 407711, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1743862628936768, "global_step": 407712, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1982951164245605, "global_step": 407713, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.096421480178833, "global_step": 407714, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1814260482788086, "global_step": 407715, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1655547618865967, "global_step": 407716, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.04338002204895, "global_step": 407717, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0660829544067383, "global_step": 407718, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0972654819488525, "global_step": 407719, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.088268756866455, "global_step": 407720, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0809288024902344, "global_step": 407721, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0772716999053955, "global_step": 407722, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.139458179473877, "global_step": 407723, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.091677188873291, "global_step": 407724, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.2102580070495605, "global_step": 407725, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1468043327331543, "global_step": 407726, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0787012577056885, "global_step": 407727, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0699400901794434, "global_step": 407728, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.048746347427368, "global_step": 407729, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.059629201889038, "global_step": 407730, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.173541307449341, "global_step": 407731, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.074348211288452, "global_step": 407732, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.095871686935425, "global_step": 407733, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.086221694946289, "global_step": 407734, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.102229118347168, "global_step": 407735, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1324737071990967, "global_step": 407736, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.050089120864868, "global_step": 407737, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1173226833343506, "global_step": 407738, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.11651611328125, "global_step": 407739, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.156346559524536, "global_step": 407740, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.134575843811035, "global_step": 407741, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1326236724853516, "global_step": 407742, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.132011651992798, "global_step": 407743, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0718696117401123, "global_step": 407744, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.068035125732422, "global_step": 407745, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1233813762664795, "global_step": 407746, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.053175449371338, "global_step": 407747, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.2268035411834717, "global_step": 407748, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0787370204925537, "global_step": 407749, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.185670852661133, "global_step": 407750, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1371257305145264, "global_step": 407751, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0653367042541504, "global_step": 407752, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.06435227394104, "global_step": 407753, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9808324575424194, "global_step": 407754, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.007338285446167, "global_step": 407755, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0964956283569336, "global_step": 407756, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1511614322662354, "global_step": 407757, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.032717227935791, "global_step": 407758, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0766096115112305, "global_step": 407759, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0498876571655273, "global_step": 407760, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0485763549804688, "global_step": 407761, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1159732341766357, "global_step": 407762, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1333107948303223, "global_step": 407763, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.102454662322998, "global_step": 407764, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1073741912841797, "global_step": 407765, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.056530714035034, "global_step": 407766, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.021312952041626, "global_step": 407767, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1890461444854736, "global_step": 407768, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0799598693847656, "global_step": 407769, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0022027492523193, "global_step": 407770, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.161501407623291, "global_step": 407771, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1123299598693848, "global_step": 407772, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0254578590393066, "global_step": 407773, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1945152282714844, "global_step": 407774, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1093976497650146, "global_step": 407775, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.165536642074585, "global_step": 407776, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1635262966156006, "global_step": 407777, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.121537685394287, "global_step": 407778, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1395103931427, "global_step": 407779, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0888900756835938, "global_step": 407780, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1089823246002197, "global_step": 407781, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9865459203720093, "global_step": 407782, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.121882915496826, "global_step": 407783, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.091820240020752, "global_step": 407784, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0451791286468506, "global_step": 407785, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0593814849853516, "global_step": 407786, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1199591159820557, "global_step": 407787, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.092311382293701, "global_step": 407788, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.080080986022949, "global_step": 407789, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0589792728424072, "global_step": 407790, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1267778873443604, "global_step": 407791, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.164165735244751, "global_step": 407792, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.12217116355896, "global_step": 407793, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.091506004333496, "global_step": 407794, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.2118802070617676, "global_step": 407795, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.173246145248413, "global_step": 407796, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.087090492248535, "global_step": 407797, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1563432216644287, "global_step": 407798, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.087484836578369, "global_step": 407799, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.120081901550293, "global_step": 407800, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0707998275756836, "global_step": 407801, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.001405954360962, "global_step": 407802, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.062744379043579, "global_step": 407803, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0499374866485596, "global_step": 407804, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.146616220474243, "global_step": 407805, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.076864242553711, "global_step": 407806, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1768555641174316, "global_step": 407807, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1221885681152344, "global_step": 407808, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.093616247177124, "global_step": 407809, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1689395904541016, "global_step": 407810, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0808098316192627, "global_step": 407811, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.012343406677246, "global_step": 407812, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0407559871673584, "global_step": 407813, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1233015060424805, "global_step": 407814, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.121135950088501, "global_step": 407815, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.056741714477539, "global_step": 407816, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0534021854400635, "global_step": 407817, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.090564012527466, "global_step": 407818, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1448378562927246, "global_step": 407819, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.142362356185913, "global_step": 407820, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1522717475891113, "global_step": 407821, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.102259635925293, "global_step": 407822, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.171276330947876, "global_step": 407823, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.081789016723633, "global_step": 407824, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.119070291519165, "global_step": 407825, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1512722969055176, "global_step": 407826, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0703470706939697, "global_step": 407827, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0205023288726807, "global_step": 407828, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0719990730285645, "global_step": 407829, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.170907497406006, "global_step": 407830, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.018907070159912, "global_step": 407831, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.034383535385132, "global_step": 407832, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0494742393493652, "global_step": 407833, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0195484161376953, "global_step": 407834, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0394532680511475, "global_step": 407835, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.101863384246826, "global_step": 407836, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.025693893432617, "global_step": 407837, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1369385719299316, "global_step": 407838, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1473653316497803, "global_step": 407839, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0498647689819336, "global_step": 407840, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.027681350708008, "global_step": 407841, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0713090896606445, "global_step": 407842, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.12890887260437, "global_step": 407843, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1084351539611816, "global_step": 407844, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.097517728805542, "global_step": 407845, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.070697546005249, "global_step": 407846, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1066346168518066, "global_step": 407847, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.137143850326538, "global_step": 407848, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1127994060516357, "global_step": 407849, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0765151977539062, "global_step": 407850, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0884411334991455, "global_step": 407851, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.035910129547119, "global_step": 407852, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0314536094665527, "global_step": 407853, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1960766315460205, "global_step": 407854, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.092021942138672, "global_step": 407855, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.122210741043091, "global_step": 407856, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.073925256729126, "global_step": 407857, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.113365650177002, "global_step": 407858, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0982275009155273, "global_step": 407859, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0447046756744385, "global_step": 407860, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.099783182144165, "global_step": 407861, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1933488845825195, "global_step": 407862, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.144005060195923, "global_step": 407863, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9982523918151855, "global_step": 407864, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1054627895355225, "global_step": 407865, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.195063829421997, "global_step": 407866, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.063554286956787, "global_step": 407867, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.042468309402466, "global_step": 407868, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1242709159851074, "global_step": 407869, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.137002944946289, "global_step": 407870, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0276434421539307, "global_step": 407871, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1074957847595215, "global_step": 407872, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1350722312927246, "global_step": 407873, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0354087352752686, "global_step": 407874, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1345832347869873, "global_step": 407875, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.11490797996521, "global_step": 407876, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0930256843566895, "global_step": 407877, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.142936944961548, "global_step": 407878, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.086547613143921, "global_step": 407879, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0922768115997314, "global_step": 407880, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.110347032546997, "global_step": 407881, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0868539810180664, "global_step": 407882, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0647013187408447, "global_step": 407883, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0487608909606934, "global_step": 407884, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1289591789245605, "global_step": 407885, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.103576898574829, "global_step": 407886, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0407378673553467, "global_step": 407887, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1804287433624268, "global_step": 407888, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0784287452697754, "global_step": 407889, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.096994400024414, "global_step": 407890, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.2039904594421387, "global_step": 407891, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.103227138519287, "global_step": 407892, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1854865550994873, "global_step": 407893, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.2102577686309814, "global_step": 407894, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0691988468170166, "global_step": 407895, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1100785732269287, "global_step": 407896, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1077685356140137, "global_step": 407897, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0528650283813477, "global_step": 407898, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1030218601226807, "global_step": 407899, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0227789878845215, "global_step": 407900, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0136232376098633, "global_step": 407901, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0333709716796875, "global_step": 407902, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1344423294067383, "global_step": 407903, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1426947116851807, "global_step": 407904, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.109959363937378, "global_step": 407905, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0488948822021484, "global_step": 407906, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1678261756896973, "global_step": 407907, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.093050956726074, "global_step": 407908, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.143454074859619, "global_step": 407909, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0679521560668945, "global_step": 407910, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0402374267578125, "global_step": 407911, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.2270896434783936, "global_step": 407912, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0958638191223145, "global_step": 407913, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0067083835601807, "global_step": 407914, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1362557411193848, "global_step": 407915, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.052635669708252, "global_step": 407916, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1483099460601807, "global_step": 407917, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.118457317352295, "global_step": 407918, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.119772434234619, "global_step": 407919, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.125164270401001, "global_step": 407920, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0306384563446045, "global_step": 407921, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1078717708587646, "global_step": 407922, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0841825008392334, "global_step": 407923, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.138143301010132, "global_step": 407924, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.232929229736328, "global_step": 407925, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0383150577545166, "global_step": 407926, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.051267147064209, "global_step": 407927, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.123830795288086, "global_step": 407928, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.056817054748535, "global_step": 407929, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.188203811645508, "global_step": 407930, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.091604709625244, "global_step": 407931, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1082684993743896, "global_step": 407932, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.14314341545105, "global_step": 407933, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1105048656463623, "global_step": 407934, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.074230432510376, "global_step": 407935, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1040213108062744, "global_step": 407936, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0728390216827393, "global_step": 407937, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1140294075012207, "global_step": 407938, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9655503034591675, "global_step": 407939, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.169515371322632, "global_step": 407940, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.115827798843384, "global_step": 407941, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1566672325134277, "global_step": 407942, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.143394947052002, "global_step": 407943, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1376140117645264, "global_step": 407944, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.2027695178985596, "global_step": 407945, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.079982042312622, "global_step": 407946, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.099400043487549, "global_step": 407947, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.031694173812866, "global_step": 407948, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0971837043762207, "global_step": 407949, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0719456672668457, "global_step": 407950, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.113569498062134, "global_step": 407951, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.112194776535034, "global_step": 407952, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1176645755767822, "global_step": 407953, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1171436309814453, "global_step": 407954, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1014246940612793, "global_step": 407955, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1636219024658203, "global_step": 407956, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1185617446899414, "global_step": 407957, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1577389240264893, "global_step": 407958, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1371426582336426, "global_step": 407959, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.061040163040161, "global_step": 407960, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.956105351448059, "global_step": 407961, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.082956075668335, "global_step": 407962, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0412662029266357, "global_step": 407963, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0805797576904297, "global_step": 407964, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.194371461868286, "global_step": 407965, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.09027099609375, "global_step": 407966, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1125028133392334, "global_step": 407967, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.052103042602539, "global_step": 407968, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1049394607543945, "global_step": 407969, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1452925205230713, "global_step": 407970, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.135117530822754, "global_step": 407971, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0805468559265137, "global_step": 407972, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0920093059539795, "global_step": 407973, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1018519401550293, "global_step": 407974, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.2279953956604004, "global_step": 407975, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.009441614151001, "global_step": 407976, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1056230068206787, "global_step": 407977, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.010988473892212, "global_step": 407978, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.212757110595703, "global_step": 407979, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.070977210998535, "global_step": 407980, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0591323375701904, "global_step": 407981, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0664989948272705, "global_step": 407982, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.091014862060547, "global_step": 407983, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.200352907180786, "global_step": 407984, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.048311948776245, "global_step": 407985, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.114625930786133, "global_step": 407986, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.135209560394287, "global_step": 407987, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0624067783355713, "global_step": 407988, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.09073543548584, "global_step": 407989, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.12430739402771, "global_step": 407990, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.102860927581787, "global_step": 407991, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.13936710357666, "global_step": 407992, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.074198007583618, "global_step": 407993, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1861765384674072, "global_step": 407994, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0059292316436768, "global_step": 407995, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.150137186050415, "global_step": 407996, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0875370502471924, "global_step": 407997, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.096510887145996, "global_step": 407998, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1313230991363525, "global_step": 407999, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1963086128234863, "global_step": 408000, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.136504650115967, "global_step": 408001, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1385726928710938, "global_step": 408002, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0937342643737793, "global_step": 408003, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0676441192626953, "global_step": 408004, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.036543130874634, "global_step": 408005, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.092111349105835, "global_step": 408006, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1425187587738037, "global_step": 408007, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0165531635284424, "global_step": 408008, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0396623611450195, "global_step": 408009, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0947492122650146, "global_step": 408010, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1461801528930664, "global_step": 408011, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9904999732971191, "global_step": 408012, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1526973247528076, "global_step": 408013, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.109593152999878, "global_step": 408014, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0897655487060547, "global_step": 408015, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1305787563323975, "global_step": 408016, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0708060264587402, "global_step": 408017, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.142303466796875, "global_step": 408018, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.161752700805664, "global_step": 408019, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1225647926330566, "global_step": 408020, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.087815284729004, "global_step": 408021, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0829670429229736, "global_step": 408022, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.002739191055298, "global_step": 408023, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.13264799118042, "global_step": 408024, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.084077835083008, "global_step": 408025, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0635366439819336, "global_step": 408026, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0944809913635254, "global_step": 408027, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1246018409729004, "global_step": 408028, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1319162845611572, "global_step": 408029, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0959954261779785, "global_step": 408030, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.119234085083008, "global_step": 408031, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.105456829071045, "global_step": 408032, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0639138221740723, "global_step": 408033, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0923380851745605, "global_step": 408034, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.145939588546753, "global_step": 408035, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9815164804458618, "global_step": 408036, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1279044151306152, "global_step": 408037, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0499842166900635, "global_step": 408038, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1041696071624756, "global_step": 408039, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.089024066925049, "global_step": 408040, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1682589054107666, "global_step": 408041, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1080198287963867, "global_step": 408042, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1147656440734863, "global_step": 408043, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.120314359664917, "global_step": 408044, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0889933109283447, "global_step": 408045, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1903457641601562, "global_step": 408046, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.114786148071289, "global_step": 408047, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0812394618988037, "global_step": 408048, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0730769634246826, "global_step": 408049, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.14076828956604, "global_step": 408050, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0483882427215576, "global_step": 408051, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.062140703201294, "global_step": 408052, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.008293867111206, "global_step": 408053, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1711666584014893, "global_step": 408054, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.152172327041626, "global_step": 408055, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1398801803588867, "global_step": 408056, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0885913372039795, "global_step": 408057, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1294498443603516, "global_step": 408058, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.157031536102295, "global_step": 408059, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.048891544342041, "global_step": 408060, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.059194803237915, "global_step": 408061, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1260437965393066, "global_step": 408062, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1160216331481934, "global_step": 408063, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.062906265258789, "global_step": 408064, "epoch": 770, "lr": 5e-05}
{"train_loss": 1.9980735778808594, "global_step": 408065, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1247336864471436, "global_step": 408066, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.080610990524292, "global_step": 408067, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0805888175964355, "global_step": 408068, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1229376792907715, "global_step": 408069, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.181119918823242, "global_step": 408070, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0978493690490723, "global_step": 408071, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0466365814208984, "global_step": 408072, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.058633804321289, "global_step": 408073, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1460859775543213, "global_step": 408074, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1441445350646973, "global_step": 408075, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0934319496154785, "global_step": 408076, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.018392324447632, "global_step": 408077, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.026728630065918, "global_step": 408078, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1486635208129883, "global_step": 408079, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.1502678394317627, "global_step": 408080, "epoch": 770, "lr": 5e-05}
{"train_loss": 2.0963079929351807, "global_step": 408081, "epoch": 770, "lr": 5e-05, "val_loss": 5.637418270111084, "test_reconst_mse": 0.07370573282241821}
{"train_loss": 2.102813720703125, "global_step": 408082, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1127500534057617, "global_step": 408083, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.105266809463501, "global_step": 408084, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.048691987991333, "global_step": 408085, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0554559230804443, "global_step": 408086, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0970633029937744, "global_step": 408087, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0910134315490723, "global_step": 408088, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0503482818603516, "global_step": 408089, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.049271821975708, "global_step": 408090, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0751473903656006, "global_step": 408091, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.119680643081665, "global_step": 408092, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0832324028015137, "global_step": 408093, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0023932456970215, "global_step": 408094, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.048152208328247, "global_step": 408095, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1082236766815186, "global_step": 408096, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1276533603668213, "global_step": 408097, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.105846405029297, "global_step": 408098, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0375771522521973, "global_step": 408099, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1074843406677246, "global_step": 408100, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.155050754547119, "global_step": 408101, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1380867958068848, "global_step": 408102, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.2068915367126465, "global_step": 408103, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.160552501678467, "global_step": 408104, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1260688304901123, "global_step": 408105, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.12138295173645, "global_step": 408106, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.043992519378662, "global_step": 408107, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.055368185043335, "global_step": 408108, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.047987222671509, "global_step": 408109, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.9846231937408447, "global_step": 408110, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.99457585811615, "global_step": 408111, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0777502059936523, "global_step": 408112, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.016569137573242, "global_step": 408113, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.103426218032837, "global_step": 408114, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0856690406799316, "global_step": 408115, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.106518030166626, "global_step": 408116, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.075018882751465, "global_step": 408117, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0711617469787598, "global_step": 408118, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1437783241271973, "global_step": 408119, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.095604181289673, "global_step": 408120, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.064797878265381, "global_step": 408121, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.054537057876587, "global_step": 408122, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0580384731292725, "global_step": 408123, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.084272861480713, "global_step": 408124, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.214160203933716, "global_step": 408125, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0679726600646973, "global_step": 408126, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.9922847747802734, "global_step": 408127, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.038893461227417, "global_step": 408128, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.056731700897217, "global_step": 408129, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.004354953765869, "global_step": 408130, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0960745811462402, "global_step": 408131, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.050689935684204, "global_step": 408132, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.010577440261841, "global_step": 408133, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1334409713745117, "global_step": 408134, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.065567970275879, "global_step": 408135, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1012473106384277, "global_step": 408136, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1159214973449707, "global_step": 408137, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0699315071105957, "global_step": 408138, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0537657737731934, "global_step": 408139, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1427273750305176, "global_step": 408140, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.078058958053589, "global_step": 408141, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1066439151763916, "global_step": 408142, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.137859344482422, "global_step": 408143, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.134578227996826, "global_step": 408144, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1194748878479004, "global_step": 408145, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0975706577301025, "global_step": 408146, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1356735229492188, "global_step": 408147, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.116288661956787, "global_step": 408148, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0145652294158936, "global_step": 408149, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0536792278289795, "global_step": 408150, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.139370918273926, "global_step": 408151, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0358829498291016, "global_step": 408152, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0799882411956787, "global_step": 408153, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1400372982025146, "global_step": 408154, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0703752040863037, "global_step": 408155, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.057528257369995, "global_step": 408156, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0695626735687256, "global_step": 408157, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.111415386199951, "global_step": 408158, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0926897525787354, "global_step": 408159, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1419689655303955, "global_step": 408160, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.055527448654175, "global_step": 408161, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.060919761657715, "global_step": 408162, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1003146171569824, "global_step": 408163, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0730998516082764, "global_step": 408164, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1360013484954834, "global_step": 408165, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1070494651794434, "global_step": 408166, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.148773193359375, "global_step": 408167, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1169660091400146, "global_step": 408168, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0347390174865723, "global_step": 408169, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0656423568725586, "global_step": 408170, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.144716501235962, "global_step": 408171, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.091428756713867, "global_step": 408172, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1104602813720703, "global_step": 408173, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0430867671966553, "global_step": 408174, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0169832706451416, "global_step": 408175, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0034992694854736, "global_step": 408176, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0947670936584473, "global_step": 408177, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0267558097839355, "global_step": 408178, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.192279577255249, "global_step": 408179, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.027418375015259, "global_step": 408180, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1166272163391113, "global_step": 408181, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1658079624176025, "global_step": 408182, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.072014570236206, "global_step": 408183, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.072221279144287, "global_step": 408184, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1002039909362793, "global_step": 408185, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.025477409362793, "global_step": 408186, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1487627029418945, "global_step": 408187, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0835154056549072, "global_step": 408188, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0699563026428223, "global_step": 408189, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.111654043197632, "global_step": 408190, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1041252613067627, "global_step": 408191, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0001981258392334, "global_step": 408192, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1732137203216553, "global_step": 408193, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.12465763092041, "global_step": 408194, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0605309009552, "global_step": 408195, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.141278028488159, "global_step": 408196, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0655386447906494, "global_step": 408197, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.090327501296997, "global_step": 408198, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0770421028137207, "global_step": 408199, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.115863800048828, "global_step": 408200, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.086413860321045, "global_step": 408201, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.071955680847168, "global_step": 408202, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1090941429138184, "global_step": 408203, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0145039558410645, "global_step": 408204, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.072828531265259, "global_step": 408205, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1103107929229736, "global_step": 408206, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.145193099975586, "global_step": 408207, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0987558364868164, "global_step": 408208, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.001645565032959, "global_step": 408209, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.09409761428833, "global_step": 408210, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.9822403192520142, "global_step": 408211, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.113375425338745, "global_step": 408212, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1017467975616455, "global_step": 408213, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.091233491897583, "global_step": 408214, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0305275917053223, "global_step": 408215, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0834739208221436, "global_step": 408216, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.078700304031372, "global_step": 408217, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1131207942962646, "global_step": 408218, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.110704183578491, "global_step": 408219, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.076578378677368, "global_step": 408220, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0915520191192627, "global_step": 408221, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0514063835144043, "global_step": 408222, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0646965503692627, "global_step": 408223, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1790480613708496, "global_step": 408224, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1562840938568115, "global_step": 408225, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0521655082702637, "global_step": 408226, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1212852001190186, "global_step": 408227, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0966527462005615, "global_step": 408228, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.99299156665802, "global_step": 408229, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.072554111480713, "global_step": 408230, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1159231662750244, "global_step": 408231, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0632243156433105, "global_step": 408232, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.04750394821167, "global_step": 408233, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.026066303253174, "global_step": 408234, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.066431760787964, "global_step": 408235, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0923378467559814, "global_step": 408236, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.060708999633789, "global_step": 408237, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1268417835235596, "global_step": 408238, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0613389015197754, "global_step": 408239, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.044673442840576, "global_step": 408240, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.147578001022339, "global_step": 408241, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.091190814971924, "global_step": 408242, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.068178415298462, "global_step": 408243, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.2845146656036377, "global_step": 408244, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.133937120437622, "global_step": 408245, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.096600294113159, "global_step": 408246, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.083099842071533, "global_step": 408247, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0770533084869385, "global_step": 408248, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.194025993347168, "global_step": 408249, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.017505168914795, "global_step": 408250, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1150379180908203, "global_step": 408251, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1622374057769775, "global_step": 408252, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.013352632522583, "global_step": 408253, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.062640905380249, "global_step": 408254, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1746814250946045, "global_step": 408255, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.128985643386841, "global_step": 408256, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1648759841918945, "global_step": 408257, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1758058071136475, "global_step": 408258, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0436675548553467, "global_step": 408259, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1017086505889893, "global_step": 408260, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0591113567352295, "global_step": 408261, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1585543155670166, "global_step": 408262, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.10909366607666, "global_step": 408263, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0867934226989746, "global_step": 408264, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0906693935394287, "global_step": 408265, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1069562435150146, "global_step": 408266, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0182793140411377, "global_step": 408267, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1411266326904297, "global_step": 408268, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1064138412475586, "global_step": 408269, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.007020950317383, "global_step": 408270, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.2289016246795654, "global_step": 408271, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.9528521299362183, "global_step": 408272, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.125236749649048, "global_step": 408273, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.117107391357422, "global_step": 408274, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1935291290283203, "global_step": 408275, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0093588829040527, "global_step": 408276, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.074982166290283, "global_step": 408277, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.082293748855591, "global_step": 408278, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.019973039627075, "global_step": 408279, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1006031036376953, "global_step": 408280, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0320842266082764, "global_step": 408281, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.086798667907715, "global_step": 408282, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1877787113189697, "global_step": 408283, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1635212898254395, "global_step": 408284, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.014167070388794, "global_step": 408285, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.113926649093628, "global_step": 408286, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.081218719482422, "global_step": 408287, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0448076725006104, "global_step": 408288, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.083238363265991, "global_step": 408289, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1024110317230225, "global_step": 408290, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1372156143188477, "global_step": 408291, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.098036527633667, "global_step": 408292, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1370530128479004, "global_step": 408293, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.066683292388916, "global_step": 408294, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0589492321014404, "global_step": 408295, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.098999261856079, "global_step": 408296, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1277403831481934, "global_step": 408297, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0885026454925537, "global_step": 408298, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.145106315612793, "global_step": 408299, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1495931148529053, "global_step": 408300, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1350841522216797, "global_step": 408301, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.9813430309295654, "global_step": 408302, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0255813598632812, "global_step": 408303, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1052112579345703, "global_step": 408304, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0953714847564697, "global_step": 408305, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0881428718566895, "global_step": 408306, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.203052043914795, "global_step": 408307, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1031301021575928, "global_step": 408308, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0812506675720215, "global_step": 408309, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.094644546508789, "global_step": 408310, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.090041399002075, "global_step": 408311, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.088695764541626, "global_step": 408312, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1832239627838135, "global_step": 408313, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.990600347518921, "global_step": 408314, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.03643798828125, "global_step": 408315, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.05027437210083, "global_step": 408316, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.059386730194092, "global_step": 408317, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.9812158346176147, "global_step": 408318, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.052467107772827, "global_step": 408319, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.130775213241577, "global_step": 408320, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.071148633956909, "global_step": 408321, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1130917072296143, "global_step": 408322, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0290896892547607, "global_step": 408323, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1413626670837402, "global_step": 408324, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1129508018493652, "global_step": 408325, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.049738645553589, "global_step": 408326, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1522159576416016, "global_step": 408327, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1317832469940186, "global_step": 408328, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1456081867218018, "global_step": 408329, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0119659900665283, "global_step": 408330, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.131261110305786, "global_step": 408331, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.092358350753784, "global_step": 408332, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.10477614402771, "global_step": 408333, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.109074831008911, "global_step": 408334, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.115368604660034, "global_step": 408335, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1425392627716064, "global_step": 408336, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.099686622619629, "global_step": 408337, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1593174934387207, "global_step": 408338, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.139802932739258, "global_step": 408339, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0741705894470215, "global_step": 408340, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0797219276428223, "global_step": 408341, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.111778497695923, "global_step": 408342, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.024308443069458, "global_step": 408343, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.126948833465576, "global_step": 408344, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1047139167785645, "global_step": 408345, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.030871629714966, "global_step": 408346, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.058795928955078, "global_step": 408347, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0964717864990234, "global_step": 408348, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.071840286254883, "global_step": 408349, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1476869583129883, "global_step": 408350, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.044398784637451, "global_step": 408351, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.150543451309204, "global_step": 408352, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.083564281463623, "global_step": 408353, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1508259773254395, "global_step": 408354, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.102226495742798, "global_step": 408355, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0409791469573975, "global_step": 408356, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.066061019897461, "global_step": 408357, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1298983097076416, "global_step": 408358, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.089724063873291, "global_step": 408359, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0989606380462646, "global_step": 408360, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1315393447875977, "global_step": 408361, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1829140186309814, "global_step": 408362, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0039188861846924, "global_step": 408363, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.130589485168457, "global_step": 408364, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.066648006439209, "global_step": 408365, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.14797043800354, "global_step": 408366, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0284366607666016, "global_step": 408367, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0608510971069336, "global_step": 408368, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.047539234161377, "global_step": 408369, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0649473667144775, "global_step": 408370, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.05470871925354, "global_step": 408371, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0928471088409424, "global_step": 408372, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.062535047531128, "global_step": 408373, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0385067462921143, "global_step": 408374, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0622830390930176, "global_step": 408375, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.103909969329834, "global_step": 408376, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1500966548919678, "global_step": 408377, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1459779739379883, "global_step": 408378, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.03657865524292, "global_step": 408379, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.05521821975708, "global_step": 408380, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1370158195495605, "global_step": 408381, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1331443786621094, "global_step": 408382, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1329612731933594, "global_step": 408383, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.101116418838501, "global_step": 408384, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.094923973083496, "global_step": 408385, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.096764087677002, "global_step": 408386, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0670418739318848, "global_step": 408387, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.126060724258423, "global_step": 408388, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0684220790863037, "global_step": 408389, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1512317657470703, "global_step": 408390, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.109187126159668, "global_step": 408391, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1649062633514404, "global_step": 408392, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.134873867034912, "global_step": 408393, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.021829128265381, "global_step": 408394, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.060267925262451, "global_step": 408395, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.163952112197876, "global_step": 408396, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.128427028656006, "global_step": 408397, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0216519832611084, "global_step": 408398, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0138373374938965, "global_step": 408399, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1416304111480713, "global_step": 408400, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.09256649017334, "global_step": 408401, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0138678550720215, "global_step": 408402, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.117457628250122, "global_step": 408403, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.9754644632339478, "global_step": 408404, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0890913009643555, "global_step": 408405, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1342556476593018, "global_step": 408406, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0686607360839844, "global_step": 408407, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.14044189453125, "global_step": 408408, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.097707509994507, "global_step": 408409, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0500004291534424, "global_step": 408410, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.2040772438049316, "global_step": 408411, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.070779323577881, "global_step": 408412, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0817556381225586, "global_step": 408413, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.050546407699585, "global_step": 408414, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1672794818878174, "global_step": 408415, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0384178161621094, "global_step": 408416, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.108710289001465, "global_step": 408417, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.063626527786255, "global_step": 408418, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.118114709854126, "global_step": 408419, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1364967823028564, "global_step": 408420, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.147883892059326, "global_step": 408421, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.021836519241333, "global_step": 408422, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.052980899810791, "global_step": 408423, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.125337600708008, "global_step": 408424, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0856738090515137, "global_step": 408425, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.087724208831787, "global_step": 408426, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.012155294418335, "global_step": 408427, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.097123146057129, "global_step": 408428, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.106050491333008, "global_step": 408429, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0380232334136963, "global_step": 408430, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0054445266723633, "global_step": 408431, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.106863260269165, "global_step": 408432, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0458731651306152, "global_step": 408433, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1098814010620117, "global_step": 408434, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1575396060943604, "global_step": 408435, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0705342292785645, "global_step": 408436, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.9576646089553833, "global_step": 408437, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0964009761810303, "global_step": 408438, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0294742584228516, "global_step": 408439, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1809444427490234, "global_step": 408440, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.059000015258789, "global_step": 408441, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0343470573425293, "global_step": 408442, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1359758377075195, "global_step": 408443, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.126101016998291, "global_step": 408444, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0915603637695312, "global_step": 408445, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.080173969268799, "global_step": 408446, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0652499198913574, "global_step": 408447, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.115062713623047, "global_step": 408448, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.236661195755005, "global_step": 408449, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0721490383148193, "global_step": 408450, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0624899864196777, "global_step": 408451, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0517258644104004, "global_step": 408452, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1822268962860107, "global_step": 408453, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0615315437316895, "global_step": 408454, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.057441234588623, "global_step": 408455, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0360963344573975, "global_step": 408456, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.139449119567871, "global_step": 408457, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0643796920776367, "global_step": 408458, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0890586376190186, "global_step": 408459, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.125847101211548, "global_step": 408460, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.138908863067627, "global_step": 408461, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.108125686645508, "global_step": 408462, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.024219036102295, "global_step": 408463, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0823800563812256, "global_step": 408464, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.048264980316162, "global_step": 408465, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.065795660018921, "global_step": 408466, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0958001613616943, "global_step": 408467, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0783190727233887, "global_step": 408468, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.9973275661468506, "global_step": 408469, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0005075931549072, "global_step": 408470, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1169824600219727, "global_step": 408471, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.104403257369995, "global_step": 408472, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0662636756896973, "global_step": 408473, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.097733974456787, "global_step": 408474, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1116256713867188, "global_step": 408475, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0424163341522217, "global_step": 408476, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.034076452255249, "global_step": 408477, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1201231479644775, "global_step": 408478, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1071887016296387, "global_step": 408479, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0515382289886475, "global_step": 408480, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.134925127029419, "global_step": 408481, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0533173084259033, "global_step": 408482, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.101918935775757, "global_step": 408483, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.15511417388916, "global_step": 408484, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0251002311706543, "global_step": 408485, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1313424110412598, "global_step": 408486, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0957624912261963, "global_step": 408487, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0957493782043457, "global_step": 408488, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.070035696029663, "global_step": 408489, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0993809700012207, "global_step": 408490, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1749517917633057, "global_step": 408491, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0283117294311523, "global_step": 408492, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.119044780731201, "global_step": 408493, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.036874294281006, "global_step": 408494, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1175484657287598, "global_step": 408495, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.079042673110962, "global_step": 408496, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0839951038360596, "global_step": 408497, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.075843334197998, "global_step": 408498, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0556066036224365, "global_step": 408499, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.078413248062134, "global_step": 408500, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0581650733947754, "global_step": 408501, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.119255542755127, "global_step": 408502, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1609511375427246, "global_step": 408503, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.060185432434082, "global_step": 408504, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.9869881868362427, "global_step": 408505, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.071687936782837, "global_step": 408506, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.9987883567810059, "global_step": 408507, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1171703338623047, "global_step": 408508, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.122765302658081, "global_step": 408509, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0388200283050537, "global_step": 408510, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0424904823303223, "global_step": 408511, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.119460105895996, "global_step": 408512, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.068709135055542, "global_step": 408513, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0724244117736816, "global_step": 408514, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.091562509536743, "global_step": 408515, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1338517665863037, "global_step": 408516, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0600481033325195, "global_step": 408517, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.144162654876709, "global_step": 408518, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.085472583770752, "global_step": 408519, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.042520761489868, "global_step": 408520, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.075042247772217, "global_step": 408521, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.097970962524414, "global_step": 408522, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.121530055999756, "global_step": 408523, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0584170818328857, "global_step": 408524, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0167276859283447, "global_step": 408525, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.054375171661377, "global_step": 408526, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.041388750076294, "global_step": 408527, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1097605228424072, "global_step": 408528, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1987879276275635, "global_step": 408529, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0910465717315674, "global_step": 408530, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.102905750274658, "global_step": 408531, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.051786184310913, "global_step": 408532, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1869988441467285, "global_step": 408533, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0832066535949707, "global_step": 408534, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.055110454559326, "global_step": 408535, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.099855422973633, "global_step": 408536, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1004526615142822, "global_step": 408537, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0277256965637207, "global_step": 408538, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1123554706573486, "global_step": 408539, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.080190896987915, "global_step": 408540, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0792367458343506, "global_step": 408541, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.062830686569214, "global_step": 408542, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.134643316268921, "global_step": 408543, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1093924045562744, "global_step": 408544, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.043440341949463, "global_step": 408545, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.069342851638794, "global_step": 408546, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.190328598022461, "global_step": 408547, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0256433486938477, "global_step": 408548, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.038043737411499, "global_step": 408549, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1256206035614014, "global_step": 408550, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.039942741394043, "global_step": 408551, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.049877405166626, "global_step": 408552, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0293564796447754, "global_step": 408553, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0753986835479736, "global_step": 408554, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0236692428588867, "global_step": 408555, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0897116661071777, "global_step": 408556, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1271090507507324, "global_step": 408557, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.129791021347046, "global_step": 408558, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.080479145050049, "global_step": 408559, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0690908432006836, "global_step": 408560, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0668694972991943, "global_step": 408561, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.065812110900879, "global_step": 408562, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0528616905212402, "global_step": 408563, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0874857902526855, "global_step": 408564, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.042140483856201, "global_step": 408565, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.033756732940674, "global_step": 408566, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0968809127807617, "global_step": 408567, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1620841026306152, "global_step": 408568, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.026217460632324, "global_step": 408569, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.030872344970703, "global_step": 408570, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.067758560180664, "global_step": 408571, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0964860916137695, "global_step": 408572, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0732643604278564, "global_step": 408573, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1372385025024414, "global_step": 408574, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.126326084136963, "global_step": 408575, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0715253353118896, "global_step": 408576, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1601076126098633, "global_step": 408577, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.2099597454071045, "global_step": 408578, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1413652896881104, "global_step": 408579, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.08959698677063, "global_step": 408580, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.060255289077759, "global_step": 408581, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.225294351577759, "global_step": 408582, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0361461639404297, "global_step": 408583, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0909574031829834, "global_step": 408584, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.029327869415283, "global_step": 408585, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0248444080352783, "global_step": 408586, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1252310276031494, "global_step": 408587, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0780231952667236, "global_step": 408588, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.117496967315674, "global_step": 408589, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0395398139953613, "global_step": 408590, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0688822269439697, "global_step": 408591, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.093590259552002, "global_step": 408592, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.051156520843506, "global_step": 408593, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.144871234893799, "global_step": 408594, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.167801856994629, "global_step": 408595, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1245980262756348, "global_step": 408596, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1212291717529297, "global_step": 408597, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0973682403564453, "global_step": 408598, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.178313732147217, "global_step": 408599, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1186790466308594, "global_step": 408600, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.123667001724243, "global_step": 408601, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.2123069763183594, "global_step": 408602, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.102262496948242, "global_step": 408603, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.098611831665039, "global_step": 408604, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.154696226119995, "global_step": 408605, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1422317028045654, "global_step": 408606, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.9991191625595093, "global_step": 408607, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1051337718963623, "global_step": 408608, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0737719535827637, "global_step": 408609, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0439302921295166, "global_step": 408610, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.085582971572876, "global_step": 408611, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.12408185005188, "global_step": 408612, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.090056896209717, "global_step": 408613, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1137168407440186, "global_step": 408614, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0822267532348633, "global_step": 408615, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1167004108428955, "global_step": 408616, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1424293518066406, "global_step": 408617, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.085651159286499, "global_step": 408618, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1590423583984375, "global_step": 408619, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.154290199279785, "global_step": 408620, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0646562576293945, "global_step": 408621, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.105548858642578, "global_step": 408622, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.9856675863265991, "global_step": 408623, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.06187105178833, "global_step": 408624, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1002254486083984, "global_step": 408625, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1416091918945312, "global_step": 408626, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.021984577178955, "global_step": 408627, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.219520092010498, "global_step": 408628, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.100140333175659, "global_step": 408629, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.126976490020752, "global_step": 408630, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1170809268951416, "global_step": 408631, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.016080141067505, "global_step": 408632, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.046665668487549, "global_step": 408633, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.120887517929077, "global_step": 408634, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1541354656219482, "global_step": 408635, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1681299209594727, "global_step": 408636, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.072324752807617, "global_step": 408637, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.026918888092041, "global_step": 408638, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1496191024780273, "global_step": 408639, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.07364559173584, "global_step": 408640, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0459728240966797, "global_step": 408641, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0794031620025635, "global_step": 408642, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.032320976257324, "global_step": 408643, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0177628993988037, "global_step": 408644, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.105404853820801, "global_step": 408645, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1331920623779297, "global_step": 408646, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0385608673095703, "global_step": 408647, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.065518856048584, "global_step": 408648, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.123465061187744, "global_step": 408649, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.049208164215088, "global_step": 408650, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0286946296691895, "global_step": 408651, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1186270713806152, "global_step": 408652, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.019322395324707, "global_step": 408653, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.161548614501953, "global_step": 408654, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.017972469329834, "global_step": 408655, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0511882305145264, "global_step": 408656, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.164229393005371, "global_step": 408657, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1475985050201416, "global_step": 408658, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1379387378692627, "global_step": 408659, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.073255777359009, "global_step": 408660, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1211321353912354, "global_step": 408661, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.095242738723755, "global_step": 408662, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.020674705505371, "global_step": 408663, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0496487617492676, "global_step": 408664, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.042712450027466, "global_step": 408665, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1564810276031494, "global_step": 408666, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1170494556427, "global_step": 408667, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.004990577697754, "global_step": 408668, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.092700242996216, "global_step": 408669, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1180193424224854, "global_step": 408670, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0641720294952393, "global_step": 408671, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.173640251159668, "global_step": 408672, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.073272705078125, "global_step": 408673, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.131955146789551, "global_step": 408674, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1393373012542725, "global_step": 408675, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.077099084854126, "global_step": 408676, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0637075901031494, "global_step": 408677, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1848316192626953, "global_step": 408678, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.060788154602051, "global_step": 408679, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0981733798980713, "global_step": 408680, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.031482458114624, "global_step": 408681, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.076613187789917, "global_step": 408682, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1178669929504395, "global_step": 408683, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1890907287597656, "global_step": 408684, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.058966875076294, "global_step": 408685, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0728161334991455, "global_step": 408686, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.121624231338501, "global_step": 408687, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1338694095611572, "global_step": 408688, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1124517917633057, "global_step": 408689, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.9806787967681885, "global_step": 408690, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.086479902267456, "global_step": 408691, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.114156723022461, "global_step": 408692, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0740902423858643, "global_step": 408693, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1390879154205322, "global_step": 408694, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1247572898864746, "global_step": 408695, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.081610679626465, "global_step": 408696, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.076817035675049, "global_step": 408697, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.157994270324707, "global_step": 408698, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.180605411529541, "global_step": 408699, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0218324661254883, "global_step": 408700, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.033271074295044, "global_step": 408701, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0361831188201904, "global_step": 408702, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0979671478271484, "global_step": 408703, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1156976222991943, "global_step": 408704, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.17954158782959, "global_step": 408705, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.165073871612549, "global_step": 408706, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.011155366897583, "global_step": 408707, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1633217334747314, "global_step": 408708, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.138742446899414, "global_step": 408709, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.072075366973877, "global_step": 408710, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.151639461517334, "global_step": 408711, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.186087131500244, "global_step": 408712, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.012634515762329, "global_step": 408713, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.065739870071411, "global_step": 408714, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.104384660720825, "global_step": 408715, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.019042730331421, "global_step": 408716, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.112351894378662, "global_step": 408717, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0649447441101074, "global_step": 408718, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.166520118713379, "global_step": 408719, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1220927238464355, "global_step": 408720, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.078202962875366, "global_step": 408721, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0091872215270996, "global_step": 408722, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0275707244873047, "global_step": 408723, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0808002948760986, "global_step": 408724, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.052389621734619, "global_step": 408725, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0244710445404053, "global_step": 408726, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.097698926925659, "global_step": 408727, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0739364624023438, "global_step": 408728, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0996639728546143, "global_step": 408729, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.072197437286377, "global_step": 408730, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0447325706481934, "global_step": 408731, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.14229679107666, "global_step": 408732, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0593855381011963, "global_step": 408733, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1371188163757324, "global_step": 408734, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1116480827331543, "global_step": 408735, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.063796043395996, "global_step": 408736, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.098405122756958, "global_step": 408737, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1176199913024902, "global_step": 408738, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1429734230041504, "global_step": 408739, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0997002124786377, "global_step": 408740, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0856642723083496, "global_step": 408741, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.108057975769043, "global_step": 408742, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0886950492858887, "global_step": 408743, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0795645713806152, "global_step": 408744, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.061777353286743, "global_step": 408745, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.109673500061035, "global_step": 408746, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.2042038440704346, "global_step": 408747, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.2104194164276123, "global_step": 408748, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1370468139648438, "global_step": 408749, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1206865310668945, "global_step": 408750, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.107382297515869, "global_step": 408751, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.088088035583496, "global_step": 408752, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.124188184738159, "global_step": 408753, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.060802936553955, "global_step": 408754, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.028157949447632, "global_step": 408755, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.973436951637268, "global_step": 408756, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.060708522796631, "global_step": 408757, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.043644428253174, "global_step": 408758, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1237807273864746, "global_step": 408759, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.995198130607605, "global_step": 408760, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1313319206237793, "global_step": 408761, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1355230808258057, "global_step": 408762, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0475707054138184, "global_step": 408763, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0977823734283447, "global_step": 408764, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.114354133605957, "global_step": 408765, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1699745655059814, "global_step": 408766, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.141038417816162, "global_step": 408767, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.10799241065979, "global_step": 408768, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0941076278686523, "global_step": 408769, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.09781551361084, "global_step": 408770, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0867648124694824, "global_step": 408771, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0948922634124756, "global_step": 408772, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.125627040863037, "global_step": 408773, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0457634925842285, "global_step": 408774, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0303127765655518, "global_step": 408775, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.110319137573242, "global_step": 408776, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.055359125137329, "global_step": 408777, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.054837465286255, "global_step": 408778, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1156914234161377, "global_step": 408779, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0870816707611084, "global_step": 408780, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.026092767715454, "global_step": 408781, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.053959846496582, "global_step": 408782, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1097238063812256, "global_step": 408783, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.164191722869873, "global_step": 408784, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.20859694480896, "global_step": 408785, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1249516010284424, "global_step": 408786, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1613681316375732, "global_step": 408787, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.109666347503662, "global_step": 408788, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1193959712982178, "global_step": 408789, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0928828716278076, "global_step": 408790, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1051111221313477, "global_step": 408791, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.2181928157806396, "global_step": 408792, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0628437995910645, "global_step": 408793, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1199896335601807, "global_step": 408794, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1598215103149414, "global_step": 408795, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1096808910369873, "global_step": 408796, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0068612098693848, "global_step": 408797, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.066300868988037, "global_step": 408798, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.078035354614258, "global_step": 408799, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.007721185684204, "global_step": 408800, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.101165771484375, "global_step": 408801, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0341999530792236, "global_step": 408802, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0052874088287354, "global_step": 408803, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1101953983306885, "global_step": 408804, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.12917423248291, "global_step": 408805, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.004988670349121, "global_step": 408806, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0971052646636963, "global_step": 408807, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.105656623840332, "global_step": 408808, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.147976875305176, "global_step": 408809, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.045870542526245, "global_step": 408810, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.128736972808838, "global_step": 408811, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0958969593048096, "global_step": 408812, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0734658241271973, "global_step": 408813, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1130051612854004, "global_step": 408814, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.036794424057007, "global_step": 408815, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.076948642730713, "global_step": 408816, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.193873405456543, "global_step": 408817, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.063431739807129, "global_step": 408818, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1223366260528564, "global_step": 408819, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.2030069828033447, "global_step": 408820, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.154934883117676, "global_step": 408821, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.069639205932617, "global_step": 408822, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0862252712249756, "global_step": 408823, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.051009178161621, "global_step": 408824, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.150888681411743, "global_step": 408825, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0922770500183105, "global_step": 408826, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.130293369293213, "global_step": 408827, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0797104835510254, "global_step": 408828, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.083003282546997, "global_step": 408829, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1134769916534424, "global_step": 408830, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.07738995552063, "global_step": 408831, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.100968837738037, "global_step": 408832, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.033216953277588, "global_step": 408833, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.083085060119629, "global_step": 408834, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.110215187072754, "global_step": 408835, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.042228937149048, "global_step": 408836, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0878756046295166, "global_step": 408837, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.054654121398926, "global_step": 408838, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.051142930984497, "global_step": 408839, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.084625005722046, "global_step": 408840, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.053072452545166, "global_step": 408841, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.182751417160034, "global_step": 408842, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.069340705871582, "global_step": 408843, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.2007293701171875, "global_step": 408844, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1112513542175293, "global_step": 408845, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1549713611602783, "global_step": 408846, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1751184463500977, "global_step": 408847, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0402066707611084, "global_step": 408848, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.052196502685547, "global_step": 408849, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0538792610168457, "global_step": 408850, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1088593006134033, "global_step": 408851, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0577151775360107, "global_step": 408852, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.118119239807129, "global_step": 408853, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.109158754348755, "global_step": 408854, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.079904556274414, "global_step": 408855, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.127257823944092, "global_step": 408856, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.084472179412842, "global_step": 408857, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.103335380554199, "global_step": 408858, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.122882127761841, "global_step": 408859, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0676562786102295, "global_step": 408860, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0634920597076416, "global_step": 408861, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1358909606933594, "global_step": 408862, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0565543174743652, "global_step": 408863, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.094291925430298, "global_step": 408864, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1001923084259033, "global_step": 408865, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1082723140716553, "global_step": 408866, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1048834323883057, "global_step": 408867, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0742249488830566, "global_step": 408868, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.089932441711426, "global_step": 408869, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0443949699401855, "global_step": 408870, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1090540885925293, "global_step": 408871, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.042494058609009, "global_step": 408872, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.9799474477767944, "global_step": 408873, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0254766941070557, "global_step": 408874, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0479719638824463, "global_step": 408875, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1063737869262695, "global_step": 408876, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.074997901916504, "global_step": 408877, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1478264331817627, "global_step": 408878, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.117867946624756, "global_step": 408879, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.087730884552002, "global_step": 408880, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1652276515960693, "global_step": 408881, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1169772148132324, "global_step": 408882, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0893349647521973, "global_step": 408883, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1434569358825684, "global_step": 408884, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.053546190261841, "global_step": 408885, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1164586544036865, "global_step": 408886, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.07547926902771, "global_step": 408887, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.074625015258789, "global_step": 408888, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.132185935974121, "global_step": 408889, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.098626136779785, "global_step": 408890, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0726823806762695, "global_step": 408891, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0283870697021484, "global_step": 408892, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.9776248931884766, "global_step": 408893, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.110461711883545, "global_step": 408894, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0581424236297607, "global_step": 408895, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0869481563568115, "global_step": 408896, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0341687202453613, "global_step": 408897, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1090080738067627, "global_step": 408898, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.151296854019165, "global_step": 408899, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1234395503997803, "global_step": 408900, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0754971504211426, "global_step": 408901, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1125025749206543, "global_step": 408902, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0167744159698486, "global_step": 408903, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0268735885620117, "global_step": 408904, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.152057409286499, "global_step": 408905, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1731746196746826, "global_step": 408906, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1675634384155273, "global_step": 408907, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1518707275390625, "global_step": 408908, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1169230937957764, "global_step": 408909, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.102972984313965, "global_step": 408910, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.105530261993408, "global_step": 408911, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1623294353485107, "global_step": 408912, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0305256843566895, "global_step": 408913, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.147719621658325, "global_step": 408914, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0508792400360107, "global_step": 408915, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.976235032081604, "global_step": 408916, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.068610191345215, "global_step": 408917, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.110095500946045, "global_step": 408918, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.042018413543701, "global_step": 408919, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1587157249450684, "global_step": 408920, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.118988513946533, "global_step": 408921, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0889503955841064, "global_step": 408922, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.071683168411255, "global_step": 408923, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.150812864303589, "global_step": 408924, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.073380470275879, "global_step": 408925, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.081630229949951, "global_step": 408926, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0487172603607178, "global_step": 408927, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.147474765777588, "global_step": 408928, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0583012104034424, "global_step": 408929, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.113036632537842, "global_step": 408930, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0440573692321777, "global_step": 408931, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0752458572387695, "global_step": 408932, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.17291522026062, "global_step": 408933, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.206679582595825, "global_step": 408934, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0623419284820557, "global_step": 408935, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.034428596496582, "global_step": 408936, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.127190113067627, "global_step": 408937, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1365973949432373, "global_step": 408938, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1458914279937744, "global_step": 408939, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0799715518951416, "global_step": 408940, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0834343433380127, "global_step": 408941, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0832784175872803, "global_step": 408942, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.110712766647339, "global_step": 408943, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.10160231590271, "global_step": 408944, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.107985019683838, "global_step": 408945, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.07845401763916, "global_step": 408946, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.118814468383789, "global_step": 408947, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0526204109191895, "global_step": 408948, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0633046627044678, "global_step": 408949, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0467567443847656, "global_step": 408950, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1864054203033447, "global_step": 408951, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.070033550262451, "global_step": 408952, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.038966655731201, "global_step": 408953, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0733258724212646, "global_step": 408954, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.116377115249634, "global_step": 408955, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0535171031951904, "global_step": 408956, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.099621295928955, "global_step": 408957, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0417776107788086, "global_step": 408958, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.195237636566162, "global_step": 408959, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.169060707092285, "global_step": 408960, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0395705699920654, "global_step": 408961, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1430368423461914, "global_step": 408962, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0834407806396484, "global_step": 408963, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0950868129730225, "global_step": 408964, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0069048404693604, "global_step": 408965, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.180135726928711, "global_step": 408966, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1931967735290527, "global_step": 408967, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1500978469848633, "global_step": 408968, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.161754608154297, "global_step": 408969, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.070009231567383, "global_step": 408970, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0901200771331787, "global_step": 408971, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.106004476547241, "global_step": 408972, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.136070489883423, "global_step": 408973, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.069112777709961, "global_step": 408974, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1252477169036865, "global_step": 408975, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0847814083099365, "global_step": 408976, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0511653423309326, "global_step": 408977, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1829440593719482, "global_step": 408978, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1025390625, "global_step": 408979, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.150989532470703, "global_step": 408980, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0990047454833984, "global_step": 408981, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.020315408706665, "global_step": 408982, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1350698471069336, "global_step": 408983, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.190185070037842, "global_step": 408984, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.034409523010254, "global_step": 408985, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.123811960220337, "global_step": 408986, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0596933364868164, "global_step": 408987, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.098470449447632, "global_step": 408988, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.9842380285263062, "global_step": 408989, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.054147720336914, "global_step": 408990, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0288374423980713, "global_step": 408991, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1212425231933594, "global_step": 408992, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0562424659729004, "global_step": 408993, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.097827434539795, "global_step": 408994, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0673298835754395, "global_step": 408995, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0361759662628174, "global_step": 408996, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0996148586273193, "global_step": 408997, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.184504747390747, "global_step": 408998, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0688514709472656, "global_step": 408999, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.044851779937744, "global_step": 409000, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1895406246185303, "global_step": 409001, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.06752610206604, "global_step": 409002, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0493671894073486, "global_step": 409003, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1025052070617676, "global_step": 409004, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0847713947296143, "global_step": 409005, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.155017852783203, "global_step": 409006, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1542701721191406, "global_step": 409007, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.071582317352295, "global_step": 409008, "epoch": 771, "lr": 5e-05}
{"train_loss": 1.9786405563354492, "global_step": 409009, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.059331178665161, "global_step": 409010, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.091989040374756, "global_step": 409011, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.186598539352417, "global_step": 409012, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0140230655670166, "global_step": 409013, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1420156955718994, "global_step": 409014, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1438937187194824, "global_step": 409015, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1187591552734375, "global_step": 409016, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.041616678237915, "global_step": 409017, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.131680727005005, "global_step": 409018, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.067636013031006, "global_step": 409019, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.09499454498291, "global_step": 409020, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.076324462890625, "global_step": 409021, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0893380641937256, "global_step": 409022, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.139732599258423, "global_step": 409023, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.165919303894043, "global_step": 409024, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0844483375549316, "global_step": 409025, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0385665893554688, "global_step": 409026, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0967018604278564, "global_step": 409027, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1919593811035156, "global_step": 409028, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0718884468078613, "global_step": 409029, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0262110233306885, "global_step": 409030, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.057368040084839, "global_step": 409031, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1119110584259033, "global_step": 409032, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.083754539489746, "global_step": 409033, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0474302768707275, "global_step": 409034, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1447842121124268, "global_step": 409035, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.081655502319336, "global_step": 409036, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.126771926879883, "global_step": 409037, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0749216079711914, "global_step": 409038, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0526905059814453, "global_step": 409039, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1400790214538574, "global_step": 409040, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.100968360900879, "global_step": 409041, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.121344804763794, "global_step": 409042, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.091156244277954, "global_step": 409043, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1739776134490967, "global_step": 409044, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1919302940368652, "global_step": 409045, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.147477865219116, "global_step": 409046, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.143522262573242, "global_step": 409047, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1158480644226074, "global_step": 409048, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.1816344261169434, "global_step": 409049, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.092120885848999, "global_step": 409050, "epoch": 771, "lr": 5e-05}
{"train_loss": 2.0484774112701416, "global_step": 409051, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0936439037323, "global_step": 409052, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.136251926422119, "global_step": 409053, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1470706462860107, "global_step": 409054, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.123898983001709, "global_step": 409055, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.034498929977417, "global_step": 409056, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0789692401885986, "global_step": 409057, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1040730476379395, "global_step": 409058, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1428287029266357, "global_step": 409059, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.01381778717041, "global_step": 409060, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9933199882507324, "global_step": 409061, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.066673517227173, "global_step": 409062, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0168282985687256, "global_step": 409063, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1065375804901123, "global_step": 409064, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.100327730178833, "global_step": 409065, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.021644353866577, "global_step": 409066, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9501694440841675, "global_step": 409067, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1170711517333984, "global_step": 409068, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.054399251937866, "global_step": 409069, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.081587076187134, "global_step": 409070, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.2250497341156006, "global_step": 409071, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.053539991378784, "global_step": 409072, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.106051445007324, "global_step": 409073, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.106107234954834, "global_step": 409074, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.050658941268921, "global_step": 409075, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0125064849853516, "global_step": 409076, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1888060569763184, "global_step": 409077, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.133239269256592, "global_step": 409078, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1083858013153076, "global_step": 409079, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.097301483154297, "global_step": 409080, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.082836627960205, "global_step": 409081, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0913703441619873, "global_step": 409082, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.103264093399048, "global_step": 409083, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.128065824508667, "global_step": 409084, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0369114875793457, "global_step": 409085, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.093010902404785, "global_step": 409086, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.037662982940674, "global_step": 409087, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.104905128479004, "global_step": 409088, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0473721027374268, "global_step": 409089, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0399184226989746, "global_step": 409090, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0847482681274414, "global_step": 409091, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.185779333114624, "global_step": 409092, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0746383666992188, "global_step": 409093, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1186280250549316, "global_step": 409094, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0694968700408936, "global_step": 409095, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.036729335784912, "global_step": 409096, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.09442138671875, "global_step": 409097, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1373496055603027, "global_step": 409098, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0527095794677734, "global_step": 409099, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1313815116882324, "global_step": 409100, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0408198833465576, "global_step": 409101, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.127533197402954, "global_step": 409102, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.068331718444824, "global_step": 409103, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.198007345199585, "global_step": 409104, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.098351001739502, "global_step": 409105, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0745811462402344, "global_step": 409106, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0847015380859375, "global_step": 409107, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.10001802444458, "global_step": 409108, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1140024662017822, "global_step": 409109, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0982282161712646, "global_step": 409110, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0759053230285645, "global_step": 409111, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1292762756347656, "global_step": 409112, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0743749141693115, "global_step": 409113, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1937265396118164, "global_step": 409114, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9819958209991455, "global_step": 409115, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1515767574310303, "global_step": 409116, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.053267002105713, "global_step": 409117, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0563790798187256, "global_step": 409118, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1069390773773193, "global_step": 409119, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.067310094833374, "global_step": 409120, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1411666870117188, "global_step": 409121, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1537866592407227, "global_step": 409122, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1423768997192383, "global_step": 409123, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0981881618499756, "global_step": 409124, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1001648902893066, "global_step": 409125, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0772268772125244, "global_step": 409126, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.141997814178467, "global_step": 409127, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1042323112487793, "global_step": 409128, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0201947689056396, "global_step": 409129, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9854100942611694, "global_step": 409130, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.043853521347046, "global_step": 409131, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0484158992767334, "global_step": 409132, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.068730115890503, "global_step": 409133, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.013206958770752, "global_step": 409134, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0684473514556885, "global_step": 409135, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0124950408935547, "global_step": 409136, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.053222417831421, "global_step": 409137, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1116721630096436, "global_step": 409138, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.027111530303955, "global_step": 409139, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.051574230194092, "global_step": 409140, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1088807582855225, "global_step": 409141, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0963358879089355, "global_step": 409142, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0935721397399902, "global_step": 409143, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1046671867370605, "global_step": 409144, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.077582597732544, "global_step": 409145, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9727952480316162, "global_step": 409146, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0088608264923096, "global_step": 409147, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0418405532836914, "global_step": 409148, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0132429599761963, "global_step": 409149, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.07749342918396, "global_step": 409150, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.088228940963745, "global_step": 409151, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0870847702026367, "global_step": 409152, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9870896339416504, "global_step": 409153, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.06439208984375, "global_step": 409154, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.040151596069336, "global_step": 409155, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1228079795837402, "global_step": 409156, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1192073822021484, "global_step": 409157, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1293790340423584, "global_step": 409158, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0384294986724854, "global_step": 409159, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0762836933135986, "global_step": 409160, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0245676040649414, "global_step": 409161, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.156498670578003, "global_step": 409162, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0455148220062256, "global_step": 409163, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0734658241271973, "global_step": 409164, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0348799228668213, "global_step": 409165, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0941827297210693, "global_step": 409166, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1650869846343994, "global_step": 409167, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1715517044067383, "global_step": 409168, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0975844860076904, "global_step": 409169, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.105952501296997, "global_step": 409170, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1036558151245117, "global_step": 409171, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0744199752807617, "global_step": 409172, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.111145257949829, "global_step": 409173, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0272796154022217, "global_step": 409174, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.121210813522339, "global_step": 409175, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.249631643295288, "global_step": 409176, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.106353282928467, "global_step": 409177, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0885848999023438, "global_step": 409178, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0333244800567627, "global_step": 409179, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.146186590194702, "global_step": 409180, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1049089431762695, "global_step": 409181, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1520934104919434, "global_step": 409182, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1311826705932617, "global_step": 409183, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0581634044647217, "global_step": 409184, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.158296585083008, "global_step": 409185, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0815653800964355, "global_step": 409186, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.034092664718628, "global_step": 409187, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.975449800491333, "global_step": 409188, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9620230197906494, "global_step": 409189, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0418636798858643, "global_step": 409190, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1181721687316895, "global_step": 409191, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1152262687683105, "global_step": 409192, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0543859004974365, "global_step": 409193, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.035551071166992, "global_step": 409194, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.046579122543335, "global_step": 409195, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.038525342941284, "global_step": 409196, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1056511402130127, "global_step": 409197, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0688092708587646, "global_step": 409198, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1230533123016357, "global_step": 409199, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0097999572753906, "global_step": 409200, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.082108736038208, "global_step": 409201, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.218280076980591, "global_step": 409202, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.2325825691223145, "global_step": 409203, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.009796619415283, "global_step": 409204, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0920722484588623, "global_step": 409205, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.087491750717163, "global_step": 409206, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.159600019454956, "global_step": 409207, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.006277084350586, "global_step": 409208, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0856940746307373, "global_step": 409209, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1373400688171387, "global_step": 409210, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.182469367980957, "global_step": 409211, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1343536376953125, "global_step": 409212, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0551693439483643, "global_step": 409213, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.082720994949341, "global_step": 409214, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.098911762237549, "global_step": 409215, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1131370067596436, "global_step": 409216, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.087536334991455, "global_step": 409217, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.048295497894287, "global_step": 409218, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9599950313568115, "global_step": 409219, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0895917415618896, "global_step": 409220, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.06502628326416, "global_step": 409221, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1072115898132324, "global_step": 409222, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1742594242095947, "global_step": 409223, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0513341426849365, "global_step": 409224, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.058267116546631, "global_step": 409225, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0783474445343018, "global_step": 409226, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1144959926605225, "global_step": 409227, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9886401891708374, "global_step": 409228, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.123915910720825, "global_step": 409229, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1009933948516846, "global_step": 409230, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.083110809326172, "global_step": 409231, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1969501972198486, "global_step": 409232, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.137566328048706, "global_step": 409233, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.161966323852539, "global_step": 409234, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1330785751342773, "global_step": 409235, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.096665382385254, "global_step": 409236, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1631124019622803, "global_step": 409237, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0646846294403076, "global_step": 409238, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0562331676483154, "global_step": 409239, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0926084518432617, "global_step": 409240, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1040780544281006, "global_step": 409241, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.112363815307617, "global_step": 409242, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1440398693084717, "global_step": 409243, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.046786308288574, "global_step": 409244, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0493807792663574, "global_step": 409245, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.081630229949951, "global_step": 409246, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9670456647872925, "global_step": 409247, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9720277786254883, "global_step": 409248, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.092712163925171, "global_step": 409249, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0665993690490723, "global_step": 409250, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.014441728591919, "global_step": 409251, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.048433780670166, "global_step": 409252, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.127249240875244, "global_step": 409253, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.001608371734619, "global_step": 409254, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.086177349090576, "global_step": 409255, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.063662528991699, "global_step": 409256, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.051353931427002, "global_step": 409257, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1317853927612305, "global_step": 409258, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0904202461242676, "global_step": 409259, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0490782260894775, "global_step": 409260, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0893094539642334, "global_step": 409261, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0247859954833984, "global_step": 409262, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.053915023803711, "global_step": 409263, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1067354679107666, "global_step": 409264, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1017000675201416, "global_step": 409265, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9892337322235107, "global_step": 409266, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.166412353515625, "global_step": 409267, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.191267251968384, "global_step": 409268, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.109372615814209, "global_step": 409269, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1790096759796143, "global_step": 409270, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0507972240448, "global_step": 409271, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9832355976104736, "global_step": 409272, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1366302967071533, "global_step": 409273, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0086617469787598, "global_step": 409274, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.110802173614502, "global_step": 409275, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0167016983032227, "global_step": 409276, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1177096366882324, "global_step": 409277, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.068521499633789, "global_step": 409278, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.033878803253174, "global_step": 409279, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1035099029541016, "global_step": 409280, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.167290687561035, "global_step": 409281, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.076972007751465, "global_step": 409282, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1333694458007812, "global_step": 409283, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.03717303276062, "global_step": 409284, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.120227575302124, "global_step": 409285, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9975241422653198, "global_step": 409286, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.062147617340088, "global_step": 409287, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.099065065383911, "global_step": 409288, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0956807136535645, "global_step": 409289, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.009793519973755, "global_step": 409290, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.051640510559082, "global_step": 409291, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.063337802886963, "global_step": 409292, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0927023887634277, "global_step": 409293, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1072983741760254, "global_step": 409294, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1633996963500977, "global_step": 409295, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.087679624557495, "global_step": 409296, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0930402278900146, "global_step": 409297, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1508734226226807, "global_step": 409298, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.07993221282959, "global_step": 409299, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.149609088897705, "global_step": 409300, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0077855587005615, "global_step": 409301, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.161860227584839, "global_step": 409302, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0503504276275635, "global_step": 409303, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9851078987121582, "global_step": 409304, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.112419843673706, "global_step": 409305, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.180335283279419, "global_step": 409306, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.136641025543213, "global_step": 409307, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.078632116317749, "global_step": 409308, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.078671932220459, "global_step": 409309, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1054317951202393, "global_step": 409310, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.2471375465393066, "global_step": 409311, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.146557092666626, "global_step": 409312, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0709242820739746, "global_step": 409313, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0799560546875, "global_step": 409314, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1058473587036133, "global_step": 409315, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0858051776885986, "global_step": 409316, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1111607551574707, "global_step": 409317, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.155985116958618, "global_step": 409318, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0732944011688232, "global_step": 409319, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9960079193115234, "global_step": 409320, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1193151473999023, "global_step": 409321, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1337125301361084, "global_step": 409322, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0534303188323975, "global_step": 409323, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1412241458892822, "global_step": 409324, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1472370624542236, "global_step": 409325, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1361138820648193, "global_step": 409326, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.034698486328125, "global_step": 409327, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1027655601501465, "global_step": 409328, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1314127445220947, "global_step": 409329, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.012289524078369, "global_step": 409330, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1133787631988525, "global_step": 409331, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1723036766052246, "global_step": 409332, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.994001030921936, "global_step": 409333, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.050576686859131, "global_step": 409334, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0580356121063232, "global_step": 409335, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0608367919921875, "global_step": 409336, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0786678791046143, "global_step": 409337, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.110944986343384, "global_step": 409338, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1218652725219727, "global_step": 409339, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.038517951965332, "global_step": 409340, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1623480319976807, "global_step": 409341, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.071234703063965, "global_step": 409342, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0993282794952393, "global_step": 409343, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.09678316116333, "global_step": 409344, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0426464080810547, "global_step": 409345, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.079571485519409, "global_step": 409346, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1458051204681396, "global_step": 409347, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1844751834869385, "global_step": 409348, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.20477032661438, "global_step": 409349, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.095912218093872, "global_step": 409350, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1819076538085938, "global_step": 409351, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.090625524520874, "global_step": 409352, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1359148025512695, "global_step": 409353, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0867061614990234, "global_step": 409354, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0974154472351074, "global_step": 409355, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1700942516326904, "global_step": 409356, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0879132747650146, "global_step": 409357, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0227408409118652, "global_step": 409358, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1597554683685303, "global_step": 409359, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0671355724334717, "global_step": 409360, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0654923915863037, "global_step": 409361, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.21449875831604, "global_step": 409362, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.130307674407959, "global_step": 409363, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9876090288162231, "global_step": 409364, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1027979850769043, "global_step": 409365, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1123147010803223, "global_step": 409366, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0604214668273926, "global_step": 409367, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1119627952575684, "global_step": 409368, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.04679274559021, "global_step": 409369, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.093520402908325, "global_step": 409370, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.157886028289795, "global_step": 409371, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.147787570953369, "global_step": 409372, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.08879017829895, "global_step": 409373, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.025242328643799, "global_step": 409374, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1090807914733887, "global_step": 409375, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0150411128997803, "global_step": 409376, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1030805110931396, "global_step": 409377, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0733108520507812, "global_step": 409378, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1180331707000732, "global_step": 409379, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0754363536834717, "global_step": 409380, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0654449462890625, "global_step": 409381, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0288262367248535, "global_step": 409382, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0580341815948486, "global_step": 409383, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0447635650634766, "global_step": 409384, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.096358060836792, "global_step": 409385, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.050100803375244, "global_step": 409386, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0838513374328613, "global_step": 409387, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.077261209487915, "global_step": 409388, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0872178077697754, "global_step": 409389, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0380947589874268, "global_step": 409390, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.002254009246826, "global_step": 409391, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1186087131500244, "global_step": 409392, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.111423969268799, "global_step": 409393, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1661291122436523, "global_step": 409394, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0812788009643555, "global_step": 409395, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.062220811843872, "global_step": 409396, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.136178731918335, "global_step": 409397, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.061288833618164, "global_step": 409398, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.130072593688965, "global_step": 409399, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1328485012054443, "global_step": 409400, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.046855926513672, "global_step": 409401, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0131676197052, "global_step": 409402, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1385929584503174, "global_step": 409403, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.139707565307617, "global_step": 409404, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.124547243118286, "global_step": 409405, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1184921264648438, "global_step": 409406, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0407700538635254, "global_step": 409407, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1044740676879883, "global_step": 409408, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.033005952835083, "global_step": 409409, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.112605333328247, "global_step": 409410, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9761929512023926, "global_step": 409411, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0168533325195312, "global_step": 409412, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0533642768859863, "global_step": 409413, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.047882318496704, "global_step": 409414, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.098896026611328, "global_step": 409415, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0293667316436768, "global_step": 409416, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.087721824645996, "global_step": 409417, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1592559814453125, "global_step": 409418, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1486997604370117, "global_step": 409419, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0992534160614014, "global_step": 409420, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.07690167427063, "global_step": 409421, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.027968645095825, "global_step": 409422, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1805856227874756, "global_step": 409423, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1984751224517822, "global_step": 409424, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0785305500030518, "global_step": 409425, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.012570858001709, "global_step": 409426, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1026711463928223, "global_step": 409427, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.127019166946411, "global_step": 409428, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1159660816192627, "global_step": 409429, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1353349685668945, "global_step": 409430, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.035010814666748, "global_step": 409431, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9839342832565308, "global_step": 409432, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.037257432937622, "global_step": 409433, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9932767152786255, "global_step": 409434, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.059081792831421, "global_step": 409435, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.138054370880127, "global_step": 409436, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0559654235839844, "global_step": 409437, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0809264183044434, "global_step": 409438, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.2086844444274902, "global_step": 409439, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1671805381774902, "global_step": 409440, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9644460678100586, "global_step": 409441, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.043259620666504, "global_step": 409442, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1477038860321045, "global_step": 409443, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0881505012512207, "global_step": 409444, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0719916820526123, "global_step": 409445, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.102440357208252, "global_step": 409446, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1143438816070557, "global_step": 409447, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0923869609832764, "global_step": 409448, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.017331600189209, "global_step": 409449, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0518317222595215, "global_step": 409450, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.045529365539551, "global_step": 409451, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.077263355255127, "global_step": 409452, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9383864402770996, "global_step": 409453, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.11224102973938, "global_step": 409454, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0680031776428223, "global_step": 409455, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.11209774017334, "global_step": 409456, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.190582275390625, "global_step": 409457, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.16437029838562, "global_step": 409458, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0368261337280273, "global_step": 409459, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.181124210357666, "global_step": 409460, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0194411277770996, "global_step": 409461, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.102177381515503, "global_step": 409462, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.245894193649292, "global_step": 409463, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.120487689971924, "global_step": 409464, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0936741828918457, "global_step": 409465, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1455678939819336, "global_step": 409466, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1536879539489746, "global_step": 409467, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0966849327087402, "global_step": 409468, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.069033145904541, "global_step": 409469, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.094858169555664, "global_step": 409470, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.153111457824707, "global_step": 409471, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.156409502029419, "global_step": 409472, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1367125511169434, "global_step": 409473, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1554410457611084, "global_step": 409474, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1887526512145996, "global_step": 409475, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.091193199157715, "global_step": 409476, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0515012741088867, "global_step": 409477, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.05358624458313, "global_step": 409478, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1024858951568604, "global_step": 409479, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1472249031066895, "global_step": 409480, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.055485725402832, "global_step": 409481, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1663708686828613, "global_step": 409482, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.097792387008667, "global_step": 409483, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0578229427337646, "global_step": 409484, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1089305877685547, "global_step": 409485, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1093344688415527, "global_step": 409486, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0648980140686035, "global_step": 409487, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0754661560058594, "global_step": 409488, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.066602945327759, "global_step": 409489, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.144718647003174, "global_step": 409490, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0881123542785645, "global_step": 409491, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0618813037872314, "global_step": 409492, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.201479196548462, "global_step": 409493, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.099214792251587, "global_step": 409494, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1050233840942383, "global_step": 409495, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.087329864501953, "global_step": 409496, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0088319778442383, "global_step": 409497, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.133772134780884, "global_step": 409498, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1481189727783203, "global_step": 409499, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0613958835601807, "global_step": 409500, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0407538414001465, "global_step": 409501, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1062207221984863, "global_step": 409502, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.092129707336426, "global_step": 409503, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0401384830474854, "global_step": 409504, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1239869594573975, "global_step": 409505, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0811100006103516, "global_step": 409506, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1282694339752197, "global_step": 409507, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1442084312438965, "global_step": 409508, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9856129884719849, "global_step": 409509, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1138668060302734, "global_step": 409510, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.200120687484741, "global_step": 409511, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.051903247833252, "global_step": 409512, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.054671287536621, "global_step": 409513, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.110736608505249, "global_step": 409514, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0743813514709473, "global_step": 409515, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.066761016845703, "global_step": 409516, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.100142002105713, "global_step": 409517, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0685558319091797, "global_step": 409518, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.139133930206299, "global_step": 409519, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0816633701324463, "global_step": 409520, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0416460037231445, "global_step": 409521, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1181952953338623, "global_step": 409522, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.120377540588379, "global_step": 409523, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1332271099090576, "global_step": 409524, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.023207902908325, "global_step": 409525, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1608786582946777, "global_step": 409526, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0624141693115234, "global_step": 409527, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.163801431655884, "global_step": 409528, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0670599937438965, "global_step": 409529, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.080920457839966, "global_step": 409530, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1131041049957275, "global_step": 409531, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1089799404144287, "global_step": 409532, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1242334842681885, "global_step": 409533, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.215695858001709, "global_step": 409534, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.089627981185913, "global_step": 409535, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1328015327453613, "global_step": 409536, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.059494733810425, "global_step": 409537, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.089677333831787, "global_step": 409538, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0509121417999268, "global_step": 409539, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9931141138076782, "global_step": 409540, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1249783039093018, "global_step": 409541, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.049767255783081, "global_step": 409542, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0043721199035645, "global_step": 409543, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0772407054901123, "global_step": 409544, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0797488689422607, "global_step": 409545, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0949389934539795, "global_step": 409546, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0179946422576904, "global_step": 409547, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1482391357421875, "global_step": 409548, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0849599838256836, "global_step": 409549, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0392043590545654, "global_step": 409550, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.166149139404297, "global_step": 409551, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9941833019256592, "global_step": 409552, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1114072799682617, "global_step": 409553, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0879437923431396, "global_step": 409554, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.20434308052063, "global_step": 409555, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1698405742645264, "global_step": 409556, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1088674068450928, "global_step": 409557, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.074237108230591, "global_step": 409558, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.138909101486206, "global_step": 409559, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1493427753448486, "global_step": 409560, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.08807110786438, "global_step": 409561, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0704421997070312, "global_step": 409562, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1239614486694336, "global_step": 409563, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.144669532775879, "global_step": 409564, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.12526535987854, "global_step": 409565, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.013697862625122, "global_step": 409566, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.2258362770080566, "global_step": 409567, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.133216142654419, "global_step": 409568, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.108510971069336, "global_step": 409569, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.074019193649292, "global_step": 409570, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0185022354125977, "global_step": 409571, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.049124240875244, "global_step": 409572, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0656094551086426, "global_step": 409573, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0736093521118164, "global_step": 409574, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.100071907043457, "global_step": 409575, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1066226959228516, "global_step": 409576, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.066431760787964, "global_step": 409577, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1122324466705322, "global_step": 409578, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0417420864105225, "global_step": 409579, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.127624750137329, "global_step": 409580, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.067209243774414, "global_step": 409581, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0562403202056885, "global_step": 409582, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0903656482696533, "global_step": 409583, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0848448276519775, "global_step": 409584, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0925841331481934, "global_step": 409585, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0610649585723877, "global_step": 409586, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0120956897735596, "global_step": 409587, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.039203643798828, "global_step": 409588, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.073850154876709, "global_step": 409589, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0410094261169434, "global_step": 409590, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0105390548706055, "global_step": 409591, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.172646999359131, "global_step": 409592, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1158998012542725, "global_step": 409593, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.103975772857666, "global_step": 409594, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0656323432922363, "global_step": 409595, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.145078420639038, "global_step": 409596, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0124382972717285, "global_step": 409597, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1127967834472656, "global_step": 409598, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.018925189971924, "global_step": 409599, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0720057487487793, "global_step": 409600, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.180358648300171, "global_step": 409601, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1800217628479004, "global_step": 409602, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1955597400665283, "global_step": 409603, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.068436861038208, "global_step": 409604, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.049015998840332, "global_step": 409605, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.131882667541504, "global_step": 409606, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0298378467559814, "global_step": 409607, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.079434871673584, "global_step": 409608, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.127117395401001, "global_step": 409609, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0464072227478027, "global_step": 409610, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1508615016937256, "global_step": 409611, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1658573150634766, "global_step": 409612, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1014153957366943, "global_step": 409613, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0916926860809326, "global_step": 409614, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1011619567871094, "global_step": 409615, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0842487812042236, "global_step": 409616, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1653101444244385, "global_step": 409617, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1377012729644775, "global_step": 409618, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.06404709815979, "global_step": 409619, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.144904613494873, "global_step": 409620, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0678458213806152, "global_step": 409621, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.046130418777466, "global_step": 409622, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1981594562530518, "global_step": 409623, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1262593269348145, "global_step": 409624, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.088979959487915, "global_step": 409625, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0428497791290283, "global_step": 409626, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0455825328826904, "global_step": 409627, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.108170747756958, "global_step": 409628, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.134720802307129, "global_step": 409629, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.027862071990967, "global_step": 409630, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.09995698928833, "global_step": 409631, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0552139282226562, "global_step": 409632, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.09531569480896, "global_step": 409633, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.115021228790283, "global_step": 409634, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1036922931671143, "global_step": 409635, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.073110342025757, "global_step": 409636, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.16172194480896, "global_step": 409637, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0154411792755127, "global_step": 409638, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1885523796081543, "global_step": 409639, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0276968479156494, "global_step": 409640, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.03003191947937, "global_step": 409641, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.05601167678833, "global_step": 409642, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0411171913146973, "global_step": 409643, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0597822666168213, "global_step": 409644, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.105543851852417, "global_step": 409645, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0779762268066406, "global_step": 409646, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.109311819076538, "global_step": 409647, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.163187026977539, "global_step": 409648, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1104397773742676, "global_step": 409649, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0527045726776123, "global_step": 409650, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.104522943496704, "global_step": 409651, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0589041709899902, "global_step": 409652, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0218162536621094, "global_step": 409653, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.135448694229126, "global_step": 409654, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.095038414001465, "global_step": 409655, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.068169593811035, "global_step": 409656, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1062982082366943, "global_step": 409657, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.003004312515259, "global_step": 409658, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1163766384124756, "global_step": 409659, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0864925384521484, "global_step": 409660, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1499955654144287, "global_step": 409661, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.143127679824829, "global_step": 409662, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.161055088043213, "global_step": 409663, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.138359546661377, "global_step": 409664, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0673298835754395, "global_step": 409665, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0470170974731445, "global_step": 409666, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.084437847137451, "global_step": 409667, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.130004405975342, "global_step": 409668, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0552306175231934, "global_step": 409669, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0430715084075928, "global_step": 409670, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0596508979797363, "global_step": 409671, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0907628536224365, "global_step": 409672, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.051981210708618, "global_step": 409673, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.070056438446045, "global_step": 409674, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1084635257720947, "global_step": 409675, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0684585571289062, "global_step": 409676, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1531238555908203, "global_step": 409677, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1943769454956055, "global_step": 409678, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.067070245742798, "global_step": 409679, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.057382822036743, "global_step": 409680, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1488943099975586, "global_step": 409681, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.070314407348633, "global_step": 409682, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.064042091369629, "global_step": 409683, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.130439281463623, "global_step": 409684, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.2301697731018066, "global_step": 409685, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0472710132598877, "global_step": 409686, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1444811820983887, "global_step": 409687, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.090618371963501, "global_step": 409688, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.122079610824585, "global_step": 409689, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0832910537719727, "global_step": 409690, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0670087337493896, "global_step": 409691, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.180723190307617, "global_step": 409692, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0795326232910156, "global_step": 409693, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.034231424331665, "global_step": 409694, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.111816883087158, "global_step": 409695, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1139676570892334, "global_step": 409696, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.11907958984375, "global_step": 409697, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.03157377243042, "global_step": 409698, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0019445419311523, "global_step": 409699, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.2378995418548584, "global_step": 409700, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.060255527496338, "global_step": 409701, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1242759227752686, "global_step": 409702, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9776328802108765, "global_step": 409703, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1227524280548096, "global_step": 409704, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.099893093109131, "global_step": 409705, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0357003211975098, "global_step": 409706, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.118943691253662, "global_step": 409707, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0809812545776367, "global_step": 409708, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.046128988265991, "global_step": 409709, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0808968544006348, "global_step": 409710, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.099160671234131, "global_step": 409711, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0620341300964355, "global_step": 409712, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.997340202331543, "global_step": 409713, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.144679069519043, "global_step": 409714, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.121279716491699, "global_step": 409715, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0458600521087646, "global_step": 409716, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.036212682723999, "global_step": 409717, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.174673080444336, "global_step": 409718, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.161090850830078, "global_step": 409719, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1193509101867676, "global_step": 409720, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.176351547241211, "global_step": 409721, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.131070852279663, "global_step": 409722, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.110673666000366, "global_step": 409723, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.136579990386963, "global_step": 409724, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.012809991836548, "global_step": 409725, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.128047227859497, "global_step": 409726, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.161900043487549, "global_step": 409727, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.083073616027832, "global_step": 409728, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1383888721466064, "global_step": 409729, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.044569492340088, "global_step": 409730, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0946285724639893, "global_step": 409731, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0670619010925293, "global_step": 409732, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.079230546951294, "global_step": 409733, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1427836418151855, "global_step": 409734, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.149669885635376, "global_step": 409735, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1280534267425537, "global_step": 409736, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9917234182357788, "global_step": 409737, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0585174560546875, "global_step": 409738, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0252978801727295, "global_step": 409739, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.090596914291382, "global_step": 409740, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.122875452041626, "global_step": 409741, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.094353199005127, "global_step": 409742, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.075171709060669, "global_step": 409743, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.091390371322632, "global_step": 409744, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1178083419799805, "global_step": 409745, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1232333183288574, "global_step": 409746, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.212026596069336, "global_step": 409747, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1799097061157227, "global_step": 409748, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0659103393554688, "global_step": 409749, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0770263671875, "global_step": 409750, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1014184951782227, "global_step": 409751, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.07718825340271, "global_step": 409752, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1227307319641113, "global_step": 409753, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1239538192749023, "global_step": 409754, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0812885761260986, "global_step": 409755, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0845704078674316, "global_step": 409756, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0642404556274414, "global_step": 409757, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1493327617645264, "global_step": 409758, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1785595417022705, "global_step": 409759, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.084480047225952, "global_step": 409760, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.101357936859131, "global_step": 409761, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.160896062850952, "global_step": 409762, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0342764854431152, "global_step": 409763, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1810619831085205, "global_step": 409764, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0352280139923096, "global_step": 409765, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0989115238189697, "global_step": 409766, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1890382766723633, "global_step": 409767, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1103553771972656, "global_step": 409768, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0760791301727295, "global_step": 409769, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1552369594573975, "global_step": 409770, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.069565534591675, "global_step": 409771, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.123525619506836, "global_step": 409772, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1177470684051514, "global_step": 409773, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1021575927734375, "global_step": 409774, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0893170833587646, "global_step": 409775, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.2445452213287354, "global_step": 409776, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1451938152313232, "global_step": 409777, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9820677042007446, "global_step": 409778, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.083606004714966, "global_step": 409779, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0768346786499023, "global_step": 409780, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0442984104156494, "global_step": 409781, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0995092391967773, "global_step": 409782, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.084203004837036, "global_step": 409783, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.104851245880127, "global_step": 409784, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1011807918548584, "global_step": 409785, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1045284271240234, "global_step": 409786, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9858982563018799, "global_step": 409787, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.194077968597412, "global_step": 409788, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.080523729324341, "global_step": 409789, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.097318172454834, "global_step": 409790, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0851428508758545, "global_step": 409791, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.078953266143799, "global_step": 409792, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.084555149078369, "global_step": 409793, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.032459259033203, "global_step": 409794, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1069533824920654, "global_step": 409795, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1249306201934814, "global_step": 409796, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.124511241912842, "global_step": 409797, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.089496374130249, "global_step": 409798, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1779251098632812, "global_step": 409799, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.058859348297119, "global_step": 409800, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0371594429016113, "global_step": 409801, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.127765655517578, "global_step": 409802, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.060326337814331, "global_step": 409803, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.082282781600952, "global_step": 409804, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1116700172424316, "global_step": 409805, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.086522102355957, "global_step": 409806, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.145768880844116, "global_step": 409807, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0649631023406982, "global_step": 409808, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.051405906677246, "global_step": 409809, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0319290161132812, "global_step": 409810, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.086822748184204, "global_step": 409811, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1130707263946533, "global_step": 409812, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.074427604675293, "global_step": 409813, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9744868278503418, "global_step": 409814, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.099041700363159, "global_step": 409815, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.064289093017578, "global_step": 409816, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1155166625976562, "global_step": 409817, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1094958782196045, "global_step": 409818, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0653624534606934, "global_step": 409819, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0695078372955322, "global_step": 409820, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.118372678756714, "global_step": 409821, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.07119083404541, "global_step": 409822, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1273577213287354, "global_step": 409823, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0384016036987305, "global_step": 409824, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.10774564743042, "global_step": 409825, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1126184463500977, "global_step": 409826, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.164346933364868, "global_step": 409827, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.069331645965576, "global_step": 409828, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0290799140930176, "global_step": 409829, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1207947731018066, "global_step": 409830, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.075653076171875, "global_step": 409831, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.06374192237854, "global_step": 409832, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1372010707855225, "global_step": 409833, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1056647300720215, "global_step": 409834, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.112650156021118, "global_step": 409835, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9534308910369873, "global_step": 409836, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0734975337982178, "global_step": 409837, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0249531269073486, "global_step": 409838, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.088538646697998, "global_step": 409839, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.126457452774048, "global_step": 409840, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0513744354248047, "global_step": 409841, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0380427837371826, "global_step": 409842, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.123990058898926, "global_step": 409843, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.085357189178467, "global_step": 409844, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0748753547668457, "global_step": 409845, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9802368879318237, "global_step": 409846, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0505642890930176, "global_step": 409847, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.140425205230713, "global_step": 409848, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.034548759460449, "global_step": 409849, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.067460775375366, "global_step": 409850, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.079404592514038, "global_step": 409851, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.059729814529419, "global_step": 409852, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0807712078094482, "global_step": 409853, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.085785388946533, "global_step": 409854, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.059912919998169, "global_step": 409855, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.065885066986084, "global_step": 409856, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.151952028274536, "global_step": 409857, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.13069224357605, "global_step": 409858, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1567201614379883, "global_step": 409859, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0977401733398438, "global_step": 409860, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1220123767852783, "global_step": 409861, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.047396421432495, "global_step": 409862, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0314793586730957, "global_step": 409863, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0860092639923096, "global_step": 409864, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0484416484832764, "global_step": 409865, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.101166248321533, "global_step": 409866, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0319454669952393, "global_step": 409867, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0565168857574463, "global_step": 409868, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.100370407104492, "global_step": 409869, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1039366722106934, "global_step": 409870, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.144453763961792, "global_step": 409871, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1347968578338623, "global_step": 409872, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.165905237197876, "global_step": 409873, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1603682041168213, "global_step": 409874, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.049149751663208, "global_step": 409875, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0276150703430176, "global_step": 409876, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1245837211608887, "global_step": 409877, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0893378257751465, "global_step": 409878, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0986952781677246, "global_step": 409879, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9888299703598022, "global_step": 409880, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.089067220687866, "global_step": 409881, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0822806358337402, "global_step": 409882, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1387710571289062, "global_step": 409883, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.107886791229248, "global_step": 409884, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.120983123779297, "global_step": 409885, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9886865615844727, "global_step": 409886, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.096390724182129, "global_step": 409887, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.096074342727661, "global_step": 409888, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1112561225891113, "global_step": 409889, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0578396320343018, "global_step": 409890, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0755057334899902, "global_step": 409891, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1085331439971924, "global_step": 409892, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.091557741165161, "global_step": 409893, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1328229904174805, "global_step": 409894, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1097381114959717, "global_step": 409895, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.136183261871338, "global_step": 409896, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.105262279510498, "global_step": 409897, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0876855850219727, "global_step": 409898, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1450212001800537, "global_step": 409899, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.140817403793335, "global_step": 409900, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0766427516937256, "global_step": 409901, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0835487842559814, "global_step": 409902, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0441997051239014, "global_step": 409903, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0649242401123047, "global_step": 409904, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0338046550750732, "global_step": 409905, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.172002077102661, "global_step": 409906, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0475411415100098, "global_step": 409907, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.049509048461914, "global_step": 409908, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.097062349319458, "global_step": 409909, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1293580532073975, "global_step": 409910, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0380640029907227, "global_step": 409911, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1269352436065674, "global_step": 409912, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.967132329940796, "global_step": 409913, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.151479721069336, "global_step": 409914, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.042980432510376, "global_step": 409915, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.114901065826416, "global_step": 409916, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.062678575515747, "global_step": 409917, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.079333782196045, "global_step": 409918, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1794841289520264, "global_step": 409919, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1156904697418213, "global_step": 409920, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1302554607391357, "global_step": 409921, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.131044387817383, "global_step": 409922, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0926225185394287, "global_step": 409923, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1184942722320557, "global_step": 409924, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0310771465301514, "global_step": 409925, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1477277278900146, "global_step": 409926, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.151176929473877, "global_step": 409927, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.161456346511841, "global_step": 409928, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9990159273147583, "global_step": 409929, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1400556564331055, "global_step": 409930, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.135927677154541, "global_step": 409931, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0925636291503906, "global_step": 409932, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.131969451904297, "global_step": 409933, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9756351709365845, "global_step": 409934, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.114755392074585, "global_step": 409935, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0727858543395996, "global_step": 409936, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.177985191345215, "global_step": 409937, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.152998208999634, "global_step": 409938, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.099439859390259, "global_step": 409939, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.08408260345459, "global_step": 409940, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1071975231170654, "global_step": 409941, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1279802322387695, "global_step": 409942, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.095770835876465, "global_step": 409943, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.164015054702759, "global_step": 409944, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0652458667755127, "global_step": 409945, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1332828998565674, "global_step": 409946, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1096227169036865, "global_step": 409947, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0796713829040527, "global_step": 409948, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0797858238220215, "global_step": 409949, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0862598419189453, "global_step": 409950, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1459603309631348, "global_step": 409951, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1335580348968506, "global_step": 409952, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0991854667663574, "global_step": 409953, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1623494625091553, "global_step": 409954, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0849735736846924, "global_step": 409955, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.150324821472168, "global_step": 409956, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1071975231170654, "global_step": 409957, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.100142002105713, "global_step": 409958, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0877554416656494, "global_step": 409959, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.12196946144104, "global_step": 409960, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0580382347106934, "global_step": 409961, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1149635314941406, "global_step": 409962, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0887205600738525, "global_step": 409963, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0772924423217773, "global_step": 409964, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.058391571044922, "global_step": 409965, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.110935926437378, "global_step": 409966, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1905899047851562, "global_step": 409967, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.057432174682617, "global_step": 409968, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0937421321868896, "global_step": 409969, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0725669860839844, "global_step": 409970, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0651485919952393, "global_step": 409971, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1078145503997803, "global_step": 409972, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0862691402435303, "global_step": 409973, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.051992893218994, "global_step": 409974, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.175704002380371, "global_step": 409975, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0145370960235596, "global_step": 409976, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1393725872039795, "global_step": 409977, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1405370235443115, "global_step": 409978, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.101651668548584, "global_step": 409979, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.070634126663208, "global_step": 409980, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0782179832458496, "global_step": 409981, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.077716112136841, "global_step": 409982, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1796789169311523, "global_step": 409983, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1921820640563965, "global_step": 409984, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1421713829040527, "global_step": 409985, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1515839099884033, "global_step": 409986, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1067070960998535, "global_step": 409987, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.157557964324951, "global_step": 409988, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.047811985015869, "global_step": 409989, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.076826810836792, "global_step": 409990, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.148322820663452, "global_step": 409991, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1102750301361084, "global_step": 409992, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1284923553466797, "global_step": 409993, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.093804359436035, "global_step": 409994, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.140414237976074, "global_step": 409995, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1041922569274902, "global_step": 409996, "epoch": 772, "lr": 5e-05}
{"train_loss": 1.9915605783462524, "global_step": 409997, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1669936180114746, "global_step": 409998, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0863404273986816, "global_step": 409999, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1703333854675293, "global_step": 410000, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.009185791015625, "global_step": 410001, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1098577976226807, "global_step": 410002, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.126297950744629, "global_step": 410003, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1765928268432617, "global_step": 410004, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.101499319076538, "global_step": 410005, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.2056076526641846, "global_step": 410006, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0482099056243896, "global_step": 410007, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.106009006500244, "global_step": 410008, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0316030979156494, "global_step": 410009, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.084808349609375, "global_step": 410010, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.067291736602783, "global_step": 410011, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.091885805130005, "global_step": 410012, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0487990379333496, "global_step": 410013, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0572757720947266, "global_step": 410014, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0544373989105225, "global_step": 410015, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.148754835128784, "global_step": 410016, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.140556812286377, "global_step": 410017, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.0789692401885986, "global_step": 410018, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.092446804046631, "global_step": 410019, "epoch": 772, "lr": 5e-05}
{"train_loss": 2.1301982402801514, "global_step": 410020, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.090526819229126, "global_step": 410021, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1884398460388184, "global_step": 410022, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.090419054031372, "global_step": 410023, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.149960517883301, "global_step": 410024, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.139219284057617, "global_step": 410025, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.051084041595459, "global_step": 410026, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0773723125457764, "global_step": 410027, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0503311157226562, "global_step": 410028, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.175220251083374, "global_step": 410029, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.06903076171875, "global_step": 410030, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9754607677459717, "global_step": 410031, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.104062080383301, "global_step": 410032, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.068209409713745, "global_step": 410033, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1339170932769775, "global_step": 410034, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9854929447174072, "global_step": 410035, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0661158561706543, "global_step": 410036, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0159599781036377, "global_step": 410037, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.2180089950561523, "global_step": 410038, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0534353256225586, "global_step": 410039, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0476367473602295, "global_step": 410040, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1335055828094482, "global_step": 410041, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1304633617401123, "global_step": 410042, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.030296802520752, "global_step": 410043, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.050898551940918, "global_step": 410044, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.114820718765259, "global_step": 410045, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0190296173095703, "global_step": 410046, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0978455543518066, "global_step": 410047, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.126206159591675, "global_step": 410048, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0604162216186523, "global_step": 410049, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.155848979949951, "global_step": 410050, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.170316219329834, "global_step": 410051, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.081498384475708, "global_step": 410052, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1301193237304688, "global_step": 410053, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.058941602706909, "global_step": 410054, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.053140163421631, "global_step": 410055, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0396764278411865, "global_step": 410056, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1738600730895996, "global_step": 410057, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.043930768966675, "global_step": 410058, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.233383893966675, "global_step": 410059, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0371923446655273, "global_step": 410060, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1613242626190186, "global_step": 410061, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9930617809295654, "global_step": 410062, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0984578132629395, "global_step": 410063, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1395225524902344, "global_step": 410064, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.032672166824341, "global_step": 410065, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.146674156188965, "global_step": 410066, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.143094062805176, "global_step": 410067, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0064239501953125, "global_step": 410068, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0779201984405518, "global_step": 410069, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.125915765762329, "global_step": 410070, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1050593852996826, "global_step": 410071, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0930564403533936, "global_step": 410072, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1147382259368896, "global_step": 410073, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1087727546691895, "global_step": 410074, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.126344919204712, "global_step": 410075, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0620102882385254, "global_step": 410076, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0860304832458496, "global_step": 410077, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1290650367736816, "global_step": 410078, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9999301433563232, "global_step": 410079, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0666344165802, "global_step": 410080, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1107177734375, "global_step": 410081, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1277270317077637, "global_step": 410082, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.096318483352661, "global_step": 410083, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0898334980010986, "global_step": 410084, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.121027708053589, "global_step": 410085, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.09684419631958, "global_step": 410086, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0442862510681152, "global_step": 410087, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0497162342071533, "global_step": 410088, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0911967754364014, "global_step": 410089, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.173982620239258, "global_step": 410090, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.041147232055664, "global_step": 410091, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0378599166870117, "global_step": 410092, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9990078210830688, "global_step": 410093, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.02693772315979, "global_step": 410094, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1503429412841797, "global_step": 410095, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1553659439086914, "global_step": 410096, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.123858690261841, "global_step": 410097, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.015906572341919, "global_step": 410098, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1250314712524414, "global_step": 410099, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.037691116333008, "global_step": 410100, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.077476739883423, "global_step": 410101, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.079690933227539, "global_step": 410102, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1532444953918457, "global_step": 410103, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0604617595672607, "global_step": 410104, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.993991732597351, "global_step": 410105, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0592567920684814, "global_step": 410106, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.001152753829956, "global_step": 410107, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1068437099456787, "global_step": 410108, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0702569484710693, "global_step": 410109, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9841067790985107, "global_step": 410110, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0324912071228027, "global_step": 410111, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1690478324890137, "global_step": 410112, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.160073757171631, "global_step": 410113, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.040148973464966, "global_step": 410114, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1208486557006836, "global_step": 410115, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.122180938720703, "global_step": 410116, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.098930835723877, "global_step": 410117, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1881792545318604, "global_step": 410118, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0673811435699463, "global_step": 410119, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.065803050994873, "global_step": 410120, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.078855037689209, "global_step": 410121, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0326385498046875, "global_step": 410122, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0809946060180664, "global_step": 410123, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0345191955566406, "global_step": 410124, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1330721378326416, "global_step": 410125, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.068239688873291, "global_step": 410126, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.067779541015625, "global_step": 410127, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.106534242630005, "global_step": 410128, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.023348331451416, "global_step": 410129, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.118427038192749, "global_step": 410130, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.068962812423706, "global_step": 410131, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.084709405899048, "global_step": 410132, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.11679744720459, "global_step": 410133, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.11979079246521, "global_step": 410134, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.096871852874756, "global_step": 410135, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0030157566070557, "global_step": 410136, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1878209114074707, "global_step": 410137, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9611802101135254, "global_step": 410138, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1059365272521973, "global_step": 410139, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.197258949279785, "global_step": 410140, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.047888994216919, "global_step": 410141, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0212011337280273, "global_step": 410142, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1566405296325684, "global_step": 410143, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.993994116783142, "global_step": 410144, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.06488037109375, "global_step": 410145, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.064720869064331, "global_step": 410146, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0765974521636963, "global_step": 410147, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1866626739501953, "global_step": 410148, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.100020170211792, "global_step": 410149, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0212035179138184, "global_step": 410150, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.076932191848755, "global_step": 410151, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.152353286743164, "global_step": 410152, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0636839866638184, "global_step": 410153, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.145817756652832, "global_step": 410154, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.037085771560669, "global_step": 410155, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0847384929656982, "global_step": 410156, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0581281185150146, "global_step": 410157, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1566734313964844, "global_step": 410158, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0522592067718506, "global_step": 410159, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0944414138793945, "global_step": 410160, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9869893789291382, "global_step": 410161, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1079747676849365, "global_step": 410162, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0537521839141846, "global_step": 410163, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1384694576263428, "global_step": 410164, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0442962646484375, "global_step": 410165, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0192861557006836, "global_step": 410166, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.158148765563965, "global_step": 410167, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1417267322540283, "global_step": 410168, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.10648250579834, "global_step": 410169, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.088646173477173, "global_step": 410170, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0369863510131836, "global_step": 410171, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.131880521774292, "global_step": 410172, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.996178150177002, "global_step": 410173, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9876272678375244, "global_step": 410174, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.024928569793701, "global_step": 410175, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.075829029083252, "global_step": 410176, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1179850101470947, "global_step": 410177, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.041102409362793, "global_step": 410178, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1230783462524414, "global_step": 410179, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.2056803703308105, "global_step": 410180, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0937516689300537, "global_step": 410181, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.003152370452881, "global_step": 410182, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.034649610519409, "global_step": 410183, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.107682704925537, "global_step": 410184, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.045708179473877, "global_step": 410185, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1153249740600586, "global_step": 410186, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.059544801712036, "global_step": 410187, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0276997089385986, "global_step": 410188, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.214670419692993, "global_step": 410189, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0931081771850586, "global_step": 410190, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.176658868789673, "global_step": 410191, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.037266731262207, "global_step": 410192, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1206717491149902, "global_step": 410193, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1412177085876465, "global_step": 410194, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0688116550445557, "global_step": 410195, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.15061092376709, "global_step": 410196, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.081510066986084, "global_step": 410197, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.098416805267334, "global_step": 410198, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1761674880981445, "global_step": 410199, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1864593029022217, "global_step": 410200, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0612268447875977, "global_step": 410201, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.092935085296631, "global_step": 410202, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1410155296325684, "global_step": 410203, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0384833812713623, "global_step": 410204, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.068861246109009, "global_step": 410205, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0925238132476807, "global_step": 410206, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.163858652114868, "global_step": 410207, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1049370765686035, "global_step": 410208, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0220301151275635, "global_step": 410209, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0804965496063232, "global_step": 410210, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0223355293273926, "global_step": 410211, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1309049129486084, "global_step": 410212, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.104283094406128, "global_step": 410213, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.124009847640991, "global_step": 410214, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0216007232666016, "global_step": 410215, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.059685468673706, "global_step": 410216, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9807946681976318, "global_step": 410217, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.065582513809204, "global_step": 410218, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.149116039276123, "global_step": 410219, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1290502548217773, "global_step": 410220, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9884634017944336, "global_step": 410221, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0049073696136475, "global_step": 410222, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.136072874069214, "global_step": 410223, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9948396682739258, "global_step": 410224, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0368411540985107, "global_step": 410225, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.142216205596924, "global_step": 410226, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0483477115631104, "global_step": 410227, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.091935157775879, "global_step": 410228, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1194307804107666, "global_step": 410229, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1587414741516113, "global_step": 410230, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.158323049545288, "global_step": 410231, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1469485759735107, "global_step": 410232, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1014981269836426, "global_step": 410233, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.03562593460083, "global_step": 410234, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9817805290222168, "global_step": 410235, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.125258445739746, "global_step": 410236, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1237008571624756, "global_step": 410237, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.2327849864959717, "global_step": 410238, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.026881217956543, "global_step": 410239, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0317986011505127, "global_step": 410240, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0280823707580566, "global_step": 410241, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1053431034088135, "global_step": 410242, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0426063537597656, "global_step": 410243, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0323946475982666, "global_step": 410244, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0935466289520264, "global_step": 410245, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0532310009002686, "global_step": 410246, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.097804307937622, "global_step": 410247, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1706554889678955, "global_step": 410248, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0691683292388916, "global_step": 410249, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1105494499206543, "global_step": 410250, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0084612369537354, "global_step": 410251, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0928494930267334, "global_step": 410252, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.049917697906494, "global_step": 410253, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0720889568328857, "global_step": 410254, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.158342123031616, "global_step": 410255, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0710692405700684, "global_step": 410256, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.092794179916382, "global_step": 410257, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1120402812957764, "global_step": 410258, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.177448272705078, "global_step": 410259, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9450336694717407, "global_step": 410260, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0139427185058594, "global_step": 410261, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.090043067932129, "global_step": 410262, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.120975971221924, "global_step": 410263, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.002389907836914, "global_step": 410264, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1015713214874268, "global_step": 410265, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.135249137878418, "global_step": 410266, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0732717514038086, "global_step": 410267, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0909018516540527, "global_step": 410268, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0607833862304688, "global_step": 410269, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0191104412078857, "global_step": 410270, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1439402103424072, "global_step": 410271, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0978987216949463, "global_step": 410272, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1305112838745117, "global_step": 410273, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.157857894897461, "global_step": 410274, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1110846996307373, "global_step": 410275, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1136438846588135, "global_step": 410276, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1301188468933105, "global_step": 410277, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.026165246963501, "global_step": 410278, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1026225090026855, "global_step": 410279, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1436243057250977, "global_step": 410280, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.052828788757324, "global_step": 410281, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1775550842285156, "global_step": 410282, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0436174869537354, "global_step": 410283, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9876502752304077, "global_step": 410284, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1345908641815186, "global_step": 410285, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0679984092712402, "global_step": 410286, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0749387741088867, "global_step": 410287, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9570082426071167, "global_step": 410288, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1026418209075928, "global_step": 410289, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.087214946746826, "global_step": 410290, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.163213014602661, "global_step": 410291, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.084878921508789, "global_step": 410292, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0264389514923096, "global_step": 410293, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.064150810241699, "global_step": 410294, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.07381534576416, "global_step": 410295, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.099276065826416, "global_step": 410296, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1082050800323486, "global_step": 410297, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.123063087463379, "global_step": 410298, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0655529499053955, "global_step": 410299, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1511776447296143, "global_step": 410300, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0408289432525635, "global_step": 410301, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0760104656219482, "global_step": 410302, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0764169692993164, "global_step": 410303, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9654654264450073, "global_step": 410304, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0981736183166504, "global_step": 410305, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.113892078399658, "global_step": 410306, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.141629934310913, "global_step": 410307, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1030797958374023, "global_step": 410308, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.06195068359375, "global_step": 410309, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.112802267074585, "global_step": 410310, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.072199583053589, "global_step": 410311, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0373082160949707, "global_step": 410312, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0727388858795166, "global_step": 410313, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.140293836593628, "global_step": 410314, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1268458366394043, "global_step": 410315, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.135350465774536, "global_step": 410316, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9952051639556885, "global_step": 410317, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.066009759902954, "global_step": 410318, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0915305614471436, "global_step": 410319, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.114525318145752, "global_step": 410320, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.046640396118164, "global_step": 410321, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.018085479736328, "global_step": 410322, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9824535846710205, "global_step": 410323, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.106567144393921, "global_step": 410324, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.036252021789551, "global_step": 410325, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0938351154327393, "global_step": 410326, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1511788368225098, "global_step": 410327, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1042444705963135, "global_step": 410328, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.131641149520874, "global_step": 410329, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.130378007888794, "global_step": 410330, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0629544258117676, "global_step": 410331, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.031662940979004, "global_step": 410332, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1074695587158203, "global_step": 410333, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.030656576156616, "global_step": 410334, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0317647457122803, "global_step": 410335, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.116204261779785, "global_step": 410336, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0933284759521484, "global_step": 410337, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0916659832000732, "global_step": 410338, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.048269748687744, "global_step": 410339, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0746498107910156, "global_step": 410340, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0548529624938965, "global_step": 410341, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1466641426086426, "global_step": 410342, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.096107244491577, "global_step": 410343, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1024067401885986, "global_step": 410344, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0609958171844482, "global_step": 410345, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0887231826782227, "global_step": 410346, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.084477424621582, "global_step": 410347, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.13631272315979, "global_step": 410348, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0955777168273926, "global_step": 410349, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1134555339813232, "global_step": 410350, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.083277702331543, "global_step": 410351, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0249569416046143, "global_step": 410352, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0462660789489746, "global_step": 410353, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0722105503082275, "global_step": 410354, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.111678123474121, "global_step": 410355, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.101362943649292, "global_step": 410356, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.100674867630005, "global_step": 410357, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0681545734405518, "global_step": 410358, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.2074062824249268, "global_step": 410359, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.169848680496216, "global_step": 410360, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0851242542266846, "global_step": 410361, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1347367763519287, "global_step": 410362, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1095314025878906, "global_step": 410363, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.121587038040161, "global_step": 410364, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0233383178710938, "global_step": 410365, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0751352310180664, "global_step": 410366, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1617424488067627, "global_step": 410367, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0460293292999268, "global_step": 410368, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0520076751708984, "global_step": 410369, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.149930000305176, "global_step": 410370, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.070227861404419, "global_step": 410371, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0591888427734375, "global_step": 410372, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0968549251556396, "global_step": 410373, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.079298496246338, "global_step": 410374, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.099233627319336, "global_step": 410375, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.095038652420044, "global_step": 410376, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.058326244354248, "global_step": 410377, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1250083446502686, "global_step": 410378, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0038626194000244, "global_step": 410379, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0933074951171875, "global_step": 410380, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.033337116241455, "global_step": 410381, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.115772008895874, "global_step": 410382, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.106017827987671, "global_step": 410383, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.164118528366089, "global_step": 410384, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.089975595474243, "global_step": 410385, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1445114612579346, "global_step": 410386, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.166921377182007, "global_step": 410387, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1440296173095703, "global_step": 410388, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1845483779907227, "global_step": 410389, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.074941635131836, "global_step": 410390, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0645341873168945, "global_step": 410391, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0362515449523926, "global_step": 410392, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.090144634246826, "global_step": 410393, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1148931980133057, "global_step": 410394, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1130449771881104, "global_step": 410395, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0502071380615234, "global_step": 410396, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1409122943878174, "global_step": 410397, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0924954414367676, "global_step": 410398, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0430798530578613, "global_step": 410399, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0650322437286377, "global_step": 410400, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.054556131362915, "global_step": 410401, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.105222225189209, "global_step": 410402, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.203777313232422, "global_step": 410403, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0680770874023438, "global_step": 410404, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.034876823425293, "global_step": 410405, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.129279136657715, "global_step": 410406, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1244659423828125, "global_step": 410407, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.118424415588379, "global_step": 410408, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.193459987640381, "global_step": 410409, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0798094272613525, "global_step": 410410, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.172736167907715, "global_step": 410411, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0846142768859863, "global_step": 410412, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1560957431793213, "global_step": 410413, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1221208572387695, "global_step": 410414, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1305668354034424, "global_step": 410415, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1179819107055664, "global_step": 410416, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.145763397216797, "global_step": 410417, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.137019395828247, "global_step": 410418, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1035637855529785, "global_step": 410419, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0547029972076416, "global_step": 410420, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1136322021484375, "global_step": 410421, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0046486854553223, "global_step": 410422, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.081403970718384, "global_step": 410423, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0148496627807617, "global_step": 410424, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0856995582580566, "global_step": 410425, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.081984519958496, "global_step": 410426, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.016150712966919, "global_step": 410427, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0912961959838867, "global_step": 410428, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1557650566101074, "global_step": 410429, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.122666120529175, "global_step": 410430, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0919201374053955, "global_step": 410431, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0935170650482178, "global_step": 410432, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.121903896331787, "global_step": 410433, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.098945140838623, "global_step": 410434, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.2131752967834473, "global_step": 410435, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0502662658691406, "global_step": 410436, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1521031856536865, "global_step": 410437, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0855958461761475, "global_step": 410438, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1294147968292236, "global_step": 410439, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0754411220550537, "global_step": 410440, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1510584354400635, "global_step": 410441, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.985721468925476, "global_step": 410442, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.145564556121826, "global_step": 410443, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.050391435623169, "global_step": 410444, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.012209892272949, "global_step": 410445, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1235954761505127, "global_step": 410446, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.033261775970459, "global_step": 410447, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0448195934295654, "global_step": 410448, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.14247727394104, "global_step": 410449, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0555419921875, "global_step": 410450, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1071465015411377, "global_step": 410451, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1194541454315186, "global_step": 410452, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.170003652572632, "global_step": 410453, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.190439462661743, "global_step": 410454, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.144803762435913, "global_step": 410455, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0230000019073486, "global_step": 410456, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.142949104309082, "global_step": 410457, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0319697856903076, "global_step": 410458, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0862720012664795, "global_step": 410459, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1025078296661377, "global_step": 410460, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.112755537033081, "global_step": 410461, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0739712715148926, "global_step": 410462, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1261181831359863, "global_step": 410463, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0640175342559814, "global_step": 410464, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0989937782287598, "global_step": 410465, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1587743759155273, "global_step": 410466, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1139791011810303, "global_step": 410467, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.123314380645752, "global_step": 410468, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0131897926330566, "global_step": 410469, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1361842155456543, "global_step": 410470, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.058807134628296, "global_step": 410471, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0054452419281006, "global_step": 410472, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1370742321014404, "global_step": 410473, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1030113697052, "global_step": 410474, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1248562335968018, "global_step": 410475, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0963854789733887, "global_step": 410476, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0909957885742188, "global_step": 410477, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.085813283920288, "global_step": 410478, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.076341152191162, "global_step": 410479, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.145169973373413, "global_step": 410480, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.164696455001831, "global_step": 410481, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.105473518371582, "global_step": 410482, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.075277090072632, "global_step": 410483, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.063626766204834, "global_step": 410484, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0469484329223633, "global_step": 410485, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0415942668914795, "global_step": 410486, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0881946086883545, "global_step": 410487, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0585179328918457, "global_step": 410488, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.069653034210205, "global_step": 410489, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.041686534881592, "global_step": 410490, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.063249111175537, "global_step": 410491, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1528420448303223, "global_step": 410492, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.047677755355835, "global_step": 410493, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.09912371635437, "global_step": 410494, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.127706527709961, "global_step": 410495, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0380730628967285, "global_step": 410496, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.146177053451538, "global_step": 410497, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1787571907043457, "global_step": 410498, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.988357663154602, "global_step": 410499, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.18700909614563, "global_step": 410500, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0814290046691895, "global_step": 410501, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.113511562347412, "global_step": 410502, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.073160171508789, "global_step": 410503, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.113511085510254, "global_step": 410504, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.169891357421875, "global_step": 410505, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0890793800354004, "global_step": 410506, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0868172645568848, "global_step": 410507, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.051309108734131, "global_step": 410508, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.090343952178955, "global_step": 410509, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1357665061950684, "global_step": 410510, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.130270004272461, "global_step": 410511, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.113684892654419, "global_step": 410512, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0852532386779785, "global_step": 410513, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0128965377807617, "global_step": 410514, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.123748779296875, "global_step": 410515, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0504531860351562, "global_step": 410516, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.226404905319214, "global_step": 410517, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0616440773010254, "global_step": 410518, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.179166555404663, "global_step": 410519, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.083573818206787, "global_step": 410520, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0355632305145264, "global_step": 410521, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0115127563476562, "global_step": 410522, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1248507499694824, "global_step": 410523, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0621914863586426, "global_step": 410524, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.071681022644043, "global_step": 410525, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.116989850997925, "global_step": 410526, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1033575534820557, "global_step": 410527, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0057523250579834, "global_step": 410528, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1257474422454834, "global_step": 410529, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0408897399902344, "global_step": 410530, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.120911121368408, "global_step": 410531, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0912463665008545, "global_step": 410532, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.081726551055908, "global_step": 410533, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.095818519592285, "global_step": 410534, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0722532272338867, "global_step": 410535, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.2027456760406494, "global_step": 410536, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.121819019317627, "global_step": 410537, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.116628885269165, "global_step": 410538, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1125659942626953, "global_step": 410539, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1317496299743652, "global_step": 410540, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.092550039291382, "global_step": 410541, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.083649158477783, "global_step": 410542, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.058384895324707, "global_step": 410543, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0912282466888428, "global_step": 410544, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.118222713470459, "global_step": 410545, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0529582500457764, "global_step": 410546, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.095414876937866, "global_step": 410547, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.12404465675354, "global_step": 410548, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.085283041000366, "global_step": 410549, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.128603935241699, "global_step": 410550, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1572628021240234, "global_step": 410551, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1085305213928223, "global_step": 410552, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.106929302215576, "global_step": 410553, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0313024520874023, "global_step": 410554, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.050877571105957, "global_step": 410555, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0739715099334717, "global_step": 410556, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.114398241043091, "global_step": 410557, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.114246129989624, "global_step": 410558, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0582339763641357, "global_step": 410559, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0980536937713623, "global_step": 410560, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.183675765991211, "global_step": 410561, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.024778366088867, "global_step": 410562, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1606552600860596, "global_step": 410563, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0993528366088867, "global_step": 410564, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.10933518409729, "global_step": 410565, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.091975688934326, "global_step": 410566, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0186893939971924, "global_step": 410567, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.085689067840576, "global_step": 410568, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.090837001800537, "global_step": 410569, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.148221731185913, "global_step": 410570, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1196389198303223, "global_step": 410571, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1166441440582275, "global_step": 410572, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.141213893890381, "global_step": 410573, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0920443534851074, "global_step": 410574, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1152255535125732, "global_step": 410575, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.107356071472168, "global_step": 410576, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.082880973815918, "global_step": 410577, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0653719902038574, "global_step": 410578, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1158480644226074, "global_step": 410579, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0923681259155273, "global_step": 410580, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0905230045318604, "global_step": 410581, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1065642833709717, "global_step": 410582, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.033390998840332, "global_step": 410583, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.009612798690796, "global_step": 410584, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0738630294799805, "global_step": 410585, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.01802134513855, "global_step": 410586, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.005265951156616, "global_step": 410587, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0896949768066406, "global_step": 410588, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1296427249908447, "global_step": 410589, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.144843101501465, "global_step": 410590, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.010758638381958, "global_step": 410591, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.105565071105957, "global_step": 410592, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0807547569274902, "global_step": 410593, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.046069622039795, "global_step": 410594, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.190572500228882, "global_step": 410595, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1367287635803223, "global_step": 410596, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.088939905166626, "global_step": 410597, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0745975971221924, "global_step": 410598, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.054593801498413, "global_step": 410599, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.15939998626709, "global_step": 410600, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1113712787628174, "global_step": 410601, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1071746349334717, "global_step": 410602, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.018054962158203, "global_step": 410603, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1230599880218506, "global_step": 410604, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0743603706359863, "global_step": 410605, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0370395183563232, "global_step": 410606, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1024816036224365, "global_step": 410607, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1122677326202393, "global_step": 410608, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1604673862457275, "global_step": 410609, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1736152172088623, "global_step": 410610, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.15738844871521, "global_step": 410611, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1696150302886963, "global_step": 410612, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.019514560699463, "global_step": 410613, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.098148822784424, "global_step": 410614, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0270931720733643, "global_step": 410615, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.193748712539673, "global_step": 410616, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.148923397064209, "global_step": 410617, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1231420040130615, "global_step": 410618, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.202211856842041, "global_step": 410619, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.197763204574585, "global_step": 410620, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.072970390319824, "global_step": 410621, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.176262140274048, "global_step": 410622, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0760695934295654, "global_step": 410623, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0854437351226807, "global_step": 410624, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0591025352478027, "global_step": 410625, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0571820735931396, "global_step": 410626, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.134227991104126, "global_step": 410627, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1649131774902344, "global_step": 410628, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0741701126098633, "global_step": 410629, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.075784683227539, "global_step": 410630, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0969889163970947, "global_step": 410631, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1115517616271973, "global_step": 410632, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.031322717666626, "global_step": 410633, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0842742919921875, "global_step": 410634, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0367348194122314, "global_step": 410635, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0683157444000244, "global_step": 410636, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1506223678588867, "global_step": 410637, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1773107051849365, "global_step": 410638, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.071730375289917, "global_step": 410639, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.092078447341919, "global_step": 410640, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0653984546661377, "global_step": 410641, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0558369159698486, "global_step": 410642, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.104463577270508, "global_step": 410643, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0769295692443848, "global_step": 410644, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1850192546844482, "global_step": 410645, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1271276473999023, "global_step": 410646, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1310505867004395, "global_step": 410647, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.072186231613159, "global_step": 410648, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0667717456817627, "global_step": 410649, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0573039054870605, "global_step": 410650, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.132106304168701, "global_step": 410651, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0679521560668945, "global_step": 410652, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.113584280014038, "global_step": 410653, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0678200721740723, "global_step": 410654, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.099888563156128, "global_step": 410655, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.087178945541382, "global_step": 410656, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.2196152210235596, "global_step": 410657, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1059699058532715, "global_step": 410658, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1528069972991943, "global_step": 410659, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0659518241882324, "global_step": 410660, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1734302043914795, "global_step": 410661, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.032407522201538, "global_step": 410662, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0543525218963623, "global_step": 410663, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1005537509918213, "global_step": 410664, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0874030590057373, "global_step": 410665, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1522228717803955, "global_step": 410666, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.109037399291992, "global_step": 410667, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1237189769744873, "global_step": 410668, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.106198310852051, "global_step": 410669, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1139633655548096, "global_step": 410670, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0632872581481934, "global_step": 410671, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.086834192276001, "global_step": 410672, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1241180896759033, "global_step": 410673, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1431894302368164, "global_step": 410674, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0295920372009277, "global_step": 410675, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0868942737579346, "global_step": 410676, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.054616928100586, "global_step": 410677, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0896170139312744, "global_step": 410678, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.028026819229126, "global_step": 410679, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1414260864257812, "global_step": 410680, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.054234743118286, "global_step": 410681, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.034456729888916, "global_step": 410682, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0444648265838623, "global_step": 410683, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.082672119140625, "global_step": 410684, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.030989170074463, "global_step": 410685, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1203420162200928, "global_step": 410686, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.020020008087158, "global_step": 410687, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0618185997009277, "global_step": 410688, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0743463039398193, "global_step": 410689, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0720789432525635, "global_step": 410690, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1678521633148193, "global_step": 410691, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0822603702545166, "global_step": 410692, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.102142333984375, "global_step": 410693, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1066975593566895, "global_step": 410694, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0787315368652344, "global_step": 410695, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.954491376876831, "global_step": 410696, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1916263103485107, "global_step": 410697, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0535380840301514, "global_step": 410698, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.058236837387085, "global_step": 410699, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0766994953155518, "global_step": 410700, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.083662509918213, "global_step": 410701, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1589529514312744, "global_step": 410702, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1206772327423096, "global_step": 410703, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9993752241134644, "global_step": 410704, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.115652561187744, "global_step": 410705, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1540091037750244, "global_step": 410706, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.087157726287842, "global_step": 410707, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0912392139434814, "global_step": 410708, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0973305702209473, "global_step": 410709, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0302205085754395, "global_step": 410710, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.020667552947998, "global_step": 410711, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.112116813659668, "global_step": 410712, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1113553047180176, "global_step": 410713, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.096322536468506, "global_step": 410714, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.247903823852539, "global_step": 410715, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.018232583999634, "global_step": 410716, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1019039154052734, "global_step": 410717, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.087437152862549, "global_step": 410718, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1185154914855957, "global_step": 410719, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0368154048919678, "global_step": 410720, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1106925010681152, "global_step": 410721, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1017792224884033, "global_step": 410722, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.030977964401245, "global_step": 410723, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0742506980895996, "global_step": 410724, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.158271312713623, "global_step": 410725, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.05725359916687, "global_step": 410726, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1309354305267334, "global_step": 410727, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.023038625717163, "global_step": 410728, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.093578815460205, "global_step": 410729, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.992344617843628, "global_step": 410730, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.025195598602295, "global_step": 410731, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0932130813598633, "global_step": 410732, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.220517873764038, "global_step": 410733, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0994508266448975, "global_step": 410734, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.066828966140747, "global_step": 410735, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0514256954193115, "global_step": 410736, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.132040500640869, "global_step": 410737, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0144362449645996, "global_step": 410738, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.141535758972168, "global_step": 410739, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.032968759536743, "global_step": 410740, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0686721801757812, "global_step": 410741, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1410841941833496, "global_step": 410742, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.144078016281128, "global_step": 410743, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1587302684783936, "global_step": 410744, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.085944890975952, "global_step": 410745, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.093398332595825, "global_step": 410746, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1851372718811035, "global_step": 410747, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1119184494018555, "global_step": 410748, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0578112602233887, "global_step": 410749, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1361451148986816, "global_step": 410750, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.097201347351074, "global_step": 410751, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.015511989593506, "global_step": 410752, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0999841690063477, "global_step": 410753, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0840723514556885, "global_step": 410754, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.002228021621704, "global_step": 410755, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0880446434020996, "global_step": 410756, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.128070592880249, "global_step": 410757, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.070256471633911, "global_step": 410758, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0893399715423584, "global_step": 410759, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.030057907104492, "global_step": 410760, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.133540630340576, "global_step": 410761, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9897716045379639, "global_step": 410762, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1365139484405518, "global_step": 410763, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0855350494384766, "global_step": 410764, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.103628635406494, "global_step": 410765, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.147552251815796, "global_step": 410766, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0804316997528076, "global_step": 410767, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0892391204833984, "global_step": 410768, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1414291858673096, "global_step": 410769, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.096219539642334, "global_step": 410770, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.063871383666992, "global_step": 410771, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9918566942214966, "global_step": 410772, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1127068996429443, "global_step": 410773, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.146933078765869, "global_step": 410774, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1075031757354736, "global_step": 410775, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0184714794158936, "global_step": 410776, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1369853019714355, "global_step": 410777, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.084746837615967, "global_step": 410778, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0956969261169434, "global_step": 410779, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1288087368011475, "global_step": 410780, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.124631404876709, "global_step": 410781, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0770392417907715, "global_step": 410782, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0784945487976074, "global_step": 410783, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.015573024749756, "global_step": 410784, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.109182357788086, "global_step": 410785, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0863330364227295, "global_step": 410786, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0821075439453125, "global_step": 410787, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.072504758834839, "global_step": 410788, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0434951782226562, "global_step": 410789, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.010633707046509, "global_step": 410790, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0663137435913086, "global_step": 410791, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1083128452301025, "global_step": 410792, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1274120807647705, "global_step": 410793, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0521039962768555, "global_step": 410794, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1577258110046387, "global_step": 410795, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0966403484344482, "global_step": 410796, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.067559242248535, "global_step": 410797, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0803542137145996, "global_step": 410798, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0956106185913086, "global_step": 410799, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.083031415939331, "global_step": 410800, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0040640830993652, "global_step": 410801, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.097931146621704, "global_step": 410802, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0797808170318604, "global_step": 410803, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0642106533050537, "global_step": 410804, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.138699531555176, "global_step": 410805, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.214783191680908, "global_step": 410806, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.118269920349121, "global_step": 410807, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.137396812438965, "global_step": 410808, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0789406299591064, "global_step": 410809, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.180534839630127, "global_step": 410810, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0961194038391113, "global_step": 410811, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0779247283935547, "global_step": 410812, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1345009803771973, "global_step": 410813, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.192671298980713, "global_step": 410814, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.082019329071045, "global_step": 410815, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1631102561950684, "global_step": 410816, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.083047866821289, "global_step": 410817, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.056047201156616, "global_step": 410818, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.091578722000122, "global_step": 410819, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9287769794464111, "global_step": 410820, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0380537509918213, "global_step": 410821, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1164586544036865, "global_step": 410822, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0662877559661865, "global_step": 410823, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0658040046691895, "global_step": 410824, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1654584407806396, "global_step": 410825, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.090668201446533, "global_step": 410826, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.058236598968506, "global_step": 410827, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.166778564453125, "global_step": 410828, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0718767642974854, "global_step": 410829, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0467469692230225, "global_step": 410830, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1541669368743896, "global_step": 410831, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0604851245880127, "global_step": 410832, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0865094661712646, "global_step": 410833, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0674707889556885, "global_step": 410834, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.128786325454712, "global_step": 410835, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0769472122192383, "global_step": 410836, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0137689113616943, "global_step": 410837, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1314961910247803, "global_step": 410838, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0553646087646484, "global_step": 410839, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.114248514175415, "global_step": 410840, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.169435501098633, "global_step": 410841, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0778703689575195, "global_step": 410842, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0806126594543457, "global_step": 410843, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1008877754211426, "global_step": 410844, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.058478832244873, "global_step": 410845, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.095055341720581, "global_step": 410846, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0201938152313232, "global_step": 410847, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0252480506896973, "global_step": 410848, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.086947202682495, "global_step": 410849, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.11741304397583, "global_step": 410850, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0994760990142822, "global_step": 410851, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.984138011932373, "global_step": 410852, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.177973508834839, "global_step": 410853, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0252606868743896, "global_step": 410854, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.054150342941284, "global_step": 410855, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1678342819213867, "global_step": 410856, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.113144636154175, "global_step": 410857, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1063625812530518, "global_step": 410858, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.092196464538574, "global_step": 410859, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1084096431732178, "global_step": 410860, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.099868059158325, "global_step": 410861, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.099224328994751, "global_step": 410862, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1438281536102295, "global_step": 410863, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.097712278366089, "global_step": 410864, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.083635091781616, "global_step": 410865, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.101259708404541, "global_step": 410866, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1339941024780273, "global_step": 410867, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.074049711227417, "global_step": 410868, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1193740367889404, "global_step": 410869, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.038593053817749, "global_step": 410870, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9841293096542358, "global_step": 410871, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.02441143989563, "global_step": 410872, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.09835147857666, "global_step": 410873, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.185068368911743, "global_step": 410874, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0999321937561035, "global_step": 410875, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.215500593185425, "global_step": 410876, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0323448181152344, "global_step": 410877, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1690995693206787, "global_step": 410878, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1743202209472656, "global_step": 410879, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0195138454437256, "global_step": 410880, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0664350986480713, "global_step": 410881, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.143934726715088, "global_step": 410882, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.076166868209839, "global_step": 410883, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.104884624481201, "global_step": 410884, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0823330879211426, "global_step": 410885, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.064472198486328, "global_step": 410886, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.095374822616577, "global_step": 410887, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.154038906097412, "global_step": 410888, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.184011220932007, "global_step": 410889, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.081240653991699, "global_step": 410890, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0960309505462646, "global_step": 410891, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.017876148223877, "global_step": 410892, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0130982398986816, "global_step": 410893, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0069100856781006, "global_step": 410894, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.131979465484619, "global_step": 410895, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.022630214691162, "global_step": 410896, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.076406955718994, "global_step": 410897, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.053084373474121, "global_step": 410898, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1207494735717773, "global_step": 410899, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1469807624816895, "global_step": 410900, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0973587036132812, "global_step": 410901, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0779991149902344, "global_step": 410902, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0939130783081055, "global_step": 410903, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1461470127105713, "global_step": 410904, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9994609355926514, "global_step": 410905, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.179905891418457, "global_step": 410906, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.123197078704834, "global_step": 410907, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.03657865524292, "global_step": 410908, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1444177627563477, "global_step": 410909, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.052074670791626, "global_step": 410910, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.108966112136841, "global_step": 410911, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.088573932647705, "global_step": 410912, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1036055088043213, "global_step": 410913, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1229405403137207, "global_step": 410914, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1458239555358887, "global_step": 410915, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9966892004013062, "global_step": 410916, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0949866771698, "global_step": 410917, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1137707233428955, "global_step": 410918, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.109895944595337, "global_step": 410919, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.154167890548706, "global_step": 410920, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1435840129852295, "global_step": 410921, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1678402423858643, "global_step": 410922, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0376129150390625, "global_step": 410923, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0877573490142822, "global_step": 410924, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.086672306060791, "global_step": 410925, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0656609535217285, "global_step": 410926, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.142002820968628, "global_step": 410927, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1778995990753174, "global_step": 410928, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0730185508728027, "global_step": 410929, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1088497638702393, "global_step": 410930, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.149033784866333, "global_step": 410931, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.156315803527832, "global_step": 410932, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0715861320495605, "global_step": 410933, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0204997062683105, "global_step": 410934, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.071105480194092, "global_step": 410935, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0293734073638916, "global_step": 410936, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1553657054901123, "global_step": 410937, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0996463298797607, "global_step": 410938, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0606698989868164, "global_step": 410939, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0841333866119385, "global_step": 410940, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9858787059783936, "global_step": 410941, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.12418270111084, "global_step": 410942, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1694090366363525, "global_step": 410943, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1188247203826904, "global_step": 410944, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.9679709672927856, "global_step": 410945, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.080416679382324, "global_step": 410946, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1351559162139893, "global_step": 410947, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.162445545196533, "global_step": 410948, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0564582347869873, "global_step": 410949, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1261134147644043, "global_step": 410950, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0406649112701416, "global_step": 410951, "epoch": 773, "lr": 5e-05}
{"train_loss": 1.99458646774292, "global_step": 410952, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1238012313842773, "global_step": 410953, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.201904773712158, "global_step": 410954, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.108609437942505, "global_step": 410955, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0768136978149414, "global_step": 410956, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1156728267669678, "global_step": 410957, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.008507251739502, "global_step": 410958, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0360496044158936, "global_step": 410959, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1726086139678955, "global_step": 410960, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0918848514556885, "global_step": 410961, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.052194595336914, "global_step": 410962, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.116917133331299, "global_step": 410963, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1020004749298096, "global_step": 410964, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0715529918670654, "global_step": 410965, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1222076416015625, "global_step": 410966, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.049342632293701, "global_step": 410967, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.12744140625, "global_step": 410968, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.184325695037842, "global_step": 410969, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1064248085021973, "global_step": 410970, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.178612470626831, "global_step": 410971, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0691747665405273, "global_step": 410972, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.016275644302368, "global_step": 410973, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1227612495422363, "global_step": 410974, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0373990535736084, "global_step": 410975, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.1794803142547607, "global_step": 410976, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.174248218536377, "global_step": 410977, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.109853506088257, "global_step": 410978, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.078864574432373, "global_step": 410979, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.2136056423187256, "global_step": 410980, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.027956008911133, "global_step": 410981, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0920193195343018, "global_step": 410982, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.096155881881714, "global_step": 410983, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.207399845123291, "global_step": 410984, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.2499449253082275, "global_step": 410985, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.07330584526062, "global_step": 410986, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0947041511535645, "global_step": 410987, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0922741889953613, "global_step": 410988, "epoch": 773, "lr": 5e-05}
{"train_loss": 2.0908336639404297, "global_step": 410989, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0438296794891357, "global_step": 410990, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0565404891967773, "global_step": 410991, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.03446626663208, "global_step": 410992, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0645687580108643, "global_step": 410993, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1254515647888184, "global_step": 410994, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.039436101913452, "global_step": 410995, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9421613216400146, "global_step": 410996, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.071136236190796, "global_step": 410997, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.148742198944092, "global_step": 410998, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0199222564697266, "global_step": 410999, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.084350824356079, "global_step": 411000, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0592503547668457, "global_step": 411001, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0817456245422363, "global_step": 411002, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0989174842834473, "global_step": 411003, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.049927234649658, "global_step": 411004, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0164694786071777, "global_step": 411005, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.076282501220703, "global_step": 411006, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0423946380615234, "global_step": 411007, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.082808017730713, "global_step": 411008, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.038435697555542, "global_step": 411009, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.206188678741455, "global_step": 411010, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.084869623184204, "global_step": 411011, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.096907138824463, "global_step": 411012, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1144399642944336, "global_step": 411013, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0844833850860596, "global_step": 411014, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0492656230926514, "global_step": 411015, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0618367195129395, "global_step": 411016, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0379719734191895, "global_step": 411017, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9676262140274048, "global_step": 411018, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0338282585144043, "global_step": 411019, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1677558422088623, "global_step": 411020, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1060049533843994, "global_step": 411021, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.04370379447937, "global_step": 411022, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0357141494750977, "global_step": 411023, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.083064317703247, "global_step": 411024, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0976152420043945, "global_step": 411025, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1449787616729736, "global_step": 411026, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0676074028015137, "global_step": 411027, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1416540145874023, "global_step": 411028, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1107280254364014, "global_step": 411029, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0931315422058105, "global_step": 411030, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.14572811126709, "global_step": 411031, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.022271156311035, "global_step": 411032, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.050236940383911, "global_step": 411033, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.104945421218872, "global_step": 411034, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.064133405685425, "global_step": 411035, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.991837978363037, "global_step": 411036, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.216174364089966, "global_step": 411037, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.033116340637207, "global_step": 411038, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.02770733833313, "global_step": 411039, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.081073045730591, "global_step": 411040, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0516180992126465, "global_step": 411041, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.12736177444458, "global_step": 411042, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1920957565307617, "global_step": 411043, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1057138442993164, "global_step": 411044, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.995803952217102, "global_step": 411045, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0701744556427, "global_step": 411046, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0666120052337646, "global_step": 411047, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.034358263015747, "global_step": 411048, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.091413974761963, "global_step": 411049, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0776164531707764, "global_step": 411050, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.073334217071533, "global_step": 411051, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1043295860290527, "global_step": 411052, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0590856075286865, "global_step": 411053, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0329062938690186, "global_step": 411054, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.05433988571167, "global_step": 411055, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.128044366836548, "global_step": 411056, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.031029462814331, "global_step": 411057, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1027283668518066, "global_step": 411058, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.037142038345337, "global_step": 411059, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0884382724761963, "global_step": 411060, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.17031192779541, "global_step": 411061, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1047568321228027, "global_step": 411062, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.109097957611084, "global_step": 411063, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.121610164642334, "global_step": 411064, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0620875358581543, "global_step": 411065, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0181057453155518, "global_step": 411066, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0653891563415527, "global_step": 411067, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.066007137298584, "global_step": 411068, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0380465984344482, "global_step": 411069, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.056886672973633, "global_step": 411070, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.138363838195801, "global_step": 411071, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1180243492126465, "global_step": 411072, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.117666244506836, "global_step": 411073, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.025758743286133, "global_step": 411074, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1551735401153564, "global_step": 411075, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0539097785949707, "global_step": 411076, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1435630321502686, "global_step": 411077, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0944559574127197, "global_step": 411078, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0760316848754883, "global_step": 411079, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0679657459259033, "global_step": 411080, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.066399097442627, "global_step": 411081, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.004925489425659, "global_step": 411082, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.092722177505493, "global_step": 411083, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1151294708251953, "global_step": 411084, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.061264991760254, "global_step": 411085, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9880582094192505, "global_step": 411086, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.113837242126465, "global_step": 411087, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.120877504348755, "global_step": 411088, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.175642728805542, "global_step": 411089, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0418713092803955, "global_step": 411090, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0686676502227783, "global_step": 411091, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0401008129119873, "global_step": 411092, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1409711837768555, "global_step": 411093, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.02321457862854, "global_step": 411094, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0844268798828125, "global_step": 411095, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0319302082061768, "global_step": 411096, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0219452381134033, "global_step": 411097, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.043219566345215, "global_step": 411098, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0678904056549072, "global_step": 411099, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1167514324188232, "global_step": 411100, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.092928647994995, "global_step": 411101, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.04850435256958, "global_step": 411102, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.151167154312134, "global_step": 411103, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.10903263092041, "global_step": 411104, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.035672187805176, "global_step": 411105, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0458638668060303, "global_step": 411106, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.992822527885437, "global_step": 411107, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.040524482727051, "global_step": 411108, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.065890312194824, "global_step": 411109, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1576340198516846, "global_step": 411110, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1347999572753906, "global_step": 411111, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1160895824432373, "global_step": 411112, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0341367721557617, "global_step": 411113, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.151346445083618, "global_step": 411114, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.082895040512085, "global_step": 411115, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.11688494682312, "global_step": 411116, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1241648197174072, "global_step": 411117, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0766961574554443, "global_step": 411118, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.134976863861084, "global_step": 411119, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.141010284423828, "global_step": 411120, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.030646324157715, "global_step": 411121, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0556693077087402, "global_step": 411122, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.084540843963623, "global_step": 411123, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0645875930786133, "global_step": 411124, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.132607936859131, "global_step": 411125, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.114872694015503, "global_step": 411126, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.120518207550049, "global_step": 411127, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.976115107536316, "global_step": 411128, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.150881290435791, "global_step": 411129, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0508973598480225, "global_step": 411130, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.097136974334717, "global_step": 411131, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1699674129486084, "global_step": 411132, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0339977741241455, "global_step": 411133, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.2008700370788574, "global_step": 411134, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0621702671051025, "global_step": 411135, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0610883235931396, "global_step": 411136, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.995581865310669, "global_step": 411137, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.026705265045166, "global_step": 411138, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1165895462036133, "global_step": 411139, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.079810380935669, "global_step": 411140, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1746606826782227, "global_step": 411141, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1337532997131348, "global_step": 411142, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0447680950164795, "global_step": 411143, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.010166645050049, "global_step": 411144, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.108553171157837, "global_step": 411145, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1052639484405518, "global_step": 411146, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.072334051132202, "global_step": 411147, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0096328258514404, "global_step": 411148, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9736919403076172, "global_step": 411149, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.168318510055542, "global_step": 411150, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.028230905532837, "global_step": 411151, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1463122367858887, "global_step": 411152, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0869534015655518, "global_step": 411153, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1381330490112305, "global_step": 411154, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.124361991882324, "global_step": 411155, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0347511768341064, "global_step": 411156, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.064319610595703, "global_step": 411157, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1326098442077637, "global_step": 411158, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0376040935516357, "global_step": 411159, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.143831253051758, "global_step": 411160, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0940122604370117, "global_step": 411161, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1151156425476074, "global_step": 411162, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1097311973571777, "global_step": 411163, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1444177627563477, "global_step": 411164, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.056809663772583, "global_step": 411165, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.030052900314331, "global_step": 411166, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1235427856445312, "global_step": 411167, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.163036823272705, "global_step": 411168, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.030533790588379, "global_step": 411169, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0843772888183594, "global_step": 411170, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0050477981567383, "global_step": 411171, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.125380516052246, "global_step": 411172, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.112684726715088, "global_step": 411173, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0839555263519287, "global_step": 411174, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0582852363586426, "global_step": 411175, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.08498215675354, "global_step": 411176, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.125126838684082, "global_step": 411177, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0895533561706543, "global_step": 411178, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1152870655059814, "global_step": 411179, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.136599540710449, "global_step": 411180, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.095895290374756, "global_step": 411181, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0437989234924316, "global_step": 411182, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.070720672607422, "global_step": 411183, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.07281231880188, "global_step": 411184, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.099203586578369, "global_step": 411185, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1733410358428955, "global_step": 411186, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.094193696975708, "global_step": 411187, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0581259727478027, "global_step": 411188, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0772085189819336, "global_step": 411189, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0818164348602295, "global_step": 411190, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1312663555145264, "global_step": 411191, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.138108015060425, "global_step": 411192, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.076220989227295, "global_step": 411193, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.058664560317993, "global_step": 411194, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.129244089126587, "global_step": 411195, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1151914596557617, "global_step": 411196, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.149261474609375, "global_step": 411197, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.052234411239624, "global_step": 411198, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1217710971832275, "global_step": 411199, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0762341022491455, "global_step": 411200, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1229114532470703, "global_step": 411201, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.151348352432251, "global_step": 411202, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.152089834213257, "global_step": 411203, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.04119610786438, "global_step": 411204, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.039374828338623, "global_step": 411205, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1547839641571045, "global_step": 411206, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.082756996154785, "global_step": 411207, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.101149797439575, "global_step": 411208, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0191361904144287, "global_step": 411209, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1474153995513916, "global_step": 411210, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.070302724838257, "global_step": 411211, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0405967235565186, "global_step": 411212, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1456422805786133, "global_step": 411213, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0807623863220215, "global_step": 411214, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.133668899536133, "global_step": 411215, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0419583320617676, "global_step": 411216, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.114917516708374, "global_step": 411217, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.114006519317627, "global_step": 411218, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0453872680664062, "global_step": 411219, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.073248863220215, "global_step": 411220, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.113879680633545, "global_step": 411221, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9717305898666382, "global_step": 411222, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1002235412597656, "global_step": 411223, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1003293991088867, "global_step": 411224, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0884103775024414, "global_step": 411225, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.096863031387329, "global_step": 411226, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9749349355697632, "global_step": 411227, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0383644104003906, "global_step": 411228, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0772814750671387, "global_step": 411229, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0803258419036865, "global_step": 411230, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0195956230163574, "global_step": 411231, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0609707832336426, "global_step": 411232, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.054473638534546, "global_step": 411233, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.2014288902282715, "global_step": 411234, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.149294853210449, "global_step": 411235, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0441346168518066, "global_step": 411236, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0703744888305664, "global_step": 411237, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1185853481292725, "global_step": 411238, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1354126930236816, "global_step": 411239, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.012758731842041, "global_step": 411240, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0998473167419434, "global_step": 411241, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1661925315856934, "global_step": 411242, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.126033306121826, "global_step": 411243, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.072598934173584, "global_step": 411244, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.989096760749817, "global_step": 411245, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1136271953582764, "global_step": 411246, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1382384300231934, "global_step": 411247, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.047987937927246, "global_step": 411248, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.149733304977417, "global_step": 411249, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9881008863449097, "global_step": 411250, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1519696712493896, "global_step": 411251, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0121583938598633, "global_step": 411252, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0235230922698975, "global_step": 411253, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0192325115203857, "global_step": 411254, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1002163887023926, "global_step": 411255, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.023371934890747, "global_step": 411256, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.022740364074707, "global_step": 411257, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0905966758728027, "global_step": 411258, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0655980110168457, "global_step": 411259, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.137298583984375, "global_step": 411260, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.063950300216675, "global_step": 411261, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1281821727752686, "global_step": 411262, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0137147903442383, "global_step": 411263, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0624892711639404, "global_step": 411264, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.093557357788086, "global_step": 411265, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1110267639160156, "global_step": 411266, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.129304885864258, "global_step": 411267, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.050508499145508, "global_step": 411268, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0240797996520996, "global_step": 411269, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1504271030426025, "global_step": 411270, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.159940004348755, "global_step": 411271, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0582380294799805, "global_step": 411272, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.030500650405884, "global_step": 411273, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.01261305809021, "global_step": 411274, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1002986431121826, "global_step": 411275, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9961817264556885, "global_step": 411276, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0356855392456055, "global_step": 411277, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.066826581954956, "global_step": 411278, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.2050704956054688, "global_step": 411279, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0121896266937256, "global_step": 411280, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0603647232055664, "global_step": 411281, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0583198070526123, "global_step": 411282, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9760524034500122, "global_step": 411283, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1118884086608887, "global_step": 411284, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.2121453285217285, "global_step": 411285, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1051688194274902, "global_step": 411286, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1455323696136475, "global_step": 411287, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1247498989105225, "global_step": 411288, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.069406032562256, "global_step": 411289, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.07694673538208, "global_step": 411290, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.044785261154175, "global_step": 411291, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.044877052307129, "global_step": 411292, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1680715084075928, "global_step": 411293, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0934646129608154, "global_step": 411294, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.04634952545166, "global_step": 411295, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0798749923706055, "global_step": 411296, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9916356801986694, "global_step": 411297, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9748820066452026, "global_step": 411298, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.03731369972229, "global_step": 411299, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0813069343566895, "global_step": 411300, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1059765815734863, "global_step": 411301, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9629863500595093, "global_step": 411302, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.091557741165161, "global_step": 411303, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1374852657318115, "global_step": 411304, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.029480457305908, "global_step": 411305, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.13767409324646, "global_step": 411306, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.052138328552246, "global_step": 411307, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1091814041137695, "global_step": 411308, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1631932258605957, "global_step": 411309, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.043187141418457, "global_step": 411310, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.091218948364258, "global_step": 411311, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.134721279144287, "global_step": 411312, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.122807502746582, "global_step": 411313, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0539276599884033, "global_step": 411314, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.162449836730957, "global_step": 411315, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.113847017288208, "global_step": 411316, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0836269855499268, "global_step": 411317, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.064453125, "global_step": 411318, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0857996940612793, "global_step": 411319, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.063128709793091, "global_step": 411320, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.193220615386963, "global_step": 411321, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.100647449493408, "global_step": 411322, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.006086826324463, "global_step": 411323, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0404021739959717, "global_step": 411324, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.2175142765045166, "global_step": 411325, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.2091612815856934, "global_step": 411326, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.173478126525879, "global_step": 411327, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1502749919891357, "global_step": 411328, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0247035026550293, "global_step": 411329, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.098550319671631, "global_step": 411330, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.160324811935425, "global_step": 411331, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0337536334991455, "global_step": 411332, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1856253147125244, "global_step": 411333, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0519096851348877, "global_step": 411334, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0270073413848877, "global_step": 411335, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.06437611579895, "global_step": 411336, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0091962814331055, "global_step": 411337, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1303629875183105, "global_step": 411338, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1458399295806885, "global_step": 411339, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.086453914642334, "global_step": 411340, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.013904571533203, "global_step": 411341, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9788206815719604, "global_step": 411342, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.170870304107666, "global_step": 411343, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.105989456176758, "global_step": 411344, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.086162805557251, "global_step": 411345, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0701591968536377, "global_step": 411346, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.067816734313965, "global_step": 411347, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.121821880340576, "global_step": 411348, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1434342861175537, "global_step": 411349, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9889577627182007, "global_step": 411350, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1037545204162598, "global_step": 411351, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.019465446472168, "global_step": 411352, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.056206226348877, "global_step": 411353, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.126854181289673, "global_step": 411354, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.104773998260498, "global_step": 411355, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0236871242523193, "global_step": 411356, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0463759899139404, "global_step": 411357, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.205888271331787, "global_step": 411358, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0812957286834717, "global_step": 411359, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0672965049743652, "global_step": 411360, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0262598991394043, "global_step": 411361, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9559581279754639, "global_step": 411362, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.096555233001709, "global_step": 411363, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1243033409118652, "global_step": 411364, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.090446949005127, "global_step": 411365, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0440785884857178, "global_step": 411366, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9940294027328491, "global_step": 411367, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0369646549224854, "global_step": 411368, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.019183397293091, "global_step": 411369, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.080841541290283, "global_step": 411370, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1264092922210693, "global_step": 411371, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.14188551902771, "global_step": 411372, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1513192653656006, "global_step": 411373, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.048302173614502, "global_step": 411374, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1045055389404297, "global_step": 411375, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0897631645202637, "global_step": 411376, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.165660858154297, "global_step": 411377, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.106454849243164, "global_step": 411378, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0429608821868896, "global_step": 411379, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1093740463256836, "global_step": 411380, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.139922618865967, "global_step": 411381, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.13901948928833, "global_step": 411382, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0241799354553223, "global_step": 411383, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.096128225326538, "global_step": 411384, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.123532295227051, "global_step": 411385, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.073207378387451, "global_step": 411386, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.088557243347168, "global_step": 411387, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.007103204727173, "global_step": 411388, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0275468826293945, "global_step": 411389, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1600308418273926, "global_step": 411390, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.123180866241455, "global_step": 411391, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.115858554840088, "global_step": 411392, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0367960929870605, "global_step": 411393, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1235554218292236, "global_step": 411394, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.090304136276245, "global_step": 411395, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1657626628875732, "global_step": 411396, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1121625900268555, "global_step": 411397, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1501009464263916, "global_step": 411398, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.15816068649292, "global_step": 411399, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.051661729812622, "global_step": 411400, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0072968006134033, "global_step": 411401, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0217580795288086, "global_step": 411402, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1301610469818115, "global_step": 411403, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.075702667236328, "global_step": 411404, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0374064445495605, "global_step": 411405, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0802602767944336, "global_step": 411406, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0615932941436768, "global_step": 411407, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0159356594085693, "global_step": 411408, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.161761522293091, "global_step": 411409, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.140449047088623, "global_step": 411410, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.107607841491699, "global_step": 411411, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.10208797454834, "global_step": 411412, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1546404361724854, "global_step": 411413, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0485801696777344, "global_step": 411414, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1830239295959473, "global_step": 411415, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.066425323486328, "global_step": 411416, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.154165506362915, "global_step": 411417, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.106959342956543, "global_step": 411418, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.100277900695801, "global_step": 411419, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1466522216796875, "global_step": 411420, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.109700918197632, "global_step": 411421, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0751233100891113, "global_step": 411422, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0248196125030518, "global_step": 411423, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.139948606491089, "global_step": 411424, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0369303226470947, "global_step": 411425, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0767624378204346, "global_step": 411426, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1750433444976807, "global_step": 411427, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.095613718032837, "global_step": 411428, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0059242248535156, "global_step": 411429, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9954936504364014, "global_step": 411430, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.109476089477539, "global_step": 411431, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.041029691696167, "global_step": 411432, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1308469772338867, "global_step": 411433, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.020282506942749, "global_step": 411434, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1217293739318848, "global_step": 411435, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0656614303588867, "global_step": 411436, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1250951290130615, "global_step": 411437, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0242087841033936, "global_step": 411438, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0733540058135986, "global_step": 411439, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1835546493530273, "global_step": 411440, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0567657947540283, "global_step": 411441, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.129467725753784, "global_step": 411442, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.082568645477295, "global_step": 411443, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1180121898651123, "global_step": 411444, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0064826011657715, "global_step": 411445, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1945152282714844, "global_step": 411446, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0430495738983154, "global_step": 411447, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.159032106399536, "global_step": 411448, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.089573621749878, "global_step": 411449, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.081834316253662, "global_step": 411450, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.083026647567749, "global_step": 411451, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.046459674835205, "global_step": 411452, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1251602172851562, "global_step": 411453, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.057823896408081, "global_step": 411454, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.08656644821167, "global_step": 411455, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.175511598587036, "global_step": 411456, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.109261989593506, "global_step": 411457, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.098315954208374, "global_step": 411458, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1190943717956543, "global_step": 411459, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.037842273712158, "global_step": 411460, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0552241802215576, "global_step": 411461, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0997979640960693, "global_step": 411462, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.108041763305664, "global_step": 411463, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.133333206176758, "global_step": 411464, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.011436939239502, "global_step": 411465, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9859890937805176, "global_step": 411466, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.022714138031006, "global_step": 411467, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0231192111968994, "global_step": 411468, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0566887855529785, "global_step": 411469, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1363136768341064, "global_step": 411470, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0298855304718018, "global_step": 411471, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0780868530273438, "global_step": 411472, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0273542404174805, "global_step": 411473, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1073453426361084, "global_step": 411474, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.045154333114624, "global_step": 411475, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0846903324127197, "global_step": 411476, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.098006248474121, "global_step": 411477, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1813430786132812, "global_step": 411478, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0716023445129395, "global_step": 411479, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.10036039352417, "global_step": 411480, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1282174587249756, "global_step": 411481, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0843844413757324, "global_step": 411482, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.105285167694092, "global_step": 411483, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1186931133270264, "global_step": 411484, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.143167734146118, "global_step": 411485, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0644149780273438, "global_step": 411486, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1056065559387207, "global_step": 411487, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.2128689289093018, "global_step": 411488, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0464770793914795, "global_step": 411489, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0392024517059326, "global_step": 411490, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.115978717803955, "global_step": 411491, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0788798332214355, "global_step": 411492, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1032629013061523, "global_step": 411493, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0798840522766113, "global_step": 411494, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.097424268722534, "global_step": 411495, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0752151012420654, "global_step": 411496, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1811599731445312, "global_step": 411497, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.038339614868164, "global_step": 411498, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1479756832122803, "global_step": 411499, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.192284107208252, "global_step": 411500, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.116992950439453, "global_step": 411501, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0101094245910645, "global_step": 411502, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.2309606075286865, "global_step": 411503, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.039222240447998, "global_step": 411504, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0646047592163086, "global_step": 411505, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0375380516052246, "global_step": 411506, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.049762010574341, "global_step": 411507, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0992257595062256, "global_step": 411508, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0008034706115723, "global_step": 411509, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.002916097640991, "global_step": 411510, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1846375465393066, "global_step": 411511, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0865888595581055, "global_step": 411512, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1107866764068604, "global_step": 411513, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0985782146453857, "global_step": 411514, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0580499172210693, "global_step": 411515, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0977864265441895, "global_step": 411516, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0814595222473145, "global_step": 411517, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0959372520446777, "global_step": 411518, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1544759273529053, "global_step": 411519, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0724422931671143, "global_step": 411520, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0660531520843506, "global_step": 411521, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9797717332839966, "global_step": 411522, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0355050563812256, "global_step": 411523, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0790140628814697, "global_step": 411524, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0622942447662354, "global_step": 411525, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.085512638092041, "global_step": 411526, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.132277250289917, "global_step": 411527, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.106039524078369, "global_step": 411528, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0448713302612305, "global_step": 411529, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0946459770202637, "global_step": 411530, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.210073232650757, "global_step": 411531, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.118305206298828, "global_step": 411532, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1027228832244873, "global_step": 411533, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.00498628616333, "global_step": 411534, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0767314434051514, "global_step": 411535, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1660494804382324, "global_step": 411536, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.042689085006714, "global_step": 411537, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.056525468826294, "global_step": 411538, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1789848804473877, "global_step": 411539, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0253140926361084, "global_step": 411540, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.128242015838623, "global_step": 411541, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1337332725524902, "global_step": 411542, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1462481021881104, "global_step": 411543, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.136526584625244, "global_step": 411544, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0669655799865723, "global_step": 411545, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.168001413345337, "global_step": 411546, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1464056968688965, "global_step": 411547, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0242888927459717, "global_step": 411548, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.037158489227295, "global_step": 411549, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1537556648254395, "global_step": 411550, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0161802768707275, "global_step": 411551, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0530664920806885, "global_step": 411552, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0337681770324707, "global_step": 411553, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0875697135925293, "global_step": 411554, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1207470893859863, "global_step": 411555, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.083221673965454, "global_step": 411556, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.041527509689331, "global_step": 411557, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0833451747894287, "global_step": 411558, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.079798460006714, "global_step": 411559, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0628650188446045, "global_step": 411560, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0537898540496826, "global_step": 411561, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0996758937835693, "global_step": 411562, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.038954973220825, "global_step": 411563, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.131777048110962, "global_step": 411564, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0602447986602783, "global_step": 411565, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0644750595092773, "global_step": 411566, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.05118989944458, "global_step": 411567, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.2024450302124023, "global_step": 411568, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0866479873657227, "global_step": 411569, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1914405822753906, "global_step": 411570, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1212713718414307, "global_step": 411571, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.127309560775757, "global_step": 411572, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1968820095062256, "global_step": 411573, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.157768726348877, "global_step": 411574, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1761069297790527, "global_step": 411575, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.047288417816162, "global_step": 411576, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1609556674957275, "global_step": 411577, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1137633323669434, "global_step": 411578, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.149305820465088, "global_step": 411579, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0226681232452393, "global_step": 411580, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0559582710266113, "global_step": 411581, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.127890110015869, "global_step": 411582, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.135122299194336, "global_step": 411583, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.011953830718994, "global_step": 411584, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0967202186584473, "global_step": 411585, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1614251136779785, "global_step": 411586, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1026113033294678, "global_step": 411587, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1138312816619873, "global_step": 411588, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1901791095733643, "global_step": 411589, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.030665397644043, "global_step": 411590, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0757699012756348, "global_step": 411591, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1588151454925537, "global_step": 411592, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1883559226989746, "global_step": 411593, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.160916566848755, "global_step": 411594, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.046832799911499, "global_step": 411595, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.049913167953491, "global_step": 411596, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1666934490203857, "global_step": 411597, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.104768991470337, "global_step": 411598, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0998005867004395, "global_step": 411599, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0557634830474854, "global_step": 411600, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0420496463775635, "global_step": 411601, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.097620725631714, "global_step": 411602, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.080453395843506, "global_step": 411603, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1398534774780273, "global_step": 411604, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.2206733226776123, "global_step": 411605, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1705403327941895, "global_step": 411606, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.079742431640625, "global_step": 411607, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.145829677581787, "global_step": 411608, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.012948989868164, "global_step": 411609, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1552090644836426, "global_step": 411610, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.140568494796753, "global_step": 411611, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.063694477081299, "global_step": 411612, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.153006076812744, "global_step": 411613, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.156942129135132, "global_step": 411614, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0545709133148193, "global_step": 411615, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.082233428955078, "global_step": 411616, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1570377349853516, "global_step": 411617, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0537209510803223, "global_step": 411618, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0909955501556396, "global_step": 411619, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.119706153869629, "global_step": 411620, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1671934127807617, "global_step": 411621, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.126927375793457, "global_step": 411622, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1354153156280518, "global_step": 411623, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0852913856506348, "global_step": 411624, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.043576955795288, "global_step": 411625, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.041926860809326, "global_step": 411626, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.015070676803589, "global_step": 411627, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1012136936187744, "global_step": 411628, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0461835861206055, "global_step": 411629, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1056573390960693, "global_step": 411630, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0538887977600098, "global_step": 411631, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.050861358642578, "global_step": 411632, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0713744163513184, "global_step": 411633, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0262246131896973, "global_step": 411634, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0750248432159424, "global_step": 411635, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.118462562561035, "global_step": 411636, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0988659858703613, "global_step": 411637, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0950114727020264, "global_step": 411638, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1074275970458984, "global_step": 411639, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9960085153579712, "global_step": 411640, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0944528579711914, "global_step": 411641, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.137376070022583, "global_step": 411642, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1419551372528076, "global_step": 411643, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1259942054748535, "global_step": 411644, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.153085470199585, "global_step": 411645, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.13706111907959, "global_step": 411646, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1547441482543945, "global_step": 411647, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0727293491363525, "global_step": 411648, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.120743989944458, "global_step": 411649, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9888134002685547, "global_step": 411650, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0578904151916504, "global_step": 411651, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.222740888595581, "global_step": 411652, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1400833129882812, "global_step": 411653, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1718392372131348, "global_step": 411654, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0989909172058105, "global_step": 411655, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0845112800598145, "global_step": 411656, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1096115112304688, "global_step": 411657, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0459632873535156, "global_step": 411658, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1349825859069824, "global_step": 411659, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.127101421356201, "global_step": 411660, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.135948657989502, "global_step": 411661, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1027772426605225, "global_step": 411662, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.157043218612671, "global_step": 411663, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.138634204864502, "global_step": 411664, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.140059232711792, "global_step": 411665, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1147890090942383, "global_step": 411666, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.074962615966797, "global_step": 411667, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1240170001983643, "global_step": 411668, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0889461040496826, "global_step": 411669, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.158318519592285, "global_step": 411670, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.06431245803833, "global_step": 411671, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.099031686782837, "global_step": 411672, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.234583616256714, "global_step": 411673, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0807058811187744, "global_step": 411674, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.083306312561035, "global_step": 411675, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.027418613433838, "global_step": 411676, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0957236289978027, "global_step": 411677, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.086097002029419, "global_step": 411678, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.107964038848877, "global_step": 411679, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.14308762550354, "global_step": 411680, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.085597038269043, "global_step": 411681, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0271213054656982, "global_step": 411682, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1867878437042236, "global_step": 411683, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.121251344680786, "global_step": 411684, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1486620903015137, "global_step": 411685, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1586012840270996, "global_step": 411686, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.139094591140747, "global_step": 411687, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0571675300598145, "global_step": 411688, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.087827682495117, "global_step": 411689, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0285136699676514, "global_step": 411690, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.082852840423584, "global_step": 411691, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.164297580718994, "global_step": 411692, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1166040897369385, "global_step": 411693, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.181943893432617, "global_step": 411694, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0479893684387207, "global_step": 411695, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1720306873321533, "global_step": 411696, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.01192045211792, "global_step": 411697, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.126727342605591, "global_step": 411698, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0116021633148193, "global_step": 411699, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1244940757751465, "global_step": 411700, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0925512313842773, "global_step": 411701, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0529181957244873, "global_step": 411702, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.098809242248535, "global_step": 411703, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.154837131500244, "global_step": 411704, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1207563877105713, "global_step": 411705, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0167171955108643, "global_step": 411706, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1246042251586914, "global_step": 411707, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.158451795578003, "global_step": 411708, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1059226989746094, "global_step": 411709, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.166360378265381, "global_step": 411710, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1478443145751953, "global_step": 411711, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.169633626937866, "global_step": 411712, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0584793090820312, "global_step": 411713, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1416144371032715, "global_step": 411714, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0402541160583496, "global_step": 411715, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1162381172180176, "global_step": 411716, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1572554111480713, "global_step": 411717, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.174136161804199, "global_step": 411718, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0552635192871094, "global_step": 411719, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1250829696655273, "global_step": 411720, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1049580574035645, "global_step": 411721, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1302261352539062, "global_step": 411722, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.038888692855835, "global_step": 411723, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0616092681884766, "global_step": 411724, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9769307374954224, "global_step": 411725, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.015018939971924, "global_step": 411726, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.079155445098877, "global_step": 411727, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.158048152923584, "global_step": 411728, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.053269624710083, "global_step": 411729, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.053985595703125, "global_step": 411730, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0698914527893066, "global_step": 411731, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0623419284820557, "global_step": 411732, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.137279748916626, "global_step": 411733, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.100480318069458, "global_step": 411734, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9898453950881958, "global_step": 411735, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1425178050994873, "global_step": 411736, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1046574115753174, "global_step": 411737, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0942673683166504, "global_step": 411738, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1390645503997803, "global_step": 411739, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0644145011901855, "global_step": 411740, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.090297222137451, "global_step": 411741, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0809969902038574, "global_step": 411742, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.145765781402588, "global_step": 411743, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.067197322845459, "global_step": 411744, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1174848079681396, "global_step": 411745, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9961966276168823, "global_step": 411746, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1498184204101562, "global_step": 411747, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1191656589508057, "global_step": 411748, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.09978985786438, "global_step": 411749, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1154487133026123, "global_step": 411750, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.06551194190979, "global_step": 411751, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0712289810180664, "global_step": 411752, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.173724412918091, "global_step": 411753, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.228720188140869, "global_step": 411754, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0794036388397217, "global_step": 411755, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1042542457580566, "global_step": 411756, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0421335697174072, "global_step": 411757, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.127532482147217, "global_step": 411758, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0406203269958496, "global_step": 411759, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1032392978668213, "global_step": 411760, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.113853931427002, "global_step": 411761, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0556490421295166, "global_step": 411762, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0223374366760254, "global_step": 411763, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1282057762145996, "global_step": 411764, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1257243156433105, "global_step": 411765, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1266136169433594, "global_step": 411766, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0174591541290283, "global_step": 411767, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0480897426605225, "global_step": 411768, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.21093487739563, "global_step": 411769, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0784332752227783, "global_step": 411770, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.005321502685547, "global_step": 411771, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.140660285949707, "global_step": 411772, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0995802879333496, "global_step": 411773, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.071108102798462, "global_step": 411774, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.081620693206787, "global_step": 411775, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1410772800445557, "global_step": 411776, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.149907112121582, "global_step": 411777, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0502960681915283, "global_step": 411778, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9676238298416138, "global_step": 411779, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.187758445739746, "global_step": 411780, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0601046085357666, "global_step": 411781, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0842576026916504, "global_step": 411782, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1433491706848145, "global_step": 411783, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0833206176757812, "global_step": 411784, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.163630962371826, "global_step": 411785, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.106696128845215, "global_step": 411786, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0235238075256348, "global_step": 411787, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1429896354675293, "global_step": 411788, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.145103693008423, "global_step": 411789, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.115230083465576, "global_step": 411790, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.107198715209961, "global_step": 411791, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.170600652694702, "global_step": 411792, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.051706075668335, "global_step": 411793, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1356661319732666, "global_step": 411794, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.048062324523926, "global_step": 411795, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.028519630432129, "global_step": 411796, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1154072284698486, "global_step": 411797, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.069629430770874, "global_step": 411798, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0392959117889404, "global_step": 411799, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0093936920166016, "global_step": 411800, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.147204637527466, "global_step": 411801, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.106773853302002, "global_step": 411802, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.045215129852295, "global_step": 411803, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0270910263061523, "global_step": 411804, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1579298973083496, "global_step": 411805, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.14921498298645, "global_step": 411806, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0305590629577637, "global_step": 411807, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.067448377609253, "global_step": 411808, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0868539810180664, "global_step": 411809, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.064220905303955, "global_step": 411810, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.061947822570801, "global_step": 411811, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.074932098388672, "global_step": 411812, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0366504192352295, "global_step": 411813, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.038857936859131, "global_step": 411814, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0604164600372314, "global_step": 411815, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.119046449661255, "global_step": 411816, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.111264705657959, "global_step": 411817, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9617425203323364, "global_step": 411818, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0441629886627197, "global_step": 411819, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1464169025421143, "global_step": 411820, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.133117914199829, "global_step": 411821, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.121767282485962, "global_step": 411822, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0291738510131836, "global_step": 411823, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.109412908554077, "global_step": 411824, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.081002950668335, "global_step": 411825, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1385929584503174, "global_step": 411826, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.06699800491333, "global_step": 411827, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0816164016723633, "global_step": 411828, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1710546016693115, "global_step": 411829, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.060436487197876, "global_step": 411830, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0728719234466553, "global_step": 411831, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0443849563598633, "global_step": 411832, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.120415687561035, "global_step": 411833, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0389490127563477, "global_step": 411834, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9841586351394653, "global_step": 411835, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0228660106658936, "global_step": 411836, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1197850704193115, "global_step": 411837, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.060943126678467, "global_step": 411838, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.051842212677002, "global_step": 411839, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1517956256866455, "global_step": 411840, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.11796498298645, "global_step": 411841, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.038534164428711, "global_step": 411842, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1187825202941895, "global_step": 411843, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.126967191696167, "global_step": 411844, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.127012252807617, "global_step": 411845, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.066227912902832, "global_step": 411846, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1459527015686035, "global_step": 411847, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1956353187561035, "global_step": 411848, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.210049629211426, "global_step": 411849, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0019562244415283, "global_step": 411850, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.173894166946411, "global_step": 411851, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0640366077423096, "global_step": 411852, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0275096893310547, "global_step": 411853, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.121823787689209, "global_step": 411854, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.104905843734741, "global_step": 411855, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.075003147125244, "global_step": 411856, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.100562572479248, "global_step": 411857, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1002230644226074, "global_step": 411858, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.2249345779418945, "global_step": 411859, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1668012142181396, "global_step": 411860, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0564894676208496, "global_step": 411861, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.089233160018921, "global_step": 411862, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.086451768875122, "global_step": 411863, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1567625999450684, "global_step": 411864, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.105253219604492, "global_step": 411865, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1454694271087646, "global_step": 411866, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.068424940109253, "global_step": 411867, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1020586490631104, "global_step": 411868, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0929126739501953, "global_step": 411869, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.043367862701416, "global_step": 411870, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.05065655708313, "global_step": 411871, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1129751205444336, "global_step": 411872, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.065202236175537, "global_step": 411873, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.176567316055298, "global_step": 411874, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1272225379943848, "global_step": 411875, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.11396861076355, "global_step": 411876, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0988211631774902, "global_step": 411877, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.119382381439209, "global_step": 411878, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.021528482437134, "global_step": 411879, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0839755535125732, "global_step": 411880, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.134249448776245, "global_step": 411881, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0095207691192627, "global_step": 411882, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.07780385017395, "global_step": 411883, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.093672037124634, "global_step": 411884, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.200892448425293, "global_step": 411885, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1541805267333984, "global_step": 411886, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0670464038848877, "global_step": 411887, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0650713443756104, "global_step": 411888, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.15816593170166, "global_step": 411889, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1830737590789795, "global_step": 411890, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0816102027893066, "global_step": 411891, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0863468647003174, "global_step": 411892, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1226329803466797, "global_step": 411893, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.211583375930786, "global_step": 411894, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.058778762817383, "global_step": 411895, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1110434532165527, "global_step": 411896, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.04377818107605, "global_step": 411897, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0290565490722656, "global_step": 411898, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1910526752471924, "global_step": 411899, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9883849620819092, "global_step": 411900, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0850889682769775, "global_step": 411901, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.117995262145996, "global_step": 411902, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1711537837982178, "global_step": 411903, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0431485176086426, "global_step": 411904, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0718367099761963, "global_step": 411905, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.111096143722534, "global_step": 411906, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.101750373840332, "global_step": 411907, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0669069290161133, "global_step": 411908, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.089381694793701, "global_step": 411909, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0991015434265137, "global_step": 411910, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0767054557800293, "global_step": 411911, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.100970983505249, "global_step": 411912, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.095583438873291, "global_step": 411913, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.045856237411499, "global_step": 411914, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1122279167175293, "global_step": 411915, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.132267951965332, "global_step": 411916, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.132922410964966, "global_step": 411917, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.109161376953125, "global_step": 411918, "epoch": 774, "lr": 5e-05}
{"train_loss": 1.9774843454360962, "global_step": 411919, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1709964275360107, "global_step": 411920, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0757296085357666, "global_step": 411921, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0547914505004883, "global_step": 411922, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.089890241622925, "global_step": 411923, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1225430965423584, "global_step": 411924, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.089005708694458, "global_step": 411925, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0185670852661133, "global_step": 411926, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1683411598205566, "global_step": 411927, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.156897783279419, "global_step": 411928, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.087775230407715, "global_step": 411929, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.060821294784546, "global_step": 411930, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.155083417892456, "global_step": 411931, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0850777626037598, "global_step": 411932, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.13458514213562, "global_step": 411933, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.127004861831665, "global_step": 411934, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0765199661254883, "global_step": 411935, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.140312671661377, "global_step": 411936, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0455920696258545, "global_step": 411937, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.101681709289551, "global_step": 411938, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.111469268798828, "global_step": 411939, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.115319013595581, "global_step": 411940, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.101823091506958, "global_step": 411941, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.024890899658203, "global_step": 411942, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1289355754852295, "global_step": 411943, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0880026817321777, "global_step": 411944, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0829017162323, "global_step": 411945, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.109074831008911, "global_step": 411946, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1124563217163086, "global_step": 411947, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0424578189849854, "global_step": 411948, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.077167510986328, "global_step": 411949, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0376269817352295, "global_step": 411950, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0081400871276855, "global_step": 411951, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.043855667114258, "global_step": 411952, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.032439708709717, "global_step": 411953, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.076765298843384, "global_step": 411954, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1711771488189697, "global_step": 411955, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.1541354656219482, "global_step": 411956, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.0907394886016846, "global_step": 411957, "epoch": 774, "lr": 5e-05}
{"train_loss": 2.058384656906128, "global_step": 411958, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.126119613647461, "global_step": 411959, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1510961055755615, "global_step": 411960, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.09946870803833, "global_step": 411961, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0406723022460938, "global_step": 411962, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.034508466720581, "global_step": 411963, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.156365156173706, "global_step": 411964, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.15449595451355, "global_step": 411965, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0653269290924072, "global_step": 411966, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1152453422546387, "global_step": 411967, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1324620246887207, "global_step": 411968, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.049208402633667, "global_step": 411969, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.2348735332489014, "global_step": 411970, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.079411268234253, "global_step": 411971, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0135982036590576, "global_step": 411972, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.088636636734009, "global_step": 411973, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1758596897125244, "global_step": 411974, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.051923990249634, "global_step": 411975, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.150428533554077, "global_step": 411976, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.078496217727661, "global_step": 411977, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.03165602684021, "global_step": 411978, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.012131452560425, "global_step": 411979, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1656441688537598, "global_step": 411980, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1142284870147705, "global_step": 411981, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0691263675689697, "global_step": 411982, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.018115758895874, "global_step": 411983, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.112365484237671, "global_step": 411984, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.055678129196167, "global_step": 411985, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0910723209381104, "global_step": 411986, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.163818597793579, "global_step": 411987, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0256786346435547, "global_step": 411988, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1070754528045654, "global_step": 411989, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.094867467880249, "global_step": 411990, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1057140827178955, "global_step": 411991, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0498976707458496, "global_step": 411992, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.100961446762085, "global_step": 411993, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0988452434539795, "global_step": 411994, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1001851558685303, "global_step": 411995, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1201436519622803, "global_step": 411996, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.065709114074707, "global_step": 411997, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.001006603240967, "global_step": 411998, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0987582206726074, "global_step": 411999, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.081110954284668, "global_step": 412000, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.095184803009033, "global_step": 412001, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0591320991516113, "global_step": 412002, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.029184341430664, "global_step": 412003, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0881595611572266, "global_step": 412004, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0685575008392334, "global_step": 412005, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0813498497009277, "global_step": 412006, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1132020950317383, "global_step": 412007, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.2159922122955322, "global_step": 412008, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0140581130981445, "global_step": 412009, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.149509906768799, "global_step": 412010, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0328338146209717, "global_step": 412011, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0583460330963135, "global_step": 412012, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0558853149414062, "global_step": 412013, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.061321496963501, "global_step": 412014, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.06565260887146, "global_step": 412015, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0784428119659424, "global_step": 412016, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0312516689300537, "global_step": 412017, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.134033203125, "global_step": 412018, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.072704553604126, "global_step": 412019, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.166637420654297, "global_step": 412020, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.061821222305298, "global_step": 412021, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.053893566131592, "global_step": 412022, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0365450382232666, "global_step": 412023, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0134871006011963, "global_step": 412024, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.005312204360962, "global_step": 412025, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.119607925415039, "global_step": 412026, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1259641647338867, "global_step": 412027, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.077920436859131, "global_step": 412028, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.2123703956604004, "global_step": 412029, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0047998428344727, "global_step": 412030, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.10549259185791, "global_step": 412031, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.098356008529663, "global_step": 412032, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0326027870178223, "global_step": 412033, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.158242702484131, "global_step": 412034, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0469417572021484, "global_step": 412035, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1709463596343994, "global_step": 412036, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0781636238098145, "global_step": 412037, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1624081134796143, "global_step": 412038, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0867228507995605, "global_step": 412039, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.022059440612793, "global_step": 412040, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0251505374908447, "global_step": 412041, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.117241621017456, "global_step": 412042, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0725979804992676, "global_step": 412043, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.032276153564453, "global_step": 412044, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9531012773513794, "global_step": 412045, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1202504634857178, "global_step": 412046, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1269285678863525, "global_step": 412047, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.134005308151245, "global_step": 412048, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.031259298324585, "global_step": 412049, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0815210342407227, "global_step": 412050, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.045431613922119, "global_step": 412051, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1382784843444824, "global_step": 412052, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0809824466705322, "global_step": 412053, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.167231559753418, "global_step": 412054, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.115114688873291, "global_step": 412055, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1309454441070557, "global_step": 412056, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1138153076171875, "global_step": 412057, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9962788820266724, "global_step": 412058, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1020281314849854, "global_step": 412059, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.117271900177002, "global_step": 412060, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0998291969299316, "global_step": 412061, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9811055660247803, "global_step": 412062, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.079040050506592, "global_step": 412063, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0990712642669678, "global_step": 412064, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1402382850646973, "global_step": 412065, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1480793952941895, "global_step": 412066, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.003228187561035, "global_step": 412067, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.105905771255493, "global_step": 412068, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.068128824234009, "global_step": 412069, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.087176561355591, "global_step": 412070, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0766525268554688, "global_step": 412071, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.073082447052002, "global_step": 412072, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1488664150238037, "global_step": 412073, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.070329427719116, "global_step": 412074, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1030163764953613, "global_step": 412075, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0730888843536377, "global_step": 412076, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0472896099090576, "global_step": 412077, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0894582271575928, "global_step": 412078, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1520466804504395, "global_step": 412079, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.108830213546753, "global_step": 412080, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.094618797302246, "global_step": 412081, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9329040050506592, "global_step": 412082, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0776405334472656, "global_step": 412083, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1610264778137207, "global_step": 412084, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0695276260375977, "global_step": 412085, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.107414960861206, "global_step": 412086, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1129515171051025, "global_step": 412087, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.189711809158325, "global_step": 412088, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0466339588165283, "global_step": 412089, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.091656446456909, "global_step": 412090, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9919131994247437, "global_step": 412091, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.106064796447754, "global_step": 412092, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.207493782043457, "global_step": 412093, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1205387115478516, "global_step": 412094, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.107783794403076, "global_step": 412095, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1455960273742676, "global_step": 412096, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.024226665496826, "global_step": 412097, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.111140251159668, "global_step": 412098, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9904924631118774, "global_step": 412099, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0741403102874756, "global_step": 412100, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0579802989959717, "global_step": 412101, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.098935842514038, "global_step": 412102, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1018733978271484, "global_step": 412103, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0666534900665283, "global_step": 412104, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0666282176971436, "global_step": 412105, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0288474559783936, "global_step": 412106, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.047783374786377, "global_step": 412107, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0936262607574463, "global_step": 412108, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0499589443206787, "global_step": 412109, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1153934001922607, "global_step": 412110, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0363411903381348, "global_step": 412111, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0772361755371094, "global_step": 412112, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.128493547439575, "global_step": 412113, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.072638988494873, "global_step": 412114, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.113100290298462, "global_step": 412115, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1599628925323486, "global_step": 412116, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0861196517944336, "global_step": 412117, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.15521240234375, "global_step": 412118, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0210914611816406, "global_step": 412119, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0855939388275146, "global_step": 412120, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.011061429977417, "global_step": 412121, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.087364435195923, "global_step": 412122, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1399521827697754, "global_step": 412123, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.083397388458252, "global_step": 412124, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0673484802246094, "global_step": 412125, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0039801597595215, "global_step": 412126, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0919718742370605, "global_step": 412127, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9863028526306152, "global_step": 412128, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.050499439239502, "global_step": 412129, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.119765043258667, "global_step": 412130, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1439356803894043, "global_step": 412131, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0990238189697266, "global_step": 412132, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0929484367370605, "global_step": 412133, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0223076343536377, "global_step": 412134, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1163487434387207, "global_step": 412135, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0898587703704834, "global_step": 412136, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0583033561706543, "global_step": 412137, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.086508274078369, "global_step": 412138, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1430583000183105, "global_step": 412139, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.122734546661377, "global_step": 412140, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.069322109222412, "global_step": 412141, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1586029529571533, "global_step": 412142, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0294761657714844, "global_step": 412143, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1186389923095703, "global_step": 412144, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1637210845947266, "global_step": 412145, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1444294452667236, "global_step": 412146, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.261901617050171, "global_step": 412147, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.121567487716675, "global_step": 412148, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.107576847076416, "global_step": 412149, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.104708671569824, "global_step": 412150, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.055866241455078, "global_step": 412151, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1085124015808105, "global_step": 412152, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.105933427810669, "global_step": 412153, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9395020008087158, "global_step": 412154, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0713677406311035, "global_step": 412155, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9999847412109375, "global_step": 412156, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.099587917327881, "global_step": 412157, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.02150297164917, "global_step": 412158, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0562472343444824, "global_step": 412159, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.056640625, "global_step": 412160, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.137223243713379, "global_step": 412161, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1114702224731445, "global_step": 412162, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.2030155658721924, "global_step": 412163, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.066932439804077, "global_step": 412164, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0559723377227783, "global_step": 412165, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1098473072052, "global_step": 412166, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0981409549713135, "global_step": 412167, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.124210834503174, "global_step": 412168, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.097958564758301, "global_step": 412169, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9684172868728638, "global_step": 412170, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.078204870223999, "global_step": 412171, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0285191535949707, "global_step": 412172, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0714035034179688, "global_step": 412173, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9913874864578247, "global_step": 412174, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.067909002304077, "global_step": 412175, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1031723022460938, "global_step": 412176, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.064826488494873, "global_step": 412177, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9954553842544556, "global_step": 412178, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1612284183502197, "global_step": 412179, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0665407180786133, "global_step": 412180, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.04885196685791, "global_step": 412181, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0165255069732666, "global_step": 412182, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0130512714385986, "global_step": 412183, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1808457374572754, "global_step": 412184, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1286277770996094, "global_step": 412185, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0895400047302246, "global_step": 412186, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1251866817474365, "global_step": 412187, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0541892051696777, "global_step": 412188, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.147454261779785, "global_step": 412189, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1083288192749023, "global_step": 412190, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.093111276626587, "global_step": 412191, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.128046989440918, "global_step": 412192, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0609631538391113, "global_step": 412193, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0875070095062256, "global_step": 412194, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9838323593139648, "global_step": 412195, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0297579765319824, "global_step": 412196, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1395506858825684, "global_step": 412197, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1249661445617676, "global_step": 412198, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.123074531555176, "global_step": 412199, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.044187307357788, "global_step": 412200, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.050915241241455, "global_step": 412201, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1224348545074463, "global_step": 412202, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0672073364257812, "global_step": 412203, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.040691375732422, "global_step": 412204, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.01358699798584, "global_step": 412205, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.060786008834839, "global_step": 412206, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.088263750076294, "global_step": 412207, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0384109020233154, "global_step": 412208, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0318355560302734, "global_step": 412209, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.03147292137146, "global_step": 412210, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.072359085083008, "global_step": 412211, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.039470672607422, "global_step": 412212, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.063830614089966, "global_step": 412213, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0617101192474365, "global_step": 412214, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.074528694152832, "global_step": 412215, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0157361030578613, "global_step": 412216, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.072296380996704, "global_step": 412217, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0904386043548584, "global_step": 412218, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.073657274246216, "global_step": 412219, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.014857292175293, "global_step": 412220, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.124711513519287, "global_step": 412221, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.105924129486084, "global_step": 412222, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.129650592803955, "global_step": 412223, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.073451519012451, "global_step": 412224, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.065366506576538, "global_step": 412225, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.089832067489624, "global_step": 412226, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0840582847595215, "global_step": 412227, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0745208263397217, "global_step": 412228, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.135981798171997, "global_step": 412229, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.051654815673828, "global_step": 412230, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1566720008850098, "global_step": 412231, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1127467155456543, "global_step": 412232, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1114699840545654, "global_step": 412233, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.996939778327942, "global_step": 412234, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0669960975646973, "global_step": 412235, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.006505250930786, "global_step": 412236, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1363580226898193, "global_step": 412237, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.2610175609588623, "global_step": 412238, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.065831422805786, "global_step": 412239, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0784366130828857, "global_step": 412240, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.039357900619507, "global_step": 412241, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0822041034698486, "global_step": 412242, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.139625072479248, "global_step": 412243, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0994906425476074, "global_step": 412244, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0602452754974365, "global_step": 412245, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0536959171295166, "global_step": 412246, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0474348068237305, "global_step": 412247, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0802955627441406, "global_step": 412248, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0854954719543457, "global_step": 412249, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9847195148468018, "global_step": 412250, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.108767032623291, "global_step": 412251, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1190600395202637, "global_step": 412252, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0569238662719727, "global_step": 412253, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.053009033203125, "global_step": 412254, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.121964693069458, "global_step": 412255, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.094647169113159, "global_step": 412256, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0678441524505615, "global_step": 412257, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1919991970062256, "global_step": 412258, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.095471143722534, "global_step": 412259, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.119112491607666, "global_step": 412260, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0809881687164307, "global_step": 412261, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.136765241622925, "global_step": 412262, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.074444055557251, "global_step": 412263, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1616714000701904, "global_step": 412264, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.2357592582702637, "global_step": 412265, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1206068992614746, "global_step": 412266, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1665077209472656, "global_step": 412267, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0744009017944336, "global_step": 412268, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0940234661102295, "global_step": 412269, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.121062994003296, "global_step": 412270, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.122452735900879, "global_step": 412271, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1277425289154053, "global_step": 412272, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1095802783966064, "global_step": 412273, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1026391983032227, "global_step": 412274, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.052982807159424, "global_step": 412275, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.163241386413574, "global_step": 412276, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.096237897872925, "global_step": 412277, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1466763019561768, "global_step": 412278, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1143782138824463, "global_step": 412279, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0927767753601074, "global_step": 412280, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.034698963165283, "global_step": 412281, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.155116319656372, "global_step": 412282, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1645216941833496, "global_step": 412283, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1516358852386475, "global_step": 412284, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.162658214569092, "global_step": 412285, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0562796592712402, "global_step": 412286, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.121941089630127, "global_step": 412287, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1071865558624268, "global_step": 412288, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.075259208679199, "global_step": 412289, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0795552730560303, "global_step": 412290, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0927464962005615, "global_step": 412291, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0670166015625, "global_step": 412292, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0761098861694336, "global_step": 412293, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.08854341506958, "global_step": 412294, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1158461570739746, "global_step": 412295, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0797626972198486, "global_step": 412296, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1432912349700928, "global_step": 412297, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0438456535339355, "global_step": 412298, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0979487895965576, "global_step": 412299, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.079163074493408, "global_step": 412300, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0620834827423096, "global_step": 412301, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0008342266082764, "global_step": 412302, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1664817333221436, "global_step": 412303, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1067960262298584, "global_step": 412304, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.079674243927002, "global_step": 412305, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1719844341278076, "global_step": 412306, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.090219020843506, "global_step": 412307, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0572235584259033, "global_step": 412308, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0301425457000732, "global_step": 412309, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.07529354095459, "global_step": 412310, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1814966201782227, "global_step": 412311, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0442957878112793, "global_step": 412312, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.021679162979126, "global_step": 412313, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0120556354522705, "global_step": 412314, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1621477603912354, "global_step": 412315, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0541088581085205, "global_step": 412316, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0742058753967285, "global_step": 412317, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1731715202331543, "global_step": 412318, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0826003551483154, "global_step": 412319, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.050058603286743, "global_step": 412320, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.083325147628784, "global_step": 412321, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.157740354537964, "global_step": 412322, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0548737049102783, "global_step": 412323, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1199069023132324, "global_step": 412324, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.027482271194458, "global_step": 412325, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.157700538635254, "global_step": 412326, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1391053199768066, "global_step": 412327, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.16256046295166, "global_step": 412328, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.132420301437378, "global_step": 412329, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.030877113342285, "global_step": 412330, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.15333890914917, "global_step": 412331, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0601062774658203, "global_step": 412332, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.124838352203369, "global_step": 412333, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0357260704040527, "global_step": 412334, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.097177505493164, "global_step": 412335, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0384137630462646, "global_step": 412336, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0739595890045166, "global_step": 412337, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1251091957092285, "global_step": 412338, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.069319725036621, "global_step": 412339, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1627392768859863, "global_step": 412340, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0724337100982666, "global_step": 412341, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.064143657684326, "global_step": 412342, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1726505756378174, "global_step": 412343, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.058372974395752, "global_step": 412344, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0819056034088135, "global_step": 412345, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.153679609298706, "global_step": 412346, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1160597801208496, "global_step": 412347, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0814168453216553, "global_step": 412348, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0784685611724854, "global_step": 412349, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.065200090408325, "global_step": 412350, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0280940532684326, "global_step": 412351, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0416598320007324, "global_step": 412352, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9745968580245972, "global_step": 412353, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1211600303649902, "global_step": 412354, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1101138591766357, "global_step": 412355, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0969440937042236, "global_step": 412356, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0173499584198, "global_step": 412357, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0843496322631836, "global_step": 412358, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0642590522766113, "global_step": 412359, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1015589237213135, "global_step": 412360, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1940066814422607, "global_step": 412361, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.050621747970581, "global_step": 412362, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0392849445343018, "global_step": 412363, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.980408787727356, "global_step": 412364, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0733959674835205, "global_step": 412365, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.169813394546509, "global_step": 412366, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.111600399017334, "global_step": 412367, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0407261848449707, "global_step": 412368, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0535476207733154, "global_step": 412369, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1482789516448975, "global_step": 412370, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1789135932922363, "global_step": 412371, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.996372103691101, "global_step": 412372, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1925477981567383, "global_step": 412373, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1343533992767334, "global_step": 412374, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.082113027572632, "global_step": 412375, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.114672899246216, "global_step": 412376, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.079777717590332, "global_step": 412377, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.073331832885742, "global_step": 412378, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.118803024291992, "global_step": 412379, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1276707649230957, "global_step": 412380, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.066680669784546, "global_step": 412381, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.14070725440979, "global_step": 412382, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1253392696380615, "global_step": 412383, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.177056074142456, "global_step": 412384, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0828099250793457, "global_step": 412385, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1689159870147705, "global_step": 412386, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0677573680877686, "global_step": 412387, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0793371200561523, "global_step": 412388, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1657023429870605, "global_step": 412389, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1053543090820312, "global_step": 412390, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0744805335998535, "global_step": 412391, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0817320346832275, "global_step": 412392, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.01539945602417, "global_step": 412393, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.073824644088745, "global_step": 412394, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.077977180480957, "global_step": 412395, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.096510648727417, "global_step": 412396, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1002235412597656, "global_step": 412397, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.232872247695923, "global_step": 412398, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.057405710220337, "global_step": 412399, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.078963279724121, "global_step": 412400, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.11777400970459, "global_step": 412401, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0355803966522217, "global_step": 412402, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.083388090133667, "global_step": 412403, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.039275884628296, "global_step": 412404, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.178151845932007, "global_step": 412405, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.116910934448242, "global_step": 412406, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0580101013183594, "global_step": 412407, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.160170078277588, "global_step": 412408, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1167969703674316, "global_step": 412409, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.025200605392456, "global_step": 412410, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0958430767059326, "global_step": 412411, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1041407585144043, "global_step": 412412, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1116223335266113, "global_step": 412413, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0586884021759033, "global_step": 412414, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0615625381469727, "global_step": 412415, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.089531183242798, "global_step": 412416, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.2478559017181396, "global_step": 412417, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0689780712127686, "global_step": 412418, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.112241268157959, "global_step": 412419, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.070887804031372, "global_step": 412420, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.014199733734131, "global_step": 412421, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.2200262546539307, "global_step": 412422, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.103256940841675, "global_step": 412423, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9788401126861572, "global_step": 412424, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1128809452056885, "global_step": 412425, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1205339431762695, "global_step": 412426, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0902974605560303, "global_step": 412427, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0890512466430664, "global_step": 412428, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0930910110473633, "global_step": 412429, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1134026050567627, "global_step": 412430, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1331570148468018, "global_step": 412431, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0641167163848877, "global_step": 412432, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.145904541015625, "global_step": 412433, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.072317361831665, "global_step": 412434, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.2079126834869385, "global_step": 412435, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.087367296218872, "global_step": 412436, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0801515579223633, "global_step": 412437, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1029746532440186, "global_step": 412438, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.020169973373413, "global_step": 412439, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0846312046051025, "global_step": 412440, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1216886043548584, "global_step": 412441, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0602705478668213, "global_step": 412442, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1004936695098877, "global_step": 412443, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.129892587661743, "global_step": 412444, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1286184787750244, "global_step": 412445, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.094552755355835, "global_step": 412446, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0766708850860596, "global_step": 412447, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0548253059387207, "global_step": 412448, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0189602375030518, "global_step": 412449, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.068873405456543, "global_step": 412450, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0515353679656982, "global_step": 412451, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.117431402206421, "global_step": 412452, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0821125507354736, "global_step": 412453, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.226163148880005, "global_step": 412454, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.109632968902588, "global_step": 412455, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1951892375946045, "global_step": 412456, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.102595090866089, "global_step": 412457, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0845515727996826, "global_step": 412458, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.2125802040100098, "global_step": 412459, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0120346546173096, "global_step": 412460, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.006031036376953, "global_step": 412461, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.040208578109741, "global_step": 412462, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0786685943603516, "global_step": 412463, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0864696502685547, "global_step": 412464, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.086418628692627, "global_step": 412465, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0762076377868652, "global_step": 412466, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0584959983825684, "global_step": 412467, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.180288553237915, "global_step": 412468, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0393450260162354, "global_step": 412469, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0679893493652344, "global_step": 412470, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0457558631896973, "global_step": 412471, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1301610469818115, "global_step": 412472, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.086860418319702, "global_step": 412473, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.165627956390381, "global_step": 412474, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1150593757629395, "global_step": 412475, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1174566745758057, "global_step": 412476, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.107048749923706, "global_step": 412477, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.06838321685791, "global_step": 412478, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1772031784057617, "global_step": 412479, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1515731811523438, "global_step": 412480, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0875089168548584, "global_step": 412481, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1523876190185547, "global_step": 412482, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0753073692321777, "global_step": 412483, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.059288740158081, "global_step": 412484, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0373358726501465, "global_step": 412485, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.020388603210449, "global_step": 412486, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.025803804397583, "global_step": 412487, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1038706302642822, "global_step": 412488, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.011204481124878, "global_step": 412489, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.147796869277954, "global_step": 412490, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0660526752471924, "global_step": 412491, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.103548049926758, "global_step": 412492, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.069375991821289, "global_step": 412493, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.057968854904175, "global_step": 412494, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1687564849853516, "global_step": 412495, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.077017068862915, "global_step": 412496, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0367212295532227, "global_step": 412497, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0840938091278076, "global_step": 412498, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0823142528533936, "global_step": 412499, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.12922739982605, "global_step": 412500, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.134669303894043, "global_step": 412501, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0595953464508057, "global_step": 412502, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.129652500152588, "global_step": 412503, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0725510120391846, "global_step": 412504, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1174750328063965, "global_step": 412505, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1087989807128906, "global_step": 412506, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0932183265686035, "global_step": 412507, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0302505493164062, "global_step": 412508, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.092755079269409, "global_step": 412509, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.107194185256958, "global_step": 412510, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0678586959838867, "global_step": 412511, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.04211163520813, "global_step": 412512, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0360686779022217, "global_step": 412513, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.069331645965576, "global_step": 412514, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0910258293151855, "global_step": 412515, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9732651710510254, "global_step": 412516, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.082606077194214, "global_step": 412517, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0896763801574707, "global_step": 412518, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0741055011749268, "global_step": 412519, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1519482135772705, "global_step": 412520, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1290438175201416, "global_step": 412521, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.2390191555023193, "global_step": 412522, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.063342332839966, "global_step": 412523, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.018195152282715, "global_step": 412524, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0744004249572754, "global_step": 412525, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0252604484558105, "global_step": 412526, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.09627103805542, "global_step": 412527, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.138054609298706, "global_step": 412528, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0923540592193604, "global_step": 412529, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9752476215362549, "global_step": 412530, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0922369956970215, "global_step": 412531, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.116283893585205, "global_step": 412532, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.160041570663452, "global_step": 412533, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.160503625869751, "global_step": 412534, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9752434492111206, "global_step": 412535, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1130735874176025, "global_step": 412536, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1230313777923584, "global_step": 412537, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1596460342407227, "global_step": 412538, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0825366973876953, "global_step": 412539, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.078456401824951, "global_step": 412540, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1598196029663086, "global_step": 412541, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.104017734527588, "global_step": 412542, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1062684059143066, "global_step": 412543, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1584131717681885, "global_step": 412544, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1438844203948975, "global_step": 412545, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1631557941436768, "global_step": 412546, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0873055458068848, "global_step": 412547, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.163512706756592, "global_step": 412548, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.048107147216797, "global_step": 412549, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.126598834991455, "global_step": 412550, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.091582775115967, "global_step": 412551, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0060858726501465, "global_step": 412552, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0670924186706543, "global_step": 412553, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1607444286346436, "global_step": 412554, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0675384998321533, "global_step": 412555, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0225982666015625, "global_step": 412556, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0950825214385986, "global_step": 412557, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0825202465057373, "global_step": 412558, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0755608081817627, "global_step": 412559, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0990326404571533, "global_step": 412560, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0311083793640137, "global_step": 412561, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1044461727142334, "global_step": 412562, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0338263511657715, "global_step": 412563, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0180604457855225, "global_step": 412564, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0661258697509766, "global_step": 412565, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0534045696258545, "global_step": 412566, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1462178230285645, "global_step": 412567, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0382583141326904, "global_step": 412568, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1901886463165283, "global_step": 412569, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0892117023468018, "global_step": 412570, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1086015701293945, "global_step": 412571, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.098173141479492, "global_step": 412572, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.2274856567382812, "global_step": 412573, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.130521774291992, "global_step": 412574, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1365602016448975, "global_step": 412575, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0675482749938965, "global_step": 412576, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0686001777648926, "global_step": 412577, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1505603790283203, "global_step": 412578, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.031977653503418, "global_step": 412579, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1085195541381836, "global_step": 412580, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.023261547088623, "global_step": 412581, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.046208143234253, "global_step": 412582, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0721242427825928, "global_step": 412583, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9871537685394287, "global_step": 412584, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.166379690170288, "global_step": 412585, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.099324941635132, "global_step": 412586, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.104156970977783, "global_step": 412587, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.016306161880493, "global_step": 412588, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0597777366638184, "global_step": 412589, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1267614364624023, "global_step": 412590, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0945241451263428, "global_step": 412591, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1330106258392334, "global_step": 412592, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.160036087036133, "global_step": 412593, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.039154529571533, "global_step": 412594, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.126228094100952, "global_step": 412595, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.145193338394165, "global_step": 412596, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1356213092803955, "global_step": 412597, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1606991291046143, "global_step": 412598, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.064690113067627, "global_step": 412599, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1886425018310547, "global_step": 412600, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.070288896560669, "global_step": 412601, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.069932460784912, "global_step": 412602, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.071272850036621, "global_step": 412603, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.077312707901001, "global_step": 412604, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0285818576812744, "global_step": 412605, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.099212408065796, "global_step": 412606, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.077383279800415, "global_step": 412607, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.2211427688598633, "global_step": 412608, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.100193977355957, "global_step": 412609, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.045271635055542, "global_step": 412610, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.093289852142334, "global_step": 412611, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.153212785720825, "global_step": 412612, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.097410202026367, "global_step": 412613, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9854013919830322, "global_step": 412614, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1253583431243896, "global_step": 412615, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1573245525360107, "global_step": 412616, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.04609751701355, "global_step": 412617, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1675162315368652, "global_step": 412618, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1027798652648926, "global_step": 412619, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.150416374206543, "global_step": 412620, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.113842725753784, "global_step": 412621, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.2015326023101807, "global_step": 412622, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.151536464691162, "global_step": 412623, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.072455406188965, "global_step": 412624, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0759053230285645, "global_step": 412625, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1403284072875977, "global_step": 412626, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1222283840179443, "global_step": 412627, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.098506450653076, "global_step": 412628, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0584230422973633, "global_step": 412629, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1364030838012695, "global_step": 412630, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.080787420272827, "global_step": 412631, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.071084976196289, "global_step": 412632, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0401077270507812, "global_step": 412633, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1468565464019775, "global_step": 412634, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0780632495880127, "global_step": 412635, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0980842113494873, "global_step": 412636, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1684415340423584, "global_step": 412637, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.116234540939331, "global_step": 412638, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0801682472229004, "global_step": 412639, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1698994636535645, "global_step": 412640, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.025879383087158, "global_step": 412641, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.074817180633545, "global_step": 412642, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.125277280807495, "global_step": 412643, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1144771575927734, "global_step": 412644, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1835246086120605, "global_step": 412645, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1083202362060547, "global_step": 412646, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0731594562530518, "global_step": 412647, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1121387481689453, "global_step": 412648, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1521456241607666, "global_step": 412649, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.071845769882202, "global_step": 412650, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.024235248565674, "global_step": 412651, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0493383407592773, "global_step": 412652, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1041624546051025, "global_step": 412653, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.032557725906372, "global_step": 412654, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.089205265045166, "global_step": 412655, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1575920581817627, "global_step": 412656, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1854867935180664, "global_step": 412657, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0982892513275146, "global_step": 412658, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.089867115020752, "global_step": 412659, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0833404064178467, "global_step": 412660, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.025113582611084, "global_step": 412661, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.161201238632202, "global_step": 412662, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0731585025787354, "global_step": 412663, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0209028720855713, "global_step": 412664, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.135716199874878, "global_step": 412665, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0932724475860596, "global_step": 412666, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.113879680633545, "global_step": 412667, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.053062677383423, "global_step": 412668, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.071495771408081, "global_step": 412669, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1223652362823486, "global_step": 412670, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.011871576309204, "global_step": 412671, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0338375568389893, "global_step": 412672, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0722572803497314, "global_step": 412673, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.039375066757202, "global_step": 412674, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0702974796295166, "global_step": 412675, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0860536098480225, "global_step": 412676, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.2317898273468018, "global_step": 412677, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0485992431640625, "global_step": 412678, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0948798656463623, "global_step": 412679, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.063964366912842, "global_step": 412680, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.154292345046997, "global_step": 412681, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.001943826675415, "global_step": 412682, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1087934970855713, "global_step": 412683, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.130847930908203, "global_step": 412684, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1780953407287598, "global_step": 412685, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.136368989944458, "global_step": 412686, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1559979915618896, "global_step": 412687, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.133667469024658, "global_step": 412688, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0942153930664062, "global_step": 412689, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.11256742477417, "global_step": 412690, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0546984672546387, "global_step": 412691, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0916731357574463, "global_step": 412692, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.140395164489746, "global_step": 412693, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1207008361816406, "global_step": 412694, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.043703079223633, "global_step": 412695, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0482218265533447, "global_step": 412696, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0121207237243652, "global_step": 412697, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0999643802642822, "global_step": 412698, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.128204584121704, "global_step": 412699, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0723774433135986, "global_step": 412700, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1459226608276367, "global_step": 412701, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1673011779785156, "global_step": 412702, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.121227741241455, "global_step": 412703, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0469343662261963, "global_step": 412704, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.2306480407714844, "global_step": 412705, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.114123821258545, "global_step": 412706, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0337705612182617, "global_step": 412707, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.101802110671997, "global_step": 412708, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1450366973876953, "global_step": 412709, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0736184120178223, "global_step": 412710, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.165027141571045, "global_step": 412711, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0978541374206543, "global_step": 412712, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0279393196105957, "global_step": 412713, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.05659818649292, "global_step": 412714, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1428568363189697, "global_step": 412715, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.175045967102051, "global_step": 412716, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0562543869018555, "global_step": 412717, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1301801204681396, "global_step": 412718, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0993921756744385, "global_step": 412719, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9908607006072998, "global_step": 412720, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0846264362335205, "global_step": 412721, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1005825996398926, "global_step": 412722, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1279468536376953, "global_step": 412723, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1515963077545166, "global_step": 412724, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1444811820983887, "global_step": 412725, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.093870162963867, "global_step": 412726, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1246166229248047, "global_step": 412727, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0700035095214844, "global_step": 412728, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0703887939453125, "global_step": 412729, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.039292573928833, "global_step": 412730, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1187853813171387, "global_step": 412731, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.068449020385742, "global_step": 412732, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.127657651901245, "global_step": 412733, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0765535831451416, "global_step": 412734, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.01627779006958, "global_step": 412735, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.073869228363037, "global_step": 412736, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.107128620147705, "global_step": 412737, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1015982627868652, "global_step": 412738, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.063568115234375, "global_step": 412739, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0927608013153076, "global_step": 412740, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.162957191467285, "global_step": 412741, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.054429531097412, "global_step": 412742, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1315348148345947, "global_step": 412743, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.136503219604492, "global_step": 412744, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.121894121170044, "global_step": 412745, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.110410213470459, "global_step": 412746, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.17920184135437, "global_step": 412747, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0765604972839355, "global_step": 412748, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1053061485290527, "global_step": 412749, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0709288120269775, "global_step": 412750, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.090181589126587, "global_step": 412751, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0892350673675537, "global_step": 412752, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.11368989944458, "global_step": 412753, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1004583835601807, "global_step": 412754, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0436887741088867, "global_step": 412755, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.079859972000122, "global_step": 412756, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.010270357131958, "global_step": 412757, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0821335315704346, "global_step": 412758, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0890207290649414, "global_step": 412759, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.05308198928833, "global_step": 412760, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.100985050201416, "global_step": 412761, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.078486204147339, "global_step": 412762, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1548328399658203, "global_step": 412763, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0825140476226807, "global_step": 412764, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.127565622329712, "global_step": 412765, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1195437908172607, "global_step": 412766, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0716283321380615, "global_step": 412767, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.077434539794922, "global_step": 412768, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0861003398895264, "global_step": 412769, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0900790691375732, "global_step": 412770, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0080881118774414, "global_step": 412771, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0994651317596436, "global_step": 412772, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.17117977142334, "global_step": 412773, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1375374794006348, "global_step": 412774, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0622081756591797, "global_step": 412775, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.198744058609009, "global_step": 412776, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1293680667877197, "global_step": 412777, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.133326768875122, "global_step": 412778, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1021652221679688, "global_step": 412779, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0125999450683594, "global_step": 412780, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.088609457015991, "global_step": 412781, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0818052291870117, "global_step": 412782, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0742359161376953, "global_step": 412783, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.007028818130493, "global_step": 412784, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.145247220993042, "global_step": 412785, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.099027156829834, "global_step": 412786, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.160336971282959, "global_step": 412787, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9881740808486938, "global_step": 412788, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1726977825164795, "global_step": 412789, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1468191146850586, "global_step": 412790, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.202556610107422, "global_step": 412791, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.07273268699646, "global_step": 412792, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0255494117736816, "global_step": 412793, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0621519088745117, "global_step": 412794, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0964457988739014, "global_step": 412795, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.015529155731201, "global_step": 412796, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.081775188446045, "global_step": 412797, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1258704662323, "global_step": 412798, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.081261157989502, "global_step": 412799, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0844011306762695, "global_step": 412800, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.051589012145996, "global_step": 412801, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.137094020843506, "global_step": 412802, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1070756912231445, "global_step": 412803, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.000483989715576, "global_step": 412804, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.98881995677948, "global_step": 412805, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1651787757873535, "global_step": 412806, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.095973253250122, "global_step": 412807, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0355050563812256, "global_step": 412808, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.110413074493408, "global_step": 412809, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0936105251312256, "global_step": 412810, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.136780023574829, "global_step": 412811, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9973167181015015, "global_step": 412812, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.044227361679077, "global_step": 412813, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.101020336151123, "global_step": 412814, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.090576648712158, "global_step": 412815, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0739147663116455, "global_step": 412816, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.191157341003418, "global_step": 412817, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.143070697784424, "global_step": 412818, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.124112844467163, "global_step": 412819, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0621650218963623, "global_step": 412820, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1273746490478516, "global_step": 412821, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.065176248550415, "global_step": 412822, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0743305683135986, "global_step": 412823, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.132564067840576, "global_step": 412824, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0736348628997803, "global_step": 412825, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1442532539367676, "global_step": 412826, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.2668566703796387, "global_step": 412827, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0864076614379883, "global_step": 412828, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0869739055633545, "global_step": 412829, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1468374729156494, "global_step": 412830, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0428733825683594, "global_step": 412831, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.189457654953003, "global_step": 412832, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0709261894226074, "global_step": 412833, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1465678215026855, "global_step": 412834, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.165496587753296, "global_step": 412835, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.113142967224121, "global_step": 412836, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.067237377166748, "global_step": 412837, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.2222681045532227, "global_step": 412838, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0809414386749268, "global_step": 412839, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.098278045654297, "global_step": 412840, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0399668216705322, "global_step": 412841, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0315420627593994, "global_step": 412842, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.112640380859375, "global_step": 412843, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9616869688034058, "global_step": 412844, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1610140800476074, "global_step": 412845, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0089187622070312, "global_step": 412846, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.104559898376465, "global_step": 412847, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.145408868789673, "global_step": 412848, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.157221555709839, "global_step": 412849, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.091071844100952, "global_step": 412850, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0571422576904297, "global_step": 412851, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.017878293991089, "global_step": 412852, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.013868808746338, "global_step": 412853, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.2136006355285645, "global_step": 412854, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0750746726989746, "global_step": 412855, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1137375831604004, "global_step": 412856, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1584322452545166, "global_step": 412857, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0507452487945557, "global_step": 412858, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0221080780029297, "global_step": 412859, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9663945436477661, "global_step": 412860, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1181509494781494, "global_step": 412861, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.109431505203247, "global_step": 412862, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.110105276107788, "global_step": 412863, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.096931219100952, "global_step": 412864, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1297333240509033, "global_step": 412865, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1138570308685303, "global_step": 412866, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.131044387817383, "global_step": 412867, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0665714740753174, "global_step": 412868, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.15693998336792, "global_step": 412869, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.162355661392212, "global_step": 412870, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0447638034820557, "global_step": 412871, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1357510089874268, "global_step": 412872, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.039834976196289, "global_step": 412873, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.07063889503479, "global_step": 412874, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0898923873901367, "global_step": 412875, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.111081600189209, "global_step": 412876, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0823519229888916, "global_step": 412877, "epoch": 775, "lr": 5e-05}
{"train_loss": 1.9950690269470215, "global_step": 412878, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1208982467651367, "global_step": 412879, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.101839065551758, "global_step": 412880, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.149951696395874, "global_step": 412881, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.018916606903076, "global_step": 412882, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.146984577178955, "global_step": 412883, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.20503568649292, "global_step": 412884, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1578917503356934, "global_step": 412885, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1045327186584473, "global_step": 412886, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0809953212738037, "global_step": 412887, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.124310255050659, "global_step": 412888, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0378215312957764, "global_step": 412889, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0701050758361816, "global_step": 412890, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.129598379135132, "global_step": 412891, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0846242904663086, "global_step": 412892, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.157613754272461, "global_step": 412893, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0523571968078613, "global_step": 412894, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.073939800262451, "global_step": 412895, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.008568525314331, "global_step": 412896, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1978423595428467, "global_step": 412897, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.163208246231079, "global_step": 412898, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.166491746902466, "global_step": 412899, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.108794689178467, "global_step": 412900, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.112475633621216, "global_step": 412901, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0350239276885986, "global_step": 412902, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.079643487930298, "global_step": 412903, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0506272315979004, "global_step": 412904, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1107213497161865, "global_step": 412905, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.180077075958252, "global_step": 412906, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0580263137817383, "global_step": 412907, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0334715843200684, "global_step": 412908, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0918021202087402, "global_step": 412909, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.058422088623047, "global_step": 412910, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0760958194732666, "global_step": 412911, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1753642559051514, "global_step": 412912, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1917574405670166, "global_step": 412913, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1173908710479736, "global_step": 412914, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1377878189086914, "global_step": 412915, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.063843250274658, "global_step": 412916, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1052424907684326, "global_step": 412917, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0689499378204346, "global_step": 412918, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0628440380096436, "global_step": 412919, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0992543697357178, "global_step": 412920, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.096980571746826, "global_step": 412921, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1592938899993896, "global_step": 412922, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.1280465126037598, "global_step": 412923, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0649685859680176, "global_step": 412924, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0106887817382812, "global_step": 412925, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.0930275917053223, "global_step": 412926, "epoch": 775, "lr": 5e-05}
{"train_loss": 2.092513084411621, "global_step": 412927, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0470190048217773, "global_step": 412928, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0834438800811768, "global_step": 412929, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0415217876434326, "global_step": 412930, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0165345668792725, "global_step": 412931, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0580756664276123, "global_step": 412932, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9881194829940796, "global_step": 412933, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.057706832885742, "global_step": 412934, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.085216522216797, "global_step": 412935, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0140485763549805, "global_step": 412936, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.061206579208374, "global_step": 412937, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.193664789199829, "global_step": 412938, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0518641471862793, "global_step": 412939, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0204837322235107, "global_step": 412940, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0394082069396973, "global_step": 412941, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0167391300201416, "global_step": 412942, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1135458946228027, "global_step": 412943, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.056462287902832, "global_step": 412944, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.2163615226745605, "global_step": 412945, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0602293014526367, "global_step": 412946, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1142184734344482, "global_step": 412947, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9844764471054077, "global_step": 412948, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1146445274353027, "global_step": 412949, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.17109751701355, "global_step": 412950, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.104940891265869, "global_step": 412951, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.048215627670288, "global_step": 412952, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.076526641845703, "global_step": 412953, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.157428026199341, "global_step": 412954, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1976375579833984, "global_step": 412955, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0834202766418457, "global_step": 412956, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1077685356140137, "global_step": 412957, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1196515560150146, "global_step": 412958, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.101358652114868, "global_step": 412959, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1721575260162354, "global_step": 412960, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.083071708679199, "global_step": 412961, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.08804988861084, "global_step": 412962, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0563368797302246, "global_step": 412963, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.046581506729126, "global_step": 412964, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0708723068237305, "global_step": 412965, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.977453589439392, "global_step": 412966, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0478594303131104, "global_step": 412967, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0764708518981934, "global_step": 412968, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1160032749176025, "global_step": 412969, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0116138458251953, "global_step": 412970, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9968228340148926, "global_step": 412971, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1662912368774414, "global_step": 412972, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0736329555511475, "global_step": 412973, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0542755126953125, "global_step": 412974, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1119604110717773, "global_step": 412975, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.108259677886963, "global_step": 412976, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1170060634613037, "global_step": 412977, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.982603907585144, "global_step": 412978, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1437876224517822, "global_step": 412979, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1225600242614746, "global_step": 412980, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0206236839294434, "global_step": 412981, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0292398929595947, "global_step": 412982, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1594882011413574, "global_step": 412983, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1785945892333984, "global_step": 412984, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0992069244384766, "global_step": 412985, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0860869884490967, "global_step": 412986, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0552055835723877, "global_step": 412987, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.109966278076172, "global_step": 412988, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1809701919555664, "global_step": 412989, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.072425127029419, "global_step": 412990, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0364890098571777, "global_step": 412991, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.102233648300171, "global_step": 412992, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1421005725860596, "global_step": 412993, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1645681858062744, "global_step": 412994, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.076388359069824, "global_step": 412995, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.038158655166626, "global_step": 412996, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.016601800918579, "global_step": 412997, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.131441354751587, "global_step": 412998, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.089573383331299, "global_step": 412999, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1105103492736816, "global_step": 413000, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0248382091522217, "global_step": 413001, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1001269817352295, "global_step": 413002, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0985841751098633, "global_step": 413003, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1320173740386963, "global_step": 413004, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0582170486450195, "global_step": 413005, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0787901878356934, "global_step": 413006, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0674214363098145, "global_step": 413007, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1004323959350586, "global_step": 413008, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.049877405166626, "global_step": 413009, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.203308343887329, "global_step": 413010, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1004908084869385, "global_step": 413011, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1552464962005615, "global_step": 413012, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1344594955444336, "global_step": 413013, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.078625440597534, "global_step": 413014, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0456795692443848, "global_step": 413015, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0702266693115234, "global_step": 413016, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1006383895874023, "global_step": 413017, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0573599338531494, "global_step": 413018, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1326448917388916, "global_step": 413019, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0563971996307373, "global_step": 413020, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.085878372192383, "global_step": 413021, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0369668006896973, "global_step": 413022, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.078907012939453, "global_step": 413023, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9514479637145996, "global_step": 413024, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0842089653015137, "global_step": 413025, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1278719902038574, "global_step": 413026, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.105943202972412, "global_step": 413027, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0771420001983643, "global_step": 413028, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.007349967956543, "global_step": 413029, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0718131065368652, "global_step": 413030, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0213980674743652, "global_step": 413031, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0356597900390625, "global_step": 413032, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1425893306732178, "global_step": 413033, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9993752241134644, "global_step": 413034, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0228335857391357, "global_step": 413035, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0350773334503174, "global_step": 413036, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0601565837860107, "global_step": 413037, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1360387802124023, "global_step": 413038, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9909789562225342, "global_step": 413039, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0497519969940186, "global_step": 413040, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.154228925704956, "global_step": 413041, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1160709857940674, "global_step": 413042, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.097029447555542, "global_step": 413043, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1040046215057373, "global_step": 413044, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1091623306274414, "global_step": 413045, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1469037532806396, "global_step": 413046, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1233911514282227, "global_step": 413047, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.120958089828491, "global_step": 413048, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.145066976547241, "global_step": 413049, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.055124521255493, "global_step": 413050, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.086117744445801, "global_step": 413051, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1325955390930176, "global_step": 413052, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.062912940979004, "global_step": 413053, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.155588150024414, "global_step": 413054, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.09490704536438, "global_step": 413055, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.072932481765747, "global_step": 413056, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.011655807495117, "global_step": 413057, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.067206859588623, "global_step": 413058, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0546910762786865, "global_step": 413059, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9440944194793701, "global_step": 413060, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.066570997238159, "global_step": 413061, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1036970615386963, "global_step": 413062, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.019474506378174, "global_step": 413063, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0679433345794678, "global_step": 413064, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0119223594665527, "global_step": 413065, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0617408752441406, "global_step": 413066, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.069911003112793, "global_step": 413067, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0945818424224854, "global_step": 413068, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1711411476135254, "global_step": 413069, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.088286876678467, "global_step": 413070, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0673704147338867, "global_step": 413071, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0595362186431885, "global_step": 413072, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.094296932220459, "global_step": 413073, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.11199951171875, "global_step": 413074, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1508023738861084, "global_step": 413075, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1066219806671143, "global_step": 413076, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1244163513183594, "global_step": 413077, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1159889698028564, "global_step": 413078, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1890196800231934, "global_step": 413079, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.025184392929077, "global_step": 413080, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.084481716156006, "global_step": 413081, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.105102300643921, "global_step": 413082, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.095290422439575, "global_step": 413083, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1162853240966797, "global_step": 413084, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.050255537033081, "global_step": 413085, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0315980911254883, "global_step": 413086, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.047300100326538, "global_step": 413087, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1030640602111816, "global_step": 413088, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1270804405212402, "global_step": 413089, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0519609451293945, "global_step": 413090, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9976202249526978, "global_step": 413091, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.115539312362671, "global_step": 413092, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.071647882461548, "global_step": 413093, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.109788179397583, "global_step": 413094, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.036268949508667, "global_step": 413095, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1253724098205566, "global_step": 413096, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.03543758392334, "global_step": 413097, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.171452045440674, "global_step": 413098, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9923617839813232, "global_step": 413099, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.013350248336792, "global_step": 413100, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0711143016815186, "global_step": 413101, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0380356311798096, "global_step": 413102, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.021635055541992, "global_step": 413103, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.077667236328125, "global_step": 413104, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0883309841156006, "global_step": 413105, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1818795204162598, "global_step": 413106, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.121471881866455, "global_step": 413107, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.076620101928711, "global_step": 413108, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1386005878448486, "global_step": 413109, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9805198907852173, "global_step": 413110, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.028163433074951, "global_step": 413111, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1711833477020264, "global_step": 413112, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.036087989807129, "global_step": 413113, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.112844705581665, "global_step": 413114, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0713653564453125, "global_step": 413115, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1186113357543945, "global_step": 413116, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0491831302642822, "global_step": 413117, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.056735038757324, "global_step": 413118, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0828027725219727, "global_step": 413119, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0493006706237793, "global_step": 413120, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.115901470184326, "global_step": 413121, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0551321506500244, "global_step": 413122, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.038144111633301, "global_step": 413123, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.134868860244751, "global_step": 413124, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0479259490966797, "global_step": 413125, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0382096767425537, "global_step": 413126, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.153538465499878, "global_step": 413127, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.003678321838379, "global_step": 413128, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.113428831100464, "global_step": 413129, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0913426876068115, "global_step": 413130, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0950517654418945, "global_step": 413131, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.082272529602051, "global_step": 413132, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0763609409332275, "global_step": 413133, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0256378650665283, "global_step": 413134, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.054631233215332, "global_step": 413135, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0237271785736084, "global_step": 413136, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.010366916656494, "global_step": 413137, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.062931537628174, "global_step": 413138, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.098520278930664, "global_step": 413139, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1497550010681152, "global_step": 413140, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0872902870178223, "global_step": 413141, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0450263023376465, "global_step": 413142, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1234078407287598, "global_step": 413143, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0623207092285156, "global_step": 413144, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.138671636581421, "global_step": 413145, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.067232608795166, "global_step": 413146, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.110675811767578, "global_step": 413147, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1167445182800293, "global_step": 413148, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1089651584625244, "global_step": 413149, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0978856086730957, "global_step": 413150, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.118431329727173, "global_step": 413151, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1097183227539062, "global_step": 413152, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1167314052581787, "global_step": 413153, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.134303569793701, "global_step": 413154, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.028947591781616, "global_step": 413155, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0454812049865723, "global_step": 413156, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0997045040130615, "global_step": 413157, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0980606079101562, "global_step": 413158, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0779151916503906, "global_step": 413159, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.058368444442749, "global_step": 413160, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.083474636077881, "global_step": 413161, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0656633377075195, "global_step": 413162, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0513463020324707, "global_step": 413163, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.088714361190796, "global_step": 413164, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.055318832397461, "global_step": 413165, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.100480556488037, "global_step": 413166, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.130821466445923, "global_step": 413167, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.024052619934082, "global_step": 413168, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0443203449249268, "global_step": 413169, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0712387561798096, "global_step": 413170, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0305070877075195, "global_step": 413171, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0572900772094727, "global_step": 413172, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.147632122039795, "global_step": 413173, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.078702449798584, "global_step": 413174, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1211233139038086, "global_step": 413175, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0823917388916016, "global_step": 413176, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.07491397857666, "global_step": 413177, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.099419116973877, "global_step": 413178, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1607730388641357, "global_step": 413179, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.019259214401245, "global_step": 413180, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0606987476348877, "global_step": 413181, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1722278594970703, "global_step": 413182, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0945591926574707, "global_step": 413183, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0408527851104736, "global_step": 413184, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1219844818115234, "global_step": 413185, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.108173131942749, "global_step": 413186, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0652706623077393, "global_step": 413187, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0969491004943848, "global_step": 413188, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1194095611572266, "global_step": 413189, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0880911350250244, "global_step": 413190, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0667574405670166, "global_step": 413191, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.138745069503784, "global_step": 413192, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0064289569854736, "global_step": 413193, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0532000064849854, "global_step": 413194, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0662426948547363, "global_step": 413195, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1361396312713623, "global_step": 413196, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.042860984802246, "global_step": 413197, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.086203098297119, "global_step": 413198, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.112757444381714, "global_step": 413199, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.105414390563965, "global_step": 413200, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.094285488128662, "global_step": 413201, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.069777488708496, "global_step": 413202, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0525946617126465, "global_step": 413203, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0946104526519775, "global_step": 413204, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0429368019104004, "global_step": 413205, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.15095853805542, "global_step": 413206, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.126009225845337, "global_step": 413207, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.023728847503662, "global_step": 413208, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.071878433227539, "global_step": 413209, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.084608793258667, "global_step": 413210, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0998268127441406, "global_step": 413211, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0680248737335205, "global_step": 413212, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0815539360046387, "global_step": 413213, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.2418298721313477, "global_step": 413214, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1009199619293213, "global_step": 413215, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0587191581726074, "global_step": 413216, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1553781032562256, "global_step": 413217, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.102299690246582, "global_step": 413218, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1372458934783936, "global_step": 413219, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0959177017211914, "global_step": 413220, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0889856815338135, "global_step": 413221, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.122152328491211, "global_step": 413222, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0805652141571045, "global_step": 413223, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0945093631744385, "global_step": 413224, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0184895992279053, "global_step": 413225, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1918210983276367, "global_step": 413226, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0657966136932373, "global_step": 413227, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0914769172668457, "global_step": 413228, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0443599224090576, "global_step": 413229, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0463805198669434, "global_step": 413230, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1356120109558105, "global_step": 413231, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1606791019439697, "global_step": 413232, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1083741188049316, "global_step": 413233, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.063180685043335, "global_step": 413234, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.163351535797119, "global_step": 413235, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.080620050430298, "global_step": 413236, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.086207151412964, "global_step": 413237, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0566418170928955, "global_step": 413238, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.103386163711548, "global_step": 413239, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.102877378463745, "global_step": 413240, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0753719806671143, "global_step": 413241, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.08217191696167, "global_step": 413242, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.146845579147339, "global_step": 413243, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.990662932395935, "global_step": 413244, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1669650077819824, "global_step": 413245, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.139397382736206, "global_step": 413246, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0505337715148926, "global_step": 413247, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0628459453582764, "global_step": 413248, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1241202354431152, "global_step": 413249, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1064274311065674, "global_step": 413250, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.122596502304077, "global_step": 413251, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0833678245544434, "global_step": 413252, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.017224073410034, "global_step": 413253, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.062302589416504, "global_step": 413254, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0620644092559814, "global_step": 413255, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.139265537261963, "global_step": 413256, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1030306816101074, "global_step": 413257, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0825483798980713, "global_step": 413258, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.005457639694214, "global_step": 413259, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.038236379623413, "global_step": 413260, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1041362285614014, "global_step": 413261, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.088575601577759, "global_step": 413262, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0940067768096924, "global_step": 413263, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9973946809768677, "global_step": 413264, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1127264499664307, "global_step": 413265, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9778646230697632, "global_step": 413266, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.057377576828003, "global_step": 413267, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1328041553497314, "global_step": 413268, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.016394853591919, "global_step": 413269, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.2089569568634033, "global_step": 413270, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.103013753890991, "global_step": 413271, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.066880702972412, "global_step": 413272, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0508992671966553, "global_step": 413273, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.043562412261963, "global_step": 413274, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.202241897583008, "global_step": 413275, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.096531391143799, "global_step": 413276, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.099897623062134, "global_step": 413277, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0474109649658203, "global_step": 413278, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.093777656555176, "global_step": 413279, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.04822039604187, "global_step": 413280, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0226926803588867, "global_step": 413281, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0123260021209717, "global_step": 413282, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0990188121795654, "global_step": 413283, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0630972385406494, "global_step": 413284, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.11757755279541, "global_step": 413285, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0787746906280518, "global_step": 413286, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.073625326156616, "global_step": 413287, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.111328125, "global_step": 413288, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.185624837875366, "global_step": 413289, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1034438610076904, "global_step": 413290, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1829681396484375, "global_step": 413291, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.090259313583374, "global_step": 413292, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.045666217803955, "global_step": 413293, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.145106077194214, "global_step": 413294, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.195615530014038, "global_step": 413295, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1271917819976807, "global_step": 413296, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1396167278289795, "global_step": 413297, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0799267292022705, "global_step": 413298, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1454648971557617, "global_step": 413299, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0333993434906006, "global_step": 413300, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1160337924957275, "global_step": 413301, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.081371784210205, "global_step": 413302, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.114595890045166, "global_step": 413303, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.096827745437622, "global_step": 413304, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.095768928527832, "global_step": 413305, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1139538288116455, "global_step": 413306, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.135162830352783, "global_step": 413307, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0919017791748047, "global_step": 413308, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.104757070541382, "global_step": 413309, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0037169456481934, "global_step": 413310, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1032562255859375, "global_step": 413311, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.052855968475342, "global_step": 413312, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0425736904144287, "global_step": 413313, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0798373222351074, "global_step": 413314, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0750813484191895, "global_step": 413315, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1380105018615723, "global_step": 413316, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1335530281066895, "global_step": 413317, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0919337272644043, "global_step": 413318, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1251182556152344, "global_step": 413319, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.169750928878784, "global_step": 413320, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0332510471343994, "global_step": 413321, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.07769513130188, "global_step": 413322, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1250503063201904, "global_step": 413323, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.124917507171631, "global_step": 413324, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1316308975219727, "global_step": 413325, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0735340118408203, "global_step": 413326, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.053347110748291, "global_step": 413327, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0855164527893066, "global_step": 413328, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.096289873123169, "global_step": 413329, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.051981210708618, "global_step": 413330, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.968477725982666, "global_step": 413331, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.07260799407959, "global_step": 413332, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1355252265930176, "global_step": 413333, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.075732946395874, "global_step": 413334, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1377787590026855, "global_step": 413335, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0757877826690674, "global_step": 413336, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.067850112915039, "global_step": 413337, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.101548671722412, "global_step": 413338, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1419265270233154, "global_step": 413339, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0824155807495117, "global_step": 413340, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0708844661712646, "global_step": 413341, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9993289709091187, "global_step": 413342, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0366122722625732, "global_step": 413343, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1085638999938965, "global_step": 413344, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0651421546936035, "global_step": 413345, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.123905897140503, "global_step": 413346, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0807037353515625, "global_step": 413347, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.109186887741089, "global_step": 413348, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.171940326690674, "global_step": 413349, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0859251022338867, "global_step": 413350, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0269923210144043, "global_step": 413351, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.113976001739502, "global_step": 413352, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0713038444519043, "global_step": 413353, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0758931636810303, "global_step": 413354, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9991453886032104, "global_step": 413355, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.150923728942871, "global_step": 413356, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1242690086364746, "global_step": 413357, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1100330352783203, "global_step": 413358, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1230859756469727, "global_step": 413359, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.101388692855835, "global_step": 413360, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0526773929595947, "global_step": 413361, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1182963848114014, "global_step": 413362, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.980793833732605, "global_step": 413363, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0653748512268066, "global_step": 413364, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1270852088928223, "global_step": 413365, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.004952907562256, "global_step": 413366, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0215718746185303, "global_step": 413367, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0128331184387207, "global_step": 413368, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.230020046234131, "global_step": 413369, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0503182411193848, "global_step": 413370, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0410523414611816, "global_step": 413371, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.138488292694092, "global_step": 413372, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.125685453414917, "global_step": 413373, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.04648494720459, "global_step": 413374, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.2202513217926025, "global_step": 413375, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0900936126708984, "global_step": 413376, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.2000577449798584, "global_step": 413377, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.163642168045044, "global_step": 413378, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.021440267562866, "global_step": 413379, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1117630004882812, "global_step": 413380, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1339385509490967, "global_step": 413381, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.054412841796875, "global_step": 413382, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0549540519714355, "global_step": 413383, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.111847400665283, "global_step": 413384, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.10158109664917, "global_step": 413385, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.064964532852173, "global_step": 413386, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0731942653656006, "global_step": 413387, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0608203411102295, "global_step": 413388, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.058206558227539, "global_step": 413389, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1467783451080322, "global_step": 413390, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.112579822540283, "global_step": 413391, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.120448350906372, "global_step": 413392, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.046518564224243, "global_step": 413393, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1062052249908447, "global_step": 413394, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.145021915435791, "global_step": 413395, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1288278102874756, "global_step": 413396, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0664749145507812, "global_step": 413397, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1222574710845947, "global_step": 413398, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1080219745635986, "global_step": 413399, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.056635618209839, "global_step": 413400, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1212666034698486, "global_step": 413401, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1148905754089355, "global_step": 413402, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0934038162231445, "global_step": 413403, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1527292728424072, "global_step": 413404, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9987785816192627, "global_step": 413405, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.088966131210327, "global_step": 413406, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1355113983154297, "global_step": 413407, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.027562379837036, "global_step": 413408, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.130774736404419, "global_step": 413409, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0211799144744873, "global_step": 413410, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0965416431427, "global_step": 413411, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1761550903320312, "global_step": 413412, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0242128372192383, "global_step": 413413, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1330370903015137, "global_step": 413414, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.081543445587158, "global_step": 413415, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0396413803100586, "global_step": 413416, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1447582244873047, "global_step": 413417, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.071173667907715, "global_step": 413418, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.079197645187378, "global_step": 413419, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0578033924102783, "global_step": 413420, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1250953674316406, "global_step": 413421, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.080458879470825, "global_step": 413422, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.05145263671875, "global_step": 413423, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0342373847961426, "global_step": 413424, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.042370319366455, "global_step": 413425, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.085533618927002, "global_step": 413426, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1610357761383057, "global_step": 413427, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.044832468032837, "global_step": 413428, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1372759342193604, "global_step": 413429, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1191952228546143, "global_step": 413430, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0410139560699463, "global_step": 413431, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1103620529174805, "global_step": 413432, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9826362133026123, "global_step": 413433, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9951571226119995, "global_step": 413434, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0596494674682617, "global_step": 413435, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.07619309425354, "global_step": 413436, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.168121337890625, "global_step": 413437, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0942225456237793, "global_step": 413438, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9977774620056152, "global_step": 413439, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0663371086120605, "global_step": 413440, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1402008533477783, "global_step": 413441, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.021289825439453, "global_step": 413442, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0837855339050293, "global_step": 413443, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.124439239501953, "global_step": 413444, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1250009536743164, "global_step": 413445, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1698644161224365, "global_step": 413446, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.164029836654663, "global_step": 413447, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1008050441741943, "global_step": 413448, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.187915802001953, "global_step": 413449, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.165513277053833, "global_step": 413450, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.037811279296875, "global_step": 413451, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.181041717529297, "global_step": 413452, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.103142261505127, "global_step": 413453, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0717830657958984, "global_step": 413454, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1555585861206055, "global_step": 413455, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1014981269836426, "global_step": 413456, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0568416118621826, "global_step": 413457, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0475265979766846, "global_step": 413458, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0928359031677246, "global_step": 413459, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1084377765655518, "global_step": 413460, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1384377479553223, "global_step": 413461, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.044102191925049, "global_step": 413462, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0898208618164062, "global_step": 413463, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.170048952102661, "global_step": 413464, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1193137168884277, "global_step": 413465, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0815038681030273, "global_step": 413466, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.053025245666504, "global_step": 413467, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.055717706680298, "global_step": 413468, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0553596019744873, "global_step": 413469, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0281009674072266, "global_step": 413470, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0135748386383057, "global_step": 413471, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1910414695739746, "global_step": 413472, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0565919876098633, "global_step": 413473, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1580941677093506, "global_step": 413474, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0182089805603027, "global_step": 413475, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.129833936691284, "global_step": 413476, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0609915256500244, "global_step": 413477, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.045053005218506, "global_step": 413478, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1197526454925537, "global_step": 413479, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0823111534118652, "global_step": 413480, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.123412609100342, "global_step": 413481, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.126116991043091, "global_step": 413482, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.072906017303467, "global_step": 413483, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0713465213775635, "global_step": 413484, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0777835845947266, "global_step": 413485, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0722804069519043, "global_step": 413486, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1401052474975586, "global_step": 413487, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0303053855895996, "global_step": 413488, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0870256423950195, "global_step": 413489, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.118704080581665, "global_step": 413490, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1540985107421875, "global_step": 413491, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.095395565032959, "global_step": 413492, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.059282064437866, "global_step": 413493, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0310258865356445, "global_step": 413494, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1490182876586914, "global_step": 413495, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0272183418273926, "global_step": 413496, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0786705017089844, "global_step": 413497, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1441924571990967, "global_step": 413498, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9712013006210327, "global_step": 413499, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0171356201171875, "global_step": 413500, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1107029914855957, "global_step": 413501, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1509978771209717, "global_step": 413502, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.018155336380005, "global_step": 413503, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1194183826446533, "global_step": 413504, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1038899421691895, "global_step": 413505, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.017442464828491, "global_step": 413506, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0677974224090576, "global_step": 413507, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1458475589752197, "global_step": 413508, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9744293689727783, "global_step": 413509, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.08351731300354, "global_step": 413510, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.093306303024292, "global_step": 413511, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.103025436401367, "global_step": 413512, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.124479293823242, "global_step": 413513, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.085740327835083, "global_step": 413514, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.2267441749572754, "global_step": 413515, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.137848138809204, "global_step": 413516, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.081674575805664, "global_step": 413517, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.04864239692688, "global_step": 413518, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1417341232299805, "global_step": 413519, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.119356870651245, "global_step": 413520, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1210317611694336, "global_step": 413521, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.103696584701538, "global_step": 413522, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.116220474243164, "global_step": 413523, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.139477491378784, "global_step": 413524, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0250284671783447, "global_step": 413525, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1071178913116455, "global_step": 413526, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.057602643966675, "global_step": 413527, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.07564115524292, "global_step": 413528, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0817134380340576, "global_step": 413529, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9681029319763184, "global_step": 413530, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.059915781021118, "global_step": 413531, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.146028757095337, "global_step": 413532, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.10416579246521, "global_step": 413533, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1164371967315674, "global_step": 413534, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1666269302368164, "global_step": 413535, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.075807571411133, "global_step": 413536, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9974846839904785, "global_step": 413537, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9959529638290405, "global_step": 413538, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.110830783843994, "global_step": 413539, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.021559715270996, "global_step": 413540, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1278011798858643, "global_step": 413541, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9960412979125977, "global_step": 413542, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0699613094329834, "global_step": 413543, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.120809555053711, "global_step": 413544, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.039695978164673, "global_step": 413545, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.032649278640747, "global_step": 413546, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0603504180908203, "global_step": 413547, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.984000563621521, "global_step": 413548, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1124460697174072, "global_step": 413549, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0642380714416504, "global_step": 413550, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.167325973510742, "global_step": 413551, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.140882730484009, "global_step": 413552, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.154954195022583, "global_step": 413553, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.084693431854248, "global_step": 413554, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.087719678878784, "global_step": 413555, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0280468463897705, "global_step": 413556, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.054295063018799, "global_step": 413557, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0820999145507812, "global_step": 413558, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.086146831512451, "global_step": 413559, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1163389682769775, "global_step": 413560, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1030678749084473, "global_step": 413561, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.109482765197754, "global_step": 413562, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.064815044403076, "global_step": 413563, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.095475912094116, "global_step": 413564, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0502243041992188, "global_step": 413565, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.114467144012451, "global_step": 413566, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.089719295501709, "global_step": 413567, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.134597063064575, "global_step": 413568, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.95849609375, "global_step": 413569, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9852633476257324, "global_step": 413570, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1458184719085693, "global_step": 413571, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1403257846832275, "global_step": 413572, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.148674964904785, "global_step": 413573, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1486194133758545, "global_step": 413574, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0968639850616455, "global_step": 413575, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9619156122207642, "global_step": 413576, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1198086738586426, "global_step": 413577, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.063720941543579, "global_step": 413578, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.005802869796753, "global_step": 413579, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1609690189361572, "global_step": 413580, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.073305368423462, "global_step": 413581, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.109421968460083, "global_step": 413582, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1638448238372803, "global_step": 413583, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.091362953186035, "global_step": 413584, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0231029987335205, "global_step": 413585, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.127553939819336, "global_step": 413586, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.105329751968384, "global_step": 413587, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.072359561920166, "global_step": 413588, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.146449327468872, "global_step": 413589, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.080549716949463, "global_step": 413590, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0713846683502197, "global_step": 413591, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1090526580810547, "global_step": 413592, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.198374032974243, "global_step": 413593, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0012805461883545, "global_step": 413594, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0707128047943115, "global_step": 413595, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0735416412353516, "global_step": 413596, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0984790325164795, "global_step": 413597, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1644670963287354, "global_step": 413598, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0274031162261963, "global_step": 413599, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1025424003601074, "global_step": 413600, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.13535737991333, "global_step": 413601, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.084542989730835, "global_step": 413602, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0828380584716797, "global_step": 413603, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.113856792449951, "global_step": 413604, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0649869441986084, "global_step": 413605, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0513389110565186, "global_step": 413606, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1390554904937744, "global_step": 413607, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0978047847747803, "global_step": 413608, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0793778896331787, "global_step": 413609, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.171051263809204, "global_step": 413610, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.2279772758483887, "global_step": 413611, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.087298631668091, "global_step": 413612, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0705862045288086, "global_step": 413613, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1407413482666016, "global_step": 413614, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.111262083053589, "global_step": 413615, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.165889024734497, "global_step": 413616, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.037097930908203, "global_step": 413617, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0723400115966797, "global_step": 413618, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.177849531173706, "global_step": 413619, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1114068031311035, "global_step": 413620, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0308992862701416, "global_step": 413621, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0201382637023926, "global_step": 413622, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1405277252197266, "global_step": 413623, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.155693531036377, "global_step": 413624, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.094886541366577, "global_step": 413625, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.024799108505249, "global_step": 413626, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0545501708984375, "global_step": 413627, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0820775032043457, "global_step": 413628, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.104271650314331, "global_step": 413629, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1010353565216064, "global_step": 413630, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0924782752990723, "global_step": 413631, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0257198810577393, "global_step": 413632, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0197601318359375, "global_step": 413633, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.070908784866333, "global_step": 413634, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1572842597961426, "global_step": 413635, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.009194850921631, "global_step": 413636, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.083383321762085, "global_step": 413637, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1541647911071777, "global_step": 413638, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.073647975921631, "global_step": 413639, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.113201141357422, "global_step": 413640, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1257479190826416, "global_step": 413641, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0809295177459717, "global_step": 413642, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.088747978210449, "global_step": 413643, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.089012622833252, "global_step": 413644, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.055816173553467, "global_step": 413645, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.123807430267334, "global_step": 413646, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.075254440307617, "global_step": 413647, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.11810040473938, "global_step": 413648, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.182147979736328, "global_step": 413649, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.036865711212158, "global_step": 413650, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.079641580581665, "global_step": 413651, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0114171504974365, "global_step": 413652, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.038207769393921, "global_step": 413653, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.024883270263672, "global_step": 413654, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.2036960124969482, "global_step": 413655, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.164968729019165, "global_step": 413656, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.112563371658325, "global_step": 413657, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.160702705383301, "global_step": 413658, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1519217491149902, "global_step": 413659, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1305739879608154, "global_step": 413660, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0511250495910645, "global_step": 413661, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0579946041107178, "global_step": 413662, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0601587295532227, "global_step": 413663, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.057924747467041, "global_step": 413664, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0631916522979736, "global_step": 413665, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.00775146484375, "global_step": 413666, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0908799171447754, "global_step": 413667, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.124433994293213, "global_step": 413668, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1552135944366455, "global_step": 413669, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.005502939224243, "global_step": 413670, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1156537532806396, "global_step": 413671, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0620222091674805, "global_step": 413672, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.114786386489868, "global_step": 413673, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0105254650115967, "global_step": 413674, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.165036201477051, "global_step": 413675, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1222245693206787, "global_step": 413676, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1002349853515625, "global_step": 413677, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.123155117034912, "global_step": 413678, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0968337059020996, "global_step": 413679, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1330294609069824, "global_step": 413680, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0783989429473877, "global_step": 413681, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1047117710113525, "global_step": 413682, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.100008010864258, "global_step": 413683, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1312780380249023, "global_step": 413684, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.081299304962158, "global_step": 413685, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1476376056671143, "global_step": 413686, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.144691228866577, "global_step": 413687, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.226189613342285, "global_step": 413688, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.089773178100586, "global_step": 413689, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.077004909515381, "global_step": 413690, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.058852434158325, "global_step": 413691, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1164867877960205, "global_step": 413692, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.077866792678833, "global_step": 413693, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1547460556030273, "global_step": 413694, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.088059186935425, "global_step": 413695, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0493948459625244, "global_step": 413696, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1513631343841553, "global_step": 413697, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.959071397781372, "global_step": 413698, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0270140171051025, "global_step": 413699, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.092059373855591, "global_step": 413700, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0910677909851074, "global_step": 413701, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0588109493255615, "global_step": 413702, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0528030395507812, "global_step": 413703, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.126598358154297, "global_step": 413704, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1126210689544678, "global_step": 413705, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0968358516693115, "global_step": 413706, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0598742961883545, "global_step": 413707, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1114394664764404, "global_step": 413708, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.118881940841675, "global_step": 413709, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.2031984329223633, "global_step": 413710, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.155329465866089, "global_step": 413711, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0991625785827637, "global_step": 413712, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.160797119140625, "global_step": 413713, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0516598224639893, "global_step": 413714, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1307437419891357, "global_step": 413715, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1449408531188965, "global_step": 413716, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.089888095855713, "global_step": 413717, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.164968729019165, "global_step": 413718, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1484460830688477, "global_step": 413719, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.049086570739746, "global_step": 413720, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0827090740203857, "global_step": 413721, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1764395236968994, "global_step": 413722, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0834884643554688, "global_step": 413723, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0982439517974854, "global_step": 413724, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.121695041656494, "global_step": 413725, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1200203895568848, "global_step": 413726, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0912487506866455, "global_step": 413727, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.078969955444336, "global_step": 413728, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.061427593231201, "global_step": 413729, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.020263910293579, "global_step": 413730, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.12748646736145, "global_step": 413731, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.159618616104126, "global_step": 413732, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9670155048370361, "global_step": 413733, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1204588413238525, "global_step": 413734, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1420652866363525, "global_step": 413735, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.085728406906128, "global_step": 413736, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0817513465881348, "global_step": 413737, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1233975887298584, "global_step": 413738, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1457722187042236, "global_step": 413739, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.079399347305298, "global_step": 413740, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1346707344055176, "global_step": 413741, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0550127029418945, "global_step": 413742, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0275018215179443, "global_step": 413743, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.125056505203247, "global_step": 413744, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0630459785461426, "global_step": 413745, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1153392791748047, "global_step": 413746, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0388004779815674, "global_step": 413747, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.059021472930908, "global_step": 413748, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.140813112258911, "global_step": 413749, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0488996505737305, "global_step": 413750, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.14035964012146, "global_step": 413751, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.11285400390625, "global_step": 413752, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.226731777191162, "global_step": 413753, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1868975162506104, "global_step": 413754, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0602166652679443, "global_step": 413755, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.083725690841675, "global_step": 413756, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.998015284538269, "global_step": 413757, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1808090209960938, "global_step": 413758, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1130456924438477, "global_step": 413759, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.142672061920166, "global_step": 413760, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0678210258483887, "global_step": 413761, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.170286178588867, "global_step": 413762, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1077113151550293, "global_step": 413763, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0579721927642822, "global_step": 413764, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0723135471343994, "global_step": 413765, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0581767559051514, "global_step": 413766, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.148376941680908, "global_step": 413767, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.034609317779541, "global_step": 413768, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0784571170806885, "global_step": 413769, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0624990463256836, "global_step": 413770, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.106328010559082, "global_step": 413771, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.172006845474243, "global_step": 413772, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.153442621231079, "global_step": 413773, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0307371616363525, "global_step": 413774, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.16743803024292, "global_step": 413775, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1057276725769043, "global_step": 413776, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.061084032058716, "global_step": 413777, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0825514793395996, "global_step": 413778, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.188854455947876, "global_step": 413779, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0330567359924316, "global_step": 413780, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.148993492126465, "global_step": 413781, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.080423355102539, "global_step": 413782, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.085545778274536, "global_step": 413783, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1370584964752197, "global_step": 413784, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0879392623901367, "global_step": 413785, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1111035346984863, "global_step": 413786, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.243574380874634, "global_step": 413787, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1624763011932373, "global_step": 413788, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9912211894989014, "global_step": 413789, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0892608165740967, "global_step": 413790, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.045409917831421, "global_step": 413791, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0706706047058105, "global_step": 413792, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1274702548980713, "global_step": 413793, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0185036659240723, "global_step": 413794, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.122913122177124, "global_step": 413795, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1045713424682617, "global_step": 413796, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.068143844604492, "global_step": 413797, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0993998050689697, "global_step": 413798, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9927423000335693, "global_step": 413799, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.056727886199951, "global_step": 413800, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1067311763763428, "global_step": 413801, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0718793869018555, "global_step": 413802, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.145190715789795, "global_step": 413803, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.017272710800171, "global_step": 413804, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1222500801086426, "global_step": 413805, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1244266033172607, "global_step": 413806, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.070575475692749, "global_step": 413807, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.088812828063965, "global_step": 413808, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1525721549987793, "global_step": 413809, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0367166996002197, "global_step": 413810, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0462546348571777, "global_step": 413811, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0923492908477783, "global_step": 413812, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1523284912109375, "global_step": 413813, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1564667224884033, "global_step": 413814, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1184070110321045, "global_step": 413815, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.075330972671509, "global_step": 413816, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0340042114257812, "global_step": 413817, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.10386323928833, "global_step": 413818, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1465771198272705, "global_step": 413819, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.002415657043457, "global_step": 413820, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.090782642364502, "global_step": 413821, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.070955276489258, "global_step": 413822, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.081113815307617, "global_step": 413823, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.103818416595459, "global_step": 413824, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.203040599822998, "global_step": 413825, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1603472232818604, "global_step": 413826, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1600232124328613, "global_step": 413827, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.073331832885742, "global_step": 413828, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1247072219848633, "global_step": 413829, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1095938682556152, "global_step": 413830, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0412960052490234, "global_step": 413831, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.123082160949707, "global_step": 413832, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.106351137161255, "global_step": 413833, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.107267379760742, "global_step": 413834, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1078481674194336, "global_step": 413835, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.146207332611084, "global_step": 413836, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.173262119293213, "global_step": 413837, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.042814016342163, "global_step": 413838, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.134092330932617, "global_step": 413839, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1358625888824463, "global_step": 413840, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0704164505004883, "global_step": 413841, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0798516273498535, "global_step": 413842, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.037729501724243, "global_step": 413843, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0992534160614014, "global_step": 413844, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.066537380218506, "global_step": 413845, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1557939052581787, "global_step": 413846, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1235413551330566, "global_step": 413847, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0546858310699463, "global_step": 413848, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.176546335220337, "global_step": 413849, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1050009727478027, "global_step": 413850, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1163299083709717, "global_step": 413851, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.075535535812378, "global_step": 413852, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.098860740661621, "global_step": 413853, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.103060483932495, "global_step": 413854, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0634777545928955, "global_step": 413855, "epoch": 776, "lr": 5e-05}
{"train_loss": 1.9532254934310913, "global_step": 413856, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.024583578109741, "global_step": 413857, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.054668664932251, "global_step": 413858, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0918307304382324, "global_step": 413859, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1619749069213867, "global_step": 413860, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0420501232147217, "global_step": 413861, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0823450088500977, "global_step": 413862, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1717257499694824, "global_step": 413863, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.07244610786438, "global_step": 413864, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.056558132171631, "global_step": 413865, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0664618015289307, "global_step": 413866, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1323769092559814, "global_step": 413867, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.2082808017730713, "global_step": 413868, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0625178813934326, "global_step": 413869, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1879184246063232, "global_step": 413870, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1215484142303467, "global_step": 413871, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1035618782043457, "global_step": 413872, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1192727088928223, "global_step": 413873, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.070815086364746, "global_step": 413874, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1634387969970703, "global_step": 413875, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.245774984359741, "global_step": 413876, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1010189056396484, "global_step": 413877, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.150697946548462, "global_step": 413878, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.04476261138916, "global_step": 413879, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.032472610473633, "global_step": 413880, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0973854064941406, "global_step": 413881, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.16113543510437, "global_step": 413882, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.022078275680542, "global_step": 413883, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0692596435546875, "global_step": 413884, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.037412643432617, "global_step": 413885, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0171806812286377, "global_step": 413886, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.041006088256836, "global_step": 413887, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0801713466644287, "global_step": 413888, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0427157878875732, "global_step": 413889, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.1494078636169434, "global_step": 413890, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.044811487197876, "global_step": 413891, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.093312978744507, "global_step": 413892, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.113093852996826, "global_step": 413893, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.065896511077881, "global_step": 413894, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.0902252197265625, "global_step": 413895, "epoch": 776, "lr": 5e-05}
{"train_loss": 2.043034553527832, "global_step": 413896, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1813511848449707, "global_step": 413897, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1204514503479004, "global_step": 413898, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0314037799835205, "global_step": 413899, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0699198246002197, "global_step": 413900, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.113882064819336, "global_step": 413901, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.029845714569092, "global_step": 413902, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1529383659362793, "global_step": 413903, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0727455615997314, "global_step": 413904, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0881173610687256, "global_step": 413905, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1824023723602295, "global_step": 413906, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0498337745666504, "global_step": 413907, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9984452724456787, "global_step": 413908, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0609018802642822, "global_step": 413909, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0129106044769287, "global_step": 413910, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0114448070526123, "global_step": 413911, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1053264141082764, "global_step": 413912, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.001378297805786, "global_step": 413913, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.15539288520813, "global_step": 413914, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0431015491485596, "global_step": 413915, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0528664588928223, "global_step": 413916, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0039896965026855, "global_step": 413917, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0863239765167236, "global_step": 413918, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.065903425216675, "global_step": 413919, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1119842529296875, "global_step": 413920, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0564799308776855, "global_step": 413921, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0991673469543457, "global_step": 413922, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0792653560638428, "global_step": 413923, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.082826852798462, "global_step": 413924, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9992784261703491, "global_step": 413925, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.056593894958496, "global_step": 413926, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1008176803588867, "global_step": 413927, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0420970916748047, "global_step": 413928, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0412425994873047, "global_step": 413929, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0404088497161865, "global_step": 413930, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1475422382354736, "global_step": 413931, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0897116661071777, "global_step": 413932, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0613040924072266, "global_step": 413933, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1530752182006836, "global_step": 413934, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.055248260498047, "global_step": 413935, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1031603813171387, "global_step": 413936, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.156122922897339, "global_step": 413937, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.022796869277954, "global_step": 413938, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0434513092041016, "global_step": 413939, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.065643310546875, "global_step": 413940, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0921638011932373, "global_step": 413941, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0907113552093506, "global_step": 413942, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.073312520980835, "global_step": 413943, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0893170833587646, "global_step": 413944, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1423909664154053, "global_step": 413945, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0516836643218994, "global_step": 413946, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.093623638153076, "global_step": 413947, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0958123207092285, "global_step": 413948, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0767836570739746, "global_step": 413949, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.139460563659668, "global_step": 413950, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0841591358184814, "global_step": 413951, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.061687707901001, "global_step": 413952, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.095278024673462, "global_step": 413953, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0262210369110107, "global_step": 413954, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.111130714416504, "global_step": 413955, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9935405254364014, "global_step": 413956, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0793814659118652, "global_step": 413957, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.095486879348755, "global_step": 413958, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.019211769104004, "global_step": 413959, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0674684047698975, "global_step": 413960, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.072460174560547, "global_step": 413961, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.105769395828247, "global_step": 413962, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0376088619232178, "global_step": 413963, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0180487632751465, "global_step": 413964, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.104419231414795, "global_step": 413965, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0913524627685547, "global_step": 413966, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.088186025619507, "global_step": 413967, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0986835956573486, "global_step": 413968, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.177518129348755, "global_step": 413969, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0524001121520996, "global_step": 413970, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.154628276824951, "global_step": 413971, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1039814949035645, "global_step": 413972, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.009693145751953, "global_step": 413973, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0775718688964844, "global_step": 413974, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1245875358581543, "global_step": 413975, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0092415809631348, "global_step": 413976, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.10211443901062, "global_step": 413977, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0654070377349854, "global_step": 413978, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0868654251098633, "global_step": 413979, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1399779319763184, "global_step": 413980, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0727670192718506, "global_step": 413981, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1141107082366943, "global_step": 413982, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0666427612304688, "global_step": 413983, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.021610736846924, "global_step": 413984, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0371720790863037, "global_step": 413985, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.11985445022583, "global_step": 413986, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.016242265701294, "global_step": 413987, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.078212261199951, "global_step": 413988, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0642149448394775, "global_step": 413989, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0754010677337646, "global_step": 413990, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1010525226593018, "global_step": 413991, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0886197090148926, "global_step": 413992, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.143155813217163, "global_step": 413993, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0264408588409424, "global_step": 413994, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1452646255493164, "global_step": 413995, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0909199714660645, "global_step": 413996, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.075119733810425, "global_step": 413997, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.180628776550293, "global_step": 413998, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9906556606292725, "global_step": 413999, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.080937623977661, "global_step": 414000, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.100353479385376, "global_step": 414001, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.112482786178589, "global_step": 414002, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0574142932891846, "global_step": 414003, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0830140113830566, "global_step": 414004, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0333828926086426, "global_step": 414005, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.148711681365967, "global_step": 414006, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.105095386505127, "global_step": 414007, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1573190689086914, "global_step": 414008, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.152534246444702, "global_step": 414009, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.160489797592163, "global_step": 414010, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0723724365234375, "global_step": 414011, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.067758083343506, "global_step": 414012, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.114044666290283, "global_step": 414013, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.04048490524292, "global_step": 414014, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1213631629943848, "global_step": 414015, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.119267225265503, "global_step": 414016, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9907948970794678, "global_step": 414017, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1697590351104736, "global_step": 414018, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.06693696975708, "global_step": 414019, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1231837272644043, "global_step": 414020, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1661629676818848, "global_step": 414021, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.104222536087036, "global_step": 414022, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1260905265808105, "global_step": 414023, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.131143093109131, "global_step": 414024, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1157917976379395, "global_step": 414025, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0364737510681152, "global_step": 414026, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.184401273727417, "global_step": 414027, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0896835327148438, "global_step": 414028, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.132830858230591, "global_step": 414029, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0635149478912354, "global_step": 414030, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.043997287750244, "global_step": 414031, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1396677494049072, "global_step": 414032, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0765202045440674, "global_step": 414033, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9998018741607666, "global_step": 414034, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.147702217102051, "global_step": 414035, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0720369815826416, "global_step": 414036, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0989596843719482, "global_step": 414037, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.101196050643921, "global_step": 414038, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0972177982330322, "global_step": 414039, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0263354778289795, "global_step": 414040, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1585967540740967, "global_step": 414041, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1192550659179688, "global_step": 414042, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1165988445281982, "global_step": 414043, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0507471561431885, "global_step": 414044, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0685946941375732, "global_step": 414045, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1395537853240967, "global_step": 414046, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0461578369140625, "global_step": 414047, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0834970474243164, "global_step": 414048, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0763351917266846, "global_step": 414049, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.172912120819092, "global_step": 414050, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0935864448547363, "global_step": 414051, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1429123878479004, "global_step": 414052, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.021043300628662, "global_step": 414053, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0318965911865234, "global_step": 414054, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.080977201461792, "global_step": 414055, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.088205337524414, "global_step": 414056, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.037693738937378, "global_step": 414057, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1830859184265137, "global_step": 414058, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0729916095733643, "global_step": 414059, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1328344345092773, "global_step": 414060, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0766377449035645, "global_step": 414061, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.056452751159668, "global_step": 414062, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.069139242172241, "global_step": 414063, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.13053035736084, "global_step": 414064, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0254344940185547, "global_step": 414065, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.053459644317627, "global_step": 414066, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.150460720062256, "global_step": 414067, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1205108165740967, "global_step": 414068, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.123264789581299, "global_step": 414069, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9537595510482788, "global_step": 414070, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0980119705200195, "global_step": 414071, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1242566108703613, "global_step": 414072, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.142434597015381, "global_step": 414073, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.051635980606079, "global_step": 414074, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.112898349761963, "global_step": 414075, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1069064140319824, "global_step": 414076, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.03110408782959, "global_step": 414077, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.109255313873291, "global_step": 414078, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.082179307937622, "global_step": 414079, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.038926839828491, "global_step": 414080, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0437960624694824, "global_step": 414081, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0906434059143066, "global_step": 414082, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.076948881149292, "global_step": 414083, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.053882122039795, "global_step": 414084, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.058568000793457, "global_step": 414085, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.09340238571167, "global_step": 414086, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0454304218292236, "global_step": 414087, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.079669713973999, "global_step": 414088, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.044896125793457, "global_step": 414089, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0409889221191406, "global_step": 414090, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.037079334259033, "global_step": 414091, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0658295154571533, "global_step": 414092, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9933087825775146, "global_step": 414093, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.152541160583496, "global_step": 414094, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0633840560913086, "global_step": 414095, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0279881954193115, "global_step": 414096, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.048363208770752, "global_step": 414097, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0760838985443115, "global_step": 414098, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.970918893814087, "global_step": 414099, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1350111961364746, "global_step": 414100, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1040048599243164, "global_step": 414101, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1509945392608643, "global_step": 414102, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1171939373016357, "global_step": 414103, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0403449535369873, "global_step": 414104, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.115725517272949, "global_step": 414105, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0856103897094727, "global_step": 414106, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0762808322906494, "global_step": 414107, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.076948642730713, "global_step": 414108, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0390853881835938, "global_step": 414109, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.075035333633423, "global_step": 414110, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0553112030029297, "global_step": 414111, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0045816898345947, "global_step": 414112, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1296396255493164, "global_step": 414113, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.139443874359131, "global_step": 414114, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.135495185852051, "global_step": 414115, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1536974906921387, "global_step": 414116, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.012519359588623, "global_step": 414117, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1513774394989014, "global_step": 414118, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.073702335357666, "global_step": 414119, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1225943565368652, "global_step": 414120, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.045196056365967, "global_step": 414121, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0315849781036377, "global_step": 414122, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.061365842819214, "global_step": 414123, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.085806369781494, "global_step": 414124, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.120633840560913, "global_step": 414125, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0279061794281006, "global_step": 414126, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0699455738067627, "global_step": 414127, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1106066703796387, "global_step": 414128, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1258606910705566, "global_step": 414129, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0684592723846436, "global_step": 414130, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.113595485687256, "global_step": 414131, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9925916194915771, "global_step": 414132, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.087421417236328, "global_step": 414133, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9931610822677612, "global_step": 414134, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.131251573562622, "global_step": 414135, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.076151132583618, "global_step": 414136, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0972793102264404, "global_step": 414137, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.017427444458008, "global_step": 414138, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0886056423187256, "global_step": 414139, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1350677013397217, "global_step": 414140, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0628695487976074, "global_step": 414141, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0879623889923096, "global_step": 414142, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.111253023147583, "global_step": 414143, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0935842990875244, "global_step": 414144, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0182573795318604, "global_step": 414145, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0764055252075195, "global_step": 414146, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1360831260681152, "global_step": 414147, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.085627317428589, "global_step": 414148, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0979979038238525, "global_step": 414149, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1167593002319336, "global_step": 414150, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.092423677444458, "global_step": 414151, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0911083221435547, "global_step": 414152, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.10622501373291, "global_step": 414153, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0578200817108154, "global_step": 414154, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.123023271560669, "global_step": 414155, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.187746524810791, "global_step": 414156, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.082627296447754, "global_step": 414157, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.080301523208618, "global_step": 414158, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0413012504577637, "global_step": 414159, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1900060176849365, "global_step": 414160, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1989428997039795, "global_step": 414161, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0979886054992676, "global_step": 414162, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0252556800842285, "global_step": 414163, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.032456398010254, "global_step": 414164, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1104297637939453, "global_step": 414165, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.107916831970215, "global_step": 414166, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.093798875808716, "global_step": 414167, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0706677436828613, "global_step": 414168, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.147862195968628, "global_step": 414169, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0658042430877686, "global_step": 414170, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1081840991973877, "global_step": 414171, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.121656656265259, "global_step": 414172, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.073147773742676, "global_step": 414173, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.064729690551758, "global_step": 414174, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0697154998779297, "global_step": 414175, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0677130222320557, "global_step": 414176, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0335538387298584, "global_step": 414177, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.990617275238037, "global_step": 414178, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0651443004608154, "global_step": 414179, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.091357469558716, "global_step": 414180, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.090296745300293, "global_step": 414181, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.085949182510376, "global_step": 414182, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0526506900787354, "global_step": 414183, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.05936861038208, "global_step": 414184, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.188981056213379, "global_step": 414185, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0922975540161133, "global_step": 414186, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.163175106048584, "global_step": 414187, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0588064193725586, "global_step": 414188, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0875861644744873, "global_step": 414189, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1112027168273926, "global_step": 414190, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1307685375213623, "global_step": 414191, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0163371562957764, "global_step": 414192, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.145758628845215, "global_step": 414193, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0591654777526855, "global_step": 414194, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1487066745758057, "global_step": 414195, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0963315963745117, "global_step": 414196, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.110844612121582, "global_step": 414197, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.124659776687622, "global_step": 414198, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.049272298812866, "global_step": 414199, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.060237407684326, "global_step": 414200, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.144603729248047, "global_step": 414201, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0009329319000244, "global_step": 414202, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9951404333114624, "global_step": 414203, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.067235231399536, "global_step": 414204, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.049494743347168, "global_step": 414205, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.070786714553833, "global_step": 414206, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1020162105560303, "global_step": 414207, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0736496448516846, "global_step": 414208, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0920162200927734, "global_step": 414209, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.113617181777954, "global_step": 414210, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1929852962493896, "global_step": 414211, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1076955795288086, "global_step": 414212, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1034188270568848, "global_step": 414213, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.2027673721313477, "global_step": 414214, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0974619388580322, "global_step": 414215, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0716183185577393, "global_step": 414216, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.084833860397339, "global_step": 414217, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0865588188171387, "global_step": 414218, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1535487174987793, "global_step": 414219, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.997015357017517, "global_step": 414220, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.130211353302002, "global_step": 414221, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.077094078063965, "global_step": 414222, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.011898994445801, "global_step": 414223, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1277315616607666, "global_step": 414224, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.132742166519165, "global_step": 414225, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.144243001937866, "global_step": 414226, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.03377103805542, "global_step": 414227, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0195932388305664, "global_step": 414228, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.082500457763672, "global_step": 414229, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.052067279815674, "global_step": 414230, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0439915657043457, "global_step": 414231, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1603925228118896, "global_step": 414232, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.146420478820801, "global_step": 414233, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1293179988861084, "global_step": 414234, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9991073608398438, "global_step": 414235, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0350756645202637, "global_step": 414236, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.101982831954956, "global_step": 414237, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0894875526428223, "global_step": 414238, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0666236877441406, "global_step": 414239, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.061932325363159, "global_step": 414240, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.057544469833374, "global_step": 414241, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.067528009414673, "global_step": 414242, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.099472761154175, "global_step": 414243, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.073563575744629, "global_step": 414244, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0875332355499268, "global_step": 414245, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0567855834960938, "global_step": 414246, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.077784538269043, "global_step": 414247, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.112602710723877, "global_step": 414248, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1301417350769043, "global_step": 414249, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0292482376098633, "global_step": 414250, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1015701293945312, "global_step": 414251, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.142587184906006, "global_step": 414252, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.104583978652954, "global_step": 414253, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1545324325561523, "global_step": 414254, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1950290203094482, "global_step": 414255, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.075429916381836, "global_step": 414256, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1086347103118896, "global_step": 414257, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.076071262359619, "global_step": 414258, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.038174867630005, "global_step": 414259, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0714898109436035, "global_step": 414260, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0911030769348145, "global_step": 414261, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0966544151306152, "global_step": 414262, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1308298110961914, "global_step": 414263, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1245503425598145, "global_step": 414264, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.029313325881958, "global_step": 414265, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1231651306152344, "global_step": 414266, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.030487298965454, "global_step": 414267, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1741530895233154, "global_step": 414268, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0520875453948975, "global_step": 414269, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.053985834121704, "global_step": 414270, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1343815326690674, "global_step": 414271, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0239107608795166, "global_step": 414272, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0491507053375244, "global_step": 414273, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.028831958770752, "global_step": 414274, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.045257091522217, "global_step": 414275, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.100198745727539, "global_step": 414276, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.049863815307617, "global_step": 414277, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0649826526641846, "global_step": 414278, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1013386249542236, "global_step": 414279, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.139802932739258, "global_step": 414280, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0644075870513916, "global_step": 414281, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0899765491485596, "global_step": 414282, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1662588119506836, "global_step": 414283, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.129373073577881, "global_step": 414284, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.098031520843506, "global_step": 414285, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.01755690574646, "global_step": 414286, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.117748260498047, "global_step": 414287, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1520814895629883, "global_step": 414288, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1522817611694336, "global_step": 414289, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.113405227661133, "global_step": 414290, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0382049083709717, "global_step": 414291, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.084702968597412, "global_step": 414292, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9708905220031738, "global_step": 414293, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1150710582733154, "global_step": 414294, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1201305389404297, "global_step": 414295, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.099520206451416, "global_step": 414296, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1509854793548584, "global_step": 414297, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.053539752960205, "global_step": 414298, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.126481056213379, "global_step": 414299, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1455819606781006, "global_step": 414300, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.049135446548462, "global_step": 414301, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0945074558258057, "global_step": 414302, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9155776500701904, "global_step": 414303, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1099514961242676, "global_step": 414304, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0493366718292236, "global_step": 414305, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0675594806671143, "global_step": 414306, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.165365219116211, "global_step": 414307, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.160593271255493, "global_step": 414308, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.102677345275879, "global_step": 414309, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1406948566436768, "global_step": 414310, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0658445358276367, "global_step": 414311, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0844123363494873, "global_step": 414312, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.126605987548828, "global_step": 414313, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1176493167877197, "global_step": 414314, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.097651481628418, "global_step": 414315, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1256003379821777, "global_step": 414316, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.024627208709717, "global_step": 414317, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.092986822128296, "global_step": 414318, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.061044454574585, "global_step": 414319, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1023244857788086, "global_step": 414320, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.135485887527466, "global_step": 414321, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1048991680145264, "global_step": 414322, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9604812860488892, "global_step": 414323, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0619800090789795, "global_step": 414324, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0945215225219727, "global_step": 414325, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.155625343322754, "global_step": 414326, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0515100955963135, "global_step": 414327, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.098856210708618, "global_step": 414328, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1115646362304688, "global_step": 414329, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.070181131362915, "global_step": 414330, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1512296199798584, "global_step": 414331, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.158328056335449, "global_step": 414332, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1316678524017334, "global_step": 414333, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1110100746154785, "global_step": 414334, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0697598457336426, "global_step": 414335, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1418960094451904, "global_step": 414336, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.93619966506958, "global_step": 414337, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0812976360321045, "global_step": 414338, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0973892211914062, "global_step": 414339, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.060551404953003, "global_step": 414340, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1187593936920166, "global_step": 414341, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0707240104675293, "global_step": 414342, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1110849380493164, "global_step": 414343, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.072018623352051, "global_step": 414344, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.128288745880127, "global_step": 414345, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.057729482650757, "global_step": 414346, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.102243423461914, "global_step": 414347, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1264796257019043, "global_step": 414348, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0549488067626953, "global_step": 414349, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1537954807281494, "global_step": 414350, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0908868312835693, "global_step": 414351, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0499234199523926, "global_step": 414352, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.139148235321045, "global_step": 414353, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.103846788406372, "global_step": 414354, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1066370010375977, "global_step": 414355, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0455996990203857, "global_step": 414356, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.096355438232422, "global_step": 414357, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.163667678833008, "global_step": 414358, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.179062843322754, "global_step": 414359, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.106848955154419, "global_step": 414360, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.063662528991699, "global_step": 414361, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0219733715057373, "global_step": 414362, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.080928087234497, "global_step": 414363, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0324313640594482, "global_step": 414364, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0953335762023926, "global_step": 414365, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.136251449584961, "global_step": 414366, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0989067554473877, "global_step": 414367, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0654587745666504, "global_step": 414368, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.082080364227295, "global_step": 414369, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.129344940185547, "global_step": 414370, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.100642442703247, "global_step": 414371, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.088120937347412, "global_step": 414372, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1206135749816895, "global_step": 414373, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0235557556152344, "global_step": 414374, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0560972690582275, "global_step": 414375, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9490686655044556, "global_step": 414376, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1288444995880127, "global_step": 414377, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0739951133728027, "global_step": 414378, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.154478073120117, "global_step": 414379, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0740697383880615, "global_step": 414380, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1163620948791504, "global_step": 414381, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0438294410705566, "global_step": 414382, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0901477336883545, "global_step": 414383, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9974256753921509, "global_step": 414384, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0953290462493896, "global_step": 414385, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1182546615600586, "global_step": 414386, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0868074893951416, "global_step": 414387, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1425015926361084, "global_step": 414388, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1263620853424072, "global_step": 414389, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.141239643096924, "global_step": 414390, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0710911750793457, "global_step": 414391, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0950570106506348, "global_step": 414392, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1136655807495117, "global_step": 414393, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.055906295776367, "global_step": 414394, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.032254219055176, "global_step": 414395, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.011880397796631, "global_step": 414396, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.122455596923828, "global_step": 414397, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.049213409423828, "global_step": 414398, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1368026733398438, "global_step": 414399, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1165266036987305, "global_step": 414400, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1420164108276367, "global_step": 414401, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.121899127960205, "global_step": 414402, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.079589366912842, "global_step": 414403, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0559120178222656, "global_step": 414404, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1731622219085693, "global_step": 414405, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0355396270751953, "global_step": 414406, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.154451847076416, "global_step": 414407, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0454349517822266, "global_step": 414408, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9858747720718384, "global_step": 414409, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1282291412353516, "global_step": 414410, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.2002980709075928, "global_step": 414411, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0656750202178955, "global_step": 414412, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.152421712875366, "global_step": 414413, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0775551795959473, "global_step": 414414, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1016321182250977, "global_step": 414415, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0648465156555176, "global_step": 414416, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0466220378875732, "global_step": 414417, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.016854763031006, "global_step": 414418, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.110224723815918, "global_step": 414419, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.045151472091675, "global_step": 414420, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.093167781829834, "global_step": 414421, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.101733684539795, "global_step": 414422, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1398942470550537, "global_step": 414423, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0767831802368164, "global_step": 414424, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.053912878036499, "global_step": 414425, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.056335687637329, "global_step": 414426, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1129610538482666, "global_step": 414427, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1626715660095215, "global_step": 414428, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.095733165740967, "global_step": 414429, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.064002275466919, "global_step": 414430, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.091270923614502, "global_step": 414431, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.108832836151123, "global_step": 414432, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0775723457336426, "global_step": 414433, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.052464246749878, "global_step": 414434, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1035492420196533, "global_step": 414435, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.100740909576416, "global_step": 414436, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.107530117034912, "global_step": 414437, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1174838542938232, "global_step": 414438, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.078809976577759, "global_step": 414439, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1341240406036377, "global_step": 414440, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0150508880615234, "global_step": 414441, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0858514308929443, "global_step": 414442, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.069390296936035, "global_step": 414443, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0601086616516113, "global_step": 414444, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1821482181549072, "global_step": 414445, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.051689863204956, "global_step": 414446, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0551655292510986, "global_step": 414447, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.085348606109619, "global_step": 414448, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0642690658569336, "global_step": 414449, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.168328046798706, "global_step": 414450, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.153531074523926, "global_step": 414451, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0762650966644287, "global_step": 414452, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0817794799804688, "global_step": 414453, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.091078758239746, "global_step": 414454, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0896947383880615, "global_step": 414455, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0772860050201416, "global_step": 414456, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1435117721557617, "global_step": 414457, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1457316875457764, "global_step": 414458, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1172101497650146, "global_step": 414459, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.013495445251465, "global_step": 414460, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0704331398010254, "global_step": 414461, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1012539863586426, "global_step": 414462, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0745067596435547, "global_step": 414463, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1493983268737793, "global_step": 414464, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.14047908782959, "global_step": 414465, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.182086944580078, "global_step": 414466, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1213510036468506, "global_step": 414467, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.109748363494873, "global_step": 414468, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.098385810852051, "global_step": 414469, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0587899684906006, "global_step": 414470, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.152738094329834, "global_step": 414471, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.014312505722046, "global_step": 414472, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0929222106933594, "global_step": 414473, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0380048751831055, "global_step": 414474, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.078169107437134, "global_step": 414475, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.096916437149048, "global_step": 414476, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.074263095855713, "global_step": 414477, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.080310583114624, "global_step": 414478, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0892317295074463, "global_step": 414479, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1158030033111572, "global_step": 414480, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.127696990966797, "global_step": 414481, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.058117628097534, "global_step": 414482, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0362486839294434, "global_step": 414483, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1120405197143555, "global_step": 414484, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0853352546691895, "global_step": 414485, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.085847854614258, "global_step": 414486, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.076585292816162, "global_step": 414487, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.133119821548462, "global_step": 414488, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.040210008621216, "global_step": 414489, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0812718868255615, "global_step": 414490, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1493446826934814, "global_step": 414491, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.145799398422241, "global_step": 414492, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1546876430511475, "global_step": 414493, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0836329460144043, "global_step": 414494, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1140570640563965, "global_step": 414495, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0738441944122314, "global_step": 414496, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.049656629562378, "global_step": 414497, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1492226123809814, "global_step": 414498, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.102891683578491, "global_step": 414499, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1121859550476074, "global_step": 414500, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0218424797058105, "global_step": 414501, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1217591762542725, "global_step": 414502, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.069312572479248, "global_step": 414503, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9580491781234741, "global_step": 414504, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1246840953826904, "global_step": 414505, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1370296478271484, "global_step": 414506, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1387391090393066, "global_step": 414507, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.070676565170288, "global_step": 414508, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9998753070831299, "global_step": 414509, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.04463267326355, "global_step": 414510, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.134310483932495, "global_step": 414511, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0744473934173584, "global_step": 414512, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1519687175750732, "global_step": 414513, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.102275848388672, "global_step": 414514, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.168785572052002, "global_step": 414515, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.066375255584717, "global_step": 414516, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0723016262054443, "global_step": 414517, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0806541442871094, "global_step": 414518, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1469929218292236, "global_step": 414519, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0949552059173584, "global_step": 414520, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.07289981842041, "global_step": 414521, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.055736780166626, "global_step": 414522, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.063218593597412, "global_step": 414523, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.126685619354248, "global_step": 414524, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.100245237350464, "global_step": 414525, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.073699951171875, "global_step": 414526, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1223630905151367, "global_step": 414527, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.022517442703247, "global_step": 414528, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.154452085494995, "global_step": 414529, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.050468683242798, "global_step": 414530, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1343133449554443, "global_step": 414531, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0890965461730957, "global_step": 414532, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0761218070983887, "global_step": 414533, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0421199798583984, "global_step": 414534, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.138251304626465, "global_step": 414535, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.059190273284912, "global_step": 414536, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0870168209075928, "global_step": 414537, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0488548278808594, "global_step": 414538, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1358087062835693, "global_step": 414539, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.170877695083618, "global_step": 414540, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.081779718399048, "global_step": 414541, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0528461933135986, "global_step": 414542, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.09592604637146, "global_step": 414543, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1258668899536133, "global_step": 414544, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0814828872680664, "global_step": 414545, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1407201290130615, "global_step": 414546, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1764895915985107, "global_step": 414547, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.025834560394287, "global_step": 414548, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0539841651916504, "global_step": 414549, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.093599319458008, "global_step": 414550, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0828869342803955, "global_step": 414551, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1246461868286133, "global_step": 414552, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1149497032165527, "global_step": 414553, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0332658290863037, "global_step": 414554, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.028261661529541, "global_step": 414555, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1718227863311768, "global_step": 414556, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.10603928565979, "global_step": 414557, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0092437267303467, "global_step": 414558, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.114480972290039, "global_step": 414559, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.068250894546509, "global_step": 414560, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1449270248413086, "global_step": 414561, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.108872175216675, "global_step": 414562, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.086853504180908, "global_step": 414563, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0513947010040283, "global_step": 414564, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.015523910522461, "global_step": 414565, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0193920135498047, "global_step": 414566, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.085406541824341, "global_step": 414567, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.126586675643921, "global_step": 414568, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.056466579437256, "global_step": 414569, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.032123565673828, "global_step": 414570, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.091531991958618, "global_step": 414571, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.087773084640503, "global_step": 414572, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0506293773651123, "global_step": 414573, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1467788219451904, "global_step": 414574, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0369954109191895, "global_step": 414575, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0962700843811035, "global_step": 414576, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.058820962905884, "global_step": 414577, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.113600730895996, "global_step": 414578, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0645909309387207, "global_step": 414579, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1406404972076416, "global_step": 414580, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0192995071411133, "global_step": 414581, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1539692878723145, "global_step": 414582, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1089611053466797, "global_step": 414583, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.110942840576172, "global_step": 414584, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.097975969314575, "global_step": 414585, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.039289712905884, "global_step": 414586, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1325082778930664, "global_step": 414587, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1852569580078125, "global_step": 414588, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1081695556640625, "global_step": 414589, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1327147483825684, "global_step": 414590, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.034731388092041, "global_step": 414591, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1073086261749268, "global_step": 414592, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.08721923828125, "global_step": 414593, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.06111216545105, "global_step": 414594, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.091810941696167, "global_step": 414595, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0862271785736084, "global_step": 414596, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0717968940734863, "global_step": 414597, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.123155355453491, "global_step": 414598, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0334506034851074, "global_step": 414599, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0842251777648926, "global_step": 414600, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0397891998291016, "global_step": 414601, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1055357456207275, "global_step": 414602, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.206547975540161, "global_step": 414603, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0614118576049805, "global_step": 414604, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.146880865097046, "global_step": 414605, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9952943325042725, "global_step": 414606, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.091559886932373, "global_step": 414607, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.099296808242798, "global_step": 414608, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0239498615264893, "global_step": 414609, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1367180347442627, "global_step": 414610, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.121927261352539, "global_step": 414611, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0570085048675537, "global_step": 414612, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.086719512939453, "global_step": 414613, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.015977144241333, "global_step": 414614, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0881850719451904, "global_step": 414615, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1213173866271973, "global_step": 414616, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1633644104003906, "global_step": 414617, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.085984468460083, "global_step": 414618, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.033067464828491, "global_step": 414619, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.082660675048828, "global_step": 414620, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.157111883163452, "global_step": 414621, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.099454402923584, "global_step": 414622, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.115805149078369, "global_step": 414623, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0803585052490234, "global_step": 414624, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0758771896362305, "global_step": 414625, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0632402896881104, "global_step": 414626, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0986950397491455, "global_step": 414627, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0732247829437256, "global_step": 414628, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1321215629577637, "global_step": 414629, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.05673885345459, "global_step": 414630, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1113083362579346, "global_step": 414631, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.152190685272217, "global_step": 414632, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.010007381439209, "global_step": 414633, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.117750406265259, "global_step": 414634, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1092493534088135, "global_step": 414635, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0431265830993652, "global_step": 414636, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.091154098510742, "global_step": 414637, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9654172658920288, "global_step": 414638, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.165558099746704, "global_step": 414639, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.079948902130127, "global_step": 414640, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.016904592514038, "global_step": 414641, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1503818035125732, "global_step": 414642, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0844244956970215, "global_step": 414643, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0498359203338623, "global_step": 414644, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1477506160736084, "global_step": 414645, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.068164587020874, "global_step": 414646, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.084733486175537, "global_step": 414647, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0808141231536865, "global_step": 414648, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.06965970993042, "global_step": 414649, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0128448009490967, "global_step": 414650, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1153769493103027, "global_step": 414651, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.2103488445281982, "global_step": 414652, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0486550331115723, "global_step": 414653, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.08622407913208, "global_step": 414654, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1374833583831787, "global_step": 414655, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0179381370544434, "global_step": 414656, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.074401617050171, "global_step": 414657, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0697600841522217, "global_step": 414658, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.099514961242676, "global_step": 414659, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1309690475463867, "global_step": 414660, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.052286148071289, "global_step": 414661, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1132235527038574, "global_step": 414662, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1113383769989014, "global_step": 414663, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0783486366271973, "global_step": 414664, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.10540509223938, "global_step": 414665, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.093280553817749, "global_step": 414666, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1030704975128174, "global_step": 414667, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0616073608398438, "global_step": 414668, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.138838768005371, "global_step": 414669, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.135054111480713, "global_step": 414670, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0831351280212402, "global_step": 414671, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.094815254211426, "global_step": 414672, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0976414680480957, "global_step": 414673, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1097910404205322, "global_step": 414674, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.104149341583252, "global_step": 414675, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0929219722747803, "global_step": 414676, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1391966342926025, "global_step": 414677, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1697192192077637, "global_step": 414678, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.047346353530884, "global_step": 414679, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.018611192703247, "global_step": 414680, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.088515043258667, "global_step": 414681, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.088060140609741, "global_step": 414682, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.125561237335205, "global_step": 414683, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1592390537261963, "global_step": 414684, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.117584228515625, "global_step": 414685, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1095643043518066, "global_step": 414686, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.101717233657837, "global_step": 414687, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.077622413635254, "global_step": 414688, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.095435857772827, "global_step": 414689, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0911433696746826, "global_step": 414690, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1424331665039062, "global_step": 414691, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1173107624053955, "global_step": 414692, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.107766628265381, "global_step": 414693, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0742592811584473, "global_step": 414694, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0741024017333984, "global_step": 414695, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1275885105133057, "global_step": 414696, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1418545246124268, "global_step": 414697, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.090179920196533, "global_step": 414698, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.045834541320801, "global_step": 414699, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0426714420318604, "global_step": 414700, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1109743118286133, "global_step": 414701, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1321420669555664, "global_step": 414702, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1453020572662354, "global_step": 414703, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0490989685058594, "global_step": 414704, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.215688943862915, "global_step": 414705, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0309255123138428, "global_step": 414706, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1064565181732178, "global_step": 414707, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9971020221710205, "global_step": 414708, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1299328804016113, "global_step": 414709, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0472404956817627, "global_step": 414710, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.035071849822998, "global_step": 414711, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.060194253921509, "global_step": 414712, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.073141574859619, "global_step": 414713, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.097942590713501, "global_step": 414714, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1220388412475586, "global_step": 414715, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0147175788879395, "global_step": 414716, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.070751428604126, "global_step": 414717, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.119166851043701, "global_step": 414718, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0452661514282227, "global_step": 414719, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1668248176574707, "global_step": 414720, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.065919876098633, "global_step": 414721, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1436800956726074, "global_step": 414722, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9996625185012817, "global_step": 414723, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1478140354156494, "global_step": 414724, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0017402172088623, "global_step": 414725, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.039524555206299, "global_step": 414726, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0971803665161133, "global_step": 414727, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.031606674194336, "global_step": 414728, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0117053985595703, "global_step": 414729, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.086383819580078, "global_step": 414730, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0723447799682617, "global_step": 414731, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1321613788604736, "global_step": 414732, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0307962894439697, "global_step": 414733, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.110689640045166, "global_step": 414734, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0010623931884766, "global_step": 414735, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0525598526000977, "global_step": 414736, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1023077964782715, "global_step": 414737, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1045572757720947, "global_step": 414738, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0877013206481934, "global_step": 414739, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.143343448638916, "global_step": 414740, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.06758975982666, "global_step": 414741, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9943873882293701, "global_step": 414742, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0952069759368896, "global_step": 414743, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0789952278137207, "global_step": 414744, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.127660036087036, "global_step": 414745, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.111837863922119, "global_step": 414746, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.059833288192749, "global_step": 414747, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1005332469940186, "global_step": 414748, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1154561042785645, "global_step": 414749, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0962460041046143, "global_step": 414750, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.2000186443328857, "global_step": 414751, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.054955005645752, "global_step": 414752, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1353847980499268, "global_step": 414753, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.140519380569458, "global_step": 414754, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.093275785446167, "global_step": 414755, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1068074703216553, "global_step": 414756, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1350460052490234, "global_step": 414757, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1372740268707275, "global_step": 414758, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.034226417541504, "global_step": 414759, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.107388734817505, "global_step": 414760, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0597169399261475, "global_step": 414761, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.076894521713257, "global_step": 414762, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.234032392501831, "global_step": 414763, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0587105751037598, "global_step": 414764, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.093991756439209, "global_step": 414765, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1661736965179443, "global_step": 414766, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1121132373809814, "global_step": 414767, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1489250659942627, "global_step": 414768, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.077195167541504, "global_step": 414769, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.112154245376587, "global_step": 414770, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1490607261657715, "global_step": 414771, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1480815410614014, "global_step": 414772, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.167203426361084, "global_step": 414773, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0734660625457764, "global_step": 414774, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0472774505615234, "global_step": 414775, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0474231243133545, "global_step": 414776, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.144024133682251, "global_step": 414777, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.10280179977417, "global_step": 414778, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0971157550811768, "global_step": 414779, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0862221717834473, "global_step": 414780, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1364264488220215, "global_step": 414781, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0527069568634033, "global_step": 414782, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.9909615516662598, "global_step": 414783, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0928001403808594, "global_step": 414784, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.045414686203003, "global_step": 414785, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.122422218322754, "global_step": 414786, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.133401870727539, "global_step": 414787, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0862112045288086, "global_step": 414788, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.011692523956299, "global_step": 414789, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0628647804260254, "global_step": 414790, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0459156036376953, "global_step": 414791, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.112884998321533, "global_step": 414792, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1334948539733887, "global_step": 414793, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1410138607025146, "global_step": 414794, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1052680015563965, "global_step": 414795, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0337154865264893, "global_step": 414796, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.161200761795044, "global_step": 414797, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.054748296737671, "global_step": 414798, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0283870697021484, "global_step": 414799, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.129714250564575, "global_step": 414800, "epoch": 777, "lr": 5e-05}
{"train_loss": 1.8977938890457153, "global_step": 414801, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0877597332000732, "global_step": 414802, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.117417812347412, "global_step": 414803, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.02186918258667, "global_step": 414804, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0598578453063965, "global_step": 414805, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0657105445861816, "global_step": 414806, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.103168487548828, "global_step": 414807, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.061316967010498, "global_step": 414808, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0797321796417236, "global_step": 414809, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0465502738952637, "global_step": 414810, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0521373748779297, "global_step": 414811, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1955947875976562, "global_step": 414812, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.05914306640625, "global_step": 414813, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0835063457489014, "global_step": 414814, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1737444400787354, "global_step": 414815, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1127703189849854, "global_step": 414816, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0360031127929688, "global_step": 414817, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.074932336807251, "global_step": 414818, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1528384685516357, "global_step": 414819, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1397392749786377, "global_step": 414820, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.064647912979126, "global_step": 414821, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0604214668273926, "global_step": 414822, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0873472690582275, "global_step": 414823, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1157479286193848, "global_step": 414824, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1148688793182373, "global_step": 414825, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1314406394958496, "global_step": 414826, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0614712238311768, "global_step": 414827, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0455260276794434, "global_step": 414828, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.083592414855957, "global_step": 414829, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0733184814453125, "global_step": 414830, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1292243003845215, "global_step": 414831, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0614378452301025, "global_step": 414832, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1861608028411865, "global_step": 414833, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.060563087463379, "global_step": 414834, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.015266180038452, "global_step": 414835, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0953831672668457, "global_step": 414836, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1079518795013428, "global_step": 414837, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.2033188343048096, "global_step": 414838, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0371146202087402, "global_step": 414839, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0742602348327637, "global_step": 414840, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.011890172958374, "global_step": 414841, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.034501791000366, "global_step": 414842, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.202974319458008, "global_step": 414843, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1005043983459473, "global_step": 414844, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.097928285598755, "global_step": 414845, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1046152114868164, "global_step": 414846, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.080897331237793, "global_step": 414847, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.033846378326416, "global_step": 414848, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.129582643508911, "global_step": 414849, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1046347618103027, "global_step": 414850, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1730480194091797, "global_step": 414851, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0452702045440674, "global_step": 414852, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.081249475479126, "global_step": 414853, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.035947799682617, "global_step": 414854, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.1083576679229736, "global_step": 414855, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.0869603157043457, "global_step": 414856, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.113616466522217, "global_step": 414857, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.105938673019409, "global_step": 414858, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.108773708343506, "global_step": 414859, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.099597692489624, "global_step": 414860, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.08663272857666, "global_step": 414861, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.003629207611084, "global_step": 414862, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.087512969970703, "global_step": 414863, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.088765859603882, "global_step": 414864, "epoch": 777, "lr": 5e-05}
{"train_loss": 2.068714141845703, "global_step": 414865, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0838394165039062, "global_step": 414866, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1006083488464355, "global_step": 414867, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0502212047576904, "global_step": 414868, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.033578395843506, "global_step": 414869, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.104010581970215, "global_step": 414870, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0951344966888428, "global_step": 414871, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1255717277526855, "global_step": 414872, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.079698324203491, "global_step": 414873, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0828235149383545, "global_step": 414874, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.085171699523926, "global_step": 414875, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.19382905960083, "global_step": 414876, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1046953201293945, "global_step": 414877, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1410553455352783, "global_step": 414878, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0551629066467285, "global_step": 414879, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0661139488220215, "global_step": 414880, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.036724090576172, "global_step": 414881, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.073762893676758, "global_step": 414882, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0982611179351807, "global_step": 414883, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0868794918060303, "global_step": 414884, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0439302921295166, "global_step": 414885, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1441895961761475, "global_step": 414886, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9724584817886353, "global_step": 414887, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.039842367172241, "global_step": 414888, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.051194906234741, "global_step": 414889, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0859570503234863, "global_step": 414890, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0776889324188232, "global_step": 414891, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0406408309936523, "global_step": 414892, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1610891819000244, "global_step": 414893, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0138559341430664, "global_step": 414894, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0914390087127686, "global_step": 414895, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0291383266448975, "global_step": 414896, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.074908971786499, "global_step": 414897, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.075477123260498, "global_step": 414898, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0783920288085938, "global_step": 414899, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0246951580047607, "global_step": 414900, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.049957036972046, "global_step": 414901, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.065300464630127, "global_step": 414902, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.053741693496704, "global_step": 414903, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0642642974853516, "global_step": 414904, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.008338212966919, "global_step": 414905, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.029078722000122, "global_step": 414906, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1480553150177, "global_step": 414907, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1316094398498535, "global_step": 414908, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.14217209815979, "global_step": 414909, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.054711103439331, "global_step": 414910, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.127589225769043, "global_step": 414911, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.139305591583252, "global_step": 414912, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0582499504089355, "global_step": 414913, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0214807987213135, "global_step": 414914, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0384230613708496, "global_step": 414915, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1187374591827393, "global_step": 414916, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0993356704711914, "global_step": 414917, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0185396671295166, "global_step": 414918, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9223239421844482, "global_step": 414919, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.089358329772949, "global_step": 414920, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1067566871643066, "global_step": 414921, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0896811485290527, "global_step": 414922, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0452933311462402, "global_step": 414923, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1112232208251953, "global_step": 414924, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.128450870513916, "global_step": 414925, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1075496673583984, "global_step": 414926, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0604937076568604, "global_step": 414927, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0681042671203613, "global_step": 414928, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.086817741394043, "global_step": 414929, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.168243885040283, "global_step": 414930, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.074653148651123, "global_step": 414931, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.063779354095459, "global_step": 414932, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.075914144515991, "global_step": 414933, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9753352403640747, "global_step": 414934, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0959556102752686, "global_step": 414935, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1267523765563965, "global_step": 414936, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0876522064208984, "global_step": 414937, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.087421178817749, "global_step": 414938, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.123875617980957, "global_step": 414939, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1107940673828125, "global_step": 414940, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.119091272354126, "global_step": 414941, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1242024898529053, "global_step": 414942, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0860724449157715, "global_step": 414943, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0487170219421387, "global_step": 414944, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0420475006103516, "global_step": 414945, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1072652339935303, "global_step": 414946, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.124976634979248, "global_step": 414947, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.13081955909729, "global_step": 414948, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.090944766998291, "global_step": 414949, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.142345905303955, "global_step": 414950, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.087611198425293, "global_step": 414951, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1136765480041504, "global_step": 414952, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1938230991363525, "global_step": 414953, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1048965454101562, "global_step": 414954, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.142939567565918, "global_step": 414955, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0874831676483154, "global_step": 414956, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0426552295684814, "global_step": 414957, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0555646419525146, "global_step": 414958, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.039963722229004, "global_step": 414959, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1476335525512695, "global_step": 414960, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.07106614112854, "global_step": 414961, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.123328924179077, "global_step": 414962, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1299877166748047, "global_step": 414963, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0235581398010254, "global_step": 414964, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.066444158554077, "global_step": 414965, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1784725189208984, "global_step": 414966, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.079538345336914, "global_step": 414967, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.040057897567749, "global_step": 414968, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1722757816314697, "global_step": 414969, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.046180009841919, "global_step": 414970, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.100830078125, "global_step": 414971, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0072524547576904, "global_step": 414972, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.158409595489502, "global_step": 414973, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.073092222213745, "global_step": 414974, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0717058181762695, "global_step": 414975, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1791326999664307, "global_step": 414976, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0261332988739014, "global_step": 414977, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.077268362045288, "global_step": 414978, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.126629590988159, "global_step": 414979, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0755393505096436, "global_step": 414980, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.101445436477661, "global_step": 414981, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.051640510559082, "global_step": 414982, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0798141956329346, "global_step": 414983, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1126279830932617, "global_step": 414984, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.048563003540039, "global_step": 414985, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.052692413330078, "global_step": 414986, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.070991277694702, "global_step": 414987, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.227992534637451, "global_step": 414988, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.172339916229248, "global_step": 414989, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0494844913482666, "global_step": 414990, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.184668779373169, "global_step": 414991, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1503190994262695, "global_step": 414992, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.041372537612915, "global_step": 414993, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0544164180755615, "global_step": 414994, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.108732223510742, "global_step": 414995, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1776373386383057, "global_step": 414996, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0376291275024414, "global_step": 414997, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.051011800765991, "global_step": 414998, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1011035442352295, "global_step": 414999, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.127772092819214, "global_step": 415000, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0862085819244385, "global_step": 415001, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1267924308776855, "global_step": 415002, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0649213790893555, "global_step": 415003, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0435547828674316, "global_step": 415004, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1411139965057373, "global_step": 415005, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.108809471130371, "global_step": 415006, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0469744205474854, "global_step": 415007, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.151634931564331, "global_step": 415008, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1838669776916504, "global_step": 415009, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0811429023742676, "global_step": 415010, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1381425857543945, "global_step": 415011, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0507826805114746, "global_step": 415012, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0772461891174316, "global_step": 415013, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0518572330474854, "global_step": 415014, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1816322803497314, "global_step": 415015, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0234034061431885, "global_step": 415016, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0912230014801025, "global_step": 415017, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9754234552383423, "global_step": 415018, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.093446731567383, "global_step": 415019, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.092616558074951, "global_step": 415020, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0778143405914307, "global_step": 415021, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0054335594177246, "global_step": 415022, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0176875591278076, "global_step": 415023, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1423683166503906, "global_step": 415024, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0278050899505615, "global_step": 415025, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0336575508117676, "global_step": 415026, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.2249460220336914, "global_step": 415027, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.045869827270508, "global_step": 415028, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0514824390411377, "global_step": 415029, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0842080116271973, "global_step": 415030, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.016169548034668, "global_step": 415031, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.088958978652954, "global_step": 415032, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0385191440582275, "global_step": 415033, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.115396499633789, "global_step": 415034, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.085836172103882, "global_step": 415035, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1121389865875244, "global_step": 415036, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1208529472351074, "global_step": 415037, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0966010093688965, "global_step": 415038, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1243317127227783, "global_step": 415039, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0750210285186768, "global_step": 415040, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0140199661254883, "global_step": 415041, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.083927631378174, "global_step": 415042, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0863685607910156, "global_step": 415043, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.06266713142395, "global_step": 415044, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0585241317749023, "global_step": 415045, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0593485832214355, "global_step": 415046, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9443241357803345, "global_step": 415047, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1542561054229736, "global_step": 415048, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1120266914367676, "global_step": 415049, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.073727607727051, "global_step": 415050, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.064683675765991, "global_step": 415051, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0451717376708984, "global_step": 415052, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.162013292312622, "global_step": 415053, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0668230056762695, "global_step": 415054, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0507280826568604, "global_step": 415055, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.047516345977783, "global_step": 415056, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0254507064819336, "global_step": 415057, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0230772495269775, "global_step": 415058, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.151646852493286, "global_step": 415059, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1343231201171875, "global_step": 415060, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.042041540145874, "global_step": 415061, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1079211235046387, "global_step": 415062, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.107532501220703, "global_step": 415063, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.076564073562622, "global_step": 415064, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.033092737197876, "global_step": 415065, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0598721504211426, "global_step": 415066, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1397528648376465, "global_step": 415067, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1835622787475586, "global_step": 415068, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.2064146995544434, "global_step": 415069, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0974009037017822, "global_step": 415070, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0544052124023438, "global_step": 415071, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.151780605316162, "global_step": 415072, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.058478355407715, "global_step": 415073, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.096973419189453, "global_step": 415074, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.062657117843628, "global_step": 415075, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0725526809692383, "global_step": 415076, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.121861457824707, "global_step": 415077, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.022273540496826, "global_step": 415078, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.097443103790283, "global_step": 415079, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.109905242919922, "global_step": 415080, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0794622898101807, "global_step": 415081, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1023478507995605, "global_step": 415082, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.101693868637085, "global_step": 415083, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1474740505218506, "global_step": 415084, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.091794967651367, "global_step": 415085, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.039712429046631, "global_step": 415086, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.107236385345459, "global_step": 415087, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9934090375900269, "global_step": 415088, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.2040810585021973, "global_step": 415089, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.131666660308838, "global_step": 415090, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.107738733291626, "global_step": 415091, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.035735607147217, "global_step": 415092, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.160517454147339, "global_step": 415093, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1124107837677, "global_step": 415094, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1162056922912598, "global_step": 415095, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.083353281021118, "global_step": 415096, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1069960594177246, "global_step": 415097, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.134080171585083, "global_step": 415098, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0738778114318848, "global_step": 415099, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0387656688690186, "global_step": 415100, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.033949851989746, "global_step": 415101, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.084967613220215, "global_step": 415102, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0602290630340576, "global_step": 415103, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.116971254348755, "global_step": 415104, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1117136478424072, "global_step": 415105, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.041193723678589, "global_step": 415106, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0362548828125, "global_step": 415107, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1558356285095215, "global_step": 415108, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0602734088897705, "global_step": 415109, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.120414972305298, "global_step": 415110, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0591912269592285, "global_step": 415111, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1229264736175537, "global_step": 415112, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.059837579727173, "global_step": 415113, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.167807102203369, "global_step": 415114, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.090503215789795, "global_step": 415115, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0187621116638184, "global_step": 415116, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.093449354171753, "global_step": 415117, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.074111223220825, "global_step": 415118, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.062563896179199, "global_step": 415119, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.158489465713501, "global_step": 415120, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.089308738708496, "global_step": 415121, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0688297748565674, "global_step": 415122, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.154353141784668, "global_step": 415123, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0857746601104736, "global_step": 415124, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0764992237091064, "global_step": 415125, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.049489736557007, "global_step": 415126, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1014206409454346, "global_step": 415127, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0134592056274414, "global_step": 415128, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9888094663619995, "global_step": 415129, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.057922840118408, "global_step": 415130, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.027724504470825, "global_step": 415131, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.044238805770874, "global_step": 415132, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0593225955963135, "global_step": 415133, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0964908599853516, "global_step": 415134, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.094271421432495, "global_step": 415135, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.045755624771118, "global_step": 415136, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0834264755249023, "global_step": 415137, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1593098640441895, "global_step": 415138, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0964252948760986, "global_step": 415139, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.121809720993042, "global_step": 415140, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.073737382888794, "global_step": 415141, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0725669860839844, "global_step": 415142, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.08630108833313, "global_step": 415143, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.033872365951538, "global_step": 415144, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0409631729125977, "global_step": 415145, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.169334888458252, "global_step": 415146, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.028120756149292, "global_step": 415147, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.032468795776367, "global_step": 415148, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1148312091827393, "global_step": 415149, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0739471912384033, "global_step": 415150, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1050002574920654, "global_step": 415151, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1009631156921387, "global_step": 415152, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1520628929138184, "global_step": 415153, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0782999992370605, "global_step": 415154, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0782790184020996, "global_step": 415155, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0862512588500977, "global_step": 415156, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.080294132232666, "global_step": 415157, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.07863187789917, "global_step": 415158, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.010277032852173, "global_step": 415159, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0113086700439453, "global_step": 415160, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.013270616531372, "global_step": 415161, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.090062141418457, "global_step": 415162, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0900638103485107, "global_step": 415163, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0472805500030518, "global_step": 415164, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0313408374786377, "global_step": 415165, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.978350043296814, "global_step": 415166, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.101165533065796, "global_step": 415167, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0086567401885986, "global_step": 415168, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0469706058502197, "global_step": 415169, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1611673831939697, "global_step": 415170, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0640363693237305, "global_step": 415171, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0915305614471436, "global_step": 415172, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0659117698669434, "global_step": 415173, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0448074340820312, "global_step": 415174, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1500768661499023, "global_step": 415175, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1008903980255127, "global_step": 415176, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.088935375213623, "global_step": 415177, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0582587718963623, "global_step": 415178, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0736465454101562, "global_step": 415179, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0456814765930176, "global_step": 415180, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0871808528900146, "global_step": 415181, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0855085849761963, "global_step": 415182, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.047264814376831, "global_step": 415183, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.113032341003418, "global_step": 415184, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1489009857177734, "global_step": 415185, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.133544921875, "global_step": 415186, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.119812488555908, "global_step": 415187, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.203626871109009, "global_step": 415188, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1294639110565186, "global_step": 415189, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1345245838165283, "global_step": 415190, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0089235305786133, "global_step": 415191, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.130537509918213, "global_step": 415192, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.170659303665161, "global_step": 415193, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0763235092163086, "global_step": 415194, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1141550540924072, "global_step": 415195, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1763126850128174, "global_step": 415196, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0294902324676514, "global_step": 415197, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0602288246154785, "global_step": 415198, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0335447788238525, "global_step": 415199, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0377578735351562, "global_step": 415200, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.022942066192627, "global_step": 415201, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.103093385696411, "global_step": 415202, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1215085983276367, "global_step": 415203, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1283974647521973, "global_step": 415204, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0908992290496826, "global_step": 415205, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0866644382476807, "global_step": 415206, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.013399362564087, "global_step": 415207, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.084110975265503, "global_step": 415208, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0059683322906494, "global_step": 415209, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.041003942489624, "global_step": 415210, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.115586757659912, "global_step": 415211, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.126967668533325, "global_step": 415212, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.099231719970703, "global_step": 415213, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.166330337524414, "global_step": 415214, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.025428056716919, "global_step": 415215, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1643710136413574, "global_step": 415216, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.104281187057495, "global_step": 415217, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.07183575630188, "global_step": 415218, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.140031099319458, "global_step": 415219, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1047184467315674, "global_step": 415220, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.130706310272217, "global_step": 415221, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1847386360168457, "global_step": 415222, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.070422649383545, "global_step": 415223, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.180469512939453, "global_step": 415224, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1016690731048584, "global_step": 415225, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.033726453781128, "global_step": 415226, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0997989177703857, "global_step": 415227, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.056680202484131, "global_step": 415228, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0663363933563232, "global_step": 415229, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1118533611297607, "global_step": 415230, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1044082641601562, "global_step": 415231, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.093653917312622, "global_step": 415232, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0968880653381348, "global_step": 415233, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0697567462921143, "global_step": 415234, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.064671516418457, "global_step": 415235, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.108811378479004, "global_step": 415236, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.119770050048828, "global_step": 415237, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0356693267822266, "global_step": 415238, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0994150638580322, "global_step": 415239, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1769042015075684, "global_step": 415240, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0247342586517334, "global_step": 415241, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0646169185638428, "global_step": 415242, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.120608329772949, "global_step": 415243, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.092486619949341, "global_step": 415244, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1068570613861084, "global_step": 415245, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.139333963394165, "global_step": 415246, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.117241382598877, "global_step": 415247, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0623257160186768, "global_step": 415248, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.11645245552063, "global_step": 415249, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.099550724029541, "global_step": 415250, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.087299346923828, "global_step": 415251, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0749781131744385, "global_step": 415252, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.106179714202881, "global_step": 415253, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.041127920150757, "global_step": 415254, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0586535930633545, "global_step": 415255, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.139072895050049, "global_step": 415256, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.019099235534668, "global_step": 415257, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0740060806274414, "global_step": 415258, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1832659244537354, "global_step": 415259, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1000242233276367, "global_step": 415260, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.058655261993408, "global_step": 415261, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0696046352386475, "global_step": 415262, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.097968578338623, "global_step": 415263, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0353193283081055, "global_step": 415264, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.061140298843384, "global_step": 415265, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.050758123397827, "global_step": 415266, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1323320865631104, "global_step": 415267, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1119213104248047, "global_step": 415268, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0662477016448975, "global_step": 415269, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0859415531158447, "global_step": 415270, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.150190591812134, "global_step": 415271, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.083890199661255, "global_step": 415272, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.090108633041382, "global_step": 415273, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9697396755218506, "global_step": 415274, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0978057384490967, "global_step": 415275, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.092650890350342, "global_step": 415276, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.063610315322876, "global_step": 415277, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.102829694747925, "global_step": 415278, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0732882022857666, "global_step": 415279, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0947141647338867, "global_step": 415280, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.061943292617798, "global_step": 415281, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0911049842834473, "global_step": 415282, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.047760009765625, "global_step": 415283, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1168155670166016, "global_step": 415284, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0643458366394043, "global_step": 415285, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0248782634735107, "global_step": 415286, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.18505597114563, "global_step": 415287, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.08294677734375, "global_step": 415288, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.2018802165985107, "global_step": 415289, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.11350154876709, "global_step": 415290, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.115109920501709, "global_step": 415291, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.121140480041504, "global_step": 415292, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0288798809051514, "global_step": 415293, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0009548664093018, "global_step": 415294, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.054403066635132, "global_step": 415295, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0390865802764893, "global_step": 415296, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1810696125030518, "global_step": 415297, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.136277675628662, "global_step": 415298, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0256450176239014, "global_step": 415299, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.105989933013916, "global_step": 415300, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0659430027008057, "global_step": 415301, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1438651084899902, "global_step": 415302, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.102663278579712, "global_step": 415303, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1004040241241455, "global_step": 415304, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1183550357818604, "global_step": 415305, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.045639991760254, "global_step": 415306, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1336140632629395, "global_step": 415307, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.152031421661377, "global_step": 415308, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9410244226455688, "global_step": 415309, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1016716957092285, "global_step": 415310, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1535964012145996, "global_step": 415311, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1104915142059326, "global_step": 415312, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9776346683502197, "global_step": 415313, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0981874465942383, "global_step": 415314, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.115306854248047, "global_step": 415315, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.070206880569458, "global_step": 415316, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1431455612182617, "global_step": 415317, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.152780294418335, "global_step": 415318, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0602798461914062, "global_step": 415319, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9913411140441895, "global_step": 415320, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.113868236541748, "global_step": 415321, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0749728679656982, "global_step": 415322, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.085089921951294, "global_step": 415323, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.097682476043701, "global_step": 415324, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1740009784698486, "global_step": 415325, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0598912239074707, "global_step": 415326, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.123246908187866, "global_step": 415327, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.066837787628174, "global_step": 415328, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1661715507507324, "global_step": 415329, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1223337650299072, "global_step": 415330, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.053152084350586, "global_step": 415331, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1072587966918945, "global_step": 415332, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1374659538269043, "global_step": 415333, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0834009647369385, "global_step": 415334, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.087439775466919, "global_step": 415335, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0531814098358154, "global_step": 415336, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.125211477279663, "global_step": 415337, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9607198238372803, "global_step": 415338, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.123969078063965, "global_step": 415339, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1382789611816406, "global_step": 415340, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1626319885253906, "global_step": 415341, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0953447818756104, "global_step": 415342, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0789101123809814, "global_step": 415343, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.093276262283325, "global_step": 415344, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0994231700897217, "global_step": 415345, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0345518589019775, "global_step": 415346, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0549821853637695, "global_step": 415347, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0329253673553467, "global_step": 415348, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.039580821990967, "global_step": 415349, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0576226711273193, "global_step": 415350, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0494887828826904, "global_step": 415351, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0426218509674072, "global_step": 415352, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.118440866470337, "global_step": 415353, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.174623489379883, "global_step": 415354, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.129577398300171, "global_step": 415355, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1609389781951904, "global_step": 415356, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.113975763320923, "global_step": 415357, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.120460033416748, "global_step": 415358, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0770936012268066, "global_step": 415359, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0977606773376465, "global_step": 415360, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.054832696914673, "global_step": 415361, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.100820541381836, "global_step": 415362, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1479101181030273, "global_step": 415363, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9835495948791504, "global_step": 415364, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1057286262512207, "global_step": 415365, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1433913707733154, "global_step": 415366, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0525364875793457, "global_step": 415367, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1386423110961914, "global_step": 415368, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1000099182128906, "global_step": 415369, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.103945255279541, "global_step": 415370, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.043851137161255, "global_step": 415371, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1066174507141113, "global_step": 415372, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1597440242767334, "global_step": 415373, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.100598096847534, "global_step": 415374, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.16304874420166, "global_step": 415375, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0907232761383057, "global_step": 415376, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1143219470977783, "global_step": 415377, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.011657238006592, "global_step": 415378, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1381611824035645, "global_step": 415379, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.120793342590332, "global_step": 415380, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.122044801712036, "global_step": 415381, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.023844003677368, "global_step": 415382, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1208813190460205, "global_step": 415383, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0500433444976807, "global_step": 415384, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.088366985321045, "global_step": 415385, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1137518882751465, "global_step": 415386, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0608561038970947, "global_step": 415387, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0597057342529297, "global_step": 415388, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.033968210220337, "global_step": 415389, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1479973793029785, "global_step": 415390, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0912222862243652, "global_step": 415391, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.962349772453308, "global_step": 415392, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0872185230255127, "global_step": 415393, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0488429069519043, "global_step": 415394, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0500800609588623, "global_step": 415395, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.042598009109497, "global_step": 415396, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.028515338897705, "global_step": 415397, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1226730346679688, "global_step": 415398, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0909314155578613, "global_step": 415399, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1836953163146973, "global_step": 415400, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1373355388641357, "global_step": 415401, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0891196727752686, "global_step": 415402, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0213208198547363, "global_step": 415403, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.067439079284668, "global_step": 415404, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0515809059143066, "global_step": 415405, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1875171661376953, "global_step": 415406, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.04581618309021, "global_step": 415407, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0805442333221436, "global_step": 415408, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0449929237365723, "global_step": 415409, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0706827640533447, "global_step": 415410, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1508686542510986, "global_step": 415411, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0646018981933594, "global_step": 415412, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0778086185455322, "global_step": 415413, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0532500743865967, "global_step": 415414, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1898043155670166, "global_step": 415415, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0996360778808594, "global_step": 415416, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.034963846206665, "global_step": 415417, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.003781318664551, "global_step": 415418, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.033468246459961, "global_step": 415419, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0681004524230957, "global_step": 415420, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1640708446502686, "global_step": 415421, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0689938068389893, "global_step": 415422, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1370038986206055, "global_step": 415423, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.096407651901245, "global_step": 415424, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0684492588043213, "global_step": 415425, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0824925899505615, "global_step": 415426, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0430660247802734, "global_step": 415427, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0879101753234863, "global_step": 415428, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1164519786834717, "global_step": 415429, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0565240383148193, "global_step": 415430, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.075861930847168, "global_step": 415431, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.011197805404663, "global_step": 415432, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1488656997680664, "global_step": 415433, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0603926181793213, "global_step": 415434, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.048133134841919, "global_step": 415435, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0826432704925537, "global_step": 415436, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.123713970184326, "global_step": 415437, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.075939655303955, "global_step": 415438, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0232436656951904, "global_step": 415439, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.006985664367676, "global_step": 415440, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1242737770080566, "global_step": 415441, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1105268001556396, "global_step": 415442, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.122272253036499, "global_step": 415443, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.085188150405884, "global_step": 415444, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1964752674102783, "global_step": 415445, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.023043155670166, "global_step": 415446, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0430684089660645, "global_step": 415447, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.059772491455078, "global_step": 415448, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0637481212615967, "global_step": 415449, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9836714267730713, "global_step": 415450, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1438841819763184, "global_step": 415451, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.127140998840332, "global_step": 415452, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0951108932495117, "global_step": 415453, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0475523471832275, "global_step": 415454, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.063041925430298, "global_step": 415455, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.05330753326416, "global_step": 415456, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1299617290496826, "global_step": 415457, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1466798782348633, "global_step": 415458, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.220912456512451, "global_step": 415459, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1498889923095703, "global_step": 415460, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.050537109375, "global_step": 415461, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1133077144622803, "global_step": 415462, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.139561891555786, "global_step": 415463, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1191232204437256, "global_step": 415464, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.130603551864624, "global_step": 415465, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.105890989303589, "global_step": 415466, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1645748615264893, "global_step": 415467, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1862633228302, "global_step": 415468, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0675573348999023, "global_step": 415469, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1065995693206787, "global_step": 415470, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.224065065383911, "global_step": 415471, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1278703212738037, "global_step": 415472, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1168644428253174, "global_step": 415473, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1740291118621826, "global_step": 415474, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1413230895996094, "global_step": 415475, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1009042263031006, "global_step": 415476, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.094257116317749, "global_step": 415477, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.127689838409424, "global_step": 415478, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1207261085510254, "global_step": 415479, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0768938064575195, "global_step": 415480, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0306544303894043, "global_step": 415481, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1029844284057617, "global_step": 415482, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.057119607925415, "global_step": 415483, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1471352577209473, "global_step": 415484, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.094041585922241, "global_step": 415485, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.047231912612915, "global_step": 415486, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1551947593688965, "global_step": 415487, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.059861183166504, "global_step": 415488, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.153984546661377, "global_step": 415489, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.123703956604004, "global_step": 415490, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1309304237365723, "global_step": 415491, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0907275676727295, "global_step": 415492, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0113210678100586, "global_step": 415493, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1010007858276367, "global_step": 415494, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.089022159576416, "global_step": 415495, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1795902252197266, "global_step": 415496, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1402158737182617, "global_step": 415497, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.084351062774658, "global_step": 415498, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1423792839050293, "global_step": 415499, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1391165256500244, "global_step": 415500, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9995616674423218, "global_step": 415501, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.081212043762207, "global_step": 415502, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0989432334899902, "global_step": 415503, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.121873617172241, "global_step": 415504, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.016928195953369, "global_step": 415505, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.13374662399292, "global_step": 415506, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1682651042938232, "global_step": 415507, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.093392848968506, "global_step": 415508, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0988430976867676, "global_step": 415509, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1081960201263428, "global_step": 415510, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1209893226623535, "global_step": 415511, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.136138916015625, "global_step": 415512, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.088322162628174, "global_step": 415513, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1125733852386475, "global_step": 415514, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.104358196258545, "global_step": 415515, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1883997917175293, "global_step": 415516, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.129992961883545, "global_step": 415517, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.131512403488159, "global_step": 415518, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0659286975860596, "global_step": 415519, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0979104042053223, "global_step": 415520, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0179646015167236, "global_step": 415521, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.018134593963623, "global_step": 415522, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.152191162109375, "global_step": 415523, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.00229549407959, "global_step": 415524, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0552852153778076, "global_step": 415525, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0865085124969482, "global_step": 415526, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.163182497024536, "global_step": 415527, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0674755573272705, "global_step": 415528, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0454022884368896, "global_step": 415529, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1226375102996826, "global_step": 415530, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0743846893310547, "global_step": 415531, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1686720848083496, "global_step": 415532, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.140594482421875, "global_step": 415533, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.022958993911743, "global_step": 415534, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.117345094680786, "global_step": 415535, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1016879081726074, "global_step": 415536, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1309046745300293, "global_step": 415537, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.004648447036743, "global_step": 415538, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.054549217224121, "global_step": 415539, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.068053722381592, "global_step": 415540, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0832979679107666, "global_step": 415541, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.078965425491333, "global_step": 415542, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0253069400787354, "global_step": 415543, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1429638862609863, "global_step": 415544, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1515543460845947, "global_step": 415545, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.068927526473999, "global_step": 415546, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0880539417266846, "global_step": 415547, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0324649810791016, "global_step": 415548, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.089872360229492, "global_step": 415549, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.12139630317688, "global_step": 415550, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.044550895690918, "global_step": 415551, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.119985342025757, "global_step": 415552, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.13378643989563, "global_step": 415553, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.068854808807373, "global_step": 415554, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.119398593902588, "global_step": 415555, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.078281879425049, "global_step": 415556, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1078436374664307, "global_step": 415557, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.118654727935791, "global_step": 415558, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1358137130737305, "global_step": 415559, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.221104383468628, "global_step": 415560, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1933681964874268, "global_step": 415561, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0237927436828613, "global_step": 415562, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1307389736175537, "global_step": 415563, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.131635904312134, "global_step": 415564, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.139324903488159, "global_step": 415565, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0877230167388916, "global_step": 415566, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1195740699768066, "global_step": 415567, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0552680492401123, "global_step": 415568, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0909924507141113, "global_step": 415569, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1105797290802, "global_step": 415570, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.132481575012207, "global_step": 415571, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0686588287353516, "global_step": 415572, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1064443588256836, "global_step": 415573, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.053812265396118, "global_step": 415574, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0313045978546143, "global_step": 415575, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.104508876800537, "global_step": 415576, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.081423282623291, "global_step": 415577, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0452880859375, "global_step": 415578, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.073425531387329, "global_step": 415579, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0651895999908447, "global_step": 415580, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1482396125793457, "global_step": 415581, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.030339479446411, "global_step": 415582, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.050285816192627, "global_step": 415583, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1496105194091797, "global_step": 415584, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0436341762542725, "global_step": 415585, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0883119106292725, "global_step": 415586, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.09171199798584, "global_step": 415587, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.124437093734741, "global_step": 415588, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0495316982269287, "global_step": 415589, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.045323371887207, "global_step": 415590, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.171668529510498, "global_step": 415591, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1085519790649414, "global_step": 415592, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.125293016433716, "global_step": 415593, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0198211669921875, "global_step": 415594, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.186598777770996, "global_step": 415595, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0999038219451904, "global_step": 415596, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.175196647644043, "global_step": 415597, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.039638042449951, "global_step": 415598, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0829737186431885, "global_step": 415599, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0885496139526367, "global_step": 415600, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0160915851593018, "global_step": 415601, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0846736431121826, "global_step": 415602, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1498961448669434, "global_step": 415603, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0581133365631104, "global_step": 415604, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.147817611694336, "global_step": 415605, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.05368709564209, "global_step": 415606, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0569040775299072, "global_step": 415607, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0342979431152344, "global_step": 415608, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0982048511505127, "global_step": 415609, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0651748180389404, "global_step": 415610, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.112745523452759, "global_step": 415611, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0929317474365234, "global_step": 415612, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.163996696472168, "global_step": 415613, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.04335880279541, "global_step": 415614, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0774192810058594, "global_step": 415615, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0167696475982666, "global_step": 415616, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.046996831893921, "global_step": 415617, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0368916988372803, "global_step": 415618, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.009145975112915, "global_step": 415619, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.083428382873535, "global_step": 415620, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1498870849609375, "global_step": 415621, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1131885051727295, "global_step": 415622, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0819170475006104, "global_step": 415623, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1519312858581543, "global_step": 415624, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1182923316955566, "global_step": 415625, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1482174396514893, "global_step": 415626, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0355477333068848, "global_step": 415627, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.099574327468872, "global_step": 415628, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.074591636657715, "global_step": 415629, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.051098346710205, "global_step": 415630, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0977284908294678, "global_step": 415631, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1150104999542236, "global_step": 415632, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.079686164855957, "global_step": 415633, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.052377700805664, "global_step": 415634, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0541436672210693, "global_step": 415635, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0922176837921143, "global_step": 415636, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0968642234802246, "global_step": 415637, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0670855045318604, "global_step": 415638, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.05776309967041, "global_step": 415639, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.109417200088501, "global_step": 415640, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.2052199840545654, "global_step": 415641, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.118195056915283, "global_step": 415642, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.116821527481079, "global_step": 415643, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.026616096496582, "global_step": 415644, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.108002185821533, "global_step": 415645, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1509153842926025, "global_step": 415646, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.115743637084961, "global_step": 415647, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.012647867202759, "global_step": 415648, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0673139095306396, "global_step": 415649, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1192774772644043, "global_step": 415650, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1633594036102295, "global_step": 415651, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0995359420776367, "global_step": 415652, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.020620822906494, "global_step": 415653, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.035022258758545, "global_step": 415654, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1623525619506836, "global_step": 415655, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1563549041748047, "global_step": 415656, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1394031047821045, "global_step": 415657, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1980175971984863, "global_step": 415658, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.10009503364563, "global_step": 415659, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0144412517547607, "global_step": 415660, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1014797687530518, "global_step": 415661, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0645031929016113, "global_step": 415662, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0329058170318604, "global_step": 415663, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0457210540771484, "global_step": 415664, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1393258571624756, "global_step": 415665, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0872719287872314, "global_step": 415666, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1583361625671387, "global_step": 415667, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.158917188644409, "global_step": 415668, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0544509887695312, "global_step": 415669, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.093764305114746, "global_step": 415670, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1097450256347656, "global_step": 415671, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0948312282562256, "global_step": 415672, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.052686929702759, "global_step": 415673, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0799107551574707, "global_step": 415674, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0659821033477783, "global_step": 415675, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.095806121826172, "global_step": 415676, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.138577461242676, "global_step": 415677, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9855183362960815, "global_step": 415678, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.093007802963257, "global_step": 415679, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.061448574066162, "global_step": 415680, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.100823163986206, "global_step": 415681, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1052844524383545, "global_step": 415682, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0129408836364746, "global_step": 415683, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1543660163879395, "global_step": 415684, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9949054718017578, "global_step": 415685, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0424723625183105, "global_step": 415686, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.10302472114563, "global_step": 415687, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1695473194122314, "global_step": 415688, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0147128105163574, "global_step": 415689, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0246036052703857, "global_step": 415690, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0981709957122803, "global_step": 415691, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1390955448150635, "global_step": 415692, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.109475612640381, "global_step": 415693, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1017115116119385, "global_step": 415694, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.071135997772217, "global_step": 415695, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0712175369262695, "global_step": 415696, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.161207914352417, "global_step": 415697, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.111818552017212, "global_step": 415698, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0591776371002197, "global_step": 415699, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.193924903869629, "global_step": 415700, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1834030151367188, "global_step": 415701, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0531582832336426, "global_step": 415702, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0451159477233887, "global_step": 415703, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1131746768951416, "global_step": 415704, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0289223194122314, "global_step": 415705, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1647849082946777, "global_step": 415706, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0776922702789307, "global_step": 415707, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.070470094680786, "global_step": 415708, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1245920658111572, "global_step": 415709, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0696237087249756, "global_step": 415710, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9810431003570557, "global_step": 415711, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0921666622161865, "global_step": 415712, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9992762804031372, "global_step": 415713, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0532445907592773, "global_step": 415714, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.150970697402954, "global_step": 415715, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0867466926574707, "global_step": 415716, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.136890411376953, "global_step": 415717, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1528537273406982, "global_step": 415718, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1429247856140137, "global_step": 415719, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0632359981536865, "global_step": 415720, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.039006233215332, "global_step": 415721, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0217366218566895, "global_step": 415722, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0479848384857178, "global_step": 415723, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.175640821456909, "global_step": 415724, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.118595838546753, "global_step": 415725, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1107192039489746, "global_step": 415726, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.061105728149414, "global_step": 415727, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0750725269317627, "global_step": 415728, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0580060482025146, "global_step": 415729, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.014211893081665, "global_step": 415730, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0308141708374023, "global_step": 415731, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.079876661300659, "global_step": 415732, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9955461025238037, "global_step": 415733, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1276724338531494, "global_step": 415734, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1293256282806396, "global_step": 415735, "epoch": 778, "lr": 5e-05}
{"train_loss": 1.9911022186279297, "global_step": 415736, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0332868099212646, "global_step": 415737, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1484732627868652, "global_step": 415738, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0796642303466797, "global_step": 415739, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1570546627044678, "global_step": 415740, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1826212406158447, "global_step": 415741, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.182461738586426, "global_step": 415742, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0956902503967285, "global_step": 415743, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.149411678314209, "global_step": 415744, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.071755886077881, "global_step": 415745, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.037125587463379, "global_step": 415746, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0664892196655273, "global_step": 415747, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1252291202545166, "global_step": 415748, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0945563316345215, "global_step": 415749, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1688754558563232, "global_step": 415750, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0145092010498047, "global_step": 415751, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.101797580718994, "global_step": 415752, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1351077556610107, "global_step": 415753, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1271591186523438, "global_step": 415754, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1299405097961426, "global_step": 415755, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0760996341705322, "global_step": 415756, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.116788387298584, "global_step": 415757, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0916969776153564, "global_step": 415758, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.083866596221924, "global_step": 415759, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0782532691955566, "global_step": 415760, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0575456619262695, "global_step": 415761, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0826377868652344, "global_step": 415762, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0824780464172363, "global_step": 415763, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0786185264587402, "global_step": 415764, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1226513385772705, "global_step": 415765, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.092015266418457, "global_step": 415766, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.176461935043335, "global_step": 415767, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.113971471786499, "global_step": 415768, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1351230144500732, "global_step": 415769, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.127744674682617, "global_step": 415770, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1723392009735107, "global_step": 415771, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.088416337966919, "global_step": 415772, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.121279239654541, "global_step": 415773, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1216859817504883, "global_step": 415774, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0769309997558594, "global_step": 415775, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0777854919433594, "global_step": 415776, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1690568923950195, "global_step": 415777, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1270666122436523, "global_step": 415778, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0640833377838135, "global_step": 415779, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0772440433502197, "global_step": 415780, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1140058040618896, "global_step": 415781, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.112898826599121, "global_step": 415782, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1949965953826904, "global_step": 415783, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.167642116546631, "global_step": 415784, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.086026906967163, "global_step": 415785, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.081430196762085, "global_step": 415786, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0894250869750977, "global_step": 415787, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.097541093826294, "global_step": 415788, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1713998317718506, "global_step": 415789, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.109022378921509, "global_step": 415790, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.2068240642547607, "global_step": 415791, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1582250595092773, "global_step": 415792, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0797598361968994, "global_step": 415793, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1644287109375, "global_step": 415794, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0425994396209717, "global_step": 415795, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.140702247619629, "global_step": 415796, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.097935676574707, "global_step": 415797, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0941357612609863, "global_step": 415798, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.206347942352295, "global_step": 415799, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1289334297180176, "global_step": 415800, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.130993127822876, "global_step": 415801, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.127732038497925, "global_step": 415802, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0101935863494873, "global_step": 415803, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1347978115081787, "global_step": 415804, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0781989097595215, "global_step": 415805, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1375327110290527, "global_step": 415806, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1117732524871826, "global_step": 415807, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1323909759521484, "global_step": 415808, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.16859769821167, "global_step": 415809, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.150890350341797, "global_step": 415810, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.044971227645874, "global_step": 415811, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0622005462646484, "global_step": 415812, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1091301441192627, "global_step": 415813, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.11555814743042, "global_step": 415814, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.075801134109497, "global_step": 415815, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0733909606933594, "global_step": 415816, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0937600135803223, "global_step": 415817, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.06071400642395, "global_step": 415818, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.08477520942688, "global_step": 415819, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0940334796905518, "global_step": 415820, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.049143075942993, "global_step": 415821, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1556620597839355, "global_step": 415822, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0862646102905273, "global_step": 415823, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0058133602142334, "global_step": 415824, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.037024974822998, "global_step": 415825, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1106057167053223, "global_step": 415826, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.068714141845703, "global_step": 415827, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.108090400695801, "global_step": 415828, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.04059100151062, "global_step": 415829, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.1587677001953125, "global_step": 415830, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0553364753723145, "global_step": 415831, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0634725093841553, "global_step": 415832, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.0909101963043213, "global_step": 415833, "epoch": 778, "lr": 5e-05}
{"train_loss": 2.080676794052124, "global_step": 415834, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.144028663635254, "global_step": 415835, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0739760398864746, "global_step": 415836, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0693533420562744, "global_step": 415837, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0222065448760986, "global_step": 415838, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0003066062927246, "global_step": 415839, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0862910747528076, "global_step": 415840, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0599210262298584, "global_step": 415841, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1760671138763428, "global_step": 415842, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0153486728668213, "global_step": 415843, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9933383464813232, "global_step": 415844, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.130744457244873, "global_step": 415845, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1193833351135254, "global_step": 415846, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.086315631866455, "global_step": 415847, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0750443935394287, "global_step": 415848, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1217446327209473, "global_step": 415849, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9882946014404297, "global_step": 415850, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0542659759521484, "global_step": 415851, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0938801765441895, "global_step": 415852, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0590744018554688, "global_step": 415853, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.106743335723877, "global_step": 415854, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.055290937423706, "global_step": 415855, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.082209587097168, "global_step": 415856, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0053234100341797, "global_step": 415857, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1018571853637695, "global_step": 415858, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.065962791442871, "global_step": 415859, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.03993821144104, "global_step": 415860, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0608479976654053, "global_step": 415861, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.071150064468384, "global_step": 415862, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.053447961807251, "global_step": 415863, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1184821128845215, "global_step": 415864, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1538267135620117, "global_step": 415865, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0590531826019287, "global_step": 415866, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0717599391937256, "global_step": 415867, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.058040142059326, "global_step": 415868, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.129204273223877, "global_step": 415869, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0811049938201904, "global_step": 415870, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0723154544830322, "global_step": 415871, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.012197494506836, "global_step": 415872, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1368656158447266, "global_step": 415873, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.130707263946533, "global_step": 415874, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.110103130340576, "global_step": 415875, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.119077682495117, "global_step": 415876, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1002590656280518, "global_step": 415877, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0866236686706543, "global_step": 415878, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.090510606765747, "global_step": 415879, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1048197746276855, "global_step": 415880, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0237419605255127, "global_step": 415881, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1408865451812744, "global_step": 415882, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0383455753326416, "global_step": 415883, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0576133728027344, "global_step": 415884, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.091172218322754, "global_step": 415885, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0615742206573486, "global_step": 415886, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.122969150543213, "global_step": 415887, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0564675331115723, "global_step": 415888, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9653114080429077, "global_step": 415889, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1005938053131104, "global_step": 415890, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1110801696777344, "global_step": 415891, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0401008129119873, "global_step": 415892, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1039819717407227, "global_step": 415893, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.058213949203491, "global_step": 415894, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.099907875061035, "global_step": 415895, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9874255657196045, "global_step": 415896, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.014366626739502, "global_step": 415897, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9490264654159546, "global_step": 415898, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.085630178451538, "global_step": 415899, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0541090965270996, "global_step": 415900, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.04062557220459, "global_step": 415901, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9942042827606201, "global_step": 415902, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0184273719787598, "global_step": 415903, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0794334411621094, "global_step": 415904, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1228456497192383, "global_step": 415905, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0044546127319336, "global_step": 415906, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9718595743179321, "global_step": 415907, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.106125831604004, "global_step": 415908, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0775671005249023, "global_step": 415909, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.067549228668213, "global_step": 415910, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.130849838256836, "global_step": 415911, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1097466945648193, "global_step": 415912, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0213067531585693, "global_step": 415913, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.014523506164551, "global_step": 415914, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1053028106689453, "global_step": 415915, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0545859336853027, "global_step": 415916, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1096177101135254, "global_step": 415917, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.088186264038086, "global_step": 415918, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1531271934509277, "global_step": 415919, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.10738205909729, "global_step": 415920, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1071441173553467, "global_step": 415921, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9976117610931396, "global_step": 415922, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.082624912261963, "global_step": 415923, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0638816356658936, "global_step": 415924, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0567071437835693, "global_step": 415925, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0704634189605713, "global_step": 415926, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0946738719940186, "global_step": 415927, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0425467491149902, "global_step": 415928, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.099611759185791, "global_step": 415929, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1109113693237305, "global_step": 415930, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1886377334594727, "global_step": 415931, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.066021680831909, "global_step": 415932, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.085599899291992, "global_step": 415933, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1174843311309814, "global_step": 415934, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0283889770507812, "global_step": 415935, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.078348398208618, "global_step": 415936, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0781753063201904, "global_step": 415937, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1021218299865723, "global_step": 415938, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.2588326930999756, "global_step": 415939, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1558454036712646, "global_step": 415940, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0528018474578857, "global_step": 415941, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.088855743408203, "global_step": 415942, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.126086950302124, "global_step": 415943, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1080868244171143, "global_step": 415944, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.137676477432251, "global_step": 415945, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.075568914413452, "global_step": 415946, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1085097789764404, "global_step": 415947, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0265660285949707, "global_step": 415948, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0710196495056152, "global_step": 415949, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0954315662384033, "global_step": 415950, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.213366985321045, "global_step": 415951, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.058419704437256, "global_step": 415952, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.147021770477295, "global_step": 415953, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.011889696121216, "global_step": 415954, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.057638168334961, "global_step": 415955, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0606815814971924, "global_step": 415956, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0884411334991455, "global_step": 415957, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0797996520996094, "global_step": 415958, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.086162567138672, "global_step": 415959, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.066223621368408, "global_step": 415960, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1151185035705566, "global_step": 415961, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0399866104125977, "global_step": 415962, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1714186668395996, "global_step": 415963, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1204121112823486, "global_step": 415964, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.094701051712036, "global_step": 415965, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.047687530517578, "global_step": 415966, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0521204471588135, "global_step": 415967, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.096235752105713, "global_step": 415968, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0839180946350098, "global_step": 415969, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0343730449676514, "global_step": 415970, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0712532997131348, "global_step": 415971, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.098865270614624, "global_step": 415972, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.111713171005249, "global_step": 415973, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.146451234817505, "global_step": 415974, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.075073719024658, "global_step": 415975, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1574597358703613, "global_step": 415976, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.107286214828491, "global_step": 415977, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.15631103515625, "global_step": 415978, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.121955394744873, "global_step": 415979, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0547871589660645, "global_step": 415980, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1313257217407227, "global_step": 415981, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0388784408569336, "global_step": 415982, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1198675632476807, "global_step": 415983, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0668280124664307, "global_step": 415984, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.058074474334717, "global_step": 415985, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0267035961151123, "global_step": 415986, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.146533727645874, "global_step": 415987, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.122197389602661, "global_step": 415988, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.061633586883545, "global_step": 415989, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0757527351379395, "global_step": 415990, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.04911208152771, "global_step": 415991, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0641610622406006, "global_step": 415992, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0125091075897217, "global_step": 415993, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9819344282150269, "global_step": 415994, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1311233043670654, "global_step": 415995, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.04201078414917, "global_step": 415996, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0994184017181396, "global_step": 415997, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.025907516479492, "global_step": 415998, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0860049724578857, "global_step": 415999, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0852417945861816, "global_step": 416000, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.100315809249878, "global_step": 416001, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0869550704956055, "global_step": 416002, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.186404228210449, "global_step": 416003, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.105043411254883, "global_step": 416004, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.053999185562134, "global_step": 416005, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0004360675811768, "global_step": 416006, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0476248264312744, "global_step": 416007, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9804505109786987, "global_step": 416008, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0142180919647217, "global_step": 416009, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.099912643432617, "global_step": 416010, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0948355197906494, "global_step": 416011, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.125887393951416, "global_step": 416012, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.138448715209961, "global_step": 416013, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.108050584793091, "global_step": 416014, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.043147563934326, "global_step": 416015, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0277764797210693, "global_step": 416016, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0627987384796143, "global_step": 416017, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1096138954162598, "global_step": 416018, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1342811584472656, "global_step": 416019, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.010347366333008, "global_step": 416020, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0666146278381348, "global_step": 416021, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0863053798675537, "global_step": 416022, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0896198749542236, "global_step": 416023, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.036831855773926, "global_step": 416024, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0659189224243164, "global_step": 416025, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.028918743133545, "global_step": 416026, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0949196815490723, "global_step": 416027, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.063291311264038, "global_step": 416028, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.034581422805786, "global_step": 416029, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1569058895111084, "global_step": 416030, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.123056650161743, "global_step": 416031, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.085015058517456, "global_step": 416032, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0896663665771484, "global_step": 416033, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1686930656433105, "global_step": 416034, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1183204650878906, "global_step": 416035, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0923051834106445, "global_step": 416036, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.057116746902466, "global_step": 416037, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1757657527923584, "global_step": 416038, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.173027515411377, "global_step": 416039, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1420366764068604, "global_step": 416040, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0317728519439697, "global_step": 416041, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.983788013458252, "global_step": 416042, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0397605895996094, "global_step": 416043, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0101547241210938, "global_step": 416044, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0471503734588623, "global_step": 416045, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0353739261627197, "global_step": 416046, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.055014133453369, "global_step": 416047, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.08081316947937, "global_step": 416048, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1018569469451904, "global_step": 416049, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.100034236907959, "global_step": 416050, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0852606296539307, "global_step": 416051, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1177239418029785, "global_step": 416052, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.07106351852417, "global_step": 416053, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.103931427001953, "global_step": 416054, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.030237913131714, "global_step": 416055, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0962002277374268, "global_step": 416056, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1000783443450928, "global_step": 416057, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0833675861358643, "global_step": 416058, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0789999961853027, "global_step": 416059, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0593621730804443, "global_step": 416060, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0950355529785156, "global_step": 416061, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0607473850250244, "global_step": 416062, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.11926007270813, "global_step": 416063, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1018924713134766, "global_step": 416064, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1431732177734375, "global_step": 416065, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.066189765930176, "global_step": 416066, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.079893112182617, "global_step": 416067, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0272574424743652, "global_step": 416068, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9929336309432983, "global_step": 416069, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.101700782775879, "global_step": 416070, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0462002754211426, "global_step": 416071, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0875699520111084, "global_step": 416072, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9881418943405151, "global_step": 416073, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1234612464904785, "global_step": 416074, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.114837408065796, "global_step": 416075, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0151548385620117, "global_step": 416076, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0619943141937256, "global_step": 416077, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1123902797698975, "global_step": 416078, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.025750160217285, "global_step": 416079, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9905472993850708, "global_step": 416080, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.152886152267456, "global_step": 416081, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1144282817840576, "global_step": 416082, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1442830562591553, "global_step": 416083, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1239192485809326, "global_step": 416084, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.154797315597534, "global_step": 416085, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0744853019714355, "global_step": 416086, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1131350994110107, "global_step": 416087, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1184349060058594, "global_step": 416088, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0939462184906006, "global_step": 416089, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0936360359191895, "global_step": 416090, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0705413818359375, "global_step": 416091, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0854408740997314, "global_step": 416092, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0634732246398926, "global_step": 416093, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0947537422180176, "global_step": 416094, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.131209135055542, "global_step": 416095, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1123340129852295, "global_step": 416096, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1775364875793457, "global_step": 416097, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0321784019470215, "global_step": 416098, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.059607982635498, "global_step": 416099, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1557095050811768, "global_step": 416100, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.021711826324463, "global_step": 416101, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0551693439483643, "global_step": 416102, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0643231868743896, "global_step": 416103, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.096096992492676, "global_step": 416104, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.024289608001709, "global_step": 416105, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.974076271057129, "global_step": 416106, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0557942390441895, "global_step": 416107, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1224801540374756, "global_step": 416108, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.095961809158325, "global_step": 416109, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.112248659133911, "global_step": 416110, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1324689388275146, "global_step": 416111, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.110691785812378, "global_step": 416112, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.062831163406372, "global_step": 416113, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.05431866645813, "global_step": 416114, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.047879219055176, "global_step": 416115, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.083019256591797, "global_step": 416116, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1122403144836426, "global_step": 416117, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0680928230285645, "global_step": 416118, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.139904737472534, "global_step": 416119, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.117316961288452, "global_step": 416120, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0949950218200684, "global_step": 416121, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0886287689208984, "global_step": 416122, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.118774890899658, "global_step": 416123, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1042520999908447, "global_step": 416124, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0863354206085205, "global_step": 416125, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.137805461883545, "global_step": 416126, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.117281436920166, "global_step": 416127, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.160353183746338, "global_step": 416128, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1024632453918457, "global_step": 416129, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.073214530944824, "global_step": 416130, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0016376972198486, "global_step": 416131, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0913610458374023, "global_step": 416132, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.968644618988037, "global_step": 416133, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.104081153869629, "global_step": 416134, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0628490447998047, "global_step": 416135, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.148069143295288, "global_step": 416136, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.166954278945923, "global_step": 416137, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0891268253326416, "global_step": 416138, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0859172344207764, "global_step": 416139, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.114414930343628, "global_step": 416140, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0054707527160645, "global_step": 416141, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9797734022140503, "global_step": 416142, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1093337535858154, "global_step": 416143, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0996525287628174, "global_step": 416144, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1442668437957764, "global_step": 416145, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.120739459991455, "global_step": 416146, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0824320316314697, "global_step": 416147, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.104177951812744, "global_step": 416148, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0971462726593018, "global_step": 416149, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1255197525024414, "global_step": 416150, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9624028205871582, "global_step": 416151, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0535855293273926, "global_step": 416152, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1139140129089355, "global_step": 416153, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.07709002494812, "global_step": 416154, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0463550090789795, "global_step": 416155, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0554518699645996, "global_step": 416156, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9629050493240356, "global_step": 416157, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.094128370285034, "global_step": 416158, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.088351249694824, "global_step": 416159, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9962339401245117, "global_step": 416160, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0119144916534424, "global_step": 416161, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1908085346221924, "global_step": 416162, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0344178676605225, "global_step": 416163, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.101911783218384, "global_step": 416164, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0272786617279053, "global_step": 416165, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0427730083465576, "global_step": 416166, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.024170160293579, "global_step": 416167, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.042684316635132, "global_step": 416168, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1115710735321045, "global_step": 416169, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.092515707015991, "global_step": 416170, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0612759590148926, "global_step": 416171, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0949110984802246, "global_step": 416172, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1250579357147217, "global_step": 416173, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.05621600151062, "global_step": 416174, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1656441688537598, "global_step": 416175, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0914762020111084, "global_step": 416176, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.052875280380249, "global_step": 416177, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1334540843963623, "global_step": 416178, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0834310054779053, "global_step": 416179, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.130307912826538, "global_step": 416180, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0543439388275146, "global_step": 416181, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0293822288513184, "global_step": 416182, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1302390098571777, "global_step": 416183, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9593697786331177, "global_step": 416184, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0850813388824463, "global_step": 416185, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.047982692718506, "global_step": 416186, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.201106548309326, "global_step": 416187, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1073837280273438, "global_step": 416188, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1223533153533936, "global_step": 416189, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.2271015644073486, "global_step": 416190, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0308938026428223, "global_step": 416191, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0231053829193115, "global_step": 416192, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.12955379486084, "global_step": 416193, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0917820930480957, "global_step": 416194, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.078984260559082, "global_step": 416195, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0318849086761475, "global_step": 416196, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0863020420074463, "global_step": 416197, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.172024726867676, "global_step": 416198, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0303292274475098, "global_step": 416199, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.057224750518799, "global_step": 416200, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1584818363189697, "global_step": 416201, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.2145729064941406, "global_step": 416202, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.188317060470581, "global_step": 416203, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.062901496887207, "global_step": 416204, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1208362579345703, "global_step": 416205, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.008723258972168, "global_step": 416206, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0541203022003174, "global_step": 416207, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.057204484939575, "global_step": 416208, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.008446455001831, "global_step": 416209, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1319401264190674, "global_step": 416210, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.06048583984375, "global_step": 416211, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.108853816986084, "global_step": 416212, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1278483867645264, "global_step": 416213, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0880768299102783, "global_step": 416214, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0566015243530273, "global_step": 416215, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.104353189468384, "global_step": 416216, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1572868824005127, "global_step": 416217, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0452401638031006, "global_step": 416218, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.058587074279785, "global_step": 416219, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.107285499572754, "global_step": 416220, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0601272583007812, "global_step": 416221, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.088361978530884, "global_step": 416222, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.092557907104492, "global_step": 416223, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0783870220184326, "global_step": 416224, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.073225259780884, "global_step": 416225, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.129939556121826, "global_step": 416226, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.192702054977417, "global_step": 416227, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.161651849746704, "global_step": 416228, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0749876499176025, "global_step": 416229, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0958757400512695, "global_step": 416230, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.078916311264038, "global_step": 416231, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.08501935005188, "global_step": 416232, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.169346809387207, "global_step": 416233, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.072373867034912, "global_step": 416234, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0717315673828125, "global_step": 416235, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1300723552703857, "global_step": 416236, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.028001546859741, "global_step": 416237, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.085179567337036, "global_step": 416238, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1074607372283936, "global_step": 416239, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.20137619972229, "global_step": 416240, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0990989208221436, "global_step": 416241, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0611681938171387, "global_step": 416242, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0119128227233887, "global_step": 416243, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1040751934051514, "global_step": 416244, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1421878337860107, "global_step": 416245, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0492477416992188, "global_step": 416246, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.2270548343658447, "global_step": 416247, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.114018678665161, "global_step": 416248, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.081496477127075, "global_step": 416249, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.109375, "global_step": 416250, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0248045921325684, "global_step": 416251, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.11777663230896, "global_step": 416252, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.133415460586548, "global_step": 416253, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.045353889465332, "global_step": 416254, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0979745388031006, "global_step": 416255, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0248842239379883, "global_step": 416256, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.134589195251465, "global_step": 416257, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1786129474639893, "global_step": 416258, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1156609058380127, "global_step": 416259, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.020604372024536, "global_step": 416260, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.105470895767212, "global_step": 416261, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0494837760925293, "global_step": 416262, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0124518871307373, "global_step": 416263, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.060499668121338, "global_step": 416264, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0597915649414062, "global_step": 416265, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.021638870239258, "global_step": 416266, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.136740207672119, "global_step": 416267, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1108975410461426, "global_step": 416268, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0577433109283447, "global_step": 416269, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.13777494430542, "global_step": 416270, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1332755088806152, "global_step": 416271, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.094651699066162, "global_step": 416272, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.119572162628174, "global_step": 416273, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1817898750305176, "global_step": 416274, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0385148525238037, "global_step": 416275, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1895670890808105, "global_step": 416276, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1729490756988525, "global_step": 416277, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.140960693359375, "global_step": 416278, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.139604330062866, "global_step": 416279, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1053504943847656, "global_step": 416280, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0653109550476074, "global_step": 416281, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.116286039352417, "global_step": 416282, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1361045837402344, "global_step": 416283, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0160038471221924, "global_step": 416284, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9993950128555298, "global_step": 416285, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0644867420196533, "global_step": 416286, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0731301307678223, "global_step": 416287, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0923783779144287, "global_step": 416288, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0749425888061523, "global_step": 416289, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0606822967529297, "global_step": 416290, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0510356426239014, "global_step": 416291, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.078188896179199, "global_step": 416292, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.218543767929077, "global_step": 416293, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.021059274673462, "global_step": 416294, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1240622997283936, "global_step": 416295, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.084468364715576, "global_step": 416296, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.037872791290283, "global_step": 416297, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.056094169616699, "global_step": 416298, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0886712074279785, "global_step": 416299, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.105973243713379, "global_step": 416300, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.168792486190796, "global_step": 416301, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0530030727386475, "global_step": 416302, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0841686725616455, "global_step": 416303, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0952327251434326, "global_step": 416304, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1094205379486084, "global_step": 416305, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0947303771972656, "global_step": 416306, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0375757217407227, "global_step": 416307, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.185731887817383, "global_step": 416308, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0979104042053223, "global_step": 416309, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0919992923736572, "global_step": 416310, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0602781772613525, "global_step": 416311, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0699920654296875, "global_step": 416312, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0841214656829834, "global_step": 416313, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1373634338378906, "global_step": 416314, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0901739597320557, "global_step": 416315, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0471653938293457, "global_step": 416316, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.086090087890625, "global_step": 416317, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1580052375793457, "global_step": 416318, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0506739616394043, "global_step": 416319, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0268561840057373, "global_step": 416320, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0187716484069824, "global_step": 416321, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0742647647857666, "global_step": 416322, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0455048084259033, "global_step": 416323, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.171876907348633, "global_step": 416324, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.037614345550537, "global_step": 416325, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1640048027038574, "global_step": 416326, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1467580795288086, "global_step": 416327, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.079033851623535, "global_step": 416328, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.068995475769043, "global_step": 416329, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0736887454986572, "global_step": 416330, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1566615104675293, "global_step": 416331, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0757830142974854, "global_step": 416332, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0191609859466553, "global_step": 416333, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.099984884262085, "global_step": 416334, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1193106174468994, "global_step": 416335, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1630349159240723, "global_step": 416336, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0772156715393066, "global_step": 416337, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0226502418518066, "global_step": 416338, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0673294067382812, "global_step": 416339, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.042104721069336, "global_step": 416340, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0771965980529785, "global_step": 416341, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1025421619415283, "global_step": 416342, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.079265832901001, "global_step": 416343, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.10813307762146, "global_step": 416344, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1044228076934814, "global_step": 416345, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.078965425491333, "global_step": 416346, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.080129623413086, "global_step": 416347, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.052581310272217, "global_step": 416348, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0604476928710938, "global_step": 416349, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0819644927978516, "global_step": 416350, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1011252403259277, "global_step": 416351, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1196582317352295, "global_step": 416352, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.027949094772339, "global_step": 416353, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0822932720184326, "global_step": 416354, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1040661334991455, "global_step": 416355, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.998680591583252, "global_step": 416356, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.084158420562744, "global_step": 416357, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.064345598220825, "global_step": 416358, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0685572624206543, "global_step": 416359, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1324281692504883, "global_step": 416360, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0489678382873535, "global_step": 416361, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.069753885269165, "global_step": 416362, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.174701452255249, "global_step": 416363, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1026740074157715, "global_step": 416364, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.044363260269165, "global_step": 416365, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1257026195526123, "global_step": 416366, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0924136638641357, "global_step": 416367, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0268356800079346, "global_step": 416368, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.147336006164551, "global_step": 416369, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.125966787338257, "global_step": 416370, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.2192864418029785, "global_step": 416371, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.160203695297241, "global_step": 416372, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0503904819488525, "global_step": 416373, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1195290088653564, "global_step": 416374, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0348150730133057, "global_step": 416375, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0933830738067627, "global_step": 416376, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.057846784591675, "global_step": 416377, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.148908853530884, "global_step": 416378, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.069073438644409, "global_step": 416379, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0551419258117676, "global_step": 416380, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.097269296646118, "global_step": 416381, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0095877647399902, "global_step": 416382, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0394232273101807, "global_step": 416383, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.135362148284912, "global_step": 416384, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0215749740600586, "global_step": 416385, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0317182540893555, "global_step": 416386, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.13586688041687, "global_step": 416387, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9641026258468628, "global_step": 416388, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1510581970214844, "global_step": 416389, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0204050540924072, "global_step": 416390, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.034740686416626, "global_step": 416391, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1177942752838135, "global_step": 416392, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1211109161376953, "global_step": 416393, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.070925235748291, "global_step": 416394, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1073529720306396, "global_step": 416395, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0460212230682373, "global_step": 416396, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1182191371917725, "global_step": 416397, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.134688138961792, "global_step": 416398, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0072405338287354, "global_step": 416399, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.032161235809326, "global_step": 416400, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1095426082611084, "global_step": 416401, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0994694232940674, "global_step": 416402, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1813275814056396, "global_step": 416403, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1340761184692383, "global_step": 416404, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.046753168106079, "global_step": 416405, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.023253917694092, "global_step": 416406, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0290913581848145, "global_step": 416407, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9434374570846558, "global_step": 416408, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.162590980529785, "global_step": 416409, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.166661500930786, "global_step": 416410, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.142425537109375, "global_step": 416411, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.113379955291748, "global_step": 416412, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.149671792984009, "global_step": 416413, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0898005962371826, "global_step": 416414, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0881640911102295, "global_step": 416415, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.084530830383301, "global_step": 416416, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0689537525177, "global_step": 416417, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.110025644302368, "global_step": 416418, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1418230533599854, "global_step": 416419, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.12668776512146, "global_step": 416420, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1138219833374023, "global_step": 416421, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.059741258621216, "global_step": 416422, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1295390129089355, "global_step": 416423, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1202828884124756, "global_step": 416424, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0440452098846436, "global_step": 416425, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0704848766326904, "global_step": 416426, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.112804889678955, "global_step": 416427, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1361916065216064, "global_step": 416428, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0586400032043457, "global_step": 416429, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0695672035217285, "global_step": 416430, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.094080924987793, "global_step": 416431, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1176817417144775, "global_step": 416432, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.134871006011963, "global_step": 416433, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.05302095413208, "global_step": 416434, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1018199920654297, "global_step": 416435, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.117500066757202, "global_step": 416436, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.082519292831421, "global_step": 416437, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.090139150619507, "global_step": 416438, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1084609031677246, "global_step": 416439, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.096750259399414, "global_step": 416440, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1342968940734863, "global_step": 416441, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1586320400238037, "global_step": 416442, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0785298347473145, "global_step": 416443, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1392788887023926, "global_step": 416444, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.112070322036743, "global_step": 416445, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0951061248779297, "global_step": 416446, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1236417293548584, "global_step": 416447, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.097325086593628, "global_step": 416448, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.028430938720703, "global_step": 416449, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1034021377563477, "global_step": 416450, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0392518043518066, "global_step": 416451, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.116661787033081, "global_step": 416452, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.099416494369507, "global_step": 416453, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0620956420898438, "global_step": 416454, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1128461360931396, "global_step": 416455, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0173869132995605, "global_step": 416456, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.130776882171631, "global_step": 416457, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0804824829101562, "global_step": 416458, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.133697271347046, "global_step": 416459, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.101957082748413, "global_step": 416460, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.079674243927002, "global_step": 416461, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0076491832733154, "global_step": 416462, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1198854446411133, "global_step": 416463, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0357666015625, "global_step": 416464, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.20032000541687, "global_step": 416465, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.069901943206787, "global_step": 416466, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1682112216949463, "global_step": 416467, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0997378826141357, "global_step": 416468, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0700221061706543, "global_step": 416469, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1624033451080322, "global_step": 416470, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0365195274353027, "global_step": 416471, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1172099113464355, "global_step": 416472, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1071763038635254, "global_step": 416473, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.030705690383911, "global_step": 416474, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0594382286071777, "global_step": 416475, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0475921630859375, "global_step": 416476, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1285994052886963, "global_step": 416477, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0535802841186523, "global_step": 416478, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.087433099746704, "global_step": 416479, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.162571907043457, "global_step": 416480, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1856720447540283, "global_step": 416481, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.097837448120117, "global_step": 416482, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0916030406951904, "global_step": 416483, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0212244987487793, "global_step": 416484, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.149930477142334, "global_step": 416485, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.106858015060425, "global_step": 416486, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0409815311431885, "global_step": 416487, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0916049480438232, "global_step": 416488, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0362348556518555, "global_step": 416489, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.102666139602661, "global_step": 416490, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1366705894470215, "global_step": 416491, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1517493724823, "global_step": 416492, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.081400156021118, "global_step": 416493, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1040213108062744, "global_step": 416494, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1364049911499023, "global_step": 416495, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0624942779541016, "global_step": 416496, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.087944984436035, "global_step": 416497, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.115443468093872, "global_step": 416498, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0553369522094727, "global_step": 416499, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.043734312057495, "global_step": 416500, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0610594749450684, "global_step": 416501, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0783770084381104, "global_step": 416502, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1145272254943848, "global_step": 416503, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0876288414001465, "global_step": 416504, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1242966651916504, "global_step": 416505, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1120669841766357, "global_step": 416506, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0664236545562744, "global_step": 416507, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.14609432220459, "global_step": 416508, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1682136058807373, "global_step": 416509, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.984984040260315, "global_step": 416510, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0787644386291504, "global_step": 416511, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.995500087738037, "global_step": 416512, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.979610562324524, "global_step": 416513, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.041409492492676, "global_step": 416514, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1019749641418457, "global_step": 416515, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1422860622406006, "global_step": 416516, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1052138805389404, "global_step": 416517, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.152155637741089, "global_step": 416518, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1143970489501953, "global_step": 416519, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0959768295288086, "global_step": 416520, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1057019233703613, "global_step": 416521, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1607437133789062, "global_step": 416522, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.044609308242798, "global_step": 416523, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0241897106170654, "global_step": 416524, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.2478115558624268, "global_step": 416525, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.100832939147949, "global_step": 416526, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.069882392883301, "global_step": 416527, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1942923069000244, "global_step": 416528, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.016188621520996, "global_step": 416529, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0871713161468506, "global_step": 416530, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.992767572402954, "global_step": 416531, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1556661128997803, "global_step": 416532, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.111417055130005, "global_step": 416533, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.135915994644165, "global_step": 416534, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.101677656173706, "global_step": 416535, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.075439929962158, "global_step": 416536, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.145979881286621, "global_step": 416537, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.090451717376709, "global_step": 416538, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.042112112045288, "global_step": 416539, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.083730697631836, "global_step": 416540, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.042106866836548, "global_step": 416541, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.055759906768799, "global_step": 416542, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1794352531433105, "global_step": 416543, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0097765922546387, "global_step": 416544, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1270511150360107, "global_step": 416545, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.101318836212158, "global_step": 416546, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1337673664093018, "global_step": 416547, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1437149047851562, "global_step": 416548, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.106086254119873, "global_step": 416549, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9968594312667847, "global_step": 416550, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.127258062362671, "global_step": 416551, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0019779205322266, "global_step": 416552, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0437989234924316, "global_step": 416553, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1534249782562256, "global_step": 416554, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.142510414123535, "global_step": 416555, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.091172218322754, "global_step": 416556, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.014535665512085, "global_step": 416557, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.121217727661133, "global_step": 416558, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0330822467803955, "global_step": 416559, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.091168165206909, "global_step": 416560, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0819711685180664, "global_step": 416561, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1032285690307617, "global_step": 416562, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.06721568107605, "global_step": 416563, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0213375091552734, "global_step": 416564, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.110370635986328, "global_step": 416565, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.072932243347168, "global_step": 416566, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.119321584701538, "global_step": 416567, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0066747665405273, "global_step": 416568, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1165788173675537, "global_step": 416569, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1290361881256104, "global_step": 416570, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1328282356262207, "global_step": 416571, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1524336338043213, "global_step": 416572, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.046038866043091, "global_step": 416573, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.110211133956909, "global_step": 416574, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.074617624282837, "global_step": 416575, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0929641723632812, "global_step": 416576, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.141256332397461, "global_step": 416577, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0661559104919434, "global_step": 416578, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9850397109985352, "global_step": 416579, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1122448444366455, "global_step": 416580, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1921329498291016, "global_step": 416581, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.11938738822937, "global_step": 416582, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9501315355300903, "global_step": 416583, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.014086961746216, "global_step": 416584, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.00040340423584, "global_step": 416585, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.054718255996704, "global_step": 416586, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1748430728912354, "global_step": 416587, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0461902618408203, "global_step": 416588, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.024937629699707, "global_step": 416589, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.176713705062866, "global_step": 416590, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0380897521972656, "global_step": 416591, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9974100589752197, "global_step": 416592, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.039130687713623, "global_step": 416593, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.102022171020508, "global_step": 416594, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0295896530151367, "global_step": 416595, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1591532230377197, "global_step": 416596, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0388431549072266, "global_step": 416597, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0712742805480957, "global_step": 416598, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.095635414123535, "global_step": 416599, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1545469760894775, "global_step": 416600, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1582069396972656, "global_step": 416601, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.164020538330078, "global_step": 416602, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.080617904663086, "global_step": 416603, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.2051174640655518, "global_step": 416604, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0735042095184326, "global_step": 416605, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1472067832946777, "global_step": 416606, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1124353408813477, "global_step": 416607, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.043182134628296, "global_step": 416608, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0929858684539795, "global_step": 416609, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0959863662719727, "global_step": 416610, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0885167121887207, "global_step": 416611, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1303517818450928, "global_step": 416612, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0109097957611084, "global_step": 416613, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.105424165725708, "global_step": 416614, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.022988796234131, "global_step": 416615, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.107456922531128, "global_step": 416616, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0467350482940674, "global_step": 416617, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.982568383216858, "global_step": 416618, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0887632369995117, "global_step": 416619, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.11938738822937, "global_step": 416620, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0981802940368652, "global_step": 416621, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0893824100494385, "global_step": 416622, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0604255199432373, "global_step": 416623, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.051886558532715, "global_step": 416624, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.077533006668091, "global_step": 416625, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9999303817749023, "global_step": 416626, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1281816959381104, "global_step": 416627, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.078542709350586, "global_step": 416628, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9948267936706543, "global_step": 416629, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0504684448242188, "global_step": 416630, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1002280712127686, "global_step": 416631, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1485471725463867, "global_step": 416632, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9681261777877808, "global_step": 416633, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0175740718841553, "global_step": 416634, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0596766471862793, "global_step": 416635, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1350018978118896, "global_step": 416636, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0794520378112793, "global_step": 416637, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0747010707855225, "global_step": 416638, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.075754404067993, "global_step": 416639, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.109243631362915, "global_step": 416640, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0488338470458984, "global_step": 416641, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.120404005050659, "global_step": 416642, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0108566284179688, "global_step": 416643, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1701011657714844, "global_step": 416644, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0799131393432617, "global_step": 416645, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0257225036621094, "global_step": 416646, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1591498851776123, "global_step": 416647, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0269956588745117, "global_step": 416648, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0416595935821533, "global_step": 416649, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1398773193359375, "global_step": 416650, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0976340770721436, "global_step": 416651, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0716278553009033, "global_step": 416652, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1238226890563965, "global_step": 416653, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0641491413116455, "global_step": 416654, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.031348705291748, "global_step": 416655, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.086399555206299, "global_step": 416656, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.098919153213501, "global_step": 416657, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.090376853942871, "global_step": 416658, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.028059244155884, "global_step": 416659, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.026031017303467, "global_step": 416660, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0658557415008545, "global_step": 416661, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.191148042678833, "global_step": 416662, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9907898902893066, "global_step": 416663, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.080723762512207, "global_step": 416664, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.109391212463379, "global_step": 416665, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0476653575897217, "global_step": 416666, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.06484317779541, "global_step": 416667, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.13533878326416, "global_step": 416668, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0823285579681396, "global_step": 416669, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.141380786895752, "global_step": 416670, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1063425540924072, "global_step": 416671, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.093846559524536, "global_step": 416672, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1050400733947754, "global_step": 416673, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.057934045791626, "global_step": 416674, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0400986671447754, "global_step": 416675, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0739688873291016, "global_step": 416676, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.163158655166626, "global_step": 416677, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.057094097137451, "global_step": 416678, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.087235450744629, "global_step": 416679, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1522226333618164, "global_step": 416680, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.024958848953247, "global_step": 416681, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0579450130462646, "global_step": 416682, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.011451482772827, "global_step": 416683, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1349172592163086, "global_step": 416684, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.053131103515625, "global_step": 416685, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0405964851379395, "global_step": 416686, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.118360757827759, "global_step": 416687, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.12009596824646, "global_step": 416688, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1083950996398926, "global_step": 416689, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.101219415664673, "global_step": 416690, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.035984516143799, "global_step": 416691, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.095165491104126, "global_step": 416692, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1384596824645996, "global_step": 416693, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.079904556274414, "global_step": 416694, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1658778190612793, "global_step": 416695, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.198596954345703, "global_step": 416696, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.120518445968628, "global_step": 416697, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.186676025390625, "global_step": 416698, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1015355587005615, "global_step": 416699, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.072809934616089, "global_step": 416700, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0785810947418213, "global_step": 416701, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.024280548095703, "global_step": 416702, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0645253658294678, "global_step": 416703, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.188815116882324, "global_step": 416704, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.061305284500122, "global_step": 416705, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.075312614440918, "global_step": 416706, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0066328048706055, "global_step": 416707, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1030938625335693, "global_step": 416708, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.058971643447876, "global_step": 416709, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0946168899536133, "global_step": 416710, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.102339744567871, "global_step": 416711, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1789536476135254, "global_step": 416712, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.056867837905884, "global_step": 416713, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.024017095565796, "global_step": 416714, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1729936599731445, "global_step": 416715, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1564555168151855, "global_step": 416716, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0843706130981445, "global_step": 416717, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.157763719558716, "global_step": 416718, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.060659885406494, "global_step": 416719, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1140127182006836, "global_step": 416720, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1214635372161865, "global_step": 416721, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.094236135482788, "global_step": 416722, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0784616470336914, "global_step": 416723, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.202270984649658, "global_step": 416724, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.140327215194702, "global_step": 416725, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.127610445022583, "global_step": 416726, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0582544803619385, "global_step": 416727, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.110644817352295, "global_step": 416728, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.060518503189087, "global_step": 416729, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1021225452423096, "global_step": 416730, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.156745672225952, "global_step": 416731, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0920443534851074, "global_step": 416732, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1833927631378174, "global_step": 416733, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1239962577819824, "global_step": 416734, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.210109233856201, "global_step": 416735, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.072134494781494, "global_step": 416736, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0484821796417236, "global_step": 416737, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0969045162200928, "global_step": 416738, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0900399684906006, "global_step": 416739, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1005618572235107, "global_step": 416740, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.138627767562866, "global_step": 416741, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.04062819480896, "global_step": 416742, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0878562927246094, "global_step": 416743, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1338281631469727, "global_step": 416744, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0622100830078125, "global_step": 416745, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0652878284454346, "global_step": 416746, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.120251417160034, "global_step": 416747, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.117429494857788, "global_step": 416748, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0229055881500244, "global_step": 416749, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0949411392211914, "global_step": 416750, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.9264906644821167, "global_step": 416751, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0484602451324463, "global_step": 416752, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0621213912963867, "global_step": 416753, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.178941249847412, "global_step": 416754, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0737903118133545, "global_step": 416755, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.099047899246216, "global_step": 416756, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.137425184249878, "global_step": 416757, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1186046600341797, "global_step": 416758, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0840423107147217, "global_step": 416759, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0901939868927, "global_step": 416760, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.156271457672119, "global_step": 416761, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1118624210357666, "global_step": 416762, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1918070316314697, "global_step": 416763, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.109919786453247, "global_step": 416764, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.175987958908081, "global_step": 416765, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.185152292251587, "global_step": 416766, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0389063358306885, "global_step": 416767, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0872442722320557, "global_step": 416768, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1035492420196533, "global_step": 416769, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1050751209259033, "global_step": 416770, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.052103042602539, "global_step": 416771, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.076892137527466, "global_step": 416772, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.127939462661743, "global_step": 416773, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1325385570526123, "global_step": 416774, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.142655611038208, "global_step": 416775, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1181106567382812, "global_step": 416776, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.055255651473999, "global_step": 416777, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1200389862060547, "global_step": 416778, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0871567726135254, "global_step": 416779, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.057920455932617, "global_step": 416780, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1799111366271973, "global_step": 416781, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.105067729949951, "global_step": 416782, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.2012128829956055, "global_step": 416783, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1373422145843506, "global_step": 416784, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.045106887817383, "global_step": 416785, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.036201238632202, "global_step": 416786, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.134397506713867, "global_step": 416787, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.068540573120117, "global_step": 416788, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.179957866668701, "global_step": 416789, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1406912803649902, "global_step": 416790, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0562803745269775, "global_step": 416791, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.06075119972229, "global_step": 416792, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0598807334899902, "global_step": 416793, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0439062118530273, "global_step": 416794, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1220850944519043, "global_step": 416795, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1100544929504395, "global_step": 416796, "epoch": 779, "lr": 5e-05}
{"train_loss": 1.987927794456482, "global_step": 416797, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.1676204204559326, "global_step": 416798, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.039639711380005, "global_step": 416799, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.048571825027466, "global_step": 416800, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0974390506744385, "global_step": 416801, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0877411365509033, "global_step": 416802, "epoch": 779, "lr": 5e-05}
{"train_loss": 2.0628387928009033, "global_step": 416803, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0997395515441895, "global_step": 416804, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.008975028991699, "global_step": 416805, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.114764928817749, "global_step": 416806, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.116521120071411, "global_step": 416807, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0357370376586914, "global_step": 416808, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0194079875946045, "global_step": 416809, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.056628942489624, "global_step": 416810, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.087724208831787, "global_step": 416811, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9881025552749634, "global_step": 416812, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.146433115005493, "global_step": 416813, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0068140029907227, "global_step": 416814, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.078176259994507, "global_step": 416815, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.062861680984497, "global_step": 416816, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0525166988372803, "global_step": 416817, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1456267833709717, "global_step": 416818, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1326117515563965, "global_step": 416819, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0778257846832275, "global_step": 416820, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1459903717041016, "global_step": 416821, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0214052200317383, "global_step": 416822, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0436270236968994, "global_step": 416823, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.088972568511963, "global_step": 416824, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0324630737304688, "global_step": 416825, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1436092853546143, "global_step": 416826, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.114046096801758, "global_step": 416827, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.038010597229004, "global_step": 416828, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0219173431396484, "global_step": 416829, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.180206298828125, "global_step": 416830, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.078847646713257, "global_step": 416831, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0730841159820557, "global_step": 416832, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1645216941833496, "global_step": 416833, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1288609504699707, "global_step": 416834, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0903890132904053, "global_step": 416835, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.09649658203125, "global_step": 416836, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1613986492156982, "global_step": 416837, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.113755702972412, "global_step": 416838, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1321160793304443, "global_step": 416839, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.067579746246338, "global_step": 416840, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.066127061843872, "global_step": 416841, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.114349603652954, "global_step": 416842, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.118265390396118, "global_step": 416843, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0532846450805664, "global_step": 416844, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.054713726043701, "global_step": 416845, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9744449853897095, "global_step": 416846, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.131840229034424, "global_step": 416847, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.009263753890991, "global_step": 416848, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1141276359558105, "global_step": 416849, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1146934032440186, "global_step": 416850, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0381624698638916, "global_step": 416851, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.096240282058716, "global_step": 416852, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0508036613464355, "global_step": 416853, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.043884038925171, "global_step": 416854, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0240564346313477, "global_step": 416855, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0750997066497803, "global_step": 416856, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.106522560119629, "global_step": 416857, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0881729125976562, "global_step": 416858, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1148853302001953, "global_step": 416859, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0263073444366455, "global_step": 416860, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.131000280380249, "global_step": 416861, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0649900436401367, "global_step": 416862, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.049098491668701, "global_step": 416863, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1189041137695312, "global_step": 416864, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1230924129486084, "global_step": 416865, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.169938325881958, "global_step": 416866, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.05348539352417, "global_step": 416867, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.083456516265869, "global_step": 416868, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0853023529052734, "global_step": 416869, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.169079303741455, "global_step": 416870, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0778560638427734, "global_step": 416871, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.089092493057251, "global_step": 416872, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0772595405578613, "global_step": 416873, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.067126512527466, "global_step": 416874, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0092012882232666, "global_step": 416875, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0645406246185303, "global_step": 416876, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.060056447982788, "global_step": 416877, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.116072177886963, "global_step": 416878, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0671703815460205, "global_step": 416879, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.015941619873047, "global_step": 416880, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.099668502807617, "global_step": 416881, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0046546459198, "global_step": 416882, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.128384590148926, "global_step": 416883, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1048638820648193, "global_step": 416884, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0424346923828125, "global_step": 416885, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9434163570404053, "global_step": 416886, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0435619354248047, "global_step": 416887, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0142459869384766, "global_step": 416888, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1581599712371826, "global_step": 416889, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1412975788116455, "global_step": 416890, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.077589511871338, "global_step": 416891, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0875742435455322, "global_step": 416892, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.181497812271118, "global_step": 416893, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1440038681030273, "global_step": 416894, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.061676502227783, "global_step": 416895, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.10658597946167, "global_step": 416896, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0815389156341553, "global_step": 416897, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.128523588180542, "global_step": 416898, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.023409366607666, "global_step": 416899, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.102489948272705, "global_step": 416900, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9704079627990723, "global_step": 416901, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1446731090545654, "global_step": 416902, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.026698350906372, "global_step": 416903, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1175434589385986, "global_step": 416904, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.044619560241699, "global_step": 416905, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1108267307281494, "global_step": 416906, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.152100086212158, "global_step": 416907, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.030580997467041, "global_step": 416908, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0870203971862793, "global_step": 416909, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.079552412033081, "global_step": 416910, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.110393762588501, "global_step": 416911, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0679497718811035, "global_step": 416912, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.070770502090454, "global_step": 416913, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0690128803253174, "global_step": 416914, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0710034370422363, "global_step": 416915, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.042612075805664, "global_step": 416916, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0124213695526123, "global_step": 416917, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0409395694732666, "global_step": 416918, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.104843854904175, "global_step": 416919, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.186459541320801, "global_step": 416920, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0643527507781982, "global_step": 416921, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1133947372436523, "global_step": 416922, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1343724727630615, "global_step": 416923, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9935261011123657, "global_step": 416924, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0887210369110107, "global_step": 416925, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0834972858428955, "global_step": 416926, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1581032276153564, "global_step": 416927, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1034817695617676, "global_step": 416928, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.083087682723999, "global_step": 416929, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0044636726379395, "global_step": 416930, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0933432579040527, "global_step": 416931, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.089226722717285, "global_step": 416932, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.040163516998291, "global_step": 416933, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.030198574066162, "global_step": 416934, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.107957601547241, "global_step": 416935, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0632262229919434, "global_step": 416936, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.144671678543091, "global_step": 416937, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.095738410949707, "global_step": 416938, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1092584133148193, "global_step": 416939, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0301830768585205, "global_step": 416940, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0879225730895996, "global_step": 416941, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0413331985473633, "global_step": 416942, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0606207847595215, "global_step": 416943, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0885910987854004, "global_step": 416944, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0637130737304688, "global_step": 416945, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.995375633239746, "global_step": 416946, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.04001522064209, "global_step": 416947, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0632479190826416, "global_step": 416948, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0624732971191406, "global_step": 416949, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.117513656616211, "global_step": 416950, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0689592361450195, "global_step": 416951, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0345921516418457, "global_step": 416952, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.051116943359375, "global_step": 416953, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1205976009368896, "global_step": 416954, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0141563415527344, "global_step": 416955, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0362792015075684, "global_step": 416956, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1102545261383057, "global_step": 416957, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.007457733154297, "global_step": 416958, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1932730674743652, "global_step": 416959, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.056913137435913, "global_step": 416960, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0906269550323486, "global_step": 416961, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0712356567382812, "global_step": 416962, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0432190895080566, "global_step": 416963, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.041567087173462, "global_step": 416964, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0974133014678955, "global_step": 416965, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1264090538024902, "global_step": 416966, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1121742725372314, "global_step": 416967, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0919344425201416, "global_step": 416968, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0491983890533447, "global_step": 416969, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.183149576187134, "global_step": 416970, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.111699104309082, "global_step": 416971, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.129805326461792, "global_step": 416972, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.150386333465576, "global_step": 416973, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0960330963134766, "global_step": 416974, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0637903213500977, "global_step": 416975, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.106346368789673, "global_step": 416976, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.087738037109375, "global_step": 416977, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.076922655105591, "global_step": 416978, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.058682680130005, "global_step": 416979, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.164684534072876, "global_step": 416980, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.075355052947998, "global_step": 416981, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0369246006011963, "global_step": 416982, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1036834716796875, "global_step": 416983, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.135424852371216, "global_step": 416984, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.04756498336792, "global_step": 416985, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.108719825744629, "global_step": 416986, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.063599109649658, "global_step": 416987, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1801462173461914, "global_step": 416988, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.074922800064087, "global_step": 416989, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1302640438079834, "global_step": 416990, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1535985469818115, "global_step": 416991, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.130763530731201, "global_step": 416992, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.174802780151367, "global_step": 416993, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0820770263671875, "global_step": 416994, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1192708015441895, "global_step": 416995, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1181623935699463, "global_step": 416996, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1331193447113037, "global_step": 416997, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0610475540161133, "global_step": 416998, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1162500381469727, "global_step": 416999, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1115968227386475, "global_step": 417000, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.072397232055664, "global_step": 417001, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.091541051864624, "global_step": 417002, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1265108585357666, "global_step": 417003, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1122801303863525, "global_step": 417004, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.061704635620117, "global_step": 417005, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1303610801696777, "global_step": 417006, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.02506160736084, "global_step": 417007, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9928762912750244, "global_step": 417008, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.039018154144287, "global_step": 417009, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.15987229347229, "global_step": 417010, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0733189582824707, "global_step": 417011, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0892181396484375, "global_step": 417012, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.098728895187378, "global_step": 417013, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0835137367248535, "global_step": 417014, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.103389024734497, "global_step": 417015, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.038810968399048, "global_step": 417016, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1655116081237793, "global_step": 417017, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1085751056671143, "global_step": 417018, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0330262184143066, "global_step": 417019, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.131274461746216, "global_step": 417020, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0139007568359375, "global_step": 417021, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0386641025543213, "global_step": 417022, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0148181915283203, "global_step": 417023, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.073971748352051, "global_step": 417024, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.111281394958496, "global_step": 417025, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.060289144515991, "global_step": 417026, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0881528854370117, "global_step": 417027, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1492533683776855, "global_step": 417028, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1306073665618896, "global_step": 417029, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0318992137908936, "global_step": 417030, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1060290336608887, "global_step": 417031, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0276827812194824, "global_step": 417032, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.025766372680664, "global_step": 417033, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0575289726257324, "global_step": 417034, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.027675151824951, "global_step": 417035, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.06571102142334, "global_step": 417036, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0520942211151123, "global_step": 417037, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.089077949523926, "global_step": 417038, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.110196113586426, "global_step": 417039, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.165036916732788, "global_step": 417040, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0705504417419434, "global_step": 417041, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0237934589385986, "global_step": 417042, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.2454116344451904, "global_step": 417043, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.050511598587036, "global_step": 417044, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.060387134552002, "global_step": 417045, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.17922043800354, "global_step": 417046, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1255528926849365, "global_step": 417047, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1067376136779785, "global_step": 417048, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.083625078201294, "global_step": 417049, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.001779079437256, "global_step": 417050, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.039764165878296, "global_step": 417051, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.185802936553955, "global_step": 417052, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1058013439178467, "global_step": 417053, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.151109218597412, "global_step": 417054, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0323867797851562, "global_step": 417055, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0915257930755615, "global_step": 417056, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.05251407623291, "global_step": 417057, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.052048683166504, "global_step": 417058, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.076038360595703, "global_step": 417059, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.091357946395874, "global_step": 417060, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1913976669311523, "global_step": 417061, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0818517208099365, "global_step": 417062, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1627986431121826, "global_step": 417063, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1157658100128174, "global_step": 417064, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.130692958831787, "global_step": 417065, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.058312177658081, "global_step": 417066, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1410210132598877, "global_step": 417067, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.084399700164795, "global_step": 417068, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0491151809692383, "global_step": 417069, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0346624851226807, "global_step": 417070, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.029763698577881, "global_step": 417071, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0985774993896484, "global_step": 417072, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.157478094100952, "global_step": 417073, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9711952209472656, "global_step": 417074, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1322522163391113, "global_step": 417075, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.126577138900757, "global_step": 417076, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1202051639556885, "global_step": 417077, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.04612135887146, "global_step": 417078, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.054595708847046, "global_step": 417079, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9785436391830444, "global_step": 417080, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.083008289337158, "global_step": 417081, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0711922645568848, "global_step": 417082, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.103349447250366, "global_step": 417083, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.080657720565796, "global_step": 417084, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.156151294708252, "global_step": 417085, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0498440265655518, "global_step": 417086, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1073174476623535, "global_step": 417087, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.141833782196045, "global_step": 417088, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1250009536743164, "global_step": 417089, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1005940437316895, "global_step": 417090, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.082146644592285, "global_step": 417091, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0458836555480957, "global_step": 417092, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.205548048019409, "global_step": 417093, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.184630870819092, "global_step": 417094, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1091978549957275, "global_step": 417095, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1858439445495605, "global_step": 417096, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1474831104278564, "global_step": 417097, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0566365718841553, "global_step": 417098, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.227186441421509, "global_step": 417099, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.011854410171509, "global_step": 417100, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.093435525894165, "global_step": 417101, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0665557384490967, "global_step": 417102, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0827934741973877, "global_step": 417103, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0764548778533936, "global_step": 417104, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0961687564849854, "global_step": 417105, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.057326555252075, "global_step": 417106, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0905957221984863, "global_step": 417107, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0926706790924072, "global_step": 417108, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0654890537261963, "global_step": 417109, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0934078693389893, "global_step": 417110, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.061502695083618, "global_step": 417111, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.106787919998169, "global_step": 417112, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.053541898727417, "global_step": 417113, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0891709327697754, "global_step": 417114, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0747172832489014, "global_step": 417115, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.065556526184082, "global_step": 417116, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1290509700775146, "global_step": 417117, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9746328592300415, "global_step": 417118, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0243561267852783, "global_step": 417119, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1361610889434814, "global_step": 417120, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0791542530059814, "global_step": 417121, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.087576389312744, "global_step": 417122, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.129120349884033, "global_step": 417123, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1185219287872314, "global_step": 417124, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0937912464141846, "global_step": 417125, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0245556831359863, "global_step": 417126, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.035487413406372, "global_step": 417127, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0594143867492676, "global_step": 417128, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1359565258026123, "global_step": 417129, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.102780342102051, "global_step": 417130, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.964829444885254, "global_step": 417131, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1572744846343994, "global_step": 417132, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1890921592712402, "global_step": 417133, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0169296264648438, "global_step": 417134, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.071988344192505, "global_step": 417135, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1107285022735596, "global_step": 417136, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0147600173950195, "global_step": 417137, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.093052625656128, "global_step": 417138, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.244969367980957, "global_step": 417139, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.146723508834839, "global_step": 417140, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.2151622772216797, "global_step": 417141, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.099545955657959, "global_step": 417142, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.116837501525879, "global_step": 417143, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1197350025177, "global_step": 417144, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0705182552337646, "global_step": 417145, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0566647052764893, "global_step": 417146, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9974819421768188, "global_step": 417147, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1283321380615234, "global_step": 417148, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.021864414215088, "global_step": 417149, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.042679786682129, "global_step": 417150, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.10007643699646, "global_step": 417151, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0889406204223633, "global_step": 417152, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.090331554412842, "global_step": 417153, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.067230224609375, "global_step": 417154, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0141379833221436, "global_step": 417155, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0534017086029053, "global_step": 417156, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.113553047180176, "global_step": 417157, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.090747594833374, "global_step": 417158, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.121678352355957, "global_step": 417159, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1114208698272705, "global_step": 417160, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0800085067749023, "global_step": 417161, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.089933395385742, "global_step": 417162, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.081753969192505, "global_step": 417163, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0377466678619385, "global_step": 417164, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.113614320755005, "global_step": 417165, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.140308380126953, "global_step": 417166, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0283989906311035, "global_step": 417167, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.132382869720459, "global_step": 417168, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1137008666992188, "global_step": 417169, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0425546169281006, "global_step": 417170, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.178642511367798, "global_step": 417171, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0317955017089844, "global_step": 417172, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.101423978805542, "global_step": 417173, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.136733055114746, "global_step": 417174, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.046436309814453, "global_step": 417175, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.038708448410034, "global_step": 417176, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1768133640289307, "global_step": 417177, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.15769100189209, "global_step": 417178, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1446805000305176, "global_step": 417179, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.080698013305664, "global_step": 417180, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.061877489089966, "global_step": 417181, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1195127964019775, "global_step": 417182, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.160342216491699, "global_step": 417183, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.058919668197632, "global_step": 417184, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0372884273529053, "global_step": 417185, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.071207284927368, "global_step": 417186, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.032118797302246, "global_step": 417187, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.003159999847412, "global_step": 417188, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0398764610290527, "global_step": 417189, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0972774028778076, "global_step": 417190, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1924002170562744, "global_step": 417191, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.166999101638794, "global_step": 417192, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1224570274353027, "global_step": 417193, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1109447479248047, "global_step": 417194, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9969063997268677, "global_step": 417195, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1487014293670654, "global_step": 417196, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.104428291320801, "global_step": 417197, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1268630027770996, "global_step": 417198, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.002983570098877, "global_step": 417199, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0645718574523926, "global_step": 417200, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0580379962921143, "global_step": 417201, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.073047161102295, "global_step": 417202, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.036942481994629, "global_step": 417203, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0678725242614746, "global_step": 417204, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1232659816741943, "global_step": 417205, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.037830114364624, "global_step": 417206, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.113272190093994, "global_step": 417207, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0284523963928223, "global_step": 417208, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1395461559295654, "global_step": 417209, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0765202045440674, "global_step": 417210, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0559983253479004, "global_step": 417211, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0701377391815186, "global_step": 417212, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9681802988052368, "global_step": 417213, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0864336490631104, "global_step": 417214, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.067800760269165, "global_step": 417215, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.039316177368164, "global_step": 417216, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0747671127319336, "global_step": 417217, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1373441219329834, "global_step": 417218, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.2183749675750732, "global_step": 417219, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0573437213897705, "global_step": 417220, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.147909164428711, "global_step": 417221, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9892194271087646, "global_step": 417222, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.059941053390503, "global_step": 417223, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.06762957572937, "global_step": 417224, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0633199214935303, "global_step": 417225, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1588857173919678, "global_step": 417226, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.047814130783081, "global_step": 417227, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9938191175460815, "global_step": 417228, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0690910816192627, "global_step": 417229, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.115399122238159, "global_step": 417230, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.041891098022461, "global_step": 417231, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1033859252929688, "global_step": 417232, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1287503242492676, "global_step": 417233, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.037315607070923, "global_step": 417234, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.045809030532837, "global_step": 417235, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.06345272064209, "global_step": 417236, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.13323974609375, "global_step": 417237, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.107182264328003, "global_step": 417238, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.036958694458008, "global_step": 417239, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0768730640411377, "global_step": 417240, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.153153419494629, "global_step": 417241, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.086099863052368, "global_step": 417242, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1522648334503174, "global_step": 417243, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.04480242729187, "global_step": 417244, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0176990032196045, "global_step": 417245, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1032192707061768, "global_step": 417246, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.102306842803955, "global_step": 417247, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0268301963806152, "global_step": 417248, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0472826957702637, "global_step": 417249, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.113591194152832, "global_step": 417250, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.126107931137085, "global_step": 417251, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1672279834747314, "global_step": 417252, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0626678466796875, "global_step": 417253, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0727877616882324, "global_step": 417254, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.097348928451538, "global_step": 417255, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.149838924407959, "global_step": 417256, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.167910099029541, "global_step": 417257, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0274031162261963, "global_step": 417258, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1412532329559326, "global_step": 417259, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.176887273788452, "global_step": 417260, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0598666667938232, "global_step": 417261, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0850989818573, "global_step": 417262, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0690560340881348, "global_step": 417263, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0350770950317383, "global_step": 417264, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.041656970977783, "global_step": 417265, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.088703155517578, "global_step": 417266, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.025531768798828, "global_step": 417267, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.129171848297119, "global_step": 417268, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.129554271697998, "global_step": 417269, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.080061435699463, "global_step": 417270, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0631113052368164, "global_step": 417271, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0407474040985107, "global_step": 417272, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.109098434448242, "global_step": 417273, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.071281671524048, "global_step": 417274, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.02811861038208, "global_step": 417275, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0796687602996826, "global_step": 417276, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0467848777770996, "global_step": 417277, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.11344838142395, "global_step": 417278, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0955300331115723, "global_step": 417279, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0477004051208496, "global_step": 417280, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0509769916534424, "global_step": 417281, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9893146753311157, "global_step": 417282, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1637537479400635, "global_step": 417283, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1014065742492676, "global_step": 417284, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9823198318481445, "global_step": 417285, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0946128368377686, "global_step": 417286, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0250422954559326, "global_step": 417287, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0280821323394775, "global_step": 417288, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0680322647094727, "global_step": 417289, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.160482883453369, "global_step": 417290, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.068406581878662, "global_step": 417291, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9996323585510254, "global_step": 417292, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1636059284210205, "global_step": 417293, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.113006591796875, "global_step": 417294, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.071650505065918, "global_step": 417295, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1243834495544434, "global_step": 417296, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.076568365097046, "global_step": 417297, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.060514450073242, "global_step": 417298, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.063159465789795, "global_step": 417299, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.048701763153076, "global_step": 417300, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.078538417816162, "global_step": 417301, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0867388248443604, "global_step": 417302, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.086308717727661, "global_step": 417303, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0272011756896973, "global_step": 417304, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0531084537506104, "global_step": 417305, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1337006092071533, "global_step": 417306, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.03983736038208, "global_step": 417307, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1055727005004883, "global_step": 417308, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0074169635772705, "global_step": 417309, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.08516001701355, "global_step": 417310, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.034130811691284, "global_step": 417311, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0511693954467773, "global_step": 417312, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1262004375457764, "global_step": 417313, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.078955888748169, "global_step": 417314, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.139937400817871, "global_step": 417315, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.151240348815918, "global_step": 417316, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0487093925476074, "global_step": 417317, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.095130443572998, "global_step": 417318, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1315019130706787, "global_step": 417319, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.099074125289917, "global_step": 417320, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.2023956775665283, "global_step": 417321, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.123523712158203, "global_step": 417322, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.01595401763916, "global_step": 417323, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.005049228668213, "global_step": 417324, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.120318651199341, "global_step": 417325, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0394649505615234, "global_step": 417326, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.059461832046509, "global_step": 417327, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9976365566253662, "global_step": 417328, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.047335147857666, "global_step": 417329, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1329736709594727, "global_step": 417330, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.141359329223633, "global_step": 417331, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0968828201293945, "global_step": 417332, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0363290309906006, "global_step": 417333, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0737438201904297, "global_step": 417334, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.11392879486084, "global_step": 417335, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.957993507385254, "global_step": 417336, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1140596866607666, "global_step": 417337, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.977132797241211, "global_step": 417338, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1588196754455566, "global_step": 417339, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1203320026397705, "global_step": 417340, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0617377758026123, "global_step": 417341, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1194982528686523, "global_step": 417342, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.18721866607666, "global_step": 417343, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0394296646118164, "global_step": 417344, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1117446422576904, "global_step": 417345, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0505385398864746, "global_step": 417346, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1681766510009766, "global_step": 417347, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1077706813812256, "global_step": 417348, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.065709114074707, "global_step": 417349, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0502381324768066, "global_step": 417350, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1283023357391357, "global_step": 417351, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.050550699234009, "global_step": 417352, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0587167739868164, "global_step": 417353, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0957674980163574, "global_step": 417354, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.138610601425171, "global_step": 417355, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.050638198852539, "global_step": 417356, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.095249891281128, "global_step": 417357, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0735228061676025, "global_step": 417358, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1310269832611084, "global_step": 417359, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.147674322128296, "global_step": 417360, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1447529792785645, "global_step": 417361, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0951452255249023, "global_step": 417362, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0006003379821777, "global_step": 417363, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.048321008682251, "global_step": 417364, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.136435031890869, "global_step": 417365, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0874409675598145, "global_step": 417366, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.015350103378296, "global_step": 417367, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1406188011169434, "global_step": 417368, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1284191608428955, "global_step": 417369, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.096710681915283, "global_step": 417370, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0764806270599365, "global_step": 417371, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0861823558807373, "global_step": 417372, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.151949882507324, "global_step": 417373, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.096370220184326, "global_step": 417374, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.043135643005371, "global_step": 417375, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1305971145629883, "global_step": 417376, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0383048057556152, "global_step": 417377, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1752612590789795, "global_step": 417378, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1057064533233643, "global_step": 417379, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1740946769714355, "global_step": 417380, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.076932191848755, "global_step": 417381, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.084256410598755, "global_step": 417382, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0478665828704834, "global_step": 417383, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.244243621826172, "global_step": 417384, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1093456745147705, "global_step": 417385, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0081357955932617, "global_step": 417386, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.079522132873535, "global_step": 417387, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0182530879974365, "global_step": 417388, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0326037406921387, "global_step": 417389, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1271238327026367, "global_step": 417390, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.093104124069214, "global_step": 417391, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.022130250930786, "global_step": 417392, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.029557466506958, "global_step": 417393, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1411917209625244, "global_step": 417394, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1421430110931396, "global_step": 417395, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0666942596435547, "global_step": 417396, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1756598949432373, "global_step": 417397, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1769285202026367, "global_step": 417398, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1099963188171387, "global_step": 417399, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0700831413269043, "global_step": 417400, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.092231512069702, "global_step": 417401, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.156771421432495, "global_step": 417402, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.030057430267334, "global_step": 417403, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.046220302581787, "global_step": 417404, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0071918964385986, "global_step": 417405, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.077728271484375, "global_step": 417406, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1082892417907715, "global_step": 417407, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1021060943603516, "global_step": 417408, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.192512273788452, "global_step": 417409, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.074141502380371, "global_step": 417410, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1070454120635986, "global_step": 417411, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.062103509902954, "global_step": 417412, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1252503395080566, "global_step": 417413, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1324551105499268, "global_step": 417414, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0291669368743896, "global_step": 417415, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0447118282318115, "global_step": 417416, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.150949239730835, "global_step": 417417, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0843842029571533, "global_step": 417418, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0703189373016357, "global_step": 417419, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.042701244354248, "global_step": 417420, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.107173204421997, "global_step": 417421, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0191330909729004, "global_step": 417422, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.051114797592163, "global_step": 417423, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0735316276550293, "global_step": 417424, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.043461799621582, "global_step": 417425, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.073892593383789, "global_step": 417426, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0341596603393555, "global_step": 417427, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1657350063323975, "global_step": 417428, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1213388442993164, "global_step": 417429, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.088035821914673, "global_step": 417430, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1410887241363525, "global_step": 417431, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0778932571411133, "global_step": 417432, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1085093021392822, "global_step": 417433, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1383893489837646, "global_step": 417434, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0844857692718506, "global_step": 417435, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1087749004364014, "global_step": 417436, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0032193660736084, "global_step": 417437, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1207196712493896, "global_step": 417438, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0743043422698975, "global_step": 417439, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0085134506225586, "global_step": 417440, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1110918521881104, "global_step": 417441, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1022281646728516, "global_step": 417442, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.149806499481201, "global_step": 417443, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9772450923919678, "global_step": 417444, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1053643226623535, "global_step": 417445, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.126871109008789, "global_step": 417446, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0705158710479736, "global_step": 417447, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0667970180511475, "global_step": 417448, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0474231243133545, "global_step": 417449, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.05490779876709, "global_step": 417450, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.067589282989502, "global_step": 417451, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1002838611602783, "global_step": 417452, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1270289421081543, "global_step": 417453, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1410443782806396, "global_step": 417454, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1294264793395996, "global_step": 417455, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0666916370391846, "global_step": 417456, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.980889081954956, "global_step": 417457, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.191455841064453, "global_step": 417458, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.994591474533081, "global_step": 417459, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.151467800140381, "global_step": 417460, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0135927200317383, "global_step": 417461, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.127945899963379, "global_step": 417462, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1287693977355957, "global_step": 417463, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.052232265472412, "global_step": 417464, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1572604179382324, "global_step": 417465, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.154465436935425, "global_step": 417466, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1212830543518066, "global_step": 417467, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1963887214660645, "global_step": 417468, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.155940532684326, "global_step": 417469, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0782954692840576, "global_step": 417470, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.054555892944336, "global_step": 417471, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.186609983444214, "global_step": 417472, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.07479190826416, "global_step": 417473, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1036601066589355, "global_step": 417474, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0379040241241455, "global_step": 417475, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.088268756866455, "global_step": 417476, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.165431261062622, "global_step": 417477, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0429251194000244, "global_step": 417478, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.104145050048828, "global_step": 417479, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1329870223999023, "global_step": 417480, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.088477611541748, "global_step": 417481, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9967191219329834, "global_step": 417482, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.085803508758545, "global_step": 417483, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1246416568756104, "global_step": 417484, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0008225440979004, "global_step": 417485, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.090681314468384, "global_step": 417486, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0549840927124023, "global_step": 417487, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.027820348739624, "global_step": 417488, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0219109058380127, "global_step": 417489, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1865878105163574, "global_step": 417490, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0693633556365967, "global_step": 417491, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0514044761657715, "global_step": 417492, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1303300857543945, "global_step": 417493, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.128537654876709, "global_step": 417494, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.139033555984497, "global_step": 417495, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.13504958152771, "global_step": 417496, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.116276502609253, "global_step": 417497, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.112647294998169, "global_step": 417498, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.997792363166809, "global_step": 417499, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0534040927886963, "global_step": 417500, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.109548807144165, "global_step": 417501, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0725972652435303, "global_step": 417502, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0486364364624023, "global_step": 417503, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0324978828430176, "global_step": 417504, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.141033172607422, "global_step": 417505, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.146186113357544, "global_step": 417506, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1129355430603027, "global_step": 417507, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.047943115234375, "global_step": 417508, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.145636796951294, "global_step": 417509, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1005353927612305, "global_step": 417510, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0969576835632324, "global_step": 417511, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.067579746246338, "global_step": 417512, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0586886405944824, "global_step": 417513, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.061584949493408, "global_step": 417514, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1268012523651123, "global_step": 417515, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.106910467147827, "global_step": 417516, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9743826389312744, "global_step": 417517, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0999433994293213, "global_step": 417518, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0647497177124023, "global_step": 417519, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.170142889022827, "global_step": 417520, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.114565372467041, "global_step": 417521, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.042344093322754, "global_step": 417522, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0454299449920654, "global_step": 417523, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.081364870071411, "global_step": 417524, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.113109588623047, "global_step": 417525, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1236155033111572, "global_step": 417526, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0655388832092285, "global_step": 417527, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9610211849212646, "global_step": 417528, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.075101613998413, "global_step": 417529, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.106774091720581, "global_step": 417530, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0101144313812256, "global_step": 417531, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.092877149581909, "global_step": 417532, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.185405969619751, "global_step": 417533, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0788168907165527, "global_step": 417534, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1471779346466064, "global_step": 417535, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0580387115478516, "global_step": 417536, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.018690347671509, "global_step": 417537, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0818397998809814, "global_step": 417538, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.125325918197632, "global_step": 417539, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1064257621765137, "global_step": 417540, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.097011089324951, "global_step": 417541, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0329432487487793, "global_step": 417542, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.06205415725708, "global_step": 417543, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0688860416412354, "global_step": 417544, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.107919216156006, "global_step": 417545, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1203665733337402, "global_step": 417546, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0605506896972656, "global_step": 417547, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.091808319091797, "global_step": 417548, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.112091064453125, "global_step": 417549, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1097629070281982, "global_step": 417550, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9926992654800415, "global_step": 417551, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1227729320526123, "global_step": 417552, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1578891277313232, "global_step": 417553, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.133925437927246, "global_step": 417554, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.082467794418335, "global_step": 417555, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.083773612976074, "global_step": 417556, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1772396564483643, "global_step": 417557, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1428732872009277, "global_step": 417558, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0641930103302, "global_step": 417559, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.978171706199646, "global_step": 417560, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.054285764694214, "global_step": 417561, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1538889408111572, "global_step": 417562, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1052844524383545, "global_step": 417563, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0861358642578125, "global_step": 417564, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0065555572509766, "global_step": 417565, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.138289213180542, "global_step": 417566, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0203044414520264, "global_step": 417567, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0335793495178223, "global_step": 417568, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1088528633117676, "global_step": 417569, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.069906711578369, "global_step": 417570, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.083859443664551, "global_step": 417571, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0686917304992676, "global_step": 417572, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.184584379196167, "global_step": 417573, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9518489837646484, "global_step": 417574, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.106276273727417, "global_step": 417575, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.000706195831299, "global_step": 417576, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.133080244064331, "global_step": 417577, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1752638816833496, "global_step": 417578, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1336171627044678, "global_step": 417579, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.029500961303711, "global_step": 417580, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.151949167251587, "global_step": 417581, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1217713356018066, "global_step": 417582, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1681876182556152, "global_step": 417583, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1195857524871826, "global_step": 417584, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1891255378723145, "global_step": 417585, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.062666177749634, "global_step": 417586, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.058288812637329, "global_step": 417587, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0775811672210693, "global_step": 417588, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0908961296081543, "global_step": 417589, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.157437801361084, "global_step": 417590, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0532968044281006, "global_step": 417591, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1568448543548584, "global_step": 417592, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.103377342224121, "global_step": 417593, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0830612182617188, "global_step": 417594, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.078908681869507, "global_step": 417595, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1029610633850098, "global_step": 417596, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0431108474731445, "global_step": 417597, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1209304332733154, "global_step": 417598, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0992465019226074, "global_step": 417599, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.083592414855957, "global_step": 417600, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.124624252319336, "global_step": 417601, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1507904529571533, "global_step": 417602, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0760276317596436, "global_step": 417603, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.020268201828003, "global_step": 417604, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1400625705718994, "global_step": 417605, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.058279037475586, "global_step": 417606, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1421775817871094, "global_step": 417607, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.073911666870117, "global_step": 417608, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0898377895355225, "global_step": 417609, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.165651321411133, "global_step": 417610, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1469202041625977, "global_step": 417611, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1045026779174805, "global_step": 417612, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.110276937484741, "global_step": 417613, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0648200511932373, "global_step": 417614, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1532559394836426, "global_step": 417615, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1550798416137695, "global_step": 417616, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.117554187774658, "global_step": 417617, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1055986881256104, "global_step": 417618, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.081641435623169, "global_step": 417619, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1060941219329834, "global_step": 417620, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0367846488952637, "global_step": 417621, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0579569339752197, "global_step": 417622, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.073533535003662, "global_step": 417623, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.2024612426757812, "global_step": 417624, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0156636238098145, "global_step": 417625, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0810563564300537, "global_step": 417626, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.130596160888672, "global_step": 417627, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1249396800994873, "global_step": 417628, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.013852119445801, "global_step": 417629, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.075092315673828, "global_step": 417630, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.039229393005371, "global_step": 417631, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0439014434814453, "global_step": 417632, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.069573163986206, "global_step": 417633, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.121035099029541, "global_step": 417634, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.069293737411499, "global_step": 417635, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0952625274658203, "global_step": 417636, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0039126873016357, "global_step": 417637, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.107016086578369, "global_step": 417638, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0932719707489014, "global_step": 417639, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0583419799804688, "global_step": 417640, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1148180961608887, "global_step": 417641, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.972426414489746, "global_step": 417642, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0893430709838867, "global_step": 417643, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1180644035339355, "global_step": 417644, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.105659246444702, "global_step": 417645, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1182565689086914, "global_step": 417646, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0937044620513916, "global_step": 417647, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9835211038589478, "global_step": 417648, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.148878574371338, "global_step": 417649, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1992859840393066, "global_step": 417650, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1026575565338135, "global_step": 417651, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0918633937835693, "global_step": 417652, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.056887149810791, "global_step": 417653, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.122279167175293, "global_step": 417654, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.145230770111084, "global_step": 417655, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0592093467712402, "global_step": 417656, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1441900730133057, "global_step": 417657, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0741262435913086, "global_step": 417658, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1147217750549316, "global_step": 417659, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.100264072418213, "global_step": 417660, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0950915813446045, "global_step": 417661, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0919106006622314, "global_step": 417662, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.082857608795166, "global_step": 417663, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9987072944641113, "global_step": 417664, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.015733242034912, "global_step": 417665, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.067826509475708, "global_step": 417666, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.126819372177124, "global_step": 417667, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.152981758117676, "global_step": 417668, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1173689365386963, "global_step": 417669, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.156017303466797, "global_step": 417670, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1603517532348633, "global_step": 417671, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1025350093841553, "global_step": 417672, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1379079818725586, "global_step": 417673, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.031148672103882, "global_step": 417674, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0824687480926514, "global_step": 417675, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0072085857391357, "global_step": 417676, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1118788719177246, "global_step": 417677, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1066133975982666, "global_step": 417678, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1173346042633057, "global_step": 417679, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0996625423431396, "global_step": 417680, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0685477256774902, "global_step": 417681, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0876364707946777, "global_step": 417682, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0541553497314453, "global_step": 417683, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.106343984603882, "global_step": 417684, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0466623306274414, "global_step": 417685, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0467824935913086, "global_step": 417686, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1695306301116943, "global_step": 417687, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1176819801330566, "global_step": 417688, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1006672382354736, "global_step": 417689, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.035709857940674, "global_step": 417690, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0026800632476807, "global_step": 417691, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.972293734550476, "global_step": 417692, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0609230995178223, "global_step": 417693, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0567870140075684, "global_step": 417694, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.138241767883301, "global_step": 417695, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1404950618743896, "global_step": 417696, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.076430082321167, "global_step": 417697, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0638763904571533, "global_step": 417698, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.077155828475952, "global_step": 417699, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1016249656677246, "global_step": 417700, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0749311447143555, "global_step": 417701, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0203359127044678, "global_step": 417702, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0966432094573975, "global_step": 417703, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.084627866744995, "global_step": 417704, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1134393215179443, "global_step": 417705, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0871689319610596, "global_step": 417706, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0859076976776123, "global_step": 417707, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.112515926361084, "global_step": 417708, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1246726512908936, "global_step": 417709, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0659384727478027, "global_step": 417710, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.02882719039917, "global_step": 417711, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0672616958618164, "global_step": 417712, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.069053888320923, "global_step": 417713, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1172420978546143, "global_step": 417714, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.072498321533203, "global_step": 417715, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0485126972198486, "global_step": 417716, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0668089389801025, "global_step": 417717, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.043022394180298, "global_step": 417718, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1370227336883545, "global_step": 417719, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.204469919204712, "global_step": 417720, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0352084636688232, "global_step": 417721, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1354174613952637, "global_step": 417722, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.058495044708252, "global_step": 417723, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.100273370742798, "global_step": 417724, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.024845600128174, "global_step": 417725, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.113046884536743, "global_step": 417726, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.045138120651245, "global_step": 417727, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.125251293182373, "global_step": 417728, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1748158931732178, "global_step": 417729, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.9870102405548096, "global_step": 417730, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1508731842041016, "global_step": 417731, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0697808265686035, "global_step": 417732, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0990376472473145, "global_step": 417733, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1184370517730713, "global_step": 417734, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0262839794158936, "global_step": 417735, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.140765905380249, "global_step": 417736, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0734848976135254, "global_step": 417737, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0331871509552, "global_step": 417738, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0490188598632812, "global_step": 417739, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.04499888420105, "global_step": 417740, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1105828285217285, "global_step": 417741, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1228442192077637, "global_step": 417742, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.131974220275879, "global_step": 417743, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.096975326538086, "global_step": 417744, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.003908157348633, "global_step": 417745, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.077056407928467, "global_step": 417746, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0522537231445312, "global_step": 417747, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0999348163604736, "global_step": 417748, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1120479106903076, "global_step": 417749, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.096968650817871, "global_step": 417750, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.106456756591797, "global_step": 417751, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0808348655700684, "global_step": 417752, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0615012645721436, "global_step": 417753, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0633749961853027, "global_step": 417754, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.125041961669922, "global_step": 417755, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.078784704208374, "global_step": 417756, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1205904483795166, "global_step": 417757, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0349740982055664, "global_step": 417758, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0113701820373535, "global_step": 417759, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.058669328689575, "global_step": 417760, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0432612895965576, "global_step": 417761, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0350542068481445, "global_step": 417762, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.091671943664551, "global_step": 417763, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1508476734161377, "global_step": 417764, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.1769680976867676, "global_step": 417765, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.162081003189087, "global_step": 417766, "epoch": 780, "lr": 5e-05}
{"train_loss": 1.970124363899231, "global_step": 417767, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0641086101531982, "global_step": 417768, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.093871831893921, "global_step": 417769, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.079087495803833, "global_step": 417770, "epoch": 780, "lr": 5e-05}
{"train_loss": 2.0868592262268066, "global_step": 417771, "epoch": 780, "lr": 5e-05, "val_loss": 5.644550323486328, "test_reconst_mse": 0.07365117222070694}
{"train_loss": 2.153303861618042, "global_step": 417772, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0684921741485596, "global_step": 417773, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0927367210388184, "global_step": 417774, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.028024196624756, "global_step": 417775, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1125094890594482, "global_step": 417776, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0862338542938232, "global_step": 417777, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1251397132873535, "global_step": 417778, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9967142343521118, "global_step": 417779, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0452451705932617, "global_step": 417780, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.06728458404541, "global_step": 417781, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1249139308929443, "global_step": 417782, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0500190258026123, "global_step": 417783, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.055939197540283, "global_step": 417784, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0993080139160156, "global_step": 417785, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.106546401977539, "global_step": 417786, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.998363971710205, "global_step": 417787, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0339856147766113, "global_step": 417788, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0290586948394775, "global_step": 417789, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.194063901901245, "global_step": 417790, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0683724880218506, "global_step": 417791, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0400519371032715, "global_step": 417792, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.122495651245117, "global_step": 417793, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0719375610351562, "global_step": 417794, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1297454833984375, "global_step": 417795, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.047022581100464, "global_step": 417796, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0956614017486572, "global_step": 417797, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1190083026885986, "global_step": 417798, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.121554374694824, "global_step": 417799, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.206986665725708, "global_step": 417800, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.06538724899292, "global_step": 417801, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.115544319152832, "global_step": 417802, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0841057300567627, "global_step": 417803, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.100066900253296, "global_step": 417804, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1322004795074463, "global_step": 417805, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.100339651107788, "global_step": 417806, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.103081226348877, "global_step": 417807, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1567821502685547, "global_step": 417808, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0243630409240723, "global_step": 417809, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1631252765655518, "global_step": 417810, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1210405826568604, "global_step": 417811, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1077682971954346, "global_step": 417812, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0536935329437256, "global_step": 417813, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0319552421569824, "global_step": 417814, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1677207946777344, "global_step": 417815, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1143014430999756, "global_step": 417816, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1190521717071533, "global_step": 417817, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0994420051574707, "global_step": 417818, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.025383472442627, "global_step": 417819, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.138805627822876, "global_step": 417820, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1048483848571777, "global_step": 417821, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1561996936798096, "global_step": 417822, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.033676862716675, "global_step": 417823, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0871567726135254, "global_step": 417824, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0341315269470215, "global_step": 417825, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.056302785873413, "global_step": 417826, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.074348211288452, "global_step": 417827, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.087573528289795, "global_step": 417828, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9154669046401978, "global_step": 417829, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.01706600189209, "global_step": 417830, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.07877516746521, "global_step": 417831, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0235137939453125, "global_step": 417832, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.075115442276001, "global_step": 417833, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0673208236694336, "global_step": 417834, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1313843727111816, "global_step": 417835, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0379159450531006, "global_step": 417836, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.132093667984009, "global_step": 417837, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1179027557373047, "global_step": 417838, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1268181800842285, "global_step": 417839, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.092897653579712, "global_step": 417840, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0894899368286133, "global_step": 417841, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.097336530685425, "global_step": 417842, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1136598587036133, "global_step": 417843, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0974254608154297, "global_step": 417844, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1009466648101807, "global_step": 417845, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1001088619232178, "global_step": 417846, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.976752758026123, "global_step": 417847, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0117626190185547, "global_step": 417848, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.061077356338501, "global_step": 417849, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0030441284179688, "global_step": 417850, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.081873655319214, "global_step": 417851, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.104982376098633, "global_step": 417852, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9885435104370117, "global_step": 417853, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0670766830444336, "global_step": 417854, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0687198638916016, "global_step": 417855, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0504465103149414, "global_step": 417856, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.059518814086914, "global_step": 417857, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0396218299865723, "global_step": 417858, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0856759548187256, "global_step": 417859, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0768866539001465, "global_step": 417860, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.072571039199829, "global_step": 417861, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.103336811065674, "global_step": 417862, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.149249315261841, "global_step": 417863, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1781930923461914, "global_step": 417864, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0669431686401367, "global_step": 417865, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.066960334777832, "global_step": 417866, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.099349021911621, "global_step": 417867, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0929133892059326, "global_step": 417868, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0296785831451416, "global_step": 417869, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0733392238616943, "global_step": 417870, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0167675018310547, "global_step": 417871, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0839743614196777, "global_step": 417872, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.132161855697632, "global_step": 417873, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.090540885925293, "global_step": 417874, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.222377061843872, "global_step": 417875, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0905253887176514, "global_step": 417876, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.035865068435669, "global_step": 417877, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.146160364151001, "global_step": 417878, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.070157289505005, "global_step": 417879, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.046570301055908, "global_step": 417880, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1148624420166016, "global_step": 417881, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0505833625793457, "global_step": 417882, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.110900640487671, "global_step": 417883, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0556812286376953, "global_step": 417884, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0356884002685547, "global_step": 417885, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.096774101257324, "global_step": 417886, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.07307505607605, "global_step": 417887, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9995181560516357, "global_step": 417888, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.096123695373535, "global_step": 417889, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.131009578704834, "global_step": 417890, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.116401433944702, "global_step": 417891, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1173415184020996, "global_step": 417892, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0101547241210938, "global_step": 417893, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.118502140045166, "global_step": 417894, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.052342176437378, "global_step": 417895, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0898265838623047, "global_step": 417896, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0143754482269287, "global_step": 417897, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.106677532196045, "global_step": 417898, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9878900051116943, "global_step": 417899, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0670225620269775, "global_step": 417900, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1183226108551025, "global_step": 417901, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1094460487365723, "global_step": 417902, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0237181186676025, "global_step": 417903, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1065540313720703, "global_step": 417904, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0751547813415527, "global_step": 417905, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.029552459716797, "global_step": 417906, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0528182983398438, "global_step": 417907, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0822179317474365, "global_step": 417908, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1756551265716553, "global_step": 417909, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.114114761352539, "global_step": 417910, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.050173044204712, "global_step": 417911, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.018120050430298, "global_step": 417912, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.196451425552368, "global_step": 417913, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1626832485198975, "global_step": 417914, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.129249095916748, "global_step": 417915, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0897936820983887, "global_step": 417916, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0960705280303955, "global_step": 417917, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.077458381652832, "global_step": 417918, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.085646629333496, "global_step": 417919, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0608365535736084, "global_step": 417920, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9732084274291992, "global_step": 417921, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0841941833496094, "global_step": 417922, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.048957347869873, "global_step": 417923, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.151601791381836, "global_step": 417924, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.07130765914917, "global_step": 417925, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.094679594039917, "global_step": 417926, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1218464374542236, "global_step": 417927, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0611109733581543, "global_step": 417928, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0666072368621826, "global_step": 417929, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.030242443084717, "global_step": 417930, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.002527952194214, "global_step": 417931, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.059814691543579, "global_step": 417932, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1289126873016357, "global_step": 417933, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9988969564437866, "global_step": 417934, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1419014930725098, "global_step": 417935, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.058748960494995, "global_step": 417936, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.025027275085449, "global_step": 417937, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0678417682647705, "global_step": 417938, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.156458854675293, "global_step": 417939, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.020345449447632, "global_step": 417940, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1415884494781494, "global_step": 417941, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.2090539932250977, "global_step": 417942, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1393189430236816, "global_step": 417943, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0802502632141113, "global_step": 417944, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1314499378204346, "global_step": 417945, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.09333872795105, "global_step": 417946, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1474955081939697, "global_step": 417947, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0966877937316895, "global_step": 417948, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.135301113128662, "global_step": 417949, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.063819646835327, "global_step": 417950, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0377867221832275, "global_step": 417951, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.023049831390381, "global_step": 417952, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0408883094787598, "global_step": 417953, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0702714920043945, "global_step": 417954, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.139765501022339, "global_step": 417955, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1497418880462646, "global_step": 417956, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0804216861724854, "global_step": 417957, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.056072950363159, "global_step": 417958, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0652377605438232, "global_step": 417959, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0426156520843506, "global_step": 417960, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0673961639404297, "global_step": 417961, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.098433256149292, "global_step": 417962, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0874764919281006, "global_step": 417963, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0921168327331543, "global_step": 417964, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1407241821289062, "global_step": 417965, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.04776930809021, "global_step": 417966, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1435487270355225, "global_step": 417967, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1466026306152344, "global_step": 417968, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.030017852783203, "global_step": 417969, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0747456550598145, "global_step": 417970, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.01642107963562, "global_step": 417971, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0948092937469482, "global_step": 417972, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.01509428024292, "global_step": 417973, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.109121799468994, "global_step": 417974, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.06786847114563, "global_step": 417975, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1525142192840576, "global_step": 417976, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.072646379470825, "global_step": 417977, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.146521806716919, "global_step": 417978, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.081406593322754, "global_step": 417979, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0497002601623535, "global_step": 417980, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1233015060424805, "global_step": 417981, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.098003387451172, "global_step": 417982, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1102609634399414, "global_step": 417983, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1337876319885254, "global_step": 417984, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0727603435516357, "global_step": 417985, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0214149951934814, "global_step": 417986, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1732852458953857, "global_step": 417987, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0891926288604736, "global_step": 417988, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1178910732269287, "global_step": 417989, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.100478410720825, "global_step": 417990, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0711679458618164, "global_step": 417991, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1321182250976562, "global_step": 417992, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0852065086364746, "global_step": 417993, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0417628288269043, "global_step": 417994, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.078108549118042, "global_step": 417995, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1211893558502197, "global_step": 417996, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.089108943939209, "global_step": 417997, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.979645013809204, "global_step": 417998, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.10959529876709, "global_step": 417999, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.087311029434204, "global_step": 418000, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9728063344955444, "global_step": 418001, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0781688690185547, "global_step": 418002, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0763330459594727, "global_step": 418003, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.072049617767334, "global_step": 418004, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.123007297515869, "global_step": 418005, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.065762519836426, "global_step": 418006, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0484156608581543, "global_step": 418007, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0072202682495117, "global_step": 418008, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.043445587158203, "global_step": 418009, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.101381301879883, "global_step": 418010, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.169783353805542, "global_step": 418011, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1551411151885986, "global_step": 418012, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.063326835632324, "global_step": 418013, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0479023456573486, "global_step": 418014, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.140577554702759, "global_step": 418015, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0501906871795654, "global_step": 418016, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1551575660705566, "global_step": 418017, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.032477378845215, "global_step": 418018, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.197974920272827, "global_step": 418019, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.130796432495117, "global_step": 418020, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.21696138381958, "global_step": 418021, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.002753973007202, "global_step": 418022, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.098116636276245, "global_step": 418023, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.110866069793701, "global_step": 418024, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0607876777648926, "global_step": 418025, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.113016366958618, "global_step": 418026, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.149716377258301, "global_step": 418027, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1761209964752197, "global_step": 418028, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1510486602783203, "global_step": 418029, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0576915740966797, "global_step": 418030, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1348047256469727, "global_step": 418031, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.10654878616333, "global_step": 418032, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1118967533111572, "global_step": 418033, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.052316427230835, "global_step": 418034, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1484432220458984, "global_step": 418035, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0138704776763916, "global_step": 418036, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.18121600151062, "global_step": 418037, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0886287689208984, "global_step": 418038, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1188621520996094, "global_step": 418039, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0706186294555664, "global_step": 418040, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0920095443725586, "global_step": 418041, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0063512325286865, "global_step": 418042, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.086599111557007, "global_step": 418043, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0405988693237305, "global_step": 418044, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0500550270080566, "global_step": 418045, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0784788131713867, "global_step": 418046, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.009254217147827, "global_step": 418047, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0656960010528564, "global_step": 418048, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.064392328262329, "global_step": 418049, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1523184776306152, "global_step": 418050, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9887605905532837, "global_step": 418051, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.055227041244507, "global_step": 418052, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0279927253723145, "global_step": 418053, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0647764205932617, "global_step": 418054, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.110739231109619, "global_step": 418055, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.074218511581421, "global_step": 418056, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0908796787261963, "global_step": 418057, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0715370178222656, "global_step": 418058, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.076080083847046, "global_step": 418059, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0173985958099365, "global_step": 418060, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1199958324432373, "global_step": 418061, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0835561752319336, "global_step": 418062, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1198477745056152, "global_step": 418063, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0678586959838867, "global_step": 418064, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0253918170928955, "global_step": 418065, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.018831968307495, "global_step": 418066, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1056089401245117, "global_step": 418067, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0769777297973633, "global_step": 418068, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0734002590179443, "global_step": 418069, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0923428535461426, "global_step": 418070, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1589443683624268, "global_step": 418071, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1149113178253174, "global_step": 418072, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.078010320663452, "global_step": 418073, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1784586906433105, "global_step": 418074, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.056796073913574, "global_step": 418075, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1093225479125977, "global_step": 418076, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0940775871276855, "global_step": 418077, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.001950740814209, "global_step": 418078, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1603856086730957, "global_step": 418079, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0070173740386963, "global_step": 418080, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1050164699554443, "global_step": 418081, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0529139041900635, "global_step": 418082, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9739576578140259, "global_step": 418083, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.143878936767578, "global_step": 418084, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1243209838867188, "global_step": 418085, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0894618034362793, "global_step": 418086, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1249542236328125, "global_step": 418087, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0790207386016846, "global_step": 418088, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.041073799133301, "global_step": 418089, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0704872608184814, "global_step": 418090, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.075899124145508, "global_step": 418091, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0626795291900635, "global_step": 418092, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0116045475006104, "global_step": 418093, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.180173635482788, "global_step": 418094, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0682737827301025, "global_step": 418095, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1088855266571045, "global_step": 418096, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0962536334991455, "global_step": 418097, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.147679328918457, "global_step": 418098, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.069098711013794, "global_step": 418099, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1044352054595947, "global_step": 418100, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0757155418395996, "global_step": 418101, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.085914134979248, "global_step": 418102, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0471696853637695, "global_step": 418103, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1404504776000977, "global_step": 418104, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0910353660583496, "global_step": 418105, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0781002044677734, "global_step": 418106, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.119847297668457, "global_step": 418107, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.079030752182007, "global_step": 418108, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.130204677581787, "global_step": 418109, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1908414363861084, "global_step": 418110, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1873278617858887, "global_step": 418111, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.029414653778076, "global_step": 418112, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.108027458190918, "global_step": 418113, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0675244331359863, "global_step": 418114, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.117751121520996, "global_step": 418115, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0306854248046875, "global_step": 418116, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0937485694885254, "global_step": 418117, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.14243745803833, "global_step": 418118, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1360933780670166, "global_step": 418119, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0791001319885254, "global_step": 418120, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.057548999786377, "global_step": 418121, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.079627513885498, "global_step": 418122, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.012967109680176, "global_step": 418123, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1045260429382324, "global_step": 418124, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1316025257110596, "global_step": 418125, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.070570468902588, "global_step": 418126, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.007847785949707, "global_step": 418127, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1525542736053467, "global_step": 418128, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9981884956359863, "global_step": 418129, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1554837226867676, "global_step": 418130, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0508058071136475, "global_step": 418131, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.128026008605957, "global_step": 418132, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1623024940490723, "global_step": 418133, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.092829465866089, "global_step": 418134, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.058239459991455, "global_step": 418135, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.179574728012085, "global_step": 418136, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1242876052856445, "global_step": 418137, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1332521438598633, "global_step": 418138, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.03507661819458, "global_step": 418139, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.107224941253662, "global_step": 418140, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1216812133789062, "global_step": 418141, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.070944309234619, "global_step": 418142, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0314409732818604, "global_step": 418143, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.117732524871826, "global_step": 418144, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1068668365478516, "global_step": 418145, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.124101400375366, "global_step": 418146, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.145204782485962, "global_step": 418147, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.170888900756836, "global_step": 418148, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.041414260864258, "global_step": 418149, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.112929344177246, "global_step": 418150, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.057847499847412, "global_step": 418151, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.076012372970581, "global_step": 418152, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1399478912353516, "global_step": 418153, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.2006216049194336, "global_step": 418154, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.077216863632202, "global_step": 418155, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0170254707336426, "global_step": 418156, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0220727920532227, "global_step": 418157, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1849727630615234, "global_step": 418158, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0824506282806396, "global_step": 418159, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.022042989730835, "global_step": 418160, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0880661010742188, "global_step": 418161, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1014182567596436, "global_step": 418162, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0943307876586914, "global_step": 418163, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.98264479637146, "global_step": 418164, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0828518867492676, "global_step": 418165, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0678837299346924, "global_step": 418166, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.173097610473633, "global_step": 418167, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.059337854385376, "global_step": 418168, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.099860429763794, "global_step": 418169, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.082993984222412, "global_step": 418170, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0405850410461426, "global_step": 418171, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0230231285095215, "global_step": 418172, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.080643892288208, "global_step": 418173, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0586321353912354, "global_step": 418174, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.09854793548584, "global_step": 418175, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.068063259124756, "global_step": 418176, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1105129718780518, "global_step": 418177, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.066371440887451, "global_step": 418178, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0935091972351074, "global_step": 418179, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9811583757400513, "global_step": 418180, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.057685375213623, "global_step": 418181, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0780625343322754, "global_step": 418182, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0416929721832275, "global_step": 418183, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0263020992279053, "global_step": 418184, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1138720512390137, "global_step": 418185, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1018764972686768, "global_step": 418186, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1088991165161133, "global_step": 418187, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.068371057510376, "global_step": 418188, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1422383785247803, "global_step": 418189, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.111534833908081, "global_step": 418190, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1287682056427, "global_step": 418191, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1141583919525146, "global_step": 418192, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1132421493530273, "global_step": 418193, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.107879877090454, "global_step": 418194, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0899014472961426, "global_step": 418195, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1635897159576416, "global_step": 418196, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.064329147338867, "global_step": 418197, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.009378671646118, "global_step": 418198, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0899462699890137, "global_step": 418199, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0662243366241455, "global_step": 418200, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1225507259368896, "global_step": 418201, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.131277084350586, "global_step": 418202, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0951316356658936, "global_step": 418203, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1302413940429688, "global_step": 418204, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0135862827301025, "global_step": 418205, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1464433670043945, "global_step": 418206, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1076369285583496, "global_step": 418207, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1189181804656982, "global_step": 418208, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.014147996902466, "global_step": 418209, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0826046466827393, "global_step": 418210, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0913569927215576, "global_step": 418211, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.048448324203491, "global_step": 418212, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1079585552215576, "global_step": 418213, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.143953800201416, "global_step": 418214, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1666672229766846, "global_step": 418215, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.081939220428467, "global_step": 418216, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0669543743133545, "global_step": 418217, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1639504432678223, "global_step": 418218, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0792124271392822, "global_step": 418219, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.062263011932373, "global_step": 418220, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0322916507720947, "global_step": 418221, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0155587196350098, "global_step": 418222, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.037745475769043, "global_step": 418223, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.10321044921875, "global_step": 418224, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1225991249084473, "global_step": 418225, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9813796281814575, "global_step": 418226, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0439114570617676, "global_step": 418227, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0784213542938232, "global_step": 418228, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.099388599395752, "global_step": 418229, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.053281545639038, "global_step": 418230, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1307055950164795, "global_step": 418231, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1099703311920166, "global_step": 418232, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1439757347106934, "global_step": 418233, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.038553237915039, "global_step": 418234, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.141338348388672, "global_step": 418235, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.095616340637207, "global_step": 418236, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0951836109161377, "global_step": 418237, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.143113851547241, "global_step": 418238, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1243040561676025, "global_step": 418239, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0372023582458496, "global_step": 418240, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0501813888549805, "global_step": 418241, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.129556655883789, "global_step": 418242, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.085008382797241, "global_step": 418243, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0911827087402344, "global_step": 418244, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.089850664138794, "global_step": 418245, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1483423709869385, "global_step": 418246, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0730202198028564, "global_step": 418247, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0654423236846924, "global_step": 418248, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0530154705047607, "global_step": 418249, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.087111711502075, "global_step": 418250, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.046736001968384, "global_step": 418251, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0802321434020996, "global_step": 418252, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.105424404144287, "global_step": 418253, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.011019468307495, "global_step": 418254, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.166677236557007, "global_step": 418255, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.153671979904175, "global_step": 418256, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.114636182785034, "global_step": 418257, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1060612201690674, "global_step": 418258, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.159749746322632, "global_step": 418259, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0248193740844727, "global_step": 418260, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0610098838806152, "global_step": 418261, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.137493371963501, "global_step": 418262, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1025171279907227, "global_step": 418263, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1709866523742676, "global_step": 418264, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.147674322128296, "global_step": 418265, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.118924140930176, "global_step": 418266, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.05914568901062, "global_step": 418267, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0573439598083496, "global_step": 418268, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.164057970046997, "global_step": 418269, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.077162742614746, "global_step": 418270, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.188974618911743, "global_step": 418271, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.993483066558838, "global_step": 418272, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1241848468780518, "global_step": 418273, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1086230278015137, "global_step": 418274, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.007413148880005, "global_step": 418275, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.151156425476074, "global_step": 418276, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0467922687530518, "global_step": 418277, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0390095710754395, "global_step": 418278, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0787508487701416, "global_step": 418279, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1242549419403076, "global_step": 418280, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1546554565429688, "global_step": 418281, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.067094564437866, "global_step": 418282, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9949926137924194, "global_step": 418283, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.110790491104126, "global_step": 418284, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0578997135162354, "global_step": 418285, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.112133264541626, "global_step": 418286, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1374216079711914, "global_step": 418287, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.022383689880371, "global_step": 418288, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.076180934906006, "global_step": 418289, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0973052978515625, "global_step": 418290, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1261825561523438, "global_step": 418291, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.005781650543213, "global_step": 418292, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.122548818588257, "global_step": 418293, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1060712337493896, "global_step": 418294, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.057605743408203, "global_step": 418295, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.109422206878662, "global_step": 418296, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.130095958709717, "global_step": 418297, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.206090211868286, "global_step": 418298, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.199589252471924, "global_step": 418299, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1455562114715576, "global_step": 418300, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0939836502075195, "global_step": 418301, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0484626293182373, "global_step": 418302, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.141115665435791, "global_step": 418303, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.015575408935547, "global_step": 418304, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.044581174850464, "global_step": 418305, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0756754875183105, "global_step": 418306, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1438443660736084, "global_step": 418307, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1254873275756836, "global_step": 418308, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.110299825668335, "global_step": 418309, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.011593818664551, "global_step": 418310, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.104628801345825, "global_step": 418311, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.047673463821411, "global_step": 418312, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1782214641571045, "global_step": 418313, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.115126609802246, "global_step": 418314, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.147966146469116, "global_step": 418315, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1016905307769775, "global_step": 418316, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0777909755706787, "global_step": 418317, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1137170791625977, "global_step": 418318, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.120683193206787, "global_step": 418319, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.099125862121582, "global_step": 418320, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.058912754058838, "global_step": 418321, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.160369396209717, "global_step": 418322, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1090543270111084, "global_step": 418323, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1368658542633057, "global_step": 418324, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0480899810791016, "global_step": 418325, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0911009311676025, "global_step": 418326, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0977671146392822, "global_step": 418327, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.057309865951538, "global_step": 418328, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0129988193511963, "global_step": 418329, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0692222118377686, "global_step": 418330, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0889434814453125, "global_step": 418331, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0462026596069336, "global_step": 418332, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.07889461517334, "global_step": 418333, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0824577808380127, "global_step": 418334, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1020147800445557, "global_step": 418335, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.12614107131958, "global_step": 418336, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0987963676452637, "global_step": 418337, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.123544692993164, "global_step": 418338, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.995248556137085, "global_step": 418339, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0401511192321777, "global_step": 418340, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.016019582748413, "global_step": 418341, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.078336477279663, "global_step": 418342, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.055433988571167, "global_step": 418343, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0219268798828125, "global_step": 418344, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0893709659576416, "global_step": 418345, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.043567180633545, "global_step": 418346, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.031630754470825, "global_step": 418347, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.103041648864746, "global_step": 418348, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1522791385650635, "global_step": 418349, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0705316066741943, "global_step": 418350, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0965633392333984, "global_step": 418351, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.013449192047119, "global_step": 418352, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.035113573074341, "global_step": 418353, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.038930654525757, "global_step": 418354, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.090541124343872, "global_step": 418355, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0187435150146484, "global_step": 418356, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1011593341827393, "global_step": 418357, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.086435317993164, "global_step": 418358, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.259840965270996, "global_step": 418359, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.028122901916504, "global_step": 418360, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.088111400604248, "global_step": 418361, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.150644302368164, "global_step": 418362, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.053858995437622, "global_step": 418363, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0934367179870605, "global_step": 418364, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.046048879623413, "global_step": 418365, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0534307956695557, "global_step": 418366, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0784096717834473, "global_step": 418367, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1151044368743896, "global_step": 418368, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.145258903503418, "global_step": 418369, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.088818073272705, "global_step": 418370, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0813217163085938, "global_step": 418371, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.969875454902649, "global_step": 418372, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0190963745117188, "global_step": 418373, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1055760383605957, "global_step": 418374, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1025893688201904, "global_step": 418375, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1428799629211426, "global_step": 418376, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0498828887939453, "global_step": 418377, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.032654047012329, "global_step": 418378, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0837388038635254, "global_step": 418379, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1268770694732666, "global_step": 418380, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1246511936187744, "global_step": 418381, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.142700672149658, "global_step": 418382, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1561694145202637, "global_step": 418383, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0723814964294434, "global_step": 418384, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.079998016357422, "global_step": 418385, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.153535842895508, "global_step": 418386, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0813822746276855, "global_step": 418387, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0595409870147705, "global_step": 418388, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0238077640533447, "global_step": 418389, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.101094961166382, "global_step": 418390, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.088491201400757, "global_step": 418391, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0960049629211426, "global_step": 418392, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0691356658935547, "global_step": 418393, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.108196973800659, "global_step": 418394, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0405073165893555, "global_step": 418395, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0861282348632812, "global_step": 418396, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0901479721069336, "global_step": 418397, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0708131790161133, "global_step": 418398, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1227920055389404, "global_step": 418399, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9828896522521973, "global_step": 418400, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0564777851104736, "global_step": 418401, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0182602405548096, "global_step": 418402, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.087702751159668, "global_step": 418403, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.019310474395752, "global_step": 418404, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.09897780418396, "global_step": 418405, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1633245944976807, "global_step": 418406, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0481154918670654, "global_step": 418407, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0852417945861816, "global_step": 418408, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0853538513183594, "global_step": 418409, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0296835899353027, "global_step": 418410, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1872997283935547, "global_step": 418411, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.134012460708618, "global_step": 418412, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9956928491592407, "global_step": 418413, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.126242160797119, "global_step": 418414, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.041808605194092, "global_step": 418415, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.113226890563965, "global_step": 418416, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1277682781219482, "global_step": 418417, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0757975578308105, "global_step": 418418, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0640342235565186, "global_step": 418419, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9739623069763184, "global_step": 418420, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.07646107673645, "global_step": 418421, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0942440032958984, "global_step": 418422, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0825579166412354, "global_step": 418423, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1044111251831055, "global_step": 418424, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.088750123977661, "global_step": 418425, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1150712966918945, "global_step": 418426, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0955522060394287, "global_step": 418427, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1567184925079346, "global_step": 418428, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.113804578781128, "global_step": 418429, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.150592565536499, "global_step": 418430, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1449599266052246, "global_step": 418431, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1240837574005127, "global_step": 418432, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.034043312072754, "global_step": 418433, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0648884773254395, "global_step": 418434, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.077324151992798, "global_step": 418435, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.01213002204895, "global_step": 418436, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0608909130096436, "global_step": 418437, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.18648624420166, "global_step": 418438, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0616095066070557, "global_step": 418439, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1155004501342773, "global_step": 418440, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1478776931762695, "global_step": 418441, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0984020233154297, "global_step": 418442, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0977964401245117, "global_step": 418443, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0355722904205322, "global_step": 418444, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0131306648254395, "global_step": 418445, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0451972484588623, "global_step": 418446, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1492300033569336, "global_step": 418447, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1646339893341064, "global_step": 418448, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.141507863998413, "global_step": 418449, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0629806518554688, "global_step": 418450, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1544926166534424, "global_step": 418451, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.060868501663208, "global_step": 418452, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1386733055114746, "global_step": 418453, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.20573353767395, "global_step": 418454, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.120082139968872, "global_step": 418455, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0825185775756836, "global_step": 418456, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1371371746063232, "global_step": 418457, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1418638229370117, "global_step": 418458, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1137242317199707, "global_step": 418459, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.117063522338867, "global_step": 418460, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.179070472717285, "global_step": 418461, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.061568021774292, "global_step": 418462, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.096876382827759, "global_step": 418463, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.110668182373047, "global_step": 418464, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0624611377716064, "global_step": 418465, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.072808027267456, "global_step": 418466, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0505192279815674, "global_step": 418467, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1033735275268555, "global_step": 418468, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0577170848846436, "global_step": 418469, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.159745693206787, "global_step": 418470, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1332318782806396, "global_step": 418471, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1028730869293213, "global_step": 418472, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.120426893234253, "global_step": 418473, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.09049129486084, "global_step": 418474, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1880829334259033, "global_step": 418475, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.113140344619751, "global_step": 418476, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0133862495422363, "global_step": 418477, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0357444286346436, "global_step": 418478, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0753731727600098, "global_step": 418479, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0806925296783447, "global_step": 418480, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.003429651260376, "global_step": 418481, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1033339500427246, "global_step": 418482, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1669278144836426, "global_step": 418483, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.051787853240967, "global_step": 418484, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.031407356262207, "global_step": 418485, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0678014755249023, "global_step": 418486, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.105886936187744, "global_step": 418487, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.058864116668701, "global_step": 418488, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0928444862365723, "global_step": 418489, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.038855791091919, "global_step": 418490, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.046753406524658, "global_step": 418491, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0598433017730713, "global_step": 418492, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.133254289627075, "global_step": 418493, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.095771074295044, "global_step": 418494, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.080620288848877, "global_step": 418495, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0846304893493652, "global_step": 418496, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.029344081878662, "global_step": 418497, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.056837797164917, "global_step": 418498, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0684845447540283, "global_step": 418499, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.085200786590576, "global_step": 418500, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0736920833587646, "global_step": 418501, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1897408962249756, "global_step": 418502, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.105631113052368, "global_step": 418503, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0472171306610107, "global_step": 418504, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.173379421234131, "global_step": 418505, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0160269737243652, "global_step": 418506, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.061875104904175, "global_step": 418507, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.127842426300049, "global_step": 418508, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.029905080795288, "global_step": 418509, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1984243392944336, "global_step": 418510, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1157889366149902, "global_step": 418511, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.147188186645508, "global_step": 418512, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.058690071105957, "global_step": 418513, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1437320709228516, "global_step": 418514, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.017465114593506, "global_step": 418515, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.113753318786621, "global_step": 418516, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1184771060943604, "global_step": 418517, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1249375343322754, "global_step": 418518, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.068549633026123, "global_step": 418519, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.066244125366211, "global_step": 418520, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0162127017974854, "global_step": 418521, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.03642201423645, "global_step": 418522, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1132261753082275, "global_step": 418523, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0032544136047363, "global_step": 418524, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0607879161834717, "global_step": 418525, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9926586151123047, "global_step": 418526, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1253929138183594, "global_step": 418527, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1122169494628906, "global_step": 418528, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1015429496765137, "global_step": 418529, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.074432849884033, "global_step": 418530, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0999388694763184, "global_step": 418531, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1029112339019775, "global_step": 418532, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1132519245147705, "global_step": 418533, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1140732765197754, "global_step": 418534, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0479915142059326, "global_step": 418535, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.084662437438965, "global_step": 418536, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0694987773895264, "global_step": 418537, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0787787437438965, "global_step": 418538, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.039768695831299, "global_step": 418539, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.194399833679199, "global_step": 418540, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.056640386581421, "global_step": 418541, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.103890895843506, "global_step": 418542, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9768537282943726, "global_step": 418543, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0877535343170166, "global_step": 418544, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0809168815612793, "global_step": 418545, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.104783773422241, "global_step": 418546, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1940035820007324, "global_step": 418547, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1655070781707764, "global_step": 418548, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.11366605758667, "global_step": 418549, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.066561698913574, "global_step": 418550, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.085573673248291, "global_step": 418551, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.072474956512451, "global_step": 418552, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.098820686340332, "global_step": 418553, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.038966417312622, "global_step": 418554, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.10353946685791, "global_step": 418555, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1956300735473633, "global_step": 418556, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0172927379608154, "global_step": 418557, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1638755798339844, "global_step": 418558, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0172064304351807, "global_step": 418559, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0441861152648926, "global_step": 418560, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.020097017288208, "global_step": 418561, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9923079013824463, "global_step": 418562, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.099414825439453, "global_step": 418563, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1121091842651367, "global_step": 418564, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1819911003112793, "global_step": 418565, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1040353775024414, "global_step": 418566, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1222338676452637, "global_step": 418567, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1184089183807373, "global_step": 418568, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.020867347717285, "global_step": 418569, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1009652614593506, "global_step": 418570, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0630550384521484, "global_step": 418571, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.020551919937134, "global_step": 418572, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.097367763519287, "global_step": 418573, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1044039726257324, "global_step": 418574, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1011805534362793, "global_step": 418575, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.032585382461548, "global_step": 418576, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.149566173553467, "global_step": 418577, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0199973583221436, "global_step": 418578, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0034899711608887, "global_step": 418579, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.126708984375, "global_step": 418580, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.077474594116211, "global_step": 418581, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1371254920959473, "global_step": 418582, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.077860116958618, "global_step": 418583, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0114827156066895, "global_step": 418584, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.142145872116089, "global_step": 418585, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.153097152709961, "global_step": 418586, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0882270336151123, "global_step": 418587, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1111032962799072, "global_step": 418588, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1001415252685547, "global_step": 418589, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.031308650970459, "global_step": 418590, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.135585308074951, "global_step": 418591, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1372411251068115, "global_step": 418592, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0517380237579346, "global_step": 418593, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.023726463317871, "global_step": 418594, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.129375696182251, "global_step": 418595, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.102782726287842, "global_step": 418596, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0866622924804688, "global_step": 418597, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.107957363128662, "global_step": 418598, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0006628036499023, "global_step": 418599, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1161415576934814, "global_step": 418600, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.126828670501709, "global_step": 418601, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1296181678771973, "global_step": 418602, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9993475675582886, "global_step": 418603, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0385639667510986, "global_step": 418604, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.053410530090332, "global_step": 418605, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1143882274627686, "global_step": 418606, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.101905584335327, "global_step": 418607, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1460320949554443, "global_step": 418608, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0628433227539062, "global_step": 418609, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.174450397491455, "global_step": 418610, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.191328525543213, "global_step": 418611, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.035959005355835, "global_step": 418612, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1331286430358887, "global_step": 418613, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.11370849609375, "global_step": 418614, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1539831161499023, "global_step": 418615, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.125375270843506, "global_step": 418616, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0312387943267822, "global_step": 418617, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0490896701812744, "global_step": 418618, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.100132703781128, "global_step": 418619, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1334545612335205, "global_step": 418620, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.09311842918396, "global_step": 418621, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.114192247390747, "global_step": 418622, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.167060613632202, "global_step": 418623, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.077570915222168, "global_step": 418624, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1144680976867676, "global_step": 418625, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.086900234222412, "global_step": 418626, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1484627723693848, "global_step": 418627, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1314988136291504, "global_step": 418628, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.967877984046936, "global_step": 418629, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.042994260787964, "global_step": 418630, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.094287633895874, "global_step": 418631, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0844626426696777, "global_step": 418632, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1642422676086426, "global_step": 418633, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.018441915512085, "global_step": 418634, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1358489990234375, "global_step": 418635, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0357911586761475, "global_step": 418636, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.14162540435791, "global_step": 418637, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.09012508392334, "global_step": 418638, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.144120454788208, "global_step": 418639, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.046452760696411, "global_step": 418640, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.108440637588501, "global_step": 418641, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.103797674179077, "global_step": 418642, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.158099412918091, "global_step": 418643, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0878005027770996, "global_step": 418644, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0870137214660645, "global_step": 418645, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.100031614303589, "global_step": 418646, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1603517532348633, "global_step": 418647, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1231086254119873, "global_step": 418648, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.037019968032837, "global_step": 418649, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1216230392456055, "global_step": 418650, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0256474018096924, "global_step": 418651, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1565184593200684, "global_step": 418652, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0414435863494873, "global_step": 418653, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1380505561828613, "global_step": 418654, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0838687419891357, "global_step": 418655, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0878305435180664, "global_step": 418656, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.107816219329834, "global_step": 418657, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1189892292022705, "global_step": 418658, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.077685594558716, "global_step": 418659, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1168205738067627, "global_step": 418660, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9997259378433228, "global_step": 418661, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.104238510131836, "global_step": 418662, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9757198095321655, "global_step": 418663, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1170246601104736, "global_step": 418664, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1304872035980225, "global_step": 418665, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1156961917877197, "global_step": 418666, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.997227668762207, "global_step": 418667, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0783731937408447, "global_step": 418668, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.201523542404175, "global_step": 418669, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0953121185302734, "global_step": 418670, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.10074520111084, "global_step": 418671, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.099508285522461, "global_step": 418672, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.084347724914551, "global_step": 418673, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.142592191696167, "global_step": 418674, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1492533683776855, "global_step": 418675, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.169492244720459, "global_step": 418676, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.096113443374634, "global_step": 418677, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.128577470779419, "global_step": 418678, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.060941696166992, "global_step": 418679, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0804965496063232, "global_step": 418680, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1263506412506104, "global_step": 418681, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.106165647506714, "global_step": 418682, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1939098834991455, "global_step": 418683, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.074136257171631, "global_step": 418684, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0617823600769043, "global_step": 418685, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.16853666305542, "global_step": 418686, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0720903873443604, "global_step": 418687, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0925581455230713, "global_step": 418688, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0977208614349365, "global_step": 418689, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.123886823654175, "global_step": 418690, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.026550531387329, "global_step": 418691, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.057741165161133, "global_step": 418692, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.162487745285034, "global_step": 418693, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0363824367523193, "global_step": 418694, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0373456478118896, "global_step": 418695, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.102647542953491, "global_step": 418696, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.123582601547241, "global_step": 418697, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1034739017486572, "global_step": 418698, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1401095390319824, "global_step": 418699, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1528854370117188, "global_step": 418700, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0828750133514404, "global_step": 418701, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.028470754623413, "global_step": 418702, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.15832781791687, "global_step": 418703, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1284141540527344, "global_step": 418704, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.088160991668701, "global_step": 418705, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9969775676727295, "global_step": 418706, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.101661205291748, "global_step": 418707, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0934176445007324, "global_step": 418708, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0295920372009277, "global_step": 418709, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0518105030059814, "global_step": 418710, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.117021083831787, "global_step": 418711, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0642333030700684, "global_step": 418712, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0943572521209717, "global_step": 418713, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1683030128479004, "global_step": 418714, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.097693681716919, "global_step": 418715, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0722005367279053, "global_step": 418716, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0707473754882812, "global_step": 418717, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9915368556976318, "global_step": 418718, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0901973247528076, "global_step": 418719, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.100398302078247, "global_step": 418720, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0769307613372803, "global_step": 418721, "epoch": 781, "lr": 5e-05}
{"train_loss": 1.9898263216018677, "global_step": 418722, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1195425987243652, "global_step": 418723, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1286509037017822, "global_step": 418724, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.118027925491333, "global_step": 418725, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0822062492370605, "global_step": 418726, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1002068519592285, "global_step": 418727, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.130897283554077, "global_step": 418728, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1619482040405273, "global_step": 418729, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1000940799713135, "global_step": 418730, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0155410766601562, "global_step": 418731, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.1518635749816895, "global_step": 418732, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.097231388092041, "global_step": 418733, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.09539532661438, "global_step": 418734, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0847983360290527, "global_step": 418735, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.068476676940918, "global_step": 418736, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0757088661193848, "global_step": 418737, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.104045867919922, "global_step": 418738, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0729339122772217, "global_step": 418739, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.088743209838867, "global_step": 418740, "epoch": 781, "lr": 5e-05}
{"train_loss": 2.0647244453430176, "global_step": 418741, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9203866720199585, "global_step": 418742, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1861088275909424, "global_step": 418743, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.185822010040283, "global_step": 418744, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.098217487335205, "global_step": 418745, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0730035305023193, "global_step": 418746, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.063262939453125, "global_step": 418747, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1033928394317627, "global_step": 418748, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.115556478500366, "global_step": 418749, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0966005325317383, "global_step": 418750, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.065586805343628, "global_step": 418751, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.059720516204834, "global_step": 418752, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0499985218048096, "global_step": 418753, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0997910499572754, "global_step": 418754, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1721506118774414, "global_step": 418755, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.087003707885742, "global_step": 418756, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1134204864501953, "global_step": 418757, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0798087120056152, "global_step": 418758, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0547373294830322, "global_step": 418759, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.111642360687256, "global_step": 418760, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.073490619659424, "global_step": 418761, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0598015785217285, "global_step": 418762, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0923781394958496, "global_step": 418763, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0927515029907227, "global_step": 418764, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.049525022506714, "global_step": 418765, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.063491106033325, "global_step": 418766, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.050872564315796, "global_step": 418767, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0917105674743652, "global_step": 418768, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.10369873046875, "global_step": 418769, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0224521160125732, "global_step": 418770, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.032843589782715, "global_step": 418771, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.060870885848999, "global_step": 418772, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.117004632949829, "global_step": 418773, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.076512336730957, "global_step": 418774, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.042755603790283, "global_step": 418775, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0672779083251953, "global_step": 418776, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.021469831466675, "global_step": 418777, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.106841802597046, "global_step": 418778, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1003706455230713, "global_step": 418779, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.031125545501709, "global_step": 418780, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1230714321136475, "global_step": 418781, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.046508312225342, "global_step": 418782, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.105048418045044, "global_step": 418783, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0606653690338135, "global_step": 418784, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0777032375335693, "global_step": 418785, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.156421184539795, "global_step": 418786, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.071930408477783, "global_step": 418787, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9783157110214233, "global_step": 418788, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0622212886810303, "global_step": 418789, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1325814723968506, "global_step": 418790, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.019166946411133, "global_step": 418791, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1132142543792725, "global_step": 418792, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.039219856262207, "global_step": 418793, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.088783025741577, "global_step": 418794, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1241347789764404, "global_step": 418795, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.072458267211914, "global_step": 418796, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0098161697387695, "global_step": 418797, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.115415334701538, "global_step": 418798, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0516953468322754, "global_step": 418799, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0662970542907715, "global_step": 418800, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.061943531036377, "global_step": 418801, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0996205806732178, "global_step": 418802, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.081433057785034, "global_step": 418803, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.078673839569092, "global_step": 418804, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.111011028289795, "global_step": 418805, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.04585862159729, "global_step": 418806, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.049809694290161, "global_step": 418807, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0456674098968506, "global_step": 418808, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0720648765563965, "global_step": 418809, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0696160793304443, "global_step": 418810, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.000182628631592, "global_step": 418811, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0835134983062744, "global_step": 418812, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0605857372283936, "global_step": 418813, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1706786155700684, "global_step": 418814, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0822103023529053, "global_step": 418815, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0279080867767334, "global_step": 418816, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9966893196105957, "global_step": 418817, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0239505767822266, "global_step": 418818, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.146681785583496, "global_step": 418819, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1388943195343018, "global_step": 418820, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.004424571990967, "global_step": 418821, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.065725803375244, "global_step": 418822, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.061399221420288, "global_step": 418823, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.083953380584717, "global_step": 418824, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.123563766479492, "global_step": 418825, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.152824878692627, "global_step": 418826, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1148440837860107, "global_step": 418827, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.032921314239502, "global_step": 418828, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.187225580215454, "global_step": 418829, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.135392189025879, "global_step": 418830, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.123685598373413, "global_step": 418831, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0862395763397217, "global_step": 418832, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.014145612716675, "global_step": 418833, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1396191120147705, "global_step": 418834, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0621933937072754, "global_step": 418835, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.014147996902466, "global_step": 418836, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.063708543777466, "global_step": 418837, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.094911575317383, "global_step": 418838, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0651538372039795, "global_step": 418839, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.028271198272705, "global_step": 418840, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.086503505706787, "global_step": 418841, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.120551824569702, "global_step": 418842, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0187954902648926, "global_step": 418843, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0864813327789307, "global_step": 418844, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.000476598739624, "global_step": 418845, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.082932710647583, "global_step": 418846, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.133821487426758, "global_step": 418847, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.107405662536621, "global_step": 418848, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.027165174484253, "global_step": 418849, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0952024459838867, "global_step": 418850, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0503764152526855, "global_step": 418851, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.116079092025757, "global_step": 418852, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.007936716079712, "global_step": 418853, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.041696071624756, "global_step": 418854, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.109112501144409, "global_step": 418855, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.085357189178467, "global_step": 418856, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.058596611022949, "global_step": 418857, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0457942485809326, "global_step": 418858, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0998799800872803, "global_step": 418859, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.124227523803711, "global_step": 418860, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9939218759536743, "global_step": 418861, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.094724178314209, "global_step": 418862, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.149266004562378, "global_step": 418863, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.055999279022217, "global_step": 418864, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1005859375, "global_step": 418865, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0698375701904297, "global_step": 418866, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0576558113098145, "global_step": 418867, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.969589114189148, "global_step": 418868, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.008455276489258, "global_step": 418869, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0831193923950195, "global_step": 418870, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.124300956726074, "global_step": 418871, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.046705722808838, "global_step": 418872, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0442895889282227, "global_step": 418873, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0825910568237305, "global_step": 418874, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.088667631149292, "global_step": 418875, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0523064136505127, "global_step": 418876, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.075394630432129, "global_step": 418877, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9949620962142944, "global_step": 418878, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.071004867553711, "global_step": 418879, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.073033332824707, "global_step": 418880, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.040836811065674, "global_step": 418881, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.109764814376831, "global_step": 418882, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1161646842956543, "global_step": 418883, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.081432342529297, "global_step": 418884, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.063398599624634, "global_step": 418885, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.030674934387207, "global_step": 418886, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.195220470428467, "global_step": 418887, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.159900426864624, "global_step": 418888, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1462061405181885, "global_step": 418889, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.013040065765381, "global_step": 418890, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0871071815490723, "global_step": 418891, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.085300922393799, "global_step": 418892, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1106560230255127, "global_step": 418893, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0856189727783203, "global_step": 418894, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.070736885070801, "global_step": 418895, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.133606195449829, "global_step": 418896, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.134815216064453, "global_step": 418897, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.108886241912842, "global_step": 418898, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0794851779937744, "global_step": 418899, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.085360050201416, "global_step": 418900, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0359997749328613, "global_step": 418901, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.104097604751587, "global_step": 418902, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0437204837799072, "global_step": 418903, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.980814814567566, "global_step": 418904, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0643482208251953, "global_step": 418905, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.02413010597229, "global_step": 418906, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.069044589996338, "global_step": 418907, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0588741302490234, "global_step": 418908, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9808540344238281, "global_step": 418909, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0832629203796387, "global_step": 418910, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.997068166732788, "global_step": 418911, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0851688385009766, "global_step": 418912, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.105109930038452, "global_step": 418913, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0946767330169678, "global_step": 418914, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0628440380096436, "global_step": 418915, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.022336006164551, "global_step": 418916, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1435256004333496, "global_step": 418917, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.087296724319458, "global_step": 418918, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0881707668304443, "global_step": 418919, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.095914125442505, "global_step": 418920, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.092207193374634, "global_step": 418921, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.035635471343994, "global_step": 418922, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1344547271728516, "global_step": 418923, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.149409055709839, "global_step": 418924, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.002147912979126, "global_step": 418925, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0506858825683594, "global_step": 418926, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.054366111755371, "global_step": 418927, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0311238765716553, "global_step": 418928, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0889344215393066, "global_step": 418929, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1187081336975098, "global_step": 418930, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1268134117126465, "global_step": 418931, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0570991039276123, "global_step": 418932, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.015230655670166, "global_step": 418933, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1350786685943604, "global_step": 418934, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.10957932472229, "global_step": 418935, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0529491901397705, "global_step": 418936, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.099050760269165, "global_step": 418937, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0561954975128174, "global_step": 418938, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0390894412994385, "global_step": 418939, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0148568153381348, "global_step": 418940, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.099668264389038, "global_step": 418941, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.038252592086792, "global_step": 418942, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.105494499206543, "global_step": 418943, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0864853858947754, "global_step": 418944, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0842456817626953, "global_step": 418945, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.074586868286133, "global_step": 418946, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0315206050872803, "global_step": 418947, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0701379776000977, "global_step": 418948, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1105451583862305, "global_step": 418949, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.151916265487671, "global_step": 418950, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.109062910079956, "global_step": 418951, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0600433349609375, "global_step": 418952, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0669636726379395, "global_step": 418953, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0793328285217285, "global_step": 418954, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.093174457550049, "global_step": 418955, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0748214721679688, "global_step": 418956, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1585581302642822, "global_step": 418957, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0099732875823975, "global_step": 418958, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.03426456451416, "global_step": 418959, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.038830518722534, "global_step": 418960, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.078198194503784, "global_step": 418961, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1183836460113525, "global_step": 418962, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0503368377685547, "global_step": 418963, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0896854400634766, "global_step": 418964, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0319528579711914, "global_step": 418965, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.119431734085083, "global_step": 418966, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0400800704956055, "global_step": 418967, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.070981025695801, "global_step": 418968, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0667710304260254, "global_step": 418969, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.154730796813965, "global_step": 418970, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1602017879486084, "global_step": 418971, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1171936988830566, "global_step": 418972, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.168485164642334, "global_step": 418973, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9817249774932861, "global_step": 418974, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1372087001800537, "global_step": 418975, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0278375148773193, "global_step": 418976, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1305644512176514, "global_step": 418977, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0631730556488037, "global_step": 418978, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.085794448852539, "global_step": 418979, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0540590286254883, "global_step": 418980, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0592193603515625, "global_step": 418981, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0709192752838135, "global_step": 418982, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.158273696899414, "global_step": 418983, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.075321674346924, "global_step": 418984, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9980026483535767, "global_step": 418985, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0926132202148438, "global_step": 418986, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0847396850585938, "global_step": 418987, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.055727481842041, "global_step": 418988, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0821657180786133, "global_step": 418989, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0778064727783203, "global_step": 418990, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.063974380493164, "global_step": 418991, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1152167320251465, "global_step": 418992, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0938236713409424, "global_step": 418993, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.007683753967285, "global_step": 418994, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0859134197235107, "global_step": 418995, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.062464475631714, "global_step": 418996, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0505263805389404, "global_step": 418997, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1004116535186768, "global_step": 418998, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.995466947555542, "global_step": 418999, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.100008964538574, "global_step": 419000, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0619988441467285, "global_step": 419001, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.100865125656128, "global_step": 419002, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1898727416992188, "global_step": 419003, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1211745738983154, "global_step": 419004, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.115385055541992, "global_step": 419005, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.053807497024536, "global_step": 419006, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1384189128875732, "global_step": 419007, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.102109670639038, "global_step": 419008, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0219812393188477, "global_step": 419009, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.11185359954834, "global_step": 419010, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.093991756439209, "global_step": 419011, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.161497116088867, "global_step": 419012, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.164998769760132, "global_step": 419013, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0853192806243896, "global_step": 419014, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.114769458770752, "global_step": 419015, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0906760692596436, "global_step": 419016, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1446056365966797, "global_step": 419017, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0918610095977783, "global_step": 419018, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.105900526046753, "global_step": 419019, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.089641809463501, "global_step": 419020, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.107299327850342, "global_step": 419021, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1492323875427246, "global_step": 419022, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0758862495422363, "global_step": 419023, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0622315406799316, "global_step": 419024, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.116105079650879, "global_step": 419025, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0468873977661133, "global_step": 419026, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.084470272064209, "global_step": 419027, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1664528846740723, "global_step": 419028, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0952630043029785, "global_step": 419029, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.105895519256592, "global_step": 419030, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.149383068084717, "global_step": 419031, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.087542772293091, "global_step": 419032, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.084327459335327, "global_step": 419033, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0198423862457275, "global_step": 419034, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1600663661956787, "global_step": 419035, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.036689281463623, "global_step": 419036, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.028251886367798, "global_step": 419037, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0855956077575684, "global_step": 419038, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.080557346343994, "global_step": 419039, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.062027931213379, "global_step": 419040, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1048593521118164, "global_step": 419041, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0640320777893066, "global_step": 419042, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1656267642974854, "global_step": 419043, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.026796579360962, "global_step": 419044, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.2079060077667236, "global_step": 419045, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0813052654266357, "global_step": 419046, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0767338275909424, "global_step": 419047, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0378830432891846, "global_step": 419048, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0580363273620605, "global_step": 419049, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1200766563415527, "global_step": 419050, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.07993221282959, "global_step": 419051, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.095376491546631, "global_step": 419052, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0161356925964355, "global_step": 419053, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.18681263923645, "global_step": 419054, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1660983562469482, "global_step": 419055, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1660633087158203, "global_step": 419056, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.007190227508545, "global_step": 419057, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.112908363342285, "global_step": 419058, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.112699270248413, "global_step": 419059, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0767481327056885, "global_step": 419060, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.140798807144165, "global_step": 419061, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1266379356384277, "global_step": 419062, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0778872966766357, "global_step": 419063, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0287985801696777, "global_step": 419064, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.021759510040283, "global_step": 419065, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.095444917678833, "global_step": 419066, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.100804090499878, "global_step": 419067, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1018965244293213, "global_step": 419068, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.12758207321167, "global_step": 419069, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0718414783477783, "global_step": 419070, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1111369132995605, "global_step": 419071, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1512160301208496, "global_step": 419072, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.090737819671631, "global_step": 419073, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1776742935180664, "global_step": 419074, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0773868560791016, "global_step": 419075, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0670483112335205, "global_step": 419076, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.070284843444824, "global_step": 419077, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1712241172790527, "global_step": 419078, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.167328119277954, "global_step": 419079, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.2068305015563965, "global_step": 419080, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0914978981018066, "global_step": 419081, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0811378955841064, "global_step": 419082, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0681166648864746, "global_step": 419083, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1234195232391357, "global_step": 419084, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1440589427948, "global_step": 419085, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.010091543197632, "global_step": 419086, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0874688625335693, "global_step": 419087, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0656988620758057, "global_step": 419088, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0881199836730957, "global_step": 419089, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0771443843841553, "global_step": 419090, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.084282398223877, "global_step": 419091, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0182597637176514, "global_step": 419092, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1210644245147705, "global_step": 419093, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.104339361190796, "global_step": 419094, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.111499071121216, "global_step": 419095, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1260783672332764, "global_step": 419096, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.121835708618164, "global_step": 419097, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.028789758682251, "global_step": 419098, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.146970510482788, "global_step": 419099, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0866692066192627, "global_step": 419100, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9928890466690063, "global_step": 419101, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0761823654174805, "global_step": 419102, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0914838314056396, "global_step": 419103, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0456349849700928, "global_step": 419104, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0313072204589844, "global_step": 419105, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1168928146362305, "global_step": 419106, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1604342460632324, "global_step": 419107, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1595699787139893, "global_step": 419108, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.2176334857940674, "global_step": 419109, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0870635509490967, "global_step": 419110, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1490259170532227, "global_step": 419111, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.104290008544922, "global_step": 419112, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9891477823257446, "global_step": 419113, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.02878737449646, "global_step": 419114, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0976996421813965, "global_step": 419115, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.053293228149414, "global_step": 419116, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1890501976013184, "global_step": 419117, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.063577651977539, "global_step": 419118, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0574100017547607, "global_step": 419119, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.128826856613159, "global_step": 419120, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.00141978263855, "global_step": 419121, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.111453056335449, "global_step": 419122, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.2030258178710938, "global_step": 419123, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.139801263809204, "global_step": 419124, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.077381134033203, "global_step": 419125, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.120328187942505, "global_step": 419126, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0557005405426025, "global_step": 419127, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.123049736022949, "global_step": 419128, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1853153705596924, "global_step": 419129, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.119584321975708, "global_step": 419130, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.063204765319824, "global_step": 419131, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0822882652282715, "global_step": 419132, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0054922103881836, "global_step": 419133, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0334341526031494, "global_step": 419134, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1440556049346924, "global_step": 419135, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.04217267036438, "global_step": 419136, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1469929218292236, "global_step": 419137, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.152028799057007, "global_step": 419138, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0885307788848877, "global_step": 419139, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0942842960357666, "global_step": 419140, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0889811515808105, "global_step": 419141, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1453475952148438, "global_step": 419142, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.2315614223480225, "global_step": 419143, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.008680820465088, "global_step": 419144, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0899252891540527, "global_step": 419145, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.102816104888916, "global_step": 419146, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1010782718658447, "global_step": 419147, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0273354053497314, "global_step": 419148, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0204660892486572, "global_step": 419149, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.163872718811035, "global_step": 419150, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0442020893096924, "global_step": 419151, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0727765560150146, "global_step": 419152, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1349544525146484, "global_step": 419153, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0261390209198, "global_step": 419154, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9939790964126587, "global_step": 419155, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0210354328155518, "global_step": 419156, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0756659507751465, "global_step": 419157, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.205625057220459, "global_step": 419158, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0215845108032227, "global_step": 419159, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0811171531677246, "global_step": 419160, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1276979446411133, "global_step": 419161, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.09309720993042, "global_step": 419162, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9612606763839722, "global_step": 419163, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.143113136291504, "global_step": 419164, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1111559867858887, "global_step": 419165, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9399168491363525, "global_step": 419166, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.164158344268799, "global_step": 419167, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0971462726593018, "global_step": 419168, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1601686477661133, "global_step": 419169, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.118260145187378, "global_step": 419170, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1073358058929443, "global_step": 419171, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0532302856445312, "global_step": 419172, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.081596851348877, "global_step": 419173, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.155130386352539, "global_step": 419174, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.065361261367798, "global_step": 419175, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.03853178024292, "global_step": 419176, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.026522397994995, "global_step": 419177, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.094104766845703, "global_step": 419178, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.102548122406006, "global_step": 419179, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.021803379058838, "global_step": 419180, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0136709213256836, "global_step": 419181, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.070054769515991, "global_step": 419182, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1405274868011475, "global_step": 419183, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.030928134918213, "global_step": 419184, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0279624462127686, "global_step": 419185, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.107758045196533, "global_step": 419186, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.131924629211426, "global_step": 419187, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0687334537506104, "global_step": 419188, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0080158710479736, "global_step": 419189, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.143446207046509, "global_step": 419190, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.238361120223999, "global_step": 419191, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0371603965759277, "global_step": 419192, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1167654991149902, "global_step": 419193, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1225574016571045, "global_step": 419194, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.09429931640625, "global_step": 419195, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.092371702194214, "global_step": 419196, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0295729637145996, "global_step": 419197, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.041167736053467, "global_step": 419198, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0922868251800537, "global_step": 419199, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.11053204536438, "global_step": 419200, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0071468353271484, "global_step": 419201, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.147855520248413, "global_step": 419202, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0278031826019287, "global_step": 419203, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0693109035491943, "global_step": 419204, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1055915355682373, "global_step": 419205, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0801236629486084, "global_step": 419206, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.093579053878784, "global_step": 419207, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0516998767852783, "global_step": 419208, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0604007244110107, "global_step": 419209, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1134371757507324, "global_step": 419210, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1230392456054688, "global_step": 419211, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0504026412963867, "global_step": 419212, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0586514472961426, "global_step": 419213, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.070915699005127, "global_step": 419214, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.096558094024658, "global_step": 419215, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1734938621520996, "global_step": 419216, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1119329929351807, "global_step": 419217, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0738449096679688, "global_step": 419218, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.181574583053589, "global_step": 419219, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1803433895111084, "global_step": 419220, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.18259334564209, "global_step": 419221, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.086014747619629, "global_step": 419222, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.093410015106201, "global_step": 419223, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.051241874694824, "global_step": 419224, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.145015239715576, "global_step": 419225, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.151371479034424, "global_step": 419226, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.040902853012085, "global_step": 419227, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.066549777984619, "global_step": 419228, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.094987392425537, "global_step": 419229, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0964043140411377, "global_step": 419230, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.076646566390991, "global_step": 419231, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9930883646011353, "global_step": 419232, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1292929649353027, "global_step": 419233, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.095632553100586, "global_step": 419234, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1148829460144043, "global_step": 419235, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.165522575378418, "global_step": 419236, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1024131774902344, "global_step": 419237, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.062561273574829, "global_step": 419238, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.2065327167510986, "global_step": 419239, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0945847034454346, "global_step": 419240, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.032674551010132, "global_step": 419241, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0738587379455566, "global_step": 419242, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0517947673797607, "global_step": 419243, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.135495662689209, "global_step": 419244, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.129438877105713, "global_step": 419245, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.147785186767578, "global_step": 419246, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0040204524993896, "global_step": 419247, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0887255668640137, "global_step": 419248, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0026774406433105, "global_step": 419249, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0313031673431396, "global_step": 419250, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.092449426651001, "global_step": 419251, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.041231393814087, "global_step": 419252, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9948854446411133, "global_step": 419253, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.966684341430664, "global_step": 419254, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1104822158813477, "global_step": 419255, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.082139253616333, "global_step": 419256, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.179276704788208, "global_step": 419257, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1242244243621826, "global_step": 419258, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.105412244796753, "global_step": 419259, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1838085651397705, "global_step": 419260, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.158231496810913, "global_step": 419261, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.07916259765625, "global_step": 419262, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1272783279418945, "global_step": 419263, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.233769178390503, "global_step": 419264, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.041471242904663, "global_step": 419265, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0396573543548584, "global_step": 419266, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0813212394714355, "global_step": 419267, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0069613456726074, "global_step": 419268, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0582504272460938, "global_step": 419269, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.128694772720337, "global_step": 419270, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0742223262786865, "global_step": 419271, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.107456684112549, "global_step": 419272, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.03318452835083, "global_step": 419273, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.099560499191284, "global_step": 419274, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0200552940368652, "global_step": 419275, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1900477409362793, "global_step": 419276, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.042433738708496, "global_step": 419277, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0757484436035156, "global_step": 419278, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.17625093460083, "global_step": 419279, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.145965576171875, "global_step": 419280, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.090945243835449, "global_step": 419281, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.092350482940674, "global_step": 419282, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.087629556655884, "global_step": 419283, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1241559982299805, "global_step": 419284, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1843831539154053, "global_step": 419285, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0250332355499268, "global_step": 419286, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1098520755767822, "global_step": 419287, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.037208080291748, "global_step": 419288, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.131971836090088, "global_step": 419289, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1584842205047607, "global_step": 419290, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.049705982208252, "global_step": 419291, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0585200786590576, "global_step": 419292, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.084703207015991, "global_step": 419293, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1022956371307373, "global_step": 419294, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.076077461242676, "global_step": 419295, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0612802505493164, "global_step": 419296, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0878171920776367, "global_step": 419297, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.119427442550659, "global_step": 419298, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0961453914642334, "global_step": 419299, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0615804195404053, "global_step": 419300, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.205578565597534, "global_step": 419301, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0965819358825684, "global_step": 419302, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1467230319976807, "global_step": 419303, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1462109088897705, "global_step": 419304, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.042149543762207, "global_step": 419305, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.090644598007202, "global_step": 419306, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.176217555999756, "global_step": 419307, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0444819927215576, "global_step": 419308, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.130978584289551, "global_step": 419309, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0381245613098145, "global_step": 419310, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0687949657440186, "global_step": 419311, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0760345458984375, "global_step": 419312, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0973684787750244, "global_step": 419313, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.031132936477661, "global_step": 419314, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.194178819656372, "global_step": 419315, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0727720260620117, "global_step": 419316, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.099700927734375, "global_step": 419317, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0638856887817383, "global_step": 419318, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0913705825805664, "global_step": 419319, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1585497856140137, "global_step": 419320, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0833160877227783, "global_step": 419321, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0804078578948975, "global_step": 419322, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0697731971740723, "global_step": 419323, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1937801837921143, "global_step": 419324, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0959010124206543, "global_step": 419325, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.042752981185913, "global_step": 419326, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.101465940475464, "global_step": 419327, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0896878242492676, "global_step": 419328, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0355305671691895, "global_step": 419329, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0065455436706543, "global_step": 419330, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0788638591766357, "global_step": 419331, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.124629259109497, "global_step": 419332, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.093787431716919, "global_step": 419333, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1028244495391846, "global_step": 419334, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0811338424682617, "global_step": 419335, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0757908821105957, "global_step": 419336, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.070162296295166, "global_step": 419337, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.016359567642212, "global_step": 419338, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0774030685424805, "global_step": 419339, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.074742317199707, "global_step": 419340, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.094799518585205, "global_step": 419341, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1147830486297607, "global_step": 419342, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9978902339935303, "global_step": 419343, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.074042320251465, "global_step": 419344, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1087350845336914, "global_step": 419345, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0291435718536377, "global_step": 419346, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.992740273475647, "global_step": 419347, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1232213973999023, "global_step": 419348, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.2266430854797363, "global_step": 419349, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.121509075164795, "global_step": 419350, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.094221353530884, "global_step": 419351, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0788514614105225, "global_step": 419352, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0379838943481445, "global_step": 419353, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0499274730682373, "global_step": 419354, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0515217781066895, "global_step": 419355, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0830605030059814, "global_step": 419356, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.065725326538086, "global_step": 419357, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.170285940170288, "global_step": 419358, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0372631549835205, "global_step": 419359, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0478744506835938, "global_step": 419360, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.061629056930542, "global_step": 419361, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.103616952896118, "global_step": 419362, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.034679889678955, "global_step": 419363, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.097121477127075, "global_step": 419364, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.096632242202759, "global_step": 419365, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0542213916778564, "global_step": 419366, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.120333194732666, "global_step": 419367, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.073171377182007, "global_step": 419368, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0862061977386475, "global_step": 419369, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1423263549804688, "global_step": 419370, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1163320541381836, "global_step": 419371, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0928215980529785, "global_step": 419372, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.011143207550049, "global_step": 419373, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1433517932891846, "global_step": 419374, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1521530151367188, "global_step": 419375, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0809404850006104, "global_step": 419376, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0454001426696777, "global_step": 419377, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1420955657958984, "global_step": 419378, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1213269233703613, "global_step": 419379, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0217063426971436, "global_step": 419380, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1145613193511963, "global_step": 419381, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1041059494018555, "global_step": 419382, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0740222930908203, "global_step": 419383, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0705339908599854, "global_step": 419384, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.111523389816284, "global_step": 419385, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.042412519454956, "global_step": 419386, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.2019970417022705, "global_step": 419387, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0607001781463623, "global_step": 419388, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1424803733825684, "global_step": 419389, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.103971481323242, "global_step": 419390, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0043225288391113, "global_step": 419391, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.049971580505371, "global_step": 419392, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0975375175476074, "global_step": 419393, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0602941513061523, "global_step": 419394, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.073122262954712, "global_step": 419395, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.030653953552246, "global_step": 419396, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.110485792160034, "global_step": 419397, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.134860038757324, "global_step": 419398, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0620763301849365, "global_step": 419399, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1003246307373047, "global_step": 419400, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0514745712280273, "global_step": 419401, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.150346040725708, "global_step": 419402, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0552122592926025, "global_step": 419403, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.085557460784912, "global_step": 419404, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.087435245513916, "global_step": 419405, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.041517734527588, "global_step": 419406, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.094738006591797, "global_step": 419407, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0881941318511963, "global_step": 419408, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1784331798553467, "global_step": 419409, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.118577480316162, "global_step": 419410, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.05983304977417, "global_step": 419411, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.029561758041382, "global_step": 419412, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1324872970581055, "global_step": 419413, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0826122760772705, "global_step": 419414, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.073427677154541, "global_step": 419415, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.079935312271118, "global_step": 419416, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.010672092437744, "global_step": 419417, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.026578664779663, "global_step": 419418, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0932319164276123, "global_step": 419419, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.16035795211792, "global_step": 419420, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0921075344085693, "global_step": 419421, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.08418869972229, "global_step": 419422, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0607972145080566, "global_step": 419423, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0884501934051514, "global_step": 419424, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1107122898101807, "global_step": 419425, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.069652557373047, "global_step": 419426, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.111635446548462, "global_step": 419427, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.035529136657715, "global_step": 419428, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1489150524139404, "global_step": 419429, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.076570987701416, "global_step": 419430, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0324556827545166, "global_step": 419431, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1141998767852783, "global_step": 419432, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.023019313812256, "global_step": 419433, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.047231435775757, "global_step": 419434, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.133324146270752, "global_step": 419435, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.073713541030884, "global_step": 419436, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.057086944580078, "global_step": 419437, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1069202423095703, "global_step": 419438, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0974719524383545, "global_step": 419439, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9869240522384644, "global_step": 419440, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0545454025268555, "global_step": 419441, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.012892246246338, "global_step": 419442, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0487563610076904, "global_step": 419443, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0874342918395996, "global_step": 419444, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.093832492828369, "global_step": 419445, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0196757316589355, "global_step": 419446, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0038723945617676, "global_step": 419447, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.060445547103882, "global_step": 419448, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.047003746032715, "global_step": 419449, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.121708393096924, "global_step": 419450, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.115631580352783, "global_step": 419451, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1575372219085693, "global_step": 419452, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1083524227142334, "global_step": 419453, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0699219703674316, "global_step": 419454, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.009486198425293, "global_step": 419455, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1134519577026367, "global_step": 419456, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0732407569885254, "global_step": 419457, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0251269340515137, "global_step": 419458, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1166234016418457, "global_step": 419459, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1305012702941895, "global_step": 419460, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0570671558380127, "global_step": 419461, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.11688232421875, "global_step": 419462, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0417354106903076, "global_step": 419463, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.065646171569824, "global_step": 419464, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1507723331451416, "global_step": 419465, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0525803565979004, "global_step": 419466, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0784051418304443, "global_step": 419467, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0953376293182373, "global_step": 419468, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0672993659973145, "global_step": 419469, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0597589015960693, "global_step": 419470, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1081066131591797, "global_step": 419471, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.107070207595825, "global_step": 419472, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1363401412963867, "global_step": 419473, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0672876834869385, "global_step": 419474, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.109025716781616, "global_step": 419475, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1040494441986084, "global_step": 419476, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0010287761688232, "global_step": 419477, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.031013250350952, "global_step": 419478, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0983309745788574, "global_step": 419479, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1521685123443604, "global_step": 419480, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.03129506111145, "global_step": 419481, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1608288288116455, "global_step": 419482, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1373820304870605, "global_step": 419483, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.122467279434204, "global_step": 419484, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1290950775146484, "global_step": 419485, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0772347450256348, "global_step": 419486, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0002334117889404, "global_step": 419487, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0882787704467773, "global_step": 419488, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.094729423522949, "global_step": 419489, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.079451560974121, "global_step": 419490, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1445229053497314, "global_step": 419491, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.106403350830078, "global_step": 419492, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.187839984893799, "global_step": 419493, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.000349521636963, "global_step": 419494, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0873353481292725, "global_step": 419495, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0981132984161377, "global_step": 419496, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.127807855606079, "global_step": 419497, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.2038114070892334, "global_step": 419498, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0990097522735596, "global_step": 419499, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.157783031463623, "global_step": 419500, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0848090648651123, "global_step": 419501, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.058990240097046, "global_step": 419502, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.114488363265991, "global_step": 419503, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1099720001220703, "global_step": 419504, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0290684700012207, "global_step": 419505, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1032488346099854, "global_step": 419506, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0669002532958984, "global_step": 419507, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0832581520080566, "global_step": 419508, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0396101474761963, "global_step": 419509, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0552868843078613, "global_step": 419510, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.024911403656006, "global_step": 419511, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.139253854751587, "global_step": 419512, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.010664463043213, "global_step": 419513, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1771445274353027, "global_step": 419514, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0551741123199463, "global_step": 419515, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1050667762756348, "global_step": 419516, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.096560001373291, "global_step": 419517, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0396358966827393, "global_step": 419518, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1478357315063477, "global_step": 419519, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1620395183563232, "global_step": 419520, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1631157398223877, "global_step": 419521, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1125223636627197, "global_step": 419522, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0833120346069336, "global_step": 419523, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0710830688476562, "global_step": 419524, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1503865718841553, "global_step": 419525, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.116851806640625, "global_step": 419526, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1575589179992676, "global_step": 419527, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1374197006225586, "global_step": 419528, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.124624490737915, "global_step": 419529, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1924023628234863, "global_step": 419530, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.127154588699341, "global_step": 419531, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1469674110412598, "global_step": 419532, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1057307720184326, "global_step": 419533, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1586108207702637, "global_step": 419534, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0875558853149414, "global_step": 419535, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0869555473327637, "global_step": 419536, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.102855682373047, "global_step": 419537, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1058542728424072, "global_step": 419538, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.08530592918396, "global_step": 419539, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1441287994384766, "global_step": 419540, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.019066572189331, "global_step": 419541, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.154242753982544, "global_step": 419542, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.02022123336792, "global_step": 419543, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.129822015762329, "global_step": 419544, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.042860269546509, "global_step": 419545, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1127476692199707, "global_step": 419546, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.113039016723633, "global_step": 419547, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0443499088287354, "global_step": 419548, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.159609317779541, "global_step": 419549, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0990779399871826, "global_step": 419550, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.140638828277588, "global_step": 419551, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.074138641357422, "global_step": 419552, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1146445274353027, "global_step": 419553, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.069878101348877, "global_step": 419554, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0798771381378174, "global_step": 419555, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0366151332855225, "global_step": 419556, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.059013605117798, "global_step": 419557, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1693503856658936, "global_step": 419558, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.095738649368286, "global_step": 419559, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1459832191467285, "global_step": 419560, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9999786615371704, "global_step": 419561, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0857248306274414, "global_step": 419562, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.11942458152771, "global_step": 419563, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1045048236846924, "global_step": 419564, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.158087730407715, "global_step": 419565, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.035836696624756, "global_step": 419566, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1582579612731934, "global_step": 419567, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0914342403411865, "global_step": 419568, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1078202724456787, "global_step": 419569, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1086909770965576, "global_step": 419570, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1442646980285645, "global_step": 419571, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.2058780193328857, "global_step": 419572, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.101302146911621, "global_step": 419573, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0231423377990723, "global_step": 419574, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0197901725769043, "global_step": 419575, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1527011394500732, "global_step": 419576, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0392887592315674, "global_step": 419577, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.068312406539917, "global_step": 419578, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0755867958068848, "global_step": 419579, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0906617641448975, "global_step": 419580, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0936644077301025, "global_step": 419581, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.134387493133545, "global_step": 419582, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0243782997131348, "global_step": 419583, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1137948036193848, "global_step": 419584, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0165624618530273, "global_step": 419585, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1257710456848145, "global_step": 419586, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1039016246795654, "global_step": 419587, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.12286376953125, "global_step": 419588, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.091323137283325, "global_step": 419589, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.2102932929992676, "global_step": 419590, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.081428050994873, "global_step": 419591, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.059164524078369, "global_step": 419592, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0580241680145264, "global_step": 419593, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0896403789520264, "global_step": 419594, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1052494049072266, "global_step": 419595, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0525503158569336, "global_step": 419596, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1221039295196533, "global_step": 419597, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0969855785369873, "global_step": 419598, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1447484493255615, "global_step": 419599, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0083396434783936, "global_step": 419600, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0355992317199707, "global_step": 419601, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1426150798797607, "global_step": 419602, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.111388921737671, "global_step": 419603, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0502586364746094, "global_step": 419604, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1356709003448486, "global_step": 419605, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1124422550201416, "global_step": 419606, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0471982955932617, "global_step": 419607, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.067793846130371, "global_step": 419608, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.052722454071045, "global_step": 419609, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.007302761077881, "global_step": 419610, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.082145929336548, "global_step": 419611, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1315903663635254, "global_step": 419612, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0503387451171875, "global_step": 419613, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.14096736907959, "global_step": 419614, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1267058849334717, "global_step": 419615, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1616268157958984, "global_step": 419616, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1022400856018066, "global_step": 419617, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0691306591033936, "global_step": 419618, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.085465908050537, "global_step": 419619, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0660181045532227, "global_step": 419620, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0751657485961914, "global_step": 419621, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.114328622817993, "global_step": 419622, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1360599994659424, "global_step": 419623, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.126004934310913, "global_step": 419624, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1841559410095215, "global_step": 419625, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1312062740325928, "global_step": 419626, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.134110689163208, "global_step": 419627, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.054731845855713, "global_step": 419628, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.111121416091919, "global_step": 419629, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1433403491973877, "global_step": 419630, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.092108964920044, "global_step": 419631, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0343785285949707, "global_step": 419632, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9683969020843506, "global_step": 419633, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1590378284454346, "global_step": 419634, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.018829822540283, "global_step": 419635, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1241860389709473, "global_step": 419636, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0913164615631104, "global_step": 419637, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1493520736694336, "global_step": 419638, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0877785682678223, "global_step": 419639, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1109774112701416, "global_step": 419640, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1288821697235107, "global_step": 419641, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0926387310028076, "global_step": 419642, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.094481945037842, "global_step": 419643, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0786256790161133, "global_step": 419644, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0709455013275146, "global_step": 419645, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0275328159332275, "global_step": 419646, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.148041009902954, "global_step": 419647, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0785253047943115, "global_step": 419648, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1643588542938232, "global_step": 419649, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.174964427947998, "global_step": 419650, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0284910202026367, "global_step": 419651, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.140596628189087, "global_step": 419652, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.118643045425415, "global_step": 419653, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.095121383666992, "global_step": 419654, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1324148178100586, "global_step": 419655, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.107855796813965, "global_step": 419656, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0841829776763916, "global_step": 419657, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.135694742202759, "global_step": 419658, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.100388288497925, "global_step": 419659, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.069150924682617, "global_step": 419660, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0749666690826416, "global_step": 419661, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.038569450378418, "global_step": 419662, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0852766036987305, "global_step": 419663, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1382737159729004, "global_step": 419664, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.168494462966919, "global_step": 419665, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.140157461166382, "global_step": 419666, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.2020020484924316, "global_step": 419667, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.150214672088623, "global_step": 419668, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1140482425689697, "global_step": 419669, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.964298129081726, "global_step": 419670, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.109276056289673, "global_step": 419671, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1297779083251953, "global_step": 419672, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.113743543624878, "global_step": 419673, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1504032611846924, "global_step": 419674, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.13666033744812, "global_step": 419675, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1115517616271973, "global_step": 419676, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1324222087860107, "global_step": 419677, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.069093942642212, "global_step": 419678, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.10736346244812, "global_step": 419679, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.19315767288208, "global_step": 419680, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.053255081176758, "global_step": 419681, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1157279014587402, "global_step": 419682, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1176156997680664, "global_step": 419683, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.200991630554199, "global_step": 419684, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.098174571990967, "global_step": 419685, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.103266716003418, "global_step": 419686, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0529348850250244, "global_step": 419687, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.075746536254883, "global_step": 419688, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.116119623184204, "global_step": 419689, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.085766553878784, "global_step": 419690, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.103665590286255, "global_step": 419691, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1404035091400146, "global_step": 419692, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1876020431518555, "global_step": 419693, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1222116947174072, "global_step": 419694, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0940966606140137, "global_step": 419695, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1595332622528076, "global_step": 419696, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1577818393707275, "global_step": 419697, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0735414028167725, "global_step": 419698, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0830585956573486, "global_step": 419699, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.13405442237854, "global_step": 419700, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0011587142944336, "global_step": 419701, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1067440509796143, "global_step": 419702, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.141185998916626, "global_step": 419703, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9661184549331665, "global_step": 419704, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0961530208587646, "global_step": 419705, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.1156833171844482, "global_step": 419706, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0561294555664062, "global_step": 419707, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.0874526500701904, "global_step": 419708, "epoch": 782, "lr": 5e-05}
{"train_loss": 2.089038848876953, "global_step": 419709, "epoch": 782, "lr": 5e-05}
{"train_loss": 1.9816306829452515, "global_step": 419710, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0995256900787354, "global_step": 419711, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.132115602493286, "global_step": 419712, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0575313568115234, "global_step": 419713, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.039846181869507, "global_step": 419714, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1132211685180664, "global_step": 419715, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1150708198547363, "global_step": 419716, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1247639656066895, "global_step": 419717, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.002795457839966, "global_step": 419718, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.036228656768799, "global_step": 419719, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9868595600128174, "global_step": 419720, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1405458450317383, "global_step": 419721, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0841403007507324, "global_step": 419722, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.032717227935791, "global_step": 419723, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.037783145904541, "global_step": 419724, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1414966583251953, "global_step": 419725, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.114271879196167, "global_step": 419726, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.149472236633301, "global_step": 419727, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1080715656280518, "global_step": 419728, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0853991508483887, "global_step": 419729, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0573692321777344, "global_step": 419730, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.050276756286621, "global_step": 419731, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1384053230285645, "global_step": 419732, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0155415534973145, "global_step": 419733, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.114170789718628, "global_step": 419734, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0916354656219482, "global_step": 419735, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.082266330718994, "global_step": 419736, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0955209732055664, "global_step": 419737, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0465850830078125, "global_step": 419738, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9716856479644775, "global_step": 419739, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.06783390045166, "global_step": 419740, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0955400466918945, "global_step": 419741, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0948731899261475, "global_step": 419742, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0693674087524414, "global_step": 419743, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0829296112060547, "global_step": 419744, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0202527046203613, "global_step": 419745, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0403809547424316, "global_step": 419746, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1256513595581055, "global_step": 419747, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0256898403167725, "global_step": 419748, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0880610942840576, "global_step": 419749, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.069425106048584, "global_step": 419750, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9822361469268799, "global_step": 419751, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1241519451141357, "global_step": 419752, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.194723129272461, "global_step": 419753, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0816283226013184, "global_step": 419754, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1285793781280518, "global_step": 419755, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0917365550994873, "global_step": 419756, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.096703052520752, "global_step": 419757, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1026690006256104, "global_step": 419758, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.086435079574585, "global_step": 419759, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9450514316558838, "global_step": 419760, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.140061616897583, "global_step": 419761, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0840587615966797, "global_step": 419762, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.144059181213379, "global_step": 419763, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.078382968902588, "global_step": 419764, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0950942039489746, "global_step": 419765, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0975754261016846, "global_step": 419766, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0682318210601807, "global_step": 419767, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.108750343322754, "global_step": 419768, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0768625736236572, "global_step": 419769, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1726937294006348, "global_step": 419770, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1282992362976074, "global_step": 419771, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1144752502441406, "global_step": 419772, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1001789569854736, "global_step": 419773, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1836702823638916, "global_step": 419774, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0368492603302, "global_step": 419775, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.074610710144043, "global_step": 419776, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.057270050048828, "global_step": 419777, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.123546600341797, "global_step": 419778, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.093904972076416, "global_step": 419779, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.085538625717163, "global_step": 419780, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0178024768829346, "global_step": 419781, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0380334854125977, "global_step": 419782, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9987150430679321, "global_step": 419783, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0650336742401123, "global_step": 419784, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0250582695007324, "global_step": 419785, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0929031372070312, "global_step": 419786, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1367251873016357, "global_step": 419787, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0589962005615234, "global_step": 419788, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1055736541748047, "global_step": 419789, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1278836727142334, "global_step": 419790, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0726072788238525, "global_step": 419791, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.034740924835205, "global_step": 419792, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0433592796325684, "global_step": 419793, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1127798557281494, "global_step": 419794, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.042534589767456, "global_step": 419795, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0724594593048096, "global_step": 419796, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1139028072357178, "global_step": 419797, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0397112369537354, "global_step": 419798, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1010570526123047, "global_step": 419799, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1248817443847656, "global_step": 419800, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.096682548522949, "global_step": 419801, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0773205757141113, "global_step": 419802, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1226630210876465, "global_step": 419803, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.130840301513672, "global_step": 419804, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1064810752868652, "global_step": 419805, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.085850477218628, "global_step": 419806, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1900155544281006, "global_step": 419807, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1159441471099854, "global_step": 419808, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.007368564605713, "global_step": 419809, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.068354845046997, "global_step": 419810, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0585479736328125, "global_step": 419811, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.113703966140747, "global_step": 419812, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0491385459899902, "global_step": 419813, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.111072301864624, "global_step": 419814, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0834665298461914, "global_step": 419815, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0652151107788086, "global_step": 419816, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.101803779602051, "global_step": 419817, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0147929191589355, "global_step": 419818, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0702097415924072, "global_step": 419819, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0519859790802, "global_step": 419820, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.107206106185913, "global_step": 419821, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0391769409179688, "global_step": 419822, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.050234317779541, "global_step": 419823, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.064145803451538, "global_step": 419824, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.113426446914673, "global_step": 419825, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0050716400146484, "global_step": 419826, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0895256996154785, "global_step": 419827, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9636214971542358, "global_step": 419828, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9933661222457886, "global_step": 419829, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.104579210281372, "global_step": 419830, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.072561740875244, "global_step": 419831, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.045118808746338, "global_step": 419832, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1367125511169434, "global_step": 419833, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0776803493499756, "global_step": 419834, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.091744899749756, "global_step": 419835, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0470564365386963, "global_step": 419836, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.051473617553711, "global_step": 419837, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.021693468093872, "global_step": 419838, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0807363986968994, "global_step": 419839, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.051118850708008, "global_step": 419840, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0341014862060547, "global_step": 419841, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.088552951812744, "global_step": 419842, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.011759042739868, "global_step": 419843, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0873947143554688, "global_step": 419844, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0460798740386963, "global_step": 419845, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.089221239089966, "global_step": 419846, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.069727659225464, "global_step": 419847, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.09466814994812, "global_step": 419848, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0907180309295654, "global_step": 419849, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.074843168258667, "global_step": 419850, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1177783012390137, "global_step": 419851, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.014418125152588, "global_step": 419852, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9976435899734497, "global_step": 419853, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.064178228378296, "global_step": 419854, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1292364597320557, "global_step": 419855, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.099818706512451, "global_step": 419856, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0458688735961914, "global_step": 419857, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9875009059906006, "global_step": 419858, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0853590965270996, "global_step": 419859, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.025702714920044, "global_step": 419860, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.073868989944458, "global_step": 419861, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0732340812683105, "global_step": 419862, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1464648246765137, "global_step": 419863, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.131652355194092, "global_step": 419864, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.035508394241333, "global_step": 419865, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.038355588912964, "global_step": 419866, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.169320821762085, "global_step": 419867, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0149428844451904, "global_step": 419868, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.131431818008423, "global_step": 419869, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.142880439758301, "global_step": 419870, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.060030221939087, "global_step": 419871, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0213124752044678, "global_step": 419872, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.051361560821533, "global_step": 419873, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0410971641540527, "global_step": 419874, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.122692346572876, "global_step": 419875, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.080871820449829, "global_step": 419876, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1410646438598633, "global_step": 419877, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0675981044769287, "global_step": 419878, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0496201515197754, "global_step": 419879, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.087279796600342, "global_step": 419880, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0776684284210205, "global_step": 419881, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.08537220954895, "global_step": 419882, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0453338623046875, "global_step": 419883, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.016439199447632, "global_step": 419884, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0725889205932617, "global_step": 419885, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.026535749435425, "global_step": 419886, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.119246006011963, "global_step": 419887, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.067958354949951, "global_step": 419888, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.128014087677002, "global_step": 419889, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1177141666412354, "global_step": 419890, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1116325855255127, "global_step": 419891, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0918564796447754, "global_step": 419892, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1113836765289307, "global_step": 419893, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0737297534942627, "global_step": 419894, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.10215163230896, "global_step": 419895, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0765535831451416, "global_step": 419896, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0969462394714355, "global_step": 419897, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.221235990524292, "global_step": 419898, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1532645225524902, "global_step": 419899, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1558306217193604, "global_step": 419900, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.067873954772949, "global_step": 419901, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.06902813911438, "global_step": 419902, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.121460437774658, "global_step": 419903, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1783316135406494, "global_step": 419904, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.078643321990967, "global_step": 419905, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.100564956665039, "global_step": 419906, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0361084938049316, "global_step": 419907, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.095364809036255, "global_step": 419908, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9546928405761719, "global_step": 419909, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.093268871307373, "global_step": 419910, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0289392471313477, "global_step": 419911, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.034787654876709, "global_step": 419912, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0933847427368164, "global_step": 419913, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0849313735961914, "global_step": 419914, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0130603313446045, "global_step": 419915, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.141089677810669, "global_step": 419916, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.054107189178467, "global_step": 419917, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.126763343811035, "global_step": 419918, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1141703128814697, "global_step": 419919, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1444485187530518, "global_step": 419920, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.960296869277954, "global_step": 419921, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.049403429031372, "global_step": 419922, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1419050693511963, "global_step": 419923, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.059889793395996, "global_step": 419924, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.088550329208374, "global_step": 419925, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.147955894470215, "global_step": 419926, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.085712432861328, "global_step": 419927, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.124263286590576, "global_step": 419928, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.091963768005371, "global_step": 419929, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.074537515640259, "global_step": 419930, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9978547096252441, "global_step": 419931, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1046299934387207, "global_step": 419932, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1278765201568604, "global_step": 419933, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.09146785736084, "global_step": 419934, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.2014594078063965, "global_step": 419935, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0900983810424805, "global_step": 419936, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9848570823669434, "global_step": 419937, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.101011037826538, "global_step": 419938, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.110982894897461, "global_step": 419939, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.086139678955078, "global_step": 419940, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1381711959838867, "global_step": 419941, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1055259704589844, "global_step": 419942, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.079418659210205, "global_step": 419943, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1024818420410156, "global_step": 419944, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1076714992523193, "global_step": 419945, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0351438522338867, "global_step": 419946, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0662124156951904, "global_step": 419947, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1455516815185547, "global_step": 419948, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.136072874069214, "global_step": 419949, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0848867893218994, "global_step": 419950, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0560719966888428, "global_step": 419951, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.071181297302246, "global_step": 419952, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1133522987365723, "global_step": 419953, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0942928791046143, "global_step": 419954, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.128329038619995, "global_step": 419955, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.045693874359131, "global_step": 419956, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0834076404571533, "global_step": 419957, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.073026657104492, "global_step": 419958, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0564401149749756, "global_step": 419959, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0546164512634277, "global_step": 419960, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.122098922729492, "global_step": 419961, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1009888648986816, "global_step": 419962, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.142489433288574, "global_step": 419963, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.102782726287842, "global_step": 419964, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0223097801208496, "global_step": 419965, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1312129497528076, "global_step": 419966, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0799143314361572, "global_step": 419967, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1641838550567627, "global_step": 419968, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.111345052719116, "global_step": 419969, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0815107822418213, "global_step": 419970, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0635180473327637, "global_step": 419971, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.126727342605591, "global_step": 419972, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0661122798919678, "global_step": 419973, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0630600452423096, "global_step": 419974, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.08581805229187, "global_step": 419975, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1205105781555176, "global_step": 419976, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1536154747009277, "global_step": 419977, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0866801738739014, "global_step": 419978, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.100710153579712, "global_step": 419979, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.125748872756958, "global_step": 419980, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.128973960876465, "global_step": 419981, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.10539174079895, "global_step": 419982, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0474789142608643, "global_step": 419983, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.140228033065796, "global_step": 419984, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.126997947692871, "global_step": 419985, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.168938398361206, "global_step": 419986, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.055278778076172, "global_step": 419987, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.117732524871826, "global_step": 419988, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0604801177978516, "global_step": 419989, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0544850826263428, "global_step": 419990, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.118216037750244, "global_step": 419991, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.103714942932129, "global_step": 419992, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.109461784362793, "global_step": 419993, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.107299327850342, "global_step": 419994, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0759801864624023, "global_step": 419995, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.09041166305542, "global_step": 419996, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9756518602371216, "global_step": 419997, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.07552433013916, "global_step": 419998, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0807032585144043, "global_step": 419999, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0877621173858643, "global_step": 420000, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0728254318237305, "global_step": 420001, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.013932228088379, "global_step": 420002, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1387932300567627, "global_step": 420003, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.170175075531006, "global_step": 420004, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1091701984405518, "global_step": 420005, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9711763858795166, "global_step": 420006, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.030360460281372, "global_step": 420007, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0467655658721924, "global_step": 420008, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0638296604156494, "global_step": 420009, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0912203788757324, "global_step": 420010, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1428778171539307, "global_step": 420011, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0607407093048096, "global_step": 420012, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0016095638275146, "global_step": 420013, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.163548469543457, "global_step": 420014, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1010923385620117, "global_step": 420015, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.127209424972534, "global_step": 420016, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1364052295684814, "global_step": 420017, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0847740173339844, "global_step": 420018, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.122645378112793, "global_step": 420019, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.02370023727417, "global_step": 420020, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0384345054626465, "global_step": 420021, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1640098094940186, "global_step": 420022, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.050058126449585, "global_step": 420023, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0266668796539307, "global_step": 420024, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.17765736579895, "global_step": 420025, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0115413665771484, "global_step": 420026, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1207275390625, "global_step": 420027, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1492135524749756, "global_step": 420028, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0512444972991943, "global_step": 420029, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0721654891967773, "global_step": 420030, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.017771005630493, "global_step": 420031, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1233088970184326, "global_step": 420032, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.05936861038208, "global_step": 420033, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9996058940887451, "global_step": 420034, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1955606937408447, "global_step": 420035, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0725321769714355, "global_step": 420036, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.021596908569336, "global_step": 420037, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.080656051635742, "global_step": 420038, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.151655912399292, "global_step": 420039, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0137405395507812, "global_step": 420040, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.154008388519287, "global_step": 420041, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.109328269958496, "global_step": 420042, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9994854927062988, "global_step": 420043, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0034360885620117, "global_step": 420044, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9884860515594482, "global_step": 420045, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1246988773345947, "global_step": 420046, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0663092136383057, "global_step": 420047, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0030651092529297, "global_step": 420048, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1353046894073486, "global_step": 420049, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0922434329986572, "global_step": 420050, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1049137115478516, "global_step": 420051, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.089017868041992, "global_step": 420052, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.143930196762085, "global_step": 420053, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.091639280319214, "global_step": 420054, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.097329616546631, "global_step": 420055, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.122256278991699, "global_step": 420056, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.13021183013916, "global_step": 420057, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0686540603637695, "global_step": 420058, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1210672855377197, "global_step": 420059, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1347386837005615, "global_step": 420060, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0856590270996094, "global_step": 420061, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1019253730773926, "global_step": 420062, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.153151512145996, "global_step": 420063, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0635409355163574, "global_step": 420064, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0296404361724854, "global_step": 420065, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0001518726348877, "global_step": 420066, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.078360080718994, "global_step": 420067, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.110654354095459, "global_step": 420068, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1165168285369873, "global_step": 420069, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1575357913970947, "global_step": 420070, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0226173400878906, "global_step": 420071, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.098273992538452, "global_step": 420072, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9552509784698486, "global_step": 420073, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0182857513427734, "global_step": 420074, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.117997169494629, "global_step": 420075, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.006195545196533, "global_step": 420076, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0478668212890625, "global_step": 420077, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1440794467926025, "global_step": 420078, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0455596446990967, "global_step": 420079, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0412817001342773, "global_step": 420080, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9715142250061035, "global_step": 420081, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.118518590927124, "global_step": 420082, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.035679817199707, "global_step": 420083, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.050682544708252, "global_step": 420084, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1902894973754883, "global_step": 420085, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.080493688583374, "global_step": 420086, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.139475107192993, "global_step": 420087, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.092588424682617, "global_step": 420088, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0751891136169434, "global_step": 420089, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.109708547592163, "global_step": 420090, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.193310260772705, "global_step": 420091, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.091850757598877, "global_step": 420092, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0801877975463867, "global_step": 420093, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0737550258636475, "global_step": 420094, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.141239881515503, "global_step": 420095, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0502421855926514, "global_step": 420096, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.034071445465088, "global_step": 420097, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0906076431274414, "global_step": 420098, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1309828758239746, "global_step": 420099, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1002631187438965, "global_step": 420100, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1432547569274902, "global_step": 420101, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.115755319595337, "global_step": 420102, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1148712635040283, "global_step": 420103, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.105314254760742, "global_step": 420104, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0891411304473877, "global_step": 420105, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1077847480773926, "global_step": 420106, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1233887672424316, "global_step": 420107, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1004831790924072, "global_step": 420108, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.111478090286255, "global_step": 420109, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.133775234222412, "global_step": 420110, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.116572141647339, "global_step": 420111, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.016901969909668, "global_step": 420112, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0760931968688965, "global_step": 420113, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0833475589752197, "global_step": 420114, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.005519151687622, "global_step": 420115, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0781404972076416, "global_step": 420116, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1852688789367676, "global_step": 420117, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0689666271209717, "global_step": 420118, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.132219076156616, "global_step": 420119, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0699234008789062, "global_step": 420120, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1161696910858154, "global_step": 420121, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.088602066040039, "global_step": 420122, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0235424041748047, "global_step": 420123, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0914342403411865, "global_step": 420124, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.205901861190796, "global_step": 420125, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.119234085083008, "global_step": 420126, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.042450428009033, "global_step": 420127, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1655445098876953, "global_step": 420128, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0905537605285645, "global_step": 420129, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.089435577392578, "global_step": 420130, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0391721725463867, "global_step": 420131, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0952091217041016, "global_step": 420132, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0801877975463867, "global_step": 420133, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.100851058959961, "global_step": 420134, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.07145094871521, "global_step": 420135, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.129025936126709, "global_step": 420136, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.133790969848633, "global_step": 420137, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0512678623199463, "global_step": 420138, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0076754093170166, "global_step": 420139, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0488526821136475, "global_step": 420140, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.11832594871521, "global_step": 420141, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1361188888549805, "global_step": 420142, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0242576599121094, "global_step": 420143, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.076355457305908, "global_step": 420144, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0644400119781494, "global_step": 420145, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0859897136688232, "global_step": 420146, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1567635536193848, "global_step": 420147, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0686423778533936, "global_step": 420148, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0866756439208984, "global_step": 420149, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.073254346847534, "global_step": 420150, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.11533784866333, "global_step": 420151, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.127894639968872, "global_step": 420152, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1031017303466797, "global_step": 420153, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0533223152160645, "global_step": 420154, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0302865505218506, "global_step": 420155, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.05145525932312, "global_step": 420156, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1885554790496826, "global_step": 420157, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0101029872894287, "global_step": 420158, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0744683742523193, "global_step": 420159, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1302757263183594, "global_step": 420160, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1307334899902344, "global_step": 420161, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.054286241531372, "global_step": 420162, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.115321159362793, "global_step": 420163, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.053539514541626, "global_step": 420164, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0779688358306885, "global_step": 420165, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0842270851135254, "global_step": 420166, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.121702194213867, "global_step": 420167, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.058048725128174, "global_step": 420168, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1415855884552, "global_step": 420169, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0830721855163574, "global_step": 420170, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.156188488006592, "global_step": 420171, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.023216724395752, "global_step": 420172, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0786221027374268, "global_step": 420173, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0224547386169434, "global_step": 420174, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0321497917175293, "global_step": 420175, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.009756326675415, "global_step": 420176, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1284945011138916, "global_step": 420177, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.101437568664551, "global_step": 420178, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.122722625732422, "global_step": 420179, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1102826595306396, "global_step": 420180, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0783629417419434, "global_step": 420181, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.062849521636963, "global_step": 420182, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.029142141342163, "global_step": 420183, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.007122278213501, "global_step": 420184, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.030582904815674, "global_step": 420185, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.092150926589966, "global_step": 420186, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1470930576324463, "global_step": 420187, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.064185857772827, "global_step": 420188, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0951380729675293, "global_step": 420189, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0715694427490234, "global_step": 420190, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1054232120513916, "global_step": 420191, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.2174487113952637, "global_step": 420192, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0223240852355957, "global_step": 420193, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.180135726928711, "global_step": 420194, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.049323320388794, "global_step": 420195, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0429458618164062, "global_step": 420196, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.073017120361328, "global_step": 420197, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0847959518432617, "global_step": 420198, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9954159259796143, "global_step": 420199, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.102327346801758, "global_step": 420200, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1576480865478516, "global_step": 420201, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1443381309509277, "global_step": 420202, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.064847469329834, "global_step": 420203, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.087719202041626, "global_step": 420204, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.063627004623413, "global_step": 420205, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0784895420074463, "global_step": 420206, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0320613384246826, "global_step": 420207, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.048950433731079, "global_step": 420208, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.085125207901001, "global_step": 420209, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1049585342407227, "global_step": 420210, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.050558090209961, "global_step": 420211, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.164544105529785, "global_step": 420212, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.095069646835327, "global_step": 420213, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1367671489715576, "global_step": 420214, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0530831813812256, "global_step": 420215, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.124753475189209, "global_step": 420216, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0357248783111572, "global_step": 420217, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0893588066101074, "global_step": 420218, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.126025438308716, "global_step": 420219, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.100968360900879, "global_step": 420220, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.060518264770508, "global_step": 420221, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1129579544067383, "global_step": 420222, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0898311138153076, "global_step": 420223, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.04837703704834, "global_step": 420224, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0937676429748535, "global_step": 420225, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.203944683074951, "global_step": 420226, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1226441860198975, "global_step": 420227, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1037209033966064, "global_step": 420228, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1207752227783203, "global_step": 420229, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0803539752960205, "global_step": 420230, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.151482105255127, "global_step": 420231, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.088050365447998, "global_step": 420232, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.159715414047241, "global_step": 420233, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0957179069519043, "global_step": 420234, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1046652793884277, "global_step": 420235, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1111326217651367, "global_step": 420236, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0022430419921875, "global_step": 420237, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.107530355453491, "global_step": 420238, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1026065349578857, "global_step": 420239, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1308412551879883, "global_step": 420240, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1106581687927246, "global_step": 420241, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0809736251831055, "global_step": 420242, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1202588081359863, "global_step": 420243, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.087578058242798, "global_step": 420244, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0377707481384277, "global_step": 420245, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1654131412506104, "global_step": 420246, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.122938871383667, "global_step": 420247, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.042527675628662, "global_step": 420248, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0655057430267334, "global_step": 420249, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0554862022399902, "global_step": 420250, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0541412830352783, "global_step": 420251, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.142860174179077, "global_step": 420252, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0942864418029785, "global_step": 420253, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.039301633834839, "global_step": 420254, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1398470401763916, "global_step": 420255, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0390591621398926, "global_step": 420256, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.027974843978882, "global_step": 420257, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0820343494415283, "global_step": 420258, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0817325115203857, "global_step": 420259, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0542426109313965, "global_step": 420260, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.072061777114868, "global_step": 420261, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.996626615524292, "global_step": 420262, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.090258836746216, "global_step": 420263, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0983293056488037, "global_step": 420264, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1376378536224365, "global_step": 420265, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.098767042160034, "global_step": 420266, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0316598415374756, "global_step": 420267, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1568870544433594, "global_step": 420268, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1457359790802, "global_step": 420269, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1155757904052734, "global_step": 420270, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.084529399871826, "global_step": 420271, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0535240173339844, "global_step": 420272, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1453287601470947, "global_step": 420273, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.050821542739868, "global_step": 420274, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.047907829284668, "global_step": 420275, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.00075364112854, "global_step": 420276, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.099932909011841, "global_step": 420277, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.044480085372925, "global_step": 420278, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1448440551757812, "global_step": 420279, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1385388374328613, "global_step": 420280, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0550010204315186, "global_step": 420281, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0664992332458496, "global_step": 420282, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0544373989105225, "global_step": 420283, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9951120615005493, "global_step": 420284, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.103424072265625, "global_step": 420285, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.131500720977783, "global_step": 420286, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1019270420074463, "global_step": 420287, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.006098747253418, "global_step": 420288, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.073920488357544, "global_step": 420289, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.99686598777771, "global_step": 420290, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.982851505279541, "global_step": 420291, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1325929164886475, "global_step": 420292, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.049572467803955, "global_step": 420293, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0369465351104736, "global_step": 420294, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0205936431884766, "global_step": 420295, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.135253667831421, "global_step": 420296, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1656441688537598, "global_step": 420297, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.069793462753296, "global_step": 420298, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.023902654647827, "global_step": 420299, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.084463357925415, "global_step": 420300, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0030741691589355, "global_step": 420301, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0231974124908447, "global_step": 420302, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1454036235809326, "global_step": 420303, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0956335067749023, "global_step": 420304, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.052736282348633, "global_step": 420305, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0623860359191895, "global_step": 420306, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.06736159324646, "global_step": 420307, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.082559108734131, "global_step": 420308, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.009685754776001, "global_step": 420309, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1078317165374756, "global_step": 420310, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.13468861579895, "global_step": 420311, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1093990802764893, "global_step": 420312, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.131298780441284, "global_step": 420313, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.132992744445801, "global_step": 420314, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0409493446350098, "global_step": 420315, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1030163764953613, "global_step": 420316, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1088449954986572, "global_step": 420317, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1009886264801025, "global_step": 420318, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.071699619293213, "global_step": 420319, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.135878324508667, "global_step": 420320, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0854978561401367, "global_step": 420321, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0453529357910156, "global_step": 420322, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0730087757110596, "global_step": 420323, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.055666446685791, "global_step": 420324, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1419878005981445, "global_step": 420325, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.99090576171875, "global_step": 420326, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.162241220474243, "global_step": 420327, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0853822231292725, "global_step": 420328, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1486754417419434, "global_step": 420329, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.115389347076416, "global_step": 420330, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1162965297698975, "global_step": 420331, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1533632278442383, "global_step": 420332, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1220505237579346, "global_step": 420333, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.158510684967041, "global_step": 420334, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1804358959198, "global_step": 420335, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.107464551925659, "global_step": 420336, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.074544668197632, "global_step": 420337, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.102522134780884, "global_step": 420338, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0702197551727295, "global_step": 420339, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.151120185852051, "global_step": 420340, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.003596782684326, "global_step": 420341, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9879770278930664, "global_step": 420342, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.054999589920044, "global_step": 420343, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.132441997528076, "global_step": 420344, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1710429191589355, "global_step": 420345, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9540833234786987, "global_step": 420346, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.07326602935791, "global_step": 420347, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0368587970733643, "global_step": 420348, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.087503671646118, "global_step": 420349, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.124833822250366, "global_step": 420350, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.143495798110962, "global_step": 420351, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.971015453338623, "global_step": 420352, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1151280403137207, "global_step": 420353, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0684642791748047, "global_step": 420354, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9880331754684448, "global_step": 420355, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.090487241744995, "global_step": 420356, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0330440998077393, "global_step": 420357, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.030367612838745, "global_step": 420358, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0929975509643555, "global_step": 420359, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.076383590698242, "global_step": 420360, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.971742868423462, "global_step": 420361, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.126800537109375, "global_step": 420362, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.111449718475342, "global_step": 420363, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0703635215759277, "global_step": 420364, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.039837598800659, "global_step": 420365, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1557364463806152, "global_step": 420366, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0739805698394775, "global_step": 420367, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0626308917999268, "global_step": 420368, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.05580735206604, "global_step": 420369, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0519332885742188, "global_step": 420370, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.141604423522949, "global_step": 420371, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.137918472290039, "global_step": 420372, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.089576482772827, "global_step": 420373, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9966312646865845, "global_step": 420374, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0683693885803223, "global_step": 420375, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.077301502227783, "global_step": 420376, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1855478286743164, "global_step": 420377, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.142514944076538, "global_step": 420378, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.141455888748169, "global_step": 420379, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.027489185333252, "global_step": 420380, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.160727024078369, "global_step": 420381, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1473183631896973, "global_step": 420382, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0059804916381836, "global_step": 420383, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.98259699344635, "global_step": 420384, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.067289352416992, "global_step": 420385, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1240456104278564, "global_step": 420386, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1373915672302246, "global_step": 420387, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.067049980163574, "global_step": 420388, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0690572261810303, "global_step": 420389, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1276297569274902, "global_step": 420390, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0838146209716797, "global_step": 420391, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1221842765808105, "global_step": 420392, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1576507091522217, "global_step": 420393, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.068237781524658, "global_step": 420394, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.142089605331421, "global_step": 420395, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.057562828063965, "global_step": 420396, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0027434825897217, "global_step": 420397, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.052448034286499, "global_step": 420398, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0831894874572754, "global_step": 420399, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1710939407348633, "global_step": 420400, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.083564043045044, "global_step": 420401, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.07585072517395, "global_step": 420402, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.020334482192993, "global_step": 420403, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.15763258934021, "global_step": 420404, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0801095962524414, "global_step": 420405, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0656440258026123, "global_step": 420406, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0824697017669678, "global_step": 420407, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1123909950256348, "global_step": 420408, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0364251136779785, "global_step": 420409, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.079442262649536, "global_step": 420410, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.2110488414764404, "global_step": 420411, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.081050157546997, "global_step": 420412, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.137071132659912, "global_step": 420413, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1762444972991943, "global_step": 420414, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.166332483291626, "global_step": 420415, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0674662590026855, "global_step": 420416, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1266984939575195, "global_step": 420417, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.103703737258911, "global_step": 420418, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1675326824188232, "global_step": 420419, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.2032477855682373, "global_step": 420420, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.023386001586914, "global_step": 420421, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1313745975494385, "global_step": 420422, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0965416431427, "global_step": 420423, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0705854892730713, "global_step": 420424, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.054396867752075, "global_step": 420425, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1202681064605713, "global_step": 420426, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0218722820281982, "global_step": 420427, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.054915428161621, "global_step": 420428, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.056140899658203, "global_step": 420429, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0840260982513428, "global_step": 420430, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.086669921875, "global_step": 420431, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0527091026306152, "global_step": 420432, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0960583686828613, "global_step": 420433, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.089509963989258, "global_step": 420434, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.087589740753174, "global_step": 420435, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1404905319213867, "global_step": 420436, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.129694700241089, "global_step": 420437, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.075157880783081, "global_step": 420438, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0367941856384277, "global_step": 420439, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.014075756072998, "global_step": 420440, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.056943416595459, "global_step": 420441, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0796585083007812, "global_step": 420442, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0490095615386963, "global_step": 420443, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.088099479675293, "global_step": 420444, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.99658203125, "global_step": 420445, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0634517669677734, "global_step": 420446, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0527336597442627, "global_step": 420447, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0321381092071533, "global_step": 420448, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0434279441833496, "global_step": 420449, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0622596740722656, "global_step": 420450, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0866401195526123, "global_step": 420451, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1215507984161377, "global_step": 420452, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.099712610244751, "global_step": 420453, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1470062732696533, "global_step": 420454, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.081315040588379, "global_step": 420455, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.105402708053589, "global_step": 420456, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.087238073348999, "global_step": 420457, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1046929359436035, "global_step": 420458, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1540141105651855, "global_step": 420459, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0685038566589355, "global_step": 420460, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1353158950805664, "global_step": 420461, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1294028759002686, "global_step": 420462, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.126786231994629, "global_step": 420463, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.141522169113159, "global_step": 420464, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1123149394989014, "global_step": 420465, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0463476181030273, "global_step": 420466, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.122373580932617, "global_step": 420467, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.122746706008911, "global_step": 420468, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.079573154449463, "global_step": 420469, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.2066500186920166, "global_step": 420470, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9981799125671387, "global_step": 420471, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0936968326568604, "global_step": 420472, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.148669958114624, "global_step": 420473, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0581412315368652, "global_step": 420474, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.099015235900879, "global_step": 420475, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1061489582061768, "global_step": 420476, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1839523315429688, "global_step": 420477, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0963761806488037, "global_step": 420478, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0424418449401855, "global_step": 420479, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9422733783721924, "global_step": 420480, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.054037094116211, "global_step": 420481, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0231175422668457, "global_step": 420482, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1401453018188477, "global_step": 420483, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.148557662963867, "global_step": 420484, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.087176561355591, "global_step": 420485, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0938007831573486, "global_step": 420486, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.161759376525879, "global_step": 420487, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.084724187850952, "global_step": 420488, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0794625282287598, "global_step": 420489, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.085416316986084, "global_step": 420490, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0965569019317627, "global_step": 420491, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0972554683685303, "global_step": 420492, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0780231952667236, "global_step": 420493, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0855283737182617, "global_step": 420494, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.086808204650879, "global_step": 420495, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.116731882095337, "global_step": 420496, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.062152147293091, "global_step": 420497, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.042149782180786, "global_step": 420498, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.148249864578247, "global_step": 420499, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1697328090667725, "global_step": 420500, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0221261978149414, "global_step": 420501, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.150172233581543, "global_step": 420502, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.014077663421631, "global_step": 420503, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.169786214828491, "global_step": 420504, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1710240840911865, "global_step": 420505, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.015291690826416, "global_step": 420506, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.128422260284424, "global_step": 420507, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0304722785949707, "global_step": 420508, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0720345973968506, "global_step": 420509, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.119835615158081, "global_step": 420510, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1070683002471924, "global_step": 420511, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0690250396728516, "global_step": 420512, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1189894676208496, "global_step": 420513, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0700676441192627, "global_step": 420514, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.142118453979492, "global_step": 420515, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1050288677215576, "global_step": 420516, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.017125129699707, "global_step": 420517, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9869916439056396, "global_step": 420518, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.090952157974243, "global_step": 420519, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.122048854827881, "global_step": 420520, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0914146900177, "global_step": 420521, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9881093502044678, "global_step": 420522, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1761603355407715, "global_step": 420523, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.140968084335327, "global_step": 420524, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.110746383666992, "global_step": 420525, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.089327335357666, "global_step": 420526, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.137819290161133, "global_step": 420527, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1391258239746094, "global_step": 420528, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1177926063537598, "global_step": 420529, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1002871990203857, "global_step": 420530, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1425445079803467, "global_step": 420531, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.01650333404541, "global_step": 420532, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1048996448516846, "global_step": 420533, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1366190910339355, "global_step": 420534, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0602383613586426, "global_step": 420535, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.194232702255249, "global_step": 420536, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0817599296569824, "global_step": 420537, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.092360734939575, "global_step": 420538, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1063950061798096, "global_step": 420539, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.095282793045044, "global_step": 420540, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0586740970611572, "global_step": 420541, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1262152194976807, "global_step": 420542, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.049983501434326, "global_step": 420543, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.003466844558716, "global_step": 420544, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.098771095275879, "global_step": 420545, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.188113212585449, "global_step": 420546, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0119197368621826, "global_step": 420547, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1350858211517334, "global_step": 420548, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0596399307250977, "global_step": 420549, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0885610580444336, "global_step": 420550, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.027986764907837, "global_step": 420551, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.064298629760742, "global_step": 420552, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.027865409851074, "global_step": 420553, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0752274990081787, "global_step": 420554, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0974831581115723, "global_step": 420555, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0243148803710938, "global_step": 420556, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.132452964782715, "global_step": 420557, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1316699981689453, "global_step": 420558, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0828301906585693, "global_step": 420559, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.13970947265625, "global_step": 420560, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0926334857940674, "global_step": 420561, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1235263347625732, "global_step": 420562, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1560091972351074, "global_step": 420563, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.129300832748413, "global_step": 420564, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.17466402053833, "global_step": 420565, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0581471920013428, "global_step": 420566, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1574268341064453, "global_step": 420567, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0538766384124756, "global_step": 420568, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1477200984954834, "global_step": 420569, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0909876823425293, "global_step": 420570, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0166220664978027, "global_step": 420571, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0849826335906982, "global_step": 420572, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.069246768951416, "global_step": 420573, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.12204647064209, "global_step": 420574, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.033518075942993, "global_step": 420575, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0987532138824463, "global_step": 420576, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0571115016937256, "global_step": 420577, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.063528060913086, "global_step": 420578, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.140305995941162, "global_step": 420579, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.042945146560669, "global_step": 420580, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1505281925201416, "global_step": 420581, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0702083110809326, "global_step": 420582, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0120556354522705, "global_step": 420583, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.132563591003418, "global_step": 420584, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.176476240158081, "global_step": 420585, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.081470012664795, "global_step": 420586, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1579480171203613, "global_step": 420587, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1369245052337646, "global_step": 420588, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0784013271331787, "global_step": 420589, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1091396808624268, "global_step": 420590, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0799148082733154, "global_step": 420591, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0716238021850586, "global_step": 420592, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1472251415252686, "global_step": 420593, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.093053102493286, "global_step": 420594, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.036255359649658, "global_step": 420595, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.098566770553589, "global_step": 420596, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.034010410308838, "global_step": 420597, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.039947986602783, "global_step": 420598, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.035080909729004, "global_step": 420599, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.043811559677124, "global_step": 420600, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0947976112365723, "global_step": 420601, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.128523588180542, "global_step": 420602, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.061802864074707, "global_step": 420603, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9667994976043701, "global_step": 420604, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.2372307777404785, "global_step": 420605, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.105576515197754, "global_step": 420606, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0707764625549316, "global_step": 420607, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0562078952789307, "global_step": 420608, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1540682315826416, "global_step": 420609, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0920491218566895, "global_step": 420610, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0630242824554443, "global_step": 420611, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0786337852478027, "global_step": 420612, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.068554162979126, "global_step": 420613, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1729893684387207, "global_step": 420614, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0160157680511475, "global_step": 420615, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.141136407852173, "global_step": 420616, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.98462975025177, "global_step": 420617, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.186161756515503, "global_step": 420618, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1641180515289307, "global_step": 420619, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0108344554901123, "global_step": 420620, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0264205932617188, "global_step": 420621, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.126377820968628, "global_step": 420622, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.014366626739502, "global_step": 420623, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.073607921600342, "global_step": 420624, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.102240562438965, "global_step": 420625, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1877245903015137, "global_step": 420626, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0973870754241943, "global_step": 420627, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.076296806335449, "global_step": 420628, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.103315830230713, "global_step": 420629, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1072211265563965, "global_step": 420630, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.026817560195923, "global_step": 420631, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0641191005706787, "global_step": 420632, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1688194274902344, "global_step": 420633, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1114790439605713, "global_step": 420634, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0773534774780273, "global_step": 420635, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.069265127182007, "global_step": 420636, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.091186046600342, "global_step": 420637, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0148983001708984, "global_step": 420638, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.111236810684204, "global_step": 420639, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.081191301345825, "global_step": 420640, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.102301836013794, "global_step": 420641, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1118955612182617, "global_step": 420642, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9506677389144897, "global_step": 420643, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1293134689331055, "global_step": 420644, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0706005096435547, "global_step": 420645, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.039621591567993, "global_step": 420646, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1377055644989014, "global_step": 420647, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9595800638198853, "global_step": 420648, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.084484577178955, "global_step": 420649, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.2147397994995117, "global_step": 420650, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0782103538513184, "global_step": 420651, "epoch": 783, "lr": 5e-05}
{"train_loss": 1.9862732887268066, "global_step": 420652, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1585683822631836, "global_step": 420653, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.008039951324463, "global_step": 420654, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0129497051239014, "global_step": 420655, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.077387809753418, "global_step": 420656, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1564671993255615, "global_step": 420657, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.174931287765503, "global_step": 420658, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.099325656890869, "global_step": 420659, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0908188819885254, "global_step": 420660, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0961062908172607, "global_step": 420661, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0708134174346924, "global_step": 420662, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.121589183807373, "global_step": 420663, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0294950008392334, "global_step": 420664, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1212539672851562, "global_step": 420665, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.1379523277282715, "global_step": 420666, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0095696449279785, "global_step": 420667, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0709266662597656, "global_step": 420668, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0953221321105957, "global_step": 420669, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.039487600326538, "global_step": 420670, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.085763454437256, "global_step": 420671, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0698421001434326, "global_step": 420672, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.084620237350464, "global_step": 420673, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0382370948791504, "global_step": 420674, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0865867137908936, "global_step": 420675, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0522665977478027, "global_step": 420676, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.071920871734619, "global_step": 420677, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.086284637451172, "global_step": 420678, "epoch": 783, "lr": 5e-05}
{"train_loss": 2.0003368854522705, "global_step": 420679, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.076235771179199, "global_step": 420680, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1230032444000244, "global_step": 420681, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0237839221954346, "global_step": 420682, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.142179012298584, "global_step": 420683, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9921118021011353, "global_step": 420684, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.137474775314331, "global_step": 420685, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0948781967163086, "global_step": 420686, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0778653621673584, "global_step": 420687, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.069016933441162, "global_step": 420688, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.116472005844116, "global_step": 420689, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0654401779174805, "global_step": 420690, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.062376022338867, "global_step": 420691, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.046177864074707, "global_step": 420692, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.112316131591797, "global_step": 420693, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0126938819885254, "global_step": 420694, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1546614170074463, "global_step": 420695, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.040048122406006, "global_step": 420696, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.091958522796631, "global_step": 420697, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.044804811477661, "global_step": 420698, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1069843769073486, "global_step": 420699, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0397796630859375, "global_step": 420700, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.024991989135742, "global_step": 420701, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0308854579925537, "global_step": 420702, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0943262577056885, "global_step": 420703, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0591657161712646, "global_step": 420704, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1034371852874756, "global_step": 420705, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0843615531921387, "global_step": 420706, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.114978790283203, "global_step": 420707, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0539803504943848, "global_step": 420708, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.066253423690796, "global_step": 420709, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0433902740478516, "global_step": 420710, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9966620206832886, "global_step": 420711, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0554914474487305, "global_step": 420712, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0997467041015625, "global_step": 420713, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.109483480453491, "global_step": 420714, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.001788854598999, "global_step": 420715, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1032967567443848, "global_step": 420716, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.063911199569702, "global_step": 420717, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.079521894454956, "global_step": 420718, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0862629413604736, "global_step": 420719, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0629231929779053, "global_step": 420720, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0217130184173584, "global_step": 420721, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0844309329986572, "global_step": 420722, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0671122074127197, "global_step": 420723, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.111835479736328, "global_step": 420724, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0644948482513428, "global_step": 420725, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0372512340545654, "global_step": 420726, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.138336658477783, "global_step": 420727, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.084501266479492, "global_step": 420728, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1535093784332275, "global_step": 420729, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1365489959716797, "global_step": 420730, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.056011199951172, "global_step": 420731, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.134355068206787, "global_step": 420732, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.135388135910034, "global_step": 420733, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.197727680206299, "global_step": 420734, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.016655445098877, "global_step": 420735, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.08935284614563, "global_step": 420736, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.055042266845703, "global_step": 420737, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0734100341796875, "global_step": 420738, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.144432306289673, "global_step": 420739, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.131423234939575, "global_step": 420740, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0207440853118896, "global_step": 420741, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1438894271850586, "global_step": 420742, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.092054843902588, "global_step": 420743, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1899654865264893, "global_step": 420744, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.135096788406372, "global_step": 420745, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0635313987731934, "global_step": 420746, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0904502868652344, "global_step": 420747, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.065314531326294, "global_step": 420748, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1296839714050293, "global_step": 420749, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0820627212524414, "global_step": 420750, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1312286853790283, "global_step": 420751, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.074221134185791, "global_step": 420752, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.058986186981201, "global_step": 420753, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.10180401802063, "global_step": 420754, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0961594581604004, "global_step": 420755, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.151679039001465, "global_step": 420756, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0861449241638184, "global_step": 420757, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.090663194656372, "global_step": 420758, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1231045722961426, "global_step": 420759, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0268914699554443, "global_step": 420760, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1024367809295654, "global_step": 420761, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0501365661621094, "global_step": 420762, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.087298631668091, "global_step": 420763, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0841164588928223, "global_step": 420764, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0833210945129395, "global_step": 420765, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.023977518081665, "global_step": 420766, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.103450059890747, "global_step": 420767, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.149327039718628, "global_step": 420768, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0724947452545166, "global_step": 420769, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0851221084594727, "global_step": 420770, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.978304147720337, "global_step": 420771, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1086862087249756, "global_step": 420772, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0135269165039062, "global_step": 420773, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.115419864654541, "global_step": 420774, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.02070689201355, "global_step": 420775, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0790233612060547, "global_step": 420776, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1053378582000732, "global_step": 420777, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0394468307495117, "global_step": 420778, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.062312126159668, "global_step": 420779, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1496026515960693, "global_step": 420780, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0983760356903076, "global_step": 420781, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.080899238586426, "global_step": 420782, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1901514530181885, "global_step": 420783, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1357853412628174, "global_step": 420784, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.081238269805908, "global_step": 420785, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.094534158706665, "global_step": 420786, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0293848514556885, "global_step": 420787, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0133800506591797, "global_step": 420788, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.038972854614258, "global_step": 420789, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.093388557434082, "global_step": 420790, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0785062313079834, "global_step": 420791, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.021790027618408, "global_step": 420792, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0076799392700195, "global_step": 420793, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1148293018341064, "global_step": 420794, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.053494453430176, "global_step": 420795, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.039675712585449, "global_step": 420796, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0621328353881836, "global_step": 420797, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.084345579147339, "global_step": 420798, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1468253135681152, "global_step": 420799, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0257604122161865, "global_step": 420800, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0331408977508545, "global_step": 420801, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1901025772094727, "global_step": 420802, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.048588752746582, "global_step": 420803, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.041908025741577, "global_step": 420804, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0573830604553223, "global_step": 420805, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1215224266052246, "global_step": 420806, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1772427558898926, "global_step": 420807, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.084848642349243, "global_step": 420808, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.040804862976074, "global_step": 420809, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1054859161376953, "global_step": 420810, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.094247341156006, "global_step": 420811, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.992590308189392, "global_step": 420812, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0087411403656006, "global_step": 420813, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.052004814147949, "global_step": 420814, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.044994592666626, "global_step": 420815, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0560057163238525, "global_step": 420816, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0058786869049072, "global_step": 420817, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0373404026031494, "global_step": 420818, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.064145088195801, "global_step": 420819, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0385799407958984, "global_step": 420820, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.074399709701538, "global_step": 420821, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0569140911102295, "global_step": 420822, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1855521202087402, "global_step": 420823, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0101819038391113, "global_step": 420824, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.042261838912964, "global_step": 420825, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.082566738128662, "global_step": 420826, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1200685501098633, "global_step": 420827, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.094529390335083, "global_step": 420828, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0334343910217285, "global_step": 420829, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0713181495666504, "global_step": 420830, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.094588279724121, "global_step": 420831, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.061570644378662, "global_step": 420832, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.040705919265747, "global_step": 420833, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0387189388275146, "global_step": 420834, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1200098991394043, "global_step": 420835, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.115090847015381, "global_step": 420836, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.084465742111206, "global_step": 420837, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0553598403930664, "global_step": 420838, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0370421409606934, "global_step": 420839, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.038097381591797, "global_step": 420840, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.009871006011963, "global_step": 420841, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.036259889602661, "global_step": 420842, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9802110195159912, "global_step": 420843, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.053713798522949, "global_step": 420844, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0876619815826416, "global_step": 420845, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.077849864959717, "global_step": 420846, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0885162353515625, "global_step": 420847, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0937235355377197, "global_step": 420848, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1095337867736816, "global_step": 420849, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.112550735473633, "global_step": 420850, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0682265758514404, "global_step": 420851, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1160521507263184, "global_step": 420852, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.038020610809326, "global_step": 420853, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.136375904083252, "global_step": 420854, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.059699773788452, "global_step": 420855, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.2027316093444824, "global_step": 420856, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1388702392578125, "global_step": 420857, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.081183910369873, "global_step": 420858, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.006725788116455, "global_step": 420859, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.015977144241333, "global_step": 420860, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1420352458953857, "global_step": 420861, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1287968158721924, "global_step": 420862, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.131521224975586, "global_step": 420863, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0976028442382812, "global_step": 420864, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1569294929504395, "global_step": 420865, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0923972129821777, "global_step": 420866, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0842278003692627, "global_step": 420867, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0183181762695312, "global_step": 420868, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0483767986297607, "global_step": 420869, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0237834453582764, "global_step": 420870, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9658925533294678, "global_step": 420871, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.152574300765991, "global_step": 420872, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1003332138061523, "global_step": 420873, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9918369054794312, "global_step": 420874, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.2332966327667236, "global_step": 420875, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.103327989578247, "global_step": 420876, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.087005376815796, "global_step": 420877, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.01483154296875, "global_step": 420878, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.091010332107544, "global_step": 420879, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1479368209838867, "global_step": 420880, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.10075306892395, "global_step": 420881, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9600167274475098, "global_step": 420882, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0434107780456543, "global_step": 420883, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.031531572341919, "global_step": 420884, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.125720977783203, "global_step": 420885, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0857796669006348, "global_step": 420886, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.09968638420105, "global_step": 420887, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0468201637268066, "global_step": 420888, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1351633071899414, "global_step": 420889, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0810914039611816, "global_step": 420890, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9972119331359863, "global_step": 420891, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1251816749572754, "global_step": 420892, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9972572326660156, "global_step": 420893, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1331732273101807, "global_step": 420894, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.062049388885498, "global_step": 420895, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0849127769470215, "global_step": 420896, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.045808792114258, "global_step": 420897, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0334482192993164, "global_step": 420898, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.130176067352295, "global_step": 420899, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1047849655151367, "global_step": 420900, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.02323842048645, "global_step": 420901, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.068850040435791, "global_step": 420902, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.088749647140503, "global_step": 420903, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1598198413848877, "global_step": 420904, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.070605516433716, "global_step": 420905, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0652432441711426, "global_step": 420906, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1191277503967285, "global_step": 420907, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.246072292327881, "global_step": 420908, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.071418046951294, "global_step": 420909, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0638837814331055, "global_step": 420910, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1449015140533447, "global_step": 420911, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1137969493865967, "global_step": 420912, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0462543964385986, "global_step": 420913, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.085692882537842, "global_step": 420914, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.139071464538574, "global_step": 420915, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.040553569793701, "global_step": 420916, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1096677780151367, "global_step": 420917, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0844290256500244, "global_step": 420918, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1514689922332764, "global_step": 420919, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0951058864593506, "global_step": 420920, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1271698474884033, "global_step": 420921, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0922601222991943, "global_step": 420922, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.070546865463257, "global_step": 420923, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0995962619781494, "global_step": 420924, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.148277759552002, "global_step": 420925, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.058016777038574, "global_step": 420926, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0719120502471924, "global_step": 420927, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.028360366821289, "global_step": 420928, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0444910526275635, "global_step": 420929, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.09521746635437, "global_step": 420930, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1079094409942627, "global_step": 420931, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1443235874176025, "global_step": 420932, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0986647605895996, "global_step": 420933, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.049454927444458, "global_step": 420934, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.155825614929199, "global_step": 420935, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1265480518341064, "global_step": 420936, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.110252618789673, "global_step": 420937, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0737617015838623, "global_step": 420938, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0683867931365967, "global_step": 420939, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.13283371925354, "global_step": 420940, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0648117065429688, "global_step": 420941, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.020817279815674, "global_step": 420942, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.053741455078125, "global_step": 420943, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.02632212638855, "global_step": 420944, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.141094446182251, "global_step": 420945, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0707907676696777, "global_step": 420946, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0304274559020996, "global_step": 420947, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.008552074432373, "global_step": 420948, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0542497634887695, "global_step": 420949, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.185570478439331, "global_step": 420950, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.047654628753662, "global_step": 420951, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0140230655670166, "global_step": 420952, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.026733160018921, "global_step": 420953, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1360714435577393, "global_step": 420954, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0800466537475586, "global_step": 420955, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.071000337600708, "global_step": 420956, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0718324184417725, "global_step": 420957, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0482265949249268, "global_step": 420958, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1330173015594482, "global_step": 420959, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1125762462615967, "global_step": 420960, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0204660892486572, "global_step": 420961, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.99667227268219, "global_step": 420962, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.004828453063965, "global_step": 420963, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.116147518157959, "global_step": 420964, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0982115268707275, "global_step": 420965, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.054159641265869, "global_step": 420966, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.073246717453003, "global_step": 420967, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.07454776763916, "global_step": 420968, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1288816928863525, "global_step": 420969, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0975430011749268, "global_step": 420970, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0985796451568604, "global_step": 420971, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.09332275390625, "global_step": 420972, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1636335849761963, "global_step": 420973, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.117055892944336, "global_step": 420974, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.11909556388855, "global_step": 420975, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1320855617523193, "global_step": 420976, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0382418632507324, "global_step": 420977, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.086487054824829, "global_step": 420978, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.058159589767456, "global_step": 420979, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.080141067504883, "global_step": 420980, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0481624603271484, "global_step": 420981, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.062002420425415, "global_step": 420982, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9768472909927368, "global_step": 420983, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.170767068862915, "global_step": 420984, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.230424165725708, "global_step": 420985, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1010477542877197, "global_step": 420986, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0116238594055176, "global_step": 420987, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.119504690170288, "global_step": 420988, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0125765800476074, "global_step": 420989, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.13561749458313, "global_step": 420990, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1213152408599854, "global_step": 420991, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.991607427597046, "global_step": 420992, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9786596298217773, "global_step": 420993, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.160975456237793, "global_step": 420994, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0759239196777344, "global_step": 420995, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.062983274459839, "global_step": 420996, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.122236728668213, "global_step": 420997, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.118703603744507, "global_step": 420998, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0436654090881348, "global_step": 420999, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.124155044555664, "global_step": 421000, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0515084266662598, "global_step": 421001, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0725698471069336, "global_step": 421002, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.095261573791504, "global_step": 421003, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.053677558898926, "global_step": 421004, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0600967407226562, "global_step": 421005, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.083528757095337, "global_step": 421006, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.069735288619995, "global_step": 421007, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.113311529159546, "global_step": 421008, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0430619716644287, "global_step": 421009, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1047468185424805, "global_step": 421010, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0009846687316895, "global_step": 421011, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0888047218322754, "global_step": 421012, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0790302753448486, "global_step": 421013, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.073227882385254, "global_step": 421014, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0922658443450928, "global_step": 421015, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1050028800964355, "global_step": 421016, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.073791027069092, "global_step": 421017, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0724244117736816, "global_step": 421018, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0950605869293213, "global_step": 421019, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1160407066345215, "global_step": 421020, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0396430492401123, "global_step": 421021, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0413551330566406, "global_step": 421022, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.086000680923462, "global_step": 421023, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0221946239471436, "global_step": 421024, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0706958770751953, "global_step": 421025, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0621466636657715, "global_step": 421026, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9877866506576538, "global_step": 421027, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1028571128845215, "global_step": 421028, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9682338237762451, "global_step": 421029, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0702567100524902, "global_step": 421030, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1954808235168457, "global_step": 421031, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0330333709716797, "global_step": 421032, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.158851385116577, "global_step": 421033, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.065887928009033, "global_step": 421034, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.078749179840088, "global_step": 421035, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.123866558074951, "global_step": 421036, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.178555965423584, "global_step": 421037, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0897276401519775, "global_step": 421038, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0551836490631104, "global_step": 421039, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1075384616851807, "global_step": 421040, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9914649724960327, "global_step": 421041, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1023755073547363, "global_step": 421042, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0956361293792725, "global_step": 421043, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.080012321472168, "global_step": 421044, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1230602264404297, "global_step": 421045, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1233010292053223, "global_step": 421046, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.112558126449585, "global_step": 421047, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.088541030883789, "global_step": 421048, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0921871662139893, "global_step": 421049, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0378026962280273, "global_step": 421050, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0433857440948486, "global_step": 421051, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0504772663116455, "global_step": 421052, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0701897144317627, "global_step": 421053, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1050968170166016, "global_step": 421054, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.123704433441162, "global_step": 421055, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.027252197265625, "global_step": 421056, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1163129806518555, "global_step": 421057, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0690791606903076, "global_step": 421058, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.140653133392334, "global_step": 421059, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1346449851989746, "global_step": 421060, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1298725605010986, "global_step": 421061, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.094449281692505, "global_step": 421062, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.098860502243042, "global_step": 421063, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.069521188735962, "global_step": 421064, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.10656476020813, "global_step": 421065, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.095691204071045, "global_step": 421066, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.009692430496216, "global_step": 421067, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.132272481918335, "global_step": 421068, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1299068927764893, "global_step": 421069, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.058607339859009, "global_step": 421070, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.16520094871521, "global_step": 421071, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0595428943634033, "global_step": 421072, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.087207555770874, "global_step": 421073, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0968780517578125, "global_step": 421074, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.023057222366333, "global_step": 421075, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0764927864074707, "global_step": 421076, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0677597522735596, "global_step": 421077, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.050323724746704, "global_step": 421078, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.11208438873291, "global_step": 421079, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.138139486312866, "global_step": 421080, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0707952976226807, "global_step": 421081, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.094940662384033, "global_step": 421082, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.055295944213867, "global_step": 421083, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0152463912963867, "global_step": 421084, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.071962594985962, "global_step": 421085, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1557862758636475, "global_step": 421086, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1505801677703857, "global_step": 421087, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0851612091064453, "global_step": 421088, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.134629249572754, "global_step": 421089, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.016582727432251, "global_step": 421090, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.074065685272217, "global_step": 421091, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1106491088867188, "global_step": 421092, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.062845230102539, "global_step": 421093, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.037226915359497, "global_step": 421094, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0157976150512695, "global_step": 421095, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1378471851348877, "global_step": 421096, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0786330699920654, "global_step": 421097, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9775654077529907, "global_step": 421098, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0732390880584717, "global_step": 421099, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.029676914215088, "global_step": 421100, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.163649082183838, "global_step": 421101, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1315972805023193, "global_step": 421102, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.119379997253418, "global_step": 421103, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.997257113456726, "global_step": 421104, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1284444332122803, "global_step": 421105, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0855143070220947, "global_step": 421106, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.097689151763916, "global_step": 421107, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.153047561645508, "global_step": 421108, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.058730125427246, "global_step": 421109, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0408883094787598, "global_step": 421110, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1671886444091797, "global_step": 421111, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0370535850524902, "global_step": 421112, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0813400745391846, "global_step": 421113, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0437541007995605, "global_step": 421114, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1455183029174805, "global_step": 421115, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.140533924102783, "global_step": 421116, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.164369821548462, "global_step": 421117, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.048393726348877, "global_step": 421118, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1496288776397705, "global_step": 421119, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.096794605255127, "global_step": 421120, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0400021076202393, "global_step": 421121, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.093087673187256, "global_step": 421122, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.060353994369507, "global_step": 421123, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1016345024108887, "global_step": 421124, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1922061443328857, "global_step": 421125, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0925052165985107, "global_step": 421126, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.039710283279419, "global_step": 421127, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1029813289642334, "global_step": 421128, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.161898136138916, "global_step": 421129, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1356639862060547, "global_step": 421130, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0520529747009277, "global_step": 421131, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0945093631744385, "global_step": 421132, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1201136112213135, "global_step": 421133, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0902252197265625, "global_step": 421134, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.064192056655884, "global_step": 421135, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0381007194519043, "global_step": 421136, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1423723697662354, "global_step": 421137, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.037477731704712, "global_step": 421138, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1749942302703857, "global_step": 421139, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.050511121749878, "global_step": 421140, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.032195568084717, "global_step": 421141, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.145674467086792, "global_step": 421142, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1633706092834473, "global_step": 421143, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1627373695373535, "global_step": 421144, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0879032611846924, "global_step": 421145, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1151018142700195, "global_step": 421146, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0604569911956787, "global_step": 421147, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.126408100128174, "global_step": 421148, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1036877632141113, "global_step": 421149, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.115142583847046, "global_step": 421150, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1210179328918457, "global_step": 421151, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1735150814056396, "global_step": 421152, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.120781183242798, "global_step": 421153, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.006545305252075, "global_step": 421154, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0318045616149902, "global_step": 421155, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.022902011871338, "global_step": 421156, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.044809341430664, "global_step": 421157, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.104743003845215, "global_step": 421158, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.056450605392456, "global_step": 421159, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.131139039993286, "global_step": 421160, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0745387077331543, "global_step": 421161, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1701712608337402, "global_step": 421162, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.145921230316162, "global_step": 421163, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.074320077896118, "global_step": 421164, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0943164825439453, "global_step": 421165, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0855438709259033, "global_step": 421166, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0803418159484863, "global_step": 421167, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0229570865631104, "global_step": 421168, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0790088176727295, "global_step": 421169, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0785205364227295, "global_step": 421170, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.062415361404419, "global_step": 421171, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1714117527008057, "global_step": 421172, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9696303606033325, "global_step": 421173, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0930802822113037, "global_step": 421174, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.127887725830078, "global_step": 421175, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0922861099243164, "global_step": 421176, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0599348545074463, "global_step": 421177, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.014563798904419, "global_step": 421178, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0837879180908203, "global_step": 421179, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.120792865753174, "global_step": 421180, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1360936164855957, "global_step": 421181, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0915963649749756, "global_step": 421182, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1150848865509033, "global_step": 421183, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0508432388305664, "global_step": 421184, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1243529319763184, "global_step": 421185, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.121772527694702, "global_step": 421186, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0155019760131836, "global_step": 421187, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.133665084838867, "global_step": 421188, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1927578449249268, "global_step": 421189, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.079563856124878, "global_step": 421190, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0135209560394287, "global_step": 421191, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.075432538986206, "global_step": 421192, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0850462913513184, "global_step": 421193, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.064220905303955, "global_step": 421194, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1441946029663086, "global_step": 421195, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0699586868286133, "global_step": 421196, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.121344566345215, "global_step": 421197, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.076707601547241, "global_step": 421198, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0645225048065186, "global_step": 421199, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0398147106170654, "global_step": 421200, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0936577320098877, "global_step": 421201, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.082423686981201, "global_step": 421202, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.203202962875366, "global_step": 421203, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0365002155303955, "global_step": 421204, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0580713748931885, "global_step": 421205, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9648804664611816, "global_step": 421206, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0244550704956055, "global_step": 421207, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9876750707626343, "global_step": 421208, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1074178218841553, "global_step": 421209, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1398541927337646, "global_step": 421210, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0047569274902344, "global_step": 421211, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0714616775512695, "global_step": 421212, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1483328342437744, "global_step": 421213, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.096937417984009, "global_step": 421214, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0454235076904297, "global_step": 421215, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.082763195037842, "global_step": 421216, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0676333904266357, "global_step": 421217, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.054654598236084, "global_step": 421218, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.067950487136841, "global_step": 421219, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1328110694885254, "global_step": 421220, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1233785152435303, "global_step": 421221, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0802247524261475, "global_step": 421222, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0688564777374268, "global_step": 421223, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0982210636138916, "global_step": 421224, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1358067989349365, "global_step": 421225, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0629100799560547, "global_step": 421226, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0968406200408936, "global_step": 421227, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0810446739196777, "global_step": 421228, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.037283420562744, "global_step": 421229, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1463119983673096, "global_step": 421230, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.141249656677246, "global_step": 421231, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0804927349090576, "global_step": 421232, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.079411745071411, "global_step": 421233, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0770816802978516, "global_step": 421234, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0675086975097656, "global_step": 421235, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1249594688415527, "global_step": 421236, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.081092357635498, "global_step": 421237, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.028226137161255, "global_step": 421238, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.10595440864563, "global_step": 421239, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0593180656433105, "global_step": 421240, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0665743350982666, "global_step": 421241, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0653693675994873, "global_step": 421242, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0066487789154053, "global_step": 421243, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.103888511657715, "global_step": 421244, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.127997875213623, "global_step": 421245, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.045077323913574, "global_step": 421246, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.142657518386841, "global_step": 421247, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.123445510864258, "global_step": 421248, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.033986806869507, "global_step": 421249, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.065183162689209, "global_step": 421250, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0561015605926514, "global_step": 421251, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1237926483154297, "global_step": 421252, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.179023504257202, "global_step": 421253, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0546438694000244, "global_step": 421254, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0261313915252686, "global_step": 421255, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.956936001777649, "global_step": 421256, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0935778617858887, "global_step": 421257, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0846939086914062, "global_step": 421258, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.117196559906006, "global_step": 421259, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.089552640914917, "global_step": 421260, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0244204998016357, "global_step": 421261, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.102080821990967, "global_step": 421262, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0092108249664307, "global_step": 421263, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1151206493377686, "global_step": 421264, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.157939910888672, "global_step": 421265, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.013153314590454, "global_step": 421266, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0382800102233887, "global_step": 421267, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0952093601226807, "global_step": 421268, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.043217897415161, "global_step": 421269, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.143548011779785, "global_step": 421270, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.060857057571411, "global_step": 421271, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0921361446380615, "global_step": 421272, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1138916015625, "global_step": 421273, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.110400915145874, "global_step": 421274, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0532126426696777, "global_step": 421275, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.17333984375, "global_step": 421276, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1357955932617188, "global_step": 421277, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.077854871749878, "global_step": 421278, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1211209297180176, "global_step": 421279, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.122098684310913, "global_step": 421280, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.2087724208831787, "global_step": 421281, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0590603351593018, "global_step": 421282, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.199965715408325, "global_step": 421283, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.042376756668091, "global_step": 421284, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1319196224212646, "global_step": 421285, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.174131155014038, "global_step": 421286, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.076900005340576, "global_step": 421287, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.075982093811035, "global_step": 421288, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0333211421966553, "global_step": 421289, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1104576587677, "global_step": 421290, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.114318370819092, "global_step": 421291, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0936784744262695, "global_step": 421292, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0899436473846436, "global_step": 421293, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.094365358352661, "global_step": 421294, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0216612815856934, "global_step": 421295, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1041245460510254, "global_step": 421296, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.051119327545166, "global_step": 421297, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.123490333557129, "global_step": 421298, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0760817527770996, "global_step": 421299, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.069399356842041, "global_step": 421300, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1278719902038574, "global_step": 421301, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.139620780944824, "global_step": 421302, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0858101844787598, "global_step": 421303, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.090956211090088, "global_step": 421304, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.065005302429199, "global_step": 421305, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0780742168426514, "global_step": 421306, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0729620456695557, "global_step": 421307, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0434012413024902, "global_step": 421308, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.142740249633789, "global_step": 421309, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.176985025405884, "global_step": 421310, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.161227226257324, "global_step": 421311, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1360297203063965, "global_step": 421312, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1186249256134033, "global_step": 421313, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1859333515167236, "global_step": 421314, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.118356943130493, "global_step": 421315, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0718071460723877, "global_step": 421316, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1035094261169434, "global_step": 421317, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.065152168273926, "global_step": 421318, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0423672199249268, "global_step": 421319, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.03519344329834, "global_step": 421320, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.179715394973755, "global_step": 421321, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.131662368774414, "global_step": 421322, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.098172426223755, "global_step": 421323, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0667152404785156, "global_step": 421324, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.116363525390625, "global_step": 421325, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.057603597640991, "global_step": 421326, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0149178504943848, "global_step": 421327, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0211668014526367, "global_step": 421328, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0184762477874756, "global_step": 421329, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0388121604919434, "global_step": 421330, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0835187435150146, "global_step": 421331, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.123396396636963, "global_step": 421332, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.988004207611084, "global_step": 421333, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0862064361572266, "global_step": 421334, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1622722148895264, "global_step": 421335, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.064608573913574, "global_step": 421336, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.138873338699341, "global_step": 421337, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1135270595550537, "global_step": 421338, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0634078979492188, "global_step": 421339, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0546250343322754, "global_step": 421340, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1680703163146973, "global_step": 421341, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9799734354019165, "global_step": 421342, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.040799617767334, "global_step": 421343, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.203366279602051, "global_step": 421344, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.131990671157837, "global_step": 421345, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0786194801330566, "global_step": 421346, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0982625484466553, "global_step": 421347, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1077065467834473, "global_step": 421348, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.986801266670227, "global_step": 421349, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.068469762802124, "global_step": 421350, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.07016921043396, "global_step": 421351, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1471242904663086, "global_step": 421352, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.178126811981201, "global_step": 421353, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0637259483337402, "global_step": 421354, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0748379230499268, "global_step": 421355, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1091389656066895, "global_step": 421356, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.017247200012207, "global_step": 421357, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1364595890045166, "global_step": 421358, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.097390651702881, "global_step": 421359, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0497169494628906, "global_step": 421360, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.072910785675049, "global_step": 421361, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.107879161834717, "global_step": 421362, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.077514410018921, "global_step": 421363, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0866928100585938, "global_step": 421364, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.093048095703125, "global_step": 421365, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.154825448989868, "global_step": 421366, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0597949028015137, "global_step": 421367, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1605589389801025, "global_step": 421368, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1006927490234375, "global_step": 421369, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.068819046020508, "global_step": 421370, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1909713745117188, "global_step": 421371, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0781807899475098, "global_step": 421372, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0415985584259033, "global_step": 421373, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1184823513031006, "global_step": 421374, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0560970306396484, "global_step": 421375, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.073323965072632, "global_step": 421376, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0629868507385254, "global_step": 421377, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0002167224884033, "global_step": 421378, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1173195838928223, "global_step": 421379, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0202152729034424, "global_step": 421380, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0071732997894287, "global_step": 421381, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0717861652374268, "global_step": 421382, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.14567494392395, "global_step": 421383, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1066818237304688, "global_step": 421384, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1674551963806152, "global_step": 421385, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0943281650543213, "global_step": 421386, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.114288091659546, "global_step": 421387, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0813450813293457, "global_step": 421388, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1809051036834717, "global_step": 421389, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.085648775100708, "global_step": 421390, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0959632396698, "global_step": 421391, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0703001022338867, "global_step": 421392, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0523436069488525, "global_step": 421393, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0560030937194824, "global_step": 421394, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0555450916290283, "global_step": 421395, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0382916927337646, "global_step": 421396, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1107234954833984, "global_step": 421397, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.056654453277588, "global_step": 421398, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.057050943374634, "global_step": 421399, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0284862518310547, "global_step": 421400, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1277687549591064, "global_step": 421401, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1288974285125732, "global_step": 421402, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1085166931152344, "global_step": 421403, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.110976457595825, "global_step": 421404, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.172020196914673, "global_step": 421405, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.094900131225586, "global_step": 421406, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.09407639503479, "global_step": 421407, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0966901779174805, "global_step": 421408, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0352776050567627, "global_step": 421409, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0266165733337402, "global_step": 421410, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.088404655456543, "global_step": 421411, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0796332359313965, "global_step": 421412, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0870461463928223, "global_step": 421413, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1563384532928467, "global_step": 421414, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1458089351654053, "global_step": 421415, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0348198413848877, "global_step": 421416, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1768951416015625, "global_step": 421417, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0506813526153564, "global_step": 421418, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0576794147491455, "global_step": 421419, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1472103595733643, "global_step": 421420, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.112976551055908, "global_step": 421421, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0900371074676514, "global_step": 421422, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.094886064529419, "global_step": 421423, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.061079263687134, "global_step": 421424, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.119067668914795, "global_step": 421425, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0323238372802734, "global_step": 421426, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1632652282714844, "global_step": 421427, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.110786199569702, "global_step": 421428, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0475049018859863, "global_step": 421429, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0145857334136963, "global_step": 421430, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9958525896072388, "global_step": 421431, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0742948055267334, "global_step": 421432, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9904175996780396, "global_step": 421433, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1315860748291016, "global_step": 421434, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0199146270751953, "global_step": 421435, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1280829906463623, "global_step": 421436, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0582499504089355, "global_step": 421437, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0910897254943848, "global_step": 421438, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1213433742523193, "global_step": 421439, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.125084161758423, "global_step": 421440, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1129209995269775, "global_step": 421441, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.114659070968628, "global_step": 421442, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0678939819335938, "global_step": 421443, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0537192821502686, "global_step": 421444, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.000174045562744, "global_step": 421445, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1373019218444824, "global_step": 421446, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0663981437683105, "global_step": 421447, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.097221612930298, "global_step": 421448, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.052741050720215, "global_step": 421449, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1177923679351807, "global_step": 421450, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9981836080551147, "global_step": 421451, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1319117546081543, "global_step": 421452, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0718348026275635, "global_step": 421453, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1124746799468994, "global_step": 421454, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0699656009674072, "global_step": 421455, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0514776706695557, "global_step": 421456, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0220210552215576, "global_step": 421457, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0772016048431396, "global_step": 421458, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.132298707962036, "global_step": 421459, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.159363031387329, "global_step": 421460, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.035959482192993, "global_step": 421461, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0854475498199463, "global_step": 421462, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1745598316192627, "global_step": 421463, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1043758392333984, "global_step": 421464, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.133957862854004, "global_step": 421465, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.098989486694336, "global_step": 421466, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.080580234527588, "global_step": 421467, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.99903404712677, "global_step": 421468, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0739188194274902, "global_step": 421469, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0631299018859863, "global_step": 421470, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.069260597229004, "global_step": 421471, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.133411169052124, "global_step": 421472, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1224186420440674, "global_step": 421473, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0615439414978027, "global_step": 421474, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.016191244125366, "global_step": 421475, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.154785394668579, "global_step": 421476, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0818114280700684, "global_step": 421477, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.125641345977783, "global_step": 421478, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.2160162925720215, "global_step": 421479, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.130739688873291, "global_step": 421480, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.154609441757202, "global_step": 421481, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1496870517730713, "global_step": 421482, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.125739097595215, "global_step": 421483, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0213165283203125, "global_step": 421484, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1047346591949463, "global_step": 421485, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.068466901779175, "global_step": 421486, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0197885036468506, "global_step": 421487, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.985769510269165, "global_step": 421488, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1119637489318848, "global_step": 421489, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1040916442871094, "global_step": 421490, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.05383563041687, "global_step": 421491, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.031224250793457, "global_step": 421492, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1248466968536377, "global_step": 421493, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.098026990890503, "global_step": 421494, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.179572582244873, "global_step": 421495, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0975770950317383, "global_step": 421496, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0959348678588867, "global_step": 421497, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.084944248199463, "global_step": 421498, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0469486713409424, "global_step": 421499, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.121429204940796, "global_step": 421500, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0393128395080566, "global_step": 421501, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.026710271835327, "global_step": 421502, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1086339950561523, "global_step": 421503, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.051046133041382, "global_step": 421504, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.031388282775879, "global_step": 421505, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1529200077056885, "global_step": 421506, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0852367877960205, "global_step": 421507, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9888134002685547, "global_step": 421508, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0257534980773926, "global_step": 421509, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0780282020568848, "global_step": 421510, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1030731201171875, "global_step": 421511, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0232205390930176, "global_step": 421512, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0748097896575928, "global_step": 421513, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.150581121444702, "global_step": 421514, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0686440467834473, "global_step": 421515, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.987407922744751, "global_step": 421516, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0944981575012207, "global_step": 421517, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1384522914886475, "global_step": 421518, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.122093677520752, "global_step": 421519, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1191446781158447, "global_step": 421520, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.014399528503418, "global_step": 421521, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.068852186203003, "global_step": 421522, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.112410545349121, "global_step": 421523, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0025765895843506, "global_step": 421524, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.153334140777588, "global_step": 421525, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.2318739891052246, "global_step": 421526, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.18510365486145, "global_step": 421527, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.205552101135254, "global_step": 421528, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.08479380607605, "global_step": 421529, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9822046756744385, "global_step": 421530, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1068756580352783, "global_step": 421531, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1125574111938477, "global_step": 421532, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1341044902801514, "global_step": 421533, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1373863220214844, "global_step": 421534, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0113983154296875, "global_step": 421535, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.08827805519104, "global_step": 421536, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.055163860321045, "global_step": 421537, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0835793018341064, "global_step": 421538, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.077353000640869, "global_step": 421539, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.145081043243408, "global_step": 421540, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1119749546051025, "global_step": 421541, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.117467164993286, "global_step": 421542, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.051647901535034, "global_step": 421543, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.17257022857666, "global_step": 421544, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.031073570251465, "global_step": 421545, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1151340007781982, "global_step": 421546, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1847028732299805, "global_step": 421547, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.113748550415039, "global_step": 421548, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.10502290725708, "global_step": 421549, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.158444881439209, "global_step": 421550, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1767184734344482, "global_step": 421551, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.118927240371704, "global_step": 421552, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1096415519714355, "global_step": 421553, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.131237030029297, "global_step": 421554, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9800076484680176, "global_step": 421555, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1188251972198486, "global_step": 421556, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.050565242767334, "global_step": 421557, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1164908409118652, "global_step": 421558, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0258259773254395, "global_step": 421559, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9693629741668701, "global_step": 421560, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.044440507888794, "global_step": 421561, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0327510833740234, "global_step": 421562, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1627023220062256, "global_step": 421563, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1265032291412354, "global_step": 421564, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.20524001121521, "global_step": 421565, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.166933536529541, "global_step": 421566, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1371476650238037, "global_step": 421567, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.08829665184021, "global_step": 421568, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1066057682037354, "global_step": 421569, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1047446727752686, "global_step": 421570, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0593912601470947, "global_step": 421571, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0259923934936523, "global_step": 421572, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.146845817565918, "global_step": 421573, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.129958391189575, "global_step": 421574, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.130842924118042, "global_step": 421575, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1782758235931396, "global_step": 421576, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0476341247558594, "global_step": 421577, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1299476623535156, "global_step": 421578, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1101229190826416, "global_step": 421579, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.120140552520752, "global_step": 421580, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0639243125915527, "global_step": 421581, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1499576568603516, "global_step": 421582, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1073946952819824, "global_step": 421583, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.116375207901001, "global_step": 421584, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.092940330505371, "global_step": 421585, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.005650758743286, "global_step": 421586, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0342490673065186, "global_step": 421587, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9915111064910889, "global_step": 421588, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.127387523651123, "global_step": 421589, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0896189212799072, "global_step": 421590, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0465216636657715, "global_step": 421591, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.099250316619873, "global_step": 421592, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.071723699569702, "global_step": 421593, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0458972454071045, "global_step": 421594, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0437302589416504, "global_step": 421595, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0878074169158936, "global_step": 421596, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.065002918243408, "global_step": 421597, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0557971000671387, "global_step": 421598, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1108360290527344, "global_step": 421599, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0561137199401855, "global_step": 421600, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.048583984375, "global_step": 421601, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.090620517730713, "global_step": 421602, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.074361562728882, "global_step": 421603, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.146104097366333, "global_step": 421604, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0970003604888916, "global_step": 421605, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1067402362823486, "global_step": 421606, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1200523376464844, "global_step": 421607, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1340103149414062, "global_step": 421608, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1542561054229736, "global_step": 421609, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1048855781555176, "global_step": 421610, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0490899085998535, "global_step": 421611, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1301379203796387, "global_step": 421612, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0094008445739746, "global_step": 421613, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.02579927444458, "global_step": 421614, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.108487367630005, "global_step": 421615, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0964736938476562, "global_step": 421616, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1667230129241943, "global_step": 421617, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1648988723754883, "global_step": 421618, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.9581531286239624, "global_step": 421619, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0918028354644775, "global_step": 421620, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.114427328109741, "global_step": 421621, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0216457843780518, "global_step": 421622, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.124145984649658, "global_step": 421623, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.181440591812134, "global_step": 421624, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1048190593719482, "global_step": 421625, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1427907943725586, "global_step": 421626, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1035983562469482, "global_step": 421627, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1189112663269043, "global_step": 421628, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0608773231506348, "global_step": 421629, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.141021490097046, "global_step": 421630, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0674996376037598, "global_step": 421631, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.2155866622924805, "global_step": 421632, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0474345684051514, "global_step": 421633, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0639805793762207, "global_step": 421634, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0333077907562256, "global_step": 421635, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0322186946868896, "global_step": 421636, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1343960762023926, "global_step": 421637, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1064634323120117, "global_step": 421638, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0804858207702637, "global_step": 421639, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.059094190597534, "global_step": 421640, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.102637529373169, "global_step": 421641, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.095550775527954, "global_step": 421642, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0670182704925537, "global_step": 421643, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1229755878448486, "global_step": 421644, "epoch": 784, "lr": 5e-05}
{"train_loss": 1.99483060836792, "global_step": 421645, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.1216092109680176, "global_step": 421646, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.0861566066741943, "global_step": 421647, "epoch": 784, "lr": 5e-05}
{"train_loss": 2.168166160583496, "global_step": 421648, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.097226858139038, "global_step": 421649, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1339848041534424, "global_step": 421650, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.037020206451416, "global_step": 421651, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.065091371536255, "global_step": 421652, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0660459995269775, "global_step": 421653, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.126451253890991, "global_step": 421654, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0741474628448486, "global_step": 421655, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0634591579437256, "global_step": 421656, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.022430419921875, "global_step": 421657, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.025944709777832, "global_step": 421658, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0180411338806152, "global_step": 421659, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1805953979492188, "global_step": 421660, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1284637451171875, "global_step": 421661, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0883588790893555, "global_step": 421662, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0680439472198486, "global_step": 421663, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1354787349700928, "global_step": 421664, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.118431568145752, "global_step": 421665, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.991664171218872, "global_step": 421666, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1065144538879395, "global_step": 421667, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.021894693374634, "global_step": 421668, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0065300464630127, "global_step": 421669, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1663730144500732, "global_step": 421670, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.080913543701172, "global_step": 421671, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0104382038116455, "global_step": 421672, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0620737075805664, "global_step": 421673, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0613672733306885, "global_step": 421674, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9905447959899902, "global_step": 421675, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.082512378692627, "global_step": 421676, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.142989158630371, "global_step": 421677, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0964951515197754, "global_step": 421678, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.129819393157959, "global_step": 421679, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.049502372741699, "global_step": 421680, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0077321529388428, "global_step": 421681, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0413947105407715, "global_step": 421682, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1046254634857178, "global_step": 421683, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.137617588043213, "global_step": 421684, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.070713520050049, "global_step": 421685, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1285042762756348, "global_step": 421686, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.031550884246826, "global_step": 421687, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.134127616882324, "global_step": 421688, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.123779058456421, "global_step": 421689, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0327060222625732, "global_step": 421690, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9914149045944214, "global_step": 421691, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1080703735351562, "global_step": 421692, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0801620483398438, "global_step": 421693, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.097745895385742, "global_step": 421694, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1465988159179688, "global_step": 421695, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0414485931396484, "global_step": 421696, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.077794075012207, "global_step": 421697, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.132526397705078, "global_step": 421698, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1315510272979736, "global_step": 421699, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0498368740081787, "global_step": 421700, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.015310049057007, "global_step": 421701, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.035146474838257, "global_step": 421702, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0667474269866943, "global_step": 421703, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.090885639190674, "global_step": 421704, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1972272396087646, "global_step": 421705, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9918917417526245, "global_step": 421706, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0533571243286133, "global_step": 421707, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1004843711853027, "global_step": 421708, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.057182550430298, "global_step": 421709, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0317704677581787, "global_step": 421710, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.043304204940796, "global_step": 421711, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.081465005874634, "global_step": 421712, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1270363330841064, "global_step": 421713, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0847549438476562, "global_step": 421714, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.142455816268921, "global_step": 421715, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0960521697998047, "global_step": 421716, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.10174822807312, "global_step": 421717, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1309680938720703, "global_step": 421718, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.05177903175354, "global_step": 421719, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.014857769012451, "global_step": 421720, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.024392604827881, "global_step": 421721, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.112138509750366, "global_step": 421722, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0865423679351807, "global_step": 421723, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0072197914123535, "global_step": 421724, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.180961847305298, "global_step": 421725, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0647103786468506, "global_step": 421726, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0212230682373047, "global_step": 421727, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0801877975463867, "global_step": 421728, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1484763622283936, "global_step": 421729, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1654212474823, "global_step": 421730, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.074925422668457, "global_step": 421731, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1330761909484863, "global_step": 421732, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0882134437561035, "global_step": 421733, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0968194007873535, "global_step": 421734, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0972020626068115, "global_step": 421735, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0382230281829834, "global_step": 421736, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.028179407119751, "global_step": 421737, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1191258430480957, "global_step": 421738, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0995771884918213, "global_step": 421739, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.094332695007324, "global_step": 421740, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0309031009674072, "global_step": 421741, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0917770862579346, "global_step": 421742, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.049572706222534, "global_step": 421743, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0428483486175537, "global_step": 421744, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.022376537322998, "global_step": 421745, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.08668851852417, "global_step": 421746, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.092985153198242, "global_step": 421747, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1022863388061523, "global_step": 421748, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0832889080047607, "global_step": 421749, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.096775531768799, "global_step": 421750, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.110339879989624, "global_step": 421751, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.997651219367981, "global_step": 421752, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1030423641204834, "global_step": 421753, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.2044715881347656, "global_step": 421754, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.099594831466675, "global_step": 421755, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0835587978363037, "global_step": 421756, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0548558235168457, "global_step": 421757, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.023345470428467, "global_step": 421758, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1056556701660156, "global_step": 421759, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.133434772491455, "global_step": 421760, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0572407245635986, "global_step": 421761, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1403512954711914, "global_step": 421762, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1172854900360107, "global_step": 421763, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1119794845581055, "global_step": 421764, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0740866661071777, "global_step": 421765, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.065483570098877, "global_step": 421766, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0991756916046143, "global_step": 421767, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0563948154449463, "global_step": 421768, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.104583501815796, "global_step": 421769, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.095679759979248, "global_step": 421770, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.200901746749878, "global_step": 421771, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0626220703125, "global_step": 421772, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0278236865997314, "global_step": 421773, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.149813175201416, "global_step": 421774, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.014174461364746, "global_step": 421775, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0789754390716553, "global_step": 421776, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.086130380630493, "global_step": 421777, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.086878538131714, "global_step": 421778, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.020494222640991, "global_step": 421779, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.043246269226074, "global_step": 421780, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.087151050567627, "global_step": 421781, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0770208835601807, "global_step": 421782, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0903756618499756, "global_step": 421783, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0229527950286865, "global_step": 421784, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0221993923187256, "global_step": 421785, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0667731761932373, "global_step": 421786, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.190755605697632, "global_step": 421787, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.083313226699829, "global_step": 421788, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0515410900115967, "global_step": 421789, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0365793704986572, "global_step": 421790, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0746653079986572, "global_step": 421791, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1894662380218506, "global_step": 421792, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1788694858551025, "global_step": 421793, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.022894859313965, "global_step": 421794, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.160984992980957, "global_step": 421795, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.972959280014038, "global_step": 421796, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0746335983276367, "global_step": 421797, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.100457191467285, "global_step": 421798, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.046359062194824, "global_step": 421799, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.092811346054077, "global_step": 421800, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.09322190284729, "global_step": 421801, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.030503749847412, "global_step": 421802, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0074501037597656, "global_step": 421803, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1121585369110107, "global_step": 421804, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.169515609741211, "global_step": 421805, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0449748039245605, "global_step": 421806, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.065786361694336, "global_step": 421807, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1312320232391357, "global_step": 421808, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1318044662475586, "global_step": 421809, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.995466947555542, "global_step": 421810, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.079908847808838, "global_step": 421811, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.130685806274414, "global_step": 421812, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1238350868225098, "global_step": 421813, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0727667808532715, "global_step": 421814, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0543134212493896, "global_step": 421815, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0198566913604736, "global_step": 421816, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0565695762634277, "global_step": 421817, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.030238389968872, "global_step": 421818, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1290979385375977, "global_step": 421819, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0283830165863037, "global_step": 421820, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.041163682937622, "global_step": 421821, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0963022708892822, "global_step": 421822, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0313851833343506, "global_step": 421823, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.139307737350464, "global_step": 421824, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0961530208587646, "global_step": 421825, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.059180736541748, "global_step": 421826, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.029597520828247, "global_step": 421827, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1328225135803223, "global_step": 421828, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1065621376037598, "global_step": 421829, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0458786487579346, "global_step": 421830, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0626795291900635, "global_step": 421831, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0396080017089844, "global_step": 421832, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1069540977478027, "global_step": 421833, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.075524091720581, "global_step": 421834, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1017203330993652, "global_step": 421835, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.112753391265869, "global_step": 421836, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1000661849975586, "global_step": 421837, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0859344005584717, "global_step": 421838, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.134263515472412, "global_step": 421839, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9771889448165894, "global_step": 421840, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1463682651519775, "global_step": 421841, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1526753902435303, "global_step": 421842, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0549230575561523, "global_step": 421843, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.105163335800171, "global_step": 421844, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.056509494781494, "global_step": 421845, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1046645641326904, "global_step": 421846, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.073230743408203, "global_step": 421847, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.13177752494812, "global_step": 421848, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1631064414978027, "global_step": 421849, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0175552368164062, "global_step": 421850, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.117666482925415, "global_step": 421851, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0511293411254883, "global_step": 421852, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1333847045898438, "global_step": 421853, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0356383323669434, "global_step": 421854, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0906429290771484, "global_step": 421855, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.040968656539917, "global_step": 421856, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.047323703765869, "global_step": 421857, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9814074039459229, "global_step": 421858, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1384425163269043, "global_step": 421859, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.100393772125244, "global_step": 421860, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.067366123199463, "global_step": 421861, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.102323293685913, "global_step": 421862, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0454185009002686, "global_step": 421863, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0544333457946777, "global_step": 421864, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0907492637634277, "global_step": 421865, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.066465377807617, "global_step": 421866, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0601675510406494, "global_step": 421867, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0611069202423096, "global_step": 421868, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.12264084815979, "global_step": 421869, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.113354444503784, "global_step": 421870, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1772661209106445, "global_step": 421871, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1089820861816406, "global_step": 421872, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.022843599319458, "global_step": 421873, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1141483783721924, "global_step": 421874, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0017430782318115, "global_step": 421875, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0835468769073486, "global_step": 421876, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0723421573638916, "global_step": 421877, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.076453685760498, "global_step": 421878, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1094977855682373, "global_step": 421879, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.144313335418701, "global_step": 421880, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.061044454574585, "global_step": 421881, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.219400644302368, "global_step": 421882, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1500768661499023, "global_step": 421883, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.122640609741211, "global_step": 421884, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1132566928863525, "global_step": 421885, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0317914485931396, "global_step": 421886, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0576066970825195, "global_step": 421887, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1254642009735107, "global_step": 421888, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.12646222114563, "global_step": 421889, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0177254676818848, "global_step": 421890, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.044785976409912, "global_step": 421891, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0497546195983887, "global_step": 421892, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.038062334060669, "global_step": 421893, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.096163511276245, "global_step": 421894, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.927773356437683, "global_step": 421895, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.015873432159424, "global_step": 421896, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.129755973815918, "global_step": 421897, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0839180946350098, "global_step": 421898, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0795390605926514, "global_step": 421899, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0526795387268066, "global_step": 421900, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1007308959960938, "global_step": 421901, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0018928050994873, "global_step": 421902, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0360848903656006, "global_step": 421903, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.05880069732666, "global_step": 421904, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.022987127304077, "global_step": 421905, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.16420841217041, "global_step": 421906, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1132259368896484, "global_step": 421907, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0707287788391113, "global_step": 421908, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1524181365966797, "global_step": 421909, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.099146604537964, "global_step": 421910, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.144399404525757, "global_step": 421911, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0928478240966797, "global_step": 421912, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1338253021240234, "global_step": 421913, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0336413383483887, "global_step": 421914, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0757226943969727, "global_step": 421915, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1227338314056396, "global_step": 421916, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1504716873168945, "global_step": 421917, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1015779972076416, "global_step": 421918, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0684993267059326, "global_step": 421919, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1107661724090576, "global_step": 421920, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.074192762374878, "global_step": 421921, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.137282371520996, "global_step": 421922, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0016443729400635, "global_step": 421923, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0733797550201416, "global_step": 421924, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.071833610534668, "global_step": 421925, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.2248682975769043, "global_step": 421926, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.190525770187378, "global_step": 421927, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.080573558807373, "global_step": 421928, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1443257331848145, "global_step": 421929, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1683366298675537, "global_step": 421930, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.053468704223633, "global_step": 421931, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.105820894241333, "global_step": 421932, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1337904930114746, "global_step": 421933, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1144912242889404, "global_step": 421934, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.107248544692993, "global_step": 421935, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.036499500274658, "global_step": 421936, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9823720455169678, "global_step": 421937, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0730960369110107, "global_step": 421938, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1707355976104736, "global_step": 421939, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0340564250946045, "global_step": 421940, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.068920135498047, "global_step": 421941, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1745173931121826, "global_step": 421942, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1132752895355225, "global_step": 421943, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1645047664642334, "global_step": 421944, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.042524814605713, "global_step": 421945, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.07378888130188, "global_step": 421946, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1370091438293457, "global_step": 421947, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1319985389709473, "global_step": 421948, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1038706302642822, "global_step": 421949, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.006598711013794, "global_step": 421950, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1023921966552734, "global_step": 421951, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0333359241485596, "global_step": 421952, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0073249340057373, "global_step": 421953, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0370049476623535, "global_step": 421954, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.013794422149658, "global_step": 421955, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.067936658859253, "global_step": 421956, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0172832012176514, "global_step": 421957, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.065629720687866, "global_step": 421958, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0486342906951904, "global_step": 421959, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0160470008850098, "global_step": 421960, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.068493366241455, "global_step": 421961, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.140244722366333, "global_step": 421962, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.161914348602295, "global_step": 421963, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0993881225585938, "global_step": 421964, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0776760578155518, "global_step": 421965, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.068601131439209, "global_step": 421966, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1541812419891357, "global_step": 421967, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0945799350738525, "global_step": 421968, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.070542335510254, "global_step": 421969, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.058593511581421, "global_step": 421970, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0583484172821045, "global_step": 421971, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1569314002990723, "global_step": 421972, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0480849742889404, "global_step": 421973, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1321287155151367, "global_step": 421974, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.178914785385132, "global_step": 421975, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.087249279022217, "global_step": 421976, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.2049176692962646, "global_step": 421977, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0329694747924805, "global_step": 421978, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0126006603240967, "global_step": 421979, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0764002799987793, "global_step": 421980, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0836730003356934, "global_step": 421981, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0514285564422607, "global_step": 421982, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0707905292510986, "global_step": 421983, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9525917768478394, "global_step": 421984, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0337655544281006, "global_step": 421985, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.18440842628479, "global_step": 421986, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.035891532897949, "global_step": 421987, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.053046703338623, "global_step": 421988, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0567781925201416, "global_step": 421989, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.075425148010254, "global_step": 421990, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1153316497802734, "global_step": 421991, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0672006607055664, "global_step": 421992, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0651891231536865, "global_step": 421993, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0872340202331543, "global_step": 421994, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0031893253326416, "global_step": 421995, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0717194080352783, "global_step": 421996, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1817190647125244, "global_step": 421997, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0735528469085693, "global_step": 421998, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0988097190856934, "global_step": 421999, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.110177993774414, "global_step": 422000, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0804202556610107, "global_step": 422001, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0817317962646484, "global_step": 422002, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.071124792098999, "global_step": 422003, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9775348901748657, "global_step": 422004, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.037264347076416, "global_step": 422005, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0571320056915283, "global_step": 422006, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0981686115264893, "global_step": 422007, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1017887592315674, "global_step": 422008, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.105776786804199, "global_step": 422009, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.141732931137085, "global_step": 422010, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1402766704559326, "global_step": 422011, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0266926288604736, "global_step": 422012, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.116175413131714, "global_step": 422013, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1826820373535156, "global_step": 422014, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.114938974380493, "global_step": 422015, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1572442054748535, "global_step": 422016, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0897629261016846, "global_step": 422017, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0676872730255127, "global_step": 422018, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.009889602661133, "global_step": 422019, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1127684116363525, "global_step": 422020, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0738799571990967, "global_step": 422021, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.063196897506714, "global_step": 422022, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.139784097671509, "global_step": 422023, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.115135669708252, "global_step": 422024, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9426685571670532, "global_step": 422025, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.097341775894165, "global_step": 422026, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1795780658721924, "global_step": 422027, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.087123394012451, "global_step": 422028, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.202968120574951, "global_step": 422029, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0361337661743164, "global_step": 422030, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.124412775039673, "global_step": 422031, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.106506824493408, "global_step": 422032, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0496294498443604, "global_step": 422033, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.052591323852539, "global_step": 422034, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.143003225326538, "global_step": 422035, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.139622449874878, "global_step": 422036, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.050684690475464, "global_step": 422037, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.176814317703247, "global_step": 422038, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0264086723327637, "global_step": 422039, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0461390018463135, "global_step": 422040, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1804709434509277, "global_step": 422041, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1325976848602295, "global_step": 422042, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.094865560531616, "global_step": 422043, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.083582639694214, "global_step": 422044, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1285245418548584, "global_step": 422045, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.054257392883301, "global_step": 422046, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0209195613861084, "global_step": 422047, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1354238986968994, "global_step": 422048, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1544039249420166, "global_step": 422049, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.119926929473877, "global_step": 422050, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0938289165496826, "global_step": 422051, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0156774520874023, "global_step": 422052, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.077087640762329, "global_step": 422053, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0185413360595703, "global_step": 422054, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1199469566345215, "global_step": 422055, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.01806640625, "global_step": 422056, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.139983654022217, "global_step": 422057, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.094756841659546, "global_step": 422058, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1724324226379395, "global_step": 422059, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.064570426940918, "global_step": 422060, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1117265224456787, "global_step": 422061, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.16886305809021, "global_step": 422062, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.095747947692871, "global_step": 422063, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1032490730285645, "global_step": 422064, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1227169036865234, "global_step": 422065, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1145431995391846, "global_step": 422066, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0756824016571045, "global_step": 422067, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0544865131378174, "global_step": 422068, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.039463996887207, "global_step": 422069, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1759345531463623, "global_step": 422070, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0635552406311035, "global_step": 422071, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0887022018432617, "global_step": 422072, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.072357654571533, "global_step": 422073, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0246217250823975, "global_step": 422074, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0553395748138428, "global_step": 422075, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.140474557876587, "global_step": 422076, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.132869243621826, "global_step": 422077, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1845695972442627, "global_step": 422078, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0553510189056396, "global_step": 422079, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.025377035140991, "global_step": 422080, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.125615358352661, "global_step": 422081, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.094702959060669, "global_step": 422082, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.086677312850952, "global_step": 422083, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.00243878364563, "global_step": 422084, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.071908712387085, "global_step": 422085, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0598506927490234, "global_step": 422086, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.05938720703125, "global_step": 422087, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0391929149627686, "global_step": 422088, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.142244338989258, "global_step": 422089, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1914000511169434, "global_step": 422090, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0101773738861084, "global_step": 422091, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1803908348083496, "global_step": 422092, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.071469306945801, "global_step": 422093, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.078590154647827, "global_step": 422094, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0637764930725098, "global_step": 422095, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9645323753356934, "global_step": 422096, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0628111362457275, "global_step": 422097, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.117720127105713, "global_step": 422098, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1040563583374023, "global_step": 422099, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.039149284362793, "global_step": 422100, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1538586616516113, "global_step": 422101, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0257649421691895, "global_step": 422102, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0832462310791016, "global_step": 422103, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.117661237716675, "global_step": 422104, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.129351854324341, "global_step": 422105, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1166625022888184, "global_step": 422106, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.08730411529541, "global_step": 422107, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.105349540710449, "global_step": 422108, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0578813552856445, "global_step": 422109, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.049503803253174, "global_step": 422110, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0765061378479004, "global_step": 422111, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.041548728942871, "global_step": 422112, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.135927438735962, "global_step": 422113, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1726291179656982, "global_step": 422114, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0731542110443115, "global_step": 422115, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.081958532333374, "global_step": 422116, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.055539846420288, "global_step": 422117, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.106680154800415, "global_step": 422118, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0703046321868896, "global_step": 422119, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0916552543640137, "global_step": 422120, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.094270706176758, "global_step": 422121, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.163184642791748, "global_step": 422122, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0459978580474854, "global_step": 422123, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.127937078475952, "global_step": 422124, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.132631540298462, "global_step": 422125, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.116878032684326, "global_step": 422126, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.064781904220581, "global_step": 422127, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1597793102264404, "global_step": 422128, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.054443359375, "global_step": 422129, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1528074741363525, "global_step": 422130, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1474685668945312, "global_step": 422131, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0970208644866943, "global_step": 422132, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.086395740509033, "global_step": 422133, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.161348819732666, "global_step": 422134, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9513726234436035, "global_step": 422135, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.122610092163086, "global_step": 422136, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0348896980285645, "global_step": 422137, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1391546726226807, "global_step": 422138, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.032226085662842, "global_step": 422139, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.108041524887085, "global_step": 422140, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.11588454246521, "global_step": 422141, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.182483673095703, "global_step": 422142, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9918270111083984, "global_step": 422143, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.016319751739502, "global_step": 422144, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.048016309738159, "global_step": 422145, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0663444995880127, "global_step": 422146, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.11997127532959, "global_step": 422147, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.08833646774292, "global_step": 422148, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.064185619354248, "global_step": 422149, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0676705837249756, "global_step": 422150, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0266201496124268, "global_step": 422151, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.076453924179077, "global_step": 422152, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1024863719940186, "global_step": 422153, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0779881477355957, "global_step": 422154, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0060312747955322, "global_step": 422155, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0344719886779785, "global_step": 422156, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1187210083007812, "global_step": 422157, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.145904779434204, "global_step": 422158, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.043287515640259, "global_step": 422159, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0758817195892334, "global_step": 422160, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0756006240844727, "global_step": 422161, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1488449573516846, "global_step": 422162, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.103425979614258, "global_step": 422163, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.043351650238037, "global_step": 422164, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0669310092926025, "global_step": 422165, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0368149280548096, "global_step": 422166, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1073617935180664, "global_step": 422167, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.085879325866699, "global_step": 422168, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.060455322265625, "global_step": 422169, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.08829665184021, "global_step": 422170, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0270485877990723, "global_step": 422171, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.027024269104004, "global_step": 422172, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.120753526687622, "global_step": 422173, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0315744876861572, "global_step": 422174, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.064199447631836, "global_step": 422175, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1079232692718506, "global_step": 422176, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0596837997436523, "global_step": 422177, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0713229179382324, "global_step": 422178, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1637983322143555, "global_step": 422179, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.033543586730957, "global_step": 422180, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.100938558578491, "global_step": 422181, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0490424633026123, "global_step": 422182, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.078014612197876, "global_step": 422183, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.040239095687866, "global_step": 422184, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0771875381469727, "global_step": 422185, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1246321201324463, "global_step": 422186, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.057936906814575, "global_step": 422187, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.16632080078125, "global_step": 422188, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1293506622314453, "global_step": 422189, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0618486404418945, "global_step": 422190, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.07570481300354, "global_step": 422191, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.162607192993164, "global_step": 422192, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.051941156387329, "global_step": 422193, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.052380084991455, "global_step": 422194, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0801727771759033, "global_step": 422195, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.091977119445801, "global_step": 422196, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1312992572784424, "global_step": 422197, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.043492317199707, "global_step": 422198, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.100679874420166, "global_step": 422199, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1347270011901855, "global_step": 422200, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0702335834503174, "global_step": 422201, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.109079122543335, "global_step": 422202, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.040165424346924, "global_step": 422203, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.168278932571411, "global_step": 422204, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0349466800689697, "global_step": 422205, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0203471183776855, "global_step": 422206, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0344321727752686, "global_step": 422207, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.147038698196411, "global_step": 422208, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.137408971786499, "global_step": 422209, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.074313163757324, "global_step": 422210, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1226446628570557, "global_step": 422211, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0355372428894043, "global_step": 422212, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.04911208152771, "global_step": 422213, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.113646984100342, "global_step": 422214, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.11161470413208, "global_step": 422215, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1253631114959717, "global_step": 422216, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.999796748161316, "global_step": 422217, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0548195838928223, "global_step": 422218, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0334160327911377, "global_step": 422219, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1145756244659424, "global_step": 422220, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1043925285339355, "global_step": 422221, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0428550243377686, "global_step": 422222, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1291215419769287, "global_step": 422223, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.156480550765991, "global_step": 422224, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.064795970916748, "global_step": 422225, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.187350034713745, "global_step": 422226, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1106975078582764, "global_step": 422227, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0672435760498047, "global_step": 422228, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1182689666748047, "global_step": 422229, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.093343496322632, "global_step": 422230, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1595327854156494, "global_step": 422231, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.186685562133789, "global_step": 422232, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0047202110290527, "global_step": 422233, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0808486938476562, "global_step": 422234, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1239991188049316, "global_step": 422235, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.097888708114624, "global_step": 422236, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0877957344055176, "global_step": 422237, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0957164764404297, "global_step": 422238, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.030609369277954, "global_step": 422239, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0129575729370117, "global_step": 422240, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0980851650238037, "global_step": 422241, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1789257526397705, "global_step": 422242, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.061041831970215, "global_step": 422243, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.12123441696167, "global_step": 422244, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.046659469604492, "global_step": 422245, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9881765842437744, "global_step": 422246, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0631065368652344, "global_step": 422247, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.063227415084839, "global_step": 422248, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0720057487487793, "global_step": 422249, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1739110946655273, "global_step": 422250, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1321864128112793, "global_step": 422251, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1023266315460205, "global_step": 422252, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1216912269592285, "global_step": 422253, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1711831092834473, "global_step": 422254, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.212611675262451, "global_step": 422255, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1667840480804443, "global_step": 422256, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.085207939147949, "global_step": 422257, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.105050563812256, "global_step": 422258, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1123228073120117, "global_step": 422259, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0626189708709717, "global_step": 422260, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0998265743255615, "global_step": 422261, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0092296600341797, "global_step": 422262, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.141599416732788, "global_step": 422263, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.104832410812378, "global_step": 422264, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.047766923904419, "global_step": 422265, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1234121322631836, "global_step": 422266, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0538620948791504, "global_step": 422267, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9943724870681763, "global_step": 422268, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1068437099456787, "global_step": 422269, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.007772922515869, "global_step": 422270, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1876046657562256, "global_step": 422271, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.015233039855957, "global_step": 422272, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.058270215988159, "global_step": 422273, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.032413959503174, "global_step": 422274, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.09045672416687, "global_step": 422275, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.169126510620117, "global_step": 422276, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0338823795318604, "global_step": 422277, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.087618350982666, "global_step": 422278, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.095961809158325, "global_step": 422279, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0413742065429688, "global_step": 422280, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0593810081481934, "global_step": 422281, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.159006357192993, "global_step": 422282, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0799710750579834, "global_step": 422283, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.124535083770752, "global_step": 422284, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0903480052948, "global_step": 422285, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0719666481018066, "global_step": 422286, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.040221929550171, "global_step": 422287, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0861270427703857, "global_step": 422288, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1229162216186523, "global_step": 422289, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.113912343978882, "global_step": 422290, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0659093856811523, "global_step": 422291, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.078604221343994, "global_step": 422292, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.129483222961426, "global_step": 422293, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.112079620361328, "global_step": 422294, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.054919958114624, "global_step": 422295, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0098533630371094, "global_step": 422296, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0127644538879395, "global_step": 422297, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.062217950820923, "global_step": 422298, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.060328483581543, "global_step": 422299, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.178457498550415, "global_step": 422300, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.115032196044922, "global_step": 422301, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0182554721832275, "global_step": 422302, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.093315839767456, "global_step": 422303, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0881145000457764, "global_step": 422304, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.032780885696411, "global_step": 422305, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0670716762542725, "global_step": 422306, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.067535877227783, "global_step": 422307, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.125999689102173, "global_step": 422308, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0590147972106934, "global_step": 422309, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0067176818847656, "global_step": 422310, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1105380058288574, "global_step": 422311, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0718657970428467, "global_step": 422312, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.147632360458374, "global_step": 422313, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1226210594177246, "global_step": 422314, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.052119255065918, "global_step": 422315, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.031097888946533, "global_step": 422316, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.132310390472412, "global_step": 422317, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0670785903930664, "global_step": 422318, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0876405239105225, "global_step": 422319, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1967215538024902, "global_step": 422320, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.125025510787964, "global_step": 422321, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.166830539703369, "global_step": 422322, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0741257667541504, "global_step": 422323, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0245261192321777, "global_step": 422324, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.028643846511841, "global_step": 422325, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.130096673965454, "global_step": 422326, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1600983142852783, "global_step": 422327, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0952165126800537, "global_step": 422328, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0795066356658936, "global_step": 422329, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.076383590698242, "global_step": 422330, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0533759593963623, "global_step": 422331, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0833308696746826, "global_step": 422332, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.067643880844116, "global_step": 422333, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0370988845825195, "global_step": 422334, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.059149742126465, "global_step": 422335, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1499791145324707, "global_step": 422336, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.065354824066162, "global_step": 422337, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.053234815597534, "global_step": 422338, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.090667963027954, "global_step": 422339, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.014094829559326, "global_step": 422340, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1206624507904053, "global_step": 422341, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0406992435455322, "global_step": 422342, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1080944538116455, "global_step": 422343, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0841763019561768, "global_step": 422344, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1102843284606934, "global_step": 422345, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0571677684783936, "global_step": 422346, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1386122703552246, "global_step": 422347, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1613352298736572, "global_step": 422348, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1031579971313477, "global_step": 422349, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0562026500701904, "global_step": 422350, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1084883213043213, "global_step": 422351, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.048146963119507, "global_step": 422352, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0429859161376953, "global_step": 422353, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.046903133392334, "global_step": 422354, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.02943754196167, "global_step": 422355, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0376596450805664, "global_step": 422356, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.145320177078247, "global_step": 422357, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0751755237579346, "global_step": 422358, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9981842041015625, "global_step": 422359, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.079282522201538, "global_step": 422360, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0610718727111816, "global_step": 422361, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.159806489944458, "global_step": 422362, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1329116821289062, "global_step": 422363, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1210904121398926, "global_step": 422364, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0236635208129883, "global_step": 422365, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0523152351379395, "global_step": 422366, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0400993824005127, "global_step": 422367, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0677578449249268, "global_step": 422368, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.123431921005249, "global_step": 422369, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.048774003982544, "global_step": 422370, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.052255868911743, "global_step": 422371, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1821742057800293, "global_step": 422372, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.129396915435791, "global_step": 422373, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.166647434234619, "global_step": 422374, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.063045024871826, "global_step": 422375, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9949980974197388, "global_step": 422376, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.014133930206299, "global_step": 422377, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.174699544906616, "global_step": 422378, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.084700345993042, "global_step": 422379, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.087158203125, "global_step": 422380, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1007561683654785, "global_step": 422381, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0464296340942383, "global_step": 422382, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.025897264480591, "global_step": 422383, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.051827907562256, "global_step": 422384, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.112670421600342, "global_step": 422385, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.131027936935425, "global_step": 422386, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0708487033843994, "global_step": 422387, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1465837955474854, "global_step": 422388, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.116180419921875, "global_step": 422389, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0758302211761475, "global_step": 422390, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1066582202911377, "global_step": 422391, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.984728455543518, "global_step": 422392, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0093834400177, "global_step": 422393, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1014697551727295, "global_step": 422394, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.2077972888946533, "global_step": 422395, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0995123386383057, "global_step": 422396, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.065563201904297, "global_step": 422397, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.030313491821289, "global_step": 422398, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.159867763519287, "global_step": 422399, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.044827938079834, "global_step": 422400, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.146585702896118, "global_step": 422401, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0780651569366455, "global_step": 422402, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.150468587875366, "global_step": 422403, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9987784624099731, "global_step": 422404, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.171754837036133, "global_step": 422405, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.067873477935791, "global_step": 422406, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.068789005279541, "global_step": 422407, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1286211013793945, "global_step": 422408, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.077364683151245, "global_step": 422409, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1935672760009766, "global_step": 422410, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0700089931488037, "global_step": 422411, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0760576725006104, "global_step": 422412, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.134894609451294, "global_step": 422413, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.068840742111206, "global_step": 422414, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.153494119644165, "global_step": 422415, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0930590629577637, "global_step": 422416, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0800530910491943, "global_step": 422417, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.09304141998291, "global_step": 422418, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1216933727264404, "global_step": 422419, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.088132619857788, "global_step": 422420, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1171534061431885, "global_step": 422421, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.087986707687378, "global_step": 422422, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1063380241394043, "global_step": 422423, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.135570764541626, "global_step": 422424, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.064077377319336, "global_step": 422425, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1315083503723145, "global_step": 422426, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.073493003845215, "global_step": 422427, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.120603084564209, "global_step": 422428, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0911223888397217, "global_step": 422429, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.060857057571411, "global_step": 422430, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.059537410736084, "global_step": 422431, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.092637538909912, "global_step": 422432, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.067574977874756, "global_step": 422433, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.061180353164673, "global_step": 422434, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1563222408294678, "global_step": 422435, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.062232494354248, "global_step": 422436, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0870330333709717, "global_step": 422437, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0766732692718506, "global_step": 422438, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.079787492752075, "global_step": 422439, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.102200508117676, "global_step": 422440, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1756937503814697, "global_step": 422441, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0814828872680664, "global_step": 422442, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0776844024658203, "global_step": 422443, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1384804248809814, "global_step": 422444, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0575575828552246, "global_step": 422445, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0615293979644775, "global_step": 422446, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.087723731994629, "global_step": 422447, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.100327253341675, "global_step": 422448, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.108916759490967, "global_step": 422449, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1465749740600586, "global_step": 422450, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.077144145965576, "global_step": 422451, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.095691442489624, "global_step": 422452, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.141766309738159, "global_step": 422453, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1002094745635986, "global_step": 422454, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0800650119781494, "global_step": 422455, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.052079677581787, "global_step": 422456, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1173291206359863, "global_step": 422457, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0395689010620117, "global_step": 422458, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0984091758728027, "global_step": 422459, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.062546730041504, "global_step": 422460, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.123840093612671, "global_step": 422461, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.082684278488159, "global_step": 422462, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0908148288726807, "global_step": 422463, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1745798587799072, "global_step": 422464, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.064023494720459, "global_step": 422465, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9710241556167603, "global_step": 422466, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0243189334869385, "global_step": 422467, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.090904951095581, "global_step": 422468, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1390511989593506, "global_step": 422469, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.2137813568115234, "global_step": 422470, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1005406379699707, "global_step": 422471, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.12813138961792, "global_step": 422472, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1592910289764404, "global_step": 422473, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.034174680709839, "global_step": 422474, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.104872465133667, "global_step": 422475, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.184131622314453, "global_step": 422476, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0982019901275635, "global_step": 422477, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1205742359161377, "global_step": 422478, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9840245246887207, "global_step": 422479, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.132075548171997, "global_step": 422480, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.079681873321533, "global_step": 422481, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0269157886505127, "global_step": 422482, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.015331268310547, "global_step": 422483, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1096978187561035, "global_step": 422484, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.093700408935547, "global_step": 422485, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0904910564422607, "global_step": 422486, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1530816555023193, "global_step": 422487, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0072946548461914, "global_step": 422488, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.091273069381714, "global_step": 422489, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0707311630249023, "global_step": 422490, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1592862606048584, "global_step": 422491, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1143124103546143, "global_step": 422492, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.974245548248291, "global_step": 422493, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.200373649597168, "global_step": 422494, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.155067205429077, "global_step": 422495, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0970354080200195, "global_step": 422496, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.145908832550049, "global_step": 422497, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.091278314590454, "global_step": 422498, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0708107948303223, "global_step": 422499, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.130861520767212, "global_step": 422500, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.043766498565674, "global_step": 422501, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.008141040802002, "global_step": 422502, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0271549224853516, "global_step": 422503, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0973970890045166, "global_step": 422504, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.142521858215332, "global_step": 422505, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1486353874206543, "global_step": 422506, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.146878719329834, "global_step": 422507, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.065079927444458, "global_step": 422508, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1237311363220215, "global_step": 422509, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.01906681060791, "global_step": 422510, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0920498371124268, "global_step": 422511, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.155538558959961, "global_step": 422512, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.088151693344116, "global_step": 422513, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1057660579681396, "global_step": 422514, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.12906813621521, "global_step": 422515, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.16857647895813, "global_step": 422516, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.138549327850342, "global_step": 422517, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1137795448303223, "global_step": 422518, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.104539394378662, "global_step": 422519, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1449058055877686, "global_step": 422520, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.101198196411133, "global_step": 422521, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.141678810119629, "global_step": 422522, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.146352767944336, "global_step": 422523, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0231740474700928, "global_step": 422524, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0989973545074463, "global_step": 422525, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1401877403259277, "global_step": 422526, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0836193561553955, "global_step": 422527, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0718746185302734, "global_step": 422528, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.083312511444092, "global_step": 422529, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1544556617736816, "global_step": 422530, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0622498989105225, "global_step": 422531, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0115511417388916, "global_step": 422532, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0844295024871826, "global_step": 422533, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0766525268554688, "global_step": 422534, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1271727085113525, "global_step": 422535, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0734593868255615, "global_step": 422536, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0789718627929688, "global_step": 422537, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.056713819503784, "global_step": 422538, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1217286586761475, "global_step": 422539, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.072709083557129, "global_step": 422540, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.060103178024292, "global_step": 422541, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.054273843765259, "global_step": 422542, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.11641001701355, "global_step": 422543, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0865416526794434, "global_step": 422544, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.017193555831909, "global_step": 422545, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1004018783569336, "global_step": 422546, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.108400344848633, "global_step": 422547, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1389968395233154, "global_step": 422548, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.082756280899048, "global_step": 422549, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.068469524383545, "global_step": 422550, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1588292121887207, "global_step": 422551, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.106100559234619, "global_step": 422552, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.114518165588379, "global_step": 422553, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1095662117004395, "global_step": 422554, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.070700168609619, "global_step": 422555, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.13932728767395, "global_step": 422556, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0692081451416016, "global_step": 422557, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1196956634521484, "global_step": 422558, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.096146583557129, "global_step": 422559, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.086071014404297, "global_step": 422560, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0801870822906494, "global_step": 422561, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.08095121383667, "global_step": 422562, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.091027021408081, "global_step": 422563, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.098170042037964, "global_step": 422564, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1121933460235596, "global_step": 422565, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.119434118270874, "global_step": 422566, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0839271545410156, "global_step": 422567, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.076012372970581, "global_step": 422568, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1127126216888428, "global_step": 422569, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.051584482192993, "global_step": 422570, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1122047901153564, "global_step": 422571, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0178136825561523, "global_step": 422572, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0130674839019775, "global_step": 422573, "epoch": 785, "lr": 5e-05}
{"train_loss": 1.9867703914642334, "global_step": 422574, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0749764442443848, "global_step": 422575, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1234936714172363, "global_step": 422576, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0686984062194824, "global_step": 422577, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0809543132781982, "global_step": 422578, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.102872133255005, "global_step": 422579, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1605911254882812, "global_step": 422580, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.099580764770508, "global_step": 422581, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.015972137451172, "global_step": 422582, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.158506155014038, "global_step": 422583, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0381486415863037, "global_step": 422584, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0567867755889893, "global_step": 422585, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0511720180511475, "global_step": 422586, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.109039783477783, "global_step": 422587, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.076917886734009, "global_step": 422588, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.149895191192627, "global_step": 422589, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.170792579650879, "global_step": 422590, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.044154644012451, "global_step": 422591, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.081732988357544, "global_step": 422592, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.058623790740967, "global_step": 422593, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1471593379974365, "global_step": 422594, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0622570514678955, "global_step": 422595, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.042905330657959, "global_step": 422596, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0504558086395264, "global_step": 422597, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.106001615524292, "global_step": 422598, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0462753772735596, "global_step": 422599, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1252963542938232, "global_step": 422600, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0419247150421143, "global_step": 422601, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.108191728591919, "global_step": 422602, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0491280555725098, "global_step": 422603, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0738282203674316, "global_step": 422604, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0229837894439697, "global_step": 422605, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.068587064743042, "global_step": 422606, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0649020671844482, "global_step": 422607, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1424877643585205, "global_step": 422608, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.048445463180542, "global_step": 422609, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.051858901977539, "global_step": 422610, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.10988450050354, "global_step": 422611, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.027501106262207, "global_step": 422612, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.061371326446533, "global_step": 422613, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0999221801757812, "global_step": 422614, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.0970053672790527, "global_step": 422615, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.086845636367798, "global_step": 422616, "epoch": 785, "lr": 5e-05}
{"train_loss": 2.1190168857574463, "global_step": 422617, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0903873443603516, "global_step": 422618, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.111513376235962, "global_step": 422619, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0648317337036133, "global_step": 422620, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0647222995758057, "global_step": 422621, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9492602348327637, "global_step": 422622, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0479238033294678, "global_step": 422623, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0120108127593994, "global_step": 422624, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.095445394515991, "global_step": 422625, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0232272148132324, "global_step": 422626, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1391217708587646, "global_step": 422627, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.048893928527832, "global_step": 422628, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0557076930999756, "global_step": 422629, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.067005157470703, "global_step": 422630, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0411970615386963, "global_step": 422631, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0378060340881348, "global_step": 422632, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0948054790496826, "global_step": 422633, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0064172744750977, "global_step": 422634, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0220754146575928, "global_step": 422635, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0695669651031494, "global_step": 422636, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.052298069000244, "global_step": 422637, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.118029832839966, "global_step": 422638, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0119240283966064, "global_step": 422639, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0809195041656494, "global_step": 422640, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.025552272796631, "global_step": 422641, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0692687034606934, "global_step": 422642, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0768511295318604, "global_step": 422643, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0751328468322754, "global_step": 422644, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0145373344421387, "global_step": 422645, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.096008062362671, "global_step": 422646, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.121319532394409, "global_step": 422647, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.068310499191284, "global_step": 422648, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1138479709625244, "global_step": 422649, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0995395183563232, "global_step": 422650, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0333216190338135, "global_step": 422651, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9777024984359741, "global_step": 422652, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.113419532775879, "global_step": 422653, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.022890567779541, "global_step": 422654, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.140180826187134, "global_step": 422655, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.034508228302002, "global_step": 422656, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.099257707595825, "global_step": 422657, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.109856128692627, "global_step": 422658, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0886919498443604, "global_step": 422659, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0526840686798096, "global_step": 422660, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0350522994995117, "global_step": 422661, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0372300148010254, "global_step": 422662, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0031566619873047, "global_step": 422663, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0900089740753174, "global_step": 422664, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0109972953796387, "global_step": 422665, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.029442310333252, "global_step": 422666, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0998547077178955, "global_step": 422667, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.084646224975586, "global_step": 422668, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.123265027999878, "global_step": 422669, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.160933494567871, "global_step": 422670, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0791983604431152, "global_step": 422671, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0107359886169434, "global_step": 422672, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0214343070983887, "global_step": 422673, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.125359535217285, "global_step": 422674, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9805947542190552, "global_step": 422675, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1655755043029785, "global_step": 422676, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.064345359802246, "global_step": 422677, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0946877002716064, "global_step": 422678, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9983018636703491, "global_step": 422679, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.989987850189209, "global_step": 422680, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0922558307647705, "global_step": 422681, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0942153930664062, "global_step": 422682, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.060875654220581, "global_step": 422683, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1677112579345703, "global_step": 422684, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0444138050079346, "global_step": 422685, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0601401329040527, "global_step": 422686, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.156552791595459, "global_step": 422687, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0467658042907715, "global_step": 422688, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1160356998443604, "global_step": 422689, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1476762294769287, "global_step": 422690, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0561094284057617, "global_step": 422691, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1452245712280273, "global_step": 422692, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.976690649986267, "global_step": 422693, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0589921474456787, "global_step": 422694, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0336391925811768, "global_step": 422695, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.130194664001465, "global_step": 422696, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.109917163848877, "global_step": 422697, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0630319118499756, "global_step": 422698, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0744175910949707, "global_step": 422699, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.084519386291504, "global_step": 422700, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0442562103271484, "global_step": 422701, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.104919672012329, "global_step": 422702, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.071300745010376, "global_step": 422703, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0565497875213623, "global_step": 422704, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.047210454940796, "global_step": 422705, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.050443649291992, "global_step": 422706, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.056802749633789, "global_step": 422707, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.04185152053833, "global_step": 422708, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9883872270584106, "global_step": 422709, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.086543560028076, "global_step": 422710, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1210289001464844, "global_step": 422711, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0702500343322754, "global_step": 422712, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.053122043609619, "global_step": 422713, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0603623390197754, "global_step": 422714, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0476067066192627, "global_step": 422715, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0937933921813965, "global_step": 422716, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9955555200576782, "global_step": 422717, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0327765941619873, "global_step": 422718, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0909392833709717, "global_step": 422719, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.062178134918213, "global_step": 422720, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1304166316986084, "global_step": 422721, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.10154128074646, "global_step": 422722, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0616848468780518, "global_step": 422723, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.131403923034668, "global_step": 422724, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0531809329986572, "global_step": 422725, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.08225154876709, "global_step": 422726, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0312066078186035, "global_step": 422727, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.136805534362793, "global_step": 422728, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.020465850830078, "global_step": 422729, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.108778476715088, "global_step": 422730, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0272183418273926, "global_step": 422731, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.139943838119507, "global_step": 422732, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.183440685272217, "global_step": 422733, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1659095287323, "global_step": 422734, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0630533695220947, "global_step": 422735, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1067750453948975, "global_step": 422736, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.034264326095581, "global_step": 422737, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.076725482940674, "global_step": 422738, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.065368175506592, "global_step": 422739, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1342365741729736, "global_step": 422740, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.168377637863159, "global_step": 422741, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.101015329360962, "global_step": 422742, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.061475992202759, "global_step": 422743, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1488842964172363, "global_step": 422744, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0188145637512207, "global_step": 422745, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0645625591278076, "global_step": 422746, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.123706579208374, "global_step": 422747, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.141742706298828, "global_step": 422748, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1230626106262207, "global_step": 422749, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0744311809539795, "global_step": 422750, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.130629062652588, "global_step": 422751, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1872360706329346, "global_step": 422752, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.081343173980713, "global_step": 422753, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0791664123535156, "global_step": 422754, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0986626148223877, "global_step": 422755, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.093965768814087, "global_step": 422756, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1770362854003906, "global_step": 422757, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0977208614349365, "global_step": 422758, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1220450401306152, "global_step": 422759, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1235713958740234, "global_step": 422760, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0662167072296143, "global_step": 422761, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0168135166168213, "global_step": 422762, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1076784133911133, "global_step": 422763, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0619826316833496, "global_step": 422764, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0530781745910645, "global_step": 422765, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1177279949188232, "global_step": 422766, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0330445766448975, "global_step": 422767, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.098057508468628, "global_step": 422768, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.212775707244873, "global_step": 422769, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1821587085723877, "global_step": 422770, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1163930892944336, "global_step": 422771, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0227737426757812, "global_step": 422772, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0693678855895996, "global_step": 422773, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0915377140045166, "global_step": 422774, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.04626202583313, "global_step": 422775, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0956616401672363, "global_step": 422776, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.116312026977539, "global_step": 422777, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.071397304534912, "global_step": 422778, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.044313430786133, "global_step": 422779, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.047475814819336, "global_step": 422780, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.116260051727295, "global_step": 422781, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0706167221069336, "global_step": 422782, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.059499740600586, "global_step": 422783, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.07784104347229, "global_step": 422784, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.102069616317749, "global_step": 422785, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.041790008544922, "global_step": 422786, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1431710720062256, "global_step": 422787, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1020917892456055, "global_step": 422788, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.056041955947876, "global_step": 422789, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1414308547973633, "global_step": 422790, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.113201379776001, "global_step": 422791, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0366268157958984, "global_step": 422792, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1725614070892334, "global_step": 422793, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.090005397796631, "global_step": 422794, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.050823926925659, "global_step": 422795, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1605470180511475, "global_step": 422796, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0372252464294434, "global_step": 422797, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9835010766983032, "global_step": 422798, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.10178804397583, "global_step": 422799, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.017517566680908, "global_step": 422800, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.069727897644043, "global_step": 422801, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.131821632385254, "global_step": 422802, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.088101863861084, "global_step": 422803, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.2042505741119385, "global_step": 422804, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0534422397613525, "global_step": 422805, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0528953075408936, "global_step": 422806, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.06057071685791, "global_step": 422807, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0189170837402344, "global_step": 422808, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.153580665588379, "global_step": 422809, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.06422758102417, "global_step": 422810, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0886588096618652, "global_step": 422811, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.968605399131775, "global_step": 422812, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0312771797180176, "global_step": 422813, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1011011600494385, "global_step": 422814, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1418230533599854, "global_step": 422815, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0482680797576904, "global_step": 422816, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0956103801727295, "global_step": 422817, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0626144409179688, "global_step": 422818, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0597174167633057, "global_step": 422819, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.128199338912964, "global_step": 422820, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0904085636138916, "global_step": 422821, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.129793643951416, "global_step": 422822, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.085630416870117, "global_step": 422823, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.077526330947876, "global_step": 422824, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1084752082824707, "global_step": 422825, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.112546443939209, "global_step": 422826, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.024212598800659, "global_step": 422827, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.083710193634033, "global_step": 422828, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.2081379890441895, "global_step": 422829, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.128774404525757, "global_step": 422830, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.022974729537964, "global_step": 422831, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0649778842926025, "global_step": 422832, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.145338773727417, "global_step": 422833, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1386187076568604, "global_step": 422834, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0776736736297607, "global_step": 422835, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0450735092163086, "global_step": 422836, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0567805767059326, "global_step": 422837, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1519322395324707, "global_step": 422838, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9622864723205566, "global_step": 422839, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.106616735458374, "global_step": 422840, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1089987754821777, "global_step": 422841, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.194362163543701, "global_step": 422842, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1122429370880127, "global_step": 422843, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.048356294631958, "global_step": 422844, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.112421751022339, "global_step": 422845, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.010955333709717, "global_step": 422846, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1619839668273926, "global_step": 422847, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0905792713165283, "global_step": 422848, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1152267456054688, "global_step": 422849, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1845338344573975, "global_step": 422850, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9947261810302734, "global_step": 422851, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0374596118927, "global_step": 422852, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.049703598022461, "global_step": 422853, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.032731771469116, "global_step": 422854, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0091450214385986, "global_step": 422855, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0086774826049805, "global_step": 422856, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1543333530426025, "global_step": 422857, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.039778470993042, "global_step": 422858, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9956022500991821, "global_step": 422859, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1039609909057617, "global_step": 422860, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0779192447662354, "global_step": 422861, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1168079376220703, "global_step": 422862, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.097912073135376, "global_step": 422863, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1099114418029785, "global_step": 422864, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9641973972320557, "global_step": 422865, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9852968454360962, "global_step": 422866, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.106093168258667, "global_step": 422867, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0834617614746094, "global_step": 422868, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1172688007354736, "global_step": 422869, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0948972702026367, "global_step": 422870, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1346802711486816, "global_step": 422871, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.049656867980957, "global_step": 422872, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.134089231491089, "global_step": 422873, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1105191707611084, "global_step": 422874, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0748825073242188, "global_step": 422875, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0914833545684814, "global_step": 422876, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.064992666244507, "global_step": 422877, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.084907054901123, "global_step": 422878, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1177778244018555, "global_step": 422879, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0874290466308594, "global_step": 422880, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.039811611175537, "global_step": 422881, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9382346868515015, "global_step": 422882, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1789164543151855, "global_step": 422883, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.043452262878418, "global_step": 422884, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1355223655700684, "global_step": 422885, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.154632806777954, "global_step": 422886, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.099785566329956, "global_step": 422887, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1150319576263428, "global_step": 422888, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0778281688690186, "global_step": 422889, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.03303861618042, "global_step": 422890, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.128743886947632, "global_step": 422891, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9933277368545532, "global_step": 422892, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1193251609802246, "global_step": 422893, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0813043117523193, "global_step": 422894, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0311930179595947, "global_step": 422895, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0609302520751953, "global_step": 422896, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.014618158340454, "global_step": 422897, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.054147720336914, "global_step": 422898, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.998234748840332, "global_step": 422899, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1217167377471924, "global_step": 422900, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1603872776031494, "global_step": 422901, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1254935264587402, "global_step": 422902, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.028621196746826, "global_step": 422903, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9568870067596436, "global_step": 422904, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0821073055267334, "global_step": 422905, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0044045448303223, "global_step": 422906, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.140291213989258, "global_step": 422907, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0593714714050293, "global_step": 422908, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0911405086517334, "global_step": 422909, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0736637115478516, "global_step": 422910, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0603408813476562, "global_step": 422911, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0414936542510986, "global_step": 422912, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0815200805664062, "global_step": 422913, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.067533493041992, "global_step": 422914, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.050778388977051, "global_step": 422915, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0881946086883545, "global_step": 422916, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.064317226409912, "global_step": 422917, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.042698621749878, "global_step": 422918, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.012570858001709, "global_step": 422919, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1070046424865723, "global_step": 422920, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0557198524475098, "global_step": 422921, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.033257246017456, "global_step": 422922, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0693349838256836, "global_step": 422923, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.079183340072632, "global_step": 422924, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.086235761642456, "global_step": 422925, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0983221530914307, "global_step": 422926, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.092366933822632, "global_step": 422927, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1226658821105957, "global_step": 422928, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.166335105895996, "global_step": 422929, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1230313777923584, "global_step": 422930, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0255727767944336, "global_step": 422931, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.133107900619507, "global_step": 422932, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0414936542510986, "global_step": 422933, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.16156005859375, "global_step": 422934, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.088548183441162, "global_step": 422935, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.091677665710449, "global_step": 422936, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.090737819671631, "global_step": 422937, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0956573486328125, "global_step": 422938, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.000720739364624, "global_step": 422939, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.033708333969116, "global_step": 422940, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.106055498123169, "global_step": 422941, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9803251028060913, "global_step": 422942, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.081632137298584, "global_step": 422943, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1755588054656982, "global_step": 422944, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1406092643737793, "global_step": 422945, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.142951011657715, "global_step": 422946, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0791714191436768, "global_step": 422947, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1075010299682617, "global_step": 422948, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1412506103515625, "global_step": 422949, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1164133548736572, "global_step": 422950, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0379204750061035, "global_step": 422951, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1623339653015137, "global_step": 422952, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0166702270507812, "global_step": 422953, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0676887035369873, "global_step": 422954, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.142817974090576, "global_step": 422955, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1094863414764404, "global_step": 422956, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0223405361175537, "global_step": 422957, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1234047412872314, "global_step": 422958, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.117155075073242, "global_step": 422959, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1460249423980713, "global_step": 422960, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0209500789642334, "global_step": 422961, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0566585063934326, "global_step": 422962, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.069559097290039, "global_step": 422963, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.169215440750122, "global_step": 422964, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.052215099334717, "global_step": 422965, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1649727821350098, "global_step": 422966, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0491437911987305, "global_step": 422967, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.159130811691284, "global_step": 422968, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1257190704345703, "global_step": 422969, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.003399133682251, "global_step": 422970, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1020407676696777, "global_step": 422971, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.075734853744507, "global_step": 422972, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.085216760635376, "global_step": 422973, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1022942066192627, "global_step": 422974, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.058950185775757, "global_step": 422975, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9512946605682373, "global_step": 422976, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.132277011871338, "global_step": 422977, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.149000883102417, "global_step": 422978, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.033478021621704, "global_step": 422979, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0597028732299805, "global_step": 422980, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0303783416748047, "global_step": 422981, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.2242372035980225, "global_step": 422982, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1255509853363037, "global_step": 422983, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1130802631378174, "global_step": 422984, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.181591510772705, "global_step": 422985, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.099956512451172, "global_step": 422986, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0119640827178955, "global_step": 422987, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.096327304840088, "global_step": 422988, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.029529333114624, "global_step": 422989, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.074704885482788, "global_step": 422990, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.994600772857666, "global_step": 422991, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.159435749053955, "global_step": 422992, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.03055739402771, "global_step": 422993, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0212581157684326, "global_step": 422994, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.08547306060791, "global_step": 422995, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.064995527267456, "global_step": 422996, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.032445192337036, "global_step": 422997, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.097721576690674, "global_step": 422998, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.143012523651123, "global_step": 422999, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.075763463973999, "global_step": 423000, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.067570686340332, "global_step": 423001, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0704851150512695, "global_step": 423002, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0323095321655273, "global_step": 423003, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9803624153137207, "global_step": 423004, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.997591257095337, "global_step": 423005, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0800318717956543, "global_step": 423006, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.01246976852417, "global_step": 423007, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.006413221359253, "global_step": 423008, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.075542449951172, "global_step": 423009, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.003962516784668, "global_step": 423010, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.017537832260132, "global_step": 423011, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0655040740966797, "global_step": 423012, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.089475393295288, "global_step": 423013, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0925965309143066, "global_step": 423014, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1765215396881104, "global_step": 423015, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1380109786987305, "global_step": 423016, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0539069175720215, "global_step": 423017, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1642003059387207, "global_step": 423018, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1457877159118652, "global_step": 423019, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0972115993499756, "global_step": 423020, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.115568161010742, "global_step": 423021, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1248064041137695, "global_step": 423022, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0916311740875244, "global_step": 423023, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9300501346588135, "global_step": 423024, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.044578790664673, "global_step": 423025, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0489208698272705, "global_step": 423026, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9694000482559204, "global_step": 423027, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.035647392272949, "global_step": 423028, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0330076217651367, "global_step": 423029, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1232945919036865, "global_step": 423030, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.088355302810669, "global_step": 423031, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9750776290893555, "global_step": 423032, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0583369731903076, "global_step": 423033, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0982820987701416, "global_step": 423034, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.110745429992676, "global_step": 423035, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9889047145843506, "global_step": 423036, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.041653871536255, "global_step": 423037, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0614511966705322, "global_step": 423038, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0880658626556396, "global_step": 423039, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0570316314697266, "global_step": 423040, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0488779544830322, "global_step": 423041, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0959701538085938, "global_step": 423042, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.141038656234741, "global_step": 423043, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0024917125701904, "global_step": 423044, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1162109375, "global_step": 423045, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.010732889175415, "global_step": 423046, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0956907272338867, "global_step": 423047, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1026928424835205, "global_step": 423048, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1348018646240234, "global_step": 423049, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0571022033691406, "global_step": 423050, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0652003288269043, "global_step": 423051, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.065903425216675, "global_step": 423052, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.161189079284668, "global_step": 423053, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.096407175064087, "global_step": 423054, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0487937927246094, "global_step": 423055, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.188185691833496, "global_step": 423056, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0982649326324463, "global_step": 423057, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0356202125549316, "global_step": 423058, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9986002445220947, "global_step": 423059, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0562820434570312, "global_step": 423060, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.081165075302124, "global_step": 423061, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0154483318328857, "global_step": 423062, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0269882678985596, "global_step": 423063, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0460596084594727, "global_step": 423064, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0195178985595703, "global_step": 423065, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.071737289428711, "global_step": 423066, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0436689853668213, "global_step": 423067, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0812582969665527, "global_step": 423068, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0403692722320557, "global_step": 423069, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.186995267868042, "global_step": 423070, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0318472385406494, "global_step": 423071, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.049985647201538, "global_step": 423072, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1059184074401855, "global_step": 423073, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.101142168045044, "global_step": 423074, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.092341661453247, "global_step": 423075, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.107793092727661, "global_step": 423076, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.030015707015991, "global_step": 423077, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0974349975585938, "global_step": 423078, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.001772403717041, "global_step": 423079, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0402512550354004, "global_step": 423080, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.112858772277832, "global_step": 423081, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0307087898254395, "global_step": 423082, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1438441276550293, "global_step": 423083, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1633493900299072, "global_step": 423084, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.034972906112671, "global_step": 423085, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0678892135620117, "global_step": 423086, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.151893377304077, "global_step": 423087, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.151672840118408, "global_step": 423088, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0841472148895264, "global_step": 423089, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.013563394546509, "global_step": 423090, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.087437629699707, "global_step": 423091, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1337814331054688, "global_step": 423092, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0681283473968506, "global_step": 423093, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0945749282836914, "global_step": 423094, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9985939264297485, "global_step": 423095, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.051300287246704, "global_step": 423096, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1415159702301025, "global_step": 423097, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.067497730255127, "global_step": 423098, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.169456958770752, "global_step": 423099, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1305313110351562, "global_step": 423100, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1617157459259033, "global_step": 423101, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1353819370269775, "global_step": 423102, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.12861704826355, "global_step": 423103, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0628063678741455, "global_step": 423104, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1367604732513428, "global_step": 423105, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0823872089385986, "global_step": 423106, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0079410076141357, "global_step": 423107, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0547006130218506, "global_step": 423108, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0868186950683594, "global_step": 423109, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0920488834381104, "global_step": 423110, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.117095470428467, "global_step": 423111, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0862340927124023, "global_step": 423112, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.05954909324646, "global_step": 423113, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.208915948867798, "global_step": 423114, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0459330081939697, "global_step": 423115, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1312339305877686, "global_step": 423116, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.122770309448242, "global_step": 423117, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1535589694976807, "global_step": 423118, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.2096989154815674, "global_step": 423119, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.14095139503479, "global_step": 423120, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0370640754699707, "global_step": 423121, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0984699726104736, "global_step": 423122, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.081648826599121, "global_step": 423123, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.032794713973999, "global_step": 423124, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1911964416503906, "global_step": 423125, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.065371513366699, "global_step": 423126, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1417195796966553, "global_step": 423127, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.124392032623291, "global_step": 423128, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.123750686645508, "global_step": 423129, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1438848972320557, "global_step": 423130, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0892767906188965, "global_step": 423131, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1162915229797363, "global_step": 423132, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0381290912628174, "global_step": 423133, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0630829334259033, "global_step": 423134, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.163369655609131, "global_step": 423135, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1056272983551025, "global_step": 423136, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.015284776687622, "global_step": 423137, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0493130683898926, "global_step": 423138, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.05985951423645, "global_step": 423139, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0914695262908936, "global_step": 423140, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.134594440460205, "global_step": 423141, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1055026054382324, "global_step": 423142, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.227426767349243, "global_step": 423143, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.15464448928833, "global_step": 423144, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.084683656692505, "global_step": 423145, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1068832874298096, "global_step": 423146, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.139097213745117, "global_step": 423147, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1653518676757812, "global_step": 423148, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.047166347503662, "global_step": 423149, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0695960521698, "global_step": 423150, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1116092205047607, "global_step": 423151, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1614065170288086, "global_step": 423152, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.049670696258545, "global_step": 423153, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.066725969314575, "global_step": 423154, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1934778690338135, "global_step": 423155, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.146735429763794, "global_step": 423156, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1478214263916016, "global_step": 423157, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1382007598876953, "global_step": 423158, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1226983070373535, "global_step": 423159, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1378726959228516, "global_step": 423160, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0808372497558594, "global_step": 423161, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.101316452026367, "global_step": 423162, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0941150188446045, "global_step": 423163, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.084599733352661, "global_step": 423164, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.074159622192383, "global_step": 423165, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.107215166091919, "global_step": 423166, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.144029378890991, "global_step": 423167, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.023155689239502, "global_step": 423168, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.128408908843994, "global_step": 423169, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1582682132720947, "global_step": 423170, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0633463859558105, "global_step": 423171, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1372928619384766, "global_step": 423172, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.086754083633423, "global_step": 423173, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1073505878448486, "global_step": 423174, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.105886220932007, "global_step": 423175, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1193203926086426, "global_step": 423176, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.149413824081421, "global_step": 423177, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9893444776535034, "global_step": 423178, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0275254249572754, "global_step": 423179, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0615134239196777, "global_step": 423180, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.007988929748535, "global_step": 423181, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.041151762008667, "global_step": 423182, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0815494060516357, "global_step": 423183, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0761098861694336, "global_step": 423184, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1293282508850098, "global_step": 423185, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0247914791107178, "global_step": 423186, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0581536293029785, "global_step": 423187, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9769669771194458, "global_step": 423188, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.075375556945801, "global_step": 423189, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.149512529373169, "global_step": 423190, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.101714611053467, "global_step": 423191, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1083827018737793, "global_step": 423192, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9996137619018555, "global_step": 423193, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.182335376739502, "global_step": 423194, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.107199192047119, "global_step": 423195, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.036491632461548, "global_step": 423196, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1007025241851807, "global_step": 423197, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.018118381500244, "global_step": 423198, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0360779762268066, "global_step": 423199, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0808916091918945, "global_step": 423200, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.098034620285034, "global_step": 423201, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1959784030914307, "global_step": 423202, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0330047607421875, "global_step": 423203, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.11321759223938, "global_step": 423204, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.082488536834717, "global_step": 423205, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.079984664916992, "global_step": 423206, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.15429949760437, "global_step": 423207, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1025264263153076, "global_step": 423208, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0666751861572266, "global_step": 423209, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0100257396698, "global_step": 423210, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1344921588897705, "global_step": 423211, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0587105751037598, "global_step": 423212, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0503809452056885, "global_step": 423213, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.11038875579834, "global_step": 423214, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9978952407836914, "global_step": 423215, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.046321392059326, "global_step": 423216, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.006697177886963, "global_step": 423217, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1658451557159424, "global_step": 423218, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.131481170654297, "global_step": 423219, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.155212163925171, "global_step": 423220, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.108976125717163, "global_step": 423221, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1317548751831055, "global_step": 423222, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.09004282951355, "global_step": 423223, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.051523208618164, "global_step": 423224, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0994315147399902, "global_step": 423225, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0779387950897217, "global_step": 423226, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0165297985076904, "global_step": 423227, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.992654800415039, "global_step": 423228, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.078486680984497, "global_step": 423229, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1701085567474365, "global_step": 423230, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0439579486846924, "global_step": 423231, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0839061737060547, "global_step": 423232, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.085686445236206, "global_step": 423233, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.056269884109497, "global_step": 423234, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.061224937438965, "global_step": 423235, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.07702898979187, "global_step": 423236, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1639413833618164, "global_step": 423237, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0423619747161865, "global_step": 423238, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1178982257843018, "global_step": 423239, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0628018379211426, "global_step": 423240, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.023143768310547, "global_step": 423241, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1988563537597656, "global_step": 423242, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.128300666809082, "global_step": 423243, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.063276767730713, "global_step": 423244, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0900964736938477, "global_step": 423245, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0941624641418457, "global_step": 423246, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.10347580909729, "global_step": 423247, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0709238052368164, "global_step": 423248, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0888447761535645, "global_step": 423249, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.095076560974121, "global_step": 423250, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.2012946605682373, "global_step": 423251, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0752975940704346, "global_step": 423252, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0571539402008057, "global_step": 423253, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.036892890930176, "global_step": 423254, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1166646480560303, "global_step": 423255, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0515389442443848, "global_step": 423256, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0648326873779297, "global_step": 423257, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.088700294494629, "global_step": 423258, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0683043003082275, "global_step": 423259, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0601654052734375, "global_step": 423260, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.161848545074463, "global_step": 423261, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.097224473953247, "global_step": 423262, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1210756301879883, "global_step": 423263, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0549917221069336, "global_step": 423264, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1529247760772705, "global_step": 423265, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.092909812927246, "global_step": 423266, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0893304347991943, "global_step": 423267, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.067356824874878, "global_step": 423268, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.034620761871338, "global_step": 423269, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.115078926086426, "global_step": 423270, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.2164528369903564, "global_step": 423271, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0872292518615723, "global_step": 423272, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.07702374458313, "global_step": 423273, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.997140884399414, "global_step": 423274, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0107858180999756, "global_step": 423275, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1218302249908447, "global_step": 423276, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0312070846557617, "global_step": 423277, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1159884929656982, "global_step": 423278, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.110105276107788, "global_step": 423279, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0653367042541504, "global_step": 423280, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0856988430023193, "global_step": 423281, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.113555908203125, "global_step": 423282, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.080436944961548, "global_step": 423283, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.130540609359741, "global_step": 423284, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.090115785598755, "global_step": 423285, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9835110902786255, "global_step": 423286, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1250836849212646, "global_step": 423287, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.978580117225647, "global_step": 423288, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.967261791229248, "global_step": 423289, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.091850757598877, "global_step": 423290, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1923935413360596, "global_step": 423291, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0350117683410645, "global_step": 423292, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0664420127868652, "global_step": 423293, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.050424098968506, "global_step": 423294, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0556344985961914, "global_step": 423295, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.128235340118408, "global_step": 423296, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.16726016998291, "global_step": 423297, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.093719720840454, "global_step": 423298, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.044969081878662, "global_step": 423299, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.132218360900879, "global_step": 423300, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1242170333862305, "global_step": 423301, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.109260082244873, "global_step": 423302, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.104792833328247, "global_step": 423303, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1605160236358643, "global_step": 423304, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.200443983078003, "global_step": 423305, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0936644077301025, "global_step": 423306, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0894737243652344, "global_step": 423307, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.058638095855713, "global_step": 423308, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.057343006134033, "global_step": 423309, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.097200870513916, "global_step": 423310, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.019374132156372, "global_step": 423311, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1401662826538086, "global_step": 423312, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1486737728118896, "global_step": 423313, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0546231269836426, "global_step": 423314, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.099515438079834, "global_step": 423315, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0877113342285156, "global_step": 423316, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.159618854522705, "global_step": 423317, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0163865089416504, "global_step": 423318, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0547094345092773, "global_step": 423319, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0817158222198486, "global_step": 423320, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0588769912719727, "global_step": 423321, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.045592784881592, "global_step": 423322, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0956645011901855, "global_step": 423323, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.057865619659424, "global_step": 423324, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1696486473083496, "global_step": 423325, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.065335512161255, "global_step": 423326, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.031327962875366, "global_step": 423327, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.143911123275757, "global_step": 423328, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.000734806060791, "global_step": 423329, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.153434991836548, "global_step": 423330, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0850329399108887, "global_step": 423331, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.2211191654205322, "global_step": 423332, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.00895357131958, "global_step": 423333, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1127405166625977, "global_step": 423334, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0280776023864746, "global_step": 423335, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.098553419113159, "global_step": 423336, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.023629903793335, "global_step": 423337, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.080087900161743, "global_step": 423338, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.007312059402466, "global_step": 423339, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1593406200408936, "global_step": 423340, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1201698780059814, "global_step": 423341, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.062952756881714, "global_step": 423342, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0445704460144043, "global_step": 423343, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1047732830047607, "global_step": 423344, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.051269054412842, "global_step": 423345, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.095336675643921, "global_step": 423346, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0727760791778564, "global_step": 423347, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0717928409576416, "global_step": 423348, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1030678749084473, "global_step": 423349, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.102400541305542, "global_step": 423350, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.077920913696289, "global_step": 423351, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.020080327987671, "global_step": 423352, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.045137643814087, "global_step": 423353, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.11165714263916, "global_step": 423354, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.068772077560425, "global_step": 423355, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0555765628814697, "global_step": 423356, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1766207218170166, "global_step": 423357, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.073166608810425, "global_step": 423358, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.107222080230713, "global_step": 423359, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1211023330688477, "global_step": 423360, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0487380027770996, "global_step": 423361, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.081364870071411, "global_step": 423362, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0727593898773193, "global_step": 423363, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0539491176605225, "global_step": 423364, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.027726411819458, "global_step": 423365, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0756704807281494, "global_step": 423366, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.052103042602539, "global_step": 423367, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.103804588317871, "global_step": 423368, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0714821815490723, "global_step": 423369, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.051772117614746, "global_step": 423370, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.073476791381836, "global_step": 423371, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1393771171569824, "global_step": 423372, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.060699224472046, "global_step": 423373, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.2132434844970703, "global_step": 423374, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9588488340377808, "global_step": 423375, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0608839988708496, "global_step": 423376, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.187749147415161, "global_step": 423377, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.186624050140381, "global_step": 423378, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.087747097015381, "global_step": 423379, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0513973236083984, "global_step": 423380, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1278862953186035, "global_step": 423381, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0616061687469482, "global_step": 423382, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1864964962005615, "global_step": 423383, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9698585271835327, "global_step": 423384, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0205578804016113, "global_step": 423385, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0304229259490967, "global_step": 423386, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.129650115966797, "global_step": 423387, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.092162609100342, "global_step": 423388, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.115452527999878, "global_step": 423389, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0506677627563477, "global_step": 423390, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.133509874343872, "global_step": 423391, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.162012815475464, "global_step": 423392, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.144266366958618, "global_step": 423393, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.054097890853882, "global_step": 423394, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.123213529586792, "global_step": 423395, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.050433874130249, "global_step": 423396, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.171506404876709, "global_step": 423397, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1823184490203857, "global_step": 423398, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0979819297790527, "global_step": 423399, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.130581855773926, "global_step": 423400, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0248963832855225, "global_step": 423401, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0967564582824707, "global_step": 423402, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.115018367767334, "global_step": 423403, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1785216331481934, "global_step": 423404, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.018101692199707, "global_step": 423405, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0825483798980713, "global_step": 423406, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.078416109085083, "global_step": 423407, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.088623285293579, "global_step": 423408, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0879294872283936, "global_step": 423409, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0645041465759277, "global_step": 423410, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0551722049713135, "global_step": 423411, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0989701747894287, "global_step": 423412, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0313446521759033, "global_step": 423413, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.21766996383667, "global_step": 423414, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.052061080932617, "global_step": 423415, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.067460060119629, "global_step": 423416, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.142538547515869, "global_step": 423417, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0853090286254883, "global_step": 423418, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.113837480545044, "global_step": 423419, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0884315967559814, "global_step": 423420, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.067060708999634, "global_step": 423421, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.131463050842285, "global_step": 423422, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.081805944442749, "global_step": 423423, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1843974590301514, "global_step": 423424, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.037947416305542, "global_step": 423425, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1679575443267822, "global_step": 423426, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0569891929626465, "global_step": 423427, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.039477825164795, "global_step": 423428, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.065809726715088, "global_step": 423429, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.155186176300049, "global_step": 423430, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.05643630027771, "global_step": 423431, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0453832149505615, "global_step": 423432, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.083767890930176, "global_step": 423433, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0859529972076416, "global_step": 423434, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1336917877197266, "global_step": 423435, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.082592487335205, "global_step": 423436, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1553056240081787, "global_step": 423437, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.988363265991211, "global_step": 423438, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1042745113372803, "global_step": 423439, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1182847023010254, "global_step": 423440, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.164870023727417, "global_step": 423441, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0992438793182373, "global_step": 423442, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0040414333343506, "global_step": 423443, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1595470905303955, "global_step": 423444, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0986013412475586, "global_step": 423445, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.078904867172241, "global_step": 423446, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0493600368499756, "global_step": 423447, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0805578231811523, "global_step": 423448, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.044039249420166, "global_step": 423449, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.06903076171875, "global_step": 423450, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.109995126724243, "global_step": 423451, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0802621841430664, "global_step": 423452, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.038074016571045, "global_step": 423453, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1489028930664062, "global_step": 423454, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1140458583831787, "global_step": 423455, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.08981990814209, "global_step": 423456, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.141544818878174, "global_step": 423457, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0983660221099854, "global_step": 423458, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.153522253036499, "global_step": 423459, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.027147054672241, "global_step": 423460, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0534369945526123, "global_step": 423461, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1138930320739746, "global_step": 423462, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.097773551940918, "global_step": 423463, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.156895399093628, "global_step": 423464, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0769753456115723, "global_step": 423465, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1027464866638184, "global_step": 423466, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.040213108062744, "global_step": 423467, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0077481269836426, "global_step": 423468, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0592031478881836, "global_step": 423469, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1333611011505127, "global_step": 423470, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.14835262298584, "global_step": 423471, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0884697437286377, "global_step": 423472, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.054992437362671, "global_step": 423473, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.065371036529541, "global_step": 423474, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.090790033340454, "global_step": 423475, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.084420919418335, "global_step": 423476, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.038831949234009, "global_step": 423477, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.105762481689453, "global_step": 423478, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.006206512451172, "global_step": 423479, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.206057071685791, "global_step": 423480, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.057466506958008, "global_step": 423481, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0661065578460693, "global_step": 423482, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.063056468963623, "global_step": 423483, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.040942668914795, "global_step": 423484, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.043285846710205, "global_step": 423485, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.172865390777588, "global_step": 423486, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.147712230682373, "global_step": 423487, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.181107997894287, "global_step": 423488, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.094026565551758, "global_step": 423489, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1204047203063965, "global_step": 423490, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.077927350997925, "global_step": 423491, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1332054138183594, "global_step": 423492, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0349631309509277, "global_step": 423493, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9980367422103882, "global_step": 423494, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.175586462020874, "global_step": 423495, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.125009298324585, "global_step": 423496, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.122239589691162, "global_step": 423497, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1177022457122803, "global_step": 423498, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.265308141708374, "global_step": 423499, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1564509868621826, "global_step": 423500, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1198015213012695, "global_step": 423501, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.120710849761963, "global_step": 423502, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1362221240997314, "global_step": 423503, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.042978286743164, "global_step": 423504, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0741124153137207, "global_step": 423505, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.2461955547332764, "global_step": 423506, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1490423679351807, "global_step": 423507, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.069197654724121, "global_step": 423508, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.127718687057495, "global_step": 423509, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.090857982635498, "global_step": 423510, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0870792865753174, "global_step": 423511, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.045893430709839, "global_step": 423512, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.103757381439209, "global_step": 423513, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0882294178009033, "global_step": 423514, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0241527557373047, "global_step": 423515, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0718631744384766, "global_step": 423516, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.049968957901001, "global_step": 423517, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.116469144821167, "global_step": 423518, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.140475034713745, "global_step": 423519, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1156179904937744, "global_step": 423520, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.005408525466919, "global_step": 423521, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0464508533477783, "global_step": 423522, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.065948009490967, "global_step": 423523, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1437737941741943, "global_step": 423524, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.066337823867798, "global_step": 423525, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1079201698303223, "global_step": 423526, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9950264692306519, "global_step": 423527, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.098799228668213, "global_step": 423528, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0896801948547363, "global_step": 423529, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1671104431152344, "global_step": 423530, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.09443998336792, "global_step": 423531, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.193240165710449, "global_step": 423532, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0686137676239014, "global_step": 423533, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.992394208908081, "global_step": 423534, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.055203437805176, "global_step": 423535, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1099984645843506, "global_step": 423536, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.07710337638855, "global_step": 423537, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.091311454772949, "global_step": 423538, "epoch": 786, "lr": 5e-05}
{"train_loss": 1.9804749488830566, "global_step": 423539, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.089207887649536, "global_step": 423540, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.030020236968994, "global_step": 423541, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.116694450378418, "global_step": 423542, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0510761737823486, "global_step": 423543, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.114919424057007, "global_step": 423544, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0426700115203857, "global_step": 423545, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.038374662399292, "global_step": 423546, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0689666271209717, "global_step": 423547, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0968918800354004, "global_step": 423548, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.077515125274658, "global_step": 423549, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1079156398773193, "global_step": 423550, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0741233825683594, "global_step": 423551, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0699539184570312, "global_step": 423552, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1731157302856445, "global_step": 423553, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0121796131134033, "global_step": 423554, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.114222288131714, "global_step": 423555, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1076810359954834, "global_step": 423556, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.08697509765625, "global_step": 423557, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.148838996887207, "global_step": 423558, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.190027952194214, "global_step": 423559, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0298094749450684, "global_step": 423560, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.060299873352051, "global_step": 423561, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0729198455810547, "global_step": 423562, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1027913093566895, "global_step": 423563, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0325775146484375, "global_step": 423564, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.195138454437256, "global_step": 423565, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.068345308303833, "global_step": 423566, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1067373752593994, "global_step": 423567, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.009800910949707, "global_step": 423568, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.076773166656494, "global_step": 423569, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1793155670166016, "global_step": 423570, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1083993911743164, "global_step": 423571, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.146219491958618, "global_step": 423572, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.133854389190674, "global_step": 423573, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0710039138793945, "global_step": 423574, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1834523677825928, "global_step": 423575, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1233038902282715, "global_step": 423576, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0765748023986816, "global_step": 423577, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1209187507629395, "global_step": 423578, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.140695571899414, "global_step": 423579, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.166214942932129, "global_step": 423580, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0745151042938232, "global_step": 423581, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.046764373779297, "global_step": 423582, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0905797481536865, "global_step": 423583, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.1394758224487305, "global_step": 423584, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.085634469985962, "global_step": 423585, "epoch": 786, "lr": 5e-05}
{"train_loss": 2.0577163696289062, "global_step": 423586, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9898713827133179, "global_step": 423587, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.068976402282715, "global_step": 423588, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.080087900161743, "global_step": 423589, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.069040060043335, "global_step": 423590, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.081613540649414, "global_step": 423591, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0356285572052, "global_step": 423592, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0903849601745605, "global_step": 423593, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1155881881713867, "global_step": 423594, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.115551710128784, "global_step": 423595, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1374573707580566, "global_step": 423596, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1237404346466064, "global_step": 423597, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.077910900115967, "global_step": 423598, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9618158340454102, "global_step": 423599, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.024076223373413, "global_step": 423600, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.138669490814209, "global_step": 423601, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.124711036682129, "global_step": 423602, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.094557046890259, "global_step": 423603, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1511216163635254, "global_step": 423604, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1656761169433594, "global_step": 423605, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.035404920578003, "global_step": 423606, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0804460048675537, "global_step": 423607, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.047774314880371, "global_step": 423608, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.063957452774048, "global_step": 423609, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.057258129119873, "global_step": 423610, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.030003547668457, "global_step": 423611, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0197787284851074, "global_step": 423612, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.132432460784912, "global_step": 423613, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.050936698913574, "global_step": 423614, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.083805561065674, "global_step": 423615, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.097956895828247, "global_step": 423616, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1218626499176025, "global_step": 423617, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1986083984375, "global_step": 423618, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0867323875427246, "global_step": 423619, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.088531017303467, "global_step": 423620, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.048278331756592, "global_step": 423621, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1380772590637207, "global_step": 423622, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.092334747314453, "global_step": 423623, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0298850536346436, "global_step": 423624, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.079944372177124, "global_step": 423625, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.994235873222351, "global_step": 423626, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0777952671051025, "global_step": 423627, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0762012004852295, "global_step": 423628, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0512242317199707, "global_step": 423629, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.036410093307495, "global_step": 423630, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.092393159866333, "global_step": 423631, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.071061372756958, "global_step": 423632, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1121253967285156, "global_step": 423633, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.078289747238159, "global_step": 423634, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1382346153259277, "global_step": 423635, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.012645721435547, "global_step": 423636, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.076660633087158, "global_step": 423637, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.060838460922241, "global_step": 423638, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.038761615753174, "global_step": 423639, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1164209842681885, "global_step": 423640, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0397770404815674, "global_step": 423641, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.08828067779541, "global_step": 423642, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.039846420288086, "global_step": 423643, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0721652507781982, "global_step": 423644, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.02017879486084, "global_step": 423645, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1174938678741455, "global_step": 423646, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0971786975860596, "global_step": 423647, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.071484088897705, "global_step": 423648, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1180694103240967, "global_step": 423649, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0379207134246826, "global_step": 423650, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.014799118041992, "global_step": 423651, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0234436988830566, "global_step": 423652, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1467440128326416, "global_step": 423653, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.987511396408081, "global_step": 423654, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0173611640930176, "global_step": 423655, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.064362049102783, "global_step": 423656, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0687198638916016, "global_step": 423657, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1190338134765625, "global_step": 423658, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0513269901275635, "global_step": 423659, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1614902019500732, "global_step": 423660, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0344736576080322, "global_step": 423661, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0585405826568604, "global_step": 423662, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.032719135284424, "global_step": 423663, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.075129747390747, "global_step": 423664, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0713577270507812, "global_step": 423665, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.121354579925537, "global_step": 423666, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.082202911376953, "global_step": 423667, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.075173854827881, "global_step": 423668, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1574606895446777, "global_step": 423669, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.120041608810425, "global_step": 423670, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9941662549972534, "global_step": 423671, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9620361328125, "global_step": 423672, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.072049140930176, "global_step": 423673, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0525782108306885, "global_step": 423674, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.107440233230591, "global_step": 423675, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0879220962524414, "global_step": 423676, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.060575485229492, "global_step": 423677, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.087906837463379, "global_step": 423678, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0880095958709717, "global_step": 423679, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.104452610015869, "global_step": 423680, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0444118976593018, "global_step": 423681, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1644272804260254, "global_step": 423682, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.090672731399536, "global_step": 423683, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1052215099334717, "global_step": 423684, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0364432334899902, "global_step": 423685, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1162636280059814, "global_step": 423686, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.144052028656006, "global_step": 423687, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.060309886932373, "global_step": 423688, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.05645489692688, "global_step": 423689, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.108184576034546, "global_step": 423690, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0110549926757812, "global_step": 423691, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.188739538192749, "global_step": 423692, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.088690996170044, "global_step": 423693, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.106489419937134, "global_step": 423694, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1283340454101562, "global_step": 423695, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.093475103378296, "global_step": 423696, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.099482774734497, "global_step": 423697, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.181342124938965, "global_step": 423698, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.078373908996582, "global_step": 423699, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.050767183303833, "global_step": 423700, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.127007007598877, "global_step": 423701, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1251087188720703, "global_step": 423702, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0362350940704346, "global_step": 423703, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0526933670043945, "global_step": 423704, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.040109157562256, "global_step": 423705, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1097304821014404, "global_step": 423706, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.049003839492798, "global_step": 423707, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0888397693634033, "global_step": 423708, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0462794303894043, "global_step": 423709, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.030221462249756, "global_step": 423710, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0763907432556152, "global_step": 423711, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9981658458709717, "global_step": 423712, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.089906930923462, "global_step": 423713, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.016831159591675, "global_step": 423714, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0840654373168945, "global_step": 423715, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0502021312713623, "global_step": 423716, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0952401161193848, "global_step": 423717, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.018319845199585, "global_step": 423718, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0642240047454834, "global_step": 423719, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0145263671875, "global_step": 423720, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.095869541168213, "global_step": 423721, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.080885171890259, "global_step": 423722, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9800972938537598, "global_step": 423723, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.095170497894287, "global_step": 423724, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0840201377868652, "global_step": 423725, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0832695960998535, "global_step": 423726, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1469314098358154, "global_step": 423727, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0178442001342773, "global_step": 423728, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.060450553894043, "global_step": 423729, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.14461088180542, "global_step": 423730, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0404810905456543, "global_step": 423731, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.07708477973938, "global_step": 423732, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1094367504119873, "global_step": 423733, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1006457805633545, "global_step": 423734, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1194052696228027, "global_step": 423735, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.047617197036743, "global_step": 423736, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.023993730545044, "global_step": 423737, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1011624336242676, "global_step": 423738, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0995547771453857, "global_step": 423739, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1327404975891113, "global_step": 423740, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1351895332336426, "global_step": 423741, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0306222438812256, "global_step": 423742, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0472922325134277, "global_step": 423743, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.198134183883667, "global_step": 423744, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.044935941696167, "global_step": 423745, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1494033336639404, "global_step": 423746, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.050215721130371, "global_step": 423747, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.13973331451416, "global_step": 423748, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1006343364715576, "global_step": 423749, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0562803745269775, "global_step": 423750, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0653135776519775, "global_step": 423751, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1522467136383057, "global_step": 423752, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1226983070373535, "global_step": 423753, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.060866594314575, "global_step": 423754, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.003100633621216, "global_step": 423755, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.14147686958313, "global_step": 423756, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.091365337371826, "global_step": 423757, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1010582447052, "global_step": 423758, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.115422487258911, "global_step": 423759, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.133244514465332, "global_step": 423760, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0454227924346924, "global_step": 423761, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.129091262817383, "global_step": 423762, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.139600992202759, "global_step": 423763, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.103529453277588, "global_step": 423764, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9865795373916626, "global_step": 423765, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1765048503875732, "global_step": 423766, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.088913917541504, "global_step": 423767, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.030073881149292, "global_step": 423768, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1165223121643066, "global_step": 423769, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1074283123016357, "global_step": 423770, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0972349643707275, "global_step": 423771, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1236791610717773, "global_step": 423772, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0090904235839844, "global_step": 423773, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.061164617538452, "global_step": 423774, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1489102840423584, "global_step": 423775, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1461715698242188, "global_step": 423776, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.138117790222168, "global_step": 423777, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.07318115234375, "global_step": 423778, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.12430739402771, "global_step": 423779, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1058526039123535, "global_step": 423780, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1069626808166504, "global_step": 423781, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0115814208984375, "global_step": 423782, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0234432220458984, "global_step": 423783, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0645639896392822, "global_step": 423784, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0943615436553955, "global_step": 423785, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0962331295013428, "global_step": 423786, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.166290283203125, "global_step": 423787, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.102250099182129, "global_step": 423788, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0905468463897705, "global_step": 423789, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.063359022140503, "global_step": 423790, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9519429206848145, "global_step": 423791, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.06532883644104, "global_step": 423792, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.07839035987854, "global_step": 423793, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.081143379211426, "global_step": 423794, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.145806312561035, "global_step": 423795, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1039674282073975, "global_step": 423796, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.043785333633423, "global_step": 423797, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.028917074203491, "global_step": 423798, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.017728328704834, "global_step": 423799, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0757858753204346, "global_step": 423800, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1071128845214844, "global_step": 423801, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.010183095932007, "global_step": 423802, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1272764205932617, "global_step": 423803, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0179762840270996, "global_step": 423804, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0907719135284424, "global_step": 423805, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.059190273284912, "global_step": 423806, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.045259714126587, "global_step": 423807, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0395846366882324, "global_step": 423808, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.137042284011841, "global_step": 423809, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.072075128555298, "global_step": 423810, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0457992553710938, "global_step": 423811, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.078674077987671, "global_step": 423812, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0313405990600586, "global_step": 423813, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9808337688446045, "global_step": 423814, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0964534282684326, "global_step": 423815, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1183855533599854, "global_step": 423816, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.028315544128418, "global_step": 423817, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.061551809310913, "global_step": 423818, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.115001916885376, "global_step": 423819, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.110352039337158, "global_step": 423820, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0757617950439453, "global_step": 423821, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.125208616256714, "global_step": 423822, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.032160997390747, "global_step": 423823, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0775277614593506, "global_step": 423824, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0783746242523193, "global_step": 423825, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.111754894256592, "global_step": 423826, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0089328289031982, "global_step": 423827, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.108429431915283, "global_step": 423828, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0807793140411377, "global_step": 423829, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.035796880722046, "global_step": 423830, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.151367664337158, "global_step": 423831, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1869115829467773, "global_step": 423832, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9953628778457642, "global_step": 423833, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1315085887908936, "global_step": 423834, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1274666786193848, "global_step": 423835, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0567455291748047, "global_step": 423836, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0655837059020996, "global_step": 423837, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.04567813873291, "global_step": 423838, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.081014633178711, "global_step": 423839, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0592503547668457, "global_step": 423840, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.151777982711792, "global_step": 423841, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0823564529418945, "global_step": 423842, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0896599292755127, "global_step": 423843, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.030758857727051, "global_step": 423844, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.127741575241089, "global_step": 423845, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.053527355194092, "global_step": 423846, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.105475425720215, "global_step": 423847, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0837461948394775, "global_step": 423848, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.075413703918457, "global_step": 423849, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0917437076568604, "global_step": 423850, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0933194160461426, "global_step": 423851, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.144056558609009, "global_step": 423852, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0877737998962402, "global_step": 423853, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.010157823562622, "global_step": 423854, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.122276782989502, "global_step": 423855, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0574562549591064, "global_step": 423856, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0869662761688232, "global_step": 423857, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.2002933025360107, "global_step": 423858, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1244454383850098, "global_step": 423859, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.135725736618042, "global_step": 423860, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1162595748901367, "global_step": 423861, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.083862543106079, "global_step": 423862, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0717809200286865, "global_step": 423863, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.037693738937378, "global_step": 423864, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.130115032196045, "global_step": 423865, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.108880043029785, "global_step": 423866, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.05383038520813, "global_step": 423867, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.027132034301758, "global_step": 423868, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1747264862060547, "global_step": 423869, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.074204206466675, "global_step": 423870, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.140026092529297, "global_step": 423871, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0884146690368652, "global_step": 423872, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0877182483673096, "global_step": 423873, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1197869777679443, "global_step": 423874, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1129841804504395, "global_step": 423875, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.073319911956787, "global_step": 423876, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.037247657775879, "global_step": 423877, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0334951877593994, "global_step": 423878, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.961126446723938, "global_step": 423879, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0419211387634277, "global_step": 423880, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.081406354904175, "global_step": 423881, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.091883659362793, "global_step": 423882, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.088113784790039, "global_step": 423883, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1256017684936523, "global_step": 423884, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1026458740234375, "global_step": 423885, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.128981113433838, "global_step": 423886, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0921902656555176, "global_step": 423887, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1046199798583984, "global_step": 423888, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.063084602355957, "global_step": 423889, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0425174236297607, "global_step": 423890, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0126450061798096, "global_step": 423891, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1173059940338135, "global_step": 423892, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.111990213394165, "global_step": 423893, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.042323589324951, "global_step": 423894, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.101426362991333, "global_step": 423895, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0508079528808594, "global_step": 423896, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0639398097991943, "global_step": 423897, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.060746908187866, "global_step": 423898, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.185652256011963, "global_step": 423899, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1968088150024414, "global_step": 423900, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0760204792022705, "global_step": 423901, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.10994291305542, "global_step": 423902, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.13421630859375, "global_step": 423903, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.049730062484741, "global_step": 423904, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9673866033554077, "global_step": 423905, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.087162971496582, "global_step": 423906, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1032087802886963, "global_step": 423907, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.129361867904663, "global_step": 423908, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.000877857208252, "global_step": 423909, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.018484115600586, "global_step": 423910, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1442947387695312, "global_step": 423911, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9832552671432495, "global_step": 423912, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.052670955657959, "global_step": 423913, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.110290050506592, "global_step": 423914, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.12017560005188, "global_step": 423915, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.036325216293335, "global_step": 423916, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1102709770202637, "global_step": 423917, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0728907585144043, "global_step": 423918, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0478837490081787, "global_step": 423919, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1646792888641357, "global_step": 423920, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0870046615600586, "global_step": 423921, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.173736572265625, "global_step": 423922, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0136194229125977, "global_step": 423923, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0481388568878174, "global_step": 423924, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1000845432281494, "global_step": 423925, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0664374828338623, "global_step": 423926, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1846938133239746, "global_step": 423927, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0423572063446045, "global_step": 423928, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.033914089202881, "global_step": 423929, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0704293251037598, "global_step": 423930, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0751819610595703, "global_step": 423931, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0568363666534424, "global_step": 423932, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0092287063598633, "global_step": 423933, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.091451406478882, "global_step": 423934, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.052311420440674, "global_step": 423935, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.084315299987793, "global_step": 423936, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.093426465988159, "global_step": 423937, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1255931854248047, "global_step": 423938, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9923536777496338, "global_step": 423939, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0534563064575195, "global_step": 423940, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0800278186798096, "global_step": 423941, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.103123664855957, "global_step": 423942, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.031285047531128, "global_step": 423943, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.090930223464966, "global_step": 423944, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.045376777648926, "global_step": 423945, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.101806879043579, "global_step": 423946, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.005373001098633, "global_step": 423947, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0490753650665283, "global_step": 423948, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0520505905151367, "global_step": 423949, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0846054553985596, "global_step": 423950, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0614371299743652, "global_step": 423951, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.066924810409546, "global_step": 423952, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.160597801208496, "global_step": 423953, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0682780742645264, "global_step": 423954, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1591596603393555, "global_step": 423955, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0935909748077393, "global_step": 423956, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.079713821411133, "global_step": 423957, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.131976842880249, "global_step": 423958, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9813305139541626, "global_step": 423959, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1136231422424316, "global_step": 423960, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0024988651275635, "global_step": 423961, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.112276792526245, "global_step": 423962, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0616233348846436, "global_step": 423963, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1364200115203857, "global_step": 423964, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0965795516967773, "global_step": 423965, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.115384817123413, "global_step": 423966, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0656678676605225, "global_step": 423967, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.2404870986938477, "global_step": 423968, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.143134117126465, "global_step": 423969, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1465296745300293, "global_step": 423970, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1045026779174805, "global_step": 423971, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0672547817230225, "global_step": 423972, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1364259719848633, "global_step": 423973, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.060333490371704, "global_step": 423974, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1145284175872803, "global_step": 423975, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.116729259490967, "global_step": 423976, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.219608783721924, "global_step": 423977, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.065014362335205, "global_step": 423978, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0869431495666504, "global_step": 423979, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0015904903411865, "global_step": 423980, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.079862117767334, "global_step": 423981, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.091430187225342, "global_step": 423982, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.083183526992798, "global_step": 423983, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1599879264831543, "global_step": 423984, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0790388584136963, "global_step": 423985, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.051924228668213, "global_step": 423986, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0729281902313232, "global_step": 423987, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.042668342590332, "global_step": 423988, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.033280849456787, "global_step": 423989, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0631189346313477, "global_step": 423990, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0313024520874023, "global_step": 423991, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.039240837097168, "global_step": 423992, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0845632553100586, "global_step": 423993, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1017301082611084, "global_step": 423994, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1464548110961914, "global_step": 423995, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.091351270675659, "global_step": 423996, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0900180339813232, "global_step": 423997, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.030851364135742, "global_step": 423998, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.076335906982422, "global_step": 423999, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0937142372131348, "global_step": 424000, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1929357051849365, "global_step": 424001, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0592477321624756, "global_step": 424002, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.182500123977661, "global_step": 424003, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0970818996429443, "global_step": 424004, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0416276454925537, "global_step": 424005, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.05549693107605, "global_step": 424006, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0375587940216064, "global_step": 424007, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0787079334259033, "global_step": 424008, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.134347438812256, "global_step": 424009, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1280295848846436, "global_step": 424010, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1454617977142334, "global_step": 424011, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.105414867401123, "global_step": 424012, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.113745927810669, "global_step": 424013, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.055194616317749, "global_step": 424014, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0809245109558105, "global_step": 424015, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.072620153427124, "global_step": 424016, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.06253719329834, "global_step": 424017, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.09830904006958, "global_step": 424018, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.044464111328125, "global_step": 424019, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0612680912017822, "global_step": 424020, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1112749576568604, "global_step": 424021, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.091122627258301, "global_step": 424022, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0645244121551514, "global_step": 424023, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0461723804473877, "global_step": 424024, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1213836669921875, "global_step": 424025, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1019201278686523, "global_step": 424026, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0637481212615967, "global_step": 424027, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.151684522628784, "global_step": 424028, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.11199688911438, "global_step": 424029, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.079709768295288, "global_step": 424030, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1160802841186523, "global_step": 424031, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.131638288497925, "global_step": 424032, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.2029712200164795, "global_step": 424033, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.104095458984375, "global_step": 424034, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.100905179977417, "global_step": 424035, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1109533309936523, "global_step": 424036, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0284197330474854, "global_step": 424037, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0794949531555176, "global_step": 424038, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0080339908599854, "global_step": 424039, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0440266132354736, "global_step": 424040, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0451512336730957, "global_step": 424041, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.089219331741333, "global_step": 424042, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0902442932128906, "global_step": 424043, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.089437484741211, "global_step": 424044, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1543595790863037, "global_step": 424045, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0350232124328613, "global_step": 424046, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1632325649261475, "global_step": 424047, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0191118717193604, "global_step": 424048, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.038677215576172, "global_step": 424049, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.05838680267334, "global_step": 424050, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0199432373046875, "global_step": 424051, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.104086399078369, "global_step": 424052, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.154405117034912, "global_step": 424053, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1412806510925293, "global_step": 424054, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0461528301239014, "global_step": 424055, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1714658737182617, "global_step": 424056, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1376750469207764, "global_step": 424057, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0198047161102295, "global_step": 424058, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0466387271881104, "global_step": 424059, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0731325149536133, "global_step": 424060, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.059671640396118, "global_step": 424061, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.112769365310669, "global_step": 424062, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.146980047225952, "global_step": 424063, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.045182943344116, "global_step": 424064, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0261478424072266, "global_step": 424065, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0542144775390625, "global_step": 424066, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.040678024291992, "global_step": 424067, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0784430503845215, "global_step": 424068, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0631227493286133, "global_step": 424069, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9833563566207886, "global_step": 424070, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0228703022003174, "global_step": 424071, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.101757049560547, "global_step": 424072, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.116250514984131, "global_step": 424073, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.062729597091675, "global_step": 424074, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1134560108184814, "global_step": 424075, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.113652467727661, "global_step": 424076, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.080462694168091, "global_step": 424077, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0092692375183105, "global_step": 424078, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0517094135284424, "global_step": 424079, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.156036376953125, "global_step": 424080, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0602548122406006, "global_step": 424081, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.116004467010498, "global_step": 424082, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0745272636413574, "global_step": 424083, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.110386848449707, "global_step": 424084, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.108059883117676, "global_step": 424085, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0448625087738037, "global_step": 424086, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.122547149658203, "global_step": 424087, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.053335666656494, "global_step": 424088, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1413841247558594, "global_step": 424089, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1114704608917236, "global_step": 424090, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.014660120010376, "global_step": 424091, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.08647084236145, "global_step": 424092, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.056471109390259, "global_step": 424093, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0348801612854004, "global_step": 424094, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9988789558410645, "global_step": 424095, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1071999073028564, "global_step": 424096, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0847949981689453, "global_step": 424097, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.138420581817627, "global_step": 424098, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0738182067871094, "global_step": 424099, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.129179000854492, "global_step": 424100, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1300461292266846, "global_step": 424101, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.073298454284668, "global_step": 424102, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1158907413482666, "global_step": 424103, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.138831377029419, "global_step": 424104, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1003313064575195, "global_step": 424105, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0832149982452393, "global_step": 424106, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1948776245117188, "global_step": 424107, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0872435569763184, "global_step": 424108, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.040600538253784, "global_step": 424109, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.023444414138794, "global_step": 424110, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0952658653259277, "global_step": 424111, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0976316928863525, "global_step": 424112, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.17402720451355, "global_step": 424113, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0243349075317383, "global_step": 424114, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.121715545654297, "global_step": 424115, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0604870319366455, "global_step": 424116, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0716161727905273, "global_step": 424117, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.099541664123535, "global_step": 424118, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.048247814178467, "global_step": 424119, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.138557195663452, "global_step": 424120, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0773324966430664, "global_step": 424121, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0437631607055664, "global_step": 424122, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0916621685028076, "global_step": 424123, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0790913105010986, "global_step": 424124, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0832557678222656, "global_step": 424125, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0560805797576904, "global_step": 424126, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1723875999450684, "global_step": 424127, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.124725818634033, "global_step": 424128, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.029987096786499, "global_step": 424129, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1900417804718018, "global_step": 424130, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0929367542266846, "global_step": 424131, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0640676021575928, "global_step": 424132, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.108513832092285, "global_step": 424133, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1035714149475098, "global_step": 424134, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.150761842727661, "global_step": 424135, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.067807197570801, "global_step": 424136, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.023955821990967, "global_step": 424137, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.117786169052124, "global_step": 424138, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1010351181030273, "global_step": 424139, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0785117149353027, "global_step": 424140, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.05648136138916, "global_step": 424141, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0367941856384277, "global_step": 424142, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0445945262908936, "global_step": 424143, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1340131759643555, "global_step": 424144, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.14992356300354, "global_step": 424145, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.114607095718384, "global_step": 424146, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0444700717926025, "global_step": 424147, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.070896863937378, "global_step": 424148, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.073636531829834, "global_step": 424149, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0516533851623535, "global_step": 424150, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.032863140106201, "global_step": 424151, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0737111568450928, "global_step": 424152, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0688161849975586, "global_step": 424153, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.125216484069824, "global_step": 424154, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.011840581893921, "global_step": 424155, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9886388778686523, "global_step": 424156, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0136587619781494, "global_step": 424157, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1646623611450195, "global_step": 424158, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1389412879943848, "global_step": 424159, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1020169258117676, "global_step": 424160, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9925453662872314, "global_step": 424161, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1075708866119385, "global_step": 424162, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1550846099853516, "global_step": 424163, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0830929279327393, "global_step": 424164, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1247079372406006, "global_step": 424165, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.055079221725464, "global_step": 424166, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.088837146759033, "global_step": 424167, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.2177345752716064, "global_step": 424168, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0944933891296387, "global_step": 424169, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.039971351623535, "global_step": 424170, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0515990257263184, "global_step": 424171, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.096467971801758, "global_step": 424172, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.045896053314209, "global_step": 424173, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9835155010223389, "global_step": 424174, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.094916343688965, "global_step": 424175, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.023223876953125, "global_step": 424176, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.2279767990112305, "global_step": 424177, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.121084213256836, "global_step": 424178, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0441019535064697, "global_step": 424179, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.152557849884033, "global_step": 424180, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1329994201660156, "global_step": 424181, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.039289951324463, "global_step": 424182, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.053807497024536, "global_step": 424183, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1452198028564453, "global_step": 424184, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.056469678878784, "global_step": 424185, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.087026596069336, "global_step": 424186, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.137770891189575, "global_step": 424187, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.088176727294922, "global_step": 424188, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.006354570388794, "global_step": 424189, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.030055046081543, "global_step": 424190, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1089296340942383, "global_step": 424191, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0849242210388184, "global_step": 424192, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1724274158477783, "global_step": 424193, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0827174186706543, "global_step": 424194, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.022667407989502, "global_step": 424195, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.083829402923584, "global_step": 424196, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9867842197418213, "global_step": 424197, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.106741189956665, "global_step": 424198, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.087739944458008, "global_step": 424199, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0518252849578857, "global_step": 424200, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0763208866119385, "global_step": 424201, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.079350233078003, "global_step": 424202, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0718812942504883, "global_step": 424203, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1474432945251465, "global_step": 424204, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1194863319396973, "global_step": 424205, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0892395973205566, "global_step": 424206, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.126911163330078, "global_step": 424207, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9996682405471802, "global_step": 424208, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1282570362091064, "global_step": 424209, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.015439987182617, "global_step": 424210, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1091580390930176, "global_step": 424211, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.125282049179077, "global_step": 424212, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.09316349029541, "global_step": 424213, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0940561294555664, "global_step": 424214, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1178040504455566, "global_step": 424215, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0394091606140137, "global_step": 424216, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.043053150177002, "global_step": 424217, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.093374729156494, "global_step": 424218, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0618247985839844, "global_step": 424219, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.037400484085083, "global_step": 424220, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.103867769241333, "global_step": 424221, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.038954973220825, "global_step": 424222, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.044717311859131, "global_step": 424223, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1058526039123535, "global_step": 424224, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1073014736175537, "global_step": 424225, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0996932983398438, "global_step": 424226, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1173152923583984, "global_step": 424227, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0586960315704346, "global_step": 424228, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.022447347640991, "global_step": 424229, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.049633741378784, "global_step": 424230, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.049391031265259, "global_step": 424231, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.166738271713257, "global_step": 424232, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1189558506011963, "global_step": 424233, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1229231357574463, "global_step": 424234, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.027712106704712, "global_step": 424235, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1642332077026367, "global_step": 424236, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1320714950561523, "global_step": 424237, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0654046535491943, "global_step": 424238, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0591940879821777, "global_step": 424239, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0708775520324707, "global_step": 424240, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0855703353881836, "global_step": 424241, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.047459363937378, "global_step": 424242, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0611581802368164, "global_step": 424243, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0356462001800537, "global_step": 424244, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1275901794433594, "global_step": 424245, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.102039337158203, "global_step": 424246, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0787999629974365, "global_step": 424247, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0561723709106445, "global_step": 424248, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.101560592651367, "global_step": 424249, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0340685844421387, "global_step": 424250, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0541601181030273, "global_step": 424251, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0211222171783447, "global_step": 424252, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.077467679977417, "global_step": 424253, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0155138969421387, "global_step": 424254, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0455780029296875, "global_step": 424255, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0692830085754395, "global_step": 424256, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.131040334701538, "global_step": 424257, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1103084087371826, "global_step": 424258, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0507194995880127, "global_step": 424259, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.082484483718872, "global_step": 424260, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1240756511688232, "global_step": 424261, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1245925426483154, "global_step": 424262, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0401265621185303, "global_step": 424263, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.071730613708496, "global_step": 424264, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1377556324005127, "global_step": 424265, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0611250400543213, "global_step": 424266, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0228428840637207, "global_step": 424267, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1288769245147705, "global_step": 424268, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0555684566497803, "global_step": 424269, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1580066680908203, "global_step": 424270, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0057241916656494, "global_step": 424271, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.146705389022827, "global_step": 424272, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1500840187072754, "global_step": 424273, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.103461742401123, "global_step": 424274, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1785895824432373, "global_step": 424275, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1237986087799072, "global_step": 424276, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.09462833404541, "global_step": 424277, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1087162494659424, "global_step": 424278, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1486620903015137, "global_step": 424279, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1684722900390625, "global_step": 424280, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.131230115890503, "global_step": 424281, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.067674160003662, "global_step": 424282, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0326380729675293, "global_step": 424283, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.032639503479004, "global_step": 424284, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1026599407196045, "global_step": 424285, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0986571311950684, "global_step": 424286, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1350700855255127, "global_step": 424287, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.036440134048462, "global_step": 424288, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1294522285461426, "global_step": 424289, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.064668893814087, "global_step": 424290, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.173322916030884, "global_step": 424291, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.141270875930786, "global_step": 424292, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.099752426147461, "global_step": 424293, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0769333839416504, "global_step": 424294, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0975089073181152, "global_step": 424295, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0620906352996826, "global_step": 424296, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1095659732818604, "global_step": 424297, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1446216106414795, "global_step": 424298, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.082834243774414, "global_step": 424299, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.065235137939453, "global_step": 424300, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1045045852661133, "global_step": 424301, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.164241075515747, "global_step": 424302, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.075423240661621, "global_step": 424303, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.122093677520752, "global_step": 424304, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.096658706665039, "global_step": 424305, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0678815841674805, "global_step": 424306, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.042330265045166, "global_step": 424307, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0461041927337646, "global_step": 424308, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.109778642654419, "global_step": 424309, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1243808269500732, "global_step": 424310, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0085089206695557, "global_step": 424311, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1231143474578857, "global_step": 424312, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1324994564056396, "global_step": 424313, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0873003005981445, "global_step": 424314, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.091759443283081, "global_step": 424315, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9962780475616455, "global_step": 424316, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.092501401901245, "global_step": 424317, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9646227359771729, "global_step": 424318, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1386878490448, "global_step": 424319, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.165158987045288, "global_step": 424320, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.096435070037842, "global_step": 424321, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0846033096313477, "global_step": 424322, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.023127317428589, "global_step": 424323, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0909366607666016, "global_step": 424324, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1434576511383057, "global_step": 424325, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.099085807800293, "global_step": 424326, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1348533630371094, "global_step": 424327, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0578789710998535, "global_step": 424328, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0438780784606934, "global_step": 424329, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.049475908279419, "global_step": 424330, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.148411989212036, "global_step": 424331, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1687586307525635, "global_step": 424332, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1486196517944336, "global_step": 424333, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1385791301727295, "global_step": 424334, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1319973468780518, "global_step": 424335, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9948618412017822, "global_step": 424336, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.140691041946411, "global_step": 424337, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1246683597564697, "global_step": 424338, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0667998790740967, "global_step": 424339, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1289024353027344, "global_step": 424340, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.066263198852539, "global_step": 424341, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1092641353607178, "global_step": 424342, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1289100646972656, "global_step": 424343, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.076854944229126, "global_step": 424344, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1092069149017334, "global_step": 424345, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0752217769622803, "global_step": 424346, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.14667010307312, "global_step": 424347, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.048881769180298, "global_step": 424348, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0578675270080566, "global_step": 424349, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1705245971679688, "global_step": 424350, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0173733234405518, "global_step": 424351, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.063326358795166, "global_step": 424352, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0470468997955322, "global_step": 424353, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.100950241088867, "global_step": 424354, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.11838698387146, "global_step": 424355, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1259748935699463, "global_step": 424356, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1377756595611572, "global_step": 424357, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1162161827087402, "global_step": 424358, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0773298740386963, "global_step": 424359, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0956413745880127, "global_step": 424360, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.089550018310547, "global_step": 424361, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1356585025787354, "global_step": 424362, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.160276412963867, "global_step": 424363, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1454381942749023, "global_step": 424364, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1445319652557373, "global_step": 424365, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1309523582458496, "global_step": 424366, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1215765476226807, "global_step": 424367, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.091326951980591, "global_step": 424368, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1629538536071777, "global_step": 424369, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0697343349456787, "global_step": 424370, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0130581855773926, "global_step": 424371, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0948646068573, "global_step": 424372, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0650370121002197, "global_step": 424373, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1228647232055664, "global_step": 424374, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0992238521575928, "global_step": 424375, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0263686180114746, "global_step": 424376, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9774097204208374, "global_step": 424377, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.181960105895996, "global_step": 424378, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.174691677093506, "global_step": 424379, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.119121551513672, "global_step": 424380, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1002426147460938, "global_step": 424381, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.087628126144409, "global_step": 424382, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0839152336120605, "global_step": 424383, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1521155834198, "global_step": 424384, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0794286727905273, "global_step": 424385, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.121918201446533, "global_step": 424386, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0348525047302246, "global_step": 424387, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0104918479919434, "global_step": 424388, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1011314392089844, "global_step": 424389, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.058091402053833, "global_step": 424390, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.043354034423828, "global_step": 424391, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.225036382675171, "global_step": 424392, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0688905715942383, "global_step": 424393, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.051356315612793, "global_step": 424394, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.062715530395508, "global_step": 424395, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0931169986724854, "global_step": 424396, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1333131790161133, "global_step": 424397, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1516027450561523, "global_step": 424398, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9934794902801514, "global_step": 424399, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.036489725112915, "global_step": 424400, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1031787395477295, "global_step": 424401, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1111462116241455, "global_step": 424402, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.971683382987976, "global_step": 424403, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.125114917755127, "global_step": 424404, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.148519992828369, "global_step": 424405, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1431806087493896, "global_step": 424406, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1120247840881348, "global_step": 424407, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.15283465385437, "global_step": 424408, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0158565044403076, "global_step": 424409, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1230297088623047, "global_step": 424410, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1390488147735596, "global_step": 424411, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1751420497894287, "global_step": 424412, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0777173042297363, "global_step": 424413, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1930859088897705, "global_step": 424414, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.201456308364868, "global_step": 424415, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.056168556213379, "global_step": 424416, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.109799861907959, "global_step": 424417, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1125576496124268, "global_step": 424418, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0416879653930664, "global_step": 424419, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0634043216705322, "global_step": 424420, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.015174388885498, "global_step": 424421, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0321476459503174, "global_step": 424422, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.147599697113037, "global_step": 424423, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.03308367729187, "global_step": 424424, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.091175079345703, "global_step": 424425, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9898208379745483, "global_step": 424426, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.069908380508423, "global_step": 424427, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0634765625, "global_step": 424428, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1035609245300293, "global_step": 424429, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.094655752182007, "global_step": 424430, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0630271434783936, "global_step": 424431, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.033642530441284, "global_step": 424432, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1345980167388916, "global_step": 424433, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1125903129577637, "global_step": 424434, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.033134937286377, "global_step": 424435, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0941944122314453, "global_step": 424436, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.072417974472046, "global_step": 424437, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0673165321350098, "global_step": 424438, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.111423969268799, "global_step": 424439, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.188925266265869, "global_step": 424440, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0071523189544678, "global_step": 424441, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.077244281768799, "global_step": 424442, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1292877197265625, "global_step": 424443, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.2527477741241455, "global_step": 424444, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.189422369003296, "global_step": 424445, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1560471057891846, "global_step": 424446, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.159975290298462, "global_step": 424447, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.024249792098999, "global_step": 424448, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.088867664337158, "global_step": 424449, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1691133975982666, "global_step": 424450, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.048515558242798, "global_step": 424451, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1047894954681396, "global_step": 424452, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1030688285827637, "global_step": 424453, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0868985652923584, "global_step": 424454, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.074516534805298, "global_step": 424455, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.01641845703125, "global_step": 424456, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0251801013946533, "global_step": 424457, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.020148754119873, "global_step": 424458, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.091609477996826, "global_step": 424459, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0888538360595703, "global_step": 424460, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.130948066711426, "global_step": 424461, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1245455741882324, "global_step": 424462, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.035055160522461, "global_step": 424463, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.061248302459717, "global_step": 424464, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0447213649749756, "global_step": 424465, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.120417833328247, "global_step": 424466, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0509629249572754, "global_step": 424467, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1988627910614014, "global_step": 424468, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1124367713928223, "global_step": 424469, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0912492275238037, "global_step": 424470, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.066669225692749, "global_step": 424471, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0746469497680664, "global_step": 424472, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.063594341278076, "global_step": 424473, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0400471687316895, "global_step": 424474, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.082559823989868, "global_step": 424475, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.161545991897583, "global_step": 424476, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.150357723236084, "global_step": 424477, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.142063617706299, "global_step": 424478, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0411441326141357, "global_step": 424479, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0612587928771973, "global_step": 424480, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.079141855239868, "global_step": 424481, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1320621967315674, "global_step": 424482, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0697808265686035, "global_step": 424483, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.109410285949707, "global_step": 424484, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1266231536865234, "global_step": 424485, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1802642345428467, "global_step": 424486, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1104695796966553, "global_step": 424487, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0619287490844727, "global_step": 424488, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1339945793151855, "global_step": 424489, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.169633150100708, "global_step": 424490, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.10172176361084, "global_step": 424491, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1650049686431885, "global_step": 424492, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0841012001037598, "global_step": 424493, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0296754837036133, "global_step": 424494, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0730037689208984, "global_step": 424495, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0580525398254395, "global_step": 424496, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1262121200561523, "global_step": 424497, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1129510402679443, "global_step": 424498, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9773428440093994, "global_step": 424499, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1267669200897217, "global_step": 424500, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1970198154449463, "global_step": 424501, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.101759195327759, "global_step": 424502, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1371281147003174, "global_step": 424503, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.194870710372925, "global_step": 424504, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0993025302886963, "global_step": 424505, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.110624074935913, "global_step": 424506, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0823371410369873, "global_step": 424507, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1300454139709473, "global_step": 424508, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.122861862182617, "global_step": 424509, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1039540767669678, "global_step": 424510, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.078925371170044, "global_step": 424511, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0824689865112305, "global_step": 424512, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0898189544677734, "global_step": 424513, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1756560802459717, "global_step": 424514, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0326619148254395, "global_step": 424515, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.048677682876587, "global_step": 424516, "epoch": 787, "lr": 5e-05}
{"train_loss": 1.9459491968154907, "global_step": 424517, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0067083835601807, "global_step": 424518, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.090083360671997, "global_step": 424519, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.133103847503662, "global_step": 424520, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0422611236572266, "global_step": 424521, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0410661697387695, "global_step": 424522, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.142416477203369, "global_step": 424523, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0889482498168945, "global_step": 424524, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0838801860809326, "global_step": 424525, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1065900325775146, "global_step": 424526, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0856499671936035, "global_step": 424527, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0590858459472656, "global_step": 424528, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1361234188079834, "global_step": 424529, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1193344593048096, "global_step": 424530, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1710429191589355, "global_step": 424531, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1112139225006104, "global_step": 424532, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0863046646118164, "global_step": 424533, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0902042388916016, "global_step": 424534, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0415868759155273, "global_step": 424535, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0787720680236816, "global_step": 424536, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0335640907287598, "global_step": 424537, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1262991428375244, "global_step": 424538, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0695159435272217, "global_step": 424539, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0990421772003174, "global_step": 424540, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0586423873901367, "global_step": 424541, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1729605197906494, "global_step": 424542, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0229923725128174, "global_step": 424543, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.061154365539551, "global_step": 424544, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0291574001312256, "global_step": 424545, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1088478565216064, "global_step": 424546, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.1564712524414062, "global_step": 424547, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.165510892868042, "global_step": 424548, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.148322343826294, "global_step": 424549, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0516018867492676, "global_step": 424550, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.091323137283325, "global_step": 424551, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.112222671508789, "global_step": 424552, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.10781192779541, "global_step": 424553, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0866832733154297, "global_step": 424554, "epoch": 787, "lr": 5e-05}
{"train_loss": 2.0173306465148926, "global_step": 424555, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0399558544158936, "global_step": 424556, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0758790969848633, "global_step": 424557, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0337440967559814, "global_step": 424558, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.086092472076416, "global_step": 424559, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.052485227584839, "global_step": 424560, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.098675489425659, "global_step": 424561, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1159844398498535, "global_step": 424562, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.05599308013916, "global_step": 424563, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0321619510650635, "global_step": 424564, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1530191898345947, "global_step": 424565, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0356805324554443, "global_step": 424566, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1628358364105225, "global_step": 424567, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0613131523132324, "global_step": 424568, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.100773334503174, "global_step": 424569, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.135692834854126, "global_step": 424570, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.997377634048462, "global_step": 424571, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.116726875305176, "global_step": 424572, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1553232669830322, "global_step": 424573, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1388943195343018, "global_step": 424574, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0899319648742676, "global_step": 424575, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.076589345932007, "global_step": 424576, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9948439598083496, "global_step": 424577, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.050050973892212, "global_step": 424578, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0425174236297607, "global_step": 424579, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.073758840560913, "global_step": 424580, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1265652179718018, "global_step": 424581, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0466973781585693, "global_step": 424582, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0837666988372803, "global_step": 424583, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0710389614105225, "global_step": 424584, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.055034637451172, "global_step": 424585, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1169915199279785, "global_step": 424586, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.068014144897461, "global_step": 424587, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.037008047103882, "global_step": 424588, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0899319648742676, "global_step": 424589, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1150383949279785, "global_step": 424590, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9915059804916382, "global_step": 424591, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0634145736694336, "global_step": 424592, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0834741592407227, "global_step": 424593, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.175438404083252, "global_step": 424594, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0961499214172363, "global_step": 424595, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0803029537200928, "global_step": 424596, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0532419681549072, "global_step": 424597, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0839297771453857, "global_step": 424598, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1033096313476562, "global_step": 424599, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.074235439300537, "global_step": 424600, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0688881874084473, "global_step": 424601, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.012911081314087, "global_step": 424602, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1033127307891846, "global_step": 424603, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.043085813522339, "global_step": 424604, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0065934658050537, "global_step": 424605, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1586244106292725, "global_step": 424606, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.109037399291992, "global_step": 424607, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0712010860443115, "global_step": 424608, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.09324049949646, "global_step": 424609, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1373777389526367, "global_step": 424610, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0512194633483887, "global_step": 424611, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.04197359085083, "global_step": 424612, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0193862915039062, "global_step": 424613, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1362123489379883, "global_step": 424614, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.092965841293335, "global_step": 424615, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9822272062301636, "global_step": 424616, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.077068567276001, "global_step": 424617, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.078082799911499, "global_step": 424618, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1047792434692383, "global_step": 424619, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0685017108917236, "global_step": 424620, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0460634231567383, "global_step": 424621, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.054790735244751, "global_step": 424622, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.03045916557312, "global_step": 424623, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.111598014831543, "global_step": 424624, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1660892963409424, "global_step": 424625, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1741795539855957, "global_step": 424626, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0884666442871094, "global_step": 424627, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.079134464263916, "global_step": 424628, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.030329704284668, "global_step": 424629, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9894965887069702, "global_step": 424630, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1010804176330566, "global_step": 424631, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.068633794784546, "global_step": 424632, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0496389865875244, "global_step": 424633, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.002854108810425, "global_step": 424634, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.15346360206604, "global_step": 424635, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.060499429702759, "global_step": 424636, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1077542304992676, "global_step": 424637, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0698113441467285, "global_step": 424638, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.071882486343384, "global_step": 424639, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1080970764160156, "global_step": 424640, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.148322820663452, "global_step": 424641, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.106278419494629, "global_step": 424642, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.080518960952759, "global_step": 424643, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.103311538696289, "global_step": 424644, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.054377317428589, "global_step": 424645, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.055386543273926, "global_step": 424646, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0075645446777344, "global_step": 424647, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0911242961883545, "global_step": 424648, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.150070905685425, "global_step": 424649, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0955810546875, "global_step": 424650, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0647785663604736, "global_step": 424651, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1884961128234863, "global_step": 424652, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0903685092926025, "global_step": 424653, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0598371028900146, "global_step": 424654, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.170461416244507, "global_step": 424655, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.107607126235962, "global_step": 424656, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0490641593933105, "global_step": 424657, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.100687265396118, "global_step": 424658, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.096553087234497, "global_step": 424659, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0301809310913086, "global_step": 424660, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0043323040008545, "global_step": 424661, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1003429889678955, "global_step": 424662, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0012660026550293, "global_step": 424663, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0411880016326904, "global_step": 424664, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0594944953918457, "global_step": 424665, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1001462936401367, "global_step": 424666, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1111860275268555, "global_step": 424667, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0455451011657715, "global_step": 424668, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0302960872650146, "global_step": 424669, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.153287887573242, "global_step": 424670, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.112027645111084, "global_step": 424671, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9800999164581299, "global_step": 424672, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.143641471862793, "global_step": 424673, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0298595428466797, "global_step": 424674, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0103249549865723, "global_step": 424675, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0303850173950195, "global_step": 424676, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.078139066696167, "global_step": 424677, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.14890456199646, "global_step": 424678, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1756176948547363, "global_step": 424679, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0283114910125732, "global_step": 424680, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0027942657470703, "global_step": 424681, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.188204765319824, "global_step": 424682, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0240893363952637, "global_step": 424683, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1540212631225586, "global_step": 424684, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0370800495147705, "global_step": 424685, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.00221848487854, "global_step": 424686, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0003092288970947, "global_step": 424687, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0403735637664795, "global_step": 424688, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1248981952667236, "global_step": 424689, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0392439365386963, "global_step": 424690, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0857491493225098, "global_step": 424691, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.089059829711914, "global_step": 424692, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0817830562591553, "global_step": 424693, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0796070098876953, "global_step": 424694, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.060201644897461, "global_step": 424695, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0468480587005615, "global_step": 424696, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.141954183578491, "global_step": 424697, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0374233722686768, "global_step": 424698, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1361262798309326, "global_step": 424699, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.013749837875366, "global_step": 424700, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.125025510787964, "global_step": 424701, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0853593349456787, "global_step": 424702, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0045230388641357, "global_step": 424703, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.148697853088379, "global_step": 424704, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.064622163772583, "global_step": 424705, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.06394362449646, "global_step": 424706, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0745561122894287, "global_step": 424707, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1493725776672363, "global_step": 424708, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.14559268951416, "global_step": 424709, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1005518436431885, "global_step": 424710, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.070380687713623, "global_step": 424711, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1348061561584473, "global_step": 424712, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.043572187423706, "global_step": 424713, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0393545627593994, "global_step": 424714, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0826761722564697, "global_step": 424715, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.078860282897949, "global_step": 424716, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1661484241485596, "global_step": 424717, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.11132550239563, "global_step": 424718, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.067753553390503, "global_step": 424719, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0220448970794678, "global_step": 424720, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1289620399475098, "global_step": 424721, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.137619733810425, "global_step": 424722, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0641441345214844, "global_step": 424723, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.053823709487915, "global_step": 424724, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.048957347869873, "global_step": 424725, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0887577533721924, "global_step": 424726, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.924190878868103, "global_step": 424727, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.169351816177368, "global_step": 424728, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.064629554748535, "global_step": 424729, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0825412273406982, "global_step": 424730, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0535531044006348, "global_step": 424731, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1572964191436768, "global_step": 424732, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1217782497406006, "global_step": 424733, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0949864387512207, "global_step": 424734, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0603222846984863, "global_step": 424735, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1605429649353027, "global_step": 424736, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0783159732818604, "global_step": 424737, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0405726432800293, "global_step": 424738, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1419684886932373, "global_step": 424739, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1205899715423584, "global_step": 424740, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0523664951324463, "global_step": 424741, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.087035655975342, "global_step": 424742, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0732743740081787, "global_step": 424743, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0836079120635986, "global_step": 424744, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.053016424179077, "global_step": 424745, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.035449981689453, "global_step": 424746, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1231441497802734, "global_step": 424747, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0765228271484375, "global_step": 424748, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0247793197631836, "global_step": 424749, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.016879081726074, "global_step": 424750, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.046444892883301, "global_step": 424751, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1223511695861816, "global_step": 424752, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1391892433166504, "global_step": 424753, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.070761203765869, "global_step": 424754, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0266330242156982, "global_step": 424755, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1092171669006348, "global_step": 424756, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1395304203033447, "global_step": 424757, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.078125, "global_step": 424758, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0681519508361816, "global_step": 424759, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.099611759185791, "global_step": 424760, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0610315799713135, "global_step": 424761, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0085439682006836, "global_step": 424762, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1502914428710938, "global_step": 424763, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1743004322052, "global_step": 424764, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1062729358673096, "global_step": 424765, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.981981873512268, "global_step": 424766, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.032498836517334, "global_step": 424767, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.119091510772705, "global_step": 424768, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.122488021850586, "global_step": 424769, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0459201335906982, "global_step": 424770, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.143115282058716, "global_step": 424771, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0985894203186035, "global_step": 424772, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0272436141967773, "global_step": 424773, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.097872734069824, "global_step": 424774, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.106199026107788, "global_step": 424775, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.091778039932251, "global_step": 424776, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1166932582855225, "global_step": 424777, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0713672637939453, "global_step": 424778, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.064303159713745, "global_step": 424779, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.002351760864258, "global_step": 424780, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.065325975418091, "global_step": 424781, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.024092435836792, "global_step": 424782, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.135953426361084, "global_step": 424783, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1000170707702637, "global_step": 424784, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0724315643310547, "global_step": 424785, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.147521495819092, "global_step": 424786, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0092971324920654, "global_step": 424787, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1111440658569336, "global_step": 424788, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.081589460372925, "global_step": 424789, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1503419876098633, "global_step": 424790, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.165062665939331, "global_step": 424791, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0585505962371826, "global_step": 424792, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0754432678222656, "global_step": 424793, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.113753080368042, "global_step": 424794, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.09287691116333, "global_step": 424795, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0739665031433105, "global_step": 424796, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0637264251708984, "global_step": 424797, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9947901964187622, "global_step": 424798, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.982974886894226, "global_step": 424799, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0948283672332764, "global_step": 424800, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0111887454986572, "global_step": 424801, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0346059799194336, "global_step": 424802, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1250154972076416, "global_step": 424803, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.155231237411499, "global_step": 424804, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.057048797607422, "global_step": 424805, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.086547613143921, "global_step": 424806, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.087512731552124, "global_step": 424807, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1922874450683594, "global_step": 424808, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0842409133911133, "global_step": 424809, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.119138717651367, "global_step": 424810, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1601197719573975, "global_step": 424811, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.083836317062378, "global_step": 424812, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.097844123840332, "global_step": 424813, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0562963485717773, "global_step": 424814, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0683069229125977, "global_step": 424815, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1225943565368652, "global_step": 424816, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1651530265808105, "global_step": 424817, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0014171600341797, "global_step": 424818, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0781543254852295, "global_step": 424819, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0162136554718018, "global_step": 424820, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.051356792449951, "global_step": 424821, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1365931034088135, "global_step": 424822, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.123713254928589, "global_step": 424823, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1781585216522217, "global_step": 424824, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0627074241638184, "global_step": 424825, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0584089756011963, "global_step": 424826, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0833592414855957, "global_step": 424827, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1178736686706543, "global_step": 424828, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0841081142425537, "global_step": 424829, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1324825286865234, "global_step": 424830, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.055874824523926, "global_step": 424831, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.04415225982666, "global_step": 424832, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.032714605331421, "global_step": 424833, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0325803756713867, "global_step": 424834, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0964276790618896, "global_step": 424835, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0660245418548584, "global_step": 424836, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0457284450531006, "global_step": 424837, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.046468496322632, "global_step": 424838, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.2058374881744385, "global_step": 424839, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.072368621826172, "global_step": 424840, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.082749605178833, "global_step": 424841, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0349602699279785, "global_step": 424842, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1020991802215576, "global_step": 424843, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.029414653778076, "global_step": 424844, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1601319313049316, "global_step": 424845, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.026651620864868, "global_step": 424846, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0112223625183105, "global_step": 424847, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1636769771575928, "global_step": 424848, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0622751712799072, "global_step": 424849, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1001765727996826, "global_step": 424850, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1307332515716553, "global_step": 424851, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.163666009902954, "global_step": 424852, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.108616352081299, "global_step": 424853, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0464184284210205, "global_step": 424854, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.10823655128479, "global_step": 424855, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.951413631439209, "global_step": 424856, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1813323497772217, "global_step": 424857, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.050994396209717, "global_step": 424858, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0751304626464844, "global_step": 424859, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.163555145263672, "global_step": 424860, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0884504318237305, "global_step": 424861, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.113377571105957, "global_step": 424862, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0219712257385254, "global_step": 424863, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1024317741394043, "global_step": 424864, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1263885498046875, "global_step": 424865, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0487654209136963, "global_step": 424866, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.082979440689087, "global_step": 424867, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.138166904449463, "global_step": 424868, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0529701709747314, "global_step": 424869, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0915627479553223, "global_step": 424870, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0811572074890137, "global_step": 424871, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.029576063156128, "global_step": 424872, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.022200107574463, "global_step": 424873, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1135733127593994, "global_step": 424874, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1285159587860107, "global_step": 424875, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.069139003753662, "global_step": 424876, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1180014610290527, "global_step": 424877, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0913259983062744, "global_step": 424878, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0671708583831787, "global_step": 424879, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0952775478363037, "global_step": 424880, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.00431489944458, "global_step": 424881, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.118910789489746, "global_step": 424882, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1394052505493164, "global_step": 424883, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.14009165763855, "global_step": 424884, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1643896102905273, "global_step": 424885, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.102705955505371, "global_step": 424886, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.088188886642456, "global_step": 424887, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.060711622238159, "global_step": 424888, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0716352462768555, "global_step": 424889, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1099205017089844, "global_step": 424890, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1099843978881836, "global_step": 424891, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9946651458740234, "global_step": 424892, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0774247646331787, "global_step": 424893, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.075922727584839, "global_step": 424894, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.994106411933899, "global_step": 424895, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.046194553375244, "global_step": 424896, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0354743003845215, "global_step": 424897, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.060997247695923, "global_step": 424898, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.050478458404541, "global_step": 424899, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.087221384048462, "global_step": 424900, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.082265615463257, "global_step": 424901, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0700466632843018, "global_step": 424902, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.051055908203125, "global_step": 424903, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.128505229949951, "global_step": 424904, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.087137460708618, "global_step": 424905, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9959752559661865, "global_step": 424906, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.072422742843628, "global_step": 424907, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0382473468780518, "global_step": 424908, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0826573371887207, "global_step": 424909, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.138000726699829, "global_step": 424910, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0222504138946533, "global_step": 424911, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.087893009185791, "global_step": 424912, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1322553157806396, "global_step": 424913, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.103976249694824, "global_step": 424914, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.133739948272705, "global_step": 424915, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.087350845336914, "global_step": 424916, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0827174186706543, "global_step": 424917, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.08494234085083, "global_step": 424918, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0998053550720215, "global_step": 424919, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1063520908355713, "global_step": 424920, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.101306915283203, "global_step": 424921, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9895515441894531, "global_step": 424922, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9802470207214355, "global_step": 424923, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.103442668914795, "global_step": 424924, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1387901306152344, "global_step": 424925, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.075951337814331, "global_step": 424926, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.213869094848633, "global_step": 424927, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.103771686553955, "global_step": 424928, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.143947124481201, "global_step": 424929, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0609912872314453, "global_step": 424930, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.047041654586792, "global_step": 424931, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0476393699645996, "global_step": 424932, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0927953720092773, "global_step": 424933, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.110774517059326, "global_step": 424934, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.04483699798584, "global_step": 424935, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1278467178344727, "global_step": 424936, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.031481981277466, "global_step": 424937, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1002719402313232, "global_step": 424938, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1377837657928467, "global_step": 424939, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1194908618927, "global_step": 424940, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1966114044189453, "global_step": 424941, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1902217864990234, "global_step": 424942, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9602689743041992, "global_step": 424943, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.068789482116699, "global_step": 424944, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.048567056655884, "global_step": 424945, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.179241180419922, "global_step": 424946, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.066253662109375, "global_step": 424947, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.110886573791504, "global_step": 424948, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1034817695617676, "global_step": 424949, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.145977258682251, "global_step": 424950, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0916380882263184, "global_step": 424951, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0930118560791016, "global_step": 424952, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0886762142181396, "global_step": 424953, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.138627052307129, "global_step": 424954, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.044546604156494, "global_step": 424955, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.024573564529419, "global_step": 424956, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0557610988616943, "global_step": 424957, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0757813453674316, "global_step": 424958, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.129115343093872, "global_step": 424959, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.028445243835449, "global_step": 424960, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.029592275619507, "global_step": 424961, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0697147846221924, "global_step": 424962, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0676169395446777, "global_step": 424963, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.042529582977295, "global_step": 424964, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.028398275375366, "global_step": 424965, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0431904792785645, "global_step": 424966, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.165992021560669, "global_step": 424967, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0387837886810303, "global_step": 424968, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9928420782089233, "global_step": 424969, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0940563678741455, "global_step": 424970, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0990419387817383, "global_step": 424971, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0398013591766357, "global_step": 424972, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0410473346710205, "global_step": 424973, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0941994190216064, "global_step": 424974, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.148453712463379, "global_step": 424975, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0806450843811035, "global_step": 424976, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0180416107177734, "global_step": 424977, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0666630268096924, "global_step": 424978, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0561041831970215, "global_step": 424979, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.010019540786743, "global_step": 424980, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0784456729888916, "global_step": 424981, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.102125883102417, "global_step": 424982, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0249085426330566, "global_step": 424983, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1300692558288574, "global_step": 424984, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0284976959228516, "global_step": 424985, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0917558670043945, "global_step": 424986, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1476073265075684, "global_step": 424987, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0954158306121826, "global_step": 424988, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0501601696014404, "global_step": 424989, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0780229568481445, "global_step": 424990, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1478278636932373, "global_step": 424991, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1200928688049316, "global_step": 424992, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.139914035797119, "global_step": 424993, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.029233455657959, "global_step": 424994, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0141165256500244, "global_step": 424995, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1168112754821777, "global_step": 424996, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0496740341186523, "global_step": 424997, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0513432025909424, "global_step": 424998, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0454564094543457, "global_step": 424999, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1095340251922607, "global_step": 425000, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0238518714904785, "global_step": 425001, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.050675630569458, "global_step": 425002, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0704731941223145, "global_step": 425003, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0898008346557617, "global_step": 425004, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1901285648345947, "global_step": 425005, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0687098503112793, "global_step": 425006, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0551657676696777, "global_step": 425007, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1011927127838135, "global_step": 425008, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.149944305419922, "global_step": 425009, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1209235191345215, "global_step": 425010, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1542110443115234, "global_step": 425011, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.178875207901001, "global_step": 425012, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1063504219055176, "global_step": 425013, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1030266284942627, "global_step": 425014, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.092940330505371, "global_step": 425015, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.027583122253418, "global_step": 425016, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0410566329956055, "global_step": 425017, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.041942596435547, "global_step": 425018, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.066004991531372, "global_step": 425019, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.059516668319702, "global_step": 425020, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.169642925262451, "global_step": 425021, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.092838764190674, "global_step": 425022, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1470823287963867, "global_step": 425023, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0611228942871094, "global_step": 425024, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9893040657043457, "global_step": 425025, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0784242153167725, "global_step": 425026, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1318695545196533, "global_step": 425027, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0516772270202637, "global_step": 425028, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0266952514648438, "global_step": 425029, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.100083589553833, "global_step": 425030, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0512123107910156, "global_step": 425031, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.089176654815674, "global_step": 425032, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0991017818450928, "global_step": 425033, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.075324296951294, "global_step": 425034, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1326191425323486, "global_step": 425035, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.066948890686035, "global_step": 425036, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1052846908569336, "global_step": 425037, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.067131519317627, "global_step": 425038, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9772062301635742, "global_step": 425039, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.166944742202759, "global_step": 425040, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0708351135253906, "global_step": 425041, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9766796827316284, "global_step": 425042, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.106576919555664, "global_step": 425043, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9679306745529175, "global_step": 425044, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0548887252807617, "global_step": 425045, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0938243865966797, "global_step": 425046, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.113903045654297, "global_step": 425047, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0861716270446777, "global_step": 425048, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.128141164779663, "global_step": 425049, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.068027973175049, "global_step": 425050, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.105480432510376, "global_step": 425051, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.992508888244629, "global_step": 425052, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0642600059509277, "global_step": 425053, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1529250144958496, "global_step": 425054, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1351959705352783, "global_step": 425055, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1806063652038574, "global_step": 425056, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0854320526123047, "global_step": 425057, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.079829454421997, "global_step": 425058, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.062485933303833, "global_step": 425059, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.144390344619751, "global_step": 425060, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1065282821655273, "global_step": 425061, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0464260578155518, "global_step": 425062, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0675692558288574, "global_step": 425063, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0400118827819824, "global_step": 425064, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.025484085083008, "global_step": 425065, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1405065059661865, "global_step": 425066, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0513012409210205, "global_step": 425067, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0352976322174072, "global_step": 425068, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.071213960647583, "global_step": 425069, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.168593406677246, "global_step": 425070, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0650925636291504, "global_step": 425071, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0721921920776367, "global_step": 425072, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.075063705444336, "global_step": 425073, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1068928241729736, "global_step": 425074, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1306660175323486, "global_step": 425075, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0098886489868164, "global_step": 425076, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.083348274230957, "global_step": 425077, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0861353874206543, "global_step": 425078, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9883780479431152, "global_step": 425079, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.035759449005127, "global_step": 425080, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1468732357025146, "global_step": 425081, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.087188243865967, "global_step": 425082, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.104548692703247, "global_step": 425083, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0743515491485596, "global_step": 425084, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1040029525756836, "global_step": 425085, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0729305744171143, "global_step": 425086, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0571930408477783, "global_step": 425087, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0444142818450928, "global_step": 425088, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1466970443725586, "global_step": 425089, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.125056505203247, "global_step": 425090, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0494284629821777, "global_step": 425091, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.035189628601074, "global_step": 425092, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1225099563598633, "global_step": 425093, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0833818912506104, "global_step": 425094, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.043259382247925, "global_step": 425095, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.144380569458008, "global_step": 425096, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0890872478485107, "global_step": 425097, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0189623832702637, "global_step": 425098, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.083407402038574, "global_step": 425099, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0486366748809814, "global_step": 425100, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.072758674621582, "global_step": 425101, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1014089584350586, "global_step": 425102, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1324846744537354, "global_step": 425103, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0377490520477295, "global_step": 425104, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.042100429534912, "global_step": 425105, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0736169815063477, "global_step": 425106, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0281593799591064, "global_step": 425107, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.046470880508423, "global_step": 425108, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9964178800582886, "global_step": 425109, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0226073265075684, "global_step": 425110, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0792593955993652, "global_step": 425111, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0360519886016846, "global_step": 425112, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1161000728607178, "global_step": 425113, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.079958200454712, "global_step": 425114, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0952699184417725, "global_step": 425115, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1184089183807373, "global_step": 425116, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.120042324066162, "global_step": 425117, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0736396312713623, "global_step": 425118, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.110269784927368, "global_step": 425119, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0401406288146973, "global_step": 425120, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.10221791267395, "global_step": 425121, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0224568843841553, "global_step": 425122, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0694103240966797, "global_step": 425123, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0365543365478516, "global_step": 425124, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.169743061065674, "global_step": 425125, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.061173677444458, "global_step": 425126, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0567705631256104, "global_step": 425127, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.023172378540039, "global_step": 425128, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.025996446609497, "global_step": 425129, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.101210594177246, "global_step": 425130, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.019092321395874, "global_step": 425131, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1342215538024902, "global_step": 425132, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.082871913909912, "global_step": 425133, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1559176445007324, "global_step": 425134, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1412909030914307, "global_step": 425135, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0835607051849365, "global_step": 425136, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0962936878204346, "global_step": 425137, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.029784679412842, "global_step": 425138, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1694326400756836, "global_step": 425139, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.033818244934082, "global_step": 425140, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.017642021179199, "global_step": 425141, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0859487056732178, "global_step": 425142, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1446452140808105, "global_step": 425143, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0318329334259033, "global_step": 425144, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0798187255859375, "global_step": 425145, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.03000545501709, "global_step": 425146, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.057901382446289, "global_step": 425147, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.149160385131836, "global_step": 425148, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0915448665618896, "global_step": 425149, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1586289405822754, "global_step": 425150, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1449403762817383, "global_step": 425151, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1461002826690674, "global_step": 425152, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0597805976867676, "global_step": 425153, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0778462886810303, "global_step": 425154, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.063159942626953, "global_step": 425155, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.2392427921295166, "global_step": 425156, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.115462303161621, "global_step": 425157, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1358587741851807, "global_step": 425158, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.118767738342285, "global_step": 425159, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0419058799743652, "global_step": 425160, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0492570400238037, "global_step": 425161, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0094082355499268, "global_step": 425162, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1612212657928467, "global_step": 425163, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0836548805236816, "global_step": 425164, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1169724464416504, "global_step": 425165, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1067147254943848, "global_step": 425166, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0351510047912598, "global_step": 425167, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0562829971313477, "global_step": 425168, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1723554134368896, "global_step": 425169, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.048084020614624, "global_step": 425170, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1173934936523438, "global_step": 425171, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9508798122406006, "global_step": 425172, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1270925998687744, "global_step": 425173, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0880584716796875, "global_step": 425174, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0601279735565186, "global_step": 425175, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.126793146133423, "global_step": 425176, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.113105535507202, "global_step": 425177, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9909207820892334, "global_step": 425178, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.076122283935547, "global_step": 425179, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0145888328552246, "global_step": 425180, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1187562942504883, "global_step": 425181, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.075360059738159, "global_step": 425182, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.092501163482666, "global_step": 425183, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1038689613342285, "global_step": 425184, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.089277505874634, "global_step": 425185, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1193687915802, "global_step": 425186, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1603407859802246, "global_step": 425187, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0739617347717285, "global_step": 425188, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.100576639175415, "global_step": 425189, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0273706912994385, "global_step": 425190, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1053309440612793, "global_step": 425191, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.140730142593384, "global_step": 425192, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1161293983459473, "global_step": 425193, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1399123668670654, "global_step": 425194, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.144315004348755, "global_step": 425195, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0689761638641357, "global_step": 425196, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0591018199920654, "global_step": 425197, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.095146894454956, "global_step": 425198, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0228118896484375, "global_step": 425199, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0875062942504883, "global_step": 425200, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.120744466781616, "global_step": 425201, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1392264366149902, "global_step": 425202, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.078120231628418, "global_step": 425203, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.111485719680786, "global_step": 425204, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.193298101425171, "global_step": 425205, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.089609384536743, "global_step": 425206, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0990188121795654, "global_step": 425207, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.145770311355591, "global_step": 425208, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1223185062408447, "global_step": 425209, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0466952323913574, "global_step": 425210, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.080735683441162, "global_step": 425211, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9729162454605103, "global_step": 425212, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0784289836883545, "global_step": 425213, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.128058671951294, "global_step": 425214, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9700404405593872, "global_step": 425215, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1428756713867188, "global_step": 425216, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1148972511291504, "global_step": 425217, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.082866668701172, "global_step": 425218, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1618120670318604, "global_step": 425219, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9857513904571533, "global_step": 425220, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.066962718963623, "global_step": 425221, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.05119252204895, "global_step": 425222, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.142458438873291, "global_step": 425223, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1398680210113525, "global_step": 425224, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1937248706817627, "global_step": 425225, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.067171812057495, "global_step": 425226, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1282236576080322, "global_step": 425227, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0832881927490234, "global_step": 425228, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.084299087524414, "global_step": 425229, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.153754234313965, "global_step": 425230, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0283241271972656, "global_step": 425231, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0171866416931152, "global_step": 425232, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0892820358276367, "global_step": 425233, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0363223552703857, "global_step": 425234, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1694817543029785, "global_step": 425235, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0997636318206787, "global_step": 425236, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0573699474334717, "global_step": 425237, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.036508321762085, "global_step": 425238, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.118936777114868, "global_step": 425239, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0960240364074707, "global_step": 425240, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0298523902893066, "global_step": 425241, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0952327251434326, "global_step": 425242, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1063575744628906, "global_step": 425243, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.038691997528076, "global_step": 425244, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0625219345092773, "global_step": 425245, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0766189098358154, "global_step": 425246, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9972952604293823, "global_step": 425247, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0929057598114014, "global_step": 425248, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1036171913146973, "global_step": 425249, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1613476276397705, "global_step": 425250, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.088876724243164, "global_step": 425251, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.046631336212158, "global_step": 425252, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1411235332489014, "global_step": 425253, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.059553384780884, "global_step": 425254, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1500842571258545, "global_step": 425255, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.109985828399658, "global_step": 425256, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1593055725097656, "global_step": 425257, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0137290954589844, "global_step": 425258, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.005586862564087, "global_step": 425259, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0939133167266846, "global_step": 425260, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1172935962677, "global_step": 425261, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.150786876678467, "global_step": 425262, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9813902378082275, "global_step": 425263, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0989301204681396, "global_step": 425264, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.081998348236084, "global_step": 425265, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0737555027008057, "global_step": 425266, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0165207386016846, "global_step": 425267, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.057204246520996, "global_step": 425268, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1152431964874268, "global_step": 425269, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.105297803878784, "global_step": 425270, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.106907844543457, "global_step": 425271, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.104843854904175, "global_step": 425272, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.156625986099243, "global_step": 425273, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.101529836654663, "global_step": 425274, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.015047073364258, "global_step": 425275, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1244287490844727, "global_step": 425276, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0542356967926025, "global_step": 425277, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.091019630432129, "global_step": 425278, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.116645574569702, "global_step": 425279, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.2234177589416504, "global_step": 425280, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.053118944168091, "global_step": 425281, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.083468437194824, "global_step": 425282, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0862600803375244, "global_step": 425283, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0861456394195557, "global_step": 425284, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1155238151550293, "global_step": 425285, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.129371166229248, "global_step": 425286, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1134390830993652, "global_step": 425287, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0566115379333496, "global_step": 425288, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0637025833129883, "global_step": 425289, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0777673721313477, "global_step": 425290, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0919888019561768, "global_step": 425291, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0555155277252197, "global_step": 425292, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1725010871887207, "global_step": 425293, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.04158616065979, "global_step": 425294, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0706069469451904, "global_step": 425295, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0484516620635986, "global_step": 425296, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1102657318115234, "global_step": 425297, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.089040994644165, "global_step": 425298, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0616824626922607, "global_step": 425299, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1076152324676514, "global_step": 425300, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.139801025390625, "global_step": 425301, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.064560890197754, "global_step": 425302, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0387465953826904, "global_step": 425303, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0389983654022217, "global_step": 425304, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.058913230895996, "global_step": 425305, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.061020612716675, "global_step": 425306, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.008483648300171, "global_step": 425307, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.109454870223999, "global_step": 425308, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0834455490112305, "global_step": 425309, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1323800086975098, "global_step": 425310, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1640641689300537, "global_step": 425311, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0241594314575195, "global_step": 425312, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0937087535858154, "global_step": 425313, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1358962059020996, "global_step": 425314, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.08819842338562, "global_step": 425315, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0480687618255615, "global_step": 425316, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.091373920440674, "global_step": 425317, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0486886501312256, "global_step": 425318, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9816734790802002, "global_step": 425319, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0656609535217285, "global_step": 425320, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1221747398376465, "global_step": 425321, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.082515239715576, "global_step": 425322, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1239850521087646, "global_step": 425323, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1466429233551025, "global_step": 425324, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0856406688690186, "global_step": 425325, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1095895767211914, "global_step": 425326, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.058468818664551, "global_step": 425327, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.113596200942993, "global_step": 425328, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0547146797180176, "global_step": 425329, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1104977130889893, "global_step": 425330, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1389753818511963, "global_step": 425331, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0002975463867188, "global_step": 425332, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1144649982452393, "global_step": 425333, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0804195404052734, "global_step": 425334, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1250405311584473, "global_step": 425335, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.17895245552063, "global_step": 425336, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0675361156463623, "global_step": 425337, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0287435054779053, "global_step": 425338, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0880613327026367, "global_step": 425339, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1266286373138428, "global_step": 425340, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0654940605163574, "global_step": 425341, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9993020296096802, "global_step": 425342, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.153759241104126, "global_step": 425343, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0955584049224854, "global_step": 425344, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.130606174468994, "global_step": 425345, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.051786422729492, "global_step": 425346, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.031254291534424, "global_step": 425347, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0179085731506348, "global_step": 425348, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0482337474823, "global_step": 425349, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.097282648086548, "global_step": 425350, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.118698835372925, "global_step": 425351, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.916969656944275, "global_step": 425352, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1474814414978027, "global_step": 425353, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.083677291870117, "global_step": 425354, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1347594261169434, "global_step": 425355, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.005678176879883, "global_step": 425356, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.085963487625122, "global_step": 425357, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1961617469787598, "global_step": 425358, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9797086715698242, "global_step": 425359, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.099087715148926, "global_step": 425360, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1956067085266113, "global_step": 425361, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0740091800689697, "global_step": 425362, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.028860330581665, "global_step": 425363, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.039255142211914, "global_step": 425364, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.090026617050171, "global_step": 425365, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0283336639404297, "global_step": 425366, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1503825187683105, "global_step": 425367, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1054527759552, "global_step": 425368, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1114280223846436, "global_step": 425369, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0883116722106934, "global_step": 425370, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.989214301109314, "global_step": 425371, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.08678936958313, "global_step": 425372, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.105386972427368, "global_step": 425373, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.109875202178955, "global_step": 425374, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0494332313537598, "global_step": 425375, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1595585346221924, "global_step": 425376, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.107912063598633, "global_step": 425377, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1810431480407715, "global_step": 425378, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.14556884765625, "global_step": 425379, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0019023418426514, "global_step": 425380, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.114467144012451, "global_step": 425381, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.064950704574585, "global_step": 425382, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.021367073059082, "global_step": 425383, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.148923397064209, "global_step": 425384, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1382362842559814, "global_step": 425385, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.06618595123291, "global_step": 425386, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0342071056365967, "global_step": 425387, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.065814971923828, "global_step": 425388, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.072129487991333, "global_step": 425389, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0260465145111084, "global_step": 425390, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.093032121658325, "global_step": 425391, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.131032705307007, "global_step": 425392, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0656702518463135, "global_step": 425393, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1232895851135254, "global_step": 425394, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.2263400554656982, "global_step": 425395, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.106759786605835, "global_step": 425396, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.10524845123291, "global_step": 425397, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.061952590942383, "global_step": 425398, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0811474323272705, "global_step": 425399, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1503548622131348, "global_step": 425400, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1114931106567383, "global_step": 425401, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.071730613708496, "global_step": 425402, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.054912567138672, "global_step": 425403, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0831944942474365, "global_step": 425404, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.03226900100708, "global_step": 425405, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1338627338409424, "global_step": 425406, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.087468147277832, "global_step": 425407, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.047823667526245, "global_step": 425408, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0937998294830322, "global_step": 425409, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0866739749908447, "global_step": 425410, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0854578018188477, "global_step": 425411, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.047055959701538, "global_step": 425412, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.143827199935913, "global_step": 425413, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0886707305908203, "global_step": 425414, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.074519395828247, "global_step": 425415, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0702168941497803, "global_step": 425416, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.073378086090088, "global_step": 425417, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.109395742416382, "global_step": 425418, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.099184989929199, "global_step": 425419, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.126661777496338, "global_step": 425420, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0984044075012207, "global_step": 425421, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1085338592529297, "global_step": 425422, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1897177696228027, "global_step": 425423, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.164572238922119, "global_step": 425424, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0458807945251465, "global_step": 425425, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.2364611625671387, "global_step": 425426, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1039538383483887, "global_step": 425427, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1091456413269043, "global_step": 425428, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0981087684631348, "global_step": 425429, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1000125408172607, "global_step": 425430, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1065890789031982, "global_step": 425431, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1412806510925293, "global_step": 425432, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1341936588287354, "global_step": 425433, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.005317449569702, "global_step": 425434, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0802793502807617, "global_step": 425435, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.048537015914917, "global_step": 425436, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1098721027374268, "global_step": 425437, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1381185054779053, "global_step": 425438, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.194608211517334, "global_step": 425439, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1087546348571777, "global_step": 425440, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.138227701187134, "global_step": 425441, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0853159427642822, "global_step": 425442, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.109433650970459, "global_step": 425443, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0680243968963623, "global_step": 425444, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1065139770507812, "global_step": 425445, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1803717613220215, "global_step": 425446, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0605835914611816, "global_step": 425447, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0847208499908447, "global_step": 425448, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.057290554046631, "global_step": 425449, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1016669273376465, "global_step": 425450, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.043545961380005, "global_step": 425451, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.043811559677124, "global_step": 425452, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1320691108703613, "global_step": 425453, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1818740367889404, "global_step": 425454, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.028442621231079, "global_step": 425455, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.072518825531006, "global_step": 425456, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1237294673919678, "global_step": 425457, "epoch": 788, "lr": 5e-05}
{"train_loss": 1.9722939729690552, "global_step": 425458, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0852718353271484, "global_step": 425459, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1276087760925293, "global_step": 425460, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1551828384399414, "global_step": 425461, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.114762783050537, "global_step": 425462, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.076958417892456, "global_step": 425463, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0504539012908936, "global_step": 425464, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1309807300567627, "global_step": 425465, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.123866319656372, "global_step": 425466, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0850954055786133, "global_step": 425467, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0525407791137695, "global_step": 425468, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.055936813354492, "global_step": 425469, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0062477588653564, "global_step": 425470, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1080918312072754, "global_step": 425471, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0457372665405273, "global_step": 425472, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1152572631835938, "global_step": 425473, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0880815982818604, "global_step": 425474, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0255415439605713, "global_step": 425475, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0909698009490967, "global_step": 425476, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.145430564880371, "global_step": 425477, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0621578693389893, "global_step": 425478, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.084113836288452, "global_step": 425479, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.12640643119812, "global_step": 425480, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.122112512588501, "global_step": 425481, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0892221927642822, "global_step": 425482, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0465996265411377, "global_step": 425483, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0904252529144287, "global_step": 425484, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.020709276199341, "global_step": 425485, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.070444107055664, "global_step": 425486, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.132324457168579, "global_step": 425487, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.07159161567688, "global_step": 425488, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0871012210845947, "global_step": 425489, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0811824798583984, "global_step": 425490, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.20462703704834, "global_step": 425491, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0169496536254883, "global_step": 425492, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.08929443359375, "global_step": 425493, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.089831590652466, "global_step": 425494, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0705924034118652, "global_step": 425495, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1029815673828125, "global_step": 425496, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.166998863220215, "global_step": 425497, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.057095527648926, "global_step": 425498, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0355799198150635, "global_step": 425499, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1048662662506104, "global_step": 425500, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0625269412994385, "global_step": 425501, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1039834022521973, "global_step": 425502, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1490437984466553, "global_step": 425503, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.070446014404297, "global_step": 425504, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0968730449676514, "global_step": 425505, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.155578851699829, "global_step": 425506, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.133765459060669, "global_step": 425507, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0999841690063477, "global_step": 425508, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.208033800125122, "global_step": 425509, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0743653774261475, "global_step": 425510, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.1457951068878174, "global_step": 425511, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.135554790496826, "global_step": 425512, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0611557960510254, "global_step": 425513, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0878336429595947, "global_step": 425514, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.142989158630371, "global_step": 425515, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.174225091934204, "global_step": 425516, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.079227924346924, "global_step": 425517, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0617380142211914, "global_step": 425518, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.053881883621216, "global_step": 425519, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.092831611633301, "global_step": 425520, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.135035753250122, "global_step": 425521, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.0627710819244385, "global_step": 425522, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.085080146789551, "global_step": 425523, "epoch": 788, "lr": 5e-05}
{"train_loss": 2.046326160430908, "global_step": 425524, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.06516170501709, "global_step": 425525, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0175247192382812, "global_step": 425526, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.062610149383545, "global_step": 425527, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.101767063140869, "global_step": 425528, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0366313457489014, "global_step": 425529, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0300700664520264, "global_step": 425530, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9933398962020874, "global_step": 425531, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0719752311706543, "global_step": 425532, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0886454582214355, "global_step": 425533, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1203198432922363, "global_step": 425534, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1296775341033936, "global_step": 425535, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0683751106262207, "global_step": 425536, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.080199956893921, "global_step": 425537, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9676622152328491, "global_step": 425538, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0655691623687744, "global_step": 425539, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.135043144226074, "global_step": 425540, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1275432109832764, "global_step": 425541, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.02980899810791, "global_step": 425542, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.07039213180542, "global_step": 425543, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.125333547592163, "global_step": 425544, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1456568241119385, "global_step": 425545, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.02490234375, "global_step": 425546, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9602077007293701, "global_step": 425547, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0913138389587402, "global_step": 425548, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1591708660125732, "global_step": 425549, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0789847373962402, "global_step": 425550, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.07332706451416, "global_step": 425551, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.149407386779785, "global_step": 425552, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.107501268386841, "global_step": 425553, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.070159912109375, "global_step": 425554, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0787317752838135, "global_step": 425555, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.060044050216675, "global_step": 425556, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.096923828125, "global_step": 425557, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0471177101135254, "global_step": 425558, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.052861213684082, "global_step": 425559, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.112196922302246, "global_step": 425560, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.076279878616333, "global_step": 425561, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9715838432312012, "global_step": 425562, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0300889015197754, "global_step": 425563, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.106346845626831, "global_step": 425564, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1507937908172607, "global_step": 425565, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.074695110321045, "global_step": 425566, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.114682912826538, "global_step": 425567, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.032060146331787, "global_step": 425568, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.179551601409912, "global_step": 425569, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.023864269256592, "global_step": 425570, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.052320957183838, "global_step": 425571, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1424903869628906, "global_step": 425572, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.025998830795288, "global_step": 425573, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0861458778381348, "global_step": 425574, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0476417541503906, "global_step": 425575, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.06931734085083, "global_step": 425576, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.105708599090576, "global_step": 425577, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0143682956695557, "global_step": 425578, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.042721748352051, "global_step": 425579, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1039018630981445, "global_step": 425580, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.116729259490967, "global_step": 425581, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0872764587402344, "global_step": 425582, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.095595598220825, "global_step": 425583, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.00956392288208, "global_step": 425584, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.09035587310791, "global_step": 425585, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0733816623687744, "global_step": 425586, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.146127700805664, "global_step": 425587, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1032097339630127, "global_step": 425588, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1459450721740723, "global_step": 425589, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9990143775939941, "global_step": 425590, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0876193046569824, "global_step": 425591, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1193175315856934, "global_step": 425592, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0577738285064697, "global_step": 425593, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0997092723846436, "global_step": 425594, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1162514686584473, "global_step": 425595, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.11336088180542, "global_step": 425596, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1016461849212646, "global_step": 425597, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0473620891571045, "global_step": 425598, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1559054851531982, "global_step": 425599, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.062321186065674, "global_step": 425600, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.048053503036499, "global_step": 425601, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.056807279586792, "global_step": 425602, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0201427936553955, "global_step": 425603, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0765798091888428, "global_step": 425604, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0700159072875977, "global_step": 425605, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.074864625930786, "global_step": 425606, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1461784839630127, "global_step": 425607, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.995643138885498, "global_step": 425608, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0659995079040527, "global_step": 425609, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.926060438156128, "global_step": 425610, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.059979200363159, "global_step": 425611, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0962040424346924, "global_step": 425612, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.171380043029785, "global_step": 425613, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0061745643615723, "global_step": 425614, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1293599605560303, "global_step": 425615, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.074547290802002, "global_step": 425616, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9595919847488403, "global_step": 425617, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1209232807159424, "global_step": 425618, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0907671451568604, "global_step": 425619, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0927932262420654, "global_step": 425620, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.991499423980713, "global_step": 425621, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0125234127044678, "global_step": 425622, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0746898651123047, "global_step": 425623, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0945966243743896, "global_step": 425624, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0132110118865967, "global_step": 425625, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.034276008605957, "global_step": 425626, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.122879981994629, "global_step": 425627, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.119826555252075, "global_step": 425628, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.040358781814575, "global_step": 425629, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0364274978637695, "global_step": 425630, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0952203273773193, "global_step": 425631, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1146342754364014, "global_step": 425632, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.066906213760376, "global_step": 425633, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.152076005935669, "global_step": 425634, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0690436363220215, "global_step": 425635, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0752084255218506, "global_step": 425636, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.119349479675293, "global_step": 425637, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9980899095535278, "global_step": 425638, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.025479316711426, "global_step": 425639, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0365939140319824, "global_step": 425640, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.999915599822998, "global_step": 425641, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.098294496536255, "global_step": 425642, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.11940336227417, "global_step": 425643, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9842054843902588, "global_step": 425644, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0852408409118652, "global_step": 425645, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1063435077667236, "global_step": 425646, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.141704559326172, "global_step": 425647, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1583337783813477, "global_step": 425648, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.063061475753784, "global_step": 425649, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1336371898651123, "global_step": 425650, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0765228271484375, "global_step": 425651, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1330108642578125, "global_step": 425652, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.034069776535034, "global_step": 425653, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0879383087158203, "global_step": 425654, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0575170516967773, "global_step": 425655, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.034162759780884, "global_step": 425656, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.089077949523926, "global_step": 425657, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.139221668243408, "global_step": 425658, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.038724184036255, "global_step": 425659, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0786354541778564, "global_step": 425660, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1032118797302246, "global_step": 425661, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0939931869506836, "global_step": 425662, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1431283950805664, "global_step": 425663, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1298415660858154, "global_step": 425664, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9922332763671875, "global_step": 425665, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0710248947143555, "global_step": 425666, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0580291748046875, "global_step": 425667, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1138439178466797, "global_step": 425668, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.065443754196167, "global_step": 425669, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0853679180145264, "global_step": 425670, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.171049118041992, "global_step": 425671, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.030524969100952, "global_step": 425672, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.020326614379883, "global_step": 425673, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1147282123565674, "global_step": 425674, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.156388998031616, "global_step": 425675, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.110499382019043, "global_step": 425676, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1341049671173096, "global_step": 425677, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0651490688323975, "global_step": 425678, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1255292892456055, "global_step": 425679, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0475571155548096, "global_step": 425680, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.059473752975464, "global_step": 425681, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1154966354370117, "global_step": 425682, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.03389835357666, "global_step": 425683, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0550787448883057, "global_step": 425684, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.087826728820801, "global_step": 425685, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.060668706893921, "global_step": 425686, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0546398162841797, "global_step": 425687, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1620213985443115, "global_step": 425688, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.040365219116211, "global_step": 425689, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.076458215713501, "global_step": 425690, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1426825523376465, "global_step": 425691, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.061526298522949, "global_step": 425692, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1012368202209473, "global_step": 425693, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.070857048034668, "global_step": 425694, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0287842750549316, "global_step": 425695, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.051713705062866, "global_step": 425696, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0707902908325195, "global_step": 425697, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.061302661895752, "global_step": 425698, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0876388549804688, "global_step": 425699, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.087388753890991, "global_step": 425700, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.125262975692749, "global_step": 425701, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.07063889503479, "global_step": 425702, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.085940361022949, "global_step": 425703, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.129274606704712, "global_step": 425704, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.03985595703125, "global_step": 425705, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.063054323196411, "global_step": 425706, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.020329236984253, "global_step": 425707, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0269272327423096, "global_step": 425708, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0986487865448, "global_step": 425709, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1412055492401123, "global_step": 425710, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.003089189529419, "global_step": 425711, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1443874835968018, "global_step": 425712, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.094442367553711, "global_step": 425713, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0405001640319824, "global_step": 425714, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9870102405548096, "global_step": 425715, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.010551929473877, "global_step": 425716, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0793817043304443, "global_step": 425717, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1777780055999756, "global_step": 425718, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.116541624069214, "global_step": 425719, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.104978561401367, "global_step": 425720, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0792341232299805, "global_step": 425721, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0723798274993896, "global_step": 425722, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0425682067871094, "global_step": 425723, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.098161220550537, "global_step": 425724, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.051414728164673, "global_step": 425725, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.006622076034546, "global_step": 425726, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0787670612335205, "global_step": 425727, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.15742826461792, "global_step": 425728, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.989020586013794, "global_step": 425729, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1392037868499756, "global_step": 425730, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0153656005859375, "global_step": 425731, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0877509117126465, "global_step": 425732, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1508681774139404, "global_step": 425733, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1947145462036133, "global_step": 425734, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1063315868377686, "global_step": 425735, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.095644950866699, "global_step": 425736, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1425793170928955, "global_step": 425737, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.019263744354248, "global_step": 425738, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0962936878204346, "global_step": 425739, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0551581382751465, "global_step": 425740, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1172537803649902, "global_step": 425741, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.045801877975464, "global_step": 425742, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.097723960876465, "global_step": 425743, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0668468475341797, "global_step": 425744, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0607051849365234, "global_step": 425745, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1038451194763184, "global_step": 425746, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.125560998916626, "global_step": 425747, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.061776876449585, "global_step": 425748, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.02262806892395, "global_step": 425749, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1043078899383545, "global_step": 425750, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.077302932739258, "global_step": 425751, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0478601455688477, "global_step": 425752, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1071465015411377, "global_step": 425753, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.032947063446045, "global_step": 425754, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1246304512023926, "global_step": 425755, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.11494779586792, "global_step": 425756, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1512362957000732, "global_step": 425757, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.070585012435913, "global_step": 425758, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.063908815383911, "global_step": 425759, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.064469575881958, "global_step": 425760, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.12632417678833, "global_step": 425761, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.167332887649536, "global_step": 425762, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.164088249206543, "global_step": 425763, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.097370147705078, "global_step": 425764, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.008335828781128, "global_step": 425765, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.133168935775757, "global_step": 425766, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.003507614135742, "global_step": 425767, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0996339321136475, "global_step": 425768, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1538443565368652, "global_step": 425769, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0990447998046875, "global_step": 425770, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.056769609451294, "global_step": 425771, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0534679889678955, "global_step": 425772, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0941598415374756, "global_step": 425773, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9786620140075684, "global_step": 425774, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0408289432525635, "global_step": 425775, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.054370164871216, "global_step": 425776, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9815778732299805, "global_step": 425777, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1965692043304443, "global_step": 425778, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1291661262512207, "global_step": 425779, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.050807476043701, "global_step": 425780, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.144425630569458, "global_step": 425781, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.145052909851074, "global_step": 425782, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.070476770401001, "global_step": 425783, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0394818782806396, "global_step": 425784, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1287784576416016, "global_step": 425785, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0903103351593018, "global_step": 425786, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.085897445678711, "global_step": 425787, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.2058451175689697, "global_step": 425788, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0680274963378906, "global_step": 425789, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0243630409240723, "global_step": 425790, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0188920497894287, "global_step": 425791, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0728628635406494, "global_step": 425792, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.036067247390747, "global_step": 425793, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1001999378204346, "global_step": 425794, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1151206493377686, "global_step": 425795, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.150883674621582, "global_step": 425796, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0160529613494873, "global_step": 425797, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1235504150390625, "global_step": 425798, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0664775371551514, "global_step": 425799, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.088186502456665, "global_step": 425800, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.001917839050293, "global_step": 425801, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.046208620071411, "global_step": 425802, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1190109252929688, "global_step": 425803, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.105527639389038, "global_step": 425804, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1230926513671875, "global_step": 425805, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0636417865753174, "global_step": 425806, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9864360094070435, "global_step": 425807, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9786996841430664, "global_step": 425808, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.022902727127075, "global_step": 425809, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.109687566757202, "global_step": 425810, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1426939964294434, "global_step": 425811, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.051090717315674, "global_step": 425812, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0400264263153076, "global_step": 425813, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0923845767974854, "global_step": 425814, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9689501523971558, "global_step": 425815, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0539214611053467, "global_step": 425816, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.066617965698242, "global_step": 425817, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0881564617156982, "global_step": 425818, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.052840232849121, "global_step": 425819, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.042072296142578, "global_step": 425820, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1010091304779053, "global_step": 425821, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.10200572013855, "global_step": 425822, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.031639337539673, "global_step": 425823, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.992445945739746, "global_step": 425824, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.081051826477051, "global_step": 425825, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1824710369110107, "global_step": 425826, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.099240779876709, "global_step": 425827, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.011033773422241, "global_step": 425828, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.119168996810913, "global_step": 425829, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.139484167098999, "global_step": 425830, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0256569385528564, "global_step": 425831, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1280767917633057, "global_step": 425832, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.077706813812256, "global_step": 425833, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1036341190338135, "global_step": 425834, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0805845260620117, "global_step": 425835, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1073508262634277, "global_step": 425836, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.171689987182617, "global_step": 425837, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1819887161254883, "global_step": 425838, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0629193782806396, "global_step": 425839, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.065565824508667, "global_step": 425840, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.088043689727783, "global_step": 425841, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1472911834716797, "global_step": 425842, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0758166313171387, "global_step": 425843, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.076533555984497, "global_step": 425844, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.113379955291748, "global_step": 425845, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0680928230285645, "global_step": 425846, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.085597276687622, "global_step": 425847, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.052957057952881, "global_step": 425848, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.202951192855835, "global_step": 425849, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.147496461868286, "global_step": 425850, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0970618724823, "global_step": 425851, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1548454761505127, "global_step": 425852, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0966784954071045, "global_step": 425853, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.088697671890259, "global_step": 425854, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.092216730117798, "global_step": 425855, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0633656978607178, "global_step": 425856, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.088841199874878, "global_step": 425857, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1214234828948975, "global_step": 425858, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0462515354156494, "global_step": 425859, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0756285190582275, "global_step": 425860, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0515825748443604, "global_step": 425861, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0370261669158936, "global_step": 425862, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1113064289093018, "global_step": 425863, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1086337566375732, "global_step": 425864, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.082568883895874, "global_step": 425865, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0865859985351562, "global_step": 425866, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1043927669525146, "global_step": 425867, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0459747314453125, "global_step": 425868, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0719943046569824, "global_step": 425869, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1105129718780518, "global_step": 425870, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.071132183074951, "global_step": 425871, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1177597045898438, "global_step": 425872, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.042365074157715, "global_step": 425873, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0222880840301514, "global_step": 425874, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1709096431732178, "global_step": 425875, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0877201557159424, "global_step": 425876, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.118185043334961, "global_step": 425877, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0768790245056152, "global_step": 425878, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0468289852142334, "global_step": 425879, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0847878456115723, "global_step": 425880, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.15498948097229, "global_step": 425881, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0425291061401367, "global_step": 425882, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.134758472442627, "global_step": 425883, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.019041061401367, "global_step": 425884, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.041583299636841, "global_step": 425885, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.018627643585205, "global_step": 425886, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.089454412460327, "global_step": 425887, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.196218967437744, "global_step": 425888, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0846028327941895, "global_step": 425889, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0499327182769775, "global_step": 425890, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0553760528564453, "global_step": 425891, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.071542978286743, "global_step": 425892, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.012542247772217, "global_step": 425893, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.217461347579956, "global_step": 425894, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1113383769989014, "global_step": 425895, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1164426803588867, "global_step": 425896, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.017486333847046, "global_step": 425897, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1327476501464844, "global_step": 425898, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.029876708984375, "global_step": 425899, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.12100887298584, "global_step": 425900, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0939786434173584, "global_step": 425901, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0758578777313232, "global_step": 425902, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0874335765838623, "global_step": 425903, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0977272987365723, "global_step": 425904, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9519259929656982, "global_step": 425905, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.182619094848633, "global_step": 425906, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.071653366088867, "global_step": 425907, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.110527276992798, "global_step": 425908, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.12341570854187, "global_step": 425909, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.132084608078003, "global_step": 425910, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.118367910385132, "global_step": 425911, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9816758632659912, "global_step": 425912, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1004130840301514, "global_step": 425913, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.136552095413208, "global_step": 425914, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0829873085021973, "global_step": 425915, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1352458000183105, "global_step": 425916, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.029167652130127, "global_step": 425917, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0590438842773438, "global_step": 425918, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.083798408508301, "global_step": 425919, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0894358158111572, "global_step": 425920, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.119499444961548, "global_step": 425921, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1303632259368896, "global_step": 425922, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.050261974334717, "global_step": 425923, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.055769443511963, "global_step": 425924, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0734879970550537, "global_step": 425925, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.017712354660034, "global_step": 425926, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1316962242126465, "global_step": 425927, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0693373680114746, "global_step": 425928, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9587465524673462, "global_step": 425929, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.115454912185669, "global_step": 425930, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0758934020996094, "global_step": 425931, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.163722038269043, "global_step": 425932, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0726420879364014, "global_step": 425933, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.039729118347168, "global_step": 425934, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0818607807159424, "global_step": 425935, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.996848702430725, "global_step": 425936, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1341662406921387, "global_step": 425937, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.151719331741333, "global_step": 425938, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9618561267852783, "global_step": 425939, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.116028308868408, "global_step": 425940, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.110532522201538, "global_step": 425941, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1908650398254395, "global_step": 425942, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1201987266540527, "global_step": 425943, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0572192668914795, "global_step": 425944, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0867087841033936, "global_step": 425945, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.156729221343994, "global_step": 425946, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0472259521484375, "global_step": 425947, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1263058185577393, "global_step": 425948, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0580666065216064, "global_step": 425949, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0183703899383545, "global_step": 425950, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.029710292816162, "global_step": 425951, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.059711456298828, "global_step": 425952, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0789706707000732, "global_step": 425953, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.046419143676758, "global_step": 425954, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0839788913726807, "global_step": 425955, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1072492599487305, "global_step": 425956, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0845837593078613, "global_step": 425957, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9798699617385864, "global_step": 425958, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.069613218307495, "global_step": 425959, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1060726642608643, "global_step": 425960, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1108648777008057, "global_step": 425961, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1674861907958984, "global_step": 425962, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.18449330329895, "global_step": 425963, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.107701063156128, "global_step": 425964, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1023948192596436, "global_step": 425965, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.108020305633545, "global_step": 425966, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.075895309448242, "global_step": 425967, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.114705801010132, "global_step": 425968, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0603139400482178, "global_step": 425969, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1034305095672607, "global_step": 425970, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0686893463134766, "global_step": 425971, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9885890483856201, "global_step": 425972, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.117262125015259, "global_step": 425973, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1697142124176025, "global_step": 425974, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0209386348724365, "global_step": 425975, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0142085552215576, "global_step": 425976, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0284721851348877, "global_step": 425977, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.109302043914795, "global_step": 425978, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0040504932403564, "global_step": 425979, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1153604984283447, "global_step": 425980, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0344271659851074, "global_step": 425981, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0313053131103516, "global_step": 425982, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0682687759399414, "global_step": 425983, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1019535064697266, "global_step": 425984, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0449233055114746, "global_step": 425985, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.149897813796997, "global_step": 425986, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1113314628601074, "global_step": 425987, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0379533767700195, "global_step": 425988, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.032005786895752, "global_step": 425989, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.036875009536743, "global_step": 425990, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1512765884399414, "global_step": 425991, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0951263904571533, "global_step": 425992, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.064239025115967, "global_step": 425993, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.040597438812256, "global_step": 425994, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.058892011642456, "global_step": 425995, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0778396129608154, "global_step": 425996, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0336201190948486, "global_step": 425997, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0637598037719727, "global_step": 425998, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1102006435394287, "global_step": 425999, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.043426513671875, "global_step": 426000, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0776216983795166, "global_step": 426001, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0771400928497314, "global_step": 426002, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.029383659362793, "global_step": 426003, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0318753719329834, "global_step": 426004, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0825865268707275, "global_step": 426005, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0243871212005615, "global_step": 426006, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1566758155822754, "global_step": 426007, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0622034072875977, "global_step": 426008, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.014044761657715, "global_step": 426009, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.103976011276245, "global_step": 426010, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0657284259796143, "global_step": 426011, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.070159912109375, "global_step": 426012, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.045879364013672, "global_step": 426013, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1102869510650635, "global_step": 426014, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.149473190307617, "global_step": 426015, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0648016929626465, "global_step": 426016, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1275808811187744, "global_step": 426017, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1222641468048096, "global_step": 426018, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.036562204360962, "global_step": 426019, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0687711238861084, "global_step": 426020, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0545666217803955, "global_step": 426021, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0254693031311035, "global_step": 426022, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0566487312316895, "global_step": 426023, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0513837337493896, "global_step": 426024, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0127484798431396, "global_step": 426025, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.133178234100342, "global_step": 426026, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1129796504974365, "global_step": 426027, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.119889259338379, "global_step": 426028, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.23045015335083, "global_step": 426029, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.098712682723999, "global_step": 426030, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.053907632827759, "global_step": 426031, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1532812118530273, "global_step": 426032, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.047797203063965, "global_step": 426033, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0857551097869873, "global_step": 426034, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.098207473754883, "global_step": 426035, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.089280366897583, "global_step": 426036, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1583480834960938, "global_step": 426037, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0742502212524414, "global_step": 426038, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0485990047454834, "global_step": 426039, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.044978141784668, "global_step": 426040, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.066739082336426, "global_step": 426041, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.036315441131592, "global_step": 426042, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.069206714630127, "global_step": 426043, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.119032382965088, "global_step": 426044, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.044037342071533, "global_step": 426045, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0753836631774902, "global_step": 426046, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0887057781219482, "global_step": 426047, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1117825508117676, "global_step": 426048, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0899665355682373, "global_step": 426049, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0774831771850586, "global_step": 426050, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0850062370300293, "global_step": 426051, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0474870204925537, "global_step": 426052, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.013792037963867, "global_step": 426053, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0829825401306152, "global_step": 426054, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9392327070236206, "global_step": 426055, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9993212223052979, "global_step": 426056, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.087890625, "global_step": 426057, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1390161514282227, "global_step": 426058, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0125057697296143, "global_step": 426059, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.113983154296875, "global_step": 426060, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.092554807662964, "global_step": 426061, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1233866214752197, "global_step": 426062, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0236618518829346, "global_step": 426063, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0341713428497314, "global_step": 426064, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.029447078704834, "global_step": 426065, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1059093475341797, "global_step": 426066, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0468385219573975, "global_step": 426067, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.087848424911499, "global_step": 426068, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0989975929260254, "global_step": 426069, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1459875106811523, "global_step": 426070, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0881025791168213, "global_step": 426071, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.168483257293701, "global_step": 426072, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0764710903167725, "global_step": 426073, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.076231002807617, "global_step": 426074, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.099428653717041, "global_step": 426075, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.080536365509033, "global_step": 426076, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.046245574951172, "global_step": 426077, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.04189395904541, "global_step": 426078, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.087186813354492, "global_step": 426079, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.073396921157837, "global_step": 426080, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0185234546661377, "global_step": 426081, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1205265522003174, "global_step": 426082, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0988616943359375, "global_step": 426083, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1556344032287598, "global_step": 426084, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9656717777252197, "global_step": 426085, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0401573181152344, "global_step": 426086, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.142287492752075, "global_step": 426087, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1642394065856934, "global_step": 426088, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0423786640167236, "global_step": 426089, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.119147777557373, "global_step": 426090, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1431145668029785, "global_step": 426091, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1301276683807373, "global_step": 426092, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1195273399353027, "global_step": 426093, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.156782865524292, "global_step": 426094, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.150949716567993, "global_step": 426095, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.032315969467163, "global_step": 426096, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1967580318450928, "global_step": 426097, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0900957584381104, "global_step": 426098, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.084146499633789, "global_step": 426099, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.048499584197998, "global_step": 426100, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.12692928314209, "global_step": 426101, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.032930374145508, "global_step": 426102, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.057443141937256, "global_step": 426103, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1006667613983154, "global_step": 426104, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.081085443496704, "global_step": 426105, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0434370040893555, "global_step": 426106, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.029633045196533, "global_step": 426107, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.08553409576416, "global_step": 426108, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0753865242004395, "global_step": 426109, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0990068912506104, "global_step": 426110, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1134111881256104, "global_step": 426111, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.101911783218384, "global_step": 426112, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.059664726257324, "global_step": 426113, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.039191722869873, "global_step": 426114, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0603020191192627, "global_step": 426115, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0871098041534424, "global_step": 426116, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.030219793319702, "global_step": 426117, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1224937438964844, "global_step": 426118, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0725595951080322, "global_step": 426119, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.072277307510376, "global_step": 426120, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1414506435394287, "global_step": 426121, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0712790489196777, "global_step": 426122, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.977244257926941, "global_step": 426123, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1004416942596436, "global_step": 426124, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0724453926086426, "global_step": 426125, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.108807325363159, "global_step": 426126, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1714727878570557, "global_step": 426127, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0532126426696777, "global_step": 426128, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.034682035446167, "global_step": 426129, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.01231050491333, "global_step": 426130, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0539395809173584, "global_step": 426131, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.072676658630371, "global_step": 426132, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.022958278656006, "global_step": 426133, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.063426971435547, "global_step": 426134, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0729525089263916, "global_step": 426135, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0757389068603516, "global_step": 426136, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1049089431762695, "global_step": 426137, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1184146404266357, "global_step": 426138, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0685715675354004, "global_step": 426139, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.084200143814087, "global_step": 426140, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.124324321746826, "global_step": 426141, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.062732219696045, "global_step": 426142, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.095555543899536, "global_step": 426143, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1615917682647705, "global_step": 426144, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0096023082733154, "global_step": 426145, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.089169979095459, "global_step": 426146, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0764710903167725, "global_step": 426147, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1108410358428955, "global_step": 426148, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.090075731277466, "global_step": 426149, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1036128997802734, "global_step": 426150, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0601119995117188, "global_step": 426151, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1448967456817627, "global_step": 426152, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9787710905075073, "global_step": 426153, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0944318771362305, "global_step": 426154, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0773489475250244, "global_step": 426155, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.070765495300293, "global_step": 426156, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1516659259796143, "global_step": 426157, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0607681274414062, "global_step": 426158, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0690040588378906, "global_step": 426159, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.141713857650757, "global_step": 426160, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1679458618164062, "global_step": 426161, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1318705081939697, "global_step": 426162, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1115317344665527, "global_step": 426163, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0492467880249023, "global_step": 426164, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.13352632522583, "global_step": 426165, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1110825538635254, "global_step": 426166, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.059227466583252, "global_step": 426167, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0698342323303223, "global_step": 426168, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.049237012863159, "global_step": 426169, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1245269775390625, "global_step": 426170, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.164325475692749, "global_step": 426171, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.116489887237549, "global_step": 426172, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.135322332382202, "global_step": 426173, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.960880160331726, "global_step": 426174, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1169211864471436, "global_step": 426175, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.085585594177246, "global_step": 426176, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.12094783782959, "global_step": 426177, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.2057712078094482, "global_step": 426178, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.099720001220703, "global_step": 426179, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0662925243377686, "global_step": 426180, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.057464361190796, "global_step": 426181, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1297969818115234, "global_step": 426182, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1491918563842773, "global_step": 426183, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.219966411590576, "global_step": 426184, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.157628297805786, "global_step": 426185, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.096484899520874, "global_step": 426186, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0921270847320557, "global_step": 426187, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9603512287139893, "global_step": 426188, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0888900756835938, "global_step": 426189, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.128709077835083, "global_step": 426190, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1167941093444824, "global_step": 426191, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1209628582000732, "global_step": 426192, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.170402765274048, "global_step": 426193, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1439719200134277, "global_step": 426194, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0507445335388184, "global_step": 426195, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0437192916870117, "global_step": 426196, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1040754318237305, "global_step": 426197, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1143834590911865, "global_step": 426198, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.104480266571045, "global_step": 426199, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.162572145462036, "global_step": 426200, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0719029903411865, "global_step": 426201, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0999741554260254, "global_step": 426202, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1151821613311768, "global_step": 426203, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.186689615249634, "global_step": 426204, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0465118885040283, "global_step": 426205, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0446951389312744, "global_step": 426206, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.107088565826416, "global_step": 426207, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0411574840545654, "global_step": 426208, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1498584747314453, "global_step": 426209, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.131334066390991, "global_step": 426210, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0800485610961914, "global_step": 426211, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1607558727264404, "global_step": 426212, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0977940559387207, "global_step": 426213, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.019906520843506, "global_step": 426214, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.014159679412842, "global_step": 426215, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.13505220413208, "global_step": 426216, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.138726234436035, "global_step": 426217, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0125625133514404, "global_step": 426218, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0732991695404053, "global_step": 426219, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.082901954650879, "global_step": 426220, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0455915927886963, "global_step": 426221, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.11286997795105, "global_step": 426222, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.026747226715088, "global_step": 426223, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.096940517425537, "global_step": 426224, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.134951114654541, "global_step": 426225, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0962159633636475, "global_step": 426226, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0538814067840576, "global_step": 426227, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0821104049682617, "global_step": 426228, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0720317363739014, "global_step": 426229, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.11159610748291, "global_step": 426230, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1220192909240723, "global_step": 426231, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.161198854446411, "global_step": 426232, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.081171751022339, "global_step": 426233, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1121110916137695, "global_step": 426234, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.123697519302368, "global_step": 426235, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.080902338027954, "global_step": 426236, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0846288204193115, "global_step": 426237, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.010568141937256, "global_step": 426238, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0946972370147705, "global_step": 426239, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.086953639984131, "global_step": 426240, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0973920822143555, "global_step": 426241, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.125359535217285, "global_step": 426242, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.097787857055664, "global_step": 426243, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.032719850540161, "global_step": 426244, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.102247476577759, "global_step": 426245, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1067566871643066, "global_step": 426246, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1399917602539062, "global_step": 426247, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0883049964904785, "global_step": 426248, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.078432321548462, "global_step": 426249, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.058436155319214, "global_step": 426250, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.076563835144043, "global_step": 426251, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.118468999862671, "global_step": 426252, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0861146450042725, "global_step": 426253, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.999764084815979, "global_step": 426254, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.060891628265381, "global_step": 426255, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0176665782928467, "global_step": 426256, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0000500679016113, "global_step": 426257, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.130392551422119, "global_step": 426258, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.096151828765869, "global_step": 426259, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.111711025238037, "global_step": 426260, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.116834878921509, "global_step": 426261, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.085901975631714, "global_step": 426262, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.2033846378326416, "global_step": 426263, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1169605255126953, "global_step": 426264, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.115007162094116, "global_step": 426265, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.051182270050049, "global_step": 426266, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9520058631896973, "global_step": 426267, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.107663869857788, "global_step": 426268, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.123548746109009, "global_step": 426269, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1621737480163574, "global_step": 426270, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0491409301757812, "global_step": 426271, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.120622396469116, "global_step": 426272, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.035377264022827, "global_step": 426273, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.098257541656494, "global_step": 426274, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0232787132263184, "global_step": 426275, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.103752851486206, "global_step": 426276, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0459837913513184, "global_step": 426277, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.045841693878174, "global_step": 426278, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.151854991912842, "global_step": 426279, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0911805629730225, "global_step": 426280, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.162940263748169, "global_step": 426281, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1112875938415527, "global_step": 426282, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.116974115371704, "global_step": 426283, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.100263833999634, "global_step": 426284, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0779778957366943, "global_step": 426285, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.064762830734253, "global_step": 426286, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1666855812072754, "global_step": 426287, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0459811687469482, "global_step": 426288, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.070984363555908, "global_step": 426289, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.116867780685425, "global_step": 426290, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1498541831970215, "global_step": 426291, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1103439331054688, "global_step": 426292, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.086674928665161, "global_step": 426293, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.056446075439453, "global_step": 426294, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0547378063201904, "global_step": 426295, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0806756019592285, "global_step": 426296, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.069317579269409, "global_step": 426297, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0570950508117676, "global_step": 426298, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0878806114196777, "global_step": 426299, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0718448162078857, "global_step": 426300, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.105076789855957, "global_step": 426301, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.109767198562622, "global_step": 426302, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.121988296508789, "global_step": 426303, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1091501712799072, "global_step": 426304, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1492221355438232, "global_step": 426305, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1691880226135254, "global_step": 426306, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0596632957458496, "global_step": 426307, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0258595943450928, "global_step": 426308, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0986406803131104, "global_step": 426309, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0535364151000977, "global_step": 426310, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0253918170928955, "global_step": 426311, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0346834659576416, "global_step": 426312, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.048996686935425, "global_step": 426313, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.039529800415039, "global_step": 426314, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0670273303985596, "global_step": 426315, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0839684009552, "global_step": 426316, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0752415657043457, "global_step": 426317, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.123609781265259, "global_step": 426318, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0287346839904785, "global_step": 426319, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1439130306243896, "global_step": 426320, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1344857215881348, "global_step": 426321, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.118135452270508, "global_step": 426322, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1648049354553223, "global_step": 426323, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.062330961227417, "global_step": 426324, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0804572105407715, "global_step": 426325, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.165823221206665, "global_step": 426326, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1065895557403564, "global_step": 426327, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0599732398986816, "global_step": 426328, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.122260570526123, "global_step": 426329, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.160827875137329, "global_step": 426330, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0176165103912354, "global_step": 426331, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.217266082763672, "global_step": 426332, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0704123973846436, "global_step": 426333, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.012993335723877, "global_step": 426334, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0310757160186768, "global_step": 426335, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0602920055389404, "global_step": 426336, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.116067886352539, "global_step": 426337, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0271897315979004, "global_step": 426338, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1240155696868896, "global_step": 426339, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1443207263946533, "global_step": 426340, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0274739265441895, "global_step": 426341, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.127080202102661, "global_step": 426342, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.004441022872925, "global_step": 426343, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1693708896636963, "global_step": 426344, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.096853256225586, "global_step": 426345, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.129857063293457, "global_step": 426346, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.142662286758423, "global_step": 426347, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0882060527801514, "global_step": 426348, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0712978839874268, "global_step": 426349, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1440317630767822, "global_step": 426350, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.094836711883545, "global_step": 426351, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.114915609359741, "global_step": 426352, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.114590883255005, "global_step": 426353, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1425273418426514, "global_step": 426354, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0941786766052246, "global_step": 426355, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0499343872070312, "global_step": 426356, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1014387607574463, "global_step": 426357, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1452245712280273, "global_step": 426358, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0927481651306152, "global_step": 426359, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1875531673431396, "global_step": 426360, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0567564964294434, "global_step": 426361, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1098663806915283, "global_step": 426362, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9905638694763184, "global_step": 426363, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.05515193939209, "global_step": 426364, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.079652786254883, "global_step": 426365, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.021198034286499, "global_step": 426366, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.032698631286621, "global_step": 426367, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.044013261795044, "global_step": 426368, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.101935386657715, "global_step": 426369, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.135092258453369, "global_step": 426370, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0274605751037598, "global_step": 426371, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0512919425964355, "global_step": 426372, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0502333641052246, "global_step": 426373, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0288405418395996, "global_step": 426374, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.134258508682251, "global_step": 426375, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.088381767272949, "global_step": 426376, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0414786338806152, "global_step": 426377, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1478219032287598, "global_step": 426378, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1068451404571533, "global_step": 426379, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0751802921295166, "global_step": 426380, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.17722225189209, "global_step": 426381, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0301127433776855, "global_step": 426382, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0220162868499756, "global_step": 426383, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0594840049743652, "global_step": 426384, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.038774013519287, "global_step": 426385, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.187403440475464, "global_step": 426386, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0701634883880615, "global_step": 426387, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.065269947052002, "global_step": 426388, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.066488742828369, "global_step": 426389, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1058170795440674, "global_step": 426390, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.006873607635498, "global_step": 426391, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0961570739746094, "global_step": 426392, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1863112449645996, "global_step": 426393, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1833083629608154, "global_step": 426394, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1232433319091797, "global_step": 426395, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.048809289932251, "global_step": 426396, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.124530792236328, "global_step": 426397, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.099735975265503, "global_step": 426398, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0344831943511963, "global_step": 426399, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1218552589416504, "global_step": 426400, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1218764781951904, "global_step": 426401, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.113152503967285, "global_step": 426402, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.991395115852356, "global_step": 426403, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1158993244171143, "global_step": 426404, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.077882766723633, "global_step": 426405, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0600104331970215, "global_step": 426406, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0445947647094727, "global_step": 426407, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0449416637420654, "global_step": 426408, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0809242725372314, "global_step": 426409, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.100825071334839, "global_step": 426410, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0646862983703613, "global_step": 426411, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1253252029418945, "global_step": 426412, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0887441635131836, "global_step": 426413, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0511891841888428, "global_step": 426414, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0779054164886475, "global_step": 426415, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.080695152282715, "global_step": 426416, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1492855548858643, "global_step": 426417, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.066035509109497, "global_step": 426418, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.113060474395752, "global_step": 426419, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1445672512054443, "global_step": 426420, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.210247278213501, "global_step": 426421, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.073777914047241, "global_step": 426422, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1675102710723877, "global_step": 426423, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.084521532058716, "global_step": 426424, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.000586748123169, "global_step": 426425, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0282466411590576, "global_step": 426426, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9866491556167603, "global_step": 426427, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0599632263183594, "global_step": 426428, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0757761001586914, "global_step": 426429, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.075685977935791, "global_step": 426430, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1107795238494873, "global_step": 426431, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1459715366363525, "global_step": 426432, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.013460874557495, "global_step": 426433, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0879299640655518, "global_step": 426434, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.029045343399048, "global_step": 426435, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9725021123886108, "global_step": 426436, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1683757305145264, "global_step": 426437, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.097642660140991, "global_step": 426438, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1640074253082275, "global_step": 426439, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.073078155517578, "global_step": 426440, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.143568277359009, "global_step": 426441, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0830819606781006, "global_step": 426442, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.137763261795044, "global_step": 426443, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1532533168792725, "global_step": 426444, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.058492660522461, "global_step": 426445, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.052096128463745, "global_step": 426446, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0517704486846924, "global_step": 426447, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.091369867324829, "global_step": 426448, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.100504159927368, "global_step": 426449, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.100935697555542, "global_step": 426450, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1602845191955566, "global_step": 426451, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0618395805358887, "global_step": 426452, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0533089637756348, "global_step": 426453, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0843160152435303, "global_step": 426454, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0801661014556885, "global_step": 426455, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.079550266265869, "global_step": 426456, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.066446542739868, "global_step": 426457, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1257312297821045, "global_step": 426458, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0582730770111084, "global_step": 426459, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0529704093933105, "global_step": 426460, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.076338291168213, "global_step": 426461, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0514769554138184, "global_step": 426462, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1073577404022217, "global_step": 426463, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.061583995819092, "global_step": 426464, "epoch": 789, "lr": 5e-05}
{"train_loss": 1.9966999292373657, "global_step": 426465, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.056865692138672, "global_step": 426466, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.204772710800171, "global_step": 426467, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1151816844940186, "global_step": 426468, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1333446502685547, "global_step": 426469, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.2271010875701904, "global_step": 426470, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1207516193389893, "global_step": 426471, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0726208686828613, "global_step": 426472, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.087763547897339, "global_step": 426473, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.027963399887085, "global_step": 426474, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0775301456451416, "global_step": 426475, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1284706592559814, "global_step": 426476, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0960142612457275, "global_step": 426477, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.183706760406494, "global_step": 426478, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.145822286605835, "global_step": 426479, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0505423545837402, "global_step": 426480, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.115213632583618, "global_step": 426481, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.091773271560669, "global_step": 426482, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0779294967651367, "global_step": 426483, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0982747077941895, "global_step": 426484, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1127123832702637, "global_step": 426485, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1111714839935303, "global_step": 426486, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.086430788040161, "global_step": 426487, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.082329273223877, "global_step": 426488, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.069516658782959, "global_step": 426489, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.077451705932617, "global_step": 426490, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0915613174438477, "global_step": 426491, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.0845141410827637, "global_step": 426492, "epoch": 789, "lr": 5e-05}
{"train_loss": 2.1000030040740967, "global_step": 426493, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1062943935394287, "global_step": 426494, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.038830518722534, "global_step": 426495, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1115753650665283, "global_step": 426496, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1622519493103027, "global_step": 426497, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.066857099533081, "global_step": 426498, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.021719455718994, "global_step": 426499, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9652962684631348, "global_step": 426500, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0747711658477783, "global_step": 426501, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.040541410446167, "global_step": 426502, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.111224889755249, "global_step": 426503, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0238068103790283, "global_step": 426504, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0231759548187256, "global_step": 426505, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.092081069946289, "global_step": 426506, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.087061882019043, "global_step": 426507, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0966989994049072, "global_step": 426508, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.015683174133301, "global_step": 426509, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.036072254180908, "global_step": 426510, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1564042568206787, "global_step": 426511, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0083630084991455, "global_step": 426512, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0398716926574707, "global_step": 426513, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0564322471618652, "global_step": 426514, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.046107769012451, "global_step": 426515, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.028918981552124, "global_step": 426516, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.066570281982422, "global_step": 426517, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.031399965286255, "global_step": 426518, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1122238636016846, "global_step": 426519, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0034525394439697, "global_step": 426520, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.103822708129883, "global_step": 426521, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0916624069213867, "global_step": 426522, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0998764038085938, "global_step": 426523, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0696959495544434, "global_step": 426524, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1389217376708984, "global_step": 426525, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0475881099700928, "global_step": 426526, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0342941284179688, "global_step": 426527, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.065159797668457, "global_step": 426528, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0468099117279053, "global_step": 426529, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0120608806610107, "global_step": 426530, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.107309341430664, "global_step": 426531, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0622663497924805, "global_step": 426532, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0013530254364014, "global_step": 426533, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.06467866897583, "global_step": 426534, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1077003479003906, "global_step": 426535, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1758742332458496, "global_step": 426536, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.054898262023926, "global_step": 426537, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0619008541107178, "global_step": 426538, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1612298488616943, "global_step": 426539, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1288623809814453, "global_step": 426540, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.075714588165283, "global_step": 426541, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0601089000701904, "global_step": 426542, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0203866958618164, "global_step": 426543, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0415494441986084, "global_step": 426544, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.018144369125366, "global_step": 426545, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.042344093322754, "global_step": 426546, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.102617025375366, "global_step": 426547, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9943852424621582, "global_step": 426548, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.096369743347168, "global_step": 426549, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0725114345550537, "global_step": 426550, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9996306896209717, "global_step": 426551, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0604820251464844, "global_step": 426552, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.073157787322998, "global_step": 426553, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0900158882141113, "global_step": 426554, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0222437381744385, "global_step": 426555, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.009870767593384, "global_step": 426556, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0459132194519043, "global_step": 426557, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0308642387390137, "global_step": 426558, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.072277069091797, "global_step": 426559, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1072757244110107, "global_step": 426560, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0915048122406006, "global_step": 426561, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.049039840698242, "global_step": 426562, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0457000732421875, "global_step": 426563, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0619149208068848, "global_step": 426564, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.125051736831665, "global_step": 426565, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0965185165405273, "global_step": 426566, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0925467014312744, "global_step": 426567, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.192840814590454, "global_step": 426568, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.062356472015381, "global_step": 426569, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0709569454193115, "global_step": 426570, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1002912521362305, "global_step": 426571, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0513193607330322, "global_step": 426572, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.092247247695923, "global_step": 426573, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1414358615875244, "global_step": 426574, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.104241371154785, "global_step": 426575, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.110948324203491, "global_step": 426576, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.132633924484253, "global_step": 426577, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0338473320007324, "global_step": 426578, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.07757306098938, "global_step": 426579, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.011789321899414, "global_step": 426580, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0328779220581055, "global_step": 426581, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0839805603027344, "global_step": 426582, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0952508449554443, "global_step": 426583, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.139585256576538, "global_step": 426584, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.056596040725708, "global_step": 426585, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1952943801879883, "global_step": 426586, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.083869457244873, "global_step": 426587, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1576762199401855, "global_step": 426588, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1018307209014893, "global_step": 426589, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.141496181488037, "global_step": 426590, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0579535961151123, "global_step": 426591, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0790557861328125, "global_step": 426592, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0575101375579834, "global_step": 426593, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.167245626449585, "global_step": 426594, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.067246437072754, "global_step": 426595, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1350300312042236, "global_step": 426596, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0232529640197754, "global_step": 426597, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.074821949005127, "global_step": 426598, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1312944889068604, "global_step": 426599, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0661191940307617, "global_step": 426600, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.129566192626953, "global_step": 426601, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1110215187072754, "global_step": 426602, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0822131633758545, "global_step": 426603, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0230116844177246, "global_step": 426604, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.062863826751709, "global_step": 426605, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0414490699768066, "global_step": 426606, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1280062198638916, "global_step": 426607, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1576170921325684, "global_step": 426608, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0368165969848633, "global_step": 426609, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0808467864990234, "global_step": 426610, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.055070161819458, "global_step": 426611, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0060253143310547, "global_step": 426612, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0687294006347656, "global_step": 426613, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0870893001556396, "global_step": 426614, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0566563606262207, "global_step": 426615, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1386923789978027, "global_step": 426616, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.040081024169922, "global_step": 426617, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.066084623336792, "global_step": 426618, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0696659088134766, "global_step": 426619, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.068814754486084, "global_step": 426620, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.047196626663208, "global_step": 426621, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1162893772125244, "global_step": 426622, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.032835006713867, "global_step": 426623, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.083261013031006, "global_step": 426624, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.116288661956787, "global_step": 426625, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.006213426589966, "global_step": 426626, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0250117778778076, "global_step": 426627, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.156219720840454, "global_step": 426628, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.145103931427002, "global_step": 426629, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.039398670196533, "global_step": 426630, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1173980236053467, "global_step": 426631, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.067924976348877, "global_step": 426632, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.038451910018921, "global_step": 426633, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0766894817352295, "global_step": 426634, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0525741577148438, "global_step": 426635, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0738632678985596, "global_step": 426636, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.028111219406128, "global_step": 426637, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.007728338241577, "global_step": 426638, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.056657314300537, "global_step": 426639, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1104073524475098, "global_step": 426640, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.980271339416504, "global_step": 426641, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.07649827003479, "global_step": 426642, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.080659866333008, "global_step": 426643, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.099274158477783, "global_step": 426644, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1007657051086426, "global_step": 426645, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0741748809814453, "global_step": 426646, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.023812770843506, "global_step": 426647, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0760996341705322, "global_step": 426648, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.01230525970459, "global_step": 426649, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.113107919692993, "global_step": 426650, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0743157863616943, "global_step": 426651, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.04044771194458, "global_step": 426652, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1872637271881104, "global_step": 426653, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.063910722732544, "global_step": 426654, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.074810266494751, "global_step": 426655, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.062685251235962, "global_step": 426656, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.05230712890625, "global_step": 426657, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0318357944488525, "global_step": 426658, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0832598209381104, "global_step": 426659, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.080373525619507, "global_step": 426660, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1287646293640137, "global_step": 426661, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.035004138946533, "global_step": 426662, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0317282676696777, "global_step": 426663, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.110342264175415, "global_step": 426664, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.026078701019287, "global_step": 426665, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0722579956054688, "global_step": 426666, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0227198600769043, "global_step": 426667, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.055647134780884, "global_step": 426668, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0301246643066406, "global_step": 426669, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0793657302856445, "global_step": 426670, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1436705589294434, "global_step": 426671, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.08880352973938, "global_step": 426672, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.140071153640747, "global_step": 426673, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1421775817871094, "global_step": 426674, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.079221725463867, "global_step": 426675, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0863335132598877, "global_step": 426676, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.127526044845581, "global_step": 426677, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0180037021636963, "global_step": 426678, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1323859691619873, "global_step": 426679, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0842459201812744, "global_step": 426680, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0494399070739746, "global_step": 426681, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1446146965026855, "global_step": 426682, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0742571353912354, "global_step": 426683, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1728644371032715, "global_step": 426684, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0994186401367188, "global_step": 426685, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.158951997756958, "global_step": 426686, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.063037633895874, "global_step": 426687, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0766592025756836, "global_step": 426688, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.172666072845459, "global_step": 426689, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.046630382537842, "global_step": 426690, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0558645725250244, "global_step": 426691, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0292105674743652, "global_step": 426692, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.119919538497925, "global_step": 426693, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0276756286621094, "global_step": 426694, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1288280487060547, "global_step": 426695, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.114454984664917, "global_step": 426696, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.094547748565674, "global_step": 426697, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0444798469543457, "global_step": 426698, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.079392194747925, "global_step": 426699, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.044990062713623, "global_step": 426700, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.117696762084961, "global_step": 426701, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1105785369873047, "global_step": 426702, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.088897943496704, "global_step": 426703, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0988667011260986, "global_step": 426704, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.055279493331909, "global_step": 426705, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9757652282714844, "global_step": 426706, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.094259262084961, "global_step": 426707, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0906624794006348, "global_step": 426708, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.068267822265625, "global_step": 426709, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9679702520370483, "global_step": 426710, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1071503162384033, "global_step": 426711, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.137364625930786, "global_step": 426712, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9667575359344482, "global_step": 426713, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.007683753967285, "global_step": 426714, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.168687343597412, "global_step": 426715, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.122335433959961, "global_step": 426716, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.066565990447998, "global_step": 426717, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0571489334106445, "global_step": 426718, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0142252445220947, "global_step": 426719, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.047236919403076, "global_step": 426720, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0831849575042725, "global_step": 426721, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9857553243637085, "global_step": 426722, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0139572620391846, "global_step": 426723, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.051720380783081, "global_step": 426724, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.179445266723633, "global_step": 426725, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0220091342926025, "global_step": 426726, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.050436496734619, "global_step": 426727, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0396225452423096, "global_step": 426728, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0536739826202393, "global_step": 426729, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.060304641723633, "global_step": 426730, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1157829761505127, "global_step": 426731, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.040820598602295, "global_step": 426732, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0413434505462646, "global_step": 426733, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.045607805252075, "global_step": 426734, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.04476261138916, "global_step": 426735, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0944015979766846, "global_step": 426736, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1161410808563232, "global_step": 426737, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.063798666000366, "global_step": 426738, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.085676908493042, "global_step": 426739, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1033639907836914, "global_step": 426740, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0463943481445312, "global_step": 426741, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.201603651046753, "global_step": 426742, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.095339298248291, "global_step": 426743, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0891404151916504, "global_step": 426744, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0624992847442627, "global_step": 426745, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1071531772613525, "global_step": 426746, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0352115631103516, "global_step": 426747, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.125598430633545, "global_step": 426748, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1174392700195312, "global_step": 426749, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.078991413116455, "global_step": 426750, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0729830265045166, "global_step": 426751, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1590652465820312, "global_step": 426752, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.050095796585083, "global_step": 426753, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.165994167327881, "global_step": 426754, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1394920349121094, "global_step": 426755, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.088390827178955, "global_step": 426756, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0134525299072266, "global_step": 426757, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.12667179107666, "global_step": 426758, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0854406356811523, "global_step": 426759, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0437233448028564, "global_step": 426760, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.998397707939148, "global_step": 426761, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.102306604385376, "global_step": 426762, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.101712703704834, "global_step": 426763, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9621883630752563, "global_step": 426764, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9936890602111816, "global_step": 426765, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1022822856903076, "global_step": 426766, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0026702880859375, "global_step": 426767, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.099919080734253, "global_step": 426768, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1328461170196533, "global_step": 426769, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1137278079986572, "global_step": 426770, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0519611835479736, "global_step": 426771, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.081118106842041, "global_step": 426772, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.118255376815796, "global_step": 426773, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1524713039398193, "global_step": 426774, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1676652431488037, "global_step": 426775, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.136563539505005, "global_step": 426776, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0444693565368652, "global_step": 426777, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.146413803100586, "global_step": 426778, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.062929153442383, "global_step": 426779, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0675697326660156, "global_step": 426780, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0954151153564453, "global_step": 426781, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0902445316314697, "global_step": 426782, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0630393028259277, "global_step": 426783, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.14516282081604, "global_step": 426784, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1089119911193848, "global_step": 426785, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0814998149871826, "global_step": 426786, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.004612684249878, "global_step": 426787, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0280380249023438, "global_step": 426788, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1741139888763428, "global_step": 426789, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.029749870300293, "global_step": 426790, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0695433616638184, "global_step": 426791, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0612337589263916, "global_step": 426792, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.065711498260498, "global_step": 426793, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.072171449661255, "global_step": 426794, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1300160884857178, "global_step": 426795, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.172109603881836, "global_step": 426796, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.050851821899414, "global_step": 426797, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0622620582580566, "global_step": 426798, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1839067935943604, "global_step": 426799, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.107536554336548, "global_step": 426800, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1729047298431396, "global_step": 426801, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0951039791107178, "global_step": 426802, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1053149700164795, "global_step": 426803, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.15678071975708, "global_step": 426804, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0513203144073486, "global_step": 426805, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.078486919403076, "global_step": 426806, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0882670879364014, "global_step": 426807, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.041095733642578, "global_step": 426808, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1183388233184814, "global_step": 426809, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9746159315109253, "global_step": 426810, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.055508613586426, "global_step": 426811, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.086148262023926, "global_step": 426812, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.093156337738037, "global_step": 426813, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1294121742248535, "global_step": 426814, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0942654609680176, "global_step": 426815, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0950124263763428, "global_step": 426816, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0141396522521973, "global_step": 426817, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.110755205154419, "global_step": 426818, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9795995950698853, "global_step": 426819, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0892221927642822, "global_step": 426820, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0015227794647217, "global_step": 426821, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.105494737625122, "global_step": 426822, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0885190963745117, "global_step": 426823, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0735998153686523, "global_step": 426824, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0472569465637207, "global_step": 426825, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0665788650512695, "global_step": 426826, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0203444957733154, "global_step": 426827, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.144451379776001, "global_step": 426828, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.022453546524048, "global_step": 426829, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.040982723236084, "global_step": 426830, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9991382360458374, "global_step": 426831, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.007666826248169, "global_step": 426832, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0628833770751953, "global_step": 426833, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9923039674758911, "global_step": 426834, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.092893362045288, "global_step": 426835, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.067735433578491, "global_step": 426836, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.109457015991211, "global_step": 426837, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.09955096244812, "global_step": 426838, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.076031446456909, "global_step": 426839, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0914344787597656, "global_step": 426840, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1321699619293213, "global_step": 426841, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0694873332977295, "global_step": 426842, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0353267192840576, "global_step": 426843, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1009745597839355, "global_step": 426844, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.167264699935913, "global_step": 426845, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0696628093719482, "global_step": 426846, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.155073404312134, "global_step": 426847, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1460916996002197, "global_step": 426848, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.087383270263672, "global_step": 426849, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.018345355987549, "global_step": 426850, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1354482173919678, "global_step": 426851, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1264076232910156, "global_step": 426852, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0454282760620117, "global_step": 426853, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0342187881469727, "global_step": 426854, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.106553554534912, "global_step": 426855, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9902880191802979, "global_step": 426856, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.042574882507324, "global_step": 426857, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1407904624938965, "global_step": 426858, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.108063220977783, "global_step": 426859, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1541593074798584, "global_step": 426860, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1460530757904053, "global_step": 426861, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.081979274749756, "global_step": 426862, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.02762770652771, "global_step": 426863, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0751266479492188, "global_step": 426864, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.068267583847046, "global_step": 426865, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.106546640396118, "global_step": 426866, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0284719467163086, "global_step": 426867, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.160629987716675, "global_step": 426868, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.09466552734375, "global_step": 426869, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.069521188735962, "global_step": 426870, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1059820652008057, "global_step": 426871, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0168581008911133, "global_step": 426872, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1596925258636475, "global_step": 426873, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1103413105010986, "global_step": 426874, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.092315912246704, "global_step": 426875, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.18271541595459, "global_step": 426876, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.099569082260132, "global_step": 426877, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.131789445877075, "global_step": 426878, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1835389137268066, "global_step": 426879, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9897433519363403, "global_step": 426880, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1499860286712646, "global_step": 426881, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0379812717437744, "global_step": 426882, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0860066413879395, "global_step": 426883, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1184422969818115, "global_step": 426884, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0859241485595703, "global_step": 426885, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0888607501983643, "global_step": 426886, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.129734516143799, "global_step": 426887, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0693438053131104, "global_step": 426888, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.019221544265747, "global_step": 426889, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.082514524459839, "global_step": 426890, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0216615200042725, "global_step": 426891, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0826125144958496, "global_step": 426892, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1761178970336914, "global_step": 426893, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0348520278930664, "global_step": 426894, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.078199863433838, "global_step": 426895, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0324630737304688, "global_step": 426896, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.090336322784424, "global_step": 426897, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0334885120391846, "global_step": 426898, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0758543014526367, "global_step": 426899, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0573384761810303, "global_step": 426900, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9985787868499756, "global_step": 426901, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.120561361312866, "global_step": 426902, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0556282997131348, "global_step": 426903, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.126108169555664, "global_step": 426904, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1233463287353516, "global_step": 426905, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1245994567871094, "global_step": 426906, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.070525884628296, "global_step": 426907, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.086575508117676, "global_step": 426908, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0856568813323975, "global_step": 426909, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1144063472747803, "global_step": 426910, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.091885805130005, "global_step": 426911, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.139620304107666, "global_step": 426912, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0597991943359375, "global_step": 426913, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.994779109954834, "global_step": 426914, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.065059185028076, "global_step": 426915, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.225790023803711, "global_step": 426916, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0453133583068848, "global_step": 426917, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0397281646728516, "global_step": 426918, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1171460151672363, "global_step": 426919, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.133270502090454, "global_step": 426920, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.051210641860962, "global_step": 426921, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.128192663192749, "global_step": 426922, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0133450031280518, "global_step": 426923, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1147572994232178, "global_step": 426924, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1123974323272705, "global_step": 426925, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0519134998321533, "global_step": 426926, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0799920558929443, "global_step": 426927, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0903055667877197, "global_step": 426928, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0087366104125977, "global_step": 426929, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1380996704101562, "global_step": 426930, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0390100479125977, "global_step": 426931, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.07552433013916, "global_step": 426932, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9240974187850952, "global_step": 426933, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0636088848114014, "global_step": 426934, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0456323623657227, "global_step": 426935, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0550692081451416, "global_step": 426936, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0266025066375732, "global_step": 426937, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.107933282852173, "global_step": 426938, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1433582305908203, "global_step": 426939, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0939064025878906, "global_step": 426940, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.091543436050415, "global_step": 426941, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.2281060218811035, "global_step": 426942, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.040564775466919, "global_step": 426943, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0992770195007324, "global_step": 426944, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.100477933883667, "global_step": 426945, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0816047191619873, "global_step": 426946, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.117943525314331, "global_step": 426947, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0827014446258545, "global_step": 426948, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1658027172088623, "global_step": 426949, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1531057357788086, "global_step": 426950, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.114837646484375, "global_step": 426951, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.086702823638916, "global_step": 426952, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.091111660003662, "global_step": 426953, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.2051148414611816, "global_step": 426954, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.195702314376831, "global_step": 426955, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.101489782333374, "global_step": 426956, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0349009037017822, "global_step": 426957, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.079177141189575, "global_step": 426958, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.049360990524292, "global_step": 426959, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.053025960922241, "global_step": 426960, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.988600492477417, "global_step": 426961, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.125242233276367, "global_step": 426962, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0457913875579834, "global_step": 426963, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0959153175354004, "global_step": 426964, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.123619318008423, "global_step": 426965, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.065591335296631, "global_step": 426966, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.992019534111023, "global_step": 426967, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1369502544403076, "global_step": 426968, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0309321880340576, "global_step": 426969, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.14416766166687, "global_step": 426970, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.08148455619812, "global_step": 426971, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.074071168899536, "global_step": 426972, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0894219875335693, "global_step": 426973, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0294113159179688, "global_step": 426974, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.11140775680542, "global_step": 426975, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.042393207550049, "global_step": 426976, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.139577627182007, "global_step": 426977, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.098684072494507, "global_step": 426978, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0430233478546143, "global_step": 426979, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.988591194152832, "global_step": 426980, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.139876127243042, "global_step": 426981, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1010804176330566, "global_step": 426982, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.062206506729126, "global_step": 426983, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1218650341033936, "global_step": 426984, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0742549896240234, "global_step": 426985, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9875739812850952, "global_step": 426986, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0968308448791504, "global_step": 426987, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.106748580932617, "global_step": 426988, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0970847606658936, "global_step": 426989, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0816173553466797, "global_step": 426990, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0631306171417236, "global_step": 426991, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0308592319488525, "global_step": 426992, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1549437046051025, "global_step": 426993, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.144605875015259, "global_step": 426994, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.071502923965454, "global_step": 426995, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1210596561431885, "global_step": 426996, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.104687452316284, "global_step": 426997, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.162719964981079, "global_step": 426998, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.106928586959839, "global_step": 426999, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1025922298431396, "global_step": 427000, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.083940267562866, "global_step": 427001, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1864683628082275, "global_step": 427002, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0558202266693115, "global_step": 427003, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.176004648208618, "global_step": 427004, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.09147047996521, "global_step": 427005, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0157556533813477, "global_step": 427006, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1034421920776367, "global_step": 427007, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.070101737976074, "global_step": 427008, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0849108695983887, "global_step": 427009, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.070809841156006, "global_step": 427010, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1133196353912354, "global_step": 427011, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.120128870010376, "global_step": 427012, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.058480978012085, "global_step": 427013, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0780258178710938, "global_step": 427014, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0581979751586914, "global_step": 427015, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.125917673110962, "global_step": 427016, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0915186405181885, "global_step": 427017, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.08819842338562, "global_step": 427018, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1321539878845215, "global_step": 427019, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0788211822509766, "global_step": 427020, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.125558853149414, "global_step": 427021, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.092852830886841, "global_step": 427022, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0740554332733154, "global_step": 427023, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0413568019866943, "global_step": 427024, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0836021900177, "global_step": 427025, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0355074405670166, "global_step": 427026, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0979907512664795, "global_step": 427027, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1575400829315186, "global_step": 427028, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.053906202316284, "global_step": 427029, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1299850940704346, "global_step": 427030, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0467112064361572, "global_step": 427031, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0907480716705322, "global_step": 427032, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0823354721069336, "global_step": 427033, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.149975299835205, "global_step": 427034, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1588635444641113, "global_step": 427035, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.026068925857544, "global_step": 427036, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0425868034362793, "global_step": 427037, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.072415351867676, "global_step": 427038, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.00063419342041, "global_step": 427039, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1425869464874268, "global_step": 427040, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0335190296173096, "global_step": 427041, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.122016191482544, "global_step": 427042, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0054004192352295, "global_step": 427043, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.085367202758789, "global_step": 427044, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.02305006980896, "global_step": 427045, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.020585775375366, "global_step": 427046, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.13319730758667, "global_step": 427047, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0748348236083984, "global_step": 427048, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0469648838043213, "global_step": 427049, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.198596715927124, "global_step": 427050, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0018057823181152, "global_step": 427051, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.075427770614624, "global_step": 427052, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0666770935058594, "global_step": 427053, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.034210681915283, "global_step": 427054, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0356686115264893, "global_step": 427055, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0518617630004883, "global_step": 427056, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0720608234405518, "global_step": 427057, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.023818254470825, "global_step": 427058, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1621251106262207, "global_step": 427059, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0436480045318604, "global_step": 427060, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1082537174224854, "global_step": 427061, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1047022342681885, "global_step": 427062, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.071763038635254, "global_step": 427063, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.987377405166626, "global_step": 427064, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0556089878082275, "global_step": 427065, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0677361488342285, "global_step": 427066, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.111318588256836, "global_step": 427067, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.109858512878418, "global_step": 427068, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.218505620956421, "global_step": 427069, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9276739358901978, "global_step": 427070, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1282358169555664, "global_step": 427071, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9934003353118896, "global_step": 427072, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0390424728393555, "global_step": 427073, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.12963604927063, "global_step": 427074, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.117600202560425, "global_step": 427075, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0874881744384766, "global_step": 427076, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0278286933898926, "global_step": 427077, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.071706771850586, "global_step": 427078, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9742345809936523, "global_step": 427079, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0311625003814697, "global_step": 427080, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0993459224700928, "global_step": 427081, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0779552459716797, "global_step": 427082, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.982914686203003, "global_step": 427083, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1135313510894775, "global_step": 427084, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.079669713973999, "global_step": 427085, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1017563343048096, "global_step": 427086, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1150848865509033, "global_step": 427087, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1044931411743164, "global_step": 427088, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9834109544754028, "global_step": 427089, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.04723858833313, "global_step": 427090, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.978778600692749, "global_step": 427091, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0332179069519043, "global_step": 427092, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.066871404647827, "global_step": 427093, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.050694227218628, "global_step": 427094, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0352439880371094, "global_step": 427095, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.092867374420166, "global_step": 427096, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1224565505981445, "global_step": 427097, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1378326416015625, "global_step": 427098, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0833191871643066, "global_step": 427099, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.204719066619873, "global_step": 427100, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.143787384033203, "global_step": 427101, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1695916652679443, "global_step": 427102, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0435338020324707, "global_step": 427103, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.047074794769287, "global_step": 427104, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1193346977233887, "global_step": 427105, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0435264110565186, "global_step": 427106, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.078673839569092, "global_step": 427107, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0510997772216797, "global_step": 427108, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1086511611938477, "global_step": 427109, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0159215927124023, "global_step": 427110, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.103381872177124, "global_step": 427111, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0611038208007812, "global_step": 427112, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.118234872817993, "global_step": 427113, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.029815673828125, "global_step": 427114, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1050541400909424, "global_step": 427115, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0931873321533203, "global_step": 427116, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1700892448425293, "global_step": 427117, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0366756916046143, "global_step": 427118, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0431416034698486, "global_step": 427119, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1615407466888428, "global_step": 427120, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0710647106170654, "global_step": 427121, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9722375869750977, "global_step": 427122, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.2090208530426025, "global_step": 427123, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.158881902694702, "global_step": 427124, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1152055263519287, "global_step": 427125, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.151291847229004, "global_step": 427126, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.069265842437744, "global_step": 427127, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1209418773651123, "global_step": 427128, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.079376220703125, "global_step": 427129, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0731284618377686, "global_step": 427130, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1585679054260254, "global_step": 427131, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9779140949249268, "global_step": 427132, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0900444984436035, "global_step": 427133, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1355032920837402, "global_step": 427134, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1495141983032227, "global_step": 427135, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.001833438873291, "global_step": 427136, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0301010608673096, "global_step": 427137, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0307722091674805, "global_step": 427138, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.023667097091675, "global_step": 427139, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0480260848999023, "global_step": 427140, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0272936820983887, "global_step": 427141, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.063533067703247, "global_step": 427142, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1439101696014404, "global_step": 427143, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.058969497680664, "global_step": 427144, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0039761066436768, "global_step": 427145, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0655033588409424, "global_step": 427146, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.138977289199829, "global_step": 427147, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.047528028488159, "global_step": 427148, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.126727342605591, "global_step": 427149, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.042388439178467, "global_step": 427150, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1124143600463867, "global_step": 427151, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.09710693359375, "global_step": 427152, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.178725481033325, "global_step": 427153, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1752102375030518, "global_step": 427154, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.173241138458252, "global_step": 427155, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1410226821899414, "global_step": 427156, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0497939586639404, "global_step": 427157, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1636288166046143, "global_step": 427158, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.03664493560791, "global_step": 427159, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.101285934448242, "global_step": 427160, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1918394565582275, "global_step": 427161, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0762104988098145, "global_step": 427162, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.056640386581421, "global_step": 427163, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1259665489196777, "global_step": 427164, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0614678859710693, "global_step": 427165, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1141958236694336, "global_step": 427166, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0226852893829346, "global_step": 427167, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1131293773651123, "global_step": 427168, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0114526748657227, "global_step": 427169, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.134641408920288, "global_step": 427170, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.030686378479004, "global_step": 427171, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0553274154663086, "global_step": 427172, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.021843910217285, "global_step": 427173, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.196993112564087, "global_step": 427174, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1642658710479736, "global_step": 427175, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.109497547149658, "global_step": 427176, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0223214626312256, "global_step": 427177, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0691733360290527, "global_step": 427178, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0629007816314697, "global_step": 427179, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1587069034576416, "global_step": 427180, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1683666706085205, "global_step": 427181, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.125342845916748, "global_step": 427182, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1287436485290527, "global_step": 427183, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.168593406677246, "global_step": 427184, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1129398345947266, "global_step": 427185, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1826741695404053, "global_step": 427186, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.119692325592041, "global_step": 427187, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1758460998535156, "global_step": 427188, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0701229572296143, "global_step": 427189, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1202244758605957, "global_step": 427190, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0708625316619873, "global_step": 427191, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9946892261505127, "global_step": 427192, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1281797885894775, "global_step": 427193, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1369199752807617, "global_step": 427194, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.085378646850586, "global_step": 427195, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0194790363311768, "global_step": 427196, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1125547885894775, "global_step": 427197, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.091325283050537, "global_step": 427198, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.088107109069824, "global_step": 427199, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.13802170753479, "global_step": 427200, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.060774564743042, "global_step": 427201, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1598384380340576, "global_step": 427202, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0321602821350098, "global_step": 427203, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1657750606536865, "global_step": 427204, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.076887845993042, "global_step": 427205, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1049294471740723, "global_step": 427206, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9893370866775513, "global_step": 427207, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.069371461868286, "global_step": 427208, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0047621726989746, "global_step": 427209, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1712794303894043, "global_step": 427210, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.087961435317993, "global_step": 427211, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1060967445373535, "global_step": 427212, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.060920000076294, "global_step": 427213, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1047966480255127, "global_step": 427214, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1082987785339355, "global_step": 427215, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1137208938598633, "global_step": 427216, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1437032222747803, "global_step": 427217, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.102329969406128, "global_step": 427218, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9563919305801392, "global_step": 427219, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.153935432434082, "global_step": 427220, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.123412847518921, "global_step": 427221, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.015033483505249, "global_step": 427222, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0339784622192383, "global_step": 427223, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0553503036499023, "global_step": 427224, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.195011854171753, "global_step": 427225, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0245327949523926, "global_step": 427226, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.152364730834961, "global_step": 427227, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0549352169036865, "global_step": 427228, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.082573652267456, "global_step": 427229, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.161125421524048, "global_step": 427230, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1357944011688232, "global_step": 427231, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.08120059967041, "global_step": 427232, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1758694648742676, "global_step": 427233, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0673046112060547, "global_step": 427234, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0389552116394043, "global_step": 427235, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1171512603759766, "global_step": 427236, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1214487552642822, "global_step": 427237, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.112088680267334, "global_step": 427238, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.209000825881958, "global_step": 427239, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.076401710510254, "global_step": 427240, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0578091144561768, "global_step": 427241, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.01411509513855, "global_step": 427242, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0988550186157227, "global_step": 427243, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0917274951934814, "global_step": 427244, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1337101459503174, "global_step": 427245, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.022427797317505, "global_step": 427246, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0665082931518555, "global_step": 427247, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.140439987182617, "global_step": 427248, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.118222951889038, "global_step": 427249, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1358702182769775, "global_step": 427250, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.144627332687378, "global_step": 427251, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.937034249305725, "global_step": 427252, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9773364067077637, "global_step": 427253, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0777416229248047, "global_step": 427254, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.994004487991333, "global_step": 427255, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.088912010192871, "global_step": 427256, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.05991530418396, "global_step": 427257, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.09666109085083, "global_step": 427258, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0967283248901367, "global_step": 427259, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.084251880645752, "global_step": 427260, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0660951137542725, "global_step": 427261, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.117685556411743, "global_step": 427262, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0468928813934326, "global_step": 427263, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.051743984222412, "global_step": 427264, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.110095262527466, "global_step": 427265, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0891056060791016, "global_step": 427266, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.119729518890381, "global_step": 427267, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0301907062530518, "global_step": 427268, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0255887508392334, "global_step": 427269, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.033299207687378, "global_step": 427270, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0394368171691895, "global_step": 427271, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.104874610900879, "global_step": 427272, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1151905059814453, "global_step": 427273, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0840725898742676, "global_step": 427274, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0494818687438965, "global_step": 427275, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.153108596801758, "global_step": 427276, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1173839569091797, "global_step": 427277, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0459136962890625, "global_step": 427278, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0823781490325928, "global_step": 427279, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0601260662078857, "global_step": 427280, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0753040313720703, "global_step": 427281, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0489766597747803, "global_step": 427282, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1139893531799316, "global_step": 427283, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.104304313659668, "global_step": 427284, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.029780387878418, "global_step": 427285, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.095630645751953, "global_step": 427286, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.115135431289673, "global_step": 427287, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1029884815216064, "global_step": 427288, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0216612815856934, "global_step": 427289, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.170783519744873, "global_step": 427290, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.060131072998047, "global_step": 427291, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.061614513397217, "global_step": 427292, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.153247833251953, "global_step": 427293, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.109649896621704, "global_step": 427294, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.050706386566162, "global_step": 427295, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.101454019546509, "global_step": 427296, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.021186590194702, "global_step": 427297, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1610114574432373, "global_step": 427298, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0413949489593506, "global_step": 427299, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1210618019104004, "global_step": 427300, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1104483604431152, "global_step": 427301, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.095534086227417, "global_step": 427302, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0618135929107666, "global_step": 427303, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.093050956726074, "global_step": 427304, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1079368591308594, "global_step": 427305, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.115471363067627, "global_step": 427306, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1312732696533203, "global_step": 427307, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0857701301574707, "global_step": 427308, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.073821544647217, "global_step": 427309, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.110018253326416, "global_step": 427310, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0985236167907715, "global_step": 427311, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0260579586029053, "global_step": 427312, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1191048622131348, "global_step": 427313, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1728451251983643, "global_step": 427314, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0879297256469727, "global_step": 427315, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.2709734439849854, "global_step": 427316, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.095860481262207, "global_step": 427317, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1075611114501953, "global_step": 427318, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.163128137588501, "global_step": 427319, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.123917818069458, "global_step": 427320, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.126263380050659, "global_step": 427321, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.101344108581543, "global_step": 427322, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.12203049659729, "global_step": 427323, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.080151319503784, "global_step": 427324, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0522310733795166, "global_step": 427325, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1304068565368652, "global_step": 427326, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.046830415725708, "global_step": 427327, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.013680934906006, "global_step": 427328, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0646109580993652, "global_step": 427329, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.085571765899658, "global_step": 427330, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.016644239425659, "global_step": 427331, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.103933811187744, "global_step": 427332, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.120821952819824, "global_step": 427333, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0694854259490967, "global_step": 427334, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.204413414001465, "global_step": 427335, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1624224185943604, "global_step": 427336, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0321686267852783, "global_step": 427337, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9678760766983032, "global_step": 427338, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0591046810150146, "global_step": 427339, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.134705066680908, "global_step": 427340, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.115913152694702, "global_step": 427341, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.157217264175415, "global_step": 427342, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0502398014068604, "global_step": 427343, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.058187246322632, "global_step": 427344, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.163184404373169, "global_step": 427345, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0927834510803223, "global_step": 427346, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.042386531829834, "global_step": 427347, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.098860263824463, "global_step": 427348, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0838940143585205, "global_step": 427349, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.198276996612549, "global_step": 427350, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.024087905883789, "global_step": 427351, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.080343008041382, "global_step": 427352, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0839755535125732, "global_step": 427353, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.132225275039673, "global_step": 427354, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.163546085357666, "global_step": 427355, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0759501457214355, "global_step": 427356, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0292670726776123, "global_step": 427357, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0689921379089355, "global_step": 427358, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.2095115184783936, "global_step": 427359, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0452957153320312, "global_step": 427360, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1590442657470703, "global_step": 427361, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1302268505096436, "global_step": 427362, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0626304149627686, "global_step": 427363, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1241936683654785, "global_step": 427364, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1269636154174805, "global_step": 427365, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.083029270172119, "global_step": 427366, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0725271701812744, "global_step": 427367, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1411032676696777, "global_step": 427368, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0097198486328125, "global_step": 427369, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.048729181289673, "global_step": 427370, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0444154739379883, "global_step": 427371, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.98089599609375, "global_step": 427372, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.055065631866455, "global_step": 427373, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.191229820251465, "global_step": 427374, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0747692584991455, "global_step": 427375, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0813682079315186, "global_step": 427376, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.984392762184143, "global_step": 427377, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.056467294692993, "global_step": 427378, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0630767345428467, "global_step": 427379, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1514554023742676, "global_step": 427380, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.027512311935425, "global_step": 427381, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0694963932037354, "global_step": 427382, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0172863006591797, "global_step": 427383, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1363866329193115, "global_step": 427384, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0380051136016846, "global_step": 427385, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.133695363998413, "global_step": 427386, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.115220308303833, "global_step": 427387, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1193103790283203, "global_step": 427388, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0070114135742188, "global_step": 427389, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.104680061340332, "global_step": 427390, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0987303256988525, "global_step": 427391, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1304121017456055, "global_step": 427392, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.067760944366455, "global_step": 427393, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.099578380584717, "global_step": 427394, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0419180393218994, "global_step": 427395, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0750956535339355, "global_step": 427396, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.126460075378418, "global_step": 427397, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.083226203918457, "global_step": 427398, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.108271598815918, "global_step": 427399, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.120295524597168, "global_step": 427400, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1273276805877686, "global_step": 427401, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.164585828781128, "global_step": 427402, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.146651268005371, "global_step": 427403, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0841290950775146, "global_step": 427404, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1202988624572754, "global_step": 427405, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0793182849884033, "global_step": 427406, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0464775562286377, "global_step": 427407, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1176035404205322, "global_step": 427408, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0476059913635254, "global_step": 427409, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1468565464019775, "global_step": 427410, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.098480701446533, "global_step": 427411, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1075379848480225, "global_step": 427412, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1400439739227295, "global_step": 427413, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1034114360809326, "global_step": 427414, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.091064929962158, "global_step": 427415, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0427279472351074, "global_step": 427416, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0578339099884033, "global_step": 427417, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.113980293273926, "global_step": 427418, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0022385120391846, "global_step": 427419, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1073405742645264, "global_step": 427420, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.094210386276245, "global_step": 427421, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1664202213287354, "global_step": 427422, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.048703908920288, "global_step": 427423, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1226260662078857, "global_step": 427424, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.115985870361328, "global_step": 427425, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.039224624633789, "global_step": 427426, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.173670768737793, "global_step": 427427, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0511999130249023, "global_step": 427428, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.08720064163208, "global_step": 427429, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.084167718887329, "global_step": 427430, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1400375366210938, "global_step": 427431, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.125492811203003, "global_step": 427432, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0688140392303467, "global_step": 427433, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0502092838287354, "global_step": 427434, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.089246988296509, "global_step": 427435, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.01420259475708, "global_step": 427436, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0474653244018555, "global_step": 427437, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0379326343536377, "global_step": 427438, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1204864978790283, "global_step": 427439, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.993204951286316, "global_step": 427440, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.025764226913452, "global_step": 427441, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0566606521606445, "global_step": 427442, "epoch": 790, "lr": 5e-05}
{"train_loss": 1.9684611558914185, "global_step": 427443, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1107921600341797, "global_step": 427444, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1241188049316406, "global_step": 427445, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.101410388946533, "global_step": 427446, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.127218008041382, "global_step": 427447, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.113436222076416, "global_step": 427448, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0978736877441406, "global_step": 427449, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.015021800994873, "global_step": 427450, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1142754554748535, "global_step": 427451, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0901050567626953, "global_step": 427452, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.109355926513672, "global_step": 427453, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0985970497131348, "global_step": 427454, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.1055033206939697, "global_step": 427455, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.129791736602783, "global_step": 427456, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.130019187927246, "global_step": 427457, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.091212034225464, "global_step": 427458, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.076657295227051, "global_step": 427459, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0889930725097656, "global_step": 427460, "epoch": 790, "lr": 5e-05}
{"train_loss": 2.0837795734405518, "global_step": 427461, "epoch": 790, "lr": 5e-05, "val_loss": 5.655811786651611, "test_reconst_mse": 0.0743742436170578}
{"train_loss": 2.041621446609497, "global_step": 427462, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0584089756011963, "global_step": 427463, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1334762573242188, "global_step": 427464, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.111424446105957, "global_step": 427465, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1486401557922363, "global_step": 427466, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.973875880241394, "global_step": 427467, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.107447624206543, "global_step": 427468, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0418949127197266, "global_step": 427469, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.057939052581787, "global_step": 427470, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.134446382522583, "global_step": 427471, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1138498783111572, "global_step": 427472, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.171354293823242, "global_step": 427473, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0081071853637695, "global_step": 427474, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.985969066619873, "global_step": 427475, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.034379720687866, "global_step": 427476, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0183281898498535, "global_step": 427477, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1253371238708496, "global_step": 427478, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.026498556137085, "global_step": 427479, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.108362913131714, "global_step": 427480, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1439123153686523, "global_step": 427481, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.109952449798584, "global_step": 427482, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.009495258331299, "global_step": 427483, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1410672664642334, "global_step": 427484, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0905890464782715, "global_step": 427485, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.016866445541382, "global_step": 427486, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0800797939300537, "global_step": 427487, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.153702974319458, "global_step": 427488, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0045485496520996, "global_step": 427489, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1162731647491455, "global_step": 427490, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.074347972869873, "global_step": 427491, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0909085273742676, "global_step": 427492, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.042226552963257, "global_step": 427493, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.141993761062622, "global_step": 427494, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.105592727661133, "global_step": 427495, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0035383701324463, "global_step": 427496, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.114802598953247, "global_step": 427497, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1427392959594727, "global_step": 427498, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0377354621887207, "global_step": 427499, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.16347074508667, "global_step": 427500, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.082872152328491, "global_step": 427501, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0482356548309326, "global_step": 427502, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.089667558670044, "global_step": 427503, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.01983904838562, "global_step": 427504, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.083385467529297, "global_step": 427505, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.005032777786255, "global_step": 427506, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.060188055038452, "global_step": 427507, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0664761066436768, "global_step": 427508, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.114454984664917, "global_step": 427509, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1497604846954346, "global_step": 427510, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.073458671569824, "global_step": 427511, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.008186101913452, "global_step": 427512, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.09153413772583, "global_step": 427513, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.110008955001831, "global_step": 427514, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9850223064422607, "global_step": 427515, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.002845525741577, "global_step": 427516, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0550765991210938, "global_step": 427517, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0600662231445312, "global_step": 427518, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1401596069335938, "global_step": 427519, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0909790992736816, "global_step": 427520, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.150857448577881, "global_step": 427521, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.048506259918213, "global_step": 427522, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1614370346069336, "global_step": 427523, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0458178520202637, "global_step": 427524, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.06718373298645, "global_step": 427525, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.076079845428467, "global_step": 427526, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0828053951263428, "global_step": 427527, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1121702194213867, "global_step": 427528, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.138705253601074, "global_step": 427529, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.095552682876587, "global_step": 427530, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1014084815979004, "global_step": 427531, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.027341365814209, "global_step": 427532, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0833241939544678, "global_step": 427533, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0295000076293945, "global_step": 427534, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0682365894317627, "global_step": 427535, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.066549301147461, "global_step": 427536, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0773544311523438, "global_step": 427537, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1187150478363037, "global_step": 427538, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1443493366241455, "global_step": 427539, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0166661739349365, "global_step": 427540, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.071805238723755, "global_step": 427541, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1344845294952393, "global_step": 427542, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0985987186431885, "global_step": 427543, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0994536876678467, "global_step": 427544, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.054771900177002, "global_step": 427545, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1503958702087402, "global_step": 427546, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9999653100967407, "global_step": 427547, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1148247718811035, "global_step": 427548, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0578434467315674, "global_step": 427549, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0690462589263916, "global_step": 427550, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0175232887268066, "global_step": 427551, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.08620548248291, "global_step": 427552, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0427961349487305, "global_step": 427553, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1389968395233154, "global_step": 427554, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0364582538604736, "global_step": 427555, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.014512062072754, "global_step": 427556, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.109750270843506, "global_step": 427557, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.108161449432373, "global_step": 427558, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1913936138153076, "global_step": 427559, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0711557865142822, "global_step": 427560, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1542913913726807, "global_step": 427561, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1151959896087646, "global_step": 427562, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0562524795532227, "global_step": 427563, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1079797744750977, "global_step": 427564, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.051711320877075, "global_step": 427565, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.145236015319824, "global_step": 427566, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.005315065383911, "global_step": 427567, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0656867027282715, "global_step": 427568, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0679924488067627, "global_step": 427569, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0473880767822266, "global_step": 427570, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.033491373062134, "global_step": 427571, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.192641258239746, "global_step": 427572, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0995309352874756, "global_step": 427573, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.100529193878174, "global_step": 427574, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0889554023742676, "global_step": 427575, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1888930797576904, "global_step": 427576, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.028202533721924, "global_step": 427577, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1445276737213135, "global_step": 427578, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9928507804870605, "global_step": 427579, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0733091831207275, "global_step": 427580, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0350258350372314, "global_step": 427581, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.192578077316284, "global_step": 427582, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0345327854156494, "global_step": 427583, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0193471908569336, "global_step": 427584, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0171985626220703, "global_step": 427585, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.158485174179077, "global_step": 427586, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0506560802459717, "global_step": 427587, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9976012706756592, "global_step": 427588, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1372973918914795, "global_step": 427589, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0120065212249756, "global_step": 427590, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.029808759689331, "global_step": 427591, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0461814403533936, "global_step": 427592, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.221748113632202, "global_step": 427593, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0823237895965576, "global_step": 427594, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.990875244140625, "global_step": 427595, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.052462577819824, "global_step": 427596, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9689334630966187, "global_step": 427597, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.094086170196533, "global_step": 427598, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.19382381439209, "global_step": 427599, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.10894775390625, "global_step": 427600, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1131043434143066, "global_step": 427601, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0932092666625977, "global_step": 427602, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.096848487854004, "global_step": 427603, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0172250270843506, "global_step": 427604, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.058824062347412, "global_step": 427605, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0454154014587402, "global_step": 427606, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1942732334136963, "global_step": 427607, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.013782501220703, "global_step": 427608, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1108481884002686, "global_step": 427609, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0588226318359375, "global_step": 427610, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.028811454772949, "global_step": 427611, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1306910514831543, "global_step": 427612, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.077802896499634, "global_step": 427613, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.160982370376587, "global_step": 427614, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0210072994232178, "global_step": 427615, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1191275119781494, "global_step": 427616, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0000407695770264, "global_step": 427617, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0608277320861816, "global_step": 427618, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0741477012634277, "global_step": 427619, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0333659648895264, "global_step": 427620, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1268835067749023, "global_step": 427621, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.088995933532715, "global_step": 427622, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.115446090698242, "global_step": 427623, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.071791648864746, "global_step": 427624, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0633952617645264, "global_step": 427625, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.032292604446411, "global_step": 427626, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0875377655029297, "global_step": 427627, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0840373039245605, "global_step": 427628, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0807135105133057, "global_step": 427629, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9931873083114624, "global_step": 427630, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0888588428497314, "global_step": 427631, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0865702629089355, "global_step": 427632, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0920212268829346, "global_step": 427633, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1027464866638184, "global_step": 427634, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.188551425933838, "global_step": 427635, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0795910358428955, "global_step": 427636, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.057874917984009, "global_step": 427637, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.057260751724243, "global_step": 427638, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1329386234283447, "global_step": 427639, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.165299415588379, "global_step": 427640, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.093169927597046, "global_step": 427641, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.135895013809204, "global_step": 427642, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1613919734954834, "global_step": 427643, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1022377014160156, "global_step": 427644, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.05633807182312, "global_step": 427645, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.015590190887451, "global_step": 427646, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.090975046157837, "global_step": 427647, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.050222396850586, "global_step": 427648, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.114964008331299, "global_step": 427649, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.102707862854004, "global_step": 427650, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9362467527389526, "global_step": 427651, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0585482120513916, "global_step": 427652, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.032836675643921, "global_step": 427653, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.157630443572998, "global_step": 427654, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0933704376220703, "global_step": 427655, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.969671607017517, "global_step": 427656, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.027683734893799, "global_step": 427657, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.14563250541687, "global_step": 427658, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0860636234283447, "global_step": 427659, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0133097171783447, "global_step": 427660, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0898289680480957, "global_step": 427661, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.084798574447632, "global_step": 427662, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.073199510574341, "global_step": 427663, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.030231237411499, "global_step": 427664, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0976057052612305, "global_step": 427665, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1387674808502197, "global_step": 427666, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.127763032913208, "global_step": 427667, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.109830617904663, "global_step": 427668, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.119858741760254, "global_step": 427669, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.136533737182617, "global_step": 427670, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0475869178771973, "global_step": 427671, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.154526948928833, "global_step": 427672, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0316050052642822, "global_step": 427673, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.119738817214966, "global_step": 427674, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.086049795150757, "global_step": 427675, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.039293050765991, "global_step": 427676, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0808956623077393, "global_step": 427677, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0377321243286133, "global_step": 427678, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.085954189300537, "global_step": 427679, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.156878709793091, "global_step": 427680, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.088226795196533, "global_step": 427681, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.089599370956421, "global_step": 427682, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1264564990997314, "global_step": 427683, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.114732265472412, "global_step": 427684, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.167661666870117, "global_step": 427685, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.982655644416809, "global_step": 427686, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.163299560546875, "global_step": 427687, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0582661628723145, "global_step": 427688, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1253252029418945, "global_step": 427689, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0997891426086426, "global_step": 427690, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0481624603271484, "global_step": 427691, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0117130279541016, "global_step": 427692, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.101447105407715, "global_step": 427693, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0413155555725098, "global_step": 427694, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1060657501220703, "global_step": 427695, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1857073307037354, "global_step": 427696, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.983817219734192, "global_step": 427697, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.992304801940918, "global_step": 427698, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.103515625, "global_step": 427699, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.06374454498291, "global_step": 427700, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1062870025634766, "global_step": 427701, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0540497303009033, "global_step": 427702, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0443735122680664, "global_step": 427703, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.188979387283325, "global_step": 427704, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.032249927520752, "global_step": 427705, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.14176607131958, "global_step": 427706, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.060523271560669, "global_step": 427707, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.127687454223633, "global_step": 427708, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.056905508041382, "global_step": 427709, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1486191749572754, "global_step": 427710, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0700011253356934, "global_step": 427711, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1376030445098877, "global_step": 427712, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0888288021087646, "global_step": 427713, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.116443634033203, "global_step": 427714, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.112704038619995, "global_step": 427715, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0352468490600586, "global_step": 427716, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0639519691467285, "global_step": 427717, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.993919014930725, "global_step": 427718, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.066584825515747, "global_step": 427719, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.118565320968628, "global_step": 427720, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0897412300109863, "global_step": 427721, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.102993965148926, "global_step": 427722, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.104614496231079, "global_step": 427723, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0756640434265137, "global_step": 427724, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0913352966308594, "global_step": 427725, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0525245666503906, "global_step": 427726, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0066192150115967, "global_step": 427727, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.17395281791687, "global_step": 427728, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.013216972351074, "global_step": 427729, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1809897422790527, "global_step": 427730, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0793309211730957, "global_step": 427731, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.096592664718628, "global_step": 427732, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0248758792877197, "global_step": 427733, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1089208126068115, "global_step": 427734, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0830466747283936, "global_step": 427735, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9906760454177856, "global_step": 427736, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1245625019073486, "global_step": 427737, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1422712802886963, "global_step": 427738, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.042404890060425, "global_step": 427739, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.088397264480591, "global_step": 427740, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.097799301147461, "global_step": 427741, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0613815784454346, "global_step": 427742, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.094031810760498, "global_step": 427743, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0665111541748047, "global_step": 427744, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1747031211853027, "global_step": 427745, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0816292762756348, "global_step": 427746, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.080002784729004, "global_step": 427747, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.117661714553833, "global_step": 427748, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0825014114379883, "global_step": 427749, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.068206548690796, "global_step": 427750, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.036956310272217, "global_step": 427751, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.001955509185791, "global_step": 427752, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0737526416778564, "global_step": 427753, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1343424320220947, "global_step": 427754, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0380403995513916, "global_step": 427755, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0262420177459717, "global_step": 427756, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9831753969192505, "global_step": 427757, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.029561758041382, "global_step": 427758, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9341436624526978, "global_step": 427759, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0410075187683105, "global_step": 427760, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.05971097946167, "global_step": 427761, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.096782684326172, "global_step": 427762, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1037847995758057, "global_step": 427763, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.128715991973877, "global_step": 427764, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0501413345336914, "global_step": 427765, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.110534429550171, "global_step": 427766, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0788214206695557, "global_step": 427767, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.080789804458618, "global_step": 427768, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1675825119018555, "global_step": 427769, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0420565605163574, "global_step": 427770, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0692968368530273, "global_step": 427771, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.03743839263916, "global_step": 427772, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0688230991363525, "global_step": 427773, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9664469957351685, "global_step": 427774, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.035752058029175, "global_step": 427775, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.101656913757324, "global_step": 427776, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.03904128074646, "global_step": 427777, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0731186866760254, "global_step": 427778, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.049537181854248, "global_step": 427779, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.121934175491333, "global_step": 427780, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0340065956115723, "global_step": 427781, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.207693576812744, "global_step": 427782, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0407540798187256, "global_step": 427783, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0970618724823, "global_step": 427784, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0802063941955566, "global_step": 427785, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.055039644241333, "global_step": 427786, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9864445924758911, "global_step": 427787, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.012148141860962, "global_step": 427788, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1232962608337402, "global_step": 427789, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0176568031311035, "global_step": 427790, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.131622552871704, "global_step": 427791, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1280457973480225, "global_step": 427792, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.03838849067688, "global_step": 427793, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1731438636779785, "global_step": 427794, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.008507490158081, "global_step": 427795, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.087385654449463, "global_step": 427796, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.034808874130249, "global_step": 427797, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.074488878250122, "global_step": 427798, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.082021951675415, "global_step": 427799, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.050926923751831, "global_step": 427800, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0971522331237793, "global_step": 427801, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1367387771606445, "global_step": 427802, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.055654287338257, "global_step": 427803, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0547564029693604, "global_step": 427804, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1053359508514404, "global_step": 427805, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.047589063644409, "global_step": 427806, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0586509704589844, "global_step": 427807, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0301709175109863, "global_step": 427808, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.050062656402588, "global_step": 427809, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1155850887298584, "global_step": 427810, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0736443996429443, "global_step": 427811, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.057119131088257, "global_step": 427812, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1234679222106934, "global_step": 427813, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.120298147201538, "global_step": 427814, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.108842372894287, "global_step": 427815, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0707194805145264, "global_step": 427816, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1587934494018555, "global_step": 427817, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.050253391265869, "global_step": 427818, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1355702877044678, "global_step": 427819, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.087385416030884, "global_step": 427820, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1684391498565674, "global_step": 427821, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.052292823791504, "global_step": 427822, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1027493476867676, "global_step": 427823, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0447769165039062, "global_step": 427824, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1148715019226074, "global_step": 427825, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0462169647216797, "global_step": 427826, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.017899990081787, "global_step": 427827, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0463573932647705, "global_step": 427828, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.136230707168579, "global_step": 427829, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.170494794845581, "global_step": 427830, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0981786251068115, "global_step": 427831, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0834038257598877, "global_step": 427832, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0805976390838623, "global_step": 427833, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0733909606933594, "global_step": 427834, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1561524868011475, "global_step": 427835, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1149539947509766, "global_step": 427836, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.028956413269043, "global_step": 427837, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0727789402008057, "global_step": 427838, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0001206398010254, "global_step": 427839, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1509077548980713, "global_step": 427840, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.174046516418457, "global_step": 427841, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.052577018737793, "global_step": 427842, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.075531482696533, "global_step": 427843, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.067275047302246, "global_step": 427844, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.113844156265259, "global_step": 427845, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0578343868255615, "global_step": 427846, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0574347972869873, "global_step": 427847, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.096252679824829, "global_step": 427848, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0562784671783447, "global_step": 427849, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.108290433883667, "global_step": 427850, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1785571575164795, "global_step": 427851, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1320109367370605, "global_step": 427852, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.046473979949951, "global_step": 427853, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.175081968307495, "global_step": 427854, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.081472635269165, "global_step": 427855, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0753562450408936, "global_step": 427856, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.138974189758301, "global_step": 427857, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.001166343688965, "global_step": 427858, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.138288974761963, "global_step": 427859, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0740833282470703, "global_step": 427860, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9988919496536255, "global_step": 427861, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0523428916931152, "global_step": 427862, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.048286199569702, "global_step": 427863, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.113412380218506, "global_step": 427864, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0598530769348145, "global_step": 427865, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0119521617889404, "global_step": 427866, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.071852207183838, "global_step": 427867, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0965657234191895, "global_step": 427868, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.176699638366699, "global_step": 427869, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1421239376068115, "global_step": 427870, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.025960922241211, "global_step": 427871, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0133414268493652, "global_step": 427872, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0630998611450195, "global_step": 427873, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.075160264968872, "global_step": 427874, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1214427947998047, "global_step": 427875, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0189731121063232, "global_step": 427876, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0885610580444336, "global_step": 427877, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.094792127609253, "global_step": 427878, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0628347396850586, "global_step": 427879, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.11822509765625, "global_step": 427880, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0702688694000244, "global_step": 427881, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0846424102783203, "global_step": 427882, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1499173641204834, "global_step": 427883, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.020381212234497, "global_step": 427884, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0554416179656982, "global_step": 427885, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.2225255966186523, "global_step": 427886, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.061300039291382, "global_step": 427887, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.109879493713379, "global_step": 427888, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.037513256072998, "global_step": 427889, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.982450008392334, "global_step": 427890, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.069873094558716, "global_step": 427891, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.146728992462158, "global_step": 427892, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1459596157073975, "global_step": 427893, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.022179126739502, "global_step": 427894, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0722646713256836, "global_step": 427895, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0993587970733643, "global_step": 427896, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0989203453063965, "global_step": 427897, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1249754428863525, "global_step": 427898, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.130084276199341, "global_step": 427899, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.985051155090332, "global_step": 427900, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1168861389160156, "global_step": 427901, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.135317802429199, "global_step": 427902, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0448200702667236, "global_step": 427903, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.082841396331787, "global_step": 427904, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0617542266845703, "global_step": 427905, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1266729831695557, "global_step": 427906, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9592607021331787, "global_step": 427907, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0504860877990723, "global_step": 427908, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1295974254608154, "global_step": 427909, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0554025173187256, "global_step": 427910, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.077260732650757, "global_step": 427911, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0897514820098877, "global_step": 427912, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.039033889770508, "global_step": 427913, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0609891414642334, "global_step": 427914, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.138542652130127, "global_step": 427915, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0075721740722656, "global_step": 427916, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.110386848449707, "global_step": 427917, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9718549251556396, "global_step": 427918, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0859262943267822, "global_step": 427919, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0567257404327393, "global_step": 427920, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0458903312683105, "global_step": 427921, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0540807247161865, "global_step": 427922, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0358786582946777, "global_step": 427923, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.197356939315796, "global_step": 427924, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0420081615448, "global_step": 427925, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.135747194290161, "global_step": 427926, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0025718212127686, "global_step": 427927, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0623233318328857, "global_step": 427928, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0461316108703613, "global_step": 427929, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.122978687286377, "global_step": 427930, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0607869625091553, "global_step": 427931, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.056535243988037, "global_step": 427932, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0401477813720703, "global_step": 427933, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0633180141448975, "global_step": 427934, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9800347089767456, "global_step": 427935, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.067458391189575, "global_step": 427936, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.127486228942871, "global_step": 427937, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.112600803375244, "global_step": 427938, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.149367570877075, "global_step": 427939, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0593984127044678, "global_step": 427940, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1513683795928955, "global_step": 427941, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0667502880096436, "global_step": 427942, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.067307949066162, "global_step": 427943, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1695921421051025, "global_step": 427944, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.139664649963379, "global_step": 427945, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.153536319732666, "global_step": 427946, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1447436809539795, "global_step": 427947, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.032949447631836, "global_step": 427948, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0913310050964355, "global_step": 427949, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.054534673690796, "global_step": 427950, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.099571704864502, "global_step": 427951, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0981717109680176, "global_step": 427952, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1145613193511963, "global_step": 427953, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.112744092941284, "global_step": 427954, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0507407188415527, "global_step": 427955, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9663833379745483, "global_step": 427956, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.064923048019409, "global_step": 427957, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0101492404937744, "global_step": 427958, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.187871217727661, "global_step": 427959, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.078969717025757, "global_step": 427960, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.030094623565674, "global_step": 427961, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.119553804397583, "global_step": 427962, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1130592823028564, "global_step": 427963, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.142646312713623, "global_step": 427964, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1194536685943604, "global_step": 427965, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.101881265640259, "global_step": 427966, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0336101055145264, "global_step": 427967, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1835100650787354, "global_step": 427968, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1255087852478027, "global_step": 427969, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1577014923095703, "global_step": 427970, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1630024909973145, "global_step": 427971, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.132859706878662, "global_step": 427972, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.071979522705078, "global_step": 427973, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0082945823669434, "global_step": 427974, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0925538539886475, "global_step": 427975, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0366623401641846, "global_step": 427976, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0478005409240723, "global_step": 427977, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1073076725006104, "global_step": 427978, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1122586727142334, "global_step": 427979, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0588440895080566, "global_step": 427980, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0446033477783203, "global_step": 427981, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.121995687484741, "global_step": 427982, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.069458484649658, "global_step": 427983, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0634162425994873, "global_step": 427984, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.111663579940796, "global_step": 427985, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0501439571380615, "global_step": 427986, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.122978687286377, "global_step": 427987, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0780110359191895, "global_step": 427988, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.144592761993408, "global_step": 427989, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1707868576049805, "global_step": 427990, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.070435047149658, "global_step": 427991, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.099329948425293, "global_step": 427992, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.156280755996704, "global_step": 427993, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.027669668197632, "global_step": 427994, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.055506467819214, "global_step": 427995, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1915907859802246, "global_step": 427996, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.052358388900757, "global_step": 427997, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9902939796447754, "global_step": 427998, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.088042736053467, "global_step": 427999, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0806968212127686, "global_step": 428000, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0674221515655518, "global_step": 428001, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0173697471618652, "global_step": 428002, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.079937696456909, "global_step": 428003, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.101849317550659, "global_step": 428004, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.126584768295288, "global_step": 428005, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.048607587814331, "global_step": 428006, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0828635692596436, "global_step": 428007, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.111337423324585, "global_step": 428008, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.056607961654663, "global_step": 428009, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.048800468444824, "global_step": 428010, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1188066005706787, "global_step": 428011, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.063554286956787, "global_step": 428012, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.198063373565674, "global_step": 428013, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1205830574035645, "global_step": 428014, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0779011249542236, "global_step": 428015, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.027265787124634, "global_step": 428016, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0111501216888428, "global_step": 428017, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.186406135559082, "global_step": 428018, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0880377292633057, "global_step": 428019, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.09798002243042, "global_step": 428020, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0890004634857178, "global_step": 428021, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0993895530700684, "global_step": 428022, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1103029251098633, "global_step": 428023, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0406980514526367, "global_step": 428024, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1216795444488525, "global_step": 428025, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.057344675064087, "global_step": 428026, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0245540142059326, "global_step": 428027, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.02288556098938, "global_step": 428028, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.168158531188965, "global_step": 428029, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0182528495788574, "global_step": 428030, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.149064302444458, "global_step": 428031, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.100623607635498, "global_step": 428032, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.029956102371216, "global_step": 428033, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0192787647247314, "global_step": 428034, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.038158416748047, "global_step": 428035, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.006957769393921, "global_step": 428036, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9415735006332397, "global_step": 428037, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0988314151763916, "global_step": 428038, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.089172840118408, "global_step": 428039, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.015134811401367, "global_step": 428040, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.153757095336914, "global_step": 428041, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.044837474822998, "global_step": 428042, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1694295406341553, "global_step": 428043, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.148113489151001, "global_step": 428044, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.070604085922241, "global_step": 428045, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1180784702301025, "global_step": 428046, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0134689807891846, "global_step": 428047, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.148690700531006, "global_step": 428048, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.197801351547241, "global_step": 428049, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.083965539932251, "global_step": 428050, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9977500438690186, "global_step": 428051, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9903552532196045, "global_step": 428052, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0939130783081055, "global_step": 428053, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.036745071411133, "global_step": 428054, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.052032709121704, "global_step": 428055, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9952462911605835, "global_step": 428056, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.108598232269287, "global_step": 428057, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0446276664733887, "global_step": 428058, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.058683156967163, "global_step": 428059, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0292041301727295, "global_step": 428060, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0720958709716797, "global_step": 428061, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.068690299987793, "global_step": 428062, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0687296390533447, "global_step": 428063, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0243325233459473, "global_step": 428064, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.142792224884033, "global_step": 428065, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.066739320755005, "global_step": 428066, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1118853092193604, "global_step": 428067, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.062093496322632, "global_step": 428068, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.062286376953125, "global_step": 428069, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.120356559753418, "global_step": 428070, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0619940757751465, "global_step": 428071, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.104315996170044, "global_step": 428072, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1082565784454346, "global_step": 428073, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0456674098968506, "global_step": 428074, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0601656436920166, "global_step": 428075, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.117914915084839, "global_step": 428076, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0239925384521484, "global_step": 428077, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1034791469573975, "global_step": 428078, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1049106121063232, "global_step": 428079, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1229515075683594, "global_step": 428080, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0501632690429688, "global_step": 428081, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0460410118103027, "global_step": 428082, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.107794761657715, "global_step": 428083, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0244245529174805, "global_step": 428084, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.065063953399658, "global_step": 428085, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0962862968444824, "global_step": 428086, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0700290203094482, "global_step": 428087, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.125657558441162, "global_step": 428088, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1094226837158203, "global_step": 428089, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9966927766799927, "global_step": 428090, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.078875780105591, "global_step": 428091, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0931928157806396, "global_step": 428092, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.054501533508301, "global_step": 428093, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0492682456970215, "global_step": 428094, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1183321475982666, "global_step": 428095, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0394513607025146, "global_step": 428096, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.133852481842041, "global_step": 428097, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9544638395309448, "global_step": 428098, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.120675802230835, "global_step": 428099, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.2245144844055176, "global_step": 428100, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.09057354927063, "global_step": 428101, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0687363147735596, "global_step": 428102, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0417261123657227, "global_step": 428103, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.076233148574829, "global_step": 428104, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0830159187316895, "global_step": 428105, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0498390197753906, "global_step": 428106, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0739266872406006, "global_step": 428107, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0798280239105225, "global_step": 428108, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.052929639816284, "global_step": 428109, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.028712749481201, "global_step": 428110, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0736520290374756, "global_step": 428111, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0085878372192383, "global_step": 428112, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1132113933563232, "global_step": 428113, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0470786094665527, "global_step": 428114, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.144165277481079, "global_step": 428115, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.041802167892456, "global_step": 428116, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.012204647064209, "global_step": 428117, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0626542568206787, "global_step": 428118, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0524041652679443, "global_step": 428119, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.127201795578003, "global_step": 428120, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.098660707473755, "global_step": 428121, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.119497776031494, "global_step": 428122, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1277127265930176, "global_step": 428123, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0955252647399902, "global_step": 428124, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.017782688140869, "global_step": 428125, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0780189037323, "global_step": 428126, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.03922963142395, "global_step": 428127, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.039259910583496, "global_step": 428128, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.010575771331787, "global_step": 428129, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1035690307617188, "global_step": 428130, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0637552738189697, "global_step": 428131, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0626790523529053, "global_step": 428132, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0442140102386475, "global_step": 428133, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0752077102661133, "global_step": 428134, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0707037448883057, "global_step": 428135, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0605125427246094, "global_step": 428136, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.153254985809326, "global_step": 428137, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9956233501434326, "global_step": 428138, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1024553775787354, "global_step": 428139, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.2193989753723145, "global_step": 428140, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1594297885894775, "global_step": 428141, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0432896614074707, "global_step": 428142, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0408899784088135, "global_step": 428143, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.128542900085449, "global_step": 428144, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1332411766052246, "global_step": 428145, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.061478614807129, "global_step": 428146, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0891215801239014, "global_step": 428147, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0938143730163574, "global_step": 428148, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.058109998703003, "global_step": 428149, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.015799045562744, "global_step": 428150, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.152315855026245, "global_step": 428151, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0493335723876953, "global_step": 428152, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.092238187789917, "global_step": 428153, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.068439245223999, "global_step": 428154, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1629228591918945, "global_step": 428155, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0926754474639893, "global_step": 428156, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1204044818878174, "global_step": 428157, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.044877767562866, "global_step": 428158, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1086740493774414, "global_step": 428159, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0344271659851074, "global_step": 428160, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.084956645965576, "global_step": 428161, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.111257553100586, "global_step": 428162, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9955706596374512, "global_step": 428163, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.058366537094116, "global_step": 428164, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0366411209106445, "global_step": 428165, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9434860944747925, "global_step": 428166, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.179837465286255, "global_step": 428167, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9908334016799927, "global_step": 428168, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0987753868103027, "global_step": 428169, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.104858636856079, "global_step": 428170, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.97788667678833, "global_step": 428171, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.10125994682312, "global_step": 428172, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.061605215072632, "global_step": 428173, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.15986704826355, "global_step": 428174, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0801918506622314, "global_step": 428175, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1902589797973633, "global_step": 428176, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0870907306671143, "global_step": 428177, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0933494567871094, "global_step": 428178, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.201612710952759, "global_step": 428179, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.087827682495117, "global_step": 428180, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0587549209594727, "global_step": 428181, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0713231563568115, "global_step": 428182, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0975115299224854, "global_step": 428183, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0387163162231445, "global_step": 428184, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1672987937927246, "global_step": 428185, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.097860336303711, "global_step": 428186, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1187169551849365, "global_step": 428187, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1475417613983154, "global_step": 428188, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.076953411102295, "global_step": 428189, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.166335344314575, "global_step": 428190, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0532190799713135, "global_step": 428191, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0946779251098633, "global_step": 428192, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.072408437728882, "global_step": 428193, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.12259840965271, "global_step": 428194, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0725443363189697, "global_step": 428195, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1186881065368652, "global_step": 428196, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0382373332977295, "global_step": 428197, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0869076251983643, "global_step": 428198, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0005745887756348, "global_step": 428199, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1200547218322754, "global_step": 428200, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.143686056137085, "global_step": 428201, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.106532335281372, "global_step": 428202, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1352148056030273, "global_step": 428203, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1447033882141113, "global_step": 428204, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.186979293823242, "global_step": 428205, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0362069606781006, "global_step": 428206, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.062466859817505, "global_step": 428207, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0380029678344727, "global_step": 428208, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9903677701950073, "global_step": 428209, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.039872169494629, "global_step": 428210, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.083930492401123, "global_step": 428211, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.2108795642852783, "global_step": 428212, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.074751377105713, "global_step": 428213, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.061659812927246, "global_step": 428214, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0564212799072266, "global_step": 428215, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.147939920425415, "global_step": 428216, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.140214443206787, "global_step": 428217, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.116701602935791, "global_step": 428218, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.096179246902466, "global_step": 428219, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.02893328666687, "global_step": 428220, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0038044452667236, "global_step": 428221, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.058081865310669, "global_step": 428222, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.050116777420044, "global_step": 428223, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.3003463745117188, "global_step": 428224, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.996325969696045, "global_step": 428225, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0454530715942383, "global_step": 428226, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.2271628379821777, "global_step": 428227, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0869154930114746, "global_step": 428228, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.099027395248413, "global_step": 428229, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1399478912353516, "global_step": 428230, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.093156337738037, "global_step": 428231, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.102782726287842, "global_step": 428232, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.172424077987671, "global_step": 428233, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0301289558410645, "global_step": 428234, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0909388065338135, "global_step": 428235, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1085665225982666, "global_step": 428236, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0855770111083984, "global_step": 428237, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0251379013061523, "global_step": 428238, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1278529167175293, "global_step": 428239, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0191543102264404, "global_step": 428240, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1153385639190674, "global_step": 428241, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1404688358306885, "global_step": 428242, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1396420001983643, "global_step": 428243, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.115200996398926, "global_step": 428244, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1171350479125977, "global_step": 428245, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.064737319946289, "global_step": 428246, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0652129650115967, "global_step": 428247, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0851004123687744, "global_step": 428248, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0459933280944824, "global_step": 428249, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1259803771972656, "global_step": 428250, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0496113300323486, "global_step": 428251, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.077897548675537, "global_step": 428252, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0598225593566895, "global_step": 428253, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1811373233795166, "global_step": 428254, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.121760845184326, "global_step": 428255, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.02003812789917, "global_step": 428256, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.066892147064209, "global_step": 428257, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0799942016601562, "global_step": 428258, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.123344898223877, "global_step": 428259, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0582594871520996, "global_step": 428260, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.089851140975952, "global_step": 428261, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.080578088760376, "global_step": 428262, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.131213903427124, "global_step": 428263, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.043818235397339, "global_step": 428264, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1782948970794678, "global_step": 428265, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0629467964172363, "global_step": 428266, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0562479496002197, "global_step": 428267, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0309715270996094, "global_step": 428268, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0660533905029297, "global_step": 428269, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.159935712814331, "global_step": 428270, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.028810501098633, "global_step": 428271, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1005327701568604, "global_step": 428272, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.075012445449829, "global_step": 428273, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0778732299804688, "global_step": 428274, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.066035747528076, "global_step": 428275, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1006016731262207, "global_step": 428276, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0803303718566895, "global_step": 428277, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.062575578689575, "global_step": 428278, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0738649368286133, "global_step": 428279, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.037043809890747, "global_step": 428280, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0455424785614014, "global_step": 428281, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.063251256942749, "global_step": 428282, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.090625286102295, "global_step": 428283, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0987961292266846, "global_step": 428284, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0557422637939453, "global_step": 428285, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0801305770874023, "global_step": 428286, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0094594955444336, "global_step": 428287, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.2209255695343018, "global_step": 428288, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.059314489364624, "global_step": 428289, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.002711057662964, "global_step": 428290, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1299633979797363, "global_step": 428291, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1692161560058594, "global_step": 428292, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9396562576293945, "global_step": 428293, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.132131576538086, "global_step": 428294, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0774905681610107, "global_step": 428295, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.036609649658203, "global_step": 428296, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0384321212768555, "global_step": 428297, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.06447696685791, "global_step": 428298, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.044191837310791, "global_step": 428299, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1522583961486816, "global_step": 428300, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0328633785247803, "global_step": 428301, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0795249938964844, "global_step": 428302, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0852181911468506, "global_step": 428303, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0718846321105957, "global_step": 428304, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0705137252807617, "global_step": 428305, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0707263946533203, "global_step": 428306, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1545557975769043, "global_step": 428307, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.136770248413086, "global_step": 428308, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1008553504943848, "global_step": 428309, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0577449798583984, "global_step": 428310, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.025120735168457, "global_step": 428311, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0581772327423096, "global_step": 428312, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.06473970413208, "global_step": 428313, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.139326333999634, "global_step": 428314, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.115676164627075, "global_step": 428315, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.101922035217285, "global_step": 428316, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.115126371383667, "global_step": 428317, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0591485500335693, "global_step": 428318, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.208561897277832, "global_step": 428319, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1160728931427, "global_step": 428320, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9487141370773315, "global_step": 428321, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.035883665084839, "global_step": 428322, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1878836154937744, "global_step": 428323, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1744256019592285, "global_step": 428324, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1935083866119385, "global_step": 428325, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0237317085266113, "global_step": 428326, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.106652021408081, "global_step": 428327, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0901012420654297, "global_step": 428328, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1100287437438965, "global_step": 428329, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9997303485870361, "global_step": 428330, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.088472604751587, "global_step": 428331, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.173659324645996, "global_step": 428332, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.09755802154541, "global_step": 428333, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1803174018859863, "global_step": 428334, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.156928300857544, "global_step": 428335, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0656588077545166, "global_step": 428336, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.083048105239868, "global_step": 428337, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.059662103652954, "global_step": 428338, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.111675500869751, "global_step": 428339, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.050865650177002, "global_step": 428340, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1109020709991455, "global_step": 428341, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0344181060791016, "global_step": 428342, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.136892318725586, "global_step": 428343, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0462615489959717, "global_step": 428344, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0820112228393555, "global_step": 428345, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0644025802612305, "global_step": 428346, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.060375213623047, "global_step": 428347, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.146153688430786, "global_step": 428348, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9846382141113281, "global_step": 428349, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1056606769561768, "global_step": 428350, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.057877540588379, "global_step": 428351, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.112851142883301, "global_step": 428352, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.053541421890259, "global_step": 428353, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.135207176208496, "global_step": 428354, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0950183868408203, "global_step": 428355, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.061267614364624, "global_step": 428356, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.046867609024048, "global_step": 428357, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0615766048431396, "global_step": 428358, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.045898199081421, "global_step": 428359, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1002702713012695, "global_step": 428360, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.027512550354004, "global_step": 428361, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.11175799369812, "global_step": 428362, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0232994556427, "global_step": 428363, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.027608633041382, "global_step": 428364, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0440120697021484, "global_step": 428365, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.115041971206665, "global_step": 428366, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.101167678833008, "global_step": 428367, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1083593368530273, "global_step": 428368, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0734691619873047, "global_step": 428369, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1077609062194824, "global_step": 428370, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1231086254119873, "global_step": 428371, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1093146800994873, "global_step": 428372, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1258552074432373, "global_step": 428373, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.068913698196411, "global_step": 428374, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1162099838256836, "global_step": 428375, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0936832427978516, "global_step": 428376, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0996832847595215, "global_step": 428377, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.037032127380371, "global_step": 428378, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.09908390045166, "global_step": 428379, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.011164903640747, "global_step": 428380, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0682108402252197, "global_step": 428381, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.111192226409912, "global_step": 428382, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1397643089294434, "global_step": 428383, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1159541606903076, "global_step": 428384, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.157625675201416, "global_step": 428385, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.100666046142578, "global_step": 428386, "epoch": 791, "lr": 5e-05}
{"train_loss": 1.9952799081802368, "global_step": 428387, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0666303634643555, "global_step": 428388, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.084735870361328, "global_step": 428389, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.158719301223755, "global_step": 428390, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.08640718460083, "global_step": 428391, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0866329669952393, "global_step": 428392, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.137316942214966, "global_step": 428393, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0769004821777344, "global_step": 428394, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.048222303390503, "global_step": 428395, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0337467193603516, "global_step": 428396, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.11600661277771, "global_step": 428397, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1866097450256348, "global_step": 428398, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0653772354125977, "global_step": 428399, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0866196155548096, "global_step": 428400, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.040727376937866, "global_step": 428401, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0725913047790527, "global_step": 428402, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0484871864318848, "global_step": 428403, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.101320505142212, "global_step": 428404, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.048381805419922, "global_step": 428405, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0641837120056152, "global_step": 428406, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.067781686782837, "global_step": 428407, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.226712703704834, "global_step": 428408, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1198039054870605, "global_step": 428409, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0801734924316406, "global_step": 428410, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0303661823272705, "global_step": 428411, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1129322052001953, "global_step": 428412, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1030478477478027, "global_step": 428413, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0693933963775635, "global_step": 428414, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0849905014038086, "global_step": 428415, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.082451820373535, "global_step": 428416, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.064882278442383, "global_step": 428417, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0995829105377197, "global_step": 428418, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.074427366256714, "global_step": 428419, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.133700370788574, "global_step": 428420, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.075918436050415, "global_step": 428421, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0995254516601562, "global_step": 428422, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.089190721511841, "global_step": 428423, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1441938877105713, "global_step": 428424, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.04716420173645, "global_step": 428425, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0922152996063232, "global_step": 428426, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0829885005950928, "global_step": 428427, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.068223476409912, "global_step": 428428, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.060249090194702, "global_step": 428429, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.0827059745788574, "global_step": 428430, "epoch": 791, "lr": 5e-05}
{"train_loss": 2.1142449378967285, "global_step": 428431, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0894908905029297, "global_step": 428432, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0774168968200684, "global_step": 428433, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1103122234344482, "global_step": 428434, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0397400856018066, "global_step": 428435, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.070385217666626, "global_step": 428436, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9741424322128296, "global_step": 428437, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0917141437530518, "global_step": 428438, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1230428218841553, "global_step": 428439, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.050563335418701, "global_step": 428440, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0853610038757324, "global_step": 428441, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1166751384735107, "global_step": 428442, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.113924503326416, "global_step": 428443, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1107871532440186, "global_step": 428444, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.2103965282440186, "global_step": 428445, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.032128095626831, "global_step": 428446, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0697619915008545, "global_step": 428447, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.043395757675171, "global_step": 428448, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.021068572998047, "global_step": 428449, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0436694622039795, "global_step": 428450, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9924297332763672, "global_step": 428451, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.005225896835327, "global_step": 428452, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1345160007476807, "global_step": 428453, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0445632934570312, "global_step": 428454, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.020123243331909, "global_step": 428455, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0283772945404053, "global_step": 428456, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0538711547851562, "global_step": 428457, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0761618614196777, "global_step": 428458, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0690343379974365, "global_step": 428459, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0202131271362305, "global_step": 428460, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.041430950164795, "global_step": 428461, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0812737941741943, "global_step": 428462, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.016632318496704, "global_step": 428463, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.041593313217163, "global_step": 428464, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0876426696777344, "global_step": 428465, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0409858226776123, "global_step": 428466, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0816023349761963, "global_step": 428467, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.037681818008423, "global_step": 428468, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0263783931732178, "global_step": 428469, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9979993104934692, "global_step": 428470, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0995283126831055, "global_step": 428471, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.226217746734619, "global_step": 428472, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0604429244995117, "global_step": 428473, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0556137561798096, "global_step": 428474, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0663821697235107, "global_step": 428475, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1227450370788574, "global_step": 428476, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.004301071166992, "global_step": 428477, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0706000328063965, "global_step": 428478, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0698442459106445, "global_step": 428479, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.04524564743042, "global_step": 428480, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.149533271789551, "global_step": 428481, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.087246894836426, "global_step": 428482, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9837610721588135, "global_step": 428483, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1887152194976807, "global_step": 428484, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0686933994293213, "global_step": 428485, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1126158237457275, "global_step": 428486, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9972138404846191, "global_step": 428487, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0711874961853027, "global_step": 428488, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.118844985961914, "global_step": 428489, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.049758195877075, "global_step": 428490, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9963537454605103, "global_step": 428491, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.117704391479492, "global_step": 428492, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0343210697174072, "global_step": 428493, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.08074688911438, "global_step": 428494, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.052957534790039, "global_step": 428495, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0487613677978516, "global_step": 428496, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0940260887145996, "global_step": 428497, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.025341272354126, "global_step": 428498, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0416879653930664, "global_step": 428499, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1504769325256348, "global_step": 428500, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0489790439605713, "global_step": 428501, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.948121190071106, "global_step": 428502, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0976696014404297, "global_step": 428503, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9634578227996826, "global_step": 428504, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.088263988494873, "global_step": 428505, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0214734077453613, "global_step": 428506, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1305227279663086, "global_step": 428507, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1537222862243652, "global_step": 428508, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.122269630432129, "global_step": 428509, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1746065616607666, "global_step": 428510, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.080949544906616, "global_step": 428511, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.128647804260254, "global_step": 428512, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.106741189956665, "global_step": 428513, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.061180830001831, "global_step": 428514, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.074943780899048, "global_step": 428515, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.080368757247925, "global_step": 428516, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1277964115142822, "global_step": 428517, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.070727825164795, "global_step": 428518, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.032398223876953, "global_step": 428519, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1223392486572266, "global_step": 428520, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9802573919296265, "global_step": 428521, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9958691596984863, "global_step": 428522, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.023331880569458, "global_step": 428523, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1676528453826904, "global_step": 428524, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.061225175857544, "global_step": 428525, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0705864429473877, "global_step": 428526, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0613484382629395, "global_step": 428527, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1539666652679443, "global_step": 428528, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.115144729614258, "global_step": 428529, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.067990303039551, "global_step": 428530, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.089773178100586, "global_step": 428531, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0491743087768555, "global_step": 428532, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.084319591522217, "global_step": 428533, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.058122396469116, "global_step": 428534, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.976729393005371, "global_step": 428535, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.108099937438965, "global_step": 428536, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.048186779022217, "global_step": 428537, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0682268142700195, "global_step": 428538, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0042996406555176, "global_step": 428539, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.101285219192505, "global_step": 428540, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0579357147216797, "global_step": 428541, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0873146057128906, "global_step": 428542, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1174371242523193, "global_step": 428543, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.118678569793701, "global_step": 428544, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.031680107116699, "global_step": 428545, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0502560138702393, "global_step": 428546, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.112666368484497, "global_step": 428547, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0341038703918457, "global_step": 428548, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1812191009521484, "global_step": 428549, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0408871173858643, "global_step": 428550, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0091018676757812, "global_step": 428551, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.06463360786438, "global_step": 428552, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.121471881866455, "global_step": 428553, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1058807373046875, "global_step": 428554, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0625436305999756, "global_step": 428555, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0374224185943604, "global_step": 428556, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.087157726287842, "global_step": 428557, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.050980806350708, "global_step": 428558, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1048381328582764, "global_step": 428559, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0618669986724854, "global_step": 428560, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0786099433898926, "global_step": 428561, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.024404764175415, "global_step": 428562, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0677552223205566, "global_step": 428563, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.124567985534668, "global_step": 428564, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0863940715789795, "global_step": 428565, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.03383207321167, "global_step": 428566, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0814054012298584, "global_step": 428567, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0148980617523193, "global_step": 428568, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0344672203063965, "global_step": 428569, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0529370307922363, "global_step": 428570, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1660945415496826, "global_step": 428571, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0746121406555176, "global_step": 428572, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.083616018295288, "global_step": 428573, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0809435844421387, "global_step": 428574, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.051398992538452, "global_step": 428575, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0284054279327393, "global_step": 428576, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.086965322494507, "global_step": 428577, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.022212505340576, "global_step": 428578, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0828311443328857, "global_step": 428579, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9997831583023071, "global_step": 428580, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.126770496368408, "global_step": 428581, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0288453102111816, "global_step": 428582, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0411059856414795, "global_step": 428583, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.03562331199646, "global_step": 428584, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.081373691558838, "global_step": 428585, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.099302053451538, "global_step": 428586, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.064568519592285, "global_step": 428587, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0996851921081543, "global_step": 428588, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0584893226623535, "global_step": 428589, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.133439064025879, "global_step": 428590, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.141418695449829, "global_step": 428591, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1227188110351562, "global_step": 428592, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.050400972366333, "global_step": 428593, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1140427589416504, "global_step": 428594, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0988364219665527, "global_step": 428595, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1834781169891357, "global_step": 428596, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.076864242553711, "global_step": 428597, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0040900707244873, "global_step": 428598, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0797085762023926, "global_step": 428599, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0602965354919434, "global_step": 428600, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0947163105010986, "global_step": 428601, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0757665634155273, "global_step": 428602, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9893544912338257, "global_step": 428603, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0492169857025146, "global_step": 428604, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0163838863372803, "global_step": 428605, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9742757081985474, "global_step": 428606, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.001131772994995, "global_step": 428607, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0986411571502686, "global_step": 428608, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0858418941497803, "global_step": 428609, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0946805477142334, "global_step": 428610, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.141127824783325, "global_step": 428611, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1533501148223877, "global_step": 428612, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0781161785125732, "global_step": 428613, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.076172113418579, "global_step": 428614, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1205527782440186, "global_step": 428615, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.077876091003418, "global_step": 428616, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9927397966384888, "global_step": 428617, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0860660076141357, "global_step": 428618, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.071641445159912, "global_step": 428619, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1213934421539307, "global_step": 428620, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.116870641708374, "global_step": 428621, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.992142915725708, "global_step": 428622, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1171250343322754, "global_step": 428623, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0756988525390625, "global_step": 428624, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1195101737976074, "global_step": 428625, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0421302318573, "global_step": 428626, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.045808792114258, "global_step": 428627, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.156765937805176, "global_step": 428628, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.078763484954834, "global_step": 428629, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1308648586273193, "global_step": 428630, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.011584758758545, "global_step": 428631, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.038274049758911, "global_step": 428632, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0800113677978516, "global_step": 428633, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0939407348632812, "global_step": 428634, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0280184745788574, "global_step": 428635, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0786914825439453, "global_step": 428636, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9953076839447021, "global_step": 428637, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0733625888824463, "global_step": 428638, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0681684017181396, "global_step": 428639, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0394482612609863, "global_step": 428640, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.123272657394409, "global_step": 428641, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0835928916931152, "global_step": 428642, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.077965259552002, "global_step": 428643, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.047632932662964, "global_step": 428644, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9730757474899292, "global_step": 428645, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0057058334350586, "global_step": 428646, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.097536563873291, "global_step": 428647, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0567104816436768, "global_step": 428648, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0753371715545654, "global_step": 428649, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.079434871673584, "global_step": 428650, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.069913864135742, "global_step": 428651, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0628585815429688, "global_step": 428652, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.125154733657837, "global_step": 428653, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1004512310028076, "global_step": 428654, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.040757656097412, "global_step": 428655, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0958216190338135, "global_step": 428656, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0831596851348877, "global_step": 428657, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.085707426071167, "global_step": 428658, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0402486324310303, "global_step": 428659, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9965096712112427, "global_step": 428660, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0768048763275146, "global_step": 428661, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0894837379455566, "global_step": 428662, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1396336555480957, "global_step": 428663, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0892655849456787, "global_step": 428664, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0891122817993164, "global_step": 428665, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0516364574432373, "global_step": 428666, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0958690643310547, "global_step": 428667, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0852301120758057, "global_step": 428668, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0629847049713135, "global_step": 428669, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0573418140411377, "global_step": 428670, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1707892417907715, "global_step": 428671, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0483286380767822, "global_step": 428672, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9510843753814697, "global_step": 428673, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.09820294380188, "global_step": 428674, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1352758407592773, "global_step": 428675, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.089362382888794, "global_step": 428676, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0532612800598145, "global_step": 428677, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.161057949066162, "global_step": 428678, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1510181427001953, "global_step": 428679, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1199207305908203, "global_step": 428680, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1127679347991943, "global_step": 428681, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.061253309249878, "global_step": 428682, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.990412950515747, "global_step": 428683, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0250437259674072, "global_step": 428684, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0219571590423584, "global_step": 428685, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0965864658355713, "global_step": 428686, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.07369065284729, "global_step": 428687, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0930368900299072, "global_step": 428688, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.147810935974121, "global_step": 428689, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.004578113555908, "global_step": 428690, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.046754837036133, "global_step": 428691, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0754473209381104, "global_step": 428692, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1893489360809326, "global_step": 428693, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0193941593170166, "global_step": 428694, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0996429920196533, "global_step": 428695, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.075338840484619, "global_step": 428696, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.125227928161621, "global_step": 428697, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0611917972564697, "global_step": 428698, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.08270525932312, "global_step": 428699, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1059110164642334, "global_step": 428700, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.042372703552246, "global_step": 428701, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1465160846710205, "global_step": 428702, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.116534948348999, "global_step": 428703, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0819056034088135, "global_step": 428704, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.05452823638916, "global_step": 428705, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.023054599761963, "global_step": 428706, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0364537239074707, "global_step": 428707, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1728570461273193, "global_step": 428708, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.135335922241211, "global_step": 428709, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0490071773529053, "global_step": 428710, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0497891902923584, "global_step": 428711, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1041343212127686, "global_step": 428712, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0736567974090576, "global_step": 428713, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1228461265563965, "global_step": 428714, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.133342742919922, "global_step": 428715, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.069976568222046, "global_step": 428716, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.062734842300415, "global_step": 428717, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0996079444885254, "global_step": 428718, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.113948345184326, "global_step": 428719, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.009934186935425, "global_step": 428720, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0109593868255615, "global_step": 428721, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.117805004119873, "global_step": 428722, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.061326742172241, "global_step": 428723, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1281580924987793, "global_step": 428724, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.072645902633667, "global_step": 428725, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0046141147613525, "global_step": 428726, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0495853424072266, "global_step": 428727, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.06575608253479, "global_step": 428728, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0677573680877686, "global_step": 428729, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.058288097381592, "global_step": 428730, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1305930614471436, "global_step": 428731, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.044551372528076, "global_step": 428732, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0449435710906982, "global_step": 428733, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0038414001464844, "global_step": 428734, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0713233947753906, "global_step": 428735, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1040573120117188, "global_step": 428736, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.077928304672241, "global_step": 428737, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.104445457458496, "global_step": 428738, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.004779815673828, "global_step": 428739, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.142925500869751, "global_step": 428740, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1562306880950928, "global_step": 428741, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1467390060424805, "global_step": 428742, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.121812582015991, "global_step": 428743, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0076000690460205, "global_step": 428744, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.127775192260742, "global_step": 428745, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.115648031234741, "global_step": 428746, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1506547927856445, "global_step": 428747, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.033644914627075, "global_step": 428748, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.034015655517578, "global_step": 428749, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1736562252044678, "global_step": 428750, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.139247417449951, "global_step": 428751, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1311354637145996, "global_step": 428752, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9852181673049927, "global_step": 428753, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.026447296142578, "global_step": 428754, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1021180152893066, "global_step": 428755, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0017263889312744, "global_step": 428756, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0613296031951904, "global_step": 428757, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1821365356445312, "global_step": 428758, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0304362773895264, "global_step": 428759, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9989471435546875, "global_step": 428760, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.105288505554199, "global_step": 428761, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0648603439331055, "global_step": 428762, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0875821113586426, "global_step": 428763, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0713586807250977, "global_step": 428764, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0853536128997803, "global_step": 428765, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.025169610977173, "global_step": 428766, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1767187118530273, "global_step": 428767, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0685954093933105, "global_step": 428768, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0384345054626465, "global_step": 428769, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.079953908920288, "global_step": 428770, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0706377029418945, "global_step": 428771, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0203800201416016, "global_step": 428772, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1053102016448975, "global_step": 428773, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0459182262420654, "global_step": 428774, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1445064544677734, "global_step": 428775, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.115410089492798, "global_step": 428776, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0108377933502197, "global_step": 428777, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1329457759857178, "global_step": 428778, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.033146381378174, "global_step": 428779, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0348360538482666, "global_step": 428780, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0840346813201904, "global_step": 428781, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0601651668548584, "global_step": 428782, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.140676736831665, "global_step": 428783, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0737407207489014, "global_step": 428784, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0256056785583496, "global_step": 428785, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1434361934661865, "global_step": 428786, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.066551923751831, "global_step": 428787, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.138425827026367, "global_step": 428788, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0644915103912354, "global_step": 428789, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0428874492645264, "global_step": 428790, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0847554206848145, "global_step": 428791, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0830841064453125, "global_step": 428792, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.095165491104126, "global_step": 428793, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0342605113983154, "global_step": 428794, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0727357864379883, "global_step": 428795, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.084425449371338, "global_step": 428796, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.095425844192505, "global_step": 428797, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0979015827178955, "global_step": 428798, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0033366680145264, "global_step": 428799, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.040900468826294, "global_step": 428800, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1180357933044434, "global_step": 428801, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1332032680511475, "global_step": 428802, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.14825439453125, "global_step": 428803, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1766459941864014, "global_step": 428804, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.083327054977417, "global_step": 428805, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1290383338928223, "global_step": 428806, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0740127563476562, "global_step": 428807, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0613391399383545, "global_step": 428808, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0775840282440186, "global_step": 428809, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.12719988822937, "global_step": 428810, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0823326110839844, "global_step": 428811, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.151931047439575, "global_step": 428812, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.059105396270752, "global_step": 428813, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.114518642425537, "global_step": 428814, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0804946422576904, "global_step": 428815, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.092219114303589, "global_step": 428816, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0622236728668213, "global_step": 428817, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0194289684295654, "global_step": 428818, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0902843475341797, "global_step": 428819, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.057182788848877, "global_step": 428820, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0829081535339355, "global_step": 428821, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.102461576461792, "global_step": 428822, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0920355319976807, "global_step": 428823, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0118651390075684, "global_step": 428824, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0348479747772217, "global_step": 428825, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.083293914794922, "global_step": 428826, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.132626533508301, "global_step": 428827, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.092528820037842, "global_step": 428828, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0393428802490234, "global_step": 428829, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.063002586364746, "global_step": 428830, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.125671625137329, "global_step": 428831, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.108361005783081, "global_step": 428832, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1981348991394043, "global_step": 428833, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0570149421691895, "global_step": 428834, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1020495891571045, "global_step": 428835, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0462629795074463, "global_step": 428836, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1809847354888916, "global_step": 428837, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1425678730010986, "global_step": 428838, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.975663185119629, "global_step": 428839, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1267738342285156, "global_step": 428840, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0743374824523926, "global_step": 428841, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.155400037765503, "global_step": 428842, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1321816444396973, "global_step": 428843, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.191027879714966, "global_step": 428844, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0850911140441895, "global_step": 428845, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.102879524230957, "global_step": 428846, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.141282320022583, "global_step": 428847, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1230735778808594, "global_step": 428848, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1242258548736572, "global_step": 428849, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.066337823867798, "global_step": 428850, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.007683515548706, "global_step": 428851, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1250452995300293, "global_step": 428852, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1246049404144287, "global_step": 428853, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0581789016723633, "global_step": 428854, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.052130937576294, "global_step": 428855, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0460305213928223, "global_step": 428856, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.084249258041382, "global_step": 428857, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9951400756835938, "global_step": 428858, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0654962062835693, "global_step": 428859, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.03104829788208, "global_step": 428860, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0134756565093994, "global_step": 428861, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0305042266845703, "global_step": 428862, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.101889133453369, "global_step": 428863, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.104034900665283, "global_step": 428864, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.16229510307312, "global_step": 428865, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0810182094573975, "global_step": 428866, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0084950923919678, "global_step": 428867, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.125903367996216, "global_step": 428868, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0441324710845947, "global_step": 428869, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0682179927825928, "global_step": 428870, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.055093765258789, "global_step": 428871, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0434720516204834, "global_step": 428872, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0689501762390137, "global_step": 428873, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0318989753723145, "global_step": 428874, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.095107316970825, "global_step": 428875, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.066497325897217, "global_step": 428876, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.124133825302124, "global_step": 428877, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0442678928375244, "global_step": 428878, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.100006580352783, "global_step": 428879, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.089071273803711, "global_step": 428880, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.134739398956299, "global_step": 428881, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.055649518966675, "global_step": 428882, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0338995456695557, "global_step": 428883, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0466256141662598, "global_step": 428884, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0930874347686768, "global_step": 428885, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.050997495651245, "global_step": 428886, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.166886806488037, "global_step": 428887, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.121396064758301, "global_step": 428888, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1960487365722656, "global_step": 428889, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.037562608718872, "global_step": 428890, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0786707401275635, "global_step": 428891, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1053543090820312, "global_step": 428892, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0684237480163574, "global_step": 428893, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.023249387741089, "global_step": 428894, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.166062116622925, "global_step": 428895, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1190223693847656, "global_step": 428896, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1764097213745117, "global_step": 428897, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.026458501815796, "global_step": 428898, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1034648418426514, "global_step": 428899, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0055222511291504, "global_step": 428900, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0625083446502686, "global_step": 428901, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.05302357673645, "global_step": 428902, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0412213802337646, "global_step": 428903, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1257574558258057, "global_step": 428904, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0798134803771973, "global_step": 428905, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1444225311279297, "global_step": 428906, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0887839794158936, "global_step": 428907, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.042400360107422, "global_step": 428908, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.111901044845581, "global_step": 428909, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1221766471862793, "global_step": 428910, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.100125789642334, "global_step": 428911, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.086820602416992, "global_step": 428912, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0746371746063232, "global_step": 428913, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.110330581665039, "global_step": 428914, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0578691959381104, "global_step": 428915, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1879916191101074, "global_step": 428916, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.151139497756958, "global_step": 428917, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.09126615524292, "global_step": 428918, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1103103160858154, "global_step": 428919, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.025327444076538, "global_step": 428920, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.103238821029663, "global_step": 428921, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.011510133743286, "global_step": 428922, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.059352397918701, "global_step": 428923, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1116933822631836, "global_step": 428924, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.00468373298645, "global_step": 428925, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.171384334564209, "global_step": 428926, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.087373971939087, "global_step": 428927, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.078651189804077, "global_step": 428928, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0697031021118164, "global_step": 428929, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0507123470306396, "global_step": 428930, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.106919050216675, "global_step": 428931, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1479320526123047, "global_step": 428932, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9915001392364502, "global_step": 428933, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.196131467819214, "global_step": 428934, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.013658285140991, "global_step": 428935, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.150362968444824, "global_step": 428936, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1195926666259766, "global_step": 428937, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0526294708251953, "global_step": 428938, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.132194995880127, "global_step": 428939, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.035781145095825, "global_step": 428940, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.084455966949463, "global_step": 428941, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0494415760040283, "global_step": 428942, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.191091537475586, "global_step": 428943, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.11690092086792, "global_step": 428944, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0395946502685547, "global_step": 428945, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1451852321624756, "global_step": 428946, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.059291362762451, "global_step": 428947, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1201369762420654, "global_step": 428948, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.149807929992676, "global_step": 428949, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1365349292755127, "global_step": 428950, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.111316204071045, "global_step": 428951, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.056035280227661, "global_step": 428952, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.134312629699707, "global_step": 428953, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.159003257751465, "global_step": 428954, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.026878595352173, "global_step": 428955, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1689295768737793, "global_step": 428956, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.015043020248413, "global_step": 428957, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0746829509735107, "global_step": 428958, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.098682403564453, "global_step": 428959, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0263314247131348, "global_step": 428960, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.121877670288086, "global_step": 428961, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1228394508361816, "global_step": 428962, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1082677841186523, "global_step": 428963, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.059454917907715, "global_step": 428964, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.077366352081299, "global_step": 428965, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.051704168319702, "global_step": 428966, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.082958459854126, "global_step": 428967, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0595366954803467, "global_step": 428968, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0731825828552246, "global_step": 428969, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0118589401245117, "global_step": 428970, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.101679801940918, "global_step": 428971, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.065408229827881, "global_step": 428972, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.113985776901245, "global_step": 428973, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1011874675750732, "global_step": 428974, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.052371025085449, "global_step": 428975, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.050926685333252, "global_step": 428976, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0974924564361572, "global_step": 428977, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.049729824066162, "global_step": 428978, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.088078498840332, "global_step": 428979, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.106729745864868, "global_step": 428980, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.103524923324585, "global_step": 428981, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0795607566833496, "global_step": 428982, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.070970296859741, "global_step": 428983, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0291807651519775, "global_step": 428984, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.090189218521118, "global_step": 428985, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1269888877868652, "global_step": 428986, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1032907962799072, "global_step": 428987, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.104240894317627, "global_step": 428988, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0384747982025146, "global_step": 428989, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.050018787384033, "global_step": 428990, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.02164888381958, "global_step": 428991, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0334227085113525, "global_step": 428992, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0517497062683105, "global_step": 428993, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0923805236816406, "global_step": 428994, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.087707042694092, "global_step": 428995, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.048548698425293, "global_step": 428996, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1159982681274414, "global_step": 428997, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.084209442138672, "global_step": 428998, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1203176975250244, "global_step": 428999, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.169969081878662, "global_step": 429000, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0915403366088867, "global_step": 429001, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1998980045318604, "global_step": 429002, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1502726078033447, "global_step": 429003, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1738264560699463, "global_step": 429004, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1080257892608643, "global_step": 429005, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0169522762298584, "global_step": 429006, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.06380558013916, "global_step": 429007, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.02983021736145, "global_step": 429008, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0367510318756104, "global_step": 429009, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0498156547546387, "global_step": 429010, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.13108229637146, "global_step": 429011, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1084113121032715, "global_step": 429012, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1033215522766113, "global_step": 429013, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0127406120300293, "global_step": 429014, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.144517421722412, "global_step": 429015, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.150146007537842, "global_step": 429016, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0941531658172607, "global_step": 429017, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0489938259124756, "global_step": 429018, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0438389778137207, "global_step": 429019, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1164498329162598, "global_step": 429020, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1014206409454346, "global_step": 429021, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1002626419067383, "global_step": 429022, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1249799728393555, "global_step": 429023, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0515596866607666, "global_step": 429024, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.057915449142456, "global_step": 429025, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.110971212387085, "global_step": 429026, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.040243625640869, "global_step": 429027, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.071491003036499, "global_step": 429028, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1595818996429443, "global_step": 429029, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1518146991729736, "global_step": 429030, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0919721126556396, "global_step": 429031, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.02539324760437, "global_step": 429032, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.066126585006714, "global_step": 429033, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.136610507965088, "global_step": 429034, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0917046070098877, "global_step": 429035, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0669374465942383, "global_step": 429036, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0873847007751465, "global_step": 429037, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9925044775009155, "global_step": 429038, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0891261100769043, "global_step": 429039, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9746854305267334, "global_step": 429040, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0926356315612793, "global_step": 429041, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.133995771408081, "global_step": 429042, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0592339038848877, "global_step": 429043, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1243703365325928, "global_step": 429044, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.020291328430176, "global_step": 429045, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1174771785736084, "global_step": 429046, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.205751657485962, "global_step": 429047, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0849082469940186, "global_step": 429048, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1133129596710205, "global_step": 429049, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.060523271560669, "global_step": 429050, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.044628858566284, "global_step": 429051, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0975637435913086, "global_step": 429052, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.103675365447998, "global_step": 429053, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.094109296798706, "global_step": 429054, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.103748321533203, "global_step": 429055, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0281848907470703, "global_step": 429056, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0577337741851807, "global_step": 429057, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0825796127319336, "global_step": 429058, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1205389499664307, "global_step": 429059, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0452706813812256, "global_step": 429060, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0998942852020264, "global_step": 429061, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0137062072753906, "global_step": 429062, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0278961658477783, "global_step": 429063, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.094484567642212, "global_step": 429064, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.11757230758667, "global_step": 429065, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1773345470428467, "global_step": 429066, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.083620309829712, "global_step": 429067, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1476292610168457, "global_step": 429068, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.062952995300293, "global_step": 429069, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.124706506729126, "global_step": 429070, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1171810626983643, "global_step": 429071, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0857295989990234, "global_step": 429072, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.101461887359619, "global_step": 429073, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9965615272521973, "global_step": 429074, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0156147480010986, "global_step": 429075, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.117877721786499, "global_step": 429076, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.160767078399658, "global_step": 429077, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.115149974822998, "global_step": 429078, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.076608896255493, "global_step": 429079, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.032010555267334, "global_step": 429080, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.037412643432617, "global_step": 429081, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.03709077835083, "global_step": 429082, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1345021724700928, "global_step": 429083, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.105180025100708, "global_step": 429084, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1162564754486084, "global_step": 429085, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.200688362121582, "global_step": 429086, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.061349630355835, "global_step": 429087, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.115617513656616, "global_step": 429088, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0703582763671875, "global_step": 429089, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0855491161346436, "global_step": 429090, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.056744337081909, "global_step": 429091, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0709805488586426, "global_step": 429092, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1292216777801514, "global_step": 429093, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.089179039001465, "global_step": 429094, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1984338760375977, "global_step": 429095, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0562024116516113, "global_step": 429096, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0497217178344727, "global_step": 429097, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.171973466873169, "global_step": 429098, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.015561103820801, "global_step": 429099, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.182142734527588, "global_step": 429100, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.078425407409668, "global_step": 429101, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0998926162719727, "global_step": 429102, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.087745189666748, "global_step": 429103, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.164733409881592, "global_step": 429104, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1275479793548584, "global_step": 429105, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0886945724487305, "global_step": 429106, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0201945304870605, "global_step": 429107, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1073999404907227, "global_step": 429108, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.037731409072876, "global_step": 429109, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.074267625808716, "global_step": 429110, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0370121002197266, "global_step": 429111, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0871315002441406, "global_step": 429112, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.152998924255371, "global_step": 429113, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.100001335144043, "global_step": 429114, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0740740299224854, "global_step": 429115, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.8894068002700806, "global_step": 429116, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9525196552276611, "global_step": 429117, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1009538173675537, "global_step": 429118, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.091505527496338, "global_step": 429119, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0524916648864746, "global_step": 429120, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.072502374649048, "global_step": 429121, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1150317192077637, "global_step": 429122, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.162160634994507, "global_step": 429123, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0039665699005127, "global_step": 429124, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.09865403175354, "global_step": 429125, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1483185291290283, "global_step": 429126, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0637316703796387, "global_step": 429127, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0395259857177734, "global_step": 429128, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.049222946166992, "global_step": 429129, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0487775802612305, "global_step": 429130, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.056739568710327, "global_step": 429131, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1081936359405518, "global_step": 429132, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9902145862579346, "global_step": 429133, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.095966100692749, "global_step": 429134, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9948240518569946, "global_step": 429135, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.068087100982666, "global_step": 429136, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1003613471984863, "global_step": 429137, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0186667442321777, "global_step": 429138, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.104588031768799, "global_step": 429139, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1579978466033936, "global_step": 429140, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1594810485839844, "global_step": 429141, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1686244010925293, "global_step": 429142, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.088789939880371, "global_step": 429143, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0334484577178955, "global_step": 429144, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.109976053237915, "global_step": 429145, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0654025077819824, "global_step": 429146, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0591423511505127, "global_step": 429147, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.095118761062622, "global_step": 429148, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.116441249847412, "global_step": 429149, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.134032964706421, "global_step": 429150, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.007535219192505, "global_step": 429151, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0508360862731934, "global_step": 429152, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1150944232940674, "global_step": 429153, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.104753255844116, "global_step": 429154, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0598835945129395, "global_step": 429155, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0196914672851562, "global_step": 429156, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.139566659927368, "global_step": 429157, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0984036922454834, "global_step": 429158, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0565671920776367, "global_step": 429159, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0213451385498047, "global_step": 429160, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.135697841644287, "global_step": 429161, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.017340898513794, "global_step": 429162, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9867446422576904, "global_step": 429163, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.078979969024658, "global_step": 429164, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.063311815261841, "global_step": 429165, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1105520725250244, "global_step": 429166, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1098575592041016, "global_step": 429167, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.101478338241577, "global_step": 429168, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0650880336761475, "global_step": 429169, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0523195266723633, "global_step": 429170, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0899908542633057, "global_step": 429171, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0647497177124023, "global_step": 429172, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1327390670776367, "global_step": 429173, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.039660930633545, "global_step": 429174, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0805439949035645, "global_step": 429175, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.115971803665161, "global_step": 429176, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.090165853500366, "global_step": 429177, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.020376205444336, "global_step": 429178, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.071228504180908, "global_step": 429179, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.150409460067749, "global_step": 429180, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1473333835601807, "global_step": 429181, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1069400310516357, "global_step": 429182, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1121134757995605, "global_step": 429183, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.212320566177368, "global_step": 429184, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1108391284942627, "global_step": 429185, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0731520652770996, "global_step": 429186, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1234524250030518, "global_step": 429187, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9965075254440308, "global_step": 429188, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0289218425750732, "global_step": 429189, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.046139717102051, "global_step": 429190, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.061475992202759, "global_step": 429191, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1779580116271973, "global_step": 429192, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1690821647644043, "global_step": 429193, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.063737630844116, "global_step": 429194, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.078071117401123, "global_step": 429195, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0681421756744385, "global_step": 429196, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.003862142562866, "global_step": 429197, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0782651901245117, "global_step": 429198, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.117846965789795, "global_step": 429199, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.11090087890625, "global_step": 429200, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0264530181884766, "global_step": 429201, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.054969310760498, "global_step": 429202, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0272951126098633, "global_step": 429203, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.158794403076172, "global_step": 429204, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1157124042510986, "global_step": 429205, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0976979732513428, "global_step": 429206, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0977818965911865, "global_step": 429207, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0636329650878906, "global_step": 429208, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.132974624633789, "global_step": 429209, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0928006172180176, "global_step": 429210, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.079050302505493, "global_step": 429211, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1226816177368164, "global_step": 429212, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.017988443374634, "global_step": 429213, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0932352542877197, "global_step": 429214, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0684187412261963, "global_step": 429215, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.115190029144287, "global_step": 429216, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.15336012840271, "global_step": 429217, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.088488817214966, "global_step": 429218, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0537006855010986, "global_step": 429219, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.192563056945801, "global_step": 429220, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.094710111618042, "global_step": 429221, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0603058338165283, "global_step": 429222, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.007063388824463, "global_step": 429223, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1364171504974365, "global_step": 429224, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0781548023223877, "global_step": 429225, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.116138219833374, "global_step": 429226, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1171936988830566, "global_step": 429227, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.11456036567688, "global_step": 429228, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.142249584197998, "global_step": 429229, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.104444742202759, "global_step": 429230, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.080814838409424, "global_step": 429231, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.104344367980957, "global_step": 429232, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0405962467193604, "global_step": 429233, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0523667335510254, "global_step": 429234, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.046351909637451, "global_step": 429235, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.008897066116333, "global_step": 429236, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1257846355438232, "global_step": 429237, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.094642162322998, "global_step": 429238, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0310685634613037, "global_step": 429239, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0767579078674316, "global_step": 429240, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0685627460479736, "global_step": 429241, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0918335914611816, "global_step": 429242, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1624345779418945, "global_step": 429243, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.070835590362549, "global_step": 429244, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.108785390853882, "global_step": 429245, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1879844665527344, "global_step": 429246, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0651001930236816, "global_step": 429247, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.111707925796509, "global_step": 429248, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9823572635650635, "global_step": 429249, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0428152084350586, "global_step": 429250, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.024643898010254, "global_step": 429251, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1664156913757324, "global_step": 429252, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9847872257232666, "global_step": 429253, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.047220468521118, "global_step": 429254, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.157310962677002, "global_step": 429255, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.086651086807251, "global_step": 429256, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1292459964752197, "global_step": 429257, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.099900960922241, "global_step": 429258, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.041494846343994, "global_step": 429259, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0054171085357666, "global_step": 429260, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1098082065582275, "global_step": 429261, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0949974060058594, "global_step": 429262, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1395254135131836, "global_step": 429263, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.145887851715088, "global_step": 429264, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.2009713649749756, "global_step": 429265, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.114495277404785, "global_step": 429266, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0970189571380615, "global_step": 429267, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.105487823486328, "global_step": 429268, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.043494939804077, "global_step": 429269, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.11942195892334, "global_step": 429270, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1403582096099854, "global_step": 429271, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.118027925491333, "global_step": 429272, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.141225814819336, "global_step": 429273, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0363810062408447, "global_step": 429274, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1447386741638184, "global_step": 429275, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.123156785964966, "global_step": 429276, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1012325286865234, "global_step": 429277, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.047673463821411, "global_step": 429278, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0533928871154785, "global_step": 429279, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.138284206390381, "global_step": 429280, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.048863649368286, "global_step": 429281, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0977585315704346, "global_step": 429282, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0859854221343994, "global_step": 429283, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1031205654144287, "global_step": 429284, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0730016231536865, "global_step": 429285, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0504093170166016, "global_step": 429286, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0395920276641846, "global_step": 429287, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.038984775543213, "global_step": 429288, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1219964027404785, "global_step": 429289, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0870163440704346, "global_step": 429290, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.107008934020996, "global_step": 429291, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.232844591140747, "global_step": 429292, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1058969497680664, "global_step": 429293, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.015683174133301, "global_step": 429294, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1419787406921387, "global_step": 429295, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9799184799194336, "global_step": 429296, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.043407678604126, "global_step": 429297, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9521565437316895, "global_step": 429298, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.098473310470581, "global_step": 429299, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0525875091552734, "global_step": 429300, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1164746284484863, "global_step": 429301, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.988839030265808, "global_step": 429302, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0214431285858154, "global_step": 429303, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0788257122039795, "global_step": 429304, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0986456871032715, "global_step": 429305, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0719313621520996, "global_step": 429306, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0636308193206787, "global_step": 429307, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0715079307556152, "global_step": 429308, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.078901767730713, "global_step": 429309, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.159573793411255, "global_step": 429310, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.104323148727417, "global_step": 429311, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0580596923828125, "global_step": 429312, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.01058030128479, "global_step": 429313, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1258697509765625, "global_step": 429314, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.100085496902466, "global_step": 429315, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0776567459106445, "global_step": 429316, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1019463539123535, "global_step": 429317, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0732898712158203, "global_step": 429318, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9795527458190918, "global_step": 429319, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0701217651367188, "global_step": 429320, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1641430854797363, "global_step": 429321, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.111754894256592, "global_step": 429322, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1510965824127197, "global_step": 429323, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1181652545928955, "global_step": 429324, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.132327079772949, "global_step": 429325, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1026692390441895, "global_step": 429326, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1048758029937744, "global_step": 429327, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0412402153015137, "global_step": 429328, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.126676082611084, "global_step": 429329, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0761630535125732, "global_step": 429330, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1527280807495117, "global_step": 429331, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1338627338409424, "global_step": 429332, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1032931804656982, "global_step": 429333, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.215477228164673, "global_step": 429334, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1383261680603027, "global_step": 429335, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.093663215637207, "global_step": 429336, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1401116847991943, "global_step": 429337, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.123749017715454, "global_step": 429338, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0818772315979004, "global_step": 429339, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0044901371002197, "global_step": 429340, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.072283983230591, "global_step": 429341, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.151928424835205, "global_step": 429342, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.055752992630005, "global_step": 429343, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.107393741607666, "global_step": 429344, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.071791172027588, "global_step": 429345, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1180505752563477, "global_step": 429346, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.14170241355896, "global_step": 429347, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9343888759613037, "global_step": 429348, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0982115268707275, "global_step": 429349, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1412954330444336, "global_step": 429350, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.084226369857788, "global_step": 429351, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.070753335952759, "global_step": 429352, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0127339363098145, "global_step": 429353, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0463502407073975, "global_step": 429354, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9715487957000732, "global_step": 429355, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.090977430343628, "global_step": 429356, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.158536911010742, "global_step": 429357, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.048936605453491, "global_step": 429358, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.015244245529175, "global_step": 429359, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0891737937927246, "global_step": 429360, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.16526460647583, "global_step": 429361, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.078625202178955, "global_step": 429362, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.136732339859009, "global_step": 429363, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.086681604385376, "global_step": 429364, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.080101490020752, "global_step": 429365, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1030874252319336, "global_step": 429366, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.099663019180298, "global_step": 429367, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0186595916748047, "global_step": 429368, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.144444704055786, "global_step": 429369, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1199262142181396, "global_step": 429370, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.9447829723358154, "global_step": 429371, "epoch": 792, "lr": 5e-05}
{"train_loss": 1.940796971321106, "global_step": 429372, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0617663860321045, "global_step": 429373, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0349812507629395, "global_step": 429374, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0393166542053223, "global_step": 429375, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0393033027648926, "global_step": 429376, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.031826972961426, "global_step": 429377, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.146549701690674, "global_step": 429378, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1143927574157715, "global_step": 429379, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0689549446105957, "global_step": 429380, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.116870880126953, "global_step": 429381, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0062129497528076, "global_step": 429382, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.118382692337036, "global_step": 429383, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0547823905944824, "global_step": 429384, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.169796943664551, "global_step": 429385, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1107308864593506, "global_step": 429386, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0433950424194336, "global_step": 429387, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0922434329986572, "global_step": 429388, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.128532886505127, "global_step": 429389, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.2120659351348877, "global_step": 429390, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0957298278808594, "global_step": 429391, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0743134021759033, "global_step": 429392, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.075234889984131, "global_step": 429393, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.05914306640625, "global_step": 429394, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1052372455596924, "global_step": 429395, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1509053707122803, "global_step": 429396, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.0640270709991455, "global_step": 429397, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1609363555908203, "global_step": 429398, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.082141876220703, "global_step": 429399, "epoch": 792, "lr": 5e-05}
{"train_loss": 2.1372525691986084, "global_step": 429400, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0379927158355713, "global_step": 429401, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0218546390533447, "global_step": 429402, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.122642993927002, "global_step": 429403, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0624709129333496, "global_step": 429404, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1123809814453125, "global_step": 429405, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0797109603881836, "global_step": 429406, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0334413051605225, "global_step": 429407, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0705599784851074, "global_step": 429408, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.020690441131592, "global_step": 429409, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1073920726776123, "global_step": 429410, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.075456142425537, "global_step": 429411, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9993462562561035, "global_step": 429412, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0843472480773926, "global_step": 429413, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1087849140167236, "global_step": 429414, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.98062002658844, "global_step": 429415, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.985085129737854, "global_step": 429416, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.069077730178833, "global_step": 429417, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0628581047058105, "global_step": 429418, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.072913646697998, "global_step": 429419, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0987977981567383, "global_step": 429420, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0586867332458496, "global_step": 429421, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1119532585144043, "global_step": 429422, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1434547901153564, "global_step": 429423, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1402785778045654, "global_step": 429424, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.083958625793457, "global_step": 429425, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0897514820098877, "global_step": 429426, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0310442447662354, "global_step": 429427, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.027484893798828, "global_step": 429428, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.063432455062866, "global_step": 429429, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0873830318450928, "global_step": 429430, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9852458238601685, "global_step": 429431, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1421585083007812, "global_step": 429432, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.000437021255493, "global_step": 429433, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0938234329223633, "global_step": 429434, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.043674945831299, "global_step": 429435, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.090108633041382, "global_step": 429436, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.061474323272705, "global_step": 429437, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.022861957550049, "global_step": 429438, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1236660480499268, "global_step": 429439, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.033615827560425, "global_step": 429440, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0552027225494385, "global_step": 429441, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.016385316848755, "global_step": 429442, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0906333923339844, "global_step": 429443, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.015859842300415, "global_step": 429444, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1379239559173584, "global_step": 429445, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.109877347946167, "global_step": 429446, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.041318416595459, "global_step": 429447, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0007247924804688, "global_step": 429448, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0035014152526855, "global_step": 429449, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.048375129699707, "global_step": 429450, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.14750075340271, "global_step": 429451, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0251240730285645, "global_step": 429452, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0409648418426514, "global_step": 429453, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.039917469024658, "global_step": 429454, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0415518283843994, "global_step": 429455, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.137613296508789, "global_step": 429456, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.118565320968628, "global_step": 429457, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.022719383239746, "global_step": 429458, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0796709060668945, "global_step": 429459, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9893670082092285, "global_step": 429460, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0143790245056152, "global_step": 429461, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1134841442108154, "global_step": 429462, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.132697582244873, "global_step": 429463, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.052628993988037, "global_step": 429464, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1662344932556152, "global_step": 429465, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.065229892730713, "global_step": 429466, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1118032932281494, "global_step": 429467, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9768943786621094, "global_step": 429468, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1698973178863525, "global_step": 429469, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1134305000305176, "global_step": 429470, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1072237491607666, "global_step": 429471, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0254716873168945, "global_step": 429472, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.039544105529785, "global_step": 429473, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0831034183502197, "global_step": 429474, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0927608013153076, "global_step": 429475, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1174793243408203, "global_step": 429476, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.070002794265747, "global_step": 429477, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0700080394744873, "global_step": 429478, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1220102310180664, "global_step": 429479, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.083103895187378, "global_step": 429480, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.990807294845581, "global_step": 429481, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1386308670043945, "global_step": 429482, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0392298698425293, "global_step": 429483, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.138707160949707, "global_step": 429484, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.04028582572937, "global_step": 429485, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.113354206085205, "global_step": 429486, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0690035820007324, "global_step": 429487, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1204402446746826, "global_step": 429488, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.06044340133667, "global_step": 429489, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0835726261138916, "global_step": 429490, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1173322200775146, "global_step": 429491, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.032506227493286, "global_step": 429492, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1558756828308105, "global_step": 429493, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0965616703033447, "global_step": 429494, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0466949939727783, "global_step": 429495, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1753950119018555, "global_step": 429496, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0900304317474365, "global_step": 429497, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0584099292755127, "global_step": 429498, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.150797128677368, "global_step": 429499, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0605170726776123, "global_step": 429500, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.132936477661133, "global_step": 429501, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1056013107299805, "global_step": 429502, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.05104923248291, "global_step": 429503, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.139324903488159, "global_step": 429504, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0497379302978516, "global_step": 429505, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9979267120361328, "global_step": 429506, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.069303512573242, "global_step": 429507, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.083104133605957, "global_step": 429508, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0037589073181152, "global_step": 429509, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.028432846069336, "global_step": 429510, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0473756790161133, "global_step": 429511, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0832834243774414, "global_step": 429512, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1816670894622803, "global_step": 429513, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.114192485809326, "global_step": 429514, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0069174766540527, "global_step": 429515, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.070040464401245, "global_step": 429516, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.125145435333252, "global_step": 429517, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1258773803710938, "global_step": 429518, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.073544502258301, "global_step": 429519, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0827677249908447, "global_step": 429520, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1347146034240723, "global_step": 429521, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0933961868286133, "global_step": 429522, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0439631938934326, "global_step": 429523, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.069319725036621, "global_step": 429524, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0936667919158936, "global_step": 429525, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.049048662185669, "global_step": 429526, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0921103954315186, "global_step": 429527, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0446832180023193, "global_step": 429528, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.151228904724121, "global_step": 429529, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0525505542755127, "global_step": 429530, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.089963674545288, "global_step": 429531, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.023822546005249, "global_step": 429532, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0851221084594727, "global_step": 429533, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.050912380218506, "global_step": 429534, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0215930938720703, "global_step": 429535, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.104419708251953, "global_step": 429536, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.111489772796631, "global_step": 429537, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.082848072052002, "global_step": 429538, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0460216999053955, "global_step": 429539, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0440657138824463, "global_step": 429540, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.094378709793091, "global_step": 429541, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0468087196350098, "global_step": 429542, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1080236434936523, "global_step": 429543, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0974528789520264, "global_step": 429544, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.048630714416504, "global_step": 429545, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.2155134677886963, "global_step": 429546, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0535101890563965, "global_step": 429547, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0260868072509766, "global_step": 429548, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.06538987159729, "global_step": 429549, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0546810626983643, "global_step": 429550, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.030763626098633, "global_step": 429551, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.087768077850342, "global_step": 429552, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1065125465393066, "global_step": 429553, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0680606365203857, "global_step": 429554, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1192705631256104, "global_step": 429555, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.107248306274414, "global_step": 429556, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1027493476867676, "global_step": 429557, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0910592079162598, "global_step": 429558, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.228520393371582, "global_step": 429559, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1131529808044434, "global_step": 429560, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1285271644592285, "global_step": 429561, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0124013423919678, "global_step": 429562, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0282299518585205, "global_step": 429563, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1009185314178467, "global_step": 429564, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0854575634002686, "global_step": 429565, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.127480983734131, "global_step": 429566, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.131242036819458, "global_step": 429567, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0724520683288574, "global_step": 429568, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0190749168395996, "global_step": 429569, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.084838390350342, "global_step": 429570, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.030358076095581, "global_step": 429571, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0706419944763184, "global_step": 429572, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0096285343170166, "global_step": 429573, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0379934310913086, "global_step": 429574, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9748879671096802, "global_step": 429575, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0284316539764404, "global_step": 429576, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1240477561950684, "global_step": 429577, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.051210880279541, "global_step": 429578, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.057746648788452, "global_step": 429579, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.062438726425171, "global_step": 429580, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.04510235786438, "global_step": 429581, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0958971977233887, "global_step": 429582, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.054351568222046, "global_step": 429583, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.145250082015991, "global_step": 429584, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0067145824432373, "global_step": 429585, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1054866313934326, "global_step": 429586, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0623111724853516, "global_step": 429587, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0723602771759033, "global_step": 429588, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0983242988586426, "global_step": 429589, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0602455139160156, "global_step": 429590, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.14947509765625, "global_step": 429591, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0151889324188232, "global_step": 429592, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.079137086868286, "global_step": 429593, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0478198528289795, "global_step": 429594, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.005333423614502, "global_step": 429595, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9855916500091553, "global_step": 429596, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.036283493041992, "global_step": 429597, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0640885829925537, "global_step": 429598, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0816733837127686, "global_step": 429599, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9585834741592407, "global_step": 429600, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.161529302597046, "global_step": 429601, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.028977870941162, "global_step": 429602, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0615036487579346, "global_step": 429603, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.093229055404663, "global_step": 429604, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1929924488067627, "global_step": 429605, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1026132106781006, "global_step": 429606, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.066551685333252, "global_step": 429607, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.098412036895752, "global_step": 429608, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.141350269317627, "global_step": 429609, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0534005165100098, "global_step": 429610, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0714476108551025, "global_step": 429611, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1248345375061035, "global_step": 429612, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1412689685821533, "global_step": 429613, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.010227918624878, "global_step": 429614, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.122602701187134, "global_step": 429615, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0860097408294678, "global_step": 429616, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1081976890563965, "global_step": 429617, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.081138849258423, "global_step": 429618, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0568466186523438, "global_step": 429619, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.123304605484009, "global_step": 429620, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.174675226211548, "global_step": 429621, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1247735023498535, "global_step": 429622, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0143473148345947, "global_step": 429623, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0938093662261963, "global_step": 429624, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0997374057769775, "global_step": 429625, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1271185874938965, "global_step": 429626, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.070160150527954, "global_step": 429627, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0624096393585205, "global_step": 429628, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1000423431396484, "global_step": 429629, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.124340772628784, "global_step": 429630, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9935134649276733, "global_step": 429631, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0315423011779785, "global_step": 429632, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.055617094039917, "global_step": 429633, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.043826103210449, "global_step": 429634, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9340274333953857, "global_step": 429635, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0961225032806396, "global_step": 429636, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0004305839538574, "global_step": 429637, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1846377849578857, "global_step": 429638, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.2152950763702393, "global_step": 429639, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1119754314422607, "global_step": 429640, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.981897234916687, "global_step": 429641, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0607821941375732, "global_step": 429642, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1807281970977783, "global_step": 429643, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.095890760421753, "global_step": 429644, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.98688542842865, "global_step": 429645, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0260374546051025, "global_step": 429646, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1273391246795654, "global_step": 429647, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.173743486404419, "global_step": 429648, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0477383136749268, "global_step": 429649, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.075437545776367, "global_step": 429650, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.130720615386963, "global_step": 429651, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0206003189086914, "global_step": 429652, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1314406394958496, "global_step": 429653, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0652554035186768, "global_step": 429654, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.093547821044922, "global_step": 429655, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1363155841827393, "global_step": 429656, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.071359634399414, "global_step": 429657, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.147930145263672, "global_step": 429658, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.035851240158081, "global_step": 429659, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1145853996276855, "global_step": 429660, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0862138271331787, "global_step": 429661, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.045360565185547, "global_step": 429662, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.135136604309082, "global_step": 429663, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.083388328552246, "global_step": 429664, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1128973960876465, "global_step": 429665, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0755856037139893, "global_step": 429666, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0791115760803223, "global_step": 429667, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.139824628829956, "global_step": 429668, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1201322078704834, "global_step": 429669, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0491509437561035, "global_step": 429670, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.023536205291748, "global_step": 429671, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1242623329162598, "global_step": 429672, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1358678340911865, "global_step": 429673, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0732829570770264, "global_step": 429674, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.12894868850708, "global_step": 429675, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.022653341293335, "global_step": 429676, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.053807020187378, "global_step": 429677, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1404640674591064, "global_step": 429678, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.114011526107788, "global_step": 429679, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9757747650146484, "global_step": 429680, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0318939685821533, "global_step": 429681, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.2279300689697266, "global_step": 429682, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.119366407394409, "global_step": 429683, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.12038254737854, "global_step": 429684, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1021382808685303, "global_step": 429685, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1082863807678223, "global_step": 429686, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0491273403167725, "global_step": 429687, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.192087411880493, "global_step": 429688, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.062293767929077, "global_step": 429689, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.064643383026123, "global_step": 429690, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0876083374023438, "global_step": 429691, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.049982786178589, "global_step": 429692, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1359951496124268, "global_step": 429693, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1091065406799316, "global_step": 429694, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0960159301757812, "global_step": 429695, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.066012382507324, "global_step": 429696, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.072033643722534, "global_step": 429697, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1189310550689697, "global_step": 429698, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0353684425354004, "global_step": 429699, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.056515693664551, "global_step": 429700, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0710670948028564, "global_step": 429701, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9609500169754028, "global_step": 429702, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0434961318969727, "global_step": 429703, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.078136682510376, "global_step": 429704, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1708219051361084, "global_step": 429705, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0647623538970947, "global_step": 429706, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.072572946548462, "global_step": 429707, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1463775634765625, "global_step": 429708, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1449079513549805, "global_step": 429709, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.048506259918213, "global_step": 429710, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.033674955368042, "global_step": 429711, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1277663707733154, "global_step": 429712, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.078568935394287, "global_step": 429713, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0442068576812744, "global_step": 429714, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.109285354614258, "global_step": 429715, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0672852993011475, "global_step": 429716, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0602035522460938, "global_step": 429717, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0459864139556885, "global_step": 429718, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1421151161193848, "global_step": 429719, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.064481496810913, "global_step": 429720, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0398075580596924, "global_step": 429721, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.057803153991699, "global_step": 429722, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.040942668914795, "global_step": 429723, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.938362717628479, "global_step": 429724, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0519702434539795, "global_step": 429725, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0930020809173584, "global_step": 429726, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1062254905700684, "global_step": 429727, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0749053955078125, "global_step": 429728, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.107731342315674, "global_step": 429729, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.076697587966919, "global_step": 429730, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.164868116378784, "global_step": 429731, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0738303661346436, "global_step": 429732, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.110809326171875, "global_step": 429733, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.085747718811035, "global_step": 429734, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.086010694503784, "global_step": 429735, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.118100166320801, "global_step": 429736, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9918328523635864, "global_step": 429737, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0357778072357178, "global_step": 429738, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.088639736175537, "global_step": 429739, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0203168392181396, "global_step": 429740, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0378975868225098, "global_step": 429741, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9874118566513062, "global_step": 429742, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.040952205657959, "global_step": 429743, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.075835943222046, "global_step": 429744, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.087372064590454, "global_step": 429745, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.083298921585083, "global_step": 429746, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.018043041229248, "global_step": 429747, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.137416124343872, "global_step": 429748, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0739235877990723, "global_step": 429749, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.055877208709717, "global_step": 429750, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0990164279937744, "global_step": 429751, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.167109727859497, "global_step": 429752, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.08109188079834, "global_step": 429753, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1390576362609863, "global_step": 429754, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0430281162261963, "global_step": 429755, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0179364681243896, "global_step": 429756, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.2060153484344482, "global_step": 429757, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.021821975708008, "global_step": 429758, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0703980922698975, "global_step": 429759, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.043349504470825, "global_step": 429760, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1678240299224854, "global_step": 429761, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.093790054321289, "global_step": 429762, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.2152037620544434, "global_step": 429763, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0476996898651123, "global_step": 429764, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9725853204727173, "global_step": 429765, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.127401113510132, "global_step": 429766, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.046900749206543, "global_step": 429767, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1688029766082764, "global_step": 429768, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0189106464385986, "global_step": 429769, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0508694648742676, "global_step": 429770, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1108462810516357, "global_step": 429771, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0993058681488037, "global_step": 429772, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1291565895080566, "global_step": 429773, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.06862735748291, "global_step": 429774, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.957641363143921, "global_step": 429775, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9887877702713013, "global_step": 429776, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1433193683624268, "global_step": 429777, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9751790761947632, "global_step": 429778, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1005640029907227, "global_step": 429779, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.069200038909912, "global_step": 429780, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0611929893493652, "global_step": 429781, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.034264087677002, "global_step": 429782, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.086918354034424, "global_step": 429783, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.00519061088562, "global_step": 429784, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.031613349914551, "global_step": 429785, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0368311405181885, "global_step": 429786, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.142540693283081, "global_step": 429787, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.097916603088379, "global_step": 429788, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.149920701980591, "global_step": 429789, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0991225242614746, "global_step": 429790, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0970964431762695, "global_step": 429791, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1486289501190186, "global_step": 429792, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0456600189208984, "global_step": 429793, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.069260597229004, "global_step": 429794, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0590341091156006, "global_step": 429795, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.066509485244751, "global_step": 429796, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0183756351470947, "global_step": 429797, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1535472869873047, "global_step": 429798, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.090846538543701, "global_step": 429799, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0295510292053223, "global_step": 429800, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.056136131286621, "global_step": 429801, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.129230260848999, "global_step": 429802, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.148393154144287, "global_step": 429803, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0821144580841064, "global_step": 429804, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0945281982421875, "global_step": 429805, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.153066396713257, "global_step": 429806, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0810468196868896, "global_step": 429807, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.127420663833618, "global_step": 429808, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1012022495269775, "global_step": 429809, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.112360715866089, "global_step": 429810, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0276050567626953, "global_step": 429811, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0382440090179443, "global_step": 429812, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0951662063598633, "global_step": 429813, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9850547313690186, "global_step": 429814, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.06141996383667, "global_step": 429815, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.15694260597229, "global_step": 429816, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1765666007995605, "global_step": 429817, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.082611322402954, "global_step": 429818, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.144331455230713, "global_step": 429819, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9758564233779907, "global_step": 429820, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1689553260803223, "global_step": 429821, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.143026113510132, "global_step": 429822, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0382814407348633, "global_step": 429823, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.136121988296509, "global_step": 429824, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.179736614227295, "global_step": 429825, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1064882278442383, "global_step": 429826, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0810019969940186, "global_step": 429827, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0671679973602295, "global_step": 429828, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.070068120956421, "global_step": 429829, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0776071548461914, "global_step": 429830, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0134668350219727, "global_step": 429831, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0985302925109863, "global_step": 429832, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1250181198120117, "global_step": 429833, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.97175133228302, "global_step": 429834, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9962501525878906, "global_step": 429835, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.052570104598999, "global_step": 429836, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.021307945251465, "global_step": 429837, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0687763690948486, "global_step": 429838, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1423726081848145, "global_step": 429839, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.013606309890747, "global_step": 429840, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1468982696533203, "global_step": 429841, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.02862811088562, "global_step": 429842, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0498173236846924, "global_step": 429843, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.023794174194336, "global_step": 429844, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0197410583496094, "global_step": 429845, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0743305683135986, "global_step": 429846, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0612714290618896, "global_step": 429847, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1241495609283447, "global_step": 429848, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0190629959106445, "global_step": 429849, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.123901605606079, "global_step": 429850, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.058598756790161, "global_step": 429851, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.087860107421875, "global_step": 429852, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0961194038391113, "global_step": 429853, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.01625394821167, "global_step": 429854, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.086271286010742, "global_step": 429855, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.071484088897705, "global_step": 429856, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0637552738189697, "global_step": 429857, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0073325634002686, "global_step": 429858, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.06563663482666, "global_step": 429859, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1514172554016113, "global_step": 429860, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.026618242263794, "global_step": 429861, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.115035057067871, "global_step": 429862, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0932328701019287, "global_step": 429863, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.103884696960449, "global_step": 429864, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.021106004714966, "global_step": 429865, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0988006591796875, "global_step": 429866, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.110738515853882, "global_step": 429867, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.024601936340332, "global_step": 429868, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0595364570617676, "global_step": 429869, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.042952299118042, "global_step": 429870, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.072570562362671, "global_step": 429871, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1264469623565674, "global_step": 429872, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1394758224487305, "global_step": 429873, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0985865592956543, "global_step": 429874, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1049885749816895, "global_step": 429875, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.176051378250122, "global_step": 429876, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.2322256565093994, "global_step": 429877, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.121264696121216, "global_step": 429878, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0369997024536133, "global_step": 429879, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9540815353393555, "global_step": 429880, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0341222286224365, "global_step": 429881, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0895440578460693, "global_step": 429882, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0916481018066406, "global_step": 429883, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0809948444366455, "global_step": 429884, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0418906211853027, "global_step": 429885, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1110730171203613, "global_step": 429886, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0300261974334717, "global_step": 429887, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.064864158630371, "global_step": 429888, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.138411045074463, "global_step": 429889, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1405301094055176, "global_step": 429890, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.023752450942993, "global_step": 429891, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.070739269256592, "global_step": 429892, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0763027667999268, "global_step": 429893, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.102888584136963, "global_step": 429894, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.086585760116577, "global_step": 429895, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0586400032043457, "global_step": 429896, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.132082462310791, "global_step": 429897, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0662379264831543, "global_step": 429898, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.067112445831299, "global_step": 429899, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9639430046081543, "global_step": 429900, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.145387649536133, "global_step": 429901, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1029229164123535, "global_step": 429902, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0706064701080322, "global_step": 429903, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.074204921722412, "global_step": 429904, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.049149513244629, "global_step": 429905, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0904388427734375, "global_step": 429906, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0823652744293213, "global_step": 429907, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0476341247558594, "global_step": 429908, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0317435264587402, "global_step": 429909, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.042052984237671, "global_step": 429910, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.105325937271118, "global_step": 429911, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.195077419281006, "global_step": 429912, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.06567120552063, "global_step": 429913, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0795137882232666, "global_step": 429914, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1742515563964844, "global_step": 429915, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1296679973602295, "global_step": 429916, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0582518577575684, "global_step": 429917, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.027832508087158, "global_step": 429918, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.128723382949829, "global_step": 429919, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0570144653320312, "global_step": 429920, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1219382286071777, "global_step": 429921, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.086883783340454, "global_step": 429922, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9927048683166504, "global_step": 429923, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0784733295440674, "global_step": 429924, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0961813926696777, "global_step": 429925, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.08878231048584, "global_step": 429926, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0702474117279053, "global_step": 429927, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.137141466140747, "global_step": 429928, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1088528633117676, "global_step": 429929, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0540857315063477, "global_step": 429930, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9874986410140991, "global_step": 429931, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0780014991760254, "global_step": 429932, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.081510066986084, "global_step": 429933, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.073291540145874, "global_step": 429934, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1702215671539307, "global_step": 429935, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.014194965362549, "global_step": 429936, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.106424570083618, "global_step": 429937, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.070607900619507, "global_step": 429938, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0851681232452393, "global_step": 429939, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9939146041870117, "global_step": 429940, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.078850746154785, "global_step": 429941, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.083287239074707, "global_step": 429942, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.074453353881836, "global_step": 429943, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0705795288085938, "global_step": 429944, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1219050884246826, "global_step": 429945, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.027235507965088, "global_step": 429946, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.103163003921509, "global_step": 429947, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.017141580581665, "global_step": 429948, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0446112155914307, "global_step": 429949, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0421018600463867, "global_step": 429950, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1556499004364014, "global_step": 429951, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0938894748687744, "global_step": 429952, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0562798976898193, "global_step": 429953, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1127426624298096, "global_step": 429954, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.090399980545044, "global_step": 429955, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1483395099639893, "global_step": 429956, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.095637559890747, "global_step": 429957, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9630759954452515, "global_step": 429958, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1034278869628906, "global_step": 429959, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1186232566833496, "global_step": 429960, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.079314708709717, "global_step": 429961, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0223498344421387, "global_step": 429962, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.093154191970825, "global_step": 429963, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1269173622131348, "global_step": 429964, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0292842388153076, "global_step": 429965, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0470573902130127, "global_step": 429966, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.125944137573242, "global_step": 429967, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.178105115890503, "global_step": 429968, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.131021022796631, "global_step": 429969, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0425572395324707, "global_step": 429970, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1572458744049072, "global_step": 429971, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9797515869140625, "global_step": 429972, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.088650941848755, "global_step": 429973, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.099315881729126, "global_step": 429974, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.054826021194458, "global_step": 429975, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.035762071609497, "global_step": 429976, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1225204467773438, "global_step": 429977, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.103632688522339, "global_step": 429978, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0479421615600586, "global_step": 429979, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1034233570098877, "global_step": 429980, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0493266582489014, "global_step": 429981, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.036616802215576, "global_step": 429982, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.073669672012329, "global_step": 429983, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.071716547012329, "global_step": 429984, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0535216331481934, "global_step": 429985, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.093670129776001, "global_step": 429986, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.017557144165039, "global_step": 429987, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.163393497467041, "global_step": 429988, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.032642126083374, "global_step": 429989, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0153684616088867, "global_step": 429990, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.137367010116577, "global_step": 429991, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.140126943588257, "global_step": 429992, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.092933416366577, "global_step": 429993, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1530942916870117, "global_step": 429994, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.062770366668701, "global_step": 429995, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1168630123138428, "global_step": 429996, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0502045154571533, "global_step": 429997, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0004711151123047, "global_step": 429998, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0510599613189697, "global_step": 429999, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.033186674118042, "global_step": 430000, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0935730934143066, "global_step": 430001, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0979137420654297, "global_step": 430002, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0910892486572266, "global_step": 430003, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.144303798675537, "global_step": 430004, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.094726324081421, "global_step": 430005, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.105377674102783, "global_step": 430006, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0611021518707275, "global_step": 430007, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0863351821899414, "global_step": 430008, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.026984453201294, "global_step": 430009, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.133591651916504, "global_step": 430010, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.140815496444702, "global_step": 430011, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0382001399993896, "global_step": 430012, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0396554470062256, "global_step": 430013, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.094388246536255, "global_step": 430014, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.02052903175354, "global_step": 430015, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.019160747528076, "global_step": 430016, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.061570644378662, "global_step": 430017, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.112001419067383, "global_step": 430018, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0759708881378174, "global_step": 430019, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0048842430114746, "global_step": 430020, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0546982288360596, "global_step": 430021, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0762643814086914, "global_step": 430022, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.039843797683716, "global_step": 430023, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0900981426239014, "global_step": 430024, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.120903253555298, "global_step": 430025, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0391876697540283, "global_step": 430026, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9744627475738525, "global_step": 430027, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.106032133102417, "global_step": 430028, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.055924892425537, "global_step": 430029, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.043773889541626, "global_step": 430030, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.057849645614624, "global_step": 430031, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.073683500289917, "global_step": 430032, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0708584785461426, "global_step": 430033, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0860376358032227, "global_step": 430034, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0328307151794434, "global_step": 430035, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.020099639892578, "global_step": 430036, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0599215030670166, "global_step": 430037, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.2510769367218018, "global_step": 430038, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0848138332366943, "global_step": 430039, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1489157676696777, "global_step": 430040, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0820858478546143, "global_step": 430041, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.129760265350342, "global_step": 430042, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.088848352432251, "global_step": 430043, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0754237174987793, "global_step": 430044, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0758612155914307, "global_step": 430045, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0854547023773193, "global_step": 430046, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1227171421051025, "global_step": 430047, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0512871742248535, "global_step": 430048, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1053085327148438, "global_step": 430049, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.076382637023926, "global_step": 430050, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0460665225982666, "global_step": 430051, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1205217838287354, "global_step": 430052, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0791256427764893, "global_step": 430053, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0897934436798096, "global_step": 430054, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.199449062347412, "global_step": 430055, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1496036052703857, "global_step": 430056, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1098856925964355, "global_step": 430057, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1415274143218994, "global_step": 430058, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0993752479553223, "global_step": 430059, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1399192810058594, "global_step": 430060, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0922319889068604, "global_step": 430061, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0544586181640625, "global_step": 430062, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9949536323547363, "global_step": 430063, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0578596591949463, "global_step": 430064, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.189343214035034, "global_step": 430065, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.181542158126831, "global_step": 430066, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0437166690826416, "global_step": 430067, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0498502254486084, "global_step": 430068, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0804648399353027, "global_step": 430069, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1421024799346924, "global_step": 430070, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.10325026512146, "global_step": 430071, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9891202449798584, "global_step": 430072, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0418217182159424, "global_step": 430073, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.2052736282348633, "global_step": 430074, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.035637855529785, "global_step": 430075, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1310136318206787, "global_step": 430076, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0487561225891113, "global_step": 430077, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1413474082946777, "global_step": 430078, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.00999116897583, "global_step": 430079, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1227481365203857, "global_step": 430080, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0784034729003906, "global_step": 430081, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.139080762863159, "global_step": 430082, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0873923301696777, "global_step": 430083, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.011918544769287, "global_step": 430084, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.2005159854888916, "global_step": 430085, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1840925216674805, "global_step": 430086, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.110363483428955, "global_step": 430087, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0669543743133545, "global_step": 430088, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1411917209625244, "global_step": 430089, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0979554653167725, "global_step": 430090, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.02838397026062, "global_step": 430091, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.086717367172241, "global_step": 430092, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.08158278465271, "global_step": 430093, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.118915557861328, "global_step": 430094, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1418328285217285, "global_step": 430095, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1081137657165527, "global_step": 430096, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.013300657272339, "global_step": 430097, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.15143084526062, "global_step": 430098, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.130960464477539, "global_step": 430099, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.146744966506958, "global_step": 430100, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1092991828918457, "global_step": 430101, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0824053287506104, "global_step": 430102, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.07613468170166, "global_step": 430103, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.094726085662842, "global_step": 430104, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.050812005996704, "global_step": 430105, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9647810459136963, "global_step": 430106, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0726890563964844, "global_step": 430107, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0769691467285156, "global_step": 430108, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1358494758605957, "global_step": 430109, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.063354253768921, "global_step": 430110, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.058413028717041, "global_step": 430111, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1395797729492188, "global_step": 430112, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9846833944320679, "global_step": 430113, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9877748489379883, "global_step": 430114, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.11004376411438, "global_step": 430115, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0661745071411133, "global_step": 430116, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.174227237701416, "global_step": 430117, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.08849835395813, "global_step": 430118, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.112590789794922, "global_step": 430119, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0145246982574463, "global_step": 430120, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0857856273651123, "global_step": 430121, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.192143201828003, "global_step": 430122, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1387150287628174, "global_step": 430123, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1496729850769043, "global_step": 430124, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.042677879333496, "global_step": 430125, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.04962158203125, "global_step": 430126, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.085106611251831, "global_step": 430127, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.998112678527832, "global_step": 430128, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0961413383483887, "global_step": 430129, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1426074504852295, "global_step": 430130, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9910963773727417, "global_step": 430131, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.071643829345703, "global_step": 430132, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1043338775634766, "global_step": 430133, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1614015102386475, "global_step": 430134, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.109649896621704, "global_step": 430135, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0818004608154297, "global_step": 430136, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1158998012542725, "global_step": 430137, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0149052143096924, "global_step": 430138, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1024513244628906, "global_step": 430139, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1697163581848145, "global_step": 430140, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0547351837158203, "global_step": 430141, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.096125364303589, "global_step": 430142, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1190743446350098, "global_step": 430143, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0872979164123535, "global_step": 430144, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0642144680023193, "global_step": 430145, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.066415309906006, "global_step": 430146, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.079820156097412, "global_step": 430147, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1497766971588135, "global_step": 430148, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0769386291503906, "global_step": 430149, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.123887777328491, "global_step": 430150, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.107238292694092, "global_step": 430151, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.111752986907959, "global_step": 430152, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0168330669403076, "global_step": 430153, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1401302814483643, "global_step": 430154, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.081645965576172, "global_step": 430155, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0219473838806152, "global_step": 430156, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.100728988647461, "global_step": 430157, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.037626266479492, "global_step": 430158, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.078131675720215, "global_step": 430159, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.062959671020508, "global_step": 430160, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.114002227783203, "global_step": 430161, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1088438034057617, "global_step": 430162, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1241695880889893, "global_step": 430163, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.038266658782959, "global_step": 430164, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.077129602432251, "global_step": 430165, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.00018048286438, "global_step": 430166, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0652410984039307, "global_step": 430167, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0119752883911133, "global_step": 430168, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.123840808868408, "global_step": 430169, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9767258167266846, "global_step": 430170, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0060272216796875, "global_step": 430171, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0949647426605225, "global_step": 430172, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1869046688079834, "global_step": 430173, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0318565368652344, "global_step": 430174, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.059720039367676, "global_step": 430175, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0581469535827637, "global_step": 430176, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1070358753204346, "global_step": 430177, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1307244300842285, "global_step": 430178, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.068211078643799, "global_step": 430179, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0265979766845703, "global_step": 430180, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1743853092193604, "global_step": 430181, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.107383966445923, "global_step": 430182, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0542354583740234, "global_step": 430183, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.174561023712158, "global_step": 430184, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.036635637283325, "global_step": 430185, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1037542819976807, "global_step": 430186, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1309702396392822, "global_step": 430187, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0712075233459473, "global_step": 430188, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0112416744232178, "global_step": 430189, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0559637546539307, "global_step": 430190, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1584460735321045, "global_step": 430191, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0126616954803467, "global_step": 430192, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0635104179382324, "global_step": 430193, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.122819662094116, "global_step": 430194, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.130681276321411, "global_step": 430195, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.079012155532837, "global_step": 430196, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0460991859436035, "global_step": 430197, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0657830238342285, "global_step": 430198, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1011085510253906, "global_step": 430199, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0616865158081055, "global_step": 430200, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.166965961456299, "global_step": 430201, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.117152690887451, "global_step": 430202, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.09035325050354, "global_step": 430203, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0851285457611084, "global_step": 430204, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9554837942123413, "global_step": 430205, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.026634693145752, "global_step": 430206, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0111093521118164, "global_step": 430207, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0593414306640625, "global_step": 430208, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.114502429962158, "global_step": 430209, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0154409408569336, "global_step": 430210, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1670069694519043, "global_step": 430211, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1632814407348633, "global_step": 430212, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0197885036468506, "global_step": 430213, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0709073543548584, "global_step": 430214, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.009998083114624, "global_step": 430215, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.100484848022461, "global_step": 430216, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.013673782348633, "global_step": 430217, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1124625205993652, "global_step": 430218, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.055858612060547, "global_step": 430219, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.068634033203125, "global_step": 430220, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.053476572036743, "global_step": 430221, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0721380710601807, "global_step": 430222, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.110088586807251, "global_step": 430223, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0131382942199707, "global_step": 430224, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.126315116882324, "global_step": 430225, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0466654300689697, "global_step": 430226, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.115628242492676, "global_step": 430227, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1160953044891357, "global_step": 430228, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0873312950134277, "global_step": 430229, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.118872880935669, "global_step": 430230, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.052598714828491, "global_step": 430231, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1541366577148438, "global_step": 430232, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.003710985183716, "global_step": 430233, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0648574829101562, "global_step": 430234, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.074955463409424, "global_step": 430235, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1193015575408936, "global_step": 430236, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0579428672790527, "global_step": 430237, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1587841510772705, "global_step": 430238, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0563173294067383, "global_step": 430239, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0854387283325195, "global_step": 430240, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1568455696105957, "global_step": 430241, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1433284282684326, "global_step": 430242, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.071949005126953, "global_step": 430243, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0528247356414795, "global_step": 430244, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1071784496307373, "global_step": 430245, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.054642915725708, "global_step": 430246, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1168811321258545, "global_step": 430247, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0002787113189697, "global_step": 430248, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0781426429748535, "global_step": 430249, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.115464210510254, "global_step": 430250, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.144897937774658, "global_step": 430251, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0541577339172363, "global_step": 430252, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0799636840820312, "global_step": 430253, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1044347286224365, "global_step": 430254, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1419320106506348, "global_step": 430255, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.030367136001587, "global_step": 430256, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0435564517974854, "global_step": 430257, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.097898483276367, "global_step": 430258, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0690197944641113, "global_step": 430259, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.098360538482666, "global_step": 430260, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0361454486846924, "global_step": 430261, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.059027910232544, "global_step": 430262, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.023599863052368, "global_step": 430263, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0947210788726807, "global_step": 430264, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.119063138961792, "global_step": 430265, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.136120080947876, "global_step": 430266, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0916457176208496, "global_step": 430267, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.07977032661438, "global_step": 430268, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0352799892425537, "global_step": 430269, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1056487560272217, "global_step": 430270, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.040120840072632, "global_step": 430271, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0771563053131104, "global_step": 430272, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.081490993499756, "global_step": 430273, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0803751945495605, "global_step": 430274, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.2384045124053955, "global_step": 430275, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0517990589141846, "global_step": 430276, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.081002712249756, "global_step": 430277, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.070154905319214, "global_step": 430278, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1053500175476074, "global_step": 430279, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.125302314758301, "global_step": 430280, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0035290718078613, "global_step": 430281, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1355719566345215, "global_step": 430282, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1387393474578857, "global_step": 430283, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0403003692626953, "global_step": 430284, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0839478969573975, "global_step": 430285, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0203845500946045, "global_step": 430286, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1253857612609863, "global_step": 430287, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0949854850769043, "global_step": 430288, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1421549320220947, "global_step": 430289, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.16261625289917, "global_step": 430290, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.147235870361328, "global_step": 430291, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0841245651245117, "global_step": 430292, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.076788902282715, "global_step": 430293, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.171018123626709, "global_step": 430294, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.101604461669922, "global_step": 430295, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1600189208984375, "global_step": 430296, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.083489179611206, "global_step": 430297, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0826351642608643, "global_step": 430298, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.096665859222412, "global_step": 430299, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0940232276916504, "global_step": 430300, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.05146861076355, "global_step": 430301, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0520238876342773, "global_step": 430302, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.009009599685669, "global_step": 430303, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.035449504852295, "global_step": 430304, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0908639430999756, "global_step": 430305, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1394970417022705, "global_step": 430306, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0372703075408936, "global_step": 430307, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0844593048095703, "global_step": 430308, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.072122097015381, "global_step": 430309, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.119290590286255, "global_step": 430310, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0478029251098633, "global_step": 430311, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.115328550338745, "global_step": 430312, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.050084114074707, "global_step": 430313, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.150447130203247, "global_step": 430314, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0799484252929688, "global_step": 430315, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1429603099823, "global_step": 430316, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0957090854644775, "global_step": 430317, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0353949069976807, "global_step": 430318, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1039912700653076, "global_step": 430319, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.10146164894104, "global_step": 430320, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1651246547698975, "global_step": 430321, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.034933567047119, "global_step": 430322, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9190086126327515, "global_step": 430323, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0418009757995605, "global_step": 430324, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9854135513305664, "global_step": 430325, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.076849937438965, "global_step": 430326, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1486198902130127, "global_step": 430327, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1365468502044678, "global_step": 430328, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1086039543151855, "global_step": 430329, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.131040096282959, "global_step": 430330, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0413272380828857, "global_step": 430331, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0393710136413574, "global_step": 430332, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.116560935974121, "global_step": 430333, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0676424503326416, "global_step": 430334, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.081644058227539, "global_step": 430335, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.111443042755127, "global_step": 430336, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.117016315460205, "global_step": 430337, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.087338924407959, "global_step": 430338, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.059145212173462, "global_step": 430339, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1493678092956543, "global_step": 430340, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.159972667694092, "global_step": 430341, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.003934860229492, "global_step": 430342, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.081845760345459, "global_step": 430343, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.054008960723877, "global_step": 430344, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.034432888031006, "global_step": 430345, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1224677562713623, "global_step": 430346, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.2397735118865967, "global_step": 430347, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.139146089553833, "global_step": 430348, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.067925214767456, "global_step": 430349, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1261768341064453, "global_step": 430350, "epoch": 793, "lr": 5e-05}
{"train_loss": 1.9756108522415161, "global_step": 430351, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.082260847091675, "global_step": 430352, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1287343502044678, "global_step": 430353, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1308672428131104, "global_step": 430354, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1265110969543457, "global_step": 430355, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.07865047454834, "global_step": 430356, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0459141731262207, "global_step": 430357, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.089909076690674, "global_step": 430358, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0978360176086426, "global_step": 430359, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.11171293258667, "global_step": 430360, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.031270742416382, "global_step": 430361, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0240087509155273, "global_step": 430362, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.1278069019317627, "global_step": 430363, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0154831409454346, "global_step": 430364, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.065964937210083, "global_step": 430365, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0751137733459473, "global_step": 430366, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0762441158294678, "global_step": 430367, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0810694694519043, "global_step": 430368, "epoch": 793, "lr": 5e-05}
{"train_loss": 2.0381972789764404, "global_step": 430369, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0747499465942383, "global_step": 430370, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1087825298309326, "global_step": 430371, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0813448429107666, "global_step": 430372, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0551276206970215, "global_step": 430373, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0165956020355225, "global_step": 430374, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.07810378074646, "global_step": 430375, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9873813390731812, "global_step": 430376, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.039478302001953, "global_step": 430377, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0283010005950928, "global_step": 430378, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.106818675994873, "global_step": 430379, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.073617935180664, "global_step": 430380, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0588955879211426, "global_step": 430381, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.063382387161255, "global_step": 430382, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0862648487091064, "global_step": 430383, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.098397731781006, "global_step": 430384, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0565881729125977, "global_step": 430385, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0266098976135254, "global_step": 430386, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.118436813354492, "global_step": 430387, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.048980474472046, "global_step": 430388, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0757362842559814, "global_step": 430389, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.129014015197754, "global_step": 430390, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.083400249481201, "global_step": 430391, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.072355270385742, "global_step": 430392, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.008969783782959, "global_step": 430393, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.027243137359619, "global_step": 430394, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0402262210845947, "global_step": 430395, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.057435989379883, "global_step": 430396, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9996066093444824, "global_step": 430397, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0791773796081543, "global_step": 430398, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.084470748901367, "global_step": 430399, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.018658399581909, "global_step": 430400, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.072854995727539, "global_step": 430401, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.110093832015991, "global_step": 430402, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.099745035171509, "global_step": 430403, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0432562828063965, "global_step": 430404, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1171932220458984, "global_step": 430405, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0735089778900146, "global_step": 430406, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0853283405303955, "global_step": 430407, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.19809627532959, "global_step": 430408, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.128848075866699, "global_step": 430409, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0593483448028564, "global_step": 430410, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1810081005096436, "global_step": 430411, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0482757091522217, "global_step": 430412, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.027832269668579, "global_step": 430413, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.113356113433838, "global_step": 430414, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.142369270324707, "global_step": 430415, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9944431781768799, "global_step": 430416, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9847477674484253, "global_step": 430417, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.045114517211914, "global_step": 430418, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0502209663391113, "global_step": 430419, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.983186960220337, "global_step": 430420, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0778281688690186, "global_step": 430421, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0601842403411865, "global_step": 430422, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0067355632781982, "global_step": 430423, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0899717807769775, "global_step": 430424, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1143641471862793, "global_step": 430425, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0165348052978516, "global_step": 430426, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.126387357711792, "global_step": 430427, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1060357093811035, "global_step": 430428, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0764660835266113, "global_step": 430429, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0203027725219727, "global_step": 430430, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9970359802246094, "global_step": 430431, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.087158441543579, "global_step": 430432, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.072385311126709, "global_step": 430433, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.026951313018799, "global_step": 430434, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.076594829559326, "global_step": 430435, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0949177742004395, "global_step": 430436, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.10844349861145, "global_step": 430437, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.2296628952026367, "global_step": 430438, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9878648519515991, "global_step": 430439, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.090754747390747, "global_step": 430440, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.089031457901001, "global_step": 430441, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1051652431488037, "global_step": 430442, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0563621520996094, "global_step": 430443, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0629801750183105, "global_step": 430444, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.071948289871216, "global_step": 430445, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.052117109298706, "global_step": 430446, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.13519287109375, "global_step": 430447, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0819432735443115, "global_step": 430448, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0059399604797363, "global_step": 430449, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0743889808654785, "global_step": 430450, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1828360557556152, "global_step": 430451, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0193371772766113, "global_step": 430452, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.025390148162842, "global_step": 430453, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.057509660720825, "global_step": 430454, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1167495250701904, "global_step": 430455, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0981287956237793, "global_step": 430456, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0483832359313965, "global_step": 430457, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.098651170730591, "global_step": 430458, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.011580228805542, "global_step": 430459, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.028059482574463, "global_step": 430460, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.262068033218384, "global_step": 430461, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.084104537963867, "global_step": 430462, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0018255710601807, "global_step": 430463, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0662667751312256, "global_step": 430464, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1466848850250244, "global_step": 430465, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1258554458618164, "global_step": 430466, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0386176109313965, "global_step": 430467, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1152379512786865, "global_step": 430468, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.034440040588379, "global_step": 430469, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.998364806175232, "global_step": 430470, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.105280876159668, "global_step": 430471, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.058781623840332, "global_step": 430472, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1102406978607178, "global_step": 430473, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.04410457611084, "global_step": 430474, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0887367725372314, "global_step": 430475, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0590717792510986, "global_step": 430476, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.061849355697632, "global_step": 430477, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.095000743865967, "global_step": 430478, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0516982078552246, "global_step": 430479, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.095787763595581, "global_step": 430480, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9508377313613892, "global_step": 430481, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.05957293510437, "global_step": 430482, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.076256513595581, "global_step": 430483, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1166388988494873, "global_step": 430484, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0719287395477295, "global_step": 430485, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.024974822998047, "global_step": 430486, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1206769943237305, "global_step": 430487, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.045488119125366, "global_step": 430488, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0725653171539307, "global_step": 430489, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.118588924407959, "global_step": 430490, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.125236988067627, "global_step": 430491, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.054185628890991, "global_step": 430492, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0325803756713867, "global_step": 430493, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0510966777801514, "global_step": 430494, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.06762957572937, "global_step": 430495, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0201210975646973, "global_step": 430496, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0909838676452637, "global_step": 430497, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0462608337402344, "global_step": 430498, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9763838052749634, "global_step": 430499, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.092005491256714, "global_step": 430500, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0608272552490234, "global_step": 430501, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.102186441421509, "global_step": 430502, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.022047996520996, "global_step": 430503, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.120145559310913, "global_step": 430504, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.138423204421997, "global_step": 430505, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0624430179595947, "global_step": 430506, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0865116119384766, "global_step": 430507, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.085251569747925, "global_step": 430508, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0308237075805664, "global_step": 430509, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.105729103088379, "global_step": 430510, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0195798873901367, "global_step": 430511, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0093164443969727, "global_step": 430512, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.074158191680908, "global_step": 430513, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.11189866065979, "global_step": 430514, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.027164936065674, "global_step": 430515, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0374133586883545, "global_step": 430516, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9829047918319702, "global_step": 430517, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9540812969207764, "global_step": 430518, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.101583957672119, "global_step": 430519, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0039145946502686, "global_step": 430520, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.066164255142212, "global_step": 430521, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.003361701965332, "global_step": 430522, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.115037202835083, "global_step": 430523, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0108184814453125, "global_step": 430524, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.066356897354126, "global_step": 430525, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.023174285888672, "global_step": 430526, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0682966709136963, "global_step": 430527, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0516176223754883, "global_step": 430528, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0605123043060303, "global_step": 430529, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.068507432937622, "global_step": 430530, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0094380378723145, "global_step": 430531, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0978403091430664, "global_step": 430532, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.082751512527466, "global_step": 430533, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.045429229736328, "global_step": 430534, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.135566473007202, "global_step": 430535, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0571465492248535, "global_step": 430536, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9918134212493896, "global_step": 430537, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0546813011169434, "global_step": 430538, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.104339599609375, "global_step": 430539, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.050689220428467, "global_step": 430540, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.090549945831299, "global_step": 430541, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.06964373588562, "global_step": 430542, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.100363254547119, "global_step": 430543, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0858473777770996, "global_step": 430544, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.08083438873291, "global_step": 430545, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1176044940948486, "global_step": 430546, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.057800531387329, "global_step": 430547, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.091062307357788, "global_step": 430548, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.17476224899292, "global_step": 430549, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.069253444671631, "global_step": 430550, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0603768825531006, "global_step": 430551, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0500621795654297, "global_step": 430552, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0632829666137695, "global_step": 430553, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0656421184539795, "global_step": 430554, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.072342872619629, "global_step": 430555, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.090549945831299, "global_step": 430556, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.11368465423584, "global_step": 430557, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0823378562927246, "global_step": 430558, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.106208086013794, "global_step": 430559, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.117276430130005, "global_step": 430560, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0369021892547607, "global_step": 430561, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.135117292404175, "global_step": 430562, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0731616020202637, "global_step": 430563, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.058480978012085, "global_step": 430564, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0905280113220215, "global_step": 430565, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0312139987945557, "global_step": 430566, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.030259132385254, "global_step": 430567, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.015212059020996, "global_step": 430568, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9631332159042358, "global_step": 430569, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0103557109832764, "global_step": 430570, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1927995681762695, "global_step": 430571, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.081176280975342, "global_step": 430572, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.042755365371704, "global_step": 430573, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1303021907806396, "global_step": 430574, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0500519275665283, "global_step": 430575, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1127066612243652, "global_step": 430576, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.110719919204712, "global_step": 430577, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0353798866271973, "global_step": 430578, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.128394842147827, "global_step": 430579, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.09952449798584, "global_step": 430580, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0633702278137207, "global_step": 430581, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.09285044670105, "global_step": 430582, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0593204498291016, "global_step": 430583, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.032285451889038, "global_step": 430584, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.139789342880249, "global_step": 430585, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.155081272125244, "global_step": 430586, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.130504846572876, "global_step": 430587, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0494349002838135, "global_step": 430588, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1477596759796143, "global_step": 430589, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.071734666824341, "global_step": 430590, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.111578941345215, "global_step": 430591, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1048049926757812, "global_step": 430592, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0927834510803223, "global_step": 430593, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.117619276046753, "global_step": 430594, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.099653959274292, "global_step": 430595, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0405094623565674, "global_step": 430596, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.016615867614746, "global_step": 430597, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1178014278411865, "global_step": 430598, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0057358741760254, "global_step": 430599, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1091835498809814, "global_step": 430600, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0947089195251465, "global_step": 430601, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.015557289123535, "global_step": 430602, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.044604778289795, "global_step": 430603, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0472190380096436, "global_step": 430604, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0623393058776855, "global_step": 430605, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0725085735321045, "global_step": 430606, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0857832431793213, "global_step": 430607, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0878944396972656, "global_step": 430608, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0593180656433105, "global_step": 430609, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.066525459289551, "global_step": 430610, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0468008518218994, "global_step": 430611, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.059152126312256, "global_step": 430612, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.118777275085449, "global_step": 430613, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0283098220825195, "global_step": 430614, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.125746726989746, "global_step": 430615, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.032294273376465, "global_step": 430616, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1297314167022705, "global_step": 430617, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.082704782485962, "global_step": 430618, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0420656204223633, "global_step": 430619, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0532610416412354, "global_step": 430620, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0374317169189453, "global_step": 430621, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.162572145462036, "global_step": 430622, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0521390438079834, "global_step": 430623, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0898280143737793, "global_step": 430624, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1061315536499023, "global_step": 430625, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9684489965438843, "global_step": 430626, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1392693519592285, "global_step": 430627, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.063933849334717, "global_step": 430628, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.084393262863159, "global_step": 430629, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.165189266204834, "global_step": 430630, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.121875286102295, "global_step": 430631, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.113673210144043, "global_step": 430632, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.033259153366089, "global_step": 430633, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.061983346939087, "global_step": 430634, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0701210498809814, "global_step": 430635, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9857481718063354, "global_step": 430636, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1042284965515137, "global_step": 430637, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1491198539733887, "global_step": 430638, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9730019569396973, "global_step": 430639, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.029362916946411, "global_step": 430640, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0368103981018066, "global_step": 430641, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0525481700897217, "global_step": 430642, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.077160358428955, "global_step": 430643, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.082597494125366, "global_step": 430644, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1285648345947266, "global_step": 430645, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.128530740737915, "global_step": 430646, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1189143657684326, "global_step": 430647, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1065316200256348, "global_step": 430648, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0287768840789795, "global_step": 430649, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0689644813537598, "global_step": 430650, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0068788528442383, "global_step": 430651, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.133509874343872, "global_step": 430652, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.141467571258545, "global_step": 430653, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1748647689819336, "global_step": 430654, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.099367141723633, "global_step": 430655, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.050262451171875, "global_step": 430656, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9827167987823486, "global_step": 430657, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.131971836090088, "global_step": 430658, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.051939010620117, "global_step": 430659, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1183547973632812, "global_step": 430660, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.064122200012207, "global_step": 430661, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9411799907684326, "global_step": 430662, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0973637104034424, "global_step": 430663, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0578784942626953, "global_step": 430664, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.020726203918457, "global_step": 430665, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.055288553237915, "global_step": 430666, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0635275840759277, "global_step": 430667, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.066582202911377, "global_step": 430668, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.086702346801758, "global_step": 430669, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.134096145629883, "global_step": 430670, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1236202716827393, "global_step": 430671, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.966770887374878, "global_step": 430672, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.106926679611206, "global_step": 430673, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.091866970062256, "global_step": 430674, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0719892978668213, "global_step": 430675, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.105750322341919, "global_step": 430676, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.072263240814209, "global_step": 430677, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9722708463668823, "global_step": 430678, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.063659429550171, "global_step": 430679, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0072624683380127, "global_step": 430680, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.10459303855896, "global_step": 430681, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.08744478225708, "global_step": 430682, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.079105854034424, "global_step": 430683, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1233012676239014, "global_step": 430684, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.08669114112854, "global_step": 430685, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0909745693206787, "global_step": 430686, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.970640778541565, "global_step": 430687, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.030059814453125, "global_step": 430688, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.014174699783325, "global_step": 430689, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0733234882354736, "global_step": 430690, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.136611223220825, "global_step": 430691, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.140556573867798, "global_step": 430692, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.131218671798706, "global_step": 430693, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.156069755554199, "global_step": 430694, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0233376026153564, "global_step": 430695, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.107994794845581, "global_step": 430696, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.087608814239502, "global_step": 430697, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.015876531600952, "global_step": 430698, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.096426248550415, "global_step": 430699, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.066190004348755, "global_step": 430700, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1252477169036865, "global_step": 430701, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0677902698516846, "global_step": 430702, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.144902229309082, "global_step": 430703, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.178178071975708, "global_step": 430704, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.031764507293701, "global_step": 430705, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0917117595672607, "global_step": 430706, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.087721347808838, "global_step": 430707, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.078359365463257, "global_step": 430708, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.075923204421997, "global_step": 430709, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.117901086807251, "global_step": 430710, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0940399169921875, "global_step": 430711, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0479073524475098, "global_step": 430712, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.037672996520996, "global_step": 430713, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1263175010681152, "global_step": 430714, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.119182825088501, "global_step": 430715, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.101020574569702, "global_step": 430716, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0516891479492188, "global_step": 430717, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0365068912506104, "global_step": 430718, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0996601581573486, "global_step": 430719, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0985732078552246, "global_step": 430720, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1747615337371826, "global_step": 430721, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.122755765914917, "global_step": 430722, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.104485034942627, "global_step": 430723, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1104443073272705, "global_step": 430724, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9991475343704224, "global_step": 430725, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0256755352020264, "global_step": 430726, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1148107051849365, "global_step": 430727, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0568346977233887, "global_step": 430728, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1084535121917725, "global_step": 430729, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.098848819732666, "global_step": 430730, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.012974262237549, "global_step": 430731, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.110872745513916, "global_step": 430732, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0563032627105713, "global_step": 430733, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0026068687438965, "global_step": 430734, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1069843769073486, "global_step": 430735, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.105969190597534, "global_step": 430736, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.066002130508423, "global_step": 430737, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0708463191986084, "global_step": 430738, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0134572982788086, "global_step": 430739, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.123215913772583, "global_step": 430740, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.040147304534912, "global_step": 430741, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.004709005355835, "global_step": 430742, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0855774879455566, "global_step": 430743, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0502543449401855, "global_step": 430744, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.038910150527954, "global_step": 430745, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0564658641815186, "global_step": 430746, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0075385570526123, "global_step": 430747, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1030325889587402, "global_step": 430748, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0855557918548584, "global_step": 430749, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.019378185272217, "global_step": 430750, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1554737091064453, "global_step": 430751, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0153796672821045, "global_step": 430752, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0104315280914307, "global_step": 430753, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0856189727783203, "global_step": 430754, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0955257415771484, "global_step": 430755, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0978095531463623, "global_step": 430756, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1169939041137695, "global_step": 430757, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.117234468460083, "global_step": 430758, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.035597801208496, "global_step": 430759, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.948491096496582, "global_step": 430760, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0831518173217773, "global_step": 430761, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0865206718444824, "global_step": 430762, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.057154893875122, "global_step": 430763, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.02134370803833, "global_step": 430764, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.146698236465454, "global_step": 430765, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0871622562408447, "global_step": 430766, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0255184173583984, "global_step": 430767, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.075305938720703, "global_step": 430768, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.06180739402771, "global_step": 430769, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.096874475479126, "global_step": 430770, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1184539794921875, "global_step": 430771, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0271553993225098, "global_step": 430772, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.039893388748169, "global_step": 430773, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0129265785217285, "global_step": 430774, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9956432580947876, "global_step": 430775, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.119344472885132, "global_step": 430776, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.061570644378662, "global_step": 430777, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.012239933013916, "global_step": 430778, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0026838779449463, "global_step": 430779, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0596132278442383, "global_step": 430780, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.039656400680542, "global_step": 430781, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0540168285369873, "global_step": 430782, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0643982887268066, "global_step": 430783, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.020833730697632, "global_step": 430784, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0073790550231934, "global_step": 430785, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1076207160949707, "global_step": 430786, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0334625244140625, "global_step": 430787, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.113511085510254, "global_step": 430788, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.106372594833374, "global_step": 430789, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0870509147644043, "global_step": 430790, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0904505252838135, "global_step": 430791, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.124791145324707, "global_step": 430792, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.08180832862854, "global_step": 430793, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0470051765441895, "global_step": 430794, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.136715888977051, "global_step": 430795, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1351168155670166, "global_step": 430796, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0684280395507812, "global_step": 430797, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1351637840270996, "global_step": 430798, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.105670690536499, "global_step": 430799, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.032302141189575, "global_step": 430800, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.134404182434082, "global_step": 430801, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1115314960479736, "global_step": 430802, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.063335418701172, "global_step": 430803, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0841152667999268, "global_step": 430804, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0502872467041016, "global_step": 430805, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0634820461273193, "global_step": 430806, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.093719244003296, "global_step": 430807, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.023838996887207, "global_step": 430808, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1114556789398193, "global_step": 430809, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1642708778381348, "global_step": 430810, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1103551387786865, "global_step": 430811, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9722844362258911, "global_step": 430812, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0744845867156982, "global_step": 430813, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0791187286376953, "global_step": 430814, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1150403022766113, "global_step": 430815, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0718936920166016, "global_step": 430816, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.096712589263916, "global_step": 430817, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0332159996032715, "global_step": 430818, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0358431339263916, "global_step": 430819, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.029080867767334, "global_step": 430820, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0689070224761963, "global_step": 430821, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.139730215072632, "global_step": 430822, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.115732431411743, "global_step": 430823, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.142030715942383, "global_step": 430824, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0361459255218506, "global_step": 430825, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0938143730163574, "global_step": 430826, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1150448322296143, "global_step": 430827, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0324509143829346, "global_step": 430828, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.055894136428833, "global_step": 430829, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.085721492767334, "global_step": 430830, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0753068923950195, "global_step": 430831, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0196244716644287, "global_step": 430832, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0829992294311523, "global_step": 430833, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9914989471435547, "global_step": 430834, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1108429431915283, "global_step": 430835, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0368430614471436, "global_step": 430836, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.095571756362915, "global_step": 430837, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0403542518615723, "global_step": 430838, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0657148361206055, "global_step": 430839, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0575954914093018, "global_step": 430840, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0874688625335693, "global_step": 430841, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.110183000564575, "global_step": 430842, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.094175338745117, "global_step": 430843, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.074327230453491, "global_step": 430844, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1325125694274902, "global_step": 430845, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1843605041503906, "global_step": 430846, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.073988676071167, "global_step": 430847, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.056724786758423, "global_step": 430848, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1358208656311035, "global_step": 430849, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1173577308654785, "global_step": 430850, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0629427433013916, "global_step": 430851, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.097445487976074, "global_step": 430852, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9502742290496826, "global_step": 430853, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1788158416748047, "global_step": 430854, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.152515172958374, "global_step": 430855, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.076551675796509, "global_step": 430856, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.023475170135498, "global_step": 430857, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1411643028259277, "global_step": 430858, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1218655109405518, "global_step": 430859, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0747265815734863, "global_step": 430860, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.125434637069702, "global_step": 430861, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.056387186050415, "global_step": 430862, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9721968173980713, "global_step": 430863, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1739084720611572, "global_step": 430864, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.107393264770508, "global_step": 430865, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0139973163604736, "global_step": 430866, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.011234998703003, "global_step": 430867, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1080989837646484, "global_step": 430868, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1296157836914062, "global_step": 430869, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.100733518600464, "global_step": 430870, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0776143074035645, "global_step": 430871, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.146620273590088, "global_step": 430872, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1890292167663574, "global_step": 430873, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1063218116760254, "global_step": 430874, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1121511459350586, "global_step": 430875, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0492172241210938, "global_step": 430876, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1127467155456543, "global_step": 430877, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0385801792144775, "global_step": 430878, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0327212810516357, "global_step": 430879, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.012556791305542, "global_step": 430880, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1473116874694824, "global_step": 430881, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.08811092376709, "global_step": 430882, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0849647521972656, "global_step": 430883, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.058922290802002, "global_step": 430884, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.987204670906067, "global_step": 430885, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.078568935394287, "global_step": 430886, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.077453851699829, "global_step": 430887, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0635716915130615, "global_step": 430888, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.078348159790039, "global_step": 430889, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.130321979522705, "global_step": 430890, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.030153751373291, "global_step": 430891, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1057097911834717, "global_step": 430892, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1377172470092773, "global_step": 430893, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1536667346954346, "global_step": 430894, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1731925010681152, "global_step": 430895, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.188903331756592, "global_step": 430896, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0382347106933594, "global_step": 430897, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0051331520080566, "global_step": 430898, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0795834064483643, "global_step": 430899, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.071713447570801, "global_step": 430900, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0945401191711426, "global_step": 430901, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1731953620910645, "global_step": 430902, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.16338849067688, "global_step": 430903, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9924207925796509, "global_step": 430904, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.101552963256836, "global_step": 430905, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.061326742172241, "global_step": 430906, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0315303802490234, "global_step": 430907, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.083771228790283, "global_step": 430908, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.072141408920288, "global_step": 430909, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.138937473297119, "global_step": 430910, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1194324493408203, "global_step": 430911, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0585644245147705, "global_step": 430912, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.071967363357544, "global_step": 430913, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.14416241645813, "global_step": 430914, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.049562692642212, "global_step": 430915, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.004655361175537, "global_step": 430916, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.184457302093506, "global_step": 430917, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0804994106292725, "global_step": 430918, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0836002826690674, "global_step": 430919, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1087021827697754, "global_step": 430920, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9855804443359375, "global_step": 430921, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.078035354614258, "global_step": 430922, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0392799377441406, "global_step": 430923, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1398699283599854, "global_step": 430924, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.996291160583496, "global_step": 430925, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0233211517333984, "global_step": 430926, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0476558208465576, "global_step": 430927, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.056767225265503, "global_step": 430928, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0880229473114014, "global_step": 430929, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.089893341064453, "global_step": 430930, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.132108688354492, "global_step": 430931, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1081736087799072, "global_step": 430932, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0727698802948, "global_step": 430933, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.072913885116577, "global_step": 430934, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.035245418548584, "global_step": 430935, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.080422878265381, "global_step": 430936, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0414915084838867, "global_step": 430937, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.997631311416626, "global_step": 430938, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0861871242523193, "global_step": 430939, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.096736192703247, "global_step": 430940, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0640721321105957, "global_step": 430941, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.110151529312134, "global_step": 430942, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0823330879211426, "global_step": 430943, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0432372093200684, "global_step": 430944, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0628561973571777, "global_step": 430945, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0353033542633057, "global_step": 430946, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.111375331878662, "global_step": 430947, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1126036643981934, "global_step": 430948, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.139303207397461, "global_step": 430949, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.033200263977051, "global_step": 430950, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1169872283935547, "global_step": 430951, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1407392024993896, "global_step": 430952, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0787503719329834, "global_step": 430953, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1525933742523193, "global_step": 430954, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.018782615661621, "global_step": 430955, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.08756160736084, "global_step": 430956, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1463623046875, "global_step": 430957, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0202207565307617, "global_step": 430958, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.188203811645508, "global_step": 430959, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0645511150360107, "global_step": 430960, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0213356018066406, "global_step": 430961, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1234116554260254, "global_step": 430962, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.112860679626465, "global_step": 430963, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0174379348754883, "global_step": 430964, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0378146171569824, "global_step": 430965, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0998148918151855, "global_step": 430966, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0894503593444824, "global_step": 430967, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1503448486328125, "global_step": 430968, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9943662881851196, "global_step": 430969, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1409084796905518, "global_step": 430970, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.157256603240967, "global_step": 430971, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.104314088821411, "global_step": 430972, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1031954288482666, "global_step": 430973, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.094412088394165, "global_step": 430974, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.132362127304077, "global_step": 430975, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0128421783447266, "global_step": 430976, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.171102523803711, "global_step": 430977, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0792908668518066, "global_step": 430978, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0494329929351807, "global_step": 430979, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.121096611022949, "global_step": 430980, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1392242908477783, "global_step": 430981, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.079864501953125, "global_step": 430982, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0857162475585938, "global_step": 430983, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.038567543029785, "global_step": 430984, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0842132568359375, "global_step": 430985, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9925552606582642, "global_step": 430986, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1020822525024414, "global_step": 430987, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1848886013031006, "global_step": 430988, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.124323844909668, "global_step": 430989, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.09458589553833, "global_step": 430990, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1139659881591797, "global_step": 430991, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.050933599472046, "global_step": 430992, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.141094207763672, "global_step": 430993, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0969948768615723, "global_step": 430994, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.034139394760132, "global_step": 430995, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.039917230606079, "global_step": 430996, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.137298583984375, "global_step": 430997, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.114915132522583, "global_step": 430998, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.01595401763916, "global_step": 430999, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0976345539093018, "global_step": 431000, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.027001142501831, "global_step": 431001, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.048175573348999, "global_step": 431002, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.16414475440979, "global_step": 431003, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.008044481277466, "global_step": 431004, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1033132076263428, "global_step": 431005, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1051948070526123, "global_step": 431006, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0743446350097656, "global_step": 431007, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0320241451263428, "global_step": 431008, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0994014739990234, "global_step": 431009, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.150186777114868, "global_step": 431010, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1091701984405518, "global_step": 431011, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.15792179107666, "global_step": 431012, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1115822792053223, "global_step": 431013, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1056456565856934, "global_step": 431014, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0977742671966553, "global_step": 431015, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.2383437156677246, "global_step": 431016, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.07525634765625, "global_step": 431017, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.120793342590332, "global_step": 431018, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0987579822540283, "global_step": 431019, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0419633388519287, "global_step": 431020, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1616742610931396, "global_step": 431021, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0962772369384766, "global_step": 431022, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.16300106048584, "global_step": 431023, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.07102108001709, "global_step": 431024, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0784096717834473, "global_step": 431025, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1192538738250732, "global_step": 431026, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0690746307373047, "global_step": 431027, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0565757751464844, "global_step": 431028, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1055986881256104, "global_step": 431029, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0442256927490234, "global_step": 431030, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.988193392753601, "global_step": 431031, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0681967735290527, "global_step": 431032, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0833728313446045, "global_step": 431033, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1325392723083496, "global_step": 431034, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9575884342193604, "global_step": 431035, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0945141315460205, "global_step": 431036, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.147249221801758, "global_step": 431037, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0260848999023438, "global_step": 431038, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.148226261138916, "global_step": 431039, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1225955486297607, "global_step": 431040, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.024904251098633, "global_step": 431041, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.06097149848938, "global_step": 431042, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.069995403289795, "global_step": 431043, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.085951805114746, "global_step": 431044, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.099078416824341, "global_step": 431045, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.065469741821289, "global_step": 431046, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0285961627960205, "global_step": 431047, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.007352590560913, "global_step": 431048, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1374142169952393, "global_step": 431049, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0906150341033936, "global_step": 431050, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1264445781707764, "global_step": 431051, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1036810874938965, "global_step": 431052, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.122563600540161, "global_step": 431053, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0813651084899902, "global_step": 431054, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1160049438476562, "global_step": 431055, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0931661128997803, "global_step": 431056, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.151657819747925, "global_step": 431057, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0814080238342285, "global_step": 431058, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0892715454101562, "global_step": 431059, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.084425449371338, "global_step": 431060, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0880680084228516, "global_step": 431061, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.049764394760132, "global_step": 431062, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.095273733139038, "global_step": 431063, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.086618185043335, "global_step": 431064, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9918164014816284, "global_step": 431065, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1331701278686523, "global_step": 431066, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.209385871887207, "global_step": 431067, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0742790699005127, "global_step": 431068, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.04697585105896, "global_step": 431069, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1027097702026367, "global_step": 431070, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0731096267700195, "global_step": 431071, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0844900608062744, "global_step": 431072, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1128149032592773, "global_step": 431073, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.053739547729492, "global_step": 431074, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.063528299331665, "global_step": 431075, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.172697067260742, "global_step": 431076, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1132631301879883, "global_step": 431077, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.217027425765991, "global_step": 431078, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.071220636367798, "global_step": 431079, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.064210891723633, "global_step": 431080, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.146991491317749, "global_step": 431081, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0669198036193848, "global_step": 431082, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0881478786468506, "global_step": 431083, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.048079013824463, "global_step": 431084, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1036195755004883, "global_step": 431085, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0748162269592285, "global_step": 431086, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1057932376861572, "global_step": 431087, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0660336017608643, "global_step": 431088, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1216840744018555, "global_step": 431089, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.093773365020752, "global_step": 431090, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0745763778686523, "global_step": 431091, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0236971378326416, "global_step": 431092, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.036956310272217, "global_step": 431093, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0555038452148438, "global_step": 431094, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0727105140686035, "global_step": 431095, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.055725574493408, "global_step": 431096, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1420083045959473, "global_step": 431097, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0681874752044678, "global_step": 431098, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.03226375579834, "global_step": 431099, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.004589319229126, "global_step": 431100, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1936116218566895, "global_step": 431101, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0576460361480713, "global_step": 431102, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1286489963531494, "global_step": 431103, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1169941425323486, "global_step": 431104, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1594533920288086, "global_step": 431105, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0946013927459717, "global_step": 431106, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.020944595336914, "global_step": 431107, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0713353157043457, "global_step": 431108, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.014822244644165, "global_step": 431109, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.051234245300293, "global_step": 431110, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0048105716705322, "global_step": 431111, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9961566925048828, "global_step": 431112, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.043205738067627, "global_step": 431113, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.094877243041992, "global_step": 431114, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0832302570343018, "global_step": 431115, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1236050128936768, "global_step": 431116, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.144169330596924, "global_step": 431117, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1665148735046387, "global_step": 431118, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1589980125427246, "global_step": 431119, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1711480617523193, "global_step": 431120, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.085545539855957, "global_step": 431121, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0561060905456543, "global_step": 431122, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.028757095336914, "global_step": 431123, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0832931995391846, "global_step": 431124, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.046431541442871, "global_step": 431125, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1042912006378174, "global_step": 431126, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.025714635848999, "global_step": 431127, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0719799995422363, "global_step": 431128, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1363251209259033, "global_step": 431129, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.059661865234375, "global_step": 431130, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.113668441772461, "global_step": 431131, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1522040367126465, "global_step": 431132, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.066011428833008, "global_step": 431133, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0571916103363037, "global_step": 431134, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1030750274658203, "global_step": 431135, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0368471145629883, "global_step": 431136, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.039118766784668, "global_step": 431137, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1332108974456787, "global_step": 431138, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0569779872894287, "global_step": 431139, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0733659267425537, "global_step": 431140, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0997793674468994, "global_step": 431141, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1098947525024414, "global_step": 431142, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1361083984375, "global_step": 431143, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.135925531387329, "global_step": 431144, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.109071731567383, "global_step": 431145, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0920207500457764, "global_step": 431146, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.2265350818634033, "global_step": 431147, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.105114221572876, "global_step": 431148, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.045714855194092, "global_step": 431149, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0245742797851562, "global_step": 431150, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0749824047088623, "global_step": 431151, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.13067364692688, "global_step": 431152, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0478038787841797, "global_step": 431153, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.015536308288574, "global_step": 431154, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.104787588119507, "global_step": 431155, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1161513328552246, "global_step": 431156, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1612536907196045, "global_step": 431157, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1407299041748047, "global_step": 431158, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.110029458999634, "global_step": 431159, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0315585136413574, "global_step": 431160, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.135955810546875, "global_step": 431161, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0086822509765625, "global_step": 431162, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0553946495056152, "global_step": 431163, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1294443607330322, "global_step": 431164, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.019285202026367, "global_step": 431165, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0478837490081787, "global_step": 431166, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0621445178985596, "global_step": 431167, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.149524211883545, "global_step": 431168, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0345728397369385, "global_step": 431169, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.124377489089966, "global_step": 431170, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1252851486206055, "global_step": 431171, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.132728099822998, "global_step": 431172, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.104529619216919, "global_step": 431173, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.083144426345825, "global_step": 431174, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.148792266845703, "global_step": 431175, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0283353328704834, "global_step": 431176, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.043459415435791, "global_step": 431177, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.206421375274658, "global_step": 431178, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9831124544143677, "global_step": 431179, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0510847568511963, "global_step": 431180, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0559446811676025, "global_step": 431181, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0666794776916504, "global_step": 431182, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1304333209991455, "global_step": 431183, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.084554433822632, "global_step": 431184, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0677120685577393, "global_step": 431185, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0512938499450684, "global_step": 431186, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0756216049194336, "global_step": 431187, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.203213691711426, "global_step": 431188, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.012570858001709, "global_step": 431189, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.080919027328491, "global_step": 431190, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0836141109466553, "global_step": 431191, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0870912075042725, "global_step": 431192, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1067230701446533, "global_step": 431193, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.98558509349823, "global_step": 431194, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.081498384475708, "global_step": 431195, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.133222818374634, "global_step": 431196, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.113605260848999, "global_step": 431197, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.226900577545166, "global_step": 431198, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1292724609375, "global_step": 431199, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.050327777862549, "global_step": 431200, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.167738199234009, "global_step": 431201, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0926289558410645, "global_step": 431202, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.092210054397583, "global_step": 431203, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0887198448181152, "global_step": 431204, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.080457925796509, "global_step": 431205, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.097219467163086, "global_step": 431206, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.048290967941284, "global_step": 431207, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0572659969329834, "global_step": 431208, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.058806896209717, "global_step": 431209, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1267361640930176, "global_step": 431210, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.245609760284424, "global_step": 431211, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0366690158843994, "global_step": 431212, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1419405937194824, "global_step": 431213, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.181333541870117, "global_step": 431214, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.049696207046509, "global_step": 431215, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1217949390411377, "global_step": 431216, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0927631855010986, "global_step": 431217, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.023280382156372, "global_step": 431218, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0322914123535156, "global_step": 431219, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.047795295715332, "global_step": 431220, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0697357654571533, "global_step": 431221, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.037191152572632, "global_step": 431222, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.108224868774414, "global_step": 431223, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1286137104034424, "global_step": 431224, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1354801654815674, "global_step": 431225, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.113960027694702, "global_step": 431226, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.029912233352661, "global_step": 431227, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.023081064224243, "global_step": 431228, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0872631072998047, "global_step": 431229, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0413544178009033, "global_step": 431230, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.052351951599121, "global_step": 431231, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.175685167312622, "global_step": 431232, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.079261064529419, "global_step": 431233, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9532036781311035, "global_step": 431234, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0562851428985596, "global_step": 431235, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.160926342010498, "global_step": 431236, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0315263271331787, "global_step": 431237, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1081864833831787, "global_step": 431238, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1590166091918945, "global_step": 431239, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0977537631988525, "global_step": 431240, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.051957368850708, "global_step": 431241, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.078036308288574, "global_step": 431242, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1449618339538574, "global_step": 431243, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.134394407272339, "global_step": 431244, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.156033992767334, "global_step": 431245, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.091468095779419, "global_step": 431246, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.096950054168701, "global_step": 431247, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0545833110809326, "global_step": 431248, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.111539363861084, "global_step": 431249, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9773560762405396, "global_step": 431250, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.139829397201538, "global_step": 431251, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0523533821105957, "global_step": 431252, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1230902671813965, "global_step": 431253, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0697312355041504, "global_step": 431254, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.098167657852173, "global_step": 431255, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.020462989807129, "global_step": 431256, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1046078205108643, "global_step": 431257, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.021693468093872, "global_step": 431258, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.2097647190093994, "global_step": 431259, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1329293251037598, "global_step": 431260, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0727288722991943, "global_step": 431261, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0524673461914062, "global_step": 431262, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1331026554107666, "global_step": 431263, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.067336320877075, "global_step": 431264, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.190927743911743, "global_step": 431265, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1587369441986084, "global_step": 431266, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1260945796966553, "global_step": 431267, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1957736015319824, "global_step": 431268, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.111370086669922, "global_step": 431269, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0514752864837646, "global_step": 431270, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0797300338745117, "global_step": 431271, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0723557472229004, "global_step": 431272, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.133761167526245, "global_step": 431273, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.057652235031128, "global_step": 431274, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.082970380783081, "global_step": 431275, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1662380695343018, "global_step": 431276, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0712010860443115, "global_step": 431277, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0405640602111816, "global_step": 431278, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.038952589035034, "global_step": 431279, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.141153335571289, "global_step": 431280, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0459985733032227, "global_step": 431281, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.150779962539673, "global_step": 431282, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.094101667404175, "global_step": 431283, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1742804050445557, "global_step": 431284, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9822388887405396, "global_step": 431285, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.096316337585449, "global_step": 431286, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.151357412338257, "global_step": 431287, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0613503456115723, "global_step": 431288, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0543739795684814, "global_step": 431289, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1194615364074707, "global_step": 431290, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0574421882629395, "global_step": 431291, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.105175256729126, "global_step": 431292, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.984798789024353, "global_step": 431293, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.104613780975342, "global_step": 431294, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.190600633621216, "global_step": 431295, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.033318281173706, "global_step": 431296, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.084508180618286, "global_step": 431297, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.14137864112854, "global_step": 431298, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1285455226898193, "global_step": 431299, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1664514541625977, "global_step": 431300, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1486082077026367, "global_step": 431301, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0946624279022217, "global_step": 431302, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1586906909942627, "global_step": 431303, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1067452430725098, "global_step": 431304, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0172505378723145, "global_step": 431305, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.020873546600342, "global_step": 431306, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0780651569366455, "global_step": 431307, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.125603675842285, "global_step": 431308, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.044778823852539, "global_step": 431309, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1105639934539795, "global_step": 431310, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.065887928009033, "global_step": 431311, "epoch": 794, "lr": 5e-05}
{"train_loss": 1.9986026287078857, "global_step": 431312, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.050281524658203, "global_step": 431313, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0952579975128174, "global_step": 431314, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.01020884513855, "global_step": 431315, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.101015329360962, "global_step": 431316, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.093421697616577, "global_step": 431317, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1688709259033203, "global_step": 431318, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0914125442504883, "global_step": 431319, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.151439905166626, "global_step": 431320, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0725529193878174, "global_step": 431321, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.050184726715088, "global_step": 431322, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.156498908996582, "global_step": 431323, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.137235403060913, "global_step": 431324, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0918776988983154, "global_step": 431325, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0285139083862305, "global_step": 431326, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1051297187805176, "global_step": 431327, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.118715524673462, "global_step": 431328, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1185779571533203, "global_step": 431329, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0245418548583984, "global_step": 431330, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.093348979949951, "global_step": 431331, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.123450756072998, "global_step": 431332, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0380232334136963, "global_step": 431333, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.134139060974121, "global_step": 431334, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.0589065551757812, "global_step": 431335, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.1523709297180176, "global_step": 431336, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.080967664718628, "global_step": 431337, "epoch": 794, "lr": 5e-05}
{"train_loss": 2.036470890045166, "global_step": 431338, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.090383291244507, "global_step": 431339, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0104217529296875, "global_step": 431340, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.080371856689453, "global_step": 431341, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0553550720214844, "global_step": 431342, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.077125072479248, "global_step": 431343, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1009411811828613, "global_step": 431344, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.068970203399658, "global_step": 431345, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.123568296432495, "global_step": 431346, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.035888671875, "global_step": 431347, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.061795711517334, "global_step": 431348, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.072608709335327, "global_step": 431349, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.178590774536133, "global_step": 431350, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1101253032684326, "global_step": 431351, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0861377716064453, "global_step": 431352, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.04329252243042, "global_step": 431353, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.046818494796753, "global_step": 431354, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1154720783233643, "global_step": 431355, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.107074499130249, "global_step": 431356, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0679359436035156, "global_step": 431357, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.016026020050049, "global_step": 431358, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.033045768737793, "global_step": 431359, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0478336811065674, "global_step": 431360, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0028884410858154, "global_step": 431361, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1114187240600586, "global_step": 431362, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.152439832687378, "global_step": 431363, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.128316879272461, "global_step": 431364, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1080431938171387, "global_step": 431365, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0829296112060547, "global_step": 431366, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.091315746307373, "global_step": 431367, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.03057599067688, "global_step": 431368, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0988190174102783, "global_step": 431369, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1164774894714355, "global_step": 431370, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.129319906234741, "global_step": 431371, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0489258766174316, "global_step": 431372, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.00419545173645, "global_step": 431373, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0776734352111816, "global_step": 431374, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1579997539520264, "global_step": 431375, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.09676194190979, "global_step": 431376, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0701487064361572, "global_step": 431377, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0688564777374268, "global_step": 431378, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.997567057609558, "global_step": 431379, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0349061489105225, "global_step": 431380, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0054988861083984, "global_step": 431381, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0420851707458496, "global_step": 431382, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.16864013671875, "global_step": 431383, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0404090881347656, "global_step": 431384, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0613090991973877, "global_step": 431385, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0678515434265137, "global_step": 431386, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.2158329486846924, "global_step": 431387, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0333473682403564, "global_step": 431388, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.148472309112549, "global_step": 431389, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.053299903869629, "global_step": 431390, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.052797317504883, "global_step": 431391, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9892394542694092, "global_step": 431392, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.081218957901001, "global_step": 431393, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1743175983428955, "global_step": 431394, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0966663360595703, "global_step": 431395, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0006160736083984, "global_step": 431396, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1195268630981445, "global_step": 431397, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.120441198348999, "global_step": 431398, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0892996788024902, "global_step": 431399, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1056129932403564, "global_step": 431400, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.107862949371338, "global_step": 431401, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0942490100860596, "global_step": 431402, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.076101303100586, "global_step": 431403, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.017930507659912, "global_step": 431404, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.034198760986328, "global_step": 431405, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0515050888061523, "global_step": 431406, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0978236198425293, "global_step": 431407, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0577147006988525, "global_step": 431408, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9955476522445679, "global_step": 431409, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1067240238189697, "global_step": 431410, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1218421459198, "global_step": 431411, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.076735496520996, "global_step": 431412, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0411570072174072, "global_step": 431413, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.069634437561035, "global_step": 431414, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0771541595458984, "global_step": 431415, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.127957820892334, "global_step": 431416, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.039884090423584, "global_step": 431417, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.041555881500244, "global_step": 431418, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.041574001312256, "global_step": 431419, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.097564697265625, "global_step": 431420, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0373404026031494, "global_step": 431421, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0249977111816406, "global_step": 431422, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1363186836242676, "global_step": 431423, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1929140090942383, "global_step": 431424, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0669422149658203, "global_step": 431425, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0665132999420166, "global_step": 431426, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0267462730407715, "global_step": 431427, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0419631004333496, "global_step": 431428, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1134517192840576, "global_step": 431429, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0682873725891113, "global_step": 431430, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.111501693725586, "global_step": 431431, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1245999336242676, "global_step": 431432, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0949478149414062, "global_step": 431433, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.134037971496582, "global_step": 431434, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.031215190887451, "global_step": 431435, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.033797025680542, "global_step": 431436, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.080244779586792, "global_step": 431437, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0256223678588867, "global_step": 431438, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1093361377716064, "global_step": 431439, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.149373769760132, "global_step": 431440, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9995461702346802, "global_step": 431441, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.123887300491333, "global_step": 431442, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0262291431427, "global_step": 431443, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.045121431350708, "global_step": 431444, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0190396308898926, "global_step": 431445, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1375579833984375, "global_step": 431446, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.081150770187378, "global_step": 431447, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1305794715881348, "global_step": 431448, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.045814037322998, "global_step": 431449, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.075092077255249, "global_step": 431450, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0652596950531006, "global_step": 431451, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1112236976623535, "global_step": 431452, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0485823154449463, "global_step": 431453, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0560903549194336, "global_step": 431454, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9764320850372314, "global_step": 431455, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.093736410140991, "global_step": 431456, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1485440731048584, "global_step": 431457, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0259602069854736, "global_step": 431458, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.069736957550049, "global_step": 431459, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0854122638702393, "global_step": 431460, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0808260440826416, "global_step": 431461, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0865638256073, "global_step": 431462, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0311648845672607, "global_step": 431463, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1134531497955322, "global_step": 431464, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0593276023864746, "global_step": 431465, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0963404178619385, "global_step": 431466, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0386362075805664, "global_step": 431467, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0264787673950195, "global_step": 431468, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.148989677429199, "global_step": 431469, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.012847900390625, "global_step": 431470, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1178476810455322, "global_step": 431471, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.107142686843872, "global_step": 431472, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0633656978607178, "global_step": 431473, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1146717071533203, "global_step": 431474, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.011629819869995, "global_step": 431475, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0077104568481445, "global_step": 431476, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0369081497192383, "global_step": 431477, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.051197052001953, "global_step": 431478, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.2202720642089844, "global_step": 431479, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.050238609313965, "global_step": 431480, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.086428165435791, "global_step": 431481, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1916327476501465, "global_step": 431482, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.113607406616211, "global_step": 431483, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.099087715148926, "global_step": 431484, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0658926963806152, "global_step": 431485, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0741512775421143, "global_step": 431486, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1086618900299072, "global_step": 431487, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.121948480606079, "global_step": 431488, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0978848934173584, "global_step": 431489, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.093801975250244, "global_step": 431490, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.016096591949463, "global_step": 431491, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0953705310821533, "global_step": 431492, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0543360710144043, "global_step": 431493, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.053563117980957, "global_step": 431494, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.10467529296875, "global_step": 431495, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0064697265625, "global_step": 431496, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.089827060699463, "global_step": 431497, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0622103214263916, "global_step": 431498, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0251786708831787, "global_step": 431499, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0375747680664062, "global_step": 431500, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.010406970977783, "global_step": 431501, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0706114768981934, "global_step": 431502, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1249237060546875, "global_step": 431503, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.045651912689209, "global_step": 431504, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.076521873474121, "global_step": 431505, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0467169284820557, "global_step": 431506, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.081195831298828, "global_step": 431507, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.078188896179199, "global_step": 431508, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0520448684692383, "global_step": 431509, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.079630136489868, "global_step": 431510, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9829391241073608, "global_step": 431511, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9705063104629517, "global_step": 431512, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.163761615753174, "global_step": 431513, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0078530311584473, "global_step": 431514, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0964090824127197, "global_step": 431515, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.038642406463623, "global_step": 431516, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9712599515914917, "global_step": 431517, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.058563709259033, "global_step": 431518, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9863896369934082, "global_step": 431519, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0477123260498047, "global_step": 431520, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1526474952697754, "global_step": 431521, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.086683511734009, "global_step": 431522, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.091566562652588, "global_step": 431523, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.032724618911743, "global_step": 431524, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1289494037628174, "global_step": 431525, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9402120113372803, "global_step": 431526, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0914294719696045, "global_step": 431527, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1457016468048096, "global_step": 431528, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1377012729644775, "global_step": 431529, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.160893201828003, "global_step": 431530, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.066956043243408, "global_step": 431531, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0178744792938232, "global_step": 431532, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0521469116210938, "global_step": 431533, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.144890069961548, "global_step": 431534, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.12278151512146, "global_step": 431535, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0149085521698, "global_step": 431536, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.110764265060425, "global_step": 431537, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.020482301712036, "global_step": 431538, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0250210762023926, "global_step": 431539, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.105422258377075, "global_step": 431540, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.093372344970703, "global_step": 431541, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0872530937194824, "global_step": 431542, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.050528049468994, "global_step": 431543, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.939664363861084, "global_step": 431544, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0483248233795166, "global_step": 431545, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0891566276550293, "global_step": 431546, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0581040382385254, "global_step": 431547, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.082960605621338, "global_step": 431548, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1734957695007324, "global_step": 431549, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.140381097793579, "global_step": 431550, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.120293140411377, "global_step": 431551, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9864469766616821, "global_step": 431552, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0206491947174072, "global_step": 431553, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0799527168273926, "global_step": 431554, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.03580641746521, "global_step": 431555, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.05403208732605, "global_step": 431556, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.040466547012329, "global_step": 431557, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.085207223892212, "global_step": 431558, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.001406192779541, "global_step": 431559, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.035050630569458, "global_step": 431560, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1129298210144043, "global_step": 431561, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.088270902633667, "global_step": 431562, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.110478639602661, "global_step": 431563, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.984750747680664, "global_step": 431564, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0663113594055176, "global_step": 431565, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.123929738998413, "global_step": 431566, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.120030403137207, "global_step": 431567, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.137291669845581, "global_step": 431568, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0637924671173096, "global_step": 431569, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.033700466156006, "global_step": 431570, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0619726181030273, "global_step": 431571, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0815048217773438, "global_step": 431572, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.077066421508789, "global_step": 431573, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0207419395446777, "global_step": 431574, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.03753662109375, "global_step": 431575, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9918302297592163, "global_step": 431576, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.061628580093384, "global_step": 431577, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0727031230926514, "global_step": 431578, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0734872817993164, "global_step": 431579, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1327311992645264, "global_step": 431580, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.083953619003296, "global_step": 431581, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.050902843475342, "global_step": 431582, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1273272037506104, "global_step": 431583, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.07978892326355, "global_step": 431584, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.119656562805176, "global_step": 431585, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.069455146789551, "global_step": 431586, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9543503522872925, "global_step": 431587, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.088172435760498, "global_step": 431588, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.094195604324341, "global_step": 431589, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0534281730651855, "global_step": 431590, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.061265230178833, "global_step": 431591, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.064594030380249, "global_step": 431592, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0604310035705566, "global_step": 431593, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.09222412109375, "global_step": 431594, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.077191114425659, "global_step": 431595, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.110560655593872, "global_step": 431596, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0723390579223633, "global_step": 431597, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0215835571289062, "global_step": 431598, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0886306762695312, "global_step": 431599, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.095783233642578, "global_step": 431600, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1403985023498535, "global_step": 431601, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.134533405303955, "global_step": 431602, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0615906715393066, "global_step": 431603, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.059363603591919, "global_step": 431604, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.995174527168274, "global_step": 431605, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0630972385406494, "global_step": 431606, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0882580280303955, "global_step": 431607, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1773204803466797, "global_step": 431608, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.139111042022705, "global_step": 431609, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.016167163848877, "global_step": 431610, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.10648250579834, "global_step": 431611, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0915603637695312, "global_step": 431612, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.066864013671875, "global_step": 431613, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.087010622024536, "global_step": 431614, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.095705032348633, "global_step": 431615, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.178670644760132, "global_step": 431616, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.096843957901001, "global_step": 431617, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0606915950775146, "global_step": 431618, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.045227527618408, "global_step": 431619, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0141403675079346, "global_step": 431620, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1139094829559326, "global_step": 431621, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.025657892227173, "global_step": 431622, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.153128147125244, "global_step": 431623, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.095388412475586, "global_step": 431624, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0796046257019043, "global_step": 431625, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.118013858795166, "global_step": 431626, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0718741416931152, "global_step": 431627, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.078359365463257, "global_step": 431628, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0303144454956055, "global_step": 431629, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0412099361419678, "global_step": 431630, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.088573694229126, "global_step": 431631, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.107560873031616, "global_step": 431632, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0838446617126465, "global_step": 431633, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0684800148010254, "global_step": 431634, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.091031789779663, "global_step": 431635, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.055452585220337, "global_step": 431636, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1618852615356445, "global_step": 431637, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0444278717041016, "global_step": 431638, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0347416400909424, "global_step": 431639, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.109090805053711, "global_step": 431640, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0476086139678955, "global_step": 431641, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0930964946746826, "global_step": 431642, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0563275814056396, "global_step": 431643, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.113743782043457, "global_step": 431644, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0920753479003906, "global_step": 431645, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.014922618865967, "global_step": 431646, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0001492500305176, "global_step": 431647, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.049164056777954, "global_step": 431648, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1239500045776367, "global_step": 431649, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.114957571029663, "global_step": 431650, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1590218544006348, "global_step": 431651, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.087176561355591, "global_step": 431652, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0852744579315186, "global_step": 431653, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0947749614715576, "global_step": 431654, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0836503505706787, "global_step": 431655, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0719754695892334, "global_step": 431656, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0816807746887207, "global_step": 431657, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.172572612762451, "global_step": 431658, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.071495532989502, "global_step": 431659, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0681185722351074, "global_step": 431660, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.053701162338257, "global_step": 431661, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.179882526397705, "global_step": 431662, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1500911712646484, "global_step": 431663, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.047957181930542, "global_step": 431664, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0247957706451416, "global_step": 431665, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.107807159423828, "global_step": 431666, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0859994888305664, "global_step": 431667, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0172007083892822, "global_step": 431668, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.195594310760498, "global_step": 431669, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1206393241882324, "global_step": 431670, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9965503215789795, "global_step": 431671, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.166710138320923, "global_step": 431672, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.011324644088745, "global_step": 431673, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.052706003189087, "global_step": 431674, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1637320518493652, "global_step": 431675, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0027735233306885, "global_step": 431676, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.986750841140747, "global_step": 431677, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.991468906402588, "global_step": 431678, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0024211406707764, "global_step": 431679, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.060885190963745, "global_step": 431680, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0994019508361816, "global_step": 431681, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1518754959106445, "global_step": 431682, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.037992238998413, "global_step": 431683, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.070927858352661, "global_step": 431684, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0461771488189697, "global_step": 431685, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9621714353561401, "global_step": 431686, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.063204050064087, "global_step": 431687, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9867714643478394, "global_step": 431688, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.019578456878662, "global_step": 431689, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0368669033050537, "global_step": 431690, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9924317598342896, "global_step": 431691, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0581634044647217, "global_step": 431692, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0620107650756836, "global_step": 431693, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0428833961486816, "global_step": 431694, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.005117177963257, "global_step": 431695, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.120748281478882, "global_step": 431696, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0056421756744385, "global_step": 431697, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.074110269546509, "global_step": 431698, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.074899435043335, "global_step": 431699, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1976771354675293, "global_step": 431700, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.078791618347168, "global_step": 431701, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.12433123588562, "global_step": 431702, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0846707820892334, "global_step": 431703, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.16161847114563, "global_step": 431704, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0679006576538086, "global_step": 431705, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.018109083175659, "global_step": 431706, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.076626777648926, "global_step": 431707, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.172755718231201, "global_step": 431708, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0673751831054688, "global_step": 431709, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0748753547668457, "global_step": 431710, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1570167541503906, "global_step": 431711, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.113619565963745, "global_step": 431712, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1121926307678223, "global_step": 431713, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.072556734085083, "global_step": 431714, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.021040201187134, "global_step": 431715, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1038742065429688, "global_step": 431716, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0212621688842773, "global_step": 431717, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.154477596282959, "global_step": 431718, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0960211753845215, "global_step": 431719, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.122786283493042, "global_step": 431720, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0411665439605713, "global_step": 431721, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.107267141342163, "global_step": 431722, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0232949256896973, "global_step": 431723, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1666364669799805, "global_step": 431724, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.06794810295105, "global_step": 431725, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0671095848083496, "global_step": 431726, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1197173595428467, "global_step": 431727, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.124202013015747, "global_step": 431728, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0330982208251953, "global_step": 431729, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0250656604766846, "global_step": 431730, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.228562831878662, "global_step": 431731, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1027421951293945, "global_step": 431732, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0724289417266846, "global_step": 431733, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0766067504882812, "global_step": 431734, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0844664573669434, "global_step": 431735, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.113483428955078, "global_step": 431736, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1168408393859863, "global_step": 431737, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1533939838409424, "global_step": 431738, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.090167999267578, "global_step": 431739, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1399497985839844, "global_step": 431740, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.07882022857666, "global_step": 431741, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0891201496124268, "global_step": 431742, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0928170680999756, "global_step": 431743, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1709179878234863, "global_step": 431744, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0669219493865967, "global_step": 431745, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.128131866455078, "global_step": 431746, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1060168743133545, "global_step": 431747, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.123307466506958, "global_step": 431748, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.079531192779541, "global_step": 431749, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.112030029296875, "global_step": 431750, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9589930772781372, "global_step": 431751, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.108786106109619, "global_step": 431752, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0115268230438232, "global_step": 431753, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.075199842453003, "global_step": 431754, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.037548303604126, "global_step": 431755, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0843863487243652, "global_step": 431756, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0958306789398193, "global_step": 431757, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0570199489593506, "global_step": 431758, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.026949882507324, "global_step": 431759, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.03291654586792, "global_step": 431760, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.113485097885132, "global_step": 431761, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.038527011871338, "global_step": 431762, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0812978744506836, "global_step": 431763, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.032021999359131, "global_step": 431764, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9518824815750122, "global_step": 431765, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0788497924804688, "global_step": 431766, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0728213787078857, "global_step": 431767, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0467469692230225, "global_step": 431768, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.020721197128296, "global_step": 431769, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0754380226135254, "global_step": 431770, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.075347423553467, "global_step": 431771, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.144512176513672, "global_step": 431772, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.06703782081604, "global_step": 431773, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.125908136367798, "global_step": 431774, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0837833881378174, "global_step": 431775, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0926477909088135, "global_step": 431776, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0940444469451904, "global_step": 431777, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.00638747215271, "global_step": 431778, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.042226552963257, "global_step": 431779, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1140284538269043, "global_step": 431780, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0550894737243652, "global_step": 431781, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0544724464416504, "global_step": 431782, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.056943416595459, "global_step": 431783, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9567131996154785, "global_step": 431784, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0917840003967285, "global_step": 431785, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.073068618774414, "global_step": 431786, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.17559552192688, "global_step": 431787, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.112882375717163, "global_step": 431788, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.05141544342041, "global_step": 431789, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1179306507110596, "global_step": 431790, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.090190887451172, "global_step": 431791, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1203532218933105, "global_step": 431792, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1338884830474854, "global_step": 431793, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.016340494155884, "global_step": 431794, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0913655757904053, "global_step": 431795, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0708394050598145, "global_step": 431796, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0676283836364746, "global_step": 431797, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0692899227142334, "global_step": 431798, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0341763496398926, "global_step": 431799, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1039392948150635, "global_step": 431800, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0158467292785645, "global_step": 431801, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.155787229537964, "global_step": 431802, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.015768051147461, "global_step": 431803, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1350536346435547, "global_step": 431804, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1319539546966553, "global_step": 431805, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1179134845733643, "global_step": 431806, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1114988327026367, "global_step": 431807, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.050546169281006, "global_step": 431808, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1967151165008545, "global_step": 431809, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.138540267944336, "global_step": 431810, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1114630699157715, "global_step": 431811, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0189247131347656, "global_step": 431812, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.11177134513855, "global_step": 431813, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1662116050720215, "global_step": 431814, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0409469604492188, "global_step": 431815, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0251967906951904, "global_step": 431816, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9818148612976074, "global_step": 431817, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1402087211608887, "global_step": 431818, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0223872661590576, "global_step": 431819, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.083815574645996, "global_step": 431820, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.058772325515747, "global_step": 431821, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.070310115814209, "global_step": 431822, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.160508155822754, "global_step": 431823, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9886305332183838, "global_step": 431824, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.047407627105713, "global_step": 431825, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1103484630584717, "global_step": 431826, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.161681890487671, "global_step": 431827, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1325857639312744, "global_step": 431828, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0929105281829834, "global_step": 431829, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0975005626678467, "global_step": 431830, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1558730602264404, "global_step": 431831, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1074252128601074, "global_step": 431832, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0978686809539795, "global_step": 431833, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9986989498138428, "global_step": 431834, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1020920276641846, "global_step": 431835, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.160825252532959, "global_step": 431836, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0278358459472656, "global_step": 431837, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.090130567550659, "global_step": 431838, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9861987829208374, "global_step": 431839, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1480021476745605, "global_step": 431840, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.145853042602539, "global_step": 431841, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.059631109237671, "global_step": 431842, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.131385087966919, "global_step": 431843, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.078172206878662, "global_step": 431844, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0896952152252197, "global_step": 431845, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0801801681518555, "global_step": 431846, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1145548820495605, "global_step": 431847, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.073802947998047, "global_step": 431848, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1992428302764893, "global_step": 431849, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.138319253921509, "global_step": 431850, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.124901294708252, "global_step": 431851, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.03047513961792, "global_step": 431852, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.031463623046875, "global_step": 431853, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9710006713867188, "global_step": 431854, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.099503993988037, "global_step": 431855, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.116001605987549, "global_step": 431856, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0644500255584717, "global_step": 431857, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1408867835998535, "global_step": 431858, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0490097999572754, "global_step": 431859, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1499857902526855, "global_step": 431860, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.004575729370117, "global_step": 431861, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1424660682678223, "global_step": 431862, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.175914764404297, "global_step": 431863, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.171555280685425, "global_step": 431864, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0676259994506836, "global_step": 431865, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.158388137817383, "global_step": 431866, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.11957049369812, "global_step": 431867, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0650174617767334, "global_step": 431868, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.115626096725464, "global_step": 431869, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.040586233139038, "global_step": 431870, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.095349073410034, "global_step": 431871, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1281723976135254, "global_step": 431872, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1083595752716064, "global_step": 431873, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.089603900909424, "global_step": 431874, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1246066093444824, "global_step": 431875, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1128580570220947, "global_step": 431876, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.106048345565796, "global_step": 431877, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1213576793670654, "global_step": 431878, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0627315044403076, "global_step": 431879, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.057558536529541, "global_step": 431880, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0463204383850098, "global_step": 431881, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1080381870269775, "global_step": 431882, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0268375873565674, "global_step": 431883, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1596250534057617, "global_step": 431884, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.085939884185791, "global_step": 431885, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.009880542755127, "global_step": 431886, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.144545793533325, "global_step": 431887, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0021960735321045, "global_step": 431888, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9846073389053345, "global_step": 431889, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0536651611328125, "global_step": 431890, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.063110828399658, "global_step": 431891, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.091693878173828, "global_step": 431892, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1469357013702393, "global_step": 431893, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1030611991882324, "global_step": 431894, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.151884078979492, "global_step": 431895, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.090786933898926, "global_step": 431896, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1095845699310303, "global_step": 431897, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0305497646331787, "global_step": 431898, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.043501615524292, "global_step": 431899, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.063279867172241, "global_step": 431900, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.142362117767334, "global_step": 431901, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.03617525100708, "global_step": 431902, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1371912956237793, "global_step": 431903, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.109441041946411, "global_step": 431904, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1014506816864014, "global_step": 431905, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0775535106658936, "global_step": 431906, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.116166830062866, "global_step": 431907, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1114256381988525, "global_step": 431908, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.169124126434326, "global_step": 431909, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0535080432891846, "global_step": 431910, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0405192375183105, "global_step": 431911, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0865678787231445, "global_step": 431912, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.2037973403930664, "global_step": 431913, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9936838150024414, "global_step": 431914, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.137861490249634, "global_step": 431915, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0349700450897217, "global_step": 431916, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1121580600738525, "global_step": 431917, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.2163662910461426, "global_step": 431918, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9879668951034546, "global_step": 431919, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.094677448272705, "global_step": 431920, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1035845279693604, "global_step": 431921, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0672688484191895, "global_step": 431922, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.117560386657715, "global_step": 431923, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.110534191131592, "global_step": 431924, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.076756715774536, "global_step": 431925, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1432290077209473, "global_step": 431926, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.135932207107544, "global_step": 431927, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0159783363342285, "global_step": 431928, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1486563682556152, "global_step": 431929, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0577597618103027, "global_step": 431930, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.113845109939575, "global_step": 431931, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.069657564163208, "global_step": 431932, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.095353841781616, "global_step": 431933, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.101128339767456, "global_step": 431934, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0241103172302246, "global_step": 431935, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1314163208007812, "global_step": 431936, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.02195143699646, "global_step": 431937, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0174834728240967, "global_step": 431938, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0955581665039062, "global_step": 431939, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.123291254043579, "global_step": 431940, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.095533847808838, "global_step": 431941, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1399736404418945, "global_step": 431942, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1613006591796875, "global_step": 431943, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1052756309509277, "global_step": 431944, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.136928081512451, "global_step": 431945, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0492966175079346, "global_step": 431946, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0741677284240723, "global_step": 431947, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0778565406799316, "global_step": 431948, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0549733638763428, "global_step": 431949, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.113431453704834, "global_step": 431950, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1005263328552246, "global_step": 431951, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0536184310913086, "global_step": 431952, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1008596420288086, "global_step": 431953, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9823180437088013, "global_step": 431954, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.030928611755371, "global_step": 431955, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1291134357452393, "global_step": 431956, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0160460472106934, "global_step": 431957, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9988852739334106, "global_step": 431958, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0464444160461426, "global_step": 431959, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1004478931427, "global_step": 431960, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.026794195175171, "global_step": 431961, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9849878549575806, "global_step": 431962, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0639944076538086, "global_step": 431963, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1064023971557617, "global_step": 431964, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1103696823120117, "global_step": 431965, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.090193271636963, "global_step": 431966, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1432526111602783, "global_step": 431967, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0247018337249756, "global_step": 431968, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.133295774459839, "global_step": 431969, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0818090438842773, "global_step": 431970, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1479146480560303, "global_step": 431971, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0437278747558594, "global_step": 431972, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.033071994781494, "global_step": 431973, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0529284477233887, "global_step": 431974, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.039199113845825, "global_step": 431975, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1035895347595215, "global_step": 431976, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.138765811920166, "global_step": 431977, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.026066541671753, "global_step": 431978, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.152650833129883, "global_step": 431979, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0364184379577637, "global_step": 431980, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0423789024353027, "global_step": 431981, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1195027828216553, "global_step": 431982, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0311760902404785, "global_step": 431983, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.101940155029297, "global_step": 431984, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1091747283935547, "global_step": 431985, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.171462059020996, "global_step": 431986, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1507511138916016, "global_step": 431987, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.095348596572876, "global_step": 431988, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1112208366394043, "global_step": 431989, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0655174255371094, "global_step": 431990, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1309444904327393, "global_step": 431991, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.113201141357422, "global_step": 431992, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.03983473777771, "global_step": 431993, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0821950435638428, "global_step": 431994, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1532232761383057, "global_step": 431995, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0745296478271484, "global_step": 431996, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1204049587249756, "global_step": 431997, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.089109420776367, "global_step": 431998, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9861388206481934, "global_step": 431999, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.100963830947876, "global_step": 432000, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1204891204833984, "global_step": 432001, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0407631397247314, "global_step": 432002, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.034961700439453, "global_step": 432003, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.049807071685791, "global_step": 432004, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0918540954589844, "global_step": 432005, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0722951889038086, "global_step": 432006, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0728747844696045, "global_step": 432007, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.125218391418457, "global_step": 432008, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1442933082580566, "global_step": 432009, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0643563270568848, "global_step": 432010, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.070686101913452, "global_step": 432011, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9797557592391968, "global_step": 432012, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0302176475524902, "global_step": 432013, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9931321144104004, "global_step": 432014, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.057314157485962, "global_step": 432015, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.024695634841919, "global_step": 432016, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0369105339050293, "global_step": 432017, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1432018280029297, "global_step": 432018, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.059114933013916, "global_step": 432019, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.074535608291626, "global_step": 432020, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0609190464019775, "global_step": 432021, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.104909658432007, "global_step": 432022, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.043164014816284, "global_step": 432023, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0251801013946533, "global_step": 432024, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1090164184570312, "global_step": 432025, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.091172933578491, "global_step": 432026, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.188692808151245, "global_step": 432027, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0073702335357666, "global_step": 432028, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0247433185577393, "global_step": 432029, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.051604747772217, "global_step": 432030, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1205101013183594, "global_step": 432031, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0559983253479004, "global_step": 432032, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.070868968963623, "global_step": 432033, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.081407070159912, "global_step": 432034, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1091866493225098, "global_step": 432035, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0125980377197266, "global_step": 432036, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1214263439178467, "global_step": 432037, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.933073878288269, "global_step": 432038, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.046689748764038, "global_step": 432039, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.118035316467285, "global_step": 432040, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1664788722991943, "global_step": 432041, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.078130006790161, "global_step": 432042, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1157355308532715, "global_step": 432043, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0986766815185547, "global_step": 432044, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0506808757781982, "global_step": 432045, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.170880079269409, "global_step": 432046, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.079958200454712, "global_step": 432047, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1387264728546143, "global_step": 432048, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1387672424316406, "global_step": 432049, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.102595090866089, "global_step": 432050, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.036484479904175, "global_step": 432051, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1248624324798584, "global_step": 432052, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.103015422821045, "global_step": 432053, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0826783180236816, "global_step": 432054, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0137951374053955, "global_step": 432055, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1326050758361816, "global_step": 432056, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.05358624458313, "global_step": 432057, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0852808952331543, "global_step": 432058, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.052947998046875, "global_step": 432059, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.102484941482544, "global_step": 432060, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.151625156402588, "global_step": 432061, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0850517749786377, "global_step": 432062, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.10738468170166, "global_step": 432063, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.079072952270508, "global_step": 432064, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.186541795730591, "global_step": 432065, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9865068197250366, "global_step": 432066, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.112525701522827, "global_step": 432067, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1104543209075928, "global_step": 432068, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.07150936126709, "global_step": 432069, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1396219730377197, "global_step": 432070, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.015580654144287, "global_step": 432071, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0544276237487793, "global_step": 432072, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1553988456726074, "global_step": 432073, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.078740358352661, "global_step": 432074, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1300454139709473, "global_step": 432075, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1064908504486084, "global_step": 432076, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.136263847351074, "global_step": 432077, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.10324764251709, "global_step": 432078, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0703964233398438, "global_step": 432079, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1099228858947754, "global_step": 432080, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.2132582664489746, "global_step": 432081, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1017158031463623, "global_step": 432082, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0884897708892822, "global_step": 432083, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0737195014953613, "global_step": 432084, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.132260799407959, "global_step": 432085, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.06540846824646, "global_step": 432086, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.074894905090332, "global_step": 432087, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1411125659942627, "global_step": 432088, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0282645225524902, "global_step": 432089, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.067242383956909, "global_step": 432090, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.11665940284729, "global_step": 432091, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0533182621002197, "global_step": 432092, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0763845443725586, "global_step": 432093, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.031144618988037, "global_step": 432094, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0116498470306396, "global_step": 432095, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0609512329101562, "global_step": 432096, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.06900954246521, "global_step": 432097, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.084439516067505, "global_step": 432098, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1194005012512207, "global_step": 432099, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1134307384490967, "global_step": 432100, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.990642786026001, "global_step": 432101, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0736403465270996, "global_step": 432102, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0901479721069336, "global_step": 432103, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1082472801208496, "global_step": 432104, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0543532371520996, "global_step": 432105, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.049603223800659, "global_step": 432106, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1497907638549805, "global_step": 432107, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1037957668304443, "global_step": 432108, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.093627691268921, "global_step": 432109, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1687161922454834, "global_step": 432110, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.045042037963867, "global_step": 432111, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.2103285789489746, "global_step": 432112, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0914266109466553, "global_step": 432113, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1186344623565674, "global_step": 432114, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.089512586593628, "global_step": 432115, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.003336191177368, "global_step": 432116, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0636374950408936, "global_step": 432117, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1426875591278076, "global_step": 432118, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1547372341156006, "global_step": 432119, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0744152069091797, "global_step": 432120, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.123178482055664, "global_step": 432121, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.077843427658081, "global_step": 432122, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0467405319213867, "global_step": 432123, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0446345806121826, "global_step": 432124, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.024005651473999, "global_step": 432125, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.137759208679199, "global_step": 432126, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0418238639831543, "global_step": 432127, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.122929096221924, "global_step": 432128, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.121608257293701, "global_step": 432129, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0773227214813232, "global_step": 432130, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0959091186523438, "global_step": 432131, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0464460849761963, "global_step": 432132, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1299185752868652, "global_step": 432133, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1157429218292236, "global_step": 432134, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0833687782287598, "global_step": 432135, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0767128467559814, "global_step": 432136, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0775039196014404, "global_step": 432137, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0865678787231445, "global_step": 432138, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1633448600769043, "global_step": 432139, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1181952953338623, "global_step": 432140, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0662014484405518, "global_step": 432141, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.081482410430908, "global_step": 432142, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.14304256439209, "global_step": 432143, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.065438985824585, "global_step": 432144, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0955402851104736, "global_step": 432145, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.188154697418213, "global_step": 432146, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0830016136169434, "global_step": 432147, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.17690110206604, "global_step": 432148, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.113729476928711, "global_step": 432149, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.047964334487915, "global_step": 432150, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.052645683288574, "global_step": 432151, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0200281143188477, "global_step": 432152, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0982582569122314, "global_step": 432153, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.099699020385742, "global_step": 432154, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0413551330566406, "global_step": 432155, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.121011257171631, "global_step": 432156, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1141974925994873, "global_step": 432157, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.086453676223755, "global_step": 432158, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.115947961807251, "global_step": 432159, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0405690670013428, "global_step": 432160, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0975005626678467, "global_step": 432161, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.087496519088745, "global_step": 432162, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0929505825042725, "global_step": 432163, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.114588975906372, "global_step": 432164, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1152560710906982, "global_step": 432165, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.116056203842163, "global_step": 432166, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.090620994567871, "global_step": 432167, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.016922950744629, "global_step": 432168, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.162914991378784, "global_step": 432169, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0815682411193848, "global_step": 432170, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0142111778259277, "global_step": 432171, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.098532199859619, "global_step": 432172, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.089808225631714, "global_step": 432173, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0870914459228516, "global_step": 432174, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0879533290863037, "global_step": 432175, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0284078121185303, "global_step": 432176, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0194287300109863, "global_step": 432177, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0800042152404785, "global_step": 432178, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0765719413757324, "global_step": 432179, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.167759895324707, "global_step": 432180, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1102592945098877, "global_step": 432181, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0755701065063477, "global_step": 432182, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1152706146240234, "global_step": 432183, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1246771812438965, "global_step": 432184, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.085484027862549, "global_step": 432185, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0289225578308105, "global_step": 432186, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1152963638305664, "global_step": 432187, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0125274658203125, "global_step": 432188, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.075622797012329, "global_step": 432189, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.088089942932129, "global_step": 432190, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1381497383117676, "global_step": 432191, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.150074005126953, "global_step": 432192, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.061774969100952, "global_step": 432193, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.060199022293091, "global_step": 432194, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0850701332092285, "global_step": 432195, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9883170127868652, "global_step": 432196, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1725401878356934, "global_step": 432197, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0795891284942627, "global_step": 432198, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0461273193359375, "global_step": 432199, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.06827974319458, "global_step": 432200, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.179229497909546, "global_step": 432201, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0408260822296143, "global_step": 432202, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0556225776672363, "global_step": 432203, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.048285722732544, "global_step": 432204, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0003232955932617, "global_step": 432205, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.031291961669922, "global_step": 432206, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0900936126708984, "global_step": 432207, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.078099012374878, "global_step": 432208, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1055591106414795, "global_step": 432209, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1262965202331543, "global_step": 432210, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1092448234558105, "global_step": 432211, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.017751932144165, "global_step": 432212, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1133549213409424, "global_step": 432213, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1571249961853027, "global_step": 432214, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.122938871383667, "global_step": 432215, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1159260272979736, "global_step": 432216, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.104071855545044, "global_step": 432217, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.044919729232788, "global_step": 432218, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.108943462371826, "global_step": 432219, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0557663440704346, "global_step": 432220, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1360321044921875, "global_step": 432221, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.112701654434204, "global_step": 432222, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0969860553741455, "global_step": 432223, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0677762031555176, "global_step": 432224, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9845588207244873, "global_step": 432225, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0451653003692627, "global_step": 432226, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.02584171295166, "global_step": 432227, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0699007511138916, "global_step": 432228, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.073745012283325, "global_step": 432229, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1383326053619385, "global_step": 432230, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0834364891052246, "global_step": 432231, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0840232372283936, "global_step": 432232, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0162360668182373, "global_step": 432233, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1036736965179443, "global_step": 432234, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.192540168762207, "global_step": 432235, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.092461109161377, "global_step": 432236, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.061967611312866, "global_step": 432237, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1514625549316406, "global_step": 432238, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1222636699676514, "global_step": 432239, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.99996018409729, "global_step": 432240, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1819405555725098, "global_step": 432241, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.001774311065674, "global_step": 432242, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.125079393386841, "global_step": 432243, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0713443756103516, "global_step": 432244, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0502023696899414, "global_step": 432245, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0481786727905273, "global_step": 432246, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.094912528991699, "global_step": 432247, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1421091556549072, "global_step": 432248, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.053445339202881, "global_step": 432249, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1499972343444824, "global_step": 432250, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.112696886062622, "global_step": 432251, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.037525177001953, "global_step": 432252, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.095372438430786, "global_step": 432253, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.128892183303833, "global_step": 432254, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.089804172515869, "global_step": 432255, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0151615142822266, "global_step": 432256, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1115012168884277, "global_step": 432257, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.005983591079712, "global_step": 432258, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.117170810699463, "global_step": 432259, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0671298503875732, "global_step": 432260, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0780155658721924, "global_step": 432261, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0989718437194824, "global_step": 432262, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.082376480102539, "global_step": 432263, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.059328556060791, "global_step": 432264, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1227164268493652, "global_step": 432265, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.151918411254883, "global_step": 432266, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.099679946899414, "global_step": 432267, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.119521379470825, "global_step": 432268, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0704379081726074, "global_step": 432269, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.065298557281494, "global_step": 432270, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1378564834594727, "global_step": 432271, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1172690391540527, "global_step": 432272, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.110767126083374, "global_step": 432273, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0042786598205566, "global_step": 432274, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.05867075920105, "global_step": 432275, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.145454168319702, "global_step": 432276, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1103622913360596, "global_step": 432277, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1557259559631348, "global_step": 432278, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1357309818267822, "global_step": 432279, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0227620601654053, "global_step": 432280, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0557405948638916, "global_step": 432281, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.165992259979248, "global_step": 432282, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.118683338165283, "global_step": 432283, "epoch": 795, "lr": 5e-05}
{"train_loss": 1.9849625825881958, "global_step": 432284, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.055516004562378, "global_step": 432285, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.153012275695801, "global_step": 432286, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1690306663513184, "global_step": 432287, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0515899658203125, "global_step": 432288, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.051884651184082, "global_step": 432289, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.147081136703491, "global_step": 432290, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1533443927764893, "global_step": 432291, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0999393463134766, "global_step": 432292, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0070250034332275, "global_step": 432293, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1103012561798096, "global_step": 432294, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.054732322692871, "global_step": 432295, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1256697177886963, "global_step": 432296, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1189584732055664, "global_step": 432297, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0466811656951904, "global_step": 432298, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.159087896347046, "global_step": 432299, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.091052532196045, "global_step": 432300, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.101438045501709, "global_step": 432301, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0640366077423096, "global_step": 432302, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.1254358291625977, "global_step": 432303, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.160627841949463, "global_step": 432304, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0241851806640625, "global_step": 432305, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0822136402130127, "global_step": 432306, "epoch": 795, "lr": 5e-05}
{"train_loss": 2.0508358478546143, "global_step": 432307, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0282912254333496, "global_step": 432308, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1065051555633545, "global_step": 432309, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.048888683319092, "global_step": 432310, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9934371709823608, "global_step": 432311, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.067296028137207, "global_step": 432312, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.02653169631958, "global_step": 432313, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.085238218307495, "global_step": 432314, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.083045721054077, "global_step": 432315, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0894815921783447, "global_step": 432316, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1178531646728516, "global_step": 432317, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.015056848526001, "global_step": 432318, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.013953447341919, "global_step": 432319, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.085524797439575, "global_step": 432320, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0261871814727783, "global_step": 432321, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.148681640625, "global_step": 432322, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.081663131713867, "global_step": 432323, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1077983379364014, "global_step": 432324, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.046984910964966, "global_step": 432325, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1500699520111084, "global_step": 432326, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0941386222839355, "global_step": 432327, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0402276515960693, "global_step": 432328, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.099945306777954, "global_step": 432329, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0679471492767334, "global_step": 432330, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.088494062423706, "global_step": 432331, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9896551370620728, "global_step": 432332, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1745951175689697, "global_step": 432333, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0584380626678467, "global_step": 432334, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.099271774291992, "global_step": 432335, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0534448623657227, "global_step": 432336, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0861306190490723, "global_step": 432337, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1132144927978516, "global_step": 432338, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.031198501586914, "global_step": 432339, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.114154815673828, "global_step": 432340, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0077402591705322, "global_step": 432341, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1547865867614746, "global_step": 432342, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.093353033065796, "global_step": 432343, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.114109992980957, "global_step": 432344, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0810892581939697, "global_step": 432345, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0466673374176025, "global_step": 432346, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1230082511901855, "global_step": 432347, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0559964179992676, "global_step": 432348, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1160929203033447, "global_step": 432349, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0477774143218994, "global_step": 432350, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.094571590423584, "global_step": 432351, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9980722665786743, "global_step": 432352, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0967471599578857, "global_step": 432353, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.056464910507202, "global_step": 432354, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.041018486022949, "global_step": 432355, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.128574848175049, "global_step": 432356, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0404415130615234, "global_step": 432357, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1634411811828613, "global_step": 432358, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1422066688537598, "global_step": 432359, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.147479772567749, "global_step": 432360, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1253254413604736, "global_step": 432361, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1648683547973633, "global_step": 432362, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.035362720489502, "global_step": 432363, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0921194553375244, "global_step": 432364, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.156524658203125, "global_step": 432365, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.009636878967285, "global_step": 432366, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.006772756576538, "global_step": 432367, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.131267547607422, "global_step": 432368, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0671916007995605, "global_step": 432369, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.143773317337036, "global_step": 432370, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1191296577453613, "global_step": 432371, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0425431728363037, "global_step": 432372, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0531468391418457, "global_step": 432373, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0669095516204834, "global_step": 432374, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.119014263153076, "global_step": 432375, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1295700073242188, "global_step": 432376, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0675137042999268, "global_step": 432377, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.10461163520813, "global_step": 432378, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.128490447998047, "global_step": 432379, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0945749282836914, "global_step": 432380, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0172598361968994, "global_step": 432381, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.07173490524292, "global_step": 432382, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.055586338043213, "global_step": 432383, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0875637531280518, "global_step": 432384, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.03875732421875, "global_step": 432385, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.107182502746582, "global_step": 432386, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1127777099609375, "global_step": 432387, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.05366849899292, "global_step": 432388, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1245486736297607, "global_step": 432389, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.114421844482422, "global_step": 432390, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1085445880889893, "global_step": 432391, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1212472915649414, "global_step": 432392, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0892903804779053, "global_step": 432393, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0457077026367188, "global_step": 432394, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.022365093231201, "global_step": 432395, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.122591972351074, "global_step": 432396, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0891237258911133, "global_step": 432397, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.152233839035034, "global_step": 432398, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1621787548065186, "global_step": 432399, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9973729848861694, "global_step": 432400, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.055408477783203, "global_step": 432401, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.952380657196045, "global_step": 432402, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.05306077003479, "global_step": 432403, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1079792976379395, "global_step": 432404, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.065420389175415, "global_step": 432405, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0432441234588623, "global_step": 432406, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0397632122039795, "global_step": 432407, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1434974670410156, "global_step": 432408, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0929858684539795, "global_step": 432409, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.044740676879883, "global_step": 432410, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.127285957336426, "global_step": 432411, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0940709114074707, "global_step": 432412, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0583207607269287, "global_step": 432413, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.104792833328247, "global_step": 432414, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0964765548706055, "global_step": 432415, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0511984825134277, "global_step": 432416, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.177222728729248, "global_step": 432417, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0900092124938965, "global_step": 432418, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9889947175979614, "global_step": 432419, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.135615825653076, "global_step": 432420, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.074921131134033, "global_step": 432421, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1028738021850586, "global_step": 432422, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.033079147338867, "global_step": 432423, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.095459222793579, "global_step": 432424, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0857529640197754, "global_step": 432425, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0879499912261963, "global_step": 432426, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.000180244445801, "global_step": 432427, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0305583477020264, "global_step": 432428, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0912837982177734, "global_step": 432429, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.083251953125, "global_step": 432430, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0455853939056396, "global_step": 432431, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.126765489578247, "global_step": 432432, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0874550342559814, "global_step": 432433, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.013936758041382, "global_step": 432434, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0653114318847656, "global_step": 432435, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0734968185424805, "global_step": 432436, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.04780912399292, "global_step": 432437, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.059906244277954, "global_step": 432438, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0789806842803955, "global_step": 432439, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1316287517547607, "global_step": 432440, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1073641777038574, "global_step": 432441, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.004415273666382, "global_step": 432442, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.089467763900757, "global_step": 432443, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.128558874130249, "global_step": 432444, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1286368370056152, "global_step": 432445, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.041304349899292, "global_step": 432446, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.095191717147827, "global_step": 432447, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.106034278869629, "global_step": 432448, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0260143280029297, "global_step": 432449, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.082005262374878, "global_step": 432450, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0860023498535156, "global_step": 432451, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0306215286254883, "global_step": 432452, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1191351413726807, "global_step": 432453, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0413527488708496, "global_step": 432454, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0957534313201904, "global_step": 432455, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9770641326904297, "global_step": 432456, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0640602111816406, "global_step": 432457, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1012210845947266, "global_step": 432458, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.056151866912842, "global_step": 432459, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1051459312438965, "global_step": 432460, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.068847179412842, "global_step": 432461, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.040320634841919, "global_step": 432462, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.068934679031372, "global_step": 432463, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.115023136138916, "global_step": 432464, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0965561866760254, "global_step": 432465, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0673046112060547, "global_step": 432466, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.101733684539795, "global_step": 432467, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.099134922027588, "global_step": 432468, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0083699226379395, "global_step": 432469, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0909197330474854, "global_step": 432470, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.04323410987854, "global_step": 432471, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9888564348220825, "global_step": 432472, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1210899353027344, "global_step": 432473, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1336655616760254, "global_step": 432474, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.216031074523926, "global_step": 432475, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1698102951049805, "global_step": 432476, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0621609687805176, "global_step": 432477, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.09302020072937, "global_step": 432478, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1435153484344482, "global_step": 432479, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.126760959625244, "global_step": 432480, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.2192249298095703, "global_step": 432481, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0099847316741943, "global_step": 432482, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1110854148864746, "global_step": 432483, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0240375995635986, "global_step": 432484, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0013599395751953, "global_step": 432485, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.008552312850952, "global_step": 432486, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.02337384223938, "global_step": 432487, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.996566653251648, "global_step": 432488, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0200023651123047, "global_step": 432489, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1155483722686768, "global_step": 432490, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.032027006149292, "global_step": 432491, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0356311798095703, "global_step": 432492, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0151400566101074, "global_step": 432493, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.03082275390625, "global_step": 432494, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0431714057922363, "global_step": 432495, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.066993236541748, "global_step": 432496, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1084868907928467, "global_step": 432497, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.014216899871826, "global_step": 432498, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1035304069519043, "global_step": 432499, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.134016513824463, "global_step": 432500, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0714311599731445, "global_step": 432501, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.161118507385254, "global_step": 432502, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0806148052215576, "global_step": 432503, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0977511405944824, "global_step": 432504, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.02274489402771, "global_step": 432505, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.070230007171631, "global_step": 432506, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.080090045928955, "global_step": 432507, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.072901725769043, "global_step": 432508, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0785202980041504, "global_step": 432509, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1225905418395996, "global_step": 432510, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0584139823913574, "global_step": 432511, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.160856246948242, "global_step": 432512, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.04571533203125, "global_step": 432513, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.034430980682373, "global_step": 432514, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0809850692749023, "global_step": 432515, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1003482341766357, "global_step": 432516, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1687753200531006, "global_step": 432517, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.095926284790039, "global_step": 432518, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0452351570129395, "global_step": 432519, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9996891021728516, "global_step": 432520, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.068748950958252, "global_step": 432521, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1079187393188477, "global_step": 432522, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.075147867202759, "global_step": 432523, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0642035007476807, "global_step": 432524, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.106508731842041, "global_step": 432525, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.074723958969116, "global_step": 432526, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.037266969680786, "global_step": 432527, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.033243179321289, "global_step": 432528, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0978810787200928, "global_step": 432529, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1404731273651123, "global_step": 432530, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.142176389694214, "global_step": 432531, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0657448768615723, "global_step": 432532, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0968356132507324, "global_step": 432533, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0251879692077637, "global_step": 432534, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.161489486694336, "global_step": 432535, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.130917549133301, "global_step": 432536, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1315953731536865, "global_step": 432537, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1177103519439697, "global_step": 432538, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0453832149505615, "global_step": 432539, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9790409803390503, "global_step": 432540, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.063664436340332, "global_step": 432541, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0207555294036865, "global_step": 432542, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0089361667633057, "global_step": 432543, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1457180976867676, "global_step": 432544, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0400490760803223, "global_step": 432545, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.042586088180542, "global_step": 432546, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.054368019104004, "global_step": 432547, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.176243305206299, "global_step": 432548, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0670554637908936, "global_step": 432549, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9968370199203491, "global_step": 432550, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0906982421875, "global_step": 432551, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0695791244506836, "global_step": 432552, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.073683738708496, "global_step": 432553, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.037442207336426, "global_step": 432554, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1146304607391357, "global_step": 432555, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.074805498123169, "global_step": 432556, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0537948608398438, "global_step": 432557, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.044557571411133, "global_step": 432558, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1020750999450684, "global_step": 432559, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0783300399780273, "global_step": 432560, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9990404844284058, "global_step": 432561, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9945439100265503, "global_step": 432562, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.056058645248413, "global_step": 432563, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9901843070983887, "global_step": 432564, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0640575885772705, "global_step": 432565, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0589375495910645, "global_step": 432566, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.131600856781006, "global_step": 432567, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0824546813964844, "global_step": 432568, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.03718638420105, "global_step": 432569, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0797111988067627, "global_step": 432570, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.117870807647705, "global_step": 432571, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.133978843688965, "global_step": 432572, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.087085008621216, "global_step": 432573, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1155810356140137, "global_step": 432574, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0077285766601562, "global_step": 432575, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.092013359069824, "global_step": 432576, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.067901849746704, "global_step": 432577, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0820019245147705, "global_step": 432578, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.092569351196289, "global_step": 432579, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.139353036880493, "global_step": 432580, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.137545585632324, "global_step": 432581, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0560953617095947, "global_step": 432582, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.119403123855591, "global_step": 432583, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0965442657470703, "global_step": 432584, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.151961088180542, "global_step": 432585, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.2085235118865967, "global_step": 432586, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.061140537261963, "global_step": 432587, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.003533363342285, "global_step": 432588, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0903971195220947, "global_step": 432589, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9341399669647217, "global_step": 432590, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.091708183288574, "global_step": 432591, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.969842553138733, "global_step": 432592, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.2117557525634766, "global_step": 432593, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1101603507995605, "global_step": 432594, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.038316249847412, "global_step": 432595, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.07751202583313, "global_step": 432596, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0965564250946045, "global_step": 432597, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0996298789978027, "global_step": 432598, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.07645583152771, "global_step": 432599, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9856510162353516, "global_step": 432600, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.152890920639038, "global_step": 432601, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.14475417137146, "global_step": 432602, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0461976528167725, "global_step": 432603, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1870691776275635, "global_step": 432604, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.056009531021118, "global_step": 432605, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.088806390762329, "global_step": 432606, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.006718397140503, "global_step": 432607, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.039412260055542, "global_step": 432608, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.051769733428955, "global_step": 432609, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0805556774139404, "global_step": 432610, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.030174732208252, "global_step": 432611, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9718310832977295, "global_step": 432612, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0746946334838867, "global_step": 432613, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0743794441223145, "global_step": 432614, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1304354667663574, "global_step": 432615, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.003061056137085, "global_step": 432616, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.064349412918091, "global_step": 432617, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0812325477600098, "global_step": 432618, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9903804063796997, "global_step": 432619, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.072950839996338, "global_step": 432620, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.136911630630493, "global_step": 432621, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1333229541778564, "global_step": 432622, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.061537981033325, "global_step": 432623, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1477959156036377, "global_step": 432624, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.115124225616455, "global_step": 432625, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.065225124359131, "global_step": 432626, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.107536792755127, "global_step": 432627, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.065201997756958, "global_step": 432628, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1247079372406006, "global_step": 432629, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0378055572509766, "global_step": 432630, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0535049438476562, "global_step": 432631, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0665700435638428, "global_step": 432632, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1437156200408936, "global_step": 432633, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.086277961730957, "global_step": 432634, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0835678577423096, "global_step": 432635, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.104362964630127, "global_step": 432636, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0319759845733643, "global_step": 432637, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.009303331375122, "global_step": 432638, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0781919956207275, "global_step": 432639, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1377761363983154, "global_step": 432640, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.04172945022583, "global_step": 432641, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0340991020202637, "global_step": 432642, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.047487258911133, "global_step": 432643, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.10650372505188, "global_step": 432644, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1026291847229004, "global_step": 432645, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1502685546875, "global_step": 432646, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.129882574081421, "global_step": 432647, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.151958703994751, "global_step": 432648, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0814032554626465, "global_step": 432649, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0201785564422607, "global_step": 432650, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.003267288208008, "global_step": 432651, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0948383808135986, "global_step": 432652, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0670065879821777, "global_step": 432653, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0545761585235596, "global_step": 432654, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0525736808776855, "global_step": 432655, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1630256175994873, "global_step": 432656, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1147348880767822, "global_step": 432657, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9987854957580566, "global_step": 432658, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0396411418914795, "global_step": 432659, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0250275135040283, "global_step": 432660, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.109445571899414, "global_step": 432661, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0705089569091797, "global_step": 432662, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0090394020080566, "global_step": 432663, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0196053981781006, "global_step": 432664, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1406097412109375, "global_step": 432665, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0125651359558105, "global_step": 432666, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.058429002761841, "global_step": 432667, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0493972301483154, "global_step": 432668, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1422274112701416, "global_step": 432669, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.138436794281006, "global_step": 432670, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.047234058380127, "global_step": 432671, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.098268747329712, "global_step": 432672, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0842416286468506, "global_step": 432673, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.03289794921875, "global_step": 432674, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.118549346923828, "global_step": 432675, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0778961181640625, "global_step": 432676, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.121962785720825, "global_step": 432677, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0823047161102295, "global_step": 432678, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0136125087738037, "global_step": 432679, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1343154907226562, "global_step": 432680, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0854015350341797, "global_step": 432681, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9844452142715454, "global_step": 432682, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0440585613250732, "global_step": 432683, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0669145584106445, "global_step": 432684, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0741024017333984, "global_step": 432685, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1077542304992676, "global_step": 432686, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1061739921569824, "global_step": 432687, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0787606239318848, "global_step": 432688, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1237618923187256, "global_step": 432689, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.965023159980774, "global_step": 432690, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0285229682922363, "global_step": 432691, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0850698947906494, "global_step": 432692, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0929911136627197, "global_step": 432693, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0442628860473633, "global_step": 432694, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0937836170196533, "global_step": 432695, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0756146907806396, "global_step": 432696, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.127875328063965, "global_step": 432697, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.068183183670044, "global_step": 432698, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1338765621185303, "global_step": 432699, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0898311138153076, "global_step": 432700, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.073273181915283, "global_step": 432701, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0996077060699463, "global_step": 432702, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0848658084869385, "global_step": 432703, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.088587522506714, "global_step": 432704, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.182957410812378, "global_step": 432705, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1692655086517334, "global_step": 432706, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0255520343780518, "global_step": 432707, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1869280338287354, "global_step": 432708, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.2639646530151367, "global_step": 432709, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0632693767547607, "global_step": 432710, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1191365718841553, "global_step": 432711, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1476142406463623, "global_step": 432712, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0941264629364014, "global_step": 432713, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.141599178314209, "global_step": 432714, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9602831602096558, "global_step": 432715, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.132600784301758, "global_step": 432716, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0934102535247803, "global_step": 432717, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0609018802642822, "global_step": 432718, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0955076217651367, "global_step": 432719, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1169326305389404, "global_step": 432720, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.104893445968628, "global_step": 432721, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.044783592224121, "global_step": 432722, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0965795516967773, "global_step": 432723, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.026336669921875, "global_step": 432724, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1542227268218994, "global_step": 432725, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0889241695404053, "global_step": 432726, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.154642343521118, "global_step": 432727, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0631017684936523, "global_step": 432728, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0399839878082275, "global_step": 432729, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.166329860687256, "global_step": 432730, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.057245969772339, "global_step": 432731, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.056715488433838, "global_step": 432732, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.035134792327881, "global_step": 432733, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1078619956970215, "global_step": 432734, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0963754653930664, "global_step": 432735, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0182912349700928, "global_step": 432736, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1076695919036865, "global_step": 432737, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0522725582122803, "global_step": 432738, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.089203119277954, "global_step": 432739, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.066284656524658, "global_step": 432740, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1232759952545166, "global_step": 432741, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.102154493331909, "global_step": 432742, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0694003105163574, "global_step": 432743, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0418648719787598, "global_step": 432744, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.073859930038452, "global_step": 432745, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0906574726104736, "global_step": 432746, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.070338010787964, "global_step": 432747, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.113308906555176, "global_step": 432748, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1001970767974854, "global_step": 432749, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.082221269607544, "global_step": 432750, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0646562576293945, "global_step": 432751, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9933782815933228, "global_step": 432752, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.13922381401062, "global_step": 432753, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.149949550628662, "global_step": 432754, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1542391777038574, "global_step": 432755, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.998497486114502, "global_step": 432756, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0633814334869385, "global_step": 432757, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0410547256469727, "global_step": 432758, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.184030532836914, "global_step": 432759, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1010191440582275, "global_step": 432760, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0064709186553955, "global_step": 432761, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0407187938690186, "global_step": 432762, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.057652235031128, "global_step": 432763, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0630171298980713, "global_step": 432764, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.107466697692871, "global_step": 432765, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0614936351776123, "global_step": 432766, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0409140586853027, "global_step": 432767, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9801896810531616, "global_step": 432768, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0440099239349365, "global_step": 432769, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0655486583709717, "global_step": 432770, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0570755004882812, "global_step": 432771, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.081066370010376, "global_step": 432772, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0319159030914307, "global_step": 432773, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1226651668548584, "global_step": 432774, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0705246925354004, "global_step": 432775, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.024691581726074, "global_step": 432776, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.04129695892334, "global_step": 432777, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0748324394226074, "global_step": 432778, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1383700370788574, "global_step": 432779, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0925815105438232, "global_step": 432780, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0953400135040283, "global_step": 432781, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.179337978363037, "global_step": 432782, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.047537088394165, "global_step": 432783, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.05460262298584, "global_step": 432784, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9719518423080444, "global_step": 432785, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.059527635574341, "global_step": 432786, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.093503475189209, "global_step": 432787, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.060145854949951, "global_step": 432788, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.090231418609619, "global_step": 432789, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0266737937927246, "global_step": 432790, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1383049488067627, "global_step": 432791, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.045611619949341, "global_step": 432792, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1403729915618896, "global_step": 432793, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1158812046051025, "global_step": 432794, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0670409202575684, "global_step": 432795, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0484230518341064, "global_step": 432796, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.157322406768799, "global_step": 432797, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0701773166656494, "global_step": 432798, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1225032806396484, "global_step": 432799, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.08278751373291, "global_step": 432800, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0561630725860596, "global_step": 432801, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9814894199371338, "global_step": 432802, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0804550647735596, "global_step": 432803, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0943853855133057, "global_step": 432804, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0393288135528564, "global_step": 432805, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.029484748840332, "global_step": 432806, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0203094482421875, "global_step": 432807, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0454399585723877, "global_step": 432808, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1047234535217285, "global_step": 432809, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1201539039611816, "global_step": 432810, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.093568801879883, "global_step": 432811, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0713393688201904, "global_step": 432812, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1370301246643066, "global_step": 432813, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.161482572555542, "global_step": 432814, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0565648078918457, "global_step": 432815, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.161487579345703, "global_step": 432816, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.07356595993042, "global_step": 432817, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0808990001678467, "global_step": 432818, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.00050950050354, "global_step": 432819, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1527934074401855, "global_step": 432820, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1097359657287598, "global_step": 432821, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.074378252029419, "global_step": 432822, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.061960220336914, "global_step": 432823, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1305899620056152, "global_step": 432824, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0816197395324707, "global_step": 432825, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0240345001220703, "global_step": 432826, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0725221633911133, "global_step": 432827, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0448241233825684, "global_step": 432828, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0201051235198975, "global_step": 432829, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1969635486602783, "global_step": 432830, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1136562824249268, "global_step": 432831, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1536734104156494, "global_step": 432832, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.101362705230713, "global_step": 432833, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0683627128601074, "global_step": 432834, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0958893299102783, "global_step": 432835, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.072944402694702, "global_step": 432836, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0556490421295166, "global_step": 432837, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1047236919403076, "global_step": 432838, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1269264221191406, "global_step": 432839, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0792455673217773, "global_step": 432840, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0873382091522217, "global_step": 432841, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.084851026535034, "global_step": 432842, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1393580436706543, "global_step": 432843, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.101743459701538, "global_step": 432844, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1358375549316406, "global_step": 432845, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.043813705444336, "global_step": 432846, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1074156761169434, "global_step": 432847, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.083076000213623, "global_step": 432848, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1042776107788086, "global_step": 432849, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.081472635269165, "global_step": 432850, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1084511280059814, "global_step": 432851, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0701138973236084, "global_step": 432852, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.2341525554656982, "global_step": 432853, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1323931217193604, "global_step": 432854, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0129151344299316, "global_step": 432855, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.044358730316162, "global_step": 432856, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1491377353668213, "global_step": 432857, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0571236610412598, "global_step": 432858, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.059892177581787, "global_step": 432859, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0626654624938965, "global_step": 432860, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0585901737213135, "global_step": 432861, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.109941005706787, "global_step": 432862, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0708096027374268, "global_step": 432863, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.109278917312622, "global_step": 432864, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.086770534515381, "global_step": 432865, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0091419219970703, "global_step": 432866, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.139881134033203, "global_step": 432867, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0885977745056152, "global_step": 432868, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0844950675964355, "global_step": 432869, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9956185817718506, "global_step": 432870, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0921976566314697, "global_step": 432871, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.148467779159546, "global_step": 432872, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0842881202697754, "global_step": 432873, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0602974891662598, "global_step": 432874, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0959632396698, "global_step": 432875, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0410304069519043, "global_step": 432876, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0317678451538086, "global_step": 432877, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1131200790405273, "global_step": 432878, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0811829566955566, "global_step": 432879, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0192792415618896, "global_step": 432880, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0566391944885254, "global_step": 432881, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0365962982177734, "global_step": 432882, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0410215854644775, "global_step": 432883, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0944972038269043, "global_step": 432884, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.103630304336548, "global_step": 432885, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0953617095947266, "global_step": 432886, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0319385528564453, "global_step": 432887, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.072885751724243, "global_step": 432888, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0417416095733643, "global_step": 432889, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1854915618896484, "global_step": 432890, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0033581256866455, "global_step": 432891, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9963935613632202, "global_step": 432892, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1068079471588135, "global_step": 432893, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1001524925231934, "global_step": 432894, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1297550201416016, "global_step": 432895, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0817790031433105, "global_step": 432896, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.105855941772461, "global_step": 432897, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0541305541992188, "global_step": 432898, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0353987216949463, "global_step": 432899, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1614913940429688, "global_step": 432900, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.17071795463562, "global_step": 432901, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.022794246673584, "global_step": 432902, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0899996757507324, "global_step": 432903, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.955124855041504, "global_step": 432904, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0844175815582275, "global_step": 432905, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1384098529815674, "global_step": 432906, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0697362422943115, "global_step": 432907, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0571720600128174, "global_step": 432908, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1276774406433105, "global_step": 432909, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.116084575653076, "global_step": 432910, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.135791063308716, "global_step": 432911, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.107848882675171, "global_step": 432912, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.10884428024292, "global_step": 432913, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0967087745666504, "global_step": 432914, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.166369915008545, "global_step": 432915, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.031482696533203, "global_step": 432916, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.069209337234497, "global_step": 432917, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0679070949554443, "global_step": 432918, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.171752452850342, "global_step": 432919, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0635673999786377, "global_step": 432920, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1312777996063232, "global_step": 432921, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0626468658447266, "global_step": 432922, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1275336742401123, "global_step": 432923, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.137712240219116, "global_step": 432924, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9632174968719482, "global_step": 432925, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0724167823791504, "global_step": 432926, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0973434448242188, "global_step": 432927, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.100532054901123, "global_step": 432928, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.056339979171753, "global_step": 432929, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.063262939453125, "global_step": 432930, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0580990314483643, "global_step": 432931, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1811931133270264, "global_step": 432932, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0165305137634277, "global_step": 432933, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0624501705169678, "global_step": 432934, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.125176429748535, "global_step": 432935, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0375800132751465, "global_step": 432936, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0295135974884033, "global_step": 432937, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.096686363220215, "global_step": 432938, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0234336853027344, "global_step": 432939, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0654702186584473, "global_step": 432940, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.126952886581421, "global_step": 432941, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.091088056564331, "global_step": 432942, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.030259132385254, "global_step": 432943, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.026746988296509, "global_step": 432944, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1573894023895264, "global_step": 432945, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9955458641052246, "global_step": 432946, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0909128189086914, "global_step": 432947, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0341756343841553, "global_step": 432948, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0765113830566406, "global_step": 432949, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.110496997833252, "global_step": 432950, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.155021905899048, "global_step": 432951, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.106865882873535, "global_step": 432952, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.061466693878174, "global_step": 432953, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1906986236572266, "global_step": 432954, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.006118059158325, "global_step": 432955, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.093212842941284, "global_step": 432956, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9672560691833496, "global_step": 432957, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0765576362609863, "global_step": 432958, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0807743072509766, "global_step": 432959, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.139280080795288, "global_step": 432960, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.035388231277466, "global_step": 432961, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.125769853591919, "global_step": 432962, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0480682849884033, "global_step": 432963, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9831782579421997, "global_step": 432964, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0283775329589844, "global_step": 432965, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0738072395324707, "global_step": 432966, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.092317819595337, "global_step": 432967, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.129648447036743, "global_step": 432968, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0993053913116455, "global_step": 432969, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1480445861816406, "global_step": 432970, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0788075923919678, "global_step": 432971, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0759499073028564, "global_step": 432972, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1048388481140137, "global_step": 432973, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1206905841827393, "global_step": 432974, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.082409381866455, "global_step": 432975, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.172438144683838, "global_step": 432976, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1261024475097656, "global_step": 432977, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.098264455795288, "global_step": 432978, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.083627223968506, "global_step": 432979, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9842370748519897, "global_step": 432980, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.997094988822937, "global_step": 432981, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.92041015625, "global_step": 432982, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.158977508544922, "global_step": 432983, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0620172023773193, "global_step": 432984, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.112422227859497, "global_step": 432985, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.087261438369751, "global_step": 432986, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0793721675872803, "global_step": 432987, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.120056629180908, "global_step": 432988, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.079265594482422, "global_step": 432989, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.046968460083008, "global_step": 432990, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.079030752182007, "global_step": 432991, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1439056396484375, "global_step": 432992, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0883865356445312, "global_step": 432993, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.054547071456909, "global_step": 432994, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.15678334236145, "global_step": 432995, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0725996494293213, "global_step": 432996, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.102138042449951, "global_step": 432997, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.066465377807617, "global_step": 432998, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0705907344818115, "global_step": 432999, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.137875556945801, "global_step": 433000, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0948917865753174, "global_step": 433001, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.09806752204895, "global_step": 433002, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0780346393585205, "global_step": 433003, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.041043519973755, "global_step": 433004, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0793297290802, "global_step": 433005, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.140451192855835, "global_step": 433006, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.051344871520996, "global_step": 433007, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.152723550796509, "global_step": 433008, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0932388305664062, "global_step": 433009, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0308024883270264, "global_step": 433010, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.085747718811035, "global_step": 433011, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.067741632461548, "global_step": 433012, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.073723554611206, "global_step": 433013, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0475642681121826, "global_step": 433014, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.102658987045288, "global_step": 433015, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1784822940826416, "global_step": 433016, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0334551334381104, "global_step": 433017, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0393993854522705, "global_step": 433018, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0814309120178223, "global_step": 433019, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.042351484298706, "global_step": 433020, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0805304050445557, "global_step": 433021, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0984511375427246, "global_step": 433022, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.144826650619507, "global_step": 433023, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1198935508728027, "global_step": 433024, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9963408708572388, "global_step": 433025, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.086045503616333, "global_step": 433026, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1230297088623047, "global_step": 433027, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.021575927734375, "global_step": 433028, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.142230749130249, "global_step": 433029, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1497862339019775, "global_step": 433030, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.104480028152466, "global_step": 433031, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.034109115600586, "global_step": 433032, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.065985679626465, "global_step": 433033, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0446605682373047, "global_step": 433034, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0742347240448, "global_step": 433035, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0625057220458984, "global_step": 433036, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.045997142791748, "global_step": 433037, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1202213764190674, "global_step": 433038, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0614588260650635, "global_step": 433039, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.084969997406006, "global_step": 433040, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0849931240081787, "global_step": 433041, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.098886489868164, "global_step": 433042, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0990288257598877, "global_step": 433043, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0522825717926025, "global_step": 433044, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0441668033599854, "global_step": 433045, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0943408012390137, "global_step": 433046, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.101675033569336, "global_step": 433047, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.09639573097229, "global_step": 433048, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.2647242546081543, "global_step": 433049, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1158108711242676, "global_step": 433050, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0245308876037598, "global_step": 433051, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0109970569610596, "global_step": 433052, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0525028705596924, "global_step": 433053, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.033768653869629, "global_step": 433054, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0683605670928955, "global_step": 433055, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.038560390472412, "global_step": 433056, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1078081130981445, "global_step": 433057, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1828722953796387, "global_step": 433058, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0253329277038574, "global_step": 433059, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1033718585968018, "global_step": 433060, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1437084674835205, "global_step": 433061, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1138882637023926, "global_step": 433062, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.12630033493042, "global_step": 433063, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.022179126739502, "global_step": 433064, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0605034828186035, "global_step": 433065, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9862934350967407, "global_step": 433066, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0794851779937744, "global_step": 433067, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0567972660064697, "global_step": 433068, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.020716667175293, "global_step": 433069, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.103835105895996, "global_step": 433070, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0855743885040283, "global_step": 433071, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1182610988616943, "global_step": 433072, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0844614505767822, "global_step": 433073, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9559870958328247, "global_step": 433074, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.10141921043396, "global_step": 433075, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0648698806762695, "global_step": 433076, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.120891809463501, "global_step": 433077, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9482332468032837, "global_step": 433078, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.098621129989624, "global_step": 433079, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0675525665283203, "global_step": 433080, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1877896785736084, "global_step": 433081, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1171300411224365, "global_step": 433082, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.129377603530884, "global_step": 433083, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1344707012176514, "global_step": 433084, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0300979614257812, "global_step": 433085, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.106677532196045, "global_step": 433086, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1115920543670654, "global_step": 433087, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0753977298736572, "global_step": 433088, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.068966865539551, "global_step": 433089, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0507562160491943, "global_step": 433090, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.086998701095581, "global_step": 433091, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.235934019088745, "global_step": 433092, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.070765733718872, "global_step": 433093, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0164523124694824, "global_step": 433094, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0801267623901367, "global_step": 433095, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0603928565979004, "global_step": 433096, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.110227346420288, "global_step": 433097, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0966691970825195, "global_step": 433098, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1297669410705566, "global_step": 433099, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.075774669647217, "global_step": 433100, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.082304000854492, "global_step": 433101, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0234768390655518, "global_step": 433102, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.991611123085022, "global_step": 433103, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.032012701034546, "global_step": 433104, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1682231426239014, "global_step": 433105, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1350035667419434, "global_step": 433106, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1598598957061768, "global_step": 433107, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1306350231170654, "global_step": 433108, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1076555252075195, "global_step": 433109, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0572595596313477, "global_step": 433110, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.086453676223755, "global_step": 433111, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1176657676696777, "global_step": 433112, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.127443313598633, "global_step": 433113, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.159661054611206, "global_step": 433114, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0711374282836914, "global_step": 433115, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.120403289794922, "global_step": 433116, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.085348606109619, "global_step": 433117, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1777384281158447, "global_step": 433118, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1998791694641113, "global_step": 433119, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.140988349914551, "global_step": 433120, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0351197719573975, "global_step": 433121, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1869311332702637, "global_step": 433122, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.114018678665161, "global_step": 433123, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.099987745285034, "global_step": 433124, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0248589515686035, "global_step": 433125, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0428647994995117, "global_step": 433126, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.050358772277832, "global_step": 433127, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.076568126678467, "global_step": 433128, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.07438063621521, "global_step": 433129, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1385462284088135, "global_step": 433130, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1340432167053223, "global_step": 433131, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0957694053649902, "global_step": 433132, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0959863662719727, "global_step": 433133, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.027458667755127, "global_step": 433134, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.090970516204834, "global_step": 433135, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.095590591430664, "global_step": 433136, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0518341064453125, "global_step": 433137, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0608952045440674, "global_step": 433138, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0411782264709473, "global_step": 433139, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.2209153175354004, "global_step": 433140, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1267025470733643, "global_step": 433141, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0779471397399902, "global_step": 433142, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0727269649505615, "global_step": 433143, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1198127269744873, "global_step": 433144, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0303120613098145, "global_step": 433145, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1399834156036377, "global_step": 433146, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0861618518829346, "global_step": 433147, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.105966329574585, "global_step": 433148, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0866763591766357, "global_step": 433149, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.07069730758667, "global_step": 433150, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0607516765594482, "global_step": 433151, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0499556064605713, "global_step": 433152, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.027876615524292, "global_step": 433153, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0706353187561035, "global_step": 433154, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0709218978881836, "global_step": 433155, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0599136352539062, "global_step": 433156, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.078566551208496, "global_step": 433157, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1074962615966797, "global_step": 433158, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1629316806793213, "global_step": 433159, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.078173875808716, "global_step": 433160, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.15435528755188, "global_step": 433161, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1562156677246094, "global_step": 433162, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0537633895874023, "global_step": 433163, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.099486827850342, "global_step": 433164, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9944475889205933, "global_step": 433165, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1389403343200684, "global_step": 433166, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.946704387664795, "global_step": 433167, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.038630723953247, "global_step": 433168, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.07163143157959, "global_step": 433169, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0795135498046875, "global_step": 433170, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.150272846221924, "global_step": 433171, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1066524982452393, "global_step": 433172, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.098853349685669, "global_step": 433173, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0301284790039062, "global_step": 433174, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9755213260650635, "global_step": 433175, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0834577083587646, "global_step": 433176, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0846405029296875, "global_step": 433177, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0301811695098877, "global_step": 433178, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1452343463897705, "global_step": 433179, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1673810482025146, "global_step": 433180, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0699656009674072, "global_step": 433181, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.085761308670044, "global_step": 433182, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.08541202545166, "global_step": 433183, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.103050470352173, "global_step": 433184, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0945911407470703, "global_step": 433185, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.14398455619812, "global_step": 433186, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.036510467529297, "global_step": 433187, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.051595687866211, "global_step": 433188, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1005327701568604, "global_step": 433189, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9532408714294434, "global_step": 433190, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1939198970794678, "global_step": 433191, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.122739791870117, "global_step": 433192, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.107795238494873, "global_step": 433193, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1195905208587646, "global_step": 433194, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1380615234375, "global_step": 433195, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1476993560791016, "global_step": 433196, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1036789417266846, "global_step": 433197, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.066556930541992, "global_step": 433198, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1511502265930176, "global_step": 433199, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.094695806503296, "global_step": 433200, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0877482891082764, "global_step": 433201, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1105093955993652, "global_step": 433202, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1275923252105713, "global_step": 433203, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.081172227859497, "global_step": 433204, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.12886118888855, "global_step": 433205, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0901994705200195, "global_step": 433206, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1332061290740967, "global_step": 433207, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0013692378997803, "global_step": 433208, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0880300998687744, "global_step": 433209, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0690054893493652, "global_step": 433210, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.130218744277954, "global_step": 433211, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.98575758934021, "global_step": 433212, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1042490005493164, "global_step": 433213, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0903708934783936, "global_step": 433214, "epoch": 796, "lr": 5e-05}
{"train_loss": 1.9776694774627686, "global_step": 433215, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1030349731445312, "global_step": 433216, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.039236307144165, "global_step": 433217, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.044914722442627, "global_step": 433218, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.102236747741699, "global_step": 433219, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0801985263824463, "global_step": 433220, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1132068634033203, "global_step": 433221, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.122770071029663, "global_step": 433222, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.108464479446411, "global_step": 433223, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1208152770996094, "global_step": 433224, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.047245502471924, "global_step": 433225, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.075643539428711, "global_step": 433226, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0942013263702393, "global_step": 433227, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.101778745651245, "global_step": 433228, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0262303352355957, "global_step": 433229, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.05364990234375, "global_step": 433230, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1164259910583496, "global_step": 433231, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0877418518066406, "global_step": 433232, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.028679370880127, "global_step": 433233, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.100613832473755, "global_step": 433234, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.061229944229126, "global_step": 433235, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.197084903717041, "global_step": 433236, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0085301399230957, "global_step": 433237, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0852768421173096, "global_step": 433238, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1511731147766113, "global_step": 433239, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.039783477783203, "global_step": 433240, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1499412059783936, "global_step": 433241, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.121185064315796, "global_step": 433242, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.04818058013916, "global_step": 433243, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.163590669631958, "global_step": 433244, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0655429363250732, "global_step": 433245, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1355843544006348, "global_step": 433246, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0898544788360596, "global_step": 433247, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.091134548187256, "global_step": 433248, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1150927543640137, "global_step": 433249, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.095209836959839, "global_step": 433250, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.194854974746704, "global_step": 433251, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0881104469299316, "global_step": 433252, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0812740325927734, "global_step": 433253, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1124181747436523, "global_step": 433254, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.195918083190918, "global_step": 433255, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.047130823135376, "global_step": 433256, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1200358867645264, "global_step": 433257, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1844539642333984, "global_step": 433258, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.071636199951172, "global_step": 433259, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1338202953338623, "global_step": 433260, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.165903329849243, "global_step": 433261, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.112626075744629, "global_step": 433262, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.088239908218384, "global_step": 433263, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1197805404663086, "global_step": 433264, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0475263595581055, "global_step": 433265, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.087174415588379, "global_step": 433266, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.0018768310546875, "global_step": 433267, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1612093448638916, "global_step": 433268, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1242103576660156, "global_step": 433269, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.109757423400879, "global_step": 433270, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.016893148422241, "global_step": 433271, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1862125396728516, "global_step": 433272, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1464099884033203, "global_step": 433273, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.1171419620513916, "global_step": 433274, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.082944393157959, "global_step": 433275, "epoch": 796, "lr": 5e-05}
{"train_loss": 2.062934637069702, "global_step": 433276, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9991408586502075, "global_step": 433277, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0311946868896484, "global_step": 433278, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.98081636428833, "global_step": 433279, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0403661727905273, "global_step": 433280, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.119875192642212, "global_step": 433281, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1136767864227295, "global_step": 433282, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0075809955596924, "global_step": 433283, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9970636367797852, "global_step": 433284, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9770839214324951, "global_step": 433285, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0410144329071045, "global_step": 433286, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9937171936035156, "global_step": 433287, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1411211490631104, "global_step": 433288, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1448757648468018, "global_step": 433289, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0076394081115723, "global_step": 433290, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.044343948364258, "global_step": 433291, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.064729690551758, "global_step": 433292, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9723126888275146, "global_step": 433293, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0214579105377197, "global_step": 433294, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0863394737243652, "global_step": 433295, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0336194038391113, "global_step": 433296, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.077237844467163, "global_step": 433297, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0800788402557373, "global_step": 433298, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.118666410446167, "global_step": 433299, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0440866947174072, "global_step": 433300, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.115455150604248, "global_step": 433301, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0110514163970947, "global_step": 433302, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0846128463745117, "global_step": 433303, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0341525077819824, "global_step": 433304, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0047929286956787, "global_step": 433305, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.983541488647461, "global_step": 433306, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0232152938842773, "global_step": 433307, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.065706491470337, "global_step": 433308, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.088756561279297, "global_step": 433309, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.038861036300659, "global_step": 433310, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0895328521728516, "global_step": 433311, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0682051181793213, "global_step": 433312, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0495805740356445, "global_step": 433313, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0296192169189453, "global_step": 433314, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0718202590942383, "global_step": 433315, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9744120836257935, "global_step": 433316, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1127610206604004, "global_step": 433317, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1399717330932617, "global_step": 433318, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.05629825592041, "global_step": 433319, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1177115440368652, "global_step": 433320, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0756101608276367, "global_step": 433321, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.084975004196167, "global_step": 433322, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.015462636947632, "global_step": 433323, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0872654914855957, "global_step": 433324, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0117945671081543, "global_step": 433325, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1035664081573486, "global_step": 433326, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.099733591079712, "global_step": 433327, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1847281455993652, "global_step": 433328, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.064798593521118, "global_step": 433329, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0393476486206055, "global_step": 433330, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0453262329101562, "global_step": 433331, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1203927993774414, "global_step": 433332, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0674245357513428, "global_step": 433333, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0638017654418945, "global_step": 433334, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.15152907371521, "global_step": 433335, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0775628089904785, "global_step": 433336, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0469141006469727, "global_step": 433337, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0298266410827637, "global_step": 433338, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0325543880462646, "global_step": 433339, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0894622802734375, "global_step": 433340, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0784966945648193, "global_step": 433341, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1275289058685303, "global_step": 433342, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.021667957305908, "global_step": 433343, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0556139945983887, "global_step": 433344, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.168891429901123, "global_step": 433345, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0400850772857666, "global_step": 433346, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.040828227996826, "global_step": 433347, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0116934776306152, "global_step": 433348, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1224803924560547, "global_step": 433349, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0942301750183105, "global_step": 433350, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0904669761657715, "global_step": 433351, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.99752938747406, "global_step": 433352, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.152242422103882, "global_step": 433353, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0447089672088623, "global_step": 433354, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.082507848739624, "global_step": 433355, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.047675371170044, "global_step": 433356, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0300357341766357, "global_step": 433357, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1542162895202637, "global_step": 433358, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.069135904312134, "global_step": 433359, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.146937131881714, "global_step": 433360, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1365983486175537, "global_step": 433361, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.092973232269287, "global_step": 433362, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9713022708892822, "global_step": 433363, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.072955846786499, "global_step": 433364, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1211721897125244, "global_step": 433365, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.028339385986328, "global_step": 433366, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0644259452819824, "global_step": 433367, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.088078737258911, "global_step": 433368, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9937270879745483, "global_step": 433369, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0149893760681152, "global_step": 433370, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1983795166015625, "global_step": 433371, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.060730218887329, "global_step": 433372, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0670979022979736, "global_step": 433373, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1235103607177734, "global_step": 433374, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0813372135162354, "global_step": 433375, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0520176887512207, "global_step": 433376, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.015468120574951, "global_step": 433377, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.073209285736084, "global_step": 433378, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0119407176971436, "global_step": 433379, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.097184181213379, "global_step": 433380, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0557925701141357, "global_step": 433381, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.078765392303467, "global_step": 433382, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.101393222808838, "global_step": 433383, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1419262886047363, "global_step": 433384, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.053483009338379, "global_step": 433385, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.079167604446411, "global_step": 433386, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.032683849334717, "global_step": 433387, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.081561803817749, "global_step": 433388, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0169155597686768, "global_step": 433389, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0447916984558105, "global_step": 433390, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0679376125335693, "global_step": 433391, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.05295467376709, "global_step": 433392, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0654830932617188, "global_step": 433393, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.033903121948242, "global_step": 433394, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.098928213119507, "global_step": 433395, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.176602363586426, "global_step": 433396, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1309638023376465, "global_step": 433397, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0421528816223145, "global_step": 433398, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0589404106140137, "global_step": 433399, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0395395755767822, "global_step": 433400, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.088779926300049, "global_step": 433401, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0153307914733887, "global_step": 433402, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0879573822021484, "global_step": 433403, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0796620845794678, "global_step": 433404, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9978796243667603, "global_step": 433405, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0284016132354736, "global_step": 433406, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.015686511993408, "global_step": 433407, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0513243675231934, "global_step": 433408, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.045673370361328, "global_step": 433409, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.118408679962158, "global_step": 433410, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0783283710479736, "global_step": 433411, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0765604972839355, "global_step": 433412, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0448455810546875, "global_step": 433413, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.105243682861328, "global_step": 433414, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1543023586273193, "global_step": 433415, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0170528888702393, "global_step": 433416, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1041276454925537, "global_step": 433417, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.064518451690674, "global_step": 433418, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.08296537399292, "global_step": 433419, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.061065196990967, "global_step": 433420, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9324586391448975, "global_step": 433421, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.122462034225464, "global_step": 433422, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0379273891448975, "global_step": 433423, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9989606142044067, "global_step": 433424, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.13736629486084, "global_step": 433425, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1743667125701904, "global_step": 433426, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1181588172912598, "global_step": 433427, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.021364450454712, "global_step": 433428, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9405524730682373, "global_step": 433429, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0477662086486816, "global_step": 433430, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.02718186378479, "global_step": 433431, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.064441442489624, "global_step": 433432, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.078545331954956, "global_step": 433433, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0222244262695312, "global_step": 433434, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1923508644104004, "global_step": 433435, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0967414379119873, "global_step": 433436, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0740549564361572, "global_step": 433437, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.029172420501709, "global_step": 433438, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0641918182373047, "global_step": 433439, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.175257444381714, "global_step": 433440, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0805459022521973, "global_step": 433441, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.052117347717285, "global_step": 433442, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0762622356414795, "global_step": 433443, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0994977951049805, "global_step": 433444, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0295486450195312, "global_step": 433445, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0232880115509033, "global_step": 433446, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0926942825317383, "global_step": 433447, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.155040979385376, "global_step": 433448, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.111901044845581, "global_step": 433449, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0558218955993652, "global_step": 433450, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0772669315338135, "global_step": 433451, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.15266752243042, "global_step": 433452, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.994198203086853, "global_step": 433453, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.094060182571411, "global_step": 433454, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0978100299835205, "global_step": 433455, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1136398315429688, "global_step": 433456, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0723445415496826, "global_step": 433457, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9988927841186523, "global_step": 433458, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0181167125701904, "global_step": 433459, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1991004943847656, "global_step": 433460, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0752015113830566, "global_step": 433461, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0527122020721436, "global_step": 433462, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1302645206451416, "global_step": 433463, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1029248237609863, "global_step": 433464, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1658105850219727, "global_step": 433465, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0529680252075195, "global_step": 433466, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.17946720123291, "global_step": 433467, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1263632774353027, "global_step": 433468, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.067312479019165, "global_step": 433469, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0340662002563477, "global_step": 433470, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.062922239303589, "global_step": 433471, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0688838958740234, "global_step": 433472, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.087808847427368, "global_step": 433473, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.083376407623291, "global_step": 433474, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.088157892227173, "global_step": 433475, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9869940280914307, "global_step": 433476, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0593128204345703, "global_step": 433477, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0787465572357178, "global_step": 433478, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1383235454559326, "global_step": 433479, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1175060272216797, "global_step": 433480, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0348126888275146, "global_step": 433481, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1592392921447754, "global_step": 433482, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0238211154937744, "global_step": 433483, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.046259880065918, "global_step": 433484, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.084584951400757, "global_step": 433485, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.996801495552063, "global_step": 433486, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.015075922012329, "global_step": 433487, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.066453456878662, "global_step": 433488, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.062347173690796, "global_step": 433489, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.052567958831787, "global_step": 433490, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1313626766204834, "global_step": 433491, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0961520671844482, "global_step": 433492, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.100503921508789, "global_step": 433493, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.077960968017578, "global_step": 433494, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0792622566223145, "global_step": 433495, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9773560762405396, "global_step": 433496, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.086726665496826, "global_step": 433497, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.03535795211792, "global_step": 433498, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0570268630981445, "global_step": 433499, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.076958656311035, "global_step": 433500, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0503480434417725, "global_step": 433501, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1747119426727295, "global_step": 433502, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1309852600097656, "global_step": 433503, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.14682674407959, "global_step": 433504, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.135817527770996, "global_step": 433505, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9771101474761963, "global_step": 433506, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0773463249206543, "global_step": 433507, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.051514148712158, "global_step": 433508, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0553276538848877, "global_step": 433509, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.072493314743042, "global_step": 433510, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0157361030578613, "global_step": 433511, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0538618564605713, "global_step": 433512, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0745432376861572, "global_step": 433513, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0574190616607666, "global_step": 433514, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1148757934570312, "global_step": 433515, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.074418306350708, "global_step": 433516, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.116873025894165, "global_step": 433517, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1624178886413574, "global_step": 433518, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.026618480682373, "global_step": 433519, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0787792205810547, "global_step": 433520, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.117980718612671, "global_step": 433521, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0113091468811035, "global_step": 433522, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0628058910369873, "global_step": 433523, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1395115852355957, "global_step": 433524, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.2152116298675537, "global_step": 433525, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0748536586761475, "global_step": 433526, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0746285915374756, "global_step": 433527, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1541404724121094, "global_step": 433528, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.055999755859375, "global_step": 433529, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0328190326690674, "global_step": 433530, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1580846309661865, "global_step": 433531, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1092607975006104, "global_step": 433532, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0440781116485596, "global_step": 433533, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.033539056777954, "global_step": 433534, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.069749116897583, "global_step": 433535, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0979151725769043, "global_step": 433536, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.058868646621704, "global_step": 433537, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.063765287399292, "global_step": 433538, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0715465545654297, "global_step": 433539, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1201343536376953, "global_step": 433540, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.138693332672119, "global_step": 433541, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.069044351577759, "global_step": 433542, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.081803798675537, "global_step": 433543, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0382721424102783, "global_step": 433544, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.117422103881836, "global_step": 433545, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.063185691833496, "global_step": 433546, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1142475605010986, "global_step": 433547, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.155064344406128, "global_step": 433548, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0388267040252686, "global_step": 433549, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.095489978790283, "global_step": 433550, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1444435119628906, "global_step": 433551, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.018314838409424, "global_step": 433552, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.124567747116089, "global_step": 433553, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0050570964813232, "global_step": 433554, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1096532344818115, "global_step": 433555, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0725018978118896, "global_step": 433556, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0045719146728516, "global_step": 433557, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.042766809463501, "global_step": 433558, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.04076886177063, "global_step": 433559, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.066653251647949, "global_step": 433560, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0363564491271973, "global_step": 433561, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0851991176605225, "global_step": 433562, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.111825466156006, "global_step": 433563, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.055752754211426, "global_step": 433564, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0321903228759766, "global_step": 433565, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.099858522415161, "global_step": 433566, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.115351438522339, "global_step": 433567, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0960471630096436, "global_step": 433568, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.024386405944824, "global_step": 433569, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.116893768310547, "global_step": 433570, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1185781955718994, "global_step": 433571, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.111703395843506, "global_step": 433572, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0875349044799805, "global_step": 433573, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0889642238616943, "global_step": 433574, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1034936904907227, "global_step": 433575, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.121511220932007, "global_step": 433576, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0756313800811768, "global_step": 433577, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0650172233581543, "global_step": 433578, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0443177223205566, "global_step": 433579, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.055483341217041, "global_step": 433580, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.120436668395996, "global_step": 433581, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.033068895339966, "global_step": 433582, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.060783624649048, "global_step": 433583, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0544626712799072, "global_step": 433584, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0872509479522705, "global_step": 433585, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.090975761413574, "global_step": 433586, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.961000680923462, "global_step": 433587, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0747430324554443, "global_step": 433588, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1291868686676025, "global_step": 433589, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.131920576095581, "global_step": 433590, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9973291158676147, "global_step": 433591, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1001944541931152, "global_step": 433592, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0661122798919678, "global_step": 433593, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1177000999450684, "global_step": 433594, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1068038940429688, "global_step": 433595, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.112854480743408, "global_step": 433596, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1073014736175537, "global_step": 433597, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0684547424316406, "global_step": 433598, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.135456085205078, "global_step": 433599, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.060239553451538, "global_step": 433600, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.128209114074707, "global_step": 433601, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.017713785171509, "global_step": 433602, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1424667835235596, "global_step": 433603, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0591440200805664, "global_step": 433604, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.114917039871216, "global_step": 433605, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1317338943481445, "global_step": 433606, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.078381299972534, "global_step": 433607, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.051875591278076, "global_step": 433608, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0083491802215576, "global_step": 433609, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.199174642562866, "global_step": 433610, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0813684463500977, "global_step": 433611, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1257755756378174, "global_step": 433612, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.106462001800537, "global_step": 433613, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.13747239112854, "global_step": 433614, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1653411388397217, "global_step": 433615, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0289146900177, "global_step": 433616, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.105591058731079, "global_step": 433617, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.085371255874634, "global_step": 433618, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0857560634613037, "global_step": 433619, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.146716833114624, "global_step": 433620, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.005629777908325, "global_step": 433621, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.996883749961853, "global_step": 433622, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0750350952148438, "global_step": 433623, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.065873861312866, "global_step": 433624, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0356040000915527, "global_step": 433625, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9903712272644043, "global_step": 433626, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0498046875, "global_step": 433627, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0420455932617188, "global_step": 433628, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0512359142303467, "global_step": 433629, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.123018741607666, "global_step": 433630, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0612878799438477, "global_step": 433631, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.086399793624878, "global_step": 433632, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.030503749847412, "global_step": 433633, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.066622257232666, "global_step": 433634, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0182621479034424, "global_step": 433635, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.129936695098877, "global_step": 433636, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0705130100250244, "global_step": 433637, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.039098024368286, "global_step": 433638, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.097729206085205, "global_step": 433639, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1180596351623535, "global_step": 433640, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1107985973358154, "global_step": 433641, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.061539888381958, "global_step": 433642, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9530750513076782, "global_step": 433643, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0777881145477295, "global_step": 433644, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.147740364074707, "global_step": 433645, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.095637321472168, "global_step": 433646, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1011428833007812, "global_step": 433647, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.078990936279297, "global_step": 433648, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9555251598358154, "global_step": 433649, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0901408195495605, "global_step": 433650, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9990456104278564, "global_step": 433651, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1687800884246826, "global_step": 433652, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0891642570495605, "global_step": 433653, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.124518871307373, "global_step": 433654, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0415775775909424, "global_step": 433655, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0770533084869385, "global_step": 433656, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1660704612731934, "global_step": 433657, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1579482555389404, "global_step": 433658, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.033458948135376, "global_step": 433659, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0247750282287598, "global_step": 433660, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.079773426055908, "global_step": 433661, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0663561820983887, "global_step": 433662, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0868849754333496, "global_step": 433663, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0889179706573486, "global_step": 433664, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.105823040008545, "global_step": 433665, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.100370168685913, "global_step": 433666, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.07149076461792, "global_step": 433667, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1962971687316895, "global_step": 433668, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0444796085357666, "global_step": 433669, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9723345041275024, "global_step": 433670, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0365991592407227, "global_step": 433671, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0675172805786133, "global_step": 433672, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0702474117279053, "global_step": 433673, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9831312894821167, "global_step": 433674, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.130002498626709, "global_step": 433675, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.059227228164673, "global_step": 433676, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0404887199401855, "global_step": 433677, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0046300888061523, "global_step": 433678, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0918638706207275, "global_step": 433679, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0674474239349365, "global_step": 433680, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0273633003234863, "global_step": 433681, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1506290435791016, "global_step": 433682, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0980710983276367, "global_step": 433683, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.098294973373413, "global_step": 433684, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0189218521118164, "global_step": 433685, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0633788108825684, "global_step": 433686, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0314929485321045, "global_step": 433687, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.154927968978882, "global_step": 433688, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0158467292785645, "global_step": 433689, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.178156614303589, "global_step": 433690, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.084317207336426, "global_step": 433691, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0607120990753174, "global_step": 433692, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.021299123764038, "global_step": 433693, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0931429862976074, "global_step": 433694, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0152804851531982, "global_step": 433695, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0626211166381836, "global_step": 433696, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.081833600997925, "global_step": 433697, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0354039669036865, "global_step": 433698, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.089320182800293, "global_step": 433699, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.072284460067749, "global_step": 433700, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1139001846313477, "global_step": 433701, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0692055225372314, "global_step": 433702, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0638833045959473, "global_step": 433703, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.006242275238037, "global_step": 433704, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9937324523925781, "global_step": 433705, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0580878257751465, "global_step": 433706, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0134904384613037, "global_step": 433707, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.102954149246216, "global_step": 433708, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.066690683364868, "global_step": 433709, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1395318508148193, "global_step": 433710, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1286089420318604, "global_step": 433711, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.146155834197998, "global_step": 433712, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.023869514465332, "global_step": 433713, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0799741744995117, "global_step": 433714, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0267348289489746, "global_step": 433715, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.113180160522461, "global_step": 433716, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.059803009033203, "global_step": 433717, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0801279544830322, "global_step": 433718, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1058714389801025, "global_step": 433719, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0724904537200928, "global_step": 433720, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.084455728530884, "global_step": 433721, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1058106422424316, "global_step": 433722, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0558595657348633, "global_step": 433723, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9734740257263184, "global_step": 433724, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.986496925354004, "global_step": 433725, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.114854574203491, "global_step": 433726, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0517234802246094, "global_step": 433727, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1034843921661377, "global_step": 433728, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.086589813232422, "global_step": 433729, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1548001766204834, "global_step": 433730, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0533549785614014, "global_step": 433731, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1654186248779297, "global_step": 433732, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.092337131500244, "global_step": 433733, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0405771732330322, "global_step": 433734, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.186598062515259, "global_step": 433735, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0504796504974365, "global_step": 433736, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0762100219726562, "global_step": 433737, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1502792835235596, "global_step": 433738, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.157729148864746, "global_step": 433739, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.060304641723633, "global_step": 433740, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.102414131164551, "global_step": 433741, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.028683662414551, "global_step": 433742, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0922768115997314, "global_step": 433743, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0556840896606445, "global_step": 433744, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9659042358398438, "global_step": 433745, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.034707546234131, "global_step": 433746, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0225775241851807, "global_step": 433747, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.156125783920288, "global_step": 433748, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.079326868057251, "global_step": 433749, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.006986141204834, "global_step": 433750, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0844414234161377, "global_step": 433751, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.101226329803467, "global_step": 433752, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0780370235443115, "global_step": 433753, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0356526374816895, "global_step": 433754, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.130317449569702, "global_step": 433755, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0768039226531982, "global_step": 433756, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0637259483337402, "global_step": 433757, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.122972249984741, "global_step": 433758, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.151622772216797, "global_step": 433759, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0927352905273438, "global_step": 433760, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9788498878479004, "global_step": 433761, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.159970283508301, "global_step": 433762, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.069640874862671, "global_step": 433763, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.008110761642456, "global_step": 433764, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1038241386413574, "global_step": 433765, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9930672645568848, "global_step": 433766, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.022754430770874, "global_step": 433767, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9876837730407715, "global_step": 433768, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.112992763519287, "global_step": 433769, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1386706829071045, "global_step": 433770, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.152209997177124, "global_step": 433771, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0664470195770264, "global_step": 433772, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9957759380340576, "global_step": 433773, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0775279998779297, "global_step": 433774, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1034624576568604, "global_step": 433775, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0962648391723633, "global_step": 433776, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.219045877456665, "global_step": 433777, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.081955909729004, "global_step": 433778, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0682175159454346, "global_step": 433779, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.134530782699585, "global_step": 433780, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1182987689971924, "global_step": 433781, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0845093727111816, "global_step": 433782, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.137761354446411, "global_step": 433783, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.057583808898926, "global_step": 433784, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0279619693756104, "global_step": 433785, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.117509126663208, "global_step": 433786, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.011460304260254, "global_step": 433787, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.006103515625, "global_step": 433788, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.103255033493042, "global_step": 433789, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.049034595489502, "global_step": 433790, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.083775758743286, "global_step": 433791, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1245007514953613, "global_step": 433792, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.107964515686035, "global_step": 433793, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0294573307037354, "global_step": 433794, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.096510887145996, "global_step": 433795, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0577893257141113, "global_step": 433796, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0686490535736084, "global_step": 433797, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1406726837158203, "global_step": 433798, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0322866439819336, "global_step": 433799, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.067180633544922, "global_step": 433800, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.122401475906372, "global_step": 433801, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.145721435546875, "global_step": 433802, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.088552951812744, "global_step": 433803, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.064213752746582, "global_step": 433804, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0183825492858887, "global_step": 433805, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0040769577026367, "global_step": 433806, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.067997455596924, "global_step": 433807, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.083320379257202, "global_step": 433808, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1166694164276123, "global_step": 433809, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0873515605926514, "global_step": 433810, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1474151611328125, "global_step": 433811, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1149704456329346, "global_step": 433812, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1349925994873047, "global_step": 433813, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0486972332000732, "global_step": 433814, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1343655586242676, "global_step": 433815, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.085942506790161, "global_step": 433816, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.121187925338745, "global_step": 433817, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.092754602432251, "global_step": 433818, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.084986686706543, "global_step": 433819, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1190707683563232, "global_step": 433820, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.997253656387329, "global_step": 433821, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.081075429916382, "global_step": 433822, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1683597564697266, "global_step": 433823, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1506311893463135, "global_step": 433824, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.038334846496582, "global_step": 433825, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0026445388793945, "global_step": 433826, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.085981845855713, "global_step": 433827, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9970582723617554, "global_step": 433828, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1307082176208496, "global_step": 433829, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.052736759185791, "global_step": 433830, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0584943294525146, "global_step": 433831, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0763657093048096, "global_step": 433832, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0733463764190674, "global_step": 433833, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0685677528381348, "global_step": 433834, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0777852535247803, "global_step": 433835, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.110999584197998, "global_step": 433836, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.119067430496216, "global_step": 433837, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.120717763900757, "global_step": 433838, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.09570050239563, "global_step": 433839, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1511147022247314, "global_step": 433840, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0842642784118652, "global_step": 433841, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.149425983428955, "global_step": 433842, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.089576005935669, "global_step": 433843, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.028900623321533, "global_step": 433844, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.035465955734253, "global_step": 433845, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0597803592681885, "global_step": 433846, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0247578620910645, "global_step": 433847, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1225779056549072, "global_step": 433848, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.046643018722534, "global_step": 433849, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.066882371902466, "global_step": 433850, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.111168622970581, "global_step": 433851, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0859439373016357, "global_step": 433852, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0680088996887207, "global_step": 433853, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0042290687561035, "global_step": 433854, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.170612335205078, "global_step": 433855, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.103192090988159, "global_step": 433856, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0575692653656006, "global_step": 433857, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.2008275985717773, "global_step": 433858, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1309196949005127, "global_step": 433859, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0532374382019043, "global_step": 433860, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0527544021606445, "global_step": 433861, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0287702083587646, "global_step": 433862, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.080479860305786, "global_step": 433863, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.096067428588867, "global_step": 433864, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.043621778488159, "global_step": 433865, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.982118010520935, "global_step": 433866, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.059995412826538, "global_step": 433867, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.143228769302368, "global_step": 433868, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1618704795837402, "global_step": 433869, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.129760980606079, "global_step": 433870, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1617629528045654, "global_step": 433871, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.077239990234375, "global_step": 433872, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.038278579711914, "global_step": 433873, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0982093811035156, "global_step": 433874, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.059751510620117, "global_step": 433875, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.172804117202759, "global_step": 433876, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.034432888031006, "global_step": 433877, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0551164150238037, "global_step": 433878, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1135189533233643, "global_step": 433879, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.094905376434326, "global_step": 433880, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0992136001586914, "global_step": 433881, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.061218023300171, "global_step": 433882, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0222012996673584, "global_step": 433883, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0347774028778076, "global_step": 433884, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.140292167663574, "global_step": 433885, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1249992847442627, "global_step": 433886, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.152526617050171, "global_step": 433887, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1166903972625732, "global_step": 433888, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1080634593963623, "global_step": 433889, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0727901458740234, "global_step": 433890, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.103675603866577, "global_step": 433891, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.115826368331909, "global_step": 433892, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1525447368621826, "global_step": 433893, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0599968433380127, "global_step": 433894, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1352169513702393, "global_step": 433895, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.067138433456421, "global_step": 433896, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1081292629241943, "global_step": 433897, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1032471656799316, "global_step": 433898, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.165454149246216, "global_step": 433899, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.141183376312256, "global_step": 433900, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.095705270767212, "global_step": 433901, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0371649265289307, "global_step": 433902, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1148502826690674, "global_step": 433903, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.082348346710205, "global_step": 433904, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0866127014160156, "global_step": 433905, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.036679983139038, "global_step": 433906, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0265309810638428, "global_step": 433907, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0875399112701416, "global_step": 433908, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0674805641174316, "global_step": 433909, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1396214962005615, "global_step": 433910, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.107964277267456, "global_step": 433911, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0925180912017822, "global_step": 433912, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0963997840881348, "global_step": 433913, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.079974889755249, "global_step": 433914, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.041081666946411, "global_step": 433915, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1109981536865234, "global_step": 433916, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0707993507385254, "global_step": 433917, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.090015172958374, "global_step": 433918, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.082404613494873, "global_step": 433919, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1488091945648193, "global_step": 433920, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0902345180511475, "global_step": 433921, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.00595760345459, "global_step": 433922, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0480258464813232, "global_step": 433923, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.011286973953247, "global_step": 433924, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.081113576889038, "global_step": 433925, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.216831922531128, "global_step": 433926, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0829904079437256, "global_step": 433927, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.098743200302124, "global_step": 433928, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0973892211914062, "global_step": 433929, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1692309379577637, "global_step": 433930, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.194197654724121, "global_step": 433931, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1128382682800293, "global_step": 433932, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1116533279418945, "global_step": 433933, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0890820026397705, "global_step": 433934, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1320223808288574, "global_step": 433935, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.127392053604126, "global_step": 433936, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0843687057495117, "global_step": 433937, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0297961235046387, "global_step": 433938, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0655784606933594, "global_step": 433939, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.106236696243286, "global_step": 433940, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.093266010284424, "global_step": 433941, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.163301706314087, "global_step": 433942, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0052716732025146, "global_step": 433943, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0902159214019775, "global_step": 433944, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0796971321105957, "global_step": 433945, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.063612461090088, "global_step": 433946, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0461058616638184, "global_step": 433947, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.077911615371704, "global_step": 433948, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0375125408172607, "global_step": 433949, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1272032260894775, "global_step": 433950, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0806725025177, "global_step": 433951, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.030550479888916, "global_step": 433952, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.141660451889038, "global_step": 433953, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1222598552703857, "global_step": 433954, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0656399726867676, "global_step": 433955, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1070892810821533, "global_step": 433956, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0460712909698486, "global_step": 433957, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.156790256500244, "global_step": 433958, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0758726596832275, "global_step": 433959, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0833489894866943, "global_step": 433960, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.098374366760254, "global_step": 433961, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.063159942626953, "global_step": 433962, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0493712425231934, "global_step": 433963, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0607147216796875, "global_step": 433964, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0834903717041016, "global_step": 433965, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1312053203582764, "global_step": 433966, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.101548671722412, "global_step": 433967, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.068526029586792, "global_step": 433968, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1113548278808594, "global_step": 433969, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.152717351913452, "global_step": 433970, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0336530208587646, "global_step": 433971, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1093807220458984, "global_step": 433972, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.014235019683838, "global_step": 433973, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.02755069732666, "global_step": 433974, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1761984825134277, "global_step": 433975, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1428894996643066, "global_step": 433976, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.124197483062744, "global_step": 433977, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1154797077178955, "global_step": 433978, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0904030799865723, "global_step": 433979, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1041266918182373, "global_step": 433980, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.072594165802002, "global_step": 433981, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1252951622009277, "global_step": 433982, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.045170783996582, "global_step": 433983, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.071944236755371, "global_step": 433984, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.07800030708313, "global_step": 433985, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.039522171020508, "global_step": 433986, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.149052381515503, "global_step": 433987, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0659823417663574, "global_step": 433988, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1168839931488037, "global_step": 433989, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.091111183166504, "global_step": 433990, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.00803804397583, "global_step": 433991, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0872409343719482, "global_step": 433992, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.115178108215332, "global_step": 433993, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0174686908721924, "global_step": 433994, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1494028568267822, "global_step": 433995, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.137498378753662, "global_step": 433996, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0612666606903076, "global_step": 433997, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0918328762054443, "global_step": 433998, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.080169916152954, "global_step": 433999, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0549216270446777, "global_step": 434000, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1247944831848145, "global_step": 434001, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0903666019439697, "global_step": 434002, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1029281616210938, "global_step": 434003, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1053860187530518, "global_step": 434004, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0584261417388916, "global_step": 434005, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0995354652404785, "global_step": 434006, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.106740951538086, "global_step": 434007, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.06014347076416, "global_step": 434008, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0643362998962402, "global_step": 434009, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.130458354949951, "global_step": 434010, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1305577754974365, "global_step": 434011, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.18227219581604, "global_step": 434012, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.005991220474243, "global_step": 434013, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.170703411102295, "global_step": 434014, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.052497386932373, "global_step": 434015, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0383310317993164, "global_step": 434016, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1346068382263184, "global_step": 434017, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.144998073577881, "global_step": 434018, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.146578311920166, "global_step": 434019, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0319533348083496, "global_step": 434020, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.070934295654297, "global_step": 434021, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0976994037628174, "global_step": 434022, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.035750150680542, "global_step": 434023, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.146923065185547, "global_step": 434024, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.08596134185791, "global_step": 434025, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0636188983917236, "global_step": 434026, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.084231376647949, "global_step": 434027, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0608413219451904, "global_step": 434028, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0604820251464844, "global_step": 434029, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0831236839294434, "global_step": 434030, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0424225330352783, "global_step": 434031, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0944511890411377, "global_step": 434032, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.030101776123047, "global_step": 434033, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.046051263809204, "global_step": 434034, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0409293174743652, "global_step": 434035, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.222243309020996, "global_step": 434036, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0502734184265137, "global_step": 434037, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0288636684417725, "global_step": 434038, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.054107666015625, "global_step": 434039, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.057716131210327, "global_step": 434040, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1333987712860107, "global_step": 434041, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1457743644714355, "global_step": 434042, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1120901107788086, "global_step": 434043, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1076507568359375, "global_step": 434044, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9974697828292847, "global_step": 434045, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0847718715667725, "global_step": 434046, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.052273988723755, "global_step": 434047, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.197727918624878, "global_step": 434048, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.075098991394043, "global_step": 434049, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.109556198120117, "global_step": 434050, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.135683298110962, "global_step": 434051, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0515365600585938, "global_step": 434052, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.059504508972168, "global_step": 434053, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.086697816848755, "global_step": 434054, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.20377254486084, "global_step": 434055, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.05610990524292, "global_step": 434056, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.033113956451416, "global_step": 434057, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0635931491851807, "global_step": 434058, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0601649284362793, "global_step": 434059, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.078901767730713, "global_step": 434060, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.127903461456299, "global_step": 434061, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0655953884124756, "global_step": 434062, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0896003246307373, "global_step": 434063, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1137964725494385, "global_step": 434064, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0769453048706055, "global_step": 434065, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.066676616668701, "global_step": 434066, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.100886821746826, "global_step": 434067, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1312670707702637, "global_step": 434068, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0782411098480225, "global_step": 434069, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.075291872024536, "global_step": 434070, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1235785484313965, "global_step": 434071, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0954461097717285, "global_step": 434072, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1704225540161133, "global_step": 434073, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0985851287841797, "global_step": 434074, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.116199493408203, "global_step": 434075, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1030213832855225, "global_step": 434076, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.064577102661133, "global_step": 434077, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.071364164352417, "global_step": 434078, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9985244274139404, "global_step": 434079, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1409974098205566, "global_step": 434080, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.139517307281494, "global_step": 434081, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.035557985305786, "global_step": 434082, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.122777223587036, "global_step": 434083, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0793893337249756, "global_step": 434084, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.15250825881958, "global_step": 434085, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.100656270980835, "global_step": 434086, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.028925657272339, "global_step": 434087, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.033658266067505, "global_step": 434088, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.146679401397705, "global_step": 434089, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1609244346618652, "global_step": 434090, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.016660690307617, "global_step": 434091, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1185455322265625, "global_step": 434092, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1281991004943848, "global_step": 434093, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1539673805236816, "global_step": 434094, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.125133514404297, "global_step": 434095, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0676138401031494, "global_step": 434096, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0679287910461426, "global_step": 434097, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0800886154174805, "global_step": 434098, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.120844602584839, "global_step": 434099, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0210464000701904, "global_step": 434100, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0484771728515625, "global_step": 434101, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.142716884613037, "global_step": 434102, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1262423992156982, "global_step": 434103, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0692319869995117, "global_step": 434104, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.114932060241699, "global_step": 434105, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.070723295211792, "global_step": 434106, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.045715808868408, "global_step": 434107, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.050395965576172, "global_step": 434108, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.06949520111084, "global_step": 434109, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.081188917160034, "global_step": 434110, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.097644567489624, "global_step": 434111, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.056279420852661, "global_step": 434112, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1633052825927734, "global_step": 434113, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.101341485977173, "global_step": 434114, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0465891361236572, "global_step": 434115, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0678679943084717, "global_step": 434116, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0369715690612793, "global_step": 434117, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0761537551879883, "global_step": 434118, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.018153429031372, "global_step": 434119, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0650787353515625, "global_step": 434120, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0665340423583984, "global_step": 434121, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1362721920013428, "global_step": 434122, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1543149948120117, "global_step": 434123, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.140164375305176, "global_step": 434124, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.130934953689575, "global_step": 434125, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.089380979537964, "global_step": 434126, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1281516551971436, "global_step": 434127, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1019887924194336, "global_step": 434128, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.114232301712036, "global_step": 434129, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0802786350250244, "global_step": 434130, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.081035614013672, "global_step": 434131, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0422325134277344, "global_step": 434132, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1270527839660645, "global_step": 434133, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0622596740722656, "global_step": 434134, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.030505895614624, "global_step": 434135, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0959112644195557, "global_step": 434136, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.060934066772461, "global_step": 434137, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1149299144744873, "global_step": 434138, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.173336982727051, "global_step": 434139, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1503279209136963, "global_step": 434140, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.16094970703125, "global_step": 434141, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0417633056640625, "global_step": 434142, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.134920835494995, "global_step": 434143, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0553338527679443, "global_step": 434144, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0876286029815674, "global_step": 434145, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.049931526184082, "global_step": 434146, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.174797773361206, "global_step": 434147, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.036423921585083, "global_step": 434148, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.125486373901367, "global_step": 434149, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0592825412750244, "global_step": 434150, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.072225570678711, "global_step": 434151, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0515096187591553, "global_step": 434152, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0347506999969482, "global_step": 434153, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.035433292388916, "global_step": 434154, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.069432258605957, "global_step": 434155, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.087092161178589, "global_step": 434156, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1534769535064697, "global_step": 434157, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9855135679244995, "global_step": 434158, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0617878437042236, "global_step": 434159, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.128760814666748, "global_step": 434160, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0357532501220703, "global_step": 434161, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1607911586761475, "global_step": 434162, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.05430006980896, "global_step": 434163, "epoch": 797, "lr": 5e-05}
{"train_loss": 1.9928405284881592, "global_step": 434164, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1333281993865967, "global_step": 434165, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1324462890625, "global_step": 434166, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0910484790802, "global_step": 434167, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1286330223083496, "global_step": 434168, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1317694187164307, "global_step": 434169, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.073244094848633, "global_step": 434170, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.042727470397949, "global_step": 434171, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.064462661743164, "global_step": 434172, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1543173789978027, "global_step": 434173, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.133676528930664, "global_step": 434174, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.151738405227661, "global_step": 434175, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0914933681488037, "global_step": 434176, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.082838773727417, "global_step": 434177, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.093456983566284, "global_step": 434178, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1085290908813477, "global_step": 434179, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.172569990158081, "global_step": 434180, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0073976516723633, "global_step": 434181, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0740978717803955, "global_step": 434182, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.094040632247925, "global_step": 434183, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.038573741912842, "global_step": 434184, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1073668003082275, "global_step": 434185, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.08663010597229, "global_step": 434186, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.11525559425354, "global_step": 434187, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.049180507659912, "global_step": 434188, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0789430141448975, "global_step": 434189, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0552265644073486, "global_step": 434190, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1139447689056396, "global_step": 434191, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0374436378479004, "global_step": 434192, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.14082407951355, "global_step": 434193, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.093735456466675, "global_step": 434194, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.099759340286255, "global_step": 434195, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1296002864837646, "global_step": 434196, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.079319477081299, "global_step": 434197, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0790646076202393, "global_step": 434198, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0560171604156494, "global_step": 434199, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.127497673034668, "global_step": 434200, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.093860149383545, "global_step": 434201, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0098989009857178, "global_step": 434202, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1117806434631348, "global_step": 434203, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.128416061401367, "global_step": 434204, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.093222141265869, "global_step": 434205, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.120516300201416, "global_step": 434206, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.035456895828247, "global_step": 434207, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0596156120300293, "global_step": 434208, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1787688732147217, "global_step": 434209, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.08357572555542, "global_step": 434210, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1083531379699707, "global_step": 434211, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0405097007751465, "global_step": 434212, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0778322219848633, "global_step": 434213, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0680980682373047, "global_step": 434214, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.09379243850708, "global_step": 434215, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.2145190238952637, "global_step": 434216, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.074566602706909, "global_step": 434217, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.167877674102783, "global_step": 434218, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1335363388061523, "global_step": 434219, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.10324764251709, "global_step": 434220, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.105537176132202, "global_step": 434221, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.105933666229248, "global_step": 434222, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1160523891448975, "global_step": 434223, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.004146099090576, "global_step": 434224, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0604147911071777, "global_step": 434225, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.040280342102051, "global_step": 434226, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.145172357559204, "global_step": 434227, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.024228096008301, "global_step": 434228, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0764641761779785, "global_step": 434229, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.069580078125, "global_step": 434230, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1235203742980957, "global_step": 434231, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0438737869262695, "global_step": 434232, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.018810510635376, "global_step": 434233, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.070647716522217, "global_step": 434234, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1329050064086914, "global_step": 434235, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0944900512695312, "global_step": 434236, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.180284023284912, "global_step": 434237, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.066985607147217, "global_step": 434238, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0549368858337402, "global_step": 434239, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.076650381088257, "global_step": 434240, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.0536530017852783, "global_step": 434241, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.01632022857666, "global_step": 434242, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.1794345378875732, "global_step": 434243, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.081514596939087, "global_step": 434244, "epoch": 797, "lr": 5e-05}
{"train_loss": 2.074446678161621, "global_step": 434245, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0349175930023193, "global_step": 434246, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0233500003814697, "global_step": 434247, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0455241203308105, "global_step": 434248, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.070338249206543, "global_step": 434249, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.083427906036377, "global_step": 434250, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.102725028991699, "global_step": 434251, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.093292236328125, "global_step": 434252, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9440606832504272, "global_step": 434253, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.057737112045288, "global_step": 434254, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.038588523864746, "global_step": 434255, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1597959995269775, "global_step": 434256, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0424797534942627, "global_step": 434257, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.070244550704956, "global_step": 434258, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9964189529418945, "global_step": 434259, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.120147228240967, "global_step": 434260, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1405742168426514, "global_step": 434261, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1483585834503174, "global_step": 434262, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.096794843673706, "global_step": 434263, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0684049129486084, "global_step": 434264, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1039366722106934, "global_step": 434265, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0946693420410156, "global_step": 434266, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0192737579345703, "global_step": 434267, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0030176639556885, "global_step": 434268, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0833449363708496, "global_step": 434269, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0673375129699707, "global_step": 434270, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.01247239112854, "global_step": 434271, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.080233335494995, "global_step": 434272, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.112204074859619, "global_step": 434273, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0918681621551514, "global_step": 434274, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9459950923919678, "global_step": 434275, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.081721067428589, "global_step": 434276, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0247857570648193, "global_step": 434277, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0953867435455322, "global_step": 434278, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1228408813476562, "global_step": 434279, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.106306552886963, "global_step": 434280, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0603532791137695, "global_step": 434281, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9509879350662231, "global_step": 434282, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.127774238586426, "global_step": 434283, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.008308172225952, "global_step": 434284, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1500983238220215, "global_step": 434285, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.005061626434326, "global_step": 434286, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.086947202682495, "global_step": 434287, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.075875997543335, "global_step": 434288, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1486802101135254, "global_step": 434289, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0337624549865723, "global_step": 434290, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.095245838165283, "global_step": 434291, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0900535583496094, "global_step": 434292, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0560874938964844, "global_step": 434293, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0400290489196777, "global_step": 434294, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.113356351852417, "global_step": 434295, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0644381046295166, "global_step": 434296, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.031367540359497, "global_step": 434297, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1122381687164307, "global_step": 434298, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1365349292755127, "global_step": 434299, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0308518409729004, "global_step": 434300, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.112450122833252, "global_step": 434301, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0608668327331543, "global_step": 434302, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0685548782348633, "global_step": 434303, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.100379467010498, "global_step": 434304, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1106033325195312, "global_step": 434305, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0422983169555664, "global_step": 434306, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0387604236602783, "global_step": 434307, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.024153232574463, "global_step": 434308, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.038410186767578, "global_step": 434309, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1039602756500244, "global_step": 434310, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0686287879943848, "global_step": 434311, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0512824058532715, "global_step": 434312, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0725772380828857, "global_step": 434313, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0607216358184814, "global_step": 434314, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0861270427703857, "global_step": 434315, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0987467765808105, "global_step": 434316, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.130502223968506, "global_step": 434317, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.044490337371826, "global_step": 434318, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0748515129089355, "global_step": 434319, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.110473155975342, "global_step": 434320, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.082130193710327, "global_step": 434321, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0353636741638184, "global_step": 434322, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1148078441619873, "global_step": 434323, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0832207202911377, "global_step": 434324, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0426175594329834, "global_step": 434325, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1000730991363525, "global_step": 434326, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1083831787109375, "global_step": 434327, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.128234624862671, "global_step": 434328, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.097569704055786, "global_step": 434329, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.091167688369751, "global_step": 434330, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0047199726104736, "global_step": 434331, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0439915657043457, "global_step": 434332, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9955960512161255, "global_step": 434333, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0167503356933594, "global_step": 434334, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0386884212493896, "global_step": 434335, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1309757232666016, "global_step": 434336, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0296127796173096, "global_step": 434337, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.954746961593628, "global_step": 434338, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.098801612854004, "global_step": 434339, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0703561305999756, "global_step": 434340, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.031377077102661, "global_step": 434341, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.072465658187866, "global_step": 434342, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.089108467102051, "global_step": 434343, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.072805166244507, "global_step": 434344, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0435097217559814, "global_step": 434345, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.07895827293396, "global_step": 434346, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0453171730041504, "global_step": 434347, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.102491855621338, "global_step": 434348, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0444934368133545, "global_step": 434349, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.041435718536377, "global_step": 434350, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1018919944763184, "global_step": 434351, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.096010446548462, "global_step": 434352, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.089156150817871, "global_step": 434353, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9801994562149048, "global_step": 434354, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.104543924331665, "global_step": 434355, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.06815242767334, "global_step": 434356, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1032774448394775, "global_step": 434357, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.025437593460083, "global_step": 434358, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.028611660003662, "global_step": 434359, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1110751628875732, "global_step": 434360, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1021945476531982, "global_step": 434361, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0352871417999268, "global_step": 434362, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0769848823547363, "global_step": 434363, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0613365173339844, "global_step": 434364, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1075422763824463, "global_step": 434365, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0909037590026855, "global_step": 434366, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0521557331085205, "global_step": 434367, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0534214973449707, "global_step": 434368, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0729691982269287, "global_step": 434369, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.141772985458374, "global_step": 434370, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.015752077102661, "global_step": 434371, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1102356910705566, "global_step": 434372, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.069962978363037, "global_step": 434373, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1111557483673096, "global_step": 434374, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.111677885055542, "global_step": 434375, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.130265235900879, "global_step": 434376, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1477880477905273, "global_step": 434377, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0965499877929688, "global_step": 434378, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0461926460266113, "global_step": 434379, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.079123020172119, "global_step": 434380, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0402982234954834, "global_step": 434381, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.064368724822998, "global_step": 434382, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.006227970123291, "global_step": 434383, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1102583408355713, "global_step": 434384, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0564022064208984, "global_step": 434385, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9998818635940552, "global_step": 434386, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9140323400497437, "global_step": 434387, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.04008412361145, "global_step": 434388, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.033572196960449, "global_step": 434389, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.035329580307007, "global_step": 434390, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1543936729431152, "global_step": 434391, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0739901065826416, "global_step": 434392, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.087127685546875, "global_step": 434393, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1679930686950684, "global_step": 434394, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.034245252609253, "global_step": 434395, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.149132251739502, "global_step": 434396, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.039968729019165, "global_step": 434397, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.076174259185791, "global_step": 434398, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9552161693572998, "global_step": 434399, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.071979522705078, "global_step": 434400, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0967910289764404, "global_step": 434401, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.096926689147949, "global_step": 434402, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.150890350341797, "global_step": 434403, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9910688400268555, "global_step": 434404, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0420093536376953, "global_step": 434405, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.120093584060669, "global_step": 434406, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.066380500793457, "global_step": 434407, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.110825538635254, "global_step": 434408, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0940394401550293, "global_step": 434409, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9701335430145264, "global_step": 434410, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0928194522857666, "global_step": 434411, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0555946826934814, "global_step": 434412, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.057809352874756, "global_step": 434413, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0637173652648926, "global_step": 434414, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9946832656860352, "global_step": 434415, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.059900999069214, "global_step": 434416, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.11087703704834, "global_step": 434417, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1105892658233643, "global_step": 434418, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0892937183380127, "global_step": 434419, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.103987216949463, "global_step": 434420, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.068979501724243, "global_step": 434421, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1264753341674805, "global_step": 434422, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0809578895568848, "global_step": 434423, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0033957958221436, "global_step": 434424, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1155307292938232, "global_step": 434425, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.118596076965332, "global_step": 434426, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0960052013397217, "global_step": 434427, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9732698202133179, "global_step": 434428, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.01037859916687, "global_step": 434429, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1132779121398926, "global_step": 434430, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.09043550491333, "global_step": 434431, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1020727157592773, "global_step": 434432, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0792789459228516, "global_step": 434433, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0627384185791016, "global_step": 434434, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.063401937484741, "global_step": 434435, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.029770612716675, "global_step": 434436, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.119326591491699, "global_step": 434437, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9856834411621094, "global_step": 434438, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.026238441467285, "global_step": 434439, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0602664947509766, "global_step": 434440, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9930038452148438, "global_step": 434441, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1305501461029053, "global_step": 434442, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.064757823944092, "global_step": 434443, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0411574840545654, "global_step": 434444, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1994760036468506, "global_step": 434445, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.079578161239624, "global_step": 434446, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.104710578918457, "global_step": 434447, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0164895057678223, "global_step": 434448, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0606164932250977, "global_step": 434449, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0583183765411377, "global_step": 434450, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.094851493835449, "global_step": 434451, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0789031982421875, "global_step": 434452, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0236449241638184, "global_step": 434453, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.080324649810791, "global_step": 434454, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1127803325653076, "global_step": 434455, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0482606887817383, "global_step": 434456, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0699918270111084, "global_step": 434457, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0963997840881348, "global_step": 434458, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.105940818786621, "global_step": 434459, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0594542026519775, "global_step": 434460, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.077284097671509, "global_step": 434461, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0935864448547363, "global_step": 434462, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1308748722076416, "global_step": 434463, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0876007080078125, "global_step": 434464, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0883536338806152, "global_step": 434465, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0098652839660645, "global_step": 434466, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0231990814208984, "global_step": 434467, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1248655319213867, "global_step": 434468, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.120023250579834, "global_step": 434469, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0288846492767334, "global_step": 434470, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0405640602111816, "global_step": 434471, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0747406482696533, "global_step": 434472, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0754141807556152, "global_step": 434473, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.041562557220459, "global_step": 434474, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.107959270477295, "global_step": 434475, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.01566219329834, "global_step": 434476, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.014986515045166, "global_step": 434477, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0868093967437744, "global_step": 434478, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0487008094787598, "global_step": 434479, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1616721153259277, "global_step": 434480, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.014195442199707, "global_step": 434481, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.069603204727173, "global_step": 434482, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1017942428588867, "global_step": 434483, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0674591064453125, "global_step": 434484, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1465415954589844, "global_step": 434485, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0759458541870117, "global_step": 434486, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0810492038726807, "global_step": 434487, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.104727268218994, "global_step": 434488, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.092294692993164, "global_step": 434489, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1645851135253906, "global_step": 434490, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1633877754211426, "global_step": 434491, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0730018615722656, "global_step": 434492, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.085932493209839, "global_step": 434493, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.088533401489258, "global_step": 434494, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.086874008178711, "global_step": 434495, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1044750213623047, "global_step": 434496, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1051087379455566, "global_step": 434497, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1256072521209717, "global_step": 434498, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.096487283706665, "global_step": 434499, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.133288860321045, "global_step": 434500, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0647170543670654, "global_step": 434501, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.142406463623047, "global_step": 434502, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.127124309539795, "global_step": 434503, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1958532333374023, "global_step": 434504, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.044130802154541, "global_step": 434505, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1456620693206787, "global_step": 434506, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0931177139282227, "global_step": 434507, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0919594764709473, "global_step": 434508, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0459554195404053, "global_step": 434509, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0840566158294678, "global_step": 434510, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1324586868286133, "global_step": 434511, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0063443183898926, "global_step": 434512, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0054619312286377, "global_step": 434513, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0931396484375, "global_step": 434514, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1235175132751465, "global_step": 434515, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.093881607055664, "global_step": 434516, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0974740982055664, "global_step": 434517, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.101529598236084, "global_step": 434518, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.969146728515625, "global_step": 434519, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.111051559448242, "global_step": 434520, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1293556690216064, "global_step": 434521, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.071667194366455, "global_step": 434522, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9641107320785522, "global_step": 434523, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0596022605895996, "global_step": 434524, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1097092628479004, "global_step": 434525, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9941540956497192, "global_step": 434526, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.110985517501831, "global_step": 434527, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.105815887451172, "global_step": 434528, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.074009418487549, "global_step": 434529, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.123018980026245, "global_step": 434530, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1064302921295166, "global_step": 434531, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.112304925918579, "global_step": 434532, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0731754302978516, "global_step": 434533, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0770857334136963, "global_step": 434534, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.041642189025879, "global_step": 434535, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0578927993774414, "global_step": 434536, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1320576667785645, "global_step": 434537, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0237479209899902, "global_step": 434538, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.099736213684082, "global_step": 434539, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0090670585632324, "global_step": 434540, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1073670387268066, "global_step": 434541, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1082334518432617, "global_step": 434542, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0886318683624268, "global_step": 434543, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.137216329574585, "global_step": 434544, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.027609348297119, "global_step": 434545, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.004197359085083, "global_step": 434546, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.078705310821533, "global_step": 434547, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0538034439086914, "global_step": 434548, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0524492263793945, "global_step": 434549, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1253929138183594, "global_step": 434550, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1306188106536865, "global_step": 434551, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.134243965148926, "global_step": 434552, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0365548133850098, "global_step": 434553, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0777814388275146, "global_step": 434554, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1246132850646973, "global_step": 434555, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1359992027282715, "global_step": 434556, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.140080213546753, "global_step": 434557, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.012277603149414, "global_step": 434558, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0956199169158936, "global_step": 434559, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.078291893005371, "global_step": 434560, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0074262619018555, "global_step": 434561, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1228139400482178, "global_step": 434562, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0070078372955322, "global_step": 434563, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1151740550994873, "global_step": 434564, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0319578647613525, "global_step": 434565, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1044211387634277, "global_step": 434566, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.016072988510132, "global_step": 434567, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.177400827407837, "global_step": 434568, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.155085325241089, "global_step": 434569, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9983536005020142, "global_step": 434570, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0815632343292236, "global_step": 434571, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.058112621307373, "global_step": 434572, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.143827199935913, "global_step": 434573, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.03236722946167, "global_step": 434574, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.08459734916687, "global_step": 434575, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1330111026763916, "global_step": 434576, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0602219104766846, "global_step": 434577, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.007638931274414, "global_step": 434578, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.047288179397583, "global_step": 434579, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1222939491271973, "global_step": 434580, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.13771390914917, "global_step": 434581, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0646400451660156, "global_step": 434582, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0623137950897217, "global_step": 434583, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1655433177948, "global_step": 434584, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.150949001312256, "global_step": 434585, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.056683301925659, "global_step": 434586, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.109123468399048, "global_step": 434587, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1631863117218018, "global_step": 434588, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1106553077697754, "global_step": 434589, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.061411142349243, "global_step": 434590, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0319771766662598, "global_step": 434591, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.088775157928467, "global_step": 434592, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.047329902648926, "global_step": 434593, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.09075665473938, "global_step": 434594, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9985315799713135, "global_step": 434595, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0785722732543945, "global_step": 434596, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.058932304382324, "global_step": 434597, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.080084800720215, "global_step": 434598, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1071808338165283, "global_step": 434599, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.137441396713257, "global_step": 434600, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0857772827148438, "global_step": 434601, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1045422554016113, "global_step": 434602, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0409395694732666, "global_step": 434603, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.118928909301758, "global_step": 434604, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.960283637046814, "global_step": 434605, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.064406394958496, "global_step": 434606, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.06593656539917, "global_step": 434607, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1020071506500244, "global_step": 434608, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1177103519439697, "global_step": 434609, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1145167350769043, "global_step": 434610, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.111100196838379, "global_step": 434611, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.088625907897949, "global_step": 434612, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.083902359008789, "global_step": 434613, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0800459384918213, "global_step": 434614, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.110438346862793, "global_step": 434615, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.11751127243042, "global_step": 434616, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0049004554748535, "global_step": 434617, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.026212453842163, "global_step": 434618, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.114506721496582, "global_step": 434619, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1216886043548584, "global_step": 434620, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.008531093597412, "global_step": 434621, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.051536798477173, "global_step": 434622, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.121103048324585, "global_step": 434623, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1030054092407227, "global_step": 434624, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.096107006072998, "global_step": 434625, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0423080921173096, "global_step": 434626, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0145366191864014, "global_step": 434627, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0705771446228027, "global_step": 434628, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1147730350494385, "global_step": 434629, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0208804607391357, "global_step": 434630, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.06115460395813, "global_step": 434631, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.078214168548584, "global_step": 434632, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0964369773864746, "global_step": 434633, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.968870759010315, "global_step": 434634, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0675439834594727, "global_step": 434635, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0840346813201904, "global_step": 434636, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.013847589492798, "global_step": 434637, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0219075679779053, "global_step": 434638, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.050328493118286, "global_step": 434639, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.149318218231201, "global_step": 434640, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.023632764816284, "global_step": 434641, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.060408353805542, "global_step": 434642, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0119452476501465, "global_step": 434643, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0722200870513916, "global_step": 434644, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1049652099609375, "global_step": 434645, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9882862567901611, "global_step": 434646, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9700617790222168, "global_step": 434647, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1088149547576904, "global_step": 434648, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.122635841369629, "global_step": 434649, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1475369930267334, "global_step": 434650, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1040351390838623, "global_step": 434651, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1025447845458984, "global_step": 434652, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1202094554901123, "global_step": 434653, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0542941093444824, "global_step": 434654, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0434646606445312, "global_step": 434655, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0858798027038574, "global_step": 434656, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.15033221244812, "global_step": 434657, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1113462448120117, "global_step": 434658, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0086488723754883, "global_step": 434659, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0562379360198975, "global_step": 434660, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.060053586959839, "global_step": 434661, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0168869495391846, "global_step": 434662, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0761301517486572, "global_step": 434663, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1261091232299805, "global_step": 434664, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1208462715148926, "global_step": 434665, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.014259099960327, "global_step": 434666, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.137774705886841, "global_step": 434667, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1243932247161865, "global_step": 434668, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1014885902404785, "global_step": 434669, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1418049335479736, "global_step": 434670, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1618294715881348, "global_step": 434671, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0892977714538574, "global_step": 434672, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9858165979385376, "global_step": 434673, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.079132556915283, "global_step": 434674, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.096142530441284, "global_step": 434675, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0927481651306152, "global_step": 434676, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.015763521194458, "global_step": 434677, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.119636058807373, "global_step": 434678, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0524775981903076, "global_step": 434679, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0557148456573486, "global_step": 434680, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.171334743499756, "global_step": 434681, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0483038425445557, "global_step": 434682, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.070082902908325, "global_step": 434683, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.025888442993164, "global_step": 434684, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0685830116271973, "global_step": 434685, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.119887113571167, "global_step": 434686, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0406413078308105, "global_step": 434687, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.111605405807495, "global_step": 434688, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.043865442276001, "global_step": 434689, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.020021915435791, "global_step": 434690, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.075418472290039, "global_step": 434691, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0823192596435547, "global_step": 434692, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0692262649536133, "global_step": 434693, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0809834003448486, "global_step": 434694, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.008777618408203, "global_step": 434695, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0898003578186035, "global_step": 434696, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0339548587799072, "global_step": 434697, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.055299997329712, "global_step": 434698, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0919668674468994, "global_step": 434699, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0666399002075195, "global_step": 434700, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0409321784973145, "global_step": 434701, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1172358989715576, "global_step": 434702, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.028351068496704, "global_step": 434703, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0987424850463867, "global_step": 434704, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.052955389022827, "global_step": 434705, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0655908584594727, "global_step": 434706, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.09386944770813, "global_step": 434707, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0818965435028076, "global_step": 434708, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1421875953674316, "global_step": 434709, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0240049362182617, "global_step": 434710, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.045931339263916, "global_step": 434711, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0890493392944336, "global_step": 434712, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1145589351654053, "global_step": 434713, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.147287607192993, "global_step": 434714, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.06262469291687, "global_step": 434715, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0593361854553223, "global_step": 434716, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0374789237976074, "global_step": 434717, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1278369426727295, "global_step": 434718, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0495855808258057, "global_step": 434719, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1086032390594482, "global_step": 434720, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0705699920654297, "global_step": 434721, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0983033180236816, "global_step": 434722, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.095243453979492, "global_step": 434723, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1006088256835938, "global_step": 434724, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.082456111907959, "global_step": 434725, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.104353427886963, "global_step": 434726, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1294877529144287, "global_step": 434727, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0125808715820312, "global_step": 434728, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.123699188232422, "global_step": 434729, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1253743171691895, "global_step": 434730, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0648350715637207, "global_step": 434731, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.15543270111084, "global_step": 434732, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.139850616455078, "global_step": 434733, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.084512948989868, "global_step": 434734, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0629444122314453, "global_step": 434735, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0773394107818604, "global_step": 434736, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1036012172698975, "global_step": 434737, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0053200721740723, "global_step": 434738, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.093155860900879, "global_step": 434739, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9616098403930664, "global_step": 434740, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.108167886734009, "global_step": 434741, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0605099201202393, "global_step": 434742, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.102165460586548, "global_step": 434743, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9444670677185059, "global_step": 434744, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0859618186950684, "global_step": 434745, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0563161373138428, "global_step": 434746, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.112898349761963, "global_step": 434747, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1221437454223633, "global_step": 434748, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.139633893966675, "global_step": 434749, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.082217216491699, "global_step": 434750, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0844240188598633, "global_step": 434751, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.039846897125244, "global_step": 434752, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0894651412963867, "global_step": 434753, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1085400581359863, "global_step": 434754, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1147778034210205, "global_step": 434755, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.023538112640381, "global_step": 434756, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0770702362060547, "global_step": 434757, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.083536386489868, "global_step": 434758, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.044886589050293, "global_step": 434759, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1075494289398193, "global_step": 434760, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0796427726745605, "global_step": 434761, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.08868145942688, "global_step": 434762, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1283323764801025, "global_step": 434763, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.011716365814209, "global_step": 434764, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.067258834838867, "global_step": 434765, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0765955448150635, "global_step": 434766, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.084665060043335, "global_step": 434767, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.139669418334961, "global_step": 434768, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.129863739013672, "global_step": 434769, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.097627639770508, "global_step": 434770, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.094801187515259, "global_step": 434771, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.970029592514038, "global_step": 434772, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.109903573989868, "global_step": 434773, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0362930297851562, "global_step": 434774, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.019170045852661, "global_step": 434775, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0462489128112793, "global_step": 434776, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0270309448242188, "global_step": 434777, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0178208351135254, "global_step": 434778, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.093212366104126, "global_step": 434779, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0816256999969482, "global_step": 434780, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.066783905029297, "global_step": 434781, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0983383655548096, "global_step": 434782, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.084074020385742, "global_step": 434783, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0726916790008545, "global_step": 434784, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0164854526519775, "global_step": 434785, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.071985960006714, "global_step": 434786, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.053062915802002, "global_step": 434787, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1441586017608643, "global_step": 434788, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0815255641937256, "global_step": 434789, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1059458255767822, "global_step": 434790, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1072750091552734, "global_step": 434791, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0832324028015137, "global_step": 434792, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0247175693511963, "global_step": 434793, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1548819541931152, "global_step": 434794, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.167572259902954, "global_step": 434795, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0703749656677246, "global_step": 434796, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0769972801208496, "global_step": 434797, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.044642925262451, "global_step": 434798, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.003962755203247, "global_step": 434799, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0330874919891357, "global_step": 434800, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.092292070388794, "global_step": 434801, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.05914306640625, "global_step": 434802, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.155508518218994, "global_step": 434803, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1056365966796875, "global_step": 434804, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.04490327835083, "global_step": 434805, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0856430530548096, "global_step": 434806, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0638630390167236, "global_step": 434807, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.09116792678833, "global_step": 434808, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1079583168029785, "global_step": 434809, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.15820574760437, "global_step": 434810, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0144784450531006, "global_step": 434811, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.035573959350586, "global_step": 434812, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1189467906951904, "global_step": 434813, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.04655122756958, "global_step": 434814, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0614264011383057, "global_step": 434815, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1158642768859863, "global_step": 434816, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1176066398620605, "global_step": 434817, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1110334396362305, "global_step": 434818, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0887224674224854, "global_step": 434819, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.000438928604126, "global_step": 434820, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0538997650146484, "global_step": 434821, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.087071657180786, "global_step": 434822, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.090717077255249, "global_step": 434823, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.09649658203125, "global_step": 434824, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0891945362091064, "global_step": 434825, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.088355541229248, "global_step": 434826, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1034350395202637, "global_step": 434827, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0515987873077393, "global_step": 434828, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0828726291656494, "global_step": 434829, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.065277338027954, "global_step": 434830, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1016297340393066, "global_step": 434831, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0396389961242676, "global_step": 434832, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0796048641204834, "global_step": 434833, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.079068660736084, "global_step": 434834, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1081998348236084, "global_step": 434835, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.061246871948242, "global_step": 434836, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.058958053588867, "global_step": 434837, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1588571071624756, "global_step": 434838, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.976662278175354, "global_step": 434839, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.120805263519287, "global_step": 434840, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.146629571914673, "global_step": 434841, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.097546339035034, "global_step": 434842, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1112139225006104, "global_step": 434843, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.129272222518921, "global_step": 434844, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0496551990509033, "global_step": 434845, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0984370708465576, "global_step": 434846, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.079641580581665, "global_step": 434847, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0054361820220947, "global_step": 434848, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0598602294921875, "global_step": 434849, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.077467679977417, "global_step": 434850, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1299726963043213, "global_step": 434851, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.059562921524048, "global_step": 434852, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.080984592437744, "global_step": 434853, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0958330631256104, "global_step": 434854, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.073575973510742, "global_step": 434855, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.03757643699646, "global_step": 434856, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.128574848175049, "global_step": 434857, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0958991050720215, "global_step": 434858, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0201799869537354, "global_step": 434859, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1177561283111572, "global_step": 434860, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9974406957626343, "global_step": 434861, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0547099113464355, "global_step": 434862, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0015993118286133, "global_step": 434863, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.063885450363159, "global_step": 434864, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1980504989624023, "global_step": 434865, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0476186275482178, "global_step": 434866, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0275373458862305, "global_step": 434867, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0741496086120605, "global_step": 434868, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.131561040878296, "global_step": 434869, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.169562339782715, "global_step": 434870, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0380890369415283, "global_step": 434871, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.124673366546631, "global_step": 434872, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.101529121398926, "global_step": 434873, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0463335514068604, "global_step": 434874, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0960030555725098, "global_step": 434875, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0913710594177246, "global_step": 434876, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1617562770843506, "global_step": 434877, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.040316343307495, "global_step": 434878, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0931992530822754, "global_step": 434879, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0749123096466064, "global_step": 434880, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1176373958587646, "global_step": 434881, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1296143531799316, "global_step": 434882, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0506911277770996, "global_step": 434883, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.073575496673584, "global_step": 434884, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1163761615753174, "global_step": 434885, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.141141653060913, "global_step": 434886, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1579010486602783, "global_step": 434887, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0636634826660156, "global_step": 434888, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.115769863128662, "global_step": 434889, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0434300899505615, "global_step": 434890, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.131453275680542, "global_step": 434891, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0641062259674072, "global_step": 434892, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.089791774749756, "global_step": 434893, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9732508659362793, "global_step": 434894, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1145081520080566, "global_step": 434895, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0262434482574463, "global_step": 434896, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0521926879882812, "global_step": 434897, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.136876106262207, "global_step": 434898, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.141094207763672, "global_step": 434899, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1303062438964844, "global_step": 434900, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1374824047088623, "global_step": 434901, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1340434551239014, "global_step": 434902, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0678298473358154, "global_step": 434903, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0730557441711426, "global_step": 434904, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.107119083404541, "global_step": 434905, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9393943548202515, "global_step": 434906, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0703823566436768, "global_step": 434907, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.065535068511963, "global_step": 434908, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1383752822875977, "global_step": 434909, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.071611166000366, "global_step": 434910, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1065571308135986, "global_step": 434911, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0617287158966064, "global_step": 434912, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1975388526916504, "global_step": 434913, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1229188442230225, "global_step": 434914, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.068904399871826, "global_step": 434915, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1298177242279053, "global_step": 434916, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.131476879119873, "global_step": 434917, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.103533983230591, "global_step": 434918, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0672969818115234, "global_step": 434919, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0480449199676514, "global_step": 434920, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.013425827026367, "global_step": 434921, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0134170055389404, "global_step": 434922, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1399312019348145, "global_step": 434923, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1276941299438477, "global_step": 434924, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0777339935302734, "global_step": 434925, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1410443782806396, "global_step": 434926, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.11110520362854, "global_step": 434927, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0905535221099854, "global_step": 434928, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.040308713912964, "global_step": 434929, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.124514579772949, "global_step": 434930, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0370442867279053, "global_step": 434931, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1332638263702393, "global_step": 434932, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0953543186187744, "global_step": 434933, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0535619258880615, "global_step": 434934, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0647261142730713, "global_step": 434935, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0489935874938965, "global_step": 434936, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0092601776123047, "global_step": 434937, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.089925527572632, "global_step": 434938, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1133432388305664, "global_step": 434939, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1150271892547607, "global_step": 434940, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.064852714538574, "global_step": 434941, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1274797916412354, "global_step": 434942, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.011301279067993, "global_step": 434943, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9552676677703857, "global_step": 434944, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.025536060333252, "global_step": 434945, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1246728897094727, "global_step": 434946, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0417702198028564, "global_step": 434947, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1442058086395264, "global_step": 434948, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.183166742324829, "global_step": 434949, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.114351272583008, "global_step": 434950, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1259078979492188, "global_step": 434951, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1446995735168457, "global_step": 434952, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9946345090866089, "global_step": 434953, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1270534992218018, "global_step": 434954, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1472504138946533, "global_step": 434955, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.02517032623291, "global_step": 434956, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.140307664871216, "global_step": 434957, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.050462245941162, "global_step": 434958, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0840344429016113, "global_step": 434959, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.012253522872925, "global_step": 434960, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.109866142272949, "global_step": 434961, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.136229991912842, "global_step": 434962, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0417158603668213, "global_step": 434963, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.164888858795166, "global_step": 434964, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1003386974334717, "global_step": 434965, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.019339084625244, "global_step": 434966, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.090261459350586, "global_step": 434967, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.027440309524536, "global_step": 434968, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0687613487243652, "global_step": 434969, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0752012729644775, "global_step": 434970, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1240034103393555, "global_step": 434971, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0870800018310547, "global_step": 434972, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.054870367050171, "global_step": 434973, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0918660163879395, "global_step": 434974, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.009772777557373, "global_step": 434975, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.138152837753296, "global_step": 434976, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.083772659301758, "global_step": 434977, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.132192611694336, "global_step": 434978, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1015384197235107, "global_step": 434979, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1690611839294434, "global_step": 434980, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0136826038360596, "global_step": 434981, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.109907388687134, "global_step": 434982, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.06592059135437, "global_step": 434983, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.113968849182129, "global_step": 434984, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9822087287902832, "global_step": 434985, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1097662448883057, "global_step": 434986, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0309178829193115, "global_step": 434987, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0413949489593506, "global_step": 434988, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1022353172302246, "global_step": 434989, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0786049365997314, "global_step": 434990, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0906195640563965, "global_step": 434991, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1246297359466553, "global_step": 434992, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.973510980606079, "global_step": 434993, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1237056255340576, "global_step": 434994, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1062991619110107, "global_step": 434995, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.061546564102173, "global_step": 434996, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1432790756225586, "global_step": 434997, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9789749383926392, "global_step": 434998, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9922748804092407, "global_step": 434999, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1259725093841553, "global_step": 435000, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9635303020477295, "global_step": 435001, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1123218536376953, "global_step": 435002, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.086660861968994, "global_step": 435003, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1292946338653564, "global_step": 435004, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1429622173309326, "global_step": 435005, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.13647198677063, "global_step": 435006, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.072255849838257, "global_step": 435007, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.062431573867798, "global_step": 435008, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0339715480804443, "global_step": 435009, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1714961528778076, "global_step": 435010, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0163791179656982, "global_step": 435011, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0800695419311523, "global_step": 435012, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1015052795410156, "global_step": 435013, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.079625368118286, "global_step": 435014, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0345895290374756, "global_step": 435015, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.072657585144043, "global_step": 435016, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.11452317237854, "global_step": 435017, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.044604539871216, "global_step": 435018, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.090162515640259, "global_step": 435019, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0353493690490723, "global_step": 435020, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1395816802978516, "global_step": 435021, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.124544143676758, "global_step": 435022, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.063401699066162, "global_step": 435023, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.040052652359009, "global_step": 435024, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0366382598876953, "global_step": 435025, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1286559104919434, "global_step": 435026, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0611555576324463, "global_step": 435027, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1151652336120605, "global_step": 435028, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.141843795776367, "global_step": 435029, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.153254985809326, "global_step": 435030, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.049511432647705, "global_step": 435031, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0706000328063965, "global_step": 435032, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9942986965179443, "global_step": 435033, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1738407611846924, "global_step": 435034, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0011544227600098, "global_step": 435035, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.11997652053833, "global_step": 435036, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0517241954803467, "global_step": 435037, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0580344200134277, "global_step": 435038, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0891735553741455, "global_step": 435039, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1289350986480713, "global_step": 435040, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.046116352081299, "global_step": 435041, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.037310838699341, "global_step": 435042, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.022352933883667, "global_step": 435043, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0800344944000244, "global_step": 435044, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.103095054626465, "global_step": 435045, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.034283399581909, "global_step": 435046, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0349667072296143, "global_step": 435047, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0481812953948975, "global_step": 435048, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.041703462600708, "global_step": 435049, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.110578775405884, "global_step": 435050, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0050437450408936, "global_step": 435051, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.118138551712036, "global_step": 435052, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.04355525970459, "global_step": 435053, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.034341812133789, "global_step": 435054, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1055121421813965, "global_step": 435055, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.091843605041504, "global_step": 435056, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0779592990875244, "global_step": 435057, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0384137630462646, "global_step": 435058, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.116135597229004, "global_step": 435059, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1038663387298584, "global_step": 435060, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.021108388900757, "global_step": 435061, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.191441297531128, "global_step": 435062, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.063925266265869, "global_step": 435063, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0807740688323975, "global_step": 435064, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1308810710906982, "global_step": 435065, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1169557571411133, "global_step": 435066, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.123652458190918, "global_step": 435067, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1496362686157227, "global_step": 435068, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.11285400390625, "global_step": 435069, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0795576572418213, "global_step": 435070, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0817859172821045, "global_step": 435071, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0559096336364746, "global_step": 435072, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0713369846343994, "global_step": 435073, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.051530599594116, "global_step": 435074, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.095031499862671, "global_step": 435075, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1359522342681885, "global_step": 435076, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0411367416381836, "global_step": 435077, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.097012996673584, "global_step": 435078, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.068408250808716, "global_step": 435079, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0543644428253174, "global_step": 435080, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.057023763656616, "global_step": 435081, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0613300800323486, "global_step": 435082, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1329264640808105, "global_step": 435083, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.149381160736084, "global_step": 435084, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.125856637954712, "global_step": 435085, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0969860553741455, "global_step": 435086, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.06982421875, "global_step": 435087, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1402413845062256, "global_step": 435088, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0806941986083984, "global_step": 435089, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0513219833374023, "global_step": 435090, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.02998423576355, "global_step": 435091, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0045669078826904, "global_step": 435092, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.062912702560425, "global_step": 435093, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0894758701324463, "global_step": 435094, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0512874126434326, "global_step": 435095, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.083376407623291, "global_step": 435096, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.014902114868164, "global_step": 435097, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.12994647026062, "global_step": 435098, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1352620124816895, "global_step": 435099, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.027827739715576, "global_step": 435100, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.100968360900879, "global_step": 435101, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.128573417663574, "global_step": 435102, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.065042018890381, "global_step": 435103, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.101480484008789, "global_step": 435104, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0672781467437744, "global_step": 435105, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0336339473724365, "global_step": 435106, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.067401647567749, "global_step": 435107, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.074944496154785, "global_step": 435108, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9834665060043335, "global_step": 435109, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.15925669670105, "global_step": 435110, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.104491949081421, "global_step": 435111, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1642465591430664, "global_step": 435112, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1725127696990967, "global_step": 435113, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.089855194091797, "global_step": 435114, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.128075122833252, "global_step": 435115, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.018557548522949, "global_step": 435116, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0856094360351562, "global_step": 435117, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0514183044433594, "global_step": 435118, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1170601844787598, "global_step": 435119, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0922131538391113, "global_step": 435120, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.060434103012085, "global_step": 435121, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.120351791381836, "global_step": 435122, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0716099739074707, "global_step": 435123, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1111912727355957, "global_step": 435124, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.072657585144043, "global_step": 435125, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.055957317352295, "global_step": 435126, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0936124324798584, "global_step": 435127, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.085181474685669, "global_step": 435128, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1928694248199463, "global_step": 435129, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1475296020507812, "global_step": 435130, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.073498010635376, "global_step": 435131, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9836515188217163, "global_step": 435132, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.182584285736084, "global_step": 435133, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1859853267669678, "global_step": 435134, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.160362958908081, "global_step": 435135, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.062898874282837, "global_step": 435136, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.045867681503296, "global_step": 435137, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9875290393829346, "global_step": 435138, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0971007347106934, "global_step": 435139, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0900509357452393, "global_step": 435140, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1033453941345215, "global_step": 435141, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.051896572113037, "global_step": 435142, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.016366481781006, "global_step": 435143, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1210439205169678, "global_step": 435144, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.081977367401123, "global_step": 435145, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.19513201713562, "global_step": 435146, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.100299119949341, "global_step": 435147, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.061605453491211, "global_step": 435148, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0368399620056152, "global_step": 435149, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.025933265686035, "global_step": 435150, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1397900581359863, "global_step": 435151, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0970733165740967, "global_step": 435152, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1277668476104736, "global_step": 435153, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.037079095840454, "global_step": 435154, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0506279468536377, "global_step": 435155, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0808370113372803, "global_step": 435156, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0747926235198975, "global_step": 435157, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.029524326324463, "global_step": 435158, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.092555046081543, "global_step": 435159, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.059086561203003, "global_step": 435160, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.998641014099121, "global_step": 435161, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0787317752838135, "global_step": 435162, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.080611228942871, "global_step": 435163, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1633410453796387, "global_step": 435164, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.079108476638794, "global_step": 435165, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.097787618637085, "global_step": 435166, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.08549427986145, "global_step": 435167, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.053237199783325, "global_step": 435168, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.12854266166687, "global_step": 435169, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0363283157348633, "global_step": 435170, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0694801807403564, "global_step": 435171, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1009559631347656, "global_step": 435172, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.201968193054199, "global_step": 435173, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0359323024749756, "global_step": 435174, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1143620014190674, "global_step": 435175, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0136334896087646, "global_step": 435176, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0497000217437744, "global_step": 435177, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0101449489593506, "global_step": 435178, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0704169273376465, "global_step": 435179, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0043582916259766, "global_step": 435180, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.060288667678833, "global_step": 435181, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1487855911254883, "global_step": 435182, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1269800662994385, "global_step": 435183, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.140033483505249, "global_step": 435184, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.121598243713379, "global_step": 435185, "epoch": 798, "lr": 5e-05}
{"train_loss": 1.9694435596466064, "global_step": 435186, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0825204849243164, "global_step": 435187, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.064244270324707, "global_step": 435188, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.177302122116089, "global_step": 435189, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0545668601989746, "global_step": 435190, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1106982231140137, "global_step": 435191, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0779237747192383, "global_step": 435192, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.102938652038574, "global_step": 435193, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.065455913543701, "global_step": 435194, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0488691329956055, "global_step": 435195, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0701894760131836, "global_step": 435196, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.080934762954712, "global_step": 435197, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1115756034851074, "global_step": 435198, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1877939701080322, "global_step": 435199, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1474251747131348, "global_step": 435200, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.050286293029785, "global_step": 435201, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0468084812164307, "global_step": 435202, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1013450622558594, "global_step": 435203, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1216182708740234, "global_step": 435204, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.108027935028076, "global_step": 435205, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.145181179046631, "global_step": 435206, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.062502145767212, "global_step": 435207, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.117185592651367, "global_step": 435208, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.127793312072754, "global_step": 435209, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.112041473388672, "global_step": 435210, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.1384952068328857, "global_step": 435211, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.115305185317993, "global_step": 435212, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.0794224739074707, "global_step": 435213, "epoch": 798, "lr": 5e-05}
{"train_loss": 2.056236743927002, "global_step": 435214, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0648486614227295, "global_step": 435215, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.051159381866455, "global_step": 435216, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0895094871520996, "global_step": 435217, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0913572311401367, "global_step": 435218, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0425169467926025, "global_step": 435219, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9878824949264526, "global_step": 435220, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0249924659729004, "global_step": 435221, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0238747596740723, "global_step": 435222, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1741840839385986, "global_step": 435223, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1205556392669678, "global_step": 435224, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0490386486053467, "global_step": 435225, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0880274772644043, "global_step": 435226, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.054469108581543, "global_step": 435227, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.076437473297119, "global_step": 435228, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0566561222076416, "global_step": 435229, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.060842752456665, "global_step": 435230, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.06530499458313, "global_step": 435231, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.035062789916992, "global_step": 435232, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.060978412628174, "global_step": 435233, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.003840923309326, "global_step": 435234, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.008915424346924, "global_step": 435235, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0889294147491455, "global_step": 435236, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0989694595336914, "global_step": 435237, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.088129758834839, "global_step": 435238, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9377341270446777, "global_step": 435239, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.036868095397949, "global_step": 435240, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.119493007659912, "global_step": 435241, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.096484661102295, "global_step": 435242, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.04764723777771, "global_step": 435243, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0669021606445312, "global_step": 435244, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.116957187652588, "global_step": 435245, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1180121898651123, "global_step": 435246, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.043339729309082, "global_step": 435247, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.143740653991699, "global_step": 435248, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.004448175430298, "global_step": 435249, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0483787059783936, "global_step": 435250, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0575358867645264, "global_step": 435251, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.044769287109375, "global_step": 435252, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.017899990081787, "global_step": 435253, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.117357015609741, "global_step": 435254, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.082977056503296, "global_step": 435255, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0830631256103516, "global_step": 435256, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.18708872795105, "global_step": 435257, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0492782592773438, "global_step": 435258, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.059385299682617, "global_step": 435259, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0653626918792725, "global_step": 435260, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1419334411621094, "global_step": 435261, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0914106369018555, "global_step": 435262, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0721254348754883, "global_step": 435263, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.085542678833008, "global_step": 435264, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.086524248123169, "global_step": 435265, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.123297691345215, "global_step": 435266, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.024712085723877, "global_step": 435267, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.112344980239868, "global_step": 435268, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.098911762237549, "global_step": 435269, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0429508686065674, "global_step": 435270, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0434985160827637, "global_step": 435271, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.172523260116577, "global_step": 435272, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0669174194335938, "global_step": 435273, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0736477375030518, "global_step": 435274, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0457842350006104, "global_step": 435275, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0603268146514893, "global_step": 435276, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0548253059387207, "global_step": 435277, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0661566257476807, "global_step": 435278, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.063931941986084, "global_step": 435279, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0833160877227783, "global_step": 435280, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0747742652893066, "global_step": 435281, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0406596660614014, "global_step": 435282, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.107900381088257, "global_step": 435283, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.070358991622925, "global_step": 435284, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0398502349853516, "global_step": 435285, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.091538667678833, "global_step": 435286, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0065221786499023, "global_step": 435287, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0787136554718018, "global_step": 435288, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0418741703033447, "global_step": 435289, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0368423461914062, "global_step": 435290, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0558950901031494, "global_step": 435291, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0752010345458984, "global_step": 435292, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0479695796966553, "global_step": 435293, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.030418872833252, "global_step": 435294, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.058504581451416, "global_step": 435295, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.071700096130371, "global_step": 435296, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0614922046661377, "global_step": 435297, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0890116691589355, "global_step": 435298, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0813028812408447, "global_step": 435299, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.072299003601074, "global_step": 435300, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.052696943283081, "global_step": 435301, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.066718339920044, "global_step": 435302, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0933609008789062, "global_step": 435303, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0995218753814697, "global_step": 435304, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0918238162994385, "global_step": 435305, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0254108905792236, "global_step": 435306, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.100010633468628, "global_step": 435307, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0371737480163574, "global_step": 435308, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0482475757598877, "global_step": 435309, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9376122951507568, "global_step": 435310, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.041982650756836, "global_step": 435311, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0293684005737305, "global_step": 435312, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1310486793518066, "global_step": 435313, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0492708683013916, "global_step": 435314, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0469586849212646, "global_step": 435315, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0379292964935303, "global_step": 435316, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1376781463623047, "global_step": 435317, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.080131769180298, "global_step": 435318, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.06592059135437, "global_step": 435319, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.099684476852417, "global_step": 435320, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.991536021232605, "global_step": 435321, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0778942108154297, "global_step": 435322, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1031792163848877, "global_step": 435323, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1177587509155273, "global_step": 435324, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1391351222991943, "global_step": 435325, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0670223236083984, "global_step": 435326, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0026748180389404, "global_step": 435327, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0980308055877686, "global_step": 435328, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0960288047790527, "global_step": 435329, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0956380367279053, "global_step": 435330, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.115556478500366, "global_step": 435331, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1071929931640625, "global_step": 435332, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1179654598236084, "global_step": 435333, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0641095638275146, "global_step": 435334, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.100658655166626, "global_step": 435335, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.100497245788574, "global_step": 435336, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0580546855926514, "global_step": 435337, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1291663646698, "global_step": 435338, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0729169845581055, "global_step": 435339, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0699172019958496, "global_step": 435340, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.146474838256836, "global_step": 435341, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.054338216781616, "global_step": 435342, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.085366725921631, "global_step": 435343, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0749804973602295, "global_step": 435344, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.107515811920166, "global_step": 435345, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.046733856201172, "global_step": 435346, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1168301105499268, "global_step": 435347, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1232128143310547, "global_step": 435348, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1331253051757812, "global_step": 435349, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.982385516166687, "global_step": 435350, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.13436222076416, "global_step": 435351, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1522603034973145, "global_step": 435352, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0192174911499023, "global_step": 435353, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0347094535827637, "global_step": 435354, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.00634765625, "global_step": 435355, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.106581926345825, "global_step": 435356, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9967314004898071, "global_step": 435357, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.050919771194458, "global_step": 435358, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1326920986175537, "global_step": 435359, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0412867069244385, "global_step": 435360, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.103369951248169, "global_step": 435361, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1623144149780273, "global_step": 435362, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0072829723358154, "global_step": 435363, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0748910903930664, "global_step": 435364, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.080392599105835, "global_step": 435365, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.063602924346924, "global_step": 435366, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1701316833496094, "global_step": 435367, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0545525550842285, "global_step": 435368, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0554416179656982, "global_step": 435369, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.121807336807251, "global_step": 435370, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1279048919677734, "global_step": 435371, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0620484352111816, "global_step": 435372, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1253013610839844, "global_step": 435373, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.034496784210205, "global_step": 435374, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0254740715026855, "global_step": 435375, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0929670333862305, "global_step": 435376, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0618979930877686, "global_step": 435377, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.066169261932373, "global_step": 435378, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.068946123123169, "global_step": 435379, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.045748710632324, "global_step": 435380, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1124043464660645, "global_step": 435381, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1341018676757812, "global_step": 435382, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1302528381347656, "global_step": 435383, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0531928539276123, "global_step": 435384, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.08087420463562, "global_step": 435385, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.2005507946014404, "global_step": 435386, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.034398317337036, "global_step": 435387, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.069380760192871, "global_step": 435388, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0464301109313965, "global_step": 435389, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.073852777481079, "global_step": 435390, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0876569747924805, "global_step": 435391, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9673571586608887, "global_step": 435392, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.079878330230713, "global_step": 435393, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1258161067962646, "global_step": 435394, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.072300910949707, "global_step": 435395, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.038996934890747, "global_step": 435396, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0646886825561523, "global_step": 435397, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1130106449127197, "global_step": 435398, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1226019859313965, "global_step": 435399, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.07368540763855, "global_step": 435400, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.066603183746338, "global_step": 435401, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1404519081115723, "global_step": 435402, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.010007381439209, "global_step": 435403, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0082788467407227, "global_step": 435404, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.137488842010498, "global_step": 435405, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0550644397735596, "global_step": 435406, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.083409547805786, "global_step": 435407, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.03922176361084, "global_step": 435408, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1001245975494385, "global_step": 435409, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.05845046043396, "global_step": 435410, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0539019107818604, "global_step": 435411, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0933218002319336, "global_step": 435412, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0995993614196777, "global_step": 435413, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1170363426208496, "global_step": 435414, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.080021858215332, "global_step": 435415, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1396734714508057, "global_step": 435416, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.239107608795166, "global_step": 435417, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.022071123123169, "global_step": 435418, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.120145559310913, "global_step": 435419, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.054610252380371, "global_step": 435420, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0832245349884033, "global_step": 435421, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0041794776916504, "global_step": 435422, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9603608846664429, "global_step": 435423, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0687592029571533, "global_step": 435424, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.073383331298828, "global_step": 435425, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1138129234313965, "global_step": 435426, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0204713344573975, "global_step": 435427, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1473493576049805, "global_step": 435428, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.075200080871582, "global_step": 435429, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.008090019226074, "global_step": 435430, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.155884265899658, "global_step": 435431, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1887288093566895, "global_step": 435432, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0427756309509277, "global_step": 435433, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.023458480834961, "global_step": 435434, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0642008781433105, "global_step": 435435, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.135768413543701, "global_step": 435436, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9840086698532104, "global_step": 435437, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0346717834472656, "global_step": 435438, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0413877964019775, "global_step": 435439, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1565592288970947, "global_step": 435440, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.10373854637146, "global_step": 435441, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.023449182510376, "global_step": 435442, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0999138355255127, "global_step": 435443, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.004962921142578, "global_step": 435444, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1057260036468506, "global_step": 435445, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.035560131072998, "global_step": 435446, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.011023998260498, "global_step": 435447, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0174713134765625, "global_step": 435448, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0727381706237793, "global_step": 435449, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0337345600128174, "global_step": 435450, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.2583529949188232, "global_step": 435451, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1127851009368896, "global_step": 435452, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0283524990081787, "global_step": 435453, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.994579792022705, "global_step": 435454, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0210623741149902, "global_step": 435455, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.2497036457061768, "global_step": 435456, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0549840927124023, "global_step": 435457, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0036470890045166, "global_step": 435458, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.050196409225464, "global_step": 435459, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.109699249267578, "global_step": 435460, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1215109825134277, "global_step": 435461, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.073904514312744, "global_step": 435462, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.04650616645813, "global_step": 435463, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0175423622131348, "global_step": 435464, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.043731927871704, "global_step": 435465, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.063976764678955, "global_step": 435466, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.057616710662842, "global_step": 435467, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1810243129730225, "global_step": 435468, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0195717811584473, "global_step": 435469, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0282084941864014, "global_step": 435470, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0354204177856445, "global_step": 435471, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.026193141937256, "global_step": 435472, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.045144557952881, "global_step": 435473, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0973780155181885, "global_step": 435474, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.134166955947876, "global_step": 435475, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.02544903755188, "global_step": 435476, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.004823923110962, "global_step": 435477, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1264302730560303, "global_step": 435478, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1105072498321533, "global_step": 435479, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1014230251312256, "global_step": 435480, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0775411128997803, "global_step": 435481, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0661439895629883, "global_step": 435482, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.099520444869995, "global_step": 435483, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.099923849105835, "global_step": 435484, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0082125663757324, "global_step": 435485, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.078181743621826, "global_step": 435486, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0249786376953125, "global_step": 435487, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1261608600616455, "global_step": 435488, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.126271963119507, "global_step": 435489, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9753174781799316, "global_step": 435490, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.017611265182495, "global_step": 435491, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0862789154052734, "global_step": 435492, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1010513305664062, "global_step": 435493, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0789785385131836, "global_step": 435494, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.092930555343628, "global_step": 435495, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1289021968841553, "global_step": 435496, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.047703742980957, "global_step": 435497, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.064527750015259, "global_step": 435498, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.085754871368408, "global_step": 435499, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.049513101577759, "global_step": 435500, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.150672674179077, "global_step": 435501, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1050033569335938, "global_step": 435502, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.100008487701416, "global_step": 435503, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9881260395050049, "global_step": 435504, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0203239917755127, "global_step": 435505, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0886282920837402, "global_step": 435506, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1145057678222656, "global_step": 435507, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.000356912612915, "global_step": 435508, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.024322032928467, "global_step": 435509, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9680376052856445, "global_step": 435510, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.04455828666687, "global_step": 435511, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.017913579940796, "global_step": 435512, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0793230533599854, "global_step": 435513, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.09932017326355, "global_step": 435514, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0888211727142334, "global_step": 435515, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0231237411499023, "global_step": 435516, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0720293521881104, "global_step": 435517, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1503186225891113, "global_step": 435518, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.11627459526062, "global_step": 435519, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0799481868743896, "global_step": 435520, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0625967979431152, "global_step": 435521, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0350680351257324, "global_step": 435522, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.065091848373413, "global_step": 435523, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0643608570098877, "global_step": 435524, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1402273178100586, "global_step": 435525, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.087405204772949, "global_step": 435526, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.113959789276123, "global_step": 435527, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0446348190307617, "global_step": 435528, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.145399332046509, "global_step": 435529, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0856308937072754, "global_step": 435530, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.118351936340332, "global_step": 435531, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.031980514526367, "global_step": 435532, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1358842849731445, "global_step": 435533, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0092153549194336, "global_step": 435534, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1619467735290527, "global_step": 435535, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.143293857574463, "global_step": 435536, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1556308269500732, "global_step": 435537, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.117176055908203, "global_step": 435538, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.082284450531006, "global_step": 435539, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0450387001037598, "global_step": 435540, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.04282546043396, "global_step": 435541, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.121180295944214, "global_step": 435542, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0522475242614746, "global_step": 435543, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.042065143585205, "global_step": 435544, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.081057071685791, "global_step": 435545, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0238397121429443, "global_step": 435546, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.160625457763672, "global_step": 435547, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0597591400146484, "global_step": 435548, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1203339099884033, "global_step": 435549, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0788164138793945, "global_step": 435550, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1254429817199707, "global_step": 435551, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.096909284591675, "global_step": 435552, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.086841344833374, "global_step": 435553, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.076871395111084, "global_step": 435554, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0625526905059814, "global_step": 435555, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1234960556030273, "global_step": 435556, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0504066944122314, "global_step": 435557, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0534915924072266, "global_step": 435558, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0919744968414307, "global_step": 435559, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.113555669784546, "global_step": 435560, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0435163974761963, "global_step": 435561, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.132499933242798, "global_step": 435562, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1867849826812744, "global_step": 435563, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9255832433700562, "global_step": 435564, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.09623646736145, "global_step": 435565, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.121004819869995, "global_step": 435566, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.042344093322754, "global_step": 435567, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1140387058258057, "global_step": 435568, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.083632469177246, "global_step": 435569, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9911601543426514, "global_step": 435570, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9977352619171143, "global_step": 435571, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.08612060546875, "global_step": 435572, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0528104305267334, "global_step": 435573, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1065876483917236, "global_step": 435574, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0595040321350098, "global_step": 435575, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0499463081359863, "global_step": 435576, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.047107219696045, "global_step": 435577, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.061699151992798, "global_step": 435578, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.021610975265503, "global_step": 435579, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0677199363708496, "global_step": 435580, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1158597469329834, "global_step": 435581, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0689308643341064, "global_step": 435582, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.085099697113037, "global_step": 435583, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1163554191589355, "global_step": 435584, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0631895065307617, "global_step": 435585, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.2125957012176514, "global_step": 435586, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0647497177124023, "global_step": 435587, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0956671237945557, "global_step": 435588, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.976387858390808, "global_step": 435589, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.076860189437866, "global_step": 435590, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.071908473968506, "global_step": 435591, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1303248405456543, "global_step": 435592, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0906174182891846, "global_step": 435593, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0503528118133545, "global_step": 435594, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1420795917510986, "global_step": 435595, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.098207712173462, "global_step": 435596, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.040109395980835, "global_step": 435597, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.070291519165039, "global_step": 435598, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.046720027923584, "global_step": 435599, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1282010078430176, "global_step": 435600, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0865838527679443, "global_step": 435601, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1305179595947266, "global_step": 435602, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.096217155456543, "global_step": 435603, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.096287965774536, "global_step": 435604, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1308367252349854, "global_step": 435605, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0368189811706543, "global_step": 435606, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.128833055496216, "global_step": 435607, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0205185413360596, "global_step": 435608, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.13649582862854, "global_step": 435609, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.128253698348999, "global_step": 435610, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0301637649536133, "global_step": 435611, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.123525619506836, "global_step": 435612, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.029183864593506, "global_step": 435613, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1591429710388184, "global_step": 435614, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1086554527282715, "global_step": 435615, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.035679340362549, "global_step": 435616, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.144937038421631, "global_step": 435617, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.112384557723999, "global_step": 435618, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.2785756587982178, "global_step": 435619, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1146457195281982, "global_step": 435620, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9666272401809692, "global_step": 435621, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.046130895614624, "global_step": 435622, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.140220880508423, "global_step": 435623, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.099299192428589, "global_step": 435624, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0394721031188965, "global_step": 435625, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.10595965385437, "global_step": 435626, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.084794521331787, "global_step": 435627, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.046499490737915, "global_step": 435628, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0946712493896484, "global_step": 435629, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1005496978759766, "global_step": 435630, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1790144443511963, "global_step": 435631, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.158843755722046, "global_step": 435632, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0216903686523438, "global_step": 435633, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0182504653930664, "global_step": 435634, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.103639602661133, "global_step": 435635, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1439905166625977, "global_step": 435636, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0175442695617676, "global_step": 435637, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1148903369903564, "global_step": 435638, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.092453956604004, "global_step": 435639, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0269391536712646, "global_step": 435640, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0846457481384277, "global_step": 435641, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9577022790908813, "global_step": 435642, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.08364200592041, "global_step": 435643, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0296506881713867, "global_step": 435644, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0757720470428467, "global_step": 435645, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1070175170898438, "global_step": 435646, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1012468338012695, "global_step": 435647, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9920376539230347, "global_step": 435648, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1076743602752686, "global_step": 435649, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.080815076828003, "global_step": 435650, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.12861704826355, "global_step": 435651, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0722696781158447, "global_step": 435652, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.06766676902771, "global_step": 435653, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1274309158325195, "global_step": 435654, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1135318279266357, "global_step": 435655, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1793134212493896, "global_step": 435656, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.125126361846924, "global_step": 435657, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1218628883361816, "global_step": 435658, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0589780807495117, "global_step": 435659, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.048258066177368, "global_step": 435660, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0872366428375244, "global_step": 435661, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.140859842300415, "global_step": 435662, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0800089836120605, "global_step": 435663, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.070605516433716, "global_step": 435664, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.051206588745117, "global_step": 435665, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0874838829040527, "global_step": 435666, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.017286539077759, "global_step": 435667, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1204233169555664, "global_step": 435668, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.041823387145996, "global_step": 435669, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9972237348556519, "global_step": 435670, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.127880811691284, "global_step": 435671, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1181113719940186, "global_step": 435672, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.086009979248047, "global_step": 435673, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0374159812927246, "global_step": 435674, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.034362554550171, "global_step": 435675, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1882617473602295, "global_step": 435676, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.127169370651245, "global_step": 435677, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.055954694747925, "global_step": 435678, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.106044054031372, "global_step": 435679, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.077899217605591, "global_step": 435680, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1559290885925293, "global_step": 435681, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0835700035095215, "global_step": 435682, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.129127264022827, "global_step": 435683, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.022063732147217, "global_step": 435684, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0870602130889893, "global_step": 435685, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.069204568862915, "global_step": 435686, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.941962480545044, "global_step": 435687, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0661635398864746, "global_step": 435688, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0695042610168457, "global_step": 435689, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0969083309173584, "global_step": 435690, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0732901096343994, "global_step": 435691, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.07989764213562, "global_step": 435692, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1234512329101562, "global_step": 435693, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0793402194976807, "global_step": 435694, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.118061065673828, "global_step": 435695, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0559096336364746, "global_step": 435696, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9783903360366821, "global_step": 435697, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0709242820739746, "global_step": 435698, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0323219299316406, "global_step": 435699, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.005758047103882, "global_step": 435700, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.109556198120117, "global_step": 435701, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.037834405899048, "global_step": 435702, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1213836669921875, "global_step": 435703, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0489139556884766, "global_step": 435704, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.05372953414917, "global_step": 435705, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.109039783477783, "global_step": 435706, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.090341091156006, "global_step": 435707, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.070866107940674, "global_step": 435708, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.079185962677002, "global_step": 435709, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.026632308959961, "global_step": 435710, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0942652225494385, "global_step": 435711, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0296826362609863, "global_step": 435712, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9905730485916138, "global_step": 435713, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0663716793060303, "global_step": 435714, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0686428546905518, "global_step": 435715, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.154771327972412, "global_step": 435716, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.068559169769287, "global_step": 435717, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.107269525527954, "global_step": 435718, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.2264223098754883, "global_step": 435719, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0782153606414795, "global_step": 435720, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1577253341674805, "global_step": 435721, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0421359539031982, "global_step": 435722, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0822200775146484, "global_step": 435723, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0381667613983154, "global_step": 435724, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1429195404052734, "global_step": 435725, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0764176845550537, "global_step": 435726, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0769972801208496, "global_step": 435727, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.996195673942566, "global_step": 435728, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0999252796173096, "global_step": 435729, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.094949245452881, "global_step": 435730, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0815703868865967, "global_step": 435731, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0664665699005127, "global_step": 435732, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1941258907318115, "global_step": 435733, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.135873556137085, "global_step": 435734, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0260708332061768, "global_step": 435735, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0265746116638184, "global_step": 435736, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.068106174468994, "global_step": 435737, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.100043773651123, "global_step": 435738, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1670022010803223, "global_step": 435739, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.068666934967041, "global_step": 435740, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1177799701690674, "global_step": 435741, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.102614402770996, "global_step": 435742, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0689773559570312, "global_step": 435743, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1069695949554443, "global_step": 435744, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.998306393623352, "global_step": 435745, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.002481460571289, "global_step": 435746, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.022759199142456, "global_step": 435747, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.024569511413574, "global_step": 435748, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.026477575302124, "global_step": 435749, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.077378511428833, "global_step": 435750, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0368685722351074, "global_step": 435751, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1226258277893066, "global_step": 435752, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.084556818008423, "global_step": 435753, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0550451278686523, "global_step": 435754, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.2410120964050293, "global_step": 435755, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9813734292984009, "global_step": 435756, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.01033091545105, "global_step": 435757, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1180999279022217, "global_step": 435758, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.018681526184082, "global_step": 435759, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1273787021636963, "global_step": 435760, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.033872127532959, "global_step": 435761, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0034046173095703, "global_step": 435762, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1334609985351562, "global_step": 435763, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0965940952301025, "global_step": 435764, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1561012268066406, "global_step": 435765, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1141269207000732, "global_step": 435766, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.014643907546997, "global_step": 435767, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.038058042526245, "global_step": 435768, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.121852397918701, "global_step": 435769, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.115078926086426, "global_step": 435770, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0173377990722656, "global_step": 435771, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0772430896759033, "global_step": 435772, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.099454879760742, "global_step": 435773, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1622183322906494, "global_step": 435774, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.214275598526001, "global_step": 435775, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.097496271133423, "global_step": 435776, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0748186111450195, "global_step": 435777, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1286234855651855, "global_step": 435778, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.13586688041687, "global_step": 435779, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.138543128967285, "global_step": 435780, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.137986898422241, "global_step": 435781, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.132199764251709, "global_step": 435782, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9928447008132935, "global_step": 435783, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1334445476531982, "global_step": 435784, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.093696117401123, "global_step": 435785, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.027452230453491, "global_step": 435786, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.080963373184204, "global_step": 435787, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.040436267852783, "global_step": 435788, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0327961444854736, "global_step": 435789, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0994246006011963, "global_step": 435790, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.097538471221924, "global_step": 435791, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0807666778564453, "global_step": 435792, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0984396934509277, "global_step": 435793, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.117825984954834, "global_step": 435794, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0841996669769287, "global_step": 435795, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1381449699401855, "global_step": 435796, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1488399505615234, "global_step": 435797, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.179311513900757, "global_step": 435798, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.007754325866699, "global_step": 435799, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.156916379928589, "global_step": 435800, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1163272857666016, "global_step": 435801, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.059171438217163, "global_step": 435802, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.013791561126709, "global_step": 435803, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.072167158126831, "global_step": 435804, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.990635633468628, "global_step": 435805, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.061789035797119, "global_step": 435806, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1430208683013916, "global_step": 435807, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0572309494018555, "global_step": 435808, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0529818534851074, "global_step": 435809, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.009823799133301, "global_step": 435810, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.065009593963623, "global_step": 435811, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9627692699432373, "global_step": 435812, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.047060489654541, "global_step": 435813, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.113961935043335, "global_step": 435814, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0846025943756104, "global_step": 435815, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1149814128875732, "global_step": 435816, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0500564575195312, "global_step": 435817, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.085867166519165, "global_step": 435818, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.049456834793091, "global_step": 435819, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1319398880004883, "global_step": 435820, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0887067317962646, "global_step": 435821, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.990036964416504, "global_step": 435822, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.061415672302246, "global_step": 435823, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0757923126220703, "global_step": 435824, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1091206073760986, "global_step": 435825, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9913526773452759, "global_step": 435826, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.120997428894043, "global_step": 435827, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1151540279388428, "global_step": 435828, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0787220001220703, "global_step": 435829, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.013364553451538, "global_step": 435830, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.157278060913086, "global_step": 435831, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0418736934661865, "global_step": 435832, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0958516597747803, "global_step": 435833, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1231300830841064, "global_step": 435834, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1259515285491943, "global_step": 435835, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0924203395843506, "global_step": 435836, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0261504650115967, "global_step": 435837, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.061743974685669, "global_step": 435838, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.2028002738952637, "global_step": 435839, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0364387035369873, "global_step": 435840, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1628503799438477, "global_step": 435841, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.030421495437622, "global_step": 435842, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.012209177017212, "global_step": 435843, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1721978187561035, "global_step": 435844, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.149972677230835, "global_step": 435845, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.145881414413452, "global_step": 435846, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.039299249649048, "global_step": 435847, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0925934314727783, "global_step": 435848, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.032654285430908, "global_step": 435849, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.048360586166382, "global_step": 435850, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0869216918945312, "global_step": 435851, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.113389253616333, "global_step": 435852, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1954259872436523, "global_step": 435853, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9851746559143066, "global_step": 435854, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.074357032775879, "global_step": 435855, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.085313558578491, "global_step": 435856, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.032275676727295, "global_step": 435857, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0341594219207764, "global_step": 435858, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0434751510620117, "global_step": 435859, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.083449363708496, "global_step": 435860, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0377140045166016, "global_step": 435861, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.059455633163452, "global_step": 435862, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1738219261169434, "global_step": 435863, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1215972900390625, "global_step": 435864, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0502371788024902, "global_step": 435865, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.131852149963379, "global_step": 435866, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1436145305633545, "global_step": 435867, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1461756229400635, "global_step": 435868, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0647482872009277, "global_step": 435869, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0889198780059814, "global_step": 435870, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1319658756256104, "global_step": 435871, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1156888008117676, "global_step": 435872, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0171058177948, "global_step": 435873, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0597708225250244, "global_step": 435874, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.024848699569702, "global_step": 435875, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.105970859527588, "global_step": 435876, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1456310749053955, "global_step": 435877, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.122337579727173, "global_step": 435878, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1257994174957275, "global_step": 435879, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0134189128875732, "global_step": 435880, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.037062406539917, "global_step": 435881, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.109328508377075, "global_step": 435882, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1125519275665283, "global_step": 435883, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.133394718170166, "global_step": 435884, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.134948968887329, "global_step": 435885, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.131481647491455, "global_step": 435886, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0466747283935547, "global_step": 435887, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.042966365814209, "global_step": 435888, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0843284130096436, "global_step": 435889, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.116657018661499, "global_step": 435890, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1449265480041504, "global_step": 435891, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.042860269546509, "global_step": 435892, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.109736680984497, "global_step": 435893, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0612521171569824, "global_step": 435894, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1535911560058594, "global_step": 435895, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.149244546890259, "global_step": 435896, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.2527475357055664, "global_step": 435897, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0579237937927246, "global_step": 435898, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1138479709625244, "global_step": 435899, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0626630783081055, "global_step": 435900, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1077609062194824, "global_step": 435901, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0751354694366455, "global_step": 435902, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1251070499420166, "global_step": 435903, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.052238702774048, "global_step": 435904, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0765490531921387, "global_step": 435905, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1193108558654785, "global_step": 435906, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1241233348846436, "global_step": 435907, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0614988803863525, "global_step": 435908, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.158668041229248, "global_step": 435909, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1088831424713135, "global_step": 435910, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0129644870758057, "global_step": 435911, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.01938796043396, "global_step": 435912, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0824830532073975, "global_step": 435913, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1013400554656982, "global_step": 435914, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9993038177490234, "global_step": 435915, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0855376720428467, "global_step": 435916, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0395607948303223, "global_step": 435917, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0525660514831543, "global_step": 435918, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0733349323272705, "global_step": 435919, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.050826072692871, "global_step": 435920, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.062652111053467, "global_step": 435921, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.064418077468872, "global_step": 435922, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.072317123413086, "global_step": 435923, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1269092559814453, "global_step": 435924, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.045304298400879, "global_step": 435925, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0998361110687256, "global_step": 435926, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1140925884246826, "global_step": 435927, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0368528366088867, "global_step": 435928, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.048123359680176, "global_step": 435929, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1211414337158203, "global_step": 435930, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.181619167327881, "global_step": 435931, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0330724716186523, "global_step": 435932, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.053727865219116, "global_step": 435933, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0878968238830566, "global_step": 435934, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1006298065185547, "global_step": 435935, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.022139072418213, "global_step": 435936, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0637459754943848, "global_step": 435937, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.049772024154663, "global_step": 435938, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.072492837905884, "global_step": 435939, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1314377784729004, "global_step": 435940, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.083834171295166, "global_step": 435941, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0644583702087402, "global_step": 435942, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0821797847747803, "global_step": 435943, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.931301474571228, "global_step": 435944, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0820446014404297, "global_step": 435945, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9939005374908447, "global_step": 435946, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0977091789245605, "global_step": 435947, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0802688598632812, "global_step": 435948, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0315849781036377, "global_step": 435949, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0783193111419678, "global_step": 435950, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0254669189453125, "global_step": 435951, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.070427656173706, "global_step": 435952, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.097546339035034, "global_step": 435953, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0190134048461914, "global_step": 435954, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.098299503326416, "global_step": 435955, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.038764238357544, "global_step": 435956, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.072943925857544, "global_step": 435957, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0194056034088135, "global_step": 435958, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9945311546325684, "global_step": 435959, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1571311950683594, "global_step": 435960, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0601842403411865, "global_step": 435961, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.051898956298828, "global_step": 435962, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0218405723571777, "global_step": 435963, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1544458866119385, "global_step": 435964, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1647961139678955, "global_step": 435965, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1493866443634033, "global_step": 435966, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.089529037475586, "global_step": 435967, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0487828254699707, "global_step": 435968, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0859923362731934, "global_step": 435969, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0298073291778564, "global_step": 435970, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1419472694396973, "global_step": 435971, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.963950514793396, "global_step": 435972, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.070801258087158, "global_step": 435973, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0630383491516113, "global_step": 435974, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.034510850906372, "global_step": 435975, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1508407592773438, "global_step": 435976, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1197385787963867, "global_step": 435977, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.175882339477539, "global_step": 435978, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0534510612487793, "global_step": 435979, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1641407012939453, "global_step": 435980, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0014681816101074, "global_step": 435981, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1073825359344482, "global_step": 435982, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1816017627716064, "global_step": 435983, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0653624534606934, "global_step": 435984, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.048476219177246, "global_step": 435985, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0591795444488525, "global_step": 435986, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0060877799987793, "global_step": 435987, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1051743030548096, "global_step": 435988, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.159214973449707, "global_step": 435989, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.109523057937622, "global_step": 435990, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1409692764282227, "global_step": 435991, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.08746337890625, "global_step": 435992, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.102116346359253, "global_step": 435993, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1712801456451416, "global_step": 435994, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1035866737365723, "global_step": 435995, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.043497085571289, "global_step": 435996, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0466952323913574, "global_step": 435997, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.130402088165283, "global_step": 435998, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.06708025932312, "global_step": 435999, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.173881769180298, "global_step": 436000, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9821635484695435, "global_step": 436001, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0216562747955322, "global_step": 436002, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0226449966430664, "global_step": 436003, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.086236000061035, "global_step": 436004, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0931107997894287, "global_step": 436005, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.024632692337036, "global_step": 436006, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.090639114379883, "global_step": 436007, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1094939708709717, "global_step": 436008, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.103365182876587, "global_step": 436009, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.096316337585449, "global_step": 436010, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1344869136810303, "global_step": 436011, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0238311290740967, "global_step": 436012, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0391016006469727, "global_step": 436013, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.152275562286377, "global_step": 436014, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0905532836914062, "global_step": 436015, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0893895626068115, "global_step": 436016, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0875332355499268, "global_step": 436017, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1146581172943115, "global_step": 436018, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0922322273254395, "global_step": 436019, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0304317474365234, "global_step": 436020, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0350193977355957, "global_step": 436021, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1652207374572754, "global_step": 436022, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.111257791519165, "global_step": 436023, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1023001670837402, "global_step": 436024, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1125426292419434, "global_step": 436025, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.169386148452759, "global_step": 436026, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1124439239501953, "global_step": 436027, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1140856742858887, "global_step": 436028, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.067363977432251, "global_step": 436029, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.025499105453491, "global_step": 436030, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.120246171951294, "global_step": 436031, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1133618354797363, "global_step": 436032, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0955281257629395, "global_step": 436033, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0873188972473145, "global_step": 436034, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0172345638275146, "global_step": 436035, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0697202682495117, "global_step": 436036, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0430667400360107, "global_step": 436037, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.115950584411621, "global_step": 436038, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1610844135284424, "global_step": 436039, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1531903743743896, "global_step": 436040, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.044353485107422, "global_step": 436041, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0767550468444824, "global_step": 436042, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.157240867614746, "global_step": 436043, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.148280143737793, "global_step": 436044, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0940427780151367, "global_step": 436045, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1605422496795654, "global_step": 436046, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1651906967163086, "global_step": 436047, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0774295330047607, "global_step": 436048, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.057574510574341, "global_step": 436049, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0997517108917236, "global_step": 436050, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.082900285720825, "global_step": 436051, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.061774253845215, "global_step": 436052, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.058466911315918, "global_step": 436053, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0769970417022705, "global_step": 436054, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1334431171417236, "global_step": 436055, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0905168056488037, "global_step": 436056, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9748737812042236, "global_step": 436057, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0908443927764893, "global_step": 436058, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1122546195983887, "global_step": 436059, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0756337642669678, "global_step": 436060, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.119378089904785, "global_step": 436061, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.112077236175537, "global_step": 436062, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0551087856292725, "global_step": 436063, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.092296600341797, "global_step": 436064, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1219851970672607, "global_step": 436065, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0559256076812744, "global_step": 436066, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.045872449874878, "global_step": 436067, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.2139389514923096, "global_step": 436068, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0590968132019043, "global_step": 436069, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.023789167404175, "global_step": 436070, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0963127613067627, "global_step": 436071, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.071021556854248, "global_step": 436072, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.167623996734619, "global_step": 436073, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1131443977355957, "global_step": 436074, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1068427562713623, "global_step": 436075, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.019057035446167, "global_step": 436076, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1153743267059326, "global_step": 436077, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.051537036895752, "global_step": 436078, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.045839309692383, "global_step": 436079, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1445720195770264, "global_step": 436080, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.111349582672119, "global_step": 436081, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9821994304656982, "global_step": 436082, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1231884956359863, "global_step": 436083, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1762938499450684, "global_step": 436084, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0617482662200928, "global_step": 436085, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0872886180877686, "global_step": 436086, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1235785484313965, "global_step": 436087, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.024289608001709, "global_step": 436088, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0993854999542236, "global_step": 436089, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1547141075134277, "global_step": 436090, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.021721839904785, "global_step": 436091, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1293606758117676, "global_step": 436092, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1431803703308105, "global_step": 436093, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.075535535812378, "global_step": 436094, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.118072271347046, "global_step": 436095, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1260263919830322, "global_step": 436096, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.066432476043701, "global_step": 436097, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0926694869995117, "global_step": 436098, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0966861248016357, "global_step": 436099, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.20143723487854, "global_step": 436100, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.074700355529785, "global_step": 436101, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.032048463821411, "global_step": 436102, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0704843997955322, "global_step": 436103, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1350646018981934, "global_step": 436104, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1767635345458984, "global_step": 436105, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.046112298965454, "global_step": 436106, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0635130405426025, "global_step": 436107, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.148897409439087, "global_step": 436108, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0845069885253906, "global_step": 436109, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0821595191955566, "global_step": 436110, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0302507877349854, "global_step": 436111, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.029644250869751, "global_step": 436112, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1257967948913574, "global_step": 436113, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0808005332946777, "global_step": 436114, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1106972694396973, "global_step": 436115, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.968505859375, "global_step": 436116, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.021542549133301, "global_step": 436117, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.082481622695923, "global_step": 436118, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0632898807525635, "global_step": 436119, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.151362657546997, "global_step": 436120, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1036553382873535, "global_step": 436121, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.128222942352295, "global_step": 436122, "epoch": 799, "lr": 5e-05}
{"train_loss": 1.9857728481292725, "global_step": 436123, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1596317291259766, "global_step": 436124, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.126635789871216, "global_step": 436125, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1269659996032715, "global_step": 436126, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1077182292938232, "global_step": 436127, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.086958885192871, "global_step": 436128, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1496686935424805, "global_step": 436129, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.088125228881836, "global_step": 436130, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1274845600128174, "global_step": 436131, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0774447917938232, "global_step": 436132, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0961294174194336, "global_step": 436133, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.119555950164795, "global_step": 436134, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0398025512695312, "global_step": 436135, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.082895040512085, "global_step": 436136, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.064894676208496, "global_step": 436137, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.044935941696167, "global_step": 436138, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0663721561431885, "global_step": 436139, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0498995780944824, "global_step": 436140, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.044339895248413, "global_step": 436141, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.041501045227051, "global_step": 436142, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0717601776123047, "global_step": 436143, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.06551456451416, "global_step": 436144, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0272216796875, "global_step": 436145, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.027867555618286, "global_step": 436146, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0179269313812256, "global_step": 436147, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.063610553741455, "global_step": 436148, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0262770652770996, "global_step": 436149, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.103358268737793, "global_step": 436150, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.094949722290039, "global_step": 436151, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.10127592086792, "global_step": 436152, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.193215847015381, "global_step": 436153, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1044609546661377, "global_step": 436154, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.009193181991577, "global_step": 436155, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1158900260925293, "global_step": 436156, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1325182914733887, "global_step": 436157, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0352120399475098, "global_step": 436158, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0811469554901123, "global_step": 436159, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.128201961517334, "global_step": 436160, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.104632616043091, "global_step": 436161, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0473287105560303, "global_step": 436162, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.2161142826080322, "global_step": 436163, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.066312551498413, "global_step": 436164, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.074093818664551, "global_step": 436165, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1949453353881836, "global_step": 436166, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.220911741256714, "global_step": 436167, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.043323278427124, "global_step": 436168, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0796024799346924, "global_step": 436169, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0477986335754395, "global_step": 436170, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.082801342010498, "global_step": 436171, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1738550662994385, "global_step": 436172, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.126599073410034, "global_step": 436173, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0552072525024414, "global_step": 436174, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.129685640335083, "global_step": 436175, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.121858596801758, "global_step": 436176, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.066035270690918, "global_step": 436177, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.053544282913208, "global_step": 436178, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1046292781829834, "global_step": 436179, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.1137638092041016, "global_step": 436180, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.044293165206909, "global_step": 436181, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.0811102390289307, "global_step": 436182, "epoch": 799, "lr": 5e-05}
{"train_loss": 2.020517349243164, "global_step": 436183, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.085237741470337, "global_step": 436184, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0391457080841064, "global_step": 436185, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9575961828231812, "global_step": 436186, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1051149368286133, "global_step": 436187, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0669450759887695, "global_step": 436188, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0861244201660156, "global_step": 436189, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0530917644500732, "global_step": 436190, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0505268573760986, "global_step": 436191, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0320403575897217, "global_step": 436192, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0078177452087402, "global_step": 436193, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.098644733428955, "global_step": 436194, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.066859245300293, "global_step": 436195, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0642130374908447, "global_step": 436196, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.091705799102783, "global_step": 436197, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.092190742492676, "global_step": 436198, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0669779777526855, "global_step": 436199, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0761971473693848, "global_step": 436200, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.081888198852539, "global_step": 436201, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0845887660980225, "global_step": 436202, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.159740924835205, "global_step": 436203, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.085346221923828, "global_step": 436204, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1309776306152344, "global_step": 436205, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1239724159240723, "global_step": 436206, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1462924480438232, "global_step": 436207, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0796117782592773, "global_step": 436208, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0849521160125732, "global_step": 436209, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0457589626312256, "global_step": 436210, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.070044755935669, "global_step": 436211, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0414912700653076, "global_step": 436212, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.020489454269409, "global_step": 436213, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9848531484603882, "global_step": 436214, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1349358558654785, "global_step": 436215, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9732211828231812, "global_step": 436216, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1071362495422363, "global_step": 436217, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.034254550933838, "global_step": 436218, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0247228145599365, "global_step": 436219, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0494086742401123, "global_step": 436220, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.091071844100952, "global_step": 436221, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1084742546081543, "global_step": 436222, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.068694591522217, "global_step": 436223, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0935752391815186, "global_step": 436224, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.049558162689209, "global_step": 436225, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.122530937194824, "global_step": 436226, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.973986268043518, "global_step": 436227, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1004748344421387, "global_step": 436228, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1122281551361084, "global_step": 436229, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.069542407989502, "global_step": 436230, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1502649784088135, "global_step": 436231, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0820109844207764, "global_step": 436232, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.042757987976074, "global_step": 436233, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0671324729919434, "global_step": 436234, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.105149269104004, "global_step": 436235, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1277687549591064, "global_step": 436236, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0387959480285645, "global_step": 436237, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1351466178894043, "global_step": 436238, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.019273042678833, "global_step": 436239, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1055431365966797, "global_step": 436240, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1035683155059814, "global_step": 436241, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0709116458892822, "global_step": 436242, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.101778268814087, "global_step": 436243, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.110239267349243, "global_step": 436244, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.095419406890869, "global_step": 436245, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.171165943145752, "global_step": 436246, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0916106700897217, "global_step": 436247, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.014601230621338, "global_step": 436248, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1001346111297607, "global_step": 436249, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0717036724090576, "global_step": 436250, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.016357183456421, "global_step": 436251, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0391297340393066, "global_step": 436252, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9970526695251465, "global_step": 436253, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.11244797706604, "global_step": 436254, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0747294425964355, "global_step": 436255, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1088085174560547, "global_step": 436256, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0640738010406494, "global_step": 436257, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.073005199432373, "global_step": 436258, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.035750150680542, "global_step": 436259, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.07897686958313, "global_step": 436260, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0538928508758545, "global_step": 436261, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.115910530090332, "global_step": 436262, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0517613887786865, "global_step": 436263, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.067598819732666, "global_step": 436264, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0347671508789062, "global_step": 436265, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.127065658569336, "global_step": 436266, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1065056324005127, "global_step": 436267, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.084030866622925, "global_step": 436268, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.98234224319458, "global_step": 436269, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9851874113082886, "global_step": 436270, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.087716817855835, "global_step": 436271, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.030569314956665, "global_step": 436272, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1133391857147217, "global_step": 436273, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.950061559677124, "global_step": 436274, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0792648792266846, "global_step": 436275, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0793023109436035, "global_step": 436276, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.972350835800171, "global_step": 436277, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0602188110351562, "global_step": 436278, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0677430629730225, "global_step": 436279, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1215131282806396, "global_step": 436280, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.148289918899536, "global_step": 436281, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.138122797012329, "global_step": 436282, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0679080486297607, "global_step": 436283, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.110372543334961, "global_step": 436284, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1825413703918457, "global_step": 436285, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.040684461593628, "global_step": 436286, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0313644409179688, "global_step": 436287, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1418559551239014, "global_step": 436288, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.026949882507324, "global_step": 436289, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0926852226257324, "global_step": 436290, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0834853649139404, "global_step": 436291, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1587986946105957, "global_step": 436292, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.122744083404541, "global_step": 436293, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.132422685623169, "global_step": 436294, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0159733295440674, "global_step": 436295, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0641705989837646, "global_step": 436296, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9852566719055176, "global_step": 436297, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.084402561187744, "global_step": 436298, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0772151947021484, "global_step": 436299, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0692191123962402, "global_step": 436300, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0429039001464844, "global_step": 436301, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.063600540161133, "global_step": 436302, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.117739677429199, "global_step": 436303, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.038992404937744, "global_step": 436304, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.031318426132202, "global_step": 436305, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9728792905807495, "global_step": 436306, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1743714809417725, "global_step": 436307, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0844767093658447, "global_step": 436308, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.121192216873169, "global_step": 436309, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0720767974853516, "global_step": 436310, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0904297828674316, "global_step": 436311, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1057698726654053, "global_step": 436312, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0503251552581787, "global_step": 436313, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1027402877807617, "global_step": 436314, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.12172794342041, "global_step": 436315, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0957250595092773, "global_step": 436316, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0016651153564453, "global_step": 436317, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0650174617767334, "global_step": 436318, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0612123012542725, "global_step": 436319, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.121962785720825, "global_step": 436320, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.008246421813965, "global_step": 436321, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.102219581604004, "global_step": 436322, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.103695869445801, "global_step": 436323, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.022172212600708, "global_step": 436324, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.072929620742798, "global_step": 436325, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0118064880371094, "global_step": 436326, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.022934913635254, "global_step": 436327, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0658762454986572, "global_step": 436328, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9475992918014526, "global_step": 436329, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0887720584869385, "global_step": 436330, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.065119743347168, "global_step": 436331, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0723369121551514, "global_step": 436332, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.096757650375366, "global_step": 436333, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1143360137939453, "global_step": 436334, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.990744709968567, "global_step": 436335, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.096003293991089, "global_step": 436336, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.072693347930908, "global_step": 436337, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.063750982284546, "global_step": 436338, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.088869571685791, "global_step": 436339, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.028294801712036, "global_step": 436340, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0862600803375244, "global_step": 436341, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0012264251708984, "global_step": 436342, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0214993953704834, "global_step": 436343, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.128803253173828, "global_step": 436344, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0927438735961914, "global_step": 436345, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1553144454956055, "global_step": 436346, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1112630367279053, "global_step": 436347, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.045724630355835, "global_step": 436348, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0276548862457275, "global_step": 436349, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.014309883117676, "global_step": 436350, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0041725635528564, "global_step": 436351, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0713353157043457, "global_step": 436352, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9945402145385742, "global_step": 436353, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.003530502319336, "global_step": 436354, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.039189100265503, "global_step": 436355, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.034172296524048, "global_step": 436356, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1317763328552246, "global_step": 436357, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1044046878814697, "global_step": 436358, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.135305881500244, "global_step": 436359, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0928726196289062, "global_step": 436360, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.130174160003662, "global_step": 436361, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0850636959075928, "global_step": 436362, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0747714042663574, "global_step": 436363, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1164791584014893, "global_step": 436364, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.090115785598755, "global_step": 436365, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0704779624938965, "global_step": 436366, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0940582752227783, "global_step": 436367, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.110687732696533, "global_step": 436368, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.08109450340271, "global_step": 436369, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0372371673583984, "global_step": 436370, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.022214412689209, "global_step": 436371, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0928590297698975, "global_step": 436372, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0248985290527344, "global_step": 436373, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0142455101013184, "global_step": 436374, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0097482204437256, "global_step": 436375, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0624051094055176, "global_step": 436376, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0499274730682373, "global_step": 436377, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0929059982299805, "global_step": 436378, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0880186557769775, "global_step": 436379, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0746796131134033, "global_step": 436380, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.032489776611328, "global_step": 436381, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.078004837036133, "global_step": 436382, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0118162631988525, "global_step": 436383, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0845119953155518, "global_step": 436384, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.116506814956665, "global_step": 436385, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.133711814880371, "global_step": 436386, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.174657106399536, "global_step": 436387, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0980303287506104, "global_step": 436388, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0193123817443848, "global_step": 436389, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.035452365875244, "global_step": 436390, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0789387226104736, "global_step": 436391, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.140098810195923, "global_step": 436392, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.073282480239868, "global_step": 436393, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.095092535018921, "global_step": 436394, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0869696140289307, "global_step": 436395, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.105872869491577, "global_step": 436396, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0485854148864746, "global_step": 436397, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0882318019866943, "global_step": 436398, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.105459451675415, "global_step": 436399, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.067692279815674, "global_step": 436400, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0761098861694336, "global_step": 436401, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.120774745941162, "global_step": 436402, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.098670482635498, "global_step": 436403, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0503733158111572, "global_step": 436404, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.067277193069458, "global_step": 436405, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0818445682525635, "global_step": 436406, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.04473614692688, "global_step": 436407, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0386626720428467, "global_step": 436408, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0901968479156494, "global_step": 436409, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0229103565216064, "global_step": 436410, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.065455675125122, "global_step": 436411, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.048241138458252, "global_step": 436412, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0960686206817627, "global_step": 436413, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.070791721343994, "global_step": 436414, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.068631887435913, "global_step": 436415, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.031977415084839, "global_step": 436416, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0687501430511475, "global_step": 436417, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0443427562713623, "global_step": 436418, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1067469120025635, "global_step": 436419, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.127458095550537, "global_step": 436420, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1399648189544678, "global_step": 436421, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.132636308670044, "global_step": 436422, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0370187759399414, "global_step": 436423, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.019127607345581, "global_step": 436424, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9733694791793823, "global_step": 436425, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.071747303009033, "global_step": 436426, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.053248405456543, "global_step": 436427, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9988188743591309, "global_step": 436428, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1429824829101562, "global_step": 436429, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.098891258239746, "global_step": 436430, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1183533668518066, "global_step": 436431, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.119478225708008, "global_step": 436432, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0697202682495117, "global_step": 436433, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0504648685455322, "global_step": 436434, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1261069774627686, "global_step": 436435, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0660440921783447, "global_step": 436436, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.101558208465576, "global_step": 436437, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.09462833404541, "global_step": 436438, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.073801040649414, "global_step": 436439, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0325915813446045, "global_step": 436440, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.044215202331543, "global_step": 436441, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0415050983428955, "global_step": 436442, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0762760639190674, "global_step": 436443, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.993981957435608, "global_step": 436444, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1017417907714844, "global_step": 436445, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.120009422302246, "global_step": 436446, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.053400993347168, "global_step": 436447, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.049738645553589, "global_step": 436448, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.086393356323242, "global_step": 436449, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.080024480819702, "global_step": 436450, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0430099964141846, "global_step": 436451, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0303947925567627, "global_step": 436452, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0483012199401855, "global_step": 436453, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.169463634490967, "global_step": 436454, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0965778827667236, "global_step": 436455, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0514066219329834, "global_step": 436456, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1358590126037598, "global_step": 436457, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0984342098236084, "global_step": 436458, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1171205043792725, "global_step": 436459, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0727710723876953, "global_step": 436460, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.113788366317749, "global_step": 436461, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0919697284698486, "global_step": 436462, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.2072505950927734, "global_step": 436463, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.020749807357788, "global_step": 436464, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1341731548309326, "global_step": 436465, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0887207984924316, "global_step": 436466, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0867977142333984, "global_step": 436467, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0504510402679443, "global_step": 436468, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1102449893951416, "global_step": 436469, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0554049015045166, "global_step": 436470, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0024771690368652, "global_step": 436471, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0867671966552734, "global_step": 436472, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.19105863571167, "global_step": 436473, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.021637439727783, "global_step": 436474, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0844783782958984, "global_step": 436475, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1459083557128906, "global_step": 436476, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0966415405273438, "global_step": 436477, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0454888343811035, "global_step": 436478, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.053448438644409, "global_step": 436479, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.106548309326172, "global_step": 436480, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0023577213287354, "global_step": 436481, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0625979900360107, "global_step": 436482, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0080606937408447, "global_step": 436483, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.147286891937256, "global_step": 436484, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.115633010864258, "global_step": 436485, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0376880168914795, "global_step": 436486, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0196502208709717, "global_step": 436487, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1174814701080322, "global_step": 436488, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.093499183654785, "global_step": 436489, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.007750988006592, "global_step": 436490, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0571067333221436, "global_step": 436491, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0688042640686035, "global_step": 436492, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.031277894973755, "global_step": 436493, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9905811548233032, "global_step": 436494, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1086392402648926, "global_step": 436495, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0472898483276367, "global_step": 436496, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.090843677520752, "global_step": 436497, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.13167142868042, "global_step": 436498, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0439181327819824, "global_step": 436499, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.055755853652954, "global_step": 436500, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0790293216705322, "global_step": 436501, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0732057094573975, "global_step": 436502, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0889909267425537, "global_step": 436503, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1090807914733887, "global_step": 436504, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0440235137939453, "global_step": 436505, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.058969020843506, "global_step": 436506, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0823869705200195, "global_step": 436507, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0513384342193604, "global_step": 436508, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.072068691253662, "global_step": 436509, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1121304035186768, "global_step": 436510, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.072941780090332, "global_step": 436511, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.088156223297119, "global_step": 436512, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.094507932662964, "global_step": 436513, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1196539402008057, "global_step": 436514, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1022629737854004, "global_step": 436515, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1114895343780518, "global_step": 436516, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0674588680267334, "global_step": 436517, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.071423292160034, "global_step": 436518, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0388855934143066, "global_step": 436519, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.025707960128784, "global_step": 436520, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0578832626342773, "global_step": 436521, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.12044620513916, "global_step": 436522, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0616767406463623, "global_step": 436523, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9844536781311035, "global_step": 436524, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.160287618637085, "global_step": 436525, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0370471477508545, "global_step": 436526, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.087026357650757, "global_step": 436527, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1792049407958984, "global_step": 436528, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1389713287353516, "global_step": 436529, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.010441541671753, "global_step": 436530, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.122831344604492, "global_step": 436531, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.165543794631958, "global_step": 436532, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1050209999084473, "global_step": 436533, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.106492519378662, "global_step": 436534, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9770011901855469, "global_step": 436535, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1135404109954834, "global_step": 436536, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0667781829833984, "global_step": 436537, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.007683753967285, "global_step": 436538, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0940656661987305, "global_step": 436539, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.14432954788208, "global_step": 436540, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.108393430709839, "global_step": 436541, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.264777898788452, "global_step": 436542, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0477709770202637, "global_step": 436543, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1080117225646973, "global_step": 436544, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.058892011642456, "global_step": 436545, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0514614582061768, "global_step": 436546, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1158905029296875, "global_step": 436547, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.031454086303711, "global_step": 436548, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1484456062316895, "global_step": 436549, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0982494354248047, "global_step": 436550, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0645763874053955, "global_step": 436551, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1488871574401855, "global_step": 436552, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1279709339141846, "global_step": 436553, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0295002460479736, "global_step": 436554, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0998687744140625, "global_step": 436555, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0700294971466064, "global_step": 436556, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.982072353363037, "global_step": 436557, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0809223651885986, "global_step": 436558, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0702128410339355, "global_step": 436559, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1285295486450195, "global_step": 436560, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.134974479675293, "global_step": 436561, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1212821006774902, "global_step": 436562, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0778956413269043, "global_step": 436563, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.131913423538208, "global_step": 436564, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0746376514434814, "global_step": 436565, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0571787357330322, "global_step": 436566, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.031968593597412, "global_step": 436567, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.109290838241577, "global_step": 436568, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.143714666366577, "global_step": 436569, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.10634708404541, "global_step": 436570, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1445930004119873, "global_step": 436571, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.057637929916382, "global_step": 436572, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1069765090942383, "global_step": 436573, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.113166332244873, "global_step": 436574, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.141101598739624, "global_step": 436575, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1415317058563232, "global_step": 436576, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0693633556365967, "global_step": 436577, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.100754737854004, "global_step": 436578, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.042860746383667, "global_step": 436579, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1035585403442383, "global_step": 436580, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0489280223846436, "global_step": 436581, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.007795572280884, "global_step": 436582, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.988043189048767, "global_step": 436583, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1249561309814453, "global_step": 436584, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.122744560241699, "global_step": 436585, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9958362579345703, "global_step": 436586, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0194458961486816, "global_step": 436587, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0790979862213135, "global_step": 436588, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0600340366363525, "global_step": 436589, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.078230381011963, "global_step": 436590, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.069687843322754, "global_step": 436591, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.108328104019165, "global_step": 436592, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0897860527038574, "global_step": 436593, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1196861267089844, "global_step": 436594, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0356149673461914, "global_step": 436595, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.137770652770996, "global_step": 436596, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0511679649353027, "global_step": 436597, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0501255989074707, "global_step": 436598, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0613229274749756, "global_step": 436599, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1053428649902344, "global_step": 436600, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0762979984283447, "global_step": 436601, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0679421424865723, "global_step": 436602, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.128706216812134, "global_step": 436603, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9799333810806274, "global_step": 436604, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.072894334793091, "global_step": 436605, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.092360258102417, "global_step": 436606, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.063532829284668, "global_step": 436607, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0572316646575928, "global_step": 436608, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0694260597229004, "global_step": 436609, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.119277238845825, "global_step": 436610, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1072916984558105, "global_step": 436611, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0463180541992188, "global_step": 436612, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9929742813110352, "global_step": 436613, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1093928813934326, "global_step": 436614, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.027958869934082, "global_step": 436615, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.120309829711914, "global_step": 436616, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.087545156478882, "global_step": 436617, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.089773178100586, "global_step": 436618, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.061398506164551, "global_step": 436619, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1548120975494385, "global_step": 436620, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.094970703125, "global_step": 436621, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1546847820281982, "global_step": 436622, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0799777507781982, "global_step": 436623, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.065016269683838, "global_step": 436624, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0416946411132812, "global_step": 436625, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.038980722427368, "global_step": 436626, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0303966999053955, "global_step": 436627, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.105529546737671, "global_step": 436628, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.105517625808716, "global_step": 436629, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.035390615463257, "global_step": 436630, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1066951751708984, "global_step": 436631, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1153697967529297, "global_step": 436632, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.029728889465332, "global_step": 436633, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.09918212890625, "global_step": 436634, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.975541591644287, "global_step": 436635, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9977272748947144, "global_step": 436636, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0815393924713135, "global_step": 436637, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1029365062713623, "global_step": 436638, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0734643936157227, "global_step": 436639, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.072620391845703, "global_step": 436640, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1399786472320557, "global_step": 436641, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0197510719299316, "global_step": 436642, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1124086380004883, "global_step": 436643, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1113476753234863, "global_step": 436644, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0162830352783203, "global_step": 436645, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1506524085998535, "global_step": 436646, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0563907623291016, "global_step": 436647, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.111138343811035, "global_step": 436648, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1067631244659424, "global_step": 436649, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.17637038230896, "global_step": 436650, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.136408567428589, "global_step": 436651, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.008406162261963, "global_step": 436652, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.186379909515381, "global_step": 436653, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0610263347625732, "global_step": 436654, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1553783416748047, "global_step": 436655, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9898642301559448, "global_step": 436656, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0877914428710938, "global_step": 436657, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0454354286193848, "global_step": 436658, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0582592487335205, "global_step": 436659, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.060821771621704, "global_step": 436660, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0268707275390625, "global_step": 436661, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0371804237365723, "global_step": 436662, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.108856678009033, "global_step": 436663, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.062798500061035, "global_step": 436664, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1252996921539307, "global_step": 436665, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.105128526687622, "global_step": 436666, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.116091728210449, "global_step": 436667, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.123607635498047, "global_step": 436668, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.071620464324951, "global_step": 436669, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.031193733215332, "global_step": 436670, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1105756759643555, "global_step": 436671, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0711283683776855, "global_step": 436672, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0826399326324463, "global_step": 436673, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1345059871673584, "global_step": 436674, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0852243900299072, "global_step": 436675, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.017947196960449, "global_step": 436676, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0315279960632324, "global_step": 436677, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0758283138275146, "global_step": 436678, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.028047800064087, "global_step": 436679, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1279735565185547, "global_step": 436680, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.092466354370117, "global_step": 436681, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0761921405792236, "global_step": 436682, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.097679853439331, "global_step": 436683, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0351102352142334, "global_step": 436684, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.031183958053589, "global_step": 436685, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0345354080200195, "global_step": 436686, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.073090076446533, "global_step": 436687, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.080223560333252, "global_step": 436688, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.193753480911255, "global_step": 436689, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.150702953338623, "global_step": 436690, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9890415668487549, "global_step": 436691, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0975441932678223, "global_step": 436692, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.995345950126648, "global_step": 436693, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0398383140563965, "global_step": 436694, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0702338218688965, "global_step": 436695, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9987218379974365, "global_step": 436696, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.2161946296691895, "global_step": 436697, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0800554752349854, "global_step": 436698, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0132973194122314, "global_step": 436699, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0893261432647705, "global_step": 436700, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.210763692855835, "global_step": 436701, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0728583335876465, "global_step": 436702, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.006352186203003, "global_step": 436703, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.135603904724121, "global_step": 436704, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1294853687286377, "global_step": 436705, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0906898975372314, "global_step": 436706, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.090081214904785, "global_step": 436707, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9943877458572388, "global_step": 436708, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1342930793762207, "global_step": 436709, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0906267166137695, "global_step": 436710, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9296842813491821, "global_step": 436711, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.170131206512451, "global_step": 436712, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.142913818359375, "global_step": 436713, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1291046142578125, "global_step": 436714, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0781662464141846, "global_step": 436715, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9830529689788818, "global_step": 436716, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1126327514648438, "global_step": 436717, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0665173530578613, "global_step": 436718, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.110710859298706, "global_step": 436719, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0095267295837402, "global_step": 436720, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1256468296051025, "global_step": 436721, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.042489767074585, "global_step": 436722, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.065553903579712, "global_step": 436723, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0295772552490234, "global_step": 436724, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.098644971847534, "global_step": 436725, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.17022967338562, "global_step": 436726, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.956393837928772, "global_step": 436727, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.098090410232544, "global_step": 436728, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0773580074310303, "global_step": 436729, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0410799980163574, "global_step": 436730, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1477513313293457, "global_step": 436731, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1587979793548584, "global_step": 436732, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0977818965911865, "global_step": 436733, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1011993885040283, "global_step": 436734, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0576021671295166, "global_step": 436735, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0806283950805664, "global_step": 436736, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.08475399017334, "global_step": 436737, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0758252143859863, "global_step": 436738, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1066291332244873, "global_step": 436739, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.005262851715088, "global_step": 436740, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1036908626556396, "global_step": 436741, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1224453449249268, "global_step": 436742, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.079288959503174, "global_step": 436743, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0379109382629395, "global_step": 436744, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0923802852630615, "global_step": 436745, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.085439443588257, "global_step": 436746, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9527778625488281, "global_step": 436747, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0681283473968506, "global_step": 436748, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.180220603942871, "global_step": 436749, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.078965187072754, "global_step": 436750, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1096198558807373, "global_step": 436751, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1630120277404785, "global_step": 436752, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0902602672576904, "global_step": 436753, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0757007598876953, "global_step": 436754, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0365848541259766, "global_step": 436755, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0703201293945312, "global_step": 436756, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0951693058013916, "global_step": 436757, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0038111209869385, "global_step": 436758, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1467719078063965, "global_step": 436759, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1325173377990723, "global_step": 436760, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0802040100097656, "global_step": 436761, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.047912359237671, "global_step": 436762, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0669686794281006, "global_step": 436763, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0549583435058594, "global_step": 436764, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0540266036987305, "global_step": 436765, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1627469062805176, "global_step": 436766, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1116178035736084, "global_step": 436767, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.081036329269409, "global_step": 436768, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1397736072540283, "global_step": 436769, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0401108264923096, "global_step": 436770, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.091435432434082, "global_step": 436771, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0789146423339844, "global_step": 436772, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.054095506668091, "global_step": 436773, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.097076416015625, "global_step": 436774, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.048793077468872, "global_step": 436775, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.072157859802246, "global_step": 436776, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.058922290802002, "global_step": 436777, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.094388008117676, "global_step": 436778, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0808115005493164, "global_step": 436779, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0402958393096924, "global_step": 436780, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.128171920776367, "global_step": 436781, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.02091383934021, "global_step": 436782, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0855629444122314, "global_step": 436783, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.090581178665161, "global_step": 436784, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0125389099121094, "global_step": 436785, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1277027130126953, "global_step": 436786, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.067551851272583, "global_step": 436787, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0922250747680664, "global_step": 436788, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0669426918029785, "global_step": 436789, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0591914653778076, "global_step": 436790, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0256235599517822, "global_step": 436791, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0259463787078857, "global_step": 436792, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.124805212020874, "global_step": 436793, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1322319507598877, "global_step": 436794, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0328619480133057, "global_step": 436795, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0815224647521973, "global_step": 436796, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.080733299255371, "global_step": 436797, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.011603593826294, "global_step": 436798, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.045379400253296, "global_step": 436799, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.133333206176758, "global_step": 436800, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1071836948394775, "global_step": 436801, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1076087951660156, "global_step": 436802, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.087036609649658, "global_step": 436803, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0470316410064697, "global_step": 436804, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.138576030731201, "global_step": 436805, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.114243268966675, "global_step": 436806, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0747292041778564, "global_step": 436807, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0605204105377197, "global_step": 436808, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9603444337844849, "global_step": 436809, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0174922943115234, "global_step": 436810, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0834436416625977, "global_step": 436811, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0971381664276123, "global_step": 436812, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.107252597808838, "global_step": 436813, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0972158908843994, "global_step": 436814, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.031099319458008, "global_step": 436815, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.047041893005371, "global_step": 436816, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.069981575012207, "global_step": 436817, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0694499015808105, "global_step": 436818, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0772669315338135, "global_step": 436819, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1250739097595215, "global_step": 436820, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.089170455932617, "global_step": 436821, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0967769622802734, "global_step": 436822, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.165097236633301, "global_step": 436823, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0350852012634277, "global_step": 436824, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.053945302963257, "global_step": 436825, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0768072605133057, "global_step": 436826, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.056630849838257, "global_step": 436827, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.086205005645752, "global_step": 436828, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.14009690284729, "global_step": 436829, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.150315046310425, "global_step": 436830, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.093078851699829, "global_step": 436831, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.057323455810547, "global_step": 436832, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0901670455932617, "global_step": 436833, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0476343631744385, "global_step": 436834, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0082757472991943, "global_step": 436835, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.057671546936035, "global_step": 436836, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9400578737258911, "global_step": 436837, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0866732597351074, "global_step": 436838, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.013908624649048, "global_step": 436839, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0247719287872314, "global_step": 436840, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0929739475250244, "global_step": 436841, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1070573329925537, "global_step": 436842, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.155860662460327, "global_step": 436843, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0218944549560547, "global_step": 436844, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1131200790405273, "global_step": 436845, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9977943897247314, "global_step": 436846, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1592013835906982, "global_step": 436847, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.017648935317993, "global_step": 436848, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.097781181335449, "global_step": 436849, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.030909299850464, "global_step": 436850, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0680482387542725, "global_step": 436851, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0807580947875977, "global_step": 436852, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.076059103012085, "global_step": 436853, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1019814014434814, "global_step": 436854, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9823969602584839, "global_step": 436855, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1345999240875244, "global_step": 436856, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0981650352478027, "global_step": 436857, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.145245313644409, "global_step": 436858, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0736632347106934, "global_step": 436859, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.112548351287842, "global_step": 436860, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0098984241485596, "global_step": 436861, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1506364345550537, "global_step": 436862, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1106438636779785, "global_step": 436863, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1019766330718994, "global_step": 436864, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1330854892730713, "global_step": 436865, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.2555294036865234, "global_step": 436866, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0860183238983154, "global_step": 436867, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.208047866821289, "global_step": 436868, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.074502944946289, "global_step": 436869, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.095705986022949, "global_step": 436870, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1494650840759277, "global_step": 436871, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0755629539489746, "global_step": 436872, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1180214881896973, "global_step": 436873, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1350760459899902, "global_step": 436874, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1495144367218018, "global_step": 436875, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.072843074798584, "global_step": 436876, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1148743629455566, "global_step": 436877, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0061209201812744, "global_step": 436878, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.104952096939087, "global_step": 436879, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1814286708831787, "global_step": 436880, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0967350006103516, "global_step": 436881, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1283907890319824, "global_step": 436882, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0698063373565674, "global_step": 436883, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.084280014038086, "global_step": 436884, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1017656326293945, "global_step": 436885, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.026013135910034, "global_step": 436886, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0764429569244385, "global_step": 436887, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0585367679595947, "global_step": 436888, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0819075107574463, "global_step": 436889, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.187495470046997, "global_step": 436890, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.10746693611145, "global_step": 436891, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0010812282562256, "global_step": 436892, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1065306663513184, "global_step": 436893, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1173932552337646, "global_step": 436894, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0746541023254395, "global_step": 436895, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1546523571014404, "global_step": 436896, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.148097038269043, "global_step": 436897, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1441261768341064, "global_step": 436898, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0308573246002197, "global_step": 436899, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0528564453125, "global_step": 436900, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0393145084381104, "global_step": 436901, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0658676624298096, "global_step": 436902, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.122789144515991, "global_step": 436903, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1212782859802246, "global_step": 436904, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.053015947341919, "global_step": 436905, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.058619260787964, "global_step": 436906, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1353166103363037, "global_step": 436907, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.099191188812256, "global_step": 436908, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.011981248855591, "global_step": 436909, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.033796787261963, "global_step": 436910, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0806753635406494, "global_step": 436911, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0328915119171143, "global_step": 436912, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0912559032440186, "global_step": 436913, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.070749044418335, "global_step": 436914, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.035022497177124, "global_step": 436915, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0741841793060303, "global_step": 436916, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.034515142440796, "global_step": 436917, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.064779758453369, "global_step": 436918, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1189706325531006, "global_step": 436919, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.074202060699463, "global_step": 436920, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0582435131073, "global_step": 436921, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0547287464141846, "global_step": 436922, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.088456630706787, "global_step": 436923, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.107761859893799, "global_step": 436924, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0945510864257812, "global_step": 436925, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0762736797332764, "global_step": 436926, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.034057378768921, "global_step": 436927, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.075331687927246, "global_step": 436928, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1547391414642334, "global_step": 436929, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0724971294403076, "global_step": 436930, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.983272910118103, "global_step": 436931, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0512266159057617, "global_step": 436932, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.08774733543396, "global_step": 436933, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9673123359680176, "global_step": 436934, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0982391834259033, "global_step": 436935, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.018038511276245, "global_step": 436936, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0968520641326904, "global_step": 436937, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0267183780670166, "global_step": 436938, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0904462337493896, "global_step": 436939, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.086024045944214, "global_step": 436940, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0705714225769043, "global_step": 436941, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1181328296661377, "global_step": 436942, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.113170623779297, "global_step": 436943, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0526466369628906, "global_step": 436944, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0382723808288574, "global_step": 436945, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.077094554901123, "global_step": 436946, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0866270065307617, "global_step": 436947, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1409974098205566, "global_step": 436948, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0979111194610596, "global_step": 436949, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.153763771057129, "global_step": 436950, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.001455783843994, "global_step": 436951, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.173037052154541, "global_step": 436952, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.201559066772461, "global_step": 436953, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.109734535217285, "global_step": 436954, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0853171348571777, "global_step": 436955, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.108574628829956, "global_step": 436956, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1011013984680176, "global_step": 436957, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.172044277191162, "global_step": 436958, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0959043502807617, "global_step": 436959, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.112912893295288, "global_step": 436960, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0451505184173584, "global_step": 436961, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0449702739715576, "global_step": 436962, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1194818019866943, "global_step": 436963, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.2139344215393066, "global_step": 436964, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.10953688621521, "global_step": 436965, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.119403839111328, "global_step": 436966, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.151798963546753, "global_step": 436967, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0123867988586426, "global_step": 436968, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.14516544342041, "global_step": 436969, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0087649822235107, "global_step": 436970, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0240414142608643, "global_step": 436971, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.010293483734131, "global_step": 436972, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.115992784500122, "global_step": 436973, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.137805700302124, "global_step": 436974, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0983364582061768, "global_step": 436975, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.016695499420166, "global_step": 436976, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0749940872192383, "global_step": 436977, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1056323051452637, "global_step": 436978, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.040163278579712, "global_step": 436979, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0879266262054443, "global_step": 436980, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1077582836151123, "global_step": 436981, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.088991165161133, "global_step": 436982, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0397140979766846, "global_step": 436983, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1064209938049316, "global_step": 436984, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.163998603820801, "global_step": 436985, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0110256671905518, "global_step": 436986, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.054152488708496, "global_step": 436987, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1308741569519043, "global_step": 436988, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.049281120300293, "global_step": 436989, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.104628324508667, "global_step": 436990, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.053422451019287, "global_step": 436991, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.071949005126953, "global_step": 436992, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.067260265350342, "global_step": 436993, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0886409282684326, "global_step": 436994, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.112532377243042, "global_step": 436995, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.098414897918701, "global_step": 436996, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1264760494232178, "global_step": 436997, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.058300733566284, "global_step": 436998, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0660219192504883, "global_step": 436999, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1310768127441406, "global_step": 437000, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.008676052093506, "global_step": 437001, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0341975688934326, "global_step": 437002, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0966928005218506, "global_step": 437003, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0242950916290283, "global_step": 437004, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.207836151123047, "global_step": 437005, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.044053077697754, "global_step": 437006, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.130964517593384, "global_step": 437007, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1021392345428467, "global_step": 437008, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0924041271209717, "global_step": 437009, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.060368061065674, "global_step": 437010, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0875489711761475, "global_step": 437011, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.128032684326172, "global_step": 437012, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.115349054336548, "global_step": 437013, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1128108501434326, "global_step": 437014, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0023207664489746, "global_step": 437015, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.049888849258423, "global_step": 437016, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.062565565109253, "global_step": 437017, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0062098503112793, "global_step": 437018, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0642426013946533, "global_step": 437019, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9870346784591675, "global_step": 437020, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0795657634735107, "global_step": 437021, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0117125511169434, "global_step": 437022, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.044482946395874, "global_step": 437023, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1059908866882324, "global_step": 437024, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0634124279022217, "global_step": 437025, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1674957275390625, "global_step": 437026, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0839786529541016, "global_step": 437027, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1238653659820557, "global_step": 437028, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.068676471710205, "global_step": 437029, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1348862648010254, "global_step": 437030, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1037209033966064, "global_step": 437031, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.03948974609375, "global_step": 437032, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.097341537475586, "global_step": 437033, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0850670337677, "global_step": 437034, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.139707326889038, "global_step": 437035, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0311782360076904, "global_step": 437036, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.971348524093628, "global_step": 437037, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.047041416168213, "global_step": 437038, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.151508331298828, "global_step": 437039, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.983824372291565, "global_step": 437040, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0814921855926514, "global_step": 437041, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.054121971130371, "global_step": 437042, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0602171421051025, "global_step": 437043, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.060323476791382, "global_step": 437044, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.177182197570801, "global_step": 437045, "epoch": 800, "lr": 5e-05}
{"train_loss": 1.9848341941833496, "global_step": 437046, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.019063949584961, "global_step": 437047, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0378947257995605, "global_step": 437048, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0650229454040527, "global_step": 437049, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1251237392425537, "global_step": 437050, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0393216609954834, "global_step": 437051, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0543272495269775, "global_step": 437052, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.142869710922241, "global_step": 437053, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0466408729553223, "global_step": 437054, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.085047721862793, "global_step": 437055, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0191569328308105, "global_step": 437056, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.019547700881958, "global_step": 437057, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0420100688934326, "global_step": 437058, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.041239023208618, "global_step": 437059, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0466463565826416, "global_step": 437060, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0944747924804688, "global_step": 437061, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1280572414398193, "global_step": 437062, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0118556022644043, "global_step": 437063, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0672733783721924, "global_step": 437064, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.077310800552368, "global_step": 437065, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1270055770874023, "global_step": 437066, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0568530559539795, "global_step": 437067, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0304388999938965, "global_step": 437068, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.049076795578003, "global_step": 437069, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0379862785339355, "global_step": 437070, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.117086887359619, "global_step": 437071, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.127277135848999, "global_step": 437072, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.134737968444824, "global_step": 437073, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0667519569396973, "global_step": 437074, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.093968629837036, "global_step": 437075, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1527903079986572, "global_step": 437076, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0449936389923096, "global_step": 437077, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.07979679107666, "global_step": 437078, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.005337715148926, "global_step": 437079, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0747838020324707, "global_step": 437080, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1778998374938965, "global_step": 437081, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0081119537353516, "global_step": 437082, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.062795400619507, "global_step": 437083, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.079632043838501, "global_step": 437084, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0440421104431152, "global_step": 437085, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.07743239402771, "global_step": 437086, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0754854679107666, "global_step": 437087, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.083712577819824, "global_step": 437088, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0269811153411865, "global_step": 437089, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.099468946456909, "global_step": 437090, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0752577781677246, "global_step": 437091, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0516815185546875, "global_step": 437092, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0296976566314697, "global_step": 437093, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0443274974823, "global_step": 437094, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.2524545192718506, "global_step": 437095, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.038245916366577, "global_step": 437096, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0686917304992676, "global_step": 437097, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1340837478637695, "global_step": 437098, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.018096685409546, "global_step": 437099, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1215567588806152, "global_step": 437100, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1092286109924316, "global_step": 437101, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.033297061920166, "global_step": 437102, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0448522567749023, "global_step": 437103, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0724058151245117, "global_step": 437104, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.110496759414673, "global_step": 437105, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0903830528259277, "global_step": 437106, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0846517086029053, "global_step": 437107, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1342885494232178, "global_step": 437108, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0283424854278564, "global_step": 437109, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0941126346588135, "global_step": 437110, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1364104747772217, "global_step": 437111, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.062882900238037, "global_step": 437112, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0902252197265625, "global_step": 437113, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.079946279525757, "global_step": 437114, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1027071475982666, "global_step": 437115, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.221468925476074, "global_step": 437116, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0683209896087646, "global_step": 437117, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0647261142730713, "global_step": 437118, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.150883913040161, "global_step": 437119, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0847349166870117, "global_step": 437120, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1549134254455566, "global_step": 437121, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.115366220474243, "global_step": 437122, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1248393058776855, "global_step": 437123, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.141803026199341, "global_step": 437124, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.095012903213501, "global_step": 437125, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1621005535125732, "global_step": 437126, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1956393718719482, "global_step": 437127, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.129706621170044, "global_step": 437128, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.107004165649414, "global_step": 437129, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.128260850906372, "global_step": 437130, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0825042724609375, "global_step": 437131, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.083989143371582, "global_step": 437132, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0805671215057373, "global_step": 437133, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.027266502380371, "global_step": 437134, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0570101737976074, "global_step": 437135, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.099374294281006, "global_step": 437136, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0347068309783936, "global_step": 437137, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.05993390083313, "global_step": 437138, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1204378604888916, "global_step": 437139, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.184123992919922, "global_step": 437140, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.08412766456604, "global_step": 437141, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0262038707733154, "global_step": 437142, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.102630138397217, "global_step": 437143, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0991132259368896, "global_step": 437144, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0598578453063965, "global_step": 437145, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0374338626861572, "global_step": 437146, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0436854362487793, "global_step": 437147, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.096323013305664, "global_step": 437148, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.1791975498199463, "global_step": 437149, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.0779361724853516, "global_step": 437150, "epoch": 800, "lr": 5e-05}
{"train_loss": 2.079190492630005, "global_step": 437151, "epoch": 800, "lr": 5e-05, "KITCHEN_SCENE6_put_the_yellow_and_white_mug_in_the_microwave_and_close_it/mean_success_rate": 0.8666666666666667, "LIVING_ROOM_SCENE2_put_both_the_alphabet_soup_and_the_tomato_sauce_in_the_basket/mean_success_rate": 0.0, "STUDY_SCENE1_pick_up_the_book_and_place_it_in_the_back_compartment_of_the_caddy/mean_success_rate": 0.5666666666666667, "KITCHEN_SCENE8_put_both_moka_pots_on_the_stove/mean_success_rate": 0.5333333333333333, "LIVING_ROOM_SCENE5_put_the_white_mug_on_the_left_plate_and_put_the_yellow_and_white_mug_on_the_right_plate/mean_success_rate": 0.36666666666666664, "LIVING_ROOM_SCENE6_put_the_white_mug_on_the_plate_and_put_the_chocolate_pudding_to_the_right_of_the_plate/mean_success_rate": 0.2, "KITCHEN_SCENE4_put_the_black_bowl_in_the_bottom_drawer_of_the_cabinet_and_close_it/mean_success_rate": 0.9666666666666667, "LIVING_ROOM_SCENE2_put_both_the_cream_cheese_box_and_the_butter_in_the_basket/mean_success_rate": 0.7, "LIVING_ROOM_SCENE1_put_both_the_alphabet_soup_and_the_cream_cheese_box_in_the_basket/mean_success_rate": 0.0, "KITCHEN_SCENE3_turn_on_the_stove_and_put_the_moka_pot_on_it/mean_success_rate": 0.8333333333333334, "mean_success_rate": 0.5033333333333333, "val_loss": 5.656228542327881, "test_reconst_mse": 0.07311995327472687}
{"train_loss": 2.061033010482788, "global_step": 437152, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.092952013015747, "global_step": 437153, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.024308681488037, "global_step": 437154, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.075439214706421, "global_step": 437155, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.108003616333008, "global_step": 437156, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.156960964202881, "global_step": 437157, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0250961780548096, "global_step": 437158, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.120579481124878, "global_step": 437159, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0971519947052, "global_step": 437160, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1628899574279785, "global_step": 437161, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.118802309036255, "global_step": 437162, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.013120174407959, "global_step": 437163, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0812599658966064, "global_step": 437164, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1223769187927246, "global_step": 437165, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0350401401519775, "global_step": 437166, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.084808111190796, "global_step": 437167, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.019779920578003, "global_step": 437168, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.11224365234375, "global_step": 437169, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1289596557617188, "global_step": 437170, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.078636407852173, "global_step": 437171, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.104523181915283, "global_step": 437172, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.124816417694092, "global_step": 437173, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0846803188323975, "global_step": 437174, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.045491933822632, "global_step": 437175, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.999550700187683, "global_step": 437176, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.005110263824463, "global_step": 437177, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0620577335357666, "global_step": 437178, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.130859851837158, "global_step": 437179, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9629346132278442, "global_step": 437180, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.103090763092041, "global_step": 437181, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0462563037872314, "global_step": 437182, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1333792209625244, "global_step": 437183, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.036292791366577, "global_step": 437184, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0328855514526367, "global_step": 437185, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0640456676483154, "global_step": 437186, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0075645446777344, "global_step": 437187, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.054094076156616, "global_step": 437188, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.144213914871216, "global_step": 437189, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.052497625350952, "global_step": 437190, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1075518131256104, "global_step": 437191, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.976158618927002, "global_step": 437192, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.044339656829834, "global_step": 437193, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.092291831970215, "global_step": 437194, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0396311283111572, "global_step": 437195, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0709500312805176, "global_step": 437196, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.011406183242798, "global_step": 437197, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1904683113098145, "global_step": 437198, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.066908121109009, "global_step": 437199, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0445051193237305, "global_step": 437200, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1834022998809814, "global_step": 437201, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.049009323120117, "global_step": 437202, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.016751527786255, "global_step": 437203, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0390350818634033, "global_step": 437204, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.173149824142456, "global_step": 437205, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.11327862739563, "global_step": 437206, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0681087970733643, "global_step": 437207, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.003048896789551, "global_step": 437208, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.035390853881836, "global_step": 437209, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1078124046325684, "global_step": 437210, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.092663288116455, "global_step": 437211, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1842501163482666, "global_step": 437212, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1142029762268066, "global_step": 437213, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.063821792602539, "global_step": 437214, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1028003692626953, "global_step": 437215, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.096068859100342, "global_step": 437216, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9972476959228516, "global_step": 437217, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.059843063354492, "global_step": 437218, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.139468193054199, "global_step": 437219, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0237536430358887, "global_step": 437220, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0968685150146484, "global_step": 437221, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1184513568878174, "global_step": 437222, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0304019451141357, "global_step": 437223, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.109002113342285, "global_step": 437224, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.138622522354126, "global_step": 437225, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.111602544784546, "global_step": 437226, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.003434658050537, "global_step": 437227, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.079256296157837, "global_step": 437228, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1067678928375244, "global_step": 437229, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1314029693603516, "global_step": 437230, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.059964895248413, "global_step": 437231, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.039680242538452, "global_step": 437232, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.093721628189087, "global_step": 437233, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0689544677734375, "global_step": 437234, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0653798580169678, "global_step": 437235, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.009857177734375, "global_step": 437236, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9775491952896118, "global_step": 437237, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0335562229156494, "global_step": 437238, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.088794469833374, "global_step": 437239, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.963542103767395, "global_step": 437240, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.075924873352051, "global_step": 437241, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0224123001098633, "global_step": 437242, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.011087656021118, "global_step": 437243, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.040759325027466, "global_step": 437244, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0020365715026855, "global_step": 437245, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0338454246520996, "global_step": 437246, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.117098808288574, "global_step": 437247, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.140007257461548, "global_step": 437248, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0931313037872314, "global_step": 437249, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.054089069366455, "global_step": 437250, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.114387273788452, "global_step": 437251, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.065774917602539, "global_step": 437252, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1297311782836914, "global_step": 437253, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0104942321777344, "global_step": 437254, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1189587116241455, "global_step": 437255, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0867252349853516, "global_step": 437256, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1477210521698, "global_step": 437257, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0646324157714844, "global_step": 437258, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.047600507736206, "global_step": 437259, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.014620304107666, "global_step": 437260, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.041891098022461, "global_step": 437261, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.022008180618286, "global_step": 437262, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0993356704711914, "global_step": 437263, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1217501163482666, "global_step": 437264, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.076350450515747, "global_step": 437265, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.044459104537964, "global_step": 437266, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0533013343811035, "global_step": 437267, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.097184658050537, "global_step": 437268, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0173964500427246, "global_step": 437269, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0134661197662354, "global_step": 437270, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1273117065429688, "global_step": 437271, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0569334030151367, "global_step": 437272, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.106398582458496, "global_step": 437273, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0372939109802246, "global_step": 437274, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.03993821144104, "global_step": 437275, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.059055805206299, "global_step": 437276, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0905351638793945, "global_step": 437277, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0525500774383545, "global_step": 437278, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0835413932800293, "global_step": 437279, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.053609848022461, "global_step": 437280, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.085878610610962, "global_step": 437281, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.990687608718872, "global_step": 437282, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.155935049057007, "global_step": 437283, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0744128227233887, "global_step": 437284, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0883395671844482, "global_step": 437285, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.077119827270508, "global_step": 437286, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0931501388549805, "global_step": 437287, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0761208534240723, "global_step": 437288, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.056004285812378, "global_step": 437289, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1470696926116943, "global_step": 437290, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0810887813568115, "global_step": 437291, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0900580883026123, "global_step": 437292, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.208148717880249, "global_step": 437293, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.106274127960205, "global_step": 437294, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0795257091522217, "global_step": 437295, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.087700843811035, "global_step": 437296, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.075676918029785, "global_step": 437297, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.120307445526123, "global_step": 437298, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.034726619720459, "global_step": 437299, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.124810218811035, "global_step": 437300, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0940139293670654, "global_step": 437301, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.105217695236206, "global_step": 437302, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0536434650421143, "global_step": 437303, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0116238594055176, "global_step": 437304, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1196188926696777, "global_step": 437305, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0176753997802734, "global_step": 437306, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.071071147918701, "global_step": 437307, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.138979911804199, "global_step": 437308, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0719494819641113, "global_step": 437309, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0827784538269043, "global_step": 437310, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.097224473953247, "global_step": 437311, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.158768653869629, "global_step": 437312, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.135481119155884, "global_step": 437313, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0987472534179688, "global_step": 437314, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1074652671813965, "global_step": 437315, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0922179222106934, "global_step": 437316, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.048701524734497, "global_step": 437317, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.121983528137207, "global_step": 437318, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.102137565612793, "global_step": 437319, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1546552181243896, "global_step": 437320, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.051727533340454, "global_step": 437321, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1189215183258057, "global_step": 437322, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.103201150894165, "global_step": 437323, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.020714521408081, "global_step": 437324, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.017742395401001, "global_step": 437325, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.039295196533203, "global_step": 437326, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0436019897460938, "global_step": 437327, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1667592525482178, "global_step": 437328, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.021311044692993, "global_step": 437329, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1010146141052246, "global_step": 437330, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0366032123565674, "global_step": 437331, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0281009674072266, "global_step": 437332, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0488035678863525, "global_step": 437333, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1505815982818604, "global_step": 437334, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0744097232818604, "global_step": 437335, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0947601795196533, "global_step": 437336, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0031089782714844, "global_step": 437337, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0966105461120605, "global_step": 437338, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.054926633834839, "global_step": 437339, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.139350652694702, "global_step": 437340, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0787031650543213, "global_step": 437341, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1474831104278564, "global_step": 437342, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.979463815689087, "global_step": 437343, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.014746904373169, "global_step": 437344, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1040003299713135, "global_step": 437345, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0866830348968506, "global_step": 437346, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0431902408599854, "global_step": 437347, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.110682487487793, "global_step": 437348, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.064164876937866, "global_step": 437349, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.092668056488037, "global_step": 437350, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0748090744018555, "global_step": 437351, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.105314016342163, "global_step": 437352, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.088329553604126, "global_step": 437353, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0598204135894775, "global_step": 437354, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0480005741119385, "global_step": 437355, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9355218410491943, "global_step": 437356, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.138814687728882, "global_step": 437357, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.043304204940796, "global_step": 437358, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.087970495223999, "global_step": 437359, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.08788800239563, "global_step": 437360, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1031837463378906, "global_step": 437361, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0508930683135986, "global_step": 437362, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.13885235786438, "global_step": 437363, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0489656925201416, "global_step": 437364, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.09106183052063, "global_step": 437365, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.014442205429077, "global_step": 437366, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.016613483428955, "global_step": 437367, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9650121927261353, "global_step": 437368, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.17326021194458, "global_step": 437369, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0856173038482666, "global_step": 437370, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.158611297607422, "global_step": 437371, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.046940803527832, "global_step": 437372, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.143258810043335, "global_step": 437373, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0456910133361816, "global_step": 437374, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.067145347595215, "global_step": 437375, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0646846294403076, "global_step": 437376, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9639159440994263, "global_step": 437377, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1005258560180664, "global_step": 437378, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0008652210235596, "global_step": 437379, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0748484134674072, "global_step": 437380, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1561203002929688, "global_step": 437381, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1473803520202637, "global_step": 437382, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9767662286758423, "global_step": 437383, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.18574595451355, "global_step": 437384, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.041276693344116, "global_step": 437385, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1334590911865234, "global_step": 437386, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.059791088104248, "global_step": 437387, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.087463140487671, "global_step": 437388, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1161110401153564, "global_step": 437389, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0339624881744385, "global_step": 437390, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0684213638305664, "global_step": 437391, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1096813678741455, "global_step": 437392, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.052438974380493, "global_step": 437393, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0638959407806396, "global_step": 437394, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0668070316314697, "global_step": 437395, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.054734706878662, "global_step": 437396, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1168808937072754, "global_step": 437397, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.125715494155884, "global_step": 437398, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0649218559265137, "global_step": 437399, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1193039417266846, "global_step": 437400, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.004493236541748, "global_step": 437401, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0652639865875244, "global_step": 437402, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0409719944000244, "global_step": 437403, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.065155267715454, "global_step": 437404, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0716090202331543, "global_step": 437405, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.111844539642334, "global_step": 437406, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0779268741607666, "global_step": 437407, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.093780994415283, "global_step": 437408, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1991260051727295, "global_step": 437409, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0962095260620117, "global_step": 437410, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.046534776687622, "global_step": 437411, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1080405712127686, "global_step": 437412, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1525230407714844, "global_step": 437413, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0476973056793213, "global_step": 437414, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.048900604248047, "global_step": 437415, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.129697799682617, "global_step": 437416, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9924113750457764, "global_step": 437417, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.141895055770874, "global_step": 437418, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0693347454071045, "global_step": 437419, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0825581550598145, "global_step": 437420, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1137514114379883, "global_step": 437421, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0892624855041504, "global_step": 437422, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1250927448272705, "global_step": 437423, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9647858142852783, "global_step": 437424, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0561885833740234, "global_step": 437425, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.027851104736328, "global_step": 437426, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0443410873413086, "global_step": 437427, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1988515853881836, "global_step": 437428, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0256459712982178, "global_step": 437429, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1727826595306396, "global_step": 437430, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1318788528442383, "global_step": 437431, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0623841285705566, "global_step": 437432, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.133131265640259, "global_step": 437433, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0788092613220215, "global_step": 437434, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0438244342803955, "global_step": 437435, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1283657550811768, "global_step": 437436, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0527687072753906, "global_step": 437437, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.061450481414795, "global_step": 437438, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0912249088287354, "global_step": 437439, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0469088554382324, "global_step": 437440, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.069763422012329, "global_step": 437441, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0989677906036377, "global_step": 437442, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0965828895568848, "global_step": 437443, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.091935634613037, "global_step": 437444, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.014129161834717, "global_step": 437445, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.079239845275879, "global_step": 437446, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0615415573120117, "global_step": 437447, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.11759614944458, "global_step": 437448, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1055378913879395, "global_step": 437449, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1542739868164062, "global_step": 437450, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1266322135925293, "global_step": 437451, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.093738555908203, "global_step": 437452, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.055922269821167, "global_step": 437453, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.139849901199341, "global_step": 437454, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.044640302658081, "global_step": 437455, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0691373348236084, "global_step": 437456, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.118543863296509, "global_step": 437457, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.107969045639038, "global_step": 437458, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0451948642730713, "global_step": 437459, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.079029083251953, "global_step": 437460, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9912291765213013, "global_step": 437461, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0979692935943604, "global_step": 437462, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.126086950302124, "global_step": 437463, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0456714630126953, "global_step": 437464, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.035449981689453, "global_step": 437465, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0505058765411377, "global_step": 437466, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0346593856811523, "global_step": 437467, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0600526332855225, "global_step": 437468, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0571091175079346, "global_step": 437469, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.118582248687744, "global_step": 437470, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0634474754333496, "global_step": 437471, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0751476287841797, "global_step": 437472, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.051452159881592, "global_step": 437473, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0822174549102783, "global_step": 437474, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0901095867156982, "global_step": 437475, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0978705883026123, "global_step": 437476, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0380706787109375, "global_step": 437477, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.165104389190674, "global_step": 437478, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1482274532318115, "global_step": 437479, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0967154502868652, "global_step": 437480, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.127596139907837, "global_step": 437481, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0736472606658936, "global_step": 437482, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.080397367477417, "global_step": 437483, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.096508741378784, "global_step": 437484, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0885558128356934, "global_step": 437485, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.111067056655884, "global_step": 437486, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.089768648147583, "global_step": 437487, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0258049964904785, "global_step": 437488, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0654122829437256, "global_step": 437489, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1057863235473633, "global_step": 437490, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1218106746673584, "global_step": 437491, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0820863246917725, "global_step": 437492, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.004305601119995, "global_step": 437493, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.038102388381958, "global_step": 437494, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.058479070663452, "global_step": 437495, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.122293710708618, "global_step": 437496, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1940581798553467, "global_step": 437497, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0844151973724365, "global_step": 437498, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1178250312805176, "global_step": 437499, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1450283527374268, "global_step": 437500, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.038637638092041, "global_step": 437501, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0915424823760986, "global_step": 437502, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0894532203674316, "global_step": 437503, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0227200984954834, "global_step": 437504, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9968544244766235, "global_step": 437505, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0445713996887207, "global_step": 437506, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0482046604156494, "global_step": 437507, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.102416515350342, "global_step": 437508, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.148491621017456, "global_step": 437509, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.109189510345459, "global_step": 437510, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0500729084014893, "global_step": 437511, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0793704986572266, "global_step": 437512, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.203617572784424, "global_step": 437513, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0565764904022217, "global_step": 437514, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.076340913772583, "global_step": 437515, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.095824956893921, "global_step": 437516, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0843985080718994, "global_step": 437517, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.061898946762085, "global_step": 437518, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.088362455368042, "global_step": 437519, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1086840629577637, "global_step": 437520, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.092485189437866, "global_step": 437521, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.065141201019287, "global_step": 437522, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1185691356658936, "global_step": 437523, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1325323581695557, "global_step": 437524, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0668954849243164, "global_step": 437525, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0784919261932373, "global_step": 437526, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0469350814819336, "global_step": 437527, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0693788528442383, "global_step": 437528, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.166846752166748, "global_step": 437529, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0976734161376953, "global_step": 437530, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1522703170776367, "global_step": 437531, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0719845294952393, "global_step": 437532, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.046173095703125, "global_step": 437533, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0583133697509766, "global_step": 437534, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0398383140563965, "global_step": 437535, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0022246837615967, "global_step": 437536, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1695914268493652, "global_step": 437537, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.038226842880249, "global_step": 437538, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.076072931289673, "global_step": 437539, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.097181558609009, "global_step": 437540, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0340263843536377, "global_step": 437541, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.150944948196411, "global_step": 437542, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.048349142074585, "global_step": 437543, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1210274696350098, "global_step": 437544, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0494987964630127, "global_step": 437545, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.016772985458374, "global_step": 437546, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1603801250457764, "global_step": 437547, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1020748615264893, "global_step": 437548, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.093677520751953, "global_step": 437549, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.150569438934326, "global_step": 437550, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0718884468078613, "global_step": 437551, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0993289947509766, "global_step": 437552, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0872623920440674, "global_step": 437553, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.098052978515625, "global_step": 437554, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0987777709960938, "global_step": 437555, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.063661575317383, "global_step": 437556, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.049086570739746, "global_step": 437557, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.115060567855835, "global_step": 437558, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.123183488845825, "global_step": 437559, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1117970943450928, "global_step": 437560, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.115009307861328, "global_step": 437561, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.064453601837158, "global_step": 437562, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.082585573196411, "global_step": 437563, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0605568885803223, "global_step": 437564, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0657994747161865, "global_step": 437565, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1201937198638916, "global_step": 437566, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1553282737731934, "global_step": 437567, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.052870512008667, "global_step": 437568, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0740766525268555, "global_step": 437569, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9765926599502563, "global_step": 437570, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1384570598602295, "global_step": 437571, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.174415111541748, "global_step": 437572, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0579042434692383, "global_step": 437573, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0397837162017822, "global_step": 437574, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.131730318069458, "global_step": 437575, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0549519062042236, "global_step": 437576, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0580954551696777, "global_step": 437577, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0333800315856934, "global_step": 437578, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0852341651916504, "global_step": 437579, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1276564598083496, "global_step": 437580, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1808385848999023, "global_step": 437581, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.052509307861328, "global_step": 437582, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.083275556564331, "global_step": 437583, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.038872241973877, "global_step": 437584, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.080493688583374, "global_step": 437585, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0474140644073486, "global_step": 437586, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0937724113464355, "global_step": 437587, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1470894813537598, "global_step": 437588, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9892643690109253, "global_step": 437589, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0591988563537598, "global_step": 437590, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.2233359813690186, "global_step": 437591, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0011842250823975, "global_step": 437592, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.2550692558288574, "global_step": 437593, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9682588577270508, "global_step": 437594, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0516653060913086, "global_step": 437595, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0124881267547607, "global_step": 437596, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1041815280914307, "global_step": 437597, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1035308837890625, "global_step": 437598, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9903327226638794, "global_step": 437599, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0828137397766113, "global_step": 437600, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.053452253341675, "global_step": 437601, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0305895805358887, "global_step": 437602, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1008963584899902, "global_step": 437603, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.074453592300415, "global_step": 437604, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0882444381713867, "global_step": 437605, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0668325424194336, "global_step": 437606, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9571774005889893, "global_step": 437607, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.039918899536133, "global_step": 437608, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0462868213653564, "global_step": 437609, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9363058805465698, "global_step": 437610, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0550167560577393, "global_step": 437611, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0870730876922607, "global_step": 437612, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0549747943878174, "global_step": 437613, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.030414342880249, "global_step": 437614, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.044482469558716, "global_step": 437615, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1001899242401123, "global_step": 437616, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1328840255737305, "global_step": 437617, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0968494415283203, "global_step": 437618, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0644829273223877, "global_step": 437619, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.086412191390991, "global_step": 437620, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0664384365081787, "global_step": 437621, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0586118698120117, "global_step": 437622, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.152050018310547, "global_step": 437623, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0299201011657715, "global_step": 437624, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0939602851867676, "global_step": 437625, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0128092765808105, "global_step": 437626, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0657901763916016, "global_step": 437627, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.109837293624878, "global_step": 437628, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.094942092895508, "global_step": 437629, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0653061866760254, "global_step": 437630, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0522990226745605, "global_step": 437631, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.07600736618042, "global_step": 437632, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0306687355041504, "global_step": 437633, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.172133684158325, "global_step": 437634, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0943801403045654, "global_step": 437635, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9958382844924927, "global_step": 437636, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.064330816268921, "global_step": 437637, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0531182289123535, "global_step": 437638, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0625834465026855, "global_step": 437639, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1085870265960693, "global_step": 437640, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0871427059173584, "global_step": 437641, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.108588695526123, "global_step": 437642, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1610238552093506, "global_step": 437643, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.125690460205078, "global_step": 437644, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.011000394821167, "global_step": 437645, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.100792169570923, "global_step": 437646, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.2079074382781982, "global_step": 437647, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0554306507110596, "global_step": 437648, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.044529914855957, "global_step": 437649, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1061246395111084, "global_step": 437650, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1527698040008545, "global_step": 437651, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0318427085876465, "global_step": 437652, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1190004348754883, "global_step": 437653, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.124476909637451, "global_step": 437654, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.077495813369751, "global_step": 437655, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9811582565307617, "global_step": 437656, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.063445806503296, "global_step": 437657, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.116135358810425, "global_step": 437658, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1325619220733643, "global_step": 437659, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.042848587036133, "global_step": 437660, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1211917400360107, "global_step": 437661, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9967151880264282, "global_step": 437662, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.122164011001587, "global_step": 437663, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0764000415802, "global_step": 437664, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0672409534454346, "global_step": 437665, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1209115982055664, "global_step": 437666, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1253108978271484, "global_step": 437667, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0697431564331055, "global_step": 437668, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1328742504119873, "global_step": 437669, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.077371597290039, "global_step": 437670, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.11761736869812, "global_step": 437671, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1563973426818848, "global_step": 437672, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.100855588912964, "global_step": 437673, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.074094533920288, "global_step": 437674, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9746851921081543, "global_step": 437675, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1004292964935303, "global_step": 437676, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9717472791671753, "global_step": 437677, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1064138412475586, "global_step": 437678, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0793933868408203, "global_step": 437679, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1084680557250977, "global_step": 437680, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.040328025817871, "global_step": 437681, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1699306964874268, "global_step": 437682, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1120314598083496, "global_step": 437683, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.043226718902588, "global_step": 437684, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9857399463653564, "global_step": 437685, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0624544620513916, "global_step": 437686, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.097973585128784, "global_step": 437687, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1074671745300293, "global_step": 437688, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.083908796310425, "global_step": 437689, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.030566930770874, "global_step": 437690, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.067922830581665, "global_step": 437691, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.122011423110962, "global_step": 437692, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0811288356781006, "global_step": 437693, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.089553117752075, "global_step": 437694, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.115694999694824, "global_step": 437695, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.044999599456787, "global_step": 437696, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1233487129211426, "global_step": 437697, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9864195585250854, "global_step": 437698, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.056884765625, "global_step": 437699, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0566976070404053, "global_step": 437700, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9913206100463867, "global_step": 437701, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0300168991088867, "global_step": 437702, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.064070224761963, "global_step": 437703, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.057612180709839, "global_step": 437704, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1712400913238525, "global_step": 437705, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0649640560150146, "global_step": 437706, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1279962062835693, "global_step": 437707, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0844743251800537, "global_step": 437708, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.072265625, "global_step": 437709, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.007640838623047, "global_step": 437710, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.052968978881836, "global_step": 437711, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0464837551116943, "global_step": 437712, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9957212209701538, "global_step": 437713, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.118800640106201, "global_step": 437714, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.066295623779297, "global_step": 437715, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.188194990158081, "global_step": 437716, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0082099437713623, "global_step": 437717, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.072085380554199, "global_step": 437718, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.035254716873169, "global_step": 437719, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.039106607437134, "global_step": 437720, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0578083992004395, "global_step": 437721, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0731637477874756, "global_step": 437722, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.089151382446289, "global_step": 437723, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1272449493408203, "global_step": 437724, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0576493740081787, "global_step": 437725, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.012223958969116, "global_step": 437726, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1273810863494873, "global_step": 437727, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0813920497894287, "global_step": 437728, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0842621326446533, "global_step": 437729, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1675238609313965, "global_step": 437730, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.103879451751709, "global_step": 437731, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1061811447143555, "global_step": 437732, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.152576446533203, "global_step": 437733, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.099642276763916, "global_step": 437734, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.058140516281128, "global_step": 437735, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.009509801864624, "global_step": 437736, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0675888061523438, "global_step": 437737, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.032716989517212, "global_step": 437738, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.156567335128784, "global_step": 437739, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.068236827850342, "global_step": 437740, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0993235111236572, "global_step": 437741, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0764310359954834, "global_step": 437742, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.034656524658203, "global_step": 437743, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1484479904174805, "global_step": 437744, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.064452886581421, "global_step": 437745, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1434028148651123, "global_step": 437746, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.084287643432617, "global_step": 437747, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9721952676773071, "global_step": 437748, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0205979347229004, "global_step": 437749, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0999693870544434, "global_step": 437750, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.052985191345215, "global_step": 437751, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.108733892440796, "global_step": 437752, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.078404426574707, "global_step": 437753, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.097916841506958, "global_step": 437754, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.045308828353882, "global_step": 437755, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0603816509246826, "global_step": 437756, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.124850273132324, "global_step": 437757, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0864057540893555, "global_step": 437758, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.095569610595703, "global_step": 437759, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.153916358947754, "global_step": 437760, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9574987888336182, "global_step": 437761, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0316860675811768, "global_step": 437762, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0407729148864746, "global_step": 437763, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.055293083190918, "global_step": 437764, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0720162391662598, "global_step": 437765, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.060025930404663, "global_step": 437766, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1324572563171387, "global_step": 437767, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0647170543670654, "global_step": 437768, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.109376907348633, "global_step": 437769, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0749361515045166, "global_step": 437770, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.083502769470215, "global_step": 437771, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.142042875289917, "global_step": 437772, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.11620831489563, "global_step": 437773, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.152163505554199, "global_step": 437774, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0897340774536133, "global_step": 437775, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.054144859313965, "global_step": 437776, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0795865058898926, "global_step": 437777, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0167274475097656, "global_step": 437778, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.002277135848999, "global_step": 437779, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0750186443328857, "global_step": 437780, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.126574993133545, "global_step": 437781, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.087332010269165, "global_step": 437782, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0241312980651855, "global_step": 437783, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1405186653137207, "global_step": 437784, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.060117721557617, "global_step": 437785, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.064039468765259, "global_step": 437786, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9706865549087524, "global_step": 437787, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.154200792312622, "global_step": 437788, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1475939750671387, "global_step": 437789, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1073222160339355, "global_step": 437790, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.098980665206909, "global_step": 437791, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0163440704345703, "global_step": 437792, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0192437171936035, "global_step": 437793, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.154055595397949, "global_step": 437794, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0936715602874756, "global_step": 437795, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.061999559402466, "global_step": 437796, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.145087242126465, "global_step": 437797, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.069354772567749, "global_step": 437798, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.092402458190918, "global_step": 437799, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1485989093780518, "global_step": 437800, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1124908924102783, "global_step": 437801, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0657851696014404, "global_step": 437802, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0260159969329834, "global_step": 437803, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0554940700531006, "global_step": 437804, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.07609486579895, "global_step": 437805, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0944743156433105, "global_step": 437806, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.105525493621826, "global_step": 437807, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0392515659332275, "global_step": 437808, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0433828830718994, "global_step": 437809, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.080561399459839, "global_step": 437810, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0683717727661133, "global_step": 437811, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0833699703216553, "global_step": 437812, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0223450660705566, "global_step": 437813, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.086333751678467, "global_step": 437814, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0798730850219727, "global_step": 437815, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.103003978729248, "global_step": 437816, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1137185096740723, "global_step": 437817, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1089279651641846, "global_step": 437818, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.176206350326538, "global_step": 437819, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1784932613372803, "global_step": 437820, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1232588291168213, "global_step": 437821, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.090278148651123, "global_step": 437822, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.136692523956299, "global_step": 437823, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0747687816619873, "global_step": 437824, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0255303382873535, "global_step": 437825, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0369961261749268, "global_step": 437826, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.062420129776001, "global_step": 437827, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.094773530960083, "global_step": 437828, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0902082920074463, "global_step": 437829, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1446754932403564, "global_step": 437830, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0271546840667725, "global_step": 437831, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0743319988250732, "global_step": 437832, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.106618642807007, "global_step": 437833, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1007883548736572, "global_step": 437834, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0831079483032227, "global_step": 437835, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1044199466705322, "global_step": 437836, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.10174298286438, "global_step": 437837, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0375630855560303, "global_step": 437838, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.072249174118042, "global_step": 437839, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0861430168151855, "global_step": 437840, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.080029249191284, "global_step": 437841, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.051630735397339, "global_step": 437842, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.164097785949707, "global_step": 437843, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0250422954559326, "global_step": 437844, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.097060203552246, "global_step": 437845, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1109390258789062, "global_step": 437846, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.077479124069214, "global_step": 437847, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.158804416656494, "global_step": 437848, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1201181411743164, "global_step": 437849, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0577232837677, "global_step": 437850, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.112931966781616, "global_step": 437851, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1182563304901123, "global_step": 437852, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.093343496322632, "global_step": 437853, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0454635620117188, "global_step": 437854, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.123659610748291, "global_step": 437855, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.068953037261963, "global_step": 437856, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1548147201538086, "global_step": 437857, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.080374240875244, "global_step": 437858, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0619072914123535, "global_step": 437859, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.043117046356201, "global_step": 437860, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0239975452423096, "global_step": 437861, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0267844200134277, "global_step": 437862, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0838465690612793, "global_step": 437863, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.111438035964966, "global_step": 437864, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9569132328033447, "global_step": 437865, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.046032667160034, "global_step": 437866, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.078162908554077, "global_step": 437867, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.07700514793396, "global_step": 437868, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.050065517425537, "global_step": 437869, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.096031904220581, "global_step": 437870, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.04807186126709, "global_step": 437871, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.075932025909424, "global_step": 437872, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0391690731048584, "global_step": 437873, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1027514934539795, "global_step": 437874, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.128970146179199, "global_step": 437875, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.13700270652771, "global_step": 437876, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.046156167984009, "global_step": 437877, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.061871290206909, "global_step": 437878, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.089667558670044, "global_step": 437879, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.073826313018799, "global_step": 437880, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.103180170059204, "global_step": 437881, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1263935565948486, "global_step": 437882, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1363444328308105, "global_step": 437883, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.042970895767212, "global_step": 437884, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.127119302749634, "global_step": 437885, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0708611011505127, "global_step": 437886, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.028986930847168, "global_step": 437887, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0842270851135254, "global_step": 437888, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1941421031951904, "global_step": 437889, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.056216239929199, "global_step": 437890, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1103692054748535, "global_step": 437891, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.137814998626709, "global_step": 437892, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.179149866104126, "global_step": 437893, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0711472034454346, "global_step": 437894, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.068542957305908, "global_step": 437895, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1077730655670166, "global_step": 437896, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.049107313156128, "global_step": 437897, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0201523303985596, "global_step": 437898, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0181949138641357, "global_step": 437899, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1274805068969727, "global_step": 437900, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.036989688873291, "global_step": 437901, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0649800300598145, "global_step": 437902, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.143860101699829, "global_step": 437903, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1147308349609375, "global_step": 437904, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0225954055786133, "global_step": 437905, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.105625629425049, "global_step": 437906, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.044032573699951, "global_step": 437907, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.139939069747925, "global_step": 437908, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1246354579925537, "global_step": 437909, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1818950176239014, "global_step": 437910, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1372904777526855, "global_step": 437911, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0654807090759277, "global_step": 437912, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.2515106201171875, "global_step": 437913, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1180474758148193, "global_step": 437914, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9724640846252441, "global_step": 437915, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.107719659805298, "global_step": 437916, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1798593997955322, "global_step": 437917, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0762550830841064, "global_step": 437918, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1489455699920654, "global_step": 437919, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.042175531387329, "global_step": 437920, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.106411933898926, "global_step": 437921, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0192980766296387, "global_step": 437922, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0573840141296387, "global_step": 437923, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.06764817237854, "global_step": 437924, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.080345392227173, "global_step": 437925, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1635398864746094, "global_step": 437926, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0533299446105957, "global_step": 437927, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.990652322769165, "global_step": 437928, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.057267189025879, "global_step": 437929, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0407447814941406, "global_step": 437930, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0624470710754395, "global_step": 437931, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.157388687133789, "global_step": 437932, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0588135719299316, "global_step": 437933, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0394811630249023, "global_step": 437934, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.109006404876709, "global_step": 437935, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.032878875732422, "global_step": 437936, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9627320766448975, "global_step": 437937, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9693139791488647, "global_step": 437938, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0628511905670166, "global_step": 437939, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0863537788391113, "global_step": 437940, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0602071285247803, "global_step": 437941, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.01326060295105, "global_step": 437942, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.2164905071258545, "global_step": 437943, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1575331687927246, "global_step": 437944, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1211087703704834, "global_step": 437945, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.069495916366577, "global_step": 437946, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.063525676727295, "global_step": 437947, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.057246685028076, "global_step": 437948, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.037424087524414, "global_step": 437949, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.079869031906128, "global_step": 437950, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.097562313079834, "global_step": 437951, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1093876361846924, "global_step": 437952, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1224944591522217, "global_step": 437953, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1640024185180664, "global_step": 437954, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0216100215911865, "global_step": 437955, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0841593742370605, "global_step": 437956, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.093410015106201, "global_step": 437957, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.195405960083008, "global_step": 437958, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.051006555557251, "global_step": 437959, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.108072519302368, "global_step": 437960, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0166313648223877, "global_step": 437961, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0673415660858154, "global_step": 437962, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0638813972473145, "global_step": 437963, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0918140411376953, "global_step": 437964, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.106931209564209, "global_step": 437965, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1505982875823975, "global_step": 437966, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0773684978485107, "global_step": 437967, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1284050941467285, "global_step": 437968, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.092106580734253, "global_step": 437969, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.000650405883789, "global_step": 437970, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0086872577667236, "global_step": 437971, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1910758018493652, "global_step": 437972, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.012953996658325, "global_step": 437973, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.099073886871338, "global_step": 437974, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.149153232574463, "global_step": 437975, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.086954116821289, "global_step": 437976, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.050154209136963, "global_step": 437977, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1427056789398193, "global_step": 437978, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1119487285614014, "global_step": 437979, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0829062461853027, "global_step": 437980, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.049745798110962, "global_step": 437981, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.073237895965576, "global_step": 437982, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1584291458129883, "global_step": 437983, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.139544725418091, "global_step": 437984, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.008777618408203, "global_step": 437985, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0668435096740723, "global_step": 437986, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0950746536254883, "global_step": 437987, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1269638538360596, "global_step": 437988, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0314314365386963, "global_step": 437989, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1332409381866455, "global_step": 437990, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1676483154296875, "global_step": 437991, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0644640922546387, "global_step": 437992, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0847864151000977, "global_step": 437993, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.159816265106201, "global_step": 437994, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.060481548309326, "global_step": 437995, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.127701997756958, "global_step": 437996, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0564064979553223, "global_step": 437997, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.065256118774414, "global_step": 437998, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0904242992401123, "global_step": 437999, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0327646732330322, "global_step": 438000, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.090242624282837, "global_step": 438001, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0982415676116943, "global_step": 438002, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0698649883270264, "global_step": 438003, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0378594398498535, "global_step": 438004, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1093854904174805, "global_step": 438005, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1200473308563232, "global_step": 438006, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.102234363555908, "global_step": 438007, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1652863025665283, "global_step": 438008, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1746418476104736, "global_step": 438009, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0102086067199707, "global_step": 438010, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0438876152038574, "global_step": 438011, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.019831418991089, "global_step": 438012, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0324764251708984, "global_step": 438013, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.160140037536621, "global_step": 438014, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1565542221069336, "global_step": 438015, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0151419639587402, "global_step": 438016, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0039048194885254, "global_step": 438017, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.09930157661438, "global_step": 438018, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.015643835067749, "global_step": 438019, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9981776475906372, "global_step": 438020, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.150864839553833, "global_step": 438021, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1078641414642334, "global_step": 438022, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9992891550064087, "global_step": 438023, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.042905330657959, "global_step": 438024, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.027252435684204, "global_step": 438025, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.044431209564209, "global_step": 438026, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.098262071609497, "global_step": 438027, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1549243927001953, "global_step": 438028, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0182647705078125, "global_step": 438029, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.084444761276245, "global_step": 438030, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0405640602111816, "global_step": 438031, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0406978130340576, "global_step": 438032, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.132796287536621, "global_step": 438033, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.066682815551758, "global_step": 438034, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0217490196228027, "global_step": 438035, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0579075813293457, "global_step": 438036, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.085897445678711, "global_step": 438037, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0830771923065186, "global_step": 438038, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0883989334106445, "global_step": 438039, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0799384117126465, "global_step": 438040, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9936200380325317, "global_step": 438041, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.065462112426758, "global_step": 438042, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1122617721557617, "global_step": 438043, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1312427520751953, "global_step": 438044, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.147873878479004, "global_step": 438045, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.061790704727173, "global_step": 438046, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9863026142120361, "global_step": 438047, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.168172597885132, "global_step": 438048, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9948596954345703, "global_step": 438049, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9956891536712646, "global_step": 438050, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.083848476409912, "global_step": 438051, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1535427570343018, "global_step": 438052, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0819127559661865, "global_step": 438053, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.996282696723938, "global_step": 438054, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1152126789093018, "global_step": 438055, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.06773042678833, "global_step": 438056, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.052006959915161, "global_step": 438057, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.140512466430664, "global_step": 438058, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0289618968963623, "global_step": 438059, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.066441774368286, "global_step": 438060, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0019779205322266, "global_step": 438061, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.090085506439209, "global_step": 438062, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1183090209960938, "global_step": 438063, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1359992027282715, "global_step": 438064, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.037344217300415, "global_step": 438065, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.100120782852173, "global_step": 438066, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.088789463043213, "global_step": 438067, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.091423749923706, "global_step": 438068, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1304879188537598, "global_step": 438069, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1462109088897705, "global_step": 438070, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0800576210021973, "global_step": 438071, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.125570297241211, "global_step": 438072, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0626282691955566, "global_step": 438073, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.025944948196411, "global_step": 438074, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.017688751220703, "global_step": 438075, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0706326961517334, "global_step": 438076, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0841500759124756, "global_step": 438077, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1412487030029297, "global_step": 438078, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1356451511383057, "global_step": 438079, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1359431743621826, "global_step": 438080, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0210559368133545, "global_step": 438081, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1118197441101074, "global_step": 438082, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.177027463912964, "global_step": 438083, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9685131311416626, "global_step": 438084, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1770846843719482, "global_step": 438085, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0781922340393066, "global_step": 438086, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.185281276702881, "global_step": 438087, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.133969306945801, "global_step": 438088, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.94643235206604, "global_step": 438089, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.062340259552002, "global_step": 438090, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1196448802948, "global_step": 438091, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.129204750061035, "global_step": 438092, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.040839433670044, "global_step": 438093, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.164478063583374, "global_step": 438094, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1157732009887695, "global_step": 438095, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.02209210395813, "global_step": 438096, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0866496562957764, "global_step": 438097, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.029797077178955, "global_step": 438098, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.094973564147949, "global_step": 438099, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0589802265167236, "global_step": 438100, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0708234310150146, "global_step": 438101, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0646321773529053, "global_step": 438102, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.099433422088623, "global_step": 438103, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0490670204162598, "global_step": 438104, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0461134910583496, "global_step": 438105, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.06577205657959, "global_step": 438106, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.104100227355957, "global_step": 438107, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.11747145652771, "global_step": 438108, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0462729930877686, "global_step": 438109, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9951143264770508, "global_step": 438110, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.068390130996704, "global_step": 438111, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.088827610015869, "global_step": 438112, "epoch": 801, "lr": 5e-05}
{"train_loss": 1.9986650943756104, "global_step": 438113, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1779661178588867, "global_step": 438114, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0356345176696777, "global_step": 438115, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1620750427246094, "global_step": 438116, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.1518642902374268, "global_step": 438117, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0770576000213623, "global_step": 438118, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0622053146362305, "global_step": 438119, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0803062915802, "global_step": 438120, "epoch": 801, "lr": 5e-05}
{"train_loss": 2.0089972019195557, "global_step": 438121, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.125164270401001, "global_step": 438122, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1142661571502686, "global_step": 438123, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.102963447570801, "global_step": 438124, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1276700496673584, "global_step": 438125, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.128815174102783, "global_step": 438126, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0224854946136475, "global_step": 438127, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.129404306411743, "global_step": 438128, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.018824338912964, "global_step": 438129, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.2376761436462402, "global_step": 438130, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0556511878967285, "global_step": 438131, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0038347244262695, "global_step": 438132, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.070460319519043, "global_step": 438133, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0543105602264404, "global_step": 438134, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9838114976882935, "global_step": 438135, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.091708183288574, "global_step": 438136, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0183095932006836, "global_step": 438137, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.024785041809082, "global_step": 438138, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.061189889907837, "global_step": 438139, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9876686334609985, "global_step": 438140, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.080833673477173, "global_step": 438141, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.121291160583496, "global_step": 438142, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.077975034713745, "global_step": 438143, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0192008018493652, "global_step": 438144, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.185453176498413, "global_step": 438145, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9457381963729858, "global_step": 438146, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.055379629135132, "global_step": 438147, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1167678833007812, "global_step": 438148, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.011806011199951, "global_step": 438149, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0268826484680176, "global_step": 438150, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9558777809143066, "global_step": 438151, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.113278388977051, "global_step": 438152, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0763344764709473, "global_step": 438153, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0806360244750977, "global_step": 438154, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1086227893829346, "global_step": 438155, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.066643476486206, "global_step": 438156, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0233404636383057, "global_step": 438157, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0880353450775146, "global_step": 438158, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9959709644317627, "global_step": 438159, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9745969772338867, "global_step": 438160, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0452425479888916, "global_step": 438161, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1791534423828125, "global_step": 438162, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0426580905914307, "global_step": 438163, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.12968111038208, "global_step": 438164, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.073148012161255, "global_step": 438165, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1053194999694824, "global_step": 438166, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.060494899749756, "global_step": 438167, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.114598274230957, "global_step": 438168, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.077382802963257, "global_step": 438169, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1826705932617188, "global_step": 438170, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.068711519241333, "global_step": 438171, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0855069160461426, "global_step": 438172, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0287134647369385, "global_step": 438173, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0527231693267822, "global_step": 438174, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1939094066619873, "global_step": 438175, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0163276195526123, "global_step": 438176, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0285398960113525, "global_step": 438177, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.08088755607605, "global_step": 438178, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0452208518981934, "global_step": 438179, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.052973747253418, "global_step": 438180, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0422749519348145, "global_step": 438181, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0155603885650635, "global_step": 438182, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.04317307472229, "global_step": 438183, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.033290386199951, "global_step": 438184, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.018937110900879, "global_step": 438185, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.013640880584717, "global_step": 438186, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.978053331375122, "global_step": 438187, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.091050386428833, "global_step": 438188, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9986885786056519, "global_step": 438189, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0288021564483643, "global_step": 438190, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0748050212860107, "global_step": 438191, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0211591720581055, "global_step": 438192, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0552380084991455, "global_step": 438193, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0383763313293457, "global_step": 438194, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.018784999847412, "global_step": 438195, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1337506771087646, "global_step": 438196, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0922842025756836, "global_step": 438197, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.022928237915039, "global_step": 438198, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.098944902420044, "global_step": 438199, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.027824878692627, "global_step": 438200, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.031468152999878, "global_step": 438201, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0133252143859863, "global_step": 438202, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0978286266326904, "global_step": 438203, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.049614429473877, "global_step": 438204, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.095984935760498, "global_step": 438205, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.09537672996521, "global_step": 438206, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.05891752243042, "global_step": 438207, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.062082290649414, "global_step": 438208, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0679244995117188, "global_step": 438209, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.069364070892334, "global_step": 438210, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0399346351623535, "global_step": 438211, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.01589298248291, "global_step": 438212, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0506601333618164, "global_step": 438213, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0490641593933105, "global_step": 438214, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0714399814605713, "global_step": 438215, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0603623390197754, "global_step": 438216, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.086704969406128, "global_step": 438217, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.119431495666504, "global_step": 438218, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1197729110717773, "global_step": 438219, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0866763591766357, "global_step": 438220, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.117335081100464, "global_step": 438221, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.115262746810913, "global_step": 438222, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1026692390441895, "global_step": 438223, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.062319040298462, "global_step": 438224, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1023428440093994, "global_step": 438225, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.063762903213501, "global_step": 438226, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.084092140197754, "global_step": 438227, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9929331541061401, "global_step": 438228, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.047290086746216, "global_step": 438229, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9417498111724854, "global_step": 438230, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0302629470825195, "global_step": 438231, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9461681842803955, "global_step": 438232, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1019842624664307, "global_step": 438233, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1049320697784424, "global_step": 438234, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0652804374694824, "global_step": 438235, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0573654174804688, "global_step": 438236, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0922298431396484, "global_step": 438237, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.071917772293091, "global_step": 438238, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.037996292114258, "global_step": 438239, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.031975030899048, "global_step": 438240, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0520553588867188, "global_step": 438241, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.120445489883423, "global_step": 438242, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0072553157806396, "global_step": 438243, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.037564277648926, "global_step": 438244, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0358543395996094, "global_step": 438245, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0951788425445557, "global_step": 438246, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.04899525642395, "global_step": 438247, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1393179893493652, "global_step": 438248, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.148181915283203, "global_step": 438249, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0547661781311035, "global_step": 438250, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1373581886291504, "global_step": 438251, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.10465669631958, "global_step": 438252, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1024367809295654, "global_step": 438253, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1105635166168213, "global_step": 438254, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.06886887550354, "global_step": 438255, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.058542490005493, "global_step": 438256, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0235824584960938, "global_step": 438257, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.093266487121582, "global_step": 438258, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.12798810005188, "global_step": 438259, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.045548915863037, "global_step": 438260, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.066399574279785, "global_step": 438261, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0778253078460693, "global_step": 438262, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0120270252227783, "global_step": 438263, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1324758529663086, "global_step": 438264, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0722599029541016, "global_step": 438265, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9885369539260864, "global_step": 438266, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.031367301940918, "global_step": 438267, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0830018520355225, "global_step": 438268, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.057785987854004, "global_step": 438269, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0920519828796387, "global_step": 438270, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.077136993408203, "global_step": 438271, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.088801145553589, "global_step": 438272, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0459465980529785, "global_step": 438273, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.996705174446106, "global_step": 438274, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.075963258743286, "global_step": 438275, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1283252239227295, "global_step": 438276, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.079864978790283, "global_step": 438277, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1905016899108887, "global_step": 438278, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.047614336013794, "global_step": 438279, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0321342945098877, "global_step": 438280, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.053262948989868, "global_step": 438281, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0671656131744385, "global_step": 438282, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.018977403640747, "global_step": 438283, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1041908264160156, "global_step": 438284, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0219054222106934, "global_step": 438285, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.009551763534546, "global_step": 438286, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9651929140090942, "global_step": 438287, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.121511936187744, "global_step": 438288, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.092463493347168, "global_step": 438289, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.036824941635132, "global_step": 438290, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0959057807922363, "global_step": 438291, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0472710132598877, "global_step": 438292, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9945157766342163, "global_step": 438293, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.059680223464966, "global_step": 438294, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.071406841278076, "global_step": 438295, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1579296588897705, "global_step": 438296, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0484659671783447, "global_step": 438297, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.16772198677063, "global_step": 438298, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.992045283317566, "global_step": 438299, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.089232921600342, "global_step": 438300, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1749207973480225, "global_step": 438301, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.204754590988159, "global_step": 438302, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.159019947052002, "global_step": 438303, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9905401468276978, "global_step": 438304, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.075685501098633, "global_step": 438305, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0847065448760986, "global_step": 438306, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0597360134124756, "global_step": 438307, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.119586229324341, "global_step": 438308, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.085813283920288, "global_step": 438309, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0908968448638916, "global_step": 438310, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0401382446289062, "global_step": 438311, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0942814350128174, "global_step": 438312, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1068077087402344, "global_step": 438313, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.006934404373169, "global_step": 438314, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0657265186309814, "global_step": 438315, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.079526901245117, "global_step": 438316, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.070003032684326, "global_step": 438317, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0941946506500244, "global_step": 438318, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0897014141082764, "global_step": 438319, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1020312309265137, "global_step": 438320, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.046334981918335, "global_step": 438321, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0475809574127197, "global_step": 438322, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.042612075805664, "global_step": 438323, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.127537727355957, "global_step": 438324, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1121199131011963, "global_step": 438325, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.082542657852173, "global_step": 438326, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1296286582946777, "global_step": 438327, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.07755970954895, "global_step": 438328, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.053805351257324, "global_step": 438329, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0535941123962402, "global_step": 438330, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9829715490341187, "global_step": 438331, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1024632453918457, "global_step": 438332, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0488109588623047, "global_step": 438333, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1130034923553467, "global_step": 438334, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0792646408081055, "global_step": 438335, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.055009365081787, "global_step": 438336, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0828464031219482, "global_step": 438337, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.027374505996704, "global_step": 438338, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.109807252883911, "global_step": 438339, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.08526349067688, "global_step": 438340, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.034611463546753, "global_step": 438341, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0050086975097656, "global_step": 438342, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0318715572357178, "global_step": 438343, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1479740142822266, "global_step": 438344, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1070938110351562, "global_step": 438345, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.140719413757324, "global_step": 438346, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1881115436553955, "global_step": 438347, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.129652500152588, "global_step": 438348, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.082712411880493, "global_step": 438349, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0016586780548096, "global_step": 438350, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0721864700317383, "global_step": 438351, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.015576124191284, "global_step": 438352, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9719780683517456, "global_step": 438353, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1068782806396484, "global_step": 438354, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9879348278045654, "global_step": 438355, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9983854293823242, "global_step": 438356, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9649192094802856, "global_step": 438357, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1016879081726074, "global_step": 438358, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0411856174468994, "global_step": 438359, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0853357315063477, "global_step": 438360, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1086578369140625, "global_step": 438361, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0145673751831055, "global_step": 438362, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9984971284866333, "global_step": 438363, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1332411766052246, "global_step": 438364, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0411031246185303, "global_step": 438365, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.121375560760498, "global_step": 438366, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.123915433883667, "global_step": 438367, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0661754608154297, "global_step": 438368, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.986426830291748, "global_step": 438369, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0836477279663086, "global_step": 438370, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.066450357437134, "global_step": 438371, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0069432258605957, "global_step": 438372, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0087475776672363, "global_step": 438373, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1023600101470947, "global_step": 438374, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.142563819885254, "global_step": 438375, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0883781909942627, "global_step": 438376, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0754904747009277, "global_step": 438377, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1296098232269287, "global_step": 438378, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1472926139831543, "global_step": 438379, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1664950847625732, "global_step": 438380, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1258294582366943, "global_step": 438381, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0906460285186768, "global_step": 438382, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0865676403045654, "global_step": 438383, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1070072650909424, "global_step": 438384, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1275858879089355, "global_step": 438385, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1199166774749756, "global_step": 438386, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.079038619995117, "global_step": 438387, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0347814559936523, "global_step": 438388, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0931835174560547, "global_step": 438389, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1065869331359863, "global_step": 438390, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.990340232849121, "global_step": 438391, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.074260950088501, "global_step": 438392, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0422797203063965, "global_step": 438393, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1036648750305176, "global_step": 438394, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.957051157951355, "global_step": 438395, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.115406036376953, "global_step": 438396, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.003549098968506, "global_step": 438397, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1216588020324707, "global_step": 438398, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0457472801208496, "global_step": 438399, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0671894550323486, "global_step": 438400, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0208427906036377, "global_step": 438401, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0450198650360107, "global_step": 438402, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.174677848815918, "global_step": 438403, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.084550142288208, "global_step": 438404, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0936360359191895, "global_step": 438405, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0826780796051025, "global_step": 438406, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1593315601348877, "global_step": 438407, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.032292366027832, "global_step": 438408, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.077204942703247, "global_step": 438409, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.037594795227051, "global_step": 438410, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.08329701423645, "global_step": 438411, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0208353996276855, "global_step": 438412, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.147542715072632, "global_step": 438413, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0736982822418213, "global_step": 438414, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.116586685180664, "global_step": 438415, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.054302215576172, "global_step": 438416, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0538289546966553, "global_step": 438417, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1629257202148438, "global_step": 438418, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0434763431549072, "global_step": 438419, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.081559896469116, "global_step": 438420, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0525221824645996, "global_step": 438421, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.097639560699463, "global_step": 438422, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.039777994155884, "global_step": 438423, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0937387943267822, "global_step": 438424, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.055422782897949, "global_step": 438425, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.049623966217041, "global_step": 438426, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0504281520843506, "global_step": 438427, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.027932643890381, "global_step": 438428, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0341134071350098, "global_step": 438429, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.031374216079712, "global_step": 438430, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1401171684265137, "global_step": 438431, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1508700847625732, "global_step": 438432, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0293760299682617, "global_step": 438433, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0583391189575195, "global_step": 438434, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0170767307281494, "global_step": 438435, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0519802570343018, "global_step": 438436, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.063723564147949, "global_step": 438437, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.11969256401062, "global_step": 438438, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.122830390930176, "global_step": 438439, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.114788293838501, "global_step": 438440, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1115963459014893, "global_step": 438441, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.99875009059906, "global_step": 438442, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1747045516967773, "global_step": 438443, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0995450019836426, "global_step": 438444, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.016284704208374, "global_step": 438445, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.157473087310791, "global_step": 438446, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0304641723632812, "global_step": 438447, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0919978618621826, "global_step": 438448, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0040836334228516, "global_step": 438449, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0909650325775146, "global_step": 438450, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0163469314575195, "global_step": 438451, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.22739839553833, "global_step": 438452, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1387641429901123, "global_step": 438453, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.037452459335327, "global_step": 438454, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0478832721710205, "global_step": 438455, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.180771589279175, "global_step": 438456, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.109767198562622, "global_step": 438457, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.152069330215454, "global_step": 438458, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0950422286987305, "global_step": 438459, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1736764907836914, "global_step": 438460, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.026841878890991, "global_step": 438461, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1969878673553467, "global_step": 438462, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1340548992156982, "global_step": 438463, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0982351303100586, "global_step": 438464, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0354042053222656, "global_step": 438465, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0588624477386475, "global_step": 438466, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.119370698928833, "global_step": 438467, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.978267788887024, "global_step": 438468, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1264748573303223, "global_step": 438469, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0660221576690674, "global_step": 438470, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.131000280380249, "global_step": 438471, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0621566772460938, "global_step": 438472, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9895492792129517, "global_step": 438473, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.048699140548706, "global_step": 438474, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.110874891281128, "global_step": 438475, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.051273822784424, "global_step": 438476, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0064401626586914, "global_step": 438477, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.238119602203369, "global_step": 438478, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.06066632270813, "global_step": 438479, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.079141616821289, "global_step": 438480, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9946014881134033, "global_step": 438481, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0501439571380615, "global_step": 438482, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9829738140106201, "global_step": 438483, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.105349540710449, "global_step": 438484, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0426156520843506, "global_step": 438485, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0868940353393555, "global_step": 438486, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9889962673187256, "global_step": 438487, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0469300746917725, "global_step": 438488, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0892603397369385, "global_step": 438489, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.146846055984497, "global_step": 438490, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.148789882659912, "global_step": 438491, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.050226926803589, "global_step": 438492, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.027937889099121, "global_step": 438493, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1703109741210938, "global_step": 438494, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.104039430618286, "global_step": 438495, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0684123039245605, "global_step": 438496, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.028324842453003, "global_step": 438497, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.155510187149048, "global_step": 438498, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0619800090789795, "global_step": 438499, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9998953342437744, "global_step": 438500, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0473058223724365, "global_step": 438501, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.015815496444702, "global_step": 438502, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.057767868041992, "global_step": 438503, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.124539613723755, "global_step": 438504, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9914768934249878, "global_step": 438505, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0841939449310303, "global_step": 438506, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0366806983947754, "global_step": 438507, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1153509616851807, "global_step": 438508, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.198549270629883, "global_step": 438509, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0819196701049805, "global_step": 438510, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.163255453109741, "global_step": 438511, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.031888484954834, "global_step": 438512, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.071606159210205, "global_step": 438513, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.031209945678711, "global_step": 438514, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1210756301879883, "global_step": 438515, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9598278999328613, "global_step": 438516, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0889012813568115, "global_step": 438517, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0877110958099365, "global_step": 438518, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.10054087638855, "global_step": 438519, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1196177005767822, "global_step": 438520, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.013136863708496, "global_step": 438521, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1160638332366943, "global_step": 438522, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1039111614227295, "global_step": 438523, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.094151020050049, "global_step": 438524, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1497433185577393, "global_step": 438525, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.125547409057617, "global_step": 438526, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.111193895339966, "global_step": 438527, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1152923107147217, "global_step": 438528, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.054847478866577, "global_step": 438529, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1620073318481445, "global_step": 438530, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.11665415763855, "global_step": 438531, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.086290121078491, "global_step": 438532, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.97812020778656, "global_step": 438533, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1033308506011963, "global_step": 438534, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.071469306945801, "global_step": 438535, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1338307857513428, "global_step": 438536, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0019302368164062, "global_step": 438537, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.145744562149048, "global_step": 438538, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.048769235610962, "global_step": 438539, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0330617427825928, "global_step": 438540, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.096193790435791, "global_step": 438541, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0893943309783936, "global_step": 438542, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.051508665084839, "global_step": 438543, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.04402232170105, "global_step": 438544, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0690793991088867, "global_step": 438545, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.053356170654297, "global_step": 438546, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.054354429244995, "global_step": 438547, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1415607929229736, "global_step": 438548, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1452114582061768, "global_step": 438549, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0512092113494873, "global_step": 438550, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0938241481781006, "global_step": 438551, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.109015464782715, "global_step": 438552, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1113619804382324, "global_step": 438553, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.138068675994873, "global_step": 438554, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.08890962600708, "global_step": 438555, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1311988830566406, "global_step": 438556, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.076441526412964, "global_step": 438557, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0616142749786377, "global_step": 438558, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.060889720916748, "global_step": 438559, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.066549062728882, "global_step": 438560, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.071624755859375, "global_step": 438561, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0806024074554443, "global_step": 438562, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0400888919830322, "global_step": 438563, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.122483491897583, "global_step": 438564, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0797934532165527, "global_step": 438565, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.022815704345703, "global_step": 438566, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.089707136154175, "global_step": 438567, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1054129600524902, "global_step": 438568, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.072479724884033, "global_step": 438569, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.139394998550415, "global_step": 438570, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0627553462982178, "global_step": 438571, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.075287103652954, "global_step": 438572, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0198051929473877, "global_step": 438573, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0800282955169678, "global_step": 438574, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1203088760375977, "global_step": 438575, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.08097505569458, "global_step": 438576, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9761219024658203, "global_step": 438577, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0156090259552, "global_step": 438578, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1255502700805664, "global_step": 438579, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9803842306137085, "global_step": 438580, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9726616144180298, "global_step": 438581, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1640419960021973, "global_step": 438582, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.126487970352173, "global_step": 438583, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.191112756729126, "global_step": 438584, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.051509380340576, "global_step": 438585, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0507137775421143, "global_step": 438586, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.147284984588623, "global_step": 438587, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.067903518676758, "global_step": 438588, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.046875238418579, "global_step": 438589, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0821170806884766, "global_step": 438590, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0610363483428955, "global_step": 438591, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0476460456848145, "global_step": 438592, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.927107572555542, "global_step": 438593, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9933130741119385, "global_step": 438594, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0224833488464355, "global_step": 438595, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.00750994682312, "global_step": 438596, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0613794326782227, "global_step": 438597, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.159313917160034, "global_step": 438598, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1203863620758057, "global_step": 438599, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1184499263763428, "global_step": 438600, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0722641944885254, "global_step": 438601, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.01342511177063, "global_step": 438602, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.058349609375, "global_step": 438603, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.994783639907837, "global_step": 438604, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1179189682006836, "global_step": 438605, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0425143241882324, "global_step": 438606, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.116079568862915, "global_step": 438607, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.123474359512329, "global_step": 438608, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0910987854003906, "global_step": 438609, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0807855129241943, "global_step": 438610, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0138564109802246, "global_step": 438611, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.071265459060669, "global_step": 438612, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.088350296020508, "global_step": 438613, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.084545612335205, "global_step": 438614, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.090134859085083, "global_step": 438615, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.133608818054199, "global_step": 438616, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0576653480529785, "global_step": 438617, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0365140438079834, "global_step": 438618, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.07822847366333, "global_step": 438619, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.069207191467285, "global_step": 438620, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.007483720779419, "global_step": 438621, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9905643463134766, "global_step": 438622, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1086347103118896, "global_step": 438623, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0057384967803955, "global_step": 438624, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0128817558288574, "global_step": 438625, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0536906719207764, "global_step": 438626, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.100989818572998, "global_step": 438627, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.109285354614258, "global_step": 438628, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0250372886657715, "global_step": 438629, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.153177499771118, "global_step": 438630, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.076047658920288, "global_step": 438631, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1210222244262695, "global_step": 438632, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.038560628890991, "global_step": 438633, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.072932481765747, "global_step": 438634, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0558817386627197, "global_step": 438635, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.094773292541504, "global_step": 438636, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0770819187164307, "global_step": 438637, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1076626777648926, "global_step": 438638, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1671273708343506, "global_step": 438639, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.108327627182007, "global_step": 438640, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1495611667633057, "global_step": 438641, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.978747844696045, "global_step": 438642, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.090120315551758, "global_step": 438643, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.013227701187134, "global_step": 438644, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0784385204315186, "global_step": 438645, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.043231964111328, "global_step": 438646, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0391509532928467, "global_step": 438647, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.031867742538452, "global_step": 438648, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0657243728637695, "global_step": 438649, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.15085768699646, "global_step": 438650, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.166590929031372, "global_step": 438651, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1640357971191406, "global_step": 438652, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0903542041778564, "global_step": 438653, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1032233238220215, "global_step": 438654, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0958950519561768, "global_step": 438655, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.029700994491577, "global_step": 438656, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0732381343841553, "global_step": 438657, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.071380376815796, "global_step": 438658, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0678787231445312, "global_step": 438659, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1336638927459717, "global_step": 438660, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1194889545440674, "global_step": 438661, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1386559009552, "global_step": 438662, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1020710468292236, "global_step": 438663, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.104196786880493, "global_step": 438664, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0470926761627197, "global_step": 438665, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0364747047424316, "global_step": 438666, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.088987112045288, "global_step": 438667, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0818982124328613, "global_step": 438668, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.103506326675415, "global_step": 438669, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0748870372772217, "global_step": 438670, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1158125400543213, "global_step": 438671, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.120818853378296, "global_step": 438672, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0766165256500244, "global_step": 438673, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.196019411087036, "global_step": 438674, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.133599042892456, "global_step": 438675, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0409369468688965, "global_step": 438676, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0451183319091797, "global_step": 438677, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.019979476928711, "global_step": 438678, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.126875877380371, "global_step": 438679, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.162726402282715, "global_step": 438680, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.115090847015381, "global_step": 438681, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0827455520629883, "global_step": 438682, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.129075765609741, "global_step": 438683, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.118471384048462, "global_step": 438684, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.095672130584717, "global_step": 438685, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.13043475151062, "global_step": 438686, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0468671321868896, "global_step": 438687, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0369362831115723, "global_step": 438688, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.107282876968384, "global_step": 438689, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.10506272315979, "global_step": 438690, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.098726511001587, "global_step": 438691, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0983686447143555, "global_step": 438692, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0125789642333984, "global_step": 438693, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.02968430519104, "global_step": 438694, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0762054920196533, "global_step": 438695, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0462136268615723, "global_step": 438696, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.084303855895996, "global_step": 438697, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0731658935546875, "global_step": 438698, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0786821842193604, "global_step": 438699, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.078350067138672, "global_step": 438700, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1396684646606445, "global_step": 438701, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.115781545639038, "global_step": 438702, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0816233158111572, "global_step": 438703, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.196354627609253, "global_step": 438704, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0034804344177246, "global_step": 438705, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.10021710395813, "global_step": 438706, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.04703950881958, "global_step": 438707, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.117903470993042, "global_step": 438708, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.092801809310913, "global_step": 438709, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.010836601257324, "global_step": 438710, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.061290979385376, "global_step": 438711, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.070687770843506, "global_step": 438712, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1025750637054443, "global_step": 438713, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9787559509277344, "global_step": 438714, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.063065528869629, "global_step": 438715, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0489096641540527, "global_step": 438716, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0828139781951904, "global_step": 438717, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1504931449890137, "global_step": 438718, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1379024982452393, "global_step": 438719, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.083528518676758, "global_step": 438720, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.08829665184021, "global_step": 438721, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.11954927444458, "global_step": 438722, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0992236137390137, "global_step": 438723, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0415048599243164, "global_step": 438724, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1285505294799805, "global_step": 438725, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1098554134368896, "global_step": 438726, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.091679811477661, "global_step": 438727, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1245737075805664, "global_step": 438728, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.070303201675415, "global_step": 438729, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.156212091445923, "global_step": 438730, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.044008731842041, "global_step": 438731, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1045498847961426, "global_step": 438732, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0571160316467285, "global_step": 438733, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.982702374458313, "global_step": 438734, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0782339572906494, "global_step": 438735, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0843875408172607, "global_step": 438736, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0975451469421387, "global_step": 438737, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9878422021865845, "global_step": 438738, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1089231967926025, "global_step": 438739, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0429680347442627, "global_step": 438740, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.042222261428833, "global_step": 438741, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.073531150817871, "global_step": 438742, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1214101314544678, "global_step": 438743, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1742677688598633, "global_step": 438744, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0907506942749023, "global_step": 438745, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.094149589538574, "global_step": 438746, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.005923271179199, "global_step": 438747, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.112583637237549, "global_step": 438748, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.104485511779785, "global_step": 438749, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0547800064086914, "global_step": 438750, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.170013427734375, "global_step": 438751, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.106215000152588, "global_step": 438752, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9984995126724243, "global_step": 438753, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0389199256896973, "global_step": 438754, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0141193866729736, "global_step": 438755, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.120664119720459, "global_step": 438756, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.095674514770508, "global_step": 438757, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0790064334869385, "global_step": 438758, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0803637504577637, "global_step": 438759, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.094259262084961, "global_step": 438760, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0859322547912598, "global_step": 438761, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9914668798446655, "global_step": 438762, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0844664573669434, "global_step": 438763, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1328182220458984, "global_step": 438764, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1136209964752197, "global_step": 438765, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1064820289611816, "global_step": 438766, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.02736234664917, "global_step": 438767, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0004324913024902, "global_step": 438768, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1317882537841797, "global_step": 438769, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1122708320617676, "global_step": 438770, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0856122970581055, "global_step": 438771, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0464060306549072, "global_step": 438772, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0742573738098145, "global_step": 438773, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1144967079162598, "global_step": 438774, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0521345138549805, "global_step": 438775, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1039905548095703, "global_step": 438776, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.2334065437316895, "global_step": 438777, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9946308135986328, "global_step": 438778, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1391985416412354, "global_step": 438779, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0614817142486572, "global_step": 438780, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0467286109924316, "global_step": 438781, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.176969289779663, "global_step": 438782, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.064725160598755, "global_step": 438783, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1335299015045166, "global_step": 438784, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.056281089782715, "global_step": 438785, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.116478204727173, "global_step": 438786, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.146709442138672, "global_step": 438787, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0114972591400146, "global_step": 438788, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.027981758117676, "global_step": 438789, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0287492275238037, "global_step": 438790, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0998032093048096, "global_step": 438791, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0515918731689453, "global_step": 438792, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.088737726211548, "global_step": 438793, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.100145101547241, "global_step": 438794, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0711283683776855, "global_step": 438795, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1396238803863525, "global_step": 438796, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0419464111328125, "global_step": 438797, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.031843423843384, "global_step": 438798, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.056034564971924, "global_step": 438799, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.110020160675049, "global_step": 438800, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9871317148208618, "global_step": 438801, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1664161682128906, "global_step": 438802, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1467297077178955, "global_step": 438803, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.125011444091797, "global_step": 438804, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0783491134643555, "global_step": 438805, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.006953001022339, "global_step": 438806, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1994593143463135, "global_step": 438807, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.035978078842163, "global_step": 438808, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.064297676086426, "global_step": 438809, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1303980350494385, "global_step": 438810, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9975353479385376, "global_step": 438811, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.038891553878784, "global_step": 438812, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0236153602600098, "global_step": 438813, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.120551347732544, "global_step": 438814, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.082315683364868, "global_step": 438815, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0987792015075684, "global_step": 438816, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1161491870880127, "global_step": 438817, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9971872568130493, "global_step": 438818, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0284245014190674, "global_step": 438819, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.097987413406372, "global_step": 438820, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1135618686676025, "global_step": 438821, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0674524307250977, "global_step": 438822, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.034377336502075, "global_step": 438823, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0091049671173096, "global_step": 438824, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0919625759124756, "global_step": 438825, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0824410915374756, "global_step": 438826, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0624186992645264, "global_step": 438827, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0029425621032715, "global_step": 438828, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0945277214050293, "global_step": 438829, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.05271315574646, "global_step": 438830, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1244914531707764, "global_step": 438831, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.087555408477783, "global_step": 438832, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.023242473602295, "global_step": 438833, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0905656814575195, "global_step": 438834, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1186439990997314, "global_step": 438835, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0315968990325928, "global_step": 438836, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.038818597793579, "global_step": 438837, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.202707052230835, "global_step": 438838, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.203021764755249, "global_step": 438839, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0786349773406982, "global_step": 438840, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0889010429382324, "global_step": 438841, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1359198093414307, "global_step": 438842, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.051178455352783, "global_step": 438843, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9232070446014404, "global_step": 438844, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.068912982940674, "global_step": 438845, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.012441396713257, "global_step": 438846, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0428996086120605, "global_step": 438847, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.124215841293335, "global_step": 438848, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0819478034973145, "global_step": 438849, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.073793888092041, "global_step": 438850, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.096409320831299, "global_step": 438851, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1126065254211426, "global_step": 438852, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0796501636505127, "global_step": 438853, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.034105062484741, "global_step": 438854, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1006920337677, "global_step": 438855, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.138625144958496, "global_step": 438856, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.969637155532837, "global_step": 438857, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0291554927825928, "global_step": 438858, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1614673137664795, "global_step": 438859, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.082732677459717, "global_step": 438860, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.021784782409668, "global_step": 438861, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.052760601043701, "global_step": 438862, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.105531930923462, "global_step": 438863, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.041701078414917, "global_step": 438864, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0487518310546875, "global_step": 438865, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1098592281341553, "global_step": 438866, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.108713150024414, "global_step": 438867, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0857796669006348, "global_step": 438868, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0592174530029297, "global_step": 438869, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0985729694366455, "global_step": 438870, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0946695804595947, "global_step": 438871, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.166200876235962, "global_step": 438872, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.079232692718506, "global_step": 438873, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0995230674743652, "global_step": 438874, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.054950475692749, "global_step": 438875, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0870323181152344, "global_step": 438876, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1277360916137695, "global_step": 438877, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0605998039245605, "global_step": 438878, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1566224098205566, "global_step": 438879, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.030017614364624, "global_step": 438880, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1495537757873535, "global_step": 438881, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0847866535186768, "global_step": 438882, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0779151916503906, "global_step": 438883, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0215654373168945, "global_step": 438884, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0404958724975586, "global_step": 438885, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.059440851211548, "global_step": 438886, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.077660083770752, "global_step": 438887, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1019790172576904, "global_step": 438888, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0365395545959473, "global_step": 438889, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1032092571258545, "global_step": 438890, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.15337872505188, "global_step": 438891, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1519598960876465, "global_step": 438892, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.063676357269287, "global_step": 438893, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.073716878890991, "global_step": 438894, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.044152021408081, "global_step": 438895, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1546144485473633, "global_step": 438896, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1093764305114746, "global_step": 438897, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.107339859008789, "global_step": 438898, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1214346885681152, "global_step": 438899, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0319974422454834, "global_step": 438900, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0105433464050293, "global_step": 438901, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0719072818756104, "global_step": 438902, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0990424156188965, "global_step": 438903, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0878236293792725, "global_step": 438904, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0940377712249756, "global_step": 438905, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.071225881576538, "global_step": 438906, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0865373611450195, "global_step": 438907, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.154508590698242, "global_step": 438908, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0707075595855713, "global_step": 438909, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1034250259399414, "global_step": 438910, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1110405921936035, "global_step": 438911, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1206233501434326, "global_step": 438912, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0503439903259277, "global_step": 438913, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1390576362609863, "global_step": 438914, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.134443521499634, "global_step": 438915, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.118291139602661, "global_step": 438916, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1024959087371826, "global_step": 438917, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0556552410125732, "global_step": 438918, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1693742275238037, "global_step": 438919, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1272902488708496, "global_step": 438920, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0839579105377197, "global_step": 438921, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.07690167427063, "global_step": 438922, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0828487873077393, "global_step": 438923, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.015315055847168, "global_step": 438924, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.147484302520752, "global_step": 438925, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.088423728942871, "global_step": 438926, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0344061851501465, "global_step": 438927, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0488672256469727, "global_step": 438928, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0009653568267822, "global_step": 438929, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0269293785095215, "global_step": 438930, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.043527603149414, "global_step": 438931, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1480822563171387, "global_step": 438932, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1109209060668945, "global_step": 438933, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.094585657119751, "global_step": 438934, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0491409301757812, "global_step": 438935, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.217231273651123, "global_step": 438936, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.057133913040161, "global_step": 438937, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9642900228500366, "global_step": 438938, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1311445236206055, "global_step": 438939, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.07417893409729, "global_step": 438940, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.126913070678711, "global_step": 438941, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1123359203338623, "global_step": 438942, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0571117401123047, "global_step": 438943, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.027914047241211, "global_step": 438944, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0720388889312744, "global_step": 438945, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.10237717628479, "global_step": 438946, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1601455211639404, "global_step": 438947, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.14585018157959, "global_step": 438948, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.072067975997925, "global_step": 438949, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0233311653137207, "global_step": 438950, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.059359550476074, "global_step": 438951, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1595890522003174, "global_step": 438952, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0461268424987793, "global_step": 438953, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0504772663116455, "global_step": 438954, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.100482940673828, "global_step": 438955, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0784759521484375, "global_step": 438956, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.019139289855957, "global_step": 438957, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.075124979019165, "global_step": 438958, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.110736608505249, "global_step": 438959, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1893608570098877, "global_step": 438960, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1227331161499023, "global_step": 438961, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1143999099731445, "global_step": 438962, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.134449005126953, "global_step": 438963, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0350723266601562, "global_step": 438964, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.089632511138916, "global_step": 438965, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.114193916320801, "global_step": 438966, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0152151584625244, "global_step": 438967, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0344035625457764, "global_step": 438968, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0649170875549316, "global_step": 438969, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0388967990875244, "global_step": 438970, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0734570026397705, "global_step": 438971, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0020275115966797, "global_step": 438972, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0885672569274902, "global_step": 438973, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.093904495239258, "global_step": 438974, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0143015384674072, "global_step": 438975, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.159306764602661, "global_step": 438976, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1560280323028564, "global_step": 438977, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.096254348754883, "global_step": 438978, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0676372051239014, "global_step": 438979, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.12101674079895, "global_step": 438980, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.066526412963867, "global_step": 438981, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0380492210388184, "global_step": 438982, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.090642213821411, "global_step": 438983, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.098496437072754, "global_step": 438984, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.033874750137329, "global_step": 438985, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0383317470550537, "global_step": 438986, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0023648738861084, "global_step": 438987, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0679867267608643, "global_step": 438988, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.190500020980835, "global_step": 438989, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1167850494384766, "global_step": 438990, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1134755611419678, "global_step": 438991, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0801916122436523, "global_step": 438992, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0898146629333496, "global_step": 438993, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1831493377685547, "global_step": 438994, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.046576738357544, "global_step": 438995, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0611155033111572, "global_step": 438996, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.2174952030181885, "global_step": 438997, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1338231563568115, "global_step": 438998, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0970308780670166, "global_step": 438999, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0647530555725098, "global_step": 439000, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1446900367736816, "global_step": 439001, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1071999073028564, "global_step": 439002, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.006472587585449, "global_step": 439003, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0109901428222656, "global_step": 439004, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1651079654693604, "global_step": 439005, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1006784439086914, "global_step": 439006, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1252264976501465, "global_step": 439007, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0667834281921387, "global_step": 439008, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.168966054916382, "global_step": 439009, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.059821605682373, "global_step": 439010, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0159811973571777, "global_step": 439011, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.08414363861084, "global_step": 439012, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1153438091278076, "global_step": 439013, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0665979385375977, "global_step": 439014, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1013710498809814, "global_step": 439015, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.054807424545288, "global_step": 439016, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0442605018615723, "global_step": 439017, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.083799123764038, "global_step": 439018, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0914788246154785, "global_step": 439019, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1184182167053223, "global_step": 439020, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1049492359161377, "global_step": 439021, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0234591960906982, "global_step": 439022, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0862176418304443, "global_step": 439023, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0462253093719482, "global_step": 439024, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0777597427368164, "global_step": 439025, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1066789627075195, "global_step": 439026, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1541788578033447, "global_step": 439027, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.013862371444702, "global_step": 439028, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.11328125, "global_step": 439029, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0139474868774414, "global_step": 439030, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.113382577896118, "global_step": 439031, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0679898262023926, "global_step": 439032, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.133347749710083, "global_step": 439033, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0387110710144043, "global_step": 439034, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.055651903152466, "global_step": 439035, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.065563917160034, "global_step": 439036, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.172386884689331, "global_step": 439037, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.174344778060913, "global_step": 439038, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0601909160614014, "global_step": 439039, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0882158279418945, "global_step": 439040, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0838024616241455, "global_step": 439041, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1222071647644043, "global_step": 439042, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.107473134994507, "global_step": 439043, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1083314418792725, "global_step": 439044, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.069878339767456, "global_step": 439045, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.029409646987915, "global_step": 439046, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.092876672744751, "global_step": 439047, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.001385450363159, "global_step": 439048, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.038879871368408, "global_step": 439049, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.085909128189087, "global_step": 439050, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1575851440429688, "global_step": 439051, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.056286096572876, "global_step": 439052, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1907267570495605, "global_step": 439053, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.98014497756958, "global_step": 439054, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0405426025390625, "global_step": 439055, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.108381986618042, "global_step": 439056, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.155486583709717, "global_step": 439057, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0586063861846924, "global_step": 439058, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1464576721191406, "global_step": 439059, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.007993221282959, "global_step": 439060, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.015516757965088, "global_step": 439061, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.2023370265960693, "global_step": 439062, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1060667037963867, "global_step": 439063, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0471203327178955, "global_step": 439064, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1269900798797607, "global_step": 439065, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.069228172302246, "global_step": 439066, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0767059326171875, "global_step": 439067, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.07550311088562, "global_step": 439068, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.05493426322937, "global_step": 439069, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.038767099380493, "global_step": 439070, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0623884201049805, "global_step": 439071, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1019976139068604, "global_step": 439072, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9834141731262207, "global_step": 439073, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.118117094039917, "global_step": 439074, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0178487300872803, "global_step": 439075, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.142446279525757, "global_step": 439076, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.098947525024414, "global_step": 439077, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.042447090148926, "global_step": 439078, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.123948097229004, "global_step": 439079, "epoch": 802, "lr": 5e-05}
{"train_loss": 1.9884719848632812, "global_step": 439080, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0861399173736572, "global_step": 439081, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1052398681640625, "global_step": 439082, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1550846099853516, "global_step": 439083, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.102036714553833, "global_step": 439084, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0712497234344482, "global_step": 439085, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.101595401763916, "global_step": 439086, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1025681495666504, "global_step": 439087, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.0298335552215576, "global_step": 439088, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.078068256378174, "global_step": 439089, "epoch": 802, "lr": 5e-05}
{"train_loss": 2.1276044845581055, "global_step": 439090, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1108689308166504, "global_step": 439091, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0638365745544434, "global_step": 439092, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0850517749786377, "global_step": 439093, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9934605360031128, "global_step": 439094, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0743815898895264, "global_step": 439095, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0972483158111572, "global_step": 439096, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.11327862739563, "global_step": 439097, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.017775774002075, "global_step": 439098, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0409739017486572, "global_step": 439099, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0932068824768066, "global_step": 439100, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0988526344299316, "global_step": 439101, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.128596067428589, "global_step": 439102, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9947395324707031, "global_step": 439103, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.052621603012085, "global_step": 439104, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.037912607192993, "global_step": 439105, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0646088123321533, "global_step": 439106, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.049652099609375, "global_step": 439107, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0569028854370117, "global_step": 439108, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.134883165359497, "global_step": 439109, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0574111938476562, "global_step": 439110, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1178581714630127, "global_step": 439111, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.066049098968506, "global_step": 439112, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.970200777053833, "global_step": 439113, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1197640895843506, "global_step": 439114, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.023906707763672, "global_step": 439115, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.011021614074707, "global_step": 439116, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0288496017456055, "global_step": 439117, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1104722023010254, "global_step": 439118, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.060652494430542, "global_step": 439119, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.2121002674102783, "global_step": 439120, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0949339866638184, "global_step": 439121, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.165017604827881, "global_step": 439122, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0353264808654785, "global_step": 439123, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1080472469329834, "global_step": 439124, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0962746143341064, "global_step": 439125, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.007051706314087, "global_step": 439126, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0978574752807617, "global_step": 439127, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0187840461730957, "global_step": 439128, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9969335794448853, "global_step": 439129, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9955965280532837, "global_step": 439130, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1338493824005127, "global_step": 439131, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9564323425292969, "global_step": 439132, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0201799869537354, "global_step": 439133, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0126068592071533, "global_step": 439134, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9707187414169312, "global_step": 439135, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0286319255828857, "global_step": 439136, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0975277423858643, "global_step": 439137, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0735111236572266, "global_step": 439138, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.206376075744629, "global_step": 439139, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0712499618530273, "global_step": 439140, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.032198190689087, "global_step": 439141, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0581493377685547, "global_step": 439142, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0675289630889893, "global_step": 439143, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0209848880767822, "global_step": 439144, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.136439561843872, "global_step": 439145, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.09061336517334, "global_step": 439146, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0858235359191895, "global_step": 439147, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0995447635650635, "global_step": 439148, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0290427207946777, "global_step": 439149, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0405659675598145, "global_step": 439150, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0951483249664307, "global_step": 439151, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.066054344177246, "global_step": 439152, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.105651378631592, "global_step": 439153, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0675952434539795, "global_step": 439154, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.034484386444092, "global_step": 439155, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.048827648162842, "global_step": 439156, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.115851879119873, "global_step": 439157, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1024045944213867, "global_step": 439158, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9937454462051392, "global_step": 439159, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.050872564315796, "global_step": 439160, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.13985013961792, "global_step": 439161, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1680407524108887, "global_step": 439162, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0781195163726807, "global_step": 439163, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.048240900039673, "global_step": 439164, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.113739252090454, "global_step": 439165, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.070779323577881, "global_step": 439166, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9783552885055542, "global_step": 439167, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1155824661254883, "global_step": 439168, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1131432056427, "global_step": 439169, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.086916923522949, "global_step": 439170, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.058596611022949, "global_step": 439171, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0631282329559326, "global_step": 439172, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0128936767578125, "global_step": 439173, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0423078536987305, "global_step": 439174, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1125452518463135, "global_step": 439175, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0635175704956055, "global_step": 439176, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0791122913360596, "global_step": 439177, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0286004543304443, "global_step": 439178, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0878758430480957, "global_step": 439179, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9186469316482544, "global_step": 439180, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1973278522491455, "global_step": 439181, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.051090955734253, "global_step": 439182, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.13987135887146, "global_step": 439183, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.074885606765747, "global_step": 439184, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.986222743988037, "global_step": 439185, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1237447261810303, "global_step": 439186, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.111589193344116, "global_step": 439187, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.132824182510376, "global_step": 439188, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1171700954437256, "global_step": 439189, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0546066761016846, "global_step": 439190, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0814414024353027, "global_step": 439191, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0482711791992188, "global_step": 439192, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.08522891998291, "global_step": 439193, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1347405910491943, "global_step": 439194, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.049814462661743, "global_step": 439195, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0884854793548584, "global_step": 439196, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0572140216827393, "global_step": 439197, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0440139770507812, "global_step": 439198, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.000397205352783, "global_step": 439199, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0902559757232666, "global_step": 439200, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0413711071014404, "global_step": 439201, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.079456329345703, "global_step": 439202, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1249101161956787, "global_step": 439203, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0958542823791504, "global_step": 439204, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0643675327301025, "global_step": 439205, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1329493522644043, "global_step": 439206, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1088879108428955, "global_step": 439207, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.018432140350342, "global_step": 439208, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0460643768310547, "global_step": 439209, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.06889009475708, "global_step": 439210, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0918092727661133, "global_step": 439211, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0323801040649414, "global_step": 439212, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.043402671813965, "global_step": 439213, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.019469976425171, "global_step": 439214, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1259853839874268, "global_step": 439215, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.133514881134033, "global_step": 439216, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.104015350341797, "global_step": 439217, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.056736469268799, "global_step": 439218, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.996809959411621, "global_step": 439219, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.116229295730591, "global_step": 439220, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.059229850769043, "global_step": 439221, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1156272888183594, "global_step": 439222, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.132538080215454, "global_step": 439223, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0522098541259766, "global_step": 439224, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0641634464263916, "global_step": 439225, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.084501028060913, "global_step": 439226, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0903704166412354, "global_step": 439227, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0979621410369873, "global_step": 439228, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0991086959838867, "global_step": 439229, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.06396222114563, "global_step": 439230, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.123248815536499, "global_step": 439231, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.02146315574646, "global_step": 439232, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0540850162506104, "global_step": 439233, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0296099185943604, "global_step": 439234, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1098544597625732, "global_step": 439235, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.053609848022461, "global_step": 439236, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1195602416992188, "global_step": 439237, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.057215690612793, "global_step": 439238, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1070594787597656, "global_step": 439239, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.041910409927368, "global_step": 439240, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0633840560913086, "global_step": 439241, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1741292476654053, "global_step": 439242, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0279552936553955, "global_step": 439243, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.973962664604187, "global_step": 439244, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.148463726043701, "global_step": 439245, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0999915599823, "global_step": 439246, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.089015483856201, "global_step": 439247, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.990586757659912, "global_step": 439248, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0195679664611816, "global_step": 439249, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1091389656066895, "global_step": 439250, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.964614987373352, "global_step": 439251, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.074185848236084, "global_step": 439252, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0257740020751953, "global_step": 439253, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.034238815307617, "global_step": 439254, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0401599407196045, "global_step": 439255, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0322296619415283, "global_step": 439256, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.087655544281006, "global_step": 439257, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1435060501098633, "global_step": 439258, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.060239315032959, "global_step": 439259, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0344619750976562, "global_step": 439260, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9965780973434448, "global_step": 439261, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.978684663772583, "global_step": 439262, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.104076623916626, "global_step": 439263, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.039966583251953, "global_step": 439264, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0133109092712402, "global_step": 439265, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.064296245574951, "global_step": 439266, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0356202125549316, "global_step": 439267, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0628888607025146, "global_step": 439268, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1552398204803467, "global_step": 439269, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.052067756652832, "global_step": 439270, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.2021539211273193, "global_step": 439271, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.019608497619629, "global_step": 439272, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1286540031433105, "global_step": 439273, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1268272399902344, "global_step": 439274, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9801380634307861, "global_step": 439275, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.2012710571289062, "global_step": 439276, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.09438419342041, "global_step": 439277, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.050319194793701, "global_step": 439278, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0670135021209717, "global_step": 439279, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.056596040725708, "global_step": 439280, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9712501764297485, "global_step": 439281, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1338562965393066, "global_step": 439282, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.101226806640625, "global_step": 439283, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0557401180267334, "global_step": 439284, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1212379932403564, "global_step": 439285, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.034116744995117, "global_step": 439286, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.110801935195923, "global_step": 439287, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0362324714660645, "global_step": 439288, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0867090225219727, "global_step": 439289, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.096884250640869, "global_step": 439290, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.067096471786499, "global_step": 439291, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0920581817626953, "global_step": 439292, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0141332149505615, "global_step": 439293, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0413103103637695, "global_step": 439294, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0883853435516357, "global_step": 439295, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.116821765899658, "global_step": 439296, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1047446727752686, "global_step": 439297, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0609049797058105, "global_step": 439298, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.099153518676758, "global_step": 439299, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1321604251861572, "global_step": 439300, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.050558567047119, "global_step": 439301, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0614981651306152, "global_step": 439302, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9859399795532227, "global_step": 439303, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0341908931732178, "global_step": 439304, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0386812686920166, "global_step": 439305, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.011650562286377, "global_step": 439306, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.070591688156128, "global_step": 439307, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.094329357147217, "global_step": 439308, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.144219160079956, "global_step": 439309, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0839359760284424, "global_step": 439310, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0777294635772705, "global_step": 439311, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.066152572631836, "global_step": 439312, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1050026416778564, "global_step": 439313, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.168724775314331, "global_step": 439314, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0567681789398193, "global_step": 439315, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1109867095947266, "global_step": 439316, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.152556896209717, "global_step": 439317, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0489139556884766, "global_step": 439318, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1071081161499023, "global_step": 439319, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.046867847442627, "global_step": 439320, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9685447216033936, "global_step": 439321, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.138399362564087, "global_step": 439322, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.037508964538574, "global_step": 439323, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0626325607299805, "global_step": 439324, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0910356044769287, "global_step": 439325, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.983214259147644, "global_step": 439326, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.042722702026367, "global_step": 439327, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0571939945220947, "global_step": 439328, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1844894886016846, "global_step": 439329, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.035977840423584, "global_step": 439330, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0605716705322266, "global_step": 439331, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0868239402770996, "global_step": 439332, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.120065450668335, "global_step": 439333, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0509233474731445, "global_step": 439334, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.062052011489868, "global_step": 439335, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.111693859100342, "global_step": 439336, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.088282585144043, "global_step": 439337, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0405287742614746, "global_step": 439338, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1931729316711426, "global_step": 439339, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0215749740600586, "global_step": 439340, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.093031883239746, "global_step": 439341, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1253552436828613, "global_step": 439342, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1136789321899414, "global_step": 439343, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9838008880615234, "global_step": 439344, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0808982849121094, "global_step": 439345, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.126533269882202, "global_step": 439346, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.038947105407715, "global_step": 439347, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0411832332611084, "global_step": 439348, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0022685527801514, "global_step": 439349, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.028701066970825, "global_step": 439350, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0565025806427, "global_step": 439351, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.077679395675659, "global_step": 439352, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0346221923828125, "global_step": 439353, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9709385633468628, "global_step": 439354, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1186399459838867, "global_step": 439355, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0275590419769287, "global_step": 439356, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0667552947998047, "global_step": 439357, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.10099196434021, "global_step": 439358, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0392305850982666, "global_step": 439359, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0879361629486084, "global_step": 439360, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.090811014175415, "global_step": 439361, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.063993215560913, "global_step": 439362, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1070284843444824, "global_step": 439363, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0753068923950195, "global_step": 439364, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.153233528137207, "global_step": 439365, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1195952892303467, "global_step": 439366, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0012333393096924, "global_step": 439367, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.151416063308716, "global_step": 439368, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1009681224823, "global_step": 439369, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9893921613693237, "global_step": 439370, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0765438079833984, "global_step": 439371, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1720926761627197, "global_step": 439372, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0836565494537354, "global_step": 439373, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0916178226470947, "global_step": 439374, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0760891437530518, "global_step": 439375, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.020638942718506, "global_step": 439376, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.092864990234375, "global_step": 439377, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.116363763809204, "global_step": 439378, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1231350898742676, "global_step": 439379, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1585090160369873, "global_step": 439380, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1040074825286865, "global_step": 439381, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.103548765182495, "global_step": 439382, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0231082439422607, "global_step": 439383, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.04403018951416, "global_step": 439384, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1078059673309326, "global_step": 439385, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.107292652130127, "global_step": 439386, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9972233772277832, "global_step": 439387, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1115036010742188, "global_step": 439388, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0082342624664307, "global_step": 439389, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.033398151397705, "global_step": 439390, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.140908718109131, "global_step": 439391, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.105572462081909, "global_step": 439392, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.070504665374756, "global_step": 439393, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.034395694732666, "global_step": 439394, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.123985767364502, "global_step": 439395, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0292489528656006, "global_step": 439396, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0461604595184326, "global_step": 439397, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.010770559310913, "global_step": 439398, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.102381706237793, "global_step": 439399, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1271626949310303, "global_step": 439400, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0608115196228027, "global_step": 439401, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1020967960357666, "global_step": 439402, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0827372074127197, "global_step": 439403, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9597605466842651, "global_step": 439404, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0703775882720947, "global_step": 439405, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.088393211364746, "global_step": 439406, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1181845664978027, "global_step": 439407, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0889644622802734, "global_step": 439408, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0601789951324463, "global_step": 439409, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0471572875976562, "global_step": 439410, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.010753870010376, "global_step": 439411, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0718226432800293, "global_step": 439412, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.096637725830078, "global_step": 439413, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1069600582122803, "global_step": 439414, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0831048488616943, "global_step": 439415, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1572225093841553, "global_step": 439416, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9494380950927734, "global_step": 439417, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.061690092086792, "global_step": 439418, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0338261127471924, "global_step": 439419, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.042177200317383, "global_step": 439420, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9673404693603516, "global_step": 439421, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0434117317199707, "global_step": 439422, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.059516668319702, "global_step": 439423, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0946671962738037, "global_step": 439424, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.074113130569458, "global_step": 439425, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0583300590515137, "global_step": 439426, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1450393199920654, "global_step": 439427, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0529303550720215, "global_step": 439428, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.039184808731079, "global_step": 439429, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0931169986724854, "global_step": 439430, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.012942314147949, "global_step": 439431, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0760464668273926, "global_step": 439432, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0949110984802246, "global_step": 439433, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.13904070854187, "global_step": 439434, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.079240322113037, "global_step": 439435, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.033980131149292, "global_step": 439436, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0426080226898193, "global_step": 439437, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.071488380432129, "global_step": 439438, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.114912271499634, "global_step": 439439, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1406917572021484, "global_step": 439440, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0904695987701416, "global_step": 439441, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0833940505981445, "global_step": 439442, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.078869581222534, "global_step": 439443, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.04966402053833, "global_step": 439444, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0875141620635986, "global_step": 439445, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0158960819244385, "global_step": 439446, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0905096530914307, "global_step": 439447, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1070103645324707, "global_step": 439448, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0311827659606934, "global_step": 439449, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.103184461593628, "global_step": 439450, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.092806100845337, "global_step": 439451, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0399465560913086, "global_step": 439452, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1059043407440186, "global_step": 439453, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.130636692047119, "global_step": 439454, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0279414653778076, "global_step": 439455, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.096703052520752, "global_step": 439456, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1152243614196777, "global_step": 439457, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0798611640930176, "global_step": 439458, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.069247007369995, "global_step": 439459, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.007323741912842, "global_step": 439460, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0985894203186035, "global_step": 439461, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0107152462005615, "global_step": 439462, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1847147941589355, "global_step": 439463, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.018235445022583, "global_step": 439464, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0839123725891113, "global_step": 439465, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0993456840515137, "global_step": 439466, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1711935997009277, "global_step": 439467, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.114407539367676, "global_step": 439468, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.018599510192871, "global_step": 439469, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.167320966720581, "global_step": 439470, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0426185131073, "global_step": 439471, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0973334312438965, "global_step": 439472, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.067744255065918, "global_step": 439473, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0344958305358887, "global_step": 439474, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0679538249969482, "global_step": 439475, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1002590656280518, "global_step": 439476, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.084716320037842, "global_step": 439477, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.121720790863037, "global_step": 439478, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.107304811477661, "global_step": 439479, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0245778560638428, "global_step": 439480, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0518007278442383, "global_step": 439481, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.970504879951477, "global_step": 439482, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0063719749450684, "global_step": 439483, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0494210720062256, "global_step": 439484, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1791694164276123, "global_step": 439485, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1247525215148926, "global_step": 439486, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.08842396736145, "global_step": 439487, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.135746955871582, "global_step": 439488, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1147923469543457, "global_step": 439489, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0974836349487305, "global_step": 439490, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.069509506225586, "global_step": 439491, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0876636505126953, "global_step": 439492, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1589772701263428, "global_step": 439493, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0342907905578613, "global_step": 439494, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.090953826904297, "global_step": 439495, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0285520553588867, "global_step": 439496, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0267348289489746, "global_step": 439497, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.156477928161621, "global_step": 439498, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.08622670173645, "global_step": 439499, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1091058254241943, "global_step": 439500, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0418334007263184, "global_step": 439501, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.122190237045288, "global_step": 439502, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.083010196685791, "global_step": 439503, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.043229341506958, "global_step": 439504, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1087584495544434, "global_step": 439505, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0800864696502686, "global_step": 439506, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9919391870498657, "global_step": 439507, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.070765256881714, "global_step": 439508, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0474700927734375, "global_step": 439509, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.075977325439453, "global_step": 439510, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.060945987701416, "global_step": 439511, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1311166286468506, "global_step": 439512, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0693702697753906, "global_step": 439513, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.048529624938965, "global_step": 439514, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.028679370880127, "global_step": 439515, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0826056003570557, "global_step": 439516, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.120169162750244, "global_step": 439517, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0271034240722656, "global_step": 439518, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.044060468673706, "global_step": 439519, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0821890830993652, "global_step": 439520, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.06354022026062, "global_step": 439521, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.067192792892456, "global_step": 439522, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1215431690216064, "global_step": 439523, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.145637035369873, "global_step": 439524, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.2047202587127686, "global_step": 439525, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0539205074310303, "global_step": 439526, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1190736293792725, "global_step": 439527, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.139312982559204, "global_step": 439528, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1657662391662598, "global_step": 439529, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0901012420654297, "global_step": 439530, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0913727283477783, "global_step": 439531, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0052053928375244, "global_step": 439532, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.165144443511963, "global_step": 439533, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0587635040283203, "global_step": 439534, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0497474670410156, "global_step": 439535, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0744638442993164, "global_step": 439536, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0757882595062256, "global_step": 439537, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.099104881286621, "global_step": 439538, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.078051805496216, "global_step": 439539, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0737693309783936, "global_step": 439540, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9819962978363037, "global_step": 439541, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.109199047088623, "global_step": 439542, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.052769184112549, "global_step": 439543, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0550780296325684, "global_step": 439544, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.034123659133911, "global_step": 439545, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0723724365234375, "global_step": 439546, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0596585273742676, "global_step": 439547, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.082847833633423, "global_step": 439548, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.135437250137329, "global_step": 439549, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0040502548217773, "global_step": 439550, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0126094818115234, "global_step": 439551, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1339168548583984, "global_step": 439552, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0712573528289795, "global_step": 439553, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.171963691711426, "global_step": 439554, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.009397506713867, "global_step": 439555, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0475382804870605, "global_step": 439556, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0593416690826416, "global_step": 439557, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0399811267852783, "global_step": 439558, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.130103588104248, "global_step": 439559, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0866682529449463, "global_step": 439560, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0947630405426025, "global_step": 439561, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.007131576538086, "global_step": 439562, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1286990642547607, "global_step": 439563, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0394058227539062, "global_step": 439564, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.082862138748169, "global_step": 439565, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1190056800842285, "global_step": 439566, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1308677196502686, "global_step": 439567, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.106204032897949, "global_step": 439568, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.07511830329895, "global_step": 439569, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.036932945251465, "global_step": 439570, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0338149070739746, "global_step": 439571, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.098513603210449, "global_step": 439572, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0903098583221436, "global_step": 439573, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.102768659591675, "global_step": 439574, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.079332113265991, "global_step": 439575, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1591553688049316, "global_step": 439576, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.061910390853882, "global_step": 439577, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.074258804321289, "global_step": 439578, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.064415454864502, "global_step": 439579, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.055715560913086, "global_step": 439580, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0931003093719482, "global_step": 439581, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0950987339019775, "global_step": 439582, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0678327083587646, "global_step": 439583, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1359658241271973, "global_step": 439584, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9904346466064453, "global_step": 439585, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0240225791931152, "global_step": 439586, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9971238374710083, "global_step": 439587, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1255440711975098, "global_step": 439588, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.081894636154175, "global_step": 439589, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.056138038635254, "global_step": 439590, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0374724864959717, "global_step": 439591, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9685547351837158, "global_step": 439592, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.079713821411133, "global_step": 439593, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.098351240158081, "global_step": 439594, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0012714862823486, "global_step": 439595, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1241488456726074, "global_step": 439596, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1573076248168945, "global_step": 439597, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0471410751342773, "global_step": 439598, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.044076919555664, "global_step": 439599, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0283203125, "global_step": 439600, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0880067348480225, "global_step": 439601, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.146688461303711, "global_step": 439602, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0084218978881836, "global_step": 439603, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.067037582397461, "global_step": 439604, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0751757621765137, "global_step": 439605, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0029962062835693, "global_step": 439606, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1271355152130127, "global_step": 439607, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.054105520248413, "global_step": 439608, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0547027587890625, "global_step": 439609, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1229074001312256, "global_step": 439610, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0719966888427734, "global_step": 439611, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1239209175109863, "global_step": 439612, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1812427043914795, "global_step": 439613, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.050647735595703, "global_step": 439614, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1031999588012695, "global_step": 439615, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.194455623626709, "global_step": 439616, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9908257722854614, "global_step": 439617, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.030287742614746, "global_step": 439618, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0343546867370605, "global_step": 439619, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0358119010925293, "global_step": 439620, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1109492778778076, "global_step": 439621, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.102461338043213, "global_step": 439622, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0263171195983887, "global_step": 439623, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0573530197143555, "global_step": 439624, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1694905757904053, "global_step": 439625, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.075390577316284, "global_step": 439626, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.079524040222168, "global_step": 439627, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9965813159942627, "global_step": 439628, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1360416412353516, "global_step": 439629, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.110663890838623, "global_step": 439630, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.101506471633911, "global_step": 439631, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1839280128479004, "global_step": 439632, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0794837474823, "global_step": 439633, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.075223445892334, "global_step": 439634, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0877184867858887, "global_step": 439635, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.040560007095337, "global_step": 439636, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.158810615539551, "global_step": 439637, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1291451454162598, "global_step": 439638, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.061267375946045, "global_step": 439639, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.099456310272217, "global_step": 439640, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0939571857452393, "global_step": 439641, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9907540082931519, "global_step": 439642, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0755178928375244, "global_step": 439643, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.109675407409668, "global_step": 439644, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0952720642089844, "global_step": 439645, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1039528846740723, "global_step": 439646, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1136863231658936, "global_step": 439647, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1278698444366455, "global_step": 439648, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0116493701934814, "global_step": 439649, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0574426651000977, "global_step": 439650, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.113637685775757, "global_step": 439651, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.109389305114746, "global_step": 439652, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0497243404388428, "global_step": 439653, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.061798572540283, "global_step": 439654, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.183525323867798, "global_step": 439655, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.112485408782959, "global_step": 439656, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.095839500427246, "global_step": 439657, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.155311107635498, "global_step": 439658, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9973766803741455, "global_step": 439659, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.061901807785034, "global_step": 439660, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9299801588058472, "global_step": 439661, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0610909461975098, "global_step": 439662, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0671238899230957, "global_step": 439663, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0762906074523926, "global_step": 439664, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.111207962036133, "global_step": 439665, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0967562198638916, "global_step": 439666, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0023293495178223, "global_step": 439667, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0825400352478027, "global_step": 439668, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0075268745422363, "global_step": 439669, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.037564516067505, "global_step": 439670, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1210122108459473, "global_step": 439671, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.012723445892334, "global_step": 439672, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.063657522201538, "global_step": 439673, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0706238746643066, "global_step": 439674, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.05127215385437, "global_step": 439675, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1549792289733887, "global_step": 439676, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.073817253112793, "global_step": 439677, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0550272464752197, "global_step": 439678, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.024728298187256, "global_step": 439679, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.117593288421631, "global_step": 439680, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0914173126220703, "global_step": 439681, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.958832025527954, "global_step": 439682, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1214005947113037, "global_step": 439683, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.035324811935425, "global_step": 439684, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.061596632003784, "global_step": 439685, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0672152042388916, "global_step": 439686, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.973747730255127, "global_step": 439687, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.99965500831604, "global_step": 439688, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0346782207489014, "global_step": 439689, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.056518316268921, "global_step": 439690, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0872714519500732, "global_step": 439691, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0733067989349365, "global_step": 439692, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.063121795654297, "global_step": 439693, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.012596607208252, "global_step": 439694, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0256898403167725, "global_step": 439695, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1161038875579834, "global_step": 439696, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.110626697540283, "global_step": 439697, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0510263442993164, "global_step": 439698, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0497021675109863, "global_step": 439699, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0680031776428223, "global_step": 439700, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1355648040771484, "global_step": 439701, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.051788091659546, "global_step": 439702, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.044210433959961, "global_step": 439703, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1644084453582764, "global_step": 439704, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0966057777404785, "global_step": 439705, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0392801761627197, "global_step": 439706, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0648481845855713, "global_step": 439707, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.090409278869629, "global_step": 439708, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.077604293823242, "global_step": 439709, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0255343914031982, "global_step": 439710, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0896475315093994, "global_step": 439711, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1053414344787598, "global_step": 439712, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0267834663391113, "global_step": 439713, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.063964605331421, "global_step": 439714, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0323915481567383, "global_step": 439715, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.057676076889038, "global_step": 439716, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9781945943832397, "global_step": 439717, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0133275985717773, "global_step": 439718, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.075303077697754, "global_step": 439719, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0315637588500977, "global_step": 439720, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0662436485290527, "global_step": 439721, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1495745182037354, "global_step": 439722, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.058414936065674, "global_step": 439723, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1111531257629395, "global_step": 439724, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.065356731414795, "global_step": 439725, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1278505325317383, "global_step": 439726, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.071521282196045, "global_step": 439727, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.106097936630249, "global_step": 439728, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.997666597366333, "global_step": 439729, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.938392996788025, "global_step": 439730, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.974928379058838, "global_step": 439731, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1162383556365967, "global_step": 439732, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.193699836730957, "global_step": 439733, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.119119644165039, "global_step": 439734, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.050156593322754, "global_step": 439735, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.121845245361328, "global_step": 439736, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1035943031311035, "global_step": 439737, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0904033184051514, "global_step": 439738, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0062484741210938, "global_step": 439739, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0699071884155273, "global_step": 439740, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0785443782806396, "global_step": 439741, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0558669567108154, "global_step": 439742, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.057537078857422, "global_step": 439743, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.098804235458374, "global_step": 439744, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1503207683563232, "global_step": 439745, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.095808267593384, "global_step": 439746, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0336878299713135, "global_step": 439747, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.161022186279297, "global_step": 439748, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.135451555252075, "global_step": 439749, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1147475242614746, "global_step": 439750, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.007814645767212, "global_step": 439751, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.139200448989868, "global_step": 439752, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0480027198791504, "global_step": 439753, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1054983139038086, "global_step": 439754, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.116741180419922, "global_step": 439755, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0852015018463135, "global_step": 439756, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.116499662399292, "global_step": 439757, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1018764972686768, "global_step": 439758, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0421388149261475, "global_step": 439759, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1272385120391846, "global_step": 439760, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.141650676727295, "global_step": 439761, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.035230875015259, "global_step": 439762, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1815273761749268, "global_step": 439763, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1153249740600586, "global_step": 439764, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.162490129470825, "global_step": 439765, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1572000980377197, "global_step": 439766, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.051671266555786, "global_step": 439767, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0874760150909424, "global_step": 439768, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0756101608276367, "global_step": 439769, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.147702932357788, "global_step": 439770, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.154416799545288, "global_step": 439771, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0135223865509033, "global_step": 439772, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1340997219085693, "global_step": 439773, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.099043607711792, "global_step": 439774, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1210243701934814, "global_step": 439775, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0745325088500977, "global_step": 439776, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.103752851486206, "global_step": 439777, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.110464334487915, "global_step": 439778, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.042435884475708, "global_step": 439779, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1603381633758545, "global_step": 439780, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.082277774810791, "global_step": 439781, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.079885482788086, "global_step": 439782, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.070037841796875, "global_step": 439783, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.06636643409729, "global_step": 439784, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0570735931396484, "global_step": 439785, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0214436054229736, "global_step": 439786, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1398141384124756, "global_step": 439787, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.108246326446533, "global_step": 439788, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0783016681671143, "global_step": 439789, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0722923278808594, "global_step": 439790, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1335933208465576, "global_step": 439791, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.055635690689087, "global_step": 439792, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1363909244537354, "global_step": 439793, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1071388721466064, "global_step": 439794, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.087942123413086, "global_step": 439795, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.049593448638916, "global_step": 439796, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1258254051208496, "global_step": 439797, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.024940252304077, "global_step": 439798, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0367720127105713, "global_step": 439799, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0301008224487305, "global_step": 439800, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0500121116638184, "global_step": 439801, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.097255229949951, "global_step": 439802, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.063788652420044, "global_step": 439803, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0042848587036133, "global_step": 439804, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0707292556762695, "global_step": 439805, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.186234951019287, "global_step": 439806, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0674996376037598, "global_step": 439807, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.025312662124634, "global_step": 439808, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0188705921173096, "global_step": 439809, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.102942943572998, "global_step": 439810, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0603601932525635, "global_step": 439811, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.083735704421997, "global_step": 439812, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1047558784484863, "global_step": 439813, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.119495153427124, "global_step": 439814, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.114003896713257, "global_step": 439815, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1271233558654785, "global_step": 439816, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.003736734390259, "global_step": 439817, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.997933268547058, "global_step": 439818, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.050798177719116, "global_step": 439819, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1539714336395264, "global_step": 439820, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0625946521759033, "global_step": 439821, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0054574012756348, "global_step": 439822, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.104067802429199, "global_step": 439823, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0853326320648193, "global_step": 439824, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0239973068237305, "global_step": 439825, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.125962257385254, "global_step": 439826, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.179065227508545, "global_step": 439827, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9779373407363892, "global_step": 439828, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.172919273376465, "global_step": 439829, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0980899333953857, "global_step": 439830, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1341824531555176, "global_step": 439831, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.068631887435913, "global_step": 439832, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.066699981689453, "global_step": 439833, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0804216861724854, "global_step": 439834, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.140075922012329, "global_step": 439835, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.059917449951172, "global_step": 439836, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0505523681640625, "global_step": 439837, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.140475034713745, "global_step": 439838, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0383574962615967, "global_step": 439839, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0482170581817627, "global_step": 439840, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.185681104660034, "global_step": 439841, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.06782865524292, "global_step": 439842, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0915207862854004, "global_step": 439843, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0367865562438965, "global_step": 439844, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.103084087371826, "global_step": 439845, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.155122995376587, "global_step": 439846, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0824568271636963, "global_step": 439847, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.065037250518799, "global_step": 439848, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.038109302520752, "global_step": 439849, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.110513925552368, "global_step": 439850, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1739559173583984, "global_step": 439851, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.164177417755127, "global_step": 439852, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.075490713119507, "global_step": 439853, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1297175884246826, "global_step": 439854, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.045013427734375, "global_step": 439855, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1672370433807373, "global_step": 439856, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.046100616455078, "global_step": 439857, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1045069694519043, "global_step": 439858, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0640745162963867, "global_step": 439859, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9971210956573486, "global_step": 439860, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0982108116149902, "global_step": 439861, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.116044521331787, "global_step": 439862, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0724151134490967, "global_step": 439863, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1485865116119385, "global_step": 439864, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.088463306427002, "global_step": 439865, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9875743389129639, "global_step": 439866, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.102916717529297, "global_step": 439867, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.076495885848999, "global_step": 439868, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0439627170562744, "global_step": 439869, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0415866374969482, "global_step": 439870, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.068392753601074, "global_step": 439871, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9812322854995728, "global_step": 439872, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.103407621383667, "global_step": 439873, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0161759853363037, "global_step": 439874, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0715818405151367, "global_step": 439875, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.009465456008911, "global_step": 439876, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0407440662384033, "global_step": 439877, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0521011352539062, "global_step": 439878, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0654006004333496, "global_step": 439879, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0922491550445557, "global_step": 439880, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0519988536834717, "global_step": 439881, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.024754762649536, "global_step": 439882, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.063486099243164, "global_step": 439883, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.069857120513916, "global_step": 439884, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.094048500061035, "global_step": 439885, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1130592823028564, "global_step": 439886, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9856483936309814, "global_step": 439887, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.098517417907715, "global_step": 439888, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.056868076324463, "global_step": 439889, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.164759874343872, "global_step": 439890, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.064120054244995, "global_step": 439891, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.067718267440796, "global_step": 439892, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.10430645942688, "global_step": 439893, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0603325366973877, "global_step": 439894, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0419793128967285, "global_step": 439895, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.14286208152771, "global_step": 439896, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9735548496246338, "global_step": 439897, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1095540523529053, "global_step": 439898, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0732545852661133, "global_step": 439899, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.195836067199707, "global_step": 439900, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1461780071258545, "global_step": 439901, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.18489146232605, "global_step": 439902, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.119142532348633, "global_step": 439903, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0438075065612793, "global_step": 439904, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.114103317260742, "global_step": 439905, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.104598045349121, "global_step": 439906, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0920310020446777, "global_step": 439907, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.039386749267578, "global_step": 439908, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1098766326904297, "global_step": 439909, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0995850563049316, "global_step": 439910, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0682156085968018, "global_step": 439911, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.9887686967849731, "global_step": 439912, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1724324226379395, "global_step": 439913, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.121020793914795, "global_step": 439914, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.088970422744751, "global_step": 439915, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1202878952026367, "global_step": 439916, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1165356636047363, "global_step": 439917, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1105308532714844, "global_step": 439918, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1202311515808105, "global_step": 439919, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1187095642089844, "global_step": 439920, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0430078506469727, "global_step": 439921, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1342966556549072, "global_step": 439922, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.066371440887451, "global_step": 439923, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.115004539489746, "global_step": 439924, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0936050415039062, "global_step": 439925, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.078713893890381, "global_step": 439926, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1858737468719482, "global_step": 439927, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1188225746154785, "global_step": 439928, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.05330753326416, "global_step": 439929, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.07631778717041, "global_step": 439930, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0769312381744385, "global_step": 439931, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1066040992736816, "global_step": 439932, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.095669746398926, "global_step": 439933, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.102513074874878, "global_step": 439934, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0784668922424316, "global_step": 439935, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.079331874847412, "global_step": 439936, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0889735221862793, "global_step": 439937, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0682120323181152, "global_step": 439938, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0645666122436523, "global_step": 439939, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0978901386260986, "global_step": 439940, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0998687744140625, "global_step": 439941, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.040478229522705, "global_step": 439942, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1280322074890137, "global_step": 439943, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0024807453155518, "global_step": 439944, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1009769439697266, "global_step": 439945, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1135661602020264, "global_step": 439946, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.2070209980010986, "global_step": 439947, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.965247392654419, "global_step": 439948, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1971559524536133, "global_step": 439949, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.088747262954712, "global_step": 439950, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.028470039367676, "global_step": 439951, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.055774211883545, "global_step": 439952, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0144217014312744, "global_step": 439953, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1238627433776855, "global_step": 439954, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.050801992416382, "global_step": 439955, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.077298402786255, "global_step": 439956, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.075894594192505, "global_step": 439957, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.019176721572876, "global_step": 439958, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.056774377822876, "global_step": 439959, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.037001609802246, "global_step": 439960, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.070866584777832, "global_step": 439961, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1737232208251953, "global_step": 439962, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1022651195526123, "global_step": 439963, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1663291454315186, "global_step": 439964, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1312501430511475, "global_step": 439965, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0604560375213623, "global_step": 439966, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.094381093978882, "global_step": 439967, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0555636882781982, "global_step": 439968, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0543570518493652, "global_step": 439969, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.998706340789795, "global_step": 439970, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1298999786376953, "global_step": 439971, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0840399265289307, "global_step": 439972, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1219918727874756, "global_step": 439973, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1671884059906006, "global_step": 439974, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.978405475616455, "global_step": 439975, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.130988597869873, "global_step": 439976, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1650030612945557, "global_step": 439977, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1249217987060547, "global_step": 439978, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.045663833618164, "global_step": 439979, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.043003797531128, "global_step": 439980, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1260690689086914, "global_step": 439981, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0285587310791016, "global_step": 439982, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.063234329223633, "global_step": 439983, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0920231342315674, "global_step": 439984, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1299028396606445, "global_step": 439985, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1361310482025146, "global_step": 439986, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1190335750579834, "global_step": 439987, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1142358779907227, "global_step": 439988, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.2223987579345703, "global_step": 439989, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1369802951812744, "global_step": 439990, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1384470462799072, "global_step": 439991, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0645124912261963, "global_step": 439992, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0798912048339844, "global_step": 439993, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.075533151626587, "global_step": 439994, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1345834732055664, "global_step": 439995, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.099677562713623, "global_step": 439996, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.09139084815979, "global_step": 439997, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.060976505279541, "global_step": 439998, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.136446475982666, "global_step": 439999, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0840957164764404, "global_step": 440000, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0733628273010254, "global_step": 440001, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.010037660598755, "global_step": 440002, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.107307195663452, "global_step": 440003, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1036062240600586, "global_step": 440004, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.111494302749634, "global_step": 440005, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.000899314880371, "global_step": 440006, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.160304069519043, "global_step": 440007, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.068445920944214, "global_step": 440008, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.15664005279541, "global_step": 440009, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1101768016815186, "global_step": 440010, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1091270446777344, "global_step": 440011, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.164271831512451, "global_step": 440012, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.110189199447632, "global_step": 440013, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.013857841491699, "global_step": 440014, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1214168071746826, "global_step": 440015, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0899159908294678, "global_step": 440016, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1243510246276855, "global_step": 440017, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0059330463409424, "global_step": 440018, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1263697147369385, "global_step": 440019, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.128049850463867, "global_step": 440020, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.149383544921875, "global_step": 440021, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.216653347015381, "global_step": 440022, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.046862840652466, "global_step": 440023, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1361451148986816, "global_step": 440024, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1277973651885986, "global_step": 440025, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.100269317626953, "global_step": 440026, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.109727144241333, "global_step": 440027, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0651068687438965, "global_step": 440028, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.118337392807007, "global_step": 440029, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1416497230529785, "global_step": 440030, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.152045726776123, "global_step": 440031, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1003339290618896, "global_step": 440032, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1642637252807617, "global_step": 440033, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1306111812591553, "global_step": 440034, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.081796407699585, "global_step": 440035, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.019559860229492, "global_step": 440036, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1125035285949707, "global_step": 440037, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0116147994995117, "global_step": 440038, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.046417474746704, "global_step": 440039, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0931103229522705, "global_step": 440040, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.095602035522461, "global_step": 440041, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0006237030029297, "global_step": 440042, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0198917388916016, "global_step": 440043, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.174605131149292, "global_step": 440044, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.111332654953003, "global_step": 440045, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.1006946563720703, "global_step": 440046, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0617198944091797, "global_step": 440047, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0935845375061035, "global_step": 440048, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.103440284729004, "global_step": 440049, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0617527961730957, "global_step": 440050, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0880753993988037, "global_step": 440051, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.054839611053467, "global_step": 440052, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.132523536682129, "global_step": 440053, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.149672508239746, "global_step": 440054, "epoch": 803, "lr": 5e-05}
{"train_loss": 1.985926628112793, "global_step": 440055, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.018111228942871, "global_step": 440056, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.0080180168151855, "global_step": 440057, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.078676223754883, "global_step": 440058, "epoch": 803, "lr": 5e-05}
{"train_loss": 2.040907144546509, "global_step": 440059, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.11203670501709, "global_step": 440060, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0776584148406982, "global_step": 440061, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0450618267059326, "global_step": 440062, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.085137367248535, "global_step": 440063, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0948195457458496, "global_step": 440064, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.069636583328247, "global_step": 440065, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.109938621520996, "global_step": 440066, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0631535053253174, "global_step": 440067, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0555529594421387, "global_step": 440068, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.081465244293213, "global_step": 440069, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0260469913482666, "global_step": 440070, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0452940464019775, "global_step": 440071, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0194246768951416, "global_step": 440072, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0512664318084717, "global_step": 440073, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.138045072555542, "global_step": 440074, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.08904767036438, "global_step": 440075, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9705784320831299, "global_step": 440076, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.062757968902588, "global_step": 440077, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9759061336517334, "global_step": 440078, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0675783157348633, "global_step": 440079, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.140134811401367, "global_step": 440080, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.979392409324646, "global_step": 440081, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.136680841445923, "global_step": 440082, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.041367769241333, "global_step": 440083, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.004816770553589, "global_step": 440084, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.041459560394287, "global_step": 440085, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1020562648773193, "global_step": 440086, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0881621837615967, "global_step": 440087, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.029905080795288, "global_step": 440088, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.065354585647583, "global_step": 440089, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.079554319381714, "global_step": 440090, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.018221855163574, "global_step": 440091, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.031162738800049, "global_step": 440092, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.044804573059082, "global_step": 440093, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9893367290496826, "global_step": 440094, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0059654712677, "global_step": 440095, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0592591762542725, "global_step": 440096, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.091578722000122, "global_step": 440097, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9663591384887695, "global_step": 440098, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0087015628814697, "global_step": 440099, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0685768127441406, "global_step": 440100, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.06831693649292, "global_step": 440101, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1641135215759277, "global_step": 440102, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.062333822250366, "global_step": 440103, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0234451293945312, "global_step": 440104, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1203038692474365, "global_step": 440105, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1013247966766357, "global_step": 440106, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0423977375030518, "global_step": 440107, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1291403770446777, "global_step": 440108, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0563251972198486, "global_step": 440109, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0238938331604004, "global_step": 440110, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0004968643188477, "global_step": 440111, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0003504753112793, "global_step": 440112, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0796496868133545, "global_step": 440113, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9663686752319336, "global_step": 440114, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1295647621154785, "global_step": 440115, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.03174090385437, "global_step": 440116, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0442540645599365, "global_step": 440117, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.042653799057007, "global_step": 440118, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0958194732666016, "global_step": 440119, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0822882652282715, "global_step": 440120, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0914440155029297, "global_step": 440121, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0822415351867676, "global_step": 440122, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.031264305114746, "global_step": 440123, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0984671115875244, "global_step": 440124, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.069732189178467, "global_step": 440125, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.120288372039795, "global_step": 440126, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1154212951660156, "global_step": 440127, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9874593019485474, "global_step": 440128, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0120110511779785, "global_step": 440129, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1439671516418457, "global_step": 440130, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1007072925567627, "global_step": 440131, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.009232759475708, "global_step": 440132, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0517587661743164, "global_step": 440133, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0195624828338623, "global_step": 440134, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1282870769500732, "global_step": 440135, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.050647258758545, "global_step": 440136, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.076660394668579, "global_step": 440137, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0033576488494873, "global_step": 440138, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.067288875579834, "global_step": 440139, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.031545639038086, "global_step": 440140, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0807933807373047, "global_step": 440141, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0709068775177, "global_step": 440142, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.143557071685791, "global_step": 440143, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0853991508483887, "global_step": 440144, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.048007011413574, "global_step": 440145, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1140847206115723, "global_step": 440146, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0555896759033203, "global_step": 440147, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.083392858505249, "global_step": 440148, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.019479990005493, "global_step": 440149, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.104738235473633, "global_step": 440150, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.060817241668701, "global_step": 440151, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9659076929092407, "global_step": 440152, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9717766046524048, "global_step": 440153, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.145692825317383, "global_step": 440154, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.076601505279541, "global_step": 440155, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1487178802490234, "global_step": 440156, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0922293663024902, "global_step": 440157, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.997633695602417, "global_step": 440158, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.168463706970215, "global_step": 440159, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.072230100631714, "global_step": 440160, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0734951496124268, "global_step": 440161, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.156888246536255, "global_step": 440162, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0836102962493896, "global_step": 440163, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.090717077255249, "global_step": 440164, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.026214599609375, "global_step": 440165, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.005537271499634, "global_step": 440166, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0921361446380615, "global_step": 440167, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0746407508850098, "global_step": 440168, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0997231006622314, "global_step": 440169, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1222429275512695, "global_step": 440170, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.047750234603882, "global_step": 440171, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0477027893066406, "global_step": 440172, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.057321548461914, "global_step": 440173, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0905208587646484, "global_step": 440174, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.021399974822998, "global_step": 440175, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.074753522872925, "global_step": 440176, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0612454414367676, "global_step": 440177, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9659868478775024, "global_step": 440178, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0627715587615967, "global_step": 440179, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9996328353881836, "global_step": 440180, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9706088304519653, "global_step": 440181, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1070425510406494, "global_step": 440182, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1092536449432373, "global_step": 440183, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.062318801879883, "global_step": 440184, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0454025268554688, "global_step": 440185, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0107743740081787, "global_step": 440186, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.024259567260742, "global_step": 440187, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.2233002185821533, "global_step": 440188, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.104433298110962, "global_step": 440189, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.085236072540283, "global_step": 440190, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0919530391693115, "global_step": 440191, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0657339096069336, "global_step": 440192, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0748767852783203, "global_step": 440193, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1218481063842773, "global_step": 440194, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.054560899734497, "global_step": 440195, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1118874549865723, "global_step": 440196, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0190658569335938, "global_step": 440197, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.111318826675415, "global_step": 440198, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0755538940429688, "global_step": 440199, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.120253562927246, "global_step": 440200, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1034281253814697, "global_step": 440201, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1138553619384766, "global_step": 440202, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.064906358718872, "global_step": 440203, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0251245498657227, "global_step": 440204, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9630346298217773, "global_step": 440205, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0104291439056396, "global_step": 440206, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0700533390045166, "global_step": 440207, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1296727657318115, "global_step": 440208, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0551600456237793, "global_step": 440209, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0393455028533936, "global_step": 440210, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0983729362487793, "global_step": 440211, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0411648750305176, "global_step": 440212, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1370065212249756, "global_step": 440213, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0986135005950928, "global_step": 440214, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9849121570587158, "global_step": 440215, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0519120693206787, "global_step": 440216, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.07873272895813, "global_step": 440217, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.008439064025879, "global_step": 440218, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0907649993896484, "global_step": 440219, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9998124837875366, "global_step": 440220, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9837102890014648, "global_step": 440221, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.096193552017212, "global_step": 440222, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.077580690383911, "global_step": 440223, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0625312328338623, "global_step": 440224, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0184743404388428, "global_step": 440225, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0422654151916504, "global_step": 440226, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.993473768234253, "global_step": 440227, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.010702133178711, "global_step": 440228, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.077768325805664, "global_step": 440229, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.044292449951172, "global_step": 440230, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0443499088287354, "global_step": 440231, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.053882598876953, "global_step": 440232, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1031742095947266, "global_step": 440233, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0528481006622314, "global_step": 440234, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0468738079071045, "global_step": 440235, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9820318222045898, "global_step": 440236, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0981743335723877, "global_step": 440237, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0501821041107178, "global_step": 440238, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1197221279144287, "global_step": 440239, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.950888752937317, "global_step": 440240, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0045883655548096, "global_step": 440241, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.067835569381714, "global_step": 440242, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.101141929626465, "global_step": 440243, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.055584192276001, "global_step": 440244, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0909054279327393, "global_step": 440245, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0855627059936523, "global_step": 440246, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0531418323516846, "global_step": 440247, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.105421304702759, "global_step": 440248, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0789601802825928, "global_step": 440249, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1715307235717773, "global_step": 440250, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0996205806732178, "global_step": 440251, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0283241271972656, "global_step": 440252, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.064450740814209, "global_step": 440253, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.065412759780884, "global_step": 440254, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.08463454246521, "global_step": 440255, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0458614826202393, "global_step": 440256, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9828490018844604, "global_step": 440257, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1326189041137695, "global_step": 440258, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.123244524002075, "global_step": 440259, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1074886322021484, "global_step": 440260, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.111316204071045, "global_step": 440261, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0150365829467773, "global_step": 440262, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1506528854370117, "global_step": 440263, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1777710914611816, "global_step": 440264, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.090934991836548, "global_step": 440265, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0975091457366943, "global_step": 440266, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.144428014755249, "global_step": 440267, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0292177200317383, "global_step": 440268, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.123297691345215, "global_step": 440269, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.099252223968506, "global_step": 440270, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0426151752471924, "global_step": 440271, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0795207023620605, "global_step": 440272, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.030243396759033, "global_step": 440273, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0999796390533447, "global_step": 440274, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.144148826599121, "global_step": 440275, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.043818473815918, "global_step": 440276, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0693929195404053, "global_step": 440277, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0155646800994873, "global_step": 440278, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1266071796417236, "global_step": 440279, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1284143924713135, "global_step": 440280, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.086486339569092, "global_step": 440281, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1506781578063965, "global_step": 440282, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0861549377441406, "global_step": 440283, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.111966609954834, "global_step": 440284, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.188844919204712, "global_step": 440285, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.048708915710449, "global_step": 440286, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.069519519805908, "global_step": 440287, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0579679012298584, "global_step": 440288, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.062713861465454, "global_step": 440289, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.109954595565796, "global_step": 440290, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0403385162353516, "global_step": 440291, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0813114643096924, "global_step": 440292, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0999908447265625, "global_step": 440293, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0792226791381836, "global_step": 440294, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0693840980529785, "global_step": 440295, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.099109172821045, "global_step": 440296, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1419193744659424, "global_step": 440297, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0521912574768066, "global_step": 440298, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.119948625564575, "global_step": 440299, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0404715538024902, "global_step": 440300, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0211830139160156, "global_step": 440301, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.07371187210083, "global_step": 440302, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0131185054779053, "global_step": 440303, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.10668683052063, "global_step": 440304, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0631816387176514, "global_step": 440305, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0711259841918945, "global_step": 440306, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.072736978530884, "global_step": 440307, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.024491786956787, "global_step": 440308, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1323647499084473, "global_step": 440309, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.055258274078369, "global_step": 440310, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.125504493713379, "global_step": 440311, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.034916639328003, "global_step": 440312, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0851335525512695, "global_step": 440313, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1640512943267822, "global_step": 440314, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.01117205619812, "global_step": 440315, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0570602416992188, "global_step": 440316, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0956993103027344, "global_step": 440317, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0839827060699463, "global_step": 440318, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.002448081970215, "global_step": 440319, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0846731662750244, "global_step": 440320, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.057600736618042, "global_step": 440321, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1372299194335938, "global_step": 440322, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.042264699935913, "global_step": 440323, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.120307445526123, "global_step": 440324, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0071933269500732, "global_step": 440325, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0446436405181885, "global_step": 440326, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1101739406585693, "global_step": 440327, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.053457260131836, "global_step": 440328, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.014742612838745, "global_step": 440329, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9895820617675781, "global_step": 440330, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.989588975906372, "global_step": 440331, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.065828323364258, "global_step": 440332, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.074462652206421, "global_step": 440333, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.033888101577759, "global_step": 440334, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.05074405670166, "global_step": 440335, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0358219146728516, "global_step": 440336, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0366034507751465, "global_step": 440337, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1384124755859375, "global_step": 440338, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0244758129119873, "global_step": 440339, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9509129524230957, "global_step": 440340, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1434855461120605, "global_step": 440341, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.072801351547241, "global_step": 440342, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.074183225631714, "global_step": 440343, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0453810691833496, "global_step": 440344, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0953140258789062, "global_step": 440345, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.077808141708374, "global_step": 440346, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1059930324554443, "global_step": 440347, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.09775710105896, "global_step": 440348, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.142167568206787, "global_step": 440349, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1050915718078613, "global_step": 440350, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.06508469581604, "global_step": 440351, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0932421684265137, "global_step": 440352, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0504958629608154, "global_step": 440353, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9855362176895142, "global_step": 440354, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1488990783691406, "global_step": 440355, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1630866527557373, "global_step": 440356, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.021010637283325, "global_step": 440357, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.102022647857666, "global_step": 440358, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0089921951293945, "global_step": 440359, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1116268634796143, "global_step": 440360, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.047395944595337, "global_step": 440361, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.097604990005493, "global_step": 440362, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1632916927337646, "global_step": 440363, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9904382228851318, "global_step": 440364, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1169321537017822, "global_step": 440365, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0881757736206055, "global_step": 440366, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.027200222015381, "global_step": 440367, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.081217050552368, "global_step": 440368, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0115392208099365, "global_step": 440369, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0488975048065186, "global_step": 440370, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.118925094604492, "global_step": 440371, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1060831546783447, "global_step": 440372, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.098750352859497, "global_step": 440373, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1101913452148438, "global_step": 440374, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.075517416000366, "global_step": 440375, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0808615684509277, "global_step": 440376, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.062854051589966, "global_step": 440377, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.092729330062866, "global_step": 440378, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0316872596740723, "global_step": 440379, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.094485282897949, "global_step": 440380, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1540606021881104, "global_step": 440381, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.050287961959839, "global_step": 440382, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0999605655670166, "global_step": 440383, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0069165229797363, "global_step": 440384, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0243418216705322, "global_step": 440385, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.005279064178467, "global_step": 440386, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.050229787826538, "global_step": 440387, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.017941474914551, "global_step": 440388, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0196380615234375, "global_step": 440389, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0181469917297363, "global_step": 440390, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.091993570327759, "global_step": 440391, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0556044578552246, "global_step": 440392, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1239686012268066, "global_step": 440393, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1528961658477783, "global_step": 440394, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0658044815063477, "global_step": 440395, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1565191745758057, "global_step": 440396, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0792171955108643, "global_step": 440397, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1283228397369385, "global_step": 440398, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.144876480102539, "global_step": 440399, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.052288293838501, "global_step": 440400, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0941829681396484, "global_step": 440401, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1197452545166016, "global_step": 440402, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1495277881622314, "global_step": 440403, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0650713443756104, "global_step": 440404, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0391485691070557, "global_step": 440405, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0449330806732178, "global_step": 440406, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0606207847595215, "global_step": 440407, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.063324451446533, "global_step": 440408, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9941496849060059, "global_step": 440409, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0826730728149414, "global_step": 440410, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.148373603820801, "global_step": 440411, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.043574810028076, "global_step": 440412, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0463826656341553, "global_step": 440413, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1004855632781982, "global_step": 440414, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0273115634918213, "global_step": 440415, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0663516521453857, "global_step": 440416, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0347540378570557, "global_step": 440417, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.110886335372925, "global_step": 440418, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0849173069000244, "global_step": 440419, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1344997882843018, "global_step": 440420, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.096202850341797, "global_step": 440421, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0640766620635986, "global_step": 440422, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.125678539276123, "global_step": 440423, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.062459707260132, "global_step": 440424, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.127201795578003, "global_step": 440425, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.052267074584961, "global_step": 440426, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.094428539276123, "global_step": 440427, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.044320583343506, "global_step": 440428, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0753097534179688, "global_step": 440429, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0660219192504883, "global_step": 440430, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1003217697143555, "global_step": 440431, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0449206829071045, "global_step": 440432, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1279146671295166, "global_step": 440433, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.17181396484375, "global_step": 440434, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0365450382232666, "global_step": 440435, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.117926836013794, "global_step": 440436, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.086927652359009, "global_step": 440437, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.111863374710083, "global_step": 440438, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0290725231170654, "global_step": 440439, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1089651584625244, "global_step": 440440, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0862715244293213, "global_step": 440441, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.036318302154541, "global_step": 440442, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1804981231689453, "global_step": 440443, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.068150281906128, "global_step": 440444, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0640506744384766, "global_step": 440445, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1226181983947754, "global_step": 440446, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0942304134368896, "global_step": 440447, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.099137544631958, "global_step": 440448, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9677090644836426, "global_step": 440449, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.056173324584961, "global_step": 440450, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.009779453277588, "global_step": 440451, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0799148082733154, "global_step": 440452, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.104069471359253, "global_step": 440453, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0156781673431396, "global_step": 440454, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.106727361679077, "global_step": 440455, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9857171773910522, "global_step": 440456, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1675381660461426, "global_step": 440457, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.111711025238037, "global_step": 440458, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0961101055145264, "global_step": 440459, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1314523220062256, "global_step": 440460, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1006181240081787, "global_step": 440461, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1311914920806885, "global_step": 440462, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.148038148880005, "global_step": 440463, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.014751672744751, "global_step": 440464, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.096752405166626, "global_step": 440465, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.031862258911133, "global_step": 440466, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9655437469482422, "global_step": 440467, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.055901050567627, "global_step": 440468, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.083076238632202, "global_step": 440469, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0942347049713135, "global_step": 440470, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.998447060585022, "global_step": 440471, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.021108388900757, "global_step": 440472, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.08273983001709, "global_step": 440473, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.137803792953491, "global_step": 440474, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1417853832244873, "global_step": 440475, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0149333477020264, "global_step": 440476, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1598286628723145, "global_step": 440477, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0999739170074463, "global_step": 440478, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.078146457672119, "global_step": 440479, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.116100549697876, "global_step": 440480, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0527024269104004, "global_step": 440481, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.045555830001831, "global_step": 440482, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0427660942077637, "global_step": 440483, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0928235054016113, "global_step": 440484, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.060101270675659, "global_step": 440485, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.155596971511841, "global_step": 440486, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1337854862213135, "global_step": 440487, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.008704423904419, "global_step": 440488, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.016737699508667, "global_step": 440489, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0893807411193848, "global_step": 440490, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9902492761611938, "global_step": 440491, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.152139663696289, "global_step": 440492, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.119966506958008, "global_step": 440493, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.042510747909546, "global_step": 440494, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.075604200363159, "global_step": 440495, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.058353900909424, "global_step": 440496, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.072333574295044, "global_step": 440497, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0539023876190186, "global_step": 440498, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0075883865356445, "global_step": 440499, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0260283946990967, "global_step": 440500, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0473897457122803, "global_step": 440501, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1422135829925537, "global_step": 440502, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.195552110671997, "global_step": 440503, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.136767625808716, "global_step": 440504, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1729533672332764, "global_step": 440505, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.131527900695801, "global_step": 440506, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.173128843307495, "global_step": 440507, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.052403450012207, "global_step": 440508, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0224342346191406, "global_step": 440509, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0999538898468018, "global_step": 440510, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1457974910736084, "global_step": 440511, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9976468086242676, "global_step": 440512, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.039907217025757, "global_step": 440513, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.050673246383667, "global_step": 440514, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.076664447784424, "global_step": 440515, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9995938539505005, "global_step": 440516, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0152034759521484, "global_step": 440517, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9847214221954346, "global_step": 440518, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0762734413146973, "global_step": 440519, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1102089881896973, "global_step": 440520, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1320691108703613, "global_step": 440521, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0725862979888916, "global_step": 440522, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0234925746917725, "global_step": 440523, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0987231731414795, "global_step": 440524, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.039060592651367, "global_step": 440525, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.145212411880493, "global_step": 440526, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0931341648101807, "global_step": 440527, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.100235939025879, "global_step": 440528, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0620670318603516, "global_step": 440529, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1285500526428223, "global_step": 440530, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0415475368499756, "global_step": 440531, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.03997540473938, "global_step": 440532, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0361328125, "global_step": 440533, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0286178588867188, "global_step": 440534, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.013352155685425, "global_step": 440535, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.060894727706909, "global_step": 440536, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.119171619415283, "global_step": 440537, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1299731731414795, "global_step": 440538, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.037198543548584, "global_step": 440539, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1021928787231445, "global_step": 440540, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.059105396270752, "global_step": 440541, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0449020862579346, "global_step": 440542, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0413591861724854, "global_step": 440543, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0063016414642334, "global_step": 440544, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.086078405380249, "global_step": 440545, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0080394744873047, "global_step": 440546, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.070650100708008, "global_step": 440547, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1039950847625732, "global_step": 440548, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.115480661392212, "global_step": 440549, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1053340435028076, "global_step": 440550, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.087893009185791, "global_step": 440551, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9857356548309326, "global_step": 440552, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1099660396575928, "global_step": 440553, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1647210121154785, "global_step": 440554, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.091937780380249, "global_step": 440555, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.077840566635132, "global_step": 440556, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.04504656791687, "global_step": 440557, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0588717460632324, "global_step": 440558, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0991668701171875, "global_step": 440559, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1254096031188965, "global_step": 440560, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.032574415206909, "global_step": 440561, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.128689765930176, "global_step": 440562, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.057854652404785, "global_step": 440563, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0997109413146973, "global_step": 440564, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.065025806427002, "global_step": 440565, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.062490701675415, "global_step": 440566, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0914037227630615, "global_step": 440567, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0296356678009033, "global_step": 440568, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0310986042022705, "global_step": 440569, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0279626846313477, "global_step": 440570, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1332244873046875, "global_step": 440571, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0756824016571045, "global_step": 440572, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.053175687789917, "global_step": 440573, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.098458766937256, "global_step": 440574, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0252654552459717, "global_step": 440575, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0782792568206787, "global_step": 440576, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.076791524887085, "global_step": 440577, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.123913288116455, "global_step": 440578, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.108058452606201, "global_step": 440579, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.094080686569214, "global_step": 440580, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1792690753936768, "global_step": 440581, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0746192932128906, "global_step": 440582, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0728540420532227, "global_step": 440583, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.139714002609253, "global_step": 440584, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0621302127838135, "global_step": 440585, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.013263702392578, "global_step": 440586, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0713295936584473, "global_step": 440587, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0057010650634766, "global_step": 440588, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0247440338134766, "global_step": 440589, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1271026134490967, "global_step": 440590, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.111639976501465, "global_step": 440591, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1536617279052734, "global_step": 440592, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0966849327087402, "global_step": 440593, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0575358867645264, "global_step": 440594, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0069775581359863, "global_step": 440595, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.102217197418213, "global_step": 440596, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.06703519821167, "global_step": 440597, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.052584171295166, "global_step": 440598, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1638760566711426, "global_step": 440599, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.111565113067627, "global_step": 440600, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.119964122772217, "global_step": 440601, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.14465594291687, "global_step": 440602, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1065499782562256, "global_step": 440603, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0797886848449707, "global_step": 440604, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1003952026367188, "global_step": 440605, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.086928129196167, "global_step": 440606, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.098360538482666, "global_step": 440607, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0361080169677734, "global_step": 440608, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.08819842338562, "global_step": 440609, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0315937995910645, "global_step": 440610, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.103851795196533, "global_step": 440611, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0133731365203857, "global_step": 440612, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0264780521392822, "global_step": 440613, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0714550018310547, "global_step": 440614, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.116730213165283, "global_step": 440615, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0890259742736816, "global_step": 440616, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0748379230499268, "global_step": 440617, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0967981815338135, "global_step": 440618, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0483202934265137, "global_step": 440619, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1812667846679688, "global_step": 440620, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0813026428222656, "global_step": 440621, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0908896923065186, "global_step": 440622, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.143286943435669, "global_step": 440623, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0076053142547607, "global_step": 440624, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.053800344467163, "global_step": 440625, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.119143486022949, "global_step": 440626, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1107490062713623, "global_step": 440627, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0324413776397705, "global_step": 440628, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0703718662261963, "global_step": 440629, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.12276029586792, "global_step": 440630, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.051820993423462, "global_step": 440631, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1039483547210693, "global_step": 440632, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.082059860229492, "global_step": 440633, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.070589780807495, "global_step": 440634, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1070592403411865, "global_step": 440635, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0832574367523193, "global_step": 440636, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0325613021850586, "global_step": 440637, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.116633415222168, "global_step": 440638, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0409445762634277, "global_step": 440639, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0838136672973633, "global_step": 440640, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.133040189743042, "global_step": 440641, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0284061431884766, "global_step": 440642, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9944109916687012, "global_step": 440643, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.093255043029785, "global_step": 440644, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.111753225326538, "global_step": 440645, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1659069061279297, "global_step": 440646, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.025033712387085, "global_step": 440647, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.166486978530884, "global_step": 440648, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0316295623779297, "global_step": 440649, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1443796157836914, "global_step": 440650, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.102569818496704, "global_step": 440651, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.999943733215332, "global_step": 440652, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0617403984069824, "global_step": 440653, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0142576694488525, "global_step": 440654, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.052258253097534, "global_step": 440655, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.10115647315979, "global_step": 440656, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1223537921905518, "global_step": 440657, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0623512268066406, "global_step": 440658, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0407073497772217, "global_step": 440659, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.149984359741211, "global_step": 440660, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0328338146209717, "global_step": 440661, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0381152629852295, "global_step": 440662, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.993236780166626, "global_step": 440663, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.080554962158203, "global_step": 440664, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.058243989944458, "global_step": 440665, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1239020824432373, "global_step": 440666, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0420145988464355, "global_step": 440667, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.059488534927368, "global_step": 440668, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.051699638366699, "global_step": 440669, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1682968139648438, "global_step": 440670, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.055769681930542, "global_step": 440671, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.092883825302124, "global_step": 440672, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.061602830886841, "global_step": 440673, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.055938959121704, "global_step": 440674, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0135011672973633, "global_step": 440675, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1211187839508057, "global_step": 440676, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0986666679382324, "global_step": 440677, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.006010055541992, "global_step": 440678, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0385468006134033, "global_step": 440679, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.092564821243286, "global_step": 440680, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.121809244155884, "global_step": 440681, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0460987091064453, "global_step": 440682, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0402848720550537, "global_step": 440683, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.129060983657837, "global_step": 440684, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.106503486633301, "global_step": 440685, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0403013229370117, "global_step": 440686, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0755577087402344, "global_step": 440687, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0320029258728027, "global_step": 440688, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.129396677017212, "global_step": 440689, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.091712713241577, "global_step": 440690, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.061648368835449, "global_step": 440691, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1857051849365234, "global_step": 440692, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.101036310195923, "global_step": 440693, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.082017421722412, "global_step": 440694, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.027674913406372, "global_step": 440695, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0227673053741455, "global_step": 440696, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.108304738998413, "global_step": 440697, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0034327507019043, "global_step": 440698, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.084836483001709, "global_step": 440699, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.124443292617798, "global_step": 440700, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.15266752243042, "global_step": 440701, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.082575798034668, "global_step": 440702, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0123419761657715, "global_step": 440703, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0162439346313477, "global_step": 440704, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1195082664489746, "global_step": 440705, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0459554195404053, "global_step": 440706, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0796093940734863, "global_step": 440707, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.089094400405884, "global_step": 440708, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.055762529373169, "global_step": 440709, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0966293811798096, "global_step": 440710, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1253092288970947, "global_step": 440711, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1089444160461426, "global_step": 440712, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0171384811401367, "global_step": 440713, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.056817054748535, "global_step": 440714, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0190365314483643, "global_step": 440715, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0729024410247803, "global_step": 440716, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.170013427734375, "global_step": 440717, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.078232526779175, "global_step": 440718, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0414607524871826, "global_step": 440719, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.117159605026245, "global_step": 440720, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1601006984710693, "global_step": 440721, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.15482497215271, "global_step": 440722, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0685501098632812, "global_step": 440723, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1392102241516113, "global_step": 440724, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0184574127197266, "global_step": 440725, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.996730923652649, "global_step": 440726, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.98799729347229, "global_step": 440727, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.087029218673706, "global_step": 440728, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.07539439201355, "global_step": 440729, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0760393142700195, "global_step": 440730, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0098788738250732, "global_step": 440731, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.101217746734619, "global_step": 440732, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.01699161529541, "global_step": 440733, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1894874572753906, "global_step": 440734, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.100616693496704, "global_step": 440735, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.067842721939087, "global_step": 440736, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.191340684890747, "global_step": 440737, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0744590759277344, "global_step": 440738, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1839699745178223, "global_step": 440739, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1894683837890625, "global_step": 440740, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1246988773345947, "global_step": 440741, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.168461799621582, "global_step": 440742, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1166391372680664, "global_step": 440743, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.151489734649658, "global_step": 440744, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0913989543914795, "global_step": 440745, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0505146980285645, "global_step": 440746, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.085522174835205, "global_step": 440747, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0571539402008057, "global_step": 440748, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1247029304504395, "global_step": 440749, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0306811332702637, "global_step": 440750, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0147948265075684, "global_step": 440751, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.039788246154785, "global_step": 440752, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0572023391723633, "global_step": 440753, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.053720712661743, "global_step": 440754, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9937626123428345, "global_step": 440755, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1141581535339355, "global_step": 440756, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0292630195617676, "global_step": 440757, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0426056385040283, "global_step": 440758, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0978991985321045, "global_step": 440759, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0156970024108887, "global_step": 440760, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0766408443450928, "global_step": 440761, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.083645820617676, "global_step": 440762, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0195372104644775, "global_step": 440763, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1802985668182373, "global_step": 440764, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1041178703308105, "global_step": 440765, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.11087965965271, "global_step": 440766, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9991637468338013, "global_step": 440767, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.032677412033081, "global_step": 440768, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1146903038024902, "global_step": 440769, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0607428550720215, "global_step": 440770, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0767080783843994, "global_step": 440771, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0679538249969482, "global_step": 440772, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0649170875549316, "global_step": 440773, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1509056091308594, "global_step": 440774, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1365597248077393, "global_step": 440775, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.008241653442383, "global_step": 440776, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.046407699584961, "global_step": 440777, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0911755561828613, "global_step": 440778, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1045937538146973, "global_step": 440779, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1260294914245605, "global_step": 440780, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.029386520385742, "global_step": 440781, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1213855743408203, "global_step": 440782, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.115367889404297, "global_step": 440783, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0909154415130615, "global_step": 440784, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.095782518386841, "global_step": 440785, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0801033973693848, "global_step": 440786, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.144700050354004, "global_step": 440787, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.094345808029175, "global_step": 440788, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.142000436782837, "global_step": 440789, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1169986724853516, "global_step": 440790, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0983216762542725, "global_step": 440791, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.088109254837036, "global_step": 440792, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0072481632232666, "global_step": 440793, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0577476024627686, "global_step": 440794, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1514999866485596, "global_step": 440795, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0859017372131348, "global_step": 440796, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.06660795211792, "global_step": 440797, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0722010135650635, "global_step": 440798, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0480968952178955, "global_step": 440799, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1038224697113037, "global_step": 440800, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0575199127197266, "global_step": 440801, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.105164051055908, "global_step": 440802, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1022467613220215, "global_step": 440803, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1568071842193604, "global_step": 440804, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0945816040039062, "global_step": 440805, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.2022953033447266, "global_step": 440806, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0308570861816406, "global_step": 440807, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0370445251464844, "global_step": 440808, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0847368240356445, "global_step": 440809, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.13216233253479, "global_step": 440810, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.140862464904785, "global_step": 440811, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.032423973083496, "global_step": 440812, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0781302452087402, "global_step": 440813, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1369895935058594, "global_step": 440814, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.074462890625, "global_step": 440815, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.166965961456299, "global_step": 440816, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0397582054138184, "global_step": 440817, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.045961856842041, "global_step": 440818, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.048558473587036, "global_step": 440819, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.001075506210327, "global_step": 440820, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0601789951324463, "global_step": 440821, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0607335567474365, "global_step": 440822, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0116212368011475, "global_step": 440823, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0779483318328857, "global_step": 440824, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.072840452194214, "global_step": 440825, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.007984161376953, "global_step": 440826, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1559555530548096, "global_step": 440827, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.210484027862549, "global_step": 440828, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.034536123275757, "global_step": 440829, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.069157600402832, "global_step": 440830, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.048945188522339, "global_step": 440831, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0272514820098877, "global_step": 440832, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.101796865463257, "global_step": 440833, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0959644317626953, "global_step": 440834, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9866224527359009, "global_step": 440835, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0769529342651367, "global_step": 440836, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.079206705093384, "global_step": 440837, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.13198184967041, "global_step": 440838, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0357742309570312, "global_step": 440839, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1289010047912598, "global_step": 440840, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1572368144989014, "global_step": 440841, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0384624004364014, "global_step": 440842, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.060551881790161, "global_step": 440843, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.041990280151367, "global_step": 440844, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0132699012756348, "global_step": 440845, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1483864784240723, "global_step": 440846, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.2103235721588135, "global_step": 440847, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.095503091812134, "global_step": 440848, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0461297035217285, "global_step": 440849, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0834193229675293, "global_step": 440850, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0356462001800537, "global_step": 440851, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0127878189086914, "global_step": 440852, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.096522569656372, "global_step": 440853, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1042561531066895, "global_step": 440854, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.073523759841919, "global_step": 440855, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0384521484375, "global_step": 440856, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.04390287399292, "global_step": 440857, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1318750381469727, "global_step": 440858, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.024768114089966, "global_step": 440859, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9945262670516968, "global_step": 440860, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1205523014068604, "global_step": 440861, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.072176933288574, "global_step": 440862, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0067625045776367, "global_step": 440863, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.135166645050049, "global_step": 440864, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.172498941421509, "global_step": 440865, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.085620164871216, "global_step": 440866, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1937930583953857, "global_step": 440867, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.083592653274536, "global_step": 440868, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0958776473999023, "global_step": 440869, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0183191299438477, "global_step": 440870, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.158242702484131, "global_step": 440871, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.115224599838257, "global_step": 440872, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.101161479949951, "global_step": 440873, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1306378841400146, "global_step": 440874, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1086018085479736, "global_step": 440875, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0843992233276367, "global_step": 440876, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.114436149597168, "global_step": 440877, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0550689697265625, "global_step": 440878, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.10028338432312, "global_step": 440879, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0792670249938965, "global_step": 440880, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.048023223876953, "global_step": 440881, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.087674856185913, "global_step": 440882, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.077075481414795, "global_step": 440883, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0857579708099365, "global_step": 440884, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1310458183288574, "global_step": 440885, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1434292793273926, "global_step": 440886, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.07973575592041, "global_step": 440887, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.166757106781006, "global_step": 440888, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0272557735443115, "global_step": 440889, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0851333141326904, "global_step": 440890, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.058929681777954, "global_step": 440891, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0616962909698486, "global_step": 440892, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1148881912231445, "global_step": 440893, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0224978923797607, "global_step": 440894, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0612189769744873, "global_step": 440895, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.055375576019287, "global_step": 440896, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.019089460372925, "global_step": 440897, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0941109657287598, "global_step": 440898, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0109007358551025, "global_step": 440899, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.119558572769165, "global_step": 440900, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1055922508239746, "global_step": 440901, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0587847232818604, "global_step": 440902, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0900986194610596, "global_step": 440903, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.057325601577759, "global_step": 440904, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.084907293319702, "global_step": 440905, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.152205467224121, "global_step": 440906, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.107424020767212, "global_step": 440907, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.069969415664673, "global_step": 440908, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1059298515319824, "global_step": 440909, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1355977058410645, "global_step": 440910, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.101423501968384, "global_step": 440911, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.059506416320801, "global_step": 440912, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.041710615158081, "global_step": 440913, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.093221664428711, "global_step": 440914, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0419089794158936, "global_step": 440915, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0254249572753906, "global_step": 440916, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1327123641967773, "global_step": 440917, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1510531902313232, "global_step": 440918, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1571431159973145, "global_step": 440919, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.049790620803833, "global_step": 440920, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0488409996032715, "global_step": 440921, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9414294958114624, "global_step": 440922, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.093510150909424, "global_step": 440923, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.000136137008667, "global_step": 440924, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1122777462005615, "global_step": 440925, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0754153728485107, "global_step": 440926, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.094189167022705, "global_step": 440927, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0758283138275146, "global_step": 440928, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0726025104522705, "global_step": 440929, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0601611137390137, "global_step": 440930, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1309502124786377, "global_step": 440931, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0665555000305176, "global_step": 440932, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.052628993988037, "global_step": 440933, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9741413593292236, "global_step": 440934, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.053953170776367, "global_step": 440935, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.030188798904419, "global_step": 440936, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0017192363739014, "global_step": 440937, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0733957290649414, "global_step": 440938, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0262880325317383, "global_step": 440939, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0316102504730225, "global_step": 440940, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0867059230804443, "global_step": 440941, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.045164108276367, "global_step": 440942, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0728683471679688, "global_step": 440943, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0217249393463135, "global_step": 440944, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.082512378692627, "global_step": 440945, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.106898784637451, "global_step": 440946, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0912046432495117, "global_step": 440947, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1359996795654297, "global_step": 440948, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.040221691131592, "global_step": 440949, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1232786178588867, "global_step": 440950, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0921785831451416, "global_step": 440951, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0613648891448975, "global_step": 440952, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1166739463806152, "global_step": 440953, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1019604206085205, "global_step": 440954, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9619059562683105, "global_step": 440955, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0590906143188477, "global_step": 440956, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0781054496765137, "global_step": 440957, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.106994867324829, "global_step": 440958, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.080406904220581, "global_step": 440959, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.080693006515503, "global_step": 440960, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1350486278533936, "global_step": 440961, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1375999450683594, "global_step": 440962, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1376664638519287, "global_step": 440963, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1129953861236572, "global_step": 440964, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0750696659088135, "global_step": 440965, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.094545364379883, "global_step": 440966, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.015864849090576, "global_step": 440967, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.06453275680542, "global_step": 440968, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.102933645248413, "global_step": 440969, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0643293857574463, "global_step": 440970, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9576737880706787, "global_step": 440971, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.041106939315796, "global_step": 440972, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1734471321105957, "global_step": 440973, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.112309217453003, "global_step": 440974, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0368692874908447, "global_step": 440975, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1494109630584717, "global_step": 440976, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1229288578033447, "global_step": 440977, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.079796314239502, "global_step": 440978, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.151474714279175, "global_step": 440979, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0122275352478027, "global_step": 440980, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0219156742095947, "global_step": 440981, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.096391201019287, "global_step": 440982, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1012518405914307, "global_step": 440983, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.047398805618286, "global_step": 440984, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0910749435424805, "global_step": 440985, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.2088959217071533, "global_step": 440986, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0942234992980957, "global_step": 440987, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0485963821411133, "global_step": 440988, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0773839950561523, "global_step": 440989, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0654163360595703, "global_step": 440990, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.073078155517578, "global_step": 440991, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.068155288696289, "global_step": 440992, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.187509775161743, "global_step": 440993, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0968408584594727, "global_step": 440994, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1395349502563477, "global_step": 440995, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.182919979095459, "global_step": 440996, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.09999418258667, "global_step": 440997, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0878190994262695, "global_step": 440998, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1489298343658447, "global_step": 440999, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0908477306365967, "global_step": 441000, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0305564403533936, "global_step": 441001, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0456831455230713, "global_step": 441002, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0928211212158203, "global_step": 441003, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.11334228515625, "global_step": 441004, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.046144962310791, "global_step": 441005, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0363595485687256, "global_step": 441006, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0889735221862793, "global_step": 441007, "epoch": 804, "lr": 5e-05}
{"train_loss": 1.9730918407440186, "global_step": 441008, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.023507595062256, "global_step": 441009, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.058690071105957, "global_step": 441010, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1153066158294678, "global_step": 441011, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.135169267654419, "global_step": 441012, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0567264556884766, "global_step": 441013, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0532891750335693, "global_step": 441014, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.106982707977295, "global_step": 441015, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0555036067962646, "global_step": 441016, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.075133800506592, "global_step": 441017, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1446666717529297, "global_step": 441018, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.088538646697998, "global_step": 441019, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.105635404586792, "global_step": 441020, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0271475315093994, "global_step": 441021, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1729393005371094, "global_step": 441022, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0598020553588867, "global_step": 441023, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.017772674560547, "global_step": 441024, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.109611988067627, "global_step": 441025, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.1153972148895264, "global_step": 441026, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.076145648956299, "global_step": 441027, "epoch": 804, "lr": 5e-05}
{"train_loss": 2.0796403884887695, "global_step": 441028, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.029716730117798, "global_step": 441029, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.132253646850586, "global_step": 441030, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.017103672027588, "global_step": 441031, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.005394220352173, "global_step": 441032, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0653762817382812, "global_step": 441033, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1274521350860596, "global_step": 441034, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.136671781539917, "global_step": 441035, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0705771446228027, "global_step": 441036, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0719242095947266, "global_step": 441037, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0313050746917725, "global_step": 441038, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0222296714782715, "global_step": 441039, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.064037322998047, "global_step": 441040, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1925814151763916, "global_step": 441041, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.068948268890381, "global_step": 441042, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.084620475769043, "global_step": 441043, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.032137870788574, "global_step": 441044, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0905256271362305, "global_step": 441045, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0367724895477295, "global_step": 441046, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9760794639587402, "global_step": 441047, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.127100944519043, "global_step": 441048, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.058119535446167, "global_step": 441049, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.975382685661316, "global_step": 441050, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0585031509399414, "global_step": 441051, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0729734897613525, "global_step": 441052, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0994579792022705, "global_step": 441053, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.021602153778076, "global_step": 441054, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0368664264678955, "global_step": 441055, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.102350950241089, "global_step": 441056, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9692158699035645, "global_step": 441057, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9905263185501099, "global_step": 441058, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.051004648208618, "global_step": 441059, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.016299247741699, "global_step": 441060, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0436034202575684, "global_step": 441061, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0707757472991943, "global_step": 441062, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0408055782318115, "global_step": 441063, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0337562561035156, "global_step": 441064, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1154625415802, "global_step": 441065, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1547889709472656, "global_step": 441066, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0975403785705566, "global_step": 441067, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1505672931671143, "global_step": 441068, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0838706493377686, "global_step": 441069, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.042938470840454, "global_step": 441070, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0559494495391846, "global_step": 441071, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.990273356437683, "global_step": 441072, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1416029930114746, "global_step": 441073, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0077221393585205, "global_step": 441074, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.040358066558838, "global_step": 441075, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.066560745239258, "global_step": 441076, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.026002883911133, "global_step": 441077, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1382896900177, "global_step": 441078, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9936212301254272, "global_step": 441079, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0838701725006104, "global_step": 441080, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1046674251556396, "global_step": 441081, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0857737064361572, "global_step": 441082, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0511910915374756, "global_step": 441083, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0632164478302, "global_step": 441084, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0835154056549072, "global_step": 441085, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.069779634475708, "global_step": 441086, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.012714385986328, "global_step": 441087, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.025972843170166, "global_step": 441088, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.019932746887207, "global_step": 441089, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0170974731445312, "global_step": 441090, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9672805070877075, "global_step": 441091, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0568244457244873, "global_step": 441092, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0769331455230713, "global_step": 441093, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0244300365448, "global_step": 441094, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.05129337310791, "global_step": 441095, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1154396533966064, "global_step": 441096, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0570406913757324, "global_step": 441097, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.091613292694092, "global_step": 441098, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.079972267150879, "global_step": 441099, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.100368022918701, "global_step": 441100, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1114678382873535, "global_step": 441101, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.096982717514038, "global_step": 441102, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.008096218109131, "global_step": 441103, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0581207275390625, "global_step": 441104, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1578269004821777, "global_step": 441105, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.032413959503174, "global_step": 441106, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1743619441986084, "global_step": 441107, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.019503355026245, "global_step": 441108, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0574023723602295, "global_step": 441109, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1059939861297607, "global_step": 441110, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1389341354370117, "global_step": 441111, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0528862476348877, "global_step": 441112, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0679423809051514, "global_step": 441113, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1448843479156494, "global_step": 441114, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.111037254333496, "global_step": 441115, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9990277290344238, "global_step": 441116, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0843210220336914, "global_step": 441117, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.048670530319214, "global_step": 441118, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.077592134475708, "global_step": 441119, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.092280864715576, "global_step": 441120, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0673487186431885, "global_step": 441121, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.041794538497925, "global_step": 441122, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.042386770248413, "global_step": 441123, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.062744379043579, "global_step": 441124, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1020588874816895, "global_step": 441125, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1797094345092773, "global_step": 441126, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.051461935043335, "global_step": 441127, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0876235961914062, "global_step": 441128, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0855650901794434, "global_step": 441129, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0433833599090576, "global_step": 441130, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9825941324234009, "global_step": 441131, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.165963649749756, "global_step": 441132, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.920106291770935, "global_step": 441133, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.145113945007324, "global_step": 441134, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.115541934967041, "global_step": 441135, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0303618907928467, "global_step": 441136, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.067039966583252, "global_step": 441137, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1869900226593018, "global_step": 441138, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0772228240966797, "global_step": 441139, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.124177932739258, "global_step": 441140, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.069316864013672, "global_step": 441141, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1406004428863525, "global_step": 441142, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1084845066070557, "global_step": 441143, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.07810640335083, "global_step": 441144, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.134444236755371, "global_step": 441145, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.036345958709717, "global_step": 441146, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.112234592437744, "global_step": 441147, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9727203845977783, "global_step": 441148, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0694892406463623, "global_step": 441149, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.017055034637451, "global_step": 441150, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.2100846767425537, "global_step": 441151, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0905354022979736, "global_step": 441152, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0262792110443115, "global_step": 441153, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.087592363357544, "global_step": 441154, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0073776245117188, "global_step": 441155, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.055088758468628, "global_step": 441156, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0739963054656982, "global_step": 441157, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.145596742630005, "global_step": 441158, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.002826690673828, "global_step": 441159, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9949766397476196, "global_step": 441160, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.038233518600464, "global_step": 441161, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0610647201538086, "global_step": 441162, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1012444496154785, "global_step": 441163, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0419368743896484, "global_step": 441164, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0615642070770264, "global_step": 441165, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.087268352508545, "global_step": 441166, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1389925479888916, "global_step": 441167, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1307616233825684, "global_step": 441168, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.06878399848938, "global_step": 441169, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0018999576568604, "global_step": 441170, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0503597259521484, "global_step": 441171, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0726521015167236, "global_step": 441172, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.045999765396118, "global_step": 441173, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.081723690032959, "global_step": 441174, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0362236499786377, "global_step": 441175, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1325817108154297, "global_step": 441176, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.093743085861206, "global_step": 441177, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.063044309616089, "global_step": 441178, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.108901023864746, "global_step": 441179, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1180379390716553, "global_step": 441180, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0430424213409424, "global_step": 441181, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.021984815597534, "global_step": 441182, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1539041996002197, "global_step": 441183, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0946896076202393, "global_step": 441184, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0383477210998535, "global_step": 441185, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.07548189163208, "global_step": 441186, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.132145404815674, "global_step": 441187, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.077986478805542, "global_step": 441188, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1000239849090576, "global_step": 441189, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0372941493988037, "global_step": 441190, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9690797328948975, "global_step": 441191, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0699782371520996, "global_step": 441192, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0827035903930664, "global_step": 441193, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.155022144317627, "global_step": 441194, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0489866733551025, "global_step": 441195, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0000855922698975, "global_step": 441196, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.051920175552368, "global_step": 441197, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1317367553710938, "global_step": 441198, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1444742679595947, "global_step": 441199, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0102202892303467, "global_step": 441200, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0805160999298096, "global_step": 441201, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0182089805603027, "global_step": 441202, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0682263374328613, "global_step": 441203, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.104775905609131, "global_step": 441204, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1450161933898926, "global_step": 441205, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0561351776123047, "global_step": 441206, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0841002464294434, "global_step": 441207, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0744576454162598, "global_step": 441208, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0429751873016357, "global_step": 441209, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.00119686126709, "global_step": 441210, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.149282693862915, "global_step": 441211, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.184239387512207, "global_step": 441212, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0299389362335205, "global_step": 441213, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.141148328781128, "global_step": 441214, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.159386396408081, "global_step": 441215, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1305882930755615, "global_step": 441216, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1184794902801514, "global_step": 441217, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.053581476211548, "global_step": 441218, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0021023750305176, "global_step": 441219, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1246278285980225, "global_step": 441220, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1323089599609375, "global_step": 441221, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.149216890335083, "global_step": 441222, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.045997381210327, "global_step": 441223, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.118407726287842, "global_step": 441224, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.025371551513672, "global_step": 441225, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.124885320663452, "global_step": 441226, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0367398262023926, "global_step": 441227, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.138563632965088, "global_step": 441228, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0727121829986572, "global_step": 441229, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.138245105743408, "global_step": 441230, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.104813575744629, "global_step": 441231, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.040020227432251, "global_step": 441232, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0024361610412598, "global_step": 441233, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.05141019821167, "global_step": 441234, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0500786304473877, "global_step": 441235, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.039926767349243, "global_step": 441236, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.09232759475708, "global_step": 441237, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1316866874694824, "global_step": 441238, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0799336433410645, "global_step": 441239, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0020182132720947, "global_step": 441240, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9961565732955933, "global_step": 441241, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0940959453582764, "global_step": 441242, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.142902374267578, "global_step": 441243, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.2106688022613525, "global_step": 441244, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9936050176620483, "global_step": 441245, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.056013584136963, "global_step": 441246, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.066204309463501, "global_step": 441247, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1852240562438965, "global_step": 441248, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.058566093444824, "global_step": 441249, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0173678398132324, "global_step": 441250, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.109595537185669, "global_step": 441251, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.075902223587036, "global_step": 441252, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0772218704223633, "global_step": 441253, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.114539623260498, "global_step": 441254, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0595943927764893, "global_step": 441255, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.014902114868164, "global_step": 441256, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0536868572235107, "global_step": 441257, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.053752899169922, "global_step": 441258, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0605180263519287, "global_step": 441259, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0622241497039795, "global_step": 441260, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.056018114089966, "global_step": 441261, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.125511407852173, "global_step": 441262, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.026740789413452, "global_step": 441263, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.129673719406128, "global_step": 441264, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0243263244628906, "global_step": 441265, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0324513912200928, "global_step": 441266, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1414332389831543, "global_step": 441267, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0169837474823, "global_step": 441268, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1022255420684814, "global_step": 441269, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.035935163497925, "global_step": 441270, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.105736017227173, "global_step": 441271, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0928876399993896, "global_step": 441272, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9983241558074951, "global_step": 441273, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0040860176086426, "global_step": 441274, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0345609188079834, "global_step": 441275, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0712082386016846, "global_step": 441276, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.027026653289795, "global_step": 441277, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0049326419830322, "global_step": 441278, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1571764945983887, "global_step": 441279, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0606887340545654, "global_step": 441280, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0486185550689697, "global_step": 441281, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1378841400146484, "global_step": 441282, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.001938581466675, "global_step": 441283, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.008136749267578, "global_step": 441284, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0199220180511475, "global_step": 441285, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.052319049835205, "global_step": 441286, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.115953207015991, "global_step": 441287, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.09080171585083, "global_step": 441288, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0874762535095215, "global_step": 441289, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.122577667236328, "global_step": 441290, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.079803228378296, "global_step": 441291, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.091820240020752, "global_step": 441292, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0655899047851562, "global_step": 441293, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.090196132659912, "global_step": 441294, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.070639133453369, "global_step": 441295, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1133275032043457, "global_step": 441296, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.114797592163086, "global_step": 441297, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.025925636291504, "global_step": 441298, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.114783763885498, "global_step": 441299, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0070810317993164, "global_step": 441300, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.096644878387451, "global_step": 441301, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1001663208007812, "global_step": 441302, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.08015775680542, "global_step": 441303, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0111422538757324, "global_step": 441304, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0922207832336426, "global_step": 441305, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1240036487579346, "global_step": 441306, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1280603408813477, "global_step": 441307, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.075092077255249, "global_step": 441308, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0664660930633545, "global_step": 441309, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1629676818847656, "global_step": 441310, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0588505268096924, "global_step": 441311, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.988197684288025, "global_step": 441312, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.982935905456543, "global_step": 441313, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0150835514068604, "global_step": 441314, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0679473876953125, "global_step": 441315, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1144092082977295, "global_step": 441316, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.051790237426758, "global_step": 441317, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1102888584136963, "global_step": 441318, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1684436798095703, "global_step": 441319, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1338229179382324, "global_step": 441320, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.080836296081543, "global_step": 441321, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.133699655532837, "global_step": 441322, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9710798263549805, "global_step": 441323, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.108963966369629, "global_step": 441324, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.099017381668091, "global_step": 441325, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.169919490814209, "global_step": 441326, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0450425148010254, "global_step": 441327, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.131448745727539, "global_step": 441328, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.085092782974243, "global_step": 441329, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0993964672088623, "global_step": 441330, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0704009532928467, "global_step": 441331, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0939533710479736, "global_step": 441332, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.003544569015503, "global_step": 441333, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0671939849853516, "global_step": 441334, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0624678134918213, "global_step": 441335, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0856478214263916, "global_step": 441336, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0149085521698, "global_step": 441337, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.065678358078003, "global_step": 441338, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.037902593612671, "global_step": 441339, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.073716163635254, "global_step": 441340, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.126384973526001, "global_step": 441341, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1127047538757324, "global_step": 441342, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.09089994430542, "global_step": 441343, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.101022481918335, "global_step": 441344, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1459665298461914, "global_step": 441345, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0478110313415527, "global_step": 441346, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1927120685577393, "global_step": 441347, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1234140396118164, "global_step": 441348, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.020156145095825, "global_step": 441349, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.135295867919922, "global_step": 441350, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0403363704681396, "global_step": 441351, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1147327423095703, "global_step": 441352, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.106126546859741, "global_step": 441353, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0553038120269775, "global_step": 441354, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.103415012359619, "global_step": 441355, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9906039237976074, "global_step": 441356, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.008453607559204, "global_step": 441357, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0558278560638428, "global_step": 441358, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0092039108276367, "global_step": 441359, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.025146007537842, "global_step": 441360, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1192097663879395, "global_step": 441361, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0924949645996094, "global_step": 441362, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.090904474258423, "global_step": 441363, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9888081550598145, "global_step": 441364, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1422007083892822, "global_step": 441365, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.025448799133301, "global_step": 441366, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.116776466369629, "global_step": 441367, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0042567253112793, "global_step": 441368, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0050370693206787, "global_step": 441369, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.094108819961548, "global_step": 441370, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0673716068267822, "global_step": 441371, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0212883949279785, "global_step": 441372, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.116696357727051, "global_step": 441373, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.157910108566284, "global_step": 441374, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.045456647872925, "global_step": 441375, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.065216541290283, "global_step": 441376, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.08708119392395, "global_step": 441377, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.110086441040039, "global_step": 441378, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0424094200134277, "global_step": 441379, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0469348430633545, "global_step": 441380, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1264500617980957, "global_step": 441381, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.131760358810425, "global_step": 441382, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.068664073944092, "global_step": 441383, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1188530921936035, "global_step": 441384, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.109750747680664, "global_step": 441385, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.089158535003662, "global_step": 441386, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.006754159927368, "global_step": 441387, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.067659378051758, "global_step": 441388, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0601842403411865, "global_step": 441389, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0631542205810547, "global_step": 441390, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.091477632522583, "global_step": 441391, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1633400917053223, "global_step": 441392, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.088780164718628, "global_step": 441393, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0566084384918213, "global_step": 441394, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1344258785247803, "global_step": 441395, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.052933931350708, "global_step": 441396, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.094761848449707, "global_step": 441397, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.2120134830474854, "global_step": 441398, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.061553716659546, "global_step": 441399, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0761196613311768, "global_step": 441400, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9996991157531738, "global_step": 441401, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0339198112487793, "global_step": 441402, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.104931116104126, "global_step": 441403, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.097597599029541, "global_step": 441404, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.012645959854126, "global_step": 441405, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1114323139190674, "global_step": 441406, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1168553829193115, "global_step": 441407, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0832738876342773, "global_step": 441408, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.124135732650757, "global_step": 441409, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0540735721588135, "global_step": 441410, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0720226764678955, "global_step": 441411, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0936758518218994, "global_step": 441412, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1183419227600098, "global_step": 441413, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.038961887359619, "global_step": 441414, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0184879302978516, "global_step": 441415, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0863070487976074, "global_step": 441416, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0894784927368164, "global_step": 441417, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.089735507965088, "global_step": 441418, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1110212802886963, "global_step": 441419, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.10072922706604, "global_step": 441420, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.067847728729248, "global_step": 441421, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.063877582550049, "global_step": 441422, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.116438627243042, "global_step": 441423, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.099724769592285, "global_step": 441424, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.033493995666504, "global_step": 441425, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0963973999023438, "global_step": 441426, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.130488395690918, "global_step": 441427, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.124579668045044, "global_step": 441428, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.182096242904663, "global_step": 441429, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.022972583770752, "global_step": 441430, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0614068508148193, "global_step": 441431, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.022536039352417, "global_step": 441432, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0849483013153076, "global_step": 441433, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.058671474456787, "global_step": 441434, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0662307739257812, "global_step": 441435, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1036934852600098, "global_step": 441436, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.021772623062134, "global_step": 441437, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.20900821685791, "global_step": 441438, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.06789231300354, "global_step": 441439, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.070668935775757, "global_step": 441440, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.127706527709961, "global_step": 441441, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.092717170715332, "global_step": 441442, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0394814014434814, "global_step": 441443, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0577657222747803, "global_step": 441444, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.106135129928589, "global_step": 441445, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0653510093688965, "global_step": 441446, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.026503562927246, "global_step": 441447, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.135803699493408, "global_step": 441448, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1941962242126465, "global_step": 441449, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1191940307617188, "global_step": 441450, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.037181854248047, "global_step": 441451, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.109313726425171, "global_step": 441452, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.079939126968384, "global_step": 441453, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.06673002243042, "global_step": 441454, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.942940354347229, "global_step": 441455, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.96454918384552, "global_step": 441456, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.01011323928833, "global_step": 441457, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.05707049369812, "global_step": 441458, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.101132869720459, "global_step": 441459, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0286872386932373, "global_step": 441460, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0783653259277344, "global_step": 441461, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.010239839553833, "global_step": 441462, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1063477993011475, "global_step": 441463, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.090569019317627, "global_step": 441464, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.134464740753174, "global_step": 441465, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.098769426345825, "global_step": 441466, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1701645851135254, "global_step": 441467, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.119500160217285, "global_step": 441468, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.061666250228882, "global_step": 441469, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.127075672149658, "global_step": 441470, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.074253559112549, "global_step": 441471, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0978357791900635, "global_step": 441472, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9171615839004517, "global_step": 441473, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0565085411071777, "global_step": 441474, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.064187526702881, "global_step": 441475, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1713976860046387, "global_step": 441476, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.175477981567383, "global_step": 441477, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1430156230926514, "global_step": 441478, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.075255870819092, "global_step": 441479, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9935414791107178, "global_step": 441480, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1486520767211914, "global_step": 441481, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0866432189941406, "global_step": 441482, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0411264896392822, "global_step": 441483, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.019763231277466, "global_step": 441484, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.145293951034546, "global_step": 441485, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.109276056289673, "global_step": 441486, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1164932250976562, "global_step": 441487, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1143674850463867, "global_step": 441488, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.088120937347412, "global_step": 441489, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0205862522125244, "global_step": 441490, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0254287719726562, "global_step": 441491, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.119767189025879, "global_step": 441492, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0963594913482666, "global_step": 441493, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0270488262176514, "global_step": 441494, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1036274433135986, "global_step": 441495, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9731636047363281, "global_step": 441496, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.150151491165161, "global_step": 441497, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.196075201034546, "global_step": 441498, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.05000901222229, "global_step": 441499, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1538946628570557, "global_step": 441500, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0523972511291504, "global_step": 441501, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.160649299621582, "global_step": 441502, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0987768173217773, "global_step": 441503, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0359058380126953, "global_step": 441504, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.116760492324829, "global_step": 441505, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0764381885528564, "global_step": 441506, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0648913383483887, "global_step": 441507, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.165827989578247, "global_step": 441508, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1276333332061768, "global_step": 441509, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0987350940704346, "global_step": 441510, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.10794734954834, "global_step": 441511, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.073288679122925, "global_step": 441512, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0787415504455566, "global_step": 441513, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0999326705932617, "global_step": 441514, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0854337215423584, "global_step": 441515, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.026925563812256, "global_step": 441516, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1119229793548584, "global_step": 441517, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.046898603439331, "global_step": 441518, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0684847831726074, "global_step": 441519, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1055471897125244, "global_step": 441520, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.172952890396118, "global_step": 441521, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.106989860534668, "global_step": 441522, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0792484283447266, "global_step": 441523, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0218093395233154, "global_step": 441524, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0789825916290283, "global_step": 441525, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.010042667388916, "global_step": 441526, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.095870018005371, "global_step": 441527, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0418283939361572, "global_step": 441528, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.035776138305664, "global_step": 441529, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1107046604156494, "global_step": 441530, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1300482749938965, "global_step": 441531, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.059694766998291, "global_step": 441532, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.068622589111328, "global_step": 441533, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.124800443649292, "global_step": 441534, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0708835124969482, "global_step": 441535, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.075604200363159, "global_step": 441536, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0719780921936035, "global_step": 441537, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.089783191680908, "global_step": 441538, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0919623374938965, "global_step": 441539, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1332709789276123, "global_step": 441540, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.113933563232422, "global_step": 441541, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1113531589508057, "global_step": 441542, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1003994941711426, "global_step": 441543, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.110729455947876, "global_step": 441544, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.057135581970215, "global_step": 441545, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.139073133468628, "global_step": 441546, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1538290977478027, "global_step": 441547, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.097870349884033, "global_step": 441548, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0923330783843994, "global_step": 441549, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.127260684967041, "global_step": 441550, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.120288133621216, "global_step": 441551, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9685139656066895, "global_step": 441552, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1444554328918457, "global_step": 441553, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.084980010986328, "global_step": 441554, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0250067710876465, "global_step": 441555, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.077755928039551, "global_step": 441556, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.070389747619629, "global_step": 441557, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1460814476013184, "global_step": 441558, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0489561557769775, "global_step": 441559, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1117637157440186, "global_step": 441560, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.07960844039917, "global_step": 441561, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.029245376586914, "global_step": 441562, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0230143070220947, "global_step": 441563, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0871400833129883, "global_step": 441564, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.081265687942505, "global_step": 441565, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0280230045318604, "global_step": 441566, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1010184288024902, "global_step": 441567, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0668816566467285, "global_step": 441568, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0736560821533203, "global_step": 441569, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.097761631011963, "global_step": 441570, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0176196098327637, "global_step": 441571, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9762142896652222, "global_step": 441572, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0625991821289062, "global_step": 441573, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.072903633117676, "global_step": 441574, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0628726482391357, "global_step": 441575, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.054262161254883, "global_step": 441576, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0667736530303955, "global_step": 441577, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.059687614440918, "global_step": 441578, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.095067024230957, "global_step": 441579, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.053123950958252, "global_step": 441580, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.054060697555542, "global_step": 441581, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.112297296524048, "global_step": 441582, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.114135265350342, "global_step": 441583, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0680129528045654, "global_step": 441584, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.072577476501465, "global_step": 441585, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.002906560897827, "global_step": 441586, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0528206825256348, "global_step": 441587, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0412933826446533, "global_step": 441588, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1233315467834473, "global_step": 441589, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0669844150543213, "global_step": 441590, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1484391689300537, "global_step": 441591, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.036005973815918, "global_step": 441592, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1178364753723145, "global_step": 441593, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0151853561401367, "global_step": 441594, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0482704639434814, "global_step": 441595, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.046492338180542, "global_step": 441596, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0341408252716064, "global_step": 441597, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0656707286834717, "global_step": 441598, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9960843324661255, "global_step": 441599, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0324254035949707, "global_step": 441600, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0395917892456055, "global_step": 441601, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.059227705001831, "global_step": 441602, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0697762966156006, "global_step": 441603, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.990412950515747, "global_step": 441604, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.157197952270508, "global_step": 441605, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0536489486694336, "global_step": 441606, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0528392791748047, "global_step": 441607, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.076296806335449, "global_step": 441608, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.075984239578247, "global_step": 441609, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.042539119720459, "global_step": 441610, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.082606315612793, "global_step": 441611, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.041768789291382, "global_step": 441612, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9807639122009277, "global_step": 441613, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1555042266845703, "global_step": 441614, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0826241970062256, "global_step": 441615, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0817253589630127, "global_step": 441616, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.123786687850952, "global_step": 441617, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.062836170196533, "global_step": 441618, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.10502290725708, "global_step": 441619, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1680397987365723, "global_step": 441620, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.00305438041687, "global_step": 441621, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1036593914031982, "global_step": 441622, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.062929153442383, "global_step": 441623, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.046069383621216, "global_step": 441624, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0814154148101807, "global_step": 441625, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.060934543609619, "global_step": 441626, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.088575601577759, "global_step": 441627, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0270965099334717, "global_step": 441628, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.061894178390503, "global_step": 441629, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.081148624420166, "global_step": 441630, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.083244562149048, "global_step": 441631, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0752246379852295, "global_step": 441632, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.074343204498291, "global_step": 441633, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0690860748291016, "global_step": 441634, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0473036766052246, "global_step": 441635, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0596818923950195, "global_step": 441636, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0504648685455322, "global_step": 441637, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1406145095825195, "global_step": 441638, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1083006858825684, "global_step": 441639, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.066923141479492, "global_step": 441640, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.070446729660034, "global_step": 441641, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.127523422241211, "global_step": 441642, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0042362213134766, "global_step": 441643, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1112616062164307, "global_step": 441644, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.095954656600952, "global_step": 441645, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.089647054672241, "global_step": 441646, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9787170886993408, "global_step": 441647, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.073805570602417, "global_step": 441648, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.143404960632324, "global_step": 441649, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0671041011810303, "global_step": 441650, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.082627534866333, "global_step": 441651, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1249938011169434, "global_step": 441652, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.077785015106201, "global_step": 441653, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.2002148628234863, "global_step": 441654, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.037384510040283, "global_step": 441655, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.185737133026123, "global_step": 441656, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9758796691894531, "global_step": 441657, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0631043910980225, "global_step": 441658, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.05501389503479, "global_step": 441659, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1057088375091553, "global_step": 441660, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0999882221221924, "global_step": 441661, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.072627067565918, "global_step": 441662, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1350533962249756, "global_step": 441663, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1694588661193848, "global_step": 441664, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.126147985458374, "global_step": 441665, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0580739974975586, "global_step": 441666, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.185077428817749, "global_step": 441667, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0874831676483154, "global_step": 441668, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.123729705810547, "global_step": 441669, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1069979667663574, "global_step": 441670, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.071406602859497, "global_step": 441671, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.055917739868164, "global_step": 441672, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.037673234939575, "global_step": 441673, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.106868028640747, "global_step": 441674, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.118002414703369, "global_step": 441675, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1202123165130615, "global_step": 441676, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.2237768173217773, "global_step": 441677, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.122166633605957, "global_step": 441678, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0689175128936768, "global_step": 441679, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0902063846588135, "global_step": 441680, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0978875160217285, "global_step": 441681, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.037748336791992, "global_step": 441682, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.037153720855713, "global_step": 441683, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.094163417816162, "global_step": 441684, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0837037563323975, "global_step": 441685, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9984025955200195, "global_step": 441686, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1059253215789795, "global_step": 441687, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1035656929016113, "global_step": 441688, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.069234609603882, "global_step": 441689, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1398537158966064, "global_step": 441690, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0977163314819336, "global_step": 441691, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0757970809936523, "global_step": 441692, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0865907669067383, "global_step": 441693, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0142054557800293, "global_step": 441694, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.058762550354004, "global_step": 441695, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1265621185302734, "global_step": 441696, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0429699420928955, "global_step": 441697, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0556845664978027, "global_step": 441698, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.057124614715576, "global_step": 441699, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0830209255218506, "global_step": 441700, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.040508270263672, "global_step": 441701, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0628068447113037, "global_step": 441702, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.132272243499756, "global_step": 441703, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0434460639953613, "global_step": 441704, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.104071617126465, "global_step": 441705, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0989696979522705, "global_step": 441706, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0818045139312744, "global_step": 441707, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0639350414276123, "global_step": 441708, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0362274646759033, "global_step": 441709, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.058673620223999, "global_step": 441710, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0400989055633545, "global_step": 441711, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0851738452911377, "global_step": 441712, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1257500648498535, "global_step": 441713, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0401124954223633, "global_step": 441714, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1119894981384277, "global_step": 441715, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0311341285705566, "global_step": 441716, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.119235038757324, "global_step": 441717, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0375962257385254, "global_step": 441718, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.062671661376953, "global_step": 441719, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.038642168045044, "global_step": 441720, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9875911474227905, "global_step": 441721, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0467801094055176, "global_step": 441722, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1081385612487793, "global_step": 441723, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.154867649078369, "global_step": 441724, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.074578285217285, "global_step": 441725, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9971015453338623, "global_step": 441726, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1999781131744385, "global_step": 441727, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1721808910369873, "global_step": 441728, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.130993127822876, "global_step": 441729, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.008009433746338, "global_step": 441730, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9937824010849, "global_step": 441731, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.2021241188049316, "global_step": 441732, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0769479274749756, "global_step": 441733, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0957565307617188, "global_step": 441734, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.101841449737549, "global_step": 441735, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.055788993835449, "global_step": 441736, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0346555709838867, "global_step": 441737, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.118995428085327, "global_step": 441738, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.045799732208252, "global_step": 441739, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0726044178009033, "global_step": 441740, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9913396835327148, "global_step": 441741, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0907375812530518, "global_step": 441742, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1043460369110107, "global_step": 441743, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.175854444503784, "global_step": 441744, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9839973449707031, "global_step": 441745, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0989012718200684, "global_step": 441746, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0075936317443848, "global_step": 441747, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0425610542297363, "global_step": 441748, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0617480278015137, "global_step": 441749, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.2206034660339355, "global_step": 441750, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.057467222213745, "global_step": 441751, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1101205348968506, "global_step": 441752, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1242265701293945, "global_step": 441753, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1425282955169678, "global_step": 441754, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0735628604888916, "global_step": 441755, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.169973134994507, "global_step": 441756, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0883805751800537, "global_step": 441757, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1022555828094482, "global_step": 441758, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0090548992156982, "global_step": 441759, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.096269369125366, "global_step": 441760, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0932440757751465, "global_step": 441761, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0833067893981934, "global_step": 441762, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0804011821746826, "global_step": 441763, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0719425678253174, "global_step": 441764, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0665743350982666, "global_step": 441765, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.027578115463257, "global_step": 441766, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.026559352874756, "global_step": 441767, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0670382976531982, "global_step": 441768, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0702762603759766, "global_step": 441769, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.064974308013916, "global_step": 441770, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0571377277374268, "global_step": 441771, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.062908172607422, "global_step": 441772, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0547609329223633, "global_step": 441773, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0936717987060547, "global_step": 441774, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.057015895843506, "global_step": 441775, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.020462989807129, "global_step": 441776, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0691747665405273, "global_step": 441777, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.148505687713623, "global_step": 441778, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0779924392700195, "global_step": 441779, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1050381660461426, "global_step": 441780, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.068443536758423, "global_step": 441781, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.028801202774048, "global_step": 441782, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0803050994873047, "global_step": 441783, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0574162006378174, "global_step": 441784, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0313494205474854, "global_step": 441785, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.091386556625366, "global_step": 441786, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.041226625442505, "global_step": 441787, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.028953790664673, "global_step": 441788, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1173551082611084, "global_step": 441789, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.054854393005371, "global_step": 441790, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.073125123977661, "global_step": 441791, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.04400897026062, "global_step": 441792, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.02876353263855, "global_step": 441793, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1079819202423096, "global_step": 441794, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0787625312805176, "global_step": 441795, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1080856323242188, "global_step": 441796, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0714938640594482, "global_step": 441797, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0009610652923584, "global_step": 441798, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0344626903533936, "global_step": 441799, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0292537212371826, "global_step": 441800, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9560422897338867, "global_step": 441801, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.137289524078369, "global_step": 441802, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1062724590301514, "global_step": 441803, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.013131856918335, "global_step": 441804, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0088634490966797, "global_step": 441805, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.081768751144409, "global_step": 441806, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1144790649414062, "global_step": 441807, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0051028728485107, "global_step": 441808, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.208510637283325, "global_step": 441809, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0548462867736816, "global_step": 441810, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1636428833007812, "global_step": 441811, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0623412132263184, "global_step": 441812, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.071420907974243, "global_step": 441813, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0189709663391113, "global_step": 441814, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1820576190948486, "global_step": 441815, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.041198968887329, "global_step": 441816, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.006378173828125, "global_step": 441817, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0714097023010254, "global_step": 441818, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0123465061187744, "global_step": 441819, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1122541427612305, "global_step": 441820, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.180483818054199, "global_step": 441821, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.166353464126587, "global_step": 441822, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0073657035827637, "global_step": 441823, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.041879892349243, "global_step": 441824, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1358487606048584, "global_step": 441825, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0910167694091797, "global_step": 441826, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.095238447189331, "global_step": 441827, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.991779088973999, "global_step": 441828, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.083059072494507, "global_step": 441829, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.013895034790039, "global_step": 441830, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0330452919006348, "global_step": 441831, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0936994552612305, "global_step": 441832, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.100576162338257, "global_step": 441833, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.029719829559326, "global_step": 441834, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9915704727172852, "global_step": 441835, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.064415454864502, "global_step": 441836, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.070791721343994, "global_step": 441837, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.01338529586792, "global_step": 441838, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0228021144866943, "global_step": 441839, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1697099208831787, "global_step": 441840, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.108818292617798, "global_step": 441841, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0237040519714355, "global_step": 441842, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0412747859954834, "global_step": 441843, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0204601287841797, "global_step": 441844, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0027623176574707, "global_step": 441845, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.068596839904785, "global_step": 441846, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0306875705718994, "global_step": 441847, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.124886989593506, "global_step": 441848, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0404534339904785, "global_step": 441849, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.034008502960205, "global_step": 441850, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0213723182678223, "global_step": 441851, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1048197746276855, "global_step": 441852, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.096397638320923, "global_step": 441853, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1272220611572266, "global_step": 441854, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9655869007110596, "global_step": 441855, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0667710304260254, "global_step": 441856, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.105550765991211, "global_step": 441857, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1278836727142334, "global_step": 441858, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.122014284133911, "global_step": 441859, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.016024112701416, "global_step": 441860, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.120777130126953, "global_step": 441861, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.001082420349121, "global_step": 441862, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1364428997039795, "global_step": 441863, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1037070751190186, "global_step": 441864, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.096299409866333, "global_step": 441865, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0954740047454834, "global_step": 441866, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1056718826293945, "global_step": 441867, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0697195529937744, "global_step": 441868, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1162726879119873, "global_step": 441869, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0696182250976562, "global_step": 441870, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1553871631622314, "global_step": 441871, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.111936330795288, "global_step": 441872, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1107702255249023, "global_step": 441873, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0864932537078857, "global_step": 441874, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.081669807434082, "global_step": 441875, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.065398693084717, "global_step": 441876, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1247472763061523, "global_step": 441877, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.097325086593628, "global_step": 441878, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.049199342727661, "global_step": 441879, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.094574451446533, "global_step": 441880, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1113924980163574, "global_step": 441881, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.046449899673462, "global_step": 441882, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.013071298599243, "global_step": 441883, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0168280601501465, "global_step": 441884, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.076749801635742, "global_step": 441885, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1707680225372314, "global_step": 441886, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1242611408233643, "global_step": 441887, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.091052770614624, "global_step": 441888, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0426025390625, "global_step": 441889, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0468697547912598, "global_step": 441890, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.184709310531616, "global_step": 441891, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0758895874023438, "global_step": 441892, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.077902317047119, "global_step": 441893, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1472175121307373, "global_step": 441894, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.199798583984375, "global_step": 441895, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0763051509857178, "global_step": 441896, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1216278076171875, "global_step": 441897, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0209429264068604, "global_step": 441898, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1892385482788086, "global_step": 441899, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.072770118713379, "global_step": 441900, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1021087169647217, "global_step": 441901, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9832994937896729, "global_step": 441902, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.075092315673828, "global_step": 441903, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.118525743484497, "global_step": 441904, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.07778263092041, "global_step": 441905, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.07586932182312, "global_step": 441906, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1008996963500977, "global_step": 441907, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.9949264526367188, "global_step": 441908, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0686628818511963, "global_step": 441909, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.109224319458008, "global_step": 441910, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.099034309387207, "global_step": 441911, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0316085815429688, "global_step": 441912, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.073727607727051, "global_step": 441913, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.09443736076355, "global_step": 441914, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.047501564025879, "global_step": 441915, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.100407361984253, "global_step": 441916, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.069700002670288, "global_step": 441917, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.07857346534729, "global_step": 441918, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.077697992324829, "global_step": 441919, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.085580587387085, "global_step": 441920, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0882959365844727, "global_step": 441921, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0690758228302, "global_step": 441922, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.04154896736145, "global_step": 441923, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0755956172943115, "global_step": 441924, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.123582601547241, "global_step": 441925, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0782737731933594, "global_step": 441926, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1688272953033447, "global_step": 441927, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0879924297332764, "global_step": 441928, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0537540912628174, "global_step": 441929, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.040644884109497, "global_step": 441930, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.097881317138672, "global_step": 441931, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.15669584274292, "global_step": 441932, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.127122640609741, "global_step": 441933, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1302711963653564, "global_step": 441934, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.120638132095337, "global_step": 441935, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0806615352630615, "global_step": 441936, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.071965217590332, "global_step": 441937, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.155055046081543, "global_step": 441938, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.085455894470215, "global_step": 441939, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.016716718673706, "global_step": 441940, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1090362071990967, "global_step": 441941, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.176069974899292, "global_step": 441942, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.149320602416992, "global_step": 441943, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1046745777130127, "global_step": 441944, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.11857271194458, "global_step": 441945, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.088510751724243, "global_step": 441946, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1483848094940186, "global_step": 441947, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.106464147567749, "global_step": 441948, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1753480434417725, "global_step": 441949, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.120223045349121, "global_step": 441950, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1211962699890137, "global_step": 441951, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.062734365463257, "global_step": 441952, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1157541275024414, "global_step": 441953, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0957250595092773, "global_step": 441954, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.07194185256958, "global_step": 441955, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0938169956207275, "global_step": 441956, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0678915977478027, "global_step": 441957, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0892105102539062, "global_step": 441958, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0758652687072754, "global_step": 441959, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0666415691375732, "global_step": 441960, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.181912422180176, "global_step": 441961, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1044669151306152, "global_step": 441962, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1701931953430176, "global_step": 441963, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1271047592163086, "global_step": 441964, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1818056106567383, "global_step": 441965, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.142666816711426, "global_step": 441966, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0762906074523926, "global_step": 441967, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.039498805999756, "global_step": 441968, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.051516056060791, "global_step": 441969, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0803489685058594, "global_step": 441970, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0749528408050537, "global_step": 441971, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.012383460998535, "global_step": 441972, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0637803077697754, "global_step": 441973, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.124457836151123, "global_step": 441974, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1421124935150146, "global_step": 441975, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1596972942352295, "global_step": 441976, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.069715976715088, "global_step": 441977, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1069746017456055, "global_step": 441978, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.058971405029297, "global_step": 441979, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1024515628814697, "global_step": 441980, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0662825107574463, "global_step": 441981, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1044559478759766, "global_step": 441982, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0735511779785156, "global_step": 441983, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0387094020843506, "global_step": 441984, "epoch": 805, "lr": 5e-05}
{"train_loss": 1.989034652709961, "global_step": 441985, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.080545425415039, "global_step": 441986, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1788744926452637, "global_step": 441987, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.086102247238159, "global_step": 441988, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1452388763427734, "global_step": 441989, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0348730087280273, "global_step": 441990, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.164220094680786, "global_step": 441991, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0378620624542236, "global_step": 441992, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.040924549102783, "global_step": 441993, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0213894844055176, "global_step": 441994, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.0337557792663574, "global_step": 441995, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.078413486480713, "global_step": 441996, "epoch": 805, "lr": 5e-05}
{"train_loss": 2.1038944721221924, "global_step": 441997, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.056575059890747, "global_step": 441998, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.068302631378174, "global_step": 441999, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0458900928497314, "global_step": 442000, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0491464138031006, "global_step": 442001, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0476090908050537, "global_step": 442002, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0694830417633057, "global_step": 442003, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.117727041244507, "global_step": 442004, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.054676055908203, "global_step": 442005, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0235748291015625, "global_step": 442006, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0079660415649414, "global_step": 442007, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.050436496734619, "global_step": 442008, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0458638668060303, "global_step": 442009, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.149578332901001, "global_step": 442010, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.022871732711792, "global_step": 442011, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.046747922897339, "global_step": 442012, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9859813451766968, "global_step": 442013, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0932791233062744, "global_step": 442014, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0744376182556152, "global_step": 442015, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.101439952850342, "global_step": 442016, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1096880435943604, "global_step": 442017, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0286037921905518, "global_step": 442018, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1131651401519775, "global_step": 442019, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.110896110534668, "global_step": 442020, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0290160179138184, "global_step": 442021, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.039339542388916, "global_step": 442022, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.158249616622925, "global_step": 442023, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1571707725524902, "global_step": 442024, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1102709770202637, "global_step": 442025, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.138077974319458, "global_step": 442026, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.092212438583374, "global_step": 442027, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9883618354797363, "global_step": 442028, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1129651069641113, "global_step": 442029, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1443183422088623, "global_step": 442030, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1192195415496826, "global_step": 442031, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1324281692504883, "global_step": 442032, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.980699896812439, "global_step": 442033, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.141611337661743, "global_step": 442034, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1100893020629883, "global_step": 442035, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1032609939575195, "global_step": 442036, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0808541774749756, "global_step": 442037, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0688626766204834, "global_step": 442038, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.095720052719116, "global_step": 442039, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0562710762023926, "global_step": 442040, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0195648670196533, "global_step": 442041, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1142332553863525, "global_step": 442042, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.012402057647705, "global_step": 442043, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0835206508636475, "global_step": 442044, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0892629623413086, "global_step": 442045, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.092716693878174, "global_step": 442046, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.963165283203125, "global_step": 442047, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0591869354248047, "global_step": 442048, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.082798957824707, "global_step": 442049, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.052481174468994, "global_step": 442050, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0309464931488037, "global_step": 442051, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1190454959869385, "global_step": 442052, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0468711853027344, "global_step": 442053, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1135478019714355, "global_step": 442054, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0504956245422363, "global_step": 442055, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.08475661277771, "global_step": 442056, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.170243501663208, "global_step": 442057, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9917675256729126, "global_step": 442058, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0221004486083984, "global_step": 442059, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.053500175476074, "global_step": 442060, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1403861045837402, "global_step": 442061, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1046061515808105, "global_step": 442062, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1104321479797363, "global_step": 442063, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.124311685562134, "global_step": 442064, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.052298069000244, "global_step": 442065, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0443360805511475, "global_step": 442066, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.028108596801758, "global_step": 442067, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.015409469604492, "global_step": 442068, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1073315143585205, "global_step": 442069, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.040372371673584, "global_step": 442070, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.061328411102295, "global_step": 442071, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.142313003540039, "global_step": 442072, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9962931871414185, "global_step": 442073, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.064791202545166, "global_step": 442074, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.978279948234558, "global_step": 442075, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0585453510284424, "global_step": 442076, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0105831623077393, "global_step": 442077, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0633928775787354, "global_step": 442078, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0280890464782715, "global_step": 442079, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0940566062927246, "global_step": 442080, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0808451175689697, "global_step": 442081, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0163614749908447, "global_step": 442082, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1295876502990723, "global_step": 442083, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.14263653755188, "global_step": 442084, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0146429538726807, "global_step": 442085, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0475962162017822, "global_step": 442086, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.083218812942505, "global_step": 442087, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.016200304031372, "global_step": 442088, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0977766513824463, "global_step": 442089, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.027684211730957, "global_step": 442090, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.041562557220459, "global_step": 442091, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0016047954559326, "global_step": 442092, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.03315806388855, "global_step": 442093, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.078228712081909, "global_step": 442094, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.119257926940918, "global_step": 442095, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0531601905822754, "global_step": 442096, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.111602306365967, "global_step": 442097, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1105153560638428, "global_step": 442098, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0724596977233887, "global_step": 442099, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0936293601989746, "global_step": 442100, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9391804933547974, "global_step": 442101, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0399587154388428, "global_step": 442102, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9772082567214966, "global_step": 442103, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.088975667953491, "global_step": 442104, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0515332221984863, "global_step": 442105, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.23283052444458, "global_step": 442106, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0712976455688477, "global_step": 442107, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1191928386688232, "global_step": 442108, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9960488080978394, "global_step": 442109, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0775506496429443, "global_step": 442110, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.999784231185913, "global_step": 442111, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.107865571975708, "global_step": 442112, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0317375659942627, "global_step": 442113, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9786899089813232, "global_step": 442114, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.065070867538452, "global_step": 442115, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0439367294311523, "global_step": 442116, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1073038578033447, "global_step": 442117, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.023205518722534, "global_step": 442118, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0419819355010986, "global_step": 442119, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.2072091102600098, "global_step": 442120, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9923239946365356, "global_step": 442121, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1056883335113525, "global_step": 442122, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.128873825073242, "global_step": 442123, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0144529342651367, "global_step": 442124, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.115032434463501, "global_step": 442125, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0935492515563965, "global_step": 442126, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.149580955505371, "global_step": 442127, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.068343162536621, "global_step": 442128, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0718400478363037, "global_step": 442129, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0164942741394043, "global_step": 442130, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.191493511199951, "global_step": 442131, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0566112995147705, "global_step": 442132, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0754311084747314, "global_step": 442133, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.090592622756958, "global_step": 442134, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.118227481842041, "global_step": 442135, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0857810974121094, "global_step": 442136, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.040215015411377, "global_step": 442137, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.009423017501831, "global_step": 442138, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0436034202575684, "global_step": 442139, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0344457626342773, "global_step": 442140, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.076031446456909, "global_step": 442141, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.158534526824951, "global_step": 442142, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1626136302948, "global_step": 442143, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9546438455581665, "global_step": 442144, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.108766794204712, "global_step": 442145, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0682621002197266, "global_step": 442146, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1029837131500244, "global_step": 442147, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1609151363372803, "global_step": 442148, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0962417125701904, "global_step": 442149, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0833699703216553, "global_step": 442150, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0266051292419434, "global_step": 442151, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.103346109390259, "global_step": 442152, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.175163507461548, "global_step": 442153, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0776150226593018, "global_step": 442154, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.120103120803833, "global_step": 442155, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.141284465789795, "global_step": 442156, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.047004222869873, "global_step": 442157, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0595498085021973, "global_step": 442158, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0296642780303955, "global_step": 442159, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.076850652694702, "global_step": 442160, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0687716007232666, "global_step": 442161, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9963452816009521, "global_step": 442162, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.100311279296875, "global_step": 442163, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0877394676208496, "global_step": 442164, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1032607555389404, "global_step": 442165, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0639073848724365, "global_step": 442166, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0407235622406006, "global_step": 442167, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0659215450286865, "global_step": 442168, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.056605100631714, "global_step": 442169, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.111698865890503, "global_step": 442170, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.068333148956299, "global_step": 442171, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.991346836090088, "global_step": 442172, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0264739990234375, "global_step": 442173, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.044280767440796, "global_step": 442174, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0817384719848633, "global_step": 442175, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.093262195587158, "global_step": 442176, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1018190383911133, "global_step": 442177, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1340372562408447, "global_step": 442178, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.088326930999756, "global_step": 442179, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1466574668884277, "global_step": 442180, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0322113037109375, "global_step": 442181, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1167945861816406, "global_step": 442182, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.038516044616699, "global_step": 442183, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0164096355438232, "global_step": 442184, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.071620464324951, "global_step": 442185, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0864603519439697, "global_step": 442186, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0154972076416016, "global_step": 442187, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1134893894195557, "global_step": 442188, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.994943618774414, "global_step": 442189, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.128530263900757, "global_step": 442190, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1157829761505127, "global_step": 442191, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1212923526763916, "global_step": 442192, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.998415470123291, "global_step": 442193, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0656604766845703, "global_step": 442194, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.038316011428833, "global_step": 442195, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0648510456085205, "global_step": 442196, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1539857387542725, "global_step": 442197, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.070561408996582, "global_step": 442198, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.2076008319854736, "global_step": 442199, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.040750503540039, "global_step": 442200, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.110541820526123, "global_step": 442201, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1436209678649902, "global_step": 442202, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0053229331970215, "global_step": 442203, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0527422428131104, "global_step": 442204, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.024523973464966, "global_step": 442205, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0565388202667236, "global_step": 442206, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0842835903167725, "global_step": 442207, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0228075981140137, "global_step": 442208, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.046973705291748, "global_step": 442209, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.057983160018921, "global_step": 442210, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9940147399902344, "global_step": 442211, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.117682456970215, "global_step": 442212, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1153969764709473, "global_step": 442213, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0837652683258057, "global_step": 442214, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0342941284179688, "global_step": 442215, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0503721237182617, "global_step": 442216, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.025449514389038, "global_step": 442217, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0926949977874756, "global_step": 442218, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1659514904022217, "global_step": 442219, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0766022205352783, "global_step": 442220, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.097874641418457, "global_step": 442221, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0413835048675537, "global_step": 442222, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.074408531188965, "global_step": 442223, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1129140853881836, "global_step": 442224, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0779223442077637, "global_step": 442225, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0969624519348145, "global_step": 442226, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0094425678253174, "global_step": 442227, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.055297613143921, "global_step": 442228, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.105346918106079, "global_step": 442229, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9767698049545288, "global_step": 442230, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.14350962638855, "global_step": 442231, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.125030279159546, "global_step": 442232, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.082050323486328, "global_step": 442233, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.087282657623291, "global_step": 442234, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.94693124294281, "global_step": 442235, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1489779949188232, "global_step": 442236, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.065676689147949, "global_step": 442237, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0793747901916504, "global_step": 442238, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.017218828201294, "global_step": 442239, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9704504013061523, "global_step": 442240, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1152710914611816, "global_step": 442241, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0695066452026367, "global_step": 442242, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1262099742889404, "global_step": 442243, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1261146068573, "global_step": 442244, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.07358455657959, "global_step": 442245, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0255484580993652, "global_step": 442246, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0953211784362793, "global_step": 442247, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.05794095993042, "global_step": 442248, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.017665386199951, "global_step": 442249, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0374505519866943, "global_step": 442250, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.136167287826538, "global_step": 442251, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0180652141571045, "global_step": 442252, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.088369607925415, "global_step": 442253, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0657098293304443, "global_step": 442254, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.032219409942627, "global_step": 442255, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0498948097229004, "global_step": 442256, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9861431121826172, "global_step": 442257, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.044694423675537, "global_step": 442258, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.049905776977539, "global_step": 442259, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0564706325531006, "global_step": 442260, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1086819171905518, "global_step": 442261, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.01578950881958, "global_step": 442262, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.089109182357788, "global_step": 442263, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0262601375579834, "global_step": 442264, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.175642251968384, "global_step": 442265, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0697546005249023, "global_step": 442266, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1001203060150146, "global_step": 442267, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.035269021987915, "global_step": 442268, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.054917335510254, "global_step": 442269, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0426037311553955, "global_step": 442270, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0793404579162598, "global_step": 442271, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0623581409454346, "global_step": 442272, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.077842950820923, "global_step": 442273, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0338926315307617, "global_step": 442274, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9863790273666382, "global_step": 442275, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0775012969970703, "global_step": 442276, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0757651329040527, "global_step": 442277, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0685431957244873, "global_step": 442278, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1167454719543457, "global_step": 442279, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9985185861587524, "global_step": 442280, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0232033729553223, "global_step": 442281, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.041408061981201, "global_step": 442282, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0855064392089844, "global_step": 442283, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0955941677093506, "global_step": 442284, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.99428129196167, "global_step": 442285, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.039032220840454, "global_step": 442286, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.121641159057617, "global_step": 442287, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1251602172851562, "global_step": 442288, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.105811595916748, "global_step": 442289, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1055030822753906, "global_step": 442290, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1386878490448, "global_step": 442291, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9961261749267578, "global_step": 442292, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.060154914855957, "global_step": 442293, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1550941467285156, "global_step": 442294, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1613881587982178, "global_step": 442295, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1373870372772217, "global_step": 442296, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.115490436553955, "global_step": 442297, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0280869007110596, "global_step": 442298, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0745322704315186, "global_step": 442299, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0831127166748047, "global_step": 442300, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1945157051086426, "global_step": 442301, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9988272190093994, "global_step": 442302, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0612823963165283, "global_step": 442303, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0343286991119385, "global_step": 442304, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.041020154953003, "global_step": 442305, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.02054500579834, "global_step": 442306, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9974077939987183, "global_step": 442307, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1144468784332275, "global_step": 442308, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.063873052597046, "global_step": 442309, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1007866859436035, "global_step": 442310, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1542882919311523, "global_step": 442311, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1703975200653076, "global_step": 442312, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1041338443756104, "global_step": 442313, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1243977546691895, "global_step": 442314, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0739872455596924, "global_step": 442315, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0790748596191406, "global_step": 442316, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1132967472076416, "global_step": 442317, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0607709884643555, "global_step": 442318, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1549179553985596, "global_step": 442319, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.09897518157959, "global_step": 442320, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1076624393463135, "global_step": 442321, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.095160961151123, "global_step": 442322, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1016976833343506, "global_step": 442323, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1640641689300537, "global_step": 442324, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.07808780670166, "global_step": 442325, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0979762077331543, "global_step": 442326, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9963452816009521, "global_step": 442327, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9652239084243774, "global_step": 442328, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0651166439056396, "global_step": 442329, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0150411128997803, "global_step": 442330, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0642967224121094, "global_step": 442331, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1134276390075684, "global_step": 442332, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.107872247695923, "global_step": 442333, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.028294563293457, "global_step": 442334, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0564799308776855, "global_step": 442335, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9769980907440186, "global_step": 442336, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9993128776550293, "global_step": 442337, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0508930683135986, "global_step": 442338, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0987555980682373, "global_step": 442339, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0565996170043945, "global_step": 442340, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0183486938476562, "global_step": 442341, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.127584457397461, "global_step": 442342, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0651023387908936, "global_step": 442343, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1034674644470215, "global_step": 442344, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.100614309310913, "global_step": 442345, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0842764377593994, "global_step": 442346, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0207691192626953, "global_step": 442347, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1135754585266113, "global_step": 442348, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0869383811950684, "global_step": 442349, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0629899501800537, "global_step": 442350, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.108874797821045, "global_step": 442351, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0922598838806152, "global_step": 442352, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0388505458831787, "global_step": 442353, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.998732566833496, "global_step": 442354, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.103142261505127, "global_step": 442355, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.147311210632324, "global_step": 442356, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.02783203125, "global_step": 442357, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.115741729736328, "global_step": 442358, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0826966762542725, "global_step": 442359, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.156959295272827, "global_step": 442360, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0407443046569824, "global_step": 442361, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1578142642974854, "global_step": 442362, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0450985431671143, "global_step": 442363, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.107790470123291, "global_step": 442364, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.074310541152954, "global_step": 442365, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.065110921859741, "global_step": 442366, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.099520206451416, "global_step": 442367, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0805256366729736, "global_step": 442368, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0282773971557617, "global_step": 442369, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0634353160858154, "global_step": 442370, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0305144786834717, "global_step": 442371, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.082679271697998, "global_step": 442372, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0864620208740234, "global_step": 442373, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9870736598968506, "global_step": 442374, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.076051712036133, "global_step": 442375, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1607751846313477, "global_step": 442376, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1316754817962646, "global_step": 442377, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0378804206848145, "global_step": 442378, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0855624675750732, "global_step": 442379, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9677512645721436, "global_step": 442380, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0895724296569824, "global_step": 442381, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.039914846420288, "global_step": 442382, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0863165855407715, "global_step": 442383, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1426665782928467, "global_step": 442384, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.072887897491455, "global_step": 442385, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.052680015563965, "global_step": 442386, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.082732677459717, "global_step": 442387, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.060744047164917, "global_step": 442388, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.10615873336792, "global_step": 442389, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.064143180847168, "global_step": 442390, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.161604166030884, "global_step": 442391, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.045236587524414, "global_step": 442392, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0671682357788086, "global_step": 442393, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0428080558776855, "global_step": 442394, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.150495767593384, "global_step": 442395, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1710457801818848, "global_step": 442396, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0504722595214844, "global_step": 442397, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0361218452453613, "global_step": 442398, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1073262691497803, "global_step": 442399, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9614657163619995, "global_step": 442400, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.096003532409668, "global_step": 442401, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0078465938568115, "global_step": 442402, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.071934938430786, "global_step": 442403, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.055123805999756, "global_step": 442404, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0435028076171875, "global_step": 442405, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.098672866821289, "global_step": 442406, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.092268228530884, "global_step": 442407, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1219818592071533, "global_step": 442408, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1019201278686523, "global_step": 442409, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.06162166595459, "global_step": 442410, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.097947120666504, "global_step": 442411, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.088046073913574, "global_step": 442412, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1452367305755615, "global_step": 442413, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.067669630050659, "global_step": 442414, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.071719169616699, "global_step": 442415, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.054504871368408, "global_step": 442416, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1245601177215576, "global_step": 442417, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.047672986984253, "global_step": 442418, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0639941692352295, "global_step": 442419, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0739026069641113, "global_step": 442420, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0092215538024902, "global_step": 442421, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1199657917022705, "global_step": 442422, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0898497104644775, "global_step": 442423, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0432422161102295, "global_step": 442424, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.089308977127075, "global_step": 442425, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0946242809295654, "global_step": 442426, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1180901527404785, "global_step": 442427, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0971522331237793, "global_step": 442428, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0597164630889893, "global_step": 442429, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9939439296722412, "global_step": 442430, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0621697902679443, "global_step": 442431, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0589258670806885, "global_step": 442432, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0194091796875, "global_step": 442433, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.074140787124634, "global_step": 442434, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0446014404296875, "global_step": 442435, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0387277603149414, "global_step": 442436, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1248724460601807, "global_step": 442437, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.041161298751831, "global_step": 442438, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1244711875915527, "global_step": 442439, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1016392707824707, "global_step": 442440, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1415653228759766, "global_step": 442441, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.120720624923706, "global_step": 442442, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0748684406280518, "global_step": 442443, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.027047872543335, "global_step": 442444, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.085073709487915, "global_step": 442445, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.092933177947998, "global_step": 442446, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1049890518188477, "global_step": 442447, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0812292098999023, "global_step": 442448, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0582220554351807, "global_step": 442449, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1999547481536865, "global_step": 442450, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.056025981903076, "global_step": 442451, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0915935039520264, "global_step": 442452, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.173240900039673, "global_step": 442453, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0203399658203125, "global_step": 442454, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.057790994644165, "global_step": 442455, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.028752565383911, "global_step": 442456, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0526232719421387, "global_step": 442457, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.029151439666748, "global_step": 442458, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.088212490081787, "global_step": 442459, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1048502922058105, "global_step": 442460, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.090806007385254, "global_step": 442461, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0889925956726074, "global_step": 442462, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1127586364746094, "global_step": 442463, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9796366691589355, "global_step": 442464, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1011524200439453, "global_step": 442465, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0657076835632324, "global_step": 442466, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0458872318267822, "global_step": 442467, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.040095090866089, "global_step": 442468, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0230824947357178, "global_step": 442469, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0791678428649902, "global_step": 442470, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.071601390838623, "global_step": 442471, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.139111280441284, "global_step": 442472, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0299439430236816, "global_step": 442473, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.064486026763916, "global_step": 442474, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.01725172996521, "global_step": 442475, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.093153715133667, "global_step": 442476, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0412352085113525, "global_step": 442477, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.022172212600708, "global_step": 442478, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0247058868408203, "global_step": 442479, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9810497760772705, "global_step": 442480, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.129972219467163, "global_step": 442481, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.12738037109375, "global_step": 442482, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.043355941772461, "global_step": 442483, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.079509735107422, "global_step": 442484, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.091923713684082, "global_step": 442485, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.021450996398926, "global_step": 442486, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0341944694519043, "global_step": 442487, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.109173059463501, "global_step": 442488, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0022659301757812, "global_step": 442489, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9717742204666138, "global_step": 442490, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.042048692703247, "global_step": 442491, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1164677143096924, "global_step": 442492, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9865649938583374, "global_step": 442493, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0430986881256104, "global_step": 442494, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0776662826538086, "global_step": 442495, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1264920234680176, "global_step": 442496, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.064913749694824, "global_step": 442497, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0501210689544678, "global_step": 442498, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1774001121520996, "global_step": 442499, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0490353107452393, "global_step": 442500, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0616514682769775, "global_step": 442501, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1443939208984375, "global_step": 442502, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.938477635383606, "global_step": 442503, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0495030879974365, "global_step": 442504, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0544533729553223, "global_step": 442505, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.058574914932251, "global_step": 442506, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.064844846725464, "global_step": 442507, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.065523386001587, "global_step": 442508, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1568732261657715, "global_step": 442509, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.129582405090332, "global_step": 442510, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0775578022003174, "global_step": 442511, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.077176809310913, "global_step": 442512, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.168426752090454, "global_step": 442513, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0848615169525146, "global_step": 442514, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0046093463897705, "global_step": 442515, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1409363746643066, "global_step": 442516, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.096132755279541, "global_step": 442517, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.032491445541382, "global_step": 442518, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.067450523376465, "global_step": 442519, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0653672218322754, "global_step": 442520, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.026256799697876, "global_step": 442521, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1577043533325195, "global_step": 442522, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.047548770904541, "global_step": 442523, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0767879486083984, "global_step": 442524, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1141252517700195, "global_step": 442525, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9963114261627197, "global_step": 442526, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1026854515075684, "global_step": 442527, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0574986934661865, "global_step": 442528, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.160844326019287, "global_step": 442529, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1061909198760986, "global_step": 442530, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0851402282714844, "global_step": 442531, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1231346130371094, "global_step": 442532, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9464765787124634, "global_step": 442533, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9786263704299927, "global_step": 442534, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.122568130493164, "global_step": 442535, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0969698429107666, "global_step": 442536, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.107694149017334, "global_step": 442537, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.994047999382019, "global_step": 442538, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0734574794769287, "global_step": 442539, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1198415756225586, "global_step": 442540, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9824607372283936, "global_step": 442541, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0562899112701416, "global_step": 442542, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1017229557037354, "global_step": 442543, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1202824115753174, "global_step": 442544, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0161080360412598, "global_step": 442545, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1273844242095947, "global_step": 442546, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.163510799407959, "global_step": 442547, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.036886215209961, "global_step": 442548, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0098183155059814, "global_step": 442549, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.163577079772949, "global_step": 442550, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0388543605804443, "global_step": 442551, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.172699451446533, "global_step": 442552, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1136255264282227, "global_step": 442553, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.06630539894104, "global_step": 442554, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.013141393661499, "global_step": 442555, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1232922077178955, "global_step": 442556, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.140235185623169, "global_step": 442557, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0748558044433594, "global_step": 442558, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.031343936920166, "global_step": 442559, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.122051239013672, "global_step": 442560, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0460455417633057, "global_step": 442561, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1325502395629883, "global_step": 442562, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0818934440612793, "global_step": 442563, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0980491638183594, "global_step": 442564, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.131594657897949, "global_step": 442565, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0357110500335693, "global_step": 442566, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0388383865356445, "global_step": 442567, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.084378242492676, "global_step": 442568, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1369588375091553, "global_step": 442569, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1523871421813965, "global_step": 442570, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.124840021133423, "global_step": 442571, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0238993167877197, "global_step": 442572, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0539112091064453, "global_step": 442573, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.077521324157715, "global_step": 442574, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1178321838378906, "global_step": 442575, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.026700258255005, "global_step": 442576, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0931315422058105, "global_step": 442577, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.095952033996582, "global_step": 442578, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0982229709625244, "global_step": 442579, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.014824390411377, "global_step": 442580, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.070554256439209, "global_step": 442581, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1127545833587646, "global_step": 442582, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0939176082611084, "global_step": 442583, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0901012420654297, "global_step": 442584, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.087348222732544, "global_step": 442585, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0823898315429688, "global_step": 442586, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.141204833984375, "global_step": 442587, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.085862874984741, "global_step": 442588, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1582396030426025, "global_step": 442589, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0030786991119385, "global_step": 442590, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.975843071937561, "global_step": 442591, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0503973960876465, "global_step": 442592, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0534608364105225, "global_step": 442593, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0913727283477783, "global_step": 442594, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.083022356033325, "global_step": 442595, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.04691743850708, "global_step": 442596, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9851291179656982, "global_step": 442597, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.07448673248291, "global_step": 442598, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.066401958465576, "global_step": 442599, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1445813179016113, "global_step": 442600, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1259191036224365, "global_step": 442601, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1037871837615967, "global_step": 442602, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0838258266448975, "global_step": 442603, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.118208885192871, "global_step": 442604, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1381728649139404, "global_step": 442605, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0721027851104736, "global_step": 442606, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0723178386688232, "global_step": 442607, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.091419219970703, "global_step": 442608, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0700488090515137, "global_step": 442609, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0827152729034424, "global_step": 442610, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1496002674102783, "global_step": 442611, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1170148849487305, "global_step": 442612, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9683470726013184, "global_step": 442613, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0992653369903564, "global_step": 442614, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1307404041290283, "global_step": 442615, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0984747409820557, "global_step": 442616, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0879836082458496, "global_step": 442617, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9816749095916748, "global_step": 442618, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9675943851470947, "global_step": 442619, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0171406269073486, "global_step": 442620, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.18556547164917, "global_step": 442621, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.082439661026001, "global_step": 442622, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0722098350524902, "global_step": 442623, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0828521251678467, "global_step": 442624, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0849194526672363, "global_step": 442625, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0928966999053955, "global_step": 442626, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0267953872680664, "global_step": 442627, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9883638620376587, "global_step": 442628, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0411481857299805, "global_step": 442629, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.013399600982666, "global_step": 442630, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1018240451812744, "global_step": 442631, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0169320106506348, "global_step": 442632, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0943920612335205, "global_step": 442633, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0222766399383545, "global_step": 442634, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9887653589248657, "global_step": 442635, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1163203716278076, "global_step": 442636, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1468770503997803, "global_step": 442637, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0741167068481445, "global_step": 442638, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.2078657150268555, "global_step": 442639, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.087364673614502, "global_step": 442640, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0894017219543457, "global_step": 442641, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1457602977752686, "global_step": 442642, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.055678129196167, "global_step": 442643, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.044981002807617, "global_step": 442644, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0783731937408447, "global_step": 442645, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.056135654449463, "global_step": 442646, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.989267349243164, "global_step": 442647, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1685268878936768, "global_step": 442648, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0433754920959473, "global_step": 442649, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1123738288879395, "global_step": 442650, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1007144451141357, "global_step": 442651, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0987937450408936, "global_step": 442652, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0748918056488037, "global_step": 442653, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0865533351898193, "global_step": 442654, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0462422370910645, "global_step": 442655, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9432487487792969, "global_step": 442656, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.158233404159546, "global_step": 442657, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.119555950164795, "global_step": 442658, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.169229507446289, "global_step": 442659, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0850377082824707, "global_step": 442660, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.072309732437134, "global_step": 442661, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.053457736968994, "global_step": 442662, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0668838024139404, "global_step": 442663, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0729358196258545, "global_step": 442664, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1221461296081543, "global_step": 442665, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.049189329147339, "global_step": 442666, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.074329137802124, "global_step": 442667, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.120325803756714, "global_step": 442668, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.120150327682495, "global_step": 442669, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.146686315536499, "global_step": 442670, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.084744453430176, "global_step": 442671, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1375732421875, "global_step": 442672, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1172163486480713, "global_step": 442673, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.175089120864868, "global_step": 442674, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0557332038879395, "global_step": 442675, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1574530601501465, "global_step": 442676, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1050777435302734, "global_step": 442677, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1286439895629883, "global_step": 442678, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0745768547058105, "global_step": 442679, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1069324016571045, "global_step": 442680, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0535387992858887, "global_step": 442681, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.049823045730591, "global_step": 442682, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9648946523666382, "global_step": 442683, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.072938919067383, "global_step": 442684, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1111679077148438, "global_step": 442685, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0508005619049072, "global_step": 442686, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.034456253051758, "global_step": 442687, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1083548069000244, "global_step": 442688, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.082599401473999, "global_step": 442689, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.079846143722534, "global_step": 442690, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1188106536865234, "global_step": 442691, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.095797061920166, "global_step": 442692, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.103131055831909, "global_step": 442693, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1100916862487793, "global_step": 442694, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1035947799682617, "global_step": 442695, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9555584192276, "global_step": 442696, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.18190336227417, "global_step": 442697, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0852720737457275, "global_step": 442698, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1354482173919678, "global_step": 442699, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1057448387145996, "global_step": 442700, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.054861307144165, "global_step": 442701, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9948559999465942, "global_step": 442702, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0553088188171387, "global_step": 442703, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1641154289245605, "global_step": 442704, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0758023262023926, "global_step": 442705, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.169424295425415, "global_step": 442706, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.066373825073242, "global_step": 442707, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.056321859359741, "global_step": 442708, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.134267807006836, "global_step": 442709, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0788910388946533, "global_step": 442710, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.076239824295044, "global_step": 442711, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1149141788482666, "global_step": 442712, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.097212791442871, "global_step": 442713, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.079592704772949, "global_step": 442714, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.055837869644165, "global_step": 442715, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0824356079101562, "global_step": 442716, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1669349670410156, "global_step": 442717, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.099660873413086, "global_step": 442718, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1368889808654785, "global_step": 442719, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0989274978637695, "global_step": 442720, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9904179573059082, "global_step": 442721, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0764386653900146, "global_step": 442722, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0592949390411377, "global_step": 442723, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0976603031158447, "global_step": 442724, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0831472873687744, "global_step": 442725, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.049285888671875, "global_step": 442726, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.078457832336426, "global_step": 442727, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0870351791381836, "global_step": 442728, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.133204460144043, "global_step": 442729, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1881303787231445, "global_step": 442730, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1294612884521484, "global_step": 442731, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1385579109191895, "global_step": 442732, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.096508741378784, "global_step": 442733, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.998699426651001, "global_step": 442734, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1074466705322266, "global_step": 442735, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0548126697540283, "global_step": 442736, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1520116329193115, "global_step": 442737, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1117753982543945, "global_step": 442738, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.102250099182129, "global_step": 442739, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0464553833007812, "global_step": 442740, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1526803970336914, "global_step": 442741, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1098549365997314, "global_step": 442742, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0547375679016113, "global_step": 442743, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.00247859954834, "global_step": 442744, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.978114128112793, "global_step": 442745, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0827572345733643, "global_step": 442746, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.072199821472168, "global_step": 442747, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.086798906326294, "global_step": 442748, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.095860481262207, "global_step": 442749, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.046743869781494, "global_step": 442750, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0958285331726074, "global_step": 442751, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.074528694152832, "global_step": 442752, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9864323139190674, "global_step": 442753, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.006472587585449, "global_step": 442754, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.053541898727417, "global_step": 442755, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1499109268188477, "global_step": 442756, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1017754077911377, "global_step": 442757, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1314613819122314, "global_step": 442758, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.034043788909912, "global_step": 442759, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0583972930908203, "global_step": 442760, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0328738689422607, "global_step": 442761, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.186596155166626, "global_step": 442762, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.196977376937866, "global_step": 442763, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0035018920898438, "global_step": 442764, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0603904724121094, "global_step": 442765, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.098989486694336, "global_step": 442766, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0361640453338623, "global_step": 442767, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0542588233947754, "global_step": 442768, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0273501873016357, "global_step": 442769, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0657126903533936, "global_step": 442770, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1020913124084473, "global_step": 442771, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0510809421539307, "global_step": 442772, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.159958839416504, "global_step": 442773, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0770263671875, "global_step": 442774, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1378684043884277, "global_step": 442775, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.032193183898926, "global_step": 442776, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9880247116088867, "global_step": 442777, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.109694004058838, "global_step": 442778, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9832924604415894, "global_step": 442779, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0525989532470703, "global_step": 442780, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.180809736251831, "global_step": 442781, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.231868267059326, "global_step": 442782, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0251171588897705, "global_step": 442783, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0766870975494385, "global_step": 442784, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.090772867202759, "global_step": 442785, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1735024452209473, "global_step": 442786, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.113584518432617, "global_step": 442787, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9595069885253906, "global_step": 442788, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.178830862045288, "global_step": 442789, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1068553924560547, "global_step": 442790, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0701844692230225, "global_step": 442791, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.092637777328491, "global_step": 442792, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0512332916259766, "global_step": 442793, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0818190574645996, "global_step": 442794, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0580267906188965, "global_step": 442795, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.099435567855835, "global_step": 442796, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.059096574783325, "global_step": 442797, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0455129146575928, "global_step": 442798, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.104689836502075, "global_step": 442799, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0754685401916504, "global_step": 442800, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1256301403045654, "global_step": 442801, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0000853538513184, "global_step": 442802, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.066204071044922, "global_step": 442803, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.056105852127075, "global_step": 442804, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9976121187210083, "global_step": 442805, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9933955669403076, "global_step": 442806, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1086103916168213, "global_step": 442807, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1014373302459717, "global_step": 442808, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1185007095336914, "global_step": 442809, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9419188499450684, "global_step": 442810, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0585732460021973, "global_step": 442811, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0409953594207764, "global_step": 442812, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0420713424682617, "global_step": 442813, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9810787439346313, "global_step": 442814, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0839040279388428, "global_step": 442815, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.057420253753662, "global_step": 442816, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0901198387145996, "global_step": 442817, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0838842391967773, "global_step": 442818, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1603219509124756, "global_step": 442819, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0909245014190674, "global_step": 442820, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1299397945404053, "global_step": 442821, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.166189193725586, "global_step": 442822, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.072195529937744, "global_step": 442823, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.077913522720337, "global_step": 442824, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.119328737258911, "global_step": 442825, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0165812969207764, "global_step": 442826, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.070417642593384, "global_step": 442827, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.120527744293213, "global_step": 442828, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.036118745803833, "global_step": 442829, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.106663465499878, "global_step": 442830, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.162672281265259, "global_step": 442831, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0632312297821045, "global_step": 442832, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.129380702972412, "global_step": 442833, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0322749614715576, "global_step": 442834, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1033029556274414, "global_step": 442835, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1291379928588867, "global_step": 442836, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1625983715057373, "global_step": 442837, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.125474691390991, "global_step": 442838, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.095250368118286, "global_step": 442839, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.127687692642212, "global_step": 442840, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.068793296813965, "global_step": 442841, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1136395931243896, "global_step": 442842, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1449880599975586, "global_step": 442843, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.120604991912842, "global_step": 442844, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.18558931350708, "global_step": 442845, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0385217666625977, "global_step": 442846, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.026505947113037, "global_step": 442847, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.142174005508423, "global_step": 442848, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.065762519836426, "global_step": 442849, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.084852933883667, "global_step": 442850, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9606845378875732, "global_step": 442851, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9995025396347046, "global_step": 442852, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0569393634796143, "global_step": 442853, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.081160545349121, "global_step": 442854, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1514320373535156, "global_step": 442855, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0333962440490723, "global_step": 442856, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1382479667663574, "global_step": 442857, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0162246227264404, "global_step": 442858, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1443419456481934, "global_step": 442859, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.036912679672241, "global_step": 442860, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.122692823410034, "global_step": 442861, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1154308319091797, "global_step": 442862, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.039745330810547, "global_step": 442863, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1440279483795166, "global_step": 442864, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1499342918395996, "global_step": 442865, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0358614921569824, "global_step": 442866, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0906500816345215, "global_step": 442867, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0296568870544434, "global_step": 442868, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0927793979644775, "global_step": 442869, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.088021755218506, "global_step": 442870, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0830671787261963, "global_step": 442871, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.077165365219116, "global_step": 442872, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0470845699310303, "global_step": 442873, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0254383087158203, "global_step": 442874, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.113243579864502, "global_step": 442875, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.140119791030884, "global_step": 442876, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.144183874130249, "global_step": 442877, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0900559425354004, "global_step": 442878, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.06935715675354, "global_step": 442879, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1051831245422363, "global_step": 442880, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9850184917449951, "global_step": 442881, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.102903366088867, "global_step": 442882, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0975935459136963, "global_step": 442883, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0617995262145996, "global_step": 442884, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.068999767303467, "global_step": 442885, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.159351348876953, "global_step": 442886, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.077615737915039, "global_step": 442887, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.097439765930176, "global_step": 442888, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0619757175445557, "global_step": 442889, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.102271318435669, "global_step": 442890, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.024338960647583, "global_step": 442891, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.104565382003784, "global_step": 442892, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1073601245880127, "global_step": 442893, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0742180347442627, "global_step": 442894, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0600719451904297, "global_step": 442895, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1247711181640625, "global_step": 442896, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0725033283233643, "global_step": 442897, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0709643363952637, "global_step": 442898, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1056325435638428, "global_step": 442899, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0989296436309814, "global_step": 442900, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9999382495880127, "global_step": 442901, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.05935001373291, "global_step": 442902, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1122050285339355, "global_step": 442903, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.159548282623291, "global_step": 442904, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.058971643447876, "global_step": 442905, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.163734197616577, "global_step": 442906, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0533320903778076, "global_step": 442907, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.121241569519043, "global_step": 442908, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.073895215988159, "global_step": 442909, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.170614242553711, "global_step": 442910, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1211202144622803, "global_step": 442911, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1429638862609863, "global_step": 442912, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.077873468399048, "global_step": 442913, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.162390947341919, "global_step": 442914, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.091618061065674, "global_step": 442915, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0530176162719727, "global_step": 442916, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1089770793914795, "global_step": 442917, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.060926675796509, "global_step": 442918, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0418930053710938, "global_step": 442919, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0768096446990967, "global_step": 442920, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1125364303588867, "global_step": 442921, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0391952991485596, "global_step": 442922, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9517531394958496, "global_step": 442923, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0137195587158203, "global_step": 442924, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0392391681671143, "global_step": 442925, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.080984354019165, "global_step": 442926, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.080172300338745, "global_step": 442927, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.096393585205078, "global_step": 442928, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.010047674179077, "global_step": 442929, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0586869716644287, "global_step": 442930, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0505197048187256, "global_step": 442931, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.015794277191162, "global_step": 442932, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.077949285507202, "global_step": 442933, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1551921367645264, "global_step": 442934, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.080540418624878, "global_step": 442935, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.098662853240967, "global_step": 442936, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.04599666595459, "global_step": 442937, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1017284393310547, "global_step": 442938, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1067347526550293, "global_step": 442939, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0941309928894043, "global_step": 442940, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.139558792114258, "global_step": 442941, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.126779794692993, "global_step": 442942, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0555496215820312, "global_step": 442943, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0783395767211914, "global_step": 442944, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.172929286956787, "global_step": 442945, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.015488862991333, "global_step": 442946, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.069209575653076, "global_step": 442947, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.111673593521118, "global_step": 442948, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1237375736236572, "global_step": 442949, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1769022941589355, "global_step": 442950, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.136719226837158, "global_step": 442951, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.012389898300171, "global_step": 442952, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.043903112411499, "global_step": 442953, "epoch": 806, "lr": 5e-05}
{"train_loss": 1.9251214265823364, "global_step": 442954, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.045189619064331, "global_step": 442955, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.07639479637146, "global_step": 442956, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.1307520866394043, "global_step": 442957, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0946826934814453, "global_step": 442958, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0448567867279053, "global_step": 442959, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.075269937515259, "global_step": 442960, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0641114711761475, "global_step": 442961, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0654332637786865, "global_step": 442962, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.117626428604126, "global_step": 442963, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.0794379711151123, "global_step": 442964, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.077105760574341, "global_step": 442965, "epoch": 806, "lr": 5e-05}
{"train_loss": 2.103132963180542, "global_step": 442966, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.954406976699829, "global_step": 442967, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.121969699859619, "global_step": 442968, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.058831214904785, "global_step": 442969, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9775508642196655, "global_step": 442970, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0523815155029297, "global_step": 442971, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1066014766693115, "global_step": 442972, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.066343307495117, "global_step": 442973, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.03926157951355, "global_step": 442974, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0989434719085693, "global_step": 442975, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.097938060760498, "global_step": 442976, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0977718830108643, "global_step": 442977, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1138713359832764, "global_step": 442978, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.09980845451355, "global_step": 442979, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9749197959899902, "global_step": 442980, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0833077430725098, "global_step": 442981, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.04976487159729, "global_step": 442982, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9076392650604248, "global_step": 442983, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1358838081359863, "global_step": 442984, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.038130044937134, "global_step": 442985, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.080881357192993, "global_step": 442986, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0549674034118652, "global_step": 442987, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9772700071334839, "global_step": 442988, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.07184100151062, "global_step": 442989, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.128844976425171, "global_step": 442990, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.08050799369812, "global_step": 442991, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.075876474380493, "global_step": 442992, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.116802453994751, "global_step": 442993, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0148468017578125, "global_step": 442994, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.157006025314331, "global_step": 442995, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0898919105529785, "global_step": 442996, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.09018611907959, "global_step": 442997, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.085599660873413, "global_step": 442998, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0340394973754883, "global_step": 442999, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.11140775680542, "global_step": 443000, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0017733573913574, "global_step": 443001, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.034043073654175, "global_step": 443002, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0051064491271973, "global_step": 443003, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.949509859085083, "global_step": 443004, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0078792572021484, "global_step": 443005, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.040043354034424, "global_step": 443006, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1494452953338623, "global_step": 443007, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.15330171585083, "global_step": 443008, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.071340560913086, "global_step": 443009, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1027984619140625, "global_step": 443010, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0704216957092285, "global_step": 443011, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.063946008682251, "global_step": 443012, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0748684406280518, "global_step": 443013, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.069153070449829, "global_step": 443014, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.071002721786499, "global_step": 443015, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9911770820617676, "global_step": 443016, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1248345375061035, "global_step": 443017, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0739643573760986, "global_step": 443018, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0258309841156006, "global_step": 443019, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0674421787261963, "global_step": 443020, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.084042549133301, "global_step": 443021, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1732382774353027, "global_step": 443022, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.115729570388794, "global_step": 443023, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.046917676925659, "global_step": 443024, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1769704818725586, "global_step": 443025, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.043881893157959, "global_step": 443026, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0795488357543945, "global_step": 443027, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.078491449356079, "global_step": 443028, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1087870597839355, "global_step": 443029, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.096144676208496, "global_step": 443030, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0296995639801025, "global_step": 443031, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.127774238586426, "global_step": 443032, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0812127590179443, "global_step": 443033, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.061006546020508, "global_step": 443034, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0688138008117676, "global_step": 443035, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0308008193969727, "global_step": 443036, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.080355405807495, "global_step": 443037, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0705995559692383, "global_step": 443038, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0145163536071777, "global_step": 443039, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0853958129882812, "global_step": 443040, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.054628849029541, "global_step": 443041, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.034271001815796, "global_step": 443042, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0616636276245117, "global_step": 443043, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0612716674804688, "global_step": 443044, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1481735706329346, "global_step": 443045, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.103041410446167, "global_step": 443046, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1402716636657715, "global_step": 443047, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9975250959396362, "global_step": 443048, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.059803009033203, "global_step": 443049, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0298304557800293, "global_step": 443050, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.023773193359375, "global_step": 443051, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0417299270629883, "global_step": 443052, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.151095390319824, "global_step": 443053, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0496013164520264, "global_step": 443054, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.01193904876709, "global_step": 443055, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0044326782226562, "global_step": 443056, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0516560077667236, "global_step": 443057, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.057887554168701, "global_step": 443058, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.083801507949829, "global_step": 443059, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.103276014328003, "global_step": 443060, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0067379474639893, "global_step": 443061, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0322458744049072, "global_step": 443062, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1675193309783936, "global_step": 443063, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0676064491271973, "global_step": 443064, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0924949645996094, "global_step": 443065, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9608968496322632, "global_step": 443066, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.014124631881714, "global_step": 443067, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0903284549713135, "global_step": 443068, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0777392387390137, "global_step": 443069, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.120576858520508, "global_step": 443070, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.05788516998291, "global_step": 443071, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.042795419692993, "global_step": 443072, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9976757764816284, "global_step": 443073, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.139298677444458, "global_step": 443074, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0980005264282227, "global_step": 443075, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.065131187438965, "global_step": 443076, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.133711099624634, "global_step": 443077, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.108950614929199, "global_step": 443078, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.057835340499878, "global_step": 443079, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.038797616958618, "global_step": 443080, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9910495281219482, "global_step": 443081, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0623462200164795, "global_step": 443082, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0245819091796875, "global_step": 443083, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.060173988342285, "global_step": 443084, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0486655235290527, "global_step": 443085, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.117417335510254, "global_step": 443086, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0691394805908203, "global_step": 443087, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0858707427978516, "global_step": 443088, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0332980155944824, "global_step": 443089, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.094953775405884, "global_step": 443090, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.05012845993042, "global_step": 443091, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.050379991531372, "global_step": 443092, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1506195068359375, "global_step": 443093, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.083883762359619, "global_step": 443094, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.055452346801758, "global_step": 443095, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0989158153533936, "global_step": 443096, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1176867485046387, "global_step": 443097, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0638577938079834, "global_step": 443098, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1201012134552, "global_step": 443099, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0880675315856934, "global_step": 443100, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0428409576416016, "global_step": 443101, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.123295783996582, "global_step": 443102, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.046729326248169, "global_step": 443103, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0350868701934814, "global_step": 443104, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9888859987258911, "global_step": 443105, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9863269329071045, "global_step": 443106, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0185093879699707, "global_step": 443107, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0626060962677, "global_step": 443108, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.093688726425171, "global_step": 443109, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.122602939605713, "global_step": 443110, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.012040138244629, "global_step": 443111, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0833640098571777, "global_step": 443112, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.081798791885376, "global_step": 443113, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1020050048828125, "global_step": 443114, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0735604763031006, "global_step": 443115, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0870938301086426, "global_step": 443116, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0766353607177734, "global_step": 443117, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.119274139404297, "global_step": 443118, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0391759872436523, "global_step": 443119, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0973689556121826, "global_step": 443120, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.06221866607666, "global_step": 443121, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0841140747070312, "global_step": 443122, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.052065134048462, "global_step": 443123, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.039113998413086, "global_step": 443124, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.093708038330078, "global_step": 443125, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0884246826171875, "global_step": 443126, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9609895944595337, "global_step": 443127, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0347042083740234, "global_step": 443128, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1479833126068115, "global_step": 443129, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0285086631774902, "global_step": 443130, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9531149864196777, "global_step": 443131, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.113211154937744, "global_step": 443132, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0481557846069336, "global_step": 443133, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.038276195526123, "global_step": 443134, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1204800605773926, "global_step": 443135, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0549886226654053, "global_step": 443136, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1099307537078857, "global_step": 443137, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.122410774230957, "global_step": 443138, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1327321529388428, "global_step": 443139, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.093153238296509, "global_step": 443140, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0375545024871826, "global_step": 443141, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.098433256149292, "global_step": 443142, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.094651460647583, "global_step": 443143, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.107405662536621, "global_step": 443144, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9812613725662231, "global_step": 443145, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0775904655456543, "global_step": 443146, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.04172682762146, "global_step": 443147, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9760236740112305, "global_step": 443148, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0508835315704346, "global_step": 443149, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.091064453125, "global_step": 443150, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.043513298034668, "global_step": 443151, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.136129379272461, "global_step": 443152, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.062767267227173, "global_step": 443153, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9643805027008057, "global_step": 443154, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0297486782073975, "global_step": 443155, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.074061632156372, "global_step": 443156, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0044360160827637, "global_step": 443157, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1068685054779053, "global_step": 443158, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.138596296310425, "global_step": 443159, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.083829402923584, "global_step": 443160, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.024477005004883, "global_step": 443161, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0853660106658936, "global_step": 443162, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.022352933883667, "global_step": 443163, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1410768032073975, "global_step": 443164, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.100393056869507, "global_step": 443165, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0274817943573, "global_step": 443166, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0765411853790283, "global_step": 443167, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0360772609710693, "global_step": 443168, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.062011241912842, "global_step": 443169, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1314032077789307, "global_step": 443170, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1621997356414795, "global_step": 443171, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0740230083465576, "global_step": 443172, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.117828369140625, "global_step": 443173, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1138150691986084, "global_step": 443174, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.191988468170166, "global_step": 443175, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.095524549484253, "global_step": 443176, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0967562198638916, "global_step": 443177, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0208375453948975, "global_step": 443178, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.085829019546509, "global_step": 443179, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1073191165924072, "global_step": 443180, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1302058696746826, "global_step": 443181, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0523674488067627, "global_step": 443182, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0611824989318848, "global_step": 443183, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.96414315700531, "global_step": 443184, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1002161502838135, "global_step": 443185, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0243473052978516, "global_step": 443186, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1106553077697754, "global_step": 443187, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0779638290405273, "global_step": 443188, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.031425952911377, "global_step": 443189, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.063655138015747, "global_step": 443190, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.050494432449341, "global_step": 443191, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1319472789764404, "global_step": 443192, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0564138889312744, "global_step": 443193, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1748664379119873, "global_step": 443194, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0081615447998047, "global_step": 443195, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0899622440338135, "global_step": 443196, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0521504878997803, "global_step": 443197, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0303730964660645, "global_step": 443198, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0431902408599854, "global_step": 443199, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0647122859954834, "global_step": 443200, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1317989826202393, "global_step": 443201, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0482945442199707, "global_step": 443202, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0313916206359863, "global_step": 443203, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0401406288146973, "global_step": 443204, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.07327938079834, "global_step": 443205, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0489084720611572, "global_step": 443206, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0058112144470215, "global_step": 443207, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.047635078430176, "global_step": 443208, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.146130084991455, "global_step": 443209, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0423901081085205, "global_step": 443210, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.109788656234741, "global_step": 443211, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0989203453063965, "global_step": 443212, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0823910236358643, "global_step": 443213, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0420849323272705, "global_step": 443214, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1511483192443848, "global_step": 443215, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.073627471923828, "global_step": 443216, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0829296112060547, "global_step": 443217, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.020561456680298, "global_step": 443218, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0668323040008545, "global_step": 443219, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1050119400024414, "global_step": 443220, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1102137565612793, "global_step": 443221, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0745015144348145, "global_step": 443222, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0630528926849365, "global_step": 443223, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0722334384918213, "global_step": 443224, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.13913631439209, "global_step": 443225, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0494155883789062, "global_step": 443226, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9927546977996826, "global_step": 443227, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0962886810302734, "global_step": 443228, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.988286018371582, "global_step": 443229, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9764060974121094, "global_step": 443230, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0352535247802734, "global_step": 443231, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.091047525405884, "global_step": 443232, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1040761470794678, "global_step": 443233, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.14262318611145, "global_step": 443234, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.095475673675537, "global_step": 443235, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.099605083465576, "global_step": 443236, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0703041553497314, "global_step": 443237, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0374324321746826, "global_step": 443238, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1371428966522217, "global_step": 443239, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9772047996520996, "global_step": 443240, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0788726806640625, "global_step": 443241, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0523264408111572, "global_step": 443242, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1084935665130615, "global_step": 443243, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1518166065216064, "global_step": 443244, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.113384962081909, "global_step": 443245, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0199508666992188, "global_step": 443246, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.055206537246704, "global_step": 443247, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0497756004333496, "global_step": 443248, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.100917339324951, "global_step": 443249, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1477975845336914, "global_step": 443250, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9919443130493164, "global_step": 443251, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.005349636077881, "global_step": 443252, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0792856216430664, "global_step": 443253, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1303634643554688, "global_step": 443254, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0808794498443604, "global_step": 443255, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.030937433242798, "global_step": 443256, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.021733522415161, "global_step": 443257, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.06318998336792, "global_step": 443258, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0547707080841064, "global_step": 443259, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1117775440216064, "global_step": 443260, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0217957496643066, "global_step": 443261, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0207431316375732, "global_step": 443262, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0427231788635254, "global_step": 443263, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1046252250671387, "global_step": 443264, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1094024181365967, "global_step": 443265, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0112862586975098, "global_step": 443266, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0636587142944336, "global_step": 443267, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.037843704223633, "global_step": 443268, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.034792900085449, "global_step": 443269, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1546366214752197, "global_step": 443270, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1275198459625244, "global_step": 443271, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0626914501190186, "global_step": 443272, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.103517770767212, "global_step": 443273, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0987870693206787, "global_step": 443274, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.079838991165161, "global_step": 443275, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0170087814331055, "global_step": 443276, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1023011207580566, "global_step": 443277, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9691683053970337, "global_step": 443278, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.078920841217041, "global_step": 443279, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1521239280700684, "global_step": 443280, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0359792709350586, "global_step": 443281, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1304550170898438, "global_step": 443282, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.085775375366211, "global_step": 443283, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0820422172546387, "global_step": 443284, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0500757694244385, "global_step": 443285, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0288026332855225, "global_step": 443286, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.065983295440674, "global_step": 443287, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0792133808135986, "global_step": 443288, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0744423866271973, "global_step": 443289, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0109310150146484, "global_step": 443290, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.11108136177063, "global_step": 443291, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9977495670318604, "global_step": 443292, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.045095920562744, "global_step": 443293, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.041638135910034, "global_step": 443294, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.086446523666382, "global_step": 443295, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.076836109161377, "global_step": 443296, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0709831714630127, "global_step": 443297, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.152301549911499, "global_step": 443298, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.073185682296753, "global_step": 443299, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0550525188446045, "global_step": 443300, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0836007595062256, "global_step": 443301, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0129153728485107, "global_step": 443302, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.122764825820923, "global_step": 443303, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1278440952301025, "global_step": 443304, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9672906398773193, "global_step": 443305, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.063657760620117, "global_step": 443306, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1673762798309326, "global_step": 443307, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0834176540374756, "global_step": 443308, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0511362552642822, "global_step": 443309, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1487720012664795, "global_step": 443310, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0643908977508545, "global_step": 443311, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.092076063156128, "global_step": 443312, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0378434658050537, "global_step": 443313, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.034693956375122, "global_step": 443314, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9899498224258423, "global_step": 443315, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.051654100418091, "global_step": 443316, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.981898307800293, "global_step": 443317, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.030245304107666, "global_step": 443318, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.113346815109253, "global_step": 443319, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0615012645721436, "global_step": 443320, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0423338413238525, "global_step": 443321, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.017526865005493, "global_step": 443322, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0327677726745605, "global_step": 443323, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1115567684173584, "global_step": 443324, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0888051986694336, "global_step": 443325, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1136672496795654, "global_step": 443326, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1370131969451904, "global_step": 443327, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.118635416030884, "global_step": 443328, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.084596633911133, "global_step": 443329, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0405073165893555, "global_step": 443330, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.076368808746338, "global_step": 443331, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.046511173248291, "global_step": 443332, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.051706552505493, "global_step": 443333, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.106614589691162, "global_step": 443334, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.056222915649414, "global_step": 443335, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0266997814178467, "global_step": 443336, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.045511484146118, "global_step": 443337, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0446865558624268, "global_step": 443338, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0972020626068115, "global_step": 443339, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1294798851013184, "global_step": 443340, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.137583017349243, "global_step": 443341, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0529208183288574, "global_step": 443342, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.123575448989868, "global_step": 443343, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1257834434509277, "global_step": 443344, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.027174711227417, "global_step": 443345, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9962098598480225, "global_step": 443346, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1482765674591064, "global_step": 443347, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0272791385650635, "global_step": 443348, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.002053737640381, "global_step": 443349, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9973374605178833, "global_step": 443350, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9731802940368652, "global_step": 443351, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0234272480010986, "global_step": 443352, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.034390449523926, "global_step": 443353, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1233208179473877, "global_step": 443354, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9838263988494873, "global_step": 443355, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0215585231781006, "global_step": 443356, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.002068519592285, "global_step": 443357, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.026827812194824, "global_step": 443358, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.045351028442383, "global_step": 443359, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0456037521362305, "global_step": 443360, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0883755683898926, "global_step": 443361, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.029127836227417, "global_step": 443362, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0249428749084473, "global_step": 443363, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.091191053390503, "global_step": 443364, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0644009113311768, "global_step": 443365, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.10601544380188, "global_step": 443366, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1319692134857178, "global_step": 443367, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.088371753692627, "global_step": 443368, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1272196769714355, "global_step": 443369, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.042832612991333, "global_step": 443370, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0067756175994873, "global_step": 443371, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0756561756134033, "global_step": 443372, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1370861530303955, "global_step": 443373, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1525955200195312, "global_step": 443374, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.078148126602173, "global_step": 443375, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9730483293533325, "global_step": 443376, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1171579360961914, "global_step": 443377, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0730514526367188, "global_step": 443378, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0694844722747803, "global_step": 443379, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0822644233703613, "global_step": 443380, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0156219005584717, "global_step": 443381, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1844539642333984, "global_step": 443382, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9998111724853516, "global_step": 443383, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.094632625579834, "global_step": 443384, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1112916469573975, "global_step": 443385, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.097571849822998, "global_step": 443386, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.086217164993286, "global_step": 443387, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0464906692504883, "global_step": 443388, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0923328399658203, "global_step": 443389, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1160969734191895, "global_step": 443390, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0646615028381348, "global_step": 443391, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.014122724533081, "global_step": 443392, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1184990406036377, "global_step": 443393, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0805113315582275, "global_step": 443394, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.084871292114258, "global_step": 443395, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0250680446624756, "global_step": 443396, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1328601837158203, "global_step": 443397, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.133082628250122, "global_step": 443398, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0445187091827393, "global_step": 443399, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1417236328125, "global_step": 443400, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.084186553955078, "global_step": 443401, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1059718132019043, "global_step": 443402, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0770344734191895, "global_step": 443403, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.10508394241333, "global_step": 443404, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.067918062210083, "global_step": 443405, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1101279258728027, "global_step": 443406, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.093865156173706, "global_step": 443407, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.036954879760742, "global_step": 443408, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0395541191101074, "global_step": 443409, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1188771724700928, "global_step": 443410, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1464903354644775, "global_step": 443411, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.054007053375244, "global_step": 443412, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0998928546905518, "global_step": 443413, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.132856845855713, "global_step": 443414, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1138529777526855, "global_step": 443415, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.118069887161255, "global_step": 443416, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0532193183898926, "global_step": 443417, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0692427158355713, "global_step": 443418, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1069891452789307, "global_step": 443419, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0551912784576416, "global_step": 443420, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.082270860671997, "global_step": 443421, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0883865356445312, "global_step": 443422, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0866806507110596, "global_step": 443423, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1891040802001953, "global_step": 443424, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.153623104095459, "global_step": 443425, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.030592679977417, "global_step": 443426, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1043622493743896, "global_step": 443427, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.101827621459961, "global_step": 443428, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.040076494216919, "global_step": 443429, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1758813858032227, "global_step": 443430, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0665206909179688, "global_step": 443431, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1830904483795166, "global_step": 443432, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0996744632720947, "global_step": 443433, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.02584171295166, "global_step": 443434, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.165343999862671, "global_step": 443435, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0756478309631348, "global_step": 443436, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.132503032684326, "global_step": 443437, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0668792724609375, "global_step": 443438, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0654850006103516, "global_step": 443439, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.071864366531372, "global_step": 443440, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.112990617752075, "global_step": 443441, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.055236577987671, "global_step": 443442, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.097475528717041, "global_step": 443443, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.06036114692688, "global_step": 443444, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.104827880859375, "global_step": 443445, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.076122999191284, "global_step": 443446, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.10579252243042, "global_step": 443447, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0747902393341064, "global_step": 443448, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9932197332382202, "global_step": 443449, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.119859457015991, "global_step": 443450, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.116755962371826, "global_step": 443451, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1173830032348633, "global_step": 443452, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1129519939422607, "global_step": 443453, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0609681606292725, "global_step": 443454, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.013063430786133, "global_step": 443455, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0327961444854736, "global_step": 443456, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.079692840576172, "global_step": 443457, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.086829423904419, "global_step": 443458, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1089975833892822, "global_step": 443459, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.067028522491455, "global_step": 443460, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0723307132720947, "global_step": 443461, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0552587509155273, "global_step": 443462, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0288615226745605, "global_step": 443463, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0749025344848633, "global_step": 443464, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0749142169952393, "global_step": 443465, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1039321422576904, "global_step": 443466, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0079920291900635, "global_step": 443467, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.100590229034424, "global_step": 443468, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.051156520843506, "global_step": 443469, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.089533567428589, "global_step": 443470, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0783379077911377, "global_step": 443471, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0710818767547607, "global_step": 443472, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.111806869506836, "global_step": 443473, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.032930612564087, "global_step": 443474, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.109416961669922, "global_step": 443475, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9568815231323242, "global_step": 443476, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1014912128448486, "global_step": 443477, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.038928747177124, "global_step": 443478, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.026912212371826, "global_step": 443479, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.023916721343994, "global_step": 443480, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.066588878631592, "global_step": 443481, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.044766902923584, "global_step": 443482, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.050171375274658, "global_step": 443483, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.975026249885559, "global_step": 443484, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0364274978637695, "global_step": 443485, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1146352291107178, "global_step": 443486, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.074608325958252, "global_step": 443487, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0853142738342285, "global_step": 443488, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.10662841796875, "global_step": 443489, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.054734230041504, "global_step": 443490, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1204464435577393, "global_step": 443491, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.032562494277954, "global_step": 443492, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.029981851577759, "global_step": 443493, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0850846767425537, "global_step": 443494, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0880286693573, "global_step": 443495, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0485644340515137, "global_step": 443496, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.160160541534424, "global_step": 443497, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1089606285095215, "global_step": 443498, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.095590591430664, "global_step": 443499, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0853703022003174, "global_step": 443500, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.071007251739502, "global_step": 443501, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9778728485107422, "global_step": 443502, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.060941696166992, "global_step": 443503, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.035637378692627, "global_step": 443504, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.046740770339966, "global_step": 443505, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.065460443496704, "global_step": 443506, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.058640480041504, "global_step": 443507, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0623795986175537, "global_step": 443508, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.080148220062256, "global_step": 443509, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0967204570770264, "global_step": 443510, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.128380537033081, "global_step": 443511, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0671982765197754, "global_step": 443512, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.04093861579895, "global_step": 443513, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.091007709503174, "global_step": 443514, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9904673099517822, "global_step": 443515, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1148109436035156, "global_step": 443516, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.062452554702759, "global_step": 443517, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.092966318130493, "global_step": 443518, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0285303592681885, "global_step": 443519, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0957982540130615, "global_step": 443520, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0727291107177734, "global_step": 443521, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1267547607421875, "global_step": 443522, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.037531614303589, "global_step": 443523, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0445237159729004, "global_step": 443524, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.058971643447876, "global_step": 443525, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.078068494796753, "global_step": 443526, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1703457832336426, "global_step": 443527, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.019529104232788, "global_step": 443528, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1135940551757812, "global_step": 443529, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0975229740142822, "global_step": 443530, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1208715438842773, "global_step": 443531, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0866858959198, "global_step": 443532, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0857088565826416, "global_step": 443533, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0341622829437256, "global_step": 443534, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0817039012908936, "global_step": 443535, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.048046827316284, "global_step": 443536, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1260671615600586, "global_step": 443537, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0293850898742676, "global_step": 443538, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1018364429473877, "global_step": 443539, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0993473529815674, "global_step": 443540, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0791513919830322, "global_step": 443541, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1280434131622314, "global_step": 443542, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0076744556427, "global_step": 443543, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.059896469116211, "global_step": 443544, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0433452129364014, "global_step": 443545, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.060713291168213, "global_step": 443546, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9828346967697144, "global_step": 443547, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.036201238632202, "global_step": 443548, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1195900440216064, "global_step": 443549, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0396432876586914, "global_step": 443550, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1603662967681885, "global_step": 443551, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.107240676879883, "global_step": 443552, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0786170959472656, "global_step": 443553, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1814568042755127, "global_step": 443554, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0867605209350586, "global_step": 443555, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.045053243637085, "global_step": 443556, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0566580295562744, "global_step": 443557, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.065807819366455, "global_step": 443558, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0698702335357666, "global_step": 443559, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0003859996795654, "global_step": 443560, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1345810890197754, "global_step": 443561, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1392087936401367, "global_step": 443562, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.024216890335083, "global_step": 443563, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1351728439331055, "global_step": 443564, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0828073024749756, "global_step": 443565, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0542995929718018, "global_step": 443566, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0709569454193115, "global_step": 443567, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.135294198989868, "global_step": 443568, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1019182205200195, "global_step": 443569, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.966249704360962, "global_step": 443570, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0666773319244385, "global_step": 443571, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.053205728530884, "global_step": 443572, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.143822193145752, "global_step": 443573, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.169222354888916, "global_step": 443574, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0202572345733643, "global_step": 443575, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0280890464782715, "global_step": 443576, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0815303325653076, "global_step": 443577, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0823922157287598, "global_step": 443578, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0546157360076904, "global_step": 443579, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1214797496795654, "global_step": 443580, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.070406436920166, "global_step": 443581, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1380374431610107, "global_step": 443582, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0287890434265137, "global_step": 443583, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.073582887649536, "global_step": 443584, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.131459951400757, "global_step": 443585, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.112884759902954, "global_step": 443586, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.095606803894043, "global_step": 443587, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.063849449157715, "global_step": 443588, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1040937900543213, "global_step": 443589, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.037598133087158, "global_step": 443590, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1752688884735107, "global_step": 443591, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.08306622505188, "global_step": 443592, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1228432655334473, "global_step": 443593, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0402612686157227, "global_step": 443594, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1350533962249756, "global_step": 443595, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0886402130126953, "global_step": 443596, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1222760677337646, "global_step": 443597, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0802602767944336, "global_step": 443598, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.079836130142212, "global_step": 443599, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.133991241455078, "global_step": 443600, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.139763116836548, "global_step": 443601, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.103576898574829, "global_step": 443602, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1531808376312256, "global_step": 443603, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0900650024414062, "global_step": 443604, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.131033182144165, "global_step": 443605, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.108351469039917, "global_step": 443606, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.062424421310425, "global_step": 443607, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0894830226898193, "global_step": 443608, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.028179883956909, "global_step": 443609, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.124666213989258, "global_step": 443610, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1113131046295166, "global_step": 443611, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.092745304107666, "global_step": 443612, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.093646764755249, "global_step": 443613, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0494964122772217, "global_step": 443614, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.064354658126831, "global_step": 443615, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0847785472869873, "global_step": 443616, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1024022102355957, "global_step": 443617, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0876166820526123, "global_step": 443618, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1242177486419678, "global_step": 443619, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.037518262863159, "global_step": 443620, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0906994342803955, "global_step": 443621, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.061659574508667, "global_step": 443622, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.013258457183838, "global_step": 443623, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0126330852508545, "global_step": 443624, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1157398223876953, "global_step": 443625, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.114365339279175, "global_step": 443626, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0922226905822754, "global_step": 443627, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1221201419830322, "global_step": 443628, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0598690509796143, "global_step": 443629, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.2007625102996826, "global_step": 443630, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0640716552734375, "global_step": 443631, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0582399368286133, "global_step": 443632, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.169835090637207, "global_step": 443633, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.102138042449951, "global_step": 443634, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1180191040039062, "global_step": 443635, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0985021591186523, "global_step": 443636, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1149635314941406, "global_step": 443637, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0312297344207764, "global_step": 443638, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0977232456207275, "global_step": 443639, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.128960371017456, "global_step": 443640, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.085009813308716, "global_step": 443641, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0019619464874268, "global_step": 443642, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0749592781066895, "global_step": 443643, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.096792459487915, "global_step": 443644, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0328257083892822, "global_step": 443645, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0011870861053467, "global_step": 443646, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.057488203048706, "global_step": 443647, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.032292366027832, "global_step": 443648, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1289117336273193, "global_step": 443649, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.10215163230896, "global_step": 443650, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0303680896759033, "global_step": 443651, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0853967666625977, "global_step": 443652, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.077613592147827, "global_step": 443653, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1168875694274902, "global_step": 443654, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0261900424957275, "global_step": 443655, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.063340187072754, "global_step": 443656, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.059751510620117, "global_step": 443657, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.103549003601074, "global_step": 443658, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9847595691680908, "global_step": 443659, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.055418014526367, "global_step": 443660, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0085952281951904, "global_step": 443661, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.05722975730896, "global_step": 443662, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.042741537094116, "global_step": 443663, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1057288646698, "global_step": 443664, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0764875411987305, "global_step": 443665, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1714489459991455, "global_step": 443666, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.063168525695801, "global_step": 443667, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.06744122505188, "global_step": 443668, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0973100662231445, "global_step": 443669, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.135833978652954, "global_step": 443670, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.075378894805908, "global_step": 443671, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.124983310699463, "global_step": 443672, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0939037799835205, "global_step": 443673, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.11356782913208, "global_step": 443674, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.115243673324585, "global_step": 443675, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0971150398254395, "global_step": 443676, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.130337715148926, "global_step": 443677, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.964881181716919, "global_step": 443678, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.112898588180542, "global_step": 443679, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.075486898422241, "global_step": 443680, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.128803253173828, "global_step": 443681, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0660276412963867, "global_step": 443682, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1033618450164795, "global_step": 443683, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1057968139648438, "global_step": 443684, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.119337558746338, "global_step": 443685, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0574958324432373, "global_step": 443686, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1023852825164795, "global_step": 443687, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1516308784484863, "global_step": 443688, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.059640407562256, "global_step": 443689, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1299808025360107, "global_step": 443690, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0851333141326904, "global_step": 443691, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1386637687683105, "global_step": 443692, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0384650230407715, "global_step": 443693, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0409722328186035, "global_step": 443694, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.129253387451172, "global_step": 443695, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0377869606018066, "global_step": 443696, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.096684455871582, "global_step": 443697, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1542177200317383, "global_step": 443698, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.130028009414673, "global_step": 443699, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1078765392303467, "global_step": 443700, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0891833305358887, "global_step": 443701, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9402186870574951, "global_step": 443702, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0571022033691406, "global_step": 443703, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0542149543762207, "global_step": 443704, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.037694215774536, "global_step": 443705, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0918383598327637, "global_step": 443706, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0968573093414307, "global_step": 443707, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0236165523529053, "global_step": 443708, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.111579656600952, "global_step": 443709, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.155611515045166, "global_step": 443710, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1513478755950928, "global_step": 443711, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.121032238006592, "global_step": 443712, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.024963855743408, "global_step": 443713, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.089245080947876, "global_step": 443714, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.081293821334839, "global_step": 443715, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1052064895629883, "global_step": 443716, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9994539022445679, "global_step": 443717, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.097912549972534, "global_step": 443718, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0868492126464844, "global_step": 443719, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.053410291671753, "global_step": 443720, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.025874614715576, "global_step": 443721, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9919953346252441, "global_step": 443722, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.118778705596924, "global_step": 443723, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.001220941543579, "global_step": 443724, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.141476631164551, "global_step": 443725, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1137475967407227, "global_step": 443726, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1905710697174072, "global_step": 443727, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.121284246444702, "global_step": 443728, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0353281497955322, "global_step": 443729, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.000465154647827, "global_step": 443730, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1513898372650146, "global_step": 443731, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1056270599365234, "global_step": 443732, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0542521476745605, "global_step": 443733, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.035766363143921, "global_step": 443734, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1300978660583496, "global_step": 443735, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1173617839813232, "global_step": 443736, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.038818597793579, "global_step": 443737, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.064927577972412, "global_step": 443738, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.141511917114258, "global_step": 443739, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0595715045928955, "global_step": 443740, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0475289821624756, "global_step": 443741, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0347347259521484, "global_step": 443742, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1503732204437256, "global_step": 443743, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1132137775421143, "global_step": 443744, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.139111280441284, "global_step": 443745, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1269638538360596, "global_step": 443746, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0833098888397217, "global_step": 443747, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.055448532104492, "global_step": 443748, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1360323429107666, "global_step": 443749, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0379230976104736, "global_step": 443750, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0423834323883057, "global_step": 443751, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.094717502593994, "global_step": 443752, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9923113584518433, "global_step": 443753, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.10074782371521, "global_step": 443754, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1365742683410645, "global_step": 443755, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.062239170074463, "global_step": 443756, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0453367233276367, "global_step": 443757, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0582752227783203, "global_step": 443758, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0759096145629883, "global_step": 443759, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0539591312408447, "global_step": 443760, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0082147121429443, "global_step": 443761, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1354384422302246, "global_step": 443762, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0586447715759277, "global_step": 443763, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.139906644821167, "global_step": 443764, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1274020671844482, "global_step": 443765, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0923712253570557, "global_step": 443766, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0458829402923584, "global_step": 443767, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1088147163391113, "global_step": 443768, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1375677585601807, "global_step": 443769, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0793368816375732, "global_step": 443770, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1319806575775146, "global_step": 443771, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.01509165763855, "global_step": 443772, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1485376358032227, "global_step": 443773, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0178818702697754, "global_step": 443774, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.2042760848999023, "global_step": 443775, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0917978286743164, "global_step": 443776, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.09584379196167, "global_step": 443777, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.123497486114502, "global_step": 443778, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1317172050476074, "global_step": 443779, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.094085216522217, "global_step": 443780, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0743699073791504, "global_step": 443781, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0880792140960693, "global_step": 443782, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.100294351577759, "global_step": 443783, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.053044557571411, "global_step": 443784, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1319682598114014, "global_step": 443785, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1536738872528076, "global_step": 443786, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1098432540893555, "global_step": 443787, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.207416296005249, "global_step": 443788, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1310932636260986, "global_step": 443789, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.108664035797119, "global_step": 443790, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0801808834075928, "global_step": 443791, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.070117712020874, "global_step": 443792, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0205674171447754, "global_step": 443793, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0519747734069824, "global_step": 443794, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0832672119140625, "global_step": 443795, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0602822303771973, "global_step": 443796, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0077223777770996, "global_step": 443797, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1837081909179688, "global_step": 443798, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0514683723449707, "global_step": 443799, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0349316596984863, "global_step": 443800, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1899752616882324, "global_step": 443801, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9990609884262085, "global_step": 443802, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0888922214508057, "global_step": 443803, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.120326519012451, "global_step": 443804, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1024415493011475, "global_step": 443805, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0030312538146973, "global_step": 443806, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0995867252349854, "global_step": 443807, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0561506748199463, "global_step": 443808, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.124689817428589, "global_step": 443809, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1228559017181396, "global_step": 443810, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.160567283630371, "global_step": 443811, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0622432231903076, "global_step": 443812, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0258266925811768, "global_step": 443813, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0207431316375732, "global_step": 443814, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1352546215057373, "global_step": 443815, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.086625337600708, "global_step": 443816, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0688624382019043, "global_step": 443817, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.055692434310913, "global_step": 443818, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.15396785736084, "global_step": 443819, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.142035722732544, "global_step": 443820, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1065659523010254, "global_step": 443821, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.17242693901062, "global_step": 443822, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1100337505340576, "global_step": 443823, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9802296161651611, "global_step": 443824, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0605461597442627, "global_step": 443825, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0938124656677246, "global_step": 443826, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.042163610458374, "global_step": 443827, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0581705570220947, "global_step": 443828, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.156489849090576, "global_step": 443829, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9978435039520264, "global_step": 443830, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0764245986938477, "global_step": 443831, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1453847885131836, "global_step": 443832, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.180962085723877, "global_step": 443833, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1025359630584717, "global_step": 443834, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.069606304168701, "global_step": 443835, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.041980743408203, "global_step": 443836, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.030768632888794, "global_step": 443837, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0539093017578125, "global_step": 443838, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.038788080215454, "global_step": 443839, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0719332695007324, "global_step": 443840, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.086972951889038, "global_step": 443841, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.137240171432495, "global_step": 443842, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1270437240600586, "global_step": 443843, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.114793539047241, "global_step": 443844, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.153374195098877, "global_step": 443845, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1244661808013916, "global_step": 443846, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.084925651550293, "global_step": 443847, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0787861347198486, "global_step": 443848, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.067760944366455, "global_step": 443849, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.018937587738037, "global_step": 443850, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1233091354370117, "global_step": 443851, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0188286304473877, "global_step": 443852, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0901622772216797, "global_step": 443853, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1286065578460693, "global_step": 443854, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.156282424926758, "global_step": 443855, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.110145330429077, "global_step": 443856, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.089642286300659, "global_step": 443857, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0533103942871094, "global_step": 443858, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9674153327941895, "global_step": 443859, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0857136249542236, "global_step": 443860, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0495407581329346, "global_step": 443861, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0764105319976807, "global_step": 443862, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0935511589050293, "global_step": 443863, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.110121250152588, "global_step": 443864, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.139275074005127, "global_step": 443865, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0983548164367676, "global_step": 443866, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0465822219848633, "global_step": 443867, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.171912908554077, "global_step": 443868, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.040055990219116, "global_step": 443869, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.082578659057617, "global_step": 443870, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1030778884887695, "global_step": 443871, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1392319202423096, "global_step": 443872, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9968007802963257, "global_step": 443873, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1953420639038086, "global_step": 443874, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.130422830581665, "global_step": 443875, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1091628074645996, "global_step": 443876, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0503106117248535, "global_step": 443877, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.144821882247925, "global_step": 443878, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1526994705200195, "global_step": 443879, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.099895477294922, "global_step": 443880, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1118814945220947, "global_step": 443881, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1300649642944336, "global_step": 443882, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.026553153991699, "global_step": 443883, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.17979097366333, "global_step": 443884, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.077125310897827, "global_step": 443885, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0275943279266357, "global_step": 443886, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.129528760910034, "global_step": 443887, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.038316249847412, "global_step": 443888, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.047419309616089, "global_step": 443889, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1013426780700684, "global_step": 443890, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0110669136047363, "global_step": 443891, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1557679176330566, "global_step": 443892, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.000066041946411, "global_step": 443893, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1044604778289795, "global_step": 443894, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1306166648864746, "global_step": 443895, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.980228066444397, "global_step": 443896, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0588607788085938, "global_step": 443897, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1118435859680176, "global_step": 443898, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0349984169006348, "global_step": 443899, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9947254657745361, "global_step": 443900, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.018935203552246, "global_step": 443901, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.004061698913574, "global_step": 443902, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0749588012695312, "global_step": 443903, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0910773277282715, "global_step": 443904, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0366501808166504, "global_step": 443905, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.01324725151062, "global_step": 443906, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1202552318573, "global_step": 443907, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0645744800567627, "global_step": 443908, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.12571120262146, "global_step": 443909, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.119119644165039, "global_step": 443910, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.087885618209839, "global_step": 443911, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0572328567504883, "global_step": 443912, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.106409788131714, "global_step": 443913, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.127467393875122, "global_step": 443914, "epoch": 807, "lr": 5e-05}
{"train_loss": 1.9814711809158325, "global_step": 443915, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.008500099182129, "global_step": 443916, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0756709575653076, "global_step": 443917, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.067941427230835, "global_step": 443918, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0783884525299072, "global_step": 443919, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1296610832214355, "global_step": 443920, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0966339111328125, "global_step": 443921, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0635485649108887, "global_step": 443922, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0583300590515137, "global_step": 443923, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.077387571334839, "global_step": 443924, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.141303062438965, "global_step": 443925, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.016464948654175, "global_step": 443926, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.112142324447632, "global_step": 443927, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.063939332962036, "global_step": 443928, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0771846771240234, "global_step": 443929, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.1233301162719727, "global_step": 443930, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.086897373199463, "global_step": 443931, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.049539566040039, "global_step": 443932, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.040499210357666, "global_step": 443933, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.0767900943756104, "global_step": 443934, "epoch": 807, "lr": 5e-05}
{"train_loss": 2.083935260772705, "global_step": 443935, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0494987964630127, "global_step": 443936, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0658364295959473, "global_step": 443937, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.070241689682007, "global_step": 443938, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.111079216003418, "global_step": 443939, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0714614391326904, "global_step": 443940, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.031973123550415, "global_step": 443941, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.050245761871338, "global_step": 443942, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0744075775146484, "global_step": 443943, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.078198194503784, "global_step": 443944, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0299360752105713, "global_step": 443945, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.093339204788208, "global_step": 443946, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0871570110321045, "global_step": 443947, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9635605812072754, "global_step": 443948, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9802899360656738, "global_step": 443949, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.077058792114258, "global_step": 443950, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.019595146179199, "global_step": 443951, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.048537015914917, "global_step": 443952, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9546371698379517, "global_step": 443953, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.041318655014038, "global_step": 443954, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0514962673187256, "global_step": 443955, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9694186449050903, "global_step": 443956, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.003577709197998, "global_step": 443957, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0477819442749023, "global_step": 443958, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0938353538513184, "global_step": 443959, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1635313034057617, "global_step": 443960, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1898396015167236, "global_step": 443961, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.070676803588867, "global_step": 443962, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.005333185195923, "global_step": 443963, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.10310697555542, "global_step": 443964, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9624155759811401, "global_step": 443965, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9342021942138672, "global_step": 443966, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.02060866355896, "global_step": 443967, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1058123111724854, "global_step": 443968, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0524325370788574, "global_step": 443969, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.027963399887085, "global_step": 443970, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.120176076889038, "global_step": 443971, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.069880962371826, "global_step": 443972, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.060084581375122, "global_step": 443973, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.119880199432373, "global_step": 443974, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0272014141082764, "global_step": 443975, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.034385919570923, "global_step": 443976, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.119199275970459, "global_step": 443977, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.016533136367798, "global_step": 443978, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0993762016296387, "global_step": 443979, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.050102949142456, "global_step": 443980, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.111046552658081, "global_step": 443981, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.027909994125366, "global_step": 443982, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.054872512817383, "global_step": 443983, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0894644260406494, "global_step": 443984, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0953428745269775, "global_step": 443985, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.952568769454956, "global_step": 443986, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.016507148742676, "global_step": 443987, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.131488561630249, "global_step": 443988, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0377116203308105, "global_step": 443989, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1071362495422363, "global_step": 443990, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0681848526000977, "global_step": 443991, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.087800979614258, "global_step": 443992, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9871307611465454, "global_step": 443993, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0817949771881104, "global_step": 443994, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0881965160369873, "global_step": 443995, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0310654640197754, "global_step": 443996, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.025742292404175, "global_step": 443997, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.075556993484497, "global_step": 443998, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.067502975463867, "global_step": 443999, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1278634071350098, "global_step": 444000, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0467662811279297, "global_step": 444001, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0514144897460938, "global_step": 444002, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.141396999359131, "global_step": 444003, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.090414047241211, "global_step": 444004, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.022890329360962, "global_step": 444005, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0329389572143555, "global_step": 444006, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.055501937866211, "global_step": 444007, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0687928199768066, "global_step": 444008, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.07401967048645, "global_step": 444009, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.087202310562134, "global_step": 444010, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.106917142868042, "global_step": 444011, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.147378444671631, "global_step": 444012, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0106801986694336, "global_step": 444013, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1896278858184814, "global_step": 444014, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0511093139648438, "global_step": 444015, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0901243686676025, "global_step": 444016, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.036132335662842, "global_step": 444017, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.034125804901123, "global_step": 444018, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0645570755004883, "global_step": 444019, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0932438373565674, "global_step": 444020, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0947768688201904, "global_step": 444021, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0377182960510254, "global_step": 444022, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1569104194641113, "global_step": 444023, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.066784381866455, "global_step": 444024, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0430729389190674, "global_step": 444025, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.140496015548706, "global_step": 444026, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0971438884735107, "global_step": 444027, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0180468559265137, "global_step": 444028, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.047898769378662, "global_step": 444029, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0821139812469482, "global_step": 444030, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1291627883911133, "global_step": 444031, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.994261384010315, "global_step": 444032, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0588207244873047, "global_step": 444033, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1022443771362305, "global_step": 444034, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1211140155792236, "global_step": 444035, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1045758724212646, "global_step": 444036, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.056781768798828, "global_step": 444037, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.105760097503662, "global_step": 444038, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9944775104522705, "global_step": 444039, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.026137113571167, "global_step": 444040, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0513877868652344, "global_step": 444041, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.067464590072632, "global_step": 444042, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.051103115081787, "global_step": 444043, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1421852111816406, "global_step": 444044, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.121450662612915, "global_step": 444045, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.080829620361328, "global_step": 444046, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.101041316986084, "global_step": 444047, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0413365364074707, "global_step": 444048, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0606818199157715, "global_step": 444049, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0867369174957275, "global_step": 444050, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1133008003234863, "global_step": 444051, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0854971408843994, "global_step": 444052, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0072317123413086, "global_step": 444053, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.112452268600464, "global_step": 444054, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0308735370635986, "global_step": 444055, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0340030193328857, "global_step": 444056, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1176397800445557, "global_step": 444057, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.129281997680664, "global_step": 444058, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9968652725219727, "global_step": 444059, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.050687551498413, "global_step": 444060, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0119590759277344, "global_step": 444061, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1073172092437744, "global_step": 444062, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.157172203063965, "global_step": 444063, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.061758518218994, "global_step": 444064, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1061911582946777, "global_step": 444065, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.192349672317505, "global_step": 444066, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0067570209503174, "global_step": 444067, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.039707899093628, "global_step": 444068, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0869550704956055, "global_step": 444069, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0608015060424805, "global_step": 444070, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0592968463897705, "global_step": 444071, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0451345443725586, "global_step": 444072, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.105180501937866, "global_step": 444073, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1399707794189453, "global_step": 444074, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0966439247131348, "global_step": 444075, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0388834476470947, "global_step": 444076, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0916261672973633, "global_step": 444077, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9467638731002808, "global_step": 444078, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0453813076019287, "global_step": 444079, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.020357370376587, "global_step": 444080, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.178713083267212, "global_step": 444081, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.038593053817749, "global_step": 444082, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1260874271392822, "global_step": 444083, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.088273048400879, "global_step": 444084, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1245031356811523, "global_step": 444085, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9972621202468872, "global_step": 444086, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.032682180404663, "global_step": 444087, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1101059913635254, "global_step": 444088, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1291611194610596, "global_step": 444089, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.097170352935791, "global_step": 444090, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9996001720428467, "global_step": 444091, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0472536087036133, "global_step": 444092, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9769684076309204, "global_step": 444093, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0638015270233154, "global_step": 444094, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9840366840362549, "global_step": 444095, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0938050746917725, "global_step": 444096, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1523866653442383, "global_step": 444097, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.015418767929077, "global_step": 444098, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.959380865097046, "global_step": 444099, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0489749908447266, "global_step": 444100, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1247448921203613, "global_step": 444101, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.036567449569702, "global_step": 444102, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.127981424331665, "global_step": 444103, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.019273519515991, "global_step": 444104, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1151623725891113, "global_step": 444105, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.995800256729126, "global_step": 444106, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.102430582046509, "global_step": 444107, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0243754386901855, "global_step": 444108, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.020813226699829, "global_step": 444109, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.054015636444092, "global_step": 444110, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.081123113632202, "global_step": 444111, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0784921646118164, "global_step": 444112, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0655927658081055, "global_step": 444113, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.041677236557007, "global_step": 444114, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1716949939727783, "global_step": 444115, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9859851598739624, "global_step": 444116, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0373775959014893, "global_step": 444117, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0953316688537598, "global_step": 444118, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0777199268341064, "global_step": 444119, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.059495210647583, "global_step": 444120, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.052178144454956, "global_step": 444121, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0558910369873047, "global_step": 444122, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1453373432159424, "global_step": 444123, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.062683343887329, "global_step": 444124, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9980661869049072, "global_step": 444125, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.120793342590332, "global_step": 444126, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.021491289138794, "global_step": 444127, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.188061237335205, "global_step": 444128, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0421414375305176, "global_step": 444129, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0121939182281494, "global_step": 444130, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.033404588699341, "global_step": 444131, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1823065280914307, "global_step": 444132, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.041700601577759, "global_step": 444133, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0470211505889893, "global_step": 444134, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.146682024002075, "global_step": 444135, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0872511863708496, "global_step": 444136, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0348401069641113, "global_step": 444137, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1251614093780518, "global_step": 444138, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0114526748657227, "global_step": 444139, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.101552963256836, "global_step": 444140, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0737056732177734, "global_step": 444141, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0731515884399414, "global_step": 444142, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0921976566314697, "global_step": 444143, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9969508647918701, "global_step": 444144, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.077505350112915, "global_step": 444145, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0753109455108643, "global_step": 444146, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.095440626144409, "global_step": 444147, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1101584434509277, "global_step": 444148, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.088361978530884, "global_step": 444149, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0600337982177734, "global_step": 444150, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1019656658172607, "global_step": 444151, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1110424995422363, "global_step": 444152, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0173423290252686, "global_step": 444153, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.061704397201538, "global_step": 444154, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0637359619140625, "global_step": 444155, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1112725734710693, "global_step": 444156, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.115159034729004, "global_step": 444157, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.031139850616455, "global_step": 444158, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9810534715652466, "global_step": 444159, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0207626819610596, "global_step": 444160, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.013150215148926, "global_step": 444161, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9880872964859009, "global_step": 444162, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.027141809463501, "global_step": 444163, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.001850128173828, "global_step": 444164, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9936360120773315, "global_step": 444165, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.117220878601074, "global_step": 444166, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0037083625793457, "global_step": 444167, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0175440311431885, "global_step": 444168, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.020254135131836, "global_step": 444169, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.071059465408325, "global_step": 444170, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0168673992156982, "global_step": 444171, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.15679931640625, "global_step": 444172, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1242921352386475, "global_step": 444173, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0327553749084473, "global_step": 444174, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.053194522857666, "global_step": 444175, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1587893962860107, "global_step": 444176, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.092099905014038, "global_step": 444177, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1695351600646973, "global_step": 444178, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.115163803100586, "global_step": 444179, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.152832508087158, "global_step": 444180, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.056058168411255, "global_step": 444181, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0439412593841553, "global_step": 444182, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.126765251159668, "global_step": 444183, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1292402744293213, "global_step": 444184, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0655033588409424, "global_step": 444185, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0528926849365234, "global_step": 444186, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.09423828125, "global_step": 444187, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1151247024536133, "global_step": 444188, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.151024341583252, "global_step": 444189, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.2259674072265625, "global_step": 444190, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1028974056243896, "global_step": 444191, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.125936508178711, "global_step": 444192, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0333492755889893, "global_step": 444193, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.151973247528076, "global_step": 444194, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.108339548110962, "global_step": 444195, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0779881477355957, "global_step": 444196, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.009887933731079, "global_step": 444197, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.042614221572876, "global_step": 444198, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.037588119506836, "global_step": 444199, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0491232872009277, "global_step": 444200, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.077481508255005, "global_step": 444201, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9920282363891602, "global_step": 444202, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0317583084106445, "global_step": 444203, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0627942085266113, "global_step": 444204, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.027557849884033, "global_step": 444205, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0756194591522217, "global_step": 444206, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0952951908111572, "global_step": 444207, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0809803009033203, "global_step": 444208, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1120572090148926, "global_step": 444209, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.045747756958008, "global_step": 444210, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0762619972229004, "global_step": 444211, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.053837299346924, "global_step": 444212, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.05710768699646, "global_step": 444213, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0278522968292236, "global_step": 444214, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0707504749298096, "global_step": 444215, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1499812602996826, "global_step": 444216, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0742883682250977, "global_step": 444217, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1386730670928955, "global_step": 444218, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.02370285987854, "global_step": 444219, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1148123741149902, "global_step": 444220, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.073925256729126, "global_step": 444221, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1497297286987305, "global_step": 444222, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0477089881896973, "global_step": 444223, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0397205352783203, "global_step": 444224, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0149216651916504, "global_step": 444225, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.061614513397217, "global_step": 444226, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0157763957977295, "global_step": 444227, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1558024883270264, "global_step": 444228, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.059155225753784, "global_step": 444229, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0363576412200928, "global_step": 444230, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0179731845855713, "global_step": 444231, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1033010482788086, "global_step": 444232, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.10067081451416, "global_step": 444233, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.123305082321167, "global_step": 444234, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0100393295288086, "global_step": 444235, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.078023672103882, "global_step": 444236, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1263365745544434, "global_step": 444237, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1107401847839355, "global_step": 444238, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1000633239746094, "global_step": 444239, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1721761226654053, "global_step": 444240, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.023493528366089, "global_step": 444241, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.047504425048828, "global_step": 444242, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0783419609069824, "global_step": 444243, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0333733558654785, "global_step": 444244, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0818495750427246, "global_step": 444245, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9996455907821655, "global_step": 444246, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0997846126556396, "global_step": 444247, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0367088317871094, "global_step": 444248, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1823205947875977, "global_step": 444249, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0823280811309814, "global_step": 444250, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.05790376663208, "global_step": 444251, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.056800365447998, "global_step": 444252, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.012418270111084, "global_step": 444253, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0935304164886475, "global_step": 444254, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.00457763671875, "global_step": 444255, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0904970169067383, "global_step": 444256, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1206068992614746, "global_step": 444257, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0291850566864014, "global_step": 444258, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1374459266662598, "global_step": 444259, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0438320636749268, "global_step": 444260, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0580039024353027, "global_step": 444261, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.129004716873169, "global_step": 444262, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.109182834625244, "global_step": 444263, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0736470222473145, "global_step": 444264, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.046621799468994, "global_step": 444265, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1187565326690674, "global_step": 444266, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.042003870010376, "global_step": 444267, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0279147624969482, "global_step": 444268, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0153939723968506, "global_step": 444269, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0187125205993652, "global_step": 444270, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.083195447921753, "global_step": 444271, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0754575729370117, "global_step": 444272, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0719094276428223, "global_step": 444273, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0864450931549072, "global_step": 444274, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1022250652313232, "global_step": 444275, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0182645320892334, "global_step": 444276, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.023861885070801, "global_step": 444277, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0531675815582275, "global_step": 444278, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0036144256591797, "global_step": 444279, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0818939208984375, "global_step": 444280, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1212799549102783, "global_step": 444281, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1781458854675293, "global_step": 444282, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1537253856658936, "global_step": 444283, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.098661422729492, "global_step": 444284, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0506107807159424, "global_step": 444285, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0593044757843018, "global_step": 444286, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.071078062057495, "global_step": 444287, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9908512830734253, "global_step": 444288, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.148256301879883, "global_step": 444289, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0649898052215576, "global_step": 444290, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0564706325531006, "global_step": 444291, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1047940254211426, "global_step": 444292, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0987367630004883, "global_step": 444293, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0441765785217285, "global_step": 444294, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.05814266204834, "global_step": 444295, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9633221626281738, "global_step": 444296, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0019991397857666, "global_step": 444297, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.121648073196411, "global_step": 444298, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.094195604324341, "global_step": 444299, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1171374320983887, "global_step": 444300, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0361123085021973, "global_step": 444301, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0442001819610596, "global_step": 444302, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0883426666259766, "global_step": 444303, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.091337203979492, "global_step": 444304, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1046040058135986, "global_step": 444305, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0816545486450195, "global_step": 444306, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0532562732696533, "global_step": 444307, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.033474922180176, "global_step": 444308, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0006186962127686, "global_step": 444309, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.052816152572632, "global_step": 444310, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1069719791412354, "global_step": 444311, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9781687259674072, "global_step": 444312, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.015646457672119, "global_step": 444313, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.068645715713501, "global_step": 444314, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.12221097946167, "global_step": 444315, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0499861240386963, "global_step": 444316, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1408071517944336, "global_step": 444317, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0314669609069824, "global_step": 444318, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.119053840637207, "global_step": 444319, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.112090587615967, "global_step": 444320, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0734541416168213, "global_step": 444321, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0484142303466797, "global_step": 444322, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.08756160736084, "global_step": 444323, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0277063846588135, "global_step": 444324, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1415038108825684, "global_step": 444325, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0425209999084473, "global_step": 444326, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.036853075027466, "global_step": 444327, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.158695697784424, "global_step": 444328, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.022618055343628, "global_step": 444329, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0740714073181152, "global_step": 444330, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.051800012588501, "global_step": 444331, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.049161195755005, "global_step": 444332, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0518672466278076, "global_step": 444333, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0864946842193604, "global_step": 444334, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.086618661880493, "global_step": 444335, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.03511381149292, "global_step": 444336, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.081111192703247, "global_step": 444337, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.096754550933838, "global_step": 444338, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.032384157180786, "global_step": 444339, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.03418231010437, "global_step": 444340, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.016017436981201, "global_step": 444341, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1413371562957764, "global_step": 444342, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.003941297531128, "global_step": 444343, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9886103868484497, "global_step": 444344, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.10204815864563, "global_step": 444345, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1761584281921387, "global_step": 444346, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.040215253829956, "global_step": 444347, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1044037342071533, "global_step": 444348, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.005563974380493, "global_step": 444349, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1231937408447266, "global_step": 444350, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1950738430023193, "global_step": 444351, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0837562084198, "global_step": 444352, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.130429267883301, "global_step": 444353, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.056647300720215, "global_step": 444354, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1157386302948, "global_step": 444355, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.047966718673706, "global_step": 444356, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.113598346710205, "global_step": 444357, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.054964780807495, "global_step": 444358, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1359758377075195, "global_step": 444359, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0033175945281982, "global_step": 444360, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9437541961669922, "global_step": 444361, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1049070358276367, "global_step": 444362, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1919851303100586, "global_step": 444363, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0958001613616943, "global_step": 444364, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.070816993713379, "global_step": 444365, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.136138916015625, "global_step": 444366, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.076753616333008, "global_step": 444367, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0813517570495605, "global_step": 444368, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0760657787323, "global_step": 444369, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1028077602386475, "global_step": 444370, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0757944583892822, "global_step": 444371, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.107597827911377, "global_step": 444372, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.078338623046875, "global_step": 444373, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9986697435379028, "global_step": 444374, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.024822950363159, "global_step": 444375, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.036090850830078, "global_step": 444376, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0318024158477783, "global_step": 444377, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0535433292388916, "global_step": 444378, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0679869651794434, "global_step": 444379, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.974657416343689, "global_step": 444380, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.064383029937744, "global_step": 444381, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.05625057220459, "global_step": 444382, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.091066360473633, "global_step": 444383, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.061757802963257, "global_step": 444384, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.068631172180176, "global_step": 444385, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.104998826980591, "global_step": 444386, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.128183364868164, "global_step": 444387, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0026705265045166, "global_step": 444388, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0257880687713623, "global_step": 444389, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1155824661254883, "global_step": 444390, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.129803419113159, "global_step": 444391, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1934592723846436, "global_step": 444392, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1061060428619385, "global_step": 444393, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0757803916931152, "global_step": 444394, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0223586559295654, "global_step": 444395, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0536088943481445, "global_step": 444396, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1075241565704346, "global_step": 444397, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0621392726898193, "global_step": 444398, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.108597993850708, "global_step": 444399, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.065106153488159, "global_step": 444400, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.103299140930176, "global_step": 444401, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0688323974609375, "global_step": 444402, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0148115158081055, "global_step": 444403, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0481183528900146, "global_step": 444404, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1319494247436523, "global_step": 444405, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0718438625335693, "global_step": 444406, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.047219753265381, "global_step": 444407, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.013868570327759, "global_step": 444408, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.025001049041748, "global_step": 444409, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.078752040863037, "global_step": 444410, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1175127029418945, "global_step": 444411, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.088707208633423, "global_step": 444412, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.168717622756958, "global_step": 444413, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0307905673980713, "global_step": 444414, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0801689624786377, "global_step": 444415, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.147371292114258, "global_step": 444416, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1209359169006348, "global_step": 444417, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0549216270446777, "global_step": 444418, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1005287170410156, "global_step": 444419, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1104161739349365, "global_step": 444420, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0131030082702637, "global_step": 444421, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1185643672943115, "global_step": 444422, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0575835704803467, "global_step": 444423, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0755045413970947, "global_step": 444424, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0178616046905518, "global_step": 444425, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1037867069244385, "global_step": 444426, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.022588014602661, "global_step": 444427, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.102799892425537, "global_step": 444428, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0544371604919434, "global_step": 444429, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.967429280281067, "global_step": 444430, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9825472831726074, "global_step": 444431, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.180140256881714, "global_step": 444432, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.069974660873413, "global_step": 444433, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0832152366638184, "global_step": 444434, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0721724033355713, "global_step": 444435, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.008047580718994, "global_step": 444436, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0355026721954346, "global_step": 444437, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1241066455841064, "global_step": 444438, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0890190601348877, "global_step": 444439, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.020822763442993, "global_step": 444440, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0888161659240723, "global_step": 444441, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0135087966918945, "global_step": 444442, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.114706039428711, "global_step": 444443, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1155107021331787, "global_step": 444444, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1101396083831787, "global_step": 444445, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9953018426895142, "global_step": 444446, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1140894889831543, "global_step": 444447, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1199281215667725, "global_step": 444448, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0600738525390625, "global_step": 444449, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.099384307861328, "global_step": 444450, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0666913986206055, "global_step": 444451, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9943511486053467, "global_step": 444452, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0424439907073975, "global_step": 444453, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0506296157836914, "global_step": 444454, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.103107452392578, "global_step": 444455, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.160144090652466, "global_step": 444456, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0535836219787598, "global_step": 444457, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1260387897491455, "global_step": 444458, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.017735242843628, "global_step": 444459, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0458083152770996, "global_step": 444460, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.090402364730835, "global_step": 444461, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0142595767974854, "global_step": 444462, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0182061195373535, "global_step": 444463, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1307780742645264, "global_step": 444464, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0007150173187256, "global_step": 444465, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1744680404663086, "global_step": 444466, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0437424182891846, "global_step": 444467, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.105875253677368, "global_step": 444468, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.097317934036255, "global_step": 444469, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0581963062286377, "global_step": 444470, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.029478073120117, "global_step": 444471, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.116910696029663, "global_step": 444472, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0389723777770996, "global_step": 444473, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1262216567993164, "global_step": 444474, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.141439199447632, "global_step": 444475, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.054891586303711, "global_step": 444476, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.108837366104126, "global_step": 444477, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.04392671585083, "global_step": 444478, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0749120712280273, "global_step": 444479, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0193228721618652, "global_step": 444480, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0796878337860107, "global_step": 444481, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1007299423217773, "global_step": 444482, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.081407070159912, "global_step": 444483, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0272605419158936, "global_step": 444484, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0330657958984375, "global_step": 444485, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0864803791046143, "global_step": 444486, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0342681407928467, "global_step": 444487, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.007944107055664, "global_step": 444488, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0449228286743164, "global_step": 444489, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9808183908462524, "global_step": 444490, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.098818778991699, "global_step": 444491, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1028518676757812, "global_step": 444492, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0735578536987305, "global_step": 444493, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.032623291015625, "global_step": 444494, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0727014541625977, "global_step": 444495, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0608036518096924, "global_step": 444496, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.014146566390991, "global_step": 444497, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0616421699523926, "global_step": 444498, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.2204220294952393, "global_step": 444499, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9995611906051636, "global_step": 444500, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0468180179595947, "global_step": 444501, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0010790824890137, "global_step": 444502, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1123368740081787, "global_step": 444503, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1520838737487793, "global_step": 444504, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0975706577301025, "global_step": 444505, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.072296142578125, "global_step": 444506, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.112870454788208, "global_step": 444507, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1548380851745605, "global_step": 444508, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.07487416267395, "global_step": 444509, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1291122436523438, "global_step": 444510, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.021785259246826, "global_step": 444511, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0763237476348877, "global_step": 444512, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1188173294067383, "global_step": 444513, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0609307289123535, "global_step": 444514, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0533952713012695, "global_step": 444515, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.037344455718994, "global_step": 444516, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.2231040000915527, "global_step": 444517, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0388410091400146, "global_step": 444518, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0810799598693848, "global_step": 444519, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.057675838470459, "global_step": 444520, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0529465675354004, "global_step": 444521, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.122861862182617, "global_step": 444522, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.018294095993042, "global_step": 444523, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.020148754119873, "global_step": 444524, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0495548248291016, "global_step": 444525, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1308412551879883, "global_step": 444526, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.07193922996521, "global_step": 444527, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1159822940826416, "global_step": 444528, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0782299041748047, "global_step": 444529, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0566208362579346, "global_step": 444530, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1012368202209473, "global_step": 444531, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1333725452423096, "global_step": 444532, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0923454761505127, "global_step": 444533, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.075314521789551, "global_step": 444534, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.056483030319214, "global_step": 444535, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.070991277694702, "global_step": 444536, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.073946237564087, "global_step": 444537, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1461873054504395, "global_step": 444538, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.162041187286377, "global_step": 444539, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0447120666503906, "global_step": 444540, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0677270889282227, "global_step": 444541, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0456249713897705, "global_step": 444542, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1224112510681152, "global_step": 444543, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.089407205581665, "global_step": 444544, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.150576114654541, "global_step": 444545, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1108546257019043, "global_step": 444546, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.080484628677368, "global_step": 444547, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9961789846420288, "global_step": 444548, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0331196784973145, "global_step": 444549, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.100806474685669, "global_step": 444550, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0388381481170654, "global_step": 444551, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.045491933822632, "global_step": 444552, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1641249656677246, "global_step": 444553, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.056022882461548, "global_step": 444554, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.190075635910034, "global_step": 444555, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0344765186309814, "global_step": 444556, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0982284545898438, "global_step": 444557, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1235859394073486, "global_step": 444558, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0532946586608887, "global_step": 444559, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.061581611633301, "global_step": 444560, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.001655340194702, "global_step": 444561, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0428009033203125, "global_step": 444562, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0823285579681396, "global_step": 444563, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0588979721069336, "global_step": 444564, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0619049072265625, "global_step": 444565, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.065842628479004, "global_step": 444566, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1346776485443115, "global_step": 444567, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.093611001968384, "global_step": 444568, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.093409538269043, "global_step": 444569, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1406188011169434, "global_step": 444570, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1291446685791016, "global_step": 444571, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0732314586639404, "global_step": 444572, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.118227481842041, "global_step": 444573, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.069220781326294, "global_step": 444574, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0912106037139893, "global_step": 444575, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.01608943939209, "global_step": 444576, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1003878116607666, "global_step": 444577, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0522124767303467, "global_step": 444578, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0261194705963135, "global_step": 444579, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0049893856048584, "global_step": 444580, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1401915550231934, "global_step": 444581, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9773975610733032, "global_step": 444582, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.056251049041748, "global_step": 444583, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.075401544570923, "global_step": 444584, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.076263427734375, "global_step": 444585, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.024310350418091, "global_step": 444586, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.989138126373291, "global_step": 444587, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0522301197052, "global_step": 444588, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0908865928649902, "global_step": 444589, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0776288509368896, "global_step": 444590, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.085674524307251, "global_step": 444591, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.11446213722229, "global_step": 444592, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0714080333709717, "global_step": 444593, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0927679538726807, "global_step": 444594, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1513383388519287, "global_step": 444595, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0134217739105225, "global_step": 444596, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1522772312164307, "global_step": 444597, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.120067596435547, "global_step": 444598, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.080695867538452, "global_step": 444599, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.054287910461426, "global_step": 444600, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0296988487243652, "global_step": 444601, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.106203079223633, "global_step": 444602, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1342380046844482, "global_step": 444603, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0903139114379883, "global_step": 444604, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.171370506286621, "global_step": 444605, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.119544506072998, "global_step": 444606, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9790023565292358, "global_step": 444607, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1418418884277344, "global_step": 444608, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0657269954681396, "global_step": 444609, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1366593837738037, "global_step": 444610, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1209828853607178, "global_step": 444611, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0263237953186035, "global_step": 444612, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.065575122833252, "global_step": 444613, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9953467845916748, "global_step": 444614, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.048210382461548, "global_step": 444615, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.167243480682373, "global_step": 444616, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0998198986053467, "global_step": 444617, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0620994567871094, "global_step": 444618, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.059156656265259, "global_step": 444619, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0522172451019287, "global_step": 444620, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.2180140018463135, "global_step": 444621, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1279914379119873, "global_step": 444622, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.087846517562866, "global_step": 444623, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1378445625305176, "global_step": 444624, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.106867551803589, "global_step": 444625, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.011312484741211, "global_step": 444626, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9623217582702637, "global_step": 444627, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9981240034103394, "global_step": 444628, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1244089603424072, "global_step": 444629, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0566020011901855, "global_step": 444630, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.06803035736084, "global_step": 444631, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.034723997116089, "global_step": 444632, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.095874071121216, "global_step": 444633, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0971767902374268, "global_step": 444634, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1751816272735596, "global_step": 444635, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.017583131790161, "global_step": 444636, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.066878080368042, "global_step": 444637, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1508560180664062, "global_step": 444638, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.033491611480713, "global_step": 444639, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1386988162994385, "global_step": 444640, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.09013032913208, "global_step": 444641, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.145552396774292, "global_step": 444642, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1590723991394043, "global_step": 444643, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.018932819366455, "global_step": 444644, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1555709838867188, "global_step": 444645, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1120572090148926, "global_step": 444646, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.090806722640991, "global_step": 444647, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.047914505004883, "global_step": 444648, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.123878240585327, "global_step": 444649, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.09615159034729, "global_step": 444650, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1262459754943848, "global_step": 444651, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.099174737930298, "global_step": 444652, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1203815937042236, "global_step": 444653, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0192253589630127, "global_step": 444654, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1002159118652344, "global_step": 444655, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.135014057159424, "global_step": 444656, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0765292644500732, "global_step": 444657, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0246338844299316, "global_step": 444658, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1595518589019775, "global_step": 444659, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1087141036987305, "global_step": 444660, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0671846866607666, "global_step": 444661, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.129291296005249, "global_step": 444662, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1001951694488525, "global_step": 444663, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.025282621383667, "global_step": 444664, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.045215129852295, "global_step": 444665, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0794928073883057, "global_step": 444666, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1114466190338135, "global_step": 444667, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0500741004943848, "global_step": 444668, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0289034843444824, "global_step": 444669, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0438003540039062, "global_step": 444670, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.124000310897827, "global_step": 444671, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.032601833343506, "global_step": 444672, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0568649768829346, "global_step": 444673, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1256906986236572, "global_step": 444674, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0670621395111084, "global_step": 444675, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0135369300842285, "global_step": 444676, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.098404884338379, "global_step": 444677, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0764052867889404, "global_step": 444678, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.097470760345459, "global_step": 444679, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.09393048286438, "global_step": 444680, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.057100296020508, "global_step": 444681, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.093203544616699, "global_step": 444682, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0423765182495117, "global_step": 444683, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9203282594680786, "global_step": 444684, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0280299186706543, "global_step": 444685, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1621477603912354, "global_step": 444686, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0779879093170166, "global_step": 444687, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0331380367279053, "global_step": 444688, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0807785987854004, "global_step": 444689, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.149441957473755, "global_step": 444690, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0372159481048584, "global_step": 444691, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.007293939590454, "global_step": 444692, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0317153930664062, "global_step": 444693, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.146137237548828, "global_step": 444694, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0411322116851807, "global_step": 444695, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.082573413848877, "global_step": 444696, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.091431140899658, "global_step": 444697, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.080116033554077, "global_step": 444698, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0071585178375244, "global_step": 444699, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0434250831604004, "global_step": 444700, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.070934295654297, "global_step": 444701, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0906472206115723, "global_step": 444702, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1551904678344727, "global_step": 444703, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.058352470397949, "global_step": 444704, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0404529571533203, "global_step": 444705, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9306371212005615, "global_step": 444706, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0757384300231934, "global_step": 444707, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.025146484375, "global_step": 444708, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.057971954345703, "global_step": 444709, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.059457778930664, "global_step": 444710, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0919950008392334, "global_step": 444711, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.065610647201538, "global_step": 444712, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1427724361419678, "global_step": 444713, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1519486904144287, "global_step": 444714, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0317044258117676, "global_step": 444715, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1322033405303955, "global_step": 444716, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.056086540222168, "global_step": 444717, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.072143077850342, "global_step": 444718, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0064809322357178, "global_step": 444719, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0889687538146973, "global_step": 444720, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1147620677948, "global_step": 444721, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.070756673812866, "global_step": 444722, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1371827125549316, "global_step": 444723, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1310694217681885, "global_step": 444724, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0608325004577637, "global_step": 444725, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.027062177658081, "global_step": 444726, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0024867057800293, "global_step": 444727, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.066908121109009, "global_step": 444728, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1141607761383057, "global_step": 444729, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.065314769744873, "global_step": 444730, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.044066905975342, "global_step": 444731, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1100411415100098, "global_step": 444732, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1339728832244873, "global_step": 444733, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.10298752784729, "global_step": 444734, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9722899198532104, "global_step": 444735, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0811147689819336, "global_step": 444736, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0907070636749268, "global_step": 444737, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0558722019195557, "global_step": 444738, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.157973527908325, "global_step": 444739, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0350751876831055, "global_step": 444740, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.105187177658081, "global_step": 444741, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0690479278564453, "global_step": 444742, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.049535036087036, "global_step": 444743, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.077603816986084, "global_step": 444744, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.095369815826416, "global_step": 444745, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.131737470626831, "global_step": 444746, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.08306622505188, "global_step": 444747, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0659923553466797, "global_step": 444748, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.116766929626465, "global_step": 444749, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9903700351715088, "global_step": 444750, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0892884731292725, "global_step": 444751, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1045637130737305, "global_step": 444752, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.098679780960083, "global_step": 444753, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0735063552856445, "global_step": 444754, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1364035606384277, "global_step": 444755, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.034766674041748, "global_step": 444756, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0576844215393066, "global_step": 444757, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0483462810516357, "global_step": 444758, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0874080657958984, "global_step": 444759, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1157941818237305, "global_step": 444760, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0648717880249023, "global_step": 444761, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0303115844726562, "global_step": 444762, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.066425085067749, "global_step": 444763, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9966225624084473, "global_step": 444764, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0306499004364014, "global_step": 444765, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.161064386367798, "global_step": 444766, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1647045612335205, "global_step": 444767, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.069885730743408, "global_step": 444768, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0437023639678955, "global_step": 444769, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0392653942108154, "global_step": 444770, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0810441970825195, "global_step": 444771, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1656382083892822, "global_step": 444772, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.050153970718384, "global_step": 444773, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0251057147979736, "global_step": 444774, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1493968963623047, "global_step": 444775, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.046875238418579, "global_step": 444776, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0851998329162598, "global_step": 444777, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9973928928375244, "global_step": 444778, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.018310070037842, "global_step": 444779, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1191554069519043, "global_step": 444780, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9853318929672241, "global_step": 444781, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.079449415206909, "global_step": 444782, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.000173807144165, "global_step": 444783, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0988380908966064, "global_step": 444784, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0827338695526123, "global_step": 444785, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.129709243774414, "global_step": 444786, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.103818416595459, "global_step": 444787, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.954227328300476, "global_step": 444788, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.057893991470337, "global_step": 444789, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0980477333068848, "global_step": 444790, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1185312271118164, "global_step": 444791, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.994840145111084, "global_step": 444792, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.099116325378418, "global_step": 444793, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9776065349578857, "global_step": 444794, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0854508876800537, "global_step": 444795, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0979838371276855, "global_step": 444796, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.043283224105835, "global_step": 444797, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.046888828277588, "global_step": 444798, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.003427505493164, "global_step": 444799, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0019218921661377, "global_step": 444800, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.00119686126709, "global_step": 444801, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.011828660964966, "global_step": 444802, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.016735315322876, "global_step": 444803, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1161928176879883, "global_step": 444804, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0379157066345215, "global_step": 444805, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.035252094268799, "global_step": 444806, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.018260955810547, "global_step": 444807, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0859360694885254, "global_step": 444808, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0687053203582764, "global_step": 444809, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.2060606479644775, "global_step": 444810, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1422362327575684, "global_step": 444811, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1689975261688232, "global_step": 444812, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.113682508468628, "global_step": 444813, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0792741775512695, "global_step": 444814, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.028533458709717, "global_step": 444815, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0878360271453857, "global_step": 444816, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.117885112762451, "global_step": 444817, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0162479877471924, "global_step": 444818, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0610268115997314, "global_step": 444819, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.013974905014038, "global_step": 444820, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.061412811279297, "global_step": 444821, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9987231492996216, "global_step": 444822, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0326380729675293, "global_step": 444823, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0864062309265137, "global_step": 444824, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0005040168762207, "global_step": 444825, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.093010425567627, "global_step": 444826, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9951062202453613, "global_step": 444827, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.023954391479492, "global_step": 444828, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0940511226654053, "global_step": 444829, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1687991619110107, "global_step": 444830, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.192014217376709, "global_step": 444831, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1398041248321533, "global_step": 444832, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1708950996398926, "global_step": 444833, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1075758934020996, "global_step": 444834, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.145568370819092, "global_step": 444835, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0580015182495117, "global_step": 444836, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0279996395111084, "global_step": 444837, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0806479454040527, "global_step": 444838, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.103161334991455, "global_step": 444839, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.00014328956604, "global_step": 444840, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.106285572052002, "global_step": 444841, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.06343936920166, "global_step": 444842, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.067835807800293, "global_step": 444843, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.026414632797241, "global_step": 444844, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1186609268188477, "global_step": 444845, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1092429161071777, "global_step": 444846, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.052565336227417, "global_step": 444847, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0683541297912598, "global_step": 444848, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.043170690536499, "global_step": 444849, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0812995433807373, "global_step": 444850, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.021824359893799, "global_step": 444851, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.075371265411377, "global_step": 444852, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.084260940551758, "global_step": 444853, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0980846881866455, "global_step": 444854, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.133678674697876, "global_step": 444855, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.101991891860962, "global_step": 444856, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.119795560836792, "global_step": 444857, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.125504493713379, "global_step": 444858, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.057553291320801, "global_step": 444859, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1662588119506836, "global_step": 444860, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.140425682067871, "global_step": 444861, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.062051773071289, "global_step": 444862, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.114609718322754, "global_step": 444863, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9991179704666138, "global_step": 444864, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.105795383453369, "global_step": 444865, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1129398345947266, "global_step": 444866, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.114187240600586, "global_step": 444867, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0856566429138184, "global_step": 444868, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1224212646484375, "global_step": 444869, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.167689800262451, "global_step": 444870, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0149197578430176, "global_step": 444871, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0851552486419678, "global_step": 444872, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.088655948638916, "global_step": 444873, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.060983419418335, "global_step": 444874, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.042271614074707, "global_step": 444875, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.100809097290039, "global_step": 444876, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0680885314941406, "global_step": 444877, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1042680740356445, "global_step": 444878, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.053449869155884, "global_step": 444879, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1348397731781006, "global_step": 444880, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0697333812713623, "global_step": 444881, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.109463930130005, "global_step": 444882, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0051047801971436, "global_step": 444883, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1664652824401855, "global_step": 444884, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1123690605163574, "global_step": 444885, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0422863960266113, "global_step": 444886, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1124725341796875, "global_step": 444887, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.093233585357666, "global_step": 444888, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0593230724334717, "global_step": 444889, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.098565101623535, "global_step": 444890, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0803284645080566, "global_step": 444891, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0230636596679688, "global_step": 444892, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1066501140594482, "global_step": 444893, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9960302114486694, "global_step": 444894, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1668944358825684, "global_step": 444895, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0937209129333496, "global_step": 444896, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.125659704208374, "global_step": 444897, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.1416878700256348, "global_step": 444898, "epoch": 808, "lr": 5e-05}
{"train_loss": 1.9495865106582642, "global_step": 444899, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.099865436553955, "global_step": 444900, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0534749031066895, "global_step": 444901, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0385050773620605, "global_step": 444902, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.0734622478485107, "global_step": 444903, "epoch": 808, "lr": 5e-05}
{"train_loss": 2.026644229888916, "global_step": 444904, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1443424224853516, "global_step": 444905, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0036888122558594, "global_step": 444906, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9956105947494507, "global_step": 444907, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9695552587509155, "global_step": 444908, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.027249813079834, "global_step": 444909, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0459136962890625, "global_step": 444910, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1369919776916504, "global_step": 444911, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.107551336288452, "global_step": 444912, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0998120307922363, "global_step": 444913, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0367538928985596, "global_step": 444914, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.054446220397949, "global_step": 444915, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0831241607666016, "global_step": 444916, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0617308616638184, "global_step": 444917, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.138246774673462, "global_step": 444918, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.004693031311035, "global_step": 444919, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9989440441131592, "global_step": 444920, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0783824920654297, "global_step": 444921, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.085263252258301, "global_step": 444922, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0605061054229736, "global_step": 444923, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0804505348205566, "global_step": 444924, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.038792371749878, "global_step": 444925, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0239274501800537, "global_step": 444926, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0526864528656006, "global_step": 444927, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.061081886291504, "global_step": 444928, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0778422355651855, "global_step": 444929, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.137653112411499, "global_step": 444930, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.075824737548828, "global_step": 444931, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9728384017944336, "global_step": 444932, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.955928087234497, "global_step": 444933, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.035975217819214, "global_step": 444934, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0870614051818848, "global_step": 444935, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.114237070083618, "global_step": 444936, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0322611331939697, "global_step": 444937, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.049567699432373, "global_step": 444938, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1460049152374268, "global_step": 444939, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0956034660339355, "global_step": 444940, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0226712226867676, "global_step": 444941, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0384747982025146, "global_step": 444942, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9943056106567383, "global_step": 444943, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1167774200439453, "global_step": 444944, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9814239740371704, "global_step": 444945, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.156187057495117, "global_step": 444946, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.088076591491699, "global_step": 444947, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.152226448059082, "global_step": 444948, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1389262676239014, "global_step": 444949, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.000438690185547, "global_step": 444950, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1044440269470215, "global_step": 444951, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0563647747039795, "global_step": 444952, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0676121711730957, "global_step": 444953, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0618886947631836, "global_step": 444954, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0918896198272705, "global_step": 444955, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0729637145996094, "global_step": 444956, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0266618728637695, "global_step": 444957, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.013425588607788, "global_step": 444958, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.2013161182403564, "global_step": 444959, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0289065837860107, "global_step": 444960, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.016505241394043, "global_step": 444961, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0058844089508057, "global_step": 444962, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.993173360824585, "global_step": 444963, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1452720165252686, "global_step": 444964, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0464107990264893, "global_step": 444965, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.118812084197998, "global_step": 444966, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0351457595825195, "global_step": 444967, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0770692825317383, "global_step": 444968, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0521206855773926, "global_step": 444969, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.064270496368408, "global_step": 444970, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9465537071228027, "global_step": 444971, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0132803916931152, "global_step": 444972, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0728378295898438, "global_step": 444973, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1393136978149414, "global_step": 444974, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0769474506378174, "global_step": 444975, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0830917358398438, "global_step": 444976, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9701781272888184, "global_step": 444977, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.102961301803589, "global_step": 444978, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.011878490447998, "global_step": 444979, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.098268985748291, "global_step": 444980, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.129894256591797, "global_step": 444981, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1051509380340576, "global_step": 444982, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.020944118499756, "global_step": 444983, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0679876804351807, "global_step": 444984, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.138789415359497, "global_step": 444985, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0538556575775146, "global_step": 444986, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0204906463623047, "global_step": 444987, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0526113510131836, "global_step": 444988, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0195987224578857, "global_step": 444989, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.059370279312134, "global_step": 444990, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1476426124572754, "global_step": 444991, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.089769124984741, "global_step": 444992, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0261032581329346, "global_step": 444993, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1226837635040283, "global_step": 444994, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.071913242340088, "global_step": 444995, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.036316394805908, "global_step": 444996, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0370349884033203, "global_step": 444997, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9985504150390625, "global_step": 444998, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.099637031555176, "global_step": 444999, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.044264554977417, "global_step": 445000, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.059065341949463, "global_step": 445001, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.072061777114868, "global_step": 445002, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1267733573913574, "global_step": 445003, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0765492916107178, "global_step": 445004, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.000190019607544, "global_step": 445005, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.102349042892456, "global_step": 445006, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.090266466140747, "global_step": 445007, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9922860860824585, "global_step": 445008, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9258275032043457, "global_step": 445009, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.092222213745117, "global_step": 445010, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1803781986236572, "global_step": 445011, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0433359146118164, "global_step": 445012, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.949946403503418, "global_step": 445013, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.051175117492676, "global_step": 445014, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.051194906234741, "global_step": 445015, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1055707931518555, "global_step": 445016, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0382027626037598, "global_step": 445017, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.07696270942688, "global_step": 445018, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0623598098754883, "global_step": 445019, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1426007747650146, "global_step": 445020, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1119537353515625, "global_step": 445021, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0897605419158936, "global_step": 445022, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.086303234100342, "global_step": 445023, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0159873962402344, "global_step": 445024, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.067020893096924, "global_step": 445025, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.051071882247925, "global_step": 445026, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1201295852661133, "global_step": 445027, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9268593788146973, "global_step": 445028, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0232510566711426, "global_step": 445029, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.118250608444214, "global_step": 445030, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.984952449798584, "global_step": 445031, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0730369091033936, "global_step": 445032, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1665561199188232, "global_step": 445033, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.124852418899536, "global_step": 445034, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0112597942352295, "global_step": 445035, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0593128204345703, "global_step": 445036, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1762185096740723, "global_step": 445037, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.073540210723877, "global_step": 445038, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.050816297531128, "global_step": 445039, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.083113193511963, "global_step": 445040, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.056211471557617, "global_step": 445041, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.104816198348999, "global_step": 445042, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.063079595565796, "global_step": 445043, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0938470363616943, "global_step": 445044, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1669623851776123, "global_step": 445045, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.107846975326538, "global_step": 445046, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.07688570022583, "global_step": 445047, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0636587142944336, "global_step": 445048, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.086352586746216, "global_step": 445049, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0682811737060547, "global_step": 445050, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.965560793876648, "global_step": 445051, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.093299627304077, "global_step": 445052, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0789270401000977, "global_step": 445053, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.044708251953125, "global_step": 445054, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.996062994003296, "global_step": 445055, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9309537410736084, "global_step": 445056, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.096991777420044, "global_step": 445057, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0673277378082275, "global_step": 445058, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.051982879638672, "global_step": 445059, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9935145378112793, "global_step": 445060, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0639073848724365, "global_step": 445061, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.053563356399536, "global_step": 445062, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0819153785705566, "global_step": 445063, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0223512649536133, "global_step": 445064, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.117385149002075, "global_step": 445065, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9567824602127075, "global_step": 445066, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9596635103225708, "global_step": 445067, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0655312538146973, "global_step": 445068, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.032379150390625, "global_step": 445069, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.075112819671631, "global_step": 445070, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.070472478866577, "global_step": 445071, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0743930339813232, "global_step": 445072, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.111772060394287, "global_step": 445073, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0653767585754395, "global_step": 445074, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.070697784423828, "global_step": 445075, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.037447690963745, "global_step": 445076, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.131593704223633, "global_step": 445077, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.080057382583618, "global_step": 445078, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0611307621002197, "global_step": 445079, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0220882892608643, "global_step": 445080, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9789869785308838, "global_step": 445081, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.174058198928833, "global_step": 445082, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0488696098327637, "global_step": 445083, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0594234466552734, "global_step": 445084, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.111583948135376, "global_step": 445085, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.097075939178467, "global_step": 445086, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.041551351547241, "global_step": 445087, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0862481594085693, "global_step": 445088, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1061060428619385, "global_step": 445089, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0607786178588867, "global_step": 445090, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0680227279663086, "global_step": 445091, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.087744951248169, "global_step": 445092, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1083717346191406, "global_step": 445093, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1273033618927, "global_step": 445094, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9832210540771484, "global_step": 445095, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0187036991119385, "global_step": 445096, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.13604998588562, "global_step": 445097, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1040267944335938, "global_step": 445098, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.089866876602173, "global_step": 445099, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9430691003799438, "global_step": 445100, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9735908508300781, "global_step": 445101, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0941073894500732, "global_step": 445102, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.115234375, "global_step": 445103, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1327483654022217, "global_step": 445104, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0292863845825195, "global_step": 445105, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0453102588653564, "global_step": 445106, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.110365629196167, "global_step": 445107, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0013394355773926, "global_step": 445108, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1026721000671387, "global_step": 445109, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1081509590148926, "global_step": 445110, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9856643676757812, "global_step": 445111, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1844558715820312, "global_step": 445112, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.110419750213623, "global_step": 445113, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1383562088012695, "global_step": 445114, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.14210844039917, "global_step": 445115, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0568487644195557, "global_step": 445116, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.048476219177246, "global_step": 445117, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0560412406921387, "global_step": 445118, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.085486888885498, "global_step": 445119, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9992324113845825, "global_step": 445120, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.131255626678467, "global_step": 445121, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0675384998321533, "global_step": 445122, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.089850664138794, "global_step": 445123, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.087163209915161, "global_step": 445124, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0433077812194824, "global_step": 445125, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0792932510375977, "global_step": 445126, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.107166290283203, "global_step": 445127, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1381607055664062, "global_step": 445128, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0402352809906006, "global_step": 445129, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.065908670425415, "global_step": 445130, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.091852903366089, "global_step": 445131, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0920379161834717, "global_step": 445132, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1547436714172363, "global_step": 445133, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.109368324279785, "global_step": 445134, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9779462814331055, "global_step": 445135, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1143057346343994, "global_step": 445136, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.063992977142334, "global_step": 445137, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.106100559234619, "global_step": 445138, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1255574226379395, "global_step": 445139, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.068850517272949, "global_step": 445140, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0206031799316406, "global_step": 445141, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.10062837600708, "global_step": 445142, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.059025287628174, "global_step": 445143, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1115527153015137, "global_step": 445144, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1295292377471924, "global_step": 445145, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1115453243255615, "global_step": 445146, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1279890537261963, "global_step": 445147, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.050333023071289, "global_step": 445148, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1540462970733643, "global_step": 445149, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0235683917999268, "global_step": 445150, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0692594051361084, "global_step": 445151, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0420284271240234, "global_step": 445152, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9659607410430908, "global_step": 445153, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.165560722351074, "global_step": 445154, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.005934000015259, "global_step": 445155, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0883424282073975, "global_step": 445156, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.981648325920105, "global_step": 445157, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0468978881835938, "global_step": 445158, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0343875885009766, "global_step": 445159, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1488819122314453, "global_step": 445160, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1376028060913086, "global_step": 445161, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1257524490356445, "global_step": 445162, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.040647268295288, "global_step": 445163, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0403194427490234, "global_step": 445164, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.110974073410034, "global_step": 445165, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.065877914428711, "global_step": 445166, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0627970695495605, "global_step": 445167, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0404162406921387, "global_step": 445168, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.112793207168579, "global_step": 445169, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0475642681121826, "global_step": 445170, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0999181270599365, "global_step": 445171, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.091062307357788, "global_step": 445172, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.104123115539551, "global_step": 445173, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0753397941589355, "global_step": 445174, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.095771551132202, "global_step": 445175, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0468876361846924, "global_step": 445176, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9739758968353271, "global_step": 445177, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.115398645401001, "global_step": 445178, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1468660831451416, "global_step": 445179, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0180282592773438, "global_step": 445180, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.184833288192749, "global_step": 445181, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.062523365020752, "global_step": 445182, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0566015243530273, "global_step": 445183, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.033156633377075, "global_step": 445184, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1321470737457275, "global_step": 445185, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.009225606918335, "global_step": 445186, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.081730604171753, "global_step": 445187, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.070986032485962, "global_step": 445188, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0280065536499023, "global_step": 445189, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.086387872695923, "global_step": 445190, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.136101722717285, "global_step": 445191, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1298890113830566, "global_step": 445192, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0270488262176514, "global_step": 445193, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1479849815368652, "global_step": 445194, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0595390796661377, "global_step": 445195, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9991896152496338, "global_step": 445196, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0889370441436768, "global_step": 445197, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.094336748123169, "global_step": 445198, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0046262741088867, "global_step": 445199, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.01749849319458, "global_step": 445200, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0736215114593506, "global_step": 445201, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0149943828582764, "global_step": 445202, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.057025194168091, "global_step": 445203, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0013513565063477, "global_step": 445204, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0891366004943848, "global_step": 445205, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.07588529586792, "global_step": 445206, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.052006244659424, "global_step": 445207, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.038465738296509, "global_step": 445208, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.119439125061035, "global_step": 445209, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1052844524383545, "global_step": 445210, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.142568826675415, "global_step": 445211, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.072047710418701, "global_step": 445212, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.083834171295166, "global_step": 445213, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0505993366241455, "global_step": 445214, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.029911994934082, "global_step": 445215, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0186123847961426, "global_step": 445216, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0592198371887207, "global_step": 445217, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1276633739471436, "global_step": 445218, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.121344804763794, "global_step": 445219, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0947577953338623, "global_step": 445220, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.042156219482422, "global_step": 445221, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1275272369384766, "global_step": 445222, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1053051948547363, "global_step": 445223, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.010667562484741, "global_step": 445224, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.037583827972412, "global_step": 445225, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9980136156082153, "global_step": 445226, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.057652235031128, "global_step": 445227, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.096011161804199, "global_step": 445228, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.134584426879883, "global_step": 445229, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.043407678604126, "global_step": 445230, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.194690227508545, "global_step": 445231, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.111255407333374, "global_step": 445232, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0686604976654053, "global_step": 445233, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1559300422668457, "global_step": 445234, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.043607473373413, "global_step": 445235, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.084118366241455, "global_step": 445236, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.058781623840332, "global_step": 445237, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9899346828460693, "global_step": 445238, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1812989711761475, "global_step": 445239, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.042060613632202, "global_step": 445240, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1717684268951416, "global_step": 445241, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0018959045410156, "global_step": 445242, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1122913360595703, "global_step": 445243, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9755451679229736, "global_step": 445244, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0883305072784424, "global_step": 445245, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9487898349761963, "global_step": 445246, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.151400089263916, "global_step": 445247, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1554057598114014, "global_step": 445248, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.085728406906128, "global_step": 445249, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.118286609649658, "global_step": 445250, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1151883602142334, "global_step": 445251, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.061760187149048, "global_step": 445252, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.121680498123169, "global_step": 445253, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.045928716659546, "global_step": 445254, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1411631107330322, "global_step": 445255, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0572121143341064, "global_step": 445256, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0553364753723145, "global_step": 445257, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0191385746002197, "global_step": 445258, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0847911834716797, "global_step": 445259, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9920793771743774, "global_step": 445260, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0882351398468018, "global_step": 445261, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.048213243484497, "global_step": 445262, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.140993356704712, "global_step": 445263, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0591611862182617, "global_step": 445264, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1051952838897705, "global_step": 445265, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.085066080093384, "global_step": 445266, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0521061420440674, "global_step": 445267, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.047921657562256, "global_step": 445268, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0147652626037598, "global_step": 445269, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.996161937713623, "global_step": 445270, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1695139408111572, "global_step": 445271, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.110546588897705, "global_step": 445272, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9807701110839844, "global_step": 445273, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0472726821899414, "global_step": 445274, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0992462635040283, "global_step": 445275, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0117673873901367, "global_step": 445276, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1628036499023438, "global_step": 445277, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.037654399871826, "global_step": 445278, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.069716453552246, "global_step": 445279, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.03145694732666, "global_step": 445280, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1009299755096436, "global_step": 445281, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0043351650238037, "global_step": 445282, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.093818426132202, "global_step": 445283, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1117496490478516, "global_step": 445284, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.061816692352295, "global_step": 445285, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.172189235687256, "global_step": 445286, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0801749229431152, "global_step": 445287, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1481823921203613, "global_step": 445288, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1132373809814453, "global_step": 445289, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1300666332244873, "global_step": 445290, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.115243911743164, "global_step": 445291, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.130495071411133, "global_step": 445292, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0057644844055176, "global_step": 445293, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.107740640640259, "global_step": 445294, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0812172889709473, "global_step": 445295, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.117985725402832, "global_step": 445296, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.12251353263855, "global_step": 445297, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0833420753479004, "global_step": 445298, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.044172763824463, "global_step": 445299, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1598100662231445, "global_step": 445300, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.113699436187744, "global_step": 445301, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.993849754333496, "global_step": 445302, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1441571712493896, "global_step": 445303, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.046449661254883, "global_step": 445304, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.084693670272827, "global_step": 445305, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9730992317199707, "global_step": 445306, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0276474952697754, "global_step": 445307, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.099242925643921, "global_step": 445308, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.200888156890869, "global_step": 445309, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0367541313171387, "global_step": 445310, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1194252967834473, "global_step": 445311, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9818933010101318, "global_step": 445312, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.125030994415283, "global_step": 445313, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.025319814682007, "global_step": 445314, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.976530909538269, "global_step": 445315, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0068037509918213, "global_step": 445316, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.065777540206909, "global_step": 445317, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.134862184524536, "global_step": 445318, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1201226711273193, "global_step": 445319, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0713040828704834, "global_step": 445320, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0255672931671143, "global_step": 445321, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.140108346939087, "global_step": 445322, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9879292249679565, "global_step": 445323, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.013139009475708, "global_step": 445324, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.034276247024536, "global_step": 445325, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0290420055389404, "global_step": 445326, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1125526428222656, "global_step": 445327, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.031385660171509, "global_step": 445328, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.047217845916748, "global_step": 445329, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.035991907119751, "global_step": 445330, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.129833459854126, "global_step": 445331, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1121537685394287, "global_step": 445332, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1865007877349854, "global_step": 445333, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.016857862472534, "global_step": 445334, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0747909545898438, "global_step": 445335, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.06046199798584, "global_step": 445336, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1032662391662598, "global_step": 445337, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0522916316986084, "global_step": 445338, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.075471878051758, "global_step": 445339, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1259031295776367, "global_step": 445340, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0941739082336426, "global_step": 445341, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0424489974975586, "global_step": 445342, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.101123094558716, "global_step": 445343, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.123323917388916, "global_step": 445344, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9874014854431152, "global_step": 445345, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0459465980529785, "global_step": 445346, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.114792823791504, "global_step": 445347, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.118337392807007, "global_step": 445348, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0402772426605225, "global_step": 445349, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0742440223693848, "global_step": 445350, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1042590141296387, "global_step": 445351, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.011606454849243, "global_step": 445352, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.097285747528076, "global_step": 445353, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0925252437591553, "global_step": 445354, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1039340496063232, "global_step": 445355, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1266696453094482, "global_step": 445356, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.070218801498413, "global_step": 445357, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0473413467407227, "global_step": 445358, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.013073205947876, "global_step": 445359, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0268795490264893, "global_step": 445360, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1375670433044434, "global_step": 445361, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.065110445022583, "global_step": 445362, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.075899839401245, "global_step": 445363, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.00742244720459, "global_step": 445364, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9895061254501343, "global_step": 445365, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0882208347320557, "global_step": 445366, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.138871192932129, "global_step": 445367, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0498077869415283, "global_step": 445368, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.058565378189087, "global_step": 445369, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9873027801513672, "global_step": 445370, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0316221714019775, "global_step": 445371, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.094346523284912, "global_step": 445372, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0697238445281982, "global_step": 445373, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9729008674621582, "global_step": 445374, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0627739429473877, "global_step": 445375, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9710783958435059, "global_step": 445376, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9899290800094604, "global_step": 445377, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.127692222595215, "global_step": 445378, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.045210599899292, "global_step": 445379, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.986833930015564, "global_step": 445380, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1075260639190674, "global_step": 445381, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1193974018096924, "global_step": 445382, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.04167103767395, "global_step": 445383, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9769599437713623, "global_step": 445384, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1340630054473877, "global_step": 445385, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0551581382751465, "global_step": 445386, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.022246837615967, "global_step": 445387, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.132307529449463, "global_step": 445388, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1301796436309814, "global_step": 445389, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.097727060317993, "global_step": 445390, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.045387029647827, "global_step": 445391, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1908466815948486, "global_step": 445392, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0390162467956543, "global_step": 445393, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0949699878692627, "global_step": 445394, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.054769992828369, "global_step": 445395, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0493733882904053, "global_step": 445396, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.133526563644409, "global_step": 445397, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0228328704833984, "global_step": 445398, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0225112438201904, "global_step": 445399, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.129938840866089, "global_step": 445400, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.151543378829956, "global_step": 445401, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1522347927093506, "global_step": 445402, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.10746693611145, "global_step": 445403, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0105366706848145, "global_step": 445404, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0612621307373047, "global_step": 445405, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1588613986968994, "global_step": 445406, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0744941234588623, "global_step": 445407, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.026563882827759, "global_step": 445408, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0810298919677734, "global_step": 445409, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0731558799743652, "global_step": 445410, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9929968118667603, "global_step": 445411, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.095114231109619, "global_step": 445412, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0879483222961426, "global_step": 445413, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0783519744873047, "global_step": 445414, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1417410373687744, "global_step": 445415, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0256052017211914, "global_step": 445416, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.18329119682312, "global_step": 445417, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0520613193511963, "global_step": 445418, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0954749584198, "global_step": 445419, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.092327833175659, "global_step": 445420, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.025435447692871, "global_step": 445421, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.076465129852295, "global_step": 445422, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0426344871520996, "global_step": 445423, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.148876905441284, "global_step": 445424, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.068934917449951, "global_step": 445425, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0487329959869385, "global_step": 445426, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0981082916259766, "global_step": 445427, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9971827268600464, "global_step": 445428, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1055331230163574, "global_step": 445429, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0433197021484375, "global_step": 445430, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.014068841934204, "global_step": 445431, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.089907646179199, "global_step": 445432, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.09541654586792, "global_step": 445433, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0834405422210693, "global_step": 445434, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.058483839035034, "global_step": 445435, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.097399950027466, "global_step": 445436, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1018009185791016, "global_step": 445437, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0411999225616455, "global_step": 445438, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0477771759033203, "global_step": 445439, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.143657922744751, "global_step": 445440, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.089956283569336, "global_step": 445441, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0847420692443848, "global_step": 445442, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0714364051818848, "global_step": 445443, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0069808959960938, "global_step": 445444, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.007878065109253, "global_step": 445445, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0436532497406006, "global_step": 445446, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0564866065979004, "global_step": 445447, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1346373558044434, "global_step": 445448, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0627903938293457, "global_step": 445449, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0681631565093994, "global_step": 445450, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.037902593612671, "global_step": 445451, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0924785137176514, "global_step": 445452, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1579079627990723, "global_step": 445453, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0352652072906494, "global_step": 445454, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1008973121643066, "global_step": 445455, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0725200176239014, "global_step": 445456, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.988918662071228, "global_step": 445457, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.230280876159668, "global_step": 445458, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.069131851196289, "global_step": 445459, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.012545108795166, "global_step": 445460, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.015397310256958, "global_step": 445461, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1118640899658203, "global_step": 445462, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0299575328826904, "global_step": 445463, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1498332023620605, "global_step": 445464, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.108776569366455, "global_step": 445465, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1029975414276123, "global_step": 445466, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0994651317596436, "global_step": 445467, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.13346529006958, "global_step": 445468, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.134821653366089, "global_step": 445469, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.042964220046997, "global_step": 445470, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.162358522415161, "global_step": 445471, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.034883737564087, "global_step": 445472, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0428528785705566, "global_step": 445473, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.084589719772339, "global_step": 445474, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0508010387420654, "global_step": 445475, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1070079803466797, "global_step": 445476, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1038661003112793, "global_step": 445477, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0035507678985596, "global_step": 445478, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.125098466873169, "global_step": 445479, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.116579294204712, "global_step": 445480, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.158125400543213, "global_step": 445481, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.035261631011963, "global_step": 445482, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0987229347229004, "global_step": 445483, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.140347719192505, "global_step": 445484, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0649614334106445, "global_step": 445485, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1059422492980957, "global_step": 445486, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.081645965576172, "global_step": 445487, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.115152597427368, "global_step": 445488, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1919937133789062, "global_step": 445489, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0268359184265137, "global_step": 445490, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.092883825302124, "global_step": 445491, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.109907627105713, "global_step": 445492, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.101083278656006, "global_step": 445493, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0299551486968994, "global_step": 445494, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.2151777744293213, "global_step": 445495, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0542755126953125, "global_step": 445496, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0145630836486816, "global_step": 445497, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.124748706817627, "global_step": 445498, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0425961017608643, "global_step": 445499, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.104818820953369, "global_step": 445500, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1502163410186768, "global_step": 445501, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.159508466720581, "global_step": 445502, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0782930850982666, "global_step": 445503, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9427303075790405, "global_step": 445504, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.178581714630127, "global_step": 445505, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0517125129699707, "global_step": 445506, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1452226638793945, "global_step": 445507, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0785622596740723, "global_step": 445508, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0732483863830566, "global_step": 445509, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0546414852142334, "global_step": 445510, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.110513925552368, "global_step": 445511, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0526223182678223, "global_step": 445512, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.066807508468628, "global_step": 445513, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0937705039978027, "global_step": 445514, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0726189613342285, "global_step": 445515, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0235915184020996, "global_step": 445516, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0652263164520264, "global_step": 445517, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.167595624923706, "global_step": 445518, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.069493293762207, "global_step": 445519, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1312661170959473, "global_step": 445520, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0677294731140137, "global_step": 445521, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.092567205429077, "global_step": 445522, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.090153455734253, "global_step": 445523, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.063314914703369, "global_step": 445524, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1154062747955322, "global_step": 445525, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1053643226623535, "global_step": 445526, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.090733289718628, "global_step": 445527, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.099362373352051, "global_step": 445528, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0487186908721924, "global_step": 445529, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0751261711120605, "global_step": 445530, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.025830030441284, "global_step": 445531, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0770251750946045, "global_step": 445532, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1329009532928467, "global_step": 445533, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.989406943321228, "global_step": 445534, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0430233478546143, "global_step": 445535, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.051687479019165, "global_step": 445536, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.095828056335449, "global_step": 445537, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.09413480758667, "global_step": 445538, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0742781162261963, "global_step": 445539, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.009031057357788, "global_step": 445540, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0797102451324463, "global_step": 445541, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.008049488067627, "global_step": 445542, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0204391479492188, "global_step": 445543, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1098012924194336, "global_step": 445544, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0881266593933105, "global_step": 445545, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0764901638031006, "global_step": 445546, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.065398693084717, "global_step": 445547, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.014122247695923, "global_step": 445548, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0797345638275146, "global_step": 445549, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0961804389953613, "global_step": 445550, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.075411796569824, "global_step": 445551, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0786447525024414, "global_step": 445552, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.111603021621704, "global_step": 445553, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0630364418029785, "global_step": 445554, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9969981908798218, "global_step": 445555, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.2778289318084717, "global_step": 445556, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1030642986297607, "global_step": 445557, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0921242237091064, "global_step": 445558, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0548973083496094, "global_step": 445559, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.973512887954712, "global_step": 445560, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1051740646362305, "global_step": 445561, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.071897506713867, "global_step": 445562, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.157379627227783, "global_step": 445563, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.111992120742798, "global_step": 445564, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.053349733352661, "global_step": 445565, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0691537857055664, "global_step": 445566, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.095371723175049, "global_step": 445567, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0953147411346436, "global_step": 445568, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.997380256652832, "global_step": 445569, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9556249380111694, "global_step": 445570, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0218448638916016, "global_step": 445571, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0814404487609863, "global_step": 445572, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0587656497955322, "global_step": 445573, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.098198175430298, "global_step": 445574, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.078094244003296, "global_step": 445575, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.066190004348755, "global_step": 445576, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.11914324760437, "global_step": 445577, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.062434196472168, "global_step": 445578, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1854567527770996, "global_step": 445579, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.105950355529785, "global_step": 445580, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.167573928833008, "global_step": 445581, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.131486177444458, "global_step": 445582, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.145545721054077, "global_step": 445583, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0936994552612305, "global_step": 445584, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1006879806518555, "global_step": 445585, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.02783203125, "global_step": 445586, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.059741735458374, "global_step": 445587, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1131484508514404, "global_step": 445588, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.087843418121338, "global_step": 445589, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1049022674560547, "global_step": 445590, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0906753540039062, "global_step": 445591, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.077167510986328, "global_step": 445592, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.087390184402466, "global_step": 445593, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0783958435058594, "global_step": 445594, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0704221725463867, "global_step": 445595, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0284924507141113, "global_step": 445596, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.01904296875, "global_step": 445597, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.037623405456543, "global_step": 445598, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1118319034576416, "global_step": 445599, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1872615814208984, "global_step": 445600, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0885238647460938, "global_step": 445601, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.99929678440094, "global_step": 445602, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0741331577301025, "global_step": 445603, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0722146034240723, "global_step": 445604, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1684672832489014, "global_step": 445605, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.106696605682373, "global_step": 445606, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0290796756744385, "global_step": 445607, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.994294285774231, "global_step": 445608, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0791218280792236, "global_step": 445609, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.099914312362671, "global_step": 445610, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1124372482299805, "global_step": 445611, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.120863437652588, "global_step": 445612, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.020051956176758, "global_step": 445613, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0220282077789307, "global_step": 445614, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0082004070281982, "global_step": 445615, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1018643379211426, "global_step": 445616, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.061434507369995, "global_step": 445617, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.104403018951416, "global_step": 445618, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0758652687072754, "global_step": 445619, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0376219749450684, "global_step": 445620, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0837318897247314, "global_step": 445621, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.057511329650879, "global_step": 445622, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0753421783447266, "global_step": 445623, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9592385292053223, "global_step": 445624, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.082669734954834, "global_step": 445625, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.066073417663574, "global_step": 445626, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1025798320770264, "global_step": 445627, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1766915321350098, "global_step": 445628, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0604190826416016, "global_step": 445629, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.998700499534607, "global_step": 445630, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.054534673690796, "global_step": 445631, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.007525682449341, "global_step": 445632, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1711015701293945, "global_step": 445633, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0520052909851074, "global_step": 445634, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.000247001647949, "global_step": 445635, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9718822240829468, "global_step": 445636, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9741450548171997, "global_step": 445637, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1463348865509033, "global_step": 445638, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.073526620864868, "global_step": 445639, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.116140604019165, "global_step": 445640, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0486483573913574, "global_step": 445641, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0922558307647705, "global_step": 445642, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.155245304107666, "global_step": 445643, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1080174446105957, "global_step": 445644, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0045619010925293, "global_step": 445645, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1040170192718506, "global_step": 445646, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9691581726074219, "global_step": 445647, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1616783142089844, "global_step": 445648, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.121173620223999, "global_step": 445649, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9959356784820557, "global_step": 445650, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.133315324783325, "global_step": 445651, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0468382835388184, "global_step": 445652, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0480356216430664, "global_step": 445653, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.143411636352539, "global_step": 445654, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0726118087768555, "global_step": 445655, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0942904949188232, "global_step": 445656, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9807467460632324, "global_step": 445657, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0654778480529785, "global_step": 445658, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.139570713043213, "global_step": 445659, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1525826454162598, "global_step": 445660, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.036534070968628, "global_step": 445661, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1411712169647217, "global_step": 445662, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0983939170837402, "global_step": 445663, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1556622982025146, "global_step": 445664, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9837613105773926, "global_step": 445665, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.037055730819702, "global_step": 445666, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.032150983810425, "global_step": 445667, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1316182613372803, "global_step": 445668, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0148589611053467, "global_step": 445669, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0722172260284424, "global_step": 445670, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.081838607788086, "global_step": 445671, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0586771965026855, "global_step": 445672, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0789194107055664, "global_step": 445673, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.023294448852539, "global_step": 445674, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1538314819335938, "global_step": 445675, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0844693183898926, "global_step": 445676, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.184771776199341, "global_step": 445677, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9903432130813599, "global_step": 445678, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.026991128921509, "global_step": 445679, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.115065813064575, "global_step": 445680, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.081719160079956, "global_step": 445681, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1071481704711914, "global_step": 445682, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.031304359436035, "global_step": 445683, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.079922676086426, "global_step": 445684, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.037522315979004, "global_step": 445685, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.136772632598877, "global_step": 445686, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0805485248565674, "global_step": 445687, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0537683963775635, "global_step": 445688, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0521962642669678, "global_step": 445689, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1761794090270996, "global_step": 445690, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.06496524810791, "global_step": 445691, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0008528232574463, "global_step": 445692, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1108431816101074, "global_step": 445693, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.033808946609497, "global_step": 445694, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1098639965057373, "global_step": 445695, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0212337970733643, "global_step": 445696, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0173535346984863, "global_step": 445697, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.092642307281494, "global_step": 445698, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.157379150390625, "global_step": 445699, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0463976860046387, "global_step": 445700, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0652730464935303, "global_step": 445701, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.135669469833374, "global_step": 445702, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1288845539093018, "global_step": 445703, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0829639434814453, "global_step": 445704, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.092636823654175, "global_step": 445705, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1396172046661377, "global_step": 445706, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1081061363220215, "global_step": 445707, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.057826042175293, "global_step": 445708, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0997886657714844, "global_step": 445709, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0461041927337646, "global_step": 445710, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.088503837585449, "global_step": 445711, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1359660625457764, "global_step": 445712, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0884358882904053, "global_step": 445713, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0886921882629395, "global_step": 445714, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.04059100151062, "global_step": 445715, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.172046661376953, "global_step": 445716, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1931450366973877, "global_step": 445717, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1023693084716797, "global_step": 445718, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1085917949676514, "global_step": 445719, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1297056674957275, "global_step": 445720, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.980985403060913, "global_step": 445721, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.059176445007324, "global_step": 445722, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.115694284439087, "global_step": 445723, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.088902711868286, "global_step": 445724, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.037139415740967, "global_step": 445725, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9968011379241943, "global_step": 445726, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.067943811416626, "global_step": 445727, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.075806140899658, "global_step": 445728, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.128920078277588, "global_step": 445729, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9735832214355469, "global_step": 445730, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1025588512420654, "global_step": 445731, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0740227699279785, "global_step": 445732, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0545074939727783, "global_step": 445733, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.164832353591919, "global_step": 445734, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.11098313331604, "global_step": 445735, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0132803916931152, "global_step": 445736, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0847115516662598, "global_step": 445737, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0371644496917725, "global_step": 445738, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0310752391815186, "global_step": 445739, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1172642707824707, "global_step": 445740, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.138204336166382, "global_step": 445741, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.07235050201416, "global_step": 445742, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9493165016174316, "global_step": 445743, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.116011381149292, "global_step": 445744, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.116008758544922, "global_step": 445745, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0988056659698486, "global_step": 445746, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.099367618560791, "global_step": 445747, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1146132946014404, "global_step": 445748, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.100417137145996, "global_step": 445749, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.178924083709717, "global_step": 445750, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0864298343658447, "global_step": 445751, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0499186515808105, "global_step": 445752, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.134694814682007, "global_step": 445753, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0824809074401855, "global_step": 445754, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.165160894393921, "global_step": 445755, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.091230630874634, "global_step": 445756, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0508627891540527, "global_step": 445757, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0731301307678223, "global_step": 445758, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1084227561950684, "global_step": 445759, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.09504771232605, "global_step": 445760, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.9525402784347534, "global_step": 445761, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1712050437927246, "global_step": 445762, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1014134883880615, "global_step": 445763, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0658445358276367, "global_step": 445764, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0661168098449707, "global_step": 445765, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.06286358833313, "global_step": 445766, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1370604038238525, "global_step": 445767, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.129993438720703, "global_step": 445768, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.135798454284668, "global_step": 445769, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.026158332824707, "global_step": 445770, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.04831862449646, "global_step": 445771, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1066598892211914, "global_step": 445772, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.074235200881958, "global_step": 445773, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.038684129714966, "global_step": 445774, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.076289176940918, "global_step": 445775, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.00002384185791, "global_step": 445776, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1088671684265137, "global_step": 445777, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0307059288024902, "global_step": 445778, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.021421432495117, "global_step": 445779, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.12858510017395, "global_step": 445780, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1167755126953125, "global_step": 445781, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1164536476135254, "global_step": 445782, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0442562103271484, "global_step": 445783, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0517823696136475, "global_step": 445784, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0763609409332275, "global_step": 445785, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0784595012664795, "global_step": 445786, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0756447315216064, "global_step": 445787, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0391061305999756, "global_step": 445788, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0668962001800537, "global_step": 445789, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.074829578399658, "global_step": 445790, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0740139484405518, "global_step": 445791, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.149364471435547, "global_step": 445792, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.139624834060669, "global_step": 445793, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1031413078308105, "global_step": 445794, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.106532335281372, "global_step": 445795, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0477685928344727, "global_step": 445796, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.164536237716675, "global_step": 445797, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.152806043624878, "global_step": 445798, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1003518104553223, "global_step": 445799, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1227314472198486, "global_step": 445800, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0329477787017822, "global_step": 445801, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0386056900024414, "global_step": 445802, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.049978256225586, "global_step": 445803, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.065178632736206, "global_step": 445804, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1306493282318115, "global_step": 445805, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.041020631790161, "global_step": 445806, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.12599515914917, "global_step": 445807, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1035571098327637, "global_step": 445808, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1431691646575928, "global_step": 445809, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0251967906951904, "global_step": 445810, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0618064403533936, "global_step": 445811, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0523672103881836, "global_step": 445812, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0641884803771973, "global_step": 445813, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.196150779724121, "global_step": 445814, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0688977241516113, "global_step": 445815, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0144529342651367, "global_step": 445816, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.091456890106201, "global_step": 445817, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.097724199295044, "global_step": 445818, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0746607780456543, "global_step": 445819, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1079275608062744, "global_step": 445820, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.125659942626953, "global_step": 445821, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1750946044921875, "global_step": 445822, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.115860939025879, "global_step": 445823, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.126450300216675, "global_step": 445824, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.083289384841919, "global_step": 445825, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0692458152770996, "global_step": 445826, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0513341426849365, "global_step": 445827, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0632331371307373, "global_step": 445828, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0986316204071045, "global_step": 445829, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1253786087036133, "global_step": 445830, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0823702812194824, "global_step": 445831, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0859405994415283, "global_step": 445832, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1574923992156982, "global_step": 445833, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1716468334198, "global_step": 445834, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0866379737854004, "global_step": 445835, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.137937545776367, "global_step": 445836, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0057172775268555, "global_step": 445837, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.078282356262207, "global_step": 445838, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.088224411010742, "global_step": 445839, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1471238136291504, "global_step": 445840, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0423197746276855, "global_step": 445841, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.044299840927124, "global_step": 445842, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.030712366104126, "global_step": 445843, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.072232246398926, "global_step": 445844, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.096005916595459, "global_step": 445845, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1535756587982178, "global_step": 445846, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1463072299957275, "global_step": 445847, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.091179609298706, "global_step": 445848, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.066157341003418, "global_step": 445849, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.078234910964966, "global_step": 445850, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.014589309692383, "global_step": 445851, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1314284801483154, "global_step": 445852, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1526448726654053, "global_step": 445853, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0027594566345215, "global_step": 445854, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.138378620147705, "global_step": 445855, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.134373903274536, "global_step": 445856, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0576207637786865, "global_step": 445857, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0605850219726562, "global_step": 445858, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.148050308227539, "global_step": 445859, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1003432273864746, "global_step": 445860, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0011539459228516, "global_step": 445861, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1623446941375732, "global_step": 445862, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.126735210418701, "global_step": 445863, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.109673261642456, "global_step": 445864, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.103450298309326, "global_step": 445865, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.1729319095611572, "global_step": 445866, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.153085708618164, "global_step": 445867, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0436851978302, "global_step": 445868, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.0991251468658447, "global_step": 445869, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.134040355682373, "global_step": 445870, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.042341947555542, "global_step": 445871, "epoch": 809, "lr": 5e-05}
{"train_loss": 2.076107978820801, "global_step": 445872, "epoch": 809, "lr": 5e-05}
{"train_loss": 1.975787878036499, "global_step": 445873, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.089860439300537, "global_step": 445874, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.007540225982666, "global_step": 445875, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0426511764526367, "global_step": 445876, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.076073169708252, "global_step": 445877, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.058736562728882, "global_step": 445878, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.065830707550049, "global_step": 445879, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.095240354537964, "global_step": 445880, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.10418438911438, "global_step": 445881, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0418779850006104, "global_step": 445882, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1689441204071045, "global_step": 445883, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1216073036193848, "global_step": 445884, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0498249530792236, "global_step": 445885, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.063004970550537, "global_step": 445886, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.152621269226074, "global_step": 445887, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.102928400039673, "global_step": 445888, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.023834228515625, "global_step": 445889, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.105208158493042, "global_step": 445890, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1201443672180176, "global_step": 445891, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0915372371673584, "global_step": 445892, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.028848648071289, "global_step": 445893, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0384018421173096, "global_step": 445894, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.136538028717041, "global_step": 445895, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0672919750213623, "global_step": 445896, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.041395902633667, "global_step": 445897, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.098424196243286, "global_step": 445898, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.043633460998535, "global_step": 445899, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0475733280181885, "global_step": 445900, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0272412300109863, "global_step": 445901, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.141388416290283, "global_step": 445902, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1163668632507324, "global_step": 445903, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1408371925354004, "global_step": 445904, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0138964653015137, "global_step": 445905, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.04594349861145, "global_step": 445906, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.184587240219116, "global_step": 445907, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.064074993133545, "global_step": 445908, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9878965616226196, "global_step": 445909, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1397459506988525, "global_step": 445910, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.127049684524536, "global_step": 445911, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.037015914916992, "global_step": 445912, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1384494304656982, "global_step": 445913, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0457615852355957, "global_step": 445914, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0771491527557373, "global_step": 445915, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0632050037384033, "global_step": 445916, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9682352542877197, "global_step": 445917, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.065039873123169, "global_step": 445918, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0922462940216064, "global_step": 445919, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.048443555831909, "global_step": 445920, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1582224369049072, "global_step": 445921, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0391218662261963, "global_step": 445922, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1026835441589355, "global_step": 445923, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0714480876922607, "global_step": 445924, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0257301330566406, "global_step": 445925, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.113100051879883, "global_step": 445926, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.076162338256836, "global_step": 445927, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.027381658554077, "global_step": 445928, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0422399044036865, "global_step": 445929, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0314061641693115, "global_step": 445930, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.012911081314087, "global_step": 445931, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0483109951019287, "global_step": 445932, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.04528546333313, "global_step": 445933, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.071807861328125, "global_step": 445934, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.085306406021118, "global_step": 445935, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.062788724899292, "global_step": 445936, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0344011783599854, "global_step": 445937, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1066644191741943, "global_step": 445938, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.119150161743164, "global_step": 445939, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0730350017547607, "global_step": 445940, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0379321575164795, "global_step": 445941, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0360817909240723, "global_step": 445942, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0465993881225586, "global_step": 445943, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0635204315185547, "global_step": 445944, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1802024841308594, "global_step": 445945, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.06382155418396, "global_step": 445946, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.031919479370117, "global_step": 445947, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.090363025665283, "global_step": 445948, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.008420944213867, "global_step": 445949, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1288673877716064, "global_step": 445950, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1645565032958984, "global_step": 445951, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9940139055252075, "global_step": 445952, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.994078516960144, "global_step": 445953, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.101858377456665, "global_step": 445954, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.09588360786438, "global_step": 445955, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9803606271743774, "global_step": 445956, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0281929969787598, "global_step": 445957, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0810515880584717, "global_step": 445958, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.03877592086792, "global_step": 445959, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0483286380767822, "global_step": 445960, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.04299259185791, "global_step": 445961, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.075645685195923, "global_step": 445962, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1004152297973633, "global_step": 445963, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0501508712768555, "global_step": 445964, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0984151363372803, "global_step": 445965, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0332424640655518, "global_step": 445966, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1739912033081055, "global_step": 445967, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.071479558944702, "global_step": 445968, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1202449798583984, "global_step": 445969, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0634243488311768, "global_step": 445970, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0786139965057373, "global_step": 445971, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1046998500823975, "global_step": 445972, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.076875686645508, "global_step": 445973, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1331286430358887, "global_step": 445974, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0401594638824463, "global_step": 445975, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.069880485534668, "global_step": 445976, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0870368480682373, "global_step": 445977, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1488070487976074, "global_step": 445978, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.112027406692505, "global_step": 445979, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.075923204421997, "global_step": 445980, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0005321502685547, "global_step": 445981, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.077118396759033, "global_step": 445982, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0975959300994873, "global_step": 445983, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0054047107696533, "global_step": 445984, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0304384231567383, "global_step": 445985, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1319921016693115, "global_step": 445986, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0789520740509033, "global_step": 445987, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0768191814422607, "global_step": 445988, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1216249465942383, "global_step": 445989, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0949437618255615, "global_step": 445990, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1412441730499268, "global_step": 445991, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1616153717041016, "global_step": 445992, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.148486852645874, "global_step": 445993, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.230170488357544, "global_step": 445994, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.944125771522522, "global_step": 445995, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0943357944488525, "global_step": 445996, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1500728130340576, "global_step": 445997, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0471932888031006, "global_step": 445998, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1143057346343994, "global_step": 445999, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.114093065261841, "global_step": 446000, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1744096279144287, "global_step": 446001, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0331826210021973, "global_step": 446002, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0777535438537598, "global_step": 446003, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0546934604644775, "global_step": 446004, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0300068855285645, "global_step": 446005, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.068962335586548, "global_step": 446006, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0468952655792236, "global_step": 446007, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.206838369369507, "global_step": 446008, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0692861080169678, "global_step": 446009, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.129523515701294, "global_step": 446010, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0804266929626465, "global_step": 446011, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.030944347381592, "global_step": 446012, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.104214668273926, "global_step": 446013, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.00649094581604, "global_step": 446014, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0422239303588867, "global_step": 446015, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0832889080047607, "global_step": 446016, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0399436950683594, "global_step": 446017, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.050764560699463, "global_step": 446018, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.122591018676758, "global_step": 446019, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9574577808380127, "global_step": 446020, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.113330841064453, "global_step": 446021, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0150563716888428, "global_step": 446022, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.038410186767578, "global_step": 446023, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.039686918258667, "global_step": 446024, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.092109441757202, "global_step": 446025, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9976624250411987, "global_step": 446026, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0759215354919434, "global_step": 446027, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.084623336791992, "global_step": 446028, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1031100749969482, "global_step": 446029, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.004377603530884, "global_step": 446030, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0935211181640625, "global_step": 446031, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0557820796966553, "global_step": 446032, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0523555278778076, "global_step": 446033, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0437934398651123, "global_step": 446034, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0791478157043457, "global_step": 446035, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0704286098480225, "global_step": 446036, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.067890167236328, "global_step": 446037, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.090313673019409, "global_step": 446038, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.114522695541382, "global_step": 446039, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1473615169525146, "global_step": 446040, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0558879375457764, "global_step": 446041, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0739049911499023, "global_step": 446042, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.2175073623657227, "global_step": 446043, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0123653411865234, "global_step": 446044, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1303532123565674, "global_step": 446045, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.053481340408325, "global_step": 446046, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0350329875946045, "global_step": 446047, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.055990695953369, "global_step": 446048, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.04943585395813, "global_step": 446049, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.101985454559326, "global_step": 446050, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0671095848083496, "global_step": 446051, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1720948219299316, "global_step": 446052, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0598695278167725, "global_step": 446053, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.080125093460083, "global_step": 446054, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0495572090148926, "global_step": 446055, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.07503080368042, "global_step": 446056, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.095052719116211, "global_step": 446057, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.069974184036255, "global_step": 446058, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0887017250061035, "global_step": 446059, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.070573329925537, "global_step": 446060, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.105661392211914, "global_step": 446061, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.151888847351074, "global_step": 446062, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1303839683532715, "global_step": 446063, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0229504108428955, "global_step": 446064, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9834928512573242, "global_step": 446065, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.076235055923462, "global_step": 446066, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0665953159332275, "global_step": 446067, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0602145195007324, "global_step": 446068, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.089444160461426, "global_step": 446069, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0584261417388916, "global_step": 446070, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0541722774505615, "global_step": 446071, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.056572914123535, "global_step": 446072, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0483434200286865, "global_step": 446073, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.089414596557617, "global_step": 446074, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0864357948303223, "global_step": 446075, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.054809331893921, "global_step": 446076, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9222146272659302, "global_step": 446077, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0854501724243164, "global_step": 446078, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1669201850891113, "global_step": 446079, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.082789421081543, "global_step": 446080, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0175187587738037, "global_step": 446081, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.096498727798462, "global_step": 446082, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0933008193969727, "global_step": 446083, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.07877516746521, "global_step": 446084, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0038511753082275, "global_step": 446085, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.125633716583252, "global_step": 446086, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.035945415496826, "global_step": 446087, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1293811798095703, "global_step": 446088, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.103994607925415, "global_step": 446089, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0716800689697266, "global_step": 446090, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9840493202209473, "global_step": 446091, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0707287788391113, "global_step": 446092, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.078146457672119, "global_step": 446093, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0618462562561035, "global_step": 446094, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0104031562805176, "global_step": 446095, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0694456100463867, "global_step": 446096, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0118257999420166, "global_step": 446097, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9582442045211792, "global_step": 446098, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0605685710906982, "global_step": 446099, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1015384197235107, "global_step": 446100, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0694570541381836, "global_step": 446101, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0444977283477783, "global_step": 446102, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0616393089294434, "global_step": 446103, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.093742847442627, "global_step": 446104, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.070636749267578, "global_step": 446105, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0904619693756104, "global_step": 446106, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.971022605895996, "global_step": 446107, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1364095211029053, "global_step": 446108, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.099454402923584, "global_step": 446109, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1057844161987305, "global_step": 446110, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1365184783935547, "global_step": 446111, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0375847816467285, "global_step": 446112, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.037065029144287, "global_step": 446113, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9950324296951294, "global_step": 446114, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0457687377929688, "global_step": 446115, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.071784257888794, "global_step": 446116, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.932054877281189, "global_step": 446117, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0733847618103027, "global_step": 446118, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0814075469970703, "global_step": 446119, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9987289905548096, "global_step": 446120, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.043325185775757, "global_step": 446121, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0448052883148193, "global_step": 446122, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.062166452407837, "global_step": 446123, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1054117679595947, "global_step": 446124, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.108815908432007, "global_step": 446125, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1092398166656494, "global_step": 446126, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1041460037231445, "global_step": 446127, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.093353509902954, "global_step": 446128, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9894810914993286, "global_step": 446129, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.113769292831421, "global_step": 446130, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1018927097320557, "global_step": 446131, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0839664936065674, "global_step": 446132, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0862038135528564, "global_step": 446133, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0965094566345215, "global_step": 446134, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0850398540496826, "global_step": 446135, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.014565944671631, "global_step": 446136, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.028008222579956, "global_step": 446137, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1370787620544434, "global_step": 446138, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1435706615448, "global_step": 446139, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.071446180343628, "global_step": 446140, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1960952281951904, "global_step": 446141, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1265509128570557, "global_step": 446142, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.042557716369629, "global_step": 446143, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.101454019546509, "global_step": 446144, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0803680419921875, "global_step": 446145, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.036252021789551, "global_step": 446146, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0974841117858887, "global_step": 446147, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.137274742126465, "global_step": 446148, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0591299533843994, "global_step": 446149, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.092515468597412, "global_step": 446150, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0452840328216553, "global_step": 446151, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.099585771560669, "global_step": 446152, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0562686920166016, "global_step": 446153, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1672468185424805, "global_step": 446154, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0861151218414307, "global_step": 446155, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0975162982940674, "global_step": 446156, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0103073120117188, "global_step": 446157, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0412158966064453, "global_step": 446158, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.081148624420166, "global_step": 446159, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1609370708465576, "global_step": 446160, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.108008623123169, "global_step": 446161, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0959293842315674, "global_step": 446162, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0294559001922607, "global_step": 446163, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1436140537261963, "global_step": 446164, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.021574020385742, "global_step": 446165, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.032447576522827, "global_step": 446166, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0782902240753174, "global_step": 446167, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.122748374938965, "global_step": 446168, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.157517910003662, "global_step": 446169, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1656315326690674, "global_step": 446170, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0506317615509033, "global_step": 446171, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0764048099517822, "global_step": 446172, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1494805812835693, "global_step": 446173, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0747947692871094, "global_step": 446174, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0321037769317627, "global_step": 446175, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0943410396575928, "global_step": 446176, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.103917360305786, "global_step": 446177, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9782440662384033, "global_step": 446178, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.01501202583313, "global_step": 446179, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0798680782318115, "global_step": 446180, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.017975330352783, "global_step": 446181, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0622034072875977, "global_step": 446182, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1381499767303467, "global_step": 446183, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.023000955581665, "global_step": 446184, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0900180339813232, "global_step": 446185, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.020108938217163, "global_step": 446186, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.038990020751953, "global_step": 446187, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0204694271087646, "global_step": 446188, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9781746864318848, "global_step": 446189, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0765044689178467, "global_step": 446190, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0352554321289062, "global_step": 446191, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0653257369995117, "global_step": 446192, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0526933670043945, "global_step": 446193, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.053074359893799, "global_step": 446194, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0657801628112793, "global_step": 446195, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0511703491210938, "global_step": 446196, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1049907207489014, "global_step": 446197, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9879083633422852, "global_step": 446198, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0468080043792725, "global_step": 446199, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9767848253250122, "global_step": 446200, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0460562705993652, "global_step": 446201, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0807206630706787, "global_step": 446202, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0622410774230957, "global_step": 446203, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0583407878875732, "global_step": 446204, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9746274948120117, "global_step": 446205, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0674116611480713, "global_step": 446206, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1228904724121094, "global_step": 446207, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.117673873901367, "global_step": 446208, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0950329303741455, "global_step": 446209, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0921742916107178, "global_step": 446210, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0842809677124023, "global_step": 446211, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.094792604446411, "global_step": 446212, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.202579975128174, "global_step": 446213, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.12353777885437, "global_step": 446214, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0757339000701904, "global_step": 446215, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.092834711074829, "global_step": 446216, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.000948905944824, "global_step": 446217, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1023752689361572, "global_step": 446218, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.065786123275757, "global_step": 446219, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1400089263916016, "global_step": 446220, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.079848051071167, "global_step": 446221, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.00795316696167, "global_step": 446222, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.2040131092071533, "global_step": 446223, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0776138305664062, "global_step": 446224, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.069444417953491, "global_step": 446225, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.04248309135437, "global_step": 446226, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0350418090820312, "global_step": 446227, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1224188804626465, "global_step": 446228, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.091022491455078, "global_step": 446229, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0473291873931885, "global_step": 446230, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.083303451538086, "global_step": 446231, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.041181802749634, "global_step": 446232, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9910883903503418, "global_step": 446233, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.030805826187134, "global_step": 446234, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0765738487243652, "global_step": 446235, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0150954723358154, "global_step": 446236, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1084794998168945, "global_step": 446237, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0623388290405273, "global_step": 446238, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.023489236831665, "global_step": 446239, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.069890260696411, "global_step": 446240, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.10192608833313, "global_step": 446241, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0825541019439697, "global_step": 446242, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.987006425857544, "global_step": 446243, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.080944776535034, "global_step": 446244, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0846047401428223, "global_step": 446245, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0648136138916016, "global_step": 446246, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1574931144714355, "global_step": 446247, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0966949462890625, "global_step": 446248, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0977535247802734, "global_step": 446249, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.036196231842041, "global_step": 446250, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1058297157287598, "global_step": 446251, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.086427688598633, "global_step": 446252, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0966031551361084, "global_step": 446253, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.169106960296631, "global_step": 446254, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0173280239105225, "global_step": 446255, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.078383445739746, "global_step": 446256, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9846631288528442, "global_step": 446257, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1231932640075684, "global_step": 446258, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.040459156036377, "global_step": 446259, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1024811267852783, "global_step": 446260, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9923490285873413, "global_step": 446261, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1226577758789062, "global_step": 446262, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1161274909973145, "global_step": 446263, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0172510147094727, "global_step": 446264, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0177597999572754, "global_step": 446265, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1101813316345215, "global_step": 446266, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0387580394744873, "global_step": 446267, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0579323768615723, "global_step": 446268, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0309202671051025, "global_step": 446269, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1271092891693115, "global_step": 446270, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.117263078689575, "global_step": 446271, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0616614818573, "global_step": 446272, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.064483880996704, "global_step": 446273, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.067694902420044, "global_step": 446274, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.100759267807007, "global_step": 446275, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0431013107299805, "global_step": 446276, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1714322566986084, "global_step": 446277, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0601043701171875, "global_step": 446278, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.077646017074585, "global_step": 446279, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0487546920776367, "global_step": 446280, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.157860279083252, "global_step": 446281, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.09627366065979, "global_step": 446282, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.098951578140259, "global_step": 446283, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.078756809234619, "global_step": 446284, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0153086185455322, "global_step": 446285, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9611700773239136, "global_step": 446286, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0232884883880615, "global_step": 446287, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.017103433609009, "global_step": 446288, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.129279851913452, "global_step": 446289, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1993799209594727, "global_step": 446290, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.014188051223755, "global_step": 446291, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0665884017944336, "global_step": 446292, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1242828369140625, "global_step": 446293, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.135115623474121, "global_step": 446294, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.044623374938965, "global_step": 446295, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.009734630584717, "global_step": 446296, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9593533277511597, "global_step": 446297, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0170726776123047, "global_step": 446298, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.11765456199646, "global_step": 446299, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0344910621643066, "global_step": 446300, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1377336978912354, "global_step": 446301, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0948619842529297, "global_step": 446302, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.095327854156494, "global_step": 446303, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.054943799972534, "global_step": 446304, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0049245357513428, "global_step": 446305, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.11696457862854, "global_step": 446306, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.202040910720825, "global_step": 446307, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.127026319503784, "global_step": 446308, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.07019305229187, "global_step": 446309, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1440234184265137, "global_step": 446310, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.069206714630127, "global_step": 446311, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1102499961853027, "global_step": 446312, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1464431285858154, "global_step": 446313, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.016342878341675, "global_step": 446314, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0549678802490234, "global_step": 446315, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.064103603363037, "global_step": 446316, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0972347259521484, "global_step": 446317, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.089127779006958, "global_step": 446318, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0280613899230957, "global_step": 446319, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.146259069442749, "global_step": 446320, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1114015579223633, "global_step": 446321, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.03444242477417, "global_step": 446322, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1049370765686035, "global_step": 446323, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0553715229034424, "global_step": 446324, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.047616481781006, "global_step": 446325, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.130657196044922, "global_step": 446326, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1232047080993652, "global_step": 446327, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.052927017211914, "global_step": 446328, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.101043224334717, "global_step": 446329, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9703506231307983, "global_step": 446330, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1237704753875732, "global_step": 446331, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.073789119720459, "global_step": 446332, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.046454429626465, "global_step": 446333, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0408430099487305, "global_step": 446334, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1279900074005127, "global_step": 446335, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.117323398590088, "global_step": 446336, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0913798809051514, "global_step": 446337, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1082563400268555, "global_step": 446338, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0141592025756836, "global_step": 446339, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.080470323562622, "global_step": 446340, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0484282970428467, "global_step": 446341, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.019744873046875, "global_step": 446342, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.079413414001465, "global_step": 446343, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9919956922531128, "global_step": 446344, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.042543649673462, "global_step": 446345, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.079071283340454, "global_step": 446346, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.019670009613037, "global_step": 446347, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.042848587036133, "global_step": 446348, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.084881067276001, "global_step": 446349, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.048482656478882, "global_step": 446350, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1386027336120605, "global_step": 446351, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0866196155548096, "global_step": 446352, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0881853103637695, "global_step": 446353, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.127753973007202, "global_step": 446354, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0974719524383545, "global_step": 446355, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1328482627868652, "global_step": 446356, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0682079792022705, "global_step": 446357, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0750534534454346, "global_step": 446358, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0081839561462402, "global_step": 446359, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.050722360610962, "global_step": 446360, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0614864826202393, "global_step": 446361, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.03005051612854, "global_step": 446362, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.083681344985962, "global_step": 446363, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1141197681427, "global_step": 446364, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.090290069580078, "global_step": 446365, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0493545532226562, "global_step": 446366, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.991771936416626, "global_step": 446367, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.105191230773926, "global_step": 446368, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1020045280456543, "global_step": 446369, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0536904335021973, "global_step": 446370, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0461533069610596, "global_step": 446371, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0293123722076416, "global_step": 446372, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.037813663482666, "global_step": 446373, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1041219234466553, "global_step": 446374, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0847697257995605, "global_step": 446375, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.07881760597229, "global_step": 446376, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1154956817626953, "global_step": 446377, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0648908615112305, "global_step": 446378, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1772501468658447, "global_step": 446379, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.09546160697937, "global_step": 446380, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.03960919380188, "global_step": 446381, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0140233039855957, "global_step": 446382, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.017186403274536, "global_step": 446383, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.059133529663086, "global_step": 446384, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0321414470672607, "global_step": 446385, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0133626461029053, "global_step": 446386, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0310895442962646, "global_step": 446387, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.031787395477295, "global_step": 446388, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.069070816040039, "global_step": 446389, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0769193172454834, "global_step": 446390, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1354997158050537, "global_step": 446391, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.2021381855010986, "global_step": 446392, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.084726572036743, "global_step": 446393, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.08776593208313, "global_step": 446394, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.101789951324463, "global_step": 446395, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1126978397369385, "global_step": 446396, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.05806303024292, "global_step": 446397, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.045325756072998, "global_step": 446398, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0521013736724854, "global_step": 446399, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.057126522064209, "global_step": 446400, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1855454444885254, "global_step": 446401, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0432958602905273, "global_step": 446402, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1023104190826416, "global_step": 446403, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0920655727386475, "global_step": 446404, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0457003116607666, "global_step": 446405, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1132829189300537, "global_step": 446406, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.029991626739502, "global_step": 446407, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0737130641937256, "global_step": 446408, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0913796424865723, "global_step": 446409, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.017683267593384, "global_step": 446410, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1022884845733643, "global_step": 446411, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.126673698425293, "global_step": 446412, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.074425458908081, "global_step": 446413, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0818076133728027, "global_step": 446414, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.112450122833252, "global_step": 446415, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0632259845733643, "global_step": 446416, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0641322135925293, "global_step": 446417, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0835916996002197, "global_step": 446418, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9482492208480835, "global_step": 446419, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9621820449829102, "global_step": 446420, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.069206714630127, "global_step": 446421, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.046999454498291, "global_step": 446422, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0432138442993164, "global_step": 446423, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.089892625808716, "global_step": 446424, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9644113779067993, "global_step": 446425, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1185948848724365, "global_step": 446426, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.035980463027954, "global_step": 446427, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.062760591506958, "global_step": 446428, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0991764068603516, "global_step": 446429, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0124404430389404, "global_step": 446430, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.061687469482422, "global_step": 446431, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1890804767608643, "global_step": 446432, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.076523542404175, "global_step": 446433, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0602612495422363, "global_step": 446434, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0544605255126953, "global_step": 446435, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.019721508026123, "global_step": 446436, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0629894733428955, "global_step": 446437, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.100957155227661, "global_step": 446438, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.164943218231201, "global_step": 446439, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0235178470611572, "global_step": 446440, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0448286533355713, "global_step": 446441, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1458821296691895, "global_step": 446442, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0282018184661865, "global_step": 446443, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.042149543762207, "global_step": 446444, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0124027729034424, "global_step": 446445, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0907275676727295, "global_step": 446446, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.055144786834717, "global_step": 446447, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.034437656402588, "global_step": 446448, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.168229341506958, "global_step": 446449, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0025830268859863, "global_step": 446450, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.08066987991333, "global_step": 446451, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.051175355911255, "global_step": 446452, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.169555425643921, "global_step": 446453, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1066579818725586, "global_step": 446454, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0852367877960205, "global_step": 446455, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0710198879241943, "global_step": 446456, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9660050868988037, "global_step": 446457, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9865354299545288, "global_step": 446458, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.032744884490967, "global_step": 446459, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.155148506164551, "global_step": 446460, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0939056873321533, "global_step": 446461, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0854125022888184, "global_step": 446462, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.090670585632324, "global_step": 446463, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.114154815673828, "global_step": 446464, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.035216808319092, "global_step": 446465, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0583982467651367, "global_step": 446466, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0522077083587646, "global_step": 446467, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0374505519866943, "global_step": 446468, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0210683345794678, "global_step": 446469, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1038100719451904, "global_step": 446470, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.032893657684326, "global_step": 446471, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.086808204650879, "global_step": 446472, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0879836082458496, "global_step": 446473, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0724680423736572, "global_step": 446474, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.999463438987732, "global_step": 446475, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0994391441345215, "global_step": 446476, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.134540319442749, "global_step": 446477, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.067957639694214, "global_step": 446478, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.2096264362335205, "global_step": 446479, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.109170436859131, "global_step": 446480, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.126737117767334, "global_step": 446481, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0570390224456787, "global_step": 446482, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0331995487213135, "global_step": 446483, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0265426635742188, "global_step": 446484, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0590531826019287, "global_step": 446485, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.077136516571045, "global_step": 446486, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.101511001586914, "global_step": 446487, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.013908624649048, "global_step": 446488, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9964308738708496, "global_step": 446489, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.131380558013916, "global_step": 446490, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.936219334602356, "global_step": 446491, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1183176040649414, "global_step": 446492, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1010053157806396, "global_step": 446493, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0695290565490723, "global_step": 446494, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9980647563934326, "global_step": 446495, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.028543472290039, "global_step": 446496, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1260712146759033, "global_step": 446497, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.057020425796509, "global_step": 446498, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0952417850494385, "global_step": 446499, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.058645725250244, "global_step": 446500, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.013606071472168, "global_step": 446501, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0996952056884766, "global_step": 446502, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.045288324356079, "global_step": 446503, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.164304494857788, "global_step": 446504, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0486583709716797, "global_step": 446505, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1220052242279053, "global_step": 446506, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1854848861694336, "global_step": 446507, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.06661057472229, "global_step": 446508, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1279709339141846, "global_step": 446509, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.023076295852661, "global_step": 446510, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.023073196411133, "global_step": 446511, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1169354915618896, "global_step": 446512, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0905182361602783, "global_step": 446513, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1628541946411133, "global_step": 446514, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9756402969360352, "global_step": 446515, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9840795993804932, "global_step": 446516, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0341286659240723, "global_step": 446517, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.095224380493164, "global_step": 446518, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.103088617324829, "global_step": 446519, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.084743022918701, "global_step": 446520, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.067687511444092, "global_step": 446521, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0623860359191895, "global_step": 446522, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0838797092437744, "global_step": 446523, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1765084266662598, "global_step": 446524, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9751973152160645, "global_step": 446525, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0691492557525635, "global_step": 446526, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.130075454711914, "global_step": 446527, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0485918521881104, "global_step": 446528, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.052800416946411, "global_step": 446529, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1066043376922607, "global_step": 446530, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.034569501876831, "global_step": 446531, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0851190090179443, "global_step": 446532, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0455245971679688, "global_step": 446533, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0780863761901855, "global_step": 446534, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.982730746269226, "global_step": 446535, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0655763149261475, "global_step": 446536, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.07079815864563, "global_step": 446537, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.012643575668335, "global_step": 446538, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.107609748840332, "global_step": 446539, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.08868670463562, "global_step": 446540, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0334246158599854, "global_step": 446541, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.087663173675537, "global_step": 446542, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.093691110610962, "global_step": 446543, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.131533145904541, "global_step": 446544, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1032392978668213, "global_step": 446545, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0379018783569336, "global_step": 446546, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.102466583251953, "global_step": 446547, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.038569450378418, "global_step": 446548, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.036344289779663, "global_step": 446549, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.071931838989258, "global_step": 446550, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0436360836029053, "global_step": 446551, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1267614364624023, "global_step": 446552, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.090404748916626, "global_step": 446553, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.022517204284668, "global_step": 446554, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0178637504577637, "global_step": 446555, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.151482343673706, "global_step": 446556, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.112454891204834, "global_step": 446557, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1256723403930664, "global_step": 446558, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.01566743850708, "global_step": 446559, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.027724266052246, "global_step": 446560, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.096891403198242, "global_step": 446561, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0687460899353027, "global_step": 446562, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.081482410430908, "global_step": 446563, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.100055456161499, "global_step": 446564, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.005370855331421, "global_step": 446565, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1387407779693604, "global_step": 446566, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.074648380279541, "global_step": 446567, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.142184019088745, "global_step": 446568, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1874823570251465, "global_step": 446569, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.129591941833496, "global_step": 446570, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.019486665725708, "global_step": 446571, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1362903118133545, "global_step": 446572, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.087587833404541, "global_step": 446573, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.135493278503418, "global_step": 446574, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.097829818725586, "global_step": 446575, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.164492607116699, "global_step": 446576, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.121150493621826, "global_step": 446577, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1486446857452393, "global_step": 446578, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9642188549041748, "global_step": 446579, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.007211446762085, "global_step": 446580, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0644443035125732, "global_step": 446581, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0917766094207764, "global_step": 446582, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0650722980499268, "global_step": 446583, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.133382558822632, "global_step": 446584, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1231720447540283, "global_step": 446585, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1905293464660645, "global_step": 446586, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1091318130493164, "global_step": 446587, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.079195261001587, "global_step": 446588, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.2120466232299805, "global_step": 446589, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9433557987213135, "global_step": 446590, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.095672607421875, "global_step": 446591, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.062727689743042, "global_step": 446592, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0137858390808105, "global_step": 446593, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1772563457489014, "global_step": 446594, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1165614128112793, "global_step": 446595, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.100689172744751, "global_step": 446596, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9771440029144287, "global_step": 446597, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.021294593811035, "global_step": 446598, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1686739921569824, "global_step": 446599, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.078667163848877, "global_step": 446600, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0615124702453613, "global_step": 446601, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0785675048828125, "global_step": 446602, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.06591796875, "global_step": 446603, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0903778076171875, "global_step": 446604, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.086829423904419, "global_step": 446605, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.144892692565918, "global_step": 446606, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.165083646774292, "global_step": 446607, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.994627594947815, "global_step": 446608, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0817208290100098, "global_step": 446609, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.038177490234375, "global_step": 446610, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.128312349319458, "global_step": 446611, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.155137777328491, "global_step": 446612, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0534842014312744, "global_step": 446613, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9818733930587769, "global_step": 446614, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0614254474639893, "global_step": 446615, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0616507530212402, "global_step": 446616, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0929195880889893, "global_step": 446617, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0552103519439697, "global_step": 446618, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1110751628875732, "global_step": 446619, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0967659950256348, "global_step": 446620, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.11489200592041, "global_step": 446621, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0997462272644043, "global_step": 446622, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.120337963104248, "global_step": 446623, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.051604986190796, "global_step": 446624, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0786349773406982, "global_step": 446625, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0547542572021484, "global_step": 446626, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.045764923095703, "global_step": 446627, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.040438652038574, "global_step": 446628, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.055814027786255, "global_step": 446629, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.128765106201172, "global_step": 446630, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0609805583953857, "global_step": 446631, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0399744510650635, "global_step": 446632, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1016159057617188, "global_step": 446633, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.079651117324829, "global_step": 446634, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0499167442321777, "global_step": 446635, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0139522552490234, "global_step": 446636, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.03871488571167, "global_step": 446637, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1270499229431152, "global_step": 446638, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0451815128326416, "global_step": 446639, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1442134380340576, "global_step": 446640, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.097118616104126, "global_step": 446641, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0657765865325928, "global_step": 446642, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.145364284515381, "global_step": 446643, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9876731634140015, "global_step": 446644, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0126686096191406, "global_step": 446645, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.19408917427063, "global_step": 446646, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.062127113342285, "global_step": 446647, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.101088762283325, "global_step": 446648, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9895811080932617, "global_step": 446649, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0499355792999268, "global_step": 446650, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.066265821456909, "global_step": 446651, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0791423320770264, "global_step": 446652, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.031555652618408, "global_step": 446653, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0926363468170166, "global_step": 446654, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.096086025238037, "global_step": 446655, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.046294689178467, "global_step": 446656, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0657899379730225, "global_step": 446657, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.108652353286743, "global_step": 446658, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.139228582382202, "global_step": 446659, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.039154291152954, "global_step": 446660, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0615313053131104, "global_step": 446661, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0320193767547607, "global_step": 446662, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1005353927612305, "global_step": 446663, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0696589946746826, "global_step": 446664, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0941526889801025, "global_step": 446665, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0937862396240234, "global_step": 446666, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.074568271636963, "global_step": 446667, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9882341623306274, "global_step": 446668, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0694222450256348, "global_step": 446669, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1058802604675293, "global_step": 446670, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0237443447113037, "global_step": 446671, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0868983268737793, "global_step": 446672, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0690250396728516, "global_step": 446673, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.094038963317871, "global_step": 446674, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0782546997070312, "global_step": 446675, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0988998413085938, "global_step": 446676, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1125316619873047, "global_step": 446677, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0457489490509033, "global_step": 446678, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.182587146759033, "global_step": 446679, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0787513256073, "global_step": 446680, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.052131414413452, "global_step": 446681, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.104342460632324, "global_step": 446682, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0692360401153564, "global_step": 446683, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1040422916412354, "global_step": 446684, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0548107624053955, "global_step": 446685, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0550386905670166, "global_step": 446686, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0770163536071777, "global_step": 446687, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.073319911956787, "global_step": 446688, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.046863317489624, "global_step": 446689, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.050266981124878, "global_step": 446690, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1051485538482666, "global_step": 446691, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0662872791290283, "global_step": 446692, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1536648273468018, "global_step": 446693, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0894734859466553, "global_step": 446694, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0959579944610596, "global_step": 446695, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0408592224121094, "global_step": 446696, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9766883850097656, "global_step": 446697, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0971760749816895, "global_step": 446698, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0972769260406494, "global_step": 446699, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0911190509796143, "global_step": 446700, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0957088470458984, "global_step": 446701, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9869632720947266, "global_step": 446702, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.092859983444214, "global_step": 446703, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.04522705078125, "global_step": 446704, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.039297580718994, "global_step": 446705, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0091519355773926, "global_step": 446706, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.06048846244812, "global_step": 446707, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.068936824798584, "global_step": 446708, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.078169822692871, "global_step": 446709, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0414388179779053, "global_step": 446710, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1087112426757812, "global_step": 446711, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1306183338165283, "global_step": 446712, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.081639289855957, "global_step": 446713, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.092649221420288, "global_step": 446714, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.172839879989624, "global_step": 446715, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.093233108520508, "global_step": 446716, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.090956449508667, "global_step": 446717, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0682225227355957, "global_step": 446718, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.210087299346924, "global_step": 446719, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0868682861328125, "global_step": 446720, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1037750244140625, "global_step": 446721, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1085665225982666, "global_step": 446722, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.100996732711792, "global_step": 446723, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1242289543151855, "global_step": 446724, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1327502727508545, "global_step": 446725, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0043909549713135, "global_step": 446726, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1173224449157715, "global_step": 446727, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.050931453704834, "global_step": 446728, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.084721565246582, "global_step": 446729, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0727686882019043, "global_step": 446730, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.104403018951416, "global_step": 446731, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1242904663085938, "global_step": 446732, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1276955604553223, "global_step": 446733, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9992560148239136, "global_step": 446734, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0370545387268066, "global_step": 446735, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0205588340759277, "global_step": 446736, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0216493606567383, "global_step": 446737, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0988430976867676, "global_step": 446738, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0675551891326904, "global_step": 446739, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.987196922302246, "global_step": 446740, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1072773933410645, "global_step": 446741, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1129062175750732, "global_step": 446742, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1059374809265137, "global_step": 446743, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0494611263275146, "global_step": 446744, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9813799858093262, "global_step": 446745, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.153111696243286, "global_step": 446746, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.145317316055298, "global_step": 446747, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.15327525138855, "global_step": 446748, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0642337799072266, "global_step": 446749, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0738213062286377, "global_step": 446750, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.065237045288086, "global_step": 446751, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.055147171020508, "global_step": 446752, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.157055616378784, "global_step": 446753, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1674814224243164, "global_step": 446754, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0595781803131104, "global_step": 446755, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0459039211273193, "global_step": 446756, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.039433002471924, "global_step": 446757, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.04370379447937, "global_step": 446758, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.21152925491333, "global_step": 446759, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.103536367416382, "global_step": 446760, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0447487831115723, "global_step": 446761, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1389992237091064, "global_step": 446762, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.099647283554077, "global_step": 446763, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0822789669036865, "global_step": 446764, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.031418561935425, "global_step": 446765, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0857505798339844, "global_step": 446766, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.142249584197998, "global_step": 446767, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0657308101654053, "global_step": 446768, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1675398349761963, "global_step": 446769, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.986030101776123, "global_step": 446770, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0599517822265625, "global_step": 446771, "epoch": 810, "lr": 5e-05}
{"train_loss": 1.9874387979507446, "global_step": 446772, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.151472568511963, "global_step": 446773, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.100210189819336, "global_step": 446774, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1735997200012207, "global_step": 446775, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0476763248443604, "global_step": 446776, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0933589935302734, "global_step": 446777, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.097848415374756, "global_step": 446778, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.095430850982666, "global_step": 446779, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.045456886291504, "global_step": 446780, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0893263816833496, "global_step": 446781, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.107151746749878, "global_step": 446782, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1323068141937256, "global_step": 446783, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1259281635284424, "global_step": 446784, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.03554368019104, "global_step": 446785, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0215463638305664, "global_step": 446786, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1728081703186035, "global_step": 446787, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.081474542617798, "global_step": 446788, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0156216621398926, "global_step": 446789, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1478965282440186, "global_step": 446790, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1330149173736572, "global_step": 446791, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1079301834106445, "global_step": 446792, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.07236385345459, "global_step": 446793, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.116672992706299, "global_step": 446794, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0530807971954346, "global_step": 446795, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.087703227996826, "global_step": 446796, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.019467353820801, "global_step": 446797, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.151153326034546, "global_step": 446798, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.2183406352996826, "global_step": 446799, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.116669178009033, "global_step": 446800, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.101125478744507, "global_step": 446801, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0610671043395996, "global_step": 446802, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0836915969848633, "global_step": 446803, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0684926509857178, "global_step": 446804, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.101715087890625, "global_step": 446805, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.037107467651367, "global_step": 446806, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0564260482788086, "global_step": 446807, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.116206169128418, "global_step": 446808, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0838563442230225, "global_step": 446809, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.123915910720825, "global_step": 446810, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.105022668838501, "global_step": 446811, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.048635482788086, "global_step": 446812, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1230926513671875, "global_step": 446813, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0036022663116455, "global_step": 446814, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0420897006988525, "global_step": 446815, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.114673137664795, "global_step": 446816, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.124202251434326, "global_step": 446817, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.029379367828369, "global_step": 446818, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1328721046447754, "global_step": 446819, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.051673412322998, "global_step": 446820, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.11505126953125, "global_step": 446821, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0717430114746094, "global_step": 446822, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0727570056915283, "global_step": 446823, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.129027843475342, "global_step": 446824, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0732367038726807, "global_step": 446825, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0541882514953613, "global_step": 446826, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0856173038482666, "global_step": 446827, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.12911057472229, "global_step": 446828, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.127795934677124, "global_step": 446829, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0680949687957764, "global_step": 446830, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.113067626953125, "global_step": 446831, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.1288769245147705, "global_step": 446832, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0834157466888428, "global_step": 446833, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.080801010131836, "global_step": 446834, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.085036039352417, "global_step": 446835, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.018378257751465, "global_step": 446836, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0595309734344482, "global_step": 446837, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.034980297088623, "global_step": 446838, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.108438014984131, "global_step": 446839, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0557050704956055, "global_step": 446840, "epoch": 810, "lr": 5e-05}
{"train_loss": 2.0757999420166016, "global_step": 446841, "epoch": 810, "lr": 5e-05, "val_loss": 5.673339366912842, "test_reconst_mse": 0.07346972078084946}
{"train_loss": 2.0802032947540283, "global_step": 446842, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0353221893310547, "global_step": 446843, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0275754928588867, "global_step": 446844, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0423977375030518, "global_step": 446845, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1388542652130127, "global_step": 446846, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0696911811828613, "global_step": 446847, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1110568046569824, "global_step": 446848, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0746781826019287, "global_step": 446849, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.099334239959717, "global_step": 446850, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.116515636444092, "global_step": 446851, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.081937551498413, "global_step": 446852, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.110675573348999, "global_step": 446853, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.115469217300415, "global_step": 446854, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.06014084815979, "global_step": 446855, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0871529579162598, "global_step": 446856, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0932247638702393, "global_step": 446857, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0446364879608154, "global_step": 446858, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.115689754486084, "global_step": 446859, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.061886787414551, "global_step": 446860, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0875210762023926, "global_step": 446861, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0742056369781494, "global_step": 446862, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1235735416412354, "global_step": 446863, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.991995930671692, "global_step": 446864, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9757112264633179, "global_step": 446865, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0322391986846924, "global_step": 446866, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9115461111068726, "global_step": 446867, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.009793996810913, "global_step": 446868, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1257543563842773, "global_step": 446869, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0065155029296875, "global_step": 446870, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1378891468048096, "global_step": 446871, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.076918840408325, "global_step": 446872, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0110762119293213, "global_step": 446873, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0363247394561768, "global_step": 446874, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.119736909866333, "global_step": 446875, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.075515031814575, "global_step": 446876, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1020348072052, "global_step": 446877, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.105767250061035, "global_step": 446878, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0366814136505127, "global_step": 446879, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.069688081741333, "global_step": 446880, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1495542526245117, "global_step": 446881, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9600695371627808, "global_step": 446882, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.949240803718567, "global_step": 446883, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0657951831817627, "global_step": 446884, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9830293655395508, "global_step": 446885, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.012080430984497, "global_step": 446886, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.027055025100708, "global_step": 446887, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.068192720413208, "global_step": 446888, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1626570224761963, "global_step": 446889, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0365285873413086, "global_step": 446890, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.120119333267212, "global_step": 446891, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.008094310760498, "global_step": 446892, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0607752799987793, "global_step": 446893, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0281195640563965, "global_step": 446894, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.018955707550049, "global_step": 446895, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.019057512283325, "global_step": 446896, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0764048099517822, "global_step": 446897, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.092092752456665, "global_step": 446898, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1219093799591064, "global_step": 446899, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0903735160827637, "global_step": 446900, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.074415683746338, "global_step": 446901, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1136605739593506, "global_step": 446902, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1139464378356934, "global_step": 446903, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0774831771850586, "global_step": 446904, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.079699993133545, "global_step": 446905, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.09430193901062, "global_step": 446906, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.105731248855591, "global_step": 446907, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.007089138031006, "global_step": 446908, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0693888664245605, "global_step": 446909, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0977094173431396, "global_step": 446910, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.088226795196533, "global_step": 446911, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0636210441589355, "global_step": 446912, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.094763994216919, "global_step": 446913, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0798604488372803, "global_step": 446914, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.078892946243286, "global_step": 446915, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.056715965270996, "global_step": 446916, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0503501892089844, "global_step": 446917, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1374011039733887, "global_step": 446918, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0679922103881836, "global_step": 446919, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9750256538391113, "global_step": 446920, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.168566942214966, "global_step": 446921, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.068467140197754, "global_step": 446922, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.077662229537964, "global_step": 446923, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.041135787963867, "global_step": 446924, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.035794734954834, "global_step": 446925, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9196476936340332, "global_step": 446926, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0627973079681396, "global_step": 446927, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0191540718078613, "global_step": 446928, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.031543016433716, "global_step": 446929, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.094278335571289, "global_step": 446930, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9937490224838257, "global_step": 446931, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9774878025054932, "global_step": 446932, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0648016929626465, "global_step": 446933, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0611393451690674, "global_step": 446934, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0756161212921143, "global_step": 446935, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0001888275146484, "global_step": 446936, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0060033798217773, "global_step": 446937, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.071500301361084, "global_step": 446938, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.053288459777832, "global_step": 446939, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1364951133728027, "global_step": 446940, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.038839340209961, "global_step": 446941, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0273165702819824, "global_step": 446942, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.078268051147461, "global_step": 446943, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1301538944244385, "global_step": 446944, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0747568607330322, "global_step": 446945, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1369869709014893, "global_step": 446946, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0174129009246826, "global_step": 446947, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9646358489990234, "global_step": 446948, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1316328048706055, "global_step": 446949, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0581297874450684, "global_step": 446950, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.064689874649048, "global_step": 446951, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.046739339828491, "global_step": 446952, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.086737871170044, "global_step": 446953, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0213727951049805, "global_step": 446954, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.081773281097412, "global_step": 446955, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.094437837600708, "global_step": 446956, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.06361722946167, "global_step": 446957, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.057786226272583, "global_step": 446958, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.117985725402832, "global_step": 446959, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0282280445098877, "global_step": 446960, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.041618585586548, "global_step": 446961, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1271426677703857, "global_step": 446962, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1023902893066406, "global_step": 446963, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9127267599105835, "global_step": 446964, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.125546932220459, "global_step": 446965, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0024590492248535, "global_step": 446966, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0421197414398193, "global_step": 446967, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0743560791015625, "global_step": 446968, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.041825294494629, "global_step": 446969, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.10994029045105, "global_step": 446970, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1507513523101807, "global_step": 446971, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.140004873275757, "global_step": 446972, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.043412446975708, "global_step": 446973, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0972886085510254, "global_step": 446974, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1796932220458984, "global_step": 446975, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0047385692596436, "global_step": 446976, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.076948404312134, "global_step": 446977, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0437610149383545, "global_step": 446978, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0254886150360107, "global_step": 446979, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.093573570251465, "global_step": 446980, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0352935791015625, "global_step": 446981, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.106029987335205, "global_step": 446982, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0373411178588867, "global_step": 446983, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0029914379119873, "global_step": 446984, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0898945331573486, "global_step": 446985, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0428996086120605, "global_step": 446986, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.081789970397949, "global_step": 446987, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0744006633758545, "global_step": 446988, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.023559808731079, "global_step": 446989, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0442452430725098, "global_step": 446990, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.01529860496521, "global_step": 446991, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.04233717918396, "global_step": 446992, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9900550842285156, "global_step": 446993, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.143486499786377, "global_step": 446994, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0661067962646484, "global_step": 446995, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.073714017868042, "global_step": 446996, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0522327423095703, "global_step": 446997, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0706064701080322, "global_step": 446998, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1064741611480713, "global_step": 446999, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0491342544555664, "global_step": 447000, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0301125049591064, "global_step": 447001, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.018221616744995, "global_step": 447002, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.040759563446045, "global_step": 447003, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0485172271728516, "global_step": 447004, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0369772911071777, "global_step": 447005, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.096510648727417, "global_step": 447006, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.013497829437256, "global_step": 447007, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.072723150253296, "global_step": 447008, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1023190021514893, "global_step": 447009, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1928911209106445, "global_step": 447010, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9756799936294556, "global_step": 447011, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0795738697052, "global_step": 447012, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0506510734558105, "global_step": 447013, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9440046548843384, "global_step": 447014, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1071741580963135, "global_step": 447015, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.062535047531128, "global_step": 447016, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0246894359588623, "global_step": 447017, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.018876075744629, "global_step": 447018, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.122751474380493, "global_step": 447019, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.072082042694092, "global_step": 447020, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0259461402893066, "global_step": 447021, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1238062381744385, "global_step": 447022, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.104363203048706, "global_step": 447023, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.093642234802246, "global_step": 447024, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9681572914123535, "global_step": 447025, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.014314889907837, "global_step": 447026, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0638344287872314, "global_step": 447027, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.074336528778076, "global_step": 447028, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9979504346847534, "global_step": 447029, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0507164001464844, "global_step": 447030, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.108139753341675, "global_step": 447031, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0378174781799316, "global_step": 447032, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.030519485473633, "global_step": 447033, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0828704833984375, "global_step": 447034, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.109011650085449, "global_step": 447035, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0283331871032715, "global_step": 447036, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.087747573852539, "global_step": 447037, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.085753917694092, "global_step": 447038, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.056685447692871, "global_step": 447039, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0102992057800293, "global_step": 447040, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.063194513320923, "global_step": 447041, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.007803440093994, "global_step": 447042, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0931003093719482, "global_step": 447043, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.076267719268799, "global_step": 447044, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.043226957321167, "global_step": 447045, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.123185873031616, "global_step": 447046, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1721410751342773, "global_step": 447047, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0335440635681152, "global_step": 447048, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.060492753982544, "global_step": 447049, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.022707223892212, "global_step": 447050, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0361480712890625, "global_step": 447051, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1140480041503906, "global_step": 447052, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.030787467956543, "global_step": 447053, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.03096342086792, "global_step": 447054, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.099442481994629, "global_step": 447055, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.042386531829834, "global_step": 447056, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0784547328948975, "global_step": 447057, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1522765159606934, "global_step": 447058, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9922473430633545, "global_step": 447059, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0107901096343994, "global_step": 447060, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0824134349823, "global_step": 447061, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1218631267547607, "global_step": 447062, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9765185117721558, "global_step": 447063, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0551974773406982, "global_step": 447064, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1630375385284424, "global_step": 447065, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.062185049057007, "global_step": 447066, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9974323511123657, "global_step": 447067, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0425357818603516, "global_step": 447068, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.006844997406006, "global_step": 447069, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.094982862472534, "global_step": 447070, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0543038845062256, "global_step": 447071, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.990334391593933, "global_step": 447072, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0218303203582764, "global_step": 447073, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0345327854156494, "global_step": 447074, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.131176471710205, "global_step": 447075, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0703680515289307, "global_step": 447076, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0963876247406006, "global_step": 447077, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1303701400756836, "global_step": 447078, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.090090036392212, "global_step": 447079, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9425876140594482, "global_step": 447080, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1191489696502686, "global_step": 447081, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0510268211364746, "global_step": 447082, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0781400203704834, "global_step": 447083, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.074162006378174, "global_step": 447084, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0133121013641357, "global_step": 447085, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.092752695083618, "global_step": 447086, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1459500789642334, "global_step": 447087, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.098698616027832, "global_step": 447088, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.03867244720459, "global_step": 447089, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.116018772125244, "global_step": 447090, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1639487743377686, "global_step": 447091, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.020297050476074, "global_step": 447092, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.053318500518799, "global_step": 447093, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.090142011642456, "global_step": 447094, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0395212173461914, "global_step": 447095, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0770952701568604, "global_step": 447096, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1956846714019775, "global_step": 447097, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0967295169830322, "global_step": 447098, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.145324230194092, "global_step": 447099, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0122785568237305, "global_step": 447100, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1166818141937256, "global_step": 447101, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0614616870880127, "global_step": 447102, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0489649772644043, "global_step": 447103, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.104599952697754, "global_step": 447104, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0066826343536377, "global_step": 447105, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0910911560058594, "global_step": 447106, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.080650806427002, "global_step": 447107, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.095700740814209, "global_step": 447108, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0378873348236084, "global_step": 447109, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1911392211914062, "global_step": 447110, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1283154487609863, "global_step": 447111, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.072270631790161, "global_step": 447112, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9978601932525635, "global_step": 447113, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0335493087768555, "global_step": 447114, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0292530059814453, "global_step": 447115, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1270055770874023, "global_step": 447116, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.047825336456299, "global_step": 447117, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1401987075805664, "global_step": 447118, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0539917945861816, "global_step": 447119, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1173057556152344, "global_step": 447120, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.131056070327759, "global_step": 447121, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0454351902008057, "global_step": 447122, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.068110942840576, "global_step": 447123, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0854179859161377, "global_step": 447124, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0012869834899902, "global_step": 447125, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9992361068725586, "global_step": 447126, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.158546209335327, "global_step": 447127, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0699493885040283, "global_step": 447128, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0679028034210205, "global_step": 447129, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9747273921966553, "global_step": 447130, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.032015085220337, "global_step": 447131, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.031853675842285, "global_step": 447132, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0602121353149414, "global_step": 447133, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0767035484313965, "global_step": 447134, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.110184907913208, "global_step": 447135, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.015423536300659, "global_step": 447136, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.136399030685425, "global_step": 447137, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1768195629119873, "global_step": 447138, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0962746143341064, "global_step": 447139, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0876293182373047, "global_step": 447140, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0674636363983154, "global_step": 447141, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.167638063430786, "global_step": 447142, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.986391544342041, "global_step": 447143, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0732407569885254, "global_step": 447144, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.050074815750122, "global_step": 447145, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0110793113708496, "global_step": 447146, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.044774055480957, "global_step": 447147, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0782899856567383, "global_step": 447148, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0649759769439697, "global_step": 447149, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0979902744293213, "global_step": 447150, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0673067569732666, "global_step": 447151, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.129293441772461, "global_step": 447152, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0329079627990723, "global_step": 447153, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.049089193344116, "global_step": 447154, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0989372730255127, "global_step": 447155, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0906081199645996, "global_step": 447156, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1430346965789795, "global_step": 447157, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9680461883544922, "global_step": 447158, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0919878482818604, "global_step": 447159, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0747625827789307, "global_step": 447160, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1337826251983643, "global_step": 447161, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.040008783340454, "global_step": 447162, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.096823215484619, "global_step": 447163, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0683109760284424, "global_step": 447164, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9570269584655762, "global_step": 447165, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.075300931930542, "global_step": 447166, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0886802673339844, "global_step": 447167, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0599563121795654, "global_step": 447168, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1154279708862305, "global_step": 447169, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0596795082092285, "global_step": 447170, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0775082111358643, "global_step": 447171, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0647571086883545, "global_step": 447172, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1451432704925537, "global_step": 447173, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0637784004211426, "global_step": 447174, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.088792085647583, "global_step": 447175, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1179370880126953, "global_step": 447176, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.053537130355835, "global_step": 447177, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.061764717102051, "global_step": 447178, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.077965021133423, "global_step": 447179, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0936548709869385, "global_step": 447180, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0486621856689453, "global_step": 447181, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1377792358398438, "global_step": 447182, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.096425771713257, "global_step": 447183, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0588836669921875, "global_step": 447184, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.120983600616455, "global_step": 447185, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.134092330932617, "global_step": 447186, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0389046669006348, "global_step": 447187, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0372543334960938, "global_step": 447188, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0838816165924072, "global_step": 447189, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.026634454727173, "global_step": 447190, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.172991991043091, "global_step": 447191, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.100123882293701, "global_step": 447192, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.098541021347046, "global_step": 447193, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1249020099639893, "global_step": 447194, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0717172622680664, "global_step": 447195, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0620815753936768, "global_step": 447196, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0521767139434814, "global_step": 447197, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0986440181732178, "global_step": 447198, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.079738140106201, "global_step": 447199, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.959886908531189, "global_step": 447200, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0851776599884033, "global_step": 447201, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.003647804260254, "global_step": 447202, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0873563289642334, "global_step": 447203, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0077853202819824, "global_step": 447204, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0966053009033203, "global_step": 447205, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.068962812423706, "global_step": 447206, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.032264471054077, "global_step": 447207, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0497922897338867, "global_step": 447208, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1446359157562256, "global_step": 447209, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.174844741821289, "global_step": 447210, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9841125011444092, "global_step": 447211, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.097632646560669, "global_step": 447212, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0363714694976807, "global_step": 447213, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1306912899017334, "global_step": 447214, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0653934478759766, "global_step": 447215, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0548083782196045, "global_step": 447216, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0634357929229736, "global_step": 447217, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.118633270263672, "global_step": 447218, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.070094585418701, "global_step": 447219, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0680253505706787, "global_step": 447220, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.060279130935669, "global_step": 447221, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1101675033569336, "global_step": 447222, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.058526039123535, "global_step": 447223, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.087663412094116, "global_step": 447224, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1496543884277344, "global_step": 447225, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.018662691116333, "global_step": 447226, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.063701629638672, "global_step": 447227, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0917015075683594, "global_step": 447228, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.102099657058716, "global_step": 447229, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.170267105102539, "global_step": 447230, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1139440536499023, "global_step": 447231, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.055570125579834, "global_step": 447232, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1401610374450684, "global_step": 447233, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.069052219390869, "global_step": 447234, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.005066156387329, "global_step": 447235, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.115703582763672, "global_step": 447236, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0008342266082764, "global_step": 447237, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1174094676971436, "global_step": 447238, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1556007862091064, "global_step": 447239, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.06083083152771, "global_step": 447240, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0374722480773926, "global_step": 447241, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0774734020233154, "global_step": 447242, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.060110330581665, "global_step": 447243, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.006754159927368, "global_step": 447244, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0756216049194336, "global_step": 447245, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0898847579956055, "global_step": 447246, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0197513103485107, "global_step": 447247, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1528351306915283, "global_step": 447248, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1971445083618164, "global_step": 447249, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0493671894073486, "global_step": 447250, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.058624744415283, "global_step": 447251, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.062487840652466, "global_step": 447252, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.101573944091797, "global_step": 447253, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0873072147369385, "global_step": 447254, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0284814834594727, "global_step": 447255, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0467734336853027, "global_step": 447256, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.017957925796509, "global_step": 447257, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.060028553009033, "global_step": 447258, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0038881301879883, "global_step": 447259, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.028130292892456, "global_step": 447260, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.008448362350464, "global_step": 447261, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1227645874023438, "global_step": 447262, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0569326877593994, "global_step": 447263, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.072573661804199, "global_step": 447264, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0394411087036133, "global_step": 447265, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.089040517807007, "global_step": 447266, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0104522705078125, "global_step": 447267, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.964322805404663, "global_step": 447268, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.215991973876953, "global_step": 447269, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.117384433746338, "global_step": 447270, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.179776430130005, "global_step": 447271, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0888984203338623, "global_step": 447272, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0268919467926025, "global_step": 447273, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0306413173675537, "global_step": 447274, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.053675651550293, "global_step": 447275, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.081268787384033, "global_step": 447276, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1240644454956055, "global_step": 447277, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0312914848327637, "global_step": 447278, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.093295097351074, "global_step": 447279, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.048537254333496, "global_step": 447280, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0726728439331055, "global_step": 447281, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1213958263397217, "global_step": 447282, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.098634958267212, "global_step": 447283, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.133070230484009, "global_step": 447284, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.031215190887451, "global_step": 447285, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0262043476104736, "global_step": 447286, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.087063789367676, "global_step": 447287, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9801362752914429, "global_step": 447288, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0935957431793213, "global_step": 447289, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9893709421157837, "global_step": 447290, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0018458366394043, "global_step": 447291, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1316025257110596, "global_step": 447292, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.136223793029785, "global_step": 447293, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.034376621246338, "global_step": 447294, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1414921283721924, "global_step": 447295, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9592286348342896, "global_step": 447296, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.075894594192505, "global_step": 447297, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1865689754486084, "global_step": 447298, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.065608501434326, "global_step": 447299, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1051621437072754, "global_step": 447300, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1204898357391357, "global_step": 447301, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.074119806289673, "global_step": 447302, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1283364295959473, "global_step": 447303, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1725807189941406, "global_step": 447304, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9878971576690674, "global_step": 447305, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.155416965484619, "global_step": 447306, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0775563716888428, "global_step": 447307, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1010940074920654, "global_step": 447308, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.117161750793457, "global_step": 447309, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.011810541152954, "global_step": 447310, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0850670337677, "global_step": 447311, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.998665690422058, "global_step": 447312, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9944151639938354, "global_step": 447313, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0043323040008545, "global_step": 447314, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.114105224609375, "global_step": 447315, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0842907428741455, "global_step": 447316, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0785512924194336, "global_step": 447317, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.139131784439087, "global_step": 447318, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1163792610168457, "global_step": 447319, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1060562133789062, "global_step": 447320, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9956728219985962, "global_step": 447321, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.994124174118042, "global_step": 447322, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.049346685409546, "global_step": 447323, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.136993885040283, "global_step": 447324, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.07619571685791, "global_step": 447325, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.113710403442383, "global_step": 447326, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1545674800872803, "global_step": 447327, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1356780529022217, "global_step": 447328, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.069340944290161, "global_step": 447329, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0970585346221924, "global_step": 447330, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.004317045211792, "global_step": 447331, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0662474632263184, "global_step": 447332, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1151628494262695, "global_step": 447333, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1771020889282227, "global_step": 447334, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.089588165283203, "global_step": 447335, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.224151849746704, "global_step": 447336, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.091261863708496, "global_step": 447337, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.056431770324707, "global_step": 447338, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9656274318695068, "global_step": 447339, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.04689359664917, "global_step": 447340, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.09128737449646, "global_step": 447341, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.21691632270813, "global_step": 447342, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1308205127716064, "global_step": 447343, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.094373941421509, "global_step": 447344, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.062840461730957, "global_step": 447345, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0378355979919434, "global_step": 447346, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0639290809631348, "global_step": 447347, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.097625732421875, "global_step": 447348, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.077359199523926, "global_step": 447349, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1192820072174072, "global_step": 447350, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.162986993789673, "global_step": 447351, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9760247468948364, "global_step": 447352, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0194215774536133, "global_step": 447353, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0232326984405518, "global_step": 447354, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.156348705291748, "global_step": 447355, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.011023998260498, "global_step": 447356, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1525161266326904, "global_step": 447357, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0975914001464844, "global_step": 447358, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9657686948776245, "global_step": 447359, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0965232849121094, "global_step": 447360, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.108945846557617, "global_step": 447361, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.018112897872925, "global_step": 447362, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.116642475128174, "global_step": 447363, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.080211877822876, "global_step": 447364, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0881869792938232, "global_step": 447365, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.161398410797119, "global_step": 447366, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.049189567565918, "global_step": 447367, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9961556196212769, "global_step": 447368, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.105405807495117, "global_step": 447369, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0939135551452637, "global_step": 447370, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.047096014022827, "global_step": 447371, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.079700231552124, "global_step": 447372, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1399121284484863, "global_step": 447373, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1193788051605225, "global_step": 447374, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0990800857543945, "global_step": 447375, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.01780104637146, "global_step": 447376, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0247721672058105, "global_step": 447377, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.072573661804199, "global_step": 447378, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.042686939239502, "global_step": 447379, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.108002185821533, "global_step": 447380, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0574066638946533, "global_step": 447381, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0747010707855225, "global_step": 447382, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.092085123062134, "global_step": 447383, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.06052303314209, "global_step": 447384, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.022681474685669, "global_step": 447385, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.072854995727539, "global_step": 447386, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.139739990234375, "global_step": 447387, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.131164312362671, "global_step": 447388, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0660054683685303, "global_step": 447389, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.029780864715576, "global_step": 447390, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0745954513549805, "global_step": 447391, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.08577561378479, "global_step": 447392, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1956093311309814, "global_step": 447393, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.106198787689209, "global_step": 447394, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0430235862731934, "global_step": 447395, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0712201595306396, "global_step": 447396, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1489415168762207, "global_step": 447397, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1149396896362305, "global_step": 447398, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.106584310531616, "global_step": 447399, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1117231845855713, "global_step": 447400, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9614938497543335, "global_step": 447401, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.131585121154785, "global_step": 447402, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.193122148513794, "global_step": 447403, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.05035400390625, "global_step": 447404, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1104812622070312, "global_step": 447405, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.966904878616333, "global_step": 447406, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0731897354125977, "global_step": 447407, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.115821599960327, "global_step": 447408, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.076655149459839, "global_step": 447409, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0570335388183594, "global_step": 447410, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.980547547340393, "global_step": 447411, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0168685913085938, "global_step": 447412, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0771052837371826, "global_step": 447413, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9742944240570068, "global_step": 447414, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0293967723846436, "global_step": 447415, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1085455417633057, "global_step": 447416, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1228857040405273, "global_step": 447417, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.095909357070923, "global_step": 447418, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.031670331954956, "global_step": 447419, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0593278408050537, "global_step": 447420, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0314881801605225, "global_step": 447421, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.105740547180176, "global_step": 447422, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0955495834350586, "global_step": 447423, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.073002338409424, "global_step": 447424, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1177072525024414, "global_step": 447425, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1120283603668213, "global_step": 447426, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.95634126663208, "global_step": 447427, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.089867353439331, "global_step": 447428, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.10044002532959, "global_step": 447429, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.116879463195801, "global_step": 447430, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0798163414001465, "global_step": 447431, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0435938835144043, "global_step": 447432, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.089664936065674, "global_step": 447433, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.059657096862793, "global_step": 447434, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1247596740722656, "global_step": 447435, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0744481086730957, "global_step": 447436, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0249364376068115, "global_step": 447437, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.074298858642578, "global_step": 447438, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1519994735717773, "global_step": 447439, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1146788597106934, "global_step": 447440, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1007490158081055, "global_step": 447441, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.093714714050293, "global_step": 447442, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0958592891693115, "global_step": 447443, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.990560531616211, "global_step": 447444, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1222383975982666, "global_step": 447445, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1277458667755127, "global_step": 447446, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0429978370666504, "global_step": 447447, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0654969215393066, "global_step": 447448, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1246566772460938, "global_step": 447449, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0783166885375977, "global_step": 447450, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0605525970458984, "global_step": 447451, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1464173793792725, "global_step": 447452, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0677428245544434, "global_step": 447453, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.048706293106079, "global_step": 447454, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.074843645095825, "global_step": 447455, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1253397464752197, "global_step": 447456, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.069781541824341, "global_step": 447457, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.195911407470703, "global_step": 447458, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0170395374298096, "global_step": 447459, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.057978868484497, "global_step": 447460, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0972554683685303, "global_step": 447461, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.091726064682007, "global_step": 447462, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.014526128768921, "global_step": 447463, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1472010612487793, "global_step": 447464, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0860631465911865, "global_step": 447465, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.023081064224243, "global_step": 447466, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1357662677764893, "global_step": 447467, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.051508903503418, "global_step": 447468, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0961170196533203, "global_step": 447469, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.049901247024536, "global_step": 447470, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.131441831588745, "global_step": 447471, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.161116123199463, "global_step": 447472, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.02838134765625, "global_step": 447473, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.059861421585083, "global_step": 447474, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1453254222869873, "global_step": 447475, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0752522945404053, "global_step": 447476, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.064134120941162, "global_step": 447477, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.070908784866333, "global_step": 447478, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0320653915405273, "global_step": 447479, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.166645050048828, "global_step": 447480, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1053929328918457, "global_step": 447481, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0420451164245605, "global_step": 447482, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.083982467651367, "global_step": 447483, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.096057891845703, "global_step": 447484, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.100200653076172, "global_step": 447485, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0316195487976074, "global_step": 447486, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.051245927810669, "global_step": 447487, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0652835369110107, "global_step": 447488, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0772948265075684, "global_step": 447489, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1047658920288086, "global_step": 447490, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1438422203063965, "global_step": 447491, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.092362403869629, "global_step": 447492, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1563594341278076, "global_step": 447493, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0542802810668945, "global_step": 447494, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.083610773086548, "global_step": 447495, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.109029531478882, "global_step": 447496, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9928776025772095, "global_step": 447497, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.037656307220459, "global_step": 447498, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.059715986251831, "global_step": 447499, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.071880578994751, "global_step": 447500, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1289710998535156, "global_step": 447501, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.092942953109741, "global_step": 447502, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0855016708374023, "global_step": 447503, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0456042289733887, "global_step": 447504, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.083732843399048, "global_step": 447505, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.117523193359375, "global_step": 447506, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1478946208953857, "global_step": 447507, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.077852964401245, "global_step": 447508, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1052606105804443, "global_step": 447509, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.104593276977539, "global_step": 447510, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0503804683685303, "global_step": 447511, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.125606060028076, "global_step": 447512, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.023590087890625, "global_step": 447513, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0846052169799805, "global_step": 447514, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.170121431350708, "global_step": 447515, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.002019166946411, "global_step": 447516, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.003046751022339, "global_step": 447517, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.042181968688965, "global_step": 447518, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.025251865386963, "global_step": 447519, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.097433090209961, "global_step": 447520, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1480939388275146, "global_step": 447521, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0350828170776367, "global_step": 447522, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0767133235931396, "global_step": 447523, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.152711868286133, "global_step": 447524, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0003628730773926, "global_step": 447525, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0842177867889404, "global_step": 447526, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.099397659301758, "global_step": 447527, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.114419460296631, "global_step": 447528, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0011065006256104, "global_step": 447529, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0197596549987793, "global_step": 447530, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9865769147872925, "global_step": 447531, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0899577140808105, "global_step": 447532, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1091485023498535, "global_step": 447533, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.115293502807617, "global_step": 447534, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1268978118896484, "global_step": 447535, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1675772666931152, "global_step": 447536, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0865793228149414, "global_step": 447537, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.078662872314453, "global_step": 447538, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0773890018463135, "global_step": 447539, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.998932957649231, "global_step": 447540, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9845796823501587, "global_step": 447541, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0142874717712402, "global_step": 447542, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1134183406829834, "global_step": 447543, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0771384239196777, "global_step": 447544, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1014034748077393, "global_step": 447545, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0506293773651123, "global_step": 447546, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.105642318725586, "global_step": 447547, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0177695751190186, "global_step": 447548, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0761640071868896, "global_step": 447549, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0684356689453125, "global_step": 447550, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9953418970108032, "global_step": 447551, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0505523681640625, "global_step": 447552, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1044905185699463, "global_step": 447553, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1084299087524414, "global_step": 447554, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1838910579681396, "global_step": 447555, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.127500057220459, "global_step": 447556, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0700008869171143, "global_step": 447557, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.024822473526001, "global_step": 447558, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.051257371902466, "global_step": 447559, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0330119132995605, "global_step": 447560, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0559990406036377, "global_step": 447561, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.119046211242676, "global_step": 447562, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0744106769561768, "global_step": 447563, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.094465494155884, "global_step": 447564, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1293110847473145, "global_step": 447565, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0443105697631836, "global_step": 447566, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.17486834526062, "global_step": 447567, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.089123249053955, "global_step": 447568, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.147127151489258, "global_step": 447569, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0809805393218994, "global_step": 447570, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0924243927001953, "global_step": 447571, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0009822845458984, "global_step": 447572, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0630571842193604, "global_step": 447573, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0509912967681885, "global_step": 447574, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.014599084854126, "global_step": 447575, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0237903594970703, "global_step": 447576, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.111158847808838, "global_step": 447577, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.097365140914917, "global_step": 447578, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9958571195602417, "global_step": 447579, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0960493087768555, "global_step": 447580, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1255195140838623, "global_step": 447581, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0897746086120605, "global_step": 447582, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0652577877044678, "global_step": 447583, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1465275287628174, "global_step": 447584, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0589370727539062, "global_step": 447585, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.187898635864258, "global_step": 447586, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0765554904937744, "global_step": 447587, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1657931804656982, "global_step": 447588, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.109567880630493, "global_step": 447589, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1832478046417236, "global_step": 447590, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0712602138519287, "global_step": 447591, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.049497127532959, "global_step": 447592, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.068939685821533, "global_step": 447593, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0822579860687256, "global_step": 447594, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.136953830718994, "global_step": 447595, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.067366123199463, "global_step": 447596, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.068411350250244, "global_step": 447597, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0435495376586914, "global_step": 447598, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1429812908172607, "global_step": 447599, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0998036861419678, "global_step": 447600, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0821897983551025, "global_step": 447601, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0536141395568848, "global_step": 447602, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.223127841949463, "global_step": 447603, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0205185413360596, "global_step": 447604, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0618221759796143, "global_step": 447605, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0950403213500977, "global_step": 447606, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.050959825515747, "global_step": 447607, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.036038637161255, "global_step": 447608, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1238605976104736, "global_step": 447609, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.088043212890625, "global_step": 447610, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.013216495513916, "global_step": 447611, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.089694023132324, "global_step": 447612, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1799960136413574, "global_step": 447613, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.072661876678467, "global_step": 447614, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1120965480804443, "global_step": 447615, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.100618600845337, "global_step": 447616, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0567328929901123, "global_step": 447617, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.104327917098999, "global_step": 447618, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.976502537727356, "global_step": 447619, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0397677421569824, "global_step": 447620, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0441207885742188, "global_step": 447621, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0585403442382812, "global_step": 447622, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1612541675567627, "global_step": 447623, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.056364059448242, "global_step": 447624, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.006462574005127, "global_step": 447625, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.007160186767578, "global_step": 447626, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0818052291870117, "global_step": 447627, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.000868082046509, "global_step": 447628, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0747616291046143, "global_step": 447629, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0568063259124756, "global_step": 447630, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.996998906135559, "global_step": 447631, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0818910598754883, "global_step": 447632, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0632991790771484, "global_step": 447633, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.079929828643799, "global_step": 447634, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.071598768234253, "global_step": 447635, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.108870267868042, "global_step": 447636, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9921469688415527, "global_step": 447637, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.116746187210083, "global_step": 447638, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0571985244750977, "global_step": 447639, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1361396312713623, "global_step": 447640, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0992300510406494, "global_step": 447641, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0498223304748535, "global_step": 447642, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0708532333374023, "global_step": 447643, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.02578067779541, "global_step": 447644, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1053762435913086, "global_step": 447645, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0315659046173096, "global_step": 447646, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.025085687637329, "global_step": 447647, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1385343074798584, "global_step": 447648, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0868899822235107, "global_step": 447649, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.018251895904541, "global_step": 447650, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0751900672912598, "global_step": 447651, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0624966621398926, "global_step": 447652, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.115615129470825, "global_step": 447653, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9647384881973267, "global_step": 447654, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1028125286102295, "global_step": 447655, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9817328453063965, "global_step": 447656, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.086787700653076, "global_step": 447657, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.011296510696411, "global_step": 447658, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.053863286972046, "global_step": 447659, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9849485158920288, "global_step": 447660, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.132873773574829, "global_step": 447661, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.055162191390991, "global_step": 447662, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.08803391456604, "global_step": 447663, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.057576894760132, "global_step": 447664, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9972609281539917, "global_step": 447665, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9950549602508545, "global_step": 447666, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1546683311462402, "global_step": 447667, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.049870014190674, "global_step": 447668, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1343653202056885, "global_step": 447669, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0782454013824463, "global_step": 447670, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.010373592376709, "global_step": 447671, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.114846706390381, "global_step": 447672, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.126838207244873, "global_step": 447673, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.072617769241333, "global_step": 447674, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.056375503540039, "global_step": 447675, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.132382869720459, "global_step": 447676, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1132912635803223, "global_step": 447677, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1793439388275146, "global_step": 447678, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.109591484069824, "global_step": 447679, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0089111328125, "global_step": 447680, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0630338191986084, "global_step": 447681, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1209466457366943, "global_step": 447682, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0492076873779297, "global_step": 447683, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0466532707214355, "global_step": 447684, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.13114070892334, "global_step": 447685, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.063546895980835, "global_step": 447686, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.042278528213501, "global_step": 447687, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.038257360458374, "global_step": 447688, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1447811126708984, "global_step": 447689, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.03735089302063, "global_step": 447690, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.087322473526001, "global_step": 447691, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.019111156463623, "global_step": 447692, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.102911949157715, "global_step": 447693, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.03310489654541, "global_step": 447694, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.2449653148651123, "global_step": 447695, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.079184055328369, "global_step": 447696, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0440192222595215, "global_step": 447697, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9948543310165405, "global_step": 447698, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0451979637145996, "global_step": 447699, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1098554134368896, "global_step": 447700, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0934925079345703, "global_step": 447701, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0774402618408203, "global_step": 447702, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1137640476226807, "global_step": 447703, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.990785837173462, "global_step": 447704, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.129507541656494, "global_step": 447705, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0099358558654785, "global_step": 447706, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1024298667907715, "global_step": 447707, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.043163776397705, "global_step": 447708, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.053560256958008, "global_step": 447709, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.086545705795288, "global_step": 447710, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1133852005004883, "global_step": 447711, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.151902675628662, "global_step": 447712, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1507794857025146, "global_step": 447713, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1145875453948975, "global_step": 447714, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0477023124694824, "global_step": 447715, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.145106792449951, "global_step": 447716, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.098994255065918, "global_step": 447717, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0390422344207764, "global_step": 447718, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0395126342773438, "global_step": 447719, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0074944496154785, "global_step": 447720, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.121394634246826, "global_step": 447721, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9932355880737305, "global_step": 447722, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1789681911468506, "global_step": 447723, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0563642978668213, "global_step": 447724, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.110816478729248, "global_step": 447725, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0748353004455566, "global_step": 447726, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0026416778564453, "global_step": 447727, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1314408779144287, "global_step": 447728, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.09468936920166, "global_step": 447729, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0352914333343506, "global_step": 447730, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.10408616065979, "global_step": 447731, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1734142303466797, "global_step": 447732, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.033869504928589, "global_step": 447733, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0453219413757324, "global_step": 447734, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0519325733184814, "global_step": 447735, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.103586196899414, "global_step": 447736, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1325266361236572, "global_step": 447737, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.089495897293091, "global_step": 447738, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.083986282348633, "global_step": 447739, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1222686767578125, "global_step": 447740, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0236175060272217, "global_step": 447741, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0380210876464844, "global_step": 447742, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1271004676818848, "global_step": 447743, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.05664324760437, "global_step": 447744, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1020209789276123, "global_step": 447745, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0486388206481934, "global_step": 447746, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1228485107421875, "global_step": 447747, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1658427715301514, "global_step": 447748, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0795834064483643, "global_step": 447749, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0114052295684814, "global_step": 447750, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.09653639793396, "global_step": 447751, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0402252674102783, "global_step": 447752, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0316972732543945, "global_step": 447753, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0963971614837646, "global_step": 447754, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1146068572998047, "global_step": 447755, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0812394618988037, "global_step": 447756, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0135066509246826, "global_step": 447757, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.14536190032959, "global_step": 447758, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0288662910461426, "global_step": 447759, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0553581714630127, "global_step": 447760, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0385868549346924, "global_step": 447761, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0132455825805664, "global_step": 447762, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1110167503356934, "global_step": 447763, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1381285190582275, "global_step": 447764, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.020382881164551, "global_step": 447765, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1141083240509033, "global_step": 447766, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.070558786392212, "global_step": 447767, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.061988353729248, "global_step": 447768, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.033449649810791, "global_step": 447769, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1250545978546143, "global_step": 447770, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0775299072265625, "global_step": 447771, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1563210487365723, "global_step": 447772, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.098667621612549, "global_step": 447773, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.070014476776123, "global_step": 447774, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0177981853485107, "global_step": 447775, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1685330867767334, "global_step": 447776, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.188507556915283, "global_step": 447777, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0780909061431885, "global_step": 447778, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.108520030975342, "global_step": 447779, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0804779529571533, "global_step": 447780, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0750670433044434, "global_step": 447781, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0557944774627686, "global_step": 447782, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.071761131286621, "global_step": 447783, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.945979356765747, "global_step": 447784, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9576739072799683, "global_step": 447785, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1764655113220215, "global_step": 447786, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.075930118560791, "global_step": 447787, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.106342315673828, "global_step": 447788, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.157496213912964, "global_step": 447789, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1813013553619385, "global_step": 447790, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0876851081848145, "global_step": 447791, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.034391403198242, "global_step": 447792, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.171109676361084, "global_step": 447793, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0208683013916016, "global_step": 447794, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1319808959960938, "global_step": 447795, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.072784423828125, "global_step": 447796, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.050722360610962, "global_step": 447797, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1505446434020996, "global_step": 447798, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0454938411712646, "global_step": 447799, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9852354526519775, "global_step": 447800, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.088718891143799, "global_step": 447801, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1259071826934814, "global_step": 447802, "epoch": 811, "lr": 5e-05}
{"train_loss": 1.9767485857009888, "global_step": 447803, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0617384910583496, "global_step": 447804, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0565874576568604, "global_step": 447805, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.1263043880462646, "global_step": 447806, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0599212646484375, "global_step": 447807, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.007098913192749, "global_step": 447808, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0842130184173584, "global_step": 447809, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.074129104614258, "global_step": 447810, "epoch": 811, "lr": 5e-05}
{"train_loss": 2.0320589542388916, "global_step": 447811, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.062760829925537, "global_step": 447812, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.05733323097229, "global_step": 447813, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0515153408050537, "global_step": 447814, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.96828293800354, "global_step": 447815, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.107524871826172, "global_step": 447816, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1133229732513428, "global_step": 447817, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0755233764648438, "global_step": 447818, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.035024881362915, "global_step": 447819, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0785562992095947, "global_step": 447820, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0560357570648193, "global_step": 447821, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.065199375152588, "global_step": 447822, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.108529567718506, "global_step": 447823, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9877195358276367, "global_step": 447824, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1094706058502197, "global_step": 447825, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.010862350463867, "global_step": 447826, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0874929428100586, "global_step": 447827, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0698156356811523, "global_step": 447828, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0961062908172607, "global_step": 447829, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0382955074310303, "global_step": 447830, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.091529369354248, "global_step": 447831, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.060147285461426, "global_step": 447832, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1127912998199463, "global_step": 447833, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.143545150756836, "global_step": 447834, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0580153465270996, "global_step": 447835, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.141876459121704, "global_step": 447836, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1167569160461426, "global_step": 447837, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9785798788070679, "global_step": 447838, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.10425066947937, "global_step": 447839, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.001873254776001, "global_step": 447840, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0820460319519043, "global_step": 447841, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.078903913497925, "global_step": 447842, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1419076919555664, "global_step": 447843, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0671708583831787, "global_step": 447844, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.060694456100464, "global_step": 447845, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1129226684570312, "global_step": 447846, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.076101303100586, "global_step": 447847, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0756142139434814, "global_step": 447848, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.068495750427246, "global_step": 447849, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.069697856903076, "global_step": 447850, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1154446601867676, "global_step": 447851, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0777411460876465, "global_step": 447852, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0759634971618652, "global_step": 447853, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1017494201660156, "global_step": 447854, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0241575241088867, "global_step": 447855, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1400890350341797, "global_step": 447856, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0871050357818604, "global_step": 447857, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.119874954223633, "global_step": 447858, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0440421104431152, "global_step": 447859, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1213724613189697, "global_step": 447860, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.154114246368408, "global_step": 447861, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.039543628692627, "global_step": 447862, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.11873459815979, "global_step": 447863, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.070387125015259, "global_step": 447864, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1094894409179688, "global_step": 447865, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0925419330596924, "global_step": 447866, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1243999004364014, "global_step": 447867, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0389139652252197, "global_step": 447868, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.158970832824707, "global_step": 447869, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.021169900894165, "global_step": 447870, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0702097415924072, "global_step": 447871, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0490105152130127, "global_step": 447872, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.116682291030884, "global_step": 447873, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.103281021118164, "global_step": 447874, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.117293119430542, "global_step": 447875, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.073356866836548, "global_step": 447876, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0188381671905518, "global_step": 447877, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1330065727233887, "global_step": 447878, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0996406078338623, "global_step": 447879, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0821800231933594, "global_step": 447880, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.007025957107544, "global_step": 447881, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0575973987579346, "global_step": 447882, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0392160415649414, "global_step": 447883, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.027522325515747, "global_step": 447884, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1343495845794678, "global_step": 447885, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1469674110412598, "global_step": 447886, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.049295425415039, "global_step": 447887, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.014798402786255, "global_step": 447888, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0862205028533936, "global_step": 447889, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.087618827819824, "global_step": 447890, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.091921091079712, "global_step": 447891, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0610969066619873, "global_step": 447892, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.023124933242798, "global_step": 447893, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.161196231842041, "global_step": 447894, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0817813873291016, "global_step": 447895, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0737409591674805, "global_step": 447896, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.041149377822876, "global_step": 447897, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0962769985198975, "global_step": 447898, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.082242488861084, "global_step": 447899, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1410136222839355, "global_step": 447900, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.097987651824951, "global_step": 447901, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0329434871673584, "global_step": 447902, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0720324516296387, "global_step": 447903, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0533299446105957, "global_step": 447904, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0601935386657715, "global_step": 447905, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.080582618713379, "global_step": 447906, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.071333408355713, "global_step": 447907, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.088758707046509, "global_step": 447908, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0385684967041016, "global_step": 447909, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1443302631378174, "global_step": 447910, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0505247116088867, "global_step": 447911, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0294833183288574, "global_step": 447912, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0674235820770264, "global_step": 447913, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1192703247070312, "global_step": 447914, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.074800968170166, "global_step": 447915, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0084450244903564, "global_step": 447916, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1099066734313965, "global_step": 447917, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0446910858154297, "global_step": 447918, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0917723178863525, "global_step": 447919, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.2136483192443848, "global_step": 447920, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.079991102218628, "global_step": 447921, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0237319469451904, "global_step": 447922, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.046168327331543, "global_step": 447923, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.042146921157837, "global_step": 447924, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0967416763305664, "global_step": 447925, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.085050106048584, "global_step": 447926, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.119589328765869, "global_step": 447927, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0881683826446533, "global_step": 447928, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.07185435295105, "global_step": 447929, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.048922538757324, "global_step": 447930, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.141953229904175, "global_step": 447931, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1306207180023193, "global_step": 447932, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1624462604522705, "global_step": 447933, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1222522258758545, "global_step": 447934, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.076094150543213, "global_step": 447935, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9980400800704956, "global_step": 447936, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.997549057006836, "global_step": 447937, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.142930746078491, "global_step": 447938, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0870840549468994, "global_step": 447939, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0845754146575928, "global_step": 447940, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0823049545288086, "global_step": 447941, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9999362230300903, "global_step": 447942, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0802652835845947, "global_step": 447943, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.018519878387451, "global_step": 447944, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0221424102783203, "global_step": 447945, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0234618186950684, "global_step": 447946, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.109158754348755, "global_step": 447947, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.129021644592285, "global_step": 447948, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.048736572265625, "global_step": 447949, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0810322761535645, "global_step": 447950, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0415279865264893, "global_step": 447951, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.080594062805176, "global_step": 447952, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.027186870574951, "global_step": 447953, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0419199466705322, "global_step": 447954, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0734777450561523, "global_step": 447955, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.004176139831543, "global_step": 447956, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0925097465515137, "global_step": 447957, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.053952932357788, "global_step": 447958, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0678815841674805, "global_step": 447959, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.146959066390991, "global_step": 447960, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0978798866271973, "global_step": 447961, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.199880599975586, "global_step": 447962, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.111419916152954, "global_step": 447963, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.091554641723633, "global_step": 447964, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1036593914031982, "global_step": 447965, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9839563369750977, "global_step": 447966, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1572041511535645, "global_step": 447967, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.068527936935425, "global_step": 447968, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1058478355407715, "global_step": 447969, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0864357948303223, "global_step": 447970, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1025943756103516, "global_step": 447971, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.088329792022705, "global_step": 447972, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0981228351593018, "global_step": 447973, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.074265956878662, "global_step": 447974, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0195131301879883, "global_step": 447975, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.11156964302063, "global_step": 447976, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1005475521087646, "global_step": 447977, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0381479263305664, "global_step": 447978, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.041935443878174, "global_step": 447979, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9819908142089844, "global_step": 447980, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.085209846496582, "global_step": 447981, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0764353275299072, "global_step": 447982, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.086568832397461, "global_step": 447983, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.097647190093994, "global_step": 447984, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0371925830841064, "global_step": 447985, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0901010036468506, "global_step": 447986, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.141183614730835, "global_step": 447987, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.016803503036499, "global_step": 447988, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.063807487487793, "global_step": 447989, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.03469181060791, "global_step": 447990, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.045736074447632, "global_step": 447991, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0854105949401855, "global_step": 447992, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0796117782592773, "global_step": 447993, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0648906230926514, "global_step": 447994, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0816521644592285, "global_step": 447995, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1013894081115723, "global_step": 447996, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9794148206710815, "global_step": 447997, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0896968841552734, "global_step": 447998, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1274149417877197, "global_step": 447999, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1042232513427734, "global_step": 448000, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0414047241210938, "global_step": 448001, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.087616443634033, "global_step": 448002, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.124206304550171, "global_step": 448003, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0457417964935303, "global_step": 448004, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.074284315109253, "global_step": 448005, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.142709970474243, "global_step": 448006, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.10752534866333, "global_step": 448007, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.022505521774292, "global_step": 448008, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.142336368560791, "global_step": 448009, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.070164918899536, "global_step": 448010, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1122913360595703, "global_step": 448011, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9988367557525635, "global_step": 448012, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9490681886672974, "global_step": 448013, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0624547004699707, "global_step": 448014, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0892350673675537, "global_step": 448015, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1493422985076904, "global_step": 448016, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.015568256378174, "global_step": 448017, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.08960223197937, "global_step": 448018, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0159783363342285, "global_step": 448019, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.020326614379883, "global_step": 448020, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.080282688140869, "global_step": 448021, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9791754484176636, "global_step": 448022, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0220866203308105, "global_step": 448023, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.007521152496338, "global_step": 448024, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.082087993621826, "global_step": 448025, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.077881097793579, "global_step": 448026, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0327723026275635, "global_step": 448027, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1148667335510254, "global_step": 448028, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.103876829147339, "global_step": 448029, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.098068952560425, "global_step": 448030, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0322494506835938, "global_step": 448031, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0579752922058105, "global_step": 448032, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.121274709701538, "global_step": 448033, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9641834497451782, "global_step": 448034, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0089499950408936, "global_step": 448035, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.105489492416382, "global_step": 448036, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0084261894226074, "global_step": 448037, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.164329767227173, "global_step": 448038, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0825862884521484, "global_step": 448039, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0431861877441406, "global_step": 448040, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0746676921844482, "global_step": 448041, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.15842604637146, "global_step": 448042, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.053694248199463, "global_step": 448043, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1120502948760986, "global_step": 448044, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0629467964172363, "global_step": 448045, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1494078636169434, "global_step": 448046, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0133702754974365, "global_step": 448047, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.10831618309021, "global_step": 448048, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.095484972000122, "global_step": 448049, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0639567375183105, "global_step": 448050, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.02496600151062, "global_step": 448051, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.053560972213745, "global_step": 448052, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1239373683929443, "global_step": 448053, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0533552169799805, "global_step": 448054, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1084084510803223, "global_step": 448055, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.031954050064087, "global_step": 448056, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.12565016746521, "global_step": 448057, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9826745986938477, "global_step": 448058, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0236527919769287, "global_step": 448059, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0235116481781006, "global_step": 448060, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1281368732452393, "global_step": 448061, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.105196237564087, "global_step": 448062, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0535056591033936, "global_step": 448063, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.106680154800415, "global_step": 448064, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0021538734436035, "global_step": 448065, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1162588596343994, "global_step": 448066, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1023387908935547, "global_step": 448067, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.002809762954712, "global_step": 448068, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.056171178817749, "global_step": 448069, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.077275037765503, "global_step": 448070, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.10128116607666, "global_step": 448071, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.052459955215454, "global_step": 448072, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.146143913269043, "global_step": 448073, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.019096612930298, "global_step": 448074, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1421029567718506, "global_step": 448075, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0575573444366455, "global_step": 448076, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1234378814697266, "global_step": 448077, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0510244369506836, "global_step": 448078, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.065645694732666, "global_step": 448079, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0994839668273926, "global_step": 448080, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0351572036743164, "global_step": 448081, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0803980827331543, "global_step": 448082, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.012493371963501, "global_step": 448083, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.065995931625366, "global_step": 448084, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0726606845855713, "global_step": 448085, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.028111457824707, "global_step": 448086, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0292248725891113, "global_step": 448087, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.080705404281616, "global_step": 448088, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9392750263214111, "global_step": 448089, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.045499801635742, "global_step": 448090, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.124939203262329, "global_step": 448091, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0805845260620117, "global_step": 448092, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1420300006866455, "global_step": 448093, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0481882095336914, "global_step": 448094, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0440642833709717, "global_step": 448095, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0981967449188232, "global_step": 448096, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0722174644470215, "global_step": 448097, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0707008838653564, "global_step": 448098, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1699841022491455, "global_step": 448099, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1428346633911133, "global_step": 448100, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0449697971343994, "global_step": 448101, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0084617137908936, "global_step": 448102, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0258519649505615, "global_step": 448103, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.032238483428955, "global_step": 448104, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.02286958694458, "global_step": 448105, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.009855031967163, "global_step": 448106, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.09723162651062, "global_step": 448107, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.035629987716675, "global_step": 448108, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0489563941955566, "global_step": 448109, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1048834323883057, "global_step": 448110, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.064220905303955, "global_step": 448111, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.102527618408203, "global_step": 448112, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1019771099090576, "global_step": 448113, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1269736289978027, "global_step": 448114, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0831077098846436, "global_step": 448115, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.188382148742676, "global_step": 448116, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.178284168243408, "global_step": 448117, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0181543827056885, "global_step": 448118, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0877654552459717, "global_step": 448119, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1160950660705566, "global_step": 448120, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.991647481918335, "global_step": 448121, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.094430446624756, "global_step": 448122, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.046543836593628, "global_step": 448123, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1404271125793457, "global_step": 448124, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1148571968078613, "global_step": 448125, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1416356563568115, "global_step": 448126, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1290862560272217, "global_step": 448127, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.106863260269165, "global_step": 448128, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1046206951141357, "global_step": 448129, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.157318592071533, "global_step": 448130, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.149054527282715, "global_step": 448131, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.083115577697754, "global_step": 448132, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0918421745300293, "global_step": 448133, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.114006996154785, "global_step": 448134, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0566208362579346, "global_step": 448135, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.099604606628418, "global_step": 448136, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0336625576019287, "global_step": 448137, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.116229295730591, "global_step": 448138, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.062034845352173, "global_step": 448139, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.051743984222412, "global_step": 448140, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0270938873291016, "global_step": 448141, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.118967294692993, "global_step": 448142, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.023859739303589, "global_step": 448143, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9686920642852783, "global_step": 448144, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.100375175476074, "global_step": 448145, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1012630462646484, "global_step": 448146, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.068103313446045, "global_step": 448147, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.092731475830078, "global_step": 448148, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.076533794403076, "global_step": 448149, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0480663776397705, "global_step": 448150, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9965379238128662, "global_step": 448151, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0432276725769043, "global_step": 448152, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0877504348754883, "global_step": 448153, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.008401870727539, "global_step": 448154, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1184608936309814, "global_step": 448155, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0125274658203125, "global_step": 448156, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0486466884613037, "global_step": 448157, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.12257981300354, "global_step": 448158, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.120861530303955, "global_step": 448159, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0424320697784424, "global_step": 448160, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1574106216430664, "global_step": 448161, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.048743724822998, "global_step": 448162, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.090043067932129, "global_step": 448163, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0085439682006836, "global_step": 448164, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.078841209411621, "global_step": 448165, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0948338508605957, "global_step": 448166, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1684694290161133, "global_step": 448167, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.111680507659912, "global_step": 448168, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.080374240875244, "global_step": 448169, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0044729709625244, "global_step": 448170, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.161738395690918, "global_step": 448171, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0425209999084473, "global_step": 448172, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1533162593841553, "global_step": 448173, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.039717674255371, "global_step": 448174, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0943853855133057, "global_step": 448175, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.078831195831299, "global_step": 448176, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0684032440185547, "global_step": 448177, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0857627391815186, "global_step": 448178, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.121194362640381, "global_step": 448179, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.071345806121826, "global_step": 448180, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1147541999816895, "global_step": 448181, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0736191272735596, "global_step": 448182, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1643102169036865, "global_step": 448183, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1446428298950195, "global_step": 448184, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1434731483459473, "global_step": 448185, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0992586612701416, "global_step": 448186, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.024880886077881, "global_step": 448187, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9564249515533447, "global_step": 448188, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.062282085418701, "global_step": 448189, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0857105255126953, "global_step": 448190, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0486273765563965, "global_step": 448191, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.075387477874756, "global_step": 448192, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1344053745269775, "global_step": 448193, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0015320777893066, "global_step": 448194, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0912113189697266, "global_step": 448195, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0543339252471924, "global_step": 448196, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.099562406539917, "global_step": 448197, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0861568450927734, "global_step": 448198, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.071768283843994, "global_step": 448199, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1179592609405518, "global_step": 448200, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1014726161956787, "global_step": 448201, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.055968761444092, "global_step": 448202, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0860202312469482, "global_step": 448203, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0002102851867676, "global_step": 448204, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0664472579956055, "global_step": 448205, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9861626625061035, "global_step": 448206, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.096240758895874, "global_step": 448207, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0723743438720703, "global_step": 448208, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.126755952835083, "global_step": 448209, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0946176052093506, "global_step": 448210, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1485369205474854, "global_step": 448211, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.148169755935669, "global_step": 448212, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0949671268463135, "global_step": 448213, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.133269786834717, "global_step": 448214, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.087308645248413, "global_step": 448215, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0902860164642334, "global_step": 448216, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.121643543243408, "global_step": 448217, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1479082107543945, "global_step": 448218, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0534567832946777, "global_step": 448219, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.09385085105896, "global_step": 448220, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0649051666259766, "global_step": 448221, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.093242883682251, "global_step": 448222, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0624654293060303, "global_step": 448223, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.187180757522583, "global_step": 448224, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.025334358215332, "global_step": 448225, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0782358646392822, "global_step": 448226, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0806798934936523, "global_step": 448227, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0782551765441895, "global_step": 448228, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0749785900115967, "global_step": 448229, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0259642601013184, "global_step": 448230, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1221187114715576, "global_step": 448231, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1223409175872803, "global_step": 448232, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.095065116882324, "global_step": 448233, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.083343982696533, "global_step": 448234, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1347951889038086, "global_step": 448235, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0700457096099854, "global_step": 448236, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9874019622802734, "global_step": 448237, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.049225091934204, "global_step": 448238, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.113624334335327, "global_step": 448239, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0712807178497314, "global_step": 448240, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0245370864868164, "global_step": 448241, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1761369705200195, "global_step": 448242, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0144150257110596, "global_step": 448243, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0197463035583496, "global_step": 448244, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0306200981140137, "global_step": 448245, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0358545780181885, "global_step": 448246, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0353050231933594, "global_step": 448247, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0863380432128906, "global_step": 448248, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0329391956329346, "global_step": 448249, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0683069229125977, "global_step": 448250, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9745408296585083, "global_step": 448251, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1264593601226807, "global_step": 448252, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.132026433944702, "global_step": 448253, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1479697227478027, "global_step": 448254, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0456488132476807, "global_step": 448255, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1539905071258545, "global_step": 448256, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.128754138946533, "global_step": 448257, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0769288539886475, "global_step": 448258, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1605687141418457, "global_step": 448259, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.100917100906372, "global_step": 448260, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9840189218521118, "global_step": 448261, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0742952823638916, "global_step": 448262, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0810441970825195, "global_step": 448263, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1516685485839844, "global_step": 448264, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0509438514709473, "global_step": 448265, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0308566093444824, "global_step": 448266, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.145618438720703, "global_step": 448267, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.063159465789795, "global_step": 448268, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0575969219207764, "global_step": 448269, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1227118968963623, "global_step": 448270, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0248262882232666, "global_step": 448271, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.10018253326416, "global_step": 448272, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0714328289031982, "global_step": 448273, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.018705368041992, "global_step": 448274, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.020939826965332, "global_step": 448275, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.139897584915161, "global_step": 448276, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0839719772338867, "global_step": 448277, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.025054454803467, "global_step": 448278, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.161017894744873, "global_step": 448279, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.021986484527588, "global_step": 448280, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0558431148529053, "global_step": 448281, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.086203098297119, "global_step": 448282, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.101665735244751, "global_step": 448283, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1020853519439697, "global_step": 448284, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.026448965072632, "global_step": 448285, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.035802125930786, "global_step": 448286, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.081542730331421, "global_step": 448287, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0747735500335693, "global_step": 448288, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0819523334503174, "global_step": 448289, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9311755895614624, "global_step": 448290, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9871443510055542, "global_step": 448291, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9715157747268677, "global_step": 448292, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0589184761047363, "global_step": 448293, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0507569313049316, "global_step": 448294, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0489561557769775, "global_step": 448295, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.021562099456787, "global_step": 448296, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1250243186950684, "global_step": 448297, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9740607738494873, "global_step": 448298, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.007136106491089, "global_step": 448299, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1174373626708984, "global_step": 448300, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0277962684631348, "global_step": 448301, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.050945520401001, "global_step": 448302, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0699071884155273, "global_step": 448303, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0613889694213867, "global_step": 448304, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1087942123413086, "global_step": 448305, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.01650071144104, "global_step": 448306, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.063835859298706, "global_step": 448307, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.05277156829834, "global_step": 448308, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.112516403198242, "global_step": 448309, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0592329502105713, "global_step": 448310, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.056835412979126, "global_step": 448311, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0947682857513428, "global_step": 448312, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.080617666244507, "global_step": 448313, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0244076251983643, "global_step": 448314, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.027737855911255, "global_step": 448315, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.198643445968628, "global_step": 448316, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.107771396636963, "global_step": 448317, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.100146770477295, "global_step": 448318, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0537381172180176, "global_step": 448319, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.156967878341675, "global_step": 448320, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.120832681655884, "global_step": 448321, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.099604368209839, "global_step": 448322, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.032711982727051, "global_step": 448323, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0897176265716553, "global_step": 448324, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.069700241088867, "global_step": 448325, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0717759132385254, "global_step": 448326, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.117593765258789, "global_step": 448327, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.130117177963257, "global_step": 448328, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1380832195281982, "global_step": 448329, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.064160108566284, "global_step": 448330, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.05004620552063, "global_step": 448331, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0782511234283447, "global_step": 448332, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1117968559265137, "global_step": 448333, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.069674015045166, "global_step": 448334, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.036740303039551, "global_step": 448335, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0520670413970947, "global_step": 448336, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1082756519317627, "global_step": 448337, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1511740684509277, "global_step": 448338, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.096198081970215, "global_step": 448339, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.075324773788452, "global_step": 448340, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0941009521484375, "global_step": 448341, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.151397705078125, "global_step": 448342, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.052211046218872, "global_step": 448343, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0513386726379395, "global_step": 448344, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0817644596099854, "global_step": 448345, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1182830333709717, "global_step": 448346, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.024406909942627, "global_step": 448347, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1179165840148926, "global_step": 448348, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0763158798217773, "global_step": 448349, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.099647045135498, "global_step": 448350, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0266003608703613, "global_step": 448351, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.039276599884033, "global_step": 448352, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1168389320373535, "global_step": 448353, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.112792730331421, "global_step": 448354, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0483081340789795, "global_step": 448355, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0414822101593018, "global_step": 448356, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.063742160797119, "global_step": 448357, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0735487937927246, "global_step": 448358, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.036508560180664, "global_step": 448359, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.086669921875, "global_step": 448360, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1223526000976562, "global_step": 448361, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.047513484954834, "global_step": 448362, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.018807888031006, "global_step": 448363, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1296842098236084, "global_step": 448364, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1042275428771973, "global_step": 448365, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.064397096633911, "global_step": 448366, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0816612243652344, "global_step": 448367, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0750606060028076, "global_step": 448368, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.050462245941162, "global_step": 448369, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.01733136177063, "global_step": 448370, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0766820907592773, "global_step": 448371, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0225956439971924, "global_step": 448372, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.153085947036743, "global_step": 448373, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.050173282623291, "global_step": 448374, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1359410285949707, "global_step": 448375, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.082942247390747, "global_step": 448376, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.039940118789673, "global_step": 448377, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.989697813987732, "global_step": 448378, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.116506576538086, "global_step": 448379, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1100986003875732, "global_step": 448380, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.151963472366333, "global_step": 448381, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.106102228164673, "global_step": 448382, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.001110553741455, "global_step": 448383, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0700173377990723, "global_step": 448384, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0169975757598877, "global_step": 448385, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.088904857635498, "global_step": 448386, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0165324211120605, "global_step": 448387, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0816256999969482, "global_step": 448388, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.091777801513672, "global_step": 448389, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9686349630355835, "global_step": 448390, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0358872413635254, "global_step": 448391, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.056846857070923, "global_step": 448392, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1308233737945557, "global_step": 448393, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.052781581878662, "global_step": 448394, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.112626791000366, "global_step": 448395, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0939488410949707, "global_step": 448396, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1298012733459473, "global_step": 448397, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0593338012695312, "global_step": 448398, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.065680980682373, "global_step": 448399, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0259313583374023, "global_step": 448400, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0852620601654053, "global_step": 448401, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9782408475875854, "global_step": 448402, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.093660354614258, "global_step": 448403, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.120088577270508, "global_step": 448404, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.076697587966919, "global_step": 448405, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0330166816711426, "global_step": 448406, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0391643047332764, "global_step": 448407, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.055074453353882, "global_step": 448408, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1098928451538086, "global_step": 448409, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0993165969848633, "global_step": 448410, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0832571983337402, "global_step": 448411, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0517497062683105, "global_step": 448412, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1258723735809326, "global_step": 448413, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.038041591644287, "global_step": 448414, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1065170764923096, "global_step": 448415, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.122087001800537, "global_step": 448416, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1449363231658936, "global_step": 448417, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0573174953460693, "global_step": 448418, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0512969493865967, "global_step": 448419, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1052865982055664, "global_step": 448420, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0477259159088135, "global_step": 448421, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0809690952301025, "global_step": 448422, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0861196517944336, "global_step": 448423, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0900838375091553, "global_step": 448424, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0827279090881348, "global_step": 448425, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0012991428375244, "global_step": 448426, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.074954032897949, "global_step": 448427, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1189446449279785, "global_step": 448428, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.166018486022949, "global_step": 448429, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1511011123657227, "global_step": 448430, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1585006713867188, "global_step": 448431, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.037301778793335, "global_step": 448432, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1448814868927, "global_step": 448433, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1112661361694336, "global_step": 448434, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.054935932159424, "global_step": 448435, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.069697856903076, "global_step": 448436, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.076043128967285, "global_step": 448437, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0432815551757812, "global_step": 448438, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9851770401000977, "global_step": 448439, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.116243362426758, "global_step": 448440, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1249592304229736, "global_step": 448441, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1189687252044678, "global_step": 448442, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1481354236602783, "global_step": 448443, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0221199989318848, "global_step": 448444, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.987619161605835, "global_step": 448445, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.099982976913452, "global_step": 448446, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.057326078414917, "global_step": 448447, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0152587890625, "global_step": 448448, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1204471588134766, "global_step": 448449, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0133373737335205, "global_step": 448450, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0555038452148438, "global_step": 448451, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.088994264602661, "global_step": 448452, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0993452072143555, "global_step": 448453, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.03170108795166, "global_step": 448454, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.041433572769165, "global_step": 448455, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1390583515167236, "global_step": 448456, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0855021476745605, "global_step": 448457, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.113292694091797, "global_step": 448458, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.030080556869507, "global_step": 448459, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0726277828216553, "global_step": 448460, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1597518920898438, "global_step": 448461, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.060476303100586, "global_step": 448462, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1072452068328857, "global_step": 448463, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0663833618164062, "global_step": 448464, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.04085636138916, "global_step": 448465, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.061086654663086, "global_step": 448466, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0163097381591797, "global_step": 448467, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1602325439453125, "global_step": 448468, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1350061893463135, "global_step": 448469, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0742645263671875, "global_step": 448470, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0156543254852295, "global_step": 448471, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1609153747558594, "global_step": 448472, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.05842661857605, "global_step": 448473, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9670506715774536, "global_step": 448474, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.066394090652466, "global_step": 448475, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0161826610565186, "global_step": 448476, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.011432647705078, "global_step": 448477, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.069021224975586, "global_step": 448478, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.118074417114258, "global_step": 448479, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0389838218688965, "global_step": 448480, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.031031370162964, "global_step": 448481, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0044193267822266, "global_step": 448482, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.002542734146118, "global_step": 448483, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0964555740356445, "global_step": 448484, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.101412534713745, "global_step": 448485, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.096369504928589, "global_step": 448486, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0693328380584717, "global_step": 448487, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.053734064102173, "global_step": 448488, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.111203193664551, "global_step": 448489, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0692970752716064, "global_step": 448490, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0416557788848877, "global_step": 448491, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0683093070983887, "global_step": 448492, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.039464235305786, "global_step": 448493, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0817012786865234, "global_step": 448494, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0317039489746094, "global_step": 448495, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.086545467376709, "global_step": 448496, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0601089000701904, "global_step": 448497, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.179447889328003, "global_step": 448498, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.20867657661438, "global_step": 448499, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.068730592727661, "global_step": 448500, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.080374240875244, "global_step": 448501, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0258591175079346, "global_step": 448502, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0771803855895996, "global_step": 448503, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.07393479347229, "global_step": 448504, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1215250492095947, "global_step": 448505, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1396725177764893, "global_step": 448506, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1344690322875977, "global_step": 448507, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1888484954833984, "global_step": 448508, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.109731674194336, "global_step": 448509, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.07834792137146, "global_step": 448510, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0190672874450684, "global_step": 448511, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1158547401428223, "global_step": 448512, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1005444526672363, "global_step": 448513, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1091768741607666, "global_step": 448514, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0294978618621826, "global_step": 448515, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1020431518554688, "global_step": 448516, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.09355092048645, "global_step": 448517, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1930203437805176, "global_step": 448518, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0886266231536865, "global_step": 448519, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.195841073989868, "global_step": 448520, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.018821954727173, "global_step": 448521, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.128079414367676, "global_step": 448522, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1576993465423584, "global_step": 448523, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0384275913238525, "global_step": 448524, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0507583618164062, "global_step": 448525, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.07472825050354, "global_step": 448526, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.162238836288452, "global_step": 448527, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1038949489593506, "global_step": 448528, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.081096887588501, "global_step": 448529, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.171842575073242, "global_step": 448530, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0388762950897217, "global_step": 448531, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0710318088531494, "global_step": 448532, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.109365224838257, "global_step": 448533, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.091294288635254, "global_step": 448534, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.072814702987671, "global_step": 448535, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.049527883529663, "global_step": 448536, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.130692958831787, "global_step": 448537, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0049965381622314, "global_step": 448538, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.032459259033203, "global_step": 448539, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1292788982391357, "global_step": 448540, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.152968168258667, "global_step": 448541, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1153106689453125, "global_step": 448542, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0881998538970947, "global_step": 448543, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1162784099578857, "global_step": 448544, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0146193504333496, "global_step": 448545, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.115316152572632, "global_step": 448546, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0986168384552, "global_step": 448547, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0545125007629395, "global_step": 448548, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.018284559249878, "global_step": 448549, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.08327317237854, "global_step": 448550, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.080061674118042, "global_step": 448551, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.017850399017334, "global_step": 448552, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0459017753601074, "global_step": 448553, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.035142421722412, "global_step": 448554, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1130425930023193, "global_step": 448555, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9921625852584839, "global_step": 448556, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0930914878845215, "global_step": 448557, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.059807300567627, "global_step": 448558, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0288968086242676, "global_step": 448559, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.137770652770996, "global_step": 448560, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0778775215148926, "global_step": 448561, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.203911781311035, "global_step": 448562, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0038187503814697, "global_step": 448563, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0262391567230225, "global_step": 448564, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.033445358276367, "global_step": 448565, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.096444606781006, "global_step": 448566, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1095941066741943, "global_step": 448567, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1274449825286865, "global_step": 448568, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0141961574554443, "global_step": 448569, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.126685619354248, "global_step": 448570, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.12612247467041, "global_step": 448571, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.092820405960083, "global_step": 448572, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.016885280609131, "global_step": 448573, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1190335750579834, "global_step": 448574, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0715115070343018, "global_step": 448575, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9946551322937012, "global_step": 448576, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1604208946228027, "global_step": 448577, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1266074180603027, "global_step": 448578, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.064133644104004, "global_step": 448579, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.049830198287964, "global_step": 448580, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.071946382522583, "global_step": 448581, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9874924421310425, "global_step": 448582, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1133618354797363, "global_step": 448583, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1434574127197266, "global_step": 448584, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.074924945831299, "global_step": 448585, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.079202890396118, "global_step": 448586, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0796568393707275, "global_step": 448587, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1010923385620117, "global_step": 448588, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1747989654541016, "global_step": 448589, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.091968297958374, "global_step": 448590, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.089021682739258, "global_step": 448591, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.17093825340271, "global_step": 448592, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.161754608154297, "global_step": 448593, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.069688081741333, "global_step": 448594, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.057124137878418, "global_step": 448595, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0365285873413086, "global_step": 448596, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.030479669570923, "global_step": 448597, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0922000408172607, "global_step": 448598, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1166975498199463, "global_step": 448599, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1064651012420654, "global_step": 448600, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.099435567855835, "global_step": 448601, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1245975494384766, "global_step": 448602, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.10427188873291, "global_step": 448603, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1296095848083496, "global_step": 448604, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.051109790802002, "global_step": 448605, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1142120361328125, "global_step": 448606, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.110156774520874, "global_step": 448607, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1045303344726562, "global_step": 448608, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.048165798187256, "global_step": 448609, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.042754888534546, "global_step": 448610, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.034984827041626, "global_step": 448611, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.06642484664917, "global_step": 448612, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0331454277038574, "global_step": 448613, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9628403186798096, "global_step": 448614, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.015977382659912, "global_step": 448615, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.040656089782715, "global_step": 448616, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0338783264160156, "global_step": 448617, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.02158784866333, "global_step": 448618, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1074187755584717, "global_step": 448619, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1240458488464355, "global_step": 448620, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0321168899536133, "global_step": 448621, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.034661293029785, "global_step": 448622, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1578216552734375, "global_step": 448623, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0529518127441406, "global_step": 448624, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.119694709777832, "global_step": 448625, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1051950454711914, "global_step": 448626, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0998659133911133, "global_step": 448627, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1640801429748535, "global_step": 448628, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.014159917831421, "global_step": 448629, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1078121662139893, "global_step": 448630, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9994336366653442, "global_step": 448631, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.09938907623291, "global_step": 448632, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0337626934051514, "global_step": 448633, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1208243370056152, "global_step": 448634, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.144474506378174, "global_step": 448635, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.068918228149414, "global_step": 448636, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1132946014404297, "global_step": 448637, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0913379192352295, "global_step": 448638, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0810606479644775, "global_step": 448639, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.056973457336426, "global_step": 448640, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0503242015838623, "global_step": 448641, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.016507148742676, "global_step": 448642, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.046457052230835, "global_step": 448643, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0475690364837646, "global_step": 448644, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.056986093521118, "global_step": 448645, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.067098379135132, "global_step": 448646, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.132870674133301, "global_step": 448647, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1326029300689697, "global_step": 448648, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9819648265838623, "global_step": 448649, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9856247901916504, "global_step": 448650, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0416431427001953, "global_step": 448651, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0547902584075928, "global_step": 448652, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0718793869018555, "global_step": 448653, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0869321823120117, "global_step": 448654, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.187072277069092, "global_step": 448655, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.07308030128479, "global_step": 448656, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0158517360687256, "global_step": 448657, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0466067790985107, "global_step": 448658, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0819084644317627, "global_step": 448659, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.03425931930542, "global_step": 448660, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.049165725708008, "global_step": 448661, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0552732944488525, "global_step": 448662, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0803215503692627, "global_step": 448663, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0449094772338867, "global_step": 448664, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0529685020446777, "global_step": 448665, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9471796751022339, "global_step": 448666, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1509039402008057, "global_step": 448667, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.2021665573120117, "global_step": 448668, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.065131425857544, "global_step": 448669, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0704853534698486, "global_step": 448670, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0880720615386963, "global_step": 448671, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1476242542266846, "global_step": 448672, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0754363536834717, "global_step": 448673, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0075573921203613, "global_step": 448674, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0650079250335693, "global_step": 448675, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.074263572692871, "global_step": 448676, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0852458477020264, "global_step": 448677, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.028826951980591, "global_step": 448678, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.063591957092285, "global_step": 448679, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.180116891860962, "global_step": 448680, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0910804271698, "global_step": 448681, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.162205934524536, "global_step": 448682, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.023171901702881, "global_step": 448683, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1059937477111816, "global_step": 448684, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0478343963623047, "global_step": 448685, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.052438259124756, "global_step": 448686, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.081615924835205, "global_step": 448687, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.06966495513916, "global_step": 448688, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0928232669830322, "global_step": 448689, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.110346555709839, "global_step": 448690, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.07824444770813, "global_step": 448691, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1589601039886475, "global_step": 448692, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0235397815704346, "global_step": 448693, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.025238037109375, "global_step": 448694, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1128106117248535, "global_step": 448695, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9978523254394531, "global_step": 448696, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0979840755462646, "global_step": 448697, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9991765022277832, "global_step": 448698, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1093263626098633, "global_step": 448699, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.029344320297241, "global_step": 448700, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.147827386856079, "global_step": 448701, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.001227378845215, "global_step": 448702, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.06882381439209, "global_step": 448703, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0932836532592773, "global_step": 448704, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.096198797225952, "global_step": 448705, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.091689109802246, "global_step": 448706, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.075718879699707, "global_step": 448707, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.071836233139038, "global_step": 448708, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.096226453781128, "global_step": 448709, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0759356021881104, "global_step": 448710, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.104944944381714, "global_step": 448711, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0487661361694336, "global_step": 448712, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0854504108428955, "global_step": 448713, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.061476469039917, "global_step": 448714, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.006601333618164, "global_step": 448715, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.186375856399536, "global_step": 448716, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0585169792175293, "global_step": 448717, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.05794358253479, "global_step": 448718, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9865608215332031, "global_step": 448719, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0695455074310303, "global_step": 448720, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.076580047607422, "global_step": 448721, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.061861991882324, "global_step": 448722, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.134636163711548, "global_step": 448723, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.107553005218506, "global_step": 448724, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0082058906555176, "global_step": 448725, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0068535804748535, "global_step": 448726, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.073498010635376, "global_step": 448727, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0685195922851562, "global_step": 448728, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0874671936035156, "global_step": 448729, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.109548330307007, "global_step": 448730, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.060520648956299, "global_step": 448731, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.067424774169922, "global_step": 448732, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1094610691070557, "global_step": 448733, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.064013957977295, "global_step": 448734, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.133422374725342, "global_step": 448735, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1776981353759766, "global_step": 448736, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0300488471984863, "global_step": 448737, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0936241149902344, "global_step": 448738, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.171941041946411, "global_step": 448739, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0678582191467285, "global_step": 448740, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.106734037399292, "global_step": 448741, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.041497230529785, "global_step": 448742, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0557069778442383, "global_step": 448743, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.119155168533325, "global_step": 448744, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1675755977630615, "global_step": 448745, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.10847544670105, "global_step": 448746, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1135761737823486, "global_step": 448747, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.173806667327881, "global_step": 448748, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1139142513275146, "global_step": 448749, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0449681282043457, "global_step": 448750, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.115269660949707, "global_step": 448751, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1232869625091553, "global_step": 448752, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.078594923019409, "global_step": 448753, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0175940990448, "global_step": 448754, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.083791494369507, "global_step": 448755, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0685508251190186, "global_step": 448756, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0281684398651123, "global_step": 448757, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0723812580108643, "global_step": 448758, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.109678268432617, "global_step": 448759, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1929965019226074, "global_step": 448760, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.014502763748169, "global_step": 448761, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9910627603530884, "global_step": 448762, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1298351287841797, "global_step": 448763, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0588033199310303, "global_step": 448764, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1467087268829346, "global_step": 448765, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0471222400665283, "global_step": 448766, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1502768993377686, "global_step": 448767, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1397225856781006, "global_step": 448768, "epoch": 812, "lr": 5e-05}
{"train_loss": 1.9814108610153198, "global_step": 448769, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1306755542755127, "global_step": 448770, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0507619380950928, "global_step": 448771, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.086493730545044, "global_step": 448772, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0587451457977295, "global_step": 448773, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0167791843414307, "global_step": 448774, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.150047540664673, "global_step": 448775, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0348260402679443, "global_step": 448776, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1523776054382324, "global_step": 448777, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.117076873779297, "global_step": 448778, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.0774807929992676, "global_step": 448779, "epoch": 812, "lr": 5e-05}
{"train_loss": 2.1430842876434326, "global_step": 448780, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0961966514587402, "global_step": 448781, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.116161346435547, "global_step": 448782, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9927573204040527, "global_step": 448783, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.107651472091675, "global_step": 448784, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0183627605438232, "global_step": 448785, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1057398319244385, "global_step": 448786, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.091024398803711, "global_step": 448787, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.01869535446167, "global_step": 448788, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0591518878936768, "global_step": 448789, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0966174602508545, "global_step": 448790, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.093306303024292, "global_step": 448791, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.125469923019409, "global_step": 448792, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9842662811279297, "global_step": 448793, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0674502849578857, "global_step": 448794, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0804057121276855, "global_step": 448795, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9918766021728516, "global_step": 448796, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0570688247680664, "global_step": 448797, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0192923545837402, "global_step": 448798, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0566227436065674, "global_step": 448799, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.044853448867798, "global_step": 448800, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.028573513031006, "global_step": 448801, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1360960006713867, "global_step": 448802, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0930263996124268, "global_step": 448803, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0484678745269775, "global_step": 448804, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0940003395080566, "global_step": 448805, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1429266929626465, "global_step": 448806, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.075589656829834, "global_step": 448807, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9891347885131836, "global_step": 448808, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1186463832855225, "global_step": 448809, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0992767810821533, "global_step": 448810, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0074329376220703, "global_step": 448811, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.047424554824829, "global_step": 448812, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.083319902420044, "global_step": 448813, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.126168727874756, "global_step": 448814, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9556106328964233, "global_step": 448815, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9498543739318848, "global_step": 448816, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0698139667510986, "global_step": 448817, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0497219562530518, "global_step": 448818, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.056286334991455, "global_step": 448819, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.046733856201172, "global_step": 448820, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0432300567626953, "global_step": 448821, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0839476585388184, "global_step": 448822, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1389434337615967, "global_step": 448823, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.126119375228882, "global_step": 448824, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1147868633270264, "global_step": 448825, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.086845874786377, "global_step": 448826, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0667295455932617, "global_step": 448827, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.106947183609009, "global_step": 448828, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.023972511291504, "global_step": 448829, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1050446033477783, "global_step": 448830, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.06624698638916, "global_step": 448831, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.070329427719116, "global_step": 448832, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0384292602539062, "global_step": 448833, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0026535987854004, "global_step": 448834, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0803494453430176, "global_step": 448835, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.075911045074463, "global_step": 448836, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0106770992279053, "global_step": 448837, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.039682388305664, "global_step": 448838, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0349044799804688, "global_step": 448839, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.067542791366577, "global_step": 448840, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0281248092651367, "global_step": 448841, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9714943170547485, "global_step": 448842, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.116335868835449, "global_step": 448843, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.08886456489563, "global_step": 448844, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1657423973083496, "global_step": 448845, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9921019077301025, "global_step": 448846, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1170074939727783, "global_step": 448847, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1030097007751465, "global_step": 448848, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9363723993301392, "global_step": 448849, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1264567375183105, "global_step": 448850, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0805399417877197, "global_step": 448851, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0689430236816406, "global_step": 448852, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.97276771068573, "global_step": 448853, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0168278217315674, "global_step": 448854, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0196142196655273, "global_step": 448855, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0921099185943604, "global_step": 448856, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.094632387161255, "global_step": 448857, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0473806858062744, "global_step": 448858, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0293099880218506, "global_step": 448859, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.97343909740448, "global_step": 448860, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.119804859161377, "global_step": 448861, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.06899356842041, "global_step": 448862, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0740914344787598, "global_step": 448863, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0724925994873047, "global_step": 448864, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.016942262649536, "global_step": 448865, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0888020992279053, "global_step": 448866, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0145328044891357, "global_step": 448867, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.084127426147461, "global_step": 448868, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.059481382369995, "global_step": 448869, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.089069366455078, "global_step": 448870, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0334184169769287, "global_step": 448871, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.991408109664917, "global_step": 448872, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.086001396179199, "global_step": 448873, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0722532272338867, "global_step": 448874, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0220947265625, "global_step": 448875, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1307742595672607, "global_step": 448876, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0532798767089844, "global_step": 448877, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.163398504257202, "global_step": 448878, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1472086906433105, "global_step": 448879, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.052241563796997, "global_step": 448880, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0854811668395996, "global_step": 448881, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0343873500823975, "global_step": 448882, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0867788791656494, "global_step": 448883, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0964200496673584, "global_step": 448884, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.018845319747925, "global_step": 448885, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.039377450942993, "global_step": 448886, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1261749267578125, "global_step": 448887, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0589609146118164, "global_step": 448888, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0537302494049072, "global_step": 448889, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0921807289123535, "global_step": 448890, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.04646635055542, "global_step": 448891, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.049851894378662, "global_step": 448892, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0917906761169434, "global_step": 448893, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0635950565338135, "global_step": 448894, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9902666807174683, "global_step": 448895, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0453171730041504, "global_step": 448896, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0616536140441895, "global_step": 448897, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0044331550598145, "global_step": 448898, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.147768497467041, "global_step": 448899, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0499393939971924, "global_step": 448900, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.102174997329712, "global_step": 448901, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.000746011734009, "global_step": 448902, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1066391468048096, "global_step": 448903, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.057158946990967, "global_step": 448904, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.120964765548706, "global_step": 448905, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1047205924987793, "global_step": 448906, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0727641582489014, "global_step": 448907, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1292474269866943, "global_step": 448908, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0677173137664795, "global_step": 448909, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.03393292427063, "global_step": 448910, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.053513765335083, "global_step": 448911, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0879645347595215, "global_step": 448912, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9985706806182861, "global_step": 448913, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1466753482818604, "global_step": 448914, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.087507963180542, "global_step": 448915, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.100212335586548, "global_step": 448916, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1274256706237793, "global_step": 448917, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1028926372528076, "global_step": 448918, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.072197914123535, "global_step": 448919, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1254894733428955, "global_step": 448920, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.033020257949829, "global_step": 448921, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.108243942260742, "global_step": 448922, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0260236263275146, "global_step": 448923, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.052561044692993, "global_step": 448924, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0351006984710693, "global_step": 448925, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0721940994262695, "global_step": 448926, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0781619548797607, "global_step": 448927, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0461738109588623, "global_step": 448928, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.058429002761841, "global_step": 448929, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.128767490386963, "global_step": 448930, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.026031494140625, "global_step": 448931, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9951591491699219, "global_step": 448932, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.106205463409424, "global_step": 448933, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0194084644317627, "global_step": 448934, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.169734001159668, "global_step": 448935, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.975123405456543, "global_step": 448936, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0045299530029297, "global_step": 448937, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9585744142532349, "global_step": 448938, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9639524221420288, "global_step": 448939, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.115281105041504, "global_step": 448940, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0577306747436523, "global_step": 448941, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.087952136993408, "global_step": 448942, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.07332444190979, "global_step": 448943, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.995132565498352, "global_step": 448944, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0518698692321777, "global_step": 448945, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.014599561691284, "global_step": 448946, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9951472282409668, "global_step": 448947, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.117248058319092, "global_step": 448948, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.040480136871338, "global_step": 448949, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1298444271087646, "global_step": 448950, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.015305995941162, "global_step": 448951, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.094515323638916, "global_step": 448952, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0228793621063232, "global_step": 448953, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9885847568511963, "global_step": 448954, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0777969360351562, "global_step": 448955, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.111539363861084, "global_step": 448956, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.079836130142212, "global_step": 448957, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0693373680114746, "global_step": 448958, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1109912395477295, "global_step": 448959, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0356156826019287, "global_step": 448960, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.088555097579956, "global_step": 448961, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0655384063720703, "global_step": 448962, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.099592924118042, "global_step": 448963, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0921807289123535, "global_step": 448964, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.161966562271118, "global_step": 448965, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.065509796142578, "global_step": 448966, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0835864543914795, "global_step": 448967, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.042773962020874, "global_step": 448968, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0850768089294434, "global_step": 448969, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.060455083847046, "global_step": 448970, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0493345260620117, "global_step": 448971, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0498695373535156, "global_step": 448972, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.113964319229126, "global_step": 448973, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.162562608718872, "global_step": 448974, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0981032848358154, "global_step": 448975, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0610477924346924, "global_step": 448976, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0747127532958984, "global_step": 448977, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0519967079162598, "global_step": 448978, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0546627044677734, "global_step": 448979, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1110949516296387, "global_step": 448980, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.045016288757324, "global_step": 448981, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.05407452583313, "global_step": 448982, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.051557779312134, "global_step": 448983, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0287654399871826, "global_step": 448984, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0567915439605713, "global_step": 448985, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0440211296081543, "global_step": 448986, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.028719425201416, "global_step": 448987, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.01092267036438, "global_step": 448988, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0764617919921875, "global_step": 448989, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0904157161712646, "global_step": 448990, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9995522499084473, "global_step": 448991, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.016779899597168, "global_step": 448992, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.147249460220337, "global_step": 448993, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0512547492980957, "global_step": 448994, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9888883829116821, "global_step": 448995, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.048501968383789, "global_step": 448996, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.06473445892334, "global_step": 448997, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.129849672317505, "global_step": 448998, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.152052402496338, "global_step": 448999, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.113966703414917, "global_step": 449000, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0776431560516357, "global_step": 449001, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0960299968719482, "global_step": 449002, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1142537593841553, "global_step": 449003, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9863672256469727, "global_step": 449004, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0105392932891846, "global_step": 449005, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.089237928390503, "global_step": 449006, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0050148963928223, "global_step": 449007, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9810938835144043, "global_step": 449008, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.100442886352539, "global_step": 449009, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.112238883972168, "global_step": 449010, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9568485021591187, "global_step": 449011, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.146477699279785, "global_step": 449012, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1536097526550293, "global_step": 449013, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0081586837768555, "global_step": 449014, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.2025704383850098, "global_step": 449015, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1647791862487793, "global_step": 449016, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.043194532394409, "global_step": 449017, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.100421905517578, "global_step": 449018, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.084097146987915, "global_step": 449019, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.143463611602783, "global_step": 449020, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1350226402282715, "global_step": 449021, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1531026363372803, "global_step": 449022, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.096499443054199, "global_step": 449023, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.069547176361084, "global_step": 449024, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.049102306365967, "global_step": 449025, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0773823261260986, "global_step": 449026, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.129690647125244, "global_step": 449027, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0476157665252686, "global_step": 449028, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0302913188934326, "global_step": 449029, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.115849018096924, "global_step": 449030, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1170215606689453, "global_step": 449031, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1487228870391846, "global_step": 449032, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0886130332946777, "global_step": 449033, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1241490840911865, "global_step": 449034, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.098947525024414, "global_step": 449035, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.019524574279785, "global_step": 449036, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.97860848903656, "global_step": 449037, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1457157135009766, "global_step": 449038, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1186537742614746, "global_step": 449039, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.040292263031006, "global_step": 449040, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.051226854324341, "global_step": 449041, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0659351348876953, "global_step": 449042, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9892512559890747, "global_step": 449043, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0312693119049072, "global_step": 449044, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.040398120880127, "global_step": 449045, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.036303758621216, "global_step": 449046, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9908889532089233, "global_step": 449047, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9644204378128052, "global_step": 449048, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.061445951461792, "global_step": 449049, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1320438385009766, "global_step": 449050, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1462628841400146, "global_step": 449051, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.023379325866699, "global_step": 449052, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.024470090866089, "global_step": 449053, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.081143379211426, "global_step": 449054, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.055051326751709, "global_step": 449055, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0160953998565674, "global_step": 449056, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1714930534362793, "global_step": 449057, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.150667428970337, "global_step": 449058, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.025670051574707, "global_step": 449059, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.093244791030884, "global_step": 449060, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.106055974960327, "global_step": 449061, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1264376640319824, "global_step": 449062, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1108875274658203, "global_step": 449063, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1355276107788086, "global_step": 449064, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.164761543273926, "global_step": 449065, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0881435871124268, "global_step": 449066, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0363166332244873, "global_step": 449067, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.074657917022705, "global_step": 449068, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9894109964370728, "global_step": 449069, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0161399841308594, "global_step": 449070, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0849685668945312, "global_step": 449071, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0087244510650635, "global_step": 449072, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1093690395355225, "global_step": 449073, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0567119121551514, "global_step": 449074, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0567920207977295, "global_step": 449075, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.110100030899048, "global_step": 449076, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.044947862625122, "global_step": 449077, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0092334747314453, "global_step": 449078, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.087256669998169, "global_step": 449079, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.973345160484314, "global_step": 449080, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0127835273742676, "global_step": 449081, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1753029823303223, "global_step": 449082, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0563578605651855, "global_step": 449083, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0357472896575928, "global_step": 449084, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0643367767333984, "global_step": 449085, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1624865531921387, "global_step": 449086, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.14329195022583, "global_step": 449087, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0312612056732178, "global_step": 449088, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0259270668029785, "global_step": 449089, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.053368330001831, "global_step": 449090, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.106196880340576, "global_step": 449091, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0846128463745117, "global_step": 449092, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0233993530273438, "global_step": 449093, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1330084800720215, "global_step": 449094, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0507495403289795, "global_step": 449095, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0430526733398438, "global_step": 449096, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.052318572998047, "global_step": 449097, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9824578762054443, "global_step": 449098, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1624114513397217, "global_step": 449099, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.097078323364258, "global_step": 449100, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0583488941192627, "global_step": 449101, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0194127559661865, "global_step": 449102, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0232596397399902, "global_step": 449103, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.054774284362793, "global_step": 449104, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0614287853240967, "global_step": 449105, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.039820671081543, "global_step": 449106, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.063154697418213, "global_step": 449107, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.169308662414551, "global_step": 449108, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0995774269104004, "global_step": 449109, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1099584102630615, "global_step": 449110, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.024432897567749, "global_step": 449111, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0732438564300537, "global_step": 449112, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0014407634735107, "global_step": 449113, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0246617794036865, "global_step": 449114, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0474088191986084, "global_step": 449115, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0527005195617676, "global_step": 449116, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1330020427703857, "global_step": 449117, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.105492353439331, "global_step": 449118, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0837228298187256, "global_step": 449119, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.042257308959961, "global_step": 449120, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.159529447555542, "global_step": 449121, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.992232322692871, "global_step": 449122, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0879762172698975, "global_step": 449123, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.2073111534118652, "global_step": 449124, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0543599128723145, "global_step": 449125, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9232351779937744, "global_step": 449126, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9785726070404053, "global_step": 449127, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0175628662109375, "global_step": 449128, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0588669776916504, "global_step": 449129, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0567739009857178, "global_step": 449130, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.120506525039673, "global_step": 449131, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0415542125701904, "global_step": 449132, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.100295066833496, "global_step": 449133, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.073944330215454, "global_step": 449134, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0538365840911865, "global_step": 449135, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0985546112060547, "global_step": 449136, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.144451141357422, "global_step": 449137, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0871846675872803, "global_step": 449138, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.132688045501709, "global_step": 449139, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.100564479827881, "global_step": 449140, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0360355377197266, "global_step": 449141, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0278377532958984, "global_step": 449142, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0175974369049072, "global_step": 449143, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0169565677642822, "global_step": 449144, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0824999809265137, "global_step": 449145, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0433216094970703, "global_step": 449146, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.005774974822998, "global_step": 449147, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9602309465408325, "global_step": 449148, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.042840003967285, "global_step": 449149, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1433465480804443, "global_step": 449150, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.956950306892395, "global_step": 449151, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.014716148376465, "global_step": 449152, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0326390266418457, "global_step": 449153, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.089043378829956, "global_step": 449154, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.07352614402771, "global_step": 449155, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0633132457733154, "global_step": 449156, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.183840036392212, "global_step": 449157, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0662553310394287, "global_step": 449158, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.026775598526001, "global_step": 449159, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0342555046081543, "global_step": 449160, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.083176851272583, "global_step": 449161, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9717837572097778, "global_step": 449162, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0218183994293213, "global_step": 449163, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0845611095428467, "global_step": 449164, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.049311399459839, "global_step": 449165, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.122934341430664, "global_step": 449166, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0621538162231445, "global_step": 449167, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1116514205932617, "global_step": 449168, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9833542108535767, "global_step": 449169, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0214855670928955, "global_step": 449170, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0728776454925537, "global_step": 449171, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.085991621017456, "global_step": 449172, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0017991065979004, "global_step": 449173, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0753073692321777, "global_step": 449174, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.037508726119995, "global_step": 449175, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.117142915725708, "global_step": 449176, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1670238971710205, "global_step": 449177, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.057649850845337, "global_step": 449178, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.095890760421753, "global_step": 449179, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.114661693572998, "global_step": 449180, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0879344940185547, "global_step": 449181, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.069216012954712, "global_step": 449182, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.058504581451416, "global_step": 449183, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.08107590675354, "global_step": 449184, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.037219762802124, "global_step": 449185, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1432182788848877, "global_step": 449186, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0994455814361572, "global_step": 449187, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0336456298828125, "global_step": 449188, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0376856327056885, "global_step": 449189, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.023122549057007, "global_step": 449190, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.084573745727539, "global_step": 449191, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.181269645690918, "global_step": 449192, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.100801467895508, "global_step": 449193, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0931243896484375, "global_step": 449194, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.089812755584717, "global_step": 449195, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1194891929626465, "global_step": 449196, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.075684070587158, "global_step": 449197, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.037018060684204, "global_step": 449198, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1232895851135254, "global_step": 449199, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0804660320281982, "global_step": 449200, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0559639930725098, "global_step": 449201, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0125937461853027, "global_step": 449202, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0879628658294678, "global_step": 449203, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0332436561584473, "global_step": 449204, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0842466354370117, "global_step": 449205, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.049234390258789, "global_step": 449206, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0658717155456543, "global_step": 449207, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9431172609329224, "global_step": 449208, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.058145523071289, "global_step": 449209, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.026991844177246, "global_step": 449210, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0134527683258057, "global_step": 449211, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0538225173950195, "global_step": 449212, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0529885292053223, "global_step": 449213, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0988800525665283, "global_step": 449214, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0217666625976562, "global_step": 449215, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.02527117729187, "global_step": 449216, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.079777956008911, "global_step": 449217, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.00919771194458, "global_step": 449218, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.065274715423584, "global_step": 449219, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0571320056915283, "global_step": 449220, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1626203060150146, "global_step": 449221, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.042156934738159, "global_step": 449222, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.076268434524536, "global_step": 449223, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1009521484375, "global_step": 449224, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.045339822769165, "global_step": 449225, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.074676752090454, "global_step": 449226, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.072927713394165, "global_step": 449227, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.130375862121582, "global_step": 449228, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0701398849487305, "global_step": 449229, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.176577568054199, "global_step": 449230, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.019439458847046, "global_step": 449231, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1186158657073975, "global_step": 449232, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1014676094055176, "global_step": 449233, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0649871826171875, "global_step": 449234, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9941201210021973, "global_step": 449235, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0370676517486572, "global_step": 449236, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0364441871643066, "global_step": 449237, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9872344732284546, "global_step": 449238, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.017185926437378, "global_step": 449239, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.167407989501953, "global_step": 449240, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1284217834472656, "global_step": 449241, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.009430170059204, "global_step": 449242, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1075422763824463, "global_step": 449243, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0290117263793945, "global_step": 449244, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.117318868637085, "global_step": 449245, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0484111309051514, "global_step": 449246, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1319005489349365, "global_step": 449247, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0948503017425537, "global_step": 449248, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0039095878601074, "global_step": 449249, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.092597484588623, "global_step": 449250, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0467309951782227, "global_step": 449251, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.021869421005249, "global_step": 449252, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0644595623016357, "global_step": 449253, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1152100563049316, "global_step": 449254, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0711545944213867, "global_step": 449255, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.074954032897949, "global_step": 449256, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.173868179321289, "global_step": 449257, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0815742015838623, "global_step": 449258, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0617496967315674, "global_step": 449259, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1268813610076904, "global_step": 449260, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9849777221679688, "global_step": 449261, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.089130163192749, "global_step": 449262, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0371434688568115, "global_step": 449263, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.971265435218811, "global_step": 449264, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0438930988311768, "global_step": 449265, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0859153270721436, "global_step": 449266, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.126741886138916, "global_step": 449267, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.178755760192871, "global_step": 449268, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.077643632888794, "global_step": 449269, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.052727222442627, "global_step": 449270, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.07210373878479, "global_step": 449271, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0604403018951416, "global_step": 449272, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.13112211227417, "global_step": 449273, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.146547317504883, "global_step": 449274, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1314876079559326, "global_step": 449275, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.070638656616211, "global_step": 449276, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0528318881988525, "global_step": 449277, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0848042964935303, "global_step": 449278, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.102961301803589, "global_step": 449279, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.00002384185791, "global_step": 449280, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1278111934661865, "global_step": 449281, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0005555152893066, "global_step": 449282, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0614304542541504, "global_step": 449283, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.079291820526123, "global_step": 449284, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0495998859405518, "global_step": 449285, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.119300365447998, "global_step": 449286, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1069188117980957, "global_step": 449287, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1298623085021973, "global_step": 449288, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.099660634994507, "global_step": 449289, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.043658494949341, "global_step": 449290, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0629889965057373, "global_step": 449291, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.049605131149292, "global_step": 449292, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1507742404937744, "global_step": 449293, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.09916090965271, "global_step": 449294, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0069620609283447, "global_step": 449295, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0625503063201904, "global_step": 449296, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.150813341140747, "global_step": 449297, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1334095001220703, "global_step": 449298, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.095494031906128, "global_step": 449299, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.089691400527954, "global_step": 449300, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0494096279144287, "global_step": 449301, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0767927169799805, "global_step": 449302, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0586764812469482, "global_step": 449303, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.118049144744873, "global_step": 449304, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0836410522460938, "global_step": 449305, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0125341415405273, "global_step": 449306, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.067746877670288, "global_step": 449307, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.046290397644043, "global_step": 449308, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.091712474822998, "global_step": 449309, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.104123115539551, "global_step": 449310, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0454511642456055, "global_step": 449311, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.067897319793701, "global_step": 449312, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1007771492004395, "global_step": 449313, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0724074840545654, "global_step": 449314, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.056480884552002, "global_step": 449315, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.085853338241577, "global_step": 449316, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.074820041656494, "global_step": 449317, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0745255947113037, "global_step": 449318, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0776615142822266, "global_step": 449319, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.059631109237671, "global_step": 449320, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0458858013153076, "global_step": 449321, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.118534564971924, "global_step": 449322, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0513830184936523, "global_step": 449323, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0007524490356445, "global_step": 449324, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.034334421157837, "global_step": 449325, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.141824245452881, "global_step": 449326, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.125133514404297, "global_step": 449327, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.032805919647217, "global_step": 449328, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1211817264556885, "global_step": 449329, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1088099479675293, "global_step": 449330, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0843114852905273, "global_step": 449331, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0207889080047607, "global_step": 449332, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.041321039199829, "global_step": 449333, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0988733768463135, "global_step": 449334, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.126246452331543, "global_step": 449335, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.073643684387207, "global_step": 449336, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.953065276145935, "global_step": 449337, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0871284008026123, "global_step": 449338, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.159989356994629, "global_step": 449339, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.094788074493408, "global_step": 449340, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0937867164611816, "global_step": 449341, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0726757049560547, "global_step": 449342, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1073715686798096, "global_step": 449343, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1901156902313232, "global_step": 449344, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.144984722137451, "global_step": 449345, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.122173547744751, "global_step": 449346, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.120208501815796, "global_step": 449347, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0935263633728027, "global_step": 449348, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1028783321380615, "global_step": 449349, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.188758134841919, "global_step": 449350, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0178818702697754, "global_step": 449351, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.110224485397339, "global_step": 449352, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0974884033203125, "global_step": 449353, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.090242862701416, "global_step": 449354, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1012213230133057, "global_step": 449355, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.120244026184082, "global_step": 449356, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.037144899368286, "global_step": 449357, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.085933208465576, "global_step": 449358, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1342036724090576, "global_step": 449359, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.058770179748535, "global_step": 449360, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0547730922698975, "global_step": 449361, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1311826705932617, "global_step": 449362, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0743746757507324, "global_step": 449363, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1467292308807373, "global_step": 449364, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.031212329864502, "global_step": 449365, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.021488666534424, "global_step": 449366, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0865142345428467, "global_step": 449367, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.074739933013916, "global_step": 449368, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.14369797706604, "global_step": 449369, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0012543201446533, "global_step": 449370, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0020883083343506, "global_step": 449371, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0491020679473877, "global_step": 449372, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.134453535079956, "global_step": 449373, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0124757289886475, "global_step": 449374, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1962342262268066, "global_step": 449375, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.048981189727783, "global_step": 449376, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.084374189376831, "global_step": 449377, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.055171251296997, "global_step": 449378, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0920181274414062, "global_step": 449379, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.021101713180542, "global_step": 449380, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1010611057281494, "global_step": 449381, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1113319396972656, "global_step": 449382, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.11517596244812, "global_step": 449383, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.076831340789795, "global_step": 449384, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.113631248474121, "global_step": 449385, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1296348571777344, "global_step": 449386, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.19309401512146, "global_step": 449387, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1492037773132324, "global_step": 449388, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1423401832580566, "global_step": 449389, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1311697959899902, "global_step": 449390, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0311684608459473, "global_step": 449391, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.087742328643799, "global_step": 449392, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0696892738342285, "global_step": 449393, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0354974269866943, "global_step": 449394, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0415401458740234, "global_step": 449395, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1975581645965576, "global_step": 449396, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1126625537872314, "global_step": 449397, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0696020126342773, "global_step": 449398, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1364715099334717, "global_step": 449399, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0502305030822754, "global_step": 449400, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0389292240142822, "global_step": 449401, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0596024990081787, "global_step": 449402, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0374011993408203, "global_step": 449403, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0721166133880615, "global_step": 449404, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.009498119354248, "global_step": 449405, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.128833055496216, "global_step": 449406, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1077823638916016, "global_step": 449407, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9436529874801636, "global_step": 449408, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.132244110107422, "global_step": 449409, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.087599754333496, "global_step": 449410, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.176703453063965, "global_step": 449411, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.074920654296875, "global_step": 449412, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.125840902328491, "global_step": 449413, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.106497049331665, "global_step": 449414, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.100165843963623, "global_step": 449415, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0457000732421875, "global_step": 449416, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0965921878814697, "global_step": 449417, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1101112365722656, "global_step": 449418, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.135488748550415, "global_step": 449419, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0225369930267334, "global_step": 449420, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.029933214187622, "global_step": 449421, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.066276788711548, "global_step": 449422, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0431854724884033, "global_step": 449423, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.139892339706421, "global_step": 449424, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.042109966278076, "global_step": 449425, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0790278911590576, "global_step": 449426, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.066312074661255, "global_step": 449427, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0876693725585938, "global_step": 449428, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9692901372909546, "global_step": 449429, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0936620235443115, "global_step": 449430, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0983433723449707, "global_step": 449431, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.07476544380188, "global_step": 449432, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0981013774871826, "global_step": 449433, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.99440336227417, "global_step": 449434, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0819084644317627, "global_step": 449435, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.078490972518921, "global_step": 449436, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.109475612640381, "global_step": 449437, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.018198013305664, "global_step": 449438, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0669853687286377, "global_step": 449439, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0467569828033447, "global_step": 449440, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0597686767578125, "global_step": 449441, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9420568943023682, "global_step": 449442, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.088123321533203, "global_step": 449443, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1143927574157715, "global_step": 449444, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0666468143463135, "global_step": 449445, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.13848876953125, "global_step": 449446, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0762970447540283, "global_step": 449447, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.068547248840332, "global_step": 449448, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1088082790374756, "global_step": 449449, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0822134017944336, "global_step": 449450, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1778299808502197, "global_step": 449451, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.123044729232788, "global_step": 449452, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1258928775787354, "global_step": 449453, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.3168020248413086, "global_step": 449454, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1429150104522705, "global_step": 449455, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9486057758331299, "global_step": 449456, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1576387882232666, "global_step": 449457, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.013654947280884, "global_step": 449458, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.048555612564087, "global_step": 449459, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0256309509277344, "global_step": 449460, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.072950839996338, "global_step": 449461, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.098576068878174, "global_step": 449462, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.02844500541687, "global_step": 449463, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.081063985824585, "global_step": 449464, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.164468288421631, "global_step": 449465, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.029024124145508, "global_step": 449466, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0862293243408203, "global_step": 449467, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.077877998352051, "global_step": 449468, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1039748191833496, "global_step": 449469, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0664751529693604, "global_step": 449470, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0156235694885254, "global_step": 449471, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1153271198272705, "global_step": 449472, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.049513578414917, "global_step": 449473, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.123314619064331, "global_step": 449474, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1137049198150635, "global_step": 449475, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0731520652770996, "global_step": 449476, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0833194255828857, "global_step": 449477, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0608253479003906, "global_step": 449478, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0681259632110596, "global_step": 449479, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.122272253036499, "global_step": 449480, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9975961446762085, "global_step": 449481, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0394768714904785, "global_step": 449482, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0387156009674072, "global_step": 449483, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0957603454589844, "global_step": 449484, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0644400119781494, "global_step": 449485, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.081981897354126, "global_step": 449486, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0954110622406006, "global_step": 449487, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1088039875030518, "global_step": 449488, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1651129722595215, "global_step": 449489, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1089932918548584, "global_step": 449490, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.101679801940918, "global_step": 449491, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.065624952316284, "global_step": 449492, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0133705139160156, "global_step": 449493, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0390737056732178, "global_step": 449494, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.000814914703369, "global_step": 449495, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0669820308685303, "global_step": 449496, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0688066482543945, "global_step": 449497, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0868844985961914, "global_step": 449498, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9345247745513916, "global_step": 449499, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0410983562469482, "global_step": 449500, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.169940710067749, "global_step": 449501, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0705552101135254, "global_step": 449502, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.070042610168457, "global_step": 449503, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.110670328140259, "global_step": 449504, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9753841161727905, "global_step": 449505, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.100698232650757, "global_step": 449506, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.101421356201172, "global_step": 449507, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0519628524780273, "global_step": 449508, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0436015129089355, "global_step": 449509, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0592691898345947, "global_step": 449510, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.123255491256714, "global_step": 449511, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1423885822296143, "global_step": 449512, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1039137840270996, "global_step": 449513, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0925018787384033, "global_step": 449514, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0505154132843018, "global_step": 449515, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.076706886291504, "global_step": 449516, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.089420795440674, "global_step": 449517, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.08534836769104, "global_step": 449518, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.103285074234009, "global_step": 449519, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1233530044555664, "global_step": 449520, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1302406787872314, "global_step": 449521, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0263328552246094, "global_step": 449522, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1010501384735107, "global_step": 449523, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.150041341781616, "global_step": 449524, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1774611473083496, "global_step": 449525, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0205488204956055, "global_step": 449526, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.000927209854126, "global_step": 449527, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.130054473876953, "global_step": 449528, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.142289161682129, "global_step": 449529, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.107841968536377, "global_step": 449530, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0387229919433594, "global_step": 449531, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1077651977539062, "global_step": 449532, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0439467430114746, "global_step": 449533, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.061614513397217, "global_step": 449534, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.173114538192749, "global_step": 449535, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0200281143188477, "global_step": 449536, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1106910705566406, "global_step": 449537, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.042245388031006, "global_step": 449538, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.108344793319702, "global_step": 449539, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.045048236846924, "global_step": 449540, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0672786235809326, "global_step": 449541, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.09006404876709, "global_step": 449542, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1533703804016113, "global_step": 449543, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1687674522399902, "global_step": 449544, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0612401962280273, "global_step": 449545, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.071143865585327, "global_step": 449546, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.054527521133423, "global_step": 449547, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0765886306762695, "global_step": 449548, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0877685546875, "global_step": 449549, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0093982219696045, "global_step": 449550, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9841946363449097, "global_step": 449551, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.102656126022339, "global_step": 449552, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0863566398620605, "global_step": 449553, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0855252742767334, "global_step": 449554, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0551750659942627, "global_step": 449555, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.203573703765869, "global_step": 449556, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0644583702087402, "global_step": 449557, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0634334087371826, "global_step": 449558, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.110506296157837, "global_step": 449559, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.062464952468872, "global_step": 449560, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0838892459869385, "global_step": 449561, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.093122959136963, "global_step": 449562, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0510308742523193, "global_step": 449563, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0305211544036865, "global_step": 449564, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0899434089660645, "global_step": 449565, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0035994052886963, "global_step": 449566, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0582404136657715, "global_step": 449567, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.067626714706421, "global_step": 449568, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1389060020446777, "global_step": 449569, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.061756134033203, "global_step": 449570, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.136366128921509, "global_step": 449571, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1483497619628906, "global_step": 449572, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.119441032409668, "global_step": 449573, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0367162227630615, "global_step": 449574, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0210273265838623, "global_step": 449575, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1257731914520264, "global_step": 449576, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9757936000823975, "global_step": 449577, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.026771306991577, "global_step": 449578, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.045269012451172, "global_step": 449579, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0107955932617188, "global_step": 449580, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.033442258834839, "global_step": 449581, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.170305013656616, "global_step": 449582, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.091231107711792, "global_step": 449583, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.122129440307617, "global_step": 449584, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0414459705352783, "global_step": 449585, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0793848037719727, "global_step": 449586, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0475947856903076, "global_step": 449587, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0291953086853027, "global_step": 449588, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1243715286254883, "global_step": 449589, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0794496536254883, "global_step": 449590, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.987284779548645, "global_step": 449591, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.156327724456787, "global_step": 449592, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.096764326095581, "global_step": 449593, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.130312204360962, "global_step": 449594, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1028218269348145, "global_step": 449595, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.171281576156616, "global_step": 449596, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0136098861694336, "global_step": 449597, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.14194393157959, "global_step": 449598, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.099609851837158, "global_step": 449599, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.032726287841797, "global_step": 449600, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.068535804748535, "global_step": 449601, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.102569341659546, "global_step": 449602, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.135911464691162, "global_step": 449603, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0518453121185303, "global_step": 449604, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0121731758117676, "global_step": 449605, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0043790340423584, "global_step": 449606, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9862746000289917, "global_step": 449607, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0627012252807617, "global_step": 449608, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1128737926483154, "global_step": 449609, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1268301010131836, "global_step": 449610, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0251667499542236, "global_step": 449611, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.025904893875122, "global_step": 449612, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.072847366333008, "global_step": 449613, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0644123554229736, "global_step": 449614, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.066725492477417, "global_step": 449615, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0917375087738037, "global_step": 449616, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1166417598724365, "global_step": 449617, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.067836046218872, "global_step": 449618, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0657339096069336, "global_step": 449619, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1188292503356934, "global_step": 449620, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.10378360748291, "global_step": 449621, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1302490234375, "global_step": 449622, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0779964923858643, "global_step": 449623, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1480231285095215, "global_step": 449624, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.107131242752075, "global_step": 449625, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.063826560974121, "global_step": 449626, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.018601417541504, "global_step": 449627, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.041058301925659, "global_step": 449628, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0989773273468018, "global_step": 449629, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0809485912323, "global_step": 449630, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0954384803771973, "global_step": 449631, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1519198417663574, "global_step": 449632, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1000282764434814, "global_step": 449633, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.134477376937866, "global_step": 449634, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1155238151550293, "global_step": 449635, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.108876943588257, "global_step": 449636, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9608702659606934, "global_step": 449637, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0415453910827637, "global_step": 449638, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.032010316848755, "global_step": 449639, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0132813453674316, "global_step": 449640, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0450384616851807, "global_step": 449641, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0889363288879395, "global_step": 449642, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1148080825805664, "global_step": 449643, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.175518035888672, "global_step": 449644, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.09287691116333, "global_step": 449645, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.049323797225952, "global_step": 449646, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0424392223358154, "global_step": 449647, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.018308162689209, "global_step": 449648, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.027092218399048, "global_step": 449649, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.099923610687256, "global_step": 449650, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.063586950302124, "global_step": 449651, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.038601875305176, "global_step": 449652, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.035520076751709, "global_step": 449653, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1748709678649902, "global_step": 449654, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0339725017547607, "global_step": 449655, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.064008951187134, "global_step": 449656, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0883543491363525, "global_step": 449657, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0207550525665283, "global_step": 449658, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0744476318359375, "global_step": 449659, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0495212078094482, "global_step": 449660, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0811960697174072, "global_step": 449661, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.083911418914795, "global_step": 449662, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9866092205047607, "global_step": 449663, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.126108169555664, "global_step": 449664, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1091434955596924, "global_step": 449665, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.003690481185913, "global_step": 449666, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.074496269226074, "global_step": 449667, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.050657272338867, "global_step": 449668, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.2201826572418213, "global_step": 449669, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.143392324447632, "global_step": 449670, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.117232322692871, "global_step": 449671, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1925716400146484, "global_step": 449672, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.055206298828125, "global_step": 449673, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0660910606384277, "global_step": 449674, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0347769260406494, "global_step": 449675, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.18626070022583, "global_step": 449676, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.079644203186035, "global_step": 449677, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.078032970428467, "global_step": 449678, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.095180034637451, "global_step": 449679, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.041815996170044, "global_step": 449680, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.073744773864746, "global_step": 449681, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.042562961578369, "global_step": 449682, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.101095199584961, "global_step": 449683, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.013658285140991, "global_step": 449684, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.2178285121917725, "global_step": 449685, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0484604835510254, "global_step": 449686, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.175488233566284, "global_step": 449687, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0577943325042725, "global_step": 449688, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0059869289398193, "global_step": 449689, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.034520149230957, "global_step": 449690, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.090319871902466, "global_step": 449691, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1427154541015625, "global_step": 449692, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1100900173187256, "global_step": 449693, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.068188190460205, "global_step": 449694, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0805225372314453, "global_step": 449695, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.097702980041504, "global_step": 449696, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0664730072021484, "global_step": 449697, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0677218437194824, "global_step": 449698, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1194000244140625, "global_step": 449699, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1291370391845703, "global_step": 449700, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.073594808578491, "global_step": 449701, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.066067934036255, "global_step": 449702, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0781517028808594, "global_step": 449703, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0584821701049805, "global_step": 449704, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.049639940261841, "global_step": 449705, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.04668927192688, "global_step": 449706, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0719237327575684, "global_step": 449707, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.052935838699341, "global_step": 449708, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.116882085800171, "global_step": 449709, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0761163234710693, "global_step": 449710, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.03222393989563, "global_step": 449711, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0559194087982178, "global_step": 449712, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.079775810241699, "global_step": 449713, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.105428695678711, "global_step": 449714, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0820064544677734, "global_step": 449715, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.052116870880127, "global_step": 449716, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.002596855163574, "global_step": 449717, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.00691556930542, "global_step": 449718, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.095754384994507, "global_step": 449719, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0610415935516357, "global_step": 449720, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0603792667388916, "global_step": 449721, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0233147144317627, "global_step": 449722, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9994310140609741, "global_step": 449723, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0341756343841553, "global_step": 449724, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1053340435028076, "global_step": 449725, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.175886392593384, "global_step": 449726, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.1312005519866943, "global_step": 449727, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.079951763153076, "global_step": 449728, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.044802188873291, "global_step": 449729, "epoch": 813, "lr": 5e-05}
{"train_loss": 1.9937305450439453, "global_step": 449730, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.096532106399536, "global_step": 449731, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0434067249298096, "global_step": 449732, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0777008533477783, "global_step": 449733, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0371718406677246, "global_step": 449734, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.048096179962158, "global_step": 449735, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.129185914993286, "global_step": 449736, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.108774185180664, "global_step": 449737, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0646657943725586, "global_step": 449738, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0591678619384766, "global_step": 449739, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0543770790100098, "global_step": 449740, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.058281660079956, "global_step": 449741, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.050253391265869, "global_step": 449742, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0425162315368652, "global_step": 449743, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.097637414932251, "global_step": 449744, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0955617427825928, "global_step": 449745, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.0626676082611084, "global_step": 449746, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.041783571243286, "global_step": 449747, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.073394775390625, "global_step": 449748, "epoch": 813, "lr": 5e-05}
{"train_loss": 2.105583667755127, "global_step": 449749, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0041706562042236, "global_step": 449750, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.076677083969116, "global_step": 449751, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0197083950042725, "global_step": 449752, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1498613357543945, "global_step": 449753, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1268889904022217, "global_step": 449754, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9422776699066162, "global_step": 449755, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0623939037323, "global_step": 449756, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.114051580429077, "global_step": 449757, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.073272466659546, "global_step": 449758, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1839046478271484, "global_step": 449759, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0122387409210205, "global_step": 449760, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.124008893966675, "global_step": 449761, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0576603412628174, "global_step": 449762, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0659713745117188, "global_step": 449763, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1050798892974854, "global_step": 449764, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0371789932250977, "global_step": 449765, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0154592990875244, "global_step": 449766, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9446866512298584, "global_step": 449767, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0104928016662598, "global_step": 449768, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.091428518295288, "global_step": 449769, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9976530075073242, "global_step": 449770, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0202908515930176, "global_step": 449771, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9982213973999023, "global_step": 449772, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0346102714538574, "global_step": 449773, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0855448246002197, "global_step": 449774, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0877599716186523, "global_step": 449775, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9392621517181396, "global_step": 449776, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1341121196746826, "global_step": 449777, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.934553623199463, "global_step": 449778, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.03981614112854, "global_step": 449779, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.060913324356079, "global_step": 449780, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.073789119720459, "global_step": 449781, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0966148376464844, "global_step": 449782, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.028618335723877, "global_step": 449783, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.078793525695801, "global_step": 449784, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.048428773880005, "global_step": 449785, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0000364780426025, "global_step": 449786, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0916028022766113, "global_step": 449787, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.108933925628662, "global_step": 449788, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.993348240852356, "global_step": 449789, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0447468757629395, "global_step": 449790, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.071873664855957, "global_step": 449791, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.07399845123291, "global_step": 449792, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.105018377304077, "global_step": 449793, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.2278146743774414, "global_step": 449794, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.064206600189209, "global_step": 449795, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0715863704681396, "global_step": 449796, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1568081378936768, "global_step": 449797, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0107133388519287, "global_step": 449798, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1451220512390137, "global_step": 449799, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.055696964263916, "global_step": 449800, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.107178211212158, "global_step": 449801, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0258028507232666, "global_step": 449802, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.093921184539795, "global_step": 449803, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0418996810913086, "global_step": 449804, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1589572429656982, "global_step": 449805, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9601894617080688, "global_step": 449806, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0475025177001953, "global_step": 449807, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9918816089630127, "global_step": 449808, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.105842351913452, "global_step": 449809, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.10213041305542, "global_step": 449810, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0294172763824463, "global_step": 449811, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.060089111328125, "global_step": 449812, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1270456314086914, "global_step": 449813, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.08624529838562, "global_step": 449814, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1219375133514404, "global_step": 449815, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.062469720840454, "global_step": 449816, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.171830177307129, "global_step": 449817, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0232913494110107, "global_step": 449818, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.09922194480896, "global_step": 449819, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1030187606811523, "global_step": 449820, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.020907402038574, "global_step": 449821, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0480103492736816, "global_step": 449822, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0847222805023193, "global_step": 449823, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0957086086273193, "global_step": 449824, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0316216945648193, "global_step": 449825, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1244688034057617, "global_step": 449826, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0197389125823975, "global_step": 449827, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9906113147735596, "global_step": 449828, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.068432569503784, "global_step": 449829, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0950350761413574, "global_step": 449830, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.039351224899292, "global_step": 449831, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0512609481811523, "global_step": 449832, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9913233518600464, "global_step": 449833, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.057133674621582, "global_step": 449834, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0727744102478027, "global_step": 449835, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9949504137039185, "global_step": 449836, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.043808937072754, "global_step": 449837, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.037492275238037, "global_step": 449838, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.097285270690918, "global_step": 449839, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.090873956680298, "global_step": 449840, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.032994508743286, "global_step": 449841, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9866547584533691, "global_step": 449842, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.042297840118408, "global_step": 449843, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.00687575340271, "global_step": 449844, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1311581134796143, "global_step": 449845, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1280910968780518, "global_step": 449846, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.052454710006714, "global_step": 449847, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0282704830169678, "global_step": 449848, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.015902280807495, "global_step": 449849, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.00655460357666, "global_step": 449850, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0706586837768555, "global_step": 449851, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0049216747283936, "global_step": 449852, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0585811138153076, "global_step": 449853, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1052165031433105, "global_step": 449854, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0649542808532715, "global_step": 449855, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0616962909698486, "global_step": 449856, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.113948106765747, "global_step": 449857, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.096487522125244, "global_step": 449858, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.068957567214966, "global_step": 449859, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0312674045562744, "global_step": 449860, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.938428521156311, "global_step": 449861, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0541341304779053, "global_step": 449862, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.075413227081299, "global_step": 449863, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0190398693084717, "global_step": 449864, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0435709953308105, "global_step": 449865, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9602535963058472, "global_step": 449866, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1377649307250977, "global_step": 449867, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0245234966278076, "global_step": 449868, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0475447177886963, "global_step": 449869, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0901339054107666, "global_step": 449870, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.997420072555542, "global_step": 449871, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.080486536026001, "global_step": 449872, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.057027816772461, "global_step": 449873, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0438504219055176, "global_step": 449874, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.05977463722229, "global_step": 449875, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9809269905090332, "global_step": 449876, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.159952402114868, "global_step": 449877, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9865508079528809, "global_step": 449878, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.950371265411377, "global_step": 449879, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0720067024230957, "global_step": 449880, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.029576301574707, "global_step": 449881, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1338255405426025, "global_step": 449882, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.062178373336792, "global_step": 449883, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.076444625854492, "global_step": 449884, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.990492820739746, "global_step": 449885, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.046891689300537, "global_step": 449886, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.101914405822754, "global_step": 449887, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.124937057495117, "global_step": 449888, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1128106117248535, "global_step": 449889, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1214184761047363, "global_step": 449890, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.063730001449585, "global_step": 449891, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0471837520599365, "global_step": 449892, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0754942893981934, "global_step": 449893, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0807032585144043, "global_step": 449894, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1252052783966064, "global_step": 449895, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.144007921218872, "global_step": 449896, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1248764991760254, "global_step": 449897, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0338730812072754, "global_step": 449898, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1471691131591797, "global_step": 449899, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0765933990478516, "global_step": 449900, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.063117265701294, "global_step": 449901, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0122435092926025, "global_step": 449902, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.195270538330078, "global_step": 449903, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0391170978546143, "global_step": 449904, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.080991506576538, "global_step": 449905, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.16232967376709, "global_step": 449906, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0510001182556152, "global_step": 449907, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0619752407073975, "global_step": 449908, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.14599871635437, "global_step": 449909, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0477287769317627, "global_step": 449910, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0763936042785645, "global_step": 449911, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0303540229797363, "global_step": 449912, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.108156442642212, "global_step": 449913, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0750887393951416, "global_step": 449914, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.066044807434082, "global_step": 449915, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1557564735412598, "global_step": 449916, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0483756065368652, "global_step": 449917, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0174238681793213, "global_step": 449918, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.156599283218384, "global_step": 449919, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0881574153900146, "global_step": 449920, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.089165210723877, "global_step": 449921, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0495424270629883, "global_step": 449922, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0962584018707275, "global_step": 449923, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0787694454193115, "global_step": 449924, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0223917961120605, "global_step": 449925, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0238964557647705, "global_step": 449926, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.024385690689087, "global_step": 449927, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.057166814804077, "global_step": 449928, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.160292148590088, "global_step": 449929, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0492758750915527, "global_step": 449930, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.159456968307495, "global_step": 449931, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0678486824035645, "global_step": 449932, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0282490253448486, "global_step": 449933, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9625359773635864, "global_step": 449934, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0617239475250244, "global_step": 449935, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0246684551239014, "global_step": 449936, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0927703380584717, "global_step": 449937, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0419068336486816, "global_step": 449938, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0423526763916016, "global_step": 449939, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.056408643722534, "global_step": 449940, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1034231185913086, "global_step": 449941, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0902068614959717, "global_step": 449942, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1323680877685547, "global_step": 449943, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.056520700454712, "global_step": 449944, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0114223957061768, "global_step": 449945, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9604363441467285, "global_step": 449946, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0991287231445312, "global_step": 449947, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9957166910171509, "global_step": 449948, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.065570116043091, "global_step": 449949, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.009122610092163, "global_step": 449950, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0578877925872803, "global_step": 449951, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.017136335372925, "global_step": 449952, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.002079486846924, "global_step": 449953, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.080310344696045, "global_step": 449954, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.040639877319336, "global_step": 449955, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9839413166046143, "global_step": 449956, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9792323112487793, "global_step": 449957, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1070919036865234, "global_step": 449958, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0253567695617676, "global_step": 449959, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.04086971282959, "global_step": 449960, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.031919002532959, "global_step": 449961, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1160333156585693, "global_step": 449962, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0949535369873047, "global_step": 449963, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0418543815612793, "global_step": 449964, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0475263595581055, "global_step": 449965, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0677554607391357, "global_step": 449966, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.016735792160034, "global_step": 449967, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.082158327102661, "global_step": 449968, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.112213134765625, "global_step": 449969, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.094987154006958, "global_step": 449970, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0214169025421143, "global_step": 449971, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.069380044937134, "global_step": 449972, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0378293991088867, "global_step": 449973, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.110337257385254, "global_step": 449974, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1531641483306885, "global_step": 449975, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.114112138748169, "global_step": 449976, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0465502738952637, "global_step": 449977, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.089233160018921, "global_step": 449978, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0215165615081787, "global_step": 449979, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1081511974334717, "global_step": 449980, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.086235761642456, "global_step": 449981, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0898256301879883, "global_step": 449982, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0590996742248535, "global_step": 449983, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.134188175201416, "global_step": 449984, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.057800054550171, "global_step": 449985, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.124223232269287, "global_step": 449986, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.085151433944702, "global_step": 449987, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.117307424545288, "global_step": 449988, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0703072547912598, "global_step": 449989, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.115595817565918, "global_step": 449990, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0467965602874756, "global_step": 449991, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0284430980682373, "global_step": 449992, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0451958179473877, "global_step": 449993, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9193943738937378, "global_step": 449994, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0663950443267822, "global_step": 449995, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1072542667388916, "global_step": 449996, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0970044136047363, "global_step": 449997, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.111937999725342, "global_step": 449998, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0073866844177246, "global_step": 449999, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.022266387939453, "global_step": 450000, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0106818675994873, "global_step": 450001, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.033968925476074, "global_step": 450002, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0479979515075684, "global_step": 450003, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.2227721214294434, "global_step": 450004, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.141146183013916, "global_step": 450005, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1506595611572266, "global_step": 450006, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0209600925445557, "global_step": 450007, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9794591665267944, "global_step": 450008, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0743701457977295, "global_step": 450009, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.118928909301758, "global_step": 450010, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.039447546005249, "global_step": 450011, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.060366630554199, "global_step": 450012, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9545676708221436, "global_step": 450013, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.134962320327759, "global_step": 450014, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0574662685394287, "global_step": 450015, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.106393337249756, "global_step": 450016, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0198469161987305, "global_step": 450017, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1196320056915283, "global_step": 450018, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1180331707000732, "global_step": 450019, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0653953552246094, "global_step": 450020, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1251420974731445, "global_step": 450021, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.053914785385132, "global_step": 450022, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.06134033203125, "global_step": 450023, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0921967029571533, "global_step": 450024, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0573160648345947, "global_step": 450025, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0876331329345703, "global_step": 450026, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0996623039245605, "global_step": 450027, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9665619134902954, "global_step": 450028, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9784133434295654, "global_step": 450029, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1130313873291016, "global_step": 450030, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0034477710723877, "global_step": 450031, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.059485673904419, "global_step": 450032, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.22039532661438, "global_step": 450033, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0133471488952637, "global_step": 450034, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.160468339920044, "global_step": 450035, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.071329355239868, "global_step": 450036, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.111448049545288, "global_step": 450037, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.091088056564331, "global_step": 450038, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.99647855758667, "global_step": 450039, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0092568397521973, "global_step": 450040, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0399014949798584, "global_step": 450041, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0931174755096436, "global_step": 450042, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.011852741241455, "global_step": 450043, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0784857273101807, "global_step": 450044, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.090893268585205, "global_step": 450045, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.053027391433716, "global_step": 450046, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9881864786148071, "global_step": 450047, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.067829132080078, "global_step": 450048, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9975618124008179, "global_step": 450049, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.107487440109253, "global_step": 450050, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0459036827087402, "global_step": 450051, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.052361249923706, "global_step": 450052, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.066972494125366, "global_step": 450053, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.133901357650757, "global_step": 450054, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.002578020095825, "global_step": 450055, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0541160106658936, "global_step": 450056, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0221993923187256, "global_step": 450057, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.066114664077759, "global_step": 450058, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.096888303756714, "global_step": 450059, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1282293796539307, "global_step": 450060, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.081533670425415, "global_step": 450061, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0403480529785156, "global_step": 450062, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.022411346435547, "global_step": 450063, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.047105073928833, "global_step": 450064, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.073864698410034, "global_step": 450065, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0443365573883057, "global_step": 450066, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.111583948135376, "global_step": 450067, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0228171348571777, "global_step": 450068, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.097209930419922, "global_step": 450069, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.064260959625244, "global_step": 450070, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0307960510253906, "global_step": 450071, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.093322515487671, "global_step": 450072, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.118204355239868, "global_step": 450073, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1606030464172363, "global_step": 450074, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0159499645233154, "global_step": 450075, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.050520420074463, "global_step": 450076, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.111549139022827, "global_step": 450077, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0579850673675537, "global_step": 450078, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9979095458984375, "global_step": 450079, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.107820987701416, "global_step": 450080, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1003549098968506, "global_step": 450081, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.041254758834839, "global_step": 450082, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1381285190582275, "global_step": 450083, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.033722400665283, "global_step": 450084, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9542464017868042, "global_step": 450085, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.074563503265381, "global_step": 450086, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.14271879196167, "global_step": 450087, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.038410186767578, "global_step": 450088, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.033277988433838, "global_step": 450089, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0613560676574707, "global_step": 450090, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1094181537628174, "global_step": 450091, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0936691761016846, "global_step": 450092, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0121588706970215, "global_step": 450093, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.031229019165039, "global_step": 450094, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0876388549804688, "global_step": 450095, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.030059814453125, "global_step": 450096, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.048222541809082, "global_step": 450097, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1104252338409424, "global_step": 450098, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0509257316589355, "global_step": 450099, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.990816593170166, "global_step": 450100, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0552399158477783, "global_step": 450101, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0772290229797363, "global_step": 450102, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0137429237365723, "global_step": 450103, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0491435527801514, "global_step": 450104, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1067123413085938, "global_step": 450105, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9644557237625122, "global_step": 450106, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0635125637054443, "global_step": 450107, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0346615314483643, "global_step": 450108, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1247174739837646, "global_step": 450109, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0647199153900146, "global_step": 450110, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0951247215270996, "global_step": 450111, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1179616451263428, "global_step": 450112, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.090094566345215, "global_step": 450113, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0565593242645264, "global_step": 450114, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0741055011749268, "global_step": 450115, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0024402141571045, "global_step": 450116, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0291786193847656, "global_step": 450117, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.09831166267395, "global_step": 450118, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.118598461151123, "global_step": 450119, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0346736907958984, "global_step": 450120, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0113253593444824, "global_step": 450121, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1614880561828613, "global_step": 450122, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.100231409072876, "global_step": 450123, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0592634677886963, "global_step": 450124, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.011291742324829, "global_step": 450125, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.13913893699646, "global_step": 450126, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.068833112716675, "global_step": 450127, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1461098194122314, "global_step": 450128, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1117501258850098, "global_step": 450129, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.091519355773926, "global_step": 450130, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0881409645080566, "global_step": 450131, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0727834701538086, "global_step": 450132, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.136716604232788, "global_step": 450133, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0468032360076904, "global_step": 450134, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.09317946434021, "global_step": 450135, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.088135004043579, "global_step": 450136, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0513687133789062, "global_step": 450137, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0520377159118652, "global_step": 450138, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0892860889434814, "global_step": 450139, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.014251947402954, "global_step": 450140, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.172114133834839, "global_step": 450141, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.120610237121582, "global_step": 450142, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0506043434143066, "global_step": 450143, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0963010787963867, "global_step": 450144, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.048600196838379, "global_step": 450145, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.074984550476074, "global_step": 450146, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0591259002685547, "global_step": 450147, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.077246904373169, "global_step": 450148, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.068056583404541, "global_step": 450149, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0981831550598145, "global_step": 450150, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.099734306335449, "global_step": 450151, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0941011905670166, "global_step": 450152, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0940566062927246, "global_step": 450153, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.03409743309021, "global_step": 450154, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1818394660949707, "global_step": 450155, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1013667583465576, "global_step": 450156, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1643528938293457, "global_step": 450157, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1215808391571045, "global_step": 450158, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.053079605102539, "global_step": 450159, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0859105587005615, "global_step": 450160, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0990984439849854, "global_step": 450161, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0468428134918213, "global_step": 450162, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0670969486236572, "global_step": 450163, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.092832326889038, "global_step": 450164, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.092484712600708, "global_step": 450165, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.032367467880249, "global_step": 450166, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.047698497772217, "global_step": 450167, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0327987670898438, "global_step": 450168, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9743151664733887, "global_step": 450169, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.045238494873047, "global_step": 450170, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0913257598876953, "global_step": 450171, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1177074909210205, "global_step": 450172, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.081545829772949, "global_step": 450173, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0227468013763428, "global_step": 450174, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1070265769958496, "global_step": 450175, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1104421615600586, "global_step": 450176, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9861094951629639, "global_step": 450177, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.161649227142334, "global_step": 450178, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0524239540100098, "global_step": 450179, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0959999561309814, "global_step": 450180, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.070871353149414, "global_step": 450181, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0136966705322266, "global_step": 450182, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.105736255645752, "global_step": 450183, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0785915851593018, "global_step": 450184, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.076768636703491, "global_step": 450185, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0599546432495117, "global_step": 450186, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0660037994384766, "global_step": 450187, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.055732250213623, "global_step": 450188, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0822224617004395, "global_step": 450189, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.01766037940979, "global_step": 450190, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.2204172611236572, "global_step": 450191, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1488332748413086, "global_step": 450192, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0278007984161377, "global_step": 450193, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.114154100418091, "global_step": 450194, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0243892669677734, "global_step": 450195, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.049730062484741, "global_step": 450196, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0354275703430176, "global_step": 450197, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0087337493896484, "global_step": 450198, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.097557783126831, "global_step": 450199, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1363978385925293, "global_step": 450200, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1689810752868652, "global_step": 450201, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.020759105682373, "global_step": 450202, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.135211706161499, "global_step": 450203, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1269264221191406, "global_step": 450204, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0933682918548584, "global_step": 450205, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0806820392608643, "global_step": 450206, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.080559730529785, "global_step": 450207, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.044753074645996, "global_step": 450208, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.137629985809326, "global_step": 450209, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0450026988983154, "global_step": 450210, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.028568744659424, "global_step": 450211, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0597500801086426, "global_step": 450212, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.032559394836426, "global_step": 450213, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.001553773880005, "global_step": 450214, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.992567777633667, "global_step": 450215, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0277860164642334, "global_step": 450216, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1626739501953125, "global_step": 450217, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0542824268341064, "global_step": 450218, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0321106910705566, "global_step": 450219, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.108384847640991, "global_step": 450220, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.091783285140991, "global_step": 450221, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.07606840133667, "global_step": 450222, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.031623363494873, "global_step": 450223, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.074256181716919, "global_step": 450224, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.106696605682373, "global_step": 450225, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0184600353240967, "global_step": 450226, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0089614391326904, "global_step": 450227, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.082797050476074, "global_step": 450228, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0104498863220215, "global_step": 450229, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.043065071105957, "global_step": 450230, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1248421669006348, "global_step": 450231, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1557834148406982, "global_step": 450232, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.144423484802246, "global_step": 450233, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.090427875518799, "global_step": 450234, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.114016532897949, "global_step": 450235, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1051597595214844, "global_step": 450236, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1284759044647217, "global_step": 450237, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1467862129211426, "global_step": 450238, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1676435470581055, "global_step": 450239, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0648932456970215, "global_step": 450240, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.100405693054199, "global_step": 450241, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.151750087738037, "global_step": 450242, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.043841600418091, "global_step": 450243, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1064841747283936, "global_step": 450244, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0851378440856934, "global_step": 450245, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.077998399734497, "global_step": 450246, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0308682918548584, "global_step": 450247, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1408939361572266, "global_step": 450248, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9707937240600586, "global_step": 450249, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0650904178619385, "global_step": 450250, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0075554847717285, "global_step": 450251, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.035858154296875, "global_step": 450252, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1761598587036133, "global_step": 450253, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0664236545562744, "global_step": 450254, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1329262256622314, "global_step": 450255, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1103427410125732, "global_step": 450256, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0323286056518555, "global_step": 450257, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.068110227584839, "global_step": 450258, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0091800689697266, "global_step": 450259, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.131843328475952, "global_step": 450260, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0642614364624023, "global_step": 450261, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.092653751373291, "global_step": 450262, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.036909580230713, "global_step": 450263, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.966752529144287, "global_step": 450264, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.2101054191589355, "global_step": 450265, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.012899875640869, "global_step": 450266, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.145150661468506, "global_step": 450267, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.124742269515991, "global_step": 450268, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0416669845581055, "global_step": 450269, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1719727516174316, "global_step": 450270, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.108327865600586, "global_step": 450271, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.095113515853882, "global_step": 450272, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0054614543914795, "global_step": 450273, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0535333156585693, "global_step": 450274, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.048757314682007, "global_step": 450275, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1268787384033203, "global_step": 450276, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0849690437316895, "global_step": 450277, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0955355167388916, "global_step": 450278, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0599021911621094, "global_step": 450279, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1220624446868896, "global_step": 450280, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.042299747467041, "global_step": 450281, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9973546266555786, "global_step": 450282, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.065897226333618, "global_step": 450283, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.011258363723755, "global_step": 450284, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.083655595779419, "global_step": 450285, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0179805755615234, "global_step": 450286, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1039047241210938, "global_step": 450287, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.067229747772217, "global_step": 450288, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.074856996536255, "global_step": 450289, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1335344314575195, "global_step": 450290, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9778478145599365, "global_step": 450291, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0904459953308105, "global_step": 450292, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.024216413497925, "global_step": 450293, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0844130516052246, "global_step": 450294, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1062309741973877, "global_step": 450295, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0433974266052246, "global_step": 450296, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.050793409347534, "global_step": 450297, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0686612129211426, "global_step": 450298, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.095827341079712, "global_step": 450299, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.106645345687866, "global_step": 450300, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0701088905334473, "global_step": 450301, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1129703521728516, "global_step": 450302, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1051933765411377, "global_step": 450303, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.062668800354004, "global_step": 450304, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1532814502716064, "global_step": 450305, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0302538871765137, "global_step": 450306, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.989587664604187, "global_step": 450307, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.03483247756958, "global_step": 450308, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.059905767440796, "global_step": 450309, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.122246503829956, "global_step": 450310, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1287450790405273, "global_step": 450311, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0238590240478516, "global_step": 450312, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.122473955154419, "global_step": 450313, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9689736366271973, "global_step": 450314, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0474483966827393, "global_step": 450315, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.076625347137451, "global_step": 450316, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.074336528778076, "global_step": 450317, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1131534576416016, "global_step": 450318, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.082524538040161, "global_step": 450319, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0673344135284424, "global_step": 450320, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0273122787475586, "global_step": 450321, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9787873029708862, "global_step": 450322, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0428006649017334, "global_step": 450323, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.163910150527954, "global_step": 450324, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.087961196899414, "global_step": 450325, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.053640842437744, "global_step": 450326, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0121068954467773, "global_step": 450327, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1009135246276855, "global_step": 450328, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1092939376831055, "global_step": 450329, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1108601093292236, "global_step": 450330, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.037236213684082, "global_step": 450331, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.113229990005493, "global_step": 450332, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.088130474090576, "global_step": 450333, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.06229829788208, "global_step": 450334, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.089452028274536, "global_step": 450335, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1524906158447266, "global_step": 450336, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0889158248901367, "global_step": 450337, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0512301921844482, "global_step": 450338, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0283024311065674, "global_step": 450339, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.05411434173584, "global_step": 450340, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.074458122253418, "global_step": 450341, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0526795387268066, "global_step": 450342, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.144702911376953, "global_step": 450343, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.103869915008545, "global_step": 450344, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0549583435058594, "global_step": 450345, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.113741159439087, "global_step": 450346, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.124034881591797, "global_step": 450347, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1693780422210693, "global_step": 450348, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.117380142211914, "global_step": 450349, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0940427780151367, "global_step": 450350, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.07027530670166, "global_step": 450351, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0269923210144043, "global_step": 450352, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9900835752487183, "global_step": 450353, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9890295267105103, "global_step": 450354, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.085069417953491, "global_step": 450355, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0395452976226807, "global_step": 450356, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1359615325927734, "global_step": 450357, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.024745464324951, "global_step": 450358, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1100471019744873, "global_step": 450359, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.102827310562134, "global_step": 450360, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0845322608947754, "global_step": 450361, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.126319646835327, "global_step": 450362, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.12488055229187, "global_step": 450363, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.101534843444824, "global_step": 450364, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1288139820098877, "global_step": 450365, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.111295223236084, "global_step": 450366, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.081397771835327, "global_step": 450367, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1145193576812744, "global_step": 450368, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0548439025878906, "global_step": 450369, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.038212299346924, "global_step": 450370, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0657596588134766, "global_step": 450371, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0194668769836426, "global_step": 450372, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0025863647460938, "global_step": 450373, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.044736623764038, "global_step": 450374, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0395545959472656, "global_step": 450375, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.054405689239502, "global_step": 450376, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.166259765625, "global_step": 450377, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1447596549987793, "global_step": 450378, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0617592334747314, "global_step": 450379, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0070960521698, "global_step": 450380, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.187824249267578, "global_step": 450381, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.030505657196045, "global_step": 450382, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0584452152252197, "global_step": 450383, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0942628383636475, "global_step": 450384, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.081568479537964, "global_step": 450385, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0516722202301025, "global_step": 450386, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.102898597717285, "global_step": 450387, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0592315196990967, "global_step": 450388, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.02944016456604, "global_step": 450389, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.970961332321167, "global_step": 450390, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0779061317443848, "global_step": 450391, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.037498712539673, "global_step": 450392, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.078062057495117, "global_step": 450393, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.067399024963379, "global_step": 450394, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0608489513397217, "global_step": 450395, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0894155502319336, "global_step": 450396, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.111239194869995, "global_step": 450397, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1459548473358154, "global_step": 450398, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0571281909942627, "global_step": 450399, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1021621227264404, "global_step": 450400, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.114680528640747, "global_step": 450401, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0205745697021484, "global_step": 450402, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.142890691757202, "global_step": 450403, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.120046615600586, "global_step": 450404, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1568446159362793, "global_step": 450405, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1029930114746094, "global_step": 450406, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.029615640640259, "global_step": 450407, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1150665283203125, "global_step": 450408, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0544183254241943, "global_step": 450409, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0364558696746826, "global_step": 450410, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0498907566070557, "global_step": 450411, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1456615924835205, "global_step": 450412, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.201961040496826, "global_step": 450413, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0998151302337646, "global_step": 450414, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9972505569458008, "global_step": 450415, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0523841381073, "global_step": 450416, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.10638427734375, "global_step": 450417, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9346007108688354, "global_step": 450418, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0471367835998535, "global_step": 450419, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.075998306274414, "global_step": 450420, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0518388748168945, "global_step": 450421, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.039618968963623, "global_step": 450422, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0353333950042725, "global_step": 450423, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.038813591003418, "global_step": 450424, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0344550609588623, "global_step": 450425, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.172089099884033, "global_step": 450426, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.049950122833252, "global_step": 450427, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0701773166656494, "global_step": 450428, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.040045976638794, "global_step": 450429, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0612142086029053, "global_step": 450430, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0890040397644043, "global_step": 450431, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0266611576080322, "global_step": 450432, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.035672903060913, "global_step": 450433, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0483901500701904, "global_step": 450434, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.038764238357544, "global_step": 450435, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9891959428787231, "global_step": 450436, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0255470275878906, "global_step": 450437, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.147019386291504, "global_step": 450438, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0288758277893066, "global_step": 450439, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.084819793701172, "global_step": 450440, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1140594482421875, "global_step": 450441, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0562267303466797, "global_step": 450442, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.136941432952881, "global_step": 450443, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0688724517822266, "global_step": 450444, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0614795684814453, "global_step": 450445, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.173051118850708, "global_step": 450446, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0030853748321533, "global_step": 450447, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0234992504119873, "global_step": 450448, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0400049686431885, "global_step": 450449, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9498835802078247, "global_step": 450450, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1358799934387207, "global_step": 450451, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.145068883895874, "global_step": 450452, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.090489387512207, "global_step": 450453, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0690293312072754, "global_step": 450454, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.00620174407959, "global_step": 450455, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.137242078781128, "global_step": 450456, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0225231647491455, "global_step": 450457, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0392825603485107, "global_step": 450458, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.141937494277954, "global_step": 450459, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.043513059616089, "global_step": 450460, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.046311140060425, "global_step": 450461, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0286452770233154, "global_step": 450462, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9863940477371216, "global_step": 450463, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.059238910675049, "global_step": 450464, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1168179512023926, "global_step": 450465, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.048905372619629, "global_step": 450466, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9926869869232178, "global_step": 450467, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.2103521823883057, "global_step": 450468, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1396472454071045, "global_step": 450469, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0591883659362793, "global_step": 450470, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.093984365463257, "global_step": 450471, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1429812908172607, "global_step": 450472, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1068522930145264, "global_step": 450473, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.102102518081665, "global_step": 450474, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.091275453567505, "global_step": 450475, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.078343629837036, "global_step": 450476, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.117133140563965, "global_step": 450477, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.042289972305298, "global_step": 450478, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.007899045944214, "global_step": 450479, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1064672470092773, "global_step": 450480, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0914437770843506, "global_step": 450481, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1478075981140137, "global_step": 450482, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.111402988433838, "global_step": 450483, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.093681812286377, "global_step": 450484, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1123430728912354, "global_step": 450485, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.008389711380005, "global_step": 450486, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.019922971725464, "global_step": 450487, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0278220176696777, "global_step": 450488, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0603246688842773, "global_step": 450489, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0323710441589355, "global_step": 450490, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0438358783721924, "global_step": 450491, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1477842330932617, "global_step": 450492, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1497082710266113, "global_step": 450493, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.123077630996704, "global_step": 450494, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0089645385742188, "global_step": 450495, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.046869993209839, "global_step": 450496, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0960731506347656, "global_step": 450497, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0894129276275635, "global_step": 450498, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.071317672729492, "global_step": 450499, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.134652614593506, "global_step": 450500, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.130913496017456, "global_step": 450501, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0921754837036133, "global_step": 450502, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.097130537033081, "global_step": 450503, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.049347162246704, "global_step": 450504, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1258938312530518, "global_step": 450505, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1299142837524414, "global_step": 450506, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1381821632385254, "global_step": 450507, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.066314935684204, "global_step": 450508, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1690170764923096, "global_step": 450509, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9922010898590088, "global_step": 450510, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.130706787109375, "global_step": 450511, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0470333099365234, "global_step": 450512, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.050022840499878, "global_step": 450513, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.085602283477783, "global_step": 450514, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0548973083496094, "global_step": 450515, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0696940422058105, "global_step": 450516, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1622464656829834, "global_step": 450517, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0333194732666016, "global_step": 450518, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.115704298019409, "global_step": 450519, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.129667043685913, "global_step": 450520, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.04542875289917, "global_step": 450521, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0113229751586914, "global_step": 450522, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.113656759262085, "global_step": 450523, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.063856363296509, "global_step": 450524, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0673866271972656, "global_step": 450525, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1208713054656982, "global_step": 450526, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1609108448028564, "global_step": 450527, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.05976939201355, "global_step": 450528, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1208856105804443, "global_step": 450529, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0966908931732178, "global_step": 450530, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.025798797607422, "global_step": 450531, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.091785192489624, "global_step": 450532, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0946478843688965, "global_step": 450533, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0649263858795166, "global_step": 450534, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1639795303344727, "global_step": 450535, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.198061943054199, "global_step": 450536, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.136967658996582, "global_step": 450537, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.053725481033325, "global_step": 450538, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.028785228729248, "global_step": 450539, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.067401885986328, "global_step": 450540, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.085801362991333, "global_step": 450541, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.044213056564331, "global_step": 450542, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1133503913879395, "global_step": 450543, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.123525381088257, "global_step": 450544, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.10996150970459, "global_step": 450545, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.04776930809021, "global_step": 450546, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.03493595123291, "global_step": 450547, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.075556516647339, "global_step": 450548, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1205732822418213, "global_step": 450549, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0596187114715576, "global_step": 450550, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0845534801483154, "global_step": 450551, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.037936210632324, "global_step": 450552, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1353490352630615, "global_step": 450553, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.117389678955078, "global_step": 450554, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0908267498016357, "global_step": 450555, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.108790397644043, "global_step": 450556, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1568121910095215, "global_step": 450557, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0986130237579346, "global_step": 450558, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.013988971710205, "global_step": 450559, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0624282360076904, "global_step": 450560, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0930800437927246, "global_step": 450561, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1240339279174805, "global_step": 450562, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0413756370544434, "global_step": 450563, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0526726245880127, "global_step": 450564, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.06304931640625, "global_step": 450565, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0592446327209473, "global_step": 450566, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0239670276641846, "global_step": 450567, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1808531284332275, "global_step": 450568, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0674638748168945, "global_step": 450569, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0607950687408447, "global_step": 450570, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1118433475494385, "global_step": 450571, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.146836280822754, "global_step": 450572, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0682106018066406, "global_step": 450573, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0820260047912598, "global_step": 450574, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.114267587661743, "global_step": 450575, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0469918251037598, "global_step": 450576, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.140289783477783, "global_step": 450577, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1009397506713867, "global_step": 450578, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.096313953399658, "global_step": 450579, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0349156856536865, "global_step": 450580, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1340792179107666, "global_step": 450581, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0401079654693604, "global_step": 450582, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0801050662994385, "global_step": 450583, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.09942364692688, "global_step": 450584, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.172556161880493, "global_step": 450585, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0361695289611816, "global_step": 450586, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.080820083618164, "global_step": 450587, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0733022689819336, "global_step": 450588, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1125667095184326, "global_step": 450589, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.051567316055298, "global_step": 450590, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.186767339706421, "global_step": 450591, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.054448127746582, "global_step": 450592, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.115548610687256, "global_step": 450593, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0258219242095947, "global_step": 450594, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.135981559753418, "global_step": 450595, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0780704021453857, "global_step": 450596, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0433132648468018, "global_step": 450597, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0577445030212402, "global_step": 450598, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0275895595550537, "global_step": 450599, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0605437755584717, "global_step": 450600, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9979426860809326, "global_step": 450601, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1364402770996094, "global_step": 450602, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.045626640319824, "global_step": 450603, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1656012535095215, "global_step": 450604, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0430569648742676, "global_step": 450605, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.056912660598755, "global_step": 450606, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0547823905944824, "global_step": 450607, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0278873443603516, "global_step": 450608, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1029019355773926, "global_step": 450609, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1116254329681396, "global_step": 450610, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.117621421813965, "global_step": 450611, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0760252475738525, "global_step": 450612, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0924785137176514, "global_step": 450613, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0156962871551514, "global_step": 450614, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1317105293273926, "global_step": 450615, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0628063678741455, "global_step": 450616, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0999181270599365, "global_step": 450617, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.088945150375366, "global_step": 450618, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1040945053100586, "global_step": 450619, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0769760608673096, "global_step": 450620, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.090698480606079, "global_step": 450621, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.046233654022217, "global_step": 450622, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0246074199676514, "global_step": 450623, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0090062618255615, "global_step": 450624, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.082339286804199, "global_step": 450625, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0570902824401855, "global_step": 450626, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.020667791366577, "global_step": 450627, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0724756717681885, "global_step": 450628, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1372272968292236, "global_step": 450629, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0225472450256348, "global_step": 450630, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.085437297821045, "global_step": 450631, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.132385730743408, "global_step": 450632, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1438558101654053, "global_step": 450633, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.001037836074829, "global_step": 450634, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.227436065673828, "global_step": 450635, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.024472951889038, "global_step": 450636, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1495189666748047, "global_step": 450637, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0787556171417236, "global_step": 450638, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0647525787353516, "global_step": 450639, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1479296684265137, "global_step": 450640, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0418710708618164, "global_step": 450641, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.05269455909729, "global_step": 450642, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.104339838027954, "global_step": 450643, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1865994930267334, "global_step": 450644, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1101365089416504, "global_step": 450645, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1627209186553955, "global_step": 450646, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.125304698944092, "global_step": 450647, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1056716442108154, "global_step": 450648, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0263419151306152, "global_step": 450649, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0460832118988037, "global_step": 450650, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.131938934326172, "global_step": 450651, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1234068870544434, "global_step": 450652, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9860832691192627, "global_step": 450653, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.082956552505493, "global_step": 450654, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.057522773742676, "global_step": 450655, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0492959022521973, "global_step": 450656, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0850634574890137, "global_step": 450657, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0325276851654053, "global_step": 450658, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0744495391845703, "global_step": 450659, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.089092254638672, "global_step": 450660, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0633621215820312, "global_step": 450661, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1290323734283447, "global_step": 450662, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0389244556427, "global_step": 450663, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0970094203948975, "global_step": 450664, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0067684650421143, "global_step": 450665, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0342230796813965, "global_step": 450666, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1284420490264893, "global_step": 450667, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.142632007598877, "global_step": 450668, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.073148488998413, "global_step": 450669, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0235354900360107, "global_step": 450670, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.081235885620117, "global_step": 450671, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.094165325164795, "global_step": 450672, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.076364755630493, "global_step": 450673, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0253024101257324, "global_step": 450674, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0161895751953125, "global_step": 450675, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.12572979927063, "global_step": 450676, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0130343437194824, "global_step": 450677, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0679612159729004, "global_step": 450678, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.020552635192871, "global_step": 450679, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.08665132522583, "global_step": 450680, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0304341316223145, "global_step": 450681, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.103940010070801, "global_step": 450682, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1284210681915283, "global_step": 450683, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1450765132904053, "global_step": 450684, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0589520931243896, "global_step": 450685, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.058319568634033, "global_step": 450686, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.217745780944824, "global_step": 450687, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0483639240264893, "global_step": 450688, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9885951280593872, "global_step": 450689, "epoch": 814, "lr": 5e-05}
{"train_loss": 1.9901978969573975, "global_step": 450690, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0425257682800293, "global_step": 450691, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.065640687942505, "global_step": 450692, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0716981887817383, "global_step": 450693, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1013123989105225, "global_step": 450694, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.090470314025879, "global_step": 450695, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.037578582763672, "global_step": 450696, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.144012451171875, "global_step": 450697, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.001361846923828, "global_step": 450698, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.110269069671631, "global_step": 450699, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.037987232208252, "global_step": 450700, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.143808603286743, "global_step": 450701, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1540749073028564, "global_step": 450702, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0853915214538574, "global_step": 450703, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0484800338745117, "global_step": 450704, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.1128005981445312, "global_step": 450705, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0307319164276123, "global_step": 450706, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.068897247314453, "global_step": 450707, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.104074001312256, "global_step": 450708, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0382392406463623, "global_step": 450709, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.134967803955078, "global_step": 450710, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0632083415985107, "global_step": 450711, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0511634349823, "global_step": 450712, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.085728645324707, "global_step": 450713, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0562736988067627, "global_step": 450714, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.044600009918213, "global_step": 450715, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0955331325531006, "global_step": 450716, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0730273723602295, "global_step": 450717, "epoch": 814, "lr": 5e-05}
{"train_loss": 2.0907680988311768, "global_step": 450718, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9992672204971313, "global_step": 450719, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0638821125030518, "global_step": 450720, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0531039237976074, "global_step": 450721, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0632810592651367, "global_step": 450722, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0646402835845947, "global_step": 450723, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0772793292999268, "global_step": 450724, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9742035865783691, "global_step": 450725, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.08980393409729, "global_step": 450726, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0560238361358643, "global_step": 450727, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0773298740386963, "global_step": 450728, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.077601432800293, "global_step": 450729, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.060964584350586, "global_step": 450730, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0594918727874756, "global_step": 450731, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9788225889205933, "global_step": 450732, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1291298866271973, "global_step": 450733, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0194091796875, "global_step": 450734, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1495985984802246, "global_step": 450735, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.045079231262207, "global_step": 450736, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.998857855796814, "global_step": 450737, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.057375431060791, "global_step": 450738, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.02522873878479, "global_step": 450739, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.10002064704895, "global_step": 450740, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0506768226623535, "global_step": 450741, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0376758575439453, "global_step": 450742, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0382368564605713, "global_step": 450743, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0106375217437744, "global_step": 450744, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0018107891082764, "global_step": 450745, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1718082427978516, "global_step": 450746, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1149566173553467, "global_step": 450747, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9495373964309692, "global_step": 450748, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.07858943939209, "global_step": 450749, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.049184560775757, "global_step": 450750, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.043286085128784, "global_step": 450751, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.047311544418335, "global_step": 450752, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0460124015808105, "global_step": 450753, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0245449542999268, "global_step": 450754, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0520012378692627, "global_step": 450755, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.106204032897949, "global_step": 450756, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0667247772216797, "global_step": 450757, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.100743055343628, "global_step": 450758, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1261982917785645, "global_step": 450759, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.132668972015381, "global_step": 450760, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.062645673751831, "global_step": 450761, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.010857343673706, "global_step": 450762, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.043407917022705, "global_step": 450763, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.084953546524048, "global_step": 450764, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0578818321228027, "global_step": 450765, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0858347415924072, "global_step": 450766, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0681381225585938, "global_step": 450767, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0740561485290527, "global_step": 450768, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0296695232391357, "global_step": 450769, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.997796893119812, "global_step": 450770, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1736621856689453, "global_step": 450771, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.087977409362793, "global_step": 450772, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.122554063796997, "global_step": 450773, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0478944778442383, "global_step": 450774, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.043168306350708, "global_step": 450775, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1105217933654785, "global_step": 450776, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0327718257904053, "global_step": 450777, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0838427543640137, "global_step": 450778, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0663278102874756, "global_step": 450779, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0712618827819824, "global_step": 450780, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.032963752746582, "global_step": 450781, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0257511138916016, "global_step": 450782, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.089970350265503, "global_step": 450783, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.069404125213623, "global_step": 450784, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.005983352661133, "global_step": 450785, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0825769901275635, "global_step": 450786, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.050360918045044, "global_step": 450787, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.013770341873169, "global_step": 450788, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.01078724861145, "global_step": 450789, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1327004432678223, "global_step": 450790, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0705482959747314, "global_step": 450791, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.066415309906006, "global_step": 450792, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.18231463432312, "global_step": 450793, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0164237022399902, "global_step": 450794, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9937629699707031, "global_step": 450795, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.191683292388916, "global_step": 450796, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0298452377319336, "global_step": 450797, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0354273319244385, "global_step": 450798, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0322906970977783, "global_step": 450799, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.055863380432129, "global_step": 450800, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.113086700439453, "global_step": 450801, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9975942373275757, "global_step": 450802, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.081312894821167, "global_step": 450803, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0689337253570557, "global_step": 450804, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0661423206329346, "global_step": 450805, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0532732009887695, "global_step": 450806, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0709304809570312, "global_step": 450807, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0892441272735596, "global_step": 450808, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9861350059509277, "global_step": 450809, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0764591693878174, "global_step": 450810, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9893747568130493, "global_step": 450811, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0391929149627686, "global_step": 450812, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0928285121917725, "global_step": 450813, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0979228019714355, "global_step": 450814, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.000041961669922, "global_step": 450815, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.059717893600464, "global_step": 450816, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9942452907562256, "global_step": 450817, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0552966594696045, "global_step": 450818, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0359718799591064, "global_step": 450819, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.044011354446411, "global_step": 450820, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.080066442489624, "global_step": 450821, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1319711208343506, "global_step": 450822, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1007707118988037, "global_step": 450823, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.110590934753418, "global_step": 450824, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0159881114959717, "global_step": 450825, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1487932205200195, "global_step": 450826, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0096590518951416, "global_step": 450827, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9769388437271118, "global_step": 450828, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1068356037139893, "global_step": 450829, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0342681407928467, "global_step": 450830, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.121371269226074, "global_step": 450831, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0841662883758545, "global_step": 450832, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9787852764129639, "global_step": 450833, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.032622814178467, "global_step": 450834, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.050513744354248, "global_step": 450835, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.128084182739258, "global_step": 450836, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0682458877563477, "global_step": 450837, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0356359481811523, "global_step": 450838, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.039064407348633, "global_step": 450839, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.044487476348877, "global_step": 450840, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0691449642181396, "global_step": 450841, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.008877992630005, "global_step": 450842, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1194498538970947, "global_step": 450843, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.107400894165039, "global_step": 450844, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.039776563644409, "global_step": 450845, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.042271614074707, "global_step": 450846, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1003775596618652, "global_step": 450847, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.13850736618042, "global_step": 450848, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0829761028289795, "global_step": 450849, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1032097339630127, "global_step": 450850, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1015114784240723, "global_step": 450851, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0438952445983887, "global_step": 450852, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0136358737945557, "global_step": 450853, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0595600605010986, "global_step": 450854, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0797626972198486, "global_step": 450855, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.086214303970337, "global_step": 450856, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0891363620758057, "global_step": 450857, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.045450210571289, "global_step": 450858, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.071786642074585, "global_step": 450859, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.05647611618042, "global_step": 450860, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.025736093521118, "global_step": 450861, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1184444427490234, "global_step": 450862, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.075819492340088, "global_step": 450863, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.020901918411255, "global_step": 450864, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1529548168182373, "global_step": 450865, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.16324782371521, "global_step": 450866, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0884063243865967, "global_step": 450867, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9821231365203857, "global_step": 450868, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.071028470993042, "global_step": 450869, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0524685382843018, "global_step": 450870, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0238566398620605, "global_step": 450871, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1193997859954834, "global_step": 450872, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.000974416732788, "global_step": 450873, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.117356300354004, "global_step": 450874, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.022824287414551, "global_step": 450875, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.058694362640381, "global_step": 450876, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.100836753845215, "global_step": 450877, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0590901374816895, "global_step": 450878, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.104762315750122, "global_step": 450879, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0216870307922363, "global_step": 450880, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.994944453239441, "global_step": 450881, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9751205444335938, "global_step": 450882, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0433239936828613, "global_step": 450883, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1168551445007324, "global_step": 450884, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9742882251739502, "global_step": 450885, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0656065940856934, "global_step": 450886, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1413068771362305, "global_step": 450887, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1011528968811035, "global_step": 450888, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0106470584869385, "global_step": 450889, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0107076168060303, "global_step": 450890, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0561227798461914, "global_step": 450891, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.107509136199951, "global_step": 450892, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0907163619995117, "global_step": 450893, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.127701759338379, "global_step": 450894, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0444753170013428, "global_step": 450895, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.133901596069336, "global_step": 450896, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1305999755859375, "global_step": 450897, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.192624568939209, "global_step": 450898, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0823473930358887, "global_step": 450899, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.966576099395752, "global_step": 450900, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0610573291778564, "global_step": 450901, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1055381298065186, "global_step": 450902, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.025424003601074, "global_step": 450903, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.122133493423462, "global_step": 450904, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0803465843200684, "global_step": 450905, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.033087968826294, "global_step": 450906, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0278735160827637, "global_step": 450907, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0496137142181396, "global_step": 450908, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0822548866271973, "global_step": 450909, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1760687828063965, "global_step": 450910, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0729901790618896, "global_step": 450911, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0549333095550537, "global_step": 450912, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.116985559463501, "global_step": 450913, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.042985677719116, "global_step": 450914, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0371150970458984, "global_step": 450915, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0937020778656006, "global_step": 450916, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.125657558441162, "global_step": 450917, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.123659610748291, "global_step": 450918, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0423028469085693, "global_step": 450919, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.068458318710327, "global_step": 450920, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0684733390808105, "global_step": 450921, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.088196277618408, "global_step": 450922, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.967413067817688, "global_step": 450923, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.040510892868042, "global_step": 450924, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.042562484741211, "global_step": 450925, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1335513591766357, "global_step": 450926, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.079625129699707, "global_step": 450927, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0559604167938232, "global_step": 450928, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0498037338256836, "global_step": 450929, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.091097831726074, "global_step": 450930, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9856654405593872, "global_step": 450931, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0570900440216064, "global_step": 450932, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.025022268295288, "global_step": 450933, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0775985717773438, "global_step": 450934, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.051084518432617, "global_step": 450935, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1184165477752686, "global_step": 450936, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1494860649108887, "global_step": 450937, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.075207233428955, "global_step": 450938, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1236281394958496, "global_step": 450939, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.139134407043457, "global_step": 450940, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0874319076538086, "global_step": 450941, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0335118770599365, "global_step": 450942, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.012671709060669, "global_step": 450943, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.072392463684082, "global_step": 450944, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1018214225769043, "global_step": 450945, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.009923219680786, "global_step": 450946, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0788700580596924, "global_step": 450947, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.007430076599121, "global_step": 450948, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0328993797302246, "global_step": 450949, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9958840608596802, "global_step": 450950, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0637927055358887, "global_step": 450951, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0593864917755127, "global_step": 450952, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1041219234466553, "global_step": 450953, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0379598140716553, "global_step": 450954, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.079796314239502, "global_step": 450955, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.193446159362793, "global_step": 450956, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0641283988952637, "global_step": 450957, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0159106254577637, "global_step": 450958, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.065532684326172, "global_step": 450959, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.162531852722168, "global_step": 450960, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.041215181350708, "global_step": 450961, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.052375555038452, "global_step": 450962, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1184256076812744, "global_step": 450963, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.2066617012023926, "global_step": 450964, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0793285369873047, "global_step": 450965, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0403895378112793, "global_step": 450966, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1017353534698486, "global_step": 450967, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.104417085647583, "global_step": 450968, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0383524894714355, "global_step": 450969, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1020915508270264, "global_step": 450970, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.068166971206665, "global_step": 450971, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.157831907272339, "global_step": 450972, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.053025722503662, "global_step": 450973, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.090242624282837, "global_step": 450974, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9925265312194824, "global_step": 450975, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1537485122680664, "global_step": 450976, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.05991530418396, "global_step": 450977, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0829319953918457, "global_step": 450978, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0903351306915283, "global_step": 450979, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1664271354675293, "global_step": 450980, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.020752191543579, "global_step": 450981, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0588672161102295, "global_step": 450982, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.106295585632324, "global_step": 450983, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.095045804977417, "global_step": 450984, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0868027210235596, "global_step": 450985, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1394119262695312, "global_step": 450986, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9854602813720703, "global_step": 450987, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0848450660705566, "global_step": 450988, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.076195478439331, "global_step": 450989, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0579028129577637, "global_step": 450990, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.049043655395508, "global_step": 450991, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0724937915802, "global_step": 450992, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1781485080718994, "global_step": 450993, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.050804853439331, "global_step": 450994, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.112435817718506, "global_step": 450995, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0625710487365723, "global_step": 450996, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1073930263519287, "global_step": 450997, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0446324348449707, "global_step": 450998, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.052381753921509, "global_step": 450999, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.077596426010132, "global_step": 451000, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1364572048187256, "global_step": 451001, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0576300621032715, "global_step": 451002, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.047726631164551, "global_step": 451003, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1771130561828613, "global_step": 451004, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0305755138397217, "global_step": 451005, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0481209754943848, "global_step": 451006, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0599758625030518, "global_step": 451007, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9865648746490479, "global_step": 451008, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.060683012008667, "global_step": 451009, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.119236707687378, "global_step": 451010, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.075390100479126, "global_step": 451011, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1322784423828125, "global_step": 451012, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.139883279800415, "global_step": 451013, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.154834747314453, "global_step": 451014, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1055126190185547, "global_step": 451015, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.043515205383301, "global_step": 451016, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0783889293670654, "global_step": 451017, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.195157766342163, "global_step": 451018, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.133002996444702, "global_step": 451019, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.055281639099121, "global_step": 451020, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.106937885284424, "global_step": 451021, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.075593948364258, "global_step": 451022, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.091846227645874, "global_step": 451023, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.166321277618408, "global_step": 451024, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0175795555114746, "global_step": 451025, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0876190662384033, "global_step": 451026, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.054861307144165, "global_step": 451027, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0463616847991943, "global_step": 451028, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0182344913482666, "global_step": 451029, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1176235675811768, "global_step": 451030, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.023500442504883, "global_step": 451031, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0974795818328857, "global_step": 451032, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.096475839614868, "global_step": 451033, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0462253093719482, "global_step": 451034, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.095761775970459, "global_step": 451035, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1028034687042236, "global_step": 451036, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0772809982299805, "global_step": 451037, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.158994674682617, "global_step": 451038, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0972423553466797, "global_step": 451039, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0817770957946777, "global_step": 451040, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0215132236480713, "global_step": 451041, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0607857704162598, "global_step": 451042, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.015690326690674, "global_step": 451043, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.081094741821289, "global_step": 451044, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.944257378578186, "global_step": 451045, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0385196208953857, "global_step": 451046, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0427138805389404, "global_step": 451047, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.045593500137329, "global_step": 451048, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0413706302642822, "global_step": 451049, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1066653728485107, "global_step": 451050, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0802862644195557, "global_step": 451051, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1399123668670654, "global_step": 451052, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9838670492172241, "global_step": 451053, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0710086822509766, "global_step": 451054, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.094175338745117, "global_step": 451055, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.096163511276245, "global_step": 451056, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.114096164703369, "global_step": 451057, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0402636528015137, "global_step": 451058, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0058393478393555, "global_step": 451059, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0706045627593994, "global_step": 451060, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.993620753288269, "global_step": 451061, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.2096621990203857, "global_step": 451062, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0698461532592773, "global_step": 451063, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0465681552886963, "global_step": 451064, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0915818214416504, "global_step": 451065, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.980043888092041, "global_step": 451066, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1659655570983887, "global_step": 451067, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0684945583343506, "global_step": 451068, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0955417156219482, "global_step": 451069, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.179617166519165, "global_step": 451070, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0326547622680664, "global_step": 451071, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.088495969772339, "global_step": 451072, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9581995010375977, "global_step": 451073, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.057607412338257, "global_step": 451074, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9365711212158203, "global_step": 451075, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9833797216415405, "global_step": 451076, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.106738567352295, "global_step": 451077, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.088740110397339, "global_step": 451078, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.008794069290161, "global_step": 451079, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9663593769073486, "global_step": 451080, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.089996576309204, "global_step": 451081, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.014307975769043, "global_step": 451082, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9910413026809692, "global_step": 451083, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0403902530670166, "global_step": 451084, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.033942222595215, "global_step": 451085, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.054152488708496, "global_step": 451086, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.051804304122925, "global_step": 451087, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0185794830322266, "global_step": 451088, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.044965982437134, "global_step": 451089, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.133312702178955, "global_step": 451090, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0314762592315674, "global_step": 451091, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.061767578125, "global_step": 451092, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.056306838989258, "global_step": 451093, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.114130973815918, "global_step": 451094, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0676681995391846, "global_step": 451095, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0371580123901367, "global_step": 451096, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0449514389038086, "global_step": 451097, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.070633888244629, "global_step": 451098, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1012940406799316, "global_step": 451099, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.032255172729492, "global_step": 451100, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0548689365386963, "global_step": 451101, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0167200565338135, "global_step": 451102, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.075784921646118, "global_step": 451103, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.108839750289917, "global_step": 451104, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1364777088165283, "global_step": 451105, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.039238214492798, "global_step": 451106, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0325279235839844, "global_step": 451107, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0476975440979004, "global_step": 451108, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.102630615234375, "global_step": 451109, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0673069953918457, "global_step": 451110, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.078916311264038, "global_step": 451111, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0953562259674072, "global_step": 451112, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.979695200920105, "global_step": 451113, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.187795400619507, "global_step": 451114, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0705373287200928, "global_step": 451115, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0261728763580322, "global_step": 451116, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1364433765411377, "global_step": 451117, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.114718198776245, "global_step": 451118, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.024174928665161, "global_step": 451119, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.027433395385742, "global_step": 451120, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0178706645965576, "global_step": 451121, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.118741512298584, "global_step": 451122, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.079331398010254, "global_step": 451123, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.083036184310913, "global_step": 451124, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1700422763824463, "global_step": 451125, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0969817638397217, "global_step": 451126, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.106606960296631, "global_step": 451127, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.082224130630493, "global_step": 451128, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.167097330093384, "global_step": 451129, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1063807010650635, "global_step": 451130, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.169635772705078, "global_step": 451131, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.155244827270508, "global_step": 451132, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0889651775360107, "global_step": 451133, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1591286659240723, "global_step": 451134, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1255924701690674, "global_step": 451135, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0634429454803467, "global_step": 451136, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0668883323669434, "global_step": 451137, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.058682918548584, "global_step": 451138, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0582261085510254, "global_step": 451139, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0478532314300537, "global_step": 451140, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0682199001312256, "global_step": 451141, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0667269229888916, "global_step": 451142, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9905555248260498, "global_step": 451143, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0735437870025635, "global_step": 451144, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.143294334411621, "global_step": 451145, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.031050682067871, "global_step": 451146, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.182661771774292, "global_step": 451147, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.119293451309204, "global_step": 451148, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0720505714416504, "global_step": 451149, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.146108388900757, "global_step": 451150, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1083970069885254, "global_step": 451151, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0917649269104004, "global_step": 451152, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.104301691055298, "global_step": 451153, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.09920072555542, "global_step": 451154, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.083787679672241, "global_step": 451155, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1986021995544434, "global_step": 451156, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1153364181518555, "global_step": 451157, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0684914588928223, "global_step": 451158, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.998242974281311, "global_step": 451159, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.06213116645813, "global_step": 451160, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1524722576141357, "global_step": 451161, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1013307571411133, "global_step": 451162, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.127748966217041, "global_step": 451163, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.087472677230835, "global_step": 451164, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.10622239112854, "global_step": 451165, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1408309936523438, "global_step": 451166, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0696799755096436, "global_step": 451167, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9423885345458984, "global_step": 451168, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0831074714660645, "global_step": 451169, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.047227621078491, "global_step": 451170, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0673434734344482, "global_step": 451171, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0875508785247803, "global_step": 451172, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0400564670562744, "global_step": 451173, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1278297901153564, "global_step": 451174, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.053600788116455, "global_step": 451175, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0446081161499023, "global_step": 451176, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.138270378112793, "global_step": 451177, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0635483264923096, "global_step": 451178, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1619210243225098, "global_step": 451179, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.087409734725952, "global_step": 451180, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.096855878829956, "global_step": 451181, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0455069541931152, "global_step": 451182, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0587308406829834, "global_step": 451183, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.090256929397583, "global_step": 451184, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.022686004638672, "global_step": 451185, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.105501651763916, "global_step": 451186, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1155831813812256, "global_step": 451187, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1194376945495605, "global_step": 451188, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.135340929031372, "global_step": 451189, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0883779525756836, "global_step": 451190, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1669259071350098, "global_step": 451191, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.082242488861084, "global_step": 451192, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.041404962539673, "global_step": 451193, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.096876382827759, "global_step": 451194, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0603015422821045, "global_step": 451195, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0801355838775635, "global_step": 451196, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.048867702484131, "global_step": 451197, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.051157236099243, "global_step": 451198, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.103562593460083, "global_step": 451199, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.105809211730957, "global_step": 451200, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0856242179870605, "global_step": 451201, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0382933616638184, "global_step": 451202, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0663952827453613, "global_step": 451203, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0463614463806152, "global_step": 451204, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0835201740264893, "global_step": 451205, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.128962755203247, "global_step": 451206, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.081908702850342, "global_step": 451207, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.135511636734009, "global_step": 451208, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1120197772979736, "global_step": 451209, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0765326023101807, "global_step": 451210, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0552608966827393, "global_step": 451211, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0949606895446777, "global_step": 451212, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0817580223083496, "global_step": 451213, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.009300708770752, "global_step": 451214, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1444754600524902, "global_step": 451215, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.092338800430298, "global_step": 451216, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0397002696990967, "global_step": 451217, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0348875522613525, "global_step": 451218, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0791659355163574, "global_step": 451219, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.122576951980591, "global_step": 451220, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.054189443588257, "global_step": 451221, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0918052196502686, "global_step": 451222, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0592339038848877, "global_step": 451223, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1446926593780518, "global_step": 451224, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.147146701812744, "global_step": 451225, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0435941219329834, "global_step": 451226, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1844191551208496, "global_step": 451227, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0369439125061035, "global_step": 451228, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0856592655181885, "global_step": 451229, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.111253499984741, "global_step": 451230, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0876736640930176, "global_step": 451231, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1370882987976074, "global_step": 451232, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.037632465362549, "global_step": 451233, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.12477970123291, "global_step": 451234, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0554094314575195, "global_step": 451235, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.074589967727661, "global_step": 451236, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1088976860046387, "global_step": 451237, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.084019184112549, "global_step": 451238, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.027472972869873, "global_step": 451239, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.07875394821167, "global_step": 451240, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0476348400115967, "global_step": 451241, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9927103519439697, "global_step": 451242, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9932096004486084, "global_step": 451243, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0253372192382812, "global_step": 451244, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.045933246612549, "global_step": 451245, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1237003803253174, "global_step": 451246, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9926563501358032, "global_step": 451247, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1900744438171387, "global_step": 451248, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1273512840270996, "global_step": 451249, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.040208101272583, "global_step": 451250, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.079158067703247, "global_step": 451251, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0721781253814697, "global_step": 451252, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.092871904373169, "global_step": 451253, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.103109836578369, "global_step": 451254, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.134045124053955, "global_step": 451255, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0111582279205322, "global_step": 451256, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9996627569198608, "global_step": 451257, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0958049297332764, "global_step": 451258, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.032818555831909, "global_step": 451259, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1100640296936035, "global_step": 451260, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0512986183166504, "global_step": 451261, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1006596088409424, "global_step": 451262, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0447497367858887, "global_step": 451263, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9689949750900269, "global_step": 451264, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0775187015533447, "global_step": 451265, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0613393783569336, "global_step": 451266, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.072073221206665, "global_step": 451267, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0716147422790527, "global_step": 451268, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0721514225006104, "global_step": 451269, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1487317085266113, "global_step": 451270, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1330008506774902, "global_step": 451271, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.074467420578003, "global_step": 451272, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1426408290863037, "global_step": 451273, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.072615385055542, "global_step": 451274, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.07301926612854, "global_step": 451275, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.082897901535034, "global_step": 451276, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1355762481689453, "global_step": 451277, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1434175968170166, "global_step": 451278, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.198239803314209, "global_step": 451279, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0528414249420166, "global_step": 451280, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1125361919403076, "global_step": 451281, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0960185527801514, "global_step": 451282, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.023850202560425, "global_step": 451283, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9907641410827637, "global_step": 451284, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.212733030319214, "global_step": 451285, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.111389398574829, "global_step": 451286, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0777692794799805, "global_step": 451287, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.074924945831299, "global_step": 451288, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0596232414245605, "global_step": 451289, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0455589294433594, "global_step": 451290, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.089444160461426, "global_step": 451291, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1577324867248535, "global_step": 451292, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0451500415802, "global_step": 451293, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.06571626663208, "global_step": 451294, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.006362199783325, "global_step": 451295, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1715333461761475, "global_step": 451296, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.031010389328003, "global_step": 451297, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.136228084564209, "global_step": 451298, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0641372203826904, "global_step": 451299, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0523788928985596, "global_step": 451300, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.033052682876587, "global_step": 451301, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9927068948745728, "global_step": 451302, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1143767833709717, "global_step": 451303, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.190004825592041, "global_step": 451304, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0501062870025635, "global_step": 451305, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9782918691635132, "global_step": 451306, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0211243629455566, "global_step": 451307, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.090996742248535, "global_step": 451308, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.064762592315674, "global_step": 451309, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0740902423858643, "global_step": 451310, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.057913303375244, "global_step": 451311, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.081272602081299, "global_step": 451312, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0695037841796875, "global_step": 451313, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0733563899993896, "global_step": 451314, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1154208183288574, "global_step": 451315, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.134265422821045, "global_step": 451316, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1955103874206543, "global_step": 451317, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9952009916305542, "global_step": 451318, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0263750553131104, "global_step": 451319, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.022747755050659, "global_step": 451320, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0425221920013428, "global_step": 451321, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.073652982711792, "global_step": 451322, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0477466583251953, "global_step": 451323, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0107665061950684, "global_step": 451324, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.094205141067505, "global_step": 451325, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.029693841934204, "global_step": 451326, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.122758150100708, "global_step": 451327, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0818848609924316, "global_step": 451328, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0338306427001953, "global_step": 451329, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0902516841888428, "global_step": 451330, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0903172492980957, "global_step": 451331, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0806758403778076, "global_step": 451332, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.054553985595703, "global_step": 451333, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1101560592651367, "global_step": 451334, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0935001373291016, "global_step": 451335, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.210069179534912, "global_step": 451336, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0291666984558105, "global_step": 451337, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0479776859283447, "global_step": 451338, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0188398361206055, "global_step": 451339, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0542285442352295, "global_step": 451340, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0437278747558594, "global_step": 451341, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0769331455230713, "global_step": 451342, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.014742851257324, "global_step": 451343, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9798245429992676, "global_step": 451344, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.062979221343994, "global_step": 451345, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.065704107284546, "global_step": 451346, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.105208396911621, "global_step": 451347, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.032294273376465, "global_step": 451348, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0132222175598145, "global_step": 451349, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1616978645324707, "global_step": 451350, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0811102390289307, "global_step": 451351, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0495810508728027, "global_step": 451352, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0897936820983887, "global_step": 451353, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.10575270652771, "global_step": 451354, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.002725124359131, "global_step": 451355, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.108717679977417, "global_step": 451356, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.053643226623535, "global_step": 451357, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0754263401031494, "global_step": 451358, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1040704250335693, "global_step": 451359, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0225887298583984, "global_step": 451360, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0271897315979004, "global_step": 451361, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.044100522994995, "global_step": 451362, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0515501499176025, "global_step": 451363, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.110523223876953, "global_step": 451364, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.992051124572754, "global_step": 451365, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0954525470733643, "global_step": 451366, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.131221294403076, "global_step": 451367, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1730120182037354, "global_step": 451368, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.059839963912964, "global_step": 451369, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.110013008117676, "global_step": 451370, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9975205659866333, "global_step": 451371, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.073880434036255, "global_step": 451372, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0660898685455322, "global_step": 451373, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.092376470565796, "global_step": 451374, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.187981605529785, "global_step": 451375, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1295251846313477, "global_step": 451376, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.048018455505371, "global_step": 451377, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.04050874710083, "global_step": 451378, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.048461675643921, "global_step": 451379, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9448628425598145, "global_step": 451380, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.069387674331665, "global_step": 451381, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.117036819458008, "global_step": 451382, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0116922855377197, "global_step": 451383, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9915491342544556, "global_step": 451384, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0846455097198486, "global_step": 451385, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0416698455810547, "global_step": 451386, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.153992176055908, "global_step": 451387, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0021374225616455, "global_step": 451388, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0637664794921875, "global_step": 451389, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.091980218887329, "global_step": 451390, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9994105100631714, "global_step": 451391, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.081887722015381, "global_step": 451392, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.065619945526123, "global_step": 451393, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0968523025512695, "global_step": 451394, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.113895893096924, "global_step": 451395, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.124358654022217, "global_step": 451396, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.005343198776245, "global_step": 451397, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0350871086120605, "global_step": 451398, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0635430812835693, "global_step": 451399, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.149498701095581, "global_step": 451400, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9884793758392334, "global_step": 451401, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1463875770568848, "global_step": 451402, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1207547187805176, "global_step": 451403, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.090714693069458, "global_step": 451404, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1378445625305176, "global_step": 451405, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0719244480133057, "global_step": 451406, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.189168930053711, "global_step": 451407, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.059997320175171, "global_step": 451408, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.048785448074341, "global_step": 451409, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.006434917449951, "global_step": 451410, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0906848907470703, "global_step": 451411, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0864298343658447, "global_step": 451412, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.048292398452759, "global_step": 451413, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1323914527893066, "global_step": 451414, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9996106624603271, "global_step": 451415, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1186141967773438, "global_step": 451416, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.022820472717285, "global_step": 451417, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0902607440948486, "global_step": 451418, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0405380725860596, "global_step": 451419, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0821404457092285, "global_step": 451420, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.069091796875, "global_step": 451421, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.042792558670044, "global_step": 451422, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0242486000061035, "global_step": 451423, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0743656158447266, "global_step": 451424, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.103766441345215, "global_step": 451425, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1301329135894775, "global_step": 451426, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.2169454097747803, "global_step": 451427, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1176533699035645, "global_step": 451428, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1233456134796143, "global_step": 451429, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0592846870422363, "global_step": 451430, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0335233211517334, "global_step": 451431, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1160888671875, "global_step": 451432, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1320345401763916, "global_step": 451433, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9625186920166016, "global_step": 451434, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0718955993652344, "global_step": 451435, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1654932498931885, "global_step": 451436, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.069230794906616, "global_step": 451437, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.065884828567505, "global_step": 451438, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.011033773422241, "global_step": 451439, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.056622266769409, "global_step": 451440, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0533814430236816, "global_step": 451441, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0501925945281982, "global_step": 451442, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0502171516418457, "global_step": 451443, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.086799144744873, "global_step": 451444, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.042151927947998, "global_step": 451445, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1379306316375732, "global_step": 451446, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.142122983932495, "global_step": 451447, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0863919258117676, "global_step": 451448, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1412322521209717, "global_step": 451449, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.061168670654297, "global_step": 451450, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.08111834526062, "global_step": 451451, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.081083059310913, "global_step": 451452, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.013442277908325, "global_step": 451453, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1280152797698975, "global_step": 451454, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.081385374069214, "global_step": 451455, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0038561820983887, "global_step": 451456, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.108442544937134, "global_step": 451457, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.158486843109131, "global_step": 451458, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.084503173828125, "global_step": 451459, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0769739151000977, "global_step": 451460, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0941998958587646, "global_step": 451461, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.087501049041748, "global_step": 451462, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.092068910598755, "global_step": 451463, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.087501287460327, "global_step": 451464, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.086644411087036, "global_step": 451465, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0321240425109863, "global_step": 451466, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0617268085479736, "global_step": 451467, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0775272846221924, "global_step": 451468, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0166690349578857, "global_step": 451469, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.071404457092285, "global_step": 451470, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.060943841934204, "global_step": 451471, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0797674655914307, "global_step": 451472, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9264154434204102, "global_step": 451473, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0141375064849854, "global_step": 451474, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0868873596191406, "global_step": 451475, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1058921813964844, "global_step": 451476, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.061258554458618, "global_step": 451477, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0249617099761963, "global_step": 451478, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9838147163391113, "global_step": 451479, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0262227058410645, "global_step": 451480, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.079267978668213, "global_step": 451481, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.128948450088501, "global_step": 451482, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.130664110183716, "global_step": 451483, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1682393550872803, "global_step": 451484, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0037641525268555, "global_step": 451485, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0894222259521484, "global_step": 451486, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1046142578125, "global_step": 451487, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0461058616638184, "global_step": 451488, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.056076765060425, "global_step": 451489, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1672465801239014, "global_step": 451490, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1684491634368896, "global_step": 451491, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.136584520339966, "global_step": 451492, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1471128463745117, "global_step": 451493, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9880561828613281, "global_step": 451494, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0348665714263916, "global_step": 451495, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.042722463607788, "global_step": 451496, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.176426649093628, "global_step": 451497, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.100008010864258, "global_step": 451498, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.117799997329712, "global_step": 451499, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0901565551757812, "global_step": 451500, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0409977436065674, "global_step": 451501, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0813698768615723, "global_step": 451502, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0830271244049072, "global_step": 451503, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.082052707672119, "global_step": 451504, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.183011770248413, "global_step": 451505, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.015441656112671, "global_step": 451506, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.126169443130493, "global_step": 451507, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0902554988861084, "global_step": 451508, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0425615310668945, "global_step": 451509, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.030240297317505, "global_step": 451510, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0154507160186768, "global_step": 451511, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.118065118789673, "global_step": 451512, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0163252353668213, "global_step": 451513, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0926949977874756, "global_step": 451514, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.072512626647949, "global_step": 451515, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0481107234954834, "global_step": 451516, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1019887924194336, "global_step": 451517, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0929644107818604, "global_step": 451518, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0341076850891113, "global_step": 451519, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.030820608139038, "global_step": 451520, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.078745126724243, "global_step": 451521, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1205668449401855, "global_step": 451522, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0081839561462402, "global_step": 451523, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0928428173065186, "global_step": 451524, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.082929849624634, "global_step": 451525, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.061854362487793, "global_step": 451526, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.146883487701416, "global_step": 451527, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.047915458679199, "global_step": 451528, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0663838386535645, "global_step": 451529, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0562126636505127, "global_step": 451530, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.083413600921631, "global_step": 451531, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.047832727432251, "global_step": 451532, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1478514671325684, "global_step": 451533, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1288797855377197, "global_step": 451534, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.089735507965088, "global_step": 451535, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.124889612197876, "global_step": 451536, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0950591564178467, "global_step": 451537, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0957698822021484, "global_step": 451538, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0246732234954834, "global_step": 451539, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0718281269073486, "global_step": 451540, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.116858959197998, "global_step": 451541, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1159534454345703, "global_step": 451542, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.119957685470581, "global_step": 451543, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.942325472831726, "global_step": 451544, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0108485221862793, "global_step": 451545, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.051844358444214, "global_step": 451546, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1031577587127686, "global_step": 451547, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.102062463760376, "global_step": 451548, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.01203989982605, "global_step": 451549, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.093160390853882, "global_step": 451550, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1452507972717285, "global_step": 451551, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0586235523223877, "global_step": 451552, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0184600353240967, "global_step": 451553, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.152350425720215, "global_step": 451554, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1327531337738037, "global_step": 451555, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0816702842712402, "global_step": 451556, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0339536666870117, "global_step": 451557, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.067070960998535, "global_step": 451558, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0989725589752197, "global_step": 451559, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0109376907348633, "global_step": 451560, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1150474548339844, "global_step": 451561, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.00988507270813, "global_step": 451562, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9834951162338257, "global_step": 451563, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.126643180847168, "global_step": 451564, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.20090913772583, "global_step": 451565, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.070981025695801, "global_step": 451566, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0026962757110596, "global_step": 451567, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.078049898147583, "global_step": 451568, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1526007652282715, "global_step": 451569, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.106818199157715, "global_step": 451570, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.078326463699341, "global_step": 451571, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.085649251937866, "global_step": 451572, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0282530784606934, "global_step": 451573, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1141176223754883, "global_step": 451574, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.036379814147949, "global_step": 451575, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1089916229248047, "global_step": 451576, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0679874420166016, "global_step": 451577, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0961577892303467, "global_step": 451578, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.103456974029541, "global_step": 451579, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1239736080169678, "global_step": 451580, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.019979953765869, "global_step": 451581, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.032866954803467, "global_step": 451582, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.128094434738159, "global_step": 451583, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0347681045532227, "global_step": 451584, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0862293243408203, "global_step": 451585, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1388230323791504, "global_step": 451586, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.07080078125, "global_step": 451587, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0372262001037598, "global_step": 451588, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.044956922531128, "global_step": 451589, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.083401918411255, "global_step": 451590, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.098390817642212, "global_step": 451591, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0409700870513916, "global_step": 451592, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9522724151611328, "global_step": 451593, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.086686134338379, "global_step": 451594, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.100280284881592, "global_step": 451595, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0830886363983154, "global_step": 451596, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.03354811668396, "global_step": 451597, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.103073835372925, "global_step": 451598, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.009732484817505, "global_step": 451599, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.022355794906616, "global_step": 451600, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0625202655792236, "global_step": 451601, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1341359615325928, "global_step": 451602, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.951506495475769, "global_step": 451603, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.091139316558838, "global_step": 451604, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0388147830963135, "global_step": 451605, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.054314136505127, "global_step": 451606, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.057807207107544, "global_step": 451607, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.023886203765869, "global_step": 451608, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.103532552719116, "global_step": 451609, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0239923000335693, "global_step": 451610, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0537548065185547, "global_step": 451611, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9713915586471558, "global_step": 451612, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0940518379211426, "global_step": 451613, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9900670051574707, "global_step": 451614, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0238752365112305, "global_step": 451615, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0042331218719482, "global_step": 451616, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1030328273773193, "global_step": 451617, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1740899085998535, "global_step": 451618, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.025538921356201, "global_step": 451619, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1092727184295654, "global_step": 451620, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.175118923187256, "global_step": 451621, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1107075214385986, "global_step": 451622, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0903146266937256, "global_step": 451623, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.100919485092163, "global_step": 451624, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.036409378051758, "global_step": 451625, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0999999046325684, "global_step": 451626, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0423505306243896, "global_step": 451627, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0846967697143555, "global_step": 451628, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1755034923553467, "global_step": 451629, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.168733596801758, "global_step": 451630, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.086090564727783, "global_step": 451631, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.118466854095459, "global_step": 451632, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1527504920959473, "global_step": 451633, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1566286087036133, "global_step": 451634, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0285513401031494, "global_step": 451635, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.137474775314331, "global_step": 451636, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.024632453918457, "global_step": 451637, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1255130767822266, "global_step": 451638, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0851733684539795, "global_step": 451639, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1353516578674316, "global_step": 451640, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1271204948425293, "global_step": 451641, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.089787483215332, "global_step": 451642, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1394805908203125, "global_step": 451643, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0515217781066895, "global_step": 451644, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0871400833129883, "global_step": 451645, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0593903064727783, "global_step": 451646, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0959036350250244, "global_step": 451647, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0397937297821045, "global_step": 451648, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.047182083129883, "global_step": 451649, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1112823486328125, "global_step": 451650, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.10793137550354, "global_step": 451651, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.08835768699646, "global_step": 451652, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.059168815612793, "global_step": 451653, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9784090518951416, "global_step": 451654, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0788702964782715, "global_step": 451655, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1057732105255127, "global_step": 451656, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.154526948928833, "global_step": 451657, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.041356325149536, "global_step": 451658, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0246307849884033, "global_step": 451659, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.078070640563965, "global_step": 451660, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0929462909698486, "global_step": 451661, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0767483711242676, "global_step": 451662, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9862496852874756, "global_step": 451663, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0386769771575928, "global_step": 451664, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.053738594055176, "global_step": 451665, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.141360282897949, "global_step": 451666, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.08354115486145, "global_step": 451667, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0852437019348145, "global_step": 451668, "epoch": 815, "lr": 5e-05}
{"train_loss": 1.9983588457107544, "global_step": 451669, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1000804901123047, "global_step": 451670, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1623151302337646, "global_step": 451671, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.188699960708618, "global_step": 451672, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.080920457839966, "global_step": 451673, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0553619861602783, "global_step": 451674, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0508291721343994, "global_step": 451675, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0990843772888184, "global_step": 451676, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.098731279373169, "global_step": 451677, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0811383724212646, "global_step": 451678, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.119527816772461, "global_step": 451679, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.100831985473633, "global_step": 451680, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0399749279022217, "global_step": 451681, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0251007080078125, "global_step": 451682, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.105294942855835, "global_step": 451683, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.132556676864624, "global_step": 451684, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.1329009532928467, "global_step": 451685, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.0743536949157715, "global_step": 451686, "epoch": 815, "lr": 5e-05}
{"train_loss": 2.092775821685791, "global_step": 451687, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9912632703781128, "global_step": 451688, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.003237247467041, "global_step": 451689, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0823922157287598, "global_step": 451690, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0460543632507324, "global_step": 451691, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0628983974456787, "global_step": 451692, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0233917236328125, "global_step": 451693, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.14095139503479, "global_step": 451694, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.97237229347229, "global_step": 451695, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1486544609069824, "global_step": 451696, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0721802711486816, "global_step": 451697, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0975258350372314, "global_step": 451698, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0364551544189453, "global_step": 451699, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0164389610290527, "global_step": 451700, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0088915824890137, "global_step": 451701, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.069638729095459, "global_step": 451702, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0321855545043945, "global_step": 451703, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.039151430130005, "global_step": 451704, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.117708206176758, "global_step": 451705, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0689213275909424, "global_step": 451706, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0770809650421143, "global_step": 451707, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1033570766448975, "global_step": 451708, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.061927318572998, "global_step": 451709, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1211202144622803, "global_step": 451710, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9992536306381226, "global_step": 451711, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1312613487243652, "global_step": 451712, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0581705570220947, "global_step": 451713, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.071770429611206, "global_step": 451714, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.021735429763794, "global_step": 451715, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.062859058380127, "global_step": 451716, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.064409017562866, "global_step": 451717, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0686795711517334, "global_step": 451718, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0357720851898193, "global_step": 451719, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0907139778137207, "global_step": 451720, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1088900566101074, "global_step": 451721, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.165384531021118, "global_step": 451722, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0536460876464844, "global_step": 451723, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1248927116394043, "global_step": 451724, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.101227283477783, "global_step": 451725, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.158473014831543, "global_step": 451726, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0400328636169434, "global_step": 451727, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.022817850112915, "global_step": 451728, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0195860862731934, "global_step": 451729, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.134807825088501, "global_step": 451730, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0510618686676025, "global_step": 451731, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0467324256896973, "global_step": 451732, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.087397813796997, "global_step": 451733, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0845911502838135, "global_step": 451734, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1208102703094482, "global_step": 451735, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.095240592956543, "global_step": 451736, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.082887649536133, "global_step": 451737, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1371243000030518, "global_step": 451738, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0064947605133057, "global_step": 451739, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1021945476531982, "global_step": 451740, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.010023593902588, "global_step": 451741, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0598347187042236, "global_step": 451742, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.08369517326355, "global_step": 451743, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.130449056625366, "global_step": 451744, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1178996562957764, "global_step": 451745, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0667059421539307, "global_step": 451746, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.098141670227051, "global_step": 451747, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9860777854919434, "global_step": 451748, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1149539947509766, "global_step": 451749, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.060314416885376, "global_step": 451750, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.152707576751709, "global_step": 451751, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0452752113342285, "global_step": 451752, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.152026891708374, "global_step": 451753, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.009500026702881, "global_step": 451754, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0261237621307373, "global_step": 451755, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.164789915084839, "global_step": 451756, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1191420555114746, "global_step": 451757, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.027585029602051, "global_step": 451758, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0515778064727783, "global_step": 451759, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.04914927482605, "global_step": 451760, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.127689838409424, "global_step": 451761, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.085303783416748, "global_step": 451762, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.118692636489868, "global_step": 451763, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1292173862457275, "global_step": 451764, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.100534677505493, "global_step": 451765, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1396493911743164, "global_step": 451766, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0222132205963135, "global_step": 451767, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.084662437438965, "global_step": 451768, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0223944187164307, "global_step": 451769, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.066075563430786, "global_step": 451770, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0983235836029053, "global_step": 451771, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0296080112457275, "global_step": 451772, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0770111083984375, "global_step": 451773, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.12078857421875, "global_step": 451774, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0633790493011475, "global_step": 451775, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1216416358947754, "global_step": 451776, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0280094146728516, "global_step": 451777, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9525654315948486, "global_step": 451778, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0400702953338623, "global_step": 451779, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1279382705688477, "global_step": 451780, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0639400482177734, "global_step": 451781, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.052487373352051, "global_step": 451782, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0860354900360107, "global_step": 451783, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.096184492111206, "global_step": 451784, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.034503698348999, "global_step": 451785, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0897271633148193, "global_step": 451786, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.055375337600708, "global_step": 451787, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0780282020568848, "global_step": 451788, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0938777923583984, "global_step": 451789, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0412847995758057, "global_step": 451790, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0525877475738525, "global_step": 451791, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.063735246658325, "global_step": 451792, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.047234535217285, "global_step": 451793, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0747785568237305, "global_step": 451794, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0663270950317383, "global_step": 451795, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.098919630050659, "global_step": 451796, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0890958309173584, "global_step": 451797, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9868475198745728, "global_step": 451798, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.021050214767456, "global_step": 451799, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0274834632873535, "global_step": 451800, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1125080585479736, "global_step": 451801, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.109718084335327, "global_step": 451802, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0108182430267334, "global_step": 451803, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.085982322692871, "global_step": 451804, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.131986141204834, "global_step": 451805, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.029789924621582, "global_step": 451806, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.181478261947632, "global_step": 451807, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1373891830444336, "global_step": 451808, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1758992671966553, "global_step": 451809, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0746545791625977, "global_step": 451810, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.024580717086792, "global_step": 451811, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1179962158203125, "global_step": 451812, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.054176092147827, "global_step": 451813, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.128648519515991, "global_step": 451814, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.047750949859619, "global_step": 451815, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.064178705215454, "global_step": 451816, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.170964241027832, "global_step": 451817, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.020881175994873, "global_step": 451818, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0612130165100098, "global_step": 451819, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.022981643676758, "global_step": 451820, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.992416262626648, "global_step": 451821, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9255419969558716, "global_step": 451822, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.076885461807251, "global_step": 451823, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0940868854522705, "global_step": 451824, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.102947950363159, "global_step": 451825, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0881621837615967, "global_step": 451826, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0485050678253174, "global_step": 451827, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.063206911087036, "global_step": 451828, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.8998944759368896, "global_step": 451829, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1583609580993652, "global_step": 451830, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.238025426864624, "global_step": 451831, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.04508376121521, "global_step": 451832, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1529457569122314, "global_step": 451833, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0102412700653076, "global_step": 451834, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.102057456970215, "global_step": 451835, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1070902347564697, "global_step": 451836, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.025999069213867, "global_step": 451837, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.115755796432495, "global_step": 451838, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9612720012664795, "global_step": 451839, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0971665382385254, "global_step": 451840, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.034287452697754, "global_step": 451841, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.032876968383789, "global_step": 451842, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.075857400894165, "global_step": 451843, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.095180034637451, "global_step": 451844, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0196642875671387, "global_step": 451845, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0639467239379883, "global_step": 451846, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.05519437789917, "global_step": 451847, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.045794725418091, "global_step": 451848, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.061324119567871, "global_step": 451849, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1010804176330566, "global_step": 451850, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9729108810424805, "global_step": 451851, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.018066644668579, "global_step": 451852, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.135528802871704, "global_step": 451853, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0538461208343506, "global_step": 451854, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.077030658721924, "global_step": 451855, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9898816347122192, "global_step": 451856, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0672767162323, "global_step": 451857, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1390085220336914, "global_step": 451858, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.060560464859009, "global_step": 451859, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0046579837799072, "global_step": 451860, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0529160499572754, "global_step": 451861, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0836293697357178, "global_step": 451862, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0036914348602295, "global_step": 451863, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0291552543640137, "global_step": 451864, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0223124027252197, "global_step": 451865, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.018643617630005, "global_step": 451866, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1052327156066895, "global_step": 451867, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.146468162536621, "global_step": 451868, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.133000135421753, "global_step": 451869, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0501232147216797, "global_step": 451870, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.08662486076355, "global_step": 451871, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0599613189697266, "global_step": 451872, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.03131365776062, "global_step": 451873, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0616214275360107, "global_step": 451874, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.061297655105591, "global_step": 451875, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.078022003173828, "global_step": 451876, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0385243892669678, "global_step": 451877, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0555777549743652, "global_step": 451878, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1106348037719727, "global_step": 451879, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0561368465423584, "global_step": 451880, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1205906867980957, "global_step": 451881, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.089648723602295, "global_step": 451882, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1031641960144043, "global_step": 451883, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0136494636535645, "global_step": 451884, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0649538040161133, "global_step": 451885, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.062342643737793, "global_step": 451886, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.17008113861084, "global_step": 451887, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.075040578842163, "global_step": 451888, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.052602529525757, "global_step": 451889, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0902035236358643, "global_step": 451890, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0737719535827637, "global_step": 451891, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.056957721710205, "global_step": 451892, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.084428310394287, "global_step": 451893, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0140841007232666, "global_step": 451894, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9998219013214111, "global_step": 451895, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.087796449661255, "global_step": 451896, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0094854831695557, "global_step": 451897, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9853739738464355, "global_step": 451898, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0734002590179443, "global_step": 451899, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.115807056427002, "global_step": 451900, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0954365730285645, "global_step": 451901, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.065098285675049, "global_step": 451902, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0152015686035156, "global_step": 451903, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0300045013427734, "global_step": 451904, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.014237403869629, "global_step": 451905, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9833203554153442, "global_step": 451906, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0598561763763428, "global_step": 451907, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1011383533477783, "global_step": 451908, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0738205909729004, "global_step": 451909, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.138868808746338, "global_step": 451910, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0736711025238037, "global_step": 451911, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0973904132843018, "global_step": 451912, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1143949031829834, "global_step": 451913, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9739537239074707, "global_step": 451914, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.112968921661377, "global_step": 451915, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1609716415405273, "global_step": 451916, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.045732021331787, "global_step": 451917, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0287787914276123, "global_step": 451918, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0029354095458984, "global_step": 451919, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0974996089935303, "global_step": 451920, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.096372365951538, "global_step": 451921, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1170828342437744, "global_step": 451922, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.065697431564331, "global_step": 451923, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.126128673553467, "global_step": 451924, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0977163314819336, "global_step": 451925, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0109055042266846, "global_step": 451926, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.085742473602295, "global_step": 451927, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0531890392303467, "global_step": 451928, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1071696281433105, "global_step": 451929, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0923855304718018, "global_step": 451930, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.175689935684204, "global_step": 451931, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0627145767211914, "global_step": 451932, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.074230670928955, "global_step": 451933, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0546653270721436, "global_step": 451934, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.055069923400879, "global_step": 451935, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0413453578948975, "global_step": 451936, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.111166000366211, "global_step": 451937, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.075363874435425, "global_step": 451938, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0440115928649902, "global_step": 451939, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0951709747314453, "global_step": 451940, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.030881881713867, "global_step": 451941, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.040320873260498, "global_step": 451942, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0840320587158203, "global_step": 451943, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0992801189422607, "global_step": 451944, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.002933979034424, "global_step": 451945, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.101973056793213, "global_step": 451946, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0687317848205566, "global_step": 451947, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0317232608795166, "global_step": 451948, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.095066785812378, "global_step": 451949, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0170531272888184, "global_step": 451950, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0374581813812256, "global_step": 451951, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.066404342651367, "global_step": 451952, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1120901107788086, "global_step": 451953, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1165289878845215, "global_step": 451954, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0304064750671387, "global_step": 451955, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9934496879577637, "global_step": 451956, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.085061550140381, "global_step": 451957, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0386290550231934, "global_step": 451958, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1543798446655273, "global_step": 451959, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9436016082763672, "global_step": 451960, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0660929679870605, "global_step": 451961, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9790127277374268, "global_step": 451962, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.130168914794922, "global_step": 451963, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.069016933441162, "global_step": 451964, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.048229217529297, "global_step": 451965, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.048523187637329, "global_step": 451966, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0259528160095215, "global_step": 451967, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1264827251434326, "global_step": 451968, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1095359325408936, "global_step": 451969, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0552337169647217, "global_step": 451970, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9572622776031494, "global_step": 451971, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0521368980407715, "global_step": 451972, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.10514235496521, "global_step": 451973, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.069157600402832, "global_step": 451974, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.086583375930786, "global_step": 451975, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9992663860321045, "global_step": 451976, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0245022773742676, "global_step": 451977, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.111950159072876, "global_step": 451978, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1302475929260254, "global_step": 451979, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.068316698074341, "global_step": 451980, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.011209487915039, "global_step": 451981, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.114457607269287, "global_step": 451982, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1427648067474365, "global_step": 451983, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0933592319488525, "global_step": 451984, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0849170684814453, "global_step": 451985, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0957400798797607, "global_step": 451986, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.062392473220825, "global_step": 451987, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.091273307800293, "global_step": 451988, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1047561168670654, "global_step": 451989, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0559420585632324, "global_step": 451990, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.111246347427368, "global_step": 451991, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.102714776992798, "global_step": 451992, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0645017623901367, "global_step": 451993, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.092542886734009, "global_step": 451994, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9854856729507446, "global_step": 451995, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0411996841430664, "global_step": 451996, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1041576862335205, "global_step": 451997, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.037717819213867, "global_step": 451998, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9883893728256226, "global_step": 451999, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.072770833969116, "global_step": 452000, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.021611213684082, "global_step": 452001, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.099273681640625, "global_step": 452002, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.146135091781616, "global_step": 452003, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.066488265991211, "global_step": 452004, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.142037868499756, "global_step": 452005, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.134568214416504, "global_step": 452006, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.134472370147705, "global_step": 452007, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0725560188293457, "global_step": 452008, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.119277000427246, "global_step": 452009, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.046433448791504, "global_step": 452010, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0320193767547607, "global_step": 452011, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.093346118927002, "global_step": 452012, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.98027503490448, "global_step": 452013, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0434317588806152, "global_step": 452014, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0138041973114014, "global_step": 452015, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.101043462753296, "global_step": 452016, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.056501626968384, "global_step": 452017, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9702006578445435, "global_step": 452018, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.136059045791626, "global_step": 452019, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0534064769744873, "global_step": 452020, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1178500652313232, "global_step": 452021, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1376588344573975, "global_step": 452022, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1147282123565674, "global_step": 452023, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.080904483795166, "global_step": 452024, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.044450044631958, "global_step": 452025, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0867908000946045, "global_step": 452026, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.093855142593384, "global_step": 452027, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0469727516174316, "global_step": 452028, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1077582836151123, "global_step": 452029, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.114912986755371, "global_step": 452030, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9912301301956177, "global_step": 452031, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0421876907348633, "global_step": 452032, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1150522232055664, "global_step": 452033, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.011045217514038, "global_step": 452034, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9809434413909912, "global_step": 452035, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.157984733581543, "global_step": 452036, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0416455268859863, "global_step": 452037, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.081157684326172, "global_step": 452038, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.092686653137207, "global_step": 452039, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.069689989089966, "global_step": 452040, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0566024780273438, "global_step": 452041, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.073180913925171, "global_step": 452042, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.044384717941284, "global_step": 452043, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.042508363723755, "global_step": 452044, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0411417484283447, "global_step": 452045, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0499918460845947, "global_step": 452046, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.045881748199463, "global_step": 452047, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9831033945083618, "global_step": 452048, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.045858860015869, "global_step": 452049, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.097261667251587, "global_step": 452050, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0673868656158447, "global_step": 452051, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.161679983139038, "global_step": 452052, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.106100559234619, "global_step": 452053, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9967378377914429, "global_step": 452054, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.027625560760498, "global_step": 452055, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1402249336242676, "global_step": 452056, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.102942943572998, "global_step": 452057, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.062101364135742, "global_step": 452058, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1315338611602783, "global_step": 452059, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0095462799072266, "global_step": 452060, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0566563606262207, "global_step": 452061, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0731072425842285, "global_step": 452062, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.053676128387451, "global_step": 452063, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.112412929534912, "global_step": 452064, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0977816581726074, "global_step": 452065, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.114530086517334, "global_step": 452066, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.074838399887085, "global_step": 452067, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0347957611083984, "global_step": 452068, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9991503953933716, "global_step": 452069, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0789449214935303, "global_step": 452070, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.112302541732788, "global_step": 452071, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0661613941192627, "global_step": 452072, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0476624965667725, "global_step": 452073, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0071182250976562, "global_step": 452074, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9839608669281006, "global_step": 452075, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0545756816864014, "global_step": 452076, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.042815923690796, "global_step": 452077, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1052792072296143, "global_step": 452078, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9960988759994507, "global_step": 452079, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1758861541748047, "global_step": 452080, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.087712287902832, "global_step": 452081, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0709950923919678, "global_step": 452082, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0749309062957764, "global_step": 452083, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.090380907058716, "global_step": 452084, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1416878700256348, "global_step": 452085, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1591711044311523, "global_step": 452086, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0686893463134766, "global_step": 452087, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.079158306121826, "global_step": 452088, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0371181964874268, "global_step": 452089, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9804903268814087, "global_step": 452090, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.040929079055786, "global_step": 452091, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.078054428100586, "global_step": 452092, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1119449138641357, "global_step": 452093, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.031283140182495, "global_step": 452094, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9928370714187622, "global_step": 452095, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9882352352142334, "global_step": 452096, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1175527572631836, "global_step": 452097, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.102736234664917, "global_step": 452098, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.059142589569092, "global_step": 452099, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1298630237579346, "global_step": 452100, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0622379779815674, "global_step": 452101, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.069192886352539, "global_step": 452102, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.11519718170166, "global_step": 452103, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.088705062866211, "global_step": 452104, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.092224597930908, "global_step": 452105, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.113194227218628, "global_step": 452106, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.008070707321167, "global_step": 452107, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9597787857055664, "global_step": 452108, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0600576400756836, "global_step": 452109, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0810434818267822, "global_step": 452110, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.112192153930664, "global_step": 452111, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0936484336853027, "global_step": 452112, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1001081466674805, "global_step": 452113, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1061770915985107, "global_step": 452114, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.055079936981201, "global_step": 452115, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0287926197052, "global_step": 452116, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.015545606613159, "global_step": 452117, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.082797050476074, "global_step": 452118, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1186959743499756, "global_step": 452119, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0343892574310303, "global_step": 452120, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1408369541168213, "global_step": 452121, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.130769729614258, "global_step": 452122, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.969482660293579, "global_step": 452123, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.053786039352417, "global_step": 452124, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.164149522781372, "global_step": 452125, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0158913135528564, "global_step": 452126, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1252059936523438, "global_step": 452127, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.075899124145508, "global_step": 452128, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0921952724456787, "global_step": 452129, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0295772552490234, "global_step": 452130, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.071096658706665, "global_step": 452131, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0497889518737793, "global_step": 452132, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.040651321411133, "global_step": 452133, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9634779691696167, "global_step": 452134, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.8472063541412354, "global_step": 452135, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.091826915740967, "global_step": 452136, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0779519081115723, "global_step": 452137, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0903074741363525, "global_step": 452138, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.091390371322632, "global_step": 452139, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0872762203216553, "global_step": 452140, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.155809164047241, "global_step": 452141, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.066112995147705, "global_step": 452142, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.073580741882324, "global_step": 452143, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.045548677444458, "global_step": 452144, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9828498363494873, "global_step": 452145, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1507458686828613, "global_step": 452146, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0891640186309814, "global_step": 452147, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.018326759338379, "global_step": 452148, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.044921875, "global_step": 452149, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1271612644195557, "global_step": 452150, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.112082004547119, "global_step": 452151, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1185805797576904, "global_step": 452152, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.090311050415039, "global_step": 452153, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.040536642074585, "global_step": 452154, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.04341721534729, "global_step": 452155, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.101815700531006, "global_step": 452156, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1504321098327637, "global_step": 452157, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0837368965148926, "global_step": 452158, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1119911670684814, "global_step": 452159, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0189783573150635, "global_step": 452160, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.07443904876709, "global_step": 452161, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1524412631988525, "global_step": 452162, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1518471240997314, "global_step": 452163, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.064624309539795, "global_step": 452164, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.224531650543213, "global_step": 452165, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1094589233398438, "global_step": 452166, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0751428604125977, "global_step": 452167, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.073726177215576, "global_step": 452168, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.004009962081909, "global_step": 452169, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0254013538360596, "global_step": 452170, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.008481025695801, "global_step": 452171, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.057124614715576, "global_step": 452172, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1268889904022217, "global_step": 452173, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.057805299758911, "global_step": 452174, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.150718927383423, "global_step": 452175, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9482046365737915, "global_step": 452176, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1425161361694336, "global_step": 452177, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.066018581390381, "global_step": 452178, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0155599117279053, "global_step": 452179, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9969991445541382, "global_step": 452180, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.150721311569214, "global_step": 452181, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0995965003967285, "global_step": 452182, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0769009590148926, "global_step": 452183, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.054645299911499, "global_step": 452184, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0937986373901367, "global_step": 452185, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1141300201416016, "global_step": 452186, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0866565704345703, "global_step": 452187, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.019340753555298, "global_step": 452188, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.105116605758667, "global_step": 452189, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0798985958099365, "global_step": 452190, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1483263969421387, "global_step": 452191, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.079716920852661, "global_step": 452192, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0652363300323486, "global_step": 452193, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.115933656692505, "global_step": 452194, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1223950386047363, "global_step": 452195, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0786170959472656, "global_step": 452196, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0433740615844727, "global_step": 452197, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.050180196762085, "global_step": 452198, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9900778532028198, "global_step": 452199, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.056215524673462, "global_step": 452200, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.060715675354004, "global_step": 452201, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.073880434036255, "global_step": 452202, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.057476758956909, "global_step": 452203, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0917091369628906, "global_step": 452204, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.148668050765991, "global_step": 452205, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.026573657989502, "global_step": 452206, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.120929002761841, "global_step": 452207, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9583758115768433, "global_step": 452208, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.09710431098938, "global_step": 452209, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.122734546661377, "global_step": 452210, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1081013679504395, "global_step": 452211, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.988067388534546, "global_step": 452212, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0213866233825684, "global_step": 452213, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0424318313598633, "global_step": 452214, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1251823902130127, "global_step": 452215, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1610896587371826, "global_step": 452216, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.02081298828125, "global_step": 452217, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.195732355117798, "global_step": 452218, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.078496217727661, "global_step": 452219, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0704259872436523, "global_step": 452220, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.02250337600708, "global_step": 452221, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0851199626922607, "global_step": 452222, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.086465358734131, "global_step": 452223, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0706770420074463, "global_step": 452224, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1153500080108643, "global_step": 452225, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.143829822540283, "global_step": 452226, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0052101612091064, "global_step": 452227, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.041918992996216, "global_step": 452228, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0687897205352783, "global_step": 452229, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.070240020751953, "global_step": 452230, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.13315486907959, "global_step": 452231, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.031572103500366, "global_step": 452232, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0775034427642822, "global_step": 452233, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0191245079040527, "global_step": 452234, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1040384769439697, "global_step": 452235, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.062238931655884, "global_step": 452236, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1790413856506348, "global_step": 452237, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0239264965057373, "global_step": 452238, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9828782081604004, "global_step": 452239, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0154082775115967, "global_step": 452240, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.069765329360962, "global_step": 452241, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.132863998413086, "global_step": 452242, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1062724590301514, "global_step": 452243, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.080949068069458, "global_step": 452244, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0844666957855225, "global_step": 452245, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.084449529647827, "global_step": 452246, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0094943046569824, "global_step": 452247, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0565731525421143, "global_step": 452248, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1542210578918457, "global_step": 452249, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0729291439056396, "global_step": 452250, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0476245880126953, "global_step": 452251, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.055408477783203, "global_step": 452252, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0150187015533447, "global_step": 452253, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.132101535797119, "global_step": 452254, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.03603196144104, "global_step": 452255, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.045395851135254, "global_step": 452256, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.092550277709961, "global_step": 452257, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0440220832824707, "global_step": 452258, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.054722785949707, "global_step": 452259, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.098111867904663, "global_step": 452260, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0724189281463623, "global_step": 452261, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1085410118103027, "global_step": 452262, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1116397380828857, "global_step": 452263, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1370480060577393, "global_step": 452264, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0580601692199707, "global_step": 452265, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.065164566040039, "global_step": 452266, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0417046546936035, "global_step": 452267, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.115567207336426, "global_step": 452268, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9869251251220703, "global_step": 452269, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0760533809661865, "global_step": 452270, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0372767448425293, "global_step": 452271, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.099626302719116, "global_step": 452272, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1308298110961914, "global_step": 452273, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0082499980926514, "global_step": 452274, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0776333808898926, "global_step": 452275, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0933165550231934, "global_step": 452276, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0908846855163574, "global_step": 452277, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0735464096069336, "global_step": 452278, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.04433274269104, "global_step": 452279, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0491700172424316, "global_step": 452280, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.007516622543335, "global_step": 452281, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.032376766204834, "global_step": 452282, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.053595542907715, "global_step": 452283, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.087120532989502, "global_step": 452284, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0256505012512207, "global_step": 452285, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.001544237136841, "global_step": 452286, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0525357723236084, "global_step": 452287, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0865824222564697, "global_step": 452288, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.015281915664673, "global_step": 452289, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.02927303314209, "global_step": 452290, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1358160972595215, "global_step": 452291, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.127332925796509, "global_step": 452292, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.073093891143799, "global_step": 452293, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0704638957977295, "global_step": 452294, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.043720006942749, "global_step": 452295, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0530972480773926, "global_step": 452296, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1385092735290527, "global_step": 452297, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1043753623962402, "global_step": 452298, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.07897686958313, "global_step": 452299, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0768239498138428, "global_step": 452300, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0933470726013184, "global_step": 452301, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9950865507125854, "global_step": 452302, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.049520492553711, "global_step": 452303, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0796215534210205, "global_step": 452304, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.072798490524292, "global_step": 452305, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0766446590423584, "global_step": 452306, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.083737373352051, "global_step": 452307, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.075753927230835, "global_step": 452308, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1227800846099854, "global_step": 452309, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.072176933288574, "global_step": 452310, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0073070526123047, "global_step": 452311, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.057267665863037, "global_step": 452312, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.07492733001709, "global_step": 452313, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1132559776306152, "global_step": 452314, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.173501491546631, "global_step": 452315, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1267640590667725, "global_step": 452316, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.087656259536743, "global_step": 452317, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.059342861175537, "global_step": 452318, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.029327154159546, "global_step": 452319, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.151911735534668, "global_step": 452320, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1024904251098633, "global_step": 452321, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0681231021881104, "global_step": 452322, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.075167417526245, "global_step": 452323, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.070678472518921, "global_step": 452324, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.068358898162842, "global_step": 452325, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.074557065963745, "global_step": 452326, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0896012783050537, "global_step": 452327, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0984139442443848, "global_step": 452328, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1156258583068848, "global_step": 452329, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0989396572113037, "global_step": 452330, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1687114238739014, "global_step": 452331, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9442769289016724, "global_step": 452332, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.026707649230957, "global_step": 452333, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0453999042510986, "global_step": 452334, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.193307876586914, "global_step": 452335, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.135580539703369, "global_step": 452336, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0790798664093018, "global_step": 452337, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.096534013748169, "global_step": 452338, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0441086292266846, "global_step": 452339, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.118821382522583, "global_step": 452340, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.080669641494751, "global_step": 452341, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.022052526473999, "global_step": 452342, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0163447856903076, "global_step": 452343, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.032513380050659, "global_step": 452344, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1562390327453613, "global_step": 452345, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0234451293945312, "global_step": 452346, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.059189558029175, "global_step": 452347, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0894949436187744, "global_step": 452348, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0441160202026367, "global_step": 452349, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.160529613494873, "global_step": 452350, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0760316848754883, "global_step": 452351, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0736215114593506, "global_step": 452352, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1908116340637207, "global_step": 452353, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1594061851501465, "global_step": 452354, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.035137176513672, "global_step": 452355, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.089108467102051, "global_step": 452356, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.119957447052002, "global_step": 452357, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.013232946395874, "global_step": 452358, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.015115976333618, "global_step": 452359, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.038865566253662, "global_step": 452360, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.050612688064575, "global_step": 452361, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.905665397644043, "global_step": 452362, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0053510665893555, "global_step": 452363, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1110692024230957, "global_step": 452364, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0868380069732666, "global_step": 452365, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.07549786567688, "global_step": 452366, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.032167673110962, "global_step": 452367, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.076524019241333, "global_step": 452368, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1845011711120605, "global_step": 452369, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.07236385345459, "global_step": 452370, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0490362644195557, "global_step": 452371, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1099002361297607, "global_step": 452372, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.003680944442749, "global_step": 452373, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9907475709915161, "global_step": 452374, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.996840238571167, "global_step": 452375, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0219132900238037, "global_step": 452376, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0503811836242676, "global_step": 452377, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1842949390411377, "global_step": 452378, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1413111686706543, "global_step": 452379, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.059145450592041, "global_step": 452380, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.06056809425354, "global_step": 452381, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.140767812728882, "global_step": 452382, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0292489528656006, "global_step": 452383, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0996806621551514, "global_step": 452384, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0033366680145264, "global_step": 452385, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.126678466796875, "global_step": 452386, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0849595069885254, "global_step": 452387, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.061457395553589, "global_step": 452388, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0508062839508057, "global_step": 452389, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.169480800628662, "global_step": 452390, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9965434074401855, "global_step": 452391, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1260321140289307, "global_step": 452392, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0677082538604736, "global_step": 452393, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0954859256744385, "global_step": 452394, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.062472105026245, "global_step": 452395, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.121800661087036, "global_step": 452396, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1422512531280518, "global_step": 452397, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.066977024078369, "global_step": 452398, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0764381885528564, "global_step": 452399, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0843453407287598, "global_step": 452400, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1275126934051514, "global_step": 452401, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9812333583831787, "global_step": 452402, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0427799224853516, "global_step": 452403, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.046171188354492, "global_step": 452404, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.086000919342041, "global_step": 452405, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0685296058654785, "global_step": 452406, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1751010417938232, "global_step": 452407, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0922253131866455, "global_step": 452408, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.061988592147827, "global_step": 452409, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1274256706237793, "global_step": 452410, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.036907196044922, "global_step": 452411, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0458009243011475, "global_step": 452412, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0127665996551514, "global_step": 452413, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.026017665863037, "global_step": 452414, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0738577842712402, "global_step": 452415, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.044750928878784, "global_step": 452416, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1290602684020996, "global_step": 452417, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.050715923309326, "global_step": 452418, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0888943672180176, "global_step": 452419, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9682241678237915, "global_step": 452420, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0619094371795654, "global_step": 452421, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0360376834869385, "global_step": 452422, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.090512275695801, "global_step": 452423, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0993568897247314, "global_step": 452424, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0374133586883545, "global_step": 452425, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0764000415802, "global_step": 452426, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1300792694091797, "global_step": 452427, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0629565715789795, "global_step": 452428, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0952696800231934, "global_step": 452429, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0396618843078613, "global_step": 452430, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.020317792892456, "global_step": 452431, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.11920428276062, "global_step": 452432, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0886759757995605, "global_step": 452433, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.033938407897949, "global_step": 452434, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9856040477752686, "global_step": 452435, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.144580364227295, "global_step": 452436, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9756128787994385, "global_step": 452437, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1358416080474854, "global_step": 452438, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0567994117736816, "global_step": 452439, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.152069091796875, "global_step": 452440, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.079972743988037, "global_step": 452441, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.144806146621704, "global_step": 452442, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.066575527191162, "global_step": 452443, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1159868240356445, "global_step": 452444, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0682833194732666, "global_step": 452445, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.049767255783081, "global_step": 452446, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.158644914627075, "global_step": 452447, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.047222375869751, "global_step": 452448, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0402166843414307, "global_step": 452449, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.022373676300049, "global_step": 452450, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9987645149230957, "global_step": 452451, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.018159866333008, "global_step": 452452, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0649831295013428, "global_step": 452453, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0376195907592773, "global_step": 452454, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.062019109725952, "global_step": 452455, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.073592185974121, "global_step": 452456, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.025528907775879, "global_step": 452457, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1086974143981934, "global_step": 452458, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.028761148452759, "global_step": 452459, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0115933418273926, "global_step": 452460, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0906662940979004, "global_step": 452461, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0127182006835938, "global_step": 452462, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.11423659324646, "global_step": 452463, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.035612106323242, "global_step": 452464, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1062188148498535, "global_step": 452465, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0906989574432373, "global_step": 452466, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.067624807357788, "global_step": 452467, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1472036838531494, "global_step": 452468, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0415420532226562, "global_step": 452469, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9873474836349487, "global_step": 452470, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1293087005615234, "global_step": 452471, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0012125968933105, "global_step": 452472, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.123622417449951, "global_step": 452473, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0654044151306152, "global_step": 452474, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0372259616851807, "global_step": 452475, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.136139154434204, "global_step": 452476, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.096633195877075, "global_step": 452477, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.087212085723877, "global_step": 452478, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0608527660369873, "global_step": 452479, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0277621746063232, "global_step": 452480, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.094318389892578, "global_step": 452481, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1333484649658203, "global_step": 452482, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0632946491241455, "global_step": 452483, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1300408840179443, "global_step": 452484, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0769827365875244, "global_step": 452485, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.074045181274414, "global_step": 452486, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1640374660491943, "global_step": 452487, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1229329109191895, "global_step": 452488, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1020569801330566, "global_step": 452489, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.054316282272339, "global_step": 452490, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.038275718688965, "global_step": 452491, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0511722564697266, "global_step": 452492, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.076962471008301, "global_step": 452493, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.109015464782715, "global_step": 452494, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9536336660385132, "global_step": 452495, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1291167736053467, "global_step": 452496, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1222238540649414, "global_step": 452497, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0510621070861816, "global_step": 452498, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.081634044647217, "global_step": 452499, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1067934036254883, "global_step": 452500, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.080533742904663, "global_step": 452501, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.00183367729187, "global_step": 452502, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9861812591552734, "global_step": 452503, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.107022285461426, "global_step": 452504, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1099627017974854, "global_step": 452505, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0661747455596924, "global_step": 452506, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.2266783714294434, "global_step": 452507, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0655269622802734, "global_step": 452508, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.11958909034729, "global_step": 452509, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.108182430267334, "global_step": 452510, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.092470169067383, "global_step": 452511, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.081061363220215, "global_step": 452512, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.108656883239746, "global_step": 452513, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.086078643798828, "global_step": 452514, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0959737300872803, "global_step": 452515, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9988598823547363, "global_step": 452516, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.125478744506836, "global_step": 452517, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.108980655670166, "global_step": 452518, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.064969301223755, "global_step": 452519, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.104853630065918, "global_step": 452520, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0648818016052246, "global_step": 452521, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.078068733215332, "global_step": 452522, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.060368776321411, "global_step": 452523, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1608951091766357, "global_step": 452524, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0384714603424072, "global_step": 452525, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0757734775543213, "global_step": 452526, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1488280296325684, "global_step": 452527, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9543719291687012, "global_step": 452528, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.116112470626831, "global_step": 452529, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0921008586883545, "global_step": 452530, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0505082607269287, "global_step": 452531, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.112123489379883, "global_step": 452532, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0634357929229736, "global_step": 452533, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.050205945968628, "global_step": 452534, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.030367136001587, "global_step": 452535, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0525169372558594, "global_step": 452536, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.006520986557007, "global_step": 452537, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.028210401535034, "global_step": 452538, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0316879749298096, "global_step": 452539, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1254403591156006, "global_step": 452540, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.016282796859741, "global_step": 452541, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.083757162094116, "global_step": 452542, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.076803207397461, "global_step": 452543, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.012139320373535, "global_step": 452544, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.050837516784668, "global_step": 452545, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1395504474639893, "global_step": 452546, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.034764051437378, "global_step": 452547, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0818676948547363, "global_step": 452548, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.08138370513916, "global_step": 452549, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0463132858276367, "global_step": 452550, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.167245626449585, "global_step": 452551, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.112072706222534, "global_step": 452552, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0768415927886963, "global_step": 452553, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1244184970855713, "global_step": 452554, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.06817889213562, "global_step": 452555, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1015727519989014, "global_step": 452556, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0214481353759766, "global_step": 452557, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0884056091308594, "global_step": 452558, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0383119583129883, "global_step": 452559, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0853078365325928, "global_step": 452560, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0659382343292236, "global_step": 452561, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.106489658355713, "global_step": 452562, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1031620502471924, "global_step": 452563, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0514111518859863, "global_step": 452564, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0152595043182373, "global_step": 452565, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1181905269622803, "global_step": 452566, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.089934825897217, "global_step": 452567, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1400930881500244, "global_step": 452568, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.064326047897339, "global_step": 452569, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.132521390914917, "global_step": 452570, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1214146614074707, "global_step": 452571, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.099759817123413, "global_step": 452572, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0962884426116943, "global_step": 452573, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.020465135574341, "global_step": 452574, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.006833791732788, "global_step": 452575, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0516932010650635, "global_step": 452576, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.101850986480713, "global_step": 452577, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.128905773162842, "global_step": 452578, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1106669902801514, "global_step": 452579, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.031791925430298, "global_step": 452580, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.059809446334839, "global_step": 452581, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.133944272994995, "global_step": 452582, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1066179275512695, "global_step": 452583, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.037631034851074, "global_step": 452584, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.088446617126465, "global_step": 452585, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1202151775360107, "global_step": 452586, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0878846645355225, "global_step": 452587, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9847967624664307, "global_step": 452588, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.083017587661743, "global_step": 452589, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0486910343170166, "global_step": 452590, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0576181411743164, "global_step": 452591, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1371419429779053, "global_step": 452592, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.071229934692383, "global_step": 452593, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0576226711273193, "global_step": 452594, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.059051275253296, "global_step": 452595, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.04124116897583, "global_step": 452596, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0599207878112793, "global_step": 452597, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0782694816589355, "global_step": 452598, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1734163761138916, "global_step": 452599, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.039518117904663, "global_step": 452600, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.047633647918701, "global_step": 452601, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0594546794891357, "global_step": 452602, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0326128005981445, "global_step": 452603, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.119734525680542, "global_step": 452604, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0680644512176514, "global_step": 452605, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0304462909698486, "global_step": 452606, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0657565593719482, "global_step": 452607, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1738121509552, "global_step": 452608, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.067051887512207, "global_step": 452609, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.084209680557251, "global_step": 452610, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.047816038131714, "global_step": 452611, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.08705472946167, "global_step": 452612, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1824798583984375, "global_step": 452613, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9670348167419434, "global_step": 452614, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0191726684570312, "global_step": 452615, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0129830837249756, "global_step": 452616, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0014328956604004, "global_step": 452617, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.10390567779541, "global_step": 452618, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0478110313415527, "global_step": 452619, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0492730140686035, "global_step": 452620, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1201224327087402, "global_step": 452621, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.140946865081787, "global_step": 452622, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0805416107177734, "global_step": 452623, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.990780234336853, "global_step": 452624, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0310521125793457, "global_step": 452625, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1883435249328613, "global_step": 452626, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0548527240753174, "global_step": 452627, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0687766075134277, "global_step": 452628, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0959177017211914, "global_step": 452629, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.046044111251831, "global_step": 452630, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0928783416748047, "global_step": 452631, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1304972171783447, "global_step": 452632, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0982584953308105, "global_step": 452633, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.097562789916992, "global_step": 452634, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.095090866088867, "global_step": 452635, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.022928237915039, "global_step": 452636, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0968644618988037, "global_step": 452637, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.167201519012451, "global_step": 452638, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.141348361968994, "global_step": 452639, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.051833152770996, "global_step": 452640, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.034533977508545, "global_step": 452641, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0568485260009766, "global_step": 452642, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9869263172149658, "global_step": 452643, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.104200839996338, "global_step": 452644, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.079467535018921, "global_step": 452645, "epoch": 816, "lr": 5e-05}
{"train_loss": 1.9680287837982178, "global_step": 452646, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.043950080871582, "global_step": 452647, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.149383783340454, "global_step": 452648, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0749402046203613, "global_step": 452649, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.041069984436035, "global_step": 452650, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.057297945022583, "global_step": 452651, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.1138455867767334, "global_step": 452652, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0196268558502197, "global_step": 452653, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.049191951751709, "global_step": 452654, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.0720674991607666, "global_step": 452655, "epoch": 816, "lr": 5e-05}
{"train_loss": 2.064547538757324, "global_step": 452656, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.042330741882324, "global_step": 452657, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.103109121322632, "global_step": 452658, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0420567989349365, "global_step": 452659, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0549612045288086, "global_step": 452660, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.10260009765625, "global_step": 452661, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0593085289001465, "global_step": 452662, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.031195640563965, "global_step": 452663, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.015702962875366, "global_step": 452664, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0276167392730713, "global_step": 452665, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.100374460220337, "global_step": 452666, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.114393472671509, "global_step": 452667, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.035299062728882, "global_step": 452668, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.042005777359009, "global_step": 452669, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0061068534851074, "global_step": 452670, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.069591999053955, "global_step": 452671, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9914110898971558, "global_step": 452672, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9953275918960571, "global_step": 452673, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1192848682403564, "global_step": 452674, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0841970443725586, "global_step": 452675, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1027932167053223, "global_step": 452676, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0299010276794434, "global_step": 452677, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.057483434677124, "global_step": 452678, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0391781330108643, "global_step": 452679, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9881532192230225, "global_step": 452680, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.076507568359375, "global_step": 452681, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1113948822021484, "global_step": 452682, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.036942481994629, "global_step": 452683, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.017141819000244, "global_step": 452684, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0267765522003174, "global_step": 452685, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0128071308135986, "global_step": 452686, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9712600708007812, "global_step": 452687, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0418081283569336, "global_step": 452688, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0555930137634277, "global_step": 452689, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1240923404693604, "global_step": 452690, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1316940784454346, "global_step": 452691, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.062505006790161, "global_step": 452692, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1217598915100098, "global_step": 452693, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0343146324157715, "global_step": 452694, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.041630744934082, "global_step": 452695, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9933029413223267, "global_step": 452696, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0742249488830566, "global_step": 452697, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0433709621429443, "global_step": 452698, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.050642251968384, "global_step": 452699, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0358543395996094, "global_step": 452700, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1581478118896484, "global_step": 452701, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0575294494628906, "global_step": 452702, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1501636505126953, "global_step": 452703, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.093259572982788, "global_step": 452704, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0567727088928223, "global_step": 452705, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0447590351104736, "global_step": 452706, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.043012857437134, "global_step": 452707, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.063425064086914, "global_step": 452708, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.073605537414551, "global_step": 452709, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.056967258453369, "global_step": 452710, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.062371253967285, "global_step": 452711, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1027722358703613, "global_step": 452712, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0126097202301025, "global_step": 452713, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.088193655014038, "global_step": 452714, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0726752281188965, "global_step": 452715, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9941686391830444, "global_step": 452716, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1027212142944336, "global_step": 452717, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1150050163269043, "global_step": 452718, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.05391263961792, "global_step": 452719, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.104264974594116, "global_step": 452720, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.047840118408203, "global_step": 452721, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.118401288986206, "global_step": 452722, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.097414970397949, "global_step": 452723, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0328075885772705, "global_step": 452724, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.039217472076416, "global_step": 452725, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0648646354675293, "global_step": 452726, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0423076152801514, "global_step": 452727, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0623538494110107, "global_step": 452728, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0623908042907715, "global_step": 452729, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0322751998901367, "global_step": 452730, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0458619594573975, "global_step": 452731, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.025677442550659, "global_step": 452732, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.05692195892334, "global_step": 452733, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0548174381256104, "global_step": 452734, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1843698024749756, "global_step": 452735, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.020979166030884, "global_step": 452736, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0247039794921875, "global_step": 452737, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.064270257949829, "global_step": 452738, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0483031272888184, "global_step": 452739, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0286617279052734, "global_step": 452740, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.070263147354126, "global_step": 452741, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.104736566543579, "global_step": 452742, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1493752002716064, "global_step": 452743, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9935848712921143, "global_step": 452744, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.038187026977539, "global_step": 452745, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0078024864196777, "global_step": 452746, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.01859974861145, "global_step": 452747, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.088660717010498, "global_step": 452748, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0569028854370117, "global_step": 452749, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0581557750701904, "global_step": 452750, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.131772518157959, "global_step": 452751, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.113260269165039, "global_step": 452752, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1188278198242188, "global_step": 452753, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0379960536956787, "global_step": 452754, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0882444381713867, "global_step": 452755, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1079699993133545, "global_step": 452756, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0797035694122314, "global_step": 452757, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.050097942352295, "global_step": 452758, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.065378427505493, "global_step": 452759, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.015763282775879, "global_step": 452760, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.128584384918213, "global_step": 452761, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9894710779190063, "global_step": 452762, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.091417074203491, "global_step": 452763, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.077735185623169, "global_step": 452764, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.095900774002075, "global_step": 452765, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1828248500823975, "global_step": 452766, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1072254180908203, "global_step": 452767, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1069676876068115, "global_step": 452768, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0665502548217773, "global_step": 452769, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0413131713867188, "global_step": 452770, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0447351932525635, "global_step": 452771, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.084777593612671, "global_step": 452772, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0774025917053223, "global_step": 452773, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.061763048171997, "global_step": 452774, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.065174102783203, "global_step": 452775, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0595686435699463, "global_step": 452776, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1223959922790527, "global_step": 452777, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0459706783294678, "global_step": 452778, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0478012561798096, "global_step": 452779, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0050508975982666, "global_step": 452780, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0416321754455566, "global_step": 452781, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0455732345581055, "global_step": 452782, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.147258996963501, "global_step": 452783, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0741231441497803, "global_step": 452784, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0242602825164795, "global_step": 452785, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0471057891845703, "global_step": 452786, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9921550750732422, "global_step": 452787, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0644595623016357, "global_step": 452788, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.153125047683716, "global_step": 452789, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0706756114959717, "global_step": 452790, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.973171591758728, "global_step": 452791, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9741915464401245, "global_step": 452792, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1134467124938965, "global_step": 452793, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.050070285797119, "global_step": 452794, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0113635063171387, "global_step": 452795, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.007871150970459, "global_step": 452796, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9858976602554321, "global_step": 452797, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0789268016815186, "global_step": 452798, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.077082872390747, "global_step": 452799, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1128435134887695, "global_step": 452800, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.046053886413574, "global_step": 452801, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.974636197090149, "global_step": 452802, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.075805902481079, "global_step": 452803, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.075026035308838, "global_step": 452804, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0450048446655273, "global_step": 452805, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0744214057922363, "global_step": 452806, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0537776947021484, "global_step": 452807, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0526585578918457, "global_step": 452808, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0838680267333984, "global_step": 452809, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.064875841140747, "global_step": 452810, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.083014488220215, "global_step": 452811, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.052055835723877, "global_step": 452812, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.080759048461914, "global_step": 452813, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.068593740463257, "global_step": 452814, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.017949104309082, "global_step": 452815, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.062052011489868, "global_step": 452816, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0652916431427, "global_step": 452817, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0119504928588867, "global_step": 452818, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0853524208068848, "global_step": 452819, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.020029306411743, "global_step": 452820, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9728546142578125, "global_step": 452821, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1385841369628906, "global_step": 452822, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9961638450622559, "global_step": 452823, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1170122623443604, "global_step": 452824, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0273425579071045, "global_step": 452825, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1650662422180176, "global_step": 452826, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.124737024307251, "global_step": 452827, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.111340045928955, "global_step": 452828, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9969817399978638, "global_step": 452829, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1766297817230225, "global_step": 452830, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1172239780426025, "global_step": 452831, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0573275089263916, "global_step": 452832, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.07677960395813, "global_step": 452833, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0365607738494873, "global_step": 452834, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1786866188049316, "global_step": 452835, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0890438556671143, "global_step": 452836, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.089118242263794, "global_step": 452837, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0310862064361572, "global_step": 452838, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1340372562408447, "global_step": 452839, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0251986980438232, "global_step": 452840, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.054708957672119, "global_step": 452841, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1323344707489014, "global_step": 452842, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.041031837463379, "global_step": 452843, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.061475992202759, "global_step": 452844, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.029174327850342, "global_step": 452845, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0047335624694824, "global_step": 452846, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0036203861236572, "global_step": 452847, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0397417545318604, "global_step": 452848, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0910356044769287, "global_step": 452849, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0039238929748535, "global_step": 452850, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0944206714630127, "global_step": 452851, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.007363796234131, "global_step": 452852, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0248684883117676, "global_step": 452853, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1175668239593506, "global_step": 452854, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1711835861206055, "global_step": 452855, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.026890754699707, "global_step": 452856, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0947535037994385, "global_step": 452857, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9643257856369019, "global_step": 452858, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.02402925491333, "global_step": 452859, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.124230146408081, "global_step": 452860, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.054412841796875, "global_step": 452861, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.058140516281128, "global_step": 452862, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0656983852386475, "global_step": 452863, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0785136222839355, "global_step": 452864, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0141801834106445, "global_step": 452865, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1063857078552246, "global_step": 452866, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.127253770828247, "global_step": 452867, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0082221031188965, "global_step": 452868, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1362850666046143, "global_step": 452869, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.08953595161438, "global_step": 452870, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1086373329162598, "global_step": 452871, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0689826011657715, "global_step": 452872, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.009006977081299, "global_step": 452873, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0844309329986572, "global_step": 452874, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1310391426086426, "global_step": 452875, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.042003631591797, "global_step": 452876, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0621321201324463, "global_step": 452877, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.03753662109375, "global_step": 452878, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0417685508728027, "global_step": 452879, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0679051876068115, "global_step": 452880, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0122036933898926, "global_step": 452881, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.090451955795288, "global_step": 452882, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1334547996520996, "global_step": 452883, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.012633800506592, "global_step": 452884, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0152089595794678, "global_step": 452885, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.153808116912842, "global_step": 452886, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0885579586029053, "global_step": 452887, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0144259929656982, "global_step": 452888, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0741477012634277, "global_step": 452889, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0347790718078613, "global_step": 452890, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0696136951446533, "global_step": 452891, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.996734380722046, "global_step": 452892, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0842177867889404, "global_step": 452893, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0833945274353027, "global_step": 452894, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0421557426452637, "global_step": 452895, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.129838228225708, "global_step": 452896, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0667052268981934, "global_step": 452897, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.040290117263794, "global_step": 452898, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0834884643554688, "global_step": 452899, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0763494968414307, "global_step": 452900, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9826101064682007, "global_step": 452901, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.128399133682251, "global_step": 452902, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.089144229888916, "global_step": 452903, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0387380123138428, "global_step": 452904, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9970970153808594, "global_step": 452905, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.017918586730957, "global_step": 452906, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.109748363494873, "global_step": 452907, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0762481689453125, "global_step": 452908, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.037837505340576, "global_step": 452909, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0267536640167236, "global_step": 452910, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0970799922943115, "global_step": 452911, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1053502559661865, "global_step": 452912, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.024615526199341, "global_step": 452913, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0840251445770264, "global_step": 452914, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0479869842529297, "global_step": 452915, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0427627563476562, "global_step": 452916, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.11366868019104, "global_step": 452917, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.105090618133545, "global_step": 452918, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.086028575897217, "global_step": 452919, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9945051670074463, "global_step": 452920, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1631479263305664, "global_step": 452921, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.061594247817993, "global_step": 452922, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1015870571136475, "global_step": 452923, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0345993041992188, "global_step": 452924, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0214219093322754, "global_step": 452925, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.020650625228882, "global_step": 452926, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9839744567871094, "global_step": 452927, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0705442428588867, "global_step": 452928, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.025700092315674, "global_step": 452929, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.048264741897583, "global_step": 452930, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9854167699813843, "global_step": 452931, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.124558210372925, "global_step": 452932, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0655596256256104, "global_step": 452933, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0819458961486816, "global_step": 452934, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0317790508270264, "global_step": 452935, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.107231378555298, "global_step": 452936, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.061180830001831, "global_step": 452937, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0332460403442383, "global_step": 452938, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9836294651031494, "global_step": 452939, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1520919799804688, "global_step": 452940, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.047175884246826, "global_step": 452941, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.021596908569336, "global_step": 452942, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0734829902648926, "global_step": 452943, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1296753883361816, "global_step": 452944, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0679702758789062, "global_step": 452945, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.026975393295288, "global_step": 452946, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.097311496734619, "global_step": 452947, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.01896595954895, "global_step": 452948, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0358760356903076, "global_step": 452949, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1125476360321045, "global_step": 452950, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9661551713943481, "global_step": 452951, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0963821411132812, "global_step": 452952, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.111037254333496, "global_step": 452953, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1508049964904785, "global_step": 452954, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0401175022125244, "global_step": 452955, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0788187980651855, "global_step": 452956, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1065759658813477, "global_step": 452957, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.097890615463257, "global_step": 452958, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0214383602142334, "global_step": 452959, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0148379802703857, "global_step": 452960, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0946624279022217, "global_step": 452961, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0602669715881348, "global_step": 452962, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.031933546066284, "global_step": 452963, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0654709339141846, "global_step": 452964, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1783037185668945, "global_step": 452965, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.056190252304077, "global_step": 452966, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.072240114212036, "global_step": 452967, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.135643720626831, "global_step": 452968, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9943525791168213, "global_step": 452969, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1010921001434326, "global_step": 452970, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0858349800109863, "global_step": 452971, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0190157890319824, "global_step": 452972, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1300201416015625, "global_step": 452973, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.050908327102661, "global_step": 452974, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0145397186279297, "global_step": 452975, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.142888307571411, "global_step": 452976, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.062260389328003, "global_step": 452977, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.069464683532715, "global_step": 452978, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0313117504119873, "global_step": 452979, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.119865655899048, "global_step": 452980, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1019554138183594, "global_step": 452981, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.125802755355835, "global_step": 452982, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.091259717941284, "global_step": 452983, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.151026487350464, "global_step": 452984, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0029332637786865, "global_step": 452985, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.06091570854187, "global_step": 452986, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0122575759887695, "global_step": 452987, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0706968307495117, "global_step": 452988, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0459237098693848, "global_step": 452989, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1179921627044678, "global_step": 452990, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0871477127075195, "global_step": 452991, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0448811054229736, "global_step": 452992, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0651233196258545, "global_step": 452993, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0787200927734375, "global_step": 452994, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.08911395072937, "global_step": 452995, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.090792417526245, "global_step": 452996, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.015291929244995, "global_step": 452997, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.085472822189331, "global_step": 452998, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0576388835906982, "global_step": 452999, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.047593355178833, "global_step": 453000, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.121659755706787, "global_step": 453001, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.091571569442749, "global_step": 453002, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.023390293121338, "global_step": 453003, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.09208607673645, "global_step": 453004, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0974442958831787, "global_step": 453005, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.24991774559021, "global_step": 453006, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0938003063201904, "global_step": 453007, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0439682006835938, "global_step": 453008, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9995990991592407, "global_step": 453009, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0816173553466797, "global_step": 453010, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.062298059463501, "global_step": 453011, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.063699722290039, "global_step": 453012, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1070289611816406, "global_step": 453013, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.065746545791626, "global_step": 453014, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.048598289489746, "global_step": 453015, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1076126098632812, "global_step": 453016, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.082792282104492, "global_step": 453017, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.034990072250366, "global_step": 453018, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.019911289215088, "global_step": 453019, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.996650218963623, "global_step": 453020, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.103576421737671, "global_step": 453021, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.117032527923584, "global_step": 453022, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1830456256866455, "global_step": 453023, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.15317964553833, "global_step": 453024, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0736701488494873, "global_step": 453025, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1305017471313477, "global_step": 453026, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.061279296875, "global_step": 453027, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.137178897857666, "global_step": 453028, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9556739330291748, "global_step": 453029, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1604690551757812, "global_step": 453030, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.012132167816162, "global_step": 453031, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.160846471786499, "global_step": 453032, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.02191162109375, "global_step": 453033, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0989086627960205, "global_step": 453034, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.052157402038574, "global_step": 453035, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0653977394104004, "global_step": 453036, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.072279691696167, "global_step": 453037, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9628846645355225, "global_step": 453038, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.03579044342041, "global_step": 453039, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0271553993225098, "global_step": 453040, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.120194911956787, "global_step": 453041, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0663113594055176, "global_step": 453042, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.021460771560669, "global_step": 453043, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0601611137390137, "global_step": 453044, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0212104320526123, "global_step": 453045, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0893330574035645, "global_step": 453046, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1745684146881104, "global_step": 453047, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.114140510559082, "global_step": 453048, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9446340799331665, "global_step": 453049, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1376543045043945, "global_step": 453050, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1551599502563477, "global_step": 453051, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.015843629837036, "global_step": 453052, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.128913640975952, "global_step": 453053, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.054603338241577, "global_step": 453054, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1812384128570557, "global_step": 453055, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0760951042175293, "global_step": 453056, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.032287359237671, "global_step": 453057, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9911549091339111, "global_step": 453058, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.069349765777588, "global_step": 453059, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0560221672058105, "global_step": 453060, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.098939895629883, "global_step": 453061, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.972503423690796, "global_step": 453062, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0962538719177246, "global_step": 453063, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.112225294113159, "global_step": 453064, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.06117582321167, "global_step": 453065, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1104917526245117, "global_step": 453066, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0519216060638428, "global_step": 453067, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0152835845947266, "global_step": 453068, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0111639499664307, "global_step": 453069, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.2493743896484375, "global_step": 453070, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.094186305999756, "global_step": 453071, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9871138334274292, "global_step": 453072, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9841678142547607, "global_step": 453073, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.106537342071533, "global_step": 453074, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.030545949935913, "global_step": 453075, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.003206729888916, "global_step": 453076, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0502686500549316, "global_step": 453077, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0828700065612793, "global_step": 453078, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.054255723953247, "global_step": 453079, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.060697078704834, "global_step": 453080, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0500857830047607, "global_step": 453081, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1191844940185547, "global_step": 453082, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1411406993865967, "global_step": 453083, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0460853576660156, "global_step": 453084, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1046998500823975, "global_step": 453085, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1250321865081787, "global_step": 453086, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.073326587677002, "global_step": 453087, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.089395046234131, "global_step": 453088, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.043113946914673, "global_step": 453089, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.087283134460449, "global_step": 453090, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.051309108734131, "global_step": 453091, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0514142513275146, "global_step": 453092, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.010160446166992, "global_step": 453093, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.137956142425537, "global_step": 453094, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1197969913482666, "global_step": 453095, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.11069655418396, "global_step": 453096, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.170630693435669, "global_step": 453097, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0845162868499756, "global_step": 453098, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.11118483543396, "global_step": 453099, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.042846918106079, "global_step": 453100, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.142098903656006, "global_step": 453101, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0406830310821533, "global_step": 453102, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0795321464538574, "global_step": 453103, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0246241092681885, "global_step": 453104, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.032984972000122, "global_step": 453105, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.017005205154419, "global_step": 453106, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.09965181350708, "global_step": 453107, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0633206367492676, "global_step": 453108, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9638187885284424, "global_step": 453109, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0901029109954834, "global_step": 453110, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.116719961166382, "global_step": 453111, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0799262523651123, "global_step": 453112, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0223231315612793, "global_step": 453113, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0033438205718994, "global_step": 453114, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0325005054473877, "global_step": 453115, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.029761791229248, "global_step": 453116, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9728050231933594, "global_step": 453117, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0352118015289307, "global_step": 453118, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0197341442108154, "global_step": 453119, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.013338565826416, "global_step": 453120, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.101320505142212, "global_step": 453121, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1409051418304443, "global_step": 453122, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.038007974624634, "global_step": 453123, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1864590644836426, "global_step": 453124, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9680534601211548, "global_step": 453125, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1475090980529785, "global_step": 453126, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.051877975463867, "global_step": 453127, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.013962745666504, "global_step": 453128, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.093433380126953, "global_step": 453129, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.070474863052368, "global_step": 453130, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0957586765289307, "global_step": 453131, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1461260318756104, "global_step": 453132, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.025668144226074, "global_step": 453133, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.067227602005005, "global_step": 453134, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0665297508239746, "global_step": 453135, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0459647178649902, "global_step": 453136, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.141735792160034, "global_step": 453137, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1417722702026367, "global_step": 453138, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.026113271713257, "global_step": 453139, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0739424228668213, "global_step": 453140, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0471372604370117, "global_step": 453141, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0985867977142334, "global_step": 453142, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1184277534484863, "global_step": 453143, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.050206422805786, "global_step": 453144, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0450918674468994, "global_step": 453145, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0425524711608887, "global_step": 453146, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0614840984344482, "global_step": 453147, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.05723237991333, "global_step": 453148, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1457221508026123, "global_step": 453149, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9728995561599731, "global_step": 453150, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.11732816696167, "global_step": 453151, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0581750869750977, "global_step": 453152, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0739481449127197, "global_step": 453153, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0444893836975098, "global_step": 453154, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0125110149383545, "global_step": 453155, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.138338088989258, "global_step": 453156, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.025129795074463, "global_step": 453157, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.045117139816284, "global_step": 453158, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1076126098632812, "global_step": 453159, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.146968126296997, "global_step": 453160, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0197343826293945, "global_step": 453161, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.017148017883301, "global_step": 453162, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.03330659866333, "global_step": 453163, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.04868745803833, "global_step": 453164, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0764780044555664, "global_step": 453165, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.084697961807251, "global_step": 453166, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9927295446395874, "global_step": 453167, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.083798885345459, "global_step": 453168, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.00909423828125, "global_step": 453169, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.047664165496826, "global_step": 453170, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.032567024230957, "global_step": 453171, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0247042179107666, "global_step": 453172, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1660807132720947, "global_step": 453173, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.018460512161255, "global_step": 453174, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0495667457580566, "global_step": 453175, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.143747568130493, "global_step": 453176, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0846407413482666, "global_step": 453177, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1457226276397705, "global_step": 453178, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.06030011177063, "global_step": 453179, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0226359367370605, "global_step": 453180, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9953407049179077, "global_step": 453181, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.088499069213867, "global_step": 453182, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0907459259033203, "global_step": 453183, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0207698345184326, "global_step": 453184, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.047778367996216, "global_step": 453185, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1211659908294678, "global_step": 453186, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9780497550964355, "global_step": 453187, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.086846113204956, "global_step": 453188, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0742268562316895, "global_step": 453189, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0762126445770264, "global_step": 453190, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0207624435424805, "global_step": 453191, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9461767673492432, "global_step": 453192, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1350624561309814, "global_step": 453193, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1292777061462402, "global_step": 453194, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.146955728530884, "global_step": 453195, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.147103786468506, "global_step": 453196, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0735604763031006, "global_step": 453197, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.078263282775879, "global_step": 453198, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0882928371429443, "global_step": 453199, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1599693298339844, "global_step": 453200, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1145975589752197, "global_step": 453201, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0997140407562256, "global_step": 453202, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0338644981384277, "global_step": 453203, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.172549247741699, "global_step": 453204, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1742796897888184, "global_step": 453205, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0641698837280273, "global_step": 453206, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0226292610168457, "global_step": 453207, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0431690216064453, "global_step": 453208, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.049454689025879, "global_step": 453209, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0932350158691406, "global_step": 453210, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.08902907371521, "global_step": 453211, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.053614854812622, "global_step": 453212, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.10317063331604, "global_step": 453213, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0678038597106934, "global_step": 453214, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.110851287841797, "global_step": 453215, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.074763059616089, "global_step": 453216, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0684280395507812, "global_step": 453217, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1119587421417236, "global_step": 453218, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0658345222473145, "global_step": 453219, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1049063205718994, "global_step": 453220, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9504154920578003, "global_step": 453221, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.099804639816284, "global_step": 453222, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0701425075531006, "global_step": 453223, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.052218198776245, "global_step": 453224, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.015284299850464, "global_step": 453225, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0684072971343994, "global_step": 453226, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0927438735961914, "global_step": 453227, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.089721202850342, "global_step": 453228, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1026298999786377, "global_step": 453229, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0034942626953125, "global_step": 453230, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1002633571624756, "global_step": 453231, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.121701955795288, "global_step": 453232, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1270220279693604, "global_step": 453233, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9906318187713623, "global_step": 453234, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.057352066040039, "global_step": 453235, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0430071353912354, "global_step": 453236, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.027249813079834, "global_step": 453237, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.158957004547119, "global_step": 453238, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.155527353286743, "global_step": 453239, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.079413890838623, "global_step": 453240, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.088754653930664, "global_step": 453241, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.023087501525879, "global_step": 453242, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1155025959014893, "global_step": 453243, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.041261911392212, "global_step": 453244, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.048858880996704, "global_step": 453245, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9951155185699463, "global_step": 453246, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.043260335922241, "global_step": 453247, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.090674877166748, "global_step": 453248, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.085437536239624, "global_step": 453249, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1344149112701416, "global_step": 453250, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0373518466949463, "global_step": 453251, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9627031087875366, "global_step": 453252, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.136826992034912, "global_step": 453253, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0528616905212402, "global_step": 453254, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.047340154647827, "global_step": 453255, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.006544589996338, "global_step": 453256, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0113775730133057, "global_step": 453257, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0770645141601562, "global_step": 453258, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1114344596862793, "global_step": 453259, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0112836360931396, "global_step": 453260, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1193201541900635, "global_step": 453261, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1187312602996826, "global_step": 453262, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0187323093414307, "global_step": 453263, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0889523029327393, "global_step": 453264, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0732150077819824, "global_step": 453265, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.060389757156372, "global_step": 453266, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1151344776153564, "global_step": 453267, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0658669471740723, "global_step": 453268, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.105649709701538, "global_step": 453269, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0743539333343506, "global_step": 453270, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0396602153778076, "global_step": 453271, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.115435838699341, "global_step": 453272, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.188793182373047, "global_step": 453273, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1086182594299316, "global_step": 453274, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.125831365585327, "global_step": 453275, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.073361396789551, "global_step": 453276, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.024963855743408, "global_step": 453277, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.107786178588867, "global_step": 453278, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0166382789611816, "global_step": 453279, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.099276542663574, "global_step": 453280, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.074103355407715, "global_step": 453281, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.15263295173645, "global_step": 453282, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.993632435798645, "global_step": 453283, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9888091087341309, "global_step": 453284, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0956432819366455, "global_step": 453285, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1368420124053955, "global_step": 453286, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.00296950340271, "global_step": 453287, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.162348508834839, "global_step": 453288, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.014087677001953, "global_step": 453289, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.083597183227539, "global_step": 453290, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.045828104019165, "global_step": 453291, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0983691215515137, "global_step": 453292, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0577542781829834, "global_step": 453293, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1290040016174316, "global_step": 453294, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.087139368057251, "global_step": 453295, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.039022445678711, "global_step": 453296, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.060499906539917, "global_step": 453297, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0651323795318604, "global_step": 453298, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0581178665161133, "global_step": 453299, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.001894950866699, "global_step": 453300, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0932440757751465, "global_step": 453301, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.135605812072754, "global_step": 453302, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.11728572845459, "global_step": 453303, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.022773265838623, "global_step": 453304, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.114665985107422, "global_step": 453305, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.092180013656616, "global_step": 453306, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.055270195007324, "global_step": 453307, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.050431728363037, "global_step": 453308, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1077451705932617, "global_step": 453309, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.068127393722534, "global_step": 453310, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.052971124649048, "global_step": 453311, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0551421642303467, "global_step": 453312, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.052027702331543, "global_step": 453313, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1384122371673584, "global_step": 453314, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.076829195022583, "global_step": 453315, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0870745182037354, "global_step": 453316, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.025334119796753, "global_step": 453317, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0837085247039795, "global_step": 453318, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.11380934715271, "global_step": 453319, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.074397087097168, "global_step": 453320, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.159834146499634, "global_step": 453321, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1465365886688232, "global_step": 453322, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.006868600845337, "global_step": 453323, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0636565685272217, "global_step": 453324, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0831189155578613, "global_step": 453325, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.095148801803589, "global_step": 453326, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.022016763687134, "global_step": 453327, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.107008695602417, "global_step": 453328, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.150177478790283, "global_step": 453329, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1165077686309814, "global_step": 453330, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0683557987213135, "global_step": 453331, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.043224334716797, "global_step": 453332, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0700836181640625, "global_step": 453333, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.096498489379883, "global_step": 453334, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0925726890563965, "global_step": 453335, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.050750970840454, "global_step": 453336, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.196946859359741, "global_step": 453337, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.130422830581665, "global_step": 453338, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0333092212677, "global_step": 453339, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.023759365081787, "global_step": 453340, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0443575382232666, "global_step": 453341, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1063857078552246, "global_step": 453342, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0440165996551514, "global_step": 453343, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.033355236053467, "global_step": 453344, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1386685371398926, "global_step": 453345, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1572329998016357, "global_step": 453346, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.125483751296997, "global_step": 453347, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0205042362213135, "global_step": 453348, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.017648458480835, "global_step": 453349, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.123734712600708, "global_step": 453350, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0948448181152344, "global_step": 453351, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1570944786071777, "global_step": 453352, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9996514320373535, "global_step": 453353, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0916759967803955, "global_step": 453354, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.045644998550415, "global_step": 453355, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.2231173515319824, "global_step": 453356, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.066267490386963, "global_step": 453357, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0266666412353516, "global_step": 453358, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0476038455963135, "global_step": 453359, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1377718448638916, "global_step": 453360, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1025314331054688, "global_step": 453361, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0235755443573, "global_step": 453362, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0243778228759766, "global_step": 453363, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1122090816497803, "global_step": 453364, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.954586386680603, "global_step": 453365, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1215758323669434, "global_step": 453366, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.037754535675049, "global_step": 453367, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.084743022918701, "global_step": 453368, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0133352279663086, "global_step": 453369, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0765061378479004, "global_step": 453370, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1884729862213135, "global_step": 453371, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.101949453353882, "global_step": 453372, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1645286083221436, "global_step": 453373, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0020968914031982, "global_step": 453374, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1282548904418945, "global_step": 453375, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.126607894897461, "global_step": 453376, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.10994029045105, "global_step": 453377, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0590128898620605, "global_step": 453378, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0974221229553223, "global_step": 453379, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0591626167297363, "global_step": 453380, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.020251512527466, "global_step": 453381, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1103293895721436, "global_step": 453382, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0927655696868896, "global_step": 453383, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0574138164520264, "global_step": 453384, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1273295879364014, "global_step": 453385, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0586743354797363, "global_step": 453386, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1071207523345947, "global_step": 453387, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0220584869384766, "global_step": 453388, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1503193378448486, "global_step": 453389, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.077889919281006, "global_step": 453390, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.042555332183838, "global_step": 453391, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.034123659133911, "global_step": 453392, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.090557813644409, "global_step": 453393, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1558597087860107, "global_step": 453394, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.007342576980591, "global_step": 453395, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.097020149230957, "global_step": 453396, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0589420795440674, "global_step": 453397, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.2205452919006348, "global_step": 453398, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.044867753982544, "global_step": 453399, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.123967170715332, "global_step": 453400, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9154711961746216, "global_step": 453401, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0725393295288086, "global_step": 453402, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.114262580871582, "global_step": 453403, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1170341968536377, "global_step": 453404, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9629982709884644, "global_step": 453405, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1142377853393555, "global_step": 453406, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1041393280029297, "global_step": 453407, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0445871353149414, "global_step": 453408, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1008949279785156, "global_step": 453409, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.139887571334839, "global_step": 453410, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.073441505432129, "global_step": 453411, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.049147367477417, "global_step": 453412, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9866583347320557, "global_step": 453413, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1059553623199463, "global_step": 453414, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.211881160736084, "global_step": 453415, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0351526737213135, "global_step": 453416, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0751399993896484, "global_step": 453417, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0223684310913086, "global_step": 453418, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.08876633644104, "global_step": 453419, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0692503452301025, "global_step": 453420, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9907803535461426, "global_step": 453421, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.122483968734741, "global_step": 453422, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.027106285095215, "global_step": 453423, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0651798248291016, "global_step": 453424, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0111804008483887, "global_step": 453425, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0628321170806885, "global_step": 453426, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.005398750305176, "global_step": 453427, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1633870601654053, "global_step": 453428, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1260898113250732, "global_step": 453429, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0000696182250977, "global_step": 453430, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.090951681137085, "global_step": 453431, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.118421792984009, "global_step": 453432, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.082756280899048, "global_step": 453433, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.078117609024048, "global_step": 453434, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0337820053100586, "global_step": 453435, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.037224769592285, "global_step": 453436, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.081087589263916, "global_step": 453437, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0863027572631836, "global_step": 453438, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0413320064544678, "global_step": 453439, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1261868476867676, "global_step": 453440, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.022785186767578, "global_step": 453441, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0512855052948, "global_step": 453442, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.09515643119812, "global_step": 453443, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.082305431365967, "global_step": 453444, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0469608306884766, "global_step": 453445, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0504283905029297, "global_step": 453446, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.023120641708374, "global_step": 453447, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0565192699432373, "global_step": 453448, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.024092435836792, "global_step": 453449, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.140497922897339, "global_step": 453450, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.033700942993164, "global_step": 453451, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.153151512145996, "global_step": 453452, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0699844360351562, "global_step": 453453, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1190316677093506, "global_step": 453454, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.032597541809082, "global_step": 453455, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0741617679595947, "global_step": 453456, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0881776809692383, "global_step": 453457, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0636651515960693, "global_step": 453458, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9542577266693115, "global_step": 453459, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0767674446105957, "global_step": 453460, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0550081729888916, "global_step": 453461, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.119844675064087, "global_step": 453462, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0866785049438477, "global_step": 453463, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0601353645324707, "global_step": 453464, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1083414554595947, "global_step": 453465, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1246485710144043, "global_step": 453466, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0335164070129395, "global_step": 453467, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.02915096282959, "global_step": 453468, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1393964290618896, "global_step": 453469, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0663585662841797, "global_step": 453470, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0625429153442383, "global_step": 453471, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0133533477783203, "global_step": 453472, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1530673503875732, "global_step": 453473, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0897159576416016, "global_step": 453474, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0227346420288086, "global_step": 453475, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.125645399093628, "global_step": 453476, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9864528179168701, "global_step": 453477, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0543370246887207, "global_step": 453478, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0537643432617188, "global_step": 453479, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1163101196289062, "global_step": 453480, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0947325229644775, "global_step": 453481, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.2142727375030518, "global_step": 453482, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9917476177215576, "global_step": 453483, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0153322219848633, "global_step": 453484, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.099607467651367, "global_step": 453485, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0235774517059326, "global_step": 453486, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0266740322113037, "global_step": 453487, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1161861419677734, "global_step": 453488, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0549683570861816, "global_step": 453489, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.072129487991333, "global_step": 453490, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1173486709594727, "global_step": 453491, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0997204780578613, "global_step": 453492, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1032276153564453, "global_step": 453493, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1473217010498047, "global_step": 453494, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.081691265106201, "global_step": 453495, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0745766162872314, "global_step": 453496, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.090179681777954, "global_step": 453497, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1748733520507812, "global_step": 453498, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0040576457977295, "global_step": 453499, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.038102149963379, "global_step": 453500, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0514211654663086, "global_step": 453501, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0918896198272705, "global_step": 453502, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0799381732940674, "global_step": 453503, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.028597593307495, "global_step": 453504, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.01592755317688, "global_step": 453505, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0491065979003906, "global_step": 453506, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1096627712249756, "global_step": 453507, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.078555107116699, "global_step": 453508, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1455330848693848, "global_step": 453509, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0924253463745117, "global_step": 453510, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1133203506469727, "global_step": 453511, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9817157983779907, "global_step": 453512, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.081676483154297, "global_step": 453513, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0630903244018555, "global_step": 453514, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9838371276855469, "global_step": 453515, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.028360605239868, "global_step": 453516, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0818593502044678, "global_step": 453517, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.090907096862793, "global_step": 453518, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.066246747970581, "global_step": 453519, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.977647304534912, "global_step": 453520, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.124480724334717, "global_step": 453521, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.089081048965454, "global_step": 453522, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0058834552764893, "global_step": 453523, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.033158540725708, "global_step": 453524, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.097093343734741, "global_step": 453525, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.12208890914917, "global_step": 453526, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.099252939224243, "global_step": 453527, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.128053903579712, "global_step": 453528, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0647828578948975, "global_step": 453529, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.089506149291992, "global_step": 453530, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1648569107055664, "global_step": 453531, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0988423824310303, "global_step": 453532, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0935990810394287, "global_step": 453533, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0860097408294678, "global_step": 453534, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1345295906066895, "global_step": 453535, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.014349937438965, "global_step": 453536, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.084988832473755, "global_step": 453537, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1222479343414307, "global_step": 453538, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1270737648010254, "global_step": 453539, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.06425142288208, "global_step": 453540, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.087113380432129, "global_step": 453541, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.19616436958313, "global_step": 453542, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.056079864501953, "global_step": 453543, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1060523986816406, "global_step": 453544, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.979893445968628, "global_step": 453545, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.053436040878296, "global_step": 453546, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0456461906433105, "global_step": 453547, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1217093467712402, "global_step": 453548, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.047708034515381, "global_step": 453549, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0072286128997803, "global_step": 453550, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1877048015594482, "global_step": 453551, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0169248580932617, "global_step": 453552, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0377931594848633, "global_step": 453553, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.028369665145874, "global_step": 453554, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0847954750061035, "global_step": 453555, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.024590253829956, "global_step": 453556, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0324103832244873, "global_step": 453557, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1768617630004883, "global_step": 453558, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0876054763793945, "global_step": 453559, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0566296577453613, "global_step": 453560, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.129856824874878, "global_step": 453561, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0806033611297607, "global_step": 453562, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0606870651245117, "global_step": 453563, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.180192232131958, "global_step": 453564, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0032854080200195, "global_step": 453565, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.98954439163208, "global_step": 453566, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0228559970855713, "global_step": 453567, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0267505645751953, "global_step": 453568, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0767714977264404, "global_step": 453569, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1450092792510986, "global_step": 453570, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.069309949874878, "global_step": 453571, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.065284252166748, "global_step": 453572, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.026289463043213, "global_step": 453573, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.045769214630127, "global_step": 453574, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0624654293060303, "global_step": 453575, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0381007194519043, "global_step": 453576, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.105041265487671, "global_step": 453577, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0896408557891846, "global_step": 453578, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1647303104400635, "global_step": 453579, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.036835193634033, "global_step": 453580, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.079983711242676, "global_step": 453581, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.066476345062256, "global_step": 453582, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.11077880859375, "global_step": 453583, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.052527904510498, "global_step": 453584, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0688202381134033, "global_step": 453585, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.113036870956421, "global_step": 453586, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0653531551361084, "global_step": 453587, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1466081142425537, "global_step": 453588, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0088658332824707, "global_step": 453589, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0064728260040283, "global_step": 453590, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0838959217071533, "global_step": 453591, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0329434871673584, "global_step": 453592, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0950543880462646, "global_step": 453593, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.056725263595581, "global_step": 453594, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1088178157806396, "global_step": 453595, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1302003860473633, "global_step": 453596, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.088066339492798, "global_step": 453597, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.122500419616699, "global_step": 453598, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0491230487823486, "global_step": 453599, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1271908283233643, "global_step": 453600, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.051793098449707, "global_step": 453601, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.096781015396118, "global_step": 453602, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.1345458030700684, "global_step": 453603, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.98304283618927, "global_step": 453604, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.117676258087158, "global_step": 453605, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0115156173706055, "global_step": 453606, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.041203498840332, "global_step": 453607, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.078505039215088, "global_step": 453608, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.097234010696411, "global_step": 453609, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0049993991851807, "global_step": 453610, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.105827569961548, "global_step": 453611, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0504627227783203, "global_step": 453612, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.070347309112549, "global_step": 453613, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.085792303085327, "global_step": 453614, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.03861927986145, "global_step": 453615, "epoch": 817, "lr": 5e-05}
{"train_loss": 1.9997026920318604, "global_step": 453616, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0782310962677, "global_step": 453617, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0323405265808105, "global_step": 453618, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.072211503982544, "global_step": 453619, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.122952938079834, "global_step": 453620, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0910024642944336, "global_step": 453621, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.078152656555176, "global_step": 453622, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.0323402881622314, "global_step": 453623, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.070416212081909, "global_step": 453624, "epoch": 817, "lr": 5e-05}
{"train_loss": 2.050675392150879, "global_step": 453625, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.002357244491577, "global_step": 453626, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0856516361236572, "global_step": 453627, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0143184661865234, "global_step": 453628, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.972362995147705, "global_step": 453629, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0250673294067383, "global_step": 453630, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.110093116760254, "global_step": 453631, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.143972396850586, "global_step": 453632, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.022027015686035, "global_step": 453633, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0627567768096924, "global_step": 453634, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.077218532562256, "global_step": 453635, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1032814979553223, "global_step": 453636, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0429563522338867, "global_step": 453637, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0077221393585205, "global_step": 453638, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.104496479034424, "global_step": 453639, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.128504991531372, "global_step": 453640, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.106623888015747, "global_step": 453641, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0758883953094482, "global_step": 453642, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1015002727508545, "global_step": 453643, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.103137254714966, "global_step": 453644, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0945827960968018, "global_step": 453645, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0769076347351074, "global_step": 453646, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.017456531524658, "global_step": 453647, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.180095911026001, "global_step": 453648, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1430280208587646, "global_step": 453649, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1171622276306152, "global_step": 453650, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.073568105697632, "global_step": 453651, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.001603364944458, "global_step": 453652, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9980096817016602, "global_step": 453653, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0009214878082275, "global_step": 453654, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0018742084503174, "global_step": 453655, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1380906105041504, "global_step": 453656, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0928587913513184, "global_step": 453657, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0576224327087402, "global_step": 453658, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0093801021575928, "global_step": 453659, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0380680561065674, "global_step": 453660, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0142385959625244, "global_step": 453661, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.959762454032898, "global_step": 453662, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.082655429840088, "global_step": 453663, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.014784574508667, "global_step": 453664, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.172584295272827, "global_step": 453665, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.04718017578125, "global_step": 453666, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0763418674468994, "global_step": 453667, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1283223628997803, "global_step": 453668, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.13608455657959, "global_step": 453669, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1003787517547607, "global_step": 453670, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1208527088165283, "global_step": 453671, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0962212085723877, "global_step": 453672, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.044682025909424, "global_step": 453673, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0248873233795166, "global_step": 453674, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1271822452545166, "global_step": 453675, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0383694171905518, "global_step": 453676, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1579601764678955, "global_step": 453677, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.030329942703247, "global_step": 453678, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0564520359039307, "global_step": 453679, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.058285713195801, "global_step": 453680, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0006542205810547, "global_step": 453681, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.015977621078491, "global_step": 453682, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0621719360351562, "global_step": 453683, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.083015203475952, "global_step": 453684, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1039583683013916, "global_step": 453685, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.001119613647461, "global_step": 453686, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.007417917251587, "global_step": 453687, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0087320804595947, "global_step": 453688, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.10837984085083, "global_step": 453689, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.032611608505249, "global_step": 453690, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.050067186355591, "global_step": 453691, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.036750555038452, "global_step": 453692, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1054530143737793, "global_step": 453693, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.088574171066284, "global_step": 453694, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0634987354278564, "global_step": 453695, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0011954307556152, "global_step": 453696, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9678866863250732, "global_step": 453697, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9938009977340698, "global_step": 453698, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.061344623565674, "global_step": 453699, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.123284101486206, "global_step": 453700, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0554752349853516, "global_step": 453701, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0462300777435303, "global_step": 453702, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0478625297546387, "global_step": 453703, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.041027545928955, "global_step": 453704, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0912821292877197, "global_step": 453705, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.025113582611084, "global_step": 453706, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0481550693511963, "global_step": 453707, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1046805381774902, "global_step": 453708, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0756828784942627, "global_step": 453709, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.11362361907959, "global_step": 453710, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9848133325576782, "global_step": 453711, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.037337064743042, "global_step": 453712, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.073279619216919, "global_step": 453713, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0577220916748047, "global_step": 453714, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1168811321258545, "global_step": 453715, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0424413681030273, "global_step": 453716, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.969972848892212, "global_step": 453717, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0155482292175293, "global_step": 453718, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0497024059295654, "global_step": 453719, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0688540935516357, "global_step": 453720, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.018397569656372, "global_step": 453721, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0793216228485107, "global_step": 453722, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0402681827545166, "global_step": 453723, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.123016834259033, "global_step": 453724, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.041038990020752, "global_step": 453725, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.011686325073242, "global_step": 453726, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0605924129486084, "global_step": 453727, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0194549560546875, "global_step": 453728, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0861587524414062, "global_step": 453729, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1095669269561768, "global_step": 453730, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9856070280075073, "global_step": 453731, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1435353755950928, "global_step": 453732, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.010359764099121, "global_step": 453733, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0374228954315186, "global_step": 453734, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.071045398712158, "global_step": 453735, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0940990447998047, "global_step": 453736, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.022784948348999, "global_step": 453737, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0512402057647705, "global_step": 453738, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0575006008148193, "global_step": 453739, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0849931240081787, "global_step": 453740, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1155219078063965, "global_step": 453741, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0336623191833496, "global_step": 453742, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0785791873931885, "global_step": 453743, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.064850091934204, "global_step": 453744, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9855146408081055, "global_step": 453745, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.02852463722229, "global_step": 453746, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.040736436843872, "global_step": 453747, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.082869052886963, "global_step": 453748, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.072439432144165, "global_step": 453749, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.003861665725708, "global_step": 453750, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0578856468200684, "global_step": 453751, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.12276029586792, "global_step": 453752, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.059735059738159, "global_step": 453753, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9893044233322144, "global_step": 453754, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0218276977539062, "global_step": 453755, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1220853328704834, "global_step": 453756, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0363574028015137, "global_step": 453757, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.105257272720337, "global_step": 453758, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.051865339279175, "global_step": 453759, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.111694574356079, "global_step": 453760, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.055652618408203, "global_step": 453761, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0422298908233643, "global_step": 453762, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1134533882141113, "global_step": 453763, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.035149335861206, "global_step": 453764, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1072585582733154, "global_step": 453765, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.078935146331787, "global_step": 453766, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0321903228759766, "global_step": 453767, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0543951988220215, "global_step": 453768, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.032571315765381, "global_step": 453769, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0433156490325928, "global_step": 453770, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.043335199356079, "global_step": 453771, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0490877628326416, "global_step": 453772, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0049636363983154, "global_step": 453773, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0799264907836914, "global_step": 453774, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0188467502593994, "global_step": 453775, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.09578537940979, "global_step": 453776, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.125767707824707, "global_step": 453777, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9682855606079102, "global_step": 453778, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9945564270019531, "global_step": 453779, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.023113250732422, "global_step": 453780, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9977061748504639, "global_step": 453781, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0659940242767334, "global_step": 453782, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.003173828125, "global_step": 453783, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1336259841918945, "global_step": 453784, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.099905252456665, "global_step": 453785, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0440969467163086, "global_step": 453786, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1371917724609375, "global_step": 453787, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.068392515182495, "global_step": 453788, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1321754455566406, "global_step": 453789, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.117398262023926, "global_step": 453790, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.034473419189453, "global_step": 453791, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0611214637756348, "global_step": 453792, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.973375916481018, "global_step": 453793, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9952354431152344, "global_step": 453794, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0772769451141357, "global_step": 453795, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9944707155227661, "global_step": 453796, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9971176385879517, "global_step": 453797, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.069683313369751, "global_step": 453798, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0374255180358887, "global_step": 453799, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1032495498657227, "global_step": 453800, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.091104745864868, "global_step": 453801, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0583841800689697, "global_step": 453802, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9972469806671143, "global_step": 453803, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0364880561828613, "global_step": 453804, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.033709764480591, "global_step": 453805, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.085956573486328, "global_step": 453806, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0075719356536865, "global_step": 453807, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1006548404693604, "global_step": 453808, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.088719367980957, "global_step": 453809, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.111043691635132, "global_step": 453810, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.052964925765991, "global_step": 453811, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.968916416168213, "global_step": 453812, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0322604179382324, "global_step": 453813, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.117581605911255, "global_step": 453814, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.075190544128418, "global_step": 453815, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1367788314819336, "global_step": 453816, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1758615970611572, "global_step": 453817, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0287599563598633, "global_step": 453818, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.030302047729492, "global_step": 453819, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0400962829589844, "global_step": 453820, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.100707769393921, "global_step": 453821, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.04060435295105, "global_step": 453822, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.192648410797119, "global_step": 453823, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.041121006011963, "global_step": 453824, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1085493564605713, "global_step": 453825, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0876457691192627, "global_step": 453826, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9390687942504883, "global_step": 453827, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9382672309875488, "global_step": 453828, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1102914810180664, "global_step": 453829, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.098543643951416, "global_step": 453830, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1034891605377197, "global_step": 453831, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.116563320159912, "global_step": 453832, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0087971687316895, "global_step": 453833, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9701294898986816, "global_step": 453834, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9522749185562134, "global_step": 453835, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.064462184906006, "global_step": 453836, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.078511953353882, "global_step": 453837, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.084256649017334, "global_step": 453838, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1049163341522217, "global_step": 453839, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.117962121963501, "global_step": 453840, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.016545534133911, "global_step": 453841, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.030480146408081, "global_step": 453842, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.061237096786499, "global_step": 453843, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0849647521972656, "global_step": 453844, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9892204999923706, "global_step": 453845, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.107128381729126, "global_step": 453846, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.013805389404297, "global_step": 453847, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0588583946228027, "global_step": 453848, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.085637331008911, "global_step": 453849, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.077951669692993, "global_step": 453850, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.108600378036499, "global_step": 453851, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0063130855560303, "global_step": 453852, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.094390869140625, "global_step": 453853, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.051816940307617, "global_step": 453854, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.943995714187622, "global_step": 453855, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.113147258758545, "global_step": 453856, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0335769653320312, "global_step": 453857, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.072575569152832, "global_step": 453858, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.138803243637085, "global_step": 453859, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0147266387939453, "global_step": 453860, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0269997119903564, "global_step": 453861, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.077817916870117, "global_step": 453862, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0069878101348877, "global_step": 453863, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.115760087966919, "global_step": 453864, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1051623821258545, "global_step": 453865, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0609984397888184, "global_step": 453866, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0912892818450928, "global_step": 453867, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0506696701049805, "global_step": 453868, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.105417251586914, "global_step": 453869, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1502718925476074, "global_step": 453870, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.007190704345703, "global_step": 453871, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1072375774383545, "global_step": 453872, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.139446258544922, "global_step": 453873, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.154412269592285, "global_step": 453874, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.06610369682312, "global_step": 453875, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0272817611694336, "global_step": 453876, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0977046489715576, "global_step": 453877, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0075507164001465, "global_step": 453878, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0530760288238525, "global_step": 453879, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.108203411102295, "global_step": 453880, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.092574119567871, "global_step": 453881, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1020102500915527, "global_step": 453882, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0547902584075928, "global_step": 453883, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9907886981964111, "global_step": 453884, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0662429332733154, "global_step": 453885, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1654908657073975, "global_step": 453886, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.933246374130249, "global_step": 453887, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.032435178756714, "global_step": 453888, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9925358295440674, "global_step": 453889, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.090792655944824, "global_step": 453890, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0653464794158936, "global_step": 453891, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.081383466720581, "global_step": 453892, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.056952714920044, "global_step": 453893, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9661304950714111, "global_step": 453894, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1497950553894043, "global_step": 453895, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.034119129180908, "global_step": 453896, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0858707427978516, "global_step": 453897, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0512642860412598, "global_step": 453898, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0771255493164062, "global_step": 453899, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.000030994415283, "global_step": 453900, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0825164318084717, "global_step": 453901, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.079221725463867, "global_step": 453902, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.028348922729492, "global_step": 453903, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0955374240875244, "global_step": 453904, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9723565578460693, "global_step": 453905, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9995924234390259, "global_step": 453906, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9690645933151245, "global_step": 453907, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.130368947982788, "global_step": 453908, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0640065670013428, "global_step": 453909, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9790819883346558, "global_step": 453910, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.044527530670166, "global_step": 453911, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0427281856536865, "global_step": 453912, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.076772689819336, "global_step": 453913, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0665547847747803, "global_step": 453914, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.064326763153076, "global_step": 453915, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1067237854003906, "global_step": 453916, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1806626319885254, "global_step": 453917, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0848729610443115, "global_step": 453918, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.089205741882324, "global_step": 453919, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0473647117614746, "global_step": 453920, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.123826503753662, "global_step": 453921, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0288448333740234, "global_step": 453922, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.056878089904785, "global_step": 453923, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9488924741744995, "global_step": 453924, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1009294986724854, "global_step": 453925, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9734346866607666, "global_step": 453926, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.142488718032837, "global_step": 453927, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9672597646713257, "global_step": 453928, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0575313568115234, "global_step": 453929, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0365591049194336, "global_step": 453930, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0381109714508057, "global_step": 453931, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0818631649017334, "global_step": 453932, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.13456130027771, "global_step": 453933, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0339951515197754, "global_step": 453934, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0542197227478027, "global_step": 453935, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.03537917137146, "global_step": 453936, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9880290031433105, "global_step": 453937, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.106257915496826, "global_step": 453938, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0954103469848633, "global_step": 453939, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1193740367889404, "global_step": 453940, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0974373817443848, "global_step": 453941, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0465118885040283, "global_step": 453942, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.024517297744751, "global_step": 453943, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.160722017288208, "global_step": 453944, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0273725986480713, "global_step": 453945, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0135982036590576, "global_step": 453946, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.083712577819824, "global_step": 453947, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.070415735244751, "global_step": 453948, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0829100608825684, "global_step": 453949, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.035125494003296, "global_step": 453950, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.039879560470581, "global_step": 453951, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.159036874771118, "global_step": 453952, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.991507649421692, "global_step": 453953, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1020619869232178, "global_step": 453954, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.07865834236145, "global_step": 453955, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0468528270721436, "global_step": 453956, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1294023990631104, "global_step": 453957, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9901363849639893, "global_step": 453958, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.093141555786133, "global_step": 453959, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0688960552215576, "global_step": 453960, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9864814281463623, "global_step": 453961, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.023233652114868, "global_step": 453962, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0375702381134033, "global_step": 453963, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0406064987182617, "global_step": 453964, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0565779209136963, "global_step": 453965, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.088688373565674, "global_step": 453966, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0425264835357666, "global_step": 453967, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.009488105773926, "global_step": 453968, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0966196060180664, "global_step": 453969, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0333409309387207, "global_step": 453970, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.00301194190979, "global_step": 453971, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1764883995056152, "global_step": 453972, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.080517530441284, "global_step": 453973, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0827858448028564, "global_step": 453974, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.090869188308716, "global_step": 453975, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0763401985168457, "global_step": 453976, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1174566745758057, "global_step": 453977, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0774760246276855, "global_step": 453978, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.183220386505127, "global_step": 453979, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0265936851501465, "global_step": 453980, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.079798936843872, "global_step": 453981, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0606184005737305, "global_step": 453982, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.10451340675354, "global_step": 453983, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0404787063598633, "global_step": 453984, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0774574279785156, "global_step": 453985, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.036968231201172, "global_step": 453986, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0667355060577393, "global_step": 453987, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0891661643981934, "global_step": 453988, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0696332454681396, "global_step": 453989, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0194363594055176, "global_step": 453990, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0804009437561035, "global_step": 453991, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0560576915740967, "global_step": 453992, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.054731845855713, "global_step": 453993, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.056811571121216, "global_step": 453994, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1346399784088135, "global_step": 453995, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.049038887023926, "global_step": 453996, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0458126068115234, "global_step": 453997, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0230724811553955, "global_step": 453998, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0017991065979004, "global_step": 453999, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.009707450866699, "global_step": 454000, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9720284938812256, "global_step": 454001, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.023662567138672, "global_step": 454002, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9823319911956787, "global_step": 454003, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0710299015045166, "global_step": 454004, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0492911338806152, "global_step": 454005, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0234920978546143, "global_step": 454006, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1201331615448, "global_step": 454007, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.058720827102661, "global_step": 454008, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0081100463867188, "global_step": 454009, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.020859956741333, "global_step": 454010, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.08198881149292, "global_step": 454011, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0774049758911133, "global_step": 454012, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.037613868713379, "global_step": 454013, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.014519214630127, "global_step": 454014, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0045182704925537, "global_step": 454015, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.019735813140869, "global_step": 454016, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0168731212615967, "global_step": 454017, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.064633369445801, "global_step": 454018, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0906801223754883, "global_step": 454019, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1278250217437744, "global_step": 454020, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.008836030960083, "global_step": 454021, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.07852840423584, "global_step": 454022, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0842020511627197, "global_step": 454023, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.038421869277954, "global_step": 454024, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0638978481292725, "global_step": 454025, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1054978370666504, "global_step": 454026, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1255340576171875, "global_step": 454027, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0391428470611572, "global_step": 454028, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.026416540145874, "global_step": 454029, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.056454658508301, "global_step": 454030, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1214866638183594, "global_step": 454031, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0764873027801514, "global_step": 454032, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9768593311309814, "global_step": 454033, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.122584581375122, "global_step": 454034, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1350343227386475, "global_step": 454035, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.089698553085327, "global_step": 454036, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0748839378356934, "global_step": 454037, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.067570447921753, "global_step": 454038, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9952716827392578, "global_step": 454039, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1638078689575195, "global_step": 454040, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.058396577835083, "global_step": 454041, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.002500057220459, "global_step": 454042, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0933682918548584, "global_step": 454043, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.016629934310913, "global_step": 454044, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.028189182281494, "global_step": 454045, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0764098167419434, "global_step": 454046, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0218074321746826, "global_step": 454047, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0826292037963867, "global_step": 454048, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.989689588546753, "global_step": 454049, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9252043962478638, "global_step": 454050, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0306246280670166, "global_step": 454051, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.175318956375122, "global_step": 454052, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1169955730438232, "global_step": 454053, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.167137384414673, "global_step": 454054, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0078511238098145, "global_step": 454055, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0559489727020264, "global_step": 454056, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.099209785461426, "global_step": 454057, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0604913234710693, "global_step": 454058, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.042980670928955, "global_step": 454059, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1570944786071777, "global_step": 454060, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.057420015335083, "global_step": 454061, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.068009853363037, "global_step": 454062, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1293129920959473, "global_step": 454063, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.071986198425293, "global_step": 454064, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0054893493652344, "global_step": 454065, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.084974765777588, "global_step": 454066, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.066678285598755, "global_step": 454067, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.155846118927002, "global_step": 454068, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0437614917755127, "global_step": 454069, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.039698839187622, "global_step": 454070, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1049258708953857, "global_step": 454071, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.093240261077881, "global_step": 454072, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0719308853149414, "global_step": 454073, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1509385108947754, "global_step": 454074, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.035005569458008, "global_step": 454075, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0777456760406494, "global_step": 454076, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.061251640319824, "global_step": 454077, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0925710201263428, "global_step": 454078, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0606231689453125, "global_step": 454079, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1108598709106445, "global_step": 454080, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1041059494018555, "global_step": 454081, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.100616693496704, "global_step": 454082, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9832212924957275, "global_step": 454083, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.016887664794922, "global_step": 454084, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.140153408050537, "global_step": 454085, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.058748483657837, "global_step": 454086, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1289620399475098, "global_step": 454087, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.078876256942749, "global_step": 454088, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0518455505371094, "global_step": 454089, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1190178394317627, "global_step": 454090, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1354215145111084, "global_step": 454091, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0298047065734863, "global_step": 454092, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0003299713134766, "global_step": 454093, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.117145538330078, "global_step": 454094, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0337185859680176, "global_step": 454095, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1274261474609375, "global_step": 454096, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1044461727142334, "global_step": 454097, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0536160469055176, "global_step": 454098, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.935240626335144, "global_step": 454099, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.149355173110962, "global_step": 454100, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0754411220550537, "global_step": 454101, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9938892126083374, "global_step": 454102, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.04692006111145, "global_step": 454103, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1182518005371094, "global_step": 454104, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0409698486328125, "global_step": 454105, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0790915489196777, "global_step": 454106, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0502500534057617, "global_step": 454107, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.06650710105896, "global_step": 454108, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.077592611312866, "global_step": 454109, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0653936862945557, "global_step": 454110, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0762693881988525, "global_step": 454111, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.09494948387146, "global_step": 454112, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1592602729797363, "global_step": 454113, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.139655351638794, "global_step": 454114, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1343889236450195, "global_step": 454115, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0566799640655518, "global_step": 454116, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9686005115509033, "global_step": 454117, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.069114923477173, "global_step": 454118, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.123528003692627, "global_step": 454119, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.088594675064087, "global_step": 454120, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.123222589492798, "global_step": 454121, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.18924880027771, "global_step": 454122, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0590174198150635, "global_step": 454123, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.064366579055786, "global_step": 454124, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.118114948272705, "global_step": 454125, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0679001808166504, "global_step": 454126, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.047279119491577, "global_step": 454127, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0803613662719727, "global_step": 454128, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.084829568862915, "global_step": 454129, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1142213344573975, "global_step": 454130, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0094032287597656, "global_step": 454131, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1140036582946777, "global_step": 454132, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.145967483520508, "global_step": 454133, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0405967235565186, "global_step": 454134, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.076578140258789, "global_step": 454135, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1237986087799072, "global_step": 454136, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9773948192596436, "global_step": 454137, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.010042190551758, "global_step": 454138, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.055391550064087, "global_step": 454139, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.141592502593994, "global_step": 454140, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0945005416870117, "global_step": 454141, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.984861969947815, "global_step": 454142, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.029029369354248, "global_step": 454143, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0634500980377197, "global_step": 454144, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0679352283477783, "global_step": 454145, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.068449020385742, "global_step": 454146, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0159544944763184, "global_step": 454147, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.099247455596924, "global_step": 454148, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.093320608139038, "global_step": 454149, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.079557418823242, "global_step": 454150, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0523765087127686, "global_step": 454151, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.059152364730835, "global_step": 454152, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1158864498138428, "global_step": 454153, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1263949871063232, "global_step": 454154, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.000900983810425, "global_step": 454155, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.015500545501709, "global_step": 454156, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.019071340560913, "global_step": 454157, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.069578170776367, "global_step": 454158, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.117060899734497, "global_step": 454159, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.088881492614746, "global_step": 454160, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.093228816986084, "global_step": 454161, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.04915452003479, "global_step": 454162, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0217792987823486, "global_step": 454163, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.966698408126831, "global_step": 454164, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.104206085205078, "global_step": 454165, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0971016883850098, "global_step": 454166, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0927531719207764, "global_step": 454167, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.064544916152954, "global_step": 454168, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.117201805114746, "global_step": 454169, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1398143768310547, "global_step": 454170, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0728793144226074, "global_step": 454171, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.98552668094635, "global_step": 454172, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.023822546005249, "global_step": 454173, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.062559127807617, "global_step": 454174, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0230953693389893, "global_step": 454175, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.074618101119995, "global_step": 454176, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.145673990249634, "global_step": 454177, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.038662910461426, "global_step": 454178, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.106919527053833, "global_step": 454179, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.034309148788452, "global_step": 454180, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.141944646835327, "global_step": 454181, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.087858200073242, "global_step": 454182, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9947829246520996, "global_step": 454183, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1226062774658203, "global_step": 454184, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0185463428497314, "global_step": 454185, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0569286346435547, "global_step": 454186, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.047368288040161, "global_step": 454187, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0582070350646973, "global_step": 454188, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.109769582748413, "global_step": 454189, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1407527923583984, "global_step": 454190, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0839455127716064, "global_step": 454191, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0944855213165283, "global_step": 454192, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.097078800201416, "global_step": 454193, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0644991397857666, "global_step": 454194, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.092207670211792, "global_step": 454195, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9783673286437988, "global_step": 454196, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.070966958999634, "global_step": 454197, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.111990451812744, "global_step": 454198, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.038454294204712, "global_step": 454199, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0727782249450684, "global_step": 454200, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.095378875732422, "global_step": 454201, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0744192600250244, "global_step": 454202, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1261186599731445, "global_step": 454203, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.089132070541382, "global_step": 454204, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.006633996963501, "global_step": 454205, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.089524745941162, "global_step": 454206, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1405553817749023, "global_step": 454207, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.060622215270996, "global_step": 454208, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1051342487335205, "global_step": 454209, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0479812622070312, "global_step": 454210, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.18662166595459, "global_step": 454211, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.058104991912842, "global_step": 454212, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0494980812072754, "global_step": 454213, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.982061505317688, "global_step": 454214, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.202789306640625, "global_step": 454215, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0642197132110596, "global_step": 454216, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.163281202316284, "global_step": 454217, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1155176162719727, "global_step": 454218, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.017789125442505, "global_step": 454219, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.125624179840088, "global_step": 454220, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1443114280700684, "global_step": 454221, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.068812608718872, "global_step": 454222, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0652599334716797, "global_step": 454223, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0302982330322266, "global_step": 454224, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0550549030303955, "global_step": 454225, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.085756778717041, "global_step": 454226, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.063840389251709, "global_step": 454227, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1143343448638916, "global_step": 454228, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.045344829559326, "global_step": 454229, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1481118202209473, "global_step": 454230, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1516404151916504, "global_step": 454231, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.036231279373169, "global_step": 454232, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.157918691635132, "global_step": 454233, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.061316967010498, "global_step": 454234, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1220734119415283, "global_step": 454235, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.042959451675415, "global_step": 454236, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.08305025100708, "global_step": 454237, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0772931575775146, "global_step": 454238, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0853946208953857, "global_step": 454239, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0377981662750244, "global_step": 454240, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.107308864593506, "global_step": 454241, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1407952308654785, "global_step": 454242, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0000717639923096, "global_step": 454243, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.108823299407959, "global_step": 454244, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.061471939086914, "global_step": 454245, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0195107460021973, "global_step": 454246, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0544450283050537, "global_step": 454247, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.111128568649292, "global_step": 454248, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.114948272705078, "global_step": 454249, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.073843479156494, "global_step": 454250, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.028869152069092, "global_step": 454251, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.046175003051758, "global_step": 454252, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1366097927093506, "global_step": 454253, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.055931806564331, "global_step": 454254, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.057401657104492, "global_step": 454255, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.042632818222046, "global_step": 454256, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.07900071144104, "global_step": 454257, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0742509365081787, "global_step": 454258, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0347657203674316, "global_step": 454259, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0803110599517822, "global_step": 454260, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0824973583221436, "global_step": 454261, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.024853229522705, "global_step": 454262, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.173600196838379, "global_step": 454263, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1144046783447266, "global_step": 454264, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1259548664093018, "global_step": 454265, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1386547088623047, "global_step": 454266, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0021047592163086, "global_step": 454267, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0944771766662598, "global_step": 454268, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.034362316131592, "global_step": 454269, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9800958633422852, "global_step": 454270, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1069071292877197, "global_step": 454271, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0454304218292236, "global_step": 454272, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0983996391296387, "global_step": 454273, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1193439960479736, "global_step": 454274, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0526697635650635, "global_step": 454275, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0053820610046387, "global_step": 454276, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0915770530700684, "global_step": 454277, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0296249389648438, "global_step": 454278, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.040964126586914, "global_step": 454279, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0697343349456787, "global_step": 454280, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.973428726196289, "global_step": 454281, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.043145179748535, "global_step": 454282, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1244990825653076, "global_step": 454283, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.038693904876709, "global_step": 454284, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.034851551055908, "global_step": 454285, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9601393938064575, "global_step": 454286, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.069002389907837, "global_step": 454287, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0426106452941895, "global_step": 454288, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.056121826171875, "global_step": 454289, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.059431791305542, "global_step": 454290, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.095080852508545, "global_step": 454291, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1228156089782715, "global_step": 454292, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.113346576690674, "global_step": 454293, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0811245441436768, "global_step": 454294, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0958292484283447, "global_step": 454295, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.103944778442383, "global_step": 454296, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.074690818786621, "global_step": 454297, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0853099822998047, "global_step": 454298, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.063532590866089, "global_step": 454299, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.156977891921997, "global_step": 454300, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1334481239318848, "global_step": 454301, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1143276691436768, "global_step": 454302, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.079618215560913, "global_step": 454303, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0823872089385986, "global_step": 454304, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0871551036834717, "global_step": 454305, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1455392837524414, "global_step": 454306, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.136188268661499, "global_step": 454307, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0472793579101562, "global_step": 454308, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0782694816589355, "global_step": 454309, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.062751054763794, "global_step": 454310, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.072968006134033, "global_step": 454311, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9515589475631714, "global_step": 454312, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.061366319656372, "global_step": 454313, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1081392765045166, "global_step": 454314, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.096752166748047, "global_step": 454315, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0372684001922607, "global_step": 454316, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0566883087158203, "global_step": 454317, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.109971523284912, "global_step": 454318, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0711522102355957, "global_step": 454319, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0952796936035156, "global_step": 454320, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0933706760406494, "global_step": 454321, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1195831298828125, "global_step": 454322, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.057093381881714, "global_step": 454323, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0347483158111572, "global_step": 454324, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1179308891296387, "global_step": 454325, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.012871026992798, "global_step": 454326, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0423524379730225, "global_step": 454327, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.002687931060791, "global_step": 454328, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.126779556274414, "global_step": 454329, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0783939361572266, "global_step": 454330, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.041065216064453, "global_step": 454331, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1568188667297363, "global_step": 454332, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.112757444381714, "global_step": 454333, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1480140686035156, "global_step": 454334, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0987460613250732, "global_step": 454335, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.157580852508545, "global_step": 454336, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.037508487701416, "global_step": 454337, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0381038188934326, "global_step": 454338, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0451884269714355, "global_step": 454339, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.085169553756714, "global_step": 454340, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.047367811203003, "global_step": 454341, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0554590225219727, "global_step": 454342, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0506391525268555, "global_step": 454343, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1413321495056152, "global_step": 454344, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0592856407165527, "global_step": 454345, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1172373294830322, "global_step": 454346, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.090790033340454, "global_step": 454347, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.075228214263916, "global_step": 454348, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0435659885406494, "global_step": 454349, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.057002544403076, "global_step": 454350, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.039358139038086, "global_step": 454351, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.043478012084961, "global_step": 454352, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.181556463241577, "global_step": 454353, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.080333709716797, "global_step": 454354, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.109373092651367, "global_step": 454355, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.059504508972168, "global_step": 454356, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.102372407913208, "global_step": 454357, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.146160125732422, "global_step": 454358, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0677106380462646, "global_step": 454359, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0478532314300537, "global_step": 454360, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1368377208709717, "global_step": 454361, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9961745738983154, "global_step": 454362, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.07651424407959, "global_step": 454363, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.104297637939453, "global_step": 454364, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.054612636566162, "global_step": 454365, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0385193824768066, "global_step": 454366, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1074936389923096, "global_step": 454367, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.078486680984497, "global_step": 454368, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.020855188369751, "global_step": 454369, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1224050521850586, "global_step": 454370, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.157118082046509, "global_step": 454371, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.119288206100464, "global_step": 454372, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0896871089935303, "global_step": 454373, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0626416206359863, "global_step": 454374, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.059643507003784, "global_step": 454375, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.111079454421997, "global_step": 454376, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.094275712966919, "global_step": 454377, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1498281955718994, "global_step": 454378, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.086524248123169, "global_step": 454379, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.037093162536621, "global_step": 454380, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0642001628875732, "global_step": 454381, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9333451986312866, "global_step": 454382, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.04297137260437, "global_step": 454383, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0961053371429443, "global_step": 454384, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0045652389526367, "global_step": 454385, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.090553045272827, "global_step": 454386, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1905877590179443, "global_step": 454387, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1412572860717773, "global_step": 454388, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1301958560943604, "global_step": 454389, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0044991970062256, "global_step": 454390, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.139780044555664, "global_step": 454391, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.020648956298828, "global_step": 454392, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.131856918334961, "global_step": 454393, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1149473190307617, "global_step": 454394, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1177000999450684, "global_step": 454395, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1423799991607666, "global_step": 454396, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.122699499130249, "global_step": 454397, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.113983154296875, "global_step": 454398, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1243679523468018, "global_step": 454399, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.013120412826538, "global_step": 454400, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0740694999694824, "global_step": 454401, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0605294704437256, "global_step": 454402, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1100010871887207, "global_step": 454403, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0047695636749268, "global_step": 454404, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.069138526916504, "global_step": 454405, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0375308990478516, "global_step": 454406, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0475127696990967, "global_step": 454407, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.075754165649414, "global_step": 454408, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0942134857177734, "global_step": 454409, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.022261619567871, "global_step": 454410, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0266056060791016, "global_step": 454411, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0367093086242676, "global_step": 454412, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.173430919647217, "global_step": 454413, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.065580368041992, "global_step": 454414, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.084683895111084, "global_step": 454415, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.124166250228882, "global_step": 454416, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.024214029312134, "global_step": 454417, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1430881023406982, "global_step": 454418, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0098471641540527, "global_step": 454419, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.123133659362793, "global_step": 454420, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.020998477935791, "global_step": 454421, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.156341075897217, "global_step": 454422, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.08662486076355, "global_step": 454423, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.111116886138916, "global_step": 454424, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.090285301208496, "global_step": 454425, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.080361843109131, "global_step": 454426, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0669991970062256, "global_step": 454427, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.116987943649292, "global_step": 454428, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.116978645324707, "global_step": 454429, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0419840812683105, "global_step": 454430, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.126987934112549, "global_step": 454431, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.08845853805542, "global_step": 454432, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1152493953704834, "global_step": 454433, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1515560150146484, "global_step": 454434, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0424091815948486, "global_step": 454435, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.998825192451477, "global_step": 454436, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.120185613632202, "global_step": 454437, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.070887565612793, "global_step": 454438, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0724194049835205, "global_step": 454439, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0958685874938965, "global_step": 454440, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.015193462371826, "global_step": 454441, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.052464485168457, "global_step": 454442, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1347312927246094, "global_step": 454443, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0888724327087402, "global_step": 454444, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0994086265563965, "global_step": 454445, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0190415382385254, "global_step": 454446, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.061676502227783, "global_step": 454447, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.10392427444458, "global_step": 454448, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0528364181518555, "global_step": 454449, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.097734212875366, "global_step": 454450, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.01543927192688, "global_step": 454451, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.098572015762329, "global_step": 454452, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1845192909240723, "global_step": 454453, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0464248657226562, "global_step": 454454, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.146204710006714, "global_step": 454455, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.091078519821167, "global_step": 454456, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0921614170074463, "global_step": 454457, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1408331394195557, "global_step": 454458, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.057354211807251, "global_step": 454459, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1393609046936035, "global_step": 454460, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0703747272491455, "global_step": 454461, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1670312881469727, "global_step": 454462, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.057492256164551, "global_step": 454463, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.165692090988159, "global_step": 454464, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0369653701782227, "global_step": 454465, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.000955104827881, "global_step": 454466, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.049131393432617, "global_step": 454467, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0625510215759277, "global_step": 454468, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.140953779220581, "global_step": 454469, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1118924617767334, "global_step": 454470, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0361857414245605, "global_step": 454471, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.073173761367798, "global_step": 454472, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0563745498657227, "global_step": 454473, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1262354850769043, "global_step": 454474, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0679163932800293, "global_step": 454475, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.063896656036377, "global_step": 454476, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0711166858673096, "global_step": 454477, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9948930740356445, "global_step": 454478, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0011463165283203, "global_step": 454479, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.075392961502075, "global_step": 454480, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.107654094696045, "global_step": 454481, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.17500901222229, "global_step": 454482, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0703442096710205, "global_step": 454483, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.108323812484741, "global_step": 454484, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.041985273361206, "global_step": 454485, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1217963695526123, "global_step": 454486, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.043684720993042, "global_step": 454487, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.055570125579834, "global_step": 454488, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0933642387390137, "global_step": 454489, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.017345428466797, "global_step": 454490, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0567712783813477, "global_step": 454491, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0267856121063232, "global_step": 454492, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1667795181274414, "global_step": 454493, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1483371257781982, "global_step": 454494, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.079104423522949, "global_step": 454495, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9931354522705078, "global_step": 454496, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1320202350616455, "global_step": 454497, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.106538772583008, "global_step": 454498, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.971964716911316, "global_step": 454499, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.102769613265991, "global_step": 454500, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.047714948654175, "global_step": 454501, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.011626958847046, "global_step": 454502, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.175142765045166, "global_step": 454503, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.017958641052246, "global_step": 454504, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0636062622070312, "global_step": 454505, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.075923442840576, "global_step": 454506, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0443782806396484, "global_step": 454507, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.052076816558838, "global_step": 454508, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.085214138031006, "global_step": 454509, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0394015312194824, "global_step": 454510, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.091597557067871, "global_step": 454511, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0208098888397217, "global_step": 454512, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.160388946533203, "global_step": 454513, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.087977170944214, "global_step": 454514, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.130439519882202, "global_step": 454515, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.047072172164917, "global_step": 454516, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.105926275253296, "global_step": 454517, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0919442176818848, "global_step": 454518, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0619075298309326, "global_step": 454519, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.013762950897217, "global_step": 454520, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.154512405395508, "global_step": 454521, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0473790168762207, "global_step": 454522, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0427849292755127, "global_step": 454523, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0967745780944824, "global_step": 454524, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0319132804870605, "global_step": 454525, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.093791961669922, "global_step": 454526, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9963966608047485, "global_step": 454527, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1111841201782227, "global_step": 454528, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.032865047454834, "global_step": 454529, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0369701385498047, "global_step": 454530, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.079373836517334, "global_step": 454531, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0173110961914062, "global_step": 454532, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0458030700683594, "global_step": 454533, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.040661334991455, "global_step": 454534, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.081132173538208, "global_step": 454535, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1188864707946777, "global_step": 454536, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.033733606338501, "global_step": 454537, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0473580360412598, "global_step": 454538, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.144174098968506, "global_step": 454539, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1205484867095947, "global_step": 454540, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.063718557357788, "global_step": 454541, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0660290718078613, "global_step": 454542, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0590546131134033, "global_step": 454543, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0078041553497314, "global_step": 454544, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0532724857330322, "global_step": 454545, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0992021560668945, "global_step": 454546, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.013624906539917, "global_step": 454547, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1365444660186768, "global_step": 454548, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.072070360183716, "global_step": 454549, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.9431625604629517, "global_step": 454550, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1119940280914307, "global_step": 454551, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0962419509887695, "global_step": 454552, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1429028511047363, "global_step": 454553, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.151837110519409, "global_step": 454554, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.060074806213379, "global_step": 454555, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1448919773101807, "global_step": 454556, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.110032558441162, "global_step": 454557, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0448975563049316, "global_step": 454558, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1697585582733154, "global_step": 454559, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.062954902648926, "global_step": 454560, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0477607250213623, "global_step": 454561, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.101682186126709, "global_step": 454562, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.049628973007202, "global_step": 454563, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0100419521331787, "global_step": 454564, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0932178497314453, "global_step": 454565, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0954642295837402, "global_step": 454566, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0420970916748047, "global_step": 454567, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0974199771881104, "global_step": 454568, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0830254554748535, "global_step": 454569, "epoch": 818, "lr": 5e-05}
{"train_loss": 1.969417691230774, "global_step": 454570, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0581955909729004, "global_step": 454571, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0276505947113037, "global_step": 454572, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.07886004447937, "global_step": 454573, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.061224937438965, "global_step": 454574, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.075040817260742, "global_step": 454575, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0449059009552, "global_step": 454576, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0957324504852295, "global_step": 454577, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.026054859161377, "global_step": 454578, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.1205756664276123, "global_step": 454579, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.123255968093872, "global_step": 454580, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0598220825195312, "global_step": 454581, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.007753610610962, "global_step": 454582, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0601062774658203, "global_step": 454583, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.058490037918091, "global_step": 454584, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0936083793640137, "global_step": 454585, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.126892328262329, "global_step": 454586, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.086343765258789, "global_step": 454587, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.087502956390381, "global_step": 454588, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0492939949035645, "global_step": 454589, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.041001319885254, "global_step": 454590, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.145631790161133, "global_step": 454591, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0904555320739746, "global_step": 454592, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.0693349838256836, "global_step": 454593, "epoch": 818, "lr": 5e-05}
{"train_loss": 2.174954414367676, "global_step": 454594, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.939997673034668, "global_step": 454595, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0163817405700684, "global_step": 454596, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.135765552520752, "global_step": 454597, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0923831462860107, "global_step": 454598, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9161161184310913, "global_step": 454599, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.010944128036499, "global_step": 454600, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.118943214416504, "global_step": 454601, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0866899490356445, "global_step": 454602, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.001707077026367, "global_step": 454603, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0987324714660645, "global_step": 454604, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.092874765396118, "global_step": 454605, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.083134651184082, "global_step": 454606, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.056621551513672, "global_step": 454607, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0878992080688477, "global_step": 454608, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0996265411376953, "global_step": 454609, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0636038780212402, "global_step": 454610, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9966922998428345, "global_step": 454611, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1115500926971436, "global_step": 454612, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.97757887840271, "global_step": 454613, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.187528133392334, "global_step": 454614, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0875093936920166, "global_step": 454615, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1716079711914062, "global_step": 454616, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.104673147201538, "global_step": 454617, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9996354579925537, "global_step": 454618, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.042839288711548, "global_step": 454619, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9953864812850952, "global_step": 454620, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0371668338775635, "global_step": 454621, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0365233421325684, "global_step": 454622, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0487823486328125, "global_step": 454623, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9721759557724, "global_step": 454624, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0968542098999023, "global_step": 454625, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9258596897125244, "global_step": 454626, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.075958728790283, "global_step": 454627, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0773282051086426, "global_step": 454628, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.09989333152771, "global_step": 454629, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0509774684906006, "global_step": 454630, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0188260078430176, "global_step": 454631, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0627634525299072, "global_step": 454632, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0387563705444336, "global_step": 454633, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0543243885040283, "global_step": 454634, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9370863437652588, "global_step": 454635, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0660300254821777, "global_step": 454636, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0841057300567627, "global_step": 454637, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.061018228530884, "global_step": 454638, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.044360876083374, "global_step": 454639, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.034714460372925, "global_step": 454640, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.026357412338257, "global_step": 454641, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0829408168792725, "global_step": 454642, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0580430030822754, "global_step": 454643, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0937039852142334, "global_step": 454644, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.951695203781128, "global_step": 454645, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0548224449157715, "global_step": 454646, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9973527193069458, "global_step": 454647, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.021714925765991, "global_step": 454648, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1333301067352295, "global_step": 454649, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.036609172821045, "global_step": 454650, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9440677165985107, "global_step": 454651, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0076045989990234, "global_step": 454652, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.066789388656616, "global_step": 454653, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.09781551361084, "global_step": 454654, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.048301935195923, "global_step": 454655, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9752511978149414, "global_step": 454656, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0295755863189697, "global_step": 454657, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.01951003074646, "global_step": 454658, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0229651927948, "global_step": 454659, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0946245193481445, "global_step": 454660, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0222079753875732, "global_step": 454661, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.027811050415039, "global_step": 454662, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1226470470428467, "global_step": 454663, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.158351421356201, "global_step": 454664, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1195502281188965, "global_step": 454665, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0139951705932617, "global_step": 454666, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.041264772415161, "global_step": 454667, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0372064113616943, "global_step": 454668, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0974247455596924, "global_step": 454669, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0511069297790527, "global_step": 454670, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0731253623962402, "global_step": 454671, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.01318359375, "global_step": 454672, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.042954206466675, "global_step": 454673, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.080979585647583, "global_step": 454674, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0609209537506104, "global_step": 454675, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1165881156921387, "global_step": 454676, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.033751964569092, "global_step": 454677, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0019819736480713, "global_step": 454678, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.028909206390381, "global_step": 454679, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1125316619873047, "global_step": 454680, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1417698860168457, "global_step": 454681, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0410425662994385, "global_step": 454682, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0691092014312744, "global_step": 454683, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0786218643188477, "global_step": 454684, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.96425199508667, "global_step": 454685, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0980582237243652, "global_step": 454686, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0458152294158936, "global_step": 454687, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.026444435119629, "global_step": 454688, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.04878306388855, "global_step": 454689, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.038910150527954, "global_step": 454690, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0649330615997314, "global_step": 454691, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.121702194213867, "global_step": 454692, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.148768901824951, "global_step": 454693, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.099283218383789, "global_step": 454694, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0714528560638428, "global_step": 454695, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0284383296966553, "global_step": 454696, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1405298709869385, "global_step": 454697, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0631723403930664, "global_step": 454698, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0317139625549316, "global_step": 454699, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.018390655517578, "global_step": 454700, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0683114528656006, "global_step": 454701, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0432419776916504, "global_step": 454702, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.051589012145996, "global_step": 454703, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9877982139587402, "global_step": 454704, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.050727128982544, "global_step": 454705, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1195802688598633, "global_step": 454706, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.972335696220398, "global_step": 454707, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.080547332763672, "global_step": 454708, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0625827312469482, "global_step": 454709, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.073117256164551, "global_step": 454710, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0330026149749756, "global_step": 454711, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0048344135284424, "global_step": 454712, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0504770278930664, "global_step": 454713, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.053553581237793, "global_step": 454714, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.083941698074341, "global_step": 454715, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0783302783966064, "global_step": 454716, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0560264587402344, "global_step": 454717, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.046576499938965, "global_step": 454718, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0810956954956055, "global_step": 454719, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0422394275665283, "global_step": 454720, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.134622573852539, "global_step": 454721, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0084383487701416, "global_step": 454722, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0568604469299316, "global_step": 454723, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.994627833366394, "global_step": 454724, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1072254180908203, "global_step": 454725, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0709519386291504, "global_step": 454726, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1369714736938477, "global_step": 454727, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0005366802215576, "global_step": 454728, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.141139268875122, "global_step": 454729, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1545042991638184, "global_step": 454730, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.002215623855591, "global_step": 454731, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.104905366897583, "global_step": 454732, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.091240882873535, "global_step": 454733, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.023101806640625, "global_step": 454734, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9910656213760376, "global_step": 454735, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9529759883880615, "global_step": 454736, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0909926891326904, "global_step": 454737, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9971082210540771, "global_step": 454738, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0643937587738037, "global_step": 454739, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0635552406311035, "global_step": 454740, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0134880542755127, "global_step": 454741, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0682969093322754, "global_step": 454742, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0378904342651367, "global_step": 454743, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1264233589172363, "global_step": 454744, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.076498031616211, "global_step": 454745, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1161348819732666, "global_step": 454746, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.099515914916992, "global_step": 454747, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1171743869781494, "global_step": 454748, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.051262855529785, "global_step": 454749, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.067197322845459, "global_step": 454750, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0646870136260986, "global_step": 454751, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0643486976623535, "global_step": 454752, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0708038806915283, "global_step": 454753, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0548977851867676, "global_step": 454754, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0604727268218994, "global_step": 454755, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.989805817604065, "global_step": 454756, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.107992172241211, "global_step": 454757, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0582468509674072, "global_step": 454758, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1377124786376953, "global_step": 454759, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9957869052886963, "global_step": 454760, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.048081636428833, "global_step": 454761, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.094473123550415, "global_step": 454762, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9673805236816406, "global_step": 454763, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0513691902160645, "global_step": 454764, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.088991641998291, "global_step": 454765, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0457546710968018, "global_step": 454766, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9677718877792358, "global_step": 454767, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1212453842163086, "global_step": 454768, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1459758281707764, "global_step": 454769, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1521825790405273, "global_step": 454770, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0033223628997803, "global_step": 454771, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.073312282562256, "global_step": 454772, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0685458183288574, "global_step": 454773, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0385642051696777, "global_step": 454774, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9818803071975708, "global_step": 454775, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.069348096847534, "global_step": 454776, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9562053680419922, "global_step": 454777, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0630600452423096, "global_step": 454778, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.057276725769043, "global_step": 454779, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9817169904708862, "global_step": 454780, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0535237789154053, "global_step": 454781, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.063084125518799, "global_step": 454782, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1306393146514893, "global_step": 454783, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.070263385772705, "global_step": 454784, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1576077938079834, "global_step": 454785, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0688140392303467, "global_step": 454786, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.030963659286499, "global_step": 454787, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0572915077209473, "global_step": 454788, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.021867513656616, "global_step": 454789, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0853233337402344, "global_step": 454790, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0896377563476562, "global_step": 454791, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.022817373275757, "global_step": 454792, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1273913383483887, "global_step": 454793, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.995530605316162, "global_step": 454794, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1138224601745605, "global_step": 454795, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1818671226501465, "global_step": 454796, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0692992210388184, "global_step": 454797, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0629920959472656, "global_step": 454798, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1039228439331055, "global_step": 454799, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.074551820755005, "global_step": 454800, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.074714183807373, "global_step": 454801, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.074373722076416, "global_step": 454802, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.074230670928955, "global_step": 454803, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0695574283599854, "global_step": 454804, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0599613189697266, "global_step": 454805, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.034417152404785, "global_step": 454806, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0514183044433594, "global_step": 454807, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1053388118743896, "global_step": 454808, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0272257328033447, "global_step": 454809, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0453646183013916, "global_step": 454810, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.032808303833008, "global_step": 454811, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0164031982421875, "global_step": 454812, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.009295701980591, "global_step": 454813, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.092888832092285, "global_step": 454814, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1403324604034424, "global_step": 454815, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0538954734802246, "global_step": 454816, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0339508056640625, "global_step": 454817, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.014122724533081, "global_step": 454818, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9996602535247803, "global_step": 454819, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0907845497131348, "global_step": 454820, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.118746280670166, "global_step": 454821, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.025481700897217, "global_step": 454822, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.059173107147217, "global_step": 454823, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.089647054672241, "global_step": 454824, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.011786937713623, "global_step": 454825, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.136437177658081, "global_step": 454826, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.07478666305542, "global_step": 454827, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.011310338973999, "global_step": 454828, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.025750160217285, "global_step": 454829, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.07871675491333, "global_step": 454830, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.069392681121826, "global_step": 454831, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.060397148132324, "global_step": 454832, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0960299968719482, "global_step": 454833, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.063829183578491, "global_step": 454834, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.024724006652832, "global_step": 454835, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.077732563018799, "global_step": 454836, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.064342498779297, "global_step": 454837, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0953421592712402, "global_step": 454838, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1213948726654053, "global_step": 454839, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.008272886276245, "global_step": 454840, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0792996883392334, "global_step": 454841, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0661394596099854, "global_step": 454842, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0162041187286377, "global_step": 454843, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.090132474899292, "global_step": 454844, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9505168199539185, "global_step": 454845, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0554537773132324, "global_step": 454846, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9930036067962646, "global_step": 454847, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.118151903152466, "global_step": 454848, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.040388345718384, "global_step": 454849, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0069079399108887, "global_step": 454850, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.13094425201416, "global_step": 454851, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1417577266693115, "global_step": 454852, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0411713123321533, "global_step": 454853, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0355262756347656, "global_step": 454854, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.102587938308716, "global_step": 454855, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0370595455169678, "global_step": 454856, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9385906457901, "global_step": 454857, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0240280628204346, "global_step": 454858, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.055314064025879, "global_step": 454859, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0770046710968018, "global_step": 454860, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1525321006774902, "global_step": 454861, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.034882068634033, "global_step": 454862, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1049888134002686, "global_step": 454863, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.086008071899414, "global_step": 454864, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.064300060272217, "global_step": 454865, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1038618087768555, "global_step": 454866, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.013368606567383, "global_step": 454867, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.117624282836914, "global_step": 454868, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9654369354248047, "global_step": 454869, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0836944580078125, "global_step": 454870, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0858254432678223, "global_step": 454871, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9742600917816162, "global_step": 454872, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1148791313171387, "global_step": 454873, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0677266120910645, "global_step": 454874, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0807437896728516, "global_step": 454875, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1189920902252197, "global_step": 454876, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.081669807434082, "global_step": 454877, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9909560680389404, "global_step": 454878, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9390716552734375, "global_step": 454879, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0242509841918945, "global_step": 454880, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0860633850097656, "global_step": 454881, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0810720920562744, "global_step": 454882, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0757625102996826, "global_step": 454883, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.092249631881714, "global_step": 454884, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.093863010406494, "global_step": 454885, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.030163288116455, "global_step": 454886, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1139020919799805, "global_step": 454887, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0810811519622803, "global_step": 454888, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.07041597366333, "global_step": 454889, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1326937675476074, "global_step": 454890, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.015932321548462, "global_step": 454891, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9313815832138062, "global_step": 454892, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0672662258148193, "global_step": 454893, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1594104766845703, "global_step": 454894, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.129640817642212, "global_step": 454895, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0161914825439453, "global_step": 454896, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0523197650909424, "global_step": 454897, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.002939462661743, "global_step": 454898, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.060347080230713, "global_step": 454899, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.059807777404785, "global_step": 454900, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9243195056915283, "global_step": 454901, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.00864839553833, "global_step": 454902, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0674870014190674, "global_step": 454903, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.130326509475708, "global_step": 454904, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1195523738861084, "global_step": 454905, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.032228708267212, "global_step": 454906, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.020894765853882, "global_step": 454907, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.080002784729004, "global_step": 454908, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0008902549743652, "global_step": 454909, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.011085033416748, "global_step": 454910, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1174674034118652, "global_step": 454911, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1228930950164795, "global_step": 454912, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.106558084487915, "global_step": 454913, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.177077054977417, "global_step": 454914, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.137343645095825, "global_step": 454915, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.077801465988159, "global_step": 454916, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0914664268493652, "global_step": 454917, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0291526317596436, "global_step": 454918, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0989227294921875, "global_step": 454919, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9680429697036743, "global_step": 454920, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.097569704055786, "global_step": 454921, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.119685411453247, "global_step": 454922, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0561087131500244, "global_step": 454923, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.128554344177246, "global_step": 454924, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1731791496276855, "global_step": 454925, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1081223487854004, "global_step": 454926, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.086062431335449, "global_step": 454927, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1392390727996826, "global_step": 454928, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0270702838897705, "global_step": 454929, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.104637861251831, "global_step": 454930, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.173724889755249, "global_step": 454931, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.132861375808716, "global_step": 454932, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1112804412841797, "global_step": 454933, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0783307552337646, "global_step": 454934, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1024036407470703, "global_step": 454935, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1302835941314697, "global_step": 454936, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0434677600860596, "global_step": 454937, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0397682189941406, "global_step": 454938, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1165425777435303, "global_step": 454939, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.088242769241333, "global_step": 454940, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.165574789047241, "global_step": 454941, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0524933338165283, "global_step": 454942, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.028567314147949, "global_step": 454943, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0309436321258545, "global_step": 454944, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.079139232635498, "global_step": 454945, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0573313236236572, "global_step": 454946, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.2079029083251953, "global_step": 454947, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0657098293304443, "global_step": 454948, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.088101387023926, "global_step": 454949, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.070380687713623, "global_step": 454950, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1211304664611816, "global_step": 454951, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.150796413421631, "global_step": 454952, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.024120569229126, "global_step": 454953, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0662806034088135, "global_step": 454954, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1371235847473145, "global_step": 454955, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.079498529434204, "global_step": 454956, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1100871562957764, "global_step": 454957, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.047272205352783, "global_step": 454958, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.130113363265991, "global_step": 454959, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1073269844055176, "global_step": 454960, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.046048641204834, "global_step": 454961, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0405561923980713, "global_step": 454962, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1135122776031494, "global_step": 454963, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.059392213821411, "global_step": 454964, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0573885440826416, "global_step": 454965, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1561949253082275, "global_step": 454966, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.100278854370117, "global_step": 454967, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.003821849822998, "global_step": 454968, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0463290214538574, "global_step": 454969, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.068578004837036, "global_step": 454970, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0196778774261475, "global_step": 454971, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1235551834106445, "global_step": 454972, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.059863328933716, "global_step": 454973, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1544885635375977, "global_step": 454974, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0930562019348145, "global_step": 454975, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0465855598449707, "global_step": 454976, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.2449259757995605, "global_step": 454977, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0711417198181152, "global_step": 454978, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1144936084747314, "global_step": 454979, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9684507846832275, "global_step": 454980, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0809898376464844, "global_step": 454981, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0499773025512695, "global_step": 454982, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.115866184234619, "global_step": 454983, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0907602310180664, "global_step": 454984, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.089308023452759, "global_step": 454985, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0212759971618652, "global_step": 454986, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.126457691192627, "global_step": 454987, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1023926734924316, "global_step": 454988, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.040515184402466, "global_step": 454989, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.08225154876709, "global_step": 454990, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.140275001525879, "global_step": 454991, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0304505825042725, "global_step": 454992, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0389699935913086, "global_step": 454993, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0877349376678467, "global_step": 454994, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.961686611175537, "global_step": 454995, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0568151473999023, "global_step": 454996, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.083934783935547, "global_step": 454997, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.051588535308838, "global_step": 454998, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0307133197784424, "global_step": 454999, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.027942657470703, "global_step": 455000, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.009538173675537, "global_step": 455001, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.13375186920166, "global_step": 455002, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.026599884033203, "global_step": 455003, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0561976432800293, "global_step": 455004, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1141605377197266, "global_step": 455005, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1139323711395264, "global_step": 455006, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1507973670959473, "global_step": 455007, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0652706623077393, "global_step": 455008, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.04056715965271, "global_step": 455009, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0331830978393555, "global_step": 455010, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0629663467407227, "global_step": 455011, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.043008327484131, "global_step": 455012, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.089118003845215, "global_step": 455013, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1204731464385986, "global_step": 455014, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1091792583465576, "global_step": 455015, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.068723201751709, "global_step": 455016, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0723042488098145, "global_step": 455017, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1385817527770996, "global_step": 455018, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.167752504348755, "global_step": 455019, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1041274070739746, "global_step": 455020, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1236729621887207, "global_step": 455021, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.048842430114746, "global_step": 455022, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0872652530670166, "global_step": 455023, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0657827854156494, "global_step": 455024, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.085904121398926, "global_step": 455025, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1128106117248535, "global_step": 455026, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0737006664276123, "global_step": 455027, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.116562604904175, "global_step": 455028, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.022336483001709, "global_step": 455029, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1555089950561523, "global_step": 455030, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.026779890060425, "global_step": 455031, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.064793825149536, "global_step": 455032, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.031134605407715, "global_step": 455033, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0696566104888916, "global_step": 455034, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0643606185913086, "global_step": 455035, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.073061943054199, "global_step": 455036, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.128763437271118, "global_step": 455037, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.026228427886963, "global_step": 455038, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.140263795852661, "global_step": 455039, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.024110794067383, "global_step": 455040, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0462441444396973, "global_step": 455041, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0375261306762695, "global_step": 455042, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1215450763702393, "global_step": 455043, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.110295534133911, "global_step": 455044, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1222915649414062, "global_step": 455045, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0531938076019287, "global_step": 455046, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0446927547454834, "global_step": 455047, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0237553119659424, "global_step": 455048, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0305771827697754, "global_step": 455049, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0023033618927, "global_step": 455050, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0509438514709473, "global_step": 455051, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.097914695739746, "global_step": 455052, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0245213508605957, "global_step": 455053, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.105504035949707, "global_step": 455054, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0766546726226807, "global_step": 455055, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.005513906478882, "global_step": 455056, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.066404342651367, "global_step": 455057, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.159311294555664, "global_step": 455058, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0077478885650635, "global_step": 455059, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9947760105133057, "global_step": 455060, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9901987314224243, "global_step": 455061, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0660459995269775, "global_step": 455062, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.084493637084961, "global_step": 455063, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0492265224456787, "global_step": 455064, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0420374870300293, "global_step": 455065, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0108439922332764, "global_step": 455066, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1191341876983643, "global_step": 455067, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1310269832611084, "global_step": 455068, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0687007904052734, "global_step": 455069, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.077378749847412, "global_step": 455070, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0956132411956787, "global_step": 455071, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.090902090072632, "global_step": 455072, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0687754154205322, "global_step": 455073, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0240895748138428, "global_step": 455074, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.072451114654541, "global_step": 455075, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.070777416229248, "global_step": 455076, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.069744348526001, "global_step": 455077, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.03902268409729, "global_step": 455078, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0127546787261963, "global_step": 455079, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1108546257019043, "global_step": 455080, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.072995662689209, "global_step": 455081, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9730205535888672, "global_step": 455082, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1154181957244873, "global_step": 455083, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0642004013061523, "global_step": 455084, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1118688583374023, "global_step": 455085, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.993722677230835, "global_step": 455086, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0414397716522217, "global_step": 455087, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0609850883483887, "global_step": 455088, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0960142612457275, "global_step": 455089, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.109691858291626, "global_step": 455090, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0399656295776367, "global_step": 455091, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0219969749450684, "global_step": 455092, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.035647392272949, "global_step": 455093, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1540603637695312, "global_step": 455094, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1373941898345947, "global_step": 455095, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.007946014404297, "global_step": 455096, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0115413665771484, "global_step": 455097, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0079140663146973, "global_step": 455098, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.049605369567871, "global_step": 455099, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.115490674972534, "global_step": 455100, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.061460256576538, "global_step": 455101, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.091470241546631, "global_step": 455102, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1791553497314453, "global_step": 455103, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1091246604919434, "global_step": 455104, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0412580966949463, "global_step": 455105, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0587844848632812, "global_step": 455106, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.022148847579956, "global_step": 455107, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.127056360244751, "global_step": 455108, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0056800842285156, "global_step": 455109, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.146062135696411, "global_step": 455110, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1182241439819336, "global_step": 455111, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.070807695388794, "global_step": 455112, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0822489261627197, "global_step": 455113, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0264883041381836, "global_step": 455114, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.118265151977539, "global_step": 455115, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.059986114501953, "global_step": 455116, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.038954973220825, "global_step": 455117, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0847811698913574, "global_step": 455118, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.071214199066162, "global_step": 455119, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0836358070373535, "global_step": 455120, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.100414991378784, "global_step": 455121, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.116666316986084, "global_step": 455122, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.092254638671875, "global_step": 455123, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9789345264434814, "global_step": 455124, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.032569169998169, "global_step": 455125, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.06593656539917, "global_step": 455126, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.052734613418579, "global_step": 455127, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.089974880218506, "global_step": 455128, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0611636638641357, "global_step": 455129, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.131629228591919, "global_step": 455130, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.156120777130127, "global_step": 455131, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.01401686668396, "global_step": 455132, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0076236724853516, "global_step": 455133, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1292972564697266, "global_step": 455134, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9847420454025269, "global_step": 455135, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1562795639038086, "global_step": 455136, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.048217535018921, "global_step": 455137, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0514979362487793, "global_step": 455138, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.064913511276245, "global_step": 455139, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.061223030090332, "global_step": 455140, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.003493070602417, "global_step": 455141, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0686488151550293, "global_step": 455142, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.065587282180786, "global_step": 455143, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.058333158493042, "global_step": 455144, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1555888652801514, "global_step": 455145, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1017227172851562, "global_step": 455146, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0689563751220703, "global_step": 455147, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0749454498291016, "global_step": 455148, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0316362380981445, "global_step": 455149, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1154048442840576, "global_step": 455150, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1602683067321777, "global_step": 455151, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9735175371170044, "global_step": 455152, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0628201961517334, "global_step": 455153, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.097076416015625, "global_step": 455154, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.059800863265991, "global_step": 455155, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9902946949005127, "global_step": 455156, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0231335163116455, "global_step": 455157, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0858373641967773, "global_step": 455158, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.123500347137451, "global_step": 455159, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.080383539199829, "global_step": 455160, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9972516298294067, "global_step": 455161, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0426857471466064, "global_step": 455162, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.019645929336548, "global_step": 455163, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0664875507354736, "global_step": 455164, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.123204231262207, "global_step": 455165, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.012157440185547, "global_step": 455166, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9981364011764526, "global_step": 455167, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0628488063812256, "global_step": 455168, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.068312168121338, "global_step": 455169, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0837631225585938, "global_step": 455170, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.053433418273926, "global_step": 455171, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.111304521560669, "global_step": 455172, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0133144855499268, "global_step": 455173, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0551834106445312, "global_step": 455174, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.03619384765625, "global_step": 455175, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9914194345474243, "global_step": 455176, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.098336935043335, "global_step": 455177, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.029247999191284, "global_step": 455178, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0656728744506836, "global_step": 455179, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0777461528778076, "global_step": 455180, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.014468193054199, "global_step": 455181, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0648064613342285, "global_step": 455182, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.043468713760376, "global_step": 455183, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.054447650909424, "global_step": 455184, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.092097520828247, "global_step": 455185, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.108391523361206, "global_step": 455186, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.23738431930542, "global_step": 455187, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.016589641571045, "global_step": 455188, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.073246717453003, "global_step": 455189, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.047173261642456, "global_step": 455190, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1616225242614746, "global_step": 455191, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.002227544784546, "global_step": 455192, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.105698347091675, "global_step": 455193, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0384860038757324, "global_step": 455194, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.070077896118164, "global_step": 455195, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0603795051574707, "global_step": 455196, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9839309453964233, "global_step": 455197, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0532212257385254, "global_step": 455198, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.148744821548462, "global_step": 455199, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1155898571014404, "global_step": 455200, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.06001353263855, "global_step": 455201, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0811362266540527, "global_step": 455202, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0449769496917725, "global_step": 455203, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0475759506225586, "global_step": 455204, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.125115394592285, "global_step": 455205, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1090786457061768, "global_step": 455206, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.073573112487793, "global_step": 455207, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.112431764602661, "global_step": 455208, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0737364292144775, "global_step": 455209, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0352039337158203, "global_step": 455210, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.133928060531616, "global_step": 455211, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.985642910003662, "global_step": 455212, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0505895614624023, "global_step": 455213, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.08120059967041, "global_step": 455214, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9862102270126343, "global_step": 455215, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.067990779876709, "global_step": 455216, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0266330242156982, "global_step": 455217, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0953242778778076, "global_step": 455218, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1116819381713867, "global_step": 455219, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.042435884475708, "global_step": 455220, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.028193950653076, "global_step": 455221, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.186310291290283, "global_step": 455222, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0503199100494385, "global_step": 455223, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.053323984146118, "global_step": 455224, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1849355697631836, "global_step": 455225, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1189653873443604, "global_step": 455226, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0547380447387695, "global_step": 455227, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.132864236831665, "global_step": 455228, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0665171146392822, "global_step": 455229, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.013572931289673, "global_step": 455230, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.078493118286133, "global_step": 455231, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0251379013061523, "global_step": 455232, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0310192108154297, "global_step": 455233, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0432071685791016, "global_step": 455234, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.05810284614563, "global_step": 455235, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9610192775726318, "global_step": 455236, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0824103355407715, "global_step": 455237, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1031041145324707, "global_step": 455238, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9883173704147339, "global_step": 455239, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0647854804992676, "global_step": 455240, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.051788806915283, "global_step": 455241, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9132184982299805, "global_step": 455242, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1191189289093018, "global_step": 455243, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.060783863067627, "global_step": 455244, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1684272289276123, "global_step": 455245, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.070543050765991, "global_step": 455246, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1495673656463623, "global_step": 455247, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.110747814178467, "global_step": 455248, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0610151290893555, "global_step": 455249, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1177892684936523, "global_step": 455250, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.080629348754883, "global_step": 455251, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.060394763946533, "global_step": 455252, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0966615676879883, "global_step": 455253, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0609397888183594, "global_step": 455254, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0014801025390625, "global_step": 455255, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.074631929397583, "global_step": 455256, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0779905319213867, "global_step": 455257, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1231820583343506, "global_step": 455258, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.099518060684204, "global_step": 455259, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.04496693611145, "global_step": 455260, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.146962881088257, "global_step": 455261, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0598080158233643, "global_step": 455262, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1838200092315674, "global_step": 455263, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1138203144073486, "global_step": 455264, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0463085174560547, "global_step": 455265, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.080122947692871, "global_step": 455266, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.08489990234375, "global_step": 455267, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.118654727935791, "global_step": 455268, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.161353588104248, "global_step": 455269, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9571672677993774, "global_step": 455270, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.048459529876709, "global_step": 455271, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.132744789123535, "global_step": 455272, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0258843898773193, "global_step": 455273, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.082993745803833, "global_step": 455274, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.002070903778076, "global_step": 455275, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.084038734436035, "global_step": 455276, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9993993043899536, "global_step": 455277, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.063572883605957, "global_step": 455278, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.164400815963745, "global_step": 455279, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0349059104919434, "global_step": 455280, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.087219476699829, "global_step": 455281, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0475447177886963, "global_step": 455282, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9962939023971558, "global_step": 455283, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.161641836166382, "global_step": 455284, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.072152853012085, "global_step": 455285, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.070216417312622, "global_step": 455286, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.103938102722168, "global_step": 455287, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0707802772521973, "global_step": 455288, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.006624937057495, "global_step": 455289, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.086636781692505, "global_step": 455290, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.091376781463623, "global_step": 455291, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.044013500213623, "global_step": 455292, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.074751853942871, "global_step": 455293, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0947160720825195, "global_step": 455294, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0551462173461914, "global_step": 455295, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.023582935333252, "global_step": 455296, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0974090099334717, "global_step": 455297, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.193561553955078, "global_step": 455298, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1141068935394287, "global_step": 455299, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0878946781158447, "global_step": 455300, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.032566785812378, "global_step": 455301, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.118823766708374, "global_step": 455302, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.050842523574829, "global_step": 455303, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1402320861816406, "global_step": 455304, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.017338275909424, "global_step": 455305, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.050143241882324, "global_step": 455306, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.041013479232788, "global_step": 455307, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0618362426757812, "global_step": 455308, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9506075382232666, "global_step": 455309, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0150065422058105, "global_step": 455310, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.106661558151245, "global_step": 455311, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.048772096633911, "global_step": 455312, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0509490966796875, "global_step": 455313, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.133361577987671, "global_step": 455314, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0501480102539062, "global_step": 455315, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1495790481567383, "global_step": 455316, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0314364433288574, "global_step": 455317, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1856069564819336, "global_step": 455318, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1914896965026855, "global_step": 455319, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.101759195327759, "global_step": 455320, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0528347492218018, "global_step": 455321, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9925023317337036, "global_step": 455322, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.985385537147522, "global_step": 455323, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.110588550567627, "global_step": 455324, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0807456970214844, "global_step": 455325, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.105198383331299, "global_step": 455326, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.00093674659729, "global_step": 455327, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1009035110473633, "global_step": 455328, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0163800716400146, "global_step": 455329, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0103187561035156, "global_step": 455330, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.076474189758301, "global_step": 455331, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1525635719299316, "global_step": 455332, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.176177501678467, "global_step": 455333, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0672178268432617, "global_step": 455334, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.057110548019409, "global_step": 455335, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.2040507793426514, "global_step": 455336, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.078564405441284, "global_step": 455337, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.061042308807373, "global_step": 455338, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.043487548828125, "global_step": 455339, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1170899868011475, "global_step": 455340, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.121644973754883, "global_step": 455341, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.122309684753418, "global_step": 455342, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0097177028656006, "global_step": 455343, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0723555088043213, "global_step": 455344, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0762734413146973, "global_step": 455345, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.13677978515625, "global_step": 455346, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.055419445037842, "global_step": 455347, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.063758373260498, "global_step": 455348, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1104912757873535, "global_step": 455349, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0131523609161377, "global_step": 455350, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0701215267181396, "global_step": 455351, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.055811643600464, "global_step": 455352, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.080085515975952, "global_step": 455353, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1205201148986816, "global_step": 455354, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0289573669433594, "global_step": 455355, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0546023845672607, "global_step": 455356, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0647661685943604, "global_step": 455357, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0531392097473145, "global_step": 455358, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.060300827026367, "global_step": 455359, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.06302809715271, "global_step": 455360, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9931944608688354, "global_step": 455361, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0689101219177246, "global_step": 455362, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.980534315109253, "global_step": 455363, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0287370681762695, "global_step": 455364, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0285050868988037, "global_step": 455365, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0430965423583984, "global_step": 455366, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0886783599853516, "global_step": 455367, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.126796245574951, "global_step": 455368, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.087820053100586, "global_step": 455369, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.999347448348999, "global_step": 455370, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1607906818389893, "global_step": 455371, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0732169151306152, "global_step": 455372, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0637614727020264, "global_step": 455373, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1220743656158447, "global_step": 455374, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0986921787261963, "global_step": 455375, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.092952013015747, "global_step": 455376, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.024550676345825, "global_step": 455377, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0647995471954346, "global_step": 455378, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.030099391937256, "global_step": 455379, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0348610877990723, "global_step": 455380, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.046624183654785, "global_step": 455381, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0653932094573975, "global_step": 455382, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0892860889434814, "global_step": 455383, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.084193468093872, "global_step": 455384, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1599137783050537, "global_step": 455385, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0497398376464844, "global_step": 455386, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.2033329010009766, "global_step": 455387, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.042917013168335, "global_step": 455388, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0787951946258545, "global_step": 455389, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.012766122817993, "global_step": 455390, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.12801456451416, "global_step": 455391, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9921090602874756, "global_step": 455392, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.047725200653076, "global_step": 455393, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.090880870819092, "global_step": 455394, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0677330493927, "global_step": 455395, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.055271863937378, "global_step": 455396, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0939724445343018, "global_step": 455397, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9997481107711792, "global_step": 455398, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0484721660614014, "global_step": 455399, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0040295124053955, "global_step": 455400, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0962395668029785, "global_step": 455401, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0701096057891846, "global_step": 455402, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.082620620727539, "global_step": 455403, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.069523334503174, "global_step": 455404, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.011995315551758, "global_step": 455405, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.059762477874756, "global_step": 455406, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0699429512023926, "global_step": 455407, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.086082696914673, "global_step": 455408, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.075800895690918, "global_step": 455409, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0593366622924805, "global_step": 455410, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0840296745300293, "global_step": 455411, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1079206466674805, "global_step": 455412, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.105903148651123, "global_step": 455413, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1199612617492676, "global_step": 455414, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1137914657592773, "global_step": 455415, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9988611936569214, "global_step": 455416, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.037207841873169, "global_step": 455417, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1128411293029785, "global_step": 455418, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0845024585723877, "global_step": 455419, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.065821647644043, "global_step": 455420, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0250911712646484, "global_step": 455421, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1513586044311523, "global_step": 455422, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.098278522491455, "global_step": 455423, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.092298984527588, "global_step": 455424, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0437982082366943, "global_step": 455425, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.079458475112915, "global_step": 455426, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9726200103759766, "global_step": 455427, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.067379951477051, "global_step": 455428, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.139357566833496, "global_step": 455429, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.122738838195801, "global_step": 455430, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.020827531814575, "global_step": 455431, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0845067501068115, "global_step": 455432, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.012782096862793, "global_step": 455433, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.006211280822754, "global_step": 455434, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0084009170532227, "global_step": 455435, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.127744674682617, "global_step": 455436, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0400919914245605, "global_step": 455437, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0008745193481445, "global_step": 455438, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1038923263549805, "global_step": 455439, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.069242000579834, "global_step": 455440, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0786993503570557, "global_step": 455441, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.138728618621826, "global_step": 455442, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.041295051574707, "global_step": 455443, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0547499656677246, "global_step": 455444, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0647454261779785, "global_step": 455445, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.06884503364563, "global_step": 455446, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.03364896774292, "global_step": 455447, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1320242881774902, "global_step": 455448, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0642566680908203, "global_step": 455449, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0922539234161377, "global_step": 455450, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0206472873687744, "global_step": 455451, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.034327268600464, "global_step": 455452, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9941906929016113, "global_step": 455453, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1327126026153564, "global_step": 455454, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1027355194091797, "global_step": 455455, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0578205585479736, "global_step": 455456, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.069554328918457, "global_step": 455457, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.003917932510376, "global_step": 455458, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.040942907333374, "global_step": 455459, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1534523963928223, "global_step": 455460, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1434993743896484, "global_step": 455461, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.045044422149658, "global_step": 455462, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0704286098480225, "global_step": 455463, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1325273513793945, "global_step": 455464, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.119002342224121, "global_step": 455465, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0852012634277344, "global_step": 455466, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0271077156066895, "global_step": 455467, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.030683994293213, "global_step": 455468, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.099186658859253, "global_step": 455469, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.010240316390991, "global_step": 455470, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.07889723777771, "global_step": 455471, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1220219135284424, "global_step": 455472, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.127291679382324, "global_step": 455473, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1181037425994873, "global_step": 455474, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0889687538146973, "global_step": 455475, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1000959873199463, "global_step": 455476, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0558183193206787, "global_step": 455477, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.043461561203003, "global_step": 455478, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.143725633621216, "global_step": 455479, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.034608840942383, "global_step": 455480, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1036903858184814, "global_step": 455481, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0954113006591797, "global_step": 455482, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.995846152305603, "global_step": 455483, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0379276275634766, "global_step": 455484, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0765810012817383, "global_step": 455485, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0917696952819824, "global_step": 455486, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.06815505027771, "global_step": 455487, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.018670082092285, "global_step": 455488, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9900038242340088, "global_step": 455489, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.069460868835449, "global_step": 455490, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.042510747909546, "global_step": 455491, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1133434772491455, "global_step": 455492, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9827589988708496, "global_step": 455493, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.106804370880127, "global_step": 455494, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.123588800430298, "global_step": 455495, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.186824083328247, "global_step": 455496, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.201047420501709, "global_step": 455497, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.021216869354248, "global_step": 455498, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.112272024154663, "global_step": 455499, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1845345497131348, "global_step": 455500, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1973562240600586, "global_step": 455501, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0249669551849365, "global_step": 455502, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.114849805831909, "global_step": 455503, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.054638385772705, "global_step": 455504, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1036033630371094, "global_step": 455505, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.062649726867676, "global_step": 455506, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.109069347381592, "global_step": 455507, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0974104404449463, "global_step": 455508, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.058241844177246, "global_step": 455509, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.139958143234253, "global_step": 455510, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0517923831939697, "global_step": 455511, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1931233406066895, "global_step": 455512, "epoch": 819, "lr": 5e-05}
{"train_loss": 1.9805572032928467, "global_step": 455513, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.152446985244751, "global_step": 455514, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.066850423812866, "global_step": 455515, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.040832281112671, "global_step": 455516, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.031134843826294, "global_step": 455517, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.026254653930664, "global_step": 455518, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.105104446411133, "global_step": 455519, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0503909587860107, "global_step": 455520, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.236961603164673, "global_step": 455521, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1470863819122314, "global_step": 455522, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1600821018218994, "global_step": 455523, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0596275329589844, "global_step": 455524, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1390724182128906, "global_step": 455525, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1609127521514893, "global_step": 455526, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.029848575592041, "global_step": 455527, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.033078193664551, "global_step": 455528, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.152068853378296, "global_step": 455529, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.147400379180908, "global_step": 455530, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0382165908813477, "global_step": 455531, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.09688401222229, "global_step": 455532, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1049208641052246, "global_step": 455533, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0952489376068115, "global_step": 455534, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0909371376037598, "global_step": 455535, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0734219551086426, "global_step": 455536, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.005990982055664, "global_step": 455537, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.061147451400757, "global_step": 455538, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.2081680297851562, "global_step": 455539, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0534861087799072, "global_step": 455540, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1101295948028564, "global_step": 455541, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0905768871307373, "global_step": 455542, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0850889682769775, "global_step": 455543, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1060121059417725, "global_step": 455544, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0776047706604004, "global_step": 455545, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0915169715881348, "global_step": 455546, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0959606170654297, "global_step": 455547, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.16428542137146, "global_step": 455548, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0754306316375732, "global_step": 455549, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.007908344268799, "global_step": 455550, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.181058406829834, "global_step": 455551, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.099170684814453, "global_step": 455552, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.131260633468628, "global_step": 455553, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1113457679748535, "global_step": 455554, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.092311382293701, "global_step": 455555, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.087268590927124, "global_step": 455556, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.1199355125427246, "global_step": 455557, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0429253578186035, "global_step": 455558, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0661003589630127, "global_step": 455559, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0599238872528076, "global_step": 455560, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.088472366333008, "global_step": 455561, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.069920778274536, "global_step": 455562, "epoch": 819, "lr": 5e-05}
{"train_loss": 2.0417988300323486, "global_step": 455563, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.174159288406372, "global_step": 455564, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0956223011016846, "global_step": 455565, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.06138277053833, "global_step": 455566, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9769152402877808, "global_step": 455567, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0636754035949707, "global_step": 455568, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1336545944213867, "global_step": 455569, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0742428302764893, "global_step": 455570, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1593217849731445, "global_step": 455571, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0862884521484375, "global_step": 455572, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0393640995025635, "global_step": 455573, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.035430431365967, "global_step": 455574, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0278444290161133, "global_step": 455575, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1025497913360596, "global_step": 455576, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0079405307769775, "global_step": 455577, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9878379106521606, "global_step": 455578, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0025908946990967, "global_step": 455579, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0100834369659424, "global_step": 455580, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.013150691986084, "global_step": 455581, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0311570167541504, "global_step": 455582, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1413962841033936, "global_step": 455583, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0393807888031006, "global_step": 455584, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.133413791656494, "global_step": 455585, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1506900787353516, "global_step": 455586, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0167646408081055, "global_step": 455587, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1128957271575928, "global_step": 455588, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.00276517868042, "global_step": 455589, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1041500568389893, "global_step": 455590, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0707836151123047, "global_step": 455591, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0258216857910156, "global_step": 455592, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0459086894989014, "global_step": 455593, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.104914665222168, "global_step": 455594, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0431597232818604, "global_step": 455595, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9691184759140015, "global_step": 455596, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.053629159927368, "global_step": 455597, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.988147497177124, "global_step": 455598, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9989463090896606, "global_step": 455599, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0501534938812256, "global_step": 455600, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0753509998321533, "global_step": 455601, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.03658390045166, "global_step": 455602, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.017834424972534, "global_step": 455603, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1033058166503906, "global_step": 455604, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.042452573776245, "global_step": 455605, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.128791093826294, "global_step": 455606, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.062486410140991, "global_step": 455607, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0590856075286865, "global_step": 455608, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9999114274978638, "global_step": 455609, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.008620262145996, "global_step": 455610, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.067711591720581, "global_step": 455611, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0538103580474854, "global_step": 455612, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1101455688476562, "global_step": 455613, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.072453737258911, "global_step": 455614, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0628743171691895, "global_step": 455615, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0510058403015137, "global_step": 455616, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.082392930984497, "global_step": 455617, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0660738945007324, "global_step": 455618, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0180366039276123, "global_step": 455619, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.130570888519287, "global_step": 455620, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1064746379852295, "global_step": 455621, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.095508575439453, "global_step": 455622, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1231284141540527, "global_step": 455623, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.023880958557129, "global_step": 455624, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.068953037261963, "global_step": 455625, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9811782836914062, "global_step": 455626, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.988073468208313, "global_step": 455627, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.043349027633667, "global_step": 455628, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.981908917427063, "global_step": 455629, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.059067487716675, "global_step": 455630, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1017229557037354, "global_step": 455631, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.12528657913208, "global_step": 455632, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.031059980392456, "global_step": 455633, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.085357189178467, "global_step": 455634, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0901904106140137, "global_step": 455635, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.089224100112915, "global_step": 455636, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0765187740325928, "global_step": 455637, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9957941770553589, "global_step": 455638, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9579883813858032, "global_step": 455639, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0476551055908203, "global_step": 455640, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.168004274368286, "global_step": 455641, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1023454666137695, "global_step": 455642, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1071221828460693, "global_step": 455643, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0668373107910156, "global_step": 455644, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0175631046295166, "global_step": 455645, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.015000343322754, "global_step": 455646, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.141040802001953, "global_step": 455647, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.030773401260376, "global_step": 455648, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9833904504776, "global_step": 455649, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9723608493804932, "global_step": 455650, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.066470146179199, "global_step": 455651, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.06490421295166, "global_step": 455652, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.045506238937378, "global_step": 455653, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0849366188049316, "global_step": 455654, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.08770751953125, "global_step": 455655, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0244228839874268, "global_step": 455656, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0567314624786377, "global_step": 455657, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9982388019561768, "global_step": 455658, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0537421703338623, "global_step": 455659, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0842506885528564, "global_step": 455660, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0614185333251953, "global_step": 455661, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.07698655128479, "global_step": 455662, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1216671466827393, "global_step": 455663, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0164294242858887, "global_step": 455664, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0753815174102783, "global_step": 455665, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9965099096298218, "global_step": 455666, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0723700523376465, "global_step": 455667, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0810470581054688, "global_step": 455668, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1265668869018555, "global_step": 455669, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0254406929016113, "global_step": 455670, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0809009075164795, "global_step": 455671, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.045764684677124, "global_step": 455672, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1026611328125, "global_step": 455673, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1182327270507812, "global_step": 455674, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.054741144180298, "global_step": 455675, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.017443895339966, "global_step": 455676, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.124351978302002, "global_step": 455677, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.99240243434906, "global_step": 455678, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.027467727661133, "global_step": 455679, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1130473613739014, "global_step": 455680, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0191454887390137, "global_step": 455681, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0258493423461914, "global_step": 455682, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0421760082244873, "global_step": 455683, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.045311450958252, "global_step": 455684, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0070698261260986, "global_step": 455685, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.161337375640869, "global_step": 455686, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0435800552368164, "global_step": 455687, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9619567394256592, "global_step": 455688, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1395349502563477, "global_step": 455689, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1140623092651367, "global_step": 455690, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0363423824310303, "global_step": 455691, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.026881694793701, "global_step": 455692, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.052004814147949, "global_step": 455693, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9715954065322876, "global_step": 455694, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0193424224853516, "global_step": 455695, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.015505075454712, "global_step": 455696, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0728535652160645, "global_step": 455697, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.07460618019104, "global_step": 455698, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9778709411621094, "global_step": 455699, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.060293674468994, "global_step": 455700, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0788826942443848, "global_step": 455701, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0856521129608154, "global_step": 455702, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0226330757141113, "global_step": 455703, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.104249954223633, "global_step": 455704, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.027036666870117, "global_step": 455705, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0713951587677, "global_step": 455706, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0097312927246094, "global_step": 455707, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0470621585845947, "global_step": 455708, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.016481876373291, "global_step": 455709, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.057927370071411, "global_step": 455710, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.071979284286499, "global_step": 455711, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.086294651031494, "global_step": 455712, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0045454502105713, "global_step": 455713, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1145424842834473, "global_step": 455714, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.005537986755371, "global_step": 455715, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.013974905014038, "global_step": 455716, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0304152965545654, "global_step": 455717, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0172269344329834, "global_step": 455718, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0161802768707275, "global_step": 455719, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.940280795097351, "global_step": 455720, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.127821445465088, "global_step": 455721, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.121701955795288, "global_step": 455722, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0835835933685303, "global_step": 455723, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9849132299423218, "global_step": 455724, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.034930467605591, "global_step": 455725, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0246312618255615, "global_step": 455726, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.066643476486206, "global_step": 455727, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1219189167022705, "global_step": 455728, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1361734867095947, "global_step": 455729, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0621917247772217, "global_step": 455730, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.033503532409668, "global_step": 455731, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0025837421417236, "global_step": 455732, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.089897632598877, "global_step": 455733, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.095931053161621, "global_step": 455734, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.963301420211792, "global_step": 455735, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.026517868041992, "global_step": 455736, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.039781093597412, "global_step": 455737, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1246278285980225, "global_step": 455738, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1591320037841797, "global_step": 455739, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0901832580566406, "global_step": 455740, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0020525455474854, "global_step": 455741, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.033714532852173, "global_step": 455742, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.055306911468506, "global_step": 455743, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.033642053604126, "global_step": 455744, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.025909662246704, "global_step": 455745, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.035811185836792, "global_step": 455746, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1484971046447754, "global_step": 455747, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0955116748809814, "global_step": 455748, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1478779315948486, "global_step": 455749, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.010587692260742, "global_step": 455750, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0671980381011963, "global_step": 455751, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.093898057937622, "global_step": 455752, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.04297137260437, "global_step": 455753, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1621007919311523, "global_step": 455754, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0442557334899902, "global_step": 455755, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.174083948135376, "global_step": 455756, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9982316493988037, "global_step": 455757, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0878257751464844, "global_step": 455758, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.059004545211792, "global_step": 455759, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9667913913726807, "global_step": 455760, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1179826259613037, "global_step": 455761, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0168616771698, "global_step": 455762, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.09409499168396, "global_step": 455763, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.053175687789917, "global_step": 455764, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.04909610748291, "global_step": 455765, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1267151832580566, "global_step": 455766, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1088273525238037, "global_step": 455767, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9843523502349854, "global_step": 455768, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.119847536087036, "global_step": 455769, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1516072750091553, "global_step": 455770, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.04014253616333, "global_step": 455771, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.098752975463867, "global_step": 455772, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.068392038345337, "global_step": 455773, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9814825057983398, "global_step": 455774, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0824527740478516, "global_step": 455775, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1281228065490723, "global_step": 455776, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.109431266784668, "global_step": 455777, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0637197494506836, "global_step": 455778, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0910532474517822, "global_step": 455779, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.100102186203003, "global_step": 455780, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0143752098083496, "global_step": 455781, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.09324049949646, "global_step": 455782, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1487948894500732, "global_step": 455783, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.08404803276062, "global_step": 455784, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0838558673858643, "global_step": 455785, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1152772903442383, "global_step": 455786, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0420005321502686, "global_step": 455787, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0861494541168213, "global_step": 455788, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0444624423980713, "global_step": 455789, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1411941051483154, "global_step": 455790, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0004358291625977, "global_step": 455791, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.036757230758667, "global_step": 455792, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1592304706573486, "global_step": 455793, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.072565793991089, "global_step": 455794, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.097567558288574, "global_step": 455795, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0874671936035156, "global_step": 455796, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.076162815093994, "global_step": 455797, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.106914758682251, "global_step": 455798, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1666414737701416, "global_step": 455799, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.063490629196167, "global_step": 455800, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0437495708465576, "global_step": 455801, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.179408550262451, "global_step": 455802, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.134359836578369, "global_step": 455803, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.079052686691284, "global_step": 455804, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.006615400314331, "global_step": 455805, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.017786741256714, "global_step": 455806, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0540993213653564, "global_step": 455807, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1361875534057617, "global_step": 455808, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.015726089477539, "global_step": 455809, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1391823291778564, "global_step": 455810, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.056041717529297, "global_step": 455811, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.076695680618286, "global_step": 455812, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0200235843658447, "global_step": 455813, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1033599376678467, "global_step": 455814, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1228761672973633, "global_step": 455815, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.01835298538208, "global_step": 455816, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1048483848571777, "global_step": 455817, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.051732301712036, "global_step": 455818, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1537113189697266, "global_step": 455819, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0787646770477295, "global_step": 455820, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.156019926071167, "global_step": 455821, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.093839406967163, "global_step": 455822, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1799347400665283, "global_step": 455823, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9268507957458496, "global_step": 455824, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.051626682281494, "global_step": 455825, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.119429588317871, "global_step": 455826, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0503439903259277, "global_step": 455827, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.138192892074585, "global_step": 455828, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.06174635887146, "global_step": 455829, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0882458686828613, "global_step": 455830, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0539886951446533, "global_step": 455831, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9999423027038574, "global_step": 455832, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.036458730697632, "global_step": 455833, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.013526439666748, "global_step": 455834, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.042890787124634, "global_step": 455835, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.07433819770813, "global_step": 455836, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.131505012512207, "global_step": 455837, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1074554920196533, "global_step": 455838, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0589263439178467, "global_step": 455839, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0666768550872803, "global_step": 455840, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1512258052825928, "global_step": 455841, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0321221351623535, "global_step": 455842, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.081570863723755, "global_step": 455843, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0640664100646973, "global_step": 455844, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.10203218460083, "global_step": 455845, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0612869262695312, "global_step": 455846, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0835025310516357, "global_step": 455847, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9575321674346924, "global_step": 455848, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1298842430114746, "global_step": 455849, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.091653823852539, "global_step": 455850, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0704424381256104, "global_step": 455851, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0889194011688232, "global_step": 455852, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0826034545898438, "global_step": 455853, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9172616004943848, "global_step": 455854, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.092287063598633, "global_step": 455855, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.024251699447632, "global_step": 455856, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0223591327667236, "global_step": 455857, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0453946590423584, "global_step": 455858, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0596072673797607, "global_step": 455859, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.031770944595337, "global_step": 455860, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.083601713180542, "global_step": 455861, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.078827142715454, "global_step": 455862, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0081374645233154, "global_step": 455863, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9687671661376953, "global_step": 455864, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1414318084716797, "global_step": 455865, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.063143253326416, "global_step": 455866, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1482343673706055, "global_step": 455867, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0943331718444824, "global_step": 455868, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0732288360595703, "global_step": 455869, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0473766326904297, "global_step": 455870, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.041632890701294, "global_step": 455871, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.022286891937256, "global_step": 455872, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.057436466217041, "global_step": 455873, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0648398399353027, "global_step": 455874, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0766100883483887, "global_step": 455875, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.114734649658203, "global_step": 455876, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0700008869171143, "global_step": 455877, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.03273606300354, "global_step": 455878, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.185210704803467, "global_step": 455879, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9657565355300903, "global_step": 455880, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0088248252868652, "global_step": 455881, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0728259086608887, "global_step": 455882, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0882320404052734, "global_step": 455883, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.106595754623413, "global_step": 455884, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1339731216430664, "global_step": 455885, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.049931287765503, "global_step": 455886, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0922627449035645, "global_step": 455887, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.131582260131836, "global_step": 455888, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.069094657897949, "global_step": 455889, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0865848064422607, "global_step": 455890, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0559980869293213, "global_step": 455891, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9721652269363403, "global_step": 455892, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0269503593444824, "global_step": 455893, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9498224258422852, "global_step": 455894, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.132486581802368, "global_step": 455895, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.051913022994995, "global_step": 455896, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0723681449890137, "global_step": 455897, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.036586046218872, "global_step": 455898, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.129380702972412, "global_step": 455899, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.07641863822937, "global_step": 455900, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9650049209594727, "global_step": 455901, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0796961784362793, "global_step": 455902, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1330273151397705, "global_step": 455903, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.055154323577881, "global_step": 455904, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0473382472991943, "global_step": 455905, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.931321620941162, "global_step": 455906, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0777029991149902, "global_step": 455907, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0439040660858154, "global_step": 455908, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0046651363372803, "global_step": 455909, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0547969341278076, "global_step": 455910, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0674521923065186, "global_step": 455911, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.05079984664917, "global_step": 455912, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0674338340759277, "global_step": 455913, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0795717239379883, "global_step": 455914, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0681991577148438, "global_step": 455915, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0141918659210205, "global_step": 455916, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1235129833221436, "global_step": 455917, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0113935470581055, "global_step": 455918, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1204023361206055, "global_step": 455919, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.107011318206787, "global_step": 455920, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1149373054504395, "global_step": 455921, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.131488561630249, "global_step": 455922, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0492284297943115, "global_step": 455923, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.106536626815796, "global_step": 455924, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.048556089401245, "global_step": 455925, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0878286361694336, "global_step": 455926, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1330227851867676, "global_step": 455927, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0634663105010986, "global_step": 455928, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.01163387298584, "global_step": 455929, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0382184982299805, "global_step": 455930, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.084071636199951, "global_step": 455931, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.171727180480957, "global_step": 455932, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.049304962158203, "global_step": 455933, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9840131998062134, "global_step": 455934, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.113999843597412, "global_step": 455935, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0202271938323975, "global_step": 455936, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1437366008758545, "global_step": 455937, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0211198329925537, "global_step": 455938, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.054625988006592, "global_step": 455939, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.166389226913452, "global_step": 455940, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1273341178894043, "global_step": 455941, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0951592922210693, "global_step": 455942, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0898947715759277, "global_step": 455943, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9940688610076904, "global_step": 455944, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0742859840393066, "global_step": 455945, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0650949478149414, "global_step": 455946, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1193816661834717, "global_step": 455947, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.068718671798706, "global_step": 455948, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0415284633636475, "global_step": 455949, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.026501178741455, "global_step": 455950, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.129829168319702, "global_step": 455951, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.060213088989258, "global_step": 455952, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.114189386367798, "global_step": 455953, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0904123783111572, "global_step": 455954, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.019122362136841, "global_step": 455955, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.083453416824341, "global_step": 455956, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9938561916351318, "global_step": 455957, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1221084594726562, "global_step": 455958, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.072439193725586, "global_step": 455959, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.135064125061035, "global_step": 455960, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1143836975097656, "global_step": 455961, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.099466562271118, "global_step": 455962, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0563995838165283, "global_step": 455963, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0824882984161377, "global_step": 455964, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.123401641845703, "global_step": 455965, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1135711669921875, "global_step": 455966, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0180046558380127, "global_step": 455967, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0963902473449707, "global_step": 455968, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1510181427001953, "global_step": 455969, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0967483520507812, "global_step": 455970, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1327972412109375, "global_step": 455971, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0844004154205322, "global_step": 455972, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.139108657836914, "global_step": 455973, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0113649368286133, "global_step": 455974, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0336132049560547, "global_step": 455975, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.064265489578247, "global_step": 455976, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.018913984298706, "global_step": 455977, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.07777738571167, "global_step": 455978, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.084563970565796, "global_step": 455979, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0142462253570557, "global_step": 455980, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0693624019622803, "global_step": 455981, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.085698127746582, "global_step": 455982, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.117145538330078, "global_step": 455983, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1101438999176025, "global_step": 455984, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.114152431488037, "global_step": 455985, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.09285831451416, "global_step": 455986, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0534181594848633, "global_step": 455987, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.09228253364563, "global_step": 455988, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0206263065338135, "global_step": 455989, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.063232183456421, "global_step": 455990, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0000321865081787, "global_step": 455991, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.00516939163208, "global_step": 455992, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1138064861297607, "global_step": 455993, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.068681001663208, "global_step": 455994, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0967047214508057, "global_step": 455995, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1335036754608154, "global_step": 455996, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1357483863830566, "global_step": 455997, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0368518829345703, "global_step": 455998, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1011099815368652, "global_step": 455999, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.105997323989868, "global_step": 456000, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0669078826904297, "global_step": 456001, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.01652193069458, "global_step": 456002, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.111536741256714, "global_step": 456003, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.03471040725708, "global_step": 456004, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.080134868621826, "global_step": 456005, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.128359794616699, "global_step": 456006, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0845818519592285, "global_step": 456007, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.064758062362671, "global_step": 456008, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1214535236358643, "global_step": 456009, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0721709728240967, "global_step": 456010, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1245992183685303, "global_step": 456011, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.049422264099121, "global_step": 456012, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.021817207336426, "global_step": 456013, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0931293964385986, "global_step": 456014, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0719175338745117, "global_step": 456015, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.024569272994995, "global_step": 456016, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.051121950149536, "global_step": 456017, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.05212664604187, "global_step": 456018, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1296443939208984, "global_step": 456019, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.074669122695923, "global_step": 456020, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0428106784820557, "global_step": 456021, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0558974742889404, "global_step": 456022, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.084298610687256, "global_step": 456023, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.166813850402832, "global_step": 456024, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0546369552612305, "global_step": 456025, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.061868906021118, "global_step": 456026, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0459465980529785, "global_step": 456027, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.108442783355713, "global_step": 456028, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0769119262695312, "global_step": 456029, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.103309392929077, "global_step": 456030, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0314033031463623, "global_step": 456031, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1378278732299805, "global_step": 456032, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.080700397491455, "global_step": 456033, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0497097969055176, "global_step": 456034, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.083289861679077, "global_step": 456035, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.131483316421509, "global_step": 456036, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0046470165252686, "global_step": 456037, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1653192043304443, "global_step": 456038, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0567548274993896, "global_step": 456039, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.093648910522461, "global_step": 456040, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1761717796325684, "global_step": 456041, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.096282720565796, "global_step": 456042, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.069027900695801, "global_step": 456043, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.10961651802063, "global_step": 456044, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.071924924850464, "global_step": 456045, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.107621669769287, "global_step": 456046, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0611515045166016, "global_step": 456047, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.04443097114563, "global_step": 456048, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0165138244628906, "global_step": 456049, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0811104774475098, "global_step": 456050, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0469107627868652, "global_step": 456051, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.105088233947754, "global_step": 456052, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.060328245162964, "global_step": 456053, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.061175584793091, "global_step": 456054, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.018568277359009, "global_step": 456055, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.989802598953247, "global_step": 456056, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.05173659324646, "global_step": 456057, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0919370651245117, "global_step": 456058, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.020469903945923, "global_step": 456059, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0585598945617676, "global_step": 456060, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0050601959228516, "global_step": 456061, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.076002597808838, "global_step": 456062, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1253902912139893, "global_step": 456063, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.149796485900879, "global_step": 456064, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1580448150634766, "global_step": 456065, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9978615045547485, "global_step": 456066, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0970325469970703, "global_step": 456067, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0172061920166016, "global_step": 456068, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0944221019744873, "global_step": 456069, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.041524648666382, "global_step": 456070, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1112802028656006, "global_step": 456071, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.09190034866333, "global_step": 456072, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0893032550811768, "global_step": 456073, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0282135009765625, "global_step": 456074, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.030763864517212, "global_step": 456075, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.137190103530884, "global_step": 456076, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9993947744369507, "global_step": 456077, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0498876571655273, "global_step": 456078, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0285186767578125, "global_step": 456079, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.085003614425659, "global_step": 456080, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.035172462463379, "global_step": 456081, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0940394401550293, "global_step": 456082, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.008204698562622, "global_step": 456083, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1119301319122314, "global_step": 456084, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0898447036743164, "global_step": 456085, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0354905128479004, "global_step": 456086, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.058743476867676, "global_step": 456087, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0200347900390625, "global_step": 456088, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0548207759857178, "global_step": 456089, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0775208473205566, "global_step": 456090, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0636870861053467, "global_step": 456091, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0500285625457764, "global_step": 456092, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.064979076385498, "global_step": 456093, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.06758451461792, "global_step": 456094, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0741705894470215, "global_step": 456095, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1492788791656494, "global_step": 456096, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.122676134109497, "global_step": 456097, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.074035882949829, "global_step": 456098, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9944649934768677, "global_step": 456099, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0627901554107666, "global_step": 456100, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9693360328674316, "global_step": 456101, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0072743892669678, "global_step": 456102, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.078991651535034, "global_step": 456103, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1101996898651123, "global_step": 456104, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.091550588607788, "global_step": 456105, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0903642177581787, "global_step": 456106, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.082704782485962, "global_step": 456107, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0105392932891846, "global_step": 456108, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0861563682556152, "global_step": 456109, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.062143325805664, "global_step": 456110, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.038754463195801, "global_step": 456111, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0780069828033447, "global_step": 456112, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0535788536071777, "global_step": 456113, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0573604106903076, "global_step": 456114, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0493063926696777, "global_step": 456115, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0766403675079346, "global_step": 456116, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.027414083480835, "global_step": 456117, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0696496963500977, "global_step": 456118, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.093128204345703, "global_step": 456119, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0601589679718018, "global_step": 456120, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1213245391845703, "global_step": 456121, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0856947898864746, "global_step": 456122, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1744847297668457, "global_step": 456123, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.110316276550293, "global_step": 456124, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0998964309692383, "global_step": 456125, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.035172939300537, "global_step": 456126, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.065530300140381, "global_step": 456127, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.127915620803833, "global_step": 456128, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1435229778289795, "global_step": 456129, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1012818813323975, "global_step": 456130, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0662038326263428, "global_step": 456131, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1234824657440186, "global_step": 456132, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.042341947555542, "global_step": 456133, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.094590187072754, "global_step": 456134, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.180155038833618, "global_step": 456135, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0743134021759033, "global_step": 456136, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.010640859603882, "global_step": 456137, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0611417293548584, "global_step": 456138, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9819998741149902, "global_step": 456139, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.119596481323242, "global_step": 456140, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.027423858642578, "global_step": 456141, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1251003742218018, "global_step": 456142, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.075939655303955, "global_step": 456143, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.020390748977661, "global_step": 456144, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0148322582244873, "global_step": 456145, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.045780897140503, "global_step": 456146, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0526881217956543, "global_step": 456147, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0670125484466553, "global_step": 456148, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.081475257873535, "global_step": 456149, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1477065086364746, "global_step": 456150, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.137722969055176, "global_step": 456151, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0216705799102783, "global_step": 456152, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.2043941020965576, "global_step": 456153, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.133429527282715, "global_step": 456154, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0989460945129395, "global_step": 456155, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.128530979156494, "global_step": 456156, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.059926748275757, "global_step": 456157, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0705978870391846, "global_step": 456158, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1721031665802, "global_step": 456159, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.167703866958618, "global_step": 456160, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.210970878601074, "global_step": 456161, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0739848613739014, "global_step": 456162, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0102145671844482, "global_step": 456163, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0448694229125977, "global_step": 456164, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0428011417388916, "global_step": 456165, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1476247310638428, "global_step": 456166, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.145711660385132, "global_step": 456167, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1298744678497314, "global_step": 456168, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0953221321105957, "global_step": 456169, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.109096050262451, "global_step": 456170, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0571396350860596, "global_step": 456171, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.164250373840332, "global_step": 456172, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.990343689918518, "global_step": 456173, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.101003646850586, "global_step": 456174, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.040719985961914, "global_step": 456175, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1012725830078125, "global_step": 456176, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1189303398132324, "global_step": 456177, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.032301664352417, "global_step": 456178, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.036670684814453, "global_step": 456179, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.099865674972534, "global_step": 456180, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.129088878631592, "global_step": 456181, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.100339412689209, "global_step": 456182, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1429617404937744, "global_step": 456183, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.083202838897705, "global_step": 456184, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.120730400085449, "global_step": 456185, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.119741678237915, "global_step": 456186, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0989296436309814, "global_step": 456187, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.093334913253784, "global_step": 456188, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0670831203460693, "global_step": 456189, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.221684217453003, "global_step": 456190, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1686689853668213, "global_step": 456191, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0418031215667725, "global_step": 456192, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0383663177490234, "global_step": 456193, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0301871299743652, "global_step": 456194, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.062898635864258, "global_step": 456195, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.063464879989624, "global_step": 456196, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1095798015594482, "global_step": 456197, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.068653106689453, "global_step": 456198, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0799825191497803, "global_step": 456199, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.113872528076172, "global_step": 456200, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1537439823150635, "global_step": 456201, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.108301877975464, "global_step": 456202, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0303702354431152, "global_step": 456203, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1916282176971436, "global_step": 456204, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9883193969726562, "global_step": 456205, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0176892280578613, "global_step": 456206, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.05993914604187, "global_step": 456207, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.021122455596924, "global_step": 456208, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9952212572097778, "global_step": 456209, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1143176555633545, "global_step": 456210, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9674437046051025, "global_step": 456211, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0503132343292236, "global_step": 456212, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0464279651641846, "global_step": 456213, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1426453590393066, "global_step": 456214, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.040605068206787, "global_step": 456215, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.057799816131592, "global_step": 456216, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0601227283477783, "global_step": 456217, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.08744478225708, "global_step": 456218, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0494637489318848, "global_step": 456219, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1440916061401367, "global_step": 456220, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1163432598114014, "global_step": 456221, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0625877380371094, "global_step": 456222, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.021028995513916, "global_step": 456223, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0910608768463135, "global_step": 456224, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.06465482711792, "global_step": 456225, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0203051567077637, "global_step": 456226, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1022109985351562, "global_step": 456227, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1075713634490967, "global_step": 456228, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0601420402526855, "global_step": 456229, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0376782417297363, "global_step": 456230, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.119176149368286, "global_step": 456231, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.079317092895508, "global_step": 456232, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0465242862701416, "global_step": 456233, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.067451000213623, "global_step": 456234, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0625598430633545, "global_step": 456235, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0371110439300537, "global_step": 456236, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0935163497924805, "global_step": 456237, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.062751054763794, "global_step": 456238, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1383330821990967, "global_step": 456239, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0599234104156494, "global_step": 456240, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1571972370147705, "global_step": 456241, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0454225540161133, "global_step": 456242, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1131362915039062, "global_step": 456243, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0395309925079346, "global_step": 456244, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0456318855285645, "global_step": 456245, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.053260326385498, "global_step": 456246, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0318474769592285, "global_step": 456247, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.058518409729004, "global_step": 456248, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0493998527526855, "global_step": 456249, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.037191867828369, "global_step": 456250, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.145231008529663, "global_step": 456251, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9958279132843018, "global_step": 456252, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1540651321411133, "global_step": 456253, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.125095844268799, "global_step": 456254, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.97645902633667, "global_step": 456255, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0347900390625, "global_step": 456256, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.194398880004883, "global_step": 456257, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0740339756011963, "global_step": 456258, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.984415888786316, "global_step": 456259, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0783421993255615, "global_step": 456260, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.082214832305908, "global_step": 456261, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0570013523101807, "global_step": 456262, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.098079204559326, "global_step": 456263, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0699572563171387, "global_step": 456264, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.059523105621338, "global_step": 456265, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0588600635528564, "global_step": 456266, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.991570234298706, "global_step": 456267, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.05877947807312, "global_step": 456268, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0782949924468994, "global_step": 456269, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0230987071990967, "global_step": 456270, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1436305046081543, "global_step": 456271, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.107633113861084, "global_step": 456272, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0413098335266113, "global_step": 456273, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.045712471008301, "global_step": 456274, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0704185962677, "global_step": 456275, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.069052219390869, "global_step": 456276, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0385396480560303, "global_step": 456277, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0425925254821777, "global_step": 456278, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.06459379196167, "global_step": 456279, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.065728187561035, "global_step": 456280, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.073967456817627, "global_step": 456281, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1095235347747803, "global_step": 456282, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.130812644958496, "global_step": 456283, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0636768341064453, "global_step": 456284, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.115222930908203, "global_step": 456285, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.2079150676727295, "global_step": 456286, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9253566265106201, "global_step": 456287, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.063309907913208, "global_step": 456288, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0618395805358887, "global_step": 456289, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.053065538406372, "global_step": 456290, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0860595703125, "global_step": 456291, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.106555700302124, "global_step": 456292, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0691261291503906, "global_step": 456293, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0238285064697266, "global_step": 456294, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.979304552078247, "global_step": 456295, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0998995304107666, "global_step": 456296, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.074042797088623, "global_step": 456297, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.092621088027954, "global_step": 456298, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.120778799057007, "global_step": 456299, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.048156261444092, "global_step": 456300, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.034152030944824, "global_step": 456301, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0373966693878174, "global_step": 456302, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0313854217529297, "global_step": 456303, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.057907819747925, "global_step": 456304, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1595988273620605, "global_step": 456305, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0133025646209717, "global_step": 456306, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1034469604492188, "global_step": 456307, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0756022930145264, "global_step": 456308, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.095127582550049, "global_step": 456309, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0839364528656006, "global_step": 456310, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.099769353866577, "global_step": 456311, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1326794624328613, "global_step": 456312, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0155699253082275, "global_step": 456313, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.987820029258728, "global_step": 456314, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1049067974090576, "global_step": 456315, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.027761459350586, "global_step": 456316, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.089155673980713, "global_step": 456317, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0199217796325684, "global_step": 456318, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0289053916931152, "global_step": 456319, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.154193878173828, "global_step": 456320, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9901708364486694, "global_step": 456321, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.115751266479492, "global_step": 456322, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0745913982391357, "global_step": 456323, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0933077335357666, "global_step": 456324, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.124541759490967, "global_step": 456325, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.119716167449951, "global_step": 456326, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0375959873199463, "global_step": 456327, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1279687881469727, "global_step": 456328, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0694897174835205, "global_step": 456329, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.021183490753174, "global_step": 456330, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0947651863098145, "global_step": 456331, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.152374267578125, "global_step": 456332, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.048903703689575, "global_step": 456333, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0642054080963135, "global_step": 456334, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.13002610206604, "global_step": 456335, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0381999015808105, "global_step": 456336, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0651159286499023, "global_step": 456337, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0822763442993164, "global_step": 456338, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.112502098083496, "global_step": 456339, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0037739276885986, "global_step": 456340, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.054863214492798, "global_step": 456341, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.119462251663208, "global_step": 456342, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1205992698669434, "global_step": 456343, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.127903938293457, "global_step": 456344, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.061967611312866, "global_step": 456345, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.171405553817749, "global_step": 456346, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.122858762741089, "global_step": 456347, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0332062244415283, "global_step": 456348, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.084853172302246, "global_step": 456349, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.06770920753479, "global_step": 456350, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0186617374420166, "global_step": 456351, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.046443223953247, "global_step": 456352, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.130596876144409, "global_step": 456353, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9940747022628784, "global_step": 456354, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.074272394180298, "global_step": 456355, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.06917142868042, "global_step": 456356, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0250895023345947, "global_step": 456357, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.073073625564575, "global_step": 456358, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.071094036102295, "global_step": 456359, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0638833045959473, "global_step": 456360, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1029107570648193, "global_step": 456361, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1123695373535156, "global_step": 456362, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0338351726531982, "global_step": 456363, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1045684814453125, "global_step": 456364, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1173954010009766, "global_step": 456365, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9994220733642578, "global_step": 456366, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.087897777557373, "global_step": 456367, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.072113275527954, "global_step": 456368, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0879459381103516, "global_step": 456369, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.096489191055298, "global_step": 456370, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.040126085281372, "global_step": 456371, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0511813163757324, "global_step": 456372, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1579201221466064, "global_step": 456373, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.084866523742676, "global_step": 456374, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1108486652374268, "global_step": 456375, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.043522596359253, "global_step": 456376, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0988054275512695, "global_step": 456377, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0707414150238037, "global_step": 456378, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1021387577056885, "global_step": 456379, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0171027183532715, "global_step": 456380, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.027179479598999, "global_step": 456381, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.087104320526123, "global_step": 456382, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0343072414398193, "global_step": 456383, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0204720497131348, "global_step": 456384, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0885000228881836, "global_step": 456385, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.063289165496826, "global_step": 456386, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1062378883361816, "global_step": 456387, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1635000705718994, "global_step": 456388, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0233535766601562, "global_step": 456389, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0637199878692627, "global_step": 456390, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.058708429336548, "global_step": 456391, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9810280799865723, "global_step": 456392, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0434210300445557, "global_step": 456393, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0854363441467285, "global_step": 456394, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1308233737945557, "global_step": 456395, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.136859178543091, "global_step": 456396, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0555784702301025, "global_step": 456397, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.050597667694092, "global_step": 456398, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0560202598571777, "global_step": 456399, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0395143032073975, "global_step": 456400, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9897990226745605, "global_step": 456401, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0540623664855957, "global_step": 456402, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0681822299957275, "global_step": 456403, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.152583122253418, "global_step": 456404, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0821261405944824, "global_step": 456405, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.002338171005249, "global_step": 456406, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.130927801132202, "global_step": 456407, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.132417917251587, "global_step": 456408, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0788872241973877, "global_step": 456409, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0779080390930176, "global_step": 456410, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1050868034362793, "global_step": 456411, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1071131229400635, "global_step": 456412, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0644924640655518, "global_step": 456413, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.031223773956299, "global_step": 456414, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.007817506790161, "global_step": 456415, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1774799823760986, "global_step": 456416, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0173213481903076, "global_step": 456417, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0782663822174072, "global_step": 456418, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1007564067840576, "global_step": 456419, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.109476327896118, "global_step": 456420, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0552284717559814, "global_step": 456421, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0008511543273926, "global_step": 456422, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.054640293121338, "global_step": 456423, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9521915912628174, "global_step": 456424, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.05922269821167, "global_step": 456425, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1196067333221436, "global_step": 456426, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1031956672668457, "global_step": 456427, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0699753761291504, "global_step": 456428, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.092010736465454, "global_step": 456429, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1400671005249023, "global_step": 456430, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0669474601745605, "global_step": 456431, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.018219232559204, "global_step": 456432, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9497926235198975, "global_step": 456433, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0031487941741943, "global_step": 456434, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0426785945892334, "global_step": 456435, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1519429683685303, "global_step": 456436, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.046229600906372, "global_step": 456437, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.082548141479492, "global_step": 456438, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.125035047531128, "global_step": 456439, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0563676357269287, "global_step": 456440, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0583548545837402, "global_step": 456441, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.098778486251831, "global_step": 456442, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1236300468444824, "global_step": 456443, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0280916690826416, "global_step": 456444, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.163210868835449, "global_step": 456445, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0797908306121826, "global_step": 456446, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0383341312408447, "global_step": 456447, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0813987255096436, "global_step": 456448, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.038682699203491, "global_step": 456449, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0980589389801025, "global_step": 456450, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.04964542388916, "global_step": 456451, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0614583492279053, "global_step": 456452, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0376806259155273, "global_step": 456453, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.128835678100586, "global_step": 456454, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.154797315597534, "global_step": 456455, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1337101459503174, "global_step": 456456, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.141913890838623, "global_step": 456457, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0433247089385986, "global_step": 456458, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0171868801116943, "global_step": 456459, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1191213130950928, "global_step": 456460, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0575013160705566, "global_step": 456461, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.080782890319824, "global_step": 456462, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.161113977432251, "global_step": 456463, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1162660121917725, "global_step": 456464, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0429210662841797, "global_step": 456465, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.050983428955078, "global_step": 456466, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.126030206680298, "global_step": 456467, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0262539386749268, "global_step": 456468, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0566580295562744, "global_step": 456469, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.115339517593384, "global_step": 456470, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.132059335708618, "global_step": 456471, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.028270721435547, "global_step": 456472, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0324480533599854, "global_step": 456473, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0674896240234375, "global_step": 456474, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.069927215576172, "global_step": 456475, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0170698165893555, "global_step": 456476, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1183362007141113, "global_step": 456477, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1238996982574463, "global_step": 456478, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.157689332962036, "global_step": 456479, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0769283771514893, "global_step": 456480, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0719666481018066, "global_step": 456481, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.184744119644165, "global_step": 456482, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0367674827575684, "global_step": 456483, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0615200996398926, "global_step": 456484, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1180901527404785, "global_step": 456485, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0393526554107666, "global_step": 456486, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9921820163726807, "global_step": 456487, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1376442909240723, "global_step": 456488, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0346338748931885, "global_step": 456489, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.062638759613037, "global_step": 456490, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0912833213806152, "global_step": 456491, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.152712106704712, "global_step": 456492, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0293149948120117, "global_step": 456493, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0932774543762207, "global_step": 456494, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.008613348007202, "global_step": 456495, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.073251247406006, "global_step": 456496, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.989648461341858, "global_step": 456497, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.10448956489563, "global_step": 456498, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.092879295349121, "global_step": 456499, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.177353620529175, "global_step": 456500, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0639638900756836, "global_step": 456501, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0932798385620117, "global_step": 456502, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0648114681243896, "global_step": 456503, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0859649181365967, "global_step": 456504, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0512161254882812, "global_step": 456505, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0246498584747314, "global_step": 456506, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0682449340820312, "global_step": 456507, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0940327644348145, "global_step": 456508, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.030845880508423, "global_step": 456509, "epoch": 820, "lr": 5e-05}
{"train_loss": 1.9778838157653809, "global_step": 456510, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.103325366973877, "global_step": 456511, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.028534412384033, "global_step": 456512, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.039804697036743, "global_step": 456513, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.121375322341919, "global_step": 456514, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.10892653465271, "global_step": 456515, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.122144937515259, "global_step": 456516, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.133322238922119, "global_step": 456517, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0035479068756104, "global_step": 456518, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0687735080718994, "global_step": 456519, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0764896869659424, "global_step": 456520, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.028554677963257, "global_step": 456521, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.116511583328247, "global_step": 456522, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.105846881866455, "global_step": 456523, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.090780019760132, "global_step": 456524, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0893964767456055, "global_step": 456525, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0781073570251465, "global_step": 456526, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.074233293533325, "global_step": 456527, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.1032333374023438, "global_step": 456528, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.064955472946167, "global_step": 456529, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0160086154937744, "global_step": 456530, "epoch": 820, "lr": 5e-05}
{"train_loss": 2.0711803436279297, "global_step": 456531, "epoch": 820, "lr": 5e-05, "val_loss": 5.678244590759277, "test_reconst_mse": 0.07391106337308884}
{"train_loss": 2.1325221061706543, "global_step": 456532, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.128737449645996, "global_step": 456533, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0437214374542236, "global_step": 456534, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.128343105316162, "global_step": 456535, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.104766845703125, "global_step": 456536, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0191612243652344, "global_step": 456537, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.142341375350952, "global_step": 456538, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.016946315765381, "global_step": 456539, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1116623878479004, "global_step": 456540, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.048877239227295, "global_step": 456541, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.066385269165039, "global_step": 456542, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.057159900665283, "global_step": 456543, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.056307315826416, "global_step": 456544, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0477757453918457, "global_step": 456545, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0422136783599854, "global_step": 456546, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.079885482788086, "global_step": 456547, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0499649047851562, "global_step": 456548, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.021789789199829, "global_step": 456549, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9942810535430908, "global_step": 456550, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0034167766571045, "global_step": 456551, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0311193466186523, "global_step": 456552, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.110703945159912, "global_step": 456553, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.034072160720825, "global_step": 456554, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1606216430664062, "global_step": 456555, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.059410810470581, "global_step": 456556, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.071892499923706, "global_step": 456557, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.004201889038086, "global_step": 456558, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.018778085708618, "global_step": 456559, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.037008047103882, "global_step": 456560, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.088033437728882, "global_step": 456561, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.030601739883423, "global_step": 456562, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.004288673400879, "global_step": 456563, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1011300086975098, "global_step": 456564, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0848381519317627, "global_step": 456565, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0347189903259277, "global_step": 456566, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0101606845855713, "global_step": 456567, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1057090759277344, "global_step": 456568, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.024421215057373, "global_step": 456569, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0034220218658447, "global_step": 456570, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.049879789352417, "global_step": 456571, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0620663166046143, "global_step": 456572, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.087372303009033, "global_step": 456573, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.012003183364868, "global_step": 456574, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0372188091278076, "global_step": 456575, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1046946048736572, "global_step": 456576, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1815342903137207, "global_step": 456577, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0134634971618652, "global_step": 456578, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0292654037475586, "global_step": 456579, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.134967565536499, "global_step": 456580, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0489044189453125, "global_step": 456581, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1262195110321045, "global_step": 456582, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0444717407226562, "global_step": 456583, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1343228816986084, "global_step": 456584, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.088221549987793, "global_step": 456585, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0947248935699463, "global_step": 456586, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.019474744796753, "global_step": 456587, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.088508129119873, "global_step": 456588, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.939253568649292, "global_step": 456589, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0715157985687256, "global_step": 456590, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.060380697250366, "global_step": 456591, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0686628818511963, "global_step": 456592, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.07372784614563, "global_step": 456593, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.053602457046509, "global_step": 456594, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.144767999649048, "global_step": 456595, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0652718544006348, "global_step": 456596, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.993245244026184, "global_step": 456597, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.055422782897949, "global_step": 456598, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0333807468414307, "global_step": 456599, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.016512870788574, "global_step": 456600, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.079097032546997, "global_step": 456601, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9953651428222656, "global_step": 456602, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0272984504699707, "global_step": 456603, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1262705326080322, "global_step": 456604, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0649919509887695, "global_step": 456605, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0912697315216064, "global_step": 456606, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.094719886779785, "global_step": 456607, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.057901620864868, "global_step": 456608, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.035386800765991, "global_step": 456609, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.086390733718872, "global_step": 456610, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.073467493057251, "global_step": 456611, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9972476959228516, "global_step": 456612, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.060138702392578, "global_step": 456613, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0605719089508057, "global_step": 456614, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.07188081741333, "global_step": 456615, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1137187480926514, "global_step": 456616, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.049942970275879, "global_step": 456617, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9630132913589478, "global_step": 456618, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0240988731384277, "global_step": 456619, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9794508218765259, "global_step": 456620, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0551209449768066, "global_step": 456621, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0517022609710693, "global_step": 456622, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1019492149353027, "global_step": 456623, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.014167547225952, "global_step": 456624, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.075500249862671, "global_step": 456625, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0056984424591064, "global_step": 456626, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0529613494873047, "global_step": 456627, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.060164451599121, "global_step": 456628, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1014404296875, "global_step": 456629, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.099242925643921, "global_step": 456630, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0803279876708984, "global_step": 456631, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.09979248046875, "global_step": 456632, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0320446491241455, "global_step": 456633, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.134831190109253, "global_step": 456634, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0639259815216064, "global_step": 456635, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0804381370544434, "global_step": 456636, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0815773010253906, "global_step": 456637, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.051802158355713, "global_step": 456638, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0726170539855957, "global_step": 456639, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0389816761016846, "global_step": 456640, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.985284447669983, "global_step": 456641, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.087035894393921, "global_step": 456642, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.131523609161377, "global_step": 456643, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1207115650177, "global_step": 456644, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.049819231033325, "global_step": 456645, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1029539108276367, "global_step": 456646, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1501471996307373, "global_step": 456647, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0949454307556152, "global_step": 456648, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.118332624435425, "global_step": 456649, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0309762954711914, "global_step": 456650, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1100356578826904, "global_step": 456651, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9641691446304321, "global_step": 456652, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1802263259887695, "global_step": 456653, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0431556701660156, "global_step": 456654, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0854408740997314, "global_step": 456655, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1263155937194824, "global_step": 456656, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.094799518585205, "global_step": 456657, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0494062900543213, "global_step": 456658, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.17741322517395, "global_step": 456659, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.123029947280884, "global_step": 456660, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.12322998046875, "global_step": 456661, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0436415672302246, "global_step": 456662, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1604647636413574, "global_step": 456663, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9529621601104736, "global_step": 456664, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0065667629241943, "global_step": 456665, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.061666250228882, "global_step": 456666, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9988363981246948, "global_step": 456667, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1116528511047363, "global_step": 456668, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0839133262634277, "global_step": 456669, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.158417224884033, "global_step": 456670, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0341598987579346, "global_step": 456671, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0474562644958496, "global_step": 456672, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.046525716781616, "global_step": 456673, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.900687336921692, "global_step": 456674, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.084465265274048, "global_step": 456675, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.082998275756836, "global_step": 456676, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.050471305847168, "global_step": 456677, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1158533096313477, "global_step": 456678, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0916404724121094, "global_step": 456679, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.057271957397461, "global_step": 456680, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1287827491760254, "global_step": 456681, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.015735387802124, "global_step": 456682, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.109402894973755, "global_step": 456683, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9988203048706055, "global_step": 456684, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0495245456695557, "global_step": 456685, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0100691318511963, "global_step": 456686, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.993123173713684, "global_step": 456687, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.080400228500366, "global_step": 456688, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.063603162765503, "global_step": 456689, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.029008388519287, "global_step": 456690, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.110689878463745, "global_step": 456691, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0573790073394775, "global_step": 456692, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0177266597747803, "global_step": 456693, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.106232166290283, "global_step": 456694, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1170477867126465, "global_step": 456695, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0258629322052, "global_step": 456696, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0622758865356445, "global_step": 456697, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1172797679901123, "global_step": 456698, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1096558570861816, "global_step": 456699, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.059013605117798, "global_step": 456700, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.120816230773926, "global_step": 456701, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9892687797546387, "global_step": 456702, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0733697414398193, "global_step": 456703, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.044862747192383, "global_step": 456704, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0919628143310547, "global_step": 456705, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0505104064941406, "global_step": 456706, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.150203227996826, "global_step": 456707, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0014376640319824, "global_step": 456708, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0844597816467285, "global_step": 456709, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0331685543060303, "global_step": 456710, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.083658456802368, "global_step": 456711, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1614444255828857, "global_step": 456712, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1595020294189453, "global_step": 456713, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.087460517883301, "global_step": 456714, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.046088933944702, "global_step": 456715, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0859174728393555, "global_step": 456716, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0393409729003906, "global_step": 456717, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0571532249450684, "global_step": 456718, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.12396240234375, "global_step": 456719, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9568650722503662, "global_step": 456720, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.106049060821533, "global_step": 456721, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.059581756591797, "global_step": 456722, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0514862537384033, "global_step": 456723, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0876529216766357, "global_step": 456724, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9397367238998413, "global_step": 456725, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.074326753616333, "global_step": 456726, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1179797649383545, "global_step": 456727, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.10052752494812, "global_step": 456728, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9715460538864136, "global_step": 456729, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1390538215637207, "global_step": 456730, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9850544929504395, "global_step": 456731, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.061027765274048, "global_step": 456732, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0783092975616455, "global_step": 456733, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.04789400100708, "global_step": 456734, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9422211647033691, "global_step": 456735, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.044499635696411, "global_step": 456736, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.083169460296631, "global_step": 456737, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0618417263031006, "global_step": 456738, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.090932607650757, "global_step": 456739, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0330684185028076, "global_step": 456740, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9815744161605835, "global_step": 456741, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9792304039001465, "global_step": 456742, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0492117404937744, "global_step": 456743, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.067371368408203, "global_step": 456744, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0407350063323975, "global_step": 456745, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0847668647766113, "global_step": 456746, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0146989822387695, "global_step": 456747, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.148533821105957, "global_step": 456748, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0642898082733154, "global_step": 456749, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0834224224090576, "global_step": 456750, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0582733154296875, "global_step": 456751, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.040583372116089, "global_step": 456752, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0971202850341797, "global_step": 456753, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0271239280700684, "global_step": 456754, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.198704957962036, "global_step": 456755, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0293619632720947, "global_step": 456756, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.10634446144104, "global_step": 456757, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.088793992996216, "global_step": 456758, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0953361988067627, "global_step": 456759, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0725631713867188, "global_step": 456760, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0314409732818604, "global_step": 456761, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.064896583557129, "global_step": 456762, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1286613941192627, "global_step": 456763, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.015084981918335, "global_step": 456764, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.144522190093994, "global_step": 456765, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9892148971557617, "global_step": 456766, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.089620351791382, "global_step": 456767, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0635387897491455, "global_step": 456768, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.164141893386841, "global_step": 456769, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1113011837005615, "global_step": 456770, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0631110668182373, "global_step": 456771, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0037708282470703, "global_step": 456772, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.046100616455078, "global_step": 456773, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.014935255050659, "global_step": 456774, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0908679962158203, "global_step": 456775, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.054830312728882, "global_step": 456776, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.184562921524048, "global_step": 456777, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1075775623321533, "global_step": 456778, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0247297286987305, "global_step": 456779, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0504112243652344, "global_step": 456780, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0971713066101074, "global_step": 456781, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0468666553497314, "global_step": 456782, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.092972755432129, "global_step": 456783, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.141368865966797, "global_step": 456784, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1578383445739746, "global_step": 456785, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0194904804229736, "global_step": 456786, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0538854598999023, "global_step": 456787, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0093061923980713, "global_step": 456788, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1360137462615967, "global_step": 456789, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0068726539611816, "global_step": 456790, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9544790983200073, "global_step": 456791, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0776419639587402, "global_step": 456792, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0148611068725586, "global_step": 456793, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.041093587875366, "global_step": 456794, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.060415506362915, "global_step": 456795, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0429813861846924, "global_step": 456796, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.075223684310913, "global_step": 456797, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.038032054901123, "global_step": 456798, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0012412071228027, "global_step": 456799, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1109580993652344, "global_step": 456800, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0870864391326904, "global_step": 456801, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0418241024017334, "global_step": 456802, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9828481674194336, "global_step": 456803, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.077794313430786, "global_step": 456804, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.077667713165283, "global_step": 456805, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0588319301605225, "global_step": 456806, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0930843353271484, "global_step": 456807, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0908727645874023, "global_step": 456808, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0798959732055664, "global_step": 456809, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.108168601989746, "global_step": 456810, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0343308448791504, "global_step": 456811, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1026721000671387, "global_step": 456812, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.19087290763855, "global_step": 456813, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1066393852233887, "global_step": 456814, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.082287073135376, "global_step": 456815, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0250449180603027, "global_step": 456816, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.00871205329895, "global_step": 456817, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.080871105194092, "global_step": 456818, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0284667015075684, "global_step": 456819, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1154494285583496, "global_step": 456820, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.088162660598755, "global_step": 456821, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.000412940979004, "global_step": 456822, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1904118061065674, "global_step": 456823, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1680655479431152, "global_step": 456824, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1105709075927734, "global_step": 456825, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0673623085021973, "global_step": 456826, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0449283123016357, "global_step": 456827, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1130785942077637, "global_step": 456828, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.138432025909424, "global_step": 456829, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.091641902923584, "global_step": 456830, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.030205011367798, "global_step": 456831, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.073930025100708, "global_step": 456832, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1519999504089355, "global_step": 456833, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.170009136199951, "global_step": 456834, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0756258964538574, "global_step": 456835, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1528921127319336, "global_step": 456836, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0688254833221436, "global_step": 456837, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.029402732849121, "global_step": 456838, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0475528240203857, "global_step": 456839, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9907903671264648, "global_step": 456840, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0281822681427, "global_step": 456841, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.035731315612793, "global_step": 456842, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0795531272888184, "global_step": 456843, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1095387935638428, "global_step": 456844, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.072850227355957, "global_step": 456845, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0835211277008057, "global_step": 456846, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0267133712768555, "global_step": 456847, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1113693714141846, "global_step": 456848, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.127372980117798, "global_step": 456849, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9979745149612427, "global_step": 456850, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1190717220306396, "global_step": 456851, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.146057605743408, "global_step": 456852, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.050490379333496, "global_step": 456853, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0440337657928467, "global_step": 456854, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9979381561279297, "global_step": 456855, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.114316940307617, "global_step": 456856, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9809645414352417, "global_step": 456857, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9875600337982178, "global_step": 456858, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.2276930809020996, "global_step": 456859, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0335347652435303, "global_step": 456860, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.243772268295288, "global_step": 456861, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.056976556777954, "global_step": 456862, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.058008909225464, "global_step": 456863, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.964919924736023, "global_step": 456864, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0441863536834717, "global_step": 456865, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.085838556289673, "global_step": 456866, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.032804250717163, "global_step": 456867, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0740303993225098, "global_step": 456868, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0603508949279785, "global_step": 456869, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1013057231903076, "global_step": 456870, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1171793937683105, "global_step": 456871, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0933122634887695, "global_step": 456872, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1075992584228516, "global_step": 456873, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.102726697921753, "global_step": 456874, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.05472469329834, "global_step": 456875, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0644400119781494, "global_step": 456876, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.173713445663452, "global_step": 456877, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0935797691345215, "global_step": 456878, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0864837169647217, "global_step": 456879, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0033576488494873, "global_step": 456880, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.033918857574463, "global_step": 456881, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.068725824356079, "global_step": 456882, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1692612171173096, "global_step": 456883, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.041527032852173, "global_step": 456884, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.168316125869751, "global_step": 456885, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.147520065307617, "global_step": 456886, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1436092853546143, "global_step": 456887, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1229734420776367, "global_step": 456888, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0893547534942627, "global_step": 456889, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0837745666503906, "global_step": 456890, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.010934829711914, "global_step": 456891, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0841190814971924, "global_step": 456892, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.062837839126587, "global_step": 456893, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.225083112716675, "global_step": 456894, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0701026916503906, "global_step": 456895, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1160645484924316, "global_step": 456896, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.088683605194092, "global_step": 456897, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1018848419189453, "global_step": 456898, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.057966709136963, "global_step": 456899, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0338456630706787, "global_step": 456900, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.076979398727417, "global_step": 456901, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9779727458953857, "global_step": 456902, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0151984691619873, "global_step": 456903, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0663692951202393, "global_step": 456904, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.034602165222168, "global_step": 456905, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1238508224487305, "global_step": 456906, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0777435302734375, "global_step": 456907, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.053551197052002, "global_step": 456908, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0692479610443115, "global_step": 456909, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9858664274215698, "global_step": 456910, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.106760025024414, "global_step": 456911, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.052257537841797, "global_step": 456912, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1107945442199707, "global_step": 456913, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1516129970550537, "global_step": 456914, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0750527381896973, "global_step": 456915, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1134963035583496, "global_step": 456916, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.055483102798462, "global_step": 456917, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.063389301300049, "global_step": 456918, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.071655511856079, "global_step": 456919, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9983720779418945, "global_step": 456920, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.112360954284668, "global_step": 456921, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.047480821609497, "global_step": 456922, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.111213207244873, "global_step": 456923, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0839905738830566, "global_step": 456924, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0151877403259277, "global_step": 456925, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1016199588775635, "global_step": 456926, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0287740230560303, "global_step": 456927, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1054341793060303, "global_step": 456928, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0451619625091553, "global_step": 456929, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0016863346099854, "global_step": 456930, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9853901863098145, "global_step": 456931, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1137778759002686, "global_step": 456932, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1508054733276367, "global_step": 456933, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0901169776916504, "global_step": 456934, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9569804668426514, "global_step": 456935, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.077286958694458, "global_step": 456936, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.026812791824341, "global_step": 456937, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0997097492218018, "global_step": 456938, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.045461893081665, "global_step": 456939, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0845470428466797, "global_step": 456940, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1104230880737305, "global_step": 456941, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1451315879821777, "global_step": 456942, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1113312244415283, "global_step": 456943, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.020216703414917, "global_step": 456944, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9834924936294556, "global_step": 456945, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1005160808563232, "global_step": 456946, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.113365650177002, "global_step": 456947, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.035693883895874, "global_step": 456948, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1793651580810547, "global_step": 456949, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1103031635284424, "global_step": 456950, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.010535717010498, "global_step": 456951, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1616780757904053, "global_step": 456952, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9938360452651978, "global_step": 456953, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0736520290374756, "global_step": 456954, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0205140113830566, "global_step": 456955, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.113776922225952, "global_step": 456956, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.104896068572998, "global_step": 456957, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.082672357559204, "global_step": 456958, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.070509910583496, "global_step": 456959, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0673987865448, "global_step": 456960, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1145248413085938, "global_step": 456961, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1837923526763916, "global_step": 456962, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0536866188049316, "global_step": 456963, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.062845230102539, "global_step": 456964, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.10237455368042, "global_step": 456965, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.062143564224243, "global_step": 456966, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0106515884399414, "global_step": 456967, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0564093589782715, "global_step": 456968, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.100407600402832, "global_step": 456969, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.076561450958252, "global_step": 456970, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.121112108230591, "global_step": 456971, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0298397541046143, "global_step": 456972, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.047083616256714, "global_step": 456973, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0881569385528564, "global_step": 456974, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.088959217071533, "global_step": 456975, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0885040760040283, "global_step": 456976, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0761096477508545, "global_step": 456977, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.087137222290039, "global_step": 456978, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1274890899658203, "global_step": 456979, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0484421253204346, "global_step": 456980, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.04134202003479, "global_step": 456981, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1046202182769775, "global_step": 456982, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1461386680603027, "global_step": 456983, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0058817863464355, "global_step": 456984, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1137375831604004, "global_step": 456985, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.047722339630127, "global_step": 456986, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.082575559616089, "global_step": 456987, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0906286239624023, "global_step": 456988, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9945940971374512, "global_step": 456989, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.110658884048462, "global_step": 456990, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0570034980773926, "global_step": 456991, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.092308759689331, "global_step": 456992, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.046428680419922, "global_step": 456993, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0221076011657715, "global_step": 456994, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.040667772293091, "global_step": 456995, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.07981538772583, "global_step": 456996, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0852034091949463, "global_step": 456997, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1337625980377197, "global_step": 456998, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0971641540527344, "global_step": 456999, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0685184001922607, "global_step": 457000, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0683341026306152, "global_step": 457001, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1250545978546143, "global_step": 457002, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0814826488494873, "global_step": 457003, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.119446277618408, "global_step": 457004, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1506147384643555, "global_step": 457005, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.002323865890503, "global_step": 457006, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0871965885162354, "global_step": 457007, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.04005765914917, "global_step": 457008, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0135445594787598, "global_step": 457009, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0633392333984375, "global_step": 457010, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1120550632476807, "global_step": 457011, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0690436363220215, "global_step": 457012, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.061326503753662, "global_step": 457013, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1083950996398926, "global_step": 457014, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.094716787338257, "global_step": 457015, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.062960147857666, "global_step": 457016, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0345067977905273, "global_step": 457017, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.2058265209198, "global_step": 457018, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0805327892303467, "global_step": 457019, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.049199342727661, "global_step": 457020, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.086132526397705, "global_step": 457021, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1074461936950684, "global_step": 457022, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0051114559173584, "global_step": 457023, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1676218509674072, "global_step": 457024, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.14567232131958, "global_step": 457025, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1072065830230713, "global_step": 457026, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.00537371635437, "global_step": 457027, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0624446868896484, "global_step": 457028, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0108604431152344, "global_step": 457029, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0807290077209473, "global_step": 457030, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.030144453048706, "global_step": 457031, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0645570755004883, "global_step": 457032, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.070298433303833, "global_step": 457033, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0939202308654785, "global_step": 457034, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.114711284637451, "global_step": 457035, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.060859203338623, "global_step": 457036, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.08958101272583, "global_step": 457037, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.076674461364746, "global_step": 457038, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.050797939300537, "global_step": 457039, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1310060024261475, "global_step": 457040, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0741686820983887, "global_step": 457041, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1013097763061523, "global_step": 457042, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0740652084350586, "global_step": 457043, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.014068603515625, "global_step": 457044, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.042344808578491, "global_step": 457045, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.097200632095337, "global_step": 457046, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.987714409828186, "global_step": 457047, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9958237409591675, "global_step": 457048, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.064556121826172, "global_step": 457049, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0136795043945312, "global_step": 457050, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0935933589935303, "global_step": 457051, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.091647148132324, "global_step": 457052, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.069319486618042, "global_step": 457053, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0802299976348877, "global_step": 457054, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1106650829315186, "global_step": 457055, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9982033967971802, "global_step": 457056, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0821051597595215, "global_step": 457057, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1402151584625244, "global_step": 457058, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1415047645568848, "global_step": 457059, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.092240810394287, "global_step": 457060, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.038006067276001, "global_step": 457061, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0577120780944824, "global_step": 457062, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.121537685394287, "global_step": 457063, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9729973077774048, "global_step": 457064, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0251505374908447, "global_step": 457065, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0466299057006836, "global_step": 457066, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.06117844581604, "global_step": 457067, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1042494773864746, "global_step": 457068, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.003157138824463, "global_step": 457069, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.038097858428955, "global_step": 457070, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1087498664855957, "global_step": 457071, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1057357788085938, "global_step": 457072, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0038962364196777, "global_step": 457073, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1490261554718018, "global_step": 457074, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0507984161376953, "global_step": 457075, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9798519611358643, "global_step": 457076, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0485260486602783, "global_step": 457077, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.033198118209839, "global_step": 457078, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0041470527648926, "global_step": 457079, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0601634979248047, "global_step": 457080, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1212949752807617, "global_step": 457081, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.00522518157959, "global_step": 457082, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0939080715179443, "global_step": 457083, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.135347604751587, "global_step": 457084, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0767180919647217, "global_step": 457085, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0838732719421387, "global_step": 457086, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.064213275909424, "global_step": 457087, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.059551954269409, "global_step": 457088, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0742597579956055, "global_step": 457089, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.066080331802368, "global_step": 457090, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9905418157577515, "global_step": 457091, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0791871547698975, "global_step": 457092, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0699660778045654, "global_step": 457093, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1160800457000732, "global_step": 457094, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0944983959198, "global_step": 457095, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0487213134765625, "global_step": 457096, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.081973075866699, "global_step": 457097, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0731070041656494, "global_step": 457098, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.070138931274414, "global_step": 457099, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.079218626022339, "global_step": 457100, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.051508665084839, "global_step": 457101, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0017073154449463, "global_step": 457102, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0496368408203125, "global_step": 457103, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.023958683013916, "global_step": 457104, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.014293909072876, "global_step": 457105, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1464626789093018, "global_step": 457106, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0910532474517822, "global_step": 457107, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0836338996887207, "global_step": 457108, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1679928302764893, "global_step": 457109, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9818366765975952, "global_step": 457110, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0888428688049316, "global_step": 457111, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1425366401672363, "global_step": 457112, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.129030466079712, "global_step": 457113, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1004326343536377, "global_step": 457114, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.047208070755005, "global_step": 457115, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0486040115356445, "global_step": 457116, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0118305683135986, "global_step": 457117, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1227378845214844, "global_step": 457118, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.050480842590332, "global_step": 457119, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.101691961288452, "global_step": 457120, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1401402950286865, "global_step": 457121, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1046969890594482, "global_step": 457122, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.137929677963257, "global_step": 457123, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.079967737197876, "global_step": 457124, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0907678604125977, "global_step": 457125, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0259501934051514, "global_step": 457126, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.123032569885254, "global_step": 457127, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0935027599334717, "global_step": 457128, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0544233322143555, "global_step": 457129, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0802934169769287, "global_step": 457130, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1126272678375244, "global_step": 457131, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.097548007965088, "global_step": 457132, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.071161985397339, "global_step": 457133, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1055426597595215, "global_step": 457134, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9830520153045654, "global_step": 457135, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0275371074676514, "global_step": 457136, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0439798831939697, "global_step": 457137, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0990653038024902, "global_step": 457138, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0424904823303223, "global_step": 457139, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0924086570739746, "global_step": 457140, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.004202365875244, "global_step": 457141, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0382440090179443, "global_step": 457142, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0085256099700928, "global_step": 457143, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1201181411743164, "global_step": 457144, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9947830438613892, "global_step": 457145, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0414679050445557, "global_step": 457146, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1045966148376465, "global_step": 457147, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.098536491394043, "global_step": 457148, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0300958156585693, "global_step": 457149, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0989975929260254, "global_step": 457150, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1169960498809814, "global_step": 457151, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9935473203659058, "global_step": 457152, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9942305088043213, "global_step": 457153, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1189205646514893, "global_step": 457154, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.048654317855835, "global_step": 457155, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.056771755218506, "global_step": 457156, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1133460998535156, "global_step": 457157, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0545849800109863, "global_step": 457158, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.027470827102661, "global_step": 457159, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.11911678314209, "global_step": 457160, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.11437726020813, "global_step": 457161, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0124402046203613, "global_step": 457162, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1130311489105225, "global_step": 457163, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.040689706802368, "global_step": 457164, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.052744150161743, "global_step": 457165, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1271731853485107, "global_step": 457166, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.097163200378418, "global_step": 457167, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.078029155731201, "global_step": 457168, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0982935428619385, "global_step": 457169, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.01338529586792, "global_step": 457170, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0422158241271973, "global_step": 457171, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.000148057937622, "global_step": 457172, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1067535877227783, "global_step": 457173, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.078011989593506, "global_step": 457174, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9473259449005127, "global_step": 457175, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.111487865447998, "global_step": 457176, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.057960033416748, "global_step": 457177, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.090571165084839, "global_step": 457178, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0929534435272217, "global_step": 457179, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1112418174743652, "global_step": 457180, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1295433044433594, "global_step": 457181, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.062683343887329, "global_step": 457182, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0633597373962402, "global_step": 457183, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.2231509685516357, "global_step": 457184, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.100473403930664, "global_step": 457185, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.113102912902832, "global_step": 457186, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1525464057922363, "global_step": 457187, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.050837755203247, "global_step": 457188, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0604100227355957, "global_step": 457189, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0626471042633057, "global_step": 457190, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1595847606658936, "global_step": 457191, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0235886573791504, "global_step": 457192, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.05104923248291, "global_step": 457193, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0483691692352295, "global_step": 457194, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.112687110900879, "global_step": 457195, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.183820962905884, "global_step": 457196, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.085773229598999, "global_step": 457197, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0200135707855225, "global_step": 457198, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.139071226119995, "global_step": 457199, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.047661542892456, "global_step": 457200, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.061852216720581, "global_step": 457201, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.047429323196411, "global_step": 457202, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.065232753753662, "global_step": 457203, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0798556804656982, "global_step": 457204, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0768051147460938, "global_step": 457205, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0545077323913574, "global_step": 457206, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1089229583740234, "global_step": 457207, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.051485538482666, "global_step": 457208, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.092542886734009, "global_step": 457209, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.054983139038086, "global_step": 457210, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.030672550201416, "global_step": 457211, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1491763591766357, "global_step": 457212, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1039860248565674, "global_step": 457213, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1543636322021484, "global_step": 457214, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1454434394836426, "global_step": 457215, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.049567461013794, "global_step": 457216, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0119094848632812, "global_step": 457217, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9832496643066406, "global_step": 457218, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.083307981491089, "global_step": 457219, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.104281425476074, "global_step": 457220, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1320607662200928, "global_step": 457221, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1221158504486084, "global_step": 457222, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.091388702392578, "global_step": 457223, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.127439260482788, "global_step": 457224, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0779950618743896, "global_step": 457225, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.013662338256836, "global_step": 457226, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1524417400360107, "global_step": 457227, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.046576976776123, "global_step": 457228, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1068286895751953, "global_step": 457229, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.047941207885742, "global_step": 457230, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.204526662826538, "global_step": 457231, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.078275203704834, "global_step": 457232, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0858497619628906, "global_step": 457233, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0705103874206543, "global_step": 457234, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.204219341278076, "global_step": 457235, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0053763389587402, "global_step": 457236, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1263561248779297, "global_step": 457237, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1342272758483887, "global_step": 457238, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.248049259185791, "global_step": 457239, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0354976654052734, "global_step": 457240, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.2179388999938965, "global_step": 457241, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1463613510131836, "global_step": 457242, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9983080625534058, "global_step": 457243, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1009256839752197, "global_step": 457244, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9946569204330444, "global_step": 457245, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.134326457977295, "global_step": 457246, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.129640579223633, "global_step": 457247, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.122464895248413, "global_step": 457248, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0876352787017822, "global_step": 457249, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1026341915130615, "global_step": 457250, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0995030403137207, "global_step": 457251, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.083167791366577, "global_step": 457252, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0521345138549805, "global_step": 457253, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.047057867050171, "global_step": 457254, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0403494834899902, "global_step": 457255, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1077301502227783, "global_step": 457256, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1005218029022217, "global_step": 457257, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.978210687637329, "global_step": 457258, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0628461837768555, "global_step": 457259, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9526184797286987, "global_step": 457260, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0873031616210938, "global_step": 457261, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1498379707336426, "global_step": 457262, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0143585205078125, "global_step": 457263, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.040339231491089, "global_step": 457264, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.125112771987915, "global_step": 457265, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1019880771636963, "global_step": 457266, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.010298728942871, "global_step": 457267, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.097477912902832, "global_step": 457268, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.032839775085449, "global_step": 457269, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1049883365631104, "global_step": 457270, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1153533458709717, "global_step": 457271, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.089662551879883, "global_step": 457272, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0622048377990723, "global_step": 457273, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1236016750335693, "global_step": 457274, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.052838087081909, "global_step": 457275, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0227510929107666, "global_step": 457276, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1045641899108887, "global_step": 457277, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0528621673583984, "global_step": 457278, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0680184364318848, "global_step": 457279, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9906573295593262, "global_step": 457280, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0244579315185547, "global_step": 457281, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.040621519088745, "global_step": 457282, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0323879718780518, "global_step": 457283, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0886263847351074, "global_step": 457284, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0677073001861572, "global_step": 457285, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1154351234436035, "global_step": 457286, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0720319747924805, "global_step": 457287, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1605935096740723, "global_step": 457288, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1374552249908447, "global_step": 457289, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1333537101745605, "global_step": 457290, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1602275371551514, "global_step": 457291, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.109851837158203, "global_step": 457292, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0226473808288574, "global_step": 457293, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0949535369873047, "global_step": 457294, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0384914875030518, "global_step": 457295, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0922739505767822, "global_step": 457296, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0913267135620117, "global_step": 457297, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.074584722518921, "global_step": 457298, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0182342529296875, "global_step": 457299, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0407910346984863, "global_step": 457300, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.098994731903076, "global_step": 457301, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.001535415649414, "global_step": 457302, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1331162452697754, "global_step": 457303, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0700697898864746, "global_step": 457304, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.054763078689575, "global_step": 457305, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.122288227081299, "global_step": 457306, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0444717407226562, "global_step": 457307, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0446417331695557, "global_step": 457308, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1184160709381104, "global_step": 457309, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0020816326141357, "global_step": 457310, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0039188861846924, "global_step": 457311, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0650341510772705, "global_step": 457312, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0866284370422363, "global_step": 457313, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0153677463531494, "global_step": 457314, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0495011806488037, "global_step": 457315, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.01824951171875, "global_step": 457316, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1419167518615723, "global_step": 457317, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.081448554992676, "global_step": 457318, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.039397954940796, "global_step": 457319, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.954538345336914, "global_step": 457320, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.114924907684326, "global_step": 457321, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1078543663024902, "global_step": 457322, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1159346103668213, "global_step": 457323, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0819756984710693, "global_step": 457324, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0634894371032715, "global_step": 457325, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.002096176147461, "global_step": 457326, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.083134174346924, "global_step": 457327, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.09306263923645, "global_step": 457328, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0265090465545654, "global_step": 457329, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0479350090026855, "global_step": 457330, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1868607997894287, "global_step": 457331, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1991994380950928, "global_step": 457332, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.133970260620117, "global_step": 457333, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0066847801208496, "global_step": 457334, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1022448539733887, "global_step": 457335, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.042414903640747, "global_step": 457336, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.129812240600586, "global_step": 457337, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.068617582321167, "global_step": 457338, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.068535327911377, "global_step": 457339, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.064133882522583, "global_step": 457340, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1795992851257324, "global_step": 457341, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0449585914611816, "global_step": 457342, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.035425901412964, "global_step": 457343, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1004891395568848, "global_step": 457344, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0749659538269043, "global_step": 457345, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.058440685272217, "global_step": 457346, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.036898374557495, "global_step": 457347, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1232316493988037, "global_step": 457348, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0305845737457275, "global_step": 457349, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9629253149032593, "global_step": 457350, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0798840522766113, "global_step": 457351, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.038212537765503, "global_step": 457352, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0478298664093018, "global_step": 457353, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.080594778060913, "global_step": 457354, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1399097442626953, "global_step": 457355, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.124340534210205, "global_step": 457356, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.006669521331787, "global_step": 457357, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1663262844085693, "global_step": 457358, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.161543369293213, "global_step": 457359, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9595913887023926, "global_step": 457360, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0415444374084473, "global_step": 457361, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.102137804031372, "global_step": 457362, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.104417324066162, "global_step": 457363, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1503233909606934, "global_step": 457364, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0383310317993164, "global_step": 457365, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.069263219833374, "global_step": 457366, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9940710067749023, "global_step": 457367, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.061756134033203, "global_step": 457368, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.035393238067627, "global_step": 457369, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0347399711608887, "global_step": 457370, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.108705997467041, "global_step": 457371, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.096435308456421, "global_step": 457372, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.060626983642578, "global_step": 457373, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.095745325088501, "global_step": 457374, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1554408073425293, "global_step": 457375, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0698328018188477, "global_step": 457376, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1105313301086426, "global_step": 457377, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0777523517608643, "global_step": 457378, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.064497709274292, "global_step": 457379, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0582306385040283, "global_step": 457380, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9831606149673462, "global_step": 457381, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0419394969940186, "global_step": 457382, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.072093963623047, "global_step": 457383, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0889229774475098, "global_step": 457384, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1086130142211914, "global_step": 457385, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.033332586288452, "global_step": 457386, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0998265743255615, "global_step": 457387, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.025855779647827, "global_step": 457388, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1627748012542725, "global_step": 457389, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.048384189605713, "global_step": 457390, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0554115772247314, "global_step": 457391, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9903454780578613, "global_step": 457392, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.080327033996582, "global_step": 457393, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0783066749572754, "global_step": 457394, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1339101791381836, "global_step": 457395, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.051880121231079, "global_step": 457396, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.101658344268799, "global_step": 457397, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0720736980438232, "global_step": 457398, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.082338333129883, "global_step": 457399, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0429434776306152, "global_step": 457400, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.08601450920105, "global_step": 457401, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.068510055541992, "global_step": 457402, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1462836265563965, "global_step": 457403, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.067755937576294, "global_step": 457404, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0319998264312744, "global_step": 457405, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.953152060508728, "global_step": 457406, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.168471097946167, "global_step": 457407, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1181490421295166, "global_step": 457408, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.058001756668091, "global_step": 457409, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.071686267852783, "global_step": 457410, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0974085330963135, "global_step": 457411, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1412734985351562, "global_step": 457412, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1331777572631836, "global_step": 457413, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0656816959381104, "global_step": 457414, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.09580135345459, "global_step": 457415, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.180332660675049, "global_step": 457416, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.14102840423584, "global_step": 457417, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1197988986968994, "global_step": 457418, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.13847279548645, "global_step": 457419, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1740894317626953, "global_step": 457420, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0146543979644775, "global_step": 457421, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0443620681762695, "global_step": 457422, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9801017045974731, "global_step": 457423, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0744776725769043, "global_step": 457424, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.048168420791626, "global_step": 457425, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.121367931365967, "global_step": 457426, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.062706470489502, "global_step": 457427, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.121870279312134, "global_step": 457428, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0635130405426025, "global_step": 457429, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1228837966918945, "global_step": 457430, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.136002540588379, "global_step": 457431, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.168929100036621, "global_step": 457432, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.085005044937134, "global_step": 457433, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.046233654022217, "global_step": 457434, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9593273401260376, "global_step": 457435, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.2077481746673584, "global_step": 457436, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0932819843292236, "global_step": 457437, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.058137893676758, "global_step": 457438, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.050614356994629, "global_step": 457439, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1703357696533203, "global_step": 457440, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0561306476593018, "global_step": 457441, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.070749282836914, "global_step": 457442, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1242494583129883, "global_step": 457443, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.07552170753479, "global_step": 457444, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0845608711242676, "global_step": 457445, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.109884023666382, "global_step": 457446, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1662871837615967, "global_step": 457447, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.033982515335083, "global_step": 457448, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9940381050109863, "global_step": 457449, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9621554613113403, "global_step": 457450, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.092266321182251, "global_step": 457451, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.094109296798706, "global_step": 457452, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0868337154388428, "global_step": 457453, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0946292877197266, "global_step": 457454, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.106318473815918, "global_step": 457455, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.075901746749878, "global_step": 457456, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1599693298339844, "global_step": 457457, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0494279861450195, "global_step": 457458, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.076974391937256, "global_step": 457459, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9922888278961182, "global_step": 457460, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1148605346679688, "global_step": 457461, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0746893882751465, "global_step": 457462, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0224387645721436, "global_step": 457463, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0284600257873535, "global_step": 457464, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.152803897857666, "global_step": 457465, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1256556510925293, "global_step": 457466, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0796494483947754, "global_step": 457467, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.138704776763916, "global_step": 457468, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.154343605041504, "global_step": 457469, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0086419582366943, "global_step": 457470, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.079124689102173, "global_step": 457471, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0887553691864014, "global_step": 457472, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0371196269989014, "global_step": 457473, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0717251300811768, "global_step": 457474, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9996259212493896, "global_step": 457475, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1029281616210938, "global_step": 457476, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.054993152618408, "global_step": 457477, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0908474922180176, "global_step": 457478, "epoch": 821, "lr": 5e-05}
{"train_loss": 1.9714183807373047, "global_step": 457479, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.084686040878296, "global_step": 457480, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.041774034500122, "global_step": 457481, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.112732172012329, "global_step": 457482, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0855624675750732, "global_step": 457483, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1106202602386475, "global_step": 457484, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0716891288757324, "global_step": 457485, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0884952545166016, "global_step": 457486, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.1589951515197754, "global_step": 457487, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0137338638305664, "global_step": 457488, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0518667697906494, "global_step": 457489, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.116114854812622, "global_step": 457490, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.139549732208252, "global_step": 457491, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.080202579498291, "global_step": 457492, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0604307651519775, "global_step": 457493, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0016746520996094, "global_step": 457494, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0246458053588867, "global_step": 457495, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0379767417907715, "global_step": 457496, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.077932596206665, "global_step": 457497, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.123599052429199, "global_step": 457498, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.073316812515259, "global_step": 457499, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.0733838081359863, "global_step": 457500, "epoch": 821, "lr": 5e-05}
{"train_loss": 2.027935743331909, "global_step": 457501, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.075984001159668, "global_step": 457502, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.136617660522461, "global_step": 457503, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0817456245422363, "global_step": 457504, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.077265739440918, "global_step": 457505, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.070174217224121, "global_step": 457506, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9913911819458008, "global_step": 457507, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1091465950012207, "global_step": 457508, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9896048307418823, "global_step": 457509, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.016040563583374, "global_step": 457510, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0408236980438232, "global_step": 457511, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1048552989959717, "global_step": 457512, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0076515674591064, "global_step": 457513, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0565896034240723, "global_step": 457514, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0361437797546387, "global_step": 457515, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9616492986679077, "global_step": 457516, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0392370223999023, "global_step": 457517, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.016787528991699, "global_step": 457518, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.094935178756714, "global_step": 457519, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.012702703475952, "global_step": 457520, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0689897537231445, "global_step": 457521, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.125509262084961, "global_step": 457522, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.063056468963623, "global_step": 457523, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.121906280517578, "global_step": 457524, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.053530693054199, "global_step": 457525, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0470333099365234, "global_step": 457526, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0116360187530518, "global_step": 457527, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0847349166870117, "global_step": 457528, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0477547645568848, "global_step": 457529, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.052307605743408, "global_step": 457530, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0183069705963135, "global_step": 457531, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1292757987976074, "global_step": 457532, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1146328449249268, "global_step": 457533, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.106609344482422, "global_step": 457534, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.101881504058838, "global_step": 457535, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.032545804977417, "global_step": 457536, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.017773389816284, "global_step": 457537, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0144762992858887, "global_step": 457538, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0224854946136475, "global_step": 457539, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0162832736968994, "global_step": 457540, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0209767818450928, "global_step": 457541, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.059892177581787, "global_step": 457542, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0691475868225098, "global_step": 457543, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.049644947052002, "global_step": 457544, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.094245195388794, "global_step": 457545, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.086953639984131, "global_step": 457546, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.064398765563965, "global_step": 457547, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.176637887954712, "global_step": 457548, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.102292060852051, "global_step": 457549, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.060685634613037, "global_step": 457550, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0783331394195557, "global_step": 457551, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0490939617156982, "global_step": 457552, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1419596672058105, "global_step": 457553, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.089794635772705, "global_step": 457554, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0588440895080566, "global_step": 457555, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0336642265319824, "global_step": 457556, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0934300422668457, "global_step": 457557, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0924153327941895, "global_step": 457558, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0140786170959473, "global_step": 457559, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1287295818328857, "global_step": 457560, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0458436012268066, "global_step": 457561, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0778093338012695, "global_step": 457562, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0386810302734375, "global_step": 457563, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0641989707946777, "global_step": 457564, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.087536573410034, "global_step": 457565, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.061152935028076, "global_step": 457566, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1268882751464844, "global_step": 457567, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0344653129577637, "global_step": 457568, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.038233518600464, "global_step": 457569, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0652425289154053, "global_step": 457570, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1351511478424072, "global_step": 457571, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1049888134002686, "global_step": 457572, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.107404947280884, "global_step": 457573, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0123040676116943, "global_step": 457574, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.034209728240967, "global_step": 457575, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0725462436676025, "global_step": 457576, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.080383062362671, "global_step": 457577, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0584983825683594, "global_step": 457578, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.009449005126953, "global_step": 457579, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0025174617767334, "global_step": 457580, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0700364112854004, "global_step": 457581, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.031146764755249, "global_step": 457582, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0736899375915527, "global_step": 457583, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0288758277893066, "global_step": 457584, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1242451667785645, "global_step": 457585, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0977652072906494, "global_step": 457586, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0767009258270264, "global_step": 457587, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0270462036132812, "global_step": 457588, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0971903800964355, "global_step": 457589, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.071502923965454, "global_step": 457590, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1259381771087646, "global_step": 457591, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9953975677490234, "global_step": 457592, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0494914054870605, "global_step": 457593, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1473989486694336, "global_step": 457594, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0471572875976562, "global_step": 457595, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.054302930831909, "global_step": 457596, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0523786544799805, "global_step": 457597, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9923315048217773, "global_step": 457598, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1628711223602295, "global_step": 457599, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0728297233581543, "global_step": 457600, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0560641288757324, "global_step": 457601, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0905299186706543, "global_step": 457602, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.078388214111328, "global_step": 457603, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.142470598220825, "global_step": 457604, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1028411388397217, "global_step": 457605, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0024964809417725, "global_step": 457606, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.032963275909424, "global_step": 457607, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.076218605041504, "global_step": 457608, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9997016191482544, "global_step": 457609, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0139002799987793, "global_step": 457610, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9989880323410034, "global_step": 457611, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0560662746429443, "global_step": 457612, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0100131034851074, "global_step": 457613, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9911928176879883, "global_step": 457614, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.970236897468567, "global_step": 457615, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9723255634307861, "global_step": 457616, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1457443237304688, "global_step": 457617, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1262497901916504, "global_step": 457618, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0805201530456543, "global_step": 457619, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1321630477905273, "global_step": 457620, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9910882711410522, "global_step": 457621, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.020705223083496, "global_step": 457622, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.952282190322876, "global_step": 457623, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.127976655960083, "global_step": 457624, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0478670597076416, "global_step": 457625, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.063961982727051, "global_step": 457626, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0492944717407227, "global_step": 457627, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9532487392425537, "global_step": 457628, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0171866416931152, "global_step": 457629, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0952932834625244, "global_step": 457630, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1530425548553467, "global_step": 457631, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.053084373474121, "global_step": 457632, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.081833600997925, "global_step": 457633, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9885919094085693, "global_step": 457634, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.131345272064209, "global_step": 457635, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.00620174407959, "global_step": 457636, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0800461769104004, "global_step": 457637, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.049410581588745, "global_step": 457638, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.158801555633545, "global_step": 457639, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9810082912445068, "global_step": 457640, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.045576810836792, "global_step": 457641, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0390660762786865, "global_step": 457642, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0109550952911377, "global_step": 457643, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.074472665786743, "global_step": 457644, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0759143829345703, "global_step": 457645, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1226043701171875, "global_step": 457646, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0112359523773193, "global_step": 457647, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0344784259796143, "global_step": 457648, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1142916679382324, "global_step": 457649, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.153240442276001, "global_step": 457650, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.117123603820801, "global_step": 457651, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0712993144989014, "global_step": 457652, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.118565320968628, "global_step": 457653, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.082376003265381, "global_step": 457654, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.074770212173462, "global_step": 457655, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0843827724456787, "global_step": 457656, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0445291996002197, "global_step": 457657, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0219833850860596, "global_step": 457658, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.000762939453125, "global_step": 457659, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0197536945343018, "global_step": 457660, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.057765007019043, "global_step": 457661, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1122233867645264, "global_step": 457662, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.070708990097046, "global_step": 457663, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9982078075408936, "global_step": 457664, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9920213222503662, "global_step": 457665, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9817287921905518, "global_step": 457666, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.09716796875, "global_step": 457667, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.062041997909546, "global_step": 457668, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1160638332366943, "global_step": 457669, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0472817420959473, "global_step": 457670, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.052264928817749, "global_step": 457671, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0387818813323975, "global_step": 457672, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0408260822296143, "global_step": 457673, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.081820487976074, "global_step": 457674, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1612110137939453, "global_step": 457675, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1714954376220703, "global_step": 457676, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.060128688812256, "global_step": 457677, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.118673324584961, "global_step": 457678, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.014326333999634, "global_step": 457679, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.045722484588623, "global_step": 457680, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.096330404281616, "global_step": 457681, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.2093443870544434, "global_step": 457682, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.11987042427063, "global_step": 457683, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0277421474456787, "global_step": 457684, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0668115615844727, "global_step": 457685, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.078516960144043, "global_step": 457686, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.04399037361145, "global_step": 457687, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0475587844848633, "global_step": 457688, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.967193365097046, "global_step": 457689, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.057528257369995, "global_step": 457690, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0880134105682373, "global_step": 457691, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.046854257583618, "global_step": 457692, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1366608142852783, "global_step": 457693, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0937485694885254, "global_step": 457694, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1024832725524902, "global_step": 457695, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0374016761779785, "global_step": 457696, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0356273651123047, "global_step": 457697, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.084306001663208, "global_step": 457698, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.057539463043213, "global_step": 457699, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.118936538696289, "global_step": 457700, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0787975788116455, "global_step": 457701, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0543782711029053, "global_step": 457702, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.045088529586792, "global_step": 457703, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.071429967880249, "global_step": 457704, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0470938682556152, "global_step": 457705, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.018939733505249, "global_step": 457706, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.016962766647339, "global_step": 457707, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1224491596221924, "global_step": 457708, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1005196571350098, "global_step": 457709, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1365702152252197, "global_step": 457710, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0233547687530518, "global_step": 457711, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.062093496322632, "global_step": 457712, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0589239597320557, "global_step": 457713, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0578362941741943, "global_step": 457714, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.042179584503174, "global_step": 457715, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1021220684051514, "global_step": 457716, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0405080318450928, "global_step": 457717, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0429041385650635, "global_step": 457718, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.009260654449463, "global_step": 457719, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.096891403198242, "global_step": 457720, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1581664085388184, "global_step": 457721, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0196280479431152, "global_step": 457722, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.045660972595215, "global_step": 457723, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.082892417907715, "global_step": 457724, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.102863073348999, "global_step": 457725, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.10109806060791, "global_step": 457726, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1647026538848877, "global_step": 457727, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.061394453048706, "global_step": 457728, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0326592922210693, "global_step": 457729, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0979835987091064, "global_step": 457730, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.065063238143921, "global_step": 457731, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.030333995819092, "global_step": 457732, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.113474130630493, "global_step": 457733, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0973026752471924, "global_step": 457734, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.054490089416504, "global_step": 457735, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.116096258163452, "global_step": 457736, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.097611665725708, "global_step": 457737, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0552995204925537, "global_step": 457738, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1633031368255615, "global_step": 457739, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0451481342315674, "global_step": 457740, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0725479125976562, "global_step": 457741, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0519258975982666, "global_step": 457742, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.147348403930664, "global_step": 457743, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.129453659057617, "global_step": 457744, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.06882381439209, "global_step": 457745, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.011671543121338, "global_step": 457746, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.003744602203369, "global_step": 457747, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0378775596618652, "global_step": 457748, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0471482276916504, "global_step": 457749, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.029486656188965, "global_step": 457750, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.088827610015869, "global_step": 457751, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0526137351989746, "global_step": 457752, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.033146858215332, "global_step": 457753, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0179872512817383, "global_step": 457754, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.064232587814331, "global_step": 457755, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1127867698669434, "global_step": 457756, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.059337615966797, "global_step": 457757, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.052032232284546, "global_step": 457758, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9378687143325806, "global_step": 457759, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.088144302368164, "global_step": 457760, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.055274248123169, "global_step": 457761, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.093021869659424, "global_step": 457762, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1323280334472656, "global_step": 457763, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.077913522720337, "global_step": 457764, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0249743461608887, "global_step": 457765, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0069780349731445, "global_step": 457766, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0922906398773193, "global_step": 457767, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0265307426452637, "global_step": 457768, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0654237270355225, "global_step": 457769, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.020739793777466, "global_step": 457770, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0490055084228516, "global_step": 457771, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0272462368011475, "global_step": 457772, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0688419342041016, "global_step": 457773, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.035104274749756, "global_step": 457774, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.010279893875122, "global_step": 457775, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.000431776046753, "global_step": 457776, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0697028636932373, "global_step": 457777, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0424888134002686, "global_step": 457778, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.085981607437134, "global_step": 457779, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0636229515075684, "global_step": 457780, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1221132278442383, "global_step": 457781, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.112975597381592, "global_step": 457782, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.168067455291748, "global_step": 457783, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0182178020477295, "global_step": 457784, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.00058650970459, "global_step": 457785, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0336203575134277, "global_step": 457786, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.119905710220337, "global_step": 457787, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0786566734313965, "global_step": 457788, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1601407527923584, "global_step": 457789, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0904130935668945, "global_step": 457790, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9936898946762085, "global_step": 457791, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0434165000915527, "global_step": 457792, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.054426670074463, "global_step": 457793, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1225404739379883, "global_step": 457794, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.192673921585083, "global_step": 457795, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0572409629821777, "global_step": 457796, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.059401512145996, "global_step": 457797, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0772910118103027, "global_step": 457798, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.104203462600708, "global_step": 457799, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0749175548553467, "global_step": 457800, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1433684825897217, "global_step": 457801, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.136906147003174, "global_step": 457802, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0381991863250732, "global_step": 457803, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0024707317352295, "global_step": 457804, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.087650775909424, "global_step": 457805, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1390016078948975, "global_step": 457806, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.092958688735962, "global_step": 457807, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0346388816833496, "global_step": 457808, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0922694206237793, "global_step": 457809, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.137083053588867, "global_step": 457810, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.074488639831543, "global_step": 457811, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1521413326263428, "global_step": 457812, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1849257946014404, "global_step": 457813, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.043642520904541, "global_step": 457814, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0872080326080322, "global_step": 457815, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9989349842071533, "global_step": 457816, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1018543243408203, "global_step": 457817, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0795140266418457, "global_step": 457818, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1249868869781494, "global_step": 457819, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.074796199798584, "global_step": 457820, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1364002227783203, "global_step": 457821, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0989952087402344, "global_step": 457822, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1313834190368652, "global_step": 457823, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.959822654724121, "global_step": 457824, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0622565746307373, "global_step": 457825, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.165510654449463, "global_step": 457826, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.017132520675659, "global_step": 457827, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.116215229034424, "global_step": 457828, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.108595848083496, "global_step": 457829, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.080307960510254, "global_step": 457830, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0387868881225586, "global_step": 457831, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0412068367004395, "global_step": 457832, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.055232048034668, "global_step": 457833, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0951712131500244, "global_step": 457834, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.05767822265625, "global_step": 457835, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.002721071243286, "global_step": 457836, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.054671287536621, "global_step": 457837, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.044111728668213, "global_step": 457838, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0508275032043457, "global_step": 457839, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0883071422576904, "global_step": 457840, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0350985527038574, "global_step": 457841, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1683828830718994, "global_step": 457842, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.000166177749634, "global_step": 457843, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9991278648376465, "global_step": 457844, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.059584617614746, "global_step": 457845, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.134859561920166, "global_step": 457846, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.097564935684204, "global_step": 457847, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.06695818901062, "global_step": 457848, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.081639051437378, "global_step": 457849, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.968835473060608, "global_step": 457850, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1197872161865234, "global_step": 457851, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.086521625518799, "global_step": 457852, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0377190113067627, "global_step": 457853, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.11561918258667, "global_step": 457854, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.002891778945923, "global_step": 457855, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.00302791595459, "global_step": 457856, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.011981964111328, "global_step": 457857, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0809366703033447, "global_step": 457858, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.049679756164551, "global_step": 457859, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0961689949035645, "global_step": 457860, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.138026714324951, "global_step": 457861, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9399052858352661, "global_step": 457862, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0371601581573486, "global_step": 457863, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.05779767036438, "global_step": 457864, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0418691635131836, "global_step": 457865, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1077873706817627, "global_step": 457866, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1168105602264404, "global_step": 457867, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9686832427978516, "global_step": 457868, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0130908489227295, "global_step": 457869, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.070709466934204, "global_step": 457870, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1014761924743652, "global_step": 457871, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1007869243621826, "global_step": 457872, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1112332344055176, "global_step": 457873, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1336679458618164, "global_step": 457874, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9553481340408325, "global_step": 457875, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.046074867248535, "global_step": 457876, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.066972255706787, "global_step": 457877, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9839293956756592, "global_step": 457878, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.090548515319824, "global_step": 457879, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.114959955215454, "global_step": 457880, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1320667266845703, "global_step": 457881, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.078084707260132, "global_step": 457882, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.036072254180908, "global_step": 457883, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1128270626068115, "global_step": 457884, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1264023780822754, "global_step": 457885, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0841128826141357, "global_step": 457886, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.112886428833008, "global_step": 457887, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.11391282081604, "global_step": 457888, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1064465045928955, "global_step": 457889, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.100708246231079, "global_step": 457890, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0741477012634277, "global_step": 457891, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.118821382522583, "global_step": 457892, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.074082612991333, "global_step": 457893, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1970038414001465, "global_step": 457894, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.103955030441284, "global_step": 457895, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.063807249069214, "global_step": 457896, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.019822597503662, "global_step": 457897, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.135885000228882, "global_step": 457898, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0810821056365967, "global_step": 457899, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1043365001678467, "global_step": 457900, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0337746143341064, "global_step": 457901, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0888288021087646, "global_step": 457902, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.124260187149048, "global_step": 457903, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.2023990154266357, "global_step": 457904, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.100219488143921, "global_step": 457905, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0558106899261475, "global_step": 457906, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0687096118927, "global_step": 457907, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1472301483154297, "global_step": 457908, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0823681354522705, "global_step": 457909, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0258798599243164, "global_step": 457910, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9592338800430298, "global_step": 457911, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.045112133026123, "global_step": 457912, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0742361545562744, "global_step": 457913, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0381627082824707, "global_step": 457914, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1262810230255127, "global_step": 457915, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.068615674972534, "global_step": 457916, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0402543544769287, "global_step": 457917, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1054627895355225, "global_step": 457918, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.139103412628174, "global_step": 457919, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0382778644561768, "global_step": 457920, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0682690143585205, "global_step": 457921, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0657436847686768, "global_step": 457922, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.131174087524414, "global_step": 457923, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0127196311950684, "global_step": 457924, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0651988983154297, "global_step": 457925, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.080817222595215, "global_step": 457926, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0710630416870117, "global_step": 457927, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0672061443328857, "global_step": 457928, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0644917488098145, "global_step": 457929, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.999955177307129, "global_step": 457930, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0945520401000977, "global_step": 457931, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.030383586883545, "global_step": 457932, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0758705139160156, "global_step": 457933, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0301899909973145, "global_step": 457934, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0454294681549072, "global_step": 457935, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.167052984237671, "global_step": 457936, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1286001205444336, "global_step": 457937, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1110472679138184, "global_step": 457938, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.028212547302246, "global_step": 457939, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.077080011367798, "global_step": 457940, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.124138355255127, "global_step": 457941, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.03426194190979, "global_step": 457942, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.07621169090271, "global_step": 457943, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0420923233032227, "global_step": 457944, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0417320728302, "global_step": 457945, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0942983627319336, "global_step": 457946, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.050009250640869, "global_step": 457947, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.027194023132324, "global_step": 457948, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.099987030029297, "global_step": 457949, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0363826751708984, "global_step": 457950, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.113406181335449, "global_step": 457951, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1118838787078857, "global_step": 457952, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.072669744491577, "global_step": 457953, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0633533000946045, "global_step": 457954, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0690579414367676, "global_step": 457955, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1084113121032715, "global_step": 457956, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1499710083007812, "global_step": 457957, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0620429515838623, "global_step": 457958, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1148085594177246, "global_step": 457959, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.987276554107666, "global_step": 457960, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.032881021499634, "global_step": 457961, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.052459478378296, "global_step": 457962, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0548341274261475, "global_step": 457963, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0818092823028564, "global_step": 457964, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0513558387756348, "global_step": 457965, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.086616039276123, "global_step": 457966, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0320725440979004, "global_step": 457967, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.195629119873047, "global_step": 457968, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.107384443283081, "global_step": 457969, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0147204399108887, "global_step": 457970, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.048569917678833, "global_step": 457971, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.025325059890747, "global_step": 457972, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.027067184448242, "global_step": 457973, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0680415630340576, "global_step": 457974, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.07818865776062, "global_step": 457975, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1246440410614014, "global_step": 457976, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.018899917602539, "global_step": 457977, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0911664962768555, "global_step": 457978, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.074361562728882, "global_step": 457979, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0852174758911133, "global_step": 457980, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0912773609161377, "global_step": 457981, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0191545486450195, "global_step": 457982, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.151045560836792, "global_step": 457983, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.137176990509033, "global_step": 457984, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.054079532623291, "global_step": 457985, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0624873638153076, "global_step": 457986, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0989983081817627, "global_step": 457987, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1126112937927246, "global_step": 457988, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.072678804397583, "global_step": 457989, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1299479007720947, "global_step": 457990, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0737836360931396, "global_step": 457991, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.022258758544922, "global_step": 457992, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.040440082550049, "global_step": 457993, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0075206756591797, "global_step": 457994, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.138779401779175, "global_step": 457995, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0851786136627197, "global_step": 457996, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0888538360595703, "global_step": 457997, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.082643508911133, "global_step": 457998, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.100299835205078, "global_step": 457999, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0979325771331787, "global_step": 458000, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1079866886138916, "global_step": 458001, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.114380359649658, "global_step": 458002, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1327314376831055, "global_step": 458003, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0335423946380615, "global_step": 458004, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.107300043106079, "global_step": 458005, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.089735746383667, "global_step": 458006, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1017446517944336, "global_step": 458007, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0856876373291016, "global_step": 458008, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0890378952026367, "global_step": 458009, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0582942962646484, "global_step": 458010, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.112412452697754, "global_step": 458011, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.078981399536133, "global_step": 458012, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.094169855117798, "global_step": 458013, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0614099502563477, "global_step": 458014, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.109550714492798, "global_step": 458015, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0280497074127197, "global_step": 458016, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0975875854492188, "global_step": 458017, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.062788724899292, "global_step": 458018, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0372233390808105, "global_step": 458019, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9525686502456665, "global_step": 458020, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0772151947021484, "global_step": 458021, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0140137672424316, "global_step": 458022, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0932469367980957, "global_step": 458023, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0264384746551514, "global_step": 458024, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9804600477218628, "global_step": 458025, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0146241188049316, "global_step": 458026, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0291478633880615, "global_step": 458027, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9802130460739136, "global_step": 458028, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.116746664047241, "global_step": 458029, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0561325550079346, "global_step": 458030, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.040999412536621, "global_step": 458031, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1652190685272217, "global_step": 458032, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0627641677856445, "global_step": 458033, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.03115177154541, "global_step": 458034, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1075141429901123, "global_step": 458035, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.06539249420166, "global_step": 458036, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.13344144821167, "global_step": 458037, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.010840654373169, "global_step": 458038, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0923259258270264, "global_step": 458039, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1235554218292236, "global_step": 458040, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.06276273727417, "global_step": 458041, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1493923664093018, "global_step": 458042, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0156373977661133, "global_step": 458043, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9920023679733276, "global_step": 458044, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0622947216033936, "global_step": 458045, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1491353511810303, "global_step": 458046, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.014873504638672, "global_step": 458047, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.074979543685913, "global_step": 458048, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0723347663879395, "global_step": 458049, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.090907096862793, "global_step": 458050, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.010718584060669, "global_step": 458051, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0107150077819824, "global_step": 458052, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0253148078918457, "global_step": 458053, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0225155353546143, "global_step": 458054, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9960790872573853, "global_step": 458055, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0762932300567627, "global_step": 458056, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0537867546081543, "global_step": 458057, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.102976083755493, "global_step": 458058, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1449928283691406, "global_step": 458059, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.041425943374634, "global_step": 458060, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.046699285507202, "global_step": 458061, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.04541277885437, "global_step": 458062, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0911059379577637, "global_step": 458063, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0944833755493164, "global_step": 458064, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9767663478851318, "global_step": 458065, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.15036940574646, "global_step": 458066, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.064152717590332, "global_step": 458067, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.989910364151001, "global_step": 458068, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1103451251983643, "global_step": 458069, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.060354709625244, "global_step": 458070, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.021556854248047, "global_step": 458071, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0269885063171387, "global_step": 458072, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9735164642333984, "global_step": 458073, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.063471794128418, "global_step": 458074, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9977898597717285, "global_step": 458075, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0466370582580566, "global_step": 458076, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1125266551971436, "global_step": 458077, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0126638412475586, "global_step": 458078, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1595563888549805, "global_step": 458079, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1169803142547607, "global_step": 458080, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1038334369659424, "global_step": 458081, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0818140506744385, "global_step": 458082, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.179619789123535, "global_step": 458083, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.074707269668579, "global_step": 458084, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0990936756134033, "global_step": 458085, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.161916732788086, "global_step": 458086, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.031205177307129, "global_step": 458087, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1319048404693604, "global_step": 458088, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.06242036819458, "global_step": 458089, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0887722969055176, "global_step": 458090, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.110665798187256, "global_step": 458091, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.173035144805908, "global_step": 458092, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.051345109939575, "global_step": 458093, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.072169542312622, "global_step": 458094, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0812346935272217, "global_step": 458095, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0254719257354736, "global_step": 458096, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0843429565429688, "global_step": 458097, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0684120655059814, "global_step": 458098, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9723113775253296, "global_step": 458099, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.028923988342285, "global_step": 458100, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.121760368347168, "global_step": 458101, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0890281200408936, "global_step": 458102, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0464730262756348, "global_step": 458103, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1489925384521484, "global_step": 458104, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.110374927520752, "global_step": 458105, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.032864809036255, "global_step": 458106, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.064788341522217, "global_step": 458107, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0186104774475098, "global_step": 458108, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0368590354919434, "global_step": 458109, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.041337490081787, "global_step": 458110, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.201361656188965, "global_step": 458111, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.931230902671814, "global_step": 458112, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0592539310455322, "global_step": 458113, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.036987781524658, "global_step": 458114, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.059364080429077, "global_step": 458115, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1399405002593994, "global_step": 458116, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1050326824188232, "global_step": 458117, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.106626033782959, "global_step": 458118, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.141022205352783, "global_step": 458119, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.032580614089966, "global_step": 458120, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.023383140563965, "global_step": 458121, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0422143936157227, "global_step": 458122, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0484619140625, "global_step": 458123, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.013446092605591, "global_step": 458124, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1290035247802734, "global_step": 458125, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.168318510055542, "global_step": 458126, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0249452590942383, "global_step": 458127, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.088841676712036, "global_step": 458128, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.034759521484375, "global_step": 458129, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9775784015655518, "global_step": 458130, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.035351037979126, "global_step": 458131, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.034898042678833, "global_step": 458132, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0077083110809326, "global_step": 458133, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0327370166778564, "global_step": 458134, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1075668334960938, "global_step": 458135, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1051604747772217, "global_step": 458136, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.113729953765869, "global_step": 458137, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0758795738220215, "global_step": 458138, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0888493061065674, "global_step": 458139, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.06839656829834, "global_step": 458140, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.074049711227417, "global_step": 458141, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0697760581970215, "global_step": 458142, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.098618507385254, "global_step": 458143, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1378424167633057, "global_step": 458144, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0998306274414062, "global_step": 458145, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0105926990509033, "global_step": 458146, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1690309047698975, "global_step": 458147, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0697124004364014, "global_step": 458148, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.063023805618286, "global_step": 458149, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.030853748321533, "global_step": 458150, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0927212238311768, "global_step": 458151, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0854945182800293, "global_step": 458152, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1540377140045166, "global_step": 458153, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0960333347320557, "global_step": 458154, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1310999393463135, "global_step": 458155, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.048064947128296, "global_step": 458156, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0871684551239014, "global_step": 458157, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.123551368713379, "global_step": 458158, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1445116996765137, "global_step": 458159, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0950191020965576, "global_step": 458160, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0048773288726807, "global_step": 458161, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0633227825164795, "global_step": 458162, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0531392097473145, "global_step": 458163, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0939688682556152, "global_step": 458164, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.113138198852539, "global_step": 458165, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0813045501708984, "global_step": 458166, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0284249782562256, "global_step": 458167, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.071857452392578, "global_step": 458168, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0244638919830322, "global_step": 458169, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0919148921966553, "global_step": 458170, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.105851650238037, "global_step": 458171, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0978269577026367, "global_step": 458172, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0896339416503906, "global_step": 458173, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.092068910598755, "global_step": 458174, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0596401691436768, "global_step": 458175, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0450446605682373, "global_step": 458176, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0787174701690674, "global_step": 458177, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.011263847351074, "global_step": 458178, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0019099712371826, "global_step": 458179, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.06239652633667, "global_step": 458180, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.106640577316284, "global_step": 458181, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1177384853363037, "global_step": 458182, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.032381772994995, "global_step": 458183, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0454204082489014, "global_step": 458184, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0426506996154785, "global_step": 458185, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0055360794067383, "global_step": 458186, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.054614305496216, "global_step": 458187, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.160358428955078, "global_step": 458188, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0972466468811035, "global_step": 458189, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.074798107147217, "global_step": 458190, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0851686000823975, "global_step": 458191, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1046102046966553, "global_step": 458192, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.070995569229126, "global_step": 458193, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0464088916778564, "global_step": 458194, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1841793060302734, "global_step": 458195, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.103585958480835, "global_step": 458196, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.070781707763672, "global_step": 458197, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1637766361236572, "global_step": 458198, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1618669033050537, "global_step": 458199, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.04617977142334, "global_step": 458200, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0749471187591553, "global_step": 458201, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0899791717529297, "global_step": 458202, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.039764165878296, "global_step": 458203, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.061990737915039, "global_step": 458204, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1697487831115723, "global_step": 458205, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.023763418197632, "global_step": 458206, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1246135234832764, "global_step": 458207, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0781564712524414, "global_step": 458208, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0442581176757812, "global_step": 458209, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1045053005218506, "global_step": 458210, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.111313819885254, "global_step": 458211, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.130143642425537, "global_step": 458212, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9563851356506348, "global_step": 458213, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0576560497283936, "global_step": 458214, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0443854331970215, "global_step": 458215, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.026186943054199, "global_step": 458216, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0241146087646484, "global_step": 458217, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.186223268508911, "global_step": 458218, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0583229064941406, "global_step": 458219, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0198633670806885, "global_step": 458220, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0474915504455566, "global_step": 458221, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1805310249328613, "global_step": 458222, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0827927589416504, "global_step": 458223, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1179158687591553, "global_step": 458224, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1208691596984863, "global_step": 458225, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.048626184463501, "global_step": 458226, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0974323749542236, "global_step": 458227, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.001410484313965, "global_step": 458228, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.096116542816162, "global_step": 458229, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.101304292678833, "global_step": 458230, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0770885944366455, "global_step": 458231, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.031083106994629, "global_step": 458232, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.069053888320923, "global_step": 458233, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0905864238739014, "global_step": 458234, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0994365215301514, "global_step": 458235, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.059833526611328, "global_step": 458236, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0581722259521484, "global_step": 458237, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.065833568572998, "global_step": 458238, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0632290840148926, "global_step": 458239, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.04925274848938, "global_step": 458240, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1347885131835938, "global_step": 458241, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0289885997772217, "global_step": 458242, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.104252338409424, "global_step": 458243, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.039257287979126, "global_step": 458244, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1046619415283203, "global_step": 458245, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0170602798461914, "global_step": 458246, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0258374214172363, "global_step": 458247, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.989707112312317, "global_step": 458248, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1717193126678467, "global_step": 458249, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0462489128112793, "global_step": 458250, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1107993125915527, "global_step": 458251, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0561208724975586, "global_step": 458252, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.105879068374634, "global_step": 458253, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.113050937652588, "global_step": 458254, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1369664669036865, "global_step": 458255, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.009028196334839, "global_step": 458256, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1079256534576416, "global_step": 458257, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1037399768829346, "global_step": 458258, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0767128467559814, "global_step": 458259, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0900557041168213, "global_step": 458260, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.159823179244995, "global_step": 458261, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0546369552612305, "global_step": 458262, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0540759563446045, "global_step": 458263, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0615968704223633, "global_step": 458264, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.028400421142578, "global_step": 458265, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1256768703460693, "global_step": 458266, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1324338912963867, "global_step": 458267, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1503353118896484, "global_step": 458268, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1150054931640625, "global_step": 458269, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9757448434829712, "global_step": 458270, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0779225826263428, "global_step": 458271, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1288809776306152, "global_step": 458272, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0646259784698486, "global_step": 458273, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9188307523727417, "global_step": 458274, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.066265106201172, "global_step": 458275, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0954477787017822, "global_step": 458276, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.010662794113159, "global_step": 458277, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0047619342803955, "global_step": 458278, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.048551321029663, "global_step": 458279, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.03837513923645, "global_step": 458280, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.983393669128418, "global_step": 458281, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.112441301345825, "global_step": 458282, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1454885005950928, "global_step": 458283, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.039069652557373, "global_step": 458284, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.064706802368164, "global_step": 458285, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.077615737915039, "global_step": 458286, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0889174938201904, "global_step": 458287, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0902018547058105, "global_step": 458288, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0831692218780518, "global_step": 458289, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.093151569366455, "global_step": 458290, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0207300186157227, "global_step": 458291, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0959603786468506, "global_step": 458292, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.029381275177002, "global_step": 458293, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1309261322021484, "global_step": 458294, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0861191749572754, "global_step": 458295, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0780832767486572, "global_step": 458296, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1817827224731445, "global_step": 458297, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.029785394668579, "global_step": 458298, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0250823497772217, "global_step": 458299, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.123126983642578, "global_step": 458300, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0178956985473633, "global_step": 458301, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9995063543319702, "global_step": 458302, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1849355697631836, "global_step": 458303, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1120457649230957, "global_step": 458304, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.112760305404663, "global_step": 458305, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0633528232574463, "global_step": 458306, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.8979796171188354, "global_step": 458307, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.051804780960083, "global_step": 458308, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0977418422698975, "global_step": 458309, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.045780897140503, "global_step": 458310, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.065300464630127, "global_step": 458311, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.2416741847991943, "global_step": 458312, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1232566833496094, "global_step": 458313, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.073723316192627, "global_step": 458314, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.04781436920166, "global_step": 458315, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1412875652313232, "global_step": 458316, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0341005325317383, "global_step": 458317, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1484625339508057, "global_step": 458318, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.193480968475342, "global_step": 458319, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.050515651702881, "global_step": 458320, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.045212507247925, "global_step": 458321, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.040982246398926, "global_step": 458322, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0304956436157227, "global_step": 458323, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.174682378768921, "global_step": 458324, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1058778762817383, "global_step": 458325, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0972118377685547, "global_step": 458326, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.082636594772339, "global_step": 458327, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.03550386428833, "global_step": 458328, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1291418075561523, "global_step": 458329, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.187469005584717, "global_step": 458330, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1366825103759766, "global_step": 458331, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.048112392425537, "global_step": 458332, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0745182037353516, "global_step": 458333, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.126593589782715, "global_step": 458334, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0861546993255615, "global_step": 458335, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1207611560821533, "global_step": 458336, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0452914237976074, "global_step": 458337, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.110443592071533, "global_step": 458338, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.059481620788574, "global_step": 458339, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.085038900375366, "global_step": 458340, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.077531337738037, "global_step": 458341, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.045682191848755, "global_step": 458342, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0667498111724854, "global_step": 458343, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0198895931243896, "global_step": 458344, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9602515697479248, "global_step": 458345, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0116477012634277, "global_step": 458346, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1068382263183594, "global_step": 458347, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.072070837020874, "global_step": 458348, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.114711284637451, "global_step": 458349, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.163301944732666, "global_step": 458350, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.123418092727661, "global_step": 458351, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0921311378479004, "global_step": 458352, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.031656265258789, "global_step": 458353, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0314137935638428, "global_step": 458354, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0429158210754395, "global_step": 458355, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0878188610076904, "global_step": 458356, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.101304292678833, "global_step": 458357, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9089857339859009, "global_step": 458358, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0665645599365234, "global_step": 458359, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.102337598800659, "global_step": 458360, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.098478317260742, "global_step": 458361, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.113485813140869, "global_step": 458362, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.068962812423706, "global_step": 458363, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.062750816345215, "global_step": 458364, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.140087842941284, "global_step": 458365, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1107773780822754, "global_step": 458366, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.096562623977661, "global_step": 458367, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.02931809425354, "global_step": 458368, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0308892726898193, "global_step": 458369, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0482900142669678, "global_step": 458370, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.139761447906494, "global_step": 458371, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9834799766540527, "global_step": 458372, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.06461238861084, "global_step": 458373, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0945634841918945, "global_step": 458374, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0643272399902344, "global_step": 458375, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0129165649414062, "global_step": 458376, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0850462913513184, "global_step": 458377, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.10349178314209, "global_step": 458378, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0918805599212646, "global_step": 458379, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0371639728546143, "global_step": 458380, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.046318531036377, "global_step": 458381, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0090572834014893, "global_step": 458382, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0577595233917236, "global_step": 458383, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0664045810699463, "global_step": 458384, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0564568042755127, "global_step": 458385, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.052046537399292, "global_step": 458386, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.02364444732666, "global_step": 458387, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0605220794677734, "global_step": 458388, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.004031181335449, "global_step": 458389, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.994980812072754, "global_step": 458390, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0400943756103516, "global_step": 458391, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0633912086486816, "global_step": 458392, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.043792724609375, "global_step": 458393, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.111017942428589, "global_step": 458394, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0897555351257324, "global_step": 458395, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1136562824249268, "global_step": 458396, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0069472789764404, "global_step": 458397, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.115591526031494, "global_step": 458398, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9759882688522339, "global_step": 458399, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.149254560470581, "global_step": 458400, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1146295070648193, "global_step": 458401, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.075087547302246, "global_step": 458402, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0817761421203613, "global_step": 458403, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0648818016052246, "global_step": 458404, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.01757550239563, "global_step": 458405, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.037055492401123, "global_step": 458406, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.183717727661133, "global_step": 458407, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.023562431335449, "global_step": 458408, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1012964248657227, "global_step": 458409, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0775954723358154, "global_step": 458410, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.062690019607544, "global_step": 458411, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.055370569229126, "global_step": 458412, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.037879705429077, "global_step": 458413, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0113909244537354, "global_step": 458414, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0932013988494873, "global_step": 458415, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0718531608581543, "global_step": 458416, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0438215732574463, "global_step": 458417, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1168527603149414, "global_step": 458418, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0799195766448975, "global_step": 458419, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.085789918899536, "global_step": 458420, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0258076190948486, "global_step": 458421, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9764537811279297, "global_step": 458422, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0288140773773193, "global_step": 458423, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0638086795806885, "global_step": 458424, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.104663133621216, "global_step": 458425, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1372604370117188, "global_step": 458426, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0778968334198, "global_step": 458427, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1139042377471924, "global_step": 458428, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1165177822113037, "global_step": 458429, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1020498275756836, "global_step": 458430, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0512022972106934, "global_step": 458431, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9822850227355957, "global_step": 458432, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.956180214881897, "global_step": 458433, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.093324661254883, "global_step": 458434, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1300601959228516, "global_step": 458435, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9440003633499146, "global_step": 458436, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.110175371170044, "global_step": 458437, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0474612712860107, "global_step": 458438, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.061681032180786, "global_step": 458439, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.040848731994629, "global_step": 458440, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9813916683197021, "global_step": 458441, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.029308557510376, "global_step": 458442, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0841410160064697, "global_step": 458443, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.076361894607544, "global_step": 458444, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.062652587890625, "global_step": 458445, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0923125743865967, "global_step": 458446, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0027737617492676, "global_step": 458447, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0534451007843018, "global_step": 458448, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0124447345733643, "global_step": 458449, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0624821186065674, "global_step": 458450, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.9911904335021973, "global_step": 458451, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1156532764434814, "global_step": 458452, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1192142963409424, "global_step": 458453, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.046076774597168, "global_step": 458454, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0325927734375, "global_step": 458455, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.171445846557617, "global_step": 458456, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.149944305419922, "global_step": 458457, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.139659881591797, "global_step": 458458, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.2123613357543945, "global_step": 458459, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1147000789642334, "global_step": 458460, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0742721557617188, "global_step": 458461, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0384225845336914, "global_step": 458462, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1233785152435303, "global_step": 458463, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0849180221557617, "global_step": 458464, "epoch": 822, "lr": 5e-05}
{"train_loss": 1.977473258972168, "global_step": 458465, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0965216159820557, "global_step": 458466, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.1614513397216797, "global_step": 458467, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0195531845092773, "global_step": 458468, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.0707626342773438, "global_step": 458469, "epoch": 822, "lr": 5e-05}
{"train_loss": 2.116338014602661, "global_step": 458470, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0461761951446533, "global_step": 458471, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9948903322219849, "global_step": 458472, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.124222993850708, "global_step": 458473, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.117734670639038, "global_step": 458474, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.030996084213257, "global_step": 458475, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9885203838348389, "global_step": 458476, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0716183185577393, "global_step": 458477, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0914504528045654, "global_step": 458478, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.063884735107422, "global_step": 458479, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.138293504714966, "global_step": 458480, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1426503658294678, "global_step": 458481, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0179641246795654, "global_step": 458482, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0327842235565186, "global_step": 458483, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.105419158935547, "global_step": 458484, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.084882974624634, "global_step": 458485, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1449391841888428, "global_step": 458486, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0258963108062744, "global_step": 458487, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0739519596099854, "global_step": 458488, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0615673065185547, "global_step": 458489, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0023365020751953, "global_step": 458490, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0862717628479004, "global_step": 458491, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.049086570739746, "global_step": 458492, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0362226963043213, "global_step": 458493, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0475447177886963, "global_step": 458494, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9843084812164307, "global_step": 458495, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0242409706115723, "global_step": 458496, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.029552459716797, "global_step": 458497, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.080740451812744, "global_step": 458498, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1267642974853516, "global_step": 458499, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.090411901473999, "global_step": 458500, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0701684951782227, "global_step": 458501, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0855274200439453, "global_step": 458502, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.030151844024658, "global_step": 458503, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9856082201004028, "global_step": 458504, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1606173515319824, "global_step": 458505, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.048542022705078, "global_step": 458506, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.05892276763916, "global_step": 458507, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.961731195449829, "global_step": 458508, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.007584810256958, "global_step": 458509, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.026998281478882, "global_step": 458510, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.058283805847168, "global_step": 458511, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.099449634552002, "global_step": 458512, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.116459608078003, "global_step": 458513, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.097597599029541, "global_step": 458514, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.041597843170166, "global_step": 458515, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.019205331802368, "global_step": 458516, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0455398559570312, "global_step": 458517, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.08284854888916, "global_step": 458518, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1367833614349365, "global_step": 458519, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0719690322875977, "global_step": 458520, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.090599775314331, "global_step": 458521, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0055696964263916, "global_step": 458522, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0883371829986572, "global_step": 458523, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.077953338623047, "global_step": 458524, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1125640869140625, "global_step": 458525, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0657286643981934, "global_step": 458526, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.048888921737671, "global_step": 458527, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0679588317871094, "global_step": 458528, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0598859786987305, "global_step": 458529, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1102304458618164, "global_step": 458530, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1691012382507324, "global_step": 458531, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0316779613494873, "global_step": 458532, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.059060573577881, "global_step": 458533, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.141148567199707, "global_step": 458534, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1145284175872803, "global_step": 458535, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.986362099647522, "global_step": 458536, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.02051043510437, "global_step": 458537, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0667779445648193, "global_step": 458538, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1137895584106445, "global_step": 458539, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1580848693847656, "global_step": 458540, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1242563724517822, "global_step": 458541, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0451700687408447, "global_step": 458542, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9872958660125732, "global_step": 458543, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1864023208618164, "global_step": 458544, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0942084789276123, "global_step": 458545, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0469584465026855, "global_step": 458546, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0359511375427246, "global_step": 458547, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0967419147491455, "global_step": 458548, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9496122598648071, "global_step": 458549, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0323550701141357, "global_step": 458550, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1641552448272705, "global_step": 458551, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9994007349014282, "global_step": 458552, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.124290704727173, "global_step": 458553, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9512659311294556, "global_step": 458554, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0461978912353516, "global_step": 458555, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0099756717681885, "global_step": 458556, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.099231481552124, "global_step": 458557, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.025484323501587, "global_step": 458558, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.013035535812378, "global_step": 458559, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.005545139312744, "global_step": 458560, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.13051700592041, "global_step": 458561, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.123549222946167, "global_step": 458562, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0292577743530273, "global_step": 458563, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0124566555023193, "global_step": 458564, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1479358673095703, "global_step": 458565, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1216437816619873, "global_step": 458566, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0106699466705322, "global_step": 458567, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.004746198654175, "global_step": 458568, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0819473266601562, "global_step": 458569, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.019711494445801, "global_step": 458570, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.005643129348755, "global_step": 458571, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.056093692779541, "global_step": 458572, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.06003999710083, "global_step": 458573, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9480030536651611, "global_step": 458574, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.138474941253662, "global_step": 458575, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1019296646118164, "global_step": 458576, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.022094964981079, "global_step": 458577, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0004568099975586, "global_step": 458578, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0068984031677246, "global_step": 458579, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1079792976379395, "global_step": 458580, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9327706098556519, "global_step": 458581, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.006026029586792, "global_step": 458582, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.076822280883789, "global_step": 458583, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0937042236328125, "global_step": 458584, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.102623224258423, "global_step": 458585, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.06221079826355, "global_step": 458586, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0349106788635254, "global_step": 458587, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0325870513916016, "global_step": 458588, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.073989152908325, "global_step": 458589, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0968165397644043, "global_step": 458590, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.016273021697998, "global_step": 458591, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9338903427124023, "global_step": 458592, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.059623956680298, "global_step": 458593, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.045342445373535, "global_step": 458594, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0923664569854736, "global_step": 458595, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.087421178817749, "global_step": 458596, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0077357292175293, "global_step": 458597, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.126051902770996, "global_step": 458598, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.065789222717285, "global_step": 458599, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.161961078643799, "global_step": 458600, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1110401153564453, "global_step": 458601, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0399341583251953, "global_step": 458602, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.008134603500366, "global_step": 458603, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0911834239959717, "global_step": 458604, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0677239894866943, "global_step": 458605, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.099463701248169, "global_step": 458606, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0749940872192383, "global_step": 458607, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.095325469970703, "global_step": 458608, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1056041717529297, "global_step": 458609, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.119333028793335, "global_step": 458610, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9781348705291748, "global_step": 458611, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.096132278442383, "global_step": 458612, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.073960542678833, "global_step": 458613, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0291409492492676, "global_step": 458614, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0344297885894775, "global_step": 458615, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.999411940574646, "global_step": 458616, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.081507921218872, "global_step": 458617, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.081319808959961, "global_step": 458618, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.029853582382202, "global_step": 458619, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0076515674591064, "global_step": 458620, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.019721031188965, "global_step": 458621, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9567986726760864, "global_step": 458622, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.984601616859436, "global_step": 458623, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0427496433258057, "global_step": 458624, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.096013307571411, "global_step": 458625, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1107993125915527, "global_step": 458626, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.155210256576538, "global_step": 458627, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.001635789871216, "global_step": 458628, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.148256778717041, "global_step": 458629, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.038067102432251, "global_step": 458630, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.009089469909668, "global_step": 458631, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0688095092773438, "global_step": 458632, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0404868125915527, "global_step": 458633, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.085202217102051, "global_step": 458634, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1275322437286377, "global_step": 458635, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.079692840576172, "global_step": 458636, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.062438726425171, "global_step": 458637, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9815235137939453, "global_step": 458638, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0649328231811523, "global_step": 458639, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0799643993377686, "global_step": 458640, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0288949012756348, "global_step": 458641, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0026657581329346, "global_step": 458642, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.10412335395813, "global_step": 458643, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.024350643157959, "global_step": 458644, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1288199424743652, "global_step": 458645, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.080112934112549, "global_step": 458646, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.021414279937744, "global_step": 458647, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.111353874206543, "global_step": 458648, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9923501014709473, "global_step": 458649, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.055696964263916, "global_step": 458650, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9990416765213013, "global_step": 458651, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0041582584381104, "global_step": 458652, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1466493606567383, "global_step": 458653, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1011767387390137, "global_step": 458654, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0671591758728027, "global_step": 458655, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0956242084503174, "global_step": 458656, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.066809892654419, "global_step": 458657, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.186882495880127, "global_step": 458658, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.13435697555542, "global_step": 458659, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0126864910125732, "global_step": 458660, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1463117599487305, "global_step": 458661, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.033231496810913, "global_step": 458662, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0746548175811768, "global_step": 458663, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.079394578933716, "global_step": 458664, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.030752182006836, "global_step": 458665, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0151374340057373, "global_step": 458666, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1349375247955322, "global_step": 458667, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.051234245300293, "global_step": 458668, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.061446189880371, "global_step": 458669, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.055610179901123, "global_step": 458670, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.075589656829834, "global_step": 458671, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0235824584960938, "global_step": 458672, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.109487295150757, "global_step": 458673, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9926302433013916, "global_step": 458674, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0174400806427, "global_step": 458675, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.012519598007202, "global_step": 458676, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.057788372039795, "global_step": 458677, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1064555644989014, "global_step": 458678, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9580721855163574, "global_step": 458679, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0256869792938232, "global_step": 458680, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.056593894958496, "global_step": 458681, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0479695796966553, "global_step": 458682, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.086299180984497, "global_step": 458683, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0590083599090576, "global_step": 458684, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0187506675720215, "global_step": 458685, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0705389976501465, "global_step": 458686, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0391082763671875, "global_step": 458687, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.062443733215332, "global_step": 458688, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.154397964477539, "global_step": 458689, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0711474418640137, "global_step": 458690, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1106529235839844, "global_step": 458691, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9641023874282837, "global_step": 458692, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1070568561553955, "global_step": 458693, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0666093826293945, "global_step": 458694, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1053102016448975, "global_step": 458695, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0685031414031982, "global_step": 458696, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9846887588500977, "global_step": 458697, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0827643871307373, "global_step": 458698, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.163416624069214, "global_step": 458699, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0828003883361816, "global_step": 458700, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.04954195022583, "global_step": 458701, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.991158366203308, "global_step": 458702, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0669186115264893, "global_step": 458703, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.991811990737915, "global_step": 458704, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0208661556243896, "global_step": 458705, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1067771911621094, "global_step": 458706, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0755224227905273, "global_step": 458707, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.112583637237549, "global_step": 458708, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.104443073272705, "global_step": 458709, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0786080360412598, "global_step": 458710, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.097358226776123, "global_step": 458711, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.140861988067627, "global_step": 458712, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0766327381134033, "global_step": 458713, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9774680137634277, "global_step": 458714, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0132827758789062, "global_step": 458715, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1176745891571045, "global_step": 458716, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.138578176498413, "global_step": 458717, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0509724617004395, "global_step": 458718, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.036376714706421, "global_step": 458719, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0420665740966797, "global_step": 458720, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1007914543151855, "global_step": 458721, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1028943061828613, "global_step": 458722, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.01377010345459, "global_step": 458723, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.112689733505249, "global_step": 458724, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.047351837158203, "global_step": 458725, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1101315021514893, "global_step": 458726, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1950619220733643, "global_step": 458727, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0838394165039062, "global_step": 458728, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0108418464660645, "global_step": 458729, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0586676597595215, "global_step": 458730, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0438084602355957, "global_step": 458731, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0932228565216064, "global_step": 458732, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1227283477783203, "global_step": 458733, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1243631839752197, "global_step": 458734, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0193488597869873, "global_step": 458735, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0735721588134766, "global_step": 458736, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.066892147064209, "global_step": 458737, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.088489294052124, "global_step": 458738, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0135364532470703, "global_step": 458739, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.060018539428711, "global_step": 458740, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1412808895111084, "global_step": 458741, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0981545448303223, "global_step": 458742, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0422816276550293, "global_step": 458743, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0494565963745117, "global_step": 458744, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0336904525756836, "global_step": 458745, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1329240798950195, "global_step": 458746, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0191380977630615, "global_step": 458747, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0671026706695557, "global_step": 458748, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0953831672668457, "global_step": 458749, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1441800594329834, "global_step": 458750, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.034318685531616, "global_step": 458751, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.126680374145508, "global_step": 458752, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0617880821228027, "global_step": 458753, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0398592948913574, "global_step": 458754, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0808732509613037, "global_step": 458755, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.017547130584717, "global_step": 458756, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1231627464294434, "global_step": 458757, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0735230445861816, "global_step": 458758, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1049575805664062, "global_step": 458759, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.035339593887329, "global_step": 458760, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0429627895355225, "global_step": 458761, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0414042472839355, "global_step": 458762, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0123775005340576, "global_step": 458763, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0992023944854736, "global_step": 458764, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0523176193237305, "global_step": 458765, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0321896076202393, "global_step": 458766, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0352749824523926, "global_step": 458767, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0985639095306396, "global_step": 458768, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9837162494659424, "global_step": 458769, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0793745517730713, "global_step": 458770, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.067007064819336, "global_step": 458771, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1263275146484375, "global_step": 458772, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0351321697235107, "global_step": 458773, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.072410821914673, "global_step": 458774, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0885958671569824, "global_step": 458775, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.020602226257324, "global_step": 458776, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.030921220779419, "global_step": 458777, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.070490837097168, "global_step": 458778, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0140609741210938, "global_step": 458779, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9972766637802124, "global_step": 458780, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.029588222503662, "global_step": 458781, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0770256519317627, "global_step": 458782, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1307337284088135, "global_step": 458783, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0462958812713623, "global_step": 458784, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.028963804244995, "global_step": 458785, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.084719657897949, "global_step": 458786, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.05631947517395, "global_step": 458787, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.089954137802124, "global_step": 458788, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0708024501800537, "global_step": 458789, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0987069606781006, "global_step": 458790, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.055885076522827, "global_step": 458791, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0610673427581787, "global_step": 458792, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0805306434631348, "global_step": 458793, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0930495262145996, "global_step": 458794, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.102142572402954, "global_step": 458795, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.047954797744751, "global_step": 458796, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0091428756713867, "global_step": 458797, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0327165126800537, "global_step": 458798, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0689456462860107, "global_step": 458799, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0664687156677246, "global_step": 458800, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1196839809417725, "global_step": 458801, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.073798894882202, "global_step": 458802, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1053102016448975, "global_step": 458803, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0685315132141113, "global_step": 458804, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1001813411712646, "global_step": 458805, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0429840087890625, "global_step": 458806, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0582315921783447, "global_step": 458807, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0350518226623535, "global_step": 458808, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1627697944641113, "global_step": 458809, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0998334884643555, "global_step": 458810, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1903059482574463, "global_step": 458811, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1402902603149414, "global_step": 458812, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0846753120422363, "global_step": 458813, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.076324224472046, "global_step": 458814, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0636768341064453, "global_step": 458815, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0833840370178223, "global_step": 458816, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9973019361495972, "global_step": 458817, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.102987766265869, "global_step": 458818, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0771355628967285, "global_step": 458819, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0364577770233154, "global_step": 458820, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.109588861465454, "global_step": 458821, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.059476613998413, "global_step": 458822, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.102854013442993, "global_step": 458823, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0451152324676514, "global_step": 458824, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9781956672668457, "global_step": 458825, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0448741912841797, "global_step": 458826, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.060089111328125, "global_step": 458827, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.060581922531128, "global_step": 458828, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.063049554824829, "global_step": 458829, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.047804594039917, "global_step": 458830, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.041778802871704, "global_step": 458831, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1110849380493164, "global_step": 458832, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.030588388442993, "global_step": 458833, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9978349208831787, "global_step": 458834, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0980324745178223, "global_step": 458835, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.114626884460449, "global_step": 458836, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1618576049804688, "global_step": 458837, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.041435480117798, "global_step": 458838, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0683043003082275, "global_step": 458839, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0611298084259033, "global_step": 458840, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0704805850982666, "global_step": 458841, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1247498989105225, "global_step": 458842, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1692798137664795, "global_step": 458843, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.019068479537964, "global_step": 458844, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0566182136535645, "global_step": 458845, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0696914196014404, "global_step": 458846, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.155357837677002, "global_step": 458847, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.088137626647949, "global_step": 458848, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.090352773666382, "global_step": 458849, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0228183269500732, "global_step": 458850, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0625088214874268, "global_step": 458851, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.044776439666748, "global_step": 458852, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.115091562271118, "global_step": 458853, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.106736183166504, "global_step": 458854, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1411843299865723, "global_step": 458855, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0834903717041016, "global_step": 458856, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1131436824798584, "global_step": 458857, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9958182573318481, "global_step": 458858, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0340051651000977, "global_step": 458859, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0361275672912598, "global_step": 458860, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.040048360824585, "global_step": 458861, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.047323226928711, "global_step": 458862, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0938055515289307, "global_step": 458863, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.068075180053711, "global_step": 458864, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1016621589660645, "global_step": 458865, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.079759120941162, "global_step": 458866, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0860610008239746, "global_step": 458867, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1164908409118652, "global_step": 458868, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.048839807510376, "global_step": 458869, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.134197473526001, "global_step": 458870, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1040828227996826, "global_step": 458871, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9997798204421997, "global_step": 458872, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.914678692817688, "global_step": 458873, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.092582941055298, "global_step": 458874, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.01659893989563, "global_step": 458875, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0393569469451904, "global_step": 458876, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.075873851776123, "global_step": 458877, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.074575901031494, "global_step": 458878, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.090616464614868, "global_step": 458879, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0276355743408203, "global_step": 458880, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.120034694671631, "global_step": 458881, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.069308042526245, "global_step": 458882, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.121516704559326, "global_step": 458883, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.105456829071045, "global_step": 458884, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.061584711074829, "global_step": 458885, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0636749267578125, "global_step": 458886, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0516722202301025, "global_step": 458887, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0425631999969482, "global_step": 458888, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9977357387542725, "global_step": 458889, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1004905700683594, "global_step": 458890, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.04386568069458, "global_step": 458891, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.075641393661499, "global_step": 458892, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0757598876953125, "global_step": 458893, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.143805742263794, "global_step": 458894, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.121058940887451, "global_step": 458895, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0084571838378906, "global_step": 458896, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1573569774627686, "global_step": 458897, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0989937782287598, "global_step": 458898, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1110308170318604, "global_step": 458899, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.111398696899414, "global_step": 458900, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.071092367172241, "global_step": 458901, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0639007091522217, "global_step": 458902, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0615384578704834, "global_step": 458903, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.128647804260254, "global_step": 458904, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.078465223312378, "global_step": 458905, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0673890113830566, "global_step": 458906, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.075369119644165, "global_step": 458907, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.077648878097534, "global_step": 458908, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1213297843933105, "global_step": 458909, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1504318714141846, "global_step": 458910, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.051870822906494, "global_step": 458911, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.011103630065918, "global_step": 458912, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.019547939300537, "global_step": 458913, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.050689458847046, "global_step": 458914, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.068815231323242, "global_step": 458915, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1270370483398438, "global_step": 458916, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.116734504699707, "global_step": 458917, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.028385877609253, "global_step": 458918, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1016876697540283, "global_step": 458919, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0600624084472656, "global_step": 458920, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.167161464691162, "global_step": 458921, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.005204677581787, "global_step": 458922, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0332064628601074, "global_step": 458923, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.087641716003418, "global_step": 458924, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0545120239257812, "global_step": 458925, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.929094910621643, "global_step": 458926, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0399329662323, "global_step": 458927, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.091555595397949, "global_step": 458928, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.131481170654297, "global_step": 458929, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0633976459503174, "global_step": 458930, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.008875846862793, "global_step": 458931, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1582984924316406, "global_step": 458932, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9554393291473389, "global_step": 458933, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.052290201187134, "global_step": 458934, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0801920890808105, "global_step": 458935, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.030163049697876, "global_step": 458936, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.114222526550293, "global_step": 458937, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.117074966430664, "global_step": 458938, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.088033676147461, "global_step": 458939, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.080016851425171, "global_step": 458940, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1124937534332275, "global_step": 458941, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0768444538116455, "global_step": 458942, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0852267742156982, "global_step": 458943, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1113293170928955, "global_step": 458944, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1740739345550537, "global_step": 458945, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.127678632736206, "global_step": 458946, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0365047454833984, "global_step": 458947, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.13033390045166, "global_step": 458948, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.090196132659912, "global_step": 458949, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0522449016571045, "global_step": 458950, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1181344985961914, "global_step": 458951, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.165351629257202, "global_step": 458952, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.116480827331543, "global_step": 458953, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.118272304534912, "global_step": 458954, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0605342388153076, "global_step": 458955, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.034482002258301, "global_step": 458956, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.131422281265259, "global_step": 458957, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0615732669830322, "global_step": 458958, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1898491382598877, "global_step": 458959, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0541610717773438, "global_step": 458960, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.032285213470459, "global_step": 458961, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0236756801605225, "global_step": 458962, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.033738851547241, "global_step": 458963, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0338501930236816, "global_step": 458964, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.176760673522949, "global_step": 458965, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0774502754211426, "global_step": 458966, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.077522039413452, "global_step": 458967, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0901787281036377, "global_step": 458968, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0698130130767822, "global_step": 458969, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.014141321182251, "global_step": 458970, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0128839015960693, "global_step": 458971, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0666518211364746, "global_step": 458972, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.090770721435547, "global_step": 458973, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0050814151763916, "global_step": 458974, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0813376903533936, "global_step": 458975, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0185999870300293, "global_step": 458976, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.035099744796753, "global_step": 458977, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0883939266204834, "global_step": 458978, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.092498540878296, "global_step": 458979, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.070859432220459, "global_step": 458980, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1590468883514404, "global_step": 458981, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.056656837463379, "global_step": 458982, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1276142597198486, "global_step": 458983, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.092360496520996, "global_step": 458984, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.030042886734009, "global_step": 458985, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0013716220855713, "global_step": 458986, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.041111946105957, "global_step": 458987, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.130108118057251, "global_step": 458988, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1534786224365234, "global_step": 458989, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.124176263809204, "global_step": 458990, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0369555950164795, "global_step": 458991, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0242998600006104, "global_step": 458992, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.081608772277832, "global_step": 458993, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0063536167144775, "global_step": 458994, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.031027317047119, "global_step": 458995, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1096670627593994, "global_step": 458996, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.057142496109009, "global_step": 458997, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1009325981140137, "global_step": 458998, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0637319087982178, "global_step": 458999, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9719159603118896, "global_step": 459000, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9842338562011719, "global_step": 459001, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1172804832458496, "global_step": 459002, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.060908555984497, "global_step": 459003, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.076674461364746, "global_step": 459004, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1319680213928223, "global_step": 459005, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.058720111846924, "global_step": 459006, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0568530559539795, "global_step": 459007, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.081347703933716, "global_step": 459008, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.069153308868408, "global_step": 459009, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0625972747802734, "global_step": 459010, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.096412420272827, "global_step": 459011, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.010145902633667, "global_step": 459012, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1279022693634033, "global_step": 459013, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1191086769104004, "global_step": 459014, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0353610515594482, "global_step": 459015, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1000795364379883, "global_step": 459016, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.08233380317688, "global_step": 459017, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.196091413497925, "global_step": 459018, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.108513832092285, "global_step": 459019, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.051879644393921, "global_step": 459020, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0572330951690674, "global_step": 459021, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.127490758895874, "global_step": 459022, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0913236141204834, "global_step": 459023, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.035797119140625, "global_step": 459024, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.105999708175659, "global_step": 459025, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1260294914245605, "global_step": 459026, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1820297241210938, "global_step": 459027, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1027424335479736, "global_step": 459028, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.113894462585449, "global_step": 459029, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0951404571533203, "global_step": 459030, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.06970477104187, "global_step": 459031, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0755767822265625, "global_step": 459032, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0836830139160156, "global_step": 459033, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.071662425994873, "global_step": 459034, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.084073066711426, "global_step": 459035, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0684092044830322, "global_step": 459036, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9883899688720703, "global_step": 459037, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0477964878082275, "global_step": 459038, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.106527090072632, "global_step": 459039, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.173491954803467, "global_step": 459040, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.077875852584839, "global_step": 459041, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1553874015808105, "global_step": 459042, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1170270442962646, "global_step": 459043, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1409778594970703, "global_step": 459044, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0849099159240723, "global_step": 459045, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.114663600921631, "global_step": 459046, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.989192008972168, "global_step": 459047, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0947396755218506, "global_step": 459048, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.102423906326294, "global_step": 459049, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9685335159301758, "global_step": 459050, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1281633377075195, "global_step": 459051, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.200681686401367, "global_step": 459052, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9132264852523804, "global_step": 459053, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0089378356933594, "global_step": 459054, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.075011730194092, "global_step": 459055, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.060497760772705, "global_step": 459056, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1063497066497803, "global_step": 459057, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0762410163879395, "global_step": 459058, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.118640661239624, "global_step": 459059, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.046786069869995, "global_step": 459060, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0168137550354004, "global_step": 459061, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0918421745300293, "global_step": 459062, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.038996458053589, "global_step": 459063, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0458226203918457, "global_step": 459064, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0606119632720947, "global_step": 459065, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0113792419433594, "global_step": 459066, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.103926181793213, "global_step": 459067, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1018226146698, "global_step": 459068, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.053898572921753, "global_step": 459069, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.101379632949829, "global_step": 459070, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.168808937072754, "global_step": 459071, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1059088706970215, "global_step": 459072, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0489256381988525, "global_step": 459073, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0780091285705566, "global_step": 459074, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0520598888397217, "global_step": 459075, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1667304039001465, "global_step": 459076, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.058556079864502, "global_step": 459077, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0863888263702393, "global_step": 459078, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0297629833221436, "global_step": 459079, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0135488510131836, "global_step": 459080, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1694445610046387, "global_step": 459081, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.090257167816162, "global_step": 459082, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1059322357177734, "global_step": 459083, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.078944683074951, "global_step": 459084, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0777900218963623, "global_step": 459085, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0435073375701904, "global_step": 459086, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1204090118408203, "global_step": 459087, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0435268878936768, "global_step": 459088, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.126305341720581, "global_step": 459089, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.205500841140747, "global_step": 459090, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1264991760253906, "global_step": 459091, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.038114309310913, "global_step": 459092, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1165220737457275, "global_step": 459093, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.055650472640991, "global_step": 459094, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0473031997680664, "global_step": 459095, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.083516836166382, "global_step": 459096, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0239548683166504, "global_step": 459097, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0981621742248535, "global_step": 459098, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.120246648788452, "global_step": 459099, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0579957962036133, "global_step": 459100, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0408763885498047, "global_step": 459101, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.053328275680542, "global_step": 459102, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.110185384750366, "global_step": 459103, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0332889556884766, "global_step": 459104, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.085942268371582, "global_step": 459105, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0343446731567383, "global_step": 459106, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0862576961517334, "global_step": 459107, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.035412073135376, "global_step": 459108, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0195443630218506, "global_step": 459109, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.982577919960022, "global_step": 459110, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.098881244659424, "global_step": 459111, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1135470867156982, "global_step": 459112, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0825347900390625, "global_step": 459113, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.067383289337158, "global_step": 459114, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.124492645263672, "global_step": 459115, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0593113899230957, "global_step": 459116, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0621025562286377, "global_step": 459117, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.165205955505371, "global_step": 459118, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.001220941543579, "global_step": 459119, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.942120909690857, "global_step": 459120, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0969960689544678, "global_step": 459121, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9756181240081787, "global_step": 459122, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.082542657852173, "global_step": 459123, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0695624351501465, "global_step": 459124, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.070763111114502, "global_step": 459125, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0136446952819824, "global_step": 459126, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1420743465423584, "global_step": 459127, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0410852432250977, "global_step": 459128, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.052706241607666, "global_step": 459129, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0292322635650635, "global_step": 459130, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.070604085922241, "global_step": 459131, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1292026042938232, "global_step": 459132, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.041994094848633, "global_step": 459133, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1592862606048584, "global_step": 459134, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.033665895462036, "global_step": 459135, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9782605171203613, "global_step": 459136, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.033609390258789, "global_step": 459137, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.027904510498047, "global_step": 459138, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0977985858917236, "global_step": 459139, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0278520584106445, "global_step": 459140, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.089876890182495, "global_step": 459141, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1212401390075684, "global_step": 459142, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0014586448669434, "global_step": 459143, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.030627727508545, "global_step": 459144, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.071648597717285, "global_step": 459145, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0301342010498047, "global_step": 459146, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0786490440368652, "global_step": 459147, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0739939212799072, "global_step": 459148, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9781494140625, "global_step": 459149, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9831352233886719, "global_step": 459150, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0380349159240723, "global_step": 459151, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0122838020324707, "global_step": 459152, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1459908485412598, "global_step": 459153, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0599887371063232, "global_step": 459154, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0568528175354004, "global_step": 459155, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0575520992279053, "global_step": 459156, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9808104038238525, "global_step": 459157, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.144821882247925, "global_step": 459158, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1126718521118164, "global_step": 459159, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0715994834899902, "global_step": 459160, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.07501220703125, "global_step": 459161, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.029188871383667, "global_step": 459162, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0904977321624756, "global_step": 459163, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.171471357345581, "global_step": 459164, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0837936401367188, "global_step": 459165, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1090900897979736, "global_step": 459166, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.060405731201172, "global_step": 459167, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0044679641723633, "global_step": 459168, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1001970767974854, "global_step": 459169, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.033238410949707, "global_step": 459170, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0921716690063477, "global_step": 459171, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.174762725830078, "global_step": 459172, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0390734672546387, "global_step": 459173, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.044462203979492, "global_step": 459174, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0739970207214355, "global_step": 459175, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0670738220214844, "global_step": 459176, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0067214965820312, "global_step": 459177, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.031468629837036, "global_step": 459178, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1067333221435547, "global_step": 459179, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0282933712005615, "global_step": 459180, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.130711078643799, "global_step": 459181, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0584237575531006, "global_step": 459182, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.999954104423523, "global_step": 459183, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.114561080932617, "global_step": 459184, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1116881370544434, "global_step": 459185, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.094276189804077, "global_step": 459186, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.212352991104126, "global_step": 459187, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0531563758850098, "global_step": 459188, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.050170660018921, "global_step": 459189, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0228734016418457, "global_step": 459190, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.052241802215576, "global_step": 459191, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.154578924179077, "global_step": 459192, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1168360710144043, "global_step": 459193, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.076545476913452, "global_step": 459194, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1181042194366455, "global_step": 459195, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9559557437896729, "global_step": 459196, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0757908821105957, "global_step": 459197, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0841429233551025, "global_step": 459198, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.063621759414673, "global_step": 459199, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.120664358139038, "global_step": 459200, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.096095323562622, "global_step": 459201, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.011603593826294, "global_step": 459202, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.089982271194458, "global_step": 459203, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0770158767700195, "global_step": 459204, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.068770170211792, "global_step": 459205, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0499918460845947, "global_step": 459206, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.154578685760498, "global_step": 459207, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9892284870147705, "global_step": 459208, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0604612827301025, "global_step": 459209, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.001155376434326, "global_step": 459210, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0468835830688477, "global_step": 459211, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1222176551818848, "global_step": 459212, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.146318197250366, "global_step": 459213, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.07342267036438, "global_step": 459214, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.064953565597534, "global_step": 459215, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.118039846420288, "global_step": 459216, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.060062885284424, "global_step": 459217, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1200687885284424, "global_step": 459218, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0710391998291016, "global_step": 459219, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1409361362457275, "global_step": 459220, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1203465461730957, "global_step": 459221, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1400365829467773, "global_step": 459222, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0608272552490234, "global_step": 459223, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0931522846221924, "global_step": 459224, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0032424926757812, "global_step": 459225, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0733022689819336, "global_step": 459226, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.021589994430542, "global_step": 459227, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.07759428024292, "global_step": 459228, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0791120529174805, "global_step": 459229, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0916311740875244, "global_step": 459230, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.121837854385376, "global_step": 459231, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.017016649246216, "global_step": 459232, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0964412689208984, "global_step": 459233, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0661888122558594, "global_step": 459234, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.098121166229248, "global_step": 459235, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0978472232818604, "global_step": 459236, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0440478324890137, "global_step": 459237, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0661630630493164, "global_step": 459238, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1247639656066895, "global_step": 459239, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9830758571624756, "global_step": 459240, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.10332989692688, "global_step": 459241, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.034497022628784, "global_step": 459242, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.071488857269287, "global_step": 459243, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.103422164916992, "global_step": 459244, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0939035415649414, "global_step": 459245, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.048661947250366, "global_step": 459246, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.099546432495117, "global_step": 459247, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0495283603668213, "global_step": 459248, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0948660373687744, "global_step": 459249, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0815365314483643, "global_step": 459250, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1278235912323, "global_step": 459251, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1056294441223145, "global_step": 459252, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.080113410949707, "global_step": 459253, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.038266658782959, "global_step": 459254, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1576943397521973, "global_step": 459255, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0578479766845703, "global_step": 459256, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.134387731552124, "global_step": 459257, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.046210527420044, "global_step": 459258, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0985865592956543, "global_step": 459259, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.135005235671997, "global_step": 459260, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0773353576660156, "global_step": 459261, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1289477348327637, "global_step": 459262, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.965699553489685, "global_step": 459263, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0608417987823486, "global_step": 459264, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1093392372131348, "global_step": 459265, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.167006492614746, "global_step": 459266, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.007676601409912, "global_step": 459267, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.027130365371704, "global_step": 459268, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.172278642654419, "global_step": 459269, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1953024864196777, "global_step": 459270, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1001272201538086, "global_step": 459271, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.106367826461792, "global_step": 459272, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1592111587524414, "global_step": 459273, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0376977920532227, "global_step": 459274, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0318360328674316, "global_step": 459275, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.095057487487793, "global_step": 459276, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.106015920639038, "global_step": 459277, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.073333740234375, "global_step": 459278, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0573158264160156, "global_step": 459279, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0325634479522705, "global_step": 459280, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.084212303161621, "global_step": 459281, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.066235303878784, "global_step": 459282, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.06372332572937, "global_step": 459283, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1292123794555664, "global_step": 459284, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.110665798187256, "global_step": 459285, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0257978439331055, "global_step": 459286, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.080043315887451, "global_step": 459287, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0556564331054688, "global_step": 459288, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.036254644393921, "global_step": 459289, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0794506072998047, "global_step": 459290, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.09019136428833, "global_step": 459291, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0068061351776123, "global_step": 459292, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.137014389038086, "global_step": 459293, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1175708770751953, "global_step": 459294, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0068368911743164, "global_step": 459295, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.028883457183838, "global_step": 459296, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0766000747680664, "global_step": 459297, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0963222980499268, "global_step": 459298, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1345231533050537, "global_step": 459299, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1298840045928955, "global_step": 459300, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1049201488494873, "global_step": 459301, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.114363431930542, "global_step": 459302, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.149482250213623, "global_step": 459303, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.062299966812134, "global_step": 459304, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0915021896362305, "global_step": 459305, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1866960525512695, "global_step": 459306, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0320444107055664, "global_step": 459307, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0724127292633057, "global_step": 459308, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.029325008392334, "global_step": 459309, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1053526401519775, "global_step": 459310, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0122835636138916, "global_step": 459311, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0574915409088135, "global_step": 459312, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0172948837280273, "global_step": 459313, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.061143636703491, "global_step": 459314, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1682546138763428, "global_step": 459315, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0421302318573, "global_step": 459316, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.190007448196411, "global_step": 459317, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0861475467681885, "global_step": 459318, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0684738159179688, "global_step": 459319, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0794801712036133, "global_step": 459320, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0451884269714355, "global_step": 459321, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0887699127197266, "global_step": 459322, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1082522869110107, "global_step": 459323, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.109001636505127, "global_step": 459324, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.177298069000244, "global_step": 459325, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0437865257263184, "global_step": 459326, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.071047306060791, "global_step": 459327, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0996339321136475, "global_step": 459328, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0703585147857666, "global_step": 459329, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.14628267288208, "global_step": 459330, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9688441753387451, "global_step": 459331, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1544833183288574, "global_step": 459332, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.012813091278076, "global_step": 459333, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0132436752319336, "global_step": 459334, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.103919267654419, "global_step": 459335, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9985955953598022, "global_step": 459336, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1304261684417725, "global_step": 459337, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1005187034606934, "global_step": 459338, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0691771507263184, "global_step": 459339, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1568965911865234, "global_step": 459340, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.102484941482544, "global_step": 459341, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.071831226348877, "global_step": 459342, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.026071786880493, "global_step": 459343, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0886037349700928, "global_step": 459344, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.03787899017334, "global_step": 459345, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.115983247756958, "global_step": 459346, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9961354732513428, "global_step": 459347, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1459741592407227, "global_step": 459348, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1540417671203613, "global_step": 459349, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0467264652252197, "global_step": 459350, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0824828147888184, "global_step": 459351, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0175766944885254, "global_step": 459352, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.075018882751465, "global_step": 459353, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1225860118865967, "global_step": 459354, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1755661964416504, "global_step": 459355, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0810117721557617, "global_step": 459356, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0792882442474365, "global_step": 459357, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0843803882598877, "global_step": 459358, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0316755771636963, "global_step": 459359, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0987026691436768, "global_step": 459360, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0839130878448486, "global_step": 459361, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.041480302810669, "global_step": 459362, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.105334997177124, "global_step": 459363, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1092042922973633, "global_step": 459364, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0225343704223633, "global_step": 459365, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0408735275268555, "global_step": 459366, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.216261148452759, "global_step": 459367, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.106515645980835, "global_step": 459368, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1078057289123535, "global_step": 459369, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.09613037109375, "global_step": 459370, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.052833318710327, "global_step": 459371, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.122174024581909, "global_step": 459372, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0603911876678467, "global_step": 459373, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.048191547393799, "global_step": 459374, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.147392749786377, "global_step": 459375, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.071803092956543, "global_step": 459376, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1047325134277344, "global_step": 459377, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0863702297210693, "global_step": 459378, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.086374521255493, "global_step": 459379, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.12695050239563, "global_step": 459380, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.105788230895996, "global_step": 459381, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.037604570388794, "global_step": 459382, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.054760217666626, "global_step": 459383, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1102609634399414, "global_step": 459384, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1063640117645264, "global_step": 459385, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.103959560394287, "global_step": 459386, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0775749683380127, "global_step": 459387, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.050741672515869, "global_step": 459388, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0227644443511963, "global_step": 459389, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.039097785949707, "global_step": 459390, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1495540142059326, "global_step": 459391, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0369622707366943, "global_step": 459392, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.073082447052002, "global_step": 459393, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0867419242858887, "global_step": 459394, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0959954261779785, "global_step": 459395, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.113823413848877, "global_step": 459396, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.064073085784912, "global_step": 459397, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0155093669891357, "global_step": 459398, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0320045948028564, "global_step": 459399, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.146562337875366, "global_step": 459400, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.082111358642578, "global_step": 459401, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0710670948028564, "global_step": 459402, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0174295902252197, "global_step": 459403, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.053938627243042, "global_step": 459404, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.074418783187866, "global_step": 459405, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.012251615524292, "global_step": 459406, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0426878929138184, "global_step": 459407, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0745620727539062, "global_step": 459408, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9888732433319092, "global_step": 459409, "epoch": 823, "lr": 5e-05}
{"train_loss": 1.9324009418487549, "global_step": 459410, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0905587673187256, "global_step": 459411, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.062791347503662, "global_step": 459412, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.103843927383423, "global_step": 459413, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0005650520324707, "global_step": 459414, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.09151291847229, "global_step": 459415, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.214568853378296, "global_step": 459416, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.084239959716797, "global_step": 459417, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0888187885284424, "global_step": 459418, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0017950534820557, "global_step": 459419, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.146789312362671, "global_step": 459420, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0916125774383545, "global_step": 459421, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.066987991333008, "global_step": 459422, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.075605869293213, "global_step": 459423, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0724310874938965, "global_step": 459424, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.111426591873169, "global_step": 459425, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0798184871673584, "global_step": 459426, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.004004716873169, "global_step": 459427, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0769481658935547, "global_step": 459428, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.037928342819214, "global_step": 459429, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0439295768737793, "global_step": 459430, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0940840244293213, "global_step": 459431, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1335415840148926, "global_step": 459432, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0991837978363037, "global_step": 459433, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.2137372493743896, "global_step": 459434, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.1500396728515625, "global_step": 459435, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0961313247680664, "global_step": 459436, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.12382173538208, "global_step": 459437, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.072465419769287, "global_step": 459438, "epoch": 823, "lr": 5e-05}
{"train_loss": 2.0301830768585205, "global_step": 459439, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0546698570251465, "global_step": 459440, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1044647693634033, "global_step": 459441, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0413081645965576, "global_step": 459442, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.171675682067871, "global_step": 459443, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.063992500305176, "global_step": 459444, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9653096199035645, "global_step": 459445, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9769132137298584, "global_step": 459446, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0394468307495117, "global_step": 459447, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.069578170776367, "global_step": 459448, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9952983856201172, "global_step": 459449, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.075314521789551, "global_step": 459450, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0642271041870117, "global_step": 459451, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.060900926589966, "global_step": 459452, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0720412731170654, "global_step": 459453, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.8889912366867065, "global_step": 459454, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.05881929397583, "global_step": 459455, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.049903392791748, "global_step": 459456, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0958309173583984, "global_step": 459457, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.081427574157715, "global_step": 459458, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9767065048217773, "global_step": 459459, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0271153450012207, "global_step": 459460, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.000868558883667, "global_step": 459461, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.062330961227417, "global_step": 459462, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0827317237854004, "global_step": 459463, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1054203510284424, "global_step": 459464, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1238694190979004, "global_step": 459465, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.052591323852539, "global_step": 459466, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0149567127227783, "global_step": 459467, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9826908111572266, "global_step": 459468, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.067122459411621, "global_step": 459469, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0606343746185303, "global_step": 459470, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0062203407287598, "global_step": 459471, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0125458240509033, "global_step": 459472, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.011326313018799, "global_step": 459473, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.09753680229187, "global_step": 459474, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0417871475219727, "global_step": 459475, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0268728733062744, "global_step": 459476, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.06632137298584, "global_step": 459477, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.101167917251587, "global_step": 459478, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0745973587036133, "global_step": 459479, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9790374040603638, "global_step": 459480, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1342720985412598, "global_step": 459481, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0566301345825195, "global_step": 459482, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0501506328582764, "global_step": 459483, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0775504112243652, "global_step": 459484, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1068625450134277, "global_step": 459485, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.056375741958618, "global_step": 459486, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0365912914276123, "global_step": 459487, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0478508472442627, "global_step": 459488, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.186549186706543, "global_step": 459489, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0893712043762207, "global_step": 459490, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.049980640411377, "global_step": 459491, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.008927583694458, "global_step": 459492, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0860249996185303, "global_step": 459493, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.029306650161743, "global_step": 459494, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0399489402770996, "global_step": 459495, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0300521850585938, "global_step": 459496, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.014116048812866, "global_step": 459497, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.001953363418579, "global_step": 459498, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1208484172821045, "global_step": 459499, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0858967304229736, "global_step": 459500, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9861117601394653, "global_step": 459501, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.056117057800293, "global_step": 459502, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9997849464416504, "global_step": 459503, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.075500965118408, "global_step": 459504, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.117539644241333, "global_step": 459505, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0557117462158203, "global_step": 459506, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0104238986968994, "global_step": 459507, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.121582508087158, "global_step": 459508, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.986212134361267, "global_step": 459509, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0777249336242676, "global_step": 459510, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0634078979492188, "global_step": 459511, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.007133960723877, "global_step": 459512, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0319271087646484, "global_step": 459513, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.094731092453003, "global_step": 459514, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0692694187164307, "global_step": 459515, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9576280117034912, "global_step": 459516, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.077633857727051, "global_step": 459517, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1095526218414307, "global_step": 459518, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0282092094421387, "global_step": 459519, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.153907299041748, "global_step": 459520, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0096044540405273, "global_step": 459521, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0139076709747314, "global_step": 459522, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9939521551132202, "global_step": 459523, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.088578224182129, "global_step": 459524, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.109428644180298, "global_step": 459525, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0518429279327393, "global_step": 459526, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0169801712036133, "global_step": 459527, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0526175498962402, "global_step": 459528, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.042309045791626, "global_step": 459529, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.03896427154541, "global_step": 459530, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1574034690856934, "global_step": 459531, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0697994232177734, "global_step": 459532, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.065882682800293, "global_step": 459533, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0472772121429443, "global_step": 459534, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0622119903564453, "global_step": 459535, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9804844856262207, "global_step": 459536, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0668678283691406, "global_step": 459537, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.05867862701416, "global_step": 459538, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1222617626190186, "global_step": 459539, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0993199348449707, "global_step": 459540, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.086643934249878, "global_step": 459541, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1451637744903564, "global_step": 459542, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.028233289718628, "global_step": 459543, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0839829444885254, "global_step": 459544, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.02432918548584, "global_step": 459545, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.996642827987671, "global_step": 459546, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0834405422210693, "global_step": 459547, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0325779914855957, "global_step": 459548, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0753045082092285, "global_step": 459549, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.105403184890747, "global_step": 459550, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.021493673324585, "global_step": 459551, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.070598840713501, "global_step": 459552, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0977847576141357, "global_step": 459553, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1429314613342285, "global_step": 459554, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0123560428619385, "global_step": 459555, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0517520904541016, "global_step": 459556, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0384042263031006, "global_step": 459557, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0164198875427246, "global_step": 459558, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0770678520202637, "global_step": 459559, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0828299522399902, "global_step": 459560, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1120564937591553, "global_step": 459561, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.037782907485962, "global_step": 459562, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0373148918151855, "global_step": 459563, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.015528440475464, "global_step": 459564, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0999438762664795, "global_step": 459565, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.036843776702881, "global_step": 459566, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0408315658569336, "global_step": 459567, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0735912322998047, "global_step": 459568, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.10357403755188, "global_step": 459569, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.045853614807129, "global_step": 459570, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0831971168518066, "global_step": 459571, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.056476593017578, "global_step": 459572, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1002347469329834, "global_step": 459573, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.096029758453369, "global_step": 459574, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0255417823791504, "global_step": 459575, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0426180362701416, "global_step": 459576, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.048556327819824, "global_step": 459577, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9937089681625366, "global_step": 459578, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0063140392303467, "global_step": 459579, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0234479904174805, "global_step": 459580, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.074085235595703, "global_step": 459581, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.089416742324829, "global_step": 459582, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0178754329681396, "global_step": 459583, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.087712526321411, "global_step": 459584, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0660347938537598, "global_step": 459585, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1114823818206787, "global_step": 459586, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1127305030822754, "global_step": 459587, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1236021518707275, "global_step": 459588, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1260244846343994, "global_step": 459589, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.104055881500244, "global_step": 459590, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0378341674804688, "global_step": 459591, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.052912950515747, "global_step": 459592, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.124307155609131, "global_step": 459593, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.047844886779785, "global_step": 459594, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9991166591644287, "global_step": 459595, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1000654697418213, "global_step": 459596, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0819594860076904, "global_step": 459597, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9940322637557983, "global_step": 459598, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0370688438415527, "global_step": 459599, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.078538179397583, "global_step": 459600, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0580036640167236, "global_step": 459601, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9381073713302612, "global_step": 459602, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.014962911605835, "global_step": 459603, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.175665855407715, "global_step": 459604, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.977757453918457, "global_step": 459605, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.053280830383301, "global_step": 459606, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0842928886413574, "global_step": 459607, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0503005981445312, "global_step": 459608, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0709736347198486, "global_step": 459609, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.024198532104492, "global_step": 459610, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0021541118621826, "global_step": 459611, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.12463641166687, "global_step": 459612, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.101566791534424, "global_step": 459613, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0473735332489014, "global_step": 459614, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0577778816223145, "global_step": 459615, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.068601608276367, "global_step": 459616, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0826971530914307, "global_step": 459617, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.036189556121826, "global_step": 459618, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.142605781555176, "global_step": 459619, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1432058811187744, "global_step": 459620, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0576772689819336, "global_step": 459621, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0170187950134277, "global_step": 459622, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.068481206893921, "global_step": 459623, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0478665828704834, "global_step": 459624, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0527875423431396, "global_step": 459625, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1123807430267334, "global_step": 459626, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.07588791847229, "global_step": 459627, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.031602382659912, "global_step": 459628, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0274453163146973, "global_step": 459629, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1282262802124023, "global_step": 459630, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0755176544189453, "global_step": 459631, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1812522411346436, "global_step": 459632, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0930800437927246, "global_step": 459633, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.086695909500122, "global_step": 459634, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.006405830383301, "global_step": 459635, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0991299152374268, "global_step": 459636, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.041414976119995, "global_step": 459637, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.091801643371582, "global_step": 459638, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.058567523956299, "global_step": 459639, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9890748262405396, "global_step": 459640, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9781628847122192, "global_step": 459641, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9949523210525513, "global_step": 459642, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0777382850646973, "global_step": 459643, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0846378803253174, "global_step": 459644, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1463024616241455, "global_step": 459645, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1119492053985596, "global_step": 459646, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0421133041381836, "global_step": 459647, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1097960472106934, "global_step": 459648, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0577359199523926, "global_step": 459649, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0196335315704346, "global_step": 459650, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.12119722366333, "global_step": 459651, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0110230445861816, "global_step": 459652, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.977615475654602, "global_step": 459653, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0977699756622314, "global_step": 459654, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0067391395568848, "global_step": 459655, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.077348470687866, "global_step": 459656, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0282042026519775, "global_step": 459657, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.095216751098633, "global_step": 459658, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.095442533493042, "global_step": 459659, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0986878871917725, "global_step": 459660, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.063115358352661, "global_step": 459661, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.069390296936035, "global_step": 459662, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0597126483917236, "global_step": 459663, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1546733379364014, "global_step": 459664, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.006261110305786, "global_step": 459665, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.999701738357544, "global_step": 459666, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0038716793060303, "global_step": 459667, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.075061321258545, "global_step": 459668, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9218496084213257, "global_step": 459669, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.120805263519287, "global_step": 459670, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0577199459075928, "global_step": 459671, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.045419931411743, "global_step": 459672, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0019233226776123, "global_step": 459673, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0589170455932617, "global_step": 459674, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0896496772766113, "global_step": 459675, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.114455461502075, "global_step": 459676, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.956871747970581, "global_step": 459677, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.135328769683838, "global_step": 459678, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0826802253723145, "global_step": 459679, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0178463459014893, "global_step": 459680, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0392632484436035, "global_step": 459681, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.050096273422241, "global_step": 459682, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0334978103637695, "global_step": 459683, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9963898658752441, "global_step": 459684, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.09637188911438, "global_step": 459685, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1133556365966797, "global_step": 459686, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.080636978149414, "global_step": 459687, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9314205646514893, "global_step": 459688, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.17038631439209, "global_step": 459689, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.989366888999939, "global_step": 459690, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9766325950622559, "global_step": 459691, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1413049697875977, "global_step": 459692, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0674362182617188, "global_step": 459693, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0329952239990234, "global_step": 459694, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0486083030700684, "global_step": 459695, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.006070613861084, "global_step": 459696, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9687165021896362, "global_step": 459697, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.07324481010437, "global_step": 459698, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0111002922058105, "global_step": 459699, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1035289764404297, "global_step": 459700, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0779802799224854, "global_step": 459701, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0340328216552734, "global_step": 459702, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0638747215270996, "global_step": 459703, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0585451126098633, "global_step": 459704, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0755369663238525, "global_step": 459705, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0060009956359863, "global_step": 459706, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.021165609359741, "global_step": 459707, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.168071746826172, "global_step": 459708, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.187458038330078, "global_step": 459709, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.083966016769409, "global_step": 459710, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1332452297210693, "global_step": 459711, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0502216815948486, "global_step": 459712, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.042990207672119, "global_step": 459713, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.97443425655365, "global_step": 459714, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.069209337234497, "global_step": 459715, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.084754467010498, "global_step": 459716, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1492295265197754, "global_step": 459717, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0732951164245605, "global_step": 459718, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.066389560699463, "global_step": 459719, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1879382133483887, "global_step": 459720, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.068112850189209, "global_step": 459721, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.087470769882202, "global_step": 459722, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.084322452545166, "global_step": 459723, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.125875234603882, "global_step": 459724, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0450923442840576, "global_step": 459725, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0669429302215576, "global_step": 459726, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.033764123916626, "global_step": 459727, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0989246368408203, "global_step": 459728, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.05124568939209, "global_step": 459729, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0283610820770264, "global_step": 459730, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0710411071777344, "global_step": 459731, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.056875228881836, "global_step": 459732, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1899642944335938, "global_step": 459733, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0759077072143555, "global_step": 459734, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.068504571914673, "global_step": 459735, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0449068546295166, "global_step": 459736, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0492708683013916, "global_step": 459737, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0930960178375244, "global_step": 459738, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0558221340179443, "global_step": 459739, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0749945640563965, "global_step": 459740, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.157841444015503, "global_step": 459741, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.04935622215271, "global_step": 459742, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.146965742111206, "global_step": 459743, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0954489707946777, "global_step": 459744, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.076218843460083, "global_step": 459745, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.071911334991455, "global_step": 459746, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.153548240661621, "global_step": 459747, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1028990745544434, "global_step": 459748, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0510523319244385, "global_step": 459749, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0810983180999756, "global_step": 459750, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1169848442077637, "global_step": 459751, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.06506609916687, "global_step": 459752, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.099776029586792, "global_step": 459753, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.011608839035034, "global_step": 459754, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.970353364944458, "global_step": 459755, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9914478063583374, "global_step": 459756, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1341888904571533, "global_step": 459757, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1148664951324463, "global_step": 459758, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0585217475891113, "global_step": 459759, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0452253818511963, "global_step": 459760, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0624890327453613, "global_step": 459761, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1354689598083496, "global_step": 459762, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.012573003768921, "global_step": 459763, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1510443687438965, "global_step": 459764, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0686981678009033, "global_step": 459765, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0657129287719727, "global_step": 459766, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0916051864624023, "global_step": 459767, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.007051706314087, "global_step": 459768, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0893537998199463, "global_step": 459769, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0765013694763184, "global_step": 459770, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0238189697265625, "global_step": 459771, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.10412335395813, "global_step": 459772, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0447537899017334, "global_step": 459773, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1699748039245605, "global_step": 459774, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0402188301086426, "global_step": 459775, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0598270893096924, "global_step": 459776, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.048198699951172, "global_step": 459777, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0360705852508545, "global_step": 459778, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0635604858398438, "global_step": 459779, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1008989810943604, "global_step": 459780, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.093295097351074, "global_step": 459781, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.027390718460083, "global_step": 459782, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0502543449401855, "global_step": 459783, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.009638547897339, "global_step": 459784, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0575478076934814, "global_step": 459785, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1098878383636475, "global_step": 459786, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0545408725738525, "global_step": 459787, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0877673625946045, "global_step": 459788, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1852197647094727, "global_step": 459789, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.113582134246826, "global_step": 459790, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0578207969665527, "global_step": 459791, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0522449016571045, "global_step": 459792, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0470633506774902, "global_step": 459793, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0991153717041016, "global_step": 459794, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1027908325195312, "global_step": 459795, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0525665283203125, "global_step": 459796, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.026536703109741, "global_step": 459797, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.023803949356079, "global_step": 459798, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.095385789871216, "global_step": 459799, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0880234241485596, "global_step": 459800, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0854287147521973, "global_step": 459801, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0273642539978027, "global_step": 459802, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0399553775787354, "global_step": 459803, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.103119134902954, "global_step": 459804, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1033406257629395, "global_step": 459805, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0622098445892334, "global_step": 459806, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.005782127380371, "global_step": 459807, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.162389039993286, "global_step": 459808, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.12007474899292, "global_step": 459809, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.062559127807617, "global_step": 459810, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1004695892333984, "global_step": 459811, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.030625581741333, "global_step": 459812, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0768327713012695, "global_step": 459813, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.089839220046997, "global_step": 459814, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.132061243057251, "global_step": 459815, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9850542545318604, "global_step": 459816, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0721800327301025, "global_step": 459817, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0937016010284424, "global_step": 459818, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1057236194610596, "global_step": 459819, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.070211887359619, "global_step": 459820, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0283284187316895, "global_step": 459821, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.93030846118927, "global_step": 459822, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.101309061050415, "global_step": 459823, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0426292419433594, "global_step": 459824, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0580036640167236, "global_step": 459825, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0275325775146484, "global_step": 459826, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.114511489868164, "global_step": 459827, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.096836805343628, "global_step": 459828, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0036299228668213, "global_step": 459829, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.077253580093384, "global_step": 459830, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.157709836959839, "global_step": 459831, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9987139701843262, "global_step": 459832, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.071302652359009, "global_step": 459833, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0719316005706787, "global_step": 459834, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.19232439994812, "global_step": 459835, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1273980140686035, "global_step": 459836, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0468127727508545, "global_step": 459837, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.040706157684326, "global_step": 459838, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1197354793548584, "global_step": 459839, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.045391798019409, "global_step": 459840, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.139770030975342, "global_step": 459841, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.124189615249634, "global_step": 459842, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0272364616394043, "global_step": 459843, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0630717277526855, "global_step": 459844, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0761327743530273, "global_step": 459845, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9810467958450317, "global_step": 459846, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0985748767852783, "global_step": 459847, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.143656015396118, "global_step": 459848, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.104058265686035, "global_step": 459849, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0774288177490234, "global_step": 459850, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0302088260650635, "global_step": 459851, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0869882106781006, "global_step": 459852, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.980120301246643, "global_step": 459853, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9909738302230835, "global_step": 459854, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.093123197555542, "global_step": 459855, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.079158306121826, "global_step": 459856, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0030040740966797, "global_step": 459857, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.019730806350708, "global_step": 459858, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.054877281188965, "global_step": 459859, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1077182292938232, "global_step": 459860, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.069483995437622, "global_step": 459861, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0831658840179443, "global_step": 459862, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.031667709350586, "global_step": 459863, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0178627967834473, "global_step": 459864, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.06844425201416, "global_step": 459865, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.135477304458618, "global_step": 459866, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0785439014434814, "global_step": 459867, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.011194944381714, "global_step": 459868, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.162346839904785, "global_step": 459869, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.109693765640259, "global_step": 459870, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0297112464904785, "global_step": 459871, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.03108286857605, "global_step": 459872, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9729841947555542, "global_step": 459873, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9773075580596924, "global_step": 459874, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0334417819976807, "global_step": 459875, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.034605026245117, "global_step": 459876, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1688568592071533, "global_step": 459877, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1286096572875977, "global_step": 459878, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0523464679718018, "global_step": 459879, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0768229961395264, "global_step": 459880, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.068455696105957, "global_step": 459881, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0998096466064453, "global_step": 459882, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.07528018951416, "global_step": 459883, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1126797199249268, "global_step": 459884, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0273849964141846, "global_step": 459885, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.100041389465332, "global_step": 459886, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.036473274230957, "global_step": 459887, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.020447254180908, "global_step": 459888, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0422561168670654, "global_step": 459889, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9556227922439575, "global_step": 459890, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9885246753692627, "global_step": 459891, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0501575469970703, "global_step": 459892, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.109367847442627, "global_step": 459893, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.001436948776245, "global_step": 459894, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0871477127075195, "global_step": 459895, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.169281244277954, "global_step": 459896, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.055967330932617, "global_step": 459897, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.046274423599243, "global_step": 459898, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.170473337173462, "global_step": 459899, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.074122428894043, "global_step": 459900, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0315840244293213, "global_step": 459901, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.046978235244751, "global_step": 459902, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1077640056610107, "global_step": 459903, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0540738105773926, "global_step": 459904, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0679588317871094, "global_step": 459905, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0002942085266113, "global_step": 459906, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.14621639251709, "global_step": 459907, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1230759620666504, "global_step": 459908, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0815846920013428, "global_step": 459909, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0854289531707764, "global_step": 459910, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.055528163909912, "global_step": 459911, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0390124320983887, "global_step": 459912, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.098289966583252, "global_step": 459913, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0667190551757812, "global_step": 459914, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.059401750564575, "global_step": 459915, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.070347785949707, "global_step": 459916, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.078207492828369, "global_step": 459917, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.039048910140991, "global_step": 459918, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.066617727279663, "global_step": 459919, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.999868631362915, "global_step": 459920, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.037876844406128, "global_step": 459921, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.081554651260376, "global_step": 459922, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0993847846984863, "global_step": 459923, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.090073585510254, "global_step": 459924, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0689918994903564, "global_step": 459925, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.061079502105713, "global_step": 459926, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.114405632019043, "global_step": 459927, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.02170467376709, "global_step": 459928, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.082016944885254, "global_step": 459929, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0670430660247803, "global_step": 459930, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0036566257476807, "global_step": 459931, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.131232500076294, "global_step": 459932, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0503644943237305, "global_step": 459933, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0182132720947266, "global_step": 459934, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0391366481781006, "global_step": 459935, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.078730344772339, "global_step": 459936, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.114849328994751, "global_step": 459937, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0619359016418457, "global_step": 459938, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.050772190093994, "global_step": 459939, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1628618240356445, "global_step": 459940, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0562665462493896, "global_step": 459941, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.062300443649292, "global_step": 459942, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0593056678771973, "global_step": 459943, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0964369773864746, "global_step": 459944, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.058750629425049, "global_step": 459945, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1255877017974854, "global_step": 459946, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9477877616882324, "global_step": 459947, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.079221248626709, "global_step": 459948, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1031150817871094, "global_step": 459949, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9869880676269531, "global_step": 459950, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.101525068283081, "global_step": 459951, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0280277729034424, "global_step": 459952, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.089749574661255, "global_step": 459953, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.02858304977417, "global_step": 459954, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0529747009277344, "global_step": 459955, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0242273807525635, "global_step": 459956, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.021831750869751, "global_step": 459957, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.06412410736084, "global_step": 459958, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0547306537628174, "global_step": 459959, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1387438774108887, "global_step": 459960, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0768160820007324, "global_step": 459961, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1293163299560547, "global_step": 459962, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0959653854370117, "global_step": 459963, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1041746139526367, "global_step": 459964, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.111577272415161, "global_step": 459965, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0674121379852295, "global_step": 459966, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0999433994293213, "global_step": 459967, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0272648334503174, "global_step": 459968, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1214168071746826, "global_step": 459969, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0690855979919434, "global_step": 459970, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0597476959228516, "global_step": 459971, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0641672611236572, "global_step": 459972, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1293575763702393, "global_step": 459973, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0829172134399414, "global_step": 459974, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.033437967300415, "global_step": 459975, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.059593915939331, "global_step": 459976, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1035656929016113, "global_step": 459977, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.059955358505249, "global_step": 459978, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0824873447418213, "global_step": 459979, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0899481773376465, "global_step": 459980, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.089785099029541, "global_step": 459981, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.081411361694336, "global_step": 459982, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.134883403778076, "global_step": 459983, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1329243183135986, "global_step": 459984, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.050868511199951, "global_step": 459985, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0416741371154785, "global_step": 459986, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.106034517288208, "global_step": 459987, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.023815631866455, "global_step": 459988, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.02264404296875, "global_step": 459989, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0602505207061768, "global_step": 459990, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0132176876068115, "global_step": 459991, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.027326822280884, "global_step": 459992, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.11771297454834, "global_step": 459993, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0895042419433594, "global_step": 459994, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.080164670944214, "global_step": 459995, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0569655895233154, "global_step": 459996, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1681931018829346, "global_step": 459997, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1521353721618652, "global_step": 459998, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0341246128082275, "global_step": 459999, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0956530570983887, "global_step": 460000, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0737547874450684, "global_step": 460001, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1104276180267334, "global_step": 460002, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.985748291015625, "global_step": 460003, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1560609340667725, "global_step": 460004, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0907626152038574, "global_step": 460005, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.010664701461792, "global_step": 460006, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0611183643341064, "global_step": 460007, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.022312879562378, "global_step": 460008, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.054300308227539, "global_step": 460009, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1345958709716797, "global_step": 460010, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0485360622406006, "global_step": 460011, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0546584129333496, "global_step": 460012, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.069561719894409, "global_step": 460013, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0702269077301025, "global_step": 460014, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0591328144073486, "global_step": 460015, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9804986715316772, "global_step": 460016, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9849464893341064, "global_step": 460017, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0655112266540527, "global_step": 460018, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0168955326080322, "global_step": 460019, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0482094287872314, "global_step": 460020, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9905613660812378, "global_step": 460021, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0498197078704834, "global_step": 460022, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0471396446228027, "global_step": 460023, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0490407943725586, "global_step": 460024, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0122861862182617, "global_step": 460025, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.046898603439331, "global_step": 460026, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.082697629928589, "global_step": 460027, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.013523578643799, "global_step": 460028, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.116572856903076, "global_step": 460029, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0807487964630127, "global_step": 460030, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0670650005340576, "global_step": 460031, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.070131778717041, "global_step": 460032, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0543646812438965, "global_step": 460033, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.184725284576416, "global_step": 460034, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.11285400390625, "global_step": 460035, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9927927255630493, "global_step": 460036, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9966704845428467, "global_step": 460037, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.053471326828003, "global_step": 460038, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.081932544708252, "global_step": 460039, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.05614972114563, "global_step": 460040, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.023376941680908, "global_step": 460041, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.10502552986145, "global_step": 460042, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.970776915550232, "global_step": 460043, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1120142936706543, "global_step": 460044, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0488009452819824, "global_step": 460045, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0696945190429688, "global_step": 460046, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9973061084747314, "global_step": 460047, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0852770805358887, "global_step": 460048, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9929074048995972, "global_step": 460049, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0196352005004883, "global_step": 460050, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1125051975250244, "global_step": 460051, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0699427127838135, "global_step": 460052, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0339083671569824, "global_step": 460053, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.030975103378296, "global_step": 460054, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.139561176300049, "global_step": 460055, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0646631717681885, "global_step": 460056, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.11388897895813, "global_step": 460057, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1226894855499268, "global_step": 460058, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0647919178009033, "global_step": 460059, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0704472064971924, "global_step": 460060, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1200218200683594, "global_step": 460061, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.062100648880005, "global_step": 460062, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0775296688079834, "global_step": 460063, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1580684185028076, "global_step": 460064, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.079573392868042, "global_step": 460065, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0373899936676025, "global_step": 460066, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.080836534500122, "global_step": 460067, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.137286424636841, "global_step": 460068, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.05489444732666, "global_step": 460069, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.074333667755127, "global_step": 460070, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9945039749145508, "global_step": 460071, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1217217445373535, "global_step": 460072, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.067060708999634, "global_step": 460073, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0500776767730713, "global_step": 460074, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.144235134124756, "global_step": 460075, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0909645557403564, "global_step": 460076, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.120668888092041, "global_step": 460077, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0670228004455566, "global_step": 460078, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0914933681488037, "global_step": 460079, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.033957004547119, "global_step": 460080, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0041298866271973, "global_step": 460081, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1216611862182617, "global_step": 460082, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1138436794281006, "global_step": 460083, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0420591831207275, "global_step": 460084, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9965780973434448, "global_step": 460085, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0770297050476074, "global_step": 460086, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.065422773361206, "global_step": 460087, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9926953315734863, "global_step": 460088, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1205170154571533, "global_step": 460089, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9462599754333496, "global_step": 460090, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0490224361419678, "global_step": 460091, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.048137903213501, "global_step": 460092, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0620360374450684, "global_step": 460093, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.99769127368927, "global_step": 460094, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.157480001449585, "global_step": 460095, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0445492267608643, "global_step": 460096, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0841076374053955, "global_step": 460097, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.071864128112793, "global_step": 460098, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.120551109313965, "global_step": 460099, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.999979019165039, "global_step": 460100, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0724434852600098, "global_step": 460101, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.044351577758789, "global_step": 460102, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0497944355010986, "global_step": 460103, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1713497638702393, "global_step": 460104, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0438852310180664, "global_step": 460105, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0384645462036133, "global_step": 460106, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.056797742843628, "global_step": 460107, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0849344730377197, "global_step": 460108, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0876240730285645, "global_step": 460109, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.118988037109375, "global_step": 460110, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0388526916503906, "global_step": 460111, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.028583526611328, "global_step": 460112, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.052725076675415, "global_step": 460113, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.08728289604187, "global_step": 460114, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.034905195236206, "global_step": 460115, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0034940242767334, "global_step": 460116, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1579113006591797, "global_step": 460117, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0473861694335938, "global_step": 460118, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.027482032775879, "global_step": 460119, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.10907244682312, "global_step": 460120, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1481447219848633, "global_step": 460121, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0742783546447754, "global_step": 460122, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1019930839538574, "global_step": 460123, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1334099769592285, "global_step": 460124, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.021172523498535, "global_step": 460125, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.146683931350708, "global_step": 460126, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1194305419921875, "global_step": 460127, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0470035076141357, "global_step": 460128, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0402770042419434, "global_step": 460129, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0969419479370117, "global_step": 460130, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0839483737945557, "global_step": 460131, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0992963314056396, "global_step": 460132, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1590399742126465, "global_step": 460133, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9827007055282593, "global_step": 460134, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1597909927368164, "global_step": 460135, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.135241985321045, "global_step": 460136, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1531529426574707, "global_step": 460137, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0757291316986084, "global_step": 460138, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0338895320892334, "global_step": 460139, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.146451711654663, "global_step": 460140, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.118959426879883, "global_step": 460141, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0950639247894287, "global_step": 460142, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1254513263702393, "global_step": 460143, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.14214825630188, "global_step": 460144, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1086742877960205, "global_step": 460145, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.000404119491577, "global_step": 460146, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.121445894241333, "global_step": 460147, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.068854808807373, "global_step": 460148, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.030850410461426, "global_step": 460149, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.063951015472412, "global_step": 460150, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0464541912078857, "global_step": 460151, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1939780712127686, "global_step": 460152, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1090288162231445, "global_step": 460153, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0690906047821045, "global_step": 460154, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0582776069641113, "global_step": 460155, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.091639518737793, "global_step": 460156, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1246566772460938, "global_step": 460157, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0480711460113525, "global_step": 460158, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.038588523864746, "global_step": 460159, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.097679853439331, "global_step": 460160, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.089473247528076, "global_step": 460161, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.038395404815674, "global_step": 460162, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0325887203216553, "global_step": 460163, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.148029088973999, "global_step": 460164, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0889434814453125, "global_step": 460165, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.04024600982666, "global_step": 460166, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.057692527770996, "global_step": 460167, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0326569080352783, "global_step": 460168, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0749497413635254, "global_step": 460169, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1695914268493652, "global_step": 460170, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0776877403259277, "global_step": 460171, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.064302682876587, "global_step": 460172, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1109888553619385, "global_step": 460173, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0895912647247314, "global_step": 460174, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.067143440246582, "global_step": 460175, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0500144958496094, "global_step": 460176, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.095794439315796, "global_step": 460177, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0804572105407715, "global_step": 460178, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0675554275512695, "global_step": 460179, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.04990816116333, "global_step": 460180, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0747530460357666, "global_step": 460181, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.950907826423645, "global_step": 460182, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.087200164794922, "global_step": 460183, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.029741048812866, "global_step": 460184, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1301660537719727, "global_step": 460185, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9824540615081787, "global_step": 460186, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.027343988418579, "global_step": 460187, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0560367107391357, "global_step": 460188, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1314077377319336, "global_step": 460189, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0864081382751465, "global_step": 460190, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0591585636138916, "global_step": 460191, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1055192947387695, "global_step": 460192, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1108639240264893, "global_step": 460193, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0108234882354736, "global_step": 460194, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.056145668029785, "global_step": 460195, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.05796480178833, "global_step": 460196, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.070572853088379, "global_step": 460197, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0649890899658203, "global_step": 460198, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.092048168182373, "global_step": 460199, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0430586338043213, "global_step": 460200, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.095928430557251, "global_step": 460201, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.172974109649658, "global_step": 460202, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0366668701171875, "global_step": 460203, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.052760124206543, "global_step": 460204, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.03886342048645, "global_step": 460205, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0822150707244873, "global_step": 460206, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.001570463180542, "global_step": 460207, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0619566440582275, "global_step": 460208, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0308995246887207, "global_step": 460209, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1256659030914307, "global_step": 460210, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0613250732421875, "global_step": 460211, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0652449131011963, "global_step": 460212, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1153693199157715, "global_step": 460213, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.067345142364502, "global_step": 460214, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0971789360046387, "global_step": 460215, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0271520614624023, "global_step": 460216, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1037559509277344, "global_step": 460217, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1182610988616943, "global_step": 460218, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.026113748550415, "global_step": 460219, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0727081298828125, "global_step": 460220, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.2330679893493652, "global_step": 460221, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.15917706489563, "global_step": 460222, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.096665382385254, "global_step": 460223, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0513827800750732, "global_step": 460224, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.109851360321045, "global_step": 460225, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.022099733352661, "global_step": 460226, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1745071411132812, "global_step": 460227, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9991282224655151, "global_step": 460228, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.046785831451416, "global_step": 460229, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9876718521118164, "global_step": 460230, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1081247329711914, "global_step": 460231, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0455353260040283, "global_step": 460232, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1204400062561035, "global_step": 460233, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.042611598968506, "global_step": 460234, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.111124038696289, "global_step": 460235, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.168057680130005, "global_step": 460236, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0868074893951416, "global_step": 460237, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0869274139404297, "global_step": 460238, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0565028190612793, "global_step": 460239, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0086007118225098, "global_step": 460240, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1575136184692383, "global_step": 460241, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1299383640289307, "global_step": 460242, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9954732656478882, "global_step": 460243, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9895399808883667, "global_step": 460244, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.039360523223877, "global_step": 460245, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.147275447845459, "global_step": 460246, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0322232246398926, "global_step": 460247, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1512300968170166, "global_step": 460248, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0868375301361084, "global_step": 460249, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.044043779373169, "global_step": 460250, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0753350257873535, "global_step": 460251, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0819990634918213, "global_step": 460252, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0987181663513184, "global_step": 460253, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0239381790161133, "global_step": 460254, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.143932819366455, "global_step": 460255, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0856125354766846, "global_step": 460256, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0820488929748535, "global_step": 460257, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.07999849319458, "global_step": 460258, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0300588607788086, "global_step": 460259, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0958850383758545, "global_step": 460260, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.989857792854309, "global_step": 460261, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.030531167984009, "global_step": 460262, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0992348194122314, "global_step": 460263, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9633045196533203, "global_step": 460264, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0035459995269775, "global_step": 460265, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.043180227279663, "global_step": 460266, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0553457736968994, "global_step": 460267, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0213687419891357, "global_step": 460268, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1407828330993652, "global_step": 460269, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.111212968826294, "global_step": 460270, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.041142702102661, "global_step": 460271, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0694518089294434, "global_step": 460272, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0452728271484375, "global_step": 460273, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.035384178161621, "global_step": 460274, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0859668254852295, "global_step": 460275, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1128551959991455, "global_step": 460276, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0763912200927734, "global_step": 460277, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0535547733306885, "global_step": 460278, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1358325481414795, "global_step": 460279, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.005201816558838, "global_step": 460280, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.074345111846924, "global_step": 460281, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0020411014556885, "global_step": 460282, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1202497482299805, "global_step": 460283, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.14374041557312, "global_step": 460284, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.081388473510742, "global_step": 460285, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0182197093963623, "global_step": 460286, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1072072982788086, "global_step": 460287, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.10827898979187, "global_step": 460288, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1049792766571045, "global_step": 460289, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1333024501800537, "global_step": 460290, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1191020011901855, "global_step": 460291, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.040215015411377, "global_step": 460292, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.081937313079834, "global_step": 460293, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.130138397216797, "global_step": 460294, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0732903480529785, "global_step": 460295, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.023571491241455, "global_step": 460296, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.111337661743164, "global_step": 460297, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1182446479797363, "global_step": 460298, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.12483286857605, "global_step": 460299, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0696640014648438, "global_step": 460300, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.101877450942993, "global_step": 460301, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.04683518409729, "global_step": 460302, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0320653915405273, "global_step": 460303, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9958040714263916, "global_step": 460304, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0725324153900146, "global_step": 460305, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.107480049133301, "global_step": 460306, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0840396881103516, "global_step": 460307, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1341326236724854, "global_step": 460308, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0602502822875977, "global_step": 460309, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1191177368164062, "global_step": 460310, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0232574939727783, "global_step": 460311, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0036022663116455, "global_step": 460312, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0101401805877686, "global_step": 460313, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1181490421295166, "global_step": 460314, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0665411949157715, "global_step": 460315, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0746688842773438, "global_step": 460316, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.070065975189209, "global_step": 460317, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.2040512561798096, "global_step": 460318, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9958759546279907, "global_step": 460319, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.10506010055542, "global_step": 460320, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0611751079559326, "global_step": 460321, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.065093994140625, "global_step": 460322, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.017807960510254, "global_step": 460323, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.139042615890503, "global_step": 460324, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.123274564743042, "global_step": 460325, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9835453033447266, "global_step": 460326, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.051156520843506, "global_step": 460327, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.075834274291992, "global_step": 460328, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.040151357650757, "global_step": 460329, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.039984941482544, "global_step": 460330, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0895378589630127, "global_step": 460331, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.06347918510437, "global_step": 460332, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.080111503601074, "global_step": 460333, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0227668285369873, "global_step": 460334, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1350479125976562, "global_step": 460335, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.103714942932129, "global_step": 460336, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0962045192718506, "global_step": 460337, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1389989852905273, "global_step": 460338, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1203086376190186, "global_step": 460339, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.107001543045044, "global_step": 460340, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0604960918426514, "global_step": 460341, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.105240821838379, "global_step": 460342, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.129350423812866, "global_step": 460343, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9924923181533813, "global_step": 460344, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.120448589324951, "global_step": 460345, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0316579341888428, "global_step": 460346, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.068892002105713, "global_step": 460347, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.084972858428955, "global_step": 460348, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0421454906463623, "global_step": 460349, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.081653118133545, "global_step": 460350, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1083457469940186, "global_step": 460351, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.010423183441162, "global_step": 460352, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0937118530273438, "global_step": 460353, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0172948837280273, "global_step": 460354, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1579365730285645, "global_step": 460355, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.075997829437256, "global_step": 460356, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0754404067993164, "global_step": 460357, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0842955112457275, "global_step": 460358, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1039767265319824, "global_step": 460359, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1108129024505615, "global_step": 460360, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0446479320526123, "global_step": 460361, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.015956401824951, "global_step": 460362, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0604968070983887, "global_step": 460363, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0309829711914062, "global_step": 460364, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0791351795196533, "global_step": 460365, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0923423767089844, "global_step": 460366, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0612876415252686, "global_step": 460367, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.140422821044922, "global_step": 460368, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0198652744293213, "global_step": 460369, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9203264713287354, "global_step": 460370, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.034027099609375, "global_step": 460371, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0768861770629883, "global_step": 460372, "epoch": 824, "lr": 5e-05}
{"train_loss": 1.9617516994476318, "global_step": 460373, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0563724040985107, "global_step": 460374, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1027159690856934, "global_step": 460375, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.022038459777832, "global_step": 460376, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.135298490524292, "global_step": 460377, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1131834983825684, "global_step": 460378, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.003037214279175, "global_step": 460379, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.033339738845825, "global_step": 460380, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.045650005340576, "global_step": 460381, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0919816493988037, "global_step": 460382, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.08493971824646, "global_step": 460383, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.137403726577759, "global_step": 460384, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0897176265716553, "global_step": 460385, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0475716590881348, "global_step": 460386, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.04978609085083, "global_step": 460387, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.035116672515869, "global_step": 460388, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1237919330596924, "global_step": 460389, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0636370182037354, "global_step": 460390, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1817641258239746, "global_step": 460391, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0688533782958984, "global_step": 460392, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0186169147491455, "global_step": 460393, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0948596000671387, "global_step": 460394, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.148172616958618, "global_step": 460395, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0045816898345947, "global_step": 460396, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0452444553375244, "global_step": 460397, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.2008790969848633, "global_step": 460398, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.1234934329986572, "global_step": 460399, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0768656730651855, "global_step": 460400, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0305869579315186, "global_step": 460401, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.04740309715271, "global_step": 460402, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.162740468978882, "global_step": 460403, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0340096950531006, "global_step": 460404, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.152928590774536, "global_step": 460405, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0849547386169434, "global_step": 460406, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0683069229125977, "global_step": 460407, "epoch": 824, "lr": 5e-05}
{"train_loss": 2.0338852405548096, "global_step": 460408, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.073002815246582, "global_step": 460409, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9720122814178467, "global_step": 460410, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.074465751647949, "global_step": 460411, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0941338539123535, "global_step": 460412, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9942090511322021, "global_step": 460413, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0222208499908447, "global_step": 460414, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0508742332458496, "global_step": 460415, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0641512870788574, "global_step": 460416, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.12809419631958, "global_step": 460417, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.989350438117981, "global_step": 460418, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.051502227783203, "global_step": 460419, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0670106410980225, "global_step": 460420, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.976770281791687, "global_step": 460421, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0642786026000977, "global_step": 460422, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0066781044006348, "global_step": 460423, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0838239192962646, "global_step": 460424, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.005242109298706, "global_step": 460425, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.027749538421631, "global_step": 460426, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0996837615966797, "global_step": 460427, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.112480878829956, "global_step": 460428, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.070158004760742, "global_step": 460429, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.044349431991577, "global_step": 460430, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1539602279663086, "global_step": 460431, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0109200477600098, "global_step": 460432, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0456748008728027, "global_step": 460433, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1070666313171387, "global_step": 460434, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0385167598724365, "global_step": 460435, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0643908977508545, "global_step": 460436, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0040323734283447, "global_step": 460437, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.029325485229492, "global_step": 460438, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9969933032989502, "global_step": 460439, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.10225248336792, "global_step": 460440, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0623936653137207, "global_step": 460441, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0312819480895996, "global_step": 460442, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0000877380371094, "global_step": 460443, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.991165280342102, "global_step": 460444, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0992138385772705, "global_step": 460445, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.09546160697937, "global_step": 460446, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1106693744659424, "global_step": 460447, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1568732261657715, "global_step": 460448, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0703818798065186, "global_step": 460449, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0211923122406006, "global_step": 460450, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.069453716278076, "global_step": 460451, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.086766242980957, "global_step": 460452, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.997226357460022, "global_step": 460453, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.10843563079834, "global_step": 460454, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.995544672012329, "global_step": 460455, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0762858390808105, "global_step": 460456, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.058664083480835, "global_step": 460457, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0712876319885254, "global_step": 460458, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.096287965774536, "global_step": 460459, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0095841884613037, "global_step": 460460, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.03010630607605, "global_step": 460461, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0936357975006104, "global_step": 460462, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9961692094802856, "global_step": 460463, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1170127391815186, "global_step": 460464, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.04246187210083, "global_step": 460465, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.062793493270874, "global_step": 460466, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.025385618209839, "global_step": 460467, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.044218063354492, "global_step": 460468, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0448200702667236, "global_step": 460469, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0680084228515625, "global_step": 460470, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.064070701599121, "global_step": 460471, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.109250545501709, "global_step": 460472, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0690019130706787, "global_step": 460473, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0243473052978516, "global_step": 460474, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0649020671844482, "global_step": 460475, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.949735164642334, "global_step": 460476, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0150725841522217, "global_step": 460477, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1104929447174072, "global_step": 460478, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0727598667144775, "global_step": 460479, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0651824474334717, "global_step": 460480, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.13309907913208, "global_step": 460481, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1165664196014404, "global_step": 460482, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.090179920196533, "global_step": 460483, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0735790729522705, "global_step": 460484, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.996384859085083, "global_step": 460485, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0460805892944336, "global_step": 460486, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.014139175415039, "global_step": 460487, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0457847118377686, "global_step": 460488, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9923560619354248, "global_step": 460489, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0555834770202637, "global_step": 460490, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.13303279876709, "global_step": 460491, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0237607955932617, "global_step": 460492, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0559098720550537, "global_step": 460493, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.120060682296753, "global_step": 460494, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.046595573425293, "global_step": 460495, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1204981803894043, "global_step": 460496, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.079622268676758, "global_step": 460497, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.079547643661499, "global_step": 460498, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0559308528900146, "global_step": 460499, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.051668882369995, "global_step": 460500, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9651210308074951, "global_step": 460501, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1581640243530273, "global_step": 460502, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0764260292053223, "global_step": 460503, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0360610485076904, "global_step": 460504, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.060584306716919, "global_step": 460505, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.042975664138794, "global_step": 460506, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0076138973236084, "global_step": 460507, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0137524604797363, "global_step": 460508, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0321879386901855, "global_step": 460509, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0669260025024414, "global_step": 460510, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0258545875549316, "global_step": 460511, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.056274652481079, "global_step": 460512, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0663046836853027, "global_step": 460513, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0855612754821777, "global_step": 460514, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0407705307006836, "global_step": 460515, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0581862926483154, "global_step": 460516, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.024912118911743, "global_step": 460517, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.104196310043335, "global_step": 460518, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.076507806777954, "global_step": 460519, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0941410064697266, "global_step": 460520, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.025266170501709, "global_step": 460521, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0970187187194824, "global_step": 460522, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0802128314971924, "global_step": 460523, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.06830096244812, "global_step": 460524, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0708422660827637, "global_step": 460525, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.029062509536743, "global_step": 460526, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9868814945220947, "global_step": 460527, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.074998378753662, "global_step": 460528, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9956893920898438, "global_step": 460529, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.020695686340332, "global_step": 460530, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.076416492462158, "global_step": 460531, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.064878463745117, "global_step": 460532, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.115044593811035, "global_step": 460533, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1029305458068848, "global_step": 460534, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.997653603553772, "global_step": 460535, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0868723392486572, "global_step": 460536, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0165843963623047, "global_step": 460537, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0613629817962646, "global_step": 460538, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.00357985496521, "global_step": 460539, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0499472618103027, "global_step": 460540, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.009505271911621, "global_step": 460541, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1125800609588623, "global_step": 460542, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.141718626022339, "global_step": 460543, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0685739517211914, "global_step": 460544, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.079102039337158, "global_step": 460545, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0322091579437256, "global_step": 460546, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.045860528945923, "global_step": 460547, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.971757173538208, "global_step": 460548, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.046950578689575, "global_step": 460549, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.017457962036133, "global_step": 460550, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1446962356567383, "global_step": 460551, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0526552200317383, "global_step": 460552, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.974131464958191, "global_step": 460553, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0855681896209717, "global_step": 460554, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0737788677215576, "global_step": 460555, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.066389322280884, "global_step": 460556, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0754892826080322, "global_step": 460557, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0312869548797607, "global_step": 460558, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.063335418701172, "global_step": 460559, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0431418418884277, "global_step": 460560, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.01938796043396, "global_step": 460561, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.095090627670288, "global_step": 460562, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1211798191070557, "global_step": 460563, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0382652282714844, "global_step": 460564, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1059184074401855, "global_step": 460565, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.061213493347168, "global_step": 460566, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0635929107666016, "global_step": 460567, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0931203365325928, "global_step": 460568, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.979649543762207, "global_step": 460569, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.034851551055908, "global_step": 460570, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0936057567596436, "global_step": 460571, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.05745792388916, "global_step": 460572, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.059833288192749, "global_step": 460573, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9737966060638428, "global_step": 460574, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0353403091430664, "global_step": 460575, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0444936752319336, "global_step": 460576, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0258867740631104, "global_step": 460577, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.091538667678833, "global_step": 460578, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1181414127349854, "global_step": 460579, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.017362594604492, "global_step": 460580, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0874991416931152, "global_step": 460581, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.064871072769165, "global_step": 460582, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9724514484405518, "global_step": 460583, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.974815011024475, "global_step": 460584, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0180444717407227, "global_step": 460585, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0450756549835205, "global_step": 460586, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.139939546585083, "global_step": 460587, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1597068309783936, "global_step": 460588, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1374804973602295, "global_step": 460589, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0880300998687744, "global_step": 460590, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0267255306243896, "global_step": 460591, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1056103706359863, "global_step": 460592, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.119550943374634, "global_step": 460593, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9849517345428467, "global_step": 460594, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.002891778945923, "global_step": 460595, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.091610908508301, "global_step": 460596, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.060969114303589, "global_step": 460597, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0310983657836914, "global_step": 460598, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9888255596160889, "global_step": 460599, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9781303405761719, "global_step": 460600, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9796676635742188, "global_step": 460601, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.221980571746826, "global_step": 460602, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0042564868927, "global_step": 460603, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0510382652282715, "global_step": 460604, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9956607818603516, "global_step": 460605, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1554770469665527, "global_step": 460606, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0328783988952637, "global_step": 460607, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0531973838806152, "global_step": 460608, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.131531238555908, "global_step": 460609, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.048964023590088, "global_step": 460610, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0968000888824463, "global_step": 460611, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0640017986297607, "global_step": 460612, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.2361433506011963, "global_step": 460613, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.057438611984253, "global_step": 460614, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0236215591430664, "global_step": 460615, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1571853160858154, "global_step": 460616, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.085596799850464, "global_step": 460617, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0475988388061523, "global_step": 460618, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.043598175048828, "global_step": 460619, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.060964822769165, "global_step": 460620, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9921566247940063, "global_step": 460621, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.096346855163574, "global_step": 460622, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0047659873962402, "global_step": 460623, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0171196460723877, "global_step": 460624, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1462411880493164, "global_step": 460625, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0874409675598145, "global_step": 460626, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.025283098220825, "global_step": 460627, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0897109508514404, "global_step": 460628, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0633962154388428, "global_step": 460629, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.047010898590088, "global_step": 460630, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1077353954315186, "global_step": 460631, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0110342502593994, "global_step": 460632, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.104121208190918, "global_step": 460633, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0841751098632812, "global_step": 460634, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.091620922088623, "global_step": 460635, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.139190435409546, "global_step": 460636, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0406928062438965, "global_step": 460637, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0416741371154785, "global_step": 460638, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1556386947631836, "global_step": 460639, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.066882848739624, "global_step": 460640, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.053694248199463, "global_step": 460641, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.081589698791504, "global_step": 460642, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.051124334335327, "global_step": 460643, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9893118143081665, "global_step": 460644, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0960843563079834, "global_step": 460645, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9948755502700806, "global_step": 460646, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.118746042251587, "global_step": 460647, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.112128496170044, "global_step": 460648, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0867342948913574, "global_step": 460649, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0739729404449463, "global_step": 460650, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0528604984283447, "global_step": 460651, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0688846111297607, "global_step": 460652, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.005504608154297, "global_step": 460653, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.124401569366455, "global_step": 460654, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0474047660827637, "global_step": 460655, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0520622730255127, "global_step": 460656, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.11657452583313, "global_step": 460657, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.107128381729126, "global_step": 460658, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0946338176727295, "global_step": 460659, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.098304033279419, "global_step": 460660, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.074178457260132, "global_step": 460661, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.164641857147217, "global_step": 460662, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0007894039154053, "global_step": 460663, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.082576274871826, "global_step": 460664, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9920856952667236, "global_step": 460665, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0842392444610596, "global_step": 460666, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0909578800201416, "global_step": 460667, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9668645858764648, "global_step": 460668, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1153576374053955, "global_step": 460669, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0750367641448975, "global_step": 460670, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.003721237182617, "global_step": 460671, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0773730278015137, "global_step": 460672, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0087661743164062, "global_step": 460673, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0818421840667725, "global_step": 460674, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1000936031341553, "global_step": 460675, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0462985038757324, "global_step": 460676, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.137695074081421, "global_step": 460677, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.016453504562378, "global_step": 460678, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0868992805480957, "global_step": 460679, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0913641452789307, "global_step": 460680, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.070539951324463, "global_step": 460681, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1429624557495117, "global_step": 460682, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.078855514526367, "global_step": 460683, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.013216257095337, "global_step": 460684, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.140854835510254, "global_step": 460685, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.074524164199829, "global_step": 460686, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0835061073303223, "global_step": 460687, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1216206550598145, "global_step": 460688, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1098666191101074, "global_step": 460689, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1182608604431152, "global_step": 460690, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0752763748168945, "global_step": 460691, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.01688551902771, "global_step": 460692, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0970280170440674, "global_step": 460693, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0069422721862793, "global_step": 460694, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0293145179748535, "global_step": 460695, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1468594074249268, "global_step": 460696, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.074141263961792, "global_step": 460697, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1180408000946045, "global_step": 460698, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.113522529602051, "global_step": 460699, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0004146099090576, "global_step": 460700, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.047569751739502, "global_step": 460701, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0585248470306396, "global_step": 460702, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1081125736236572, "global_step": 460703, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.063858985900879, "global_step": 460704, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0079314708709717, "global_step": 460705, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.062309503555298, "global_step": 460706, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1844804286956787, "global_step": 460707, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0463650226593018, "global_step": 460708, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.045320510864258, "global_step": 460709, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.045912742614746, "global_step": 460710, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.006939172744751, "global_step": 460711, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1161997318267822, "global_step": 460712, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.098780870437622, "global_step": 460713, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1370933055877686, "global_step": 460714, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0096054077148438, "global_step": 460715, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.086519241333008, "global_step": 460716, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0593950748443604, "global_step": 460717, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9891003370285034, "global_step": 460718, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1700098514556885, "global_step": 460719, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0705416202545166, "global_step": 460720, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0482966899871826, "global_step": 460721, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0558454990386963, "global_step": 460722, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.050185203552246, "global_step": 460723, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.109637498855591, "global_step": 460724, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.086482048034668, "global_step": 460725, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0694801807403564, "global_step": 460726, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.027881145477295, "global_step": 460727, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1562297344207764, "global_step": 460728, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.07013201713562, "global_step": 460729, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.099303960800171, "global_step": 460730, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.040884494781494, "global_step": 460731, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1033716201782227, "global_step": 460732, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1116626262664795, "global_step": 460733, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1118502616882324, "global_step": 460734, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.046523094177246, "global_step": 460735, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0149660110473633, "global_step": 460736, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1162428855895996, "global_step": 460737, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0883662700653076, "global_step": 460738, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.109462261199951, "global_step": 460739, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.085029363632202, "global_step": 460740, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.100069999694824, "global_step": 460741, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.077505588531494, "global_step": 460742, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0293960571289062, "global_step": 460743, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1369917392730713, "global_step": 460744, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0233571529388428, "global_step": 460745, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.118154525756836, "global_step": 460746, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1098878383636475, "global_step": 460747, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.077501058578491, "global_step": 460748, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0008983612060547, "global_step": 460749, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0193872451782227, "global_step": 460750, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0527877807617188, "global_step": 460751, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1468470096588135, "global_step": 460752, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0962753295898438, "global_step": 460753, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1110315322875977, "global_step": 460754, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.060410499572754, "global_step": 460755, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.039341449737549, "global_step": 460756, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0472824573516846, "global_step": 460757, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0626678466796875, "global_step": 460758, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.972751498222351, "global_step": 460759, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.016150951385498, "global_step": 460760, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.123783588409424, "global_step": 460761, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.108004093170166, "global_step": 460762, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0404536724090576, "global_step": 460763, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.98633873462677, "global_step": 460764, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0358715057373047, "global_step": 460765, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9518532752990723, "global_step": 460766, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9860879182815552, "global_step": 460767, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0930097103118896, "global_step": 460768, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0531580448150635, "global_step": 460769, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1561503410339355, "global_step": 460770, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0958011150360107, "global_step": 460771, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0817887783050537, "global_step": 460772, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.068516731262207, "global_step": 460773, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0133814811706543, "global_step": 460774, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0513482093811035, "global_step": 460775, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.010057210922241, "global_step": 460776, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.057931661605835, "global_step": 460777, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.07670521736145, "global_step": 460778, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1588284969329834, "global_step": 460779, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0423829555511475, "global_step": 460780, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.040623664855957, "global_step": 460781, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0447311401367188, "global_step": 460782, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1234190464019775, "global_step": 460783, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.148566484451294, "global_step": 460784, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.053340196609497, "global_step": 460785, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.080005407333374, "global_step": 460786, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0151901245117188, "global_step": 460787, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.042355537414551, "global_step": 460788, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9972906112670898, "global_step": 460789, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.107178211212158, "global_step": 460790, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1041417121887207, "global_step": 460791, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.090378761291504, "global_step": 460792, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0439693927764893, "global_step": 460793, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.07023024559021, "global_step": 460794, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.071652412414551, "global_step": 460795, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1534368991851807, "global_step": 460796, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0843374729156494, "global_step": 460797, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9660086631774902, "global_step": 460798, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0459680557250977, "global_step": 460799, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0855207443237305, "global_step": 460800, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1322853565216064, "global_step": 460801, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.080787181854248, "global_step": 460802, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0588884353637695, "global_step": 460803, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9876519441604614, "global_step": 460804, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0575451850891113, "global_step": 460805, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.116956949234009, "global_step": 460806, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0535192489624023, "global_step": 460807, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.031555414199829, "global_step": 460808, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0842225551605225, "global_step": 460809, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0377817153930664, "global_step": 460810, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.055429697036743, "global_step": 460811, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.014636516571045, "global_step": 460812, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0856268405914307, "global_step": 460813, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1012909412384033, "global_step": 460814, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.026198387145996, "global_step": 460815, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0166401863098145, "global_step": 460816, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.003282308578491, "global_step": 460817, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.08208966255188, "global_step": 460818, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.103513479232788, "global_step": 460819, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1304354667663574, "global_step": 460820, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1732850074768066, "global_step": 460821, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1091856956481934, "global_step": 460822, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.033090591430664, "global_step": 460823, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0109336376190186, "global_step": 460824, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.056756019592285, "global_step": 460825, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.165987730026245, "global_step": 460826, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0034618377685547, "global_step": 460827, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1228861808776855, "global_step": 460828, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0156149864196777, "global_step": 460829, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.028076410293579, "global_step": 460830, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.095210075378418, "global_step": 460831, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0840799808502197, "global_step": 460832, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0621979236602783, "global_step": 460833, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.095196485519409, "global_step": 460834, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.043390989303589, "global_step": 460835, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0991857051849365, "global_step": 460836, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.028160333633423, "global_step": 460837, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.062990665435791, "global_step": 460838, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0440542697906494, "global_step": 460839, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0458149909973145, "global_step": 460840, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.058218479156494, "global_step": 460841, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.110860586166382, "global_step": 460842, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.085069179534912, "global_step": 460843, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0179386138916016, "global_step": 460844, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1479039192199707, "global_step": 460845, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1421360969543457, "global_step": 460846, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.220201253890991, "global_step": 460847, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1345102787017822, "global_step": 460848, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0634701251983643, "global_step": 460849, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.032226800918579, "global_step": 460850, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.121246576309204, "global_step": 460851, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1495187282562256, "global_step": 460852, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9063806533813477, "global_step": 460853, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9784126281738281, "global_step": 460854, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.197648286819458, "global_step": 460855, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.186788558959961, "global_step": 460856, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.069777250289917, "global_step": 460857, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0294454097747803, "global_step": 460858, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.058396577835083, "global_step": 460859, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1863627433776855, "global_step": 460860, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0934946537017822, "global_step": 460861, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.096444606781006, "global_step": 460862, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1209096908569336, "global_step": 460863, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9689850807189941, "global_step": 460864, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0395584106445312, "global_step": 460865, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.068943977355957, "global_step": 460866, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0403034687042236, "global_step": 460867, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.071085214614868, "global_step": 460868, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.018932342529297, "global_step": 460869, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0578012466430664, "global_step": 460870, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.013563632965088, "global_step": 460871, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.101412057876587, "global_step": 460872, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0236430168151855, "global_step": 460873, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9830503463745117, "global_step": 460874, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0750112533569336, "global_step": 460875, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1381218433380127, "global_step": 460876, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0142946243286133, "global_step": 460877, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9443557262420654, "global_step": 460878, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1348390579223633, "global_step": 460879, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.095935583114624, "global_step": 460880, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.952800989151001, "global_step": 460881, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0803680419921875, "global_step": 460882, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.088547706604004, "global_step": 460883, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9728585481643677, "global_step": 460884, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.040663719177246, "global_step": 460885, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0575153827667236, "global_step": 460886, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.112177610397339, "global_step": 460887, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0613975524902344, "global_step": 460888, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.027031421661377, "global_step": 460889, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.09359073638916, "global_step": 460890, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0589680671691895, "global_step": 460891, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.052161693572998, "global_step": 460892, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1113038063049316, "global_step": 460893, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.087688446044922, "global_step": 460894, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1212503910064697, "global_step": 460895, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0379738807678223, "global_step": 460896, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0814971923828125, "global_step": 460897, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.102665901184082, "global_step": 460898, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.033991813659668, "global_step": 460899, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0956506729125977, "global_step": 460900, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.097989559173584, "global_step": 460901, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.11012864112854, "global_step": 460902, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9793918132781982, "global_step": 460903, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1371424198150635, "global_step": 460904, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0965733528137207, "global_step": 460905, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0750463008880615, "global_step": 460906, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1585283279418945, "global_step": 460907, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.042689085006714, "global_step": 460908, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0208427906036377, "global_step": 460909, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1443471908569336, "global_step": 460910, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.135615110397339, "global_step": 460911, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0941619873046875, "global_step": 460912, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0624892711639404, "global_step": 460913, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.030428647994995, "global_step": 460914, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.051107168197632, "global_step": 460915, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.053393840789795, "global_step": 460916, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0605952739715576, "global_step": 460917, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1189305782318115, "global_step": 460918, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.030717372894287, "global_step": 460919, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.025977373123169, "global_step": 460920, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0314154624938965, "global_step": 460921, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.032452344894409, "global_step": 460922, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0833005905151367, "global_step": 460923, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.04890513420105, "global_step": 460924, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0526459217071533, "global_step": 460925, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1197822093963623, "global_step": 460926, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0982284545898438, "global_step": 460927, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.023193597793579, "global_step": 460928, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0687036514282227, "global_step": 460929, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.037626028060913, "global_step": 460930, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.039388418197632, "global_step": 460931, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.095383882522583, "global_step": 460932, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1543359756469727, "global_step": 460933, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0389552116394043, "global_step": 460934, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0936636924743652, "global_step": 460935, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.04365611076355, "global_step": 460936, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1239840984344482, "global_step": 460937, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0418694019317627, "global_step": 460938, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.101489543914795, "global_step": 460939, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0440449714660645, "global_step": 460940, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0897133350372314, "global_step": 460941, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1350996494293213, "global_step": 460942, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.05531644821167, "global_step": 460943, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.152630090713501, "global_step": 460944, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0904085636138916, "global_step": 460945, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0748987197875977, "global_step": 460946, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9867753982543945, "global_step": 460947, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9593372344970703, "global_step": 460948, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.190403461456299, "global_step": 460949, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0702576637268066, "global_step": 460950, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9845277070999146, "global_step": 460951, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0892114639282227, "global_step": 460952, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1346874237060547, "global_step": 460953, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.066524028778076, "global_step": 460954, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.034918785095215, "global_step": 460955, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9660656452178955, "global_step": 460956, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.141591787338257, "global_step": 460957, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0543017387390137, "global_step": 460958, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0592637062072754, "global_step": 460959, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.141941547393799, "global_step": 460960, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.170825481414795, "global_step": 460961, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.113494634628296, "global_step": 460962, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0452356338500977, "global_step": 460963, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0656111240386963, "global_step": 460964, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0256848335266113, "global_step": 460965, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0299322605133057, "global_step": 460966, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0958425998687744, "global_step": 460967, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0785017013549805, "global_step": 460968, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.081592321395874, "global_step": 460969, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0522215366363525, "global_step": 460970, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9889665842056274, "global_step": 460971, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.08015513420105, "global_step": 460972, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.095327615737915, "global_step": 460973, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9678739309310913, "global_step": 460974, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0491509437561035, "global_step": 460975, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.125932216644287, "global_step": 460976, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0718276500701904, "global_step": 460977, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0545339584350586, "global_step": 460978, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9947774410247803, "global_step": 460979, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0328750610351562, "global_step": 460980, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.989634394645691, "global_step": 460981, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0411829948425293, "global_step": 460982, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0325307846069336, "global_step": 460983, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.139103412628174, "global_step": 460984, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.97560453414917, "global_step": 460985, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.104569435119629, "global_step": 460986, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.150693655014038, "global_step": 460987, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0239412784576416, "global_step": 460988, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0698602199554443, "global_step": 460989, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0659189224243164, "global_step": 460990, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.058964967727661, "global_step": 460991, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9892299175262451, "global_step": 460992, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.134645462036133, "global_step": 460993, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0671722888946533, "global_step": 460994, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.114156723022461, "global_step": 460995, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.163442850112915, "global_step": 460996, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0369811058044434, "global_step": 460997, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.007538080215454, "global_step": 460998, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.027238368988037, "global_step": 460999, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.03916072845459, "global_step": 461000, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1222879886627197, "global_step": 461001, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.974501132965088, "global_step": 461002, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.005199670791626, "global_step": 461003, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0430476665496826, "global_step": 461004, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.099494457244873, "global_step": 461005, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1120760440826416, "global_step": 461006, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9979380369186401, "global_step": 461007, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.106008768081665, "global_step": 461008, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.032628059387207, "global_step": 461009, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.083737373352051, "global_step": 461010, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.054241895675659, "global_step": 461011, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.016317129135132, "global_step": 461012, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.077504873275757, "global_step": 461013, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.078038454055786, "global_step": 461014, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.064310073852539, "global_step": 461015, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.144108772277832, "global_step": 461016, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.149681329727173, "global_step": 461017, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.175191640853882, "global_step": 461018, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.083266019821167, "global_step": 461019, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9596527814865112, "global_step": 461020, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0628817081451416, "global_step": 461021, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0632543563842773, "global_step": 461022, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.104051351547241, "global_step": 461023, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.057246685028076, "global_step": 461024, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.068143367767334, "global_step": 461025, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.069002866744995, "global_step": 461026, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.098985433578491, "global_step": 461027, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0319983959198, "global_step": 461028, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0802488327026367, "global_step": 461029, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0034806728363037, "global_step": 461030, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.005566358566284, "global_step": 461031, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.14066219329834, "global_step": 461032, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0526444911956787, "global_step": 461033, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.007261276245117, "global_step": 461034, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9973440170288086, "global_step": 461035, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.127115488052368, "global_step": 461036, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9684644937515259, "global_step": 461037, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0933282375335693, "global_step": 461038, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0227279663085938, "global_step": 461039, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.126363515853882, "global_step": 461040, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1057205200195312, "global_step": 461041, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0469329357147217, "global_step": 461042, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0730409622192383, "global_step": 461043, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.057119369506836, "global_step": 461044, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0811917781829834, "global_step": 461045, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.084120512008667, "global_step": 461046, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0691540241241455, "global_step": 461047, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.07344913482666, "global_step": 461048, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9957159757614136, "global_step": 461049, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0961127281188965, "global_step": 461050, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0612545013427734, "global_step": 461051, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0234100818634033, "global_step": 461052, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.008087158203125, "global_step": 461053, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.101294994354248, "global_step": 461054, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.06691575050354, "global_step": 461055, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.120054244995117, "global_step": 461056, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0497331619262695, "global_step": 461057, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0298831462860107, "global_step": 461058, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.003225088119507, "global_step": 461059, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0161478519439697, "global_step": 461060, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0941317081451416, "global_step": 461061, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0266759395599365, "global_step": 461062, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1863174438476562, "global_step": 461063, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.030658721923828, "global_step": 461064, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.060493230819702, "global_step": 461065, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0268476009368896, "global_step": 461066, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0286669731140137, "global_step": 461067, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.168015718460083, "global_step": 461068, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0423102378845215, "global_step": 461069, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1387929916381836, "global_step": 461070, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0834288597106934, "global_step": 461071, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9992951154708862, "global_step": 461072, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0169801712036133, "global_step": 461073, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0885367393493652, "global_step": 461074, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.117664098739624, "global_step": 461075, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9672870635986328, "global_step": 461076, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.976833462715149, "global_step": 461077, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.084874153137207, "global_step": 461078, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0167477130889893, "global_step": 461079, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.048144578933716, "global_step": 461080, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0968446731567383, "global_step": 461081, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1138715744018555, "global_step": 461082, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9875209331512451, "global_step": 461083, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.114457845687866, "global_step": 461084, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1550111770629883, "global_step": 461085, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0202057361602783, "global_step": 461086, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0785868167877197, "global_step": 461087, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1617441177368164, "global_step": 461088, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.104031801223755, "global_step": 461089, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0719187259674072, "global_step": 461090, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9990062713623047, "global_step": 461091, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.072740077972412, "global_step": 461092, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.160179853439331, "global_step": 461093, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.049839735031128, "global_step": 461094, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0465071201324463, "global_step": 461095, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.052351951599121, "global_step": 461096, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0329389572143555, "global_step": 461097, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.075493812561035, "global_step": 461098, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.095266819000244, "global_step": 461099, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0296413898468018, "global_step": 461100, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1133944988250732, "global_step": 461101, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.056527853012085, "global_step": 461102, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.120096445083618, "global_step": 461103, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.127441883087158, "global_step": 461104, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.068237066268921, "global_step": 461105, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1313045024871826, "global_step": 461106, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0811688899993896, "global_step": 461107, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9894821643829346, "global_step": 461108, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9742740392684937, "global_step": 461109, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.120175838470459, "global_step": 461110, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0821967124938965, "global_step": 461111, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.134610414505005, "global_step": 461112, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.134939670562744, "global_step": 461113, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0596656799316406, "global_step": 461114, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0031142234802246, "global_step": 461115, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0252749919891357, "global_step": 461116, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.989760160446167, "global_step": 461117, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.032107353210449, "global_step": 461118, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.022982597351074, "global_step": 461119, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1077077388763428, "global_step": 461120, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0279674530029297, "global_step": 461121, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.093425750732422, "global_step": 461122, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.048978805541992, "global_step": 461123, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.10249662399292, "global_step": 461124, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0453429222106934, "global_step": 461125, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.074028491973877, "global_step": 461126, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.005342483520508, "global_step": 461127, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0284712314605713, "global_step": 461128, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.014521598815918, "global_step": 461129, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.031437397003174, "global_step": 461130, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.039452075958252, "global_step": 461131, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.121053457260132, "global_step": 461132, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1162424087524414, "global_step": 461133, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0966079235076904, "global_step": 461134, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1301121711730957, "global_step": 461135, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.043287754058838, "global_step": 461136, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1025390625, "global_step": 461137, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9791845083236694, "global_step": 461138, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0773019790649414, "global_step": 461139, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.134134531021118, "global_step": 461140, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0377068519592285, "global_step": 461141, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0717458724975586, "global_step": 461142, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0289976596832275, "global_step": 461143, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.073288679122925, "global_step": 461144, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.033759117126465, "global_step": 461145, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1578750610351562, "global_step": 461146, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9910426139831543, "global_step": 461147, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1010560989379883, "global_step": 461148, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.056614875793457, "global_step": 461149, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.977085828781128, "global_step": 461150, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1526594161987305, "global_step": 461151, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0979130268096924, "global_step": 461152, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0582616329193115, "global_step": 461153, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0324888229370117, "global_step": 461154, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9555021524429321, "global_step": 461155, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1361756324768066, "global_step": 461156, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1991424560546875, "global_step": 461157, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0043838024139404, "global_step": 461158, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.033535957336426, "global_step": 461159, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0183632373809814, "global_step": 461160, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.053162097930908, "global_step": 461161, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.081639528274536, "global_step": 461162, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.049564838409424, "global_step": 461163, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0869836807250977, "global_step": 461164, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0513596534729004, "global_step": 461165, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.062751531600952, "global_step": 461166, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1022987365722656, "global_step": 461167, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.111215353012085, "global_step": 461168, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.008216619491577, "global_step": 461169, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.062285900115967, "global_step": 461170, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1197774410247803, "global_step": 461171, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.086397409439087, "global_step": 461172, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.09283447265625, "global_step": 461173, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.067786455154419, "global_step": 461174, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.062734842300415, "global_step": 461175, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9916231632232666, "global_step": 461176, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1121737957000732, "global_step": 461177, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1046619415283203, "global_step": 461178, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0891470909118652, "global_step": 461179, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1195144653320312, "global_step": 461180, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9776781797409058, "global_step": 461181, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1288516521453857, "global_step": 461182, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0891523361206055, "global_step": 461183, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.028294563293457, "global_step": 461184, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0485756397247314, "global_step": 461185, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.016430616378784, "global_step": 461186, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0790722370147705, "global_step": 461187, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0597753524780273, "global_step": 461188, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.094336986541748, "global_step": 461189, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1203505992889404, "global_step": 461190, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0890722274780273, "global_step": 461191, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.121795177459717, "global_step": 461192, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.007512331008911, "global_step": 461193, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0629796981811523, "global_step": 461194, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0544989109039307, "global_step": 461195, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0047993659973145, "global_step": 461196, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0277488231658936, "global_step": 461197, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0923173427581787, "global_step": 461198, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0907907485961914, "global_step": 461199, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0581624507904053, "global_step": 461200, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1067914962768555, "global_step": 461201, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0775840282440186, "global_step": 461202, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1079251766204834, "global_step": 461203, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1629626750946045, "global_step": 461204, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.087503671646118, "global_step": 461205, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.086040496826172, "global_step": 461206, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0126755237579346, "global_step": 461207, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0356438159942627, "global_step": 461208, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1060891151428223, "global_step": 461209, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0644853115081787, "global_step": 461210, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0748722553253174, "global_step": 461211, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1043126583099365, "global_step": 461212, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.005772829055786, "global_step": 461213, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.075104236602783, "global_step": 461214, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.064619302749634, "global_step": 461215, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0745139122009277, "global_step": 461216, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0520081520080566, "global_step": 461217, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.028852939605713, "global_step": 461218, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.047450065612793, "global_step": 461219, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.114816904067993, "global_step": 461220, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.08503794670105, "global_step": 461221, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.02846097946167, "global_step": 461222, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.055706262588501, "global_step": 461223, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0430290699005127, "global_step": 461224, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.160142421722412, "global_step": 461225, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.157834053039551, "global_step": 461226, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.147799015045166, "global_step": 461227, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0540108680725098, "global_step": 461228, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.069133996963501, "global_step": 461229, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0316617488861084, "global_step": 461230, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0108072757720947, "global_step": 461231, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9973511695861816, "global_step": 461232, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1531403064727783, "global_step": 461233, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.087322473526001, "global_step": 461234, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0748305320739746, "global_step": 461235, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.03342866897583, "global_step": 461236, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.01987361907959, "global_step": 461237, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1133322715759277, "global_step": 461238, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0621347427368164, "global_step": 461239, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.091298818588257, "global_step": 461240, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9965453147888184, "global_step": 461241, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0434184074401855, "global_step": 461242, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.142197608947754, "global_step": 461243, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0608694553375244, "global_step": 461244, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0780041217803955, "global_step": 461245, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0049312114715576, "global_step": 461246, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.070728063583374, "global_step": 461247, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0774402618408203, "global_step": 461248, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0439019203186035, "global_step": 461249, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0743424892425537, "global_step": 461250, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.140401840209961, "global_step": 461251, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.032862424850464, "global_step": 461252, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0900025367736816, "global_step": 461253, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0037434101104736, "global_step": 461254, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1195220947265625, "global_step": 461255, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1503865718841553, "global_step": 461256, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.079533815383911, "global_step": 461257, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.074841260910034, "global_step": 461258, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1147823333740234, "global_step": 461259, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.069265365600586, "global_step": 461260, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1303000450134277, "global_step": 461261, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.029024600982666, "global_step": 461262, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.040708065032959, "global_step": 461263, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9766991138458252, "global_step": 461264, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0580966472625732, "global_step": 461265, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1347904205322266, "global_step": 461266, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0113472938537598, "global_step": 461267, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1210598945617676, "global_step": 461268, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0806124210357666, "global_step": 461269, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0688350200653076, "global_step": 461270, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.083728790283203, "global_step": 461271, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0818684101104736, "global_step": 461272, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1327455043792725, "global_step": 461273, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0616042613983154, "global_step": 461274, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.06369686126709, "global_step": 461275, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0818004608154297, "global_step": 461276, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0831103324890137, "global_step": 461277, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0873067378997803, "global_step": 461278, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.097994089126587, "global_step": 461279, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.052598476409912, "global_step": 461280, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.077517509460449, "global_step": 461281, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0230166912078857, "global_step": 461282, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9830210208892822, "global_step": 461283, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.075591564178467, "global_step": 461284, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.059004068374634, "global_step": 461285, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.027233123779297, "global_step": 461286, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.090284824371338, "global_step": 461287, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.150601863861084, "global_step": 461288, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9866127967834473, "global_step": 461289, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0457372665405273, "global_step": 461290, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.100517511367798, "global_step": 461291, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.006502151489258, "global_step": 461292, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.082550048828125, "global_step": 461293, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.054365873336792, "global_step": 461294, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.036745071411133, "global_step": 461295, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0780677795410156, "global_step": 461296, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0174002647399902, "global_step": 461297, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0984671115875244, "global_step": 461298, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.141402244567871, "global_step": 461299, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.212045907974243, "global_step": 461300, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.077461004257202, "global_step": 461301, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.023266553878784, "global_step": 461302, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.088873863220215, "global_step": 461303, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.103687047958374, "global_step": 461304, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.039897918701172, "global_step": 461305, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0156989097595215, "global_step": 461306, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0362796783447266, "global_step": 461307, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1331214904785156, "global_step": 461308, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.012457847595215, "global_step": 461309, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.042680263519287, "global_step": 461310, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1231775283813477, "global_step": 461311, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.073302745819092, "global_step": 461312, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0973169803619385, "global_step": 461313, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1165058612823486, "global_step": 461314, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.067683696746826, "global_step": 461315, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0838050842285156, "global_step": 461316, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.09659481048584, "global_step": 461317, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.992594838142395, "global_step": 461318, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.066087007522583, "global_step": 461319, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.021611213684082, "global_step": 461320, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.97984778881073, "global_step": 461321, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.121882200241089, "global_step": 461322, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.076197385787964, "global_step": 461323, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9560167789459229, "global_step": 461324, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9968197345733643, "global_step": 461325, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.070866107940674, "global_step": 461326, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.072144031524658, "global_step": 461327, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.9716823101043701, "global_step": 461328, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.042086601257324, "global_step": 461329, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0576608180999756, "global_step": 461330, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.065000534057617, "global_step": 461331, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0690202713012695, "global_step": 461332, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.037306547164917, "global_step": 461333, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0483651161193848, "global_step": 461334, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1146323680877686, "global_step": 461335, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.178650379180908, "global_step": 461336, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1374921798706055, "global_step": 461337, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0685911178588867, "global_step": 461338, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.062603712081909, "global_step": 461339, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.106442928314209, "global_step": 461340, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.2706668376922607, "global_step": 461341, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0632033348083496, "global_step": 461342, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.072025775909424, "global_step": 461343, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.10945987701416, "global_step": 461344, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.122347116470337, "global_step": 461345, "epoch": 825, "lr": 5e-05}
{"train_loss": 1.994326114654541, "global_step": 461346, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1290483474731445, "global_step": 461347, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0969014167785645, "global_step": 461348, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1390159130096436, "global_step": 461349, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.05442476272583, "global_step": 461350, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1578142642974854, "global_step": 461351, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0318517684936523, "global_step": 461352, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0797512531280518, "global_step": 461353, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0905396938323975, "global_step": 461354, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.08076548576355, "global_step": 461355, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0894775390625, "global_step": 461356, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.214524507522583, "global_step": 461357, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.021059989929199, "global_step": 461358, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.083030939102173, "global_step": 461359, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.076099157333374, "global_step": 461360, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.1332030296325684, "global_step": 461361, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0777194499969482, "global_step": 461362, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0275321006774902, "global_step": 461363, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0143866539001465, "global_step": 461364, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0684731006622314, "global_step": 461365, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0805327892303467, "global_step": 461366, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.075688600540161, "global_step": 461367, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.110215187072754, "global_step": 461368, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0870096683502197, "global_step": 461369, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0843470096588135, "global_step": 461370, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.137716293334961, "global_step": 461371, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0534098148345947, "global_step": 461372, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0905630588531494, "global_step": 461373, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.0681471824645996, "global_step": 461374, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.128199815750122, "global_step": 461375, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.066946029663086, "global_step": 461376, "epoch": 825, "lr": 5e-05}
{"train_loss": 2.105753183364868, "global_step": 461377, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0976531505584717, "global_step": 461378, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9976037740707397, "global_step": 461379, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0545525550842285, "global_step": 461380, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0230562686920166, "global_step": 461381, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0034353733062744, "global_step": 461382, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.081822156906128, "global_step": 461383, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1031970977783203, "global_step": 461384, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0644302368164062, "global_step": 461385, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.063777208328247, "global_step": 461386, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.067805051803589, "global_step": 461387, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0868771076202393, "global_step": 461388, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0680196285247803, "global_step": 461389, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0713822841644287, "global_step": 461390, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.00058913230896, "global_step": 461391, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.130661725997925, "global_step": 461392, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.087369441986084, "global_step": 461393, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.990265965461731, "global_step": 461394, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.130899667739868, "global_step": 461395, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0802462100982666, "global_step": 461396, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0339841842651367, "global_step": 461397, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0731544494628906, "global_step": 461398, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.127737522125244, "global_step": 461399, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0636653900146484, "global_step": 461400, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0063300132751465, "global_step": 461401, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0366404056549072, "global_step": 461402, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0306718349456787, "global_step": 461403, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.01216197013855, "global_step": 461404, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.033109664916992, "global_step": 461405, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0944724082946777, "global_step": 461406, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.103623628616333, "global_step": 461407, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9683915376663208, "global_step": 461408, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0656609535217285, "global_step": 461409, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0709147453308105, "global_step": 461410, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0801942348480225, "global_step": 461411, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.066532611846924, "global_step": 461412, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0155274868011475, "global_step": 461413, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9672213792800903, "global_step": 461414, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.039923667907715, "global_step": 461415, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0577282905578613, "global_step": 461416, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.95769464969635, "global_step": 461417, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9301618337631226, "global_step": 461418, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0424258708953857, "global_step": 461419, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.04791259765625, "global_step": 461420, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1172120571136475, "global_step": 461421, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0605289936065674, "global_step": 461422, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0836660861968994, "global_step": 461423, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1008920669555664, "global_step": 461424, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.042080879211426, "global_step": 461425, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1071560382843018, "global_step": 461426, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.096578359603882, "global_step": 461427, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.118706464767456, "global_step": 461428, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.030045986175537, "global_step": 461429, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.008505344390869, "global_step": 461430, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9987581968307495, "global_step": 461431, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.037651777267456, "global_step": 461432, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.070155382156372, "global_step": 461433, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.030769109725952, "global_step": 461434, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.097003698348999, "global_step": 461435, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.05545973777771, "global_step": 461436, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.140450954437256, "global_step": 461437, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1131703853607178, "global_step": 461438, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.104564666748047, "global_step": 461439, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.981536626815796, "global_step": 461440, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.093264579772949, "global_step": 461441, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.060837745666504, "global_step": 461442, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.084843397140503, "global_step": 461443, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0879580974578857, "global_step": 461444, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9954875707626343, "global_step": 461445, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.111964464187622, "global_step": 461446, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.106520891189575, "global_step": 461447, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0267601013183594, "global_step": 461448, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0558390617370605, "global_step": 461449, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9844322204589844, "global_step": 461450, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.00327730178833, "global_step": 461451, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.106210947036743, "global_step": 461452, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0474841594696045, "global_step": 461453, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1010470390319824, "global_step": 461454, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1240530014038086, "global_step": 461455, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.024871826171875, "global_step": 461456, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.04866886138916, "global_step": 461457, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0820608139038086, "global_step": 461458, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.034990072250366, "global_step": 461459, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.040249824523926, "global_step": 461460, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.031751871109009, "global_step": 461461, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.06630802154541, "global_step": 461462, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9919812679290771, "global_step": 461463, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.078653335571289, "global_step": 461464, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.126070737838745, "global_step": 461465, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.026548385620117, "global_step": 461466, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.033140182495117, "global_step": 461467, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9820209741592407, "global_step": 461468, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0036847591400146, "global_step": 461469, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.073976516723633, "global_step": 461470, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.038952350616455, "global_step": 461471, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.029507875442505, "global_step": 461472, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.027325391769409, "global_step": 461473, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.044914722442627, "global_step": 461474, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.072587013244629, "global_step": 461475, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.110386610031128, "global_step": 461476, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0749704837799072, "global_step": 461477, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0763096809387207, "global_step": 461478, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.067300319671631, "global_step": 461479, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0018956661224365, "global_step": 461480, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0759220123291016, "global_step": 461481, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0871927738189697, "global_step": 461482, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.993189811706543, "global_step": 461483, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1005687713623047, "global_step": 461484, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0213801860809326, "global_step": 461485, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0029354095458984, "global_step": 461486, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.969602108001709, "global_step": 461487, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0409061908721924, "global_step": 461488, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0578975677490234, "global_step": 461489, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1180920600891113, "global_step": 461490, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.120241641998291, "global_step": 461491, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0690338611602783, "global_step": 461492, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9560943841934204, "global_step": 461493, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9991830587387085, "global_step": 461494, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9863104820251465, "global_step": 461495, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.126889705657959, "global_step": 461496, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1905367374420166, "global_step": 461497, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.041478157043457, "global_step": 461498, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0413732528686523, "global_step": 461499, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.157740354537964, "global_step": 461500, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.072347402572632, "global_step": 461501, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.016470432281494, "global_step": 461502, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.035048246383667, "global_step": 461503, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0091264247894287, "global_step": 461504, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0957796573638916, "global_step": 461505, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.009190320968628, "global_step": 461506, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.021005868911743, "global_step": 461507, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0062098503112793, "global_step": 461508, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0612313747406006, "global_step": 461509, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0168514251708984, "global_step": 461510, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.026559829711914, "global_step": 461511, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1308209896087646, "global_step": 461512, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0080442428588867, "global_step": 461513, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1146862506866455, "global_step": 461514, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9955337047576904, "global_step": 461515, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.018138885498047, "global_step": 461516, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1286165714263916, "global_step": 461517, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0757148265838623, "global_step": 461518, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0616509914398193, "global_step": 461519, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.150482416152954, "global_step": 461520, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.074913501739502, "global_step": 461521, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1614830493927, "global_step": 461522, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.063194990158081, "global_step": 461523, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.03802752494812, "global_step": 461524, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1127867698669434, "global_step": 461525, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.064177989959717, "global_step": 461526, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.057302474975586, "global_step": 461527, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9649641513824463, "global_step": 461528, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1015610694885254, "global_step": 461529, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0592100620269775, "global_step": 461530, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.019075393676758, "global_step": 461531, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9842231273651123, "global_step": 461532, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.061455488204956, "global_step": 461533, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.058107852935791, "global_step": 461534, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.070202112197876, "global_step": 461535, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.077619791030884, "global_step": 461536, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.118039608001709, "global_step": 461537, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.044849157333374, "global_step": 461538, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1058104038238525, "global_step": 461539, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0786633491516113, "global_step": 461540, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0711162090301514, "global_step": 461541, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.104320764541626, "global_step": 461542, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.001852035522461, "global_step": 461543, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9874870777130127, "global_step": 461544, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.050091028213501, "global_step": 461545, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0808424949645996, "global_step": 461546, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0625476837158203, "global_step": 461547, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0857326984405518, "global_step": 461548, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.043743133544922, "global_step": 461549, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.055128812789917, "global_step": 461550, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.060695171356201, "global_step": 461551, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0961387157440186, "global_step": 461552, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0004782676696777, "global_step": 461553, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0413172245025635, "global_step": 461554, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.980278730392456, "global_step": 461555, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9922596216201782, "global_step": 461556, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0515522956848145, "global_step": 461557, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.999556303024292, "global_step": 461558, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.128648519515991, "global_step": 461559, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.062267303466797, "global_step": 461560, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0916669368743896, "global_step": 461561, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0093812942504883, "global_step": 461562, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0669143199920654, "global_step": 461563, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.038116693496704, "global_step": 461564, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.130594253540039, "global_step": 461565, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1009511947631836, "global_step": 461566, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0700368881225586, "global_step": 461567, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.157843589782715, "global_step": 461568, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0574591159820557, "global_step": 461569, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.097728729248047, "global_step": 461570, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.120497941970825, "global_step": 461571, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1174514293670654, "global_step": 461572, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.025773525238037, "global_step": 461573, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1095070838928223, "global_step": 461574, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0680038928985596, "global_step": 461575, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.080101728439331, "global_step": 461576, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0562238693237305, "global_step": 461577, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0505282878875732, "global_step": 461578, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0734143257141113, "global_step": 461579, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0538828372955322, "global_step": 461580, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.013561248779297, "global_step": 461581, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1223747730255127, "global_step": 461582, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.061872720718384, "global_step": 461583, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0772855281829834, "global_step": 461584, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0707991123199463, "global_step": 461585, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.095442533493042, "global_step": 461586, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0807578563690186, "global_step": 461587, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0286896228790283, "global_step": 461588, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.164045810699463, "global_step": 461589, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.111992359161377, "global_step": 461590, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.071432590484619, "global_step": 461591, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0654702186584473, "global_step": 461592, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1699745655059814, "global_step": 461593, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.128574848175049, "global_step": 461594, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.012192964553833, "global_step": 461595, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.054859161376953, "global_step": 461596, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1170718669891357, "global_step": 461597, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.085923671722412, "global_step": 461598, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.128392457962036, "global_step": 461599, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0529539585113525, "global_step": 461600, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.063539981842041, "global_step": 461601, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0784406661987305, "global_step": 461602, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0884323120117188, "global_step": 461603, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1425483226776123, "global_step": 461604, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.121448516845703, "global_step": 461605, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.049391984939575, "global_step": 461606, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.184032678604126, "global_step": 461607, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.144860029220581, "global_step": 461608, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0164756774902344, "global_step": 461609, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.057187795639038, "global_step": 461610, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0764718055725098, "global_step": 461611, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0597167015075684, "global_step": 461612, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0843734741210938, "global_step": 461613, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.14040207862854, "global_step": 461614, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0448648929595947, "global_step": 461615, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.073725461959839, "global_step": 461616, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9861420392990112, "global_step": 461617, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.082005739212036, "global_step": 461618, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1346819400787354, "global_step": 461619, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0404539108276367, "global_step": 461620, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9894911050796509, "global_step": 461621, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0308611392974854, "global_step": 461622, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.083371162414551, "global_step": 461623, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.091329574584961, "global_step": 461624, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0501010417938232, "global_step": 461625, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.2048516273498535, "global_step": 461626, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.036673069000244, "global_step": 461627, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1685612201690674, "global_step": 461628, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0264008045196533, "global_step": 461629, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0529797077178955, "global_step": 461630, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1320247650146484, "global_step": 461631, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.065953254699707, "global_step": 461632, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.06048583984375, "global_step": 461633, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.118068218231201, "global_step": 461634, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0428779125213623, "global_step": 461635, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0529494285583496, "global_step": 461636, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0161936283111572, "global_step": 461637, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.954370379447937, "global_step": 461638, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.092921018600464, "global_step": 461639, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0211598873138428, "global_step": 461640, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.214932441711426, "global_step": 461641, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.03615403175354, "global_step": 461642, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.027588129043579, "global_step": 461643, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0339956283569336, "global_step": 461644, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.079019784927368, "global_step": 461645, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.081799030303955, "global_step": 461646, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0907156467437744, "global_step": 461647, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9795253276824951, "global_step": 461648, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0387542247772217, "global_step": 461649, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.154766798019409, "global_step": 461650, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0520200729370117, "global_step": 461651, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.004315137863159, "global_step": 461652, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.097723960876465, "global_step": 461653, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0955312252044678, "global_step": 461654, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.006096601486206, "global_step": 461655, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.001276731491089, "global_step": 461656, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.064880847930908, "global_step": 461657, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.183049440383911, "global_step": 461658, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0819268226623535, "global_step": 461659, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0785346031188965, "global_step": 461660, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.058591842651367, "global_step": 461661, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0794153213500977, "global_step": 461662, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.031280755996704, "global_step": 461663, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.059058666229248, "global_step": 461664, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.108487606048584, "global_step": 461665, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1211307048797607, "global_step": 461666, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.970431923866272, "global_step": 461667, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1285271644592285, "global_step": 461668, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0977916717529297, "global_step": 461669, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9942421913146973, "global_step": 461670, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0565600395202637, "global_step": 461671, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0727548599243164, "global_step": 461672, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.113302230834961, "global_step": 461673, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0125327110290527, "global_step": 461674, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.106964111328125, "global_step": 461675, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9699786901474, "global_step": 461676, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.054217576980591, "global_step": 461677, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0814456939697266, "global_step": 461678, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1086339950561523, "global_step": 461679, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1266980171203613, "global_step": 461680, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.069193124771118, "global_step": 461681, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.02308988571167, "global_step": 461682, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.032344102859497, "global_step": 461683, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0979278087615967, "global_step": 461684, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1513590812683105, "global_step": 461685, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.101475238800049, "global_step": 461686, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.122899293899536, "global_step": 461687, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.019865036010742, "global_step": 461688, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.119079828262329, "global_step": 461689, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.096510171890259, "global_step": 461690, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0695338249206543, "global_step": 461691, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9435105323791504, "global_step": 461692, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0607059001922607, "global_step": 461693, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9538747072219849, "global_step": 461694, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.077497959136963, "global_step": 461695, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0905911922454834, "global_step": 461696, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.136002540588379, "global_step": 461697, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0472192764282227, "global_step": 461698, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.01056170463562, "global_step": 461699, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.010322093963623, "global_step": 461700, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.077908992767334, "global_step": 461701, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.113731861114502, "global_step": 461702, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.076024293899536, "global_step": 461703, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.016444683074951, "global_step": 461704, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.049405097961426, "global_step": 461705, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.014843225479126, "global_step": 461706, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1573824882507324, "global_step": 461707, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.011101245880127, "global_step": 461708, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9022040367126465, "global_step": 461709, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0107219219207764, "global_step": 461710, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9762873649597168, "global_step": 461711, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.054924964904785, "global_step": 461712, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9979013204574585, "global_step": 461713, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0827829837799072, "global_step": 461714, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.100553512573242, "global_step": 461715, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0536108016967773, "global_step": 461716, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0158891677856445, "global_step": 461717, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9586849212646484, "global_step": 461718, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0936076641082764, "global_step": 461719, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.08701753616333, "global_step": 461720, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0630664825439453, "global_step": 461721, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0756728649139404, "global_step": 461722, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0167927742004395, "global_step": 461723, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0520365238189697, "global_step": 461724, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1302103996276855, "global_step": 461725, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.961124300956726, "global_step": 461726, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.055246353149414, "global_step": 461727, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0689315795898438, "global_step": 461728, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.998711347579956, "global_step": 461729, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.150120735168457, "global_step": 461730, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1624841690063477, "global_step": 461731, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0169551372528076, "global_step": 461732, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1737923622131348, "global_step": 461733, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1144471168518066, "global_step": 461734, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.019012928009033, "global_step": 461735, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0465965270996094, "global_step": 461736, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.2254040241241455, "global_step": 461737, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.105670928955078, "global_step": 461738, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.03666353225708, "global_step": 461739, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.058919668197632, "global_step": 461740, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.00342059135437, "global_step": 461741, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.067495346069336, "global_step": 461742, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.043978452682495, "global_step": 461743, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0669567584991455, "global_step": 461744, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.113985538482666, "global_step": 461745, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1841156482696533, "global_step": 461746, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1760873794555664, "global_step": 461747, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0882699489593506, "global_step": 461748, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.110572099685669, "global_step": 461749, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.040400505065918, "global_step": 461750, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1033763885498047, "global_step": 461751, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0417416095733643, "global_step": 461752, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0251498222351074, "global_step": 461753, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0435962677001953, "global_step": 461754, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0427353382110596, "global_step": 461755, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1600496768951416, "global_step": 461756, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0206286907196045, "global_step": 461757, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.048405170440674, "global_step": 461758, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0027074813842773, "global_step": 461759, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.097852945327759, "global_step": 461760, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0799505710601807, "global_step": 461761, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0749542713165283, "global_step": 461762, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0114738941192627, "global_step": 461763, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.019226551055908, "global_step": 461764, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1234993934631348, "global_step": 461765, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.099472999572754, "global_step": 461766, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.005337953567505, "global_step": 461767, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.120290994644165, "global_step": 461768, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0523276329040527, "global_step": 461769, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1115918159484863, "global_step": 461770, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.048051357269287, "global_step": 461771, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.070499897003174, "global_step": 461772, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.107645273208618, "global_step": 461773, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0233118534088135, "global_step": 461774, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0520782470703125, "global_step": 461775, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.054636240005493, "global_step": 461776, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0973639488220215, "global_step": 461777, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0164129734039307, "global_step": 461778, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.114809513092041, "global_step": 461779, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0417003631591797, "global_step": 461780, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9861704111099243, "global_step": 461781, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0095086097717285, "global_step": 461782, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0096137523651123, "global_step": 461783, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1583895683288574, "global_step": 461784, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.013700485229492, "global_step": 461785, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.043644666671753, "global_step": 461786, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.074406623840332, "global_step": 461787, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0743961334228516, "global_step": 461788, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0716731548309326, "global_step": 461789, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.066497325897217, "global_step": 461790, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1554887294769287, "global_step": 461791, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.089092493057251, "global_step": 461792, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.062474489212036, "global_step": 461793, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.101088523864746, "global_step": 461794, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0296974182128906, "global_step": 461795, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.053119421005249, "global_step": 461796, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0690488815307617, "global_step": 461797, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.148061752319336, "global_step": 461798, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.158374309539795, "global_step": 461799, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0934977531433105, "global_step": 461800, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.032227039337158, "global_step": 461801, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1262941360473633, "global_step": 461802, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.037374258041382, "global_step": 461803, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0264391899108887, "global_step": 461804, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.2165095806121826, "global_step": 461805, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0797574520111084, "global_step": 461806, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1070375442504883, "global_step": 461807, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0745701789855957, "global_step": 461808, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.014293670654297, "global_step": 461809, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.100386142730713, "global_step": 461810, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0953686237335205, "global_step": 461811, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.081880569458008, "global_step": 461812, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0806262493133545, "global_step": 461813, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1753039360046387, "global_step": 461814, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0997021198272705, "global_step": 461815, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0255720615386963, "global_step": 461816, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0519039630889893, "global_step": 461817, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0565197467803955, "global_step": 461818, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.055541515350342, "global_step": 461819, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0882413387298584, "global_step": 461820, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.159597396850586, "global_step": 461821, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9939444065093994, "global_step": 461822, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0533370971679688, "global_step": 461823, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.030100107192993, "global_step": 461824, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0054521560668945, "global_step": 461825, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.077301025390625, "global_step": 461826, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.104372978210449, "global_step": 461827, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.091278553009033, "global_step": 461828, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.125370740890503, "global_step": 461829, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0232956409454346, "global_step": 461830, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0587408542633057, "global_step": 461831, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0723323822021484, "global_step": 461832, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0558767318725586, "global_step": 461833, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0770256519317627, "global_step": 461834, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9462627172470093, "global_step": 461835, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1067092418670654, "global_step": 461836, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9520593881607056, "global_step": 461837, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0899226665496826, "global_step": 461838, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0178580284118652, "global_step": 461839, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.209223747253418, "global_step": 461840, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.082710027694702, "global_step": 461841, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9231460094451904, "global_step": 461842, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.07184100151062, "global_step": 461843, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0925517082214355, "global_step": 461844, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0488967895507812, "global_step": 461845, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.173964023590088, "global_step": 461846, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.028541326522827, "global_step": 461847, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0804238319396973, "global_step": 461848, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.061166763305664, "global_step": 461849, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.109581708908081, "global_step": 461850, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0521080493927, "global_step": 461851, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1214632987976074, "global_step": 461852, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0747790336608887, "global_step": 461853, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0567455291748047, "global_step": 461854, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1005446910858154, "global_step": 461855, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.166152000427246, "global_step": 461856, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0671777725219727, "global_step": 461857, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9598169326782227, "global_step": 461858, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0477991104125977, "global_step": 461859, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.033743143081665, "global_step": 461860, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1526308059692383, "global_step": 461861, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.05489182472229, "global_step": 461862, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0712709426879883, "global_step": 461863, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.958122968673706, "global_step": 461864, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9854663610458374, "global_step": 461865, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.000804901123047, "global_step": 461866, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.013942241668701, "global_step": 461867, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0471885204315186, "global_step": 461868, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0605242252349854, "global_step": 461869, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0328445434570312, "global_step": 461870, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.060304880142212, "global_step": 461871, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.055213689804077, "global_step": 461872, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1175734996795654, "global_step": 461873, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9002283811569214, "global_step": 461874, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1110918521881104, "global_step": 461875, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.136415958404541, "global_step": 461876, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0910587310791016, "global_step": 461877, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9872022867202759, "global_step": 461878, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0894908905029297, "global_step": 461879, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0691628456115723, "global_step": 461880, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.044696807861328, "global_step": 461881, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0252299308776855, "global_step": 461882, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.110426425933838, "global_step": 461883, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1067895889282227, "global_step": 461884, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.008232831954956, "global_step": 461885, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0919854640960693, "global_step": 461886, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.116734504699707, "global_step": 461887, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.059839963912964, "global_step": 461888, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1757357120513916, "global_step": 461889, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.124901294708252, "global_step": 461890, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1010468006134033, "global_step": 461891, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.116630792617798, "global_step": 461892, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1466338634490967, "global_step": 461893, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0314862728118896, "global_step": 461894, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.106572389602661, "global_step": 461895, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.100700855255127, "global_step": 461896, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.065312623977661, "global_step": 461897, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0321366786956787, "global_step": 461898, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9909156560897827, "global_step": 461899, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0139777660369873, "global_step": 461900, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1142024993896484, "global_step": 461901, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.072899103164673, "global_step": 461902, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0830764770507812, "global_step": 461903, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1503617763519287, "global_step": 461904, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0100529193878174, "global_step": 461905, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.112574577331543, "global_step": 461906, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1220290660858154, "global_step": 461907, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9651029109954834, "global_step": 461908, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9937543869018555, "global_step": 461909, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.127685546875, "global_step": 461910, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0862414836883545, "global_step": 461911, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0339739322662354, "global_step": 461912, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0819313526153564, "global_step": 461913, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0704760551452637, "global_step": 461914, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.062213659286499, "global_step": 461915, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0892179012298584, "global_step": 461916, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9899548292160034, "global_step": 461917, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.104020357131958, "global_step": 461918, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0056753158569336, "global_step": 461919, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.118645668029785, "global_step": 461920, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0576353073120117, "global_step": 461921, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.094669818878174, "global_step": 461922, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1211941242218018, "global_step": 461923, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0473952293395996, "global_step": 461924, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0801141262054443, "global_step": 461925, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.041895627975464, "global_step": 461926, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0899817943573, "global_step": 461927, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1419172286987305, "global_step": 461928, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0021331310272217, "global_step": 461929, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0818262100219727, "global_step": 461930, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.054673671722412, "global_step": 461931, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.104142189025879, "global_step": 461932, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0675508975982666, "global_step": 461933, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0909945964813232, "global_step": 461934, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.060964822769165, "global_step": 461935, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0347111225128174, "global_step": 461936, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9823169708251953, "global_step": 461937, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0534889698028564, "global_step": 461938, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.072472333908081, "global_step": 461939, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.025906801223755, "global_step": 461940, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0333824157714844, "global_step": 461941, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.007695198059082, "global_step": 461942, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0847504138946533, "global_step": 461943, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0213494300842285, "global_step": 461944, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1051745414733887, "global_step": 461945, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.097480297088623, "global_step": 461946, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0872318744659424, "global_step": 461947, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1058433055877686, "global_step": 461948, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1148390769958496, "global_step": 461949, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9897465705871582, "global_step": 461950, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.048184871673584, "global_step": 461951, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.059112310409546, "global_step": 461952, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1414196491241455, "global_step": 461953, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9546922445297241, "global_step": 461954, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.024437427520752, "global_step": 461955, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.07173228263855, "global_step": 461956, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1920535564422607, "global_step": 461957, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0164847373962402, "global_step": 461958, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0693368911743164, "global_step": 461959, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0331199169158936, "global_step": 461960, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.972065806388855, "global_step": 461961, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.012554883956909, "global_step": 461962, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0545620918273926, "global_step": 461963, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0529797077178955, "global_step": 461964, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0247061252593994, "global_step": 461965, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1155667304992676, "global_step": 461966, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0650391578674316, "global_step": 461967, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0560052394866943, "global_step": 461968, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0231773853302, "global_step": 461969, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9827022552490234, "global_step": 461970, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.091752290725708, "global_step": 461971, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0700597763061523, "global_step": 461972, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0016160011291504, "global_step": 461973, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.123569965362549, "global_step": 461974, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0040478706359863, "global_step": 461975, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1238205432891846, "global_step": 461976, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.069589138031006, "global_step": 461977, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9927585124969482, "global_step": 461978, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9936758279800415, "global_step": 461979, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.11078143119812, "global_step": 461980, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0286269187927246, "global_step": 461981, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.116346597671509, "global_step": 461982, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.109926223754883, "global_step": 461983, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0665390491485596, "global_step": 461984, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0920472145080566, "global_step": 461985, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0779097080230713, "global_step": 461986, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0235791206359863, "global_step": 461987, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.150777816772461, "global_step": 461988, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.079890251159668, "global_step": 461989, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.105264902114868, "global_step": 461990, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0372061729431152, "global_step": 461991, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.094672203063965, "global_step": 461992, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9977773427963257, "global_step": 461993, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0707342624664307, "global_step": 461994, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.087860584259033, "global_step": 461995, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.063361644744873, "global_step": 461996, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.066758871078491, "global_step": 461997, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.069828510284424, "global_step": 461998, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0715811252593994, "global_step": 461999, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.006493091583252, "global_step": 462000, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0133323669433594, "global_step": 462001, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0687344074249268, "global_step": 462002, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0515520572662354, "global_step": 462003, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0232019424438477, "global_step": 462004, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0556039810180664, "global_step": 462005, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0080978870391846, "global_step": 462006, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.090390920639038, "global_step": 462007, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0835936069488525, "global_step": 462008, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.004164218902588, "global_step": 462009, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.070600986480713, "global_step": 462010, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.050685167312622, "global_step": 462011, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.097452402114868, "global_step": 462012, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1084654331207275, "global_step": 462013, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0597643852233887, "global_step": 462014, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.021416187286377, "global_step": 462015, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.052295207977295, "global_step": 462016, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9933685064315796, "global_step": 462017, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.066943645477295, "global_step": 462018, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.132356643676758, "global_step": 462019, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.054670810699463, "global_step": 462020, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.164844274520874, "global_step": 462021, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0449788570404053, "global_step": 462022, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1386818885803223, "global_step": 462023, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0533249378204346, "global_step": 462024, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0117857456207275, "global_step": 462025, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.073413848876953, "global_step": 462026, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0375986099243164, "global_step": 462027, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0157268047332764, "global_step": 462028, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9975225925445557, "global_step": 462029, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.106865644454956, "global_step": 462030, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1394295692443848, "global_step": 462031, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9820504188537598, "global_step": 462032, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.971150517463684, "global_step": 462033, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.106032371520996, "global_step": 462034, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0704407691955566, "global_step": 462035, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0777740478515625, "global_step": 462036, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0904390811920166, "global_step": 462037, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.007702589035034, "global_step": 462038, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.08415150642395, "global_step": 462039, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.123055934906006, "global_step": 462040, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0260682106018066, "global_step": 462041, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0254087448120117, "global_step": 462042, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.997045636177063, "global_step": 462043, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1108055114746094, "global_step": 462044, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1312689781188965, "global_step": 462045, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0409085750579834, "global_step": 462046, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0816564559936523, "global_step": 462047, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0207104682922363, "global_step": 462048, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1200504302978516, "global_step": 462049, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1095566749572754, "global_step": 462050, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.112720251083374, "global_step": 462051, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0078775882720947, "global_step": 462052, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.043783664703369, "global_step": 462053, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.025895118713379, "global_step": 462054, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1326088905334473, "global_step": 462055, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1220903396606445, "global_step": 462056, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.159940481185913, "global_step": 462057, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0604774951934814, "global_step": 462058, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.013793468475342, "global_step": 462059, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0848350524902344, "global_step": 462060, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1033363342285156, "global_step": 462061, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1144068241119385, "global_step": 462062, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0556905269622803, "global_step": 462063, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.082226276397705, "global_step": 462064, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.008613348007202, "global_step": 462065, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.052649974822998, "global_step": 462066, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.073864698410034, "global_step": 462067, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.966054081916809, "global_step": 462068, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0620200634002686, "global_step": 462069, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9936457872390747, "global_step": 462070, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.096256971359253, "global_step": 462071, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.107802629470825, "global_step": 462072, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1755788326263428, "global_step": 462073, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.022263526916504, "global_step": 462074, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.072218179702759, "global_step": 462075, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.106262445449829, "global_step": 462076, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1319758892059326, "global_step": 462077, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.122366189956665, "global_step": 462078, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9946269989013672, "global_step": 462079, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.163794755935669, "global_step": 462080, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0137441158294678, "global_step": 462081, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.097510814666748, "global_step": 462082, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0895068645477295, "global_step": 462083, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9985827207565308, "global_step": 462084, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0432956218719482, "global_step": 462085, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9860103130340576, "global_step": 462086, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.099501609802246, "global_step": 462087, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0262298583984375, "global_step": 462088, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1140875816345215, "global_step": 462089, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.111926794052124, "global_step": 462090, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0793004035949707, "global_step": 462091, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0247044563293457, "global_step": 462092, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1026628017425537, "global_step": 462093, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.145071506500244, "global_step": 462094, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0220141410827637, "global_step": 462095, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.053065061569214, "global_step": 462096, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0157852172851562, "global_step": 462097, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0097591876983643, "global_step": 462098, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0960516929626465, "global_step": 462099, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0880775451660156, "global_step": 462100, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0899975299835205, "global_step": 462101, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.099492073059082, "global_step": 462102, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9914366006851196, "global_step": 462103, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1358933448791504, "global_step": 462104, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.044417142868042, "global_step": 462105, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.043689250946045, "global_step": 462106, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0597715377807617, "global_step": 462107, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1155617237091064, "global_step": 462108, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0024795532226562, "global_step": 462109, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.032836437225342, "global_step": 462110, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1029651165008545, "global_step": 462111, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.103433132171631, "global_step": 462112, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.092599391937256, "global_step": 462113, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.064037561416626, "global_step": 462114, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.123684883117676, "global_step": 462115, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1109812259674072, "global_step": 462116, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.025404214859009, "global_step": 462117, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.043997287750244, "global_step": 462118, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.044748067855835, "global_step": 462119, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0360610485076904, "global_step": 462120, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0966219902038574, "global_step": 462121, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.157489061355591, "global_step": 462122, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.078002691268921, "global_step": 462123, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.026693344116211, "global_step": 462124, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.034661054611206, "global_step": 462125, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.028848171234131, "global_step": 462126, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0952889919281006, "global_step": 462127, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0288338661193848, "global_step": 462128, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.114570140838623, "global_step": 462129, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0935282707214355, "global_step": 462130, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.133134603500366, "global_step": 462131, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.034127950668335, "global_step": 462132, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1068685054779053, "global_step": 462133, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1430675983428955, "global_step": 462134, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.122743844985962, "global_step": 462135, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1023030281066895, "global_step": 462136, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0921006202697754, "global_step": 462137, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1004319190979004, "global_step": 462138, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.108835220336914, "global_step": 462139, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0864505767822266, "global_step": 462140, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1199452877044678, "global_step": 462141, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.081599473953247, "global_step": 462142, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.100086212158203, "global_step": 462143, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0894699096679688, "global_step": 462144, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1930665969848633, "global_step": 462145, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0921552181243896, "global_step": 462146, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0322892665863037, "global_step": 462147, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.104677677154541, "global_step": 462148, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0200300216674805, "global_step": 462149, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.149146556854248, "global_step": 462150, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0276246070861816, "global_step": 462151, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.069988250732422, "global_step": 462152, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.11940860748291, "global_step": 462153, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0729525089263916, "global_step": 462154, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.020730495452881, "global_step": 462155, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0592381954193115, "global_step": 462156, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1080970764160156, "global_step": 462157, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.051548719406128, "global_step": 462158, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0807716846466064, "global_step": 462159, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1505908966064453, "global_step": 462160, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.022590398788452, "global_step": 462161, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.114584445953369, "global_step": 462162, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.121708869934082, "global_step": 462163, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0055296421051025, "global_step": 462164, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1177053451538086, "global_step": 462165, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.076664686203003, "global_step": 462166, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.081695795059204, "global_step": 462167, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.093698740005493, "global_step": 462168, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0264711380004883, "global_step": 462169, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.994588017463684, "global_step": 462170, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0716240406036377, "global_step": 462171, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.104771852493286, "global_step": 462172, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.055236577987671, "global_step": 462173, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.114319086074829, "global_step": 462174, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.069988250732422, "global_step": 462175, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0656189918518066, "global_step": 462176, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0451560020446777, "global_step": 462177, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.092423439025879, "global_step": 462178, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0356051921844482, "global_step": 462179, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.115124464035034, "global_step": 462180, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1391794681549072, "global_step": 462181, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1669864654541016, "global_step": 462182, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0348031520843506, "global_step": 462183, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0186095237731934, "global_step": 462184, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.094492197036743, "global_step": 462185, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.074441909790039, "global_step": 462186, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1058754920959473, "global_step": 462187, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0440938472747803, "global_step": 462188, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0075628757476807, "global_step": 462189, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.069765090942383, "global_step": 462190, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0890352725982666, "global_step": 462191, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0463976860046387, "global_step": 462192, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.109283447265625, "global_step": 462193, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.055227279663086, "global_step": 462194, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1370561122894287, "global_step": 462195, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.080286979675293, "global_step": 462196, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.109251022338867, "global_step": 462197, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.020564317703247, "global_step": 462198, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.059170722961426, "global_step": 462199, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.044203281402588, "global_step": 462200, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.015646457672119, "global_step": 462201, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0883708000183105, "global_step": 462202, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9798301458358765, "global_step": 462203, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.047935962677002, "global_step": 462204, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0936639308929443, "global_step": 462205, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0530126094818115, "global_step": 462206, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1918270587921143, "global_step": 462207, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.075125217437744, "global_step": 462208, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0579700469970703, "global_step": 462209, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1228737831115723, "global_step": 462210, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0613274574279785, "global_step": 462211, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.124845266342163, "global_step": 462212, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0895755290985107, "global_step": 462213, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1049301624298096, "global_step": 462214, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.018272638320923, "global_step": 462215, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0678062438964844, "global_step": 462216, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9576046466827393, "global_step": 462217, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0621120929718018, "global_step": 462218, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1296792030334473, "global_step": 462219, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0827364921569824, "global_step": 462220, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.038386583328247, "global_step": 462221, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.075685739517212, "global_step": 462222, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9912312030792236, "global_step": 462223, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.088216543197632, "global_step": 462224, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.088660955429077, "global_step": 462225, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.132115602493286, "global_step": 462226, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0524978637695312, "global_step": 462227, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.027989149093628, "global_step": 462228, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.092653751373291, "global_step": 462229, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0379152297973633, "global_step": 462230, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.028444766998291, "global_step": 462231, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0440714359283447, "global_step": 462232, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.117180109024048, "global_step": 462233, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0580811500549316, "global_step": 462234, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0613815784454346, "global_step": 462235, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1418869495391846, "global_step": 462236, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0515401363372803, "global_step": 462237, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.047612190246582, "global_step": 462238, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0082666873931885, "global_step": 462239, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.133265495300293, "global_step": 462240, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.074246883392334, "global_step": 462241, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.015950918197632, "global_step": 462242, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0326626300811768, "global_step": 462243, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1230812072753906, "global_step": 462244, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0754103660583496, "global_step": 462245, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1570935249328613, "global_step": 462246, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.040771961212158, "global_step": 462247, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.189541816711426, "global_step": 462248, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1180896759033203, "global_step": 462249, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0534613132476807, "global_step": 462250, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0587596893310547, "global_step": 462251, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.098430871963501, "global_step": 462252, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0422677993774414, "global_step": 462253, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0197594165802, "global_step": 462254, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0717532634735107, "global_step": 462255, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.120723009109497, "global_step": 462256, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.125234365463257, "global_step": 462257, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0857596397399902, "global_step": 462258, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.048203945159912, "global_step": 462259, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1227548122406006, "global_step": 462260, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9894778728485107, "global_step": 462261, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9941904544830322, "global_step": 462262, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.014518976211548, "global_step": 462263, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.014986276626587, "global_step": 462264, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.093790292739868, "global_step": 462265, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.141799211502075, "global_step": 462266, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1301333904266357, "global_step": 462267, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.057914972305298, "global_step": 462268, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.018442392349243, "global_step": 462269, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0570006370544434, "global_step": 462270, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0628232955932617, "global_step": 462271, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9938353300094604, "global_step": 462272, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1124229431152344, "global_step": 462273, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1372573375701904, "global_step": 462274, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1542160511016846, "global_step": 462275, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9818453788757324, "global_step": 462276, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.12888503074646, "global_step": 462277, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.109778881072998, "global_step": 462278, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0493195056915283, "global_step": 462279, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9569838047027588, "global_step": 462280, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.98666250705719, "global_step": 462281, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1253914833068848, "global_step": 462282, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.971937894821167, "global_step": 462283, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0224132537841797, "global_step": 462284, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1041460037231445, "global_step": 462285, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1173572540283203, "global_step": 462286, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0517995357513428, "global_step": 462287, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1342997550964355, "global_step": 462288, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1557412147521973, "global_step": 462289, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0976245403289795, "global_step": 462290, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.105034589767456, "global_step": 462291, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0911407470703125, "global_step": 462292, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1143462657928467, "global_step": 462293, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.06858491897583, "global_step": 462294, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1563167572021484, "global_step": 462295, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.098804235458374, "global_step": 462296, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.036623001098633, "global_step": 462297, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1328351497650146, "global_step": 462298, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.043949842453003, "global_step": 462299, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.2391104698181152, "global_step": 462300, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0653913021087646, "global_step": 462301, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.025259256362915, "global_step": 462302, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.024132251739502, "global_step": 462303, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0803349018096924, "global_step": 462304, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1293747425079346, "global_step": 462305, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1306276321411133, "global_step": 462306, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.148073196411133, "global_step": 462307, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.087873697280884, "global_step": 462308, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1083946228027344, "global_step": 462309, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0433640480041504, "global_step": 462310, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1754631996154785, "global_step": 462311, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.112043619155884, "global_step": 462312, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1411399841308594, "global_step": 462313, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1194326877593994, "global_step": 462314, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.082246780395508, "global_step": 462315, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0593326091766357, "global_step": 462316, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0939760208129883, "global_step": 462317, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0911996364593506, "global_step": 462318, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0389277935028076, "global_step": 462319, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1060237884521484, "global_step": 462320, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1256067752838135, "global_step": 462321, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1196095943450928, "global_step": 462322, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.039210557937622, "global_step": 462323, "epoch": 826, "lr": 5e-05}
{"train_loss": 1.9866808652877808, "global_step": 462324, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0470991134643555, "global_step": 462325, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1021769046783447, "global_step": 462326, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.075521469116211, "global_step": 462327, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.049346923828125, "global_step": 462328, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0705106258392334, "global_step": 462329, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0666513442993164, "global_step": 462330, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1028928756713867, "global_step": 462331, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.101708173751831, "global_step": 462332, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1098856925964355, "global_step": 462333, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.189864158630371, "global_step": 462334, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0440802574157715, "global_step": 462335, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0951600074768066, "global_step": 462336, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1125266551971436, "global_step": 462337, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.066173553466797, "global_step": 462338, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1363790035247803, "global_step": 462339, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0695722103118896, "global_step": 462340, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.1354808807373047, "global_step": 462341, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0658462047576904, "global_step": 462342, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0997867584228516, "global_step": 462343, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.0862064361572266, "global_step": 462344, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.068333625793457, "global_step": 462345, "epoch": 826, "lr": 5e-05}
{"train_loss": 2.045323610305786, "global_step": 462346, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0975167751312256, "global_step": 462347, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.067650318145752, "global_step": 462348, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9957526922225952, "global_step": 462349, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.089850425720215, "global_step": 462350, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0353853702545166, "global_step": 462351, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0667099952697754, "global_step": 462352, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.106290817260742, "global_step": 462353, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.04734468460083, "global_step": 462354, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.075927972793579, "global_step": 462355, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0873780250549316, "global_step": 462356, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9754332304000854, "global_step": 462357, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.09151554107666, "global_step": 462358, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.014511823654175, "global_step": 462359, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0845515727996826, "global_step": 462360, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.097433090209961, "global_step": 462361, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1010022163391113, "global_step": 462362, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.003366470336914, "global_step": 462363, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9818520545959473, "global_step": 462364, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0308682918548584, "global_step": 462365, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0283617973327637, "global_step": 462366, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.003551483154297, "global_step": 462367, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9723377227783203, "global_step": 462368, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.142827033996582, "global_step": 462369, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.064345121383667, "global_step": 462370, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1470508575439453, "global_step": 462371, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0169806480407715, "global_step": 462372, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1020443439483643, "global_step": 462373, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.076613664627075, "global_step": 462374, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0223517417907715, "global_step": 462375, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1192774772644043, "global_step": 462376, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0627095699310303, "global_step": 462377, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.035507917404175, "global_step": 462378, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.131359577178955, "global_step": 462379, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0696866512298584, "global_step": 462380, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.152851104736328, "global_step": 462381, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9869325160980225, "global_step": 462382, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1029577255249023, "global_step": 462383, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.096924066543579, "global_step": 462384, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9547299146652222, "global_step": 462385, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0519731044769287, "global_step": 462386, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0416812896728516, "global_step": 462387, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.02681303024292, "global_step": 462388, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1196234226226807, "global_step": 462389, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.021087884902954, "global_step": 462390, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.092458963394165, "global_step": 462391, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9954984188079834, "global_step": 462392, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.02520751953125, "global_step": 462393, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0000381469726562, "global_step": 462394, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9928597211837769, "global_step": 462395, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.037191867828369, "global_step": 462396, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.03450608253479, "global_step": 462397, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.101020097732544, "global_step": 462398, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.047790765762329, "global_step": 462399, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.07527494430542, "global_step": 462400, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1178760528564453, "global_step": 462401, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9803855419158936, "global_step": 462402, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.041362762451172, "global_step": 462403, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0399434566497803, "global_step": 462404, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0847437381744385, "global_step": 462405, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.14436411857605, "global_step": 462406, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0593619346618652, "global_step": 462407, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.062629222869873, "global_step": 462408, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0882039070129395, "global_step": 462409, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1105165481567383, "global_step": 462410, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0663211345672607, "global_step": 462411, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9876515865325928, "global_step": 462412, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0738444328308105, "global_step": 462413, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.149367332458496, "global_step": 462414, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1107165813446045, "global_step": 462415, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.064371347427368, "global_step": 462416, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1038858890533447, "global_step": 462417, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.032015323638916, "global_step": 462418, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.026670455932617, "global_step": 462419, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.071284532546997, "global_step": 462420, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.023325204849243, "global_step": 462421, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.00002121925354, "global_step": 462422, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9894112348556519, "global_step": 462423, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0575883388519287, "global_step": 462424, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.029477596282959, "global_step": 462425, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1271779537200928, "global_step": 462426, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1275081634521484, "global_step": 462427, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.003953695297241, "global_step": 462428, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1024491786956787, "global_step": 462429, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0737459659576416, "global_step": 462430, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0721933841705322, "global_step": 462431, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0939297676086426, "global_step": 462432, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0903937816619873, "global_step": 462433, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0140769481658936, "global_step": 462434, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0754284858703613, "global_step": 462435, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0816750526428223, "global_step": 462436, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.085893154144287, "global_step": 462437, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1062753200531006, "global_step": 462438, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.072648048400879, "global_step": 462439, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0380501747131348, "global_step": 462440, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.119258165359497, "global_step": 462441, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9537361860275269, "global_step": 462442, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9340057373046875, "global_step": 462443, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.017165422439575, "global_step": 462444, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.100250720977783, "global_step": 462445, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.092066764831543, "global_step": 462446, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.12378191947937, "global_step": 462447, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9863028526306152, "global_step": 462448, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.042483329772949, "global_step": 462449, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1165199279785156, "global_step": 462450, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0025064945220947, "global_step": 462451, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.132323741912842, "global_step": 462452, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1115670204162598, "global_step": 462453, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0069081783294678, "global_step": 462454, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.09303617477417, "global_step": 462455, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0969018936157227, "global_step": 462456, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.109621047973633, "global_step": 462457, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0884790420532227, "global_step": 462458, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0506224632263184, "global_step": 462459, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.203950881958008, "global_step": 462460, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.08111572265625, "global_step": 462461, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0718111991882324, "global_step": 462462, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.087477684020996, "global_step": 462463, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0668210983276367, "global_step": 462464, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.126617908477783, "global_step": 462465, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.021773099899292, "global_step": 462466, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.028895854949951, "global_step": 462467, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.081972122192383, "global_step": 462468, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0871083736419678, "global_step": 462469, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.131382703781128, "global_step": 462470, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0759358406066895, "global_step": 462471, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.047307252883911, "global_step": 462472, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0072455406188965, "global_step": 462473, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0333173274993896, "global_step": 462474, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1284587383270264, "global_step": 462475, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0366108417510986, "global_step": 462476, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1331820487976074, "global_step": 462477, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.068963050842285, "global_step": 462478, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.05305814743042, "global_step": 462479, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0694448947906494, "global_step": 462480, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0901339054107666, "global_step": 462481, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.03252911567688, "global_step": 462482, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1219594478607178, "global_step": 462483, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0267012119293213, "global_step": 462484, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.06657075881958, "global_step": 462485, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1031031608581543, "global_step": 462486, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0750880241394043, "global_step": 462487, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1041600704193115, "global_step": 462488, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0308141708374023, "global_step": 462489, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9812427759170532, "global_step": 462490, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0320472717285156, "global_step": 462491, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1083791255950928, "global_step": 462492, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0575079917907715, "global_step": 462493, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9809194803237915, "global_step": 462494, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.109891176223755, "global_step": 462495, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0673184394836426, "global_step": 462496, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.043635845184326, "global_step": 462497, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0718743801116943, "global_step": 462498, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.106031656265259, "global_step": 462499, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0011396408081055, "global_step": 462500, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.093161106109619, "global_step": 462501, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.052365779876709, "global_step": 462502, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.104447603225708, "global_step": 462503, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0369513034820557, "global_step": 462504, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9737887382507324, "global_step": 462505, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0317442417144775, "global_step": 462506, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0699284076690674, "global_step": 462507, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0281710624694824, "global_step": 462508, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.001171827316284, "global_step": 462509, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.093108654022217, "global_step": 462510, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.022627830505371, "global_step": 462511, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.065185546875, "global_step": 462512, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0480780601501465, "global_step": 462513, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.061150074005127, "global_step": 462514, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0519280433654785, "global_step": 462515, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.157398223876953, "global_step": 462516, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.093690872192383, "global_step": 462517, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.061079263687134, "global_step": 462518, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.995538592338562, "global_step": 462519, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1503124237060547, "global_step": 462520, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.100402355194092, "global_step": 462521, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1046195030212402, "global_step": 462522, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.042048931121826, "global_step": 462523, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0696964263916016, "global_step": 462524, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1206629276275635, "global_step": 462525, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0299556255340576, "global_step": 462526, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.085362195968628, "global_step": 462527, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1234476566314697, "global_step": 462528, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0809357166290283, "global_step": 462529, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0768885612487793, "global_step": 462530, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.075927495956421, "global_step": 462531, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0728020668029785, "global_step": 462532, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.046616792678833, "global_step": 462533, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.028597831726074, "global_step": 462534, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.039464235305786, "global_step": 462535, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0902068614959717, "global_step": 462536, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0725433826446533, "global_step": 462537, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.05741024017334, "global_step": 462538, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0055062770843506, "global_step": 462539, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.008657932281494, "global_step": 462540, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0041110515594482, "global_step": 462541, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.092886447906494, "global_step": 462542, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1653647422790527, "global_step": 462543, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0804457664489746, "global_step": 462544, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1263930797576904, "global_step": 462545, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9919233322143555, "global_step": 462546, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0615592002868652, "global_step": 462547, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.065448045730591, "global_step": 462548, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.108778476715088, "global_step": 462549, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0839312076568604, "global_step": 462550, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1074442863464355, "global_step": 462551, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0249998569488525, "global_step": 462552, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9922831058502197, "global_step": 462553, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.090632677078247, "global_step": 462554, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1010494232177734, "global_step": 462555, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0307412147521973, "global_step": 462556, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9908207654953003, "global_step": 462557, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.033478260040283, "global_step": 462558, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.063184976577759, "global_step": 462559, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0680532455444336, "global_step": 462560, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1986141204833984, "global_step": 462561, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.059602975845337, "global_step": 462562, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1107757091522217, "global_step": 462563, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0311126708984375, "global_step": 462564, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.996759057044983, "global_step": 462565, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0391685962677, "global_step": 462566, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1254143714904785, "global_step": 462567, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1348023414611816, "global_step": 462568, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0454330444335938, "global_step": 462569, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0733110904693604, "global_step": 462570, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.080886125564575, "global_step": 462571, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.10810923576355, "global_step": 462572, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0654780864715576, "global_step": 462573, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0114002227783203, "global_step": 462574, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.045290946960449, "global_step": 462575, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0610544681549072, "global_step": 462576, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0598974227905273, "global_step": 462577, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.111915349960327, "global_step": 462578, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0062148571014404, "global_step": 462579, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.963705062866211, "global_step": 462580, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.159904956817627, "global_step": 462581, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.034046173095703, "global_step": 462582, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.069725751876831, "global_step": 462583, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1130597591400146, "global_step": 462584, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.034647226333618, "global_step": 462585, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1061792373657227, "global_step": 462586, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0434446334838867, "global_step": 462587, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.073322057723999, "global_step": 462588, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.081838369369507, "global_step": 462589, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9767869710922241, "global_step": 462590, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0724964141845703, "global_step": 462591, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.136152744293213, "global_step": 462592, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.075277805328369, "global_step": 462593, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1458261013031006, "global_step": 462594, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.2118353843688965, "global_step": 462595, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9816827774047852, "global_step": 462596, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0265982151031494, "global_step": 462597, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.104827880859375, "global_step": 462598, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.015245199203491, "global_step": 462599, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1081721782684326, "global_step": 462600, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.085365056991577, "global_step": 462601, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0369553565979004, "global_step": 462602, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0616626739501953, "global_step": 462603, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0451250076293945, "global_step": 462604, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1066784858703613, "global_step": 462605, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.043860673904419, "global_step": 462606, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.107778787612915, "global_step": 462607, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0837771892547607, "global_step": 462608, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.141065835952759, "global_step": 462609, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0055344104766846, "global_step": 462610, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9687399864196777, "global_step": 462611, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.068267822265625, "global_step": 462612, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.074364423751831, "global_step": 462613, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1531550884246826, "global_step": 462614, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0295653343200684, "global_step": 462615, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1427359580993652, "global_step": 462616, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1053121089935303, "global_step": 462617, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9922102689743042, "global_step": 462618, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.011320114135742, "global_step": 462619, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.075777053833008, "global_step": 462620, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.056941032409668, "global_step": 462621, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.075740337371826, "global_step": 462622, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1271698474884033, "global_step": 462623, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1193761825561523, "global_step": 462624, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0597658157348633, "global_step": 462625, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0741934776306152, "global_step": 462626, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0253102779388428, "global_step": 462627, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.030409097671509, "global_step": 462628, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0965139865875244, "global_step": 462629, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0374608039855957, "global_step": 462630, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0761160850524902, "global_step": 462631, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1101744174957275, "global_step": 462632, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0598292350769043, "global_step": 462633, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0678794384002686, "global_step": 462634, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.020169973373413, "global_step": 462635, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.070432662963867, "global_step": 462636, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.082969903945923, "global_step": 462637, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0544142723083496, "global_step": 462638, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.157365083694458, "global_step": 462639, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.029099702835083, "global_step": 462640, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.047840118408203, "global_step": 462641, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.933747410774231, "global_step": 462642, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0818426609039307, "global_step": 462643, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.106239080429077, "global_step": 462644, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.048797130584717, "global_step": 462645, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0261216163635254, "global_step": 462646, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.115460157394409, "global_step": 462647, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.08320951461792, "global_step": 462648, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.13134765625, "global_step": 462649, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.09537410736084, "global_step": 462650, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1044490337371826, "global_step": 462651, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.102200984954834, "global_step": 462652, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0397913455963135, "global_step": 462653, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0111539363861084, "global_step": 462654, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1055052280426025, "global_step": 462655, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0944530963897705, "global_step": 462656, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0869171619415283, "global_step": 462657, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.130838394165039, "global_step": 462658, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.079230308532715, "global_step": 462659, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0434484481811523, "global_step": 462660, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9948550462722778, "global_step": 462661, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0939440727233887, "global_step": 462662, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.094806671142578, "global_step": 462663, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0319013595581055, "global_step": 462664, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.058220863342285, "global_step": 462665, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.092257499694824, "global_step": 462666, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0487759113311768, "global_step": 462667, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.028958559036255, "global_step": 462668, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0554304122924805, "global_step": 462669, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.176821231842041, "global_step": 462670, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9917683601379395, "global_step": 462671, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.043731451034546, "global_step": 462672, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.022916316986084, "global_step": 462673, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1224143505096436, "global_step": 462674, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0584535598754883, "global_step": 462675, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9841800928115845, "global_step": 462676, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.054258346557617, "global_step": 462677, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9897962808609009, "global_step": 462678, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0453124046325684, "global_step": 462679, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0502593517303467, "global_step": 462680, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.05788254737854, "global_step": 462681, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1159605979919434, "global_step": 462682, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1024341583251953, "global_step": 462683, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.947316288948059, "global_step": 462684, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0528974533081055, "global_step": 462685, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1071765422821045, "global_step": 462686, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.093125343322754, "global_step": 462687, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1113088130950928, "global_step": 462688, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1026129722595215, "global_step": 462689, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0379738807678223, "global_step": 462690, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0613644123077393, "global_step": 462691, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.054914951324463, "global_step": 462692, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.019380569458008, "global_step": 462693, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.023181676864624, "global_step": 462694, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9727287292480469, "global_step": 462695, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9927343130111694, "global_step": 462696, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0661823749542236, "global_step": 462697, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0894808769226074, "global_step": 462698, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.065096855163574, "global_step": 462699, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.006533145904541, "global_step": 462700, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0051209926605225, "global_step": 462701, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.035907745361328, "global_step": 462702, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0639872550964355, "global_step": 462703, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0624594688415527, "global_step": 462704, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.082555055618286, "global_step": 462705, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.054983615875244, "global_step": 462706, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0591890811920166, "global_step": 462707, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.120344400405884, "global_step": 462708, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0648868083953857, "global_step": 462709, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0896592140197754, "global_step": 462710, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.076493978500366, "global_step": 462711, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.037689208984375, "global_step": 462712, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.128831148147583, "global_step": 462713, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.132401704788208, "global_step": 462714, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0512561798095703, "global_step": 462715, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0705325603485107, "global_step": 462716, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1137914657592773, "global_step": 462717, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.023900270462036, "global_step": 462718, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1175243854522705, "global_step": 462719, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0749828815460205, "global_step": 462720, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0736842155456543, "global_step": 462721, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.083505630493164, "global_step": 462722, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0664005279541016, "global_step": 462723, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.055642604827881, "global_step": 462724, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0698401927948, "global_step": 462725, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0147273540496826, "global_step": 462726, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0558629035949707, "global_step": 462727, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1356430053710938, "global_step": 462728, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0027575492858887, "global_step": 462729, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.034604549407959, "global_step": 462730, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1282455921173096, "global_step": 462731, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0571951866149902, "global_step": 462732, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0823328495025635, "global_step": 462733, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.105269193649292, "global_step": 462734, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.065161943435669, "global_step": 462735, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1041641235351562, "global_step": 462736, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0221076011657715, "global_step": 462737, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1236960887908936, "global_step": 462738, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0158064365386963, "global_step": 462739, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1963772773742676, "global_step": 462740, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0246431827545166, "global_step": 462741, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1082112789154053, "global_step": 462742, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1128127574920654, "global_step": 462743, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9758378267288208, "global_step": 462744, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0759124755859375, "global_step": 462745, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9622498750686646, "global_step": 462746, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.060779571533203, "global_step": 462747, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.008190393447876, "global_step": 462748, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1127514839172363, "global_step": 462749, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0673110485076904, "global_step": 462750, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0659210681915283, "global_step": 462751, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1311280727386475, "global_step": 462752, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.143866539001465, "global_step": 462753, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0325186252593994, "global_step": 462754, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1293673515319824, "global_step": 462755, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0447704792022705, "global_step": 462756, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.052232027053833, "global_step": 462757, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.054774284362793, "global_step": 462758, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.133249282836914, "global_step": 462759, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9820367097854614, "global_step": 462760, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.131470203399658, "global_step": 462761, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.084202766418457, "global_step": 462762, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0579400062561035, "global_step": 462763, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0887088775634766, "global_step": 462764, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.088869571685791, "global_step": 462765, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0705316066741943, "global_step": 462766, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0992963314056396, "global_step": 462767, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.069221258163452, "global_step": 462768, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.025529623031616, "global_step": 462769, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1047682762145996, "global_step": 462770, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1998071670532227, "global_step": 462771, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9870004653930664, "global_step": 462772, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.138021469116211, "global_step": 462773, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0514931678771973, "global_step": 462774, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1024906635284424, "global_step": 462775, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9985378980636597, "global_step": 462776, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0178070068359375, "global_step": 462777, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.059107780456543, "global_step": 462778, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0993573665618896, "global_step": 462779, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.024404764175415, "global_step": 462780, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0704333782196045, "global_step": 462781, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.082716464996338, "global_step": 462782, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0721871852874756, "global_step": 462783, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.088361978530884, "global_step": 462784, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0544633865356445, "global_step": 462785, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1224277019500732, "global_step": 462786, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0648672580718994, "global_step": 462787, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0551977157592773, "global_step": 462788, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.074986219406128, "global_step": 462789, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0281081199645996, "global_step": 462790, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.017941474914551, "global_step": 462791, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1077077388763428, "global_step": 462792, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.089109182357788, "global_step": 462793, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0336270332336426, "global_step": 462794, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.089611530303955, "global_step": 462795, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1232473850250244, "global_step": 462796, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0546207427978516, "global_step": 462797, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0572268962860107, "global_step": 462798, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.016608953475952, "global_step": 462799, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0503368377685547, "global_step": 462800, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0919578075408936, "global_step": 462801, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.119661808013916, "global_step": 462802, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.085923433303833, "global_step": 462803, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.031221389770508, "global_step": 462804, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.036611795425415, "global_step": 462805, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0871589183807373, "global_step": 462806, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0171022415161133, "global_step": 462807, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1766834259033203, "global_step": 462808, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.038187026977539, "global_step": 462809, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0316171646118164, "global_step": 462810, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1670427322387695, "global_step": 462811, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.069809913635254, "global_step": 462812, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0277302265167236, "global_step": 462813, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.128936529159546, "global_step": 462814, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.105815887451172, "global_step": 462815, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0131654739379883, "global_step": 462816, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.129716396331787, "global_step": 462817, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.096489429473877, "global_step": 462818, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1093876361846924, "global_step": 462819, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.101423501968384, "global_step": 462820, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.121987819671631, "global_step": 462821, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1931300163269043, "global_step": 462822, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0664188861846924, "global_step": 462823, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1571826934814453, "global_step": 462824, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0779168605804443, "global_step": 462825, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.00258207321167, "global_step": 462826, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1621410846710205, "global_step": 462827, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.013396978378296, "global_step": 462828, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.032512664794922, "global_step": 462829, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0769248008728027, "global_step": 462830, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0786845684051514, "global_step": 462831, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0270047187805176, "global_step": 462832, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.155712127685547, "global_step": 462833, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9920654296875, "global_step": 462834, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0859811305999756, "global_step": 462835, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.011178731918335, "global_step": 462836, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0202646255493164, "global_step": 462837, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.105903148651123, "global_step": 462838, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0305466651916504, "global_step": 462839, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9480279684066772, "global_step": 462840, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.105421543121338, "global_step": 462841, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.073601722717285, "global_step": 462842, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.095454216003418, "global_step": 462843, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.089982509613037, "global_step": 462844, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.072401523590088, "global_step": 462845, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0688934326171875, "global_step": 462846, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.146862745285034, "global_step": 462847, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1354074478149414, "global_step": 462848, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.116950273513794, "global_step": 462849, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0521132946014404, "global_step": 462850, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1419334411621094, "global_step": 462851, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.047563314437866, "global_step": 462852, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.102989435195923, "global_step": 462853, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.069852352142334, "global_step": 462854, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.076756238937378, "global_step": 462855, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.095759868621826, "global_step": 462856, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1255016326904297, "global_step": 462857, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1049087047576904, "global_step": 462858, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.076817750930786, "global_step": 462859, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9923421144485474, "global_step": 462860, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0030994415283203, "global_step": 462861, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.066164016723633, "global_step": 462862, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.160013198852539, "global_step": 462863, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0316288471221924, "global_step": 462864, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.062629222869873, "global_step": 462865, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.048835039138794, "global_step": 462866, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.12225604057312, "global_step": 462867, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.067000150680542, "global_step": 462868, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9829851388931274, "global_step": 462869, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0288755893707275, "global_step": 462870, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.169463634490967, "global_step": 462871, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9993700981140137, "global_step": 462872, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0434813499450684, "global_step": 462873, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.045682668685913, "global_step": 462874, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1004180908203125, "global_step": 462875, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0845284461975098, "global_step": 462876, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.14194655418396, "global_step": 462877, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.136807918548584, "global_step": 462878, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0025382041931152, "global_step": 462879, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0596728324890137, "global_step": 462880, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9080666303634644, "global_step": 462881, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0728368759155273, "global_step": 462882, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.156491279602051, "global_step": 462883, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1860384941101074, "global_step": 462884, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.093137264251709, "global_step": 462885, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.060171604156494, "global_step": 462886, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.026423692703247, "global_step": 462887, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.2032909393310547, "global_step": 462888, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0673940181732178, "global_step": 462889, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1034276485443115, "global_step": 462890, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1093876361846924, "global_step": 462891, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0815279483795166, "global_step": 462892, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.040695905685425, "global_step": 462893, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.144015312194824, "global_step": 462894, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0950021743774414, "global_step": 462895, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0523695945739746, "global_step": 462896, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9880937337875366, "global_step": 462897, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1436102390289307, "global_step": 462898, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.014260768890381, "global_step": 462899, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.961681604385376, "global_step": 462900, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0125272274017334, "global_step": 462901, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0293116569519043, "global_step": 462902, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0790765285491943, "global_step": 462903, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0339155197143555, "global_step": 462904, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0215935707092285, "global_step": 462905, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1651830673217773, "global_step": 462906, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.088808536529541, "global_step": 462907, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.024533748626709, "global_step": 462908, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0658435821533203, "global_step": 462909, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.022552251815796, "global_step": 462910, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0907981395721436, "global_step": 462911, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0424535274505615, "global_step": 462912, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0508718490600586, "global_step": 462913, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.058012008666992, "global_step": 462914, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0222387313842773, "global_step": 462915, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.058410882949829, "global_step": 462916, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.004760503768921, "global_step": 462917, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.088587760925293, "global_step": 462918, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.102576971054077, "global_step": 462919, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.134230852127075, "global_step": 462920, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9629030227661133, "global_step": 462921, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0320374965667725, "global_step": 462922, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0083189010620117, "global_step": 462923, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1178383827209473, "global_step": 462924, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0793344974517822, "global_step": 462925, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.096984624862671, "global_step": 462926, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.09505033493042, "global_step": 462927, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0628929138183594, "global_step": 462928, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.134789228439331, "global_step": 462929, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0469632148742676, "global_step": 462930, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0359158515930176, "global_step": 462931, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.116466522216797, "global_step": 462932, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0826549530029297, "global_step": 462933, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.020146131515503, "global_step": 462934, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.027172803878784, "global_step": 462935, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.041646957397461, "global_step": 462936, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.098827362060547, "global_step": 462937, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.059988260269165, "global_step": 462938, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.097705364227295, "global_step": 462939, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0690619945526123, "global_step": 462940, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0957884788513184, "global_step": 462941, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.967320442199707, "global_step": 462942, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.975917935371399, "global_step": 462943, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.111283540725708, "global_step": 462944, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.092768430709839, "global_step": 462945, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1324214935302734, "global_step": 462946, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0998854637145996, "global_step": 462947, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.128018856048584, "global_step": 462948, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0793087482452393, "global_step": 462949, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9930505752563477, "global_step": 462950, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0732972621917725, "global_step": 462951, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0120038986206055, "global_step": 462952, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.141620635986328, "global_step": 462953, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1003336906433105, "global_step": 462954, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1286840438842773, "global_step": 462955, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.075967788696289, "global_step": 462956, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0347747802734375, "global_step": 462957, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0360805988311768, "global_step": 462958, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.057300329208374, "global_step": 462959, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0285356044769287, "global_step": 462960, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1173524856567383, "global_step": 462961, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1367664337158203, "global_step": 462962, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1573519706726074, "global_step": 462963, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.113732099533081, "global_step": 462964, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0968472957611084, "global_step": 462965, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0584702491760254, "global_step": 462966, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1686367988586426, "global_step": 462967, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0167341232299805, "global_step": 462968, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.105865478515625, "global_step": 462969, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.056461811065674, "global_step": 462970, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0909135341644287, "global_step": 462971, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.095736503601074, "global_step": 462972, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.055182695388794, "global_step": 462973, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.066253423690796, "global_step": 462974, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0433712005615234, "global_step": 462975, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1203789710998535, "global_step": 462976, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0966126918792725, "global_step": 462977, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1587021350860596, "global_step": 462978, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0596981048583984, "global_step": 462979, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.010772705078125, "global_step": 462980, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0496182441711426, "global_step": 462981, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.065185308456421, "global_step": 462982, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1789488792419434, "global_step": 462983, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0721521377563477, "global_step": 462984, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.028961181640625, "global_step": 462985, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0980093479156494, "global_step": 462986, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0395419597625732, "global_step": 462987, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0740609169006348, "global_step": 462988, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.041616201400757, "global_step": 462989, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0852434635162354, "global_step": 462990, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0937604904174805, "global_step": 462991, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.067323684692383, "global_step": 462992, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.098388910293579, "global_step": 462993, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.019803047180176, "global_step": 462994, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.103823661804199, "global_step": 462995, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0804314613342285, "global_step": 462996, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0000641345977783, "global_step": 462997, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.124328136444092, "global_step": 462998, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1156861782073975, "global_step": 462999, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1192755699157715, "global_step": 463000, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0857372283935547, "global_step": 463001, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.08058500289917, "global_step": 463002, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.06779408454895, "global_step": 463003, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.13753080368042, "global_step": 463004, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.059522867202759, "global_step": 463005, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.183483123779297, "global_step": 463006, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0047295093536377, "global_step": 463007, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.113996982574463, "global_step": 463008, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0877764225006104, "global_step": 463009, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.141355037689209, "global_step": 463010, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.050616979598999, "global_step": 463011, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.041290760040283, "global_step": 463012, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.064068078994751, "global_step": 463013, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0405027866363525, "global_step": 463014, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1416029930114746, "global_step": 463015, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.099025011062622, "global_step": 463016, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0787174701690674, "global_step": 463017, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0996227264404297, "global_step": 463018, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0522491931915283, "global_step": 463019, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1357619762420654, "global_step": 463020, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.066828489303589, "global_step": 463021, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0691943168640137, "global_step": 463022, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0628621578216553, "global_step": 463023, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1135473251342773, "global_step": 463024, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0489604473114014, "global_step": 463025, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.056025266647339, "global_step": 463026, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.026853084564209, "global_step": 463027, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1799371242523193, "global_step": 463028, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1299691200256348, "global_step": 463029, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1284098625183105, "global_step": 463030, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1087985038757324, "global_step": 463031, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.049099922180176, "global_step": 463032, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1414709091186523, "global_step": 463033, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0836617946624756, "global_step": 463034, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.127175807952881, "global_step": 463035, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.998445987701416, "global_step": 463036, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0620877742767334, "global_step": 463037, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.072455644607544, "global_step": 463038, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.087582588195801, "global_step": 463039, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1349971294403076, "global_step": 463040, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9969451427459717, "global_step": 463041, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1001524925231934, "global_step": 463042, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0404322147369385, "global_step": 463043, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.076014280319214, "global_step": 463044, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1662392616271973, "global_step": 463045, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.158841133117676, "global_step": 463046, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.06904935836792, "global_step": 463047, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.093801498413086, "global_step": 463048, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0818629264831543, "global_step": 463049, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0060691833496094, "global_step": 463050, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.04805588722229, "global_step": 463051, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.077143430709839, "global_step": 463052, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0687315464019775, "global_step": 463053, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1387062072753906, "global_step": 463054, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.068249225616455, "global_step": 463055, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.071509838104248, "global_step": 463056, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.109685182571411, "global_step": 463057, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.090053081512451, "global_step": 463058, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.099303722381592, "global_step": 463059, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.084886074066162, "global_step": 463060, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0940332412719727, "global_step": 463061, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1212985515594482, "global_step": 463062, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.085601568222046, "global_step": 463063, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9899729490280151, "global_step": 463064, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0266330242156982, "global_step": 463065, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.065711259841919, "global_step": 463066, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1430845260620117, "global_step": 463067, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0310158729553223, "global_step": 463068, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9790434837341309, "global_step": 463069, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.165940046310425, "global_step": 463070, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0302746295928955, "global_step": 463071, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.09061861038208, "global_step": 463072, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0484745502471924, "global_step": 463073, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.06855845451355, "global_step": 463074, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0836904048919678, "global_step": 463075, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0031545162200928, "global_step": 463076, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1953160762786865, "global_step": 463077, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0674920082092285, "global_step": 463078, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1033711433410645, "global_step": 463079, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0585806369781494, "global_step": 463080, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.060685157775879, "global_step": 463081, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.146289348602295, "global_step": 463082, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9329869747161865, "global_step": 463083, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0677194595336914, "global_step": 463084, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.022719621658325, "global_step": 463085, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0891354084014893, "global_step": 463086, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.068540573120117, "global_step": 463087, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9862197637557983, "global_step": 463088, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.081373691558838, "global_step": 463089, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.052696704864502, "global_step": 463090, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0458149909973145, "global_step": 463091, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.114931583404541, "global_step": 463092, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.095701217651367, "global_step": 463093, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0575857162475586, "global_step": 463094, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0083799362182617, "global_step": 463095, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0999064445495605, "global_step": 463096, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1891930103302, "global_step": 463097, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.147538661956787, "global_step": 463098, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.042355537414551, "global_step": 463099, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.008831262588501, "global_step": 463100, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0850303173065186, "global_step": 463101, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.162125825881958, "global_step": 463102, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1084134578704834, "global_step": 463103, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0038986206054688, "global_step": 463104, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0885462760925293, "global_step": 463105, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1103789806365967, "global_step": 463106, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.078965425491333, "global_step": 463107, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0371756553649902, "global_step": 463108, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1534440517425537, "global_step": 463109, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0304794311523438, "global_step": 463110, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0452113151550293, "global_step": 463111, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.025721788406372, "global_step": 463112, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1342618465423584, "global_step": 463113, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0930612087249756, "global_step": 463114, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9958537817001343, "global_step": 463115, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1082301139831543, "global_step": 463116, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0584402084350586, "global_step": 463117, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0876615047454834, "global_step": 463118, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0479648113250732, "global_step": 463119, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.085134506225586, "global_step": 463120, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.106548309326172, "global_step": 463121, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0273306369781494, "global_step": 463122, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.037771224975586, "global_step": 463123, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.105898141860962, "global_step": 463124, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.037726879119873, "global_step": 463125, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.097656726837158, "global_step": 463126, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.098562240600586, "global_step": 463127, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.067669630050659, "global_step": 463128, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.062457799911499, "global_step": 463129, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1033196449279785, "global_step": 463130, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.058624744415283, "global_step": 463131, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.072345018386841, "global_step": 463132, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1185317039489746, "global_step": 463133, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1588194370269775, "global_step": 463134, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0269110202789307, "global_step": 463135, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9951591491699219, "global_step": 463136, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0430068969726562, "global_step": 463137, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1700971126556396, "global_step": 463138, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.059704542160034, "global_step": 463139, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.100114107131958, "global_step": 463140, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0531859397888184, "global_step": 463141, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0404295921325684, "global_step": 463142, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0935611724853516, "global_step": 463143, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9880242347717285, "global_step": 463144, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0747804641723633, "global_step": 463145, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0940139293670654, "global_step": 463146, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0216755867004395, "global_step": 463147, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.104315757751465, "global_step": 463148, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.041964292526245, "global_step": 463149, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0600571632385254, "global_step": 463150, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.112262725830078, "global_step": 463151, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9757744073867798, "global_step": 463152, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0032296180725098, "global_step": 463153, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0426089763641357, "global_step": 463154, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0582454204559326, "global_step": 463155, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0360066890716553, "global_step": 463156, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.085069179534912, "global_step": 463157, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.084223985671997, "global_step": 463158, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.01127552986145, "global_step": 463159, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0934271812438965, "global_step": 463160, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0909998416900635, "global_step": 463161, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0663416385650635, "global_step": 463162, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0209462642669678, "global_step": 463163, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.067122459411621, "global_step": 463164, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.107849359512329, "global_step": 463165, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0899813175201416, "global_step": 463166, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0744364261627197, "global_step": 463167, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.055030584335327, "global_step": 463168, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1212379932403564, "global_step": 463169, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0989325046539307, "global_step": 463170, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.099565267562866, "global_step": 463171, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.001819133758545, "global_step": 463172, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0834462642669678, "global_step": 463173, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.034578323364258, "global_step": 463174, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1841726303100586, "global_step": 463175, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0785248279571533, "global_step": 463176, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1945226192474365, "global_step": 463177, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1082282066345215, "global_step": 463178, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.143083095550537, "global_step": 463179, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.020399570465088, "global_step": 463180, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1281356811523438, "global_step": 463181, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.083369493484497, "global_step": 463182, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1446313858032227, "global_step": 463183, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.151196241378784, "global_step": 463184, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.078747510910034, "global_step": 463185, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0520169734954834, "global_step": 463186, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.160120725631714, "global_step": 463187, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1853630542755127, "global_step": 463188, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0660953521728516, "global_step": 463189, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0990896224975586, "global_step": 463190, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0846405029296875, "global_step": 463191, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.078575372695923, "global_step": 463192, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1168696880340576, "global_step": 463193, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.135930299758911, "global_step": 463194, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0795671939849854, "global_step": 463195, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0638349056243896, "global_step": 463196, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.157482385635376, "global_step": 463197, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.036102533340454, "global_step": 463198, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.004159450531006, "global_step": 463199, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.028578519821167, "global_step": 463200, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.088944435119629, "global_step": 463201, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.080282688140869, "global_step": 463202, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1891329288482666, "global_step": 463203, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.023452043533325, "global_step": 463204, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.027228593826294, "global_step": 463205, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.043010950088501, "global_step": 463206, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.088212013244629, "global_step": 463207, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.127563238143921, "global_step": 463208, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.102341651916504, "global_step": 463209, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1591439247131348, "global_step": 463210, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.141282558441162, "global_step": 463211, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1280815601348877, "global_step": 463212, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0518958568573, "global_step": 463213, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0153520107269287, "global_step": 463214, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.161245584487915, "global_step": 463215, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0648000240325928, "global_step": 463216, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0043070316314697, "global_step": 463217, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1086490154266357, "global_step": 463218, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.048758029937744, "global_step": 463219, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.062134027481079, "global_step": 463220, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0631186962127686, "global_step": 463221, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0743751525878906, "global_step": 463222, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1370127201080322, "global_step": 463223, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.090265989303589, "global_step": 463224, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0047192573547363, "global_step": 463225, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0565595626831055, "global_step": 463226, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.070619821548462, "global_step": 463227, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.113891124725342, "global_step": 463228, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.179525136947632, "global_step": 463229, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0484602451324463, "global_step": 463230, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.108677864074707, "global_step": 463231, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.054990768432617, "global_step": 463232, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.093303918838501, "global_step": 463233, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0739030838012695, "global_step": 463234, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1316051483154297, "global_step": 463235, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9899193048477173, "global_step": 463236, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.055093288421631, "global_step": 463237, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0399482250213623, "global_step": 463238, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.154996871948242, "global_step": 463239, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.032013177871704, "global_step": 463240, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.147191047668457, "global_step": 463241, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.991382360458374, "global_step": 463242, "epoch": 827, "lr": 5e-05}
{"train_loss": 1.9872239828109741, "global_step": 463243, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.061105728149414, "global_step": 463244, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0620501041412354, "global_step": 463245, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0492708683013916, "global_step": 463246, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.029226541519165, "global_step": 463247, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0124526023864746, "global_step": 463248, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.113645315170288, "global_step": 463249, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0976524353027344, "global_step": 463250, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.070772171020508, "global_step": 463251, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0154385566711426, "global_step": 463252, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0884346961975098, "global_step": 463253, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.112076997756958, "global_step": 463254, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0755198001861572, "global_step": 463255, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.084747791290283, "global_step": 463256, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.109067678451538, "global_step": 463257, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1037771701812744, "global_step": 463258, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1133806705474854, "global_step": 463259, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1796770095825195, "global_step": 463260, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.119438409805298, "global_step": 463261, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.002776861190796, "global_step": 463262, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.046264410018921, "global_step": 463263, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.094543933868408, "global_step": 463264, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.008049726486206, "global_step": 463265, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0462093353271484, "global_step": 463266, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1053662300109863, "global_step": 463267, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1392552852630615, "global_step": 463268, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0754284858703613, "global_step": 463269, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.071922540664673, "global_step": 463270, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.118389844894409, "global_step": 463271, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1463797092437744, "global_step": 463272, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1506383419036865, "global_step": 463273, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1332380771636963, "global_step": 463274, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0714123249053955, "global_step": 463275, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0814411640167236, "global_step": 463276, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0681707859039307, "global_step": 463277, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0460147857666016, "global_step": 463278, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0839712619781494, "global_step": 463279, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0813543796539307, "global_step": 463280, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0785369873046875, "global_step": 463281, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0622453689575195, "global_step": 463282, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0489516258239746, "global_step": 463283, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0729777812957764, "global_step": 463284, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0086874961853027, "global_step": 463285, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0932910442352295, "global_step": 463286, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0986993312835693, "global_step": 463287, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.066154718399048, "global_step": 463288, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1044909954071045, "global_step": 463289, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0567054748535156, "global_step": 463290, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0486271381378174, "global_step": 463291, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0742833614349365, "global_step": 463292, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0474958419799805, "global_step": 463293, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1050541400909424, "global_step": 463294, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0808827877044678, "global_step": 463295, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.011280059814453, "global_step": 463296, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1468405723571777, "global_step": 463297, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.124728202819824, "global_step": 463298, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.1310510635375977, "global_step": 463299, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0241973400115967, "global_step": 463300, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0166702270507812, "global_step": 463301, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0182230472564697, "global_step": 463302, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.137071371078491, "global_step": 463303, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.00148868560791, "global_step": 463304, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0679123401641846, "global_step": 463305, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0161876678466797, "global_step": 463306, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.064603805541992, "global_step": 463307, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.029890537261963, "global_step": 463308, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0171847343444824, "global_step": 463309, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.027782678604126, "global_step": 463310, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0534589290618896, "global_step": 463311, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.115558624267578, "global_step": 463312, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.095586061477661, "global_step": 463313, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0715951919555664, "global_step": 463314, "epoch": 827, "lr": 5e-05}
{"train_loss": 2.0316319465637207, "global_step": 463315, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0490810871124268, "global_step": 463316, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.052748441696167, "global_step": 463317, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.043903112411499, "global_step": 463318, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9774545431137085, "global_step": 463319, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.091625928878784, "global_step": 463320, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1019492149353027, "global_step": 463321, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.087371349334717, "global_step": 463322, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1718597412109375, "global_step": 463323, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0372273921966553, "global_step": 463324, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.031811475753784, "global_step": 463325, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0851242542266846, "global_step": 463326, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.090212106704712, "global_step": 463327, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0136492252349854, "global_step": 463328, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0515663623809814, "global_step": 463329, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.088383674621582, "global_step": 463330, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0834052562713623, "global_step": 463331, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.092341423034668, "global_step": 463332, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1621551513671875, "global_step": 463333, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9966795444488525, "global_step": 463334, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.052353620529175, "global_step": 463335, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.039551258087158, "global_step": 463336, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1603169441223145, "global_step": 463337, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9950896501541138, "global_step": 463338, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1178672313690186, "global_step": 463339, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1204981803894043, "global_step": 463340, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.045307159423828, "global_step": 463341, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.032024621963501, "global_step": 463342, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0123326778411865, "global_step": 463343, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9843882322311401, "global_step": 463344, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.029890537261963, "global_step": 463345, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.06770396232605, "global_step": 463346, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0702438354492188, "global_step": 463347, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0572762489318848, "global_step": 463348, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0608575344085693, "global_step": 463349, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.970766544342041, "global_step": 463350, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.092219591140747, "global_step": 463351, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0379292964935303, "global_step": 463352, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0720536708831787, "global_step": 463353, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.131761074066162, "global_step": 463354, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1100924015045166, "global_step": 463355, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0320849418640137, "global_step": 463356, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.174164295196533, "global_step": 463357, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.102064847946167, "global_step": 463358, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.064394235610962, "global_step": 463359, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1337203979492188, "global_step": 463360, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.046929121017456, "global_step": 463361, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.06412672996521, "global_step": 463362, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0353565216064453, "global_step": 463363, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.145272970199585, "global_step": 463364, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.210503578186035, "global_step": 463365, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0461978912353516, "global_step": 463366, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9909616708755493, "global_step": 463367, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.081367015838623, "global_step": 463368, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0809707641601562, "global_step": 463369, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.014756679534912, "global_step": 463370, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0258662700653076, "global_step": 463371, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0319151878356934, "global_step": 463372, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.123528480529785, "global_step": 463373, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0385398864746094, "global_step": 463374, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0777409076690674, "global_step": 463375, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.080490827560425, "global_step": 463376, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0167996883392334, "global_step": 463377, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.118147373199463, "global_step": 463378, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1279494762420654, "global_step": 463379, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0842511653900146, "global_step": 463380, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9970481395721436, "global_step": 463381, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9966487884521484, "global_step": 463382, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9994239807128906, "global_step": 463383, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.083636999130249, "global_step": 463384, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.068552255630493, "global_step": 463385, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0867018699645996, "global_step": 463386, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.015820264816284, "global_step": 463387, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.035264015197754, "global_step": 463388, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.104430675506592, "global_step": 463389, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.01941180229187, "global_step": 463390, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0759923458099365, "global_step": 463391, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0437426567077637, "global_step": 463392, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0809035301208496, "global_step": 463393, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0508790016174316, "global_step": 463394, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.058739423751831, "global_step": 463395, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0246903896331787, "global_step": 463396, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.065507173538208, "global_step": 463397, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0660388469696045, "global_step": 463398, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.927638292312622, "global_step": 463399, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0206542015075684, "global_step": 463400, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.071587562561035, "global_step": 463401, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.085573196411133, "global_step": 463402, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1255712509155273, "global_step": 463403, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0969769954681396, "global_step": 463404, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9890083074569702, "global_step": 463405, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9919852018356323, "global_step": 463406, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0072920322418213, "global_step": 463407, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9498045444488525, "global_step": 463408, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.945839524269104, "global_step": 463409, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0650718212127686, "global_step": 463410, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1145904064178467, "global_step": 463411, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0934596061706543, "global_step": 463412, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.021934747695923, "global_step": 463413, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0503885746002197, "global_step": 463414, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0890040397644043, "global_step": 463415, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1871495246887207, "global_step": 463416, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9539834260940552, "global_step": 463417, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0961709022521973, "global_step": 463418, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0672988891601562, "global_step": 463419, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0786449909210205, "global_step": 463420, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0364296436309814, "global_step": 463421, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0302140712738037, "global_step": 463422, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1495606899261475, "global_step": 463423, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0970940589904785, "global_step": 463424, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.093921422958374, "global_step": 463425, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0609233379364014, "global_step": 463426, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1105966567993164, "global_step": 463427, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.054626703262329, "global_step": 463428, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0164756774902344, "global_step": 463429, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0100274085998535, "global_step": 463430, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.992565393447876, "global_step": 463431, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0726478099823, "global_step": 463432, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.089183807373047, "global_step": 463433, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.133852958679199, "global_step": 463434, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0611412525177, "global_step": 463435, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.047621250152588, "global_step": 463436, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1373660564422607, "global_step": 463437, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.065023899078369, "global_step": 463438, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.045799970626831, "global_step": 463439, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1095001697540283, "global_step": 463440, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0722920894622803, "global_step": 463441, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0430729389190674, "global_step": 463442, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0922322273254395, "global_step": 463443, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0868470668792725, "global_step": 463444, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1571178436279297, "global_step": 463445, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.076812267303467, "global_step": 463446, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.081239938735962, "global_step": 463447, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0663199424743652, "global_step": 463448, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.040541410446167, "global_step": 463449, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.08809232711792, "global_step": 463450, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1153464317321777, "global_step": 463451, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.023038864135742, "global_step": 463452, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.007202625274658, "global_step": 463453, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0745115280151367, "global_step": 463454, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0676567554473877, "global_step": 463455, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.142904043197632, "global_step": 463456, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.093848943710327, "global_step": 463457, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.096134901046753, "global_step": 463458, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0849902629852295, "global_step": 463459, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.034288167953491, "global_step": 463460, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.13118839263916, "global_step": 463461, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.085650682449341, "global_step": 463462, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0153493881225586, "global_step": 463463, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0211806297302246, "global_step": 463464, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0480048656463623, "global_step": 463465, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.064188241958618, "global_step": 463466, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.017622470855713, "global_step": 463467, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.044370174407959, "global_step": 463468, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0939266681671143, "global_step": 463469, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0906496047973633, "global_step": 463470, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1183526515960693, "global_step": 463471, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.112053632736206, "global_step": 463472, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9959235191345215, "global_step": 463473, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.058242082595825, "global_step": 463474, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1082632541656494, "global_step": 463475, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1210856437683105, "global_step": 463476, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0947864055633545, "global_step": 463477, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.093942642211914, "global_step": 463478, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0499446392059326, "global_step": 463479, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.040613889694214, "global_step": 463480, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1077992916107178, "global_step": 463481, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.95722496509552, "global_step": 463482, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0276436805725098, "global_step": 463483, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1025338172912598, "global_step": 463484, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.052354335784912, "global_step": 463485, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.112346887588501, "global_step": 463486, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0538151264190674, "global_step": 463487, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.113668918609619, "global_step": 463488, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0979645252227783, "global_step": 463489, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0146398544311523, "global_step": 463490, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0753049850463867, "global_step": 463491, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0743308067321777, "global_step": 463492, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1296584606170654, "global_step": 463493, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.016214370727539, "global_step": 463494, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.092937707901001, "global_step": 463495, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0840089321136475, "global_step": 463496, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.081737995147705, "global_step": 463497, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.962524652481079, "global_step": 463498, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1045515537261963, "global_step": 463499, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.02993106842041, "global_step": 463500, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0369653701782227, "global_step": 463501, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0375893115997314, "global_step": 463502, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1058027744293213, "global_step": 463503, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9494237899780273, "global_step": 463504, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0602591037750244, "global_step": 463505, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9454582929611206, "global_step": 463506, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.063711643218994, "global_step": 463507, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.056511878967285, "global_step": 463508, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1231517791748047, "global_step": 463509, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0041680335998535, "global_step": 463510, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.081667184829712, "global_step": 463511, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0719213485717773, "global_step": 463512, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0537796020507812, "global_step": 463513, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.029010772705078, "global_step": 463514, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0689027309417725, "global_step": 463515, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0852184295654297, "global_step": 463516, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1641762256622314, "global_step": 463517, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.091644525527954, "global_step": 463518, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.010293960571289, "global_step": 463519, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0600664615631104, "global_step": 463520, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.078204393386841, "global_step": 463521, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1305365562438965, "global_step": 463522, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0406360626220703, "global_step": 463523, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0776000022888184, "global_step": 463524, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1522467136383057, "global_step": 463525, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0776219367980957, "global_step": 463526, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.089069366455078, "global_step": 463527, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0747692584991455, "global_step": 463528, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.070345640182495, "global_step": 463529, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0538768768310547, "global_step": 463530, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0447072982788086, "global_step": 463531, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.052725076675415, "global_step": 463532, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1008522510528564, "global_step": 463533, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.070423126220703, "global_step": 463534, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.070988893508911, "global_step": 463535, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.038789987564087, "global_step": 463536, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.062501907348633, "global_step": 463537, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.073382616043091, "global_step": 463538, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.092468738555908, "global_step": 463539, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.071141481399536, "global_step": 463540, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.138216972351074, "global_step": 463541, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.080387592315674, "global_step": 463542, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1258528232574463, "global_step": 463543, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.027409553527832, "global_step": 463544, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0396535396575928, "global_step": 463545, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0133273601531982, "global_step": 463546, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.018913507461548, "global_step": 463547, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0234010219573975, "global_step": 463548, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0727806091308594, "global_step": 463549, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9854283332824707, "global_step": 463550, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1273467540740967, "global_step": 463551, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.076390504837036, "global_step": 463552, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1226725578308105, "global_step": 463553, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.047023057937622, "global_step": 463554, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0183510780334473, "global_step": 463555, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0912628173828125, "global_step": 463556, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.059471368789673, "global_step": 463557, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.054811954498291, "global_step": 463558, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0227293968200684, "global_step": 463559, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1242449283599854, "global_step": 463560, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9702978134155273, "global_step": 463561, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.049816846847534, "global_step": 463562, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9544103145599365, "global_step": 463563, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.074463129043579, "global_step": 463564, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1126513481140137, "global_step": 463565, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0929930210113525, "global_step": 463566, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1207056045532227, "global_step": 463567, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0543324947357178, "global_step": 463568, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0700583457946777, "global_step": 463569, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.056502103805542, "global_step": 463570, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0965094566345215, "global_step": 463571, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.096622943878174, "global_step": 463572, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0635299682617188, "global_step": 463573, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.052100896835327, "global_step": 463574, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.123169183731079, "global_step": 463575, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.105543613433838, "global_step": 463576, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.033170461654663, "global_step": 463577, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.117403984069824, "global_step": 463578, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0552918910980225, "global_step": 463579, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0839216709136963, "global_step": 463580, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.109011650085449, "global_step": 463581, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.060107707977295, "global_step": 463582, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0517914295196533, "global_step": 463583, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.10768723487854, "global_step": 463584, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0203299522399902, "global_step": 463585, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0914883613586426, "global_step": 463586, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.118203639984131, "global_step": 463587, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.07265043258667, "global_step": 463588, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0332934856414795, "global_step": 463589, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0371639728546143, "global_step": 463590, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9875112771987915, "global_step": 463591, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.136049509048462, "global_step": 463592, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.138788938522339, "global_step": 463593, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0943048000335693, "global_step": 463594, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.047569751739502, "global_step": 463595, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0730979442596436, "global_step": 463596, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0842156410217285, "global_step": 463597, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0519824028015137, "global_step": 463598, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.070167064666748, "global_step": 463599, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.025190591812134, "global_step": 463600, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.085097312927246, "global_step": 463601, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0103917121887207, "global_step": 463602, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0375144481658936, "global_step": 463603, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0491981506347656, "global_step": 463604, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1438755989074707, "global_step": 463605, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.071627140045166, "global_step": 463606, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.034160852432251, "global_step": 463607, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.107036590576172, "global_step": 463608, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0674376487731934, "global_step": 463609, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.8980172872543335, "global_step": 463610, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0713136196136475, "global_step": 463611, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9638347625732422, "global_step": 463612, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1138763427734375, "global_step": 463613, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9965412616729736, "global_step": 463614, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0630621910095215, "global_step": 463615, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0394821166992188, "global_step": 463616, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.068769693374634, "global_step": 463617, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0673694610595703, "global_step": 463618, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0653316974639893, "global_step": 463619, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.076843738555908, "global_step": 463620, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.079288959503174, "global_step": 463621, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.08492112159729, "global_step": 463622, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0927698612213135, "global_step": 463623, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0675923824310303, "global_step": 463624, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1417551040649414, "global_step": 463625, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0593221187591553, "global_step": 463626, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9902775287628174, "global_step": 463627, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.046964168548584, "global_step": 463628, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0485990047454834, "global_step": 463629, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0026674270629883, "global_step": 463630, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1449475288391113, "global_step": 463631, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0996780395507812, "global_step": 463632, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0633504390716553, "global_step": 463633, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0425806045532227, "global_step": 463634, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0133681297302246, "global_step": 463635, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9710955619812012, "global_step": 463636, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.02361798286438, "global_step": 463637, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.2154974937438965, "global_step": 463638, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.134664297103882, "global_step": 463639, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.08276104927063, "global_step": 463640, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1468067169189453, "global_step": 463641, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.058781862258911, "global_step": 463642, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.084806203842163, "global_step": 463643, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.074202537536621, "global_step": 463644, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.081761598587036, "global_step": 463645, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0673232078552246, "global_step": 463646, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0945935249328613, "global_step": 463647, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0631370544433594, "global_step": 463648, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.049560070037842, "global_step": 463649, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0283474922180176, "global_step": 463650, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.07608962059021, "global_step": 463651, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1821115016937256, "global_step": 463652, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.052063465118408, "global_step": 463653, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0698506832122803, "global_step": 463654, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9638581275939941, "global_step": 463655, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0467677116394043, "global_step": 463656, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.060878038406372, "global_step": 463657, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.029844045639038, "global_step": 463658, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0034823417663574, "global_step": 463659, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.027364492416382, "global_step": 463660, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0708260536193848, "global_step": 463661, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1089940071105957, "global_step": 463662, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0614898204803467, "global_step": 463663, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.062350034713745, "global_step": 463664, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.018265724182129, "global_step": 463665, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0968480110168457, "global_step": 463666, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.095737934112549, "global_step": 463667, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0884435176849365, "global_step": 463668, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.036102294921875, "global_step": 463669, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.04761004447937, "global_step": 463670, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0924603939056396, "global_step": 463671, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.099815607070923, "global_step": 463672, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0740807056427, "global_step": 463673, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0553903579711914, "global_step": 463674, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0632519721984863, "global_step": 463675, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.055220127105713, "global_step": 463676, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.991753101348877, "global_step": 463677, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0764777660369873, "global_step": 463678, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.09230637550354, "global_step": 463679, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0581932067871094, "global_step": 463680, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0318427085876465, "global_step": 463681, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.089688301086426, "global_step": 463682, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.033705949783325, "global_step": 463683, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0397286415100098, "global_step": 463684, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1600286960601807, "global_step": 463685, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.064404010772705, "global_step": 463686, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0467355251312256, "global_step": 463687, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.071226119995117, "global_step": 463688, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.098396062850952, "global_step": 463689, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.989208459854126, "global_step": 463690, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0787289142608643, "global_step": 463691, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.191649913787842, "global_step": 463692, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0815162658691406, "global_step": 463693, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.15712833404541, "global_step": 463694, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.085155963897705, "global_step": 463695, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0353481769561768, "global_step": 463696, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.062258243560791, "global_step": 463697, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0952844619750977, "global_step": 463698, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1428050994873047, "global_step": 463699, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0814836025238037, "global_step": 463700, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0721585750579834, "global_step": 463701, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0275230407714844, "global_step": 463702, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1316380500793457, "global_step": 463703, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0696446895599365, "global_step": 463704, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.033299684524536, "global_step": 463705, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.071662664413452, "global_step": 463706, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0332157611846924, "global_step": 463707, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0430495738983154, "global_step": 463708, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.106499671936035, "global_step": 463709, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1072871685028076, "global_step": 463710, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0481581687927246, "global_step": 463711, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1239066123962402, "global_step": 463712, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9638047218322754, "global_step": 463713, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0275816917419434, "global_step": 463714, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0378525257110596, "global_step": 463715, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0545735359191895, "global_step": 463716, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.088820457458496, "global_step": 463717, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0782551765441895, "global_step": 463718, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9730981588363647, "global_step": 463719, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.018380880355835, "global_step": 463720, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0922555923461914, "global_step": 463721, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0311279296875, "global_step": 463722, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.101335048675537, "global_step": 463723, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9757575988769531, "global_step": 463724, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1028237342834473, "global_step": 463725, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.032430648803711, "global_step": 463726, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9870274066925049, "global_step": 463727, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0926363468170166, "global_step": 463728, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0112030506134033, "global_step": 463729, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1741726398468018, "global_step": 463730, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.055527448654175, "global_step": 463731, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0400378704071045, "global_step": 463732, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1063878536224365, "global_step": 463733, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0626742839813232, "global_step": 463734, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.113253355026245, "global_step": 463735, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9993990659713745, "global_step": 463736, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0985727310180664, "global_step": 463737, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0531070232391357, "global_step": 463738, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.11440110206604, "global_step": 463739, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.07163405418396, "global_step": 463740, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.010162353515625, "global_step": 463741, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0076115131378174, "global_step": 463742, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0461626052856445, "global_step": 463743, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0709314346313477, "global_step": 463744, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.11104679107666, "global_step": 463745, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9471467733383179, "global_step": 463746, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0630042552948, "global_step": 463747, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0351369380950928, "global_step": 463748, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1004843711853027, "global_step": 463749, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0803606510162354, "global_step": 463750, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0078749656677246, "global_step": 463751, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0180742740631104, "global_step": 463752, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0960512161254883, "global_step": 463753, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1363062858581543, "global_step": 463754, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.048670768737793, "global_step": 463755, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.024702548980713, "global_step": 463756, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.095763683319092, "global_step": 463757, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9493186473846436, "global_step": 463758, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.080298662185669, "global_step": 463759, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0327584743499756, "global_step": 463760, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0077478885650635, "global_step": 463761, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9771385192871094, "global_step": 463762, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0377166271209717, "global_step": 463763, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0540823936462402, "global_step": 463764, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0805139541625977, "global_step": 463765, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1330909729003906, "global_step": 463766, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.05444073677063, "global_step": 463767, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0114011764526367, "global_step": 463768, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0733883380889893, "global_step": 463769, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1062331199645996, "global_step": 463770, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1463518142700195, "global_step": 463771, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0732178688049316, "global_step": 463772, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1405019760131836, "global_step": 463773, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0113275051116943, "global_step": 463774, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.161670207977295, "global_step": 463775, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.088130235671997, "global_step": 463776, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0208189487457275, "global_step": 463777, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.134568214416504, "global_step": 463778, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.083704948425293, "global_step": 463779, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1534619331359863, "global_step": 463780, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0602450370788574, "global_step": 463781, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9769392013549805, "global_step": 463782, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.065739154815674, "global_step": 463783, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.138009548187256, "global_step": 463784, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.014763832092285, "global_step": 463785, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.098543405532837, "global_step": 463786, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.105173110961914, "global_step": 463787, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.121734619140625, "global_step": 463788, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1310532093048096, "global_step": 463789, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0526156425476074, "global_step": 463790, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1316657066345215, "global_step": 463791, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0897955894470215, "global_step": 463792, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0315022468566895, "global_step": 463793, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0646421909332275, "global_step": 463794, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.993415355682373, "global_step": 463795, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9655684232711792, "global_step": 463796, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0320076942443848, "global_step": 463797, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.115905284881592, "global_step": 463798, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0701446533203125, "global_step": 463799, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9993447065353394, "global_step": 463800, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.166149854660034, "global_step": 463801, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0659735202789307, "global_step": 463802, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0758635997772217, "global_step": 463803, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0661323070526123, "global_step": 463804, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0748815536499023, "global_step": 463805, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0984854698181152, "global_step": 463806, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0740792751312256, "global_step": 463807, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1192333698272705, "global_step": 463808, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1977758407592773, "global_step": 463809, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.124584913253784, "global_step": 463810, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0320842266082764, "global_step": 463811, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0794293880462646, "global_step": 463812, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.112865447998047, "global_step": 463813, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.161039352416992, "global_step": 463814, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0601396560668945, "global_step": 463815, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.02710223197937, "global_step": 463816, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0319786071777344, "global_step": 463817, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0859925746917725, "global_step": 463818, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1632349491119385, "global_step": 463819, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1088593006134033, "global_step": 463820, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0491528511047363, "global_step": 463821, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1815998554229736, "global_step": 463822, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.087811231613159, "global_step": 463823, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0197336673736572, "global_step": 463824, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9705373048782349, "global_step": 463825, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1636853218078613, "global_step": 463826, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0774309635162354, "global_step": 463827, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.062131881713867, "global_step": 463828, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0143494606018066, "global_step": 463829, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.074899196624756, "global_step": 463830, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.018752098083496, "global_step": 463831, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1247994899749756, "global_step": 463832, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0184664726257324, "global_step": 463833, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.043705701828003, "global_step": 463834, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1069700717926025, "global_step": 463835, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.074904441833496, "global_step": 463836, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.056140661239624, "global_step": 463837, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0692696571350098, "global_step": 463838, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0149166584014893, "global_step": 463839, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.07074236869812, "global_step": 463840, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.07674241065979, "global_step": 463841, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.110579252243042, "global_step": 463842, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.052609443664551, "global_step": 463843, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.979794979095459, "global_step": 463844, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.150829792022705, "global_step": 463845, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.141533851623535, "global_step": 463846, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0539166927337646, "global_step": 463847, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1224606037139893, "global_step": 463848, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1487531661987305, "global_step": 463849, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0621562004089355, "global_step": 463850, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.021554470062256, "global_step": 463851, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9727742671966553, "global_step": 463852, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0274460315704346, "global_step": 463853, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.043095111846924, "global_step": 463854, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0561904907226562, "global_step": 463855, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1038098335266113, "global_step": 463856, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0160751342773438, "global_step": 463857, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9974623918533325, "global_step": 463858, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.053593873977661, "global_step": 463859, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1052255630493164, "global_step": 463860, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1607649326324463, "global_step": 463861, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1280157566070557, "global_step": 463862, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0667426586151123, "global_step": 463863, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1413991451263428, "global_step": 463864, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0517866611480713, "global_step": 463865, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.122357130050659, "global_step": 463866, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1176319122314453, "global_step": 463867, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0777015686035156, "global_step": 463868, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0160367488861084, "global_step": 463869, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.071171522140503, "global_step": 463870, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.045811653137207, "global_step": 463871, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.196929931640625, "global_step": 463872, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9731398820877075, "global_step": 463873, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.137084484100342, "global_step": 463874, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.048696517944336, "global_step": 463875, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.992850422859192, "global_step": 463876, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0832622051239014, "global_step": 463877, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0522642135620117, "global_step": 463878, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0552942752838135, "global_step": 463879, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0204739570617676, "global_step": 463880, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1496763229370117, "global_step": 463881, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0580894947052, "global_step": 463882, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.063502550125122, "global_step": 463883, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0995914936065674, "global_step": 463884, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0139524936676025, "global_step": 463885, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.051053524017334, "global_step": 463886, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0710785388946533, "global_step": 463887, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0094971656799316, "global_step": 463888, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.148411989212036, "global_step": 463889, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1092824935913086, "global_step": 463890, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.083244800567627, "global_step": 463891, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.055842399597168, "global_step": 463892, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0911073684692383, "global_step": 463893, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.077230930328369, "global_step": 463894, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0483906269073486, "global_step": 463895, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0936152935028076, "global_step": 463896, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.078256368637085, "global_step": 463897, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1238372325897217, "global_step": 463898, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0875377655029297, "global_step": 463899, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.071892261505127, "global_step": 463900, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.043372869491577, "global_step": 463901, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1340858936309814, "global_step": 463902, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0072593688964844, "global_step": 463903, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1040732860565186, "global_step": 463904, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.994529366493225, "global_step": 463905, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1479380130767822, "global_step": 463906, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.118584156036377, "global_step": 463907, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0400328636169434, "global_step": 463908, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0788261890411377, "global_step": 463909, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0633091926574707, "global_step": 463910, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.129734754562378, "global_step": 463911, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0101051330566406, "global_step": 463912, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0629684925079346, "global_step": 463913, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.088491201400757, "global_step": 463914, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.075731039047241, "global_step": 463915, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0529096126556396, "global_step": 463916, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0657503604888916, "global_step": 463917, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0500943660736084, "global_step": 463918, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.046265125274658, "global_step": 463919, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0452382564544678, "global_step": 463920, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.133225202560425, "global_step": 463921, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0180740356445312, "global_step": 463922, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0495572090148926, "global_step": 463923, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1232218742370605, "global_step": 463924, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0427606105804443, "global_step": 463925, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.164639711380005, "global_step": 463926, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0791890621185303, "global_step": 463927, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0276260375976562, "global_step": 463928, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1030080318450928, "global_step": 463929, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0572681427001953, "global_step": 463930, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.117086887359619, "global_step": 463931, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0869078636169434, "global_step": 463932, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1426467895507812, "global_step": 463933, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0279862880706787, "global_step": 463934, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.2011334896087646, "global_step": 463935, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.118947982788086, "global_step": 463936, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0471763610839844, "global_step": 463937, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0569427013397217, "global_step": 463938, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.099008083343506, "global_step": 463939, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0298688411712646, "global_step": 463940, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.075073480606079, "global_step": 463941, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.2044060230255127, "global_step": 463942, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0700509548187256, "global_step": 463943, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0678491592407227, "global_step": 463944, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.102504014968872, "global_step": 463945, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0674569606781006, "global_step": 463946, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.077000141143799, "global_step": 463947, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0920419692993164, "global_step": 463948, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0696613788604736, "global_step": 463949, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1415493488311768, "global_step": 463950, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.996112585067749, "global_step": 463951, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.055868625640869, "global_step": 463952, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9759215116500854, "global_step": 463953, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0759530067443848, "global_step": 463954, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0010793209075928, "global_step": 463955, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0922088623046875, "global_step": 463956, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0698509216308594, "global_step": 463957, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.045848846435547, "global_step": 463958, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0676064491271973, "global_step": 463959, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.099269151687622, "global_step": 463960, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.008850574493408, "global_step": 463961, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0552098751068115, "global_step": 463962, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0458426475524902, "global_step": 463963, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0884835720062256, "global_step": 463964, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.072845220565796, "global_step": 463965, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0179734230041504, "global_step": 463966, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.006105899810791, "global_step": 463967, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.06540584564209, "global_step": 463968, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.153944969177246, "global_step": 463969, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0335865020751953, "global_step": 463970, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0526373386383057, "global_step": 463971, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0848052501678467, "global_step": 463972, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0061111450195312, "global_step": 463973, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.113128662109375, "global_step": 463974, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0982561111450195, "global_step": 463975, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0028128623962402, "global_step": 463976, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.060504913330078, "global_step": 463977, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.000642776489258, "global_step": 463978, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.079413652420044, "global_step": 463979, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1052870750427246, "global_step": 463980, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0988235473632812, "global_step": 463981, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0038065910339355, "global_step": 463982, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0713813304901123, "global_step": 463983, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.108215093612671, "global_step": 463984, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.970932960510254, "global_step": 463985, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.104278564453125, "global_step": 463986, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.010683536529541, "global_step": 463987, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.072110652923584, "global_step": 463988, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0999178886413574, "global_step": 463989, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.031792640686035, "global_step": 463990, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.109562397003174, "global_step": 463991, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0824639797210693, "global_step": 463992, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.108064651489258, "global_step": 463993, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1093616485595703, "global_step": 463994, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1592440605163574, "global_step": 463995, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1591663360595703, "global_step": 463996, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0963125228881836, "global_step": 463997, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0871806144714355, "global_step": 463998, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.178684711456299, "global_step": 463999, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.052825689315796, "global_step": 464000, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.057068347930908, "global_step": 464001, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0328173637390137, "global_step": 464002, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.060598373413086, "global_step": 464003, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.128664255142212, "global_step": 464004, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1309144496917725, "global_step": 464005, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.060370445251465, "global_step": 464006, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.124345064163208, "global_step": 464007, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0197432041168213, "global_step": 464008, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0129354000091553, "global_step": 464009, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9556872844696045, "global_step": 464010, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0290520191192627, "global_step": 464011, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.06435227394104, "global_step": 464012, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0393364429473877, "global_step": 464013, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0289385318756104, "global_step": 464014, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1434855461120605, "global_step": 464015, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1151177883148193, "global_step": 464016, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.011867046356201, "global_step": 464017, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.076903820037842, "global_step": 464018, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1002063751220703, "global_step": 464019, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0883779525756836, "global_step": 464020, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0883395671844482, "global_step": 464021, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9831774234771729, "global_step": 464022, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0327181816101074, "global_step": 464023, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.050933361053467, "global_step": 464024, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1054606437683105, "global_step": 464025, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1131062507629395, "global_step": 464026, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.117354393005371, "global_step": 464027, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.093463659286499, "global_step": 464028, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1200597286224365, "global_step": 464029, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.100421667098999, "global_step": 464030, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.127469301223755, "global_step": 464031, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.165879964828491, "global_step": 464032, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9902420043945312, "global_step": 464033, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0486838817596436, "global_step": 464034, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.166888952255249, "global_step": 464035, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.04994797706604, "global_step": 464036, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.200570583343506, "global_step": 464037, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1280884742736816, "global_step": 464038, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0769290924072266, "global_step": 464039, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.046959638595581, "global_step": 464040, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.094811201095581, "global_step": 464041, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.990505337715149, "global_step": 464042, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1006546020507812, "global_step": 464043, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0244553089141846, "global_step": 464044, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.090075731277466, "global_step": 464045, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0672783851623535, "global_step": 464046, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9171528816223145, "global_step": 464047, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0390591621398926, "global_step": 464048, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.063713788986206, "global_step": 464049, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.074787139892578, "global_step": 464050, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1258864402770996, "global_step": 464051, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1119751930236816, "global_step": 464052, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.004356861114502, "global_step": 464053, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9969282150268555, "global_step": 464054, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1579854488372803, "global_step": 464055, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1031978130340576, "global_step": 464056, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.061737060546875, "global_step": 464057, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0421454906463623, "global_step": 464058, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1040334701538086, "global_step": 464059, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0947930812835693, "global_step": 464060, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1085288524627686, "global_step": 464061, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.055745840072632, "global_step": 464062, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0278022289276123, "global_step": 464063, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.076098680496216, "global_step": 464064, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.05977463722229, "global_step": 464065, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1387205123901367, "global_step": 464066, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0241825580596924, "global_step": 464067, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0515787601470947, "global_step": 464068, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.111370325088501, "global_step": 464069, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.033017158508301, "global_step": 464070, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9696435928344727, "global_step": 464071, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.050729990005493, "global_step": 464072, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0222084522247314, "global_step": 464073, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1213018894195557, "global_step": 464074, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.092819929122925, "global_step": 464075, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.150787353515625, "global_step": 464076, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.077754497528076, "global_step": 464077, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9660359621047974, "global_step": 464078, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.128154993057251, "global_step": 464079, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0680551528930664, "global_step": 464080, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.107081890106201, "global_step": 464081, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1448895931243896, "global_step": 464082, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.2061405181884766, "global_step": 464083, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1254847049713135, "global_step": 464084, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.057725429534912, "global_step": 464085, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0794432163238525, "global_step": 464086, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.001340866088867, "global_step": 464087, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0410196781158447, "global_step": 464088, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.049652099609375, "global_step": 464089, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.158731460571289, "global_step": 464090, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.036564826965332, "global_step": 464091, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.027726888656616, "global_step": 464092, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.030290126800537, "global_step": 464093, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1191301345825195, "global_step": 464094, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0555503368377686, "global_step": 464095, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.169349431991577, "global_step": 464096, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0008060932159424, "global_step": 464097, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0601634979248047, "global_step": 464098, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0921905040740967, "global_step": 464099, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.111820936203003, "global_step": 464100, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0088706016540527, "global_step": 464101, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0293467044830322, "global_step": 464102, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.100046396255493, "global_step": 464103, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0088372230529785, "global_step": 464104, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0888419151306152, "global_step": 464105, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.119401454925537, "global_step": 464106, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.050213575363159, "global_step": 464107, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1463637351989746, "global_step": 464108, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1439383029937744, "global_step": 464109, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.035490036010742, "global_step": 464110, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9960720539093018, "global_step": 464111, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.022394895553589, "global_step": 464112, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0830652713775635, "global_step": 464113, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1257734298706055, "global_step": 464114, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.10697340965271, "global_step": 464115, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1089582443237305, "global_step": 464116, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1123626232147217, "global_step": 464117, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1325788497924805, "global_step": 464118, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0427656173706055, "global_step": 464119, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.039740800857544, "global_step": 464120, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0526764392852783, "global_step": 464121, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0459415912628174, "global_step": 464122, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0736184120178223, "global_step": 464123, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1557912826538086, "global_step": 464124, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.118845224380493, "global_step": 464125, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.039658546447754, "global_step": 464126, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0816595554351807, "global_step": 464127, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0905957221984863, "global_step": 464128, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0094597339630127, "global_step": 464129, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0161798000335693, "global_step": 464130, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0750303268432617, "global_step": 464131, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0376853942871094, "global_step": 464132, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1047492027282715, "global_step": 464133, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9866268634796143, "global_step": 464134, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9901551008224487, "global_step": 464135, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1087121963500977, "global_step": 464136, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1123759746551514, "global_step": 464137, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0248823165893555, "global_step": 464138, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.049586534500122, "global_step": 464139, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1293158531188965, "global_step": 464140, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9656111001968384, "global_step": 464141, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.127547025680542, "global_step": 464142, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0775976181030273, "global_step": 464143, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1359543800354004, "global_step": 464144, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.050649642944336, "global_step": 464145, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1457037925720215, "global_step": 464146, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0727715492248535, "global_step": 464147, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1148910522460938, "global_step": 464148, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.007599353790283, "global_step": 464149, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9887163639068604, "global_step": 464150, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0821893215179443, "global_step": 464151, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.042208433151245, "global_step": 464152, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1061365604400635, "global_step": 464153, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.077084541320801, "global_step": 464154, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0474565029144287, "global_step": 464155, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0257718563079834, "global_step": 464156, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0379109382629395, "global_step": 464157, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0787668228149414, "global_step": 464158, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.066481828689575, "global_step": 464159, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0971946716308594, "global_step": 464160, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1359450817108154, "global_step": 464161, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.078082323074341, "global_step": 464162, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1820576190948486, "global_step": 464163, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.144577980041504, "global_step": 464164, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0902724266052246, "global_step": 464165, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.108880043029785, "global_step": 464166, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.009429931640625, "global_step": 464167, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.106619358062744, "global_step": 464168, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1049954891204834, "global_step": 464169, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.092508554458618, "global_step": 464170, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.126922845840454, "global_step": 464171, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.082397699356079, "global_step": 464172, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.02531361579895, "global_step": 464173, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0643885135650635, "global_step": 464174, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0981106758117676, "global_step": 464175, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.098064661026001, "global_step": 464176, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.164609909057617, "global_step": 464177, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0478482246398926, "global_step": 464178, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1448543071746826, "global_step": 464179, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.042151689529419, "global_step": 464180, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.974106788635254, "global_step": 464181, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.161978244781494, "global_step": 464182, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9545552730560303, "global_step": 464183, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.109696865081787, "global_step": 464184, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0144147872924805, "global_step": 464185, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0902228355407715, "global_step": 464186, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.044891357421875, "global_step": 464187, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.104322671890259, "global_step": 464188, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0308430194854736, "global_step": 464189, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1063649654388428, "global_step": 464190, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.980025053024292, "global_step": 464191, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1255056858062744, "global_step": 464192, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.088620185852051, "global_step": 464193, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0790295600891113, "global_step": 464194, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0446927547454834, "global_step": 464195, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1111080646514893, "global_step": 464196, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0315306186676025, "global_step": 464197, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.066060781478882, "global_step": 464198, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.054413318634033, "global_step": 464199, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.148287296295166, "global_step": 464200, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9668382406234741, "global_step": 464201, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9569379091262817, "global_step": 464202, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.122495174407959, "global_step": 464203, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1121912002563477, "global_step": 464204, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.140536308288574, "global_step": 464205, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.08176589012146, "global_step": 464206, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0301616191864014, "global_step": 464207, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.064913034439087, "global_step": 464208, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1003479957580566, "global_step": 464209, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.007852554321289, "global_step": 464210, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0978281497955322, "global_step": 464211, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0448997020721436, "global_step": 464212, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9922113418579102, "global_step": 464213, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9679685831069946, "global_step": 464214, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.045520782470703, "global_step": 464215, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1279282569885254, "global_step": 464216, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.147564649581909, "global_step": 464217, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.061056613922119, "global_step": 464218, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.046302556991577, "global_step": 464219, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.105583429336548, "global_step": 464220, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.112631320953369, "global_step": 464221, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1516032218933105, "global_step": 464222, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0241684913635254, "global_step": 464223, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1017959117889404, "global_step": 464224, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.02361798286438, "global_step": 464225, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.041072130203247, "global_step": 464226, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0006773471832275, "global_step": 464227, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1035566329956055, "global_step": 464228, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1410815715789795, "global_step": 464229, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1196634769439697, "global_step": 464230, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.095609426498413, "global_step": 464231, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0558295249938965, "global_step": 464232, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1101388931274414, "global_step": 464233, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0943198204040527, "global_step": 464234, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9626456499099731, "global_step": 464235, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1054134368896484, "global_step": 464236, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0429606437683105, "global_step": 464237, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0828986167907715, "global_step": 464238, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.022692918777466, "global_step": 464239, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.201995849609375, "global_step": 464240, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.103355646133423, "global_step": 464241, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0780906677246094, "global_step": 464242, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1842010021209717, "global_step": 464243, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.088639259338379, "global_step": 464244, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0228254795074463, "global_step": 464245, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0449984073638916, "global_step": 464246, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9797965288162231, "global_step": 464247, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0694689750671387, "global_step": 464248, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.127037525177002, "global_step": 464249, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.144266366958618, "global_step": 464250, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.045165538787842, "global_step": 464251, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.048494577407837, "global_step": 464252, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0070672035217285, "global_step": 464253, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.019442319869995, "global_step": 464254, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9902478456497192, "global_step": 464255, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0514752864837646, "global_step": 464256, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.113285541534424, "global_step": 464257, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1059961318969727, "global_step": 464258, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0240273475646973, "global_step": 464259, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.087127923965454, "global_step": 464260, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0867533683776855, "global_step": 464261, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0484530925750732, "global_step": 464262, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0651657581329346, "global_step": 464263, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0747947692871094, "global_step": 464264, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0676920413970947, "global_step": 464265, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.122917413711548, "global_step": 464266, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0492501258850098, "global_step": 464267, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1097824573516846, "global_step": 464268, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0785861015319824, "global_step": 464269, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0567216873168945, "global_step": 464270, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1372859477996826, "global_step": 464271, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0651662349700928, "global_step": 464272, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0146732330322266, "global_step": 464273, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0294389724731445, "global_step": 464274, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.1172573566436768, "global_step": 464275, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0309722423553467, "global_step": 464276, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0492050647735596, "global_step": 464277, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.032179594039917, "global_step": 464278, "epoch": 828, "lr": 5e-05}
{"train_loss": 1.9956085681915283, "global_step": 464279, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.091489791870117, "global_step": 464280, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.129438638687134, "global_step": 464281, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0321340560913086, "global_step": 464282, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0693280696868896, "global_step": 464283, "epoch": 828, "lr": 5e-05}
{"train_loss": 2.0520007610321045, "global_step": 464284, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0682547092437744, "global_step": 464285, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0318944454193115, "global_step": 464286, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.979742169380188, "global_step": 464287, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0063655376434326, "global_step": 464288, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0617408752441406, "global_step": 464289, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0246849060058594, "global_step": 464290, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.020914077758789, "global_step": 464291, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.110217571258545, "global_step": 464292, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.136199951171875, "global_step": 464293, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.027379035949707, "global_step": 464294, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.076267957687378, "global_step": 464295, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0137908458709717, "global_step": 464296, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0459842681884766, "global_step": 464297, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.058444023132324, "global_step": 464298, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.10245680809021, "global_step": 464299, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0701282024383545, "global_step": 464300, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.112360954284668, "global_step": 464301, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1323952674865723, "global_step": 464302, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1024608612060547, "global_step": 464303, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.026848793029785, "global_step": 464304, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0184645652770996, "global_step": 464305, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0292913913726807, "global_step": 464306, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.127164840698242, "global_step": 464307, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.009725332260132, "global_step": 464308, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9917892217636108, "global_step": 464309, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.015854597091675, "global_step": 464310, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.097562789916992, "global_step": 464311, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.016547679901123, "global_step": 464312, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9972673654556274, "global_step": 464313, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.091174602508545, "global_step": 464314, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.041388511657715, "global_step": 464315, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.054872751235962, "global_step": 464316, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0543949604034424, "global_step": 464317, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.123901844024658, "global_step": 464318, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.113926410675049, "global_step": 464319, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0824992656707764, "global_step": 464320, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0194926261901855, "global_step": 464321, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.201789140701294, "global_step": 464322, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.022796154022217, "global_step": 464323, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0884294509887695, "global_step": 464324, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0696358680725098, "global_step": 464325, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0582363605499268, "global_step": 464326, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.060636281967163, "global_step": 464327, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.110374689102173, "global_step": 464328, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.081528902053833, "global_step": 464329, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.076483726501465, "global_step": 464330, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1949121952056885, "global_step": 464331, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.105872869491577, "global_step": 464332, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1067495346069336, "global_step": 464333, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0345702171325684, "global_step": 464334, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0300819873809814, "global_step": 464335, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.062429904937744, "global_step": 464336, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1077206134796143, "global_step": 464337, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0522396564483643, "global_step": 464338, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.111392021179199, "global_step": 464339, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.07283353805542, "global_step": 464340, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1140944957733154, "global_step": 464341, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.003386974334717, "global_step": 464342, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1061227321624756, "global_step": 464343, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9917607307434082, "global_step": 464344, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0506837368011475, "global_step": 464345, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0141773223876953, "global_step": 464346, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0722904205322266, "global_step": 464347, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0944271087646484, "global_step": 464348, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.030602216720581, "global_step": 464349, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0027709007263184, "global_step": 464350, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0169548988342285, "global_step": 464351, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.136058807373047, "global_step": 464352, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.029813528060913, "global_step": 464353, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9352881908416748, "global_step": 464354, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0694515705108643, "global_step": 464355, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0327489376068115, "global_step": 464356, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1167898178100586, "global_step": 464357, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0313336849212646, "global_step": 464358, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0707950592041016, "global_step": 464359, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0245916843414307, "global_step": 464360, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.986227035522461, "global_step": 464361, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0745716094970703, "global_step": 464362, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.001939296722412, "global_step": 464363, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.10727596282959, "global_step": 464364, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0233609676361084, "global_step": 464365, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0316925048828125, "global_step": 464366, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.959203839302063, "global_step": 464367, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0935816764831543, "global_step": 464368, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1276094913482666, "global_step": 464369, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9444338083267212, "global_step": 464370, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9565157890319824, "global_step": 464371, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.016019582748413, "global_step": 464372, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0525858402252197, "global_step": 464373, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.104156017303467, "global_step": 464374, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.103522539138794, "global_step": 464375, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.059187889099121, "global_step": 464376, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1080310344696045, "global_step": 464377, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0501623153686523, "global_step": 464378, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.965526819229126, "global_step": 464379, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.122422933578491, "global_step": 464380, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0580086708068848, "global_step": 464381, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.041826009750366, "global_step": 464382, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0727319717407227, "global_step": 464383, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.040233612060547, "global_step": 464384, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.11031174659729, "global_step": 464385, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0038387775421143, "global_step": 464386, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.015753984451294, "global_step": 464387, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9949167966842651, "global_step": 464388, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1081855297088623, "global_step": 464389, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0892505645751953, "global_step": 464390, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.101095676422119, "global_step": 464391, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1131789684295654, "global_step": 464392, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.072591543197632, "global_step": 464393, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.019775152206421, "global_step": 464394, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.195822238922119, "global_step": 464395, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1045594215393066, "global_step": 464396, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.090695381164551, "global_step": 464397, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0821409225463867, "global_step": 464398, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.101130962371826, "global_step": 464399, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.105282783508301, "global_step": 464400, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.054783344268799, "global_step": 464401, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.996616005897522, "global_step": 464402, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.992490530014038, "global_step": 464403, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0126702785491943, "global_step": 464404, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.060447931289673, "global_step": 464405, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0950942039489746, "global_step": 464406, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.090369939804077, "global_step": 464407, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.007035970687866, "global_step": 464408, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.135507106781006, "global_step": 464409, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0564491748809814, "global_step": 464410, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.961409330368042, "global_step": 464411, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9375593662261963, "global_step": 464412, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.162809133529663, "global_step": 464413, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0112388134002686, "global_step": 464414, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1023712158203125, "global_step": 464415, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0402615070343018, "global_step": 464416, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.030172348022461, "global_step": 464417, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1248106956481934, "global_step": 464418, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.104811668395996, "global_step": 464419, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0910303592681885, "global_step": 464420, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0496973991394043, "global_step": 464421, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0658397674560547, "global_step": 464422, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1388587951660156, "global_step": 464423, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.080979585647583, "global_step": 464424, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.091634750366211, "global_step": 464425, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.125293254852295, "global_step": 464426, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1244614124298096, "global_step": 464427, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9838452339172363, "global_step": 464428, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.164513349533081, "global_step": 464429, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1296563148498535, "global_step": 464430, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9778687953948975, "global_step": 464431, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0457112789154053, "global_step": 464432, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.046658754348755, "global_step": 464433, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1092946529388428, "global_step": 464434, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.985108733177185, "global_step": 464435, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.047891855239868, "global_step": 464436, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.945515751838684, "global_step": 464437, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0239784717559814, "global_step": 464438, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.089275598526001, "global_step": 464439, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0928845405578613, "global_step": 464440, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0174384117126465, "global_step": 464441, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.012183904647827, "global_step": 464442, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.049513339996338, "global_step": 464443, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.049847364425659, "global_step": 464444, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9871976375579834, "global_step": 464445, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0697426795959473, "global_step": 464446, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.137338638305664, "global_step": 464447, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0207457542419434, "global_step": 464448, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0024161338806152, "global_step": 464449, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.144787073135376, "global_step": 464450, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.049694299697876, "global_step": 464451, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0209429264068604, "global_step": 464452, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.073026180267334, "global_step": 464453, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.017301321029663, "global_step": 464454, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0043485164642334, "global_step": 464455, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.057884693145752, "global_step": 464456, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.059842109680176, "global_step": 464457, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.034233331680298, "global_step": 464458, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.091806173324585, "global_step": 464459, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.013477087020874, "global_step": 464460, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.131535530090332, "global_step": 464461, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.065399169921875, "global_step": 464462, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.005896806716919, "global_step": 464463, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.046135663986206, "global_step": 464464, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1058082580566406, "global_step": 464465, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.157837152481079, "global_step": 464466, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0659546852111816, "global_step": 464467, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0455479621887207, "global_step": 464468, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1216769218444824, "global_step": 464469, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0673935413360596, "global_step": 464470, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0191516876220703, "global_step": 464471, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.03973126411438, "global_step": 464472, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.046990394592285, "global_step": 464473, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9984902143478394, "global_step": 464474, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0722460746765137, "global_step": 464475, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0846383571624756, "global_step": 464476, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0058035850524902, "global_step": 464477, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0178489685058594, "global_step": 464478, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0503475666046143, "global_step": 464479, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.090067148208618, "global_step": 464480, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9894700050354004, "global_step": 464481, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.991675615310669, "global_step": 464482, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1012794971466064, "global_step": 464483, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0586016178131104, "global_step": 464484, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1002426147460938, "global_step": 464485, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.033648729324341, "global_step": 464486, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0470497608184814, "global_step": 464487, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9913525581359863, "global_step": 464488, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0560569763183594, "global_step": 464489, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0998103618621826, "global_step": 464490, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0710747241973877, "global_step": 464491, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.200997829437256, "global_step": 464492, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0582613945007324, "global_step": 464493, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0609564781188965, "global_step": 464494, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0980587005615234, "global_step": 464495, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0775179862976074, "global_step": 464496, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1717286109924316, "global_step": 464497, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0174853801727295, "global_step": 464498, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0554099082946777, "global_step": 464499, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0340664386749268, "global_step": 464500, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1293139457702637, "global_step": 464501, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0047082901000977, "global_step": 464502, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1072676181793213, "global_step": 464503, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1080615520477295, "global_step": 464504, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0514166355133057, "global_step": 464505, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.997552752494812, "global_step": 464506, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.022202968597412, "global_step": 464507, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1537270545959473, "global_step": 464508, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1072041988372803, "global_step": 464509, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0426392555236816, "global_step": 464510, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0874338150024414, "global_step": 464511, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0666229724884033, "global_step": 464512, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.094942569732666, "global_step": 464513, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0575015544891357, "global_step": 464514, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.030229091644287, "global_step": 464515, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.055889844894409, "global_step": 464516, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1657586097717285, "global_step": 464517, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.040776252746582, "global_step": 464518, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0627784729003906, "global_step": 464519, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.119403839111328, "global_step": 464520, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9983936548233032, "global_step": 464521, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0021400451660156, "global_step": 464522, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0709164142608643, "global_step": 464523, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0615363121032715, "global_step": 464524, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.122173309326172, "global_step": 464525, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1605961322784424, "global_step": 464526, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0854623317718506, "global_step": 464527, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0446982383728027, "global_step": 464528, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.089191436767578, "global_step": 464529, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.062251091003418, "global_step": 464530, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.043788194656372, "global_step": 464531, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.036140203475952, "global_step": 464532, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.091322898864746, "global_step": 464533, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.092515707015991, "global_step": 464534, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0958049297332764, "global_step": 464535, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0360782146453857, "global_step": 464536, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9488873481750488, "global_step": 464537, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.977734088897705, "global_step": 464538, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.108494520187378, "global_step": 464539, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1312477588653564, "global_step": 464540, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.118096113204956, "global_step": 464541, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0791141986846924, "global_step": 464542, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.09428071975708, "global_step": 464543, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.05077862739563, "global_step": 464544, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0070817470550537, "global_step": 464545, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0891926288604736, "global_step": 464546, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.107069492340088, "global_step": 464547, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0605032444000244, "global_step": 464548, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.10402774810791, "global_step": 464549, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.14035701751709, "global_step": 464550, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0265331268310547, "global_step": 464551, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.087667465209961, "global_step": 464552, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0615897178649902, "global_step": 464553, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.062065601348877, "global_step": 464554, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0486650466918945, "global_step": 464555, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0657734870910645, "global_step": 464556, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.090625524520874, "global_step": 464557, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.139744281768799, "global_step": 464558, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.130838632583618, "global_step": 464559, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1091527938842773, "global_step": 464560, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.017099380493164, "global_step": 464561, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.092738151550293, "global_step": 464562, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.040809392929077, "global_step": 464563, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.085765838623047, "global_step": 464564, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.078143358230591, "global_step": 464565, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0525481700897217, "global_step": 464566, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.081770896911621, "global_step": 464567, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.092238426208496, "global_step": 464568, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0668745040893555, "global_step": 464569, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1075727939605713, "global_step": 464570, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0868101119995117, "global_step": 464571, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.029614210128784, "global_step": 464572, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.063382863998413, "global_step": 464573, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0885443687438965, "global_step": 464574, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0894486904144287, "global_step": 464575, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1112022399902344, "global_step": 464576, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1413872241973877, "global_step": 464577, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0440480709075928, "global_step": 464578, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0667426586151123, "global_step": 464579, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0857045650482178, "global_step": 464580, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.070704936981201, "global_step": 464581, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.114755392074585, "global_step": 464582, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9906792640686035, "global_step": 464583, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0174248218536377, "global_step": 464584, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1180026531219482, "global_step": 464585, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0218045711517334, "global_step": 464586, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0115551948547363, "global_step": 464587, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1332805156707764, "global_step": 464588, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.048147439956665, "global_step": 464589, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0772743225097656, "global_step": 464590, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0356357097625732, "global_step": 464591, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.078173875808716, "global_step": 464592, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.098353624343872, "global_step": 464593, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.135209321975708, "global_step": 464594, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0277607440948486, "global_step": 464595, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1722469329833984, "global_step": 464596, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.118213653564453, "global_step": 464597, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.042337656021118, "global_step": 464598, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9977747201919556, "global_step": 464599, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0868442058563232, "global_step": 464600, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.056739091873169, "global_step": 464601, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.148071050643921, "global_step": 464602, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0524098873138428, "global_step": 464603, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.2057344913482666, "global_step": 464604, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.014810085296631, "global_step": 464605, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0688469409942627, "global_step": 464606, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1070120334625244, "global_step": 464607, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1215131282806396, "global_step": 464608, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0740864276885986, "global_step": 464609, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.035879611968994, "global_step": 464610, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0365183353424072, "global_step": 464611, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.117323637008667, "global_step": 464612, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1515307426452637, "global_step": 464613, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0711021423339844, "global_step": 464614, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0644917488098145, "global_step": 464615, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.073455572128296, "global_step": 464616, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.100658893585205, "global_step": 464617, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.222043037414551, "global_step": 464618, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0594797134399414, "global_step": 464619, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0813493728637695, "global_step": 464620, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1160693168640137, "global_step": 464621, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1031482219696045, "global_step": 464622, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1253573894500732, "global_step": 464623, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.109618663787842, "global_step": 464624, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.081268548965454, "global_step": 464625, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.056535482406616, "global_step": 464626, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.066213846206665, "global_step": 464627, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.029299736022949, "global_step": 464628, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0186736583709717, "global_step": 464629, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.064704418182373, "global_step": 464630, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9910352230072021, "global_step": 464631, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0567147731781006, "global_step": 464632, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0431816577911377, "global_step": 464633, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0018622875213623, "global_step": 464634, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.998681902885437, "global_step": 464635, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0531110763549805, "global_step": 464636, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.034482479095459, "global_step": 464637, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9731717109680176, "global_step": 464638, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0157978534698486, "global_step": 464639, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0251896381378174, "global_step": 464640, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.098761558532715, "global_step": 464641, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0562427043914795, "global_step": 464642, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0302751064300537, "global_step": 464643, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.028024196624756, "global_step": 464644, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0699610710144043, "global_step": 464645, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0373551845550537, "global_step": 464646, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.094984769821167, "global_step": 464647, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0630481243133545, "global_step": 464648, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.066094398498535, "global_step": 464649, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.085946798324585, "global_step": 464650, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9443893432617188, "global_step": 464651, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0497477054595947, "global_step": 464652, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.074275016784668, "global_step": 464653, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.093100070953369, "global_step": 464654, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0733914375305176, "global_step": 464655, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.009471893310547, "global_step": 464656, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0627870559692383, "global_step": 464657, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1040396690368652, "global_step": 464658, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.075396776199341, "global_step": 464659, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9893972873687744, "global_step": 464660, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0540950298309326, "global_step": 464661, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.057450294494629, "global_step": 464662, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.047720193862915, "global_step": 464663, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.123891592025757, "global_step": 464664, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0444257259368896, "global_step": 464665, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0397326946258545, "global_step": 464666, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0748343467712402, "global_step": 464667, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.153184652328491, "global_step": 464668, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9591208696365356, "global_step": 464669, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.051140308380127, "global_step": 464670, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.027428388595581, "global_step": 464671, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0572431087493896, "global_step": 464672, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.073366641998291, "global_step": 464673, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0000016689300537, "global_step": 464674, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0916173458099365, "global_step": 464675, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0914061069488525, "global_step": 464676, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0190773010253906, "global_step": 464677, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0552937984466553, "global_step": 464678, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0298776626586914, "global_step": 464679, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.071256637573242, "global_step": 464680, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0459678173065186, "global_step": 464681, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.01678466796875, "global_step": 464682, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.096248149871826, "global_step": 464683, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1807119846343994, "global_step": 464684, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1332476139068604, "global_step": 464685, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1230387687683105, "global_step": 464686, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.02728533744812, "global_step": 464687, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.007404088973999, "global_step": 464688, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0376791954040527, "global_step": 464689, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1002557277679443, "global_step": 464690, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.025846004486084, "global_step": 464691, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.032620668411255, "global_step": 464692, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9841235876083374, "global_step": 464693, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.038238525390625, "global_step": 464694, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0649704933166504, "global_step": 464695, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1371612548828125, "global_step": 464696, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0774521827697754, "global_step": 464697, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.114877939224243, "global_step": 464698, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.942865014076233, "global_step": 464699, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.062844753265381, "global_step": 464700, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0864012241363525, "global_step": 464701, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.040766477584839, "global_step": 464702, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.111750841140747, "global_step": 464703, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.118257999420166, "global_step": 464704, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.016165018081665, "global_step": 464705, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0632193088531494, "global_step": 464706, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.994360089302063, "global_step": 464707, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.003276824951172, "global_step": 464708, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0479602813720703, "global_step": 464709, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.985632061958313, "global_step": 464710, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0299506187438965, "global_step": 464711, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.087548017501831, "global_step": 464712, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0504748821258545, "global_step": 464713, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0219693183898926, "global_step": 464714, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1045145988464355, "global_step": 464715, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9982519149780273, "global_step": 464716, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1109743118286133, "global_step": 464717, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0724871158599854, "global_step": 464718, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1142208576202393, "global_step": 464719, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.086977243423462, "global_step": 464720, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9719061851501465, "global_step": 464721, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0639185905456543, "global_step": 464722, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.076108455657959, "global_step": 464723, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.026733636856079, "global_step": 464724, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0910751819610596, "global_step": 464725, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.110524892807007, "global_step": 464726, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0086936950683594, "global_step": 464727, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1118276119232178, "global_step": 464728, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.046504497528076, "global_step": 464729, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0837738513946533, "global_step": 464730, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1195738315582275, "global_step": 464731, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9938886165618896, "global_step": 464732, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0315001010894775, "global_step": 464733, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0474753379821777, "global_step": 464734, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.065884590148926, "global_step": 464735, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.080990791320801, "global_step": 464736, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.053920269012451, "global_step": 464737, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1061129570007324, "global_step": 464738, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1000750064849854, "global_step": 464739, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.14247989654541, "global_step": 464740, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0697994232177734, "global_step": 464741, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0263214111328125, "global_step": 464742, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1434597969055176, "global_step": 464743, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.052164077758789, "global_step": 464744, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.140993356704712, "global_step": 464745, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1258745193481445, "global_step": 464746, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.108219861984253, "global_step": 464747, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1135547161102295, "global_step": 464748, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0277676582336426, "global_step": 464749, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.043544292449951, "global_step": 464750, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1313021183013916, "global_step": 464751, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0562350749969482, "global_step": 464752, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1102850437164307, "global_step": 464753, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.112656354904175, "global_step": 464754, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.105395555496216, "global_step": 464755, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0362658500671387, "global_step": 464756, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.093057870864868, "global_step": 464757, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1082746982574463, "global_step": 464758, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.002737283706665, "global_step": 464759, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0824685096740723, "global_step": 464760, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.129509925842285, "global_step": 464761, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0914642810821533, "global_step": 464762, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0370728969573975, "global_step": 464763, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0720407962799072, "global_step": 464764, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.070072889328003, "global_step": 464765, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1071524620056152, "global_step": 464766, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.035767078399658, "global_step": 464767, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1050827503204346, "global_step": 464768, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0904524326324463, "global_step": 464769, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1226046085357666, "global_step": 464770, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1496520042419434, "global_step": 464771, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0567381381988525, "global_step": 464772, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9585070610046387, "global_step": 464773, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0312259197235107, "global_step": 464774, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0406064987182617, "global_step": 464775, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.125735282897949, "global_step": 464776, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.120781421661377, "global_step": 464777, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0243005752563477, "global_step": 464778, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0168168544769287, "global_step": 464779, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0562996864318848, "global_step": 464780, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0786242485046387, "global_step": 464781, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1151669025421143, "global_step": 464782, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0734996795654297, "global_step": 464783, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0781519412994385, "global_step": 464784, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0675806999206543, "global_step": 464785, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.14752459526062, "global_step": 464786, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0837159156799316, "global_step": 464787, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.061284065246582, "global_step": 464788, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0351967811584473, "global_step": 464789, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.079223155975342, "global_step": 464790, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.039574146270752, "global_step": 464791, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.067045211791992, "global_step": 464792, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0913703441619873, "global_step": 464793, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.04621958732605, "global_step": 464794, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9698421955108643, "global_step": 464795, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0422441959381104, "global_step": 464796, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1043591499328613, "global_step": 464797, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9884376525878906, "global_step": 464798, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9955430030822754, "global_step": 464799, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1030640602111816, "global_step": 464800, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9883755445480347, "global_step": 464801, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1125521659851074, "global_step": 464802, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0153379440307617, "global_step": 464803, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1157100200653076, "global_step": 464804, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1037092208862305, "global_step": 464805, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0113563537597656, "global_step": 464806, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0709049701690674, "global_step": 464807, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.998514175415039, "global_step": 464808, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0462193489074707, "global_step": 464809, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.126039743423462, "global_step": 464810, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.102189064025879, "global_step": 464811, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1428840160369873, "global_step": 464812, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0680177211761475, "global_step": 464813, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.114409923553467, "global_step": 464814, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.034658193588257, "global_step": 464815, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9724152088165283, "global_step": 464816, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.161987781524658, "global_step": 464817, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.009800910949707, "global_step": 464818, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0559823513031006, "global_step": 464819, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.101454019546509, "global_step": 464820, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0655195713043213, "global_step": 464821, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.003467082977295, "global_step": 464822, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9879333972930908, "global_step": 464823, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.067262887954712, "global_step": 464824, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.142159938812256, "global_step": 464825, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0803098678588867, "global_step": 464826, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0371885299682617, "global_step": 464827, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0879697799682617, "global_step": 464828, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.077458143234253, "global_step": 464829, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0934600830078125, "global_step": 464830, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.071837902069092, "global_step": 464831, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.061171054840088, "global_step": 464832, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.980216145515442, "global_step": 464833, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.149578094482422, "global_step": 464834, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.090769052505493, "global_step": 464835, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0500636100769043, "global_step": 464836, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1141695976257324, "global_step": 464837, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9751871824264526, "global_step": 464838, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.074106454849243, "global_step": 464839, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.050421714782715, "global_step": 464840, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9763668775558472, "global_step": 464841, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1623549461364746, "global_step": 464842, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.145189046859741, "global_step": 464843, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0911808013916016, "global_step": 464844, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0900373458862305, "global_step": 464845, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.095353841781616, "global_step": 464846, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0464305877685547, "global_step": 464847, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.149165391921997, "global_step": 464848, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.100630760192871, "global_step": 464849, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.977639079093933, "global_step": 464850, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1389260292053223, "global_step": 464851, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9938511848449707, "global_step": 464852, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0718014240264893, "global_step": 464853, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.987741231918335, "global_step": 464854, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.108210563659668, "global_step": 464855, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1201083660125732, "global_step": 464856, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.024862051010132, "global_step": 464857, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0386409759521484, "global_step": 464858, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.078981399536133, "global_step": 464859, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0724949836730957, "global_step": 464860, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1393234729766846, "global_step": 464861, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0849640369415283, "global_step": 464862, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0946502685546875, "global_step": 464863, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.119347095489502, "global_step": 464864, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.017674446105957, "global_step": 464865, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0887503623962402, "global_step": 464866, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.084437131881714, "global_step": 464867, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.066678285598755, "global_step": 464868, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1010453701019287, "global_step": 464869, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9769418239593506, "global_step": 464870, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.074169635772705, "global_step": 464871, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0485329627990723, "global_step": 464872, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.995008945465088, "global_step": 464873, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.024418592453003, "global_step": 464874, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.035573959350586, "global_step": 464875, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0809895992279053, "global_step": 464876, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1257057189941406, "global_step": 464877, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9979588985443115, "global_step": 464878, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0187344551086426, "global_step": 464879, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.013935089111328, "global_step": 464880, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0163772106170654, "global_step": 464881, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0421507358551025, "global_step": 464882, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.012340545654297, "global_step": 464883, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0638701915740967, "global_step": 464884, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9722754955291748, "global_step": 464885, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0569663047790527, "global_step": 464886, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0933823585510254, "global_step": 464887, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0623910427093506, "global_step": 464888, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0290470123291016, "global_step": 464889, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.969552993774414, "global_step": 464890, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0686490535736084, "global_step": 464891, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0033257007598877, "global_step": 464892, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9778929948806763, "global_step": 464893, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0889439582824707, "global_step": 464894, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0846171379089355, "global_step": 464895, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0061168670654297, "global_step": 464896, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0920894145965576, "global_step": 464897, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.94106125831604, "global_step": 464898, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.077298402786255, "global_step": 464899, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0474765300750732, "global_step": 464900, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1258747577667236, "global_step": 464901, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.097970724105835, "global_step": 464902, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.001168966293335, "global_step": 464903, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0649590492248535, "global_step": 464904, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0941874980926514, "global_step": 464905, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9966423511505127, "global_step": 464906, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.021827459335327, "global_step": 464907, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.089296579360962, "global_step": 464908, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.003615617752075, "global_step": 464909, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1099307537078857, "global_step": 464910, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0081546306610107, "global_step": 464911, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.141187906265259, "global_step": 464912, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.026128053665161, "global_step": 464913, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.02758526802063, "global_step": 464914, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9995425939559937, "global_step": 464915, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1024668216705322, "global_step": 464916, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1189587116241455, "global_step": 464917, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0614397525787354, "global_step": 464918, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.044517993927002, "global_step": 464919, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.073634624481201, "global_step": 464920, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0496859550476074, "global_step": 464921, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.024683713912964, "global_step": 464922, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0600404739379883, "global_step": 464923, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.114877939224243, "global_step": 464924, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.084001064300537, "global_step": 464925, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1515233516693115, "global_step": 464926, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0114426612854004, "global_step": 464927, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.136787176132202, "global_step": 464928, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.148641347885132, "global_step": 464929, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0695173740386963, "global_step": 464930, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0548484325408936, "global_step": 464931, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.075631856918335, "global_step": 464932, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1302850246429443, "global_step": 464933, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.105389356613159, "global_step": 464934, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0417556762695312, "global_step": 464935, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.055243968963623, "global_step": 464936, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0486490726470947, "global_step": 464937, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0393357276916504, "global_step": 464938, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.041478157043457, "global_step": 464939, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.066906452178955, "global_step": 464940, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0361597537994385, "global_step": 464941, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0350940227508545, "global_step": 464942, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0858564376831055, "global_step": 464943, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0007431507110596, "global_step": 464944, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.132333755493164, "global_step": 464945, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0682339668273926, "global_step": 464946, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.146981954574585, "global_step": 464947, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9993723630905151, "global_step": 464948, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0492467880249023, "global_step": 464949, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9859553575515747, "global_step": 464950, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1021721363067627, "global_step": 464951, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.032536506652832, "global_step": 464952, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0151054859161377, "global_step": 464953, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.029961347579956, "global_step": 464954, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0561182498931885, "global_step": 464955, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0082342624664307, "global_step": 464956, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0596976280212402, "global_step": 464957, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.050966739654541, "global_step": 464958, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1034555435180664, "global_step": 464959, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.188035011291504, "global_step": 464960, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1051361560821533, "global_step": 464961, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0031089782714844, "global_step": 464962, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9466533660888672, "global_step": 464963, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.065669536590576, "global_step": 464964, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.960503339767456, "global_step": 464965, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.095907211303711, "global_step": 464966, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1438095569610596, "global_step": 464967, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.017148733139038, "global_step": 464968, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0568623542785645, "global_step": 464969, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.132134199142456, "global_step": 464970, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.092745780944824, "global_step": 464971, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.045651912689209, "global_step": 464972, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0870614051818848, "global_step": 464973, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0726675987243652, "global_step": 464974, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.096419095993042, "global_step": 464975, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1005606651306152, "global_step": 464976, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1231114864349365, "global_step": 464977, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1602940559387207, "global_step": 464978, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.049762487411499, "global_step": 464979, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0484402179718018, "global_step": 464980, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0459320545196533, "global_step": 464981, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1202807426452637, "global_step": 464982, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.035736560821533, "global_step": 464983, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.160311222076416, "global_step": 464984, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0126760005950928, "global_step": 464985, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0219168663024902, "global_step": 464986, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0145020484924316, "global_step": 464987, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.087296962738037, "global_step": 464988, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.129978895187378, "global_step": 464989, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.097015142440796, "global_step": 464990, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1137208938598633, "global_step": 464991, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0237627029418945, "global_step": 464992, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.026378631591797, "global_step": 464993, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0028977394104004, "global_step": 464994, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0680203437805176, "global_step": 464995, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1077849864959717, "global_step": 464996, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1099915504455566, "global_step": 464997, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0292105674743652, "global_step": 464998, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0356531143188477, "global_step": 464999, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1404495239257812, "global_step": 465000, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.103883743286133, "global_step": 465001, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0958428382873535, "global_step": 465002, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9954359531402588, "global_step": 465003, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0648226737976074, "global_step": 465004, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0458590984344482, "global_step": 465005, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0439417362213135, "global_step": 465006, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.086860179901123, "global_step": 465007, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1463093757629395, "global_step": 465008, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.06638765335083, "global_step": 465009, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.048854351043701, "global_step": 465010, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1624011993408203, "global_step": 465011, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0438456535339355, "global_step": 465012, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0321266651153564, "global_step": 465013, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0727643966674805, "global_step": 465014, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0429418087005615, "global_step": 465015, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.051159143447876, "global_step": 465016, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1048076152801514, "global_step": 465017, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.104114532470703, "global_step": 465018, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.061929225921631, "global_step": 465019, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0245296955108643, "global_step": 465020, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.069875955581665, "global_step": 465021, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.118457794189453, "global_step": 465022, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0145790576934814, "global_step": 465023, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0589022636413574, "global_step": 465024, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0736560821533203, "global_step": 465025, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0246479511260986, "global_step": 465026, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1254777908325195, "global_step": 465027, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.140482187271118, "global_step": 465028, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0587048530578613, "global_step": 465029, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0839245319366455, "global_step": 465030, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1778368949890137, "global_step": 465031, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.110410451889038, "global_step": 465032, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0730748176574707, "global_step": 465033, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1029112339019775, "global_step": 465034, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0029382705688477, "global_step": 465035, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0297141075134277, "global_step": 465036, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0485870838165283, "global_step": 465037, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.108431339263916, "global_step": 465038, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1093225479125977, "global_step": 465039, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0358850955963135, "global_step": 465040, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.029146671295166, "global_step": 465041, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0270941257476807, "global_step": 465042, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0624303817749023, "global_step": 465043, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.031013250350952, "global_step": 465044, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1036949157714844, "global_step": 465045, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9822981357574463, "global_step": 465046, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0096969604492188, "global_step": 465047, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.002377510070801, "global_step": 465048, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1382200717926025, "global_step": 465049, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0639731884002686, "global_step": 465050, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0929858684539795, "global_step": 465051, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1023359298706055, "global_step": 465052, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1136233806610107, "global_step": 465053, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1041460037231445, "global_step": 465054, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.056837558746338, "global_step": 465055, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.124122142791748, "global_step": 465056, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0864827632904053, "global_step": 465057, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0948777198791504, "global_step": 465058, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.113474130630493, "global_step": 465059, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0766994953155518, "global_step": 465060, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.049377679824829, "global_step": 465061, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1132960319519043, "global_step": 465062, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1460165977478027, "global_step": 465063, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.018418550491333, "global_step": 465064, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0415003299713135, "global_step": 465065, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.114140033721924, "global_step": 465066, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0635898113250732, "global_step": 465067, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.098405122756958, "global_step": 465068, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0949885845184326, "global_step": 465069, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1553421020507812, "global_step": 465070, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.129444122314453, "global_step": 465071, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.096564769744873, "global_step": 465072, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.077346086502075, "global_step": 465073, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0557191371917725, "global_step": 465074, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0842905044555664, "global_step": 465075, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.090815782546997, "global_step": 465076, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0579001903533936, "global_step": 465077, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.007361650466919, "global_step": 465078, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.055340528488159, "global_step": 465079, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1123762130737305, "global_step": 465080, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.023921489715576, "global_step": 465081, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0386507511138916, "global_step": 465082, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.022444725036621, "global_step": 465083, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0821497440338135, "global_step": 465084, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1868278980255127, "global_step": 465085, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0450289249420166, "global_step": 465086, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.054105758666992, "global_step": 465087, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.068145751953125, "global_step": 465088, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.048072576522827, "global_step": 465089, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.046790838241577, "global_step": 465090, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1830456256866455, "global_step": 465091, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0728073120117188, "global_step": 465092, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1063807010650635, "global_step": 465093, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0593080520629883, "global_step": 465094, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1921560764312744, "global_step": 465095, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0192220211029053, "global_step": 465096, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0667343139648438, "global_step": 465097, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0726280212402344, "global_step": 465098, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0425353050231934, "global_step": 465099, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0868980884552, "global_step": 465100, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9335682392120361, "global_step": 465101, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1252951622009277, "global_step": 465102, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0621511936187744, "global_step": 465103, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.070866107940674, "global_step": 465104, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1230967044830322, "global_step": 465105, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0456767082214355, "global_step": 465106, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1107656955718994, "global_step": 465107, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0676114559173584, "global_step": 465108, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0388567447662354, "global_step": 465109, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0830204486846924, "global_step": 465110, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.102726459503174, "global_step": 465111, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.143263101577759, "global_step": 465112, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.06160044670105, "global_step": 465113, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1108779907226562, "global_step": 465114, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9376384019851685, "global_step": 465115, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.006678581237793, "global_step": 465116, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.084745168685913, "global_step": 465117, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0355241298675537, "global_step": 465118, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1319034099578857, "global_step": 465119, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.039902448654175, "global_step": 465120, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1207876205444336, "global_step": 465121, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1211886405944824, "global_step": 465122, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0776445865631104, "global_step": 465123, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0675506591796875, "global_step": 465124, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1164069175720215, "global_step": 465125, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.096687078475952, "global_step": 465126, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.127577543258667, "global_step": 465127, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1159284114837646, "global_step": 465128, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.150681495666504, "global_step": 465129, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0161056518554688, "global_step": 465130, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0986320972442627, "global_step": 465131, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0688722133636475, "global_step": 465132, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1050076484680176, "global_step": 465133, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.081249237060547, "global_step": 465134, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0482869148254395, "global_step": 465135, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.087932586669922, "global_step": 465136, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0878164768218994, "global_step": 465137, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.02453351020813, "global_step": 465138, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1493430137634277, "global_step": 465139, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0781493186950684, "global_step": 465140, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.053466796875, "global_step": 465141, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.118448495864868, "global_step": 465142, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0621182918548584, "global_step": 465143, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0840985774993896, "global_step": 465144, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.120490312576294, "global_step": 465145, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0251495838165283, "global_step": 465146, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0740914344787598, "global_step": 465147, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0789408683776855, "global_step": 465148, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0456135272979736, "global_step": 465149, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0507657527923584, "global_step": 465150, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1252171993255615, "global_step": 465151, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0021064281463623, "global_step": 465152, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0208616256713867, "global_step": 465153, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0964763164520264, "global_step": 465154, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0062859058380127, "global_step": 465155, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0470833778381348, "global_step": 465156, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1499643325805664, "global_step": 465157, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.079524517059326, "global_step": 465158, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.045663356781006, "global_step": 465159, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.028698205947876, "global_step": 465160, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.12976336479187, "global_step": 465161, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1042606830596924, "global_step": 465162, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1434121131896973, "global_step": 465163, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.17503023147583, "global_step": 465164, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9835522174835205, "global_step": 465165, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.069697141647339, "global_step": 465166, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0388216972351074, "global_step": 465167, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.013383388519287, "global_step": 465168, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0262625217437744, "global_step": 465169, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1596479415893555, "global_step": 465170, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0169003009796143, "global_step": 465171, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0225791931152344, "global_step": 465172, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.064409017562866, "global_step": 465173, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.087456464767456, "global_step": 465174, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.090886354446411, "global_step": 465175, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0660383701324463, "global_step": 465176, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0174152851104736, "global_step": 465177, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.998473882675171, "global_step": 465178, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.085958480834961, "global_step": 465179, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0625216960906982, "global_step": 465180, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0891635417938232, "global_step": 465181, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0905892848968506, "global_step": 465182, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.921532392501831, "global_step": 465183, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.096834182739258, "global_step": 465184, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.164508104324341, "global_step": 465185, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0788698196411133, "global_step": 465186, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1722679138183594, "global_step": 465187, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.100569486618042, "global_step": 465188, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0039291381835938, "global_step": 465189, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.971076250076294, "global_step": 465190, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0924041271209717, "global_step": 465191, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.060443639755249, "global_step": 465192, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0497872829437256, "global_step": 465193, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.086615800857544, "global_step": 465194, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1711955070495605, "global_step": 465195, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.024925470352173, "global_step": 465196, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.056920051574707, "global_step": 465197, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.053647756576538, "global_step": 465198, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1073591709136963, "global_step": 465199, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0616066455841064, "global_step": 465200, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0719106197357178, "global_step": 465201, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0675723552703857, "global_step": 465202, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.029923439025879, "global_step": 465203, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.076519727706909, "global_step": 465204, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.056981086730957, "global_step": 465205, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1472179889678955, "global_step": 465206, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1308021545410156, "global_step": 465207, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1595654487609863, "global_step": 465208, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.087986946105957, "global_step": 465209, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0359363555908203, "global_step": 465210, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0322089195251465, "global_step": 465211, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1394171714782715, "global_step": 465212, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.054290771484375, "global_step": 465213, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.027407646179199, "global_step": 465214, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.144545316696167, "global_step": 465215, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.129404067993164, "global_step": 465216, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.014143943786621, "global_step": 465217, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0613656044006348, "global_step": 465218, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0028231143951416, "global_step": 465219, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0743627548217773, "global_step": 465220, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.125404119491577, "global_step": 465221, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9521268606185913, "global_step": 465222, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.132089138031006, "global_step": 465223, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.073688268661499, "global_step": 465224, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9977259635925293, "global_step": 465225, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0278918743133545, "global_step": 465226, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9964187145233154, "global_step": 465227, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.039921998977661, "global_step": 465228, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0649168491363525, "global_step": 465229, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1015236377716064, "global_step": 465230, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0730140209198, "global_step": 465231, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0236849784851074, "global_step": 465232, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0430924892425537, "global_step": 465233, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0953874588012695, "global_step": 465234, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0116517543792725, "global_step": 465235, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0917227268218994, "global_step": 465236, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.027256488800049, "global_step": 465237, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9987469911575317, "global_step": 465238, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.1118743419647217, "global_step": 465239, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0348827838897705, "global_step": 465240, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0346996784210205, "global_step": 465241, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.101062059402466, "global_step": 465242, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.144761562347412, "global_step": 465243, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0588138103485107, "global_step": 465244, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.070585250854492, "global_step": 465245, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.080031156539917, "global_step": 465246, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.049649715423584, "global_step": 465247, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0977182388305664, "global_step": 465248, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.038485527038574, "global_step": 465249, "epoch": 829, "lr": 5e-05}
{"train_loss": 1.9766309261322021, "global_step": 465250, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.0641982555389404, "global_step": 465251, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.066541910171509, "global_step": 465252, "epoch": 829, "lr": 5e-05}
{"train_loss": 2.061403751373291, "global_step": 465253, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0539135932922363, "global_step": 465254, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0815958976745605, "global_step": 465255, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1430745124816895, "global_step": 465256, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.121305465698242, "global_step": 465257, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9746360778808594, "global_step": 465258, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.095245361328125, "global_step": 465259, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0120646953582764, "global_step": 465260, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.048348903656006, "global_step": 465261, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0443358421325684, "global_step": 465262, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0593440532684326, "global_step": 465263, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.037560224533081, "global_step": 465264, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.976266860961914, "global_step": 465265, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.025172233581543, "global_step": 465266, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.112152338027954, "global_step": 465267, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0544166564941406, "global_step": 465268, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9354643821716309, "global_step": 465269, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.132507801055908, "global_step": 465270, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9675981998443604, "global_step": 465271, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1105363368988037, "global_step": 465272, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1294775009155273, "global_step": 465273, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.010469436645508, "global_step": 465274, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9965327978134155, "global_step": 465275, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0858986377716064, "global_step": 465276, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.052381992340088, "global_step": 465277, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0234997272491455, "global_step": 465278, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0575897693634033, "global_step": 465279, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0800392627716064, "global_step": 465280, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.119659662246704, "global_step": 465281, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9746021032333374, "global_step": 465282, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0852532386779785, "global_step": 465283, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.065864086151123, "global_step": 465284, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.053183078765869, "global_step": 465285, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0832297801971436, "global_step": 465286, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1827754974365234, "global_step": 465287, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.071878433227539, "global_step": 465288, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0039381980895996, "global_step": 465289, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.032236337661743, "global_step": 465290, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9886987209320068, "global_step": 465291, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.157947301864624, "global_step": 465292, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9596983194351196, "global_step": 465293, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.053105354309082, "global_step": 465294, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0641074180603027, "global_step": 465295, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0674397945404053, "global_step": 465296, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.008132219314575, "global_step": 465297, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.003075122833252, "global_step": 465298, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.037316083908081, "global_step": 465299, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0611796379089355, "global_step": 465300, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1079626083374023, "global_step": 465301, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9344922304153442, "global_step": 465302, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0833311080932617, "global_step": 465303, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0687623023986816, "global_step": 465304, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.047029972076416, "global_step": 465305, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.000654458999634, "global_step": 465306, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0834827423095703, "global_step": 465307, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0340704917907715, "global_step": 465308, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.035245895385742, "global_step": 465309, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1102850437164307, "global_step": 465310, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.161285877227783, "global_step": 465311, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1686387062072754, "global_step": 465312, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.049013614654541, "global_step": 465313, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.077763557434082, "global_step": 465314, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1150450706481934, "global_step": 465315, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1002984046936035, "global_step": 465316, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0486905574798584, "global_step": 465317, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0260138511657715, "global_step": 465318, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0166714191436768, "global_step": 465319, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0932860374450684, "global_step": 465320, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1146695613861084, "global_step": 465321, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0621144771575928, "global_step": 465322, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0430541038513184, "global_step": 465323, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0401322841644287, "global_step": 465324, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.04111647605896, "global_step": 465325, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0708861351013184, "global_step": 465326, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0177981853485107, "global_step": 465327, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1044654846191406, "global_step": 465328, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.044079542160034, "global_step": 465329, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.073045253753662, "global_step": 465330, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1091251373291016, "global_step": 465331, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0084147453308105, "global_step": 465332, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0670011043548584, "global_step": 465333, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9811142683029175, "global_step": 465334, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0350422859191895, "global_step": 465335, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.072221279144287, "global_step": 465336, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.01444673538208, "global_step": 465337, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9316918849945068, "global_step": 465338, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0341219902038574, "global_step": 465339, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.040761947631836, "global_step": 465340, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.098620653152466, "global_step": 465341, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0765857696533203, "global_step": 465342, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0179922580718994, "global_step": 465343, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0601000785827637, "global_step": 465344, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0446815490722656, "global_step": 465345, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.001387596130371, "global_step": 465346, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0562052726745605, "global_step": 465347, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9869506359100342, "global_step": 465348, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.128896713256836, "global_step": 465349, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0967981815338135, "global_step": 465350, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0762250423431396, "global_step": 465351, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.103005886077881, "global_step": 465352, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0192651748657227, "global_step": 465353, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0360021591186523, "global_step": 465354, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0876317024230957, "global_step": 465355, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0003418922424316, "global_step": 465356, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.077075481414795, "global_step": 465357, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9945549964904785, "global_step": 465358, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0715904235839844, "global_step": 465359, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.009936809539795, "global_step": 465360, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.165187358856201, "global_step": 465361, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0487093925476074, "global_step": 465362, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0438220500946045, "global_step": 465363, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.062361240386963, "global_step": 465364, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1007583141326904, "global_step": 465365, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0909316539764404, "global_step": 465366, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0810186862945557, "global_step": 465367, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.096454620361328, "global_step": 465368, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0857925415039062, "global_step": 465369, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0169098377227783, "global_step": 465370, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.020723342895508, "global_step": 465371, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1849894523620605, "global_step": 465372, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0338289737701416, "global_step": 465373, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0992276668548584, "global_step": 465374, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0709192752838135, "global_step": 465375, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0748798847198486, "global_step": 465376, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.141099452972412, "global_step": 465377, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.030406951904297, "global_step": 465378, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.145991802215576, "global_step": 465379, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.047987222671509, "global_step": 465380, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.970691442489624, "global_step": 465381, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.058687448501587, "global_step": 465382, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.076122760772705, "global_step": 465383, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9843440055847168, "global_step": 465384, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0270721912384033, "global_step": 465385, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0570340156555176, "global_step": 465386, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0855109691619873, "global_step": 465387, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.08134126663208, "global_step": 465388, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.152074098587036, "global_step": 465389, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0607006549835205, "global_step": 465390, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0825445652008057, "global_step": 465391, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.976023554801941, "global_step": 465392, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0103530883789062, "global_step": 465393, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0400514602661133, "global_step": 465394, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.077463388442993, "global_step": 465395, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9795929193496704, "global_step": 465396, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0537185668945312, "global_step": 465397, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.04898738861084, "global_step": 465398, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0969386100769043, "global_step": 465399, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0018370151519775, "global_step": 465400, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.074455499649048, "global_step": 465401, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.10184907913208, "global_step": 465402, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1496434211730957, "global_step": 465403, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.061899185180664, "global_step": 465404, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0991618633270264, "global_step": 465405, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1615471839904785, "global_step": 465406, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0882856845855713, "global_step": 465407, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0238378047943115, "global_step": 465408, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.049863815307617, "global_step": 465409, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.106142044067383, "global_step": 465410, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.033843517303467, "global_step": 465411, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9836211204528809, "global_step": 465412, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.066476821899414, "global_step": 465413, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.014723777770996, "global_step": 465414, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1069564819335938, "global_step": 465415, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.068002700805664, "global_step": 465416, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.035921335220337, "global_step": 465417, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0865695476531982, "global_step": 465418, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1236259937286377, "global_step": 465419, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0695502758026123, "global_step": 465420, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.060924768447876, "global_step": 465421, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.044485330581665, "global_step": 465422, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0613040924072266, "global_step": 465423, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.017479181289673, "global_step": 465424, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.007082462310791, "global_step": 465425, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0368778705596924, "global_step": 465426, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0915849208831787, "global_step": 465427, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0081772804260254, "global_step": 465428, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.082610845565796, "global_step": 465429, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.042322874069214, "global_step": 465430, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.950458288192749, "global_step": 465431, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.013730049133301, "global_step": 465432, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.078514337539673, "global_step": 465433, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0586283206939697, "global_step": 465434, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1206226348876953, "global_step": 465435, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.069004774093628, "global_step": 465436, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.113999366760254, "global_step": 465437, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.969778299331665, "global_step": 465438, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.053523302078247, "global_step": 465439, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.165292501449585, "global_step": 465440, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.032731771469116, "global_step": 465441, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.14495849609375, "global_step": 465442, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.092669725418091, "global_step": 465443, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.066274881362915, "global_step": 465444, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.134220600128174, "global_step": 465445, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0746943950653076, "global_step": 465446, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1418750286102295, "global_step": 465447, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.109450101852417, "global_step": 465448, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1049962043762207, "global_step": 465449, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0332014560699463, "global_step": 465450, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0040440559387207, "global_step": 465451, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.088101387023926, "global_step": 465452, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0503668785095215, "global_step": 465453, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.048438310623169, "global_step": 465454, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.037055492401123, "global_step": 465455, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9892635345458984, "global_step": 465456, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.030055046081543, "global_step": 465457, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.056274652481079, "global_step": 465458, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.182145357131958, "global_step": 465459, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0053696632385254, "global_step": 465460, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0717077255249023, "global_step": 465461, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9916051626205444, "global_step": 465462, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0230460166931152, "global_step": 465463, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.080376386642456, "global_step": 465464, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0517280101776123, "global_step": 465465, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.073215961456299, "global_step": 465466, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.209746837615967, "global_step": 465467, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.090858221054077, "global_step": 465468, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.000044822692871, "global_step": 465469, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.052919626235962, "global_step": 465470, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.017897605895996, "global_step": 465471, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1340067386627197, "global_step": 465472, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0775606632232666, "global_step": 465473, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.063365936279297, "global_step": 465474, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1014702320098877, "global_step": 465475, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0584444999694824, "global_step": 465476, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0567257404327393, "global_step": 465477, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0584402084350586, "global_step": 465478, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0389838218688965, "global_step": 465479, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0570459365844727, "global_step": 465480, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0283687114715576, "global_step": 465481, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.948651671409607, "global_step": 465482, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9541398286819458, "global_step": 465483, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1023848056793213, "global_step": 465484, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.016712188720703, "global_step": 465485, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0341076850891113, "global_step": 465486, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0310170650482178, "global_step": 465487, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.136482000350952, "global_step": 465488, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0726823806762695, "global_step": 465489, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.027416467666626, "global_step": 465490, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.054821014404297, "global_step": 465491, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.08205509185791, "global_step": 465492, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.053830862045288, "global_step": 465493, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0461227893829346, "global_step": 465494, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9927502870559692, "global_step": 465495, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.039280652999878, "global_step": 465496, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.065948963165283, "global_step": 465497, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.105421781539917, "global_step": 465498, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.076963186264038, "global_step": 465499, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0217692852020264, "global_step": 465500, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0297915935516357, "global_step": 465501, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0667030811309814, "global_step": 465502, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0382087230682373, "global_step": 465503, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0898993015289307, "global_step": 465504, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9703792333602905, "global_step": 465505, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9886860847473145, "global_step": 465506, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1239826679229736, "global_step": 465507, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.128817558288574, "global_step": 465508, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0384531021118164, "global_step": 465509, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0378940105438232, "global_step": 465510, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.051727294921875, "global_step": 465511, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.076827049255371, "global_step": 465512, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.073190689086914, "global_step": 465513, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0021252632141113, "global_step": 465514, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.031257152557373, "global_step": 465515, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0399184226989746, "global_step": 465516, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.115046501159668, "global_step": 465517, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1598103046417236, "global_step": 465518, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9681788682937622, "global_step": 465519, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0019054412841797, "global_step": 465520, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.098637819290161, "global_step": 465521, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0931241512298584, "global_step": 465522, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0581765174865723, "global_step": 465523, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.097151756286621, "global_step": 465524, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0621514320373535, "global_step": 465525, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9927951097488403, "global_step": 465526, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0380892753601074, "global_step": 465527, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0216360092163086, "global_step": 465528, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1837689876556396, "global_step": 465529, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.189415216445923, "global_step": 465530, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0284817218780518, "global_step": 465531, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0670166015625, "global_step": 465532, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.053291082382202, "global_step": 465533, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0804948806762695, "global_step": 465534, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.085897445678711, "global_step": 465535, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.056767463684082, "global_step": 465536, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0880537033081055, "global_step": 465537, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.128544569015503, "global_step": 465538, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9827638864517212, "global_step": 465539, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.015784978866577, "global_step": 465540, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0259108543395996, "global_step": 465541, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.022907018661499, "global_step": 465542, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.107935905456543, "global_step": 465543, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0439815521240234, "global_step": 465544, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.09346079826355, "global_step": 465545, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0515639781951904, "global_step": 465546, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0788121223449707, "global_step": 465547, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0350522994995117, "global_step": 465548, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0253968238830566, "global_step": 465549, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0334928035736084, "global_step": 465550, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.097353219985962, "global_step": 465551, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1258671283721924, "global_step": 465552, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1311614513397217, "global_step": 465553, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0930066108703613, "global_step": 465554, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0227763652801514, "global_step": 465555, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0282905101776123, "global_step": 465556, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0401437282562256, "global_step": 465557, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0647661685943604, "global_step": 465558, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.089681625366211, "global_step": 465559, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.050400733947754, "global_step": 465560, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1292803287506104, "global_step": 465561, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0058023929595947, "global_step": 465562, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.058821201324463, "global_step": 465563, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1099143028259277, "global_step": 465564, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0958502292633057, "global_step": 465565, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1002414226531982, "global_step": 465566, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1743876934051514, "global_step": 465567, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0283570289611816, "global_step": 465568, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.113513708114624, "global_step": 465569, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0692172050476074, "global_step": 465570, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.108819007873535, "global_step": 465571, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0148656368255615, "global_step": 465572, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0467073917388916, "global_step": 465573, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0533885955810547, "global_step": 465574, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0352587699890137, "global_step": 465575, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0093367099761963, "global_step": 465576, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9557299613952637, "global_step": 465577, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.094790458679199, "global_step": 465578, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0855906009674072, "global_step": 465579, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.037625551223755, "global_step": 465580, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0485074520111084, "global_step": 465581, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.063185214996338, "global_step": 465582, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.000901937484741, "global_step": 465583, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1491384506225586, "global_step": 465584, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.083979368209839, "global_step": 465585, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.158531904220581, "global_step": 465586, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0278337001800537, "global_step": 465587, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0161547660827637, "global_step": 465588, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.106257915496826, "global_step": 465589, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1363115310668945, "global_step": 465590, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.002901554107666, "global_step": 465591, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.936014175415039, "global_step": 465592, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0689074993133545, "global_step": 465593, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.037438154220581, "global_step": 465594, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0801563262939453, "global_step": 465595, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0961966514587402, "global_step": 465596, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.104520797729492, "global_step": 465597, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.066250801086426, "global_step": 465598, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.036853075027466, "global_step": 465599, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1150660514831543, "global_step": 465600, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.047865867614746, "global_step": 465601, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0740034580230713, "global_step": 465602, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9850064516067505, "global_step": 465603, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0265889167785645, "global_step": 465604, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0425493717193604, "global_step": 465605, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.143641233444214, "global_step": 465606, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.037090301513672, "global_step": 465607, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.128483772277832, "global_step": 465608, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0976085662841797, "global_step": 465609, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.187041997909546, "global_step": 465610, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.112084150314331, "global_step": 465611, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.068450450897217, "global_step": 465612, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.040473699569702, "global_step": 465613, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0198793411254883, "global_step": 465614, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1009371280670166, "global_step": 465615, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.20259690284729, "global_step": 465616, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0624430179595947, "global_step": 465617, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1256275177001953, "global_step": 465618, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1556594371795654, "global_step": 465619, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.098792552947998, "global_step": 465620, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0960307121276855, "global_step": 465621, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.126620292663574, "global_step": 465622, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0797030925750732, "global_step": 465623, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.039357900619507, "global_step": 465624, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9805923700332642, "global_step": 465625, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1097562313079834, "global_step": 465626, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0789012908935547, "global_step": 465627, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0098769664764404, "global_step": 465628, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.093655586242676, "global_step": 465629, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.06203293800354, "global_step": 465630, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1012704372406006, "global_step": 465631, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.059037446975708, "global_step": 465632, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.122197389602661, "global_step": 465633, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1142680644989014, "global_step": 465634, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.077394485473633, "global_step": 465635, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.094604969024658, "global_step": 465636, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.121955156326294, "global_step": 465637, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0128090381622314, "global_step": 465638, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0743863582611084, "global_step": 465639, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1304640769958496, "global_step": 465640, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.085881471633911, "global_step": 465641, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1044774055480957, "global_step": 465642, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9896827936172485, "global_step": 465643, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1204276084899902, "global_step": 465644, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1407346725463867, "global_step": 465645, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.174516201019287, "global_step": 465646, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.102219343185425, "global_step": 465647, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.081822395324707, "global_step": 465648, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0581376552581787, "global_step": 465649, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0256993770599365, "global_step": 465650, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.018852949142456, "global_step": 465651, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0713043212890625, "global_step": 465652, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0599639415740967, "global_step": 465653, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.076082706451416, "global_step": 465654, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0223145484924316, "global_step": 465655, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0824697017669678, "global_step": 465656, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.026848554611206, "global_step": 465657, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.048849582672119, "global_step": 465658, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0551252365112305, "global_step": 465659, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0069923400878906, "global_step": 465660, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0607120990753174, "global_step": 465661, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.176422119140625, "global_step": 465662, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.120544910430908, "global_step": 465663, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.077019691467285, "global_step": 465664, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.14182710647583, "global_step": 465665, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0748841762542725, "global_step": 465666, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.097344160079956, "global_step": 465667, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.104004144668579, "global_step": 465668, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1145026683807373, "global_step": 465669, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.107787609100342, "global_step": 465670, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.114335298538208, "global_step": 465671, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.148874521255493, "global_step": 465672, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.040710926055908, "global_step": 465673, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0872976779937744, "global_step": 465674, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0345914363861084, "global_step": 465675, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0237417221069336, "global_step": 465676, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.037297010421753, "global_step": 465677, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0104167461395264, "global_step": 465678, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1184895038604736, "global_step": 465679, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0698394775390625, "global_step": 465680, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0794730186462402, "global_step": 465681, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1342363357543945, "global_step": 465682, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.098742723464966, "global_step": 465683, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.081623077392578, "global_step": 465684, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.135502338409424, "global_step": 465685, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.02462100982666, "global_step": 465686, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.039867639541626, "global_step": 465687, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0543265342712402, "global_step": 465688, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.159698486328125, "global_step": 465689, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.11785888671875, "global_step": 465690, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.090885639190674, "global_step": 465691, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1325738430023193, "global_step": 465692, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0484964847564697, "global_step": 465693, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1264545917510986, "global_step": 465694, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0485987663269043, "global_step": 465695, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1076083183288574, "global_step": 465696, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.139557361602783, "global_step": 465697, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0768768787384033, "global_step": 465698, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.048940420150757, "global_step": 465699, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0552241802215576, "global_step": 465700, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0340099334716797, "global_step": 465701, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0011582374572754, "global_step": 465702, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0280191898345947, "global_step": 465703, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0238683223724365, "global_step": 465704, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9592243432998657, "global_step": 465705, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.036003589630127, "global_step": 465706, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.055002450942993, "global_step": 465707, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0761492252349854, "global_step": 465708, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0136947631835938, "global_step": 465709, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1357061862945557, "global_step": 465710, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0909414291381836, "global_step": 465711, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1128127574920654, "global_step": 465712, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0390281677246094, "global_step": 465713, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.057887315750122, "global_step": 465714, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0607681274414062, "global_step": 465715, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0387816429138184, "global_step": 465716, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.003591775894165, "global_step": 465717, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0686047077178955, "global_step": 465718, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.061786651611328, "global_step": 465719, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.091381311416626, "global_step": 465720, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.173286199569702, "global_step": 465721, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.105978012084961, "global_step": 465722, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0420572757720947, "global_step": 465723, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1296727657318115, "global_step": 465724, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1124606132507324, "global_step": 465725, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0324552059173584, "global_step": 465726, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.067507266998291, "global_step": 465727, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0151753425598145, "global_step": 465728, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1050281524658203, "global_step": 465729, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0234615802764893, "global_step": 465730, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1002187728881836, "global_step": 465731, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.058802366256714, "global_step": 465732, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0342109203338623, "global_step": 465733, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.171261787414551, "global_step": 465734, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0916459560394287, "global_step": 465735, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.077336311340332, "global_step": 465736, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.040712833404541, "global_step": 465737, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0940349102020264, "global_step": 465738, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1658589839935303, "global_step": 465739, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.045900344848633, "global_step": 465740, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1516058444976807, "global_step": 465741, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0672061443328857, "global_step": 465742, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.026293992996216, "global_step": 465743, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1140341758728027, "global_step": 465744, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0597305297851562, "global_step": 465745, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9953216314315796, "global_step": 465746, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0597290992736816, "global_step": 465747, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0882554054260254, "global_step": 465748, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.070922613143921, "global_step": 465749, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0321826934814453, "global_step": 465750, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0800302028656006, "global_step": 465751, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0311484336853027, "global_step": 465752, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.092264413833618, "global_step": 465753, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0767548084259033, "global_step": 465754, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0350611209869385, "global_step": 465755, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9921064376831055, "global_step": 465756, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9333289861679077, "global_step": 465757, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9766783714294434, "global_step": 465758, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.082805633544922, "global_step": 465759, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0227103233337402, "global_step": 465760, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0210278034210205, "global_step": 465761, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.048384428024292, "global_step": 465762, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.029364585876465, "global_step": 465763, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.046884298324585, "global_step": 465764, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.066929578781128, "global_step": 465765, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1057846546173096, "global_step": 465766, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0329129695892334, "global_step": 465767, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0651464462280273, "global_step": 465768, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1460678577423096, "global_step": 465769, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0679545402526855, "global_step": 465770, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0267770290374756, "global_step": 465771, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.070791244506836, "global_step": 465772, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1028287410736084, "global_step": 465773, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1221766471862793, "global_step": 465774, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0457918643951416, "global_step": 465775, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0970752239227295, "global_step": 465776, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0832788944244385, "global_step": 465777, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0365309715270996, "global_step": 465778, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0493719577789307, "global_step": 465779, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0617055892944336, "global_step": 465780, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.072526693344116, "global_step": 465781, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0680127143859863, "global_step": 465782, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0138556957244873, "global_step": 465783, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0129318237304688, "global_step": 465784, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.114102363586426, "global_step": 465785, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1188435554504395, "global_step": 465786, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1187593936920166, "global_step": 465787, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.098611354827881, "global_step": 465788, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9900233745574951, "global_step": 465789, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.014277935028076, "global_step": 465790, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1720175743103027, "global_step": 465791, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.095950126647949, "global_step": 465792, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1156439781188965, "global_step": 465793, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0810718536376953, "global_step": 465794, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0130624771118164, "global_step": 465795, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.2029037475585938, "global_step": 465796, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1188299655914307, "global_step": 465797, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.984256625175476, "global_step": 465798, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.011378765106201, "global_step": 465799, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0508463382720947, "global_step": 465800, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.057684898376465, "global_step": 465801, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.074061393737793, "global_step": 465802, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.107743263244629, "global_step": 465803, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0446178913116455, "global_step": 465804, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1006579399108887, "global_step": 465805, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0796613693237305, "global_step": 465806, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.122448444366455, "global_step": 465807, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0399434566497803, "global_step": 465808, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.126955986022949, "global_step": 465809, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9878724813461304, "global_step": 465810, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1575143337249756, "global_step": 465811, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1180310249328613, "global_step": 465812, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0624942779541016, "global_step": 465813, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0804479122161865, "global_step": 465814, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0786197185516357, "global_step": 465815, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.071160078048706, "global_step": 465816, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0192744731903076, "global_step": 465817, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.080049991607666, "global_step": 465818, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.069908618927002, "global_step": 465819, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.106539011001587, "global_step": 465820, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.117401599884033, "global_step": 465821, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0793936252593994, "global_step": 465822, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1184704303741455, "global_step": 465823, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9741452932357788, "global_step": 465824, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.055250644683838, "global_step": 465825, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.007819175720215, "global_step": 465826, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0060102939605713, "global_step": 465827, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.122389554977417, "global_step": 465828, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0786328315734863, "global_step": 465829, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1481268405914307, "global_step": 465830, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0445663928985596, "global_step": 465831, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0267794132232666, "global_step": 465832, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.040358066558838, "global_step": 465833, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0958523750305176, "global_step": 465834, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.060634136199951, "global_step": 465835, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0825910568237305, "global_step": 465836, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1422641277313232, "global_step": 465837, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0891802310943604, "global_step": 465838, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0524754524230957, "global_step": 465839, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0207486152648926, "global_step": 465840, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.033867120742798, "global_step": 465841, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.051032066345215, "global_step": 465842, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9783735275268555, "global_step": 465843, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9702329635620117, "global_step": 465844, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1377241611480713, "global_step": 465845, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0866074562072754, "global_step": 465846, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.089660167694092, "global_step": 465847, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0510716438293457, "global_step": 465848, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1125752925872803, "global_step": 465849, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0598978996276855, "global_step": 465850, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.033372163772583, "global_step": 465851, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9772419929504395, "global_step": 465852, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1168320178985596, "global_step": 465853, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.045557737350464, "global_step": 465854, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.071394443511963, "global_step": 465855, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.124868392944336, "global_step": 465856, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0826268196105957, "global_step": 465857, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9922503232955933, "global_step": 465858, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0292017459869385, "global_step": 465859, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0810022354125977, "global_step": 465860, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.172654390335083, "global_step": 465861, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.009902238845825, "global_step": 465862, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0659735202789307, "global_step": 465863, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.078094482421875, "global_step": 465864, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.030351161956787, "global_step": 465865, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.068028450012207, "global_step": 465866, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1340723037719727, "global_step": 465867, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.06244158744812, "global_step": 465868, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0841708183288574, "global_step": 465869, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1128554344177246, "global_step": 465870, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1148548126220703, "global_step": 465871, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.074096441268921, "global_step": 465872, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.076174020767212, "global_step": 465873, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.054288625717163, "global_step": 465874, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0915801525115967, "global_step": 465875, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0392801761627197, "global_step": 465876, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0844156742095947, "global_step": 465877, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9936504364013672, "global_step": 465878, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1032700538635254, "global_step": 465879, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1117568016052246, "global_step": 465880, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0921552181243896, "global_step": 465881, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1469907760620117, "global_step": 465882, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1237311363220215, "global_step": 465883, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0797877311706543, "global_step": 465884, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.122608184814453, "global_step": 465885, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.109259843826294, "global_step": 465886, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0459518432617188, "global_step": 465887, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0206093788146973, "global_step": 465888, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0640153884887695, "global_step": 465889, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0632686614990234, "global_step": 465890, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0903241634368896, "global_step": 465891, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0548131465911865, "global_step": 465892, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.043391227722168, "global_step": 465893, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1791083812713623, "global_step": 465894, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.038294792175293, "global_step": 465895, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.096076726913452, "global_step": 465896, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0105020999908447, "global_step": 465897, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.112273693084717, "global_step": 465898, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0564258098602295, "global_step": 465899, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.149193525314331, "global_step": 465900, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0893051624298096, "global_step": 465901, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1137266159057617, "global_step": 465902, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.061084508895874, "global_step": 465903, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.059135675430298, "global_step": 465904, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.083432912826538, "global_step": 465905, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.09029221534729, "global_step": 465906, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.07425856590271, "global_step": 465907, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0127055644989014, "global_step": 465908, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.111740827560425, "global_step": 465909, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0606706142425537, "global_step": 465910, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.111431121826172, "global_step": 465911, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.019571304321289, "global_step": 465912, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.132530689239502, "global_step": 465913, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9800407886505127, "global_step": 465914, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0522491931915283, "global_step": 465915, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1130757331848145, "global_step": 465916, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.023448944091797, "global_step": 465917, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.118515968322754, "global_step": 465918, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0334551334381104, "global_step": 465919, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.107617139816284, "global_step": 465920, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.139307975769043, "global_step": 465921, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0118277072906494, "global_step": 465922, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.062814235687256, "global_step": 465923, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.133077621459961, "global_step": 465924, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.075742721557617, "global_step": 465925, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1010375022888184, "global_step": 465926, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9637492895126343, "global_step": 465927, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0306053161621094, "global_step": 465928, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9898362159729004, "global_step": 465929, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0352771282196045, "global_step": 465930, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0603792667388916, "global_step": 465931, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.103367805480957, "global_step": 465932, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.037417411804199, "global_step": 465933, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1362481117248535, "global_step": 465934, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0694289207458496, "global_step": 465935, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.084583044052124, "global_step": 465936, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1596620082855225, "global_step": 465937, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.106579542160034, "global_step": 465938, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.063915729522705, "global_step": 465939, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.012871026992798, "global_step": 465940, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0865890979766846, "global_step": 465941, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0472702980041504, "global_step": 465942, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.106811285018921, "global_step": 465943, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.104227066040039, "global_step": 465944, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1130526065826416, "global_step": 465945, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1285862922668457, "global_step": 465946, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.141430139541626, "global_step": 465947, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0651071071624756, "global_step": 465948, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0812325477600098, "global_step": 465949, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1216044425964355, "global_step": 465950, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.057603597640991, "global_step": 465951, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9646490812301636, "global_step": 465952, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0524954795837402, "global_step": 465953, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1379024982452393, "global_step": 465954, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0938267707824707, "global_step": 465955, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9903991222381592, "global_step": 465956, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.151559591293335, "global_step": 465957, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.043097496032715, "global_step": 465958, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0332424640655518, "global_step": 465959, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1749560832977295, "global_step": 465960, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0323355197906494, "global_step": 465961, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.096967935562134, "global_step": 465962, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.170926570892334, "global_step": 465963, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0357580184936523, "global_step": 465964, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0984015464782715, "global_step": 465965, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.110708713531494, "global_step": 465966, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.974801778793335, "global_step": 465967, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.014233350753784, "global_step": 465968, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.093425750732422, "global_step": 465969, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0407726764678955, "global_step": 465970, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.046915054321289, "global_step": 465971, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0702497959136963, "global_step": 465972, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.075915575027466, "global_step": 465973, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.016793727874756, "global_step": 465974, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.052788734436035, "global_step": 465975, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1334609985351562, "global_step": 465976, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.122837781906128, "global_step": 465977, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0943853855133057, "global_step": 465978, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.059504747390747, "global_step": 465979, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0841193199157715, "global_step": 465980, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.052978277206421, "global_step": 465981, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.03625750541687, "global_step": 465982, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.087355613708496, "global_step": 465983, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9966442584991455, "global_step": 465984, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.8905364274978638, "global_step": 465985, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.018894672393799, "global_step": 465986, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.111104965209961, "global_step": 465987, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.074704647064209, "global_step": 465988, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.022921562194824, "global_step": 465989, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.038235902786255, "global_step": 465990, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0310752391815186, "global_step": 465991, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.128662586212158, "global_step": 465992, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.002769708633423, "global_step": 465993, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.122431516647339, "global_step": 465994, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1037039756774902, "global_step": 465995, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0809166431427, "global_step": 465996, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0401902198791504, "global_step": 465997, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0410146713256836, "global_step": 465998, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0970473289489746, "global_step": 465999, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.175593137741089, "global_step": 466000, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.081793785095215, "global_step": 466001, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0585930347442627, "global_step": 466002, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9839876890182495, "global_step": 466003, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0865890979766846, "global_step": 466004, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0933053493499756, "global_step": 466005, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.166869640350342, "global_step": 466006, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9803835153579712, "global_step": 466007, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0089244842529297, "global_step": 466008, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.024867296218872, "global_step": 466009, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0796377658843994, "global_step": 466010, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.032343864440918, "global_step": 466011, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.004340171813965, "global_step": 466012, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0666112899780273, "global_step": 466013, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.07073712348938, "global_step": 466014, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1134109497070312, "global_step": 466015, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.034174680709839, "global_step": 466016, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1146163940429688, "global_step": 466017, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0963428020477295, "global_step": 466018, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0691258907318115, "global_step": 466019, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.098799705505371, "global_step": 466020, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.128239393234253, "global_step": 466021, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.025353193283081, "global_step": 466022, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.990504264831543, "global_step": 466023, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.003114700317383, "global_step": 466024, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1937382221221924, "global_step": 466025, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1240181922912598, "global_step": 466026, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1270389556884766, "global_step": 466027, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9952718019485474, "global_step": 466028, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9823102951049805, "global_step": 466029, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.103652000427246, "global_step": 466030, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0830883979797363, "global_step": 466031, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0563557147979736, "global_step": 466032, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1389243602752686, "global_step": 466033, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0356035232543945, "global_step": 466034, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1287527084350586, "global_step": 466035, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1048290729522705, "global_step": 466036, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.025266647338867, "global_step": 466037, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.081050395965576, "global_step": 466038, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.145357370376587, "global_step": 466039, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1283063888549805, "global_step": 466040, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1050875186920166, "global_step": 466041, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0313775539398193, "global_step": 466042, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1674389839172363, "global_step": 466043, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0779755115509033, "global_step": 466044, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.109548330307007, "global_step": 466045, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.135518789291382, "global_step": 466046, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.057499647140503, "global_step": 466047, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1167869567871094, "global_step": 466048, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.981735110282898, "global_step": 466049, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0639703273773193, "global_step": 466050, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0055694580078125, "global_step": 466051, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.026818037033081, "global_step": 466052, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1069579124450684, "global_step": 466053, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9941387176513672, "global_step": 466054, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.064852714538574, "global_step": 466055, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0123467445373535, "global_step": 466056, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.120577335357666, "global_step": 466057, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0647921562194824, "global_step": 466058, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.086059331893921, "global_step": 466059, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.081162929534912, "global_step": 466060, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.097662925720215, "global_step": 466061, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0893185138702393, "global_step": 466062, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.026319980621338, "global_step": 466063, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1185903549194336, "global_step": 466064, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1329221725463867, "global_step": 466065, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.150195837020874, "global_step": 466066, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0088820457458496, "global_step": 466067, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0243031978607178, "global_step": 466068, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.057504653930664, "global_step": 466069, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1084280014038086, "global_step": 466070, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.088773250579834, "global_step": 466071, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0223865509033203, "global_step": 466072, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.081120252609253, "global_step": 466073, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0167858600616455, "global_step": 466074, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.037972927093506, "global_step": 466075, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.066434144973755, "global_step": 466076, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.046293020248413, "global_step": 466077, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.100127935409546, "global_step": 466078, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.08150577545166, "global_step": 466079, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0131654739379883, "global_step": 466080, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.092090129852295, "global_step": 466081, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9859421253204346, "global_step": 466082, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.021219253540039, "global_step": 466083, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.027866840362549, "global_step": 466084, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9923919439315796, "global_step": 466085, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0361454486846924, "global_step": 466086, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.058375835418701, "global_step": 466087, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0559487342834473, "global_step": 466088, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0501396656036377, "global_step": 466089, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0831849575042725, "global_step": 466090, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.088373899459839, "global_step": 466091, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0416831970214844, "global_step": 466092, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.029139995574951, "global_step": 466093, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.001859188079834, "global_step": 466094, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.10231614112854, "global_step": 466095, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.057248115539551, "global_step": 466096, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.057508945465088, "global_step": 466097, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.047172784805298, "global_step": 466098, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9796617031097412, "global_step": 466099, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.090772867202759, "global_step": 466100, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0658700466156006, "global_step": 466101, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0233349800109863, "global_step": 466102, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0869362354278564, "global_step": 466103, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0212438106536865, "global_step": 466104, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0987844467163086, "global_step": 466105, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0850043296813965, "global_step": 466106, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.090660810470581, "global_step": 466107, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.068307399749756, "global_step": 466108, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0799167156219482, "global_step": 466109, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.143357515335083, "global_step": 466110, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.998359203338623, "global_step": 466111, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.200528383255005, "global_step": 466112, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.148867607116699, "global_step": 466113, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.040867805480957, "global_step": 466114, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.11248517036438, "global_step": 466115, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0567054748535156, "global_step": 466116, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.091287851333618, "global_step": 466117, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0321829319000244, "global_step": 466118, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.2097327709198, "global_step": 466119, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.117588520050049, "global_step": 466120, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.126044750213623, "global_step": 466121, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0093019008636475, "global_step": 466122, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0882503986358643, "global_step": 466123, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1844568252563477, "global_step": 466124, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.040527105331421, "global_step": 466125, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9858349561691284, "global_step": 466126, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0845327377319336, "global_step": 466127, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0160202980041504, "global_step": 466128, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.080205202102661, "global_step": 466129, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.102135181427002, "global_step": 466130, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0157148838043213, "global_step": 466131, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0827925205230713, "global_step": 466132, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.126858711242676, "global_step": 466133, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0698130130767822, "global_step": 466134, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.056666135787964, "global_step": 466135, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1565685272216797, "global_step": 466136, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.044569492340088, "global_step": 466137, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0867109298706055, "global_step": 466138, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0714962482452393, "global_step": 466139, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0553882122039795, "global_step": 466140, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0039961338043213, "global_step": 466141, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9664463996887207, "global_step": 466142, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.09675669670105, "global_step": 466143, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.010248899459839, "global_step": 466144, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.062873601913452, "global_step": 466145, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0681965351104736, "global_step": 466146, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0949599742889404, "global_step": 466147, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0577785968780518, "global_step": 466148, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1014907360076904, "global_step": 466149, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.118837594985962, "global_step": 466150, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.040893316268921, "global_step": 466151, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9836269617080688, "global_step": 466152, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1003878116607666, "global_step": 466153, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9844483137130737, "global_step": 466154, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.120978355407715, "global_step": 466155, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1376445293426514, "global_step": 466156, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1021010875701904, "global_step": 466157, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.015252113342285, "global_step": 466158, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0926477909088135, "global_step": 466159, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0753657817840576, "global_step": 466160, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0553665161132812, "global_step": 466161, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.040363311767578, "global_step": 466162, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0379674434661865, "global_step": 466163, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.181230068206787, "global_step": 466164, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.065450668334961, "global_step": 466165, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.040431261062622, "global_step": 466166, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.133622169494629, "global_step": 466167, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9718575477600098, "global_step": 466168, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.113046407699585, "global_step": 466169, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.081705331802368, "global_step": 466170, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1059069633483887, "global_step": 466171, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.037991523742676, "global_step": 466172, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0663163661956787, "global_step": 466173, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.085505485534668, "global_step": 466174, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.123589515686035, "global_step": 466175, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.111088514328003, "global_step": 466176, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.058913230895996, "global_step": 466177, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0143866539001465, "global_step": 466178, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0989089012145996, "global_step": 466179, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.014697551727295, "global_step": 466180, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0450541973114014, "global_step": 466181, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.155557155609131, "global_step": 466182, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0971426963806152, "global_step": 466183, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.124903917312622, "global_step": 466184, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.992071270942688, "global_step": 466185, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.062307119369507, "global_step": 466186, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1090869903564453, "global_step": 466187, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0589189529418945, "global_step": 466188, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.022228240966797, "global_step": 466189, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.119269371032715, "global_step": 466190, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.112391471862793, "global_step": 466191, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9825694561004639, "global_step": 466192, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.080766201019287, "global_step": 466193, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1299777030944824, "global_step": 466194, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1274290084838867, "global_step": 466195, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.118722677230835, "global_step": 466196, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.100494384765625, "global_step": 466197, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.090991735458374, "global_step": 466198, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.119940757751465, "global_step": 466199, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0745620727539062, "global_step": 466200, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9681109189987183, "global_step": 466201, "epoch": 830, "lr": 5e-05}
{"train_loss": 1.9741528034210205, "global_step": 466202, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0363094806671143, "global_step": 466203, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0544588565826416, "global_step": 466204, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.075532913208008, "global_step": 466205, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0417895317077637, "global_step": 466206, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.076584577560425, "global_step": 466207, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.081934690475464, "global_step": 466208, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0409348011016846, "global_step": 466209, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0597715377807617, "global_step": 466210, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1045854091644287, "global_step": 466211, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1893386840820312, "global_step": 466212, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0701401233673096, "global_step": 466213, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.087813377380371, "global_step": 466214, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0684008598327637, "global_step": 466215, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1012892723083496, "global_step": 466216, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.0317728519439697, "global_step": 466217, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1105034351348877, "global_step": 466218, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.016855239868164, "global_step": 466219, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.1213574409484863, "global_step": 466220, "epoch": 830, "lr": 5e-05}
{"train_loss": 2.067821979522705, "global_step": 466221, "epoch": 830, "lr": 5e-05, "val_loss": 5.687366008758545, "test_reconst_mse": 0.07392007857561111}
{"train_loss": 2.0151965618133545, "global_step": 466222, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.042685031890869, "global_step": 466223, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1033573150634766, "global_step": 466224, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.045823812484741, "global_step": 466225, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9831359386444092, "global_step": 466226, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0477452278137207, "global_step": 466227, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.144221782684326, "global_step": 466228, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.12654972076416, "global_step": 466229, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0434954166412354, "global_step": 466230, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0699303150177, "global_step": 466231, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.076963186264038, "global_step": 466232, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.06363844871521, "global_step": 466233, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.018427610397339, "global_step": 466234, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0782430171966553, "global_step": 466235, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0771002769470215, "global_step": 466236, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.035876750946045, "global_step": 466237, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.023367166519165, "global_step": 466238, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.096153736114502, "global_step": 466239, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0630645751953125, "global_step": 466240, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0616278648376465, "global_step": 466241, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0398800373077393, "global_step": 466242, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.067843437194824, "global_step": 466243, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0378434658050537, "global_step": 466244, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.993823528289795, "global_step": 466245, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.029278039932251, "global_step": 466246, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.004657745361328, "global_step": 466247, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9986554384231567, "global_step": 466248, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0504612922668457, "global_step": 466249, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9942198991775513, "global_step": 466250, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0135245323181152, "global_step": 466251, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0687386989593506, "global_step": 466252, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.052666187286377, "global_step": 466253, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.998733401298523, "global_step": 466254, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.025738477706909, "global_step": 466255, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.093935966491699, "global_step": 466256, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0493595600128174, "global_step": 466257, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.115349531173706, "global_step": 466258, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0336647033691406, "global_step": 466259, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0114240646362305, "global_step": 466260, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0872254371643066, "global_step": 466261, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0545096397399902, "global_step": 466262, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.034517288208008, "global_step": 466263, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.106687545776367, "global_step": 466264, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9984674453735352, "global_step": 466265, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0249862670898438, "global_step": 466266, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9527496099472046, "global_step": 466267, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1118462085723877, "global_step": 466268, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1239991188049316, "global_step": 466269, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1072769165039062, "global_step": 466270, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.064115285873413, "global_step": 466271, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.041778802871704, "global_step": 466272, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.101231575012207, "global_step": 466273, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0510177612304688, "global_step": 466274, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0211312770843506, "global_step": 466275, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1911351680755615, "global_step": 466276, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9816797971725464, "global_step": 466277, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0592880249023438, "global_step": 466278, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0423762798309326, "global_step": 466279, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.103243827819824, "global_step": 466280, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1418089866638184, "global_step": 466281, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0021045207977295, "global_step": 466282, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0372400283813477, "global_step": 466283, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.121408462524414, "global_step": 466284, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0069687366485596, "global_step": 466285, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0792171955108643, "global_step": 466286, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0361735820770264, "global_step": 466287, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9959969520568848, "global_step": 466288, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9747025966644287, "global_step": 466289, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.155975341796875, "global_step": 466290, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0497419834136963, "global_step": 466291, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0745503902435303, "global_step": 466292, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0600709915161133, "global_step": 466293, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.075350284576416, "global_step": 466294, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.053715467453003, "global_step": 466295, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0132455825805664, "global_step": 466296, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9791359901428223, "global_step": 466297, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.123225450515747, "global_step": 466298, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.081568956375122, "global_step": 466299, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.062640428543091, "global_step": 466300, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1049976348876953, "global_step": 466301, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0406768321990967, "global_step": 466302, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.010730266571045, "global_step": 466303, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0795857906341553, "global_step": 466304, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1040334701538086, "global_step": 466305, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.008798837661743, "global_step": 466306, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0244250297546387, "global_step": 466307, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0458731651306152, "global_step": 466308, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9957504272460938, "global_step": 466309, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1205945014953613, "global_step": 466310, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.016392230987549, "global_step": 466311, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0150794982910156, "global_step": 466312, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1149394512176514, "global_step": 466313, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9837534427642822, "global_step": 466314, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1632230281829834, "global_step": 466315, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9964536428451538, "global_step": 466316, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.989829421043396, "global_step": 466317, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.987237572669983, "global_step": 466318, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1138718128204346, "global_step": 466319, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.055230140686035, "global_step": 466320, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.013275146484375, "global_step": 466321, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9869886636734009, "global_step": 466322, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0754549503326416, "global_step": 466323, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.045836925506592, "global_step": 466324, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0521535873413086, "global_step": 466325, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0711538791656494, "global_step": 466326, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0609118938446045, "global_step": 466327, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0613040924072266, "global_step": 466328, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0765368938446045, "global_step": 466329, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0935561656951904, "global_step": 466330, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.983626365661621, "global_step": 466331, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0191590785980225, "global_step": 466332, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9946902990341187, "global_step": 466333, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.014544725418091, "global_step": 466334, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0383875370025635, "global_step": 466335, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0473906993865967, "global_step": 466336, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.054230213165283, "global_step": 466337, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1046786308288574, "global_step": 466338, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0117886066436768, "global_step": 466339, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0315146446228027, "global_step": 466340, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1587929725646973, "global_step": 466341, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.031799793243408, "global_step": 466342, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9480057954788208, "global_step": 466343, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0779738426208496, "global_step": 466344, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.10152268409729, "global_step": 466345, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0547902584075928, "global_step": 466346, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.015810012817383, "global_step": 466347, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.113403081893921, "global_step": 466348, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.010322332382202, "global_step": 466349, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.14119029045105, "global_step": 466350, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.12237811088562, "global_step": 466351, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.060626745223999, "global_step": 466352, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.038280725479126, "global_step": 466353, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0279541015625, "global_step": 466354, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.030985116958618, "global_step": 466355, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0527005195617676, "global_step": 466356, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1731250286102295, "global_step": 466357, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.076169729232788, "global_step": 466358, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0783817768096924, "global_step": 466359, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.140740156173706, "global_step": 466360, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0659635066986084, "global_step": 466361, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.023996114730835, "global_step": 466362, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1479651927948, "global_step": 466363, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.999638557434082, "global_step": 466364, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.069831132888794, "global_step": 466365, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1297454833984375, "global_step": 466366, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0756473541259766, "global_step": 466367, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0522782802581787, "global_step": 466368, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0465009212493896, "global_step": 466369, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.03865647315979, "global_step": 466370, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0981521606445312, "global_step": 466371, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1397483348846436, "global_step": 466372, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9912726879119873, "global_step": 466373, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0074403285980225, "global_step": 466374, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.098445415496826, "global_step": 466375, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.046635627746582, "global_step": 466376, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0536482334136963, "global_step": 466377, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1288325786590576, "global_step": 466378, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1077988147735596, "global_step": 466379, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.066014051437378, "global_step": 466380, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1032843589782715, "global_step": 466381, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1503803730010986, "global_step": 466382, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0986549854278564, "global_step": 466383, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.100912570953369, "global_step": 466384, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9330852031707764, "global_step": 466385, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.033384084701538, "global_step": 466386, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.03885555267334, "global_step": 466387, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.04353404045105, "global_step": 466388, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0898592472076416, "global_step": 466389, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.070931911468506, "global_step": 466390, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9936811923980713, "global_step": 466391, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.998524785041809, "global_step": 466392, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9719666242599487, "global_step": 466393, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.091055393218994, "global_step": 466394, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0773699283599854, "global_step": 466395, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.040526866912842, "global_step": 466396, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.013651132583618, "global_step": 466397, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.072889566421509, "global_step": 466398, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0048954486846924, "global_step": 466399, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0752320289611816, "global_step": 466400, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.048060178756714, "global_step": 466401, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0253446102142334, "global_step": 466402, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0072124004364014, "global_step": 466403, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0180394649505615, "global_step": 466404, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0373682975769043, "global_step": 466405, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1017353534698486, "global_step": 466406, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0343809127807617, "global_step": 466407, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.014754295349121, "global_step": 466408, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0063040256500244, "global_step": 466409, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1186094284057617, "global_step": 466410, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1089141368865967, "global_step": 466411, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.042656898498535, "global_step": 466412, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0643632411956787, "global_step": 466413, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1174423694610596, "global_step": 466414, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.087172031402588, "global_step": 466415, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.024477243423462, "global_step": 466416, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0671451091766357, "global_step": 466417, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0306806564331055, "global_step": 466418, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.028393030166626, "global_step": 466419, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.134860038757324, "global_step": 466420, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0071427822113037, "global_step": 466421, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.100522994995117, "global_step": 466422, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.036360025405884, "global_step": 466423, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0912773609161377, "global_step": 466424, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1319241523742676, "global_step": 466425, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0327982902526855, "global_step": 466426, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0531039237976074, "global_step": 466427, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1079440116882324, "global_step": 466428, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0242393016815186, "global_step": 466429, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.101435661315918, "global_step": 466430, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0359129905700684, "global_step": 466431, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.011570692062378, "global_step": 466432, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0512218475341797, "global_step": 466433, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.056635856628418, "global_step": 466434, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1462008953094482, "global_step": 466435, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0223331451416016, "global_step": 466436, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.063749074935913, "global_step": 466437, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.038663864135742, "global_step": 466438, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1113059520721436, "global_step": 466439, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.111591339111328, "global_step": 466440, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.055513858795166, "global_step": 466441, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.066650629043579, "global_step": 466442, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0497825145721436, "global_step": 466443, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.07546329498291, "global_step": 466444, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0721404552459717, "global_step": 466445, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0860586166381836, "global_step": 466446, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0492053031921387, "global_step": 466447, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1038784980773926, "global_step": 466448, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.049414873123169, "global_step": 466449, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0276851654052734, "global_step": 466450, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1156997680664062, "global_step": 466451, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9989534616470337, "global_step": 466452, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9945663213729858, "global_step": 466453, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0493855476379395, "global_step": 466454, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0612895488739014, "global_step": 466455, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.074239492416382, "global_step": 466456, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.956379771232605, "global_step": 466457, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.102210760116577, "global_step": 466458, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0414533615112305, "global_step": 466459, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.105555295944214, "global_step": 466460, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9953337907791138, "global_step": 466461, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0040395259857178, "global_step": 466462, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0113911628723145, "global_step": 466463, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0573437213897705, "global_step": 466464, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.04471755027771, "global_step": 466465, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.102949380874634, "global_step": 466466, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.184699535369873, "global_step": 466467, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.009800910949707, "global_step": 466468, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0368452072143555, "global_step": 466469, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0251495838165283, "global_step": 466470, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1220626831054688, "global_step": 466471, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0137038230895996, "global_step": 466472, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.007323741912842, "global_step": 466473, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.996720552444458, "global_step": 466474, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9578379392623901, "global_step": 466475, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.05698561668396, "global_step": 466476, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0461995601654053, "global_step": 466477, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0573902130126953, "global_step": 466478, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.135225534439087, "global_step": 466479, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0456907749176025, "global_step": 466480, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.042532205581665, "global_step": 466481, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.09342360496521, "global_step": 466482, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0732667446136475, "global_step": 466483, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0152204036712646, "global_step": 466484, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1061296463012695, "global_step": 466485, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.048043727874756, "global_step": 466486, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1124978065490723, "global_step": 466487, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.087123155593872, "global_step": 466488, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9897501468658447, "global_step": 466489, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0058467388153076, "global_step": 466490, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.060483694076538, "global_step": 466491, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1154985427856445, "global_step": 466492, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.081770181655884, "global_step": 466493, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0190911293029785, "global_step": 466494, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1453535556793213, "global_step": 466495, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0514659881591797, "global_step": 466496, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.017091751098633, "global_step": 466497, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1014177799224854, "global_step": 466498, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0684282779693604, "global_step": 466499, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.008558750152588, "global_step": 466500, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0077881813049316, "global_step": 466501, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9462740421295166, "global_step": 466502, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.113168716430664, "global_step": 466503, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9978448152542114, "global_step": 466504, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1166012287139893, "global_step": 466505, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0658371448516846, "global_step": 466506, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0822064876556396, "global_step": 466507, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1071722507476807, "global_step": 466508, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0847930908203125, "global_step": 466509, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.148715019226074, "global_step": 466510, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0932178497314453, "global_step": 466511, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0797061920166016, "global_step": 466512, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.091168165206909, "global_step": 466513, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1339516639709473, "global_step": 466514, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0370640754699707, "global_step": 466515, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1194114685058594, "global_step": 466516, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0859010219573975, "global_step": 466517, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1336116790771484, "global_step": 466518, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9411815404891968, "global_step": 466519, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.124650001525879, "global_step": 466520, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.007601499557495, "global_step": 466521, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0344386100769043, "global_step": 466522, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0439512729644775, "global_step": 466523, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0668487548828125, "global_step": 466524, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1069865226745605, "global_step": 466525, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.10023832321167, "global_step": 466526, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.065267324447632, "global_step": 466527, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.133681535720825, "global_step": 466528, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0915653705596924, "global_step": 466529, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1260647773742676, "global_step": 466530, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.005406379699707, "global_step": 466531, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0355236530303955, "global_step": 466532, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0128731727600098, "global_step": 466533, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.998138666152954, "global_step": 466534, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.028810501098633, "global_step": 466535, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.031182050704956, "global_step": 466536, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.091480016708374, "global_step": 466537, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0733673572540283, "global_step": 466538, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0736522674560547, "global_step": 466539, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0366485118865967, "global_step": 466540, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0555646419525146, "global_step": 466541, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.078752040863037, "global_step": 466542, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0257184505462646, "global_step": 466543, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0485591888427734, "global_step": 466544, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1756591796875, "global_step": 466545, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0760462284088135, "global_step": 466546, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.116180658340454, "global_step": 466547, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.072385311126709, "global_step": 466548, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.096133232116699, "global_step": 466549, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.14239501953125, "global_step": 466550, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.091710090637207, "global_step": 466551, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1231024265289307, "global_step": 466552, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0416035652160645, "global_step": 466553, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0095529556274414, "global_step": 466554, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0165886878967285, "global_step": 466555, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.137629270553589, "global_step": 466556, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9945191144943237, "global_step": 466557, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0367112159729004, "global_step": 466558, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1042847633361816, "global_step": 466559, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.100904941558838, "global_step": 466560, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0586743354797363, "global_step": 466561, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1165781021118164, "global_step": 466562, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.012028694152832, "global_step": 466563, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.094032049179077, "global_step": 466564, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0492935180664062, "global_step": 466565, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.014951467514038, "global_step": 466566, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.156096935272217, "global_step": 466567, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.072662830352783, "global_step": 466568, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0240025520324707, "global_step": 466569, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.062931776046753, "global_step": 466570, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0594096183776855, "global_step": 466571, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.124910354614258, "global_step": 466572, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.119718074798584, "global_step": 466573, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.007585287094116, "global_step": 466574, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.016021251678467, "global_step": 466575, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.000067949295044, "global_step": 466576, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0821638107299805, "global_step": 466577, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0769011974334717, "global_step": 466578, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.068931818008423, "global_step": 466579, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1212191581726074, "global_step": 466580, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1097311973571777, "global_step": 466581, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.053194999694824, "global_step": 466582, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.158607244491577, "global_step": 466583, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0691614151000977, "global_step": 466584, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1178057193756104, "global_step": 466585, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0383694171905518, "global_step": 466586, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1115851402282715, "global_step": 466587, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0448391437530518, "global_step": 466588, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0962774753570557, "global_step": 466589, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.022245168685913, "global_step": 466590, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0552937984466553, "global_step": 466591, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.053908348083496, "global_step": 466592, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0706124305725098, "global_step": 466593, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.083198070526123, "global_step": 466594, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.994490385055542, "global_step": 466595, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0877315998077393, "global_step": 466596, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0749950408935547, "global_step": 466597, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.085252285003662, "global_step": 466598, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.166783332824707, "global_step": 466599, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.040062189102173, "global_step": 466600, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0289840698242188, "global_step": 466601, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0035462379455566, "global_step": 466602, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9921941757202148, "global_step": 466603, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0320215225219727, "global_step": 466604, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9957925081253052, "global_step": 466605, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.075953483581543, "global_step": 466606, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0779550075531006, "global_step": 466607, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.092151403427124, "global_step": 466608, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0105414390563965, "global_step": 466609, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0045132637023926, "global_step": 466610, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0997159481048584, "global_step": 466611, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0703377723693848, "global_step": 466612, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0588202476501465, "global_step": 466613, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0852694511413574, "global_step": 466614, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0504417419433594, "global_step": 466615, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1236369609832764, "global_step": 466616, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1276276111602783, "global_step": 466617, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9675098657608032, "global_step": 466618, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1789228916168213, "global_step": 466619, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.042696475982666, "global_step": 466620, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0720198154449463, "global_step": 466621, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0402774810791016, "global_step": 466622, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1361637115478516, "global_step": 466623, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1120989322662354, "global_step": 466624, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0937986373901367, "global_step": 466625, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9904261827468872, "global_step": 466626, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.03656268119812, "global_step": 466627, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.090625524520874, "global_step": 466628, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.081442356109619, "global_step": 466629, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.069265604019165, "global_step": 466630, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9990884065628052, "global_step": 466631, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.051194906234741, "global_step": 466632, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0173611640930176, "global_step": 466633, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.098824977874756, "global_step": 466634, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0547192096710205, "global_step": 466635, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0252816677093506, "global_step": 466636, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0657410621643066, "global_step": 466637, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1107380390167236, "global_step": 466638, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0451772212982178, "global_step": 466639, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.108135461807251, "global_step": 466640, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0668487548828125, "global_step": 466641, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1663479804992676, "global_step": 466642, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9832675457000732, "global_step": 466643, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0436809062957764, "global_step": 466644, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.132909059524536, "global_step": 466645, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0516014099121094, "global_step": 466646, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0007824897766113, "global_step": 466647, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1080780029296875, "global_step": 466648, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.111506938934326, "global_step": 466649, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.025871753692627, "global_step": 466650, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1296162605285645, "global_step": 466651, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9767998456954956, "global_step": 466652, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.00942325592041, "global_step": 466653, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9539817571640015, "global_step": 466654, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.012348175048828, "global_step": 466655, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0612473487854004, "global_step": 466656, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0793545246124268, "global_step": 466657, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9824172258377075, "global_step": 466658, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0373528003692627, "global_step": 466659, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.067150354385376, "global_step": 466660, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1174001693725586, "global_step": 466661, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.149038076400757, "global_step": 466662, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.083113670349121, "global_step": 466663, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.053485870361328, "global_step": 466664, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1510798931121826, "global_step": 466665, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.119511604309082, "global_step": 466666, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.079313039779663, "global_step": 466667, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.087660074234009, "global_step": 466668, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0805535316467285, "global_step": 466669, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.107316017150879, "global_step": 466670, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.073875665664673, "global_step": 466671, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.083350658416748, "global_step": 466672, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9800760746002197, "global_step": 466673, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0343499183654785, "global_step": 466674, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0539581775665283, "global_step": 466675, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.075925827026367, "global_step": 466676, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0432653427124023, "global_step": 466677, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9706722497940063, "global_step": 466678, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.102485179901123, "global_step": 466679, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1048171520233154, "global_step": 466680, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0546152591705322, "global_step": 466681, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0922327041625977, "global_step": 466682, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0803005695343018, "global_step": 466683, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1383001804351807, "global_step": 466684, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9980199337005615, "global_step": 466685, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.036550998687744, "global_step": 466686, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.045079469680786, "global_step": 466687, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.054549217224121, "global_step": 466688, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9751052856445312, "global_step": 466689, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0811045169830322, "global_step": 466690, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1539812088012695, "global_step": 466691, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0981132984161377, "global_step": 466692, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0435447692871094, "global_step": 466693, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0591607093811035, "global_step": 466694, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.077028512954712, "global_step": 466695, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9908443689346313, "global_step": 466696, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0842487812042236, "global_step": 466697, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0205087661743164, "global_step": 466698, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0820045471191406, "global_step": 466699, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.074002504348755, "global_step": 466700, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0714852809906006, "global_step": 466701, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.051793336868286, "global_step": 466702, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0911431312561035, "global_step": 466703, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.04653000831604, "global_step": 466704, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0750818252563477, "global_step": 466705, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.102006435394287, "global_step": 466706, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.044560194015503, "global_step": 466707, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1021759510040283, "global_step": 466708, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0522632598876953, "global_step": 466709, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0415327548980713, "global_step": 466710, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.045128345489502, "global_step": 466711, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.022676944732666, "global_step": 466712, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0556411743164062, "global_step": 466713, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.008242607116699, "global_step": 466714, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0479187965393066, "global_step": 466715, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0669353008270264, "global_step": 466716, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.119551420211792, "global_step": 466717, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0982789993286133, "global_step": 466718, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0837044715881348, "global_step": 466719, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0586299896240234, "global_step": 466720, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0598666667938232, "global_step": 466721, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0887444019317627, "global_step": 466722, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.091442823410034, "global_step": 466723, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1056928634643555, "global_step": 466724, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0928683280944824, "global_step": 466725, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.05551815032959, "global_step": 466726, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.05279541015625, "global_step": 466727, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1307878494262695, "global_step": 466728, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.052877426147461, "global_step": 466729, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.065558910369873, "global_step": 466730, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.170759916305542, "global_step": 466731, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0918030738830566, "global_step": 466732, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0586729049682617, "global_step": 466733, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0482072830200195, "global_step": 466734, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.900533676147461, "global_step": 466735, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0283164978027344, "global_step": 466736, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0412795543670654, "global_step": 466737, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.125206470489502, "global_step": 466738, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.999602198600769, "global_step": 466739, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.090923547744751, "global_step": 466740, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0371577739715576, "global_step": 466741, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.168067216873169, "global_step": 466742, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.108006715774536, "global_step": 466743, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9944937229156494, "global_step": 466744, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.074225664138794, "global_step": 466745, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1324751377105713, "global_step": 466746, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.033440351486206, "global_step": 466747, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0760533809661865, "global_step": 466748, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.100658655166626, "global_step": 466749, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0193421840667725, "global_step": 466750, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0941927433013916, "global_step": 466751, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.021635055541992, "global_step": 466752, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.978249430656433, "global_step": 466753, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.105703830718994, "global_step": 466754, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0614876747131348, "global_step": 466755, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1387925148010254, "global_step": 466756, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0811007022857666, "global_step": 466757, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.143925428390503, "global_step": 466758, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0428009033203125, "global_step": 466759, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.074126720428467, "global_step": 466760, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.03062105178833, "global_step": 466761, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.019057512283325, "global_step": 466762, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1614747047424316, "global_step": 466763, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.012221574783325, "global_step": 466764, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.059854507446289, "global_step": 466765, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0070505142211914, "global_step": 466766, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9399960041046143, "global_step": 466767, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.082437038421631, "global_step": 466768, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.10001277923584, "global_step": 466769, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1004252433776855, "global_step": 466770, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0535776615142822, "global_step": 466771, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0888803005218506, "global_step": 466772, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.148324728012085, "global_step": 466773, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.149806261062622, "global_step": 466774, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9600671529769897, "global_step": 466775, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.983238935470581, "global_step": 466776, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0325815677642822, "global_step": 466777, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9705697298049927, "global_step": 466778, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.076019763946533, "global_step": 466779, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0993106365203857, "global_step": 466780, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.962113618850708, "global_step": 466781, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0473251342773438, "global_step": 466782, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0443077087402344, "global_step": 466783, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.089235544204712, "global_step": 466784, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.034449577331543, "global_step": 466785, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1318283081054688, "global_step": 466786, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.019848346710205, "global_step": 466787, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0625128746032715, "global_step": 466788, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0377283096313477, "global_step": 466789, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.009058713912964, "global_step": 466790, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.972177505493164, "global_step": 466791, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0876669883728027, "global_step": 466792, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0450496673583984, "global_step": 466793, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0713469982147217, "global_step": 466794, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.109806776046753, "global_step": 466795, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.087987184524536, "global_step": 466796, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.071457624435425, "global_step": 466797, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.069145441055298, "global_step": 466798, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.110774278640747, "global_step": 466799, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1202523708343506, "global_step": 466800, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.070945978164673, "global_step": 466801, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1717610359191895, "global_step": 466802, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0809547901153564, "global_step": 466803, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1024208068847656, "global_step": 466804, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0126757621765137, "global_step": 466805, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9212214946746826, "global_step": 466806, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0137057304382324, "global_step": 466807, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1322083473205566, "global_step": 466808, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1227951049804688, "global_step": 466809, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0517191886901855, "global_step": 466810, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9841440916061401, "global_step": 466811, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0380289554595947, "global_step": 466812, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0995991230010986, "global_step": 466813, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0646984577178955, "global_step": 466814, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0593652725219727, "global_step": 466815, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.083742141723633, "global_step": 466816, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1075925827026367, "global_step": 466817, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.075195074081421, "global_step": 466818, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0290400981903076, "global_step": 466819, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0224215984344482, "global_step": 466820, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0939347743988037, "global_step": 466821, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1464858055114746, "global_step": 466822, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.143850803375244, "global_step": 466823, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.057187557220459, "global_step": 466824, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0613479614257812, "global_step": 466825, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.09236478805542, "global_step": 466826, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0832207202911377, "global_step": 466827, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0175347328186035, "global_step": 466828, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0021255016326904, "global_step": 466829, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0387027263641357, "global_step": 466830, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.013157606124878, "global_step": 466831, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9816652536392212, "global_step": 466832, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9734421968460083, "global_step": 466833, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0958147048950195, "global_step": 466834, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0786757469177246, "global_step": 466835, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0488269329071045, "global_step": 466836, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.065005302429199, "global_step": 466837, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.05450701713562, "global_step": 466838, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.061110734939575, "global_step": 466839, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0321333408355713, "global_step": 466840, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1181135177612305, "global_step": 466841, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1071252822875977, "global_step": 466842, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0690722465515137, "global_step": 466843, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0730161666870117, "global_step": 466844, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0734357833862305, "global_step": 466845, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0674984455108643, "global_step": 466846, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1091766357421875, "global_step": 466847, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.098795175552368, "global_step": 466848, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.068434000015259, "global_step": 466849, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.093897581100464, "global_step": 466850, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0775952339172363, "global_step": 466851, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0061895847320557, "global_step": 466852, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.032961845397949, "global_step": 466853, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.041565418243408, "global_step": 466854, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0720319747924805, "global_step": 466855, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.037083625793457, "global_step": 466856, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.027303457260132, "global_step": 466857, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0606729984283447, "global_step": 466858, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0634336471557617, "global_step": 466859, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.021130084991455, "global_step": 466860, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.028632402420044, "global_step": 466861, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.094391107559204, "global_step": 466862, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0836031436920166, "global_step": 466863, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0263116359710693, "global_step": 466864, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.02841854095459, "global_step": 466865, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0767147541046143, "global_step": 466866, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1457679271698, "global_step": 466867, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.060528039932251, "global_step": 466868, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0619847774505615, "global_step": 466869, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.002485752105713, "global_step": 466870, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0761685371398926, "global_step": 466871, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0588796138763428, "global_step": 466872, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.079986810684204, "global_step": 466873, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.074777841567993, "global_step": 466874, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0027265548706055, "global_step": 466875, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0727434158325195, "global_step": 466876, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0280961990356445, "global_step": 466877, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.022857189178467, "global_step": 466878, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0467779636383057, "global_step": 466879, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1642069816589355, "global_step": 466880, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.022012233734131, "global_step": 466881, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9968719482421875, "global_step": 466882, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0735607147216797, "global_step": 466883, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.096975326538086, "global_step": 466884, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1393685340881348, "global_step": 466885, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.044489622116089, "global_step": 466886, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.017791271209717, "global_step": 466887, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0596494674682617, "global_step": 466888, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1039717197418213, "global_step": 466889, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1367201805114746, "global_step": 466890, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0271148681640625, "global_step": 466891, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.134237289428711, "global_step": 466892, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.059208631515503, "global_step": 466893, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0065619945526123, "global_step": 466894, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0453550815582275, "global_step": 466895, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.107044219970703, "global_step": 466896, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.035443067550659, "global_step": 466897, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.079721450805664, "global_step": 466898, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0931010246276855, "global_step": 466899, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0365798473358154, "global_step": 466900, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1316335201263428, "global_step": 466901, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.079425573348999, "global_step": 466902, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.152574300765991, "global_step": 466903, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.057648181915283, "global_step": 466904, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.162245273590088, "global_step": 466905, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1375434398651123, "global_step": 466906, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.054549217224121, "global_step": 466907, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0169270038604736, "global_step": 466908, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.097465753555298, "global_step": 466909, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.110408306121826, "global_step": 466910, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9953513145446777, "global_step": 466911, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0667386054992676, "global_step": 466912, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0876879692077637, "global_step": 466913, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.087491989135742, "global_step": 466914, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0544302463531494, "global_step": 466915, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0649640560150146, "global_step": 466916, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1267030239105225, "global_step": 466917, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.077393054962158, "global_step": 466918, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0334012508392334, "global_step": 466919, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0142080783843994, "global_step": 466920, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1000916957855225, "global_step": 466921, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.115598678588867, "global_step": 466922, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.032292127609253, "global_step": 466923, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9423856735229492, "global_step": 466924, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1535723209381104, "global_step": 466925, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0231130123138428, "global_step": 466926, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.038235902786255, "global_step": 466927, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.135044813156128, "global_step": 466928, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.084304094314575, "global_step": 466929, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0853464603424072, "global_step": 466930, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.073974370956421, "global_step": 466931, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.118544816970825, "global_step": 466932, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1295766830444336, "global_step": 466933, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0553343296051025, "global_step": 466934, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1340904235839844, "global_step": 466935, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0144152641296387, "global_step": 466936, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.050908327102661, "global_step": 466937, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0501370429992676, "global_step": 466938, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.087383985519409, "global_step": 466939, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9897823333740234, "global_step": 466940, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.128783702850342, "global_step": 466941, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0464043617248535, "global_step": 466942, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.064039707183838, "global_step": 466943, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0246164798736572, "global_step": 466944, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.093312978744507, "global_step": 466945, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0547125339508057, "global_step": 466946, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0758349895477295, "global_step": 466947, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.981775164604187, "global_step": 466948, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.030827045440674, "global_step": 466949, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.086484909057617, "global_step": 466950, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1033551692962646, "global_step": 466951, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0779426097869873, "global_step": 466952, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1081998348236084, "global_step": 466953, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.120028257369995, "global_step": 466954, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0383496284484863, "global_step": 466955, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0199437141418457, "global_step": 466956, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0643343925476074, "global_step": 466957, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.093385696411133, "global_step": 466958, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0495553016662598, "global_step": 466959, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.064962863922119, "global_step": 466960, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.115079879760742, "global_step": 466961, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.034263849258423, "global_step": 466962, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.045283317565918, "global_step": 466963, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.071317672729492, "global_step": 466964, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0606908798217773, "global_step": 466965, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0770857334136963, "global_step": 466966, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0372581481933594, "global_step": 466967, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0450379848480225, "global_step": 466968, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0500996112823486, "global_step": 466969, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0895237922668457, "global_step": 466970, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0641121864318848, "global_step": 466971, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.004589319229126, "global_step": 466972, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0181779861450195, "global_step": 466973, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.046156167984009, "global_step": 466974, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.010721445083618, "global_step": 466975, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0274596214294434, "global_step": 466976, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.996898889541626, "global_step": 466977, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.026754140853882, "global_step": 466978, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0526976585388184, "global_step": 466979, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.008105754852295, "global_step": 466980, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0051517486572266, "global_step": 466981, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1341774463653564, "global_step": 466982, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0120649337768555, "global_step": 466983, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0332276821136475, "global_step": 466984, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.056262969970703, "global_step": 466985, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.060741662979126, "global_step": 466986, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.074183464050293, "global_step": 466987, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1275272369384766, "global_step": 466988, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.034421920776367, "global_step": 466989, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0691967010498047, "global_step": 466990, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0817818641662598, "global_step": 466991, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.07116961479187, "global_step": 466992, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.072265625, "global_step": 466993, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0529980659484863, "global_step": 466994, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0476555824279785, "global_step": 466995, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.997515082359314, "global_step": 466996, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9799960851669312, "global_step": 466997, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.046398401260376, "global_step": 466998, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.065192461013794, "global_step": 466999, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.068920850753784, "global_step": 467000, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0516481399536133, "global_step": 467001, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0041446685791016, "global_step": 467002, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.120347738265991, "global_step": 467003, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0725014209747314, "global_step": 467004, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1082191467285156, "global_step": 467005, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0551397800445557, "global_step": 467006, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.162830114364624, "global_step": 467007, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.110196352005005, "global_step": 467008, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0134708881378174, "global_step": 467009, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.043635845184326, "global_step": 467010, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.186318874359131, "global_step": 467011, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0982301235198975, "global_step": 467012, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.066394329071045, "global_step": 467013, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0712990760803223, "global_step": 467014, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0557861328125, "global_step": 467015, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.118434190750122, "global_step": 467016, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.120939254760742, "global_step": 467017, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1543853282928467, "global_step": 467018, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9784551858901978, "global_step": 467019, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0844640731811523, "global_step": 467020, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.028467893600464, "global_step": 467021, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.119180679321289, "global_step": 467022, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.102287530899048, "global_step": 467023, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.060980796813965, "global_step": 467024, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9950200319290161, "global_step": 467025, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1426780223846436, "global_step": 467026, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0757129192352295, "global_step": 467027, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0375890731811523, "global_step": 467028, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1370182037353516, "global_step": 467029, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.128917694091797, "global_step": 467030, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.048475980758667, "global_step": 467031, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.026258945465088, "global_step": 467032, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0604333877563477, "global_step": 467033, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.992419719696045, "global_step": 467034, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0610008239746094, "global_step": 467035, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0738439559936523, "global_step": 467036, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0987048149108887, "global_step": 467037, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.090090751647949, "global_step": 467038, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0911576747894287, "global_step": 467039, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0332610607147217, "global_step": 467040, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.120035171508789, "global_step": 467041, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1209208965301514, "global_step": 467042, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0583553314208984, "global_step": 467043, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1184470653533936, "global_step": 467044, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.056478500366211, "global_step": 467045, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.040649652481079, "global_step": 467046, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9728446006774902, "global_step": 467047, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.075230598449707, "global_step": 467048, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0226922035217285, "global_step": 467049, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.065866708755493, "global_step": 467050, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.073408365249634, "global_step": 467051, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.112292528152466, "global_step": 467052, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.148756504058838, "global_step": 467053, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.011373996734619, "global_step": 467054, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.13106107711792, "global_step": 467055, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.010080337524414, "global_step": 467056, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1069231033325195, "global_step": 467057, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.063462018966675, "global_step": 467058, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.141528367996216, "global_step": 467059, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.087310552597046, "global_step": 467060, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0763473510742188, "global_step": 467061, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.126190423965454, "global_step": 467062, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.109368324279785, "global_step": 467063, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0218513011932373, "global_step": 467064, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0495989322662354, "global_step": 467065, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0364387035369873, "global_step": 467066, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0131866931915283, "global_step": 467067, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.114201307296753, "global_step": 467068, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0601274967193604, "global_step": 467069, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0778379440307617, "global_step": 467070, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0318074226379395, "global_step": 467071, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.047485828399658, "global_step": 467072, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.078531503677368, "global_step": 467073, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.075648307800293, "global_step": 467074, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.073324680328369, "global_step": 467075, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0520312786102295, "global_step": 467076, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.010051727294922, "global_step": 467077, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.085622787475586, "global_step": 467078, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0712218284606934, "global_step": 467079, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0697810649871826, "global_step": 467080, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.118168354034424, "global_step": 467081, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0722551345825195, "global_step": 467082, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.103952646255493, "global_step": 467083, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.067958354949951, "global_step": 467084, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.033982992172241, "global_step": 467085, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0650503635406494, "global_step": 467086, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0927517414093018, "global_step": 467087, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.100966453552246, "global_step": 467088, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0071535110473633, "global_step": 467089, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0106213092803955, "global_step": 467090, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0602524280548096, "global_step": 467091, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.054440975189209, "global_step": 467092, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1593074798583984, "global_step": 467093, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0402302742004395, "global_step": 467094, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.067936420440674, "global_step": 467095, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0714924335479736, "global_step": 467096, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.11869215965271, "global_step": 467097, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0565643310546875, "global_step": 467098, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.04278826713562, "global_step": 467099, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0870320796966553, "global_step": 467100, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1591744422912598, "global_step": 467101, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0388896465301514, "global_step": 467102, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.034355878829956, "global_step": 467103, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1357152462005615, "global_step": 467104, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.116778612136841, "global_step": 467105, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1186912059783936, "global_step": 467106, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0149855613708496, "global_step": 467107, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.150242328643799, "global_step": 467108, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.012305498123169, "global_step": 467109, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.031635284423828, "global_step": 467110, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.052154779434204, "global_step": 467111, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.120222568511963, "global_step": 467112, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1059086322784424, "global_step": 467113, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1377084255218506, "global_step": 467114, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0803544521331787, "global_step": 467115, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1320111751556396, "global_step": 467116, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1469151973724365, "global_step": 467117, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9789807796478271, "global_step": 467118, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1563937664031982, "global_step": 467119, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1213650703430176, "global_step": 467120, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0630359649658203, "global_step": 467121, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0917720794677734, "global_step": 467122, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.038532018661499, "global_step": 467123, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9690827131271362, "global_step": 467124, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1434335708618164, "global_step": 467125, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0816216468811035, "global_step": 467126, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1325395107269287, "global_step": 467127, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1155076026916504, "global_step": 467128, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1349849700927734, "global_step": 467129, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0848844051361084, "global_step": 467130, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1257340908050537, "global_step": 467131, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.067256450653076, "global_step": 467132, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.068406343460083, "global_step": 467133, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.136298418045044, "global_step": 467134, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.115115165710449, "global_step": 467135, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.105081081390381, "global_step": 467136, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0451765060424805, "global_step": 467137, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0784389972686768, "global_step": 467138, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1349339485168457, "global_step": 467139, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.062626361846924, "global_step": 467140, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.106531858444214, "global_step": 467141, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0717368125915527, "global_step": 467142, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.038034200668335, "global_step": 467143, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.003505229949951, "global_step": 467144, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1128499507904053, "global_step": 467145, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0848305225372314, "global_step": 467146, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0357136726379395, "global_step": 467147, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.072049617767334, "global_step": 467148, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.019695520401001, "global_step": 467149, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0674054622650146, "global_step": 467150, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1805288791656494, "global_step": 467151, "epoch": 831, "lr": 5e-05}
{"train_loss": 1.9736034870147705, "global_step": 467152, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0490036010742188, "global_step": 467153, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.107903480529785, "global_step": 467154, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0944783687591553, "global_step": 467155, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0685698986053467, "global_step": 467156, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.13399600982666, "global_step": 467157, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0476837158203125, "global_step": 467158, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.057853937149048, "global_step": 467159, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0831241607666016, "global_step": 467160, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0537168979644775, "global_step": 467161, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.045362949371338, "global_step": 467162, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.045490026473999, "global_step": 467163, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0943572521209717, "global_step": 467164, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.2137539386749268, "global_step": 467165, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0193753242492676, "global_step": 467166, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0719735622406006, "global_step": 467167, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0382776260375977, "global_step": 467168, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.097262382507324, "global_step": 467169, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1649250984191895, "global_step": 467170, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0527608394622803, "global_step": 467171, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1329150199890137, "global_step": 467172, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.02427339553833, "global_step": 467173, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0012853145599365, "global_step": 467174, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.082916736602783, "global_step": 467175, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0508201122283936, "global_step": 467176, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0113701820373535, "global_step": 467177, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.098519802093506, "global_step": 467178, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.161940097808838, "global_step": 467179, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.041069984436035, "global_step": 467180, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0652291774749756, "global_step": 467181, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.109178304672241, "global_step": 467182, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0803298950195312, "global_step": 467183, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.031996011734009, "global_step": 467184, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.1351749897003174, "global_step": 467185, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.066720724105835, "global_step": 467186, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.067246198654175, "global_step": 467187, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.051846981048584, "global_step": 467188, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0538723468780518, "global_step": 467189, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.064586639404297, "global_step": 467190, "epoch": 831, "lr": 5e-05}
{"train_loss": 2.0895886421203613, "global_step": 467191, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.116422414779663, "global_step": 467192, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.011624336242676, "global_step": 467193, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0903561115264893, "global_step": 467194, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9496264457702637, "global_step": 467195, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0779311656951904, "global_step": 467196, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0999975204467773, "global_step": 467197, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0540802478790283, "global_step": 467198, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9909641742706299, "global_step": 467199, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0254619121551514, "global_step": 467200, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0607917308807373, "global_step": 467201, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.092297077178955, "global_step": 467202, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1281564235687256, "global_step": 467203, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.069344997406006, "global_step": 467204, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0576956272125244, "global_step": 467205, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.10910964012146, "global_step": 467206, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.05375337600708, "global_step": 467207, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0240001678466797, "global_step": 467208, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.021489143371582, "global_step": 467209, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1434109210968018, "global_step": 467210, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9981358051300049, "global_step": 467211, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0113940238952637, "global_step": 467212, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.097761869430542, "global_step": 467213, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9910372495651245, "global_step": 467214, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0492312908172607, "global_step": 467215, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0992777347564697, "global_step": 467216, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.07867431640625, "global_step": 467217, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0205376148223877, "global_step": 467218, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.026531934738159, "global_step": 467219, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.050520420074463, "global_step": 467220, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.085524797439575, "global_step": 467221, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0271763801574707, "global_step": 467222, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.002779960632324, "global_step": 467223, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.051917314529419, "global_step": 467224, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.985270380973816, "global_step": 467225, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.089803695678711, "global_step": 467226, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.032766103744507, "global_step": 467227, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.035015821456909, "global_step": 467228, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.085054636001587, "global_step": 467229, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.006866216659546, "global_step": 467230, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.133781909942627, "global_step": 467231, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0798346996307373, "global_step": 467232, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0896265506744385, "global_step": 467233, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.060481071472168, "global_step": 467234, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1253855228424072, "global_step": 467235, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.083434581756592, "global_step": 467236, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0573370456695557, "global_step": 467237, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.068620443344116, "global_step": 467238, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.923850178718567, "global_step": 467239, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.092949867248535, "global_step": 467240, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0772032737731934, "global_step": 467241, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1016361713409424, "global_step": 467242, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1157188415527344, "global_step": 467243, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0741233825683594, "global_step": 467244, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9702314138412476, "global_step": 467245, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9973864555358887, "global_step": 467246, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.027318239212036, "global_step": 467247, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.020737648010254, "global_step": 467248, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9931203126907349, "global_step": 467249, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0352673530578613, "global_step": 467250, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.102731704711914, "global_step": 467251, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0178301334381104, "global_step": 467252, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0352818965911865, "global_step": 467253, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0834908485412598, "global_step": 467254, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.111701726913452, "global_step": 467255, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9533052444458008, "global_step": 467256, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.026398181915283, "global_step": 467257, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.028620719909668, "global_step": 467258, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0571646690368652, "global_step": 467259, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.060734510421753, "global_step": 467260, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.994563341140747, "global_step": 467261, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0834414958953857, "global_step": 467262, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1360716819763184, "global_step": 467263, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.061687469482422, "global_step": 467264, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1323301792144775, "global_step": 467265, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.088663339614868, "global_step": 467266, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0603091716766357, "global_step": 467267, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1207275390625, "global_step": 467268, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.01076340675354, "global_step": 467269, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.131337881088257, "global_step": 467270, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.095900535583496, "global_step": 467271, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1198575496673584, "global_step": 467272, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0628716945648193, "global_step": 467273, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0238661766052246, "global_step": 467274, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0860841274261475, "global_step": 467275, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.073683261871338, "global_step": 467276, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0454652309417725, "global_step": 467277, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.065871238708496, "global_step": 467278, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0201938152313232, "global_step": 467279, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0750999450683594, "global_step": 467280, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0403809547424316, "global_step": 467281, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.094805955886841, "global_step": 467282, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0108563899993896, "global_step": 467283, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9807469844818115, "global_step": 467284, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0695853233337402, "global_step": 467285, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0150060653686523, "global_step": 467286, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.068981885910034, "global_step": 467287, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9394066333770752, "global_step": 467288, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0492916107177734, "global_step": 467289, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.037278413772583, "global_step": 467290, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1559531688690186, "global_step": 467291, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1548986434936523, "global_step": 467292, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.07489275932312, "global_step": 467293, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0867509841918945, "global_step": 467294, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.014819860458374, "global_step": 467295, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0659756660461426, "global_step": 467296, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.980278491973877, "global_step": 467297, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9772999286651611, "global_step": 467298, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.067445993423462, "global_step": 467299, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0461912155151367, "global_step": 467300, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.976161003112793, "global_step": 467301, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0221264362335205, "global_step": 467302, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.123814582824707, "global_step": 467303, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.073361396789551, "global_step": 467304, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.120488405227661, "global_step": 467305, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0584001541137695, "global_step": 467306, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.018078088760376, "global_step": 467307, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0354156494140625, "global_step": 467308, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0640907287597656, "global_step": 467309, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0540730953216553, "global_step": 467310, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0722289085388184, "global_step": 467311, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0993244647979736, "global_step": 467312, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0567662715911865, "global_step": 467313, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.090298891067505, "global_step": 467314, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1007816791534424, "global_step": 467315, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0993690490722656, "global_step": 467316, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0653395652770996, "global_step": 467317, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0173983573913574, "global_step": 467318, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0689375400543213, "global_step": 467319, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1218419075012207, "global_step": 467320, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.059211015701294, "global_step": 467321, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.123131036758423, "global_step": 467322, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0648088455200195, "global_step": 467323, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.080200433731079, "global_step": 467324, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0132062435150146, "global_step": 467325, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0706911087036133, "global_step": 467326, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0281589031219482, "global_step": 467327, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0595221519470215, "global_step": 467328, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.090923547744751, "global_step": 467329, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0030720233917236, "global_step": 467330, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0069169998168945, "global_step": 467331, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.07159423828125, "global_step": 467332, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1119704246520996, "global_step": 467333, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0182645320892334, "global_step": 467334, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.02736496925354, "global_step": 467335, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.004326581954956, "global_step": 467336, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.988179326057434, "global_step": 467337, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0086669921875, "global_step": 467338, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9775978326797485, "global_step": 467339, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.117323875427246, "global_step": 467340, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.977023720741272, "global_step": 467341, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.135204315185547, "global_step": 467342, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.030611038208008, "global_step": 467343, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0586302280426025, "global_step": 467344, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0014491081237793, "global_step": 467345, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.108814239501953, "global_step": 467346, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.049954652786255, "global_step": 467347, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0410525798797607, "global_step": 467348, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0511081218719482, "global_step": 467349, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.05015230178833, "global_step": 467350, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.007192611694336, "global_step": 467351, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.034869432449341, "global_step": 467352, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0310206413269043, "global_step": 467353, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.089170455932617, "global_step": 467354, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0403287410736084, "global_step": 467355, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.064877986907959, "global_step": 467356, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0497567653656006, "global_step": 467357, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0232949256896973, "global_step": 467358, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.059133529663086, "global_step": 467359, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.150120735168457, "global_step": 467360, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9996405839920044, "global_step": 467361, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.086102247238159, "global_step": 467362, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.118302822113037, "global_step": 467363, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0686867237091064, "global_step": 467364, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9706326723098755, "global_step": 467365, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1180307865142822, "global_step": 467366, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0850470066070557, "global_step": 467367, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.005784034729004, "global_step": 467368, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1487715244293213, "global_step": 467369, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9823591709136963, "global_step": 467370, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.016693592071533, "global_step": 467371, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.081637144088745, "global_step": 467372, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.049649477005005, "global_step": 467373, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.075206756591797, "global_step": 467374, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.045661687850952, "global_step": 467375, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.108567237854004, "global_step": 467376, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0926263332366943, "global_step": 467377, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9989486932754517, "global_step": 467378, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9693779945373535, "global_step": 467379, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.042853355407715, "global_step": 467380, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1017239093780518, "global_step": 467381, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1244208812713623, "global_step": 467382, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.127220630645752, "global_step": 467383, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1248068809509277, "global_step": 467384, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0167477130889893, "global_step": 467385, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0836918354034424, "global_step": 467386, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0101749897003174, "global_step": 467387, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9963593482971191, "global_step": 467388, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0868003368377686, "global_step": 467389, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1264517307281494, "global_step": 467390, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1125576496124268, "global_step": 467391, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0155189037323, "global_step": 467392, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0765793323516846, "global_step": 467393, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.100449562072754, "global_step": 467394, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0882644653320312, "global_step": 467395, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.131485939025879, "global_step": 467396, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.135267734527588, "global_step": 467397, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0611400604248047, "global_step": 467398, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0664138793945312, "global_step": 467399, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0606398582458496, "global_step": 467400, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9867749214172363, "global_step": 467401, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.06811261177063, "global_step": 467402, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0699198246002197, "global_step": 467403, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0333449840545654, "global_step": 467404, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.069957733154297, "global_step": 467405, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.017117500305176, "global_step": 467406, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.027452230453491, "global_step": 467407, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.054616928100586, "global_step": 467408, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1475441455841064, "global_step": 467409, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0457708835601807, "global_step": 467410, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0712547302246094, "global_step": 467411, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.012176036834717, "global_step": 467412, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9931018352508545, "global_step": 467413, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.14452862739563, "global_step": 467414, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0939736366271973, "global_step": 467415, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0371415615081787, "global_step": 467416, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0789623260498047, "global_step": 467417, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0660767555236816, "global_step": 467418, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1719541549682617, "global_step": 467419, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0988879203796387, "global_step": 467420, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1086277961730957, "global_step": 467421, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.045626640319824, "global_step": 467422, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0045406818389893, "global_step": 467423, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.074434518814087, "global_step": 467424, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1310248374938965, "global_step": 467425, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0980019569396973, "global_step": 467426, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1041321754455566, "global_step": 467427, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.019481897354126, "global_step": 467428, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1462976932525635, "global_step": 467429, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9659655094146729, "global_step": 467430, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0307130813598633, "global_step": 467431, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.058405876159668, "global_step": 467432, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0886268615722656, "global_step": 467433, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.001180648803711, "global_step": 467434, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.168144941329956, "global_step": 467435, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0268146991729736, "global_step": 467436, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0669658184051514, "global_step": 467437, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0588455200195312, "global_step": 467438, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.963157296180725, "global_step": 467439, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.100170135498047, "global_step": 467440, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0461173057556152, "global_step": 467441, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.102876901626587, "global_step": 467442, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.108734369277954, "global_step": 467443, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0749905109405518, "global_step": 467444, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.079920530319214, "global_step": 467445, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.147535562515259, "global_step": 467446, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.050302743911743, "global_step": 467447, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0898356437683105, "global_step": 467448, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1614668369293213, "global_step": 467449, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0802910327911377, "global_step": 467450, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0562095642089844, "global_step": 467451, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1299850940704346, "global_step": 467452, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9818674325942993, "global_step": 467453, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.07629132270813, "global_step": 467454, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9671962261199951, "global_step": 467455, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0940744876861572, "global_step": 467456, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1282877922058105, "global_step": 467457, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1143014430999756, "global_step": 467458, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0678138732910156, "global_step": 467459, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9888375997543335, "global_step": 467460, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0950634479522705, "global_step": 467461, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0961127281188965, "global_step": 467462, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.115739345550537, "global_step": 467463, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0614702701568604, "global_step": 467464, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.082041025161743, "global_step": 467465, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.107295036315918, "global_step": 467466, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.106666088104248, "global_step": 467467, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.087911367416382, "global_step": 467468, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0552077293395996, "global_step": 467469, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0939712524414062, "global_step": 467470, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.049708366394043, "global_step": 467471, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9931057691574097, "global_step": 467472, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.113105058670044, "global_step": 467473, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0466818809509277, "global_step": 467474, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.076169490814209, "global_step": 467475, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.129831075668335, "global_step": 467476, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.081514596939087, "global_step": 467477, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1326212882995605, "global_step": 467478, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1259968280792236, "global_step": 467479, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0663113594055176, "global_step": 467480, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.115269899368286, "global_step": 467481, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0840635299682617, "global_step": 467482, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.049482583999634, "global_step": 467483, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.181541681289673, "global_step": 467484, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.043407678604126, "global_step": 467485, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.059617757797241, "global_step": 467486, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1435706615448, "global_step": 467487, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.078947067260742, "global_step": 467488, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0721919536590576, "global_step": 467489, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.042600154876709, "global_step": 467490, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.081873655319214, "global_step": 467491, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0939338207244873, "global_step": 467492, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9902528524398804, "global_step": 467493, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0829169750213623, "global_step": 467494, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1075985431671143, "global_step": 467495, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0185396671295166, "global_step": 467496, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0956199169158936, "global_step": 467497, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.154709577560425, "global_step": 467498, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.03314471244812, "global_step": 467499, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.063325881958008, "global_step": 467500, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.055015802383423, "global_step": 467501, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0137534141540527, "global_step": 467502, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0658156871795654, "global_step": 467503, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9926197528839111, "global_step": 467504, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1098012924194336, "global_step": 467505, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.08418345451355, "global_step": 467506, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0297164916992188, "global_step": 467507, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0720274448394775, "global_step": 467508, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0884408950805664, "global_step": 467509, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9843741655349731, "global_step": 467510, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0029780864715576, "global_step": 467511, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0195579528808594, "global_step": 467512, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.071016788482666, "global_step": 467513, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0676372051239014, "global_step": 467514, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0711700916290283, "global_step": 467515, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0828590393066406, "global_step": 467516, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1320760250091553, "global_step": 467517, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0764567852020264, "global_step": 467518, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.074568033218384, "global_step": 467519, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.055060625076294, "global_step": 467520, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9874953031539917, "global_step": 467521, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1131510734558105, "global_step": 467522, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.103635787963867, "global_step": 467523, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.021226167678833, "global_step": 467524, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.121077537536621, "global_step": 467525, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0554444789886475, "global_step": 467526, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9777508974075317, "global_step": 467527, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.052290916442871, "global_step": 467528, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.038827896118164, "global_step": 467529, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.087604522705078, "global_step": 467530, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.054236650466919, "global_step": 467531, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0240564346313477, "global_step": 467532, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0945041179656982, "global_step": 467533, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.065023422241211, "global_step": 467534, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1384005546569824, "global_step": 467535, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0678956508636475, "global_step": 467536, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0494003295898438, "global_step": 467537, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0262694358825684, "global_step": 467538, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0892064571380615, "global_step": 467539, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.094064712524414, "global_step": 467540, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.186384677886963, "global_step": 467541, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1032495498657227, "global_step": 467542, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.028393507003784, "global_step": 467543, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0828325748443604, "global_step": 467544, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0419070720672607, "global_step": 467545, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.12219500541687, "global_step": 467546, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0600974559783936, "global_step": 467547, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.041280746459961, "global_step": 467548, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0332791805267334, "global_step": 467549, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.021838903427124, "global_step": 467550, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.136200428009033, "global_step": 467551, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.018101215362549, "global_step": 467552, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.12461519241333, "global_step": 467553, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.024930238723755, "global_step": 467554, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1725990772247314, "global_step": 467555, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.169410228729248, "global_step": 467556, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0578465461730957, "global_step": 467557, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0090041160583496, "global_step": 467558, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0078606605529785, "global_step": 467559, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0569472312927246, "global_step": 467560, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.087712287902832, "global_step": 467561, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9881521463394165, "global_step": 467562, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.100688934326172, "global_step": 467563, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0178048610687256, "global_step": 467564, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.011352062225342, "global_step": 467565, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0587260723114014, "global_step": 467566, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9786795377731323, "global_step": 467567, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0328643321990967, "global_step": 467568, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0388803482055664, "global_step": 467569, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.117109537124634, "global_step": 467570, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0606071949005127, "global_step": 467571, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.134566307067871, "global_step": 467572, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0297842025756836, "global_step": 467573, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1291418075561523, "global_step": 467574, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.071948528289795, "global_step": 467575, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1166036128997803, "global_step": 467576, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.045745611190796, "global_step": 467577, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.024637222290039, "global_step": 467578, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.055419445037842, "global_step": 467579, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.145634651184082, "global_step": 467580, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0769307613372803, "global_step": 467581, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0545315742492676, "global_step": 467582, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0912153720855713, "global_step": 467583, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.056339740753174, "global_step": 467584, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1003317832946777, "global_step": 467585, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0868542194366455, "global_step": 467586, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0788447856903076, "global_step": 467587, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1139976978302, "global_step": 467588, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0792460441589355, "global_step": 467589, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.131042242050171, "global_step": 467590, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0875580310821533, "global_step": 467591, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.008033037185669, "global_step": 467592, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0842151641845703, "global_step": 467593, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1088547706604004, "global_step": 467594, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0286405086517334, "global_step": 467595, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.091305732727051, "global_step": 467596, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1261091232299805, "global_step": 467597, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.057612895965576, "global_step": 467598, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.037325382232666, "global_step": 467599, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.046549081802368, "global_step": 467600, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0919315814971924, "global_step": 467601, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.087568759918213, "global_step": 467602, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.10941219329834, "global_step": 467603, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1439359188079834, "global_step": 467604, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.094926118850708, "global_step": 467605, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0069167613983154, "global_step": 467606, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0889782905578613, "global_step": 467607, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0669877529144287, "global_step": 467608, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0378353595733643, "global_step": 467609, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.022298574447632, "global_step": 467610, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0165226459503174, "global_step": 467611, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0801260471343994, "global_step": 467612, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0548903942108154, "global_step": 467613, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9739954471588135, "global_step": 467614, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0986247062683105, "global_step": 467615, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.008232831954956, "global_step": 467616, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0632004737854004, "global_step": 467617, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9788252115249634, "global_step": 467618, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1103289127349854, "global_step": 467619, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.022878885269165, "global_step": 467620, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.004516124725342, "global_step": 467621, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0635452270507812, "global_step": 467622, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.145596742630005, "global_step": 467623, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0835585594177246, "global_step": 467624, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.07361102104187, "global_step": 467625, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.036038398742676, "global_step": 467626, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0378971099853516, "global_step": 467627, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.055683135986328, "global_step": 467628, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.019787311553955, "global_step": 467629, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1048686504364014, "global_step": 467630, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0352141857147217, "global_step": 467631, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1415653228759766, "global_step": 467632, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.055464029312134, "global_step": 467633, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.026965379714966, "global_step": 467634, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0526862144470215, "global_step": 467635, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.033216953277588, "global_step": 467636, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9638293981552124, "global_step": 467637, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1318166255950928, "global_step": 467638, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0549118518829346, "global_step": 467639, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.128908634185791, "global_step": 467640, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.14579439163208, "global_step": 467641, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9916318655014038, "global_step": 467642, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0899627208709717, "global_step": 467643, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.109341621398926, "global_step": 467644, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1753041744232178, "global_step": 467645, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9907119274139404, "global_step": 467646, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0385146141052246, "global_step": 467647, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9904226064682007, "global_step": 467648, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1555118560791016, "global_step": 467649, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0894062519073486, "global_step": 467650, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1099534034729004, "global_step": 467651, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1097328662872314, "global_step": 467652, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9924904108047485, "global_step": 467653, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.048311948776245, "global_step": 467654, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.060605049133301, "global_step": 467655, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1159610748291016, "global_step": 467656, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.132084369659424, "global_step": 467657, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.026304244995117, "global_step": 467658, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.103739023208618, "global_step": 467659, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0301802158355713, "global_step": 467660, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0508556365966797, "global_step": 467661, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.087038278579712, "global_step": 467662, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.936932921409607, "global_step": 467663, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1095380783081055, "global_step": 467664, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9805638790130615, "global_step": 467665, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0421223640441895, "global_step": 467666, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0590107440948486, "global_step": 467667, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0676329135894775, "global_step": 467668, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0318515300750732, "global_step": 467669, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.077876329421997, "global_step": 467670, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.078096389770508, "global_step": 467671, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.06594181060791, "global_step": 467672, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9960963726043701, "global_step": 467673, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.025261640548706, "global_step": 467674, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.022076368331909, "global_step": 467675, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1321310997009277, "global_step": 467676, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0526084899902344, "global_step": 467677, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1033880710601807, "global_step": 467678, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9880048036575317, "global_step": 467679, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.091986894607544, "global_step": 467680, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.094255208969116, "global_step": 467681, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0545547008514404, "global_step": 467682, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.066709518432617, "global_step": 467683, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1424927711486816, "global_step": 467684, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0824270248413086, "global_step": 467685, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.110154628753662, "global_step": 467686, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0996222496032715, "global_step": 467687, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0551204681396484, "global_step": 467688, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.037203550338745, "global_step": 467689, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1501667499542236, "global_step": 467690, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0010597705841064, "global_step": 467691, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0457534790039062, "global_step": 467692, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1071901321411133, "global_step": 467693, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1038081645965576, "global_step": 467694, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.047919750213623, "global_step": 467695, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.092048168182373, "global_step": 467696, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.071640968322754, "global_step": 467697, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.045287609100342, "global_step": 467698, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0727319717407227, "global_step": 467699, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1431901454925537, "global_step": 467700, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0804102420806885, "global_step": 467701, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1640207767486572, "global_step": 467702, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1189916133880615, "global_step": 467703, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.043997049331665, "global_step": 467704, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.07364821434021, "global_step": 467705, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1696348190307617, "global_step": 467706, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.121415138244629, "global_step": 467707, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1113550662994385, "global_step": 467708, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.097231149673462, "global_step": 467709, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0187628269195557, "global_step": 467710, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.061260461807251, "global_step": 467711, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0539770126342773, "global_step": 467712, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9860270023345947, "global_step": 467713, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.021369695663452, "global_step": 467714, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.032048225402832, "global_step": 467715, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0973238945007324, "global_step": 467716, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9698925018310547, "global_step": 467717, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0323660373687744, "global_step": 467718, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.032942295074463, "global_step": 467719, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0306482315063477, "global_step": 467720, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.2004222869873047, "global_step": 467721, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1060290336608887, "global_step": 467722, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0542218685150146, "global_step": 467723, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0201570987701416, "global_step": 467724, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.048426389694214, "global_step": 467725, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1130030155181885, "global_step": 467726, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.026442050933838, "global_step": 467727, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.120485305786133, "global_step": 467728, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.091083526611328, "global_step": 467729, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1016452312469482, "global_step": 467730, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0504260063171387, "global_step": 467731, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.959061622619629, "global_step": 467732, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.048131227493286, "global_step": 467733, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1009716987609863, "global_step": 467734, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.050159454345703, "global_step": 467735, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1196086406707764, "global_step": 467736, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1246132850646973, "global_step": 467737, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1030497550964355, "global_step": 467738, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.083907127380371, "global_step": 467739, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.105983018875122, "global_step": 467740, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0045268535614014, "global_step": 467741, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0448732376098633, "global_step": 467742, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0191798210144043, "global_step": 467743, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0955710411071777, "global_step": 467744, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0645320415496826, "global_step": 467745, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.108283281326294, "global_step": 467746, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.119872570037842, "global_step": 467747, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0391194820404053, "global_step": 467748, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9852627515792847, "global_step": 467749, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.152928113937378, "global_step": 467750, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0964176654815674, "global_step": 467751, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.059218406677246, "global_step": 467752, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0779192447662354, "global_step": 467753, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1044294834136963, "global_step": 467754, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.02732515335083, "global_step": 467755, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.05008864402771, "global_step": 467756, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0612523555755615, "global_step": 467757, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0314931869506836, "global_step": 467758, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1107561588287354, "global_step": 467759, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0789783000946045, "global_step": 467760, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9914671182632446, "global_step": 467761, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.151686191558838, "global_step": 467762, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0247690677642822, "global_step": 467763, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.198110580444336, "global_step": 467764, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.122443437576294, "global_step": 467765, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.121692657470703, "global_step": 467766, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0549569129943848, "global_step": 467767, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1753909587860107, "global_step": 467768, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9686306715011597, "global_step": 467769, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.146827220916748, "global_step": 467770, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.115321397781372, "global_step": 467771, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0817532539367676, "global_step": 467772, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0445172786712646, "global_step": 467773, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1168243885040283, "global_step": 467774, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.043640613555908, "global_step": 467775, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1053547859191895, "global_step": 467776, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0853078365325928, "global_step": 467777, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.010371208190918, "global_step": 467778, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0523953437805176, "global_step": 467779, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0871903896331787, "global_step": 467780, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0385758876800537, "global_step": 467781, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0063295364379883, "global_step": 467782, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0431160926818848, "global_step": 467783, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0626420974731445, "global_step": 467784, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0341033935546875, "global_step": 467785, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.064509153366089, "global_step": 467786, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.985196590423584, "global_step": 467787, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.155125379562378, "global_step": 467788, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0855681896209717, "global_step": 467789, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.075340509414673, "global_step": 467790, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.114733934402466, "global_step": 467791, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9993007183074951, "global_step": 467792, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.069580554962158, "global_step": 467793, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.100773334503174, "global_step": 467794, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0869574546813965, "global_step": 467795, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9873089790344238, "global_step": 467796, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0692391395568848, "global_step": 467797, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0100858211517334, "global_step": 467798, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0592424869537354, "global_step": 467799, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0069243907928467, "global_step": 467800, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.078796625137329, "global_step": 467801, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0572402477264404, "global_step": 467802, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.117075204849243, "global_step": 467803, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9397289752960205, "global_step": 467804, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0907609462738037, "global_step": 467805, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.058478832244873, "global_step": 467806, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.002868175506592, "global_step": 467807, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.105461597442627, "global_step": 467808, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1142237186431885, "global_step": 467809, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0893163681030273, "global_step": 467810, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.063262462615967, "global_step": 467811, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.05706787109375, "global_step": 467812, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.046414613723755, "global_step": 467813, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.075408697128296, "global_step": 467814, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.070971727371216, "global_step": 467815, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0260846614837646, "global_step": 467816, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.085766553878784, "global_step": 467817, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.082037925720215, "global_step": 467818, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.073336124420166, "global_step": 467819, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.05662202835083, "global_step": 467820, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.104093313217163, "global_step": 467821, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0889596939086914, "global_step": 467822, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9950737953186035, "global_step": 467823, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.05120587348938, "global_step": 467824, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1231939792633057, "global_step": 467825, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9811832904815674, "global_step": 467826, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0462000370025635, "global_step": 467827, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.055375337600708, "global_step": 467828, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.097092390060425, "global_step": 467829, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0738961696624756, "global_step": 467830, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.100278615951538, "global_step": 467831, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0473129749298096, "global_step": 467832, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0698254108428955, "global_step": 467833, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0055716037750244, "global_step": 467834, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.045896291732788, "global_step": 467835, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0988638401031494, "global_step": 467836, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.115023136138916, "global_step": 467837, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.080303430557251, "global_step": 467838, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.028323173522949, "global_step": 467839, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.004960536956787, "global_step": 467840, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0526673793792725, "global_step": 467841, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.035289764404297, "global_step": 467842, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.046933889389038, "global_step": 467843, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.057389497756958, "global_step": 467844, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.130171060562134, "global_step": 467845, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.084197521209717, "global_step": 467846, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.075965166091919, "global_step": 467847, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.133831739425659, "global_step": 467848, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1133387088775635, "global_step": 467849, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.072688102722168, "global_step": 467850, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0069737434387207, "global_step": 467851, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0905375480651855, "global_step": 467852, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1284539699554443, "global_step": 467853, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0239264965057373, "global_step": 467854, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0040011405944824, "global_step": 467855, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9792168140411377, "global_step": 467856, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.048508644104004, "global_step": 467857, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.168189287185669, "global_step": 467858, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0460119247436523, "global_step": 467859, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.010730266571045, "global_step": 467860, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.083246946334839, "global_step": 467861, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0344398021698, "global_step": 467862, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0542032718658447, "global_step": 467863, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.024524211883545, "global_step": 467864, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0481293201446533, "global_step": 467865, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0583319664001465, "global_step": 467866, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0066473484039307, "global_step": 467867, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0944111347198486, "global_step": 467868, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.085265874862671, "global_step": 467869, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.007584571838379, "global_step": 467870, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.132497549057007, "global_step": 467871, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.052476406097412, "global_step": 467872, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.168325424194336, "global_step": 467873, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.139463424682617, "global_step": 467874, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0556910037994385, "global_step": 467875, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.072181463241577, "global_step": 467876, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.068406105041504, "global_step": 467877, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0286033153533936, "global_step": 467878, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.083858013153076, "global_step": 467879, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.04325008392334, "global_step": 467880, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.036707639694214, "global_step": 467881, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1094346046447754, "global_step": 467882, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0369210243225098, "global_step": 467883, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0886788368225098, "global_step": 467884, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.107205867767334, "global_step": 467885, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.123502254486084, "global_step": 467886, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.053107500076294, "global_step": 467887, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1218807697296143, "global_step": 467888, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1150615215301514, "global_step": 467889, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.106590986251831, "global_step": 467890, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.954156756401062, "global_step": 467891, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9891608953475952, "global_step": 467892, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9958231449127197, "global_step": 467893, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0470471382141113, "global_step": 467894, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.086550712585449, "global_step": 467895, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1207997798919678, "global_step": 467896, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.067554473876953, "global_step": 467897, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.031013011932373, "global_step": 467898, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.078320264816284, "global_step": 467899, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0093777179718018, "global_step": 467900, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.022250175476074, "global_step": 467901, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1383044719696045, "global_step": 467902, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0904622077941895, "global_step": 467903, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0629489421844482, "global_step": 467904, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.075667381286621, "global_step": 467905, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.016794204711914, "global_step": 467906, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0052247047424316, "global_step": 467907, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.027528762817383, "global_step": 467908, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.101595163345337, "global_step": 467909, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0772714614868164, "global_step": 467910, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0417535305023193, "global_step": 467911, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.042508125305176, "global_step": 467912, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.11602783203125, "global_step": 467913, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.094630241394043, "global_step": 467914, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0006160736083984, "global_step": 467915, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1176388263702393, "global_step": 467916, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0411617755889893, "global_step": 467917, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0438220500946045, "global_step": 467918, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0947654247283936, "global_step": 467919, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.053297519683838, "global_step": 467920, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0298891067504883, "global_step": 467921, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.037365674972534, "global_step": 467922, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0748484134674072, "global_step": 467923, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0486252307891846, "global_step": 467924, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0764262676239014, "global_step": 467925, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.04971981048584, "global_step": 467926, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1003916263580322, "global_step": 467927, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9592082500457764, "global_step": 467928, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1544384956359863, "global_step": 467929, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1201274394989014, "global_step": 467930, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.085645914077759, "global_step": 467931, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.151399850845337, "global_step": 467932, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.012543201446533, "global_step": 467933, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1261255741119385, "global_step": 467934, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9874696731567383, "global_step": 467935, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0003468990325928, "global_step": 467936, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0650689601898193, "global_step": 467937, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0690231323242188, "global_step": 467938, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0183961391448975, "global_step": 467939, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.045762300491333, "global_step": 467940, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0590124130249023, "global_step": 467941, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0222980976104736, "global_step": 467942, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.111048460006714, "global_step": 467943, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0857012271881104, "global_step": 467944, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0782501697540283, "global_step": 467945, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0068588256835938, "global_step": 467946, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.991444706916809, "global_step": 467947, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9492263793945312, "global_step": 467948, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1263186931610107, "global_step": 467949, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0786538124084473, "global_step": 467950, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0740714073181152, "global_step": 467951, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.965822696685791, "global_step": 467952, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.037905216217041, "global_step": 467953, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.08347487449646, "global_step": 467954, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0326004028320312, "global_step": 467955, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.056431770324707, "global_step": 467956, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1223907470703125, "global_step": 467957, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9698336124420166, "global_step": 467958, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.083261251449585, "global_step": 467959, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.150836944580078, "global_step": 467960, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.031299591064453, "global_step": 467961, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9555466175079346, "global_step": 467962, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9890047311782837, "global_step": 467963, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.101593017578125, "global_step": 467964, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.026752471923828, "global_step": 467965, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.099771022796631, "global_step": 467966, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.061037302017212, "global_step": 467967, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.026059865951538, "global_step": 467968, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.047041654586792, "global_step": 467969, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0615479946136475, "global_step": 467970, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0375232696533203, "global_step": 467971, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.094083786010742, "global_step": 467972, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1255528926849365, "global_step": 467973, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0545833110809326, "global_step": 467974, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0590128898620605, "global_step": 467975, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.13606595993042, "global_step": 467976, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0237033367156982, "global_step": 467977, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.036094903945923, "global_step": 467978, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.078028678894043, "global_step": 467979, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0654516220092773, "global_step": 467980, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.066469669342041, "global_step": 467981, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.096724271774292, "global_step": 467982, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0365772247314453, "global_step": 467983, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9861611127853394, "global_step": 467984, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.017350673675537, "global_step": 467985, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.968113660812378, "global_step": 467986, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1157805919647217, "global_step": 467987, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.14627742767334, "global_step": 467988, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0718750953674316, "global_step": 467989, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0891408920288086, "global_step": 467990, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.095486879348755, "global_step": 467991, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1727969646453857, "global_step": 467992, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0868937969207764, "global_step": 467993, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.062433958053589, "global_step": 467994, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9729913473129272, "global_step": 467995, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0533387660980225, "global_step": 467996, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.895222544670105, "global_step": 467997, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1461286544799805, "global_step": 467998, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0830507278442383, "global_step": 467999, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9488320350646973, "global_step": 468000, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0424652099609375, "global_step": 468001, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.105534791946411, "global_step": 468002, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1029820442199707, "global_step": 468003, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0630886554718018, "global_step": 468004, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9784648418426514, "global_step": 468005, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0249457359313965, "global_step": 468006, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1325523853302, "global_step": 468007, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1299495697021484, "global_step": 468008, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.098127603530884, "global_step": 468009, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0280957221984863, "global_step": 468010, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.042142391204834, "global_step": 468011, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.103017807006836, "global_step": 468012, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0545713901519775, "global_step": 468013, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.051793098449707, "global_step": 468014, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.067708969116211, "global_step": 468015, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0189337730407715, "global_step": 468016, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.137986898422241, "global_step": 468017, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.014310598373413, "global_step": 468018, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.006723165512085, "global_step": 468019, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.021343469619751, "global_step": 468020, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9733684062957764, "global_step": 468021, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0874428749084473, "global_step": 468022, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0689549446105957, "global_step": 468023, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0136396884918213, "global_step": 468024, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1736176013946533, "global_step": 468025, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0565578937530518, "global_step": 468026, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.131164073944092, "global_step": 468027, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.071413993835449, "global_step": 468028, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0411806106567383, "global_step": 468029, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.158135175704956, "global_step": 468030, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.104900360107422, "global_step": 468031, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.039907693862915, "global_step": 468032, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9994990825653076, "global_step": 468033, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1331241130828857, "global_step": 468034, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0832202434539795, "global_step": 468035, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.082017421722412, "global_step": 468036, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.080937385559082, "global_step": 468037, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.039132595062256, "global_step": 468038, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.014988422393799, "global_step": 468039, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.092454433441162, "global_step": 468040, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.074737310409546, "global_step": 468041, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.050339937210083, "global_step": 468042, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9830039739608765, "global_step": 468043, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1264278888702393, "global_step": 468044, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.003251314163208, "global_step": 468045, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9977123737335205, "global_step": 468046, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9661533832550049, "global_step": 468047, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.121458053588867, "global_step": 468048, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1198208332061768, "global_step": 468049, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0556540489196777, "global_step": 468050, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.033403158187866, "global_step": 468051, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0907974243164062, "global_step": 468052, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0411713123321533, "global_step": 468053, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1569125652313232, "global_step": 468054, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.129218339920044, "global_step": 468055, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.10345721244812, "global_step": 468056, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.074054718017578, "global_step": 468057, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.110103130340576, "global_step": 468058, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0873045921325684, "global_step": 468059, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.02169132232666, "global_step": 468060, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.099001169204712, "global_step": 468061, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0492143630981445, "global_step": 468062, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.060978889465332, "global_step": 468063, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.103255271911621, "global_step": 468064, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0539193153381348, "global_step": 468065, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0869104862213135, "global_step": 468066, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.095489740371704, "global_step": 468067, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1037039756774902, "global_step": 468068, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.15028715133667, "global_step": 468069, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0499584674835205, "global_step": 468070, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.027369499206543, "global_step": 468071, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.097494602203369, "global_step": 468072, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1306166648864746, "global_step": 468073, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.136842727661133, "global_step": 468074, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0263991355895996, "global_step": 468075, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1315343379974365, "global_step": 468076, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.05228853225708, "global_step": 468077, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.048231601715088, "global_step": 468078, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1092777252197266, "global_step": 468079, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.048055648803711, "global_step": 468080, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0440354347229004, "global_step": 468081, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.061628818511963, "global_step": 468082, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0641281604766846, "global_step": 468083, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0810391902923584, "global_step": 468084, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0867271423339844, "global_step": 468085, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1513233184814453, "global_step": 468086, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0371365547180176, "global_step": 468087, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.053455114364624, "global_step": 468088, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.123228073120117, "global_step": 468089, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1777613162994385, "global_step": 468090, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.012348175048828, "global_step": 468091, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0594162940979004, "global_step": 468092, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.041832447052002, "global_step": 468093, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0421082973480225, "global_step": 468094, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0280508995056152, "global_step": 468095, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.031803607940674, "global_step": 468096, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.057316541671753, "global_step": 468097, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.084185838699341, "global_step": 468098, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9782965183258057, "global_step": 468099, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.07867169380188, "global_step": 468100, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0296013355255127, "global_step": 468101, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.014726161956787, "global_step": 468102, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0585572719573975, "global_step": 468103, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0717320442199707, "global_step": 468104, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.023340940475464, "global_step": 468105, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.049105167388916, "global_step": 468106, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.04775071144104, "global_step": 468107, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.160818576812744, "global_step": 468108, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.185702323913574, "global_step": 468109, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.050778865814209, "global_step": 468110, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.070695161819458, "global_step": 468111, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.124462366104126, "global_step": 468112, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0455832481384277, "global_step": 468113, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0974011421203613, "global_step": 468114, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0376248359680176, "global_step": 468115, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0119237899780273, "global_step": 468116, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.121769905090332, "global_step": 468117, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1099109649658203, "global_step": 468118, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.116036891937256, "global_step": 468119, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0742275714874268, "global_step": 468120, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0791726112365723, "global_step": 468121, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9839951992034912, "global_step": 468122, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0631961822509766, "global_step": 468123, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0745699405670166, "global_step": 468124, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.136471748352051, "global_step": 468125, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.062623977661133, "global_step": 468126, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0932185649871826, "global_step": 468127, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.977188229560852, "global_step": 468128, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0931758880615234, "global_step": 468129, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.152273416519165, "global_step": 468130, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.077730178833008, "global_step": 468131, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.086956024169922, "global_step": 468132, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.113037109375, "global_step": 468133, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.128363609313965, "global_step": 468134, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.127902030944824, "global_step": 468135, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0370116233825684, "global_step": 468136, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0609865188598633, "global_step": 468137, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0896763801574707, "global_step": 468138, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.04221510887146, "global_step": 468139, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0694494247436523, "global_step": 468140, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.192016839981079, "global_step": 468141, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0630226135253906, "global_step": 468142, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0660884380340576, "global_step": 468143, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0858800411224365, "global_step": 468144, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0573132038116455, "global_step": 468145, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.051145553588867, "global_step": 468146, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.092273473739624, "global_step": 468147, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.007514715194702, "global_step": 468148, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.103747606277466, "global_step": 468149, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1093993186950684, "global_step": 468150, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.120548963546753, "global_step": 468151, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.117875099182129, "global_step": 468152, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.061305284500122, "global_step": 468153, "epoch": 832, "lr": 5e-05}
{"train_loss": 1.9518868923187256, "global_step": 468154, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.005246877670288, "global_step": 468155, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1383471488952637, "global_step": 468156, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0537707805633545, "global_step": 468157, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.1366922855377197, "global_step": 468158, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0655899047851562, "global_step": 468159, "epoch": 832, "lr": 5e-05}
{"train_loss": 2.0842466354370117, "global_step": 468160, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0910351276397705, "global_step": 468161, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0634329319000244, "global_step": 468162, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0618531703948975, "global_step": 468163, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.117382049560547, "global_step": 468164, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0361928939819336, "global_step": 468165, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.09724497795105, "global_step": 468166, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.053299903869629, "global_step": 468167, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.092919111251831, "global_step": 468168, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9498279094696045, "global_step": 468169, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9856394529342651, "global_step": 468170, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0477075576782227, "global_step": 468171, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0374388694763184, "global_step": 468172, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0923116207122803, "global_step": 468173, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0940101146698, "global_step": 468174, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9833158254623413, "global_step": 468175, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0277791023254395, "global_step": 468176, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.060908079147339, "global_step": 468177, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0318076610565186, "global_step": 468178, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.033813714981079, "global_step": 468179, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0963189601898193, "global_step": 468180, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.075557231903076, "global_step": 468181, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0909440517425537, "global_step": 468182, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.046461820602417, "global_step": 468183, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1011152267456055, "global_step": 468184, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0311238765716553, "global_step": 468185, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.042886972427368, "global_step": 468186, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9694827795028687, "global_step": 468187, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.022489309310913, "global_step": 468188, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.078692674636841, "global_step": 468189, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1568655967712402, "global_step": 468190, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.049800157546997, "global_step": 468191, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.166494607925415, "global_step": 468192, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0448904037475586, "global_step": 468193, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0919992923736572, "global_step": 468194, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0130107402801514, "global_step": 468195, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.041278600692749, "global_step": 468196, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.053222417831421, "global_step": 468197, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.004547595977783, "global_step": 468198, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0609853267669678, "global_step": 468199, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0331740379333496, "global_step": 468200, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9720300436019897, "global_step": 468201, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.08805251121521, "global_step": 468202, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9704669713974, "global_step": 468203, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0631864070892334, "global_step": 468204, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.116664171218872, "global_step": 468205, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0232701301574707, "global_step": 468206, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0103750228881836, "global_step": 468207, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0660367012023926, "global_step": 468208, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1489431858062744, "global_step": 468209, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0878610610961914, "global_step": 468210, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0326037406921387, "global_step": 468211, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0533556938171387, "global_step": 468212, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0331413745880127, "global_step": 468213, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1040713787078857, "global_step": 468214, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.992337703704834, "global_step": 468215, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0072968006134033, "global_step": 468216, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.111321210861206, "global_step": 468217, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0402464866638184, "global_step": 468218, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1015422344207764, "global_step": 468219, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0728883743286133, "global_step": 468220, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9333539009094238, "global_step": 468221, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.142850637435913, "global_step": 468222, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.131709575653076, "global_step": 468223, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0698890686035156, "global_step": 468224, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.032388210296631, "global_step": 468225, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.01033616065979, "global_step": 468226, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1762850284576416, "global_step": 468227, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.056166887283325, "global_step": 468228, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0724127292633057, "global_step": 468229, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9849399328231812, "global_step": 468230, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0184032917022705, "global_step": 468231, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.008841037750244, "global_step": 468232, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0915868282318115, "global_step": 468233, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0478265285491943, "global_step": 468234, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9914216995239258, "global_step": 468235, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.984033465385437, "global_step": 468236, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.063615560531616, "global_step": 468237, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0462753772735596, "global_step": 468238, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1224312782287598, "global_step": 468239, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.106410503387451, "global_step": 468240, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0087456703186035, "global_step": 468241, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1152291297912598, "global_step": 468242, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9709886312484741, "global_step": 468243, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.104844570159912, "global_step": 468244, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0220887660980225, "global_step": 468245, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0653395652770996, "global_step": 468246, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.06412935256958, "global_step": 468247, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.081066846847534, "global_step": 468248, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0555436611175537, "global_step": 468249, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9785958528518677, "global_step": 468250, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1150922775268555, "global_step": 468251, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9507160186767578, "global_step": 468252, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0955286026000977, "global_step": 468253, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.083411693572998, "global_step": 468254, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.986355185508728, "global_step": 468255, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0865774154663086, "global_step": 468256, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.08780574798584, "global_step": 468257, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0542852878570557, "global_step": 468258, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.103567123413086, "global_step": 468259, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.12746000289917, "global_step": 468260, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.144552230834961, "global_step": 468261, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0046844482421875, "global_step": 468262, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9761708974838257, "global_step": 468263, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.058713436126709, "global_step": 468264, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1031334400177, "global_step": 468265, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.001105546951294, "global_step": 468266, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.147794723510742, "global_step": 468267, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.041944742202759, "global_step": 468268, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.068974733352661, "global_step": 468269, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.025967836380005, "global_step": 468270, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9788087606430054, "global_step": 468271, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0269298553466797, "global_step": 468272, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0585198402404785, "global_step": 468273, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.004079580307007, "global_step": 468274, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0955703258514404, "global_step": 468275, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0602967739105225, "global_step": 468276, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.075059652328491, "global_step": 468277, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.097100019454956, "global_step": 468278, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0872225761413574, "global_step": 468279, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0413947105407715, "global_step": 468280, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0193164348602295, "global_step": 468281, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.038530111312866, "global_step": 468282, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0539278984069824, "global_step": 468283, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0252749919891357, "global_step": 468284, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.063161611557007, "global_step": 468285, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0413718223571777, "global_step": 468286, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.013033151626587, "global_step": 468287, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0354223251342773, "global_step": 468288, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0488951206207275, "global_step": 468289, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0896902084350586, "global_step": 468290, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.107496976852417, "global_step": 468291, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0235238075256348, "global_step": 468292, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1263630390167236, "global_step": 468293, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.024240255355835, "global_step": 468294, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9949065446853638, "global_step": 468295, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1443355083465576, "global_step": 468296, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0373387336730957, "global_step": 468297, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0816922187805176, "global_step": 468298, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0157077312469482, "global_step": 468299, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.042553663253784, "global_step": 468300, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.076838970184326, "global_step": 468301, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0228075981140137, "global_step": 468302, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0863664150238037, "global_step": 468303, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9855436086654663, "global_step": 468304, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0445542335510254, "global_step": 468305, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.052755832672119, "global_step": 468306, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.02254581451416, "global_step": 468307, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0182950496673584, "global_step": 468308, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0652015209198, "global_step": 468309, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0799505710601807, "global_step": 468310, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.116056203842163, "global_step": 468311, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9280720949172974, "global_step": 468312, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0523149967193604, "global_step": 468313, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.110926389694214, "global_step": 468314, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9668400287628174, "global_step": 468315, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.10646390914917, "global_step": 468316, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0500576496124268, "global_step": 468317, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0946340560913086, "global_step": 468318, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.115640163421631, "global_step": 468319, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.030122995376587, "global_step": 468320, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0296764373779297, "global_step": 468321, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.036362648010254, "global_step": 468322, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1340906620025635, "global_step": 468323, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0313470363616943, "global_step": 468324, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9445246458053589, "global_step": 468325, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9616923332214355, "global_step": 468326, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.081331968307495, "global_step": 468327, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.039762020111084, "global_step": 468328, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9865038394927979, "global_step": 468329, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.081206798553467, "global_step": 468330, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0589759349823, "global_step": 468331, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0237925052642822, "global_step": 468332, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0126891136169434, "global_step": 468333, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.007240056991577, "global_step": 468334, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.145170211791992, "global_step": 468335, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.060810089111328, "global_step": 468336, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9898865222930908, "global_step": 468337, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.181638240814209, "global_step": 468338, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0943329334259033, "global_step": 468339, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.998948335647583, "global_step": 468340, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.066023349761963, "global_step": 468341, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.006059408187866, "global_step": 468342, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.081653594970703, "global_step": 468343, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.086503028869629, "global_step": 468344, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0809357166290283, "global_step": 468345, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.105034351348877, "global_step": 468346, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0524046421051025, "global_step": 468347, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.060131072998047, "global_step": 468348, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.149778366088867, "global_step": 468349, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0337634086608887, "global_step": 468350, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9908310174942017, "global_step": 468351, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.040050745010376, "global_step": 468352, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.189919948577881, "global_step": 468353, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0569119453430176, "global_step": 468354, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0950989723205566, "global_step": 468355, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.06384539604187, "global_step": 468356, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.140474557876587, "global_step": 468357, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.051450729370117, "global_step": 468358, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.119619846343994, "global_step": 468359, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.176826238632202, "global_step": 468360, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0663907527923584, "global_step": 468361, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.989222526550293, "global_step": 468362, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.024725914001465, "global_step": 468363, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9445173740386963, "global_step": 468364, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.045278310775757, "global_step": 468365, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.065473794937134, "global_step": 468366, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.031447649002075, "global_step": 468367, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0166478157043457, "global_step": 468368, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1121408939361572, "global_step": 468369, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0714986324310303, "global_step": 468370, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0089194774627686, "global_step": 468371, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0948433876037598, "global_step": 468372, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0657615661621094, "global_step": 468373, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1491875648498535, "global_step": 468374, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0798184871673584, "global_step": 468375, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0832974910736084, "global_step": 468376, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.010551929473877, "global_step": 468377, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9641246795654297, "global_step": 468378, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0025599002838135, "global_step": 468379, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.972577691078186, "global_step": 468380, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0390515327453613, "global_step": 468381, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.091156244277954, "global_step": 468382, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0053882598876953, "global_step": 468383, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.026390552520752, "global_step": 468384, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9822405576705933, "global_step": 468385, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0524470806121826, "global_step": 468386, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0458953380584717, "global_step": 468387, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.049745559692383, "global_step": 468388, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.162546396255493, "global_step": 468389, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1192708015441895, "global_step": 468390, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1177480220794678, "global_step": 468391, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0247013568878174, "global_step": 468392, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0809125900268555, "global_step": 468393, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.047971725463867, "global_step": 468394, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.978498101234436, "global_step": 468395, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0228264331817627, "global_step": 468396, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1018714904785156, "global_step": 468397, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0511043071746826, "global_step": 468398, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9886131286621094, "global_step": 468399, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0232558250427246, "global_step": 468400, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0656003952026367, "global_step": 468401, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.092336893081665, "global_step": 468402, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0639729499816895, "global_step": 468403, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.051931858062744, "global_step": 468404, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.092292070388794, "global_step": 468405, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.006848096847534, "global_step": 468406, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0042996406555176, "global_step": 468407, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9823286533355713, "global_step": 468408, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.019195079803467, "global_step": 468409, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0691380500793457, "global_step": 468410, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1080617904663086, "global_step": 468411, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1176247596740723, "global_step": 468412, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0498766899108887, "global_step": 468413, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.11027193069458, "global_step": 468414, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.169015645980835, "global_step": 468415, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1673452854156494, "global_step": 468416, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.054141044616699, "global_step": 468417, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9914522171020508, "global_step": 468418, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0433871746063232, "global_step": 468419, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.031921148300171, "global_step": 468420, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0553860664367676, "global_step": 468421, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0163393020629883, "global_step": 468422, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.03802490234375, "global_step": 468423, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9858050346374512, "global_step": 468424, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9885445833206177, "global_step": 468425, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.098418951034546, "global_step": 468426, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0715200901031494, "global_step": 468427, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0426177978515625, "global_step": 468428, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9814324378967285, "global_step": 468429, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.154975175857544, "global_step": 468430, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.097094774246216, "global_step": 468431, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0692830085754395, "global_step": 468432, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.145296096801758, "global_step": 468433, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0277280807495117, "global_step": 468434, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.032379388809204, "global_step": 468435, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1121115684509277, "global_step": 468436, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.056687116622925, "global_step": 468437, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0067758560180664, "global_step": 468438, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.083559513092041, "global_step": 468439, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.113886833190918, "global_step": 468440, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.093801975250244, "global_step": 468441, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0644803047180176, "global_step": 468442, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.065067768096924, "global_step": 468443, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.027425765991211, "global_step": 468444, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9578362703323364, "global_step": 468445, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0418920516967773, "global_step": 468446, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.024646759033203, "global_step": 468447, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0866036415100098, "global_step": 468448, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0640056133270264, "global_step": 468449, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.056244134902954, "global_step": 468450, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.09478759765625, "global_step": 468451, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.038877248764038, "global_step": 468452, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0214195251464844, "global_step": 468453, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1048426628112793, "global_step": 468454, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.015644073486328, "global_step": 468455, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.101900577545166, "global_step": 468456, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.095776319503784, "global_step": 468457, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0441858768463135, "global_step": 468458, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0719799995422363, "global_step": 468459, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0629611015319824, "global_step": 468460, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.022468090057373, "global_step": 468461, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1121768951416016, "global_step": 468462, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.068181276321411, "global_step": 468463, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0535316467285156, "global_step": 468464, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.128161907196045, "global_step": 468465, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.226571798324585, "global_step": 468466, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0013606548309326, "global_step": 468467, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9960891008377075, "global_step": 468468, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0900156497955322, "global_step": 468469, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.08264422416687, "global_step": 468470, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.129021644592285, "global_step": 468471, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.034003973007202, "global_step": 468472, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0220553874969482, "global_step": 468473, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0468130111694336, "global_step": 468474, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0170814990997314, "global_step": 468475, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.056962490081787, "global_step": 468476, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.079251527786255, "global_step": 468477, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0445895195007324, "global_step": 468478, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0737130641937256, "global_step": 468479, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.044459104537964, "global_step": 468480, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9521758556365967, "global_step": 468481, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9818753004074097, "global_step": 468482, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1881070137023926, "global_step": 468483, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.063521146774292, "global_step": 468484, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.099494218826294, "global_step": 468485, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.030240297317505, "global_step": 468486, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.065387725830078, "global_step": 468487, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0049448013305664, "global_step": 468488, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0176868438720703, "global_step": 468489, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.977696418762207, "global_step": 468490, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.052561044692993, "global_step": 468491, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1128158569335938, "global_step": 468492, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1574807167053223, "global_step": 468493, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.054774522781372, "global_step": 468494, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.141531229019165, "global_step": 468495, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1137402057647705, "global_step": 468496, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0267109870910645, "global_step": 468497, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.070523262023926, "global_step": 468498, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0746495723724365, "global_step": 468499, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1215670108795166, "global_step": 468500, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.003441095352173, "global_step": 468501, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0725605487823486, "global_step": 468502, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.005953788757324, "global_step": 468503, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9650195837020874, "global_step": 468504, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.06947660446167, "global_step": 468505, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.027276039123535, "global_step": 468506, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0825276374816895, "global_step": 468507, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.112912893295288, "global_step": 468508, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.052729368209839, "global_step": 468509, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0311801433563232, "global_step": 468510, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.116323947906494, "global_step": 468511, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.049471616744995, "global_step": 468512, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.987284541130066, "global_step": 468513, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0332531929016113, "global_step": 468514, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9998008012771606, "global_step": 468515, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1337835788726807, "global_step": 468516, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0952095985412598, "global_step": 468517, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0619304180145264, "global_step": 468518, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.036066770553589, "global_step": 468519, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0417582988739014, "global_step": 468520, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1317408084869385, "global_step": 468521, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.054281234741211, "global_step": 468522, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.174588918685913, "global_step": 468523, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9960663318634033, "global_step": 468524, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.046469211578369, "global_step": 468525, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.078223466873169, "global_step": 468526, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.944237232208252, "global_step": 468527, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.006485939025879, "global_step": 468528, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.099792003631592, "global_step": 468529, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0055575370788574, "global_step": 468530, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.091526508331299, "global_step": 468531, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.093341827392578, "global_step": 468532, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0371954441070557, "global_step": 468533, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.15733003616333, "global_step": 468534, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.124845027923584, "global_step": 468535, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.047513484954834, "global_step": 468536, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.074106454849243, "global_step": 468537, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1544177532196045, "global_step": 468538, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0509355068206787, "global_step": 468539, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1249313354492188, "global_step": 468540, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.085376739501953, "global_step": 468541, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.044642210006714, "global_step": 468542, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0864627361297607, "global_step": 468543, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.154478073120117, "global_step": 468544, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9498249292373657, "global_step": 468545, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0513548851013184, "global_step": 468546, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1051244735717773, "global_step": 468547, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.058140754699707, "global_step": 468548, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9907755851745605, "global_step": 468549, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.140001058578491, "global_step": 468550, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0843780040740967, "global_step": 468551, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0712761878967285, "global_step": 468552, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1161508560180664, "global_step": 468553, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9569222927093506, "global_step": 468554, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0320560932159424, "global_step": 468555, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9959776401519775, "global_step": 468556, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0150678157806396, "global_step": 468557, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.049727439880371, "global_step": 468558, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.071880340576172, "global_step": 468559, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.018399953842163, "global_step": 468560, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.039490222930908, "global_step": 468561, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.105027914047241, "global_step": 468562, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1616671085357666, "global_step": 468563, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.157924175262451, "global_step": 468564, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0167524814605713, "global_step": 468565, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0324831008911133, "global_step": 468566, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.060790777206421, "global_step": 468567, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.125426769256592, "global_step": 468568, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0479233264923096, "global_step": 468569, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9989370107650757, "global_step": 468570, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.069514274597168, "global_step": 468571, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1124396324157715, "global_step": 468572, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.997880220413208, "global_step": 468573, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.059990167617798, "global_step": 468574, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.165874719619751, "global_step": 468575, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9949313402175903, "global_step": 468576, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.043750047683716, "global_step": 468577, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.02494478225708, "global_step": 468578, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0787136554718018, "global_step": 468579, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9855059385299683, "global_step": 468580, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0814733505249023, "global_step": 468581, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.081298351287842, "global_step": 468582, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.132701873779297, "global_step": 468583, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.02258563041687, "global_step": 468584, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0324854850769043, "global_step": 468585, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.014519691467285, "global_step": 468586, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1484503746032715, "global_step": 468587, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.053266763687134, "global_step": 468588, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0623977184295654, "global_step": 468589, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.088178873062134, "global_step": 468590, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.007763624191284, "global_step": 468591, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0184097290039062, "global_step": 468592, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.069746255874634, "global_step": 468593, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9607951641082764, "global_step": 468594, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0449342727661133, "global_step": 468595, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.031453847885132, "global_step": 468596, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0271453857421875, "global_step": 468597, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9662742614746094, "global_step": 468598, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1617369651794434, "global_step": 468599, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.116523027420044, "global_step": 468600, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.086580753326416, "global_step": 468601, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.132668972015381, "global_step": 468602, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.025055408477783, "global_step": 468603, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0260932445526123, "global_step": 468604, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0748350620269775, "global_step": 468605, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.8948060274124146, "global_step": 468606, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.054149866104126, "global_step": 468607, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0747909545898438, "global_step": 468608, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9647834300994873, "global_step": 468609, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0401992797851562, "global_step": 468610, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0472733974456787, "global_step": 468611, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0360870361328125, "global_step": 468612, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.034480094909668, "global_step": 468613, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0438754558563232, "global_step": 468614, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1324284076690674, "global_step": 468615, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9860448837280273, "global_step": 468616, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9706370830535889, "global_step": 468617, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.968855857849121, "global_step": 468618, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.045032024383545, "global_step": 468619, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0884125232696533, "global_step": 468620, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0731208324432373, "global_step": 468621, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.118858575820923, "global_step": 468622, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0742807388305664, "global_step": 468623, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.952906608581543, "global_step": 468624, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0425167083740234, "global_step": 468625, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0561654567718506, "global_step": 468626, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0760443210601807, "global_step": 468627, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.153235912322998, "global_step": 468628, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0058465003967285, "global_step": 468629, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1810266971588135, "global_step": 468630, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0354971885681152, "global_step": 468631, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0214412212371826, "global_step": 468632, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.983372449874878, "global_step": 468633, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0535635948181152, "global_step": 468634, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9982473850250244, "global_step": 468635, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.034234046936035, "global_step": 468636, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.017838954925537, "global_step": 468637, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.00116229057312, "global_step": 468638, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0239875316619873, "global_step": 468639, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1378700733184814, "global_step": 468640, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0715272426605225, "global_step": 468641, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.111403465270996, "global_step": 468642, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.175485372543335, "global_step": 468643, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.161052942276001, "global_step": 468644, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.025484085083008, "global_step": 468645, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.207580089569092, "global_step": 468646, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.059727191925049, "global_step": 468647, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.063711166381836, "global_step": 468648, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0994842052459717, "global_step": 468649, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1050405502319336, "global_step": 468650, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.988709807395935, "global_step": 468651, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0961952209472656, "global_step": 468652, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0687341690063477, "global_step": 468653, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0497074127197266, "global_step": 468654, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.121061325073242, "global_step": 468655, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.099761962890625, "global_step": 468656, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0480501651763916, "global_step": 468657, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0989279747009277, "global_step": 468658, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.027047634124756, "global_step": 468659, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1079142093658447, "global_step": 468660, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.027771234512329, "global_step": 468661, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0617623329162598, "global_step": 468662, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.086091995239258, "global_step": 468663, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.064729690551758, "global_step": 468664, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0628581047058105, "global_step": 468665, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0642669200897217, "global_step": 468666, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1051924228668213, "global_step": 468667, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1311187744140625, "global_step": 468668, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.134204149246216, "global_step": 468669, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0290865898132324, "global_step": 468670, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.078519105911255, "global_step": 468671, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1522598266601562, "global_step": 468672, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0981009006500244, "global_step": 468673, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1557250022888184, "global_step": 468674, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.088214874267578, "global_step": 468675, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.049936056137085, "global_step": 468676, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0514345169067383, "global_step": 468677, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0569849014282227, "global_step": 468678, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0919830799102783, "global_step": 468679, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.087373733520508, "global_step": 468680, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.027015447616577, "global_step": 468681, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0816850662231445, "global_step": 468682, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1535794734954834, "global_step": 468683, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.136861801147461, "global_step": 468684, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0511581897735596, "global_step": 468685, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.062084436416626, "global_step": 468686, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1119890213012695, "global_step": 468687, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.98263680934906, "global_step": 468688, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.997228741645813, "global_step": 468689, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0485408306121826, "global_step": 468690, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1391348838806152, "global_step": 468691, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0755627155303955, "global_step": 468692, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0805537700653076, "global_step": 468693, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.07184100151062, "global_step": 468694, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0038249492645264, "global_step": 468695, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1260507106781006, "global_step": 468696, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1185476779937744, "global_step": 468697, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.030254602432251, "global_step": 468698, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.045070171356201, "global_step": 468699, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1071598529815674, "global_step": 468700, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0796408653259277, "global_step": 468701, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.093383550643921, "global_step": 468702, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0366365909576416, "global_step": 468703, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.167980194091797, "global_step": 468704, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.018993854522705, "global_step": 468705, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0975494384765625, "global_step": 468706, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.178126096725464, "global_step": 468707, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0456430912017822, "global_step": 468708, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0096232891082764, "global_step": 468709, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9956340789794922, "global_step": 468710, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.141425609588623, "global_step": 468711, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1097795963287354, "global_step": 468712, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0466179847717285, "global_step": 468713, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0741565227508545, "global_step": 468714, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.129578113555908, "global_step": 468715, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9844988584518433, "global_step": 468716, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.100815534591675, "global_step": 468717, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0537760257720947, "global_step": 468718, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9631186723709106, "global_step": 468719, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0383245944976807, "global_step": 468720, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1527960300445557, "global_step": 468721, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.984485149383545, "global_step": 468722, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.125976324081421, "global_step": 468723, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0069961547851562, "global_step": 468724, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.116626262664795, "global_step": 468725, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1083168983459473, "global_step": 468726, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.145967483520508, "global_step": 468727, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.074414014816284, "global_step": 468728, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.056515693664551, "global_step": 468729, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0893681049346924, "global_step": 468730, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.041558265686035, "global_step": 468731, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0442821979522705, "global_step": 468732, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1354575157165527, "global_step": 468733, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1304216384887695, "global_step": 468734, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0603110790252686, "global_step": 468735, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.064286470413208, "global_step": 468736, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9849339723587036, "global_step": 468737, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0017879009246826, "global_step": 468738, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0411722660064697, "global_step": 468739, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1091911792755127, "global_step": 468740, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.023693323135376, "global_step": 468741, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0256855487823486, "global_step": 468742, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0161492824554443, "global_step": 468743, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.154012680053711, "global_step": 468744, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1102383136749268, "global_step": 468745, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0598223209381104, "global_step": 468746, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.002957344055176, "global_step": 468747, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0846378803253174, "global_step": 468748, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.05657958984375, "global_step": 468749, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1456267833709717, "global_step": 468750, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0196375846862793, "global_step": 468751, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0232646465301514, "global_step": 468752, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0517826080322266, "global_step": 468753, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0408623218536377, "global_step": 468754, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.068127155303955, "global_step": 468755, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.109598159790039, "global_step": 468756, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1223206520080566, "global_step": 468757, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1259806156158447, "global_step": 468758, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0435361862182617, "global_step": 468759, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.042797088623047, "global_step": 468760, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.10198712348938, "global_step": 468761, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0627634525299072, "global_step": 468762, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0507872104644775, "global_step": 468763, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0720291137695312, "global_step": 468764, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0184004306793213, "global_step": 468765, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.072709798812866, "global_step": 468766, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.086358070373535, "global_step": 468767, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0728025436401367, "global_step": 468768, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0394444465637207, "global_step": 468769, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0903706550598145, "global_step": 468770, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9826414585113525, "global_step": 468771, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0590951442718506, "global_step": 468772, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0799787044525146, "global_step": 468773, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0760648250579834, "global_step": 468774, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.02835750579834, "global_step": 468775, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.11173677444458, "global_step": 468776, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1175994873046875, "global_step": 468777, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0477705001831055, "global_step": 468778, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0680227279663086, "global_step": 468779, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.120983362197876, "global_step": 468780, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.016345262527466, "global_step": 468781, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.067274808883667, "global_step": 468782, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.05277943611145, "global_step": 468783, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.067326545715332, "global_step": 468784, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.066786766052246, "global_step": 468785, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0661239624023438, "global_step": 468786, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0255606174468994, "global_step": 468787, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.973630428314209, "global_step": 468788, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.052126407623291, "global_step": 468789, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.15018892288208, "global_step": 468790, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0196192264556885, "global_step": 468791, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.107243299484253, "global_step": 468792, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.124128580093384, "global_step": 468793, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.085747003555298, "global_step": 468794, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.075856924057007, "global_step": 468795, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1017351150512695, "global_step": 468796, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.028054714202881, "global_step": 468797, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.119974136352539, "global_step": 468798, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.090236186981201, "global_step": 468799, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.128657102584839, "global_step": 468800, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0922019481658936, "global_step": 468801, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1463305950164795, "global_step": 468802, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.129744052886963, "global_step": 468803, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.030514717102051, "global_step": 468804, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9650567770004272, "global_step": 468805, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1428110599517822, "global_step": 468806, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0722429752349854, "global_step": 468807, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0333638191223145, "global_step": 468808, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0933780670166016, "global_step": 468809, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.073174476623535, "global_step": 468810, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.075043201446533, "global_step": 468811, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.168883800506592, "global_step": 468812, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0489675998687744, "global_step": 468813, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.112058162689209, "global_step": 468814, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.067634105682373, "global_step": 468815, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1033575534820557, "global_step": 468816, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.135917901992798, "global_step": 468817, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.060685157775879, "global_step": 468818, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.014575958251953, "global_step": 468819, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.065718412399292, "global_step": 468820, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.073768377304077, "global_step": 468821, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.025655508041382, "global_step": 468822, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0273149013519287, "global_step": 468823, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0591788291931152, "global_step": 468824, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.046717405319214, "global_step": 468825, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1325020790100098, "global_step": 468826, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.133943557739258, "global_step": 468827, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.105750322341919, "global_step": 468828, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0435943603515625, "global_step": 468829, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.120728015899658, "global_step": 468830, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0781631469726562, "global_step": 468831, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0999836921691895, "global_step": 468832, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1280622482299805, "global_step": 468833, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0490877628326416, "global_step": 468834, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9898998737335205, "global_step": 468835, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0510101318359375, "global_step": 468836, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0048770904541016, "global_step": 468837, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.098148822784424, "global_step": 468838, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.056784152984619, "global_step": 468839, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1294798851013184, "global_step": 468840, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1744472980499268, "global_step": 468841, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.084110975265503, "global_step": 468842, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.081895351409912, "global_step": 468843, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1064913272857666, "global_step": 468844, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1400725841522217, "global_step": 468845, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0823962688446045, "global_step": 468846, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1367270946502686, "global_step": 468847, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1169533729553223, "global_step": 468848, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.075294256210327, "global_step": 468849, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.039337396621704, "global_step": 468850, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0278072357177734, "global_step": 468851, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9892537593841553, "global_step": 468852, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1678993701934814, "global_step": 468853, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.016564130783081, "global_step": 468854, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9999120235443115, "global_step": 468855, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0475354194641113, "global_step": 468856, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.992139220237732, "global_step": 468857, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0495967864990234, "global_step": 468858, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1007144451141357, "global_step": 468859, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1075475215911865, "global_step": 468860, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0549769401550293, "global_step": 468861, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.089772939682007, "global_step": 468862, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1520402431488037, "global_step": 468863, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.05696439743042, "global_step": 468864, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0937469005584717, "global_step": 468865, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.034050703048706, "global_step": 468866, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1281893253326416, "global_step": 468867, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.056583881378174, "global_step": 468868, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1039886474609375, "global_step": 468869, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0203404426574707, "global_step": 468870, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0939433574676514, "global_step": 468871, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0741794109344482, "global_step": 468872, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1263883113861084, "global_step": 468873, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0537683963775635, "global_step": 468874, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9612979888916016, "global_step": 468875, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0608766078948975, "global_step": 468876, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0138514041900635, "global_step": 468877, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.155022621154785, "global_step": 468878, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1059179306030273, "global_step": 468879, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0660817623138428, "global_step": 468880, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.188293695449829, "global_step": 468881, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.051663875579834, "global_step": 468882, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0416159629821777, "global_step": 468883, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.072765350341797, "global_step": 468884, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0177509784698486, "global_step": 468885, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1015076637268066, "global_step": 468886, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0643060207366943, "global_step": 468887, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1458160877227783, "global_step": 468888, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.099397897720337, "global_step": 468889, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0024523735046387, "global_step": 468890, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9911940097808838, "global_step": 468891, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0645487308502197, "global_step": 468892, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.161644458770752, "global_step": 468893, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0853679180145264, "global_step": 468894, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0478384494781494, "global_step": 468895, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.131671905517578, "global_step": 468896, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0396628379821777, "global_step": 468897, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1074845790863037, "global_step": 468898, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.01586651802063, "global_step": 468899, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.138211727142334, "global_step": 468900, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9758214950561523, "global_step": 468901, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9774434566497803, "global_step": 468902, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1422908306121826, "global_step": 468903, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0962436199188232, "global_step": 468904, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0772316455841064, "global_step": 468905, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9739022254943848, "global_step": 468906, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1119582653045654, "global_step": 468907, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0220236778259277, "global_step": 468908, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.070730686187744, "global_step": 468909, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.062551498413086, "global_step": 468910, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.116335153579712, "global_step": 468911, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1036767959594727, "global_step": 468912, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0484418869018555, "global_step": 468913, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0215678215026855, "global_step": 468914, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0631661415100098, "global_step": 468915, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.042360544204712, "global_step": 468916, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0748348236083984, "global_step": 468917, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.036663770675659, "global_step": 468918, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0324227809906006, "global_step": 468919, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.053570032119751, "global_step": 468920, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0361273288726807, "global_step": 468921, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0704095363616943, "global_step": 468922, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.074709177017212, "global_step": 468923, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0995378494262695, "global_step": 468924, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0478732585906982, "global_step": 468925, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.120365619659424, "global_step": 468926, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.062908411026001, "global_step": 468927, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0921831130981445, "global_step": 468928, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1245343685150146, "global_step": 468929, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0436272621154785, "global_step": 468930, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0459489822387695, "global_step": 468931, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0863640308380127, "global_step": 468932, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1063642501831055, "global_step": 468933, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9812190532684326, "global_step": 468934, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9864749908447266, "global_step": 468935, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.133552074432373, "global_step": 468936, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0899312496185303, "global_step": 468937, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.042865514755249, "global_step": 468938, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.092339277267456, "global_step": 468939, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.115504503250122, "global_step": 468940, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0215389728546143, "global_step": 468941, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9975560903549194, "global_step": 468942, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0278513431549072, "global_step": 468943, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0578558444976807, "global_step": 468944, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1352736949920654, "global_step": 468945, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.067145586013794, "global_step": 468946, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0168421268463135, "global_step": 468947, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0442380905151367, "global_step": 468948, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.035020351409912, "global_step": 468949, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.140428066253662, "global_step": 468950, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1091742515563965, "global_step": 468951, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.12280011177063, "global_step": 468952, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.055989980697632, "global_step": 468953, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.041595697402954, "global_step": 468954, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.036799192428589, "global_step": 468955, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0413761138916016, "global_step": 468956, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.054133653640747, "global_step": 468957, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0761566162109375, "global_step": 468958, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1099228858947754, "global_step": 468959, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.157611608505249, "global_step": 468960, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0246005058288574, "global_step": 468961, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.02408504486084, "global_step": 468962, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.088768720626831, "global_step": 468963, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1157290935516357, "global_step": 468964, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.100477933883667, "global_step": 468965, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0074782371520996, "global_step": 468966, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.075047254562378, "global_step": 468967, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0265207290649414, "global_step": 468968, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0156235694885254, "global_step": 468969, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0837037563323975, "global_step": 468970, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.059617519378662, "global_step": 468971, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.082125425338745, "global_step": 468972, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0327682495117188, "global_step": 468973, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.131361484527588, "global_step": 468974, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1158945560455322, "global_step": 468975, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9981814622879028, "global_step": 468976, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.028891086578369, "global_step": 468977, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0835862159729004, "global_step": 468978, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0911686420440674, "global_step": 468979, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0108978748321533, "global_step": 468980, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0144472122192383, "global_step": 468981, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.909944772720337, "global_step": 468982, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0923874378204346, "global_step": 468983, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1403121948242188, "global_step": 468984, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1064181327819824, "global_step": 468985, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0731918811798096, "global_step": 468986, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0653462409973145, "global_step": 468987, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1482744216918945, "global_step": 468988, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0924320220947266, "global_step": 468989, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1205151081085205, "global_step": 468990, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.035385847091675, "global_step": 468991, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.07133150100708, "global_step": 468992, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0940890312194824, "global_step": 468993, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0957295894622803, "global_step": 468994, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0025157928466797, "global_step": 468995, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.128295660018921, "global_step": 468996, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.140594720840454, "global_step": 468997, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0477635860443115, "global_step": 468998, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1210265159606934, "global_step": 468999, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0756607055664062, "global_step": 469000, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.08834171295166, "global_step": 469001, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1050026416778564, "global_step": 469002, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0562095642089844, "global_step": 469003, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1107637882232666, "global_step": 469004, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.038844585418701, "global_step": 469005, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.141758918762207, "global_step": 469006, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.086062431335449, "global_step": 469007, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0516951084136963, "global_step": 469008, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.073129415512085, "global_step": 469009, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.109781503677368, "global_step": 469010, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0693371295928955, "global_step": 469011, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0990662574768066, "global_step": 469012, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0715408325195312, "global_step": 469013, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0601296424865723, "global_step": 469014, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1095051765441895, "global_step": 469015, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0294384956359863, "global_step": 469016, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.061760187149048, "global_step": 469017, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.08321213722229, "global_step": 469018, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1319522857666016, "global_step": 469019, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.086650848388672, "global_step": 469020, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.147284746170044, "global_step": 469021, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.909811019897461, "global_step": 469022, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.080592155456543, "global_step": 469023, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9769600629806519, "global_step": 469024, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.052757501602173, "global_step": 469025, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0939199924468994, "global_step": 469026, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0826151371002197, "global_step": 469027, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.979145884513855, "global_step": 469028, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9831169843673706, "global_step": 469029, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0945897102355957, "global_step": 469030, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.115036964416504, "global_step": 469031, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0004093647003174, "global_step": 469032, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0286786556243896, "global_step": 469033, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.04289174079895, "global_step": 469034, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.072263479232788, "global_step": 469035, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.134575605392456, "global_step": 469036, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.995835542678833, "global_step": 469037, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.092313766479492, "global_step": 469038, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0311262607574463, "global_step": 469039, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0533499717712402, "global_step": 469040, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1099233627319336, "global_step": 469041, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.028855085372925, "global_step": 469042, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1011977195739746, "global_step": 469043, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0892388820648193, "global_step": 469044, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.047685146331787, "global_step": 469045, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.043128252029419, "global_step": 469046, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.067782163619995, "global_step": 469047, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0452420711517334, "global_step": 469048, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.07000994682312, "global_step": 469049, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0938849449157715, "global_step": 469050, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1078598499298096, "global_step": 469051, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.106931447982788, "global_step": 469052, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0450973510742188, "global_step": 469053, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.04463267326355, "global_step": 469054, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0770459175109863, "global_step": 469055, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.081052303314209, "global_step": 469056, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1344733238220215, "global_step": 469057, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0707614421844482, "global_step": 469058, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.168849229812622, "global_step": 469059, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.09869384765625, "global_step": 469060, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.020122766494751, "global_step": 469061, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.950594186782837, "global_step": 469062, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.111269235610962, "global_step": 469063, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.040586471557617, "global_step": 469064, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0927274227142334, "global_step": 469065, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.105743646621704, "global_step": 469066, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0284085273742676, "global_step": 469067, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0430731773376465, "global_step": 469068, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1628994941711426, "global_step": 469069, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.07603120803833, "global_step": 469070, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.049682140350342, "global_step": 469071, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0861058235168457, "global_step": 469072, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0949273109436035, "global_step": 469073, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1278254985809326, "global_step": 469074, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0721189975738525, "global_step": 469075, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.049288511276245, "global_step": 469076, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0649640560150146, "global_step": 469077, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.127703905105591, "global_step": 469078, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.080662965774536, "global_step": 469079, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.083645820617676, "global_step": 469080, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.059772253036499, "global_step": 469081, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0190038681030273, "global_step": 469082, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.068484306335449, "global_step": 469083, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.025743007659912, "global_step": 469084, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.038849353790283, "global_step": 469085, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0402324199676514, "global_step": 469086, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0958681106567383, "global_step": 469087, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1081767082214355, "global_step": 469088, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.086359739303589, "global_step": 469089, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.037583589553833, "global_step": 469090, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0917084217071533, "global_step": 469091, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0777668952941895, "global_step": 469092, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1389386653900146, "global_step": 469093, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0610382556915283, "global_step": 469094, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0832464694976807, "global_step": 469095, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9719054698944092, "global_step": 469096, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1148765087127686, "global_step": 469097, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.083887815475464, "global_step": 469098, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.064819574356079, "global_step": 469099, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.089559555053711, "global_step": 469100, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.045970916748047, "global_step": 469101, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0348684787750244, "global_step": 469102, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0661776065826416, "global_step": 469103, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.000656843185425, "global_step": 469104, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.072737216949463, "global_step": 469105, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.12726092338562, "global_step": 469106, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.078902006149292, "global_step": 469107, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.044356107711792, "global_step": 469108, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0293455123901367, "global_step": 469109, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9942715167999268, "global_step": 469110, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9655574560165405, "global_step": 469111, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0017788410186768, "global_step": 469112, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0032436847686768, "global_step": 469113, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.083669662475586, "global_step": 469114, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9917184114456177, "global_step": 469115, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.072535753250122, "global_step": 469116, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1270859241485596, "global_step": 469117, "epoch": 833, "lr": 5e-05}
{"train_loss": 1.9512827396392822, "global_step": 469118, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0227537155151367, "global_step": 469119, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.055826187133789, "global_step": 469120, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.02836537361145, "global_step": 469121, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1345677375793457, "global_step": 469122, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0917067527770996, "global_step": 469123, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.1069931983947754, "global_step": 469124, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0925004482269287, "global_step": 469125, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0083327293395996, "global_step": 469126, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.0994131565093994, "global_step": 469127, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.063795804977417, "global_step": 469128, "epoch": 833, "lr": 5e-05}
{"train_loss": 2.105665683746338, "global_step": 469129, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0782673358917236, "global_step": 469130, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9950801134109497, "global_step": 469131, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9849553108215332, "global_step": 469132, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0071921348571777, "global_step": 469133, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1130542755126953, "global_step": 469134, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.00492525100708, "global_step": 469135, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0725183486938477, "global_step": 469136, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.136319398880005, "global_step": 469137, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.096121311187744, "global_step": 469138, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0846614837646484, "global_step": 469139, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0220584869384766, "global_step": 469140, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0106637477874756, "global_step": 469141, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0190727710723877, "global_step": 469142, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.037814140319824, "global_step": 469143, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1099917888641357, "global_step": 469144, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.080585479736328, "global_step": 469145, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0415942668914795, "global_step": 469146, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.053109884262085, "global_step": 469147, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0421767234802246, "global_step": 469148, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0465641021728516, "global_step": 469149, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.048177719116211, "global_step": 469150, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9939091205596924, "global_step": 469151, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1118667125701904, "global_step": 469152, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.065357208251953, "global_step": 469153, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0783867835998535, "global_step": 469154, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0629637241363525, "global_step": 469155, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0958633422851562, "global_step": 469156, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0903515815734863, "global_step": 469157, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0887320041656494, "global_step": 469158, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.998077630996704, "global_step": 469159, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9396928548812866, "global_step": 469160, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0151209831237793, "global_step": 469161, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.042473316192627, "global_step": 469162, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0922164916992188, "global_step": 469163, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1271889209747314, "global_step": 469164, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.921367883682251, "global_step": 469165, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.052354574203491, "global_step": 469166, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0840303897857666, "global_step": 469167, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0274577140808105, "global_step": 469168, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0184290409088135, "global_step": 469169, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.113171100616455, "global_step": 469170, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0457375049591064, "global_step": 469171, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.046119451522827, "global_step": 469172, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9611780643463135, "global_step": 469173, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.009355068206787, "global_step": 469174, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.067233085632324, "global_step": 469175, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0682156085968018, "global_step": 469176, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0422351360321045, "global_step": 469177, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9960711002349854, "global_step": 469178, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.116396427154541, "global_step": 469179, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0781538486480713, "global_step": 469180, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.000819683074951, "global_step": 469181, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.955137848854065, "global_step": 469182, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.02201771736145, "global_step": 469183, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.969370722770691, "global_step": 469184, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.085460901260376, "global_step": 469185, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0200681686401367, "global_step": 469186, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0910794734954834, "global_step": 469187, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9278656244277954, "global_step": 469188, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9969903230667114, "global_step": 469189, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9852737188339233, "global_step": 469190, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0815789699554443, "global_step": 469191, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.123105525970459, "global_step": 469192, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.111628770828247, "global_step": 469193, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.060969829559326, "global_step": 469194, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0819754600524902, "global_step": 469195, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0980072021484375, "global_step": 469196, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0432205200195312, "global_step": 469197, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1280224323272705, "global_step": 469198, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.100578546524048, "global_step": 469199, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.160715341567993, "global_step": 469200, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.039771795272827, "global_step": 469201, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.096428155899048, "global_step": 469202, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0279464721679688, "global_step": 469203, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.11218523979187, "global_step": 469204, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0179498195648193, "global_step": 469205, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9964020252227783, "global_step": 469206, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0752675533294678, "global_step": 469207, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.095918655395508, "global_step": 469208, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.087334394454956, "global_step": 469209, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.095635414123535, "global_step": 469210, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0564117431640625, "global_step": 469211, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.023829698562622, "global_step": 469212, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.075793504714966, "global_step": 469213, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.086097478866577, "global_step": 469214, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0711028575897217, "global_step": 469215, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0904343128204346, "global_step": 469216, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.071124792098999, "global_step": 469217, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9473013877868652, "global_step": 469218, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1114449501037598, "global_step": 469219, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.992773175239563, "global_step": 469220, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9835749864578247, "global_step": 469221, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0725224018096924, "global_step": 469222, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0042548179626465, "global_step": 469223, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0560123920440674, "global_step": 469224, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1106138229370117, "global_step": 469225, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.051176071166992, "global_step": 469226, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.010362386703491, "global_step": 469227, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.090472936630249, "global_step": 469228, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.096015453338623, "global_step": 469229, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0515036582946777, "global_step": 469230, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0994465351104736, "global_step": 469231, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9938879013061523, "global_step": 469232, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0730559825897217, "global_step": 469233, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0788557529449463, "global_step": 469234, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0520811080932617, "global_step": 469235, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9565284252166748, "global_step": 469236, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0083954334259033, "global_step": 469237, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.091149091720581, "global_step": 469238, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1030373573303223, "global_step": 469239, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0663113594055176, "global_step": 469240, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.09110164642334, "global_step": 469241, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.022815227508545, "global_step": 469242, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.983847737312317, "global_step": 469243, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0516610145568848, "global_step": 469244, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0307676792144775, "global_step": 469245, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0156328678131104, "global_step": 469246, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9988237619400024, "global_step": 469247, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0531575679779053, "global_step": 469248, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0750746726989746, "global_step": 469249, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.002753734588623, "global_step": 469250, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1424825191497803, "global_step": 469251, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1469595432281494, "global_step": 469252, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0674495697021484, "global_step": 469253, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0280895233154297, "global_step": 469254, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0617964267730713, "global_step": 469255, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0628840923309326, "global_step": 469256, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0488662719726562, "global_step": 469257, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.101569890975952, "global_step": 469258, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0746495723724365, "global_step": 469259, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0506765842437744, "global_step": 469260, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9896973371505737, "global_step": 469261, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.116421937942505, "global_step": 469262, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.038299322128296, "global_step": 469263, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0335686206817627, "global_step": 469264, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0977258682250977, "global_step": 469265, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0727381706237793, "global_step": 469266, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0614304542541504, "global_step": 469267, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0009613037109375, "global_step": 469268, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1079463958740234, "global_step": 469269, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.045923948287964, "global_step": 469270, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.077739953994751, "global_step": 469271, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0962891578674316, "global_step": 469272, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9592970609664917, "global_step": 469273, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1202142238616943, "global_step": 469274, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0681846141815186, "global_step": 469275, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9731457233428955, "global_step": 469276, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0439555644989014, "global_step": 469277, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.089246988296509, "global_step": 469278, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.085744857788086, "global_step": 469279, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0099143981933594, "global_step": 469280, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.091729164123535, "global_step": 469281, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.99465012550354, "global_step": 469282, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.059670925140381, "global_step": 469283, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1013259887695312, "global_step": 469284, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.087954521179199, "global_step": 469285, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9868966341018677, "global_step": 469286, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.149146556854248, "global_step": 469287, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1568398475646973, "global_step": 469288, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1150240898132324, "global_step": 469289, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0873143672943115, "global_step": 469290, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0768883228302, "global_step": 469291, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.175471067428589, "global_step": 469292, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0793659687042236, "global_step": 469293, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0451791286468506, "global_step": 469294, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1035985946655273, "global_step": 469295, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.96478271484375, "global_step": 469296, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0335381031036377, "global_step": 469297, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1312901973724365, "global_step": 469298, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1001322269439697, "global_step": 469299, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.032066583633423, "global_step": 469300, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0771169662475586, "global_step": 469301, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1428182125091553, "global_step": 469302, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.077164888381958, "global_step": 469303, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0790817737579346, "global_step": 469304, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9817619323730469, "global_step": 469305, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0238687992095947, "global_step": 469306, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.020719528198242, "global_step": 469307, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0254080295562744, "global_step": 469308, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0983242988586426, "global_step": 469309, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.058999538421631, "global_step": 469310, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0378403663635254, "global_step": 469311, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.116556167602539, "global_step": 469312, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.009051561355591, "global_step": 469313, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.087270498275757, "global_step": 469314, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0672500133514404, "global_step": 469315, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0314252376556396, "global_step": 469316, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9347847700119019, "global_step": 469317, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.046025037765503, "global_step": 469318, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0536015033721924, "global_step": 469319, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.119417667388916, "global_step": 469320, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.124316930770874, "global_step": 469321, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.062915086746216, "global_step": 469322, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.04291033744812, "global_step": 469323, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9655743837356567, "global_step": 469324, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0837347507476807, "global_step": 469325, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1024701595306396, "global_step": 469326, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9882047176361084, "global_step": 469327, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1010501384735107, "global_step": 469328, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0904855728149414, "global_step": 469329, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0842294692993164, "global_step": 469330, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.032580852508545, "global_step": 469331, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.017735481262207, "global_step": 469332, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0928537845611572, "global_step": 469333, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0333094596862793, "global_step": 469334, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0758326053619385, "global_step": 469335, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.102084159851074, "global_step": 469336, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.106058120727539, "global_step": 469337, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0210139751434326, "global_step": 469338, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0306713581085205, "global_step": 469339, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.026310920715332, "global_step": 469340, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0421364307403564, "global_step": 469341, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1250104904174805, "global_step": 469342, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.041938543319702, "global_step": 469343, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9759831428527832, "global_step": 469344, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9739422798156738, "global_step": 469345, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1200759410858154, "global_step": 469346, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0833356380462646, "global_step": 469347, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0665464401245117, "global_step": 469348, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0555853843688965, "global_step": 469349, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0409295558929443, "global_step": 469350, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0867698192596436, "global_step": 469351, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.964969277381897, "global_step": 469352, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9746119976043701, "global_step": 469353, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0372018814086914, "global_step": 469354, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1019515991210938, "global_step": 469355, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0989990234375, "global_step": 469356, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.066281318664551, "global_step": 469357, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.123901605606079, "global_step": 469358, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0683741569519043, "global_step": 469359, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1048953533172607, "global_step": 469360, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.09316086769104, "global_step": 469361, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.026242971420288, "global_step": 469362, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1012444496154785, "global_step": 469363, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.082401990890503, "global_step": 469364, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9359772205352783, "global_step": 469365, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1003196239471436, "global_step": 469366, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.068404197692871, "global_step": 469367, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0435256958007812, "global_step": 469368, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1035337448120117, "global_step": 469369, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.108389377593994, "global_step": 469370, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9694522619247437, "global_step": 469371, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0948874950408936, "global_step": 469372, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0530507564544678, "global_step": 469373, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.016035556793213, "global_step": 469374, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0620522499084473, "global_step": 469375, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0831403732299805, "global_step": 469376, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9676845073699951, "global_step": 469377, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0923142433166504, "global_step": 469378, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.046215534210205, "global_step": 469379, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9029128551483154, "global_step": 469380, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.126746654510498, "global_step": 469381, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0431554317474365, "global_step": 469382, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0918328762054443, "global_step": 469383, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.131396532058716, "global_step": 469384, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0751230716705322, "global_step": 469385, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.058633804321289, "global_step": 469386, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9178783893585205, "global_step": 469387, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0355224609375, "global_step": 469388, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0501904487609863, "global_step": 469389, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0937435626983643, "global_step": 469390, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.098278284072876, "global_step": 469391, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0640339851379395, "global_step": 469392, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0285799503326416, "global_step": 469393, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0197970867156982, "global_step": 469394, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0327296257019043, "global_step": 469395, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0113160610198975, "global_step": 469396, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.984135389328003, "global_step": 469397, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0483908653259277, "global_step": 469398, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0031051635742188, "global_step": 469399, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0619781017303467, "global_step": 469400, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.09570050239563, "global_step": 469401, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.070873498916626, "global_step": 469402, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0290982723236084, "global_step": 469403, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.049669027328491, "global_step": 469404, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0358495712280273, "global_step": 469405, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.158808946609497, "global_step": 469406, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0627236366271973, "global_step": 469407, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9949713945388794, "global_step": 469408, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0523457527160645, "global_step": 469409, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.054161310195923, "global_step": 469410, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.126117467880249, "global_step": 469411, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0560014247894287, "global_step": 469412, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0743958950042725, "global_step": 469413, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0450968742370605, "global_step": 469414, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.072460889816284, "global_step": 469415, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.069071054458618, "global_step": 469416, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9370617866516113, "global_step": 469417, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0731923580169678, "global_step": 469418, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0483717918395996, "global_step": 469419, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0282764434814453, "global_step": 469420, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.05033540725708, "global_step": 469421, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0671889781951904, "global_step": 469422, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0246896743774414, "global_step": 469423, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1075780391693115, "global_step": 469424, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0661115646362305, "global_step": 469425, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.065014600753784, "global_step": 469426, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9798481464385986, "global_step": 469427, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1452717781066895, "global_step": 469428, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.023160219192505, "global_step": 469429, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0198111534118652, "global_step": 469430, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1256496906280518, "global_step": 469431, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1372971534729004, "global_step": 469432, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0573556423187256, "global_step": 469433, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0384938716888428, "global_step": 469434, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0641160011291504, "global_step": 469435, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0479767322540283, "global_step": 469436, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.035249948501587, "global_step": 469437, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0402703285217285, "global_step": 469438, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9894620180130005, "global_step": 469439, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0794477462768555, "global_step": 469440, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.106254816055298, "global_step": 469441, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9843026399612427, "global_step": 469442, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0707406997680664, "global_step": 469443, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.047719955444336, "global_step": 469444, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.060037851333618, "global_step": 469445, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1992719173431396, "global_step": 469446, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0507514476776123, "global_step": 469447, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0770089626312256, "global_step": 469448, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.018949270248413, "global_step": 469449, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.045283555984497, "global_step": 469450, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.060739755630493, "global_step": 469451, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0602829456329346, "global_step": 469452, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.110852003097534, "global_step": 469453, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0006985664367676, "global_step": 469454, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.033945083618164, "global_step": 469455, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0658082962036133, "global_step": 469456, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1323022842407227, "global_step": 469457, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0352554321289062, "global_step": 469458, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1450858116149902, "global_step": 469459, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.089998722076416, "global_step": 469460, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.036691427230835, "global_step": 469461, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.028512477874756, "global_step": 469462, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0507102012634277, "global_step": 469463, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.05714750289917, "global_step": 469464, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.154179811477661, "global_step": 469465, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0074546337127686, "global_step": 469466, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1455860137939453, "global_step": 469467, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.039278745651245, "global_step": 469468, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0273594856262207, "global_step": 469469, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9890108108520508, "global_step": 469470, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0518958568573, "global_step": 469471, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.108588218688965, "global_step": 469472, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1553828716278076, "global_step": 469473, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0682592391967773, "global_step": 469474, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.04543137550354, "global_step": 469475, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0078284740448, "global_step": 469476, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1197922229766846, "global_step": 469477, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1567161083221436, "global_step": 469478, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0689167976379395, "global_step": 469479, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.01669979095459, "global_step": 469480, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.144214153289795, "global_step": 469481, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.113755226135254, "global_step": 469482, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1178388595581055, "global_step": 469483, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0851211547851562, "global_step": 469484, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.043424606323242, "global_step": 469485, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9981374740600586, "global_step": 469486, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.053762912750244, "global_step": 469487, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1318538188934326, "global_step": 469488, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1413729190826416, "global_step": 469489, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0004570484161377, "global_step": 469490, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.104588747024536, "global_step": 469491, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0861001014709473, "global_step": 469492, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0811996459960938, "global_step": 469493, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.02135968208313, "global_step": 469494, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.125870943069458, "global_step": 469495, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.054673910140991, "global_step": 469496, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.068296432495117, "global_step": 469497, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.061192750930786, "global_step": 469498, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1019835472106934, "global_step": 469499, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.112016439437866, "global_step": 469500, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.029143810272217, "global_step": 469501, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0889968872070312, "global_step": 469502, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0456650257110596, "global_step": 469503, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0424652099609375, "global_step": 469504, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.006650686264038, "global_step": 469505, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0062477588653564, "global_step": 469506, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.011336326599121, "global_step": 469507, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0699710845947266, "global_step": 469508, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0867979526519775, "global_step": 469509, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.056790828704834, "global_step": 469510, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0625152587890625, "global_step": 469511, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0768797397613525, "global_step": 469512, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.011826753616333, "global_step": 469513, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.124570608139038, "global_step": 469514, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0179355144500732, "global_step": 469515, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9717638492584229, "global_step": 469516, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.063859224319458, "global_step": 469517, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.981749415397644, "global_step": 469518, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.116189479827881, "global_step": 469519, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1032185554504395, "global_step": 469520, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.027919054031372, "global_step": 469521, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1089956760406494, "global_step": 469522, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.034518003463745, "global_step": 469523, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.100144147872925, "global_step": 469524, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0684306621551514, "global_step": 469525, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.091681480407715, "global_step": 469526, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9813388586044312, "global_step": 469527, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.157304048538208, "global_step": 469528, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.022299289703369, "global_step": 469529, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0240325927734375, "global_step": 469530, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0229873657226562, "global_step": 469531, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0706825256347656, "global_step": 469532, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.033482074737549, "global_step": 469533, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0948755741119385, "global_step": 469534, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0244479179382324, "global_step": 469535, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.115614175796509, "global_step": 469536, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0849099159240723, "global_step": 469537, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.030099868774414, "global_step": 469538, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0133566856384277, "global_step": 469539, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.073162794113159, "global_step": 469540, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9744470119476318, "global_step": 469541, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0797219276428223, "global_step": 469542, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0131115913391113, "global_step": 469543, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9477182626724243, "global_step": 469544, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.12349271774292, "global_step": 469545, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0610833168029785, "global_step": 469546, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0386970043182373, "global_step": 469547, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0515642166137695, "global_step": 469548, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.051691770553589, "global_step": 469549, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0061254501342773, "global_step": 469550, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1027915477752686, "global_step": 469551, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9891213178634644, "global_step": 469552, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.012467861175537, "global_step": 469553, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0770039558410645, "global_step": 469554, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0605316162109375, "global_step": 469555, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9860575199127197, "global_step": 469556, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0540828704833984, "global_step": 469557, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.05051589012146, "global_step": 469558, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1519179344177246, "global_step": 469559, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0637872219085693, "global_step": 469560, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.068706512451172, "global_step": 469561, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0386815071105957, "global_step": 469562, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0650722980499268, "global_step": 469563, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.010201930999756, "global_step": 469564, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0284669399261475, "global_step": 469565, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1695444583892822, "global_step": 469566, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.049525499343872, "global_step": 469567, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0384063720703125, "global_step": 469568, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1530344486236572, "global_step": 469569, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.089982509613037, "global_step": 469570, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.038119077682495, "global_step": 469571, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.085205554962158, "global_step": 469572, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0541441440582275, "global_step": 469573, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0983986854553223, "global_step": 469574, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1019110679626465, "global_step": 469575, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0550284385681152, "global_step": 469576, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.023996114730835, "global_step": 469577, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9924190044403076, "global_step": 469578, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0570998191833496, "global_step": 469579, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0770468711853027, "global_step": 469580, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.108031749725342, "global_step": 469581, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.050762176513672, "global_step": 469582, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.087921619415283, "global_step": 469583, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9736263751983643, "global_step": 469584, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1143176555633545, "global_step": 469585, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0759477615356445, "global_step": 469586, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0459158420562744, "global_step": 469587, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1078600883483887, "global_step": 469588, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1163151264190674, "global_step": 469589, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1690683364868164, "global_step": 469590, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.106290102005005, "global_step": 469591, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1683945655822754, "global_step": 469592, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.002686023712158, "global_step": 469593, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0294418334960938, "global_step": 469594, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0308077335357666, "global_step": 469595, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1160576343536377, "global_step": 469596, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.110767126083374, "global_step": 469597, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9794034957885742, "global_step": 469598, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0880656242370605, "global_step": 469599, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9540996551513672, "global_step": 469600, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.043349266052246, "global_step": 469601, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0310256481170654, "global_step": 469602, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.050980806350708, "global_step": 469603, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9585951566696167, "global_step": 469604, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0415260791778564, "global_step": 469605, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0254735946655273, "global_step": 469606, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0190563201904297, "global_step": 469607, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.064009666442871, "global_step": 469608, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0697810649871826, "global_step": 469609, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0557000637054443, "global_step": 469610, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.071282386779785, "global_step": 469611, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0363571643829346, "global_step": 469612, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0703184604644775, "global_step": 469613, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0005288124084473, "global_step": 469614, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1189489364624023, "global_step": 469615, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0338990688323975, "global_step": 469616, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0925750732421875, "global_step": 469617, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.000471830368042, "global_step": 469618, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.153569221496582, "global_step": 469619, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.15574049949646, "global_step": 469620, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.081242322921753, "global_step": 469621, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.104423761367798, "global_step": 469622, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0185396671295166, "global_step": 469623, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0533394813537598, "global_step": 469624, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.104248046875, "global_step": 469625, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0241878032684326, "global_step": 469626, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1254196166992188, "global_step": 469627, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0794837474823, "global_step": 469628, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0839390754699707, "global_step": 469629, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.087275743484497, "global_step": 469630, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0566940307617188, "global_step": 469631, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.100313901901245, "global_step": 469632, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0625431537628174, "global_step": 469633, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0359134674072266, "global_step": 469634, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.94827139377594, "global_step": 469635, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0766804218292236, "global_step": 469636, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1718904972076416, "global_step": 469637, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0103321075439453, "global_step": 469638, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0275416374206543, "global_step": 469639, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0182316303253174, "global_step": 469640, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.074240207672119, "global_step": 469641, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0388431549072266, "global_step": 469642, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0450475215911865, "global_step": 469643, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1022439002990723, "global_step": 469644, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.128856658935547, "global_step": 469645, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.023651599884033, "global_step": 469646, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9644598960876465, "global_step": 469647, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0328240394592285, "global_step": 469648, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0808796882629395, "global_step": 469649, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0726187229156494, "global_step": 469650, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0635128021240234, "global_step": 469651, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0005574226379395, "global_step": 469652, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.103207588195801, "global_step": 469653, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.067561149597168, "global_step": 469654, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0529117584228516, "global_step": 469655, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.029088020324707, "global_step": 469656, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0832457542419434, "global_step": 469657, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.084092617034912, "global_step": 469658, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0698256492614746, "global_step": 469659, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0629730224609375, "global_step": 469660, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.073869228363037, "global_step": 469661, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1336164474487305, "global_step": 469662, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.119727611541748, "global_step": 469663, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.03214430809021, "global_step": 469664, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.074547529220581, "global_step": 469665, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.016700029373169, "global_step": 469666, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.056316614151001, "global_step": 469667, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.017841339111328, "global_step": 469668, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0433709621429443, "global_step": 469669, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9838776588439941, "global_step": 469670, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.070430278778076, "global_step": 469671, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.999673843383789, "global_step": 469672, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0553364753723145, "global_step": 469673, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0579922199249268, "global_step": 469674, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.005017042160034, "global_step": 469675, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9999867677688599, "global_step": 469676, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0783543586730957, "global_step": 469677, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1158599853515625, "global_step": 469678, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0207226276397705, "global_step": 469679, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.123324155807495, "global_step": 469680, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1424202919006348, "global_step": 469681, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.040444850921631, "global_step": 469682, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0947141647338867, "global_step": 469683, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0153040885925293, "global_step": 469684, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0487186908721924, "global_step": 469685, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.168628692626953, "global_step": 469686, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0037946701049805, "global_step": 469687, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9896732568740845, "global_step": 469688, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0003058910369873, "global_step": 469689, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.088865041732788, "global_step": 469690, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.082502841949463, "global_step": 469691, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0998849868774414, "global_step": 469692, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.027348279953003, "global_step": 469693, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.073141574859619, "global_step": 469694, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0970723628997803, "global_step": 469695, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1264712810516357, "global_step": 469696, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.079298257827759, "global_step": 469697, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.04486346244812, "global_step": 469698, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0762808322906494, "global_step": 469699, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0894131660461426, "global_step": 469700, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.974697470664978, "global_step": 469701, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1140644550323486, "global_step": 469702, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0611460208892822, "global_step": 469703, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1088693141937256, "global_step": 469704, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.114807605743408, "global_step": 469705, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0418012142181396, "global_step": 469706, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0899295806884766, "global_step": 469707, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1368677616119385, "global_step": 469708, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1234970092773438, "global_step": 469709, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0650155544281006, "global_step": 469710, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.063711404800415, "global_step": 469711, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0958669185638428, "global_step": 469712, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0942163467407227, "global_step": 469713, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0212786197662354, "global_step": 469714, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0929172039031982, "global_step": 469715, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.190347909927368, "global_step": 469716, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9282848834991455, "global_step": 469717, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0024988651275635, "global_step": 469718, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1082403659820557, "global_step": 469719, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0710670948028564, "global_step": 469720, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.043809175491333, "global_step": 469721, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.154831886291504, "global_step": 469722, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0710413455963135, "global_step": 469723, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0655105113983154, "global_step": 469724, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.090068817138672, "global_step": 469725, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0246880054473877, "global_step": 469726, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0536084175109863, "global_step": 469727, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0993740558624268, "global_step": 469728, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0796456336975098, "global_step": 469729, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1233062744140625, "global_step": 469730, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.066929578781128, "global_step": 469731, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0661227703094482, "global_step": 469732, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.019068717956543, "global_step": 469733, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9898279905319214, "global_step": 469734, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9545574188232422, "global_step": 469735, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.051644802093506, "global_step": 469736, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.10988712310791, "global_step": 469737, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1232855319976807, "global_step": 469738, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1017603874206543, "global_step": 469739, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.064906120300293, "global_step": 469740, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.07285475730896, "global_step": 469741, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1540238857269287, "global_step": 469742, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9670835733413696, "global_step": 469743, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0267560482025146, "global_step": 469744, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.059046983718872, "global_step": 469745, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0198681354522705, "global_step": 469746, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.059368848800659, "global_step": 469747, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.091961145401001, "global_step": 469748, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.063309669494629, "global_step": 469749, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1150193214416504, "global_step": 469750, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.106215238571167, "global_step": 469751, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.170469045639038, "global_step": 469752, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.136167287826538, "global_step": 469753, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.072016716003418, "global_step": 469754, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0600521564483643, "global_step": 469755, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.039355993270874, "global_step": 469756, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.112250566482544, "global_step": 469757, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0403871536254883, "global_step": 469758, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.054837942123413, "global_step": 469759, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.020963430404663, "global_step": 469760, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0208849906921387, "global_step": 469761, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0647478103637695, "global_step": 469762, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.091238498687744, "global_step": 469763, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0475659370422363, "global_step": 469764, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.138352155685425, "global_step": 469765, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0233378410339355, "global_step": 469766, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.14617657661438, "global_step": 469767, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1381750106811523, "global_step": 469768, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9708318710327148, "global_step": 469769, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0975124835968018, "global_step": 469770, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.085157632827759, "global_step": 469771, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0365140438079834, "global_step": 469772, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.042351245880127, "global_step": 469773, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.108292818069458, "global_step": 469774, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.089400291442871, "global_step": 469775, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.089224338531494, "global_step": 469776, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.157296657562256, "global_step": 469777, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0779693126678467, "global_step": 469778, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.059330463409424, "global_step": 469779, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.130404233932495, "global_step": 469780, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0114474296569824, "global_step": 469781, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9730859994888306, "global_step": 469782, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.141082525253296, "global_step": 469783, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.037121057510376, "global_step": 469784, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9727387428283691, "global_step": 469785, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1398253440856934, "global_step": 469786, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0624125003814697, "global_step": 469787, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0700833797454834, "global_step": 469788, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.103602886199951, "global_step": 469789, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0714664459228516, "global_step": 469790, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.036051034927368, "global_step": 469791, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.13456654548645, "global_step": 469792, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1318624019622803, "global_step": 469793, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1047799587249756, "global_step": 469794, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0626158714294434, "global_step": 469795, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.061678886413574, "global_step": 469796, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0335896015167236, "global_step": 469797, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0813307762145996, "global_step": 469798, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.027932643890381, "global_step": 469799, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.998562216758728, "global_step": 469800, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1234347820281982, "global_step": 469801, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0920822620391846, "global_step": 469802, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0395328998565674, "global_step": 469803, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.065614938735962, "global_step": 469804, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0087480545043945, "global_step": 469805, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0209896564483643, "global_step": 469806, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0278573036193848, "global_step": 469807, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.119222640991211, "global_step": 469808, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.054821014404297, "global_step": 469809, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0284059047698975, "global_step": 469810, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1215767860412598, "global_step": 469811, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9933794736862183, "global_step": 469812, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0899434089660645, "global_step": 469813, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.117065191268921, "global_step": 469814, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0549962520599365, "global_step": 469815, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.059572696685791, "global_step": 469816, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.078242301940918, "global_step": 469817, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0937628746032715, "global_step": 469818, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0782670974731445, "global_step": 469819, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9840171337127686, "global_step": 469820, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.981674313545227, "global_step": 469821, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9827022552490234, "global_step": 469822, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1041817665100098, "global_step": 469823, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.022979497909546, "global_step": 469824, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0686936378479004, "global_step": 469825, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.068145751953125, "global_step": 469826, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.035172939300537, "global_step": 469827, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0750842094421387, "global_step": 469828, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1070005893707275, "global_step": 469829, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.080778121948242, "global_step": 469830, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0551981925964355, "global_step": 469831, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0401408672332764, "global_step": 469832, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9959335327148438, "global_step": 469833, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0610768795013428, "global_step": 469834, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.100264072418213, "global_step": 469835, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.137287139892578, "global_step": 469836, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0711989402770996, "global_step": 469837, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1494531631469727, "global_step": 469838, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.039402723312378, "global_step": 469839, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.059659481048584, "global_step": 469840, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.092846155166626, "global_step": 469841, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0357019901275635, "global_step": 469842, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.036189556121826, "global_step": 469843, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1094934940338135, "global_step": 469844, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1072185039520264, "global_step": 469845, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1786348819732666, "global_step": 469846, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9754374027252197, "global_step": 469847, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.111237049102783, "global_step": 469848, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.070718288421631, "global_step": 469849, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.116121292114258, "global_step": 469850, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.016265869140625, "global_step": 469851, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.092552423477173, "global_step": 469852, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.008143186569214, "global_step": 469853, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1506292819976807, "global_step": 469854, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.12833309173584, "global_step": 469855, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0860180854797363, "global_step": 469856, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.034899950027466, "global_step": 469857, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.062608242034912, "global_step": 469858, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.016173839569092, "global_step": 469859, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.042194128036499, "global_step": 469860, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.075326442718506, "global_step": 469861, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0321576595306396, "global_step": 469862, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.990116000175476, "global_step": 469863, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9983564615249634, "global_step": 469864, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0027501583099365, "global_step": 469865, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0700595378875732, "global_step": 469866, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.073167085647583, "global_step": 469867, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.021038055419922, "global_step": 469868, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0295798778533936, "global_step": 469869, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.110748291015625, "global_step": 469870, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0550057888031006, "global_step": 469871, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0324935913085938, "global_step": 469872, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.084040880203247, "global_step": 469873, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0353429317474365, "global_step": 469874, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.034792184829712, "global_step": 469875, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.096776008605957, "global_step": 469876, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.100782871246338, "global_step": 469877, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0687429904937744, "global_step": 469878, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.107640504837036, "global_step": 469879, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0752835273742676, "global_step": 469880, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.087522506713867, "global_step": 469881, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9829773902893066, "global_step": 469882, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1397902965545654, "global_step": 469883, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.036802291870117, "global_step": 469884, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1788434982299805, "global_step": 469885, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.00579571723938, "global_step": 469886, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0365209579467773, "global_step": 469887, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0778965950012207, "global_step": 469888, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1513988971710205, "global_step": 469889, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.139188528060913, "global_step": 469890, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.022247552871704, "global_step": 469891, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1299257278442383, "global_step": 469892, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.099491596221924, "global_step": 469893, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0819175243377686, "global_step": 469894, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1207962036132812, "global_step": 469895, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1498186588287354, "global_step": 469896, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0958592891693115, "global_step": 469897, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9763919115066528, "global_step": 469898, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.07364821434021, "global_step": 469899, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.113454818725586, "global_step": 469900, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.082695722579956, "global_step": 469901, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0918326377868652, "global_step": 469902, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0542643070220947, "global_step": 469903, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9811971187591553, "global_step": 469904, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0710067749023438, "global_step": 469905, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.065936326980591, "global_step": 469906, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0641191005706787, "global_step": 469907, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0547094345092773, "global_step": 469908, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9891765117645264, "global_step": 469909, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1183815002441406, "global_step": 469910, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.095754861831665, "global_step": 469911, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1055173873901367, "global_step": 469912, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1326422691345215, "global_step": 469913, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0364458560943604, "global_step": 469914, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1182777881622314, "global_step": 469915, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0200493335723877, "global_step": 469916, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.050914764404297, "global_step": 469917, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1102757453918457, "global_step": 469918, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1051926612854004, "global_step": 469919, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0533742904663086, "global_step": 469920, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.046846866607666, "global_step": 469921, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0326075553894043, "global_step": 469922, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0351874828338623, "global_step": 469923, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1014745235443115, "global_step": 469924, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.083754062652588, "global_step": 469925, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0900697708129883, "global_step": 469926, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0980308055877686, "global_step": 469927, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0777339935302734, "global_step": 469928, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0588362216949463, "global_step": 469929, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1237542629241943, "global_step": 469930, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.135824680328369, "global_step": 469931, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0822784900665283, "global_step": 469932, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.067692756652832, "global_step": 469933, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1050493717193604, "global_step": 469934, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0583996772766113, "global_step": 469935, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.120506525039673, "global_step": 469936, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1115639209747314, "global_step": 469937, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1124606132507324, "global_step": 469938, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0734503269195557, "global_step": 469939, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0552845001220703, "global_step": 469940, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9676285982131958, "global_step": 469941, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0725550651550293, "global_step": 469942, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0429906845092773, "global_step": 469943, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.103745222091675, "global_step": 469944, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.140282154083252, "global_step": 469945, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0367178916931152, "global_step": 469946, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.020644187927246, "global_step": 469947, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0803182125091553, "global_step": 469948, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1061856746673584, "global_step": 469949, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.958042025566101, "global_step": 469950, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.03470778465271, "global_step": 469951, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0988807678222656, "global_step": 469952, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0777738094329834, "global_step": 469953, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.041754722595215, "global_step": 469954, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1482150554656982, "global_step": 469955, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9651676416397095, "global_step": 469956, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1011338233947754, "global_step": 469957, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0321736335754395, "global_step": 469958, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0726943016052246, "global_step": 469959, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.138921022415161, "global_step": 469960, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0695366859436035, "global_step": 469961, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.080505847930908, "global_step": 469962, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.065861940383911, "global_step": 469963, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1151046752929688, "global_step": 469964, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0469112396240234, "global_step": 469965, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.024996757507324, "global_step": 469966, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.046048641204834, "global_step": 469967, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.080181837081909, "global_step": 469968, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1622824668884277, "global_step": 469969, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.113290786743164, "global_step": 469970, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1057024002075195, "global_step": 469971, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1225101947784424, "global_step": 469972, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.086493492126465, "global_step": 469973, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.113203763961792, "global_step": 469974, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0773940086364746, "global_step": 469975, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0609192848205566, "global_step": 469976, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1317248344421387, "global_step": 469977, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.121264934539795, "global_step": 469978, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1337504386901855, "global_step": 469979, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.108469247817993, "global_step": 469980, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0549163818359375, "global_step": 469981, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0766561031341553, "global_step": 469982, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.107196807861328, "global_step": 469983, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.08368182182312, "global_step": 469984, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0549912452697754, "global_step": 469985, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9697777032852173, "global_step": 469986, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.166945695877075, "global_step": 469987, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0965075492858887, "global_step": 469988, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.045170545578003, "global_step": 469989, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0652873516082764, "global_step": 469990, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0701613426208496, "global_step": 469991, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.058990240097046, "global_step": 469992, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.034843921661377, "global_step": 469993, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.178546190261841, "global_step": 469994, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0363471508026123, "global_step": 469995, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0908203125, "global_step": 469996, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.080717086791992, "global_step": 469997, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.141010046005249, "global_step": 469998, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.100083589553833, "global_step": 469999, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0972280502319336, "global_step": 470000, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0848276615142822, "global_step": 470001, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1429200172424316, "global_step": 470002, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0325968265533447, "global_step": 470003, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1287288665771484, "global_step": 470004, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.015960216522217, "global_step": 470005, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0328733921051025, "global_step": 470006, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1184537410736084, "global_step": 470007, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0974597930908203, "global_step": 470008, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.2113521099090576, "global_step": 470009, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9880046844482422, "global_step": 470010, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.13765811920166, "global_step": 470011, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0548179149627686, "global_step": 470012, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1162853240966797, "global_step": 470013, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.086371660232544, "global_step": 470014, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0875022411346436, "global_step": 470015, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.027733087539673, "global_step": 470016, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.06156849861145, "global_step": 470017, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0823192596435547, "global_step": 470018, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1297712326049805, "global_step": 470019, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.076462507247925, "global_step": 470020, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.123734712600708, "global_step": 470021, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.079810619354248, "global_step": 470022, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0168511867523193, "global_step": 470023, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.073184013366699, "global_step": 470024, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0595855712890625, "global_step": 470025, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.068277359008789, "global_step": 470026, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0181005001068115, "global_step": 470027, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.02421498298645, "global_step": 470028, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0754499435424805, "global_step": 470029, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.092298984527588, "global_step": 470030, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0535528659820557, "global_step": 470031, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0845508575439453, "global_step": 470032, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.075239419937134, "global_step": 470033, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1093273162841797, "global_step": 470034, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0842645168304443, "global_step": 470035, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0906476974487305, "global_step": 470036, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1366703510284424, "global_step": 470037, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0338516235351562, "global_step": 470038, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.070319890975952, "global_step": 470039, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0239577293395996, "global_step": 470040, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0953657627105713, "global_step": 470041, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0502936840057373, "global_step": 470042, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.080416202545166, "global_step": 470043, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.01554274559021, "global_step": 470044, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.084439277648926, "global_step": 470045, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9948360919952393, "global_step": 470046, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1092848777770996, "global_step": 470047, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0686962604522705, "global_step": 470048, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0348732471466064, "global_step": 470049, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0532267093658447, "global_step": 470050, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0770559310913086, "global_step": 470051, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0532588958740234, "global_step": 470052, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0242016315460205, "global_step": 470053, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.965991735458374, "global_step": 470054, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0956149101257324, "global_step": 470055, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.124502182006836, "global_step": 470056, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9662169218063354, "global_step": 470057, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0797157287597656, "global_step": 470058, "epoch": 834, "lr": 5e-05}
{"train_loss": 1.9789762496948242, "global_step": 470059, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0541176795959473, "global_step": 470060, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.025207042694092, "global_step": 470061, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1508989334106445, "global_step": 470062, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0849111080169678, "global_step": 470063, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0202550888061523, "global_step": 470064, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.081862211227417, "global_step": 470065, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0802927017211914, "global_step": 470066, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1212775707244873, "global_step": 470067, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0932350158691406, "global_step": 470068, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.050306797027588, "global_step": 470069, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.080125331878662, "global_step": 470070, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0877363681793213, "global_step": 470071, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0771405696868896, "global_step": 470072, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1021904945373535, "global_step": 470073, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0798404216766357, "global_step": 470074, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.010385513305664, "global_step": 470075, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.082947254180908, "global_step": 470076, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0598642826080322, "global_step": 470077, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0664210319519043, "global_step": 470078, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.176149368286133, "global_step": 470079, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.077273368835449, "global_step": 470080, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1493871212005615, "global_step": 470081, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.087920665740967, "global_step": 470082, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1510329246520996, "global_step": 470083, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.028923511505127, "global_step": 470084, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0839829444885254, "global_step": 470085, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.087592840194702, "global_step": 470086, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0454375743865967, "global_step": 470087, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1402547359466553, "global_step": 470088, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1000630855560303, "global_step": 470089, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.077892541885376, "global_step": 470090, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.133392333984375, "global_step": 470091, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0374526977539062, "global_step": 470092, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.005950450897217, "global_step": 470093, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1206536293029785, "global_step": 470094, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0951075553894043, "global_step": 470095, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.0874102115631104, "global_step": 470096, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.064507246017456, "global_step": 470097, "epoch": 834, "lr": 5e-05}
{"train_loss": 2.1014716625213623, "global_step": 470098, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.067147731781006, "global_step": 470099, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.069800853729248, "global_step": 470100, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9339287281036377, "global_step": 470101, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1146979331970215, "global_step": 470102, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.145714521408081, "global_step": 470103, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0716042518615723, "global_step": 470104, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.015592098236084, "global_step": 470105, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.043858289718628, "global_step": 470106, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0286202430725098, "global_step": 470107, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.021240234375, "global_step": 470108, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.98162841796875, "global_step": 470109, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9925130605697632, "global_step": 470110, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1191697120666504, "global_step": 470111, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0832324028015137, "global_step": 470112, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.055846691131592, "global_step": 470113, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.041363477706909, "global_step": 470114, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0577147006988525, "global_step": 470115, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9726951122283936, "global_step": 470116, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.030797004699707, "global_step": 470117, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0958526134490967, "global_step": 470118, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9570869207382202, "global_step": 470119, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.083303213119507, "global_step": 470120, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.085679531097412, "global_step": 470121, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.073395013809204, "global_step": 470122, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.102334976196289, "global_step": 470123, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.942283034324646, "global_step": 470124, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.059206485748291, "global_step": 470125, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.017012119293213, "global_step": 470126, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0059797763824463, "global_step": 470127, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0746805667877197, "global_step": 470128, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0751760005950928, "global_step": 470129, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.014726161956787, "global_step": 470130, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0507655143737793, "global_step": 470131, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0691442489624023, "global_step": 470132, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0226950645446777, "global_step": 470133, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0195465087890625, "global_step": 470134, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.11122989654541, "global_step": 470135, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0795013904571533, "global_step": 470136, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.068150758743286, "global_step": 470137, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0447328090667725, "global_step": 470138, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.093999147415161, "global_step": 470139, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.111762523651123, "global_step": 470140, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9855324029922485, "global_step": 470141, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0225307941436768, "global_step": 470142, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9995110034942627, "global_step": 470143, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1070609092712402, "global_step": 470144, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0882492065429688, "global_step": 470145, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0358922481536865, "global_step": 470146, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.107583522796631, "global_step": 470147, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.040750741958618, "global_step": 470148, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0853006839752197, "global_step": 470149, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.089759349822998, "global_step": 470150, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.069248914718628, "global_step": 470151, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0514161586761475, "global_step": 470152, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0164012908935547, "global_step": 470153, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1561315059661865, "global_step": 470154, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0957329273223877, "global_step": 470155, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.959558367729187, "global_step": 470156, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.049633264541626, "global_step": 470157, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.109623432159424, "global_step": 470158, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1030690670013428, "global_step": 470159, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1326191425323486, "global_step": 470160, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0736067295074463, "global_step": 470161, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0828771591186523, "global_step": 470162, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.039957046508789, "global_step": 470163, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.124882698059082, "global_step": 470164, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0039236545562744, "global_step": 470165, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0497865676879883, "global_step": 470166, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0306544303894043, "global_step": 470167, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0341567993164062, "global_step": 470168, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0729286670684814, "global_step": 470169, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.074723482131958, "global_step": 470170, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.082507610321045, "global_step": 470171, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9338037967681885, "global_step": 470172, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9907090663909912, "global_step": 470173, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9793952703475952, "global_step": 470174, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0473527908325195, "global_step": 470175, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0828070640563965, "global_step": 470176, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.057133436203003, "global_step": 470177, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.99180269241333, "global_step": 470178, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0365664958953857, "global_step": 470179, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1296567916870117, "global_step": 470180, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1097373962402344, "global_step": 470181, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.008253812789917, "global_step": 470182, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.014897346496582, "global_step": 470183, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.941174030303955, "global_step": 470184, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0938878059387207, "global_step": 470185, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0372314453125, "global_step": 470186, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.079054832458496, "global_step": 470187, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0787758827209473, "global_step": 470188, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.989829421043396, "global_step": 470189, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0278892517089844, "global_step": 470190, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0757296085357666, "global_step": 470191, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.010283946990967, "global_step": 470192, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0376951694488525, "global_step": 470193, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.001666784286499, "global_step": 470194, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0859625339508057, "global_step": 470195, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0596888065338135, "global_step": 470196, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.064725875854492, "global_step": 470197, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0427541732788086, "global_step": 470198, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.032245635986328, "global_step": 470199, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1091325283050537, "global_step": 470200, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0610008239746094, "global_step": 470201, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0547242164611816, "global_step": 470202, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9792462587356567, "global_step": 470203, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0881431102752686, "global_step": 470204, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.124494791030884, "global_step": 470205, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0721004009246826, "global_step": 470206, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.049271821975708, "global_step": 470207, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0927348136901855, "global_step": 470208, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9804799556732178, "global_step": 470209, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9932974576950073, "global_step": 470210, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.079130172729492, "global_step": 470211, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.018845558166504, "global_step": 470212, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.095360040664673, "global_step": 470213, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.045510768890381, "global_step": 470214, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.083827495574951, "global_step": 470215, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.046201229095459, "global_step": 470216, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9307953119277954, "global_step": 470217, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0603106021881104, "global_step": 470218, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1119227409362793, "global_step": 470219, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9492369890213013, "global_step": 470220, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.071439743041992, "global_step": 470221, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.073086738586426, "global_step": 470222, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0735182762145996, "global_step": 470223, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0603957176208496, "global_step": 470224, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.082751750946045, "global_step": 470225, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9612295627593994, "global_step": 470226, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.198380947113037, "global_step": 470227, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0591392517089844, "global_step": 470228, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0846242904663086, "global_step": 470229, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0425572395324707, "global_step": 470230, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.044668436050415, "global_step": 470231, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1159727573394775, "global_step": 470232, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.029873847961426, "global_step": 470233, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9991217851638794, "global_step": 470234, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9840229749679565, "global_step": 470235, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0686047077178955, "global_step": 470236, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0239789485931396, "global_step": 470237, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1045026779174805, "global_step": 470238, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0162720680236816, "global_step": 470239, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0470755100250244, "global_step": 470240, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.142411470413208, "global_step": 470241, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0266880989074707, "global_step": 470242, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0443975925445557, "global_step": 470243, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.047619581222534, "global_step": 470244, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.073064088821411, "global_step": 470245, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0413870811462402, "global_step": 470246, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0583770275115967, "global_step": 470247, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0107696056365967, "global_step": 470248, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0998871326446533, "global_step": 470249, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.048541307449341, "global_step": 470250, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.191758871078491, "global_step": 470251, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0058038234710693, "global_step": 470252, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.990303635597229, "global_step": 470253, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.009936809539795, "global_step": 470254, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.059176206588745, "global_step": 470255, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0415964126586914, "global_step": 470256, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0479350090026855, "global_step": 470257, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.124790906906128, "global_step": 470258, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1187775135040283, "global_step": 470259, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0927999019622803, "global_step": 470260, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0527167320251465, "global_step": 470261, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.01373553276062, "global_step": 470262, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1081221103668213, "global_step": 470263, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0455162525177, "global_step": 470264, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0691723823547363, "global_step": 470265, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0344200134277344, "global_step": 470266, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.8796497583389282, "global_step": 470267, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.019465208053589, "global_step": 470268, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.002356767654419, "global_step": 470269, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0583324432373047, "global_step": 470270, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.152043581008911, "global_step": 470271, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0401530265808105, "global_step": 470272, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1233248710632324, "global_step": 470273, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9569114446640015, "global_step": 470274, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0888917446136475, "global_step": 470275, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0386784076690674, "global_step": 470276, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0987930297851562, "global_step": 470277, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9867315292358398, "global_step": 470278, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0410664081573486, "global_step": 470279, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0859596729278564, "global_step": 470280, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9938548803329468, "global_step": 470281, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9680099487304688, "global_step": 470282, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.050328493118286, "global_step": 470283, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0899245738983154, "global_step": 470284, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.955446720123291, "global_step": 470285, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0459251403808594, "global_step": 470286, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1405975818634033, "global_step": 470287, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.021794557571411, "global_step": 470288, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0442895889282227, "global_step": 470289, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.057772159576416, "global_step": 470290, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.071589946746826, "global_step": 470291, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0811641216278076, "global_step": 470292, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.050539016723633, "global_step": 470293, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0875329971313477, "global_step": 470294, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1798245906829834, "global_step": 470295, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9831500053405762, "global_step": 470296, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0425004959106445, "global_step": 470297, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0458664894104004, "global_step": 470298, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1165719032287598, "global_step": 470299, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0645737648010254, "global_step": 470300, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0153205394744873, "global_step": 470301, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0088720321655273, "global_step": 470302, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0864033699035645, "global_step": 470303, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9977021217346191, "global_step": 470304, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0919950008392334, "global_step": 470305, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.004521608352661, "global_step": 470306, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.014557123184204, "global_step": 470307, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.078467607498169, "global_step": 470308, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.105982542037964, "global_step": 470309, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.081925630569458, "global_step": 470310, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.06990385055542, "global_step": 470311, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9957289695739746, "global_step": 470312, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0833518505096436, "global_step": 470313, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0422170162200928, "global_step": 470314, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0293495655059814, "global_step": 470315, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0705838203430176, "global_step": 470316, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0125784873962402, "global_step": 470317, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0633928775787354, "global_step": 470318, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0529158115386963, "global_step": 470319, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0878958702087402, "global_step": 470320, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0891377925872803, "global_step": 470321, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0444555282592773, "global_step": 470322, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.066263437271118, "global_step": 470323, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.998896598815918, "global_step": 470324, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.039005994796753, "global_step": 470325, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.028334617614746, "global_step": 470326, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0998659133911133, "global_step": 470327, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1048696041107178, "global_step": 470328, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.139536142349243, "global_step": 470329, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.096339464187622, "global_step": 470330, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.062839984893799, "global_step": 470331, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.015225887298584, "global_step": 470332, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.996775507926941, "global_step": 470333, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1087143421173096, "global_step": 470334, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0744996070861816, "global_step": 470335, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9955012798309326, "global_step": 470336, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.054213762283325, "global_step": 470337, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0723512172698975, "global_step": 470338, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0321030616760254, "global_step": 470339, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0991265773773193, "global_step": 470340, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.110004186630249, "global_step": 470341, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0109190940856934, "global_step": 470342, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.080655336380005, "global_step": 470343, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0591166019439697, "global_step": 470344, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1065895557403564, "global_step": 470345, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.154629945755005, "global_step": 470346, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.043483018875122, "global_step": 470347, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9691076278686523, "global_step": 470348, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.031832218170166, "global_step": 470349, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.032109022140503, "global_step": 470350, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0015904903411865, "global_step": 470351, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0148675441741943, "global_step": 470352, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1020708084106445, "global_step": 470353, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.03554630279541, "global_step": 470354, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9960635900497437, "global_step": 470355, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.007239580154419, "global_step": 470356, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9931424856185913, "global_step": 470357, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.037736415863037, "global_step": 470358, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0921897888183594, "global_step": 470359, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0283679962158203, "global_step": 470360, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.06170392036438, "global_step": 470361, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.070916175842285, "global_step": 470362, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0598950386047363, "global_step": 470363, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9496173858642578, "global_step": 470364, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1145453453063965, "global_step": 470365, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.091688632965088, "global_step": 470366, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0356545448303223, "global_step": 470367, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0243024826049805, "global_step": 470368, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.012070894241333, "global_step": 470369, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.054344415664673, "global_step": 470370, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0710554122924805, "global_step": 470371, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0936577320098877, "global_step": 470372, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0504395961761475, "global_step": 470373, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.07891845703125, "global_step": 470374, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.107907295227051, "global_step": 470375, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1503891944885254, "global_step": 470376, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0078935623168945, "global_step": 470377, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0664751529693604, "global_step": 470378, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9830358028411865, "global_step": 470379, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0329465866088867, "global_step": 470380, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1231398582458496, "global_step": 470381, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.047799825668335, "global_step": 470382, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1350388526916504, "global_step": 470383, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.023210287094116, "global_step": 470384, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.148582935333252, "global_step": 470385, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.087115526199341, "global_step": 470386, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.045785903930664, "global_step": 470387, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0535776615142822, "global_step": 470388, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.040829658508301, "global_step": 470389, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1263859272003174, "global_step": 470390, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0281612873077393, "global_step": 470391, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0242080688476562, "global_step": 470392, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.020617961883545, "global_step": 470393, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.039271831512451, "global_step": 470394, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0791258811950684, "global_step": 470395, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.064115285873413, "global_step": 470396, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0511417388916016, "global_step": 470397, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0615193843841553, "global_step": 470398, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9805915355682373, "global_step": 470399, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.126147508621216, "global_step": 470400, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.032963514328003, "global_step": 470401, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.056696653366089, "global_step": 470402, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.022937774658203, "global_step": 470403, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1196069717407227, "global_step": 470404, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.057675838470459, "global_step": 470405, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9525175094604492, "global_step": 470406, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.085019588470459, "global_step": 470407, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.107883930206299, "global_step": 470408, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0386948585510254, "global_step": 470409, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0740692615509033, "global_step": 470410, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0221989154815674, "global_step": 470411, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1552767753601074, "global_step": 470412, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0828094482421875, "global_step": 470413, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0269429683685303, "global_step": 470414, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1005196571350098, "global_step": 470415, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0685272216796875, "global_step": 470416, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.086042642593384, "global_step": 470417, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.983255386352539, "global_step": 470418, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1094863414764404, "global_step": 470419, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0906271934509277, "global_step": 470420, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.107494354248047, "global_step": 470421, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.069797992706299, "global_step": 470422, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0548179149627686, "global_step": 470423, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0260884761810303, "global_step": 470424, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.18717360496521, "global_step": 470425, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1057307720184326, "global_step": 470426, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.13027286529541, "global_step": 470427, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0271236896514893, "global_step": 470428, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0653536319732666, "global_step": 470429, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.05570125579834, "global_step": 470430, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.116638422012329, "global_step": 470431, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1298022270202637, "global_step": 470432, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0701253414154053, "global_step": 470433, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1524524688720703, "global_step": 470434, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9956252574920654, "global_step": 470435, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1053903102874756, "global_step": 470436, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0869367122650146, "global_step": 470437, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0573525428771973, "global_step": 470438, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0143375396728516, "global_step": 470439, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.016279935836792, "global_step": 470440, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0190179347991943, "global_step": 470441, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.977154016494751, "global_step": 470442, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.039065361022949, "global_step": 470443, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9708077907562256, "global_step": 470444, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.124788284301758, "global_step": 470445, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.043117046356201, "global_step": 470446, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.139526605606079, "global_step": 470447, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.065694570541382, "global_step": 470448, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.068202257156372, "global_step": 470449, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0571606159210205, "global_step": 470450, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.063106060028076, "global_step": 470451, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.031111717224121, "global_step": 470452, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0688116550445557, "global_step": 470453, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0680887699127197, "global_step": 470454, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.968692660331726, "global_step": 470455, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.019970655441284, "global_step": 470456, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.139864206314087, "global_step": 470457, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.03275990486145, "global_step": 470458, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.118786334991455, "global_step": 470459, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1154699325561523, "global_step": 470460, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0098378658294678, "global_step": 470461, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0589542388916016, "global_step": 470462, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0586607456207275, "global_step": 470463, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1200222969055176, "global_step": 470464, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0142176151275635, "global_step": 470465, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1156530380249023, "global_step": 470466, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.026991844177246, "global_step": 470467, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.090125799179077, "global_step": 470468, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.2004287242889404, "global_step": 470469, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0739901065826416, "global_step": 470470, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.076350450515747, "global_step": 470471, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.082986831665039, "global_step": 470472, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0440752506256104, "global_step": 470473, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.003359794616699, "global_step": 470474, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0388269424438477, "global_step": 470475, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0387611389160156, "global_step": 470476, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.064420461654663, "global_step": 470477, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.108517646789551, "global_step": 470478, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0711560249328613, "global_step": 470479, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0817501544952393, "global_step": 470480, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1097054481506348, "global_step": 470481, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0037786960601807, "global_step": 470482, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1661932468414307, "global_step": 470483, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.103426694869995, "global_step": 470484, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1420609951019287, "global_step": 470485, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.031049966812134, "global_step": 470486, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0759243965148926, "global_step": 470487, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.119434118270874, "global_step": 470488, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.077361822128296, "global_step": 470489, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1128318309783936, "global_step": 470490, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0954554080963135, "global_step": 470491, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.999715805053711, "global_step": 470492, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.06251859664917, "global_step": 470493, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.050048351287842, "global_step": 470494, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1030712127685547, "global_step": 470495, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.033895969390869, "global_step": 470496, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.075395345687866, "global_step": 470497, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.132537603378296, "global_step": 470498, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9654817581176758, "global_step": 470499, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9829405546188354, "global_step": 470500, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9678486585617065, "global_step": 470501, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1046719551086426, "global_step": 470502, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1024272441864014, "global_step": 470503, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1815433502197266, "global_step": 470504, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0413243770599365, "global_step": 470505, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.156848669052124, "global_step": 470506, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.101628065109253, "global_step": 470507, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0603225231170654, "global_step": 470508, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.040329933166504, "global_step": 470509, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.101304531097412, "global_step": 470510, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.057888984680176, "global_step": 470511, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1241934299468994, "global_step": 470512, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.01273775100708, "global_step": 470513, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1262664794921875, "global_step": 470514, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0307772159576416, "global_step": 470515, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1268134117126465, "global_step": 470516, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1027462482452393, "global_step": 470517, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1140661239624023, "global_step": 470518, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0818445682525635, "global_step": 470519, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1427414417266846, "global_step": 470520, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1550254821777344, "global_step": 470521, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0495290756225586, "global_step": 470522, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1085376739501953, "global_step": 470523, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.033961057662964, "global_step": 470524, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0940380096435547, "global_step": 470525, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1373510360717773, "global_step": 470526, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0982720851898193, "global_step": 470527, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0562186241149902, "global_step": 470528, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0813112258911133, "global_step": 470529, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1538760662078857, "global_step": 470530, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.038769483566284, "global_step": 470531, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1176419258117676, "global_step": 470532, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0978662967681885, "global_step": 470533, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0172672271728516, "global_step": 470534, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0416648387908936, "global_step": 470535, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0383925437927246, "global_step": 470536, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1130805015563965, "global_step": 470537, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.093496799468994, "global_step": 470538, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0750935077667236, "global_step": 470539, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9683712720870972, "global_step": 470540, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.081740140914917, "global_step": 470541, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0860023498535156, "global_step": 470542, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9767462015151978, "global_step": 470543, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.073587417602539, "global_step": 470544, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1494829654693604, "global_step": 470545, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.066026210784912, "global_step": 470546, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.037628412246704, "global_step": 470547, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.107422113418579, "global_step": 470548, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.977663278579712, "global_step": 470549, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.102226495742798, "global_step": 470550, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0752556324005127, "global_step": 470551, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.069214344024658, "global_step": 470552, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0175230503082275, "global_step": 470553, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1238391399383545, "global_step": 470554, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0563390254974365, "global_step": 470555, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0496206283569336, "global_step": 470556, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0772173404693604, "global_step": 470557, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0550637245178223, "global_step": 470558, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9341092109680176, "global_step": 470559, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0544886589050293, "global_step": 470560, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.155712604522705, "global_step": 470561, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.123257875442505, "global_step": 470562, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.083010196685791, "global_step": 470563, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0536437034606934, "global_step": 470564, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0899691581726074, "global_step": 470565, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.033174753189087, "global_step": 470566, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1577491760253906, "global_step": 470567, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.087069272994995, "global_step": 470568, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.097578525543213, "global_step": 470569, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1049437522888184, "global_step": 470570, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0288355350494385, "global_step": 470571, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0127501487731934, "global_step": 470572, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1010968685150146, "global_step": 470573, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1666393280029297, "global_step": 470574, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.027125597000122, "global_step": 470575, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.063204765319824, "global_step": 470576, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0494885444641113, "global_step": 470577, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9981074333190918, "global_step": 470578, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.016512393951416, "global_step": 470579, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0807275772094727, "global_step": 470580, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0656323432922363, "global_step": 470581, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0074121952056885, "global_step": 470582, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.116079092025757, "global_step": 470583, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.07928204536438, "global_step": 470584, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0371577739715576, "global_step": 470585, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0021708011627197, "global_step": 470586, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.146172285079956, "global_step": 470587, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0503439903259277, "global_step": 470588, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.033463716506958, "global_step": 470589, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0504868030548096, "global_step": 470590, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.069709062576294, "global_step": 470591, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.074263095855713, "global_step": 470592, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9891010522842407, "global_step": 470593, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9773974418640137, "global_step": 470594, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0359480381011963, "global_step": 470595, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.000854969024658, "global_step": 470596, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.155670642852783, "global_step": 470597, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1004536151885986, "global_step": 470598, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0108606815338135, "global_step": 470599, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.046755313873291, "global_step": 470600, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.079218626022339, "global_step": 470601, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.036184072494507, "global_step": 470602, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.037034034729004, "global_step": 470603, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.175360679626465, "global_step": 470604, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0978267192840576, "global_step": 470605, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.104951858520508, "global_step": 470606, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.064748525619507, "global_step": 470607, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.088022470474243, "global_step": 470608, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0324201583862305, "global_step": 470609, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0918056964874268, "global_step": 470610, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9588825702667236, "global_step": 470611, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.024977207183838, "global_step": 470612, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.132455587387085, "global_step": 470613, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0387189388275146, "global_step": 470614, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0938899517059326, "global_step": 470615, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0239651203155518, "global_step": 470616, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1430516242980957, "global_step": 470617, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.077538251876831, "global_step": 470618, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.062587022781372, "global_step": 470619, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9733365774154663, "global_step": 470620, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.070110321044922, "global_step": 470621, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0530989170074463, "global_step": 470622, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0608818531036377, "global_step": 470623, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1591153144836426, "global_step": 470624, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.063364267349243, "global_step": 470625, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.05037260055542, "global_step": 470626, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.048048257827759, "global_step": 470627, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.111933469772339, "global_step": 470628, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1368215084075928, "global_step": 470629, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0138070583343506, "global_step": 470630, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0593955516815186, "global_step": 470631, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.120664596557617, "global_step": 470632, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1669254302978516, "global_step": 470633, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0560414791107178, "global_step": 470634, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0545740127563477, "global_step": 470635, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.118112564086914, "global_step": 470636, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9599529504776, "global_step": 470637, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.163191795349121, "global_step": 470638, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.138395309448242, "global_step": 470639, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0697202682495117, "global_step": 470640, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.162968873977661, "global_step": 470641, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1328039169311523, "global_step": 470642, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.029963493347168, "global_step": 470643, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.116274118423462, "global_step": 470644, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.022778034210205, "global_step": 470645, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9883646965026855, "global_step": 470646, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0556623935699463, "global_step": 470647, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.163217306137085, "global_step": 470648, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0405807495117188, "global_step": 470649, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1188910007476807, "global_step": 470650, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.128728151321411, "global_step": 470651, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.064138412475586, "global_step": 470652, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.996634602546692, "global_step": 470653, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1067981719970703, "global_step": 470654, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.164017677307129, "global_step": 470655, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1050009727478027, "global_step": 470656, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0206403732299805, "global_step": 470657, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0607783794403076, "global_step": 470658, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1093733310699463, "global_step": 470659, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.019364833831787, "global_step": 470660, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0601227283477783, "global_step": 470661, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.004952907562256, "global_step": 470662, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9932373762130737, "global_step": 470663, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9894057512283325, "global_step": 470664, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0866191387176514, "global_step": 470665, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.046579599380493, "global_step": 470666, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1325910091400146, "global_step": 470667, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0739283561706543, "global_step": 470668, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0340495109558105, "global_step": 470669, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1346988677978516, "global_step": 470670, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.039781093597412, "global_step": 470671, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.046588659286499, "global_step": 470672, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0794827938079834, "global_step": 470673, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.063868761062622, "global_step": 470674, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0625643730163574, "global_step": 470675, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.053709030151367, "global_step": 470676, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0878143310546875, "global_step": 470677, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.03324031829834, "global_step": 470678, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0217819213867188, "global_step": 470679, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.040065288543701, "global_step": 470680, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0657315254211426, "global_step": 470681, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0669188499450684, "global_step": 470682, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.054267168045044, "global_step": 470683, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0406384468078613, "global_step": 470684, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.00960636138916, "global_step": 470685, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.040518283843994, "global_step": 470686, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0883803367614746, "global_step": 470687, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0800466537475586, "global_step": 470688, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.022962808609009, "global_step": 470689, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.151170015335083, "global_step": 470690, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.093322515487671, "global_step": 470691, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0416905879974365, "global_step": 470692, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0622246265411377, "global_step": 470693, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.086641788482666, "global_step": 470694, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0767030715942383, "global_step": 470695, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9503684043884277, "global_step": 470696, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.113870143890381, "global_step": 470697, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1540238857269287, "global_step": 470698, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0962510108947754, "global_step": 470699, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1540825366973877, "global_step": 470700, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0193512439727783, "global_step": 470701, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.010838747024536, "global_step": 470702, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.070233106613159, "global_step": 470703, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.091171979904175, "global_step": 470704, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.986560344696045, "global_step": 470705, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.043849229812622, "global_step": 470706, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.111982583999634, "global_step": 470707, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.062366485595703, "global_step": 470708, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0212037563323975, "global_step": 470709, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.068164348602295, "global_step": 470710, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.070012092590332, "global_step": 470711, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.047819137573242, "global_step": 470712, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1249310970306396, "global_step": 470713, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0809342861175537, "global_step": 470714, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.132009506225586, "global_step": 470715, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0498576164245605, "global_step": 470716, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9905916452407837, "global_step": 470717, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.064967632293701, "global_step": 470718, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1317059993743896, "global_step": 470719, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.990298867225647, "global_step": 470720, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.079590082168579, "global_step": 470721, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.04876708984375, "global_step": 470722, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.126276969909668, "global_step": 470723, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.072847366333008, "global_step": 470724, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1119613647460938, "global_step": 470725, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1607677936553955, "global_step": 470726, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.06611704826355, "global_step": 470727, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0620222091674805, "global_step": 470728, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1364247798919678, "global_step": 470729, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0137767791748047, "global_step": 470730, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0555012226104736, "global_step": 470731, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0479116439819336, "global_step": 470732, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.079625368118286, "global_step": 470733, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.053828001022339, "global_step": 470734, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.047434091567993, "global_step": 470735, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.151353120803833, "global_step": 470736, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9733514785766602, "global_step": 470737, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.054945945739746, "global_step": 470738, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1943647861480713, "global_step": 470739, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0344560146331787, "global_step": 470740, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.081082344055176, "global_step": 470741, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.044613838195801, "global_step": 470742, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.091480255126953, "global_step": 470743, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0494606494903564, "global_step": 470744, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.010218381881714, "global_step": 470745, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.104112386703491, "global_step": 470746, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1280136108398438, "global_step": 470747, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0812580585479736, "global_step": 470748, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.057901382446289, "global_step": 470749, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0774924755096436, "global_step": 470750, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.202742099761963, "global_step": 470751, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0585803985595703, "global_step": 470752, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0575571060180664, "global_step": 470753, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.022216796875, "global_step": 470754, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1208112239837646, "global_step": 470755, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.002152442932129, "global_step": 470756, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.123946189880371, "global_step": 470757, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.094583511352539, "global_step": 470758, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0574467182159424, "global_step": 470759, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.8914713859558105, "global_step": 470760, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1302988529205322, "global_step": 470761, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.041250467300415, "global_step": 470762, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0732643604278564, "global_step": 470763, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0200700759887695, "global_step": 470764, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.098771095275879, "global_step": 470765, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.016453266143799, "global_step": 470766, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1025424003601074, "global_step": 470767, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.099280595779419, "global_step": 470768, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.065598964691162, "global_step": 470769, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1001555919647217, "global_step": 470770, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.048900842666626, "global_step": 470771, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.064755439758301, "global_step": 470772, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9887151718139648, "global_step": 470773, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.048036813735962, "global_step": 470774, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0731890201568604, "global_step": 470775, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0213232040405273, "global_step": 470776, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1240134239196777, "global_step": 470777, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0327248573303223, "global_step": 470778, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0458762645721436, "global_step": 470779, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.07820463180542, "global_step": 470780, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0343258380889893, "global_step": 470781, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0871095657348633, "global_step": 470782, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0941240787506104, "global_step": 470783, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0547053813934326, "global_step": 470784, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.042736768722534, "global_step": 470785, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.083209753036499, "global_step": 470786, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0196824073791504, "global_step": 470787, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0415456295013428, "global_step": 470788, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0952351093292236, "global_step": 470789, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.012057065963745, "global_step": 470790, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1033456325531006, "global_step": 470791, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1258668899536133, "global_step": 470792, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.027238368988037, "global_step": 470793, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0642106533050537, "global_step": 470794, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.147406816482544, "global_step": 470795, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.074842929840088, "global_step": 470796, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1239728927612305, "global_step": 470797, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0610597133636475, "global_step": 470798, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0553476810455322, "global_step": 470799, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0514395236968994, "global_step": 470800, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.103304624557495, "global_step": 470801, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0835232734680176, "global_step": 470802, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1521623134613037, "global_step": 470803, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0760843753814697, "global_step": 470804, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0737760066986084, "global_step": 470805, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.035742998123169, "global_step": 470806, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.08782696723938, "global_step": 470807, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.082989454269409, "global_step": 470808, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0564517974853516, "global_step": 470809, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1403818130493164, "global_step": 470810, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0430116653442383, "global_step": 470811, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0673584938049316, "global_step": 470812, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.016310691833496, "global_step": 470813, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.069800615310669, "global_step": 470814, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0964772701263428, "global_step": 470815, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0720274448394775, "global_step": 470816, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0088939666748047, "global_step": 470817, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.01068377494812, "global_step": 470818, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0750534534454346, "global_step": 470819, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0962672233581543, "global_step": 470820, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0234215259552, "global_step": 470821, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9886354207992554, "global_step": 470822, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.143638849258423, "global_step": 470823, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0303444862365723, "global_step": 470824, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0459277629852295, "global_step": 470825, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9737627506256104, "global_step": 470826, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9909228086471558, "global_step": 470827, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0391147136688232, "global_step": 470828, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.104182720184326, "global_step": 470829, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.121715784072876, "global_step": 470830, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9547183513641357, "global_step": 470831, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0947141647338867, "global_step": 470832, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0744690895080566, "global_step": 470833, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0668559074401855, "global_step": 470834, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0180914402008057, "global_step": 470835, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.033787250518799, "global_step": 470836, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.088564395904541, "global_step": 470837, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.053560495376587, "global_step": 470838, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9818012714385986, "global_step": 470839, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.078099250793457, "global_step": 470840, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.071927070617676, "global_step": 470841, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9587616920471191, "global_step": 470842, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0842444896698, "global_step": 470843, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.063974142074585, "global_step": 470844, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.092313766479492, "global_step": 470845, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1140782833099365, "global_step": 470846, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0335047245025635, "global_step": 470847, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0015077590942383, "global_step": 470848, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.11873722076416, "global_step": 470849, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0211808681488037, "global_step": 470850, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9603129625320435, "global_step": 470851, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.102159261703491, "global_step": 470852, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9727139472961426, "global_step": 470853, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.015310525894165, "global_step": 470854, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1810123920440674, "global_step": 470855, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0501625537872314, "global_step": 470856, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0873453617095947, "global_step": 470857, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.047063112258911, "global_step": 470858, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.110907793045044, "global_step": 470859, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.041102886199951, "global_step": 470860, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9945907592773438, "global_step": 470861, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0694806575775146, "global_step": 470862, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0811312198638916, "global_step": 470863, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0891504287719727, "global_step": 470864, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0739686489105225, "global_step": 470865, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.08213472366333, "global_step": 470866, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0962331295013428, "global_step": 470867, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.14815616607666, "global_step": 470868, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1227834224700928, "global_step": 470869, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.093095541000366, "global_step": 470870, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0160300731658936, "global_step": 470871, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0649006366729736, "global_step": 470872, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0322937965393066, "global_step": 470873, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0835065841674805, "global_step": 470874, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.022935390472412, "global_step": 470875, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9750646352767944, "global_step": 470876, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1272377967834473, "global_step": 470877, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9936554431915283, "global_step": 470878, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.035837411880493, "global_step": 470879, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.03950572013855, "global_step": 470880, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.136291742324829, "global_step": 470881, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0743627548217773, "global_step": 470882, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9882526397705078, "global_step": 470883, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0179412364959717, "global_step": 470884, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0902152061462402, "global_step": 470885, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.12489652633667, "global_step": 470886, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.093242883682251, "global_step": 470887, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0893290042877197, "global_step": 470888, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.033093214035034, "global_step": 470889, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.043792963027954, "global_step": 470890, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0583677291870117, "global_step": 470891, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1241321563720703, "global_step": 470892, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.127716064453125, "global_step": 470893, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0599560737609863, "global_step": 470894, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.099968433380127, "global_step": 470895, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9931187629699707, "global_step": 470896, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0889859199523926, "global_step": 470897, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0489180088043213, "global_step": 470898, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.037112236022949, "global_step": 470899, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0838119983673096, "global_step": 470900, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.058866500854492, "global_step": 470901, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9809750318527222, "global_step": 470902, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9864659309387207, "global_step": 470903, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9922521114349365, "global_step": 470904, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0916059017181396, "global_step": 470905, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1076226234436035, "global_step": 470906, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.085939407348633, "global_step": 470907, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.149437189102173, "global_step": 470908, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.01567006111145, "global_step": 470909, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.10050630569458, "global_step": 470910, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0011494159698486, "global_step": 470911, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.146261215209961, "global_step": 470912, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.090587615966797, "global_step": 470913, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.111950159072876, "global_step": 470914, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9844341278076172, "global_step": 470915, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1265950202941895, "global_step": 470916, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.111713409423828, "global_step": 470917, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1259219646453857, "global_step": 470918, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0472233295440674, "global_step": 470919, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9999982118606567, "global_step": 470920, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.160747766494751, "global_step": 470921, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.057450771331787, "global_step": 470922, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.001120090484619, "global_step": 470923, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.067354679107666, "global_step": 470924, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.019484043121338, "global_step": 470925, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0409996509552, "global_step": 470926, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.041590690612793, "global_step": 470927, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1516098976135254, "global_step": 470928, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.122114896774292, "global_step": 470929, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1003010272979736, "global_step": 470930, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9779374599456787, "global_step": 470931, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.171327829360962, "global_step": 470932, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0848629474639893, "global_step": 470933, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0863895416259766, "global_step": 470934, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0180201530456543, "global_step": 470935, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0538675785064697, "global_step": 470936, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.107823133468628, "global_step": 470937, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1321322917938232, "global_step": 470938, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0114474296569824, "global_step": 470939, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1213512420654297, "global_step": 470940, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9701493978500366, "global_step": 470941, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.043667793273926, "global_step": 470942, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9790935516357422, "global_step": 470943, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0471010208129883, "global_step": 470944, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.106353998184204, "global_step": 470945, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.118335247039795, "global_step": 470946, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0352866649627686, "global_step": 470947, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0989110469818115, "global_step": 470948, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0920069217681885, "global_step": 470949, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1667373180389404, "global_step": 470950, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.110856294631958, "global_step": 470951, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.052736282348633, "global_step": 470952, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.141679286956787, "global_step": 470953, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1150400638580322, "global_step": 470954, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.108074188232422, "global_step": 470955, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0640921592712402, "global_step": 470956, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.101766586303711, "global_step": 470957, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1212642192840576, "global_step": 470958, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0839996337890625, "global_step": 470959, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9759377241134644, "global_step": 470960, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9946221113204956, "global_step": 470961, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.131995916366577, "global_step": 470962, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.018831968307495, "global_step": 470963, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9484432935714722, "global_step": 470964, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0452568531036377, "global_step": 470965, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0498344898223877, "global_step": 470966, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.2166452407836914, "global_step": 470967, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0520706176757812, "global_step": 470968, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1399998664855957, "global_step": 470969, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1005682945251465, "global_step": 470970, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0655806064605713, "global_step": 470971, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0189692974090576, "global_step": 470972, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1306495666503906, "global_step": 470973, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.065159320831299, "global_step": 470974, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0186588764190674, "global_step": 470975, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0677623748779297, "global_step": 470976, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.049165725708008, "global_step": 470977, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0782558917999268, "global_step": 470978, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1032400131225586, "global_step": 470979, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0024280548095703, "global_step": 470980, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.096256971359253, "global_step": 470981, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0095345973968506, "global_step": 470982, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0879626274108887, "global_step": 470983, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0616118907928467, "global_step": 470984, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0381650924682617, "global_step": 470985, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1255359649658203, "global_step": 470986, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1188175678253174, "global_step": 470987, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0139613151550293, "global_step": 470988, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.975928544998169, "global_step": 470989, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0541393756866455, "global_step": 470990, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1189072132110596, "global_step": 470991, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.090993881225586, "global_step": 470992, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1333906650543213, "global_step": 470993, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0505590438842773, "global_step": 470994, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0305497646331787, "global_step": 470995, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.029932737350464, "global_step": 470996, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9685477018356323, "global_step": 470997, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.2090911865234375, "global_step": 470998, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.106943368911743, "global_step": 470999, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.917667031288147, "global_step": 471000, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0357038974761963, "global_step": 471001, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0492453575134277, "global_step": 471002, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.018008232116699, "global_step": 471003, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.113461494445801, "global_step": 471004, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1226465702056885, "global_step": 471005, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0170326232910156, "global_step": 471006, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.047877550125122, "global_step": 471007, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0461227893829346, "global_step": 471008, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.06931209564209, "global_step": 471009, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9999955892562866, "global_step": 471010, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.03505539894104, "global_step": 471011, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.029421329498291, "global_step": 471012, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0581014156341553, "global_step": 471013, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1031875610351562, "global_step": 471014, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1052799224853516, "global_step": 471015, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0707826614379883, "global_step": 471016, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.170571804046631, "global_step": 471017, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9897629022598267, "global_step": 471018, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.089109182357788, "global_step": 471019, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.137455701828003, "global_step": 471020, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9596365690231323, "global_step": 471021, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0072126388549805, "global_step": 471022, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.020897150039673, "global_step": 471023, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.004091262817383, "global_step": 471024, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0237324237823486, "global_step": 471025, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.056835889816284, "global_step": 471026, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9685707092285156, "global_step": 471027, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.011651039123535, "global_step": 471028, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.037768602371216, "global_step": 471029, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1181447505950928, "global_step": 471030, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.013434410095215, "global_step": 471031, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.084892988204956, "global_step": 471032, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0658819675445557, "global_step": 471033, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.014479398727417, "global_step": 471034, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0111401081085205, "global_step": 471035, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0305211544036865, "global_step": 471036, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.127531051635742, "global_step": 471037, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.007538080215454, "global_step": 471038, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0474581718444824, "global_step": 471039, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0545413494110107, "global_step": 471040, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.09849214553833, "global_step": 471041, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0525736808776855, "global_step": 471042, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.069413661956787, "global_step": 471043, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.075603723526001, "global_step": 471044, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.101228713989258, "global_step": 471045, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0616564750671387, "global_step": 471046, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.075996160507202, "global_step": 471047, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0893869400024414, "global_step": 471048, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.034485101699829, "global_step": 471049, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0652902126312256, "global_step": 471050, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0365819931030273, "global_step": 471051, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1088051795959473, "global_step": 471052, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.063758134841919, "global_step": 471053, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1134753227233887, "global_step": 471054, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1557719707489014, "global_step": 471055, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0188817977905273, "global_step": 471056, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.091322660446167, "global_step": 471057, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0775842666625977, "global_step": 471058, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0156588554382324, "global_step": 471059, "epoch": 835, "lr": 5e-05}
{"train_loss": 1.9750934839248657, "global_step": 471060, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0434725284576416, "global_step": 471061, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0614173412323, "global_step": 471062, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.142214298248291, "global_step": 471063, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.1868929862976074, "global_step": 471064, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.060096263885498, "global_step": 471065, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0628762245178223, "global_step": 471066, "epoch": 835, "lr": 5e-05}
{"train_loss": 2.0289220809936523, "global_step": 471067, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.952512502670288, "global_step": 471068, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1099557876586914, "global_step": 471069, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0625951290130615, "global_step": 471070, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0388684272766113, "global_step": 471071, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1166515350341797, "global_step": 471072, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.071230173110962, "global_step": 471073, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0782971382141113, "global_step": 471074, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1011078357696533, "global_step": 471075, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0058209896087646, "global_step": 471076, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.065295457839966, "global_step": 471077, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.034712791442871, "global_step": 471078, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.080514907836914, "global_step": 471079, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1031911373138428, "global_step": 471080, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9732133150100708, "global_step": 471081, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0918350219726562, "global_step": 471082, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.026841640472412, "global_step": 471083, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.059396743774414, "global_step": 471084, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0581414699554443, "global_step": 471085, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.075279712677002, "global_step": 471086, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1462690830230713, "global_step": 471087, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9752984046936035, "global_step": 471088, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.031789779663086, "global_step": 471089, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0490942001342773, "global_step": 471090, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0400538444519043, "global_step": 471091, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0100455284118652, "global_step": 471092, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0745291709899902, "global_step": 471093, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.092752695083618, "global_step": 471094, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1658148765563965, "global_step": 471095, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0743865966796875, "global_step": 471096, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0695178508758545, "global_step": 471097, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0204758644104004, "global_step": 471098, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.015537738800049, "global_step": 471099, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0640721321105957, "global_step": 471100, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.096311330795288, "global_step": 471101, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.94707453250885, "global_step": 471102, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.059753656387329, "global_step": 471103, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0690643787384033, "global_step": 471104, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0428497791290283, "global_step": 471105, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0553300380706787, "global_step": 471106, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0495991706848145, "global_step": 471107, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0120890140533447, "global_step": 471108, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0671744346618652, "global_step": 471109, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.982223629951477, "global_step": 471110, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.050004482269287, "global_step": 471111, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0368757247924805, "global_step": 471112, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9850220680236816, "global_step": 471113, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.057560920715332, "global_step": 471114, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.112304449081421, "global_step": 471115, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.119325637817383, "global_step": 471116, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0599071979522705, "global_step": 471117, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9504145383834839, "global_step": 471118, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.095583438873291, "global_step": 471119, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0094668865203857, "global_step": 471120, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.004770278930664, "global_step": 471121, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0810165405273438, "global_step": 471122, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.027939558029175, "global_step": 471123, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0130767822265625, "global_step": 471124, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0190799236297607, "global_step": 471125, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0191798210144043, "global_step": 471126, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0753021240234375, "global_step": 471127, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.013166904449463, "global_step": 471128, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.029853343963623, "global_step": 471129, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0779035091400146, "global_step": 471130, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0444133281707764, "global_step": 471131, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.04742431640625, "global_step": 471132, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0352389812469482, "global_step": 471133, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1668989658355713, "global_step": 471134, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.099893808364868, "global_step": 471135, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.109902858734131, "global_step": 471136, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0633111000061035, "global_step": 471137, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.152897357940674, "global_step": 471138, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.015077590942383, "global_step": 471139, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0430796146392822, "global_step": 471140, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.004108190536499, "global_step": 471141, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.055234432220459, "global_step": 471142, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0493109226226807, "global_step": 471143, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0376696586608887, "global_step": 471144, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.094752073287964, "global_step": 471145, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0291147232055664, "global_step": 471146, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0405972003936768, "global_step": 471147, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1567325592041016, "global_step": 471148, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1380109786987305, "global_step": 471149, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9393305778503418, "global_step": 471150, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.05387282371521, "global_step": 471151, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9917773008346558, "global_step": 471152, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0468742847442627, "global_step": 471153, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.057985305786133, "global_step": 471154, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0956063270568848, "global_step": 471155, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0421526432037354, "global_step": 471156, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.029557704925537, "global_step": 471157, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0548789501190186, "global_step": 471158, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0740914344787598, "global_step": 471159, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0684967041015625, "global_step": 471160, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0861315727233887, "global_step": 471161, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0131912231445312, "global_step": 471162, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.110274314880371, "global_step": 471163, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.164984941482544, "global_step": 471164, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0402281284332275, "global_step": 471165, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.125873327255249, "global_step": 471166, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9918313026428223, "global_step": 471167, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0485291481018066, "global_step": 471168, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9910526275634766, "global_step": 471169, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1507270336151123, "global_step": 471170, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0350773334503174, "global_step": 471171, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.03957200050354, "global_step": 471172, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.102390766143799, "global_step": 471173, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0627875328063965, "global_step": 471174, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.02197003364563, "global_step": 471175, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.034898281097412, "global_step": 471176, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.000154495239258, "global_step": 471177, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0349409580230713, "global_step": 471178, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1128618717193604, "global_step": 471179, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.059635877609253, "global_step": 471180, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.081254243850708, "global_step": 471181, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.083857536315918, "global_step": 471182, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.018796920776367, "global_step": 471183, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.061049699783325, "global_step": 471184, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.083804130554199, "global_step": 471185, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.050175905227661, "global_step": 471186, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0390539169311523, "global_step": 471187, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1224780082702637, "global_step": 471188, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.050973892211914, "global_step": 471189, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0242488384246826, "global_step": 471190, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.065558433532715, "global_step": 471191, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0232300758361816, "global_step": 471192, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0735888481140137, "global_step": 471193, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0123586654663086, "global_step": 471194, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0375754833221436, "global_step": 471195, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0364105701446533, "global_step": 471196, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.081265926361084, "global_step": 471197, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.059257984161377, "global_step": 471198, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.03556227684021, "global_step": 471199, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.974948763847351, "global_step": 471200, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.037839651107788, "global_step": 471201, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0683953762054443, "global_step": 471202, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.00669002532959, "global_step": 471203, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0493004322052, "global_step": 471204, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0060875415802, "global_step": 471205, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9751050472259521, "global_step": 471206, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1764075756073, "global_step": 471207, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0471861362457275, "global_step": 471208, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.07175350189209, "global_step": 471209, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1215760707855225, "global_step": 471210, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0672309398651123, "global_step": 471211, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0213370323181152, "global_step": 471212, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.05118727684021, "global_step": 471213, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.037590980529785, "global_step": 471214, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1521244049072266, "global_step": 471215, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0581350326538086, "global_step": 471216, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.035567283630371, "global_step": 471217, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.08846378326416, "global_step": 471218, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9561126232147217, "global_step": 471219, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0509018898010254, "global_step": 471220, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.094806432723999, "global_step": 471221, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0510334968566895, "global_step": 471222, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0412817001342773, "global_step": 471223, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0160627365112305, "global_step": 471224, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.065429210662842, "global_step": 471225, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0520544052124023, "global_step": 471226, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0594935417175293, "global_step": 471227, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0441091060638428, "global_step": 471228, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.105747938156128, "global_step": 471229, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1057252883911133, "global_step": 471230, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0685956478118896, "global_step": 471231, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0615837574005127, "global_step": 471232, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.042816400527954, "global_step": 471233, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0387585163116455, "global_step": 471234, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0032575130462646, "global_step": 471235, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.076871871948242, "global_step": 471236, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1205976009368896, "global_step": 471237, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9498437643051147, "global_step": 471238, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0927035808563232, "global_step": 471239, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0617945194244385, "global_step": 471240, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1134116649627686, "global_step": 471241, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0289554595947266, "global_step": 471242, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.098764419555664, "global_step": 471243, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1409623622894287, "global_step": 471244, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.02827525138855, "global_step": 471245, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1030118465423584, "global_step": 471246, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9636105298995972, "global_step": 471247, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0173535346984863, "global_step": 471248, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.099632978439331, "global_step": 471249, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.060634136199951, "global_step": 471250, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.16202449798584, "global_step": 471251, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0346388816833496, "global_step": 471252, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0405848026275635, "global_step": 471253, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1407222747802734, "global_step": 471254, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.008915901184082, "global_step": 471255, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.024183750152588, "global_step": 471256, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.005361795425415, "global_step": 471257, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.051973581314087, "global_step": 471258, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9953408241271973, "global_step": 471259, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.095271348953247, "global_step": 471260, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.026968479156494, "global_step": 471261, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.07045841217041, "global_step": 471262, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.97311532497406, "global_step": 471263, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.056087017059326, "global_step": 471264, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0660789012908936, "global_step": 471265, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.019150495529175, "global_step": 471266, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0508875846862793, "global_step": 471267, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1030631065368652, "global_step": 471268, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.030409336090088, "global_step": 471269, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0873982906341553, "global_step": 471270, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.032226800918579, "global_step": 471271, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0321145057678223, "global_step": 471272, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0533478260040283, "global_step": 471273, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0300588607788086, "global_step": 471274, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0379579067230225, "global_step": 471275, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.072598457336426, "global_step": 471276, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.061899423599243, "global_step": 471277, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.134148597717285, "global_step": 471278, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.040087938308716, "global_step": 471279, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9968278408050537, "global_step": 471280, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.090686082839966, "global_step": 471281, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0851833820343018, "global_step": 471282, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1139626502990723, "global_step": 471283, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0338492393493652, "global_step": 471284, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0071916580200195, "global_step": 471285, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.110851287841797, "global_step": 471286, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0764944553375244, "global_step": 471287, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.078524112701416, "global_step": 471288, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0195815563201904, "global_step": 471289, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.038426160812378, "global_step": 471290, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.047886848449707, "global_step": 471291, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9833928346633911, "global_step": 471292, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9964518547058105, "global_step": 471293, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.087146759033203, "global_step": 471294, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.2005512714385986, "global_step": 471295, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9946883916854858, "global_step": 471296, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.025317430496216, "global_step": 471297, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.119398355484009, "global_step": 471298, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.00068736076355, "global_step": 471299, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.005718469619751, "global_step": 471300, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0638253688812256, "global_step": 471301, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.046938896179199, "global_step": 471302, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0450775623321533, "global_step": 471303, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1125683784484863, "global_step": 471304, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.033806085586548, "global_step": 471305, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9976246356964111, "global_step": 471306, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.11678147315979, "global_step": 471307, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.034010410308838, "global_step": 471308, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.102940797805786, "global_step": 471309, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.097886323928833, "global_step": 471310, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.069969654083252, "global_step": 471311, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0721492767333984, "global_step": 471312, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.091951370239258, "global_step": 471313, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.060539960861206, "global_step": 471314, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1313157081604004, "global_step": 471315, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.081570863723755, "global_step": 471316, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.956046223640442, "global_step": 471317, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0553174018859863, "global_step": 471318, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0571892261505127, "global_step": 471319, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0464255809783936, "global_step": 471320, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.028154134750366, "global_step": 471321, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.097977876663208, "global_step": 471322, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.033661365509033, "global_step": 471323, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0645735263824463, "global_step": 471324, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.096186399459839, "global_step": 471325, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0343499183654785, "global_step": 471326, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0741710662841797, "global_step": 471327, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0716044902801514, "global_step": 471328, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.108854055404663, "global_step": 471329, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.106734275817871, "global_step": 471330, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0168542861938477, "global_step": 471331, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.006866216659546, "global_step": 471332, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0279576778411865, "global_step": 471333, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.075948476791382, "global_step": 471334, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.124725818634033, "global_step": 471335, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1175034046173096, "global_step": 471336, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.020883798599243, "global_step": 471337, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.060795307159424, "global_step": 471338, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.031097173690796, "global_step": 471339, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0522000789642334, "global_step": 471340, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0697250366210938, "global_step": 471341, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.020679235458374, "global_step": 471342, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0590879917144775, "global_step": 471343, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.033625602722168, "global_step": 471344, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.05100417137146, "global_step": 471345, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9895727634429932, "global_step": 471346, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1818008422851562, "global_step": 471347, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.044630289077759, "global_step": 471348, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.06939959526062, "global_step": 471349, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.054614782333374, "global_step": 471350, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0449256896972656, "global_step": 471351, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.031560182571411, "global_step": 471352, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.015155553817749, "global_step": 471353, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0420382022857666, "global_step": 471354, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0564584732055664, "global_step": 471355, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.016446113586426, "global_step": 471356, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.057626485824585, "global_step": 471357, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.090695858001709, "global_step": 471358, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.037637710571289, "global_step": 471359, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.106501579284668, "global_step": 471360, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0024924278259277, "global_step": 471361, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0677835941314697, "global_step": 471362, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0838840007781982, "global_step": 471363, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0328850746154785, "global_step": 471364, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0343165397644043, "global_step": 471365, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.005230665206909, "global_step": 471366, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0476057529449463, "global_step": 471367, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0300183296203613, "global_step": 471368, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.048807144165039, "global_step": 471369, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1305370330810547, "global_step": 471370, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.004251718521118, "global_step": 471371, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.108881950378418, "global_step": 471372, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.076624631881714, "global_step": 471373, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.054112672805786, "global_step": 471374, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9676448106765747, "global_step": 471375, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0854694843292236, "global_step": 471376, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9660240411758423, "global_step": 471377, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.106351375579834, "global_step": 471378, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.03378963470459, "global_step": 471379, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1572227478027344, "global_step": 471380, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.090458631515503, "global_step": 471381, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.017987012863159, "global_step": 471382, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0443530082702637, "global_step": 471383, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.089238166809082, "global_step": 471384, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0609347820281982, "global_step": 471385, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0308964252471924, "global_step": 471386, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0037074089050293, "global_step": 471387, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.019698143005371, "global_step": 471388, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0425353050231934, "global_step": 471389, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.096278190612793, "global_step": 471390, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.020689010620117, "global_step": 471391, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1269137859344482, "global_step": 471392, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0161821842193604, "global_step": 471393, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.026181697845459, "global_step": 471394, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.058475971221924, "global_step": 471395, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.067026138305664, "global_step": 471396, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9713001251220703, "global_step": 471397, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9993202686309814, "global_step": 471398, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0717859268188477, "global_step": 471399, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.038529872894287, "global_step": 471400, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.016261577606201, "global_step": 471401, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.035433530807495, "global_step": 471402, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0391907691955566, "global_step": 471403, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0729711055755615, "global_step": 471404, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9822295904159546, "global_step": 471405, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.046849012374878, "global_step": 471406, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.039377212524414, "global_step": 471407, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0316367149353027, "global_step": 471408, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0802760124206543, "global_step": 471409, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9716787338256836, "global_step": 471410, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9937454462051392, "global_step": 471411, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0218605995178223, "global_step": 471412, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.036350727081299, "global_step": 471413, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.065476894378662, "global_step": 471414, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.061417579650879, "global_step": 471415, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0133249759674072, "global_step": 471416, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0840258598327637, "global_step": 471417, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0414927005767822, "global_step": 471418, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0370559692382812, "global_step": 471419, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.001986265182495, "global_step": 471420, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1146140098571777, "global_step": 471421, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0957980155944824, "global_step": 471422, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0371649265289307, "global_step": 471423, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0846855640411377, "global_step": 471424, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.115696430206299, "global_step": 471425, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.037703037261963, "global_step": 471426, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9708714485168457, "global_step": 471427, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0004258155822754, "global_step": 471428, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0844578742980957, "global_step": 471429, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1759190559387207, "global_step": 471430, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.997113585472107, "global_step": 471431, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.074047565460205, "global_step": 471432, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0362768173217773, "global_step": 471433, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.021296977996826, "global_step": 471434, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0345635414123535, "global_step": 471435, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1442623138427734, "global_step": 471436, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.19486927986145, "global_step": 471437, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.068502187728882, "global_step": 471438, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0078988075256348, "global_step": 471439, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.082420587539673, "global_step": 471440, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0834221839904785, "global_step": 471441, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0513570308685303, "global_step": 471442, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.124786615371704, "global_step": 471443, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.080508232116699, "global_step": 471444, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.091883420944214, "global_step": 471445, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1566901206970215, "global_step": 471446, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0574324131011963, "global_step": 471447, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0857245922088623, "global_step": 471448, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.047056198120117, "global_step": 471449, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.99043869972229, "global_step": 471450, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1653027534484863, "global_step": 471451, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0079164505004883, "global_step": 471452, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0904290676116943, "global_step": 471453, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0451836585998535, "global_step": 471454, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0636417865753174, "global_step": 471455, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.079336166381836, "global_step": 471456, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1392900943756104, "global_step": 471457, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9931236505508423, "global_step": 471458, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9951293468475342, "global_step": 471459, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.018195629119873, "global_step": 471460, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.023355722427368, "global_step": 471461, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0650634765625, "global_step": 471462, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.076613664627075, "global_step": 471463, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0259480476379395, "global_step": 471464, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0768940448760986, "global_step": 471465, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0856213569641113, "global_step": 471466, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0175955295562744, "global_step": 471467, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0514614582061768, "global_step": 471468, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.160548210144043, "global_step": 471469, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0879087448120117, "global_step": 471470, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0816943645477295, "global_step": 471471, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.021282434463501, "global_step": 471472, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1120212078094482, "global_step": 471473, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.02964448928833, "global_step": 471474, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9951452016830444, "global_step": 471475, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0358269214630127, "global_step": 471476, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.052253007888794, "global_step": 471477, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.034510374069214, "global_step": 471478, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.077108383178711, "global_step": 471479, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.113262176513672, "global_step": 471480, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1360557079315186, "global_step": 471481, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1549363136291504, "global_step": 471482, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.188314437866211, "global_step": 471483, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.085265874862671, "global_step": 471484, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.01621413230896, "global_step": 471485, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.052244186401367, "global_step": 471486, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0206894874572754, "global_step": 471487, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1049230098724365, "global_step": 471488, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.103379011154175, "global_step": 471489, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0316720008850098, "global_step": 471490, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0750269889831543, "global_step": 471491, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.020671844482422, "global_step": 471492, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.061965227127075, "global_step": 471493, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.120192050933838, "global_step": 471494, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.124507188796997, "global_step": 471495, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.080312728881836, "global_step": 471496, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.027620553970337, "global_step": 471497, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0885095596313477, "global_step": 471498, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0302724838256836, "global_step": 471499, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0083365440368652, "global_step": 471500, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1178886890411377, "global_step": 471501, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.069868564605713, "global_step": 471502, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1502742767333984, "global_step": 471503, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9728820323944092, "global_step": 471504, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.040783166885376, "global_step": 471505, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0227017402648926, "global_step": 471506, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0247855186462402, "global_step": 471507, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.005037546157837, "global_step": 471508, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.174579620361328, "global_step": 471509, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0116324424743652, "global_step": 471510, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1695706844329834, "global_step": 471511, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0974035263061523, "global_step": 471512, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1096391677856445, "global_step": 471513, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9893736839294434, "global_step": 471514, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0266876220703125, "global_step": 471515, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1059916019439697, "global_step": 471516, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0027613639831543, "global_step": 471517, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9714076519012451, "global_step": 471518, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.106241464614868, "global_step": 471519, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0553207397460938, "global_step": 471520, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.044637441635132, "global_step": 471521, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.012058973312378, "global_step": 471522, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.05989670753479, "global_step": 471523, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.145711660385132, "global_step": 471524, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.031972646713257, "global_step": 471525, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0618321895599365, "global_step": 471526, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.000896453857422, "global_step": 471527, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1228017807006836, "global_step": 471528, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.060415267944336, "global_step": 471529, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.038879632949829, "global_step": 471530, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.014249801635742, "global_step": 471531, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0521204471588135, "global_step": 471532, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0932443141937256, "global_step": 471533, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.031648635864258, "global_step": 471534, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.043607711791992, "global_step": 471535, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.119286060333252, "global_step": 471536, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.069854497909546, "global_step": 471537, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1225838661193848, "global_step": 471538, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.081996202468872, "global_step": 471539, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.099428653717041, "global_step": 471540, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.046380043029785, "global_step": 471541, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1463000774383545, "global_step": 471542, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.064659595489502, "global_step": 471543, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.003199815750122, "global_step": 471544, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.010404109954834, "global_step": 471545, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1218342781066895, "global_step": 471546, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0448100566864014, "global_step": 471547, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1378331184387207, "global_step": 471548, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.029256582260132, "global_step": 471549, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0697340965270996, "global_step": 471550, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.066516637802124, "global_step": 471551, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.145686388015747, "global_step": 471552, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.059582471847534, "global_step": 471553, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1083617210388184, "global_step": 471554, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0410938262939453, "global_step": 471555, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.077631950378418, "global_step": 471556, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0885705947875977, "global_step": 471557, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.105208396911621, "global_step": 471558, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1101369857788086, "global_step": 471559, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0606610774993896, "global_step": 471560, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.021070718765259, "global_step": 471561, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1516408920288086, "global_step": 471562, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.093907594680786, "global_step": 471563, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1081056594848633, "global_step": 471564, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9946708679199219, "global_step": 471565, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.999274730682373, "global_step": 471566, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1010637283325195, "global_step": 471567, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.039238929748535, "global_step": 471568, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.001687526702881, "global_step": 471569, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0931098461151123, "global_step": 471570, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.007551431655884, "global_step": 471571, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0545759201049805, "global_step": 471572, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9786467552185059, "global_step": 471573, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0382187366485596, "global_step": 471574, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1193814277648926, "global_step": 471575, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9812031984329224, "global_step": 471576, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.973517894744873, "global_step": 471577, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.021000862121582, "global_step": 471578, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.211599111557007, "global_step": 471579, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.127974033355713, "global_step": 471580, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9952633380889893, "global_step": 471581, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.028905153274536, "global_step": 471582, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0383262634277344, "global_step": 471583, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.015366554260254, "global_step": 471584, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.080569267272949, "global_step": 471585, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0198328495025635, "global_step": 471586, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1307311058044434, "global_step": 471587, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9935619831085205, "global_step": 471588, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0487730503082275, "global_step": 471589, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.176301956176758, "global_step": 471590, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.073465585708618, "global_step": 471591, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.031071901321411, "global_step": 471592, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.091501474380493, "global_step": 471593, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0342490673065186, "global_step": 471594, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9518847465515137, "global_step": 471595, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0865957736968994, "global_step": 471596, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0543229579925537, "global_step": 471597, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.091583728790283, "global_step": 471598, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.02406907081604, "global_step": 471599, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9875414371490479, "global_step": 471600, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0607657432556152, "global_step": 471601, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.058037757873535, "global_step": 471602, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.088822841644287, "global_step": 471603, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1922495365142822, "global_step": 471604, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.058241844177246, "global_step": 471605, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0494272708892822, "global_step": 471606, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0386624336242676, "global_step": 471607, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1192684173583984, "global_step": 471608, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0748326778411865, "global_step": 471609, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.098860263824463, "global_step": 471610, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.11453914642334, "global_step": 471611, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.052257537841797, "global_step": 471612, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.049328327178955, "global_step": 471613, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0624356269836426, "global_step": 471614, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.125283718109131, "global_step": 471615, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.023952007293701, "global_step": 471616, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.083554267883301, "global_step": 471617, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.002166509628296, "global_step": 471618, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0379881858825684, "global_step": 471619, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0897881984710693, "global_step": 471620, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0449490547180176, "global_step": 471621, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0909931659698486, "global_step": 471622, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.046090602874756, "global_step": 471623, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.015625476837158, "global_step": 471624, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1640548706054688, "global_step": 471625, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0321881771087646, "global_step": 471626, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.138895034790039, "global_step": 471627, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9633070230484009, "global_step": 471628, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0328867435455322, "global_step": 471629, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0864272117614746, "global_step": 471630, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.143808126449585, "global_step": 471631, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0189168453216553, "global_step": 471632, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0783002376556396, "global_step": 471633, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9717328548431396, "global_step": 471634, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.021695137023926, "global_step": 471635, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1061480045318604, "global_step": 471636, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.072704315185547, "global_step": 471637, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.055140256881714, "global_step": 471638, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.05946946144104, "global_step": 471639, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.973747730255127, "global_step": 471640, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9871292114257812, "global_step": 471641, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.137953996658325, "global_step": 471642, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.028430938720703, "global_step": 471643, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0960278511047363, "global_step": 471644, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.058488607406616, "global_step": 471645, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0499420166015625, "global_step": 471646, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.065080404281616, "global_step": 471647, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9654736518859863, "global_step": 471648, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0348165035247803, "global_step": 471649, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.108548879623413, "global_step": 471650, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.079913854598999, "global_step": 471651, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0403213500976562, "global_step": 471652, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0232484340667725, "global_step": 471653, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0801942348480225, "global_step": 471654, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.032358407974243, "global_step": 471655, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1282694339752197, "global_step": 471656, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.050069570541382, "global_step": 471657, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.147531270980835, "global_step": 471658, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.067763566970825, "global_step": 471659, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0732269287109375, "global_step": 471660, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0717742443084717, "global_step": 471661, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0491156578063965, "global_step": 471662, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9712011814117432, "global_step": 471663, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.031796455383301, "global_step": 471664, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.131580114364624, "global_step": 471665, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1276609897613525, "global_step": 471666, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.076709747314453, "global_step": 471667, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0900862216949463, "global_step": 471668, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1595206260681152, "global_step": 471669, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.022770881652832, "global_step": 471670, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0136377811431885, "global_step": 471671, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.007354259490967, "global_step": 471672, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.064492702484131, "global_step": 471673, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1170742511749268, "global_step": 471674, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0533721446990967, "global_step": 471675, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.081068277359009, "global_step": 471676, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0823519229888916, "global_step": 471677, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.025949001312256, "global_step": 471678, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0932767391204834, "global_step": 471679, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0345988273620605, "global_step": 471680, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9561097621917725, "global_step": 471681, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1077022552490234, "global_step": 471682, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.068798065185547, "global_step": 471683, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.056011199951172, "global_step": 471684, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0750763416290283, "global_step": 471685, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0304172039031982, "global_step": 471686, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0395560264587402, "global_step": 471687, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1258466243743896, "global_step": 471688, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0570545196533203, "global_step": 471689, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0493690967559814, "global_step": 471690, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0597736835479736, "global_step": 471691, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1307754516601562, "global_step": 471692, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1630024909973145, "global_step": 471693, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0426290035247803, "global_step": 471694, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.054241418838501, "global_step": 471695, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0904200077056885, "global_step": 471696, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1233625411987305, "global_step": 471697, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9957979917526245, "global_step": 471698, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.075568914413452, "global_step": 471699, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.163621425628662, "global_step": 471700, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0523526668548584, "global_step": 471701, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1316843032836914, "global_step": 471702, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.025453567504883, "global_step": 471703, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0168957710266113, "global_step": 471704, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1121652126312256, "global_step": 471705, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0069222450256348, "global_step": 471706, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0485193729400635, "global_step": 471707, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.048079013824463, "global_step": 471708, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0858757495880127, "global_step": 471709, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.01878023147583, "global_step": 471710, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0220351219177246, "global_step": 471711, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.038543462753296, "global_step": 471712, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.019287347793579, "global_step": 471713, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.065373420715332, "global_step": 471714, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.056845188140869, "global_step": 471715, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.117410898208618, "global_step": 471716, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0985090732574463, "global_step": 471717, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0875556468963623, "global_step": 471718, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0857059955596924, "global_step": 471719, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.022031307220459, "global_step": 471720, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0938000679016113, "global_step": 471721, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.113328456878662, "global_step": 471722, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.146059513092041, "global_step": 471723, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0398151874542236, "global_step": 471724, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0994646549224854, "global_step": 471725, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9608275890350342, "global_step": 471726, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.077016830444336, "global_step": 471727, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0586578845977783, "global_step": 471728, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0219030380249023, "global_step": 471729, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0541672706604004, "global_step": 471730, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0621261596679688, "global_step": 471731, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.066091775894165, "global_step": 471732, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.070528507232666, "global_step": 471733, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0471622943878174, "global_step": 471734, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.061206579208374, "global_step": 471735, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.058506965637207, "global_step": 471736, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.968321681022644, "global_step": 471737, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1310927867889404, "global_step": 471738, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1126902103424072, "global_step": 471739, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.081576347351074, "global_step": 471740, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.055992841720581, "global_step": 471741, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1268796920776367, "global_step": 471742, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.11344838142395, "global_step": 471743, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.057011127471924, "global_step": 471744, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.068207025527954, "global_step": 471745, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.028564929962158, "global_step": 471746, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.116319417953491, "global_step": 471747, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.21256947517395, "global_step": 471748, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1515371799468994, "global_step": 471749, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0261964797973633, "global_step": 471750, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1974844932556152, "global_step": 471751, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1070244312286377, "global_step": 471752, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0900728702545166, "global_step": 471753, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0086028575897217, "global_step": 471754, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.185995578765869, "global_step": 471755, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.045313835144043, "global_step": 471756, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.141024589538574, "global_step": 471757, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.111196279525757, "global_step": 471758, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.019627332687378, "global_step": 471759, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.118713617324829, "global_step": 471760, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.16816782951355, "global_step": 471761, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0346901416778564, "global_step": 471762, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0847089290618896, "global_step": 471763, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1643991470336914, "global_step": 471764, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1553843021392822, "global_step": 471765, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0882692337036133, "global_step": 471766, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0215156078338623, "global_step": 471767, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.081278085708618, "global_step": 471768, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0948734283447266, "global_step": 471769, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.087085723876953, "global_step": 471770, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.031156063079834, "global_step": 471771, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0479202270507812, "global_step": 471772, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.092904567718506, "global_step": 471773, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.042515516281128, "global_step": 471774, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.111542224884033, "global_step": 471775, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.083186149597168, "global_step": 471776, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0816261768341064, "global_step": 471777, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0583205223083496, "global_step": 471778, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0547850131988525, "global_step": 471779, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0622684955596924, "global_step": 471780, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.105220079421997, "global_step": 471781, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.078258752822876, "global_step": 471782, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.067596673965454, "global_step": 471783, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.077352523803711, "global_step": 471784, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1324846744537354, "global_step": 471785, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0938611030578613, "global_step": 471786, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9987783432006836, "global_step": 471787, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.106276512145996, "global_step": 471788, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0691399574279785, "global_step": 471789, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0980825424194336, "global_step": 471790, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.049832344055176, "global_step": 471791, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.017113208770752, "global_step": 471792, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1046249866485596, "global_step": 471793, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1537790298461914, "global_step": 471794, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0230231285095215, "global_step": 471795, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.075712203979492, "global_step": 471796, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.069077491760254, "global_step": 471797, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.117582082748413, "global_step": 471798, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.086888074874878, "global_step": 471799, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0708718299865723, "global_step": 471800, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0490660667419434, "global_step": 471801, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0577402114868164, "global_step": 471802, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.030575752258301, "global_step": 471803, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1162567138671875, "global_step": 471804, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.027259111404419, "global_step": 471805, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1393649578094482, "global_step": 471806, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.04313588142395, "global_step": 471807, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0389750003814697, "global_step": 471808, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.056136131286621, "global_step": 471809, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0293142795562744, "global_step": 471810, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1681432723999023, "global_step": 471811, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0118987560272217, "global_step": 471812, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0569300651550293, "global_step": 471813, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.08638596534729, "global_step": 471814, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0936031341552734, "global_step": 471815, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0815038681030273, "global_step": 471816, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.174201488494873, "global_step": 471817, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1579275131225586, "global_step": 471818, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0834600925445557, "global_step": 471819, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0731937885284424, "global_step": 471820, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.173365354537964, "global_step": 471821, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.132091999053955, "global_step": 471822, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0672976970672607, "global_step": 471823, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.030071496963501, "global_step": 471824, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0589542388916016, "global_step": 471825, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0271801948547363, "global_step": 471826, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9990044832229614, "global_step": 471827, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0169756412506104, "global_step": 471828, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.989681601524353, "global_step": 471829, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9772201776504517, "global_step": 471830, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0769429206848145, "global_step": 471831, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.101743459701538, "global_step": 471832, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.120945930480957, "global_step": 471833, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0697267055511475, "global_step": 471834, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0706369876861572, "global_step": 471835, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1141674518585205, "global_step": 471836, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0593225955963135, "global_step": 471837, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.040067672729492, "global_step": 471838, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0554823875427246, "global_step": 471839, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.009556531906128, "global_step": 471840, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.066592216491699, "global_step": 471841, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.068308115005493, "global_step": 471842, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.093470811843872, "global_step": 471843, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0262060165405273, "global_step": 471844, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1185214519500732, "global_step": 471845, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0378787517547607, "global_step": 471846, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.060458183288574, "global_step": 471847, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0075502395629883, "global_step": 471848, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0774028301239014, "global_step": 471849, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.100878953933716, "global_step": 471850, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.053067207336426, "global_step": 471851, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0881028175354004, "global_step": 471852, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1061160564422607, "global_step": 471853, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.034461736679077, "global_step": 471854, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.099334478378296, "global_step": 471855, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.056894302368164, "global_step": 471856, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.106860637664795, "global_step": 471857, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0732593536376953, "global_step": 471858, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.045755624771118, "global_step": 471859, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.093799352645874, "global_step": 471860, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0363543033599854, "global_step": 471861, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.114903211593628, "global_step": 471862, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0681190490722656, "global_step": 471863, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.137303113937378, "global_step": 471864, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1322686672210693, "global_step": 471865, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1044230461120605, "global_step": 471866, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0910253524780273, "global_step": 471867, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.12074875831604, "global_step": 471868, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0424981117248535, "global_step": 471869, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.06200909614563, "global_step": 471870, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1492936611175537, "global_step": 471871, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.104909896850586, "global_step": 471872, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.120299816131592, "global_step": 471873, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0028445720672607, "global_step": 471874, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.007289409637451, "global_step": 471875, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0332658290863037, "global_step": 471876, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.079742431640625, "global_step": 471877, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.119596481323242, "global_step": 471878, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.157268524169922, "global_step": 471879, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0290844440460205, "global_step": 471880, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1717236042022705, "global_step": 471881, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0930840969085693, "global_step": 471882, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1209235191345215, "global_step": 471883, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9955376386642456, "global_step": 471884, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1636462211608887, "global_step": 471885, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0737483501434326, "global_step": 471886, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.028416872024536, "global_step": 471887, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0886900424957275, "global_step": 471888, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.073117971420288, "global_step": 471889, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0514562129974365, "global_step": 471890, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0560011863708496, "global_step": 471891, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.060701608657837, "global_step": 471892, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0084471702575684, "global_step": 471893, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.010788917541504, "global_step": 471894, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0517420768737793, "global_step": 471895, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.036583423614502, "global_step": 471896, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.049386978149414, "global_step": 471897, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.036496877670288, "global_step": 471898, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.085916519165039, "global_step": 471899, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0940091609954834, "global_step": 471900, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.109367847442627, "global_step": 471901, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.069561243057251, "global_step": 471902, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1120781898498535, "global_step": 471903, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0131595134735107, "global_step": 471904, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0808119773864746, "global_step": 471905, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0484273433685303, "global_step": 471906, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0272202491760254, "global_step": 471907, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1306614875793457, "global_step": 471908, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1055102348327637, "global_step": 471909, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0965752601623535, "global_step": 471910, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0986759662628174, "global_step": 471911, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.096859931945801, "global_step": 471912, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.078005790710449, "global_step": 471913, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9626413583755493, "global_step": 471914, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0075366497039795, "global_step": 471915, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.045928955078125, "global_step": 471916, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0571887493133545, "global_step": 471917, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1158695220947266, "global_step": 471918, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1405394077301025, "global_step": 471919, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.090562105178833, "global_step": 471920, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.061260223388672, "global_step": 471921, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.121793746948242, "global_step": 471922, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1090683937072754, "global_step": 471923, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0154035091400146, "global_step": 471924, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.06345796585083, "global_step": 471925, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.116218090057373, "global_step": 471926, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1011104583740234, "global_step": 471927, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0104072093963623, "global_step": 471928, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1669962406158447, "global_step": 471929, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0735416412353516, "global_step": 471930, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0838449001312256, "global_step": 471931, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0463716983795166, "global_step": 471932, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.014425039291382, "global_step": 471933, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0386176109313965, "global_step": 471934, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1083860397338867, "global_step": 471935, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0549075603485107, "global_step": 471936, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0660929679870605, "global_step": 471937, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0139729976654053, "global_step": 471938, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0638692378997803, "global_step": 471939, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.034571886062622, "global_step": 471940, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1017258167266846, "global_step": 471941, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.102639675140381, "global_step": 471942, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9810072183609009, "global_step": 471943, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0396482944488525, "global_step": 471944, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.02314829826355, "global_step": 471945, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.038923740386963, "global_step": 471946, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.084261417388916, "global_step": 471947, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0521857738494873, "global_step": 471948, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0998637676239014, "global_step": 471949, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1278045177459717, "global_step": 471950, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1260828971862793, "global_step": 471951, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0451271533966064, "global_step": 471952, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1186041831970215, "global_step": 471953, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1334660053253174, "global_step": 471954, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0642011165618896, "global_step": 471955, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.082547664642334, "global_step": 471956, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.11049222946167, "global_step": 471957, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1538758277893066, "global_step": 471958, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9988616704940796, "global_step": 471959, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.078216791152954, "global_step": 471960, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0072436332702637, "global_step": 471961, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.041396141052246, "global_step": 471962, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.107574462890625, "global_step": 471963, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.08469295501709, "global_step": 471964, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.057488441467285, "global_step": 471965, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.08380126953125, "global_step": 471966, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0349507331848145, "global_step": 471967, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0824077129364014, "global_step": 471968, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0651135444641113, "global_step": 471969, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.117793321609497, "global_step": 471970, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1553611755371094, "global_step": 471971, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0227441787719727, "global_step": 471972, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.171306848526001, "global_step": 471973, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0436155796051025, "global_step": 471974, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.092282295227051, "global_step": 471975, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.07171368598938, "global_step": 471976, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.086763858795166, "global_step": 471977, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0931591987609863, "global_step": 471978, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0138962268829346, "global_step": 471979, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0190041065216064, "global_step": 471980, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.149077892303467, "global_step": 471981, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0698256492614746, "global_step": 471982, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0390193462371826, "global_step": 471983, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0531065464019775, "global_step": 471984, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0259063243865967, "global_step": 471985, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.032447099685669, "global_step": 471986, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.087670087814331, "global_step": 471987, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0955917835235596, "global_step": 471988, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0430166721343994, "global_step": 471989, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0427916049957275, "global_step": 471990, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1359641551971436, "global_step": 471991, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0481913089752197, "global_step": 471992, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0095341205596924, "global_step": 471993, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.142488956451416, "global_step": 471994, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.03432559967041, "global_step": 471995, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0431318283081055, "global_step": 471996, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0669591426849365, "global_step": 471997, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.055332660675049, "global_step": 471998, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0875110626220703, "global_step": 471999, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0341479778289795, "global_step": 472000, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.004309892654419, "global_step": 472001, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1212961673736572, "global_step": 472002, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0690104961395264, "global_step": 472003, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.113009214401245, "global_step": 472004, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.076927423477173, "global_step": 472005, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.099586248397827, "global_step": 472006, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.115741014480591, "global_step": 472007, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.082444667816162, "global_step": 472008, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1231820583343506, "global_step": 472009, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1698012351989746, "global_step": 472010, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0879695415496826, "global_step": 472011, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.093674659729004, "global_step": 472012, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.033291816711426, "global_step": 472013, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.059183120727539, "global_step": 472014, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0224714279174805, "global_step": 472015, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.17120361328125, "global_step": 472016, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.084954023361206, "global_step": 472017, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.059994697570801, "global_step": 472018, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.085559844970703, "global_step": 472019, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1294801235198975, "global_step": 472020, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.054187536239624, "global_step": 472021, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0732674598693848, "global_step": 472022, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0387723445892334, "global_step": 472023, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1110050678253174, "global_step": 472024, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0900912284851074, "global_step": 472025, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0780303478240967, "global_step": 472026, "epoch": 836, "lr": 5e-05}
{"train_loss": 1.9666301012039185, "global_step": 472027, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.059669256210327, "global_step": 472028, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1653695106506348, "global_step": 472029, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1226818561553955, "global_step": 472030, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.0074286460876465, "global_step": 472031, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.024674892425537, "global_step": 472032, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.1205008029937744, "global_step": 472033, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.071298360824585, "global_step": 472034, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.064249277114868, "global_step": 472035, "epoch": 836, "lr": 5e-05}
{"train_loss": 2.050522565841675, "global_step": 472036, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0062992572784424, "global_step": 472037, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.045433759689331, "global_step": 472038, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1098413467407227, "global_step": 472039, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.115020513534546, "global_step": 472040, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0655510425567627, "global_step": 472041, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0958590507507324, "global_step": 472042, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0510611534118652, "global_step": 472043, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0938210487365723, "global_step": 472044, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0868330001831055, "global_step": 472045, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0715696811676025, "global_step": 472046, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.046201705932617, "global_step": 472047, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.031501293182373, "global_step": 472048, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.040330410003662, "global_step": 472049, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0474486351013184, "global_step": 472050, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0646114349365234, "global_step": 472051, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.152085065841675, "global_step": 472052, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9878628253936768, "global_step": 472053, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.091243028640747, "global_step": 472054, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.071373701095581, "global_step": 472055, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9906938076019287, "global_step": 472056, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1255784034729004, "global_step": 472057, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.103149175643921, "global_step": 472058, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9872972965240479, "global_step": 472059, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1112563610076904, "global_step": 472060, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0973854064941406, "global_step": 472061, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9928134679794312, "global_step": 472062, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0766444206237793, "global_step": 472063, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9888331890106201, "global_step": 472064, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0350096225738525, "global_step": 472065, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.01275634765625, "global_step": 472066, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0254509449005127, "global_step": 472067, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.034059524536133, "global_step": 472068, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.081228494644165, "global_step": 472069, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0764412879943848, "global_step": 472070, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.043900489807129, "global_step": 472071, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1302497386932373, "global_step": 472072, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0749807357788086, "global_step": 472073, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0443928241729736, "global_step": 472074, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.018474817276001, "global_step": 472075, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0397424697875977, "global_step": 472076, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0387046337127686, "global_step": 472077, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.00252628326416, "global_step": 472078, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0362024307250977, "global_step": 472079, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.006983518600464, "global_step": 472080, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0271575450897217, "global_step": 472081, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.077357769012451, "global_step": 472082, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1836252212524414, "global_step": 472083, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.111077070236206, "global_step": 472084, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.050694465637207, "global_step": 472085, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0766971111297607, "global_step": 472086, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0901074409484863, "global_step": 472087, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0453922748565674, "global_step": 472088, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0851023197174072, "global_step": 472089, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0060174465179443, "global_step": 472090, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0459487438201904, "global_step": 472091, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0268521308898926, "global_step": 472092, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0592474937438965, "global_step": 472093, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0550999641418457, "global_step": 472094, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.107455253601074, "global_step": 472095, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.046783208847046, "global_step": 472096, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.11407732963562, "global_step": 472097, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.049778938293457, "global_step": 472098, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9630775451660156, "global_step": 472099, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1011202335357666, "global_step": 472100, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0048153400421143, "global_step": 472101, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.024052143096924, "global_step": 472102, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.072890043258667, "global_step": 472103, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.032947540283203, "global_step": 472104, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9879788160324097, "global_step": 472105, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.111708879470825, "global_step": 472106, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0888049602508545, "global_step": 472107, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0527408123016357, "global_step": 472108, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.997423529624939, "global_step": 472109, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.055335283279419, "global_step": 472110, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1059865951538086, "global_step": 472111, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.123694658279419, "global_step": 472112, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0167131423950195, "global_step": 472113, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1073386669158936, "global_step": 472114, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0429840087890625, "global_step": 472115, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0515499114990234, "global_step": 472116, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0172770023345947, "global_step": 472117, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.019400119781494, "global_step": 472118, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9738918542861938, "global_step": 472119, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0864553451538086, "global_step": 472120, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.047912120819092, "global_step": 472121, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0520801544189453, "global_step": 472122, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.091132402420044, "global_step": 472123, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.046358823776245, "global_step": 472124, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.01037859916687, "global_step": 472125, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1722471714019775, "global_step": 472126, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0738961696624756, "global_step": 472127, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0919134616851807, "global_step": 472128, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.99429190158844, "global_step": 472129, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0638818740844727, "global_step": 472130, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0991408824920654, "global_step": 472131, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.063267230987549, "global_step": 472132, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9767858982086182, "global_step": 472133, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.023801565170288, "global_step": 472134, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1169354915618896, "global_step": 472135, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.014005184173584, "global_step": 472136, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.031646728515625, "global_step": 472137, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0993127822875977, "global_step": 472138, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1223034858703613, "global_step": 472139, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.10367751121521, "global_step": 472140, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.916154384613037, "global_step": 472141, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.098595142364502, "global_step": 472142, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9795434474945068, "global_step": 472143, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.12733793258667, "global_step": 472144, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.042447090148926, "global_step": 472145, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.059809446334839, "global_step": 472146, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0301437377929688, "global_step": 472147, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1079015731811523, "global_step": 472148, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1016621589660645, "global_step": 472149, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9928873777389526, "global_step": 472150, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9683107137680054, "global_step": 472151, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0790014266967773, "global_step": 472152, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.088120698928833, "global_step": 472153, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0486629009246826, "global_step": 472154, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9910194873809814, "global_step": 472155, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9080547094345093, "global_step": 472156, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0496909618377686, "global_step": 472157, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0515472888946533, "global_step": 472158, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9870243072509766, "global_step": 472159, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0206315517425537, "global_step": 472160, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1049578189849854, "global_step": 472161, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9966930150985718, "global_step": 472162, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.080345630645752, "global_step": 472163, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.129896879196167, "global_step": 472164, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0480871200561523, "global_step": 472165, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1098670959472656, "global_step": 472166, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.049311399459839, "global_step": 472167, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0194852352142334, "global_step": 472168, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.10976243019104, "global_step": 472169, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1190669536590576, "global_step": 472170, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0441629886627197, "global_step": 472171, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0228607654571533, "global_step": 472172, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.050657272338867, "global_step": 472173, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0712950229644775, "global_step": 472174, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0578489303588867, "global_step": 472175, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.069679021835327, "global_step": 472176, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0845937728881836, "global_step": 472177, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0790398120880127, "global_step": 472178, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0403261184692383, "global_step": 472179, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.038261890411377, "global_step": 472180, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0305094718933105, "global_step": 472181, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.018035650253296, "global_step": 472182, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0458483695983887, "global_step": 472183, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.077806234359741, "global_step": 472184, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.083397388458252, "global_step": 472185, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9861199855804443, "global_step": 472186, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.102943181991577, "global_step": 472187, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0367331504821777, "global_step": 472188, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0599162578582764, "global_step": 472189, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0005135536193848, "global_step": 472190, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0714170932769775, "global_step": 472191, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0892226696014404, "global_step": 472192, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0063931941986084, "global_step": 472193, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1392018795013428, "global_step": 472194, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0677342414855957, "global_step": 472195, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.05977201461792, "global_step": 472196, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.023719310760498, "global_step": 472197, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0629758834838867, "global_step": 472198, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.988669991493225, "global_step": 472199, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.085691213607788, "global_step": 472200, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.026266098022461, "global_step": 472201, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0097711086273193, "global_step": 472202, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.102107524871826, "global_step": 472203, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9841883182525635, "global_step": 472204, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0288572311401367, "global_step": 472205, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.089322090148926, "global_step": 472206, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0998306274414062, "global_step": 472207, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0661909580230713, "global_step": 472208, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0848288536071777, "global_step": 472209, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0818700790405273, "global_step": 472210, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.088399887084961, "global_step": 472211, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0325918197631836, "global_step": 472212, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0672364234924316, "global_step": 472213, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0560693740844727, "global_step": 472214, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.04573655128479, "global_step": 472215, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9943516254425049, "global_step": 472216, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1128647327423096, "global_step": 472217, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0480892658233643, "global_step": 472218, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0383358001708984, "global_step": 472219, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.090268850326538, "global_step": 472220, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.010979652404785, "global_step": 472221, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.057260513305664, "global_step": 472222, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0921716690063477, "global_step": 472223, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0866453647613525, "global_step": 472224, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.063359022140503, "global_step": 472225, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9710400104522705, "global_step": 472226, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.021193265914917, "global_step": 472227, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1697912216186523, "global_step": 472228, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0922181606292725, "global_step": 472229, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.032059669494629, "global_step": 472230, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0315659046173096, "global_step": 472231, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0263068675994873, "global_step": 472232, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.102055788040161, "global_step": 472233, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.046928644180298, "global_step": 472234, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1079702377319336, "global_step": 472235, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.130577802658081, "global_step": 472236, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1162357330322266, "global_step": 472237, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0336649417877197, "global_step": 472238, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0943658351898193, "global_step": 472239, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9761134386062622, "global_step": 472240, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0303971767425537, "global_step": 472241, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0932064056396484, "global_step": 472242, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.066352367401123, "global_step": 472243, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0343868732452393, "global_step": 472244, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.022468328475952, "global_step": 472245, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.106163263320923, "global_step": 472246, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.025980234146118, "global_step": 472247, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0625193119049072, "global_step": 472248, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1378300189971924, "global_step": 472249, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1484315395355225, "global_step": 472250, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1073787212371826, "global_step": 472251, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1157801151275635, "global_step": 472252, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0310492515563965, "global_step": 472253, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.015270709991455, "global_step": 472254, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.090909004211426, "global_step": 472255, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.057732343673706, "global_step": 472256, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0329253673553467, "global_step": 472257, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.04992938041687, "global_step": 472258, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.04811954498291, "global_step": 472259, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.016221046447754, "global_step": 472260, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0493080615997314, "global_step": 472261, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0986053943634033, "global_step": 472262, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0769550800323486, "global_step": 472263, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1151058673858643, "global_step": 472264, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.106623649597168, "global_step": 472265, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0669989585876465, "global_step": 472266, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0523359775543213, "global_step": 472267, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0135040283203125, "global_step": 472268, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9349583387374878, "global_step": 472269, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0416958332061768, "global_step": 472270, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1329152584075928, "global_step": 472271, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.102433443069458, "global_step": 472272, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0648880004882812, "global_step": 472273, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0797481536865234, "global_step": 472274, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.046950340270996, "global_step": 472275, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.039511203765869, "global_step": 472276, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0921213626861572, "global_step": 472277, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.031416177749634, "global_step": 472278, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.063267946243286, "global_step": 472279, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0434961318969727, "global_step": 472280, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1198031902313232, "global_step": 472281, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.141331672668457, "global_step": 472282, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.118576765060425, "global_step": 472283, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9621092081069946, "global_step": 472284, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0391719341278076, "global_step": 472285, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0345706939697266, "global_step": 472286, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9982030391693115, "global_step": 472287, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9272723197937012, "global_step": 472288, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.147876024246216, "global_step": 472289, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.054624557495117, "global_step": 472290, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.959476113319397, "global_step": 472291, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0942986011505127, "global_step": 472292, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.006319761276245, "global_step": 472293, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.063141107559204, "global_step": 472294, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0596675872802734, "global_step": 472295, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0896248817443848, "global_step": 472296, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0537819862365723, "global_step": 472297, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0541090965270996, "global_step": 472298, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.011267900466919, "global_step": 472299, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.059767961502075, "global_step": 472300, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0995047092437744, "global_step": 472301, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9905872344970703, "global_step": 472302, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.067594528198242, "global_step": 472303, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.074126958847046, "global_step": 472304, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.989398717880249, "global_step": 472305, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0341711044311523, "global_step": 472306, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.02414608001709, "global_step": 472307, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0834169387817383, "global_step": 472308, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0898661613464355, "global_step": 472309, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0391502380371094, "global_step": 472310, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.008049249649048, "global_step": 472311, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.077108383178711, "global_step": 472312, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0025367736816406, "global_step": 472313, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0589969158172607, "global_step": 472314, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.025738000869751, "global_step": 472315, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0694236755371094, "global_step": 472316, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0452163219451904, "global_step": 472317, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0094518661499023, "global_step": 472318, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9859179258346558, "global_step": 472319, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1323819160461426, "global_step": 472320, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0299811363220215, "global_step": 472321, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.045652389526367, "global_step": 472322, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0651540756225586, "global_step": 472323, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9896659851074219, "global_step": 472324, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0570123195648193, "global_step": 472325, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.102970838546753, "global_step": 472326, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.039142370223999, "global_step": 472327, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0512330532073975, "global_step": 472328, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.019437074661255, "global_step": 472329, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0172157287597656, "global_step": 472330, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.130763530731201, "global_step": 472331, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.053511381149292, "global_step": 472332, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0958337783813477, "global_step": 472333, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0501956939697266, "global_step": 472334, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.063586711883545, "global_step": 472335, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0343923568725586, "global_step": 472336, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0146429538726807, "global_step": 472337, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.071108818054199, "global_step": 472338, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0436830520629883, "global_step": 472339, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0135974884033203, "global_step": 472340, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.981342077255249, "global_step": 472341, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.153550624847412, "global_step": 472342, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0700457096099854, "global_step": 472343, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.065242290496826, "global_step": 472344, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0633814334869385, "global_step": 472345, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.099917411804199, "global_step": 472346, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.024684429168701, "global_step": 472347, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9698681831359863, "global_step": 472348, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.016173839569092, "global_step": 472349, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.062511682510376, "global_step": 472350, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.038801670074463, "global_step": 472351, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1625308990478516, "global_step": 472352, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0903282165527344, "global_step": 472353, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.093182325363159, "global_step": 472354, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.118640422821045, "global_step": 472355, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.147062063217163, "global_step": 472356, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.10434889793396, "global_step": 472357, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.054279088973999, "global_step": 472358, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0475094318389893, "global_step": 472359, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.110825777053833, "global_step": 472360, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0932929515838623, "global_step": 472361, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0256810188293457, "global_step": 472362, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0641651153564453, "global_step": 472363, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9942835569381714, "global_step": 472364, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.144261121749878, "global_step": 472365, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.040081739425659, "global_step": 472366, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1046013832092285, "global_step": 472367, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.111494779586792, "global_step": 472368, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.03307843208313, "global_step": 472369, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0385191440582275, "global_step": 472370, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.028087615966797, "global_step": 472371, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0667285919189453, "global_step": 472372, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.05183482170105, "global_step": 472373, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9949162006378174, "global_step": 472374, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0763309001922607, "global_step": 472375, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0982584953308105, "global_step": 472376, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9966189861297607, "global_step": 472377, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.143981695175171, "global_step": 472378, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.03067684173584, "global_step": 472379, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0393221378326416, "global_step": 472380, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1215438842773438, "global_step": 472381, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1644158363342285, "global_step": 472382, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.078577995300293, "global_step": 472383, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1261637210845947, "global_step": 472384, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0816128253936768, "global_step": 472385, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.063150405883789, "global_step": 472386, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.109809637069702, "global_step": 472387, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0060927867889404, "global_step": 472388, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0073909759521484, "global_step": 472389, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0596861839294434, "global_step": 472390, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1067609786987305, "global_step": 472391, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0938379764556885, "global_step": 472392, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.122375965118408, "global_step": 472393, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.068127393722534, "global_step": 472394, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9923254251480103, "global_step": 472395, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.971472978591919, "global_step": 472396, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0998482704162598, "global_step": 472397, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.014575481414795, "global_step": 472398, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0620205402374268, "global_step": 472399, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.103142261505127, "global_step": 472400, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.154848575592041, "global_step": 472401, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1194498538970947, "global_step": 472402, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9783135652542114, "global_step": 472403, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0378594398498535, "global_step": 472404, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0372188091278076, "global_step": 472405, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0438671112060547, "global_step": 472406, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9978784322738647, "global_step": 472407, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1674790382385254, "global_step": 472408, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.100658655166626, "global_step": 472409, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.118014097213745, "global_step": 472410, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1127264499664307, "global_step": 472411, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1369333267211914, "global_step": 472412, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.151646852493286, "global_step": 472413, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1251399517059326, "global_step": 472414, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.065981149673462, "global_step": 472415, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.015326976776123, "global_step": 472416, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0796360969543457, "global_step": 472417, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1273367404937744, "global_step": 472418, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.061414957046509, "global_step": 472419, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0342302322387695, "global_step": 472420, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0181527137756348, "global_step": 472421, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.096641778945923, "global_step": 472422, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9763158559799194, "global_step": 472423, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.006843328475952, "global_step": 472424, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0070135593414307, "global_step": 472425, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.030890941619873, "global_step": 472426, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0611369609832764, "global_step": 472427, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.089745283126831, "global_step": 472428, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.108057975769043, "global_step": 472429, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0193777084350586, "global_step": 472430, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.113492965698242, "global_step": 472431, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0737950801849365, "global_step": 472432, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.068732738494873, "global_step": 472433, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1225900650024414, "global_step": 472434, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.093857526779175, "global_step": 472435, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0732972621917725, "global_step": 472436, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1183955669403076, "global_step": 472437, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9985865354537964, "global_step": 472438, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.081364393234253, "global_step": 472439, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9791176319122314, "global_step": 472440, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.138298273086548, "global_step": 472441, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0580732822418213, "global_step": 472442, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.144321918487549, "global_step": 472443, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.113363742828369, "global_step": 472444, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0757079124450684, "global_step": 472445, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9580825567245483, "global_step": 472446, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.026959180831909, "global_step": 472447, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1532559394836426, "global_step": 472448, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1533114910125732, "global_step": 472449, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.096245765686035, "global_step": 472450, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.061749219894409, "global_step": 472451, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1112208366394043, "global_step": 472452, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0623779296875, "global_step": 472453, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.047173500061035, "global_step": 472454, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0735504627227783, "global_step": 472455, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.121356725692749, "global_step": 472456, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.070598602294922, "global_step": 472457, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.081949234008789, "global_step": 472458, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9967460632324219, "global_step": 472459, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1238579750061035, "global_step": 472460, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0968594551086426, "global_step": 472461, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0824005603790283, "global_step": 472462, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.02034592628479, "global_step": 472463, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.131963014602661, "global_step": 472464, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.005873918533325, "global_step": 472465, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.05975341796875, "global_step": 472466, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1023612022399902, "global_step": 472467, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0092849731445312, "global_step": 472468, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.091020107269287, "global_step": 472469, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0813465118408203, "global_step": 472470, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.136085033416748, "global_step": 472471, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.060929536819458, "global_step": 472472, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.080967426300049, "global_step": 472473, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.008619546890259, "global_step": 472474, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.049039363861084, "global_step": 472475, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.151233673095703, "global_step": 472476, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0051729679107666, "global_step": 472477, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.060659170150757, "global_step": 472478, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0535943508148193, "global_step": 472479, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0313661098480225, "global_step": 472480, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.997558355331421, "global_step": 472481, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.047271490097046, "global_step": 472482, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0152831077575684, "global_step": 472483, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0176241397857666, "global_step": 472484, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0687718391418457, "global_step": 472485, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0748724937438965, "global_step": 472486, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0241763591766357, "global_step": 472487, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.073228359222412, "global_step": 472488, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0195703506469727, "global_step": 472489, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0099892616271973, "global_step": 472490, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.076911449432373, "global_step": 472491, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9793323278427124, "global_step": 472492, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.082864999771118, "global_step": 472493, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9714871644973755, "global_step": 472494, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0370826721191406, "global_step": 472495, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0982537269592285, "global_step": 472496, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0755975246429443, "global_step": 472497, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1244378089904785, "global_step": 472498, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0330147743225098, "global_step": 472499, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9717236757278442, "global_step": 472500, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.07283353805542, "global_step": 472501, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0262880325317383, "global_step": 472502, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0188233852386475, "global_step": 472503, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.141582727432251, "global_step": 472504, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1431586742401123, "global_step": 472505, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.026113271713257, "global_step": 472506, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.05558180809021, "global_step": 472507, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1584928035736084, "global_step": 472508, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0068540573120117, "global_step": 472509, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1018011569976807, "global_step": 472510, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.084298849105835, "global_step": 472511, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.009629249572754, "global_step": 472512, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.122657537460327, "global_step": 472513, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.068629503250122, "global_step": 472514, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0358502864837646, "global_step": 472515, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.979907751083374, "global_step": 472516, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1364150047302246, "global_step": 472517, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.019838333129883, "global_step": 472518, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0544707775115967, "global_step": 472519, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1070308685302734, "global_step": 472520, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.987914800643921, "global_step": 472521, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.106337547302246, "global_step": 472522, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0504379272460938, "global_step": 472523, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0443713665008545, "global_step": 472524, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0705127716064453, "global_step": 472525, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.157867670059204, "global_step": 472526, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0137908458709717, "global_step": 472527, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9846529960632324, "global_step": 472528, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.013871669769287, "global_step": 472529, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.04740047454834, "global_step": 472530, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0304253101348877, "global_step": 472531, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9756276607513428, "global_step": 472532, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0945370197296143, "global_step": 472533, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0590620040893555, "global_step": 472534, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.068297863006592, "global_step": 472535, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1022541522979736, "global_step": 472536, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0750250816345215, "global_step": 472537, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0616602897644043, "global_step": 472538, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.088301181793213, "global_step": 472539, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1002297401428223, "global_step": 472540, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.07069730758667, "global_step": 472541, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0597612857818604, "global_step": 472542, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0963854789733887, "global_step": 472543, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0891547203063965, "global_step": 472544, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.111725091934204, "global_step": 472545, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1118218898773193, "global_step": 472546, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0495877265930176, "global_step": 472547, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.041473627090454, "global_step": 472548, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.009117841720581, "global_step": 472549, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.103149890899658, "global_step": 472550, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.116771936416626, "global_step": 472551, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9712707996368408, "global_step": 472552, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.078856945037842, "global_step": 472553, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0489397048950195, "global_step": 472554, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.099937915802002, "global_step": 472555, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9507988691329956, "global_step": 472556, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0692076683044434, "global_step": 472557, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0734198093414307, "global_step": 472558, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0229074954986572, "global_step": 472559, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0644657611846924, "global_step": 472560, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.998814344406128, "global_step": 472561, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9499062299728394, "global_step": 472562, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.142437219619751, "global_step": 472563, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1087706089019775, "global_step": 472564, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0535953044891357, "global_step": 472565, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.066582441329956, "global_step": 472566, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0331404209136963, "global_step": 472567, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0610063076019287, "global_step": 472568, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1793200969696045, "global_step": 472569, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0939884185791016, "global_step": 472570, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0886359214782715, "global_step": 472571, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.053025007247925, "global_step": 472572, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1695199012756348, "global_step": 472573, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.115548610687256, "global_step": 472574, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.035733938217163, "global_step": 472575, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0307583808898926, "global_step": 472576, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.169339179992676, "global_step": 472577, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0276057720184326, "global_step": 472578, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0782854557037354, "global_step": 472579, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0753417015075684, "global_step": 472580, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.979374647140503, "global_step": 472581, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9991607666015625, "global_step": 472582, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.041229486465454, "global_step": 472583, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0858473777770996, "global_step": 472584, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0590193271636963, "global_step": 472585, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1218101978302, "global_step": 472586, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0018815994262695, "global_step": 472587, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1169159412384033, "global_step": 472588, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.954005479812622, "global_step": 472589, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0842485427856445, "global_step": 472590, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.135070562362671, "global_step": 472591, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.056398391723633, "global_step": 472592, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0207138061523438, "global_step": 472593, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.032064914703369, "global_step": 472594, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0184531211853027, "global_step": 472595, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0406696796417236, "global_step": 472596, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0849952697753906, "global_step": 472597, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0204954147338867, "global_step": 472598, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.019376277923584, "global_step": 472599, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.017665386199951, "global_step": 472600, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.083003520965576, "global_step": 472601, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.015521764755249, "global_step": 472602, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.122818946838379, "global_step": 472603, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0479304790496826, "global_step": 472604, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.041564702987671, "global_step": 472605, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1410329341888428, "global_step": 472606, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0950937271118164, "global_step": 472607, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.115154981613159, "global_step": 472608, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0366580486297607, "global_step": 472609, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.046701669692993, "global_step": 472610, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1238887310028076, "global_step": 472611, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1496846675872803, "global_step": 472612, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0910210609436035, "global_step": 472613, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.058602809906006, "global_step": 472614, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0655124187469482, "global_step": 472615, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.061194896697998, "global_step": 472616, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0910415649414062, "global_step": 472617, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.086652994155884, "global_step": 472618, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0338215827941895, "global_step": 472619, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.034395694732666, "global_step": 472620, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.073533535003662, "global_step": 472621, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1191821098327637, "global_step": 472622, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.041520357131958, "global_step": 472623, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1534101963043213, "global_step": 472624, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0789058208465576, "global_step": 472625, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0692105293273926, "global_step": 472626, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0700461864471436, "global_step": 472627, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0380849838256836, "global_step": 472628, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0400218963623047, "global_step": 472629, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1015005111694336, "global_step": 472630, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0028915405273438, "global_step": 472631, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0537478923797607, "global_step": 472632, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0960071086883545, "global_step": 472633, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1210062503814697, "global_step": 472634, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0879335403442383, "global_step": 472635, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9968338012695312, "global_step": 472636, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0514168739318848, "global_step": 472637, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9896316528320312, "global_step": 472638, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.006941556930542, "global_step": 472639, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1123783588409424, "global_step": 472640, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.187307596206665, "global_step": 472641, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0801548957824707, "global_step": 472642, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.121755599975586, "global_step": 472643, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.064812421798706, "global_step": 472644, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.097980499267578, "global_step": 472645, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0744378566741943, "global_step": 472646, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0026564598083496, "global_step": 472647, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.102656364440918, "global_step": 472648, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0538222789764404, "global_step": 472649, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1181068420410156, "global_step": 472650, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0896122455596924, "global_step": 472651, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.967545747756958, "global_step": 472652, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0934057235717773, "global_step": 472653, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.076117515563965, "global_step": 472654, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.024902820587158, "global_step": 472655, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0180211067199707, "global_step": 472656, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0434935092926025, "global_step": 472657, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.041067361831665, "global_step": 472658, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0392160415649414, "global_step": 472659, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0873701572418213, "global_step": 472660, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1241111755371094, "global_step": 472661, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0154712200164795, "global_step": 472662, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0538649559020996, "global_step": 472663, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.072835683822632, "global_step": 472664, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.094223976135254, "global_step": 472665, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0253894329071045, "global_step": 472666, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1481194496154785, "global_step": 472667, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0207769870758057, "global_step": 472668, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.046721935272217, "global_step": 472669, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9334863424301147, "global_step": 472670, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0459256172180176, "global_step": 472671, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.048811912536621, "global_step": 472672, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0304324626922607, "global_step": 472673, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.138761520385742, "global_step": 472674, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.131126880645752, "global_step": 472675, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.104830741882324, "global_step": 472676, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0976812839508057, "global_step": 472677, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.02028489112854, "global_step": 472678, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.037369728088379, "global_step": 472679, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.003307819366455, "global_step": 472680, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1358911991119385, "global_step": 472681, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.084373950958252, "global_step": 472682, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0616366863250732, "global_step": 472683, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0903546810150146, "global_step": 472684, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1243138313293457, "global_step": 472685, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0070414543151855, "global_step": 472686, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.156320095062256, "global_step": 472687, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1085152626037598, "global_step": 472688, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.067263603210449, "global_step": 472689, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.12019681930542, "global_step": 472690, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0438265800476074, "global_step": 472691, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0937209129333496, "global_step": 472692, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.038191318511963, "global_step": 472693, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1006603240966797, "global_step": 472694, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.04753041267395, "global_step": 472695, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.083037853240967, "global_step": 472696, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0398125648498535, "global_step": 472697, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.028618097305298, "global_step": 472698, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.066089630126953, "global_step": 472699, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1206517219543457, "global_step": 472700, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1219677925109863, "global_step": 472701, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9644029140472412, "global_step": 472702, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0619301795959473, "global_step": 472703, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1197152137756348, "global_step": 472704, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.091273307800293, "global_step": 472705, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0265917778015137, "global_step": 472706, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.993666648864746, "global_step": 472707, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.128937244415283, "global_step": 472708, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0162158012390137, "global_step": 472709, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0791666507720947, "global_step": 472710, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0873894691467285, "global_step": 472711, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1244544982910156, "global_step": 472712, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0459482669830322, "global_step": 472713, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0422539710998535, "global_step": 472714, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.014254570007324, "global_step": 472715, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0943214893341064, "global_step": 472716, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0467746257781982, "global_step": 472717, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.030125141143799, "global_step": 472718, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.091108798980713, "global_step": 472719, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1442391872406006, "global_step": 472720, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1488394737243652, "global_step": 472721, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9934927225112915, "global_step": 472722, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0784571170806885, "global_step": 472723, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.034097909927368, "global_step": 472724, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0576422214508057, "global_step": 472725, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0471463203430176, "global_step": 472726, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1174209117889404, "global_step": 472727, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.03493070602417, "global_step": 472728, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.143077850341797, "global_step": 472729, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.997191309928894, "global_step": 472730, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.075774908065796, "global_step": 472731, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0709011554718018, "global_step": 472732, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.110656499862671, "global_step": 472733, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1405746936798096, "global_step": 472734, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.108384132385254, "global_step": 472735, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1567647457122803, "global_step": 472736, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0831809043884277, "global_step": 472737, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.004183530807495, "global_step": 472738, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0963571071624756, "global_step": 472739, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0260729789733887, "global_step": 472740, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.008612871170044, "global_step": 472741, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.066749334335327, "global_step": 472742, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9899792671203613, "global_step": 472743, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9965260028839111, "global_step": 472744, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0985233783721924, "global_step": 472745, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.102229118347168, "global_step": 472746, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.096816301345825, "global_step": 472747, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.092266321182251, "global_step": 472748, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0802042484283447, "global_step": 472749, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0577495098114014, "global_step": 472750, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1149742603302, "global_step": 472751, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1167962551116943, "global_step": 472752, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.003685235977173, "global_step": 472753, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0997731685638428, "global_step": 472754, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.037630796432495, "global_step": 472755, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.023536443710327, "global_step": 472756, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9948570728302002, "global_step": 472757, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0549256801605225, "global_step": 472758, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.003661632537842, "global_step": 472759, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0594279766082764, "global_step": 472760, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1115763187408447, "global_step": 472761, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1247997283935547, "global_step": 472762, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.095763683319092, "global_step": 472763, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.089078426361084, "global_step": 472764, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.078463554382324, "global_step": 472765, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.079407215118408, "global_step": 472766, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9875515699386597, "global_step": 472767, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1204960346221924, "global_step": 472768, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0973222255706787, "global_step": 472769, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1266825199127197, "global_step": 472770, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.055126190185547, "global_step": 472771, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0574958324432373, "global_step": 472772, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1497862339019775, "global_step": 472773, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.094796895980835, "global_step": 472774, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9540516138076782, "global_step": 472775, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9826608896255493, "global_step": 472776, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0572874546051025, "global_step": 472777, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.033205509185791, "global_step": 472778, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0385537147521973, "global_step": 472779, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.10506534576416, "global_step": 472780, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.050967216491699, "global_step": 472781, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0833699703216553, "global_step": 472782, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.02030611038208, "global_step": 472783, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9813793897628784, "global_step": 472784, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1449923515319824, "global_step": 472785, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.072251081466675, "global_step": 472786, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1077589988708496, "global_step": 472787, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0437793731689453, "global_step": 472788, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1156461238861084, "global_step": 472789, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.075460433959961, "global_step": 472790, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.114006519317627, "global_step": 472791, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0294508934020996, "global_step": 472792, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1056759357452393, "global_step": 472793, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.089094400405884, "global_step": 472794, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0188040733337402, "global_step": 472795, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0728416442871094, "global_step": 472796, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0638315677642822, "global_step": 472797, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.054166793823242, "global_step": 472798, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0824594497680664, "global_step": 472799, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0921597480773926, "global_step": 472800, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9987503290176392, "global_step": 472801, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9659103155136108, "global_step": 472802, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1106150150299072, "global_step": 472803, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.109295606613159, "global_step": 472804, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.062053918838501, "global_step": 472805, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0955913066864014, "global_step": 472806, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1128337383270264, "global_step": 472807, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1155753135681152, "global_step": 472808, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.045004367828369, "global_step": 472809, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0673701763153076, "global_step": 472810, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0233190059661865, "global_step": 472811, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.068005323410034, "global_step": 472812, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0594189167022705, "global_step": 472813, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.067561149597168, "global_step": 472814, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1685822010040283, "global_step": 472815, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.130521774291992, "global_step": 472816, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.129746675491333, "global_step": 472817, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1166799068450928, "global_step": 472818, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0475575923919678, "global_step": 472819, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1196932792663574, "global_step": 472820, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0720536708831787, "global_step": 472821, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.046156406402588, "global_step": 472822, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.055307149887085, "global_step": 472823, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0989904403686523, "global_step": 472824, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.123739004135132, "global_step": 472825, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.03436017036438, "global_step": 472826, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9542427062988281, "global_step": 472827, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1023035049438477, "global_step": 472828, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.040747880935669, "global_step": 472829, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.08542537689209, "global_step": 472830, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1585237979888916, "global_step": 472831, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.989245891571045, "global_step": 472832, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1700124740600586, "global_step": 472833, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0938472747802734, "global_step": 472834, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0506856441497803, "global_step": 472835, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1084702014923096, "global_step": 472836, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.012040615081787, "global_step": 472837, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9602919816970825, "global_step": 472838, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.981896162033081, "global_step": 472839, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0658226013183594, "global_step": 472840, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.082538604736328, "global_step": 472841, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.052316188812256, "global_step": 472842, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.029106616973877, "global_step": 472843, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.091284990310669, "global_step": 472844, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0848617553710938, "global_step": 472845, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0882081985473633, "global_step": 472846, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0660266876220703, "global_step": 472847, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1127872467041016, "global_step": 472848, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9828404188156128, "global_step": 472849, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.091916561126709, "global_step": 472850, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0426223278045654, "global_step": 472851, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0614230632781982, "global_step": 472852, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0153424739837646, "global_step": 472853, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0890610218048096, "global_step": 472854, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.038572311401367, "global_step": 472855, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.018892526626587, "global_step": 472856, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.105853319168091, "global_step": 472857, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0719902515411377, "global_step": 472858, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.157849073410034, "global_step": 472859, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1454951763153076, "global_step": 472860, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0138790607452393, "global_step": 472861, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0353291034698486, "global_step": 472862, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.047163486480713, "global_step": 472863, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0685181617736816, "global_step": 472864, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0395333766937256, "global_step": 472865, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.066985845565796, "global_step": 472866, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1207587718963623, "global_step": 472867, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.062455415725708, "global_step": 472868, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1725428104400635, "global_step": 472869, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.046515941619873, "global_step": 472870, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.044095516204834, "global_step": 472871, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.099174976348877, "global_step": 472872, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.025205612182617, "global_step": 472873, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.036323308944702, "global_step": 472874, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9897910356521606, "global_step": 472875, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.186361312866211, "global_step": 472876, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0597872734069824, "global_step": 472877, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.062236785888672, "global_step": 472878, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9803745746612549, "global_step": 472879, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0381357669830322, "global_step": 472880, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.017732620239258, "global_step": 472881, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.024456262588501, "global_step": 472882, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1014623641967773, "global_step": 472883, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0645360946655273, "global_step": 472884, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.126508951187134, "global_step": 472885, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.167912244796753, "global_step": 472886, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0715479850769043, "global_step": 472887, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0638341903686523, "global_step": 472888, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.003826379776001, "global_step": 472889, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1136372089385986, "global_step": 472890, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0344583988189697, "global_step": 472891, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1311910152435303, "global_step": 472892, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.2044873237609863, "global_step": 472893, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.009632110595703, "global_step": 472894, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.091550827026367, "global_step": 472895, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0295028686523438, "global_step": 472896, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.092440366744995, "global_step": 472897, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0488545894622803, "global_step": 472898, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.006490707397461, "global_step": 472899, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9489405155181885, "global_step": 472900, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0485610961914062, "global_step": 472901, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.132260799407959, "global_step": 472902, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.036165475845337, "global_step": 472903, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.049151659011841, "global_step": 472904, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.096189022064209, "global_step": 472905, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0402350425720215, "global_step": 472906, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1139628887176514, "global_step": 472907, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.139662265777588, "global_step": 472908, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.049786329269409, "global_step": 472909, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.014892578125, "global_step": 472910, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0825297832489014, "global_step": 472911, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0024149417877197, "global_step": 472912, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1125481128692627, "global_step": 472913, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.095459222793579, "global_step": 472914, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0761775970458984, "global_step": 472915, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9593307971954346, "global_step": 472916, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1235363483428955, "global_step": 472917, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.121520519256592, "global_step": 472918, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1515495777130127, "global_step": 472919, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1084201335906982, "global_step": 472920, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.076023578643799, "global_step": 472921, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0703682899475098, "global_step": 472922, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.184351682662964, "global_step": 472923, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0536158084869385, "global_step": 472924, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.040266752243042, "global_step": 472925, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.079375982284546, "global_step": 472926, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1207315921783447, "global_step": 472927, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.05155086517334, "global_step": 472928, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1297669410705566, "global_step": 472929, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.080070972442627, "global_step": 472930, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.081399917602539, "global_step": 472931, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1059954166412354, "global_step": 472932, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.055185079574585, "global_step": 472933, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.049999952316284, "global_step": 472934, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0872230529785156, "global_step": 472935, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1022820472717285, "global_step": 472936, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.084993839263916, "global_step": 472937, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0891079902648926, "global_step": 472938, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.061650276184082, "global_step": 472939, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0208635330200195, "global_step": 472940, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1056413650512695, "global_step": 472941, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.133491039276123, "global_step": 472942, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.155585765838623, "global_step": 472943, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0985002517700195, "global_step": 472944, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1119003295898438, "global_step": 472945, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1132009029388428, "global_step": 472946, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0397839546203613, "global_step": 472947, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0693600177764893, "global_step": 472948, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1021716594696045, "global_step": 472949, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0873641967773438, "global_step": 472950, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1091837882995605, "global_step": 472951, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9724427461624146, "global_step": 472952, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.051079034805298, "global_step": 472953, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.982417106628418, "global_step": 472954, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0808236598968506, "global_step": 472955, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.011104106903076, "global_step": 472956, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0693626403808594, "global_step": 472957, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.050762176513672, "global_step": 472958, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0325043201446533, "global_step": 472959, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.111243963241577, "global_step": 472960, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.152146100997925, "global_step": 472961, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.051750421524048, "global_step": 472962, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9782700538635254, "global_step": 472963, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0869717597961426, "global_step": 472964, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0694351196289062, "global_step": 472965, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.069343328475952, "global_step": 472966, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0694684982299805, "global_step": 472967, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1048381328582764, "global_step": 472968, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0895543098449707, "global_step": 472969, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0127170085906982, "global_step": 472970, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.102349281311035, "global_step": 472971, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0705902576446533, "global_step": 472972, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0348610877990723, "global_step": 472973, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.15752911567688, "global_step": 472974, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.024707317352295, "global_step": 472975, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.169088363647461, "global_step": 472976, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0658061504364014, "global_step": 472977, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.023669481277466, "global_step": 472978, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0780675411224365, "global_step": 472979, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.06489634513855, "global_step": 472980, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.001770257949829, "global_step": 472981, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.057645559310913, "global_step": 472982, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.07446551322937, "global_step": 472983, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.117738723754883, "global_step": 472984, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0790348052978516, "global_step": 472985, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.095151901245117, "global_step": 472986, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0372931957244873, "global_step": 472987, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.037766933441162, "global_step": 472988, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1063175201416016, "global_step": 472989, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.066800117492676, "global_step": 472990, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0343801975250244, "global_step": 472991, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0859153270721436, "global_step": 472992, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0395138263702393, "global_step": 472993, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.038182020187378, "global_step": 472994, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0060980319976807, "global_step": 472995, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.055638551712036, "global_step": 472996, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1031737327575684, "global_step": 472997, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.1225943565368652, "global_step": 472998, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0342366695404053, "global_step": 472999, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.032111167907715, "global_step": 473000, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9819616079330444, "global_step": 473001, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0297374725341797, "global_step": 473002, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.0541560649871826, "global_step": 473003, "epoch": 837, "lr": 5e-05}
{"train_loss": 2.063997983932495, "global_step": 473004, "epoch": 837, "lr": 5e-05}
{"train_loss": 1.9911527633666992, "global_step": 473005, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1140708923339844, "global_step": 473006, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0461044311523438, "global_step": 473007, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.044794797897339, "global_step": 473008, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.126629590988159, "global_step": 473009, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.034982919692993, "global_step": 473010, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.026078939437866, "global_step": 473011, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.124859094619751, "global_step": 473012, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.999263048171997, "global_step": 473013, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0320448875427246, "global_step": 473014, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0037105083465576, "global_step": 473015, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.031670093536377, "global_step": 473016, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0020344257354736, "global_step": 473017, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0595993995666504, "global_step": 473018, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.117457389831543, "global_step": 473019, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1745598316192627, "global_step": 473020, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.077714443206787, "global_step": 473021, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0302295684814453, "global_step": 473022, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.095268726348877, "global_step": 473023, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0579633712768555, "global_step": 473024, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0400233268737793, "global_step": 473025, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0793185234069824, "global_step": 473026, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.050956964492798, "global_step": 473027, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.058609962463379, "global_step": 473028, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9829603433609009, "global_step": 473029, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.01413893699646, "global_step": 473030, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.042766571044922, "global_step": 473031, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1332476139068604, "global_step": 473032, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0354390144348145, "global_step": 473033, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.106571912765503, "global_step": 473034, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0476577281951904, "global_step": 473035, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1388063430786133, "global_step": 473036, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.039936065673828, "global_step": 473037, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.014922857284546, "global_step": 473038, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0171754360198975, "global_step": 473039, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0918679237365723, "global_step": 473040, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0880696773529053, "global_step": 473041, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0290744304656982, "global_step": 473042, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9797252416610718, "global_step": 473043, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.103541612625122, "global_step": 473044, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.030836582183838, "global_step": 473045, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0911262035369873, "global_step": 473046, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.040788412094116, "global_step": 473047, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.07059383392334, "global_step": 473048, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0491108894348145, "global_step": 473049, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1561594009399414, "global_step": 473050, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.089723587036133, "global_step": 473051, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0981030464172363, "global_step": 473052, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0654513835906982, "global_step": 473053, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0233829021453857, "global_step": 473054, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.062542676925659, "global_step": 473055, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.04042911529541, "global_step": 473056, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0021047592163086, "global_step": 473057, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1333446502685547, "global_step": 473058, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9543870687484741, "global_step": 473059, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.001584053039551, "global_step": 473060, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.106750965118408, "global_step": 473061, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0493149757385254, "global_step": 473062, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0917556285858154, "global_step": 473063, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1158525943756104, "global_step": 473064, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9402049779891968, "global_step": 473065, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0615100860595703, "global_step": 473066, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.109168529510498, "global_step": 473067, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0491507053375244, "global_step": 473068, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9666045904159546, "global_step": 473069, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0162205696105957, "global_step": 473070, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0912108421325684, "global_step": 473071, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0896639823913574, "global_step": 473072, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.01802396774292, "global_step": 473073, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0305676460266113, "global_step": 473074, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.094025135040283, "global_step": 473075, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1305153369903564, "global_step": 473076, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0544517040252686, "global_step": 473077, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.038980484008789, "global_step": 473078, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.999612808227539, "global_step": 473079, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0822043418884277, "global_step": 473080, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0556249618530273, "global_step": 473081, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0621955394744873, "global_step": 473082, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9924410581588745, "global_step": 473083, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9832707643508911, "global_step": 473084, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.045706033706665, "global_step": 473085, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0083067417144775, "global_step": 473086, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.025705337524414, "global_step": 473087, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1060280799865723, "global_step": 473088, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0746724605560303, "global_step": 473089, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.049936294555664, "global_step": 473090, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1588032245635986, "global_step": 473091, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0411856174468994, "global_step": 473092, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.000450372695923, "global_step": 473093, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0084757804870605, "global_step": 473094, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9894436597824097, "global_step": 473095, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.047995090484619, "global_step": 473096, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0381381511688232, "global_step": 473097, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9802565574645996, "global_step": 473098, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.10467791557312, "global_step": 473099, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.093431234359741, "global_step": 473100, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.123058557510376, "global_step": 473101, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1220314502716064, "global_step": 473102, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.107367515563965, "global_step": 473103, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0159525871276855, "global_step": 473104, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.065162420272827, "global_step": 473105, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0364909172058105, "global_step": 473106, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0738987922668457, "global_step": 473107, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0095088481903076, "global_step": 473108, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9259934425354004, "global_step": 473109, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0259597301483154, "global_step": 473110, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.049872636795044, "global_step": 473111, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9833968877792358, "global_step": 473112, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0392773151397705, "global_step": 473113, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.072744846343994, "global_step": 473114, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.078688383102417, "global_step": 473115, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.064525604248047, "global_step": 473116, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0597763061523438, "global_step": 473117, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9844529628753662, "global_step": 473118, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1072940826416016, "global_step": 473119, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.023932695388794, "global_step": 473120, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0177998542785645, "global_step": 473121, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.972708821296692, "global_step": 473122, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.094276189804077, "global_step": 473123, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9983241558074951, "global_step": 473124, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0851006507873535, "global_step": 473125, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1347129344940186, "global_step": 473126, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.964360237121582, "global_step": 473127, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9782865047454834, "global_step": 473128, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.060532331466675, "global_step": 473129, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.072505474090576, "global_step": 473130, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.065209150314331, "global_step": 473131, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.101224184036255, "global_step": 473132, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0282156467437744, "global_step": 473133, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.104081153869629, "global_step": 473134, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0760133266448975, "global_step": 473135, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0511386394500732, "global_step": 473136, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.061382532119751, "global_step": 473137, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1681931018829346, "global_step": 473138, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.01092529296875, "global_step": 473139, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0827839374542236, "global_step": 473140, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0273029804229736, "global_step": 473141, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0091333389282227, "global_step": 473142, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0753519535064697, "global_step": 473143, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0951485633850098, "global_step": 473144, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.091038465499878, "global_step": 473145, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9795273542404175, "global_step": 473146, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1023926734924316, "global_step": 473147, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.064112424850464, "global_step": 473148, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0468122959136963, "global_step": 473149, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.989929437637329, "global_step": 473150, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.072585344314575, "global_step": 473151, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.064932346343994, "global_step": 473152, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9878443479537964, "global_step": 473153, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0866522789001465, "global_step": 473154, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.103067636489868, "global_step": 473155, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0774827003479004, "global_step": 473156, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0303869247436523, "global_step": 473157, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9801220893859863, "global_step": 473158, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1164822578430176, "global_step": 473159, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0935206413269043, "global_step": 473160, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0975241661071777, "global_step": 473161, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.084249258041382, "global_step": 473162, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0756962299346924, "global_step": 473163, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.083481550216675, "global_step": 473164, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0141212940216064, "global_step": 473165, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.059953451156616, "global_step": 473166, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.991432785987854, "global_step": 473167, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.073776960372925, "global_step": 473168, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.122739315032959, "global_step": 473169, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0521740913391113, "global_step": 473170, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.08039927482605, "global_step": 473171, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.000386953353882, "global_step": 473172, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1106507778167725, "global_step": 473173, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.015209436416626, "global_step": 473174, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.043567419052124, "global_step": 473175, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0669124126434326, "global_step": 473176, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0345678329467773, "global_step": 473177, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.116550922393799, "global_step": 473178, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0869810581207275, "global_step": 473179, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0458154678344727, "global_step": 473180, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.945090889930725, "global_step": 473181, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1570396423339844, "global_step": 473182, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0036110877990723, "global_step": 473183, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0678486824035645, "global_step": 473184, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.082822322845459, "global_step": 473185, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1321938037872314, "global_step": 473186, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0732781887054443, "global_step": 473187, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.076690435409546, "global_step": 473188, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1306378841400146, "global_step": 473189, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.048179864883423, "global_step": 473190, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.002251386642456, "global_step": 473191, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.044476270675659, "global_step": 473192, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0469913482666016, "global_step": 473193, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0854904651641846, "global_step": 473194, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9599931240081787, "global_step": 473195, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.014014720916748, "global_step": 473196, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.055638074874878, "global_step": 473197, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0221755504608154, "global_step": 473198, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0251448154449463, "global_step": 473199, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.151538372039795, "global_step": 473200, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0392541885375977, "global_step": 473201, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1471047401428223, "global_step": 473202, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.034247636795044, "global_step": 473203, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.008280038833618, "global_step": 473204, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0725338459014893, "global_step": 473205, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9996956586837769, "global_step": 473206, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0319883823394775, "global_step": 473207, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1211318969726562, "global_step": 473208, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0997190475463867, "global_step": 473209, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.096174716949463, "global_step": 473210, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0793941020965576, "global_step": 473211, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1066954135894775, "global_step": 473212, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0641849040985107, "global_step": 473213, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0724759101867676, "global_step": 473214, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.030684232711792, "global_step": 473215, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0118324756622314, "global_step": 473216, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9961811304092407, "global_step": 473217, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.241023063659668, "global_step": 473218, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.08609938621521, "global_step": 473219, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1504030227661133, "global_step": 473220, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0795633792877197, "global_step": 473221, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0557429790496826, "global_step": 473222, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.06853985786438, "global_step": 473223, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.043916940689087, "global_step": 473224, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0767881870269775, "global_step": 473225, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.118842601776123, "global_step": 473226, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0006392002105713, "global_step": 473227, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1003918647766113, "global_step": 473228, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0709168910980225, "global_step": 473229, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.075376272201538, "global_step": 473230, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.077439546585083, "global_step": 473231, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.102360486984253, "global_step": 473232, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.022069215774536, "global_step": 473233, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.109292984008789, "global_step": 473234, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0651333332061768, "global_step": 473235, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0462422370910645, "global_step": 473236, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0857369899749756, "global_step": 473237, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0789787769317627, "global_step": 473238, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.138667583465576, "global_step": 473239, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0208911895751953, "global_step": 473240, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.10156512260437, "global_step": 473241, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0326225757598877, "global_step": 473242, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0364437103271484, "global_step": 473243, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0870165824890137, "global_step": 473244, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.14910626411438, "global_step": 473245, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.07542085647583, "global_step": 473246, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9374408721923828, "global_step": 473247, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.031219720840454, "global_step": 473248, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.025113344192505, "global_step": 473249, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0439021587371826, "global_step": 473250, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.064570426940918, "global_step": 473251, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0977871417999268, "global_step": 473252, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.025294780731201, "global_step": 473253, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.010162115097046, "global_step": 473254, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.081615686416626, "global_step": 473255, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0753135681152344, "global_step": 473256, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0301294326782227, "global_step": 473257, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1032934188842773, "global_step": 473258, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0540568828582764, "global_step": 473259, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.060161590576172, "global_step": 473260, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.113084077835083, "global_step": 473261, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.078036069869995, "global_step": 473262, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0930275917053223, "global_step": 473263, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9596068859100342, "global_step": 473264, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9891927242279053, "global_step": 473265, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0173897743225098, "global_step": 473266, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.065354347229004, "global_step": 473267, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0328309535980225, "global_step": 473268, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.070162534713745, "global_step": 473269, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0697617530822754, "global_step": 473270, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.076639413833618, "global_step": 473271, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9973176717758179, "global_step": 473272, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0581462383270264, "global_step": 473273, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.098055124282837, "global_step": 473274, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.115647077560425, "global_step": 473275, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9674410820007324, "global_step": 473276, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1092276573181152, "global_step": 473277, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1156623363494873, "global_step": 473278, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.042551279067993, "global_step": 473279, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0622968673706055, "global_step": 473280, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.026224374771118, "global_step": 473281, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1038362979888916, "global_step": 473282, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1505563259124756, "global_step": 473283, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0305168628692627, "global_step": 473284, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0550413131713867, "global_step": 473285, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.998157262802124, "global_step": 473286, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0495591163635254, "global_step": 473287, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0590360164642334, "global_step": 473288, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9964712858200073, "global_step": 473289, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0454022884368896, "global_step": 473290, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0863683223724365, "global_step": 473291, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0677056312561035, "global_step": 473292, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9624924659729004, "global_step": 473293, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.048673629760742, "global_step": 473294, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.050269603729248, "global_step": 473295, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0338985919952393, "global_step": 473296, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9932986497879028, "global_step": 473297, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0935826301574707, "global_step": 473298, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.02960467338562, "global_step": 473299, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1502957344055176, "global_step": 473300, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.056551694869995, "global_step": 473301, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0267088413238525, "global_step": 473302, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.103252649307251, "global_step": 473303, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1936981678009033, "global_step": 473304, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0218734741210938, "global_step": 473305, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0282585620880127, "global_step": 473306, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.138521194458008, "global_step": 473307, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0362002849578857, "global_step": 473308, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0369625091552734, "global_step": 473309, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.075028657913208, "global_step": 473310, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.038802146911621, "global_step": 473311, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.062012195587158, "global_step": 473312, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0391032695770264, "global_step": 473313, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.139533758163452, "global_step": 473314, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.082583427429199, "global_step": 473315, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.005676507949829, "global_step": 473316, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.155881643295288, "global_step": 473317, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.079220771789551, "global_step": 473318, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1515560150146484, "global_step": 473319, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0176913738250732, "global_step": 473320, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.958046793937683, "global_step": 473321, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9824355840682983, "global_step": 473322, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9990687370300293, "global_step": 473323, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.016890287399292, "global_step": 473324, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1346898078918457, "global_step": 473325, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.100315570831299, "global_step": 473326, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0686745643615723, "global_step": 473327, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.117868661880493, "global_step": 473328, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.022392749786377, "global_step": 473329, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9804587364196777, "global_step": 473330, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1378705501556396, "global_step": 473331, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.144467830657959, "global_step": 473332, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0245378017425537, "global_step": 473333, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.071455478668213, "global_step": 473334, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.09643292427063, "global_step": 473335, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.072260618209839, "global_step": 473336, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.011092185974121, "global_step": 473337, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.995561122894287, "global_step": 473338, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.083714246749878, "global_step": 473339, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.058527946472168, "global_step": 473340, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.089292526245117, "global_step": 473341, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0429112911224365, "global_step": 473342, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0627689361572266, "global_step": 473343, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0857510566711426, "global_step": 473344, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.017059087753296, "global_step": 473345, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.051891803741455, "global_step": 473346, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.057671308517456, "global_step": 473347, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.049361228942871, "global_step": 473348, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0965516567230225, "global_step": 473349, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.013394832611084, "global_step": 473350, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9853734970092773, "global_step": 473351, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9907736778259277, "global_step": 473352, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.047877550125122, "global_step": 473353, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0558457374572754, "global_step": 473354, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0646891593933105, "global_step": 473355, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0202603340148926, "global_step": 473356, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.098421335220337, "global_step": 473357, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.030517339706421, "global_step": 473358, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0493602752685547, "global_step": 473359, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.978226900100708, "global_step": 473360, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1358447074890137, "global_step": 473361, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0404927730560303, "global_step": 473362, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1521127223968506, "global_step": 473363, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.103900671005249, "global_step": 473364, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.070280075073242, "global_step": 473365, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.008246660232544, "global_step": 473366, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.058673858642578, "global_step": 473367, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.028928518295288, "global_step": 473368, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0140984058380127, "global_step": 473369, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.120136260986328, "global_step": 473370, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.173600673675537, "global_step": 473371, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0876801013946533, "global_step": 473372, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.030855417251587, "global_step": 473373, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0753087997436523, "global_step": 473374, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0672409534454346, "global_step": 473375, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.099123239517212, "global_step": 473376, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.00329327583313, "global_step": 473377, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0840983390808105, "global_step": 473378, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.027608633041382, "global_step": 473379, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.099531888961792, "global_step": 473380, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1487810611724854, "global_step": 473381, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0244011878967285, "global_step": 473382, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0784478187561035, "global_step": 473383, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.02982234954834, "global_step": 473384, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0633885860443115, "global_step": 473385, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0488529205322266, "global_step": 473386, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0156338214874268, "global_step": 473387, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.057318925857544, "global_step": 473388, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0340869426727295, "global_step": 473389, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1073966026306152, "global_step": 473390, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0096004009246826, "global_step": 473391, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0115158557891846, "global_step": 473392, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0633046627044678, "global_step": 473393, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.094712734222412, "global_step": 473394, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.073115110397339, "global_step": 473395, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0610482692718506, "global_step": 473396, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.106257200241089, "global_step": 473397, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0637893676757812, "global_step": 473398, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.10361385345459, "global_step": 473399, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0006396770477295, "global_step": 473400, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.124922752380371, "global_step": 473401, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0591981410980225, "global_step": 473402, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0778050422668457, "global_step": 473403, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.032052516937256, "global_step": 473404, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.054572343826294, "global_step": 473405, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0340871810913086, "global_step": 473406, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.030971050262451, "global_step": 473407, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0486667156219482, "global_step": 473408, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1336777210235596, "global_step": 473409, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.04468035697937, "global_step": 473410, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.034569501876831, "global_step": 473411, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0484349727630615, "global_step": 473412, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.028634548187256, "global_step": 473413, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0357723236083984, "global_step": 473414, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0636322498321533, "global_step": 473415, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.018731117248535, "global_step": 473416, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.070333242416382, "global_step": 473417, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1174216270446777, "global_step": 473418, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.091770887374878, "global_step": 473419, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.146024703979492, "global_step": 473420, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0258398056030273, "global_step": 473421, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0183794498443604, "global_step": 473422, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9374498128890991, "global_step": 473423, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0960278511047363, "global_step": 473424, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.05159330368042, "global_step": 473425, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.066786289215088, "global_step": 473426, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0975396633148193, "global_step": 473427, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0774717330932617, "global_step": 473428, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.053884506225586, "global_step": 473429, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.105440855026245, "global_step": 473430, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1037538051605225, "global_step": 473431, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.097421646118164, "global_step": 473432, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0453999042510986, "global_step": 473433, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9943270683288574, "global_step": 473434, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0447280406951904, "global_step": 473435, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1194210052490234, "global_step": 473436, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0288803577423096, "global_step": 473437, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.062183380126953, "global_step": 473438, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0701606273651123, "global_step": 473439, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1143882274627686, "global_step": 473440, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.001030445098877, "global_step": 473441, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1199185848236084, "global_step": 473442, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.072706699371338, "global_step": 473443, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1063849925994873, "global_step": 473444, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.007627248764038, "global_step": 473445, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1002919673919678, "global_step": 473446, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.015871286392212, "global_step": 473447, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0255911350250244, "global_step": 473448, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1597015857696533, "global_step": 473449, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0611515045166016, "global_step": 473450, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.081132411956787, "global_step": 473451, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0101423263549805, "global_step": 473452, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.089188814163208, "global_step": 473453, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0278680324554443, "global_step": 473454, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0350468158721924, "global_step": 473455, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.110795259475708, "global_step": 473456, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0856897830963135, "global_step": 473457, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.061131000518799, "global_step": 473458, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9818062782287598, "global_step": 473459, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.008054733276367, "global_step": 473460, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1071834564208984, "global_step": 473461, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.003046751022339, "global_step": 473462, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9804654121398926, "global_step": 473463, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0848891735076904, "global_step": 473464, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0946826934814453, "global_step": 473465, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.096940279006958, "global_step": 473466, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.121903419494629, "global_step": 473467, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9565186500549316, "global_step": 473468, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0805656909942627, "global_step": 473469, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.035332441329956, "global_step": 473470, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.110509157180786, "global_step": 473471, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.108952760696411, "global_step": 473472, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.2287497520446777, "global_step": 473473, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.062429189682007, "global_step": 473474, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0793142318725586, "global_step": 473475, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1030502319335938, "global_step": 473476, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.039094924926758, "global_step": 473477, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.190516948699951, "global_step": 473478, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.020458221435547, "global_step": 473479, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.07234263420105, "global_step": 473480, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.128265619277954, "global_step": 473481, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.081730365753174, "global_step": 473482, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.092987060546875, "global_step": 473483, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.116589069366455, "global_step": 473484, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0277063846588135, "global_step": 473485, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.086167812347412, "global_step": 473486, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0373098850250244, "global_step": 473487, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.073258638381958, "global_step": 473488, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.073906183242798, "global_step": 473489, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0295841693878174, "global_step": 473490, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.054779052734375, "global_step": 473491, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9926581382751465, "global_step": 473492, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.060823678970337, "global_step": 473493, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0209178924560547, "global_step": 473494, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0372135639190674, "global_step": 473495, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.007988214492798, "global_step": 473496, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.065251588821411, "global_step": 473497, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0588021278381348, "global_step": 473498, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0108087062835693, "global_step": 473499, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0785880088806152, "global_step": 473500, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0891671180725098, "global_step": 473501, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0914762020111084, "global_step": 473502, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.072751760482788, "global_step": 473503, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0926122665405273, "global_step": 473504, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1023287773132324, "global_step": 473505, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1215648651123047, "global_step": 473506, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0662407875061035, "global_step": 473507, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.055326461791992, "global_step": 473508, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1030266284942627, "global_step": 473509, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0688209533691406, "global_step": 473510, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1011226177215576, "global_step": 473511, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.086848497390747, "global_step": 473512, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1608376502990723, "global_step": 473513, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.057792901992798, "global_step": 473514, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0730834007263184, "global_step": 473515, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.988147258758545, "global_step": 473516, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0666472911834717, "global_step": 473517, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0667104721069336, "global_step": 473518, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1039726734161377, "global_step": 473519, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0243797302246094, "global_step": 473520, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.095287799835205, "global_step": 473521, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0995523929595947, "global_step": 473522, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0181989669799805, "global_step": 473523, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0794878005981445, "global_step": 473524, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.085862874984741, "global_step": 473525, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1194610595703125, "global_step": 473526, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0552685260772705, "global_step": 473527, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.054013252258301, "global_step": 473528, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.085557222366333, "global_step": 473529, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.169084072113037, "global_step": 473530, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9985054731369019, "global_step": 473531, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.046578884124756, "global_step": 473532, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0811142921447754, "global_step": 473533, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0525124073028564, "global_step": 473534, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0456085205078125, "global_step": 473535, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.089142084121704, "global_step": 473536, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1679370403289795, "global_step": 473537, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1091158390045166, "global_step": 473538, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.094101905822754, "global_step": 473539, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.10850191116333, "global_step": 473540, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.062964677810669, "global_step": 473541, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.078129529953003, "global_step": 473542, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.033174991607666, "global_step": 473543, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0393073558807373, "global_step": 473544, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1038999557495117, "global_step": 473545, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0868804454803467, "global_step": 473546, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9704333543777466, "global_step": 473547, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.079152822494507, "global_step": 473548, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.005549669265747, "global_step": 473549, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.214578866958618, "global_step": 473550, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0257837772369385, "global_step": 473551, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.017204761505127, "global_step": 473552, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0835154056549072, "global_step": 473553, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9733980894088745, "global_step": 473554, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.089876651763916, "global_step": 473555, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9724767208099365, "global_step": 473556, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1478350162506104, "global_step": 473557, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9967788457870483, "global_step": 473558, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.070983648300171, "global_step": 473559, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9589147567749023, "global_step": 473560, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0659046173095703, "global_step": 473561, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.14951753616333, "global_step": 473562, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.066143035888672, "global_step": 473563, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0495290756225586, "global_step": 473564, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.056891918182373, "global_step": 473565, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0566306114196777, "global_step": 473566, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0197489261627197, "global_step": 473567, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.088951826095581, "global_step": 473568, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.147106409072876, "global_step": 473569, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.110926389694214, "global_step": 473570, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.038017511367798, "global_step": 473571, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9915695190429688, "global_step": 473572, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0827715396881104, "global_step": 473573, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0343668460845947, "global_step": 473574, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0421299934387207, "global_step": 473575, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0079588890075684, "global_step": 473576, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.029442548751831, "global_step": 473577, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.062479019165039, "global_step": 473578, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.047572135925293, "global_step": 473579, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.096956968307495, "global_step": 473580, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0512144565582275, "global_step": 473581, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.102983236312866, "global_step": 473582, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.017421245574951, "global_step": 473583, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9867171049118042, "global_step": 473584, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0299439430236816, "global_step": 473585, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.049699068069458, "global_step": 473586, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0795435905456543, "global_step": 473587, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.191416025161743, "global_step": 473588, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9810898303985596, "global_step": 473589, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0688552856445312, "global_step": 473590, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0186846256256104, "global_step": 473591, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1409752368927, "global_step": 473592, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.057098150253296, "global_step": 473593, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0558903217315674, "global_step": 473594, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.052459478378296, "global_step": 473595, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0116097927093506, "global_step": 473596, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.099809169769287, "global_step": 473597, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.041959285736084, "global_step": 473598, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0686070919036865, "global_step": 473599, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.019188165664673, "global_step": 473600, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0091805458068848, "global_step": 473601, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0573415756225586, "global_step": 473602, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1104719638824463, "global_step": 473603, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0582990646362305, "global_step": 473604, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.061662435531616, "global_step": 473605, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.013237476348877, "global_step": 473606, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0986974239349365, "global_step": 473607, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.97953462600708, "global_step": 473608, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.07204532623291, "global_step": 473609, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.97866690158844, "global_step": 473610, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.092074394226074, "global_step": 473611, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9889297485351562, "global_step": 473612, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.044027805328369, "global_step": 473613, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0100865364074707, "global_step": 473614, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.053562879562378, "global_step": 473615, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.001110792160034, "global_step": 473616, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.060539960861206, "global_step": 473617, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9779835939407349, "global_step": 473618, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0806050300598145, "global_step": 473619, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.127729654312134, "global_step": 473620, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0575006008148193, "global_step": 473621, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.065864324569702, "global_step": 473622, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.094085454940796, "global_step": 473623, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.013615608215332, "global_step": 473624, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.00748872756958, "global_step": 473625, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0434036254882812, "global_step": 473626, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.04903507232666, "global_step": 473627, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.057839870452881, "global_step": 473628, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.111339807510376, "global_step": 473629, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.102997303009033, "global_step": 473630, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.16646146774292, "global_step": 473631, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0395395755767822, "global_step": 473632, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.076918601989746, "global_step": 473633, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.037477970123291, "global_step": 473634, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0133609771728516, "global_step": 473635, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.13250470161438, "global_step": 473636, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0853121280670166, "global_step": 473637, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.129791736602783, "global_step": 473638, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0283548831939697, "global_step": 473639, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.063504695892334, "global_step": 473640, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0524728298187256, "global_step": 473641, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9735326766967773, "global_step": 473642, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.072998523712158, "global_step": 473643, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0100901126861572, "global_step": 473644, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9553433656692505, "global_step": 473645, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.035266637802124, "global_step": 473646, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.093209981918335, "global_step": 473647, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0760855674743652, "global_step": 473648, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0626790523529053, "global_step": 473649, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0766453742980957, "global_step": 473650, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.084500551223755, "global_step": 473651, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.026581287384033, "global_step": 473652, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0925726890563965, "global_step": 473653, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.047866106033325, "global_step": 473654, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0802392959594727, "global_step": 473655, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9795408248901367, "global_step": 473656, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0608608722686768, "global_step": 473657, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.131664276123047, "global_step": 473658, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1163506507873535, "global_step": 473659, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0569393634796143, "global_step": 473660, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.136273145675659, "global_step": 473661, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.974789023399353, "global_step": 473662, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0468387603759766, "global_step": 473663, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.99484121799469, "global_step": 473664, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9898319244384766, "global_step": 473665, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0442237854003906, "global_step": 473666, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1550452709198, "global_step": 473667, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0494213104248047, "global_step": 473668, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0528156757354736, "global_step": 473669, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0862784385681152, "global_step": 473670, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.005667209625244, "global_step": 473671, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0921785831451416, "global_step": 473672, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0525903701782227, "global_step": 473673, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0892069339752197, "global_step": 473674, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.078974485397339, "global_step": 473675, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0536539554595947, "global_step": 473676, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.076889991760254, "global_step": 473677, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.102158784866333, "global_step": 473678, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.068591594696045, "global_step": 473679, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.049027919769287, "global_step": 473680, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.02730655670166, "global_step": 473681, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0873801708221436, "global_step": 473682, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.096407175064087, "global_step": 473683, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0820682048797607, "global_step": 473684, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.089397668838501, "global_step": 473685, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0954744815826416, "global_step": 473686, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0620908737182617, "global_step": 473687, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0457208156585693, "global_step": 473688, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0544557571411133, "global_step": 473689, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9767199754714966, "global_step": 473690, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.091035842895508, "global_step": 473691, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0584633350372314, "global_step": 473692, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1004793643951416, "global_step": 473693, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.131814956665039, "global_step": 473694, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0784900188446045, "global_step": 473695, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0049421787261963, "global_step": 473696, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1155149936676025, "global_step": 473697, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.03029203414917, "global_step": 473698, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0118274688720703, "global_step": 473699, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0660672187805176, "global_step": 473700, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.147063970565796, "global_step": 473701, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1429014205932617, "global_step": 473702, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0711658000946045, "global_step": 473703, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.101374626159668, "global_step": 473704, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0556797981262207, "global_step": 473705, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.022001266479492, "global_step": 473706, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.022260904312134, "global_step": 473707, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1153907775878906, "global_step": 473708, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0669336318969727, "global_step": 473709, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0318245887756348, "global_step": 473710, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0440480709075928, "global_step": 473711, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0691096782684326, "global_step": 473712, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0512826442718506, "global_step": 473713, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0862133502960205, "global_step": 473714, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9814764261245728, "global_step": 473715, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1194469928741455, "global_step": 473716, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.970431923866272, "global_step": 473717, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.157841205596924, "global_step": 473718, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0539755821228027, "global_step": 473719, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0583817958831787, "global_step": 473720, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0462679862976074, "global_step": 473721, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9974629878997803, "global_step": 473722, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0535647869110107, "global_step": 473723, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0275895595550537, "global_step": 473724, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.043724536895752, "global_step": 473725, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.00492525100708, "global_step": 473726, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.041759490966797, "global_step": 473727, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.136019468307495, "global_step": 473728, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.064500093460083, "global_step": 473729, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.073072671890259, "global_step": 473730, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.148610830307007, "global_step": 473731, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1622610092163086, "global_step": 473732, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.024226188659668, "global_step": 473733, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.089672327041626, "global_step": 473734, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.058893918991089, "global_step": 473735, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0766830444335938, "global_step": 473736, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.067249059677124, "global_step": 473737, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.072445869445801, "global_step": 473738, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1432790756225586, "global_step": 473739, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.028304100036621, "global_step": 473740, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.066230297088623, "global_step": 473741, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1031715869903564, "global_step": 473742, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.011878252029419, "global_step": 473743, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0892176628112793, "global_step": 473744, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.135314702987671, "global_step": 473745, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.129786491394043, "global_step": 473746, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0413618087768555, "global_step": 473747, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.144305944442749, "global_step": 473748, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0349197387695312, "global_step": 473749, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.198159694671631, "global_step": 473750, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.138399362564087, "global_step": 473751, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.127171516418457, "global_step": 473752, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9988991022109985, "global_step": 473753, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1259591579437256, "global_step": 473754, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1003599166870117, "global_step": 473755, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0543324947357178, "global_step": 473756, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.112243890762329, "global_step": 473757, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.078378677368164, "global_step": 473758, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0173275470733643, "global_step": 473759, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0004429817199707, "global_step": 473760, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0330631732940674, "global_step": 473761, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9472781419754028, "global_step": 473762, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0644702911376953, "global_step": 473763, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.014099359512329, "global_step": 473764, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9993757009506226, "global_step": 473765, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0190622806549072, "global_step": 473766, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.009084939956665, "global_step": 473767, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.010101556777954, "global_step": 473768, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1725354194641113, "global_step": 473769, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0910940170288086, "global_step": 473770, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.078433036804199, "global_step": 473771, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0885651111602783, "global_step": 473772, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1480581760406494, "global_step": 473773, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1058197021484375, "global_step": 473774, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.013728380203247, "global_step": 473775, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0744781494140625, "global_step": 473776, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0211541652679443, "global_step": 473777, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0074996948242188, "global_step": 473778, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1630349159240723, "global_step": 473779, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.15986704826355, "global_step": 473780, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.108549118041992, "global_step": 473781, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0271668434143066, "global_step": 473782, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.079744815826416, "global_step": 473783, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.055504083633423, "global_step": 473784, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.058364152908325, "global_step": 473785, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0165510177612305, "global_step": 473786, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0374042987823486, "global_step": 473787, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0508158206939697, "global_step": 473788, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0098202228546143, "global_step": 473789, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1045820713043213, "global_step": 473790, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0975162982940674, "global_step": 473791, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0639355182647705, "global_step": 473792, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0208234786987305, "global_step": 473793, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.058027744293213, "global_step": 473794, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0985379219055176, "global_step": 473795, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0025205612182617, "global_step": 473796, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0350759029388428, "global_step": 473797, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0596556663513184, "global_step": 473798, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0000216960906982, "global_step": 473799, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.057666540145874, "global_step": 473800, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.073230266571045, "global_step": 473801, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.10172438621521, "global_step": 473802, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.095294713973999, "global_step": 473803, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.055875778198242, "global_step": 473804, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.117236852645874, "global_step": 473805, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.065906524658203, "global_step": 473806, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.135796308517456, "global_step": 473807, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.016568899154663, "global_step": 473808, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.042292833328247, "global_step": 473809, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0403428077697754, "global_step": 473810, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.044983386993408, "global_step": 473811, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0519917011260986, "global_step": 473812, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0837574005126953, "global_step": 473813, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0225424766540527, "global_step": 473814, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.008324384689331, "global_step": 473815, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9678616523742676, "global_step": 473816, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.03310489654541, "global_step": 473817, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9598455429077148, "global_step": 473818, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0021822452545166, "global_step": 473819, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0443551540374756, "global_step": 473820, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.152404546737671, "global_step": 473821, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.11879563331604, "global_step": 473822, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.111250400543213, "global_step": 473823, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0658464431762695, "global_step": 473824, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0272629261016846, "global_step": 473825, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1342437267303467, "global_step": 473826, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0368425846099854, "global_step": 473827, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0792808532714844, "global_step": 473828, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0924272537231445, "global_step": 473829, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0463438034057617, "global_step": 473830, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0448179244995117, "global_step": 473831, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.135101556777954, "global_step": 473832, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.040970802307129, "global_step": 473833, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.165700912475586, "global_step": 473834, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.004315137863159, "global_step": 473835, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.124373197555542, "global_step": 473836, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.056241273880005, "global_step": 473837, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.083240032196045, "global_step": 473838, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0709197521209717, "global_step": 473839, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.101850748062134, "global_step": 473840, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.033916711807251, "global_step": 473841, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.083195924758911, "global_step": 473842, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0640926361083984, "global_step": 473843, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0524978637695312, "global_step": 473844, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.08492374420166, "global_step": 473845, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0463666915893555, "global_step": 473846, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0874974727630615, "global_step": 473847, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1143577098846436, "global_step": 473848, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0972847938537598, "global_step": 473849, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0683040618896484, "global_step": 473850, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0247089862823486, "global_step": 473851, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0605878829956055, "global_step": 473852, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.032153606414795, "global_step": 473853, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.035607099533081, "global_step": 473854, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0366060733795166, "global_step": 473855, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.061333179473877, "global_step": 473856, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0880379676818848, "global_step": 473857, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0953867435455322, "global_step": 473858, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0817315578460693, "global_step": 473859, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.119982957839966, "global_step": 473860, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.096477746963501, "global_step": 473861, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.055314302444458, "global_step": 473862, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0903842449188232, "global_step": 473863, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.004565477371216, "global_step": 473864, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9485485553741455, "global_step": 473865, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0754711627960205, "global_step": 473866, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1387314796447754, "global_step": 473867, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.009504795074463, "global_step": 473868, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.111809253692627, "global_step": 473869, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.111116409301758, "global_step": 473870, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.111945867538452, "global_step": 473871, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.069359064102173, "global_step": 473872, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.054858922958374, "global_step": 473873, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.121030569076538, "global_step": 473874, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9817724227905273, "global_step": 473875, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0509138107299805, "global_step": 473876, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0519096851348877, "global_step": 473877, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.016119956970215, "global_step": 473878, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.00740647315979, "global_step": 473879, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0920603275299072, "global_step": 473880, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.049584150314331, "global_step": 473881, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1178717613220215, "global_step": 473882, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9994511604309082, "global_step": 473883, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.111145496368408, "global_step": 473884, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.081165313720703, "global_step": 473885, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1414191722869873, "global_step": 473886, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0629756450653076, "global_step": 473887, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1594812870025635, "global_step": 473888, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.051328659057617, "global_step": 473889, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.117462635040283, "global_step": 473890, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.030534505844116, "global_step": 473891, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.110530376434326, "global_step": 473892, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.070594310760498, "global_step": 473893, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.085998296737671, "global_step": 473894, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1045608520507812, "global_step": 473895, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.988508939743042, "global_step": 473896, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.081609010696411, "global_step": 473897, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0904135704040527, "global_step": 473898, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1953585147857666, "global_step": 473899, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9898910522460938, "global_step": 473900, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.081050395965576, "global_step": 473901, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9870667457580566, "global_step": 473902, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0663270950317383, "global_step": 473903, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9821648597717285, "global_step": 473904, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.08109450340271, "global_step": 473905, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.088855028152466, "global_step": 473906, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.106724977493286, "global_step": 473907, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.043398141860962, "global_step": 473908, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1076717376708984, "global_step": 473909, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0767030715942383, "global_step": 473910, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0394561290740967, "global_step": 473911, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.146941661834717, "global_step": 473912, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.091822385787964, "global_step": 473913, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.156818389892578, "global_step": 473914, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0026984214782715, "global_step": 473915, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0467443466186523, "global_step": 473916, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0964231491088867, "global_step": 473917, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0628297328948975, "global_step": 473918, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.023254156112671, "global_step": 473919, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0637359619140625, "global_step": 473920, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0157947540283203, "global_step": 473921, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.026425838470459, "global_step": 473922, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.098564386367798, "global_step": 473923, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.991847038269043, "global_step": 473924, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.102635383605957, "global_step": 473925, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0822885036468506, "global_step": 473926, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9727016687393188, "global_step": 473927, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0489325523376465, "global_step": 473928, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1822867393493652, "global_step": 473929, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.038010835647583, "global_step": 473930, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0692391395568848, "global_step": 473931, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0779805183410645, "global_step": 473932, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9600425958633423, "global_step": 473933, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.008998394012451, "global_step": 473934, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0739035606384277, "global_step": 473935, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1004951000213623, "global_step": 473936, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.048544406890869, "global_step": 473937, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0509345531463623, "global_step": 473938, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.032250165939331, "global_step": 473939, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0990421772003174, "global_step": 473940, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.005488157272339, "global_step": 473941, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.082913637161255, "global_step": 473942, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0978586673736572, "global_step": 473943, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1283068656921387, "global_step": 473944, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0696709156036377, "global_step": 473945, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.062673330307007, "global_step": 473946, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0445194244384766, "global_step": 473947, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0224199295043945, "global_step": 473948, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.041987180709839, "global_step": 473949, "epoch": 838, "lr": 5e-05}
{"train_loss": 1.9848424196243286, "global_step": 473950, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0785460472106934, "global_step": 473951, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.181536912918091, "global_step": 473952, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.082552671432495, "global_step": 473953, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0993804931640625, "global_step": 473954, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1729912757873535, "global_step": 473955, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.161996603012085, "global_step": 473956, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0772948265075684, "global_step": 473957, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1193697452545166, "global_step": 473958, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1085922718048096, "global_step": 473959, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.027352809906006, "global_step": 473960, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.117668867111206, "global_step": 473961, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0889129638671875, "global_step": 473962, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.065495729446411, "global_step": 473963, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1118099689483643, "global_step": 473964, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.054936647415161, "global_step": 473965, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.130697727203369, "global_step": 473966, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0564024448394775, "global_step": 473967, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0922906398773193, "global_step": 473968, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0195958614349365, "global_step": 473969, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0314362049102783, "global_step": 473970, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.1154589653015137, "global_step": 473971, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0396182537078857, "global_step": 473972, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.062610149383545, "global_step": 473973, "epoch": 838, "lr": 5e-05}
{"train_loss": 2.0752007961273193, "global_step": 473974, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.053995132446289, "global_step": 473975, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0264434814453125, "global_step": 473976, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0647854804992676, "global_step": 473977, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1094417572021484, "global_step": 473978, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.094820499420166, "global_step": 473979, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0697505474090576, "global_step": 473980, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.046578884124756, "global_step": 473981, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.080730438232422, "global_step": 473982, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.088181257247925, "global_step": 473983, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0554823875427246, "global_step": 473984, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1002085208892822, "global_step": 473985, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0174362659454346, "global_step": 473986, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0549657344818115, "global_step": 473987, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.056476593017578, "global_step": 473988, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.064438581466675, "global_step": 473989, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.953342080116272, "global_step": 473990, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.027815103530884, "global_step": 473991, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0440125465393066, "global_step": 473992, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.097752094268799, "global_step": 473993, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9634853601455688, "global_step": 473994, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0174717903137207, "global_step": 473995, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9806833267211914, "global_step": 473996, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.059229850769043, "global_step": 473997, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.084406614303589, "global_step": 473998, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1302759647369385, "global_step": 473999, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.979525089263916, "global_step": 474000, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0429089069366455, "global_step": 474001, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0627193450927734, "global_step": 474002, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.080481767654419, "global_step": 474003, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.04937744140625, "global_step": 474004, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.07318115234375, "global_step": 474005, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.036238193511963, "global_step": 474006, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.009397506713867, "global_step": 474007, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.11962890625, "global_step": 474008, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.225374698638916, "global_step": 474009, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.039611339569092, "global_step": 474010, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.062762498855591, "global_step": 474011, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9714627265930176, "global_step": 474012, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0805037021636963, "global_step": 474013, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0871129035949707, "global_step": 474014, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0148322582244873, "global_step": 474015, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1048500537872314, "global_step": 474016, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.130297899246216, "global_step": 474017, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.977146029472351, "global_step": 474018, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.062096118927002, "global_step": 474019, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.066397190093994, "global_step": 474020, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1073505878448486, "global_step": 474021, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0603644847869873, "global_step": 474022, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0425233840942383, "global_step": 474023, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0795652866363525, "global_step": 474024, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1408097743988037, "global_step": 474025, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0575759410858154, "global_step": 474026, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.013383388519287, "global_step": 474027, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.978145718574524, "global_step": 474028, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0377492904663086, "global_step": 474029, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9970911741256714, "global_step": 474030, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0764503479003906, "global_step": 474031, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9772435426712036, "global_step": 474032, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.131166458129883, "global_step": 474033, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1167354583740234, "global_step": 474034, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.025055170059204, "global_step": 474035, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.112818717956543, "global_step": 474036, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0251691341400146, "global_step": 474037, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0426244735717773, "global_step": 474038, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0757851600646973, "global_step": 474039, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0056142807006836, "global_step": 474040, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.059669256210327, "global_step": 474041, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9743903875350952, "global_step": 474042, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0138137340545654, "global_step": 474043, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.073025941848755, "global_step": 474044, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0437164306640625, "global_step": 474045, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.007429599761963, "global_step": 474046, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0459647178649902, "global_step": 474047, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.02900767326355, "global_step": 474048, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0894927978515625, "global_step": 474049, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0326218605041504, "global_step": 474050, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.02059006690979, "global_step": 474051, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0312728881835938, "global_step": 474052, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.974855661392212, "global_step": 474053, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0383925437927246, "global_step": 474054, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9974058866500854, "global_step": 474055, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0635905265808105, "global_step": 474056, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0832157135009766, "global_step": 474057, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0097219944000244, "global_step": 474058, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.016775131225586, "global_step": 474059, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.020876884460449, "global_step": 474060, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0312302112579346, "global_step": 474061, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.04837703704834, "global_step": 474062, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.02022123336792, "global_step": 474063, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.103987693786621, "global_step": 474064, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9898582696914673, "global_step": 474065, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0702991485595703, "global_step": 474066, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0246872901916504, "global_step": 474067, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0846612453460693, "global_step": 474068, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.023270606994629, "global_step": 474069, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9618762731552124, "global_step": 474070, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0672967433929443, "global_step": 474071, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.020437240600586, "global_step": 474072, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.026789665222168, "global_step": 474073, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0291361808776855, "global_step": 474074, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.966816782951355, "global_step": 474075, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.096733808517456, "global_step": 474076, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.094857931137085, "global_step": 474077, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0985171794891357, "global_step": 474078, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.072577953338623, "global_step": 474079, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0065271854400635, "global_step": 474080, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1339097023010254, "global_step": 474081, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1091678142547607, "global_step": 474082, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0380592346191406, "global_step": 474083, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0461690425872803, "global_step": 474084, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9882644414901733, "global_step": 474085, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0210137367248535, "global_step": 474086, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.026663303375244, "global_step": 474087, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1228721141815186, "global_step": 474088, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.007803440093994, "global_step": 474089, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.060819625854492, "global_step": 474090, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1324801445007324, "global_step": 474091, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0500540733337402, "global_step": 474092, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0785770416259766, "global_step": 474093, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1343488693237305, "global_step": 474094, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.004654884338379, "global_step": 474095, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9785256385803223, "global_step": 474096, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9442510604858398, "global_step": 474097, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0878002643585205, "global_step": 474098, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1414544582366943, "global_step": 474099, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.012932777404785, "global_step": 474100, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.141439437866211, "global_step": 474101, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1036012172698975, "global_step": 474102, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0568015575408936, "global_step": 474103, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9815189838409424, "global_step": 474104, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.990156888961792, "global_step": 474105, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0373494625091553, "global_step": 474106, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.137908935546875, "global_step": 474107, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1816980838775635, "global_step": 474108, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0825600624084473, "global_step": 474109, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.041311025619507, "global_step": 474110, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.090264320373535, "global_step": 474111, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0872983932495117, "global_step": 474112, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1136302947998047, "global_step": 474113, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.071561813354492, "global_step": 474114, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0772833824157715, "global_step": 474115, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.093493938446045, "global_step": 474116, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0506198406219482, "global_step": 474117, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0353496074676514, "global_step": 474118, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.064958333969116, "global_step": 474119, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9906941652297974, "global_step": 474120, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.095144033432007, "global_step": 474121, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1024160385131836, "global_step": 474122, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.079495668411255, "global_step": 474123, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0362493991851807, "global_step": 474124, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1278185844421387, "global_step": 474125, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9954067468643188, "global_step": 474126, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.089183807373047, "global_step": 474127, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0354232788085938, "global_step": 474128, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0858216285705566, "global_step": 474129, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.079352855682373, "global_step": 474130, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1140990257263184, "global_step": 474131, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0411245822906494, "global_step": 474132, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0292248725891113, "global_step": 474133, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0903539657592773, "global_step": 474134, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0506584644317627, "global_step": 474135, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0910234451293945, "global_step": 474136, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.003877639770508, "global_step": 474137, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9846470355987549, "global_step": 474138, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0899078845977783, "global_step": 474139, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.045619249343872, "global_step": 474140, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.076972007751465, "global_step": 474141, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0558667182922363, "global_step": 474142, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0497257709503174, "global_step": 474143, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9462966918945312, "global_step": 474144, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9385840892791748, "global_step": 474145, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1165733337402344, "global_step": 474146, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.05876088142395, "global_step": 474147, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9773298501968384, "global_step": 474148, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1113314628601074, "global_step": 474149, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.063547372817993, "global_step": 474150, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.034148931503296, "global_step": 474151, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.160768508911133, "global_step": 474152, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9694582223892212, "global_step": 474153, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0914273262023926, "global_step": 474154, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9943386316299438, "global_step": 474155, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0607521533966064, "global_step": 474156, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9888919591903687, "global_step": 474157, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.011894464492798, "global_step": 474158, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0497689247131348, "global_step": 474159, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0948548316955566, "global_step": 474160, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9318418502807617, "global_step": 474161, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0584959983825684, "global_step": 474162, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0173659324645996, "global_step": 474163, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9172028303146362, "global_step": 474164, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1028382778167725, "global_step": 474165, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.054945707321167, "global_step": 474166, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.016087770462036, "global_step": 474167, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0763182640075684, "global_step": 474168, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.101574420928955, "global_step": 474169, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1050384044647217, "global_step": 474170, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0566580295562744, "global_step": 474171, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0759389400482178, "global_step": 474172, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.065850257873535, "global_step": 474173, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0365123748779297, "global_step": 474174, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.120762348175049, "global_step": 474175, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.121746778488159, "global_step": 474176, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9817252159118652, "global_step": 474177, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9276645183563232, "global_step": 474178, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0362508296966553, "global_step": 474179, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0125772953033447, "global_step": 474180, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0136332511901855, "global_step": 474181, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0425527095794678, "global_step": 474182, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0339303016662598, "global_step": 474183, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.028130531311035, "global_step": 474184, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.048865795135498, "global_step": 474185, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0217928886413574, "global_step": 474186, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0585625171661377, "global_step": 474187, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.084754467010498, "global_step": 474188, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.017764091491699, "global_step": 474189, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9965041875839233, "global_step": 474190, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9745150804519653, "global_step": 474191, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.084120988845825, "global_step": 474192, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1281630992889404, "global_step": 474193, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0159101486206055, "global_step": 474194, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0423715114593506, "global_step": 474195, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.002204179763794, "global_step": 474196, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.142923593521118, "global_step": 474197, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0202343463897705, "global_step": 474198, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9925154447555542, "global_step": 474199, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.05086088180542, "global_step": 474200, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0989773273468018, "global_step": 474201, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1270413398742676, "global_step": 474202, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1278629302978516, "global_step": 474203, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0008492469787598, "global_step": 474204, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0121216773986816, "global_step": 474205, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0404772758483887, "global_step": 474206, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.072425127029419, "global_step": 474207, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.015159845352173, "global_step": 474208, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0731394290924072, "global_step": 474209, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0951080322265625, "global_step": 474210, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9666498899459839, "global_step": 474211, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.093061923980713, "global_step": 474212, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0201404094696045, "global_step": 474213, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.131561517715454, "global_step": 474214, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0652453899383545, "global_step": 474215, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9928628206253052, "global_step": 474216, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.098811149597168, "global_step": 474217, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9962990283966064, "global_step": 474218, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.013777732849121, "global_step": 474219, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.143425226211548, "global_step": 474220, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.063026189804077, "global_step": 474221, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0625407695770264, "global_step": 474222, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0666184425354004, "global_step": 474223, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0540852546691895, "global_step": 474224, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.109741687774658, "global_step": 474225, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0431301593780518, "global_step": 474226, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9899886846542358, "global_step": 474227, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0147271156311035, "global_step": 474228, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.083885431289673, "global_step": 474229, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.023994207382202, "global_step": 474230, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0509073734283447, "global_step": 474231, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0272860527038574, "global_step": 474232, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0688860416412354, "global_step": 474233, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.054670572280884, "global_step": 474234, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0186595916748047, "global_step": 474235, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9819711446762085, "global_step": 474236, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.054797410964966, "global_step": 474237, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0842158794403076, "global_step": 474238, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0189366340637207, "global_step": 474239, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0286030769348145, "global_step": 474240, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.094539165496826, "global_step": 474241, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.106947183609009, "global_step": 474242, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0163443088531494, "global_step": 474243, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0741806030273438, "global_step": 474244, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0210464000701904, "global_step": 474245, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1200761795043945, "global_step": 474246, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0073249340057373, "global_step": 474247, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0278940200805664, "global_step": 474248, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0923221111297607, "global_step": 474249, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0535714626312256, "global_step": 474250, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.998510718345642, "global_step": 474251, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1022682189941406, "global_step": 474252, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.056032657623291, "global_step": 474253, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0787689685821533, "global_step": 474254, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.049462080001831, "global_step": 474255, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1140072345733643, "global_step": 474256, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.086477518081665, "global_step": 474257, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0555074214935303, "global_step": 474258, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.067077159881592, "global_step": 474259, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0844743251800537, "global_step": 474260, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.061973810195923, "global_step": 474261, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.012307643890381, "global_step": 474262, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1162664890289307, "global_step": 474263, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0589380264282227, "global_step": 474264, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.088907480239868, "global_step": 474265, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0913326740264893, "global_step": 474266, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.096156597137451, "global_step": 474267, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.146024465560913, "global_step": 474268, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.057765007019043, "global_step": 474269, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9901098012924194, "global_step": 474270, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.008375883102417, "global_step": 474271, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0931689739227295, "global_step": 474272, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0003576278686523, "global_step": 474273, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0710701942443848, "global_step": 474274, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9926551580429077, "global_step": 474275, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0374391078948975, "global_step": 474276, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.024022102355957, "global_step": 474277, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9780994653701782, "global_step": 474278, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0927116870880127, "global_step": 474279, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.011406183242798, "global_step": 474280, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.964809775352478, "global_step": 474281, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0577008724212646, "global_step": 474282, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.098555564880371, "global_step": 474283, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0035154819488525, "global_step": 474284, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0595266819000244, "global_step": 474285, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0372509956359863, "global_step": 474286, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.121504783630371, "global_step": 474287, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.014103889465332, "global_step": 474288, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.026857614517212, "global_step": 474289, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0552077293395996, "global_step": 474290, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1092441082000732, "global_step": 474291, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9900550842285156, "global_step": 474292, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0821492671966553, "global_step": 474293, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.079937696456909, "global_step": 474294, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.000743865966797, "global_step": 474295, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0045576095581055, "global_step": 474296, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.022247314453125, "global_step": 474297, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.046112537384033, "global_step": 474298, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.038591146469116, "global_step": 474299, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0292749404907227, "global_step": 474300, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1138815879821777, "global_step": 474301, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1205906867980957, "global_step": 474302, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.09824275970459, "global_step": 474303, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9731999635696411, "global_step": 474304, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.038332462310791, "global_step": 474305, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0194950103759766, "global_step": 474306, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0176639556884766, "global_step": 474307, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0585620403289795, "global_step": 474308, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1154274940490723, "global_step": 474309, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.01747465133667, "global_step": 474310, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0514657497406006, "global_step": 474311, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1010982990264893, "global_step": 474312, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0525872707366943, "global_step": 474313, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.119020700454712, "global_step": 474314, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.047102928161621, "global_step": 474315, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.010314702987671, "global_step": 474316, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0282042026519775, "global_step": 474317, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.062805414199829, "global_step": 474318, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.071230411529541, "global_step": 474319, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9743313789367676, "global_step": 474320, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9737374782562256, "global_step": 474321, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.044623613357544, "global_step": 474322, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.040376901626587, "global_step": 474323, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1033358573913574, "global_step": 474324, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.165593147277832, "global_step": 474325, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.10667085647583, "global_step": 474326, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.096588373184204, "global_step": 474327, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0441668033599854, "global_step": 474328, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.997814416885376, "global_step": 474329, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.016387939453125, "global_step": 474330, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.126931667327881, "global_step": 474331, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0536112785339355, "global_step": 474332, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9946513175964355, "global_step": 474333, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.033653736114502, "global_step": 474334, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.8985000848770142, "global_step": 474335, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0895650386810303, "global_step": 474336, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.097554922103882, "global_step": 474337, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.108670711517334, "global_step": 474338, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.094545364379883, "global_step": 474339, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0941884517669678, "global_step": 474340, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.946413278579712, "global_step": 474341, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0468175411224365, "global_step": 474342, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0152838230133057, "global_step": 474343, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.042509078979492, "global_step": 474344, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.056816816329956, "global_step": 474345, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0684187412261963, "global_step": 474346, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.07204532623291, "global_step": 474347, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0101771354675293, "global_step": 474348, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.093472957611084, "global_step": 474349, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.22107195854187, "global_step": 474350, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.096708297729492, "global_step": 474351, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1071765422821045, "global_step": 474352, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0949347019195557, "global_step": 474353, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0428061485290527, "global_step": 474354, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.082075595855713, "global_step": 474355, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1242191791534424, "global_step": 474356, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.038886785507202, "global_step": 474357, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.071417808532715, "global_step": 474358, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1058874130249023, "global_step": 474359, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.130443811416626, "global_step": 474360, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0341429710388184, "global_step": 474361, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.100156545639038, "global_step": 474362, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0535531044006348, "global_step": 474363, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0886635780334473, "global_step": 474364, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1113855838775635, "global_step": 474365, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1092376708984375, "global_step": 474366, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0181944370269775, "global_step": 474367, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.074328899383545, "global_step": 474368, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0081732273101807, "global_step": 474369, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0423011779785156, "global_step": 474370, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1182074546813965, "global_step": 474371, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9771597385406494, "global_step": 474372, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.106509208679199, "global_step": 474373, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.074075698852539, "global_step": 474374, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1462996006011963, "global_step": 474375, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0927040576934814, "global_step": 474376, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.005777359008789, "global_step": 474377, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.028916358947754, "global_step": 474378, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0251169204711914, "global_step": 474379, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.090747594833374, "global_step": 474380, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.100419282913208, "global_step": 474381, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.060093879699707, "global_step": 474382, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9993127584457397, "global_step": 474383, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1140894889831543, "global_step": 474384, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.090636730194092, "global_step": 474385, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9990887641906738, "global_step": 474386, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9855289459228516, "global_step": 474387, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0107922554016113, "global_step": 474388, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0763580799102783, "global_step": 474389, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.043260335922241, "global_step": 474390, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0276615619659424, "global_step": 474391, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0247061252593994, "global_step": 474392, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0314533710479736, "global_step": 474393, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.036344289779663, "global_step": 474394, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0398850440979004, "global_step": 474395, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9634567499160767, "global_step": 474396, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0461907386779785, "global_step": 474397, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.009126901626587, "global_step": 474398, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0332868099212646, "global_step": 474399, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9903011322021484, "global_step": 474400, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.07547664642334, "global_step": 474401, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.018749952316284, "global_step": 474402, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.109325408935547, "global_step": 474403, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0144829750061035, "global_step": 474404, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.041215181350708, "global_step": 474405, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.154553174972534, "global_step": 474406, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1181578636169434, "global_step": 474407, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0424835681915283, "global_step": 474408, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1419053077697754, "global_step": 474409, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9611334800720215, "global_step": 474410, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0504586696624756, "global_step": 474411, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.050413131713867, "global_step": 474412, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0223066806793213, "global_step": 474413, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9925248622894287, "global_step": 474414, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.149143934249878, "global_step": 474415, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.011345624923706, "global_step": 474416, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.992499589920044, "global_step": 474417, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.078824043273926, "global_step": 474418, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.024188756942749, "global_step": 474419, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9849579334259033, "global_step": 474420, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9795984029769897, "global_step": 474421, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.063936471939087, "global_step": 474422, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.084723472595215, "global_step": 474423, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.09751033782959, "global_step": 474424, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.098684310913086, "global_step": 474425, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.007499933242798, "global_step": 474426, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1226160526275635, "global_step": 474427, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.122307300567627, "global_step": 474428, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.121748685836792, "global_step": 474429, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.090855598449707, "global_step": 474430, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.07822585105896, "global_step": 474431, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.012061595916748, "global_step": 474432, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.029557466506958, "global_step": 474433, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.041734457015991, "global_step": 474434, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0922927856445312, "global_step": 474435, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0648415088653564, "global_step": 474436, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.072282075881958, "global_step": 474437, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0465455055236816, "global_step": 474438, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0250091552734375, "global_step": 474439, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.105923652648926, "global_step": 474440, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.101940870285034, "global_step": 474441, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1128475666046143, "global_step": 474442, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.142996311187744, "global_step": 474443, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.2212047576904297, "global_step": 474444, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.052778959274292, "global_step": 474445, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0959930419921875, "global_step": 474446, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0408124923706055, "global_step": 474447, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.014069080352783, "global_step": 474448, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1253509521484375, "global_step": 474449, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.062331199645996, "global_step": 474450, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0639071464538574, "global_step": 474451, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0771708488464355, "global_step": 474452, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0384109020233154, "global_step": 474453, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1246767044067383, "global_step": 474454, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.051128625869751, "global_step": 474455, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0105907917022705, "global_step": 474456, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.980900526046753, "global_step": 474457, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9385935068130493, "global_step": 474458, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0781354904174805, "global_step": 474459, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9227319955825806, "global_step": 474460, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0583572387695312, "global_step": 474461, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0618631839752197, "global_step": 474462, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1266708374023438, "global_step": 474463, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.106278419494629, "global_step": 474464, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9790014028549194, "global_step": 474465, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.039532423019409, "global_step": 474466, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.029934883117676, "global_step": 474467, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9713807106018066, "global_step": 474468, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0401031970977783, "global_step": 474469, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0674116611480713, "global_step": 474470, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.052109718322754, "global_step": 474471, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0790014266967773, "global_step": 474472, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0782833099365234, "global_step": 474473, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.055806875228882, "global_step": 474474, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9865117073059082, "global_step": 474475, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.068328857421875, "global_step": 474476, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0854923725128174, "global_step": 474477, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9560297727584839, "global_step": 474478, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9694608449935913, "global_step": 474479, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9713659286499023, "global_step": 474480, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0691726207733154, "global_step": 474481, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.059530735015869, "global_step": 474482, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0051395893096924, "global_step": 474483, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.078731060028076, "global_step": 474484, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0553030967712402, "global_step": 474485, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.036163091659546, "global_step": 474486, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.124927520751953, "global_step": 474487, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.100893497467041, "global_step": 474488, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.044142961502075, "global_step": 474489, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0830471515655518, "global_step": 474490, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0521600246429443, "global_step": 474491, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.062934160232544, "global_step": 474492, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0778589248657227, "global_step": 474493, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.03764271736145, "global_step": 474494, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.027662992477417, "global_step": 474495, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1490864753723145, "global_step": 474496, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0510780811309814, "global_step": 474497, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0679268836975098, "global_step": 474498, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.96090829372406, "global_step": 474499, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.063741445541382, "global_step": 474500, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0605103969573975, "global_step": 474501, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9924492835998535, "global_step": 474502, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0183756351470947, "global_step": 474503, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.018035411834717, "global_step": 474504, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1068077087402344, "global_step": 474505, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.028529167175293, "global_step": 474506, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1771175861358643, "global_step": 474507, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.082606554031372, "global_step": 474508, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0441901683807373, "global_step": 474509, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.108311891555786, "global_step": 474510, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.077141284942627, "global_step": 474511, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.019575834274292, "global_step": 474512, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0373923778533936, "global_step": 474513, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9663549661636353, "global_step": 474514, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0385634899139404, "global_step": 474515, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0945990085601807, "global_step": 474516, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.090465784072876, "global_step": 474517, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0232458114624023, "global_step": 474518, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.050781726837158, "global_step": 474519, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0426712036132812, "global_step": 474520, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0477497577667236, "global_step": 474521, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1202032566070557, "global_step": 474522, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.039314031600952, "global_step": 474523, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.138885021209717, "global_step": 474524, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.114992380142212, "global_step": 474525, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1324689388275146, "global_step": 474526, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.020286798477173, "global_step": 474527, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1132936477661133, "global_step": 474528, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.059349536895752, "global_step": 474529, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0902607440948486, "global_step": 474530, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1042113304138184, "global_step": 474531, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.068114757537842, "global_step": 474532, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.092329263687134, "global_step": 474533, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0663013458251953, "global_step": 474534, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0013926029205322, "global_step": 474535, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1134109497070312, "global_step": 474536, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.079580068588257, "global_step": 474537, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0573136806488037, "global_step": 474538, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0986897945404053, "global_step": 474539, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0497429370880127, "global_step": 474540, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9948277473449707, "global_step": 474541, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.120875358581543, "global_step": 474542, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.03395414352417, "global_step": 474543, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.120067834854126, "global_step": 474544, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1059131622314453, "global_step": 474545, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0400848388671875, "global_step": 474546, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.135868787765503, "global_step": 474547, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0255587100982666, "global_step": 474548, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0271835327148438, "global_step": 474549, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.045527935028076, "global_step": 474550, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0583646297454834, "global_step": 474551, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0205724239349365, "global_step": 474552, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.016842842102051, "global_step": 474553, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0834572315216064, "global_step": 474554, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1634325981140137, "global_step": 474555, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0406746864318848, "global_step": 474556, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9729855060577393, "global_step": 474557, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.044766902923584, "global_step": 474558, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.123260021209717, "global_step": 474559, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.021730661392212, "global_step": 474560, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1258552074432373, "global_step": 474561, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0902457237243652, "global_step": 474562, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1773290634155273, "global_step": 474563, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.032820701599121, "global_step": 474564, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0571718215942383, "global_step": 474565, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.138150930404663, "global_step": 474566, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.089017629623413, "global_step": 474567, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.059689998626709, "global_step": 474568, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0891332626342773, "global_step": 474569, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9906519651412964, "global_step": 474570, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0406994819641113, "global_step": 474571, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1340279579162598, "global_step": 474572, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.004171848297119, "global_step": 474573, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.038489818572998, "global_step": 474574, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0455336570739746, "global_step": 474575, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9737204313278198, "global_step": 474576, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0597918033599854, "global_step": 474577, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.108656406402588, "global_step": 474578, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1324691772460938, "global_step": 474579, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0890471935272217, "global_step": 474580, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.112833023071289, "global_step": 474581, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.022190570831299, "global_step": 474582, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.073659896850586, "global_step": 474583, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0580596923828125, "global_step": 474584, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.06270432472229, "global_step": 474585, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1158998012542725, "global_step": 474586, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0938825607299805, "global_step": 474587, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.070380210876465, "global_step": 474588, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.004528760910034, "global_step": 474589, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.158667802810669, "global_step": 474590, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.194446325302124, "global_step": 474591, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9930753707885742, "global_step": 474592, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.138944387435913, "global_step": 474593, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.10615611076355, "global_step": 474594, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0997982025146484, "global_step": 474595, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.036107063293457, "global_step": 474596, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.020125389099121, "global_step": 474597, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0878639221191406, "global_step": 474598, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.042353630065918, "global_step": 474599, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0605452060699463, "global_step": 474600, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.147876262664795, "global_step": 474601, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9881540536880493, "global_step": 474602, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.177544116973877, "global_step": 474603, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0692436695098877, "global_step": 474604, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0414676666259766, "global_step": 474605, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0337255001068115, "global_step": 474606, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0803472995758057, "global_step": 474607, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.96234130859375, "global_step": 474608, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.010094165802002, "global_step": 474609, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.105672597885132, "global_step": 474610, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.028831958770752, "global_step": 474611, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0709657669067383, "global_step": 474612, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.053640604019165, "global_step": 474613, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.040214776992798, "global_step": 474614, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1466891765594482, "global_step": 474615, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.159472703933716, "global_step": 474616, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9827501773834229, "global_step": 474617, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1088907718658447, "global_step": 474618, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9668811559677124, "global_step": 474619, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.080512762069702, "global_step": 474620, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0248584747314453, "global_step": 474621, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.026954412460327, "global_step": 474622, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.117096424102783, "global_step": 474623, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.03896164894104, "global_step": 474624, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.036264181137085, "global_step": 474625, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9864391088485718, "global_step": 474626, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.007143497467041, "global_step": 474627, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.016810417175293, "global_step": 474628, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0130624771118164, "global_step": 474629, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1618764400482178, "global_step": 474630, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.018043279647827, "global_step": 474631, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0689351558685303, "global_step": 474632, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0647034645080566, "global_step": 474633, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.049938917160034, "global_step": 474634, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0341362953186035, "global_step": 474635, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0556693077087402, "global_step": 474636, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.093860149383545, "global_step": 474637, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0750205516815186, "global_step": 474638, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0831830501556396, "global_step": 474639, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.018076181411743, "global_step": 474640, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0638012886047363, "global_step": 474641, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1037487983703613, "global_step": 474642, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.068781852722168, "global_step": 474643, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0736465454101562, "global_step": 474644, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1140332221984863, "global_step": 474645, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9942389726638794, "global_step": 474646, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0124692916870117, "global_step": 474647, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0651509761810303, "global_step": 474648, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.046746015548706, "global_step": 474649, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0659983158111572, "global_step": 474650, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0900204181671143, "global_step": 474651, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.021576166152954, "global_step": 474652, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0682361125946045, "global_step": 474653, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0896031856536865, "global_step": 474654, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0862035751342773, "global_step": 474655, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0110621452331543, "global_step": 474656, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0535576343536377, "global_step": 474657, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0805206298828125, "global_step": 474658, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9803000688552856, "global_step": 474659, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0963644981384277, "global_step": 474660, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0002615451812744, "global_step": 474661, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.016955852508545, "global_step": 474662, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.135204315185547, "global_step": 474663, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1164867877960205, "global_step": 474664, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0523629188537598, "global_step": 474665, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.160193920135498, "global_step": 474666, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1196320056915283, "global_step": 474667, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.060023069381714, "global_step": 474668, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0691590309143066, "global_step": 474669, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0735135078430176, "global_step": 474670, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.070288896560669, "global_step": 474671, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0936269760131836, "global_step": 474672, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.06465482711792, "global_step": 474673, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0704338550567627, "global_step": 474674, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0690393447875977, "global_step": 474675, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0628631114959717, "global_step": 474676, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0800235271453857, "global_step": 474677, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0986411571502686, "global_step": 474678, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.12619686126709, "global_step": 474679, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0718560218811035, "global_step": 474680, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0618433952331543, "global_step": 474681, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.065261125564575, "global_step": 474682, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0268588066101074, "global_step": 474683, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.036569118499756, "global_step": 474684, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0542359352111816, "global_step": 474685, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0684142112731934, "global_step": 474686, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9805916547775269, "global_step": 474687, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0811607837677, "global_step": 474688, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.019341468811035, "global_step": 474689, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.967194676399231, "global_step": 474690, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0535221099853516, "global_step": 474691, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.055957078933716, "global_step": 474692, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0509462356567383, "global_step": 474693, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.069797992706299, "global_step": 474694, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0200531482696533, "global_step": 474695, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1265130043029785, "global_step": 474696, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.115440607070923, "global_step": 474697, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0378682613372803, "global_step": 474698, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0629446506500244, "global_step": 474699, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1273622512817383, "global_step": 474700, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0003662109375, "global_step": 474701, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.008617639541626, "global_step": 474702, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.050771951675415, "global_step": 474703, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.035681962966919, "global_step": 474704, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1049387454986572, "global_step": 474705, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0941567420959473, "global_step": 474706, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1151134967803955, "global_step": 474707, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0572867393493652, "global_step": 474708, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.028550863265991, "global_step": 474709, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.07765531539917, "global_step": 474710, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1337671279907227, "global_step": 474711, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.954818844795227, "global_step": 474712, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0731287002563477, "global_step": 474713, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1554951667785645, "global_step": 474714, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.126234292984009, "global_step": 474715, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9889689683914185, "global_step": 474716, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1418747901916504, "global_step": 474717, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.038205623626709, "global_step": 474718, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0460445880889893, "global_step": 474719, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0859286785125732, "global_step": 474720, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.994073510169983, "global_step": 474721, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9251136779785156, "global_step": 474722, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1220102310180664, "global_step": 474723, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.011080265045166, "global_step": 474724, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.003519296646118, "global_step": 474725, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9973580837249756, "global_step": 474726, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.056668281555176, "global_step": 474727, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.036898374557495, "global_step": 474728, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0626347064971924, "global_step": 474729, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0066089630126953, "global_step": 474730, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0415546894073486, "global_step": 474731, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.057781457901001, "global_step": 474732, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.184030771255493, "global_step": 474733, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9693338871002197, "global_step": 474734, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.057332992553711, "global_step": 474735, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0362560749053955, "global_step": 474736, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.995570421218872, "global_step": 474737, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0808603763580322, "global_step": 474738, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0501046180725098, "global_step": 474739, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.030695676803589, "global_step": 474740, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9959604740142822, "global_step": 474741, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0560860633850098, "global_step": 474742, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9938089847564697, "global_step": 474743, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0102591514587402, "global_step": 474744, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.084872007369995, "global_step": 474745, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1144678592681885, "global_step": 474746, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1413745880126953, "global_step": 474747, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0068893432617188, "global_step": 474748, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0349619388580322, "global_step": 474749, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.016098737716675, "global_step": 474750, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1471614837646484, "global_step": 474751, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.133697509765625, "global_step": 474752, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1006839275360107, "global_step": 474753, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1463589668273926, "global_step": 474754, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0882182121276855, "global_step": 474755, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9370192289352417, "global_step": 474756, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1289806365966797, "global_step": 474757, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9866654872894287, "global_step": 474758, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.992496132850647, "global_step": 474759, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.041141986846924, "global_step": 474760, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0318243503570557, "global_step": 474761, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.992722988128662, "global_step": 474762, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0391247272491455, "global_step": 474763, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0704102516174316, "global_step": 474764, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0906922817230225, "global_step": 474765, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.069434642791748, "global_step": 474766, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0218069553375244, "global_step": 474767, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1253821849823, "global_step": 474768, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0426855087280273, "global_step": 474769, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.144137382507324, "global_step": 474770, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.025052785873413, "global_step": 474771, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.942886471748352, "global_step": 474772, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0999391078948975, "global_step": 474773, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0594775676727295, "global_step": 474774, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0717995166778564, "global_step": 474775, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0363690853118896, "global_step": 474776, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.109372615814209, "global_step": 474777, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0374562740325928, "global_step": 474778, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.026634693145752, "global_step": 474779, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1028363704681396, "global_step": 474780, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.009596109390259, "global_step": 474781, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0353927612304688, "global_step": 474782, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.197943925857544, "global_step": 474783, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0852413177490234, "global_step": 474784, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0975186824798584, "global_step": 474785, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.062220335006714, "global_step": 474786, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.2050693035125732, "global_step": 474787, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.003403663635254, "global_step": 474788, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.087355375289917, "global_step": 474789, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.049875259399414, "global_step": 474790, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.003481864929199, "global_step": 474791, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9968156814575195, "global_step": 474792, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.114131212234497, "global_step": 474793, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0313520431518555, "global_step": 474794, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0528297424316406, "global_step": 474795, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.020796537399292, "global_step": 474796, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.136646032333374, "global_step": 474797, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0625898838043213, "global_step": 474798, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.095017671585083, "global_step": 474799, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1237049102783203, "global_step": 474800, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1174094676971436, "global_step": 474801, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.021912097930908, "global_step": 474802, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0419766902923584, "global_step": 474803, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0958688259124756, "global_step": 474804, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.115722179412842, "global_step": 474805, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.100900173187256, "global_step": 474806, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1079165935516357, "global_step": 474807, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0404977798461914, "global_step": 474808, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0279881954193115, "global_step": 474809, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.026765823364258, "global_step": 474810, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0622646808624268, "global_step": 474811, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.122335433959961, "global_step": 474812, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.081122398376465, "global_step": 474813, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0689594745635986, "global_step": 474814, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.070249319076538, "global_step": 474815, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9932944774627686, "global_step": 474816, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.989246129989624, "global_step": 474817, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.024552822113037, "global_step": 474818, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0607872009277344, "global_step": 474819, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.063840389251709, "global_step": 474820, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0386898517608643, "global_step": 474821, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0446460247039795, "global_step": 474822, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1322004795074463, "global_step": 474823, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0788776874542236, "global_step": 474824, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1038293838500977, "global_step": 474825, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1191821098327637, "global_step": 474826, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0742099285125732, "global_step": 474827, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9963470697402954, "global_step": 474828, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9948201179504395, "global_step": 474829, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0387728214263916, "global_step": 474830, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.046816825866699, "global_step": 474831, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9989618062973022, "global_step": 474832, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1748557090759277, "global_step": 474833, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.048560619354248, "global_step": 474834, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1127493381500244, "global_step": 474835, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.036651134490967, "global_step": 474836, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.051335334777832, "global_step": 474837, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.089629650115967, "global_step": 474838, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0602993965148926, "global_step": 474839, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1316354274749756, "global_step": 474840, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.057358741760254, "global_step": 474841, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0314407348632812, "global_step": 474842, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1226518154144287, "global_step": 474843, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1430766582489014, "global_step": 474844, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1134140491485596, "global_step": 474845, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0319652557373047, "global_step": 474846, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0840258598327637, "global_step": 474847, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9965648651123047, "global_step": 474848, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.096327066421509, "global_step": 474849, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0155129432678223, "global_step": 474850, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.095954656600952, "global_step": 474851, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0981152057647705, "global_step": 474852, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.015108108520508, "global_step": 474853, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0732409954071045, "global_step": 474854, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1530098915100098, "global_step": 474855, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.077816963195801, "global_step": 474856, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.116595983505249, "global_step": 474857, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.019519805908203, "global_step": 474858, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0638020038604736, "global_step": 474859, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.058443546295166, "global_step": 474860, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.08831787109375, "global_step": 474861, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0222666263580322, "global_step": 474862, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.101529598236084, "global_step": 474863, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0910043716430664, "global_step": 474864, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1109282970428467, "global_step": 474865, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.022214889526367, "global_step": 474866, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1980624198913574, "global_step": 474867, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0943150520324707, "global_step": 474868, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.979028582572937, "global_step": 474869, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.988992691040039, "global_step": 474870, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.12353253364563, "global_step": 474871, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.131645917892456, "global_step": 474872, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1155784130096436, "global_step": 474873, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.085214376449585, "global_step": 474874, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.096639394760132, "global_step": 474875, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1282548904418945, "global_step": 474876, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0452256202697754, "global_step": 474877, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.119540214538574, "global_step": 474878, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.072843074798584, "global_step": 474879, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.07388973236084, "global_step": 474880, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1203954219818115, "global_step": 474881, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1697745323181152, "global_step": 474882, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.038743495941162, "global_step": 474883, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.2028849124908447, "global_step": 474884, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0101242065429688, "global_step": 474885, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1511621475219727, "global_step": 474886, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.037146806716919, "global_step": 474887, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0305423736572266, "global_step": 474888, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1892917156219482, "global_step": 474889, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0835158824920654, "global_step": 474890, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9978598356246948, "global_step": 474891, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0806026458740234, "global_step": 474892, "epoch": 839, "lr": 5e-05}
{"train_loss": 1.9943437576293945, "global_step": 474893, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.115385055541992, "global_step": 474894, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0576133728027344, "global_step": 474895, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0878798961639404, "global_step": 474896, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1143248081207275, "global_step": 474897, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0815560817718506, "global_step": 474898, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.149796485900879, "global_step": 474899, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.024592638015747, "global_step": 474900, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0176148414611816, "global_step": 474901, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.079326629638672, "global_step": 474902, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.077101230621338, "global_step": 474903, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1007018089294434, "global_step": 474904, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1179983615875244, "global_step": 474905, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0737252235412598, "global_step": 474906, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.038419723510742, "global_step": 474907, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.084059476852417, "global_step": 474908, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.035551071166992, "global_step": 474909, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0090160369873047, "global_step": 474910, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.122122287750244, "global_step": 474911, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0633018016815186, "global_step": 474912, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.155148983001709, "global_step": 474913, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0190088748931885, "global_step": 474914, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1467018127441406, "global_step": 474915, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0407397747039795, "global_step": 474916, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0186409950256348, "global_step": 474917, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.061668634414673, "global_step": 474918, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.058957815170288, "global_step": 474919, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0157198905944824, "global_step": 474920, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.072345733642578, "global_step": 474921, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.076986312866211, "global_step": 474922, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0591940879821777, "global_step": 474923, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0852363109588623, "global_step": 474924, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1765756607055664, "global_step": 474925, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0941851139068604, "global_step": 474926, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0810434818267822, "global_step": 474927, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.136382818222046, "global_step": 474928, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0912530422210693, "global_step": 474929, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0569965839385986, "global_step": 474930, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.07064151763916, "global_step": 474931, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.133079767227173, "global_step": 474932, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0419042110443115, "global_step": 474933, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0616836547851562, "global_step": 474934, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0650241374969482, "global_step": 474935, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.03427791595459, "global_step": 474936, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.098496675491333, "global_step": 474937, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0484845638275146, "global_step": 474938, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.1195576190948486, "global_step": 474939, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0733447074890137, "global_step": 474940, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.044518232345581, "global_step": 474941, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.05948805809021, "global_step": 474942, "epoch": 839, "lr": 5e-05}
{"train_loss": 2.0780694484710693, "global_step": 474943, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.06935453414917, "global_step": 474944, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.038923501968384, "global_step": 474945, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.097674608230591, "global_step": 474946, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.062053680419922, "global_step": 474947, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0294575691223145, "global_step": 474948, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0377228260040283, "global_step": 474949, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9921438694000244, "global_step": 474950, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9522956609725952, "global_step": 474951, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1051642894744873, "global_step": 474952, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.086721658706665, "global_step": 474953, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.047816276550293, "global_step": 474954, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0741472244262695, "global_step": 474955, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0356521606445312, "global_step": 474956, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0675666332244873, "global_step": 474957, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.075355052947998, "global_step": 474958, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0539984703063965, "global_step": 474959, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0918169021606445, "global_step": 474960, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.029296398162842, "global_step": 474961, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.079224109649658, "global_step": 474962, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.055310010910034, "global_step": 474963, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.2044003009796143, "global_step": 474964, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0259172916412354, "global_step": 474965, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.073042392730713, "global_step": 474966, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.05046010017395, "global_step": 474967, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0322425365448, "global_step": 474968, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.015073776245117, "global_step": 474969, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.06247615814209, "global_step": 474970, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0338058471679688, "global_step": 474971, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.076533794403076, "global_step": 474972, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.140437602996826, "global_step": 474973, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.115743637084961, "global_step": 474974, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0076968669891357, "global_step": 474975, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.096667528152466, "global_step": 474976, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.065068483352661, "global_step": 474977, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.122713088989258, "global_step": 474978, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1756598949432373, "global_step": 474979, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.077627182006836, "global_step": 474980, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.154771327972412, "global_step": 474981, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.045419454574585, "global_step": 474982, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0191116333007812, "global_step": 474983, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.040489912033081, "global_step": 474984, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.04549241065979, "global_step": 474985, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0180673599243164, "global_step": 474986, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.100566864013672, "global_step": 474987, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0343713760375977, "global_step": 474988, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9950517416000366, "global_step": 474989, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0903677940368652, "global_step": 474990, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.058641195297241, "global_step": 474991, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0515806674957275, "global_step": 474992, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.076993703842163, "global_step": 474993, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0007376670837402, "global_step": 474994, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.109802722930908, "global_step": 474995, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.073220729827881, "global_step": 474996, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1375253200531006, "global_step": 474997, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0702762603759766, "global_step": 474998, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0231008529663086, "global_step": 474999, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.142059803009033, "global_step": 475000, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1271064281463623, "global_step": 475001, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1314682960510254, "global_step": 475002, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0589966773986816, "global_step": 475003, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0689923763275146, "global_step": 475004, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.06274676322937, "global_step": 475005, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.151308536529541, "global_step": 475006, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0859150886535645, "global_step": 475007, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9799199104309082, "global_step": 475008, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0465192794799805, "global_step": 475009, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9887161254882812, "global_step": 475010, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1443963050842285, "global_step": 475011, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.087509870529175, "global_step": 475012, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9738978147506714, "global_step": 475013, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0312862396240234, "global_step": 475014, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0642764568328857, "global_step": 475015, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.997697114944458, "global_step": 475016, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.940974235534668, "global_step": 475017, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0576651096343994, "global_step": 475018, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0205395221710205, "global_step": 475019, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.062695026397705, "global_step": 475020, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.156294345855713, "global_step": 475021, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0340123176574707, "global_step": 475022, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0783679485321045, "global_step": 475023, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0101370811462402, "global_step": 475024, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.154160499572754, "global_step": 475025, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.06341290473938, "global_step": 475026, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0155961513519287, "global_step": 475027, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.180838108062744, "global_step": 475028, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0234580039978027, "global_step": 475029, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0618672370910645, "global_step": 475030, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0405561923980713, "global_step": 475031, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9999951124191284, "global_step": 475032, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0358381271362305, "global_step": 475033, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.13118577003479, "global_step": 475034, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.028615713119507, "global_step": 475035, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0866196155548096, "global_step": 475036, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0353503227233887, "global_step": 475037, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0080583095550537, "global_step": 475038, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.111379384994507, "global_step": 475039, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.037691354751587, "global_step": 475040, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.068124294281006, "global_step": 475041, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0202856063842773, "global_step": 475042, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0826339721679688, "global_step": 475043, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.119274139404297, "global_step": 475044, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.048633575439453, "global_step": 475045, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0917983055114746, "global_step": 475046, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0700507164001465, "global_step": 475047, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0946712493896484, "global_step": 475048, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.052140474319458, "global_step": 475049, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1448006629943848, "global_step": 475050, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.029609203338623, "global_step": 475051, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0661869049072266, "global_step": 475052, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1061508655548096, "global_step": 475053, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.13779616355896, "global_step": 475054, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0469021797180176, "global_step": 475055, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.072516918182373, "global_step": 475056, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0274078845977783, "global_step": 475057, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0859603881835938, "global_step": 475058, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1160945892333984, "global_step": 475059, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.146754026412964, "global_step": 475060, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0436205863952637, "global_step": 475061, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0476975440979004, "global_step": 475062, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0073840618133545, "global_step": 475063, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0431931018829346, "global_step": 475064, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0607845783233643, "global_step": 475065, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0283777713775635, "global_step": 475066, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0414812564849854, "global_step": 475067, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.160292863845825, "global_step": 475068, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0635132789611816, "global_step": 475069, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0793111324310303, "global_step": 475070, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.071826457977295, "global_step": 475071, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.030538320541382, "global_step": 475072, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9780837297439575, "global_step": 475073, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9901598691940308, "global_step": 475074, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.026597738265991, "global_step": 475075, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0592222213745117, "global_step": 475076, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1143932342529297, "global_step": 475077, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0214765071868896, "global_step": 475078, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0397863388061523, "global_step": 475079, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.039762258529663, "global_step": 475080, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0586867332458496, "global_step": 475081, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9967318773269653, "global_step": 475082, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0321245193481445, "global_step": 475083, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1601366996765137, "global_step": 475084, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.057361364364624, "global_step": 475085, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9770561456680298, "global_step": 475086, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.074845790863037, "global_step": 475087, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.030838966369629, "global_step": 475088, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.138000965118408, "global_step": 475089, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9982757568359375, "global_step": 475090, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1353228092193604, "global_step": 475091, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0514345169067383, "global_step": 475092, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.038461208343506, "global_step": 475093, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.04215669631958, "global_step": 475094, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.060842514038086, "global_step": 475095, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.084089756011963, "global_step": 475096, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0589699745178223, "global_step": 475097, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1462085247039795, "global_step": 475098, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.042330503463745, "global_step": 475099, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0461881160736084, "global_step": 475100, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1591403484344482, "global_step": 475101, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0224387645721436, "global_step": 475102, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.066230297088623, "global_step": 475103, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.01949405670166, "global_step": 475104, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0923452377319336, "global_step": 475105, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.037189245223999, "global_step": 475106, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0332891941070557, "global_step": 475107, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.111074924468994, "global_step": 475108, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0583722591400146, "global_step": 475109, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0030405521392822, "global_step": 475110, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1162638664245605, "global_step": 475111, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0217456817626953, "global_step": 475112, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0753917694091797, "global_step": 475113, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0055065155029297, "global_step": 475114, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9984736442565918, "global_step": 475115, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.109790325164795, "global_step": 475116, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.056286573410034, "global_step": 475117, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.031378984451294, "global_step": 475118, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.073939085006714, "global_step": 475119, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.053281307220459, "global_step": 475120, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.055946111679077, "global_step": 475121, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0978262424468994, "global_step": 475122, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.096454381942749, "global_step": 475123, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9996193647384644, "global_step": 475124, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9710230827331543, "global_step": 475125, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.996894121170044, "global_step": 475126, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.070571184158325, "global_step": 475127, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0228004455566406, "global_step": 475128, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0756850242614746, "global_step": 475129, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0741240978240967, "global_step": 475130, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1154019832611084, "global_step": 475131, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.066173791885376, "global_step": 475132, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9810513257980347, "global_step": 475133, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.06796932220459, "global_step": 475134, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0750467777252197, "global_step": 475135, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0508363246917725, "global_step": 475136, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0977654457092285, "global_step": 475137, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0035436153411865, "global_step": 475138, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1226909160614014, "global_step": 475139, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0370707511901855, "global_step": 475140, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.024639368057251, "global_step": 475141, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1737492084503174, "global_step": 475142, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.089237689971924, "global_step": 475143, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0550143718719482, "global_step": 475144, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0962436199188232, "global_step": 475145, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.106975555419922, "global_step": 475146, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.039154052734375, "global_step": 475147, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.077197551727295, "global_step": 475148, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9761794805526733, "global_step": 475149, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.022493600845337, "global_step": 475150, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.032555103302002, "global_step": 475151, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0703365802764893, "global_step": 475152, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0581212043762207, "global_step": 475153, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.114328145980835, "global_step": 475154, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.100048303604126, "global_step": 475155, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0164077281951904, "global_step": 475156, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.978011131286621, "global_step": 475157, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.067791700363159, "global_step": 475158, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0747785568237305, "global_step": 475159, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.065114736557007, "global_step": 475160, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9584649801254272, "global_step": 475161, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.006462812423706, "global_step": 475162, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.11918568611145, "global_step": 475163, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.013253688812256, "global_step": 475164, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0916907787323, "global_step": 475165, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1250643730163574, "global_step": 475166, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.099696159362793, "global_step": 475167, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0937583446502686, "global_step": 475168, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0485267639160156, "global_step": 475169, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.03503155708313, "global_step": 475170, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.024001121520996, "global_step": 475171, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.058398485183716, "global_step": 475172, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.114997625350952, "global_step": 475173, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0312886238098145, "global_step": 475174, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.028590440750122, "global_step": 475175, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.021588087081909, "global_step": 475176, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.101302146911621, "global_step": 475177, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1038806438446045, "global_step": 475178, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0139689445495605, "global_step": 475179, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.021967649459839, "global_step": 475180, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0299854278564453, "global_step": 475181, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0711584091186523, "global_step": 475182, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0673575401306152, "global_step": 475183, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.125950336456299, "global_step": 475184, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.081098794937134, "global_step": 475185, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0291948318481445, "global_step": 475186, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0465073585510254, "global_step": 475187, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0570976734161377, "global_step": 475188, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.046642780303955, "global_step": 475189, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.136326789855957, "global_step": 475190, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1897013187408447, "global_step": 475191, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.128793716430664, "global_step": 475192, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.092430353164673, "global_step": 475193, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0656614303588867, "global_step": 475194, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0995113849639893, "global_step": 475195, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.070014238357544, "global_step": 475196, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9937267303466797, "global_step": 475197, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.036269187927246, "global_step": 475198, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0618185997009277, "global_step": 475199, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0871236324310303, "global_step": 475200, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1316466331481934, "global_step": 475201, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.062180280685425, "global_step": 475202, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.071826934814453, "global_step": 475203, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0227017402648926, "global_step": 475204, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0789718627929688, "global_step": 475205, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9985958337783813, "global_step": 475206, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.074578285217285, "global_step": 475207, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.013009786605835, "global_step": 475208, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0341296195983887, "global_step": 475209, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1224923133850098, "global_step": 475210, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0718512535095215, "global_step": 475211, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.062147617340088, "global_step": 475212, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9912887811660767, "global_step": 475213, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.066455841064453, "global_step": 475214, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.061296224594116, "global_step": 475215, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.085984706878662, "global_step": 475216, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0407187938690186, "global_step": 475217, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0414857864379883, "global_step": 475218, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0440802574157715, "global_step": 475219, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0649538040161133, "global_step": 475220, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0457024574279785, "global_step": 475221, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1028754711151123, "global_step": 475222, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9739530086517334, "global_step": 475223, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0599405765533447, "global_step": 475224, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.989356279373169, "global_step": 475225, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1072983741760254, "global_step": 475226, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0729520320892334, "global_step": 475227, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0193192958831787, "global_step": 475228, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.186760902404785, "global_step": 475229, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0741119384765625, "global_step": 475230, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.070932626724243, "global_step": 475231, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0480148792266846, "global_step": 475232, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0594534873962402, "global_step": 475233, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9888323545455933, "global_step": 475234, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.061434745788574, "global_step": 475235, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1385843753814697, "global_step": 475236, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0067999362945557, "global_step": 475237, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0422046184539795, "global_step": 475238, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1013262271881104, "global_step": 475239, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1020214557647705, "global_step": 475240, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0672712326049805, "global_step": 475241, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1073484420776367, "global_step": 475242, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0350494384765625, "global_step": 475243, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0671374797821045, "global_step": 475244, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0700767040252686, "global_step": 475245, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1216955184936523, "global_step": 475246, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0463695526123047, "global_step": 475247, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1127588748931885, "global_step": 475248, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.080256700515747, "global_step": 475249, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9434853792190552, "global_step": 475250, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0026514530181885, "global_step": 475251, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0113065242767334, "global_step": 475252, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0950934886932373, "global_step": 475253, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0858802795410156, "global_step": 475254, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0140323638916016, "global_step": 475255, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0692825317382812, "global_step": 475256, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0564208030700684, "global_step": 475257, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0531983375549316, "global_step": 475258, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.004016399383545, "global_step": 475259, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.046997308731079, "global_step": 475260, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.037423610687256, "global_step": 475261, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.067779541015625, "global_step": 475262, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.100177049636841, "global_step": 475263, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0881764888763428, "global_step": 475264, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9662206172943115, "global_step": 475265, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1184730529785156, "global_step": 475266, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.115501880645752, "global_step": 475267, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1632907390594482, "global_step": 475268, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0992178916931152, "global_step": 475269, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.155555009841919, "global_step": 475270, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.128495216369629, "global_step": 475271, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.118417978286743, "global_step": 475272, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.041369915008545, "global_step": 475273, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0650508403778076, "global_step": 475274, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.122298002243042, "global_step": 475275, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.01603627204895, "global_step": 475276, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0602047443389893, "global_step": 475277, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0301120281219482, "global_step": 475278, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0999674797058105, "global_step": 475279, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9914355278015137, "global_step": 475280, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.001387357711792, "global_step": 475281, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.148998975753784, "global_step": 475282, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1440887451171875, "global_step": 475283, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.074186086654663, "global_step": 475284, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.094830274581909, "global_step": 475285, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.087963342666626, "global_step": 475286, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0587732791900635, "global_step": 475287, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0054714679718018, "global_step": 475288, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.043091058731079, "global_step": 475289, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1076276302337646, "global_step": 475290, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.036097764968872, "global_step": 475291, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0954880714416504, "global_step": 475292, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.11311936378479, "global_step": 475293, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.182995557785034, "global_step": 475294, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0914714336395264, "global_step": 475295, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0509746074676514, "global_step": 475296, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.031632423400879, "global_step": 475297, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0563504695892334, "global_step": 475298, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0273609161376953, "global_step": 475299, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0161030292510986, "global_step": 475300, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.090204954147339, "global_step": 475301, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9844087362289429, "global_step": 475302, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.093679904937744, "global_step": 475303, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9841818809509277, "global_step": 475304, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0753438472747803, "global_step": 475305, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.949986219406128, "global_step": 475306, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.091827154159546, "global_step": 475307, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.078674554824829, "global_step": 475308, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0653905868530273, "global_step": 475309, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0178961753845215, "global_step": 475310, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0733325481414795, "global_step": 475311, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0831243991851807, "global_step": 475312, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.115158796310425, "global_step": 475313, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0663325786590576, "global_step": 475314, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0010275840759277, "global_step": 475315, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.066817283630371, "global_step": 475316, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.01114821434021, "global_step": 475317, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0184378623962402, "global_step": 475318, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.116204023361206, "global_step": 475319, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1121761798858643, "global_step": 475320, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.008517265319824, "global_step": 475321, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.047055959701538, "global_step": 475322, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.027726173400879, "global_step": 475323, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0572261810302734, "global_step": 475324, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.006286382675171, "global_step": 475325, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0431454181671143, "global_step": 475326, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.093290328979492, "global_step": 475327, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.123490333557129, "global_step": 475328, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.031851053237915, "global_step": 475329, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9145413637161255, "global_step": 475330, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.072366952896118, "global_step": 475331, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.006044864654541, "global_step": 475332, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.062041759490967, "global_step": 475333, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9914498329162598, "global_step": 475334, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0039710998535156, "global_step": 475335, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0393002033233643, "global_step": 475336, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.01568865776062, "global_step": 475337, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.088297128677368, "global_step": 475338, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1251728534698486, "global_step": 475339, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.019460439682007, "global_step": 475340, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9805858135223389, "global_step": 475341, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.165766477584839, "global_step": 475342, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0189430713653564, "global_step": 475343, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0517115592956543, "global_step": 475344, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0610880851745605, "global_step": 475345, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.047825336456299, "global_step": 475346, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0689854621887207, "global_step": 475347, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.000927686691284, "global_step": 475348, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.018070697784424, "global_step": 475349, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0954644680023193, "global_step": 475350, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.044191360473633, "global_step": 475351, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9974238872528076, "global_step": 475352, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.150292158126831, "global_step": 475353, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0524542331695557, "global_step": 475354, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0549063682556152, "global_step": 475355, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.204840898513794, "global_step": 475356, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1341912746429443, "global_step": 475357, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.088132381439209, "global_step": 475358, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.067660331726074, "global_step": 475359, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.192427396774292, "global_step": 475360, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9129277467727661, "global_step": 475361, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.079030990600586, "global_step": 475362, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9773303270339966, "global_step": 475363, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.05281138420105, "global_step": 475364, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.112323760986328, "global_step": 475365, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.162827491760254, "global_step": 475366, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.009251832962036, "global_step": 475367, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.029383420944214, "global_step": 475368, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0625016689300537, "global_step": 475369, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0426433086395264, "global_step": 475370, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9846088886260986, "global_step": 475371, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1491072177886963, "global_step": 475372, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0205130577087402, "global_step": 475373, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.994316816329956, "global_step": 475374, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.107555389404297, "global_step": 475375, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0452842712402344, "global_step": 475376, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.110196352005005, "global_step": 475377, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.121065616607666, "global_step": 475378, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0696823596954346, "global_step": 475379, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0922999382019043, "global_step": 475380, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.113992929458618, "global_step": 475381, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.106842517852783, "global_step": 475382, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0372095108032227, "global_step": 475383, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0391414165496826, "global_step": 475384, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0816073417663574, "global_step": 475385, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1078333854675293, "global_step": 475386, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.172436237335205, "global_step": 475387, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.046790838241577, "global_step": 475388, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9453774690628052, "global_step": 475389, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.10286808013916, "global_step": 475390, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.082169771194458, "global_step": 475391, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9903675317764282, "global_step": 475392, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.978851556777954, "global_step": 475393, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.101156711578369, "global_step": 475394, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9726499319076538, "global_step": 475395, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9731225967407227, "global_step": 475396, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.059929609298706, "global_step": 475397, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0843982696533203, "global_step": 475398, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0011932849884033, "global_step": 475399, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0110504627227783, "global_step": 475400, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.003035545349121, "global_step": 475401, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0628743171691895, "global_step": 475402, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0823452472686768, "global_step": 475403, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0562868118286133, "global_step": 475404, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.974805235862732, "global_step": 475405, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1029224395751953, "global_step": 475406, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0947563648223877, "global_step": 475407, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0942721366882324, "global_step": 475408, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0476343631744385, "global_step": 475409, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0197594165802, "global_step": 475410, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.02866792678833, "global_step": 475411, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.05523681640625, "global_step": 475412, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0368263721466064, "global_step": 475413, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.107210397720337, "global_step": 475414, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0512866973876953, "global_step": 475415, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.070577383041382, "global_step": 475416, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0862460136413574, "global_step": 475417, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.011948347091675, "global_step": 475418, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0671494007110596, "global_step": 475419, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.076551675796509, "global_step": 475420, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.125600576400757, "global_step": 475421, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9354248046875, "global_step": 475422, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1368536949157715, "global_step": 475423, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1168181896209717, "global_step": 475424, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1085045337677, "global_step": 475425, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1095657348632812, "global_step": 475426, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1061336994171143, "global_step": 475427, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.050107479095459, "global_step": 475428, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1300392150878906, "global_step": 475429, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.010190725326538, "global_step": 475430, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.057598114013672, "global_step": 475431, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.098921537399292, "global_step": 475432, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1817901134490967, "global_step": 475433, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9920284748077393, "global_step": 475434, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1196820735931396, "global_step": 475435, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9968230724334717, "global_step": 475436, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0401017665863037, "global_step": 475437, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.095463752746582, "global_step": 475438, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9487360715866089, "global_step": 475439, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.044968366622925, "global_step": 475440, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.03212833404541, "global_step": 475441, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1211256980895996, "global_step": 475442, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.032388210296631, "global_step": 475443, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.104797840118408, "global_step": 475444, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1781623363494873, "global_step": 475445, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.981729507446289, "global_step": 475446, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0873939990997314, "global_step": 475447, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1189980506896973, "global_step": 475448, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0260448455810547, "global_step": 475449, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1385059356689453, "global_step": 475450, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1054868698120117, "global_step": 475451, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9874721765518188, "global_step": 475452, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.119760751724243, "global_step": 475453, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9892385005950928, "global_step": 475454, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0538127422332764, "global_step": 475455, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.036573886871338, "global_step": 475456, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.035877227783203, "global_step": 475457, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.026705265045166, "global_step": 475458, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0736048221588135, "global_step": 475459, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0243780612945557, "global_step": 475460, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.068068504333496, "global_step": 475461, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.113898515701294, "global_step": 475462, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.080456018447876, "global_step": 475463, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0783133506774902, "global_step": 475464, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.082613229751587, "global_step": 475465, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9985125064849854, "global_step": 475466, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0918285846710205, "global_step": 475467, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.089160442352295, "global_step": 475468, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9600379467010498, "global_step": 475469, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.061314821243286, "global_step": 475470, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.035329580307007, "global_step": 475471, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0620908737182617, "global_step": 475472, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.027188301086426, "global_step": 475473, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.059577703475952, "global_step": 475474, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.131042957305908, "global_step": 475475, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.021422863006592, "global_step": 475476, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0248756408691406, "global_step": 475477, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0291378498077393, "global_step": 475478, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.11440110206604, "global_step": 475479, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.144326686859131, "global_step": 475480, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0670166015625, "global_step": 475481, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0980212688446045, "global_step": 475482, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1479783058166504, "global_step": 475483, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9908771514892578, "global_step": 475484, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0854172706604004, "global_step": 475485, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1446890830993652, "global_step": 475486, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0466737747192383, "global_step": 475487, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1163456439971924, "global_step": 475488, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.020244836807251, "global_step": 475489, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0831594467163086, "global_step": 475490, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1298365592956543, "global_step": 475491, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0843279361724854, "global_step": 475492, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0488338470458984, "global_step": 475493, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1518068313598633, "global_step": 475494, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0074315071105957, "global_step": 475495, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0671443939208984, "global_step": 475496, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1149182319641113, "global_step": 475497, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0867702960968018, "global_step": 475498, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0898191928863525, "global_step": 475499, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9753797054290771, "global_step": 475500, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1248068809509277, "global_step": 475501, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.073272943496704, "global_step": 475502, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0507047176361084, "global_step": 475503, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0293924808502197, "global_step": 475504, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0617547035217285, "global_step": 475505, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0754971504211426, "global_step": 475506, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0709269046783447, "global_step": 475507, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.031212329864502, "global_step": 475508, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.135096311569214, "global_step": 475509, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.052518129348755, "global_step": 475510, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.052332878112793, "global_step": 475511, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1351683139801025, "global_step": 475512, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0742733478546143, "global_step": 475513, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9617784023284912, "global_step": 475514, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.007699966430664, "global_step": 475515, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.041623115539551, "global_step": 475516, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0358855724334717, "global_step": 475517, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0472636222839355, "global_step": 475518, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0388782024383545, "global_step": 475519, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0321035385131836, "global_step": 475520, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.035093307495117, "global_step": 475521, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.013401746749878, "global_step": 475522, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0488486289978027, "global_step": 475523, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1030473709106445, "global_step": 475524, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0992915630340576, "global_step": 475525, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0092339515686035, "global_step": 475526, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0948002338409424, "global_step": 475527, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.990144968032837, "global_step": 475528, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.011122941970825, "global_step": 475529, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0849719047546387, "global_step": 475530, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.137157440185547, "global_step": 475531, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9973608255386353, "global_step": 475532, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.031740188598633, "global_step": 475533, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0619304180145264, "global_step": 475534, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0425095558166504, "global_step": 475535, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.10129451751709, "global_step": 475536, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0857954025268555, "global_step": 475537, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1024792194366455, "global_step": 475538, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.128126382827759, "global_step": 475539, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.971758246421814, "global_step": 475540, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.085754871368408, "global_step": 475541, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.109308958053589, "global_step": 475542, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1244754791259766, "global_step": 475543, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.045346736907959, "global_step": 475544, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.060830593109131, "global_step": 475545, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1012728214263916, "global_step": 475546, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.101402997970581, "global_step": 475547, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0434837341308594, "global_step": 475548, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0801939964294434, "global_step": 475549, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0620734691619873, "global_step": 475550, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.084073543548584, "global_step": 475551, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.053499698638916, "global_step": 475552, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.084153413772583, "global_step": 475553, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.059892177581787, "global_step": 475554, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1215410232543945, "global_step": 475555, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0452158451080322, "global_step": 475556, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.006747245788574, "global_step": 475557, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0765674114227295, "global_step": 475558, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.011727809906006, "global_step": 475559, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.087380886077881, "global_step": 475560, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9933830499649048, "global_step": 475561, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0813019275665283, "global_step": 475562, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.085557222366333, "global_step": 475563, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1350560188293457, "global_step": 475564, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.024005889892578, "global_step": 475565, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9863592386245728, "global_step": 475566, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0783896446228027, "global_step": 475567, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0867016315460205, "global_step": 475568, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0348453521728516, "global_step": 475569, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.09088134765625, "global_step": 475570, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0074622631073, "global_step": 475571, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.043513298034668, "global_step": 475572, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0687432289123535, "global_step": 475573, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0950043201446533, "global_step": 475574, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.989198923110962, "global_step": 475575, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0032780170440674, "global_step": 475576, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0131402015686035, "global_step": 475577, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.107128858566284, "global_step": 475578, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9949238300323486, "global_step": 475579, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0818819999694824, "global_step": 475580, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.060858964920044, "global_step": 475581, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1788783073425293, "global_step": 475582, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.105508804321289, "global_step": 475583, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0350937843322754, "global_step": 475584, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0795624256134033, "global_step": 475585, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1148462295532227, "global_step": 475586, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.079294204711914, "global_step": 475587, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0187575817108154, "global_step": 475588, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1190247535705566, "global_step": 475589, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0172548294067383, "global_step": 475590, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.004138946533203, "global_step": 475591, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.070068359375, "global_step": 475592, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0778861045837402, "global_step": 475593, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0566365718841553, "global_step": 475594, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1226966381073, "global_step": 475595, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0116920471191406, "global_step": 475596, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.129422187805176, "global_step": 475597, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0009541511535645, "global_step": 475598, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.092057466506958, "global_step": 475599, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0942153930664062, "global_step": 475600, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0970332622528076, "global_step": 475601, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.150167942047119, "global_step": 475602, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.056100606918335, "global_step": 475603, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.02347993850708, "global_step": 475604, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0017828941345215, "global_step": 475605, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0559468269348145, "global_step": 475606, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.080148935317993, "global_step": 475607, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1164519786834717, "global_step": 475608, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0664937496185303, "global_step": 475609, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0325496196746826, "global_step": 475610, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.080515146255493, "global_step": 475611, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.101119041442871, "global_step": 475612, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0870916843414307, "global_step": 475613, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.030355215072632, "global_step": 475614, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0262718200683594, "global_step": 475615, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.102041482925415, "global_step": 475616, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.11201548576355, "global_step": 475617, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0820960998535156, "global_step": 475618, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0761094093322754, "global_step": 475619, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9821397066116333, "global_step": 475620, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.048743486404419, "global_step": 475621, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0390238761901855, "global_step": 475622, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.006398916244507, "global_step": 475623, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.079747200012207, "global_step": 475624, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0348963737487793, "global_step": 475625, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0340843200683594, "global_step": 475626, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.106905221939087, "global_step": 475627, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0899367332458496, "global_step": 475628, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0394480228424072, "global_step": 475629, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9695700407028198, "global_step": 475630, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0311851501464844, "global_step": 475631, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.140305280685425, "global_step": 475632, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.094940662384033, "global_step": 475633, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1138253211975098, "global_step": 475634, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0869035720825195, "global_step": 475635, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.051870584487915, "global_step": 475636, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.079336643218994, "global_step": 475637, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.082181215286255, "global_step": 475638, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.081616163253784, "global_step": 475639, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0439140796661377, "global_step": 475640, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0769519805908203, "global_step": 475641, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.122042179107666, "global_step": 475642, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0363993644714355, "global_step": 475643, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.061011791229248, "global_step": 475644, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0503640174865723, "global_step": 475645, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.011807918548584, "global_step": 475646, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0089573860168457, "global_step": 475647, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.152998924255371, "global_step": 475648, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1130897998809814, "global_step": 475649, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.097907066345215, "global_step": 475650, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1255006790161133, "global_step": 475651, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.031296730041504, "global_step": 475652, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9874168634414673, "global_step": 475653, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.062549591064453, "global_step": 475654, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.00449800491333, "global_step": 475655, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0594823360443115, "global_step": 475656, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1914479732513428, "global_step": 475657, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.071728467941284, "global_step": 475658, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.111757755279541, "global_step": 475659, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.073380947113037, "global_step": 475660, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.089197874069214, "global_step": 475661, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.03450608253479, "global_step": 475662, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.14266300201416, "global_step": 475663, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0022714138031006, "global_step": 475664, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1180689334869385, "global_step": 475665, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1270804405212402, "global_step": 475666, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0887248516082764, "global_step": 475667, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0957491397857666, "global_step": 475668, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9769078493118286, "global_step": 475669, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.042727470397949, "global_step": 475670, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.077383041381836, "global_step": 475671, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.067797899246216, "global_step": 475672, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0634939670562744, "global_step": 475673, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9844141006469727, "global_step": 475674, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.102175235748291, "global_step": 475675, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0310988426208496, "global_step": 475676, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.994693636894226, "global_step": 475677, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.057788610458374, "global_step": 475678, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.031484365463257, "global_step": 475679, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0830776691436768, "global_step": 475680, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0157811641693115, "global_step": 475681, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.040792226791382, "global_step": 475682, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0710089206695557, "global_step": 475683, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.071638822555542, "global_step": 475684, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1173155307769775, "global_step": 475685, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.188378095626831, "global_step": 475686, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1552271842956543, "global_step": 475687, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1533396244049072, "global_step": 475688, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.084502696990967, "global_step": 475689, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1668848991394043, "global_step": 475690, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0697813034057617, "global_step": 475691, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.130845308303833, "global_step": 475692, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.123441696166992, "global_step": 475693, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.030949115753174, "global_step": 475694, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0324649810791016, "global_step": 475695, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1133906841278076, "global_step": 475696, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.039602041244507, "global_step": 475697, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1260080337524414, "global_step": 475698, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.099050521850586, "global_step": 475699, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.062375545501709, "global_step": 475700, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.085488796234131, "global_step": 475701, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.120495080947876, "global_step": 475702, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0779199600219727, "global_step": 475703, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0350141525268555, "global_step": 475704, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.132920503616333, "global_step": 475705, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.057398796081543, "global_step": 475706, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.082902193069458, "global_step": 475707, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0274715423583984, "global_step": 475708, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9796159267425537, "global_step": 475709, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.002777099609375, "global_step": 475710, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1127240657806396, "global_step": 475711, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.028259038925171, "global_step": 475712, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.119629383087158, "global_step": 475713, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0534281730651855, "global_step": 475714, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.089338779449463, "global_step": 475715, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0907819271087646, "global_step": 475716, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.043630838394165, "global_step": 475717, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.033900022506714, "global_step": 475718, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.038536310195923, "global_step": 475719, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0445241928100586, "global_step": 475720, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.059445381164551, "global_step": 475721, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1167895793914795, "global_step": 475722, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0550312995910645, "global_step": 475723, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0421175956726074, "global_step": 475724, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9823386669158936, "global_step": 475725, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9666342735290527, "global_step": 475726, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.122276782989502, "global_step": 475727, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.064310073852539, "global_step": 475728, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0316765308380127, "global_step": 475729, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0659193992614746, "global_step": 475730, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1238691806793213, "global_step": 475731, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0941288471221924, "global_step": 475732, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.982579231262207, "global_step": 475733, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.056196451187134, "global_step": 475734, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.177372455596924, "global_step": 475735, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1312386989593506, "global_step": 475736, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1570043563842773, "global_step": 475737, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0031445026397705, "global_step": 475738, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0177812576293945, "global_step": 475739, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.2315094470977783, "global_step": 475740, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.101841926574707, "global_step": 475741, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1488189697265625, "global_step": 475742, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9839746952056885, "global_step": 475743, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0999553203582764, "global_step": 475744, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.073206663131714, "global_step": 475745, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.11354398727417, "global_step": 475746, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1014373302459717, "global_step": 475747, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0960373878479004, "global_step": 475748, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.065171480178833, "global_step": 475749, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1115503311157227, "global_step": 475750, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0864357948303223, "global_step": 475751, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0567355155944824, "global_step": 475752, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0786452293395996, "global_step": 475753, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1296627521514893, "global_step": 475754, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0657782554626465, "global_step": 475755, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.093059778213501, "global_step": 475756, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0269696712493896, "global_step": 475757, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9080389738082886, "global_step": 475758, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9815313816070557, "global_step": 475759, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0341787338256836, "global_step": 475760, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.052783966064453, "global_step": 475761, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1715710163116455, "global_step": 475762, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.078289747238159, "global_step": 475763, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.035867214202881, "global_step": 475764, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.995792031288147, "global_step": 475765, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0463900566101074, "global_step": 475766, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.045145034790039, "global_step": 475767, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0679306983947754, "global_step": 475768, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1617884635925293, "global_step": 475769, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.006995677947998, "global_step": 475770, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0798017978668213, "global_step": 475771, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.022480010986328, "global_step": 475772, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.031381368637085, "global_step": 475773, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0115668773651123, "global_step": 475774, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0021536350250244, "global_step": 475775, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9950655698776245, "global_step": 475776, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9895216226577759, "global_step": 475777, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0451812744140625, "global_step": 475778, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1100847721099854, "global_step": 475779, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0544471740722656, "global_step": 475780, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0028820037841797, "global_step": 475781, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0643529891967773, "global_step": 475782, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0790014266967773, "global_step": 475783, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1078341007232666, "global_step": 475784, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.115626811981201, "global_step": 475785, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0641579627990723, "global_step": 475786, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0932140350341797, "global_step": 475787, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.068751573562622, "global_step": 475788, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.970469355583191, "global_step": 475789, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0323166847229004, "global_step": 475790, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0449533462524414, "global_step": 475791, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1384451389312744, "global_step": 475792, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1437385082244873, "global_step": 475793, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1227738857269287, "global_step": 475794, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0318093299865723, "global_step": 475795, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.916211724281311, "global_step": 475796, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1199474334716797, "global_step": 475797, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0657477378845215, "global_step": 475798, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0523109436035156, "global_step": 475799, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1603024005889893, "global_step": 475800, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9870359897613525, "global_step": 475801, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1268527507781982, "global_step": 475802, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0739474296569824, "global_step": 475803, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0731940269470215, "global_step": 475804, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1394901275634766, "global_step": 475805, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.04872989654541, "global_step": 475806, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.963292121887207, "global_step": 475807, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0666298866271973, "global_step": 475808, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1412246227264404, "global_step": 475809, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9675277471542358, "global_step": 475810, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1099417209625244, "global_step": 475811, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.058180809020996, "global_step": 475812, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.09416127204895, "global_step": 475813, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0622122287750244, "global_step": 475814, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.013686418533325, "global_step": 475815, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0097806453704834, "global_step": 475816, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1308515071868896, "global_step": 475817, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0476953983306885, "global_step": 475818, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0997040271759033, "global_step": 475819, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1172311305999756, "global_step": 475820, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0469658374786377, "global_step": 475821, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.059173345565796, "global_step": 475822, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1191647052764893, "global_step": 475823, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.116562604904175, "global_step": 475824, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0391392707824707, "global_step": 475825, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0818533897399902, "global_step": 475826, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0450477600097656, "global_step": 475827, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0374643802642822, "global_step": 475828, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0221822261810303, "global_step": 475829, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0628507137298584, "global_step": 475830, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0610218048095703, "global_step": 475831, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0397307872772217, "global_step": 475832, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.049151659011841, "global_step": 475833, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0518407821655273, "global_step": 475834, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.032465696334839, "global_step": 475835, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1193687915802, "global_step": 475836, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9474529027938843, "global_step": 475837, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0160303115844727, "global_step": 475838, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1132194995880127, "global_step": 475839, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1211371421813965, "global_step": 475840, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0582287311553955, "global_step": 475841, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0362048149108887, "global_step": 475842, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.085789203643799, "global_step": 475843, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0083162784576416, "global_step": 475844, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.009644031524658, "global_step": 475845, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9637162685394287, "global_step": 475846, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9921491146087646, "global_step": 475847, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1110308170318604, "global_step": 475848, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.028531074523926, "global_step": 475849, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.08990740776062, "global_step": 475850, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.128511667251587, "global_step": 475851, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0936920642852783, "global_step": 475852, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0501792430877686, "global_step": 475853, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0301082134246826, "global_step": 475854, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.059737205505371, "global_step": 475855, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0256340503692627, "global_step": 475856, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0758957862854004, "global_step": 475857, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0245656967163086, "global_step": 475858, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0183322429656982, "global_step": 475859, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.130491018295288, "global_step": 475860, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0264296531677246, "global_step": 475861, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0236713886260986, "global_step": 475862, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.205214738845825, "global_step": 475863, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1278371810913086, "global_step": 475864, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.082869291305542, "global_step": 475865, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0780344009399414, "global_step": 475866, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0582306385040283, "global_step": 475867, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.096440553665161, "global_step": 475868, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1081085205078125, "global_step": 475869, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.129786491394043, "global_step": 475870, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0570321083068848, "global_step": 475871, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9456837177276611, "global_step": 475872, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.058379888534546, "global_step": 475873, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0121383666992188, "global_step": 475874, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9911912679672241, "global_step": 475875, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.112112045288086, "global_step": 475876, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0861544609069824, "global_step": 475877, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0301053524017334, "global_step": 475878, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1348025798797607, "global_step": 475879, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0292654037475586, "global_step": 475880, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1464879512786865, "global_step": 475881, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0641865730285645, "global_step": 475882, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.033249855041504, "global_step": 475883, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.994877576828003, "global_step": 475884, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.021244764328003, "global_step": 475885, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0573720932006836, "global_step": 475886, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0561633110046387, "global_step": 475887, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0526914596557617, "global_step": 475888, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0640721321105957, "global_step": 475889, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.062443494796753, "global_step": 475890, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9336553812026978, "global_step": 475891, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.115818977355957, "global_step": 475892, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.01157546043396, "global_step": 475893, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1241655349731445, "global_step": 475894, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0888469219207764, "global_step": 475895, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0837554931640625, "global_step": 475896, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0944743156433105, "global_step": 475897, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0197501182556152, "global_step": 475898, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.1676535606384277, "global_step": 475899, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.082508087158203, "global_step": 475900, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0463314056396484, "global_step": 475901, "epoch": 840, "lr": 5e-05}
{"train_loss": 1.9900727272033691, "global_step": 475902, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0360682010650635, "global_step": 475903, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.17266583442688, "global_step": 475904, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.007341146469116, "global_step": 475905, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.083237886428833, "global_step": 475906, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0341594219207764, "global_step": 475907, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0731089115142822, "global_step": 475908, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0668246746063232, "global_step": 475909, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.105116844177246, "global_step": 475910, "epoch": 840, "lr": 5e-05}
{"train_loss": 2.0635464191436768, "global_step": 475911, "epoch": 840, "lr": 5e-05, "val_loss": 5.6941914558410645, "test_reconst_mse": 0.07345110923051834}
{"train_loss": 2.0305473804473877, "global_step": 475912, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0071303844451904, "global_step": 475913, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0078022480010986, "global_step": 475914, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0031750202178955, "global_step": 475915, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.118595600128174, "global_step": 475916, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.043835163116455, "global_step": 475917, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.140345573425293, "global_step": 475918, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0507092475891113, "global_step": 475919, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.000319242477417, "global_step": 475920, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9943318367004395, "global_step": 475921, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.111135482788086, "global_step": 475922, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0380501747131348, "global_step": 475923, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.094006299972534, "global_step": 475924, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0863566398620605, "global_step": 475925, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.032923460006714, "global_step": 475926, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.042367935180664, "global_step": 475927, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0627336502075195, "global_step": 475928, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0834884643554688, "global_step": 475929, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.108534812927246, "global_step": 475930, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0723495483398438, "global_step": 475931, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.034350872039795, "global_step": 475932, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.134157657623291, "global_step": 475933, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0584046840667725, "global_step": 475934, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0500142574310303, "global_step": 475935, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0706770420074463, "global_step": 475936, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.109924077987671, "global_step": 475937, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1883480548858643, "global_step": 475938, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9563864469528198, "global_step": 475939, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0271358489990234, "global_step": 475940, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9478988647460938, "global_step": 475941, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.087902307510376, "global_step": 475942, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0526132583618164, "global_step": 475943, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0637001991271973, "global_step": 475944, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.078460216522217, "global_step": 475945, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9490221738815308, "global_step": 475946, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0585269927978516, "global_step": 475947, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.129725456237793, "global_step": 475948, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.050778865814209, "global_step": 475949, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1297972202301025, "global_step": 475950, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.033294677734375, "global_step": 475951, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.073674440383911, "global_step": 475952, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0086331367492676, "global_step": 475953, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0515944957733154, "global_step": 475954, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1421663761138916, "global_step": 475955, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0620899200439453, "global_step": 475956, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0018699169158936, "global_step": 475957, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.068830966949463, "global_step": 475958, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1277570724487305, "global_step": 475959, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.039839029312134, "global_step": 475960, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0812737941741943, "global_step": 475961, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.994214653968811, "global_step": 475962, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1078429222106934, "global_step": 475963, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0353081226348877, "global_step": 475964, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0980851650238037, "global_step": 475965, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0305898189544678, "global_step": 475966, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.098909378051758, "global_step": 475967, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.029635190963745, "global_step": 475968, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0260672569274902, "global_step": 475969, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.105184555053711, "global_step": 475970, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9956951141357422, "global_step": 475971, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0821473598480225, "global_step": 475972, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.072727680206299, "global_step": 475973, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.106698751449585, "global_step": 475974, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.113039970397949, "global_step": 475975, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.097080707550049, "global_step": 475976, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0753045082092285, "global_step": 475977, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0794661045074463, "global_step": 475978, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9832017421722412, "global_step": 475979, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.135984420776367, "global_step": 475980, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.069550037384033, "global_step": 475981, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.007248640060425, "global_step": 475982, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0238399505615234, "global_step": 475983, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.09663987159729, "global_step": 475984, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9993274211883545, "global_step": 475985, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.075441360473633, "global_step": 475986, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.087528944015503, "global_step": 475987, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0699121952056885, "global_step": 475988, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.068051815032959, "global_step": 475989, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.113581418991089, "global_step": 475990, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0652353763580322, "global_step": 475991, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.094345808029175, "global_step": 475992, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.09769606590271, "global_step": 475993, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0869617462158203, "global_step": 475994, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.078388214111328, "global_step": 475995, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1045308113098145, "global_step": 475996, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.102015256881714, "global_step": 475997, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.073885202407837, "global_step": 475998, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0867302417755127, "global_step": 475999, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0330862998962402, "global_step": 476000, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.016496181488037, "global_step": 476001, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9955190420150757, "global_step": 476002, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.107396125793457, "global_step": 476003, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1564857959747314, "global_step": 476004, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1087327003479004, "global_step": 476005, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0108299255371094, "global_step": 476006, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.04776668548584, "global_step": 476007, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0361509323120117, "global_step": 476008, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1370961666107178, "global_step": 476009, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1259164810180664, "global_step": 476010, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1230173110961914, "global_step": 476011, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0337560176849365, "global_step": 476012, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.2006590366363525, "global_step": 476013, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.103482961654663, "global_step": 476014, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.072441816329956, "global_step": 476015, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0369625091552734, "global_step": 476016, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.148773431777954, "global_step": 476017, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0583558082580566, "global_step": 476018, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0287888050079346, "global_step": 476019, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.132103443145752, "global_step": 476020, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0255184173583984, "global_step": 476021, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0674614906311035, "global_step": 476022, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0511507987976074, "global_step": 476023, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.020055055618286, "global_step": 476024, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.114964485168457, "global_step": 476025, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1245028972625732, "global_step": 476026, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9755979776382446, "global_step": 476027, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1000418663024902, "global_step": 476028, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.013503074645996, "global_step": 476029, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0101568698883057, "global_step": 476030, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1311752796173096, "global_step": 476031, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0171008110046387, "global_step": 476032, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0698952674865723, "global_step": 476033, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0303194522857666, "global_step": 476034, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0059361457824707, "global_step": 476035, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9289615154266357, "global_step": 476036, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.10235595703125, "global_step": 476037, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.009441614151001, "global_step": 476038, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.037834405899048, "global_step": 476039, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.099282741546631, "global_step": 476040, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.11012864112854, "global_step": 476041, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.962441325187683, "global_step": 476042, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0361530780792236, "global_step": 476043, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0774946212768555, "global_step": 476044, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.052703619003296, "global_step": 476045, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1203646659851074, "global_step": 476046, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.079113721847534, "global_step": 476047, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1227359771728516, "global_step": 476048, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0994365215301514, "global_step": 476049, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1563074588775635, "global_step": 476050, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.01249361038208, "global_step": 476051, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0403082370758057, "global_step": 476052, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0868642330169678, "global_step": 476053, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0447988510131836, "global_step": 476054, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0634403228759766, "global_step": 476055, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0605647563934326, "global_step": 476056, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1220366954803467, "global_step": 476057, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.013359546661377, "global_step": 476058, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.163647174835205, "global_step": 476059, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9774237871170044, "global_step": 476060, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.998291254043579, "global_step": 476061, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.031259298324585, "global_step": 476062, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0692803859710693, "global_step": 476063, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.042633295059204, "global_step": 476064, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0249807834625244, "global_step": 476065, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.078029155731201, "global_step": 476066, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9959403276443481, "global_step": 476067, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.064995050430298, "global_step": 476068, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.983622670173645, "global_step": 476069, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.077241897583008, "global_step": 476070, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.984392523765564, "global_step": 476071, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1412370204925537, "global_step": 476072, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9835621118545532, "global_step": 476073, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9594801664352417, "global_step": 476074, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0848898887634277, "global_step": 476075, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1363282203674316, "global_step": 476076, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0738160610198975, "global_step": 476077, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.06772780418396, "global_step": 476078, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.082148790359497, "global_step": 476079, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.024543285369873, "global_step": 476080, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1252238750457764, "global_step": 476081, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.032835006713867, "global_step": 476082, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.040173292160034, "global_step": 476083, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1439874172210693, "global_step": 476084, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1087605953216553, "global_step": 476085, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1072676181793213, "global_step": 476086, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1269876956939697, "global_step": 476087, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.02382493019104, "global_step": 476088, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0344650745391846, "global_step": 476089, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0680603981018066, "global_step": 476090, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0597920417785645, "global_step": 476091, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.076103925704956, "global_step": 476092, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9977543354034424, "global_step": 476093, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.091454267501831, "global_step": 476094, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0233864784240723, "global_step": 476095, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.016223430633545, "global_step": 476096, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9636884927749634, "global_step": 476097, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0414469242095947, "global_step": 476098, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.070984125137329, "global_step": 476099, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0284945964813232, "global_step": 476100, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.127476453781128, "global_step": 476101, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.064023494720459, "global_step": 476102, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0984084606170654, "global_step": 476103, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0435526371002197, "global_step": 476104, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0972237586975098, "global_step": 476105, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0064926147460938, "global_step": 476106, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0230445861816406, "global_step": 476107, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.972021460533142, "global_step": 476108, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.02962064743042, "global_step": 476109, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.023294448852539, "global_step": 476110, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0820510387420654, "global_step": 476111, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.976739525794983, "global_step": 476112, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9455573558807373, "global_step": 476113, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0536327362060547, "global_step": 476114, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.06992506980896, "global_step": 476115, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0559468269348145, "global_step": 476116, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.092411518096924, "global_step": 476117, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1093878746032715, "global_step": 476118, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1226115226745605, "global_step": 476119, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9836363792419434, "global_step": 476120, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0176994800567627, "global_step": 476121, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0233747959136963, "global_step": 476122, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.057731866836548, "global_step": 476123, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.156440019607544, "global_step": 476124, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9860848188400269, "global_step": 476125, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0037214756011963, "global_step": 476126, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1058168411254883, "global_step": 476127, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.066190719604492, "global_step": 476128, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1316776275634766, "global_step": 476129, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1372759342193604, "global_step": 476130, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.04054594039917, "global_step": 476131, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1200222969055176, "global_step": 476132, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.069005012512207, "global_step": 476133, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.013460636138916, "global_step": 476134, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0520966053009033, "global_step": 476135, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1253905296325684, "global_step": 476136, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9382346868515015, "global_step": 476137, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0599637031555176, "global_step": 476138, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.990681529045105, "global_step": 476139, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.064432144165039, "global_step": 476140, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.126438856124878, "global_step": 476141, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0315325260162354, "global_step": 476142, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.028055191040039, "global_step": 476143, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1017634868621826, "global_step": 476144, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1007747650146484, "global_step": 476145, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.056570053100586, "global_step": 476146, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.050032138824463, "global_step": 476147, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0062527656555176, "global_step": 476148, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0867085456848145, "global_step": 476149, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.091338872909546, "global_step": 476150, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0716712474823, "global_step": 476151, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0708465576171875, "global_step": 476152, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0706725120544434, "global_step": 476153, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0174176692962646, "global_step": 476154, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.006758213043213, "global_step": 476155, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0760083198547363, "global_step": 476156, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.049354076385498, "global_step": 476157, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1075832843780518, "global_step": 476158, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1830222606658936, "global_step": 476159, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.998187780380249, "global_step": 476160, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.032973527908325, "global_step": 476161, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.124603033065796, "global_step": 476162, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0543577671051025, "global_step": 476163, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0535435676574707, "global_step": 476164, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.063028573989868, "global_step": 476165, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.039456844329834, "global_step": 476166, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0861809253692627, "global_step": 476167, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.097120761871338, "global_step": 476168, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.021031618118286, "global_step": 476169, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.019663095474243, "global_step": 476170, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.02209210395813, "global_step": 476171, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0073626041412354, "global_step": 476172, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0887699127197266, "global_step": 476173, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9887737035751343, "global_step": 476174, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0289297103881836, "global_step": 476175, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0818402767181396, "global_step": 476176, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0003416538238525, "global_step": 476177, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1170289516448975, "global_step": 476178, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.052227735519409, "global_step": 476179, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9592583179473877, "global_step": 476180, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.064203977584839, "global_step": 476181, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.8644970655441284, "global_step": 476182, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0315563678741455, "global_step": 476183, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1270854473114014, "global_step": 476184, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.049267292022705, "global_step": 476185, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1112983226776123, "global_step": 476186, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0269198417663574, "global_step": 476187, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0420265197753906, "global_step": 476188, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.186573028564453, "global_step": 476189, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1006252765655518, "global_step": 476190, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1832478046417236, "global_step": 476191, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1016221046447754, "global_step": 476192, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.07108736038208, "global_step": 476193, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0867533683776855, "global_step": 476194, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0520565509796143, "global_step": 476195, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.022360324859619, "global_step": 476196, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9909175634384155, "global_step": 476197, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.105804443359375, "global_step": 476198, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0074832439422607, "global_step": 476199, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0508103370666504, "global_step": 476200, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.97606360912323, "global_step": 476201, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0229384899139404, "global_step": 476202, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.032505512237549, "global_step": 476203, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1512365341186523, "global_step": 476204, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.102039098739624, "global_step": 476205, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.108074188232422, "global_step": 476206, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0766890048980713, "global_step": 476207, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9623509645462036, "global_step": 476208, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1523187160491943, "global_step": 476209, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0644283294677734, "global_step": 476210, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9924068450927734, "global_step": 476211, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.11543607711792, "global_step": 476212, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.035623788833618, "global_step": 476213, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9493895769119263, "global_step": 476214, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.050173044204712, "global_step": 476215, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0320017337799072, "global_step": 476216, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.123544216156006, "global_step": 476217, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1191020011901855, "global_step": 476218, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0544674396514893, "global_step": 476219, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0895297527313232, "global_step": 476220, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0796868801116943, "global_step": 476221, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0347228050231934, "global_step": 476222, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1599366664886475, "global_step": 476223, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0338876247406006, "global_step": 476224, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1060831546783447, "global_step": 476225, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0292820930480957, "global_step": 476226, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0463573932647705, "global_step": 476227, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0842092037200928, "global_step": 476228, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0641493797302246, "global_step": 476229, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0634207725524902, "global_step": 476230, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.092625379562378, "global_step": 476231, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.021395444869995, "global_step": 476232, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.052595615386963, "global_step": 476233, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0919606685638428, "global_step": 476234, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9561254978179932, "global_step": 476235, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1011440753936768, "global_step": 476236, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0001463890075684, "global_step": 476237, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0423405170440674, "global_step": 476238, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.043787717819214, "global_step": 476239, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9893543720245361, "global_step": 476240, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0684406757354736, "global_step": 476241, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.069577932357788, "global_step": 476242, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0876221656799316, "global_step": 476243, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.05792498588562, "global_step": 476244, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0447745323181152, "global_step": 476245, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0208420753479004, "global_step": 476246, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0972073078155518, "global_step": 476247, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.052262783050537, "global_step": 476248, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.008754253387451, "global_step": 476249, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.09627103805542, "global_step": 476250, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.063478946685791, "global_step": 476251, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0600392818450928, "global_step": 476252, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.092818021774292, "global_step": 476253, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.029810905456543, "global_step": 476254, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0751376152038574, "global_step": 476255, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.031428098678589, "global_step": 476256, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1233763694763184, "global_step": 476257, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.98861563205719, "global_step": 476258, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1086740493774414, "global_step": 476259, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0341198444366455, "global_step": 476260, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.042860984802246, "global_step": 476261, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1406118869781494, "global_step": 476262, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.065891981124878, "global_step": 476263, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0405654907226562, "global_step": 476264, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.068352699279785, "global_step": 476265, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0500614643096924, "global_step": 476266, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1106438636779785, "global_step": 476267, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0181736946105957, "global_step": 476268, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1474368572235107, "global_step": 476269, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.112881660461426, "global_step": 476270, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0626206398010254, "global_step": 476271, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.102449655532837, "global_step": 476272, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0587828159332275, "global_step": 476273, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1041464805603027, "global_step": 476274, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9939848184585571, "global_step": 476275, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.05696964263916, "global_step": 476276, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0075483322143555, "global_step": 476277, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9699023962020874, "global_step": 476278, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.067509412765503, "global_step": 476279, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.089242458343506, "global_step": 476280, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1200132369995117, "global_step": 476281, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.091493606567383, "global_step": 476282, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0233821868896484, "global_step": 476283, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0747668743133545, "global_step": 476284, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0334975719451904, "global_step": 476285, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0728323459625244, "global_step": 476286, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0521483421325684, "global_step": 476287, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.065734386444092, "global_step": 476288, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.121583938598633, "global_step": 476289, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0454540252685547, "global_step": 476290, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0863325595855713, "global_step": 476291, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1259636878967285, "global_step": 476292, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.072002649307251, "global_step": 476293, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.070741891860962, "global_step": 476294, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9852038621902466, "global_step": 476295, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.054935932159424, "global_step": 476296, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0700621604919434, "global_step": 476297, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.031766176223755, "global_step": 476298, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.083178758621216, "global_step": 476299, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.032731771469116, "global_step": 476300, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0642378330230713, "global_step": 476301, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.024016857147217, "global_step": 476302, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.060732126235962, "global_step": 476303, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.052255630493164, "global_step": 476304, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1346981525421143, "global_step": 476305, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.05133318901062, "global_step": 476306, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9919042587280273, "global_step": 476307, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1010804176330566, "global_step": 476308, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0270891189575195, "global_step": 476309, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.063883066177368, "global_step": 476310, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0551185607910156, "global_step": 476311, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9787447452545166, "global_step": 476312, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.143170118331909, "global_step": 476313, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.973589301109314, "global_step": 476314, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.04254150390625, "global_step": 476315, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0093445777893066, "global_step": 476316, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0773208141326904, "global_step": 476317, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.066930055618286, "global_step": 476318, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0467987060546875, "global_step": 476319, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.130204200744629, "global_step": 476320, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0331504344940186, "global_step": 476321, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0427424907684326, "global_step": 476322, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.035315752029419, "global_step": 476323, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.053053140640259, "global_step": 476324, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1310739517211914, "global_step": 476325, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.085174322128296, "global_step": 476326, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9711252450942993, "global_step": 476327, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0637829303741455, "global_step": 476328, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.041146993637085, "global_step": 476329, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0926222801208496, "global_step": 476330, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0313892364501953, "global_step": 476331, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0912678241729736, "global_step": 476332, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9874566793441772, "global_step": 476333, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0332579612731934, "global_step": 476334, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9887477159500122, "global_step": 476335, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0720982551574707, "global_step": 476336, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1013472080230713, "global_step": 476337, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.07077693939209, "global_step": 476338, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0782699584960938, "global_step": 476339, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.02978777885437, "global_step": 476340, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.006749153137207, "global_step": 476341, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.067164421081543, "global_step": 476342, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9842766523361206, "global_step": 476343, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.983798623085022, "global_step": 476344, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0685274600982666, "global_step": 476345, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.111074209213257, "global_step": 476346, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0841002464294434, "global_step": 476347, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0923447608947754, "global_step": 476348, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0477659702301025, "global_step": 476349, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0987305641174316, "global_step": 476350, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.07144832611084, "global_step": 476351, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0063979625701904, "global_step": 476352, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.043623924255371, "global_step": 476353, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0692243576049805, "global_step": 476354, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.054358720779419, "global_step": 476355, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.163081407546997, "global_step": 476356, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9966148138046265, "global_step": 476357, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0879719257354736, "global_step": 476358, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.061958074569702, "global_step": 476359, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0519304275512695, "global_step": 476360, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0998682975769043, "global_step": 476361, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0488972663879395, "global_step": 476362, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.101832151412964, "global_step": 476363, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0529816150665283, "global_step": 476364, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.02551007270813, "global_step": 476365, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.021536111831665, "global_step": 476366, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.054445266723633, "global_step": 476367, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.090827703475952, "global_step": 476368, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.149202585220337, "global_step": 476369, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.105499744415283, "global_step": 476370, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.103360652923584, "global_step": 476371, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.033041477203369, "global_step": 476372, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1293351650238037, "global_step": 476373, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.084484338760376, "global_step": 476374, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.158026933670044, "global_step": 476375, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0183451175689697, "global_step": 476376, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0115280151367188, "global_step": 476377, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9978512525558472, "global_step": 476378, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1131467819213867, "global_step": 476379, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9936339855194092, "global_step": 476380, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1070518493652344, "global_step": 476381, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9867074489593506, "global_step": 476382, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.050739049911499, "global_step": 476383, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.005317211151123, "global_step": 476384, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0273678302764893, "global_step": 476385, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.019202470779419, "global_step": 476386, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.041022777557373, "global_step": 476387, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.00435733795166, "global_step": 476388, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.006218671798706, "global_step": 476389, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.077812910079956, "global_step": 476390, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0622456073760986, "global_step": 476391, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.966288447380066, "global_step": 476392, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0709054470062256, "global_step": 476393, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0141327381134033, "global_step": 476394, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.065135955810547, "global_step": 476395, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9687635898590088, "global_step": 476396, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1342148780822754, "global_step": 476397, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0454468727111816, "global_step": 476398, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1255712509155273, "global_step": 476399, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.11602520942688, "global_step": 476400, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.085479736328125, "global_step": 476401, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.111469030380249, "global_step": 476402, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1110050678253174, "global_step": 476403, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.019968032836914, "global_step": 476404, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0218334197998047, "global_step": 476405, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1059625148773193, "global_step": 476406, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0437562465667725, "global_step": 476407, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1150708198547363, "global_step": 476408, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.022585868835449, "global_step": 476409, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.073054313659668, "global_step": 476410, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0104892253875732, "global_step": 476411, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.034512996673584, "global_step": 476412, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1265029907226562, "global_step": 476413, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0764575004577637, "global_step": 476414, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.034822463989258, "global_step": 476415, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9914369583129883, "global_step": 476416, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0844147205352783, "global_step": 476417, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.988295316696167, "global_step": 476418, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.2137014865875244, "global_step": 476419, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0750222206115723, "global_step": 476420, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.106886386871338, "global_step": 476421, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0676352977752686, "global_step": 476422, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0689098834991455, "global_step": 476423, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.949385166168213, "global_step": 476424, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.045820474624634, "global_step": 476425, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.001335620880127, "global_step": 476426, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1154820919036865, "global_step": 476427, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0200679302215576, "global_step": 476428, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0021746158599854, "global_step": 476429, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.054976224899292, "global_step": 476430, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0180182456970215, "global_step": 476431, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9916001558303833, "global_step": 476432, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0162577629089355, "global_step": 476433, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.169569969177246, "global_step": 476434, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.074709415435791, "global_step": 476435, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.111854314804077, "global_step": 476436, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0361766815185547, "global_step": 476437, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0211687088012695, "global_step": 476438, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.053091287612915, "global_step": 476439, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1222431659698486, "global_step": 476440, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9787341356277466, "global_step": 476441, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9969489574432373, "global_step": 476442, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1484458446502686, "global_step": 476443, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0892281532287598, "global_step": 476444, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1191775798797607, "global_step": 476445, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0850236415863037, "global_step": 476446, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0359692573547363, "global_step": 476447, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0163230895996094, "global_step": 476448, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0110201835632324, "global_step": 476449, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.035553216934204, "global_step": 476450, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.116680383682251, "global_step": 476451, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.027783155441284, "global_step": 476452, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9657511711120605, "global_step": 476453, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0871758460998535, "global_step": 476454, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0783181190490723, "global_step": 476455, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.100625514984131, "global_step": 476456, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1048479080200195, "global_step": 476457, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0315396785736084, "global_step": 476458, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0730457305908203, "global_step": 476459, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0734283924102783, "global_step": 476460, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.052251100540161, "global_step": 476461, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.037916660308838, "global_step": 476462, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.069420337677002, "global_step": 476463, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.2802469730377197, "global_step": 476464, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.061495780944824, "global_step": 476465, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9855421781539917, "global_step": 476466, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0957908630371094, "global_step": 476467, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0543553829193115, "global_step": 476468, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0868959426879883, "global_step": 476469, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1017415523529053, "global_step": 476470, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.152132511138916, "global_step": 476471, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9959608316421509, "global_step": 476472, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0392019748687744, "global_step": 476473, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0286102294921875, "global_step": 476474, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0755176544189453, "global_step": 476475, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0045790672302246, "global_step": 476476, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9410096406936646, "global_step": 476477, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.141988754272461, "global_step": 476478, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1232712268829346, "global_step": 476479, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0528526306152344, "global_step": 476480, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0985474586486816, "global_step": 476481, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.997576117515564, "global_step": 476482, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.082925796508789, "global_step": 476483, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0774497985839844, "global_step": 476484, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.019097328186035, "global_step": 476485, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.080440044403076, "global_step": 476486, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0598433017730713, "global_step": 476487, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0339701175689697, "global_step": 476488, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1079652309417725, "global_step": 476489, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0668327808380127, "global_step": 476490, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1306324005126953, "global_step": 476491, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9913674592971802, "global_step": 476492, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0234642028808594, "global_step": 476493, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1246933937072754, "global_step": 476494, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.152735710144043, "global_step": 476495, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0159106254577637, "global_step": 476496, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.099391222000122, "global_step": 476497, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0593433380126953, "global_step": 476498, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1798269748687744, "global_step": 476499, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.064427375793457, "global_step": 476500, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.019850969314575, "global_step": 476501, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1457231044769287, "global_step": 476502, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0333611965179443, "global_step": 476503, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.129222869873047, "global_step": 476504, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1700034141540527, "global_step": 476505, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.037810802459717, "global_step": 476506, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.046736717224121, "global_step": 476507, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.070653200149536, "global_step": 476508, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0430312156677246, "global_step": 476509, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1522159576416016, "global_step": 476510, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1496334075927734, "global_step": 476511, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0931270122528076, "global_step": 476512, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0178897380828857, "global_step": 476513, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.114790916442871, "global_step": 476514, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0618467330932617, "global_step": 476515, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1311440467834473, "global_step": 476516, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9990147352218628, "global_step": 476517, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0669021606445312, "global_step": 476518, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.061577081680298, "global_step": 476519, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0821099281311035, "global_step": 476520, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0539355278015137, "global_step": 476521, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.056779384613037, "global_step": 476522, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.085864305496216, "global_step": 476523, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.042970657348633, "global_step": 476524, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.081618309020996, "global_step": 476525, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0705504417419434, "global_step": 476526, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1084163188934326, "global_step": 476527, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.023495674133301, "global_step": 476528, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.078606128692627, "global_step": 476529, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9595141410827637, "global_step": 476530, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0680229663848877, "global_step": 476531, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0443642139434814, "global_step": 476532, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9761624336242676, "global_step": 476533, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0731208324432373, "global_step": 476534, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.167079210281372, "global_step": 476535, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.000978946685791, "global_step": 476536, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.10219407081604, "global_step": 476537, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.031407117843628, "global_step": 476538, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1754350662231445, "global_step": 476539, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1314713954925537, "global_step": 476540, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0319020748138428, "global_step": 476541, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0090980529785156, "global_step": 476542, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.047391653060913, "global_step": 476543, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.18147349357605, "global_step": 476544, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0433714389801025, "global_step": 476545, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.131589889526367, "global_step": 476546, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0936551094055176, "global_step": 476547, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.123293399810791, "global_step": 476548, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.066767454147339, "global_step": 476549, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.048231840133667, "global_step": 476550, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1167876720428467, "global_step": 476551, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.94353187084198, "global_step": 476552, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.109518527984619, "global_step": 476553, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.114415407180786, "global_step": 476554, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0268797874450684, "global_step": 476555, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0897510051727295, "global_step": 476556, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.028979778289795, "global_step": 476557, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0555436611175537, "global_step": 476558, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0714831352233887, "global_step": 476559, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0802252292633057, "global_step": 476560, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0371696949005127, "global_step": 476561, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1068100929260254, "global_step": 476562, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9979802370071411, "global_step": 476563, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.087538003921509, "global_step": 476564, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.990272879600525, "global_step": 476565, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1566407680511475, "global_step": 476566, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0525851249694824, "global_step": 476567, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9756487607955933, "global_step": 476568, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9651589393615723, "global_step": 476569, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.121192216873169, "global_step": 476570, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1123623847961426, "global_step": 476571, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.053098201751709, "global_step": 476572, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.984975814819336, "global_step": 476573, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1186623573303223, "global_step": 476574, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.010532855987549, "global_step": 476575, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.068629264831543, "global_step": 476576, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9572833776474, "global_step": 476577, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.060375452041626, "global_step": 476578, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0546367168426514, "global_step": 476579, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.113353729248047, "global_step": 476580, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9730663299560547, "global_step": 476581, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.049989938735962, "global_step": 476582, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0772695541381836, "global_step": 476583, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0745832920074463, "global_step": 476584, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9878051280975342, "global_step": 476585, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.043118476867676, "global_step": 476586, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.125897169113159, "global_step": 476587, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9409489631652832, "global_step": 476588, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.006194829940796, "global_step": 476589, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0853281021118164, "global_step": 476590, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.118065357208252, "global_step": 476591, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.063772201538086, "global_step": 476592, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0056049823760986, "global_step": 476593, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.03592586517334, "global_step": 476594, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1616551876068115, "global_step": 476595, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0465149879455566, "global_step": 476596, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1461246013641357, "global_step": 476597, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.075629234313965, "global_step": 476598, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.070920467376709, "global_step": 476599, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9909993410110474, "global_step": 476600, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0957999229431152, "global_step": 476601, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0808184146881104, "global_step": 476602, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.048198699951172, "global_step": 476603, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0513954162597656, "global_step": 476604, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1029467582702637, "global_step": 476605, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.077061414718628, "global_step": 476606, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0542495250701904, "global_step": 476607, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0620601177215576, "global_step": 476608, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0650079250335693, "global_step": 476609, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.124225378036499, "global_step": 476610, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1279404163360596, "global_step": 476611, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.039599895477295, "global_step": 476612, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.003955841064453, "global_step": 476613, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0680248737335205, "global_step": 476614, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.055060863494873, "global_step": 476615, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1435787677764893, "global_step": 476616, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0418007373809814, "global_step": 476617, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.062227964401245, "global_step": 476618, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.147001266479492, "global_step": 476619, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.072507619857788, "global_step": 476620, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0581071376800537, "global_step": 476621, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1404836177825928, "global_step": 476622, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1222262382507324, "global_step": 476623, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0471885204315186, "global_step": 476624, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9881130456924438, "global_step": 476625, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0315353870391846, "global_step": 476626, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0637879371643066, "global_step": 476627, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0306973457336426, "global_step": 476628, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0398671627044678, "global_step": 476629, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9976369142532349, "global_step": 476630, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0860791206359863, "global_step": 476631, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.020867109298706, "global_step": 476632, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.149904727935791, "global_step": 476633, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.103957176208496, "global_step": 476634, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0863611698150635, "global_step": 476635, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.997205138206482, "global_step": 476636, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0467121601104736, "global_step": 476637, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0371851921081543, "global_step": 476638, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.147965431213379, "global_step": 476639, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.069232702255249, "global_step": 476640, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0939950942993164, "global_step": 476641, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.020662784576416, "global_step": 476642, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9206945896148682, "global_step": 476643, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1130123138427734, "global_step": 476644, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.020902156829834, "global_step": 476645, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.027406692504883, "global_step": 476646, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9644783735275269, "global_step": 476647, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.06182861328125, "global_step": 476648, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9879961013793945, "global_step": 476649, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0945940017700195, "global_step": 476650, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1049044132232666, "global_step": 476651, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0458996295928955, "global_step": 476652, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0070266723632812, "global_step": 476653, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.158752679824829, "global_step": 476654, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0232653617858887, "global_step": 476655, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0394012928009033, "global_step": 476656, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0143167972564697, "global_step": 476657, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0681142807006836, "global_step": 476658, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0227837562561035, "global_step": 476659, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.07450532913208, "global_step": 476660, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1073546409606934, "global_step": 476661, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1118581295013428, "global_step": 476662, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0535714626312256, "global_step": 476663, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1274282932281494, "global_step": 476664, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1318318843841553, "global_step": 476665, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.118034839630127, "global_step": 476666, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0868821144104004, "global_step": 476667, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1251301765441895, "global_step": 476668, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0462820529937744, "global_step": 476669, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0397872924804688, "global_step": 476670, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.128880262374878, "global_step": 476671, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.086442708969116, "global_step": 476672, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1038784980773926, "global_step": 476673, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.064542055130005, "global_step": 476674, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9970241785049438, "global_step": 476675, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0809333324432373, "global_step": 476676, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.006777048110962, "global_step": 476677, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0880258083343506, "global_step": 476678, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.091275930404663, "global_step": 476679, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9899424314498901, "global_step": 476680, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.036259174346924, "global_step": 476681, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0022876262664795, "global_step": 476682, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.089209794998169, "global_step": 476683, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9987989664077759, "global_step": 476684, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.2107112407684326, "global_step": 476685, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.052889823913574, "global_step": 476686, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.107678174972534, "global_step": 476687, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0144741535186768, "global_step": 476688, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0417604446411133, "global_step": 476689, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.050204038619995, "global_step": 476690, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.007779121398926, "global_step": 476691, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.114989995956421, "global_step": 476692, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0805399417877197, "global_step": 476693, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.066951274871826, "global_step": 476694, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.109267473220825, "global_step": 476695, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.012470245361328, "global_step": 476696, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.087366819381714, "global_step": 476697, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0941216945648193, "global_step": 476698, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.115893840789795, "global_step": 476699, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0252463817596436, "global_step": 476700, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.066800832748413, "global_step": 476701, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.052664041519165, "global_step": 476702, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1117587089538574, "global_step": 476703, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0772335529327393, "global_step": 476704, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0864098072052, "global_step": 476705, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0199241638183594, "global_step": 476706, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0167043209075928, "global_step": 476707, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1308536529541016, "global_step": 476708, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9995406866073608, "global_step": 476709, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9817153215408325, "global_step": 476710, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.078911781311035, "global_step": 476711, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.086366653442383, "global_step": 476712, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0745627880096436, "global_step": 476713, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.098597764968872, "global_step": 476714, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.187079906463623, "global_step": 476715, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9925329685211182, "global_step": 476716, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.013826847076416, "global_step": 476717, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0783579349517822, "global_step": 476718, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1741788387298584, "global_step": 476719, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0893120765686035, "global_step": 476720, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9741555452346802, "global_step": 476721, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.029799699783325, "global_step": 476722, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9866998195648193, "global_step": 476723, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1826319694519043, "global_step": 476724, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0104482173919678, "global_step": 476725, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.015218734741211, "global_step": 476726, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1094698905944824, "global_step": 476727, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9620747566223145, "global_step": 476728, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0902185440063477, "global_step": 476729, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.009477138519287, "global_step": 476730, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.03147292137146, "global_step": 476731, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0064170360565186, "global_step": 476732, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1168038845062256, "global_step": 476733, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.02577543258667, "global_step": 476734, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0908689498901367, "global_step": 476735, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.938255786895752, "global_step": 476736, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.059983968734741, "global_step": 476737, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.072920322418213, "global_step": 476738, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.131490468978882, "global_step": 476739, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0875589847564697, "global_step": 476740, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9975982904434204, "global_step": 476741, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0916600227355957, "global_step": 476742, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.060183525085449, "global_step": 476743, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.032803535461426, "global_step": 476744, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.972618579864502, "global_step": 476745, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.118513584136963, "global_step": 476746, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.087775707244873, "global_step": 476747, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9803674221038818, "global_step": 476748, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1200618743896484, "global_step": 476749, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0355145931243896, "global_step": 476750, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.056844472885132, "global_step": 476751, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0604076385498047, "global_step": 476752, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0588932037353516, "global_step": 476753, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.071599006652832, "global_step": 476754, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0829312801361084, "global_step": 476755, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.05574631690979, "global_step": 476756, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0110726356506348, "global_step": 476757, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.052496910095215, "global_step": 476758, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.037179708480835, "global_step": 476759, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1302828788757324, "global_step": 476760, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.129561424255371, "global_step": 476761, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9577631950378418, "global_step": 476762, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0519893169403076, "global_step": 476763, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0243430137634277, "global_step": 476764, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1215531826019287, "global_step": 476765, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.102058172225952, "global_step": 476766, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1310524940490723, "global_step": 476767, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.023181676864624, "global_step": 476768, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.074660539627075, "global_step": 476769, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0629348754882812, "global_step": 476770, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1664929389953613, "global_step": 476771, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.113572359085083, "global_step": 476772, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0147504806518555, "global_step": 476773, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0591185092926025, "global_step": 476774, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0550129413604736, "global_step": 476775, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.098005771636963, "global_step": 476776, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9694886207580566, "global_step": 476777, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0889225006103516, "global_step": 476778, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1408097743988037, "global_step": 476779, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.070838451385498, "global_step": 476780, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9833335876464844, "global_step": 476781, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.078500509262085, "global_step": 476782, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.081543207168579, "global_step": 476783, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.01358699798584, "global_step": 476784, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.079460859298706, "global_step": 476785, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1017894744873047, "global_step": 476786, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.041470527648926, "global_step": 476787, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0733392238616943, "global_step": 476788, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0547873973846436, "global_step": 476789, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0769948959350586, "global_step": 476790, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.115692377090454, "global_step": 476791, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.137739658355713, "global_step": 476792, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0698323249816895, "global_step": 476793, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.012446165084839, "global_step": 476794, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0739457607269287, "global_step": 476795, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0774221420288086, "global_step": 476796, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.122387647628784, "global_step": 476797, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0348308086395264, "global_step": 476798, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0418717861175537, "global_step": 476799, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1008269786834717, "global_step": 476800, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0648627281188965, "global_step": 476801, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.083045244216919, "global_step": 476802, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.996826171875, "global_step": 476803, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0723140239715576, "global_step": 476804, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0963962078094482, "global_step": 476805, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0692079067230225, "global_step": 476806, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.154346227645874, "global_step": 476807, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.150625467300415, "global_step": 476808, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0694491863250732, "global_step": 476809, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.039945125579834, "global_step": 476810, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9767262935638428, "global_step": 476811, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0898854732513428, "global_step": 476812, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.040740966796875, "global_step": 476813, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0764803886413574, "global_step": 476814, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.047304153442383, "global_step": 476815, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0276038646698, "global_step": 476816, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.116926908493042, "global_step": 476817, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1449098587036133, "global_step": 476818, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.997727632522583, "global_step": 476819, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0443220138549805, "global_step": 476820, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1728832721710205, "global_step": 476821, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.026764392852783, "global_step": 476822, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.040750503540039, "global_step": 476823, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.059330940246582, "global_step": 476824, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9871938228607178, "global_step": 476825, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0657455921173096, "global_step": 476826, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.058380126953125, "global_step": 476827, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.997093677520752, "global_step": 476828, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0862348079681396, "global_step": 476829, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.157876491546631, "global_step": 476830, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0644919872283936, "global_step": 476831, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.126694440841675, "global_step": 476832, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0942065715789795, "global_step": 476833, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1364448070526123, "global_step": 476834, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.073439836502075, "global_step": 476835, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.047769784927368, "global_step": 476836, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0370216369628906, "global_step": 476837, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0350353717803955, "global_step": 476838, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0867092609405518, "global_step": 476839, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0468263626098633, "global_step": 476840, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.08681321144104, "global_step": 476841, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.087695598602295, "global_step": 476842, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9698785543441772, "global_step": 476843, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.054196357727051, "global_step": 476844, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0606002807617188, "global_step": 476845, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.041696548461914, "global_step": 476846, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0510497093200684, "global_step": 476847, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9881492853164673, "global_step": 476848, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0419986248016357, "global_step": 476849, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.057803153991699, "global_step": 476850, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0890188217163086, "global_step": 476851, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1055266857147217, "global_step": 476852, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0945398807525635, "global_step": 476853, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.104228973388672, "global_step": 476854, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1469244956970215, "global_step": 476855, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0696630477905273, "global_step": 476856, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9906986951828003, "global_step": 476857, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0822911262512207, "global_step": 476858, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.107970952987671, "global_step": 476859, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0283374786376953, "global_step": 476860, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0569303035736084, "global_step": 476861, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.027892589569092, "global_step": 476862, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0465281009674072, "global_step": 476863, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0139684677124023, "global_step": 476864, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1534764766693115, "global_step": 476865, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.05757474899292, "global_step": 476866, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.1208014488220215, "global_step": 476867, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.943027377128601, "global_step": 476868, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.019984006881714, "global_step": 476869, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.126333236694336, "global_step": 476870, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0479984283447266, "global_step": 476871, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.074460506439209, "global_step": 476872, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0305020809173584, "global_step": 476873, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.03779935836792, "global_step": 476874, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.052694320678711, "global_step": 476875, "epoch": 841, "lr": 5e-05}
{"train_loss": 1.9797524213790894, "global_step": 476876, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.039848804473877, "global_step": 476877, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0560319423675537, "global_step": 476878, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0408921241760254, "global_step": 476879, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0619139671325684, "global_step": 476880, "epoch": 841, "lr": 5e-05}
{"train_loss": 2.0959506034851074, "global_step": 476881, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1069109439849854, "global_step": 476882, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9827643632888794, "global_step": 476883, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.06123948097229, "global_step": 476884, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.045302152633667, "global_step": 476885, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.093716859817505, "global_step": 476886, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1283109188079834, "global_step": 476887, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0816986560821533, "global_step": 476888, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0591413974761963, "global_step": 476889, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0155675411224365, "global_step": 476890, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0060393810272217, "global_step": 476891, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.029320240020752, "global_step": 476892, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.146350622177124, "global_step": 476893, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.043846607208252, "global_step": 476894, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0298967361450195, "global_step": 476895, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0332796573638916, "global_step": 476896, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0534796714782715, "global_step": 476897, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.104067325592041, "global_step": 476898, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0847511291503906, "global_step": 476899, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.008629083633423, "global_step": 476900, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9773932695388794, "global_step": 476901, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9178391695022583, "global_step": 476902, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.133802652359009, "global_step": 476903, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0381510257720947, "global_step": 476904, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0419294834136963, "global_step": 476905, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1753716468811035, "global_step": 476906, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0110530853271484, "global_step": 476907, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0189461708068848, "global_step": 476908, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9837086200714111, "global_step": 476909, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0810000896453857, "global_step": 476910, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9805423021316528, "global_step": 476911, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0700154304504395, "global_step": 476912, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0157508850097656, "global_step": 476913, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.081406831741333, "global_step": 476914, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9949091672897339, "global_step": 476915, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0534842014312744, "global_step": 476916, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.961067795753479, "global_step": 476917, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0297141075134277, "global_step": 476918, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9926871061325073, "global_step": 476919, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0401594638824463, "global_step": 476920, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.004255771636963, "global_step": 476921, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.146594285964966, "global_step": 476922, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.015298366546631, "global_step": 476923, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0528934001922607, "global_step": 476924, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.065864324569702, "global_step": 476925, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0361406803131104, "global_step": 476926, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1029415130615234, "global_step": 476927, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0838990211486816, "global_step": 476928, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0666210651397705, "global_step": 476929, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0165724754333496, "global_step": 476930, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1193454265594482, "global_step": 476931, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.022763252258301, "global_step": 476932, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0764107704162598, "global_step": 476933, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0600643157958984, "global_step": 476934, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1594066619873047, "global_step": 476935, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0452301502227783, "global_step": 476936, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0233516693115234, "global_step": 476937, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0772383213043213, "global_step": 476938, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0781331062316895, "global_step": 476939, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.103475332260132, "global_step": 476940, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1110410690307617, "global_step": 476941, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.049034595489502, "global_step": 476942, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.086867570877075, "global_step": 476943, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.085078477859497, "global_step": 476944, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.017085313796997, "global_step": 476945, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0825960636138916, "global_step": 476946, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0778796672821045, "global_step": 476947, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.074363946914673, "global_step": 476948, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1286425590515137, "global_step": 476949, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0227746963500977, "global_step": 476950, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.085642099380493, "global_step": 476951, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.97323477268219, "global_step": 476952, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.06765079498291, "global_step": 476953, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.001641273498535, "global_step": 476954, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0542030334472656, "global_step": 476955, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0466299057006836, "global_step": 476956, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0881094932556152, "global_step": 476957, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.071903944015503, "global_step": 476958, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0185351371765137, "global_step": 476959, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.101137399673462, "global_step": 476960, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.165393590927124, "global_step": 476961, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0520639419555664, "global_step": 476962, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1031508445739746, "global_step": 476963, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1089303493499756, "global_step": 476964, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1151371002197266, "global_step": 476965, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.057452440261841, "global_step": 476966, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1304843425750732, "global_step": 476967, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9841084480285645, "global_step": 476968, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9861085414886475, "global_step": 476969, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9389045238494873, "global_step": 476970, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0622730255126953, "global_step": 476971, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9497437477111816, "global_step": 476972, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.947813868522644, "global_step": 476973, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.146873950958252, "global_step": 476974, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.095972776412964, "global_step": 476975, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0610458850860596, "global_step": 476976, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.086317539215088, "global_step": 476977, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.126683235168457, "global_step": 476978, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0122509002685547, "global_step": 476979, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0451855659484863, "global_step": 476980, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.003364324569702, "global_step": 476981, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0421648025512695, "global_step": 476982, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0391833782196045, "global_step": 476983, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.085203170776367, "global_step": 476984, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.115577220916748, "global_step": 476985, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.022094964981079, "global_step": 476986, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.012657880783081, "global_step": 476987, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.090219736099243, "global_step": 476988, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0469512939453125, "global_step": 476989, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0877692699432373, "global_step": 476990, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0104310512542725, "global_step": 476991, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.045275926589966, "global_step": 476992, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1375741958618164, "global_step": 476993, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0515124797821045, "global_step": 476994, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.063394784927368, "global_step": 476995, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0109915733337402, "global_step": 476996, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0830483436584473, "global_step": 476997, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9988148212432861, "global_step": 476998, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0170810222625732, "global_step": 476999, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0381531715393066, "global_step": 477000, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0590875148773193, "global_step": 477001, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.053746461868286, "global_step": 477002, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.087836742401123, "global_step": 477003, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0025794506073, "global_step": 477004, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9965742826461792, "global_step": 477005, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0664772987365723, "global_step": 477006, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0761141777038574, "global_step": 477007, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0293054580688477, "global_step": 477008, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0554897785186768, "global_step": 477009, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0836644172668457, "global_step": 477010, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0863661766052246, "global_step": 477011, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0990307331085205, "global_step": 477012, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1178717613220215, "global_step": 477013, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0350260734558105, "global_step": 477014, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0735437870025635, "global_step": 477015, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0452866554260254, "global_step": 477016, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1044559478759766, "global_step": 477017, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.107412099838257, "global_step": 477018, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9787315130233765, "global_step": 477019, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0652246475219727, "global_step": 477020, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9881794452667236, "global_step": 477021, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1719448566436768, "global_step": 477022, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.026399612426758, "global_step": 477023, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.092830181121826, "global_step": 477024, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0757229328155518, "global_step": 477025, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.066378355026245, "global_step": 477026, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0159449577331543, "global_step": 477027, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1327908039093018, "global_step": 477028, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0982046127319336, "global_step": 477029, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.024918556213379, "global_step": 477030, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.092740058898926, "global_step": 477031, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.012845516204834, "global_step": 477032, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.007885217666626, "global_step": 477033, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0042412281036377, "global_step": 477034, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0261690616607666, "global_step": 477035, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0215566158294678, "global_step": 477036, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.244485855102539, "global_step": 477037, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.098217725753784, "global_step": 477038, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0527002811431885, "global_step": 477039, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.066870927810669, "global_step": 477040, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.094311475753784, "global_step": 477041, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9971799850463867, "global_step": 477042, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.143404483795166, "global_step": 477043, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0383715629577637, "global_step": 477044, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.031416654586792, "global_step": 477045, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.017157793045044, "global_step": 477046, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0645527839660645, "global_step": 477047, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.037889242172241, "global_step": 477048, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9737718105316162, "global_step": 477049, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9804996252059937, "global_step": 477050, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.050395965576172, "global_step": 477051, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0166025161743164, "global_step": 477052, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0446910858154297, "global_step": 477053, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.12774658203125, "global_step": 477054, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1686317920684814, "global_step": 477055, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.045117139816284, "global_step": 477056, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1479744911193848, "global_step": 477057, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0270466804504395, "global_step": 477058, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.122342109680176, "global_step": 477059, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9684287309646606, "global_step": 477060, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.104954957962036, "global_step": 477061, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.099123954772949, "global_step": 477062, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.956977128982544, "global_step": 477063, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.130141258239746, "global_step": 477064, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0941147804260254, "global_step": 477065, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9959887266159058, "global_step": 477066, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0822300910949707, "global_step": 477067, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0239970684051514, "global_step": 477068, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0166337490081787, "global_step": 477069, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.031892776489258, "global_step": 477070, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0386409759521484, "global_step": 477071, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1214253902435303, "global_step": 477072, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0419933795928955, "global_step": 477073, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0282158851623535, "global_step": 477074, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1048951148986816, "global_step": 477075, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.021411180496216, "global_step": 477076, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9832675457000732, "global_step": 477077, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0887372493743896, "global_step": 477078, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.03517484664917, "global_step": 477079, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.092684745788574, "global_step": 477080, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9432882070541382, "global_step": 477081, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0221829414367676, "global_step": 477082, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9635539054870605, "global_step": 477083, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.158050775527954, "global_step": 477084, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0583314895629883, "global_step": 477085, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0967390537261963, "global_step": 477086, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.014847993850708, "global_step": 477087, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9808025360107422, "global_step": 477088, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.097325086593628, "global_step": 477089, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9684040546417236, "global_step": 477090, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0675528049468994, "global_step": 477091, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.052154541015625, "global_step": 477092, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9715704917907715, "global_step": 477093, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0662567615509033, "global_step": 477094, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1145918369293213, "global_step": 477095, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1307389736175537, "global_step": 477096, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0464580059051514, "global_step": 477097, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.014155387878418, "global_step": 477098, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.05582332611084, "global_step": 477099, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0299110412597656, "global_step": 477100, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.073211193084717, "global_step": 477101, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.089280605316162, "global_step": 477102, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.974294900894165, "global_step": 477103, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1497678756713867, "global_step": 477104, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.150615692138672, "global_step": 477105, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0768933296203613, "global_step": 477106, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.08256196975708, "global_step": 477107, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9404866695404053, "global_step": 477108, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0548977851867676, "global_step": 477109, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0233709812164307, "global_step": 477110, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.067178249359131, "global_step": 477111, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.091191053390503, "global_step": 477112, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0554285049438477, "global_step": 477113, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.984681248664856, "global_step": 477114, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0945780277252197, "global_step": 477115, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.974904179573059, "global_step": 477116, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.116438388824463, "global_step": 477117, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0528855323791504, "global_step": 477118, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0378036499023438, "global_step": 477119, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0493788719177246, "global_step": 477120, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.112170696258545, "global_step": 477121, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0721914768218994, "global_step": 477122, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0738396644592285, "global_step": 477123, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1001341342926025, "global_step": 477124, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1884562969207764, "global_step": 477125, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0252530574798584, "global_step": 477126, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.082435369491577, "global_step": 477127, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.084343433380127, "global_step": 477128, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9845592975616455, "global_step": 477129, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0446722507476807, "global_step": 477130, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0619728565216064, "global_step": 477131, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.074997663497925, "global_step": 477132, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.010894298553467, "global_step": 477133, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.120854377746582, "global_step": 477134, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0814075469970703, "global_step": 477135, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.110422372817993, "global_step": 477136, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0732412338256836, "global_step": 477137, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.034510850906372, "global_step": 477138, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1670289039611816, "global_step": 477139, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0795936584472656, "global_step": 477140, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0302720069885254, "global_step": 477141, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.129528522491455, "global_step": 477142, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0350351333618164, "global_step": 477143, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0009896755218506, "global_step": 477144, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1427149772644043, "global_step": 477145, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.026697874069214, "global_step": 477146, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0450754165649414, "global_step": 477147, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0935592651367188, "global_step": 477148, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0533032417297363, "global_step": 477149, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9990572929382324, "global_step": 477150, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.078333616256714, "global_step": 477151, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.095825433731079, "global_step": 477152, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9921711683273315, "global_step": 477153, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9433587789535522, "global_step": 477154, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0085787773132324, "global_step": 477155, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0830719470977783, "global_step": 477156, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1487770080566406, "global_step": 477157, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.024630546569824, "global_step": 477158, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0200066566467285, "global_step": 477159, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.025299072265625, "global_step": 477160, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0086984634399414, "global_step": 477161, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.04061222076416, "global_step": 477162, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.055347442626953, "global_step": 477163, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.065985918045044, "global_step": 477164, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.136349678039551, "global_step": 477165, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.993690013885498, "global_step": 477166, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.032707452774048, "global_step": 477167, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0304548740386963, "global_step": 477168, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.131988286972046, "global_step": 477169, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9838433265686035, "global_step": 477170, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0910990238189697, "global_step": 477171, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.024786949157715, "global_step": 477172, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.026038646697998, "global_step": 477173, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.05584716796875, "global_step": 477174, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0450439453125, "global_step": 477175, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.077822208404541, "global_step": 477176, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.073096752166748, "global_step": 477177, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9950515031814575, "global_step": 477178, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.076467752456665, "global_step": 477179, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.114403247833252, "global_step": 477180, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0573863983154297, "global_step": 477181, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.065642833709717, "global_step": 477182, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.143451452255249, "global_step": 477183, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.038614273071289, "global_step": 477184, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0761055946350098, "global_step": 477185, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.066958427429199, "global_step": 477186, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.085848331451416, "global_step": 477187, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.11478328704834, "global_step": 477188, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0410637855529785, "global_step": 477189, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.011126756668091, "global_step": 477190, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.046799421310425, "global_step": 477191, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.117790937423706, "global_step": 477192, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0898425579071045, "global_step": 477193, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1172983646392822, "global_step": 477194, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.059962034225464, "global_step": 477195, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.060612440109253, "global_step": 477196, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.913375973701477, "global_step": 477197, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.069876194000244, "global_step": 477198, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.170806407928467, "global_step": 477199, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0731966495513916, "global_step": 477200, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.056039571762085, "global_step": 477201, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.99452543258667, "global_step": 477202, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1073825359344482, "global_step": 477203, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0788938999176025, "global_step": 477204, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0339407920837402, "global_step": 477205, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0490825176239014, "global_step": 477206, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.988298773765564, "global_step": 477207, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.091384172439575, "global_step": 477208, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0002996921539307, "global_step": 477209, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0706870555877686, "global_step": 477210, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.051459550857544, "global_step": 477211, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.066920042037964, "global_step": 477212, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9945286512374878, "global_step": 477213, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.080641269683838, "global_step": 477214, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0708773136138916, "global_step": 477215, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.029653310775757, "global_step": 477216, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0359203815460205, "global_step": 477217, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0799832344055176, "global_step": 477218, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.053600788116455, "global_step": 477219, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.962972640991211, "global_step": 477220, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.028604030609131, "global_step": 477221, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0176491737365723, "global_step": 477222, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0594048500061035, "global_step": 477223, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9931615591049194, "global_step": 477224, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.991689682006836, "global_step": 477225, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.045762777328491, "global_step": 477226, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1091392040252686, "global_step": 477227, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.158172369003296, "global_step": 477228, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0297226905822754, "global_step": 477229, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.056838035583496, "global_step": 477230, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0777645111083984, "global_step": 477231, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.03564453125, "global_step": 477232, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.952602505683899, "global_step": 477233, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0541443824768066, "global_step": 477234, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0130369663238525, "global_step": 477235, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.101588726043701, "global_step": 477236, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0658981800079346, "global_step": 477237, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.114112138748169, "global_step": 477238, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.142737865447998, "global_step": 477239, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.009688377380371, "global_step": 477240, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.092834234237671, "global_step": 477241, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9928789138793945, "global_step": 477242, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.114802360534668, "global_step": 477243, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1570913791656494, "global_step": 477244, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9886566400527954, "global_step": 477245, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0623388290405273, "global_step": 477246, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0968730449676514, "global_step": 477247, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.965827226638794, "global_step": 477248, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9811978340148926, "global_step": 477249, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.050755500793457, "global_step": 477250, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0092501640319824, "global_step": 477251, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9649182558059692, "global_step": 477252, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.029632806777954, "global_step": 477253, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0245935916900635, "global_step": 477254, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1106746196746826, "global_step": 477255, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0445659160614014, "global_step": 477256, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.038440227508545, "global_step": 477257, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1285085678100586, "global_step": 477258, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0512988567352295, "global_step": 477259, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.013751983642578, "global_step": 477260, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.086714506149292, "global_step": 477261, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0184295177459717, "global_step": 477262, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9594852924346924, "global_step": 477263, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.043118715286255, "global_step": 477264, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0563125610351562, "global_step": 477265, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0224368572235107, "global_step": 477266, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1273386478424072, "global_step": 477267, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.049542188644409, "global_step": 477268, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0547919273376465, "global_step": 477269, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0297117233276367, "global_step": 477270, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0511555671691895, "global_step": 477271, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9966975450515747, "global_step": 477272, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0266475677490234, "global_step": 477273, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.070493698120117, "global_step": 477274, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0708863735198975, "global_step": 477275, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0904603004455566, "global_step": 477276, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1792547702789307, "global_step": 477277, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0927000045776367, "global_step": 477278, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0471408367156982, "global_step": 477279, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1015641689300537, "global_step": 477280, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1047139167785645, "global_step": 477281, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.024911403656006, "global_step": 477282, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1263656616210938, "global_step": 477283, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0097897052764893, "global_step": 477284, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.048146963119507, "global_step": 477285, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9984790086746216, "global_step": 477286, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.02870774269104, "global_step": 477287, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0219783782958984, "global_step": 477288, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.090336561203003, "global_step": 477289, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0327534675598145, "global_step": 477290, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9914124011993408, "global_step": 477291, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0427048206329346, "global_step": 477292, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0875637531280518, "global_step": 477293, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.14644718170166, "global_step": 477294, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1154656410217285, "global_step": 477295, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.061990976333618, "global_step": 477296, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0880250930786133, "global_step": 477297, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.109670639038086, "global_step": 477298, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.105959892272949, "global_step": 477299, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.014476776123047, "global_step": 477300, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0757875442504883, "global_step": 477301, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0245375633239746, "global_step": 477302, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.088142156600952, "global_step": 477303, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.064138412475586, "global_step": 477304, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9627538919448853, "global_step": 477305, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0717902183532715, "global_step": 477306, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.058774948120117, "global_step": 477307, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.040938138961792, "global_step": 477308, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0855863094329834, "global_step": 477309, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1144237518310547, "global_step": 477310, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.003727674484253, "global_step": 477311, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0319390296936035, "global_step": 477312, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.113011121749878, "global_step": 477313, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.018148183822632, "global_step": 477314, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.066838026046753, "global_step": 477315, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0463931560516357, "global_step": 477316, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0373849868774414, "global_step": 477317, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.041034460067749, "global_step": 477318, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1387360095977783, "global_step": 477319, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.969533085823059, "global_step": 477320, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1046218872070312, "global_step": 477321, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.041463613510132, "global_step": 477322, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0418636798858643, "global_step": 477323, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.036296844482422, "global_step": 477324, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0310492515563965, "global_step": 477325, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9973195791244507, "global_step": 477326, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.038297653198242, "global_step": 477327, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9957106113433838, "global_step": 477328, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.110917568206787, "global_step": 477329, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0711288452148438, "global_step": 477330, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0187032222747803, "global_step": 477331, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0299835205078125, "global_step": 477332, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0060060024261475, "global_step": 477333, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.10657000541687, "global_step": 477334, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0232913494110107, "global_step": 477335, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9944336414337158, "global_step": 477336, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0484158992767334, "global_step": 477337, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1034951210021973, "global_step": 477338, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.062530755996704, "global_step": 477339, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.070021629333496, "global_step": 477340, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.027813196182251, "global_step": 477341, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0774474143981934, "global_step": 477342, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1032121181488037, "global_step": 477343, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.036159038543701, "global_step": 477344, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1480460166931152, "global_step": 477345, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.149714708328247, "global_step": 477346, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.061248540878296, "global_step": 477347, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.139991521835327, "global_step": 477348, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9944722652435303, "global_step": 477349, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1458845138549805, "global_step": 477350, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.143780469894409, "global_step": 477351, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.144629955291748, "global_step": 477352, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0445783138275146, "global_step": 477353, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.005739450454712, "global_step": 477354, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.037660598754883, "global_step": 477355, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.017239570617676, "global_step": 477356, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.072661876678467, "global_step": 477357, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0654494762420654, "global_step": 477358, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.039011240005493, "global_step": 477359, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1073198318481445, "global_step": 477360, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.168292760848999, "global_step": 477361, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0427393913269043, "global_step": 477362, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0955440998077393, "global_step": 477363, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1213269233703613, "global_step": 477364, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1835479736328125, "global_step": 477365, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1450839042663574, "global_step": 477366, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0270698070526123, "global_step": 477367, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.042599678039551, "global_step": 477368, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.977943778038025, "global_step": 477369, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.019928216934204, "global_step": 477370, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0653305053710938, "global_step": 477371, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9554057121276855, "global_step": 477372, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9353877305984497, "global_step": 477373, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0301260948181152, "global_step": 477374, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.129680633544922, "global_step": 477375, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.137519121170044, "global_step": 477376, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0702946186065674, "global_step": 477377, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.022193670272827, "global_step": 477378, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0259337425231934, "global_step": 477379, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0007989406585693, "global_step": 477380, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0931928157806396, "global_step": 477381, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0549814701080322, "global_step": 477382, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1296024322509766, "global_step": 477383, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0652472972869873, "global_step": 477384, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0211164951324463, "global_step": 477385, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1325252056121826, "global_step": 477386, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1192259788513184, "global_step": 477387, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1414318084716797, "global_step": 477388, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1287477016448975, "global_step": 477389, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0618643760681152, "global_step": 477390, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0711472034454346, "global_step": 477391, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.028146743774414, "global_step": 477392, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9830745458602905, "global_step": 477393, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1756508350372314, "global_step": 477394, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0877366065979004, "global_step": 477395, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1160147190093994, "global_step": 477396, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1168758869171143, "global_step": 477397, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0583817958831787, "global_step": 477398, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0810277462005615, "global_step": 477399, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.014559268951416, "global_step": 477400, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0993340015411377, "global_step": 477401, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.089965581893921, "global_step": 477402, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.073106050491333, "global_step": 477403, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0063037872314453, "global_step": 477404, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.058436393737793, "global_step": 477405, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0049614906311035, "global_step": 477406, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.136904239654541, "global_step": 477407, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0733165740966797, "global_step": 477408, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0749502182006836, "global_step": 477409, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.090127468109131, "global_step": 477410, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.076977252960205, "global_step": 477411, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.006650447845459, "global_step": 477412, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.013326406478882, "global_step": 477413, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1465628147125244, "global_step": 477414, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.048969030380249, "global_step": 477415, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0336554050445557, "global_step": 477416, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.077753782272339, "global_step": 477417, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.102208375930786, "global_step": 477418, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0764858722686768, "global_step": 477419, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.031139373779297, "global_step": 477420, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1801700592041016, "global_step": 477421, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.031557083129883, "global_step": 477422, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.09234356880188, "global_step": 477423, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.063645839691162, "global_step": 477424, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0487232208251953, "global_step": 477425, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.057326555252075, "global_step": 477426, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.052879571914673, "global_step": 477427, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.191420316696167, "global_step": 477428, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0159735679626465, "global_step": 477429, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0906481742858887, "global_step": 477430, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1357638835906982, "global_step": 477431, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1107192039489746, "global_step": 477432, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0354669094085693, "global_step": 477433, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0341384410858154, "global_step": 477434, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0316078662872314, "global_step": 477435, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.06579852104187, "global_step": 477436, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9605308771133423, "global_step": 477437, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.114861249923706, "global_step": 477438, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1127986907958984, "global_step": 477439, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9717339277267456, "global_step": 477440, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.074270725250244, "global_step": 477441, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.043086528778076, "global_step": 477442, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1289901733398438, "global_step": 477443, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0282323360443115, "global_step": 477444, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0873560905456543, "global_step": 477445, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0861048698425293, "global_step": 477446, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.100752830505371, "global_step": 477447, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0132761001586914, "global_step": 477448, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.048281669616699, "global_step": 477449, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0831429958343506, "global_step": 477450, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.061284303665161, "global_step": 477451, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0576233863830566, "global_step": 477452, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.164334774017334, "global_step": 477453, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0900306701660156, "global_step": 477454, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.088021993637085, "global_step": 477455, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0599071979522705, "global_step": 477456, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0888071060180664, "global_step": 477457, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0836079120635986, "global_step": 477458, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0634682178497314, "global_step": 477459, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0476512908935547, "global_step": 477460, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.956384539604187, "global_step": 477461, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0767998695373535, "global_step": 477462, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1000304222106934, "global_step": 477463, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0725414752960205, "global_step": 477464, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9957551956176758, "global_step": 477465, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.071925640106201, "global_step": 477466, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0090761184692383, "global_step": 477467, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0626134872436523, "global_step": 477468, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0647776126861572, "global_step": 477469, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.093801975250244, "global_step": 477470, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0448548793792725, "global_step": 477471, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1246190071105957, "global_step": 477472, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0519073009490967, "global_step": 477473, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1025235652923584, "global_step": 477474, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0107905864715576, "global_step": 477475, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.096891164779663, "global_step": 477476, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0748353004455566, "global_step": 477477, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0615315437316895, "global_step": 477478, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.112436294555664, "global_step": 477479, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.033111810684204, "global_step": 477480, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9584448337554932, "global_step": 477481, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.2015092372894287, "global_step": 477482, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.084981918334961, "global_step": 477483, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.054337739944458, "global_step": 477484, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9944740533828735, "global_step": 477485, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0795910358428955, "global_step": 477486, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1391355991363525, "global_step": 477487, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0024895668029785, "global_step": 477488, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.082371234893799, "global_step": 477489, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0315122604370117, "global_step": 477490, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.099500894546509, "global_step": 477491, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.05782413482666, "global_step": 477492, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.083238363265991, "global_step": 477493, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0713140964508057, "global_step": 477494, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0463316440582275, "global_step": 477495, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.152989625930786, "global_step": 477496, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1034042835235596, "global_step": 477497, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0199687480926514, "global_step": 477498, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0520830154418945, "global_step": 477499, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.07427978515625, "global_step": 477500, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1058993339538574, "global_step": 477501, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.066612482070923, "global_step": 477502, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1226367950439453, "global_step": 477503, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0770423412323, "global_step": 477504, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0347049236297607, "global_step": 477505, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0262749195098877, "global_step": 477506, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.112614393234253, "global_step": 477507, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.036257266998291, "global_step": 477508, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.141289710998535, "global_step": 477509, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.090094804763794, "global_step": 477510, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.049532651901245, "global_step": 477511, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.048537015914917, "global_step": 477512, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0723423957824707, "global_step": 477513, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0674147605895996, "global_step": 477514, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.01969575881958, "global_step": 477515, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0780842304229736, "global_step": 477516, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0557305812835693, "global_step": 477517, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.042135238647461, "global_step": 477518, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0687005519866943, "global_step": 477519, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.067077875137329, "global_step": 477520, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1399307250976562, "global_step": 477521, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1027464866638184, "global_step": 477522, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0981619358062744, "global_step": 477523, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1230270862579346, "global_step": 477524, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0571987628936768, "global_step": 477525, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0404744148254395, "global_step": 477526, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0616047382354736, "global_step": 477527, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.023303747177124, "global_step": 477528, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.148421049118042, "global_step": 477529, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0391979217529297, "global_step": 477530, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0894827842712402, "global_step": 477531, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.038020133972168, "global_step": 477532, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0105667114257812, "global_step": 477533, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1338396072387695, "global_step": 477534, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.073945999145508, "global_step": 477535, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.060251474380493, "global_step": 477536, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0554487705230713, "global_step": 477537, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.076899766921997, "global_step": 477538, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.039278984069824, "global_step": 477539, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1388885974884033, "global_step": 477540, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9910469055175781, "global_step": 477541, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.05289626121521, "global_step": 477542, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.044847011566162, "global_step": 477543, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0420241355895996, "global_step": 477544, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0832996368408203, "global_step": 477545, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.086242437362671, "global_step": 477546, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9989084005355835, "global_step": 477547, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0240445137023926, "global_step": 477548, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0441391468048096, "global_step": 477549, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0451319217681885, "global_step": 477550, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9925161600112915, "global_step": 477551, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.111018180847168, "global_step": 477552, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0774600505828857, "global_step": 477553, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0403695106506348, "global_step": 477554, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.049506425857544, "global_step": 477555, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9959760904312134, "global_step": 477556, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1135025024414062, "global_step": 477557, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1484203338623047, "global_step": 477558, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0418288707733154, "global_step": 477559, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.070005178451538, "global_step": 477560, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0415027141571045, "global_step": 477561, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.044060230255127, "global_step": 477562, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0140321254730225, "global_step": 477563, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.13193416595459, "global_step": 477564, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0891385078430176, "global_step": 477565, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.168231248855591, "global_step": 477566, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0805490016937256, "global_step": 477567, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1341397762298584, "global_step": 477568, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.011636972427368, "global_step": 477569, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.084723949432373, "global_step": 477570, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0550031661987305, "global_step": 477571, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1103103160858154, "global_step": 477572, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.049194812774658, "global_step": 477573, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1217525005340576, "global_step": 477574, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.054295539855957, "global_step": 477575, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0703463554382324, "global_step": 477576, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.176480531692505, "global_step": 477577, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0960452556610107, "global_step": 477578, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.129624128341675, "global_step": 477579, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.124518394470215, "global_step": 477580, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0912184715270996, "global_step": 477581, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0661063194274902, "global_step": 477582, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.044614791870117, "global_step": 477583, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0590882301330566, "global_step": 477584, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9282366037368774, "global_step": 477585, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0199203491210938, "global_step": 477586, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.066005229949951, "global_step": 477587, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.137331008911133, "global_step": 477588, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.043952465057373, "global_step": 477589, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.069392442703247, "global_step": 477590, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0100631713867188, "global_step": 477591, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.14169979095459, "global_step": 477592, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0747790336608887, "global_step": 477593, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0848100185394287, "global_step": 477594, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.078720808029175, "global_step": 477595, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.017582893371582, "global_step": 477596, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.059644937515259, "global_step": 477597, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0439069271087646, "global_step": 477598, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1197991371154785, "global_step": 477599, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.062889575958252, "global_step": 477600, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0576109886169434, "global_step": 477601, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.019829034805298, "global_step": 477602, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.97219979763031, "global_step": 477603, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1993918418884277, "global_step": 477604, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.06345796585083, "global_step": 477605, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0317656993865967, "global_step": 477606, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0026872158050537, "global_step": 477607, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.112269163131714, "global_step": 477608, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0208146572113037, "global_step": 477609, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.098198413848877, "global_step": 477610, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1166598796844482, "global_step": 477611, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.138728618621826, "global_step": 477612, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9350550174713135, "global_step": 477613, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0682408809661865, "global_step": 477614, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1380016803741455, "global_step": 477615, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0073416233062744, "global_step": 477616, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1230711936950684, "global_step": 477617, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0471649169921875, "global_step": 477618, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1298294067382812, "global_step": 477619, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1384389400482178, "global_step": 477620, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.000375986099243, "global_step": 477621, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.093397378921509, "global_step": 477622, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0430567264556885, "global_step": 477623, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0750653743743896, "global_step": 477624, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.052309036254883, "global_step": 477625, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0100646018981934, "global_step": 477626, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.120500326156616, "global_step": 477627, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0425572395324707, "global_step": 477628, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1098315715789795, "global_step": 477629, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0794973373413086, "global_step": 477630, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.159782886505127, "global_step": 477631, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.06380558013916, "global_step": 477632, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1173322200775146, "global_step": 477633, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.963687777519226, "global_step": 477634, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0471982955932617, "global_step": 477635, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0603222846984863, "global_step": 477636, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0405561923980713, "global_step": 477637, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0038816928863525, "global_step": 477638, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0658841133117676, "global_step": 477639, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.042276382446289, "global_step": 477640, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.059346914291382, "global_step": 477641, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.075260877609253, "global_step": 477642, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0392367839813232, "global_step": 477643, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.003876209259033, "global_step": 477644, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1361775398254395, "global_step": 477645, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1666815280914307, "global_step": 477646, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.061638832092285, "global_step": 477647, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0480034351348877, "global_step": 477648, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1765213012695312, "global_step": 477649, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9896113872528076, "global_step": 477650, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1103227138519287, "global_step": 477651, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.07088041305542, "global_step": 477652, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9501572847366333, "global_step": 477653, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0260355472564697, "global_step": 477654, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.083723783493042, "global_step": 477655, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9775530099868774, "global_step": 477656, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.111720323562622, "global_step": 477657, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.090127944946289, "global_step": 477658, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.068864107131958, "global_step": 477659, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9420582056045532, "global_step": 477660, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0540952682495117, "global_step": 477661, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0728421211242676, "global_step": 477662, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.037245988845825, "global_step": 477663, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.084132671356201, "global_step": 477664, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.056689739227295, "global_step": 477665, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0650413036346436, "global_step": 477666, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0444328784942627, "global_step": 477667, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0234618186950684, "global_step": 477668, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0415258407592773, "global_step": 477669, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.027573347091675, "global_step": 477670, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.015460729598999, "global_step": 477671, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0741333961486816, "global_step": 477672, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.077066421508789, "global_step": 477673, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.03174090385437, "global_step": 477674, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1290853023529053, "global_step": 477675, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0364558696746826, "global_step": 477676, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9644091129302979, "global_step": 477677, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.016148805618286, "global_step": 477678, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1538805961608887, "global_step": 477679, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0297141075134277, "global_step": 477680, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0499796867370605, "global_step": 477681, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0707061290740967, "global_step": 477682, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.037827730178833, "global_step": 477683, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0314671993255615, "global_step": 477684, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.098771572113037, "global_step": 477685, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0977280139923096, "global_step": 477686, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0966861248016357, "global_step": 477687, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0891242027282715, "global_step": 477688, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.065966844558716, "global_step": 477689, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0625972747802734, "global_step": 477690, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.059990644454956, "global_step": 477691, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.027322292327881, "global_step": 477692, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0840914249420166, "global_step": 477693, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.090590238571167, "global_step": 477694, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.00313663482666, "global_step": 477695, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1043317317962646, "global_step": 477696, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.11319637298584, "global_step": 477697, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0934994220733643, "global_step": 477698, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0091910362243652, "global_step": 477699, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.976425290107727, "global_step": 477700, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.111591100692749, "global_step": 477701, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0363664627075195, "global_step": 477702, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0574517250061035, "global_step": 477703, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0950570106506348, "global_step": 477704, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.039039373397827, "global_step": 477705, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0284371376037598, "global_step": 477706, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.06441593170166, "global_step": 477707, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0019595623016357, "global_step": 477708, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.017075538635254, "global_step": 477709, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0427448749542236, "global_step": 477710, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9597164392471313, "global_step": 477711, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1245310306549072, "global_step": 477712, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0344655513763428, "global_step": 477713, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.014504909515381, "global_step": 477714, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0866003036499023, "global_step": 477715, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0492892265319824, "global_step": 477716, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9825685024261475, "global_step": 477717, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1072487831115723, "global_step": 477718, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0497493743896484, "global_step": 477719, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1028993129730225, "global_step": 477720, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1542673110961914, "global_step": 477721, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.086107015609741, "global_step": 477722, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.09433913230896, "global_step": 477723, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.074012279510498, "global_step": 477724, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0190064907073975, "global_step": 477725, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0984866619110107, "global_step": 477726, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9696800708770752, "global_step": 477727, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.074357032775879, "global_step": 477728, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.102125406265259, "global_step": 477729, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.074594259262085, "global_step": 477730, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0322375297546387, "global_step": 477731, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.018357276916504, "global_step": 477732, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.054365634918213, "global_step": 477733, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1183581352233887, "global_step": 477734, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0279152393341064, "global_step": 477735, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0922272205352783, "global_step": 477736, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.065586805343628, "global_step": 477737, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9987915754318237, "global_step": 477738, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.085580825805664, "global_step": 477739, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1076343059539795, "global_step": 477740, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0371806621551514, "global_step": 477741, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0667686462402344, "global_step": 477742, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1657309532165527, "global_step": 477743, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.071239471435547, "global_step": 477744, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.003748893737793, "global_step": 477745, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.090693950653076, "global_step": 477746, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1085309982299805, "global_step": 477747, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0268683433532715, "global_step": 477748, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0617668628692627, "global_step": 477749, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1701083183288574, "global_step": 477750, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.023597240447998, "global_step": 477751, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.017533779144287, "global_step": 477752, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0538253784179688, "global_step": 477753, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.022639513015747, "global_step": 477754, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0736749172210693, "global_step": 477755, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0461277961730957, "global_step": 477756, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1335434913635254, "global_step": 477757, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0308563709259033, "global_step": 477758, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9910801649093628, "global_step": 477759, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.984921932220459, "global_step": 477760, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.042686939239502, "global_step": 477761, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9948387145996094, "global_step": 477762, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9522260427474976, "global_step": 477763, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0580356121063232, "global_step": 477764, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0475802421569824, "global_step": 477765, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.095360517501831, "global_step": 477766, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0336852073669434, "global_step": 477767, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0812771320343018, "global_step": 477768, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0602641105651855, "global_step": 477769, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.087986707687378, "global_step": 477770, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0733249187469482, "global_step": 477771, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0605390071868896, "global_step": 477772, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0942914485931396, "global_step": 477773, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1200733184814453, "global_step": 477774, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0653445720672607, "global_step": 477775, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0058205127716064, "global_step": 477776, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.080244302749634, "global_step": 477777, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1214284896850586, "global_step": 477778, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0845530033111572, "global_step": 477779, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.12152099609375, "global_step": 477780, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1386611461639404, "global_step": 477781, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9915711879730225, "global_step": 477782, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0963385105133057, "global_step": 477783, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.038992404937744, "global_step": 477784, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.054971694946289, "global_step": 477785, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.111640691757202, "global_step": 477786, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.083575963973999, "global_step": 477787, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.088517665863037, "global_step": 477788, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0998308658599854, "global_step": 477789, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1256070137023926, "global_step": 477790, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.075528383255005, "global_step": 477791, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1181914806365967, "global_step": 477792, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9974987506866455, "global_step": 477793, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9905915260314941, "global_step": 477794, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1101081371307373, "global_step": 477795, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0263161659240723, "global_step": 477796, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.042417526245117, "global_step": 477797, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.136281728744507, "global_step": 477798, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0295250415802, "global_step": 477799, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1188886165618896, "global_step": 477800, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.078317642211914, "global_step": 477801, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.081434965133667, "global_step": 477802, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0361483097076416, "global_step": 477803, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.070319414138794, "global_step": 477804, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0603091716766357, "global_step": 477805, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.005825996398926, "global_step": 477806, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0037686824798584, "global_step": 477807, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9828529357910156, "global_step": 477808, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0992774963378906, "global_step": 477809, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.118340492248535, "global_step": 477810, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0781140327453613, "global_step": 477811, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0319552421569824, "global_step": 477812, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.031095266342163, "global_step": 477813, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0525002479553223, "global_step": 477814, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0314888954162598, "global_step": 477815, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.9925484657287598, "global_step": 477816, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0578150749206543, "global_step": 477817, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0767927169799805, "global_step": 477818, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0424656867980957, "global_step": 477819, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.055001735687256, "global_step": 477820, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0687055587768555, "global_step": 477821, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0881733894348145, "global_step": 477822, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.019439697265625, "global_step": 477823, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0460267066955566, "global_step": 477824, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0572257041931152, "global_step": 477825, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.063882827758789, "global_step": 477826, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.108593463897705, "global_step": 477827, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0906293392181396, "global_step": 477828, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0773589611053467, "global_step": 477829, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0716848373413086, "global_step": 477830, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.038578510284424, "global_step": 477831, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1087188720703125, "global_step": 477832, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.029282569885254, "global_step": 477833, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1383795738220215, "global_step": 477834, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.070542097091675, "global_step": 477835, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1464409828186035, "global_step": 477836, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.044179677963257, "global_step": 477837, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.132721424102783, "global_step": 477838, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.094419479370117, "global_step": 477839, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.061959743499756, "global_step": 477840, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1418521404266357, "global_step": 477841, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0591588020324707, "global_step": 477842, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0439047813415527, "global_step": 477843, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1547086238861084, "global_step": 477844, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1124000549316406, "global_step": 477845, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1064343452453613, "global_step": 477846, "epoch": 842, "lr": 5e-05}
{"train_loss": 1.997178316116333, "global_step": 477847, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.1005759239196777, "global_step": 477848, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.061572551727295, "global_step": 477849, "epoch": 842, "lr": 5e-05}
{"train_loss": 2.0451815128326416, "global_step": 477850, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.049572229385376, "global_step": 477851, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.079753875732422, "global_step": 477852, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.088472843170166, "global_step": 477853, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0437262058258057, "global_step": 477854, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.009434700012207, "global_step": 477855, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.041642665863037, "global_step": 477856, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.033693313598633, "global_step": 477857, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1317474842071533, "global_step": 477858, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.011357069015503, "global_step": 477859, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.131470203399658, "global_step": 477860, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.159924268722534, "global_step": 477861, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0772502422332764, "global_step": 477862, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0907299518585205, "global_step": 477863, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1196088790893555, "global_step": 477864, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0881412029266357, "global_step": 477865, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9736319780349731, "global_step": 477866, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0643084049224854, "global_step": 477867, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1658408641815186, "global_step": 477868, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0581905841827393, "global_step": 477869, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0494563579559326, "global_step": 477870, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.118048667907715, "global_step": 477871, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1812822818756104, "global_step": 477872, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0583508014678955, "global_step": 477873, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9815857410430908, "global_step": 477874, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.079281806945801, "global_step": 477875, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0187861919403076, "global_step": 477876, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.071070432662964, "global_step": 477877, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.005812406539917, "global_step": 477878, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0531790256500244, "global_step": 477879, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0400569438934326, "global_step": 477880, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.982602834701538, "global_step": 477881, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.032987117767334, "global_step": 477882, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0948429107666016, "global_step": 477883, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.110548496246338, "global_step": 477884, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0450944900512695, "global_step": 477885, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0825507640838623, "global_step": 477886, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9500783681869507, "global_step": 477887, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.036263942718506, "global_step": 477888, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0942814350128174, "global_step": 477889, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0430808067321777, "global_step": 477890, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0999863147735596, "global_step": 477891, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9906541109085083, "global_step": 477892, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.055767059326172, "global_step": 477893, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.05755352973938, "global_step": 477894, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0241267681121826, "global_step": 477895, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.071876287460327, "global_step": 477896, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1290135383605957, "global_step": 477897, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.990072250366211, "global_step": 477898, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.047722816467285, "global_step": 477899, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9938817024230957, "global_step": 477900, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.094200611114502, "global_step": 477901, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0910086631774902, "global_step": 477902, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.031129837036133, "global_step": 477903, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0653464794158936, "global_step": 477904, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.074618339538574, "global_step": 477905, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.157503366470337, "global_step": 477906, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9983128309249878, "global_step": 477907, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.094276189804077, "global_step": 477908, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.036318063735962, "global_step": 477909, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.116879463195801, "global_step": 477910, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.03424072265625, "global_step": 477911, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.084017515182495, "global_step": 477912, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.096982955932617, "global_step": 477913, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0490102767944336, "global_step": 477914, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0822250843048096, "global_step": 477915, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.023571014404297, "global_step": 477916, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1048500537872314, "global_step": 477917, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.058492660522461, "global_step": 477918, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.105273723602295, "global_step": 477919, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.044480562210083, "global_step": 477920, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.071552038192749, "global_step": 477921, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0589847564697266, "global_step": 477922, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1061339378356934, "global_step": 477923, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1157751083374023, "global_step": 477924, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9980626106262207, "global_step": 477925, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0172011852264404, "global_step": 477926, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.055298089981079, "global_step": 477927, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1031579971313477, "global_step": 477928, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0528056621551514, "global_step": 477929, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.084639072418213, "global_step": 477930, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0426185131073, "global_step": 477931, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0711846351623535, "global_step": 477932, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.127898693084717, "global_step": 477933, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0224459171295166, "global_step": 477934, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0642178058624268, "global_step": 477935, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.994251012802124, "global_step": 477936, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1051437854766846, "global_step": 477937, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0697977542877197, "global_step": 477938, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.112114906311035, "global_step": 477939, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.133028507232666, "global_step": 477940, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9264332056045532, "global_step": 477941, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.080592632293701, "global_step": 477942, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0860366821289062, "global_step": 477943, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.12473464012146, "global_step": 477944, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0257065296173096, "global_step": 477945, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.951566457748413, "global_step": 477946, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.061572551727295, "global_step": 477947, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0135042667388916, "global_step": 477948, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9980223178863525, "global_step": 477949, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.025719165802002, "global_step": 477950, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.134737253189087, "global_step": 477951, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0547165870666504, "global_step": 477952, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1107101440429688, "global_step": 477953, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9761486053466797, "global_step": 477954, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0603153705596924, "global_step": 477955, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0876712799072266, "global_step": 477956, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0244510173797607, "global_step": 477957, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0716049671173096, "global_step": 477958, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.035043954849243, "global_step": 477959, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0928869247436523, "global_step": 477960, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.103933334350586, "global_step": 477961, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0633950233459473, "global_step": 477962, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0778021812438965, "global_step": 477963, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9994175434112549, "global_step": 477964, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.139625310897827, "global_step": 477965, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0674309730529785, "global_step": 477966, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1306777000427246, "global_step": 477967, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0760536193847656, "global_step": 477968, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0644423961639404, "global_step": 477969, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0607244968414307, "global_step": 477970, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9879138469696045, "global_step": 477971, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.918786644935608, "global_step": 477972, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0360090732574463, "global_step": 477973, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.002351999282837, "global_step": 477974, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0592379570007324, "global_step": 477975, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0490336418151855, "global_step": 477976, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0534169673919678, "global_step": 477977, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.051142454147339, "global_step": 477978, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.103315830230713, "global_step": 477979, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.086172580718994, "global_step": 477980, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0948257446289062, "global_step": 477981, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0827481746673584, "global_step": 477982, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0773441791534424, "global_step": 477983, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.016148328781128, "global_step": 477984, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.054830551147461, "global_step": 477985, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0280098915100098, "global_step": 477986, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.019073009490967, "global_step": 477987, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1723179817199707, "global_step": 477988, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0426387786865234, "global_step": 477989, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.072796583175659, "global_step": 477990, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1035256385803223, "global_step": 477991, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0646443367004395, "global_step": 477992, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0780770778656006, "global_step": 477993, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.174685001373291, "global_step": 477994, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.036513566970825, "global_step": 477995, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.021444320678711, "global_step": 477996, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.040661096572876, "global_step": 477997, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.050910472869873, "global_step": 477998, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.039391279220581, "global_step": 477999, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9760000705718994, "global_step": 478000, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.053539514541626, "global_step": 478001, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0862064361572266, "global_step": 478002, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.069160223007202, "global_step": 478003, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.054954767227173, "global_step": 478004, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.054570198059082, "global_step": 478005, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0653700828552246, "global_step": 478006, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.075650930404663, "global_step": 478007, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0776078701019287, "global_step": 478008, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9868111610412598, "global_step": 478009, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0175282955169678, "global_step": 478010, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.962094783782959, "global_step": 478011, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0624618530273438, "global_step": 478012, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0372507572174072, "global_step": 478013, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.034553050994873, "global_step": 478014, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0243847370147705, "global_step": 478015, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0058367252349854, "global_step": 478016, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0190236568450928, "global_step": 478017, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1177496910095215, "global_step": 478018, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.09714674949646, "global_step": 478019, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9904495477676392, "global_step": 478020, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.032740831375122, "global_step": 478021, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0280494689941406, "global_step": 478022, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0650954246520996, "global_step": 478023, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9723249673843384, "global_step": 478024, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0920770168304443, "global_step": 478025, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0943799018859863, "global_step": 478026, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1020400524139404, "global_step": 478027, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1648271083831787, "global_step": 478028, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.064758777618408, "global_step": 478029, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0738604068756104, "global_step": 478030, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9668519496917725, "global_step": 478031, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.055717945098877, "global_step": 478032, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.058941602706909, "global_step": 478033, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.067397117614746, "global_step": 478034, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0302000045776367, "global_step": 478035, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0922906398773193, "global_step": 478036, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0317113399505615, "global_step": 478037, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.052854537963867, "global_step": 478038, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1021811962127686, "global_step": 478039, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.032686948776245, "global_step": 478040, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1043481826782227, "global_step": 478041, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.052063465118408, "global_step": 478042, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0697197914123535, "global_step": 478043, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0381526947021484, "global_step": 478044, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9831162691116333, "global_step": 478045, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.042133092880249, "global_step": 478046, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1289308071136475, "global_step": 478047, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0628199577331543, "global_step": 478048, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.026036500930786, "global_step": 478049, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.065708875656128, "global_step": 478050, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.034917116165161, "global_step": 478051, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0488946437835693, "global_step": 478052, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.045990467071533, "global_step": 478053, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.091085910797119, "global_step": 478054, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1186954975128174, "global_step": 478055, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.103264808654785, "global_step": 478056, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1099696159362793, "global_step": 478057, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.045612335205078, "global_step": 478058, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0561585426330566, "global_step": 478059, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.059450626373291, "global_step": 478060, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0230181217193604, "global_step": 478061, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9889487028121948, "global_step": 478062, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.051614999771118, "global_step": 478063, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.01800274848938, "global_step": 478064, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1203043460845947, "global_step": 478065, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0237412452697754, "global_step": 478066, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9798883199691772, "global_step": 478067, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0703701972961426, "global_step": 478068, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.109241008758545, "global_step": 478069, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0614821910858154, "global_step": 478070, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1344964504241943, "global_step": 478071, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0509424209594727, "global_step": 478072, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.079380989074707, "global_step": 478073, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.084080219268799, "global_step": 478074, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0584805011749268, "global_step": 478075, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0196189880371094, "global_step": 478076, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9679315090179443, "global_step": 478077, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1232707500457764, "global_step": 478078, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.031247615814209, "global_step": 478079, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.160503387451172, "global_step": 478080, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0898561477661133, "global_step": 478081, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.016976833343506, "global_step": 478082, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9789800643920898, "global_step": 478083, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.042940378189087, "global_step": 478084, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0641965866088867, "global_step": 478085, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.050985813140869, "global_step": 478086, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9730422496795654, "global_step": 478087, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.018786668777466, "global_step": 478088, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9945982694625854, "global_step": 478089, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0167016983032227, "global_step": 478090, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0393245220184326, "global_step": 478091, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.093132495880127, "global_step": 478092, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1409912109375, "global_step": 478093, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0188376903533936, "global_step": 478094, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.989488959312439, "global_step": 478095, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0187764167785645, "global_step": 478096, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.034139394760132, "global_step": 478097, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9999877214431763, "global_step": 478098, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0838804244995117, "global_step": 478099, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9622230529785156, "global_step": 478100, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0514943599700928, "global_step": 478101, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.076141119003296, "global_step": 478102, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0540318489074707, "global_step": 478103, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.057190179824829, "global_step": 478104, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0443081855773926, "global_step": 478105, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0853824615478516, "global_step": 478106, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.002380847930908, "global_step": 478107, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0181102752685547, "global_step": 478108, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.02079701423645, "global_step": 478109, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.034593105316162, "global_step": 478110, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.006985664367676, "global_step": 478111, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.105658531188965, "global_step": 478112, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.987736701965332, "global_step": 478113, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0293757915496826, "global_step": 478114, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.033284902572632, "global_step": 478115, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.00282621383667, "global_step": 478116, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0898733139038086, "global_step": 478117, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0043444633483887, "global_step": 478118, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0665557384490967, "global_step": 478119, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0711324214935303, "global_step": 478120, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0394628047943115, "global_step": 478121, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0709996223449707, "global_step": 478122, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.006490707397461, "global_step": 478123, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1331071853637695, "global_step": 478124, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0555942058563232, "global_step": 478125, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.037299633026123, "global_step": 478126, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9888373613357544, "global_step": 478127, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.983595848083496, "global_step": 478128, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.096867799758911, "global_step": 478129, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0271832942962646, "global_step": 478130, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9922945499420166, "global_step": 478131, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0932881832122803, "global_step": 478132, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0889549255371094, "global_step": 478133, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9946913719177246, "global_step": 478134, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9150029420852661, "global_step": 478135, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0888092517852783, "global_step": 478136, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0117411613464355, "global_step": 478137, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0593833923339844, "global_step": 478138, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.129352569580078, "global_step": 478139, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0078225135803223, "global_step": 478140, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.030205011367798, "global_step": 478141, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0743906497955322, "global_step": 478142, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9900652170181274, "global_step": 478143, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.98448646068573, "global_step": 478144, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1466312408447266, "global_step": 478145, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.078021764755249, "global_step": 478146, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.165601968765259, "global_step": 478147, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1258373260498047, "global_step": 478148, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0940582752227783, "global_step": 478149, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9548944234848022, "global_step": 478150, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1314921379089355, "global_step": 478151, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1004836559295654, "global_step": 478152, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.049948215484619, "global_step": 478153, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0272748470306396, "global_step": 478154, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.997514009475708, "global_step": 478155, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.062049627304077, "global_step": 478156, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.02061128616333, "global_step": 478157, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1063921451568604, "global_step": 478158, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0819733142852783, "global_step": 478159, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.059248924255371, "global_step": 478160, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.017756938934326, "global_step": 478161, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0352702140808105, "global_step": 478162, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.027761936187744, "global_step": 478163, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.069349527359009, "global_step": 478164, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0640480518341064, "global_step": 478165, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1017372608184814, "global_step": 478166, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0443763732910156, "global_step": 478167, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.028564214706421, "global_step": 478168, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0849452018737793, "global_step": 478169, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0180656909942627, "global_step": 478170, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0667641162872314, "global_step": 478171, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.043757200241089, "global_step": 478172, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.004761219024658, "global_step": 478173, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1387245655059814, "global_step": 478174, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1355857849121094, "global_step": 478175, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.049359083175659, "global_step": 478176, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0307540893554688, "global_step": 478177, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.079474449157715, "global_step": 478178, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.078944444656372, "global_step": 478179, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0532126426696777, "global_step": 478180, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0753674507141113, "global_step": 478181, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.011680841445923, "global_step": 478182, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0040903091430664, "global_step": 478183, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1154470443725586, "global_step": 478184, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.021005392074585, "global_step": 478185, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0682742595672607, "global_step": 478186, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.12164568901062, "global_step": 478187, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0471267700195312, "global_step": 478188, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0976295471191406, "global_step": 478189, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.108398675918579, "global_step": 478190, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0539846420288086, "global_step": 478191, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.014596939086914, "global_step": 478192, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0803821086883545, "global_step": 478193, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.023331642150879, "global_step": 478194, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.073199987411499, "global_step": 478195, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.118203639984131, "global_step": 478196, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0601813793182373, "global_step": 478197, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1225991249084473, "global_step": 478198, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1190497875213623, "global_step": 478199, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.045123815536499, "global_step": 478200, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0528602600097656, "global_step": 478201, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1035714149475098, "global_step": 478202, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.133157968521118, "global_step": 478203, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.067528009414673, "global_step": 478204, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0350635051727295, "global_step": 478205, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0621654987335205, "global_step": 478206, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.110492467880249, "global_step": 478207, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.079428195953369, "global_step": 478208, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.993853211402893, "global_step": 478209, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0705406665802, "global_step": 478210, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0223848819732666, "global_step": 478211, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.055483341217041, "global_step": 478212, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0278449058532715, "global_step": 478213, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9322007894515991, "global_step": 478214, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.03786563873291, "global_step": 478215, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0061047077178955, "global_step": 478216, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9863629341125488, "global_step": 478217, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9519809484481812, "global_step": 478218, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.039137125015259, "global_step": 478219, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1336052417755127, "global_step": 478220, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0387251377105713, "global_step": 478221, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0970711708068848, "global_step": 478222, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0797975063323975, "global_step": 478223, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0423011779785156, "global_step": 478224, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0222015380859375, "global_step": 478225, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0216972827911377, "global_step": 478226, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.999939203262329, "global_step": 478227, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0786869525909424, "global_step": 478228, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0890274047851562, "global_step": 478229, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.997016191482544, "global_step": 478230, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.025010585784912, "global_step": 478231, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9710166454315186, "global_step": 478232, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.034660577774048, "global_step": 478233, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0100226402282715, "global_step": 478234, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0008344650268555, "global_step": 478235, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9896039962768555, "global_step": 478236, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.111790418624878, "global_step": 478237, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0605037212371826, "global_step": 478238, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1143243312835693, "global_step": 478239, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0843217372894287, "global_step": 478240, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.078148603439331, "global_step": 478241, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.032606601715088, "global_step": 478242, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.084876537322998, "global_step": 478243, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.094501256942749, "global_step": 478244, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0990679264068604, "global_step": 478245, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9839863777160645, "global_step": 478246, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.05564284324646, "global_step": 478247, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0302438735961914, "global_step": 478248, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1020097732543945, "global_step": 478249, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.075312852859497, "global_step": 478250, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.054417848587036, "global_step": 478251, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.052027940750122, "global_step": 478252, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9752458333969116, "global_step": 478253, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0452611446380615, "global_step": 478254, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1036415100097656, "global_step": 478255, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0712828636169434, "global_step": 478256, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9945729970932007, "global_step": 478257, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9938706159591675, "global_step": 478258, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0405664443969727, "global_step": 478259, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0924549102783203, "global_step": 478260, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0652308464050293, "global_step": 478261, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1133973598480225, "global_step": 478262, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.102839469909668, "global_step": 478263, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0494353771209717, "global_step": 478264, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.05106520652771, "global_step": 478265, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1038119792938232, "global_step": 478266, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.091057300567627, "global_step": 478267, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0820233821868896, "global_step": 478268, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.060777425765991, "global_step": 478269, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9807517528533936, "global_step": 478270, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.038257360458374, "global_step": 478271, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.032038927078247, "global_step": 478272, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1265413761138916, "global_step": 478273, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.172159433364868, "global_step": 478274, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.116760730743408, "global_step": 478275, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0942468643188477, "global_step": 478276, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.108327865600586, "global_step": 478277, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0644447803497314, "global_step": 478278, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.062828302383423, "global_step": 478279, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.08284854888916, "global_step": 478280, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0383994579315186, "global_step": 478281, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.05808162689209, "global_step": 478282, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.084052801132202, "global_step": 478283, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.039919376373291, "global_step": 478284, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1020467281341553, "global_step": 478285, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0529701709747314, "global_step": 478286, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.056668519973755, "global_step": 478287, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.15268611907959, "global_step": 478288, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0812323093414307, "global_step": 478289, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.083843231201172, "global_step": 478290, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.011644124984741, "global_step": 478291, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1603779792785645, "global_step": 478292, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0406460762023926, "global_step": 478293, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1466681957244873, "global_step": 478294, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0598537921905518, "global_step": 478295, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.029055118560791, "global_step": 478296, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9703125953674316, "global_step": 478297, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.091308832168579, "global_step": 478298, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.067213773727417, "global_step": 478299, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0397791862487793, "global_step": 478300, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.112339496612549, "global_step": 478301, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0379066467285156, "global_step": 478302, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0722124576568604, "global_step": 478303, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.049593210220337, "global_step": 478304, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0139732360839844, "global_step": 478305, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0961546897888184, "global_step": 478306, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0036981105804443, "global_step": 478307, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.037529230117798, "global_step": 478308, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.021461009979248, "global_step": 478309, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0270447731018066, "global_step": 478310, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0604734420776367, "global_step": 478311, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0976438522338867, "global_step": 478312, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.091430902481079, "global_step": 478313, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9885711669921875, "global_step": 478314, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0324904918670654, "global_step": 478315, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0027711391448975, "global_step": 478316, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0180704593658447, "global_step": 478317, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.124483823776245, "global_step": 478318, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9921292066574097, "global_step": 478319, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0952999591827393, "global_step": 478320, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0425941944122314, "global_step": 478321, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.029557228088379, "global_step": 478322, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.043959140777588, "global_step": 478323, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0733911991119385, "global_step": 478324, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.121035575866699, "global_step": 478325, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1541712284088135, "global_step": 478326, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9672707319259644, "global_step": 478327, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.103713035583496, "global_step": 478328, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1668808460235596, "global_step": 478329, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.087008237838745, "global_step": 478330, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1474573612213135, "global_step": 478331, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1218504905700684, "global_step": 478332, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9767711162567139, "global_step": 478333, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0506322383880615, "global_step": 478334, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.037874698638916, "global_step": 478335, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.013575315475464, "global_step": 478336, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.036118745803833, "global_step": 478337, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.067078113555908, "global_step": 478338, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0821030139923096, "global_step": 478339, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0531582832336426, "global_step": 478340, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0133116245269775, "global_step": 478341, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0345048904418945, "global_step": 478342, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.020728588104248, "global_step": 478343, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0998101234436035, "global_step": 478344, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1070668697357178, "global_step": 478345, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.091383457183838, "global_step": 478346, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1377856731414795, "global_step": 478347, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0098187923431396, "global_step": 478348, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1389951705932617, "global_step": 478349, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0209131240844727, "global_step": 478350, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.091383218765259, "global_step": 478351, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1725518703460693, "global_step": 478352, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0410828590393066, "global_step": 478353, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0469419956207275, "global_step": 478354, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0489015579223633, "global_step": 478355, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.046113967895508, "global_step": 478356, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0890495777130127, "global_step": 478357, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9868651628494263, "global_step": 478358, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1724040508270264, "global_step": 478359, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.026015043258667, "global_step": 478360, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.026691198348999, "global_step": 478361, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.041360378265381, "global_step": 478362, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0594944953918457, "global_step": 478363, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0297861099243164, "global_step": 478364, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.106049060821533, "global_step": 478365, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0285086631774902, "global_step": 478366, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0962531566619873, "global_step": 478367, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.002553939819336, "global_step": 478368, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.121884346008301, "global_step": 478369, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.070805788040161, "global_step": 478370, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9930858612060547, "global_step": 478371, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1060738563537598, "global_step": 478372, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0287716388702393, "global_step": 478373, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0605099201202393, "global_step": 478374, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.961372971534729, "global_step": 478375, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0802979469299316, "global_step": 478376, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.068452835083008, "global_step": 478377, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.122939109802246, "global_step": 478378, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0180537700653076, "global_step": 478379, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0874624252319336, "global_step": 478380, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1161909103393555, "global_step": 478381, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0664920806884766, "global_step": 478382, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9414994716644287, "global_step": 478383, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9713653326034546, "global_step": 478384, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.065438985824585, "global_step": 478385, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.013965368270874, "global_step": 478386, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0694029331207275, "global_step": 478387, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.060804843902588, "global_step": 478388, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0878443717956543, "global_step": 478389, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9791948795318604, "global_step": 478390, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.087085723876953, "global_step": 478391, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1186444759368896, "global_step": 478392, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.028792142868042, "global_step": 478393, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.150036334991455, "global_step": 478394, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0642898082733154, "global_step": 478395, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.026934862136841, "global_step": 478396, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.117445468902588, "global_step": 478397, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0456361770629883, "global_step": 478398, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.056659460067749, "global_step": 478399, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.084290027618408, "global_step": 478400, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.09405779838562, "global_step": 478401, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0574004650115967, "global_step": 478402, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0287036895751953, "global_step": 478403, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0008740425109863, "global_step": 478404, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.01999831199646, "global_step": 478405, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.053253650665283, "global_step": 478406, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.123570442199707, "global_step": 478407, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1237847805023193, "global_step": 478408, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.104651689529419, "global_step": 478409, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.086468458175659, "global_step": 478410, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0717015266418457, "global_step": 478411, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.096611976623535, "global_step": 478412, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.091479778289795, "global_step": 478413, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.042555570602417, "global_step": 478414, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.065347909927368, "global_step": 478415, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.068512201309204, "global_step": 478416, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1187708377838135, "global_step": 478417, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.993141531944275, "global_step": 478418, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9836918115615845, "global_step": 478419, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.047757387161255, "global_step": 478420, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0953259468078613, "global_step": 478421, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.107150077819824, "global_step": 478422, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0993425846099854, "global_step": 478423, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0369324684143066, "global_step": 478424, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.042836904525757, "global_step": 478425, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.067943572998047, "global_step": 478426, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.080155849456787, "global_step": 478427, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.116990089416504, "global_step": 478428, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.96454656124115, "global_step": 478429, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.023256540298462, "global_step": 478430, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1174814701080322, "global_step": 478431, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0942773818969727, "global_step": 478432, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.997730016708374, "global_step": 478433, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.014519214630127, "global_step": 478434, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0642828941345215, "global_step": 478435, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0469133853912354, "global_step": 478436, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.035226821899414, "global_step": 478437, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1274795532226562, "global_step": 478438, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.104552984237671, "global_step": 478439, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.052705764770508, "global_step": 478440, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0258538722991943, "global_step": 478441, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0428285598754883, "global_step": 478442, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.074545383453369, "global_step": 478443, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.091520309448242, "global_step": 478444, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1110422611236572, "global_step": 478445, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.062879800796509, "global_step": 478446, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1587016582489014, "global_step": 478447, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0053176879882812, "global_step": 478448, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.062410593032837, "global_step": 478449, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.179316997528076, "global_step": 478450, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.068202257156372, "global_step": 478451, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0608270168304443, "global_step": 478452, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0396196842193604, "global_step": 478453, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.059197187423706, "global_step": 478454, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.103088617324829, "global_step": 478455, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1020638942718506, "global_step": 478456, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0705909729003906, "global_step": 478457, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0841224193573, "global_step": 478458, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.046653985977173, "global_step": 478459, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0478811264038086, "global_step": 478460, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1223325729370117, "global_step": 478461, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1565475463867188, "global_step": 478462, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.027684450149536, "global_step": 478463, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1390480995178223, "global_step": 478464, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0538721084594727, "global_step": 478465, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0005085468292236, "global_step": 478466, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0866646766662598, "global_step": 478467, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1255555152893066, "global_step": 478468, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.084583282470703, "global_step": 478469, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.094505786895752, "global_step": 478470, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0846245288848877, "global_step": 478471, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9891068935394287, "global_step": 478472, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1121938228607178, "global_step": 478473, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0967373847961426, "global_step": 478474, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1375582218170166, "global_step": 478475, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0091240406036377, "global_step": 478476, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.019956111907959, "global_step": 478477, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0751590728759766, "global_step": 478478, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0779781341552734, "global_step": 478479, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9707669019699097, "global_step": 478480, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0857818126678467, "global_step": 478481, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.006664991378784, "global_step": 478482, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9788933992385864, "global_step": 478483, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.030454635620117, "global_step": 478484, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.122641086578369, "global_step": 478485, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0253658294677734, "global_step": 478486, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0619728565216064, "global_step": 478487, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0618889331817627, "global_step": 478488, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1103477478027344, "global_step": 478489, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.099965810775757, "global_step": 478490, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1116783618927, "global_step": 478491, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.102325201034546, "global_step": 478492, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1145153045654297, "global_step": 478493, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.990727186203003, "global_step": 478494, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0272488594055176, "global_step": 478495, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1674954891204834, "global_step": 478496, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0277533531188965, "global_step": 478497, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1271607875823975, "global_step": 478498, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0079898834228516, "global_step": 478499, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9219273328781128, "global_step": 478500, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9874495267868042, "global_step": 478501, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0130717754364014, "global_step": 478502, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0253446102142334, "global_step": 478503, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.082308530807495, "global_step": 478504, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9835209846496582, "global_step": 478505, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.00479793548584, "global_step": 478506, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.027709484100342, "global_step": 478507, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.019566059112549, "global_step": 478508, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.017143487930298, "global_step": 478509, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0557937622070312, "global_step": 478510, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.079519271850586, "global_step": 478511, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.992412805557251, "global_step": 478512, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.098745584487915, "global_step": 478513, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0355663299560547, "global_step": 478514, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0691184997558594, "global_step": 478515, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0628581047058105, "global_step": 478516, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1617634296417236, "global_step": 478517, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.040172815322876, "global_step": 478518, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1141574382781982, "global_step": 478519, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0635273456573486, "global_step": 478520, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9889700412750244, "global_step": 478521, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9984419345855713, "global_step": 478522, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.063546657562256, "global_step": 478523, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.089491128921509, "global_step": 478524, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.075730085372925, "global_step": 478525, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0385775566101074, "global_step": 478526, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0107319355010986, "global_step": 478527, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0731759071350098, "global_step": 478528, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.120716094970703, "global_step": 478529, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0150623321533203, "global_step": 478530, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.994504690170288, "global_step": 478531, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0544748306274414, "global_step": 478532, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.095388412475586, "global_step": 478533, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.004911422729492, "global_step": 478534, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.035221815109253, "global_step": 478535, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.154186248779297, "global_step": 478536, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0478012561798096, "global_step": 478537, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0775716304779053, "global_step": 478538, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.049694538116455, "global_step": 478539, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0074713230133057, "global_step": 478540, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0213894844055176, "global_step": 478541, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.038670539855957, "global_step": 478542, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.097398519515991, "global_step": 478543, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0701701641082764, "global_step": 478544, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0584545135498047, "global_step": 478545, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.112720251083374, "global_step": 478546, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0789194107055664, "global_step": 478547, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1608288288116455, "global_step": 478548, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0450282096862793, "global_step": 478549, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1842124462127686, "global_step": 478550, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0879461765289307, "global_step": 478551, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9987401962280273, "global_step": 478552, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.044774055480957, "global_step": 478553, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0072855949401855, "global_step": 478554, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1100854873657227, "global_step": 478555, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.05710506439209, "global_step": 478556, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.10925030708313, "global_step": 478557, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0883915424346924, "global_step": 478558, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.2529642581939697, "global_step": 478559, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.060293197631836, "global_step": 478560, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9888619184494019, "global_step": 478561, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0591506958007812, "global_step": 478562, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.052265167236328, "global_step": 478563, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0486857891082764, "global_step": 478564, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.154853582382202, "global_step": 478565, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0989224910736084, "global_step": 478566, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.092465400695801, "global_step": 478567, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0324411392211914, "global_step": 478568, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.03609037399292, "global_step": 478569, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1067028045654297, "global_step": 478570, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9528639316558838, "global_step": 478571, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.137528419494629, "global_step": 478572, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0383150577545166, "global_step": 478573, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.061161756515503, "global_step": 478574, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0592503547668457, "global_step": 478575, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.99977707862854, "global_step": 478576, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0358097553253174, "global_step": 478577, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1230616569519043, "global_step": 478578, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9904533624649048, "global_step": 478579, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0583221912384033, "global_step": 478580, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1447277069091797, "global_step": 478581, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0657198429107666, "global_step": 478582, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0754730701446533, "global_step": 478583, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0702993869781494, "global_step": 478584, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0587246417999268, "global_step": 478585, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.157073497772217, "global_step": 478586, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0588653087615967, "global_step": 478587, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.039828300476074, "global_step": 478588, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.035038948059082, "global_step": 478589, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.083495855331421, "global_step": 478590, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0807785987854004, "global_step": 478591, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1001412868499756, "global_step": 478592, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.09665846824646, "global_step": 478593, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0934643745422363, "global_step": 478594, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.026952028274536, "global_step": 478595, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1255931854248047, "global_step": 478596, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.069019079208374, "global_step": 478597, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.067101001739502, "global_step": 478598, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.189436674118042, "global_step": 478599, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0541422367095947, "global_step": 478600, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.052064895629883, "global_step": 478601, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.015087366104126, "global_step": 478602, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1838223934173584, "global_step": 478603, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.093409776687622, "global_step": 478604, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.998376488685608, "global_step": 478605, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.04585599899292, "global_step": 478606, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1426236629486084, "global_step": 478607, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.108647108078003, "global_step": 478608, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.025446891784668, "global_step": 478609, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1442785263061523, "global_step": 478610, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1129884719848633, "global_step": 478611, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.027555227279663, "global_step": 478612, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.040135145187378, "global_step": 478613, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1013875007629395, "global_step": 478614, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1070499420166016, "global_step": 478615, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0864717960357666, "global_step": 478616, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1359822750091553, "global_step": 478617, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.120877504348755, "global_step": 478618, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0364205837249756, "global_step": 478619, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.968314290046692, "global_step": 478620, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9875550270080566, "global_step": 478621, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.019214391708374, "global_step": 478622, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.052412986755371, "global_step": 478623, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9869801998138428, "global_step": 478624, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.074690818786621, "global_step": 478625, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0588860511779785, "global_step": 478626, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1308388710021973, "global_step": 478627, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0805513858795166, "global_step": 478628, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1239449977874756, "global_step": 478629, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1451570987701416, "global_step": 478630, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0400431156158447, "global_step": 478631, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0966882705688477, "global_step": 478632, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.116126775741577, "global_step": 478633, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0759968757629395, "global_step": 478634, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1128296852111816, "global_step": 478635, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.076167106628418, "global_step": 478636, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.03763747215271, "global_step": 478637, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1440682411193848, "global_step": 478638, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1146750450134277, "global_step": 478639, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0827832221984863, "global_step": 478640, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.019402503967285, "global_step": 478641, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0860655307769775, "global_step": 478642, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1435186862945557, "global_step": 478643, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.093770742416382, "global_step": 478644, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1001362800598145, "global_step": 478645, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0236854553222656, "global_step": 478646, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.087662935256958, "global_step": 478647, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1072757244110107, "global_step": 478648, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0530872344970703, "global_step": 478649, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.117069959640503, "global_step": 478650, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.031247615814209, "global_step": 478651, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0641672611236572, "global_step": 478652, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.107861042022705, "global_step": 478653, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.057284116744995, "global_step": 478654, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.124920129776001, "global_step": 478655, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.072375535964966, "global_step": 478656, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0459165573120117, "global_step": 478657, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0049197673797607, "global_step": 478658, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9799892902374268, "global_step": 478659, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0980358123779297, "global_step": 478660, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0888195037841797, "global_step": 478661, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.064286947250366, "global_step": 478662, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0893311500549316, "global_step": 478663, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9700149297714233, "global_step": 478664, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1452267169952393, "global_step": 478665, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0358359813690186, "global_step": 478666, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1083812713623047, "global_step": 478667, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0854363441467285, "global_step": 478668, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.121526002883911, "global_step": 478669, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.080885648727417, "global_step": 478670, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1055309772491455, "global_step": 478671, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.115945339202881, "global_step": 478672, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.030557155609131, "global_step": 478673, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0934202671051025, "global_step": 478674, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1482999324798584, "global_step": 478675, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1101717948913574, "global_step": 478676, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.070401191711426, "global_step": 478677, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.069953680038452, "global_step": 478678, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0840840339660645, "global_step": 478679, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.034522294998169, "global_step": 478680, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0236828327178955, "global_step": 478681, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0075252056121826, "global_step": 478682, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.109801769256592, "global_step": 478683, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9571123123168945, "global_step": 478684, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0723674297332764, "global_step": 478685, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.041353464126587, "global_step": 478686, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0351552963256836, "global_step": 478687, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0988707542419434, "global_step": 478688, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0401742458343506, "global_step": 478689, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0881099700927734, "global_step": 478690, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0098910331726074, "global_step": 478691, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0909366607666016, "global_step": 478692, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0177690982818604, "global_step": 478693, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.013319253921509, "global_step": 478694, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.021254539489746, "global_step": 478695, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0469226837158203, "global_step": 478696, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0917699337005615, "global_step": 478697, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9906752109527588, "global_step": 478698, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.061119556427002, "global_step": 478699, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9587492942810059, "global_step": 478700, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0267956256866455, "global_step": 478701, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.994072437286377, "global_step": 478702, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.073908567428589, "global_step": 478703, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1105527877807617, "global_step": 478704, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.052593231201172, "global_step": 478705, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0696051120758057, "global_step": 478706, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9938486814498901, "global_step": 478707, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.199472188949585, "global_step": 478708, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.979981780052185, "global_step": 478709, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9998451471328735, "global_step": 478710, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.970521092414856, "global_step": 478711, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.12245512008667, "global_step": 478712, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.112421989440918, "global_step": 478713, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9806536436080933, "global_step": 478714, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.025529623031616, "global_step": 478715, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.103982448577881, "global_step": 478716, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0258591175079346, "global_step": 478717, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1241085529327393, "global_step": 478718, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9907946586608887, "global_step": 478719, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.063652753829956, "global_step": 478720, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.08721661567688, "global_step": 478721, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.097628355026245, "global_step": 478722, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0772602558135986, "global_step": 478723, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.060777425765991, "global_step": 478724, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9997498989105225, "global_step": 478725, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.055509328842163, "global_step": 478726, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0635361671447754, "global_step": 478727, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0934951305389404, "global_step": 478728, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0875279903411865, "global_step": 478729, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0721561908721924, "global_step": 478730, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0867602825164795, "global_step": 478731, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0236003398895264, "global_step": 478732, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.110780954360962, "global_step": 478733, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0274932384490967, "global_step": 478734, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.074127674102783, "global_step": 478735, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1344072818756104, "global_step": 478736, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9724795818328857, "global_step": 478737, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9900075197219849, "global_step": 478738, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.151855707168579, "global_step": 478739, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.035531759262085, "global_step": 478740, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1581974029541016, "global_step": 478741, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.07210111618042, "global_step": 478742, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.074070453643799, "global_step": 478743, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.13252329826355, "global_step": 478744, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.113992929458618, "global_step": 478745, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.107313632965088, "global_step": 478746, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0661892890930176, "global_step": 478747, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.078972339630127, "global_step": 478748, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0733718872070312, "global_step": 478749, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0443153381347656, "global_step": 478750, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0490477085113525, "global_step": 478751, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1097943782806396, "global_step": 478752, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.075462579727173, "global_step": 478753, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.099325656890869, "global_step": 478754, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.065585136413574, "global_step": 478755, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0171186923980713, "global_step": 478756, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0092148780822754, "global_step": 478757, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0408947467803955, "global_step": 478758, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0784993171691895, "global_step": 478759, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0834157466888428, "global_step": 478760, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0446159839630127, "global_step": 478761, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.073355197906494, "global_step": 478762, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0724878311157227, "global_step": 478763, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0305609703063965, "global_step": 478764, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.135725736618042, "global_step": 478765, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.040487051010132, "global_step": 478766, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0322787761688232, "global_step": 478767, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0527615547180176, "global_step": 478768, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.052018165588379, "global_step": 478769, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.027672052383423, "global_step": 478770, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1454050540924072, "global_step": 478771, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.028639793395996, "global_step": 478772, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1122891902923584, "global_step": 478773, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9532464742660522, "global_step": 478774, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1564722061157227, "global_step": 478775, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1272997856140137, "global_step": 478776, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9847286939620972, "global_step": 478777, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.051767349243164, "global_step": 478778, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1502649784088135, "global_step": 478779, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0521321296691895, "global_step": 478780, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0989015102386475, "global_step": 478781, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.045025587081909, "global_step": 478782, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0990333557128906, "global_step": 478783, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1082026958465576, "global_step": 478784, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9207497835159302, "global_step": 478785, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1545827388763428, "global_step": 478786, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1037120819091797, "global_step": 478787, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1327083110809326, "global_step": 478788, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1074817180633545, "global_step": 478789, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.133561611175537, "global_step": 478790, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.16792893409729, "global_step": 478791, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0893430709838867, "global_step": 478792, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.971479058265686, "global_step": 478793, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0725953578948975, "global_step": 478794, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.040762424468994, "global_step": 478795, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0795350074768066, "global_step": 478796, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.144740581512451, "global_step": 478797, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.069023370742798, "global_step": 478798, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0462512969970703, "global_step": 478799, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0975966453552246, "global_step": 478800, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.069796085357666, "global_step": 478801, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.077629566192627, "global_step": 478802, "epoch": 843, "lr": 5e-05}
{"train_loss": 1.9445720911026, "global_step": 478803, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1518075466156006, "global_step": 478804, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.1407487392425537, "global_step": 478805, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0607399940490723, "global_step": 478806, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.118191957473755, "global_step": 478807, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0300049781799316, "global_step": 478808, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.021617889404297, "global_step": 478809, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0255327224731445, "global_step": 478810, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.104696035385132, "global_step": 478811, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0492966175079346, "global_step": 478812, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.060943126678467, "global_step": 478813, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0821945667266846, "global_step": 478814, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0086936950683594, "global_step": 478815, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0426714420318604, "global_step": 478816, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.115091562271118, "global_step": 478817, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.0617101192474365, "global_step": 478818, "epoch": 843, "lr": 5e-05}
{"train_loss": 2.076643943786621, "global_step": 478819, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0445053577423096, "global_step": 478820, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0643956661224365, "global_step": 478821, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9545660018920898, "global_step": 478822, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.111764430999756, "global_step": 478823, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0072526931762695, "global_step": 478824, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.088385820388794, "global_step": 478825, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1211652755737305, "global_step": 478826, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0025668144226074, "global_step": 478827, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0219500064849854, "global_step": 478828, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9677836894989014, "global_step": 478829, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.025057077407837, "global_step": 478830, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9994884729385376, "global_step": 478831, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.102785587310791, "global_step": 478832, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0659618377685547, "global_step": 478833, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.10907244682312, "global_step": 478834, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.081296920776367, "global_step": 478835, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.028627395629883, "global_step": 478836, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.089620351791382, "global_step": 478837, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.040968894958496, "global_step": 478838, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.058905601501465, "global_step": 478839, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0006206035614014, "global_step": 478840, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1048660278320312, "global_step": 478841, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9828603267669678, "global_step": 478842, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.053342819213867, "global_step": 478843, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0915229320526123, "global_step": 478844, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.118242025375366, "global_step": 478845, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0758986473083496, "global_step": 478846, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0102696418762207, "global_step": 478847, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.001410484313965, "global_step": 478848, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0467936992645264, "global_step": 478849, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0798397064208984, "global_step": 478850, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0506763458251953, "global_step": 478851, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.064164400100708, "global_step": 478852, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.027972459793091, "global_step": 478853, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1034491062164307, "global_step": 478854, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0780413150787354, "global_step": 478855, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0379855632781982, "global_step": 478856, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9980721473693848, "global_step": 478857, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.015334129333496, "global_step": 478858, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0488245487213135, "global_step": 478859, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0598948001861572, "global_step": 478860, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0736117362976074, "global_step": 478861, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9750486612319946, "global_step": 478862, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.061568260192871, "global_step": 478863, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.052002191543579, "global_step": 478864, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.030667304992676, "global_step": 478865, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0011632442474365, "global_step": 478866, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.02083158493042, "global_step": 478867, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.053119659423828, "global_step": 478868, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9536714553833008, "global_step": 478869, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9905685186386108, "global_step": 478870, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0595498085021973, "global_step": 478871, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.046699285507202, "global_step": 478872, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9117594957351685, "global_step": 478873, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0852596759796143, "global_step": 478874, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.953359603881836, "global_step": 478875, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.06410551071167, "global_step": 478876, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.09053111076355, "global_step": 478877, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1052536964416504, "global_step": 478878, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.133974552154541, "global_step": 478879, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.059382915496826, "global_step": 478880, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9636578559875488, "global_step": 478881, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1058197021484375, "global_step": 478882, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.09563946723938, "global_step": 478883, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.015279769897461, "global_step": 478884, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9934598207473755, "global_step": 478885, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9784064292907715, "global_step": 478886, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0337460041046143, "global_step": 478887, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.040968894958496, "global_step": 478888, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.100548267364502, "global_step": 478889, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0119848251342773, "global_step": 478890, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.070780038833618, "global_step": 478891, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0084023475646973, "global_step": 478892, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0608763694763184, "global_step": 478893, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.036499261856079, "global_step": 478894, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.030306816101074, "global_step": 478895, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.055450916290283, "global_step": 478896, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.007605791091919, "global_step": 478897, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9383834600448608, "global_step": 478898, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.07000732421875, "global_step": 478899, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1005706787109375, "global_step": 478900, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.112506628036499, "global_step": 478901, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0395936965942383, "global_step": 478902, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9939241409301758, "global_step": 478903, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0388782024383545, "global_step": 478904, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0877957344055176, "global_step": 478905, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.039207935333252, "global_step": 478906, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.167415142059326, "global_step": 478907, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1143407821655273, "global_step": 478908, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.084495782852173, "global_step": 478909, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0991804599761963, "global_step": 478910, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1077394485473633, "global_step": 478911, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0739595890045166, "global_step": 478912, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0451204776763916, "global_step": 478913, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0197741985321045, "global_step": 478914, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1546828746795654, "global_step": 478915, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9689645767211914, "global_step": 478916, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0504565238952637, "global_step": 478917, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.059556484222412, "global_step": 478918, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1556241512298584, "global_step": 478919, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0220038890838623, "global_step": 478920, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0568363666534424, "global_step": 478921, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0877788066864014, "global_step": 478922, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9935953617095947, "global_step": 478923, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.965029001235962, "global_step": 478924, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9380189180374146, "global_step": 478925, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0641167163848877, "global_step": 478926, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9653619527816772, "global_step": 478927, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.101801872253418, "global_step": 478928, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.11750864982605, "global_step": 478929, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0772619247436523, "global_step": 478930, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0118372440338135, "global_step": 478931, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.982184648513794, "global_step": 478932, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0697364807128906, "global_step": 478933, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.110943078994751, "global_step": 478934, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.063875198364258, "global_step": 478935, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0309386253356934, "global_step": 478936, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9916280508041382, "global_step": 478937, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0640220642089844, "global_step": 478938, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.103679895401001, "global_step": 478939, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0413384437561035, "global_step": 478940, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0853826999664307, "global_step": 478941, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.105337619781494, "global_step": 478942, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.051694631576538, "global_step": 478943, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9651156663894653, "global_step": 478944, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.083665609359741, "global_step": 478945, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1112308502197266, "global_step": 478946, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0895323753356934, "global_step": 478947, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9876329898834229, "global_step": 478948, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1075737476348877, "global_step": 478949, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.052708625793457, "global_step": 478950, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.989736557006836, "global_step": 478951, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.024691343307495, "global_step": 478952, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.007467269897461, "global_step": 478953, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.030000686645508, "global_step": 478954, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1187522411346436, "global_step": 478955, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0097553730010986, "global_step": 478956, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0564558506011963, "global_step": 478957, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0451366901397705, "global_step": 478958, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9409122467041016, "global_step": 478959, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.067538261413574, "global_step": 478960, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0159542560577393, "global_step": 478961, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.050006866455078, "global_step": 478962, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1153321266174316, "global_step": 478963, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.099254608154297, "global_step": 478964, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.091622829437256, "global_step": 478965, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0195305347442627, "global_step": 478966, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.015678882598877, "global_step": 478967, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0377018451690674, "global_step": 478968, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9332712888717651, "global_step": 478969, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0987889766693115, "global_step": 478970, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1362624168395996, "global_step": 478971, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0437185764312744, "global_step": 478972, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0146803855895996, "global_step": 478973, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0905983448028564, "global_step": 478974, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.960716962814331, "global_step": 478975, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.051046848297119, "global_step": 478976, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.109931707382202, "global_step": 478977, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0475409030914307, "global_step": 478978, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0902762413024902, "global_step": 478979, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0853872299194336, "global_step": 478980, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0855555534362793, "global_step": 478981, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0479674339294434, "global_step": 478982, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.099838972091675, "global_step": 478983, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1330411434173584, "global_step": 478984, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.051802396774292, "global_step": 478985, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0782670974731445, "global_step": 478986, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0535547733306885, "global_step": 478987, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0453572273254395, "global_step": 478988, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0644748210906982, "global_step": 478989, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.114283800125122, "global_step": 478990, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0952682495117188, "global_step": 478991, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.027906894683838, "global_step": 478992, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0016870498657227, "global_step": 478993, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0976221561431885, "global_step": 478994, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.090916156768799, "global_step": 478995, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.996333122253418, "global_step": 478996, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0928304195404053, "global_step": 478997, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0336129665374756, "global_step": 478998, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.07912015914917, "global_step": 478999, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0817997455596924, "global_step": 479000, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.016380548477173, "global_step": 479001, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9744364023208618, "global_step": 479002, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9967237710952759, "global_step": 479003, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.056968927383423, "global_step": 479004, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0205979347229004, "global_step": 479005, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1263210773468018, "global_step": 479006, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0324172973632812, "global_step": 479007, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.027921438217163, "global_step": 479008, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.070034980773926, "global_step": 479009, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.044041395187378, "global_step": 479010, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.047503709793091, "global_step": 479011, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0360963344573975, "global_step": 479012, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.053908348083496, "global_step": 479013, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.028315305709839, "global_step": 479014, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0074985027313232, "global_step": 479015, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0722274780273438, "global_step": 479016, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0044748783111572, "global_step": 479017, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0010924339294434, "global_step": 479018, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0341968536376953, "global_step": 479019, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.021723747253418, "global_step": 479020, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0850889682769775, "global_step": 479021, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0334110260009766, "global_step": 479022, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.030806541442871, "global_step": 479023, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0194644927978516, "global_step": 479024, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0767507553100586, "global_step": 479025, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.105649948120117, "global_step": 479026, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.164466381072998, "global_step": 479027, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1823408603668213, "global_step": 479028, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0360372066497803, "global_step": 479029, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.107848882675171, "global_step": 479030, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.024564266204834, "global_step": 479031, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0555801391601562, "global_step": 479032, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0257017612457275, "global_step": 479033, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.133608341217041, "global_step": 479034, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.069624662399292, "global_step": 479035, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0877525806427, "global_step": 479036, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.065983533859253, "global_step": 479037, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.018608570098877, "global_step": 479038, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.050346612930298, "global_step": 479039, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9829779863357544, "global_step": 479040, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.075740098953247, "global_step": 479041, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0557668209075928, "global_step": 479042, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.016206979751587, "global_step": 479043, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.090601682662964, "global_step": 479044, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.072803497314453, "global_step": 479045, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1079418659210205, "global_step": 479046, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.00577974319458, "global_step": 479047, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0618526935577393, "global_step": 479048, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1111814975738525, "global_step": 479049, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.055482864379883, "global_step": 479050, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.083482503890991, "global_step": 479051, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1571638584136963, "global_step": 479052, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.10733962059021, "global_step": 479053, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.051184892654419, "global_step": 479054, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0988292694091797, "global_step": 479055, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.034823417663574, "global_step": 479056, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1660501956939697, "global_step": 479057, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.057199239730835, "global_step": 479058, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.067244291305542, "global_step": 479059, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0904338359832764, "global_step": 479060, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9858638048171997, "global_step": 479061, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0381064414978027, "global_step": 479062, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0154764652252197, "global_step": 479063, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9779348373413086, "global_step": 479064, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.059605836868286, "global_step": 479065, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.106891632080078, "global_step": 479066, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0520057678222656, "global_step": 479067, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.016230821609497, "global_step": 479068, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0135581493377686, "global_step": 479069, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.022559881210327, "global_step": 479070, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1557743549346924, "global_step": 479071, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0468637943267822, "global_step": 479072, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.971144199371338, "global_step": 479073, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.097947835922241, "global_step": 479074, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9707648754119873, "global_step": 479075, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0040993690490723, "global_step": 479076, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0944983959198, "global_step": 479077, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0553760528564453, "global_step": 479078, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.117267608642578, "global_step": 479079, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0955417156219482, "global_step": 479080, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0406885147094727, "global_step": 479081, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1221511363983154, "global_step": 479082, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.060715675354004, "global_step": 479083, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0484390258789062, "global_step": 479084, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.09439754486084, "global_step": 479085, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9577654600143433, "global_step": 479086, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.195652961730957, "global_step": 479087, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.014716386795044, "global_step": 479088, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.184601068496704, "global_step": 479089, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0459673404693604, "global_step": 479090, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9469558000564575, "global_step": 479091, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9707920551300049, "global_step": 479092, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.15085768699646, "global_step": 479093, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.084212064743042, "global_step": 479094, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.053269863128662, "global_step": 479095, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.117960214614868, "global_step": 479096, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0856189727783203, "global_step": 479097, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.976989507675171, "global_step": 479098, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.029292583465576, "global_step": 479099, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0850749015808105, "global_step": 479100, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.074815034866333, "global_step": 479101, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.154503107070923, "global_step": 479102, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9606274366378784, "global_step": 479103, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.08548903465271, "global_step": 479104, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0340735912323, "global_step": 479105, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0856704711914062, "global_step": 479106, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0081820487976074, "global_step": 479107, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9753204584121704, "global_step": 479108, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0285587310791016, "global_step": 479109, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.019314765930176, "global_step": 479110, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.157989978790283, "global_step": 479111, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9958539009094238, "global_step": 479112, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.052873134613037, "global_step": 479113, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1452221870422363, "global_step": 479114, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0693678855895996, "global_step": 479115, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.030639171600342, "global_step": 479116, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.075077533721924, "global_step": 479117, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.07853102684021, "global_step": 479118, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1005077362060547, "global_step": 479119, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0443944931030273, "global_step": 479120, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9921810626983643, "global_step": 479121, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.033374309539795, "global_step": 479122, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.148003101348877, "global_step": 479123, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0141680240631104, "global_step": 479124, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0598514080047607, "global_step": 479125, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.023961305618286, "global_step": 479126, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9826388359069824, "global_step": 479127, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.046010732650757, "global_step": 479128, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.973253846168518, "global_step": 479129, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9662559032440186, "global_step": 479130, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.013028860092163, "global_step": 479131, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0320992469787598, "global_step": 479132, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0070202350616455, "global_step": 479133, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0759050846099854, "global_step": 479134, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1192784309387207, "global_step": 479135, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0499649047851562, "global_step": 479136, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.032870054244995, "global_step": 479137, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.036433458328247, "global_step": 479138, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.154043197631836, "global_step": 479139, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0412702560424805, "global_step": 479140, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0749449729919434, "global_step": 479141, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.066368579864502, "global_step": 479142, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0637154579162598, "global_step": 479143, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1040825843811035, "global_step": 479144, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.144169569015503, "global_step": 479145, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1525893211364746, "global_step": 479146, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.156445026397705, "global_step": 479147, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0074055194854736, "global_step": 479148, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.083488941192627, "global_step": 479149, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.031381130218506, "global_step": 479150, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1034576892852783, "global_step": 479151, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0367777347564697, "global_step": 479152, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9292237758636475, "global_step": 479153, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.036837577819824, "global_step": 479154, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9851477146148682, "global_step": 479155, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.041691780090332, "global_step": 479156, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0733225345611572, "global_step": 479157, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.091705322265625, "global_step": 479158, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0380637645721436, "global_step": 479159, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.088156223297119, "global_step": 479160, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1239519119262695, "global_step": 479161, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.145301342010498, "global_step": 479162, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.991148829460144, "global_step": 479163, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9938052892684937, "global_step": 479164, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0695905685424805, "global_step": 479165, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.086134672164917, "global_step": 479166, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1833655834198, "global_step": 479167, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0407726764678955, "global_step": 479168, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.075399160385132, "global_step": 479169, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0144333839416504, "global_step": 479170, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.063713312149048, "global_step": 479171, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0736684799194336, "global_step": 479172, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.076408863067627, "global_step": 479173, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.025122880935669, "global_step": 479174, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.984709620475769, "global_step": 479175, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0198497772216797, "global_step": 479176, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1185312271118164, "global_step": 479177, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.086718797683716, "global_step": 479178, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1095409393310547, "global_step": 479179, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1536028385162354, "global_step": 479180, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0243263244628906, "global_step": 479181, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.132800340652466, "global_step": 479182, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.018476724624634, "global_step": 479183, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9577161073684692, "global_step": 479184, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0588786602020264, "global_step": 479185, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.123004198074341, "global_step": 479186, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.058321475982666, "global_step": 479187, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1020333766937256, "global_step": 479188, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0946590900421143, "global_step": 479189, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.093385696411133, "global_step": 479190, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.141061782836914, "global_step": 479191, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.112632989883423, "global_step": 479192, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0978996753692627, "global_step": 479193, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0362613201141357, "global_step": 479194, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0135035514831543, "global_step": 479195, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.052456855773926, "global_step": 479196, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0858163833618164, "global_step": 479197, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0321836471557617, "global_step": 479198, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.076540231704712, "global_step": 479199, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0707502365112305, "global_step": 479200, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.090264320373535, "global_step": 479201, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.019521951675415, "global_step": 479202, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.026155471801758, "global_step": 479203, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9376554489135742, "global_step": 479204, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0825419425964355, "global_step": 479205, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0710372924804688, "global_step": 479206, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0698940753936768, "global_step": 479207, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0214316844940186, "global_step": 479208, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0393190383911133, "global_step": 479209, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.080101251602173, "global_step": 479210, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9525842666625977, "global_step": 479211, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0570359230041504, "global_step": 479212, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0410218238830566, "global_step": 479213, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.009220838546753, "global_step": 479214, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.10605525970459, "global_step": 479215, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.057069778442383, "global_step": 479216, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.105353832244873, "global_step": 479217, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0112857818603516, "global_step": 479218, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0408196449279785, "global_step": 479219, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.058760404586792, "global_step": 479220, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1543753147125244, "global_step": 479221, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.031804084777832, "global_step": 479222, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0615170001983643, "global_step": 479223, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1197824478149414, "global_step": 479224, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1015169620513916, "global_step": 479225, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.032831907272339, "global_step": 479226, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0933024883270264, "global_step": 479227, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0268359184265137, "global_step": 479228, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0899429321289062, "global_step": 479229, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9902271032333374, "global_step": 479230, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0235755443573, "global_step": 479231, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0582032203674316, "global_step": 479232, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.034830331802368, "global_step": 479233, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0469136238098145, "global_step": 479234, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1351497173309326, "global_step": 479235, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1483566761016846, "global_step": 479236, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1067302227020264, "global_step": 479237, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.042372465133667, "global_step": 479238, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0778887271881104, "global_step": 479239, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.066042900085449, "global_step": 479240, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0306782722473145, "global_step": 479241, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.061858892440796, "global_step": 479242, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.001347541809082, "global_step": 479243, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0039315223693848, "global_step": 479244, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.991853952407837, "global_step": 479245, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0576553344726562, "global_step": 479246, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9998319149017334, "global_step": 479247, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.989819049835205, "global_step": 479248, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1113884449005127, "global_step": 479249, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9638906717300415, "global_step": 479250, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0443222522735596, "global_step": 479251, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.093575954437256, "global_step": 479252, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0496888160705566, "global_step": 479253, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9961448907852173, "global_step": 479254, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9313722848892212, "global_step": 479255, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0852839946746826, "global_step": 479256, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.992169976234436, "global_step": 479257, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.052194118499756, "global_step": 479258, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0390076637268066, "global_step": 479259, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0401880741119385, "global_step": 479260, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0331623554229736, "global_step": 479261, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1146934032440186, "global_step": 479262, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9586657285690308, "global_step": 479263, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9995193481445312, "global_step": 479264, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.091996669769287, "global_step": 479265, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9928301572799683, "global_step": 479266, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.013927459716797, "global_step": 479267, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1314680576324463, "global_step": 479268, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0524306297302246, "global_step": 479269, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.013517141342163, "global_step": 479270, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1070144176483154, "global_step": 479271, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0006253719329834, "global_step": 479272, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0925371646881104, "global_step": 479273, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0120372772216797, "global_step": 479274, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.139472246170044, "global_step": 479275, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.013427495956421, "global_step": 479276, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1042897701263428, "global_step": 479277, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0330135822296143, "global_step": 479278, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0921099185943604, "global_step": 479279, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.10298752784729, "global_step": 479280, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.019690990447998, "global_step": 479281, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1594579219818115, "global_step": 479282, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1408162117004395, "global_step": 479283, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.079306125640869, "global_step": 479284, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9962310791015625, "global_step": 479285, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.035104274749756, "global_step": 479286, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0238959789276123, "global_step": 479287, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.130704641342163, "global_step": 479288, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0170605182647705, "global_step": 479289, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1062047481536865, "global_step": 479290, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0340702533721924, "global_step": 479291, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0603697299957275, "global_step": 479292, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0572197437286377, "global_step": 479293, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.041813850402832, "global_step": 479294, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.027191162109375, "global_step": 479295, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1097452640533447, "global_step": 479296, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0111143589019775, "global_step": 479297, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0081591606140137, "global_step": 479298, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.098762035369873, "global_step": 479299, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0837442874908447, "global_step": 479300, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9194897413253784, "global_step": 479301, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0465915203094482, "global_step": 479302, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0916554927825928, "global_step": 479303, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0456461906433105, "global_step": 479304, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.116636037826538, "global_step": 479305, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.962792158126831, "global_step": 479306, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0091943740844727, "global_step": 479307, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.128798484802246, "global_step": 479308, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0145771503448486, "global_step": 479309, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1304118633270264, "global_step": 479310, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0454225540161133, "global_step": 479311, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0978057384490967, "global_step": 479312, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0138442516326904, "global_step": 479313, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0394222736358643, "global_step": 479314, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9974769353866577, "global_step": 479315, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1600887775421143, "global_step": 479316, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9989012479782104, "global_step": 479317, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1411328315734863, "global_step": 479318, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1356277465820312, "global_step": 479319, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0117204189300537, "global_step": 479320, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1325228214263916, "global_step": 479321, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0510752201080322, "global_step": 479322, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.094992160797119, "global_step": 479323, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.096498727798462, "global_step": 479324, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0664992332458496, "global_step": 479325, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.018728494644165, "global_step": 479326, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.096785306930542, "global_step": 479327, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.082695245742798, "global_step": 479328, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.042628526687622, "global_step": 479329, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1155896186828613, "global_step": 479330, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0490779876708984, "global_step": 479331, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0474915504455566, "global_step": 479332, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9843591451644897, "global_step": 479333, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.138805866241455, "global_step": 479334, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0819923877716064, "global_step": 479335, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0848259925842285, "global_step": 479336, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0744588375091553, "global_step": 479337, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.07867693901062, "global_step": 479338, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9728447198867798, "global_step": 479339, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.005190849304199, "global_step": 479340, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.093662738800049, "global_step": 479341, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.114138126373291, "global_step": 479342, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.06527042388916, "global_step": 479343, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.017442464828491, "global_step": 479344, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.057354688644409, "global_step": 479345, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0512983798980713, "global_step": 479346, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.986698865890503, "global_step": 479347, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0118374824523926, "global_step": 479348, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.026716947555542, "global_step": 479349, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0987389087677, "global_step": 479350, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9994076490402222, "global_step": 479351, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0652332305908203, "global_step": 479352, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0414297580718994, "global_step": 479353, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0800094604492188, "global_step": 479354, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.086284637451172, "global_step": 479355, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0155041217803955, "global_step": 479356, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.032771110534668, "global_step": 479357, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1988253593444824, "global_step": 479358, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.090930700302124, "global_step": 479359, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0453248023986816, "global_step": 479360, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9668641090393066, "global_step": 479361, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.05474853515625, "global_step": 479362, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1335854530334473, "global_step": 479363, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.039997100830078, "global_step": 479364, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0966954231262207, "global_step": 479365, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.059645414352417, "global_step": 479366, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.057560682296753, "global_step": 479367, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0602493286132812, "global_step": 479368, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0636096000671387, "global_step": 479369, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.028956890106201, "global_step": 479370, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.096344470977783, "global_step": 479371, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.143007755279541, "global_step": 479372, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.012204170227051, "global_step": 479373, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0589241981506348, "global_step": 479374, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.082775354385376, "global_step": 479375, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.040274143218994, "global_step": 479376, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.051136016845703, "global_step": 479377, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9762190580368042, "global_step": 479378, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1082329750061035, "global_step": 479379, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1012589931488037, "global_step": 479380, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.056137800216675, "global_step": 479381, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0761618614196777, "global_step": 479382, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.099321126937866, "global_step": 479383, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.033888101577759, "global_step": 479384, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0917487144470215, "global_step": 479385, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9727922677993774, "global_step": 479386, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.096224069595337, "global_step": 479387, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0418100357055664, "global_step": 479388, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0885488986968994, "global_step": 479389, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0408384799957275, "global_step": 479390, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0911362171173096, "global_step": 479391, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.046015977859497, "global_step": 479392, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1190130710601807, "global_step": 479393, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.016144037246704, "global_step": 479394, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0637779235839844, "global_step": 479395, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0233240127563477, "global_step": 479396, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.092957019805908, "global_step": 479397, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0205328464508057, "global_step": 479398, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1057591438293457, "global_step": 479399, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.186889410018921, "global_step": 479400, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0370798110961914, "global_step": 479401, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0955557823181152, "global_step": 479402, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0382797718048096, "global_step": 479403, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0256495475769043, "global_step": 479404, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9231425523757935, "global_step": 479405, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9803030490875244, "global_step": 479406, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1203010082244873, "global_step": 479407, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0235114097595215, "global_step": 479408, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0583248138427734, "global_step": 479409, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.022726535797119, "global_step": 479410, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.05659818649292, "global_step": 479411, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0796430110931396, "global_step": 479412, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1329450607299805, "global_step": 479413, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0700929164886475, "global_step": 479414, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0713655948638916, "global_step": 479415, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9925531148910522, "global_step": 479416, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0868706703186035, "global_step": 479417, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0934746265411377, "global_step": 479418, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1080281734466553, "global_step": 479419, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1006360054016113, "global_step": 479420, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0873966217041016, "global_step": 479421, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0836706161499023, "global_step": 479422, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0093140602111816, "global_step": 479423, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.050633668899536, "global_step": 479424, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0980751514434814, "global_step": 479425, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.127166271209717, "global_step": 479426, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.123760461807251, "global_step": 479427, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0964231491088867, "global_step": 479428, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0116567611694336, "global_step": 479429, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9531556367874146, "global_step": 479430, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.106980085372925, "global_step": 479431, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.101071357727051, "global_step": 479432, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.05120587348938, "global_step": 479433, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.028656005859375, "global_step": 479434, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0445454120635986, "global_step": 479435, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.102118492126465, "global_step": 479436, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.039313316345215, "global_step": 479437, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.038450002670288, "global_step": 479438, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9734302759170532, "global_step": 479439, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0437090396881104, "global_step": 479440, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.041346549987793, "global_step": 479441, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0661771297454834, "global_step": 479442, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0984160900115967, "global_step": 479443, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1714675426483154, "global_step": 479444, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0707578659057617, "global_step": 479445, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.121243715286255, "global_step": 479446, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.094543218612671, "global_step": 479447, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.157708168029785, "global_step": 479448, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0597434043884277, "global_step": 479449, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0818397998809814, "global_step": 479450, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9919519424438477, "global_step": 479451, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.086003541946411, "global_step": 479452, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0662624835968018, "global_step": 479453, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9936717748641968, "global_step": 479454, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0024428367614746, "global_step": 479455, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0408360958099365, "global_step": 479456, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0915369987487793, "global_step": 479457, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0156784057617188, "global_step": 479458, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9195200204849243, "global_step": 479459, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0139718055725098, "global_step": 479460, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0892322063446045, "global_step": 479461, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.103957176208496, "global_step": 479462, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0549440383911133, "global_step": 479463, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.12924861907959, "global_step": 479464, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0859172344207764, "global_step": 479465, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.064143657684326, "global_step": 479466, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.082270860671997, "global_step": 479467, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.05735445022583, "global_step": 479468, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.001965045928955, "global_step": 479469, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0962255001068115, "global_step": 479470, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0551393032073975, "global_step": 479471, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1545376777648926, "global_step": 479472, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0671212673187256, "global_step": 479473, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0790774822235107, "global_step": 479474, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0600640773773193, "global_step": 479475, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0922319889068604, "global_step": 479476, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0712592601776123, "global_step": 479477, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.056853771209717, "global_step": 479478, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.091437816619873, "global_step": 479479, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1239678859710693, "global_step": 479480, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.075807809829712, "global_step": 479481, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0404233932495117, "global_step": 479482, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0667495727539062, "global_step": 479483, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0493433475494385, "global_step": 479484, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0570812225341797, "global_step": 479485, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9230403900146484, "global_step": 479486, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0246167182922363, "global_step": 479487, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.06462025642395, "global_step": 479488, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0638887882232666, "global_step": 479489, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9701104164123535, "global_step": 479490, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0545079708099365, "global_step": 479491, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.01560115814209, "global_step": 479492, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.061694622039795, "global_step": 479493, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.055131196975708, "global_step": 479494, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.049246072769165, "global_step": 479495, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0853805541992188, "global_step": 479496, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.078416585922241, "global_step": 479497, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.084075450897217, "global_step": 479498, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.122631788253784, "global_step": 479499, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1284661293029785, "global_step": 479500, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.103456497192383, "global_step": 479501, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.070441246032715, "global_step": 479502, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0916385650634766, "global_step": 479503, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1030266284942627, "global_step": 479504, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1054325103759766, "global_step": 479505, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.009969711303711, "global_step": 479506, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0572686195373535, "global_step": 479507, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0225040912628174, "global_step": 479508, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.03466534614563, "global_step": 479509, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0545883178710938, "global_step": 479510, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.11086368560791, "global_step": 479511, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1056482791900635, "global_step": 479512, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.021385669708252, "global_step": 479513, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.037769317626953, "global_step": 479514, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0300240516662598, "global_step": 479515, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0756912231445312, "global_step": 479516, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9973689317703247, "global_step": 479517, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.116915702819824, "global_step": 479518, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1514081954956055, "global_step": 479519, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1273882389068604, "global_step": 479520, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.087150812149048, "global_step": 479521, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.087557077407837, "global_step": 479522, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1222314834594727, "global_step": 479523, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0968313217163086, "global_step": 479524, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0134165287017822, "global_step": 479525, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0253889560699463, "global_step": 479526, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0404067039489746, "global_step": 479527, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1715407371520996, "global_step": 479528, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.055652379989624, "global_step": 479529, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0202620029449463, "global_step": 479530, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9696550369262695, "global_step": 479531, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0689330101013184, "global_step": 479532, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9913917779922485, "global_step": 479533, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0763607025146484, "global_step": 479534, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0424723625183105, "global_step": 479535, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.060685396194458, "global_step": 479536, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.079742670059204, "global_step": 479537, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.09834885597229, "global_step": 479538, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.068376064300537, "global_step": 479539, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.003018617630005, "global_step": 479540, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1655638217926025, "global_step": 479541, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1353843212127686, "global_step": 479542, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0977368354797363, "global_step": 479543, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0647430419921875, "global_step": 479544, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.094708204269409, "global_step": 479545, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.106854200363159, "global_step": 479546, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.036642551422119, "global_step": 479547, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.093233585357666, "global_step": 479548, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.972399353981018, "global_step": 479549, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0296223163604736, "global_step": 479550, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.051990270614624, "global_step": 479551, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.970698595046997, "global_step": 479552, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0923728942871094, "global_step": 479553, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0375678539276123, "global_step": 479554, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0465309619903564, "global_step": 479555, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.071723222732544, "global_step": 479556, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0384292602539062, "global_step": 479557, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0632941722869873, "global_step": 479558, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.091850996017456, "global_step": 479559, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.041703701019287, "global_step": 479560, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0496959686279297, "global_step": 479561, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1051948070526123, "global_step": 479562, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0448222160339355, "global_step": 479563, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1144063472747803, "global_step": 479564, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1076931953430176, "global_step": 479565, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0401296615600586, "global_step": 479566, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0374104976654053, "global_step": 479567, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0240883827209473, "global_step": 479568, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0393857955932617, "global_step": 479569, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.074167251586914, "global_step": 479570, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.085395336151123, "global_step": 479571, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.088958978652954, "global_step": 479572, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0902528762817383, "global_step": 479573, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.043178081512451, "global_step": 479574, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0821688175201416, "global_step": 479575, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.014322519302368, "global_step": 479576, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0363566875457764, "global_step": 479577, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.049807071685791, "global_step": 479578, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0558619499206543, "global_step": 479579, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.064643144607544, "global_step": 479580, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1027534008026123, "global_step": 479581, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0734641551971436, "global_step": 479582, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0356252193450928, "global_step": 479583, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.067513942718506, "global_step": 479584, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0657589435577393, "global_step": 479585, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1307356357574463, "global_step": 479586, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1245150566101074, "global_step": 479587, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0676286220550537, "global_step": 479588, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0325732231140137, "global_step": 479589, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.05513334274292, "global_step": 479590, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0998878479003906, "global_step": 479591, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0182414054870605, "global_step": 479592, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0762264728546143, "global_step": 479593, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0322277545928955, "global_step": 479594, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0925683975219727, "global_step": 479595, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.101125478744507, "global_step": 479596, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0230746269226074, "global_step": 479597, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9926236867904663, "global_step": 479598, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0552945137023926, "global_step": 479599, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.990759253501892, "global_step": 479600, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0162947177886963, "global_step": 479601, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.091912031173706, "global_step": 479602, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0075409412384033, "global_step": 479603, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.129143238067627, "global_step": 479604, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0590014457702637, "global_step": 479605, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9555233716964722, "global_step": 479606, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0271618366241455, "global_step": 479607, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9741621017456055, "global_step": 479608, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1215600967407227, "global_step": 479609, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0919928550720215, "global_step": 479610, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0495543479919434, "global_step": 479611, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0991647243499756, "global_step": 479612, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0133297443389893, "global_step": 479613, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0568299293518066, "global_step": 479614, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.057335138320923, "global_step": 479615, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.097862482070923, "global_step": 479616, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0983760356903076, "global_step": 479617, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0652477741241455, "global_step": 479618, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1058437824249268, "global_step": 479619, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1422860622406006, "global_step": 479620, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.082615375518799, "global_step": 479621, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0816314220428467, "global_step": 479622, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.2052619457244873, "global_step": 479623, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.120361328125, "global_step": 479624, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0429201126098633, "global_step": 479625, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.039898157119751, "global_step": 479626, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.072810411453247, "global_step": 479627, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0802507400512695, "global_step": 479628, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.121861696243286, "global_step": 479629, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1852338314056396, "global_step": 479630, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0630457401275635, "global_step": 479631, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9853464365005493, "global_step": 479632, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.075613498687744, "global_step": 479633, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9529738426208496, "global_step": 479634, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.044067859649658, "global_step": 479635, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9519813060760498, "global_step": 479636, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0921671390533447, "global_step": 479637, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1517374515533447, "global_step": 479638, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.128805637359619, "global_step": 479639, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0868446826934814, "global_step": 479640, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0848746299743652, "global_step": 479641, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0859029293060303, "global_step": 479642, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.04581880569458, "global_step": 479643, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0441434383392334, "global_step": 479644, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.045426845550537, "global_step": 479645, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.066798448562622, "global_step": 479646, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.117004871368408, "global_step": 479647, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.101221799850464, "global_step": 479648, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.108306407928467, "global_step": 479649, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.038733720779419, "global_step": 479650, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0824201107025146, "global_step": 479651, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.038867473602295, "global_step": 479652, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0421102046966553, "global_step": 479653, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0919029712677, "global_step": 479654, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.117598533630371, "global_step": 479655, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9949166774749756, "global_step": 479656, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1178035736083984, "global_step": 479657, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.062791585922241, "global_step": 479658, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.089446544647217, "global_step": 479659, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.066347599029541, "global_step": 479660, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0028960704803467, "global_step": 479661, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.061182737350464, "global_step": 479662, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1355769634246826, "global_step": 479663, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.998610019683838, "global_step": 479664, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0562307834625244, "global_step": 479665, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.06233286857605, "global_step": 479666, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0431606769561768, "global_step": 479667, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.010794162750244, "global_step": 479668, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.058194875717163, "global_step": 479669, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1059021949768066, "global_step": 479670, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0967605113983154, "global_step": 479671, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0882203578948975, "global_step": 479672, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0721750259399414, "global_step": 479673, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.076389789581299, "global_step": 479674, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0592470169067383, "global_step": 479675, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0630195140838623, "global_step": 479676, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1195666790008545, "global_step": 479677, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.057007074356079, "global_step": 479678, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0822532176971436, "global_step": 479679, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1575934886932373, "global_step": 479680, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.035351514816284, "global_step": 479681, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0492236614227295, "global_step": 479682, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0284111499786377, "global_step": 479683, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.089040756225586, "global_step": 479684, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0636887550354004, "global_step": 479685, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.069632053375244, "global_step": 479686, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0815823078155518, "global_step": 479687, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0665087699890137, "global_step": 479688, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0740387439727783, "global_step": 479689, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0314478874206543, "global_step": 479690, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0454952716827393, "global_step": 479691, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.035022735595703, "global_step": 479692, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.98485267162323, "global_step": 479693, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0719153881073, "global_step": 479694, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0812666416168213, "global_step": 479695, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1247663497924805, "global_step": 479696, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0780508518218994, "global_step": 479697, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.013793468475342, "global_step": 479698, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.116055965423584, "global_step": 479699, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.067045211791992, "global_step": 479700, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9655259847640991, "global_step": 479701, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.080718517303467, "global_step": 479702, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0403451919555664, "global_step": 479703, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.093757152557373, "global_step": 479704, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.045103073120117, "global_step": 479705, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0021677017211914, "global_step": 479706, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.06589674949646, "global_step": 479707, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.094141960144043, "global_step": 479708, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0458884239196777, "global_step": 479709, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.990496277809143, "global_step": 479710, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0818819999694824, "global_step": 479711, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0448555946350098, "global_step": 479712, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.044018507003784, "global_step": 479713, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0965311527252197, "global_step": 479714, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.064594268798828, "global_step": 479715, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.10270094871521, "global_step": 479716, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0290486812591553, "global_step": 479717, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.108638048171997, "global_step": 479718, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.95980966091156, "global_step": 479719, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.017346143722534, "global_step": 479720, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.030308485031128, "global_step": 479721, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.106931686401367, "global_step": 479722, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0915513038635254, "global_step": 479723, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.000523805618286, "global_step": 479724, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0390141010284424, "global_step": 479725, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.00392484664917, "global_step": 479726, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1142454147338867, "global_step": 479727, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0596282482147217, "global_step": 479728, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0586509704589844, "global_step": 479729, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0400912761688232, "global_step": 479730, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.100464344024658, "global_step": 479731, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9381694793701172, "global_step": 479732, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1018097400665283, "global_step": 479733, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0649428367614746, "global_step": 479734, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0305850505828857, "global_step": 479735, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0905256271362305, "global_step": 479736, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.117176055908203, "global_step": 479737, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0812649726867676, "global_step": 479738, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1250064373016357, "global_step": 479739, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.108457088470459, "global_step": 479740, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.112196445465088, "global_step": 479741, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.076143503189087, "global_step": 479742, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9935591220855713, "global_step": 479743, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.107313871383667, "global_step": 479744, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0489461421966553, "global_step": 479745, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.077284574508667, "global_step": 479746, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0186927318573, "global_step": 479747, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.163459539413452, "global_step": 479748, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0282626152038574, "global_step": 479749, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0584826469421387, "global_step": 479750, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.015928030014038, "global_step": 479751, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.107365369796753, "global_step": 479752, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1561331748962402, "global_step": 479753, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.041659116744995, "global_step": 479754, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.077242374420166, "global_step": 479755, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.015897274017334, "global_step": 479756, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1115150451660156, "global_step": 479757, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.028750419616699, "global_step": 479758, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.056882619857788, "global_step": 479759, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.022522449493408, "global_step": 479760, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0795018672943115, "global_step": 479761, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1208531856536865, "global_step": 479762, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.052614688873291, "global_step": 479763, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0992932319641113, "global_step": 479764, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.122013807296753, "global_step": 479765, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.106003999710083, "global_step": 479766, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0082638263702393, "global_step": 479767, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.047365427017212, "global_step": 479768, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0920064449310303, "global_step": 479769, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0031378269195557, "global_step": 479770, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.034834146499634, "global_step": 479771, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.1418824195861816, "global_step": 479772, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0576820373535156, "global_step": 479773, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0655899047851562, "global_step": 479774, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9657602310180664, "global_step": 479775, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0701498985290527, "global_step": 479776, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.070652723312378, "global_step": 479777, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0887985229492188, "global_step": 479778, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0724809169769287, "global_step": 479779, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.143998861312866, "global_step": 479780, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.056661605834961, "global_step": 479781, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0843489170074463, "global_step": 479782, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9893839359283447, "global_step": 479783, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0744552612304688, "global_step": 479784, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.067873477935791, "global_step": 479785, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.02681827545166, "global_step": 479786, "epoch": 844, "lr": 5e-05}
{"train_loss": 2.0591156482696533, "global_step": 479787, "epoch": 844, "lr": 5e-05}
{"train_loss": 1.9986871480941772, "global_step": 479788, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0966386795043945, "global_step": 479789, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0215003490448, "global_step": 479790, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.102224111557007, "global_step": 479791, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0962440967559814, "global_step": 479792, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.140472412109375, "global_step": 479793, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.147473096847534, "global_step": 479794, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.071007013320923, "global_step": 479795, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.064926862716675, "global_step": 479796, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0153791904449463, "global_step": 479797, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1172008514404297, "global_step": 479798, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0435473918914795, "global_step": 479799, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.050814628601074, "global_step": 479800, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.031355857849121, "global_step": 479801, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0967483520507812, "global_step": 479802, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0478055477142334, "global_step": 479803, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.038787364959717, "global_step": 479804, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0772905349731445, "global_step": 479805, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0926830768585205, "global_step": 479806, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.011401414871216, "global_step": 479807, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9708081483840942, "global_step": 479808, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.079590082168579, "global_step": 479809, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0464248657226562, "global_step": 479810, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0836970806121826, "global_step": 479811, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.040297508239746, "global_step": 479812, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0822372436523438, "global_step": 479813, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0235183238983154, "global_step": 479814, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0002353191375732, "global_step": 479815, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.101893424987793, "global_step": 479816, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9668703079223633, "global_step": 479817, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0701792240142822, "global_step": 479818, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0980217456817627, "global_step": 479819, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1574201583862305, "global_step": 479820, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.064408302307129, "global_step": 479821, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9640756845474243, "global_step": 479822, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0871541500091553, "global_step": 479823, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.142141819000244, "global_step": 479824, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0768489837646484, "global_step": 479825, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0311331748962402, "global_step": 479826, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.102468490600586, "global_step": 479827, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0626351833343506, "global_step": 479828, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.977676510810852, "global_step": 479829, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9965661764144897, "global_step": 479830, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.134697198867798, "global_step": 479831, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9555083513259888, "global_step": 479832, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9881906509399414, "global_step": 479833, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9670088291168213, "global_step": 479834, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.092413902282715, "global_step": 479835, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0211987495422363, "global_step": 479836, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0361485481262207, "global_step": 479837, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0245752334594727, "global_step": 479838, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9940850734710693, "global_step": 479839, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.094322681427002, "global_step": 479840, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.012098789215088, "global_step": 479841, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0301284790039062, "global_step": 479842, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.001171350479126, "global_step": 479843, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.103883981704712, "global_step": 479844, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.97727632522583, "global_step": 479845, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.972075343132019, "global_step": 479846, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0858709812164307, "global_step": 479847, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1225078105926514, "global_step": 479848, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.114287853240967, "global_step": 479849, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9813882112503052, "global_step": 479850, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.084374189376831, "global_step": 479851, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.061563730239868, "global_step": 479852, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0321807861328125, "global_step": 479853, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.082573175430298, "global_step": 479854, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0028233528137207, "global_step": 479855, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.996508002281189, "global_step": 479856, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9790512323379517, "global_step": 479857, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0093536376953125, "global_step": 479858, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.043576955795288, "global_step": 479859, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0413224697113037, "global_step": 479860, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9362365007400513, "global_step": 479861, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.037630319595337, "global_step": 479862, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9817970991134644, "global_step": 479863, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0132853984832764, "global_step": 479864, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.063519239425659, "global_step": 479865, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0866143703460693, "global_step": 479866, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0731399059295654, "global_step": 479867, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0613508224487305, "global_step": 479868, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0401039123535156, "global_step": 479869, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.045356035232544, "global_step": 479870, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.113361358642578, "global_step": 479871, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.965083360671997, "global_step": 479872, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0219295024871826, "global_step": 479873, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0145864486694336, "global_step": 479874, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.047935724258423, "global_step": 479875, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.022251605987549, "global_step": 479876, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0855319499969482, "global_step": 479877, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0713913440704346, "global_step": 479878, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9438400268554688, "global_step": 479879, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0819895267486572, "global_step": 479880, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9741874933242798, "global_step": 479881, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0662143230438232, "global_step": 479882, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9910608530044556, "global_step": 479883, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9949119091033936, "global_step": 479884, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1087214946746826, "global_step": 479885, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0414440631866455, "global_step": 479886, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.032829523086548, "global_step": 479887, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0066494941711426, "global_step": 479888, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0191712379455566, "global_step": 479889, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9714868068695068, "global_step": 479890, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0161352157592773, "global_step": 479891, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9912564754486084, "global_step": 479892, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.041778802871704, "global_step": 479893, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0731801986694336, "global_step": 479894, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.062408924102783, "global_step": 479895, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0238873958587646, "global_step": 479896, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.018460988998413, "global_step": 479897, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.055954933166504, "global_step": 479898, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.01991868019104, "global_step": 479899, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0126914978027344, "global_step": 479900, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0383925437927246, "global_step": 479901, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.060901165008545, "global_step": 479902, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0315139293670654, "global_step": 479903, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0330810546875, "global_step": 479904, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0851330757141113, "global_step": 479905, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0430397987365723, "global_step": 479906, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.000462293624878, "global_step": 479907, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1077425479888916, "global_step": 479908, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9806780815124512, "global_step": 479909, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.070162534713745, "global_step": 479910, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0539348125457764, "global_step": 479911, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0540404319763184, "global_step": 479912, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.032301664352417, "global_step": 479913, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.125579357147217, "global_step": 479914, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9806009531021118, "global_step": 479915, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9844489097595215, "global_step": 479916, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9491382837295532, "global_step": 479917, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.044039726257324, "global_step": 479918, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.117060661315918, "global_step": 479919, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0936782360076904, "global_step": 479920, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9751888513565063, "global_step": 479921, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.115852117538452, "global_step": 479922, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1033778190612793, "global_step": 479923, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.071669340133667, "global_step": 479924, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1326494216918945, "global_step": 479925, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.087123394012451, "global_step": 479926, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1546027660369873, "global_step": 479927, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.033737897872925, "global_step": 479928, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.055769443511963, "global_step": 479929, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.075714349746704, "global_step": 479930, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0439906120300293, "global_step": 479931, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9827862977981567, "global_step": 479932, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0029191970825195, "global_step": 479933, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.026017189025879, "global_step": 479934, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.05969500541687, "global_step": 479935, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0806310176849365, "global_step": 479936, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.128718376159668, "global_step": 479937, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0542874336242676, "global_step": 479938, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0610947608947754, "global_step": 479939, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.047736167907715, "global_step": 479940, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0772013664245605, "global_step": 479941, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0091209411621094, "global_step": 479942, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.056953191757202, "global_step": 479943, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.114158868789673, "global_step": 479944, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1148765087127686, "global_step": 479945, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0403084754943848, "global_step": 479946, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0176620483398438, "global_step": 479947, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0575108528137207, "global_step": 479948, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9930877685546875, "global_step": 479949, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9503813982009888, "global_step": 479950, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1316356658935547, "global_step": 479951, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0910804271698, "global_step": 479952, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0782856941223145, "global_step": 479953, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0819568634033203, "global_step": 479954, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.03583025932312, "global_step": 479955, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0323266983032227, "global_step": 479956, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9762476682662964, "global_step": 479957, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0550341606140137, "global_step": 479958, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.099348545074463, "global_step": 479959, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.082336187362671, "global_step": 479960, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9765605926513672, "global_step": 479961, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1245176792144775, "global_step": 479962, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0880115032196045, "global_step": 479963, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9887712001800537, "global_step": 479964, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0063679218292236, "global_step": 479965, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0397727489471436, "global_step": 479966, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.014582872390747, "global_step": 479967, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0654616355895996, "global_step": 479968, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0787601470947266, "global_step": 479969, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.058532953262329, "global_step": 479970, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.056948661804199, "global_step": 479971, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0018365383148193, "global_step": 479972, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.017333984375, "global_step": 479973, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0595927238464355, "global_step": 479974, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0476725101470947, "global_step": 479975, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.046675205230713, "global_step": 479976, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.09773588180542, "global_step": 479977, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.04331636428833, "global_step": 479978, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.105098247528076, "global_step": 479979, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9635436534881592, "global_step": 479980, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.006774663925171, "global_step": 479981, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.103870153427124, "global_step": 479982, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.104729652404785, "global_step": 479983, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9920620918273926, "global_step": 479984, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0362770557403564, "global_step": 479985, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9914143085479736, "global_step": 479986, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.01835298538208, "global_step": 479987, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1355366706848145, "global_step": 479988, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9715040922164917, "global_step": 479989, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0524511337280273, "global_step": 479990, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0795769691467285, "global_step": 479991, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1078786849975586, "global_step": 479992, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.056462526321411, "global_step": 479993, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.077810525894165, "global_step": 479994, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.092808723449707, "global_step": 479995, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.118540048599243, "global_step": 479996, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9920824766159058, "global_step": 479997, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.108952522277832, "global_step": 479998, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1044375896453857, "global_step": 479999, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0590085983276367, "global_step": 480000, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.021592617034912, "global_step": 480001, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.078929901123047, "global_step": 480002, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.090494394302368, "global_step": 480003, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0197935104370117, "global_step": 480004, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0402464866638184, "global_step": 480005, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9998681545257568, "global_step": 480006, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.051889657974243, "global_step": 480007, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0624194145202637, "global_step": 480008, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.024420738220215, "global_step": 480009, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.01225209236145, "global_step": 480010, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1268186569213867, "global_step": 480011, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0354092121124268, "global_step": 480012, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.125523090362549, "global_step": 480013, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0709755420684814, "global_step": 480014, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9951388835906982, "global_step": 480015, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0900983810424805, "global_step": 480016, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0902628898620605, "global_step": 480017, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9934723377227783, "global_step": 480018, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0807695388793945, "global_step": 480019, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.136122941970825, "global_step": 480020, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.048955202102661, "global_step": 480021, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.122009754180908, "global_step": 480022, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.071706771850586, "global_step": 480023, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.026034116744995, "global_step": 480024, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0763964653015137, "global_step": 480025, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0275111198425293, "global_step": 480026, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0566906929016113, "global_step": 480027, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9889525175094604, "global_step": 480028, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0916213989257812, "global_step": 480029, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1265316009521484, "global_step": 480030, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.099947452545166, "global_step": 480031, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1263070106506348, "global_step": 480032, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.020235300064087, "global_step": 480033, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9919644594192505, "global_step": 480034, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0358428955078125, "global_step": 480035, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0521183013916016, "global_step": 480036, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0533089637756348, "global_step": 480037, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.01143741607666, "global_step": 480038, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0196542739868164, "global_step": 480039, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0628488063812256, "global_step": 480040, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.025245428085327, "global_step": 480041, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.056516647338867, "global_step": 480042, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0557868480682373, "global_step": 480043, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0396320819854736, "global_step": 480044, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0391151905059814, "global_step": 480045, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1201107501983643, "global_step": 480046, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.029249429702759, "global_step": 480047, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.015932083129883, "global_step": 480048, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.014275550842285, "global_step": 480049, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0439679622650146, "global_step": 480050, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1051435470581055, "global_step": 480051, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0216195583343506, "global_step": 480052, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.14355206489563, "global_step": 480053, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0962986946105957, "global_step": 480054, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.026151418685913, "global_step": 480055, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0559158325195312, "global_step": 480056, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0721540451049805, "global_step": 480057, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0874056816101074, "global_step": 480058, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.960880160331726, "global_step": 480059, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.021031141281128, "global_step": 480060, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0380005836486816, "global_step": 480061, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9641706943511963, "global_step": 480062, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0221855640411377, "global_step": 480063, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0424530506134033, "global_step": 480064, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.085433006286621, "global_step": 480065, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0219249725341797, "global_step": 480066, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.020596742630005, "global_step": 480067, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.069575548171997, "global_step": 480068, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0536892414093018, "global_step": 480069, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.013395309448242, "global_step": 480070, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.023122787475586, "global_step": 480071, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0547566413879395, "global_step": 480072, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.034870147705078, "global_step": 480073, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0090742111206055, "global_step": 480074, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.068702220916748, "global_step": 480075, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0393941402435303, "global_step": 480076, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1322896480560303, "global_step": 480077, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0522141456604004, "global_step": 480078, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0624706745147705, "global_step": 480079, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0614547729492188, "global_step": 480080, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1257877349853516, "global_step": 480081, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0322346687316895, "global_step": 480082, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0646719932556152, "global_step": 480083, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0557315349578857, "global_step": 480084, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0740468502044678, "global_step": 480085, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.102473497390747, "global_step": 480086, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0678184032440186, "global_step": 480087, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1112451553344727, "global_step": 480088, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0337185859680176, "global_step": 480089, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.072355031967163, "global_step": 480090, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0372676849365234, "global_step": 480091, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0518641471862793, "global_step": 480092, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.101703643798828, "global_step": 480093, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0892348289489746, "global_step": 480094, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0203521251678467, "global_step": 480095, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9981625080108643, "global_step": 480096, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0658109188079834, "global_step": 480097, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9947447776794434, "global_step": 480098, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.092442750930786, "global_step": 480099, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.116718292236328, "global_step": 480100, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.098005533218384, "global_step": 480101, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0789101123809814, "global_step": 480102, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.057234525680542, "global_step": 480103, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.010753631591797, "global_step": 480104, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0861093997955322, "global_step": 480105, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1085424423217773, "global_step": 480106, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9690749645233154, "global_step": 480107, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0681769847869873, "global_step": 480108, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0659611225128174, "global_step": 480109, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0674197673797607, "global_step": 480110, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0836780071258545, "global_step": 480111, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9484965801239014, "global_step": 480112, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.033623695373535, "global_step": 480113, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9536389112472534, "global_step": 480114, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0072712898254395, "global_step": 480115, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0955610275268555, "global_step": 480116, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0300583839416504, "global_step": 480117, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1087656021118164, "global_step": 480118, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0352184772491455, "global_step": 480119, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0417516231536865, "global_step": 480120, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.011435031890869, "global_step": 480121, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.033240556716919, "global_step": 480122, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.089357376098633, "global_step": 480123, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.039608955383301, "global_step": 480124, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0074751377105713, "global_step": 480125, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0784876346588135, "global_step": 480126, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0545473098754883, "global_step": 480127, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0515637397766113, "global_step": 480128, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.013047218322754, "global_step": 480129, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.063413381576538, "global_step": 480130, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0106265544891357, "global_step": 480131, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1007707118988037, "global_step": 480132, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.122044324874878, "global_step": 480133, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0496878623962402, "global_step": 480134, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.032071352005005, "global_step": 480135, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0418970584869385, "global_step": 480136, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0158400535583496, "global_step": 480137, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1084444522857666, "global_step": 480138, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9802818298339844, "global_step": 480139, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.088926315307617, "global_step": 480140, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.088671922683716, "global_step": 480141, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1587042808532715, "global_step": 480142, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0786027908325195, "global_step": 480143, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0933258533477783, "global_step": 480144, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.123544454574585, "global_step": 480145, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0807342529296875, "global_step": 480146, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0449419021606445, "global_step": 480147, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.088482141494751, "global_step": 480148, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.075749397277832, "global_step": 480149, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0919559001922607, "global_step": 480150, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.162374258041382, "global_step": 480151, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0724406242370605, "global_step": 480152, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.056891441345215, "global_step": 480153, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.032344102859497, "global_step": 480154, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.061760425567627, "global_step": 480155, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0409035682678223, "global_step": 480156, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0349721908569336, "global_step": 480157, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0929245948791504, "global_step": 480158, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0932464599609375, "global_step": 480159, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0906636714935303, "global_step": 480160, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0368621349334717, "global_step": 480161, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9863966703414917, "global_step": 480162, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0995712280273438, "global_step": 480163, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0202019214630127, "global_step": 480164, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.057548761367798, "global_step": 480165, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.137890100479126, "global_step": 480166, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9523760080337524, "global_step": 480167, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9838273525238037, "global_step": 480168, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.073310613632202, "global_step": 480169, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0528650283813477, "global_step": 480170, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.145521402359009, "global_step": 480171, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.010037422180176, "global_step": 480172, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0094380378723145, "global_step": 480173, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1166865825653076, "global_step": 480174, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0538294315338135, "global_step": 480175, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0299901962280273, "global_step": 480176, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.062499761581421, "global_step": 480177, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0522825717926025, "global_step": 480178, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.075406312942505, "global_step": 480179, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0350935459136963, "global_step": 480180, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1340138912200928, "global_step": 480181, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0751116275787354, "global_step": 480182, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.063753128051758, "global_step": 480183, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1072001457214355, "global_step": 480184, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9927048683166504, "global_step": 480185, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0152478218078613, "global_step": 480186, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1344728469848633, "global_step": 480187, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.031343460083008, "global_step": 480188, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0895068645477295, "global_step": 480189, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0178897380828857, "global_step": 480190, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9066016674041748, "global_step": 480191, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0752248764038086, "global_step": 480192, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.137352466583252, "global_step": 480193, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0512003898620605, "global_step": 480194, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0881471633911133, "global_step": 480195, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.988440752029419, "global_step": 480196, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0838892459869385, "global_step": 480197, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.07647967338562, "global_step": 480198, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.069450616836548, "global_step": 480199, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0788938999176025, "global_step": 480200, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0054166316986084, "global_step": 480201, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.066896677017212, "global_step": 480202, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0686521530151367, "global_step": 480203, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0607309341430664, "global_step": 480204, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.099700450897217, "global_step": 480205, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.065631151199341, "global_step": 480206, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.038701057434082, "global_step": 480207, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0132453441619873, "global_step": 480208, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9809213876724243, "global_step": 480209, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1042563915252686, "global_step": 480210, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.133779764175415, "global_step": 480211, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.038254737854004, "global_step": 480212, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.15783953666687, "global_step": 480213, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1631133556365967, "global_step": 480214, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0389351844787598, "global_step": 480215, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.090517997741699, "global_step": 480216, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0839922428131104, "global_step": 480217, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0627026557922363, "global_step": 480218, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9956419467926025, "global_step": 480219, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.122227430343628, "global_step": 480220, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.031667470932007, "global_step": 480221, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1899313926696777, "global_step": 480222, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.100386381149292, "global_step": 480223, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1696383953094482, "global_step": 480224, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0966200828552246, "global_step": 480225, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0444107055664062, "global_step": 480226, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0925652980804443, "global_step": 480227, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1542274951934814, "global_step": 480228, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.054593563079834, "global_step": 480229, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0031538009643555, "global_step": 480230, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.018004894256592, "global_step": 480231, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.99849271774292, "global_step": 480232, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1384215354919434, "global_step": 480233, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0414302349090576, "global_step": 480234, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0285346508026123, "global_step": 480235, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.021512269973755, "global_step": 480236, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.196577787399292, "global_step": 480237, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.115119218826294, "global_step": 480238, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0580809116363525, "global_step": 480239, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0275092124938965, "global_step": 480240, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0250794887542725, "global_step": 480241, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.113212823867798, "global_step": 480242, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0908865928649902, "global_step": 480243, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.139404773712158, "global_step": 480244, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.092968225479126, "global_step": 480245, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.101909637451172, "global_step": 480246, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0285515785217285, "global_step": 480247, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1193151473999023, "global_step": 480248, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.072903871536255, "global_step": 480249, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.022026300430298, "global_step": 480250, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0026848316192627, "global_step": 480251, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0345308780670166, "global_step": 480252, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0169005393981934, "global_step": 480253, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0526044368743896, "global_step": 480254, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.076920986175537, "global_step": 480255, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.133923053741455, "global_step": 480256, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.045579671859741, "global_step": 480257, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.016498327255249, "global_step": 480258, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9999217987060547, "global_step": 480259, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.013744354248047, "global_step": 480260, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1401000022888184, "global_step": 480261, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.075200080871582, "global_step": 480262, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1141011714935303, "global_step": 480263, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.995796799659729, "global_step": 480264, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0548362731933594, "global_step": 480265, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0497841835021973, "global_step": 480266, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.132503032684326, "global_step": 480267, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1036295890808105, "global_step": 480268, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.124323606491089, "global_step": 480269, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1239869594573975, "global_step": 480270, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.044442653656006, "global_step": 480271, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1304194927215576, "global_step": 480272, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.042841672897339, "global_step": 480273, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1167385578155518, "global_step": 480274, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.03764009475708, "global_step": 480275, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.160325527191162, "global_step": 480276, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9504899978637695, "global_step": 480277, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.031498908996582, "global_step": 480278, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1190025806427, "global_step": 480279, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0889341831207275, "global_step": 480280, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1941747665405273, "global_step": 480281, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0079169273376465, "global_step": 480282, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1218159198760986, "global_step": 480283, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.980138897895813, "global_step": 480284, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.063164710998535, "global_step": 480285, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0212655067443848, "global_step": 480286, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0515005588531494, "global_step": 480287, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.15868878364563, "global_step": 480288, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.125244379043579, "global_step": 480289, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0567450523376465, "global_step": 480290, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0086681842803955, "global_step": 480291, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.2001664638519287, "global_step": 480292, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9580656290054321, "global_step": 480293, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.109622001647949, "global_step": 480294, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.077199697494507, "global_step": 480295, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0748636722564697, "global_step": 480296, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.062784433364868, "global_step": 480297, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.091154098510742, "global_step": 480298, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.052269458770752, "global_step": 480299, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0106232166290283, "global_step": 480300, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0381176471710205, "global_step": 480301, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.110427141189575, "global_step": 480302, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0750067234039307, "global_step": 480303, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0329108238220215, "global_step": 480304, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0977375507354736, "global_step": 480305, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0729787349700928, "global_step": 480306, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9257049560546875, "global_step": 480307, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.001534938812256, "global_step": 480308, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0637309551239014, "global_step": 480309, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1249337196350098, "global_step": 480310, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.082437753677368, "global_step": 480311, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0854620933532715, "global_step": 480312, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0415890216827393, "global_step": 480313, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.068307638168335, "global_step": 480314, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.011327028274536, "global_step": 480315, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.144092321395874, "global_step": 480316, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1149370670318604, "global_step": 480317, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0430452823638916, "global_step": 480318, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0933709144592285, "global_step": 480319, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1535696983337402, "global_step": 480320, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.003448963165283, "global_step": 480321, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.033461570739746, "global_step": 480322, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1208837032318115, "global_step": 480323, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1243133544921875, "global_step": 480324, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.072845220565796, "global_step": 480325, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.092625379562378, "global_step": 480326, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.058269739151001, "global_step": 480327, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.032140016555786, "global_step": 480328, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.038790225982666, "global_step": 480329, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0438718795776367, "global_step": 480330, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0126230716705322, "global_step": 480331, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0287070274353027, "global_step": 480332, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0329582691192627, "global_step": 480333, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.070944309234619, "global_step": 480334, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0598981380462646, "global_step": 480335, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.067730188369751, "global_step": 480336, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0364696979522705, "global_step": 480337, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0077028274536133, "global_step": 480338, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.017703056335449, "global_step": 480339, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0634026527404785, "global_step": 480340, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0174131393432617, "global_step": 480341, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0850088596343994, "global_step": 480342, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0306482315063477, "global_step": 480343, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.099743127822876, "global_step": 480344, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1020071506500244, "global_step": 480345, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.051032066345215, "global_step": 480346, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0601556301116943, "global_step": 480347, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.072753429412842, "global_step": 480348, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0278162956237793, "global_step": 480349, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.024852991104126, "global_step": 480350, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.04779052734375, "global_step": 480351, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.074418544769287, "global_step": 480352, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0496058464050293, "global_step": 480353, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1424553394317627, "global_step": 480354, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.950345754623413, "global_step": 480355, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0705275535583496, "global_step": 480356, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0507471561431885, "global_step": 480357, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0471134185791016, "global_step": 480358, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.126852035522461, "global_step": 480359, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0341153144836426, "global_step": 480360, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0820019245147705, "global_step": 480361, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0688540935516357, "global_step": 480362, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.058913230895996, "global_step": 480363, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9964885711669922, "global_step": 480364, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0619542598724365, "global_step": 480365, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1218886375427246, "global_step": 480366, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.01383376121521, "global_step": 480367, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0527305603027344, "global_step": 480368, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.041203737258911, "global_step": 480369, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.126823663711548, "global_step": 480370, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0217654705047607, "global_step": 480371, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.054535150527954, "global_step": 480372, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.2038490772247314, "global_step": 480373, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.095571994781494, "global_step": 480374, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.084611177444458, "global_step": 480375, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.086627721786499, "global_step": 480376, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.049907922744751, "global_step": 480377, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.055302381515503, "global_step": 480378, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0152857303619385, "global_step": 480379, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0132267475128174, "global_step": 480380, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0404486656188965, "global_step": 480381, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0773158073425293, "global_step": 480382, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.168369770050049, "global_step": 480383, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9680016040802002, "global_step": 480384, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.048515796661377, "global_step": 480385, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1016738414764404, "global_step": 480386, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0733256340026855, "global_step": 480387, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0905981063842773, "global_step": 480388, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0981040000915527, "global_step": 480389, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.07124400138855, "global_step": 480390, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0654523372650146, "global_step": 480391, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1166653633117676, "global_step": 480392, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.039249897003174, "global_step": 480393, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0944883823394775, "global_step": 480394, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1115148067474365, "global_step": 480395, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.09309458732605, "global_step": 480396, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.045990467071533, "global_step": 480397, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.150557518005371, "global_step": 480398, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0020854473114014, "global_step": 480399, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0820960998535156, "global_step": 480400, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.168570041656494, "global_step": 480401, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.051485300064087, "global_step": 480402, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.073140859603882, "global_step": 480403, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0180273056030273, "global_step": 480404, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9988529682159424, "global_step": 480405, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.042727470397949, "global_step": 480406, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.095418691635132, "global_step": 480407, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0777719020843506, "global_step": 480408, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9813816547393799, "global_step": 480409, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0817575454711914, "global_step": 480410, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.025139808654785, "global_step": 480411, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.2185158729553223, "global_step": 480412, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0584914684295654, "global_step": 480413, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0902040004730225, "global_step": 480414, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.046710968017578, "global_step": 480415, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1152212619781494, "global_step": 480416, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9674632549285889, "global_step": 480417, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0544352531433105, "global_step": 480418, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.088850498199463, "global_step": 480419, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.091280937194824, "global_step": 480420, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1155056953430176, "global_step": 480421, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.064183473587036, "global_step": 480422, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.994463562965393, "global_step": 480423, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1241111755371094, "global_step": 480424, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0085861682891846, "global_step": 480425, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0608036518096924, "global_step": 480426, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0398168563842773, "global_step": 480427, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0692405700683594, "global_step": 480428, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.057313919067383, "global_step": 480429, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0960090160369873, "global_step": 480430, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0555660724639893, "global_step": 480431, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.109550952911377, "global_step": 480432, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0119831562042236, "global_step": 480433, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.009711980819702, "global_step": 480434, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0774788856506348, "global_step": 480435, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0447518825531006, "global_step": 480436, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1095001697540283, "global_step": 480437, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1317946910858154, "global_step": 480438, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.087865114212036, "global_step": 480439, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.025327205657959, "global_step": 480440, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1348888874053955, "global_step": 480441, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1052086353302, "global_step": 480442, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.038708209991455, "global_step": 480443, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0639991760253906, "global_step": 480444, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9980969429016113, "global_step": 480445, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.013476848602295, "global_step": 480446, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9921501874923706, "global_step": 480447, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.049846887588501, "global_step": 480448, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0086309909820557, "global_step": 480449, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.116395950317383, "global_step": 480450, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.052063465118408, "global_step": 480451, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1202573776245117, "global_step": 480452, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.089186191558838, "global_step": 480453, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0830330848693848, "global_step": 480454, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.125751256942749, "global_step": 480455, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.111630439758301, "global_step": 480456, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.027583599090576, "global_step": 480457, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0221574306488037, "global_step": 480458, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0158779621124268, "global_step": 480459, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.092144012451172, "global_step": 480460, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0990171432495117, "global_step": 480461, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.04642653465271, "global_step": 480462, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0413730144500732, "global_step": 480463, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.000889301300049, "global_step": 480464, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0764224529266357, "global_step": 480465, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.04073166847229, "global_step": 480466, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.056994915008545, "global_step": 480467, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9905825853347778, "global_step": 480468, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1172866821289062, "global_step": 480469, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.010518789291382, "global_step": 480470, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0920357704162598, "global_step": 480471, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1068100929260254, "global_step": 480472, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.145683526992798, "global_step": 480473, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.078961133956909, "global_step": 480474, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0398976802825928, "global_step": 480475, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0721938610076904, "global_step": 480476, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1309382915496826, "global_step": 480477, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0817198753356934, "global_step": 480478, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0519514083862305, "global_step": 480479, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0724306106567383, "global_step": 480480, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0235331058502197, "global_step": 480481, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.056967258453369, "global_step": 480482, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0133073329925537, "global_step": 480483, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0401506423950195, "global_step": 480484, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.156639337539673, "global_step": 480485, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.060844659805298, "global_step": 480486, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9623504877090454, "global_step": 480487, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.044152021408081, "global_step": 480488, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0171995162963867, "global_step": 480489, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0807840824127197, "global_step": 480490, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0481719970703125, "global_step": 480491, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9962903261184692, "global_step": 480492, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0725717544555664, "global_step": 480493, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.066710948944092, "global_step": 480494, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0271503925323486, "global_step": 480495, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9812941551208496, "global_step": 480496, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.066441535949707, "global_step": 480497, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.024724245071411, "global_step": 480498, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.086308002471924, "global_step": 480499, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0190694332122803, "global_step": 480500, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.079383134841919, "global_step": 480501, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.938521146774292, "global_step": 480502, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.00587797164917, "global_step": 480503, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0246381759643555, "global_step": 480504, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0043087005615234, "global_step": 480505, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0614356994628906, "global_step": 480506, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0060136318206787, "global_step": 480507, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0145208835601807, "global_step": 480508, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1025805473327637, "global_step": 480509, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.975512146949768, "global_step": 480510, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.073671817779541, "global_step": 480511, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1093266010284424, "global_step": 480512, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0451173782348633, "global_step": 480513, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.074681520462036, "global_step": 480514, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.025893211364746, "global_step": 480515, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.027836322784424, "global_step": 480516, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0455636978149414, "global_step": 480517, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0740113258361816, "global_step": 480518, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1336283683776855, "global_step": 480519, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.158695697784424, "global_step": 480520, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.092665433883667, "global_step": 480521, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0873053073883057, "global_step": 480522, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0659737586975098, "global_step": 480523, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0811731815338135, "global_step": 480524, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1039769649505615, "global_step": 480525, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9962648153305054, "global_step": 480526, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0606558322906494, "global_step": 480527, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0169169902801514, "global_step": 480528, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.996595859527588, "global_step": 480529, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0253398418426514, "global_step": 480530, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1075332164764404, "global_step": 480531, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.019611358642578, "global_step": 480532, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9821439981460571, "global_step": 480533, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0722575187683105, "global_step": 480534, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.018584966659546, "global_step": 480535, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1233503818511963, "global_step": 480536, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0742526054382324, "global_step": 480537, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.171640157699585, "global_step": 480538, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0217108726501465, "global_step": 480539, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0994150638580322, "global_step": 480540, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.040574789047241, "global_step": 480541, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1568121910095215, "global_step": 480542, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.026336431503296, "global_step": 480543, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0456044673919678, "global_step": 480544, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.2003657817840576, "global_step": 480545, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0548431873321533, "global_step": 480546, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.031136989593506, "global_step": 480547, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0204834938049316, "global_step": 480548, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.026607036590576, "global_step": 480549, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.217533588409424, "global_step": 480550, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0016579627990723, "global_step": 480551, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0740935802459717, "global_step": 480552, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0460867881774902, "global_step": 480553, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.095324754714966, "global_step": 480554, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1994335651397705, "global_step": 480555, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0656750202178955, "global_step": 480556, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0960772037506104, "global_step": 480557, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.113194465637207, "global_step": 480558, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0226049423217773, "global_step": 480559, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.15571665763855, "global_step": 480560, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.036498785018921, "global_step": 480561, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1053566932678223, "global_step": 480562, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.035808563232422, "global_step": 480563, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.066272258758545, "global_step": 480564, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0593888759613037, "global_step": 480565, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.13041090965271, "global_step": 480566, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0934743881225586, "global_step": 480567, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.065216064453125, "global_step": 480568, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.11765193939209, "global_step": 480569, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9647297859191895, "global_step": 480570, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0234973430633545, "global_step": 480571, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0585274696350098, "global_step": 480572, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0226237773895264, "global_step": 480573, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.074718475341797, "global_step": 480574, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0404789447784424, "global_step": 480575, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.000546455383301, "global_step": 480576, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0633106231689453, "global_step": 480577, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.039120674133301, "global_step": 480578, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.059539318084717, "global_step": 480579, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0121357440948486, "global_step": 480580, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0640299320220947, "global_step": 480581, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0419721603393555, "global_step": 480582, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.089402675628662, "global_step": 480583, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.15846586227417, "global_step": 480584, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1260316371917725, "global_step": 480585, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.011240243911743, "global_step": 480586, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.22761607170105, "global_step": 480587, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0203771591186523, "global_step": 480588, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0405094623565674, "global_step": 480589, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.05062198638916, "global_step": 480590, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0600523948669434, "global_step": 480591, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1205952167510986, "global_step": 480592, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0263402462005615, "global_step": 480593, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.107076644897461, "global_step": 480594, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1150615215301514, "global_step": 480595, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.953550934791565, "global_step": 480596, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.118671178817749, "global_step": 480597, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0648550987243652, "global_step": 480598, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0004210472106934, "global_step": 480599, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1281630992889404, "global_step": 480600, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.014166831970215, "global_step": 480601, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.010657787322998, "global_step": 480602, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.038942337036133, "global_step": 480603, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0432543754577637, "global_step": 480604, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1164371967315674, "global_step": 480605, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1689867973327637, "global_step": 480606, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0342419147491455, "global_step": 480607, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1213204860687256, "global_step": 480608, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.153209924697876, "global_step": 480609, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0140128135681152, "global_step": 480610, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.066952705383301, "global_step": 480611, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9773571491241455, "global_step": 480612, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9897066354751587, "global_step": 480613, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.17206072807312, "global_step": 480614, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.024857759475708, "global_step": 480615, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.070007085800171, "global_step": 480616, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.142057418823242, "global_step": 480617, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.030146837234497, "global_step": 480618, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.07865047454834, "global_step": 480619, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.079678773880005, "global_step": 480620, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1321871280670166, "global_step": 480621, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.061769962310791, "global_step": 480622, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.171044111251831, "global_step": 480623, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.044534206390381, "global_step": 480624, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0397324562072754, "global_step": 480625, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0520029067993164, "global_step": 480626, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0556576251983643, "global_step": 480627, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0913617610931396, "global_step": 480628, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0437464714050293, "global_step": 480629, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1335792541503906, "global_step": 480630, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0420114994049072, "global_step": 480631, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9853332042694092, "global_step": 480632, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.150005578994751, "global_step": 480633, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0469257831573486, "global_step": 480634, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.090402603149414, "global_step": 480635, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.03379225730896, "global_step": 480636, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0576255321502686, "global_step": 480637, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0335865020751953, "global_step": 480638, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.081726551055908, "global_step": 480639, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.068488359451294, "global_step": 480640, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1158738136291504, "global_step": 480641, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9809330701828003, "global_step": 480642, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0816001892089844, "global_step": 480643, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0897743701934814, "global_step": 480644, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1807284355163574, "global_step": 480645, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.09110426902771, "global_step": 480646, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.103123903274536, "global_step": 480647, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.111199378967285, "global_step": 480648, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9889941215515137, "global_step": 480649, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0629091262817383, "global_step": 480650, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0770277976989746, "global_step": 480651, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.070584297180176, "global_step": 480652, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9894665479660034, "global_step": 480653, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.13689923286438, "global_step": 480654, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0372321605682373, "global_step": 480655, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0105226039886475, "global_step": 480656, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0821738243103027, "global_step": 480657, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0419387817382812, "global_step": 480658, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0539324283599854, "global_step": 480659, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1253652572631836, "global_step": 480660, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0301918983459473, "global_step": 480661, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1395695209503174, "global_step": 480662, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.031607151031494, "global_step": 480663, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0066990852355957, "global_step": 480664, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0388009548187256, "global_step": 480665, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0418081283569336, "global_step": 480666, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0621252059936523, "global_step": 480667, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0300850868225098, "global_step": 480668, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0907201766967773, "global_step": 480669, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0593276023864746, "global_step": 480670, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1387178897857666, "global_step": 480671, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1144416332244873, "global_step": 480672, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.081373929977417, "global_step": 480673, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0621449947357178, "global_step": 480674, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.064563512802124, "global_step": 480675, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.053028106689453, "global_step": 480676, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0563955307006836, "global_step": 480677, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0328569412231445, "global_step": 480678, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1102218627929688, "global_step": 480679, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.077592611312866, "global_step": 480680, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1033737659454346, "global_step": 480681, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.066925287246704, "global_step": 480682, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0664517879486084, "global_step": 480683, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.062159538269043, "global_step": 480684, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1118242740631104, "global_step": 480685, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1299846172332764, "global_step": 480686, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0808193683624268, "global_step": 480687, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0845794677734375, "global_step": 480688, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0314252376556396, "global_step": 480689, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.113391399383545, "global_step": 480690, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0483551025390625, "global_step": 480691, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1031482219696045, "global_step": 480692, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0847978591918945, "global_step": 480693, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9686636924743652, "global_step": 480694, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.030164957046509, "global_step": 480695, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.099355697631836, "global_step": 480696, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1140289306640625, "global_step": 480697, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.030411958694458, "global_step": 480698, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9330403804779053, "global_step": 480699, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.133000373840332, "global_step": 480700, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1275181770324707, "global_step": 480701, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.105807065963745, "global_step": 480702, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.072772741317749, "global_step": 480703, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.048182487487793, "global_step": 480704, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.104464292526245, "global_step": 480705, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0597188472747803, "global_step": 480706, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.009589195251465, "global_step": 480707, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0511295795440674, "global_step": 480708, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.059678792953491, "global_step": 480709, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0638251304626465, "global_step": 480710, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9753867387771606, "global_step": 480711, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.114382266998291, "global_step": 480712, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.09057354927063, "global_step": 480713, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1184256076812744, "global_step": 480714, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0460567474365234, "global_step": 480715, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.120006799697876, "global_step": 480716, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1107282638549805, "global_step": 480717, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.074233293533325, "global_step": 480718, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0840821266174316, "global_step": 480719, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1721248626708984, "global_step": 480720, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0799522399902344, "global_step": 480721, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0767412185668945, "global_step": 480722, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.067533493041992, "global_step": 480723, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1382603645324707, "global_step": 480724, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.084289789199829, "global_step": 480725, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1752898693084717, "global_step": 480726, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.015374183654785, "global_step": 480727, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1448349952697754, "global_step": 480728, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9666905403137207, "global_step": 480729, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.043654441833496, "global_step": 480730, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.049351930618286, "global_step": 480731, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1454222202301025, "global_step": 480732, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.031560182571411, "global_step": 480733, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.170487642288208, "global_step": 480734, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0913121700286865, "global_step": 480735, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0883328914642334, "global_step": 480736, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0146777629852295, "global_step": 480737, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.093559503555298, "global_step": 480738, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.1110763549804688, "global_step": 480739, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0389177799224854, "global_step": 480740, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9292957782745361, "global_step": 480741, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.105668544769287, "global_step": 480742, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0290074348449707, "global_step": 480743, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.029132843017578, "global_step": 480744, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9905813932418823, "global_step": 480745, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0856001377105713, "global_step": 480746, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9526801109313965, "global_step": 480747, "epoch": 845, "lr": 5e-05}
{"train_loss": 1.9899522066116333, "global_step": 480748, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.035834550857544, "global_step": 480749, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0712554454803467, "global_step": 480750, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.085467576980591, "global_step": 480751, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.096977710723877, "global_step": 480752, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.116652250289917, "global_step": 480753, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0757126808166504, "global_step": 480754, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0491139888763428, "global_step": 480755, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.060417890548706, "global_step": 480756, "epoch": 845, "lr": 5e-05}
{"train_loss": 2.0667803287506104, "global_step": 480757, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.114072799682617, "global_step": 480758, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0982048511505127, "global_step": 480759, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0985677242279053, "global_step": 480760, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0892186164855957, "global_step": 480761, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0911130905151367, "global_step": 480762, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.021366834640503, "global_step": 480763, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.005598545074463, "global_step": 480764, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.118985176086426, "global_step": 480765, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.964833378791809, "global_step": 480766, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.124560594558716, "global_step": 480767, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1410250663757324, "global_step": 480768, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.035735845565796, "global_step": 480769, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.074589490890503, "global_step": 480770, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9980180263519287, "global_step": 480771, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0353317260742188, "global_step": 480772, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0332376956939697, "global_step": 480773, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0332865715026855, "global_step": 480774, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0391201972961426, "global_step": 480775, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0742900371551514, "global_step": 480776, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.139538526535034, "global_step": 480777, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1180572509765625, "global_step": 480778, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0736136436462402, "global_step": 480779, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0577876567840576, "global_step": 480780, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.033545732498169, "global_step": 480781, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.059774398803711, "global_step": 480782, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0486087799072266, "global_step": 480783, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1079201698303223, "global_step": 480784, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0182907581329346, "global_step": 480785, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.128075361251831, "global_step": 480786, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.8957972526550293, "global_step": 480787, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.984228491783142, "global_step": 480788, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0053353309631348, "global_step": 480789, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0482747554779053, "global_step": 480790, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0664374828338623, "global_step": 480791, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.028296709060669, "global_step": 480792, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.108736753463745, "global_step": 480793, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.028733968734741, "global_step": 480794, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9851458072662354, "global_step": 480795, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.085153818130493, "global_step": 480796, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0280983448028564, "global_step": 480797, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9835199117660522, "global_step": 480798, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9854615926742554, "global_step": 480799, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0885164737701416, "global_step": 480800, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0548722743988037, "global_step": 480801, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.02040433883667, "global_step": 480802, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.026866912841797, "global_step": 480803, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.036198616027832, "global_step": 480804, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.08685564994812, "global_step": 480805, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.077817440032959, "global_step": 480806, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.171962261199951, "global_step": 480807, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0816245079040527, "global_step": 480808, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9959800243377686, "global_step": 480809, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.074265956878662, "global_step": 480810, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0474588871002197, "global_step": 480811, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0862910747528076, "global_step": 480812, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9699535369873047, "global_step": 480813, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0131258964538574, "global_step": 480814, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0349009037017822, "global_step": 480815, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.005145788192749, "global_step": 480816, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0659940242767334, "global_step": 480817, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1461305618286133, "global_step": 480818, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9657561779022217, "global_step": 480819, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.076587200164795, "global_step": 480820, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0075953006744385, "global_step": 480821, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0163731575012207, "global_step": 480822, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0508217811584473, "global_step": 480823, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.110196352005005, "global_step": 480824, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.124891757965088, "global_step": 480825, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0930685997009277, "global_step": 480826, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9739829301834106, "global_step": 480827, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0142147541046143, "global_step": 480828, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0833535194396973, "global_step": 480829, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9775505065917969, "global_step": 480830, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.10477876663208, "global_step": 480831, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.060791254043579, "global_step": 480832, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0525641441345215, "global_step": 480833, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0948326587677, "global_step": 480834, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9966278076171875, "global_step": 480835, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0727903842926025, "global_step": 480836, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9723385572433472, "global_step": 480837, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0235514640808105, "global_step": 480838, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.065582513809204, "global_step": 480839, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9920343160629272, "global_step": 480840, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0846621990203857, "global_step": 480841, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0714030265808105, "global_step": 480842, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.130415916442871, "global_step": 480843, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.141509532928467, "global_step": 480844, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9580812454223633, "global_step": 480845, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0518171787261963, "global_step": 480846, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.035209894180298, "global_step": 480847, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.065434694290161, "global_step": 480848, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9822685718536377, "global_step": 480849, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0471317768096924, "global_step": 480850, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.139453649520874, "global_step": 480851, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0085527896881104, "global_step": 480852, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.103604316711426, "global_step": 480853, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0638391971588135, "global_step": 480854, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1841468811035156, "global_step": 480855, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0629284381866455, "global_step": 480856, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9629833698272705, "global_step": 480857, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0858123302459717, "global_step": 480858, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1102652549743652, "global_step": 480859, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0618960857391357, "global_step": 480860, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0462887287139893, "global_step": 480861, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.019724130630493, "global_step": 480862, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1496944427490234, "global_step": 480863, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.091078281402588, "global_step": 480864, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.14200496673584, "global_step": 480865, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0350897312164307, "global_step": 480866, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0920517444610596, "global_step": 480867, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0378026962280273, "global_step": 480868, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.065526247024536, "global_step": 480869, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.001626491546631, "global_step": 480870, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0242347717285156, "global_step": 480871, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0897254943847656, "global_step": 480872, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0598061084747314, "global_step": 480873, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.05562686920166, "global_step": 480874, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1190037727355957, "global_step": 480875, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.020124673843384, "global_step": 480876, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.054884910583496, "global_step": 480877, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.057107448577881, "global_step": 480878, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1765787601470947, "global_step": 480879, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9604616165161133, "global_step": 480880, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0075531005859375, "global_step": 480881, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0668396949768066, "global_step": 480882, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.172316551208496, "global_step": 480883, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.072266101837158, "global_step": 480884, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0064330101013184, "global_step": 480885, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0438201427459717, "global_step": 480886, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.016071319580078, "global_step": 480887, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0957789421081543, "global_step": 480888, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1147546768188477, "global_step": 480889, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.086846113204956, "global_step": 480890, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0984950065612793, "global_step": 480891, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.125488519668579, "global_step": 480892, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.170527458190918, "global_step": 480893, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1323795318603516, "global_step": 480894, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.073302984237671, "global_step": 480895, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1663014888763428, "global_step": 480896, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.016432046890259, "global_step": 480897, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.032555341720581, "global_step": 480898, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0162131786346436, "global_step": 480899, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9724571704864502, "global_step": 480900, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.00495982170105, "global_step": 480901, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.074958086013794, "global_step": 480902, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0825254917144775, "global_step": 480903, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1570143699645996, "global_step": 480904, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.075753927230835, "global_step": 480905, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0323503017425537, "global_step": 480906, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0704591274261475, "global_step": 480907, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.08847975730896, "global_step": 480908, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1383886337280273, "global_step": 480909, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.031372547149658, "global_step": 480910, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0572757720947266, "global_step": 480911, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.008716344833374, "global_step": 480912, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9879026412963867, "global_step": 480913, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.033966541290283, "global_step": 480914, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9912916421890259, "global_step": 480915, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.2082324028015137, "global_step": 480916, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0228562355041504, "global_step": 480917, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1151223182678223, "global_step": 480918, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.052475929260254, "global_step": 480919, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0319173336029053, "global_step": 480920, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.112379789352417, "global_step": 480921, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.071885585784912, "global_step": 480922, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0312068462371826, "global_step": 480923, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9997773170471191, "global_step": 480924, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9668360948562622, "global_step": 480925, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.94084894657135, "global_step": 480926, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9839279651641846, "global_step": 480927, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0553855895996094, "global_step": 480928, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.171618938446045, "global_step": 480929, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0274240970611572, "global_step": 480930, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0815913677215576, "global_step": 480931, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1047511100769043, "global_step": 480932, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9451013803482056, "global_step": 480933, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.005598783493042, "global_step": 480934, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.082564353942871, "global_step": 480935, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0647521018981934, "global_step": 480936, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.05413818359375, "global_step": 480937, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0681724548339844, "global_step": 480938, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.078167676925659, "global_step": 480939, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0589706897735596, "global_step": 480940, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0860769748687744, "global_step": 480941, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.036604881286621, "global_step": 480942, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0889713764190674, "global_step": 480943, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.066258668899536, "global_step": 480944, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0505077838897705, "global_step": 480945, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.120089530944824, "global_step": 480946, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0067014694213867, "global_step": 480947, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0591447353363037, "global_step": 480948, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9516968727111816, "global_step": 480949, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0783305168151855, "global_step": 480950, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0746917724609375, "global_step": 480951, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0015387535095215, "global_step": 480952, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.048427104949951, "global_step": 480953, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1374058723449707, "global_step": 480954, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.031264305114746, "global_step": 480955, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0507400035858154, "global_step": 480956, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0849568843841553, "global_step": 480957, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.125908613204956, "global_step": 480958, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.060460329055786, "global_step": 480959, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0076935291290283, "global_step": 480960, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.979945182800293, "global_step": 480961, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.119352340698242, "global_step": 480962, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.095538377761841, "global_step": 480963, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.087040662765503, "global_step": 480964, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9973936080932617, "global_step": 480965, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.070415496826172, "global_step": 480966, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9322538375854492, "global_step": 480967, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.05362868309021, "global_step": 480968, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.020951747894287, "global_step": 480969, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0427591800689697, "global_step": 480970, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.028738260269165, "global_step": 480971, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.133197784423828, "global_step": 480972, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.088754653930664, "global_step": 480973, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.919255018234253, "global_step": 480974, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.991086483001709, "global_step": 480975, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.078404664993286, "global_step": 480976, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9948481321334839, "global_step": 480977, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1282119750976562, "global_step": 480978, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9936108589172363, "global_step": 480979, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.050394058227539, "global_step": 480980, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.116267442703247, "global_step": 480981, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.10042142868042, "global_step": 480982, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0694494247436523, "global_step": 480983, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1065280437469482, "global_step": 480984, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1395461559295654, "global_step": 480985, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0200181007385254, "global_step": 480986, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.029975175857544, "global_step": 480987, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0185036659240723, "global_step": 480988, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9846205711364746, "global_step": 480989, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.008647918701172, "global_step": 480990, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9698545932769775, "global_step": 480991, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0599069595336914, "global_step": 480992, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0859596729278564, "global_step": 480993, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9509323835372925, "global_step": 480994, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.006279945373535, "global_step": 480995, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1632120609283447, "global_step": 480996, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.008049488067627, "global_step": 480997, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1519274711608887, "global_step": 480998, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.099656581878662, "global_step": 480999, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.157130718231201, "global_step": 481000, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.141573667526245, "global_step": 481001, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0701863765716553, "global_step": 481002, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9673488140106201, "global_step": 481003, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0137710571289062, "global_step": 481004, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0338330268859863, "global_step": 481005, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.046807050704956, "global_step": 481006, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0572948455810547, "global_step": 481007, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9698834419250488, "global_step": 481008, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.12445330619812, "global_step": 481009, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0442466735839844, "global_step": 481010, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.055586576461792, "global_step": 481011, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1209616661071777, "global_step": 481012, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.042090892791748, "global_step": 481013, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9982554912567139, "global_step": 481014, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9864426851272583, "global_step": 481015, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.113579034805298, "global_step": 481016, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1353964805603027, "global_step": 481017, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.134127616882324, "global_step": 481018, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.074429988861084, "global_step": 481019, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.056847333908081, "global_step": 481020, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0452544689178467, "global_step": 481021, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.14739727973938, "global_step": 481022, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.061079740524292, "global_step": 481023, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.011831045150757, "global_step": 481024, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0859644412994385, "global_step": 481025, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.047626256942749, "global_step": 481026, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0710062980651855, "global_step": 481027, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1127490997314453, "global_step": 481028, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0528922080993652, "global_step": 481029, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0194313526153564, "global_step": 481030, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1139941215515137, "global_step": 481031, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.095141649246216, "global_step": 481032, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.040646553039551, "global_step": 481033, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.069007396697998, "global_step": 481034, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9903452396392822, "global_step": 481035, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0797526836395264, "global_step": 481036, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.131490468978882, "global_step": 481037, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0063395500183105, "global_step": 481038, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0472030639648438, "global_step": 481039, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0486767292022705, "global_step": 481040, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0644705295562744, "global_step": 481041, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0452072620391846, "global_step": 481042, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1427109241485596, "global_step": 481043, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0204761028289795, "global_step": 481044, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9872254133224487, "global_step": 481045, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.120074510574341, "global_step": 481046, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.125948905944824, "global_step": 481047, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.046116590499878, "global_step": 481048, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0666205883026123, "global_step": 481049, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.007037401199341, "global_step": 481050, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0848655700683594, "global_step": 481051, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.165313720703125, "global_step": 481052, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.050023078918457, "global_step": 481053, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.056286096572876, "global_step": 481054, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.075164556503296, "global_step": 481055, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0423424243927, "global_step": 481056, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0136382579803467, "global_step": 481057, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.063530206680298, "global_step": 481058, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.001547336578369, "global_step": 481059, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1344053745269775, "global_step": 481060, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.010197639465332, "global_step": 481061, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1720638275146484, "global_step": 481062, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0978307723999023, "global_step": 481063, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.053490400314331, "global_step": 481064, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0641355514526367, "global_step": 481065, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.043386697769165, "global_step": 481066, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.056037187576294, "global_step": 481067, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.081110715866089, "global_step": 481068, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0771260261535645, "global_step": 481069, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0479934215545654, "global_step": 481070, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.020280599594116, "global_step": 481071, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.083073854446411, "global_step": 481072, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0106751918792725, "global_step": 481073, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0427138805389404, "global_step": 481074, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0900368690490723, "global_step": 481075, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.026336431503296, "global_step": 481076, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.096226215362549, "global_step": 481077, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1290431022644043, "global_step": 481078, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.056849956512451, "global_step": 481079, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9587081670761108, "global_step": 481080, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.095366954803467, "global_step": 481081, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.117670774459839, "global_step": 481082, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.044930934906006, "global_step": 481083, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0280745029449463, "global_step": 481084, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.04117751121521, "global_step": 481085, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0705251693725586, "global_step": 481086, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.071545124053955, "global_step": 481087, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9953466653823853, "global_step": 481088, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.00825572013855, "global_step": 481089, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.019803285598755, "global_step": 481090, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.132600784301758, "global_step": 481091, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0893750190734863, "global_step": 481092, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.145416259765625, "global_step": 481093, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9681155681610107, "global_step": 481094, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0833628177642822, "global_step": 481095, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0560035705566406, "global_step": 481096, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0754706859588623, "global_step": 481097, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0749804973602295, "global_step": 481098, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1934614181518555, "global_step": 481099, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0748238563537598, "global_step": 481100, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0249085426330566, "global_step": 481101, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0280699729919434, "global_step": 481102, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9979252815246582, "global_step": 481103, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.046074151992798, "global_step": 481104, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.090930461883545, "global_step": 481105, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.069425106048584, "global_step": 481106, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.98125422000885, "global_step": 481107, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.966093897819519, "global_step": 481108, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.048215389251709, "global_step": 481109, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.001500368118286, "global_step": 481110, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0611929893493652, "global_step": 481111, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.057940721511841, "global_step": 481112, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.991938829421997, "global_step": 481113, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.001176118850708, "global_step": 481114, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0568313598632812, "global_step": 481115, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9763593673706055, "global_step": 481116, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.062623977661133, "global_step": 481117, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0066895484924316, "global_step": 481118, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0430409908294678, "global_step": 481119, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9581631422042847, "global_step": 481120, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0032620429992676, "global_step": 481121, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.056394338607788, "global_step": 481122, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.13818097114563, "global_step": 481123, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.023538827896118, "global_step": 481124, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1190073490142822, "global_step": 481125, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.125332832336426, "global_step": 481126, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0716443061828613, "global_step": 481127, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.937610149383545, "global_step": 481128, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0178511142730713, "global_step": 481129, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0603201389312744, "global_step": 481130, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9863512516021729, "global_step": 481131, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0683600902557373, "global_step": 481132, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0196142196655273, "global_step": 481133, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.036072015762329, "global_step": 481134, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0552475452423096, "global_step": 481135, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0707337856292725, "global_step": 481136, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0625874996185303, "global_step": 481137, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.068505048751831, "global_step": 481138, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.012753963470459, "global_step": 481139, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0447216033935547, "global_step": 481140, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.062173366546631, "global_step": 481141, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0068373680114746, "global_step": 481142, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0945661067962646, "global_step": 481143, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0812275409698486, "global_step": 481144, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.009701728820801, "global_step": 481145, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.065842866897583, "global_step": 481146, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0602009296417236, "global_step": 481147, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.030639886856079, "global_step": 481148, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1255080699920654, "global_step": 481149, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0082614421844482, "global_step": 481150, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0665011405944824, "global_step": 481151, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1102383136749268, "global_step": 481152, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.08988618850708, "global_step": 481153, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.066267490386963, "global_step": 481154, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.054074764251709, "global_step": 481155, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.074615240097046, "global_step": 481156, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.979567289352417, "global_step": 481157, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0890049934387207, "global_step": 481158, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0683205127716064, "global_step": 481159, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.993666410446167, "global_step": 481160, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9664442539215088, "global_step": 481161, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0163004398345947, "global_step": 481162, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.083101749420166, "global_step": 481163, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0535173416137695, "global_step": 481164, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9639503955841064, "global_step": 481165, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0932440757751465, "global_step": 481166, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0903797149658203, "global_step": 481167, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1131110191345215, "global_step": 481168, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.011991500854492, "global_step": 481169, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0254452228546143, "global_step": 481170, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0375940799713135, "global_step": 481171, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0603513717651367, "global_step": 481172, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9617369174957275, "global_step": 481173, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0991077423095703, "global_step": 481174, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9159631729125977, "global_step": 481175, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0525553226470947, "global_step": 481176, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0170488357543945, "global_step": 481177, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.068052291870117, "global_step": 481178, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.009225845336914, "global_step": 481179, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0250494480133057, "global_step": 481180, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.066601276397705, "global_step": 481181, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.085005760192871, "global_step": 481182, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.213322162628174, "global_step": 481183, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0243842601776123, "global_step": 481184, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.042792558670044, "global_step": 481185, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.036937952041626, "global_step": 481186, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0219526290893555, "global_step": 481187, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0336923599243164, "global_step": 481188, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.030057430267334, "global_step": 481189, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.044382095336914, "global_step": 481190, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.079824686050415, "global_step": 481191, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0122697353363037, "global_step": 481192, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0955185890197754, "global_step": 481193, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.116533041000366, "global_step": 481194, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0799529552459717, "global_step": 481195, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1401078701019287, "global_step": 481196, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0520949363708496, "global_step": 481197, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.104294776916504, "global_step": 481198, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.064617872238159, "global_step": 481199, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1470367908477783, "global_step": 481200, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.066418409347534, "global_step": 481201, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0562033653259277, "global_step": 481202, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.116020917892456, "global_step": 481203, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.045743703842163, "global_step": 481204, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.018376111984253, "global_step": 481205, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9784311056137085, "global_step": 481206, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.061184883117676, "global_step": 481207, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0967068672180176, "global_step": 481208, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.010739326477051, "global_step": 481209, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.009026050567627, "global_step": 481210, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0781850814819336, "global_step": 481211, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.025275230407715, "global_step": 481212, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0568249225616455, "global_step": 481213, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0282132625579834, "global_step": 481214, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9947060346603394, "global_step": 481215, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0384809970855713, "global_step": 481216, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0141289234161377, "global_step": 481217, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.039421558380127, "global_step": 481218, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.047898530960083, "global_step": 481219, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.979490876197815, "global_step": 481220, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.112091064453125, "global_step": 481221, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0308444499969482, "global_step": 481222, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.969140887260437, "global_step": 481223, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.016306161880493, "global_step": 481224, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.080138921737671, "global_step": 481225, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0602221488952637, "global_step": 481226, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1231682300567627, "global_step": 481227, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.06541109085083, "global_step": 481228, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1079745292663574, "global_step": 481229, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.073413372039795, "global_step": 481230, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.035879373550415, "global_step": 481231, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.071913957595825, "global_step": 481232, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9822583198547363, "global_step": 481233, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0135693550109863, "global_step": 481234, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.105670690536499, "global_step": 481235, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.034385919570923, "global_step": 481236, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.074418544769287, "global_step": 481237, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.166102409362793, "global_step": 481238, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.014523983001709, "global_step": 481239, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.088186264038086, "global_step": 481240, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.095177412033081, "global_step": 481241, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9650851488113403, "global_step": 481242, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0414557456970215, "global_step": 481243, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.003262519836426, "global_step": 481244, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.087625741958618, "global_step": 481245, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0315778255462646, "global_step": 481246, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.037219762802124, "global_step": 481247, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0753440856933594, "global_step": 481248, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0080833435058594, "global_step": 481249, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.061184883117676, "global_step": 481250, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.069098949432373, "global_step": 481251, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.030909776687622, "global_step": 481252, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0770442485809326, "global_step": 481253, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1384260654449463, "global_step": 481254, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1043107509613037, "global_step": 481255, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1300888061523438, "global_step": 481256, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0236287117004395, "global_step": 481257, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.012877941131592, "global_step": 481258, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0950465202331543, "global_step": 481259, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.976460576057434, "global_step": 481260, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0514278411865234, "global_step": 481261, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.072418451309204, "global_step": 481262, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.030196189880371, "global_step": 481263, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1121349334716797, "global_step": 481264, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0888686180114746, "global_step": 481265, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1470632553100586, "global_step": 481266, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1126627922058105, "global_step": 481267, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0429742336273193, "global_step": 481268, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.016803741455078, "global_step": 481269, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0809175968170166, "global_step": 481270, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9758552312850952, "global_step": 481271, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0653364658355713, "global_step": 481272, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.01513409614563, "global_step": 481273, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0978095531463623, "global_step": 481274, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1118175983428955, "global_step": 481275, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0377233028411865, "global_step": 481276, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0752875804901123, "global_step": 481277, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0811784267425537, "global_step": 481278, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.006563901901245, "global_step": 481279, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.042353630065918, "global_step": 481280, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0242533683776855, "global_step": 481281, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0713024139404297, "global_step": 481282, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.108656406402588, "global_step": 481283, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.159437656402588, "global_step": 481284, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0985562801361084, "global_step": 481285, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.046058177947998, "global_step": 481286, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.054535388946533, "global_step": 481287, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.061797618865967, "global_step": 481288, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.053972005844116, "global_step": 481289, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0154075622558594, "global_step": 481290, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.01931095123291, "global_step": 481291, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0630037784576416, "global_step": 481292, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1303417682647705, "global_step": 481293, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.082766056060791, "global_step": 481294, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0687599182128906, "global_step": 481295, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.134669780731201, "global_step": 481296, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.07926869392395, "global_step": 481297, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0458807945251465, "global_step": 481298, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0142009258270264, "global_step": 481299, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9901798963546753, "global_step": 481300, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0775885581970215, "global_step": 481301, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.159226179122925, "global_step": 481302, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0507607460021973, "global_step": 481303, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.102411985397339, "global_step": 481304, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.98646879196167, "global_step": 481305, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0474886894226074, "global_step": 481306, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1127374172210693, "global_step": 481307, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1161937713623047, "global_step": 481308, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1200637817382812, "global_step": 481309, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0178635120391846, "global_step": 481310, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1051599979400635, "global_step": 481311, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1012401580810547, "global_step": 481312, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.117650032043457, "global_step": 481313, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.095623016357422, "global_step": 481314, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.075056791305542, "global_step": 481315, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.093132734298706, "global_step": 481316, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0234832763671875, "global_step": 481317, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0636143684387207, "global_step": 481318, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0518198013305664, "global_step": 481319, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0769758224487305, "global_step": 481320, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1122043132781982, "global_step": 481321, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1411187648773193, "global_step": 481322, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.028671979904175, "global_step": 481323, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1322054862976074, "global_step": 481324, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0682902336120605, "global_step": 481325, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.104858160018921, "global_step": 481326, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.056394100189209, "global_step": 481327, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0888946056365967, "global_step": 481328, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.077004909515381, "global_step": 481329, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0268588066101074, "global_step": 481330, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0549123287200928, "global_step": 481331, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9790704250335693, "global_step": 481332, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.140545606613159, "global_step": 481333, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.072129487991333, "global_step": 481334, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.203200101852417, "global_step": 481335, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0660922527313232, "global_step": 481336, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.127387762069702, "global_step": 481337, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0713751316070557, "global_step": 481338, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1011688709259033, "global_step": 481339, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0579674243927, "global_step": 481340, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0823757648468018, "global_step": 481341, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.2132363319396973, "global_step": 481342, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.035315752029419, "global_step": 481343, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.997124195098877, "global_step": 481344, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.102631092071533, "global_step": 481345, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.074411630630493, "global_step": 481346, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0492641925811768, "global_step": 481347, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.115811347961426, "global_step": 481348, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.123387575149536, "global_step": 481349, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0984034538269043, "global_step": 481350, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.04474139213562, "global_step": 481351, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0443835258483887, "global_step": 481352, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0171027183532715, "global_step": 481353, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0073657035827637, "global_step": 481354, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9859193563461304, "global_step": 481355, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0356616973876953, "global_step": 481356, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0331125259399414, "global_step": 481357, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9826173782348633, "global_step": 481358, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9930311441421509, "global_step": 481359, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9816354513168335, "global_step": 481360, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.088707208633423, "global_step": 481361, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.937292456626892, "global_step": 481362, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0536978244781494, "global_step": 481363, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1292827129364014, "global_step": 481364, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.081195831298828, "global_step": 481365, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.067235231399536, "global_step": 481366, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.998612403869629, "global_step": 481367, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0241377353668213, "global_step": 481368, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.042851448059082, "global_step": 481369, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9951170682907104, "global_step": 481370, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.035987138748169, "global_step": 481371, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.104252815246582, "global_step": 481372, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0882081985473633, "global_step": 481373, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.057615041732788, "global_step": 481374, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.164513349533081, "global_step": 481375, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0695464611053467, "global_step": 481376, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9343096017837524, "global_step": 481377, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1068553924560547, "global_step": 481378, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.082972526550293, "global_step": 481379, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0066826343536377, "global_step": 481380, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9953529834747314, "global_step": 481381, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0400381088256836, "global_step": 481382, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0392606258392334, "global_step": 481383, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.045543909072876, "global_step": 481384, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.157893657684326, "global_step": 481385, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1381003856658936, "global_step": 481386, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1064858436584473, "global_step": 481387, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.122173547744751, "global_step": 481388, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0766046047210693, "global_step": 481389, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.174272298812866, "global_step": 481390, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0158562660217285, "global_step": 481391, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.060652017593384, "global_step": 481392, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0245542526245117, "global_step": 481393, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1550614833831787, "global_step": 481394, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0597054958343506, "global_step": 481395, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.046665668487549, "global_step": 481396, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.000889778137207, "global_step": 481397, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.026684284210205, "global_step": 481398, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0772762298583984, "global_step": 481399, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0354881286621094, "global_step": 481400, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1073222160339355, "global_step": 481401, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0845441818237305, "global_step": 481402, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.115323543548584, "global_step": 481403, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0299036502838135, "global_step": 481404, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1090586185455322, "global_step": 481405, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0375149250030518, "global_step": 481406, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.045475959777832, "global_step": 481407, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0157268047332764, "global_step": 481408, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0820083618164062, "global_step": 481409, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0811595916748047, "global_step": 481410, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.010371685028076, "global_step": 481411, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.040114641189575, "global_step": 481412, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.070155143737793, "global_step": 481413, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9782863855361938, "global_step": 481414, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0688934326171875, "global_step": 481415, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0575690269470215, "global_step": 481416, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.036562919616699, "global_step": 481417, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0552167892456055, "global_step": 481418, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0572619438171387, "global_step": 481419, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.016472578048706, "global_step": 481420, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1483452320098877, "global_step": 481421, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.045027017593384, "global_step": 481422, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.044656991958618, "global_step": 481423, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0752038955688477, "global_step": 481424, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.025691270828247, "global_step": 481425, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0292766094207764, "global_step": 481426, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9821234941482544, "global_step": 481427, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0686001777648926, "global_step": 481428, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1033177375793457, "global_step": 481429, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1678450107574463, "global_step": 481430, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0658199787139893, "global_step": 481431, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.073420763015747, "global_step": 481432, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.067087173461914, "global_step": 481433, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.033578872680664, "global_step": 481434, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.074108839035034, "global_step": 481435, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.094381093978882, "global_step": 481436, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.943057656288147, "global_step": 481437, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0874478816986084, "global_step": 481438, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0188653469085693, "global_step": 481439, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0375077724456787, "global_step": 481440, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0254576206207275, "global_step": 481441, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0020058155059814, "global_step": 481442, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.082275867462158, "global_step": 481443, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0755293369293213, "global_step": 481444, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.087336301803589, "global_step": 481445, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.024449110031128, "global_step": 481446, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0774824619293213, "global_step": 481447, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0791876316070557, "global_step": 481448, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.068075180053711, "global_step": 481449, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0322701930999756, "global_step": 481450, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.139871597290039, "global_step": 481451, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.09149432182312, "global_step": 481452, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.061056137084961, "global_step": 481453, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1407899856567383, "global_step": 481454, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1081125736236572, "global_step": 481455, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9575086832046509, "global_step": 481456, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0679128170013428, "global_step": 481457, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0546793937683105, "global_step": 481458, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0737056732177734, "global_step": 481459, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9839134216308594, "global_step": 481460, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.088688850402832, "global_step": 481461, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9565225839614868, "global_step": 481462, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0555942058563232, "global_step": 481463, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.015916585922241, "global_step": 481464, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.077134609222412, "global_step": 481465, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.116462469100952, "global_step": 481466, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0812649726867676, "global_step": 481467, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.057292938232422, "global_step": 481468, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0708401203155518, "global_step": 481469, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0874533653259277, "global_step": 481470, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0433101654052734, "global_step": 481471, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0806593894958496, "global_step": 481472, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.169865369796753, "global_step": 481473, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9890438318252563, "global_step": 481474, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.07035493850708, "global_step": 481475, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.010838031768799, "global_step": 481476, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9806369543075562, "global_step": 481477, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.074252128601074, "global_step": 481478, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.039557456970215, "global_step": 481479, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0808122158050537, "global_step": 481480, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.09639310836792, "global_step": 481481, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0742855072021484, "global_step": 481482, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.063023567199707, "global_step": 481483, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.172322988510132, "global_step": 481484, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0626046657562256, "global_step": 481485, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0395259857177734, "global_step": 481486, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0766854286193848, "global_step": 481487, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.088402271270752, "global_step": 481488, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.054690361022949, "global_step": 481489, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.051239490509033, "global_step": 481490, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.088197946548462, "global_step": 481491, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0628397464752197, "global_step": 481492, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.063573122024536, "global_step": 481493, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1191046237945557, "global_step": 481494, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.030639171600342, "global_step": 481495, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.007535219192505, "global_step": 481496, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0912060737609863, "global_step": 481497, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0376906394958496, "global_step": 481498, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.049262285232544, "global_step": 481499, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0255091190338135, "global_step": 481500, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0384767055511475, "global_step": 481501, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.044569492340088, "global_step": 481502, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.128617763519287, "global_step": 481503, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0429320335388184, "global_step": 481504, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0745296478271484, "global_step": 481505, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0084214210510254, "global_step": 481506, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0621230602264404, "global_step": 481507, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9839451313018799, "global_step": 481508, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0524187088012695, "global_step": 481509, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.034339666366577, "global_step": 481510, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0583033561706543, "global_step": 481511, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0995702743530273, "global_step": 481512, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1246564388275146, "global_step": 481513, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0623884201049805, "global_step": 481514, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0542256832122803, "global_step": 481515, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.041551351547241, "global_step": 481516, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.04439640045166, "global_step": 481517, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.018413543701172, "global_step": 481518, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.107879638671875, "global_step": 481519, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0383410453796387, "global_step": 481520, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0902774333953857, "global_step": 481521, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.027198553085327, "global_step": 481522, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0511579513549805, "global_step": 481523, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0440289974212646, "global_step": 481524, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1007778644561768, "global_step": 481525, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.055715322494507, "global_step": 481526, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0544729232788086, "global_step": 481527, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.05488657951355, "global_step": 481528, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0161726474761963, "global_step": 481529, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0549254417419434, "global_step": 481530, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1285037994384766, "global_step": 481531, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.028277635574341, "global_step": 481532, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.132920026779175, "global_step": 481533, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1052777767181396, "global_step": 481534, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.177105188369751, "global_step": 481535, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1576359272003174, "global_step": 481536, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9849574565887451, "global_step": 481537, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0912091732025146, "global_step": 481538, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0739669799804688, "global_step": 481539, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1267573833465576, "global_step": 481540, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.071446180343628, "global_step": 481541, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1073286533355713, "global_step": 481542, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1030828952789307, "global_step": 481543, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9510271549224854, "global_step": 481544, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0538973808288574, "global_step": 481545, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.077946424484253, "global_step": 481546, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0288515090942383, "global_step": 481547, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0958845615386963, "global_step": 481548, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.159707546234131, "global_step": 481549, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0709290504455566, "global_step": 481550, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.982011079788208, "global_step": 481551, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1040148735046387, "global_step": 481552, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0448853969573975, "global_step": 481553, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1203136444091797, "global_step": 481554, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1132771968841553, "global_step": 481555, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0079619884490967, "global_step": 481556, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0386810302734375, "global_step": 481557, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.047637939453125, "global_step": 481558, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.038677215576172, "global_step": 481559, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.057844638824463, "global_step": 481560, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.071449041366577, "global_step": 481561, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0364081859588623, "global_step": 481562, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.115856647491455, "global_step": 481563, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.046630859375, "global_step": 481564, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.093717336654663, "global_step": 481565, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0468688011169434, "global_step": 481566, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.119671106338501, "global_step": 481567, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.985540509223938, "global_step": 481568, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1390092372894287, "global_step": 481569, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9686609506607056, "global_step": 481570, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1055521965026855, "global_step": 481571, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0296316146850586, "global_step": 481572, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.010962724685669, "global_step": 481573, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0588831901550293, "global_step": 481574, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0401833057403564, "global_step": 481575, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.107313394546509, "global_step": 481576, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.123650074005127, "global_step": 481577, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0611026287078857, "global_step": 481578, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.019036293029785, "global_step": 481579, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0779242515563965, "global_step": 481580, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1112308502197266, "global_step": 481581, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.074470043182373, "global_step": 481582, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1160073280334473, "global_step": 481583, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0713260173797607, "global_step": 481584, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1583688259124756, "global_step": 481585, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0792157649993896, "global_step": 481586, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0638790130615234, "global_step": 481587, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0687687397003174, "global_step": 481588, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0633013248443604, "global_step": 481589, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.023023843765259, "global_step": 481590, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.089310646057129, "global_step": 481591, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0640923976898193, "global_step": 481592, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9821900129318237, "global_step": 481593, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0545756816864014, "global_step": 481594, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1407148838043213, "global_step": 481595, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.03840708732605, "global_step": 481596, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.077853202819824, "global_step": 481597, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.026048183441162, "global_step": 481598, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0405232906341553, "global_step": 481599, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.991721749305725, "global_step": 481600, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0036635398864746, "global_step": 481601, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9774738550186157, "global_step": 481602, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.005720615386963, "global_step": 481603, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.114361047744751, "global_step": 481604, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0566768646240234, "global_step": 481605, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0435376167297363, "global_step": 481606, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0720882415771484, "global_step": 481607, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.158205509185791, "global_step": 481608, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.053513765335083, "global_step": 481609, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.085944890975952, "global_step": 481610, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.041675329208374, "global_step": 481611, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.054809331893921, "global_step": 481612, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9490236043930054, "global_step": 481613, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0418176651000977, "global_step": 481614, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0765068531036377, "global_step": 481615, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0531904697418213, "global_step": 481616, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0565009117126465, "global_step": 481617, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1847028732299805, "global_step": 481618, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0887725353240967, "global_step": 481619, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.999300241470337, "global_step": 481620, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0070252418518066, "global_step": 481621, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.055349588394165, "global_step": 481622, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0797951221466064, "global_step": 481623, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.116273880004883, "global_step": 481624, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.128610610961914, "global_step": 481625, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.047090530395508, "global_step": 481626, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1089348793029785, "global_step": 481627, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.119384288787842, "global_step": 481628, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.057281255722046, "global_step": 481629, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.021268129348755, "global_step": 481630, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9685600996017456, "global_step": 481631, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0589377880096436, "global_step": 481632, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1204822063446045, "global_step": 481633, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0053069591522217, "global_step": 481634, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0061635971069336, "global_step": 481635, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0981009006500244, "global_step": 481636, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.175671100616455, "global_step": 481637, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.108043909072876, "global_step": 481638, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0180444717407227, "global_step": 481639, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.024916648864746, "global_step": 481640, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0972647666931152, "global_step": 481641, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0019497871398926, "global_step": 481642, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0316660404205322, "global_step": 481643, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.103773355484009, "global_step": 481644, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.099503993988037, "global_step": 481645, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.10907244682312, "global_step": 481646, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0848307609558105, "global_step": 481647, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.112762212753296, "global_step": 481648, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0746328830718994, "global_step": 481649, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0817511081695557, "global_step": 481650, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.183856248855591, "global_step": 481651, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1263411045074463, "global_step": 481652, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.019151449203491, "global_step": 481653, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.023369550704956, "global_step": 481654, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0752761363983154, "global_step": 481655, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.961316466331482, "global_step": 481656, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.123589277267456, "global_step": 481657, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1617684364318848, "global_step": 481658, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.055264472961426, "global_step": 481659, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0477561950683594, "global_step": 481660, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1191298961639404, "global_step": 481661, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1497631072998047, "global_step": 481662, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0595593452453613, "global_step": 481663, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0942366123199463, "global_step": 481664, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0850300788879395, "global_step": 481665, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0856382846832275, "global_step": 481666, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.122046709060669, "global_step": 481667, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.036228895187378, "global_step": 481668, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0447497367858887, "global_step": 481669, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0445873737335205, "global_step": 481670, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1033880710601807, "global_step": 481671, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0703773498535156, "global_step": 481672, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0012283325195312, "global_step": 481673, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9831774234771729, "global_step": 481674, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.02946400642395, "global_step": 481675, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.069352626800537, "global_step": 481676, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1107025146484375, "global_step": 481677, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1135292053222656, "global_step": 481678, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1380395889282227, "global_step": 481679, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.121100902557373, "global_step": 481680, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.152970314025879, "global_step": 481681, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0958831310272217, "global_step": 481682, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.123771905899048, "global_step": 481683, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0991368293762207, "global_step": 481684, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.066333532333374, "global_step": 481685, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0372161865234375, "global_step": 481686, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.95139741897583, "global_step": 481687, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0220224857330322, "global_step": 481688, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0578620433807373, "global_step": 481689, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.942808747291565, "global_step": 481690, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0039849281311035, "global_step": 481691, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0903491973876953, "global_step": 481692, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.094764471054077, "global_step": 481693, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0569536685943604, "global_step": 481694, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0453712940216064, "global_step": 481695, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1415770053863525, "global_step": 481696, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0583713054656982, "global_step": 481697, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1265509128570557, "global_step": 481698, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0940308570861816, "global_step": 481699, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0187206268310547, "global_step": 481700, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0124518871307373, "global_step": 481701, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1613035202026367, "global_step": 481702, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.102306604385376, "global_step": 481703, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.024102210998535, "global_step": 481704, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1148858070373535, "global_step": 481705, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0602078437805176, "global_step": 481706, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0884175300598145, "global_step": 481707, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.02606463432312, "global_step": 481708, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0486185550689697, "global_step": 481709, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.033034563064575, "global_step": 481710, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.052072763442993, "global_step": 481711, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0797317028045654, "global_step": 481712, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0499331951141357, "global_step": 481713, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1530659198760986, "global_step": 481714, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.038295269012451, "global_step": 481715, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1254961490631104, "global_step": 481716, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0389068126678467, "global_step": 481717, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.069429636001587, "global_step": 481718, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9321932792663574, "global_step": 481719, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.118100643157959, "global_step": 481720, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.133822441101074, "global_step": 481721, "epoch": 846, "lr": 5e-05}
{"train_loss": 1.9917916059494019, "global_step": 481722, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.1364850997924805, "global_step": 481723, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0875084400177, "global_step": 481724, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.0604147911071777, "global_step": 481725, "epoch": 846, "lr": 5e-05}
{"train_loss": 2.025381565093994, "global_step": 481726, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.095552682876587, "global_step": 481727, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.080076217651367, "global_step": 481728, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.054154872894287, "global_step": 481729, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9873268604278564, "global_step": 481730, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0209529399871826, "global_step": 481731, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1151132583618164, "global_step": 481732, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.117048501968384, "global_step": 481733, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0959386825561523, "global_step": 481734, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1722772121429443, "global_step": 481735, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.027804374694824, "global_step": 481736, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0425970554351807, "global_step": 481737, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.053248643875122, "global_step": 481738, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.018860101699829, "global_step": 481739, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0676708221435547, "global_step": 481740, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.022651433944702, "global_step": 481741, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0621652603149414, "global_step": 481742, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.018047332763672, "global_step": 481743, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0470306873321533, "global_step": 481744, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.070347785949707, "global_step": 481745, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1011624336242676, "global_step": 481746, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0414276123046875, "global_step": 481747, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.075186014175415, "global_step": 481748, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9262268543243408, "global_step": 481749, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0472350120544434, "global_step": 481750, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.018901824951172, "global_step": 481751, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0433778762817383, "global_step": 481752, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0471458435058594, "global_step": 481753, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0631914138793945, "global_step": 481754, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0286803245544434, "global_step": 481755, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.026780366897583, "global_step": 481756, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.090055465698242, "global_step": 481757, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.070450782775879, "global_step": 481758, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1273508071899414, "global_step": 481759, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9715266227722168, "global_step": 481760, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.087113618850708, "global_step": 481761, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0810394287109375, "global_step": 481762, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1032018661499023, "global_step": 481763, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.977020263671875, "global_step": 481764, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0858964920043945, "global_step": 481765, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.056272506713867, "global_step": 481766, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9918997287750244, "global_step": 481767, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.114241361618042, "global_step": 481768, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0144786834716797, "global_step": 481769, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.983156681060791, "global_step": 481770, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0752549171447754, "global_step": 481771, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0316035747528076, "global_step": 481772, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0933878421783447, "global_step": 481773, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.07114577293396, "global_step": 481774, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9828535318374634, "global_step": 481775, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.017536163330078, "global_step": 481776, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1362147331237793, "global_step": 481777, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.060593366622925, "global_step": 481778, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0257296562194824, "global_step": 481779, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.053356170654297, "global_step": 481780, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.099883556365967, "global_step": 481781, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0091400146484375, "global_step": 481782, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.148742914199829, "global_step": 481783, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0709288120269775, "global_step": 481784, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9701404571533203, "global_step": 481785, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1788859367370605, "global_step": 481786, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.051152467727661, "global_step": 481787, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9984004497528076, "global_step": 481788, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.058610677719116, "global_step": 481789, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.058820962905884, "global_step": 481790, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1444084644317627, "global_step": 481791, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0824155807495117, "global_step": 481792, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9373712539672852, "global_step": 481793, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.036381483078003, "global_step": 481794, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0673978328704834, "global_step": 481795, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1443746089935303, "global_step": 481796, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0290520191192627, "global_step": 481797, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0872182846069336, "global_step": 481798, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.000419855117798, "global_step": 481799, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0496163368225098, "global_step": 481800, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.041710138320923, "global_step": 481801, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.035604953765869, "global_step": 481802, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9874215126037598, "global_step": 481803, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9782178401947021, "global_step": 481804, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.124969720840454, "global_step": 481805, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0790741443634033, "global_step": 481806, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0882582664489746, "global_step": 481807, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0169894695281982, "global_step": 481808, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0613372325897217, "global_step": 481809, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.08137583732605, "global_step": 481810, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1295175552368164, "global_step": 481811, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0510988235473633, "global_step": 481812, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0634496212005615, "global_step": 481813, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.060807943344116, "global_step": 481814, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9640194177627563, "global_step": 481815, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.105865001678467, "global_step": 481816, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.056394338607788, "global_step": 481817, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.127248764038086, "global_step": 481818, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0504589080810547, "global_step": 481819, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0400004386901855, "global_step": 481820, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0105183124542236, "global_step": 481821, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0491504669189453, "global_step": 481822, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.150359869003296, "global_step": 481823, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1467840671539307, "global_step": 481824, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.051159381866455, "global_step": 481825, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0307693481445312, "global_step": 481826, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0413765907287598, "global_step": 481827, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0865426063537598, "global_step": 481828, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0373919010162354, "global_step": 481829, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.131216287612915, "global_step": 481830, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.083064079284668, "global_step": 481831, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.118903875350952, "global_step": 481832, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0459892749786377, "global_step": 481833, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0895557403564453, "global_step": 481834, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0481443405151367, "global_step": 481835, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9366570711135864, "global_step": 481836, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0421760082244873, "global_step": 481837, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0695958137512207, "global_step": 481838, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0803372859954834, "global_step": 481839, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0332553386688232, "global_step": 481840, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0519845485687256, "global_step": 481841, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.028636932373047, "global_step": 481842, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.097266912460327, "global_step": 481843, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.054025173187256, "global_step": 481844, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1348493099212646, "global_step": 481845, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1046903133392334, "global_step": 481846, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.060570001602173, "global_step": 481847, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.048964738845825, "global_step": 481848, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.014017343521118, "global_step": 481849, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0813417434692383, "global_step": 481850, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0419938564300537, "global_step": 481851, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1541812419891357, "global_step": 481852, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.101616382598877, "global_step": 481853, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.04537296295166, "global_step": 481854, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.113273859024048, "global_step": 481855, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0117127895355225, "global_step": 481856, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0877208709716797, "global_step": 481857, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1624574661254883, "global_step": 481858, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.038341760635376, "global_step": 481859, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9981968402862549, "global_step": 481860, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.085921049118042, "global_step": 481861, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.054534435272217, "global_step": 481862, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0211031436920166, "global_step": 481863, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.035158634185791, "global_step": 481864, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.110585927963257, "global_step": 481865, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0597598552703857, "global_step": 481866, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.041017770767212, "global_step": 481867, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.088289737701416, "global_step": 481868, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1152210235595703, "global_step": 481869, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9553678035736084, "global_step": 481870, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9828757047653198, "global_step": 481871, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.068373203277588, "global_step": 481872, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.083827495574951, "global_step": 481873, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.069257974624634, "global_step": 481874, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.065317153930664, "global_step": 481875, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.129601001739502, "global_step": 481876, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0320639610290527, "global_step": 481877, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.039689779281616, "global_step": 481878, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0452370643615723, "global_step": 481879, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.039111614227295, "global_step": 481880, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.039598226547241, "global_step": 481881, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.004572868347168, "global_step": 481882, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.024029493331909, "global_step": 481883, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.025688409805298, "global_step": 481884, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.071772575378418, "global_step": 481885, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0830583572387695, "global_step": 481886, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0547423362731934, "global_step": 481887, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0246872901916504, "global_step": 481888, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.998453974723816, "global_step": 481889, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.056476593017578, "global_step": 481890, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0174994468688965, "global_step": 481891, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9809998273849487, "global_step": 481892, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.978963851928711, "global_step": 481893, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1215643882751465, "global_step": 481894, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9686763286590576, "global_step": 481895, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0555336475372314, "global_step": 481896, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0826830863952637, "global_step": 481897, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0633158683776855, "global_step": 481898, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.059248208999634, "global_step": 481899, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9529333114624023, "global_step": 481900, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1251418590545654, "global_step": 481901, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.014610767364502, "global_step": 481902, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1053640842437744, "global_step": 481903, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0941519737243652, "global_step": 481904, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.072077989578247, "global_step": 481905, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.056269884109497, "global_step": 481906, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0012574195861816, "global_step": 481907, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.983903169631958, "global_step": 481908, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.080768585205078, "global_step": 481909, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9966943264007568, "global_step": 481910, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.049049139022827, "global_step": 481911, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0471885204315186, "global_step": 481912, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1278865337371826, "global_step": 481913, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0994765758514404, "global_step": 481914, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0472257137298584, "global_step": 481915, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0727856159210205, "global_step": 481916, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.2031805515289307, "global_step": 481917, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.129124164581299, "global_step": 481918, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0698022842407227, "global_step": 481919, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.986931562423706, "global_step": 481920, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0085012912750244, "global_step": 481921, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1197543144226074, "global_step": 481922, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0741770267486572, "global_step": 481923, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0529234409332275, "global_step": 481924, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0748729705810547, "global_step": 481925, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0492959022521973, "global_step": 481926, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.013000726699829, "global_step": 481927, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0505216121673584, "global_step": 481928, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0400900840759277, "global_step": 481929, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0684566497802734, "global_step": 481930, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1197633743286133, "global_step": 481931, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0074656009674072, "global_step": 481932, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0266013145446777, "global_step": 481933, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.995189905166626, "global_step": 481934, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.988385558128357, "global_step": 481935, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.079982042312622, "global_step": 481936, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0668764114379883, "global_step": 481937, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9755604267120361, "global_step": 481938, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9946995973587036, "global_step": 481939, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.052562952041626, "global_step": 481940, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.086155652999878, "global_step": 481941, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.956166386604309, "global_step": 481942, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0674943923950195, "global_step": 481943, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0444436073303223, "global_step": 481944, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0229835510253906, "global_step": 481945, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.963628888130188, "global_step": 481946, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0544795989990234, "global_step": 481947, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0553369522094727, "global_step": 481948, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.090430974960327, "global_step": 481949, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9960968494415283, "global_step": 481950, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.11311411857605, "global_step": 481951, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1596739292144775, "global_step": 481952, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.122525691986084, "global_step": 481953, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0838680267333984, "global_step": 481954, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.049945116043091, "global_step": 481955, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.041980266571045, "global_step": 481956, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0787224769592285, "global_step": 481957, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0203192234039307, "global_step": 481958, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.029573440551758, "global_step": 481959, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0484297275543213, "global_step": 481960, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.05570912361145, "global_step": 481961, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0796031951904297, "global_step": 481962, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0529327392578125, "global_step": 481963, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.139575242996216, "global_step": 481964, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9910887479782104, "global_step": 481965, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.026190996170044, "global_step": 481966, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.033292055130005, "global_step": 481967, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0404906272888184, "global_step": 481968, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.005617141723633, "global_step": 481969, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9655218124389648, "global_step": 481970, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0540122985839844, "global_step": 481971, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0202064514160156, "global_step": 481972, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0869383811950684, "global_step": 481973, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1049699783325195, "global_step": 481974, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.077354669570923, "global_step": 481975, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.076674699783325, "global_step": 481976, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0248115062713623, "global_step": 481977, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.087395429611206, "global_step": 481978, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.074871063232422, "global_step": 481979, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1375479698181152, "global_step": 481980, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1458184719085693, "global_step": 481981, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9577161073684692, "global_step": 481982, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1025643348693848, "global_step": 481983, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0111591815948486, "global_step": 481984, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0415260791778564, "global_step": 481985, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.000417947769165, "global_step": 481986, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.03609561920166, "global_step": 481987, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.041358232498169, "global_step": 481988, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0215399265289307, "global_step": 481989, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.062098503112793, "global_step": 481990, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9989986419677734, "global_step": 481991, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0485098361968994, "global_step": 481992, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.107369899749756, "global_step": 481993, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0704400539398193, "global_step": 481994, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0672976970672607, "global_step": 481995, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0398573875427246, "global_step": 481996, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.111670732498169, "global_step": 481997, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.007145643234253, "global_step": 481998, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0776970386505127, "global_step": 481999, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1047685146331787, "global_step": 482000, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0182697772979736, "global_step": 482001, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.024686098098755, "global_step": 482002, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1096079349517822, "global_step": 482003, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.088611602783203, "global_step": 482004, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.131777286529541, "global_step": 482005, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1023013591766357, "global_step": 482006, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.996630311012268, "global_step": 482007, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.105139970779419, "global_step": 482008, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0430376529693604, "global_step": 482009, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.054391860961914, "global_step": 482010, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1337530612945557, "global_step": 482011, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0576541423797607, "global_step": 482012, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0615625381469727, "global_step": 482013, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.025839328765869, "global_step": 482014, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0664989948272705, "global_step": 482015, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.012737512588501, "global_step": 482016, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.983410358428955, "global_step": 482017, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0978198051452637, "global_step": 482018, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1055994033813477, "global_step": 482019, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1424856185913086, "global_step": 482020, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0778050422668457, "global_step": 482021, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.999422550201416, "global_step": 482022, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.089911460876465, "global_step": 482023, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9974368810653687, "global_step": 482024, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.062180995941162, "global_step": 482025, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.028822898864746, "global_step": 482026, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.08282208442688, "global_step": 482027, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0547032356262207, "global_step": 482028, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0649759769439697, "global_step": 482029, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.120220899581909, "global_step": 482030, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9915049076080322, "global_step": 482031, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.053126335144043, "global_step": 482032, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.091102361679077, "global_step": 482033, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.100846290588379, "global_step": 482034, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0301737785339355, "global_step": 482035, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0534732341766357, "global_step": 482036, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.053424119949341, "global_step": 482037, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.134385108947754, "global_step": 482038, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0855331420898438, "global_step": 482039, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0271830558776855, "global_step": 482040, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.059141159057617, "global_step": 482041, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1521732807159424, "global_step": 482042, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.147212028503418, "global_step": 482043, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0830001831054688, "global_step": 482044, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.070253610610962, "global_step": 482045, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0747573375701904, "global_step": 482046, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.106156826019287, "global_step": 482047, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0583086013793945, "global_step": 482048, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1544744968414307, "global_step": 482049, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1079094409942627, "global_step": 482050, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.123657703399658, "global_step": 482051, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0486443042755127, "global_step": 482052, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.011740207672119, "global_step": 482053, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.096778631210327, "global_step": 482054, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.024047374725342, "global_step": 482055, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0387301445007324, "global_step": 482056, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.107789993286133, "global_step": 482057, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1573410034179688, "global_step": 482058, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0337581634521484, "global_step": 482059, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.027512550354004, "global_step": 482060, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.976574420928955, "global_step": 482061, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0517077445983887, "global_step": 482062, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0774922370910645, "global_step": 482063, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0265157222747803, "global_step": 482064, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.01979923248291, "global_step": 482065, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.10418701171875, "global_step": 482066, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.102198600769043, "global_step": 482067, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.067099094390869, "global_step": 482068, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9595985412597656, "global_step": 482069, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0138416290283203, "global_step": 482070, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.041222095489502, "global_step": 482071, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0481202602386475, "global_step": 482072, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.086230754852295, "global_step": 482073, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0100200176239014, "global_step": 482074, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9899113178253174, "global_step": 482075, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.082270383834839, "global_step": 482076, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.997925043106079, "global_step": 482077, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.044623613357544, "global_step": 482078, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.113542079925537, "global_step": 482079, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0532233715057373, "global_step": 482080, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9909374713897705, "global_step": 482081, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0417048931121826, "global_step": 482082, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1205179691314697, "global_step": 482083, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.97395658493042, "global_step": 482084, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.01584529876709, "global_step": 482085, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0449726581573486, "global_step": 482086, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1280410289764404, "global_step": 482087, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.988724708557129, "global_step": 482088, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.074925184249878, "global_step": 482089, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.105567216873169, "global_step": 482090, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0244414806365967, "global_step": 482091, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0953335762023926, "global_step": 482092, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.057462453842163, "global_step": 482093, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0528783798217773, "global_step": 482094, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.102760076522827, "global_step": 482095, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.024466037750244, "global_step": 482096, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9734174013137817, "global_step": 482097, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.089683771133423, "global_step": 482098, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0287301540374756, "global_step": 482099, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9413820505142212, "global_step": 482100, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1008214950561523, "global_step": 482101, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0362744331359863, "global_step": 482102, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0829532146453857, "global_step": 482103, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.972782850265503, "global_step": 482104, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0642640590667725, "global_step": 482105, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1225404739379883, "global_step": 482106, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.034183979034424, "global_step": 482107, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0063588619232178, "global_step": 482108, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0847060680389404, "global_step": 482109, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.155076026916504, "global_step": 482110, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.057081699371338, "global_step": 482111, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.032040596008301, "global_step": 482112, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.055082082748413, "global_step": 482113, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1668004989624023, "global_step": 482114, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.120692729949951, "global_step": 482115, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0742347240448, "global_step": 482116, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1321754455566406, "global_step": 482117, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.019258499145508, "global_step": 482118, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0794713497161865, "global_step": 482119, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1023919582366943, "global_step": 482120, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.080585241317749, "global_step": 482121, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.146960496902466, "global_step": 482122, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.060228109359741, "global_step": 482123, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0960958003997803, "global_step": 482124, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0633883476257324, "global_step": 482125, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0328056812286377, "global_step": 482126, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.039748191833496, "global_step": 482127, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0367891788482666, "global_step": 482128, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0585107803344727, "global_step": 482129, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0106453895568848, "global_step": 482130, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9942195415496826, "global_step": 482131, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.011892080307007, "global_step": 482132, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1097655296325684, "global_step": 482133, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.002729892730713, "global_step": 482134, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9985517263412476, "global_step": 482135, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.059387683868408, "global_step": 482136, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0724868774414062, "global_step": 482137, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.075704336166382, "global_step": 482138, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0830183029174805, "global_step": 482139, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0800724029541016, "global_step": 482140, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1032803058624268, "global_step": 482141, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.141868829727173, "global_step": 482142, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0772478580474854, "global_step": 482143, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.118476390838623, "global_step": 482144, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1619932651519775, "global_step": 482145, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0722663402557373, "global_step": 482146, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.031944513320923, "global_step": 482147, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.06174635887146, "global_step": 482148, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.2003958225250244, "global_step": 482149, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9956976175308228, "global_step": 482150, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9982284307479858, "global_step": 482151, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.068199634552002, "global_step": 482152, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0755677223205566, "global_step": 482153, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.053043842315674, "global_step": 482154, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0811898708343506, "global_step": 482155, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0426878929138184, "global_step": 482156, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.015089988708496, "global_step": 482157, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0482988357543945, "global_step": 482158, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0153768062591553, "global_step": 482159, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.000701427459717, "global_step": 482160, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.057661533355713, "global_step": 482161, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9893779754638672, "global_step": 482162, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.025786876678467, "global_step": 482163, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0999326705932617, "global_step": 482164, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1662824153900146, "global_step": 482165, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.038156032562256, "global_step": 482166, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0210204124450684, "global_step": 482167, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0813326835632324, "global_step": 482168, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9707343578338623, "global_step": 482169, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.047980308532715, "global_step": 482170, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.091916561126709, "global_step": 482171, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0799014568328857, "global_step": 482172, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0023701190948486, "global_step": 482173, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0403802394866943, "global_step": 482174, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0567243099212646, "global_step": 482175, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.019390344619751, "global_step": 482176, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0570807456970215, "global_step": 482177, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0108461380004883, "global_step": 482178, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1277012825012207, "global_step": 482179, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.05448842048645, "global_step": 482180, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1094226837158203, "global_step": 482181, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.083749294281006, "global_step": 482182, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.114844560623169, "global_step": 482183, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.065507411956787, "global_step": 482184, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0260980129241943, "global_step": 482185, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1263792514801025, "global_step": 482186, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0288937091827393, "global_step": 482187, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9965691566467285, "global_step": 482188, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.100562572479248, "global_step": 482189, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1365318298339844, "global_step": 482190, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0793299674987793, "global_step": 482191, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.131061315536499, "global_step": 482192, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0496206283569336, "global_step": 482193, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.048985481262207, "global_step": 482194, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9629061222076416, "global_step": 482195, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.089977264404297, "global_step": 482196, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1501801013946533, "global_step": 482197, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.070204734802246, "global_step": 482198, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.00669527053833, "global_step": 482199, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.008798360824585, "global_step": 482200, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0255982875823975, "global_step": 482201, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.034857749938965, "global_step": 482202, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0688161849975586, "global_step": 482203, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9722135066986084, "global_step": 482204, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9947731494903564, "global_step": 482205, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.107809066772461, "global_step": 482206, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0802557468414307, "global_step": 482207, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9977614879608154, "global_step": 482208, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0181326866149902, "global_step": 482209, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1066977977752686, "global_step": 482210, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0682215690612793, "global_step": 482211, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.203352212905884, "global_step": 482212, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.099001884460449, "global_step": 482213, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.012660503387451, "global_step": 482214, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.072230100631714, "global_step": 482215, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0436458587646484, "global_step": 482216, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9936847686767578, "global_step": 482217, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.056403636932373, "global_step": 482218, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.017439603805542, "global_step": 482219, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.007020950317383, "global_step": 482220, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0260708332061768, "global_step": 482221, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.113469123840332, "global_step": 482222, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.031355381011963, "global_step": 482223, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.042607307434082, "global_step": 482224, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0501091480255127, "global_step": 482225, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9804002046585083, "global_step": 482226, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.042999505996704, "global_step": 482227, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.035289764404297, "global_step": 482228, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0366508960723877, "global_step": 482229, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.114126205444336, "global_step": 482230, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.095635175704956, "global_step": 482231, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0641064643859863, "global_step": 482232, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1665523052215576, "global_step": 482233, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1015381813049316, "global_step": 482234, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.035930633544922, "global_step": 482235, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0452661514282227, "global_step": 482236, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0990655422210693, "global_step": 482237, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.08318829536438, "global_step": 482238, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.999932050704956, "global_step": 482239, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.970194935798645, "global_step": 482240, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.105421781539917, "global_step": 482241, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0070853233337402, "global_step": 482242, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0198943614959717, "global_step": 482243, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.12541127204895, "global_step": 482244, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0587003231048584, "global_step": 482245, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.016982316970825, "global_step": 482246, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0448737144470215, "global_step": 482247, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0471606254577637, "global_step": 482248, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.024406671524048, "global_step": 482249, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9936308860778809, "global_step": 482250, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1159169673919678, "global_step": 482251, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0108628273010254, "global_step": 482252, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0286455154418945, "global_step": 482253, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0663580894470215, "global_step": 482254, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.102503538131714, "global_step": 482255, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0862112045288086, "global_step": 482256, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0440831184387207, "global_step": 482257, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9688563346862793, "global_step": 482258, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0470547676086426, "global_step": 482259, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1835155487060547, "global_step": 482260, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.006157159805298, "global_step": 482261, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9882347583770752, "global_step": 482262, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.128795623779297, "global_step": 482263, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9802844524383545, "global_step": 482264, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.104245185852051, "global_step": 482265, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0329086780548096, "global_step": 482266, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1372296810150146, "global_step": 482267, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1202640533447266, "global_step": 482268, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.046663522720337, "global_step": 482269, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0073442459106445, "global_step": 482270, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.025538444519043, "global_step": 482271, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0044138431549072, "global_step": 482272, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.978285789489746, "global_step": 482273, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.031435966491699, "global_step": 482274, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.00697922706604, "global_step": 482275, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.016775131225586, "global_step": 482276, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.001570224761963, "global_step": 482277, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.020942211151123, "global_step": 482278, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0291805267333984, "global_step": 482279, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.136685848236084, "global_step": 482280, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.144615411758423, "global_step": 482281, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0212862491607666, "global_step": 482282, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0540030002593994, "global_step": 482283, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0916662216186523, "global_step": 482284, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.049084424972534, "global_step": 482285, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.066822052001953, "global_step": 482286, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.00150203704834, "global_step": 482287, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.072709798812866, "global_step": 482288, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1265709400177, "global_step": 482289, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.017072916030884, "global_step": 482290, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9840248823165894, "global_step": 482291, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0629405975341797, "global_step": 482292, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.075439929962158, "global_step": 482293, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.953586459159851, "global_step": 482294, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1482126712799072, "global_step": 482295, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1455650329589844, "global_step": 482296, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0868730545043945, "global_step": 482297, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0415894985198975, "global_step": 482298, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0712339878082275, "global_step": 482299, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0842230319976807, "global_step": 482300, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1008200645446777, "global_step": 482301, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.123607635498047, "global_step": 482302, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.076629877090454, "global_step": 482303, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.149702787399292, "global_step": 482304, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0366945266723633, "global_step": 482305, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0871565341949463, "global_step": 482306, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.127697706222534, "global_step": 482307, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9958505630493164, "global_step": 482308, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0148348808288574, "global_step": 482309, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.989914894104004, "global_step": 482310, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.966991901397705, "global_step": 482311, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0303919315338135, "global_step": 482312, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.224451780319214, "global_step": 482313, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0335817337036133, "global_step": 482314, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1260366439819336, "global_step": 482315, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0577845573425293, "global_step": 482316, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9970029592514038, "global_step": 482317, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0423946380615234, "global_step": 482318, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1325554847717285, "global_step": 482319, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.045476198196411, "global_step": 482320, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9173084497451782, "global_step": 482321, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.057945966720581, "global_step": 482322, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.129631280899048, "global_step": 482323, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0994768142700195, "global_step": 482324, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.068507194519043, "global_step": 482325, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.082825183868408, "global_step": 482326, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.105144739151001, "global_step": 482327, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1036524772644043, "global_step": 482328, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.027811050415039, "global_step": 482329, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1337528228759766, "global_step": 482330, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.033336877822876, "global_step": 482331, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.07326078414917, "global_step": 482332, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0735225677490234, "global_step": 482333, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.056946039199829, "global_step": 482334, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0647189617156982, "global_step": 482335, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.00827693939209, "global_step": 482336, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0557034015655518, "global_step": 482337, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.093104600906372, "global_step": 482338, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.079315662384033, "global_step": 482339, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.06378173828125, "global_step": 482340, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0426037311553955, "global_step": 482341, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0113911628723145, "global_step": 482342, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0665509700775146, "global_step": 482343, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0791568756103516, "global_step": 482344, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.014770746231079, "global_step": 482345, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.110729932785034, "global_step": 482346, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.049877405166626, "global_step": 482347, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.09307861328125, "global_step": 482348, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.100229501724243, "global_step": 482349, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.075448751449585, "global_step": 482350, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.075456380844116, "global_step": 482351, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.131300687789917, "global_step": 482352, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0207269191741943, "global_step": 482353, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.060302495956421, "global_step": 482354, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1003198623657227, "global_step": 482355, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0080177783966064, "global_step": 482356, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0202696323394775, "global_step": 482357, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.023486852645874, "global_step": 482358, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0203237533569336, "global_step": 482359, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.131305456161499, "global_step": 482360, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9873822927474976, "global_step": 482361, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0837903022766113, "global_step": 482362, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1155858039855957, "global_step": 482363, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0176632404327393, "global_step": 482364, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0837604999542236, "global_step": 482365, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0764689445495605, "global_step": 482366, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1189846992492676, "global_step": 482367, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1223561763763428, "global_step": 482368, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.011443853378296, "global_step": 482369, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0996015071868896, "global_step": 482370, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0837490558624268, "global_step": 482371, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.031289577484131, "global_step": 482372, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.148383140563965, "global_step": 482373, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0290513038635254, "global_step": 482374, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.060750722885132, "global_step": 482375, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.042522430419922, "global_step": 482376, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0783472061157227, "global_step": 482377, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9444971084594727, "global_step": 482378, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.099287271499634, "global_step": 482379, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.069531202316284, "global_step": 482380, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1220264434814453, "global_step": 482381, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0430195331573486, "global_step": 482382, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.060168504714966, "global_step": 482383, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0591909885406494, "global_step": 482384, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0822479724884033, "global_step": 482385, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0864245891571045, "global_step": 482386, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.03791880607605, "global_step": 482387, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.147265911102295, "global_step": 482388, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9811440706253052, "global_step": 482389, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1294445991516113, "global_step": 482390, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0687975883483887, "global_step": 482391, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9934346675872803, "global_step": 482392, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9622085094451904, "global_step": 482393, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.049368381500244, "global_step": 482394, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0886447429656982, "global_step": 482395, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.140603542327881, "global_step": 482396, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.063135862350464, "global_step": 482397, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.137608766555786, "global_step": 482398, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.091571569442749, "global_step": 482399, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0438945293426514, "global_step": 482400, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.102447032928467, "global_step": 482401, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.081376075744629, "global_step": 482402, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.060990333557129, "global_step": 482403, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.065434694290161, "global_step": 482404, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0960891246795654, "global_step": 482405, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9929908514022827, "global_step": 482406, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.077824354171753, "global_step": 482407, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.054328203201294, "global_step": 482408, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.04347562789917, "global_step": 482409, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0182740688323975, "global_step": 482410, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0347368717193604, "global_step": 482411, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1232261657714844, "global_step": 482412, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0325822830200195, "global_step": 482413, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.070266008377075, "global_step": 482414, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0831122398376465, "global_step": 482415, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.084665060043335, "global_step": 482416, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.100743532180786, "global_step": 482417, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.081815481185913, "global_step": 482418, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.111144781112671, "global_step": 482419, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.11527681350708, "global_step": 482420, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.092442035675049, "global_step": 482421, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1180152893066406, "global_step": 482422, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.097576141357422, "global_step": 482423, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9876253604888916, "global_step": 482424, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.119023561477661, "global_step": 482425, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0474953651428223, "global_step": 482426, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.011190414428711, "global_step": 482427, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0878796577453613, "global_step": 482428, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1233558654785156, "global_step": 482429, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.023268222808838, "global_step": 482430, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0340933799743652, "global_step": 482431, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.95626699924469, "global_step": 482432, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.096522092819214, "global_step": 482433, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.084683895111084, "global_step": 482434, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0500972270965576, "global_step": 482435, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.123501777648926, "global_step": 482436, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1183881759643555, "global_step": 482437, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.096686601638794, "global_step": 482438, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0270795822143555, "global_step": 482439, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.069380760192871, "global_step": 482440, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1016321182250977, "global_step": 482441, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.079881191253662, "global_step": 482442, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9713813066482544, "global_step": 482443, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9792506694793701, "global_step": 482444, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.027115821838379, "global_step": 482445, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.158949136734009, "global_step": 482446, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0935301780700684, "global_step": 482447, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0083630084991455, "global_step": 482448, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.048274517059326, "global_step": 482449, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0961811542510986, "global_step": 482450, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.079824686050415, "global_step": 482451, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.099059581756592, "global_step": 482452, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.026776075363159, "global_step": 482453, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9589617252349854, "global_step": 482454, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.004056453704834, "global_step": 482455, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0824625492095947, "global_step": 482456, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9981553554534912, "global_step": 482457, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.141632556915283, "global_step": 482458, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.004551410675049, "global_step": 482459, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.093356132507324, "global_step": 482460, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0393686294555664, "global_step": 482461, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0050742626190186, "global_step": 482462, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1392858028411865, "global_step": 482463, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1273183822631836, "global_step": 482464, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.124671697616577, "global_step": 482465, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.090125799179077, "global_step": 482466, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0477631092071533, "global_step": 482467, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.035796880722046, "global_step": 482468, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0297064781188965, "global_step": 482469, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1245830059051514, "global_step": 482470, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.022216558456421, "global_step": 482471, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9657373428344727, "global_step": 482472, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.059015989303589, "global_step": 482473, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0534632205963135, "global_step": 482474, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.048813819885254, "global_step": 482475, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1007680892944336, "global_step": 482476, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9486461877822876, "global_step": 482477, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.23569655418396, "global_step": 482478, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.113574981689453, "global_step": 482479, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0337586402893066, "global_step": 482480, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.003044366836548, "global_step": 482481, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0471973419189453, "global_step": 482482, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0448038578033447, "global_step": 482483, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1238186359405518, "global_step": 482484, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.08272123336792, "global_step": 482485, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.116037130355835, "global_step": 482486, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0861704349517822, "global_step": 482487, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0770299434661865, "global_step": 482488, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.050365924835205, "global_step": 482489, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0080084800720215, "global_step": 482490, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0714151859283447, "global_step": 482491, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.035750389099121, "global_step": 482492, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0591988563537598, "global_step": 482493, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0162665843963623, "global_step": 482494, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0461137294769287, "global_step": 482495, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9735925197601318, "global_step": 482496, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.02101469039917, "global_step": 482497, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0640347003936768, "global_step": 482498, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9851789474487305, "global_step": 482499, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.164975166320801, "global_step": 482500, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.033672571182251, "global_step": 482501, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.024049997329712, "global_step": 482502, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.043958902359009, "global_step": 482503, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.163248300552368, "global_step": 482504, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0479896068573, "global_step": 482505, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0737953186035156, "global_step": 482506, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0278491973876953, "global_step": 482507, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.09352970123291, "global_step": 482508, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.09506893157959, "global_step": 482509, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0440917015075684, "global_step": 482510, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1117072105407715, "global_step": 482511, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1762173175811768, "global_step": 482512, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.085303783416748, "global_step": 482513, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.02832293510437, "global_step": 482514, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.114931106567383, "global_step": 482515, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0152485370635986, "global_step": 482516, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1488912105560303, "global_step": 482517, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.058669090270996, "global_step": 482518, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0137269496917725, "global_step": 482519, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0621421337127686, "global_step": 482520, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.08795428276062, "global_step": 482521, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1425111293792725, "global_step": 482522, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.050485849380493, "global_step": 482523, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.029113531112671, "global_step": 482524, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0586509704589844, "global_step": 482525, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0425140857696533, "global_step": 482526, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0080652236938477, "global_step": 482527, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.108548879623413, "global_step": 482528, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0194976329803467, "global_step": 482529, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.032642126083374, "global_step": 482530, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.049747943878174, "global_step": 482531, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0793445110321045, "global_step": 482532, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.113804578781128, "global_step": 482533, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0573151111602783, "global_step": 482534, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.083662509918213, "global_step": 482535, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0238587856292725, "global_step": 482536, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.044088125228882, "global_step": 482537, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.094700336456299, "global_step": 482538, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1059327125549316, "global_step": 482539, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.143203020095825, "global_step": 482540, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0263895988464355, "global_step": 482541, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.081193447113037, "global_step": 482542, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.17303204536438, "global_step": 482543, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0264105796813965, "global_step": 482544, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1150689125061035, "global_step": 482545, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0974011421203613, "global_step": 482546, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0489888191223145, "global_step": 482547, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.154326915740967, "global_step": 482548, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.078247308731079, "global_step": 482549, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1016845703125, "global_step": 482550, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0825753211975098, "global_step": 482551, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.030449867248535, "global_step": 482552, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.087500810623169, "global_step": 482553, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0847203731536865, "global_step": 482554, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0868773460388184, "global_step": 482555, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1564862728118896, "global_step": 482556, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9859355688095093, "global_step": 482557, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1454882621765137, "global_step": 482558, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0449235439300537, "global_step": 482559, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1090447902679443, "global_step": 482560, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0893540382385254, "global_step": 482561, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0719265937805176, "global_step": 482562, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.176217555999756, "global_step": 482563, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0483710765838623, "global_step": 482564, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.078772783279419, "global_step": 482565, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.072089672088623, "global_step": 482566, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0654385089874268, "global_step": 482567, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9910895824432373, "global_step": 482568, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0667660236358643, "global_step": 482569, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0863285064697266, "global_step": 482570, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.044713258743286, "global_step": 482571, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0411994457244873, "global_step": 482572, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0247671604156494, "global_step": 482573, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0539088249206543, "global_step": 482574, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.030804395675659, "global_step": 482575, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1224710941314697, "global_step": 482576, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.039048910140991, "global_step": 482577, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0162911415100098, "global_step": 482578, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1203131675720215, "global_step": 482579, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0702648162841797, "global_step": 482580, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1442723274230957, "global_step": 482581, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0544590950012207, "global_step": 482582, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1026389598846436, "global_step": 482583, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0933048725128174, "global_step": 482584, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0438969135284424, "global_step": 482585, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0373430252075195, "global_step": 482586, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.089953660964966, "global_step": 482587, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.07027268409729, "global_step": 482588, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0745155811309814, "global_step": 482589, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.031998872756958, "global_step": 482590, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1338441371917725, "global_step": 482591, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9912109375, "global_step": 482592, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1040451526641846, "global_step": 482593, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.07643723487854, "global_step": 482594, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.080177068710327, "global_step": 482595, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.075791358947754, "global_step": 482596, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0566811561584473, "global_step": 482597, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1159021854400635, "global_step": 482598, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9842113256454468, "global_step": 482599, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.075575590133667, "global_step": 482600, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0934817790985107, "global_step": 482601, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9976063966751099, "global_step": 482602, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1408376693725586, "global_step": 482603, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0487983226776123, "global_step": 482604, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.064936637878418, "global_step": 482605, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0304713249206543, "global_step": 482606, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0611233711242676, "global_step": 482607, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0435945987701416, "global_step": 482608, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1408932209014893, "global_step": 482609, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0864334106445312, "global_step": 482610, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.102440118789673, "global_step": 482611, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1326334476470947, "global_step": 482612, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0955147743225098, "global_step": 482613, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0726723670959473, "global_step": 482614, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9823631048202515, "global_step": 482615, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.017728090286255, "global_step": 482616, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0954501628875732, "global_step": 482617, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1609973907470703, "global_step": 482618, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.071125030517578, "global_step": 482619, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0187363624572754, "global_step": 482620, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0731687545776367, "global_step": 482621, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9999547004699707, "global_step": 482622, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.071566343307495, "global_step": 482623, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.960976481437683, "global_step": 482624, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1058707237243652, "global_step": 482625, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.00419545173645, "global_step": 482626, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.071199655532837, "global_step": 482627, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0370094776153564, "global_step": 482628, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.072270154953003, "global_step": 482629, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.09712290763855, "global_step": 482630, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0090765953063965, "global_step": 482631, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.166290521621704, "global_step": 482632, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.971558928489685, "global_step": 482633, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0589702129364014, "global_step": 482634, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9477206468582153, "global_step": 482635, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1102399826049805, "global_step": 482636, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.059452772140503, "global_step": 482637, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.102513074874878, "global_step": 482638, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9692479372024536, "global_step": 482639, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0088894367218018, "global_step": 482640, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1049673557281494, "global_step": 482641, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0649194717407227, "global_step": 482642, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0840752124786377, "global_step": 482643, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1281332969665527, "global_step": 482644, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.047196865081787, "global_step": 482645, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0365540981292725, "global_step": 482646, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0319814682006836, "global_step": 482647, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0814225673675537, "global_step": 482648, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1164498329162598, "global_step": 482649, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.097348690032959, "global_step": 482650, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.077512741088867, "global_step": 482651, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0914366245269775, "global_step": 482652, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0600569248199463, "global_step": 482653, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.100717782974243, "global_step": 482654, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.148080587387085, "global_step": 482655, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.139874219894409, "global_step": 482656, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.081169366836548, "global_step": 482657, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.078298330307007, "global_step": 482658, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0713918209075928, "global_step": 482659, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.074215888977051, "global_step": 482660, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1111443042755127, "global_step": 482661, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.074056625366211, "global_step": 482662, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.050863027572632, "global_step": 482663, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9387372732162476, "global_step": 482664, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0804038047790527, "global_step": 482665, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1505632400512695, "global_step": 482666, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0761401653289795, "global_step": 482667, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9510159492492676, "global_step": 482668, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9305427074432373, "global_step": 482669, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0192952156066895, "global_step": 482670, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.098569631576538, "global_step": 482671, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1106619834899902, "global_step": 482672, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.184969425201416, "global_step": 482673, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.087536573410034, "global_step": 482674, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0405614376068115, "global_step": 482675, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.985490322113037, "global_step": 482676, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0782577991485596, "global_step": 482677, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9534320831298828, "global_step": 482678, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0263843536376953, "global_step": 482679, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0545785427093506, "global_step": 482680, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.067523717880249, "global_step": 482681, "epoch": 847, "lr": 5e-05}
{"train_loss": 1.9812349081039429, "global_step": 482682, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.027874708175659, "global_step": 482683, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.074425220489502, "global_step": 482684, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.08054256439209, "global_step": 482685, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.04819917678833, "global_step": 482686, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1190526485443115, "global_step": 482687, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0222952365875244, "global_step": 482688, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0102598667144775, "global_step": 482689, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1085808277130127, "global_step": 482690, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.1051790714263916, "global_step": 482691, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0382227897644043, "global_step": 482692, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.090394973754883, "global_step": 482693, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.0610532760620117, "global_step": 482694, "epoch": 847, "lr": 5e-05}
{"train_loss": 2.092186450958252, "global_step": 482695, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.010171890258789, "global_step": 482696, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.109004497528076, "global_step": 482697, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.8763153553009033, "global_step": 482698, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0126073360443115, "global_step": 482699, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.060480833053589, "global_step": 482700, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.058673858642578, "global_step": 482701, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9716323614120483, "global_step": 482702, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0235788822174072, "global_step": 482703, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1083550453186035, "global_step": 482704, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0612306594848633, "global_step": 482705, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0346691608428955, "global_step": 482706, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0710980892181396, "global_step": 482707, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1437859535217285, "global_step": 482708, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.119840383529663, "global_step": 482709, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0479319095611572, "global_step": 482710, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0185530185699463, "global_step": 482711, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.05879282951355, "global_step": 482712, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1143107414245605, "global_step": 482713, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.091284990310669, "global_step": 482714, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.021839141845703, "global_step": 482715, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.072673797607422, "global_step": 482716, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1064250469207764, "global_step": 482717, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1435914039611816, "global_step": 482718, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.003979206085205, "global_step": 482719, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0871877670288086, "global_step": 482720, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.115161895751953, "global_step": 482721, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0580739974975586, "global_step": 482722, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1036272048950195, "global_step": 482723, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.063506841659546, "global_step": 482724, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.065021514892578, "global_step": 482725, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0370514392852783, "global_step": 482726, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.011669635772705, "global_step": 482727, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0480716228485107, "global_step": 482728, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9587575197219849, "global_step": 482729, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.08957576751709, "global_step": 482730, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1114487648010254, "global_step": 482731, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9939581155776978, "global_step": 482732, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.050312042236328, "global_step": 482733, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0488507747650146, "global_step": 482734, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0812337398529053, "global_step": 482735, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9912762641906738, "global_step": 482736, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0353035926818848, "global_step": 482737, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0349059104919434, "global_step": 482738, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1022274494171143, "global_step": 482739, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0424017906188965, "global_step": 482740, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.118370294570923, "global_step": 482741, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.140011787414551, "global_step": 482742, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.118680715560913, "global_step": 482743, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.99953293800354, "global_step": 482744, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.994004487991333, "global_step": 482745, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0480682849884033, "global_step": 482746, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.031337022781372, "global_step": 482747, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9967761039733887, "global_step": 482748, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9989242553710938, "global_step": 482749, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0325775146484375, "global_step": 482750, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0551841259002686, "global_step": 482751, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0997507572174072, "global_step": 482752, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0571603775024414, "global_step": 482753, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.960883378982544, "global_step": 482754, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.04744291305542, "global_step": 482755, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0222113132476807, "global_step": 482756, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9846491813659668, "global_step": 482757, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0403432846069336, "global_step": 482758, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9918632507324219, "global_step": 482759, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.052161693572998, "global_step": 482760, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.047523021697998, "global_step": 482761, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.096078634262085, "global_step": 482762, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0081803798675537, "global_step": 482763, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1593282222747803, "global_step": 482764, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0486807823181152, "global_step": 482765, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.098454475402832, "global_step": 482766, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.055065393447876, "global_step": 482767, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1093592643737793, "global_step": 482768, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0855765342712402, "global_step": 482769, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.048276424407959, "global_step": 482770, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.067913770675659, "global_step": 482771, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.157992362976074, "global_step": 482772, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0089330673217773, "global_step": 482773, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0568392276763916, "global_step": 482774, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1059234142303467, "global_step": 482775, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.045403242111206, "global_step": 482776, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9869285821914673, "global_step": 482777, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9320120811462402, "global_step": 482778, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1295526027679443, "global_step": 482779, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0477166175842285, "global_step": 482780, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1166770458221436, "global_step": 482781, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.961854338645935, "global_step": 482782, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.098503589630127, "global_step": 482783, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1352717876434326, "global_step": 482784, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0107319355010986, "global_step": 482785, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0479843616485596, "global_step": 482786, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9810731410980225, "global_step": 482787, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9063011407852173, "global_step": 482788, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1168212890625, "global_step": 482789, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1238911151885986, "global_step": 482790, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.097590208053589, "global_step": 482791, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0266692638397217, "global_step": 482792, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0745160579681396, "global_step": 482793, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9593088626861572, "global_step": 482794, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.002044439315796, "global_step": 482795, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0192620754241943, "global_step": 482796, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1203484535217285, "global_step": 482797, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.066844940185547, "global_step": 482798, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.000223398208618, "global_step": 482799, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1250293254852295, "global_step": 482800, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.072051525115967, "global_step": 482801, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.01584529876709, "global_step": 482802, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0504775047302246, "global_step": 482803, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.007350206375122, "global_step": 482804, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.01234769821167, "global_step": 482805, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.992116928100586, "global_step": 482806, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.01263165473938, "global_step": 482807, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1077821254730225, "global_step": 482808, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9979759454727173, "global_step": 482809, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.027599573135376, "global_step": 482810, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9910335540771484, "global_step": 482811, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0540554523468018, "global_step": 482812, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.124103307723999, "global_step": 482813, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0557332038879395, "global_step": 482814, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.009380578994751, "global_step": 482815, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1130528450012207, "global_step": 482816, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9870014190673828, "global_step": 482817, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9719840288162231, "global_step": 482818, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9733651876449585, "global_step": 482819, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.111999273300171, "global_step": 482820, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.057914972305298, "global_step": 482821, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9620578289031982, "global_step": 482822, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.10082745552063, "global_step": 482823, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0296714305877686, "global_step": 482824, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0529675483703613, "global_step": 482825, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.010373115539551, "global_step": 482826, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0820839405059814, "global_step": 482827, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1230227947235107, "global_step": 482828, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.081115961074829, "global_step": 482829, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9750776290893555, "global_step": 482830, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0189571380615234, "global_step": 482831, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.058688163757324, "global_step": 482832, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.087747812271118, "global_step": 482833, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0877366065979004, "global_step": 482834, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9898761510849, "global_step": 482835, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1263022422790527, "global_step": 482836, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9800992012023926, "global_step": 482837, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0372633934020996, "global_step": 482838, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1373908519744873, "global_step": 482839, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1127376556396484, "global_step": 482840, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.09142804145813, "global_step": 482841, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.016136884689331, "global_step": 482842, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9766377210617065, "global_step": 482843, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0421853065490723, "global_step": 482844, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.045386552810669, "global_step": 482845, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0964198112487793, "global_step": 482846, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.102566719055176, "global_step": 482847, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0547232627868652, "global_step": 482848, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0597128868103027, "global_step": 482849, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0396642684936523, "global_step": 482850, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0456855297088623, "global_step": 482851, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0774922370910645, "global_step": 482852, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0333943367004395, "global_step": 482853, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1111717224121094, "global_step": 482854, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.043360710144043, "global_step": 482855, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1066980361938477, "global_step": 482856, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.063559055328369, "global_step": 482857, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1025681495666504, "global_step": 482858, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1318092346191406, "global_step": 482859, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.055788278579712, "global_step": 482860, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0480024814605713, "global_step": 482861, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0500693321228027, "global_step": 482862, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.17238712310791, "global_step": 482863, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.08734130859375, "global_step": 482864, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0013046264648438, "global_step": 482865, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0215630531311035, "global_step": 482866, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0923469066619873, "global_step": 482867, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9719878435134888, "global_step": 482868, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9663116931915283, "global_step": 482869, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1207828521728516, "global_step": 482870, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.020681858062744, "global_step": 482871, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.983117699623108, "global_step": 482872, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.063225030899048, "global_step": 482873, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0737051963806152, "global_step": 482874, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0171499252319336, "global_step": 482875, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0375583171844482, "global_step": 482876, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.009042978286743, "global_step": 482877, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.07564640045166, "global_step": 482878, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1097190380096436, "global_step": 482879, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0762126445770264, "global_step": 482880, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.024503469467163, "global_step": 482881, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9640390872955322, "global_step": 482882, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.057375192642212, "global_step": 482883, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0343127250671387, "global_step": 482884, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0528204441070557, "global_step": 482885, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0835251808166504, "global_step": 482886, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.077807664871216, "global_step": 482887, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.997226595878601, "global_step": 482888, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0533576011657715, "global_step": 482889, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1208608150482178, "global_step": 482890, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.034541606903076, "global_step": 482891, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.097409963607788, "global_step": 482892, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0218188762664795, "global_step": 482893, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0988540649414062, "global_step": 482894, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0320258140563965, "global_step": 482895, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0903525352478027, "global_step": 482896, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0780436992645264, "global_step": 482897, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9857659339904785, "global_step": 482898, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1489789485931396, "global_step": 482899, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0304088592529297, "global_step": 482900, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.085240602493286, "global_step": 482901, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0380823612213135, "global_step": 482902, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.03619384765625, "global_step": 482903, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.039830207824707, "global_step": 482904, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0383663177490234, "global_step": 482905, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9464051723480225, "global_step": 482906, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.093858242034912, "global_step": 482907, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.023393392562866, "global_step": 482908, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0207114219665527, "global_step": 482909, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0663528442382812, "global_step": 482910, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0713539123535156, "global_step": 482911, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0164694786071777, "global_step": 482912, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.01448917388916, "global_step": 482913, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0368475914001465, "global_step": 482914, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1073696613311768, "global_step": 482915, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9907704591751099, "global_step": 482916, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1024739742279053, "global_step": 482917, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.061052083969116, "global_step": 482918, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0013856887817383, "global_step": 482919, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.09661865234375, "global_step": 482920, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0303304195404053, "global_step": 482921, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0104994773864746, "global_step": 482922, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0409765243530273, "global_step": 482923, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0404410362243652, "global_step": 482924, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9945844411849976, "global_step": 482925, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.00351881980896, "global_step": 482926, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0646743774414062, "global_step": 482927, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.062342405319214, "global_step": 482928, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0282914638519287, "global_step": 482929, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1133830547332764, "global_step": 482930, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.099769115447998, "global_step": 482931, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.044891595840454, "global_step": 482932, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0719802379608154, "global_step": 482933, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.089393377304077, "global_step": 482934, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.006624937057495, "global_step": 482935, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.031134843826294, "global_step": 482936, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0448343753814697, "global_step": 482937, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1274333000183105, "global_step": 482938, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.021395683288574, "global_step": 482939, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.022376537322998, "global_step": 482940, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0693466663360596, "global_step": 482941, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0068793296813965, "global_step": 482942, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9921972751617432, "global_step": 482943, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.068732500076294, "global_step": 482944, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0289082527160645, "global_step": 482945, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0029408931732178, "global_step": 482946, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0962166786193848, "global_step": 482947, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9955625534057617, "global_step": 482948, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0174522399902344, "global_step": 482949, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.057528495788574, "global_step": 482950, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0859978199005127, "global_step": 482951, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.168661594390869, "global_step": 482952, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0781073570251465, "global_step": 482953, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.073915958404541, "global_step": 482954, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.087900161743164, "global_step": 482955, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0408198833465576, "global_step": 482956, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0567471981048584, "global_step": 482957, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.106210231781006, "global_step": 482958, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1162829399108887, "global_step": 482959, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.042341709136963, "global_step": 482960, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1374504566192627, "global_step": 482961, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0515782833099365, "global_step": 482962, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0345547199249268, "global_step": 482963, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0980756282806396, "global_step": 482964, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.021743059158325, "global_step": 482965, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.085247278213501, "global_step": 482966, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9857596158981323, "global_step": 482967, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.082766532897949, "global_step": 482968, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0586512088775635, "global_step": 482969, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1002070903778076, "global_step": 482970, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0332117080688477, "global_step": 482971, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0052833557128906, "global_step": 482972, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0428178310394287, "global_step": 482973, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0982038974761963, "global_step": 482974, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.074551582336426, "global_step": 482975, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0934364795684814, "global_step": 482976, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0905263423919678, "global_step": 482977, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1314942836761475, "global_step": 482978, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.083897113800049, "global_step": 482979, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.981107473373413, "global_step": 482980, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9767810106277466, "global_step": 482981, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0945796966552734, "global_step": 482982, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0238611698150635, "global_step": 482983, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0826473236083984, "global_step": 482984, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9884984493255615, "global_step": 482985, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.067683219909668, "global_step": 482986, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.029522180557251, "global_step": 482987, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0591471195220947, "global_step": 482988, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.104318380355835, "global_step": 482989, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.125823497772217, "global_step": 482990, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0563619136810303, "global_step": 482991, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0065293312072754, "global_step": 482992, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0460572242736816, "global_step": 482993, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1086266040802, "global_step": 482994, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9854927062988281, "global_step": 482995, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9945282936096191, "global_step": 482996, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.068938732147217, "global_step": 482997, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0649352073669434, "global_step": 482998, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.104989767074585, "global_step": 482999, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.966428279876709, "global_step": 483000, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0437228679656982, "global_step": 483001, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0456902980804443, "global_step": 483002, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0165505409240723, "global_step": 483003, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0405266284942627, "global_step": 483004, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0489189624786377, "global_step": 483005, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.067143201828003, "global_step": 483006, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.054903745651245, "global_step": 483007, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0482609272003174, "global_step": 483008, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0435633659362793, "global_step": 483009, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1048026084899902, "global_step": 483010, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1072216033935547, "global_step": 483011, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1100575923919678, "global_step": 483012, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.090294599533081, "global_step": 483013, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0008745193481445, "global_step": 483014, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.034435510635376, "global_step": 483015, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0425078868865967, "global_step": 483016, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.014666795730591, "global_step": 483017, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9907972812652588, "global_step": 483018, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.131375312805176, "global_step": 483019, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1434295177459717, "global_step": 483020, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.012072801589966, "global_step": 483021, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9578626155853271, "global_step": 483022, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.991102695465088, "global_step": 483023, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.006028175354004, "global_step": 483024, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0210630893707275, "global_step": 483025, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0732779502868652, "global_step": 483026, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.120939254760742, "global_step": 483027, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1214401721954346, "global_step": 483028, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1053943634033203, "global_step": 483029, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.03342342376709, "global_step": 483030, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.094137191772461, "global_step": 483031, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.056530475616455, "global_step": 483032, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.057084798812866, "global_step": 483033, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.048039436340332, "global_step": 483034, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1060123443603516, "global_step": 483035, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0736770629882812, "global_step": 483036, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0301437377929688, "global_step": 483037, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0132503509521484, "global_step": 483038, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0227200984954834, "global_step": 483039, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.089125394821167, "global_step": 483040, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.089472532272339, "global_step": 483041, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.128220319747925, "global_step": 483042, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0404138565063477, "global_step": 483043, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0121548175811768, "global_step": 483044, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1000633239746094, "global_step": 483045, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0377488136291504, "global_step": 483046, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1743576526641846, "global_step": 483047, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0315513610839844, "global_step": 483048, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0164055824279785, "global_step": 483049, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0934367179870605, "global_step": 483050, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0866196155548096, "global_step": 483051, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.026561737060547, "global_step": 483052, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0258796215057373, "global_step": 483053, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.072253942489624, "global_step": 483054, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9972532987594604, "global_step": 483055, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.09745192527771, "global_step": 483056, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.073474168777466, "global_step": 483057, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.047278642654419, "global_step": 483058, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9919967651367188, "global_step": 483059, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.144822359085083, "global_step": 483060, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1009182929992676, "global_step": 483061, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9956892728805542, "global_step": 483062, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0578296184539795, "global_step": 483063, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0908589363098145, "global_step": 483064, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.109246015548706, "global_step": 483065, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9847233295440674, "global_step": 483066, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.019382953643799, "global_step": 483067, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0520060062408447, "global_step": 483068, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0589659214019775, "global_step": 483069, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.062648296356201, "global_step": 483070, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.093836784362793, "global_step": 483071, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9771332740783691, "global_step": 483072, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0816195011138916, "global_step": 483073, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0753250122070312, "global_step": 483074, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1070430278778076, "global_step": 483075, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9728511571884155, "global_step": 483076, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0950255393981934, "global_step": 483077, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0887365341186523, "global_step": 483078, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0883803367614746, "global_step": 483079, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.053863286972046, "global_step": 483080, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1244640350341797, "global_step": 483081, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.978820562362671, "global_step": 483082, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0591671466827393, "global_step": 483083, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.090109348297119, "global_step": 483084, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.076766014099121, "global_step": 483085, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.007802724838257, "global_step": 483086, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0940558910369873, "global_step": 483087, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.046142101287842, "global_step": 483088, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0713229179382324, "global_step": 483089, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1260170936584473, "global_step": 483090, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1159379482269287, "global_step": 483091, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0518405437469482, "global_step": 483092, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0486233234405518, "global_step": 483093, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0420966148376465, "global_step": 483094, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.02996563911438, "global_step": 483095, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.129715919494629, "global_step": 483096, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0371909141540527, "global_step": 483097, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.170013666152954, "global_step": 483098, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.013383150100708, "global_step": 483099, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.076965570449829, "global_step": 483100, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0404958724975586, "global_step": 483101, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.057028293609619, "global_step": 483102, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.058006763458252, "global_step": 483103, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.10036563873291, "global_step": 483104, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9541929960250854, "global_step": 483105, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0696544647216797, "global_step": 483106, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1778335571289062, "global_step": 483107, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0237104892730713, "global_step": 483108, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0427238941192627, "global_step": 483109, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.087742328643799, "global_step": 483110, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0171384811401367, "global_step": 483111, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.086414098739624, "global_step": 483112, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0059216022491455, "global_step": 483113, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0483880043029785, "global_step": 483114, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.113762617111206, "global_step": 483115, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.020933151245117, "global_step": 483116, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.065117597579956, "global_step": 483117, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.02698016166687, "global_step": 483118, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.049532890319824, "global_step": 483119, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0243542194366455, "global_step": 483120, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0221686363220215, "global_step": 483121, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.101553201675415, "global_step": 483122, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.020286798477173, "global_step": 483123, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.069176197052002, "global_step": 483124, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0563712120056152, "global_step": 483125, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0505237579345703, "global_step": 483126, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.081843376159668, "global_step": 483127, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0608091354370117, "global_step": 483128, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0546345710754395, "global_step": 483129, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9799880981445312, "global_step": 483130, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.053373098373413, "global_step": 483131, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0049474239349365, "global_step": 483132, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.058676242828369, "global_step": 483133, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.035580635070801, "global_step": 483134, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1020188331604004, "global_step": 483135, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1270251274108887, "global_step": 483136, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0763285160064697, "global_step": 483137, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.165573835372925, "global_step": 483138, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.043250560760498, "global_step": 483139, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9710015058517456, "global_step": 483140, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0857107639312744, "global_step": 483141, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1425235271453857, "global_step": 483142, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0403342247009277, "global_step": 483143, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.944748878479004, "global_step": 483144, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.036775827407837, "global_step": 483145, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0563132762908936, "global_step": 483146, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0336008071899414, "global_step": 483147, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0515875816345215, "global_step": 483148, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0539231300354004, "global_step": 483149, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9913246631622314, "global_step": 483150, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0149998664855957, "global_step": 483151, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1156907081604004, "global_step": 483152, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9448297023773193, "global_step": 483153, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.06264328956604, "global_step": 483154, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9853875637054443, "global_step": 483155, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0447452068328857, "global_step": 483156, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0382163524627686, "global_step": 483157, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0172688961029053, "global_step": 483158, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.085632801055908, "global_step": 483159, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.062657117843628, "global_step": 483160, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.995936632156372, "global_step": 483161, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0161428451538086, "global_step": 483162, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1147096157073975, "global_step": 483163, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.029008626937866, "global_step": 483164, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.085374593734741, "global_step": 483165, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1792829036712646, "global_step": 483166, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.026167869567871, "global_step": 483167, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.181654691696167, "global_step": 483168, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0483527183532715, "global_step": 483169, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9554451704025269, "global_step": 483170, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0793209075927734, "global_step": 483171, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0624942779541016, "global_step": 483172, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1270689964294434, "global_step": 483173, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9930871725082397, "global_step": 483174, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1013991832733154, "global_step": 483175, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.127086639404297, "global_step": 483176, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.09979248046875, "global_step": 483177, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.103288412094116, "global_step": 483178, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.048405647277832, "global_step": 483179, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.050534248352051, "global_step": 483180, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.067533016204834, "global_step": 483181, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.123173475265503, "global_step": 483182, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.045773506164551, "global_step": 483183, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.022096633911133, "global_step": 483184, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0853428840637207, "global_step": 483185, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0793309211730957, "global_step": 483186, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0675408840179443, "global_step": 483187, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0716638565063477, "global_step": 483188, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1190683841705322, "global_step": 483189, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0626742839813232, "global_step": 483190, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0342211723327637, "global_step": 483191, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1789798736572266, "global_step": 483192, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.004150152206421, "global_step": 483193, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1533524990081787, "global_step": 483194, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.984787106513977, "global_step": 483195, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1675190925598145, "global_step": 483196, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1126465797424316, "global_step": 483197, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.105555772781372, "global_step": 483198, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1266121864318848, "global_step": 483199, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0639524459838867, "global_step": 483200, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9959218502044678, "global_step": 483201, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.029038667678833, "global_step": 483202, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0968596935272217, "global_step": 483203, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.906305193901062, "global_step": 483204, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.057629346847534, "global_step": 483205, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.066185712814331, "global_step": 483206, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0902297496795654, "global_step": 483207, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0711963176727295, "global_step": 483208, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.026557207107544, "global_step": 483209, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.028961181640625, "global_step": 483210, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0529558658599854, "global_step": 483211, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.018885850906372, "global_step": 483212, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0784857273101807, "global_step": 483213, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.108372926712036, "global_step": 483214, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.061147689819336, "global_step": 483215, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.118048906326294, "global_step": 483216, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0238354206085205, "global_step": 483217, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1377005577087402, "global_step": 483218, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.075564384460449, "global_step": 483219, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.125837802886963, "global_step": 483220, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.028895139694214, "global_step": 483221, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1131932735443115, "global_step": 483222, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0707504749298096, "global_step": 483223, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.133937358856201, "global_step": 483224, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0591421127319336, "global_step": 483225, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.069398880004883, "global_step": 483226, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0869810581207275, "global_step": 483227, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0654196739196777, "global_step": 483228, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0804390907287598, "global_step": 483229, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0701441764831543, "global_step": 483230, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.8860177993774414, "global_step": 483231, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0069267749786377, "global_step": 483232, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.067946195602417, "global_step": 483233, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0983574390411377, "global_step": 483234, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9713718891143799, "global_step": 483235, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.046006917953491, "global_step": 483236, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1888186931610107, "global_step": 483237, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9598125219345093, "global_step": 483238, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.114104986190796, "global_step": 483239, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0448291301727295, "global_step": 483240, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0353965759277344, "global_step": 483241, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0888121128082275, "global_step": 483242, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.059842824935913, "global_step": 483243, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9873038530349731, "global_step": 483244, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0319151878356934, "global_step": 483245, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0608749389648438, "global_step": 483246, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0516908168792725, "global_step": 483247, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0391666889190674, "global_step": 483248, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0147969722747803, "global_step": 483249, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0879085063934326, "global_step": 483250, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1002695560455322, "global_step": 483251, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1113674640655518, "global_step": 483252, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.099760055541992, "global_step": 483253, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.125514030456543, "global_step": 483254, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0851056575775146, "global_step": 483255, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.137928009033203, "global_step": 483256, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.135774612426758, "global_step": 483257, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0158252716064453, "global_step": 483258, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0790109634399414, "global_step": 483259, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.008481979370117, "global_step": 483260, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9544312953948975, "global_step": 483261, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0427732467651367, "global_step": 483262, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1152126789093018, "global_step": 483263, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0762722492218018, "global_step": 483264, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0362448692321777, "global_step": 483265, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9975590705871582, "global_step": 483266, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0813629627227783, "global_step": 483267, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0847058296203613, "global_step": 483268, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1079022884368896, "global_step": 483269, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.027569055557251, "global_step": 483270, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9814201593399048, "global_step": 483271, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.019014358520508, "global_step": 483272, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.135399580001831, "global_step": 483273, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.040008783340454, "global_step": 483274, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.073582887649536, "global_step": 483275, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.02790904045105, "global_step": 483276, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0535354614257812, "global_step": 483277, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.040379762649536, "global_step": 483278, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.13981556892395, "global_step": 483279, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0902774333953857, "global_step": 483280, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.049283981323242, "global_step": 483281, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.023890495300293, "global_step": 483282, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.028585433959961, "global_step": 483283, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0529258251190186, "global_step": 483284, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0463685989379883, "global_step": 483285, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9904396533966064, "global_step": 483286, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0962367057800293, "global_step": 483287, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.096973419189453, "global_step": 483288, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0615293979644775, "global_step": 483289, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0506746768951416, "global_step": 483290, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.072042226791382, "global_step": 483291, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9935812950134277, "global_step": 483292, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.067552328109741, "global_step": 483293, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.116091251373291, "global_step": 483294, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1109609603881836, "global_step": 483295, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1167657375335693, "global_step": 483296, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0152149200439453, "global_step": 483297, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0088706016540527, "global_step": 483298, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9232577085494995, "global_step": 483299, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1018595695495605, "global_step": 483300, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1126315593719482, "global_step": 483301, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.043761968612671, "global_step": 483302, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1464078426361084, "global_step": 483303, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0583255290985107, "global_step": 483304, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.973297119140625, "global_step": 483305, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1034600734710693, "global_step": 483306, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.026705741882324, "global_step": 483307, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.030031204223633, "global_step": 483308, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0401012897491455, "global_step": 483309, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.037904977798462, "global_step": 483310, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.040426015853882, "global_step": 483311, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.206587076187134, "global_step": 483312, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.003523588180542, "global_step": 483313, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1090049743652344, "global_step": 483314, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.035823106765747, "global_step": 483315, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.043875217437744, "global_step": 483316, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.060267925262451, "global_step": 483317, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0316247940063477, "global_step": 483318, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.060997724533081, "global_step": 483319, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0161304473876953, "global_step": 483320, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0377957820892334, "global_step": 483321, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0051145553588867, "global_step": 483322, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0983943939208984, "global_step": 483323, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0978190898895264, "global_step": 483324, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0650408267974854, "global_step": 483325, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.113579273223877, "global_step": 483326, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0626559257507324, "global_step": 483327, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0778629779815674, "global_step": 483328, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0821683406829834, "global_step": 483329, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0565314292907715, "global_step": 483330, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0864651203155518, "global_step": 483331, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1641769409179688, "global_step": 483332, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0988399982452393, "global_step": 483333, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.081582546234131, "global_step": 483334, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9766942262649536, "global_step": 483335, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.083165168762207, "global_step": 483336, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.946635127067566, "global_step": 483337, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.021639347076416, "global_step": 483338, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1257808208465576, "global_step": 483339, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.120126247406006, "global_step": 483340, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0241916179656982, "global_step": 483341, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0164523124694824, "global_step": 483342, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.160828113555908, "global_step": 483343, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0578534603118896, "global_step": 483344, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.107166290283203, "global_step": 483345, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0732266902923584, "global_step": 483346, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.037571430206299, "global_step": 483347, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.105875253677368, "global_step": 483348, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0890612602233887, "global_step": 483349, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.062804937362671, "global_step": 483350, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1966216564178467, "global_step": 483351, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.027939796447754, "global_step": 483352, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0313687324523926, "global_step": 483353, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9485855102539062, "global_step": 483354, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.015164375305176, "global_step": 483355, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0110042095184326, "global_step": 483356, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9987437725067139, "global_step": 483357, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0458905696868896, "global_step": 483358, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9923717975616455, "global_step": 483359, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1416831016540527, "global_step": 483360, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0097756385803223, "global_step": 483361, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.088386297225952, "global_step": 483362, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0336947441101074, "global_step": 483363, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.028139352798462, "global_step": 483364, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.104645252227783, "global_step": 483365, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9792481660842896, "global_step": 483366, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0675065517425537, "global_step": 483367, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0458824634552, "global_step": 483368, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.091276168823242, "global_step": 483369, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0964577198028564, "global_step": 483370, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0178139209747314, "global_step": 483371, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0994064807891846, "global_step": 483372, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1352903842926025, "global_step": 483373, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9815127849578857, "global_step": 483374, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9979248046875, "global_step": 483375, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0813071727752686, "global_step": 483376, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.038210153579712, "global_step": 483377, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.030831813812256, "global_step": 483378, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.082010269165039, "global_step": 483379, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.049062490463257, "global_step": 483380, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0861620903015137, "global_step": 483381, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0683650970458984, "global_step": 483382, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.994868516921997, "global_step": 483383, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.064228057861328, "global_step": 483384, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1009011268615723, "global_step": 483385, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0930304527282715, "global_step": 483386, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0991697311401367, "global_step": 483387, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.096710681915283, "global_step": 483388, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.088941812515259, "global_step": 483389, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.156607151031494, "global_step": 483390, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9650604724884033, "global_step": 483391, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0898313522338867, "global_step": 483392, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.043856143951416, "global_step": 483393, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0888094902038574, "global_step": 483394, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.086644411087036, "global_step": 483395, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1218490600585938, "global_step": 483396, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.076647996902466, "global_step": 483397, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0880722999572754, "global_step": 483398, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1420445442199707, "global_step": 483399, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1349756717681885, "global_step": 483400, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0238969326019287, "global_step": 483401, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.027811050415039, "global_step": 483402, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.04777455329895, "global_step": 483403, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.150252342224121, "global_step": 483404, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9599653482437134, "global_step": 483405, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0004522800445557, "global_step": 483406, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.044574022293091, "global_step": 483407, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9653465747833252, "global_step": 483408, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.087737560272217, "global_step": 483409, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1172173023223877, "global_step": 483410, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0091958045959473, "global_step": 483411, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.104008436203003, "global_step": 483412, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0571773052215576, "global_step": 483413, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9957770109176636, "global_step": 483414, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0878281593322754, "global_step": 483415, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.030440092086792, "global_step": 483416, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9591320753097534, "global_step": 483417, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0523712635040283, "global_step": 483418, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.101715326309204, "global_step": 483419, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0956223011016846, "global_step": 483420, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0222294330596924, "global_step": 483421, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0890207290649414, "global_step": 483422, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.088557004928589, "global_step": 483423, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1534719467163086, "global_step": 483424, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.018765926361084, "global_step": 483425, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0768814086914062, "global_step": 483426, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1289615631103516, "global_step": 483427, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0645742416381836, "global_step": 483428, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0534815788269043, "global_step": 483429, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.133484125137329, "global_step": 483430, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0887656211853027, "global_step": 483431, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.150543451309204, "global_step": 483432, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0537729263305664, "global_step": 483433, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0244266986846924, "global_step": 483434, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0124168395996094, "global_step": 483435, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0014026165008545, "global_step": 483436, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1288342475891113, "global_step": 483437, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1351006031036377, "global_step": 483438, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9840761423110962, "global_step": 483439, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.165471076965332, "global_step": 483440, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.150775194168091, "global_step": 483441, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0620999336242676, "global_step": 483442, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.105733633041382, "global_step": 483443, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.081467390060425, "global_step": 483444, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.117730140686035, "global_step": 483445, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0821545124053955, "global_step": 483446, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.007697105407715, "global_step": 483447, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.062899351119995, "global_step": 483448, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0604989528656006, "global_step": 483449, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9718942642211914, "global_step": 483450, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.124840021133423, "global_step": 483451, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0599477291107178, "global_step": 483452, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.146667242050171, "global_step": 483453, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1454830169677734, "global_step": 483454, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.052833080291748, "global_step": 483455, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0971007347106934, "global_step": 483456, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0949347019195557, "global_step": 483457, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.074486255645752, "global_step": 483458, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0045909881591797, "global_step": 483459, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.034362316131592, "global_step": 483460, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0805728435516357, "global_step": 483461, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0628581047058105, "global_step": 483462, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1098532676696777, "global_step": 483463, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.093073844909668, "global_step": 483464, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9452896118164062, "global_step": 483465, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0247814655303955, "global_step": 483466, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.037856340408325, "global_step": 483467, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.022784948348999, "global_step": 483468, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.065486192703247, "global_step": 483469, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.094027280807495, "global_step": 483470, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9560439586639404, "global_step": 483471, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1527931690216064, "global_step": 483472, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0157017707824707, "global_step": 483473, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.073777437210083, "global_step": 483474, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0644419193267822, "global_step": 483475, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1054458618164062, "global_step": 483476, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1382930278778076, "global_step": 483477, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.033306837081909, "global_step": 483478, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9506721496582031, "global_step": 483479, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.178879737854004, "global_step": 483480, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.062108039855957, "global_step": 483481, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1484954357147217, "global_step": 483482, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1082563400268555, "global_step": 483483, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9097933769226074, "global_step": 483484, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0911550521850586, "global_step": 483485, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.037539482116699, "global_step": 483486, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0193421840667725, "global_step": 483487, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.052539348602295, "global_step": 483488, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9548910856246948, "global_step": 483489, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1026461124420166, "global_step": 483490, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0948421955108643, "global_step": 483491, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0327675342559814, "global_step": 483492, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9994373321533203, "global_step": 483493, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0764472484588623, "global_step": 483494, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0156989097595215, "global_step": 483495, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1359357833862305, "global_step": 483496, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.075777769088745, "global_step": 483497, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1193344593048096, "global_step": 483498, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0134854316711426, "global_step": 483499, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0516374111175537, "global_step": 483500, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0143375396728516, "global_step": 483501, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1162869930267334, "global_step": 483502, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0673465728759766, "global_step": 483503, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.103694438934326, "global_step": 483504, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0349364280700684, "global_step": 483505, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0692224502563477, "global_step": 483506, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0511362552642822, "global_step": 483507, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.116758108139038, "global_step": 483508, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.067443609237671, "global_step": 483509, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9561238288879395, "global_step": 483510, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1231117248535156, "global_step": 483511, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.120072841644287, "global_step": 483512, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0179872512817383, "global_step": 483513, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0967764854431152, "global_step": 483514, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.152242422103882, "global_step": 483515, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0022287368774414, "global_step": 483516, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0663318634033203, "global_step": 483517, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.03029465675354, "global_step": 483518, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0909945964813232, "global_step": 483519, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.078111171722412, "global_step": 483520, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0201056003570557, "global_step": 483521, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9780277013778687, "global_step": 483522, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9987311363220215, "global_step": 483523, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.090869188308716, "global_step": 483524, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.070575714111328, "global_step": 483525, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.061340808868408, "global_step": 483526, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1185076236724854, "global_step": 483527, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9823766946792603, "global_step": 483528, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1030683517456055, "global_step": 483529, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.048276662826538, "global_step": 483530, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.062896251678467, "global_step": 483531, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0614380836486816, "global_step": 483532, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.073099374771118, "global_step": 483533, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1320862770080566, "global_step": 483534, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.029733657836914, "global_step": 483535, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0323240756988525, "global_step": 483536, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.012787342071533, "global_step": 483537, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0713300704956055, "global_step": 483538, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.097968816757202, "global_step": 483539, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0516128540039062, "global_step": 483540, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.161015272140503, "global_step": 483541, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.019062042236328, "global_step": 483542, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1496431827545166, "global_step": 483543, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0852670669555664, "global_step": 483544, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0945775508880615, "global_step": 483545, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0310068130493164, "global_step": 483546, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.044764995574951, "global_step": 483547, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0266950130462646, "global_step": 483548, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0843021869659424, "global_step": 483549, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.027362108230591, "global_step": 483550, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.02299427986145, "global_step": 483551, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1137349605560303, "global_step": 483552, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0232954025268555, "global_step": 483553, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.092467784881592, "global_step": 483554, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.042386054992676, "global_step": 483555, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0655922889709473, "global_step": 483556, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.161336660385132, "global_step": 483557, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.090857744216919, "global_step": 483558, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.047928810119629, "global_step": 483559, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0532078742980957, "global_step": 483560, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.037990093231201, "global_step": 483561, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0486576557159424, "global_step": 483562, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0206828117370605, "global_step": 483563, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.04049015045166, "global_step": 483564, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9722628593444824, "global_step": 483565, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0420401096343994, "global_step": 483566, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.073761224746704, "global_step": 483567, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.145611047744751, "global_step": 483568, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9915351867675781, "global_step": 483569, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0832056999206543, "global_step": 483570, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9921828508377075, "global_step": 483571, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1229028701782227, "global_step": 483572, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0684866905212402, "global_step": 483573, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.031843662261963, "global_step": 483574, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0024683475494385, "global_step": 483575, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0365943908691406, "global_step": 483576, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.993577480316162, "global_step": 483577, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.061361074447632, "global_step": 483578, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0356743335723877, "global_step": 483579, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0008039474487305, "global_step": 483580, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0450072288513184, "global_step": 483581, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0619707107543945, "global_step": 483582, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.136583089828491, "global_step": 483583, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.047361373901367, "global_step": 483584, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9541101455688477, "global_step": 483585, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.05019474029541, "global_step": 483586, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0984301567077637, "global_step": 483587, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9960182905197144, "global_step": 483588, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.044459104537964, "global_step": 483589, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.130829095840454, "global_step": 483590, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1532270908355713, "global_step": 483591, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.07792067527771, "global_step": 483592, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.108386516571045, "global_step": 483593, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.07285213470459, "global_step": 483594, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0286476612091064, "global_step": 483595, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.2000069618225098, "global_step": 483596, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0190436840057373, "global_step": 483597, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0275018215179443, "global_step": 483598, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0610239505767822, "global_step": 483599, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0109682083129883, "global_step": 483600, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.135349988937378, "global_step": 483601, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.033665657043457, "global_step": 483602, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1227991580963135, "global_step": 483603, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9771618843078613, "global_step": 483604, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.026597261428833, "global_step": 483605, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9925048351287842, "global_step": 483606, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0389745235443115, "global_step": 483607, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.105333089828491, "global_step": 483608, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9877430200576782, "global_step": 483609, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0362210273742676, "global_step": 483610, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.072986125946045, "global_step": 483611, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0883638858795166, "global_step": 483612, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.049851655960083, "global_step": 483613, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.090970516204834, "global_step": 483614, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.081827402114868, "global_step": 483615, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0014150142669678, "global_step": 483616, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0132904052734375, "global_step": 483617, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0745527744293213, "global_step": 483618, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.096646547317505, "global_step": 483619, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.131664276123047, "global_step": 483620, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.120227813720703, "global_step": 483621, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1052818298339844, "global_step": 483622, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.097475051879883, "global_step": 483623, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0356240272521973, "global_step": 483624, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.062307119369507, "global_step": 483625, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0920445919036865, "global_step": 483626, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1033225059509277, "global_step": 483627, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.124405860900879, "global_step": 483628, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.998997449874878, "global_step": 483629, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0845470428466797, "global_step": 483630, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0328872203826904, "global_step": 483631, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0970823764801025, "global_step": 483632, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0367214679718018, "global_step": 483633, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0663726329803467, "global_step": 483634, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0482094287872314, "global_step": 483635, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.9880913496017456, "global_step": 483636, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0443055629730225, "global_step": 483637, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.082552671432495, "global_step": 483638, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1082398891448975, "global_step": 483639, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0347981452941895, "global_step": 483640, "epoch": 848, "lr": 5e-05}
{"train_loss": 1.985390067100525, "global_step": 483641, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.060385227203369, "global_step": 483642, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0671489238739014, "global_step": 483643, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.039795398712158, "global_step": 483644, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1338250637054443, "global_step": 483645, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0899126529693604, "global_step": 483646, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1706316471099854, "global_step": 483647, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1066067218780518, "global_step": 483648, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0435469150543213, "global_step": 483649, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0161349773406982, "global_step": 483650, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1232800483703613, "global_step": 483651, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0982375144958496, "global_step": 483652, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0496039390563965, "global_step": 483653, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.006990909576416, "global_step": 483654, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1863162517547607, "global_step": 483655, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0823915004730225, "global_step": 483656, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0705714225769043, "global_step": 483657, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0538861751556396, "global_step": 483658, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.145385503768921, "global_step": 483659, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.1116225719451904, "global_step": 483660, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0853655338287354, "global_step": 483661, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0778794288635254, "global_step": 483662, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.059131622314453, "global_step": 483663, "epoch": 848, "lr": 5e-05}
{"train_loss": 2.0516512393951416, "global_step": 483664, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0325686931610107, "global_step": 483665, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.069875717163086, "global_step": 483666, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9926525354385376, "global_step": 483667, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.994719386100769, "global_step": 483668, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.073530673980713, "global_step": 483669, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0388777256011963, "global_step": 483670, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.049656867980957, "global_step": 483671, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.086671829223633, "global_step": 483672, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0708446502685547, "global_step": 483673, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.058217763900757, "global_step": 483674, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1019980907440186, "global_step": 483675, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9982753992080688, "global_step": 483676, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0556411743164062, "global_step": 483677, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.038032293319702, "global_step": 483678, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0552616119384766, "global_step": 483679, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.007542848587036, "global_step": 483680, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0893568992614746, "global_step": 483681, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.043381690979004, "global_step": 483682, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9254097938537598, "global_step": 483683, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0663859844207764, "global_step": 483684, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.001572608947754, "global_step": 483685, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0096092224121094, "global_step": 483686, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.043902635574341, "global_step": 483687, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9319608211517334, "global_step": 483688, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.055588483810425, "global_step": 483689, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0569944381713867, "global_step": 483690, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.062859296798706, "global_step": 483691, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.044567823410034, "global_step": 483692, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.047119140625, "global_step": 483693, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9875679016113281, "global_step": 483694, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.033703088760376, "global_step": 483695, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.028282642364502, "global_step": 483696, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0135655403137207, "global_step": 483697, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0790703296661377, "global_step": 483698, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.944275975227356, "global_step": 483699, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.116654634475708, "global_step": 483700, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0908472537994385, "global_step": 483701, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0404269695281982, "global_step": 483702, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0939760208129883, "global_step": 483703, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.051044225692749, "global_step": 483704, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0810179710388184, "global_step": 483705, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.034235715866089, "global_step": 483706, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.106703519821167, "global_step": 483707, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1282906532287598, "global_step": 483708, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0895111560821533, "global_step": 483709, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0626001358032227, "global_step": 483710, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0370922088623047, "global_step": 483711, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9887136220932007, "global_step": 483712, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.115342617034912, "global_step": 483713, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.043945074081421, "global_step": 483714, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9690581560134888, "global_step": 483715, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0360867977142334, "global_step": 483716, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0142393112182617, "global_step": 483717, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1535820960998535, "global_step": 483718, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0229644775390625, "global_step": 483719, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0886101722717285, "global_step": 483720, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0202903747558594, "global_step": 483721, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9877564907073975, "global_step": 483722, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.098720073699951, "global_step": 483723, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0402114391326904, "global_step": 483724, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0480871200561523, "global_step": 483725, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9904417991638184, "global_step": 483726, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0013427734375, "global_step": 483727, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0078792572021484, "global_step": 483728, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.077169895172119, "global_step": 483729, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.078397512435913, "global_step": 483730, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.101688861846924, "global_step": 483731, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.097827196121216, "global_step": 483732, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9764552116394043, "global_step": 483733, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0855824947357178, "global_step": 483734, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0981805324554443, "global_step": 483735, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.137934923171997, "global_step": 483736, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0627219676971436, "global_step": 483737, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0432496070861816, "global_step": 483738, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.976999044418335, "global_step": 483739, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1622469425201416, "global_step": 483740, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.023681640625, "global_step": 483741, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.062135934829712, "global_step": 483742, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0185799598693848, "global_step": 483743, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1776974201202393, "global_step": 483744, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1557791233062744, "global_step": 483745, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.07741117477417, "global_step": 483746, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0395145416259766, "global_step": 483747, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.026381015777588, "global_step": 483748, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.070685625076294, "global_step": 483749, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.006061553955078, "global_step": 483750, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1124792098999023, "global_step": 483751, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9930881261825562, "global_step": 483752, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.015188694000244, "global_step": 483753, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0714271068573, "global_step": 483754, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.000943422317505, "global_step": 483755, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.072503089904785, "global_step": 483756, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1027963161468506, "global_step": 483757, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0534565448760986, "global_step": 483758, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0564842224121094, "global_step": 483759, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.051727294921875, "global_step": 483760, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9942266941070557, "global_step": 483761, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0573856830596924, "global_step": 483762, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.058934211730957, "global_step": 483763, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9671683311462402, "global_step": 483764, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.013688564300537, "global_step": 483765, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0764689445495605, "global_step": 483766, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0728251934051514, "global_step": 483767, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.111602783203125, "global_step": 483768, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1032629013061523, "global_step": 483769, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0830092430114746, "global_step": 483770, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0091872215270996, "global_step": 483771, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.049821615219116, "global_step": 483772, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.012089252471924, "global_step": 483773, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0717415809631348, "global_step": 483774, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.04740834236145, "global_step": 483775, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9438706636428833, "global_step": 483776, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.079859972000122, "global_step": 483777, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1458041667938232, "global_step": 483778, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9755196571350098, "global_step": 483779, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0660905838012695, "global_step": 483780, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0889902114868164, "global_step": 483781, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0166244506835938, "global_step": 483782, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1340882778167725, "global_step": 483783, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0314114093780518, "global_step": 483784, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0775232315063477, "global_step": 483785, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.087418794631958, "global_step": 483786, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.059114456176758, "global_step": 483787, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0349373817443848, "global_step": 483788, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9871890544891357, "global_step": 483789, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0726659297943115, "global_step": 483790, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.004328727722168, "global_step": 483791, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0050103664398193, "global_step": 483792, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.051898717880249, "global_step": 483793, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0319583415985107, "global_step": 483794, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.013087034225464, "global_step": 483795, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.01296329498291, "global_step": 483796, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1070077419281006, "global_step": 483797, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.051325559616089, "global_step": 483798, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.014462947845459, "global_step": 483799, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.082287073135376, "global_step": 483800, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1010901927948, "global_step": 483801, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9073207378387451, "global_step": 483802, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0650691986083984, "global_step": 483803, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0809426307678223, "global_step": 483804, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0940051078796387, "global_step": 483805, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.082030773162842, "global_step": 483806, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9974557161331177, "global_step": 483807, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0914466381073, "global_step": 483808, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.109121799468994, "global_step": 483809, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.045137882232666, "global_step": 483810, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.066509246826172, "global_step": 483811, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9781886339187622, "global_step": 483812, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0218615531921387, "global_step": 483813, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0154783725738525, "global_step": 483814, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9845765829086304, "global_step": 483815, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0346145629882812, "global_step": 483816, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.063730001449585, "global_step": 483817, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.13042950630188, "global_step": 483818, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.088573694229126, "global_step": 483819, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.062839984893799, "global_step": 483820, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0216333866119385, "global_step": 483821, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.082063913345337, "global_step": 483822, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0264246463775635, "global_step": 483823, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0118606090545654, "global_step": 483824, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0478124618530273, "global_step": 483825, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.099956750869751, "global_step": 483826, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.02396559715271, "global_step": 483827, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0517027378082275, "global_step": 483828, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0783238410949707, "global_step": 483829, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.121030569076538, "global_step": 483830, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0295493602752686, "global_step": 483831, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0669445991516113, "global_step": 483832, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.056540012359619, "global_step": 483833, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0401675701141357, "global_step": 483834, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.141705274581909, "global_step": 483835, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0075924396514893, "global_step": 483836, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.136934518814087, "global_step": 483837, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.022585391998291, "global_step": 483838, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1042487621307373, "global_step": 483839, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0819106101989746, "global_step": 483840, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.055121660232544, "global_step": 483841, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9901541471481323, "global_step": 483842, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1280972957611084, "global_step": 483843, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0975072383880615, "global_step": 483844, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9628292322158813, "global_step": 483845, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.028576374053955, "global_step": 483846, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1851494312286377, "global_step": 483847, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0933680534362793, "global_step": 483848, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9848511219024658, "global_step": 483849, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.937564492225647, "global_step": 483850, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0487172603607178, "global_step": 483851, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9660810232162476, "global_step": 483852, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9577631950378418, "global_step": 483853, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0651516914367676, "global_step": 483854, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0899765491485596, "global_step": 483855, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0614423751831055, "global_step": 483856, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.051387310028076, "global_step": 483857, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.04750919342041, "global_step": 483858, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.056551218032837, "global_step": 483859, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.974077820777893, "global_step": 483860, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.098271608352661, "global_step": 483861, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.055506467819214, "global_step": 483862, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0621442794799805, "global_step": 483863, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0612916946411133, "global_step": 483864, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.075183629989624, "global_step": 483865, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9911913871765137, "global_step": 483866, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0144402980804443, "global_step": 483867, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0606625080108643, "global_step": 483868, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0285353660583496, "global_step": 483869, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.028083324432373, "global_step": 483870, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0495448112487793, "global_step": 483871, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.048363447189331, "global_step": 483872, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9582890272140503, "global_step": 483873, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0427656173706055, "global_step": 483874, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.053439140319824, "global_step": 483875, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0425877571105957, "global_step": 483876, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0042600631713867, "global_step": 483877, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0421090126037598, "global_step": 483878, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.132951259613037, "global_step": 483879, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.048823595046997, "global_step": 483880, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.137714385986328, "global_step": 483881, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1531593799591064, "global_step": 483882, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0736336708068848, "global_step": 483883, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1294751167297363, "global_step": 483884, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.036850929260254, "global_step": 483885, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1052608489990234, "global_step": 483886, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9733859300613403, "global_step": 483887, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9389253854751587, "global_step": 483888, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0601820945739746, "global_step": 483889, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.091463804244995, "global_step": 483890, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0492327213287354, "global_step": 483891, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0301706790924072, "global_step": 483892, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.079188585281372, "global_step": 483893, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0762779712677, "global_step": 483894, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.996753215789795, "global_step": 483895, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.055476188659668, "global_step": 483896, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0588152408599854, "global_step": 483897, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1724469661712646, "global_step": 483898, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.084099531173706, "global_step": 483899, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9989346265792847, "global_step": 483900, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1294455528259277, "global_step": 483901, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.06671404838562, "global_step": 483902, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0443012714385986, "global_step": 483903, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0624096393585205, "global_step": 483904, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0863492488861084, "global_step": 483905, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.031780242919922, "global_step": 483906, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0765185356140137, "global_step": 483907, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9864115715026855, "global_step": 483908, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0203096866607666, "global_step": 483909, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.106931447982788, "global_step": 483910, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9904823303222656, "global_step": 483911, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1038405895233154, "global_step": 483912, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9932606220245361, "global_step": 483913, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.074368953704834, "global_step": 483914, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0247037410736084, "global_step": 483915, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.039369821548462, "global_step": 483916, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0711491107940674, "global_step": 483917, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9786698818206787, "global_step": 483918, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.065671682357788, "global_step": 483919, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9959224462509155, "global_step": 483920, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.031921148300171, "global_step": 483921, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0187277793884277, "global_step": 483922, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0510594844818115, "global_step": 483923, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.110046148300171, "global_step": 483924, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.055194616317749, "global_step": 483925, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0892202854156494, "global_step": 483926, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.106987714767456, "global_step": 483927, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0572104454040527, "global_step": 483928, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0082054138183594, "global_step": 483929, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0126965045928955, "global_step": 483930, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1328928470611572, "global_step": 483931, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.028085470199585, "global_step": 483932, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.095233678817749, "global_step": 483933, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0846903324127197, "global_step": 483934, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.058635711669922, "global_step": 483935, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9917739629745483, "global_step": 483936, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0700714588165283, "global_step": 483937, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0515410900115967, "global_step": 483938, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9671918153762817, "global_step": 483939, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0785648822784424, "global_step": 483940, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0429306030273438, "global_step": 483941, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.090146541595459, "global_step": 483942, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0841288566589355, "global_step": 483943, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1161513328552246, "global_step": 483944, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.015373468399048, "global_step": 483945, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0880885124206543, "global_step": 483946, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.969989538192749, "global_step": 483947, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.172351121902466, "global_step": 483948, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.067969560623169, "global_step": 483949, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.07491135597229, "global_step": 483950, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.106489658355713, "global_step": 483951, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.990620493888855, "global_step": 483952, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.112530469894409, "global_step": 483953, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.053084135055542, "global_step": 483954, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0393571853637695, "global_step": 483955, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9748730659484863, "global_step": 483956, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0591228008270264, "global_step": 483957, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0063490867614746, "global_step": 483958, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0714564323425293, "global_step": 483959, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.040804862976074, "global_step": 483960, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0063607692718506, "global_step": 483961, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0556626319885254, "global_step": 483962, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9997469186782837, "global_step": 483963, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0627214908599854, "global_step": 483964, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9804960489273071, "global_step": 483965, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0695416927337646, "global_step": 483966, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9874330759048462, "global_step": 483967, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.051187753677368, "global_step": 483968, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.149698495864868, "global_step": 483969, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0252199172973633, "global_step": 483970, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0465803146362305, "global_step": 483971, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0582568645477295, "global_step": 483972, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0716841220855713, "global_step": 483973, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1313092708587646, "global_step": 483974, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0518341064453125, "global_step": 483975, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1073570251464844, "global_step": 483976, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.039637804031372, "global_step": 483977, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0294060707092285, "global_step": 483978, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.036573886871338, "global_step": 483979, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0918240547180176, "global_step": 483980, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0441648960113525, "global_step": 483981, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.014648914337158, "global_step": 483982, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.084836959838867, "global_step": 483983, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0521225929260254, "global_step": 483984, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1544108390808105, "global_step": 483985, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.039026975631714, "global_step": 483986, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0362513065338135, "global_step": 483987, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1013729572296143, "global_step": 483988, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9970412254333496, "global_step": 483989, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.081575632095337, "global_step": 483990, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0937888622283936, "global_step": 483991, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.051408529281616, "global_step": 483992, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0537497997283936, "global_step": 483993, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0899906158447266, "global_step": 483994, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0249946117401123, "global_step": 483995, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0781025886535645, "global_step": 483996, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0472960472106934, "global_step": 483997, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.042602062225342, "global_step": 483998, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.109748601913452, "global_step": 483999, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1146247386932373, "global_step": 484000, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9629228115081787, "global_step": 484001, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9797028303146362, "global_step": 484002, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9512701034545898, "global_step": 484003, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1207661628723145, "global_step": 484004, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0644826889038086, "global_step": 484005, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.103555202484131, "global_step": 484006, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1131012439727783, "global_step": 484007, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.048402786254883, "global_step": 484008, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.070849657058716, "global_step": 484009, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1194732189178467, "global_step": 484010, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.031864643096924, "global_step": 484011, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0820083618164062, "global_step": 484012, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0584731101989746, "global_step": 484013, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1487739086151123, "global_step": 484014, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.095341920852661, "global_step": 484015, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.998580813407898, "global_step": 484016, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.014582872390747, "global_step": 484017, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9786678552627563, "global_step": 484018, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0974597930908203, "global_step": 484019, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9910030364990234, "global_step": 484020, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1561882495880127, "global_step": 484021, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0885837078094482, "global_step": 484022, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.058528184890747, "global_step": 484023, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1225860118865967, "global_step": 484024, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.2196786403656006, "global_step": 484025, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0945358276367188, "global_step": 484026, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0767781734466553, "global_step": 484027, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1055634021759033, "global_step": 484028, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0305843353271484, "global_step": 484029, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0759270191192627, "global_step": 484030, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9681957960128784, "global_step": 484031, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.094538927078247, "global_step": 484032, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0910251140594482, "global_step": 484033, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0727643966674805, "global_step": 484034, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.022904634475708, "global_step": 484035, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.146230697631836, "global_step": 484036, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0306484699249268, "global_step": 484037, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.056637763977051, "global_step": 484038, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0542094707489014, "global_step": 484039, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.118304491043091, "global_step": 484040, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.086953639984131, "global_step": 484041, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9994103908538818, "global_step": 484042, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.036367416381836, "global_step": 484043, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.09736704826355, "global_step": 484044, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0236287117004395, "global_step": 484045, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.010173797607422, "global_step": 484046, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0312306880950928, "global_step": 484047, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0977087020874023, "global_step": 484048, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0998852252960205, "global_step": 484049, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1385366916656494, "global_step": 484050, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.998487949371338, "global_step": 484051, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0628058910369873, "global_step": 484052, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0919740200042725, "global_step": 484053, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0838265419006348, "global_step": 484054, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0861897468566895, "global_step": 484055, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1502861976623535, "global_step": 484056, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0485689640045166, "global_step": 484057, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.051358938217163, "global_step": 484058, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0432775020599365, "global_step": 484059, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.033849000930786, "global_step": 484060, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.080227851867676, "global_step": 484061, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0402023792266846, "global_step": 484062, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.053250551223755, "global_step": 484063, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.060918092727661, "global_step": 484064, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.079291582107544, "global_step": 484065, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0610032081604004, "global_step": 484066, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0319392681121826, "global_step": 484067, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.053224802017212, "global_step": 484068, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.075899362564087, "global_step": 484069, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9985729455947876, "global_step": 484070, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0987234115600586, "global_step": 484071, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.987265944480896, "global_step": 484072, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0097873210906982, "global_step": 484073, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.988786220550537, "global_step": 484074, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0389630794525146, "global_step": 484075, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1096763610839844, "global_step": 484076, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0588436126708984, "global_step": 484077, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.191277265548706, "global_step": 484078, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0251708030700684, "global_step": 484079, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.113081693649292, "global_step": 484080, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.053208351135254, "global_step": 484081, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.097168207168579, "global_step": 484082, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1041481494903564, "global_step": 484083, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.174316883087158, "global_step": 484084, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0747644901275635, "global_step": 484085, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0400850772857666, "global_step": 484086, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0598483085632324, "global_step": 484087, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.070631742477417, "global_step": 484088, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.020676612854004, "global_step": 484089, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0411834716796875, "global_step": 484090, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1292881965637207, "global_step": 484091, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9433201551437378, "global_step": 484092, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.992385745048523, "global_step": 484093, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1189498901367188, "global_step": 484094, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.05996036529541, "global_step": 484095, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.084606647491455, "global_step": 484096, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0262672901153564, "global_step": 484097, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.071486473083496, "global_step": 484098, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1204447746276855, "global_step": 484099, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0600404739379883, "global_step": 484100, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9787765741348267, "global_step": 484101, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.056499481201172, "global_step": 484102, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0378189086914062, "global_step": 484103, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.977204442024231, "global_step": 484104, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0806100368499756, "global_step": 484105, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0726301670074463, "global_step": 484106, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.035940647125244, "global_step": 484107, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.034120798110962, "global_step": 484108, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0365960597991943, "global_step": 484109, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.108895778656006, "global_step": 484110, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9979125261306763, "global_step": 484111, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0602684020996094, "global_step": 484112, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0776357650756836, "global_step": 484113, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0241403579711914, "global_step": 484114, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.090172052383423, "global_step": 484115, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0446183681488037, "global_step": 484116, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.057706594467163, "global_step": 484117, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.122992992401123, "global_step": 484118, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1703109741210938, "global_step": 484119, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.117149591445923, "global_step": 484120, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0352749824523926, "global_step": 484121, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.059220790863037, "global_step": 484122, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.118077039718628, "global_step": 484123, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.08731746673584, "global_step": 484124, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0857162475585938, "global_step": 484125, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.130293607711792, "global_step": 484126, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9771273136138916, "global_step": 484127, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0935864448547363, "global_step": 484128, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.055572986602783, "global_step": 484129, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.097784996032715, "global_step": 484130, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.030829668045044, "global_step": 484131, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0897679328918457, "global_step": 484132, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1892025470733643, "global_step": 484133, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0976760387420654, "global_step": 484134, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0566866397857666, "global_step": 484135, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0469138622283936, "global_step": 484136, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9785208702087402, "global_step": 484137, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0028936862945557, "global_step": 484138, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.019908905029297, "global_step": 484139, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0717175006866455, "global_step": 484140, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.056711196899414, "global_step": 484141, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.195406913757324, "global_step": 484142, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0337557792663574, "global_step": 484143, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.027531385421753, "global_step": 484144, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0344934463500977, "global_step": 484145, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0229063034057617, "global_step": 484146, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.054016351699829, "global_step": 484147, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0838515758514404, "global_step": 484148, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.038011074066162, "global_step": 484149, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.052304744720459, "global_step": 484150, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0799081325531006, "global_step": 484151, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0995495319366455, "global_step": 484152, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.102748394012451, "global_step": 484153, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.035888671875, "global_step": 484154, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.075089693069458, "global_step": 484155, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.967820405960083, "global_step": 484156, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.120199680328369, "global_step": 484157, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1130154132843018, "global_step": 484158, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0535292625427246, "global_step": 484159, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0557572841644287, "global_step": 484160, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0918996334075928, "global_step": 484161, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0055017471313477, "global_step": 484162, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.137821674346924, "global_step": 484163, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0440335273742676, "global_step": 484164, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9430172443389893, "global_step": 484165, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.038022994995117, "global_step": 484166, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.00742244720459, "global_step": 484167, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.060896635055542, "global_step": 484168, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.974014163017273, "global_step": 484169, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.15194034576416, "global_step": 484170, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.102494239807129, "global_step": 484171, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.140327215194702, "global_step": 484172, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0665934085845947, "global_step": 484173, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0161349773406982, "global_step": 484174, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.089613914489746, "global_step": 484175, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.056227922439575, "global_step": 484176, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1472525596618652, "global_step": 484177, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0708892345428467, "global_step": 484178, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.052295207977295, "global_step": 484179, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1148760318756104, "global_step": 484180, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9907478094100952, "global_step": 484181, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1374173164367676, "global_step": 484182, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0339674949645996, "global_step": 484183, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.019256830215454, "global_step": 484184, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0338616371154785, "global_step": 484185, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9655319452285767, "global_step": 484186, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0301601886749268, "global_step": 484187, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.06467604637146, "global_step": 484188, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.099665403366089, "global_step": 484189, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0993664264678955, "global_step": 484190, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0721282958984375, "global_step": 484191, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.10072660446167, "global_step": 484192, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1400539875030518, "global_step": 484193, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.037158489227295, "global_step": 484194, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.17173433303833, "global_step": 484195, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0587642192840576, "global_step": 484196, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0306003093719482, "global_step": 484197, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0343472957611084, "global_step": 484198, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.097931385040283, "global_step": 484199, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.01312518119812, "global_step": 484200, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9927036762237549, "global_step": 484201, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.078911781311035, "global_step": 484202, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1265347003936768, "global_step": 484203, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0433497428894043, "global_step": 484204, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.038191795349121, "global_step": 484205, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.000767230987549, "global_step": 484206, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.054795503616333, "global_step": 484207, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0816433429718018, "global_step": 484208, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.121033191680908, "global_step": 484209, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0038692951202393, "global_step": 484210, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9997706413269043, "global_step": 484211, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0459632873535156, "global_step": 484212, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0213735103607178, "global_step": 484213, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0976669788360596, "global_step": 484214, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.055881977081299, "global_step": 484215, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.085218906402588, "global_step": 484216, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.080528497695923, "global_step": 484217, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1800172328948975, "global_step": 484218, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.087193012237549, "global_step": 484219, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.054385185241699, "global_step": 484220, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.030492067337036, "global_step": 484221, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0177319049835205, "global_step": 484222, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0823934078216553, "global_step": 484223, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.008845329284668, "global_step": 484224, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0628676414489746, "global_step": 484225, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0335886478424072, "global_step": 484226, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.097987651824951, "global_step": 484227, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0304033756256104, "global_step": 484228, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0110340118408203, "global_step": 484229, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1342265605926514, "global_step": 484230, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0968761444091797, "global_step": 484231, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9784002304077148, "global_step": 484232, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.098048686981201, "global_step": 484233, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0452322959899902, "global_step": 484234, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.011669397354126, "global_step": 484235, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1642544269561768, "global_step": 484236, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.058631658554077, "global_step": 484237, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0763232707977295, "global_step": 484238, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.027726650238037, "global_step": 484239, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0363550186157227, "global_step": 484240, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1235461235046387, "global_step": 484241, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.067917585372925, "global_step": 484242, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0670268535614014, "global_step": 484243, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.094836711883545, "global_step": 484244, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1269824504852295, "global_step": 484245, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.020355463027954, "global_step": 484246, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9784859418869019, "global_step": 484247, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0109007358551025, "global_step": 484248, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0524563789367676, "global_step": 484249, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0728495121002197, "global_step": 484250, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0400288105010986, "global_step": 484251, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.109088897705078, "global_step": 484252, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9853495359420776, "global_step": 484253, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.090409517288208, "global_step": 484254, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0073986053466797, "global_step": 484255, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.101310968399048, "global_step": 484256, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.104292631149292, "global_step": 484257, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0553343296051025, "global_step": 484258, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0157196521759033, "global_step": 484259, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.057673692703247, "global_step": 484260, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9566982984542847, "global_step": 484261, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0767242908477783, "global_step": 484262, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.041741371154785, "global_step": 484263, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.118776798248291, "global_step": 484264, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0914337635040283, "global_step": 484265, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.034052610397339, "global_step": 484266, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0348386764526367, "global_step": 484267, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0965843200683594, "global_step": 484268, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.107253074645996, "global_step": 484269, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0816380977630615, "global_step": 484270, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1513733863830566, "global_step": 484271, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.077570676803589, "global_step": 484272, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.019580602645874, "global_step": 484273, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9954657554626465, "global_step": 484274, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.074624538421631, "global_step": 484275, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.11051082611084, "global_step": 484276, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0979645252227783, "global_step": 484277, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.040351152420044, "global_step": 484278, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0998547077178955, "global_step": 484279, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9961986541748047, "global_step": 484280, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.132542133331299, "global_step": 484281, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.085787296295166, "global_step": 484282, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.013482093811035, "global_step": 484283, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0187907218933105, "global_step": 484284, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.044656991958618, "global_step": 484285, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9995090961456299, "global_step": 484286, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0226616859436035, "global_step": 484287, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0754201412200928, "global_step": 484288, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0394153594970703, "global_step": 484289, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9873586893081665, "global_step": 484290, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.092041254043579, "global_step": 484291, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0138683319091797, "global_step": 484292, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.076106071472168, "global_step": 484293, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.982007622718811, "global_step": 484294, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.092843532562256, "global_step": 484295, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1153416633605957, "global_step": 484296, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0636000633239746, "global_step": 484297, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0795648097991943, "global_step": 484298, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.048086166381836, "global_step": 484299, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.080904483795166, "global_step": 484300, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0939254760742188, "global_step": 484301, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0800437927246094, "global_step": 484302, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0330960750579834, "global_step": 484303, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.017652988433838, "global_step": 484304, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.063856363296509, "global_step": 484305, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.081512928009033, "global_step": 484306, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.060673713684082, "global_step": 484307, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0848071575164795, "global_step": 484308, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0656228065490723, "global_step": 484309, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0263118743896484, "global_step": 484310, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0946176052093506, "global_step": 484311, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.02573823928833, "global_step": 484312, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.079468250274658, "global_step": 484313, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.055274486541748, "global_step": 484314, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.149778366088867, "global_step": 484315, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.145420551300049, "global_step": 484316, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.042273759841919, "global_step": 484317, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.099306106567383, "global_step": 484318, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0309765338897705, "global_step": 484319, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1435604095458984, "global_step": 484320, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0675458908081055, "global_step": 484321, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.094715118408203, "global_step": 484322, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0324501991271973, "global_step": 484323, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.042276382446289, "global_step": 484324, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0918776988983154, "global_step": 484325, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0668630599975586, "global_step": 484326, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0280117988586426, "global_step": 484327, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.021577835083008, "global_step": 484328, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0925278663635254, "global_step": 484329, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0831990242004395, "global_step": 484330, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.094592571258545, "global_step": 484331, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.052231550216675, "global_step": 484332, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0267891883850098, "global_step": 484333, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.031485080718994, "global_step": 484334, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.060045003890991, "global_step": 484335, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.195223331451416, "global_step": 484336, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.983359694480896, "global_step": 484337, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0026395320892334, "global_step": 484338, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.133815288543701, "global_step": 484339, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0585927963256836, "global_step": 484340, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.013097047805786, "global_step": 484341, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.038607597351074, "global_step": 484342, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0536584854125977, "global_step": 484343, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.973716139793396, "global_step": 484344, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.031090259552002, "global_step": 484345, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0479116439819336, "global_step": 484346, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0756564140319824, "global_step": 484347, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0315423011779785, "global_step": 484348, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1756856441497803, "global_step": 484349, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.091326951980591, "global_step": 484350, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1256425380706787, "global_step": 484351, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0547893047332764, "global_step": 484352, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0316097736358643, "global_step": 484353, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.057983636856079, "global_step": 484354, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1175472736358643, "global_step": 484355, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.042543649673462, "global_step": 484356, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0500924587249756, "global_step": 484357, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.000697135925293, "global_step": 484358, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0662529468536377, "global_step": 484359, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0837457180023193, "global_step": 484360, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.104252815246582, "global_step": 484361, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9931055307388306, "global_step": 484362, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0959296226501465, "global_step": 484363, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9883695840835571, "global_step": 484364, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0898704528808594, "global_step": 484365, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0598337650299072, "global_step": 484366, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.080977439880371, "global_step": 484367, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0097086429595947, "global_step": 484368, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1119892597198486, "global_step": 484369, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.134983777999878, "global_step": 484370, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0363996028900146, "global_step": 484371, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0875754356384277, "global_step": 484372, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.076791763305664, "global_step": 484373, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.05845308303833, "global_step": 484374, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0962064266204834, "global_step": 484375, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.123339891433716, "global_step": 484376, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0024657249450684, "global_step": 484377, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0583043098449707, "global_step": 484378, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0287957191467285, "global_step": 484379, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0553345680236816, "global_step": 484380, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.071730613708496, "global_step": 484381, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0739731788635254, "global_step": 484382, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0603103637695312, "global_step": 484383, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0849733352661133, "global_step": 484384, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9673418998718262, "global_step": 484385, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.019805908203125, "global_step": 484386, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0020127296447754, "global_step": 484387, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0812301635742188, "global_step": 484388, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9766250848770142, "global_step": 484389, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.030608892440796, "global_step": 484390, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.065664529800415, "global_step": 484391, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1168642044067383, "global_step": 484392, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9880093336105347, "global_step": 484393, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.045079231262207, "global_step": 484394, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0988404750823975, "global_step": 484395, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0090394020080566, "global_step": 484396, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0416922569274902, "global_step": 484397, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0680599212646484, "global_step": 484398, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0117554664611816, "global_step": 484399, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0275306701660156, "global_step": 484400, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0388901233673096, "global_step": 484401, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0323619842529297, "global_step": 484402, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.067784070968628, "global_step": 484403, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.102303981781006, "global_step": 484404, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.058209180831909, "global_step": 484405, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.10406756401062, "global_step": 484406, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9991248846054077, "global_step": 484407, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0693883895874023, "global_step": 484408, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1030380725860596, "global_step": 484409, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9748032093048096, "global_step": 484410, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.962013840675354, "global_step": 484411, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1231155395507812, "global_step": 484412, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0774476528167725, "global_step": 484413, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0988593101501465, "global_step": 484414, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1311464309692383, "global_step": 484415, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9825412034988403, "global_step": 484416, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0378386974334717, "global_step": 484417, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.061741828918457, "global_step": 484418, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0346767902374268, "global_step": 484419, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.019927501678467, "global_step": 484420, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0086960792541504, "global_step": 484421, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1571602821350098, "global_step": 484422, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.040595769882202, "global_step": 484423, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.08609938621521, "global_step": 484424, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0369338989257812, "global_step": 484425, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.14666485786438, "global_step": 484426, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0630831718444824, "global_step": 484427, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0283737182617188, "global_step": 484428, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.063605308532715, "global_step": 484429, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.044726610183716, "global_step": 484430, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9968165159225464, "global_step": 484431, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.020831823348999, "global_step": 484432, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0407893657684326, "global_step": 484433, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.079209327697754, "global_step": 484434, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0858235359191895, "global_step": 484435, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1679012775421143, "global_step": 484436, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0820870399475098, "global_step": 484437, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0296170711517334, "global_step": 484438, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0108611583709717, "global_step": 484439, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0720748901367188, "global_step": 484440, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0534799098968506, "global_step": 484441, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1155080795288086, "global_step": 484442, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.057992458343506, "global_step": 484443, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9636050462722778, "global_step": 484444, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.118332624435425, "global_step": 484445, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.928984522819519, "global_step": 484446, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9946987628936768, "global_step": 484447, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9565688371658325, "global_step": 484448, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0653741359710693, "global_step": 484449, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1031525135040283, "global_step": 484450, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.048379898071289, "global_step": 484451, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.024632453918457, "global_step": 484452, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.2013649940490723, "global_step": 484453, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0197458267211914, "global_step": 484454, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.094721794128418, "global_step": 484455, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.989804744720459, "global_step": 484456, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0787060260772705, "global_step": 484457, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.045868158340454, "global_step": 484458, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9831066131591797, "global_step": 484459, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0423853397369385, "global_step": 484460, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.024543285369873, "global_step": 484461, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0488762855529785, "global_step": 484462, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1261467933654785, "global_step": 484463, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0666840076446533, "global_step": 484464, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0364906787872314, "global_step": 484465, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.022002696990967, "global_step": 484466, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0675148963928223, "global_step": 484467, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.08036470413208, "global_step": 484468, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0740137100219727, "global_step": 484469, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1122095584869385, "global_step": 484470, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0868332386016846, "global_step": 484471, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9680554866790771, "global_step": 484472, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0846099853515625, "global_step": 484473, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0666964054107666, "global_step": 484474, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0030205249786377, "global_step": 484475, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0186305046081543, "global_step": 484476, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.142413854598999, "global_step": 484477, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.090000867843628, "global_step": 484478, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.05312180519104, "global_step": 484479, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.026360034942627, "global_step": 484480, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.087390661239624, "global_step": 484481, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.045290231704712, "global_step": 484482, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0250346660614014, "global_step": 484483, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.020434617996216, "global_step": 484484, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.089263677597046, "global_step": 484485, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.099128246307373, "global_step": 484486, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.148336410522461, "global_step": 484487, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0318620204925537, "global_step": 484488, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.063883066177368, "global_step": 484489, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.025895118713379, "global_step": 484490, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0049045085906982, "global_step": 484491, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1353063583374023, "global_step": 484492, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.104717493057251, "global_step": 484493, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0857348442077637, "global_step": 484494, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1073358058929443, "global_step": 484495, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.112246513366699, "global_step": 484496, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.13386607170105, "global_step": 484497, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0860114097595215, "global_step": 484498, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.075571298599243, "global_step": 484499, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0869343280792236, "global_step": 484500, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1708433628082275, "global_step": 484501, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0503430366516113, "global_step": 484502, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0267391204833984, "global_step": 484503, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1372320652008057, "global_step": 484504, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0523128509521484, "global_step": 484505, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.085865020751953, "global_step": 484506, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1242268085479736, "global_step": 484507, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0455055236816406, "global_step": 484508, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9532570838928223, "global_step": 484509, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0619280338287354, "global_step": 484510, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9967252016067505, "global_step": 484511, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0958728790283203, "global_step": 484512, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.088996171951294, "global_step": 484513, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.069585084915161, "global_step": 484514, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9725350141525269, "global_step": 484515, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.114781379699707, "global_step": 484516, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.087143898010254, "global_step": 484517, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.164910316467285, "global_step": 484518, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0645267963409424, "global_step": 484519, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0980782508850098, "global_step": 484520, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0726912021636963, "global_step": 484521, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.046387195587158, "global_step": 484522, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.114071846008301, "global_step": 484523, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0486841201782227, "global_step": 484524, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0886406898498535, "global_step": 484525, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0227468013763428, "global_step": 484526, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.136709213256836, "global_step": 484527, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.09075927734375, "global_step": 484528, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.030540943145752, "global_step": 484529, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0785388946533203, "global_step": 484530, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0532264709472656, "global_step": 484531, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0439581871032715, "global_step": 484532, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0816566944122314, "global_step": 484533, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0767741203308105, "global_step": 484534, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1306347846984863, "global_step": 484535, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0325605869293213, "global_step": 484536, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.132768392562866, "global_step": 484537, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.10656476020813, "global_step": 484538, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.017113208770752, "global_step": 484539, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0880091190338135, "global_step": 484540, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.032510280609131, "global_step": 484541, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.060743570327759, "global_step": 484542, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.087364673614502, "global_step": 484543, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0508933067321777, "global_step": 484544, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1909642219543457, "global_step": 484545, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0253021717071533, "global_step": 484546, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9759721755981445, "global_step": 484547, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.010471820831299, "global_step": 484548, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.151916980743408, "global_step": 484549, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.123586416244507, "global_step": 484550, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0378732681274414, "global_step": 484551, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1090564727783203, "global_step": 484552, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.041564464569092, "global_step": 484553, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.030425548553467, "global_step": 484554, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0317928791046143, "global_step": 484555, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9815257787704468, "global_step": 484556, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0660643577575684, "global_step": 484557, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.040203094482422, "global_step": 484558, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0514118671417236, "global_step": 484559, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1293251514434814, "global_step": 484560, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0810279846191406, "global_step": 484561, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.11334228515625, "global_step": 484562, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1224186420440674, "global_step": 484563, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0555267333984375, "global_step": 484564, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.060757875442505, "global_step": 484565, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9982558488845825, "global_step": 484566, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0691471099853516, "global_step": 484567, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0935235023498535, "global_step": 484568, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.071000576019287, "global_step": 484569, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.163574695587158, "global_step": 484570, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0245516300201416, "global_step": 484571, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.968458890914917, "global_step": 484572, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1879184246063232, "global_step": 484573, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.112027645111084, "global_step": 484574, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1332972049713135, "global_step": 484575, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0038485527038574, "global_step": 484576, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.035027027130127, "global_step": 484577, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.006901741027832, "global_step": 484578, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.023585557937622, "global_step": 484579, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0714969635009766, "global_step": 484580, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.06854510307312, "global_step": 484581, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.059600591659546, "global_step": 484582, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.052469253540039, "global_step": 484583, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0640125274658203, "global_step": 484584, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.042766809463501, "global_step": 484585, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0919768810272217, "global_step": 484586, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9815295934677124, "global_step": 484587, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0926718711853027, "global_step": 484588, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9384267330169678, "global_step": 484589, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0356340408325195, "global_step": 484590, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9828791618347168, "global_step": 484591, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0578250885009766, "global_step": 484592, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.070221424102783, "global_step": 484593, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.09675931930542, "global_step": 484594, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0382442474365234, "global_step": 484595, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.062025547027588, "global_step": 484596, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1810860633850098, "global_step": 484597, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.051095962524414, "global_step": 484598, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1150588989257812, "global_step": 484599, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0528512001037598, "global_step": 484600, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.053112030029297, "global_step": 484601, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.119300365447998, "global_step": 484602, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.028536796569824, "global_step": 484603, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.119394540786743, "global_step": 484604, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9206186532974243, "global_step": 484605, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1384854316711426, "global_step": 484606, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0399343967437744, "global_step": 484607, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0073065757751465, "global_step": 484608, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.058382511138916, "global_step": 484609, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0845513343811035, "global_step": 484610, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1078712940216064, "global_step": 484611, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9471834897994995, "global_step": 484612, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.040292501449585, "global_step": 484613, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.130462169647217, "global_step": 484614, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.069044828414917, "global_step": 484615, "epoch": 849, "lr": 5e-05}
{"train_loss": 1.9950329065322876, "global_step": 484616, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0819380283355713, "global_step": 484617, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.038217067718506, "global_step": 484618, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0341570377349854, "global_step": 484619, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0906383991241455, "global_step": 484620, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0757391452789307, "global_step": 484621, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.140040874481201, "global_step": 484622, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.050201177597046, "global_step": 484623, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.012934684753418, "global_step": 484624, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0127251148223877, "global_step": 484625, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.055499315261841, "global_step": 484626, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1004490852355957, "global_step": 484627, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0337512493133545, "global_step": 484628, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.1419553756713867, "global_step": 484629, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0425612926483154, "global_step": 484630, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.0287106037139893, "global_step": 484631, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.05880069732666, "global_step": 484632, "epoch": 849, "lr": 5e-05}
{"train_loss": 2.022404670715332, "global_step": 484633, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9578908681869507, "global_step": 484634, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.015026569366455, "global_step": 484635, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9869604110717773, "global_step": 484636, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.044330358505249, "global_step": 484637, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0733299255371094, "global_step": 484638, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9985703229904175, "global_step": 484639, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.022439479827881, "global_step": 484640, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0637295246124268, "global_step": 484641, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0176897048950195, "global_step": 484642, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0950064659118652, "global_step": 484643, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0267629623413086, "global_step": 484644, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0529837608337402, "global_step": 484645, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0587005615234375, "global_step": 484646, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.152153253555298, "global_step": 484647, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9909024238586426, "global_step": 484648, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9907176494598389, "global_step": 484649, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.115734100341797, "global_step": 484650, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.016343355178833, "global_step": 484651, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9562398195266724, "global_step": 484652, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0552613735198975, "global_step": 484653, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.069729804992676, "global_step": 484654, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.073066234588623, "global_step": 484655, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1037118434906006, "global_step": 484656, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0836386680603027, "global_step": 484657, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0193324089050293, "global_step": 484658, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9989947080612183, "global_step": 484659, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.961802363395691, "global_step": 484660, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.038395404815674, "global_step": 484661, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9517971277236938, "global_step": 484662, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0876314640045166, "global_step": 484663, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0122690200805664, "global_step": 484664, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.076547861099243, "global_step": 484665, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.09257435798645, "global_step": 484666, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0687761306762695, "global_step": 484667, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.981812596321106, "global_step": 484668, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9805465936660767, "global_step": 484669, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.105656147003174, "global_step": 484670, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.01165771484375, "global_step": 484671, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.033947706222534, "global_step": 484672, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0830767154693604, "global_step": 484673, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0611026287078857, "global_step": 484674, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.075693130493164, "global_step": 484675, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.03875994682312, "global_step": 484676, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0610196590423584, "global_step": 484677, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.11378812789917, "global_step": 484678, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.094362735748291, "global_step": 484679, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9658575057983398, "global_step": 484680, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.082035541534424, "global_step": 484681, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.000382661819458, "global_step": 484682, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9849557876586914, "global_step": 484683, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9697128534317017, "global_step": 484684, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0546939373016357, "global_step": 484685, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0399580001831055, "global_step": 484686, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.116953134536743, "global_step": 484687, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1065056324005127, "global_step": 484688, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9860713481903076, "global_step": 484689, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.086352825164795, "global_step": 484690, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.029985189437866, "global_step": 484691, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1011478900909424, "global_step": 484692, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9836434125900269, "global_step": 484693, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0263559818267822, "global_step": 484694, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0483810901641846, "global_step": 484695, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1471633911132812, "global_step": 484696, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0921404361724854, "global_step": 484697, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.94748055934906, "global_step": 484698, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0326578617095947, "global_step": 484699, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0772452354431152, "global_step": 484700, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0535521507263184, "global_step": 484701, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9746052026748657, "global_step": 484702, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.093327760696411, "global_step": 484703, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0985419750213623, "global_step": 484704, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9686321020126343, "global_step": 484705, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9916839599609375, "global_step": 484706, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.034627914428711, "global_step": 484707, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1561009883880615, "global_step": 484708, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0340330600738525, "global_step": 484709, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.060373306274414, "global_step": 484710, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9913321733474731, "global_step": 484711, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.034167528152466, "global_step": 484712, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.070683717727661, "global_step": 484713, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.158773899078369, "global_step": 484714, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.002657175064087, "global_step": 484715, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.047295570373535, "global_step": 484716, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.016258955001831, "global_step": 484717, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.104978561401367, "global_step": 484718, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0622997283935547, "global_step": 484719, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0706753730773926, "global_step": 484720, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.057440996170044, "global_step": 484721, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1024858951568604, "global_step": 484722, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.046428918838501, "global_step": 484723, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1178677082061768, "global_step": 484724, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1880099773406982, "global_step": 484725, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1467578411102295, "global_step": 484726, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.020528793334961, "global_step": 484727, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0455310344696045, "global_step": 484728, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0765719413757324, "global_step": 484729, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.049055576324463, "global_step": 484730, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0647425651550293, "global_step": 484731, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0958423614501953, "global_step": 484732, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.088143825531006, "global_step": 484733, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0739026069641113, "global_step": 484734, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0766215324401855, "global_step": 484735, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.019911289215088, "global_step": 484736, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.038511037826538, "global_step": 484737, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.058410406112671, "global_step": 484738, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9883099794387817, "global_step": 484739, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0162084102630615, "global_step": 484740, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0386087894439697, "global_step": 484741, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9258393049240112, "global_step": 484742, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.11023211479187, "global_step": 484743, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0407817363739014, "global_step": 484744, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1035118103027344, "global_step": 484745, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9763503074645996, "global_step": 484746, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9833574295043945, "global_step": 484747, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9931445121765137, "global_step": 484748, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.989558458328247, "global_step": 484749, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.09903883934021, "global_step": 484750, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9999935626983643, "global_step": 484751, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.066819429397583, "global_step": 484752, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.072183609008789, "global_step": 484753, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9985135793685913, "global_step": 484754, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0557987689971924, "global_step": 484755, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0656652450561523, "global_step": 484756, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.011035680770874, "global_step": 484757, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.954878568649292, "global_step": 484758, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.069096326828003, "global_step": 484759, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.985382080078125, "global_step": 484760, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.961512804031372, "global_step": 484761, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0858192443847656, "global_step": 484762, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0616724491119385, "global_step": 484763, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0603127479553223, "global_step": 484764, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0694243907928467, "global_step": 484765, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.139150381088257, "global_step": 484766, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9906491041183472, "global_step": 484767, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0574898719787598, "global_step": 484768, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0019824504852295, "global_step": 484769, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.032810688018799, "global_step": 484770, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9840360879898071, "global_step": 484771, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0075013637542725, "global_step": 484772, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.063366651535034, "global_step": 484773, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0535571575164795, "global_step": 484774, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.101578712463379, "global_step": 484775, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.974703073501587, "global_step": 484776, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1522648334503174, "global_step": 484777, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.063242197036743, "global_step": 484778, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.028080701828003, "global_step": 484779, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.095308303833008, "global_step": 484780, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.066854476928711, "global_step": 484781, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0293188095092773, "global_step": 484782, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0343644618988037, "global_step": 484783, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0827295780181885, "global_step": 484784, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9818308353424072, "global_step": 484785, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.113538980484009, "global_step": 484786, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0829994678497314, "global_step": 484787, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.963247537612915, "global_step": 484788, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.013690233230591, "global_step": 484789, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.007185935974121, "global_step": 484790, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.01436448097229, "global_step": 484791, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.079927444458008, "global_step": 484792, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0529520511627197, "global_step": 484793, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0843114852905273, "global_step": 484794, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0627663135528564, "global_step": 484795, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.110222101211548, "global_step": 484796, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.054417133331299, "global_step": 484797, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0133697986602783, "global_step": 484798, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0569958686828613, "global_step": 484799, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.11637544631958, "global_step": 484800, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.041571617126465, "global_step": 484801, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9579663276672363, "global_step": 484802, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9860483407974243, "global_step": 484803, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0235373973846436, "global_step": 484804, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.982576608657837, "global_step": 484805, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0652499198913574, "global_step": 484806, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.057535171508789, "global_step": 484807, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9043455123901367, "global_step": 484808, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9625085592269897, "global_step": 484809, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0900051593780518, "global_step": 484810, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9813401699066162, "global_step": 484811, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1153695583343506, "global_step": 484812, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1163527965545654, "global_step": 484813, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0509681701660156, "global_step": 484814, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0219650268554688, "global_step": 484815, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0958797931671143, "global_step": 484816, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0659267902374268, "global_step": 484817, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1165244579315186, "global_step": 484818, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.132277250289917, "global_step": 484819, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1224658489227295, "global_step": 484820, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0621328353881836, "global_step": 484821, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0352885723114014, "global_step": 484822, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0121073722839355, "global_step": 484823, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1060950756073, "global_step": 484824, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0202863216400146, "global_step": 484825, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.06282114982605, "global_step": 484826, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.108635187149048, "global_step": 484827, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0821282863616943, "global_step": 484828, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.126025915145874, "global_step": 484829, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9603530168533325, "global_step": 484830, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0904953479766846, "global_step": 484831, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.054638624191284, "global_step": 484832, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1022555828094482, "global_step": 484833, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9854868650436401, "global_step": 484834, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.058763027191162, "global_step": 484835, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0614519119262695, "global_step": 484836, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0016627311706543, "global_step": 484837, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0389821529388428, "global_step": 484838, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.120450973510742, "global_step": 484839, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.963464379310608, "global_step": 484840, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.114750862121582, "global_step": 484841, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0135436058044434, "global_step": 484842, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.06381893157959, "global_step": 484843, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0441393852233887, "global_step": 484844, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9950464963912964, "global_step": 484845, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0417866706848145, "global_step": 484846, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1033480167388916, "global_step": 484847, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0881080627441406, "global_step": 484848, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.159972906112671, "global_step": 484849, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.018381357192993, "global_step": 484850, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.019864320755005, "global_step": 484851, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.11079478263855, "global_step": 484852, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0336034297943115, "global_step": 484853, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0152077674865723, "global_step": 484854, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.010324478149414, "global_step": 484855, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0638427734375, "global_step": 484856, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.048199415206909, "global_step": 484857, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0669023990631104, "global_step": 484858, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1303179264068604, "global_step": 484859, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0830023288726807, "global_step": 484860, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1438841819763184, "global_step": 484861, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0875651836395264, "global_step": 484862, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.104215621948242, "global_step": 484863, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.175424337387085, "global_step": 484864, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.057615280151367, "global_step": 484865, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.028552770614624, "global_step": 484866, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0712339878082275, "global_step": 484867, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.077852487564087, "global_step": 484868, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.089303970336914, "global_step": 484869, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.120457649230957, "global_step": 484870, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1221823692321777, "global_step": 484871, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.089621067047119, "global_step": 484872, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0852088928222656, "global_step": 484873, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.066316843032837, "global_step": 484874, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.086570978164673, "global_step": 484875, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0988993644714355, "global_step": 484876, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1074371337890625, "global_step": 484877, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0437116622924805, "global_step": 484878, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.00547456741333, "global_step": 484879, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0698184967041016, "global_step": 484880, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.955501675605774, "global_step": 484881, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9804542064666748, "global_step": 484882, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.126394033432007, "global_step": 484883, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.058955430984497, "global_step": 484884, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.974308729171753, "global_step": 484885, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.08479380607605, "global_step": 484886, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0779151916503906, "global_step": 484887, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0586912631988525, "global_step": 484888, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0834100246429443, "global_step": 484889, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.048121213912964, "global_step": 484890, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.006971597671509, "global_step": 484891, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.117748260498047, "global_step": 484892, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0131497383117676, "global_step": 484893, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0717694759368896, "global_step": 484894, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.065962076187134, "global_step": 484895, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1507019996643066, "global_step": 484896, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.129371404647827, "global_step": 484897, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.000627040863037, "global_step": 484898, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.028012752532959, "global_step": 484899, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9650822877883911, "global_step": 484900, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1051933765411377, "global_step": 484901, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9884724617004395, "global_step": 484902, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1134376525878906, "global_step": 484903, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.115553379058838, "global_step": 484904, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.009190082550049, "global_step": 484905, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0754270553588867, "global_step": 484906, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0041134357452393, "global_step": 484907, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9800513982772827, "global_step": 484908, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9912958145141602, "global_step": 484909, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0698530673980713, "global_step": 484910, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1062140464782715, "global_step": 484911, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1073179244995117, "global_step": 484912, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.992817759513855, "global_step": 484913, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.999235987663269, "global_step": 484914, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.065530776977539, "global_step": 484915, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.124589443206787, "global_step": 484916, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1781840324401855, "global_step": 484917, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1427459716796875, "global_step": 484918, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.001871109008789, "global_step": 484919, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.984871506690979, "global_step": 484920, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9425742626190186, "global_step": 484921, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.043728828430176, "global_step": 484922, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0645968914031982, "global_step": 484923, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.015655040740967, "global_step": 484924, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0125575065612793, "global_step": 484925, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.092165470123291, "global_step": 484926, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9522000551223755, "global_step": 484927, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.006549835205078, "global_step": 484928, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0784122943878174, "global_step": 484929, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.036069393157959, "global_step": 484930, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0606908798217773, "global_step": 484931, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1082603931427, "global_step": 484932, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.040498733520508, "global_step": 484933, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.052517890930176, "global_step": 484934, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.033285617828369, "global_step": 484935, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0638232231140137, "global_step": 484936, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1221437454223633, "global_step": 484937, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0676567554473877, "global_step": 484938, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0273401737213135, "global_step": 484939, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0614986419677734, "global_step": 484940, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.087390184402466, "global_step": 484941, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.015615701675415, "global_step": 484942, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.014171600341797, "global_step": 484943, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0826900005340576, "global_step": 484944, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.077373504638672, "global_step": 484945, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9784972667694092, "global_step": 484946, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.187800884246826, "global_step": 484947, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1135027408599854, "global_step": 484948, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0253939628601074, "global_step": 484949, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0143356323242188, "global_step": 484950, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0527825355529785, "global_step": 484951, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1081905364990234, "global_step": 484952, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0192394256591797, "global_step": 484953, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9389934539794922, "global_step": 484954, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9983171224594116, "global_step": 484955, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9863747358322144, "global_step": 484956, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.019613265991211, "global_step": 484957, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9791964292526245, "global_step": 484958, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.102943181991577, "global_step": 484959, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1600112915039062, "global_step": 484960, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9359307289123535, "global_step": 484961, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9972344636917114, "global_step": 484962, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9949822425842285, "global_step": 484963, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0648181438446045, "global_step": 484964, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0979621410369873, "global_step": 484965, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.020495891571045, "global_step": 484966, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.062005043029785, "global_step": 484967, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0494282245635986, "global_step": 484968, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0160088539123535, "global_step": 484969, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.062260389328003, "global_step": 484970, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.150456428527832, "global_step": 484971, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1038973331451416, "global_step": 484972, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.121208667755127, "global_step": 484973, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.011444091796875, "global_step": 484974, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1063055992126465, "global_step": 484975, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0461366176605225, "global_step": 484976, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.099320650100708, "global_step": 484977, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0251951217651367, "global_step": 484978, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0893502235412598, "global_step": 484979, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0889458656311035, "global_step": 484980, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.105255603790283, "global_step": 484981, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0132946968078613, "global_step": 484982, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0889790058135986, "global_step": 484983, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.102727174758911, "global_step": 484984, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0941689014434814, "global_step": 484985, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0404274463653564, "global_step": 484986, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.18329119682312, "global_step": 484987, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.016244888305664, "global_step": 484988, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.947016954421997, "global_step": 484989, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1329503059387207, "global_step": 484990, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.006566286087036, "global_step": 484991, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.074662446975708, "global_step": 484992, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1165404319763184, "global_step": 484993, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0714380741119385, "global_step": 484994, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.120922565460205, "global_step": 484995, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0955965518951416, "global_step": 484996, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9816064834594727, "global_step": 484997, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.005502462387085, "global_step": 484998, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1268577575683594, "global_step": 484999, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.150149345397949, "global_step": 485000, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.067553758621216, "global_step": 485001, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0843138694763184, "global_step": 485002, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.034977674484253, "global_step": 485003, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9016811847686768, "global_step": 485004, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.046391487121582, "global_step": 485005, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0780391693115234, "global_step": 485006, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0513503551483154, "global_step": 485007, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0996291637420654, "global_step": 485008, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0524585247039795, "global_step": 485009, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.956335186958313, "global_step": 485010, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0520901679992676, "global_step": 485011, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0861334800720215, "global_step": 485012, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0585544109344482, "global_step": 485013, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1443071365356445, "global_step": 485014, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.032339334487915, "global_step": 485015, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.072465658187866, "global_step": 485016, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.062235116958618, "global_step": 485017, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0678110122680664, "global_step": 485018, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0348904132843018, "global_step": 485019, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9949519634246826, "global_step": 485020, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0094943046569824, "global_step": 485021, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.07023024559021, "global_step": 485022, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.068087339401245, "global_step": 485023, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9597878456115723, "global_step": 485024, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0364418029785156, "global_step": 485025, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0676045417785645, "global_step": 485026, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.015394687652588, "global_step": 485027, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0164945125579834, "global_step": 485028, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.022428274154663, "global_step": 485029, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1895055770874023, "global_step": 485030, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0883004665374756, "global_step": 485031, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0688655376434326, "global_step": 485032, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0498549938201904, "global_step": 485033, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.101280927658081, "global_step": 485034, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.113572359085083, "global_step": 485035, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.004460096359253, "global_step": 485036, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.2037651538848877, "global_step": 485037, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.020536422729492, "global_step": 485038, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.07326602935791, "global_step": 485039, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.127704620361328, "global_step": 485040, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.048189163208008, "global_step": 485041, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0931222438812256, "global_step": 485042, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.114873170852661, "global_step": 485043, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.102550745010376, "global_step": 485044, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.086545944213867, "global_step": 485045, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9718984365463257, "global_step": 485046, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.093383550643921, "global_step": 485047, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0694050788879395, "global_step": 485048, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.01041316986084, "global_step": 485049, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.104116439819336, "global_step": 485050, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0616748332977295, "global_step": 485051, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0856544971466064, "global_step": 485052, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1083779335021973, "global_step": 485053, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0353856086730957, "global_step": 485054, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.026947498321533, "global_step": 485055, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9836214780807495, "global_step": 485056, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0418314933776855, "global_step": 485057, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0073769092559814, "global_step": 485058, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.056809186935425, "global_step": 485059, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0451431274414062, "global_step": 485060, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.03839111328125, "global_step": 485061, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0735666751861572, "global_step": 485062, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.045067548751831, "global_step": 485063, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.020098924636841, "global_step": 485064, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.076920509338379, "global_step": 485065, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.108198642730713, "global_step": 485066, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9834859371185303, "global_step": 485067, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0591161251068115, "global_step": 485068, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1319780349731445, "global_step": 485069, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.104275941848755, "global_step": 485070, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0768754482269287, "global_step": 485071, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0796964168548584, "global_step": 485072, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.016484498977661, "global_step": 485073, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.057048797607422, "global_step": 485074, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.100309133529663, "global_step": 485075, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.030104875564575, "global_step": 485076, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0510339736938477, "global_step": 485077, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1033380031585693, "global_step": 485078, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0439798831939697, "global_step": 485079, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.105573892593384, "global_step": 485080, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1333250999450684, "global_step": 485081, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1204514503479004, "global_step": 485082, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1181302070617676, "global_step": 485083, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.053448438644409, "global_step": 485084, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.006225347518921, "global_step": 485085, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.108029842376709, "global_step": 485086, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.078554630279541, "global_step": 485087, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9654247760772705, "global_step": 485088, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1165566444396973, "global_step": 485089, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1059281826019287, "global_step": 485090, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0980489253997803, "global_step": 485091, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0311315059661865, "global_step": 485092, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0738298892974854, "global_step": 485093, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.112901210784912, "global_step": 485094, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0380594730377197, "global_step": 485095, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9511969089508057, "global_step": 485096, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.017415761947632, "global_step": 485097, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0443851947784424, "global_step": 485098, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0482430458068848, "global_step": 485099, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0122690200805664, "global_step": 485100, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0548086166381836, "global_step": 485101, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.001070976257324, "global_step": 485102, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.150268793106079, "global_step": 485103, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.022632598876953, "global_step": 485104, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1348602771759033, "global_step": 485105, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1088032722473145, "global_step": 485106, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0164241790771484, "global_step": 485107, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.100125551223755, "global_step": 485108, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0076231956481934, "global_step": 485109, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0678954124450684, "global_step": 485110, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0516364574432373, "global_step": 485111, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1532671451568604, "global_step": 485112, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.046600341796875, "global_step": 485113, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0372509956359863, "global_step": 485114, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.066328525543213, "global_step": 485115, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.031812906265259, "global_step": 485116, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.072847366333008, "global_step": 485117, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1078696250915527, "global_step": 485118, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.051658868789673, "global_step": 485119, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9852827787399292, "global_step": 485120, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0632412433624268, "global_step": 485121, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0941061973571777, "global_step": 485122, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0926053524017334, "global_step": 485123, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9930126667022705, "global_step": 485124, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0919017791748047, "global_step": 485125, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.129102945327759, "global_step": 485126, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0898184776306152, "global_step": 485127, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0619120597839355, "global_step": 485128, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0240464210510254, "global_step": 485129, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.045419216156006, "global_step": 485130, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0365264415740967, "global_step": 485131, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.054443120956421, "global_step": 485132, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.077131986618042, "global_step": 485133, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9937546253204346, "global_step": 485134, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0512194633483887, "global_step": 485135, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0690059661865234, "global_step": 485136, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0318198204040527, "global_step": 485137, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.075127124786377, "global_step": 485138, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.141897678375244, "global_step": 485139, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0117437839508057, "global_step": 485140, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9896748065948486, "global_step": 485141, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0796284675598145, "global_step": 485142, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.067133665084839, "global_step": 485143, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.078763961791992, "global_step": 485144, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0888214111328125, "global_step": 485145, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.02557110786438, "global_step": 485146, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1275181770324707, "global_step": 485147, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.086665630340576, "global_step": 485148, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0990684032440186, "global_step": 485149, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1803479194641113, "global_step": 485150, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0678317546844482, "global_step": 485151, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1018474102020264, "global_step": 485152, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.115319013595581, "global_step": 485153, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0665149688720703, "global_step": 485154, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.101567506790161, "global_step": 485155, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.991888165473938, "global_step": 485156, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.046515464782715, "global_step": 485157, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9895071983337402, "global_step": 485158, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0669751167297363, "global_step": 485159, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0456202030181885, "global_step": 485160, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0292177200317383, "global_step": 485161, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0512044429779053, "global_step": 485162, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0703318119049072, "global_step": 485163, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.079393148422241, "global_step": 485164, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.065206527709961, "global_step": 485165, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0153563022613525, "global_step": 485166, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0280187129974365, "global_step": 485167, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.012263298034668, "global_step": 485168, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0043108463287354, "global_step": 485169, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0962111949920654, "global_step": 485170, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0434653759002686, "global_step": 485171, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0838229656219482, "global_step": 485172, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0791382789611816, "global_step": 485173, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.041304588317871, "global_step": 485174, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1067094802856445, "global_step": 485175, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1250860691070557, "global_step": 485176, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0052061080932617, "global_step": 485177, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9529273509979248, "global_step": 485178, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.083202362060547, "global_step": 485179, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1168549060821533, "global_step": 485180, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.048701524734497, "global_step": 485181, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0710456371307373, "global_step": 485182, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.051818609237671, "global_step": 485183, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.106060743331909, "global_step": 485184, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.072154998779297, "global_step": 485185, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.062594413757324, "global_step": 485186, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1027965545654297, "global_step": 485187, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0134825706481934, "global_step": 485188, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.023629903793335, "global_step": 485189, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0161101818084717, "global_step": 485190, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0457019805908203, "global_step": 485191, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.09067702293396, "global_step": 485192, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1052589416503906, "global_step": 485193, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0917372703552246, "global_step": 485194, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.031658411026001, "global_step": 485195, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0583176612854004, "global_step": 485196, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9345494508743286, "global_step": 485197, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.032250165939331, "global_step": 485198, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0503857135772705, "global_step": 485199, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.008887529373169, "global_step": 485200, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9412614107131958, "global_step": 485201, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1274099349975586, "global_step": 485202, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.954735517501831, "global_step": 485203, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.069323778152466, "global_step": 485204, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0670583248138428, "global_step": 485205, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.081691026687622, "global_step": 485206, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0789616107940674, "global_step": 485207, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.162017822265625, "global_step": 485208, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.991227626800537, "global_step": 485209, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.044186592102051, "global_step": 485210, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.072558879852295, "global_step": 485211, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1290030479431152, "global_step": 485212, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.062483072280884, "global_step": 485213, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1415488719940186, "global_step": 485214, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0545642375946045, "global_step": 485215, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0574774742126465, "global_step": 485216, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1038355827331543, "global_step": 485217, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0782108306884766, "global_step": 485218, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9703519344329834, "global_step": 485219, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.015962600708008, "global_step": 485220, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.165825843811035, "global_step": 485221, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.006364345550537, "global_step": 485222, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0549187660217285, "global_step": 485223, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1016530990600586, "global_step": 485224, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.065997838973999, "global_step": 485225, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0817291736602783, "global_step": 485226, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.082008123397827, "global_step": 485227, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0936625003814697, "global_step": 485228, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0387821197509766, "global_step": 485229, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.99007248878479, "global_step": 485230, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.2098283767700195, "global_step": 485231, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.097169876098633, "global_step": 485232, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.053081512451172, "global_step": 485233, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.068930149078369, "global_step": 485234, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.05317759513855, "global_step": 485235, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.115027904510498, "global_step": 485236, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0881614685058594, "global_step": 485237, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0028655529022217, "global_step": 485238, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.053403377532959, "global_step": 485239, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0841965675354004, "global_step": 485240, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.117449998855591, "global_step": 485241, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.087812900543213, "global_step": 485242, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.024304151535034, "global_step": 485243, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.100654363632202, "global_step": 485244, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0331380367279053, "global_step": 485245, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.046440839767456, "global_step": 485246, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.100856304168701, "global_step": 485247, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0882387161254883, "global_step": 485248, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1016619205474854, "global_step": 485249, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.149965524673462, "global_step": 485250, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0312178134918213, "global_step": 485251, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0498874187469482, "global_step": 485252, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0985536575317383, "global_step": 485253, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.118759870529175, "global_step": 485254, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0096077919006348, "global_step": 485255, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0862812995910645, "global_step": 485256, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0679924488067627, "global_step": 485257, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0518555641174316, "global_step": 485258, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.111389398574829, "global_step": 485259, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1613588333129883, "global_step": 485260, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.051666736602783, "global_step": 485261, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.048840284347534, "global_step": 485262, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0458290576934814, "global_step": 485263, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.106515407562256, "global_step": 485264, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9296188354492188, "global_step": 485265, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0594277381896973, "global_step": 485266, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0786983966827393, "global_step": 485267, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0114970207214355, "global_step": 485268, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.105743169784546, "global_step": 485269, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9970648288726807, "global_step": 485270, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0510811805725098, "global_step": 485271, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0986411571502686, "global_step": 485272, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0699241161346436, "global_step": 485273, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.980049967765808, "global_step": 485274, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0379257202148438, "global_step": 485275, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0891551971435547, "global_step": 485276, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9864957332611084, "global_step": 485277, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0814857482910156, "global_step": 485278, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.097689628601074, "global_step": 485279, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.089453935623169, "global_step": 485280, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0579898357391357, "global_step": 485281, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0797855854034424, "global_step": 485282, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9924875497817993, "global_step": 485283, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0368704795837402, "global_step": 485284, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9704581499099731, "global_step": 485285, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0876359939575195, "global_step": 485286, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0748281478881836, "global_step": 485287, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.040358066558838, "global_step": 485288, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9999967813491821, "global_step": 485289, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.025947332382202, "global_step": 485290, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1036057472229004, "global_step": 485291, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1167359352111816, "global_step": 485292, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0562775135040283, "global_step": 485293, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.071662425994873, "global_step": 485294, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.981711983680725, "global_step": 485295, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1313154697418213, "global_step": 485296, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1536929607391357, "global_step": 485297, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0950169563293457, "global_step": 485298, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1033947467803955, "global_step": 485299, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0743093490600586, "global_step": 485300, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9835346937179565, "global_step": 485301, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0657856464385986, "global_step": 485302, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0997493267059326, "global_step": 485303, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.052395820617676, "global_step": 485304, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.054692268371582, "global_step": 485305, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1300196647644043, "global_step": 485306, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0358150005340576, "global_step": 485307, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9934474229812622, "global_step": 485308, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.112470865249634, "global_step": 485309, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.051194190979004, "global_step": 485310, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.026952028274536, "global_step": 485311, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.06711745262146, "global_step": 485312, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.023981809616089, "global_step": 485313, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0541038513183594, "global_step": 485314, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.08030104637146, "global_step": 485315, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1310431957244873, "global_step": 485316, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.023996114730835, "global_step": 485317, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0857832431793213, "global_step": 485318, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0712380409240723, "global_step": 485319, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.016631841659546, "global_step": 485320, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0331201553344727, "global_step": 485321, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.123774290084839, "global_step": 485322, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.080430269241333, "global_step": 485323, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.092480182647705, "global_step": 485324, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0276215076446533, "global_step": 485325, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0489039421081543, "global_step": 485326, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0220019817352295, "global_step": 485327, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0320982933044434, "global_step": 485328, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0393223762512207, "global_step": 485329, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9528155326843262, "global_step": 485330, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.109147071838379, "global_step": 485331, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0491671562194824, "global_step": 485332, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9525362253189087, "global_step": 485333, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0483274459838867, "global_step": 485334, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1187615394592285, "global_step": 485335, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.024869918823242, "global_step": 485336, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.144432783126831, "global_step": 485337, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.093299627304077, "global_step": 485338, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1068191528320312, "global_step": 485339, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1152708530426025, "global_step": 485340, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0500192642211914, "global_step": 485341, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.084404706954956, "global_step": 485342, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0866363048553467, "global_step": 485343, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.093096971511841, "global_step": 485344, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0704851150512695, "global_step": 485345, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0207912921905518, "global_step": 485346, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.11126708984375, "global_step": 485347, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.118509292602539, "global_step": 485348, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.074782133102417, "global_step": 485349, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0080599784851074, "global_step": 485350, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0886971950531006, "global_step": 485351, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1003942489624023, "global_step": 485352, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0228271484375, "global_step": 485353, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.089036464691162, "global_step": 485354, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0520923137664795, "global_step": 485355, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.044400215148926, "global_step": 485356, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.988332748413086, "global_step": 485357, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0005733966827393, "global_step": 485358, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1270065307617188, "global_step": 485359, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0834429264068604, "global_step": 485360, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1201319694519043, "global_step": 485361, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.985588550567627, "global_step": 485362, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.973214864730835, "global_step": 485363, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0441503524780273, "global_step": 485364, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0344419479370117, "global_step": 485365, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0990447998046875, "global_step": 485366, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0343358516693115, "global_step": 485367, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1121482849121094, "global_step": 485368, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.001918077468872, "global_step": 485369, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1183009147644043, "global_step": 485370, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0000462532043457, "global_step": 485371, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9882614612579346, "global_step": 485372, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.055069923400879, "global_step": 485373, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.077369451522827, "global_step": 485374, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.066084623336792, "global_step": 485375, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9882326126098633, "global_step": 485376, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.056089401245117, "global_step": 485377, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.020315408706665, "global_step": 485378, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9820919036865234, "global_step": 485379, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.095719814300537, "global_step": 485380, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1013286113739014, "global_step": 485381, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0631096363067627, "global_step": 485382, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0868706703186035, "global_step": 485383, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0517332553863525, "global_step": 485384, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.078295946121216, "global_step": 485385, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9936420917510986, "global_step": 485386, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.132004976272583, "global_step": 485387, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.051250696182251, "global_step": 485388, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9582792520523071, "global_step": 485389, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.074066162109375, "global_step": 485390, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.061338186264038, "global_step": 485391, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0908565521240234, "global_step": 485392, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0673208236694336, "global_step": 485393, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.05924654006958, "global_step": 485394, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.091728448867798, "global_step": 485395, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0626304149627686, "global_step": 485396, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0668246746063232, "global_step": 485397, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.063962459564209, "global_step": 485398, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.088829517364502, "global_step": 485399, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0380806922912598, "global_step": 485400, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.078115701675415, "global_step": 485401, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.048590898513794, "global_step": 485402, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0656449794769287, "global_step": 485403, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0742251873016357, "global_step": 485404, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.122950792312622, "global_step": 485405, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1132729053497314, "global_step": 485406, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.013301134109497, "global_step": 485407, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.067229747772217, "global_step": 485408, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.029841184616089, "global_step": 485409, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0816876888275146, "global_step": 485410, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1445155143737793, "global_step": 485411, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0216705799102783, "global_step": 485412, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0999324321746826, "global_step": 485413, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.096651315689087, "global_step": 485414, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.038034200668335, "global_step": 485415, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.028970241546631, "global_step": 485416, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9866855144500732, "global_step": 485417, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0472376346588135, "global_step": 485418, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1826581954956055, "global_step": 485419, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1490044593811035, "global_step": 485420, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.036245822906494, "global_step": 485421, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0866546630859375, "global_step": 485422, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9786412715911865, "global_step": 485423, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.043076276779175, "global_step": 485424, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1069278717041016, "global_step": 485425, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.110985279083252, "global_step": 485426, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0602710247039795, "global_step": 485427, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0816097259521484, "global_step": 485428, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.071345329284668, "global_step": 485429, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.081892967224121, "global_step": 485430, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.133974075317383, "global_step": 485431, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0454554557800293, "global_step": 485432, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.129661798477173, "global_step": 485433, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0441906452178955, "global_step": 485434, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.100825309753418, "global_step": 485435, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9508507251739502, "global_step": 485436, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9965604543685913, "global_step": 485437, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.999843955039978, "global_step": 485438, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.044813394546509, "global_step": 485439, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0371594429016113, "global_step": 485440, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1193816661834717, "global_step": 485441, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0173892974853516, "global_step": 485442, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0879874229431152, "global_step": 485443, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0502898693084717, "global_step": 485444, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.048729419708252, "global_step": 485445, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9942474365234375, "global_step": 485446, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1593658924102783, "global_step": 485447, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1130263805389404, "global_step": 485448, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.052438497543335, "global_step": 485449, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0600686073303223, "global_step": 485450, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.105870246887207, "global_step": 485451, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.079806089401245, "global_step": 485452, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0773112773895264, "global_step": 485453, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0368142127990723, "global_step": 485454, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0642125606536865, "global_step": 485455, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9777332544326782, "global_step": 485456, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.02758526802063, "global_step": 485457, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.130028486251831, "global_step": 485458, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0424964427948, "global_step": 485459, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1497650146484375, "global_step": 485460, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1110808849334717, "global_step": 485461, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0714447498321533, "global_step": 485462, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0756914615631104, "global_step": 485463, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0643527507781982, "global_step": 485464, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.06439471244812, "global_step": 485465, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0796139240264893, "global_step": 485466, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0688493251800537, "global_step": 485467, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.029421329498291, "global_step": 485468, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0291733741760254, "global_step": 485469, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0188865661621094, "global_step": 485470, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.087614059448242, "global_step": 485471, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0018844604492188, "global_step": 485472, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0546748638153076, "global_step": 485473, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0563125610351562, "global_step": 485474, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0774056911468506, "global_step": 485475, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9684257507324219, "global_step": 485476, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.121831178665161, "global_step": 485477, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.153388023376465, "global_step": 485478, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.033841133117676, "global_step": 485479, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1708571910858154, "global_step": 485480, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.117156982421875, "global_step": 485481, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0814831256866455, "global_step": 485482, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0880022048950195, "global_step": 485483, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.083073377609253, "global_step": 485484, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0175037384033203, "global_step": 485485, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.066669464111328, "global_step": 485486, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0388472080230713, "global_step": 485487, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0810306072235107, "global_step": 485488, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0237624645233154, "global_step": 485489, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.077662944793701, "global_step": 485490, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1142067909240723, "global_step": 485491, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9596563577651978, "global_step": 485492, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0578577518463135, "global_step": 485493, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1131396293640137, "global_step": 485494, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.118112087249756, "global_step": 485495, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0068211555480957, "global_step": 485496, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.012953758239746, "global_step": 485497, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0800673961639404, "global_step": 485498, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0848283767700195, "global_step": 485499, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1307992935180664, "global_step": 485500, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.039668083190918, "global_step": 485501, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1087191104888916, "global_step": 485502, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.114708423614502, "global_step": 485503, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.085343360900879, "global_step": 485504, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.065619468688965, "global_step": 485505, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.02709698677063, "global_step": 485506, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1000218391418457, "global_step": 485507, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0762321949005127, "global_step": 485508, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0742082595825195, "global_step": 485509, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.139941692352295, "global_step": 485510, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.101609945297241, "global_step": 485511, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.092313289642334, "global_step": 485512, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0408003330230713, "global_step": 485513, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0238428115844727, "global_step": 485514, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.112821102142334, "global_step": 485515, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.075183868408203, "global_step": 485516, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0777792930603027, "global_step": 485517, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1166820526123047, "global_step": 485518, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0590810775756836, "global_step": 485519, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.026317834854126, "global_step": 485520, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.045541763305664, "global_step": 485521, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.004664897918701, "global_step": 485522, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.040191888809204, "global_step": 485523, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1598458290100098, "global_step": 485524, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.060192108154297, "global_step": 485525, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.054996967315674, "global_step": 485526, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.115328311920166, "global_step": 485527, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.099557876586914, "global_step": 485528, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.124516725540161, "global_step": 485529, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.115027666091919, "global_step": 485530, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1137537956237793, "global_step": 485531, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0668435096740723, "global_step": 485532, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.017092227935791, "global_step": 485533, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0569682121276855, "global_step": 485534, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0156235694885254, "global_step": 485535, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0544180870056152, "global_step": 485536, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0461177825927734, "global_step": 485537, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0418903827667236, "global_step": 485538, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.020193576812744, "global_step": 485539, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.123577833175659, "global_step": 485540, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0869507789611816, "global_step": 485541, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0333595275878906, "global_step": 485542, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9686952829360962, "global_step": 485543, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.9971466064453125, "global_step": 485544, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.103905439376831, "global_step": 485545, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.167417049407959, "global_step": 485546, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.094470977783203, "global_step": 485547, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0721983909606934, "global_step": 485548, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0486631393432617, "global_step": 485549, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.968314290046692, "global_step": 485550, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1046371459960938, "global_step": 485551, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.023409366607666, "global_step": 485552, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.052677869796753, "global_step": 485553, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.128758668899536, "global_step": 485554, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0727486610412598, "global_step": 485555, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.029299020767212, "global_step": 485556, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0639164447784424, "global_step": 485557, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1528053283691406, "global_step": 485558, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0776994228363037, "global_step": 485559, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0877909660339355, "global_step": 485560, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0773558616638184, "global_step": 485561, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0480189323425293, "global_step": 485562, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0789992809295654, "global_step": 485563, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.174302339553833, "global_step": 485564, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.219315528869629, "global_step": 485565, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.125955581665039, "global_step": 485566, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.031101703643799, "global_step": 485567, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.103759765625, "global_step": 485568, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0479230880737305, "global_step": 485569, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1011672019958496, "global_step": 485570, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0164411067962646, "global_step": 485571, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.095767021179199, "global_step": 485572, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1141092777252197, "global_step": 485573, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.004178762435913, "global_step": 485574, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.062190055847168, "global_step": 485575, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.06543231010437, "global_step": 485576, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.007991313934326, "global_step": 485577, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0523266792297363, "global_step": 485578, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1031558513641357, "global_step": 485579, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0425288677215576, "global_step": 485580, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0742218494415283, "global_step": 485581, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1130855083465576, "global_step": 485582, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0697338581085205, "global_step": 485583, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.102598190307617, "global_step": 485584, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.123493194580078, "global_step": 485585, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0708529949188232, "global_step": 485586, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0540826320648193, "global_step": 485587, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0814247131347656, "global_step": 485588, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0911948680877686, "global_step": 485589, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.147559881210327, "global_step": 485590, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0849146842956543, "global_step": 485591, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0995779037475586, "global_step": 485592, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0086333751678467, "global_step": 485593, "epoch": 850, "lr": 5e-05}
{"train_loss": 1.962336540222168, "global_step": 485594, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.071085214614868, "global_step": 485595, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0500757694244385, "global_step": 485596, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.037433385848999, "global_step": 485597, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.1157238483428955, "global_step": 485598, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.092755079269409, "global_step": 485599, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0696072578430176, "global_step": 485600, "epoch": 850, "lr": 5e-05}
{"train_loss": 2.0597474575042725, "global_step": 485601, "epoch": 850, "lr": 5e-05, "KITCHEN_SCENE6_put_the_yellow_and_white_mug_in_the_microwave_and_close_it/mean_success_rate": 0.8333333333333334, "LIVING_ROOM_SCENE2_put_both_the_alphabet_soup_and_the_tomato_sauce_in_the_basket/mean_success_rate": 0.0, "STUDY_SCENE1_pick_up_the_book_and_place_it_in_the_back_compartment_of_the_caddy/mean_success_rate": 0.5666666666666667, "KITCHEN_SCENE8_put_both_moka_pots_on_the_stove/mean_success_rate": 0.36666666666666664, "LIVING_ROOM_SCENE5_put_the_white_mug_on_the_left_plate_and_put_the_yellow_and_white_mug_on_the_right_plate/mean_success_rate": 0.3333333333333333, "LIVING_ROOM_SCENE6_put_the_white_mug_on_the_plate_and_put_the_chocolate_pudding_to_the_right_of_the_plate/mean_success_rate": 0.4, "KITCHEN_SCENE4_put_the_black_bowl_in_the_bottom_drawer_of_the_cabinet_and_close_it/mean_success_rate": 0.9, "LIVING_ROOM_SCENE2_put_both_the_cream_cheese_box_and_the_butter_in_the_basket/mean_success_rate": 0.5, "LIVING_ROOM_SCENE1_put_both_the_alphabet_soup_and_the_cream_cheese_box_in_the_basket/mean_success_rate": 0.0, "KITCHEN_SCENE3_turn_on_the_stove_and_put_the_moka_pot_on_it/mean_success_rate": 0.8333333333333334, "mean_success_rate": 0.47333333333333333, "val_loss": 5.707435131072998, "test_reconst_mse": 0.07312510162591934}
{"train_loss": 2.055192708969116, "global_step": 485602, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9857734441757202, "global_step": 485603, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9844701290130615, "global_step": 485604, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9695073366165161, "global_step": 485605, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9684066772460938, "global_step": 485606, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1093058586120605, "global_step": 485607, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0948212146759033, "global_step": 485608, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0025861263275146, "global_step": 485609, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.089021921157837, "global_step": 485610, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.049105405807495, "global_step": 485611, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9868108034133911, "global_step": 485612, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.095133066177368, "global_step": 485613, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0899813175201416, "global_step": 485614, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.037412643432617, "global_step": 485615, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0939810276031494, "global_step": 485616, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0490710735321045, "global_step": 485617, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.010242462158203, "global_step": 485618, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0339605808258057, "global_step": 485619, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.029562473297119, "global_step": 485620, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9954016208648682, "global_step": 485621, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0018558502197266, "global_step": 485622, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0659561157226562, "global_step": 485623, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.015916347503662, "global_step": 485624, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0779669284820557, "global_step": 485625, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0185892581939697, "global_step": 485626, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0444631576538086, "global_step": 485627, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1396381855010986, "global_step": 485628, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0728871822357178, "global_step": 485629, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.039264678955078, "global_step": 485630, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0786020755767822, "global_step": 485631, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0650477409362793, "global_step": 485632, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.103261947631836, "global_step": 485633, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0464961528778076, "global_step": 485634, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1082394123077393, "global_step": 485635, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.12693452835083, "global_step": 485636, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0883982181549072, "global_step": 485637, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.105997085571289, "global_step": 485638, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0769448280334473, "global_step": 485639, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1503031253814697, "global_step": 485640, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0217607021331787, "global_step": 485641, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1157898902893066, "global_step": 485642, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.104834794998169, "global_step": 485643, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1393210887908936, "global_step": 485644, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0472452640533447, "global_step": 485645, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.035001754760742, "global_step": 485646, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.994805932044983, "global_step": 485647, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0205483436584473, "global_step": 485648, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0598926544189453, "global_step": 485649, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0684046745300293, "global_step": 485650, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0679309368133545, "global_step": 485651, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.071178674697876, "global_step": 485652, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9393022060394287, "global_step": 485653, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.107304096221924, "global_step": 485654, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0573127269744873, "global_step": 485655, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1199259757995605, "global_step": 485656, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0460798740386963, "global_step": 485657, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.101468801498413, "global_step": 485658, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0761289596557617, "global_step": 485659, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0523383617401123, "global_step": 485660, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0344831943511963, "global_step": 485661, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.112057685852051, "global_step": 485662, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9796879291534424, "global_step": 485663, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9305672645568848, "global_step": 485664, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0111913681030273, "global_step": 485665, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0390963554382324, "global_step": 485666, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0543127059936523, "global_step": 485667, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.2067859172821045, "global_step": 485668, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0505878925323486, "global_step": 485669, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0700082778930664, "global_step": 485670, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9880201816558838, "global_step": 485671, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0455005168914795, "global_step": 485672, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0740275382995605, "global_step": 485673, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.129512071609497, "global_step": 485674, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0787975788116455, "global_step": 485675, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0801260471343994, "global_step": 485676, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.059065103530884, "global_step": 485677, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1210854053497314, "global_step": 485678, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.031534433364868, "global_step": 485679, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0576956272125244, "global_step": 485680, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.006086826324463, "global_step": 485681, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.044797897338867, "global_step": 485682, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.006338119506836, "global_step": 485683, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0729010105133057, "global_step": 485684, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.018095016479492, "global_step": 485685, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0983033180236816, "global_step": 485686, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1198153495788574, "global_step": 485687, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.039738416671753, "global_step": 485688, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.076813220977783, "global_step": 485689, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.061936616897583, "global_step": 485690, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.064488649368286, "global_step": 485691, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0168986320495605, "global_step": 485692, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.040706157684326, "global_step": 485693, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0487942695617676, "global_step": 485694, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1261842250823975, "global_step": 485695, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0577926635742188, "global_step": 485696, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.012006998062134, "global_step": 485697, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.133206605911255, "global_step": 485698, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9743540287017822, "global_step": 485699, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0439393520355225, "global_step": 485700, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0650572776794434, "global_step": 485701, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0244884490966797, "global_step": 485702, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.044771671295166, "global_step": 485703, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1181602478027344, "global_step": 485704, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0437636375427246, "global_step": 485705, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0112321376800537, "global_step": 485706, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.097654342651367, "global_step": 485707, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0654683113098145, "global_step": 485708, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.069185256958008, "global_step": 485709, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9857288599014282, "global_step": 485710, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.030906915664673, "global_step": 485711, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.060166120529175, "global_step": 485712, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.017914295196533, "global_step": 485713, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9958899021148682, "global_step": 485714, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.035315752029419, "global_step": 485715, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0399231910705566, "global_step": 485716, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0603187084198, "global_step": 485717, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9977660179138184, "global_step": 485718, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.038588285446167, "global_step": 485719, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9754749536514282, "global_step": 485720, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.029991626739502, "global_step": 485721, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.05460262298584, "global_step": 485722, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0528931617736816, "global_step": 485723, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.059239387512207, "global_step": 485724, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0828447341918945, "global_step": 485725, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0265021324157715, "global_step": 485726, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0709519386291504, "global_step": 485727, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0161290168762207, "global_step": 485728, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9849517345428467, "global_step": 485729, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0645689964294434, "global_step": 485730, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0897929668426514, "global_step": 485731, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.054149627685547, "global_step": 485732, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0518791675567627, "global_step": 485733, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9140892028808594, "global_step": 485734, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1242270469665527, "global_step": 485735, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0747478008270264, "global_step": 485736, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0247962474823, "global_step": 485737, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.999070405960083, "global_step": 485738, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.044644355773926, "global_step": 485739, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.035456895828247, "global_step": 485740, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.116940975189209, "global_step": 485741, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0503077507019043, "global_step": 485742, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0477075576782227, "global_step": 485743, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9919987916946411, "global_step": 485744, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.024724245071411, "global_step": 485745, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.013402223587036, "global_step": 485746, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.979830265045166, "global_step": 485747, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0720534324645996, "global_step": 485748, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1079578399658203, "global_step": 485749, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1037285327911377, "global_step": 485750, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0244662761688232, "global_step": 485751, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0351359844207764, "global_step": 485752, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.067564010620117, "global_step": 485753, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.077519655227661, "global_step": 485754, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.061419725418091, "global_step": 485755, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.080655097961426, "global_step": 485756, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.956180214881897, "global_step": 485757, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.004988193511963, "global_step": 485758, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0469894409179688, "global_step": 485759, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9867466688156128, "global_step": 485760, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9753336906433105, "global_step": 485761, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0081450939178467, "global_step": 485762, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0985448360443115, "global_step": 485763, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0566768646240234, "global_step": 485764, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.178995370864868, "global_step": 485765, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1157748699188232, "global_step": 485766, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.047090530395508, "global_step": 485767, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.112957715988159, "global_step": 485768, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.036198139190674, "global_step": 485769, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0399959087371826, "global_step": 485770, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9805036783218384, "global_step": 485771, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0997045040130615, "global_step": 485772, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0501718521118164, "global_step": 485773, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0930798053741455, "global_step": 485774, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9649121761322021, "global_step": 485775, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0391011238098145, "global_step": 485776, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0533649921417236, "global_step": 485777, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.145875930786133, "global_step": 485778, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.147254705429077, "global_step": 485779, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1369986534118652, "global_step": 485780, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.081195592880249, "global_step": 485781, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0752925872802734, "global_step": 485782, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9641540050506592, "global_step": 485783, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9877052307128906, "global_step": 485784, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0752625465393066, "global_step": 485785, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0736570358276367, "global_step": 485786, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9972848892211914, "global_step": 485787, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.032217025756836, "global_step": 485788, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.033116102218628, "global_step": 485789, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.07664155960083, "global_step": 485790, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.017158031463623, "global_step": 485791, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.030642032623291, "global_step": 485792, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.012016534805298, "global_step": 485793, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1333634853363037, "global_step": 485794, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.068293571472168, "global_step": 485795, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.039645195007324, "global_step": 485796, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.093597650527954, "global_step": 485797, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0571694374084473, "global_step": 485798, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0171446800231934, "global_step": 485799, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0516786575317383, "global_step": 485800, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9856446981430054, "global_step": 485801, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0248043537139893, "global_step": 485802, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.021611213684082, "global_step": 485803, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1170907020568848, "global_step": 485804, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.015449285507202, "global_step": 485805, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9913349151611328, "global_step": 485806, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.060349941253662, "global_step": 485807, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1303389072418213, "global_step": 485808, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.994388461112976, "global_step": 485809, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.003751754760742, "global_step": 485810, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.031606674194336, "global_step": 485811, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0406038761138916, "global_step": 485812, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.090689182281494, "global_step": 485813, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0013105869293213, "global_step": 485814, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0827133655548096, "global_step": 485815, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0238780975341797, "global_step": 485816, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0542399883270264, "global_step": 485817, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.080909490585327, "global_step": 485818, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1526570320129395, "global_step": 485819, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1543257236480713, "global_step": 485820, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1267716884613037, "global_step": 485821, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.139737606048584, "global_step": 485822, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0687246322631836, "global_step": 485823, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.102764844894409, "global_step": 485824, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0396320819854736, "global_step": 485825, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0516045093536377, "global_step": 485826, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1355772018432617, "global_step": 485827, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9811875820159912, "global_step": 485828, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9962869882583618, "global_step": 485829, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0682926177978516, "global_step": 485830, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.101865291595459, "global_step": 485831, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0252299308776855, "global_step": 485832, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.218668222427368, "global_step": 485833, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.121175765991211, "global_step": 485834, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.114820718765259, "global_step": 485835, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.002018928527832, "global_step": 485836, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0384891033172607, "global_step": 485837, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.995683193206787, "global_step": 485838, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1909091472625732, "global_step": 485839, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0652313232421875, "global_step": 485840, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0858771800994873, "global_step": 485841, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9587193727493286, "global_step": 485842, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1232168674468994, "global_step": 485843, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1047189235687256, "global_step": 485844, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9776744842529297, "global_step": 485845, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9993505477905273, "global_step": 485846, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9996681213378906, "global_step": 485847, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9847865104675293, "global_step": 485848, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0469772815704346, "global_step": 485849, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0850508213043213, "global_step": 485850, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.11456298828125, "global_step": 485851, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.15142822265625, "global_step": 485852, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0716888904571533, "global_step": 485853, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9932548999786377, "global_step": 485854, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0195281505584717, "global_step": 485855, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0332190990448, "global_step": 485856, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0215556621551514, "global_step": 485857, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.064765214920044, "global_step": 485858, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0095441341400146, "global_step": 485859, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.058873414993286, "global_step": 485860, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.103987455368042, "global_step": 485861, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.047017812728882, "global_step": 485862, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9758620262145996, "global_step": 485863, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0570240020751953, "global_step": 485864, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.077390193939209, "global_step": 485865, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1103296279907227, "global_step": 485866, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0193991661071777, "global_step": 485867, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.081929922103882, "global_step": 485868, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.042603015899658, "global_step": 485869, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0496811866760254, "global_step": 485870, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.057377576828003, "global_step": 485871, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.140871047973633, "global_step": 485872, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.121155023574829, "global_step": 485873, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0542657375335693, "global_step": 485874, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0471768379211426, "global_step": 485875, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.078835964202881, "global_step": 485876, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0397908687591553, "global_step": 485877, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.044259786605835, "global_step": 485878, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.075639009475708, "global_step": 485879, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.010500907897949, "global_step": 485880, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0005857944488525, "global_step": 485881, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.032437562942505, "global_step": 485882, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.082240343093872, "global_step": 485883, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.084547996520996, "global_step": 485884, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9789258241653442, "global_step": 485885, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.057324171066284, "global_step": 485886, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.148240089416504, "global_step": 485887, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.082671642303467, "global_step": 485888, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1036620140075684, "global_step": 485889, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9801172018051147, "global_step": 485890, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0033397674560547, "global_step": 485891, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0083117485046387, "global_step": 485892, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0471746921539307, "global_step": 485893, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.032064437866211, "global_step": 485894, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.016266345977783, "global_step": 485895, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.027801513671875, "global_step": 485896, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9969632625579834, "global_step": 485897, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0930213928222656, "global_step": 485898, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.052561044692993, "global_step": 485899, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0664522647857666, "global_step": 485900, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0301334857940674, "global_step": 485901, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1163928508758545, "global_step": 485902, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0475919246673584, "global_step": 485903, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.138657331466675, "global_step": 485904, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.107686996459961, "global_step": 485905, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0581021308898926, "global_step": 485906, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1151645183563232, "global_step": 485907, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.032611608505249, "global_step": 485908, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.019338607788086, "global_step": 485909, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.040620803833008, "global_step": 485910, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.051807165145874, "global_step": 485911, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0117928981781006, "global_step": 485912, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0373966693878174, "global_step": 485913, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0598549842834473, "global_step": 485914, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0652639865875244, "global_step": 485915, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1092004776000977, "global_step": 485916, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0249481201171875, "global_step": 485917, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9834808111190796, "global_step": 485918, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1067352294921875, "global_step": 485919, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0774893760681152, "global_step": 485920, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.028376579284668, "global_step": 485921, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.105311632156372, "global_step": 485922, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9580128192901611, "global_step": 485923, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1360440254211426, "global_step": 485924, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.109062671661377, "global_step": 485925, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.041684627532959, "global_step": 485926, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.035996437072754, "global_step": 485927, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0358874797821045, "global_step": 485928, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0500504970550537, "global_step": 485929, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1412367820739746, "global_step": 485930, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.104875087738037, "global_step": 485931, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0411007404327393, "global_step": 485932, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0292277336120605, "global_step": 485933, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0917959213256836, "global_step": 485934, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1309399604797363, "global_step": 485935, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1305603981018066, "global_step": 485936, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.050055980682373, "global_step": 485937, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.077420234680176, "global_step": 485938, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1082918643951416, "global_step": 485939, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.060044527053833, "global_step": 485940, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.137739658355713, "global_step": 485941, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0103492736816406, "global_step": 485942, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0421016216278076, "global_step": 485943, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0219321250915527, "global_step": 485944, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0964479446411133, "global_step": 485945, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0425305366516113, "global_step": 485946, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1220357418060303, "global_step": 485947, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.097905158996582, "global_step": 485948, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0807316303253174, "global_step": 485949, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.058854818344116, "global_step": 485950, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0031237602233887, "global_step": 485951, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9490643739700317, "global_step": 485952, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.165587902069092, "global_step": 485953, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0606038570404053, "global_step": 485954, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9919888973236084, "global_step": 485955, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0160720348358154, "global_step": 485956, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.056872844696045, "global_step": 485957, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0119707584381104, "global_step": 485958, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0525031089782715, "global_step": 485959, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0361897945404053, "global_step": 485960, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9715057611465454, "global_step": 485961, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.970324993133545, "global_step": 485962, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.034057378768921, "global_step": 485963, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.079555034637451, "global_step": 485964, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0335888862609863, "global_step": 485965, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.063293933868408, "global_step": 485966, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0428221225738525, "global_step": 485967, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9950382709503174, "global_step": 485968, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9970026016235352, "global_step": 485969, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.200946807861328, "global_step": 485970, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.031658887863159, "global_step": 485971, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9422131776809692, "global_step": 485972, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.010490894317627, "global_step": 485973, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.085099220275879, "global_step": 485974, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0370259284973145, "global_step": 485975, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.043100357055664, "global_step": 485976, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.056917190551758, "global_step": 485977, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.156698703765869, "global_step": 485978, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.00974440574646, "global_step": 485979, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1079583168029785, "global_step": 485980, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.065830945968628, "global_step": 485981, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.058800458908081, "global_step": 485982, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0995969772338867, "global_step": 485983, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.051503896713257, "global_step": 485984, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.988100528717041, "global_step": 485985, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1061158180236816, "global_step": 485986, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.090132236480713, "global_step": 485987, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0552804470062256, "global_step": 485988, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0675621032714844, "global_step": 485989, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.067568302154541, "global_step": 485990, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.092827320098877, "global_step": 485991, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.98573637008667, "global_step": 485992, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.07374906539917, "global_step": 485993, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9777913093566895, "global_step": 485994, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.063765287399292, "global_step": 485995, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1710033416748047, "global_step": 485996, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1352601051330566, "global_step": 485997, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.097477436065674, "global_step": 485998, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9647841453552246, "global_step": 485999, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.017064094543457, "global_step": 486000, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0751683712005615, "global_step": 486001, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0790047645568848, "global_step": 486002, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.028233528137207, "global_step": 486003, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0922458171844482, "global_step": 486004, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0346245765686035, "global_step": 486005, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0786619186401367, "global_step": 486006, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.117096185684204, "global_step": 486007, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1193928718566895, "global_step": 486008, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1020514965057373, "global_step": 486009, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.057663917541504, "global_step": 486010, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0202295780181885, "global_step": 486011, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0709362030029297, "global_step": 486012, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0119833946228027, "global_step": 486013, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0491995811462402, "global_step": 486014, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1113829612731934, "global_step": 486015, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9757611751556396, "global_step": 486016, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.078665018081665, "global_step": 486017, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1168301105499268, "global_step": 486018, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.057516574859619, "global_step": 486019, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0737338066101074, "global_step": 486020, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.122335195541382, "global_step": 486021, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1035573482513428, "global_step": 486022, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0985679626464844, "global_step": 486023, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1201674938201904, "global_step": 486024, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.141265869140625, "global_step": 486025, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.087528705596924, "global_step": 486026, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0820186138153076, "global_step": 486027, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1047449111938477, "global_step": 486028, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0304534435272217, "global_step": 486029, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0744073390960693, "global_step": 486030, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0597856044769287, "global_step": 486031, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9998847246170044, "global_step": 486032, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.133997917175293, "global_step": 486033, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.039748430252075, "global_step": 486034, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.994149088859558, "global_step": 486035, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1108410358428955, "global_step": 486036, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9897147417068481, "global_step": 486037, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.19987416267395, "global_step": 486038, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.11698055267334, "global_step": 486039, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0618834495544434, "global_step": 486040, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0577991008758545, "global_step": 486041, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0668208599090576, "global_step": 486042, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0468437671661377, "global_step": 486043, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.980661153793335, "global_step": 486044, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.103858232498169, "global_step": 486045, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0851571559906006, "global_step": 486046, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0537538528442383, "global_step": 486047, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.059316873550415, "global_step": 486048, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.05246639251709, "global_step": 486049, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0428617000579834, "global_step": 486050, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.065092086791992, "global_step": 486051, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.096074342727661, "global_step": 486052, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0449604988098145, "global_step": 486053, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.005939245223999, "global_step": 486054, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9998035430908203, "global_step": 486055, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.962751030921936, "global_step": 486056, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.114655017852783, "global_step": 486057, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0484251976013184, "global_step": 486058, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0407252311706543, "global_step": 486059, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0601115226745605, "global_step": 486060, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.085418462753296, "global_step": 486061, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1434028148651123, "global_step": 486062, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.973897099494934, "global_step": 486063, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.040626049041748, "global_step": 486064, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1230359077453613, "global_step": 486065, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0963757038116455, "global_step": 486066, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0370044708251953, "global_step": 486067, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.040074110031128, "global_step": 486068, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.000247001647949, "global_step": 486069, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0999643802642822, "global_step": 486070, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.086482524871826, "global_step": 486071, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0768356323242188, "global_step": 486072, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.054792881011963, "global_step": 486073, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0610735416412354, "global_step": 486074, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0502076148986816, "global_step": 486075, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.083801507949829, "global_step": 486076, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0624396800994873, "global_step": 486077, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0416224002838135, "global_step": 486078, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0355849266052246, "global_step": 486079, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.010481119155884, "global_step": 486080, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9539293050765991, "global_step": 486081, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0778145790100098, "global_step": 486082, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.010733127593994, "global_step": 486083, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0911457538604736, "global_step": 486084, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1382789611816406, "global_step": 486085, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0357320308685303, "global_step": 486086, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.068770408630371, "global_step": 486087, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.050410747528076, "global_step": 486088, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0653340816497803, "global_step": 486089, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0633349418640137, "global_step": 486090, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.044780969619751, "global_step": 486091, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0248775482177734, "global_step": 486092, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0445547103881836, "global_step": 486093, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.028219223022461, "global_step": 486094, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9854493141174316, "global_step": 486095, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.008528709411621, "global_step": 486096, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1425607204437256, "global_step": 486097, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.083616018295288, "global_step": 486098, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1287121772766113, "global_step": 486099, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0201711654663086, "global_step": 486100, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.059701919555664, "global_step": 486101, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0173420906066895, "global_step": 486102, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.077362060546875, "global_step": 486103, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0148253440856934, "global_step": 486104, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0300140380859375, "global_step": 486105, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.074314832687378, "global_step": 486106, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.074061155319214, "global_step": 486107, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1183900833129883, "global_step": 486108, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1298859119415283, "global_step": 486109, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1121180057525635, "global_step": 486110, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.086909532546997, "global_step": 486111, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.091674327850342, "global_step": 486112, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0560200214385986, "global_step": 486113, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0819380283355713, "global_step": 486114, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.050888776779175, "global_step": 486115, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.090179443359375, "global_step": 486116, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.049252510070801, "global_step": 486117, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.185819625854492, "global_step": 486118, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9964075088500977, "global_step": 486119, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.03792405128479, "global_step": 486120, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0057554244995117, "global_step": 486121, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0656239986419678, "global_step": 486122, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.171544313430786, "global_step": 486123, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0320799350738525, "global_step": 486124, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9767404794692993, "global_step": 486125, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.047443151473999, "global_step": 486126, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.096804618835449, "global_step": 486127, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0219287872314453, "global_step": 486128, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.092325210571289, "global_step": 486129, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0521416664123535, "global_step": 486130, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0816824436187744, "global_step": 486131, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.003504991531372, "global_step": 486132, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0727622509002686, "global_step": 486133, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.033993721008301, "global_step": 486134, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.038600444793701, "global_step": 486135, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9770667552947998, "global_step": 486136, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0761144161224365, "global_step": 486137, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.053297281265259, "global_step": 486138, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.066279888153076, "global_step": 486139, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0744714736938477, "global_step": 486140, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0444700717926025, "global_step": 486141, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.141942024230957, "global_step": 486142, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.048306703567505, "global_step": 486143, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9912775754928589, "global_step": 486144, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0784995555877686, "global_step": 486145, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.124340057373047, "global_step": 486146, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.989168643951416, "global_step": 486147, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0595431327819824, "global_step": 486148, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9481172561645508, "global_step": 486149, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.057624101638794, "global_step": 486150, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9727592468261719, "global_step": 486151, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9987635612487793, "global_step": 486152, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0340993404388428, "global_step": 486153, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0638866424560547, "global_step": 486154, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.065657615661621, "global_step": 486155, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9955241680145264, "global_step": 486156, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1779651641845703, "global_step": 486157, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.05157470703125, "global_step": 486158, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9726009368896484, "global_step": 486159, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.052063465118408, "global_step": 486160, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.014514446258545, "global_step": 486161, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.124246597290039, "global_step": 486162, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0394928455352783, "global_step": 486163, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1274430751800537, "global_step": 486164, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.101106882095337, "global_step": 486165, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.090927839279175, "global_step": 486166, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.071443557739258, "global_step": 486167, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.11553955078125, "global_step": 486168, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.053001880645752, "global_step": 486169, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.125810146331787, "global_step": 486170, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0540874004364014, "global_step": 486171, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.111668348312378, "global_step": 486172, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0879569053649902, "global_step": 486173, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.063819408416748, "global_step": 486174, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1139490604400635, "global_step": 486175, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.00954270362854, "global_step": 486176, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0929582118988037, "global_step": 486177, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.966078281402588, "global_step": 486178, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.035240411758423, "global_step": 486179, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.11869478225708, "global_step": 486180, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.031765937805176, "global_step": 486181, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.041365385055542, "global_step": 486182, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9996614456176758, "global_step": 486183, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.072338104248047, "global_step": 486184, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0843937397003174, "global_step": 486185, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.036098003387451, "global_step": 486186, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1171326637268066, "global_step": 486187, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.019360065460205, "global_step": 486188, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0602705478668213, "global_step": 486189, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.048140048980713, "global_step": 486190, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9930208921432495, "global_step": 486191, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0310866832733154, "global_step": 486192, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9477838277816772, "global_step": 486193, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0236663818359375, "global_step": 486194, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9984478950500488, "global_step": 486195, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0708167552948, "global_step": 486196, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.086925983428955, "global_step": 486197, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.126610279083252, "global_step": 486198, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0332722663879395, "global_step": 486199, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.114964723587036, "global_step": 486200, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1026089191436768, "global_step": 486201, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.134350061416626, "global_step": 486202, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.119678258895874, "global_step": 486203, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0566647052764893, "global_step": 486204, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9635246992111206, "global_step": 486205, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0257015228271484, "global_step": 486206, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9686650037765503, "global_step": 486207, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0758700370788574, "global_step": 486208, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1441261768341064, "global_step": 486209, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.057574987411499, "global_step": 486210, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0911641120910645, "global_step": 486211, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.008049964904785, "global_step": 486212, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.033956527709961, "global_step": 486213, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0744733810424805, "global_step": 486214, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.164214611053467, "global_step": 486215, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1136293411254883, "global_step": 486216, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.132674217224121, "global_step": 486217, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1035170555114746, "global_step": 486218, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.049495220184326, "global_step": 486219, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1018319129943848, "global_step": 486220, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0621166229248047, "global_step": 486221, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1256580352783203, "global_step": 486222, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0770046710968018, "global_step": 486223, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.102830171585083, "global_step": 486224, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.116776466369629, "global_step": 486225, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.022916555404663, "global_step": 486226, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9201430082321167, "global_step": 486227, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.057101249694824, "global_step": 486228, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.035905122756958, "global_step": 486229, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0249783992767334, "global_step": 486230, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.082763671875, "global_step": 486231, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.142989158630371, "global_step": 486232, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.09953236579895, "global_step": 486233, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0092194080352783, "global_step": 486234, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.158137083053589, "global_step": 486235, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1272952556610107, "global_step": 486236, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0248982906341553, "global_step": 486237, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0598175525665283, "global_step": 486238, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.061816692352295, "global_step": 486239, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9884326457977295, "global_step": 486240, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.067732572555542, "global_step": 486241, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.064007043838501, "global_step": 486242, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.024216413497925, "global_step": 486243, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9673622846603394, "global_step": 486244, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.096184492111206, "global_step": 486245, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.186267614364624, "global_step": 486246, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0315804481506348, "global_step": 486247, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.082184314727783, "global_step": 486248, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0626304149627686, "global_step": 486249, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.08406138420105, "global_step": 486250, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1273984909057617, "global_step": 486251, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1957662105560303, "global_step": 486252, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0927467346191406, "global_step": 486253, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0568630695343018, "global_step": 486254, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.095113754272461, "global_step": 486255, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9413518905639648, "global_step": 486256, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.09104061126709, "global_step": 486257, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.072505235671997, "global_step": 486258, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0515811443328857, "global_step": 486259, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.06681227684021, "global_step": 486260, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0618526935577393, "global_step": 486261, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9994478225708008, "global_step": 486262, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0758140087127686, "global_step": 486263, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1144206523895264, "global_step": 486264, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0595006942749023, "global_step": 486265, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0129454135894775, "global_step": 486266, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1010732650756836, "global_step": 486267, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0742838382720947, "global_step": 486268, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.033292293548584, "global_step": 486269, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.079092264175415, "global_step": 486270, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0495543479919434, "global_step": 486271, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1615068912506104, "global_step": 486272, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1179471015930176, "global_step": 486273, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1578094959259033, "global_step": 486274, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1465234756469727, "global_step": 486275, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9751319885253906, "global_step": 486276, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9950929880142212, "global_step": 486277, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9389994144439697, "global_step": 486278, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0720932483673096, "global_step": 486279, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.096287965774536, "global_step": 486280, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.085742712020874, "global_step": 486281, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.053229331970215, "global_step": 486282, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0815770626068115, "global_step": 486283, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0530130863189697, "global_step": 486284, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.089751958847046, "global_step": 486285, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0336313247680664, "global_step": 486286, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0511574745178223, "global_step": 486287, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1132874488830566, "global_step": 486288, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.067089796066284, "global_step": 486289, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.048004627227783, "global_step": 486290, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1035215854644775, "global_step": 486291, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.045762777328491, "global_step": 486292, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.985664963722229, "global_step": 486293, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0506134033203125, "global_step": 486294, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1305480003356934, "global_step": 486295, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0891196727752686, "global_step": 486296, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1090245246887207, "global_step": 486297, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.145176649093628, "global_step": 486298, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0460407733917236, "global_step": 486299, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.031643867492676, "global_step": 486300, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.048156976699829, "global_step": 486301, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.133934259414673, "global_step": 486302, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0492653846740723, "global_step": 486303, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0457539558410645, "global_step": 486304, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0280539989471436, "global_step": 486305, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.10270094871521, "global_step": 486306, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1098592281341553, "global_step": 486307, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.072970390319824, "global_step": 486308, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0056374073028564, "global_step": 486309, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0474586486816406, "global_step": 486310, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9900362491607666, "global_step": 486311, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0300257205963135, "global_step": 486312, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.076214075088501, "global_step": 486313, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0981571674346924, "global_step": 486314, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.070244073867798, "global_step": 486315, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0145535469055176, "global_step": 486316, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.013803482055664, "global_step": 486317, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.073943853378296, "global_step": 486318, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.090217113494873, "global_step": 486319, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9855945110321045, "global_step": 486320, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0118408203125, "global_step": 486321, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.099640369415283, "global_step": 486322, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0747666358947754, "global_step": 486323, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1219818592071533, "global_step": 486324, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.121772289276123, "global_step": 486325, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.008847951889038, "global_step": 486326, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0702247619628906, "global_step": 486327, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1239993572235107, "global_step": 486328, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0291242599487305, "global_step": 486329, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.046506643295288, "global_step": 486330, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0701143741607666, "global_step": 486331, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0205585956573486, "global_step": 486332, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.092604637145996, "global_step": 486333, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1267309188842773, "global_step": 486334, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.017077684402466, "global_step": 486335, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0198559761047363, "global_step": 486336, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.047656536102295, "global_step": 486337, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0836360454559326, "global_step": 486338, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.092648506164551, "global_step": 486339, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.047531843185425, "global_step": 486340, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0429561138153076, "global_step": 486341, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0218124389648438, "global_step": 486342, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.052222967147827, "global_step": 486343, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.045316696166992, "global_step": 486344, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1152279376983643, "global_step": 486345, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9648754596710205, "global_step": 486346, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.141733407974243, "global_step": 486347, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0413053035736084, "global_step": 486348, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9553382396697998, "global_step": 486349, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0395004749298096, "global_step": 486350, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.028721570968628, "global_step": 486351, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0779619216918945, "global_step": 486352, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9762771129608154, "global_step": 486353, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0569095611572266, "global_step": 486354, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1227662563323975, "global_step": 486355, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0633649826049805, "global_step": 486356, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9922341108322144, "global_step": 486357, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.04223895072937, "global_step": 486358, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0228655338287354, "global_step": 486359, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0363311767578125, "global_step": 486360, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.011019468307495, "global_step": 486361, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1514647006988525, "global_step": 486362, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.142152786254883, "global_step": 486363, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.17212176322937, "global_step": 486364, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0206682682037354, "global_step": 486365, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0756096839904785, "global_step": 486366, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0786967277526855, "global_step": 486367, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.093904972076416, "global_step": 486368, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.059607744216919, "global_step": 486369, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0037941932678223, "global_step": 486370, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.075944662094116, "global_step": 486371, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0670242309570312, "global_step": 486372, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9995875358581543, "global_step": 486373, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.093402862548828, "global_step": 486374, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0510902404785156, "global_step": 486375, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0900626182556152, "global_step": 486376, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0188000202178955, "global_step": 486377, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9618501663208008, "global_step": 486378, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0999488830566406, "global_step": 486379, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.053067207336426, "global_step": 486380, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1363842487335205, "global_step": 486381, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1049232482910156, "global_step": 486382, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.121102809906006, "global_step": 486383, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0825939178466797, "global_step": 486384, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0502753257751465, "global_step": 486385, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0426864624023438, "global_step": 486386, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0002315044403076, "global_step": 486387, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.014253854751587, "global_step": 486388, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.108605146408081, "global_step": 486389, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.163130521774292, "global_step": 486390, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9998774528503418, "global_step": 486391, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1161999702453613, "global_step": 486392, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0418615341186523, "global_step": 486393, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.059276819229126, "global_step": 486394, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1259942054748535, "global_step": 486395, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9906463623046875, "global_step": 486396, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9539523124694824, "global_step": 486397, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.049621105194092, "global_step": 486398, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0775299072265625, "global_step": 486399, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9782723188400269, "global_step": 486400, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.105952262878418, "global_step": 486401, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0134363174438477, "global_step": 486402, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0206470489501953, "global_step": 486403, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0193846225738525, "global_step": 486404, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0595550537109375, "global_step": 486405, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0286643505096436, "global_step": 486406, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0980966091156006, "global_step": 486407, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0172739028930664, "global_step": 486408, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0863661766052246, "global_step": 486409, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0478618144989014, "global_step": 486410, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.091193914413452, "global_step": 486411, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1327931880950928, "global_step": 486412, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0588150024414062, "global_step": 486413, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1177573204040527, "global_step": 486414, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.030311107635498, "global_step": 486415, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1460719108581543, "global_step": 486416, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1177725791931152, "global_step": 486417, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.226283073425293, "global_step": 486418, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.051591396331787, "global_step": 486419, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9500999450683594, "global_step": 486420, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0721654891967773, "global_step": 486421, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0668153762817383, "global_step": 486422, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.029202461242676, "global_step": 486423, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0716445446014404, "global_step": 486424, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.095538377761841, "global_step": 486425, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.09246826171875, "global_step": 486426, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1034109592437744, "global_step": 486427, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0947906970977783, "global_step": 486428, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.084301233291626, "global_step": 486429, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.100884437561035, "global_step": 486430, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.129307270050049, "global_step": 486431, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9639239311218262, "global_step": 486432, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0652248859405518, "global_step": 486433, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0753726959228516, "global_step": 486434, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.019746780395508, "global_step": 486435, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1338703632354736, "global_step": 486436, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1614575386047363, "global_step": 486437, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.054680824279785, "global_step": 486438, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.016101598739624, "global_step": 486439, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.111111640930176, "global_step": 486440, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0863378047943115, "global_step": 486441, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.090117931365967, "global_step": 486442, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.058274984359741, "global_step": 486443, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.117379903793335, "global_step": 486444, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1179072856903076, "global_step": 486445, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0869228839874268, "global_step": 486446, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1063334941864014, "global_step": 486447, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0342800617218018, "global_step": 486448, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0868101119995117, "global_step": 486449, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.989060640335083, "global_step": 486450, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.068477153778076, "global_step": 486451, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0656192302703857, "global_step": 486452, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1048755645751953, "global_step": 486453, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.069821357727051, "global_step": 486454, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.117335319519043, "global_step": 486455, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0500760078430176, "global_step": 486456, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.062246799468994, "global_step": 486457, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0518693923950195, "global_step": 486458, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.054150104522705, "global_step": 486459, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9575319290161133, "global_step": 486460, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0214481353759766, "global_step": 486461, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0531439781188965, "global_step": 486462, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1316630840301514, "global_step": 486463, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1173737049102783, "global_step": 486464, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.057187080383301, "global_step": 486465, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.012500524520874, "global_step": 486466, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.073791265487671, "global_step": 486467, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.054596185684204, "global_step": 486468, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.112154722213745, "global_step": 486469, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1643025875091553, "global_step": 486470, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.086341381072998, "global_step": 486471, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.097825288772583, "global_step": 486472, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0223066806793213, "global_step": 486473, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0879147052764893, "global_step": 486474, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0190563201904297, "global_step": 486475, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.056131362915039, "global_step": 486476, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0386950969696045, "global_step": 486477, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.997755765914917, "global_step": 486478, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.060702085494995, "global_step": 486479, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.979771614074707, "global_step": 486480, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.111708879470825, "global_step": 486481, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.041771411895752, "global_step": 486482, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0280890464782715, "global_step": 486483, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0834789276123047, "global_step": 486484, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0409250259399414, "global_step": 486485, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.069871187210083, "global_step": 486486, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.059558391571045, "global_step": 486487, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0863277912139893, "global_step": 486488, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1125447750091553, "global_step": 486489, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.067354440689087, "global_step": 486490, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.055668354034424, "global_step": 486491, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.012552499771118, "global_step": 486492, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.035135269165039, "global_step": 486493, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0715255737304688, "global_step": 486494, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9742242097854614, "global_step": 486495, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.039789915084839, "global_step": 486496, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9552239179611206, "global_step": 486497, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.111467123031616, "global_step": 486498, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.063267469406128, "global_step": 486499, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.09094500541687, "global_step": 486500, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.018561840057373, "global_step": 486501, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.089838981628418, "global_step": 486502, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0511655807495117, "global_step": 486503, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.145111560821533, "global_step": 486504, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.116734266281128, "global_step": 486505, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0592939853668213, "global_step": 486506, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.084484815597534, "global_step": 486507, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.007476806640625, "global_step": 486508, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9358041286468506, "global_step": 486509, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1097710132598877, "global_step": 486510, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.935871958732605, "global_step": 486511, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.114485740661621, "global_step": 486512, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1086740493774414, "global_step": 486513, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0372204780578613, "global_step": 486514, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.055837631225586, "global_step": 486515, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.008188486099243, "global_step": 486516, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1051180362701416, "global_step": 486517, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.090236186981201, "global_step": 486518, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.106619119644165, "global_step": 486519, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.094094753265381, "global_step": 486520, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.052971601486206, "global_step": 486521, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0434329509735107, "global_step": 486522, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0132083892822266, "global_step": 486523, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0442705154418945, "global_step": 486524, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1234614849090576, "global_step": 486525, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9245896339416504, "global_step": 486526, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.047154188156128, "global_step": 486527, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.086869478225708, "global_step": 486528, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1381330490112305, "global_step": 486529, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0823025703430176, "global_step": 486530, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0147011280059814, "global_step": 486531, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0293128490448, "global_step": 486532, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0008418560028076, "global_step": 486533, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.006999969482422, "global_step": 486534, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.099804639816284, "global_step": 486535, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0971319675445557, "global_step": 486536, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0205819606781006, "global_step": 486537, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0295393466949463, "global_step": 486538, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0367038249969482, "global_step": 486539, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.095980644226074, "global_step": 486540, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.132068157196045, "global_step": 486541, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.079580545425415, "global_step": 486542, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.2021589279174805, "global_step": 486543, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0429458618164062, "global_step": 486544, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0771679878234863, "global_step": 486545, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1191275119781494, "global_step": 486546, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.081277847290039, "global_step": 486547, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.038541078567505, "global_step": 486548, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1377625465393066, "global_step": 486549, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0959808826446533, "global_step": 486550, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.047954797744751, "global_step": 486551, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0033657550811768, "global_step": 486552, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.989010214805603, "global_step": 486553, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9569536447525024, "global_step": 486554, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.047726631164551, "global_step": 486555, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1047592163085938, "global_step": 486556, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.083986759185791, "global_step": 486557, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.109522581100464, "global_step": 486558, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0726089477539062, "global_step": 486559, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.075125217437744, "global_step": 486560, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0741591453552246, "global_step": 486561, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0259876251220703, "global_step": 486562, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9655652046203613, "global_step": 486563, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0742878913879395, "global_step": 486564, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.010967254638672, "global_step": 486565, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.1990723609924316, "global_step": 486566, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.018298864364624, "global_step": 486567, "epoch": 851, "lr": 5e-05}
{"train_loss": 1.9529517889022827, "global_step": 486568, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.117145299911499, "global_step": 486569, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0595383644104004, "global_step": 486570, "epoch": 851, "lr": 5e-05}
{"train_loss": 2.0733988285064697, "global_step": 486571, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.123953342437744, "global_step": 486572, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0009021759033203, "global_step": 486573, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0271341800689697, "global_step": 486574, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0754454135894775, "global_step": 486575, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0220067501068115, "global_step": 486576, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9659992456436157, "global_step": 486577, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.039485216140747, "global_step": 486578, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1070992946624756, "global_step": 486579, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0681774616241455, "global_step": 486580, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.086134910583496, "global_step": 486581, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9770936965942383, "global_step": 486582, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0679984092712402, "global_step": 486583, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.019010543823242, "global_step": 486584, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.052577018737793, "global_step": 486585, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1083035469055176, "global_step": 486586, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0829927921295166, "global_step": 486587, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1186676025390625, "global_step": 486588, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0362186431884766, "global_step": 486589, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.112297773361206, "global_step": 486590, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0561556816101074, "global_step": 486591, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.079354763031006, "global_step": 486592, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0806872844696045, "global_step": 486593, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0916364192962646, "global_step": 486594, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.005695104598999, "global_step": 486595, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9784877300262451, "global_step": 486596, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.133164882659912, "global_step": 486597, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.011747360229492, "global_step": 486598, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0562798976898193, "global_step": 486599, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9708199501037598, "global_step": 486600, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.017096757888794, "global_step": 486601, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0173280239105225, "global_step": 486602, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0026755332946777, "global_step": 486603, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9548619985580444, "global_step": 486604, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0765180587768555, "global_step": 486605, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0747060775756836, "global_step": 486606, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.067631959915161, "global_step": 486607, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.036402702331543, "global_step": 486608, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.13616681098938, "global_step": 486609, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.016221761703491, "global_step": 486610, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.048367500305176, "global_step": 486611, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0931451320648193, "global_step": 486612, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.034273147583008, "global_step": 486613, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1038501262664795, "global_step": 486614, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.124802827835083, "global_step": 486615, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9808058738708496, "global_step": 486616, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0179226398468018, "global_step": 486617, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9582149982452393, "global_step": 486618, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9495880603790283, "global_step": 486619, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.058622121810913, "global_step": 486620, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.022218942642212, "global_step": 486621, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9774919748306274, "global_step": 486622, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9727753400802612, "global_step": 486623, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0136146545410156, "global_step": 486624, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0776686668395996, "global_step": 486625, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0058631896972656, "global_step": 486626, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1316137313842773, "global_step": 486627, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0623598098754883, "global_step": 486628, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0698366165161133, "global_step": 486629, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.060415744781494, "global_step": 486630, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.037295341491699, "global_step": 486631, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0412116050720215, "global_step": 486632, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0699424743652344, "global_step": 486633, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.065817356109619, "global_step": 486634, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0049962997436523, "global_step": 486635, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.06278920173645, "global_step": 486636, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0126516819000244, "global_step": 486637, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0220491886138916, "global_step": 486638, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1661221981048584, "global_step": 486639, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.109990119934082, "global_step": 486640, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0410304069519043, "global_step": 486641, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1034209728240967, "global_step": 486642, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.032167673110962, "global_step": 486643, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.051769495010376, "global_step": 486644, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0646657943725586, "global_step": 486645, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1610026359558105, "global_step": 486646, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.05733060836792, "global_step": 486647, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.00044584274292, "global_step": 486648, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.072880268096924, "global_step": 486649, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.080120801925659, "global_step": 486650, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.99815833568573, "global_step": 486651, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0186522006988525, "global_step": 486652, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0607333183288574, "global_step": 486653, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0786426067352295, "global_step": 486654, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0154268741607666, "global_step": 486655, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.073596477508545, "global_step": 486656, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0696277618408203, "global_step": 486657, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1264030933380127, "global_step": 486658, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.093754768371582, "global_step": 486659, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1162569522857666, "global_step": 486660, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0585227012634277, "global_step": 486661, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9880316257476807, "global_step": 486662, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0551798343658447, "global_step": 486663, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9502826929092407, "global_step": 486664, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.073800802230835, "global_step": 486665, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1240618228912354, "global_step": 486666, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9548102617263794, "global_step": 486667, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.092942714691162, "global_step": 486668, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.047437906265259, "global_step": 486669, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0299315452575684, "global_step": 486670, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.068629264831543, "global_step": 486671, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9961638450622559, "global_step": 486672, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.047523021697998, "global_step": 486673, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0094587802886963, "global_step": 486674, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9826794862747192, "global_step": 486675, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9704630374908447, "global_step": 486676, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.130188226699829, "global_step": 486677, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.029115676879883, "global_step": 486678, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9909379482269287, "global_step": 486679, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0501065254211426, "global_step": 486680, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0765581130981445, "global_step": 486681, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.003408193588257, "global_step": 486682, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.118234395980835, "global_step": 486683, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0667917728424072, "global_step": 486684, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1125364303588867, "global_step": 486685, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0764472484588623, "global_step": 486686, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.198057174682617, "global_step": 486687, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.100714683532715, "global_step": 486688, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0827524662017822, "global_step": 486689, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0481064319610596, "global_step": 486690, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9833756685256958, "global_step": 486691, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.075303554534912, "global_step": 486692, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0385754108428955, "global_step": 486693, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.109801769256592, "global_step": 486694, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9964152574539185, "global_step": 486695, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0184414386749268, "global_step": 486696, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.092742919921875, "global_step": 486697, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0376222133636475, "global_step": 486698, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0587799549102783, "global_step": 486699, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0288774967193604, "global_step": 486700, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.069892644882202, "global_step": 486701, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0990331172943115, "global_step": 486702, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1169817447662354, "global_step": 486703, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.114434003829956, "global_step": 486704, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0372681617736816, "global_step": 486705, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0683906078338623, "global_step": 486706, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.03696346282959, "global_step": 486707, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.973218560218811, "global_step": 486708, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0201234817504883, "global_step": 486709, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.071382522583008, "global_step": 486710, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0337042808532715, "global_step": 486711, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0420987606048584, "global_step": 486712, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0823521614074707, "global_step": 486713, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0541224479675293, "global_step": 486714, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0319888591766357, "global_step": 486715, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0386433601379395, "global_step": 486716, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.002753496170044, "global_step": 486717, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9325628280639648, "global_step": 486718, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0983893871307373, "global_step": 486719, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.072150468826294, "global_step": 486720, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9436951875686646, "global_step": 486721, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1015732288360596, "global_step": 486722, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.074309825897217, "global_step": 486723, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0573818683624268, "global_step": 486724, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.130154848098755, "global_step": 486725, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0842690467834473, "global_step": 486726, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0261647701263428, "global_step": 486727, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9968961477279663, "global_step": 486728, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9575841426849365, "global_step": 486729, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.024278163909912, "global_step": 486730, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0986759662628174, "global_step": 486731, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.167804002761841, "global_step": 486732, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.136744499206543, "global_step": 486733, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9905996322631836, "global_step": 486734, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0609216690063477, "global_step": 486735, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.08278751373291, "global_step": 486736, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.029047966003418, "global_step": 486737, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9462753534317017, "global_step": 486738, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.962533950805664, "global_step": 486739, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9645259380340576, "global_step": 486740, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.048844575881958, "global_step": 486741, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0027220249176025, "global_step": 486742, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.083094358444214, "global_step": 486743, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0708823204040527, "global_step": 486744, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.058121919631958, "global_step": 486745, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0813567638397217, "global_step": 486746, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.103090763092041, "global_step": 486747, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0381083488464355, "global_step": 486748, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.029568910598755, "global_step": 486749, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0315797328948975, "global_step": 486750, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.063692092895508, "global_step": 486751, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0323994159698486, "global_step": 486752, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.091059446334839, "global_step": 486753, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.130427837371826, "global_step": 486754, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9680097103118896, "global_step": 486755, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.021921396255493, "global_step": 486756, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.081246852874756, "global_step": 486757, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.097557544708252, "global_step": 486758, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0555050373077393, "global_step": 486759, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.108281135559082, "global_step": 486760, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.063436985015869, "global_step": 486761, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.135887384414673, "global_step": 486762, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.006605625152588, "global_step": 486763, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.958543300628662, "global_step": 486764, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0485007762908936, "global_step": 486765, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0032033920288086, "global_step": 486766, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0156540870666504, "global_step": 486767, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.114858388900757, "global_step": 486768, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1072475910186768, "global_step": 486769, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9644438028335571, "global_step": 486770, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.988740086555481, "global_step": 486771, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0489718914031982, "global_step": 486772, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9671730995178223, "global_step": 486773, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0999274253845215, "global_step": 486774, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1703293323516846, "global_step": 486775, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.039532423019409, "global_step": 486776, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.124558448791504, "global_step": 486777, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1270711421966553, "global_step": 486778, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.018266201019287, "global_step": 486779, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.108126401901245, "global_step": 486780, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.062471389770508, "global_step": 486781, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0114657878875732, "global_step": 486782, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1181774139404297, "global_step": 486783, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.097019910812378, "global_step": 486784, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0005791187286377, "global_step": 486785, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0692460536956787, "global_step": 486786, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.089071750640869, "global_step": 486787, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.037489891052246, "global_step": 486788, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1571128368377686, "global_step": 486789, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.095590591430664, "global_step": 486790, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0208609104156494, "global_step": 486791, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0245628356933594, "global_step": 486792, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.073971748352051, "global_step": 486793, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0433971881866455, "global_step": 486794, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0381035804748535, "global_step": 486795, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.01741099357605, "global_step": 486796, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1034581661224365, "global_step": 486797, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.059664249420166, "global_step": 486798, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.06225323677063, "global_step": 486799, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.094898223876953, "global_step": 486800, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.028079032897949, "global_step": 486801, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.132028579711914, "global_step": 486802, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0529141426086426, "global_step": 486803, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0271058082580566, "global_step": 486804, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9586862325668335, "global_step": 486805, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0279746055603027, "global_step": 486806, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.096259355545044, "global_step": 486807, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.073033094406128, "global_step": 486808, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.062045097351074, "global_step": 486809, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.022284746170044, "global_step": 486810, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.051894187927246, "global_step": 486811, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0681519508361816, "global_step": 486812, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0400264263153076, "global_step": 486813, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.021483898162842, "global_step": 486814, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1839540004730225, "global_step": 486815, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9770663976669312, "global_step": 486816, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9726186990737915, "global_step": 486817, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0271685123443604, "global_step": 486818, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9942612648010254, "global_step": 486819, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1127188205718994, "global_step": 486820, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.003887414932251, "global_step": 486821, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1082329750061035, "global_step": 486822, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0713140964508057, "global_step": 486823, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.959218144416809, "global_step": 486824, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0234899520874023, "global_step": 486825, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0931015014648438, "global_step": 486826, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.032230854034424, "global_step": 486827, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.053565263748169, "global_step": 486828, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9879149198532104, "global_step": 486829, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.159156560897827, "global_step": 486830, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0694079399108887, "global_step": 486831, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.073086977005005, "global_step": 486832, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0944786071777344, "global_step": 486833, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1294748783111572, "global_step": 486834, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.02336049079895, "global_step": 486835, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.999862790107727, "global_step": 486836, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.023601770401001, "global_step": 486837, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0772545337677, "global_step": 486838, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.977739930152893, "global_step": 486839, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.009572982788086, "global_step": 486840, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.150581121444702, "global_step": 486841, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9702764749526978, "global_step": 486842, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0239057540893555, "global_step": 486843, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.097665548324585, "global_step": 486844, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.076842784881592, "global_step": 486845, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9958841800689697, "global_step": 486846, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0905613899230957, "global_step": 486847, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0157291889190674, "global_step": 486848, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0215258598327637, "global_step": 486849, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.009808301925659, "global_step": 486850, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0615475177764893, "global_step": 486851, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.117236614227295, "global_step": 486852, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0134589672088623, "global_step": 486853, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0896408557891846, "global_step": 486854, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1067235469818115, "global_step": 486855, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.126047134399414, "global_step": 486856, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0403599739074707, "global_step": 486857, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0365426540374756, "global_step": 486858, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.062823534011841, "global_step": 486859, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.013375997543335, "global_step": 486860, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0041167736053467, "global_step": 486861, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0463876724243164, "global_step": 486862, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1003177165985107, "global_step": 486863, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0536069869995117, "global_step": 486864, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.090148448944092, "global_step": 486865, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0803446769714355, "global_step": 486866, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0245015621185303, "global_step": 486867, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0922656059265137, "global_step": 486868, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1137959957122803, "global_step": 486869, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9905298948287964, "global_step": 486870, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0858798027038574, "global_step": 486871, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0330049991607666, "global_step": 486872, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.135226249694824, "global_step": 486873, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0801937580108643, "global_step": 486874, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0683600902557373, "global_step": 486875, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0216867923736572, "global_step": 486876, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.107801675796509, "global_step": 486877, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0348963737487793, "global_step": 486878, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0232136249542236, "global_step": 486879, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0917623043060303, "global_step": 486880, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0543875694274902, "global_step": 486881, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.99504816532135, "global_step": 486882, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0265450477600098, "global_step": 486883, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0775773525238037, "global_step": 486884, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0285627841949463, "global_step": 486885, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.054034948348999, "global_step": 486886, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0786514282226562, "global_step": 486887, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.131580114364624, "global_step": 486888, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.079521894454956, "global_step": 486889, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.2050888538360596, "global_step": 486890, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1433253288269043, "global_step": 486891, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0635159015655518, "global_step": 486892, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.020540714263916, "global_step": 486893, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.10264253616333, "global_step": 486894, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.077380895614624, "global_step": 486895, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0783796310424805, "global_step": 486896, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0399930477142334, "global_step": 486897, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0746572017669678, "global_step": 486898, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.139220952987671, "global_step": 486899, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0117549896240234, "global_step": 486900, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9911125898361206, "global_step": 486901, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0153236389160156, "global_step": 486902, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.025541067123413, "global_step": 486903, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.105191946029663, "global_step": 486904, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.055727481842041, "global_step": 486905, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.094546318054199, "global_step": 486906, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0087273120880127, "global_step": 486907, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.085496187210083, "global_step": 486908, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.107550859451294, "global_step": 486909, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0618956089019775, "global_step": 486910, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.164314031600952, "global_step": 486911, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0247998237609863, "global_step": 486912, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9607470035552979, "global_step": 486913, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.107689142227173, "global_step": 486914, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.040126323699951, "global_step": 486915, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.124368190765381, "global_step": 486916, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.071572780609131, "global_step": 486917, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.066633462905884, "global_step": 486918, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0466651916503906, "global_step": 486919, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.011971950531006, "global_step": 486920, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.02940034866333, "global_step": 486921, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.000891923904419, "global_step": 486922, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.129964828491211, "global_step": 486923, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.091228723526001, "global_step": 486924, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0648529529571533, "global_step": 486925, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0327866077423096, "global_step": 486926, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0205109119415283, "global_step": 486927, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1215591430664062, "global_step": 486928, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.042783498764038, "global_step": 486929, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.111891508102417, "global_step": 486930, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9857474565505981, "global_step": 486931, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0773589611053467, "global_step": 486932, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0536863803863525, "global_step": 486933, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0474092960357666, "global_step": 486934, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1044514179229736, "global_step": 486935, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0419840812683105, "global_step": 486936, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0421576499938965, "global_step": 486937, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9925971031188965, "global_step": 486938, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0412769317626953, "global_step": 486939, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.030115842819214, "global_step": 486940, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0596320629119873, "global_step": 486941, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.97265625, "global_step": 486942, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1066782474517822, "global_step": 486943, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0615506172180176, "global_step": 486944, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.083514928817749, "global_step": 486945, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0617077350616455, "global_step": 486946, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0434353351593018, "global_step": 486947, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.159219980239868, "global_step": 486948, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1354434490203857, "global_step": 486949, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.018744707107544, "global_step": 486950, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0271685123443604, "global_step": 486951, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0419154167175293, "global_step": 486952, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.103583812713623, "global_step": 486953, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1024909019470215, "global_step": 486954, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0919010639190674, "global_step": 486955, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0788002014160156, "global_step": 486956, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0150339603424072, "global_step": 486957, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1191534996032715, "global_step": 486958, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0008535385131836, "global_step": 486959, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0283701419830322, "global_step": 486960, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.001452922821045, "global_step": 486961, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9914534091949463, "global_step": 486962, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.031843662261963, "global_step": 486963, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.092550754547119, "global_step": 486964, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.030012369155884, "global_step": 486965, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.095879554748535, "global_step": 486966, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.139493942260742, "global_step": 486967, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.138699769973755, "global_step": 486968, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9920580387115479, "global_step": 486969, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1047122478485107, "global_step": 486970, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.000387668609619, "global_step": 486971, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.046020746231079, "global_step": 486972, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.03238582611084, "global_step": 486973, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.083664894104004, "global_step": 486974, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9600547552108765, "global_step": 486975, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0666887760162354, "global_step": 486976, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0077857971191406, "global_step": 486977, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0013108253479004, "global_step": 486978, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.026379346847534, "global_step": 486979, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.028019905090332, "global_step": 486980, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.058037757873535, "global_step": 486981, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.028019666671753, "global_step": 486982, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.169377088546753, "global_step": 486983, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0435194969177246, "global_step": 486984, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.029705286026001, "global_step": 486985, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0201070308685303, "global_step": 486986, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0398173332214355, "global_step": 486987, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9742136001586914, "global_step": 486988, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.003239393234253, "global_step": 486989, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0879745483398438, "global_step": 486990, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.088783025741577, "global_step": 486991, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.013126850128174, "global_step": 486992, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.086763381958008, "global_step": 486993, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0667531490325928, "global_step": 486994, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0547285079956055, "global_step": 486995, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.130768299102783, "global_step": 486996, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1547303199768066, "global_step": 486997, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9677402973175049, "global_step": 486998, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9576640129089355, "global_step": 486999, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.039572238922119, "global_step": 487000, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0381815433502197, "global_step": 487001, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.079484462738037, "global_step": 487002, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0492401123046875, "global_step": 487003, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.107600450515747, "global_step": 487004, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9972269535064697, "global_step": 487005, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0631463527679443, "global_step": 487006, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0499587059020996, "global_step": 487007, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.070901870727539, "global_step": 487008, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.044442653656006, "global_step": 487009, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0672974586486816, "global_step": 487010, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.075671434402466, "global_step": 487011, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0368192195892334, "global_step": 487012, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0314114093780518, "global_step": 487013, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0773160457611084, "global_step": 487014, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.052527666091919, "global_step": 487015, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1144778728485107, "global_step": 487016, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1037659645080566, "global_step": 487017, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.050954580307007, "global_step": 487018, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.103815793991089, "global_step": 487019, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.02921986579895, "global_step": 487020, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1068131923675537, "global_step": 487021, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9780594110488892, "global_step": 487022, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.047325611114502, "global_step": 487023, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9986680746078491, "global_step": 487024, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0928709506988525, "global_step": 487025, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0262680053710938, "global_step": 487026, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0864319801330566, "global_step": 487027, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.037893295288086, "global_step": 487028, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9961788654327393, "global_step": 487029, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1049888134002686, "global_step": 487030, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0587711334228516, "global_step": 487031, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1303043365478516, "global_step": 487032, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0948143005371094, "global_step": 487033, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0507068634033203, "global_step": 487034, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.024782657623291, "global_step": 487035, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.155153274536133, "global_step": 487036, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.027200698852539, "global_step": 487037, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.066190004348755, "global_step": 487038, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.063605785369873, "global_step": 487039, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.079735279083252, "global_step": 487040, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1182782649993896, "global_step": 487041, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0909717082977295, "global_step": 487042, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0325944423675537, "global_step": 487043, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.012399911880493, "global_step": 487044, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0334012508392334, "global_step": 487045, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9941638708114624, "global_step": 487046, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9958772659301758, "global_step": 487047, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9901155233383179, "global_step": 487048, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9109959602355957, "global_step": 487049, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.034026861190796, "global_step": 487050, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0502705574035645, "global_step": 487051, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1035971641540527, "global_step": 487052, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.110531806945801, "global_step": 487053, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.040318489074707, "global_step": 487054, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.003589630126953, "global_step": 487055, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1234519481658936, "global_step": 487056, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.025430679321289, "global_step": 487057, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0457305908203125, "global_step": 487058, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0575497150421143, "global_step": 487059, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0597591400146484, "global_step": 487060, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1277244091033936, "global_step": 487061, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.123871088027954, "global_step": 487062, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.018092155456543, "global_step": 487063, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0256378650665283, "global_step": 487064, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.126095771789551, "global_step": 487065, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9687272310256958, "global_step": 487066, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0010807514190674, "global_step": 487067, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0987319946289062, "global_step": 487068, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.036452054977417, "global_step": 487069, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0975987911224365, "global_step": 487070, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.133455753326416, "global_step": 487071, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.145625114440918, "global_step": 487072, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.060535430908203, "global_step": 487073, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0179221630096436, "global_step": 487074, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.06957745552063, "global_step": 487075, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0437490940093994, "global_step": 487076, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.152528762817383, "global_step": 487077, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1239027976989746, "global_step": 487078, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.064563274383545, "global_step": 487079, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0923080444335938, "global_step": 487080, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.976806402206421, "global_step": 487081, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0182137489318848, "global_step": 487082, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.098903179168701, "global_step": 487083, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0293288230895996, "global_step": 487084, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0751616954803467, "global_step": 487085, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.019522190093994, "global_step": 487086, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0545806884765625, "global_step": 487087, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.038849115371704, "global_step": 487088, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9410136938095093, "global_step": 487089, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9868779182434082, "global_step": 487090, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.006068706512451, "global_step": 487091, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.109710693359375, "global_step": 487092, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1336958408355713, "global_step": 487093, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9943488836288452, "global_step": 487094, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.062060594558716, "global_step": 487095, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0815136432647705, "global_step": 487096, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.098400115966797, "global_step": 487097, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1463468074798584, "global_step": 487098, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1222140789031982, "global_step": 487099, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.130000114440918, "global_step": 487100, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.050575017929077, "global_step": 487101, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.042830467224121, "global_step": 487102, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.027200698852539, "global_step": 487103, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0306923389434814, "global_step": 487104, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.05900239944458, "global_step": 487105, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.099177837371826, "global_step": 487106, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9494473934173584, "global_step": 487107, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0090553760528564, "global_step": 487108, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0782976150512695, "global_step": 487109, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0193309783935547, "global_step": 487110, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.045419692993164, "global_step": 487111, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0821290016174316, "global_step": 487112, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9902210235595703, "global_step": 487113, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.950238823890686, "global_step": 487114, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0318219661712646, "global_step": 487115, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1015684604644775, "global_step": 487116, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1571500301361084, "global_step": 487117, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0688791275024414, "global_step": 487118, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.014455795288086, "global_step": 487119, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0844619274139404, "global_step": 487120, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0662434101104736, "global_step": 487121, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0307929515838623, "global_step": 487122, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0969271659851074, "global_step": 487123, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.062509059906006, "global_step": 487124, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0237619876861572, "global_step": 487125, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.065594434738159, "global_step": 487126, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.08811092376709, "global_step": 487127, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.994520664215088, "global_step": 487128, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0461909770965576, "global_step": 487129, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.095733165740967, "global_step": 487130, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1099531650543213, "global_step": 487131, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0343947410583496, "global_step": 487132, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0430691242218018, "global_step": 487133, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.053853750228882, "global_step": 487134, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1140780448913574, "global_step": 487135, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.076559543609619, "global_step": 487136, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0012094974517822, "global_step": 487137, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.110625982284546, "global_step": 487138, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.994185209274292, "global_step": 487139, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.079979658126831, "global_step": 487140, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.047137975692749, "global_step": 487141, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1045327186584473, "global_step": 487142, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.040776491165161, "global_step": 487143, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0371716022491455, "global_step": 487144, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.022059440612793, "global_step": 487145, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0481619834899902, "global_step": 487146, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9976669549942017, "global_step": 487147, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0967581272125244, "global_step": 487148, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.111203670501709, "global_step": 487149, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0241494178771973, "global_step": 487150, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0143582820892334, "global_step": 487151, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0593838691711426, "global_step": 487152, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0226857662200928, "global_step": 487153, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.029017925262451, "global_step": 487154, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1457712650299072, "global_step": 487155, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0933918952941895, "global_step": 487156, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.066459894180298, "global_step": 487157, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0518994331359863, "global_step": 487158, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.089426040649414, "global_step": 487159, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.088439464569092, "global_step": 487160, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.122040271759033, "global_step": 487161, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9543826580047607, "global_step": 487162, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.065061092376709, "global_step": 487163, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.029883861541748, "global_step": 487164, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.047673225402832, "global_step": 487165, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9936145544052124, "global_step": 487166, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.062464952468872, "global_step": 487167, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0391793251037598, "global_step": 487168, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.067739725112915, "global_step": 487169, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0688445568084717, "global_step": 487170, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0203208923339844, "global_step": 487171, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.019448757171631, "global_step": 487172, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.103243827819824, "global_step": 487173, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.025846004486084, "global_step": 487174, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.083205223083496, "global_step": 487175, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.040590286254883, "global_step": 487176, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9911718368530273, "global_step": 487177, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0503268241882324, "global_step": 487178, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.140737771987915, "global_step": 487179, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0368497371673584, "global_step": 487180, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0110414028167725, "global_step": 487181, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.076650857925415, "global_step": 487182, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.030470132827759, "global_step": 487183, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0076935291290283, "global_step": 487184, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0357680320739746, "global_step": 487185, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0444507598876953, "global_step": 487186, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.053887367248535, "global_step": 487187, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1164257526397705, "global_step": 487188, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.021880865097046, "global_step": 487189, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0881330966949463, "global_step": 487190, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1255249977111816, "global_step": 487191, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.988739252090454, "global_step": 487192, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0682883262634277, "global_step": 487193, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.086799144744873, "global_step": 487194, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1142027378082275, "global_step": 487195, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.089900016784668, "global_step": 487196, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0637636184692383, "global_step": 487197, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0736873149871826, "global_step": 487198, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.043745994567871, "global_step": 487199, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.05423903465271, "global_step": 487200, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0291898250579834, "global_step": 487201, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0648951530456543, "global_step": 487202, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0324594974517822, "global_step": 487203, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0521576404571533, "global_step": 487204, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0870449542999268, "global_step": 487205, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.00581955909729, "global_step": 487206, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.080796003341675, "global_step": 487207, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0657687187194824, "global_step": 487208, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.101653814315796, "global_step": 487209, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0160789489746094, "global_step": 487210, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.080759048461914, "global_step": 487211, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.035813331604004, "global_step": 487212, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0667927265167236, "global_step": 487213, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0758988857269287, "global_step": 487214, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.022040605545044, "global_step": 487215, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0583810806274414, "global_step": 487216, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0929105281829834, "global_step": 487217, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0412092208862305, "global_step": 487218, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9998942613601685, "global_step": 487219, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.055152416229248, "global_step": 487220, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.053539514541626, "global_step": 487221, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.967512607574463, "global_step": 487222, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1121389865875244, "global_step": 487223, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1357200145721436, "global_step": 487224, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0694739818573, "global_step": 487225, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9884116649627686, "global_step": 487226, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.128406047821045, "global_step": 487227, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.106593608856201, "global_step": 487228, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0354533195495605, "global_step": 487229, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9929157495498657, "global_step": 487230, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.032254219055176, "global_step": 487231, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1479036808013916, "global_step": 487232, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.140815019607544, "global_step": 487233, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.048687219619751, "global_step": 487234, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0619914531707764, "global_step": 487235, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0917556285858154, "global_step": 487236, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0419983863830566, "global_step": 487237, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.013824701309204, "global_step": 487238, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0516464710235596, "global_step": 487239, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.074585437774658, "global_step": 487240, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0696516036987305, "global_step": 487241, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0500986576080322, "global_step": 487242, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0653390884399414, "global_step": 487243, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1195809841156006, "global_step": 487244, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0884594917297363, "global_step": 487245, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0920846462249756, "global_step": 487246, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0047221183776855, "global_step": 487247, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.026048421859741, "global_step": 487248, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.070213556289673, "global_step": 487249, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.04372239112854, "global_step": 487250, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.073194980621338, "global_step": 487251, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0882649421691895, "global_step": 487252, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0353848934173584, "global_step": 487253, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.2000956535339355, "global_step": 487254, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.049476146697998, "global_step": 487255, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0771501064300537, "global_step": 487256, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.026479959487915, "global_step": 487257, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.097229242324829, "global_step": 487258, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.073054075241089, "global_step": 487259, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0515763759613037, "global_step": 487260, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0977840423583984, "global_step": 487261, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.086758613586426, "global_step": 487262, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.075270414352417, "global_step": 487263, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.039785623550415, "global_step": 487264, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0601561069488525, "global_step": 487265, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0406877994537354, "global_step": 487266, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0612611770629883, "global_step": 487267, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.024167060852051, "global_step": 487268, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9413326978683472, "global_step": 487269, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0891354084014893, "global_step": 487270, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.063594341278076, "global_step": 487271, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.016305446624756, "global_step": 487272, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0567572116851807, "global_step": 487273, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.057117462158203, "global_step": 487274, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.127028703689575, "global_step": 487275, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0033838748931885, "global_step": 487276, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0162155628204346, "global_step": 487277, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.04573655128479, "global_step": 487278, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.081390857696533, "global_step": 487279, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.050758123397827, "global_step": 487280, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.055156946182251, "global_step": 487281, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9799059629440308, "global_step": 487282, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.033159017562866, "global_step": 487283, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0826618671417236, "global_step": 487284, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0632948875427246, "global_step": 487285, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.077540397644043, "global_step": 487286, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1378512382507324, "global_step": 487287, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1281979084014893, "global_step": 487288, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.037038803100586, "global_step": 487289, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.122037649154663, "global_step": 487290, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1182546615600586, "global_step": 487291, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.089426279067993, "global_step": 487292, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.051429033279419, "global_step": 487293, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0743510723114014, "global_step": 487294, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0623092651367188, "global_step": 487295, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0335962772369385, "global_step": 487296, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0569498538970947, "global_step": 487297, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1088335514068604, "global_step": 487298, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0875091552734375, "global_step": 487299, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0413429737091064, "global_step": 487300, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.042731285095215, "global_step": 487301, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.005305051803589, "global_step": 487302, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.069629430770874, "global_step": 487303, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.136901617050171, "global_step": 487304, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0895168781280518, "global_step": 487305, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.026270866394043, "global_step": 487306, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0411133766174316, "global_step": 487307, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0024333000183105, "global_step": 487308, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.033501148223877, "global_step": 487309, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0798935890197754, "global_step": 487310, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1564149856567383, "global_step": 487311, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1395180225372314, "global_step": 487312, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0826780796051025, "global_step": 487313, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.015953779220581, "global_step": 487314, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0299665927886963, "global_step": 487315, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0376224517822266, "global_step": 487316, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0683786869049072, "global_step": 487317, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0901176929473877, "global_step": 487318, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0940468311309814, "global_step": 487319, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.081162452697754, "global_step": 487320, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0174360275268555, "global_step": 487321, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0529186725616455, "global_step": 487322, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.99545419216156, "global_step": 487323, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9897534847259521, "global_step": 487324, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1320033073425293, "global_step": 487325, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0833258628845215, "global_step": 487326, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.070528268814087, "global_step": 487327, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.097503662109375, "global_step": 487328, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.128746747970581, "global_step": 487329, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.029475688934326, "global_step": 487330, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.082090139389038, "global_step": 487331, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0672824382781982, "global_step": 487332, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9624884128570557, "global_step": 487333, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0763399600982666, "global_step": 487334, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.066253423690796, "global_step": 487335, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.101651668548584, "global_step": 487336, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.052793264389038, "global_step": 487337, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0334243774414062, "global_step": 487338, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1020467281341553, "global_step": 487339, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0839216709136963, "global_step": 487340, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.12488055229187, "global_step": 487341, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0382232666015625, "global_step": 487342, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.034276247024536, "global_step": 487343, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.072685956954956, "global_step": 487344, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1093146800994873, "global_step": 487345, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.034111976623535, "global_step": 487346, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.129432201385498, "global_step": 487347, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0913727283477783, "global_step": 487348, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.034210443496704, "global_step": 487349, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.067065954208374, "global_step": 487350, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0945098400115967, "global_step": 487351, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.115769386291504, "global_step": 487352, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.013725996017456, "global_step": 487353, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0274407863616943, "global_step": 487354, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.152336835861206, "global_step": 487355, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0652475357055664, "global_step": 487356, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0343711376190186, "global_step": 487357, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.019174098968506, "global_step": 487358, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0298266410827637, "global_step": 487359, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9499574899673462, "global_step": 487360, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0630054473876953, "global_step": 487361, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.117579936981201, "global_step": 487362, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.122981548309326, "global_step": 487363, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0326011180877686, "global_step": 487364, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.045483350753784, "global_step": 487365, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1007118225097656, "global_step": 487366, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.122661590576172, "global_step": 487367, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0501787662506104, "global_step": 487368, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.103052854537964, "global_step": 487369, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.004302978515625, "global_step": 487370, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.041905403137207, "global_step": 487371, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0305519104003906, "global_step": 487372, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9943463802337646, "global_step": 487373, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.135754346847534, "global_step": 487374, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0714330673217773, "global_step": 487375, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0934898853302, "global_step": 487376, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0723540782928467, "global_step": 487377, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.075049877166748, "global_step": 487378, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.154151201248169, "global_step": 487379, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.017592191696167, "global_step": 487380, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0668373107910156, "global_step": 487381, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.034024238586426, "global_step": 487382, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0360748767852783, "global_step": 487383, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.088115692138672, "global_step": 487384, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0744829177856445, "global_step": 487385, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0879158973693848, "global_step": 487386, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0888655185699463, "global_step": 487387, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.003354072570801, "global_step": 487388, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0359103679656982, "global_step": 487389, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.030677556991577, "global_step": 487390, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1684045791625977, "global_step": 487391, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0760369300842285, "global_step": 487392, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0386953353881836, "global_step": 487393, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0869250297546387, "global_step": 487394, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0690104961395264, "global_step": 487395, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0291242599487305, "global_step": 487396, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.087448835372925, "global_step": 487397, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9823837280273438, "global_step": 487398, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.046380043029785, "global_step": 487399, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.071908950805664, "global_step": 487400, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.014112710952759, "global_step": 487401, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0161080360412598, "global_step": 487402, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.06296443939209, "global_step": 487403, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0185675621032715, "global_step": 487404, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.035191774368286, "global_step": 487405, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9746819734573364, "global_step": 487406, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.01939058303833, "global_step": 487407, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0611674785614014, "global_step": 487408, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.054476261138916, "global_step": 487409, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9208738803863525, "global_step": 487410, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9986093044281006, "global_step": 487411, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.059243679046631, "global_step": 487412, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.994059681892395, "global_step": 487413, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0889382362365723, "global_step": 487414, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0860395431518555, "global_step": 487415, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.115774154663086, "global_step": 487416, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0953121185302734, "global_step": 487417, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0677237510681152, "global_step": 487418, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0769665241241455, "global_step": 487419, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1107778549194336, "global_step": 487420, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0407323837280273, "global_step": 487421, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0206897258758545, "global_step": 487422, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.131704092025757, "global_step": 487423, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0621063709259033, "global_step": 487424, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0794055461883545, "global_step": 487425, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1053428649902344, "global_step": 487426, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0875244140625, "global_step": 487427, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.039646625518799, "global_step": 487428, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9557602405548096, "global_step": 487429, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1787006855010986, "global_step": 487430, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9896173477172852, "global_step": 487431, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0491015911102295, "global_step": 487432, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0955376625061035, "global_step": 487433, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1054303646087646, "global_step": 487434, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1881725788116455, "global_step": 487435, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.151705741882324, "global_step": 487436, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1303210258483887, "global_step": 487437, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.152101755142212, "global_step": 487438, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.000640630722046, "global_step": 487439, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.111215829849243, "global_step": 487440, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.039885997772217, "global_step": 487441, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0224056243896484, "global_step": 487442, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9790383577346802, "global_step": 487443, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.055239677429199, "global_step": 487444, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.074907064437866, "global_step": 487445, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1937668323516846, "global_step": 487446, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.038797378540039, "global_step": 487447, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.073169708251953, "global_step": 487448, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9835408926010132, "global_step": 487449, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0205626487731934, "global_step": 487450, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.054391860961914, "global_step": 487451, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.062419891357422, "global_step": 487452, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1368281841278076, "global_step": 487453, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0862205028533936, "global_step": 487454, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0732715129852295, "global_step": 487455, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0016446113586426, "global_step": 487456, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.053385019302368, "global_step": 487457, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0948548316955566, "global_step": 487458, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0273303985595703, "global_step": 487459, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0756025314331055, "global_step": 487460, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.071424722671509, "global_step": 487461, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0359504222869873, "global_step": 487462, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.026829719543457, "global_step": 487463, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9956445693969727, "global_step": 487464, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.09517765045166, "global_step": 487465, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0773303508758545, "global_step": 487466, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0663139820098877, "global_step": 487467, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.018507480621338, "global_step": 487468, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0676798820495605, "global_step": 487469, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.030210494995117, "global_step": 487470, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.049320697784424, "global_step": 487471, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1193349361419678, "global_step": 487472, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0554163455963135, "global_step": 487473, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0127480030059814, "global_step": 487474, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.037865400314331, "global_step": 487475, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.113816499710083, "global_step": 487476, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.042067289352417, "global_step": 487477, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.091254949569702, "global_step": 487478, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9850659370422363, "global_step": 487479, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0878665447235107, "global_step": 487480, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.996721625328064, "global_step": 487481, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9982881546020508, "global_step": 487482, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.091355085372925, "global_step": 487483, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9481192827224731, "global_step": 487484, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.094707489013672, "global_step": 487485, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0973947048187256, "global_step": 487486, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9967001676559448, "global_step": 487487, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.118563175201416, "global_step": 487488, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.069470167160034, "global_step": 487489, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.122993230819702, "global_step": 487490, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0955514907836914, "global_step": 487491, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.000786781311035, "global_step": 487492, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.008474826812744, "global_step": 487493, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0462377071380615, "global_step": 487494, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.031848669052124, "global_step": 487495, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9455333948135376, "global_step": 487496, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1069817543029785, "global_step": 487497, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.051039695739746, "global_step": 487498, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9978282451629639, "global_step": 487499, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0352816581726074, "global_step": 487500, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1560781002044678, "global_step": 487501, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1080029010772705, "global_step": 487502, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1072864532470703, "global_step": 487503, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9926282167434692, "global_step": 487504, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.070664405822754, "global_step": 487505, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1528515815734863, "global_step": 487506, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0336458683013916, "global_step": 487507, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0546088218688965, "global_step": 487508, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0769975185394287, "global_step": 487509, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.02180552482605, "global_step": 487510, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1035218238830566, "global_step": 487511, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1171669960021973, "global_step": 487512, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0605392456054688, "global_step": 487513, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0731446743011475, "global_step": 487514, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1409201622009277, "global_step": 487515, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0242197513580322, "global_step": 487516, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.084833860397339, "global_step": 487517, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.041630506515503, "global_step": 487518, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0864195823669434, "global_step": 487519, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0291852951049805, "global_step": 487520, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.014346122741699, "global_step": 487521, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0952765941619873, "global_step": 487522, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1144134998321533, "global_step": 487523, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.047358751296997, "global_step": 487524, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1220293045043945, "global_step": 487525, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.116149663925171, "global_step": 487526, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9803073406219482, "global_step": 487527, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.057447910308838, "global_step": 487528, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0757782459259033, "global_step": 487529, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9863663911819458, "global_step": 487530, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.109232187271118, "global_step": 487531, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.036407232284546, "global_step": 487532, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0514118671417236, "global_step": 487533, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.1036360263824463, "global_step": 487534, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0901684761047363, "global_step": 487535, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0285074710845947, "global_step": 487536, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0257625579833984, "global_step": 487537, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.062617540359497, "global_step": 487538, "epoch": 852, "lr": 5e-05}
{"train_loss": 2.0575764179229736, "global_step": 487539, "epoch": 852, "lr": 5e-05}
{"train_loss": 1.9834758043289185, "global_step": 487540, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0651350021362305, "global_step": 487541, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.000676393508911, "global_step": 487542, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0619428157806396, "global_step": 487543, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.02363657951355, "global_step": 487544, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.965524435043335, "global_step": 487545, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.097689151763916, "global_step": 487546, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0608763694763184, "global_step": 487547, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.091379404067993, "global_step": 487548, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0409669876098633, "global_step": 487549, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0389537811279297, "global_step": 487550, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0879979133605957, "global_step": 487551, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0291645526885986, "global_step": 487552, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9849177598953247, "global_step": 487553, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0420634746551514, "global_step": 487554, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.072556257247925, "global_step": 487555, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0317773818969727, "global_step": 487556, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.026502847671509, "global_step": 487557, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9867860078811646, "global_step": 487558, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.00108003616333, "global_step": 487559, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0907156467437744, "global_step": 487560, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0596923828125, "global_step": 487561, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0999703407287598, "global_step": 487562, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9526699781417847, "global_step": 487563, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9796475172042847, "global_step": 487564, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.03373122215271, "global_step": 487565, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.086144208908081, "global_step": 487566, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.019561290740967, "global_step": 487567, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0333962440490723, "global_step": 487568, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.030883312225342, "global_step": 487569, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9488002061843872, "global_step": 487570, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.065398931503296, "global_step": 487571, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.088623046875, "global_step": 487572, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.043050765991211, "global_step": 487573, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1516640186309814, "global_step": 487574, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0949766635894775, "global_step": 487575, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0329225063323975, "global_step": 487576, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0600075721740723, "global_step": 487577, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1333463191986084, "global_step": 487578, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0562310218811035, "global_step": 487579, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1008996963500977, "global_step": 487580, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.080275058746338, "global_step": 487581, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0633087158203125, "global_step": 487582, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0992655754089355, "global_step": 487583, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0172078609466553, "global_step": 487584, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1091411113739014, "global_step": 487585, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.108426809310913, "global_step": 487586, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0513720512390137, "global_step": 487587, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.066645860671997, "global_step": 487588, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0707530975341797, "global_step": 487589, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1558678150177, "global_step": 487590, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0645008087158203, "global_step": 487591, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1107287406921387, "global_step": 487592, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0316622257232666, "global_step": 487593, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9961049556732178, "global_step": 487594, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0475335121154785, "global_step": 487595, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.108588218688965, "global_step": 487596, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9956108331680298, "global_step": 487597, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0512006282806396, "global_step": 487598, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1962106227874756, "global_step": 487599, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9930869340896606, "global_step": 487600, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9986753463745117, "global_step": 487601, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0736565589904785, "global_step": 487602, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0233216285705566, "global_step": 487603, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1615612506866455, "global_step": 487604, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.059911012649536, "global_step": 487605, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0275323390960693, "global_step": 487606, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.059664726257324, "global_step": 487607, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0245561599731445, "global_step": 487608, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0350944995880127, "global_step": 487609, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1173741817474365, "global_step": 487610, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9999829530715942, "global_step": 487611, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0299508571624756, "global_step": 487612, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0540573596954346, "global_step": 487613, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.979734182357788, "global_step": 487614, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.998451590538025, "global_step": 487615, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9954286813735962, "global_step": 487616, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.044753074645996, "global_step": 487617, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.036357879638672, "global_step": 487618, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1188437938690186, "global_step": 487619, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0286810398101807, "global_step": 487620, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0154449939727783, "global_step": 487621, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.080690383911133, "global_step": 487622, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0226335525512695, "global_step": 487623, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.067622184753418, "global_step": 487624, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9846667051315308, "global_step": 487625, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.000188112258911, "global_step": 487626, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0084638595581055, "global_step": 487627, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0793375968933105, "global_step": 487628, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0607924461364746, "global_step": 487629, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1215853691101074, "global_step": 487630, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.018188714981079, "global_step": 487631, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0899088382720947, "global_step": 487632, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0063211917877197, "global_step": 487633, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.097216844558716, "global_step": 487634, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0473456382751465, "global_step": 487635, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1649882793426514, "global_step": 487636, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.088474988937378, "global_step": 487637, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.006678819656372, "global_step": 487638, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0870301723480225, "global_step": 487639, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0561342239379883, "global_step": 487640, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.090470314025879, "global_step": 487641, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0404648780822754, "global_step": 487642, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.058170795440674, "global_step": 487643, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.005845546722412, "global_step": 487644, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9881458282470703, "global_step": 487645, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0571630001068115, "global_step": 487646, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9382820129394531, "global_step": 487647, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1271917819976807, "global_step": 487648, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0630035400390625, "global_step": 487649, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0485055446624756, "global_step": 487650, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.040982484817505, "global_step": 487651, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9931530952453613, "global_step": 487652, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0790488719940186, "global_step": 487653, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0794599056243896, "global_step": 487654, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.018354654312134, "global_step": 487655, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.043456554412842, "global_step": 487656, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.008340835571289, "global_step": 487657, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1341896057128906, "global_step": 487658, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0678153038024902, "global_step": 487659, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0515429973602295, "global_step": 487660, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0468506813049316, "global_step": 487661, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9920241832733154, "global_step": 487662, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.016152858734131, "global_step": 487663, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0349984169006348, "global_step": 487664, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.043259382247925, "global_step": 487665, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.017988681793213, "global_step": 487666, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.050419569015503, "global_step": 487667, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0921311378479004, "global_step": 487668, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.071448564529419, "global_step": 487669, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.995963454246521, "global_step": 487670, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0442700386047363, "global_step": 487671, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0553157329559326, "global_step": 487672, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0334722995758057, "global_step": 487673, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0235610008239746, "global_step": 487674, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.014512300491333, "global_step": 487675, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.980004072189331, "global_step": 487676, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.008329391479492, "global_step": 487677, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1076245307922363, "global_step": 487678, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.102250576019287, "global_step": 487679, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.036517858505249, "global_step": 487680, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.047457695007324, "global_step": 487681, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.168809652328491, "global_step": 487682, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0197575092315674, "global_step": 487683, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.040379762649536, "global_step": 487684, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0144152641296387, "global_step": 487685, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0667598247528076, "global_step": 487686, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9823665618896484, "global_step": 487687, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0301780700683594, "global_step": 487688, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0066473484039307, "global_step": 487689, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9799063205718994, "global_step": 487690, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0178349018096924, "global_step": 487691, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1300339698791504, "global_step": 487692, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.027782678604126, "global_step": 487693, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9936655759811401, "global_step": 487694, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1077866554260254, "global_step": 487695, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0150485038757324, "global_step": 487696, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.997344970703125, "global_step": 487697, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.073017120361328, "global_step": 487698, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.061945676803589, "global_step": 487699, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.038174629211426, "global_step": 487700, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9772318601608276, "global_step": 487701, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9985008239746094, "global_step": 487702, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.009993553161621, "global_step": 487703, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0809531211853027, "global_step": 487704, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0678253173828125, "global_step": 487705, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9345307350158691, "global_step": 487706, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.024754285812378, "global_step": 487707, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.995003342628479, "global_step": 487708, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1030995845794678, "global_step": 487709, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.098945140838623, "global_step": 487710, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1123688220977783, "global_step": 487711, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.091569423675537, "global_step": 487712, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9522242546081543, "global_step": 487713, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.95945405960083, "global_step": 487714, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.058202028274536, "global_step": 487715, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0920321941375732, "global_step": 487716, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0867197513580322, "global_step": 487717, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0781407356262207, "global_step": 487718, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1437559127807617, "global_step": 487719, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.025588274002075, "global_step": 487720, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0606071949005127, "global_step": 487721, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.04939603805542, "global_step": 487722, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0353055000305176, "global_step": 487723, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.096431255340576, "global_step": 487724, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.036778688430786, "global_step": 487725, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0977466106414795, "global_step": 487726, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0303499698638916, "global_step": 487727, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9943127632141113, "global_step": 487728, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.99287748336792, "global_step": 487729, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0115838050842285, "global_step": 487730, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0188450813293457, "global_step": 487731, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1332061290740967, "global_step": 487732, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.068054676055908, "global_step": 487733, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0200419425964355, "global_step": 487734, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.030167818069458, "global_step": 487735, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0895066261291504, "global_step": 487736, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.031196355819702, "global_step": 487737, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0640556812286377, "global_step": 487738, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.083700180053711, "global_step": 487739, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0227293968200684, "global_step": 487740, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.015615224838257, "global_step": 487741, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0437357425689697, "global_step": 487742, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9976587295532227, "global_step": 487743, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.051748037338257, "global_step": 487744, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9754478931427002, "global_step": 487745, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1532716751098633, "global_step": 487746, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0407750606536865, "global_step": 487747, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.067086935043335, "global_step": 487748, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9977233409881592, "global_step": 487749, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0240976810455322, "global_step": 487750, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1429295539855957, "global_step": 487751, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.05578875541687, "global_step": 487752, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.152183771133423, "global_step": 487753, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0394604206085205, "global_step": 487754, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.070935010910034, "global_step": 487755, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0536816120147705, "global_step": 487756, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.00016450881958, "global_step": 487757, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.086794376373291, "global_step": 487758, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.099445104598999, "global_step": 487759, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.018599510192871, "global_step": 487760, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.043931007385254, "global_step": 487761, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9934161901474, "global_step": 487762, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.11580753326416, "global_step": 487763, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.009223699569702, "global_step": 487764, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9671552181243896, "global_step": 487765, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.983117699623108, "global_step": 487766, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0298144817352295, "global_step": 487767, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0310113430023193, "global_step": 487768, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0175392627716064, "global_step": 487769, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1520166397094727, "global_step": 487770, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0642426013946533, "global_step": 487771, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.035696029663086, "global_step": 487772, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.027367353439331, "global_step": 487773, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0108821392059326, "global_step": 487774, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9399073123931885, "global_step": 487775, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.078406810760498, "global_step": 487776, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1471128463745117, "global_step": 487777, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.035823345184326, "global_step": 487778, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.030457019805908, "global_step": 487779, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.983588695526123, "global_step": 487780, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0975875854492188, "global_step": 487781, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0285069942474365, "global_step": 487782, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0186970233917236, "global_step": 487783, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.108477830886841, "global_step": 487784, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0772817134857178, "global_step": 487785, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.099217414855957, "global_step": 487786, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0785083770751953, "global_step": 487787, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.092660665512085, "global_step": 487788, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0003106594085693, "global_step": 487789, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.969342827796936, "global_step": 487790, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.06796932220459, "global_step": 487791, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9031853675842285, "global_step": 487792, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.031066417694092, "global_step": 487793, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0958549976348877, "global_step": 487794, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9993727207183838, "global_step": 487795, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.042651414871216, "global_step": 487796, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1506407260894775, "global_step": 487797, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0555946826934814, "global_step": 487798, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.051597833633423, "global_step": 487799, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1064298152923584, "global_step": 487800, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.083566665649414, "global_step": 487801, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.048092842102051, "global_step": 487802, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.011887550354004, "global_step": 487803, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.054769277572632, "global_step": 487804, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0424580574035645, "global_step": 487805, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.069706439971924, "global_step": 487806, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9938931465148926, "global_step": 487807, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1013150215148926, "global_step": 487808, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0534098148345947, "global_step": 487809, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.027888774871826, "global_step": 487810, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0559167861938477, "global_step": 487811, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1226227283477783, "global_step": 487812, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.072648048400879, "global_step": 487813, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.101990222930908, "global_step": 487814, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0949809551239014, "global_step": 487815, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9551500082015991, "global_step": 487816, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9399610757827759, "global_step": 487817, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.065599203109741, "global_step": 487818, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.099820852279663, "global_step": 487819, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9795821905136108, "global_step": 487820, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1316070556640625, "global_step": 487821, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0318973064422607, "global_step": 487822, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.128011465072632, "global_step": 487823, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.054232358932495, "global_step": 487824, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1286582946777344, "global_step": 487825, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9946262836456299, "global_step": 487826, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1082756519317627, "global_step": 487827, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0832583904266357, "global_step": 487828, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.102334976196289, "global_step": 487829, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.989015817642212, "global_step": 487830, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0465140342712402, "global_step": 487831, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.080014944076538, "global_step": 487832, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9983032941818237, "global_step": 487833, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.09346342086792, "global_step": 487834, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0797929763793945, "global_step": 487835, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9874507188796997, "global_step": 487836, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0605905055999756, "global_step": 487837, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0259459018707275, "global_step": 487838, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.050672769546509, "global_step": 487839, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0721824169158936, "global_step": 487840, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9974558353424072, "global_step": 487841, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.004451036453247, "global_step": 487842, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.063380241394043, "global_step": 487843, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.033179521560669, "global_step": 487844, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0375173091888428, "global_step": 487845, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.969937801361084, "global_step": 487846, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9656016826629639, "global_step": 487847, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1317451000213623, "global_step": 487848, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9131613969802856, "global_step": 487849, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1156091690063477, "global_step": 487850, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.083895206451416, "global_step": 487851, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0050888061523438, "global_step": 487852, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9691442251205444, "global_step": 487853, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0495030879974365, "global_step": 487854, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.018834114074707, "global_step": 487855, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9813086986541748, "global_step": 487856, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9448422193527222, "global_step": 487857, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.08004093170166, "global_step": 487858, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0481274127960205, "global_step": 487859, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0543742179870605, "global_step": 487860, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0378501415252686, "global_step": 487861, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0613722801208496, "global_step": 487862, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9650899171829224, "global_step": 487863, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0697216987609863, "global_step": 487864, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.035184383392334, "global_step": 487865, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0428826808929443, "global_step": 487866, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0971481800079346, "global_step": 487867, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0607409477233887, "global_step": 487868, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0870249271392822, "global_step": 487869, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.016427516937256, "global_step": 487870, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0339887142181396, "global_step": 487871, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.05208158493042, "global_step": 487872, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0080902576446533, "global_step": 487873, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0102622509002686, "global_step": 487874, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.085254192352295, "global_step": 487875, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.029069662094116, "global_step": 487876, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.027822732925415, "global_step": 487877, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.149244546890259, "global_step": 487878, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.144941568374634, "global_step": 487879, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.088130474090576, "global_step": 487880, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.012329578399658, "global_step": 487881, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9643149375915527, "global_step": 487882, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0464863777160645, "global_step": 487883, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0263073444366455, "global_step": 487884, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0616767406463623, "global_step": 487885, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.150088310241699, "global_step": 487886, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.977985143661499, "global_step": 487887, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.040299654006958, "global_step": 487888, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.092676877975464, "global_step": 487889, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0327887535095215, "global_step": 487890, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0601773262023926, "global_step": 487891, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.023200750350952, "global_step": 487892, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.06492018699646, "global_step": 487893, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9772411584854126, "global_step": 487894, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1143388748168945, "global_step": 487895, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1283063888549805, "global_step": 487896, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0865437984466553, "global_step": 487897, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.090035915374756, "global_step": 487898, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1257870197296143, "global_step": 487899, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0879220962524414, "global_step": 487900, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0319461822509766, "global_step": 487901, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0877299308776855, "global_step": 487902, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0521576404571533, "global_step": 487903, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0227835178375244, "global_step": 487904, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.012146472930908, "global_step": 487905, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.116382360458374, "global_step": 487906, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.029085397720337, "global_step": 487907, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0777955055236816, "global_step": 487908, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.998136043548584, "global_step": 487909, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9805766344070435, "global_step": 487910, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0132384300231934, "global_step": 487911, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0591936111450195, "global_step": 487912, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.095263719558716, "global_step": 487913, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0609729290008545, "global_step": 487914, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.029805898666382, "global_step": 487915, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0638701915740967, "global_step": 487916, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.034228563308716, "global_step": 487917, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0475239753723145, "global_step": 487918, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1103365421295166, "global_step": 487919, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.161644220352173, "global_step": 487920, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9832574129104614, "global_step": 487921, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0242700576782227, "global_step": 487922, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9951945543289185, "global_step": 487923, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0041239261627197, "global_step": 487924, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.074140787124634, "global_step": 487925, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0839078426361084, "global_step": 487926, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0648512840270996, "global_step": 487927, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0753586292266846, "global_step": 487928, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9941869974136353, "global_step": 487929, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9277329444885254, "global_step": 487930, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0082285404205322, "global_step": 487931, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.049870252609253, "global_step": 487932, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.044267177581787, "global_step": 487933, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1243577003479004, "global_step": 487934, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0536766052246094, "global_step": 487935, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0230026245117188, "global_step": 487936, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.054781436920166, "global_step": 487937, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.139662027359009, "global_step": 487938, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.933928370475769, "global_step": 487939, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0503971576690674, "global_step": 487940, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0845797061920166, "global_step": 487941, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.00311017036438, "global_step": 487942, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.109271287918091, "global_step": 487943, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1997528076171875, "global_step": 487944, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0514464378356934, "global_step": 487945, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.05074143409729, "global_step": 487946, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1000335216522217, "global_step": 487947, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.120802402496338, "global_step": 487948, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0323781967163086, "global_step": 487949, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0767083168029785, "global_step": 487950, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.059725284576416, "global_step": 487951, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9894216060638428, "global_step": 487952, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0220961570739746, "global_step": 487953, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9734967947006226, "global_step": 487954, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9807062149047852, "global_step": 487955, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9700491428375244, "global_step": 487956, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.036127805709839, "global_step": 487957, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9634153842926025, "global_step": 487958, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.089398145675659, "global_step": 487959, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.003295660018921, "global_step": 487960, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0826568603515625, "global_step": 487961, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0155599117279053, "global_step": 487962, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0016727447509766, "global_step": 487963, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.046135187149048, "global_step": 487964, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.068849563598633, "global_step": 487965, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1286611557006836, "global_step": 487966, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.066512107849121, "global_step": 487967, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0905494689941406, "global_step": 487968, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.140373945236206, "global_step": 487969, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.047811508178711, "global_step": 487970, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0240111351013184, "global_step": 487971, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0042357444763184, "global_step": 487972, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0488970279693604, "global_step": 487973, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.010354995727539, "global_step": 487974, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0093600749969482, "global_step": 487975, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0405988693237305, "global_step": 487976, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1402642726898193, "global_step": 487977, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9946322441101074, "global_step": 487978, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0361719131469727, "global_step": 487979, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.082002878189087, "global_step": 487980, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0891764163970947, "global_step": 487981, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0463037490844727, "global_step": 487982, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.08841609954834, "global_step": 487983, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.067517042160034, "global_step": 487984, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0651907920837402, "global_step": 487985, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.008639097213745, "global_step": 487986, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.017732620239258, "global_step": 487987, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0070629119873047, "global_step": 487988, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.009958505630493, "global_step": 487989, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0339713096618652, "global_step": 487990, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1045665740966797, "global_step": 487991, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0930614471435547, "global_step": 487992, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0727763175964355, "global_step": 487993, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0971028804779053, "global_step": 487994, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0119097232818604, "global_step": 487995, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0706470012664795, "global_step": 487996, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.07724928855896, "global_step": 487997, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0850257873535156, "global_step": 487998, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.053773880004883, "global_step": 487999, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9837360382080078, "global_step": 488000, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0205442905426025, "global_step": 488001, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0539562702178955, "global_step": 488002, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.11317777633667, "global_step": 488003, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.098151922225952, "global_step": 488004, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.097829818725586, "global_step": 488005, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0575757026672363, "global_step": 488006, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.009192705154419, "global_step": 488007, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0791571140289307, "global_step": 488008, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0040550231933594, "global_step": 488009, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.070826292037964, "global_step": 488010, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.076052665710449, "global_step": 488011, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0126874446868896, "global_step": 488012, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0441017150878906, "global_step": 488013, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.137922763824463, "global_step": 488014, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.134004831314087, "global_step": 488015, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.064906597137451, "global_step": 488016, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0297560691833496, "global_step": 488017, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0517430305480957, "global_step": 488018, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9629194736480713, "global_step": 488019, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9981366395950317, "global_step": 488020, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.024885416030884, "global_step": 488021, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1540095806121826, "global_step": 488022, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.941306710243225, "global_step": 488023, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0774929523468018, "global_step": 488024, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.2198736667633057, "global_step": 488025, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.031229257583618, "global_step": 488026, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0704638957977295, "global_step": 488027, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.2345283031463623, "global_step": 488028, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1105599403381348, "global_step": 488029, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.029629707336426, "global_step": 488030, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.106559991836548, "global_step": 488031, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.107802629470825, "global_step": 488032, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.139080762863159, "global_step": 488033, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9833394289016724, "global_step": 488034, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.06998610496521, "global_step": 488035, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.058121919631958, "global_step": 488036, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0530011653900146, "global_step": 488037, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.124493360519409, "global_step": 488038, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0664210319519043, "global_step": 488039, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0948476791381836, "global_step": 488040, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.127540111541748, "global_step": 488041, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0756874084472656, "global_step": 488042, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.080275058746338, "global_step": 488043, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0766096115112305, "global_step": 488044, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.134089946746826, "global_step": 488045, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1158218383789062, "global_step": 488046, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0449843406677246, "global_step": 488047, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0556206703186035, "global_step": 488048, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0154757499694824, "global_step": 488049, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0673723220825195, "global_step": 488050, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0153186321258545, "global_step": 488051, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1304969787597656, "global_step": 488052, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0571210384368896, "global_step": 488053, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0037431716918945, "global_step": 488054, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0755481719970703, "global_step": 488055, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0160939693450928, "global_step": 488056, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.098186492919922, "global_step": 488057, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0295114517211914, "global_step": 488058, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0847373008728027, "global_step": 488059, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9753345251083374, "global_step": 488060, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9802862405776978, "global_step": 488061, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.051666498184204, "global_step": 488062, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.013587713241577, "global_step": 488063, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.012131690979004, "global_step": 488064, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9745044708251953, "global_step": 488065, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0559892654418945, "global_step": 488066, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1192898750305176, "global_step": 488067, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.072396993637085, "global_step": 488068, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1268668174743652, "global_step": 488069, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1269407272338867, "global_step": 488070, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0400550365448, "global_step": 488071, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0379133224487305, "global_step": 488072, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0217361450195312, "global_step": 488073, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.083397150039673, "global_step": 488074, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1646816730499268, "global_step": 488075, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0426623821258545, "global_step": 488076, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9948173761367798, "global_step": 488077, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0836169719696045, "global_step": 488078, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0815625190734863, "global_step": 488079, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1093602180480957, "global_step": 488080, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1072773933410645, "global_step": 488081, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0923619270324707, "global_step": 488082, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.065757989883423, "global_step": 488083, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0258798599243164, "global_step": 488084, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.054201602935791, "global_step": 488085, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.060633897781372, "global_step": 488086, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0029842853546143, "global_step": 488087, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.02051043510437, "global_step": 488088, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0660500526428223, "global_step": 488089, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.045119047164917, "global_step": 488090, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1025545597076416, "global_step": 488091, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.955369472503662, "global_step": 488092, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.054476499557495, "global_step": 488093, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0830886363983154, "global_step": 488094, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.086515188217163, "global_step": 488095, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.047473430633545, "global_step": 488096, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1178736686706543, "global_step": 488097, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0409340858459473, "global_step": 488098, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0471014976501465, "global_step": 488099, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.035506248474121, "global_step": 488100, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.018219232559204, "global_step": 488101, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.003469228744507, "global_step": 488102, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.028454542160034, "global_step": 488103, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.041438341140747, "global_step": 488104, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.041282892227173, "global_step": 488105, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.003974676132202, "global_step": 488106, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.014939069747925, "global_step": 488107, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0293943881988525, "global_step": 488108, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.035395860671997, "global_step": 488109, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1258862018585205, "global_step": 488110, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0765175819396973, "global_step": 488111, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9966585636138916, "global_step": 488112, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0600955486297607, "global_step": 488113, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1029298305511475, "global_step": 488114, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0844295024871826, "global_step": 488115, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1091630458831787, "global_step": 488116, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1047253608703613, "global_step": 488117, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.026533365249634, "global_step": 488118, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0201196670532227, "global_step": 488119, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0412094593048096, "global_step": 488120, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0840816497802734, "global_step": 488121, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1101832389831543, "global_step": 488122, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0849087238311768, "global_step": 488123, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.017726421356201, "global_step": 488124, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0791473388671875, "global_step": 488125, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1196532249450684, "global_step": 488126, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.105515480041504, "global_step": 488127, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0861902236938477, "global_step": 488128, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0569512844085693, "global_step": 488129, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0816593170166016, "global_step": 488130, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0679774284362793, "global_step": 488131, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0243141651153564, "global_step": 488132, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1172173023223877, "global_step": 488133, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.021561622619629, "global_step": 488134, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0437393188476562, "global_step": 488135, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0755693912506104, "global_step": 488136, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0415220260620117, "global_step": 488137, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.124488353729248, "global_step": 488138, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0933101177215576, "global_step": 488139, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9522491693496704, "global_step": 488140, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.975035548210144, "global_step": 488141, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1049275398254395, "global_step": 488142, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1035685539245605, "global_step": 488143, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9721969366073608, "global_step": 488144, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0845141410827637, "global_step": 488145, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.035797357559204, "global_step": 488146, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0188140869140625, "global_step": 488147, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.987136721611023, "global_step": 488148, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9979524612426758, "global_step": 488149, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1740636825561523, "global_step": 488150, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0947518348693848, "global_step": 488151, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9895344972610474, "global_step": 488152, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9471675157546997, "global_step": 488153, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.07584285736084, "global_step": 488154, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.05609393119812, "global_step": 488155, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0591938495635986, "global_step": 488156, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.033137083053589, "global_step": 488157, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0804123878479004, "global_step": 488158, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0638623237609863, "global_step": 488159, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0070266723632812, "global_step": 488160, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0825626850128174, "global_step": 488161, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.05795955657959, "global_step": 488162, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0826327800750732, "global_step": 488163, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0796477794647217, "global_step": 488164, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1305220127105713, "global_step": 488165, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0080647468566895, "global_step": 488166, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0427236557006836, "global_step": 488167, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0975706577301025, "global_step": 488168, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.047668695449829, "global_step": 488169, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0775225162506104, "global_step": 488170, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9655083417892456, "global_step": 488171, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0363948345184326, "global_step": 488172, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0356080532073975, "global_step": 488173, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9561164379119873, "global_step": 488174, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.179464340209961, "global_step": 488175, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0179014205932617, "global_step": 488176, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.048173666000366, "global_step": 488177, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.109675407409668, "global_step": 488178, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0789198875427246, "global_step": 488179, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.038616180419922, "global_step": 488180, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1735386848449707, "global_step": 488181, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0766680240631104, "global_step": 488182, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0829174518585205, "global_step": 488183, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.074887275695801, "global_step": 488184, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.009097099304199, "global_step": 488185, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0146100521087646, "global_step": 488186, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.15458345413208, "global_step": 488187, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0353353023529053, "global_step": 488188, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.988778829574585, "global_step": 488189, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0619354248046875, "global_step": 488190, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9954150915145874, "global_step": 488191, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.03708815574646, "global_step": 488192, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.058354139328003, "global_step": 488193, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.142489194869995, "global_step": 488194, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0986480712890625, "global_step": 488195, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.074387788772583, "global_step": 488196, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1057283878326416, "global_step": 488197, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0994691848754883, "global_step": 488198, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.004743814468384, "global_step": 488199, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0722055435180664, "global_step": 488200, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.082207202911377, "global_step": 488201, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1161346435546875, "global_step": 488202, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0045392513275146, "global_step": 488203, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0767321586608887, "global_step": 488204, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9995802640914917, "global_step": 488205, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9946988821029663, "global_step": 488206, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9636054039001465, "global_step": 488207, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0292210578918457, "global_step": 488208, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.033752679824829, "global_step": 488209, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.060391902923584, "global_step": 488210, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0911827087402344, "global_step": 488211, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.125117778778076, "global_step": 488212, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0583150386810303, "global_step": 488213, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0606305599212646, "global_step": 488214, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.101020574569702, "global_step": 488215, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.048757791519165, "global_step": 488216, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0729024410247803, "global_step": 488217, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.012035608291626, "global_step": 488218, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0803134441375732, "global_step": 488219, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1371805667877197, "global_step": 488220, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1425540447235107, "global_step": 488221, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.005265235900879, "global_step": 488222, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9949702024459839, "global_step": 488223, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.051060438156128, "global_step": 488224, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.062260389328003, "global_step": 488225, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0611562728881836, "global_step": 488226, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.09454607963562, "global_step": 488227, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0787551403045654, "global_step": 488228, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.016047477722168, "global_step": 488229, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.075392723083496, "global_step": 488230, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0800037384033203, "global_step": 488231, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0668270587921143, "global_step": 488232, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1410508155822754, "global_step": 488233, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0221962928771973, "global_step": 488234, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9792076349258423, "global_step": 488235, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0564188957214355, "global_step": 488236, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9933654069900513, "global_step": 488237, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9628870487213135, "global_step": 488238, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1565258502960205, "global_step": 488239, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0336968898773193, "global_step": 488240, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9975361824035645, "global_step": 488241, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.037217140197754, "global_step": 488242, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0700206756591797, "global_step": 488243, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0290687084198, "global_step": 488244, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0344462394714355, "global_step": 488245, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0282676219940186, "global_step": 488246, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.037961483001709, "global_step": 488247, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1274423599243164, "global_step": 488248, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9947350025177002, "global_step": 488249, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.140540599822998, "global_step": 488250, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0724620819091797, "global_step": 488251, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0328099727630615, "global_step": 488252, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0106277465820312, "global_step": 488253, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.978415846824646, "global_step": 488254, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0986807346343994, "global_step": 488255, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.013507843017578, "global_step": 488256, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9995026588439941, "global_step": 488257, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0882656574249268, "global_step": 488258, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.120265483856201, "global_step": 488259, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.958909034729004, "global_step": 488260, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.046051025390625, "global_step": 488261, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0935018062591553, "global_step": 488262, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0676558017730713, "global_step": 488263, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.145493745803833, "global_step": 488264, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.013735294342041, "global_step": 488265, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.10745906829834, "global_step": 488266, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1229867935180664, "global_step": 488267, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0896639823913574, "global_step": 488268, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0147955417633057, "global_step": 488269, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.078606128692627, "global_step": 488270, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9723888635635376, "global_step": 488271, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0688393115997314, "global_step": 488272, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.07855486869812, "global_step": 488273, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1279735565185547, "global_step": 488274, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.117871046066284, "global_step": 488275, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.030740261077881, "global_step": 488276, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0594005584716797, "global_step": 488277, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.123791456222534, "global_step": 488278, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0085904598236084, "global_step": 488279, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.101752519607544, "global_step": 488280, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.038456916809082, "global_step": 488281, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.940024733543396, "global_step": 488282, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9894996881484985, "global_step": 488283, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0920321941375732, "global_step": 488284, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0690855979919434, "global_step": 488285, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1294949054718018, "global_step": 488286, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1154253482818604, "global_step": 488287, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0227582454681396, "global_step": 488288, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.071199893951416, "global_step": 488289, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.055568218231201, "global_step": 488290, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0768864154815674, "global_step": 488291, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1202456951141357, "global_step": 488292, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0260329246520996, "global_step": 488293, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0750784873962402, "global_step": 488294, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.093970537185669, "global_step": 488295, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.120790481567383, "global_step": 488296, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0544443130493164, "global_step": 488297, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0863683223724365, "global_step": 488298, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0566322803497314, "global_step": 488299, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.006530284881592, "global_step": 488300, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9564383029937744, "global_step": 488301, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0659565925598145, "global_step": 488302, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0811429023742676, "global_step": 488303, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.03723406791687, "global_step": 488304, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.124638795852661, "global_step": 488305, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0201268196105957, "global_step": 488306, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.111558198928833, "global_step": 488307, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1054253578186035, "global_step": 488308, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0403850078582764, "global_step": 488309, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.094675302505493, "global_step": 488310, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0896902084350586, "global_step": 488311, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0924289226531982, "global_step": 488312, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.090611219406128, "global_step": 488313, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1200692653656006, "global_step": 488314, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.066244125366211, "global_step": 488315, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1690285205841064, "global_step": 488316, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.067028760910034, "global_step": 488317, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.988079309463501, "global_step": 488318, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1219582557678223, "global_step": 488319, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0103864669799805, "global_step": 488320, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.095874071121216, "global_step": 488321, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.067934513092041, "global_step": 488322, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0136992931365967, "global_step": 488323, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9931443929672241, "global_step": 488324, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.07110333442688, "global_step": 488325, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0724875926971436, "global_step": 488326, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0946593284606934, "global_step": 488327, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0057079792022705, "global_step": 488328, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.048846960067749, "global_step": 488329, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.007232427597046, "global_step": 488330, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.061030387878418, "global_step": 488331, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0028040409088135, "global_step": 488332, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0089151859283447, "global_step": 488333, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1482925415039062, "global_step": 488334, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.04327130317688, "global_step": 488335, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1075263023376465, "global_step": 488336, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.108039140701294, "global_step": 488337, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.013822317123413, "global_step": 488338, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0110843181610107, "global_step": 488339, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1501991748809814, "global_step": 488340, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.080301523208618, "global_step": 488341, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.082779884338379, "global_step": 488342, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0429885387420654, "global_step": 488343, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.02179217338562, "global_step": 488344, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0699760913848877, "global_step": 488345, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0967977046966553, "global_step": 488346, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0767056941986084, "global_step": 488347, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9850585460662842, "global_step": 488348, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.042506217956543, "global_step": 488349, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.028731346130371, "global_step": 488350, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.096583127975464, "global_step": 488351, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.017817497253418, "global_step": 488352, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.057159900665283, "global_step": 488353, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0499017238616943, "global_step": 488354, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0289695262908936, "global_step": 488355, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1771433353424072, "global_step": 488356, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.991921305656433, "global_step": 488357, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0232443809509277, "global_step": 488358, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.082430362701416, "global_step": 488359, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0608935356140137, "global_step": 488360, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.074185609817505, "global_step": 488361, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9986134767532349, "global_step": 488362, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0860581398010254, "global_step": 488363, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.06492018699646, "global_step": 488364, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9929559230804443, "global_step": 488365, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0050437450408936, "global_step": 488366, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0411317348480225, "global_step": 488367, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.167635679244995, "global_step": 488368, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.050330877304077, "global_step": 488369, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9483643770217896, "global_step": 488370, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0967931747436523, "global_step": 488371, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9639744758605957, "global_step": 488372, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0967657566070557, "global_step": 488373, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1835215091705322, "global_step": 488374, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0803983211517334, "global_step": 488375, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0687687397003174, "global_step": 488376, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.152209997177124, "global_step": 488377, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0700318813323975, "global_step": 488378, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1373980045318604, "global_step": 488379, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0577826499938965, "global_step": 488380, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.061000108718872, "global_step": 488381, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1030399799346924, "global_step": 488382, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0314433574676514, "global_step": 488383, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0715067386627197, "global_step": 488384, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9639112949371338, "global_step": 488385, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9873758554458618, "global_step": 488386, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0924885272979736, "global_step": 488387, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1047236919403076, "global_step": 488388, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0457546710968018, "global_step": 488389, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1552088260650635, "global_step": 488390, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1299922466278076, "global_step": 488391, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0534796714782715, "global_step": 488392, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.05155348777771, "global_step": 488393, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0023818016052246, "global_step": 488394, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0743470191955566, "global_step": 488395, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0573997497558594, "global_step": 488396, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0580437183380127, "global_step": 488397, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1274759769439697, "global_step": 488398, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.04451584815979, "global_step": 488399, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0455081462860107, "global_step": 488400, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.098358631134033, "global_step": 488401, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.106180429458618, "global_step": 488402, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0555784702301025, "global_step": 488403, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0025408267974854, "global_step": 488404, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0874550342559814, "global_step": 488405, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.051909923553467, "global_step": 488406, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9701359272003174, "global_step": 488407, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0513250827789307, "global_step": 488408, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1471927165985107, "global_step": 488409, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.049891948699951, "global_step": 488410, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.014775276184082, "global_step": 488411, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1497862339019775, "global_step": 488412, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0982842445373535, "global_step": 488413, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.933869481086731, "global_step": 488414, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1217784881591797, "global_step": 488415, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0198886394500732, "global_step": 488416, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.101557493209839, "global_step": 488417, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0383801460266113, "global_step": 488418, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.035632371902466, "global_step": 488419, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0243160724639893, "global_step": 488420, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9965938329696655, "global_step": 488421, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.009728193283081, "global_step": 488422, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0844075679779053, "global_step": 488423, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.11163067817688, "global_step": 488424, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.080057382583618, "global_step": 488425, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.054841995239258, "global_step": 488426, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0833611488342285, "global_step": 488427, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1778435707092285, "global_step": 488428, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1296911239624023, "global_step": 488429, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.024141550064087, "global_step": 488430, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9690877199172974, "global_step": 488431, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.040043830871582, "global_step": 488432, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.084289789199829, "global_step": 488433, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9596554040908813, "global_step": 488434, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.993316888809204, "global_step": 488435, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.949154019355774, "global_step": 488436, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0100502967834473, "global_step": 488437, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1073546409606934, "global_step": 488438, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.035655975341797, "global_step": 488439, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.097379207611084, "global_step": 488440, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.054487705230713, "global_step": 488441, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0408935546875, "global_step": 488442, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1490635871887207, "global_step": 488443, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.104645013809204, "global_step": 488444, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0750956535339355, "global_step": 488445, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0014545917510986, "global_step": 488446, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.016709566116333, "global_step": 488447, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0522868633270264, "global_step": 488448, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.084315061569214, "global_step": 488449, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.114327907562256, "global_step": 488450, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.099364995956421, "global_step": 488451, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.055335283279419, "global_step": 488452, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.108705759048462, "global_step": 488453, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.063931703567505, "global_step": 488454, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.040055990219116, "global_step": 488455, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.106243371963501, "global_step": 488456, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0019116401672363, "global_step": 488457, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1167657375335693, "global_step": 488458, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0686566829681396, "global_step": 488459, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.02032208442688, "global_step": 488460, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.107748031616211, "global_step": 488461, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0794265270233154, "global_step": 488462, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0501160621643066, "global_step": 488463, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0168206691741943, "global_step": 488464, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.131427526473999, "global_step": 488465, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.048081398010254, "global_step": 488466, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.1044812202453613, "global_step": 488467, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.067831039428711, "global_step": 488468, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.081800699234009, "global_step": 488469, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.132359027862549, "global_step": 488470, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0366268157958984, "global_step": 488471, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.052471160888672, "global_step": 488472, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.056610584259033, "global_step": 488473, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.123903751373291, "global_step": 488474, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.099307060241699, "global_step": 488475, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0500283241271973, "global_step": 488476, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.144357204437256, "global_step": 488477, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.089928150177002, "global_step": 488478, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0651872158050537, "global_step": 488479, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.963550090789795, "global_step": 488480, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0417141914367676, "global_step": 488481, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0883443355560303, "global_step": 488482, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.084897994995117, "global_step": 488483, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.079806327819824, "global_step": 488484, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0608773231506348, "global_step": 488485, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9917486906051636, "global_step": 488486, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0212228298187256, "global_step": 488487, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.046701431274414, "global_step": 488488, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.127545118331909, "global_step": 488489, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.068833589553833, "global_step": 488490, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0333540439605713, "global_step": 488491, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9923810958862305, "global_step": 488492, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.106182336807251, "global_step": 488493, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0971968173980713, "global_step": 488494, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0597708225250244, "global_step": 488495, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.947560429573059, "global_step": 488496, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0613088607788086, "global_step": 488497, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.033843994140625, "global_step": 488498, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0434181690216064, "global_step": 488499, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.131476879119873, "global_step": 488500, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0697085857391357, "global_step": 488501, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.089669704437256, "global_step": 488502, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0707247257232666, "global_step": 488503, "epoch": 853, "lr": 5e-05}
{"train_loss": 1.9924808740615845, "global_step": 488504, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0241506099700928, "global_step": 488505, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.051459789276123, "global_step": 488506, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.0667524337768555, "global_step": 488507, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.054830551147461, "global_step": 488508, "epoch": 853, "lr": 5e-05}
{"train_loss": 2.103426933288574, "global_step": 488509, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0730912685394287, "global_step": 488510, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.016155242919922, "global_step": 488511, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0433011054992676, "global_step": 488512, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9785876274108887, "global_step": 488513, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.979116678237915, "global_step": 488514, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.115736246109009, "global_step": 488515, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.054056167602539, "global_step": 488516, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.026873826980591, "global_step": 488517, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9797906875610352, "global_step": 488518, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.000681161880493, "global_step": 488519, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0484964847564697, "global_step": 488520, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.023808002471924, "global_step": 488521, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0614283084869385, "global_step": 488522, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0730371475219727, "global_step": 488523, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0939793586730957, "global_step": 488524, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0936105251312256, "global_step": 488525, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0696842670440674, "global_step": 488526, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9895167350769043, "global_step": 488527, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.981907606124878, "global_step": 488528, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9810161590576172, "global_step": 488529, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0497653484344482, "global_step": 488530, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0698277950286865, "global_step": 488531, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9716600179672241, "global_step": 488532, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0983645915985107, "global_step": 488533, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.054807424545288, "global_step": 488534, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.902720332145691, "global_step": 488535, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.092747211456299, "global_step": 488536, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0558197498321533, "global_step": 488537, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9805521965026855, "global_step": 488538, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1193087100982666, "global_step": 488539, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0579674243927, "global_step": 488540, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9694424867630005, "global_step": 488541, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.019879102706909, "global_step": 488542, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0699377059936523, "global_step": 488543, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0628578662872314, "global_step": 488544, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1372475624084473, "global_step": 488545, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0097107887268066, "global_step": 488546, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1531736850738525, "global_step": 488547, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.10746693611145, "global_step": 488548, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.091078042984009, "global_step": 488549, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1061301231384277, "global_step": 488550, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1144533157348633, "global_step": 488551, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.007723808288574, "global_step": 488552, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.08107328414917, "global_step": 488553, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0275328159332275, "global_step": 488554, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0729212760925293, "global_step": 488555, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1214892864227295, "global_step": 488556, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9918798208236694, "global_step": 488557, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.136528730392456, "global_step": 488558, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0357425212860107, "global_step": 488559, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0922017097473145, "global_step": 488560, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9466114044189453, "global_step": 488561, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0917797088623047, "global_step": 488562, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.981058120727539, "global_step": 488563, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.17206072807312, "global_step": 488564, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0207886695861816, "global_step": 488565, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0526881217956543, "global_step": 488566, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9900003671646118, "global_step": 488567, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0252976417541504, "global_step": 488568, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9790217876434326, "global_step": 488569, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.02239990234375, "global_step": 488570, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0425102710723877, "global_step": 488571, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9671757221221924, "global_step": 488572, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0099387168884277, "global_step": 488573, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.098062515258789, "global_step": 488574, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.036839485168457, "global_step": 488575, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9881937503814697, "global_step": 488576, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.028538227081299, "global_step": 488577, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.999152421951294, "global_step": 488578, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.101722240447998, "global_step": 488579, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1225461959838867, "global_step": 488580, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9743781089782715, "global_step": 488581, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0962324142456055, "global_step": 488582, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1068787574768066, "global_step": 488583, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.068239688873291, "global_step": 488584, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.012254476547241, "global_step": 488585, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0666606426239014, "global_step": 488586, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1043176651000977, "global_step": 488587, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.098564386367798, "global_step": 488588, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.053703784942627, "global_step": 488589, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0180821418762207, "global_step": 488590, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0645806789398193, "global_step": 488591, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0403380393981934, "global_step": 488592, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.011413097381592, "global_step": 488593, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.065187454223633, "global_step": 488594, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.113542079925537, "global_step": 488595, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0338134765625, "global_step": 488596, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.05617618560791, "global_step": 488597, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0800185203552246, "global_step": 488598, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0548059940338135, "global_step": 488599, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0483527183532715, "global_step": 488600, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.059349775314331, "global_step": 488601, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0695652961730957, "global_step": 488602, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9604642391204834, "global_step": 488603, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.983150601387024, "global_step": 488604, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.071293592453003, "global_step": 488605, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0536587238311768, "global_step": 488606, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.987531304359436, "global_step": 488607, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.052731990814209, "global_step": 488608, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0577332973480225, "global_step": 488609, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.046926498413086, "global_step": 488610, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0441925525665283, "global_step": 488611, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9823002815246582, "global_step": 488612, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0699753761291504, "global_step": 488613, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.115142822265625, "global_step": 488614, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0083911418914795, "global_step": 488615, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0649209022521973, "global_step": 488616, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1399691104888916, "global_step": 488617, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0238888263702393, "global_step": 488618, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9973993301391602, "global_step": 488619, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9979568719863892, "global_step": 488620, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.041508674621582, "global_step": 488621, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0717036724090576, "global_step": 488622, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0135257244110107, "global_step": 488623, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1167454719543457, "global_step": 488624, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0672214031219482, "global_step": 488625, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1286356449127197, "global_step": 488626, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0506536960601807, "global_step": 488627, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.035297155380249, "global_step": 488628, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0458719730377197, "global_step": 488629, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0868422985076904, "global_step": 488630, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9549773931503296, "global_step": 488631, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.043424129486084, "global_step": 488632, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.040599822998047, "global_step": 488633, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.054168462753296, "global_step": 488634, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0079689025878906, "global_step": 488635, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.072828769683838, "global_step": 488636, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0157251358032227, "global_step": 488637, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.083707809448242, "global_step": 488638, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.016735553741455, "global_step": 488639, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.987122654914856, "global_step": 488640, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.095155715942383, "global_step": 488641, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9748295545578003, "global_step": 488642, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0560314655303955, "global_step": 488643, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.02317476272583, "global_step": 488644, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.039597272872925, "global_step": 488645, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0483105182647705, "global_step": 488646, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0640461444854736, "global_step": 488647, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0796074867248535, "global_step": 488648, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.056292772293091, "global_step": 488649, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0378293991088867, "global_step": 488650, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1019744873046875, "global_step": 488651, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.037681818008423, "global_step": 488652, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.062985420227051, "global_step": 488653, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0174129009246826, "global_step": 488654, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.088862895965576, "global_step": 488655, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0849967002868652, "global_step": 488656, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.015437364578247, "global_step": 488657, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1107897758483887, "global_step": 488658, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.113513708114624, "global_step": 488659, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1061625480651855, "global_step": 488660, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0890073776245117, "global_step": 488661, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.151761531829834, "global_step": 488662, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1167125701904297, "global_step": 488663, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0209298133850098, "global_step": 488664, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.006465196609497, "global_step": 488665, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0303421020507812, "global_step": 488666, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.036799430847168, "global_step": 488667, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.948340654373169, "global_step": 488668, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.100940227508545, "global_step": 488669, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9927408695220947, "global_step": 488670, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.01064133644104, "global_step": 488671, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9816713333129883, "global_step": 488672, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.078493356704712, "global_step": 488673, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.984256386756897, "global_step": 488674, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0247349739074707, "global_step": 488675, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0187292098999023, "global_step": 488676, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.038447141647339, "global_step": 488677, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9576127529144287, "global_step": 488678, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.058600902557373, "global_step": 488679, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.086300849914551, "global_step": 488680, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.006471872329712, "global_step": 488681, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0868377685546875, "global_step": 488682, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0490567684173584, "global_step": 488683, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9965840578079224, "global_step": 488684, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1283116340637207, "global_step": 488685, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.080636501312256, "global_step": 488686, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0654282569885254, "global_step": 488687, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.985150694847107, "global_step": 488688, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0379798412323, "global_step": 488689, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.12492299079895, "global_step": 488690, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.080826997756958, "global_step": 488691, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0475103855133057, "global_step": 488692, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.038360118865967, "global_step": 488693, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.074817419052124, "global_step": 488694, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0548555850982666, "global_step": 488695, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.067439556121826, "global_step": 488696, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0097432136535645, "global_step": 488697, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0638909339904785, "global_step": 488698, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0343072414398193, "global_step": 488699, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.027681589126587, "global_step": 488700, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.207836151123047, "global_step": 488701, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1204638481140137, "global_step": 488702, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.098369598388672, "global_step": 488703, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.087235450744629, "global_step": 488704, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.973815679550171, "global_step": 488705, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0279531478881836, "global_step": 488706, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0573997497558594, "global_step": 488707, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.076000452041626, "global_step": 488708, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.076523542404175, "global_step": 488709, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.050356388092041, "global_step": 488710, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.044544219970703, "global_step": 488711, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.055793046951294, "global_step": 488712, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9923851490020752, "global_step": 488713, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.055579423904419, "global_step": 488714, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1692731380462646, "global_step": 488715, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.130072832107544, "global_step": 488716, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.115727186203003, "global_step": 488717, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0442166328430176, "global_step": 488718, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.061061382293701, "global_step": 488719, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0806350708007812, "global_step": 488720, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0045502185821533, "global_step": 488721, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.8917927742004395, "global_step": 488722, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1001362800598145, "global_step": 488723, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.050405502319336, "global_step": 488724, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.042639970779419, "global_step": 488725, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1573989391326904, "global_step": 488726, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0580174922943115, "global_step": 488727, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9908018112182617, "global_step": 488728, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.978603720664978, "global_step": 488729, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0897879600524902, "global_step": 488730, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0476675033569336, "global_step": 488731, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0910091400146484, "global_step": 488732, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9610505104064941, "global_step": 488733, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0623300075531006, "global_step": 488734, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0203678607940674, "global_step": 488735, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.016416311264038, "global_step": 488736, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.076469898223877, "global_step": 488737, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0569262504577637, "global_step": 488738, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.039536476135254, "global_step": 488739, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0948896408081055, "global_step": 488740, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9564664363861084, "global_step": 488741, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0950844287872314, "global_step": 488742, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1228575706481934, "global_step": 488743, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9820009469985962, "global_step": 488744, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.063650608062744, "global_step": 488745, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9902571439743042, "global_step": 488746, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0635368824005127, "global_step": 488747, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0396790504455566, "global_step": 488748, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.134603261947632, "global_step": 488749, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1462419033050537, "global_step": 488750, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.058260202407837, "global_step": 488751, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0273807048797607, "global_step": 488752, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9876372814178467, "global_step": 488753, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0848238468170166, "global_step": 488754, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9802474975585938, "global_step": 488755, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9943774938583374, "global_step": 488756, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.011824131011963, "global_step": 488757, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.049532175064087, "global_step": 488758, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0824551582336426, "global_step": 488759, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.087430000305176, "global_step": 488760, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0646159648895264, "global_step": 488761, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0314438343048096, "global_step": 488762, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0762288570404053, "global_step": 488763, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0605013370513916, "global_step": 488764, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9786709547042847, "global_step": 488765, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.116457939147949, "global_step": 488766, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9767632484436035, "global_step": 488767, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0949230194091797, "global_step": 488768, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0583558082580566, "global_step": 488769, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9688910245895386, "global_step": 488770, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0796620845794678, "global_step": 488771, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1091651916503906, "global_step": 488772, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.092167615890503, "global_step": 488773, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.12990665435791, "global_step": 488774, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1177852153778076, "global_step": 488775, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.075335741043091, "global_step": 488776, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1104230880737305, "global_step": 488777, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.01994252204895, "global_step": 488778, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.097865581512451, "global_step": 488779, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0159192085266113, "global_step": 488780, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.032494068145752, "global_step": 488781, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9899166822433472, "global_step": 488782, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0744457244873047, "global_step": 488783, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.128096580505371, "global_step": 488784, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.093275308609009, "global_step": 488785, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.142608880996704, "global_step": 488786, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0537776947021484, "global_step": 488787, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.8994919061660767, "global_step": 488788, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.064008951187134, "global_step": 488789, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1188251972198486, "global_step": 488790, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1241185665130615, "global_step": 488791, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9954330921173096, "global_step": 488792, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0781307220458984, "global_step": 488793, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.109464168548584, "global_step": 488794, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0276546478271484, "global_step": 488795, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.033499240875244, "global_step": 488796, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.076606273651123, "global_step": 488797, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9914305210113525, "global_step": 488798, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.058218240737915, "global_step": 488799, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0605642795562744, "global_step": 488800, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0150623321533203, "global_step": 488801, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0122077465057373, "global_step": 488802, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.024536371231079, "global_step": 488803, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0056116580963135, "global_step": 488804, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.014008045196533, "global_step": 488805, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0626354217529297, "global_step": 488806, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.042930841445923, "global_step": 488807, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0895333290100098, "global_step": 488808, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9922617673873901, "global_step": 488809, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.170945882797241, "global_step": 488810, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0988128185272217, "global_step": 488811, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9842320680618286, "global_step": 488812, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0944929122924805, "global_step": 488813, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.107084274291992, "global_step": 488814, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.119861125946045, "global_step": 488815, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.044210910797119, "global_step": 488816, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0630435943603516, "global_step": 488817, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.072016716003418, "global_step": 488818, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9206598997116089, "global_step": 488819, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9853370189666748, "global_step": 488820, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.049405574798584, "global_step": 488821, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0626606941223145, "global_step": 488822, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.985898733139038, "global_step": 488823, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.000401496887207, "global_step": 488824, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0895402431488037, "global_step": 488825, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1599361896514893, "global_step": 488826, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1102795600891113, "global_step": 488827, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0672531127929688, "global_step": 488828, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0201995372772217, "global_step": 488829, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.042806625366211, "global_step": 488830, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.06764554977417, "global_step": 488831, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.074373483657837, "global_step": 488832, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0981342792510986, "global_step": 488833, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0901496410369873, "global_step": 488834, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.053696632385254, "global_step": 488835, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.050762891769409, "global_step": 488836, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1023895740509033, "global_step": 488837, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.022235870361328, "global_step": 488838, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0056445598602295, "global_step": 488839, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1409552097320557, "global_step": 488840, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0513641834259033, "global_step": 488841, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.224864959716797, "global_step": 488842, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.02081561088562, "global_step": 488843, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0078296661376953, "global_step": 488844, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0207061767578125, "global_step": 488845, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.043602705001831, "global_step": 488846, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.104069948196411, "global_step": 488847, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0815303325653076, "global_step": 488848, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0684022903442383, "global_step": 488849, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1166305541992188, "global_step": 488850, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0830495357513428, "global_step": 488851, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.039383888244629, "global_step": 488852, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0933218002319336, "global_step": 488853, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9871578216552734, "global_step": 488854, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.054399013519287, "global_step": 488855, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0443005561828613, "global_step": 488856, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9361664056777954, "global_step": 488857, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.096938371658325, "global_step": 488858, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.12789249420166, "global_step": 488859, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.06638240814209, "global_step": 488860, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0781564712524414, "global_step": 488861, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0878424644470215, "global_step": 488862, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0800654888153076, "global_step": 488863, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0266928672790527, "global_step": 488864, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.022674083709717, "global_step": 488865, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.054201364517212, "global_step": 488866, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.006107807159424, "global_step": 488867, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0643298625946045, "global_step": 488868, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.068528890609741, "global_step": 488869, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0663790702819824, "global_step": 488870, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.02083420753479, "global_step": 488871, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.024677276611328, "global_step": 488872, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1204617023468018, "global_step": 488873, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.004228353500366, "global_step": 488874, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.097801685333252, "global_step": 488875, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9806382656097412, "global_step": 488876, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0483405590057373, "global_step": 488877, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9551035165786743, "global_step": 488878, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.996087908744812, "global_step": 488879, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.936293125152588, "global_step": 488880, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0183818340301514, "global_step": 488881, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0188958644866943, "global_step": 488882, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0409774780273438, "global_step": 488883, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9868091344833374, "global_step": 488884, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.099252939224243, "global_step": 488885, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.020174503326416, "global_step": 488886, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9540536403656006, "global_step": 488887, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.032593250274658, "global_step": 488888, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.166689395904541, "global_step": 488889, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9824888706207275, "global_step": 488890, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0920464992523193, "global_step": 488891, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9997522830963135, "global_step": 488892, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1098201274871826, "global_step": 488893, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.974870204925537, "global_step": 488894, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.010282039642334, "global_step": 488895, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.135917901992798, "global_step": 488896, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9882831573486328, "global_step": 488897, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0135140419006348, "global_step": 488898, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0443594455718994, "global_step": 488899, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.064845561981201, "global_step": 488900, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.103834390640259, "global_step": 488901, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0641801357269287, "global_step": 488902, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.932873249053955, "global_step": 488903, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1022591590881348, "global_step": 488904, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.036851167678833, "global_step": 488905, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0508158206939697, "global_step": 488906, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.055446147918701, "global_step": 488907, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.072911024093628, "global_step": 488908, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0422534942626953, "global_step": 488909, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.023271083831787, "global_step": 488910, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.128572463989258, "global_step": 488911, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.064560651779175, "global_step": 488912, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0279414653778076, "global_step": 488913, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0628821849823, "global_step": 488914, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0423052310943604, "global_step": 488915, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.068667411804199, "global_step": 488916, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.091947078704834, "global_step": 488917, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.076143503189087, "global_step": 488918, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0382487773895264, "global_step": 488919, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.115222215652466, "global_step": 488920, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0086872577667236, "global_step": 488921, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.969723105430603, "global_step": 488922, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0980119705200195, "global_step": 488923, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.115328788757324, "global_step": 488924, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0661375522613525, "global_step": 488925, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0479447841644287, "global_step": 488926, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.11482834815979, "global_step": 488927, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.032346248626709, "global_step": 488928, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0786221027374268, "global_step": 488929, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.017307996749878, "global_step": 488930, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.156446933746338, "global_step": 488931, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.022426128387451, "global_step": 488932, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0721969604492188, "global_step": 488933, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9952540397644043, "global_step": 488934, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.981663703918457, "global_step": 488935, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.062467098236084, "global_step": 488936, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0199832916259766, "global_step": 488937, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0582990646362305, "global_step": 488938, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1380088329315186, "global_step": 488939, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.031524419784546, "global_step": 488940, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.093977451324463, "global_step": 488941, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.005478620529175, "global_step": 488942, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.089028835296631, "global_step": 488943, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0680325031280518, "global_step": 488944, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1345326900482178, "global_step": 488945, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1603689193725586, "global_step": 488946, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0247323513031006, "global_step": 488947, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9944099187850952, "global_step": 488948, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1177635192871094, "global_step": 488949, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.017686605453491, "global_step": 488950, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1300487518310547, "global_step": 488951, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1242012977600098, "global_step": 488952, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.084843397140503, "global_step": 488953, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.04063081741333, "global_step": 488954, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0489699840545654, "global_step": 488955, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0371148586273193, "global_step": 488956, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0233969688415527, "global_step": 488957, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.045682191848755, "global_step": 488958, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.104238271713257, "global_step": 488959, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0224876403808594, "global_step": 488960, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1266164779663086, "global_step": 488961, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.042020559310913, "global_step": 488962, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.019500732421875, "global_step": 488963, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.120847463607788, "global_step": 488964, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.075029134750366, "global_step": 488965, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.046581983566284, "global_step": 488966, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0346603393554688, "global_step": 488967, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.035404920578003, "global_step": 488968, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1616568565368652, "global_step": 488969, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.099748373031616, "global_step": 488970, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0350394248962402, "global_step": 488971, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.109346866607666, "global_step": 488972, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0868425369262695, "global_step": 488973, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.999019742012024, "global_step": 488974, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.099644660949707, "global_step": 488975, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.021088123321533, "global_step": 488976, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1172659397125244, "global_step": 488977, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0352184772491455, "global_step": 488978, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0448501110076904, "global_step": 488979, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.053894519805908, "global_step": 488980, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.073274850845337, "global_step": 488981, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0870730876922607, "global_step": 488982, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9728013277053833, "global_step": 488983, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1245083808898926, "global_step": 488984, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.028590202331543, "global_step": 488985, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0950284004211426, "global_step": 488986, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0898375511169434, "global_step": 488987, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0236332416534424, "global_step": 488988, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.122802734375, "global_step": 488989, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0450856685638428, "global_step": 488990, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.061868190765381, "global_step": 488991, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0324196815490723, "global_step": 488992, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0402965545654297, "global_step": 488993, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0507659912109375, "global_step": 488994, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9969475269317627, "global_step": 488995, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.02152156829834, "global_step": 488996, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0783910751342773, "global_step": 488997, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0578529834747314, "global_step": 488998, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0058679580688477, "global_step": 488999, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.028209686279297, "global_step": 489000, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1356801986694336, "global_step": 489001, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0003905296325684, "global_step": 489002, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0756449699401855, "global_step": 489003, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.02938175201416, "global_step": 489004, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.051239252090454, "global_step": 489005, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.068912982940674, "global_step": 489006, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.101041555404663, "global_step": 489007, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.056981325149536, "global_step": 489008, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1449317932128906, "global_step": 489009, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.065746784210205, "global_step": 489010, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.009075880050659, "global_step": 489011, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1325576305389404, "global_step": 489012, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9714577198028564, "global_step": 489013, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.141486167907715, "global_step": 489014, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0451197624206543, "global_step": 489015, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.073742151260376, "global_step": 489016, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.200039863586426, "global_step": 489017, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0682737827301025, "global_step": 489018, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0386667251586914, "global_step": 489019, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.146322250366211, "global_step": 489020, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0047824382781982, "global_step": 489021, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0498483180999756, "global_step": 489022, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9773449897766113, "global_step": 489023, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0305869579315186, "global_step": 489024, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.07645320892334, "global_step": 489025, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.013169527053833, "global_step": 489026, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.048633575439453, "global_step": 489027, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1494147777557373, "global_step": 489028, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1190037727355957, "global_step": 489029, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.066195011138916, "global_step": 489030, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1103498935699463, "global_step": 489031, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9696460962295532, "global_step": 489032, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.051988124847412, "global_step": 489033, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0347676277160645, "global_step": 489034, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9839301109313965, "global_step": 489035, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.065260410308838, "global_step": 489036, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0556893348693848, "global_step": 489037, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.039586067199707, "global_step": 489038, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.087681531906128, "global_step": 489039, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.052093267440796, "global_step": 489040, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1243200302124023, "global_step": 489041, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0003299713134766, "global_step": 489042, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.02817702293396, "global_step": 489043, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1414129734039307, "global_step": 489044, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9878566265106201, "global_step": 489045, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1003401279449463, "global_step": 489046, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.121931314468384, "global_step": 489047, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0486488342285156, "global_step": 489048, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1255249977111816, "global_step": 489049, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.092299461364746, "global_step": 489050, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.019984245300293, "global_step": 489051, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0613198280334473, "global_step": 489052, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.118436098098755, "global_step": 489053, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9913885593414307, "global_step": 489054, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0669476985931396, "global_step": 489055, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.073246717453003, "global_step": 489056, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0415351390838623, "global_step": 489057, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.072131395339966, "global_step": 489058, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1346607208251953, "global_step": 489059, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.991089940071106, "global_step": 489060, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.011904001235962, "global_step": 489061, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.067338705062866, "global_step": 489062, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.111886978149414, "global_step": 489063, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.020264148712158, "global_step": 489064, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0304675102233887, "global_step": 489065, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0276341438293457, "global_step": 489066, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9740452766418457, "global_step": 489067, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0956709384918213, "global_step": 489068, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.164311647415161, "global_step": 489069, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0892999172210693, "global_step": 489070, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.07609486579895, "global_step": 489071, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.040518045425415, "global_step": 489072, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.087509870529175, "global_step": 489073, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.052190065383911, "global_step": 489074, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0220842361450195, "global_step": 489075, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0456364154815674, "global_step": 489076, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9847921133041382, "global_step": 489077, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.106071710586548, "global_step": 489078, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.151658535003662, "global_step": 489079, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.099289655685425, "global_step": 489080, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1202030181884766, "global_step": 489081, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0303475856781006, "global_step": 489082, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.092245101928711, "global_step": 489083, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.096837282180786, "global_step": 489084, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0148873329162598, "global_step": 489085, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.066283702850342, "global_step": 489086, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.041721820831299, "global_step": 489087, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.075488805770874, "global_step": 489088, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0132625102996826, "global_step": 489089, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.056434154510498, "global_step": 489090, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0555548667907715, "global_step": 489091, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0348002910614014, "global_step": 489092, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0797951221466064, "global_step": 489093, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.075989007949829, "global_step": 489094, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0631659030914307, "global_step": 489095, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0299792289733887, "global_step": 489096, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.048654317855835, "global_step": 489097, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0317845344543457, "global_step": 489098, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0285143852233887, "global_step": 489099, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0716991424560547, "global_step": 489100, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9855586290359497, "global_step": 489101, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.072732925415039, "global_step": 489102, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.074911594390869, "global_step": 489103, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1261565685272217, "global_step": 489104, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0394599437713623, "global_step": 489105, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.137906074523926, "global_step": 489106, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9658639430999756, "global_step": 489107, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1183254718780518, "global_step": 489108, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1446242332458496, "global_step": 489109, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0335710048675537, "global_step": 489110, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.029823064804077, "global_step": 489111, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9929320812225342, "global_step": 489112, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.041343927383423, "global_step": 489113, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9579075574874878, "global_step": 489114, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0388095378875732, "global_step": 489115, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1817896366119385, "global_step": 489116, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0206570625305176, "global_step": 489117, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0792133808135986, "global_step": 489118, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.988793969154358, "global_step": 489119, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.983851671218872, "global_step": 489120, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0446836948394775, "global_step": 489121, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0236759185791016, "global_step": 489122, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0452821254730225, "global_step": 489123, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1727373600006104, "global_step": 489124, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0898280143737793, "global_step": 489125, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1269373893737793, "global_step": 489126, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1051766872406006, "global_step": 489127, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.019043445587158, "global_step": 489128, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0564351081848145, "global_step": 489129, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.087122917175293, "global_step": 489130, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.148559331893921, "global_step": 489131, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0208489894866943, "global_step": 489132, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0444416999816895, "global_step": 489133, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.12001895904541, "global_step": 489134, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.069178342819214, "global_step": 489135, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0473313331604004, "global_step": 489136, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.087146043777466, "global_step": 489137, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0317983627319336, "global_step": 489138, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.137146234512329, "global_step": 489139, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.009104013442993, "global_step": 489140, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.057819128036499, "global_step": 489141, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.072273015975952, "global_step": 489142, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.066486358642578, "global_step": 489143, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.101520538330078, "global_step": 489144, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0414528846740723, "global_step": 489145, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9880883693695068, "global_step": 489146, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0438761711120605, "global_step": 489147, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.075742244720459, "global_step": 489148, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.058837652206421, "global_step": 489149, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1127538681030273, "global_step": 489150, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.035090684890747, "global_step": 489151, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.089890480041504, "global_step": 489152, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1019864082336426, "global_step": 489153, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.054095506668091, "global_step": 489154, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.898901104927063, "global_step": 489155, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0726585388183594, "global_step": 489156, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9730287790298462, "global_step": 489157, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0680720806121826, "global_step": 489158, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0254833698272705, "global_step": 489159, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9715818166732788, "global_step": 489160, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.092449188232422, "global_step": 489161, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.019634485244751, "global_step": 489162, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.125215530395508, "global_step": 489163, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1148033142089844, "global_step": 489164, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.048349618911743, "global_step": 489165, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.072971820831299, "global_step": 489166, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.039997100830078, "global_step": 489167, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0041027069091797, "global_step": 489168, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0580880641937256, "global_step": 489169, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0778353214263916, "global_step": 489170, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1254520416259766, "global_step": 489171, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0653507709503174, "global_step": 489172, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.050044298171997, "global_step": 489173, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0500924587249756, "global_step": 489174, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1242449283599854, "global_step": 489175, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.047215461730957, "global_step": 489176, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.073692560195923, "global_step": 489177, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.12937068939209, "global_step": 489178, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1193020343780518, "global_step": 489179, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.071563243865967, "global_step": 489180, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.093254804611206, "global_step": 489181, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0272300243377686, "global_step": 489182, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.011542558670044, "global_step": 489183, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9821052551269531, "global_step": 489184, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9882029294967651, "global_step": 489185, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.010711431503296, "global_step": 489186, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9951574802398682, "global_step": 489187, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1645774841308594, "global_step": 489188, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.010962963104248, "global_step": 489189, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1154582500457764, "global_step": 489190, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.036015033721924, "global_step": 489191, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.993422269821167, "global_step": 489192, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0674800872802734, "global_step": 489193, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1509530544281006, "global_step": 489194, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1107101440429688, "global_step": 489195, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0697197914123535, "global_step": 489196, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0569393634796143, "global_step": 489197, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.153413772583008, "global_step": 489198, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.135651111602783, "global_step": 489199, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.060004472732544, "global_step": 489200, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.040771484375, "global_step": 489201, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0352559089660645, "global_step": 489202, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.060964345932007, "global_step": 489203, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.071768283843994, "global_step": 489204, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0655152797698975, "global_step": 489205, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.091494560241699, "global_step": 489206, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0386972427368164, "global_step": 489207, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.023087978363037, "global_step": 489208, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0542941093444824, "global_step": 489209, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.043067693710327, "global_step": 489210, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0279319286346436, "global_step": 489211, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9741144180297852, "global_step": 489212, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0125555992126465, "global_step": 489213, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0339601039886475, "global_step": 489214, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.038229465484619, "global_step": 489215, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.177942991256714, "global_step": 489216, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.065518379211426, "global_step": 489217, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.133852958679199, "global_step": 489218, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9464606046676636, "global_step": 489219, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.070486307144165, "global_step": 489220, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.056948661804199, "global_step": 489221, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.046076774597168, "global_step": 489222, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0778286457061768, "global_step": 489223, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0639052391052246, "global_step": 489224, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.08463716506958, "global_step": 489225, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9861247539520264, "global_step": 489226, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0338568687438965, "global_step": 489227, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0982115268707275, "global_step": 489228, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9818971157073975, "global_step": 489229, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.066267728805542, "global_step": 489230, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0417733192443848, "global_step": 489231, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.02964448928833, "global_step": 489232, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0599613189697266, "global_step": 489233, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0909454822540283, "global_step": 489234, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9955768585205078, "global_step": 489235, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.079627513885498, "global_step": 489236, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.969743013381958, "global_step": 489237, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0034339427948, "global_step": 489238, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0018444061279297, "global_step": 489239, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0293946266174316, "global_step": 489240, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.112550973892212, "global_step": 489241, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.014650344848633, "global_step": 489242, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1170265674591064, "global_step": 489243, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.06724214553833, "global_step": 489244, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.097303628921509, "global_step": 489245, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.032942295074463, "global_step": 489246, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.116230010986328, "global_step": 489247, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.037538528442383, "global_step": 489248, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0383238792419434, "global_step": 489249, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1515092849731445, "global_step": 489250, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0197291374206543, "global_step": 489251, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.083897590637207, "global_step": 489252, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.071833610534668, "global_step": 489253, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9854215383529663, "global_step": 489254, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0202555656433105, "global_step": 489255, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.053095579147339, "global_step": 489256, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0465099811553955, "global_step": 489257, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.053887367248535, "global_step": 489258, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.082793951034546, "global_step": 489259, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0063695907592773, "global_step": 489260, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9902764558792114, "global_step": 489261, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1406373977661133, "global_step": 489262, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.056720495223999, "global_step": 489263, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0289409160614014, "global_step": 489264, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0253825187683105, "global_step": 489265, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0423312187194824, "global_step": 489266, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0044822692871094, "global_step": 489267, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0170257091522217, "global_step": 489268, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0199007987976074, "global_step": 489269, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.124889850616455, "global_step": 489270, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.058178663253784, "global_step": 489271, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0456807613372803, "global_step": 489272, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0408763885498047, "global_step": 489273, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9822946786880493, "global_step": 489274, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.070672035217285, "global_step": 489275, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0631046295166016, "global_step": 489276, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1349759101867676, "global_step": 489277, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0750722885131836, "global_step": 489278, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.035318613052368, "global_step": 489279, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1089489459991455, "global_step": 489280, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.035728931427002, "global_step": 489281, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0671088695526123, "global_step": 489282, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.076751947402954, "global_step": 489283, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.085113525390625, "global_step": 489284, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.998424768447876, "global_step": 489285, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.134091377258301, "global_step": 489286, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.124432325363159, "global_step": 489287, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.092743396759033, "global_step": 489288, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1614928245544434, "global_step": 489289, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1078526973724365, "global_step": 489290, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0583560466766357, "global_step": 489291, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0574889183044434, "global_step": 489292, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.103348970413208, "global_step": 489293, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9506057500839233, "global_step": 489294, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0789599418640137, "global_step": 489295, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.136695623397827, "global_step": 489296, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.055593729019165, "global_step": 489297, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0587754249572754, "global_step": 489298, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1340584754943848, "global_step": 489299, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0081045627593994, "global_step": 489300, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9542495012283325, "global_step": 489301, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0251028537750244, "global_step": 489302, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.063152313232422, "global_step": 489303, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1076889038085938, "global_step": 489304, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.013331651687622, "global_step": 489305, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0179355144500732, "global_step": 489306, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9594752788543701, "global_step": 489307, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0023813247680664, "global_step": 489308, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0602638721466064, "global_step": 489309, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.039466381072998, "global_step": 489310, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.024092674255371, "global_step": 489311, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0410327911376953, "global_step": 489312, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0588579177856445, "global_step": 489313, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0449085235595703, "global_step": 489314, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.024275064468384, "global_step": 489315, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.08160400390625, "global_step": 489316, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0668532848358154, "global_step": 489317, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.101578950881958, "global_step": 489318, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0115034580230713, "global_step": 489319, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0430517196655273, "global_step": 489320, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0385196208953857, "global_step": 489321, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.03106427192688, "global_step": 489322, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1421279907226562, "global_step": 489323, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0796103477478027, "global_step": 489324, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1224513053894043, "global_step": 489325, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.122077465057373, "global_step": 489326, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0521130561828613, "global_step": 489327, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0183372497558594, "global_step": 489328, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0451607704162598, "global_step": 489329, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0329079627990723, "global_step": 489330, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0521936416625977, "global_step": 489331, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0489444732666016, "global_step": 489332, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9956327676773071, "global_step": 489333, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1105000972747803, "global_step": 489334, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.033963918685913, "global_step": 489335, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0637757778167725, "global_step": 489336, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0498151779174805, "global_step": 489337, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.02414870262146, "global_step": 489338, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.080570697784424, "global_step": 489339, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0346198081970215, "global_step": 489340, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.020899534225464, "global_step": 489341, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1508562564849854, "global_step": 489342, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1346375942230225, "global_step": 489343, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0050904750823975, "global_step": 489344, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.133213758468628, "global_step": 489345, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0775744915008545, "global_step": 489346, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9666019678115845, "global_step": 489347, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0565073490142822, "global_step": 489348, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.031888246536255, "global_step": 489349, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.05843448638916, "global_step": 489350, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.047312021255493, "global_step": 489351, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0234310626983643, "global_step": 489352, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1218135356903076, "global_step": 489353, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.086686372756958, "global_step": 489354, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0048649311065674, "global_step": 489355, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.014953374862671, "global_step": 489356, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9778423309326172, "global_step": 489357, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0542502403259277, "global_step": 489358, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0733423233032227, "global_step": 489359, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1389060020446777, "global_step": 489360, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.02314829826355, "global_step": 489361, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1128432750701904, "global_step": 489362, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0974743366241455, "global_step": 489363, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9282463788986206, "global_step": 489364, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.102074146270752, "global_step": 489365, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.015336751937866, "global_step": 489366, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0173420906066895, "global_step": 489367, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0882768630981445, "global_step": 489368, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.093651056289673, "global_step": 489369, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.042949676513672, "global_step": 489370, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0663058757781982, "global_step": 489371, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1905112266540527, "global_step": 489372, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9938887357711792, "global_step": 489373, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0465128421783447, "global_step": 489374, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.064504623413086, "global_step": 489375, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0271036624908447, "global_step": 489376, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.073007345199585, "global_step": 489377, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1305952072143555, "global_step": 489378, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1241140365600586, "global_step": 489379, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0039806365966797, "global_step": 489380, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.108717441558838, "global_step": 489381, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1026270389556885, "global_step": 489382, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0270488262176514, "global_step": 489383, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.127516508102417, "global_step": 489384, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0739083290100098, "global_step": 489385, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0478737354278564, "global_step": 489386, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0060906410217285, "global_step": 489387, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0409064292907715, "global_step": 489388, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1476831436157227, "global_step": 489389, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0563814640045166, "global_step": 489390, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0584986209869385, "global_step": 489391, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0362343788146973, "global_step": 489392, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.030797004699707, "global_step": 489393, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.095872163772583, "global_step": 489394, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1435000896453857, "global_step": 489395, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.963852882385254, "global_step": 489396, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1180684566497803, "global_step": 489397, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1378462314605713, "global_step": 489398, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9868841171264648, "global_step": 489399, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0579135417938232, "global_step": 489400, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1134917736053467, "global_step": 489401, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0920825004577637, "global_step": 489402, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9842469692230225, "global_step": 489403, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0781328678131104, "global_step": 489404, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0572094917297363, "global_step": 489405, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.054941415786743, "global_step": 489406, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0676348209381104, "global_step": 489407, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1108129024505615, "global_step": 489408, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.100897789001465, "global_step": 489409, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1289703845977783, "global_step": 489410, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0124058723449707, "global_step": 489411, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.072129726409912, "global_step": 489412, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1326873302459717, "global_step": 489413, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0690877437591553, "global_step": 489414, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0606689453125, "global_step": 489415, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.074047088623047, "global_step": 489416, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.083461046218872, "global_step": 489417, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.060467481613159, "global_step": 489418, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0792787075042725, "global_step": 489419, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1149275302886963, "global_step": 489420, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0477294921875, "global_step": 489421, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1309099197387695, "global_step": 489422, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1948328018188477, "global_step": 489423, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0093626976013184, "global_step": 489424, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.040426015853882, "global_step": 489425, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0757181644439697, "global_step": 489426, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.026329517364502, "global_step": 489427, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.114530563354492, "global_step": 489428, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0750503540039062, "global_step": 489429, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.12142014503479, "global_step": 489430, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0528311729431152, "global_step": 489431, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0723512172698975, "global_step": 489432, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.059086322784424, "global_step": 489433, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.149034261703491, "global_step": 489434, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0385146141052246, "global_step": 489435, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9852089881896973, "global_step": 489436, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.051060438156128, "global_step": 489437, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.050344467163086, "global_step": 489438, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0656986236572266, "global_step": 489439, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0819432735443115, "global_step": 489440, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.072179079055786, "global_step": 489441, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1358275413513184, "global_step": 489442, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0990114212036133, "global_step": 489443, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.13533353805542, "global_step": 489444, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9870725870132446, "global_step": 489445, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.067863941192627, "global_step": 489446, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0975289344787598, "global_step": 489447, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1165482997894287, "global_step": 489448, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.014761209487915, "global_step": 489449, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0608179569244385, "global_step": 489450, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1068618297576904, "global_step": 489451, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.994274616241455, "global_step": 489452, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9428385496139526, "global_step": 489453, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0375683307647705, "global_step": 489454, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0775344371795654, "global_step": 489455, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1575074195861816, "global_step": 489456, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.076477527618408, "global_step": 489457, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0206594467163086, "global_step": 489458, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0814292430877686, "global_step": 489459, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.029472589492798, "global_step": 489460, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0899667739868164, "global_step": 489461, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0425610542297363, "global_step": 489462, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.027294397354126, "global_step": 489463, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0029003620147705, "global_step": 489464, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.075578451156616, "global_step": 489465, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.033623695373535, "global_step": 489466, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1152303218841553, "global_step": 489467, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.9835026264190674, "global_step": 489468, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0730724334716797, "global_step": 489469, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1830155849456787, "global_step": 489470, "epoch": 854, "lr": 5e-05}
{"train_loss": 1.977306842803955, "global_step": 489471, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1161954402923584, "global_step": 489472, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0307600498199463, "global_step": 489473, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0493826866149902, "global_step": 489474, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.06620454788208, "global_step": 489475, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.1028945446014404, "global_step": 489476, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.056896686553955, "global_step": 489477, "epoch": 854, "lr": 5e-05}
{"train_loss": 2.0105409622192383, "global_step": 489478, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0262393951416016, "global_step": 489479, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0726089477539062, "global_step": 489480, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1477150917053223, "global_step": 489481, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9682507514953613, "global_step": 489482, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0880560874938965, "global_step": 489483, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.058678388595581, "global_step": 489484, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9856404066085815, "global_step": 489485, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1177978515625, "global_step": 489486, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.029083490371704, "global_step": 489487, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.114908218383789, "global_step": 489488, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0973060131073, "global_step": 489489, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.116222858428955, "global_step": 489490, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.040254831314087, "global_step": 489491, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9985432624816895, "global_step": 489492, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.078059673309326, "global_step": 489493, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.030944585800171, "global_step": 489494, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.13147234916687, "global_step": 489495, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0429282188415527, "global_step": 489496, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0853347778320312, "global_step": 489497, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.058424949645996, "global_step": 489498, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.975457787513733, "global_step": 489499, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.018984794616699, "global_step": 489500, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0557148456573486, "global_step": 489501, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1110663414001465, "global_step": 489502, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.062375068664551, "global_step": 489503, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0806291103363037, "global_step": 489504, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.962714672088623, "global_step": 489505, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0419249534606934, "global_step": 489506, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9999176263809204, "global_step": 489507, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0168416500091553, "global_step": 489508, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0146689414978027, "global_step": 489509, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0694940090179443, "global_step": 489510, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9988113641738892, "global_step": 489511, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1352157592773438, "global_step": 489512, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.082406759262085, "global_step": 489513, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.034806728363037, "global_step": 489514, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0900661945343018, "global_step": 489515, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9874553680419922, "global_step": 489516, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9830141067504883, "global_step": 489517, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0688469409942627, "global_step": 489518, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1008660793304443, "global_step": 489519, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0742645263671875, "global_step": 489520, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.96426260471344, "global_step": 489521, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9771971702575684, "global_step": 489522, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0356454849243164, "global_step": 489523, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.071497917175293, "global_step": 489524, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0444579124450684, "global_step": 489525, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0184831619262695, "global_step": 489526, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.106400489807129, "global_step": 489527, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.015625238418579, "global_step": 489528, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0800747871398926, "global_step": 489529, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0854835510253906, "global_step": 489530, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.017080783843994, "global_step": 489531, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1012797355651855, "global_step": 489532, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9934524297714233, "global_step": 489533, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0446619987487793, "global_step": 489534, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0940451622009277, "global_step": 489535, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.015568971633911, "global_step": 489536, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1002821922302246, "global_step": 489537, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.134403944015503, "global_step": 489538, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1029388904571533, "global_step": 489539, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9757858514785767, "global_step": 489540, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.022200107574463, "global_step": 489541, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.045607566833496, "global_step": 489542, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.074004650115967, "global_step": 489543, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9064180850982666, "global_step": 489544, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0058319568634033, "global_step": 489545, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9550585746765137, "global_step": 489546, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9847817420959473, "global_step": 489547, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0496652126312256, "global_step": 489548, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.078728437423706, "global_step": 489549, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1315274238586426, "global_step": 489550, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1166017055511475, "global_step": 489551, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0865912437438965, "global_step": 489552, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1606967449188232, "global_step": 489553, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9789358377456665, "global_step": 489554, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0025064945220947, "global_step": 489555, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.065004825592041, "global_step": 489556, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0895354747772217, "global_step": 489557, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1174261569976807, "global_step": 489558, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9598091840744019, "global_step": 489559, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0725231170654297, "global_step": 489560, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.135707139968872, "global_step": 489561, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1803641319274902, "global_step": 489562, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0239715576171875, "global_step": 489563, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0032451152801514, "global_step": 489564, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1042728424072266, "global_step": 489565, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.959614634513855, "global_step": 489566, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9884014129638672, "global_step": 489567, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9342436790466309, "global_step": 489568, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.052891731262207, "global_step": 489569, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.057929039001465, "global_step": 489570, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.073767900466919, "global_step": 489571, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.123926877975464, "global_step": 489572, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1000514030456543, "global_step": 489573, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.044548988342285, "global_step": 489574, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0642309188842773, "global_step": 489575, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0402746200561523, "global_step": 489576, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0061235427856445, "global_step": 489577, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.13508677482605, "global_step": 489578, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.022637128829956, "global_step": 489579, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.06112003326416, "global_step": 489580, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.061894416809082, "global_step": 489581, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.01235294342041, "global_step": 489582, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0835533142089844, "global_step": 489583, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0257065296173096, "global_step": 489584, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0702507495880127, "global_step": 489585, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1124017238616943, "global_step": 489586, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.080409049987793, "global_step": 489587, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.087921619415283, "global_step": 489588, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9829844236373901, "global_step": 489589, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9704819917678833, "global_step": 489590, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0537259578704834, "global_step": 489591, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.034158229827881, "global_step": 489592, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.983420968055725, "global_step": 489593, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0893006324768066, "global_step": 489594, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0988523960113525, "global_step": 489595, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9970446825027466, "global_step": 489596, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.082472801208496, "global_step": 489597, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0316872596740723, "global_step": 489598, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0900254249572754, "global_step": 489599, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.059373378753662, "global_step": 489600, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0530996322631836, "global_step": 489601, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0823190212249756, "global_step": 489602, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0576579570770264, "global_step": 489603, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0111207962036133, "global_step": 489604, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0932323932647705, "global_step": 489605, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9662755727767944, "global_step": 489606, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1346919536590576, "global_step": 489607, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0295088291168213, "global_step": 489608, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0566890239715576, "global_step": 489609, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.045851230621338, "global_step": 489610, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.067706346511841, "global_step": 489611, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0351531505584717, "global_step": 489612, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1067070960998535, "global_step": 489613, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.069995403289795, "global_step": 489614, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.057037830352783, "global_step": 489615, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1056723594665527, "global_step": 489616, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.991917610168457, "global_step": 489617, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.092921733856201, "global_step": 489618, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9850338697433472, "global_step": 489619, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9703198671340942, "global_step": 489620, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.089629888534546, "global_step": 489621, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0049071311950684, "global_step": 489622, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.103684186935425, "global_step": 489623, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.056966781616211, "global_step": 489624, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.02595591545105, "global_step": 489625, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.103724479675293, "global_step": 489626, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.037040948867798, "global_step": 489627, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.081165075302124, "global_step": 489628, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9994174242019653, "global_step": 489629, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0867373943328857, "global_step": 489630, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9916409254074097, "global_step": 489631, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0602316856384277, "global_step": 489632, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.101452112197876, "global_step": 489633, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0107414722442627, "global_step": 489634, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0957062244415283, "global_step": 489635, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.049511432647705, "global_step": 489636, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9405794143676758, "global_step": 489637, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1338798999786377, "global_step": 489638, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1429855823516846, "global_step": 489639, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0431535243988037, "global_step": 489640, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0360958576202393, "global_step": 489641, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0985686779022217, "global_step": 489642, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0262014865875244, "global_step": 489643, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.155578851699829, "global_step": 489644, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.068965196609497, "global_step": 489645, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.093261480331421, "global_step": 489646, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.035742998123169, "global_step": 489647, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0782995223999023, "global_step": 489648, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0966856479644775, "global_step": 489649, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.074774742126465, "global_step": 489650, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.073469400405884, "global_step": 489651, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.137026786804199, "global_step": 489652, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.096980094909668, "global_step": 489653, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0206995010375977, "global_step": 489654, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1186635494232178, "global_step": 489655, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1269853115081787, "global_step": 489656, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0721657276153564, "global_step": 489657, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.001380681991577, "global_step": 489658, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.118859052658081, "global_step": 489659, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0378646850585938, "global_step": 489660, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0580251216888428, "global_step": 489661, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.082122802734375, "global_step": 489662, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1234161853790283, "global_step": 489663, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1566126346588135, "global_step": 489664, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0931167602539062, "global_step": 489665, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.056792736053467, "global_step": 489666, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0994672775268555, "global_step": 489667, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9960861206054688, "global_step": 489668, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0534708499908447, "global_step": 489669, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.029006004333496, "global_step": 489670, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0605862140655518, "global_step": 489671, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.961437702178955, "global_step": 489672, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1231346130371094, "global_step": 489673, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0210697650909424, "global_step": 489674, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1296679973602295, "global_step": 489675, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0249085426330566, "global_step": 489676, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0526199340820312, "global_step": 489677, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1948795318603516, "global_step": 489678, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.098029136657715, "global_step": 489679, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.131408929824829, "global_step": 489680, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0415854454040527, "global_step": 489681, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0222346782684326, "global_step": 489682, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.068565845489502, "global_step": 489683, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0446200370788574, "global_step": 489684, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0057530403137207, "global_step": 489685, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0388474464416504, "global_step": 489686, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0424888134002686, "global_step": 489687, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.065524101257324, "global_step": 489688, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9991686344146729, "global_step": 489689, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1957626342773438, "global_step": 489690, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.120647430419922, "global_step": 489691, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0797221660614014, "global_step": 489692, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.030892848968506, "global_step": 489693, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.041867733001709, "global_step": 489694, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.04712176322937, "global_step": 489695, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0485424995422363, "global_step": 489696, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0765674114227295, "global_step": 489697, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0630033016204834, "global_step": 489698, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.05131196975708, "global_step": 489699, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.096144199371338, "global_step": 489700, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.009711742401123, "global_step": 489701, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0706417560577393, "global_step": 489702, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1410088539123535, "global_step": 489703, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0028910636901855, "global_step": 489704, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0158987045288086, "global_step": 489705, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0478930473327637, "global_step": 489706, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9807907342910767, "global_step": 489707, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0547096729278564, "global_step": 489708, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.108891487121582, "global_step": 489709, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.042168617248535, "global_step": 489710, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0881824493408203, "global_step": 489711, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.04233980178833, "global_step": 489712, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0672333240509033, "global_step": 489713, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0586745738983154, "global_step": 489714, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0811750888824463, "global_step": 489715, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1134307384490967, "global_step": 489716, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.111135482788086, "global_step": 489717, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.013730764389038, "global_step": 489718, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.019592523574829, "global_step": 489719, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.035026788711548, "global_step": 489720, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.061864137649536, "global_step": 489721, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9616832733154297, "global_step": 489722, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0723934173583984, "global_step": 489723, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.120789051055908, "global_step": 489724, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.043931484222412, "global_step": 489725, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0640456676483154, "global_step": 489726, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0540578365325928, "global_step": 489727, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.121593713760376, "global_step": 489728, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.129577159881592, "global_step": 489729, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0464069843292236, "global_step": 489730, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1249499320983887, "global_step": 489731, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0558359622955322, "global_step": 489732, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0665979385375977, "global_step": 489733, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1010937690734863, "global_step": 489734, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.057439088821411, "global_step": 489735, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1012954711914062, "global_step": 489736, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0371105670928955, "global_step": 489737, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1317391395568848, "global_step": 489738, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0783050060272217, "global_step": 489739, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0392279624938965, "global_step": 489740, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.990573525428772, "global_step": 489741, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.076638698577881, "global_step": 489742, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0876200199127197, "global_step": 489743, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1228597164154053, "global_step": 489744, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0960779190063477, "global_step": 489745, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0608174800872803, "global_step": 489746, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.080512523651123, "global_step": 489747, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.992386817932129, "global_step": 489748, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.066434860229492, "global_step": 489749, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0296525955200195, "global_step": 489750, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.031754493713379, "global_step": 489751, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0402321815490723, "global_step": 489752, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0451719760894775, "global_step": 489753, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0114293098449707, "global_step": 489754, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.04453444480896, "global_step": 489755, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.074681043624878, "global_step": 489756, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.029204845428467, "global_step": 489757, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.077010154724121, "global_step": 489758, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0072877407073975, "global_step": 489759, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.019979476928711, "global_step": 489760, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9986075162887573, "global_step": 489761, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.147153854370117, "global_step": 489762, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0565147399902344, "global_step": 489763, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.044308662414551, "global_step": 489764, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9639354944229126, "global_step": 489765, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.117784023284912, "global_step": 489766, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0515565872192383, "global_step": 489767, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0566444396972656, "global_step": 489768, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.090343713760376, "global_step": 489769, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0142204761505127, "global_step": 489770, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0144245624542236, "global_step": 489771, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.048381805419922, "global_step": 489772, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.089613914489746, "global_step": 489773, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0934736728668213, "global_step": 489774, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.101430892944336, "global_step": 489775, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.159233331680298, "global_step": 489776, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1012516021728516, "global_step": 489777, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9682366847991943, "global_step": 489778, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.123741865158081, "global_step": 489779, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0418996810913086, "global_step": 489780, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.029340982437134, "global_step": 489781, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0856683254241943, "global_step": 489782, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1361236572265625, "global_step": 489783, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1001698970794678, "global_step": 489784, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0817043781280518, "global_step": 489785, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.055300235748291, "global_step": 489786, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.127838134765625, "global_step": 489787, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.141331672668457, "global_step": 489788, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.06408429145813, "global_step": 489789, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.022167921066284, "global_step": 489790, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.011610984802246, "global_step": 489791, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9941673278808594, "global_step": 489792, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9632389545440674, "global_step": 489793, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0533251762390137, "global_step": 489794, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0831639766693115, "global_step": 489795, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0053956508636475, "global_step": 489796, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0089375972747803, "global_step": 489797, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.05077862739563, "global_step": 489798, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.033184289932251, "global_step": 489799, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0346109867095947, "global_step": 489800, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9631175994873047, "global_step": 489801, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9908767938613892, "global_step": 489802, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0533735752105713, "global_step": 489803, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9802300930023193, "global_step": 489804, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0745644569396973, "global_step": 489805, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.000473976135254, "global_step": 489806, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0588488578796387, "global_step": 489807, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.041090250015259, "global_step": 489808, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.09456205368042, "global_step": 489809, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9860557317733765, "global_step": 489810, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0720911026000977, "global_step": 489811, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0139012336730957, "global_step": 489812, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.060842990875244, "global_step": 489813, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.043837547302246, "global_step": 489814, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0795793533325195, "global_step": 489815, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.054431200027466, "global_step": 489816, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.113642692565918, "global_step": 489817, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.033047914505005, "global_step": 489818, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9798375368118286, "global_step": 489819, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0835437774658203, "global_step": 489820, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.023430824279785, "global_step": 489821, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.113518476486206, "global_step": 489822, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0015132427215576, "global_step": 489823, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.016456365585327, "global_step": 489824, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.081495761871338, "global_step": 489825, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1385653018951416, "global_step": 489826, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1023786067962646, "global_step": 489827, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0747785568237305, "global_step": 489828, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0379059314727783, "global_step": 489829, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9844696521759033, "global_step": 489830, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0723769664764404, "global_step": 489831, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0172293186187744, "global_step": 489832, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.022162675857544, "global_step": 489833, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.00626277923584, "global_step": 489834, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9652003049850464, "global_step": 489835, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9809376001358032, "global_step": 489836, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1664342880249023, "global_step": 489837, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.066542863845825, "global_step": 489838, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.004915475845337, "global_step": 489839, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0814080238342285, "global_step": 489840, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0888419151306152, "global_step": 489841, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.092254877090454, "global_step": 489842, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9853949546813965, "global_step": 489843, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0514919757843018, "global_step": 489844, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.047665596008301, "global_step": 489845, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.059102773666382, "global_step": 489846, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.03503155708313, "global_step": 489847, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0674045085906982, "global_step": 489848, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.094338893890381, "global_step": 489849, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9677448272705078, "global_step": 489850, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9576857089996338, "global_step": 489851, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0394811630249023, "global_step": 489852, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0227723121643066, "global_step": 489853, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0573785305023193, "global_step": 489854, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1131045818328857, "global_step": 489855, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0664186477661133, "global_step": 489856, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.111236333847046, "global_step": 489857, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.072253465652466, "global_step": 489858, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.056180238723755, "global_step": 489859, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.060123920440674, "global_step": 489860, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9954423904418945, "global_step": 489861, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9470027685165405, "global_step": 489862, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0063135623931885, "global_step": 489863, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1006717681884766, "global_step": 489864, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.050126075744629, "global_step": 489865, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.003999710083008, "global_step": 489866, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.04545521736145, "global_step": 489867, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1696596145629883, "global_step": 489868, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.153681516647339, "global_step": 489869, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0621337890625, "global_step": 489870, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0985348224639893, "global_step": 489871, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.109330654144287, "global_step": 489872, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0827178955078125, "global_step": 489873, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.128770351409912, "global_step": 489874, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0051708221435547, "global_step": 489875, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0328617095947266, "global_step": 489876, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9936180114746094, "global_step": 489877, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1252236366271973, "global_step": 489878, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.040717363357544, "global_step": 489879, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.087386131286621, "global_step": 489880, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.022005796432495, "global_step": 489881, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.088068723678589, "global_step": 489882, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9972026348114014, "global_step": 489883, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.05696964263916, "global_step": 489884, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.053947687149048, "global_step": 489885, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1299638748168945, "global_step": 489886, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.050037384033203, "global_step": 489887, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9616312980651855, "global_step": 489888, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0576889514923096, "global_step": 489889, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0891542434692383, "global_step": 489890, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.033088445663452, "global_step": 489891, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1358494758605957, "global_step": 489892, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0897226333618164, "global_step": 489893, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0640740394592285, "global_step": 489894, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.970941424369812, "global_step": 489895, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9922006130218506, "global_step": 489896, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0066463947296143, "global_step": 489897, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0786306858062744, "global_step": 489898, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.088920831680298, "global_step": 489899, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0403780937194824, "global_step": 489900, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0331480503082275, "global_step": 489901, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.068333625793457, "global_step": 489902, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.041522741317749, "global_step": 489903, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9746991395950317, "global_step": 489904, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.081684112548828, "global_step": 489905, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0433106422424316, "global_step": 489906, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0829646587371826, "global_step": 489907, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.041780948638916, "global_step": 489908, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1238999366760254, "global_step": 489909, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1251885890960693, "global_step": 489910, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0371885299682617, "global_step": 489911, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0417516231536865, "global_step": 489912, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.067214250564575, "global_step": 489913, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.988521695137024, "global_step": 489914, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9419752359390259, "global_step": 489915, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.109257221221924, "global_step": 489916, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.10046124458313, "global_step": 489917, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0239250659942627, "global_step": 489918, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0639584064483643, "global_step": 489919, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.967663049697876, "global_step": 489920, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0611348152160645, "global_step": 489921, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1150310039520264, "global_step": 489922, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0535478591918945, "global_step": 489923, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9756851196289062, "global_step": 489924, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.115659475326538, "global_step": 489925, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.064789295196533, "global_step": 489926, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.074702739715576, "global_step": 489927, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.068117380142212, "global_step": 489928, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.124485969543457, "global_step": 489929, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.061373233795166, "global_step": 489930, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.010721206665039, "global_step": 489931, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0427417755126953, "global_step": 489932, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9979647397994995, "global_step": 489933, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.044539213180542, "global_step": 489934, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.022308826446533, "global_step": 489935, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9797338247299194, "global_step": 489936, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0775699615478516, "global_step": 489937, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.012134552001953, "global_step": 489938, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0674057006835938, "global_step": 489939, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0571041107177734, "global_step": 489940, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1254143714904785, "global_step": 489941, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0516793727874756, "global_step": 489942, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.094749927520752, "global_step": 489943, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9763517379760742, "global_step": 489944, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9866451025009155, "global_step": 489945, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0839004516601562, "global_step": 489946, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.074671983718872, "global_step": 489947, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.055168628692627, "global_step": 489948, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1224420070648193, "global_step": 489949, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9835501909255981, "global_step": 489950, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.092998504638672, "global_step": 489951, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1251626014709473, "global_step": 489952, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1163034439086914, "global_step": 489953, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0025124549865723, "global_step": 489954, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.124201774597168, "global_step": 489955, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0314998626708984, "global_step": 489956, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0275187492370605, "global_step": 489957, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0768656730651855, "global_step": 489958, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0534238815307617, "global_step": 489959, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0259554386138916, "global_step": 489960, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.061851739883423, "global_step": 489961, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0183517932891846, "global_step": 489962, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0565335750579834, "global_step": 489963, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0625884532928467, "global_step": 489964, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0831193923950195, "global_step": 489965, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9777402877807617, "global_step": 489966, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.085238456726074, "global_step": 489967, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0540783405303955, "global_step": 489968, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1013975143432617, "global_step": 489969, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0501513481140137, "global_step": 489970, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0697238445281982, "global_step": 489971, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1072754859924316, "global_step": 489972, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.062784433364868, "global_step": 489973, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9773142337799072, "global_step": 489974, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1181039810180664, "global_step": 489975, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0477957725524902, "global_step": 489976, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0536649227142334, "global_step": 489977, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.067204236984253, "global_step": 489978, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.004995822906494, "global_step": 489979, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0483744144439697, "global_step": 489980, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0277531147003174, "global_step": 489981, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.014524221420288, "global_step": 489982, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1113295555114746, "global_step": 489983, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1046714782714844, "global_step": 489984, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0510003566741943, "global_step": 489985, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1107981204986572, "global_step": 489986, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.132516384124756, "global_step": 489987, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.052433967590332, "global_step": 489988, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.06036114692688, "global_step": 489989, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0761890411376953, "global_step": 489990, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.031391143798828, "global_step": 489991, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.082705020904541, "global_step": 489992, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.126103162765503, "global_step": 489993, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.06583833694458, "global_step": 489994, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.064056396484375, "global_step": 489995, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.07137393951416, "global_step": 489996, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0791075229644775, "global_step": 489997, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.081780195236206, "global_step": 489998, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.062805414199829, "global_step": 489999, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.030733108520508, "global_step": 490000, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9371088743209839, "global_step": 490001, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0350093841552734, "global_step": 490002, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1399993896484375, "global_step": 490003, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.024625539779663, "global_step": 490004, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.016417980194092, "global_step": 490005, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0341975688934326, "global_step": 490006, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9849909543991089, "global_step": 490007, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.063511371612549, "global_step": 490008, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.051804542541504, "global_step": 490009, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.045989513397217, "global_step": 490010, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0069873332977295, "global_step": 490011, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0913643836975098, "global_step": 490012, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0665619373321533, "global_step": 490013, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0566561222076416, "global_step": 490014, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1500301361083984, "global_step": 490015, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9719923734664917, "global_step": 490016, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0556232929229736, "global_step": 490017, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.062418222427368, "global_step": 490018, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.146711587905884, "global_step": 490019, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.019514799118042, "global_step": 490020, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.095136880874634, "global_step": 490021, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0153326988220215, "global_step": 490022, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9971916675567627, "global_step": 490023, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0404605865478516, "global_step": 490024, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0153932571411133, "global_step": 490025, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.105088949203491, "global_step": 490026, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.069279193878174, "global_step": 490027, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.12601900100708, "global_step": 490028, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9894942045211792, "global_step": 490029, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.06972599029541, "global_step": 490030, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.052306652069092, "global_step": 490031, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0400617122650146, "global_step": 490032, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.990771770477295, "global_step": 490033, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0419979095458984, "global_step": 490034, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0878829956054688, "global_step": 490035, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.012361764907837, "global_step": 490036, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.145427942276001, "global_step": 490037, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0473110675811768, "global_step": 490038, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.039233684539795, "global_step": 490039, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.088521957397461, "global_step": 490040, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9612741470336914, "global_step": 490041, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.043421745300293, "global_step": 490042, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.061060905456543, "global_step": 490043, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.986009120941162, "global_step": 490044, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0601913928985596, "global_step": 490045, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.027315855026245, "global_step": 490046, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0191805362701416, "global_step": 490047, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.095903158187866, "global_step": 490048, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0514590740203857, "global_step": 490049, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.053285837173462, "global_step": 490050, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1156442165374756, "global_step": 490051, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0262045860290527, "global_step": 490052, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0631117820739746, "global_step": 490053, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.098804473876953, "global_step": 490054, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.030665636062622, "global_step": 490055, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0520992279052734, "global_step": 490056, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0976157188415527, "global_step": 490057, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0344371795654297, "global_step": 490058, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.062068223953247, "global_step": 490059, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.008762836456299, "global_step": 490060, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.047069549560547, "global_step": 490061, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0825304985046387, "global_step": 490062, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.097442388534546, "global_step": 490063, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0669422149658203, "global_step": 490064, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0229880809783936, "global_step": 490065, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.020629644393921, "global_step": 490066, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.054365873336792, "global_step": 490067, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0420877933502197, "global_step": 490068, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1114742755889893, "global_step": 490069, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0654404163360596, "global_step": 490070, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9834767580032349, "global_step": 490071, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1090457439422607, "global_step": 490072, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.078274726867676, "global_step": 490073, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0378856658935547, "global_step": 490074, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.061340808868408, "global_step": 490075, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0705907344818115, "global_step": 490076, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0548009872436523, "global_step": 490077, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0158731937408447, "global_step": 490078, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0147218704223633, "global_step": 490079, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.037968873977661, "global_step": 490080, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0468552112579346, "global_step": 490081, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.998716950416565, "global_step": 490082, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.020930051803589, "global_step": 490083, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0793182849884033, "global_step": 490084, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9895892143249512, "global_step": 490085, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.090672492980957, "global_step": 490086, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1214990615844727, "global_step": 490087, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.052562952041626, "global_step": 490088, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.10075306892395, "global_step": 490089, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.2618134021759033, "global_step": 490090, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0054380893707275, "global_step": 490091, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.109574317932129, "global_step": 490092, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1333272457122803, "global_step": 490093, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0671751499176025, "global_step": 490094, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.055222511291504, "global_step": 490095, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0677125453948975, "global_step": 490096, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.07438325881958, "global_step": 490097, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9955700635910034, "global_step": 490098, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0708866119384766, "global_step": 490099, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0969302654266357, "global_step": 490100, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.028200149536133, "global_step": 490101, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0479965209960938, "global_step": 490102, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0735185146331787, "global_step": 490103, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.065297842025757, "global_step": 490104, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0542960166931152, "global_step": 490105, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.03657865524292, "global_step": 490106, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0181162357330322, "global_step": 490107, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1269474029541016, "global_step": 490108, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.043501853942871, "global_step": 490109, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0487966537475586, "global_step": 490110, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1318657398223877, "global_step": 490111, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0433638095855713, "global_step": 490112, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.138256311416626, "global_step": 490113, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0885939598083496, "global_step": 490114, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0896804332733154, "global_step": 490115, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0935561656951904, "global_step": 490116, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0825815200805664, "global_step": 490117, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0053513050079346, "global_step": 490118, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0705952644348145, "global_step": 490119, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0368447303771973, "global_step": 490120, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0127124786376953, "global_step": 490121, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0065412521362305, "global_step": 490122, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.031923770904541, "global_step": 490123, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1298675537109375, "global_step": 490124, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0475516319274902, "global_step": 490125, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.073688268661499, "global_step": 490126, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0844178199768066, "global_step": 490127, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0608255863189697, "global_step": 490128, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0815365314483643, "global_step": 490129, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0722076892852783, "global_step": 490130, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.058988571166992, "global_step": 490131, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0755064487457275, "global_step": 490132, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0599546432495117, "global_step": 490133, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0529370307922363, "global_step": 490134, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.982351303100586, "global_step": 490135, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0768799781799316, "global_step": 490136, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0574228763580322, "global_step": 490137, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9740092754364014, "global_step": 490138, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1518542766571045, "global_step": 490139, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.04898738861084, "global_step": 490140, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.155573606491089, "global_step": 490141, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0241539478302, "global_step": 490142, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0264761447906494, "global_step": 490143, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0405900478363037, "global_step": 490144, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.074941873550415, "global_step": 490145, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0917224884033203, "global_step": 490146, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0775532722473145, "global_step": 490147, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0012311935424805, "global_step": 490148, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.105787992477417, "global_step": 490149, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0525686740875244, "global_step": 490150, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9899457693099976, "global_step": 490151, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.052489757537842, "global_step": 490152, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0974831581115723, "global_step": 490153, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0370540618896484, "global_step": 490154, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.118774175643921, "global_step": 490155, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0490715503692627, "global_step": 490156, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0149526596069336, "global_step": 490157, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.023054599761963, "global_step": 490158, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0787627696990967, "global_step": 490159, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0688133239746094, "global_step": 490160, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9622762203216553, "global_step": 490161, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0521745681762695, "global_step": 490162, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0218920707702637, "global_step": 490163, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.088792324066162, "global_step": 490164, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0255918502807617, "global_step": 490165, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0323312282562256, "global_step": 490166, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0365517139434814, "global_step": 490167, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0212035179138184, "global_step": 490168, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0495917797088623, "global_step": 490169, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.071187973022461, "global_step": 490170, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.064030647277832, "global_step": 490171, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0855743885040283, "global_step": 490172, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0849432945251465, "global_step": 490173, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9781025648117065, "global_step": 490174, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9842544794082642, "global_step": 490175, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0760722160339355, "global_step": 490176, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.056983709335327, "global_step": 490177, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.075186252593994, "global_step": 490178, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.075491189956665, "global_step": 490179, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0461461544036865, "global_step": 490180, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0983331203460693, "global_step": 490181, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0434646606445312, "global_step": 490182, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.100358009338379, "global_step": 490183, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.008478879928589, "global_step": 490184, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1496951580047607, "global_step": 490185, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0441455841064453, "global_step": 490186, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0961501598358154, "global_step": 490187, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0354621410369873, "global_step": 490188, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0493812561035156, "global_step": 490189, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0667426586151123, "global_step": 490190, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0548667907714844, "global_step": 490191, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.016603708267212, "global_step": 490192, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.099062442779541, "global_step": 490193, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0559568405151367, "global_step": 490194, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1150505542755127, "global_step": 490195, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.122419834136963, "global_step": 490196, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.8727396726608276, "global_step": 490197, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1305596828460693, "global_step": 490198, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.037379503250122, "global_step": 490199, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.160109043121338, "global_step": 490200, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9608615636825562, "global_step": 490201, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1233434677124023, "global_step": 490202, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.051682949066162, "global_step": 490203, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1423263549804688, "global_step": 490204, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0651981830596924, "global_step": 490205, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0344364643096924, "global_step": 490206, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9762110710144043, "global_step": 490207, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0466132164001465, "global_step": 490208, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0608620643615723, "global_step": 490209, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9747352600097656, "global_step": 490210, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.061933755874634, "global_step": 490211, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1194353103637695, "global_step": 490212, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.970536470413208, "global_step": 490213, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.96990966796875, "global_step": 490214, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1108884811401367, "global_step": 490215, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.054642915725708, "global_step": 490216, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0478665828704834, "global_step": 490217, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.043872594833374, "global_step": 490218, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0075862407684326, "global_step": 490219, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0148298740386963, "global_step": 490220, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.017270803451538, "global_step": 490221, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1295390129089355, "global_step": 490222, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9675116539001465, "global_step": 490223, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1226327419281006, "global_step": 490224, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.108372211456299, "global_step": 490225, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9852277040481567, "global_step": 490226, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0323119163513184, "global_step": 490227, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0382559299468994, "global_step": 490228, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9931970834732056, "global_step": 490229, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9668059349060059, "global_step": 490230, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0621719360351562, "global_step": 490231, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.086582899093628, "global_step": 490232, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0860252380371094, "global_step": 490233, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0671939849853516, "global_step": 490234, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0770111083984375, "global_step": 490235, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.050185203552246, "global_step": 490236, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.055314540863037, "global_step": 490237, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.977035641670227, "global_step": 490238, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0584518909454346, "global_step": 490239, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1324622631073, "global_step": 490240, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1062607765197754, "global_step": 490241, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0800797939300537, "global_step": 490242, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1501283645629883, "global_step": 490243, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.063847541809082, "global_step": 490244, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1711320877075195, "global_step": 490245, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.993991494178772, "global_step": 490246, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1328890323638916, "global_step": 490247, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.074467658996582, "global_step": 490248, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0788521766662598, "global_step": 490249, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.051370620727539, "global_step": 490250, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1214866638183594, "global_step": 490251, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1137144565582275, "global_step": 490252, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.016650676727295, "global_step": 490253, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.937528133392334, "global_step": 490254, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0007193088531494, "global_step": 490255, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0132195949554443, "global_step": 490256, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.011011838912964, "global_step": 490257, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.060161590576172, "global_step": 490258, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1469993591308594, "global_step": 490259, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1234192848205566, "global_step": 490260, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1038472652435303, "global_step": 490261, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.068995237350464, "global_step": 490262, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.120173454284668, "global_step": 490263, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.108166217803955, "global_step": 490264, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.036811590194702, "global_step": 490265, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.108181953430176, "global_step": 490266, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0206210613250732, "global_step": 490267, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.052623987197876, "global_step": 490268, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.044194221496582, "global_step": 490269, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0660977363586426, "global_step": 490270, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9967821836471558, "global_step": 490271, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0371925830841064, "global_step": 490272, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1365227699279785, "global_step": 490273, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9863673448562622, "global_step": 490274, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.106961965560913, "global_step": 490275, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0849955081939697, "global_step": 490276, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0555648803710938, "global_step": 490277, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0898804664611816, "global_step": 490278, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.099463701248169, "global_step": 490279, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9746099710464478, "global_step": 490280, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9973710775375366, "global_step": 490281, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.013629198074341, "global_step": 490282, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.155879259109497, "global_step": 490283, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0309746265411377, "global_step": 490284, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0435433387756348, "global_step": 490285, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1018683910369873, "global_step": 490286, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0329339504241943, "global_step": 490287, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0003316402435303, "global_step": 490288, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9972478151321411, "global_step": 490289, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.022857427597046, "global_step": 490290, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.011070728302002, "global_step": 490291, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1725826263427734, "global_step": 490292, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.145275115966797, "global_step": 490293, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1394760608673096, "global_step": 490294, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0375823974609375, "global_step": 490295, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.007319688796997, "global_step": 490296, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.101917266845703, "global_step": 490297, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0860700607299805, "global_step": 490298, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.09329891204834, "global_step": 490299, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0374584197998047, "global_step": 490300, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0602121353149414, "global_step": 490301, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0562498569488525, "global_step": 490302, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0430705547332764, "global_step": 490303, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0111083984375, "global_step": 490304, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0675454139709473, "global_step": 490305, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1050450801849365, "global_step": 490306, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9879146814346313, "global_step": 490307, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.025336980819702, "global_step": 490308, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0666439533233643, "global_step": 490309, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.109006643295288, "global_step": 490310, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1765387058258057, "global_step": 490311, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1483333110809326, "global_step": 490312, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1234045028686523, "global_step": 490313, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0428500175476074, "global_step": 490314, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.928707242012024, "global_step": 490315, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.045100688934326, "global_step": 490316, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.002183198928833, "global_step": 490317, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9997928142547607, "global_step": 490318, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0577287673950195, "global_step": 490319, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.078857183456421, "global_step": 490320, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1054115295410156, "global_step": 490321, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0649383068084717, "global_step": 490322, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0544745922088623, "global_step": 490323, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.072699546813965, "global_step": 490324, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0020124912261963, "global_step": 490325, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1168570518493652, "global_step": 490326, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9738036394119263, "global_step": 490327, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0597219467163086, "global_step": 490328, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0266292095184326, "global_step": 490329, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.082866907119751, "global_step": 490330, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0109448432922363, "global_step": 490331, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0435726642608643, "global_step": 490332, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0435707569122314, "global_step": 490333, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.060725450515747, "global_step": 490334, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.079568862915039, "global_step": 490335, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.130953311920166, "global_step": 490336, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9890875816345215, "global_step": 490337, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.13188099861145, "global_step": 490338, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0761780738830566, "global_step": 490339, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9855310916900635, "global_step": 490340, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0161116123199463, "global_step": 490341, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0587611198425293, "global_step": 490342, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9584473371505737, "global_step": 490343, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.984562635421753, "global_step": 490344, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.015132427215576, "global_step": 490345, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.011594295501709, "global_step": 490346, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.067756414413452, "global_step": 490347, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0789973735809326, "global_step": 490348, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1129212379455566, "global_step": 490349, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.041454315185547, "global_step": 490350, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.019315004348755, "global_step": 490351, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1033313274383545, "global_step": 490352, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0130457878112793, "global_step": 490353, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.070336103439331, "global_step": 490354, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0413248538970947, "global_step": 490355, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.100795030593872, "global_step": 490356, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0864391326904297, "global_step": 490357, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0514564514160156, "global_step": 490358, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.093022346496582, "global_step": 490359, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0850770473480225, "global_step": 490360, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.178135633468628, "global_step": 490361, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.101417064666748, "global_step": 490362, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9961243867874146, "global_step": 490363, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.057218313217163, "global_step": 490364, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1633388996124268, "global_step": 490365, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1148171424865723, "global_step": 490366, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0415542125701904, "global_step": 490367, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1384987831115723, "global_step": 490368, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9989432096481323, "global_step": 490369, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0665481090545654, "global_step": 490370, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.193925380706787, "global_step": 490371, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0377352237701416, "global_step": 490372, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.07047176361084, "global_step": 490373, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.052419662475586, "global_step": 490374, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.064929723739624, "global_step": 490375, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.098515272140503, "global_step": 490376, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0697131156921387, "global_step": 490377, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0746407508850098, "global_step": 490378, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.97515869140625, "global_step": 490379, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0772340297698975, "global_step": 490380, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.990705132484436, "global_step": 490381, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.056356906890869, "global_step": 490382, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0636043548583984, "global_step": 490383, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0101959705352783, "global_step": 490384, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0926599502563477, "global_step": 490385, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0513219833374023, "global_step": 490386, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0960988998413086, "global_step": 490387, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.083920955657959, "global_step": 490388, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9046562910079956, "global_step": 490389, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.042731761932373, "global_step": 490390, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0755112171173096, "global_step": 490391, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.059213876724243, "global_step": 490392, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.064418077468872, "global_step": 490393, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0501437187194824, "global_step": 490394, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.016268014907837, "global_step": 490395, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0230331420898438, "global_step": 490396, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0518717765808105, "global_step": 490397, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0711963176727295, "global_step": 490398, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0798487663269043, "global_step": 490399, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0472331047058105, "global_step": 490400, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.114579677581787, "global_step": 490401, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.068636178970337, "global_step": 490402, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0136659145355225, "global_step": 490403, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0171384811401367, "global_step": 490404, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9122728109359741, "global_step": 490405, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.036229372024536, "global_step": 490406, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.180248498916626, "global_step": 490407, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.081911087036133, "global_step": 490408, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0575647354125977, "global_step": 490409, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.010317802429199, "global_step": 490410, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1331238746643066, "global_step": 490411, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0517287254333496, "global_step": 490412, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0846750736236572, "global_step": 490413, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.991707682609558, "global_step": 490414, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.058175563812256, "global_step": 490415, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9771753549575806, "global_step": 490416, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.018040180206299, "global_step": 490417, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1454997062683105, "global_step": 490418, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.076632499694824, "global_step": 490419, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0177204608917236, "global_step": 490420, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.995880365371704, "global_step": 490421, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0453879833221436, "global_step": 490422, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0583314895629883, "global_step": 490423, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0043275356292725, "global_step": 490424, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.984416127204895, "global_step": 490425, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0057904720306396, "global_step": 490426, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0774104595184326, "global_step": 490427, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0462255477905273, "global_step": 490428, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0554211139678955, "global_step": 490429, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0885987281799316, "global_step": 490430, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0809974670410156, "global_step": 490431, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.165529251098633, "global_step": 490432, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.038595676422119, "global_step": 490433, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.11203932762146, "global_step": 490434, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9703688621520996, "global_step": 490435, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1047000885009766, "global_step": 490436, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.119532346725464, "global_step": 490437, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1365468502044678, "global_step": 490438, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0114731788635254, "global_step": 490439, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1066670417785645, "global_step": 490440, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0077781677246094, "global_step": 490441, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1096298694610596, "global_step": 490442, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.1583969593048096, "global_step": 490443, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0957844257354736, "global_step": 490444, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.106037139892578, "global_step": 490445, "epoch": 855, "lr": 5e-05}
{"train_loss": 2.0570220947265625, "global_step": 490446, "epoch": 855, "lr": 5e-05}
{"train_loss": 1.9192651510238647, "global_step": 490447, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9542725086212158, "global_step": 490448, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0535025596618652, "global_step": 490449, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0851612091064453, "global_step": 490450, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.000974178314209, "global_step": 490451, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.967607021331787, "global_step": 490452, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9232319593429565, "global_step": 490453, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.988965392112732, "global_step": 490454, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.082714796066284, "global_step": 490455, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9558659791946411, "global_step": 490456, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.063701629638672, "global_step": 490457, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0538034439086914, "global_step": 490458, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0275039672851562, "global_step": 490459, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.053459405899048, "global_step": 490460, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9746876955032349, "global_step": 490461, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1105000972747803, "global_step": 490462, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.059788465499878, "global_step": 490463, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.129335403442383, "global_step": 490464, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0864365100860596, "global_step": 490465, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9694371223449707, "global_step": 490466, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9728304147720337, "global_step": 490467, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0115039348602295, "global_step": 490468, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0667097568511963, "global_step": 490469, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9828507900238037, "global_step": 490470, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.028989315032959, "global_step": 490471, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.046638011932373, "global_step": 490472, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1045520305633545, "global_step": 490473, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0985255241394043, "global_step": 490474, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.087998390197754, "global_step": 490475, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1426143646240234, "global_step": 490476, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0218396186828613, "global_step": 490477, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.096416711807251, "global_step": 490478, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9956474304199219, "global_step": 490479, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.006254196166992, "global_step": 490480, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.041830539703369, "global_step": 490481, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0782670974731445, "global_step": 490482, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.090254306793213, "global_step": 490483, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.06467604637146, "global_step": 490484, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0082292556762695, "global_step": 490485, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0815861225128174, "global_step": 490486, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0096781253814697, "global_step": 490487, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0937461853027344, "global_step": 490488, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1943633556365967, "global_step": 490489, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9768644571304321, "global_step": 490490, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0205960273742676, "global_step": 490491, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.05240535736084, "global_step": 490492, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.970876932144165, "global_step": 490493, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.997671127319336, "global_step": 490494, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.084935426712036, "global_step": 490495, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0344014167785645, "global_step": 490496, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9848101139068604, "global_step": 490497, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9960839748382568, "global_step": 490498, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.087697744369507, "global_step": 490499, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0085806846618652, "global_step": 490500, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0430760383605957, "global_step": 490501, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.018721580505371, "global_step": 490502, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9804381132125854, "global_step": 490503, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0490243434906006, "global_step": 490504, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0361716747283936, "global_step": 490505, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.948075294494629, "global_step": 490506, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.063044309616089, "global_step": 490507, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0278091430664062, "global_step": 490508, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1102519035339355, "global_step": 490509, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0106523036956787, "global_step": 490510, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0086278915405273, "global_step": 490511, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0809755325317383, "global_step": 490512, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0494487285614014, "global_step": 490513, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0132036209106445, "global_step": 490514, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.112649917602539, "global_step": 490515, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0457804203033447, "global_step": 490516, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.006967067718506, "global_step": 490517, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0241596698760986, "global_step": 490518, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0571200847625732, "global_step": 490519, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1560590267181396, "global_step": 490520, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0407702922821045, "global_step": 490521, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.052743911743164, "global_step": 490522, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0139026641845703, "global_step": 490523, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.071509838104248, "global_step": 490524, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.083726406097412, "global_step": 490525, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9347398281097412, "global_step": 490526, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.035749912261963, "global_step": 490527, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.11641001701355, "global_step": 490528, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.059797763824463, "global_step": 490529, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0387728214263916, "global_step": 490530, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0556440353393555, "global_step": 490531, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0188066959381104, "global_step": 490532, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.026204824447632, "global_step": 490533, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0516104698181152, "global_step": 490534, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0484111309051514, "global_step": 490535, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0084266662597656, "global_step": 490536, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0779013633728027, "global_step": 490537, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.16763973236084, "global_step": 490538, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0533156394958496, "global_step": 490539, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0016205310821533, "global_step": 490540, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.029531717300415, "global_step": 490541, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.148526668548584, "global_step": 490542, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.125948905944824, "global_step": 490543, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1317403316497803, "global_step": 490544, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.087369203567505, "global_step": 490545, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.972922921180725, "global_step": 490546, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1131248474121094, "global_step": 490547, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.091595411300659, "global_step": 490548, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0267395973205566, "global_step": 490549, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0191421508789062, "global_step": 490550, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0391390323638916, "global_step": 490551, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9935537576675415, "global_step": 490552, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0906221866607666, "global_step": 490553, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9389591217041016, "global_step": 490554, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0618479251861572, "global_step": 490555, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9048148393630981, "global_step": 490556, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9856901168823242, "global_step": 490557, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9411054849624634, "global_step": 490558, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.029778480529785, "global_step": 490559, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0414657592773438, "global_step": 490560, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0492565631866455, "global_step": 490561, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9940822124481201, "global_step": 490562, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0874574184417725, "global_step": 490563, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9961717128753662, "global_step": 490564, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1388957500457764, "global_step": 490565, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.978105902671814, "global_step": 490566, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0053679943084717, "global_step": 490567, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.038391351699829, "global_step": 490568, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0796988010406494, "global_step": 490569, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.081021785736084, "global_step": 490570, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0898003578186035, "global_step": 490571, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0678861141204834, "global_step": 490572, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.086979866027832, "global_step": 490573, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.049872636795044, "global_step": 490574, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.002518892288208, "global_step": 490575, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0455069541931152, "global_step": 490576, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.082120418548584, "global_step": 490577, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0497002601623535, "global_step": 490578, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9192841053009033, "global_step": 490579, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.055412769317627, "global_step": 490580, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0300731658935547, "global_step": 490581, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0997066497802734, "global_step": 490582, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0818557739257812, "global_step": 490583, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1289310455322266, "global_step": 490584, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.116816759109497, "global_step": 490585, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.092782497406006, "global_step": 490586, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0272603034973145, "global_step": 490587, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9537452459335327, "global_step": 490588, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9952735900878906, "global_step": 490589, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.083570718765259, "global_step": 490590, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1186447143554688, "global_step": 490591, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.035022020339966, "global_step": 490592, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.103915214538574, "global_step": 490593, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.055136203765869, "global_step": 490594, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.034393072128296, "global_step": 490595, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0778696537017822, "global_step": 490596, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.027259588241577, "global_step": 490597, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.025390625, "global_step": 490598, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0306148529052734, "global_step": 490599, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.039902687072754, "global_step": 490600, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9739234447479248, "global_step": 490601, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.078258752822876, "global_step": 490602, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9658349752426147, "global_step": 490603, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9740046262741089, "global_step": 490604, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0966947078704834, "global_step": 490605, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0666396617889404, "global_step": 490606, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9913887977600098, "global_step": 490607, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.082899570465088, "global_step": 490608, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.053652048110962, "global_step": 490609, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1195790767669678, "global_step": 490610, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1635892391204834, "global_step": 490611, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.08223295211792, "global_step": 490612, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0893030166625977, "global_step": 490613, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1900625228881836, "global_step": 490614, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.019874095916748, "global_step": 490615, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.018498659133911, "global_step": 490616, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.135460376739502, "global_step": 490617, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.027315378189087, "global_step": 490618, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0318143367767334, "global_step": 490619, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0926060676574707, "global_step": 490620, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0800137519836426, "global_step": 490621, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0760421752929688, "global_step": 490622, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.015430450439453, "global_step": 490623, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.058034658432007, "global_step": 490624, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0928659439086914, "global_step": 490625, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0298373699188232, "global_step": 490626, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.100492238998413, "global_step": 490627, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0818233489990234, "global_step": 490628, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9627939462661743, "global_step": 490629, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0586371421813965, "global_step": 490630, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1127126216888428, "global_step": 490631, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.03828763961792, "global_step": 490632, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.051571846008301, "global_step": 490633, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.029618740081787, "global_step": 490634, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0908162593841553, "global_step": 490635, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0679194927215576, "global_step": 490636, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.158552646636963, "global_step": 490637, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.034386157989502, "global_step": 490638, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0254669189453125, "global_step": 490639, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.10432505607605, "global_step": 490640, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0216710567474365, "global_step": 490641, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.045057535171509, "global_step": 490642, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.038830280303955, "global_step": 490643, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0463764667510986, "global_step": 490644, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0554018020629883, "global_step": 490645, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0191025733947754, "global_step": 490646, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0328760147094727, "global_step": 490647, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.051058769226074, "global_step": 490648, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9907925128936768, "global_step": 490649, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.041384220123291, "global_step": 490650, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.073819875717163, "global_step": 490651, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0666823387145996, "global_step": 490652, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.111137866973877, "global_step": 490653, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.089632987976074, "global_step": 490654, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0311923027038574, "global_step": 490655, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0404040813446045, "global_step": 490656, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1194980144500732, "global_step": 490657, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9846495389938354, "global_step": 490658, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1049904823303223, "global_step": 490659, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9729539155960083, "global_step": 490660, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0334551334381104, "global_step": 490661, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0130667686462402, "global_step": 490662, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.054967164993286, "global_step": 490663, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.051030397415161, "global_step": 490664, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0685181617736816, "global_step": 490665, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.086160659790039, "global_step": 490666, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.036306381225586, "global_step": 490667, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.02089786529541, "global_step": 490668, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0827457904815674, "global_step": 490669, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0641531944274902, "global_step": 490670, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0769686698913574, "global_step": 490671, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0895309448242188, "global_step": 490672, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.06833553314209, "global_step": 490673, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.017148017883301, "global_step": 490674, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0044217109680176, "global_step": 490675, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0463790893554688, "global_step": 490676, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9688113927841187, "global_step": 490677, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.040639638900757, "global_step": 490678, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9956611394882202, "global_step": 490679, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0265920162200928, "global_step": 490680, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.063476085662842, "global_step": 490681, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0292768478393555, "global_step": 490682, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0227878093719482, "global_step": 490683, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.078915596008301, "global_step": 490684, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0373499393463135, "global_step": 490685, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9997014999389648, "global_step": 490686, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.017346143722534, "global_step": 490687, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9968843460083008, "global_step": 490688, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.000851631164551, "global_step": 490689, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9408446550369263, "global_step": 490690, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0801849365234375, "global_step": 490691, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0256710052490234, "global_step": 490692, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.030606746673584, "global_step": 490693, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.086824417114258, "global_step": 490694, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.967464566230774, "global_step": 490695, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0944786071777344, "global_step": 490696, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.025559425354004, "global_step": 490697, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.023658275604248, "global_step": 490698, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.006160020828247, "global_step": 490699, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.088219404220581, "global_step": 490700, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.2010440826416016, "global_step": 490701, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0901308059692383, "global_step": 490702, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.021334648132324, "global_step": 490703, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.061976909637451, "global_step": 490704, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9071685075759888, "global_step": 490705, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.04024076461792, "global_step": 490706, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.068007230758667, "global_step": 490707, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0450308322906494, "global_step": 490708, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.063046932220459, "global_step": 490709, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0099430084228516, "global_step": 490710, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0258865356445312, "global_step": 490711, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.096531391143799, "global_step": 490712, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1133029460906982, "global_step": 490713, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0442872047424316, "global_step": 490714, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.01823091506958, "global_step": 490715, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0873730182647705, "global_step": 490716, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0703437328338623, "global_step": 490717, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9492237567901611, "global_step": 490718, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.016871452331543, "global_step": 490719, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.019209384918213, "global_step": 490720, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0413026809692383, "global_step": 490721, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0199596881866455, "global_step": 490722, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.13527250289917, "global_step": 490723, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9585938453674316, "global_step": 490724, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0368950366973877, "global_step": 490725, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9614835977554321, "global_step": 490726, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0639686584472656, "global_step": 490727, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.019883632659912, "global_step": 490728, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0546913146972656, "global_step": 490729, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.078709840774536, "global_step": 490730, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.971970558166504, "global_step": 490731, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0784008502960205, "global_step": 490732, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0384387969970703, "global_step": 490733, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9727107286453247, "global_step": 490734, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.150367259979248, "global_step": 490735, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9678027629852295, "global_step": 490736, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.101545572280884, "global_step": 490737, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0072708129882812, "global_step": 490738, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.057678699493408, "global_step": 490739, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1000115871429443, "global_step": 490740, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0838708877563477, "global_step": 490741, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.099477529525757, "global_step": 490742, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0373315811157227, "global_step": 490743, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.043485164642334, "global_step": 490744, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0720620155334473, "global_step": 490745, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.947801113128662, "global_step": 490746, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1146488189697266, "global_step": 490747, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0395779609680176, "global_step": 490748, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.878772258758545, "global_step": 490749, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.082481622695923, "global_step": 490750, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0416419506073, "global_step": 490751, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.992126703262329, "global_step": 490752, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.055074691772461, "global_step": 490753, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.131086826324463, "global_step": 490754, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0451860427856445, "global_step": 490755, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.050750255584717, "global_step": 490756, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0987749099731445, "global_step": 490757, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9997756481170654, "global_step": 490758, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.026315212249756, "global_step": 490759, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0055949687957764, "global_step": 490760, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0461108684539795, "global_step": 490761, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.032668113708496, "global_step": 490762, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.04620099067688, "global_step": 490763, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0381224155426025, "global_step": 490764, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0314114093780518, "global_step": 490765, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0475692749023438, "global_step": 490766, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0474655628204346, "global_step": 490767, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.011273145675659, "global_step": 490768, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0666797161102295, "global_step": 490769, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0471649169921875, "global_step": 490770, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0380146503448486, "global_step": 490771, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1921796798706055, "global_step": 490772, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.998295783996582, "global_step": 490773, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0215611457824707, "global_step": 490774, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0335440635681152, "global_step": 490775, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1084182262420654, "global_step": 490776, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0501089096069336, "global_step": 490777, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0147154331207275, "global_step": 490778, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1346120834350586, "global_step": 490779, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.094442367553711, "global_step": 490780, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.088813543319702, "global_step": 490781, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9709928035736084, "global_step": 490782, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0595526695251465, "global_step": 490783, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0399746894836426, "global_step": 490784, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.047734260559082, "global_step": 490785, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.060903310775757, "global_step": 490786, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0152015686035156, "global_step": 490787, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0892536640167236, "global_step": 490788, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.015071392059326, "global_step": 490789, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0832436084747314, "global_step": 490790, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1577601432800293, "global_step": 490791, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1144328117370605, "global_step": 490792, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9959802627563477, "global_step": 490793, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.181840658187866, "global_step": 490794, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.035140037536621, "global_step": 490795, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0784223079681396, "global_step": 490796, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9672396183013916, "global_step": 490797, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.087207794189453, "global_step": 490798, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9800114631652832, "global_step": 490799, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9599816799163818, "global_step": 490800, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.064788818359375, "global_step": 490801, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.980660080909729, "global_step": 490802, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.983249545097351, "global_step": 490803, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0268876552581787, "global_step": 490804, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0652453899383545, "global_step": 490805, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.054652214050293, "global_step": 490806, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0763297080993652, "global_step": 490807, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.108109474182129, "global_step": 490808, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.096151828765869, "global_step": 490809, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.028533697128296, "global_step": 490810, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0140864849090576, "global_step": 490811, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.080963134765625, "global_step": 490812, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0620672702789307, "global_step": 490813, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0782458782196045, "global_step": 490814, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.044403314590454, "global_step": 490815, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0855162143707275, "global_step": 490816, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.094682455062866, "global_step": 490817, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9717665910720825, "global_step": 490818, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.093597173690796, "global_step": 490819, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0485002994537354, "global_step": 490820, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.06917405128479, "global_step": 490821, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.021761178970337, "global_step": 490822, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0359132289886475, "global_step": 490823, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.074026107788086, "global_step": 490824, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.109544277191162, "global_step": 490825, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.985420823097229, "global_step": 490826, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1412103176116943, "global_step": 490827, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0134646892547607, "global_step": 490828, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.102374315261841, "global_step": 490829, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.130617380142212, "global_step": 490830, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1461293697357178, "global_step": 490831, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0514886379241943, "global_step": 490832, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1039366722106934, "global_step": 490833, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0567867755889893, "global_step": 490834, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.089632272720337, "global_step": 490835, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.998571753501892, "global_step": 490836, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.989384651184082, "global_step": 490837, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0315659046173096, "global_step": 490838, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.102982997894287, "global_step": 490839, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.001530408859253, "global_step": 490840, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1125781536102295, "global_step": 490841, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0573112964630127, "global_step": 490842, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0704967975616455, "global_step": 490843, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0255117416381836, "global_step": 490844, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0122101306915283, "global_step": 490845, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.087313413619995, "global_step": 490846, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9757847785949707, "global_step": 490847, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0897536277770996, "global_step": 490848, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1317336559295654, "global_step": 490849, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9515362977981567, "global_step": 490850, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.006465196609497, "global_step": 490851, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0263495445251465, "global_step": 490852, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.006962776184082, "global_step": 490853, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1260874271392822, "global_step": 490854, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0516464710235596, "global_step": 490855, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9807045459747314, "global_step": 490856, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.083648681640625, "global_step": 490857, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.088500499725342, "global_step": 490858, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0415737628936768, "global_step": 490859, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1241424083709717, "global_step": 490860, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.126253604888916, "global_step": 490861, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.089637517929077, "global_step": 490862, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0563111305236816, "global_step": 490863, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1465096473693848, "global_step": 490864, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.901476502418518, "global_step": 490865, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.938929796218872, "global_step": 490866, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.096316337585449, "global_step": 490867, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.038393020629883, "global_step": 490868, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.023373603820801, "global_step": 490869, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0364654064178467, "global_step": 490870, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0539655685424805, "global_step": 490871, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.062690258026123, "global_step": 490872, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.003486156463623, "global_step": 490873, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1505327224731445, "global_step": 490874, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.995536208152771, "global_step": 490875, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0681540966033936, "global_step": 490876, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0252509117126465, "global_step": 490877, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.146014451980591, "global_step": 490878, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.049142599105835, "global_step": 490879, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.021314859390259, "global_step": 490880, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0284130573272705, "global_step": 490881, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.071481704711914, "global_step": 490882, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1712779998779297, "global_step": 490883, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.07983136177063, "global_step": 490884, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.108067274093628, "global_step": 490885, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.001829147338867, "global_step": 490886, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.075853109359741, "global_step": 490887, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.05686616897583, "global_step": 490888, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0270168781280518, "global_step": 490889, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0572738647460938, "global_step": 490890, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.065078020095825, "global_step": 490891, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0385663509368896, "global_step": 490892, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.065255641937256, "global_step": 490893, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0848212242126465, "global_step": 490894, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.956348180770874, "global_step": 490895, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9769190549850464, "global_step": 490896, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0769386291503906, "global_step": 490897, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.009348154067993, "global_step": 490898, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1404693126678467, "global_step": 490899, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0142011642456055, "global_step": 490900, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0232129096984863, "global_step": 490901, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0719408988952637, "global_step": 490902, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0795068740844727, "global_step": 490903, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.116089344024658, "global_step": 490904, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.098754405975342, "global_step": 490905, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0608317852020264, "global_step": 490906, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.060781955718994, "global_step": 490907, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0732483863830566, "global_step": 490908, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0686306953430176, "global_step": 490909, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.030435085296631, "global_step": 490910, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.090315103530884, "global_step": 490911, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.037355661392212, "global_step": 490912, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0196547508239746, "global_step": 490913, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0705161094665527, "global_step": 490914, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9917267560958862, "global_step": 490915, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0685863494873047, "global_step": 490916, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0803208351135254, "global_step": 490917, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9399527311325073, "global_step": 490918, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1144559383392334, "global_step": 490919, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.029745101928711, "global_step": 490920, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0896947383880615, "global_step": 490921, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9662507772445679, "global_step": 490922, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0506808757781982, "global_step": 490923, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1283071041107178, "global_step": 490924, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0932912826538086, "global_step": 490925, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1560091972351074, "global_step": 490926, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0478157997131348, "global_step": 490927, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0239357948303223, "global_step": 490928, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0847737789154053, "global_step": 490929, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0751278400421143, "global_step": 490930, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.146397113800049, "global_step": 490931, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.006793975830078, "global_step": 490932, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9831726551055908, "global_step": 490933, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0624489784240723, "global_step": 490934, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.046372175216675, "global_step": 490935, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0943591594696045, "global_step": 490936, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0829548835754395, "global_step": 490937, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0761725902557373, "global_step": 490938, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0525927543640137, "global_step": 490939, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0828287601470947, "global_step": 490940, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.012993574142456, "global_step": 490941, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1433119773864746, "global_step": 490942, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.045863389968872, "global_step": 490943, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9944307804107666, "global_step": 490944, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1010687351226807, "global_step": 490945, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.070551633834839, "global_step": 490946, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9782289266586304, "global_step": 490947, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9600287675857544, "global_step": 490948, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.045605182647705, "global_step": 490949, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.001957416534424, "global_step": 490950, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.004136800765991, "global_step": 490951, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.013627767562866, "global_step": 490952, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9701459407806396, "global_step": 490953, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0760109424591064, "global_step": 490954, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0430595874786377, "global_step": 490955, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.983587622642517, "global_step": 490956, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1042520999908447, "global_step": 490957, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9361534118652344, "global_step": 490958, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0610599517822266, "global_step": 490959, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.046602964401245, "global_step": 490960, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1091296672821045, "global_step": 490961, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0739362239837646, "global_step": 490962, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9010931253433228, "global_step": 490963, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0364973545074463, "global_step": 490964, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.041525363922119, "global_step": 490965, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0252392292022705, "global_step": 490966, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.054253339767456, "global_step": 490967, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.119837522506714, "global_step": 490968, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0110323429107666, "global_step": 490969, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.966536283493042, "global_step": 490970, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.014122247695923, "global_step": 490971, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.959185242652893, "global_step": 490972, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0052847862243652, "global_step": 490973, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0694048404693604, "global_step": 490974, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1331028938293457, "global_step": 490975, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0439116954803467, "global_step": 490976, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1622557640075684, "global_step": 490977, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0172815322875977, "global_step": 490978, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.003498077392578, "global_step": 490979, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.101602554321289, "global_step": 490980, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9905704259872437, "global_step": 490981, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1470282077789307, "global_step": 490982, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1669065952301025, "global_step": 490983, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0486788749694824, "global_step": 490984, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0723111629486084, "global_step": 490985, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.096414566040039, "global_step": 490986, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9700361490249634, "global_step": 490987, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.027989625930786, "global_step": 490988, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1342897415161133, "global_step": 490989, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.152569055557251, "global_step": 490990, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9711990356445312, "global_step": 490991, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1056880950927734, "global_step": 490992, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.093776226043701, "global_step": 490993, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0828499794006348, "global_step": 490994, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.084662675857544, "global_step": 490995, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0087344646453857, "global_step": 490996, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.021702289581299, "global_step": 490997, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.055095672607422, "global_step": 490998, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.054072141647339, "global_step": 490999, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1815760135650635, "global_step": 491000, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0400912761688232, "global_step": 491001, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9526313543319702, "global_step": 491002, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0935518741607666, "global_step": 491003, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.117293119430542, "global_step": 491004, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0362157821655273, "global_step": 491005, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1013245582580566, "global_step": 491006, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.062002658843994, "global_step": 491007, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.108771800994873, "global_step": 491008, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.00046443939209, "global_step": 491009, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.014421224594116, "global_step": 491010, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0210962295532227, "global_step": 491011, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.120534896850586, "global_step": 491012, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1113626956939697, "global_step": 491013, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.079681634902954, "global_step": 491014, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0935935974121094, "global_step": 491015, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9770528078079224, "global_step": 491016, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.11037540435791, "global_step": 491017, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9533281326293945, "global_step": 491018, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0428543090820312, "global_step": 491019, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0097339153289795, "global_step": 491020, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.165731191635132, "global_step": 491021, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9886417388916016, "global_step": 491022, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.142129421234131, "global_step": 491023, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0997941493988037, "global_step": 491024, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0252459049224854, "global_step": 491025, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0425844192504883, "global_step": 491026, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9935542345046997, "global_step": 491027, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.014296531677246, "global_step": 491028, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.083010196685791, "global_step": 491029, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.097257375717163, "global_step": 491030, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1278269290924072, "global_step": 491031, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9743729829788208, "global_step": 491032, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1818156242370605, "global_step": 491033, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.065629482269287, "global_step": 491034, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.11879563331604, "global_step": 491035, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0180110931396484, "global_step": 491036, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.082893133163452, "global_step": 491037, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.019822359085083, "global_step": 491038, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0325794219970703, "global_step": 491039, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1941542625427246, "global_step": 491040, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0788216590881348, "global_step": 491041, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0370049476623535, "global_step": 491042, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.067392587661743, "global_step": 491043, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9788172245025635, "global_step": 491044, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.040449857711792, "global_step": 491045, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.096561908721924, "global_step": 491046, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9973214864730835, "global_step": 491047, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.146395683288574, "global_step": 491048, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.15657901763916, "global_step": 491049, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.081486225128174, "global_step": 491050, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.155695676803589, "global_step": 491051, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9151721000671387, "global_step": 491052, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.019602060317993, "global_step": 491053, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.081378221511841, "global_step": 491054, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1355109214782715, "global_step": 491055, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1015584468841553, "global_step": 491056, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0211100578308105, "global_step": 491057, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.173065662384033, "global_step": 491058, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.066723108291626, "global_step": 491059, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0346832275390625, "global_step": 491060, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0138044357299805, "global_step": 491061, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.930938720703125, "global_step": 491062, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0662593841552734, "global_step": 491063, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9975898265838623, "global_step": 491064, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0520575046539307, "global_step": 491065, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0807087421417236, "global_step": 491066, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0925207138061523, "global_step": 491067, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.013700008392334, "global_step": 491068, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0607972145080566, "global_step": 491069, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0667941570281982, "global_step": 491070, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0448338985443115, "global_step": 491071, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.120274543762207, "global_step": 491072, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0571649074554443, "global_step": 491073, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9900575876235962, "global_step": 491074, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0072107315063477, "global_step": 491075, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9819706678390503, "global_step": 491076, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1233408451080322, "global_step": 491077, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0258615016937256, "global_step": 491078, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1474905014038086, "global_step": 491079, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.045471429824829, "global_step": 491080, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0566704273223877, "global_step": 491081, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.108245372772217, "global_step": 491082, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0052380561828613, "global_step": 491083, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.102320432662964, "global_step": 491084, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0096399784088135, "global_step": 491085, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1100335121154785, "global_step": 491086, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.011125326156616, "global_step": 491087, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.042112112045288, "global_step": 491088, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.122941732406616, "global_step": 491089, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.143860340118408, "global_step": 491090, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.09619140625, "global_step": 491091, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.006862163543701, "global_step": 491092, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.160696268081665, "global_step": 491093, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0586798191070557, "global_step": 491094, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0553410053253174, "global_step": 491095, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0301849842071533, "global_step": 491096, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0902950763702393, "global_step": 491097, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0547053813934326, "global_step": 491098, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9650137424468994, "global_step": 491099, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0907065868377686, "global_step": 491100, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0271549224853516, "global_step": 491101, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.071348190307617, "global_step": 491102, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.025892734527588, "global_step": 491103, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.087104320526123, "global_step": 491104, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.045170545578003, "global_step": 491105, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.110675573348999, "global_step": 491106, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.937654972076416, "global_step": 491107, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.04685115814209, "global_step": 491108, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.149378538131714, "global_step": 491109, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1447367668151855, "global_step": 491110, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.103692054748535, "global_step": 491111, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1117210388183594, "global_step": 491112, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.126394271850586, "global_step": 491113, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.050588846206665, "global_step": 491114, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.030207633972168, "global_step": 491115, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.029531955718994, "global_step": 491116, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.013770818710327, "global_step": 491117, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0301785469055176, "global_step": 491118, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0274715423583984, "global_step": 491119, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.116884708404541, "global_step": 491120, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0655834674835205, "global_step": 491121, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0829505920410156, "global_step": 491122, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0636961460113525, "global_step": 491123, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0818042755126953, "global_step": 491124, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0009684562683105, "global_step": 491125, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9640825986862183, "global_step": 491126, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0067591667175293, "global_step": 491127, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.060591220855713, "global_step": 491128, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9886083602905273, "global_step": 491129, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0525591373443604, "global_step": 491130, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1012251377105713, "global_step": 491131, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9864486455917358, "global_step": 491132, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.107367753982544, "global_step": 491133, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.048936605453491, "global_step": 491134, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.033127784729004, "global_step": 491135, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0750484466552734, "global_step": 491136, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0577285289764404, "global_step": 491137, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.104804754257202, "global_step": 491138, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.050422191619873, "global_step": 491139, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.082331895828247, "global_step": 491140, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.069227695465088, "global_step": 491141, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.974652647972107, "global_step": 491142, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.121797561645508, "global_step": 491143, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0486905574798584, "global_step": 491144, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1447296142578125, "global_step": 491145, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0986015796661377, "global_step": 491146, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.039759635925293, "global_step": 491147, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0787220001220703, "global_step": 491148, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0837912559509277, "global_step": 491149, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0533177852630615, "global_step": 491150, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.036680221557617, "global_step": 491151, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.027848720550537, "global_step": 491152, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.073472261428833, "global_step": 491153, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.115323066711426, "global_step": 491154, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0998880863189697, "global_step": 491155, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1087045669555664, "global_step": 491156, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0826416015625, "global_step": 491157, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0629734992980957, "global_step": 491158, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0513665676116943, "global_step": 491159, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0549747943878174, "global_step": 491160, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.004225492477417, "global_step": 491161, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.063912868499756, "global_step": 491162, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.102135181427002, "global_step": 491163, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.099909543991089, "global_step": 491164, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.035790205001831, "global_step": 491165, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0350687503814697, "global_step": 491166, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.035998582839966, "global_step": 491167, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0425407886505127, "global_step": 491168, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1184070110321045, "global_step": 491169, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9367343187332153, "global_step": 491170, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0517396926879883, "global_step": 491171, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.088326930999756, "global_step": 491172, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.050358295440674, "global_step": 491173, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0746448040008545, "global_step": 491174, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9888486862182617, "global_step": 491175, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.098341941833496, "global_step": 491176, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.092691659927368, "global_step": 491177, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1043291091918945, "global_step": 491178, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.051079750061035, "global_step": 491179, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0825324058532715, "global_step": 491180, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0467989444732666, "global_step": 491181, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0080180168151855, "global_step": 491182, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.993939757347107, "global_step": 491183, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.097715377807617, "global_step": 491184, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0239439010620117, "global_step": 491185, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1293230056762695, "global_step": 491186, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.15461802482605, "global_step": 491187, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.073671579360962, "global_step": 491188, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1221089363098145, "global_step": 491189, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0438461303710938, "global_step": 491190, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.067979097366333, "global_step": 491191, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.101304292678833, "global_step": 491192, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0583176612854004, "global_step": 491193, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1006155014038086, "global_step": 491194, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9033578634262085, "global_step": 491195, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.081615447998047, "global_step": 491196, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9183375835418701, "global_step": 491197, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.079756259918213, "global_step": 491198, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.123347043991089, "global_step": 491199, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.120553970336914, "global_step": 491200, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.054689884185791, "global_step": 491201, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1318554878234863, "global_step": 491202, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.983141303062439, "global_step": 491203, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.022099018096924, "global_step": 491204, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9994473457336426, "global_step": 491205, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.062879800796509, "global_step": 491206, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0470876693725586, "global_step": 491207, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0598607063293457, "global_step": 491208, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.071187973022461, "global_step": 491209, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1191213130950928, "global_step": 491210, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.114567279815674, "global_step": 491211, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.07063627243042, "global_step": 491212, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0144498348236084, "global_step": 491213, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.022012948989868, "global_step": 491214, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1185309886932373, "global_step": 491215, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.033940553665161, "global_step": 491216, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.113731861114502, "global_step": 491217, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.047750234603882, "global_step": 491218, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.054819345474243, "global_step": 491219, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.064423084259033, "global_step": 491220, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1690673828125, "global_step": 491221, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.088301181793213, "global_step": 491222, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.099309206008911, "global_step": 491223, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0956170558929443, "global_step": 491224, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0288279056549072, "global_step": 491225, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0099174976348877, "global_step": 491226, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.09405779838562, "global_step": 491227, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9881856441497803, "global_step": 491228, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.018535852432251, "global_step": 491229, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0351791381835938, "global_step": 491230, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0445878505706787, "global_step": 491231, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9957549571990967, "global_step": 491232, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.145447254180908, "global_step": 491233, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.94485604763031, "global_step": 491234, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9658820629119873, "global_step": 491235, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1197354793548584, "global_step": 491236, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0432629585266113, "global_step": 491237, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.099653959274292, "global_step": 491238, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0644993782043457, "global_step": 491239, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.086994171142578, "global_step": 491240, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.047323703765869, "global_step": 491241, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0158534049987793, "global_step": 491242, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.070561408996582, "global_step": 491243, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.010953426361084, "global_step": 491244, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.047971487045288, "global_step": 491245, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9552559852600098, "global_step": 491246, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0759437084198, "global_step": 491247, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0729761123657227, "global_step": 491248, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.089090347290039, "global_step": 491249, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1149203777313232, "global_step": 491250, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.994140386581421, "global_step": 491251, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0472254753112793, "global_step": 491252, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0355923175811768, "global_step": 491253, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1022074222564697, "global_step": 491254, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0626492500305176, "global_step": 491255, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9712460041046143, "global_step": 491256, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0301685333251953, "global_step": 491257, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0871222019195557, "global_step": 491258, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.02583646774292, "global_step": 491259, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1772186756134033, "global_step": 491260, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.064842939376831, "global_step": 491261, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0202596187591553, "global_step": 491262, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.105682373046875, "global_step": 491263, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.050487995147705, "global_step": 491264, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.042271852493286, "global_step": 491265, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0673623085021973, "global_step": 491266, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.045335531234741, "global_step": 491267, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.026634931564331, "global_step": 491268, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.15004825592041, "global_step": 491269, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.974018931388855, "global_step": 491270, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0727288722991943, "global_step": 491271, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0994701385498047, "global_step": 491272, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0957231521606445, "global_step": 491273, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0849056243896484, "global_step": 491274, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.128263235092163, "global_step": 491275, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0900096893310547, "global_step": 491276, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.10469126701355, "global_step": 491277, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.136039972305298, "global_step": 491278, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.025940179824829, "global_step": 491279, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0878071784973145, "global_step": 491280, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0445480346679688, "global_step": 491281, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9959355592727661, "global_step": 491282, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1009483337402344, "global_step": 491283, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.056990385055542, "global_step": 491284, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0654289722442627, "global_step": 491285, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0696234703063965, "global_step": 491286, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0319063663482666, "global_step": 491287, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1497604846954346, "global_step": 491288, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.025808572769165, "global_step": 491289, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0111711025238037, "global_step": 491290, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0422816276550293, "global_step": 491291, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.021545886993408, "global_step": 491292, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.081112861633301, "global_step": 491293, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.102001428604126, "global_step": 491294, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.118041515350342, "global_step": 491295, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.074101686477661, "global_step": 491296, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0242505073547363, "global_step": 491297, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.047630548477173, "global_step": 491298, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0722997188568115, "global_step": 491299, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0386476516723633, "global_step": 491300, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.042795419692993, "global_step": 491301, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1159145832061768, "global_step": 491302, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0932605266571045, "global_step": 491303, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0073211193084717, "global_step": 491304, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0469205379486084, "global_step": 491305, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0760984420776367, "global_step": 491306, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.041456699371338, "global_step": 491307, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0756330490112305, "global_step": 491308, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0660176277160645, "global_step": 491309, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0366132259368896, "global_step": 491310, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.053968667984009, "global_step": 491311, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1035208702087402, "global_step": 491312, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.133026123046875, "global_step": 491313, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1063785552978516, "global_step": 491314, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0488033294677734, "global_step": 491315, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0793890953063965, "global_step": 491316, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.110555410385132, "global_step": 491317, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.116420269012451, "global_step": 491318, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1364574432373047, "global_step": 491319, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1227800846099854, "global_step": 491320, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.078139066696167, "global_step": 491321, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.057398557662964, "global_step": 491322, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1073455810546875, "global_step": 491323, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0107924938201904, "global_step": 491324, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.076784372329712, "global_step": 491325, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.991695761680603, "global_step": 491326, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9639918804168701, "global_step": 491327, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1071324348449707, "global_step": 491328, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9607861042022705, "global_step": 491329, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.065455675125122, "global_step": 491330, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.012213945388794, "global_step": 491331, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.085083484649658, "global_step": 491332, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.09829044342041, "global_step": 491333, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0314037799835205, "global_step": 491334, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0313923358917236, "global_step": 491335, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0183680057525635, "global_step": 491336, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.011643886566162, "global_step": 491337, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.102480411529541, "global_step": 491338, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0678441524505615, "global_step": 491339, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9927337169647217, "global_step": 491340, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0799341201782227, "global_step": 491341, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.137185573577881, "global_step": 491342, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0500681400299072, "global_step": 491343, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1487514972686768, "global_step": 491344, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0393083095550537, "global_step": 491345, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0423834323883057, "global_step": 491346, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.060479164123535, "global_step": 491347, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.031827449798584, "global_step": 491348, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.110307455062866, "global_step": 491349, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0567550659179688, "global_step": 491350, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.018489122390747, "global_step": 491351, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.00930118560791, "global_step": 491352, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.150728225708008, "global_step": 491353, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.006588935852051, "global_step": 491354, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0507025718688965, "global_step": 491355, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1356582641601562, "global_step": 491356, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0831360816955566, "global_step": 491357, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0604567527770996, "global_step": 491358, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0528666973114014, "global_step": 491359, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9932267665863037, "global_step": 491360, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0292253494262695, "global_step": 491361, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.071122884750366, "global_step": 491362, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1279006004333496, "global_step": 491363, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.089648723602295, "global_step": 491364, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1116323471069336, "global_step": 491365, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0541648864746094, "global_step": 491366, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.087786912918091, "global_step": 491367, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.075684070587158, "global_step": 491368, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0191798210144043, "global_step": 491369, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0708799362182617, "global_step": 491370, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0109095573425293, "global_step": 491371, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0571742057800293, "global_step": 491372, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1194047927856445, "global_step": 491373, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.02531099319458, "global_step": 491374, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.181408166885376, "global_step": 491375, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.039787530899048, "global_step": 491376, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0581424236297607, "global_step": 491377, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0094785690307617, "global_step": 491378, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0409038066864014, "global_step": 491379, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9895029067993164, "global_step": 491380, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0749900341033936, "global_step": 491381, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.016555070877075, "global_step": 491382, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1343085765838623, "global_step": 491383, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0714311599731445, "global_step": 491384, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.04951810836792, "global_step": 491385, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.051278591156006, "global_step": 491386, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9998761415481567, "global_step": 491387, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1311070919036865, "global_step": 491388, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1219139099121094, "global_step": 491389, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1006290912628174, "global_step": 491390, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0831735134124756, "global_step": 491391, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0907251834869385, "global_step": 491392, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0276286602020264, "global_step": 491393, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0306599140167236, "global_step": 491394, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0611624717712402, "global_step": 491395, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1069729328155518, "global_step": 491396, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.058006525039673, "global_step": 491397, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0379199981689453, "global_step": 491398, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.126605987548828, "global_step": 491399, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1016616821289062, "global_step": 491400, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.013108730316162, "global_step": 491401, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9998292922973633, "global_step": 491402, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0651817321777344, "global_step": 491403, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.086426019668579, "global_step": 491404, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9626988172531128, "global_step": 491405, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.060891628265381, "global_step": 491406, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.095963478088379, "global_step": 491407, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0455071926116943, "global_step": 491408, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.9771887063980103, "global_step": 491409, "epoch": 856, "lr": 5e-05}
{"train_loss": 1.992628812789917, "global_step": 491410, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0389339923858643, "global_step": 491411, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1136269569396973, "global_step": 491412, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.030665874481201, "global_step": 491413, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.124025344848633, "global_step": 491414, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.0543057918548584, "global_step": 491415, "epoch": 856, "lr": 5e-05}
{"train_loss": 2.1191253662109375, "global_step": 491416, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0316197872161865, "global_step": 491417, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0773675441741943, "global_step": 491418, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0441579818725586, "global_step": 491419, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9165301322937012, "global_step": 491420, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9966251850128174, "global_step": 491421, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0241589546203613, "global_step": 491422, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0122218132019043, "global_step": 491423, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0128703117370605, "global_step": 491424, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0970473289489746, "global_step": 491425, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.054220199584961, "global_step": 491426, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.029092311859131, "global_step": 491427, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.041090726852417, "global_step": 491428, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.016327142715454, "global_step": 491429, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0447065830230713, "global_step": 491430, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.982036828994751, "global_step": 491431, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0857737064361572, "global_step": 491432, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.052236557006836, "global_step": 491433, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0797812938690186, "global_step": 491434, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0571465492248535, "global_step": 491435, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0174052715301514, "global_step": 491436, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0195465087890625, "global_step": 491437, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0440127849578857, "global_step": 491438, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0974831581115723, "global_step": 491439, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9816956520080566, "global_step": 491440, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0470714569091797, "global_step": 491441, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.026423215866089, "global_step": 491442, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.054489850997925, "global_step": 491443, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0354039669036865, "global_step": 491444, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0910372734069824, "global_step": 491445, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.037510395050049, "global_step": 491446, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0000946521759033, "global_step": 491447, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9890658855438232, "global_step": 491448, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9724706411361694, "global_step": 491449, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0609803199768066, "global_step": 491450, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0397839546203613, "global_step": 491451, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.094874858856201, "global_step": 491452, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0298664569854736, "global_step": 491453, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.030956983566284, "global_step": 491454, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9963775873184204, "global_step": 491455, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0673205852508545, "global_step": 491456, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0062103271484375, "global_step": 491457, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.012751579284668, "global_step": 491458, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.035888671875, "global_step": 491459, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.984017252922058, "global_step": 491460, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0336601734161377, "global_step": 491461, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1442103385925293, "global_step": 491462, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.98404061794281, "global_step": 491463, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0084333419799805, "global_step": 491464, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.015933036804199, "global_step": 491465, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.140136957168579, "global_step": 491466, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9906364679336548, "global_step": 491467, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.118565559387207, "global_step": 491468, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9786999225616455, "global_step": 491469, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0496037006378174, "global_step": 491470, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.061950922012329, "global_step": 491471, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.054713726043701, "global_step": 491472, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.037510871887207, "global_step": 491473, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0809977054595947, "global_step": 491474, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.063394546508789, "global_step": 491475, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.072207450866699, "global_step": 491476, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0412697792053223, "global_step": 491477, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.044072389602661, "global_step": 491478, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.073040246963501, "global_step": 491479, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.040489435195923, "global_step": 491480, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0490145683288574, "global_step": 491481, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.070840835571289, "global_step": 491482, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0818793773651123, "global_step": 491483, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.092562437057495, "global_step": 491484, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9933934211730957, "global_step": 491485, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1262381076812744, "global_step": 491486, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0469729900360107, "global_step": 491487, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.172635078430176, "global_step": 491488, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0338339805603027, "global_step": 491489, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9632456302642822, "global_step": 491490, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.038222312927246, "global_step": 491491, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0753018856048584, "global_step": 491492, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0586955547332764, "global_step": 491493, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0303072929382324, "global_step": 491494, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9885761737823486, "global_step": 491495, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9820029735565186, "global_step": 491496, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0770668983459473, "global_step": 491497, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9889559745788574, "global_step": 491498, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0268187522888184, "global_step": 491499, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.137103796005249, "global_step": 491500, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.024481773376465, "global_step": 491501, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1232972145080566, "global_step": 491502, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.056222677230835, "global_step": 491503, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0206785202026367, "global_step": 491504, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0857608318328857, "global_step": 491505, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0179667472839355, "global_step": 491506, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.190396785736084, "global_step": 491507, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0640149116516113, "global_step": 491508, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.06644606590271, "global_step": 491509, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.084965467453003, "global_step": 491510, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.016190528869629, "global_step": 491511, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0723676681518555, "global_step": 491512, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.11970591545105, "global_step": 491513, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.094796895980835, "global_step": 491514, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0601370334625244, "global_step": 491515, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0572609901428223, "global_step": 491516, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0171260833740234, "global_step": 491517, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9991185665130615, "global_step": 491518, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9966928958892822, "global_step": 491519, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0142951011657715, "global_step": 491520, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0920188426971436, "global_step": 491521, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.058459758758545, "global_step": 491522, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0442609786987305, "global_step": 491523, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.14066481590271, "global_step": 491524, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0459213256835938, "global_step": 491525, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1082329750061035, "global_step": 491526, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0866100788116455, "global_step": 491527, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0403122901916504, "global_step": 491528, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.038867235183716, "global_step": 491529, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1024153232574463, "global_step": 491530, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.071469783782959, "global_step": 491531, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9680194854736328, "global_step": 491532, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0703465938568115, "global_step": 491533, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.005852699279785, "global_step": 491534, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0700628757476807, "global_step": 491535, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9540388584136963, "global_step": 491536, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0023033618927, "global_step": 491537, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0208780765533447, "global_step": 491538, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.038501262664795, "global_step": 491539, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.019711971282959, "global_step": 491540, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.072793483734131, "global_step": 491541, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.022355556488037, "global_step": 491542, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1413381099700928, "global_step": 491543, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0313501358032227, "global_step": 491544, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.064828634262085, "global_step": 491545, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0899319648742676, "global_step": 491546, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0266547203063965, "global_step": 491547, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9851865768432617, "global_step": 491548, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9867759943008423, "global_step": 491549, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0744879245758057, "global_step": 491550, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0847480297088623, "global_step": 491551, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0501818656921387, "global_step": 491552, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9839873313903809, "global_step": 491553, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0808279514312744, "global_step": 491554, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9712063074111938, "global_step": 491555, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0487747192382812, "global_step": 491556, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0571932792663574, "global_step": 491557, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.14935302734375, "global_step": 491558, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9438960552215576, "global_step": 491559, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9978234767913818, "global_step": 491560, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.038081407546997, "global_step": 491561, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0174050331115723, "global_step": 491562, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.048370838165283, "global_step": 491563, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1455674171447754, "global_step": 491564, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9881794452667236, "global_step": 491565, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.962751865386963, "global_step": 491566, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.017399549484253, "global_step": 491567, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.046050548553467, "global_step": 491568, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.005206823348999, "global_step": 491569, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0639607906341553, "global_step": 491570, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0311574935913086, "global_step": 491571, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.999556064605713, "global_step": 491572, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0185468196868896, "global_step": 491573, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.043367624282837, "global_step": 491574, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.102447748184204, "global_step": 491575, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0656116008758545, "global_step": 491576, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1250534057617188, "global_step": 491577, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0252280235290527, "global_step": 491578, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9961564540863037, "global_step": 491579, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.061492919921875, "global_step": 491580, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0598862171173096, "global_step": 491581, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0995428562164307, "global_step": 491582, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1536738872528076, "global_step": 491583, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9990242719650269, "global_step": 491584, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1304664611816406, "global_step": 491585, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.112327814102173, "global_step": 491586, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0470025539398193, "global_step": 491587, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.000988721847534, "global_step": 491588, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.049306869506836, "global_step": 491589, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0512685775756836, "global_step": 491590, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0186989307403564, "global_step": 491591, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0163586139678955, "global_step": 491592, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0458858013153076, "global_step": 491593, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0014946460723877, "global_step": 491594, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.085139036178589, "global_step": 491595, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.076580762863159, "global_step": 491596, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0862176418304443, "global_step": 491597, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9950402975082397, "global_step": 491598, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0289368629455566, "global_step": 491599, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0808827877044678, "global_step": 491600, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0552873611450195, "global_step": 491601, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9616032838821411, "global_step": 491602, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.003304958343506, "global_step": 491603, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.116238832473755, "global_step": 491604, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9880383014678955, "global_step": 491605, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.034168243408203, "global_step": 491606, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9812387228012085, "global_step": 491607, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.098839282989502, "global_step": 491608, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.05348801612854, "global_step": 491609, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0027341842651367, "global_step": 491610, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.090477466583252, "global_step": 491611, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0530905723571777, "global_step": 491612, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.974940538406372, "global_step": 491613, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.055241107940674, "global_step": 491614, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9686945676803589, "global_step": 491615, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0494751930236816, "global_step": 491616, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9655232429504395, "global_step": 491617, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0443837642669678, "global_step": 491618, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9858301877975464, "global_step": 491619, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.09901762008667, "global_step": 491620, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1289117336273193, "global_step": 491621, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9617012739181519, "global_step": 491622, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.095869779586792, "global_step": 491623, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0296566486358643, "global_step": 491624, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.05602765083313, "global_step": 491625, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.136204719543457, "global_step": 491626, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9925822019577026, "global_step": 491627, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0698800086975098, "global_step": 491628, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.06715726852417, "global_step": 491629, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9021177291870117, "global_step": 491630, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0731797218322754, "global_step": 491631, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.027979850769043, "global_step": 491632, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.997818112373352, "global_step": 491633, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0000364780426025, "global_step": 491634, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1598265171051025, "global_step": 491635, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1091744899749756, "global_step": 491636, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0224218368530273, "global_step": 491637, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0821774005889893, "global_step": 491638, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9948322772979736, "global_step": 491639, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9584059715270996, "global_step": 491640, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.050971269607544, "global_step": 491641, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0189919471740723, "global_step": 491642, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.046168565750122, "global_step": 491643, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0481934547424316, "global_step": 491644, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.051102638244629, "global_step": 491645, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.065412998199463, "global_step": 491646, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.016737699508667, "global_step": 491647, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0408897399902344, "global_step": 491648, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0379397869110107, "global_step": 491649, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.064687490463257, "global_step": 491650, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.051992177963257, "global_step": 491651, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0888466835021973, "global_step": 491652, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1169376373291016, "global_step": 491653, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0611674785614014, "global_step": 491654, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.964799404144287, "global_step": 491655, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.109532117843628, "global_step": 491656, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1061394214630127, "global_step": 491657, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.080369472503662, "global_step": 491658, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0453941822052, "global_step": 491659, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.036614418029785, "global_step": 491660, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0791029930114746, "global_step": 491661, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.095226526260376, "global_step": 491662, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.08380126953125, "global_step": 491663, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0000078678131104, "global_step": 491664, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.047271966934204, "global_step": 491665, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.097499132156372, "global_step": 491666, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0011701583862305, "global_step": 491667, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.09438419342041, "global_step": 491668, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0700035095214844, "global_step": 491669, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.959769606590271, "global_step": 491670, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0224061012268066, "global_step": 491671, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1243011951446533, "global_step": 491672, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.096196413040161, "global_step": 491673, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9874022006988525, "global_step": 491674, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1203877925872803, "global_step": 491675, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0227932929992676, "global_step": 491676, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.010871171951294, "global_step": 491677, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.032635450363159, "global_step": 491678, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0349369049072266, "global_step": 491679, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9915409088134766, "global_step": 491680, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9742555618286133, "global_step": 491681, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.086566925048828, "global_step": 491682, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0550739765167236, "global_step": 491683, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9580022096633911, "global_step": 491684, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.101871967315674, "global_step": 491685, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.068082094192505, "global_step": 491686, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.100759983062744, "global_step": 491687, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.981156826019287, "global_step": 491688, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.072993755340576, "global_step": 491689, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0780415534973145, "global_step": 491690, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0369820594787598, "global_step": 491691, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.060706615447998, "global_step": 491692, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.096611738204956, "global_step": 491693, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1551761627197266, "global_step": 491694, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1354095935821533, "global_step": 491695, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.035635232925415, "global_step": 491696, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1041553020477295, "global_step": 491697, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1329901218414307, "global_step": 491698, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0542972087860107, "global_step": 491699, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.052924633026123, "global_step": 491700, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.010462999343872, "global_step": 491701, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.112997055053711, "global_step": 491702, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0213282108306885, "global_step": 491703, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0557138919830322, "global_step": 491704, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0917537212371826, "global_step": 491705, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.114161252975464, "global_step": 491706, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.041079044342041, "global_step": 491707, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0817103385925293, "global_step": 491708, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0754292011260986, "global_step": 491709, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.043222188949585, "global_step": 491710, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.131751775741577, "global_step": 491711, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0442984104156494, "global_step": 491712, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0178322792053223, "global_step": 491713, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0345306396484375, "global_step": 491714, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1327786445617676, "global_step": 491715, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.009385347366333, "global_step": 491716, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0989341735839844, "global_step": 491717, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0953991413116455, "global_step": 491718, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0600883960723877, "global_step": 491719, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0609216690063477, "global_step": 491720, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.085780620574951, "global_step": 491721, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1313960552215576, "global_step": 491722, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0003299713134766, "global_step": 491723, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9810599088668823, "global_step": 491724, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9858555793762207, "global_step": 491725, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.004760265350342, "global_step": 491726, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.053300380706787, "global_step": 491727, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0323445796966553, "global_step": 491728, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9580891132354736, "global_step": 491729, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.043593168258667, "global_step": 491730, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.095162868499756, "global_step": 491731, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0745184421539307, "global_step": 491732, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0397396087646484, "global_step": 491733, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.085031747817993, "global_step": 491734, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9713424444198608, "global_step": 491735, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0657594203948975, "global_step": 491736, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.062248945236206, "global_step": 491737, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.051908493041992, "global_step": 491738, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0452537536621094, "global_step": 491739, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0807173252105713, "global_step": 491740, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.076112747192383, "global_step": 491741, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.109987497329712, "global_step": 491742, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0214545726776123, "global_step": 491743, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.08516001701355, "global_step": 491744, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0551068782806396, "global_step": 491745, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9762845039367676, "global_step": 491746, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0937414169311523, "global_step": 491747, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0405290126800537, "global_step": 491748, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.99198579788208, "global_step": 491749, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1440987586975098, "global_step": 491750, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0542855262756348, "global_step": 491751, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0682692527770996, "global_step": 491752, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9837937355041504, "global_step": 491753, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.053743600845337, "global_step": 491754, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0623347759246826, "global_step": 491755, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.028777837753296, "global_step": 491756, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0260519981384277, "global_step": 491757, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.8931955099105835, "global_step": 491758, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1430232524871826, "global_step": 491759, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.075943946838379, "global_step": 491760, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9826449155807495, "global_step": 491761, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.020185947418213, "global_step": 491762, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1098642349243164, "global_step": 491763, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.062999725341797, "global_step": 491764, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.032764196395874, "global_step": 491765, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0534262657165527, "global_step": 491766, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.021562099456787, "global_step": 491767, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.038022994995117, "global_step": 491768, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0181896686553955, "global_step": 491769, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.074708938598633, "global_step": 491770, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.8799827098846436, "global_step": 491771, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0425221920013428, "global_step": 491772, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.102051258087158, "global_step": 491773, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0073790550231934, "global_step": 491774, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0657758712768555, "global_step": 491775, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0535495281219482, "global_step": 491776, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.048292875289917, "global_step": 491777, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0243756771087646, "global_step": 491778, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1227636337280273, "global_step": 491779, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.02840256690979, "global_step": 491780, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.113189220428467, "global_step": 491781, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.124201536178589, "global_step": 491782, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.069638729095459, "global_step": 491783, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0787439346313477, "global_step": 491784, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.053499460220337, "global_step": 491785, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.110424518585205, "global_step": 491786, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.991105556488037, "global_step": 491787, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.074394702911377, "global_step": 491788, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.085216999053955, "global_step": 491789, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.054704189300537, "global_step": 491790, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.073326587677002, "global_step": 491791, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.098388671875, "global_step": 491792, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9800790548324585, "global_step": 491793, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9897704124450684, "global_step": 491794, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0438318252563477, "global_step": 491795, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0480380058288574, "global_step": 491796, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0538017749786377, "global_step": 491797, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.088153600692749, "global_step": 491798, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0917108058929443, "global_step": 491799, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0608620643615723, "global_step": 491800, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9208810329437256, "global_step": 491801, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9489412307739258, "global_step": 491802, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.028247356414795, "global_step": 491803, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0805823802948, "global_step": 491804, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.099799633026123, "global_step": 491805, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0951242446899414, "global_step": 491806, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9823881387710571, "global_step": 491807, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.015338182449341, "global_step": 491808, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0560336112976074, "global_step": 491809, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0656204223632812, "global_step": 491810, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.999159574508667, "global_step": 491811, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.024468183517456, "global_step": 491812, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0825510025024414, "global_step": 491813, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.043761730194092, "global_step": 491814, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0182158946990967, "global_step": 491815, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.94775390625, "global_step": 491816, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0425755977630615, "global_step": 491817, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.014500379562378, "global_step": 491818, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0614006519317627, "global_step": 491819, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0928080081939697, "global_step": 491820, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0509727001190186, "global_step": 491821, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.069960355758667, "global_step": 491822, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0491912364959717, "global_step": 491823, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0151307582855225, "global_step": 491824, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.028501510620117, "global_step": 491825, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.062957763671875, "global_step": 491826, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1283254623413086, "global_step": 491827, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.048175573348999, "global_step": 491828, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1038818359375, "global_step": 491829, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.036025285720825, "global_step": 491830, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0983152389526367, "global_step": 491831, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.056489944458008, "global_step": 491832, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.064368486404419, "global_step": 491833, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1178317070007324, "global_step": 491834, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.009186029434204, "global_step": 491835, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9294513463974, "global_step": 491836, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0108535289764404, "global_step": 491837, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0198795795440674, "global_step": 491838, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0753278732299805, "global_step": 491839, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0943472385406494, "global_step": 491840, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0740041732788086, "global_step": 491841, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.046342134475708, "global_step": 491842, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0188233852386475, "global_step": 491843, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0150725841522217, "global_step": 491844, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.072446823120117, "global_step": 491845, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0850706100463867, "global_step": 491846, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0530829429626465, "global_step": 491847, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.131162643432617, "global_step": 491848, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.129469394683838, "global_step": 491849, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.090372323989868, "global_step": 491850, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0531413555145264, "global_step": 491851, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.146400213241577, "global_step": 491852, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.030503511428833, "global_step": 491853, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1188714504241943, "global_step": 491854, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0116024017333984, "global_step": 491855, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0050714015960693, "global_step": 491856, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0750529766082764, "global_step": 491857, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0694515705108643, "global_step": 491858, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.125765800476074, "global_step": 491859, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.948828101158142, "global_step": 491860, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9957647323608398, "global_step": 491861, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0445661544799805, "global_step": 491862, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.05281400680542, "global_step": 491863, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9817148447036743, "global_step": 491864, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9445127248764038, "global_step": 491865, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0392487049102783, "global_step": 491866, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.030099391937256, "global_step": 491867, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.106996774673462, "global_step": 491868, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.026651382446289, "global_step": 491869, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.021906852722168, "global_step": 491870, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.043182611465454, "global_step": 491871, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0234453678131104, "global_step": 491872, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.060884952545166, "global_step": 491873, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0658035278320312, "global_step": 491874, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.927980661392212, "global_step": 491875, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0334441661834717, "global_step": 491876, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.056086540222168, "global_step": 491877, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.14300799369812, "global_step": 491878, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.089247703552246, "global_step": 491879, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0299596786499023, "global_step": 491880, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.044039726257324, "global_step": 491881, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.109316110610962, "global_step": 491882, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1368038654327393, "global_step": 491883, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1301746368408203, "global_step": 491884, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0416581630706787, "global_step": 491885, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.046379327774048, "global_step": 491886, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.101224660873413, "global_step": 491887, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.064965009689331, "global_step": 491888, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0418310165405273, "global_step": 491889, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.056185483932495, "global_step": 491890, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.029818058013916, "global_step": 491891, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.031952142715454, "global_step": 491892, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.087423324584961, "global_step": 491893, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9743103981018066, "global_step": 491894, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.984084963798523, "global_step": 491895, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1606640815734863, "global_step": 491896, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0671753883361816, "global_step": 491897, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.054332733154297, "global_step": 491898, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0531728267669678, "global_step": 491899, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1163642406463623, "global_step": 491900, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.019944190979004, "global_step": 491901, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0091593265533447, "global_step": 491902, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0373902320861816, "global_step": 491903, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.075441837310791, "global_step": 491904, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9914014339447021, "global_step": 491905, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.059803009033203, "global_step": 491906, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0433847904205322, "global_step": 491907, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9616588354110718, "global_step": 491908, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9726536273956299, "global_step": 491909, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.099444627761841, "global_step": 491910, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.103304624557495, "global_step": 491911, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1339223384857178, "global_step": 491912, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1171510219573975, "global_step": 491913, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.8900848627090454, "global_step": 491914, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0832526683807373, "global_step": 491915, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9667834043502808, "global_step": 491916, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9924795627593994, "global_step": 491917, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0980002880096436, "global_step": 491918, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0948805809020996, "global_step": 491919, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.058526039123535, "global_step": 491920, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9974368810653687, "global_step": 491921, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0350992679595947, "global_step": 491922, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0961110591888428, "global_step": 491923, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.032547950744629, "global_step": 491924, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1318414211273193, "global_step": 491925, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1005067825317383, "global_step": 491926, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1768009662628174, "global_step": 491927, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0664429664611816, "global_step": 491928, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0717356204986572, "global_step": 491929, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1249775886535645, "global_step": 491930, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.107300281524658, "global_step": 491931, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0566608905792236, "global_step": 491932, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0675883293151855, "global_step": 491933, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.936156988143921, "global_step": 491934, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.12744140625, "global_step": 491935, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.036857843399048, "global_step": 491936, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.136946439743042, "global_step": 491937, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0890567302703857, "global_step": 491938, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0218162536621094, "global_step": 491939, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0167834758758545, "global_step": 491940, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0170884132385254, "global_step": 491941, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.069878101348877, "global_step": 491942, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0127720832824707, "global_step": 491943, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9679802656173706, "global_step": 491944, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.117820978164673, "global_step": 491945, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.071568012237549, "global_step": 491946, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0483012199401855, "global_step": 491947, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.060458183288574, "global_step": 491948, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0503785610198975, "global_step": 491949, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9971766471862793, "global_step": 491950, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.02067494392395, "global_step": 491951, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0332374572753906, "global_step": 491952, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0174155235290527, "global_step": 491953, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0342764854431152, "global_step": 491954, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1088130474090576, "global_step": 491955, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.126814126968384, "global_step": 491956, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.047358989715576, "global_step": 491957, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.112064838409424, "global_step": 491958, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.010096549987793, "global_step": 491959, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1590912342071533, "global_step": 491960, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0917325019836426, "global_step": 491961, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.079364776611328, "global_step": 491962, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.041318416595459, "global_step": 491963, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1146323680877686, "global_step": 491964, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0128800868988037, "global_step": 491965, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.061692237854004, "global_step": 491966, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0905685424804688, "global_step": 491967, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.068024158477783, "global_step": 491968, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0696561336517334, "global_step": 491969, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1017494201660156, "global_step": 491970, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0909063816070557, "global_step": 491971, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1256051063537598, "global_step": 491972, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.129396438598633, "global_step": 491973, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.990108847618103, "global_step": 491974, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0991573333740234, "global_step": 491975, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.02363657951355, "global_step": 491976, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0952606201171875, "global_step": 491977, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1312999725341797, "global_step": 491978, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0716958045959473, "global_step": 491979, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0435760021209717, "global_step": 491980, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0915839672088623, "global_step": 491981, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0977818965911865, "global_step": 491982, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.038041591644287, "global_step": 491983, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.148768424987793, "global_step": 491984, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0171403884887695, "global_step": 491985, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0911152362823486, "global_step": 491986, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0166590213775635, "global_step": 491987, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0835416316986084, "global_step": 491988, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.101532459259033, "global_step": 491989, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.037017345428467, "global_step": 491990, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.970771312713623, "global_step": 491991, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0822901725769043, "global_step": 491992, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0553042888641357, "global_step": 491993, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0796961784362793, "global_step": 491994, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9760799407958984, "global_step": 491995, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0976572036743164, "global_step": 491996, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.054408073425293, "global_step": 491997, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0745675563812256, "global_step": 491998, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.087430715560913, "global_step": 491999, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0165855884552, "global_step": 492000, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0264105796813965, "global_step": 492001, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0780162811279297, "global_step": 492002, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.066086530685425, "global_step": 492003, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9541566371917725, "global_step": 492004, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.066136598587036, "global_step": 492005, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9927234649658203, "global_step": 492006, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.080007314682007, "global_step": 492007, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9790853261947632, "global_step": 492008, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.964646577835083, "global_step": 492009, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0737478733062744, "global_step": 492010, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.013140916824341, "global_step": 492011, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0698776245117188, "global_step": 492012, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.061245918273926, "global_step": 492013, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9517298936843872, "global_step": 492014, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0884904861450195, "global_step": 492015, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.030944347381592, "global_step": 492016, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0400185585021973, "global_step": 492017, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0670368671417236, "global_step": 492018, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9777003526687622, "global_step": 492019, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0605533123016357, "global_step": 492020, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.958707571029663, "global_step": 492021, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.039461374282837, "global_step": 492022, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9905747175216675, "global_step": 492023, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1084277629852295, "global_step": 492024, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1162846088409424, "global_step": 492025, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0244781970977783, "global_step": 492026, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.136021137237549, "global_step": 492027, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1229374408721924, "global_step": 492028, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.040365219116211, "global_step": 492029, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1331288814544678, "global_step": 492030, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.052854299545288, "global_step": 492031, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.030606746673584, "global_step": 492032, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1210861206054688, "global_step": 492033, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9763392210006714, "global_step": 492034, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0500521659851074, "global_step": 492035, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0594358444213867, "global_step": 492036, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0047481060028076, "global_step": 492037, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1081149578094482, "global_step": 492038, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0892412662506104, "global_step": 492039, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.070958137512207, "global_step": 492040, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.052476167678833, "global_step": 492041, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1018788814544678, "global_step": 492042, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.069054126739502, "global_step": 492043, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.00435733795166, "global_step": 492044, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0373764038085938, "global_step": 492045, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0610897541046143, "global_step": 492046, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.09649395942688, "global_step": 492047, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.041396379470825, "global_step": 492048, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0508968830108643, "global_step": 492049, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.037508964538574, "global_step": 492050, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.996328353881836, "global_step": 492051, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1347150802612305, "global_step": 492052, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0490214824676514, "global_step": 492053, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0086991786956787, "global_step": 492054, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0414350032806396, "global_step": 492055, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0385069847106934, "global_step": 492056, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0452818870544434, "global_step": 492057, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1572189331054688, "global_step": 492058, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1122889518737793, "global_step": 492059, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9655210971832275, "global_step": 492060, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9734224081039429, "global_step": 492061, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9827642440795898, "global_step": 492062, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.059889554977417, "global_step": 492063, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9463326930999756, "global_step": 492064, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.119321823120117, "global_step": 492065, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.043755292892456, "global_step": 492066, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1564526557922363, "global_step": 492067, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0858094692230225, "global_step": 492068, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.071225881576538, "global_step": 492069, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0887959003448486, "global_step": 492070, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.030841827392578, "global_step": 492071, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9642807245254517, "global_step": 492072, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.144390821456909, "global_step": 492073, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.112096071243286, "global_step": 492074, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9723306894302368, "global_step": 492075, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9798942804336548, "global_step": 492076, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.012525796890259, "global_step": 492077, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0334768295288086, "global_step": 492078, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0986740589141846, "global_step": 492079, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.013155460357666, "global_step": 492080, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.094911813735962, "global_step": 492081, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0910933017730713, "global_step": 492082, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.009408950805664, "global_step": 492083, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0530223846435547, "global_step": 492084, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0821971893310547, "global_step": 492085, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.099263906478882, "global_step": 492086, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0565099716186523, "global_step": 492087, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.08333683013916, "global_step": 492088, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0239760875701904, "global_step": 492089, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.01395320892334, "global_step": 492090, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.038050889968872, "global_step": 492091, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9305996894836426, "global_step": 492092, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9792683124542236, "global_step": 492093, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.98555326461792, "global_step": 492094, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0607924461364746, "global_step": 492095, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1300792694091797, "global_step": 492096, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0489614009857178, "global_step": 492097, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.043269157409668, "global_step": 492098, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0325241088867188, "global_step": 492099, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0716850757598877, "global_step": 492100, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.071622610092163, "global_step": 492101, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0164647102355957, "global_step": 492102, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0615952014923096, "global_step": 492103, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.07167649269104, "global_step": 492104, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1086997985839844, "global_step": 492105, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0611865520477295, "global_step": 492106, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.981982707977295, "global_step": 492107, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0850048065185547, "global_step": 492108, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0078446865081787, "global_step": 492109, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0257761478424072, "global_step": 492110, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0849459171295166, "global_step": 492111, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0751285552978516, "global_step": 492112, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.04156231880188, "global_step": 492113, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.06650447845459, "global_step": 492114, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0492496490478516, "global_step": 492115, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0174977779388428, "global_step": 492116, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0813255310058594, "global_step": 492117, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0410711765289307, "global_step": 492118, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.080075979232788, "global_step": 492119, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.071641206741333, "global_step": 492120, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1751708984375, "global_step": 492121, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.127819538116455, "global_step": 492122, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.020216703414917, "global_step": 492123, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1338980197906494, "global_step": 492124, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.140113592147827, "global_step": 492125, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.115271806716919, "global_step": 492126, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1435844898223877, "global_step": 492127, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0398402214050293, "global_step": 492128, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.027404546737671, "global_step": 492129, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.033283233642578, "global_step": 492130, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.110639810562134, "global_step": 492131, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.985400676727295, "global_step": 492132, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0812923908233643, "global_step": 492133, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.035120964050293, "global_step": 492134, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0778021812438965, "global_step": 492135, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.103928565979004, "global_step": 492136, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0354788303375244, "global_step": 492137, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9832038879394531, "global_step": 492138, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.046973943710327, "global_step": 492139, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0589792728424072, "global_step": 492140, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1149260997772217, "global_step": 492141, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0633370876312256, "global_step": 492142, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0292484760284424, "global_step": 492143, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.005652904510498, "global_step": 492144, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0862128734588623, "global_step": 492145, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1400060653686523, "global_step": 492146, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0447568893432617, "global_step": 492147, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.953582525253296, "global_step": 492148, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0428335666656494, "global_step": 492149, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0054140090942383, "global_step": 492150, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0143864154815674, "global_step": 492151, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0719099044799805, "global_step": 492152, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0704329013824463, "global_step": 492153, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9874361753463745, "global_step": 492154, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.096463203430176, "global_step": 492155, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.086974620819092, "global_step": 492156, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.110720634460449, "global_step": 492157, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0242807865142822, "global_step": 492158, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.149524450302124, "global_step": 492159, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0144119262695312, "global_step": 492160, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.08176851272583, "global_step": 492161, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0571341514587402, "global_step": 492162, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0584442615509033, "global_step": 492163, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.059343099594116, "global_step": 492164, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.061583995819092, "global_step": 492165, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0236194133758545, "global_step": 492166, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0914461612701416, "global_step": 492167, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9864182472229004, "global_step": 492168, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.109372138977051, "global_step": 492169, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0630807876586914, "global_step": 492170, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9643559455871582, "global_step": 492171, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.030726194381714, "global_step": 492172, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0935170650482178, "global_step": 492173, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.070876359939575, "global_step": 492174, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.027609348297119, "global_step": 492175, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1212852001190186, "global_step": 492176, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0273587703704834, "global_step": 492177, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1859755516052246, "global_step": 492178, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9522162675857544, "global_step": 492179, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.082974672317505, "global_step": 492180, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.011662006378174, "global_step": 492181, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9632036685943604, "global_step": 492182, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.142554521560669, "global_step": 492183, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0175650119781494, "global_step": 492184, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0824012756347656, "global_step": 492185, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.145073890686035, "global_step": 492186, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.2080495357513428, "global_step": 492187, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.065202236175537, "global_step": 492188, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9967925548553467, "global_step": 492189, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.084409475326538, "global_step": 492190, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.119342088699341, "global_step": 492191, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0987327098846436, "global_step": 492192, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.089237689971924, "global_step": 492193, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.030933141708374, "global_step": 492194, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.099560022354126, "global_step": 492195, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0314173698425293, "global_step": 492196, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0812346935272217, "global_step": 492197, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.048431634902954, "global_step": 492198, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.995914101600647, "global_step": 492199, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9458965063095093, "global_step": 492200, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.007920026779175, "global_step": 492201, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9655104875564575, "global_step": 492202, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0924506187438965, "global_step": 492203, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9743059873580933, "global_step": 492204, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0383238792419434, "global_step": 492205, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1124095916748047, "global_step": 492206, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.993859052658081, "global_step": 492207, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0684938430786133, "global_step": 492208, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0728273391723633, "global_step": 492209, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0920684337615967, "global_step": 492210, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0090982913970947, "global_step": 492211, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0747110843658447, "global_step": 492212, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1167685985565186, "global_step": 492213, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0996711254119873, "global_step": 492214, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.097135305404663, "global_step": 492215, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.100571870803833, "global_step": 492216, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1024606227874756, "global_step": 492217, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.04229998588562, "global_step": 492218, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9763063192367554, "global_step": 492219, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0772290229797363, "global_step": 492220, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0652530193328857, "global_step": 492221, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0012238025665283, "global_step": 492222, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.039957046508789, "global_step": 492223, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0575315952301025, "global_step": 492224, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.041149377822876, "global_step": 492225, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.055701732635498, "global_step": 492226, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1260414123535156, "global_step": 492227, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9561519622802734, "global_step": 492228, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.063209056854248, "global_step": 492229, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9728963375091553, "global_step": 492230, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.059800148010254, "global_step": 492231, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.131540298461914, "global_step": 492232, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0657124519348145, "global_step": 492233, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0635242462158203, "global_step": 492234, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0761914253234863, "global_step": 492235, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0528528690338135, "global_step": 492236, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1450796127319336, "global_step": 492237, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0979301929473877, "global_step": 492238, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0564842224121094, "global_step": 492239, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0395054817199707, "global_step": 492240, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0742878913879395, "global_step": 492241, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0428953170776367, "global_step": 492242, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0496649742126465, "global_step": 492243, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0844779014587402, "global_step": 492244, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0609452724456787, "global_step": 492245, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.96098792552948, "global_step": 492246, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.039400100708008, "global_step": 492247, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0610387325286865, "global_step": 492248, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.047077178955078, "global_step": 492249, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.065702199935913, "global_step": 492250, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1127777099609375, "global_step": 492251, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.165168285369873, "global_step": 492252, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0251667499542236, "global_step": 492253, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0455167293548584, "global_step": 492254, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.043152332305908, "global_step": 492255, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9901010990142822, "global_step": 492256, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0577163696289062, "global_step": 492257, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.991457462310791, "global_step": 492258, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0333199501037598, "global_step": 492259, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1462531089782715, "global_step": 492260, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1319093704223633, "global_step": 492261, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1147732734680176, "global_step": 492262, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0491933822631836, "global_step": 492263, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0619516372680664, "global_step": 492264, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0252981185913086, "global_step": 492265, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.112596035003662, "global_step": 492266, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1822805404663086, "global_step": 492267, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.072700023651123, "global_step": 492268, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0410332679748535, "global_step": 492269, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0126638412475586, "global_step": 492270, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9709935188293457, "global_step": 492271, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0654220581054688, "global_step": 492272, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0081560611724854, "global_step": 492273, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0466232299804688, "global_step": 492274, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.10439395904541, "global_step": 492275, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0966343879699707, "global_step": 492276, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.10070538520813, "global_step": 492277, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0275402069091797, "global_step": 492278, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.123807668685913, "global_step": 492279, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.040337562561035, "global_step": 492280, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0236783027648926, "global_step": 492281, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0991969108581543, "global_step": 492282, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0725152492523193, "global_step": 492283, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.946697473526001, "global_step": 492284, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.097862958908081, "global_step": 492285, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0888278484344482, "global_step": 492286, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0478758811950684, "global_step": 492287, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0675113201141357, "global_step": 492288, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.09584641456604, "global_step": 492289, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0604422092437744, "global_step": 492290, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.061757802963257, "global_step": 492291, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0907704830169678, "global_step": 492292, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.129321336746216, "global_step": 492293, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.064528465270996, "global_step": 492294, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.123502731323242, "global_step": 492295, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.092088460922241, "global_step": 492296, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0357091426849365, "global_step": 492297, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0628323554992676, "global_step": 492298, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.121427536010742, "global_step": 492299, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.008262872695923, "global_step": 492300, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9928117990493774, "global_step": 492301, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.106470823287964, "global_step": 492302, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.06195330619812, "global_step": 492303, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0223474502563477, "global_step": 492304, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.048008680343628, "global_step": 492305, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.135507583618164, "global_step": 492306, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0770978927612305, "global_step": 492307, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0857536792755127, "global_step": 492308, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0320870876312256, "global_step": 492309, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0996296405792236, "global_step": 492310, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.11432147026062, "global_step": 492311, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.000075578689575, "global_step": 492312, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0401113033294678, "global_step": 492313, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.047790765762329, "global_step": 492314, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0960233211517334, "global_step": 492315, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.114786148071289, "global_step": 492316, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0451295375823975, "global_step": 492317, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1160449981689453, "global_step": 492318, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.165156841278076, "global_step": 492319, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1074798107147217, "global_step": 492320, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.093656301498413, "global_step": 492321, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.089811325073242, "global_step": 492322, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0147993564605713, "global_step": 492323, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0142054557800293, "global_step": 492324, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.098543882369995, "global_step": 492325, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0397374629974365, "global_step": 492326, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0296690464019775, "global_step": 492327, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9756983518600464, "global_step": 492328, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1161739826202393, "global_step": 492329, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9956434965133667, "global_step": 492330, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0385477542877197, "global_step": 492331, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.080061197280884, "global_step": 492332, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9935871362686157, "global_step": 492333, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.110144853591919, "global_step": 492334, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0840578079223633, "global_step": 492335, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.114114761352539, "global_step": 492336, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.118438720703125, "global_step": 492337, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0417966842651367, "global_step": 492338, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.043060302734375, "global_step": 492339, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0889456272125244, "global_step": 492340, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.123483657836914, "global_step": 492341, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0386624336242676, "global_step": 492342, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0677058696746826, "global_step": 492343, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0711145401000977, "global_step": 492344, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0920114517211914, "global_step": 492345, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0615768432617188, "global_step": 492346, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.049452066421509, "global_step": 492347, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9823431968688965, "global_step": 492348, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.046842336654663, "global_step": 492349, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.014064073562622, "global_step": 492350, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.021056652069092, "global_step": 492351, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.102715492248535, "global_step": 492352, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0633881092071533, "global_step": 492353, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9900898933410645, "global_step": 492354, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.020989179611206, "global_step": 492355, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.011641025543213, "global_step": 492356, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.109607696533203, "global_step": 492357, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.052816867828369, "global_step": 492358, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0571627616882324, "global_step": 492359, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.049208641052246, "global_step": 492360, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.103489398956299, "global_step": 492361, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0408873558044434, "global_step": 492362, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.065540075302124, "global_step": 492363, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9632407426834106, "global_step": 492364, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.085463285446167, "global_step": 492365, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0798001289367676, "global_step": 492366, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0516366958618164, "global_step": 492367, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0339510440826416, "global_step": 492368, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.065340757369995, "global_step": 492369, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0350358486175537, "global_step": 492370, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.076911211013794, "global_step": 492371, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.029606580734253, "global_step": 492372, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0591390132904053, "global_step": 492373, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.108656167984009, "global_step": 492374, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1168112754821777, "global_step": 492375, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.054872751235962, "global_step": 492376, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9671329259872437, "global_step": 492377, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1716575622558594, "global_step": 492378, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0045087337493896, "global_step": 492379, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.0591161251068115, "global_step": 492380, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.1250054836273193, "global_step": 492381, "epoch": 857, "lr": 5e-05}
{"train_loss": 1.9860272407531738, "global_step": 492382, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.066108226776123, "global_step": 492383, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.053617477416992, "global_step": 492384, "epoch": 857, "lr": 5e-05}
{"train_loss": 2.042311668395996, "global_step": 492385, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.029542922973633, "global_step": 492386, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0743510723114014, "global_step": 492387, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.04154109954834, "global_step": 492388, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0481367111206055, "global_step": 492389, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0944201946258545, "global_step": 492390, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9727188348770142, "global_step": 492391, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.085775136947632, "global_step": 492392, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9991846084594727, "global_step": 492393, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.071953773498535, "global_step": 492394, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.095562696456909, "global_step": 492395, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0477867126464844, "global_step": 492396, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.94825279712677, "global_step": 492397, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0690951347351074, "global_step": 492398, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.981981635093689, "global_step": 492399, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0458269119262695, "global_step": 492400, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0897483825683594, "global_step": 492401, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.091182231903076, "global_step": 492402, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.025453805923462, "global_step": 492403, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.085242509841919, "global_step": 492404, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9926797151565552, "global_step": 492405, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0772154331207275, "global_step": 492406, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.012944459915161, "global_step": 492407, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.005944013595581, "global_step": 492408, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0964720249176025, "global_step": 492409, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0465595722198486, "global_step": 492410, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0377085208892822, "global_step": 492411, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.011599063873291, "global_step": 492412, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0312089920043945, "global_step": 492413, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.039283037185669, "global_step": 492414, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1049962043762207, "global_step": 492415, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0463509559631348, "global_step": 492416, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9703871011734009, "global_step": 492417, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0809335708618164, "global_step": 492418, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1061031818389893, "global_step": 492419, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0099804401397705, "global_step": 492420, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9905321598052979, "global_step": 492421, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0787065029144287, "global_step": 492422, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9776828289031982, "global_step": 492423, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1522438526153564, "global_step": 492424, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0399229526519775, "global_step": 492425, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1244137287139893, "global_step": 492426, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0119130611419678, "global_step": 492427, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.044358968734741, "global_step": 492428, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0282182693481445, "global_step": 492429, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.041963577270508, "global_step": 492430, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9869474172592163, "global_step": 492431, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.024970054626465, "global_step": 492432, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1602537631988525, "global_step": 492433, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0616397857666016, "global_step": 492434, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0291714668273926, "global_step": 492435, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.034020185470581, "global_step": 492436, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0568084716796875, "global_step": 492437, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9410442113876343, "global_step": 492438, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1080987453460693, "global_step": 492439, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.100219488143921, "global_step": 492440, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.096518039703369, "global_step": 492441, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.004685640335083, "global_step": 492442, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0547304153442383, "global_step": 492443, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0795345306396484, "global_step": 492444, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.019409656524658, "global_step": 492445, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.062817096710205, "global_step": 492446, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9394598007202148, "global_step": 492447, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.099775791168213, "global_step": 492448, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0519051551818848, "global_step": 492449, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.086982011795044, "global_step": 492450, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.091697931289673, "global_step": 492451, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.123922824859619, "global_step": 492452, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9732359647750854, "global_step": 492453, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.126781940460205, "global_step": 492454, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.052698850631714, "global_step": 492455, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0669474601745605, "global_step": 492456, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0599043369293213, "global_step": 492457, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9591697454452515, "global_step": 492458, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0058722496032715, "global_step": 492459, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0620839595794678, "global_step": 492460, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.060142755508423, "global_step": 492461, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9598726034164429, "global_step": 492462, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.078958749771118, "global_step": 492463, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.005937099456787, "global_step": 492464, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.093080997467041, "global_step": 492465, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9927589893341064, "global_step": 492466, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0231850147247314, "global_step": 492467, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.098914861679077, "global_step": 492468, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.086386203765869, "global_step": 492469, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0303750038146973, "global_step": 492470, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0606019496917725, "global_step": 492471, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9679304361343384, "global_step": 492472, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.983370065689087, "global_step": 492473, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9668586254119873, "global_step": 492474, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1034669876098633, "global_step": 492475, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.063390016555786, "global_step": 492476, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0462331771850586, "global_step": 492477, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1121413707733154, "global_step": 492478, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0482382774353027, "global_step": 492479, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0482654571533203, "global_step": 492480, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.975982666015625, "global_step": 492481, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.022238254547119, "global_step": 492482, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9819644689559937, "global_step": 492483, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0219852924346924, "global_step": 492484, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9286152124404907, "global_step": 492485, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0385360717773438, "global_step": 492486, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0608596801757812, "global_step": 492487, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9993582963943481, "global_step": 492488, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.096574068069458, "global_step": 492489, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.131662368774414, "global_step": 492490, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.974595546722412, "global_step": 492491, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0476200580596924, "global_step": 492492, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9872936010360718, "global_step": 492493, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0210022926330566, "global_step": 492494, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.083681106567383, "global_step": 492495, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9934324026107788, "global_step": 492496, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.030848264694214, "global_step": 492497, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0514421463012695, "global_step": 492498, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9929312467575073, "global_step": 492499, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0298092365264893, "global_step": 492500, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0936548709869385, "global_step": 492501, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1252853870391846, "global_step": 492502, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0402567386627197, "global_step": 492503, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.09090518951416, "global_step": 492504, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1077635288238525, "global_step": 492505, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0389082431793213, "global_step": 492506, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.100736618041992, "global_step": 492507, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.024402618408203, "global_step": 492508, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.069119691848755, "global_step": 492509, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.025926351547241, "global_step": 492510, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0215818881988525, "global_step": 492511, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.033682346343994, "global_step": 492512, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.032771348953247, "global_step": 492513, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0039737224578857, "global_step": 492514, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.122079372406006, "global_step": 492515, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.012457847595215, "global_step": 492516, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1121630668640137, "global_step": 492517, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0126161575317383, "global_step": 492518, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0910227298736572, "global_step": 492519, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0067830085754395, "global_step": 492520, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0852251052856445, "global_step": 492521, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.036376714706421, "global_step": 492522, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1387763023376465, "global_step": 492523, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.973796010017395, "global_step": 492524, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0124306678771973, "global_step": 492525, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.01175594329834, "global_step": 492526, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9825799465179443, "global_step": 492527, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.086545467376709, "global_step": 492528, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.027994155883789, "global_step": 492529, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.004730701446533, "global_step": 492530, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0383200645446777, "global_step": 492531, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9872478246688843, "global_step": 492532, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0250515937805176, "global_step": 492533, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.039682626724243, "global_step": 492534, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0322394371032715, "global_step": 492535, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0504848957061768, "global_step": 492536, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.031113862991333, "global_step": 492537, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.050842523574829, "global_step": 492538, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.081441879272461, "global_step": 492539, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.08331036567688, "global_step": 492540, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.043431520462036, "global_step": 492541, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9923732280731201, "global_step": 492542, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0486860275268555, "global_step": 492543, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1084911823272705, "global_step": 492544, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.040923595428467, "global_step": 492545, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9644098281860352, "global_step": 492546, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0398921966552734, "global_step": 492547, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.073330879211426, "global_step": 492548, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.010249376296997, "global_step": 492549, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1054129600524902, "global_step": 492550, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0692176818847656, "global_step": 492551, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.091672897338867, "global_step": 492552, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0737075805664062, "global_step": 492553, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0424795150756836, "global_step": 492554, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0385971069335938, "global_step": 492555, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1157448291778564, "global_step": 492556, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0784153938293457, "global_step": 492557, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0651514530181885, "global_step": 492558, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9632099866867065, "global_step": 492559, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0443828105926514, "global_step": 492560, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.093860626220703, "global_step": 492561, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.990025520324707, "global_step": 492562, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0719313621520996, "global_step": 492563, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0328211784362793, "global_step": 492564, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.016690492630005, "global_step": 492565, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.028634786605835, "global_step": 492566, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0145418643951416, "global_step": 492567, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0414419174194336, "global_step": 492568, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.070974588394165, "global_step": 492569, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.035499095916748, "global_step": 492570, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.09309983253479, "global_step": 492571, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.021571159362793, "global_step": 492572, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0750794410705566, "global_step": 492573, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0630359649658203, "global_step": 492574, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0129032135009766, "global_step": 492575, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9962021112442017, "global_step": 492576, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.996422529220581, "global_step": 492577, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.099233388900757, "global_step": 492578, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0606179237365723, "global_step": 492579, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9901673793792725, "global_step": 492580, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0492465496063232, "global_step": 492581, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.040767192840576, "global_step": 492582, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.053337812423706, "global_step": 492583, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9482231140136719, "global_step": 492584, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.061490297317505, "global_step": 492585, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1512298583984375, "global_step": 492586, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0314180850982666, "global_step": 492587, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0129494667053223, "global_step": 492588, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0300726890563965, "global_step": 492589, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0325229167938232, "global_step": 492590, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0090198516845703, "global_step": 492591, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0141689777374268, "global_step": 492592, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.03423810005188, "global_step": 492593, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9398088455200195, "global_step": 492594, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0870630741119385, "global_step": 492595, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.00553560256958, "global_step": 492596, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0596935749053955, "global_step": 492597, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0766777992248535, "global_step": 492598, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9916119575500488, "global_step": 492599, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.994922161102295, "global_step": 492600, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9594285488128662, "global_step": 492601, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9936926364898682, "global_step": 492602, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.033018112182617, "global_step": 492603, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0406386852264404, "global_step": 492604, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.116464138031006, "global_step": 492605, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1113672256469727, "global_step": 492606, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.02923846244812, "global_step": 492607, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0379934310913086, "global_step": 492608, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.046290397644043, "global_step": 492609, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0740458965301514, "global_step": 492610, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.013601303100586, "global_step": 492611, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0491178035736084, "global_step": 492612, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9995101690292358, "global_step": 492613, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0337295532226562, "global_step": 492614, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0230932235717773, "global_step": 492615, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.010788679122925, "global_step": 492616, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1062374114990234, "global_step": 492617, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0882420539855957, "global_step": 492618, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9407879114151, "global_step": 492619, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.990368366241455, "global_step": 492620, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.140038251876831, "global_step": 492621, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.106153726577759, "global_step": 492622, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0199732780456543, "global_step": 492623, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.028104305267334, "global_step": 492624, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0794620513916016, "global_step": 492625, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0045835971832275, "global_step": 492626, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.138488292694092, "global_step": 492627, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1021358966827393, "global_step": 492628, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.047409772872925, "global_step": 492629, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9403150081634521, "global_step": 492630, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.023101806640625, "global_step": 492631, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9780662059783936, "global_step": 492632, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.013655424118042, "global_step": 492633, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.108410358428955, "global_step": 492634, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1260809898376465, "global_step": 492635, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.029977798461914, "global_step": 492636, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.044027090072632, "global_step": 492637, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.157766103744507, "global_step": 492638, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0555927753448486, "global_step": 492639, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0562875270843506, "global_step": 492640, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.077637195587158, "global_step": 492641, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0521042346954346, "global_step": 492642, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0618326663970947, "global_step": 492643, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.043818235397339, "global_step": 492644, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9804071187973022, "global_step": 492645, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.972165584564209, "global_step": 492646, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0355725288391113, "global_step": 492647, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9697812795639038, "global_step": 492648, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.010209560394287, "global_step": 492649, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0272440910339355, "global_step": 492650, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.018606424331665, "global_step": 492651, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.042466402053833, "global_step": 492652, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.118591785430908, "global_step": 492653, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9751232862472534, "global_step": 492654, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.169827699661255, "global_step": 492655, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.024540424346924, "global_step": 492656, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0609662532806396, "global_step": 492657, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.013127088546753, "global_step": 492658, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.05568265914917, "global_step": 492659, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0415048599243164, "global_step": 492660, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.098062515258789, "global_step": 492661, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0878751277923584, "global_step": 492662, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.028404474258423, "global_step": 492663, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.031031608581543, "global_step": 492664, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0093421936035156, "global_step": 492665, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9463814496994019, "global_step": 492666, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0581157207489014, "global_step": 492667, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.041705846786499, "global_step": 492668, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.000166416168213, "global_step": 492669, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0096094608306885, "global_step": 492670, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0476229190826416, "global_step": 492671, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.085249185562134, "global_step": 492672, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.000635862350464, "global_step": 492673, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0481433868408203, "global_step": 492674, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0509192943573, "global_step": 492675, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0337531566619873, "global_step": 492676, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.099374532699585, "global_step": 492677, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1343166828155518, "global_step": 492678, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9859699010849, "global_step": 492679, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.077068567276001, "global_step": 492680, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.945677638053894, "global_step": 492681, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.05890154838562, "global_step": 492682, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0726821422576904, "global_step": 492683, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.065932512283325, "global_step": 492684, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.097074031829834, "global_step": 492685, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.090738534927368, "global_step": 492686, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.041236400604248, "global_step": 492687, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1002702713012695, "global_step": 492688, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.015871524810791, "global_step": 492689, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.103161573410034, "global_step": 492690, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0610759258270264, "global_step": 492691, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.043647050857544, "global_step": 492692, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.048494815826416, "global_step": 492693, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0952324867248535, "global_step": 492694, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.026397466659546, "global_step": 492695, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.059535503387451, "global_step": 492696, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0639617443084717, "global_step": 492697, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1328771114349365, "global_step": 492698, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.051903486251831, "global_step": 492699, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1590640544891357, "global_step": 492700, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1362557411193848, "global_step": 492701, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.040019989013672, "global_step": 492702, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.066295862197876, "global_step": 492703, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0613620281219482, "global_step": 492704, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.020254611968994, "global_step": 492705, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.106285572052002, "global_step": 492706, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0625720024108887, "global_step": 492707, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.081033706665039, "global_step": 492708, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0773983001708984, "global_step": 492709, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0729012489318848, "global_step": 492710, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.059297561645508, "global_step": 492711, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0162241458892822, "global_step": 492712, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0804476737976074, "global_step": 492713, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.070586919784546, "global_step": 492714, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.014239549636841, "global_step": 492715, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.04754638671875, "global_step": 492716, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.098280429840088, "global_step": 492717, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9480775594711304, "global_step": 492718, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1219873428344727, "global_step": 492719, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9957484006881714, "global_step": 492720, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.129687786102295, "global_step": 492721, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.146219491958618, "global_step": 492722, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.131650686264038, "global_step": 492723, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0884838104248047, "global_step": 492724, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1277849674224854, "global_step": 492725, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9990911483764648, "global_step": 492726, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0814409255981445, "global_step": 492727, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.008683681488037, "global_step": 492728, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.022047996520996, "global_step": 492729, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.054518938064575, "global_step": 492730, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0117671489715576, "global_step": 492731, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1116766929626465, "global_step": 492732, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.11051344871521, "global_step": 492733, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.059920310974121, "global_step": 492734, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0605640411376953, "global_step": 492735, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.043888807296753, "global_step": 492736, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0715675354003906, "global_step": 492737, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.046754837036133, "global_step": 492738, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0548999309539795, "global_step": 492739, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0836026668548584, "global_step": 492740, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0601930618286133, "global_step": 492741, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0081427097320557, "global_step": 492742, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.058067560195923, "global_step": 492743, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.007296562194824, "global_step": 492744, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9909859895706177, "global_step": 492745, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.027740478515625, "global_step": 492746, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0397634506225586, "global_step": 492747, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0600335597991943, "global_step": 492748, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.033879280090332, "global_step": 492749, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.100111961364746, "global_step": 492750, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.085852861404419, "global_step": 492751, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0102651119232178, "global_step": 492752, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.145524501800537, "global_step": 492753, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0339415073394775, "global_step": 492754, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.06103777885437, "global_step": 492755, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0942089557647705, "global_step": 492756, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.096792697906494, "global_step": 492757, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.021007537841797, "global_step": 492758, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0360488891601562, "global_step": 492759, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.111365795135498, "global_step": 492760, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0582613945007324, "global_step": 492761, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1574342250823975, "global_step": 492762, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.049506902694702, "global_step": 492763, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9784736633300781, "global_step": 492764, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.09700083732605, "global_step": 492765, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.105790853500366, "global_step": 492766, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0547027587890625, "global_step": 492767, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0260729789733887, "global_step": 492768, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.953171730041504, "global_step": 492769, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1275246143341064, "global_step": 492770, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.096320629119873, "global_step": 492771, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.086030960083008, "global_step": 492772, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0518064498901367, "global_step": 492773, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0172832012176514, "global_step": 492774, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9930833578109741, "global_step": 492775, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.100994110107422, "global_step": 492776, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.003685712814331, "global_step": 492777, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0811192989349365, "global_step": 492778, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0457565784454346, "global_step": 492779, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9649333953857422, "global_step": 492780, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.018188953399658, "global_step": 492781, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0417258739471436, "global_step": 492782, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.083730459213257, "global_step": 492783, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.070951461791992, "global_step": 492784, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.029918670654297, "global_step": 492785, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.006864309310913, "global_step": 492786, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.045039653778076, "global_step": 492787, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0488641262054443, "global_step": 492788, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.132636308670044, "global_step": 492789, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0610599517822266, "global_step": 492790, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0579652786254883, "global_step": 492791, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0737617015838623, "global_step": 492792, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.997774600982666, "global_step": 492793, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.035322666168213, "global_step": 492794, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.140171527862549, "global_step": 492795, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9910531044006348, "global_step": 492796, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0220775604248047, "global_step": 492797, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0039026737213135, "global_step": 492798, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9920763969421387, "global_step": 492799, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.052807569503784, "global_step": 492800, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.085585832595825, "global_step": 492801, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9889148473739624, "global_step": 492802, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0381526947021484, "global_step": 492803, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.050523519515991, "global_step": 492804, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.025928258895874, "global_step": 492805, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.029365301132202, "global_step": 492806, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0521292686462402, "global_step": 492807, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0380916595458984, "global_step": 492808, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0482072830200195, "global_step": 492809, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1008055210113525, "global_step": 492810, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.031236171722412, "global_step": 492811, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1041295528411865, "global_step": 492812, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0033628940582275, "global_step": 492813, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.035005569458008, "global_step": 492814, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0354738235473633, "global_step": 492815, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.077979803085327, "global_step": 492816, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0736892223358154, "global_step": 492817, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.104722023010254, "global_step": 492818, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9904024600982666, "global_step": 492819, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0021700859069824, "global_step": 492820, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9755603075027466, "global_step": 492821, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.148416042327881, "global_step": 492822, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0322704315185547, "global_step": 492823, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1301791667938232, "global_step": 492824, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9713695049285889, "global_step": 492825, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0302748680114746, "global_step": 492826, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0240120887756348, "global_step": 492827, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.063847541809082, "global_step": 492828, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0878374576568604, "global_step": 492829, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1243155002593994, "global_step": 492830, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0214991569519043, "global_step": 492831, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.007723569869995, "global_step": 492832, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1020429134368896, "global_step": 492833, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.055548906326294, "global_step": 492834, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1498863697052, "global_step": 492835, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0275659561157227, "global_step": 492836, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.098667860031128, "global_step": 492837, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0931475162506104, "global_step": 492838, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0440433025360107, "global_step": 492839, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.086702823638916, "global_step": 492840, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.138584852218628, "global_step": 492841, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1030795574188232, "global_step": 492842, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0695550441741943, "global_step": 492843, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0110297203063965, "global_step": 492844, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0790188312530518, "global_step": 492845, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1001105308532715, "global_step": 492846, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0699093341827393, "global_step": 492847, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0164151191711426, "global_step": 492848, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.098466634750366, "global_step": 492849, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1181907653808594, "global_step": 492850, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.011472225189209, "global_step": 492851, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.11246395111084, "global_step": 492852, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.013389825820923, "global_step": 492853, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1285316944122314, "global_step": 492854, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0708608627319336, "global_step": 492855, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.001272201538086, "global_step": 492856, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.046790599822998, "global_step": 492857, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0201008319854736, "global_step": 492858, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9809396266937256, "global_step": 492859, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1075897216796875, "global_step": 492860, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.024106979370117, "global_step": 492861, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0491292476654053, "global_step": 492862, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0375590324401855, "global_step": 492863, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9614309072494507, "global_step": 492864, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0103752613067627, "global_step": 492865, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.016462564468384, "global_step": 492866, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0077812671661377, "global_step": 492867, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0481159687042236, "global_step": 492868, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0451011657714844, "global_step": 492869, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.088348388671875, "global_step": 492870, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1281843185424805, "global_step": 492871, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0912625789642334, "global_step": 492872, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.994006872177124, "global_step": 492873, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9648926258087158, "global_step": 492874, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.087693691253662, "global_step": 492875, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.06199312210083, "global_step": 492876, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0828120708465576, "global_step": 492877, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1238863468170166, "global_step": 492878, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.027383804321289, "global_step": 492879, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1584668159484863, "global_step": 492880, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.09930682182312, "global_step": 492881, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.090792417526245, "global_step": 492882, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0667166709899902, "global_step": 492883, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1444191932678223, "global_step": 492884, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9874759912490845, "global_step": 492885, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.05147647857666, "global_step": 492886, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1027045249938965, "global_step": 492887, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0403707027435303, "global_step": 492888, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0433247089385986, "global_step": 492889, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0083870887756348, "global_step": 492890, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.049370288848877, "global_step": 492891, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0396111011505127, "global_step": 492892, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.092264175415039, "global_step": 492893, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.098452568054199, "global_step": 492894, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0083725452423096, "global_step": 492895, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9735277891159058, "global_step": 492896, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.086724042892456, "global_step": 492897, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.075233221054077, "global_step": 492898, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0176444053649902, "global_step": 492899, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.051971435546875, "global_step": 492900, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.010012626647949, "global_step": 492901, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0297961235046387, "global_step": 492902, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0508499145507812, "global_step": 492903, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0509579181671143, "global_step": 492904, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.155545473098755, "global_step": 492905, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.072756767272949, "global_step": 492906, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9800891876220703, "global_step": 492907, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.062302589416504, "global_step": 492908, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0427589416503906, "global_step": 492909, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.067833423614502, "global_step": 492910, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.122467041015625, "global_step": 492911, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0524704456329346, "global_step": 492912, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0923635959625244, "global_step": 492913, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.063730478286743, "global_step": 492914, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.003539562225342, "global_step": 492915, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0555591583251953, "global_step": 492916, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.099794864654541, "global_step": 492917, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0514633655548096, "global_step": 492918, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0460946559906006, "global_step": 492919, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.021223306655884, "global_step": 492920, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.2030632495880127, "global_step": 492921, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.100724697113037, "global_step": 492922, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.001927614212036, "global_step": 492923, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0910167694091797, "global_step": 492924, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0018582344055176, "global_step": 492925, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.012984275817871, "global_step": 492926, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0886714458465576, "global_step": 492927, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0781490802764893, "global_step": 492928, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9978140592575073, "global_step": 492929, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9682589769363403, "global_step": 492930, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0814733505249023, "global_step": 492931, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9694733619689941, "global_step": 492932, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.034701347351074, "global_step": 492933, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.088625192642212, "global_step": 492934, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1733291149139404, "global_step": 492935, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.023482084274292, "global_step": 492936, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.101118803024292, "global_step": 492937, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1191561222076416, "global_step": 492938, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.111412525177002, "global_step": 492939, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0609962940216064, "global_step": 492940, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.105210304260254, "global_step": 492941, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1107048988342285, "global_step": 492942, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.014540910720825, "global_step": 492943, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0096325874328613, "global_step": 492944, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0521228313446045, "global_step": 492945, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.061479091644287, "global_step": 492946, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.112419366836548, "global_step": 492947, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.129894733428955, "global_step": 492948, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9831429719924927, "global_step": 492949, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0616581439971924, "global_step": 492950, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.081350088119507, "global_step": 492951, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0535430908203125, "global_step": 492952, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0623691082000732, "global_step": 492953, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.020704746246338, "global_step": 492954, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.046612024307251, "global_step": 492955, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.068464756011963, "global_step": 492956, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0290369987487793, "global_step": 492957, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.026829481124878, "global_step": 492958, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0343575477600098, "global_step": 492959, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0882492065429688, "global_step": 492960, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9727709293365479, "global_step": 492961, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9705852270126343, "global_step": 492962, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1255955696105957, "global_step": 492963, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0502610206604004, "global_step": 492964, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.013160228729248, "global_step": 492965, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0632317066192627, "global_step": 492966, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.023130178451538, "global_step": 492967, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0951173305511475, "global_step": 492968, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.025097370147705, "global_step": 492969, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.119704246520996, "global_step": 492970, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1248931884765625, "global_step": 492971, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1082184314727783, "global_step": 492972, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0325491428375244, "global_step": 492973, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0050275325775146, "global_step": 492974, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.096238136291504, "global_step": 492975, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.068952798843384, "global_step": 492976, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0004639625549316, "global_step": 492977, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.001953125, "global_step": 492978, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.064502716064453, "global_step": 492979, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.983222484588623, "global_step": 492980, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0529749393463135, "global_step": 492981, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0799007415771484, "global_step": 492982, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.099334716796875, "global_step": 492983, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0517566204071045, "global_step": 492984, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.001864194869995, "global_step": 492985, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1060314178466797, "global_step": 492986, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9677296876907349, "global_step": 492987, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1118686199188232, "global_step": 492988, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0984513759613037, "global_step": 492989, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1484735012054443, "global_step": 492990, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1249892711639404, "global_step": 492991, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.112638235092163, "global_step": 492992, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0425479412078857, "global_step": 492993, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1584577560424805, "global_step": 492994, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.066035032272339, "global_step": 492995, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.048557996749878, "global_step": 492996, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0859885215759277, "global_step": 492997, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.08072829246521, "global_step": 492998, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.042537212371826, "global_step": 492999, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.132270336151123, "global_step": 493000, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1231279373168945, "global_step": 493001, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0233144760131836, "global_step": 493002, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.096874952316284, "global_step": 493003, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.991579294204712, "global_step": 493004, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0611395835876465, "global_step": 493005, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.177849054336548, "global_step": 493006, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0930590629577637, "global_step": 493007, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.069284200668335, "global_step": 493008, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0765209197998047, "global_step": 493009, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1018316745758057, "global_step": 493010, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0885257720947266, "global_step": 493011, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.04718017578125, "global_step": 493012, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.122710704803467, "global_step": 493013, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1024460792541504, "global_step": 493014, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1180777549743652, "global_step": 493015, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0473268032073975, "global_step": 493016, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0155842304229736, "global_step": 493017, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0184309482574463, "global_step": 493018, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.91182541847229, "global_step": 493019, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0222764015197754, "global_step": 493020, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.027709722518921, "global_step": 493021, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0001072883605957, "global_step": 493022, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.019838809967041, "global_step": 493023, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.055771827697754, "global_step": 493024, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.109675645828247, "global_step": 493025, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.029665946960449, "global_step": 493026, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0700483322143555, "global_step": 493027, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.110710382461548, "global_step": 493028, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0732944011688232, "global_step": 493029, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0980894565582275, "global_step": 493030, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.105347156524658, "global_step": 493031, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.055314779281616, "global_step": 493032, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0520882606506348, "global_step": 493033, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9252188205718994, "global_step": 493034, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.011125326156616, "global_step": 493035, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0900959968566895, "global_step": 493036, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9899656772613525, "global_step": 493037, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.028907299041748, "global_step": 493038, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0463740825653076, "global_step": 493039, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1196980476379395, "global_step": 493040, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0421721935272217, "global_step": 493041, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1118035316467285, "global_step": 493042, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.991420865058899, "global_step": 493043, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.070767402648926, "global_step": 493044, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.061612844467163, "global_step": 493045, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9744102954864502, "global_step": 493046, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0015158653259277, "global_step": 493047, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0680348873138428, "global_step": 493048, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.156681776046753, "global_step": 493049, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0678982734680176, "global_step": 493050, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.090118885040283, "global_step": 493051, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0347821712493896, "global_step": 493052, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0779943466186523, "global_step": 493053, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0883893966674805, "global_step": 493054, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0141708850860596, "global_step": 493055, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.067241907119751, "global_step": 493056, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0873801708221436, "global_step": 493057, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.045762062072754, "global_step": 493058, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0244388580322266, "global_step": 493059, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0968236923217773, "global_step": 493060, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.094465732574463, "global_step": 493061, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0339012145996094, "global_step": 493062, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0320382118225098, "global_step": 493063, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1073594093322754, "global_step": 493064, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.033902645111084, "global_step": 493065, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9989185333251953, "global_step": 493066, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.030797243118286, "global_step": 493067, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.163271188735962, "global_step": 493068, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9776488542556763, "global_step": 493069, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.121746778488159, "global_step": 493070, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.062938928604126, "global_step": 493071, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1271283626556396, "global_step": 493072, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.051063060760498, "global_step": 493073, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0051932334899902, "global_step": 493074, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9953620433807373, "global_step": 493075, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.034397602081299, "global_step": 493076, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.067397117614746, "global_step": 493077, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1231918334960938, "global_step": 493078, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.964492917060852, "global_step": 493079, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0629396438598633, "global_step": 493080, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.042233467102051, "global_step": 493081, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1193249225616455, "global_step": 493082, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0839884281158447, "global_step": 493083, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.118835687637329, "global_step": 493084, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0897645950317383, "global_step": 493085, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0533080101013184, "global_step": 493086, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.098065137863159, "global_step": 493087, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0071122646331787, "global_step": 493088, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0407965183258057, "global_step": 493089, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0610666275024414, "global_step": 493090, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0156567096710205, "global_step": 493091, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.041030168533325, "global_step": 493092, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.123697280883789, "global_step": 493093, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.075140953063965, "global_step": 493094, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.106463670730591, "global_step": 493095, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0258827209472656, "global_step": 493096, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.033357858657837, "global_step": 493097, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0413901805877686, "global_step": 493098, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0849738121032715, "global_step": 493099, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0310182571411133, "global_step": 493100, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9647786617279053, "global_step": 493101, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0328524112701416, "global_step": 493102, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.041835069656372, "global_step": 493103, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.163835287094116, "global_step": 493104, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.059931755065918, "global_step": 493105, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.061638593673706, "global_step": 493106, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1101584434509277, "global_step": 493107, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.028839588165283, "global_step": 493108, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.012876272201538, "global_step": 493109, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0988943576812744, "global_step": 493110, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0475239753723145, "global_step": 493111, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.095181703567505, "global_step": 493112, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0743608474731445, "global_step": 493113, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.022926092147827, "global_step": 493114, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.972137212753296, "global_step": 493115, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0967788696289062, "global_step": 493116, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1244258880615234, "global_step": 493117, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.098597288131714, "global_step": 493118, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0852837562561035, "global_step": 493119, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.056910753250122, "global_step": 493120, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.028766632080078, "global_step": 493121, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9562642574310303, "global_step": 493122, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.079625129699707, "global_step": 493123, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.999746322631836, "global_step": 493124, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0710153579711914, "global_step": 493125, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0008013248443604, "global_step": 493126, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.060849905014038, "global_step": 493127, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.118994951248169, "global_step": 493128, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.005584478378296, "global_step": 493129, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.133967876434326, "global_step": 493130, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.039470672607422, "global_step": 493131, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.008423328399658, "global_step": 493132, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0212936401367188, "global_step": 493133, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0295474529266357, "global_step": 493134, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1118555068969727, "global_step": 493135, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0191991329193115, "global_step": 493136, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1150262355804443, "global_step": 493137, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.110546112060547, "global_step": 493138, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1089348793029785, "global_step": 493139, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.014653205871582, "global_step": 493140, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0546317100524902, "global_step": 493141, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.056187868118286, "global_step": 493142, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.045511245727539, "global_step": 493143, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.087531805038452, "global_step": 493144, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0665299892425537, "global_step": 493145, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0398924350738525, "global_step": 493146, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0079293251037598, "global_step": 493147, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.092471122741699, "global_step": 493148, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0301570892333984, "global_step": 493149, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0766751766204834, "global_step": 493150, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0227038860321045, "global_step": 493151, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0350842475891113, "global_step": 493152, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0843586921691895, "global_step": 493153, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.12754225730896, "global_step": 493154, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1314303874969482, "global_step": 493155, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.041973829269409, "global_step": 493156, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0260229110717773, "global_step": 493157, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.110837936401367, "global_step": 493158, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.043015718460083, "global_step": 493159, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9473258256912231, "global_step": 493160, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.050295352935791, "global_step": 493161, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0646698474884033, "global_step": 493162, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1389636993408203, "global_step": 493163, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.060842514038086, "global_step": 493164, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.060786485671997, "global_step": 493165, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1211049556732178, "global_step": 493166, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0491137504577637, "global_step": 493167, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.978668451309204, "global_step": 493168, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.12374210357666, "global_step": 493169, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0309624671936035, "global_step": 493170, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9692065715789795, "global_step": 493171, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0720160007476807, "global_step": 493172, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1254544258117676, "global_step": 493173, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9833678007125854, "global_step": 493174, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.050307273864746, "global_step": 493175, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0695929527282715, "global_step": 493176, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.007603645324707, "global_step": 493177, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.150235176086426, "global_step": 493178, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.058032751083374, "global_step": 493179, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.068983316421509, "global_step": 493180, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.993950366973877, "global_step": 493181, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.043972969055176, "global_step": 493182, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0333244800567627, "global_step": 493183, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1200428009033203, "global_step": 493184, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.088358163833618, "global_step": 493185, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.081333875656128, "global_step": 493186, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9426236152648926, "global_step": 493187, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1013712882995605, "global_step": 493188, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.016417980194092, "global_step": 493189, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.095562696456909, "global_step": 493190, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.104670763015747, "global_step": 493191, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.11413836479187, "global_step": 493192, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0242879390716553, "global_step": 493193, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.020519256591797, "global_step": 493194, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.032527208328247, "global_step": 493195, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0493502616882324, "global_step": 493196, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.071610450744629, "global_step": 493197, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0692899227142334, "global_step": 493198, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.08243989944458, "global_step": 493199, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9795317649841309, "global_step": 493200, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.100332736968994, "global_step": 493201, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9889872074127197, "global_step": 493202, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.060570478439331, "global_step": 493203, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.057842969894409, "global_step": 493204, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0773253440856934, "global_step": 493205, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.056896924972534, "global_step": 493206, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0495917797088623, "global_step": 493207, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.019749164581299, "global_step": 493208, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1174895763397217, "global_step": 493209, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.058872938156128, "global_step": 493210, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0595951080322266, "global_step": 493211, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1086416244506836, "global_step": 493212, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1235735416412354, "global_step": 493213, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0142264366149902, "global_step": 493214, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0559303760528564, "global_step": 493215, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1704580783843994, "global_step": 493216, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.12819504737854, "global_step": 493217, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.073751926422119, "global_step": 493218, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0691304206848145, "global_step": 493219, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0512495040893555, "global_step": 493220, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0686001777648926, "global_step": 493221, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.028899669647217, "global_step": 493222, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.129030704498291, "global_step": 493223, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0614430904388428, "global_step": 493224, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.091059923171997, "global_step": 493225, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0185706615448, "global_step": 493226, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.078906297683716, "global_step": 493227, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.062131881713867, "global_step": 493228, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.100586175918579, "global_step": 493229, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0814733505249023, "global_step": 493230, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1630821228027344, "global_step": 493231, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.047649621963501, "global_step": 493232, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.020785093307495, "global_step": 493233, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.081655263900757, "global_step": 493234, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9709892272949219, "global_step": 493235, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0508248805999756, "global_step": 493236, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.140624761581421, "global_step": 493237, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.010075092315674, "global_step": 493238, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0759830474853516, "global_step": 493239, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0375797748565674, "global_step": 493240, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0343027114868164, "global_step": 493241, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.086270570755005, "global_step": 493242, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.078514575958252, "global_step": 493243, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1089212894439697, "global_step": 493244, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.086989641189575, "global_step": 493245, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0740292072296143, "global_step": 493246, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0149500370025635, "global_step": 493247, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9977762699127197, "global_step": 493248, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.977447509765625, "global_step": 493249, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.011380672454834, "global_step": 493250, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0968964099884033, "global_step": 493251, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0650634765625, "global_step": 493252, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.066166877746582, "global_step": 493253, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.128469705581665, "global_step": 493254, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.988657832145691, "global_step": 493255, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.043975830078125, "global_step": 493256, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0656347274780273, "global_step": 493257, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0704925060272217, "global_step": 493258, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.039851665496826, "global_step": 493259, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1006171703338623, "global_step": 493260, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0312960147857666, "global_step": 493261, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0595569610595703, "global_step": 493262, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9616235494613647, "global_step": 493263, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9880175590515137, "global_step": 493264, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1783111095428467, "global_step": 493265, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0821280479431152, "global_step": 493266, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0815796852111816, "global_step": 493267, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.017137050628662, "global_step": 493268, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1084578037261963, "global_step": 493269, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1125268936157227, "global_step": 493270, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0835530757904053, "global_step": 493271, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.039064645767212, "global_step": 493272, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9673995971679688, "global_step": 493273, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0777952671051025, "global_step": 493274, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.050957202911377, "global_step": 493275, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.166612386703491, "global_step": 493276, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1114461421966553, "global_step": 493277, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0902271270751953, "global_step": 493278, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.042574167251587, "global_step": 493279, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0429937839508057, "global_step": 493280, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.017512798309326, "global_step": 493281, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0462586879730225, "global_step": 493282, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.004404306411743, "global_step": 493283, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0235962867736816, "global_step": 493284, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.153876304626465, "global_step": 493285, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9699450731277466, "global_step": 493286, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.08048939704895, "global_step": 493287, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0839924812316895, "global_step": 493288, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.030870199203491, "global_step": 493289, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0732297897338867, "global_step": 493290, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1667563915252686, "global_step": 493291, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0934505462646484, "global_step": 493292, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9978059530258179, "global_step": 493293, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0252132415771484, "global_step": 493294, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1298739910125732, "global_step": 493295, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0929195880889893, "global_step": 493296, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0068068504333496, "global_step": 493297, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.067702293395996, "global_step": 493298, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0035014152526855, "global_step": 493299, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9683442115783691, "global_step": 493300, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0999720096588135, "global_step": 493301, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.121579647064209, "global_step": 493302, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.038433313369751, "global_step": 493303, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0707178115844727, "global_step": 493304, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0779097080230713, "global_step": 493305, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.107520818710327, "global_step": 493306, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.042935848236084, "global_step": 493307, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0797512531280518, "global_step": 493308, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1315977573394775, "global_step": 493309, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.06941819190979, "global_step": 493310, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.083754539489746, "global_step": 493311, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0421066284179688, "global_step": 493312, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.186450242996216, "global_step": 493313, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.039297342300415, "global_step": 493314, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.079155445098877, "global_step": 493315, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0855138301849365, "global_step": 493316, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.084956645965576, "global_step": 493317, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.024460792541504, "global_step": 493318, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.140197515487671, "global_step": 493319, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9772717952728271, "global_step": 493320, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.046241521835327, "global_step": 493321, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.028914451599121, "global_step": 493322, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.086552619934082, "global_step": 493323, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.025324821472168, "global_step": 493324, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.05739426612854, "global_step": 493325, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0289554595947266, "global_step": 493326, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1052136421203613, "global_step": 493327, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0215439796447754, "global_step": 493328, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1151282787323, "global_step": 493329, "epoch": 858, "lr": 5e-05}
{"train_loss": 1.9709997177124023, "global_step": 493330, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0876381397247314, "global_step": 493331, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.110973358154297, "global_step": 493332, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.046128034591675, "global_step": 493333, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0512449741363525, "global_step": 493334, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0069668292999268, "global_step": 493335, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1101083755493164, "global_step": 493336, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1037325859069824, "global_step": 493337, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.055769443511963, "global_step": 493338, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.046217441558838, "global_step": 493339, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.124654769897461, "global_step": 493340, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.064458131790161, "global_step": 493341, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0576229095458984, "global_step": 493342, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.112971782684326, "global_step": 493343, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.083726644515991, "global_step": 493344, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0277018547058105, "global_step": 493345, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0336215496063232, "global_step": 493346, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0159225463867188, "global_step": 493347, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0470142364501953, "global_step": 493348, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0190978050231934, "global_step": 493349, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0803635120391846, "global_step": 493350, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.154930591583252, "global_step": 493351, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0210959911346436, "global_step": 493352, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.0546345710754395, "global_step": 493353, "epoch": 858, "lr": 5e-05}
{"train_loss": 2.1045053005218506, "global_step": 493354, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.137474298477173, "global_step": 493355, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9470691680908203, "global_step": 493356, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.045067071914673, "global_step": 493357, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.03611421585083, "global_step": 493358, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.01335072517395, "global_step": 493359, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0228381156921387, "global_step": 493360, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0236423015594482, "global_step": 493361, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.207824945449829, "global_step": 493362, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9675956964492798, "global_step": 493363, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.105222702026367, "global_step": 493364, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.03718900680542, "global_step": 493365, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9632318019866943, "global_step": 493366, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0851364135742188, "global_step": 493367, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.039198160171509, "global_step": 493368, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0383503437042236, "global_step": 493369, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1011948585510254, "global_step": 493370, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.098745822906494, "global_step": 493371, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0628128051757812, "global_step": 493372, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0655558109283447, "global_step": 493373, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1022253036499023, "global_step": 493374, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0399439334869385, "global_step": 493375, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.03143310546875, "global_step": 493376, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0285327434539795, "global_step": 493377, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9856287240982056, "global_step": 493378, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0423996448516846, "global_step": 493379, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9753777980804443, "global_step": 493380, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0117499828338623, "global_step": 493381, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0989530086517334, "global_step": 493382, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.001312255859375, "global_step": 493383, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0294153690338135, "global_step": 493384, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.059889316558838, "global_step": 493385, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0146806240081787, "global_step": 493386, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.070143222808838, "global_step": 493387, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.053847312927246, "global_step": 493388, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0413482189178467, "global_step": 493389, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.129737377166748, "global_step": 493390, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9289768934249878, "global_step": 493391, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.055375337600708, "global_step": 493392, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0290982723236084, "global_step": 493393, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0466489791870117, "global_step": 493394, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0075523853302, "global_step": 493395, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0229220390319824, "global_step": 493396, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0532593727111816, "global_step": 493397, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.040492296218872, "global_step": 493398, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0606741905212402, "global_step": 493399, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0341696739196777, "global_step": 493400, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.906625509262085, "global_step": 493401, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0500617027282715, "global_step": 493402, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.05676007270813, "global_step": 493403, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.046358346939087, "global_step": 493404, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0577826499938965, "global_step": 493405, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0203514099121094, "global_step": 493406, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.066012144088745, "global_step": 493407, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0403542518615723, "global_step": 493408, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.008915901184082, "global_step": 493409, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0671985149383545, "global_step": 493410, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.103811025619507, "global_step": 493411, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.052576780319214, "global_step": 493412, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.106916904449463, "global_step": 493413, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.063061237335205, "global_step": 493414, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0039939880371094, "global_step": 493415, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.079202175140381, "global_step": 493416, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0732812881469727, "global_step": 493417, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0519888401031494, "global_step": 493418, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0219900608062744, "global_step": 493419, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0160586833953857, "global_step": 493420, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.051931619644165, "global_step": 493421, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9610257148742676, "global_step": 493422, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.047447681427002, "global_step": 493423, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.955250859260559, "global_step": 493424, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0635006427764893, "global_step": 493425, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0402708053588867, "global_step": 493426, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0000298023223877, "global_step": 493427, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0475549697875977, "global_step": 493428, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0245985984802246, "global_step": 493429, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1233303546905518, "global_step": 493430, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0851974487304688, "global_step": 493431, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.081787109375, "global_step": 493432, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.118424415588379, "global_step": 493433, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.038996934890747, "global_step": 493434, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0647010803222656, "global_step": 493435, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.059278964996338, "global_step": 493436, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.008348226547241, "global_step": 493437, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.02472186088562, "global_step": 493438, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0420470237731934, "global_step": 493439, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0434319972991943, "global_step": 493440, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0182993412017822, "global_step": 493441, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0378518104553223, "global_step": 493442, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0652694702148438, "global_step": 493443, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.069173812866211, "global_step": 493444, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.135658025741577, "global_step": 493445, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0351030826568604, "global_step": 493446, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0795392990112305, "global_step": 493447, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.055885076522827, "global_step": 493448, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.091325283050537, "global_step": 493449, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1335184574127197, "global_step": 493450, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0246803760528564, "global_step": 493451, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0723071098327637, "global_step": 493452, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0088753700256348, "global_step": 493453, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9945266246795654, "global_step": 493454, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0061299800872803, "global_step": 493455, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9883776903152466, "global_step": 493456, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0245227813720703, "global_step": 493457, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.065387487411499, "global_step": 493458, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.044689178466797, "global_step": 493459, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.084181785583496, "global_step": 493460, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0163896083831787, "global_step": 493461, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0819318294525146, "global_step": 493462, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1461129188537598, "global_step": 493463, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.043027639389038, "global_step": 493464, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.116976022720337, "global_step": 493465, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9691569805145264, "global_step": 493466, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9953358173370361, "global_step": 493467, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.09894061088562, "global_step": 493468, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0232033729553223, "global_step": 493469, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.009754180908203, "global_step": 493470, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0615367889404297, "global_step": 493471, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1084113121032715, "global_step": 493472, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0510356426239014, "global_step": 493473, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0347394943237305, "global_step": 493474, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.088214159011841, "global_step": 493475, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.040067434310913, "global_step": 493476, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.047927141189575, "global_step": 493477, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0191986560821533, "global_step": 493478, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0354325771331787, "global_step": 493479, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0136940479278564, "global_step": 493480, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.10699200630188, "global_step": 493481, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.023911714553833, "global_step": 493482, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1437957286834717, "global_step": 493483, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0276124477386475, "global_step": 493484, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.042935371398926, "global_step": 493485, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9856293201446533, "global_step": 493486, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.075202226638794, "global_step": 493487, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0170679092407227, "global_step": 493488, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.095560073852539, "global_step": 493489, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0657103061676025, "global_step": 493490, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.011218547821045, "global_step": 493491, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9831957817077637, "global_step": 493492, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0823092460632324, "global_step": 493493, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0298619270324707, "global_step": 493494, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.099299430847168, "global_step": 493495, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0092477798461914, "global_step": 493496, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0736563205718994, "global_step": 493497, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.012739658355713, "global_step": 493498, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0013015270233154, "global_step": 493499, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0489742755889893, "global_step": 493500, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.104839563369751, "global_step": 493501, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.124854564666748, "global_step": 493502, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1227500438690186, "global_step": 493503, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0182766914367676, "global_step": 493504, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.021144390106201, "global_step": 493505, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0015430450439453, "global_step": 493506, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0897886753082275, "global_step": 493507, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.02431058883667, "global_step": 493508, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.091413736343384, "global_step": 493509, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.061082601547241, "global_step": 493510, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0820376873016357, "global_step": 493511, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0061583518981934, "global_step": 493512, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0500600337982178, "global_step": 493513, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.078368902206421, "global_step": 493514, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.016772985458374, "global_step": 493515, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9949960708618164, "global_step": 493516, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.100677013397217, "global_step": 493517, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1164920330047607, "global_step": 493518, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.106745481491089, "global_step": 493519, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0097925662994385, "global_step": 493520, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0433566570281982, "global_step": 493521, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.06365704536438, "global_step": 493522, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0964365005493164, "global_step": 493523, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0696825981140137, "global_step": 493524, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.077763319015503, "global_step": 493525, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0220015048980713, "global_step": 493526, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0407791137695312, "global_step": 493527, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.016101598739624, "global_step": 493528, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.037956476211548, "global_step": 493529, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1233885288238525, "global_step": 493530, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0665674209594727, "global_step": 493531, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.072559356689453, "global_step": 493532, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.067267894744873, "global_step": 493533, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0361151695251465, "global_step": 493534, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.974839448928833, "global_step": 493535, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.009563446044922, "global_step": 493536, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.085704803466797, "global_step": 493537, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9914226531982422, "global_step": 493538, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0465774536132812, "global_step": 493539, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9636662006378174, "global_step": 493540, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.046212911605835, "global_step": 493541, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0987014770507812, "global_step": 493542, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0189285278320312, "global_step": 493543, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0084280967712402, "global_step": 493544, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.051527261734009, "global_step": 493545, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9578810930252075, "global_step": 493546, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0096540451049805, "global_step": 493547, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9461044073104858, "global_step": 493548, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0690364837646484, "global_step": 493549, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.030311346054077, "global_step": 493550, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.039078712463379, "global_step": 493551, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0173208713531494, "global_step": 493552, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0473058223724365, "global_step": 493553, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0698094367980957, "global_step": 493554, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0022644996643066, "global_step": 493555, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.113579273223877, "global_step": 493556, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9669275283813477, "global_step": 493557, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0367050170898438, "global_step": 493558, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0628762245178223, "global_step": 493559, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.028393507003784, "global_step": 493560, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0653316974639893, "global_step": 493561, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0498886108398438, "global_step": 493562, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1063714027404785, "global_step": 493563, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1055874824523926, "global_step": 493564, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0591514110565186, "global_step": 493565, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0900750160217285, "global_step": 493566, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.133431911468506, "global_step": 493567, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1078076362609863, "global_step": 493568, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.039361000061035, "global_step": 493569, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.053478717803955, "global_step": 493570, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9849462509155273, "global_step": 493571, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1416521072387695, "global_step": 493572, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.087151050567627, "global_step": 493573, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.013617992401123, "global_step": 493574, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9999275207519531, "global_step": 493575, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.022745370864868, "global_step": 493576, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.094515562057495, "global_step": 493577, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0251388549804688, "global_step": 493578, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.099106788635254, "global_step": 493579, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0222816467285156, "global_step": 493580, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0577995777130127, "global_step": 493581, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.134640693664551, "global_step": 493582, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.066725492477417, "global_step": 493583, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.051060199737549, "global_step": 493584, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.051973581314087, "global_step": 493585, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9876623153686523, "global_step": 493586, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.127650022506714, "global_step": 493587, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.116394519805908, "global_step": 493588, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0336761474609375, "global_step": 493589, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0574944019317627, "global_step": 493590, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9851924180984497, "global_step": 493591, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9516383409500122, "global_step": 493592, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0367937088012695, "global_step": 493593, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.120112419128418, "global_step": 493594, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0241315364837646, "global_step": 493595, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9576624631881714, "global_step": 493596, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.084066390991211, "global_step": 493597, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.018059015274048, "global_step": 493598, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1457676887512207, "global_step": 493599, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0694386959075928, "global_step": 493600, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0255625247955322, "global_step": 493601, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.035337448120117, "global_step": 493602, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.09989070892334, "global_step": 493603, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1456778049468994, "global_step": 493604, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0337514877319336, "global_step": 493605, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1219165325164795, "global_step": 493606, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.016744375228882, "global_step": 493607, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.058532953262329, "global_step": 493608, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9920626878738403, "global_step": 493609, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0364294052124023, "global_step": 493610, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.029496192932129, "global_step": 493611, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0427896976470947, "global_step": 493612, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.114961862564087, "global_step": 493613, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.024885654449463, "global_step": 493614, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.087419271469116, "global_step": 493615, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0778236389160156, "global_step": 493616, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.048785924911499, "global_step": 493617, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.057681083679199, "global_step": 493618, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.007937431335449, "global_step": 493619, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0416033267974854, "global_step": 493620, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0869193077087402, "global_step": 493621, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0101964473724365, "global_step": 493622, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0830390453338623, "global_step": 493623, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.039458751678467, "global_step": 493624, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9963741302490234, "global_step": 493625, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0042779445648193, "global_step": 493626, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0365445613861084, "global_step": 493627, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9781832695007324, "global_step": 493628, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.004796266555786, "global_step": 493629, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.114752769470215, "global_step": 493630, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0477917194366455, "global_step": 493631, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.085628032684326, "global_step": 493632, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9433728456497192, "global_step": 493633, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0447099208831787, "global_step": 493634, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1110804080963135, "global_step": 493635, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0959668159484863, "global_step": 493636, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.076685667037964, "global_step": 493637, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.122232437133789, "global_step": 493638, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.071302890777588, "global_step": 493639, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0442028045654297, "global_step": 493640, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.036759376525879, "global_step": 493641, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.111989974975586, "global_step": 493642, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0576887130737305, "global_step": 493643, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.035276174545288, "global_step": 493644, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9915411472320557, "global_step": 493645, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0327253341674805, "global_step": 493646, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9940532445907593, "global_step": 493647, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0724265575408936, "global_step": 493648, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0103559494018555, "global_step": 493649, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0084850788116455, "global_step": 493650, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.056445360183716, "global_step": 493651, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.014446973800659, "global_step": 493652, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0851805210113525, "global_step": 493653, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0409932136535645, "global_step": 493654, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0942814350128174, "global_step": 493655, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.045966625213623, "global_step": 493656, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0353496074676514, "global_step": 493657, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0362389087677, "global_step": 493658, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.066248655319214, "global_step": 493659, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.010284423828125, "global_step": 493660, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.059678554534912, "global_step": 493661, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.02138090133667, "global_step": 493662, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.101440191268921, "global_step": 493663, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.046771287918091, "global_step": 493664, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9513466358184814, "global_step": 493665, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0934836864471436, "global_step": 493666, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0844554901123047, "global_step": 493667, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1174590587615967, "global_step": 493668, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.976446509361267, "global_step": 493669, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0510618686676025, "global_step": 493670, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0106189250946045, "global_step": 493671, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9660004377365112, "global_step": 493672, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.013251304626465, "global_step": 493673, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.112640857696533, "global_step": 493674, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0916054248809814, "global_step": 493675, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.119663715362549, "global_step": 493676, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9777191877365112, "global_step": 493677, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9399452209472656, "global_step": 493678, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0543792247772217, "global_step": 493679, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1052358150482178, "global_step": 493680, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.100961923599243, "global_step": 493681, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.106548309326172, "global_step": 493682, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1489646434783936, "global_step": 493683, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.956376552581787, "global_step": 493684, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0383450984954834, "global_step": 493685, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.011840343475342, "global_step": 493686, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0606958866119385, "global_step": 493687, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.132274627685547, "global_step": 493688, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9987303018569946, "global_step": 493689, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0150794982910156, "global_step": 493690, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0296056270599365, "global_step": 493691, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.065234422683716, "global_step": 493692, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0478415489196777, "global_step": 493693, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.035942316055298, "global_step": 493694, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1455605030059814, "global_step": 493695, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.070279121398926, "global_step": 493696, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0516741275787354, "global_step": 493697, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.133188247680664, "global_step": 493698, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0648298263549805, "global_step": 493699, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0505318641662598, "global_step": 493700, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.000969409942627, "global_step": 493701, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.07346773147583, "global_step": 493702, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9820002317428589, "global_step": 493703, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0888943672180176, "global_step": 493704, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.100165605545044, "global_step": 493705, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0917410850524902, "global_step": 493706, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0668692588806152, "global_step": 493707, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0638434886932373, "global_step": 493708, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0253841876983643, "global_step": 493709, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9910401105880737, "global_step": 493710, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0669312477111816, "global_step": 493711, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.027249574661255, "global_step": 493712, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0578997135162354, "global_step": 493713, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.064129590988159, "global_step": 493714, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.081223487854004, "global_step": 493715, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9702543020248413, "global_step": 493716, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0057566165924072, "global_step": 493717, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.027503490447998, "global_step": 493718, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.032191514968872, "global_step": 493719, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0358664989471436, "global_step": 493720, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1000380516052246, "global_step": 493721, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.083340644836426, "global_step": 493722, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.114614725112915, "global_step": 493723, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1548144817352295, "global_step": 493724, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0755295753479004, "global_step": 493725, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9888982772827148, "global_step": 493726, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.042637825012207, "global_step": 493727, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0495340824127197, "global_step": 493728, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.996176838874817, "global_step": 493729, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0465073585510254, "global_step": 493730, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0329058170318604, "global_step": 493731, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.125774383544922, "global_step": 493732, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.031454086303711, "global_step": 493733, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.10333251953125, "global_step": 493734, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.051776647567749, "global_step": 493735, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0678536891937256, "global_step": 493736, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.010333776473999, "global_step": 493737, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.000924587249756, "global_step": 493738, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0137717723846436, "global_step": 493739, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1073434352874756, "global_step": 493740, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1032557487487793, "global_step": 493741, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1005899906158447, "global_step": 493742, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.051381826400757, "global_step": 493743, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0759763717651367, "global_step": 493744, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0096335411071777, "global_step": 493745, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0847885608673096, "global_step": 493746, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1228771209716797, "global_step": 493747, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0139973163604736, "global_step": 493748, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.909615397453308, "global_step": 493749, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9467051029205322, "global_step": 493750, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9707223176956177, "global_step": 493751, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0695993900299072, "global_step": 493752, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9401146173477173, "global_step": 493753, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0427818298339844, "global_step": 493754, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.094459056854248, "global_step": 493755, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.073892116546631, "global_step": 493756, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1012723445892334, "global_step": 493757, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0522046089172363, "global_step": 493758, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9771946668624878, "global_step": 493759, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.069594144821167, "global_step": 493760, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.041788101196289, "global_step": 493761, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9845058917999268, "global_step": 493762, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0750129222869873, "global_step": 493763, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1379036903381348, "global_step": 493764, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.059772491455078, "global_step": 493765, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0408666133880615, "global_step": 493766, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1294472217559814, "global_step": 493767, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.980963945388794, "global_step": 493768, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0112738609313965, "global_step": 493769, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0808634757995605, "global_step": 493770, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.128969430923462, "global_step": 493771, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.081329822540283, "global_step": 493772, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9904707670211792, "global_step": 493773, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.081533193588257, "global_step": 493774, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0495431423187256, "global_step": 493775, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1473147869110107, "global_step": 493776, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.105755090713501, "global_step": 493777, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.044344902038574, "global_step": 493778, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0557074546813965, "global_step": 493779, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1158018112182617, "global_step": 493780, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9715826511383057, "global_step": 493781, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1445298194885254, "global_step": 493782, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0415780544281006, "global_step": 493783, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.101257562637329, "global_step": 493784, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.015709400177002, "global_step": 493785, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9623100757598877, "global_step": 493786, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0570528507232666, "global_step": 493787, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.025780439376831, "global_step": 493788, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.043203115463257, "global_step": 493789, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0587706565856934, "global_step": 493790, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9280554056167603, "global_step": 493791, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9834946393966675, "global_step": 493792, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.023758888244629, "global_step": 493793, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0705337524414062, "global_step": 493794, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0565507411956787, "global_step": 493795, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.144989252090454, "global_step": 493796, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0817816257476807, "global_step": 493797, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.082402229309082, "global_step": 493798, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9193631410598755, "global_step": 493799, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.042924404144287, "global_step": 493800, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.111487865447998, "global_step": 493801, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.069483518600464, "global_step": 493802, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0762364864349365, "global_step": 493803, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9911717176437378, "global_step": 493804, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0048635005950928, "global_step": 493805, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.066328287124634, "global_step": 493806, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.095247268676758, "global_step": 493807, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0501084327697754, "global_step": 493808, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.011422872543335, "global_step": 493809, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0804946422576904, "global_step": 493810, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0911879539489746, "global_step": 493811, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.116983652114868, "global_step": 493812, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.005293846130371, "global_step": 493813, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0290520191192627, "global_step": 493814, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.128429412841797, "global_step": 493815, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0097172260284424, "global_step": 493816, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9957103729248047, "global_step": 493817, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.031778335571289, "global_step": 493818, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9707978963851929, "global_step": 493819, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.170259952545166, "global_step": 493820, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9456816911697388, "global_step": 493821, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0860188007354736, "global_step": 493822, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9470301866531372, "global_step": 493823, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0903518199920654, "global_step": 493824, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.084689140319824, "global_step": 493825, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0455222129821777, "global_step": 493826, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1182773113250732, "global_step": 493827, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1120331287384033, "global_step": 493828, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9973989725112915, "global_step": 493829, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9637359380722046, "global_step": 493830, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9756691455841064, "global_step": 493831, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0086557865142822, "global_step": 493832, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0066170692443848, "global_step": 493833, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9915034770965576, "global_step": 493834, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.10581636428833, "global_step": 493835, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0920214653015137, "global_step": 493836, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1207947731018066, "global_step": 493837, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.013899326324463, "global_step": 493838, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0578675270080566, "global_step": 493839, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1189260482788086, "global_step": 493840, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1047933101654053, "global_step": 493841, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.081723928451538, "global_step": 493842, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0746593475341797, "global_step": 493843, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0617847442626953, "global_step": 493844, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0483391284942627, "global_step": 493845, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0166215896606445, "global_step": 493846, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0570287704467773, "global_step": 493847, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.997454285621643, "global_step": 493848, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.057947874069214, "global_step": 493849, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0212059020996094, "global_step": 493850, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1320035457611084, "global_step": 493851, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0255286693573, "global_step": 493852, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.055835485458374, "global_step": 493853, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.967572808265686, "global_step": 493854, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0258326530456543, "global_step": 493855, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0452935695648193, "global_step": 493856, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0582330226898193, "global_step": 493857, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.115713596343994, "global_step": 493858, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.080080509185791, "global_step": 493859, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1098737716674805, "global_step": 493860, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0407538414001465, "global_step": 493861, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.134190082550049, "global_step": 493862, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0529608726501465, "global_step": 493863, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0136525630950928, "global_step": 493864, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0188727378845215, "global_step": 493865, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.091310977935791, "global_step": 493866, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0140540599823, "global_step": 493867, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0590243339538574, "global_step": 493868, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.022081136703491, "global_step": 493869, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0767416954040527, "global_step": 493870, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0493528842926025, "global_step": 493871, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0673580169677734, "global_step": 493872, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0658323764801025, "global_step": 493873, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.946134328842163, "global_step": 493874, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0511538982391357, "global_step": 493875, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0892131328582764, "global_step": 493876, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0555217266082764, "global_step": 493877, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1435422897338867, "global_step": 493878, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0159738063812256, "global_step": 493879, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.06820011138916, "global_step": 493880, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.095627784729004, "global_step": 493881, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0492873191833496, "global_step": 493882, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0299627780914307, "global_step": 493883, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0615272521972656, "global_step": 493884, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0237815380096436, "global_step": 493885, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0796597003936768, "global_step": 493886, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0365936756134033, "global_step": 493887, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.045233726501465, "global_step": 493888, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.020012378692627, "global_step": 493889, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.105457305908203, "global_step": 493890, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.072956085205078, "global_step": 493891, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.117267370223999, "global_step": 493892, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.024468421936035, "global_step": 493893, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0856869220733643, "global_step": 493894, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.045548677444458, "global_step": 493895, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.058945894241333, "global_step": 493896, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0604536533355713, "global_step": 493897, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.055494546890259, "global_step": 493898, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9970155954360962, "global_step": 493899, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9864858388900757, "global_step": 493900, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0449130535125732, "global_step": 493901, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0422017574310303, "global_step": 493902, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1009485721588135, "global_step": 493903, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.060818910598755, "global_step": 493904, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.066195249557495, "global_step": 493905, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0741162300109863, "global_step": 493906, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0426597595214844, "global_step": 493907, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.008753538131714, "global_step": 493908, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.931035041809082, "global_step": 493909, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0244007110595703, "global_step": 493910, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0843896865844727, "global_step": 493911, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.077540636062622, "global_step": 493912, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9966003894805908, "global_step": 493913, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0701732635498047, "global_step": 493914, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0259554386138916, "global_step": 493915, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9720871448516846, "global_step": 493916, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9763405323028564, "global_step": 493917, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1316661834716797, "global_step": 493918, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0883657932281494, "global_step": 493919, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.079728603363037, "global_step": 493920, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9556583166122437, "global_step": 493921, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0896923542022705, "global_step": 493922, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0528318881988525, "global_step": 493923, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1333065032958984, "global_step": 493924, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.072282075881958, "global_step": 493925, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.077393054962158, "global_step": 493926, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.156452178955078, "global_step": 493927, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0757153034210205, "global_step": 493928, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.036781072616577, "global_step": 493929, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.076627254486084, "global_step": 493930, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0414674282073975, "global_step": 493931, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0913891792297363, "global_step": 493932, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.117516040802002, "global_step": 493933, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0895872116088867, "global_step": 493934, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.058094024658203, "global_step": 493935, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0384225845336914, "global_step": 493936, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9234496355056763, "global_step": 493937, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9684646129608154, "global_step": 493938, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.054063558578491, "global_step": 493939, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1125056743621826, "global_step": 493940, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.084629774093628, "global_step": 493941, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9785780906677246, "global_step": 493942, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0253818035125732, "global_step": 493943, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.039494276046753, "global_step": 493944, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.098780632019043, "global_step": 493945, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.070549488067627, "global_step": 493946, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0172502994537354, "global_step": 493947, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0770552158355713, "global_step": 493948, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0259897708892822, "global_step": 493949, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0435307025909424, "global_step": 493950, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0373311042785645, "global_step": 493951, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0809853076934814, "global_step": 493952, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.058159351348877, "global_step": 493953, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1029396057128906, "global_step": 493954, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0280940532684326, "global_step": 493955, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.059981107711792, "global_step": 493956, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.008856773376465, "global_step": 493957, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.094799757003784, "global_step": 493958, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.152949571609497, "global_step": 493959, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.040558338165283, "global_step": 493960, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0363869667053223, "global_step": 493961, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.069448232650757, "global_step": 493962, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1002023220062256, "global_step": 493963, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.099141836166382, "global_step": 493964, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.135117530822754, "global_step": 493965, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.033643960952759, "global_step": 493966, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.058840274810791, "global_step": 493967, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0424859523773193, "global_step": 493968, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9940426349639893, "global_step": 493969, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.066399097442627, "global_step": 493970, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.097503423690796, "global_step": 493971, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0952398777008057, "global_step": 493972, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.030503034591675, "global_step": 493973, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0754644870758057, "global_step": 493974, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0509746074676514, "global_step": 493975, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0854132175445557, "global_step": 493976, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0061209201812744, "global_step": 493977, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0827317237854004, "global_step": 493978, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.044541597366333, "global_step": 493979, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0743443965911865, "global_step": 493980, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.051396369934082, "global_step": 493981, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1576318740844727, "global_step": 493982, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0617239475250244, "global_step": 493983, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.019911527633667, "global_step": 493984, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0559682846069336, "global_step": 493985, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0768954753875732, "global_step": 493986, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.14931583404541, "global_step": 493987, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.100891351699829, "global_step": 493988, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0729141235351562, "global_step": 493989, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9820966720581055, "global_step": 493990, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1263692378997803, "global_step": 493991, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.099735975265503, "global_step": 493992, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9865034818649292, "global_step": 493993, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0307674407958984, "global_step": 493994, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9963583946228027, "global_step": 493995, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0818936824798584, "global_step": 493996, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9893062114715576, "global_step": 493997, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.079007148742676, "global_step": 493998, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1160531044006348, "global_step": 493999, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0194203853607178, "global_step": 494000, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0349817276000977, "global_step": 494001, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.000776767730713, "global_step": 494002, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1217284202575684, "global_step": 494003, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.989555835723877, "global_step": 494004, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.081878900527954, "global_step": 494005, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.002041816711426, "global_step": 494006, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.004056930541992, "global_step": 494007, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1587092876434326, "global_step": 494008, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1175200939178467, "global_step": 494009, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0858004093170166, "global_step": 494010, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0418171882629395, "global_step": 494011, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.045403480529785, "global_step": 494012, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0264573097229004, "global_step": 494013, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.022280216217041, "global_step": 494014, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0660088062286377, "global_step": 494015, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9852197170257568, "global_step": 494016, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0998880863189697, "global_step": 494017, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1157584190368652, "global_step": 494018, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.106321334838867, "global_step": 494019, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0569944381713867, "global_step": 494020, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.004056215286255, "global_step": 494021, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0210325717926025, "global_step": 494022, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0235512256622314, "global_step": 494023, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0580508708953857, "global_step": 494024, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1139822006225586, "global_step": 494025, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.040952205657959, "global_step": 494026, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0805931091308594, "global_step": 494027, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.09022855758667, "global_step": 494028, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1013011932373047, "global_step": 494029, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0291521549224854, "global_step": 494030, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.08577299118042, "global_step": 494031, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0189337730407715, "global_step": 494032, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0419962406158447, "global_step": 494033, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9603667259216309, "global_step": 494034, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.082854986190796, "global_step": 494035, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0467491149902344, "global_step": 494036, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1161608695983887, "global_step": 494037, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.104408025741577, "global_step": 494038, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.023430109024048, "global_step": 494039, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1138553619384766, "global_step": 494040, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0236825942993164, "global_step": 494041, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0409231185913086, "global_step": 494042, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1018788814544678, "global_step": 494043, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.039862632751465, "global_step": 494044, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0374503135681152, "global_step": 494045, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1476800441741943, "global_step": 494046, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0581817626953125, "global_step": 494047, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.069519281387329, "global_step": 494048, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0020623207092285, "global_step": 494049, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.113379716873169, "global_step": 494050, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9519555568695068, "global_step": 494051, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1149373054504395, "global_step": 494052, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9933114051818848, "global_step": 494053, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1302330493927, "global_step": 494054, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0762317180633545, "global_step": 494055, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.149369478225708, "global_step": 494056, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1320221424102783, "global_step": 494057, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0745182037353516, "global_step": 494058, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.127882480621338, "global_step": 494059, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0551700592041016, "global_step": 494060, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0182766914367676, "global_step": 494061, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0643680095672607, "global_step": 494062, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1231069564819336, "global_step": 494063, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.026475429534912, "global_step": 494064, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9675158262252808, "global_step": 494065, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9798555374145508, "global_step": 494066, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.058454751968384, "global_step": 494067, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.084035634994507, "global_step": 494068, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.990272879600525, "global_step": 494069, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1060028076171875, "global_step": 494070, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.021972894668579, "global_step": 494071, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0595672130584717, "global_step": 494072, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0416879653930664, "global_step": 494073, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1270549297332764, "global_step": 494074, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1463804244995117, "global_step": 494075, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.068887948989868, "global_step": 494076, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0454070568084717, "global_step": 494077, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.081825017929077, "global_step": 494078, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.2180681228637695, "global_step": 494079, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0268406867980957, "global_step": 494080, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9880987405776978, "global_step": 494081, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9862639904022217, "global_step": 494082, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0543904304504395, "global_step": 494083, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.089674711227417, "global_step": 494084, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1092758178710938, "global_step": 494085, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0569820404052734, "global_step": 494086, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.970933437347412, "global_step": 494087, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.118230104446411, "global_step": 494088, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0267295837402344, "global_step": 494089, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.010209321975708, "global_step": 494090, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0819220542907715, "global_step": 494091, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0737416744232178, "global_step": 494092, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.140714168548584, "global_step": 494093, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1056580543518066, "global_step": 494094, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0598747730255127, "global_step": 494095, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0672688484191895, "global_step": 494096, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.021498203277588, "global_step": 494097, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0496113300323486, "global_step": 494098, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.107327461242676, "global_step": 494099, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.192490816116333, "global_step": 494100, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0422773361206055, "global_step": 494101, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.097694158554077, "global_step": 494102, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0274925231933594, "global_step": 494103, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0096800327301025, "global_step": 494104, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0723557472229004, "global_step": 494105, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1591811180114746, "global_step": 494106, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.007471799850464, "global_step": 494107, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.073974370956421, "global_step": 494108, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1215426921844482, "global_step": 494109, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0774168968200684, "global_step": 494110, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.122265100479126, "global_step": 494111, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.117492914199829, "global_step": 494112, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0189716815948486, "global_step": 494113, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.00411057472229, "global_step": 494114, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.153390407562256, "global_step": 494115, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0500926971435547, "global_step": 494116, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.01880145072937, "global_step": 494117, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0519871711730957, "global_step": 494118, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.086522340774536, "global_step": 494119, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.133394479751587, "global_step": 494120, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9363411664962769, "global_step": 494121, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.04103684425354, "global_step": 494122, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9446240663528442, "global_step": 494123, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1175646781921387, "global_step": 494124, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.134132146835327, "global_step": 494125, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1087646484375, "global_step": 494126, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.016665458679199, "global_step": 494127, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.078169345855713, "global_step": 494128, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0429611206054688, "global_step": 494129, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1986429691314697, "global_step": 494130, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.040886402130127, "global_step": 494131, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1483147144317627, "global_step": 494132, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0601534843444824, "global_step": 494133, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9803425073623657, "global_step": 494134, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0902512073516846, "global_step": 494135, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.093524217605591, "global_step": 494136, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.098872423171997, "global_step": 494137, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0747437477111816, "global_step": 494138, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.046579599380493, "global_step": 494139, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1449787616729736, "global_step": 494140, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0675368309020996, "global_step": 494141, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.170437812805176, "global_step": 494142, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0812900066375732, "global_step": 494143, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0420892238616943, "global_step": 494144, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0637807846069336, "global_step": 494145, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0462799072265625, "global_step": 494146, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.128084421157837, "global_step": 494147, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0769705772399902, "global_step": 494148, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.030754327774048, "global_step": 494149, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0926694869995117, "global_step": 494150, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.10239315032959, "global_step": 494151, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.062955856323242, "global_step": 494152, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.065261125564575, "global_step": 494153, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.083768367767334, "global_step": 494154, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9590272903442383, "global_step": 494155, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.056674003601074, "global_step": 494156, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.084489345550537, "global_step": 494157, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9590551853179932, "global_step": 494158, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1403231620788574, "global_step": 494159, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0274147987365723, "global_step": 494160, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9892072677612305, "global_step": 494161, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9959864616394043, "global_step": 494162, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0709853172302246, "global_step": 494163, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0329859256744385, "global_step": 494164, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.955480694770813, "global_step": 494165, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0153512954711914, "global_step": 494166, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.063948154449463, "global_step": 494167, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0511786937713623, "global_step": 494168, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.052487373352051, "global_step": 494169, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0323328971862793, "global_step": 494170, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0893807411193848, "global_step": 494171, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.057105779647827, "global_step": 494172, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.055997848510742, "global_step": 494173, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.006129741668701, "global_step": 494174, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0965681076049805, "global_step": 494175, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.032334089279175, "global_step": 494176, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0690596103668213, "global_step": 494177, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1579315662384033, "global_step": 494178, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0185465812683105, "global_step": 494179, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.091364622116089, "global_step": 494180, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1505751609802246, "global_step": 494181, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.996754765510559, "global_step": 494182, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.024418354034424, "global_step": 494183, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.010463237762451, "global_step": 494184, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0699827671051025, "global_step": 494185, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.054302930831909, "global_step": 494186, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.038350820541382, "global_step": 494187, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.095987319946289, "global_step": 494188, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0720930099487305, "global_step": 494189, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9979197978973389, "global_step": 494190, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0185298919677734, "global_step": 494191, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9236960411071777, "global_step": 494192, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0939159393310547, "global_step": 494193, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0636370182037354, "global_step": 494194, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.079418182373047, "global_step": 494195, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.095931053161621, "global_step": 494196, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.056342124938965, "global_step": 494197, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9953157901763916, "global_step": 494198, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.036841630935669, "global_step": 494199, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0295279026031494, "global_step": 494200, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.093608856201172, "global_step": 494201, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.054111957550049, "global_step": 494202, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1098411083221436, "global_step": 494203, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.068023204803467, "global_step": 494204, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0898334980010986, "global_step": 494205, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0779614448547363, "global_step": 494206, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1132731437683105, "global_step": 494207, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9965585470199585, "global_step": 494208, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1217498779296875, "global_step": 494209, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0714669227600098, "global_step": 494210, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0603272914886475, "global_step": 494211, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0766897201538086, "global_step": 494212, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.082024574279785, "global_step": 494213, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.009742021560669, "global_step": 494214, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.035682201385498, "global_step": 494215, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.094691514968872, "global_step": 494216, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.081111431121826, "global_step": 494217, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1283764839172363, "global_step": 494218, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0866005420684814, "global_step": 494219, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.047238349914551, "global_step": 494220, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0674233436584473, "global_step": 494221, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.094193935394287, "global_step": 494222, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.042634963989258, "global_step": 494223, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0129635334014893, "global_step": 494224, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0658376216888428, "global_step": 494225, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0262451171875, "global_step": 494226, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.098843574523926, "global_step": 494227, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0344936847686768, "global_step": 494228, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.071223258972168, "global_step": 494229, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1724984645843506, "global_step": 494230, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.049280881881714, "global_step": 494231, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0850279331207275, "global_step": 494232, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0780768394470215, "global_step": 494233, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0326120853424072, "global_step": 494234, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9940507411956787, "global_step": 494235, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.075455665588379, "global_step": 494236, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1127212047576904, "global_step": 494237, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.108635187149048, "global_step": 494238, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0752456188201904, "global_step": 494239, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.049928665161133, "global_step": 494240, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1292057037353516, "global_step": 494241, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1039185523986816, "global_step": 494242, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0545897483825684, "global_step": 494243, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.057770252227783, "global_step": 494244, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.939348816871643, "global_step": 494245, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0608460903167725, "global_step": 494246, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.090156078338623, "global_step": 494247, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0292751789093018, "global_step": 494248, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0073509216308594, "global_step": 494249, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0627784729003906, "global_step": 494250, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.113652467727661, "global_step": 494251, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0521724224090576, "global_step": 494252, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0611653327941895, "global_step": 494253, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9965654611587524, "global_step": 494254, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.055691719055176, "global_step": 494255, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.088937997817993, "global_step": 494256, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0621185302734375, "global_step": 494257, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.977940559387207, "global_step": 494258, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0158190727233887, "global_step": 494259, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.137894630432129, "global_step": 494260, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0038676261901855, "global_step": 494261, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0390052795410156, "global_step": 494262, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.090113401412964, "global_step": 494263, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0490689277648926, "global_step": 494264, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.013087272644043, "global_step": 494265, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.040436029434204, "global_step": 494266, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0630788803100586, "global_step": 494267, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.105908155441284, "global_step": 494268, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.963042140007019, "global_step": 494269, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0716283321380615, "global_step": 494270, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.050570487976074, "global_step": 494271, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.07627534866333, "global_step": 494272, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.06947922706604, "global_step": 494273, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0155441761016846, "global_step": 494274, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.140200138092041, "global_step": 494275, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.121748685836792, "global_step": 494276, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0664632320404053, "global_step": 494277, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9987131357192993, "global_step": 494278, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.126157760620117, "global_step": 494279, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1015520095825195, "global_step": 494280, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0693256855010986, "global_step": 494281, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0265471935272217, "global_step": 494282, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0995326042175293, "global_step": 494283, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.091600179672241, "global_step": 494284, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0215952396392822, "global_step": 494285, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0698189735412598, "global_step": 494286, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0928502082824707, "global_step": 494287, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9266753196716309, "global_step": 494288, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9681419134140015, "global_step": 494289, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0377097129821777, "global_step": 494290, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.104402542114258, "global_step": 494291, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0682458877563477, "global_step": 494292, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1034059524536133, "global_step": 494293, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.04664945602417, "global_step": 494294, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.011143684387207, "global_step": 494295, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1009719371795654, "global_step": 494296, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1263351440429688, "global_step": 494297, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.9773598909378052, "global_step": 494298, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0986950397491455, "global_step": 494299, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.051300287246704, "global_step": 494300, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.013273000717163, "global_step": 494301, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.073808193206787, "global_step": 494302, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.041475772857666, "global_step": 494303, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0772817134857178, "global_step": 494304, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1474609375, "global_step": 494305, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0587446689605713, "global_step": 494306, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0363500118255615, "global_step": 494307, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.116037607192993, "global_step": 494308, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0644826889038086, "global_step": 494309, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.028921365737915, "global_step": 494310, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.081273078918457, "global_step": 494311, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.057243824005127, "global_step": 494312, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.085829019546509, "global_step": 494313, "epoch": 859, "lr": 5e-05}
{"train_loss": 1.999742031097412, "global_step": 494314, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0303704738616943, "global_step": 494315, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.065786361694336, "global_step": 494316, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1173722743988037, "global_step": 494317, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0831024646759033, "global_step": 494318, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.1436116695404053, "global_step": 494319, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.041640520095825, "global_step": 494320, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.012286424636841, "global_step": 494321, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0547735691070557, "global_step": 494322, "epoch": 859, "lr": 5e-05}
{"train_loss": 2.0205540657043457, "global_step": 494323, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.099033832550049, "global_step": 494324, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.088813066482544, "global_step": 494325, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.137861967086792, "global_step": 494326, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.000638961791992, "global_step": 494327, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.033616065979004, "global_step": 494328, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0224387645721436, "global_step": 494329, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0645830631256104, "global_step": 494330, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0361175537109375, "global_step": 494331, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0028505325317383, "global_step": 494332, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.010104179382324, "global_step": 494333, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0554614067077637, "global_step": 494334, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.052020788192749, "global_step": 494335, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9971199035644531, "global_step": 494336, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0054850578308105, "global_step": 494337, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.989168405532837, "global_step": 494338, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.089406967163086, "global_step": 494339, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.018483877182007, "global_step": 494340, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0721263885498047, "global_step": 494341, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.028292655944824, "global_step": 494342, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.00815749168396, "global_step": 494343, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1801750659942627, "global_step": 494344, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0095551013946533, "global_step": 494345, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.034118890762329, "global_step": 494346, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1063716411590576, "global_step": 494347, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9564224481582642, "global_step": 494348, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0280814170837402, "global_step": 494349, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9885246753692627, "global_step": 494350, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.115445375442505, "global_step": 494351, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0246055126190186, "global_step": 494352, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0483083724975586, "global_step": 494353, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.044830560684204, "global_step": 494354, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.128441572189331, "global_step": 494355, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.997039794921875, "global_step": 494356, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.011002779006958, "global_step": 494357, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0717527866363525, "global_step": 494358, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0868349075317383, "global_step": 494359, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0710721015930176, "global_step": 494360, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.042469024658203, "global_step": 494361, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0453011989593506, "global_step": 494362, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.030123472213745, "global_step": 494363, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.041429042816162, "global_step": 494364, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.080066204071045, "global_step": 494365, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0842339992523193, "global_step": 494366, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0083935260772705, "global_step": 494367, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.013457775115967, "global_step": 494368, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.046398639678955, "global_step": 494369, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.060692310333252, "global_step": 494370, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.047940492630005, "global_step": 494371, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9810413122177124, "global_step": 494372, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9983750581741333, "global_step": 494373, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0103931427001953, "global_step": 494374, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.065930128097534, "global_step": 494375, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0983335971832275, "global_step": 494376, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0185160636901855, "global_step": 494377, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1390979290008545, "global_step": 494378, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.03926682472229, "global_step": 494379, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.117400646209717, "global_step": 494380, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0360095500946045, "global_step": 494381, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0020041465759277, "global_step": 494382, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1089844703674316, "global_step": 494383, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9958579540252686, "global_step": 494384, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.01119065284729, "global_step": 494385, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.971651554107666, "global_step": 494386, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.027261257171631, "global_step": 494387, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.01714825630188, "global_step": 494388, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.135214328765869, "global_step": 494389, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.099109649658203, "global_step": 494390, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0288500785827637, "global_step": 494391, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0614991188049316, "global_step": 494392, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.076756715774536, "global_step": 494393, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.103203773498535, "global_step": 494394, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9666483402252197, "global_step": 494395, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9567185640335083, "global_step": 494396, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0655150413513184, "global_step": 494397, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.089571952819824, "global_step": 494398, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9937989711761475, "global_step": 494399, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.000511884689331, "global_step": 494400, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9987260103225708, "global_step": 494401, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.091531753540039, "global_step": 494402, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0353407859802246, "global_step": 494403, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9954333305358887, "global_step": 494404, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.168154239654541, "global_step": 494405, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.041841506958008, "global_step": 494406, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.048949718475342, "global_step": 494407, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.08504319190979, "global_step": 494408, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1215474605560303, "global_step": 494409, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.026123523712158, "global_step": 494410, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0667099952697754, "global_step": 494411, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.99332594871521, "global_step": 494412, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.068025588989258, "global_step": 494413, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9441652297973633, "global_step": 494414, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0447542667388916, "global_step": 494415, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0463554859161377, "global_step": 494416, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9921748638153076, "global_step": 494417, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0031590461730957, "global_step": 494418, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0489964485168457, "global_step": 494419, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0464227199554443, "global_step": 494420, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.023897409439087, "global_step": 494421, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9861059188842773, "global_step": 494422, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9098761081695557, "global_step": 494423, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0990612506866455, "global_step": 494424, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.110713481903076, "global_step": 494425, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0512049198150635, "global_step": 494426, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.077054977416992, "global_step": 494427, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0702712535858154, "global_step": 494428, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.058567523956299, "global_step": 494429, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9079186916351318, "global_step": 494430, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0249783992767334, "global_step": 494431, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0805866718292236, "global_step": 494432, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.077334403991699, "global_step": 494433, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0614922046661377, "global_step": 494434, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.054076671600342, "global_step": 494435, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0397329330444336, "global_step": 494436, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9561463594436646, "global_step": 494437, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.038841962814331, "global_step": 494438, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.8846668004989624, "global_step": 494439, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1264591217041016, "global_step": 494440, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9988905191421509, "global_step": 494441, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9922698736190796, "global_step": 494442, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.13198184967041, "global_step": 494443, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.079266309738159, "global_step": 494444, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9904203414916992, "global_step": 494445, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.033364772796631, "global_step": 494446, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0660409927368164, "global_step": 494447, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.023422956466675, "global_step": 494448, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.985857605934143, "global_step": 494449, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.086439371109009, "global_step": 494450, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0058600902557373, "global_step": 494451, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.051103115081787, "global_step": 494452, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.159092903137207, "global_step": 494453, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0862014293670654, "global_step": 494454, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0338358879089355, "global_step": 494455, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0283970832824707, "global_step": 494456, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0597078800201416, "global_step": 494457, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1124155521392822, "global_step": 494458, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.112081527709961, "global_step": 494459, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.144213914871216, "global_step": 494460, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.022353410720825, "global_step": 494461, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.08575439453125, "global_step": 494462, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.129436731338501, "global_step": 494463, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0843398571014404, "global_step": 494464, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0979974269866943, "global_step": 494465, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.066101312637329, "global_step": 494466, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0215084552764893, "global_step": 494467, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1168949604034424, "global_step": 494468, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1188974380493164, "global_step": 494469, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.007014513015747, "global_step": 494470, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1029698848724365, "global_step": 494471, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9426348209381104, "global_step": 494472, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0833520889282227, "global_step": 494473, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.00213885307312, "global_step": 494474, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9446200132369995, "global_step": 494475, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.020737648010254, "global_step": 494476, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0695412158966064, "global_step": 494477, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9728797674179077, "global_step": 494478, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0331037044525146, "global_step": 494479, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.018646001815796, "global_step": 494480, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1458897590637207, "global_step": 494481, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0021393299102783, "global_step": 494482, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.040955066680908, "global_step": 494483, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.087634325027466, "global_step": 494484, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0957581996917725, "global_step": 494485, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0710978507995605, "global_step": 494486, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.059018850326538, "global_step": 494487, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.055269956588745, "global_step": 494488, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0668938159942627, "global_step": 494489, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0039284229278564, "global_step": 494490, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.055864095687866, "global_step": 494491, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.062509298324585, "global_step": 494492, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0003840923309326, "global_step": 494493, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1285531520843506, "global_step": 494494, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0976741313934326, "global_step": 494495, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1412672996520996, "global_step": 494496, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0188729763031006, "global_step": 494497, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0881049633026123, "global_step": 494498, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1305952072143555, "global_step": 494499, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0503666400909424, "global_step": 494500, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0039374828338623, "global_step": 494501, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0623421669006348, "global_step": 494502, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.072258949279785, "global_step": 494503, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.074183225631714, "global_step": 494504, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.067687749862671, "global_step": 494505, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9093202352523804, "global_step": 494506, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.056399345397949, "global_step": 494507, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0893664360046387, "global_step": 494508, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.017486810684204, "global_step": 494509, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0586204528808594, "global_step": 494510, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0553669929504395, "global_step": 494511, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1014208793640137, "global_step": 494512, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9854066371917725, "global_step": 494513, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0545918941497803, "global_step": 494514, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9695996046066284, "global_step": 494515, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0507044792175293, "global_step": 494516, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9866935014724731, "global_step": 494517, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.059920310974121, "global_step": 494518, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0040106773376465, "global_step": 494519, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0921213626861572, "global_step": 494520, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9369527101516724, "global_step": 494521, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0323541164398193, "global_step": 494522, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0838656425476074, "global_step": 494523, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.101572275161743, "global_step": 494524, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.010887622833252, "global_step": 494525, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0307812690734863, "global_step": 494526, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0803399085998535, "global_step": 494527, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9935853481292725, "global_step": 494528, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9449783563613892, "global_step": 494529, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0869057178497314, "global_step": 494530, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.991135597229004, "global_step": 494531, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0473601818084717, "global_step": 494532, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0786046981811523, "global_step": 494533, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.988685131072998, "global_step": 494534, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.00799298286438, "global_step": 494535, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9876216650009155, "global_step": 494536, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.960303544998169, "global_step": 494537, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0704078674316406, "global_step": 494538, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0650453567504883, "global_step": 494539, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0695629119873047, "global_step": 494540, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9391512870788574, "global_step": 494541, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0344743728637695, "global_step": 494542, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0017216205596924, "global_step": 494543, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0495612621307373, "global_step": 494544, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0448203086853027, "global_step": 494545, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0036606788635254, "global_step": 494546, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.011969566345215, "global_step": 494547, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0205447673797607, "global_step": 494548, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.078125, "global_step": 494549, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1267874240875244, "global_step": 494550, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.031604766845703, "global_step": 494551, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0803301334381104, "global_step": 494552, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.983619213104248, "global_step": 494553, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.977552056312561, "global_step": 494554, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0181167125701904, "global_step": 494555, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0834388732910156, "global_step": 494556, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9900785684585571, "global_step": 494557, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9581019878387451, "global_step": 494558, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.046020269393921, "global_step": 494559, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0025763511657715, "global_step": 494560, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.11165452003479, "global_step": 494561, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0344340801239014, "global_step": 494562, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0363683700561523, "global_step": 494563, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0927822589874268, "global_step": 494564, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.004241704940796, "global_step": 494565, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.066645860671997, "global_step": 494566, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.120027542114258, "global_step": 494567, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.140280246734619, "global_step": 494568, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0519423484802246, "global_step": 494569, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0124671459198, "global_step": 494570, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.060708999633789, "global_step": 494571, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.062497615814209, "global_step": 494572, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0448012351989746, "global_step": 494573, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.157712936401367, "global_step": 494574, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.073237419128418, "global_step": 494575, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.150310516357422, "global_step": 494576, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.013524293899536, "global_step": 494577, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.077735424041748, "global_step": 494578, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.037935256958008, "global_step": 494579, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9770766496658325, "global_step": 494580, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.045109272003174, "global_step": 494581, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1552112102508545, "global_step": 494582, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.009990692138672, "global_step": 494583, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1151020526885986, "global_step": 494584, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.115072011947632, "global_step": 494585, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0825905799865723, "global_step": 494586, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0341804027557373, "global_step": 494587, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.041142463684082, "global_step": 494588, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1224892139434814, "global_step": 494589, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0705552101135254, "global_step": 494590, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0088422298431396, "global_step": 494591, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0801799297332764, "global_step": 494592, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.017320156097412, "global_step": 494593, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1229653358459473, "global_step": 494594, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9821335077285767, "global_step": 494595, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.079299211502075, "global_step": 494596, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0298194885253906, "global_step": 494597, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0847771167755127, "global_step": 494598, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0281317234039307, "global_step": 494599, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.022718906402588, "global_step": 494600, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.02540922164917, "global_step": 494601, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.025801658630371, "global_step": 494602, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0385890007019043, "global_step": 494603, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9954026937484741, "global_step": 494604, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0774338245391846, "global_step": 494605, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.097805976867676, "global_step": 494606, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9343403577804565, "global_step": 494607, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.01605224609375, "global_step": 494608, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.108959197998047, "global_step": 494609, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0570294857025146, "global_step": 494610, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9748191833496094, "global_step": 494611, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9664182662963867, "global_step": 494612, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1009082794189453, "global_step": 494613, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0277318954467773, "global_step": 494614, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1597225666046143, "global_step": 494615, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.026120662689209, "global_step": 494616, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1238677501678467, "global_step": 494617, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.065936326980591, "global_step": 494618, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.003882646560669, "global_step": 494619, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.004916191101074, "global_step": 494620, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1837446689605713, "global_step": 494621, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.103638172149658, "global_step": 494622, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1705119609832764, "global_step": 494623, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0028228759765625, "global_step": 494624, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0035204887390137, "global_step": 494625, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.101712703704834, "global_step": 494626, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.108097791671753, "global_step": 494627, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.038238048553467, "global_step": 494628, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.049159049987793, "global_step": 494629, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.057257652282715, "global_step": 494630, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.056770086288452, "global_step": 494631, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1026906967163086, "global_step": 494632, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0753090381622314, "global_step": 494633, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.049595832824707, "global_step": 494634, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0316290855407715, "global_step": 494635, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0489611625671387, "global_step": 494636, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.995768666267395, "global_step": 494637, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0602712631225586, "global_step": 494638, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.096644639968872, "global_step": 494639, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0124638080596924, "global_step": 494640, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.988053321838379, "global_step": 494641, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9852956533432007, "global_step": 494642, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9879519939422607, "global_step": 494643, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0559208393096924, "global_step": 494644, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0151052474975586, "global_step": 494645, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0102884769439697, "global_step": 494646, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.027034044265747, "global_step": 494647, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0543148517608643, "global_step": 494648, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0412940979003906, "global_step": 494649, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0127837657928467, "global_step": 494650, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1115972995758057, "global_step": 494651, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0222690105438232, "global_step": 494652, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0052273273468018, "global_step": 494653, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.049705982208252, "global_step": 494654, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0145890712738037, "global_step": 494655, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9347280263900757, "global_step": 494656, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0744709968566895, "global_step": 494657, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0035207271575928, "global_step": 494658, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.09375262260437, "global_step": 494659, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.090548038482666, "global_step": 494660, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0644919872283936, "global_step": 494661, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0907094478607178, "global_step": 494662, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9446663856506348, "global_step": 494663, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9985934495925903, "global_step": 494664, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0817084312438965, "global_step": 494665, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.983223557472229, "global_step": 494666, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.102987766265869, "global_step": 494667, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.033353328704834, "global_step": 494668, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1199827194213867, "global_step": 494669, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0905096530914307, "global_step": 494670, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9890086650848389, "global_step": 494671, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9683151245117188, "global_step": 494672, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.026392936706543, "global_step": 494673, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.011570930480957, "global_step": 494674, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0132803916931152, "global_step": 494675, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0657646656036377, "global_step": 494676, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0555660724639893, "global_step": 494677, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1400907039642334, "global_step": 494678, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.026909112930298, "global_step": 494679, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.130159854888916, "global_step": 494680, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9755213260650635, "global_step": 494681, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0907249450683594, "global_step": 494682, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1225249767303467, "global_step": 494683, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0617411136627197, "global_step": 494684, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.078552484512329, "global_step": 494685, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.060493230819702, "global_step": 494686, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0862114429473877, "global_step": 494687, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.049797773361206, "global_step": 494688, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0107598304748535, "global_step": 494689, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.139104127883911, "global_step": 494690, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0497963428497314, "global_step": 494691, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.034472703933716, "global_step": 494692, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0705983638763428, "global_step": 494693, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9705926179885864, "global_step": 494694, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.013320207595825, "global_step": 494695, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0900862216949463, "global_step": 494696, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.01192045211792, "global_step": 494697, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0807716846466064, "global_step": 494698, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0259878635406494, "global_step": 494699, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0588998794555664, "global_step": 494700, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0184149742126465, "global_step": 494701, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.03940749168396, "global_step": 494702, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0279834270477295, "global_step": 494703, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1272361278533936, "global_step": 494704, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0565853118896484, "global_step": 494705, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9639232158660889, "global_step": 494706, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1158127784729004, "global_step": 494707, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0451905727386475, "global_step": 494708, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1443376541137695, "global_step": 494709, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1553828716278076, "global_step": 494710, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0483405590057373, "global_step": 494711, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9973533153533936, "global_step": 494712, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.018233299255371, "global_step": 494713, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.07363224029541, "global_step": 494714, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0327141284942627, "global_step": 494715, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1519079208374023, "global_step": 494716, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.05522084236145, "global_step": 494717, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.033456802368164, "global_step": 494718, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0488154888153076, "global_step": 494719, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1004481315612793, "global_step": 494720, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0168638229370117, "global_step": 494721, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0805017948150635, "global_step": 494722, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.958223819732666, "global_step": 494723, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0585289001464844, "global_step": 494724, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9678794145584106, "global_step": 494725, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0163400173187256, "global_step": 494726, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0575509071350098, "global_step": 494727, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0228991508483887, "global_step": 494728, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9674978256225586, "global_step": 494729, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.059314012527466, "global_step": 494730, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0045766830444336, "global_step": 494731, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.080951690673828, "global_step": 494732, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0534937381744385, "global_step": 494733, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.00614595413208, "global_step": 494734, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0462543964385986, "global_step": 494735, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.057283401489258, "global_step": 494736, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.037475109100342, "global_step": 494737, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0744357109069824, "global_step": 494738, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.060133218765259, "global_step": 494739, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.991486668586731, "global_step": 494740, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.050398588180542, "global_step": 494741, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.004016876220703, "global_step": 494742, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0774385929107666, "global_step": 494743, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.046781063079834, "global_step": 494744, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.077958822250366, "global_step": 494745, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0878612995147705, "global_step": 494746, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.035205364227295, "global_step": 494747, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.989595890045166, "global_step": 494748, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1009819507598877, "global_step": 494749, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0940661430358887, "global_step": 494750, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9806134700775146, "global_step": 494751, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.086050033569336, "global_step": 494752, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0497446060180664, "global_step": 494753, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.046393394470215, "global_step": 494754, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.085031270980835, "global_step": 494755, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9867483377456665, "global_step": 494756, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.028294563293457, "global_step": 494757, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1017909049987793, "global_step": 494758, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.034207582473755, "global_step": 494759, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.064342737197876, "global_step": 494760, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.07045316696167, "global_step": 494761, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0431876182556152, "global_step": 494762, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.009321451187134, "global_step": 494763, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.034623146057129, "global_step": 494764, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0329103469848633, "global_step": 494765, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0740373134613037, "global_step": 494766, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0432283878326416, "global_step": 494767, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0641257762908936, "global_step": 494768, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0086934566497803, "global_step": 494769, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0999984741210938, "global_step": 494770, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.178490400314331, "global_step": 494771, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.04365873336792, "global_step": 494772, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0461461544036865, "global_step": 494773, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9661630392074585, "global_step": 494774, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0681989192962646, "global_step": 494775, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0164942741394043, "global_step": 494776, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.066741943359375, "global_step": 494777, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0770394802093506, "global_step": 494778, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0250041484832764, "global_step": 494779, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0529632568359375, "global_step": 494780, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.073859930038452, "global_step": 494781, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0350682735443115, "global_step": 494782, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.129746198654175, "global_step": 494783, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0956673622131348, "global_step": 494784, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1576592922210693, "global_step": 494785, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0750179290771484, "global_step": 494786, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1480021476745605, "global_step": 494787, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1187074184417725, "global_step": 494788, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1121878623962402, "global_step": 494789, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0790321826934814, "global_step": 494790, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0435245037078857, "global_step": 494791, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.042102813720703, "global_step": 494792, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.02097225189209, "global_step": 494793, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0507023334503174, "global_step": 494794, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.097160577774048, "global_step": 494795, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0343494415283203, "global_step": 494796, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0778329372406006, "global_step": 494797, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1108405590057373, "global_step": 494798, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.134150743484497, "global_step": 494799, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.110600709915161, "global_step": 494800, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0490219593048096, "global_step": 494801, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0731961727142334, "global_step": 494802, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0334043502807617, "global_step": 494803, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1247334480285645, "global_step": 494804, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0367698669433594, "global_step": 494805, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0261378288269043, "global_step": 494806, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0354063510894775, "global_step": 494807, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9495816230773926, "global_step": 494808, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.100402593612671, "global_step": 494809, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0336296558380127, "global_step": 494810, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0057473182678223, "global_step": 494811, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9736013412475586, "global_step": 494812, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0800819396972656, "global_step": 494813, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9944965839385986, "global_step": 494814, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1393868923187256, "global_step": 494815, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0757858753204346, "global_step": 494816, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0907092094421387, "global_step": 494817, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0354888439178467, "global_step": 494818, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.057161331176758, "global_step": 494819, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0842761993408203, "global_step": 494820, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0642471313476562, "global_step": 494821, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0974106788635254, "global_step": 494822, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.086060047149658, "global_step": 494823, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0406343936920166, "global_step": 494824, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.924038290977478, "global_step": 494825, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.075887441635132, "global_step": 494826, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0643696784973145, "global_step": 494827, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0658812522888184, "global_step": 494828, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.023294687271118, "global_step": 494829, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0591156482696533, "global_step": 494830, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0645406246185303, "global_step": 494831, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0026700496673584, "global_step": 494832, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.000795364379883, "global_step": 494833, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.031151294708252, "global_step": 494834, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.055429697036743, "global_step": 494835, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.992260456085205, "global_step": 494836, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9961274862289429, "global_step": 494837, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9916775226593018, "global_step": 494838, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0300581455230713, "global_step": 494839, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0715935230255127, "global_step": 494840, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.984007477760315, "global_step": 494841, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.058626890182495, "global_step": 494842, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0368142127990723, "global_step": 494843, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0529606342315674, "global_step": 494844, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0445263385772705, "global_step": 494845, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0129616260528564, "global_step": 494846, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1178622245788574, "global_step": 494847, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0989503860473633, "global_step": 494848, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0609242916107178, "global_step": 494849, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.02873158454895, "global_step": 494850, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0653064250946045, "global_step": 494851, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.047389268875122, "global_step": 494852, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0127577781677246, "global_step": 494853, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0767180919647217, "global_step": 494854, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9950182437896729, "global_step": 494855, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.023777484893799, "global_step": 494856, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.014850378036499, "global_step": 494857, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.063091993331909, "global_step": 494858, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.033054828643799, "global_step": 494859, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.983349323272705, "global_step": 494860, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0517966747283936, "global_step": 494861, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0486862659454346, "global_step": 494862, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0631232261657715, "global_step": 494863, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.004922389984131, "global_step": 494864, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.104966402053833, "global_step": 494865, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.156243085861206, "global_step": 494866, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.048457622528076, "global_step": 494867, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0595710277557373, "global_step": 494868, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0689055919647217, "global_step": 494869, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9993572235107422, "global_step": 494870, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0869219303131104, "global_step": 494871, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0321459770202637, "global_step": 494872, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.035879611968994, "global_step": 494873, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0572726726531982, "global_step": 494874, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.090972423553467, "global_step": 494875, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1032955646514893, "global_step": 494876, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9996249675750732, "global_step": 494877, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.941001534461975, "global_step": 494878, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.045900821685791, "global_step": 494879, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.088878631591797, "global_step": 494880, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.002488851547241, "global_step": 494881, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.088711738586426, "global_step": 494882, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0740811824798584, "global_step": 494883, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.077239513397217, "global_step": 494884, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0006630420684814, "global_step": 494885, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0427980422973633, "global_step": 494886, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.062154531478882, "global_step": 494887, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.028198719024658, "global_step": 494888, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0910396575927734, "global_step": 494889, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.01106858253479, "global_step": 494890, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.009422779083252, "global_step": 494891, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.040987253189087, "global_step": 494892, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.084083080291748, "global_step": 494893, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0327024459838867, "global_step": 494894, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0941693782806396, "global_step": 494895, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0894834995269775, "global_step": 494896, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1091578006744385, "global_step": 494897, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.05275297164917, "global_step": 494898, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.055945873260498, "global_step": 494899, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.019899845123291, "global_step": 494900, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.145761728286743, "global_step": 494901, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.064303159713745, "global_step": 494902, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.100116729736328, "global_step": 494903, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1504483222961426, "global_step": 494904, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.008415699005127, "global_step": 494905, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0496182441711426, "global_step": 494906, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9804209470748901, "global_step": 494907, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0200321674346924, "global_step": 494908, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1058602333068848, "global_step": 494909, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1325671672821045, "global_step": 494910, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9669883251190186, "global_step": 494911, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0259199142456055, "global_step": 494912, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.093508243560791, "global_step": 494913, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.056030511856079, "global_step": 494914, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.080068349838257, "global_step": 494915, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0836164951324463, "global_step": 494916, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1620943546295166, "global_step": 494917, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9600634574890137, "global_step": 494918, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1040074825286865, "global_step": 494919, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0352914333343506, "global_step": 494920, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0168259143829346, "global_step": 494921, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.03403639793396, "global_step": 494922, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9798810482025146, "global_step": 494923, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0238003730773926, "global_step": 494924, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.037219524383545, "global_step": 494925, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0264670848846436, "global_step": 494926, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.054255485534668, "global_step": 494927, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.009514808654785, "global_step": 494928, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.059976577758789, "global_step": 494929, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0483455657958984, "global_step": 494930, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.028402805328369, "global_step": 494931, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.058561086654663, "global_step": 494932, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.126131534576416, "global_step": 494933, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0781915187835693, "global_step": 494934, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.045175552368164, "global_step": 494935, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.120295763015747, "global_step": 494936, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.117248058319092, "global_step": 494937, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.015742540359497, "global_step": 494938, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.137014150619507, "global_step": 494939, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.086352825164795, "global_step": 494940, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.092198133468628, "global_step": 494941, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0603291988372803, "global_step": 494942, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.035149335861206, "global_step": 494943, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0769519805908203, "global_step": 494944, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.112506866455078, "global_step": 494945, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0353751182556152, "global_step": 494946, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1066904067993164, "global_step": 494947, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0200061798095703, "global_step": 494948, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0195202827453613, "global_step": 494949, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.00933575630188, "global_step": 494950, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0999228954315186, "global_step": 494951, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0758132934570312, "global_step": 494952, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9981701374053955, "global_step": 494953, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.108212947845459, "global_step": 494954, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0589799880981445, "global_step": 494955, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0982918739318848, "global_step": 494956, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0668983459472656, "global_step": 494957, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0236783027648926, "global_step": 494958, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0648398399353027, "global_step": 494959, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0303826332092285, "global_step": 494960, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0406765937805176, "global_step": 494961, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0476162433624268, "global_step": 494962, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9797694683074951, "global_step": 494963, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.128864049911499, "global_step": 494964, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.088714122772217, "global_step": 494965, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0117485523223877, "global_step": 494966, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0840213298797607, "global_step": 494967, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.068471670150757, "global_step": 494968, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.000232458114624, "global_step": 494969, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.088118076324463, "global_step": 494970, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.06113600730896, "global_step": 494971, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1865572929382324, "global_step": 494972, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.023164987564087, "global_step": 494973, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0629968643188477, "global_step": 494974, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0733399391174316, "global_step": 494975, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0086002349853516, "global_step": 494976, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0934183597564697, "global_step": 494977, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0579442977905273, "global_step": 494978, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1705808639526367, "global_step": 494979, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.092698574066162, "global_step": 494980, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.137540817260742, "global_step": 494981, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0353095531463623, "global_step": 494982, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.089299440383911, "global_step": 494983, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0810647010803223, "global_step": 494984, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.2110118865966797, "global_step": 494985, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9904024600982666, "global_step": 494986, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0182747840881348, "global_step": 494987, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0008418560028076, "global_step": 494988, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0713930130004883, "global_step": 494989, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0666403770446777, "global_step": 494990, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0336544513702393, "global_step": 494991, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.946801781654358, "global_step": 494992, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1262519359588623, "global_step": 494993, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1634395122528076, "global_step": 494994, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.013261556625366, "global_step": 494995, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.116204261779785, "global_step": 494996, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9726625680923462, "global_step": 494997, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.140059232711792, "global_step": 494998, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0718700885772705, "global_step": 494999, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.064868927001953, "global_step": 495000, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.032127857208252, "global_step": 495001, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.092132091522217, "global_step": 495002, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9638009071350098, "global_step": 495003, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.060835838317871, "global_step": 495004, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9453799724578857, "global_step": 495005, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0958359241485596, "global_step": 495006, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0877041816711426, "global_step": 495007, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0320241451263428, "global_step": 495008, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0961897373199463, "global_step": 495009, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1343541145324707, "global_step": 495010, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9725998640060425, "global_step": 495011, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9825514554977417, "global_step": 495012, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0038726329803467, "global_step": 495013, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1236541271209717, "global_step": 495014, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.072066068649292, "global_step": 495015, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0243048667907715, "global_step": 495016, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0838544368743896, "global_step": 495017, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.101477861404419, "global_step": 495018, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.028341770172119, "global_step": 495019, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0482048988342285, "global_step": 495020, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.999274730682373, "global_step": 495021, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.050009250640869, "global_step": 495022, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.947259783744812, "global_step": 495023, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.049978017807007, "global_step": 495024, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.064142942428589, "global_step": 495025, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0595781803131104, "global_step": 495026, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0362558364868164, "global_step": 495027, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.048239231109619, "global_step": 495028, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0958054065704346, "global_step": 495029, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.184640645980835, "global_step": 495030, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.087576389312744, "global_step": 495031, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0071048736572266, "global_step": 495032, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.107527256011963, "global_step": 495033, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0600476264953613, "global_step": 495034, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0717544555664062, "global_step": 495035, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0850462913513184, "global_step": 495036, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1291215419769287, "global_step": 495037, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0254781246185303, "global_step": 495038, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0240602493286133, "global_step": 495039, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0557992458343506, "global_step": 495040, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0026862621307373, "global_step": 495041, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1198596954345703, "global_step": 495042, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0628623962402344, "global_step": 495043, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.2114150524139404, "global_step": 495044, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0127789974212646, "global_step": 495045, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9912919998168945, "global_step": 495046, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9611157178878784, "global_step": 495047, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9857573509216309, "global_step": 495048, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0087759494781494, "global_step": 495049, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0278804302215576, "global_step": 495050, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0301496982574463, "global_step": 495051, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0424251556396484, "global_step": 495052, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.15728759765625, "global_step": 495053, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.107163906097412, "global_step": 495054, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9420490264892578, "global_step": 495055, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1852164268493652, "global_step": 495056, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.065432548522949, "global_step": 495057, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.068618059158325, "global_step": 495058, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.047025203704834, "global_step": 495059, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.983994960784912, "global_step": 495060, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.105229139328003, "global_step": 495061, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0335729122161865, "global_step": 495062, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.05981707572937, "global_step": 495063, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.033961057662964, "global_step": 495064, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9687178134918213, "global_step": 495065, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0563220977783203, "global_step": 495066, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0059900283813477, "global_step": 495067, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.048967123031616, "global_step": 495068, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.009857416152954, "global_step": 495069, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.086333751678467, "global_step": 495070, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0552918910980225, "global_step": 495071, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.006801128387451, "global_step": 495072, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.066368579864502, "global_step": 495073, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.062899589538574, "global_step": 495074, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0275230407714844, "global_step": 495075, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0902202129364014, "global_step": 495076, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0053632259368896, "global_step": 495077, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0965447425842285, "global_step": 495078, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0924415588378906, "global_step": 495079, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9282463788986206, "global_step": 495080, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.047313690185547, "global_step": 495081, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0402626991271973, "global_step": 495082, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0952906608581543, "global_step": 495083, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0919573307037354, "global_step": 495084, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9599558115005493, "global_step": 495085, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1004104614257812, "global_step": 495086, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0000548362731934, "global_step": 495087, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.046717882156372, "global_step": 495088, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.078897714614868, "global_step": 495089, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0992844104766846, "global_step": 495090, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0374882221221924, "global_step": 495091, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9988062381744385, "global_step": 495092, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.040379762649536, "global_step": 495093, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.079817533493042, "global_step": 495094, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.995483160018921, "global_step": 495095, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.054692506790161, "global_step": 495096, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0357837677001953, "global_step": 495097, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0057544708251953, "global_step": 495098, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.073692798614502, "global_step": 495099, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0967037677764893, "global_step": 495100, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0980827808380127, "global_step": 495101, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0077602863311768, "global_step": 495102, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0429975986480713, "global_step": 495103, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9910998344421387, "global_step": 495104, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0399539470672607, "global_step": 495105, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.112246036529541, "global_step": 495106, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0311813354492188, "global_step": 495107, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0646796226501465, "global_step": 495108, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.065851926803589, "global_step": 495109, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.102546215057373, "global_step": 495110, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9868637323379517, "global_step": 495111, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0286576747894287, "global_step": 495112, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.049013376235962, "global_step": 495113, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1410393714904785, "global_step": 495114, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.962554693222046, "global_step": 495115, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.005671977996826, "global_step": 495116, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0270886421203613, "global_step": 495117, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.998178243637085, "global_step": 495118, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0695881843566895, "global_step": 495119, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.045076608657837, "global_step": 495120, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0832815170288086, "global_step": 495121, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.073410749435425, "global_step": 495122, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9786713123321533, "global_step": 495123, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9981590509414673, "global_step": 495124, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.055830240249634, "global_step": 495125, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.069300651550293, "global_step": 495126, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0635735988616943, "global_step": 495127, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0914995670318604, "global_step": 495128, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1173367500305176, "global_step": 495129, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0498995780944824, "global_step": 495130, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.990543007850647, "global_step": 495131, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0909183025360107, "global_step": 495132, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.117433547973633, "global_step": 495133, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0734806060791016, "global_step": 495134, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.005960702896118, "global_step": 495135, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.021657943725586, "global_step": 495136, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0618410110473633, "global_step": 495137, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1275997161865234, "global_step": 495138, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.095468044281006, "global_step": 495139, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.989665150642395, "global_step": 495140, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0290489196777344, "global_step": 495141, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0408308506011963, "global_step": 495142, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.055908679962158, "global_step": 495143, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.035922050476074, "global_step": 495144, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0383191108703613, "global_step": 495145, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0827150344848633, "global_step": 495146, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0613322257995605, "global_step": 495147, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.014071226119995, "global_step": 495148, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1882567405700684, "global_step": 495149, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1801605224609375, "global_step": 495150, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9996365308761597, "global_step": 495151, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.023873805999756, "global_step": 495152, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0746054649353027, "global_step": 495153, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.042731285095215, "global_step": 495154, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9947526454925537, "global_step": 495155, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.071105480194092, "global_step": 495156, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.049323320388794, "global_step": 495157, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9902267456054688, "global_step": 495158, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.142937660217285, "global_step": 495159, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.080676317214966, "global_step": 495160, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.115368604660034, "global_step": 495161, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.180866003036499, "global_step": 495162, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1031908988952637, "global_step": 495163, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.072702169418335, "global_step": 495164, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.056006669998169, "global_step": 495165, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0467591285705566, "global_step": 495166, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.085960865020752, "global_step": 495167, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0787899494171143, "global_step": 495168, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9580607414245605, "global_step": 495169, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1361756324768066, "global_step": 495170, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0768065452575684, "global_step": 495171, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.100954532623291, "global_step": 495172, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.144711971282959, "global_step": 495173, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1281986236572266, "global_step": 495174, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0377068519592285, "global_step": 495175, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9949907064437866, "global_step": 495176, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1170594692230225, "global_step": 495177, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0645878314971924, "global_step": 495178, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0966739654541016, "global_step": 495179, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0227489471435547, "global_step": 495180, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9791185855865479, "global_step": 495181, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1030972003936768, "global_step": 495182, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0593574047088623, "global_step": 495183, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.056276559829712, "global_step": 495184, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.096083164215088, "global_step": 495185, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0349724292755127, "global_step": 495186, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.139565944671631, "global_step": 495187, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.093001365661621, "global_step": 495188, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1090128421783447, "global_step": 495189, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.001707077026367, "global_step": 495190, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.072226047515869, "global_step": 495191, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0663578510284424, "global_step": 495192, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1160364151000977, "global_step": 495193, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0644912719726562, "global_step": 495194, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.085317850112915, "global_step": 495195, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.005127191543579, "global_step": 495196, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.007990837097168, "global_step": 495197, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0756146907806396, "global_step": 495198, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0842912197113037, "global_step": 495199, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.036546468734741, "global_step": 495200, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.006704568862915, "global_step": 495201, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9996262788772583, "global_step": 495202, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9962695837020874, "global_step": 495203, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.074066162109375, "global_step": 495204, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0518271923065186, "global_step": 495205, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.151834487915039, "global_step": 495206, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.048142671585083, "global_step": 495207, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0515623092651367, "global_step": 495208, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0983080863952637, "global_step": 495209, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9891035556793213, "global_step": 495210, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0134735107421875, "global_step": 495211, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.124269485473633, "global_step": 495212, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9552539587020874, "global_step": 495213, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.143980026245117, "global_step": 495214, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0716357231140137, "global_step": 495215, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0197622776031494, "global_step": 495216, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.049839496612549, "global_step": 495217, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.086430549621582, "global_step": 495218, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0426506996154785, "global_step": 495219, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1065726280212402, "global_step": 495220, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.05303955078125, "global_step": 495221, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.040006160736084, "global_step": 495222, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.052407741546631, "global_step": 495223, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.016355514526367, "global_step": 495224, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.072254180908203, "global_step": 495225, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9814727306365967, "global_step": 495226, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0617358684539795, "global_step": 495227, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1715595722198486, "global_step": 495228, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0421879291534424, "global_step": 495229, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.141117811203003, "global_step": 495230, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1030285358428955, "global_step": 495231, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.113611936569214, "global_step": 495232, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.149322509765625, "global_step": 495233, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0313363075256348, "global_step": 495234, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.063591718673706, "global_step": 495235, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0472214221954346, "global_step": 495236, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9583948850631714, "global_step": 495237, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.069408893585205, "global_step": 495238, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.053675413131714, "global_step": 495239, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0765695571899414, "global_step": 495240, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1177332401275635, "global_step": 495241, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0626444816589355, "global_step": 495242, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0474894046783447, "global_step": 495243, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0190579891204834, "global_step": 495244, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1077985763549805, "global_step": 495245, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.086458206176758, "global_step": 495246, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.039792060852051, "global_step": 495247, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9877467155456543, "global_step": 495248, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.038463592529297, "global_step": 495249, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1212332248687744, "global_step": 495250, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.119279623031616, "global_step": 495251, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1196541786193848, "global_step": 495252, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.035857677459717, "global_step": 495253, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0140342712402344, "global_step": 495254, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.075857400894165, "global_step": 495255, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0197529792785645, "global_step": 495256, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.074725866317749, "global_step": 495257, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.00492262840271, "global_step": 495258, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0871565341949463, "global_step": 495259, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0449936389923096, "global_step": 495260, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.092709541320801, "global_step": 495261, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.039734125137329, "global_step": 495262, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.013639211654663, "global_step": 495263, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0941858291625977, "global_step": 495264, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.053359031677246, "global_step": 495265, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0315468311309814, "global_step": 495266, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.053356885910034, "global_step": 495267, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0434279441833496, "global_step": 495268, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9555745124816895, "global_step": 495269, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.042645215988159, "global_step": 495270, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1184606552124023, "global_step": 495271, "epoch": 860, "lr": 5e-05}
{"train_loss": 1.9974322319030762, "global_step": 495272, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.10530424118042, "global_step": 495273, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.175401449203491, "global_step": 495274, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.098480463027954, "global_step": 495275, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1108198165893555, "global_step": 495276, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1686172485351562, "global_step": 495277, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0987095832824707, "global_step": 495278, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.052304744720459, "global_step": 495279, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.102418899536133, "global_step": 495280, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.04624080657959, "global_step": 495281, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0257561206817627, "global_step": 495282, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.066757917404175, "global_step": 495283, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.089716672897339, "global_step": 495284, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.094456434249878, "global_step": 495285, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0408082008361816, "global_step": 495286, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.1454830169677734, "global_step": 495287, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0059421062469482, "global_step": 495288, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0985982418060303, "global_step": 495289, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.0402119159698486, "global_step": 495290, "epoch": 860, "lr": 5e-05}
{"train_loss": 2.052919626235962, "global_step": 495291, "epoch": 860, "lr": 5e-05, "val_loss": 5.710189342498779, "test_reconst_mse": 0.0734667032957077}
{"train_loss": 1.9772922992706299, "global_step": 495292, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9613984823226929, "global_step": 495293, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.024744987487793, "global_step": 495294, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0716373920440674, "global_step": 495295, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0227489471435547, "global_step": 495296, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0586936473846436, "global_step": 495297, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.023371696472168, "global_step": 495298, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.101039409637451, "global_step": 495299, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0274529457092285, "global_step": 495300, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.025977373123169, "global_step": 495301, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0480637550354004, "global_step": 495302, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0576024055480957, "global_step": 495303, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.010787010192871, "global_step": 495304, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9639889001846313, "global_step": 495305, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0691730976104736, "global_step": 495306, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.982155203819275, "global_step": 495307, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9892537593841553, "global_step": 495308, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.079554557800293, "global_step": 495309, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9924944639205933, "global_step": 495310, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1351916790008545, "global_step": 495311, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.964114785194397, "global_step": 495312, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0019307136535645, "global_step": 495313, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0042991638183594, "global_step": 495314, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.982635736465454, "global_step": 495315, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0504539012908936, "global_step": 495316, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0082125663757324, "global_step": 495317, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.979896068572998, "global_step": 495318, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.046476125717163, "global_step": 495319, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0283889770507812, "global_step": 495320, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0855493545532227, "global_step": 495321, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.094109296798706, "global_step": 495322, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.073775053024292, "global_step": 495323, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.048790454864502, "global_step": 495324, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0179033279418945, "global_step": 495325, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9913969039916992, "global_step": 495326, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9855563640594482, "global_step": 495327, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.04268741607666, "global_step": 495328, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.134608745574951, "global_step": 495329, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.04681658744812, "global_step": 495330, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0597996711730957, "global_step": 495331, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1072773933410645, "global_step": 495332, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9965028762817383, "global_step": 495333, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0583646297454834, "global_step": 495334, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.096715211868286, "global_step": 495335, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0257272720336914, "global_step": 495336, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0457653999328613, "global_step": 495337, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.979784607887268, "global_step": 495338, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.041506052017212, "global_step": 495339, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.02062726020813, "global_step": 495340, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.8985451459884644, "global_step": 495341, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.064687728881836, "global_step": 495342, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0126261711120605, "global_step": 495343, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.060577154159546, "global_step": 495344, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0770835876464844, "global_step": 495345, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0665643215179443, "global_step": 495346, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0397725105285645, "global_step": 495347, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0490572452545166, "global_step": 495348, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.01775860786438, "global_step": 495349, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0679409503936768, "global_step": 495350, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0047380924224854, "global_step": 495351, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.109282970428467, "global_step": 495352, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0819947719573975, "global_step": 495353, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.03597092628479, "global_step": 495354, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1026723384857178, "global_step": 495355, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.026019811630249, "global_step": 495356, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0427980422973633, "global_step": 495357, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.044302463531494, "global_step": 495358, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0351059436798096, "global_step": 495359, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.003772497177124, "global_step": 495360, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9882787466049194, "global_step": 495361, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0744118690490723, "global_step": 495362, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0918121337890625, "global_step": 495363, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0637853145599365, "global_step": 495364, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0246450901031494, "global_step": 495365, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.033193588256836, "global_step": 495366, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.991742491722107, "global_step": 495367, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.024704694747925, "global_step": 495368, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9973679780960083, "global_step": 495369, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0992941856384277, "global_step": 495370, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0721282958984375, "global_step": 495371, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0114924907684326, "global_step": 495372, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.945491909980774, "global_step": 495373, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0249738693237305, "global_step": 495374, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9877406358718872, "global_step": 495375, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0948240756988525, "global_step": 495376, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9923707246780396, "global_step": 495377, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0787250995635986, "global_step": 495378, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.130960702896118, "global_step": 495379, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.030231475830078, "global_step": 495380, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0439398288726807, "global_step": 495381, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9943745136260986, "global_step": 495382, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9757349491119385, "global_step": 495383, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0479495525360107, "global_step": 495384, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1277272701263428, "global_step": 495385, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0884318351745605, "global_step": 495386, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0293633937835693, "global_step": 495387, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0377562046051025, "global_step": 495388, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.009645700454712, "global_step": 495389, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0760610103607178, "global_step": 495390, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9793601036071777, "global_step": 495391, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9664908647537231, "global_step": 495392, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0344467163085938, "global_step": 495393, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.025301694869995, "global_step": 495394, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0947344303131104, "global_step": 495395, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0847039222717285, "global_step": 495396, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0728273391723633, "global_step": 495397, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0383899211883545, "global_step": 495398, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0245938301086426, "global_step": 495399, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.040410041809082, "global_step": 495400, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0906877517700195, "global_step": 495401, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0072476863861084, "global_step": 495402, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9664766788482666, "global_step": 495403, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0741498470306396, "global_step": 495404, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0841994285583496, "global_step": 495405, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1109206676483154, "global_step": 495406, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0216705799102783, "global_step": 495407, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1248927116394043, "global_step": 495408, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9608266353607178, "global_step": 495409, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0933313369750977, "global_step": 495410, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.021994113922119, "global_step": 495411, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.042527198791504, "global_step": 495412, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1100831031799316, "global_step": 495413, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.040616512298584, "global_step": 495414, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0220587253570557, "global_step": 495415, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0091896057128906, "global_step": 495416, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0621869564056396, "global_step": 495417, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.099494695663452, "global_step": 495418, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.060908555984497, "global_step": 495419, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.024005174636841, "global_step": 495420, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.984633445739746, "global_step": 495421, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1312060356140137, "global_step": 495422, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0702314376831055, "global_step": 495423, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.97731614112854, "global_step": 495424, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0250673294067383, "global_step": 495425, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.078601598739624, "global_step": 495426, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.031681537628174, "global_step": 495427, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0584495067596436, "global_step": 495428, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.034541368484497, "global_step": 495429, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0923237800598145, "global_step": 495430, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0254194736480713, "global_step": 495431, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0433528423309326, "global_step": 495432, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9739261865615845, "global_step": 495433, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.072965383529663, "global_step": 495434, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0818893909454346, "global_step": 495435, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9765958786010742, "global_step": 495436, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0569989681243896, "global_step": 495437, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.069960832595825, "global_step": 495438, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.117191791534424, "global_step": 495439, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.047178030014038, "global_step": 495440, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.050859212875366, "global_step": 495441, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0787508487701416, "global_step": 495442, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.048173666000366, "global_step": 495443, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0866646766662598, "global_step": 495444, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0017457008361816, "global_step": 495445, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.038541555404663, "global_step": 495446, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1363208293914795, "global_step": 495447, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0055904388427734, "global_step": 495448, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.075739860534668, "global_step": 495449, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.021876335144043, "global_step": 495450, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1322872638702393, "global_step": 495451, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0676136016845703, "global_step": 495452, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.01155161857605, "global_step": 495453, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0275416374206543, "global_step": 495454, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.002163887023926, "global_step": 495455, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.05641508102417, "global_step": 495456, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.131161689758301, "global_step": 495457, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.073423385620117, "global_step": 495458, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0138890743255615, "global_step": 495459, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.997913122177124, "global_step": 495460, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9860097169876099, "global_step": 495461, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0239925384521484, "global_step": 495462, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9986720085144043, "global_step": 495463, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0656559467315674, "global_step": 495464, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0829615592956543, "global_step": 495465, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9588857889175415, "global_step": 495466, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0928328037261963, "global_step": 495467, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.091925621032715, "global_step": 495468, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9762846231460571, "global_step": 495469, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0396463871002197, "global_step": 495470, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1228291988372803, "global_step": 495471, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0303661823272705, "global_step": 495472, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.081303596496582, "global_step": 495473, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.980788230895996, "global_step": 495474, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0243172645568848, "global_step": 495475, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0380027294158936, "global_step": 495476, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.009813070297241, "global_step": 495477, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.974144458770752, "global_step": 495478, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.073845624923706, "global_step": 495479, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0522804260253906, "global_step": 495480, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0467758178710938, "global_step": 495481, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9663195610046387, "global_step": 495482, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.974471092224121, "global_step": 495483, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9415663480758667, "global_step": 495484, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.093834161758423, "global_step": 495485, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9798697233200073, "global_step": 495486, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1023755073547363, "global_step": 495487, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1967976093292236, "global_step": 495488, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0638856887817383, "global_step": 495489, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0535361766815186, "global_step": 495490, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0171420574188232, "global_step": 495491, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.009314775466919, "global_step": 495492, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0609805583953857, "global_step": 495493, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.041116714477539, "global_step": 495494, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1288881301879883, "global_step": 495495, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9721583127975464, "global_step": 495496, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.033949613571167, "global_step": 495497, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0684618949890137, "global_step": 495498, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0301003456115723, "global_step": 495499, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0916666984558105, "global_step": 495500, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.077219009399414, "global_step": 495501, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.032325267791748, "global_step": 495502, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0195071697235107, "global_step": 495503, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0698626041412354, "global_step": 495504, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0923969745635986, "global_step": 495505, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.036506414413452, "global_step": 495506, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.059134006500244, "global_step": 495507, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0170199871063232, "global_step": 495508, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0334725379943848, "global_step": 495509, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.98519766330719, "global_step": 495510, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0619959831237793, "global_step": 495511, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.031618118286133, "global_step": 495512, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0592687129974365, "global_step": 495513, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.029461622238159, "global_step": 495514, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0080463886260986, "global_step": 495515, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9548416137695312, "global_step": 495516, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1073243618011475, "global_step": 495517, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.082583427429199, "global_step": 495518, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0103940963745117, "global_step": 495519, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0199646949768066, "global_step": 495520, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.099043607711792, "global_step": 495521, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.051748275756836, "global_step": 495522, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.091803550720215, "global_step": 495523, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.091681718826294, "global_step": 495524, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0414071083068848, "global_step": 495525, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.011361837387085, "global_step": 495526, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.050370693206787, "global_step": 495527, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.111741542816162, "global_step": 495528, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.069977283477783, "global_step": 495529, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1324477195739746, "global_step": 495530, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9988398551940918, "global_step": 495531, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.107163667678833, "global_step": 495532, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.069330930709839, "global_step": 495533, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.983275055885315, "global_step": 495534, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9061994552612305, "global_step": 495535, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9756550788879395, "global_step": 495536, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.010659694671631, "global_step": 495537, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0655386447906494, "global_step": 495538, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.030339002609253, "global_step": 495539, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0229268074035645, "global_step": 495540, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0663180351257324, "global_step": 495541, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.09631085395813, "global_step": 495542, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0660290718078613, "global_step": 495543, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.092416763305664, "global_step": 495544, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.051166534423828, "global_step": 495545, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9592026472091675, "global_step": 495546, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9468742609024048, "global_step": 495547, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.994696855545044, "global_step": 495548, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0212836265563965, "global_step": 495549, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0498855113983154, "global_step": 495550, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9965604543685913, "global_step": 495551, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0708770751953125, "global_step": 495552, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0359785556793213, "global_step": 495553, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.986688494682312, "global_step": 495554, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.078664541244507, "global_step": 495555, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0452167987823486, "global_step": 495556, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.018186330795288, "global_step": 495557, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1023709774017334, "global_step": 495558, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.083345651626587, "global_step": 495559, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.012075662612915, "global_step": 495560, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0024330615997314, "global_step": 495561, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0417428016662598, "global_step": 495562, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9995338916778564, "global_step": 495563, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1739931106567383, "global_step": 495564, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.142237901687622, "global_step": 495565, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0816075801849365, "global_step": 495566, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.160574436187744, "global_step": 495567, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.075007677078247, "global_step": 495568, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0646722316741943, "global_step": 495569, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9909307956695557, "global_step": 495570, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1392464637756348, "global_step": 495571, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0371286869049072, "global_step": 495572, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0225613117218018, "global_step": 495573, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0405919551849365, "global_step": 495574, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1349289417266846, "global_step": 495575, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.07180118560791, "global_step": 495576, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0041472911834717, "global_step": 495577, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0663559436798096, "global_step": 495578, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.058461904525757, "global_step": 495579, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0908005237579346, "global_step": 495580, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0733022689819336, "global_step": 495581, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0728142261505127, "global_step": 495582, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0266788005828857, "global_step": 495583, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.11340069770813, "global_step": 495584, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.06655216217041, "global_step": 495585, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0578465461730957, "global_step": 495586, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9851629734039307, "global_step": 495587, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.03863525390625, "global_step": 495588, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1183245182037354, "global_step": 495589, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0358006954193115, "global_step": 495590, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.133958578109741, "global_step": 495591, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0411057472229004, "global_step": 495592, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.065539598464966, "global_step": 495593, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0356476306915283, "global_step": 495594, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1241166591644287, "global_step": 495595, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.077126979827881, "global_step": 495596, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.055616617202759, "global_step": 495597, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.038494348526001, "global_step": 495598, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.08736252784729, "global_step": 495599, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.026024341583252, "global_step": 495600, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0068178176879883, "global_step": 495601, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.009399652481079, "global_step": 495602, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.032710313796997, "global_step": 495603, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0580365657806396, "global_step": 495604, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0441079139709473, "global_step": 495605, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.006833076477051, "global_step": 495606, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0719380378723145, "global_step": 495607, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9904083013534546, "global_step": 495608, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.154188394546509, "global_step": 495609, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.064544916152954, "global_step": 495610, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.078871250152588, "global_step": 495611, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.06906795501709, "global_step": 495612, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.017251968383789, "global_step": 495613, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.033113479614258, "global_step": 495614, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0045793056488037, "global_step": 495615, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1243226528167725, "global_step": 495616, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1176095008850098, "global_step": 495617, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0292255878448486, "global_step": 495618, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.006756544113159, "global_step": 495619, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0329034328460693, "global_step": 495620, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.046752691268921, "global_step": 495621, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9665418863296509, "global_step": 495622, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.097888469696045, "global_step": 495623, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.046933889389038, "global_step": 495624, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9915854930877686, "global_step": 495625, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0353095531463623, "global_step": 495626, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0363450050354004, "global_step": 495627, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9815808534622192, "global_step": 495628, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0608980655670166, "global_step": 495629, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.012502908706665, "global_step": 495630, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0478289127349854, "global_step": 495631, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.00457763671875, "global_step": 495632, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9462558031082153, "global_step": 495633, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.122105598449707, "global_step": 495634, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0614748001098633, "global_step": 495635, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0977578163146973, "global_step": 495636, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9530354738235474, "global_step": 495637, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1057558059692383, "global_step": 495638, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0818047523498535, "global_step": 495639, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0301952362060547, "global_step": 495640, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.076561450958252, "global_step": 495641, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1024129390716553, "global_step": 495642, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9706215858459473, "global_step": 495643, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1162378787994385, "global_step": 495644, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0436038970947266, "global_step": 495645, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.017746686935425, "global_step": 495646, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.009610652923584, "global_step": 495647, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.043879985809326, "global_step": 495648, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.033827304840088, "global_step": 495649, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.05914306640625, "global_step": 495650, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9861323833465576, "global_step": 495651, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0828912258148193, "global_step": 495652, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.2000114917755127, "global_step": 495653, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0195531845092773, "global_step": 495654, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0124361515045166, "global_step": 495655, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9962507486343384, "global_step": 495656, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0865068435668945, "global_step": 495657, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.075796127319336, "global_step": 495658, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.067232608795166, "global_step": 495659, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9984934329986572, "global_step": 495660, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.109238624572754, "global_step": 495661, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.079620361328125, "global_step": 495662, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.086716890335083, "global_step": 495663, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.12009334564209, "global_step": 495664, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.059854745864868, "global_step": 495665, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.025949239730835, "global_step": 495666, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9491591453552246, "global_step": 495667, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.116225242614746, "global_step": 495668, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.109281539916992, "global_step": 495669, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9740675687789917, "global_step": 495670, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.11037278175354, "global_step": 495671, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.009770154953003, "global_step": 495672, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9635709524154663, "global_step": 495673, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1183664798736572, "global_step": 495674, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.056682825088501, "global_step": 495675, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.059508800506592, "global_step": 495676, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1213626861572266, "global_step": 495677, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0051820278167725, "global_step": 495678, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.096709966659546, "global_step": 495679, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.943962812423706, "global_step": 495680, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.039346694946289, "global_step": 495681, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0072827339172363, "global_step": 495682, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.075949192047119, "global_step": 495683, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0003294944763184, "global_step": 495684, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9864391088485718, "global_step": 495685, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0155255794525146, "global_step": 495686, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.057417154312134, "global_step": 495687, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.147243022918701, "global_step": 495688, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.053335189819336, "global_step": 495689, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.105813503265381, "global_step": 495690, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0995032787323, "global_step": 495691, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0500242710113525, "global_step": 495692, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.057626247406006, "global_step": 495693, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1284430027008057, "global_step": 495694, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.115797281265259, "global_step": 495695, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.025726079940796, "global_step": 495696, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0044078826904297, "global_step": 495697, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.987541913986206, "global_step": 495698, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0076777935028076, "global_step": 495699, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.004718065261841, "global_step": 495700, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0791819095611572, "global_step": 495701, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0803849697113037, "global_step": 495702, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.091109275817871, "global_step": 495703, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.034975290298462, "global_step": 495704, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.108945369720459, "global_step": 495705, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0128848552703857, "global_step": 495706, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.082319498062134, "global_step": 495707, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.06000018119812, "global_step": 495708, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1071479320526123, "global_step": 495709, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1171159744262695, "global_step": 495710, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0863687992095947, "global_step": 495711, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0462288856506348, "global_step": 495712, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9758857488632202, "global_step": 495713, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0281150341033936, "global_step": 495714, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.029768466949463, "global_step": 495715, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.027761459350586, "global_step": 495716, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.078399658203125, "global_step": 495717, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9905493259429932, "global_step": 495718, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0477421283721924, "global_step": 495719, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.040252447128296, "global_step": 495720, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0720088481903076, "global_step": 495721, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0440516471862793, "global_step": 495722, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1077077388763428, "global_step": 495723, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.005615472793579, "global_step": 495724, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0251190662384033, "global_step": 495725, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.072593927383423, "global_step": 495726, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0318233966827393, "global_step": 495727, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0079874992370605, "global_step": 495728, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1061675548553467, "global_step": 495729, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0711662769317627, "global_step": 495730, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1138052940368652, "global_step": 495731, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0723843574523926, "global_step": 495732, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0462334156036377, "global_step": 495733, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0514004230499268, "global_step": 495734, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.054478406906128, "global_step": 495735, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.131211280822754, "global_step": 495736, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0406250953674316, "global_step": 495737, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9779677391052246, "global_step": 495738, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.063953399658203, "global_step": 495739, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.046055316925049, "global_step": 495740, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0945467948913574, "global_step": 495741, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.054264545440674, "global_step": 495742, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0772593021392822, "global_step": 495743, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.035680055618286, "global_step": 495744, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0350756645202637, "global_step": 495745, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9398490190505981, "global_step": 495746, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9955846071243286, "global_step": 495747, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.102520704269409, "global_step": 495748, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.05666184425354, "global_step": 495749, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0149614810943604, "global_step": 495750, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0760347843170166, "global_step": 495751, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9814391136169434, "global_step": 495752, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0989484786987305, "global_step": 495753, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.123168468475342, "global_step": 495754, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1573054790496826, "global_step": 495755, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0604217052459717, "global_step": 495756, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1142101287841797, "global_step": 495757, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.080284357070923, "global_step": 495758, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.051638126373291, "global_step": 495759, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0861525535583496, "global_step": 495760, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0187716484069824, "global_step": 495761, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.954379677772522, "global_step": 495762, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9363828897476196, "global_step": 495763, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.093489408493042, "global_step": 495764, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.021747350692749, "global_step": 495765, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9209083318710327, "global_step": 495766, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0269081592559814, "global_step": 495767, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.083056926727295, "global_step": 495768, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1057920455932617, "global_step": 495769, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.057638645172119, "global_step": 495770, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9702463150024414, "global_step": 495771, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.003814935684204, "global_step": 495772, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.106086254119873, "global_step": 495773, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.095881700515747, "global_step": 495774, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0928421020507812, "global_step": 495775, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0042223930358887, "global_step": 495776, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.024186849594116, "global_step": 495777, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1109938621520996, "global_step": 495778, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0835230350494385, "global_step": 495779, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.003154993057251, "global_step": 495780, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0034403800964355, "global_step": 495781, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.062577247619629, "global_step": 495782, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.041694402694702, "global_step": 495783, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.009343147277832, "global_step": 495784, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9597259759902954, "global_step": 495785, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9713153839111328, "global_step": 495786, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0418777465820312, "global_step": 495787, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0505144596099854, "global_step": 495788, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0246918201446533, "global_step": 495789, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0612335205078125, "global_step": 495790, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9768650531768799, "global_step": 495791, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.119513750076294, "global_step": 495792, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0973432064056396, "global_step": 495793, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.010728597640991, "global_step": 495794, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0683631896972656, "global_step": 495795, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.063089609146118, "global_step": 495796, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1252880096435547, "global_step": 495797, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.987761378288269, "global_step": 495798, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9985344409942627, "global_step": 495799, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.021064281463623, "global_step": 495800, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0769009590148926, "global_step": 495801, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0547678470611572, "global_step": 495802, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.122102975845337, "global_step": 495803, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0331077575683594, "global_step": 495804, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.042823076248169, "global_step": 495805, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.15956711769104, "global_step": 495806, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.063896417617798, "global_step": 495807, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0206305980682373, "global_step": 495808, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.110929012298584, "global_step": 495809, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0737879276275635, "global_step": 495810, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0189406871795654, "global_step": 495811, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0424752235412598, "global_step": 495812, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.057455062866211, "global_step": 495813, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.02368426322937, "global_step": 495814, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0404083728790283, "global_step": 495815, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.037590980529785, "global_step": 495816, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.12894868850708, "global_step": 495817, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.031287908554077, "global_step": 495818, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0527751445770264, "global_step": 495819, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0504984855651855, "global_step": 495820, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1053125858306885, "global_step": 495821, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.089325189590454, "global_step": 495822, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0685884952545166, "global_step": 495823, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0280191898345947, "global_step": 495824, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.122739791870117, "global_step": 495825, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0257904529571533, "global_step": 495826, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.014488935470581, "global_step": 495827, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0191447734832764, "global_step": 495828, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9477391242980957, "global_step": 495829, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0712201595306396, "global_step": 495830, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0352401733398438, "global_step": 495831, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1404571533203125, "global_step": 495832, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.046549081802368, "global_step": 495833, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1264150142669678, "global_step": 495834, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9997177124023438, "global_step": 495835, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.104034185409546, "global_step": 495836, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0646297931671143, "global_step": 495837, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1874594688415527, "global_step": 495838, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0559122562408447, "global_step": 495839, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.03022837638855, "global_step": 495840, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1135857105255127, "global_step": 495841, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0728418827056885, "global_step": 495842, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0791614055633545, "global_step": 495843, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.048163890838623, "global_step": 495844, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.040391206741333, "global_step": 495845, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0167922973632812, "global_step": 495846, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.09183406829834, "global_step": 495847, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.182633876800537, "global_step": 495848, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.039931058883667, "global_step": 495849, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1005825996398926, "global_step": 495850, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1031181812286377, "global_step": 495851, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9956880807876587, "global_step": 495852, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0472469329833984, "global_step": 495853, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9701331853866577, "global_step": 495854, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1054065227508545, "global_step": 495855, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1069624423980713, "global_step": 495856, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.104503631591797, "global_step": 495857, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.063436508178711, "global_step": 495858, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0723044872283936, "global_step": 495859, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0943832397460938, "global_step": 495860, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0716097354888916, "global_step": 495861, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0404653549194336, "global_step": 495862, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0551185607910156, "global_step": 495863, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1064541339874268, "global_step": 495864, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.083237409591675, "global_step": 495865, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.051952600479126, "global_step": 495866, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.013512134552002, "global_step": 495867, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.074989080429077, "global_step": 495868, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.980271577835083, "global_step": 495869, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1188623905181885, "global_step": 495870, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.085875988006592, "global_step": 495871, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.069894790649414, "global_step": 495872, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.061478614807129, "global_step": 495873, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.17242431640625, "global_step": 495874, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0993990898132324, "global_step": 495875, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.017406702041626, "global_step": 495876, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.113485813140869, "global_step": 495877, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.046182870864868, "global_step": 495878, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0771255493164062, "global_step": 495879, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9705545902252197, "global_step": 495880, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1496710777282715, "global_step": 495881, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0668625831604004, "global_step": 495882, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0903193950653076, "global_step": 495883, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.106783151626587, "global_step": 495884, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.112703800201416, "global_step": 495885, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.129584550857544, "global_step": 495886, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0439698696136475, "global_step": 495887, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.011869430541992, "global_step": 495888, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.045030355453491, "global_step": 495889, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0705456733703613, "global_step": 495890, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0476417541503906, "global_step": 495891, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.044257640838623, "global_step": 495892, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0560262203216553, "global_step": 495893, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1305251121520996, "global_step": 495894, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.055180788040161, "global_step": 495895, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.112816095352173, "global_step": 495896, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0841128826141357, "global_step": 495897, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1356279850006104, "global_step": 495898, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0426008701324463, "global_step": 495899, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0398874282836914, "global_step": 495900, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0659866333007812, "global_step": 495901, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.104675531387329, "global_step": 495902, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0441410541534424, "global_step": 495903, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0465826988220215, "global_step": 495904, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.106710195541382, "global_step": 495905, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9939378499984741, "global_step": 495906, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.122509241104126, "global_step": 495907, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9545058012008667, "global_step": 495908, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9208626747131348, "global_step": 495909, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.017916679382324, "global_step": 495910, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1173038482666016, "global_step": 495911, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1932895183563232, "global_step": 495912, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0490102767944336, "global_step": 495913, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0007762908935547, "global_step": 495914, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9563905000686646, "global_step": 495915, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9996837377548218, "global_step": 495916, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1360394954681396, "global_step": 495917, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0510380268096924, "global_step": 495918, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9747248888015747, "global_step": 495919, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0126450061798096, "global_step": 495920, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.117643117904663, "global_step": 495921, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.061004877090454, "global_step": 495922, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.056295394897461, "global_step": 495923, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0340232849121094, "global_step": 495924, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.113408327102661, "global_step": 495925, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.063284158706665, "global_step": 495926, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.124382972717285, "global_step": 495927, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.077390193939209, "global_step": 495928, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0319955348968506, "global_step": 495929, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0994763374328613, "global_step": 495930, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1292121410369873, "global_step": 495931, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0770020484924316, "global_step": 495932, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1184816360473633, "global_step": 495933, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0037715435028076, "global_step": 495934, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.138436794281006, "global_step": 495935, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.073540210723877, "global_step": 495936, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.044583320617676, "global_step": 495937, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9930522441864014, "global_step": 495938, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0683236122131348, "global_step": 495939, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.112739086151123, "global_step": 495940, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.106447219848633, "global_step": 495941, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9860953092575073, "global_step": 495942, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.066645860671997, "global_step": 495943, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.117804765701294, "global_step": 495944, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0385782718658447, "global_step": 495945, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0916271209716797, "global_step": 495946, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0749197006225586, "global_step": 495947, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.070014238357544, "global_step": 495948, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.022749900817871, "global_step": 495949, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.015603542327881, "global_step": 495950, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0893447399139404, "global_step": 495951, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.963565707206726, "global_step": 495952, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0778772830963135, "global_step": 495953, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0805776119232178, "global_step": 495954, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0446627140045166, "global_step": 495955, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.937650442123413, "global_step": 495956, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.093752145767212, "global_step": 495957, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0319507122039795, "global_step": 495958, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0294649600982666, "global_step": 495959, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1127066612243652, "global_step": 495960, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.081782102584839, "global_step": 495961, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0575313568115234, "global_step": 495962, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0305874347686768, "global_step": 495963, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1011922359466553, "global_step": 495964, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9535549879074097, "global_step": 495965, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0352256298065186, "global_step": 495966, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.023073196411133, "global_step": 495967, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.973433494567871, "global_step": 495968, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9948872327804565, "global_step": 495969, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.076878070831299, "global_step": 495970, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0339484214782715, "global_step": 495971, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0598251819610596, "global_step": 495972, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0052566528320312, "global_step": 495973, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1692495346069336, "global_step": 495974, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.06949520111084, "global_step": 495975, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9811277389526367, "global_step": 495976, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.07783842086792, "global_step": 495977, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0808000564575195, "global_step": 495978, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9656275510787964, "global_step": 495979, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1010003089904785, "global_step": 495980, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0663046836853027, "global_step": 495981, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.123225450515747, "global_step": 495982, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1158807277679443, "global_step": 495983, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9929636716842651, "global_step": 495984, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.093019962310791, "global_step": 495985, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.153597354888916, "global_step": 495986, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1063570976257324, "global_step": 495987, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.118253469467163, "global_step": 495988, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0940332412719727, "global_step": 495989, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0656332969665527, "global_step": 495990, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0197062492370605, "global_step": 495991, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.013852596282959, "global_step": 495992, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0024428367614746, "global_step": 495993, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0340735912323, "global_step": 495994, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.081141948699951, "global_step": 495995, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.042670965194702, "global_step": 495996, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9942046403884888, "global_step": 495997, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0941436290740967, "global_step": 495998, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0723724365234375, "global_step": 495999, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0729026794433594, "global_step": 496000, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.094001293182373, "global_step": 496001, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.078685998916626, "global_step": 496002, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0960652828216553, "global_step": 496003, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0891425609588623, "global_step": 496004, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9958642721176147, "global_step": 496005, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1175713539123535, "global_step": 496006, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.117709159851074, "global_step": 496007, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0138983726501465, "global_step": 496008, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0623836517333984, "global_step": 496009, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0442540645599365, "global_step": 496010, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1084437370300293, "global_step": 496011, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9981483221054077, "global_step": 496012, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9885692596435547, "global_step": 496013, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.103391170501709, "global_step": 496014, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1307783126831055, "global_step": 496015, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0144262313842773, "global_step": 496016, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1052348613739014, "global_step": 496017, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1598565578460693, "global_step": 496018, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0510520935058594, "global_step": 496019, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.11361026763916, "global_step": 496020, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.8834222555160522, "global_step": 496021, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.999502182006836, "global_step": 496022, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.089110851287842, "global_step": 496023, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.111778974533081, "global_step": 496024, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.072908878326416, "global_step": 496025, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9827747344970703, "global_step": 496026, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.085287570953369, "global_step": 496027, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9337170124053955, "global_step": 496028, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0679008960723877, "global_step": 496029, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0718367099761963, "global_step": 496030, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.05460524559021, "global_step": 496031, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.039215564727783, "global_step": 496032, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.014559507369995, "global_step": 496033, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.05906343460083, "global_step": 496034, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9787455797195435, "global_step": 496035, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1788322925567627, "global_step": 496036, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.141193151473999, "global_step": 496037, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0460824966430664, "global_step": 496038, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9994622468948364, "global_step": 496039, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9894819259643555, "global_step": 496040, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0580785274505615, "global_step": 496041, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0835156440734863, "global_step": 496042, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.084505558013916, "global_step": 496043, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.103405714035034, "global_step": 496044, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.117400884628296, "global_step": 496045, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0851969718933105, "global_step": 496046, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0365586280822754, "global_step": 496047, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0395336151123047, "global_step": 496048, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.054901599884033, "global_step": 496049, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0288538932800293, "global_step": 496050, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.11020827293396, "global_step": 496051, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0606675148010254, "global_step": 496052, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0874478816986084, "global_step": 496053, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0689220428466797, "global_step": 496054, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1023285388946533, "global_step": 496055, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0476620197296143, "global_step": 496056, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.022934675216675, "global_step": 496057, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0421886444091797, "global_step": 496058, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9873065948486328, "global_step": 496059, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.036421060562134, "global_step": 496060, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.034085750579834, "global_step": 496061, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9349476099014282, "global_step": 496062, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.15767502784729, "global_step": 496063, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.092946767807007, "global_step": 496064, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.080127716064453, "global_step": 496065, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.139981508255005, "global_step": 496066, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.030487537384033, "global_step": 496067, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.001469612121582, "global_step": 496068, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.02150559425354, "global_step": 496069, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0905323028564453, "global_step": 496070, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.102126121520996, "global_step": 496071, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0211684703826904, "global_step": 496072, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0979795455932617, "global_step": 496073, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0994718074798584, "global_step": 496074, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.081103563308716, "global_step": 496075, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0105388164520264, "global_step": 496076, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.057098388671875, "global_step": 496077, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0640809535980225, "global_step": 496078, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9663029909133911, "global_step": 496079, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1419222354888916, "global_step": 496080, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.992067575454712, "global_step": 496081, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1198880672454834, "global_step": 496082, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0979080200195312, "global_step": 496083, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0056777000427246, "global_step": 496084, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.100736618041992, "global_step": 496085, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.021371841430664, "global_step": 496086, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.035418748855591, "global_step": 496087, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0490312576293945, "global_step": 496088, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9879039525985718, "global_step": 496089, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.975079894065857, "global_step": 496090, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.062629461288452, "global_step": 496091, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1011438369750977, "global_step": 496092, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.07440447807312, "global_step": 496093, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.076059579849243, "global_step": 496094, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0139503479003906, "global_step": 496095, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0146405696868896, "global_step": 496096, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0303947925567627, "global_step": 496097, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.057729482650757, "global_step": 496098, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.141486644744873, "global_step": 496099, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.989670991897583, "global_step": 496100, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0089268684387207, "global_step": 496101, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0534591674804688, "global_step": 496102, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1291208267211914, "global_step": 496103, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.008925199508667, "global_step": 496104, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0535621643066406, "global_step": 496105, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0692193508148193, "global_step": 496106, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0238535404205322, "global_step": 496107, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9866877794265747, "global_step": 496108, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0524024963378906, "global_step": 496109, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.2086055278778076, "global_step": 496110, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.005671501159668, "global_step": 496111, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9611055850982666, "global_step": 496112, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0126852989196777, "global_step": 496113, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.07315993309021, "global_step": 496114, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.041215419769287, "global_step": 496115, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.039329767227173, "global_step": 496116, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.063767194747925, "global_step": 496117, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.048963785171509, "global_step": 496118, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.052680730819702, "global_step": 496119, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0597259998321533, "global_step": 496120, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0165481567382812, "global_step": 496121, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.08805513381958, "global_step": 496122, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.984872579574585, "global_step": 496123, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.051882743835449, "global_step": 496124, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.047701120376587, "global_step": 496125, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1430160999298096, "global_step": 496126, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.131032943725586, "global_step": 496127, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0627429485321045, "global_step": 496128, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.053779125213623, "global_step": 496129, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0487546920776367, "global_step": 496130, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.029944658279419, "global_step": 496131, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.997393012046814, "global_step": 496132, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0722482204437256, "global_step": 496133, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.063446521759033, "global_step": 496134, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.086209297180176, "global_step": 496135, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0745904445648193, "global_step": 496136, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.036426067352295, "global_step": 496137, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.013162136077881, "global_step": 496138, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.012387275695801, "global_step": 496139, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1024835109710693, "global_step": 496140, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.006661891937256, "global_step": 496141, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0583205223083496, "global_step": 496142, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.055690288543701, "global_step": 496143, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0014936923980713, "global_step": 496144, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0270795822143555, "global_step": 496145, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0600781440734863, "global_step": 496146, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.031992197036743, "global_step": 496147, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.041586399078369, "global_step": 496148, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.019134759902954, "global_step": 496149, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0376980304718018, "global_step": 496150, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.936679720878601, "global_step": 496151, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0291812419891357, "global_step": 496152, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.047356128692627, "global_step": 496153, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.074206590652466, "global_step": 496154, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0859551429748535, "global_step": 496155, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.107994556427002, "global_step": 496156, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9870203733444214, "global_step": 496157, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.069228172302246, "global_step": 496158, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0316643714904785, "global_step": 496159, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.104386806488037, "global_step": 496160, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0885651111602783, "global_step": 496161, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.038402795791626, "global_step": 496162, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1275360584259033, "global_step": 496163, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.06215238571167, "global_step": 496164, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.090315341949463, "global_step": 496165, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.027560234069824, "global_step": 496166, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0229973793029785, "global_step": 496167, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1072299480438232, "global_step": 496168, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0910556316375732, "global_step": 496169, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0033249855041504, "global_step": 496170, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.046205759048462, "global_step": 496171, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.124250650405884, "global_step": 496172, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.02725887298584, "global_step": 496173, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0698981285095215, "global_step": 496174, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.071621894836426, "global_step": 496175, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0542168617248535, "global_step": 496176, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0511345863342285, "global_step": 496177, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.038146495819092, "global_step": 496178, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1385626792907715, "global_step": 496179, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9738199710845947, "global_step": 496180, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0219826698303223, "global_step": 496181, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0992112159729004, "global_step": 496182, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0235743522644043, "global_step": 496183, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0624330043792725, "global_step": 496184, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9997129440307617, "global_step": 496185, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1333236694335938, "global_step": 496186, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0748677253723145, "global_step": 496187, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0228195190429688, "global_step": 496188, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.118567705154419, "global_step": 496189, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.045891761779785, "global_step": 496190, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0693700313568115, "global_step": 496191, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0724971294403076, "global_step": 496192, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.015292167663574, "global_step": 496193, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0037217140197754, "global_step": 496194, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.039860725402832, "global_step": 496195, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1380298137664795, "global_step": 496196, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.101907968521118, "global_step": 496197, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0386266708374023, "global_step": 496198, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0053281784057617, "global_step": 496199, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.980689525604248, "global_step": 496200, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.013143539428711, "global_step": 496201, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.138427734375, "global_step": 496202, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0372018814086914, "global_step": 496203, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1249380111694336, "global_step": 496204, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9360334873199463, "global_step": 496205, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.172710657119751, "global_step": 496206, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.107666015625, "global_step": 496207, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0529632568359375, "global_step": 496208, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.043602466583252, "global_step": 496209, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0515499114990234, "global_step": 496210, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.002307653427124, "global_step": 496211, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0252256393432617, "global_step": 496212, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.096775770187378, "global_step": 496213, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.091287612915039, "global_step": 496214, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.055668592453003, "global_step": 496215, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9863288402557373, "global_step": 496216, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9840668439865112, "global_step": 496217, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.117262601852417, "global_step": 496218, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1364126205444336, "global_step": 496219, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.986639142036438, "global_step": 496220, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.006852149963379, "global_step": 496221, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.116180419921875, "global_step": 496222, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0840582847595215, "global_step": 496223, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0591471195220947, "global_step": 496224, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0551860332489014, "global_step": 496225, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.051570177078247, "global_step": 496226, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1144344806671143, "global_step": 496227, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0555028915405273, "global_step": 496228, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1190671920776367, "global_step": 496229, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.030975341796875, "global_step": 496230, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1180989742279053, "global_step": 496231, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.060093641281128, "global_step": 496232, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.003891944885254, "global_step": 496233, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0014779567718506, "global_step": 496234, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0158114433288574, "global_step": 496235, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1191084384918213, "global_step": 496236, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.109879493713379, "global_step": 496237, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.133146286010742, "global_step": 496238, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9995245933532715, "global_step": 496239, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.044506788253784, "global_step": 496240, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.115983486175537, "global_step": 496241, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0612950325012207, "global_step": 496242, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9632644653320312, "global_step": 496243, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.042264223098755, "global_step": 496244, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1333017349243164, "global_step": 496245, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0508086681365967, "global_step": 496246, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1319003105163574, "global_step": 496247, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0421338081359863, "global_step": 496248, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.04240083694458, "global_step": 496249, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.989281177520752, "global_step": 496250, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0151922702789307, "global_step": 496251, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.048816442489624, "global_step": 496252, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0064074993133545, "global_step": 496253, "epoch": 861, "lr": 5e-05}
{"train_loss": 1.9891284704208374, "global_step": 496254, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0326898097991943, "global_step": 496255, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0368077754974365, "global_step": 496256, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.045896291732788, "global_step": 496257, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0767085552215576, "global_step": 496258, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.1274850368499756, "global_step": 496259, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.0520918369293213, "global_step": 496260, "epoch": 861, "lr": 5e-05}
{"train_loss": 2.047839879989624, "global_step": 496261, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0719547271728516, "global_step": 496262, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.054065704345703, "global_step": 496263, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.055433988571167, "global_step": 496264, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.075772285461426, "global_step": 496265, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0066795349121094, "global_step": 496266, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.01360821723938, "global_step": 496267, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0500099658966064, "global_step": 496268, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.081024408340454, "global_step": 496269, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9496866464614868, "global_step": 496270, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1065101623535156, "global_step": 496271, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.994606375694275, "global_step": 496272, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0232272148132324, "global_step": 496273, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.028695821762085, "global_step": 496274, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.041019916534424, "global_step": 496275, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0723631381988525, "global_step": 496276, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1526410579681396, "global_step": 496277, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0472469329833984, "global_step": 496278, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0038580894470215, "global_step": 496279, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0003292560577393, "global_step": 496280, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0224931240081787, "global_step": 496281, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9681071043014526, "global_step": 496282, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0682716369628906, "global_step": 496283, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0345349311828613, "global_step": 496284, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.062608242034912, "global_step": 496285, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.043682336807251, "global_step": 496286, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0091400146484375, "global_step": 496287, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0856759548187256, "global_step": 496288, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.033576488494873, "global_step": 496289, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.046459197998047, "global_step": 496290, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.050662040710449, "global_step": 496291, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0861523151397705, "global_step": 496292, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0802876949310303, "global_step": 496293, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.057204484939575, "global_step": 496294, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.063490629196167, "global_step": 496295, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0865371227264404, "global_step": 496296, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.034241199493408, "global_step": 496297, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0739049911499023, "global_step": 496298, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.039280414581299, "global_step": 496299, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.080156087875366, "global_step": 496300, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.000328302383423, "global_step": 496301, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0176146030426025, "global_step": 496302, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.086233377456665, "global_step": 496303, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.043048143386841, "global_step": 496304, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9984663724899292, "global_step": 496305, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0935726165771484, "global_step": 496306, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9414576292037964, "global_step": 496307, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0690484046936035, "global_step": 496308, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9703657627105713, "global_step": 496309, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0442357063293457, "global_step": 496310, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.08748722076416, "global_step": 496311, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.024372100830078, "global_step": 496312, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.168438673019409, "global_step": 496313, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0804989337921143, "global_step": 496314, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.025529623031616, "global_step": 496315, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0893962383270264, "global_step": 496316, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0366697311401367, "global_step": 496317, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.072467565536499, "global_step": 496318, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.117612600326538, "global_step": 496319, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.029890537261963, "global_step": 496320, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0159921646118164, "global_step": 496321, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0880813598632812, "global_step": 496322, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0690176486968994, "global_step": 496323, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0409629344940186, "global_step": 496324, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.094144105911255, "global_step": 496325, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9562245607376099, "global_step": 496326, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0621397495269775, "global_step": 496327, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.961186170578003, "global_step": 496328, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.049210786819458, "global_step": 496329, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.933435082435608, "global_step": 496330, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9945554733276367, "global_step": 496331, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1348798274993896, "global_step": 496332, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0374600887298584, "global_step": 496333, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1273014545440674, "global_step": 496334, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9586676359176636, "global_step": 496335, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.030557155609131, "global_step": 496336, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0827364921569824, "global_step": 496337, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.075942277908325, "global_step": 496338, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9963490962982178, "global_step": 496339, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0879340171813965, "global_step": 496340, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0190787315368652, "global_step": 496341, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.080024003982544, "global_step": 496342, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.035492181777954, "global_step": 496343, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.099606513977051, "global_step": 496344, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0243277549743652, "global_step": 496345, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0391266345977783, "global_step": 496346, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0754244327545166, "global_step": 496347, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9980309009552002, "global_step": 496348, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.025479793548584, "global_step": 496349, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0775671005249023, "global_step": 496350, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0758540630340576, "global_step": 496351, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9748905897140503, "global_step": 496352, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0863237380981445, "global_step": 496353, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0488173961639404, "global_step": 496354, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0386383533477783, "global_step": 496355, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.067598342895508, "global_step": 496356, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.995613694190979, "global_step": 496357, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0556726455688477, "global_step": 496358, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0227432250976562, "global_step": 496359, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0550479888916016, "global_step": 496360, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0254483222961426, "global_step": 496361, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0476436614990234, "global_step": 496362, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1278321743011475, "global_step": 496363, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.082047939300537, "global_step": 496364, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.089240074157715, "global_step": 496365, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0798192024230957, "global_step": 496366, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1301991939544678, "global_step": 496367, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0016896724700928, "global_step": 496368, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.040996789932251, "global_step": 496369, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0970170497894287, "global_step": 496370, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9845417737960815, "global_step": 496371, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.105503797531128, "global_step": 496372, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0283632278442383, "global_step": 496373, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0555012226104736, "global_step": 496374, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0795228481292725, "global_step": 496375, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0156848430633545, "global_step": 496376, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1519596576690674, "global_step": 496377, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9953886270523071, "global_step": 496378, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0660195350646973, "global_step": 496379, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.007962942123413, "global_step": 496380, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0213816165924072, "global_step": 496381, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9788129329681396, "global_step": 496382, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0685384273529053, "global_step": 496383, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.058476686477661, "global_step": 496384, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1105685234069824, "global_step": 496385, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.039585590362549, "global_step": 496386, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.006300687789917, "global_step": 496387, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0071945190429688, "global_step": 496388, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0228333473205566, "global_step": 496389, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0383412837982178, "global_step": 496390, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.154900074005127, "global_step": 496391, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.001513957977295, "global_step": 496392, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.961530089378357, "global_step": 496393, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0587964057922363, "global_step": 496394, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0416224002838135, "global_step": 496395, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0532338619232178, "global_step": 496396, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9839240312576294, "global_step": 496397, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.036456823348999, "global_step": 496398, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.072892189025879, "global_step": 496399, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.075927257537842, "global_step": 496400, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.103607654571533, "global_step": 496401, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.11383056640625, "global_step": 496402, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0541892051696777, "global_step": 496403, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.029083490371704, "global_step": 496404, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.980886459350586, "global_step": 496405, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9812822341918945, "global_step": 496406, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0249083042144775, "global_step": 496407, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0517144203186035, "global_step": 496408, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.053162097930908, "global_step": 496409, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.09629225730896, "global_step": 496410, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0896856784820557, "global_step": 496411, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.992090106010437, "global_step": 496412, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.083404541015625, "global_step": 496413, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.143789291381836, "global_step": 496414, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1337122917175293, "global_step": 496415, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0847253799438477, "global_step": 496416, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.030986785888672, "global_step": 496417, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0594465732574463, "global_step": 496418, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0294768810272217, "global_step": 496419, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.082669496536255, "global_step": 496420, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.010491371154785, "global_step": 496421, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0977187156677246, "global_step": 496422, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.975691795349121, "global_step": 496423, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.05192232131958, "global_step": 496424, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.001546859741211, "global_step": 496425, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1094141006469727, "global_step": 496426, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9704235792160034, "global_step": 496427, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0790016651153564, "global_step": 496428, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.922116756439209, "global_step": 496429, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.089918613433838, "global_step": 496430, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.048466682434082, "global_step": 496431, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.115103006362915, "global_step": 496432, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0229713916778564, "global_step": 496433, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.043057918548584, "global_step": 496434, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.008298635482788, "global_step": 496435, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9738469123840332, "global_step": 496436, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0571839809417725, "global_step": 496437, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.02771258354187, "global_step": 496438, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.03806734085083, "global_step": 496439, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.135737657546997, "global_step": 496440, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0372297763824463, "global_step": 496441, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0151352882385254, "global_step": 496442, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.03603196144104, "global_step": 496443, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0721676349639893, "global_step": 496444, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0716655254364014, "global_step": 496445, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.006420850753784, "global_step": 496446, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9850120544433594, "global_step": 496447, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.058256149291992, "global_step": 496448, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0932259559631348, "global_step": 496449, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0567495822906494, "global_step": 496450, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9975107908248901, "global_step": 496451, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9568167924880981, "global_step": 496452, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1438822746276855, "global_step": 496453, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.075723648071289, "global_step": 496454, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9696786403656006, "global_step": 496455, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0191948413848877, "global_step": 496456, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1210527420043945, "global_step": 496457, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0434954166412354, "global_step": 496458, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0121140480041504, "global_step": 496459, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0062999725341797, "global_step": 496460, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0196869373321533, "global_step": 496461, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.026716709136963, "global_step": 496462, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0413687229156494, "global_step": 496463, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.022494077682495, "global_step": 496464, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.047401189804077, "global_step": 496465, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0004618167877197, "global_step": 496466, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.078779935836792, "global_step": 496467, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0681018829345703, "global_step": 496468, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0404727458953857, "global_step": 496469, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9996765851974487, "global_step": 496470, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.069355010986328, "global_step": 496471, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0723695755004883, "global_step": 496472, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0264949798583984, "global_step": 496473, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.056128978729248, "global_step": 496474, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0545296669006348, "global_step": 496475, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.011655807495117, "global_step": 496476, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.039292097091675, "global_step": 496477, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1095361709594727, "global_step": 496478, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.030513048171997, "global_step": 496479, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9695197343826294, "global_step": 496480, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.144927978515625, "global_step": 496481, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9946056604385376, "global_step": 496482, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.065227508544922, "global_step": 496483, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.089272975921631, "global_step": 496484, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0601823329925537, "global_step": 496485, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9842408895492554, "global_step": 496486, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0123605728149414, "global_step": 496487, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.996458649635315, "global_step": 496488, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0343551635742188, "global_step": 496489, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.000170946121216, "global_step": 496490, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.033470630645752, "global_step": 496491, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0450732707977295, "global_step": 496492, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0544564723968506, "global_step": 496493, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0358502864837646, "global_step": 496494, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0583250522613525, "global_step": 496495, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9372587203979492, "global_step": 496496, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0087599754333496, "global_step": 496497, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0290327072143555, "global_step": 496498, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1148993968963623, "global_step": 496499, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0381722450256348, "global_step": 496500, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1186482906341553, "global_step": 496501, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.00378155708313, "global_step": 496502, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1076393127441406, "global_step": 496503, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.035534381866455, "global_step": 496504, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0278735160827637, "global_step": 496505, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0782368183135986, "global_step": 496506, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1155993938446045, "global_step": 496507, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0208187103271484, "global_step": 496508, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.087172746658325, "global_step": 496509, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.061274290084839, "global_step": 496510, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1271398067474365, "global_step": 496511, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1591289043426514, "global_step": 496512, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.024454355239868, "global_step": 496513, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1314339637756348, "global_step": 496514, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9813796281814575, "global_step": 496515, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9850512742996216, "global_step": 496516, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1259877681732178, "global_step": 496517, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.054870367050171, "global_step": 496518, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.973309874534607, "global_step": 496519, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.104346990585327, "global_step": 496520, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.000732898712158, "global_step": 496521, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0043551921844482, "global_step": 496522, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9691274166107178, "global_step": 496523, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.170341968536377, "global_step": 496524, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1239614486694336, "global_step": 496525, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.080639362335205, "global_step": 496526, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9640735387802124, "global_step": 496527, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0624964237213135, "global_step": 496528, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0231454372406006, "global_step": 496529, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0562233924865723, "global_step": 496530, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.051400661468506, "global_step": 496531, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1061649322509766, "global_step": 496532, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.120673179626465, "global_step": 496533, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.093505859375, "global_step": 496534, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0549004077911377, "global_step": 496535, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0260512828826904, "global_step": 496536, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.083847761154175, "global_step": 496537, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0350053310394287, "global_step": 496538, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9899635314941406, "global_step": 496539, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1357083320617676, "global_step": 496540, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.083040475845337, "global_step": 496541, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0417819023132324, "global_step": 496542, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0686538219451904, "global_step": 496543, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9993163347244263, "global_step": 496544, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.082104444503784, "global_step": 496545, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1752140522003174, "global_step": 496546, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0587658882141113, "global_step": 496547, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0020875930786133, "global_step": 496548, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.938543438911438, "global_step": 496549, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.030275344848633, "global_step": 496550, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.101921796798706, "global_step": 496551, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1532297134399414, "global_step": 496552, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.070869207382202, "global_step": 496553, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1444735527038574, "global_step": 496554, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.038546323776245, "global_step": 496555, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1404614448547363, "global_step": 496556, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.107038736343384, "global_step": 496557, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1245832443237305, "global_step": 496558, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0493807792663574, "global_step": 496559, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1549298763275146, "global_step": 496560, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1131112575531006, "global_step": 496561, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.005047559738159, "global_step": 496562, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0032684803009033, "global_step": 496563, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.164477586746216, "global_step": 496564, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.112178087234497, "global_step": 496565, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.064925193786621, "global_step": 496566, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.104665994644165, "global_step": 496567, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0890960693359375, "global_step": 496568, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1480166912078857, "global_step": 496569, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.024778366088867, "global_step": 496570, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0051846504211426, "global_step": 496571, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0506045818328857, "global_step": 496572, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9970680475234985, "global_step": 496573, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.048271656036377, "global_step": 496574, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0523428916931152, "global_step": 496575, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0237531661987305, "global_step": 496576, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.058840274810791, "global_step": 496577, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9250173568725586, "global_step": 496578, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1152901649475098, "global_step": 496579, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0052802562713623, "global_step": 496580, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0450992584228516, "global_step": 496581, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0129892826080322, "global_step": 496582, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0501914024353027, "global_step": 496583, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.049571990966797, "global_step": 496584, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0256848335266113, "global_step": 496585, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.027597427368164, "global_step": 496586, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.087082862854004, "global_step": 496587, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0542116165161133, "global_step": 496588, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1225128173828125, "global_step": 496589, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0406014919281006, "global_step": 496590, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9932390451431274, "global_step": 496591, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1309304237365723, "global_step": 496592, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9834765195846558, "global_step": 496593, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.107327938079834, "global_step": 496594, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.948433756828308, "global_step": 496595, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0346245765686035, "global_step": 496596, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.035780429840088, "global_step": 496597, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0871999263763428, "global_step": 496598, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9599456787109375, "global_step": 496599, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9858314990997314, "global_step": 496600, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0493266582489014, "global_step": 496601, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9936976432800293, "global_step": 496602, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.048521041870117, "global_step": 496603, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.146713972091675, "global_step": 496604, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.11190128326416, "global_step": 496605, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0776588916778564, "global_step": 496606, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0668184757232666, "global_step": 496607, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0276660919189453, "global_step": 496608, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.082698345184326, "global_step": 496609, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0638065338134766, "global_step": 496610, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0822761058807373, "global_step": 496611, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0329623222351074, "global_step": 496612, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.094679355621338, "global_step": 496613, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0417277812957764, "global_step": 496614, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.058192729949951, "global_step": 496615, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0168685913085938, "global_step": 496616, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0657498836517334, "global_step": 496617, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9815768003463745, "global_step": 496618, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.016977071762085, "global_step": 496619, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.99755859375, "global_step": 496620, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0394182205200195, "global_step": 496621, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.115757465362549, "global_step": 496622, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0667171478271484, "global_step": 496623, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0329861640930176, "global_step": 496624, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.055443048477173, "global_step": 496625, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.112712860107422, "global_step": 496626, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0091962814331055, "global_step": 496627, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0800089836120605, "global_step": 496628, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0696027278900146, "global_step": 496629, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9648090600967407, "global_step": 496630, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1252634525299072, "global_step": 496631, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.049319267272949, "global_step": 496632, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1054434776306152, "global_step": 496633, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.117177724838257, "global_step": 496634, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.040809392929077, "global_step": 496635, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9752429723739624, "global_step": 496636, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0546045303344727, "global_step": 496637, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0430312156677246, "global_step": 496638, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0913314819335938, "global_step": 496639, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9672292470932007, "global_step": 496640, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.073826313018799, "global_step": 496641, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.016343593597412, "global_step": 496642, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1021103858947754, "global_step": 496643, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0716569423675537, "global_step": 496644, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9715673923492432, "global_step": 496645, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0584592819213867, "global_step": 496646, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0470807552337646, "global_step": 496647, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0059165954589844, "global_step": 496648, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0212814807891846, "global_step": 496649, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0211751461029053, "global_step": 496650, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1325409412384033, "global_step": 496651, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1165707111358643, "global_step": 496652, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.059121608734131, "global_step": 496653, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0575852394104004, "global_step": 496654, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.010197877883911, "global_step": 496655, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.06634521484375, "global_step": 496656, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0364513397216797, "global_step": 496657, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.142258882522583, "global_step": 496658, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.148829460144043, "global_step": 496659, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.053752899169922, "global_step": 496660, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0988571643829346, "global_step": 496661, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.004173994064331, "global_step": 496662, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0353424549102783, "global_step": 496663, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0335378646850586, "global_step": 496664, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0807178020477295, "global_step": 496665, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0939712524414062, "global_step": 496666, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0956532955169678, "global_step": 496667, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9917808771133423, "global_step": 496668, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.081026792526245, "global_step": 496669, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.005568265914917, "global_step": 496670, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1175906658172607, "global_step": 496671, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.106369972229004, "global_step": 496672, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9990451335906982, "global_step": 496673, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1216535568237305, "global_step": 496674, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.023801803588867, "global_step": 496675, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0615451335906982, "global_step": 496676, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1057546138763428, "global_step": 496677, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0466954708099365, "global_step": 496678, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0932395458221436, "global_step": 496679, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.120715618133545, "global_step": 496680, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0093514919281006, "global_step": 496681, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.088440179824829, "global_step": 496682, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1265439987182617, "global_step": 496683, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0923619270324707, "global_step": 496684, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0145633220672607, "global_step": 496685, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.014383554458618, "global_step": 496686, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.094589948654175, "global_step": 496687, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9463142156600952, "global_step": 496688, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.069014549255371, "global_step": 496689, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9619280099868774, "global_step": 496690, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0620839595794678, "global_step": 496691, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.026829719543457, "global_step": 496692, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1040866374969482, "global_step": 496693, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0519208908081055, "global_step": 496694, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0246024131774902, "global_step": 496695, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0212676525115967, "global_step": 496696, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0889811515808105, "global_step": 496697, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1423051357269287, "global_step": 496698, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9701781272888184, "global_step": 496699, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0107662677764893, "global_step": 496700, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.03580904006958, "global_step": 496701, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.039551258087158, "global_step": 496702, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0558741092681885, "global_step": 496703, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.106614112854004, "global_step": 496704, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0767862796783447, "global_step": 496705, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0911898612976074, "global_step": 496706, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0637383460998535, "global_step": 496707, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.055218458175659, "global_step": 496708, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9935165643692017, "global_step": 496709, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0141186714172363, "global_step": 496710, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0560500621795654, "global_step": 496711, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0372767448425293, "global_step": 496712, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0280563831329346, "global_step": 496713, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1452126502990723, "global_step": 496714, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.082421064376831, "global_step": 496715, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1006662845611572, "global_step": 496716, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.084660053253174, "global_step": 496717, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0320229530334473, "global_step": 496718, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0021812915802, "global_step": 496719, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0097460746765137, "global_step": 496720, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1175057888031006, "global_step": 496721, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.114124059677124, "global_step": 496722, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9858895540237427, "global_step": 496723, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1124274730682373, "global_step": 496724, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0998916625976562, "global_step": 496725, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.042872190475464, "global_step": 496726, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0118844509124756, "global_step": 496727, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0241713523864746, "global_step": 496728, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1761069297790527, "global_step": 496729, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0352494716644287, "global_step": 496730, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0370631217956543, "global_step": 496731, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0403501987457275, "global_step": 496732, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9939508438110352, "global_step": 496733, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0911953449249268, "global_step": 496734, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0768537521362305, "global_step": 496735, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0387046337127686, "global_step": 496736, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0893077850341797, "global_step": 496737, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.017139434814453, "global_step": 496738, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.103400707244873, "global_step": 496739, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0347187519073486, "global_step": 496740, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9922477006912231, "global_step": 496741, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0784850120544434, "global_step": 496742, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0947420597076416, "global_step": 496743, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0216119289398193, "global_step": 496744, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0469353199005127, "global_step": 496745, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.078995943069458, "global_step": 496746, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0713412761688232, "global_step": 496747, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0065183639526367, "global_step": 496748, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.005772590637207, "global_step": 496749, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1284799575805664, "global_step": 496750, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9802041053771973, "global_step": 496751, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0461628437042236, "global_step": 496752, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1299870014190674, "global_step": 496753, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9871695041656494, "global_step": 496754, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.056126832962036, "global_step": 496755, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9550936222076416, "global_step": 496756, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0003836154937744, "global_step": 496757, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0358262062072754, "global_step": 496758, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0520453453063965, "global_step": 496759, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0675532817840576, "global_step": 496760, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.073415994644165, "global_step": 496761, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0647921562194824, "global_step": 496762, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0605287551879883, "global_step": 496763, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.032430648803711, "global_step": 496764, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9602994918823242, "global_step": 496765, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0397045612335205, "global_step": 496766, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.088099956512451, "global_step": 496767, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.120530366897583, "global_step": 496768, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.924328327178955, "global_step": 496769, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9811023473739624, "global_step": 496770, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.108382225036621, "global_step": 496771, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.015906810760498, "global_step": 496772, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0080676078796387, "global_step": 496773, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0019874572753906, "global_step": 496774, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0583837032318115, "global_step": 496775, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.082890033721924, "global_step": 496776, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0368762016296387, "global_step": 496777, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0705528259277344, "global_step": 496778, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.076345443725586, "global_step": 496779, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0719211101531982, "global_step": 496780, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1182751655578613, "global_step": 496781, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.051687479019165, "global_step": 496782, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.162470579147339, "global_step": 496783, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9830018281936646, "global_step": 496784, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.15102481842041, "global_step": 496785, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9484094381332397, "global_step": 496786, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.106856107711792, "global_step": 496787, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1433663368225098, "global_step": 496788, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.088125705718994, "global_step": 496789, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.062124729156494, "global_step": 496790, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0586307048797607, "global_step": 496791, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9720368385314941, "global_step": 496792, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.038515090942383, "global_step": 496793, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0404393672943115, "global_step": 496794, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0444860458374023, "global_step": 496795, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0779638290405273, "global_step": 496796, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.076747179031372, "global_step": 496797, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0342795848846436, "global_step": 496798, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9834736585617065, "global_step": 496799, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1441292762756348, "global_step": 496800, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.067815065383911, "global_step": 496801, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0034871101379395, "global_step": 496802, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0657243728637695, "global_step": 496803, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.07126522064209, "global_step": 496804, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9934604167938232, "global_step": 496805, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0517024993896484, "global_step": 496806, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.066901922225952, "global_step": 496807, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0707647800445557, "global_step": 496808, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9646296501159668, "global_step": 496809, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0777273178100586, "global_step": 496810, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.045821189880371, "global_step": 496811, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.030256509780884, "global_step": 496812, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0663022994995117, "global_step": 496813, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9431703090667725, "global_step": 496814, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9620904922485352, "global_step": 496815, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.029357671737671, "global_step": 496816, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0207369327545166, "global_step": 496817, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.095052480697632, "global_step": 496818, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0646772384643555, "global_step": 496819, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.09488844871521, "global_step": 496820, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.069905996322632, "global_step": 496821, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0672640800476074, "global_step": 496822, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9953693151474, "global_step": 496823, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0060553550720215, "global_step": 496824, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9663310050964355, "global_step": 496825, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0491273403167725, "global_step": 496826, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1220321655273438, "global_step": 496827, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0953094959259033, "global_step": 496828, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0484097003936768, "global_step": 496829, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0651798248291016, "global_step": 496830, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.05031418800354, "global_step": 496831, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.095797300338745, "global_step": 496832, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1723947525024414, "global_step": 496833, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0128328800201416, "global_step": 496834, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.121436834335327, "global_step": 496835, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1031060218811035, "global_step": 496836, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0316200256347656, "global_step": 496837, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.121163845062256, "global_step": 496838, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9982532262802124, "global_step": 496839, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0389251708984375, "global_step": 496840, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0257346630096436, "global_step": 496841, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.056541919708252, "global_step": 496842, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9521468877792358, "global_step": 496843, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1124908924102783, "global_step": 496844, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0088508129119873, "global_step": 496845, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.02675199508667, "global_step": 496846, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.020864725112915, "global_step": 496847, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0470776557922363, "global_step": 496848, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0853517055511475, "global_step": 496849, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9949930906295776, "global_step": 496850, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0420897006988525, "global_step": 496851, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0452191829681396, "global_step": 496852, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.151211977005005, "global_step": 496853, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0792529582977295, "global_step": 496854, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1037485599517822, "global_step": 496855, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0318617820739746, "global_step": 496856, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.052875518798828, "global_step": 496857, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0697152614593506, "global_step": 496858, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1213161945343018, "global_step": 496859, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0462682247161865, "global_step": 496860, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.12044358253479, "global_step": 496861, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0552594661712646, "global_step": 496862, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.072455644607544, "global_step": 496863, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0740816593170166, "global_step": 496864, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9443714618682861, "global_step": 496865, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0373833179473877, "global_step": 496866, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0507638454437256, "global_step": 496867, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0208418369293213, "global_step": 496868, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0885651111602783, "global_step": 496869, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.089205026626587, "global_step": 496870, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1025595664978027, "global_step": 496871, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0633106231689453, "global_step": 496872, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0462534427642822, "global_step": 496873, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.080918312072754, "global_step": 496874, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0811657905578613, "global_step": 496875, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0975000858306885, "global_step": 496876, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.066051483154297, "global_step": 496877, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1784651279449463, "global_step": 496878, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0038983821868896, "global_step": 496879, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0417280197143555, "global_step": 496880, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1392807960510254, "global_step": 496881, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.031801462173462, "global_step": 496882, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1441831588745117, "global_step": 496883, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1221985816955566, "global_step": 496884, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.007326126098633, "global_step": 496885, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0721828937530518, "global_step": 496886, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0829083919525146, "global_step": 496887, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.059227466583252, "global_step": 496888, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.035759449005127, "global_step": 496889, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0229883193969727, "global_step": 496890, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0864193439483643, "global_step": 496891, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0878703594207764, "global_step": 496892, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1581265926361084, "global_step": 496893, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9972693920135498, "global_step": 496894, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0561747550964355, "global_step": 496895, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0430197715759277, "global_step": 496896, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0359623432159424, "global_step": 496897, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0781309604644775, "global_step": 496898, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1128218173980713, "global_step": 496899, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1133947372436523, "global_step": 496900, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.056802749633789, "global_step": 496901, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0628485679626465, "global_step": 496902, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.053690195083618, "global_step": 496903, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.034639596939087, "global_step": 496904, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9956402778625488, "global_step": 496905, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0794851779937744, "global_step": 496906, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9747060537338257, "global_step": 496907, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0281364917755127, "global_step": 496908, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1040573120117188, "global_step": 496909, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0681209564208984, "global_step": 496910, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0491905212402344, "global_step": 496911, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.065255641937256, "global_step": 496912, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.065605640411377, "global_step": 496913, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.037506580352783, "global_step": 496914, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.012645721435547, "global_step": 496915, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.065894603729248, "global_step": 496916, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0869994163513184, "global_step": 496917, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0300450325012207, "global_step": 496918, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0708813667297363, "global_step": 496919, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0875232219696045, "global_step": 496920, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.098888397216797, "global_step": 496921, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.032487630844116, "global_step": 496922, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0176010131835938, "global_step": 496923, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0900988578796387, "global_step": 496924, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0660977363586426, "global_step": 496925, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0670104026794434, "global_step": 496926, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0648841857910156, "global_step": 496927, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.068441152572632, "global_step": 496928, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0446419715881348, "global_step": 496929, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.095273017883301, "global_step": 496930, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0720648765563965, "global_step": 496931, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.099219560623169, "global_step": 496932, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1120004653930664, "global_step": 496933, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1002120971679688, "global_step": 496934, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0497536659240723, "global_step": 496935, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0378308296203613, "global_step": 496936, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0575859546661377, "global_step": 496937, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.165175437927246, "global_step": 496938, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0293917655944824, "global_step": 496939, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.046379804611206, "global_step": 496940, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0557992458343506, "global_step": 496941, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0498046875, "global_step": 496942, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9845850467681885, "global_step": 496943, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1049230098724365, "global_step": 496944, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0798723697662354, "global_step": 496945, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0654618740081787, "global_step": 496946, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.065004587173462, "global_step": 496947, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9779623746871948, "global_step": 496948, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0487797260284424, "global_step": 496949, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.085505723953247, "global_step": 496950, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0920608043670654, "global_step": 496951, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0274412631988525, "global_step": 496952, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.992799162864685, "global_step": 496953, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.045191764831543, "global_step": 496954, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.038313388824463, "global_step": 496955, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.076204538345337, "global_step": 496956, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0481154918670654, "global_step": 496957, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1396613121032715, "global_step": 496958, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0786781311035156, "global_step": 496959, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.053844928741455, "global_step": 496960, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.033083915710449, "global_step": 496961, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0896425247192383, "global_step": 496962, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0963683128356934, "global_step": 496963, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0669703483581543, "global_step": 496964, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1535229682922363, "global_step": 496965, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0347394943237305, "global_step": 496966, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0756115913391113, "global_step": 496967, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1114001274108887, "global_step": 496968, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0073719024658203, "global_step": 496969, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0683579444885254, "global_step": 496970, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1425089836120605, "global_step": 496971, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.035503387451172, "global_step": 496972, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0054094791412354, "global_step": 496973, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0631728172302246, "global_step": 496974, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9896411895751953, "global_step": 496975, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.077834367752075, "global_step": 496976, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.046175479888916, "global_step": 496977, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0564804077148438, "global_step": 496978, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.048490285873413, "global_step": 496979, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.113985061645508, "global_step": 496980, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.108103036880493, "global_step": 496981, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1750173568725586, "global_step": 496982, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1111886501312256, "global_step": 496983, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0787742137908936, "global_step": 496984, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0175960063934326, "global_step": 496985, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0820300579071045, "global_step": 496986, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9880809783935547, "global_step": 496987, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.087221384048462, "global_step": 496988, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0509748458862305, "global_step": 496989, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1175670623779297, "global_step": 496990, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9896516799926758, "global_step": 496991, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9853980541229248, "global_step": 496992, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1298651695251465, "global_step": 496993, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.039254665374756, "global_step": 496994, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0111334323883057, "global_step": 496995, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0984063148498535, "global_step": 496996, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0999362468719482, "global_step": 496997, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0541465282440186, "global_step": 496998, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0864953994750977, "global_step": 496999, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0155231952667236, "global_step": 497000, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9943782091140747, "global_step": 497001, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0734775066375732, "global_step": 497002, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9524493217468262, "global_step": 497003, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0826990604400635, "global_step": 497004, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0952677726745605, "global_step": 497005, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0649023056030273, "global_step": 497006, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0461812019348145, "global_step": 497007, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0117876529693604, "global_step": 497008, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0302834510803223, "global_step": 497009, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.040086030960083, "global_step": 497010, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0546317100524902, "global_step": 497011, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.057457447052002, "global_step": 497012, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0574238300323486, "global_step": 497013, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.091644763946533, "global_step": 497014, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0469117164611816, "global_step": 497015, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.058497905731201, "global_step": 497016, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9823949337005615, "global_step": 497017, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0909109115600586, "global_step": 497018, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.031731367111206, "global_step": 497019, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9959379434585571, "global_step": 497020, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.058586597442627, "global_step": 497021, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.000305652618408, "global_step": 497022, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.03004789352417, "global_step": 497023, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.139927864074707, "global_step": 497024, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.019956350326538, "global_step": 497025, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.045466423034668, "global_step": 497026, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.014177083969116, "global_step": 497027, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.086160182952881, "global_step": 497028, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0435681343078613, "global_step": 497029, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0511155128479004, "global_step": 497030, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0198147296905518, "global_step": 497031, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.021944522857666, "global_step": 497032, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.053638458251953, "global_step": 497033, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.131725549697876, "global_step": 497034, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0805318355560303, "global_step": 497035, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0469019412994385, "global_step": 497036, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.024477481842041, "global_step": 497037, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1185834407806396, "global_step": 497038, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.018897294998169, "global_step": 497039, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0939462184906006, "global_step": 497040, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0107057094573975, "global_step": 497041, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1257848739624023, "global_step": 497042, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.021766185760498, "global_step": 497043, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.084618091583252, "global_step": 497044, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0613787174224854, "global_step": 497045, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0547409057617188, "global_step": 497046, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9520591497421265, "global_step": 497047, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0352444648742676, "global_step": 497048, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0699362754821777, "global_step": 497049, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0945825576782227, "global_step": 497050, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.094895839691162, "global_step": 497051, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.053494930267334, "global_step": 497052, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0638132095336914, "global_step": 497053, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0533924102783203, "global_step": 497054, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0867698192596436, "global_step": 497055, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0415408611297607, "global_step": 497056, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.121746778488159, "global_step": 497057, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0469558238983154, "global_step": 497058, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.018406629562378, "global_step": 497059, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.083681106567383, "global_step": 497060, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.031437873840332, "global_step": 497061, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9859474897384644, "global_step": 497062, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9695498943328857, "global_step": 497063, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.993499517440796, "global_step": 497064, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0274746417999268, "global_step": 497065, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.068793296813965, "global_step": 497066, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0925447940826416, "global_step": 497067, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0393567085266113, "global_step": 497068, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0201778411865234, "global_step": 497069, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0229175090789795, "global_step": 497070, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9830650091171265, "global_step": 497071, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.086688756942749, "global_step": 497072, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1054646968841553, "global_step": 497073, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.008280038833618, "global_step": 497074, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.049323797225952, "global_step": 497075, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0952930450439453, "global_step": 497076, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.033618211746216, "global_step": 497077, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1019890308380127, "global_step": 497078, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1241254806518555, "global_step": 497079, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.189714193344116, "global_step": 497080, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0896689891815186, "global_step": 497081, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.096550226211548, "global_step": 497082, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0743069648742676, "global_step": 497083, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0808522701263428, "global_step": 497084, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9106462001800537, "global_step": 497085, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.961037516593933, "global_step": 497086, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0519301891326904, "global_step": 497087, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.027067184448242, "global_step": 497088, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9748539924621582, "global_step": 497089, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0108182430267334, "global_step": 497090, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.119173526763916, "global_step": 497091, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.104597806930542, "global_step": 497092, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0611517429351807, "global_step": 497093, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0406196117401123, "global_step": 497094, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.060157299041748, "global_step": 497095, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0327043533325195, "global_step": 497096, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.012709140777588, "global_step": 497097, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.056654453277588, "global_step": 497098, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.955657958984375, "global_step": 497099, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0691463947296143, "global_step": 497100, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1205625534057617, "global_step": 497101, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.145857572555542, "global_step": 497102, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0680620670318604, "global_step": 497103, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0988965034484863, "global_step": 497104, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0759708881378174, "global_step": 497105, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0898451805114746, "global_step": 497106, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.069164276123047, "global_step": 497107, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9880694150924683, "global_step": 497108, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.107581853866577, "global_step": 497109, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.032191514968872, "global_step": 497110, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.13533091545105, "global_step": 497111, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.01729679107666, "global_step": 497112, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0874080657958984, "global_step": 497113, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0517690181732178, "global_step": 497114, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0053560733795166, "global_step": 497115, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.075526237487793, "global_step": 497116, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0469090938568115, "global_step": 497117, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.996652603149414, "global_step": 497118, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9944950342178345, "global_step": 497119, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.115748882293701, "global_step": 497120, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0475258827209473, "global_step": 497121, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1111531257629395, "global_step": 497122, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.035719394683838, "global_step": 497123, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0855512619018555, "global_step": 497124, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1007509231567383, "global_step": 497125, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9197070598602295, "global_step": 497126, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.069084644317627, "global_step": 497127, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.124506711959839, "global_step": 497128, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.091359853744507, "global_step": 497129, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0823283195495605, "global_step": 497130, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9974061250686646, "global_step": 497131, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1370439529418945, "global_step": 497132, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0016684532165527, "global_step": 497133, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.103576183319092, "global_step": 497134, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1154897212982178, "global_step": 497135, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0582425594329834, "global_step": 497136, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0550320148468018, "global_step": 497137, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.074275493621826, "global_step": 497138, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0654287338256836, "global_step": 497139, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0062506198883057, "global_step": 497140, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9951939582824707, "global_step": 497141, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.024649143218994, "global_step": 497142, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.124473810195923, "global_step": 497143, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0546717643737793, "global_step": 497144, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1075031757354736, "global_step": 497145, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.004549980163574, "global_step": 497146, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9021400213241577, "global_step": 497147, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0808310508728027, "global_step": 497148, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0902280807495117, "global_step": 497149, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.053555488586426, "global_step": 497150, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1374058723449707, "global_step": 497151, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1266884803771973, "global_step": 497152, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.030942440032959, "global_step": 497153, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0235745906829834, "global_step": 497154, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.040186643600464, "global_step": 497155, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.04101300239563, "global_step": 497156, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1438891887664795, "global_step": 497157, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0594663619995117, "global_step": 497158, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.994674563407898, "global_step": 497159, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1246283054351807, "global_step": 497160, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9737902879714966, "global_step": 497161, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.061047315597534, "global_step": 497162, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.031020164489746, "global_step": 497163, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.112461566925049, "global_step": 497164, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9948468208312988, "global_step": 497165, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.99097740650177, "global_step": 497166, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0589919090270996, "global_step": 497167, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0633909702301025, "global_step": 497168, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.121458053588867, "global_step": 497169, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.10300612449646, "global_step": 497170, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0466156005859375, "global_step": 497171, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0651581287384033, "global_step": 497172, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0166051387786865, "global_step": 497173, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0602638721466064, "global_step": 497174, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0444986820220947, "global_step": 497175, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1213786602020264, "global_step": 497176, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.107938051223755, "global_step": 497177, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0535972118377686, "global_step": 497178, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.053853988647461, "global_step": 497179, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.069681406021118, "global_step": 497180, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0091006755828857, "global_step": 497181, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0703353881835938, "global_step": 497182, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.133878231048584, "global_step": 497183, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.106971025466919, "global_step": 497184, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0516839027404785, "global_step": 497185, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1293506622314453, "global_step": 497186, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.093726634979248, "global_step": 497187, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0588128566741943, "global_step": 497188, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.073239326477051, "global_step": 497189, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.033362865447998, "global_step": 497190, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9662728309631348, "global_step": 497191, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.162370443344116, "global_step": 497192, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0498244762420654, "global_step": 497193, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.017253875732422, "global_step": 497194, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0847110748291016, "global_step": 497195, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.061760663986206, "global_step": 497196, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.059521198272705, "global_step": 497197, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.160731315612793, "global_step": 497198, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0964231491088867, "global_step": 497199, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1426734924316406, "global_step": 497200, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0613811016082764, "global_step": 497201, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0667002201080322, "global_step": 497202, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1048433780670166, "global_step": 497203, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.090120553970337, "global_step": 497204, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0581440925598145, "global_step": 497205, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0876593589782715, "global_step": 497206, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.063673734664917, "global_step": 497207, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.032902240753174, "global_step": 497208, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9451260566711426, "global_step": 497209, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0511314868927, "global_step": 497210, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.100937604904175, "global_step": 497211, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1092047691345215, "global_step": 497212, "epoch": 862, "lr": 5e-05}
{"train_loss": 1.9158648252487183, "global_step": 497213, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.112706184387207, "global_step": 497214, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0460832118988037, "global_step": 497215, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1274452209472656, "global_step": 497216, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.038065195083618, "global_step": 497217, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0227198600769043, "global_step": 497218, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.141085386276245, "global_step": 497219, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.033393383026123, "global_step": 497220, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1111247539520264, "global_step": 497221, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0270237922668457, "global_step": 497222, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.085244655609131, "global_step": 497223, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.03989839553833, "global_step": 497224, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1635348796844482, "global_step": 497225, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.1165366172790527, "global_step": 497226, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0526533126831055, "global_step": 497227, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0010805130004883, "global_step": 497228, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.054955244064331, "global_step": 497229, "epoch": 862, "lr": 5e-05}
{"train_loss": 2.0601301193237305, "global_step": 497230, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0876662731170654, "global_step": 497231, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0619001388549805, "global_step": 497232, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.054872751235962, "global_step": 497233, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0659945011138916, "global_step": 497234, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0780603885650635, "global_step": 497235, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9895251989364624, "global_step": 497236, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0953171253204346, "global_step": 497237, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.011936664581299, "global_step": 497238, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.063927412033081, "global_step": 497239, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0677196979522705, "global_step": 497240, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0500168800354004, "global_step": 497241, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0289132595062256, "global_step": 497242, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9872363805770874, "global_step": 497243, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0340476036071777, "global_step": 497244, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1359493732452393, "global_step": 497245, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1148593425750732, "global_step": 497246, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0337319374084473, "global_step": 497247, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1630821228027344, "global_step": 497248, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.071554660797119, "global_step": 497249, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9677387475967407, "global_step": 497250, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0737318992614746, "global_step": 497251, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.968463659286499, "global_step": 497252, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.8991222381591797, "global_step": 497253, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1536777019500732, "global_step": 497254, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0688016414642334, "global_step": 497255, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1082191467285156, "global_step": 497256, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.096626043319702, "global_step": 497257, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0635368824005127, "global_step": 497258, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0118985176086426, "global_step": 497259, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.002673864364624, "global_step": 497260, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9568883180618286, "global_step": 497261, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0030105113983154, "global_step": 497262, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9843066930770874, "global_step": 497263, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.110492706298828, "global_step": 497264, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.031409740447998, "global_step": 497265, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.103926181793213, "global_step": 497266, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0444400310516357, "global_step": 497267, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9611625671386719, "global_step": 497268, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9749488830566406, "global_step": 497269, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.000267505645752, "global_step": 497270, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.046584129333496, "global_step": 497271, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.041600227355957, "global_step": 497272, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9988858699798584, "global_step": 497273, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1252501010894775, "global_step": 497274, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.153109550476074, "global_step": 497275, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1406493186950684, "global_step": 497276, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.065659999847412, "global_step": 497277, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9790722131729126, "global_step": 497278, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0217444896698, "global_step": 497279, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.067096471786499, "global_step": 497280, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.03446102142334, "global_step": 497281, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0396854877471924, "global_step": 497282, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0953314304351807, "global_step": 497283, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0501296520233154, "global_step": 497284, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0113525390625, "global_step": 497285, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1098599433898926, "global_step": 497286, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0542194843292236, "global_step": 497287, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.003793478012085, "global_step": 497288, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.06181001663208, "global_step": 497289, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0085813999176025, "global_step": 497290, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.024453639984131, "global_step": 497291, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.157355785369873, "global_step": 497292, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0033226013183594, "global_step": 497293, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.100879192352295, "global_step": 497294, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9466028213500977, "global_step": 497295, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0033929347991943, "global_step": 497296, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0869715213775635, "global_step": 497297, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0975611209869385, "global_step": 497298, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0705931186676025, "global_step": 497299, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0702357292175293, "global_step": 497300, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.976091980934143, "global_step": 497301, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.99717378616333, "global_step": 497302, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.997015118598938, "global_step": 497303, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9942700862884521, "global_step": 497304, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0141549110412598, "global_step": 497305, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0836212635040283, "global_step": 497306, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0353941917419434, "global_step": 497307, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9815595149993896, "global_step": 497308, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0484018325805664, "global_step": 497309, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9594593048095703, "global_step": 497310, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.021921157836914, "global_step": 497311, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0663034915924072, "global_step": 497312, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.999855399131775, "global_step": 497313, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0540506839752197, "global_step": 497314, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0646822452545166, "global_step": 497315, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0684404373168945, "global_step": 497316, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0703625679016113, "global_step": 497317, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0785207748413086, "global_step": 497318, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1119377613067627, "global_step": 497319, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.078521966934204, "global_step": 497320, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.975417137145996, "global_step": 497321, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.933696985244751, "global_step": 497322, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0705413818359375, "global_step": 497323, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0139989852905273, "global_step": 497324, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0659537315368652, "global_step": 497325, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0452914237976074, "global_step": 497326, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.05338716506958, "global_step": 497327, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0660505294799805, "global_step": 497328, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0710198879241943, "global_step": 497329, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.061099052429199, "global_step": 497330, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0081472396850586, "global_step": 497331, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9653069972991943, "global_step": 497332, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0170910358428955, "global_step": 497333, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0144190788269043, "global_step": 497334, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0519790649414062, "global_step": 497335, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9294215440750122, "global_step": 497336, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0527961254119873, "global_step": 497337, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9898239374160767, "global_step": 497338, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.003012180328369, "global_step": 497339, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0064055919647217, "global_step": 497340, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9819306135177612, "global_step": 497341, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9735053777694702, "global_step": 497342, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.037322521209717, "global_step": 497343, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.971678376197815, "global_step": 497344, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0946033000946045, "global_step": 497345, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0511207580566406, "global_step": 497346, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0928773880004883, "global_step": 497347, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.100008249282837, "global_step": 497348, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9838833808898926, "global_step": 497349, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9976743459701538, "global_step": 497350, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9710062742233276, "global_step": 497351, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0150387287139893, "global_step": 497352, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9656531810760498, "global_step": 497353, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.097285509109497, "global_step": 497354, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.080458164215088, "global_step": 497355, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0862996578216553, "global_step": 497356, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.076098918914795, "global_step": 497357, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0934011936187744, "global_step": 497358, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.043332576751709, "global_step": 497359, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0053372383117676, "global_step": 497360, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0520567893981934, "global_step": 497361, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.131922483444214, "global_step": 497362, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0520851612091064, "global_step": 497363, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.006571054458618, "global_step": 497364, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.029087781906128, "global_step": 497365, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9733175039291382, "global_step": 497366, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0724070072174072, "global_step": 497367, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.004868984222412, "global_step": 497368, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0164072513580322, "global_step": 497369, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.046835422515869, "global_step": 497370, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0558314323425293, "global_step": 497371, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1101603507995605, "global_step": 497372, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0431082248687744, "global_step": 497373, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.100877285003662, "global_step": 497374, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9744516611099243, "global_step": 497375, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1297340393066406, "global_step": 497376, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1165168285369873, "global_step": 497377, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0398311614990234, "global_step": 497378, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.065091609954834, "global_step": 497379, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9656994342803955, "global_step": 497380, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1248297691345215, "global_step": 497381, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.096897840499878, "global_step": 497382, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0764596462249756, "global_step": 497383, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.104621410369873, "global_step": 497384, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.004411458969116, "global_step": 497385, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1010985374450684, "global_step": 497386, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0088608264923096, "global_step": 497387, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9987229108810425, "global_step": 497388, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9868800640106201, "global_step": 497389, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0101635456085205, "global_step": 497390, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.049128770828247, "global_step": 497391, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0617122650146484, "global_step": 497392, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.073756694793701, "global_step": 497393, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.128565788269043, "global_step": 497394, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0664427280426025, "global_step": 497395, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0835511684417725, "global_step": 497396, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0550951957702637, "global_step": 497397, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.102731466293335, "global_step": 497398, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.039679527282715, "global_step": 497399, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0874271392822266, "global_step": 497400, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.119055986404419, "global_step": 497401, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.020279884338379, "global_step": 497402, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.006373405456543, "global_step": 497403, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.128894090652466, "global_step": 497404, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0798139572143555, "global_step": 497405, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9946541786193848, "global_step": 497406, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.019306182861328, "global_step": 497407, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0816049575805664, "global_step": 497408, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.131908416748047, "global_step": 497409, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.041898727416992, "global_step": 497410, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0599353313446045, "global_step": 497411, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.050596237182617, "global_step": 497412, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.137570381164551, "global_step": 497413, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0060250759124756, "global_step": 497414, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.047053098678589, "global_step": 497415, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.031104803085327, "global_step": 497416, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.981346607208252, "global_step": 497417, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.066577672958374, "global_step": 497418, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.083601951599121, "global_step": 497419, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.039067268371582, "global_step": 497420, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.003283977508545, "global_step": 497421, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.992244839668274, "global_step": 497422, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9889492988586426, "global_step": 497423, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1354260444641113, "global_step": 497424, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.147233009338379, "global_step": 497425, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0993504524230957, "global_step": 497426, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9848817586898804, "global_step": 497427, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.101539134979248, "global_step": 497428, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0626015663146973, "global_step": 497429, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.038201093673706, "global_step": 497430, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0753257274627686, "global_step": 497431, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.074495553970337, "global_step": 497432, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0436837673187256, "global_step": 497433, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.174445390701294, "global_step": 497434, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9812662601470947, "global_step": 497435, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.077526807785034, "global_step": 497436, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0857105255126953, "global_step": 497437, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1042232513427734, "global_step": 497438, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.108086585998535, "global_step": 497439, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.096276044845581, "global_step": 497440, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9612741470336914, "global_step": 497441, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0274956226348877, "global_step": 497442, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.077836275100708, "global_step": 497443, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0461769104003906, "global_step": 497444, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.017263412475586, "global_step": 497445, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0462210178375244, "global_step": 497446, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9663041830062866, "global_step": 497447, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.020249605178833, "global_step": 497448, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.04795503616333, "global_step": 497449, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.08823823928833, "global_step": 497450, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.064241886138916, "global_step": 497451, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.084425687789917, "global_step": 497452, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0081703662872314, "global_step": 497453, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9997973442077637, "global_step": 497454, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0347788333892822, "global_step": 497455, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.014413833618164, "global_step": 497456, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.051095724105835, "global_step": 497457, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0696518421173096, "global_step": 497458, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.131834030151367, "global_step": 497459, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9820514917373657, "global_step": 497460, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.101881980895996, "global_step": 497461, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.046844959259033, "global_step": 497462, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.096313714981079, "global_step": 497463, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.087266445159912, "global_step": 497464, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1089107990264893, "global_step": 497465, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0709471702575684, "global_step": 497466, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0690042972564697, "global_step": 497467, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0966567993164062, "global_step": 497468, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.087703227996826, "global_step": 497469, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9674450159072876, "global_step": 497470, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.018303155899048, "global_step": 497471, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0589797496795654, "global_step": 497472, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9301154613494873, "global_step": 497473, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.052747964859009, "global_step": 497474, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0422027111053467, "global_step": 497475, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.148728132247925, "global_step": 497476, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9695228338241577, "global_step": 497477, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0368010997772217, "global_step": 497478, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.060929536819458, "global_step": 497479, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.104614019393921, "global_step": 497480, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0443286895751953, "global_step": 497481, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.020343780517578, "global_step": 497482, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1230359077453613, "global_step": 497483, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.037360429763794, "global_step": 497484, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.099637746810913, "global_step": 497485, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.030942916870117, "global_step": 497486, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.026188611984253, "global_step": 497487, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.027376651763916, "global_step": 497488, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1644229888916016, "global_step": 497489, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1066477298736572, "global_step": 497490, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.131618022918701, "global_step": 497491, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0604610443115234, "global_step": 497492, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0045223236083984, "global_step": 497493, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0668578147888184, "global_step": 497494, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.054825782775879, "global_step": 497495, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0230484008789062, "global_step": 497496, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0695950984954834, "global_step": 497497, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0573136806488037, "global_step": 497498, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.051286458969116, "global_step": 497499, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0670652389526367, "global_step": 497500, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.019737958908081, "global_step": 497501, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.065849542617798, "global_step": 497502, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.143932580947876, "global_step": 497503, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.065918445587158, "global_step": 497504, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0609490871429443, "global_step": 497505, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.070091724395752, "global_step": 497506, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.010066032409668, "global_step": 497507, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9932135343551636, "global_step": 497508, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0768585205078125, "global_step": 497509, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9321622848510742, "global_step": 497510, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0583322048187256, "global_step": 497511, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0211620330810547, "global_step": 497512, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1375222206115723, "global_step": 497513, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0552384853363037, "global_step": 497514, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0279572010040283, "global_step": 497515, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.087254524230957, "global_step": 497516, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.047053337097168, "global_step": 497517, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0622193813323975, "global_step": 497518, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0879223346710205, "global_step": 497519, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0257372856140137, "global_step": 497520, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9676177501678467, "global_step": 497521, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9547045230865479, "global_step": 497522, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.972398042678833, "global_step": 497523, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.039003372192383, "global_step": 497524, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0581696033477783, "global_step": 497525, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1182522773742676, "global_step": 497526, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0767054557800293, "global_step": 497527, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1241800785064697, "global_step": 497528, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1348891258239746, "global_step": 497529, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0699758529663086, "global_step": 497530, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0036911964416504, "global_step": 497531, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.05100417137146, "global_step": 497532, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0487356185913086, "global_step": 497533, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.026512384414673, "global_step": 497534, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.8716386556625366, "global_step": 497535, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0760934352874756, "global_step": 497536, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0719385147094727, "global_step": 497537, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0637176036834717, "global_step": 497538, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.144345283508301, "global_step": 497539, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9956616163253784, "global_step": 497540, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9482884407043457, "global_step": 497541, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0718560218811035, "global_step": 497542, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.030886173248291, "global_step": 497543, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1204662322998047, "global_step": 497544, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0199344158172607, "global_step": 497545, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0294888019561768, "global_step": 497546, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.005399227142334, "global_step": 497547, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.053849935531616, "global_step": 497548, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.000211238861084, "global_step": 497549, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0508270263671875, "global_step": 497550, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.155026435852051, "global_step": 497551, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1329925060272217, "global_step": 497552, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0753509998321533, "global_step": 497553, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.088029146194458, "global_step": 497554, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0518178939819336, "global_step": 497555, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0677061080932617, "global_step": 497556, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.002460241317749, "global_step": 497557, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9752700328826904, "global_step": 497558, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0599148273468018, "global_step": 497559, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9969185590744019, "global_step": 497560, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0625758171081543, "global_step": 497561, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.046088218688965, "global_step": 497562, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.125856399536133, "global_step": 497563, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.117244243621826, "global_step": 497564, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9987170696258545, "global_step": 497565, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.989650011062622, "global_step": 497566, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0249974727630615, "global_step": 497567, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0198445320129395, "global_step": 497568, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1459760665893555, "global_step": 497569, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9461348056793213, "global_step": 497570, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0212292671203613, "global_step": 497571, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.981825828552246, "global_step": 497572, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0441036224365234, "global_step": 497573, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0737574100494385, "global_step": 497574, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.01308274269104, "global_step": 497575, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0144591331481934, "global_step": 497576, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0695624351501465, "global_step": 497577, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0176286697387695, "global_step": 497578, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0971179008483887, "global_step": 497579, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.039940357208252, "global_step": 497580, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0016884803771973, "global_step": 497581, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.978873372077942, "global_step": 497582, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0918118953704834, "global_step": 497583, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0679731369018555, "global_step": 497584, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.068734645843506, "global_step": 497585, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.002981424331665, "global_step": 497586, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9820005893707275, "global_step": 497587, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0545918941497803, "global_step": 497588, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0634241104125977, "global_step": 497589, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0814619064331055, "global_step": 497590, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0323143005371094, "global_step": 497591, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9661012887954712, "global_step": 497592, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1362991333007812, "global_step": 497593, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.067077875137329, "global_step": 497594, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.063551425933838, "global_step": 497595, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.17111873626709, "global_step": 497596, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0214004516601562, "global_step": 497597, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.150320053100586, "global_step": 497598, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0299715995788574, "global_step": 497599, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0797526836395264, "global_step": 497600, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.095372200012207, "global_step": 497601, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0567002296447754, "global_step": 497602, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.117206573486328, "global_step": 497603, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.014322280883789, "global_step": 497604, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.03725004196167, "global_step": 497605, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.071232557296753, "global_step": 497606, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0913779735565186, "global_step": 497607, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0461220741271973, "global_step": 497608, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0887832641601562, "global_step": 497609, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0740654468536377, "global_step": 497610, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0565366744995117, "global_step": 497611, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9781990051269531, "global_step": 497612, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0168867111206055, "global_step": 497613, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.073845624923706, "global_step": 497614, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9839208126068115, "global_step": 497615, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0658671855926514, "global_step": 497616, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.075139045715332, "global_step": 497617, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.060727596282959, "global_step": 497618, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0214035511016846, "global_step": 497619, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.082134485244751, "global_step": 497620, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0266923904418945, "global_step": 497621, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0386648178100586, "global_step": 497622, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.087728500366211, "global_step": 497623, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.066556215286255, "global_step": 497624, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1122019290924072, "global_step": 497625, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0785329341888428, "global_step": 497626, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0351319313049316, "global_step": 497627, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.975756049156189, "global_step": 497628, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1507115364074707, "global_step": 497629, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0443742275238037, "global_step": 497630, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0073812007904053, "global_step": 497631, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.020941734313965, "global_step": 497632, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0379114151000977, "global_step": 497633, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0806164741516113, "global_step": 497634, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1125125885009766, "global_step": 497635, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9795153141021729, "global_step": 497636, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.975480318069458, "global_step": 497637, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0901174545288086, "global_step": 497638, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9902119636535645, "global_step": 497639, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.07623028755188, "global_step": 497640, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.051776170730591, "global_step": 497641, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0550637245178223, "global_step": 497642, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0495553016662598, "global_step": 497643, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1089096069335938, "global_step": 497644, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.072636842727661, "global_step": 497645, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.987404465675354, "global_step": 497646, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.094796657562256, "global_step": 497647, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.091925859451294, "global_step": 497648, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.039346933364868, "global_step": 497649, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0038812160491943, "global_step": 497650, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1167194843292236, "global_step": 497651, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0895309448242188, "global_step": 497652, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9681811332702637, "global_step": 497653, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.101914167404175, "global_step": 497654, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0962936878204346, "global_step": 497655, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0932624340057373, "global_step": 497656, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0398967266082764, "global_step": 497657, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0529818534851074, "global_step": 497658, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.079942226409912, "global_step": 497659, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.05595326423645, "global_step": 497660, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0120439529418945, "global_step": 497661, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.023797035217285, "global_step": 497662, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.01248836517334, "global_step": 497663, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.038667678833008, "global_step": 497664, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1048827171325684, "global_step": 497665, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0474283695220947, "global_step": 497666, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0007033348083496, "global_step": 497667, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.116342544555664, "global_step": 497668, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0462193489074707, "global_step": 497669, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.055636167526245, "global_step": 497670, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0990841388702393, "global_step": 497671, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0809519290924072, "global_step": 497672, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.094844341278076, "global_step": 497673, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0470519065856934, "global_step": 497674, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.079806327819824, "global_step": 497675, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.124418258666992, "global_step": 497676, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0988261699676514, "global_step": 497677, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.952987551689148, "global_step": 497678, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1033644676208496, "global_step": 497679, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0611650943756104, "global_step": 497680, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.06235408782959, "global_step": 497681, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.092982530593872, "global_step": 497682, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.079852342605591, "global_step": 497683, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0202767848968506, "global_step": 497684, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1182329654693604, "global_step": 497685, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1559088230133057, "global_step": 497686, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0459768772125244, "global_step": 497687, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.066364288330078, "global_step": 497688, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9791243076324463, "global_step": 497689, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0037992000579834, "global_step": 497690, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0768561363220215, "global_step": 497691, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1083285808563232, "global_step": 497692, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9870659112930298, "global_step": 497693, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.03559947013855, "global_step": 497694, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9763243198394775, "global_step": 497695, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9618977308273315, "global_step": 497696, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1126904487609863, "global_step": 497697, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0422236919403076, "global_step": 497698, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0242793560028076, "global_step": 497699, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9808220863342285, "global_step": 497700, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.007350206375122, "global_step": 497701, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9755700826644897, "global_step": 497702, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9946686029434204, "global_step": 497703, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.051968574523926, "global_step": 497704, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.069892644882202, "global_step": 497705, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9706757068634033, "global_step": 497706, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.005633592605591, "global_step": 497707, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0981123447418213, "global_step": 497708, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9884247779846191, "global_step": 497709, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1552059650421143, "global_step": 497710, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0998828411102295, "global_step": 497711, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.015195369720459, "global_step": 497712, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.010864496231079, "global_step": 497713, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.037919044494629, "global_step": 497714, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.091750144958496, "global_step": 497715, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.089573621749878, "global_step": 497716, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.09789776802063, "global_step": 497717, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.098496675491333, "global_step": 497718, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.009910821914673, "global_step": 497719, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.077657461166382, "global_step": 497720, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0702242851257324, "global_step": 497721, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.137458562850952, "global_step": 497722, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9897929430007935, "global_step": 497723, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9959807395935059, "global_step": 497724, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.07494854927063, "global_step": 497725, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0367166996002197, "global_step": 497726, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0941336154937744, "global_step": 497727, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1238839626312256, "global_step": 497728, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0457515716552734, "global_step": 497729, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0492777824401855, "global_step": 497730, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0671327114105225, "global_step": 497731, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1476407051086426, "global_step": 497732, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1788923740386963, "global_step": 497733, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.075864553451538, "global_step": 497734, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0646679401397705, "global_step": 497735, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0505340099334717, "global_step": 497736, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1362247467041016, "global_step": 497737, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9344425201416016, "global_step": 497738, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1142020225524902, "global_step": 497739, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.004251480102539, "global_step": 497740, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.081655740737915, "global_step": 497741, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.068509101867676, "global_step": 497742, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1092936992645264, "global_step": 497743, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0379672050476074, "global_step": 497744, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.074467420578003, "global_step": 497745, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1564784049987793, "global_step": 497746, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0328545570373535, "global_step": 497747, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1031334400177, "global_step": 497748, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.067047357559204, "global_step": 497749, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.054535388946533, "global_step": 497750, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.022559642791748, "global_step": 497751, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0909388065338135, "global_step": 497752, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9567028284072876, "global_step": 497753, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0525360107421875, "global_step": 497754, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9242618083953857, "global_step": 497755, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.016479969024658, "global_step": 497756, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1474573612213135, "global_step": 497757, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0354788303375244, "global_step": 497758, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0203864574432373, "global_step": 497759, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0387089252471924, "global_step": 497760, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0546226501464844, "global_step": 497761, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.089158058166504, "global_step": 497762, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0966506004333496, "global_step": 497763, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.038140296936035, "global_step": 497764, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.129868268966675, "global_step": 497765, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1100142002105713, "global_step": 497766, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0265817642211914, "global_step": 497767, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0834767818450928, "global_step": 497768, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.046818494796753, "global_step": 497769, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1093733310699463, "global_step": 497770, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.062486171722412, "global_step": 497771, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.050077199935913, "global_step": 497772, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0166447162628174, "global_step": 497773, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.046686887741089, "global_step": 497774, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0952579975128174, "global_step": 497775, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9899606704711914, "global_step": 497776, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0619943141937256, "global_step": 497777, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1707005500793457, "global_step": 497778, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0317811965942383, "global_step": 497779, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.117746591567993, "global_step": 497780, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0052881240844727, "global_step": 497781, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9911795854568481, "global_step": 497782, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1039950847625732, "global_step": 497783, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.114360809326172, "global_step": 497784, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.144927740097046, "global_step": 497785, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.080646514892578, "global_step": 497786, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9997671842575073, "global_step": 497787, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9570839405059814, "global_step": 497788, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.072021484375, "global_step": 497789, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0265796184539795, "global_step": 497790, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.038102388381958, "global_step": 497791, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1465373039245605, "global_step": 497792, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.054765462875366, "global_step": 497793, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0027947425842285, "global_step": 497794, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1071293354034424, "global_step": 497795, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0330605506896973, "global_step": 497796, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.037731170654297, "global_step": 497797, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0834155082702637, "global_step": 497798, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1511378288269043, "global_step": 497799, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.013733148574829, "global_step": 497800, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0766656398773193, "global_step": 497801, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9963515996932983, "global_step": 497802, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0895049571990967, "global_step": 497803, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0169644355773926, "global_step": 497804, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1001152992248535, "global_step": 497805, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0868868827819824, "global_step": 497806, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.045502185821533, "global_step": 497807, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9503424167633057, "global_step": 497808, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.100053548812866, "global_step": 497809, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0851986408233643, "global_step": 497810, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0427138805389404, "global_step": 497811, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9973188638687134, "global_step": 497812, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.139354944229126, "global_step": 497813, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.047694206237793, "global_step": 497814, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0682690143585205, "global_step": 497815, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0894381999969482, "global_step": 497816, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0336151123046875, "global_step": 497817, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.041259765625, "global_step": 497818, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.047468423843384, "global_step": 497819, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0469555854797363, "global_step": 497820, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1340954303741455, "global_step": 497821, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0063438415527344, "global_step": 497822, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.03817081451416, "global_step": 497823, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.055068254470825, "global_step": 497824, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0099854469299316, "global_step": 497825, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1295924186706543, "global_step": 497826, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.985984444618225, "global_step": 497827, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9622485637664795, "global_step": 497828, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0796027183532715, "global_step": 497829, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0952200889587402, "global_step": 497830, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1124136447906494, "global_step": 497831, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9997223615646362, "global_step": 497832, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.03779935836792, "global_step": 497833, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.117025852203369, "global_step": 497834, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.01241397857666, "global_step": 497835, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.112037181854248, "global_step": 497836, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0905420780181885, "global_step": 497837, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0476930141448975, "global_step": 497838, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0752735137939453, "global_step": 497839, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9552847146987915, "global_step": 497840, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.037489891052246, "global_step": 497841, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.124319553375244, "global_step": 497842, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1616134643554688, "global_step": 497843, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.00488543510437, "global_step": 497844, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9617681503295898, "global_step": 497845, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.148890495300293, "global_step": 497846, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1109061241149902, "global_step": 497847, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.02665638923645, "global_step": 497848, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9800130128860474, "global_step": 497849, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0257372856140137, "global_step": 497850, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.142582654953003, "global_step": 497851, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0294387340545654, "global_step": 497852, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.106825113296509, "global_step": 497853, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0952844619750977, "global_step": 497854, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0656490325927734, "global_step": 497855, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1064417362213135, "global_step": 497856, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0093703269958496, "global_step": 497857, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0462992191314697, "global_step": 497858, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0292184352874756, "global_step": 497859, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.054644823074341, "global_step": 497860, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0810558795928955, "global_step": 497861, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.067138910293579, "global_step": 497862, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.00062894821167, "global_step": 497863, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.056594133377075, "global_step": 497864, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.085787296295166, "global_step": 497865, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.040105104446411, "global_step": 497866, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1282763481140137, "global_step": 497867, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0931172370910645, "global_step": 497868, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0754013061523438, "global_step": 497869, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9663910865783691, "global_step": 497870, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0268428325653076, "global_step": 497871, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.099226474761963, "global_step": 497872, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1081840991973877, "global_step": 497873, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9986530542373657, "global_step": 497874, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.001305103302002, "global_step": 497875, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0583770275115967, "global_step": 497876, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.083799123764038, "global_step": 497877, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.037121057510376, "global_step": 497878, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1084177494049072, "global_step": 497879, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0517776012420654, "global_step": 497880, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0279018878936768, "global_step": 497881, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.106715679168701, "global_step": 497882, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9730244874954224, "global_step": 497883, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0385401248931885, "global_step": 497884, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.051994800567627, "global_step": 497885, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.045647382736206, "global_step": 497886, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0465221405029297, "global_step": 497887, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0567848682403564, "global_step": 497888, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.990270972251892, "global_step": 497889, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.098576068878174, "global_step": 497890, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0161781311035156, "global_step": 497891, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0460996627807617, "global_step": 497892, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.126049757003784, "global_step": 497893, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0033562183380127, "global_step": 497894, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.130078077316284, "global_step": 497895, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9459340572357178, "global_step": 497896, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.01361083984375, "global_step": 497897, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.03644061088562, "global_step": 497898, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.034048318862915, "global_step": 497899, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0597147941589355, "global_step": 497900, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.029364824295044, "global_step": 497901, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0935401916503906, "global_step": 497902, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0217812061309814, "global_step": 497903, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.943896770477295, "global_step": 497904, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9794602394104004, "global_step": 497905, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0294766426086426, "global_step": 497906, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.983778953552246, "global_step": 497907, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9952577352523804, "global_step": 497908, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.949691891670227, "global_step": 497909, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0394489765167236, "global_step": 497910, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0659382343292236, "global_step": 497911, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.132793426513672, "global_step": 497912, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.05867862701416, "global_step": 497913, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0181689262390137, "global_step": 497914, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0203981399536133, "global_step": 497915, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.024691581726074, "global_step": 497916, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0628013610839844, "global_step": 497917, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0071351528167725, "global_step": 497918, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0596766471862793, "global_step": 497919, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0107223987579346, "global_step": 497920, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9846254587173462, "global_step": 497921, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0016331672668457, "global_step": 497922, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.08323073387146, "global_step": 497923, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.060736894607544, "global_step": 497924, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9551913738250732, "global_step": 497925, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9868557453155518, "global_step": 497926, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1150314807891846, "global_step": 497927, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0791850090026855, "global_step": 497928, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.025172472000122, "global_step": 497929, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0890355110168457, "global_step": 497930, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0045177936553955, "global_step": 497931, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1081783771514893, "global_step": 497932, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0098025798797607, "global_step": 497933, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0923962593078613, "global_step": 497934, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.039073944091797, "global_step": 497935, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0500824451446533, "global_step": 497936, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.048945903778076, "global_step": 497937, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1324429512023926, "global_step": 497938, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.032468795776367, "global_step": 497939, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1154041290283203, "global_step": 497940, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0921010971069336, "global_step": 497941, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0296053886413574, "global_step": 497942, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.183689594268799, "global_step": 497943, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1081364154815674, "global_step": 497944, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0150375366210938, "global_step": 497945, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.053302526473999, "global_step": 497946, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0217032432556152, "global_step": 497947, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0880815982818604, "global_step": 497948, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0713558197021484, "global_step": 497949, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0630030632019043, "global_step": 497950, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1094512939453125, "global_step": 497951, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0303142070770264, "global_step": 497952, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.005673885345459, "global_step": 497953, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.161250591278076, "global_step": 497954, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0602385997772217, "global_step": 497955, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9680997133255005, "global_step": 497956, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0486347675323486, "global_step": 497957, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9953190088272095, "global_step": 497958, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.030870199203491, "global_step": 497959, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.00477933883667, "global_step": 497960, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1286683082580566, "global_step": 497961, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.075653553009033, "global_step": 497962, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.029146671295166, "global_step": 497963, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9575878381729126, "global_step": 497964, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0080244541168213, "global_step": 497965, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.081146240234375, "global_step": 497966, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.031029224395752, "global_step": 497967, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0531954765319824, "global_step": 497968, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1571109294891357, "global_step": 497969, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0579593181610107, "global_step": 497970, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.05873966217041, "global_step": 497971, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0551366806030273, "global_step": 497972, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0621566772460938, "global_step": 497973, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0219264030456543, "global_step": 497974, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0504472255706787, "global_step": 497975, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.004132032394409, "global_step": 497976, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0035009384155273, "global_step": 497977, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.05877947807312, "global_step": 497978, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0623645782470703, "global_step": 497979, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0697665214538574, "global_step": 497980, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0034663677215576, "global_step": 497981, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0302224159240723, "global_step": 497982, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0837173461914062, "global_step": 497983, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0763442516326904, "global_step": 497984, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.039818048477173, "global_step": 497985, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.040684461593628, "global_step": 497986, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0228397846221924, "global_step": 497987, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1461880207061768, "global_step": 497988, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1457467079162598, "global_step": 497989, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0312156677246094, "global_step": 497990, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0877206325531006, "global_step": 497991, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.053743362426758, "global_step": 497992, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0346899032592773, "global_step": 497993, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9920140504837036, "global_step": 497994, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1141674518585205, "global_step": 497995, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.158977746963501, "global_step": 497996, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0078537464141846, "global_step": 497997, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.08903169631958, "global_step": 497998, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0080366134643555, "global_step": 497999, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0173747539520264, "global_step": 498000, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0102145671844482, "global_step": 498001, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.042457103729248, "global_step": 498002, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.086212396621704, "global_step": 498003, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.052442789077759, "global_step": 498004, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1148529052734375, "global_step": 498005, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0776710510253906, "global_step": 498006, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.140982151031494, "global_step": 498007, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.068228006362915, "global_step": 498008, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9780086278915405, "global_step": 498009, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0024642944335938, "global_step": 498010, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9598370790481567, "global_step": 498011, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0509393215179443, "global_step": 498012, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1161274909973145, "global_step": 498013, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0231144428253174, "global_step": 498014, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0564355850219727, "global_step": 498015, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0155460834503174, "global_step": 498016, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0580172538757324, "global_step": 498017, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.080899477005005, "global_step": 498018, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0561304092407227, "global_step": 498019, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.007958173751831, "global_step": 498020, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0530614852905273, "global_step": 498021, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0242772102355957, "global_step": 498022, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.092416524887085, "global_step": 498023, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0376052856445312, "global_step": 498024, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.080562114715576, "global_step": 498025, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0823333263397217, "global_step": 498026, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0809214115142822, "global_step": 498027, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9862465858459473, "global_step": 498028, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0723562240600586, "global_step": 498029, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.060899019241333, "global_step": 498030, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.144489288330078, "global_step": 498031, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1222121715545654, "global_step": 498032, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9833009243011475, "global_step": 498033, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.038553237915039, "global_step": 498034, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0484421253204346, "global_step": 498035, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0600950717926025, "global_step": 498036, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.040956974029541, "global_step": 498037, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0396695137023926, "global_step": 498038, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.087200880050659, "global_step": 498039, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.12817120552063, "global_step": 498040, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0280613899230957, "global_step": 498041, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.015692710876465, "global_step": 498042, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9859789609909058, "global_step": 498043, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0624279975891113, "global_step": 498044, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.091017484664917, "global_step": 498045, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0203418731689453, "global_step": 498046, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1210553646087646, "global_step": 498047, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.075471878051758, "global_step": 498048, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9905954599380493, "global_step": 498049, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.044060468673706, "global_step": 498050, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0194239616394043, "global_step": 498051, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9973093271255493, "global_step": 498052, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.06787371635437, "global_step": 498053, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0608346462249756, "global_step": 498054, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.112464189529419, "global_step": 498055, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.03875994682312, "global_step": 498056, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0907742977142334, "global_step": 498057, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.002344846725464, "global_step": 498058, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0585262775421143, "global_step": 498059, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0665531158447266, "global_step": 498060, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.097423553466797, "global_step": 498061, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.038090705871582, "global_step": 498062, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.059567451477051, "global_step": 498063, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0184075832366943, "global_step": 498064, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9488221406936646, "global_step": 498065, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.077293872833252, "global_step": 498066, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9877556562423706, "global_step": 498067, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0752811431884766, "global_step": 498068, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.056605339050293, "global_step": 498069, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.084198236465454, "global_step": 498070, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0987846851348877, "global_step": 498071, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.104526996612549, "global_step": 498072, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0021419525146484, "global_step": 498073, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.009223222732544, "global_step": 498074, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.088287115097046, "global_step": 498075, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.032449960708618, "global_step": 498076, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.037677764892578, "global_step": 498077, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0391921997070312, "global_step": 498078, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0376083850860596, "global_step": 498079, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1765077114105225, "global_step": 498080, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.051518678665161, "global_step": 498081, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0651214122772217, "global_step": 498082, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.994598627090454, "global_step": 498083, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.05755615234375, "global_step": 498084, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.081249713897705, "global_step": 498085, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.070352077484131, "global_step": 498086, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0823795795440674, "global_step": 498087, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1124908924102783, "global_step": 498088, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.027676820755005, "global_step": 498089, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.033559560775757, "global_step": 498090, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.075237989425659, "global_step": 498091, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9778984785079956, "global_step": 498092, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.031285047531128, "global_step": 498093, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0017249584198, "global_step": 498094, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0611093044281006, "global_step": 498095, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.02262544631958, "global_step": 498096, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0368456840515137, "global_step": 498097, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0666775703430176, "global_step": 498098, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1116738319396973, "global_step": 498099, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9706305265426636, "global_step": 498100, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.002955198287964, "global_step": 498101, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0848913192749023, "global_step": 498102, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.975556492805481, "global_step": 498103, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.045475959777832, "global_step": 498104, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1207833290100098, "global_step": 498105, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0984995365142822, "global_step": 498106, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0030770301818848, "global_step": 498107, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0821242332458496, "global_step": 498108, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1347033977508545, "global_step": 498109, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0726938247680664, "global_step": 498110, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.079249382019043, "global_step": 498111, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.051386833190918, "global_step": 498112, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0356457233428955, "global_step": 498113, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1144001483917236, "global_step": 498114, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9840418100357056, "global_step": 498115, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1441092491149902, "global_step": 498116, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.14095139503479, "global_step": 498117, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.078575611114502, "global_step": 498118, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9701621532440186, "global_step": 498119, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0116567611694336, "global_step": 498120, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.091813087463379, "global_step": 498121, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0455174446105957, "global_step": 498122, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.01343035697937, "global_step": 498123, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.074943780899048, "global_step": 498124, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0734264850616455, "global_step": 498125, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.067633867263794, "global_step": 498126, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1307156085968018, "global_step": 498127, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0953686237335205, "global_step": 498128, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9933232069015503, "global_step": 498129, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.107480764389038, "global_step": 498130, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.103968858718872, "global_step": 498131, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0928773880004883, "global_step": 498132, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0757758617401123, "global_step": 498133, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0240325927734375, "global_step": 498134, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.027200698852539, "global_step": 498135, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0720348358154297, "global_step": 498136, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.111531972885132, "global_step": 498137, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0299489498138428, "global_step": 498138, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0752038955688477, "global_step": 498139, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1104321479797363, "global_step": 498140, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.009495973587036, "global_step": 498141, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.034614086151123, "global_step": 498142, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9562171697616577, "global_step": 498143, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0240490436553955, "global_step": 498144, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0068368911743164, "global_step": 498145, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1680409908294678, "global_step": 498146, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9955772161483765, "global_step": 498147, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.106417179107666, "global_step": 498148, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.068182945251465, "global_step": 498149, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.120758295059204, "global_step": 498150, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0681190490722656, "global_step": 498151, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0374224185943604, "global_step": 498152, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.990517020225525, "global_step": 498153, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0739662647247314, "global_step": 498154, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0259246826171875, "global_step": 498155, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0967869758605957, "global_step": 498156, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.081301689147949, "global_step": 498157, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1353821754455566, "global_step": 498158, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.016265869140625, "global_step": 498159, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0686213970184326, "global_step": 498160, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.007388114929199, "global_step": 498161, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1513373851776123, "global_step": 498162, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.025761604309082, "global_step": 498163, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1390504837036133, "global_step": 498164, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1266305446624756, "global_step": 498165, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.092777729034424, "global_step": 498166, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.029702663421631, "global_step": 498167, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1541082859039307, "global_step": 498168, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.020388603210449, "global_step": 498169, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1188557147979736, "global_step": 498170, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.06449031829834, "global_step": 498171, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0390567779541016, "global_step": 498172, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.063239812850952, "global_step": 498173, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0496013164520264, "global_step": 498174, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.070571184158325, "global_step": 498175, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1144425868988037, "global_step": 498176, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0577356815338135, "global_step": 498177, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9954332113265991, "global_step": 498178, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9419313669204712, "global_step": 498179, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.100107192993164, "global_step": 498180, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.066850185394287, "global_step": 498181, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0970327854156494, "global_step": 498182, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0746192932128906, "global_step": 498183, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.067319631576538, "global_step": 498184, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.070309638977051, "global_step": 498185, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.060020923614502, "global_step": 498186, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9635735750198364, "global_step": 498187, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.058767318725586, "global_step": 498188, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.068063974380493, "global_step": 498189, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.125147581100464, "global_step": 498190, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.112936496734619, "global_step": 498191, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0223729610443115, "global_step": 498192, "epoch": 863, "lr": 5e-05}
{"train_loss": 1.9934693574905396, "global_step": 498193, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0659193992614746, "global_step": 498194, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.095736265182495, "global_step": 498195, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.1118223667144775, "global_step": 498196, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.082960605621338, "global_step": 498197, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.053037643432617, "global_step": 498198, "epoch": 863, "lr": 5e-05}
{"train_loss": 2.0340347290039062, "global_step": 498199, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.05301570892334, "global_step": 498200, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0553505420684814, "global_step": 498201, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9920196533203125, "global_step": 498202, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1152210235595703, "global_step": 498203, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.151108980178833, "global_step": 498204, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.113800048828125, "global_step": 498205, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.073596477508545, "global_step": 498206, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0929436683654785, "global_step": 498207, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.066358804702759, "global_step": 498208, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0709121227264404, "global_step": 498209, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0136303901672363, "global_step": 498210, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.965595006942749, "global_step": 498211, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.930115818977356, "global_step": 498212, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0431456565856934, "global_step": 498213, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9761056900024414, "global_step": 498214, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0776803493499756, "global_step": 498215, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.062113046646118, "global_step": 498216, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9807792901992798, "global_step": 498217, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0750532150268555, "global_step": 498218, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9887696504592896, "global_step": 498219, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0620901584625244, "global_step": 498220, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.056485652923584, "global_step": 498221, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0541446208953857, "global_step": 498222, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1057450771331787, "global_step": 498223, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.015118360519409, "global_step": 498224, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.048720121383667, "global_step": 498225, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0081653594970703, "global_step": 498226, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.148078203201294, "global_step": 498227, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0182716846466064, "global_step": 498228, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0993881225585938, "global_step": 498229, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.089742660522461, "global_step": 498230, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.011512517929077, "global_step": 498231, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0167691707611084, "global_step": 498232, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0151736736297607, "global_step": 498233, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.043557643890381, "global_step": 498234, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.060299873352051, "global_step": 498235, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.150669574737549, "global_step": 498236, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.044768810272217, "global_step": 498237, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0855274200439453, "global_step": 498238, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.042759895324707, "global_step": 498239, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.080885887145996, "global_step": 498240, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.961289405822754, "global_step": 498241, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0156726837158203, "global_step": 498242, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0354933738708496, "global_step": 498243, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.063277006149292, "global_step": 498244, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0835723876953125, "global_step": 498245, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.06339955329895, "global_step": 498246, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.015838384628296, "global_step": 498247, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0215859413146973, "global_step": 498248, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.126260757446289, "global_step": 498249, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9877132177352905, "global_step": 498250, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1083383560180664, "global_step": 498251, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.070435047149658, "global_step": 498252, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0962023735046387, "global_step": 498253, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0092642307281494, "global_step": 498254, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.091663122177124, "global_step": 498255, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.080883741378784, "global_step": 498256, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1215405464172363, "global_step": 498257, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.051175355911255, "global_step": 498258, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.031130790710449, "global_step": 498259, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.036370038986206, "global_step": 498260, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9831020832061768, "global_step": 498261, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.015695095062256, "global_step": 498262, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0529658794403076, "global_step": 498263, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9659110307693481, "global_step": 498264, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0962798595428467, "global_step": 498265, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0262556076049805, "global_step": 498266, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0007941722869873, "global_step": 498267, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1339080333709717, "global_step": 498268, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0174500942230225, "global_step": 498269, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1031739711761475, "global_step": 498270, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.076235294342041, "global_step": 498271, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9904543161392212, "global_step": 498272, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0924437046051025, "global_step": 498273, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0416040420532227, "global_step": 498274, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0442581176757812, "global_step": 498275, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9747987985610962, "global_step": 498276, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.123469829559326, "global_step": 498277, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.013305425643921, "global_step": 498278, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0014266967773438, "global_step": 498279, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.029569149017334, "global_step": 498280, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0696969032287598, "global_step": 498281, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.038256883621216, "global_step": 498282, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.139708995819092, "global_step": 498283, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0206310749053955, "global_step": 498284, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0783724784851074, "global_step": 498285, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.006606101989746, "global_step": 498286, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0352590084075928, "global_step": 498287, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0893328189849854, "global_step": 498288, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0741491317749023, "global_step": 498289, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1706700325012207, "global_step": 498290, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0837550163269043, "global_step": 498291, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9765758514404297, "global_step": 498292, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0646026134490967, "global_step": 498293, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0956974029541016, "global_step": 498294, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.098778009414673, "global_step": 498295, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9814921617507935, "global_step": 498296, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.094559669494629, "global_step": 498297, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0313644409179688, "global_step": 498298, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.032973527908325, "global_step": 498299, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0786867141723633, "global_step": 498300, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0454964637756348, "global_step": 498301, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.13661789894104, "global_step": 498302, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.025296688079834, "global_step": 498303, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.018310785293579, "global_step": 498304, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0516605377197266, "global_step": 498305, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0365352630615234, "global_step": 498306, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.141331672668457, "global_step": 498307, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.082028865814209, "global_step": 498308, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.069432258605957, "global_step": 498309, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0087087154388428, "global_step": 498310, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0730791091918945, "global_step": 498311, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0488369464874268, "global_step": 498312, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.072510242462158, "global_step": 498313, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.977794885635376, "global_step": 498314, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9575045108795166, "global_step": 498315, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0335373878479004, "global_step": 498316, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0866386890411377, "global_step": 498317, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.038637161254883, "global_step": 498318, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9735065698623657, "global_step": 498319, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0526840686798096, "global_step": 498320, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1005752086639404, "global_step": 498321, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.109309434890747, "global_step": 498322, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0900421142578125, "global_step": 498323, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.042027711868286, "global_step": 498324, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9687074422836304, "global_step": 498325, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1104624271392822, "global_step": 498326, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0766353607177734, "global_step": 498327, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0399463176727295, "global_step": 498328, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0056002140045166, "global_step": 498329, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9642313718795776, "global_step": 498330, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1421890258789062, "global_step": 498331, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0055110454559326, "global_step": 498332, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9602959156036377, "global_step": 498333, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0641212463378906, "global_step": 498334, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0336086750030518, "global_step": 498335, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.008114814758301, "global_step": 498336, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9312740564346313, "global_step": 498337, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.004131317138672, "global_step": 498338, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.039449691772461, "global_step": 498339, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0596818923950195, "global_step": 498340, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0595808029174805, "global_step": 498341, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0793087482452393, "global_step": 498342, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0616257190704346, "global_step": 498343, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0850586891174316, "global_step": 498344, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0011656284332275, "global_step": 498345, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9785469770431519, "global_step": 498346, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9995158910751343, "global_step": 498347, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.084425687789917, "global_step": 498348, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.10265851020813, "global_step": 498349, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.087898015975952, "global_step": 498350, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.002969264984131, "global_step": 498351, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9673466682434082, "global_step": 498352, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.047154188156128, "global_step": 498353, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1011924743652344, "global_step": 498354, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9755444526672363, "global_step": 498355, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.090320110321045, "global_step": 498356, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.05305814743042, "global_step": 498357, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9839833974838257, "global_step": 498358, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.084174871444702, "global_step": 498359, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1188182830810547, "global_step": 498360, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.057964324951172, "global_step": 498361, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9912645816802979, "global_step": 498362, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.035947799682617, "global_step": 498363, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.064021110534668, "global_step": 498364, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9890773296356201, "global_step": 498365, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0108962059020996, "global_step": 498366, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0633771419525146, "global_step": 498367, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.992231845855713, "global_step": 498368, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0245721340179443, "global_step": 498369, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0941624641418457, "global_step": 498370, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.05265474319458, "global_step": 498371, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9908498525619507, "global_step": 498372, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9976602792739868, "global_step": 498373, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.108551263809204, "global_step": 498374, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.051159143447876, "global_step": 498375, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.048842668533325, "global_step": 498376, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0745906829833984, "global_step": 498377, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.112213373184204, "global_step": 498378, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.099302291870117, "global_step": 498379, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1029794216156006, "global_step": 498380, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0349888801574707, "global_step": 498381, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.105816125869751, "global_step": 498382, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0653510093688965, "global_step": 498383, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0199801921844482, "global_step": 498384, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.067281484603882, "global_step": 498385, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.091484308242798, "global_step": 498386, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.073704481124878, "global_step": 498387, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0555410385131836, "global_step": 498388, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.034780263900757, "global_step": 498389, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1677660942077637, "global_step": 498390, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.100799560546875, "global_step": 498391, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.005758762359619, "global_step": 498392, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0446853637695312, "global_step": 498393, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.074432134628296, "global_step": 498394, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0357377529144287, "global_step": 498395, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.105790853500366, "global_step": 498396, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0544593334198, "global_step": 498397, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.027052402496338, "global_step": 498398, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0866775512695312, "global_step": 498399, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0169970989227295, "global_step": 498400, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.027500867843628, "global_step": 498401, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0876333713531494, "global_step": 498402, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9917869567871094, "global_step": 498403, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0191986560821533, "global_step": 498404, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0660102367401123, "global_step": 498405, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.023862361907959, "global_step": 498406, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.012268304824829, "global_step": 498407, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0635335445404053, "global_step": 498408, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1707661151885986, "global_step": 498409, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0048913955688477, "global_step": 498410, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0452263355255127, "global_step": 498411, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0481793880462646, "global_step": 498412, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0691750049591064, "global_step": 498413, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0274195671081543, "global_step": 498414, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0376827716827393, "global_step": 498415, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9500868320465088, "global_step": 498416, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0628435611724854, "global_step": 498417, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.08941650390625, "global_step": 498418, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0265116691589355, "global_step": 498419, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0074992179870605, "global_step": 498420, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.011918783187866, "global_step": 498421, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0658884048461914, "global_step": 498422, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0460495948791504, "global_step": 498423, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.067005157470703, "global_step": 498424, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9444596767425537, "global_step": 498425, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0913679599761963, "global_step": 498426, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1373238563537598, "global_step": 498427, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0638656616210938, "global_step": 498428, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.065601348876953, "global_step": 498429, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9744946956634521, "global_step": 498430, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0027620792388916, "global_step": 498431, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1262826919555664, "global_step": 498432, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.016522169113159, "global_step": 498433, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.972931981086731, "global_step": 498434, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.020009756088257, "global_step": 498435, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1470720767974854, "global_step": 498436, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0722994804382324, "global_step": 498437, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.099505662918091, "global_step": 498438, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0899040699005127, "global_step": 498439, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0014426708221436, "global_step": 498440, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.055156946182251, "global_step": 498441, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.040144681930542, "global_step": 498442, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.092039108276367, "global_step": 498443, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9844305515289307, "global_step": 498444, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.069000244140625, "global_step": 498445, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.002476930618286, "global_step": 498446, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0280141830444336, "global_step": 498447, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.072496175765991, "global_step": 498448, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.028258800506592, "global_step": 498449, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0435571670532227, "global_step": 498450, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9683359861373901, "global_step": 498451, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9868853092193604, "global_step": 498452, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0521771907806396, "global_step": 498453, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0943915843963623, "global_step": 498454, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0477800369262695, "global_step": 498455, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1125075817108154, "global_step": 498456, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0450844764709473, "global_step": 498457, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0662574768066406, "global_step": 498458, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.045952081680298, "global_step": 498459, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.983195424079895, "global_step": 498460, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.031649112701416, "global_step": 498461, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.055314779281616, "global_step": 498462, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.140472888946533, "global_step": 498463, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.033158779144287, "global_step": 498464, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0431950092315674, "global_step": 498465, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0624947547912598, "global_step": 498466, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9830375909805298, "global_step": 498467, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.031437635421753, "global_step": 498468, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9883382320404053, "global_step": 498469, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9736969470977783, "global_step": 498470, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0909523963928223, "global_step": 498471, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.018098831176758, "global_step": 498472, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.073781728744507, "global_step": 498473, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1110243797302246, "global_step": 498474, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0048811435699463, "global_step": 498475, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.017235279083252, "global_step": 498476, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1008784770965576, "global_step": 498477, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.046985387802124, "global_step": 498478, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0399529933929443, "global_step": 498479, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0017731189727783, "global_step": 498480, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.06335186958313, "global_step": 498481, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0284316539764404, "global_step": 498482, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1135027408599854, "global_step": 498483, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1334359645843506, "global_step": 498484, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.029529333114624, "global_step": 498485, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.06367826461792, "global_step": 498486, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.012172222137451, "global_step": 498487, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0822038650512695, "global_step": 498488, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.083632707595825, "global_step": 498489, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.062490940093994, "global_step": 498490, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0252456665039062, "global_step": 498491, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.041989803314209, "global_step": 498492, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0457851886749268, "global_step": 498493, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0385444164276123, "global_step": 498494, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0729644298553467, "global_step": 498495, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.070915460586548, "global_step": 498496, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.002471923828125, "global_step": 498497, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0164403915405273, "global_step": 498498, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0116162300109863, "global_step": 498499, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0112125873565674, "global_step": 498500, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1188132762908936, "global_step": 498501, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0119826793670654, "global_step": 498502, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.12099289894104, "global_step": 498503, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.047772169113159, "global_step": 498504, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0500309467315674, "global_step": 498505, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9664149284362793, "global_step": 498506, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0533690452575684, "global_step": 498507, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0255489349365234, "global_step": 498508, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.096012830734253, "global_step": 498509, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.019426107406616, "global_step": 498510, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1499338150024414, "global_step": 498511, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1264548301696777, "global_step": 498512, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1364595890045166, "global_step": 498513, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0282719135284424, "global_step": 498514, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.00726318359375, "global_step": 498515, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.036684274673462, "global_step": 498516, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.023198366165161, "global_step": 498517, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.090646266937256, "global_step": 498518, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0708179473876953, "global_step": 498519, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0513248443603516, "global_step": 498520, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.021812677383423, "global_step": 498521, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.012956380844116, "global_step": 498522, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0339527130126953, "global_step": 498523, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0575034618377686, "global_step": 498524, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9930942058563232, "global_step": 498525, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.008960485458374, "global_step": 498526, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0155301094055176, "global_step": 498527, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.04526948928833, "global_step": 498528, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.050182819366455, "global_step": 498529, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.046771287918091, "global_step": 498530, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9946157932281494, "global_step": 498531, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.049870014190674, "global_step": 498532, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0725276470184326, "global_step": 498533, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9768049716949463, "global_step": 498534, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0016369819641113, "global_step": 498535, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0469563007354736, "global_step": 498536, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9741894006729126, "global_step": 498537, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0357015132904053, "global_step": 498538, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9713892936706543, "global_step": 498539, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.13622784614563, "global_step": 498540, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0636532306671143, "global_step": 498541, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0333166122436523, "global_step": 498542, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.015194892883301, "global_step": 498543, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.031843662261963, "global_step": 498544, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.071180582046509, "global_step": 498545, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.067556619644165, "global_step": 498546, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.071714401245117, "global_step": 498547, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1190478801727295, "global_step": 498548, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.033308506011963, "global_step": 498549, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0791523456573486, "global_step": 498550, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0446059703826904, "global_step": 498551, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.104562759399414, "global_step": 498552, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0499773025512695, "global_step": 498553, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.081059217453003, "global_step": 498554, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0829906463623047, "global_step": 498555, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0565402507781982, "global_step": 498556, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1063196659088135, "global_step": 498557, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0266246795654297, "global_step": 498558, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.111372470855713, "global_step": 498559, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.112694025039673, "global_step": 498560, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9907809495925903, "global_step": 498561, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1153581142425537, "global_step": 498562, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0453760623931885, "global_step": 498563, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.064835786819458, "global_step": 498564, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0370051860809326, "global_step": 498565, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1157827377319336, "global_step": 498566, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.99709153175354, "global_step": 498567, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9948188066482544, "global_step": 498568, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1000630855560303, "global_step": 498569, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9939157962799072, "global_step": 498570, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.059340000152588, "global_step": 498571, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0501444339752197, "global_step": 498572, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.039824962615967, "global_step": 498573, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.089628219604492, "global_step": 498574, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1341917514801025, "global_step": 498575, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9867528676986694, "global_step": 498576, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0684568881988525, "global_step": 498577, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0593206882476807, "global_step": 498578, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.119418144226074, "global_step": 498579, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0342328548431396, "global_step": 498580, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0623319149017334, "global_step": 498581, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1218812465667725, "global_step": 498582, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.008539915084839, "global_step": 498583, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.049034595489502, "global_step": 498584, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1270127296447754, "global_step": 498585, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.003286838531494, "global_step": 498586, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.019383192062378, "global_step": 498587, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0570297241210938, "global_step": 498588, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9988335371017456, "global_step": 498589, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0503990650177, "global_step": 498590, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9894580841064453, "global_step": 498591, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0318970680236816, "global_step": 498592, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.006575107574463, "global_step": 498593, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.085620880126953, "global_step": 498594, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.00471830368042, "global_step": 498595, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.02364444732666, "global_step": 498596, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1004140377044678, "global_step": 498597, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1037790775299072, "global_step": 498598, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9871772527694702, "global_step": 498599, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.064866065979004, "global_step": 498600, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.117434501647949, "global_step": 498601, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0991902351379395, "global_step": 498602, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.078925609588623, "global_step": 498603, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.997675895690918, "global_step": 498604, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.104494571685791, "global_step": 498605, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.010162353515625, "global_step": 498606, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.072157859802246, "global_step": 498607, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1174192428588867, "global_step": 498608, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.098017454147339, "global_step": 498609, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.04148006439209, "global_step": 498610, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.024613618850708, "global_step": 498611, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.130664110183716, "global_step": 498612, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.064446449279785, "global_step": 498613, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0082848072052, "global_step": 498614, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1283609867095947, "global_step": 498615, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.032892942428589, "global_step": 498616, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9850150346755981, "global_step": 498617, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.051259994506836, "global_step": 498618, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9860633611679077, "global_step": 498619, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.028761386871338, "global_step": 498620, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0009632110595703, "global_step": 498621, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.031034231185913, "global_step": 498622, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9592281579971313, "global_step": 498623, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0778536796569824, "global_step": 498624, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.035227060317993, "global_step": 498625, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0661838054656982, "global_step": 498626, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0532379150390625, "global_step": 498627, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0502355098724365, "global_step": 498628, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.021958827972412, "global_step": 498629, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.02278995513916, "global_step": 498630, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.114208698272705, "global_step": 498631, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9683398008346558, "global_step": 498632, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0459582805633545, "global_step": 498633, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9980981349945068, "global_step": 498634, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0226995944976807, "global_step": 498635, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0944955348968506, "global_step": 498636, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9981591701507568, "global_step": 498637, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0133056640625, "global_step": 498638, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.004007339477539, "global_step": 498639, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.116506576538086, "global_step": 498640, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9535685777664185, "global_step": 498641, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.117581367492676, "global_step": 498642, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0453851222991943, "global_step": 498643, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9265100955963135, "global_step": 498644, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.090984582901001, "global_step": 498645, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0342750549316406, "global_step": 498646, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1159234046936035, "global_step": 498647, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.030372142791748, "global_step": 498648, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.041621208190918, "global_step": 498649, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0764734745025635, "global_step": 498650, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0651321411132812, "global_step": 498651, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.043367624282837, "global_step": 498652, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.11799955368042, "global_step": 498653, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.149188756942749, "global_step": 498654, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0581326484680176, "global_step": 498655, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0168991088867188, "global_step": 498656, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9643741846084595, "global_step": 498657, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.087803602218628, "global_step": 498658, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9304732084274292, "global_step": 498659, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0580434799194336, "global_step": 498660, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9549158811569214, "global_step": 498661, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9712574481964111, "global_step": 498662, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.066284418106079, "global_step": 498663, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0163955688476562, "global_step": 498664, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.065156936645508, "global_step": 498665, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0357484817504883, "global_step": 498666, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.011578321456909, "global_step": 498667, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0522239208221436, "global_step": 498668, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0458598136901855, "global_step": 498669, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9088397026062012, "global_step": 498670, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1393022537231445, "global_step": 498671, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.15132474899292, "global_step": 498672, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1066696643829346, "global_step": 498673, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.003425121307373, "global_step": 498674, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9303996562957764, "global_step": 498675, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0457944869995117, "global_step": 498676, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0605504512786865, "global_step": 498677, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.101975440979004, "global_step": 498678, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.115508794784546, "global_step": 498679, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.129171848297119, "global_step": 498680, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.055870294570923, "global_step": 498681, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0488204956054688, "global_step": 498682, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.094510316848755, "global_step": 498683, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.105224847793579, "global_step": 498684, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.067826271057129, "global_step": 498685, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1203062534332275, "global_step": 498686, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.979780673980713, "global_step": 498687, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.062106132507324, "global_step": 498688, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9764072895050049, "global_step": 498689, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.153756856918335, "global_step": 498690, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.00882887840271, "global_step": 498691, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9582102298736572, "global_step": 498692, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0480499267578125, "global_step": 498693, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.018714427947998, "global_step": 498694, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0466675758361816, "global_step": 498695, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.098271369934082, "global_step": 498696, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.945085048675537, "global_step": 498697, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1151037216186523, "global_step": 498698, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9984910488128662, "global_step": 498699, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9946370124816895, "global_step": 498700, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.048630714416504, "global_step": 498701, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0088961124420166, "global_step": 498702, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.103055477142334, "global_step": 498703, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.047168731689453, "global_step": 498704, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.110508680343628, "global_step": 498705, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.049194097518921, "global_step": 498706, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9786615371704102, "global_step": 498707, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0868537425994873, "global_step": 498708, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.119359254837036, "global_step": 498709, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1017682552337646, "global_step": 498710, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0333597660064697, "global_step": 498711, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.001469135284424, "global_step": 498712, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0310800075531006, "global_step": 498713, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.06706166267395, "global_step": 498714, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9802814722061157, "global_step": 498715, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0332953929901123, "global_step": 498716, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.051942825317383, "global_step": 498717, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1346957683563232, "global_step": 498718, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0027880668640137, "global_step": 498719, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.076860189437866, "global_step": 498720, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0880730152130127, "global_step": 498721, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.036440849304199, "global_step": 498722, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0546934604644775, "global_step": 498723, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.118152141571045, "global_step": 498724, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.017395257949829, "global_step": 498725, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.040601968765259, "global_step": 498726, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.046003580093384, "global_step": 498727, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.044274091720581, "global_step": 498728, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1334593296051025, "global_step": 498729, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0252974033355713, "global_step": 498730, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0627644062042236, "global_step": 498731, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0539257526397705, "global_step": 498732, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.022693395614624, "global_step": 498733, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0130558013916016, "global_step": 498734, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.102630138397217, "global_step": 498735, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9709047079086304, "global_step": 498736, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.047449827194214, "global_step": 498737, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.043046236038208, "global_step": 498738, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9460766315460205, "global_step": 498739, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9942140579223633, "global_step": 498740, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0587451457977295, "global_step": 498741, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.075716257095337, "global_step": 498742, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0488502979278564, "global_step": 498743, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0675973892211914, "global_step": 498744, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1205756664276123, "global_step": 498745, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9858551025390625, "global_step": 498746, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0750038623809814, "global_step": 498747, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.009274959564209, "global_step": 498748, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0674750804901123, "global_step": 498749, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.169935703277588, "global_step": 498750, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.030881881713867, "global_step": 498751, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.123654365539551, "global_step": 498752, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.115269422531128, "global_step": 498753, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0158557891845703, "global_step": 498754, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1185853481292725, "global_step": 498755, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.061943292617798, "global_step": 498756, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9927220344543457, "global_step": 498757, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.04947829246521, "global_step": 498758, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0813145637512207, "global_step": 498759, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0462851524353027, "global_step": 498760, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.037292003631592, "global_step": 498761, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.090703248977661, "global_step": 498762, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.131852865219116, "global_step": 498763, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1145918369293213, "global_step": 498764, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.071537494659424, "global_step": 498765, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0750858783721924, "global_step": 498766, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.011543035507202, "global_step": 498767, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.099731922149658, "global_step": 498768, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.969187617301941, "global_step": 498769, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.181171178817749, "global_step": 498770, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.056075096130371, "global_step": 498771, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0351362228393555, "global_step": 498772, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1670494079589844, "global_step": 498773, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.031123638153076, "global_step": 498774, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.048222541809082, "global_step": 498775, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9978259801864624, "global_step": 498776, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0376675128936768, "global_step": 498777, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.095318078994751, "global_step": 498778, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0645086765289307, "global_step": 498779, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.12272310256958, "global_step": 498780, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9840881824493408, "global_step": 498781, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0817017555236816, "global_step": 498782, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0127663612365723, "global_step": 498783, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0631394386291504, "global_step": 498784, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9858952760696411, "global_step": 498785, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.100681781768799, "global_step": 498786, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.951646327972412, "global_step": 498787, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.080915927886963, "global_step": 498788, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.001441478729248, "global_step": 498789, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9650992155075073, "global_step": 498790, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0608787536621094, "global_step": 498791, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9872920513153076, "global_step": 498792, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0104117393493652, "global_step": 498793, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.052940607070923, "global_step": 498794, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.002169609069824, "global_step": 498795, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0260448455810547, "global_step": 498796, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0748825073242188, "global_step": 498797, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9539324045181274, "global_step": 498798, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0551419258117676, "global_step": 498799, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1018319129943848, "global_step": 498800, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0144598484039307, "global_step": 498801, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9854614734649658, "global_step": 498802, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0969300270080566, "global_step": 498803, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0514278411865234, "global_step": 498804, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9957107305526733, "global_step": 498805, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.076094388961792, "global_step": 498806, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0536575317382812, "global_step": 498807, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.008941888809204, "global_step": 498808, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.048609495162964, "global_step": 498809, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.071258306503296, "global_step": 498810, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0741612911224365, "global_step": 498811, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9757351875305176, "global_step": 498812, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.064196825027466, "global_step": 498813, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.082368850708008, "global_step": 498814, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0896825790405273, "global_step": 498815, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0493407249450684, "global_step": 498816, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9752955436706543, "global_step": 498817, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0541176795959473, "global_step": 498818, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0717005729675293, "global_step": 498819, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.115196943283081, "global_step": 498820, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1364879608154297, "global_step": 498821, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0077741146087646, "global_step": 498822, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.028904914855957, "global_step": 498823, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0263774394989014, "global_step": 498824, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.066030263900757, "global_step": 498825, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0125348567962646, "global_step": 498826, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.007441282272339, "global_step": 498827, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0298075675964355, "global_step": 498828, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.054182767868042, "global_step": 498829, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.046757459640503, "global_step": 498830, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0260519981384277, "global_step": 498831, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9624401330947876, "global_step": 498832, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0279381275177, "global_step": 498833, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9624848365783691, "global_step": 498834, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0238404273986816, "global_step": 498835, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1234822273254395, "global_step": 498836, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.031136989593506, "global_step": 498837, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0609779357910156, "global_step": 498838, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9991755485534668, "global_step": 498839, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9741291999816895, "global_step": 498840, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1014015674591064, "global_step": 498841, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.02518367767334, "global_step": 498842, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0126662254333496, "global_step": 498843, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0656139850616455, "global_step": 498844, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.086000442504883, "global_step": 498845, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1987674236297607, "global_step": 498846, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.020252227783203, "global_step": 498847, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.045647621154785, "global_step": 498848, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0620615482330322, "global_step": 498849, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0137062072753906, "global_step": 498850, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1786983013153076, "global_step": 498851, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0377402305603027, "global_step": 498852, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0539114475250244, "global_step": 498853, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0055155754089355, "global_step": 498854, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0510804653167725, "global_step": 498855, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.111467123031616, "global_step": 498856, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0792768001556396, "global_step": 498857, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0699684619903564, "global_step": 498858, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.106553316116333, "global_step": 498859, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0737709999084473, "global_step": 498860, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1126019954681396, "global_step": 498861, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0337679386138916, "global_step": 498862, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9938790798187256, "global_step": 498863, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.073643922805786, "global_step": 498864, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0509769916534424, "global_step": 498865, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0152156352996826, "global_step": 498866, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.070977210998535, "global_step": 498867, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1290910243988037, "global_step": 498868, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.103093385696411, "global_step": 498869, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.050481081008911, "global_step": 498870, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.080106019973755, "global_step": 498871, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.110457181930542, "global_step": 498872, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0225653648376465, "global_step": 498873, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0745763778686523, "global_step": 498874, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.066549777984619, "global_step": 498875, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0388638973236084, "global_step": 498876, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.070870876312256, "global_step": 498877, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0600075721740723, "global_step": 498878, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0800137519836426, "global_step": 498879, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0443403720855713, "global_step": 498880, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.012601852416992, "global_step": 498881, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9757908582687378, "global_step": 498882, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0339443683624268, "global_step": 498883, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.068314790725708, "global_step": 498884, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.086704969406128, "global_step": 498885, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1275997161865234, "global_step": 498886, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.037872314453125, "global_step": 498887, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.043152093887329, "global_step": 498888, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0446555614471436, "global_step": 498889, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.119272232055664, "global_step": 498890, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.011584520339966, "global_step": 498891, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0693771839141846, "global_step": 498892, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.036137580871582, "global_step": 498893, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0825037956237793, "global_step": 498894, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0058815479278564, "global_step": 498895, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.069023609161377, "global_step": 498896, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0509033203125, "global_step": 498897, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.050034284591675, "global_step": 498898, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.04449725151062, "global_step": 498899, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0930938720703125, "global_step": 498900, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9577804803848267, "global_step": 498901, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.029637336730957, "global_step": 498902, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.038679838180542, "global_step": 498903, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0798306465148926, "global_step": 498904, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0164120197296143, "global_step": 498905, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0559539794921875, "global_step": 498906, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0301530361175537, "global_step": 498907, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0813448429107666, "global_step": 498908, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0672225952148438, "global_step": 498909, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1316099166870117, "global_step": 498910, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0883936882019043, "global_step": 498911, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.038938045501709, "global_step": 498912, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.040907621383667, "global_step": 498913, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0796561241149902, "global_step": 498914, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.060153007507324, "global_step": 498915, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0414857864379883, "global_step": 498916, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0993611812591553, "global_step": 498917, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1217563152313232, "global_step": 498918, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0574698448181152, "global_step": 498919, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.096114158630371, "global_step": 498920, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0980544090270996, "global_step": 498921, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0613622665405273, "global_step": 498922, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0461277961730957, "global_step": 498923, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0273849964141846, "global_step": 498924, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0139095783233643, "global_step": 498925, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0869686603546143, "global_step": 498926, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0679850578308105, "global_step": 498927, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.928044319152832, "global_step": 498928, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0316481590270996, "global_step": 498929, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.048488140106201, "global_step": 498930, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.059826135635376, "global_step": 498931, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9720240831375122, "global_step": 498932, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1118826866149902, "global_step": 498933, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.049804925918579, "global_step": 498934, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0669891834259033, "global_step": 498935, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1062707901000977, "global_step": 498936, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.994689702987671, "global_step": 498937, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0483028888702393, "global_step": 498938, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1227612495422363, "global_step": 498939, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0634233951568604, "global_step": 498940, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0724282264709473, "global_step": 498941, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0239477157592773, "global_step": 498942, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0252277851104736, "global_step": 498943, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0885372161865234, "global_step": 498944, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.019756555557251, "global_step": 498945, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9250191450119019, "global_step": 498946, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.058131456375122, "global_step": 498947, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9862139225006104, "global_step": 498948, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0298845767974854, "global_step": 498949, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.063131809234619, "global_step": 498950, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0492632389068604, "global_step": 498951, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0157570838928223, "global_step": 498952, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.078495502471924, "global_step": 498953, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0172789096832275, "global_step": 498954, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1301283836364746, "global_step": 498955, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1484673023223877, "global_step": 498956, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.013978958129883, "global_step": 498957, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0738062858581543, "global_step": 498958, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.009049654006958, "global_step": 498959, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0086798667907715, "global_step": 498960, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.011528968811035, "global_step": 498961, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1586692333221436, "global_step": 498962, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.023399591445923, "global_step": 498963, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.041649103164673, "global_step": 498964, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9082001447677612, "global_step": 498965, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.127488613128662, "global_step": 498966, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0618491172790527, "global_step": 498967, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.00962495803833, "global_step": 498968, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.074492931365967, "global_step": 498969, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.032559633255005, "global_step": 498970, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0029501914978027, "global_step": 498971, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.932827115058899, "global_step": 498972, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.148711919784546, "global_step": 498973, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1106925010681152, "global_step": 498974, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.008744716644287, "global_step": 498975, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.013737678527832, "global_step": 498976, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.110299587249756, "global_step": 498977, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0862953662872314, "global_step": 498978, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0864198207855225, "global_step": 498979, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.120591640472412, "global_step": 498980, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9996552467346191, "global_step": 498981, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.989730954170227, "global_step": 498982, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0377416610717773, "global_step": 498983, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.005894899368286, "global_step": 498984, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1231164932250977, "global_step": 498985, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0919647216796875, "global_step": 498986, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9803791046142578, "global_step": 498987, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0124900341033936, "global_step": 498988, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.057279586791992, "global_step": 498989, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.104241132736206, "global_step": 498990, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1044676303863525, "global_step": 498991, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.091237783432007, "global_step": 498992, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9959484338760376, "global_step": 498993, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0229897499084473, "global_step": 498994, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0738577842712402, "global_step": 498995, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.042119026184082, "global_step": 498996, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9775422811508179, "global_step": 498997, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.138986587524414, "global_step": 498998, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.090183973312378, "global_step": 498999, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0536725521087646, "global_step": 499000, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0141918659210205, "global_step": 499001, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.043941020965576, "global_step": 499002, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.02209210395813, "global_step": 499003, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1101138591766357, "global_step": 499004, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0325984954833984, "global_step": 499005, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.979353904724121, "global_step": 499006, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.098503589630127, "global_step": 499007, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.099565029144287, "global_step": 499008, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.04496169090271, "global_step": 499009, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0405759811401367, "global_step": 499010, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0795555114746094, "global_step": 499011, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.159545660018921, "global_step": 499012, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0891835689544678, "global_step": 499013, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0735270977020264, "global_step": 499014, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.06807541847229, "global_step": 499015, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0595905780792236, "global_step": 499016, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0532922744750977, "global_step": 499017, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1091957092285156, "global_step": 499018, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0512290000915527, "global_step": 499019, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9896036386489868, "global_step": 499020, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.077988862991333, "global_step": 499021, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0387609004974365, "global_step": 499022, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.058556318283081, "global_step": 499023, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0812461376190186, "global_step": 499024, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0258054733276367, "global_step": 499025, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0745761394500732, "global_step": 499026, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0119521617889404, "global_step": 499027, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9695287942886353, "global_step": 499028, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0631394386291504, "global_step": 499029, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0399556159973145, "global_step": 499030, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.139660596847534, "global_step": 499031, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0051186084747314, "global_step": 499032, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9937005043029785, "global_step": 499033, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0928499698638916, "global_step": 499034, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0394246578216553, "global_step": 499035, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.071605682373047, "global_step": 499036, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0656309127807617, "global_step": 499037, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1049952507019043, "global_step": 499038, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.085568904876709, "global_step": 499039, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.071906805038452, "global_step": 499040, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.100146770477295, "global_step": 499041, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0926249027252197, "global_step": 499042, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.040999412536621, "global_step": 499043, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.088253974914551, "global_step": 499044, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9773533344268799, "global_step": 499045, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.063307285308838, "global_step": 499046, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.112870931625366, "global_step": 499047, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.049034357070923, "global_step": 499048, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.03686785697937, "global_step": 499049, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.13106632232666, "global_step": 499050, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0723936557769775, "global_step": 499051, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.136497735977173, "global_step": 499052, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0744738578796387, "global_step": 499053, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9942290782928467, "global_step": 499054, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.095715284347534, "global_step": 499055, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0291805267333984, "global_step": 499056, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.046658754348755, "global_step": 499057, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0920207500457764, "global_step": 499058, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9462616443634033, "global_step": 499059, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0374982357025146, "global_step": 499060, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0502071380615234, "global_step": 499061, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.052706480026245, "global_step": 499062, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0628833770751953, "global_step": 499063, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.043020248413086, "global_step": 499064, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0920591354370117, "global_step": 499065, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.057216167449951, "global_step": 499066, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.069739580154419, "global_step": 499067, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9951695203781128, "global_step": 499068, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0200436115264893, "global_step": 499069, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0689427852630615, "global_step": 499070, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.078888177871704, "global_step": 499071, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0468437671661377, "global_step": 499072, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0469045639038086, "global_step": 499073, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0898361206054688, "global_step": 499074, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0361499786376953, "global_step": 499075, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0400946140289307, "global_step": 499076, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9791501760482788, "global_step": 499077, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0510480403900146, "global_step": 499078, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0390100479125977, "global_step": 499079, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9978992938995361, "global_step": 499080, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.94985032081604, "global_step": 499081, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.957407832145691, "global_step": 499082, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9261260032653809, "global_step": 499083, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0685415267944336, "global_step": 499084, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0057296752929688, "global_step": 499085, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.025986909866333, "global_step": 499086, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0975894927978516, "global_step": 499087, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9977376461029053, "global_step": 499088, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1382381916046143, "global_step": 499089, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.063251495361328, "global_step": 499090, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1135404109954834, "global_step": 499091, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1255016326904297, "global_step": 499092, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0708727836608887, "global_step": 499093, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.03708553314209, "global_step": 499094, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0580179691314697, "global_step": 499095, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.089118480682373, "global_step": 499096, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9789270162582397, "global_step": 499097, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.070486307144165, "global_step": 499098, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0477147102355957, "global_step": 499099, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.113370895385742, "global_step": 499100, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1053123474121094, "global_step": 499101, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.087658643722534, "global_step": 499102, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.059537410736084, "global_step": 499103, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1078011989593506, "global_step": 499104, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.009697675704956, "global_step": 499105, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0476367473602295, "global_step": 499106, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.096452474594116, "global_step": 499107, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.084947109222412, "global_step": 499108, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.086775779724121, "global_step": 499109, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0098795890808105, "global_step": 499110, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0424349308013916, "global_step": 499111, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0891802310943604, "global_step": 499112, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.071807622909546, "global_step": 499113, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.047063112258911, "global_step": 499114, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.025336980819702, "global_step": 499115, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.042177200317383, "global_step": 499116, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0795230865478516, "global_step": 499117, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0056748390197754, "global_step": 499118, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.960585594177246, "global_step": 499119, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9903331995010376, "global_step": 499120, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.980870246887207, "global_step": 499121, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.062723398208618, "global_step": 499122, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0466270446777344, "global_step": 499123, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1058132648468018, "global_step": 499124, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0556416511535645, "global_step": 499125, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0525379180908203, "global_step": 499126, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.051257610321045, "global_step": 499127, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.076049327850342, "global_step": 499128, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1230502128601074, "global_step": 499129, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0273823738098145, "global_step": 499130, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9620733261108398, "global_step": 499131, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1472020149230957, "global_step": 499132, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.08614444732666, "global_step": 499133, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.034257411956787, "global_step": 499134, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.036370038986206, "global_step": 499135, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0702412128448486, "global_step": 499136, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.101175308227539, "global_step": 499137, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.045156717300415, "global_step": 499138, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1275572776794434, "global_step": 499139, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1308040618896484, "global_step": 499140, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.141453981399536, "global_step": 499141, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9808381795883179, "global_step": 499142, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.088843584060669, "global_step": 499143, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.020324945449829, "global_step": 499144, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0779166221618652, "global_step": 499145, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.003748893737793, "global_step": 499146, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.004220962524414, "global_step": 499147, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.106717348098755, "global_step": 499148, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0056917667388916, "global_step": 499149, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.9792972803115845, "global_step": 499150, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1117289066314697, "global_step": 499151, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.128600597381592, "global_step": 499152, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.047119140625, "global_step": 499153, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.063278913497925, "global_step": 499154, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.1217312812805176, "global_step": 499155, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0027661323547363, "global_step": 499156, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.019428253173828, "global_step": 499157, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0668277740478516, "global_step": 499158, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0646908283233643, "global_step": 499159, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.028744697570801, "global_step": 499160, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0469486713409424, "global_step": 499161, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0242714881896973, "global_step": 499162, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.028731107711792, "global_step": 499163, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.140817165374756, "global_step": 499164, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.010450601577759, "global_step": 499165, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.0537638664245605, "global_step": 499166, "epoch": 864, "lr": 5e-05}
{"train_loss": 2.050852060317993, "global_step": 499167, "epoch": 864, "lr": 5e-05}
{"train_loss": 1.96635901927948, "global_step": 499168, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9885101318359375, "global_step": 499169, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9836859703063965, "global_step": 499170, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0157692432403564, "global_step": 499171, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0957930088043213, "global_step": 499172, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0326638221740723, "global_step": 499173, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.095581293106079, "global_step": 499174, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.004753351211548, "global_step": 499175, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.000028371810913, "global_step": 499176, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.021883249282837, "global_step": 499177, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.008439540863037, "global_step": 499178, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.04972243309021, "global_step": 499179, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0451433658599854, "global_step": 499180, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.030191659927368, "global_step": 499181, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1249115467071533, "global_step": 499182, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.048351526260376, "global_step": 499183, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.992936134338379, "global_step": 499184, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0098206996917725, "global_step": 499185, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1031575202941895, "global_step": 499186, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.045527935028076, "global_step": 499187, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.057102918624878, "global_step": 499188, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.074317455291748, "global_step": 499189, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0482382774353027, "global_step": 499190, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9938372373580933, "global_step": 499191, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.06876540184021, "global_step": 499192, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0092339515686035, "global_step": 499193, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.090651750564575, "global_step": 499194, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1005380153656006, "global_step": 499195, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.018401622772217, "global_step": 499196, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.089853048324585, "global_step": 499197, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.953849196434021, "global_step": 499198, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.148239850997925, "global_step": 499199, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0785155296325684, "global_step": 499200, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.092559337615967, "global_step": 499201, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.006856679916382, "global_step": 499202, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9607309103012085, "global_step": 499203, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.973644733428955, "global_step": 499204, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0296578407287598, "global_step": 499205, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.063554286956787, "global_step": 499206, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.003833055496216, "global_step": 499207, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0599052906036377, "global_step": 499208, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0507700443267822, "global_step": 499209, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.004246950149536, "global_step": 499210, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9809463024139404, "global_step": 499211, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0043375492095947, "global_step": 499212, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0125510692596436, "global_step": 499213, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0019710063934326, "global_step": 499214, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.097925901412964, "global_step": 499215, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0133283138275146, "global_step": 499216, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9817920923233032, "global_step": 499217, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0243334770202637, "global_step": 499218, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0218513011932373, "global_step": 499219, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.083153247833252, "global_step": 499220, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0706217288970947, "global_step": 499221, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.083939790725708, "global_step": 499222, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9946843385696411, "global_step": 499223, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0425939559936523, "global_step": 499224, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0684802532196045, "global_step": 499225, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0653629302978516, "global_step": 499226, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0932059288024902, "global_step": 499227, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0167627334594727, "global_step": 499228, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0770397186279297, "global_step": 499229, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0779125690460205, "global_step": 499230, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0221974849700928, "global_step": 499231, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.004324197769165, "global_step": 499232, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0084617137908936, "global_step": 499233, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0712060928344727, "global_step": 499234, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0668468475341797, "global_step": 499235, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.081376552581787, "global_step": 499236, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.047212839126587, "global_step": 499237, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1212575435638428, "global_step": 499238, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0141327381134033, "global_step": 499239, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.131007194519043, "global_step": 499240, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.122570037841797, "global_step": 499241, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0164315700531006, "global_step": 499242, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9871671199798584, "global_step": 499243, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0659945011138916, "global_step": 499244, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1769039630889893, "global_step": 499245, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.062225818634033, "global_step": 499246, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.025190591812134, "global_step": 499247, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.007633686065674, "global_step": 499248, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.062316656112671, "global_step": 499249, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0549333095550537, "global_step": 499250, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0217316150665283, "global_step": 499251, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.069959878921509, "global_step": 499252, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1160523891448975, "global_step": 499253, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9875648021697998, "global_step": 499254, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9945578575134277, "global_step": 499255, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.035266399383545, "global_step": 499256, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.02671217918396, "global_step": 499257, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0539305210113525, "global_step": 499258, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0336523056030273, "global_step": 499259, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0663576126098633, "global_step": 499260, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0467753410339355, "global_step": 499261, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.008904457092285, "global_step": 499262, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.035940647125244, "global_step": 499263, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.098891258239746, "global_step": 499264, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.16282320022583, "global_step": 499265, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.065002918243408, "global_step": 499266, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.047973155975342, "global_step": 499267, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.046994209289551, "global_step": 499268, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.089432716369629, "global_step": 499269, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0277767181396484, "global_step": 499270, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0089664459228516, "global_step": 499271, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0756189823150635, "global_step": 499272, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.039550542831421, "global_step": 499273, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.055608034133911, "global_step": 499274, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0439932346343994, "global_step": 499275, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0532419681549072, "global_step": 499276, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0020556449890137, "global_step": 499277, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1151316165924072, "global_step": 499278, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0308616161346436, "global_step": 499279, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0243418216705322, "global_step": 499280, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1382312774658203, "global_step": 499281, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.002394914627075, "global_step": 499282, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.052797794342041, "global_step": 499283, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.038907051086426, "global_step": 499284, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.093217611312866, "global_step": 499285, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.991517186164856, "global_step": 499286, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.033033847808838, "global_step": 499287, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9995181560516357, "global_step": 499288, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.080381393432617, "global_step": 499289, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0176963806152344, "global_step": 499290, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.027954339981079, "global_step": 499291, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.091493606567383, "global_step": 499292, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0392978191375732, "global_step": 499293, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.078127384185791, "global_step": 499294, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.146416425704956, "global_step": 499295, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.103551149368286, "global_step": 499296, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0364863872528076, "global_step": 499297, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.023125648498535, "global_step": 499298, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.064237117767334, "global_step": 499299, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0026488304138184, "global_step": 499300, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.044455051422119, "global_step": 499301, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9569423198699951, "global_step": 499302, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.064404249191284, "global_step": 499303, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0159056186676025, "global_step": 499304, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.090243101119995, "global_step": 499305, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.051774740219116, "global_step": 499306, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0135104656219482, "global_step": 499307, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0322775840759277, "global_step": 499308, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.034944772720337, "global_step": 499309, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0675840377807617, "global_step": 499310, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0774307250976562, "global_step": 499311, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.11051082611084, "global_step": 499312, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.041370153427124, "global_step": 499313, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0789313316345215, "global_step": 499314, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.074157953262329, "global_step": 499315, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.044215202331543, "global_step": 499316, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0578434467315674, "global_step": 499317, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.072927951812744, "global_step": 499318, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0324158668518066, "global_step": 499319, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0177011489868164, "global_step": 499320, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9438658952713013, "global_step": 499321, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.056474208831787, "global_step": 499322, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0269243717193604, "global_step": 499323, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9744659662246704, "global_step": 499324, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.110942840576172, "global_step": 499325, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.027012348175049, "global_step": 499326, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0461983680725098, "global_step": 499327, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.041987419128418, "global_step": 499328, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0514729022979736, "global_step": 499329, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0236382484436035, "global_step": 499330, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.138780355453491, "global_step": 499331, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.060555934906006, "global_step": 499332, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.027691602706909, "global_step": 499333, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0284531116485596, "global_step": 499334, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.981058120727539, "global_step": 499335, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.044983386993408, "global_step": 499336, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.00545597076416, "global_step": 499337, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0768513679504395, "global_step": 499338, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.070540428161621, "global_step": 499339, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.02262544631958, "global_step": 499340, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.173527956008911, "global_step": 499341, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0896127223968506, "global_step": 499342, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0558269023895264, "global_step": 499343, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.011699914932251, "global_step": 499344, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.128730058670044, "global_step": 499345, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0095901489257812, "global_step": 499346, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0270371437072754, "global_step": 499347, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.992299199104309, "global_step": 499348, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0937039852142334, "global_step": 499349, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0268349647521973, "global_step": 499350, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0150744915008545, "global_step": 499351, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9985482692718506, "global_step": 499352, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0345940589904785, "global_step": 499353, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0875561237335205, "global_step": 499354, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9936498403549194, "global_step": 499355, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9680209159851074, "global_step": 499356, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9837685823440552, "global_step": 499357, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0410115718841553, "global_step": 499358, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.031406879425049, "global_step": 499359, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0799896717071533, "global_step": 499360, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0929412841796875, "global_step": 499361, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.057163715362549, "global_step": 499362, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1294894218444824, "global_step": 499363, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.111926794052124, "global_step": 499364, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9399017095565796, "global_step": 499365, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.068772792816162, "global_step": 499366, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.054152488708496, "global_step": 499367, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.084275484085083, "global_step": 499368, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9948575496673584, "global_step": 499369, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.054652214050293, "global_step": 499370, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.086670398712158, "global_step": 499371, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9340964555740356, "global_step": 499372, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9567763805389404, "global_step": 499373, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1351101398468018, "global_step": 499374, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9663797616958618, "global_step": 499375, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1030826568603516, "global_step": 499376, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0512430667877197, "global_step": 499377, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0012905597686768, "global_step": 499378, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0948269367218018, "global_step": 499379, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.040584087371826, "global_step": 499380, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.048117160797119, "global_step": 499381, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.094897508621216, "global_step": 499382, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0163400173187256, "global_step": 499383, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.030222177505493, "global_step": 499384, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.027336835861206, "global_step": 499385, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1585028171539307, "global_step": 499386, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.040449380874634, "global_step": 499387, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0355019569396973, "global_step": 499388, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0837934017181396, "global_step": 499389, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.142421007156372, "global_step": 499390, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0117344856262207, "global_step": 499391, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.102078676223755, "global_step": 499392, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0820443630218506, "global_step": 499393, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0225706100463867, "global_step": 499394, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0340769290924072, "global_step": 499395, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0420408248901367, "global_step": 499396, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.084742784500122, "global_step": 499397, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0694386959075928, "global_step": 499398, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0554094314575195, "global_step": 499399, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0141115188598633, "global_step": 499400, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0338058471679688, "global_step": 499401, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0379152297973633, "global_step": 499402, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1161882877349854, "global_step": 499403, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1052277088165283, "global_step": 499404, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0765788555145264, "global_step": 499405, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0291123390197754, "global_step": 499406, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1687004566192627, "global_step": 499407, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1207215785980225, "global_step": 499408, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0217654705047607, "global_step": 499409, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9537559747695923, "global_step": 499410, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0711748600006104, "global_step": 499411, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9751003980636597, "global_step": 499412, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.089003801345825, "global_step": 499413, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.054500102996826, "global_step": 499414, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9749186038970947, "global_step": 499415, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.066833257675171, "global_step": 499416, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.085019826889038, "global_step": 499417, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0494461059570312, "global_step": 499418, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.040114641189575, "global_step": 499419, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.111431121826172, "global_step": 499420, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1125783920288086, "global_step": 499421, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0800552368164062, "global_step": 499422, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0400288105010986, "global_step": 499423, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.050791025161743, "global_step": 499424, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.007474422454834, "global_step": 499425, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1072001457214355, "global_step": 499426, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.024397373199463, "global_step": 499427, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.024665594100952, "global_step": 499428, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1088192462921143, "global_step": 499429, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0710813999176025, "global_step": 499430, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0569872856140137, "global_step": 499431, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.02192759513855, "global_step": 499432, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.089035749435425, "global_step": 499433, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9958624839782715, "global_step": 499434, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0602784156799316, "global_step": 499435, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0272023677825928, "global_step": 499436, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0698022842407227, "global_step": 499437, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0400257110595703, "global_step": 499438, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.05179762840271, "global_step": 499439, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0358235836029053, "global_step": 499440, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1539273262023926, "global_step": 499441, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0072553157806396, "global_step": 499442, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.114215135574341, "global_step": 499443, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0099918842315674, "global_step": 499444, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9964172840118408, "global_step": 499445, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.087629795074463, "global_step": 499446, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0858635902404785, "global_step": 499447, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.121731758117676, "global_step": 499448, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.004930257797241, "global_step": 499449, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0272319316864014, "global_step": 499450, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0835907459259033, "global_step": 499451, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0182464122772217, "global_step": 499452, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0507309436798096, "global_step": 499453, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9722676277160645, "global_step": 499454, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0327107906341553, "global_step": 499455, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.050762176513672, "global_step": 499456, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.052675485610962, "global_step": 499457, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.093628168106079, "global_step": 499458, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.111140489578247, "global_step": 499459, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.021331310272217, "global_step": 499460, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0103602409362793, "global_step": 499461, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.05971360206604, "global_step": 499462, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0564916133880615, "global_step": 499463, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0055134296417236, "global_step": 499464, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.091247797012329, "global_step": 499465, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0526692867279053, "global_step": 499466, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1281185150146484, "global_step": 499467, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.034843683242798, "global_step": 499468, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.050093173980713, "global_step": 499469, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9938565492630005, "global_step": 499470, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1108059883117676, "global_step": 499471, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1183090209960938, "global_step": 499472, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0077991485595703, "global_step": 499473, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.089242696762085, "global_step": 499474, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.993887186050415, "global_step": 499475, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0736069679260254, "global_step": 499476, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.102553129196167, "global_step": 499477, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.148711919784546, "global_step": 499478, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.049896240234375, "global_step": 499479, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1230685710906982, "global_step": 499480, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0249369144439697, "global_step": 499481, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1275203227996826, "global_step": 499482, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0606930255889893, "global_step": 499483, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.001218557357788, "global_step": 499484, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9684029817581177, "global_step": 499485, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9695892333984375, "global_step": 499486, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0741894245147705, "global_step": 499487, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9983338117599487, "global_step": 499488, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0779895782470703, "global_step": 499489, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.055972099304199, "global_step": 499490, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0978221893310547, "global_step": 499491, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9913275241851807, "global_step": 499492, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0064587593078613, "global_step": 499493, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0754449367523193, "global_step": 499494, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0426530838012695, "global_step": 499495, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9181554317474365, "global_step": 499496, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0001726150512695, "global_step": 499497, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.985008955001831, "global_step": 499498, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.041698694229126, "global_step": 499499, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0189735889434814, "global_step": 499500, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0049262046813965, "global_step": 499501, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9661945104599, "global_step": 499502, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9955780506134033, "global_step": 499503, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0428459644317627, "global_step": 499504, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9989980459213257, "global_step": 499505, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.101736068725586, "global_step": 499506, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.069963216781616, "global_step": 499507, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0883638858795166, "global_step": 499508, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0190699100494385, "global_step": 499509, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0034072399139404, "global_step": 499510, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0528359413146973, "global_step": 499511, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.083921194076538, "global_step": 499512, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1115798950195312, "global_step": 499513, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9180959463119507, "global_step": 499514, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.101680040359497, "global_step": 499515, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.137167453765869, "global_step": 499516, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0924832820892334, "global_step": 499517, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0201785564422607, "global_step": 499518, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0129549503326416, "global_step": 499519, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.090184211730957, "global_step": 499520, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.990465760231018, "global_step": 499521, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.107060432434082, "global_step": 499522, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.046330213546753, "global_step": 499523, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.004258155822754, "global_step": 499524, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9886844158172607, "global_step": 499525, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0042121410369873, "global_step": 499526, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0463061332702637, "global_step": 499527, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0760738849639893, "global_step": 499528, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.035161256790161, "global_step": 499529, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0674006938934326, "global_step": 499530, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0208921432495117, "global_step": 499531, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9899895191192627, "global_step": 499532, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1226601600646973, "global_step": 499533, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.061866283416748, "global_step": 499534, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0102810859680176, "global_step": 499535, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.001965284347534, "global_step": 499536, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0139005184173584, "global_step": 499537, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.043675184249878, "global_step": 499538, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.119412899017334, "global_step": 499539, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.017794609069824, "global_step": 499540, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0577738285064697, "global_step": 499541, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.038613796234131, "global_step": 499542, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.101916551589966, "global_step": 499543, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.091487169265747, "global_step": 499544, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.023601770401001, "global_step": 499545, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0529375076293945, "global_step": 499546, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1494102478027344, "global_step": 499547, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9509297609329224, "global_step": 499548, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0270962715148926, "global_step": 499549, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0022783279418945, "global_step": 499550, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0393869876861572, "global_step": 499551, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0286755561828613, "global_step": 499552, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.012397527694702, "global_step": 499553, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0422158241271973, "global_step": 499554, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.049622058868408, "global_step": 499555, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0829451084136963, "global_step": 499556, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.067518949508667, "global_step": 499557, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0479812622070312, "global_step": 499558, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.060265302658081, "global_step": 499559, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.097938299179077, "global_step": 499560, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0314910411834717, "global_step": 499561, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0774192810058594, "global_step": 499562, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.088247060775757, "global_step": 499563, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1117665767669678, "global_step": 499564, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0757381916046143, "global_step": 499565, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0058960914611816, "global_step": 499566, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.137404680252075, "global_step": 499567, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.034398078918457, "global_step": 499568, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0387227535247803, "global_step": 499569, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9693830013275146, "global_step": 499570, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0695183277130127, "global_step": 499571, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.139636516571045, "global_step": 499572, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0196826457977295, "global_step": 499573, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0745413303375244, "global_step": 499574, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.046139717102051, "global_step": 499575, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.030590534210205, "global_step": 499576, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.073509693145752, "global_step": 499577, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.083970069885254, "global_step": 499578, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0350255966186523, "global_step": 499579, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0303149223327637, "global_step": 499580, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9932763576507568, "global_step": 499581, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9900153875350952, "global_step": 499582, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.092608690261841, "global_step": 499583, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.071725606918335, "global_step": 499584, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0379886627197266, "global_step": 499585, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0207395553588867, "global_step": 499586, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9807108640670776, "global_step": 499587, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1109232902526855, "global_step": 499588, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.070061683654785, "global_step": 499589, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.102555513381958, "global_step": 499590, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.034140110015869, "global_step": 499591, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0114355087280273, "global_step": 499592, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0115931034088135, "global_step": 499593, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.135139226913452, "global_step": 499594, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1019418239593506, "global_step": 499595, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0268123149871826, "global_step": 499596, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.042975664138794, "global_step": 499597, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9923585653305054, "global_step": 499598, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0038225650787354, "global_step": 499599, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.051501989364624, "global_step": 499600, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0205559730529785, "global_step": 499601, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.017094373703003, "global_step": 499602, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9881701469421387, "global_step": 499603, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0255918502807617, "global_step": 499604, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.103105068206787, "global_step": 499605, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0812408924102783, "global_step": 499606, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0816524028778076, "global_step": 499607, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.019930124282837, "global_step": 499608, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0825846195220947, "global_step": 499609, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.038494110107422, "global_step": 499610, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.075699806213379, "global_step": 499611, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0656325817108154, "global_step": 499612, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0521998405456543, "global_step": 499613, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1123616695404053, "global_step": 499614, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.101874351501465, "global_step": 499615, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.037106513977051, "global_step": 499616, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.140239715576172, "global_step": 499617, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0844521522521973, "global_step": 499618, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1132867336273193, "global_step": 499619, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1112117767333984, "global_step": 499620, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.01416015625, "global_step": 499621, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0494956970214844, "global_step": 499622, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.972529649734497, "global_step": 499623, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.896056890487671, "global_step": 499624, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9687036275863647, "global_step": 499625, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0220859050750732, "global_step": 499626, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0062148571014404, "global_step": 499627, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.046764373779297, "global_step": 499628, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1237716674804688, "global_step": 499629, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1542115211486816, "global_step": 499630, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0214016437530518, "global_step": 499631, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9460207223892212, "global_step": 499632, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.099438428878784, "global_step": 499633, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9671140909194946, "global_step": 499634, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0282342433929443, "global_step": 499635, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0700199604034424, "global_step": 499636, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9973434209823608, "global_step": 499637, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0668137073516846, "global_step": 499638, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.114851713180542, "global_step": 499639, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9952757358551025, "global_step": 499640, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.083879232406616, "global_step": 499641, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.009488344192505, "global_step": 499642, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0863258838653564, "global_step": 499643, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0561749935150146, "global_step": 499644, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.024895191192627, "global_step": 499645, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9827560186386108, "global_step": 499646, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.00105881690979, "global_step": 499647, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0402157306671143, "global_step": 499648, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.065709352493286, "global_step": 499649, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0798351764678955, "global_step": 499650, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.129657030105591, "global_step": 499651, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.044999837875366, "global_step": 499652, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0122108459472656, "global_step": 499653, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1216037273406982, "global_step": 499654, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0352089405059814, "global_step": 499655, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1360788345336914, "global_step": 499656, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0783028602600098, "global_step": 499657, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0699281692504883, "global_step": 499658, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0247364044189453, "global_step": 499659, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.069385051727295, "global_step": 499660, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0730834007263184, "global_step": 499661, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0022101402282715, "global_step": 499662, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0856330394744873, "global_step": 499663, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1204214096069336, "global_step": 499664, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.091186761856079, "global_step": 499665, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.043492317199707, "global_step": 499666, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9807462692260742, "global_step": 499667, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0681445598602295, "global_step": 499668, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0206801891326904, "global_step": 499669, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1894893646240234, "global_step": 499670, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.082721710205078, "global_step": 499671, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0203630924224854, "global_step": 499672, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9531742334365845, "global_step": 499673, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.062433958053589, "global_step": 499674, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.023942708969116, "global_step": 499675, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0075435638427734, "global_step": 499676, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0340416431427, "global_step": 499677, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9841959476470947, "global_step": 499678, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0849626064300537, "global_step": 499679, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0983481407165527, "global_step": 499680, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.100796699523926, "global_step": 499681, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.031780481338501, "global_step": 499682, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.137549638748169, "global_step": 499683, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9875584840774536, "global_step": 499684, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1066603660583496, "global_step": 499685, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0187861919403076, "global_step": 499686, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1114907264709473, "global_step": 499687, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0575695037841797, "global_step": 499688, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0634593963623047, "global_step": 499689, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0562727451324463, "global_step": 499690, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0424411296844482, "global_step": 499691, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9904189109802246, "global_step": 499692, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.004913806915283, "global_step": 499693, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.090698480606079, "global_step": 499694, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.134251117706299, "global_step": 499695, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9801360368728638, "global_step": 499696, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.075704574584961, "global_step": 499697, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1826717853546143, "global_step": 499698, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.083202362060547, "global_step": 499699, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0725603103637695, "global_step": 499700, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0384562015533447, "global_step": 499701, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.109510898590088, "global_step": 499702, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9708847999572754, "global_step": 499703, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.009524345397949, "global_step": 499704, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1195452213287354, "global_step": 499705, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0448408126831055, "global_step": 499706, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.076432943344116, "global_step": 499707, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0296168327331543, "global_step": 499708, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0921738147735596, "global_step": 499709, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0084245204925537, "global_step": 499710, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.023876667022705, "global_step": 499711, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.995896577835083, "global_step": 499712, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9331063032150269, "global_step": 499713, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0832459926605225, "global_step": 499714, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0021157264709473, "global_step": 499715, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9553964138031006, "global_step": 499716, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0140299797058105, "global_step": 499717, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.131276845932007, "global_step": 499718, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1090760231018066, "global_step": 499719, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0598130226135254, "global_step": 499720, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.010418176651001, "global_step": 499721, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.08512544631958, "global_step": 499722, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.013282299041748, "global_step": 499723, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1122405529022217, "global_step": 499724, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.129429817199707, "global_step": 499725, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0430984497070312, "global_step": 499726, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0910110473632812, "global_step": 499727, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0602052211761475, "global_step": 499728, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.112387180328369, "global_step": 499729, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1148619651794434, "global_step": 499730, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0732271671295166, "global_step": 499731, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9619871377944946, "global_step": 499732, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.194467067718506, "global_step": 499733, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.067032814025879, "global_step": 499734, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0790321826934814, "global_step": 499735, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.066426992416382, "global_step": 499736, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.043956756591797, "global_step": 499737, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.079516887664795, "global_step": 499738, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0850701332092285, "global_step": 499739, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0076472759246826, "global_step": 499740, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0373637676239014, "global_step": 499741, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9882943630218506, "global_step": 499742, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0565080642700195, "global_step": 499743, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0294389724731445, "global_step": 499744, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.061697006225586, "global_step": 499745, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.115607500076294, "global_step": 499746, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.097975730895996, "global_step": 499747, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.059316873550415, "global_step": 499748, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.019458293914795, "global_step": 499749, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.101388454437256, "global_step": 499750, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0077342987060547, "global_step": 499751, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.080777406692505, "global_step": 499752, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9819563627243042, "global_step": 499753, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0110154151916504, "global_step": 499754, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0442819595336914, "global_step": 499755, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.066948175430298, "global_step": 499756, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0605249404907227, "global_step": 499757, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.144101858139038, "global_step": 499758, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.080773115158081, "global_step": 499759, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0186309814453125, "global_step": 499760, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0954341888427734, "global_step": 499761, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.154081106185913, "global_step": 499762, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9564462900161743, "global_step": 499763, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.110470771789551, "global_step": 499764, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.03715443611145, "global_step": 499765, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0225377082824707, "global_step": 499766, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.138927698135376, "global_step": 499767, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0762014389038086, "global_step": 499768, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.048175096511841, "global_step": 499769, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.996546983718872, "global_step": 499770, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9667121171951294, "global_step": 499771, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0365493297576904, "global_step": 499772, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9839555025100708, "global_step": 499773, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.056025505065918, "global_step": 499774, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.122180938720703, "global_step": 499775, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0588765144348145, "global_step": 499776, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0373404026031494, "global_step": 499777, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.056783676147461, "global_step": 499778, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0516417026519775, "global_step": 499779, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1330008506774902, "global_step": 499780, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0630459785461426, "global_step": 499781, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1001434326171875, "global_step": 499782, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.015110731124878, "global_step": 499783, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.030675172805786, "global_step": 499784, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.006756544113159, "global_step": 499785, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.040658473968506, "global_step": 499786, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9967271089553833, "global_step": 499787, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.019303560256958, "global_step": 499788, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1056716442108154, "global_step": 499789, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0640437602996826, "global_step": 499790, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0672833919525146, "global_step": 499791, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1111884117126465, "global_step": 499792, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1244752407073975, "global_step": 499793, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0117199420928955, "global_step": 499794, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9692579507827759, "global_step": 499795, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0127854347229004, "global_step": 499796, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.07484769821167, "global_step": 499797, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.081120491027832, "global_step": 499798, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0308890342712402, "global_step": 499799, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1156482696533203, "global_step": 499800, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.053375244140625, "global_step": 499801, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0253303050994873, "global_step": 499802, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0837740898132324, "global_step": 499803, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.117225170135498, "global_step": 499804, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9555702209472656, "global_step": 499805, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.087144613265991, "global_step": 499806, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0594942569732666, "global_step": 499807, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0931944847106934, "global_step": 499808, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0514039993286133, "global_step": 499809, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.054959774017334, "global_step": 499810, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0668904781341553, "global_step": 499811, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9922431707382202, "global_step": 499812, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.08054780960083, "global_step": 499813, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.082073926925659, "global_step": 499814, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9976255893707275, "global_step": 499815, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0792412757873535, "global_step": 499816, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1102004051208496, "global_step": 499817, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0794055461883545, "global_step": 499818, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9897056818008423, "global_step": 499819, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9990570545196533, "global_step": 499820, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1005196571350098, "global_step": 499821, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.10699462890625, "global_step": 499822, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.050034284591675, "global_step": 499823, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0483317375183105, "global_step": 499824, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.053941011428833, "global_step": 499825, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.024414300918579, "global_step": 499826, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0061752796173096, "global_step": 499827, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.058424949645996, "global_step": 499828, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0004546642303467, "global_step": 499829, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0783095359802246, "global_step": 499830, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1132569313049316, "global_step": 499831, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0021979808807373, "global_step": 499832, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0724570751190186, "global_step": 499833, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0357754230499268, "global_step": 499834, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1302874088287354, "global_step": 499835, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0428171157836914, "global_step": 499836, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.999626636505127, "global_step": 499837, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.009432077407837, "global_step": 499838, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0631697177886963, "global_step": 499839, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.097371816635132, "global_step": 499840, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.043677568435669, "global_step": 499841, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.01267147064209, "global_step": 499842, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9859230518341064, "global_step": 499843, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0564844608306885, "global_step": 499844, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0330004692077637, "global_step": 499845, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.081876277923584, "global_step": 499846, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1238949298858643, "global_step": 499847, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.137972354888916, "global_step": 499848, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.116605281829834, "global_step": 499849, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.011945962905884, "global_step": 499850, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.081784963607788, "global_step": 499851, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.962365746498108, "global_step": 499852, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.104504108428955, "global_step": 499853, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.098379611968994, "global_step": 499854, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.063218355178833, "global_step": 499855, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.070143699645996, "global_step": 499856, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0364346504211426, "global_step": 499857, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.095745086669922, "global_step": 499858, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.058756113052368, "global_step": 499859, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9780877828598022, "global_step": 499860, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0863349437713623, "global_step": 499861, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9875603914260864, "global_step": 499862, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.004592180252075, "global_step": 499863, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0559611320495605, "global_step": 499864, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.080993890762329, "global_step": 499865, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9874423742294312, "global_step": 499866, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0835931301116943, "global_step": 499867, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0720887184143066, "global_step": 499868, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0636649131774902, "global_step": 499869, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.030750036239624, "global_step": 499870, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9965729713439941, "global_step": 499871, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.024841547012329, "global_step": 499872, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0745577812194824, "global_step": 499873, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.04807448387146, "global_step": 499874, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.025031328201294, "global_step": 499875, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9972702264785767, "global_step": 499876, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.045647621154785, "global_step": 499877, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0570130348205566, "global_step": 499878, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0105247497558594, "global_step": 499879, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.96775221824646, "global_step": 499880, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9848148822784424, "global_step": 499881, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0847854614257812, "global_step": 499882, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0645833015441895, "global_step": 499883, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.075737476348877, "global_step": 499884, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0245535373687744, "global_step": 499885, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9362034797668457, "global_step": 499886, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0906026363372803, "global_step": 499887, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.058415651321411, "global_step": 499888, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0135927200317383, "global_step": 499889, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0247697830200195, "global_step": 499890, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.113429307937622, "global_step": 499891, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9601987600326538, "global_step": 499892, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0056214332580566, "global_step": 499893, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.11897873878479, "global_step": 499894, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.001722812652588, "global_step": 499895, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1624903678894043, "global_step": 499896, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0276787281036377, "global_step": 499897, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0195906162261963, "global_step": 499898, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.112527847290039, "global_step": 499899, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.074786424636841, "global_step": 499900, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0828726291656494, "global_step": 499901, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.064453125, "global_step": 499902, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0279951095581055, "global_step": 499903, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.05008602142334, "global_step": 499904, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1471261978149414, "global_step": 499905, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.080355644226074, "global_step": 499906, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0323784351348877, "global_step": 499907, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.046816825866699, "global_step": 499908, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0379467010498047, "global_step": 499909, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.112053394317627, "global_step": 499910, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0178682804107666, "global_step": 499911, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.043860912322998, "global_step": 499912, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1030874252319336, "global_step": 499913, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0661306381225586, "global_step": 499914, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0878891944885254, "global_step": 499915, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1289710998535156, "global_step": 499916, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0621917247772217, "global_step": 499917, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0326287746429443, "global_step": 499918, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0218677520751953, "global_step": 499919, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.030634641647339, "global_step": 499920, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0232906341552734, "global_step": 499921, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1330363750457764, "global_step": 499922, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0720980167388916, "global_step": 499923, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.040940523147583, "global_step": 499924, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0082783699035645, "global_step": 499925, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0252344608306885, "global_step": 499926, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0054445266723633, "global_step": 499927, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0320591926574707, "global_step": 499928, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.091797113418579, "global_step": 499929, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9739391803741455, "global_step": 499930, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9953445196151733, "global_step": 499931, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0464816093444824, "global_step": 499932, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0939857959747314, "global_step": 499933, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9908713102340698, "global_step": 499934, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1238183975219727, "global_step": 499935, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0087430477142334, "global_step": 499936, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.086062431335449, "global_step": 499937, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.979846477508545, "global_step": 499938, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9447145462036133, "global_step": 499939, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.101802349090576, "global_step": 499940, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.134586811065674, "global_step": 499941, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.022260904312134, "global_step": 499942, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.088615655899048, "global_step": 499943, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0486667156219482, "global_step": 499944, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0237224102020264, "global_step": 499945, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0832340717315674, "global_step": 499946, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1108531951904297, "global_step": 499947, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.048976182937622, "global_step": 499948, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0443546772003174, "global_step": 499949, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.065023422241211, "global_step": 499950, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.968375563621521, "global_step": 499951, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.055510997772217, "global_step": 499952, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.994167685508728, "global_step": 499953, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.057560920715332, "global_step": 499954, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0811476707458496, "global_step": 499955, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.051478624343872, "global_step": 499956, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.175100803375244, "global_step": 499957, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0872082710266113, "global_step": 499958, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.041393756866455, "global_step": 499959, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1192638874053955, "global_step": 499960, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0798568725585938, "global_step": 499961, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0843870639801025, "global_step": 499962, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.051609992980957, "global_step": 499963, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1170523166656494, "global_step": 499964, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.079613208770752, "global_step": 499965, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.114210367202759, "global_step": 499966, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.044769525527954, "global_step": 499967, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0168299674987793, "global_step": 499968, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0390584468841553, "global_step": 499969, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.023310422897339, "global_step": 499970, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1192450523376465, "global_step": 499971, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0285322666168213, "global_step": 499972, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0546610355377197, "global_step": 499973, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0816376209259033, "global_step": 499974, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9831838607788086, "global_step": 499975, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0717029571533203, "global_step": 499976, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9256782531738281, "global_step": 499977, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0230348110198975, "global_step": 499978, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.02998685836792, "global_step": 499979, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.052218437194824, "global_step": 499980, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.110048532485962, "global_step": 499981, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0096774101257324, "global_step": 499982, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.086441993713379, "global_step": 499983, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.075777530670166, "global_step": 499984, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0699822902679443, "global_step": 499985, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9463640451431274, "global_step": 499986, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1050798892974854, "global_step": 499987, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0843963623046875, "global_step": 499988, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.064711809158325, "global_step": 499989, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0846729278564453, "global_step": 499990, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9966951608657837, "global_step": 499991, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0167202949523926, "global_step": 499992, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.045753240585327, "global_step": 499993, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.056248903274536, "global_step": 499994, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0365846157073975, "global_step": 499995, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0224709510803223, "global_step": 499996, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.075662612915039, "global_step": 499997, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.137819290161133, "global_step": 499998, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0745115280151367, "global_step": 499999, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9656158685684204, "global_step": 500000, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.025439977645874, "global_step": 500001, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0466830730438232, "global_step": 500002, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9588080644607544, "global_step": 500003, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.097487449645996, "global_step": 500004, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.005007028579712, "global_step": 500005, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9468845129013062, "global_step": 500006, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1425790786743164, "global_step": 500007, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1647870540618896, "global_step": 500008, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1589341163635254, "global_step": 500009, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0695295333862305, "global_step": 500010, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.2207350730895996, "global_step": 500011, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.044961929321289, "global_step": 500012, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0819590091705322, "global_step": 500013, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.055407762527466, "global_step": 500014, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0804872512817383, "global_step": 500015, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1548643112182617, "global_step": 500016, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0439774990081787, "global_step": 500017, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0922231674194336, "global_step": 500018, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.056661605834961, "global_step": 500019, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.07338285446167, "global_step": 500020, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0734570026397705, "global_step": 500021, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.989770770072937, "global_step": 500022, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.036898374557495, "global_step": 500023, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.050015449523926, "global_step": 500024, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0934548377990723, "global_step": 500025, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0402581691741943, "global_step": 500026, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.081873893737793, "global_step": 500027, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9625473022460938, "global_step": 500028, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1303746700286865, "global_step": 500029, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.087508201599121, "global_step": 500030, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.064176082611084, "global_step": 500031, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.035663604736328, "global_step": 500032, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0814883708953857, "global_step": 500033, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0529537200927734, "global_step": 500034, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.049846887588501, "global_step": 500035, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0508482456207275, "global_step": 500036, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0477242469787598, "global_step": 500037, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1024417877197266, "global_step": 500038, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0109078884124756, "global_step": 500039, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0774588584899902, "global_step": 500040, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.13561749458313, "global_step": 500041, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0781631469726562, "global_step": 500042, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0835845470428467, "global_step": 500043, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0410027503967285, "global_step": 500044, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0762054920196533, "global_step": 500045, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.127812385559082, "global_step": 500046, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.085953950881958, "global_step": 500047, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.04427433013916, "global_step": 500048, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1693308353424072, "global_step": 500049, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.09769868850708, "global_step": 500050, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0768587589263916, "global_step": 500051, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9806594848632812, "global_step": 500052, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.028270721435547, "global_step": 500053, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.115644693374634, "global_step": 500054, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.979277491569519, "global_step": 500055, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0163462162017822, "global_step": 500056, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.078097105026245, "global_step": 500057, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.050516128540039, "global_step": 500058, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9666763544082642, "global_step": 500059, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.093595027923584, "global_step": 500060, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9822871685028076, "global_step": 500061, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0144314765930176, "global_step": 500062, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0622596740722656, "global_step": 500063, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9312037229537964, "global_step": 500064, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0140607357025146, "global_step": 500065, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0696074962615967, "global_step": 500066, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1019110679626465, "global_step": 500067, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0250580310821533, "global_step": 500068, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0578665733337402, "global_step": 500069, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.131596803665161, "global_step": 500070, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.095684051513672, "global_step": 500071, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0134806632995605, "global_step": 500072, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0139400959014893, "global_step": 500073, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.139660358428955, "global_step": 500074, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1308236122131348, "global_step": 500075, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0374159812927246, "global_step": 500076, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1150994300842285, "global_step": 500077, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0273444652557373, "global_step": 500078, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.034334897994995, "global_step": 500079, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0507314205169678, "global_step": 500080, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0396108627319336, "global_step": 500081, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0212831497192383, "global_step": 500082, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0420262813568115, "global_step": 500083, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9497288465499878, "global_step": 500084, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9536325931549072, "global_step": 500085, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0846545696258545, "global_step": 500086, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.024350166320801, "global_step": 500087, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0129387378692627, "global_step": 500088, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0840179920196533, "global_step": 500089, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.076545476913452, "global_step": 500090, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0244200229644775, "global_step": 500091, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1033804416656494, "global_step": 500092, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.026685953140259, "global_step": 500093, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.069899082183838, "global_step": 500094, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.021946430206299, "global_step": 500095, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0320260524749756, "global_step": 500096, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.116548776626587, "global_step": 500097, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.073885679244995, "global_step": 500098, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9925750494003296, "global_step": 500099, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.121901750564575, "global_step": 500100, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.142116069793701, "global_step": 500101, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1197261810302734, "global_step": 500102, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.118894338607788, "global_step": 500103, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.109349250793457, "global_step": 500104, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.061349391937256, "global_step": 500105, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0232107639312744, "global_step": 500106, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.017946720123291, "global_step": 500107, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0331168174743652, "global_step": 500108, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0523085594177246, "global_step": 500109, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.95956552028656, "global_step": 500110, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0497958660125732, "global_step": 500111, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0803303718566895, "global_step": 500112, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.061516284942627, "global_step": 500113, "epoch": 865, "lr": 5e-05}
{"train_loss": 1.9671270847320557, "global_step": 500114, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1175105571746826, "global_step": 500115, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.10155987739563, "global_step": 500116, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.06925106048584, "global_step": 500117, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.022186279296875, "global_step": 500118, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0713071823120117, "global_step": 500119, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.157592535018921, "global_step": 500120, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0712928771972656, "global_step": 500121, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1347455978393555, "global_step": 500122, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0623557567596436, "global_step": 500123, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0507004261016846, "global_step": 500124, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.073183059692383, "global_step": 500125, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0710301399230957, "global_step": 500126, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.1146445274353027, "global_step": 500127, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.051673412322998, "global_step": 500128, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.019366979598999, "global_step": 500129, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0690526962280273, "global_step": 500130, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0976364612579346, "global_step": 500131, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.080861806869507, "global_step": 500132, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0480830669403076, "global_step": 500133, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0773959159851074, "global_step": 500134, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.045525074005127, "global_step": 500135, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.0521225929260254, "global_step": 500136, "epoch": 865, "lr": 5e-05}
{"train_loss": 2.09013032913208, "global_step": 500137, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0091779232025146, "global_step": 500138, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.030689001083374, "global_step": 500139, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9644771814346313, "global_step": 500140, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1010823249816895, "global_step": 500141, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0671210289001465, "global_step": 500142, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0645134449005127, "global_step": 500143, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9724760055541992, "global_step": 500144, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0064237117767334, "global_step": 500145, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9946675300598145, "global_step": 500146, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0467679500579834, "global_step": 500147, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9872392416000366, "global_step": 500148, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0746214389801025, "global_step": 500149, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0779294967651367, "global_step": 500150, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0206258296966553, "global_step": 500151, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.054136276245117, "global_step": 500152, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.015524387359619, "global_step": 500153, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0548899173736572, "global_step": 500154, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1048614978790283, "global_step": 500155, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0243332386016846, "global_step": 500156, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.044161558151245, "global_step": 500157, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9999001026153564, "global_step": 500158, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.100767135620117, "global_step": 500159, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0784668922424316, "global_step": 500160, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.111222982406616, "global_step": 500161, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0522336959838867, "global_step": 500162, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.096282482147217, "global_step": 500163, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9876275062561035, "global_step": 500164, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0053772926330566, "global_step": 500165, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.075706958770752, "global_step": 500166, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0285544395446777, "global_step": 500167, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0230870246887207, "global_step": 500168, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0062923431396484, "global_step": 500169, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0283913612365723, "global_step": 500170, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0110597610473633, "global_step": 500171, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9413965940475464, "global_step": 500172, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0512378215789795, "global_step": 500173, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0443718433380127, "global_step": 500174, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9978713989257812, "global_step": 500175, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.021070957183838, "global_step": 500176, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1706511974334717, "global_step": 500177, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0274457931518555, "global_step": 500178, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9988125562667847, "global_step": 500179, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.992724061012268, "global_step": 500180, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0081748962402344, "global_step": 500181, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0904970169067383, "global_step": 500182, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1240835189819336, "global_step": 500183, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.026338815689087, "global_step": 500184, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0564911365509033, "global_step": 500185, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9882721900939941, "global_step": 500186, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.060879945755005, "global_step": 500187, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.015557289123535, "global_step": 500188, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.082526206970215, "global_step": 500189, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.117398977279663, "global_step": 500190, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0426626205444336, "global_step": 500191, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.080589532852173, "global_step": 500192, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9928672313690186, "global_step": 500193, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0553646087646484, "global_step": 500194, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0530598163604736, "global_step": 500195, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.041555881500244, "global_step": 500196, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0990524291992188, "global_step": 500197, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0614166259765625, "global_step": 500198, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.06531023979187, "global_step": 500199, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9614149332046509, "global_step": 500200, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.012906789779663, "global_step": 500201, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0854129791259766, "global_step": 500202, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0629172325134277, "global_step": 500203, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0669167041778564, "global_step": 500204, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0248353481292725, "global_step": 500205, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0231056213378906, "global_step": 500206, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0312371253967285, "global_step": 500207, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0240602493286133, "global_step": 500208, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.033982038497925, "global_step": 500209, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0441629886627197, "global_step": 500210, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0473153591156006, "global_step": 500211, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.921444058418274, "global_step": 500212, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9995564222335815, "global_step": 500213, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9589805603027344, "global_step": 500214, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9738237857818604, "global_step": 500215, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.050743818283081, "global_step": 500216, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.008661985397339, "global_step": 500217, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.055084466934204, "global_step": 500218, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0012130737304688, "global_step": 500219, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.003211259841919, "global_step": 500220, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.045045852661133, "global_step": 500221, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0310873985290527, "global_step": 500222, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0171823501586914, "global_step": 500223, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9476035833358765, "global_step": 500224, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.114832878112793, "global_step": 500225, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9645357131958008, "global_step": 500226, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.033879280090332, "global_step": 500227, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0541834831237793, "global_step": 500228, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0691745281219482, "global_step": 500229, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.040621280670166, "global_step": 500230, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0498275756835938, "global_step": 500231, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.987716555595398, "global_step": 500232, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0639660358428955, "global_step": 500233, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0367634296417236, "global_step": 500234, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.093658208847046, "global_step": 500235, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0658257007598877, "global_step": 500236, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.029815912246704, "global_step": 500237, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9617083072662354, "global_step": 500238, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0759010314941406, "global_step": 500239, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.070429801940918, "global_step": 500240, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0349342823028564, "global_step": 500241, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9782280921936035, "global_step": 500242, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1453356742858887, "global_step": 500243, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9870455265045166, "global_step": 500244, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9787828922271729, "global_step": 500245, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9440031051635742, "global_step": 500246, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.070432186126709, "global_step": 500247, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.055297374725342, "global_step": 500248, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0513975620269775, "global_step": 500249, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0098369121551514, "global_step": 500250, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1605522632598877, "global_step": 500251, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.052633762359619, "global_step": 500252, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.122955560684204, "global_step": 500253, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.036724328994751, "global_step": 500254, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0967087745666504, "global_step": 500255, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.031046152114868, "global_step": 500256, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9203059673309326, "global_step": 500257, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.02997088432312, "global_step": 500258, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0617027282714844, "global_step": 500259, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.009990930557251, "global_step": 500260, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0778706073760986, "global_step": 500261, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9903314113616943, "global_step": 500262, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0965070724487305, "global_step": 500263, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9863888025283813, "global_step": 500264, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0763204097747803, "global_step": 500265, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0057621002197266, "global_step": 500266, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.989115834236145, "global_step": 500267, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.089463710784912, "global_step": 500268, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9999395608901978, "global_step": 500269, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0357022285461426, "global_step": 500270, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.120659589767456, "global_step": 500271, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1134774684906006, "global_step": 500272, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9895018339157104, "global_step": 500273, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0388107299804688, "global_step": 500274, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.958463430404663, "global_step": 500275, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0276107788085938, "global_step": 500276, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1184024810791016, "global_step": 500277, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0517830848693848, "global_step": 500278, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0657784938812256, "global_step": 500279, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.017486095428467, "global_step": 500280, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.039874315261841, "global_step": 500281, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9995144605636597, "global_step": 500282, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9841487407684326, "global_step": 500283, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.005730628967285, "global_step": 500284, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0911810398101807, "global_step": 500285, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.004249095916748, "global_step": 500286, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.036180019378662, "global_step": 500287, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0397555828094482, "global_step": 500288, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.052560329437256, "global_step": 500289, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0870487689971924, "global_step": 500290, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0590107440948486, "global_step": 500291, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0375285148620605, "global_step": 500292, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.987876296043396, "global_step": 500293, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0256011486053467, "global_step": 500294, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.038032293319702, "global_step": 500295, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0689992904663086, "global_step": 500296, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1492960453033447, "global_step": 500297, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0688681602478027, "global_step": 500298, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1260640621185303, "global_step": 500299, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0719683170318604, "global_step": 500300, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9874008893966675, "global_step": 500301, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9975471496582031, "global_step": 500302, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0247631072998047, "global_step": 500303, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.070432186126709, "global_step": 500304, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0518569946289062, "global_step": 500305, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.016201972961426, "global_step": 500306, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0436646938323975, "global_step": 500307, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1091020107269287, "global_step": 500308, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.952404499053955, "global_step": 500309, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9772911071777344, "global_step": 500310, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.050723075866699, "global_step": 500311, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0355606079101562, "global_step": 500312, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.107252836227417, "global_step": 500313, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.115098476409912, "global_step": 500314, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.072256088256836, "global_step": 500315, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0867719650268555, "global_step": 500316, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0703086853027344, "global_step": 500317, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.055516481399536, "global_step": 500318, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9796850681304932, "global_step": 500319, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.075599193572998, "global_step": 500320, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.044454574584961, "global_step": 500321, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0639402866363525, "global_step": 500322, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9832468032836914, "global_step": 500323, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0633838176727295, "global_step": 500324, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.049334764480591, "global_step": 500325, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0632452964782715, "global_step": 500326, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0004770755767822, "global_step": 500327, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0401949882507324, "global_step": 500328, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9947113990783691, "global_step": 500329, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.038412094116211, "global_step": 500330, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.04959774017334, "global_step": 500331, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0389788150787354, "global_step": 500332, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.090083599090576, "global_step": 500333, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.943523645401001, "global_step": 500334, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.085920572280884, "global_step": 500335, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0217809677124023, "global_step": 500336, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0477845668792725, "global_step": 500337, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0045340061187744, "global_step": 500338, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.044966697692871, "global_step": 500339, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9584523439407349, "global_step": 500340, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0639891624450684, "global_step": 500341, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.993132472038269, "global_step": 500342, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.111426830291748, "global_step": 500343, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.048274278640747, "global_step": 500344, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.093722105026245, "global_step": 500345, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1312992572784424, "global_step": 500346, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.127084970474243, "global_step": 500347, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0124824047088623, "global_step": 500348, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1088345050811768, "global_step": 500349, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.029207468032837, "global_step": 500350, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0223021507263184, "global_step": 500351, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.166675329208374, "global_step": 500352, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0431621074676514, "global_step": 500353, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1157281398773193, "global_step": 500354, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.115114688873291, "global_step": 500355, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.041879177093506, "global_step": 500356, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0472283363342285, "global_step": 500357, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0854556560516357, "global_step": 500358, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.030350685119629, "global_step": 500359, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0496325492858887, "global_step": 500360, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0134875774383545, "global_step": 500361, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1042981147766113, "global_step": 500362, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9960172176361084, "global_step": 500363, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.006074905395508, "global_step": 500364, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9844428300857544, "global_step": 500365, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0191214084625244, "global_step": 500366, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9886311292648315, "global_step": 500367, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0021443367004395, "global_step": 500368, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0076358318328857, "global_step": 500369, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0438621044158936, "global_step": 500370, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0970027446746826, "global_step": 500371, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.049639940261841, "global_step": 500372, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0067996978759766, "global_step": 500373, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0301826000213623, "global_step": 500374, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0249478816986084, "global_step": 500375, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.053865671157837, "global_step": 500376, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0123369693756104, "global_step": 500377, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.020925998687744, "global_step": 500378, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9527634382247925, "global_step": 500379, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0319714546203613, "global_step": 500380, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0139315128326416, "global_step": 500381, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1254355907440186, "global_step": 500382, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.088730573654175, "global_step": 500383, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9872418642044067, "global_step": 500384, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0615861415863037, "global_step": 500385, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.092982292175293, "global_step": 500386, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1419715881347656, "global_step": 500387, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.006037712097168, "global_step": 500388, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.038285255432129, "global_step": 500389, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0207037925720215, "global_step": 500390, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0421392917633057, "global_step": 500391, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9402384757995605, "global_step": 500392, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.069600820541382, "global_step": 500393, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.05338716506958, "global_step": 500394, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9729598760604858, "global_step": 500395, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0233585834503174, "global_step": 500396, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.044722318649292, "global_step": 500397, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.999105453491211, "global_step": 500398, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0845601558685303, "global_step": 500399, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9696526527404785, "global_step": 500400, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.174698829650879, "global_step": 500401, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0627694129943848, "global_step": 500402, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0201833248138428, "global_step": 500403, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0958378314971924, "global_step": 500404, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1350550651550293, "global_step": 500405, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0462608337402344, "global_step": 500406, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0407729148864746, "global_step": 500407, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.053556442260742, "global_step": 500408, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9415137767791748, "global_step": 500409, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1468706130981445, "global_step": 500410, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.060340642929077, "global_step": 500411, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1007065773010254, "global_step": 500412, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0823652744293213, "global_step": 500413, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0566697120666504, "global_step": 500414, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9780317544937134, "global_step": 500415, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1353564262390137, "global_step": 500416, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9895843267440796, "global_step": 500417, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0450210571289062, "global_step": 500418, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0372438430786133, "global_step": 500419, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0643162727355957, "global_step": 500420, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9337092638015747, "global_step": 500421, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.12959885597229, "global_step": 500422, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.010662794113159, "global_step": 500423, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1355350017547607, "global_step": 500424, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0677359104156494, "global_step": 500425, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0245132446289062, "global_step": 500426, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0951993465423584, "global_step": 500427, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1305885314941406, "global_step": 500428, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.163668155670166, "global_step": 500429, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0323257446289062, "global_step": 500430, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0677976608276367, "global_step": 500431, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9760953187942505, "global_step": 500432, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9745382070541382, "global_step": 500433, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.115891218185425, "global_step": 500434, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0450048446655273, "global_step": 500435, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0522499084472656, "global_step": 500436, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1231985092163086, "global_step": 500437, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.042992353439331, "global_step": 500438, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0860867500305176, "global_step": 500439, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0048794746398926, "global_step": 500440, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0232317447662354, "global_step": 500441, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0130248069763184, "global_step": 500442, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9987844228744507, "global_step": 500443, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0037784576416016, "global_step": 500444, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1083903312683105, "global_step": 500445, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0588459968566895, "global_step": 500446, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0892186164855957, "global_step": 500447, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9636197090148926, "global_step": 500448, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0096752643585205, "global_step": 500449, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9833941459655762, "global_step": 500450, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0925583839416504, "global_step": 500451, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9793589115142822, "global_step": 500452, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9837706089019775, "global_step": 500453, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0317585468292236, "global_step": 500454, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.06016206741333, "global_step": 500455, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9797948598861694, "global_step": 500456, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0739951133728027, "global_step": 500457, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0867908000946045, "global_step": 500458, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0036544799804688, "global_step": 500459, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0233154296875, "global_step": 500460, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1083898544311523, "global_step": 500461, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9852215051651, "global_step": 500462, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.051553964614868, "global_step": 500463, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.106337547302246, "global_step": 500464, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.054260015487671, "global_step": 500465, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.112966775894165, "global_step": 500466, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1234943866729736, "global_step": 500467, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0411908626556396, "global_step": 500468, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9827817678451538, "global_step": 500469, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.077671766281128, "global_step": 500470, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.8560185432434082, "global_step": 500471, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9881666898727417, "global_step": 500472, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9964466094970703, "global_step": 500473, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.00061297416687, "global_step": 500474, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1022074222564697, "global_step": 500475, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0477194786071777, "global_step": 500476, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0179877281188965, "global_step": 500477, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9844558238983154, "global_step": 500478, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9929691553115845, "global_step": 500479, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.061483144760132, "global_step": 500480, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0752005577087402, "global_step": 500481, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.051846742630005, "global_step": 500482, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0992465019226074, "global_step": 500483, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.029357671737671, "global_step": 500484, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0112597942352295, "global_step": 500485, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0677452087402344, "global_step": 500486, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9455387592315674, "global_step": 500487, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1328165531158447, "global_step": 500488, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.110320568084717, "global_step": 500489, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.01946759223938, "global_step": 500490, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1133623123168945, "global_step": 500491, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.021393299102783, "global_step": 500492, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.143418788909912, "global_step": 500493, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.02490234375, "global_step": 500494, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.059910297393799, "global_step": 500495, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0214860439300537, "global_step": 500496, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.065718650817871, "global_step": 500497, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.115513563156128, "global_step": 500498, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0589137077331543, "global_step": 500499, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1201884746551514, "global_step": 500500, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.070693254470825, "global_step": 500501, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.051368474960327, "global_step": 500502, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0850064754486084, "global_step": 500503, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.014453172683716, "global_step": 500504, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.063915252685547, "global_step": 500505, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0644819736480713, "global_step": 500506, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9823009967803955, "global_step": 500507, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.070911169052124, "global_step": 500508, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9685460329055786, "global_step": 500509, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0232858657836914, "global_step": 500510, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.089550256729126, "global_step": 500511, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0114636421203613, "global_step": 500512, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.064847469329834, "global_step": 500513, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0538172721862793, "global_step": 500514, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0706045627593994, "global_step": 500515, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.104935646057129, "global_step": 500516, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0318257808685303, "global_step": 500517, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0458457469940186, "global_step": 500518, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.051149606704712, "global_step": 500519, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9352326393127441, "global_step": 500520, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.033994674682617, "global_step": 500521, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9929271936416626, "global_step": 500522, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0805366039276123, "global_step": 500523, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.061110019683838, "global_step": 500524, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0487899780273438, "global_step": 500525, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0382237434387207, "global_step": 500526, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0390233993530273, "global_step": 500527, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.065096855163574, "global_step": 500528, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0285820960998535, "global_step": 500529, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0513882637023926, "global_step": 500530, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1068601608276367, "global_step": 500531, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9880189895629883, "global_step": 500532, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.065467119216919, "global_step": 500533, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.067857503890991, "global_step": 500534, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1115150451660156, "global_step": 500535, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0655274391174316, "global_step": 500536, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0671825408935547, "global_step": 500537, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.02038836479187, "global_step": 500538, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.069761276245117, "global_step": 500539, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0331614017486572, "global_step": 500540, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0557191371917725, "global_step": 500541, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0003578662872314, "global_step": 500542, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0378987789154053, "global_step": 500543, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0266189575195312, "global_step": 500544, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1080286502838135, "global_step": 500545, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0037457942962646, "global_step": 500546, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0642383098602295, "global_step": 500547, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9802742004394531, "global_step": 500548, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9769506454467773, "global_step": 500549, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.038201093673706, "global_step": 500550, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0834994316101074, "global_step": 500551, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0497803688049316, "global_step": 500552, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0779151916503906, "global_step": 500553, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0531747341156006, "global_step": 500554, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0634326934814453, "global_step": 500555, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0615646839141846, "global_step": 500556, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0536301136016846, "global_step": 500557, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.010800361633301, "global_step": 500558, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0478365421295166, "global_step": 500559, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.078000068664551, "global_step": 500560, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.134211301803589, "global_step": 500561, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.048942804336548, "global_step": 500562, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.072146415710449, "global_step": 500563, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.081386089324951, "global_step": 500564, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.104583501815796, "global_step": 500565, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9894167184829712, "global_step": 500566, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1295602321624756, "global_step": 500567, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.104180335998535, "global_step": 500568, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.048862934112549, "global_step": 500569, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.072604179382324, "global_step": 500570, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0086824893951416, "global_step": 500571, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.088489055633545, "global_step": 500572, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.107879638671875, "global_step": 500573, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0392866134643555, "global_step": 500574, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0279505252838135, "global_step": 500575, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.121086359024048, "global_step": 500576, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.064105272293091, "global_step": 500577, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0551204681396484, "global_step": 500578, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.034266948699951, "global_step": 500579, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1255733966827393, "global_step": 500580, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0209460258483887, "global_step": 500581, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1085829734802246, "global_step": 500582, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.048884630203247, "global_step": 500583, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.114856719970703, "global_step": 500584, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1054179668426514, "global_step": 500585, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1187336444854736, "global_step": 500586, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.2187583446502686, "global_step": 500587, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.045051097869873, "global_step": 500588, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0176162719726562, "global_step": 500589, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9992539882659912, "global_step": 500590, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.050985097885132, "global_step": 500591, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.935836911201477, "global_step": 500592, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1441938877105713, "global_step": 500593, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.038825750350952, "global_step": 500594, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0589420795440674, "global_step": 500595, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0540947914123535, "global_step": 500596, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.009051561355591, "global_step": 500597, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0255191326141357, "global_step": 500598, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.072031259536743, "global_step": 500599, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.009164810180664, "global_step": 500600, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.083192825317383, "global_step": 500601, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0585825443267822, "global_step": 500602, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.970467209815979, "global_step": 500603, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.069850206375122, "global_step": 500604, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.044400215148926, "global_step": 500605, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.057915449142456, "global_step": 500606, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.011168956756592, "global_step": 500607, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9468685388565063, "global_step": 500608, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.101970672607422, "global_step": 500609, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0654635429382324, "global_step": 500610, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0340418815612793, "global_step": 500611, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0034539699554443, "global_step": 500612, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.042968273162842, "global_step": 500613, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0013017654418945, "global_step": 500614, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9797401428222656, "global_step": 500615, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.113717555999756, "global_step": 500616, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0235002040863037, "global_step": 500617, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9991626739501953, "global_step": 500618, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.173004150390625, "global_step": 500619, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.031705141067505, "global_step": 500620, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0155386924743652, "global_step": 500621, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.089338779449463, "global_step": 500622, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9740376472473145, "global_step": 500623, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.030082941055298, "global_step": 500624, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.088134288787842, "global_step": 500625, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0494747161865234, "global_step": 500626, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.080467939376831, "global_step": 500627, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1119399070739746, "global_step": 500628, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0984296798706055, "global_step": 500629, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0097689628601074, "global_step": 500630, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0690054893493652, "global_step": 500631, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9844536781311035, "global_step": 500632, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0314292907714844, "global_step": 500633, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0061745643615723, "global_step": 500634, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0886404514312744, "global_step": 500635, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0012917518615723, "global_step": 500636, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.072354555130005, "global_step": 500637, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1259732246398926, "global_step": 500638, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1250717639923096, "global_step": 500639, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0232725143432617, "global_step": 500640, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1046364307403564, "global_step": 500641, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9811774492263794, "global_step": 500642, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0421879291534424, "global_step": 500643, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.030115842819214, "global_step": 500644, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0169105529785156, "global_step": 500645, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9807687997817993, "global_step": 500646, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.162262201309204, "global_step": 500647, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.052919626235962, "global_step": 500648, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0639350414276123, "global_step": 500649, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0057153701782227, "global_step": 500650, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1161599159240723, "global_step": 500651, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.032400369644165, "global_step": 500652, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1058082580566406, "global_step": 500653, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.004941701889038, "global_step": 500654, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0647594928741455, "global_step": 500655, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.120051860809326, "global_step": 500656, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.098381280899048, "global_step": 500657, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.049412488937378, "global_step": 500658, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.093909502029419, "global_step": 500659, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.070619821548462, "global_step": 500660, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0057365894317627, "global_step": 500661, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9968222379684448, "global_step": 500662, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.055790424346924, "global_step": 500663, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0869033336639404, "global_step": 500664, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9198052883148193, "global_step": 500665, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.060519218444824, "global_step": 500666, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0793604850769043, "global_step": 500667, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0309548377990723, "global_step": 500668, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.998507022857666, "global_step": 500669, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0308804512023926, "global_step": 500670, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1007816791534424, "global_step": 500671, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0495457649230957, "global_step": 500672, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.04032564163208, "global_step": 500673, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0375330448150635, "global_step": 500674, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.032747983932495, "global_step": 500675, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0123088359832764, "global_step": 500676, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9122393131256104, "global_step": 500677, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0488061904907227, "global_step": 500678, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9925369024276733, "global_step": 500679, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.097088575363159, "global_step": 500680, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0237505435943604, "global_step": 500681, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0664100646972656, "global_step": 500682, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9597810506820679, "global_step": 500683, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0162734985351562, "global_step": 500684, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0268468856811523, "global_step": 500685, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9912506341934204, "global_step": 500686, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.023409843444824, "global_step": 500687, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.034341812133789, "global_step": 500688, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0756423473358154, "global_step": 500689, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9764076471328735, "global_step": 500690, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0137293338775635, "global_step": 500691, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.051318883895874, "global_step": 500692, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9338949918746948, "global_step": 500693, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.002974271774292, "global_step": 500694, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0484707355499268, "global_step": 500695, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.037470579147339, "global_step": 500696, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.060847282409668, "global_step": 500697, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.093960762023926, "global_step": 500698, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0641579627990723, "global_step": 500699, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0946578979492188, "global_step": 500700, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.077054023742676, "global_step": 500701, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.001889228820801, "global_step": 500702, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0069992542266846, "global_step": 500703, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0955798625946045, "global_step": 500704, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.115137815475464, "global_step": 500705, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0166759490966797, "global_step": 500706, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.05767560005188, "global_step": 500707, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9816094636917114, "global_step": 500708, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9607486724853516, "global_step": 500709, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.090087652206421, "global_step": 500710, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.076568841934204, "global_step": 500711, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0686028003692627, "global_step": 500712, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0706801414489746, "global_step": 500713, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.093020439147949, "global_step": 500714, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0566165447235107, "global_step": 500715, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.007504940032959, "global_step": 500716, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.060319662094116, "global_step": 500717, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.060541868209839, "global_step": 500718, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9236607551574707, "global_step": 500719, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.025927782058716, "global_step": 500720, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0327484607696533, "global_step": 500721, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.052807331085205, "global_step": 500722, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.081862688064575, "global_step": 500723, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1011123657226562, "global_step": 500724, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.057811737060547, "global_step": 500725, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.125070333480835, "global_step": 500726, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.036168098449707, "global_step": 500727, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0259976387023926, "global_step": 500728, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0492725372314453, "global_step": 500729, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.007584810256958, "global_step": 500730, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0241823196411133, "global_step": 500731, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9695289134979248, "global_step": 500732, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0062997341156006, "global_step": 500733, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0420777797698975, "global_step": 500734, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0867366790771484, "global_step": 500735, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0482161045074463, "global_step": 500736, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0388526916503906, "global_step": 500737, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1034369468688965, "global_step": 500738, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1041736602783203, "global_step": 500739, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.095431327819824, "global_step": 500740, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0680882930755615, "global_step": 500741, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.035170316696167, "global_step": 500742, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0751583576202393, "global_step": 500743, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0532684326171875, "global_step": 500744, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0108447074890137, "global_step": 500745, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0509533882141113, "global_step": 500746, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0730748176574707, "global_step": 500747, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0843937397003174, "global_step": 500748, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.074402093887329, "global_step": 500749, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9911079406738281, "global_step": 500750, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0466136932373047, "global_step": 500751, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9888591766357422, "global_step": 500752, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0253453254699707, "global_step": 500753, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0420868396759033, "global_step": 500754, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0427944660186768, "global_step": 500755, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.107433795928955, "global_step": 500756, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.058976650238037, "global_step": 500757, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0625839233398438, "global_step": 500758, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0300612449645996, "global_step": 500759, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9821749925613403, "global_step": 500760, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9695842266082764, "global_step": 500761, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.046968936920166, "global_step": 500762, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0075619220733643, "global_step": 500763, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.03029203414917, "global_step": 500764, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0508861541748047, "global_step": 500765, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9287999868392944, "global_step": 500766, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9795010089874268, "global_step": 500767, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9782060384750366, "global_step": 500768, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1076548099517822, "global_step": 500769, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0499863624572754, "global_step": 500770, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.094123601913452, "global_step": 500771, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9798229932785034, "global_step": 500772, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0991828441619873, "global_step": 500773, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0736937522888184, "global_step": 500774, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9859261512756348, "global_step": 500775, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0304410457611084, "global_step": 500776, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0410995483398438, "global_step": 500777, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0091519355773926, "global_step": 500778, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1050398349761963, "global_step": 500779, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0318872928619385, "global_step": 500780, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0853588581085205, "global_step": 500781, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1090734004974365, "global_step": 500782, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0935354232788086, "global_step": 500783, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0889222621917725, "global_step": 500784, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1118428707122803, "global_step": 500785, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1104674339294434, "global_step": 500786, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.050726890563965, "global_step": 500787, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0653841495513916, "global_step": 500788, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0476248264312744, "global_step": 500789, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.039562702178955, "global_step": 500790, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0651278495788574, "global_step": 500791, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.013360023498535, "global_step": 500792, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.025279998779297, "global_step": 500793, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9944190979003906, "global_step": 500794, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0492703914642334, "global_step": 500795, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9705003499984741, "global_step": 500796, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.964528203010559, "global_step": 500797, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.991068720817566, "global_step": 500798, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.046922445297241, "global_step": 500799, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0406198501586914, "global_step": 500800, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.043954610824585, "global_step": 500801, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.078965425491333, "global_step": 500802, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0216422080993652, "global_step": 500803, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.108567953109741, "global_step": 500804, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1374058723449707, "global_step": 500805, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0301496982574463, "global_step": 500806, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.090362787246704, "global_step": 500807, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.166734457015991, "global_step": 500808, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0729899406433105, "global_step": 500809, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0022666454315186, "global_step": 500810, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0891382694244385, "global_step": 500811, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.071186065673828, "global_step": 500812, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9891163110733032, "global_step": 500813, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0755615234375, "global_step": 500814, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.070383071899414, "global_step": 500815, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0100858211517334, "global_step": 500816, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.084042549133301, "global_step": 500817, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.007840633392334, "global_step": 500818, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.022350788116455, "global_step": 500819, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9906049966812134, "global_step": 500820, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0771780014038086, "global_step": 500821, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.042942762374878, "global_step": 500822, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1204476356506348, "global_step": 500823, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0538554191589355, "global_step": 500824, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0765037536621094, "global_step": 500825, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9751280546188354, "global_step": 500826, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.016458034515381, "global_step": 500827, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.098299741744995, "global_step": 500828, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0404715538024902, "global_step": 500829, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0771727561950684, "global_step": 500830, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9908710718154907, "global_step": 500831, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.111839532852173, "global_step": 500832, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0765461921691895, "global_step": 500833, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.06855845451355, "global_step": 500834, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0348570346832275, "global_step": 500835, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.160630464553833, "global_step": 500836, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.042781352996826, "global_step": 500837, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1563680171966553, "global_step": 500838, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.126955509185791, "global_step": 500839, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1098735332489014, "global_step": 500840, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1296541690826416, "global_step": 500841, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0617544651031494, "global_step": 500842, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.998942494392395, "global_step": 500843, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9747745990753174, "global_step": 500844, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.974373698234558, "global_step": 500845, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0824480056762695, "global_step": 500846, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0666205883026123, "global_step": 500847, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0556514263153076, "global_step": 500848, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.047088623046875, "global_step": 500849, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1268653869628906, "global_step": 500850, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.047595739364624, "global_step": 500851, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0743937492370605, "global_step": 500852, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9280565977096558, "global_step": 500853, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.03824782371521, "global_step": 500854, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0754969120025635, "global_step": 500855, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1106510162353516, "global_step": 500856, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0087273120880127, "global_step": 500857, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0736775398254395, "global_step": 500858, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.086390733718872, "global_step": 500859, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0673630237579346, "global_step": 500860, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0303025245666504, "global_step": 500861, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0923752784729004, "global_step": 500862, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.072582960128784, "global_step": 500863, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0707647800445557, "global_step": 500864, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.909414529800415, "global_step": 500865, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0641181468963623, "global_step": 500866, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9935040473937988, "global_step": 500867, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.050776481628418, "global_step": 500868, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0370919704437256, "global_step": 500869, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0766894817352295, "global_step": 500870, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0298337936401367, "global_step": 500871, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1083836555480957, "global_step": 500872, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.08278489112854, "global_step": 500873, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0479209423065186, "global_step": 500874, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.078354597091675, "global_step": 500875, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9850077629089355, "global_step": 500876, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0612971782684326, "global_step": 500877, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.060500383377075, "global_step": 500878, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.060711145401001, "global_step": 500879, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.022446632385254, "global_step": 500880, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1428778171539307, "global_step": 500881, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9436085224151611, "global_step": 500882, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.076341152191162, "global_step": 500883, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0353660583496094, "global_step": 500884, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0875940322875977, "global_step": 500885, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1293771266937256, "global_step": 500886, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.068931818008423, "global_step": 500887, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1284711360931396, "global_step": 500888, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.136625289916992, "global_step": 500889, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0063095092773438, "global_step": 500890, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0133612155914307, "global_step": 500891, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0145819187164307, "global_step": 500892, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0774712562561035, "global_step": 500893, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.061924934387207, "global_step": 500894, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.034334182739258, "global_step": 500895, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0450215339660645, "global_step": 500896, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0359225273132324, "global_step": 500897, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.065225839614868, "global_step": 500898, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.007828712463379, "global_step": 500899, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.999748945236206, "global_step": 500900, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0229249000549316, "global_step": 500901, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.09671688079834, "global_step": 500902, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1339385509490967, "global_step": 500903, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1346285343170166, "global_step": 500904, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9456164836883545, "global_step": 500905, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0263049602508545, "global_step": 500906, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0449113845825195, "global_step": 500907, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.088254928588867, "global_step": 500908, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.063457489013672, "global_step": 500909, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.064619302749634, "global_step": 500910, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.144296169281006, "global_step": 500911, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.028703451156616, "global_step": 500912, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1664047241210938, "global_step": 500913, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9865829944610596, "global_step": 500914, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.070216178894043, "global_step": 500915, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.008629083633423, "global_step": 500916, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0991952419281006, "global_step": 500917, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.075446844100952, "global_step": 500918, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1085164546966553, "global_step": 500919, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.101066827774048, "global_step": 500920, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9489479064941406, "global_step": 500921, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1005640029907227, "global_step": 500922, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1078526973724365, "global_step": 500923, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.083761692047119, "global_step": 500924, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.039073944091797, "global_step": 500925, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1206765174865723, "global_step": 500926, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.047539710998535, "global_step": 500927, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0712170600891113, "global_step": 500928, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0066215991973877, "global_step": 500929, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0713205337524414, "global_step": 500930, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0212595462799072, "global_step": 500931, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9741384983062744, "global_step": 500932, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.071187734603882, "global_step": 500933, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0149333477020264, "global_step": 500934, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.01444935798645, "global_step": 500935, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0824525356292725, "global_step": 500936, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.083862066268921, "global_step": 500937, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0757949352264404, "global_step": 500938, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0835742950439453, "global_step": 500939, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.049179792404175, "global_step": 500940, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0101757049560547, "global_step": 500941, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0351274013519287, "global_step": 500942, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0278472900390625, "global_step": 500943, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.075195789337158, "global_step": 500944, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.98856520652771, "global_step": 500945, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9887562990188599, "global_step": 500946, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.108513832092285, "global_step": 500947, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.044086217880249, "global_step": 500948, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0183136463165283, "global_step": 500949, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0704967975616455, "global_step": 500950, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.096251964569092, "global_step": 500951, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1185085773468018, "global_step": 500952, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9857057332992554, "global_step": 500953, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.029369831085205, "global_step": 500954, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9993435144424438, "global_step": 500955, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.110292911529541, "global_step": 500956, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1094515323638916, "global_step": 500957, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0726945400238037, "global_step": 500958, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1060285568237305, "global_step": 500959, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0088112354278564, "global_step": 500960, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0027718544006348, "global_step": 500961, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0266151428222656, "global_step": 500962, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.050692558288574, "global_step": 500963, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.02544903755188, "global_step": 500964, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1011431217193604, "global_step": 500965, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0207438468933105, "global_step": 500966, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0373072624206543, "global_step": 500967, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0565438270568848, "global_step": 500968, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.072577476501465, "global_step": 500969, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0609383583068848, "global_step": 500970, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0632376670837402, "global_step": 500971, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.210244655609131, "global_step": 500972, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9490584135055542, "global_step": 500973, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1137516498565674, "global_step": 500974, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.11861252784729, "global_step": 500975, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.997601866722107, "global_step": 500976, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0026776790618896, "global_step": 500977, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.136608123779297, "global_step": 500978, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0093092918395996, "global_step": 500979, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1505284309387207, "global_step": 500980, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0699987411499023, "global_step": 500981, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.965713620185852, "global_step": 500982, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1396563053131104, "global_step": 500983, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0667619705200195, "global_step": 500984, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.046093225479126, "global_step": 500985, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.101325035095215, "global_step": 500986, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.114694356918335, "global_step": 500987, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0611398220062256, "global_step": 500988, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.088348150253296, "global_step": 500989, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0810933113098145, "global_step": 500990, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.006890296936035, "global_step": 500991, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0339314937591553, "global_step": 500992, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.053575277328491, "global_step": 500993, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.020596504211426, "global_step": 500994, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9929585456848145, "global_step": 500995, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1337437629699707, "global_step": 500996, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.980207085609436, "global_step": 500997, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.043252944946289, "global_step": 500998, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.061838150024414, "global_step": 500999, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0118210315704346, "global_step": 501000, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.074514627456665, "global_step": 501001, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0170083045959473, "global_step": 501002, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.040705442428589, "global_step": 501003, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0443625450134277, "global_step": 501004, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.070441484451294, "global_step": 501005, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0768513679504395, "global_step": 501006, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0599706172943115, "global_step": 501007, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.978129506111145, "global_step": 501008, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0778958797454834, "global_step": 501009, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0866799354553223, "global_step": 501010, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0962445735931396, "global_step": 501011, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1610147953033447, "global_step": 501012, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.068575620651245, "global_step": 501013, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1022486686706543, "global_step": 501014, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0583598613739014, "global_step": 501015, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1104817390441895, "global_step": 501016, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.052494764328003, "global_step": 501017, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9860668182373047, "global_step": 501018, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0000405311584473, "global_step": 501019, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.077542304992676, "global_step": 501020, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.095264434814453, "global_step": 501021, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.091982364654541, "global_step": 501022, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0148892402648926, "global_step": 501023, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.122359275817871, "global_step": 501024, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.016343593597412, "global_step": 501025, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.117232084274292, "global_step": 501026, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0307979583740234, "global_step": 501027, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.005646228790283, "global_step": 501028, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.013887882232666, "global_step": 501029, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.090073585510254, "global_step": 501030, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0870399475097656, "global_step": 501031, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0560555458068848, "global_step": 501032, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0817761421203613, "global_step": 501033, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.064879894256592, "global_step": 501034, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.015289545059204, "global_step": 501035, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0281856060028076, "global_step": 501036, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0254058837890625, "global_step": 501037, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.02691650390625, "global_step": 501038, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0408666133880615, "global_step": 501039, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0721962451934814, "global_step": 501040, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.087165117263794, "global_step": 501041, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0928378105163574, "global_step": 501042, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.044019937515259, "global_step": 501043, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9438673257827759, "global_step": 501044, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.993514895439148, "global_step": 501045, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0015151500701904, "global_step": 501046, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.110680103302002, "global_step": 501047, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.025677442550659, "global_step": 501048, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.097440481185913, "global_step": 501049, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0628018379211426, "global_step": 501050, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0945279598236084, "global_step": 501051, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.137878179550171, "global_step": 501052, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.052678108215332, "global_step": 501053, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.9752310514450073, "global_step": 501054, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0184590816497803, "global_step": 501055, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.045625686645508, "global_step": 501056, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.099043607711792, "global_step": 501057, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0941388607025146, "global_step": 501058, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.087705135345459, "global_step": 501059, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0479135513305664, "global_step": 501060, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.070807933807373, "global_step": 501061, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.143409252166748, "global_step": 501062, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.031093120574951, "global_step": 501063, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0398266315460205, "global_step": 501064, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0579378604888916, "global_step": 501065, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.983792781829834, "global_step": 501066, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0854296684265137, "global_step": 501067, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.030117988586426, "global_step": 501068, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.008941650390625, "global_step": 501069, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0423929691314697, "global_step": 501070, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0472612380981445, "global_step": 501071, "epoch": 866, "lr": 5e-05}
{"train_loss": 1.978190302848816, "global_step": 501072, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.064521312713623, "global_step": 501073, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.102346897125244, "global_step": 501074, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1138486862182617, "global_step": 501075, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1031875610351562, "global_step": 501076, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0490574836730957, "global_step": 501077, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0051355361938477, "global_step": 501078, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0621883869171143, "global_step": 501079, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1460909843444824, "global_step": 501080, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1073098182678223, "global_step": 501081, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.109440565109253, "global_step": 501082, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.031761407852173, "global_step": 501083, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0401718616485596, "global_step": 501084, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.011763334274292, "global_step": 501085, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1040830612182617, "global_step": 501086, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0817840099334717, "global_step": 501087, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.066312313079834, "global_step": 501088, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0193371772766113, "global_step": 501089, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0963141918182373, "global_step": 501090, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.139233112335205, "global_step": 501091, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.02872633934021, "global_step": 501092, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.034214496612549, "global_step": 501093, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0117857456207275, "global_step": 501094, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.097154378890991, "global_step": 501095, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.062880277633667, "global_step": 501096, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.026534080505371, "global_step": 501097, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1345934867858887, "global_step": 501098, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.0601580142974854, "global_step": 501099, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.050264835357666, "global_step": 501100, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.1577093601226807, "global_step": 501101, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.096806526184082, "global_step": 501102, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.104149580001831, "global_step": 501103, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.088164806365967, "global_step": 501104, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.049180746078491, "global_step": 501105, "epoch": 866, "lr": 5e-05}
{"train_loss": 2.003443956375122, "global_step": 501106, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0986135005950928, "global_step": 501107, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.125014066696167, "global_step": 501108, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.037217140197754, "global_step": 501109, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.095757246017456, "global_step": 501110, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9492202997207642, "global_step": 501111, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.049027681350708, "global_step": 501112, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.061217784881592, "global_step": 501113, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.065661907196045, "global_step": 501114, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0838918685913086, "global_step": 501115, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1251060962677, "global_step": 501116, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.061284303665161, "global_step": 501117, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0086498260498047, "global_step": 501118, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.072033405303955, "global_step": 501119, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1573543548583984, "global_step": 501120, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0962789058685303, "global_step": 501121, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.111842155456543, "global_step": 501122, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9445984363555908, "global_step": 501123, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.031578779220581, "global_step": 501124, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9884666204452515, "global_step": 501125, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.129664421081543, "global_step": 501126, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0784242153167725, "global_step": 501127, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0950558185577393, "global_step": 501128, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0788209438323975, "global_step": 501129, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.068965196609497, "global_step": 501130, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1318747997283936, "global_step": 501131, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.026472568511963, "global_step": 501132, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0800344944000244, "global_step": 501133, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.070128917694092, "global_step": 501134, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9893460273742676, "global_step": 501135, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0196964740753174, "global_step": 501136, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.092388391494751, "global_step": 501137, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9996352195739746, "global_step": 501138, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0324161052703857, "global_step": 501139, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0441763401031494, "global_step": 501140, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1115286350250244, "global_step": 501141, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.017807722091675, "global_step": 501142, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0346784591674805, "global_step": 501143, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.028698444366455, "global_step": 501144, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.112182140350342, "global_step": 501145, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0291054248809814, "global_step": 501146, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.062262535095215, "global_step": 501147, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.974246621131897, "global_step": 501148, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.082592010498047, "global_step": 501149, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0684635639190674, "global_step": 501150, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0776028633117676, "global_step": 501151, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0663204193115234, "global_step": 501152, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.022184371948242, "global_step": 501153, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0385775566101074, "global_step": 501154, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.106935739517212, "global_step": 501155, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0492911338806152, "global_step": 501156, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.050083637237549, "global_step": 501157, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0787856578826904, "global_step": 501158, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9662995338439941, "global_step": 501159, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.034867286682129, "global_step": 501160, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0136678218841553, "global_step": 501161, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.03039288520813, "global_step": 501162, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.043402910232544, "global_step": 501163, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.018242120742798, "global_step": 501164, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0696866512298584, "global_step": 501165, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.027167797088623, "global_step": 501166, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0662431716918945, "global_step": 501167, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9953279495239258, "global_step": 501168, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0392277240753174, "global_step": 501169, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1218085289001465, "global_step": 501170, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.083458423614502, "global_step": 501171, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.053727388381958, "global_step": 501172, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.981604814529419, "global_step": 501173, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.002052068710327, "global_step": 501174, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0274994373321533, "global_step": 501175, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.003237724304199, "global_step": 501176, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0515215396881104, "global_step": 501177, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.064054250717163, "global_step": 501178, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9821809530258179, "global_step": 501179, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.993796944618225, "global_step": 501180, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0885281562805176, "global_step": 501181, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0322234630584717, "global_step": 501182, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0249757766723633, "global_step": 501183, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.073430061340332, "global_step": 501184, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0199897289276123, "global_step": 501185, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.104116201400757, "global_step": 501186, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0575811862945557, "global_step": 501187, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.017547369003296, "global_step": 501188, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0639967918395996, "global_step": 501189, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.041438579559326, "global_step": 501190, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9728899002075195, "global_step": 501191, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.007293939590454, "global_step": 501192, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.041098117828369, "global_step": 501193, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.089592456817627, "global_step": 501194, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0211617946624756, "global_step": 501195, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.052215576171875, "global_step": 501196, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.105890989303589, "global_step": 501197, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0804991722106934, "global_step": 501198, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9575318098068237, "global_step": 501199, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.044574499130249, "global_step": 501200, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9937405586242676, "global_step": 501201, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9685255289077759, "global_step": 501202, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.080653190612793, "global_step": 501203, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.036008596420288, "global_step": 501204, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0300140380859375, "global_step": 501205, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0343732833862305, "global_step": 501206, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1123673915863037, "global_step": 501207, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0541555881500244, "global_step": 501208, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.036149740219116, "global_step": 501209, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.042659044265747, "global_step": 501210, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.096531867980957, "global_step": 501211, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.988079309463501, "global_step": 501212, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0741028785705566, "global_step": 501213, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0584545135498047, "global_step": 501214, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9849835634231567, "global_step": 501215, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.014711618423462, "global_step": 501216, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0252187252044678, "global_step": 501217, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0708167552948, "global_step": 501218, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0465762615203857, "global_step": 501219, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9170080423355103, "global_step": 501220, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9789811372756958, "global_step": 501221, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0722854137420654, "global_step": 501222, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0175983905792236, "global_step": 501223, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.058706045150757, "global_step": 501224, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0055739879608154, "global_step": 501225, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9605298042297363, "global_step": 501226, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0767734050750732, "global_step": 501227, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.075249195098877, "global_step": 501228, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9907326698303223, "global_step": 501229, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.059443473815918, "global_step": 501230, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0188255310058594, "global_step": 501231, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.080322742462158, "global_step": 501232, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0239908695220947, "global_step": 501233, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9987820386886597, "global_step": 501234, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.024679183959961, "global_step": 501235, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0010340213775635, "global_step": 501236, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.073568820953369, "global_step": 501237, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0052125453948975, "global_step": 501238, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.031780958175659, "global_step": 501239, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0743649005889893, "global_step": 501240, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0513882637023926, "global_step": 501241, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0092217922210693, "global_step": 501242, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0387048721313477, "global_step": 501243, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.012990951538086, "global_step": 501244, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.074002504348755, "global_step": 501245, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0435538291931152, "global_step": 501246, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0893900394439697, "global_step": 501247, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0231425762176514, "global_step": 501248, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9652290344238281, "global_step": 501249, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.099456787109375, "global_step": 501250, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1057920455932617, "global_step": 501251, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.067570447921753, "global_step": 501252, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9986554384231567, "global_step": 501253, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0719616413116455, "global_step": 501254, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0818748474121094, "global_step": 501255, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.077415704727173, "global_step": 501256, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0162971019744873, "global_step": 501257, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1299192905426025, "global_step": 501258, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0278232097625732, "global_step": 501259, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9875942468643188, "global_step": 501260, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.06391978263855, "global_step": 501261, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.049086093902588, "global_step": 501262, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0450761318206787, "global_step": 501263, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.032735824584961, "global_step": 501264, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9916168451309204, "global_step": 501265, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1179771423339844, "global_step": 501266, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.024921417236328, "global_step": 501267, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.039865255355835, "global_step": 501268, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0427486896514893, "global_step": 501269, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9741061925888062, "global_step": 501270, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0224950313568115, "global_step": 501271, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0040762424468994, "global_step": 501272, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.98787260055542, "global_step": 501273, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.091280937194824, "global_step": 501274, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9464906454086304, "global_step": 501275, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.099302291870117, "global_step": 501276, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1161575317382812, "global_step": 501277, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0322377681732178, "global_step": 501278, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9656645059585571, "global_step": 501279, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0619473457336426, "global_step": 501280, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9678000211715698, "global_step": 501281, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0299627780914307, "global_step": 501282, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0911974906921387, "global_step": 501283, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.049635887145996, "global_step": 501284, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9563125371932983, "global_step": 501285, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.026343822479248, "global_step": 501286, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1380460262298584, "global_step": 501287, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.052793264389038, "global_step": 501288, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1432104110717773, "global_step": 501289, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.041529655456543, "global_step": 501290, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1532676219940186, "global_step": 501291, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.089473247528076, "global_step": 501292, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9581471681594849, "global_step": 501293, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.087756633758545, "global_step": 501294, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0021963119506836, "global_step": 501295, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0223541259765625, "global_step": 501296, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1004955768585205, "global_step": 501297, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0144333839416504, "global_step": 501298, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0602428913116455, "global_step": 501299, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0961267948150635, "global_step": 501300, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1230146884918213, "global_step": 501301, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.061598777770996, "global_step": 501302, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0839951038360596, "global_step": 501303, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.116213321685791, "global_step": 501304, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9869571924209595, "global_step": 501305, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0611014366149902, "global_step": 501306, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.058317184448242, "global_step": 501307, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.069080352783203, "global_step": 501308, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.077885866165161, "global_step": 501309, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0774853229522705, "global_step": 501310, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0500080585479736, "global_step": 501311, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0097835063934326, "global_step": 501312, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9689369201660156, "global_step": 501313, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.011540412902832, "global_step": 501314, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9845287799835205, "global_step": 501315, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.091492176055908, "global_step": 501316, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.056051731109619, "global_step": 501317, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.069185972213745, "global_step": 501318, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9938997030258179, "global_step": 501319, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9687689542770386, "global_step": 501320, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0003161430358887, "global_step": 501321, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0216474533081055, "global_step": 501322, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0320510864257812, "global_step": 501323, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0701491832733154, "global_step": 501324, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0208213329315186, "global_step": 501325, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.038980722427368, "global_step": 501326, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0212714672088623, "global_step": 501327, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.007483720779419, "global_step": 501328, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0513856410980225, "global_step": 501329, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9786250591278076, "global_step": 501330, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.077949285507202, "global_step": 501331, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1747894287109375, "global_step": 501332, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.057729721069336, "global_step": 501333, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.056967258453369, "global_step": 501334, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1219918727874756, "global_step": 501335, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0757346153259277, "global_step": 501336, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9853564500808716, "global_step": 501337, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.068373680114746, "global_step": 501338, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.048485040664673, "global_step": 501339, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0283865928649902, "global_step": 501340, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0550003051757812, "global_step": 501341, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.096806526184082, "global_step": 501342, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0598514080047607, "global_step": 501343, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.06760311126709, "global_step": 501344, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0878443717956543, "global_step": 501345, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.130060911178589, "global_step": 501346, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1380817890167236, "global_step": 501347, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.013277769088745, "global_step": 501348, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0436017513275146, "global_step": 501349, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0469517707824707, "global_step": 501350, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0258073806762695, "global_step": 501351, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0661354064941406, "global_step": 501352, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.054081439971924, "global_step": 501353, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.043386697769165, "global_step": 501354, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1623010635375977, "global_step": 501355, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.01971435546875, "global_step": 501356, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.091703414916992, "global_step": 501357, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0319814682006836, "global_step": 501358, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0968048572540283, "global_step": 501359, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9950675964355469, "global_step": 501360, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0150156021118164, "global_step": 501361, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0791661739349365, "global_step": 501362, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0050909519195557, "global_step": 501363, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0382583141326904, "global_step": 501364, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0740790367126465, "global_step": 501365, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0337860584259033, "global_step": 501366, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9013978242874146, "global_step": 501367, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0348668098449707, "global_step": 501368, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1098406314849854, "global_step": 501369, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.095977544784546, "global_step": 501370, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.037550926208496, "global_step": 501371, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0344574451446533, "global_step": 501372, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.04768705368042, "global_step": 501373, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1070709228515625, "global_step": 501374, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.076117753982544, "global_step": 501375, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.032871961593628, "global_step": 501376, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0852086544036865, "global_step": 501377, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.176260471343994, "global_step": 501378, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9735229015350342, "global_step": 501379, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.144757032394409, "global_step": 501380, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.016230583190918, "global_step": 501381, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0921835899353027, "global_step": 501382, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.06904935836792, "global_step": 501383, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0349645614624023, "global_step": 501384, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0514743328094482, "global_step": 501385, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.95671546459198, "global_step": 501386, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.070756435394287, "global_step": 501387, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0732779502868652, "global_step": 501388, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0720674991607666, "global_step": 501389, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0295891761779785, "global_step": 501390, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0320868492126465, "global_step": 501391, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0293779373168945, "global_step": 501392, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.030460834503174, "global_step": 501393, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.001946449279785, "global_step": 501394, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0775136947631836, "global_step": 501395, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0286993980407715, "global_step": 501396, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.016951322555542, "global_step": 501397, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0907957553863525, "global_step": 501398, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0925304889678955, "global_step": 501399, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9900871515274048, "global_step": 501400, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.008502244949341, "global_step": 501401, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0896427631378174, "global_step": 501402, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9873853921890259, "global_step": 501403, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0731990337371826, "global_step": 501404, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.116971015930176, "global_step": 501405, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0705032348632812, "global_step": 501406, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9324069023132324, "global_step": 501407, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0969903469085693, "global_step": 501408, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0210177898406982, "global_step": 501409, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.079632043838501, "global_step": 501410, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.066098928451538, "global_step": 501411, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9494893550872803, "global_step": 501412, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0333385467529297, "global_step": 501413, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.062875270843506, "global_step": 501414, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0022199153900146, "global_step": 501415, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9806241989135742, "global_step": 501416, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.076772451400757, "global_step": 501417, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9315035343170166, "global_step": 501418, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1315364837646484, "global_step": 501419, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.099574565887451, "global_step": 501420, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0702781677246094, "global_step": 501421, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9988266229629517, "global_step": 501422, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.065335512161255, "global_step": 501423, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9807524681091309, "global_step": 501424, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0543153285980225, "global_step": 501425, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.110590696334839, "global_step": 501426, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1552577018737793, "global_step": 501427, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0469987392425537, "global_step": 501428, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0834357738494873, "global_step": 501429, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.034926652908325, "global_step": 501430, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0755040645599365, "global_step": 501431, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0557234287261963, "global_step": 501432, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9778128862380981, "global_step": 501433, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1373963356018066, "global_step": 501434, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0225133895874023, "global_step": 501435, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.029240608215332, "global_step": 501436, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1206865310668945, "global_step": 501437, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9792420864105225, "global_step": 501438, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9939860105514526, "global_step": 501439, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0150504112243652, "global_step": 501440, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0824437141418457, "global_step": 501441, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1909961700439453, "global_step": 501442, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9952201843261719, "global_step": 501443, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0024304389953613, "global_step": 501444, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.123856782913208, "global_step": 501445, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1032121181488037, "global_step": 501446, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0842859745025635, "global_step": 501447, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0771090984344482, "global_step": 501448, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0836992263793945, "global_step": 501449, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0765907764434814, "global_step": 501450, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.042665958404541, "global_step": 501451, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.082073211669922, "global_step": 501452, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1507441997528076, "global_step": 501453, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.069962978363037, "global_step": 501454, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.020570755004883, "global_step": 501455, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1215403079986572, "global_step": 501456, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9732061624526978, "global_step": 501457, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0330216884613037, "global_step": 501458, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1621475219726562, "global_step": 501459, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.02014422416687, "global_step": 501460, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0039899349212646, "global_step": 501461, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0743508338928223, "global_step": 501462, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1127309799194336, "global_step": 501463, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0853192806243896, "global_step": 501464, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1244847774505615, "global_step": 501465, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0123448371887207, "global_step": 501466, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.075594663619995, "global_step": 501467, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9687004089355469, "global_step": 501468, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.005331516265869, "global_step": 501469, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.941795825958252, "global_step": 501470, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.036163330078125, "global_step": 501471, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.06791353225708, "global_step": 501472, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9992941617965698, "global_step": 501473, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.037893772125244, "global_step": 501474, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9998465776443481, "global_step": 501475, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0124149322509766, "global_step": 501476, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0322697162628174, "global_step": 501477, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.00038743019104, "global_step": 501478, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0906128883361816, "global_step": 501479, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0636115074157715, "global_step": 501480, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.124019145965576, "global_step": 501481, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0997345447540283, "global_step": 501482, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.120129346847534, "global_step": 501483, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0096185207366943, "global_step": 501484, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0639500617980957, "global_step": 501485, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0305862426757812, "global_step": 501486, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.045215368270874, "global_step": 501487, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.035027503967285, "global_step": 501488, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9348505735397339, "global_step": 501489, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9674429893493652, "global_step": 501490, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.008512496948242, "global_step": 501491, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1398468017578125, "global_step": 501492, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0173254013061523, "global_step": 501493, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.114370346069336, "global_step": 501494, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1141467094421387, "global_step": 501495, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1299259662628174, "global_step": 501496, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.066946506500244, "global_step": 501497, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.074681282043457, "global_step": 501498, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9848421812057495, "global_step": 501499, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1129987239837646, "global_step": 501500, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.115529775619507, "global_step": 501501, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0198512077331543, "global_step": 501502, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0846571922302246, "global_step": 501503, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9598078727722168, "global_step": 501504, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.144335985183716, "global_step": 501505, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.064729690551758, "global_step": 501506, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9258970022201538, "global_step": 501507, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0272164344787598, "global_step": 501508, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9895309209823608, "global_step": 501509, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0276496410369873, "global_step": 501510, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1292378902435303, "global_step": 501511, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.052595853805542, "global_step": 501512, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9476698637008667, "global_step": 501513, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0769219398498535, "global_step": 501514, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0642783641815186, "global_step": 501515, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.052060127258301, "global_step": 501516, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0224218368530273, "global_step": 501517, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.022465944290161, "global_step": 501518, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.06471586227417, "global_step": 501519, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.074039936065674, "global_step": 501520, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.143422842025757, "global_step": 501521, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0354197025299072, "global_step": 501522, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.090987205505371, "global_step": 501523, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.075939178466797, "global_step": 501524, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0919926166534424, "global_step": 501525, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9516663551330566, "global_step": 501526, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0385758876800537, "global_step": 501527, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.956380009651184, "global_step": 501528, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0772480964660645, "global_step": 501529, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0443975925445557, "global_step": 501530, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.077509641647339, "global_step": 501531, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0578525066375732, "global_step": 501532, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.087829113006592, "global_step": 501533, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9919006824493408, "global_step": 501534, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.034764289855957, "global_step": 501535, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.07677960395813, "global_step": 501536, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.164879083633423, "global_step": 501537, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0982420444488525, "global_step": 501538, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0957987308502197, "global_step": 501539, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.050191640853882, "global_step": 501540, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.050234317779541, "global_step": 501541, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.016307830810547, "global_step": 501542, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.981812834739685, "global_step": 501543, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9492768049240112, "global_step": 501544, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9777629375457764, "global_step": 501545, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.15970778465271, "global_step": 501546, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.11696720123291, "global_step": 501547, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1250805854797363, "global_step": 501548, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0257227420806885, "global_step": 501549, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0798513889312744, "global_step": 501550, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.027034282684326, "global_step": 501551, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.055574893951416, "global_step": 501552, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9874682426452637, "global_step": 501553, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.018803358078003, "global_step": 501554, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.031376838684082, "global_step": 501555, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0346317291259766, "global_step": 501556, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.084038257598877, "global_step": 501557, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1453449726104736, "global_step": 501558, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9754339456558228, "global_step": 501559, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.044548273086548, "global_step": 501560, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9803215265274048, "global_step": 501561, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9880807399749756, "global_step": 501562, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.029308795928955, "global_step": 501563, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.105323076248169, "global_step": 501564, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0529632568359375, "global_step": 501565, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.041508913040161, "global_step": 501566, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.062439441680908, "global_step": 501567, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9648953676223755, "global_step": 501568, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1249873638153076, "global_step": 501569, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.002509355545044, "global_step": 501570, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.039421796798706, "global_step": 501571, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.988756775856018, "global_step": 501572, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0467939376831055, "global_step": 501573, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0411369800567627, "global_step": 501574, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9923545122146606, "global_step": 501575, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.931262493133545, "global_step": 501576, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0573837757110596, "global_step": 501577, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0417799949645996, "global_step": 501578, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0651745796203613, "global_step": 501579, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0269789695739746, "global_step": 501580, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0219085216522217, "global_step": 501581, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0919322967529297, "global_step": 501582, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0591039657592773, "global_step": 501583, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.985571026802063, "global_step": 501584, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.08384370803833, "global_step": 501585, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9359091520309448, "global_step": 501586, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1004292964935303, "global_step": 501587, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0034875869750977, "global_step": 501588, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.012817621231079, "global_step": 501589, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.056321144104004, "global_step": 501590, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1271605491638184, "global_step": 501591, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0695412158966064, "global_step": 501592, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0033228397369385, "global_step": 501593, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0610644817352295, "global_step": 501594, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.025050401687622, "global_step": 501595, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0663464069366455, "global_step": 501596, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.092210531234741, "global_step": 501597, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0142128467559814, "global_step": 501598, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0235612392425537, "global_step": 501599, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0112459659576416, "global_step": 501600, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0539755821228027, "global_step": 501601, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.027526378631592, "global_step": 501602, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1188066005706787, "global_step": 501603, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.107919692993164, "global_step": 501604, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.108903646469116, "global_step": 501605, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.091252088546753, "global_step": 501606, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0329620838165283, "global_step": 501607, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9882928133010864, "global_step": 501608, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0759894847869873, "global_step": 501609, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0277693271636963, "global_step": 501610, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.089466094970703, "global_step": 501611, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0996832847595215, "global_step": 501612, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.080228567123413, "global_step": 501613, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9933866262435913, "global_step": 501614, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1351478099823, "global_step": 501615, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0325732231140137, "global_step": 501616, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1459193229675293, "global_step": 501617, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0220742225646973, "global_step": 501618, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.005218029022217, "global_step": 501619, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0792012214660645, "global_step": 501620, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0430002212524414, "global_step": 501621, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0923378467559814, "global_step": 501622, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.142681121826172, "global_step": 501623, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.984118103981018, "global_step": 501624, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0885446071624756, "global_step": 501625, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.081585645675659, "global_step": 501626, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0457043647766113, "global_step": 501627, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.97367262840271, "global_step": 501628, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0642216205596924, "global_step": 501629, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0470187664031982, "global_step": 501630, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.117243528366089, "global_step": 501631, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0192172527313232, "global_step": 501632, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.02522611618042, "global_step": 501633, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0968236923217773, "global_step": 501634, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0483920574188232, "global_step": 501635, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0718564987182617, "global_step": 501636, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1145846843719482, "global_step": 501637, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.997713327407837, "global_step": 501638, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0981457233428955, "global_step": 501639, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.949784755706787, "global_step": 501640, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0844614505767822, "global_step": 501641, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.193721294403076, "global_step": 501642, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1459836959838867, "global_step": 501643, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0242934226989746, "global_step": 501644, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.023871898651123, "global_step": 501645, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.087801456451416, "global_step": 501646, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.067307233810425, "global_step": 501647, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.028125524520874, "global_step": 501648, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.008715867996216, "global_step": 501649, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.122668981552124, "global_step": 501650, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9986538887023926, "global_step": 501651, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.021050214767456, "global_step": 501652, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.131187915802002, "global_step": 501653, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0349528789520264, "global_step": 501654, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0838003158569336, "global_step": 501655, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0824806690216064, "global_step": 501656, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.045214891433716, "global_step": 501657, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0175087451934814, "global_step": 501658, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0534677505493164, "global_step": 501659, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.044374942779541, "global_step": 501660, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.062356472015381, "global_step": 501661, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.974714756011963, "global_step": 501662, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0579710006713867, "global_step": 501663, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.151913642883301, "global_step": 501664, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.092996120452881, "global_step": 501665, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.042417526245117, "global_step": 501666, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.019333600997925, "global_step": 501667, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.008821487426758, "global_step": 501668, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.901850700378418, "global_step": 501669, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0219926834106445, "global_step": 501670, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.158115863800049, "global_step": 501671, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.077340841293335, "global_step": 501672, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1557300090789795, "global_step": 501673, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0544137954711914, "global_step": 501674, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1015448570251465, "global_step": 501675, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1349594593048096, "global_step": 501676, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.045767307281494, "global_step": 501677, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.052475690841675, "global_step": 501678, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.107218027114868, "global_step": 501679, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.060352325439453, "global_step": 501680, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.090306282043457, "global_step": 501681, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9976921081542969, "global_step": 501682, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.082805633544922, "global_step": 501683, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.059365749359131, "global_step": 501684, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.00055193901062, "global_step": 501685, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.071287155151367, "global_step": 501686, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0317585468292236, "global_step": 501687, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0725486278533936, "global_step": 501688, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.11680269241333, "global_step": 501689, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1025807857513428, "global_step": 501690, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.048795461654663, "global_step": 501691, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0422942638397217, "global_step": 501692, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.124206304550171, "global_step": 501693, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1595449447631836, "global_step": 501694, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.980479121208191, "global_step": 501695, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0737195014953613, "global_step": 501696, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1418063640594482, "global_step": 501697, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.045982599258423, "global_step": 501698, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1620213985443115, "global_step": 501699, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1157259941101074, "global_step": 501700, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9796762466430664, "global_step": 501701, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.055305004119873, "global_step": 501702, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.088975667953491, "global_step": 501703, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.012836217880249, "global_step": 501704, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.022444486618042, "global_step": 501705, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0297858715057373, "global_step": 501706, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9921633005142212, "global_step": 501707, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0537710189819336, "global_step": 501708, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.071279525756836, "global_step": 501709, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.056614398956299, "global_step": 501710, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.058943748474121, "global_step": 501711, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0734968185424805, "global_step": 501712, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1314148902893066, "global_step": 501713, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0655455589294434, "global_step": 501714, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.109888792037964, "global_step": 501715, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.075058698654175, "global_step": 501716, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0942509174346924, "global_step": 501717, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.051327705383301, "global_step": 501718, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9934155941009521, "global_step": 501719, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.039273977279663, "global_step": 501720, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.129365921020508, "global_step": 501721, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0661141872406006, "global_step": 501722, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0125412940979004, "global_step": 501723, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.097623586654663, "global_step": 501724, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.067756175994873, "global_step": 501725, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0546936988830566, "global_step": 501726, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9489399194717407, "global_step": 501727, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1127734184265137, "global_step": 501728, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9154762029647827, "global_step": 501729, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0458600521087646, "global_step": 501730, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0810415744781494, "global_step": 501731, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.985097885131836, "global_step": 501732, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.079166889190674, "global_step": 501733, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.088254928588867, "global_step": 501734, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.071960687637329, "global_step": 501735, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0904810428619385, "global_step": 501736, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0224721431732178, "global_step": 501737, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0120229721069336, "global_step": 501738, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0994019508361816, "global_step": 501739, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.064621686935425, "global_step": 501740, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9717482328414917, "global_step": 501741, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0669350624084473, "global_step": 501742, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9787707328796387, "global_step": 501743, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9278779029846191, "global_step": 501744, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9498915672302246, "global_step": 501745, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0418097972869873, "global_step": 501746, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.006423234939575, "global_step": 501747, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0974154472351074, "global_step": 501748, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.053354501724243, "global_step": 501749, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9789327383041382, "global_step": 501750, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.083251953125, "global_step": 501751, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.012204647064209, "global_step": 501752, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0823862552642822, "global_step": 501753, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.056239366531372, "global_step": 501754, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0909276008605957, "global_step": 501755, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.043323040008545, "global_step": 501756, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.062774658203125, "global_step": 501757, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9288803339004517, "global_step": 501758, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0594494342803955, "global_step": 501759, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.059281349182129, "global_step": 501760, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.024794578552246, "global_step": 501761, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9681528806686401, "global_step": 501762, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.93110990524292, "global_step": 501763, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.974786400794983, "global_step": 501764, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.014227867126465, "global_step": 501765, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.04116153717041, "global_step": 501766, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0720157623291016, "global_step": 501767, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0442919731140137, "global_step": 501768, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.110323429107666, "global_step": 501769, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1596977710723877, "global_step": 501770, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.022001266479492, "global_step": 501771, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0545122623443604, "global_step": 501772, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0875930786132812, "global_step": 501773, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0509040355682373, "global_step": 501774, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.032334327697754, "global_step": 501775, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.072845935821533, "global_step": 501776, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0670838356018066, "global_step": 501777, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.101130723953247, "global_step": 501778, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0841660499572754, "global_step": 501779, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9990346431732178, "global_step": 501780, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0681138038635254, "global_step": 501781, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0071396827697754, "global_step": 501782, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0637924671173096, "global_step": 501783, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0836727619171143, "global_step": 501784, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.208589792251587, "global_step": 501785, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.063774585723877, "global_step": 501786, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0549514293670654, "global_step": 501787, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.041802406311035, "global_step": 501788, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.135160207748413, "global_step": 501789, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1053929328918457, "global_step": 501790, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.994475245475769, "global_step": 501791, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0795538425445557, "global_step": 501792, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.039376974105835, "global_step": 501793, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1063570976257324, "global_step": 501794, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1182548999786377, "global_step": 501795, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0538463592529297, "global_step": 501796, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.027606725692749, "global_step": 501797, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0506832599639893, "global_step": 501798, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0426061153411865, "global_step": 501799, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0725533962249756, "global_step": 501800, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0448200702667236, "global_step": 501801, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0807406902313232, "global_step": 501802, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0403425693511963, "global_step": 501803, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0018959045410156, "global_step": 501804, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.988022804260254, "global_step": 501805, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0142221450805664, "global_step": 501806, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0790977478027344, "global_step": 501807, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1386044025421143, "global_step": 501808, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0797207355499268, "global_step": 501809, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.105733871459961, "global_step": 501810, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.176565647125244, "global_step": 501811, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0040619373321533, "global_step": 501812, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.046647548675537, "global_step": 501813, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.992142677307129, "global_step": 501814, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.062380313873291, "global_step": 501815, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0392773151397705, "global_step": 501816, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0720608234405518, "global_step": 501817, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.012144088745117, "global_step": 501818, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0484588146209717, "global_step": 501819, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.029082775115967, "global_step": 501820, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0073158740997314, "global_step": 501821, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.056659698486328, "global_step": 501822, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0257036685943604, "global_step": 501823, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.050147533416748, "global_step": 501824, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.103555202484131, "global_step": 501825, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0384695529937744, "global_step": 501826, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.03544545173645, "global_step": 501827, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.019195079803467, "global_step": 501828, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.037724494934082, "global_step": 501829, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0136444568634033, "global_step": 501830, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.080374240875244, "global_step": 501831, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0122568607330322, "global_step": 501832, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.080449342727661, "global_step": 501833, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9972624778747559, "global_step": 501834, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.170488119125366, "global_step": 501835, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0821139812469482, "global_step": 501836, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.143033742904663, "global_step": 501837, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0438072681427, "global_step": 501838, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.125493049621582, "global_step": 501839, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1546664237976074, "global_step": 501840, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0057461261749268, "global_step": 501841, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9807766675949097, "global_step": 501842, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.055877208709717, "global_step": 501843, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0298376083374023, "global_step": 501844, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.146578311920166, "global_step": 501845, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0573387145996094, "global_step": 501846, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.089470863342285, "global_step": 501847, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.056955575942993, "global_step": 501848, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.048271417617798, "global_step": 501849, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0592381954193115, "global_step": 501850, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.992314338684082, "global_step": 501851, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0899131298065186, "global_step": 501852, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9797619581222534, "global_step": 501853, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.950895071029663, "global_step": 501854, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.087512254714966, "global_step": 501855, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.086988687515259, "global_step": 501856, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.069444179534912, "global_step": 501857, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.045515537261963, "global_step": 501858, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0933265686035156, "global_step": 501859, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0287227630615234, "global_step": 501860, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0350279808044434, "global_step": 501861, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.033623695373535, "global_step": 501862, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0361194610595703, "global_step": 501863, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0788052082061768, "global_step": 501864, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1458218097686768, "global_step": 501865, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.95768141746521, "global_step": 501866, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1343932151794434, "global_step": 501867, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0047645568847656, "global_step": 501868, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.966579556465149, "global_step": 501869, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0680575370788574, "global_step": 501870, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0845842361450195, "global_step": 501871, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0309062004089355, "global_step": 501872, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1488869190216064, "global_step": 501873, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.067805528640747, "global_step": 501874, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.129561424255371, "global_step": 501875, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0023224353790283, "global_step": 501876, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0537917613983154, "global_step": 501877, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.020846128463745, "global_step": 501878, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.135629415512085, "global_step": 501879, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0267884731292725, "global_step": 501880, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.100876808166504, "global_step": 501881, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0699076652526855, "global_step": 501882, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.045874834060669, "global_step": 501883, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.013442039489746, "global_step": 501884, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0904719829559326, "global_step": 501885, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0465023517608643, "global_step": 501886, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.112136125564575, "global_step": 501887, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1611719131469727, "global_step": 501888, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1373844146728516, "global_step": 501889, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.2174429893493652, "global_step": 501890, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.060586452484131, "global_step": 501891, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.010162353515625, "global_step": 501892, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.010679244995117, "global_step": 501893, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9862333536148071, "global_step": 501894, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.058781623840332, "global_step": 501895, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9393686056137085, "global_step": 501896, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0684869289398193, "global_step": 501897, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9569730758666992, "global_step": 501898, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.075510263442993, "global_step": 501899, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.068815231323242, "global_step": 501900, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1262307167053223, "global_step": 501901, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1043925285339355, "global_step": 501902, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.030050039291382, "global_step": 501903, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.062972068786621, "global_step": 501904, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0729780197143555, "global_step": 501905, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.074185848236084, "global_step": 501906, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.040933847427368, "global_step": 501907, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9681003093719482, "global_step": 501908, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.037946939468384, "global_step": 501909, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0102415084838867, "global_step": 501910, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0561604499816895, "global_step": 501911, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.114938735961914, "global_step": 501912, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.040804862976074, "global_step": 501913, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.04585337638855, "global_step": 501914, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.021796226501465, "global_step": 501915, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.986452579498291, "global_step": 501916, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0501389503479004, "global_step": 501917, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0230653285980225, "global_step": 501918, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.083545207977295, "global_step": 501919, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0854923725128174, "global_step": 501920, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.06378436088562, "global_step": 501921, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.061904191970825, "global_step": 501922, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.036529064178467, "global_step": 501923, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0095458030700684, "global_step": 501924, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.124537944793701, "global_step": 501925, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1034798622131348, "global_step": 501926, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.076709747314453, "global_step": 501927, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0674052238464355, "global_step": 501928, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9976156949996948, "global_step": 501929, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.07856822013855, "global_step": 501930, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0452933311462402, "global_step": 501931, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0345475673675537, "global_step": 501932, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.058444023132324, "global_step": 501933, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0266382694244385, "global_step": 501934, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0804526805877686, "global_step": 501935, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.189628839492798, "global_step": 501936, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0475642681121826, "global_step": 501937, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0524649620056152, "global_step": 501938, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9777841567993164, "global_step": 501939, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0508453845977783, "global_step": 501940, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.198110818862915, "global_step": 501941, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.063849925994873, "global_step": 501942, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1008639335632324, "global_step": 501943, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0372378826141357, "global_step": 501944, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.005692720413208, "global_step": 501945, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9922435283660889, "global_step": 501946, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0396323204040527, "global_step": 501947, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.014172315597534, "global_step": 501948, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.998844861984253, "global_step": 501949, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0393660068511963, "global_step": 501950, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0216732025146484, "global_step": 501951, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0997533798217773, "global_step": 501952, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.130890369415283, "global_step": 501953, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0367188453674316, "global_step": 501954, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0724434852600098, "global_step": 501955, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1974360942840576, "global_step": 501956, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0965523719787598, "global_step": 501957, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0747594833374023, "global_step": 501958, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.046048402786255, "global_step": 501959, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0125584602355957, "global_step": 501960, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.115001916885376, "global_step": 501961, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0848262310028076, "global_step": 501962, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.081894636154175, "global_step": 501963, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.078967571258545, "global_step": 501964, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.110989809036255, "global_step": 501965, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9926270246505737, "global_step": 501966, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0646567344665527, "global_step": 501967, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0719964504241943, "global_step": 501968, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.150618314743042, "global_step": 501969, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0707621574401855, "global_step": 501970, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0441665649414062, "global_step": 501971, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.030200242996216, "global_step": 501972, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0915024280548096, "global_step": 501973, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.001354217529297, "global_step": 501974, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0872161388397217, "global_step": 501975, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0543551445007324, "global_step": 501976, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9111886024475098, "global_step": 501977, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0619583129882812, "global_step": 501978, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0308315753936768, "global_step": 501979, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.146491765975952, "global_step": 501980, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0616226196289062, "global_step": 501981, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0550496578216553, "global_step": 501982, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.034311532974243, "global_step": 501983, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9989811182022095, "global_step": 501984, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0721631050109863, "global_step": 501985, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.018298387527466, "global_step": 501986, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0940840244293213, "global_step": 501987, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.084409475326538, "global_step": 501988, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0175724029541016, "global_step": 501989, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9394683837890625, "global_step": 501990, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0482795238494873, "global_step": 501991, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.999280333518982, "global_step": 501992, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.04703950881958, "global_step": 501993, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0234601497650146, "global_step": 501994, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0390069484710693, "global_step": 501995, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9551204442977905, "global_step": 501996, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.063649892807007, "global_step": 501997, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1016223430633545, "global_step": 501998, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0717151165008545, "global_step": 501999, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0882952213287354, "global_step": 502000, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0769424438476562, "global_step": 502001, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.054062604904175, "global_step": 502002, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0246825218200684, "global_step": 502003, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0083489418029785, "global_step": 502004, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0400264263153076, "global_step": 502005, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.069932460784912, "global_step": 502006, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.085543155670166, "global_step": 502007, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.021080732345581, "global_step": 502008, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.052990436553955, "global_step": 502009, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0541040897369385, "global_step": 502010, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.102597236633301, "global_step": 502011, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1436779499053955, "global_step": 502012, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0296480655670166, "global_step": 502013, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0588326454162598, "global_step": 502014, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.072087526321411, "global_step": 502015, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.086216688156128, "global_step": 502016, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.133378505706787, "global_step": 502017, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0924856662750244, "global_step": 502018, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0094454288482666, "global_step": 502019, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.063434600830078, "global_step": 502020, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0221967697143555, "global_step": 502021, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0694377422332764, "global_step": 502022, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1584436893463135, "global_step": 502023, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1640703678131104, "global_step": 502024, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.996565341949463, "global_step": 502025, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9637112617492676, "global_step": 502026, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9356341361999512, "global_step": 502027, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0880839824676514, "global_step": 502028, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0986413955688477, "global_step": 502029, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.034121036529541, "global_step": 502030, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0163094997406006, "global_step": 502031, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0373611450195312, "global_step": 502032, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0258681774139404, "global_step": 502033, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0378808975219727, "global_step": 502034, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0365090370178223, "global_step": 502035, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0188565254211426, "global_step": 502036, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1394882202148438, "global_step": 502037, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9384385347366333, "global_step": 502038, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0676326751708984, "global_step": 502039, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0374906063079834, "global_step": 502040, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0437450408935547, "global_step": 502041, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.103581190109253, "global_step": 502042, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.010685682296753, "global_step": 502043, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.030087947845459, "global_step": 502044, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.064882516860962, "global_step": 502045, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.077643871307373, "global_step": 502046, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0911436080932617, "global_step": 502047, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0396547317504883, "global_step": 502048, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1243600845336914, "global_step": 502049, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0277554988861084, "global_step": 502050, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.112677812576294, "global_step": 502051, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0028200149536133, "global_step": 502052, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0084426403045654, "global_step": 502053, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9736443758010864, "global_step": 502054, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.085232734680176, "global_step": 502055, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.117300271987915, "global_step": 502056, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.138392210006714, "global_step": 502057, "epoch": 867, "lr": 5e-05}
{"train_loss": 1.9725180864334106, "global_step": 502058, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0439155101776123, "global_step": 502059, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0386271476745605, "global_step": 502060, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.043631076812744, "global_step": 502061, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.033806562423706, "global_step": 502062, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0016536712646484, "global_step": 502063, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.079538583755493, "global_step": 502064, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.055874824523926, "global_step": 502065, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0477609634399414, "global_step": 502066, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0013248920440674, "global_step": 502067, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.123232126235962, "global_step": 502068, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.069504499435425, "global_step": 502069, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0366413593292236, "global_step": 502070, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.1032326221466064, "global_step": 502071, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.172142744064331, "global_step": 502072, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.087628126144409, "global_step": 502073, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.0521013736724854, "global_step": 502074, "epoch": 867, "lr": 5e-05}
{"train_loss": 2.000743865966797, "global_step": 502075, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.067366600036621, "global_step": 502076, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.08735990524292, "global_step": 502077, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1451897621154785, "global_step": 502078, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0229921340942383, "global_step": 502079, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.040497064590454, "global_step": 502080, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.050736427307129, "global_step": 502081, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.015817403793335, "global_step": 502082, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.016822338104248, "global_step": 502083, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9994913339614868, "global_step": 502084, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0479955673217773, "global_step": 502085, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.034728765487671, "global_step": 502086, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9967209100723267, "global_step": 502087, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.980022668838501, "global_step": 502088, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.115788459777832, "global_step": 502089, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.035621166229248, "global_step": 502090, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1042089462280273, "global_step": 502091, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.04286527633667, "global_step": 502092, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.020000696182251, "global_step": 502093, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9537293910980225, "global_step": 502094, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0292248725891113, "global_step": 502095, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9766309261322021, "global_step": 502096, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9757053852081299, "global_step": 502097, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.988814353942871, "global_step": 502098, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9879918098449707, "global_step": 502099, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.021679639816284, "global_step": 502100, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.059450387954712, "global_step": 502101, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.024078845977783, "global_step": 502102, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0011820793151855, "global_step": 502103, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0865249633789062, "global_step": 502104, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.019792079925537, "global_step": 502105, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.095889091491699, "global_step": 502106, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0577590465545654, "global_step": 502107, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.085059642791748, "global_step": 502108, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0313761234283447, "global_step": 502109, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.049255609512329, "global_step": 502110, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.046391010284424, "global_step": 502111, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0460853576660156, "global_step": 502112, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0248782634735107, "global_step": 502113, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0032711029052734, "global_step": 502114, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9925377368927002, "global_step": 502115, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0663180351257324, "global_step": 502116, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9754889011383057, "global_step": 502117, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0268428325653076, "global_step": 502118, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9727044105529785, "global_step": 502119, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9776825904846191, "global_step": 502120, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.06435227394104, "global_step": 502121, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0129566192626953, "global_step": 502122, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.007852792739868, "global_step": 502123, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.034966230392456, "global_step": 502124, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.064272165298462, "global_step": 502125, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.002066135406494, "global_step": 502126, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9987480640411377, "global_step": 502127, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0884978771209717, "global_step": 502128, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.02870774269104, "global_step": 502129, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0432932376861572, "global_step": 502130, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0500130653381348, "global_step": 502131, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0994865894317627, "global_step": 502132, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9581472873687744, "global_step": 502133, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0467748641967773, "global_step": 502134, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.102126359939575, "global_step": 502135, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0086913108825684, "global_step": 502136, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9403345584869385, "global_step": 502137, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.964345932006836, "global_step": 502138, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.064368963241577, "global_step": 502139, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0478694438934326, "global_step": 502140, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.068255662918091, "global_step": 502141, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9901139736175537, "global_step": 502142, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9482728242874146, "global_step": 502143, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0136141777038574, "global_step": 502144, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0367214679718018, "global_step": 502145, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0146484375, "global_step": 502146, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.066014051437378, "global_step": 502147, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9341692924499512, "global_step": 502148, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0578653812408447, "global_step": 502149, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.049074172973633, "global_step": 502150, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9579840898513794, "global_step": 502151, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0503785610198975, "global_step": 502152, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0391111373901367, "global_step": 502153, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0688633918762207, "global_step": 502154, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9596939086914062, "global_step": 502155, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.105656623840332, "global_step": 502156, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0263447761535645, "global_step": 502157, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0943851470947266, "global_step": 502158, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.133528232574463, "global_step": 502159, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.103379249572754, "global_step": 502160, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.021023750305176, "global_step": 502161, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0995306968688965, "global_step": 502162, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0701498985290527, "global_step": 502163, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0803921222686768, "global_step": 502164, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.980380654335022, "global_step": 502165, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9949575662612915, "global_step": 502166, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1068403720855713, "global_step": 502167, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9808460474014282, "global_step": 502168, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.980150580406189, "global_step": 502169, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0429327487945557, "global_step": 502170, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.080724000930786, "global_step": 502171, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0837152004241943, "global_step": 502172, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0488383769989014, "global_step": 502173, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0271267890930176, "global_step": 502174, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0703701972961426, "global_step": 502175, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0761966705322266, "global_step": 502176, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.020733594894409, "global_step": 502177, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0145726203918457, "global_step": 502178, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0507891178131104, "global_step": 502179, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1325979232788086, "global_step": 502180, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9445849657058716, "global_step": 502181, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0618269443511963, "global_step": 502182, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9856314659118652, "global_step": 502183, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0743274688720703, "global_step": 502184, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.071413516998291, "global_step": 502185, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0449957847595215, "global_step": 502186, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0462870597839355, "global_step": 502187, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0337891578674316, "global_step": 502188, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0160558223724365, "global_step": 502189, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.000641107559204, "global_step": 502190, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.082190990447998, "global_step": 502191, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0198099613189697, "global_step": 502192, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0352940559387207, "global_step": 502193, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0579893589019775, "global_step": 502194, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0845892429351807, "global_step": 502195, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.047224998474121, "global_step": 502196, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1040189266204834, "global_step": 502197, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0549142360687256, "global_step": 502198, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.131037712097168, "global_step": 502199, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0619611740112305, "global_step": 502200, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1111974716186523, "global_step": 502201, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9331026077270508, "global_step": 502202, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0206656455993652, "global_step": 502203, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0359318256378174, "global_step": 502204, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.983216643333435, "global_step": 502205, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.009716272354126, "global_step": 502206, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.029233694076538, "global_step": 502207, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.994031310081482, "global_step": 502208, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.965295672416687, "global_step": 502209, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.013167381286621, "global_step": 502210, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0534157752990723, "global_step": 502211, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.070418357849121, "global_step": 502212, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1101725101470947, "global_step": 502213, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0250680446624756, "global_step": 502214, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0099282264709473, "global_step": 502215, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0186524391174316, "global_step": 502216, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.182616710662842, "global_step": 502217, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9870240688323975, "global_step": 502218, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0168912410736084, "global_step": 502219, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0556132793426514, "global_step": 502220, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9884405136108398, "global_step": 502221, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.00632905960083, "global_step": 502222, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9843488931655884, "global_step": 502223, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.136586904525757, "global_step": 502224, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0992891788482666, "global_step": 502225, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0745961666107178, "global_step": 502226, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0643274784088135, "global_step": 502227, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.115237236022949, "global_step": 502228, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0668251514434814, "global_step": 502229, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0799577236175537, "global_step": 502230, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.004197835922241, "global_step": 502231, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0582292079925537, "global_step": 502232, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0021822452545166, "global_step": 502233, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0521504878997803, "global_step": 502234, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0075604915618896, "global_step": 502235, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0468175411224365, "global_step": 502236, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.051999568939209, "global_step": 502237, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9982150793075562, "global_step": 502238, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0871963500976562, "global_step": 502239, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.123204231262207, "global_step": 502240, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.014683246612549, "global_step": 502241, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9795113801956177, "global_step": 502242, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1845436096191406, "global_step": 502243, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.062929630279541, "global_step": 502244, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9987409114837646, "global_step": 502245, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.008852005004883, "global_step": 502246, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.099855422973633, "global_step": 502247, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0757992267608643, "global_step": 502248, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.958072543144226, "global_step": 502249, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0323243141174316, "global_step": 502250, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0659196376800537, "global_step": 502251, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0367493629455566, "global_step": 502252, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0430216789245605, "global_step": 502253, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.050306797027588, "global_step": 502254, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.015231132507324, "global_step": 502255, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.026554822921753, "global_step": 502256, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.120544195175171, "global_step": 502257, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0657355785369873, "global_step": 502258, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0793609619140625, "global_step": 502259, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9857043027877808, "global_step": 502260, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0090320110321045, "global_step": 502261, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.009767770767212, "global_step": 502262, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0815491676330566, "global_step": 502263, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.05444073677063, "global_step": 502264, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.048034191131592, "global_step": 502265, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0742039680480957, "global_step": 502266, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.104769229888916, "global_step": 502267, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.082773208618164, "global_step": 502268, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0087599754333496, "global_step": 502269, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9590356349945068, "global_step": 502270, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0896177291870117, "global_step": 502271, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.139469861984253, "global_step": 502272, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.062763214111328, "global_step": 502273, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0440711975097656, "global_step": 502274, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.006951332092285, "global_step": 502275, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.033435821533203, "global_step": 502276, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0437934398651123, "global_step": 502277, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0401771068573, "global_step": 502278, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.066504955291748, "global_step": 502279, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9532639980316162, "global_step": 502280, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9813711643218994, "global_step": 502281, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.949023723602295, "global_step": 502282, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0805394649505615, "global_step": 502283, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9101554155349731, "global_step": 502284, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0622620582580566, "global_step": 502285, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.022404909133911, "global_step": 502286, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1240057945251465, "global_step": 502287, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9881805181503296, "global_step": 502288, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.142073154449463, "global_step": 502289, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.056058406829834, "global_step": 502290, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.029031276702881, "global_step": 502291, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.083747386932373, "global_step": 502292, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.009446382522583, "global_step": 502293, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0322585105895996, "global_step": 502294, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0182440280914307, "global_step": 502295, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0863497257232666, "global_step": 502296, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.009084939956665, "global_step": 502297, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.054579496383667, "global_step": 502298, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.017822742462158, "global_step": 502299, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.014058828353882, "global_step": 502300, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0949103832244873, "global_step": 502301, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.053009510040283, "global_step": 502302, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.968581199645996, "global_step": 502303, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0516254901885986, "global_step": 502304, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.072356939315796, "global_step": 502305, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9976527690887451, "global_step": 502306, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0793449878692627, "global_step": 502307, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0639283657073975, "global_step": 502308, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9612559080123901, "global_step": 502309, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0491175651550293, "global_step": 502310, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.027350902557373, "global_step": 502311, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.039787769317627, "global_step": 502312, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.161893844604492, "global_step": 502313, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0173511505126953, "global_step": 502314, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0748209953308105, "global_step": 502315, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.025369644165039, "global_step": 502316, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.058187961578369, "global_step": 502317, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.018470525741577, "global_step": 502318, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.058375835418701, "global_step": 502319, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0791358947753906, "global_step": 502320, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0337188243865967, "global_step": 502321, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.078202962875366, "global_step": 502322, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0722081661224365, "global_step": 502323, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0702288150787354, "global_step": 502324, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0248355865478516, "global_step": 502325, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0566699504852295, "global_step": 502326, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0992066860198975, "global_step": 502327, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.030092477798462, "global_step": 502328, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.040672779083252, "global_step": 502329, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0936388969421387, "global_step": 502330, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0368640422821045, "global_step": 502331, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0608904361724854, "global_step": 502332, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0737380981445312, "global_step": 502333, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.085841655731201, "global_step": 502334, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9796587228775024, "global_step": 502335, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.122828722000122, "global_step": 502336, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.037079334259033, "global_step": 502337, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0276641845703125, "global_step": 502338, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.065819501876831, "global_step": 502339, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0504729747772217, "global_step": 502340, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.066830635070801, "global_step": 502341, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.078437089920044, "global_step": 502342, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0770785808563232, "global_step": 502343, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9828119277954102, "global_step": 502344, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.025930166244507, "global_step": 502345, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0882792472839355, "global_step": 502346, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.080371379852295, "global_step": 502347, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.030949115753174, "global_step": 502348, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.121805191040039, "global_step": 502349, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9623996019363403, "global_step": 502350, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0681092739105225, "global_step": 502351, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.091801881790161, "global_step": 502352, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.087001085281372, "global_step": 502353, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.074205160140991, "global_step": 502354, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.036975860595703, "global_step": 502355, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1027140617370605, "global_step": 502356, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0364699363708496, "global_step": 502357, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.059863328933716, "global_step": 502358, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0076873302459717, "global_step": 502359, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0237245559692383, "global_step": 502360, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0007705688476562, "global_step": 502361, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0373175144195557, "global_step": 502362, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0963525772094727, "global_step": 502363, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.063483953475952, "global_step": 502364, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.055408477783203, "global_step": 502365, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9776592254638672, "global_step": 502366, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.022242546081543, "global_step": 502367, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9885890483856201, "global_step": 502368, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.062631607055664, "global_step": 502369, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.078704357147217, "global_step": 502370, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0857632160186768, "global_step": 502371, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.988539457321167, "global_step": 502372, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.040205478668213, "global_step": 502373, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.023494243621826, "global_step": 502374, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0501043796539307, "global_step": 502375, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9955888986587524, "global_step": 502376, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0729031562805176, "global_step": 502377, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0888311862945557, "global_step": 502378, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9541560411453247, "global_step": 502379, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0101540088653564, "global_step": 502380, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.034644842147827, "global_step": 502381, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.081204652786255, "global_step": 502382, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0392448902130127, "global_step": 502383, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.010732650756836, "global_step": 502384, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.01585054397583, "global_step": 502385, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.078190803527832, "global_step": 502386, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.043017625808716, "global_step": 502387, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1072492599487305, "global_step": 502388, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.037336587905884, "global_step": 502389, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.036867618560791, "global_step": 502390, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.101702928543091, "global_step": 502391, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.091672897338867, "global_step": 502392, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.003079891204834, "global_step": 502393, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0175602436065674, "global_step": 502394, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.032102108001709, "global_step": 502395, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1173830032348633, "global_step": 502396, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.016977310180664, "global_step": 502397, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0659940242767334, "global_step": 502398, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.999079704284668, "global_step": 502399, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0418894290924072, "global_step": 502400, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0386886596679688, "global_step": 502401, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0154309272766113, "global_step": 502402, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0525426864624023, "global_step": 502403, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9419543743133545, "global_step": 502404, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0514919757843018, "global_step": 502405, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.96967351436615, "global_step": 502406, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0530474185943604, "global_step": 502407, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.06669282913208, "global_step": 502408, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0632011890411377, "global_step": 502409, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.019930601119995, "global_step": 502410, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.035724639892578, "global_step": 502411, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.088595151901245, "global_step": 502412, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0956497192382812, "global_step": 502413, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1120235919952393, "global_step": 502414, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0558056831359863, "global_step": 502415, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.08278489112854, "global_step": 502416, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1548824310302734, "global_step": 502417, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.100168228149414, "global_step": 502418, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.069093942642212, "global_step": 502419, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9797722101211548, "global_step": 502420, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.994754433631897, "global_step": 502421, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.038167715072632, "global_step": 502422, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0354437828063965, "global_step": 502423, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9916913509368896, "global_step": 502424, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1181440353393555, "global_step": 502425, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.047034978866577, "global_step": 502426, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0731279850006104, "global_step": 502427, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0516912937164307, "global_step": 502428, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.012268543243408, "global_step": 502429, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0340657234191895, "global_step": 502430, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0892274379730225, "global_step": 502431, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1559977531433105, "global_step": 502432, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.996201515197754, "global_step": 502433, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0729806423187256, "global_step": 502434, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.012820243835449, "global_step": 502435, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0120038986206055, "global_step": 502436, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9712026119232178, "global_step": 502437, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.089265823364258, "global_step": 502438, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.036872148513794, "global_step": 502439, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0393238067626953, "global_step": 502440, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0501463413238525, "global_step": 502441, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0280916690826416, "global_step": 502442, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0433130264282227, "global_step": 502443, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9954735040664673, "global_step": 502444, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.086348056793213, "global_step": 502445, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0152060985565186, "global_step": 502446, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9860070943832397, "global_step": 502447, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.071458101272583, "global_step": 502448, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.131864547729492, "global_step": 502449, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.032928466796875, "global_step": 502450, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.086962938308716, "global_step": 502451, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0274906158447266, "global_step": 502452, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0344436168670654, "global_step": 502453, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.095175266265869, "global_step": 502454, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.057710647583008, "global_step": 502455, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9957003593444824, "global_step": 502456, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9530388116836548, "global_step": 502457, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1159303188323975, "global_step": 502458, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.033254623413086, "global_step": 502459, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.030600070953369, "global_step": 502460, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.044126272201538, "global_step": 502461, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0521819591522217, "global_step": 502462, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.942167043685913, "global_step": 502463, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0549583435058594, "global_step": 502464, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.973712682723999, "global_step": 502465, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0518150329589844, "global_step": 502466, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0655839443206787, "global_step": 502467, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0178654193878174, "global_step": 502468, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.042725086212158, "global_step": 502469, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0630319118499756, "global_step": 502470, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.033342123031616, "global_step": 502471, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0458486080169678, "global_step": 502472, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0864222049713135, "global_step": 502473, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.005697011947632, "global_step": 502474, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.072333812713623, "global_step": 502475, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0249035358428955, "global_step": 502476, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.021942615509033, "global_step": 502477, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0615527629852295, "global_step": 502478, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.8890432119369507, "global_step": 502479, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0483765602111816, "global_step": 502480, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9824163913726807, "global_step": 502481, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.05666446685791, "global_step": 502482, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.074324131011963, "global_step": 502483, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9874591827392578, "global_step": 502484, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0858709812164307, "global_step": 502485, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.106527805328369, "global_step": 502486, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0546586513519287, "global_step": 502487, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0738167762756348, "global_step": 502488, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0166759490966797, "global_step": 502489, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0234477519989014, "global_step": 502490, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.079406499862671, "global_step": 502491, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0021140575408936, "global_step": 502492, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0786046981811523, "global_step": 502493, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.004795789718628, "global_step": 502494, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0609793663024902, "global_step": 502495, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.004732847213745, "global_step": 502496, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0978493690490723, "global_step": 502497, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1058287620544434, "global_step": 502498, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.092158555984497, "global_step": 502499, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.003359794616699, "global_step": 502500, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.049290657043457, "global_step": 502501, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.992066740989685, "global_step": 502502, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0687081813812256, "global_step": 502503, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1569619178771973, "global_step": 502504, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.032179355621338, "global_step": 502505, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0197348594665527, "global_step": 502506, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.168147563934326, "global_step": 502507, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.115502119064331, "global_step": 502508, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9651973247528076, "global_step": 502509, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.083923816680908, "global_step": 502510, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0121638774871826, "global_step": 502511, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9789503812789917, "global_step": 502512, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.996198058128357, "global_step": 502513, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0542755126953125, "global_step": 502514, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0130598545074463, "global_step": 502515, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1406402587890625, "global_step": 502516, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0526106357574463, "global_step": 502517, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0772705078125, "global_step": 502518, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.038140296936035, "global_step": 502519, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.072810411453247, "global_step": 502520, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0318820476531982, "global_step": 502521, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.041472911834717, "global_step": 502522, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0323493480682373, "global_step": 502523, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0158469676971436, "global_step": 502524, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1119301319122314, "global_step": 502525, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0066986083984375, "global_step": 502526, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0252773761749268, "global_step": 502527, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0152957439422607, "global_step": 502528, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.033343553543091, "global_step": 502529, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0120363235473633, "global_step": 502530, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.093369483947754, "global_step": 502531, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.065782070159912, "global_step": 502532, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0104820728302, "global_step": 502533, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.124188184738159, "global_step": 502534, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0024149417877197, "global_step": 502535, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0725083351135254, "global_step": 502536, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0379929542541504, "global_step": 502537, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0313916206359863, "global_step": 502538, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.094651222229004, "global_step": 502539, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.037280797958374, "global_step": 502540, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0376243591308594, "global_step": 502541, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9894193410873413, "global_step": 502542, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0516700744628906, "global_step": 502543, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1080942153930664, "global_step": 502544, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0570144653320312, "global_step": 502545, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1288318634033203, "global_step": 502546, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9891661405563354, "global_step": 502547, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.157979726791382, "global_step": 502548, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0662808418273926, "global_step": 502549, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.068073272705078, "global_step": 502550, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.070402145385742, "global_step": 502551, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9917209148406982, "global_step": 502552, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0974807739257812, "global_step": 502553, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.052110433578491, "global_step": 502554, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1191632747650146, "global_step": 502555, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0710806846618652, "global_step": 502556, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0528128147125244, "global_step": 502557, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0564074516296387, "global_step": 502558, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1653592586517334, "global_step": 502559, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0601892471313477, "global_step": 502560, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0107645988464355, "global_step": 502561, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0539700984954834, "global_step": 502562, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.002976655960083, "global_step": 502563, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.998267650604248, "global_step": 502564, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.061997890472412, "global_step": 502565, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0934300422668457, "global_step": 502566, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.145599126815796, "global_step": 502567, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0074119567871094, "global_step": 502568, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0922656059265137, "global_step": 502569, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.013512372970581, "global_step": 502570, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.029454231262207, "global_step": 502571, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1115775108337402, "global_step": 502572, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9999068975448608, "global_step": 502573, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0181684494018555, "global_step": 502574, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9540305137634277, "global_step": 502575, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0933711528778076, "global_step": 502576, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1087872982025146, "global_step": 502577, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0182979106903076, "global_step": 502578, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0922083854675293, "global_step": 502579, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0149388313293457, "global_step": 502580, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0960888862609863, "global_step": 502581, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.090909957885742, "global_step": 502582, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.003288984298706, "global_step": 502583, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.020078182220459, "global_step": 502584, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.008512496948242, "global_step": 502585, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.089352607727051, "global_step": 502586, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.160356283187866, "global_step": 502587, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.039400815963745, "global_step": 502588, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0167858600616455, "global_step": 502589, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.017895221710205, "global_step": 502590, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.083508253097534, "global_step": 502591, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0674889087677, "global_step": 502592, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.045789957046509, "global_step": 502593, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.031294107437134, "global_step": 502594, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0916872024536133, "global_step": 502595, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.042628049850464, "global_step": 502596, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.045156478881836, "global_step": 502597, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0568439960479736, "global_step": 502598, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0090205669403076, "global_step": 502599, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1480820178985596, "global_step": 502600, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0294201374053955, "global_step": 502601, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0634055137634277, "global_step": 502602, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.021143674850464, "global_step": 502603, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0370569229125977, "global_step": 502604, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0520784854888916, "global_step": 502605, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.065355062484741, "global_step": 502606, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1219279766082764, "global_step": 502607, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.979603886604309, "global_step": 502608, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9852591753005981, "global_step": 502609, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.973947525024414, "global_step": 502610, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0117201805114746, "global_step": 502611, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.008324146270752, "global_step": 502612, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9752267599105835, "global_step": 502613, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.078882932662964, "global_step": 502614, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1199076175689697, "global_step": 502615, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.054631233215332, "global_step": 502616, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9814473390579224, "global_step": 502617, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.195848226547241, "global_step": 502618, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0723185539245605, "global_step": 502619, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0815720558166504, "global_step": 502620, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.126880168914795, "global_step": 502621, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.023757219314575, "global_step": 502622, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.015395164489746, "global_step": 502623, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0805869102478027, "global_step": 502624, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0716702938079834, "global_step": 502625, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1254260540008545, "global_step": 502626, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.998412847518921, "global_step": 502627, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.057910203933716, "global_step": 502628, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.122913360595703, "global_step": 502629, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0986454486846924, "global_step": 502630, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.096083641052246, "global_step": 502631, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1034457683563232, "global_step": 502632, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0914900302886963, "global_step": 502633, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0538241863250732, "global_step": 502634, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0979225635528564, "global_step": 502635, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.105694532394409, "global_step": 502636, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1094141006469727, "global_step": 502637, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0916733741760254, "global_step": 502638, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0197088718414307, "global_step": 502639, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1425883769989014, "global_step": 502640, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.022451639175415, "global_step": 502641, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0823910236358643, "global_step": 502642, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.091761589050293, "global_step": 502643, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0499439239501953, "global_step": 502644, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0261576175689697, "global_step": 502645, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0263867378234863, "global_step": 502646, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9638503789901733, "global_step": 502647, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.160456418991089, "global_step": 502648, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1122207641601562, "global_step": 502649, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0616180896759033, "global_step": 502650, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.111788749694824, "global_step": 502651, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.088986396789551, "global_step": 502652, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0437252521514893, "global_step": 502653, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.089961290359497, "global_step": 502654, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.004749298095703, "global_step": 502655, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0672659873962402, "global_step": 502656, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.064138174057007, "global_step": 502657, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0528738498687744, "global_step": 502658, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0039052963256836, "global_step": 502659, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0954596996307373, "global_step": 502660, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0630648136138916, "global_step": 502661, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0761237144470215, "global_step": 502662, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.139181613922119, "global_step": 502663, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.057034730911255, "global_step": 502664, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0798983573913574, "global_step": 502665, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0569255352020264, "global_step": 502666, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9486595392227173, "global_step": 502667, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0565743446350098, "global_step": 502668, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0369889736175537, "global_step": 502669, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0243821144104004, "global_step": 502670, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0222840309143066, "global_step": 502671, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1341004371643066, "global_step": 502672, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0300211906433105, "global_step": 502673, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9591336250305176, "global_step": 502674, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.979227900505066, "global_step": 502675, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0354650020599365, "global_step": 502676, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9781513214111328, "global_step": 502677, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.080233573913574, "global_step": 502678, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0038862228393555, "global_step": 502679, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0633788108825684, "global_step": 502680, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1126081943511963, "global_step": 502681, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0502336025238037, "global_step": 502682, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0957682132720947, "global_step": 502683, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0207021236419678, "global_step": 502684, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.002156972885132, "global_step": 502685, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9822970628738403, "global_step": 502686, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0554072856903076, "global_step": 502687, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0918610095977783, "global_step": 502688, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.035334825515747, "global_step": 502689, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.079760789871216, "global_step": 502690, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.014639139175415, "global_step": 502691, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.097689390182495, "global_step": 502692, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0938644409179688, "global_step": 502693, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.100266695022583, "global_step": 502694, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.052644729614258, "global_step": 502695, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.054849624633789, "global_step": 502696, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.053293228149414, "global_step": 502697, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1057093143463135, "global_step": 502698, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.08894944190979, "global_step": 502699, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.093855619430542, "global_step": 502700, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.106208324432373, "global_step": 502701, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.117554187774658, "global_step": 502702, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0415031909942627, "global_step": 502703, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0216050148010254, "global_step": 502704, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0964338779449463, "global_step": 502705, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.070166826248169, "global_step": 502706, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.013117790222168, "global_step": 502707, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9702173471450806, "global_step": 502708, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0834081172943115, "global_step": 502709, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0172598361968994, "global_step": 502710, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.070751190185547, "global_step": 502711, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.121821165084839, "global_step": 502712, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0572428703308105, "global_step": 502713, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.130122423171997, "global_step": 502714, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0772316455841064, "global_step": 502715, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0151400566101074, "global_step": 502716, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.025547504425049, "global_step": 502717, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1502127647399902, "global_step": 502718, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1254656314849854, "global_step": 502719, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.033895969390869, "global_step": 502720, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.052584171295166, "global_step": 502721, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.065873622894287, "global_step": 502722, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0226330757141113, "global_step": 502723, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9726747274398804, "global_step": 502724, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1430511474609375, "global_step": 502725, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.133829355239868, "global_step": 502726, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0519728660583496, "global_step": 502727, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.01729679107666, "global_step": 502728, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.000082015991211, "global_step": 502729, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0406460762023926, "global_step": 502730, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0465917587280273, "global_step": 502731, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1276915073394775, "global_step": 502732, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.987382173538208, "global_step": 502733, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0959343910217285, "global_step": 502734, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9992899894714355, "global_step": 502735, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.06048846244812, "global_step": 502736, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.991149663925171, "global_step": 502737, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0782339572906494, "global_step": 502738, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.020850658416748, "global_step": 502739, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.103679895401001, "global_step": 502740, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0288045406341553, "global_step": 502741, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.038703203201294, "global_step": 502742, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0670106410980225, "global_step": 502743, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.063169479370117, "global_step": 502744, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.006617546081543, "global_step": 502745, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0063936710357666, "global_step": 502746, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.027879238128662, "global_step": 502747, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0210084915161133, "global_step": 502748, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0168848037719727, "global_step": 502749, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0588600635528564, "global_step": 502750, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.058382749557495, "global_step": 502751, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0353970527648926, "global_step": 502752, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0542831420898438, "global_step": 502753, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0371477603912354, "global_step": 502754, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.005035400390625, "global_step": 502755, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0558559894561768, "global_step": 502756, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0650136470794678, "global_step": 502757, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0589241981506348, "global_step": 502758, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0414562225341797, "global_step": 502759, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9530409574508667, "global_step": 502760, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1043126583099365, "global_step": 502761, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9788910150527954, "global_step": 502762, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.006967782974243, "global_step": 502763, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.049415349960327, "global_step": 502764, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0508298873901367, "global_step": 502765, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9614394903182983, "global_step": 502766, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0939807891845703, "global_step": 502767, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.130950689315796, "global_step": 502768, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9814459085464478, "global_step": 502769, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.072547674179077, "global_step": 502770, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0820670127868652, "global_step": 502771, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.939103364944458, "global_step": 502772, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0691158771514893, "global_step": 502773, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0292437076568604, "global_step": 502774, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0026354789733887, "global_step": 502775, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0794789791107178, "global_step": 502776, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9689217805862427, "global_step": 502777, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0252559185028076, "global_step": 502778, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0807034969329834, "global_step": 502779, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0559659004211426, "global_step": 502780, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.048752546310425, "global_step": 502781, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0952796936035156, "global_step": 502782, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.947137475013733, "global_step": 502783, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9743579626083374, "global_step": 502784, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1221957206726074, "global_step": 502785, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0608582496643066, "global_step": 502786, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.992859125137329, "global_step": 502787, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0688023567199707, "global_step": 502788, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0633723735809326, "global_step": 502789, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0585787296295166, "global_step": 502790, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.046766519546509, "global_step": 502791, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.038564682006836, "global_step": 502792, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1065468788146973, "global_step": 502793, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0112433433532715, "global_step": 502794, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9505081176757812, "global_step": 502795, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.100698709487915, "global_step": 502796, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.060150146484375, "global_step": 502797, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0165886878967285, "global_step": 502798, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.137331008911133, "global_step": 502799, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.041618585586548, "global_step": 502800, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0751712322235107, "global_step": 502801, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0559606552124023, "global_step": 502802, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0839169025421143, "global_step": 502803, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0804173946380615, "global_step": 502804, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.000520944595337, "global_step": 502805, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0362207889556885, "global_step": 502806, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.125335216522217, "global_step": 502807, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9829225540161133, "global_step": 502808, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9938297271728516, "global_step": 502809, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.000349521636963, "global_step": 502810, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.020781993865967, "global_step": 502811, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1000118255615234, "global_step": 502812, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1716268062591553, "global_step": 502813, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1384010314941406, "global_step": 502814, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.08128023147583, "global_step": 502815, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0786898136138916, "global_step": 502816, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1355910301208496, "global_step": 502817, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.091956853866577, "global_step": 502818, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0900373458862305, "global_step": 502819, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0818629264831543, "global_step": 502820, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0608296394348145, "global_step": 502821, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9924429655075073, "global_step": 502822, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.081296443939209, "global_step": 502823, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1407341957092285, "global_step": 502824, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0680315494537354, "global_step": 502825, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1901421546936035, "global_step": 502826, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0477964878082275, "global_step": 502827, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0518248081207275, "global_step": 502828, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0209105014801025, "global_step": 502829, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9614145755767822, "global_step": 502830, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9859254360198975, "global_step": 502831, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0047121047973633, "global_step": 502832, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0982842445373535, "global_step": 502833, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.00403094291687, "global_step": 502834, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0834975242614746, "global_step": 502835, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0126137733459473, "global_step": 502836, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0255775451660156, "global_step": 502837, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.028932571411133, "global_step": 502838, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.068136692047119, "global_step": 502839, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9825867414474487, "global_step": 502840, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1265740394592285, "global_step": 502841, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9838030338287354, "global_step": 502842, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.075863838195801, "global_step": 502843, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.172595977783203, "global_step": 502844, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0404915809631348, "global_step": 502845, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0638198852539062, "global_step": 502846, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.101191759109497, "global_step": 502847, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0666725635528564, "global_step": 502848, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9992029666900635, "global_step": 502849, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1094045639038086, "global_step": 502850, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.058398962020874, "global_step": 502851, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0585508346557617, "global_step": 502852, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0675113201141357, "global_step": 502853, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0301313400268555, "global_step": 502854, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0706841945648193, "global_step": 502855, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1506295204162598, "global_step": 502856, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0305206775665283, "global_step": 502857, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.028810501098633, "global_step": 502858, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.137911796569824, "global_step": 502859, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.107398748397827, "global_step": 502860, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.002864360809326, "global_step": 502861, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0963997840881348, "global_step": 502862, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1415627002716064, "global_step": 502863, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0510103702545166, "global_step": 502864, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0098299980163574, "global_step": 502865, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.031275749206543, "global_step": 502866, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0166165828704834, "global_step": 502867, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0112760066986084, "global_step": 502868, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0960614681243896, "global_step": 502869, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0757317543029785, "global_step": 502870, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0402352809906006, "global_step": 502871, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.046945095062256, "global_step": 502872, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9637192487716675, "global_step": 502873, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9600857496261597, "global_step": 502874, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.037264823913574, "global_step": 502875, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0539047718048096, "global_step": 502876, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.067934036254883, "global_step": 502877, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1019952297210693, "global_step": 502878, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0100960731506348, "global_step": 502879, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0684399604797363, "global_step": 502880, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0268032550811768, "global_step": 502881, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0428667068481445, "global_step": 502882, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9655120372772217, "global_step": 502883, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0722243785858154, "global_step": 502884, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.058368444442749, "global_step": 502885, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0770111083984375, "global_step": 502886, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9803483486175537, "global_step": 502887, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.125013828277588, "global_step": 502888, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0915935039520264, "global_step": 502889, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9985450506210327, "global_step": 502890, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0279476642608643, "global_step": 502891, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.083517551422119, "global_step": 502892, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0335936546325684, "global_step": 502893, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.077042579650879, "global_step": 502894, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.065377950668335, "global_step": 502895, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.122626304626465, "global_step": 502896, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0819408893585205, "global_step": 502897, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0643041133880615, "global_step": 502898, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0519938468933105, "global_step": 502899, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0461630821228027, "global_step": 502900, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0008904933929443, "global_step": 502901, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.089623212814331, "global_step": 502902, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.024998426437378, "global_step": 502903, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.068004608154297, "global_step": 502904, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0743885040283203, "global_step": 502905, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.072366952896118, "global_step": 502906, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.027782917022705, "global_step": 502907, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.051431179046631, "global_step": 502908, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0146632194519043, "global_step": 502909, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0640265941619873, "global_step": 502910, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9855713844299316, "global_step": 502911, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0933473110198975, "global_step": 502912, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0724449157714844, "global_step": 502913, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.062337875366211, "global_step": 502914, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9922115802764893, "global_step": 502915, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0512332916259766, "global_step": 502916, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0120582580566406, "global_step": 502917, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0315818786621094, "global_step": 502918, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0602056980133057, "global_step": 502919, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0578255653381348, "global_step": 502920, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.122922420501709, "global_step": 502921, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0018668174743652, "global_step": 502922, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9832632541656494, "global_step": 502923, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.021881341934204, "global_step": 502924, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0957181453704834, "global_step": 502925, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.063107490539551, "global_step": 502926, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0563294887542725, "global_step": 502927, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.101019859313965, "global_step": 502928, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.035686492919922, "global_step": 502929, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1139206886291504, "global_step": 502930, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0507941246032715, "global_step": 502931, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.134429693222046, "global_step": 502932, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.150768756866455, "global_step": 502933, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1397597789764404, "global_step": 502934, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1428723335266113, "global_step": 502935, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.981346607208252, "global_step": 502936, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.084475040435791, "global_step": 502937, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9442269802093506, "global_step": 502938, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0962250232696533, "global_step": 502939, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.096409320831299, "global_step": 502940, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0267693996429443, "global_step": 502941, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1185567378997803, "global_step": 502942, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1057581901550293, "global_step": 502943, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0235724449157715, "global_step": 502944, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9758623838424683, "global_step": 502945, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0477046966552734, "global_step": 502946, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.084552049636841, "global_step": 502947, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0938193798065186, "global_step": 502948, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0510411262512207, "global_step": 502949, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0112483501434326, "global_step": 502950, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0808279514312744, "global_step": 502951, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.060349702835083, "global_step": 502952, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0922210216522217, "global_step": 502953, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.029874801635742, "global_step": 502954, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.011507987976074, "global_step": 502955, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.981763482093811, "global_step": 502956, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.027066469192505, "global_step": 502957, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.108397960662842, "global_step": 502958, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0733351707458496, "global_step": 502959, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0393307209014893, "global_step": 502960, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.019664764404297, "global_step": 502961, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0696287155151367, "global_step": 502962, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.094709634780884, "global_step": 502963, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.126535177230835, "global_step": 502964, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.046536445617676, "global_step": 502965, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0494720935821533, "global_step": 502966, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0702834129333496, "global_step": 502967, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.053950071334839, "global_step": 502968, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0396616458892822, "global_step": 502969, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0899605751037598, "global_step": 502970, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0676088333129883, "global_step": 502971, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0235679149627686, "global_step": 502972, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1258773803710938, "global_step": 502973, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0476114749908447, "global_step": 502974, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0949196815490723, "global_step": 502975, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.050661563873291, "global_step": 502976, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1012537479400635, "global_step": 502977, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9509432315826416, "global_step": 502978, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.120887517929077, "global_step": 502979, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0906779766082764, "global_step": 502980, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1176977157592773, "global_step": 502981, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.121023416519165, "global_step": 502982, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0229122638702393, "global_step": 502983, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.06827974319458, "global_step": 502984, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0220813751220703, "global_step": 502985, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1188840866088867, "global_step": 502986, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.056605100631714, "global_step": 502987, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.055421829223633, "global_step": 502988, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0426082611083984, "global_step": 502989, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.114797353744507, "global_step": 502990, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0060293674468994, "global_step": 502991, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.038043975830078, "global_step": 502992, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0355794429779053, "global_step": 502993, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.010897397994995, "global_step": 502994, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0513715744018555, "global_step": 502995, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.026812791824341, "global_step": 502996, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0301270484924316, "global_step": 502997, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1003119945526123, "global_step": 502998, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0440855026245117, "global_step": 502999, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.99674391746521, "global_step": 503000, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.027620315551758, "global_step": 503001, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.944810390472412, "global_step": 503002, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.8864400386810303, "global_step": 503003, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.099114418029785, "global_step": 503004, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0599076747894287, "global_step": 503005, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.102966547012329, "global_step": 503006, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.078505277633667, "global_step": 503007, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0696301460266113, "global_step": 503008, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9623667001724243, "global_step": 503009, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1294119358062744, "global_step": 503010, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.004976511001587, "global_step": 503011, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.975672960281372, "global_step": 503012, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9971035718917847, "global_step": 503013, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0616676807403564, "global_step": 503014, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.973127841949463, "global_step": 503015, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9832298755645752, "global_step": 503016, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.043147087097168, "global_step": 503017, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9996532201766968, "global_step": 503018, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0115139484405518, "global_step": 503019, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9858795404434204, "global_step": 503020, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.024373769760132, "global_step": 503021, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.079360008239746, "global_step": 503022, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0881943702697754, "global_step": 503023, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0110721588134766, "global_step": 503024, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.128761053085327, "global_step": 503025, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0819265842437744, "global_step": 503026, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0454866886138916, "global_step": 503027, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.120779514312744, "global_step": 503028, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.981076717376709, "global_step": 503029, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9694697856903076, "global_step": 503030, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9383318424224854, "global_step": 503031, "epoch": 868, "lr": 5e-05}
{"train_loss": 1.9962708950042725, "global_step": 503032, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0081958770751953, "global_step": 503033, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0112335681915283, "global_step": 503034, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.129896879196167, "global_step": 503035, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0375547409057617, "global_step": 503036, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.055389165878296, "global_step": 503037, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.081338405609131, "global_step": 503038, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0906424522399902, "global_step": 503039, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.1105430126190186, "global_step": 503040, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0762174129486084, "global_step": 503041, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.028989315032959, "global_step": 503042, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.048900604248047, "global_step": 503043, "epoch": 868, "lr": 5e-05}
{"train_loss": 2.0181374549865723, "global_step": 503044, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9895411729812622, "global_step": 503045, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.101223945617676, "global_step": 503046, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.111541986465454, "global_step": 503047, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.038827896118164, "global_step": 503048, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0285239219665527, "global_step": 503049, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9244567155838013, "global_step": 503050, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.016709327697754, "global_step": 503051, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0246400833129883, "global_step": 503052, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0617048740386963, "global_step": 503053, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0481925010681152, "global_step": 503054, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9991445541381836, "global_step": 503055, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0767712593078613, "global_step": 503056, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0762550830841064, "global_step": 503057, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0023956298828125, "global_step": 503058, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9873378276824951, "global_step": 503059, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.055492639541626, "global_step": 503060, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0444447994232178, "global_step": 503061, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0596179962158203, "global_step": 503062, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0327908992767334, "global_step": 503063, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0212695598602295, "global_step": 503064, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1085898876190186, "global_step": 503065, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9633828401565552, "global_step": 503066, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.093205451965332, "global_step": 503067, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.03476881980896, "global_step": 503068, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0232067108154297, "global_step": 503069, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1094467639923096, "global_step": 503070, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9825248718261719, "global_step": 503071, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0754220485687256, "global_step": 503072, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1395158767700195, "global_step": 503073, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.041477680206299, "global_step": 503074, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.020324230194092, "global_step": 503075, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0596015453338623, "global_step": 503076, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.026928186416626, "global_step": 503077, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0885238647460938, "global_step": 503078, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0860722064971924, "global_step": 503079, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0306949615478516, "global_step": 503080, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.034355401992798, "global_step": 503081, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.155017614364624, "global_step": 503082, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0381650924682617, "global_step": 503083, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0212559700012207, "global_step": 503084, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.140913486480713, "global_step": 503085, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.007885217666626, "global_step": 503086, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0037856101989746, "global_step": 503087, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.117194652557373, "global_step": 503088, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.09230637550354, "global_step": 503089, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.021806478500366, "global_step": 503090, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.950624942779541, "global_step": 503091, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.02669620513916, "global_step": 503092, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9955214262008667, "global_step": 503093, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.123873472213745, "global_step": 503094, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9835561513900757, "global_step": 503095, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0241682529449463, "global_step": 503096, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1302905082702637, "global_step": 503097, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.072308301925659, "global_step": 503098, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0582425594329834, "global_step": 503099, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0003509521484375, "global_step": 503100, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0472474098205566, "global_step": 503101, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.039740800857544, "global_step": 503102, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1045358180999756, "global_step": 503103, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.036459445953369, "global_step": 503104, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.029630422592163, "global_step": 503105, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0621352195739746, "global_step": 503106, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.088129997253418, "global_step": 503107, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0336601734161377, "global_step": 503108, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.025935411453247, "global_step": 503109, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0492300987243652, "global_step": 503110, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.967260479927063, "global_step": 503111, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0621397495269775, "global_step": 503112, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0020852088928223, "global_step": 503113, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.012444496154785, "global_step": 503114, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9952374696731567, "global_step": 503115, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.949865698814392, "global_step": 503116, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.016540765762329, "global_step": 503117, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0391616821289062, "global_step": 503118, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0339772701263428, "global_step": 503119, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.022475242614746, "global_step": 503120, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.987287163734436, "global_step": 503121, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9973018169403076, "global_step": 503122, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9706424474716187, "global_step": 503123, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0785536766052246, "global_step": 503124, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0199522972106934, "global_step": 503125, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0125913619995117, "global_step": 503126, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0655088424682617, "global_step": 503127, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.979236125946045, "global_step": 503128, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1246542930603027, "global_step": 503129, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0343008041381836, "global_step": 503130, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0479278564453125, "global_step": 503131, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0622496604919434, "global_step": 503132, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0789694786071777, "global_step": 503133, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1150455474853516, "global_step": 503134, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.048520088195801, "global_step": 503135, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.020956039428711, "global_step": 503136, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9927546977996826, "global_step": 503137, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0844531059265137, "global_step": 503138, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.021129846572876, "global_step": 503139, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.011289119720459, "global_step": 503140, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.026481866836548, "global_step": 503141, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0146188735961914, "global_step": 503142, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.026442050933838, "global_step": 503143, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1305291652679443, "global_step": 503144, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.993647813796997, "global_step": 503145, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.024960517883301, "global_step": 503146, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0559844970703125, "global_step": 503147, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0371897220611572, "global_step": 503148, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0674097537994385, "global_step": 503149, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0308589935302734, "global_step": 503150, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.017197370529175, "global_step": 503151, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.103963851928711, "global_step": 503152, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.008394241333008, "global_step": 503153, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.082016944885254, "global_step": 503154, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1079704761505127, "global_step": 503155, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9567924737930298, "global_step": 503156, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0680885314941406, "global_step": 503157, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0802013874053955, "global_step": 503158, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0964059829711914, "global_step": 503159, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.154470205307007, "global_step": 503160, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.020930051803589, "global_step": 503161, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0699782371520996, "global_step": 503162, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9791840314865112, "global_step": 503163, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0441415309906006, "global_step": 503164, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0165557861328125, "global_step": 503165, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.08833646774292, "global_step": 503166, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.091097354888916, "global_step": 503167, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9836868047714233, "global_step": 503168, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0946030616760254, "global_step": 503169, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.052449941635132, "global_step": 503170, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.989044427871704, "global_step": 503171, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9331910610198975, "global_step": 503172, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0136497020721436, "global_step": 503173, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9836602210998535, "global_step": 503174, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.023536443710327, "global_step": 503175, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.093893527984619, "global_step": 503176, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0637905597686768, "global_step": 503177, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.065753936767578, "global_step": 503178, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0534560680389404, "global_step": 503179, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0312366485595703, "global_step": 503180, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.044238567352295, "global_step": 503181, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0956320762634277, "global_step": 503182, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.020005702972412, "global_step": 503183, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0390937328338623, "global_step": 503184, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0464529991149902, "global_step": 503185, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0892109870910645, "global_step": 503186, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1186041831970215, "global_step": 503187, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0554990768432617, "global_step": 503188, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9453914165496826, "global_step": 503189, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1146786212921143, "global_step": 503190, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0349197387695312, "global_step": 503191, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0646567344665527, "global_step": 503192, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0412991046905518, "global_step": 503193, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9981781244277954, "global_step": 503194, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.044105291366577, "global_step": 503195, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0111443996429443, "global_step": 503196, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0450611114501953, "global_step": 503197, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.939591884613037, "global_step": 503198, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0893826484680176, "global_step": 503199, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0113656520843506, "global_step": 503200, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0043647289276123, "global_step": 503201, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.14106822013855, "global_step": 503202, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0719354152679443, "global_step": 503203, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0254571437835693, "global_step": 503204, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9980581998825073, "global_step": 503205, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0966989994049072, "global_step": 503206, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9602010250091553, "global_step": 503207, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0925793647766113, "global_step": 503208, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9787695407867432, "global_step": 503209, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.111924648284912, "global_step": 503210, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0299742221832275, "global_step": 503211, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0700790882110596, "global_step": 503212, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0732967853546143, "global_step": 503213, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9166642427444458, "global_step": 503214, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9973527193069458, "global_step": 503215, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9194616079330444, "global_step": 503216, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.031442642211914, "global_step": 503217, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.074354410171509, "global_step": 503218, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1273608207702637, "global_step": 503219, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.061340808868408, "global_step": 503220, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1033101081848145, "global_step": 503221, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0181217193603516, "global_step": 503222, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9508198499679565, "global_step": 503223, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.056426763534546, "global_step": 503224, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.065415143966675, "global_step": 503225, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.103271484375, "global_step": 503226, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1059184074401855, "global_step": 503227, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0519731044769287, "global_step": 503228, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.012200355529785, "global_step": 503229, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0069544315338135, "global_step": 503230, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.988853096961975, "global_step": 503231, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0597622394561768, "global_step": 503232, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9846426248550415, "global_step": 503233, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0308802127838135, "global_step": 503234, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.034735918045044, "global_step": 503235, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0194506645202637, "global_step": 503236, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0160646438598633, "global_step": 503237, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.136652708053589, "global_step": 503238, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.109372138977051, "global_step": 503239, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.068603754043579, "global_step": 503240, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9669119119644165, "global_step": 503241, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1664323806762695, "global_step": 503242, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.030986785888672, "global_step": 503243, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.2204654216766357, "global_step": 503244, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0154197216033936, "global_step": 503245, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0399205684661865, "global_step": 503246, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0807087421417236, "global_step": 503247, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0735561847686768, "global_step": 503248, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1016845703125, "global_step": 503249, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.033576488494873, "global_step": 503250, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9796745777130127, "global_step": 503251, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.089024066925049, "global_step": 503252, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9969532489776611, "global_step": 503253, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0460386276245117, "global_step": 503254, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.017686367034912, "global_step": 503255, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.023620843887329, "global_step": 503256, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0453407764434814, "global_step": 503257, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.090092658996582, "global_step": 503258, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0149292945861816, "global_step": 503259, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.005098581314087, "global_step": 503260, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0104424953460693, "global_step": 503261, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0357422828674316, "global_step": 503262, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9798341989517212, "global_step": 503263, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.128211498260498, "global_step": 503264, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.066864013671875, "global_step": 503265, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1067206859588623, "global_step": 503266, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.06256103515625, "global_step": 503267, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9560539722442627, "global_step": 503268, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9768028259277344, "global_step": 503269, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.094482898712158, "global_step": 503270, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.03466534614563, "global_step": 503271, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.006627321243286, "global_step": 503272, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0398058891296387, "global_step": 503273, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.048550844192505, "global_step": 503274, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0335187911987305, "global_step": 503275, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0275590419769287, "global_step": 503276, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.104802131652832, "global_step": 503277, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.077341318130493, "global_step": 503278, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.982975721359253, "global_step": 503279, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0856833457946777, "global_step": 503280, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9914354085922241, "global_step": 503281, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9680571556091309, "global_step": 503282, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9853614568710327, "global_step": 503283, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0438296794891357, "global_step": 503284, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0189034938812256, "global_step": 503285, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0779459476470947, "global_step": 503286, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0709125995635986, "global_step": 503287, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.02412748336792, "global_step": 503288, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.081998586654663, "global_step": 503289, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.01930832862854, "global_step": 503290, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0052330493927, "global_step": 503291, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.006714344024658, "global_step": 503292, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.014187812805176, "global_step": 503293, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0671942234039307, "global_step": 503294, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0705177783966064, "global_step": 503295, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.954779028892517, "global_step": 503296, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.08325457572937, "global_step": 503297, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.023451328277588, "global_step": 503298, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0337891578674316, "global_step": 503299, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0125510692596436, "global_step": 503300, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.063418388366699, "global_step": 503301, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.040801763534546, "global_step": 503302, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0612401962280273, "global_step": 503303, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.127955436706543, "global_step": 503304, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1756465435028076, "global_step": 503305, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.981199026107788, "global_step": 503306, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.177737236022949, "global_step": 503307, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.056882381439209, "global_step": 503308, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0792312622070312, "global_step": 503309, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.027980327606201, "global_step": 503310, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9992421865463257, "global_step": 503311, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0909793376922607, "global_step": 503312, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.080946683883667, "global_step": 503313, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0994338989257812, "global_step": 503314, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0929791927337646, "global_step": 503315, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.981097936630249, "global_step": 503316, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0603456497192383, "global_step": 503317, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0285234451293945, "global_step": 503318, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.003361701965332, "global_step": 503319, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9631543159484863, "global_step": 503320, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.030848979949951, "global_step": 503321, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0160462856292725, "global_step": 503322, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1581778526306152, "global_step": 503323, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0655291080474854, "global_step": 503324, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.992241621017456, "global_step": 503325, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9647315740585327, "global_step": 503326, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.008660316467285, "global_step": 503327, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1243293285369873, "global_step": 503328, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0127830505371094, "global_step": 503329, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0338072776794434, "global_step": 503330, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9874238967895508, "global_step": 503331, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0389955043792725, "global_step": 503332, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9978601932525635, "global_step": 503333, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0206964015960693, "global_step": 503334, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9792547225952148, "global_step": 503335, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0796144008636475, "global_step": 503336, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0512216091156006, "global_step": 503337, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.163905382156372, "global_step": 503338, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0699517726898193, "global_step": 503339, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0539214611053467, "global_step": 503340, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0247979164123535, "global_step": 503341, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1238977909088135, "global_step": 503342, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.122694492340088, "global_step": 503343, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0198466777801514, "global_step": 503344, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.104978561401367, "global_step": 503345, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0149598121643066, "global_step": 503346, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0120363235473633, "global_step": 503347, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0107994079589844, "global_step": 503348, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.087150812149048, "global_step": 503349, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0131170749664307, "global_step": 503350, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1384360790252686, "global_step": 503351, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9833011627197266, "global_step": 503352, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9612840414047241, "global_step": 503353, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0147604942321777, "global_step": 503354, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0501298904418945, "global_step": 503355, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0463085174560547, "global_step": 503356, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0796749591827393, "global_step": 503357, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1051573753356934, "global_step": 503358, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0270137786865234, "global_step": 503359, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0415077209472656, "global_step": 503360, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0243897438049316, "global_step": 503361, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9884247779846191, "global_step": 503362, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.076535224914551, "global_step": 503363, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0391793251037598, "global_step": 503364, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9823997020721436, "global_step": 503365, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0816473960876465, "global_step": 503366, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9803866147994995, "global_step": 503367, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0307226181030273, "global_step": 503368, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.088855028152466, "global_step": 503369, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.069847822189331, "global_step": 503370, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.059270143508911, "global_step": 503371, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.043678045272827, "global_step": 503372, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.928995966911316, "global_step": 503373, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0054469108581543, "global_step": 503374, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0514352321624756, "global_step": 503375, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0826752185821533, "global_step": 503376, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0139694213867188, "global_step": 503377, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.001798152923584, "global_step": 503378, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.144716501235962, "global_step": 503379, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.036179304122925, "global_step": 503380, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0211238861083984, "global_step": 503381, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.054969549179077, "global_step": 503382, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0350732803344727, "global_step": 503383, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.183098793029785, "global_step": 503384, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.060612916946411, "global_step": 503385, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.947765588760376, "global_step": 503386, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.011584520339966, "global_step": 503387, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.034569501876831, "global_step": 503388, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.019925832748413, "global_step": 503389, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.063581705093384, "global_step": 503390, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9608707427978516, "global_step": 503391, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0411109924316406, "global_step": 503392, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.037160873413086, "global_step": 503393, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.091931104660034, "global_step": 503394, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0663554668426514, "global_step": 503395, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0466320514678955, "global_step": 503396, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.982864499092102, "global_step": 503397, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.130033016204834, "global_step": 503398, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9680564403533936, "global_step": 503399, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.005554437637329, "global_step": 503400, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9821805953979492, "global_step": 503401, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0167157649993896, "global_step": 503402, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.103576421737671, "global_step": 503403, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0504064559936523, "global_step": 503404, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0652029514312744, "global_step": 503405, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.045837640762329, "global_step": 503406, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0698916912078857, "global_step": 503407, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0667333602905273, "global_step": 503408, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0499236583709717, "global_step": 503409, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.093095302581787, "global_step": 503410, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.034454822540283, "global_step": 503411, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9977833032608032, "global_step": 503412, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.151930332183838, "global_step": 503413, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0489344596862793, "global_step": 503414, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.088681697845459, "global_step": 503415, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.079960823059082, "global_step": 503416, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0537185668945312, "global_step": 503417, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0627474784851074, "global_step": 503418, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.043087959289551, "global_step": 503419, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9794435501098633, "global_step": 503420, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.071704864501953, "global_step": 503421, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0604026317596436, "global_step": 503422, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0300915241241455, "global_step": 503423, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0315499305725098, "global_step": 503424, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0846128463745117, "global_step": 503425, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0217485427856445, "global_step": 503426, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.097832679748535, "global_step": 503427, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1276416778564453, "global_step": 503428, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0445187091827393, "global_step": 503429, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0442936420440674, "global_step": 503430, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0499041080474854, "global_step": 503431, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.029054880142212, "global_step": 503432, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.041924476623535, "global_step": 503433, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1196813583374023, "global_step": 503434, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0883383750915527, "global_step": 503435, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0109684467315674, "global_step": 503436, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0485525131225586, "global_step": 503437, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.073648691177368, "global_step": 503438, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0640103816986084, "global_step": 503439, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.041724920272827, "global_step": 503440, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9922139644622803, "global_step": 503441, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9802284240722656, "global_step": 503442, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.061627149581909, "global_step": 503443, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9834216833114624, "global_step": 503444, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.085059881210327, "global_step": 503445, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.040074348449707, "global_step": 503446, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.029785394668579, "global_step": 503447, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9913324117660522, "global_step": 503448, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.163846969604492, "global_step": 503449, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.09108567237854, "global_step": 503450, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0243513584136963, "global_step": 503451, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0494375228881836, "global_step": 503452, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1119303703308105, "global_step": 503453, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0229930877685547, "global_step": 503454, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9995079040527344, "global_step": 503455, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.948934555053711, "global_step": 503456, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9960873126983643, "global_step": 503457, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0608623027801514, "global_step": 503458, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.133546829223633, "global_step": 503459, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.030632972717285, "global_step": 503460, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0576589107513428, "global_step": 503461, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9536584615707397, "global_step": 503462, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.041072130203247, "global_step": 503463, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0683093070983887, "global_step": 503464, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0499088764190674, "global_step": 503465, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0646371841430664, "global_step": 503466, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0930535793304443, "global_step": 503467, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0215976238250732, "global_step": 503468, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.090970039367676, "global_step": 503469, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.06919264793396, "global_step": 503470, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9879748821258545, "global_step": 503471, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0111348628997803, "global_step": 503472, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.107969045639038, "global_step": 503473, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.071251153945923, "global_step": 503474, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.050368070602417, "global_step": 503475, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0608444213867188, "global_step": 503476, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.078217029571533, "global_step": 503477, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9864839315414429, "global_step": 503478, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.030292272567749, "global_step": 503479, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0752358436584473, "global_step": 503480, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0076887607574463, "global_step": 503481, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0198988914489746, "global_step": 503482, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.022939920425415, "global_step": 503483, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.09657883644104, "global_step": 503484, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0233983993530273, "global_step": 503485, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0736923217773438, "global_step": 503486, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.00504732131958, "global_step": 503487, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.011526584625244, "global_step": 503488, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.079002618789673, "global_step": 503489, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.032019853591919, "global_step": 503490, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.071709632873535, "global_step": 503491, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.06718111038208, "global_step": 503492, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0716278553009033, "global_step": 503493, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0254993438720703, "global_step": 503494, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1214704513549805, "global_step": 503495, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.119605541229248, "global_step": 503496, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.057058572769165, "global_step": 503497, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0067973136901855, "global_step": 503498, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0658552646636963, "global_step": 503499, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.082432508468628, "global_step": 503500, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1305503845214844, "global_step": 503501, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9917573928833008, "global_step": 503502, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0170814990997314, "global_step": 503503, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0362887382507324, "global_step": 503504, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0595345497131348, "global_step": 503505, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0467472076416016, "global_step": 503506, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.000640630722046, "global_step": 503507, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.102501153945923, "global_step": 503508, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0194520950317383, "global_step": 503509, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0674846172332764, "global_step": 503510, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0372836589813232, "global_step": 503511, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.03463077545166, "global_step": 503512, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0719223022460938, "global_step": 503513, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0179624557495117, "global_step": 503514, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0023043155670166, "global_step": 503515, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1028690338134766, "global_step": 503516, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.02703857421875, "global_step": 503517, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0213303565979004, "global_step": 503518, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.986906886100769, "global_step": 503519, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.044724941253662, "global_step": 503520, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0316150188446045, "global_step": 503521, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0132315158843994, "global_step": 503522, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0883729457855225, "global_step": 503523, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.974936842918396, "global_step": 503524, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0063679218292236, "global_step": 503525, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.051020860671997, "global_step": 503526, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.00168514251709, "global_step": 503527, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9955283403396606, "global_step": 503528, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0703482627868652, "global_step": 503529, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9584746360778809, "global_step": 503530, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.108961820602417, "global_step": 503531, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0868966579437256, "global_step": 503532, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0164713859558105, "global_step": 503533, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9763697385787964, "global_step": 503534, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0214040279388428, "global_step": 503535, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.061121940612793, "global_step": 503536, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.031707763671875, "global_step": 503537, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0919511318206787, "global_step": 503538, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0658581256866455, "global_step": 503539, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.137359857559204, "global_step": 503540, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.050894260406494, "global_step": 503541, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.044210433959961, "global_step": 503542, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.070413827896118, "global_step": 503543, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0948522090911865, "global_step": 503544, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.018859386444092, "global_step": 503545, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.092291831970215, "global_step": 503546, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0622947216033936, "global_step": 503547, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.002988338470459, "global_step": 503548, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9853367805480957, "global_step": 503549, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.977936863899231, "global_step": 503550, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9824249744415283, "global_step": 503551, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1167855262756348, "global_step": 503552, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0624125003814697, "global_step": 503553, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.019465684890747, "global_step": 503554, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0196692943573, "global_step": 503555, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9705467224121094, "global_step": 503556, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0242838859558105, "global_step": 503557, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1046652793884277, "global_step": 503558, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.039203643798828, "global_step": 503559, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.068028688430786, "global_step": 503560, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9558453559875488, "global_step": 503561, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.021437168121338, "global_step": 503562, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0759363174438477, "global_step": 503563, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.063891649246216, "global_step": 503564, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9730195999145508, "global_step": 503565, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0840516090393066, "global_step": 503566, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.035482406616211, "global_step": 503567, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0891714096069336, "global_step": 503568, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0794925689697266, "global_step": 503569, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0259618759155273, "global_step": 503570, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0307605266571045, "global_step": 503571, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1195695400238037, "global_step": 503572, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.081003189086914, "global_step": 503573, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.087078332901001, "global_step": 503574, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0102193355560303, "global_step": 503575, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1434848308563232, "global_step": 503576, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.041069269180298, "global_step": 503577, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.032274007797241, "global_step": 503578, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9757778644561768, "global_step": 503579, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0386815071105957, "global_step": 503580, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0887415409088135, "global_step": 503581, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0331623554229736, "global_step": 503582, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9758145809173584, "global_step": 503583, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.02710223197937, "global_step": 503584, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1091909408569336, "global_step": 503585, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0761032104492188, "global_step": 503586, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9837197065353394, "global_step": 503587, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0533640384674072, "global_step": 503588, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9357516765594482, "global_step": 503589, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1683130264282227, "global_step": 503590, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.078740358352661, "global_step": 503591, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.091177225112915, "global_step": 503592, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0271692276000977, "global_step": 503593, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9950733184814453, "global_step": 503594, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0098137855529785, "global_step": 503595, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0705838203430176, "global_step": 503596, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9552617073059082, "global_step": 503597, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1286840438842773, "global_step": 503598, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0718605518341064, "global_step": 503599, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1303861141204834, "global_step": 503600, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.115135908126831, "global_step": 503601, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0375757217407227, "global_step": 503602, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.062551736831665, "global_step": 503603, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.966002106666565, "global_step": 503604, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.981650710105896, "global_step": 503605, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.040065288543701, "global_step": 503606, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.996377944946289, "global_step": 503607, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0609240531921387, "global_step": 503608, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0340943336486816, "global_step": 503609, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.030759572982788, "global_step": 503610, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.132882595062256, "global_step": 503611, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.055445671081543, "global_step": 503612, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1171116828918457, "global_step": 503613, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0243492126464844, "global_step": 503614, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.116142749786377, "global_step": 503615, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0011532306671143, "global_step": 503616, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0695314407348633, "global_step": 503617, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.082808017730713, "global_step": 503618, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0606801509857178, "global_step": 503619, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.015601396560669, "global_step": 503620, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.150662899017334, "global_step": 503621, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.040365695953369, "global_step": 503622, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.991207242012024, "global_step": 503623, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0394434928894043, "global_step": 503624, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0606496334075928, "global_step": 503625, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.097540855407715, "global_step": 503626, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0881567001342773, "global_step": 503627, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.100579023361206, "global_step": 503628, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0628538131713867, "global_step": 503629, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1010897159576416, "global_step": 503630, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.078129529953003, "global_step": 503631, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9833221435546875, "global_step": 503632, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.150195837020874, "global_step": 503633, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0661613941192627, "global_step": 503634, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0553324222564697, "global_step": 503635, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0382330417633057, "global_step": 503636, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9840903282165527, "global_step": 503637, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0291683673858643, "global_step": 503638, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.118532657623291, "global_step": 503639, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9822683334350586, "global_step": 503640, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1260387897491455, "global_step": 503641, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9887428283691406, "global_step": 503642, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.028110980987549, "global_step": 503643, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0665957927703857, "global_step": 503644, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.033365249633789, "global_step": 503645, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.060542583465576, "global_step": 503646, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.046480655670166, "global_step": 503647, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0846047401428223, "global_step": 503648, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0046143531799316, "global_step": 503649, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0817923545837402, "global_step": 503650, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1039040088653564, "global_step": 503651, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0394933223724365, "global_step": 503652, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.067244052886963, "global_step": 503653, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.099526882171631, "global_step": 503654, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.032910108566284, "global_step": 503655, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.106409788131714, "global_step": 503656, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.125896692276001, "global_step": 503657, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0697741508483887, "global_step": 503658, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0065903663635254, "global_step": 503659, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.047700881958008, "global_step": 503660, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1252317428588867, "global_step": 503661, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.02156138420105, "global_step": 503662, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.079280376434326, "global_step": 503663, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0610759258270264, "global_step": 503664, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9855854511260986, "global_step": 503665, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.072028636932373, "global_step": 503666, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0329267978668213, "global_step": 503667, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0701000690460205, "global_step": 503668, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.040210723876953, "global_step": 503669, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1060736179351807, "global_step": 503670, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.099113702774048, "global_step": 503671, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.095059633255005, "global_step": 503672, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.096169948577881, "global_step": 503673, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.064939260482788, "global_step": 503674, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0893800258636475, "global_step": 503675, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1269240379333496, "global_step": 503676, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1324236392974854, "global_step": 503677, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1109209060668945, "global_step": 503678, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0718846321105957, "global_step": 503679, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0814924240112305, "global_step": 503680, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9585938453674316, "global_step": 503681, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1022679805755615, "global_step": 503682, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.054537534713745, "global_step": 503683, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9936293363571167, "global_step": 503684, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0502045154571533, "global_step": 503685, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.2130789756774902, "global_step": 503686, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1007673740386963, "global_step": 503687, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9765245914459229, "global_step": 503688, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9875717163085938, "global_step": 503689, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.017244338989258, "global_step": 503690, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0856542587280273, "global_step": 503691, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.022200107574463, "global_step": 503692, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9848639965057373, "global_step": 503693, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.088318347930908, "global_step": 503694, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.052039623260498, "global_step": 503695, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1015546321868896, "global_step": 503696, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0279364585876465, "global_step": 503697, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.034644365310669, "global_step": 503698, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0564374923706055, "global_step": 503699, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9741740226745605, "global_step": 503700, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.028468608856201, "global_step": 503701, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0948781967163086, "global_step": 503702, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0996627807617188, "global_step": 503703, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.070342779159546, "global_step": 503704, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9829425811767578, "global_step": 503705, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.045927047729492, "global_step": 503706, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9557913541793823, "global_step": 503707, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0685079097747803, "global_step": 503708, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.087475061416626, "global_step": 503709, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0056264400482178, "global_step": 503710, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1376123428344727, "global_step": 503711, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.168306350708008, "global_step": 503712, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.063584804534912, "global_step": 503713, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.035651445388794, "global_step": 503714, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0424671173095703, "global_step": 503715, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.978410243988037, "global_step": 503716, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0809104442596436, "global_step": 503717, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.081052541732788, "global_step": 503718, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1439220905303955, "global_step": 503719, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.063910484313965, "global_step": 503720, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.081364631652832, "global_step": 503721, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.007258176803589, "global_step": 503722, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.977407693862915, "global_step": 503723, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0278420448303223, "global_step": 503724, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0740549564361572, "global_step": 503725, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0587685108184814, "global_step": 503726, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.079718589782715, "global_step": 503727, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.060868501663208, "global_step": 503728, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0816683769226074, "global_step": 503729, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.116382360458374, "global_step": 503730, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0787041187286377, "global_step": 503731, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0713000297546387, "global_step": 503732, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.003601551055908, "global_step": 503733, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.020815134048462, "global_step": 503734, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.096067428588867, "global_step": 503735, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0797104835510254, "global_step": 503736, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0768582820892334, "global_step": 503737, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.04150128364563, "global_step": 503738, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.998351812362671, "global_step": 503739, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0295395851135254, "global_step": 503740, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.060258388519287, "global_step": 503741, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.017481565475464, "global_step": 503742, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.031604051589966, "global_step": 503743, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.085663318634033, "global_step": 503744, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.129826784133911, "global_step": 503745, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0485761165618896, "global_step": 503746, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0526304244995117, "global_step": 503747, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.035289764404297, "global_step": 503748, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0166304111480713, "global_step": 503749, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0965914726257324, "global_step": 503750, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.095970869064331, "global_step": 503751, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.112292528152466, "global_step": 503752, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0034918785095215, "global_step": 503753, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.078461170196533, "global_step": 503754, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1070563793182373, "global_step": 503755, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0053305625915527, "global_step": 503756, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.015727996826172, "global_step": 503757, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.057800531387329, "global_step": 503758, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0388708114624023, "global_step": 503759, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.026646375656128, "global_step": 503760, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0666937828063965, "global_step": 503761, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.077425718307495, "global_step": 503762, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.130828380584717, "global_step": 503763, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0291333198547363, "global_step": 503764, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.127920627593994, "global_step": 503765, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.092989444732666, "global_step": 503766, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.043423652648926, "global_step": 503767, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.007970094680786, "global_step": 503768, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.074601650238037, "global_step": 503769, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.068308115005493, "global_step": 503770, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0782198905944824, "global_step": 503771, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.059875011444092, "global_step": 503772, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0342860221862793, "global_step": 503773, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.141615629196167, "global_step": 503774, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9860045909881592, "global_step": 503775, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0226070880889893, "global_step": 503776, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.017078161239624, "global_step": 503777, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0139269828796387, "global_step": 503778, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.064171314239502, "global_step": 503779, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.069565534591675, "global_step": 503780, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1418185234069824, "global_step": 503781, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0485031604766846, "global_step": 503782, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.123749017715454, "global_step": 503783, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0790867805480957, "global_step": 503784, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.014026641845703, "global_step": 503785, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1030797958374023, "global_step": 503786, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.079988956451416, "global_step": 503787, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.039719820022583, "global_step": 503788, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1016836166381836, "global_step": 503789, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1445605754852295, "global_step": 503790, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9722610712051392, "global_step": 503791, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0686187744140625, "global_step": 503792, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0790865421295166, "global_step": 503793, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0714666843414307, "global_step": 503794, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.98647141456604, "global_step": 503795, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.021451950073242, "global_step": 503796, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0858945846557617, "global_step": 503797, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.128697395324707, "global_step": 503798, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1388092041015625, "global_step": 503799, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0761971473693848, "global_step": 503800, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9561084508895874, "global_step": 503801, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1336309909820557, "global_step": 503802, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0800681114196777, "global_step": 503803, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9965544939041138, "global_step": 503804, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0008468627929688, "global_step": 503805, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0228936672210693, "global_step": 503806, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1416685581207275, "global_step": 503807, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.142897367477417, "global_step": 503808, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.012000322341919, "global_step": 503809, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.946516513824463, "global_step": 503810, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0218942165374756, "global_step": 503811, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0222434997558594, "global_step": 503812, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0936901569366455, "global_step": 503813, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.04423189163208, "global_step": 503814, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0245089530944824, "global_step": 503815, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.021911144256592, "global_step": 503816, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.113028049468994, "global_step": 503817, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.034466505050659, "global_step": 503818, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.023252248764038, "global_step": 503819, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0167903900146484, "global_step": 503820, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9464741945266724, "global_step": 503821, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.050747871398926, "global_step": 503822, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0443382263183594, "global_step": 503823, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0056381225585938, "global_step": 503824, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0756733417510986, "global_step": 503825, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0533416271209717, "global_step": 503826, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9492686986923218, "global_step": 503827, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.036799430847168, "global_step": 503828, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0441393852233887, "global_step": 503829, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.081493854522705, "global_step": 503830, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0568227767944336, "global_step": 503831, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.101564884185791, "global_step": 503832, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.035382032394409, "global_step": 503833, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0970630645751953, "global_step": 503834, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0184741020202637, "global_step": 503835, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9716088771820068, "global_step": 503836, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0096099376678467, "global_step": 503837, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0604145526885986, "global_step": 503838, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0118863582611084, "global_step": 503839, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0177862644195557, "global_step": 503840, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9861682653427124, "global_step": 503841, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0258569717407227, "global_step": 503842, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0224623680114746, "global_step": 503843, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1286017894744873, "global_step": 503844, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.067539930343628, "global_step": 503845, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0654618740081787, "global_step": 503846, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.04764461517334, "global_step": 503847, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.945866584777832, "global_step": 503848, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.022836446762085, "global_step": 503849, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.097975254058838, "global_step": 503850, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0626370906829834, "global_step": 503851, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.049345016479492, "global_step": 503852, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0641863346099854, "global_step": 503853, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0110561847686768, "global_step": 503854, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0074727535247803, "global_step": 503855, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0866286754608154, "global_step": 503856, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9823135137557983, "global_step": 503857, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.000835418701172, "global_step": 503858, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1108286380767822, "global_step": 503859, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0498392581939697, "global_step": 503860, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.036547899246216, "global_step": 503861, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9783145189285278, "global_step": 503862, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9149107933044434, "global_step": 503863, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0512261390686035, "global_step": 503864, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.128535747528076, "global_step": 503865, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0786995887756348, "global_step": 503866, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1413114070892334, "global_step": 503867, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.142014503479004, "global_step": 503868, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.101940155029297, "global_step": 503869, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.032195806503296, "global_step": 503870, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1219213008880615, "global_step": 503871, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.100611686706543, "global_step": 503872, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0821499824523926, "global_step": 503873, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.052464723587036, "global_step": 503874, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0272583961486816, "global_step": 503875, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9867664575576782, "global_step": 503876, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1485321521759033, "global_step": 503877, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9942210912704468, "global_step": 503878, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.087888240814209, "global_step": 503879, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.032052993774414, "global_step": 503880, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0534517765045166, "global_step": 503881, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.109478712081909, "global_step": 503882, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0513598918914795, "global_step": 503883, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.076162338256836, "global_step": 503884, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0512514114379883, "global_step": 503885, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.970005750656128, "global_step": 503886, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9979724884033203, "global_step": 503887, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.040269374847412, "global_step": 503888, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0740904808044434, "global_step": 503889, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.064248561859131, "global_step": 503890, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.155186176300049, "global_step": 503891, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.073406457901001, "global_step": 503892, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.056262254714966, "global_step": 503893, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1228082180023193, "global_step": 503894, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0013132095336914, "global_step": 503895, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.031251907348633, "global_step": 503896, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.094005584716797, "global_step": 503897, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.040545701980591, "global_step": 503898, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0011749267578125, "global_step": 503899, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0559120178222656, "global_step": 503900, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1431798934936523, "global_step": 503901, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.011681079864502, "global_step": 503902, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0880160331726074, "global_step": 503903, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0557212829589844, "global_step": 503904, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.095586061477661, "global_step": 503905, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.03617787361145, "global_step": 503906, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0614123344421387, "global_step": 503907, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.096120595932007, "global_step": 503908, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0609524250030518, "global_step": 503909, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1719398498535156, "global_step": 503910, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.07218861579895, "global_step": 503911, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0460238456726074, "global_step": 503912, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0162060260772705, "global_step": 503913, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.074418544769287, "global_step": 503914, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.124864101409912, "global_step": 503915, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1012115478515625, "global_step": 503916, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1369259357452393, "global_step": 503917, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.072483539581299, "global_step": 503918, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.080015182495117, "global_step": 503919, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.146221160888672, "global_step": 503920, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.149714946746826, "global_step": 503921, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.986507773399353, "global_step": 503922, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0702054500579834, "global_step": 503923, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.024780750274658, "global_step": 503924, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.11125111579895, "global_step": 503925, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0488038063049316, "global_step": 503926, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.029921770095825, "global_step": 503927, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.114466667175293, "global_step": 503928, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0368881225585938, "global_step": 503929, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.015807628631592, "global_step": 503930, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0746805667877197, "global_step": 503931, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.075657367706299, "global_step": 503932, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1509666442871094, "global_step": 503933, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.060833692550659, "global_step": 503934, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.074683666229248, "global_step": 503935, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0859508514404297, "global_step": 503936, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1380887031555176, "global_step": 503937, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.143679141998291, "global_step": 503938, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.019458293914795, "global_step": 503939, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.148820161819458, "global_step": 503940, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1094794273376465, "global_step": 503941, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.058149576187134, "global_step": 503942, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.095883369445801, "global_step": 503943, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0488758087158203, "global_step": 503944, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.081953763961792, "global_step": 503945, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.102015972137451, "global_step": 503946, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0958032608032227, "global_step": 503947, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0677835941314697, "global_step": 503948, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.075981616973877, "global_step": 503949, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.043487787246704, "global_step": 503950, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9474238157272339, "global_step": 503951, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0325756072998047, "global_step": 503952, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.060697555541992, "global_step": 503953, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.979341983795166, "global_step": 503954, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0429270267486572, "global_step": 503955, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.016145944595337, "global_step": 503956, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0895297527313232, "global_step": 503957, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.083174467086792, "global_step": 503958, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.036595582962036, "global_step": 503959, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.01780366897583, "global_step": 503960, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9791837930679321, "global_step": 503961, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0195600986480713, "global_step": 503962, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0688114166259766, "global_step": 503963, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.012237548828125, "global_step": 503964, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0886635780334473, "global_step": 503965, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.067300796508789, "global_step": 503966, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.953186273574829, "global_step": 503967, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1083147525787354, "global_step": 503968, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0709640979766846, "global_step": 503969, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.025970220565796, "global_step": 503970, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.060891628265381, "global_step": 503971, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9821302890777588, "global_step": 503972, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0441646575927734, "global_step": 503973, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.033010244369507, "global_step": 503974, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0522854328155518, "global_step": 503975, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.099850654602051, "global_step": 503976, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0064191818237305, "global_step": 503977, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0943470001220703, "global_step": 503978, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0479211807250977, "global_step": 503979, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0094704627990723, "global_step": 503980, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0470571517944336, "global_step": 503981, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0060372352600098, "global_step": 503982, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0951006412506104, "global_step": 503983, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.148123025894165, "global_step": 503984, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0016674995422363, "global_step": 503985, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1290125846862793, "global_step": 503986, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9703967571258545, "global_step": 503987, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.028270721435547, "global_step": 503988, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0988240242004395, "global_step": 503989, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.985610842704773, "global_step": 503990, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9822498559951782, "global_step": 503991, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0675528049468994, "global_step": 503992, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.100477695465088, "global_step": 503993, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.013307809829712, "global_step": 503994, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0753097534179688, "global_step": 503995, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9893032312393188, "global_step": 503996, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0595052242279053, "global_step": 503997, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.9829820394515991, "global_step": 503998, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0225467681884766, "global_step": 503999, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.116231679916382, "global_step": 504000, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.052804708480835, "global_step": 504001, "epoch": 869, "lr": 5e-05}
{"train_loss": 1.949600338935852, "global_step": 504002, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.030034303665161, "global_step": 504003, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0637710094451904, "global_step": 504004, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.043339252471924, "global_step": 504005, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1071581840515137, "global_step": 504006, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.1406173706054688, "global_step": 504007, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.049126148223877, "global_step": 504008, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.047513008117676, "global_step": 504009, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.026749849319458, "global_step": 504010, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0711617469787598, "global_step": 504011, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.0497543811798096, "global_step": 504012, "epoch": 869, "lr": 5e-05}
{"train_loss": 2.077829599380493, "global_step": 504013, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.077301502227783, "global_step": 504014, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0129902362823486, "global_step": 504015, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9900381565093994, "global_step": 504016, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0575640201568604, "global_step": 504017, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0127217769622803, "global_step": 504018, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0197224617004395, "global_step": 504019, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0447466373443604, "global_step": 504020, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0543651580810547, "global_step": 504021, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9756008386611938, "global_step": 504022, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0800657272338867, "global_step": 504023, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9476871490478516, "global_step": 504024, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0162477493286133, "global_step": 504025, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.067443609237671, "global_step": 504026, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.098637580871582, "global_step": 504027, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0787484645843506, "global_step": 504028, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9949077367782593, "global_step": 504029, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0263850688934326, "global_step": 504030, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0494258403778076, "global_step": 504031, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0109899044036865, "global_step": 504032, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9512907266616821, "global_step": 504033, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0500295162200928, "global_step": 504034, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9973433017730713, "global_step": 504035, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.036576747894287, "global_step": 504036, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0392332077026367, "global_step": 504037, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.940300703048706, "global_step": 504038, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1198928356170654, "global_step": 504039, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.085904598236084, "global_step": 504040, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9760159254074097, "global_step": 504041, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.06687593460083, "global_step": 504042, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.035876512527466, "global_step": 504043, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9561597108840942, "global_step": 504044, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.066359519958496, "global_step": 504045, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.163189649581909, "global_step": 504046, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0063724517822266, "global_step": 504047, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0451691150665283, "global_step": 504048, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0738515853881836, "global_step": 504049, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.081141471862793, "global_step": 504050, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.061068058013916, "global_step": 504051, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.029675006866455, "global_step": 504052, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.01220703125, "global_step": 504053, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0718986988067627, "global_step": 504054, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.067690134048462, "global_step": 504055, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1330649852752686, "global_step": 504056, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0898630619049072, "global_step": 504057, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.006105422973633, "global_step": 504058, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.045454740524292, "global_step": 504059, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9491225481033325, "global_step": 504060, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0706632137298584, "global_step": 504061, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9457353353500366, "global_step": 504062, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0837390422821045, "global_step": 504063, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0315160751342773, "global_step": 504064, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9952330589294434, "global_step": 504065, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.111231565475464, "global_step": 504066, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.078197956085205, "global_step": 504067, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9720873832702637, "global_step": 504068, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0869932174682617, "global_step": 504069, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.064924716949463, "global_step": 504070, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1176702976226807, "global_step": 504071, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1081979274749756, "global_step": 504072, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0218966007232666, "global_step": 504073, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9775480031967163, "global_step": 504074, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0172202587127686, "global_step": 504075, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0362541675567627, "global_step": 504076, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0036017894744873, "global_step": 504077, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9717926979064941, "global_step": 504078, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0234687328338623, "global_step": 504079, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1154727935791016, "global_step": 504080, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0165786743164062, "global_step": 504081, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.030245304107666, "global_step": 504082, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1053004264831543, "global_step": 504083, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.080735206604004, "global_step": 504084, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0315327644348145, "global_step": 504085, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0632166862487793, "global_step": 504086, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1451621055603027, "global_step": 504087, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0405216217041016, "global_step": 504088, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0219011306762695, "global_step": 504089, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0266408920288086, "global_step": 504090, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1110680103302, "global_step": 504091, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.069974184036255, "global_step": 504092, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9943971633911133, "global_step": 504093, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0362634658813477, "global_step": 504094, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.033804416656494, "global_step": 504095, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0249855518341064, "global_step": 504096, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0847437381744385, "global_step": 504097, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0445942878723145, "global_step": 504098, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9832954406738281, "global_step": 504099, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.015042781829834, "global_step": 504100, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.025629758834839, "global_step": 504101, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0302324295043945, "global_step": 504102, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0706663131713867, "global_step": 504103, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9126161336898804, "global_step": 504104, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0438404083251953, "global_step": 504105, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0806081295013428, "global_step": 504106, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.070824146270752, "global_step": 504107, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0070652961730957, "global_step": 504108, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0208535194396973, "global_step": 504109, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.033583164215088, "global_step": 504110, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0734500885009766, "global_step": 504111, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.014803647994995, "global_step": 504112, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.008430004119873, "global_step": 504113, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.091010570526123, "global_step": 504114, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.070507526397705, "global_step": 504115, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0544745922088623, "global_step": 504116, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.090076446533203, "global_step": 504117, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.104113817214966, "global_step": 504118, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0060391426086426, "global_step": 504119, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0459141731262207, "global_step": 504120, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0434882640838623, "global_step": 504121, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.141287088394165, "global_step": 504122, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.142181396484375, "global_step": 504123, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.029552698135376, "global_step": 504124, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0077998638153076, "global_step": 504125, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9347409009933472, "global_step": 504126, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.000389337539673, "global_step": 504127, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.998085618019104, "global_step": 504128, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9834518432617188, "global_step": 504129, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.035731792449951, "global_step": 504130, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0726125240325928, "global_step": 504131, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9427884817123413, "global_step": 504132, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.102430820465088, "global_step": 504133, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.029085874557495, "global_step": 504134, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0057947635650635, "global_step": 504135, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.083469867706299, "global_step": 504136, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.951791763305664, "global_step": 504137, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9458805322647095, "global_step": 504138, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.086923599243164, "global_step": 504139, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0093629360198975, "global_step": 504140, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.981286883354187, "global_step": 504141, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1875720024108887, "global_step": 504142, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.127000093460083, "global_step": 504143, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0060818195343018, "global_step": 504144, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.068127155303955, "global_step": 504145, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0053372383117676, "global_step": 504146, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.092593193054199, "global_step": 504147, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0828328132629395, "global_step": 504148, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.016589879989624, "global_step": 504149, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9741735458374023, "global_step": 504150, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9705657958984375, "global_step": 504151, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0722241401672363, "global_step": 504152, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.012657403945923, "global_step": 504153, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0736474990844727, "global_step": 504154, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.014787435531616, "global_step": 504155, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.075648546218872, "global_step": 504156, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.071906805038452, "global_step": 504157, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0607991218566895, "global_step": 504158, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9447274208068848, "global_step": 504159, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9643498659133911, "global_step": 504160, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0403153896331787, "global_step": 504161, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.005679130554199, "global_step": 504162, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1046767234802246, "global_step": 504163, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.059410572052002, "global_step": 504164, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.988828182220459, "global_step": 504165, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9806314706802368, "global_step": 504166, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9791350364685059, "global_step": 504167, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9983654022216797, "global_step": 504168, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0246453285217285, "global_step": 504169, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0230979919433594, "global_step": 504170, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.045254707336426, "global_step": 504171, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0171444416046143, "global_step": 504172, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0199618339538574, "global_step": 504173, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9924869537353516, "global_step": 504174, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9269599914550781, "global_step": 504175, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0762009620666504, "global_step": 504176, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.047776460647583, "global_step": 504177, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1189136505126953, "global_step": 504178, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.116509199142456, "global_step": 504179, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9389008283615112, "global_step": 504180, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0579559803009033, "global_step": 504181, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0820698738098145, "global_step": 504182, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9666626453399658, "global_step": 504183, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0294508934020996, "global_step": 504184, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.057833433151245, "global_step": 504185, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0665552616119385, "global_step": 504186, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9991050958633423, "global_step": 504187, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.054509162902832, "global_step": 504188, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0711328983306885, "global_step": 504189, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0351011753082275, "global_step": 504190, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0469229221343994, "global_step": 504191, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9741002321243286, "global_step": 504192, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0203521251678467, "global_step": 504193, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.019606351852417, "global_step": 504194, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.054161548614502, "global_step": 504195, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1133854389190674, "global_step": 504196, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0571365356445312, "global_step": 504197, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0879626274108887, "global_step": 504198, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0006189346313477, "global_step": 504199, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0260231494903564, "global_step": 504200, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9925143718719482, "global_step": 504201, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0449304580688477, "global_step": 504202, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.100435733795166, "global_step": 504203, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.003023862838745, "global_step": 504204, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.976011872291565, "global_step": 504205, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0903265476226807, "global_step": 504206, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9975332021713257, "global_step": 504207, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.046776533126831, "global_step": 504208, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.026832342147827, "global_step": 504209, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0320773124694824, "global_step": 504210, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.03643798828125, "global_step": 504211, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.006059408187866, "global_step": 504212, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.003865957260132, "global_step": 504213, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0889463424682617, "global_step": 504214, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0048372745513916, "global_step": 504215, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.049410104751587, "global_step": 504216, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.039992332458496, "global_step": 504217, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0080678462982178, "global_step": 504218, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.035447359085083, "global_step": 504219, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1070830821990967, "global_step": 504220, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.076641082763672, "global_step": 504221, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0437700748443604, "global_step": 504222, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9323312044143677, "global_step": 504223, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9705138206481934, "global_step": 504224, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0655314922332764, "global_step": 504225, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1194753646850586, "global_step": 504226, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.069891929626465, "global_step": 504227, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0167741775512695, "global_step": 504228, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0505247116088867, "global_step": 504229, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0297560691833496, "global_step": 504230, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.067537784576416, "global_step": 504231, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9905441999435425, "global_step": 504232, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0430448055267334, "global_step": 504233, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.081486463546753, "global_step": 504234, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0431673526763916, "global_step": 504235, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9396916627883911, "global_step": 504236, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0617027282714844, "global_step": 504237, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0529685020446777, "global_step": 504238, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.055685043334961, "global_step": 504239, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0195255279541016, "global_step": 504240, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0043106079101562, "global_step": 504241, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.057176113128662, "global_step": 504242, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.065185308456421, "global_step": 504243, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.078984260559082, "global_step": 504244, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0293467044830322, "global_step": 504245, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0488951206207275, "global_step": 504246, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0298941135406494, "global_step": 504247, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0805962085723877, "global_step": 504248, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.057589292526245, "global_step": 504249, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.042243719100952, "global_step": 504250, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9924468994140625, "global_step": 504251, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1239500045776367, "global_step": 504252, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.098267078399658, "global_step": 504253, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9477163553237915, "global_step": 504254, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.057182550430298, "global_step": 504255, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0087578296661377, "global_step": 504256, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0240249633789062, "global_step": 504257, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0950615406036377, "global_step": 504258, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9896622896194458, "global_step": 504259, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1094021797180176, "global_step": 504260, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0042037963867188, "global_step": 504261, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.932849645614624, "global_step": 504262, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0902228355407715, "global_step": 504263, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.091827630996704, "global_step": 504264, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0322554111480713, "global_step": 504265, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0476267337799072, "global_step": 504266, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.019174098968506, "global_step": 504267, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.067458152770996, "global_step": 504268, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0301713943481445, "global_step": 504269, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.022150754928589, "global_step": 504270, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1296839714050293, "global_step": 504271, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.04422664642334, "global_step": 504272, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0609986782073975, "global_step": 504273, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9786306619644165, "global_step": 504274, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.110408067703247, "global_step": 504275, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.013556480407715, "global_step": 504276, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9272099733352661, "global_step": 504277, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.927802324295044, "global_step": 504278, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0535244941711426, "global_step": 504279, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0437121391296387, "global_step": 504280, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.078326463699341, "global_step": 504281, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.151487350463867, "global_step": 504282, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.076854705810547, "global_step": 504283, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1017050743103027, "global_step": 504284, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.050131320953369, "global_step": 504285, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9927771091461182, "global_step": 504286, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0016462802886963, "global_step": 504287, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.039473533630371, "global_step": 504288, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.026060104370117, "global_step": 504289, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0585005283355713, "global_step": 504290, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0414271354675293, "global_step": 504291, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.007089376449585, "global_step": 504292, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0404229164123535, "global_step": 504293, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9815162420272827, "global_step": 504294, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9873878955841064, "global_step": 504295, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.008199691772461, "global_step": 504296, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.933358907699585, "global_step": 504297, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.044074773788452, "global_step": 504298, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.057454824447632, "global_step": 504299, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1005373001098633, "global_step": 504300, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0647590160369873, "global_step": 504301, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.04829740524292, "global_step": 504302, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0840070247650146, "global_step": 504303, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.996025800704956, "global_step": 504304, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0136797428131104, "global_step": 504305, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.127807855606079, "global_step": 504306, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0512588024139404, "global_step": 504307, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.10298228263855, "global_step": 504308, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0423011779785156, "global_step": 504309, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9984066486358643, "global_step": 504310, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.057729721069336, "global_step": 504311, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.037801742553711, "global_step": 504312, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0740768909454346, "global_step": 504313, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.063530683517456, "global_step": 504314, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.080660104751587, "global_step": 504315, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.069821834564209, "global_step": 504316, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9865317344665527, "global_step": 504317, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0003678798675537, "global_step": 504318, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.091513156890869, "global_step": 504319, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0557315349578857, "global_step": 504320, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0115950107574463, "global_step": 504321, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0827057361602783, "global_step": 504322, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.098708391189575, "global_step": 504323, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.018458366394043, "global_step": 504324, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.041144371032715, "global_step": 504325, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9788360595703125, "global_step": 504326, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0447897911071777, "global_step": 504327, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0827062129974365, "global_step": 504328, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.011209726333618, "global_step": 504329, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0016345977783203, "global_step": 504330, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9884995222091675, "global_step": 504331, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9250004291534424, "global_step": 504332, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.137430191040039, "global_step": 504333, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0559821128845215, "global_step": 504334, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.023181200027466, "global_step": 504335, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.065382480621338, "global_step": 504336, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.121248960494995, "global_step": 504337, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.038738965988159, "global_step": 504338, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9619349241256714, "global_step": 504339, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.034101963043213, "global_step": 504340, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0740127563476562, "global_step": 504341, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0385255813598633, "global_step": 504342, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.987636923789978, "global_step": 504343, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1135220527648926, "global_step": 504344, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.010759115219116, "global_step": 504345, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.070005416870117, "global_step": 504346, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0868606567382812, "global_step": 504347, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.109805107116699, "global_step": 504348, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0387229919433594, "global_step": 504349, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0582220554351807, "global_step": 504350, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0404212474823, "global_step": 504351, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0593173503875732, "global_step": 504352, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0843393802642822, "global_step": 504353, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0764641761779785, "global_step": 504354, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0980591773986816, "global_step": 504355, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0438308715820312, "global_step": 504356, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.943499207496643, "global_step": 504357, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1056156158447266, "global_step": 504358, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.023695230484009, "global_step": 504359, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.038045644760132, "global_step": 504360, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.045670747756958, "global_step": 504361, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0244407653808594, "global_step": 504362, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.059034824371338, "global_step": 504363, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1273725032806396, "global_step": 504364, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.084233522415161, "global_step": 504365, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0453176498413086, "global_step": 504366, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.035130023956299, "global_step": 504367, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0808796882629395, "global_step": 504368, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.03965163230896, "global_step": 504369, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0544021129608154, "global_step": 504370, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.020556926727295, "global_step": 504371, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9909849166870117, "global_step": 504372, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.072066307067871, "global_step": 504373, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9353961944580078, "global_step": 504374, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.093358278274536, "global_step": 504375, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9928946495056152, "global_step": 504376, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.078467607498169, "global_step": 504377, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.039407730102539, "global_step": 504378, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.03935170173645, "global_step": 504379, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0062384605407715, "global_step": 504380, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.059807777404785, "global_step": 504381, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9819663763046265, "global_step": 504382, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.004868745803833, "global_step": 504383, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0073256492614746, "global_step": 504384, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.051038980484009, "global_step": 504385, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1169698238372803, "global_step": 504386, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.051727294921875, "global_step": 504387, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.021576404571533, "global_step": 504388, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9526723623275757, "global_step": 504389, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.085118055343628, "global_step": 504390, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0295321941375732, "global_step": 504391, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0002055168151855, "global_step": 504392, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0063345432281494, "global_step": 504393, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0991063117980957, "global_step": 504394, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9919414520263672, "global_step": 504395, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.130826950073242, "global_step": 504396, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0180556774139404, "global_step": 504397, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1274967193603516, "global_step": 504398, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.046706438064575, "global_step": 504399, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0907113552093506, "global_step": 504400, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.087622880935669, "global_step": 504401, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9968011379241943, "global_step": 504402, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0178232192993164, "global_step": 504403, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.059114933013916, "global_step": 504404, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9710721969604492, "global_step": 504405, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1206228733062744, "global_step": 504406, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.03471040725708, "global_step": 504407, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.062154769897461, "global_step": 504408, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1337227821350098, "global_step": 504409, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9845125675201416, "global_step": 504410, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1601169109344482, "global_step": 504411, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.156090021133423, "global_step": 504412, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0470640659332275, "global_step": 504413, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.078667640686035, "global_step": 504414, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0630953311920166, "global_step": 504415, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.102569580078125, "global_step": 504416, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.037079334259033, "global_step": 504417, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.073120355606079, "global_step": 504418, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.874435305595398, "global_step": 504419, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.063932180404663, "global_step": 504420, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0286266803741455, "global_step": 504421, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0614702701568604, "global_step": 504422, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0772790908813477, "global_step": 504423, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9826804399490356, "global_step": 504424, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.098881244659424, "global_step": 504425, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0145137310028076, "global_step": 504426, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.07865571975708, "global_step": 504427, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0904483795166016, "global_step": 504428, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.067780017852783, "global_step": 504429, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9788905382156372, "global_step": 504430, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.029266834259033, "global_step": 504431, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.027045249938965, "global_step": 504432, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9216431379318237, "global_step": 504433, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.978933334350586, "global_step": 504434, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0759928226470947, "global_step": 504435, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.081275224685669, "global_step": 504436, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0544700622558594, "global_step": 504437, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0559723377227783, "global_step": 504438, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.995110273361206, "global_step": 504439, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.027153730392456, "global_step": 504440, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.132314443588257, "global_step": 504441, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1114161014556885, "global_step": 504442, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.027958393096924, "global_step": 504443, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1061818599700928, "global_step": 504444, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9816607236862183, "global_step": 504445, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.04821515083313, "global_step": 504446, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.073702335357666, "global_step": 504447, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0801987648010254, "global_step": 504448, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.019578456878662, "global_step": 504449, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0418055057525635, "global_step": 504450, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0909225940704346, "global_step": 504451, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0269765853881836, "global_step": 504452, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1137681007385254, "global_step": 504453, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.067011594772339, "global_step": 504454, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0385286808013916, "global_step": 504455, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.125171661376953, "global_step": 504456, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.011713743209839, "global_step": 504457, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.084226608276367, "global_step": 504458, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.010676145553589, "global_step": 504459, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.083655595779419, "global_step": 504460, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9957127571105957, "global_step": 504461, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0105583667755127, "global_step": 504462, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0714797973632812, "global_step": 504463, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0466995239257812, "global_step": 504464, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.027708053588867, "global_step": 504465, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0541064739227295, "global_step": 504466, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1589956283569336, "global_step": 504467, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.003089189529419, "global_step": 504468, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.145995855331421, "global_step": 504469, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.117482900619507, "global_step": 504470, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.008275270462036, "global_step": 504471, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0430150032043457, "global_step": 504472, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.056917190551758, "global_step": 504473, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.041335105895996, "global_step": 504474, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.104827880859375, "global_step": 504475, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9892505407333374, "global_step": 504476, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9937127828598022, "global_step": 504477, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.095000982284546, "global_step": 504478, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9205278158187866, "global_step": 504479, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0221750736236572, "global_step": 504480, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0286338329315186, "global_step": 504481, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0456671714782715, "global_step": 504482, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.134943723678589, "global_step": 504483, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.007344961166382, "global_step": 504484, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0960569381713867, "global_step": 504485, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.059432029724121, "global_step": 504486, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0746548175811768, "global_step": 504487, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0248146057128906, "global_step": 504488, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1683359146118164, "global_step": 504489, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.06261944770813, "global_step": 504490, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.160508871078491, "global_step": 504491, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0244665145874023, "global_step": 504492, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1015069484710693, "global_step": 504493, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0425965785980225, "global_step": 504494, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1149373054504395, "global_step": 504495, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.121934175491333, "global_step": 504496, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0317015647888184, "global_step": 504497, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0961036682128906, "global_step": 504498, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.051401376724243, "global_step": 504499, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.074115037918091, "global_step": 504500, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.037658929824829, "global_step": 504501, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0073153972625732, "global_step": 504502, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0999202728271484, "global_step": 504503, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0852746963500977, "global_step": 504504, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.121089458465576, "global_step": 504505, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.079937696456909, "global_step": 504506, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.078780174255371, "global_step": 504507, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0057272911071777, "global_step": 504508, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0167629718780518, "global_step": 504509, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.022273063659668, "global_step": 504510, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0252857208251953, "global_step": 504511, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.045624256134033, "global_step": 504512, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.105710744857788, "global_step": 504513, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.020233392715454, "global_step": 504514, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.124521017074585, "global_step": 504515, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.122105598449707, "global_step": 504516, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0561881065368652, "global_step": 504517, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.034412384033203, "global_step": 504518, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.026448965072632, "global_step": 504519, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.048513650894165, "global_step": 504520, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.076380729675293, "global_step": 504521, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.072089910507202, "global_step": 504522, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0948243141174316, "global_step": 504523, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0184261798858643, "global_step": 504524, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1431353092193604, "global_step": 504525, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0415520668029785, "global_step": 504526, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9869730472564697, "global_step": 504527, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.029318332672119, "global_step": 504528, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0385193824768066, "global_step": 504529, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.002992630004883, "global_step": 504530, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.058821439743042, "global_step": 504531, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.072455883026123, "global_step": 504532, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0616989135742188, "global_step": 504533, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0360372066497803, "global_step": 504534, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0620672702789307, "global_step": 504535, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.089668035507202, "global_step": 504536, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0516374111175537, "global_step": 504537, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0429129600524902, "global_step": 504538, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0095479488372803, "global_step": 504539, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0679409503936768, "global_step": 504540, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0647029876708984, "global_step": 504541, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0729904174804688, "global_step": 504542, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0820276737213135, "global_step": 504543, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0137548446655273, "global_step": 504544, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.087651252746582, "global_step": 504545, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.011852741241455, "global_step": 504546, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9720189571380615, "global_step": 504547, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.111783742904663, "global_step": 504548, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1081008911132812, "global_step": 504549, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0555670261383057, "global_step": 504550, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.090102195739746, "global_step": 504551, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9748839139938354, "global_step": 504552, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.03139591217041, "global_step": 504553, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.000882625579834, "global_step": 504554, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.021266460418701, "global_step": 504555, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.945681095123291, "global_step": 504556, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.097132921218872, "global_step": 504557, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9722071886062622, "global_step": 504558, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0731847286224365, "global_step": 504559, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0412402153015137, "global_step": 504560, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0814337730407715, "global_step": 504561, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9868841171264648, "global_step": 504562, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0887551307678223, "global_step": 504563, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0300536155700684, "global_step": 504564, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.988614797592163, "global_step": 504565, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.027939796447754, "global_step": 504566, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0951426029205322, "global_step": 504567, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.030089855194092, "global_step": 504568, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1137819290161133, "global_step": 504569, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1190240383148193, "global_step": 504570, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0590898990631104, "global_step": 504571, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.027651309967041, "global_step": 504572, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.103536367416382, "global_step": 504573, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0831308364868164, "global_step": 504574, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.111959457397461, "global_step": 504575, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.074713945388794, "global_step": 504576, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0758121013641357, "global_step": 504577, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9986624717712402, "global_step": 504578, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0804831981658936, "global_step": 504579, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1227385997772217, "global_step": 504580, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.021944999694824, "global_step": 504581, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.076122999191284, "global_step": 504582, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.986786127090454, "global_step": 504583, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0243961811065674, "global_step": 504584, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9973121881484985, "global_step": 504585, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1299986839294434, "global_step": 504586, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0260255336761475, "global_step": 504587, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9633301496505737, "global_step": 504588, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.005439043045044, "global_step": 504589, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.015791416168213, "global_step": 504590, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0104639530181885, "global_step": 504591, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.038799524307251, "global_step": 504592, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.118478298187256, "global_step": 504593, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0738308429718018, "global_step": 504594, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.043921947479248, "global_step": 504595, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.133235454559326, "global_step": 504596, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0516037940979004, "global_step": 504597, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1163411140441895, "global_step": 504598, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.99727463722229, "global_step": 504599, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.057905673980713, "global_step": 504600, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.118894577026367, "global_step": 504601, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.077338695526123, "global_step": 504602, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0466866493225098, "global_step": 504603, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.980525016784668, "global_step": 504604, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.177525043487549, "global_step": 504605, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0769240856170654, "global_step": 504606, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.2025530338287354, "global_step": 504607, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0634195804595947, "global_step": 504608, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.096902370452881, "global_step": 504609, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1179263591766357, "global_step": 504610, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0559020042419434, "global_step": 504611, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.047865629196167, "global_step": 504612, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9892957210540771, "global_step": 504613, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.023273468017578, "global_step": 504614, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0746266841888428, "global_step": 504615, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.043991804122925, "global_step": 504616, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0890026092529297, "global_step": 504617, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9868090152740479, "global_step": 504618, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0401933193206787, "global_step": 504619, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0264647006988525, "global_step": 504620, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.103912591934204, "global_step": 504621, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0944247245788574, "global_step": 504622, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.128950595855713, "global_step": 504623, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9993751049041748, "global_step": 504624, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.124852180480957, "global_step": 504625, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0446228981018066, "global_step": 504626, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.948540210723877, "global_step": 504627, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.06225323677063, "global_step": 504628, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0694620609283447, "global_step": 504629, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0309481620788574, "global_step": 504630, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.979020595550537, "global_step": 504631, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0951087474823, "global_step": 504632, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.993912935256958, "global_step": 504633, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0585663318634033, "global_step": 504634, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.087247133255005, "global_step": 504635, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0620696544647217, "global_step": 504636, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0822083950042725, "global_step": 504637, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.035717487335205, "global_step": 504638, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0243079662323, "global_step": 504639, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.099388837814331, "global_step": 504640, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9997503757476807, "global_step": 504641, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0345046520233154, "global_step": 504642, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0292131900787354, "global_step": 504643, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.145508289337158, "global_step": 504644, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0038938522338867, "global_step": 504645, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0875465869903564, "global_step": 504646, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.074214458465576, "global_step": 504647, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0266833305358887, "global_step": 504648, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.92771577835083, "global_step": 504649, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0044331550598145, "global_step": 504650, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0497989654541016, "global_step": 504651, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.053596019744873, "global_step": 504652, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0916121006011963, "global_step": 504653, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0378365516662598, "global_step": 504654, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1821579933166504, "global_step": 504655, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0962610244750977, "global_step": 504656, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.15236234664917, "global_step": 504657, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0989573001861572, "global_step": 504658, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0638070106506348, "global_step": 504659, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.081667900085449, "global_step": 504660, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9858027696609497, "global_step": 504661, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0291292667388916, "global_step": 504662, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0407705307006836, "global_step": 504663, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9854886531829834, "global_step": 504664, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.00292706489563, "global_step": 504665, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.021892786026001, "global_step": 504666, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.073803186416626, "global_step": 504667, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.050187110900879, "global_step": 504668, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.170442819595337, "global_step": 504669, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0808486938476562, "global_step": 504670, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1143007278442383, "global_step": 504671, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0383903980255127, "global_step": 504672, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0207157135009766, "global_step": 504673, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.037712335586548, "global_step": 504674, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.153794765472412, "global_step": 504675, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9812637567520142, "global_step": 504676, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0591516494750977, "global_step": 504677, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9946898221969604, "global_step": 504678, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0648257732391357, "global_step": 504679, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.024139881134033, "global_step": 504680, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0506789684295654, "global_step": 504681, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1306231021881104, "global_step": 504682, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.045836925506592, "global_step": 504683, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0132014751434326, "global_step": 504684, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9800465106964111, "global_step": 504685, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.088200569152832, "global_step": 504686, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.10664963722229, "global_step": 504687, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.992187261581421, "global_step": 504688, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0741305351257324, "global_step": 504689, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9882400035858154, "global_step": 504690, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0320818424224854, "global_step": 504691, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0969855785369873, "global_step": 504692, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0855002403259277, "global_step": 504693, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.065960645675659, "global_step": 504694, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0248453617095947, "global_step": 504695, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0522878170013428, "global_step": 504696, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.011631727218628, "global_step": 504697, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1596262454986572, "global_step": 504698, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1098792552948, "global_step": 504699, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0596699714660645, "global_step": 504700, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.062920093536377, "global_step": 504701, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.091662645339966, "global_step": 504702, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0840256214141846, "global_step": 504703, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0561866760253906, "global_step": 504704, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.032982110977173, "global_step": 504705, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0231235027313232, "global_step": 504706, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9193412065505981, "global_step": 504707, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1815035343170166, "global_step": 504708, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0800065994262695, "global_step": 504709, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0250232219696045, "global_step": 504710, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.04292368888855, "global_step": 504711, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.043579339981079, "global_step": 504712, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.085838794708252, "global_step": 504713, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.070267677307129, "global_step": 504714, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.017991065979004, "global_step": 504715, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.034881353378296, "global_step": 504716, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9880939722061157, "global_step": 504717, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.111159324645996, "global_step": 504718, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0956437587738037, "global_step": 504719, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.123603582382202, "global_step": 504720, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0313034057617188, "global_step": 504721, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.127723217010498, "global_step": 504722, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.143829822540283, "global_step": 504723, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0329043865203857, "global_step": 504724, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.109259605407715, "global_step": 504725, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.06577467918396, "global_step": 504726, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0732572078704834, "global_step": 504727, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0942516326904297, "global_step": 504728, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.019867181777954, "global_step": 504729, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.136742115020752, "global_step": 504730, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.975721001625061, "global_step": 504731, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.056581497192383, "global_step": 504732, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0308420658111572, "global_step": 504733, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.129408121109009, "global_step": 504734, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.050752639770508, "global_step": 504735, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0446174144744873, "global_step": 504736, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9919945001602173, "global_step": 504737, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.149386405944824, "global_step": 504738, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1407363414764404, "global_step": 504739, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0376827716827393, "global_step": 504740, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0676238536834717, "global_step": 504741, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.014683246612549, "global_step": 504742, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.131962776184082, "global_step": 504743, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0060572624206543, "global_step": 504744, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.016590118408203, "global_step": 504745, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.055232524871826, "global_step": 504746, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9651422500610352, "global_step": 504747, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.103383779525757, "global_step": 504748, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.054800510406494, "global_step": 504749, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1014702320098877, "global_step": 504750, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0021300315856934, "global_step": 504751, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0164902210235596, "global_step": 504752, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0655415058135986, "global_step": 504753, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9989118576049805, "global_step": 504754, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.05774188041687, "global_step": 504755, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0205256938934326, "global_step": 504756, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0981216430664062, "global_step": 504757, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.043367385864258, "global_step": 504758, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.045180082321167, "global_step": 504759, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9541255235671997, "global_step": 504760, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9904264211654663, "global_step": 504761, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.091348171234131, "global_step": 504762, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9968758821487427, "global_step": 504763, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.017897367477417, "global_step": 504764, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.059877872467041, "global_step": 504765, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.052201986312866, "global_step": 504766, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0573582649230957, "global_step": 504767, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.07698917388916, "global_step": 504768, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.992005467414856, "global_step": 504769, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0605950355529785, "global_step": 504770, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0781843662261963, "global_step": 504771, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1287283897399902, "global_step": 504772, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.077272891998291, "global_step": 504773, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1290969848632812, "global_step": 504774, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0856494903564453, "global_step": 504775, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.113985061645508, "global_step": 504776, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.07958984375, "global_step": 504777, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.096519708633423, "global_step": 504778, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.053079128265381, "global_step": 504779, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.083167314529419, "global_step": 504780, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9661412239074707, "global_step": 504781, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0628345012664795, "global_step": 504782, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0878190994262695, "global_step": 504783, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.070443630218506, "global_step": 504784, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1563689708709717, "global_step": 504785, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.062894105911255, "global_step": 504786, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0551629066467285, "global_step": 504787, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.995008111000061, "global_step": 504788, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.936672329902649, "global_step": 504789, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.080371856689453, "global_step": 504790, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.105254888534546, "global_step": 504791, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0630416870117188, "global_step": 504792, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.081411600112915, "global_step": 504793, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.052889823913574, "global_step": 504794, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1530542373657227, "global_step": 504795, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1005475521087646, "global_step": 504796, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0915894508361816, "global_step": 504797, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.120576858520508, "global_step": 504798, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9806355237960815, "global_step": 504799, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0907866954803467, "global_step": 504800, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.019700765609741, "global_step": 504801, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1010544300079346, "global_step": 504802, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1063644886016846, "global_step": 504803, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0625667572021484, "global_step": 504804, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0444247722625732, "global_step": 504805, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9902640581130981, "global_step": 504806, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0390501022338867, "global_step": 504807, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.018444299697876, "global_step": 504808, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0289268493652344, "global_step": 504809, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1137964725494385, "global_step": 504810, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9913554191589355, "global_step": 504811, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.997931718826294, "global_step": 504812, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0497500896453857, "global_step": 504813, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0701262950897217, "global_step": 504814, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.084423303604126, "global_step": 504815, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9877909421920776, "global_step": 504816, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1061208248138428, "global_step": 504817, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0282516479492188, "global_step": 504818, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0024750232696533, "global_step": 504819, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0401389598846436, "global_step": 504820, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0177018642425537, "global_step": 504821, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.977302074432373, "global_step": 504822, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.092487096786499, "global_step": 504823, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9763787984848022, "global_step": 504824, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0550315380096436, "global_step": 504825, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9869099855422974, "global_step": 504826, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.2014803886413574, "global_step": 504827, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0734593868255615, "global_step": 504828, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0718324184417725, "global_step": 504829, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0311150550842285, "global_step": 504830, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.023127794265747, "global_step": 504831, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.051468849182129, "global_step": 504832, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0264663696289062, "global_step": 504833, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1028828620910645, "global_step": 504834, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0277817249298096, "global_step": 504835, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.035214900970459, "global_step": 504836, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.049903154373169, "global_step": 504837, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1258368492126465, "global_step": 504838, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0055649280548096, "global_step": 504839, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.048741340637207, "global_step": 504840, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.053090810775757, "global_step": 504841, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1131834983825684, "global_step": 504842, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.069700241088867, "global_step": 504843, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1029927730560303, "global_step": 504844, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0990183353424072, "global_step": 504845, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.017184019088745, "global_step": 504846, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0506205558776855, "global_step": 504847, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.130174160003662, "global_step": 504848, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.107287645339966, "global_step": 504849, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.065718650817871, "global_step": 504850, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.056640148162842, "global_step": 504851, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0498180389404297, "global_step": 504852, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.043351411819458, "global_step": 504853, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.077690362930298, "global_step": 504854, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0779740810394287, "global_step": 504855, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.046396017074585, "global_step": 504856, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.089839220046997, "global_step": 504857, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9958451986312866, "global_step": 504858, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0784385204315186, "global_step": 504859, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.04703950881958, "global_step": 504860, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.064453125, "global_step": 504861, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9514329433441162, "global_step": 504862, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.048889636993408, "global_step": 504863, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0247273445129395, "global_step": 504864, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1014623641967773, "global_step": 504865, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1025359630584717, "global_step": 504866, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0874693393707275, "global_step": 504867, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.139601945877075, "global_step": 504868, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1326119899749756, "global_step": 504869, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1145620346069336, "global_step": 504870, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9717179536819458, "global_step": 504871, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.077047109603882, "global_step": 504872, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.117496967315674, "global_step": 504873, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0522735118865967, "global_step": 504874, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.172513008117676, "global_step": 504875, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0896644592285156, "global_step": 504876, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.993337869644165, "global_step": 504877, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0990846157073975, "global_step": 504878, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0691394805908203, "global_step": 504879, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0367650985717773, "global_step": 504880, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.067941427230835, "global_step": 504881, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0695600509643555, "global_step": 504882, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0105717182159424, "global_step": 504883, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.003361225128174, "global_step": 504884, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0428147315979004, "global_step": 504885, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0232532024383545, "global_step": 504886, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1404576301574707, "global_step": 504887, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0985844135284424, "global_step": 504888, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0715277194976807, "global_step": 504889, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0564982891082764, "global_step": 504890, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.038163661956787, "global_step": 504891, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.963668704032898, "global_step": 504892, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0442512035369873, "global_step": 504893, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.990397334098816, "global_step": 504894, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.001089334487915, "global_step": 504895, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0591490268707275, "global_step": 504896, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.989729404449463, "global_step": 504897, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.036489963531494, "global_step": 504898, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0256357192993164, "global_step": 504899, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0649213790893555, "global_step": 504900, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.024111747741699, "global_step": 504901, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9821285009384155, "global_step": 504902, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.117190361022949, "global_step": 504903, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.088017702102661, "global_step": 504904, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9906142950057983, "global_step": 504905, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.045276641845703, "global_step": 504906, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.038292169570923, "global_step": 504907, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1272025108337402, "global_step": 504908, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.025991201400757, "global_step": 504909, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0858383178710938, "global_step": 504910, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.957412838935852, "global_step": 504911, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.026163101196289, "global_step": 504912, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.046581506729126, "global_step": 504913, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0897443294525146, "global_step": 504914, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.990255355834961, "global_step": 504915, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0511691570281982, "global_step": 504916, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9558511972427368, "global_step": 504917, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0665416717529297, "global_step": 504918, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9169899225234985, "global_step": 504919, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.088862180709839, "global_step": 504920, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9979339838027954, "global_step": 504921, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0214197635650635, "global_step": 504922, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.088827133178711, "global_step": 504923, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.096129894256592, "global_step": 504924, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.035442352294922, "global_step": 504925, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0288214683532715, "global_step": 504926, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0119245052337646, "global_step": 504927, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0189268589019775, "global_step": 504928, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0717782974243164, "global_step": 504929, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1148672103881836, "global_step": 504930, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.990962266921997, "global_step": 504931, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.127009868621826, "global_step": 504932, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0747427940368652, "global_step": 504933, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0998637676239014, "global_step": 504934, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.057681083679199, "global_step": 504935, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1078667640686035, "global_step": 504936, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0785880088806152, "global_step": 504937, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.017124891281128, "global_step": 504938, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0767903327941895, "global_step": 504939, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.973931074142456, "global_step": 504940, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0125906467437744, "global_step": 504941, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.092008352279663, "global_step": 504942, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1301681995391846, "global_step": 504943, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0535268783569336, "global_step": 504944, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.988161563873291, "global_step": 504945, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.965309739112854, "global_step": 504946, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.065423011779785, "global_step": 504947, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.127129077911377, "global_step": 504948, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.031379222869873, "global_step": 504949, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0547680854797363, "global_step": 504950, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.050990104675293, "global_step": 504951, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1178693771362305, "global_step": 504952, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9814985990524292, "global_step": 504953, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0331971645355225, "global_step": 504954, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9186153411865234, "global_step": 504955, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9826874732971191, "global_step": 504956, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9650022983551025, "global_step": 504957, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9942055940628052, "global_step": 504958, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.119556427001953, "global_step": 504959, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.021838903427124, "global_step": 504960, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0896618366241455, "global_step": 504961, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.002901792526245, "global_step": 504962, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0058369636535645, "global_step": 504963, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0469400882720947, "global_step": 504964, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.012655258178711, "global_step": 504965, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.048701286315918, "global_step": 504966, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.065394639968872, "global_step": 504967, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1431186199188232, "global_step": 504968, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0205509662628174, "global_step": 504969, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0915768146514893, "global_step": 504970, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0529849529266357, "global_step": 504971, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.125563621520996, "global_step": 504972, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0018842220306396, "global_step": 504973, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.043328285217285, "global_step": 504974, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1188905239105225, "global_step": 504975, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.1195120811462402, "global_step": 504976, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.152644157409668, "global_step": 504977, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.003277063369751, "global_step": 504978, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0720438957214355, "global_step": 504979, "epoch": 870, "lr": 5e-05}
{"train_loss": 1.9722979068756104, "global_step": 504980, "epoch": 870, "lr": 5e-05}
{"train_loss": 2.0490481853485107, "global_step": 504981, "epoch": 870, "lr": 5e-05, "val_loss": 5.719595432281494, "test_reconst_mse": 0.07364454120397568}
{"train_loss": 1.9944589138031006, "global_step": 504982, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.070902109146118, "global_step": 504983, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.049121141433716, "global_step": 504984, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.001817464828491, "global_step": 504985, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0903689861297607, "global_step": 504986, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.981220006942749, "global_step": 504987, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1102941036224365, "global_step": 504988, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9891178607940674, "global_step": 504989, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0317869186401367, "global_step": 504990, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9505058526992798, "global_step": 504991, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.041133165359497, "global_step": 504992, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.131277561187744, "global_step": 504993, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0355029106140137, "global_step": 504994, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0036885738372803, "global_step": 504995, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0640954971313477, "global_step": 504996, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.123049020767212, "global_step": 504997, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0529775619506836, "global_step": 504998, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9797513484954834, "global_step": 504999, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0023000240325928, "global_step": 505000, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9566946029663086, "global_step": 505001, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0123369693756104, "global_step": 505002, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0586159229278564, "global_step": 505003, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.036210298538208, "global_step": 505004, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.998671054840088, "global_step": 505005, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0576891899108887, "global_step": 505006, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0577569007873535, "global_step": 505007, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0033998489379883, "global_step": 505008, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.01248836517334, "global_step": 505009, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0341832637786865, "global_step": 505010, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0303854942321777, "global_step": 505011, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0309767723083496, "global_step": 505012, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9420981407165527, "global_step": 505013, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.050743341445923, "global_step": 505014, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0515637397766113, "global_step": 505015, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0333290100097656, "global_step": 505016, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.041863203048706, "global_step": 505017, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.020205020904541, "global_step": 505018, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0834672451019287, "global_step": 505019, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1047868728637695, "global_step": 505020, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.020453453063965, "global_step": 505021, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.007589817047119, "global_step": 505022, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0148515701293945, "global_step": 505023, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.013845205307007, "global_step": 505024, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.059953451156616, "global_step": 505025, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.015923023223877, "global_step": 505026, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0109992027282715, "global_step": 505027, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.034576416015625, "global_step": 505028, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.024447202682495, "global_step": 505029, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0771257877349854, "global_step": 505030, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0074117183685303, "global_step": 505031, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0070834159851074, "global_step": 505032, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.041520595550537, "global_step": 505033, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0124905109405518, "global_step": 505034, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9769980907440186, "global_step": 505035, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.979193925857544, "global_step": 505036, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.97946035861969, "global_step": 505037, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0023627281188965, "global_step": 505038, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0038554668426514, "global_step": 505039, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0892345905303955, "global_step": 505040, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.055006980895996, "global_step": 505041, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.07397198677063, "global_step": 505042, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.080578327178955, "global_step": 505043, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.037519693374634, "global_step": 505044, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0335617065429688, "global_step": 505045, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9636826515197754, "global_step": 505046, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.070544719696045, "global_step": 505047, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0461955070495605, "global_step": 505048, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0872817039489746, "global_step": 505049, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9947168827056885, "global_step": 505050, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0775558948516846, "global_step": 505051, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.116020917892456, "global_step": 505052, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9887638092041016, "global_step": 505053, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.052788257598877, "global_step": 505054, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1296327114105225, "global_step": 505055, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0127828121185303, "global_step": 505056, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.099199056625366, "global_step": 505057, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9947603940963745, "global_step": 505058, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.000917673110962, "global_step": 505059, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0385472774505615, "global_step": 505060, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.071462869644165, "global_step": 505061, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0558652877807617, "global_step": 505062, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.070713758468628, "global_step": 505063, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.060532331466675, "global_step": 505064, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.057832956314087, "global_step": 505065, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1245198249816895, "global_step": 505066, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.980933427810669, "global_step": 505067, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0075125694274902, "global_step": 505068, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.024625539779663, "global_step": 505069, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0101799964904785, "global_step": 505070, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.06986927986145, "global_step": 505071, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.98967707157135, "global_step": 505072, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1034486293792725, "global_step": 505073, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0435757637023926, "global_step": 505074, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0290446281433105, "global_step": 505075, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0052857398986816, "global_step": 505076, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.09192156791687, "global_step": 505077, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0587635040283203, "global_step": 505078, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.035325527191162, "global_step": 505079, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0430915355682373, "global_step": 505080, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0710878372192383, "global_step": 505081, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.08558988571167, "global_step": 505082, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.01003098487854, "global_step": 505083, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0281240940093994, "global_step": 505084, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.038485288619995, "global_step": 505085, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.111199378967285, "global_step": 505086, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0155303478240967, "global_step": 505087, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9641393423080444, "global_step": 505088, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.081132411956787, "global_step": 505089, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.119657516479492, "global_step": 505090, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9960274696350098, "global_step": 505091, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.088216543197632, "global_step": 505092, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0057766437530518, "global_step": 505093, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.016286611557007, "global_step": 505094, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9792639017105103, "global_step": 505095, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9744393825531006, "global_step": 505096, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0047919750213623, "global_step": 505097, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1175386905670166, "global_step": 505098, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.068190574645996, "global_step": 505099, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9821275472640991, "global_step": 505100, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1385045051574707, "global_step": 505101, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0872085094451904, "global_step": 505102, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9979088306427002, "global_step": 505103, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.043912887573242, "global_step": 505104, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.081998109817505, "global_step": 505105, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0075418949127197, "global_step": 505106, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0298595428466797, "global_step": 505107, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.000183582305908, "global_step": 505108, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.064373254776001, "global_step": 505109, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0799477100372314, "global_step": 505110, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0313873291015625, "global_step": 505111, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.968311071395874, "global_step": 505112, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0927655696868896, "global_step": 505113, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9494459629058838, "global_step": 505114, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.049323797225952, "global_step": 505115, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0004687309265137, "global_step": 505116, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0436513423919678, "global_step": 505117, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0247373580932617, "global_step": 505118, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9999207258224487, "global_step": 505119, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0763988494873047, "global_step": 505120, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0386199951171875, "global_step": 505121, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0075154304504395, "global_step": 505122, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0100080966949463, "global_step": 505123, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0565309524536133, "global_step": 505124, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.04262113571167, "global_step": 505125, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.110361099243164, "global_step": 505126, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.071472406387329, "global_step": 505127, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.981113076210022, "global_step": 505128, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9979982376098633, "global_step": 505129, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0086402893066406, "global_step": 505130, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0987043380737305, "global_step": 505131, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0780863761901855, "global_step": 505132, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.172987937927246, "global_step": 505133, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9319387674331665, "global_step": 505134, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9884933233261108, "global_step": 505135, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9993914365768433, "global_step": 505136, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.977102518081665, "global_step": 505137, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.979010820388794, "global_step": 505138, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0153162479400635, "global_step": 505139, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0311100482940674, "global_step": 505140, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0538406372070312, "global_step": 505141, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.962156057357788, "global_step": 505142, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.026041030883789, "global_step": 505143, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0367884635925293, "global_step": 505144, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.072327136993408, "global_step": 505145, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1596004962921143, "global_step": 505146, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0602402687072754, "global_step": 505147, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.072476387023926, "global_step": 505148, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.016299247741699, "global_step": 505149, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9572052955627441, "global_step": 505150, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9503612518310547, "global_step": 505151, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9997717142105103, "global_step": 505152, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0366122722625732, "global_step": 505153, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0466933250427246, "global_step": 505154, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.026948928833008, "global_step": 505155, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0271449089050293, "global_step": 505156, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0691680908203125, "global_step": 505157, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9736660718917847, "global_step": 505158, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9532305002212524, "global_step": 505159, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9982211589813232, "global_step": 505160, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9060090780258179, "global_step": 505161, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0391452312469482, "global_step": 505162, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0745019912719727, "global_step": 505163, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9170314073562622, "global_step": 505164, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0365099906921387, "global_step": 505165, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0358712673187256, "global_step": 505166, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9909206628799438, "global_step": 505167, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9767059087753296, "global_step": 505168, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0360631942749023, "global_step": 505169, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1133010387420654, "global_step": 505170, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.947806715965271, "global_step": 505171, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.075225830078125, "global_step": 505172, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0377485752105713, "global_step": 505173, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.106462001800537, "global_step": 505174, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.009880304336548, "global_step": 505175, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0584969520568848, "global_step": 505176, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0326178073883057, "global_step": 505177, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0789639949798584, "global_step": 505178, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0663363933563232, "global_step": 505179, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9763299226760864, "global_step": 505180, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.163994312286377, "global_step": 505181, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0268309116363525, "global_step": 505182, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0581374168395996, "global_step": 505183, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.108848810195923, "global_step": 505184, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1162400245666504, "global_step": 505185, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0330936908721924, "global_step": 505186, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9723516702651978, "global_step": 505187, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.091542959213257, "global_step": 505188, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.072481155395508, "global_step": 505189, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.010504722595215, "global_step": 505190, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1346518993377686, "global_step": 505191, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0219004154205322, "global_step": 505192, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0045113563537598, "global_step": 505193, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0267019271850586, "global_step": 505194, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.072023391723633, "global_step": 505195, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0251717567443848, "global_step": 505196, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.064300298690796, "global_step": 505197, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0791947841644287, "global_step": 505198, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.01475191116333, "global_step": 505199, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0317423343658447, "global_step": 505200, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0178921222686768, "global_step": 505201, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.088459014892578, "global_step": 505202, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1009373664855957, "global_step": 505203, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.079967498779297, "global_step": 505204, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.063502550125122, "global_step": 505205, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.031599521636963, "global_step": 505206, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1215357780456543, "global_step": 505207, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9692840576171875, "global_step": 505208, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.039464235305786, "global_step": 505209, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0669310092926025, "global_step": 505210, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1762137413024902, "global_step": 505211, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0486268997192383, "global_step": 505212, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1023855209350586, "global_step": 505213, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.084127426147461, "global_step": 505214, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9015717506408691, "global_step": 505215, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.040423631668091, "global_step": 505216, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.132833242416382, "global_step": 505217, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.087254047393799, "global_step": 505218, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.047020673751831, "global_step": 505219, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1189043521881104, "global_step": 505220, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0720295906066895, "global_step": 505221, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0375068187713623, "global_step": 505222, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0182385444641113, "global_step": 505223, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.088554620742798, "global_step": 505224, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9724262952804565, "global_step": 505225, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0287764072418213, "global_step": 505226, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.050114631652832, "global_step": 505227, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.047107458114624, "global_step": 505228, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.10001802444458, "global_step": 505229, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.159834384918213, "global_step": 505230, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9577059745788574, "global_step": 505231, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.020533561706543, "global_step": 505232, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.048577070236206, "global_step": 505233, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0420374870300293, "global_step": 505234, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.129288911819458, "global_step": 505235, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0527255535125732, "global_step": 505236, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.172269821166992, "global_step": 505237, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.025078535079956, "global_step": 505238, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9793970584869385, "global_step": 505239, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0579593181610107, "global_step": 505240, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.041445732116699, "global_step": 505241, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1090681552886963, "global_step": 505242, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.059497117996216, "global_step": 505243, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1088175773620605, "global_step": 505244, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0644993782043457, "global_step": 505245, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0290424823760986, "global_step": 505246, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9935215711593628, "global_step": 505247, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.076852321624756, "global_step": 505248, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.082183599472046, "global_step": 505249, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9736607074737549, "global_step": 505250, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0259222984313965, "global_step": 505251, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9612221717834473, "global_step": 505252, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0744855403900146, "global_step": 505253, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.093700885772705, "global_step": 505254, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0847511291503906, "global_step": 505255, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0149405002593994, "global_step": 505256, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.104031562805176, "global_step": 505257, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.038224220275879, "global_step": 505258, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0380423069000244, "global_step": 505259, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0776782035827637, "global_step": 505260, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.165261745452881, "global_step": 505261, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0080015659332275, "global_step": 505262, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.096820116043091, "global_step": 505263, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.04840350151062, "global_step": 505264, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9955995082855225, "global_step": 505265, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.021561861038208, "global_step": 505266, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.969184160232544, "global_step": 505267, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.012624740600586, "global_step": 505268, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0720224380493164, "global_step": 505269, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9992843866348267, "global_step": 505270, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0461483001708984, "global_step": 505271, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.082888126373291, "global_step": 505272, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0536272525787354, "global_step": 505273, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.052995204925537, "global_step": 505274, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.120299816131592, "global_step": 505275, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0542190074920654, "global_step": 505276, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1015207767486572, "global_step": 505277, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.108426094055176, "global_step": 505278, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.2205183506011963, "global_step": 505279, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.084821939468384, "global_step": 505280, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9553635120391846, "global_step": 505281, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9781348705291748, "global_step": 505282, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0390522480010986, "global_step": 505283, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.056879997253418, "global_step": 505284, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.082026481628418, "global_step": 505285, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.024207592010498, "global_step": 505286, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1146390438079834, "global_step": 505287, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.064934015274048, "global_step": 505288, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0725057125091553, "global_step": 505289, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9839459657669067, "global_step": 505290, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1209914684295654, "global_step": 505291, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.051037311553955, "global_step": 505292, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0695691108703613, "global_step": 505293, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.016951322555542, "global_step": 505294, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0109057426452637, "global_step": 505295, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.999606728553772, "global_step": 505296, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.072011709213257, "global_step": 505297, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9907710552215576, "global_step": 505298, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0881683826446533, "global_step": 505299, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.126685857772827, "global_step": 505300, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.06801700592041, "global_step": 505301, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.09834361076355, "global_step": 505302, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0230138301849365, "global_step": 505303, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0272696018218994, "global_step": 505304, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.2060489654541016, "global_step": 505305, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.114957332611084, "global_step": 505306, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.035611391067505, "global_step": 505307, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0173988342285156, "global_step": 505308, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.083832025527954, "global_step": 505309, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0802855491638184, "global_step": 505310, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0044708251953125, "global_step": 505311, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1095707416534424, "global_step": 505312, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1123716831207275, "global_step": 505313, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.966668725013733, "global_step": 505314, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.040203809738159, "global_step": 505315, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.064295768737793, "global_step": 505316, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0711703300476074, "global_step": 505317, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0401556491851807, "global_step": 505318, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0014255046844482, "global_step": 505319, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.052816867828369, "global_step": 505320, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.077211856842041, "global_step": 505321, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0196096897125244, "global_step": 505322, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.090688705444336, "global_step": 505323, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0273847579956055, "global_step": 505324, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.042713165283203, "global_step": 505325, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9227112531661987, "global_step": 505326, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0144522190093994, "global_step": 505327, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0855042934417725, "global_step": 505328, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1132912635803223, "global_step": 505329, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.009061813354492, "global_step": 505330, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.073032855987549, "global_step": 505331, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.955991268157959, "global_step": 505332, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0803287029266357, "global_step": 505333, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.015828847885132, "global_step": 505334, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9808337688446045, "global_step": 505335, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9931626319885254, "global_step": 505336, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9074233770370483, "global_step": 505337, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1292011737823486, "global_step": 505338, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0298023223876953, "global_step": 505339, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0701637268066406, "global_step": 505340, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1034507751464844, "global_step": 505341, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1131675243377686, "global_step": 505342, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9949674606323242, "global_step": 505343, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9809634685516357, "global_step": 505344, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0446887016296387, "global_step": 505345, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1464991569519043, "global_step": 505346, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9935258626937866, "global_step": 505347, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0110251903533936, "global_step": 505348, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.009840488433838, "global_step": 505349, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0301733016967773, "global_step": 505350, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0736165046691895, "global_step": 505351, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.036935806274414, "global_step": 505352, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0600006580352783, "global_step": 505353, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0148813724517822, "global_step": 505354, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9912339448928833, "global_step": 505355, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0593669414520264, "global_step": 505356, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.049708127975464, "global_step": 505357, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.032255172729492, "global_step": 505358, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.053635358810425, "global_step": 505359, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.080510139465332, "global_step": 505360, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0313496589660645, "global_step": 505361, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0712363719940186, "global_step": 505362, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9910402297973633, "global_step": 505363, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1228585243225098, "global_step": 505364, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9750428199768066, "global_step": 505365, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0808024406433105, "global_step": 505366, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.064779758453369, "global_step": 505367, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0989158153533936, "global_step": 505368, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.008927345275879, "global_step": 505369, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9566664695739746, "global_step": 505370, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9595297574996948, "global_step": 505371, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.090451240539551, "global_step": 505372, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9975435733795166, "global_step": 505373, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9774971008300781, "global_step": 505374, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.068838357925415, "global_step": 505375, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.8768959045410156, "global_step": 505376, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0844156742095947, "global_step": 505377, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.083347797393799, "global_step": 505378, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9998193979263306, "global_step": 505379, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.117051601409912, "global_step": 505380, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1191160678863525, "global_step": 505381, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9148907661437988, "global_step": 505382, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.065587282180786, "global_step": 505383, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0567500591278076, "global_step": 505384, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.095463991165161, "global_step": 505385, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9621027708053589, "global_step": 505386, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.078974962234497, "global_step": 505387, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.067387342453003, "global_step": 505388, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.118698835372925, "global_step": 505389, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0334503650665283, "global_step": 505390, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9926090240478516, "global_step": 505391, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.015641450881958, "global_step": 505392, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1038291454315186, "global_step": 505393, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.020275831222534, "global_step": 505394, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0668082237243652, "global_step": 505395, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.09567928314209, "global_step": 505396, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0072057247161865, "global_step": 505397, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0267958641052246, "global_step": 505398, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.040682792663574, "global_step": 505399, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9916739463806152, "global_step": 505400, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1008706092834473, "global_step": 505401, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9989571571350098, "global_step": 505402, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0601749420166016, "global_step": 505403, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.104198455810547, "global_step": 505404, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0837936401367188, "global_step": 505405, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0579710006713867, "global_step": 505406, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0838913917541504, "global_step": 505407, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9960145950317383, "global_step": 505408, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0086097717285156, "global_step": 505409, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9904628992080688, "global_step": 505410, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1087474822998047, "global_step": 505411, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.059342622756958, "global_step": 505412, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9405831098556519, "global_step": 505413, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.089210271835327, "global_step": 505414, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.176638126373291, "global_step": 505415, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0304980278015137, "global_step": 505416, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.052441120147705, "global_step": 505417, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1182990074157715, "global_step": 505418, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0928804874420166, "global_step": 505419, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0214264392852783, "global_step": 505420, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.109462261199951, "global_step": 505421, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9733140468597412, "global_step": 505422, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9775841236114502, "global_step": 505423, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.077406644821167, "global_step": 505424, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9930977821350098, "global_step": 505425, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9859908819198608, "global_step": 505426, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1169509887695312, "global_step": 505427, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.153592348098755, "global_step": 505428, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.106489896774292, "global_step": 505429, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0265932083129883, "global_step": 505430, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0153517723083496, "global_step": 505431, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.973165512084961, "global_step": 505432, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9437921047210693, "global_step": 505433, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0448999404907227, "global_step": 505434, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0474185943603516, "global_step": 505435, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0487992763519287, "global_step": 505436, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.031022787094116, "global_step": 505437, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.959913969039917, "global_step": 505438, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.031987190246582, "global_step": 505439, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0509390830993652, "global_step": 505440, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.04415225982666, "global_step": 505441, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1455881595611572, "global_step": 505442, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.010664463043213, "global_step": 505443, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9750958681106567, "global_step": 505444, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0794777870178223, "global_step": 505445, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1673691272735596, "global_step": 505446, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.044740676879883, "global_step": 505447, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0159168243408203, "global_step": 505448, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.024341106414795, "global_step": 505449, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0204689502716064, "global_step": 505450, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0314126014709473, "global_step": 505451, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0576021671295166, "global_step": 505452, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1970949172973633, "global_step": 505453, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0596485137939453, "global_step": 505454, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0308427810668945, "global_step": 505455, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0856258869171143, "global_step": 505456, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0456254482269287, "global_step": 505457, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0301003456115723, "global_step": 505458, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1094675064086914, "global_step": 505459, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.071153163909912, "global_step": 505460, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0810184478759766, "global_step": 505461, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0780892372131348, "global_step": 505462, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.027514934539795, "global_step": 505463, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9833533763885498, "global_step": 505464, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0229225158691406, "global_step": 505465, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1103813648223877, "global_step": 505466, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9961236715316772, "global_step": 505467, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0345051288604736, "global_step": 505468, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.128366470336914, "global_step": 505469, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0749733448028564, "global_step": 505470, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0802958011627197, "global_step": 505471, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.065563201904297, "global_step": 505472, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0425631999969482, "global_step": 505473, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9776748418807983, "global_step": 505474, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0471346378326416, "global_step": 505475, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.159456729888916, "global_step": 505476, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0138297080993652, "global_step": 505477, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0251102447509766, "global_step": 505478, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9355213642120361, "global_step": 505479, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0581042766571045, "global_step": 505480, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.018676280975342, "global_step": 505481, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0680060386657715, "global_step": 505482, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.068634271621704, "global_step": 505483, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0103507041931152, "global_step": 505484, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.01770281791687, "global_step": 505485, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0763936042785645, "global_step": 505486, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0373849868774414, "global_step": 505487, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.132572650909424, "global_step": 505488, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0279924869537354, "global_step": 505489, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9852325916290283, "global_step": 505490, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0078530311584473, "global_step": 505491, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0925207138061523, "global_step": 505492, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0168213844299316, "global_step": 505493, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9907968044281006, "global_step": 505494, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0795812606811523, "global_step": 505495, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.122375965118408, "global_step": 505496, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0240468978881836, "global_step": 505497, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0746572017669678, "global_step": 505498, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.984150767326355, "global_step": 505499, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.017831325531006, "global_step": 505500, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.050222158432007, "global_step": 505501, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0724668502807617, "global_step": 505502, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0193397998809814, "global_step": 505503, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.02683687210083, "global_step": 505504, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.045475959777832, "global_step": 505505, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.035287380218506, "global_step": 505506, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.030608892440796, "global_step": 505507, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.079521656036377, "global_step": 505508, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.074984312057495, "global_step": 505509, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.020536184310913, "global_step": 505510, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9803656339645386, "global_step": 505511, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.088196039199829, "global_step": 505512, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0582804679870605, "global_step": 505513, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9341086149215698, "global_step": 505514, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1097617149353027, "global_step": 505515, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1270623207092285, "global_step": 505516, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0714409351348877, "global_step": 505517, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.060750722885132, "global_step": 505518, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0741634368896484, "global_step": 505519, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0586776733398438, "global_step": 505520, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.120328903198242, "global_step": 505521, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1411094665527344, "global_step": 505522, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0038654804229736, "global_step": 505523, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.165912389755249, "global_step": 505524, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.072554349899292, "global_step": 505525, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0514514446258545, "global_step": 505526, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.004526376724243, "global_step": 505527, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.049412250518799, "global_step": 505528, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.075324296951294, "global_step": 505529, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0387332439422607, "global_step": 505530, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0090696811676025, "global_step": 505531, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0442581176757812, "global_step": 505532, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0308194160461426, "global_step": 505533, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0886459350585938, "global_step": 505534, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0969250202178955, "global_step": 505535, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9842820167541504, "global_step": 505536, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1482269763946533, "global_step": 505537, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0359678268432617, "global_step": 505538, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.048128843307495, "global_step": 505539, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.086200714111328, "global_step": 505540, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.022489547729492, "global_step": 505541, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0415573120117188, "global_step": 505542, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0553295612335205, "global_step": 505543, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0105738639831543, "global_step": 505544, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.033393383026123, "global_step": 505545, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0551247596740723, "global_step": 505546, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.986169457435608, "global_step": 505547, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1279566287994385, "global_step": 505548, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.033482313156128, "global_step": 505549, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0790352821350098, "global_step": 505550, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.015878200531006, "global_step": 505551, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1125094890594482, "global_step": 505552, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.030409574508667, "global_step": 505553, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0228288173675537, "global_step": 505554, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0532004833221436, "global_step": 505555, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.113041877746582, "global_step": 505556, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.085905075073242, "global_step": 505557, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1099026203155518, "global_step": 505558, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0204384326934814, "global_step": 505559, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1044435501098633, "global_step": 505560, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9796249866485596, "global_step": 505561, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0706546306610107, "global_step": 505562, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.059143304824829, "global_step": 505563, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1600887775421143, "global_step": 505564, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9968793392181396, "global_step": 505565, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1084797382354736, "global_step": 505566, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0880203247070312, "global_step": 505567, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.026503562927246, "global_step": 505568, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9750182628631592, "global_step": 505569, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0845954418182373, "global_step": 505570, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0407016277313232, "global_step": 505571, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.044515371322632, "global_step": 505572, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0724520683288574, "global_step": 505573, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0613057613372803, "global_step": 505574, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.171543598175049, "global_step": 505575, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0255908966064453, "global_step": 505576, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0820415019989014, "global_step": 505577, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1083154678344727, "global_step": 505578, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.043663263320923, "global_step": 505579, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1019508838653564, "global_step": 505580, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0580129623413086, "global_step": 505581, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.008199453353882, "global_step": 505582, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0275092124938965, "global_step": 505583, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.958114743232727, "global_step": 505584, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1009883880615234, "global_step": 505585, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.062802791595459, "global_step": 505586, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1324291229248047, "global_step": 505587, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0288171768188477, "global_step": 505588, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0482609272003174, "global_step": 505589, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1250345706939697, "global_step": 505590, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0478720664978027, "global_step": 505591, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9848605394363403, "global_step": 505592, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.079289436340332, "global_step": 505593, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.052511215209961, "global_step": 505594, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1151533126831055, "global_step": 505595, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1421351432800293, "global_step": 505596, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1172478199005127, "global_step": 505597, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0334644317626953, "global_step": 505598, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0060534477233887, "global_step": 505599, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0310678482055664, "global_step": 505600, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0429887771606445, "global_step": 505601, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.036212921142578, "global_step": 505602, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0894033908843994, "global_step": 505603, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0616400241851807, "global_step": 505604, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.133770227432251, "global_step": 505605, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1207945346832275, "global_step": 505606, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.010878324508667, "global_step": 505607, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.03055739402771, "global_step": 505608, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0755672454833984, "global_step": 505609, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.022268772125244, "global_step": 505610, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1122896671295166, "global_step": 505611, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9504716396331787, "global_step": 505612, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.058476209640503, "global_step": 505613, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0134823322296143, "global_step": 505614, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0060436725616455, "global_step": 505615, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0639114379882812, "global_step": 505616, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.031839370727539, "global_step": 505617, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.005432605743408, "global_step": 505618, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0558297634124756, "global_step": 505619, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.117286205291748, "global_step": 505620, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1296465396881104, "global_step": 505621, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0700337886810303, "global_step": 505622, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.041569948196411, "global_step": 505623, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0330917835235596, "global_step": 505624, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.083601713180542, "global_step": 505625, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0825114250183105, "global_step": 505626, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.023101568222046, "global_step": 505627, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.097028970718384, "global_step": 505628, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9768575429916382, "global_step": 505629, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9930446147918701, "global_step": 505630, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.051657199859619, "global_step": 505631, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0543971061706543, "global_step": 505632, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.071524143218994, "global_step": 505633, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0296244621276855, "global_step": 505634, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0060884952545166, "global_step": 505635, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.016366720199585, "global_step": 505636, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.074265718460083, "global_step": 505637, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0812008380889893, "global_step": 505638, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.089841365814209, "global_step": 505639, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0261306762695312, "global_step": 505640, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9900944232940674, "global_step": 505641, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0275356769561768, "global_step": 505642, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0600745677948, "global_step": 505643, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.069160223007202, "global_step": 505644, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.065277099609375, "global_step": 505645, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.074251174926758, "global_step": 505646, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0543601512908936, "global_step": 505647, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0194337368011475, "global_step": 505648, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.084900140762329, "global_step": 505649, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0230510234832764, "global_step": 505650, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9654268026351929, "global_step": 505651, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.045769214630127, "global_step": 505652, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.995908498764038, "global_step": 505653, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0040037631988525, "global_step": 505654, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0078346729278564, "global_step": 505655, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1101975440979004, "global_step": 505656, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0410923957824707, "global_step": 505657, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.125744581222534, "global_step": 505658, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.118694305419922, "global_step": 505659, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1065540313720703, "global_step": 505660, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.997527003288269, "global_step": 505661, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0832161903381348, "global_step": 505662, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0294010639190674, "global_step": 505663, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0046706199645996, "global_step": 505664, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0716662406921387, "global_step": 505665, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.075432538986206, "global_step": 505666, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.066753625869751, "global_step": 505667, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0186991691589355, "global_step": 505668, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9820805788040161, "global_step": 505669, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0423223972320557, "global_step": 505670, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0130209922790527, "global_step": 505671, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0329225063323975, "global_step": 505672, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.12211275100708, "global_step": 505673, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.058101177215576, "global_step": 505674, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0680298805236816, "global_step": 505675, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.067176342010498, "global_step": 505676, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.036658525466919, "global_step": 505677, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.032031297683716, "global_step": 505678, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.055337429046631, "global_step": 505679, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0217370986938477, "global_step": 505680, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0438101291656494, "global_step": 505681, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0329277515411377, "global_step": 505682, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1248745918273926, "global_step": 505683, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.026620388031006, "global_step": 505684, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0751359462738037, "global_step": 505685, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.982253909111023, "global_step": 505686, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.108128786087036, "global_step": 505687, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.110401153564453, "global_step": 505688, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.213545799255371, "global_step": 505689, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.114595890045166, "global_step": 505690, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.006758213043213, "global_step": 505691, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0827794075012207, "global_step": 505692, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0219826698303223, "global_step": 505693, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.052711248397827, "global_step": 505694, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1006691455841064, "global_step": 505695, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.074716806411743, "global_step": 505696, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9450472593307495, "global_step": 505697, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1396589279174805, "global_step": 505698, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.035003900527954, "global_step": 505699, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.065890312194824, "global_step": 505700, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.068366765975952, "global_step": 505701, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0367133617401123, "global_step": 505702, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0592808723449707, "global_step": 505703, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9685524702072144, "global_step": 505704, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0228524208068848, "global_step": 505705, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0416109561920166, "global_step": 505706, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.059638261795044, "global_step": 505707, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0250368118286133, "global_step": 505708, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.101822853088379, "global_step": 505709, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.056744337081909, "global_step": 505710, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0492823123931885, "global_step": 505711, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.089287519454956, "global_step": 505712, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0542333126068115, "global_step": 505713, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.028186798095703, "global_step": 505714, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.017582416534424, "global_step": 505715, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1375532150268555, "global_step": 505716, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0360777378082275, "global_step": 505717, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.016514539718628, "global_step": 505718, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.030942916870117, "global_step": 505719, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1516501903533936, "global_step": 505720, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.105630397796631, "global_step": 505721, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0647478103637695, "global_step": 505722, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0592598915100098, "global_step": 505723, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9991189241409302, "global_step": 505724, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.024954080581665, "global_step": 505725, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.880719542503357, "global_step": 505726, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0567448139190674, "global_step": 505727, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1629319190979004, "global_step": 505728, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.066821575164795, "global_step": 505729, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9974466562271118, "global_step": 505730, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0833001136779785, "global_step": 505731, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0074121952056885, "global_step": 505732, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9636893272399902, "global_step": 505733, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9879471063613892, "global_step": 505734, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0277349948883057, "global_step": 505735, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.117659568786621, "global_step": 505736, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1420910358428955, "global_step": 505737, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.039808511734009, "global_step": 505738, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9965184926986694, "global_step": 505739, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.071075439453125, "global_step": 505740, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.017096757888794, "global_step": 505741, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.034043788909912, "global_step": 505742, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1592698097229004, "global_step": 505743, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0417959690093994, "global_step": 505744, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.114593267440796, "global_step": 505745, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.060422420501709, "global_step": 505746, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.000361204147339, "global_step": 505747, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0519025325775146, "global_step": 505748, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9537107944488525, "global_step": 505749, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.978245735168457, "global_step": 505750, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0298573970794678, "global_step": 505751, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.034588575363159, "global_step": 505752, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0730323791503906, "global_step": 505753, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.960221529006958, "global_step": 505754, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9803746938705444, "global_step": 505755, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.012784242630005, "global_step": 505756, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0895676612854004, "global_step": 505757, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1029155254364014, "global_step": 505758, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0475480556488037, "global_step": 505759, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0384654998779297, "global_step": 505760, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.117793560028076, "global_step": 505761, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9929612874984741, "global_step": 505762, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.104539632797241, "global_step": 505763, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1010255813598633, "global_step": 505764, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0570521354675293, "global_step": 505765, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9978686571121216, "global_step": 505766, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0468993186950684, "global_step": 505767, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.053757905960083, "global_step": 505768, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0428836345672607, "global_step": 505769, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0173816680908203, "global_step": 505770, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.076992988586426, "global_step": 505771, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.022184133529663, "global_step": 505772, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0609748363494873, "global_step": 505773, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.094822883605957, "global_step": 505774, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1023054122924805, "global_step": 505775, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.064682722091675, "global_step": 505776, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.058444023132324, "global_step": 505777, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.066793441772461, "global_step": 505778, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1024653911590576, "global_step": 505779, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0167133808135986, "global_step": 505780, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0851356983184814, "global_step": 505781, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9904941320419312, "global_step": 505782, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0914907455444336, "global_step": 505783, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.054884195327759, "global_step": 505784, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9893078804016113, "global_step": 505785, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9022631645202637, "global_step": 505786, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.055375814437866, "global_step": 505787, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1156623363494873, "global_step": 505788, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.006169080734253, "global_step": 505789, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.056027412414551, "global_step": 505790, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0562283992767334, "global_step": 505791, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9910801649093628, "global_step": 505792, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.076301097869873, "global_step": 505793, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.004214286804199, "global_step": 505794, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.009827136993408, "global_step": 505795, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1039552688598633, "global_step": 505796, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0515098571777344, "global_step": 505797, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0250062942504883, "global_step": 505798, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.083571434020996, "global_step": 505799, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0731968879699707, "global_step": 505800, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0580811500549316, "global_step": 505801, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1396071910858154, "global_step": 505802, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.092313289642334, "global_step": 505803, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0749881267547607, "global_step": 505804, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0954971313476562, "global_step": 505805, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0713226795196533, "global_step": 505806, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9823745489120483, "global_step": 505807, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.063521385192871, "global_step": 505808, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0881268978118896, "global_step": 505809, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0584850311279297, "global_step": 505810, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0729527473449707, "global_step": 505811, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1341445446014404, "global_step": 505812, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0577902793884277, "global_step": 505813, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0057015419006348, "global_step": 505814, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9791386127471924, "global_step": 505815, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0320544242858887, "global_step": 505816, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.117332935333252, "global_step": 505817, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.145677328109741, "global_step": 505818, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.085120916366577, "global_step": 505819, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0702743530273438, "global_step": 505820, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1735281944274902, "global_step": 505821, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.070695638656616, "global_step": 505822, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9959478378295898, "global_step": 505823, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.034402370452881, "global_step": 505824, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.999511480331421, "global_step": 505825, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9964519739151, "global_step": 505826, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0925309658050537, "global_step": 505827, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0637662410736084, "global_step": 505828, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.11657977104187, "global_step": 505829, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.035573959350586, "global_step": 505830, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0982325077056885, "global_step": 505831, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.056004524230957, "global_step": 505832, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.019841432571411, "global_step": 505833, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0065183639526367, "global_step": 505834, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0018515586853027, "global_step": 505835, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.056905746459961, "global_step": 505836, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1095938682556152, "global_step": 505837, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.025570869445801, "global_step": 505838, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0369932651519775, "global_step": 505839, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0201778411865234, "global_step": 505840, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9506018161773682, "global_step": 505841, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1079137325286865, "global_step": 505842, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.081134080886841, "global_step": 505843, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0425732135772705, "global_step": 505844, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.02567458152771, "global_step": 505845, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0748941898345947, "global_step": 505846, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0143799781799316, "global_step": 505847, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1155972480773926, "global_step": 505848, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.042050361633301, "global_step": 505849, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.049546957015991, "global_step": 505850, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1110002994537354, "global_step": 505851, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0160884857177734, "global_step": 505852, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.039290189743042, "global_step": 505853, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9866715669631958, "global_step": 505854, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0179178714752197, "global_step": 505855, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.091630458831787, "global_step": 505856, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0577166080474854, "global_step": 505857, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.048710584640503, "global_step": 505858, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9894084930419922, "global_step": 505859, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.109485149383545, "global_step": 505860, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9778475761413574, "global_step": 505861, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0604305267333984, "global_step": 505862, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.089999198913574, "global_step": 505863, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1294617652893066, "global_step": 505864, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9265309572219849, "global_step": 505865, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0844314098358154, "global_step": 505866, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0136334896087646, "global_step": 505867, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0968897342681885, "global_step": 505868, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.048846960067749, "global_step": 505869, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9813040494918823, "global_step": 505870, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1150567531585693, "global_step": 505871, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.959895133972168, "global_step": 505872, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0136032104492188, "global_step": 505873, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9713518619537354, "global_step": 505874, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.988876223564148, "global_step": 505875, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0722286701202393, "global_step": 505876, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0425329208374023, "global_step": 505877, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.041707992553711, "global_step": 505878, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1123313903808594, "global_step": 505879, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.057036876678467, "global_step": 505880, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0827622413635254, "global_step": 505881, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.957974910736084, "global_step": 505882, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0325253009796143, "global_step": 505883, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9805808067321777, "global_step": 505884, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1082637310028076, "global_step": 505885, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.034228801727295, "global_step": 505886, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.104600191116333, "global_step": 505887, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0748538970947266, "global_step": 505888, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.015441417694092, "global_step": 505889, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.096743583679199, "global_step": 505890, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0670409202575684, "global_step": 505891, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.06864595413208, "global_step": 505892, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0447511672973633, "global_step": 505893, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0510075092315674, "global_step": 505894, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.110576629638672, "global_step": 505895, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0359787940979004, "global_step": 505896, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.044896364212036, "global_step": 505897, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.148881673812866, "global_step": 505898, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.088189125061035, "global_step": 505899, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9602822065353394, "global_step": 505900, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0152533054351807, "global_step": 505901, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.089017629623413, "global_step": 505902, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0447845458984375, "global_step": 505903, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.044180393218994, "global_step": 505904, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.145681619644165, "global_step": 505905, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1425862312316895, "global_step": 505906, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.055994749069214, "global_step": 505907, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0589141845703125, "global_step": 505908, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.124423027038574, "global_step": 505909, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0658419132232666, "global_step": 505910, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9968007802963257, "global_step": 505911, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.080674648284912, "global_step": 505912, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.035639762878418, "global_step": 505913, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.059523582458496, "global_step": 505914, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0020978450775146, "global_step": 505915, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0892579555511475, "global_step": 505916, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1254475116729736, "global_step": 505917, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0913562774658203, "global_step": 505918, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0742714405059814, "global_step": 505919, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0172297954559326, "global_step": 505920, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0536091327667236, "global_step": 505921, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.119034767150879, "global_step": 505922, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0139591693878174, "global_step": 505923, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.175309419631958, "global_step": 505924, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0609915256500244, "global_step": 505925, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0959839820861816, "global_step": 505926, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0756995677948, "global_step": 505927, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.044558048248291, "global_step": 505928, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.067030191421509, "global_step": 505929, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0883936882019043, "global_step": 505930, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1667182445526123, "global_step": 505931, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0658926963806152, "global_step": 505932, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.098877429962158, "global_step": 505933, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.096334218978882, "global_step": 505934, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.051833391189575, "global_step": 505935, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.031214952468872, "global_step": 505936, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.035966396331787, "global_step": 505937, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.038215160369873, "global_step": 505938, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9717735052108765, "global_step": 505939, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.143953561782837, "global_step": 505940, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0718531608581543, "global_step": 505941, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.120967388153076, "global_step": 505942, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9837968349456787, "global_step": 505943, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.016903877258301, "global_step": 505944, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.0280141830444336, "global_step": 505945, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.025836706161499, "global_step": 505946, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.020437479019165, "global_step": 505947, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.1519391536712646, "global_step": 505948, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.144885301589966, "global_step": 505949, "epoch": 871, "lr": 5e-05}
{"train_loss": 2.048800468444824, "global_step": 505950, "epoch": 871, "lr": 5e-05}
{"train_loss": 1.9370192289352417, "global_step": 505951, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0587973594665527, "global_step": 505952, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0014545917510986, "global_step": 505953, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0157179832458496, "global_step": 505954, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0065388679504395, "global_step": 505955, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0203027725219727, "global_step": 505956, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.056245803833008, "global_step": 505957, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.012389898300171, "global_step": 505958, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0995326042175293, "global_step": 505959, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9833801984786987, "global_step": 505960, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9881387948989868, "global_step": 505961, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0363094806671143, "global_step": 505962, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.978716254234314, "global_step": 505963, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0248708724975586, "global_step": 505964, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9884215593338013, "global_step": 505965, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.081268072128296, "global_step": 505966, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9814774990081787, "global_step": 505967, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9674025774002075, "global_step": 505968, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.066636562347412, "global_step": 505969, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.052035331726074, "global_step": 505970, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9733479022979736, "global_step": 505971, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.026620388031006, "global_step": 505972, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9344935417175293, "global_step": 505973, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.920375943183899, "global_step": 505974, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0416908264160156, "global_step": 505975, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0893514156341553, "global_step": 505976, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9675840139389038, "global_step": 505977, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.982755422592163, "global_step": 505978, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0750341415405273, "global_step": 505979, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9822883605957031, "global_step": 505980, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.014979124069214, "global_step": 505981, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0915122032165527, "global_step": 505982, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.05849552154541, "global_step": 505983, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.999865174293518, "global_step": 505984, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.092308759689331, "global_step": 505985, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.977123498916626, "global_step": 505986, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9582674503326416, "global_step": 505987, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.023092746734619, "global_step": 505988, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9884005784988403, "global_step": 505989, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0810511112213135, "global_step": 505990, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9988974332809448, "global_step": 505991, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.980792760848999, "global_step": 505992, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0229647159576416, "global_step": 505993, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.098207950592041, "global_step": 505994, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.034583806991577, "global_step": 505995, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1211349964141846, "global_step": 505996, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.041452407836914, "global_step": 505997, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0412352085113525, "global_step": 505998, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.018080711364746, "global_step": 505999, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.038562536239624, "global_step": 506000, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9653010368347168, "global_step": 506001, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.975039005279541, "global_step": 506002, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0308141708374023, "global_step": 506003, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9597715139389038, "global_step": 506004, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0688140392303467, "global_step": 506005, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0005767345428467, "global_step": 506006, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.057466506958008, "global_step": 506007, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.092827320098877, "global_step": 506008, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9967695474624634, "global_step": 506009, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0086512565612793, "global_step": 506010, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.043285608291626, "global_step": 506011, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.046074390411377, "global_step": 506012, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0942718982696533, "global_step": 506013, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0231270790100098, "global_step": 506014, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0353636741638184, "global_step": 506015, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0214734077453613, "global_step": 506016, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.063044309616089, "global_step": 506017, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0155556201934814, "global_step": 506018, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1179606914520264, "global_step": 506019, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.092970609664917, "global_step": 506020, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.009936571121216, "global_step": 506021, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0042738914489746, "global_step": 506022, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.041097640991211, "global_step": 506023, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.010629653930664, "global_step": 506024, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0791351795196533, "global_step": 506025, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1149730682373047, "global_step": 506026, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.972583532333374, "global_step": 506027, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.027916669845581, "global_step": 506028, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1125857830047607, "global_step": 506029, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0186948776245117, "global_step": 506030, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9868900775909424, "global_step": 506031, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0117642879486084, "global_step": 506032, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0461483001708984, "global_step": 506033, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.16367244720459, "global_step": 506034, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.968666672706604, "global_step": 506035, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0774855613708496, "global_step": 506036, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.025996685028076, "global_step": 506037, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0674326419830322, "global_step": 506038, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.068066358566284, "global_step": 506039, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9940487146377563, "global_step": 506040, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0612854957580566, "global_step": 506041, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.095895290374756, "global_step": 506042, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.100742816925049, "global_step": 506043, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0946671962738037, "global_step": 506044, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.128203868865967, "global_step": 506045, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.051401138305664, "global_step": 506046, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1034443378448486, "global_step": 506047, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0342118740081787, "global_step": 506048, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0311362743377686, "global_step": 506049, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9817149639129639, "global_step": 506050, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.075540065765381, "global_step": 506051, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.01813006401062, "global_step": 506052, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.025941848754883, "global_step": 506053, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9598605632781982, "global_step": 506054, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0890214443206787, "global_step": 506055, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.026840925216675, "global_step": 506056, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0614466667175293, "global_step": 506057, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.004840612411499, "global_step": 506058, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.050171375274658, "global_step": 506059, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.011569023132324, "global_step": 506060, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0042381286621094, "global_step": 506061, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0867655277252197, "global_step": 506062, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.995808482170105, "global_step": 506063, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9886581897735596, "global_step": 506064, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.055509090423584, "global_step": 506065, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1325674057006836, "global_step": 506066, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9601682424545288, "global_step": 506067, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.107421398162842, "global_step": 506068, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9926284551620483, "global_step": 506069, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1014394760131836, "global_step": 506070, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.067946195602417, "global_step": 506071, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.051882743835449, "global_step": 506072, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.049020290374756, "global_step": 506073, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0130462646484375, "global_step": 506074, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0278050899505615, "global_step": 506075, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.029520034790039, "global_step": 506076, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9822938442230225, "global_step": 506077, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0933890342712402, "global_step": 506078, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.017296075820923, "global_step": 506079, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.992343783378601, "global_step": 506080, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0432491302490234, "global_step": 506081, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.117739200592041, "global_step": 506082, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.020388603210449, "global_step": 506083, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1007907390594482, "global_step": 506084, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0302791595458984, "global_step": 506085, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0221312046051025, "global_step": 506086, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0750088691711426, "global_step": 506087, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0065391063690186, "global_step": 506088, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.093426465988159, "global_step": 506089, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.035498857498169, "global_step": 506090, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0857174396514893, "global_step": 506091, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0040805339813232, "global_step": 506092, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.998971939086914, "global_step": 506093, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9808120727539062, "global_step": 506094, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0049126148223877, "global_step": 506095, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.017909526824951, "global_step": 506096, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9928631782531738, "global_step": 506097, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0025062561035156, "global_step": 506098, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0193278789520264, "global_step": 506099, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0355138778686523, "global_step": 506100, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0244123935699463, "global_step": 506101, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0793330669403076, "global_step": 506102, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9682109355926514, "global_step": 506103, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.094597816467285, "global_step": 506104, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1150918006896973, "global_step": 506105, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0653302669525146, "global_step": 506106, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1147027015686035, "global_step": 506107, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9752427339553833, "global_step": 506108, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0376389026641846, "global_step": 506109, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0704479217529297, "global_step": 506110, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.123427152633667, "global_step": 506111, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1028401851654053, "global_step": 506112, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1073174476623535, "global_step": 506113, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.073962688446045, "global_step": 506114, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9849224090576172, "global_step": 506115, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0848069190979004, "global_step": 506116, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.049492597579956, "global_step": 506117, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0065994262695312, "global_step": 506118, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0257925987243652, "global_step": 506119, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9606096744537354, "global_step": 506120, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.025066614151001, "global_step": 506121, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.043977737426758, "global_step": 506122, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0653176307678223, "global_step": 506123, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0808913707733154, "global_step": 506124, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.075444221496582, "global_step": 506125, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0340914726257324, "global_step": 506126, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0959510803222656, "global_step": 506127, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.034024238586426, "global_step": 506128, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0068655014038086, "global_step": 506129, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.08689284324646, "global_step": 506130, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.035794496536255, "global_step": 506131, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0172781944274902, "global_step": 506132, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1375889778137207, "global_step": 506133, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.111362934112549, "global_step": 506134, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.011190891265869, "global_step": 506135, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.040010690689087, "global_step": 506136, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.027569532394409, "global_step": 506137, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0875771045684814, "global_step": 506138, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0658907890319824, "global_step": 506139, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.099087715148926, "global_step": 506140, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1198205947875977, "global_step": 506141, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0192925930023193, "global_step": 506142, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0213189125061035, "global_step": 506143, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0353798866271973, "global_step": 506144, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9791892766952515, "global_step": 506145, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0373966693878174, "global_step": 506146, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.121044874191284, "global_step": 506147, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0407776832580566, "global_step": 506148, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0260753631591797, "global_step": 506149, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9303749799728394, "global_step": 506150, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.027024269104004, "global_step": 506151, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.056554079055786, "global_step": 506152, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0918078422546387, "global_step": 506153, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0506632328033447, "global_step": 506154, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.943198323249817, "global_step": 506155, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.067391872406006, "global_step": 506156, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0158021450042725, "global_step": 506157, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.016411781311035, "global_step": 506158, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9700928926467896, "global_step": 506159, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.042276382446289, "global_step": 506160, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.072537422180176, "global_step": 506161, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.043165922164917, "global_step": 506162, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9818421602249146, "global_step": 506163, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.021322011947632, "global_step": 506164, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0174975395202637, "global_step": 506165, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9944208860397339, "global_step": 506166, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.017141819000244, "global_step": 506167, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9880155324935913, "global_step": 506168, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1005330085754395, "global_step": 506169, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0783984661102295, "global_step": 506170, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1065728664398193, "global_step": 506171, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.043177366256714, "global_step": 506172, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0319409370422363, "global_step": 506173, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0644946098327637, "global_step": 506174, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9789382219314575, "global_step": 506175, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0318288803100586, "global_step": 506176, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.058255910873413, "global_step": 506177, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.088693380355835, "global_step": 506178, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9557989835739136, "global_step": 506179, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.08358097076416, "global_step": 506180, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.052877426147461, "global_step": 506181, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0384938716888428, "global_step": 506182, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.04762864112854, "global_step": 506183, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9737486839294434, "global_step": 506184, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.063713550567627, "global_step": 506185, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.010037660598755, "global_step": 506186, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9871731996536255, "global_step": 506187, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9387872219085693, "global_step": 506188, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0344316959381104, "global_step": 506189, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1266062259674072, "global_step": 506190, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0693552494049072, "global_step": 506191, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.084230422973633, "global_step": 506192, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.093714714050293, "global_step": 506193, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9762808084487915, "global_step": 506194, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0621776580810547, "global_step": 506195, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9313082695007324, "global_step": 506196, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0033912658691406, "global_step": 506197, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.088683605194092, "global_step": 506198, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1564066410064697, "global_step": 506199, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.072213888168335, "global_step": 506200, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.020024061203003, "global_step": 506201, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0604796409606934, "global_step": 506202, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.081818103790283, "global_step": 506203, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.118337869644165, "global_step": 506204, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.064509630203247, "global_step": 506205, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1138930320739746, "global_step": 506206, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0426065921783447, "global_step": 506207, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9652044773101807, "global_step": 506208, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0913403034210205, "global_step": 506209, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.071815013885498, "global_step": 506210, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0097830295562744, "global_step": 506211, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0687201023101807, "global_step": 506212, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0721898078918457, "global_step": 506213, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0209901332855225, "global_step": 506214, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.098925828933716, "global_step": 506215, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9915058612823486, "global_step": 506216, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.001830577850342, "global_step": 506217, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9544036388397217, "global_step": 506218, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.01005220413208, "global_step": 506219, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0000500679016113, "global_step": 506220, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0913867950439453, "global_step": 506221, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0336601734161377, "global_step": 506222, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.087754726409912, "global_step": 506223, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1343495845794678, "global_step": 506224, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.008995294570923, "global_step": 506225, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.04354190826416, "global_step": 506226, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9843965768814087, "global_step": 506227, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9832079410552979, "global_step": 506228, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.079608201980591, "global_step": 506229, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0137763023376465, "global_step": 506230, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.070065498352051, "global_step": 506231, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0338265895843506, "global_step": 506232, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0803635120391846, "global_step": 506233, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.010951042175293, "global_step": 506234, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0681071281433105, "global_step": 506235, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9649468660354614, "global_step": 506236, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0872535705566406, "global_step": 506237, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.044851303100586, "global_step": 506238, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0367918014526367, "global_step": 506239, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.186905860900879, "global_step": 506240, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.97748863697052, "global_step": 506241, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0770490169525146, "global_step": 506242, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0393009185791016, "global_step": 506243, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9449645280838013, "global_step": 506244, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.964590311050415, "global_step": 506245, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1246237754821777, "global_step": 506246, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0004425048828125, "global_step": 506247, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9896807670593262, "global_step": 506248, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0571141242980957, "global_step": 506249, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.014578104019165, "global_step": 506250, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9894496202468872, "global_step": 506251, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9936549663543701, "global_step": 506252, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0755295753479004, "global_step": 506253, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1052613258361816, "global_step": 506254, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0471408367156982, "global_step": 506255, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0114965438842773, "global_step": 506256, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0709071159362793, "global_step": 506257, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0858640670776367, "global_step": 506258, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.992647647857666, "global_step": 506259, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.027771234512329, "global_step": 506260, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9899206161499023, "global_step": 506261, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.129889965057373, "global_step": 506262, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9873229265213013, "global_step": 506263, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9449068307876587, "global_step": 506264, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0652260780334473, "global_step": 506265, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.034336805343628, "global_step": 506266, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0275156497955322, "global_step": 506267, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.08895206451416, "global_step": 506268, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0375912189483643, "global_step": 506269, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0207417011260986, "global_step": 506270, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.008901357650757, "global_step": 506271, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0883123874664307, "global_step": 506272, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0728490352630615, "global_step": 506273, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.148944616317749, "global_step": 506274, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0497941970825195, "global_step": 506275, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9737058877944946, "global_step": 506276, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0123672485351562, "global_step": 506277, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1053407192230225, "global_step": 506278, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1204116344451904, "global_step": 506279, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.015698194503784, "global_step": 506280, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.100400447845459, "global_step": 506281, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.045037031173706, "global_step": 506282, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.075537919998169, "global_step": 506283, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1085424423217773, "global_step": 506284, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1254043579101562, "global_step": 506285, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.09820294380188, "global_step": 506286, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.048130750656128, "global_step": 506287, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0839483737945557, "global_step": 506288, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.066659688949585, "global_step": 506289, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.087421417236328, "global_step": 506290, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0454764366149902, "global_step": 506291, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0394771099090576, "global_step": 506292, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0322773456573486, "global_step": 506293, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0850698947906494, "global_step": 506294, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0294203758239746, "global_step": 506295, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0507168769836426, "global_step": 506296, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0745177268981934, "global_step": 506297, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.124025344848633, "global_step": 506298, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0044796466827393, "global_step": 506299, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9587793350219727, "global_step": 506300, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.033576488494873, "global_step": 506301, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0031561851501465, "global_step": 506302, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.968656301498413, "global_step": 506303, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.089193820953369, "global_step": 506304, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.042203187942505, "global_step": 506305, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0102016925811768, "global_step": 506306, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0576179027557373, "global_step": 506307, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9456721544265747, "global_step": 506308, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0199573040008545, "global_step": 506309, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.046534538269043, "global_step": 506310, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0930352210998535, "global_step": 506311, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1555564403533936, "global_step": 506312, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9837911128997803, "global_step": 506313, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0575075149536133, "global_step": 506314, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.04207706451416, "global_step": 506315, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9982404708862305, "global_step": 506316, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9260362386703491, "global_step": 506317, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.010674238204956, "global_step": 506318, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.056907892227173, "global_step": 506319, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0125086307525635, "global_step": 506320, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1042847633361816, "global_step": 506321, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.039245128631592, "global_step": 506322, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0183236598968506, "global_step": 506323, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0736024379730225, "global_step": 506324, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9616433382034302, "global_step": 506325, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.006220817565918, "global_step": 506326, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.012716770172119, "global_step": 506327, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.046354293823242, "global_step": 506328, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.005004405975342, "global_step": 506329, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0407543182373047, "global_step": 506330, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9475135803222656, "global_step": 506331, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0774857997894287, "global_step": 506332, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1079955101013184, "global_step": 506333, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.077214241027832, "global_step": 506334, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0511488914489746, "global_step": 506335, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1131203174591064, "global_step": 506336, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.075104236602783, "global_step": 506337, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0613045692443848, "global_step": 506338, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0031046867370605, "global_step": 506339, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.122817277908325, "global_step": 506340, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.115914821624756, "global_step": 506341, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.093867301940918, "global_step": 506342, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0926105976104736, "global_step": 506343, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0031044483184814, "global_step": 506344, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0598652362823486, "global_step": 506345, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.067650556564331, "global_step": 506346, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.077359914779663, "global_step": 506347, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9928269386291504, "global_step": 506348, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0660908222198486, "global_step": 506349, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.050532102584839, "global_step": 506350, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.067383289337158, "global_step": 506351, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0441431999206543, "global_step": 506352, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0036067962646484, "global_step": 506353, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.147043228149414, "global_step": 506354, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9600954055786133, "global_step": 506355, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0418388843536377, "global_step": 506356, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0323994159698486, "global_step": 506357, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0451338291168213, "global_step": 506358, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9899797439575195, "global_step": 506359, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0089614391326904, "global_step": 506360, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1308705806732178, "global_step": 506361, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.030975103378296, "global_step": 506362, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0954232215881348, "global_step": 506363, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0668742656707764, "global_step": 506364, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.035137176513672, "global_step": 506365, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0143346786499023, "global_step": 506366, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.097632646560669, "global_step": 506367, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.05989670753479, "global_step": 506368, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.008673906326294, "global_step": 506369, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1028265953063965, "global_step": 506370, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.095319986343384, "global_step": 506371, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0819501876831055, "global_step": 506372, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0970349311828613, "global_step": 506373, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.996340036392212, "global_step": 506374, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0212297439575195, "global_step": 506375, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9979479312896729, "global_step": 506376, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0236642360687256, "global_step": 506377, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.017302989959717, "global_step": 506378, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9226043224334717, "global_step": 506379, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.024174213409424, "global_step": 506380, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0950565338134766, "global_step": 506381, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9956297874450684, "global_step": 506382, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.038569450378418, "global_step": 506383, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.038635730743408, "global_step": 506384, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9898147583007812, "global_step": 506385, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1044836044311523, "global_step": 506386, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.047574996948242, "global_step": 506387, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0957202911376953, "global_step": 506388, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.048923969268799, "global_step": 506389, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.054201126098633, "global_step": 506390, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1197612285614014, "global_step": 506391, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.064403533935547, "global_step": 506392, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0256271362304688, "global_step": 506393, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.038710117340088, "global_step": 506394, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.055520534515381, "global_step": 506395, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.039586305618286, "global_step": 506396, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9891681671142578, "global_step": 506397, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.075080633163452, "global_step": 506398, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0309295654296875, "global_step": 506399, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0625860691070557, "global_step": 506400, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0870680809020996, "global_step": 506401, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1762325763702393, "global_step": 506402, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1344707012176514, "global_step": 506403, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0225460529327393, "global_step": 506404, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0163683891296387, "global_step": 506405, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.059417963027954, "global_step": 506406, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0414719581604004, "global_step": 506407, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1515166759490967, "global_step": 506408, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.053701400756836, "global_step": 506409, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1140213012695312, "global_step": 506410, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1016950607299805, "global_step": 506411, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0973222255706787, "global_step": 506412, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9021843671798706, "global_step": 506413, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.029453754425049, "global_step": 506414, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0223522186279297, "global_step": 506415, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.060556173324585, "global_step": 506416, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.043142795562744, "global_step": 506417, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0353751182556152, "global_step": 506418, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0300822257995605, "global_step": 506419, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0220396518707275, "global_step": 506420, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0863497257232666, "global_step": 506421, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0521159172058105, "global_step": 506422, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0125479698181152, "global_step": 506423, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0915145874023438, "global_step": 506424, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0374791622161865, "global_step": 506425, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0774221420288086, "global_step": 506426, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0972557067871094, "global_step": 506427, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.122004508972168, "global_step": 506428, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.040188789367676, "global_step": 506429, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0562212467193604, "global_step": 506430, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0747125148773193, "global_step": 506431, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.014961004257202, "global_step": 506432, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.070267677307129, "global_step": 506433, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0194427967071533, "global_step": 506434, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.061944007873535, "global_step": 506435, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0148990154266357, "global_step": 506436, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.091916799545288, "global_step": 506437, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.095938205718994, "global_step": 506438, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0465636253356934, "global_step": 506439, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9759998321533203, "global_step": 506440, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.02636456489563, "global_step": 506441, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0851352214813232, "global_step": 506442, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.160315752029419, "global_step": 506443, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0132694244384766, "global_step": 506444, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.101064920425415, "global_step": 506445, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.088045597076416, "global_step": 506446, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0513131618499756, "global_step": 506447, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0250587463378906, "global_step": 506448, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1006319522857666, "global_step": 506449, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0796546936035156, "global_step": 506450, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.034435749053955, "global_step": 506451, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9837294816970825, "global_step": 506452, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0789778232574463, "global_step": 506453, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.095048189163208, "global_step": 506454, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.11247181892395, "global_step": 506455, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9782700538635254, "global_step": 506456, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.07181715965271, "global_step": 506457, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9875874519348145, "global_step": 506458, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0036258697509766, "global_step": 506459, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.142481803894043, "global_step": 506460, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0092079639434814, "global_step": 506461, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.055473804473877, "global_step": 506462, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.979935646057129, "global_step": 506463, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0207502841949463, "global_step": 506464, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.069643497467041, "global_step": 506465, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0498769283294678, "global_step": 506466, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.081176519393921, "global_step": 506467, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.022393226623535, "global_step": 506468, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.087682008743286, "global_step": 506469, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0763301849365234, "global_step": 506470, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0984160900115967, "global_step": 506471, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.074448347091675, "global_step": 506472, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0345287322998047, "global_step": 506473, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.043260097503662, "global_step": 506474, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9925425052642822, "global_step": 506475, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0222699642181396, "global_step": 506476, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9842990636825562, "global_step": 506477, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9916976690292358, "global_step": 506478, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.076076030731201, "global_step": 506479, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0247395038604736, "global_step": 506480, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0259642601013184, "global_step": 506481, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.084517240524292, "global_step": 506482, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0335142612457275, "global_step": 506483, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.053102970123291, "global_step": 506484, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.020322322845459, "global_step": 506485, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0842278003692627, "global_step": 506486, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9984031915664673, "global_step": 506487, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9500924348831177, "global_step": 506488, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9994860887527466, "global_step": 506489, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.045126438140869, "global_step": 506490, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0157437324523926, "global_step": 506491, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.085542678833008, "global_step": 506492, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.080320358276367, "global_step": 506493, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0614969730377197, "global_step": 506494, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9724373817443848, "global_step": 506495, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0011072158813477, "global_step": 506496, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.048164129257202, "global_step": 506497, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0696535110473633, "global_step": 506498, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.083719491958618, "global_step": 506499, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0738773345947266, "global_step": 506500, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1022799015045166, "global_step": 506501, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0796725749969482, "global_step": 506502, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.107985496520996, "global_step": 506503, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0781667232513428, "global_step": 506504, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0057549476623535, "global_step": 506505, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0906646251678467, "global_step": 506506, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1249892711639404, "global_step": 506507, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0400619506835938, "global_step": 506508, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.111834764480591, "global_step": 506509, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.082869529724121, "global_step": 506510, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0348260402679443, "global_step": 506511, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0379157066345215, "global_step": 506512, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0654218196868896, "global_step": 506513, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.066023826599121, "global_step": 506514, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.046218156814575, "global_step": 506515, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1084372997283936, "global_step": 506516, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9632200002670288, "global_step": 506517, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.049743890762329, "global_step": 506518, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1373116970062256, "global_step": 506519, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0608606338500977, "global_step": 506520, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0093040466308594, "global_step": 506521, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0339736938476562, "global_step": 506522, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.115959882736206, "global_step": 506523, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0512924194335938, "global_step": 506524, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.024075984954834, "global_step": 506525, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.008946418762207, "global_step": 506526, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0722405910491943, "global_step": 506527, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.17146372795105, "global_step": 506528, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0567493438720703, "global_step": 506529, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0591447353363037, "global_step": 506530, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.06917142868042, "global_step": 506531, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0699424743652344, "global_step": 506532, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0016753673553467, "global_step": 506533, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0871806144714355, "global_step": 506534, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1498727798461914, "global_step": 506535, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0442490577697754, "global_step": 506536, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0415408611297607, "global_step": 506537, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.170269012451172, "global_step": 506538, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0170350074768066, "global_step": 506539, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0321104526519775, "global_step": 506540, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0250537395477295, "global_step": 506541, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.069439172744751, "global_step": 506542, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0764544010162354, "global_step": 506543, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0760021209716797, "global_step": 506544, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.028125762939453, "global_step": 506545, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.151553153991699, "global_step": 506546, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9918898344039917, "global_step": 506547, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.113852024078369, "global_step": 506548, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9835809469223022, "global_step": 506549, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.021118402481079, "global_step": 506550, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9686381816864014, "global_step": 506551, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0394928455352783, "global_step": 506552, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0406992435455322, "global_step": 506553, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0233724117279053, "global_step": 506554, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0761263370513916, "global_step": 506555, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.132021427154541, "global_step": 506556, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.14753794670105, "global_step": 506557, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0896267890930176, "global_step": 506558, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0090415477752686, "global_step": 506559, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1044111251831055, "global_step": 506560, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0601179599761963, "global_step": 506561, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.163816452026367, "global_step": 506562, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.029757499694824, "global_step": 506563, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.070697069168091, "global_step": 506564, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.104212760925293, "global_step": 506565, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.056185483932495, "global_step": 506566, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.087700366973877, "global_step": 506567, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.024627923965454, "global_step": 506568, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0696070194244385, "global_step": 506569, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0431723594665527, "global_step": 506570, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.114271640777588, "global_step": 506571, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0000734329223633, "global_step": 506572, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0403568744659424, "global_step": 506573, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.140728712081909, "global_step": 506574, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1232552528381348, "global_step": 506575, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.036332368850708, "global_step": 506576, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.064862012863159, "global_step": 506577, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.07585072517395, "global_step": 506578, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0382437705993652, "global_step": 506579, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.017199754714966, "global_step": 506580, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0495705604553223, "global_step": 506581, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9923522472381592, "global_step": 506582, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.034985065460205, "global_step": 506583, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0353400707244873, "global_step": 506584, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9779738187789917, "global_step": 506585, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9862526655197144, "global_step": 506586, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0775647163391113, "global_step": 506587, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9794116020202637, "global_step": 506588, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.039585828781128, "global_step": 506589, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0892202854156494, "global_step": 506590, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.065852642059326, "global_step": 506591, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0550224781036377, "global_step": 506592, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0659403800964355, "global_step": 506593, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0142016410827637, "global_step": 506594, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0942656993865967, "global_step": 506595, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.098431348800659, "global_step": 506596, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0183801651000977, "global_step": 506597, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1561732292175293, "global_step": 506598, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.062159538269043, "global_step": 506599, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0342423915863037, "global_step": 506600, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.991454839706421, "global_step": 506601, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.093864679336548, "global_step": 506602, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.048668146133423, "global_step": 506603, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0884182453155518, "global_step": 506604, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0780279636383057, "global_step": 506605, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0539114475250244, "global_step": 506606, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.068756103515625, "global_step": 506607, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9650052785873413, "global_step": 506608, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.008906602859497, "global_step": 506609, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1112356185913086, "global_step": 506610, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.141230583190918, "global_step": 506611, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0625698566436768, "global_step": 506612, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0960381031036377, "global_step": 506613, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9783368110656738, "global_step": 506614, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.042494058609009, "global_step": 506615, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.043696641921997, "global_step": 506616, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.107928514480591, "global_step": 506617, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0442349910736084, "global_step": 506618, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.076977252960205, "global_step": 506619, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.104083776473999, "global_step": 506620, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0715274810791016, "global_step": 506621, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.999866008758545, "global_step": 506622, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0119216442108154, "global_step": 506623, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.061293840408325, "global_step": 506624, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.011571168899536, "global_step": 506625, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.039212465286255, "global_step": 506626, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.98501718044281, "global_step": 506627, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1295316219329834, "global_step": 506628, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.077000617980957, "global_step": 506629, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.036344051361084, "global_step": 506630, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0898776054382324, "global_step": 506631, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0145041942596436, "global_step": 506632, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1114959716796875, "global_step": 506633, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9523377418518066, "global_step": 506634, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9871785640716553, "global_step": 506635, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.042719602584839, "global_step": 506636, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.981271743774414, "global_step": 506637, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.090221881866455, "global_step": 506638, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0302820205688477, "global_step": 506639, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.10823392868042, "global_step": 506640, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0224969387054443, "global_step": 506641, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.053035020828247, "global_step": 506642, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.954818606376648, "global_step": 506643, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.085581064224243, "global_step": 506644, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0836968421936035, "global_step": 506645, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0357301235198975, "global_step": 506646, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0385401248931885, "global_step": 506647, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0681447982788086, "global_step": 506648, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.138122320175171, "global_step": 506649, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0399138927459717, "global_step": 506650, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.062331199645996, "global_step": 506651, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0029940605163574, "global_step": 506652, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.104135513305664, "global_step": 506653, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.006164073944092, "global_step": 506654, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0805068016052246, "global_step": 506655, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.110109329223633, "global_step": 506656, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0971405506134033, "global_step": 506657, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0840189456939697, "global_step": 506658, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0772056579589844, "global_step": 506659, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.090846538543701, "global_step": 506660, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.097907066345215, "global_step": 506661, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9756406545639038, "global_step": 506662, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0683987140655518, "global_step": 506663, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.023723602294922, "global_step": 506664, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0236899852752686, "global_step": 506665, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9843804836273193, "global_step": 506666, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9981331825256348, "global_step": 506667, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0368504524230957, "global_step": 506668, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0942134857177734, "global_step": 506669, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.064271926879883, "global_step": 506670, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9679135084152222, "global_step": 506671, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9846346378326416, "global_step": 506672, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0253524780273438, "global_step": 506673, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9957458972930908, "global_step": 506674, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0539042949676514, "global_step": 506675, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0328807830810547, "global_step": 506676, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.05629563331604, "global_step": 506677, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.992106318473816, "global_step": 506678, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.047238826751709, "global_step": 506679, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9728859663009644, "global_step": 506680, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0724728107452393, "global_step": 506681, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.057685613632202, "global_step": 506682, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1286346912384033, "global_step": 506683, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0210485458374023, "global_step": 506684, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.080118417739868, "global_step": 506685, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1177637577056885, "global_step": 506686, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1001031398773193, "global_step": 506687, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1104748249053955, "global_step": 506688, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0834665298461914, "global_step": 506689, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.075871467590332, "global_step": 506690, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0969221591949463, "global_step": 506691, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.092916965484619, "global_step": 506692, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0247223377227783, "global_step": 506693, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0403971672058105, "global_step": 506694, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0362071990966797, "global_step": 506695, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.07283091545105, "global_step": 506696, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1140987873077393, "global_step": 506697, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.059211015701294, "global_step": 506698, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9824398756027222, "global_step": 506699, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.914469838142395, "global_step": 506700, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1154935359954834, "global_step": 506701, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0148940086364746, "global_step": 506702, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.042360305786133, "global_step": 506703, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1222541332244873, "global_step": 506704, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.08998441696167, "global_step": 506705, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0488362312316895, "global_step": 506706, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0874600410461426, "global_step": 506707, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.096001148223877, "global_step": 506708, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.005632162094116, "global_step": 506709, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.967404842376709, "global_step": 506710, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0947189331054688, "global_step": 506711, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0699188709259033, "global_step": 506712, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.112902879714966, "global_step": 506713, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0332484245300293, "global_step": 506714, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0093331336975098, "global_step": 506715, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.173469305038452, "global_step": 506716, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9807428121566772, "global_step": 506717, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0243146419525146, "global_step": 506718, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0550527572631836, "global_step": 506719, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9910883903503418, "global_step": 506720, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1193838119506836, "global_step": 506721, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.086862802505493, "global_step": 506722, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1219911575317383, "global_step": 506723, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0364420413970947, "global_step": 506724, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.046344518661499, "global_step": 506725, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9683268070220947, "global_step": 506726, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.113018035888672, "global_step": 506727, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.093677520751953, "global_step": 506728, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.045139789581299, "global_step": 506729, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0277349948883057, "global_step": 506730, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.016165018081665, "global_step": 506731, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0865917205810547, "global_step": 506732, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0204203128814697, "global_step": 506733, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.010455846786499, "global_step": 506734, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1159491539001465, "global_step": 506735, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.074908494949341, "global_step": 506736, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.034393787384033, "global_step": 506737, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.06223201751709, "global_step": 506738, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0995445251464844, "global_step": 506739, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9687397480010986, "global_step": 506740, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1369636058807373, "global_step": 506741, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0421080589294434, "global_step": 506742, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1175332069396973, "global_step": 506743, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.983708143234253, "global_step": 506744, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.129377603530884, "global_step": 506745, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9681682586669922, "global_step": 506746, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9928843975067139, "global_step": 506747, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.006072998046875, "global_step": 506748, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.05603289604187, "global_step": 506749, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9991364479064941, "global_step": 506750, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0304946899414062, "global_step": 506751, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0990750789642334, "global_step": 506752, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0079638957977295, "global_step": 506753, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1160218715667725, "global_step": 506754, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0795300006866455, "global_step": 506755, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.985365867614746, "global_step": 506756, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0153894424438477, "global_step": 506757, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.2266063690185547, "global_step": 506758, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.077096939086914, "global_step": 506759, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0051605701446533, "global_step": 506760, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.032724380493164, "global_step": 506761, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9010761976242065, "global_step": 506762, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0721795558929443, "global_step": 506763, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0677685737609863, "global_step": 506764, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1436474323272705, "global_step": 506765, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.047199249267578, "global_step": 506766, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.108443260192871, "global_step": 506767, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1430892944335938, "global_step": 506768, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.051410436630249, "global_step": 506769, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.100569486618042, "global_step": 506770, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.093825578689575, "global_step": 506771, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0332517623901367, "global_step": 506772, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.042893409729004, "global_step": 506773, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0310215950012207, "global_step": 506774, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.076223850250244, "global_step": 506775, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1028833389282227, "global_step": 506776, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.031219720840454, "global_step": 506777, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1025586128234863, "global_step": 506778, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0453691482543945, "global_step": 506779, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.159367561340332, "global_step": 506780, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1827666759490967, "global_step": 506781, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.102672576904297, "global_step": 506782, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.97518789768219, "global_step": 506783, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.192051887512207, "global_step": 506784, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.001504898071289, "global_step": 506785, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.06253719329834, "global_step": 506786, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0434370040893555, "global_step": 506787, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0599377155303955, "global_step": 506788, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0762860774993896, "global_step": 506789, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0327534675598145, "global_step": 506790, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1139638423919678, "global_step": 506791, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.084418296813965, "global_step": 506792, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0222883224487305, "global_step": 506793, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0356554985046387, "global_step": 506794, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1841137409210205, "global_step": 506795, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9958758354187012, "global_step": 506796, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.083165168762207, "global_step": 506797, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0099899768829346, "global_step": 506798, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.079503059387207, "global_step": 506799, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0899698734283447, "global_step": 506800, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.05041241645813, "global_step": 506801, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1793711185455322, "global_step": 506802, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1416828632354736, "global_step": 506803, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0649778842926025, "global_step": 506804, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.063467502593994, "global_step": 506805, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.053835153579712, "global_step": 506806, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0875778198242188, "global_step": 506807, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.073974609375, "global_step": 506808, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1692655086517334, "global_step": 506809, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0557737350463867, "global_step": 506810, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0308659076690674, "global_step": 506811, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.089006185531616, "global_step": 506812, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.00976300239563, "global_step": 506813, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9696112871170044, "global_step": 506814, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9851011037826538, "global_step": 506815, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0552306175231934, "global_step": 506816, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.066584348678589, "global_step": 506817, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9853386878967285, "global_step": 506818, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0640103816986084, "global_step": 506819, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1174960136413574, "global_step": 506820, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1469883918762207, "global_step": 506821, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0718274116516113, "global_step": 506822, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0839834213256836, "global_step": 506823, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9996885061264038, "global_step": 506824, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.100501298904419, "global_step": 506825, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1124918460845947, "global_step": 506826, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0914037227630615, "global_step": 506827, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.072814702987671, "global_step": 506828, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.029317855834961, "global_step": 506829, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0396811962127686, "global_step": 506830, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.080057144165039, "global_step": 506831, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.111084461212158, "global_step": 506832, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.059476852416992, "global_step": 506833, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0852856636047363, "global_step": 506834, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.971787929534912, "global_step": 506835, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.973393201828003, "global_step": 506836, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0176239013671875, "global_step": 506837, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0746898651123047, "global_step": 506838, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0992448329925537, "global_step": 506839, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0936708450317383, "global_step": 506840, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9805258512496948, "global_step": 506841, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0642197132110596, "global_step": 506842, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0380547046661377, "global_step": 506843, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0839831829071045, "global_step": 506844, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0735085010528564, "global_step": 506845, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0433402061462402, "global_step": 506846, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1143147945404053, "global_step": 506847, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9969635009765625, "global_step": 506848, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.012404441833496, "global_step": 506849, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0799481868743896, "global_step": 506850, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0066161155700684, "global_step": 506851, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.094423532485962, "global_step": 506852, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.150834560394287, "global_step": 506853, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0795061588287354, "global_step": 506854, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.047823905944824, "global_step": 506855, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9758766889572144, "global_step": 506856, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0523619651794434, "global_step": 506857, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.052081346511841, "global_step": 506858, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0655272006988525, "global_step": 506859, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.052706718444824, "global_step": 506860, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9956533908843994, "global_step": 506861, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.958361268043518, "global_step": 506862, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0741143226623535, "global_step": 506863, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.037735939025879, "global_step": 506864, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.155726671218872, "global_step": 506865, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0712122917175293, "global_step": 506866, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9807984828948975, "global_step": 506867, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0698299407958984, "global_step": 506868, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.05110239982605, "global_step": 506869, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.03312349319458, "global_step": 506870, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.023604154586792, "global_step": 506871, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0414552688598633, "global_step": 506872, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.052353858947754, "global_step": 506873, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0139377117156982, "global_step": 506874, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0822622776031494, "global_step": 506875, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0467793941497803, "global_step": 506876, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.036871910095215, "global_step": 506877, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.016749143600464, "global_step": 506878, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0302648544311523, "global_step": 506879, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0426480770111084, "global_step": 506880, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.128690719604492, "global_step": 506881, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.048192262649536, "global_step": 506882, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.005685806274414, "global_step": 506883, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0560085773468018, "global_step": 506884, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.997086524963379, "global_step": 506885, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0701863765716553, "global_step": 506886, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9852733612060547, "global_step": 506887, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.035440444946289, "global_step": 506888, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.126840591430664, "global_step": 506889, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.039491891860962, "global_step": 506890, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0094571113586426, "global_step": 506891, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.115203380584717, "global_step": 506892, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9386260509490967, "global_step": 506893, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.065260410308838, "global_step": 506894, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9179834127426147, "global_step": 506895, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0916378498077393, "global_step": 506896, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.007272958755493, "global_step": 506897, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.056952714920044, "global_step": 506898, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.110478401184082, "global_step": 506899, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.081451177597046, "global_step": 506900, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1576080322265625, "global_step": 506901, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1229655742645264, "global_step": 506902, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.068826913833618, "global_step": 506903, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0885791778564453, "global_step": 506904, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0615177154541016, "global_step": 506905, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.156867504119873, "global_step": 506906, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.021496295928955, "global_step": 506907, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.01194167137146, "global_step": 506908, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.056260347366333, "global_step": 506909, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.034137010574341, "global_step": 506910, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0576086044311523, "global_step": 506911, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.0632529258728027, "global_step": 506912, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.1172192096710205, "global_step": 506913, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.042797803878784, "global_step": 506914, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.054356336593628, "global_step": 506915, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.059887170791626, "global_step": 506916, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.068403720855713, "global_step": 506917, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9891830682754517, "global_step": 506918, "epoch": 872, "lr": 5e-05}
{"train_loss": 2.049226999282837, "global_step": 506919, "epoch": 872, "lr": 5e-05}
{"train_loss": 1.9360582828521729, "global_step": 506920, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9728623628616333, "global_step": 506921, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.065842390060425, "global_step": 506922, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9078823328018188, "global_step": 506923, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0518441200256348, "global_step": 506924, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0041444301605225, "global_step": 506925, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.047067403793335, "global_step": 506926, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9678303003311157, "global_step": 506927, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9675880670547485, "global_step": 506928, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0955886840820312, "global_step": 506929, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.095506191253662, "global_step": 506930, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.081329822540283, "global_step": 506931, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.974736213684082, "global_step": 506932, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0438714027404785, "global_step": 506933, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9873309135437012, "global_step": 506934, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1123013496398926, "global_step": 506935, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0416340827941895, "global_step": 506936, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0677318572998047, "global_step": 506937, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.07793927192688, "global_step": 506938, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.99569833278656, "global_step": 506939, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9870178699493408, "global_step": 506940, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0160999298095703, "global_step": 506941, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0828988552093506, "global_step": 506942, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.018765449523926, "global_step": 506943, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.091900587081909, "global_step": 506944, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0545148849487305, "global_step": 506945, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.050020933151245, "global_step": 506946, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.037403106689453, "global_step": 506947, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.033066749572754, "global_step": 506948, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0013070106506348, "global_step": 506949, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0787816047668457, "global_step": 506950, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9288681745529175, "global_step": 506951, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0461063385009766, "global_step": 506952, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0229392051696777, "global_step": 506953, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0186402797698975, "global_step": 506954, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0029489994049072, "global_step": 506955, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9875463247299194, "global_step": 506956, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.091125011444092, "global_step": 506957, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0860767364501953, "global_step": 506958, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9817934036254883, "global_step": 506959, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0951120853424072, "global_step": 506960, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.956702470779419, "global_step": 506961, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0518603324890137, "global_step": 506962, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.115952968597412, "global_step": 506963, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.056379795074463, "global_step": 506964, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.073822021484375, "global_step": 506965, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0014357566833496, "global_step": 506966, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9847145080566406, "global_step": 506967, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.05991268157959, "global_step": 506968, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.035149335861206, "global_step": 506969, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1136293411254883, "global_step": 506970, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.031541347503662, "global_step": 506971, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0544354915618896, "global_step": 506972, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0235633850097656, "global_step": 506973, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0348641872406006, "global_step": 506974, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0625343322753906, "global_step": 506975, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.101201057434082, "global_step": 506976, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0326595306396484, "global_step": 506977, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.00373911857605, "global_step": 506978, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0679407119750977, "global_step": 506979, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.004721164703369, "global_step": 506980, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9610234498977661, "global_step": 506981, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0838756561279297, "global_step": 506982, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1012165546417236, "global_step": 506983, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.005260705947876, "global_step": 506984, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0662620067596436, "global_step": 506985, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.075817823410034, "global_step": 506986, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.003354072570801, "global_step": 506987, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9551600217819214, "global_step": 506988, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0830483436584473, "global_step": 506989, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0491769313812256, "global_step": 506990, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.056793212890625, "global_step": 506991, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9985743761062622, "global_step": 506992, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.12685489654541, "global_step": 506993, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0500574111938477, "global_step": 506994, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0784237384796143, "global_step": 506995, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0549826622009277, "global_step": 506996, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.999352216720581, "global_step": 506997, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.015134334564209, "global_step": 506998, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.94149649143219, "global_step": 506999, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0910983085632324, "global_step": 507000, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9534956216812134, "global_step": 507001, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.955790638923645, "global_step": 507002, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.001951217651367, "global_step": 507003, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1368792057037354, "global_step": 507004, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0851593017578125, "global_step": 507005, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0162038803100586, "global_step": 507006, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.011610269546509, "global_step": 507007, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9941976070404053, "global_step": 507008, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.050661563873291, "global_step": 507009, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.099808931350708, "global_step": 507010, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1095798015594482, "global_step": 507011, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.015789031982422, "global_step": 507012, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9775391817092896, "global_step": 507013, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0523693561553955, "global_step": 507014, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0504398345947266, "global_step": 507015, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0055906772613525, "global_step": 507016, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0616328716278076, "global_step": 507017, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1236143112182617, "global_step": 507018, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.136549949645996, "global_step": 507019, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.04245924949646, "global_step": 507020, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0294222831726074, "global_step": 507021, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9837476015090942, "global_step": 507022, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0522971153259277, "global_step": 507023, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0452117919921875, "global_step": 507024, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.069976329803467, "global_step": 507025, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.015601634979248, "global_step": 507026, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.05359148979187, "global_step": 507027, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0575976371765137, "global_step": 507028, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0415287017822266, "global_step": 507029, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9569272994995117, "global_step": 507030, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0571014881134033, "global_step": 507031, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0106000900268555, "global_step": 507032, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.915926218032837, "global_step": 507033, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.073619842529297, "global_step": 507034, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9638084173202515, "global_step": 507035, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.042487859725952, "global_step": 507036, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0699143409729004, "global_step": 507037, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0560500621795654, "global_step": 507038, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.022631883621216, "global_step": 507039, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.060279607772827, "global_step": 507040, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1042985916137695, "global_step": 507041, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.071157455444336, "global_step": 507042, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.037691593170166, "global_step": 507043, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.057570695877075, "global_step": 507044, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0769455432891846, "global_step": 507045, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0427513122558594, "global_step": 507046, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9823988676071167, "global_step": 507047, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.074475049972534, "global_step": 507048, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0311779975891113, "global_step": 507049, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.127070665359497, "global_step": 507050, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9978020191192627, "global_step": 507051, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0445799827575684, "global_step": 507052, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.055696725845337, "global_step": 507053, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1190638542175293, "global_step": 507054, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.129460573196411, "global_step": 507055, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9414242506027222, "global_step": 507056, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.056323766708374, "global_step": 507057, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.074277639389038, "global_step": 507058, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0301339626312256, "global_step": 507059, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.157336711883545, "global_step": 507060, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0519657135009766, "global_step": 507061, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0702896118164062, "global_step": 507062, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.152716875076294, "global_step": 507063, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0353832244873047, "global_step": 507064, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9708040952682495, "global_step": 507065, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.057616710662842, "global_step": 507066, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0602705478668213, "global_step": 507067, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0623388290405273, "global_step": 507068, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.039929151535034, "global_step": 507069, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.018789768218994, "global_step": 507070, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.082429885864258, "global_step": 507071, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.104076862335205, "global_step": 507072, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1012563705444336, "global_step": 507073, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.006049871444702, "global_step": 507074, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9448535442352295, "global_step": 507075, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.012676239013672, "global_step": 507076, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0966668128967285, "global_step": 507077, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.088920831680298, "global_step": 507078, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.162135124206543, "global_step": 507079, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.978655219078064, "global_step": 507080, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9948457479476929, "global_step": 507081, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.049485445022583, "global_step": 507082, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.140906572341919, "global_step": 507083, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.099761486053467, "global_step": 507084, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1094889640808105, "global_step": 507085, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0841763019561768, "global_step": 507086, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.030503749847412, "global_step": 507087, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0228207111358643, "global_step": 507088, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0383591651916504, "global_step": 507089, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0996954441070557, "global_step": 507090, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.012110710144043, "global_step": 507091, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.031914234161377, "global_step": 507092, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0732638835906982, "global_step": 507093, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0510356426239014, "global_step": 507094, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.021155834197998, "global_step": 507095, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0707764625549316, "global_step": 507096, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9708361625671387, "global_step": 507097, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.052671194076538, "global_step": 507098, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0282413959503174, "global_step": 507099, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0761120319366455, "global_step": 507100, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9948465824127197, "global_step": 507101, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0451619625091553, "global_step": 507102, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.023561477661133, "global_step": 507103, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.140371799468994, "global_step": 507104, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0672266483306885, "global_step": 507105, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9893845319747925, "global_step": 507106, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0586183071136475, "global_step": 507107, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1301259994506836, "global_step": 507108, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.090599775314331, "global_step": 507109, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0908336639404297, "global_step": 507110, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9807020425796509, "global_step": 507111, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.01413893699646, "global_step": 507112, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.144521474838257, "global_step": 507113, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.105342149734497, "global_step": 507114, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1931231021881104, "global_step": 507115, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0127224922180176, "global_step": 507116, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0298092365264893, "global_step": 507117, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0917093753814697, "global_step": 507118, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.117593288421631, "global_step": 507119, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1291918754577637, "global_step": 507120, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0746119022369385, "global_step": 507121, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0103888511657715, "global_step": 507122, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9946485757827759, "global_step": 507123, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0513625144958496, "global_step": 507124, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1415693759918213, "global_step": 507125, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0614748001098633, "global_step": 507126, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.070255994796753, "global_step": 507127, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.082007884979248, "global_step": 507128, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0094528198242188, "global_step": 507129, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.109229803085327, "global_step": 507130, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0840530395507812, "global_step": 507131, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0281922817230225, "global_step": 507132, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.067538261413574, "global_step": 507133, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0828747749328613, "global_step": 507134, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0498440265655518, "global_step": 507135, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.031484842300415, "global_step": 507136, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.058947801589966, "global_step": 507137, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9171764850616455, "global_step": 507138, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0877268314361572, "global_step": 507139, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.082528829574585, "global_step": 507140, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9980010986328125, "global_step": 507141, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9816110134124756, "global_step": 507142, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0189719200134277, "global_step": 507143, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9976226091384888, "global_step": 507144, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0652289390563965, "global_step": 507145, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0543110370635986, "global_step": 507146, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.082343578338623, "global_step": 507147, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1219332218170166, "global_step": 507148, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0244312286376953, "global_step": 507149, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0150911808013916, "global_step": 507150, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.051374912261963, "global_step": 507151, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9467713832855225, "global_step": 507152, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9930907487869263, "global_step": 507153, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.028200149536133, "global_step": 507154, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.061842203140259, "global_step": 507155, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.010706663131714, "global_step": 507156, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9995334148406982, "global_step": 507157, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9642388820648193, "global_step": 507158, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.033259630203247, "global_step": 507159, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0743460655212402, "global_step": 507160, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.028533697128296, "global_step": 507161, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0211591720581055, "global_step": 507162, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0465970039367676, "global_step": 507163, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.054065704345703, "global_step": 507164, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0250277519226074, "global_step": 507165, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9992133378982544, "global_step": 507166, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0931081771850586, "global_step": 507167, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1203701496124268, "global_step": 507168, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0865213871002197, "global_step": 507169, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0181055068969727, "global_step": 507170, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9802930355072021, "global_step": 507171, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1023478507995605, "global_step": 507172, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.022656202316284, "global_step": 507173, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.035353899002075, "global_step": 507174, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9912077188491821, "global_step": 507175, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.044368028640747, "global_step": 507176, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.017141580581665, "global_step": 507177, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9875890016555786, "global_step": 507178, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.098003625869751, "global_step": 507179, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.976352572441101, "global_step": 507180, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.04848575592041, "global_step": 507181, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.988598108291626, "global_step": 507182, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.009000301361084, "global_step": 507183, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9802151918411255, "global_step": 507184, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9663145542144775, "global_step": 507185, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0004003047943115, "global_step": 507186, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0265657901763916, "global_step": 507187, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.111431121826172, "global_step": 507188, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.139402151107788, "global_step": 507189, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.089001417160034, "global_step": 507190, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0265302658081055, "global_step": 507191, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.097607374191284, "global_step": 507192, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0887601375579834, "global_step": 507193, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1218199729919434, "global_step": 507194, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0539767742156982, "global_step": 507195, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9997071027755737, "global_step": 507196, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.030209541320801, "global_step": 507197, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.030543327331543, "global_step": 507198, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.959862470626831, "global_step": 507199, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0068070888519287, "global_step": 507200, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.126579523086548, "global_step": 507201, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.093109607696533, "global_step": 507202, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1555466651916504, "global_step": 507203, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0809144973754883, "global_step": 507204, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0183277130126953, "global_step": 507205, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0418736934661865, "global_step": 507206, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9546568393707275, "global_step": 507207, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0533621311187744, "global_step": 507208, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9316514730453491, "global_step": 507209, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0426225662231445, "global_step": 507210, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.059676170349121, "global_step": 507211, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1146254539489746, "global_step": 507212, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0104193687438965, "global_step": 507213, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9950041770935059, "global_step": 507214, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.084312915802002, "global_step": 507215, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.061483383178711, "global_step": 507216, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0996105670928955, "global_step": 507217, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.061192035675049, "global_step": 507218, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.109130382537842, "global_step": 507219, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0717368125915527, "global_step": 507220, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.014683723449707, "global_step": 507221, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9528052806854248, "global_step": 507222, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.136688232421875, "global_step": 507223, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0264458656311035, "global_step": 507224, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.011582374572754, "global_step": 507225, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0287654399871826, "global_step": 507226, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0650618076324463, "global_step": 507227, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1445486545562744, "global_step": 507228, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.062152147293091, "global_step": 507229, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0177111625671387, "global_step": 507230, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1109561920166016, "global_step": 507231, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0884616374969482, "global_step": 507232, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0944125652313232, "global_step": 507233, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9348660707473755, "global_step": 507234, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0410730838775635, "global_step": 507235, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.998163104057312, "global_step": 507236, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.087574005126953, "global_step": 507237, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0043187141418457, "global_step": 507238, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9810523986816406, "global_step": 507239, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9585562944412231, "global_step": 507240, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0241482257843018, "global_step": 507241, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0681192874908447, "global_step": 507242, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0643577575683594, "global_step": 507243, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.993974208831787, "global_step": 507244, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0283472537994385, "global_step": 507245, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.114793062210083, "global_step": 507246, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.006685256958008, "global_step": 507247, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.092719078063965, "global_step": 507248, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9994525909423828, "global_step": 507249, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0947694778442383, "global_step": 507250, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0769898891448975, "global_step": 507251, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9941046237945557, "global_step": 507252, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9640558958053589, "global_step": 507253, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.082650661468506, "global_step": 507254, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9931223392486572, "global_step": 507255, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0627634525299072, "global_step": 507256, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0919246673583984, "global_step": 507257, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.055347204208374, "global_step": 507258, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.011934280395508, "global_step": 507259, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1102747917175293, "global_step": 507260, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0341169834136963, "global_step": 507261, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.045484781265259, "global_step": 507262, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9308604001998901, "global_step": 507263, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1279873847961426, "global_step": 507264, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.98123037815094, "global_step": 507265, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.02276611328125, "global_step": 507266, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0469043254852295, "global_step": 507267, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9041067361831665, "global_step": 507268, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.077956199645996, "global_step": 507269, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9668078422546387, "global_step": 507270, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0553479194641113, "global_step": 507271, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0485026836395264, "global_step": 507272, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0465869903564453, "global_step": 507273, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.093963623046875, "global_step": 507274, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0294649600982666, "global_step": 507275, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.078200578689575, "global_step": 507276, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.042681932449341, "global_step": 507277, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.075504779815674, "global_step": 507278, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0490522384643555, "global_step": 507279, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1012425422668457, "global_step": 507280, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1070973873138428, "global_step": 507281, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9842318296432495, "global_step": 507282, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9833765029907227, "global_step": 507283, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.051539421081543, "global_step": 507284, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.020451545715332, "global_step": 507285, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0275161266326904, "global_step": 507286, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.053340435028076, "global_step": 507287, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0758440494537354, "global_step": 507288, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0697214603424072, "global_step": 507289, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.024757146835327, "global_step": 507290, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.2027153968811035, "global_step": 507291, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0413734912872314, "global_step": 507292, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9762228727340698, "global_step": 507293, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0815138816833496, "global_step": 507294, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.016334295272827, "global_step": 507295, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9802085161209106, "global_step": 507296, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.084479331970215, "global_step": 507297, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0551109313964844, "global_step": 507298, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.005756378173828, "global_step": 507299, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.112192153930664, "global_step": 507300, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0641634464263916, "global_step": 507301, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.00065279006958, "global_step": 507302, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.189535140991211, "global_step": 507303, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0744972229003906, "global_step": 507304, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0077099800109863, "global_step": 507305, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0590434074401855, "global_step": 507306, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0023138523101807, "global_step": 507307, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0760695934295654, "global_step": 507308, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9528424739837646, "global_step": 507309, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0425188541412354, "global_step": 507310, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.109086513519287, "global_step": 507311, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.013944149017334, "global_step": 507312, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.068391799926758, "global_step": 507313, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.099513530731201, "global_step": 507314, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.040870428085327, "global_step": 507315, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0120325088500977, "global_step": 507316, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0529675483703613, "global_step": 507317, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.011850357055664, "global_step": 507318, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.006258010864258, "global_step": 507319, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.049060583114624, "global_step": 507320, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0315983295440674, "global_step": 507321, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9494105577468872, "global_step": 507322, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0092732906341553, "global_step": 507323, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.049595594406128, "global_step": 507324, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9718080759048462, "global_step": 507325, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9979383945465088, "global_step": 507326, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.041022300720215, "global_step": 507327, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0771381855010986, "global_step": 507328, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.013106107711792, "global_step": 507329, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0233285427093506, "global_step": 507330, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0208261013031006, "global_step": 507331, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.069660186767578, "global_step": 507332, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.036139965057373, "global_step": 507333, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0169003009796143, "global_step": 507334, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0560965538024902, "global_step": 507335, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.086434841156006, "global_step": 507336, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.006510019302368, "global_step": 507337, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1101503372192383, "global_step": 507338, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0346059799194336, "global_step": 507339, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.115712881088257, "global_step": 507340, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0083773136138916, "global_step": 507341, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.075474500656128, "global_step": 507342, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0630011558532715, "global_step": 507343, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.044987678527832, "global_step": 507344, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0094823837280273, "global_step": 507345, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9966011047363281, "global_step": 507346, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.974812388420105, "global_step": 507347, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.061084270477295, "global_step": 507348, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1004292964935303, "global_step": 507349, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.019674301147461, "global_step": 507350, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9754664897918701, "global_step": 507351, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.036623477935791, "global_step": 507352, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.089966297149658, "global_step": 507353, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0691847801208496, "global_step": 507354, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.089430570602417, "global_step": 507355, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0435569286346436, "global_step": 507356, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1036782264709473, "global_step": 507357, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.077744483947754, "global_step": 507358, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0338525772094727, "global_step": 507359, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0635809898376465, "global_step": 507360, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0519180297851562, "global_step": 507361, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0590248107910156, "global_step": 507362, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0826025009155273, "global_step": 507363, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.013470411300659, "global_step": 507364, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1135692596435547, "global_step": 507365, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0670273303985596, "global_step": 507366, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0869903564453125, "global_step": 507367, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.001629590988159, "global_step": 507368, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.009491443634033, "global_step": 507369, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.05660343170166, "global_step": 507370, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0202860832214355, "global_step": 507371, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0291314125061035, "global_step": 507372, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0334489345550537, "global_step": 507373, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1300833225250244, "global_step": 507374, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0337071418762207, "global_step": 507375, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.080676317214966, "global_step": 507376, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.062730550765991, "global_step": 507377, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.146707534790039, "global_step": 507378, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9992657899856567, "global_step": 507379, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.079423189163208, "global_step": 507380, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9363243579864502, "global_step": 507381, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0456387996673584, "global_step": 507382, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.070375442504883, "global_step": 507383, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1160178184509277, "global_step": 507384, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0177218914031982, "global_step": 507385, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.031008720397949, "global_step": 507386, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.056997299194336, "global_step": 507387, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.076598882675171, "global_step": 507388, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9832643270492554, "global_step": 507389, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.119856357574463, "global_step": 507390, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.027724504470825, "global_step": 507391, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0653233528137207, "global_step": 507392, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0035994052886963, "global_step": 507393, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0485379695892334, "global_step": 507394, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9924046993255615, "global_step": 507395, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0276174545288086, "global_step": 507396, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0196759700775146, "global_step": 507397, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0142719745635986, "global_step": 507398, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9766291379928589, "global_step": 507399, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0409562587738037, "global_step": 507400, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0192365646362305, "global_step": 507401, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0535755157470703, "global_step": 507402, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0985772609710693, "global_step": 507403, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.044114112854004, "global_step": 507404, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0337162017822266, "global_step": 507405, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1554763317108154, "global_step": 507406, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1085991859436035, "global_step": 507407, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0703234672546387, "global_step": 507408, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0319437980651855, "global_step": 507409, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0374550819396973, "global_step": 507410, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9797062873840332, "global_step": 507411, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9875783920288086, "global_step": 507412, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.012925386428833, "global_step": 507413, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0402603149414062, "global_step": 507414, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9860745668411255, "global_step": 507415, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.998049020767212, "global_step": 507416, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.092743158340454, "global_step": 507417, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.013418197631836, "global_step": 507418, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.024815559387207, "global_step": 507419, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0705556869506836, "global_step": 507420, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.031221866607666, "global_step": 507421, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0247230529785156, "global_step": 507422, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9933253526687622, "global_step": 507423, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9566624164581299, "global_step": 507424, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.032154083251953, "global_step": 507425, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.000307321548462, "global_step": 507426, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9929585456848145, "global_step": 507427, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1001224517822266, "global_step": 507428, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.014950752258301, "global_step": 507429, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9835516214370728, "global_step": 507430, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9987636804580688, "global_step": 507431, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0398683547973633, "global_step": 507432, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9650838375091553, "global_step": 507433, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0435097217559814, "global_step": 507434, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.110100269317627, "global_step": 507435, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0268566608428955, "global_step": 507436, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.979387879371643, "global_step": 507437, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0585055351257324, "global_step": 507438, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0020344257354736, "global_step": 507439, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.032959461212158, "global_step": 507440, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0023739337921143, "global_step": 507441, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0908989906311035, "global_step": 507442, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0747690200805664, "global_step": 507443, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0615880489349365, "global_step": 507444, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.073495626449585, "global_step": 507445, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9502376317977905, "global_step": 507446, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.044992685317993, "global_step": 507447, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0987274646759033, "global_step": 507448, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0132079124450684, "global_step": 507449, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1249840259552, "global_step": 507450, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.037358522415161, "global_step": 507451, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0701701641082764, "global_step": 507452, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1123228073120117, "global_step": 507453, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1183531284332275, "global_step": 507454, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0297939777374268, "global_step": 507455, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.006977081298828, "global_step": 507456, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1004374027252197, "global_step": 507457, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.029801845550537, "global_step": 507458, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9821339845657349, "global_step": 507459, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.022054672241211, "global_step": 507460, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0178401470184326, "global_step": 507461, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9445850849151611, "global_step": 507462, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0120954513549805, "global_step": 507463, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.061602830886841, "global_step": 507464, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0350232124328613, "global_step": 507465, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.938378095626831, "global_step": 507466, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0071938037872314, "global_step": 507467, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0466148853302, "global_step": 507468, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9914530515670776, "global_step": 507469, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.004631280899048, "global_step": 507470, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0682170391082764, "global_step": 507471, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9901849031448364, "global_step": 507472, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.102637767791748, "global_step": 507473, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.099153995513916, "global_step": 507474, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0274078845977783, "global_step": 507475, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.048356771469116, "global_step": 507476, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.107886791229248, "global_step": 507477, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0624566078186035, "global_step": 507478, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.070995330810547, "global_step": 507479, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0674054622650146, "global_step": 507480, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9421614408493042, "global_step": 507481, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9966561794281006, "global_step": 507482, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.042393922805786, "global_step": 507483, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0215773582458496, "global_step": 507484, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9812473058700562, "global_step": 507485, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.100187301635742, "global_step": 507486, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1666147708892822, "global_step": 507487, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0375161170959473, "global_step": 507488, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1223742961883545, "global_step": 507489, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9759551286697388, "global_step": 507490, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0260732173919678, "global_step": 507491, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0406081676483154, "global_step": 507492, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0181431770324707, "global_step": 507493, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.047736406326294, "global_step": 507494, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.129573106765747, "global_step": 507495, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.038628339767456, "global_step": 507496, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9829460382461548, "global_step": 507497, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1165881156921387, "global_step": 507498, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0862367153167725, "global_step": 507499, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.985002875328064, "global_step": 507500, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9993089437484741, "global_step": 507501, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.108227491378784, "global_step": 507502, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.044201374053955, "global_step": 507503, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.130622386932373, "global_step": 507504, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0388026237487793, "global_step": 507505, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.120587110519409, "global_step": 507506, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.086904525756836, "global_step": 507507, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.058730363845825, "global_step": 507508, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.033719062805176, "global_step": 507509, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9809935092926025, "global_step": 507510, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0113935470581055, "global_step": 507511, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9856984615325928, "global_step": 507512, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1316640377044678, "global_step": 507513, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0173163414001465, "global_step": 507514, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.957335114479065, "global_step": 507515, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0192196369171143, "global_step": 507516, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0423450469970703, "global_step": 507517, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0121583938598633, "global_step": 507518, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.033602714538574, "global_step": 507519, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.985442042350769, "global_step": 507520, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0401740074157715, "global_step": 507521, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0457468032836914, "global_step": 507522, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9996403455734253, "global_step": 507523, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.02874493598938, "global_step": 507524, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.026289939880371, "global_step": 507525, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.114898681640625, "global_step": 507526, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9938392639160156, "global_step": 507527, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.022952079772949, "global_step": 507528, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9209988117218018, "global_step": 507529, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0215604305267334, "global_step": 507530, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0239522457122803, "global_step": 507531, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.095341920852661, "global_step": 507532, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.191314697265625, "global_step": 507533, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.13081431388855, "global_step": 507534, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.112865924835205, "global_step": 507535, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0602145195007324, "global_step": 507536, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.036264181137085, "global_step": 507537, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9960311651229858, "global_step": 507538, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.128676652908325, "global_step": 507539, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9575095176696777, "global_step": 507540, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.078293800354004, "global_step": 507541, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.964026689529419, "global_step": 507542, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0225319862365723, "global_step": 507543, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9560821056365967, "global_step": 507544, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0425760746002197, "global_step": 507545, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1004316806793213, "global_step": 507546, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.038264513015747, "global_step": 507547, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0066428184509277, "global_step": 507548, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0910305976867676, "global_step": 507549, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1477062702178955, "global_step": 507550, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.028088092803955, "global_step": 507551, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9832302331924438, "global_step": 507552, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1400651931762695, "global_step": 507553, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0636353492736816, "global_step": 507554, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0954487323760986, "global_step": 507555, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.035825252532959, "global_step": 507556, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0275068283081055, "global_step": 507557, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0026869773864746, "global_step": 507558, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.07776141166687, "global_step": 507559, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0317037105560303, "global_step": 507560, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0684268474578857, "global_step": 507561, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9544230699539185, "global_step": 507562, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.984601378440857, "global_step": 507563, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9809517860412598, "global_step": 507564, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1147308349609375, "global_step": 507565, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.091904640197754, "global_step": 507566, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0387461185455322, "global_step": 507567, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0806491374969482, "global_step": 507568, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.022763729095459, "global_step": 507569, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0395007133483887, "global_step": 507570, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0400373935699463, "global_step": 507571, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.102975845336914, "global_step": 507572, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.068112850189209, "global_step": 507573, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.114053726196289, "global_step": 507574, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0294222831726074, "global_step": 507575, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0076963901519775, "global_step": 507576, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.034320592880249, "global_step": 507577, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.023777484893799, "global_step": 507578, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0420191287994385, "global_step": 507579, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0711686611175537, "global_step": 507580, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0696659088134766, "global_step": 507581, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.061406373977661, "global_step": 507582, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.078805685043335, "global_step": 507583, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1065120697021484, "global_step": 507584, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.080601453781128, "global_step": 507585, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.066479206085205, "global_step": 507586, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0809707641601562, "global_step": 507587, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.113844871520996, "global_step": 507588, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.026348114013672, "global_step": 507589, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0410563945770264, "global_step": 507590, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0140552520751953, "global_step": 507591, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.990679144859314, "global_step": 507592, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0560302734375, "global_step": 507593, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9779249429702759, "global_step": 507594, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0504279136657715, "global_step": 507595, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.101789712905884, "global_step": 507596, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.087413787841797, "global_step": 507597, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1031367778778076, "global_step": 507598, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0677638053894043, "global_step": 507599, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0182511806488037, "global_step": 507600, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0454840660095215, "global_step": 507601, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.04003643989563, "global_step": 507602, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1071486473083496, "global_step": 507603, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0280299186706543, "global_step": 507604, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.920987844467163, "global_step": 507605, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.089735269546509, "global_step": 507606, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.079918622970581, "global_step": 507607, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.056680679321289, "global_step": 507608, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0427188873291016, "global_step": 507609, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.065408706665039, "global_step": 507610, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.080681800842285, "global_step": 507611, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.038550853729248, "global_step": 507612, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9386612176895142, "global_step": 507613, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.131634473800659, "global_step": 507614, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0503897666931152, "global_step": 507615, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0983879566192627, "global_step": 507616, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0321574211120605, "global_step": 507617, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.088757276535034, "global_step": 507618, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0251595973968506, "global_step": 507619, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0046918392181396, "global_step": 507620, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.086359977722168, "global_step": 507621, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.041177749633789, "global_step": 507622, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0293829441070557, "global_step": 507623, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1380228996276855, "global_step": 507624, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0704452991485596, "global_step": 507625, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.038503646850586, "global_step": 507626, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.081172227859497, "global_step": 507627, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0755200386047363, "global_step": 507628, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9894535541534424, "global_step": 507629, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0594804286956787, "global_step": 507630, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.055694818496704, "global_step": 507631, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0783567428588867, "global_step": 507632, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0817604064941406, "global_step": 507633, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0098156929016113, "global_step": 507634, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.967629075050354, "global_step": 507635, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.033933162689209, "global_step": 507636, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0802814960479736, "global_step": 507637, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.023102283477783, "global_step": 507638, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9995415210723877, "global_step": 507639, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1258509159088135, "global_step": 507640, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.055622100830078, "global_step": 507641, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9351695775985718, "global_step": 507642, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0822203159332275, "global_step": 507643, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.042905330657959, "global_step": 507644, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0279488563537598, "global_step": 507645, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0116360187530518, "global_step": 507646, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.070638418197632, "global_step": 507647, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0668632984161377, "global_step": 507648, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.051453113555908, "global_step": 507649, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0632646083831787, "global_step": 507650, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.170712471008301, "global_step": 507651, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0669729709625244, "global_step": 507652, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.02987003326416, "global_step": 507653, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.973170280456543, "global_step": 507654, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1654369831085205, "global_step": 507655, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0936341285705566, "global_step": 507656, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0280721187591553, "global_step": 507657, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.034980535507202, "global_step": 507658, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.008213520050049, "global_step": 507659, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1352052688598633, "global_step": 507660, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0052032470703125, "global_step": 507661, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0176451206207275, "global_step": 507662, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0851850509643555, "global_step": 507663, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0339183807373047, "global_step": 507664, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0906386375427246, "global_step": 507665, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0797042846679688, "global_step": 507666, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0425801277160645, "global_step": 507667, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.03226375579834, "global_step": 507668, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.00811505317688, "global_step": 507669, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9874593019485474, "global_step": 507670, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0890729427337646, "global_step": 507671, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.021989107131958, "global_step": 507672, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.038761615753174, "global_step": 507673, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.070976495742798, "global_step": 507674, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0129997730255127, "global_step": 507675, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9962763786315918, "global_step": 507676, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0180206298828125, "global_step": 507677, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0670175552368164, "global_step": 507678, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1264395713806152, "global_step": 507679, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.070639133453369, "global_step": 507680, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0152344703674316, "global_step": 507681, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1054561138153076, "global_step": 507682, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0028488636016846, "global_step": 507683, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.039207696914673, "global_step": 507684, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.051305055618286, "global_step": 507685, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.039055585861206, "global_step": 507686, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.028911828994751, "global_step": 507687, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0819814205169678, "global_step": 507688, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.058744430541992, "global_step": 507689, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.023693561553955, "global_step": 507690, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0233142375946045, "global_step": 507691, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.074617624282837, "global_step": 507692, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.100238800048828, "global_step": 507693, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0444376468658447, "global_step": 507694, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.059643268585205, "global_step": 507695, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.060825824737549, "global_step": 507696, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0468599796295166, "global_step": 507697, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0255298614501953, "global_step": 507698, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.008937358856201, "global_step": 507699, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0692195892333984, "global_step": 507700, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0121231079101562, "global_step": 507701, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0137107372283936, "global_step": 507702, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.073151111602783, "global_step": 507703, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.035637855529785, "global_step": 507704, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0756354331970215, "global_step": 507705, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0236122608184814, "global_step": 507706, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0590639114379883, "global_step": 507707, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0422072410583496, "global_step": 507708, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.079007387161255, "global_step": 507709, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0620689392089844, "global_step": 507710, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.005180835723877, "global_step": 507711, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.97259521484375, "global_step": 507712, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.031938076019287, "global_step": 507713, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.001504421234131, "global_step": 507714, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.124577760696411, "global_step": 507715, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.054112434387207, "global_step": 507716, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0873284339904785, "global_step": 507717, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1145455837249756, "global_step": 507718, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0033087730407715, "global_step": 507719, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0804481506347656, "global_step": 507720, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0267038345336914, "global_step": 507721, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0759170055389404, "global_step": 507722, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.110257625579834, "global_step": 507723, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0217769145965576, "global_step": 507724, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1043779850006104, "global_step": 507725, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.090176820755005, "global_step": 507726, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9925246238708496, "global_step": 507727, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.050211191177368, "global_step": 507728, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0569097995758057, "global_step": 507729, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.948486328125, "global_step": 507730, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0658164024353027, "global_step": 507731, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.055417060852051, "global_step": 507732, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0702857971191406, "global_step": 507733, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0902340412139893, "global_step": 507734, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0443496704101562, "global_step": 507735, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0912811756134033, "global_step": 507736, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0939183235168457, "global_step": 507737, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9962295293807983, "global_step": 507738, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0991921424865723, "global_step": 507739, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0464911460876465, "global_step": 507740, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0950722694396973, "global_step": 507741, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0449578762054443, "global_step": 507742, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.141157627105713, "global_step": 507743, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0828118324279785, "global_step": 507744, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0354714393615723, "global_step": 507745, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0359621047973633, "global_step": 507746, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.122896909713745, "global_step": 507747, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0964667797088623, "global_step": 507748, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.074939727783203, "global_step": 507749, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0627498626708984, "global_step": 507750, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0742545127868652, "global_step": 507751, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9983223676681519, "global_step": 507752, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.069234609603882, "global_step": 507753, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0511696338653564, "global_step": 507754, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1162147521972656, "global_step": 507755, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0826191902160645, "global_step": 507756, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.099783182144165, "global_step": 507757, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0499587059020996, "global_step": 507758, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.058955192565918, "global_step": 507759, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.958155632019043, "global_step": 507760, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1470515727996826, "global_step": 507761, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0779807567596436, "global_step": 507762, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1180102825164795, "global_step": 507763, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0596718788146973, "global_step": 507764, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.988787293434143, "global_step": 507765, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0822043418884277, "global_step": 507766, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0613417625427246, "global_step": 507767, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.108811378479004, "global_step": 507768, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.993360161781311, "global_step": 507769, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0423920154571533, "global_step": 507770, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.984097957611084, "global_step": 507771, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.127601385116577, "global_step": 507772, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.084946632385254, "global_step": 507773, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0565052032470703, "global_step": 507774, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0907020568847656, "global_step": 507775, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.103182315826416, "global_step": 507776, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.089667558670044, "global_step": 507777, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.056004762649536, "global_step": 507778, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0433778762817383, "global_step": 507779, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.032125949859619, "global_step": 507780, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0471432209014893, "global_step": 507781, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0279324054718018, "global_step": 507782, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.977565050125122, "global_step": 507783, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0363919734954834, "global_step": 507784, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9940454959869385, "global_step": 507785, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.006650924682617, "global_step": 507786, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9951214790344238, "global_step": 507787, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.033595085144043, "global_step": 507788, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.033013105392456, "global_step": 507789, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.018685817718506, "global_step": 507790, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.995710849761963, "global_step": 507791, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.018176794052124, "global_step": 507792, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0484254360198975, "global_step": 507793, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0395090579986572, "global_step": 507794, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.097085952758789, "global_step": 507795, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9817798137664795, "global_step": 507796, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.062307596206665, "global_step": 507797, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.106891632080078, "global_step": 507798, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0646464824676514, "global_step": 507799, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0423355102539062, "global_step": 507800, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0489416122436523, "global_step": 507801, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.061943292617798, "global_step": 507802, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.052410364151001, "global_step": 507803, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0185301303863525, "global_step": 507804, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9937251806259155, "global_step": 507805, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0088016986846924, "global_step": 507806, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9943420886993408, "global_step": 507807, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0577664375305176, "global_step": 507808, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0302369594573975, "global_step": 507809, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.091545343399048, "global_step": 507810, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0650365352630615, "global_step": 507811, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.010526657104492, "global_step": 507812, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.134798526763916, "global_step": 507813, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9887932538986206, "global_step": 507814, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.989749550819397, "global_step": 507815, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.072364091873169, "global_step": 507816, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.013880491256714, "global_step": 507817, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.09627103805542, "global_step": 507818, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.196477174758911, "global_step": 507819, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1162614822387695, "global_step": 507820, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.071268081665039, "global_step": 507821, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0973267555236816, "global_step": 507822, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.082545280456543, "global_step": 507823, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1340513229370117, "global_step": 507824, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.005033493041992, "global_step": 507825, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9646728038787842, "global_step": 507826, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.043545961380005, "global_step": 507827, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.009871244430542, "global_step": 507828, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1471195220947266, "global_step": 507829, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1178712844848633, "global_step": 507830, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0743253231048584, "global_step": 507831, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0734400749206543, "global_step": 507832, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1736154556274414, "global_step": 507833, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0652177333831787, "global_step": 507834, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1079816818237305, "global_step": 507835, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0039525032043457, "global_step": 507836, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.078735113143921, "global_step": 507837, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0385782718658447, "global_step": 507838, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.10368013381958, "global_step": 507839, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0626659393310547, "global_step": 507840, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0664045810699463, "global_step": 507841, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0985989570617676, "global_step": 507842, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0558977127075195, "global_step": 507843, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.115602970123291, "global_step": 507844, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9103306531906128, "global_step": 507845, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0916357040405273, "global_step": 507846, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.923283338546753, "global_step": 507847, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9923961162567139, "global_step": 507848, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0263147354125977, "global_step": 507849, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.07593035697937, "global_step": 507850, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0761213302612305, "global_step": 507851, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0591800212860107, "global_step": 507852, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0581657886505127, "global_step": 507853, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0561904907226562, "global_step": 507854, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0759365558624268, "global_step": 507855, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1203975677490234, "global_step": 507856, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0489091873168945, "global_step": 507857, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9729673862457275, "global_step": 507858, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.092810869216919, "global_step": 507859, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.02249813079834, "global_step": 507860, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0127644538879395, "global_step": 507861, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.152313709259033, "global_step": 507862, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.191678285598755, "global_step": 507863, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.958269476890564, "global_step": 507864, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.105189085006714, "global_step": 507865, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.998326063156128, "global_step": 507866, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1084649562835693, "global_step": 507867, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0283114910125732, "global_step": 507868, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0976033210754395, "global_step": 507869, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0417168140411377, "global_step": 507870, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0607972145080566, "global_step": 507871, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0228960514068604, "global_step": 507872, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.006418466567993, "global_step": 507873, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.090629816055298, "global_step": 507874, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0544984340667725, "global_step": 507875, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0317580699920654, "global_step": 507876, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0700244903564453, "global_step": 507877, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9265000820159912, "global_step": 507878, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.089938163757324, "global_step": 507879, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.138803482055664, "global_step": 507880, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1039514541625977, "global_step": 507881, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.075930595397949, "global_step": 507882, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.1519505977630615, "global_step": 507883, "epoch": 873, "lr": 5e-05}
{"train_loss": 1.9386370182037354, "global_step": 507884, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0943236351013184, "global_step": 507885, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.019866704940796, "global_step": 507886, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.026444911956787, "global_step": 507887, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0468826293945312, "global_step": 507888, "epoch": 873, "lr": 5e-05}
{"train_loss": 2.0171449184417725, "global_step": 507889, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9879451990127563, "global_step": 507890, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9849023818969727, "global_step": 507891, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0482466220855713, "global_step": 507892, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.052333116531372, "global_step": 507893, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0698602199554443, "global_step": 507894, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0043625831604004, "global_step": 507895, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9842140674591064, "global_step": 507896, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.13082218170166, "global_step": 507897, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.096395492553711, "global_step": 507898, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0359745025634766, "global_step": 507899, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.038217306137085, "global_step": 507900, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0842525959014893, "global_step": 507901, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9668164253234863, "global_step": 507902, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.996782898902893, "global_step": 507903, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0717194080352783, "global_step": 507904, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0375020503997803, "global_step": 507905, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0879623889923096, "global_step": 507906, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0646955966949463, "global_step": 507907, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.973093867301941, "global_step": 507908, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.127851724624634, "global_step": 507909, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0669093132019043, "global_step": 507910, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0029542446136475, "global_step": 507911, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0054233074188232, "global_step": 507912, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.979810118675232, "global_step": 507913, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0436296463012695, "global_step": 507914, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.088125705718994, "global_step": 507915, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0143425464630127, "global_step": 507916, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.104883909225464, "global_step": 507917, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.981278657913208, "global_step": 507918, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0933055877685547, "global_step": 507919, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.106135845184326, "global_step": 507920, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0898475646972656, "global_step": 507921, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9926328659057617, "global_step": 507922, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0944361686706543, "global_step": 507923, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0645534992218018, "global_step": 507924, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.096618890762329, "global_step": 507925, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.04423189163208, "global_step": 507926, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1105284690856934, "global_step": 507927, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0170419216156006, "global_step": 507928, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.046201705932617, "global_step": 507929, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0873899459838867, "global_step": 507930, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.034911632537842, "global_step": 507931, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0780491828918457, "global_step": 507932, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0372421741485596, "global_step": 507933, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0682320594787598, "global_step": 507934, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.007380723953247, "global_step": 507935, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.071937322616577, "global_step": 507936, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.100090980529785, "global_step": 507937, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0719659328460693, "global_step": 507938, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.980637788772583, "global_step": 507939, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.027440071105957, "global_step": 507940, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.984489917755127, "global_step": 507941, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0350325107574463, "global_step": 507942, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0176079273223877, "global_step": 507943, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1004977226257324, "global_step": 507944, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.097402572631836, "global_step": 507945, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.062549114227295, "global_step": 507946, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.996887445449829, "global_step": 507947, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.062267303466797, "global_step": 507948, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0300285816192627, "global_step": 507949, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9788893461227417, "global_step": 507950, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.054260492324829, "global_step": 507951, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.04360294342041, "global_step": 507952, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0100057125091553, "global_step": 507953, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.073690891265869, "global_step": 507954, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0044007301330566, "global_step": 507955, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1618456840515137, "global_step": 507956, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0424885749816895, "global_step": 507957, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0330698490142822, "global_step": 507958, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.021169900894165, "global_step": 507959, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9924209117889404, "global_step": 507960, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.117067813873291, "global_step": 507961, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9870163202285767, "global_step": 507962, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0214426517486572, "global_step": 507963, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0727007389068604, "global_step": 507964, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.027406930923462, "global_step": 507965, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0181217193603516, "global_step": 507966, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0800116062164307, "global_step": 507967, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.028836250305176, "global_step": 507968, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0590944290161133, "global_step": 507969, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0216662883758545, "global_step": 507970, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0309526920318604, "global_step": 507971, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.020028829574585, "global_step": 507972, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.038633346557617, "global_step": 507973, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0235755443573, "global_step": 507974, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1313323974609375, "global_step": 507975, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.007758378982544, "global_step": 507976, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.082207202911377, "global_step": 507977, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0562562942504883, "global_step": 507978, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0420305728912354, "global_step": 507979, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.103820323944092, "global_step": 507980, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0420432090759277, "global_step": 507981, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9568458795547485, "global_step": 507982, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.128591299057007, "global_step": 507983, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.15222430229187, "global_step": 507984, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.001385450363159, "global_step": 507985, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.033074140548706, "global_step": 507986, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.092256784439087, "global_step": 507987, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.078521251678467, "global_step": 507988, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.029876708984375, "global_step": 507989, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.082709550857544, "global_step": 507990, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.079190492630005, "global_step": 507991, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0979127883911133, "global_step": 507992, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.108762502670288, "global_step": 507993, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0079376697540283, "global_step": 507994, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9954397678375244, "global_step": 507995, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1447033882141113, "global_step": 507996, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0520577430725098, "global_step": 507997, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.933793067932129, "global_step": 507998, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0875041484832764, "global_step": 507999, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.018181562423706, "global_step": 508000, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.031266689300537, "global_step": 508001, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9974488019943237, "global_step": 508002, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9926358461380005, "global_step": 508003, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1404876708984375, "global_step": 508004, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.06016206741333, "global_step": 508005, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.11877179145813, "global_step": 508006, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0225162506103516, "global_step": 508007, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0173308849334717, "global_step": 508008, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.039848804473877, "global_step": 508009, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0254695415496826, "global_step": 508010, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.970646858215332, "global_step": 508011, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9445358514785767, "global_step": 508012, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0650389194488525, "global_step": 508013, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.001513719558716, "global_step": 508014, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.048943281173706, "global_step": 508015, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.095050096511841, "global_step": 508016, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.13462233543396, "global_step": 508017, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.084242343902588, "global_step": 508018, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0169758796691895, "global_step": 508019, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.122356414794922, "global_step": 508020, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0019993782043457, "global_step": 508021, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.025376558303833, "global_step": 508022, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0242505073547363, "global_step": 508023, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.930687427520752, "global_step": 508024, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0963480472564697, "global_step": 508025, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0861592292785645, "global_step": 508026, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0951192378997803, "global_step": 508027, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.031698703765869, "global_step": 508028, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0319151878356934, "global_step": 508029, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9620081186294556, "global_step": 508030, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.010618209838867, "global_step": 508031, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.024709701538086, "global_step": 508032, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0162436962127686, "global_step": 508033, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0707485675811768, "global_step": 508034, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0028233528137207, "global_step": 508035, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0830864906311035, "global_step": 508036, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.060407876968384, "global_step": 508037, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.02506160736084, "global_step": 508038, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1211953163146973, "global_step": 508039, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.034440040588379, "global_step": 508040, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.071427583694458, "global_step": 508041, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.076739549636841, "global_step": 508042, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0207080841064453, "global_step": 508043, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9894920587539673, "global_step": 508044, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0467207431793213, "global_step": 508045, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0124406814575195, "global_step": 508046, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1252055168151855, "global_step": 508047, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.038713216781616, "global_step": 508048, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0402536392211914, "global_step": 508049, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1188671588897705, "global_step": 508050, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0609824657440186, "global_step": 508051, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0034396648406982, "global_step": 508052, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.959875464439392, "global_step": 508053, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0214123725891113, "global_step": 508054, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.103731155395508, "global_step": 508055, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.021599292755127, "global_step": 508056, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0608506202697754, "global_step": 508057, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.083016872406006, "global_step": 508058, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0580718517303467, "global_step": 508059, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.014071226119995, "global_step": 508060, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1119840145111084, "global_step": 508061, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.010957717895508, "global_step": 508062, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.00984263420105, "global_step": 508063, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1068642139434814, "global_step": 508064, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.036679983139038, "global_step": 508065, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.050812005996704, "global_step": 508066, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.045131206512451, "global_step": 508067, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0118610858917236, "global_step": 508068, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9760359525680542, "global_step": 508069, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.085526943206787, "global_step": 508070, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0116381645202637, "global_step": 508071, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9993393421173096, "global_step": 508072, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.057192325592041, "global_step": 508073, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0355420112609863, "global_step": 508074, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0470569133758545, "global_step": 508075, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0758016109466553, "global_step": 508076, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.014380931854248, "global_step": 508077, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9607361555099487, "global_step": 508078, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9968725442886353, "global_step": 508079, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0572309494018555, "global_step": 508080, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0679190158843994, "global_step": 508081, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.028702735900879, "global_step": 508082, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9889947175979614, "global_step": 508083, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9769248962402344, "global_step": 508084, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9832549095153809, "global_step": 508085, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.03549861907959, "global_step": 508086, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.148106336593628, "global_step": 508087, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.115588665008545, "global_step": 508088, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0338191986083984, "global_step": 508089, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0068142414093018, "global_step": 508090, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1271557807922363, "global_step": 508091, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.130204200744629, "global_step": 508092, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.101562023162842, "global_step": 508093, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9386217594146729, "global_step": 508094, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9944486618041992, "global_step": 508095, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9787355661392212, "global_step": 508096, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.043520212173462, "global_step": 508097, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9209407567977905, "global_step": 508098, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9648481607437134, "global_step": 508099, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.057541847229004, "global_step": 508100, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.066798210144043, "global_step": 508101, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0800845623016357, "global_step": 508102, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0473504066467285, "global_step": 508103, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0680899620056152, "global_step": 508104, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9946430921554565, "global_step": 508105, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0409224033355713, "global_step": 508106, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.031494617462158, "global_step": 508107, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.090758800506592, "global_step": 508108, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.045149803161621, "global_step": 508109, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.031064748764038, "global_step": 508110, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0190677642822266, "global_step": 508111, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9753903150558472, "global_step": 508112, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.025075912475586, "global_step": 508113, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.091348648071289, "global_step": 508114, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9139907360076904, "global_step": 508115, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.043437957763672, "global_step": 508116, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0865142345428467, "global_step": 508117, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0571393966674805, "global_step": 508118, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.019244909286499, "global_step": 508119, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0605835914611816, "global_step": 508120, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0063278675079346, "global_step": 508121, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.001925468444824, "global_step": 508122, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1269004344940186, "global_step": 508123, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0160083770751953, "global_step": 508124, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.039792537689209, "global_step": 508125, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.023855686187744, "global_step": 508126, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0091068744659424, "global_step": 508127, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1037967205047607, "global_step": 508128, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.169492244720459, "global_step": 508129, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.8971232175827026, "global_step": 508130, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0176751613616943, "global_step": 508131, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.119354724884033, "global_step": 508132, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0489156246185303, "global_step": 508133, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9858208894729614, "global_step": 508134, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0562374591827393, "global_step": 508135, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.132963180541992, "global_step": 508136, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0691182613372803, "global_step": 508137, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9896605014801025, "global_step": 508138, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0508358478546143, "global_step": 508139, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0768723487854004, "global_step": 508140, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9411581754684448, "global_step": 508141, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0526092052459717, "global_step": 508142, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1416733264923096, "global_step": 508143, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0203566551208496, "global_step": 508144, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0339319705963135, "global_step": 508145, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0301454067230225, "global_step": 508146, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.054142475128174, "global_step": 508147, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1253600120544434, "global_step": 508148, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9779331684112549, "global_step": 508149, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.041968584060669, "global_step": 508150, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9286576509475708, "global_step": 508151, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0861432552337646, "global_step": 508152, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.057070016860962, "global_step": 508153, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0343852043151855, "global_step": 508154, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0884251594543457, "global_step": 508155, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.073317289352417, "global_step": 508156, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.02012300491333, "global_step": 508157, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0474839210510254, "global_step": 508158, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0227463245391846, "global_step": 508159, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0087146759033203, "global_step": 508160, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.047614574432373, "global_step": 508161, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.03432297706604, "global_step": 508162, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0795645713806152, "global_step": 508163, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1313488483428955, "global_step": 508164, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0773143768310547, "global_step": 508165, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0669498443603516, "global_step": 508166, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.091517686843872, "global_step": 508167, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.105792999267578, "global_step": 508168, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.087667226791382, "global_step": 508169, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.111675500869751, "global_step": 508170, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0703623294830322, "global_step": 508171, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0110671520233154, "global_step": 508172, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.050246238708496, "global_step": 508173, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.080268383026123, "global_step": 508174, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9982954263687134, "global_step": 508175, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.032027006149292, "global_step": 508176, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0603950023651123, "global_step": 508177, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.06900691986084, "global_step": 508178, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.014540910720825, "global_step": 508179, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.076697826385498, "global_step": 508180, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1005191802978516, "global_step": 508181, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1320149898529053, "global_step": 508182, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.097398042678833, "global_step": 508183, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9652084112167358, "global_step": 508184, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.015341281890869, "global_step": 508185, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.117664337158203, "global_step": 508186, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.933531403541565, "global_step": 508187, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.083585262298584, "global_step": 508188, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9716492891311646, "global_step": 508189, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.151804208755493, "global_step": 508190, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.060002565383911, "global_step": 508191, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.048661231994629, "global_step": 508192, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.988584041595459, "global_step": 508193, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.986510157585144, "global_step": 508194, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.034348249435425, "global_step": 508195, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.125075101852417, "global_step": 508196, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0739519596099854, "global_step": 508197, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9991194009780884, "global_step": 508198, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.971898078918457, "global_step": 508199, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.984700322151184, "global_step": 508200, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.097965717315674, "global_step": 508201, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.043375253677368, "global_step": 508202, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0771379470825195, "global_step": 508203, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0216939449310303, "global_step": 508204, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9602527618408203, "global_step": 508205, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.043560028076172, "global_step": 508206, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.019737482070923, "global_step": 508207, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.086714267730713, "global_step": 508208, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.04290509223938, "global_step": 508209, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0231125354766846, "global_step": 508210, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.093224287033081, "global_step": 508211, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0569467544555664, "global_step": 508212, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0007879734039307, "global_step": 508213, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1464478969573975, "global_step": 508214, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0344133377075195, "global_step": 508215, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1055119037628174, "global_step": 508216, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9915918111801147, "global_step": 508217, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0177700519561768, "global_step": 508218, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.045689582824707, "global_step": 508219, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.012396812438965, "global_step": 508220, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.992315411567688, "global_step": 508221, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.078331470489502, "global_step": 508222, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0181431770324707, "global_step": 508223, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.007903814315796, "global_step": 508224, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.993628978729248, "global_step": 508225, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0876994132995605, "global_step": 508226, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.028188943862915, "global_step": 508227, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0702669620513916, "global_step": 508228, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9914252758026123, "global_step": 508229, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.061448812484741, "global_step": 508230, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9791220426559448, "global_step": 508231, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0102789402008057, "global_step": 508232, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.025632381439209, "global_step": 508233, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9668792486190796, "global_step": 508234, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0148727893829346, "global_step": 508235, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9942342042922974, "global_step": 508236, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.048945426940918, "global_step": 508237, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0979936122894287, "global_step": 508238, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.056126832962036, "global_step": 508239, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.970138669013977, "global_step": 508240, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0077764987945557, "global_step": 508241, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0349764823913574, "global_step": 508242, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9978053569793701, "global_step": 508243, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.10953688621521, "global_step": 508244, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.03420090675354, "global_step": 508245, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.070594310760498, "global_step": 508246, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9756965637207031, "global_step": 508247, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0075924396514893, "global_step": 508248, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0115392208099365, "global_step": 508249, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.105839967727661, "global_step": 508250, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0085983276367188, "global_step": 508251, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9732930660247803, "global_step": 508252, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.009702682495117, "global_step": 508253, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0163607597351074, "global_step": 508254, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.046903610229492, "global_step": 508255, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1354503631591797, "global_step": 508256, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.030059576034546, "global_step": 508257, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0748894214630127, "global_step": 508258, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0975000858306885, "global_step": 508259, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1705691814422607, "global_step": 508260, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.053647041320801, "global_step": 508261, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.999147891998291, "global_step": 508262, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0350818634033203, "global_step": 508263, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1254589557647705, "global_step": 508264, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9677983522415161, "global_step": 508265, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0850424766540527, "global_step": 508266, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1076300144195557, "global_step": 508267, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.111542224884033, "global_step": 508268, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0103156566619873, "global_step": 508269, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0039806365966797, "global_step": 508270, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0332279205322266, "global_step": 508271, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.033090114593506, "global_step": 508272, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.08378529548645, "global_step": 508273, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9877456426620483, "global_step": 508274, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0238077640533447, "global_step": 508275, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0394973754882812, "global_step": 508276, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0553066730499268, "global_step": 508277, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.04396915435791, "global_step": 508278, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.025434732437134, "global_step": 508279, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.086195707321167, "global_step": 508280, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0410995483398438, "global_step": 508281, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.004282236099243, "global_step": 508282, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.052626848220825, "global_step": 508283, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0364878177642822, "global_step": 508284, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.092127561569214, "global_step": 508285, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.993073582649231, "global_step": 508286, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.062278985977173, "global_step": 508287, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0366194248199463, "global_step": 508288, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0470077991485596, "global_step": 508289, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0588459968566895, "global_step": 508290, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0272037982940674, "global_step": 508291, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.14304518699646, "global_step": 508292, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.028966188430786, "global_step": 508293, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9650728702545166, "global_step": 508294, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0144267082214355, "global_step": 508295, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.102979898452759, "global_step": 508296, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.063924551010132, "global_step": 508297, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0393922328948975, "global_step": 508298, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9899927377700806, "global_step": 508299, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9086138010025024, "global_step": 508300, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.098677158355713, "global_step": 508301, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.023970365524292, "global_step": 508302, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0402884483337402, "global_step": 508303, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9440299272537231, "global_step": 508304, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0602149963378906, "global_step": 508305, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1002087593078613, "global_step": 508306, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1107017993927, "global_step": 508307, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0805821418762207, "global_step": 508308, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.103908061981201, "global_step": 508309, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.040766716003418, "global_step": 508310, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.11649227142334, "global_step": 508311, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0599467754364014, "global_step": 508312, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.017524480819702, "global_step": 508313, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.064565896987915, "global_step": 508314, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.050227165222168, "global_step": 508315, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.031052827835083, "global_step": 508316, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.07682728767395, "global_step": 508317, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0569722652435303, "global_step": 508318, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.006826400756836, "global_step": 508319, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.018031597137451, "global_step": 508320, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0280323028564453, "global_step": 508321, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0310800075531006, "global_step": 508322, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.046586036682129, "global_step": 508323, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.095546007156372, "global_step": 508324, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.081888437271118, "global_step": 508325, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.102456569671631, "global_step": 508326, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0249338150024414, "global_step": 508327, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1060214042663574, "global_step": 508328, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9474890232086182, "global_step": 508329, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0014641284942627, "global_step": 508330, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.996341586112976, "global_step": 508331, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.017544746398926, "global_step": 508332, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9536656141281128, "global_step": 508333, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0607340335845947, "global_step": 508334, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.036590337753296, "global_step": 508335, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0496444702148438, "global_step": 508336, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.999402642250061, "global_step": 508337, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.096665859222412, "global_step": 508338, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.112152099609375, "global_step": 508339, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1127355098724365, "global_step": 508340, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.018009662628174, "global_step": 508341, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0975475311279297, "global_step": 508342, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.143850088119507, "global_step": 508343, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9798834323883057, "global_step": 508344, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0823235511779785, "global_step": 508345, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0848300457000732, "global_step": 508346, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.140390634536743, "global_step": 508347, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.091573476791382, "global_step": 508348, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9691749811172485, "global_step": 508349, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0283501148223877, "global_step": 508350, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.000122547149658, "global_step": 508351, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0232574939727783, "global_step": 508352, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1077232360839844, "global_step": 508353, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9888732433319092, "global_step": 508354, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0441713333129883, "global_step": 508355, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0390396118164062, "global_step": 508356, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.144972324371338, "global_step": 508357, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1243486404418945, "global_step": 508358, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1622867584228516, "global_step": 508359, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0025229454040527, "global_step": 508360, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9777837991714478, "global_step": 508361, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0184707641601562, "global_step": 508362, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9891786575317383, "global_step": 508363, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.083261728286743, "global_step": 508364, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1072819232940674, "global_step": 508365, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9973852634429932, "global_step": 508366, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.002220392227173, "global_step": 508367, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1683177947998047, "global_step": 508368, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.984682559967041, "global_step": 508369, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1280617713928223, "global_step": 508370, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0547029972076416, "global_step": 508371, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.160719871520996, "global_step": 508372, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9316705465316772, "global_step": 508373, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.061148166656494, "global_step": 508374, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.015406608581543, "global_step": 508375, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.094395160675049, "global_step": 508376, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0020196437835693, "global_step": 508377, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.052656888961792, "global_step": 508378, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.041956663131714, "global_step": 508379, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0671262741088867, "global_step": 508380, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.97989821434021, "global_step": 508381, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0614867210388184, "global_step": 508382, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0800364017486572, "global_step": 508383, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0905675888061523, "global_step": 508384, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0779027938842773, "global_step": 508385, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.113295793533325, "global_step": 508386, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0677733421325684, "global_step": 508387, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0826544761657715, "global_step": 508388, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.973879337310791, "global_step": 508389, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.123028039932251, "global_step": 508390, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0188376903533936, "global_step": 508391, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.192960739135742, "global_step": 508392, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1762924194335938, "global_step": 508393, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.973037600517273, "global_step": 508394, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.020627021789551, "global_step": 508395, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9569591283798218, "global_step": 508396, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.053433895111084, "global_step": 508397, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9735486507415771, "global_step": 508398, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.075833559036255, "global_step": 508399, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.04382586479187, "global_step": 508400, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0498239994049072, "global_step": 508401, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.019963264465332, "global_step": 508402, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.126765727996826, "global_step": 508403, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.151560068130493, "global_step": 508404, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0706403255462646, "global_step": 508405, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0963921546936035, "global_step": 508406, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0620439052581787, "global_step": 508407, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.08984375, "global_step": 508408, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0347065925598145, "global_step": 508409, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.074174642562866, "global_step": 508410, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.046393394470215, "global_step": 508411, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0248937606811523, "global_step": 508412, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0178027153015137, "global_step": 508413, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9744234085083008, "global_step": 508414, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1335365772247314, "global_step": 508415, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.017606019973755, "global_step": 508416, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1255054473876953, "global_step": 508417, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.115755796432495, "global_step": 508418, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1134932041168213, "global_step": 508419, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9892032146453857, "global_step": 508420, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1024036407470703, "global_step": 508421, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.052534818649292, "global_step": 508422, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0369038581848145, "global_step": 508423, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0477349758148193, "global_step": 508424, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9871169328689575, "global_step": 508425, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.007723569869995, "global_step": 508426, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9696873426437378, "global_step": 508427, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.031930923461914, "global_step": 508428, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0499980449676514, "global_step": 508429, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.008533477783203, "global_step": 508430, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.067103147506714, "global_step": 508431, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.004488468170166, "global_step": 508432, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.06618595123291, "global_step": 508433, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0073909759521484, "global_step": 508434, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.042341947555542, "global_step": 508435, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0301921367645264, "global_step": 508436, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0283591747283936, "global_step": 508437, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0470471382141113, "global_step": 508438, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.067913293838501, "global_step": 508439, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.108961820602417, "global_step": 508440, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1192407608032227, "global_step": 508441, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0744271278381348, "global_step": 508442, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.038379669189453, "global_step": 508443, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1918399333953857, "global_step": 508444, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0291671752929688, "global_step": 508445, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.079052209854126, "global_step": 508446, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.10717511177063, "global_step": 508447, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0608654022216797, "global_step": 508448, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1206886768341064, "global_step": 508449, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.149869441986084, "global_step": 508450, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.121248960494995, "global_step": 508451, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0486974716186523, "global_step": 508452, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.077261447906494, "global_step": 508453, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1092309951782227, "global_step": 508454, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.023435354232788, "global_step": 508455, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.093886375427246, "global_step": 508456, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9891176223754883, "global_step": 508457, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.019441604614258, "global_step": 508458, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.980009913444519, "global_step": 508459, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.055419683456421, "global_step": 508460, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0148768424987793, "global_step": 508461, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.078925371170044, "global_step": 508462, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.062323570251465, "global_step": 508463, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0578293800354004, "global_step": 508464, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1094775199890137, "global_step": 508465, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0184855461120605, "global_step": 508466, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.069354295730591, "global_step": 508467, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.087022542953491, "global_step": 508468, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0331737995147705, "global_step": 508469, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9997856616973877, "global_step": 508470, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0850558280944824, "global_step": 508471, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.040741443634033, "global_step": 508472, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.050387144088745, "global_step": 508473, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0569801330566406, "global_step": 508474, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0649800300598145, "global_step": 508475, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0544650554656982, "global_step": 508476, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.008890151977539, "global_step": 508477, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.068859100341797, "global_step": 508478, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9925075769424438, "global_step": 508479, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0682528018951416, "global_step": 508480, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0297203063964844, "global_step": 508481, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0173778533935547, "global_step": 508482, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0821287631988525, "global_step": 508483, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1016652584075928, "global_step": 508484, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.049372911453247, "global_step": 508485, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0496416091918945, "global_step": 508486, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0779576301574707, "global_step": 508487, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0645742416381836, "global_step": 508488, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.068315029144287, "global_step": 508489, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9913272857666016, "global_step": 508490, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.025848150253296, "global_step": 508491, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.081749677658081, "global_step": 508492, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0050175189971924, "global_step": 508493, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0448741912841797, "global_step": 508494, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.07771635055542, "global_step": 508495, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.000366449356079, "global_step": 508496, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.987794280052185, "global_step": 508497, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1222610473632812, "global_step": 508498, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0544180870056152, "global_step": 508499, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.166907787322998, "global_step": 508500, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.002554178237915, "global_step": 508501, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0855324268341064, "global_step": 508502, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9881433248519897, "global_step": 508503, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0237958431243896, "global_step": 508504, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0074174404144287, "global_step": 508505, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9498690366744995, "global_step": 508506, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.023376941680908, "global_step": 508507, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0457921028137207, "global_step": 508508, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.050255060195923, "global_step": 508509, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.026263952255249, "global_step": 508510, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.099721670150757, "global_step": 508511, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.107224941253662, "global_step": 508512, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1016666889190674, "global_step": 508513, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0740439891815186, "global_step": 508514, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9546865224838257, "global_step": 508515, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0179595947265625, "global_step": 508516, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0809998512268066, "global_step": 508517, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.079371929168701, "global_step": 508518, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9928356409072876, "global_step": 508519, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0476346015930176, "global_step": 508520, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0614206790924072, "global_step": 508521, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1001384258270264, "global_step": 508522, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.052441358566284, "global_step": 508523, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0995564460754395, "global_step": 508524, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.040860414505005, "global_step": 508525, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.029188632965088, "global_step": 508526, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0677082538604736, "global_step": 508527, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.066124677658081, "global_step": 508528, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.016165018081665, "global_step": 508529, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0576741695404053, "global_step": 508530, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0416719913482666, "global_step": 508531, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.060725212097168, "global_step": 508532, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0478878021240234, "global_step": 508533, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.063316822052002, "global_step": 508534, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0477969646453857, "global_step": 508535, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.078425884246826, "global_step": 508536, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.045469045639038, "global_step": 508537, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.001070499420166, "global_step": 508538, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.048266649246216, "global_step": 508539, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.048002243041992, "global_step": 508540, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0466246604919434, "global_step": 508541, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.037506580352783, "global_step": 508542, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.061906337738037, "global_step": 508543, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.023054838180542, "global_step": 508544, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0449883937835693, "global_step": 508545, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.127544403076172, "global_step": 508546, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.105557680130005, "global_step": 508547, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9946619272232056, "global_step": 508548, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.089872121810913, "global_step": 508549, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9940009117126465, "global_step": 508550, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.126821279525757, "global_step": 508551, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.987353801727295, "global_step": 508552, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0006637573242188, "global_step": 508553, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0800507068634033, "global_step": 508554, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0530099868774414, "global_step": 508555, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0501012802124023, "global_step": 508556, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0381855964660645, "global_step": 508557, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.110152244567871, "global_step": 508558, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1000478267669678, "global_step": 508559, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.998412013053894, "global_step": 508560, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0581583976745605, "global_step": 508561, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0691709518432617, "global_step": 508562, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0268092155456543, "global_step": 508563, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0189478397369385, "global_step": 508564, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1105661392211914, "global_step": 508565, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1211702823638916, "global_step": 508566, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.041748046875, "global_step": 508567, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1258747577667236, "global_step": 508568, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.060182571411133, "global_step": 508569, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.067431926727295, "global_step": 508570, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.049989938735962, "global_step": 508571, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0458385944366455, "global_step": 508572, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0573036670684814, "global_step": 508573, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.084481716156006, "global_step": 508574, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.001450300216675, "global_step": 508575, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.038774013519287, "global_step": 508576, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0477919578552246, "global_step": 508577, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0407729148864746, "global_step": 508578, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.021196126937866, "global_step": 508579, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.098560094833374, "global_step": 508580, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.081848621368408, "global_step": 508581, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0207271575927734, "global_step": 508582, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.034658193588257, "global_step": 508583, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.064516544342041, "global_step": 508584, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0463778972625732, "global_step": 508585, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.186002254486084, "global_step": 508586, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.025512933731079, "global_step": 508587, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.06801176071167, "global_step": 508588, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0440993309020996, "global_step": 508589, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0714828968048096, "global_step": 508590, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0095057487487793, "global_step": 508591, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.064427614212036, "global_step": 508592, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0603811740875244, "global_step": 508593, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0365686416625977, "global_step": 508594, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0525176525115967, "global_step": 508595, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.064488649368286, "global_step": 508596, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0619373321533203, "global_step": 508597, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.030059814453125, "global_step": 508598, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9453113079071045, "global_step": 508599, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0270464420318604, "global_step": 508600, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0215439796447754, "global_step": 508601, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.027456045150757, "global_step": 508602, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0248849391937256, "global_step": 508603, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0710630416870117, "global_step": 508604, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1450157165527344, "global_step": 508605, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0303099155426025, "global_step": 508606, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1552159786224365, "global_step": 508607, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0774900913238525, "global_step": 508608, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9989384412765503, "global_step": 508609, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0496432781219482, "global_step": 508610, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0549402236938477, "global_step": 508611, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0237529277801514, "global_step": 508612, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9811094999313354, "global_step": 508613, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0689868927001953, "global_step": 508614, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9737091064453125, "global_step": 508615, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.08223819732666, "global_step": 508616, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0357837677001953, "global_step": 508617, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.038569927215576, "global_step": 508618, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0666964054107666, "global_step": 508619, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0730526447296143, "global_step": 508620, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0255815982818604, "global_step": 508621, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1183085441589355, "global_step": 508622, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9729397296905518, "global_step": 508623, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0763800144195557, "global_step": 508624, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0024378299713135, "global_step": 508625, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0749940872192383, "global_step": 508626, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.011796236038208, "global_step": 508627, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9318197965621948, "global_step": 508628, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.976294755935669, "global_step": 508629, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0813980102539062, "global_step": 508630, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1125130653381348, "global_step": 508631, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.06125545501709, "global_step": 508632, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0679900646209717, "global_step": 508633, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1495909690856934, "global_step": 508634, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9938435554504395, "global_step": 508635, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0557167530059814, "global_step": 508636, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.126863718032837, "global_step": 508637, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.056135654449463, "global_step": 508638, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.028310775756836, "global_step": 508639, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.068659782409668, "global_step": 508640, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.049067735671997, "global_step": 508641, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0359721183776855, "global_step": 508642, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.085660934448242, "global_step": 508643, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1516265869140625, "global_step": 508644, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9498828649520874, "global_step": 508645, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0040738582611084, "global_step": 508646, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1361942291259766, "global_step": 508647, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0318424701690674, "global_step": 508648, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.057206153869629, "global_step": 508649, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.006880283355713, "global_step": 508650, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0903398990631104, "global_step": 508651, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9924137592315674, "global_step": 508652, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.102246046066284, "global_step": 508653, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0003480911254883, "global_step": 508654, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.040353536605835, "global_step": 508655, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.024125576019287, "global_step": 508656, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.014430046081543, "global_step": 508657, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0431430339813232, "global_step": 508658, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.036712408065796, "global_step": 508659, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.101276397705078, "global_step": 508660, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.97933828830719, "global_step": 508661, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.042929172515869, "global_step": 508662, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0643458366394043, "global_step": 508663, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.046455144882202, "global_step": 508664, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.052126169204712, "global_step": 508665, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.03422474861145, "global_step": 508666, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0426011085510254, "global_step": 508667, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.064453363418579, "global_step": 508668, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0701687335968018, "global_step": 508669, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0686774253845215, "global_step": 508670, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1121320724487305, "global_step": 508671, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1303460597991943, "global_step": 508672, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0747945308685303, "global_step": 508673, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.064707040786743, "global_step": 508674, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9153610467910767, "global_step": 508675, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0728230476379395, "global_step": 508676, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.035646915435791, "global_step": 508677, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9857063293457031, "global_step": 508678, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0503740310668945, "global_step": 508679, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0846004486083984, "global_step": 508680, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0671727657318115, "global_step": 508681, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1260528564453125, "global_step": 508682, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.011317729949951, "global_step": 508683, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0701887607574463, "global_step": 508684, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.128408670425415, "global_step": 508685, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.995760202407837, "global_step": 508686, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.049532890319824, "global_step": 508687, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9721848964691162, "global_step": 508688, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0008747577667236, "global_step": 508689, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.090543270111084, "global_step": 508690, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0698611736297607, "global_step": 508691, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1531479358673096, "global_step": 508692, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.042370080947876, "global_step": 508693, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.075059413909912, "global_step": 508694, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.094672679901123, "global_step": 508695, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0921289920806885, "global_step": 508696, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.021244764328003, "global_step": 508697, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9227769374847412, "global_step": 508698, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.02133846282959, "global_step": 508699, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.072761297225952, "global_step": 508700, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.010096549987793, "global_step": 508701, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.014733076095581, "global_step": 508702, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0284180641174316, "global_step": 508703, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9998116493225098, "global_step": 508704, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.034377098083496, "global_step": 508705, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.012089490890503, "global_step": 508706, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.095865488052368, "global_step": 508707, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0526628494262695, "global_step": 508708, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0971152782440186, "global_step": 508709, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.087954044342041, "global_step": 508710, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0456435680389404, "global_step": 508711, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.117065668106079, "global_step": 508712, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9560796022415161, "global_step": 508713, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9640860557556152, "global_step": 508714, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0552759170532227, "global_step": 508715, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.037710428237915, "global_step": 508716, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0371174812316895, "global_step": 508717, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.051377534866333, "global_step": 508718, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9742783308029175, "global_step": 508719, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.99408757686615, "global_step": 508720, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0633387565612793, "global_step": 508721, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0012357234954834, "global_step": 508722, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.029273509979248, "global_step": 508723, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1212687492370605, "global_step": 508724, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1012933254241943, "global_step": 508725, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9937433004379272, "global_step": 508726, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.05446720123291, "global_step": 508727, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0469071865081787, "global_step": 508728, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0650527477264404, "global_step": 508729, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0486090183258057, "global_step": 508730, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9831080436706543, "global_step": 508731, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0081958770751953, "global_step": 508732, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0340256690979004, "global_step": 508733, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0712389945983887, "global_step": 508734, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1183016300201416, "global_step": 508735, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1093156337738037, "global_step": 508736, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.92560875415802, "global_step": 508737, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0789241790771484, "global_step": 508738, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0665903091430664, "global_step": 508739, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0151946544647217, "global_step": 508740, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0295627117156982, "global_step": 508741, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0326998233795166, "global_step": 508742, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.06278395652771, "global_step": 508743, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0370934009552, "global_step": 508744, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0021097660064697, "global_step": 508745, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9958988428115845, "global_step": 508746, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0632176399230957, "global_step": 508747, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0627169609069824, "global_step": 508748, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0434975624084473, "global_step": 508749, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1134681701660156, "global_step": 508750, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0885651111602783, "global_step": 508751, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.065134048461914, "global_step": 508752, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.14062762260437, "global_step": 508753, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.013784408569336, "global_step": 508754, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9810006618499756, "global_step": 508755, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0945534706115723, "global_step": 508756, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0691978931427, "global_step": 508757, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0416641235351562, "global_step": 508758, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.002713680267334, "global_step": 508759, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0709149837493896, "global_step": 508760, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0754446983337402, "global_step": 508761, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9638549089431763, "global_step": 508762, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0626018047332764, "global_step": 508763, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.014702558517456, "global_step": 508764, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9728350639343262, "global_step": 508765, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.078305959701538, "global_step": 508766, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1185736656188965, "global_step": 508767, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0508081912994385, "global_step": 508768, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0104236602783203, "global_step": 508769, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.956477165222168, "global_step": 508770, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.068621873855591, "global_step": 508771, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.057199239730835, "global_step": 508772, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.043543577194214, "global_step": 508773, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0284509658813477, "global_step": 508774, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.03507137298584, "global_step": 508775, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9428021907806396, "global_step": 508776, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0944976806640625, "global_step": 508777, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0000240802764893, "global_step": 508778, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9667537212371826, "global_step": 508779, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.065330982208252, "global_step": 508780, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.068608283996582, "global_step": 508781, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.001945734024048, "global_step": 508782, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.009230852127075, "global_step": 508783, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1284077167510986, "global_step": 508784, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9504961967468262, "global_step": 508785, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9997622966766357, "global_step": 508786, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0161619186401367, "global_step": 508787, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0580055713653564, "global_step": 508788, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0950307846069336, "global_step": 508789, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.049913167953491, "global_step": 508790, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0789456367492676, "global_step": 508791, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0666418075561523, "global_step": 508792, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9814192056655884, "global_step": 508793, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0546646118164062, "global_step": 508794, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0838727951049805, "global_step": 508795, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.042173385620117, "global_step": 508796, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0545148849487305, "global_step": 508797, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0650973320007324, "global_step": 508798, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.148695468902588, "global_step": 508799, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0248827934265137, "global_step": 508800, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.022914409637451, "global_step": 508801, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1202468872070312, "global_step": 508802, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0228116512298584, "global_step": 508803, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.091149091720581, "global_step": 508804, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0376086235046387, "global_step": 508805, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0468575954437256, "global_step": 508806, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.044384717941284, "global_step": 508807, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1168229579925537, "global_step": 508808, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0627217292785645, "global_step": 508809, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0309553146362305, "global_step": 508810, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0409791469573975, "global_step": 508811, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.122235059738159, "global_step": 508812, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9427495002746582, "global_step": 508813, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.087146282196045, "global_step": 508814, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.962688684463501, "global_step": 508815, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.048910140991211, "global_step": 508816, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.087278127670288, "global_step": 508817, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.052283763885498, "global_step": 508818, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0038998126983643, "global_step": 508819, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1700477600097656, "global_step": 508820, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0262038707733154, "global_step": 508821, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.023120164871216, "global_step": 508822, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9419524669647217, "global_step": 508823, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0059449672698975, "global_step": 508824, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.025681734085083, "global_step": 508825, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0899925231933594, "global_step": 508826, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1142022609710693, "global_step": 508827, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9849462509155273, "global_step": 508828, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0289697647094727, "global_step": 508829, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.068899631500244, "global_step": 508830, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9754661321640015, "global_step": 508831, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.080655336380005, "global_step": 508832, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.001917600631714, "global_step": 508833, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0726327896118164, "global_step": 508834, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.048038959503174, "global_step": 508835, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1106534004211426, "global_step": 508836, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1120786666870117, "global_step": 508837, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9661846160888672, "global_step": 508838, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.004204034805298, "global_step": 508839, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0972900390625, "global_step": 508840, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.1364474296569824, "global_step": 508841, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.024724245071411, "global_step": 508842, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.040717840194702, "global_step": 508843, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9963467121124268, "global_step": 508844, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.029203414916992, "global_step": 508845, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9899929761886597, "global_step": 508846, "epoch": 874, "lr": 5e-05}
{"train_loss": 1.9486712217330933, "global_step": 508847, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.062342405319214, "global_step": 508848, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0634207725524902, "global_step": 508849, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.063175678253174, "global_step": 508850, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.003380060195923, "global_step": 508851, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0677709579467773, "global_step": 508852, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.106724977493286, "global_step": 508853, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.075183868408203, "global_step": 508854, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0875093936920166, "global_step": 508855, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0836400985717773, "global_step": 508856, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.047433376312256, "global_step": 508857, "epoch": 874, "lr": 5e-05}
{"train_loss": 2.0446362495422363, "global_step": 508858, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0896008014678955, "global_step": 508859, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0684597492218018, "global_step": 508860, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9962998628616333, "global_step": 508861, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0399887561798096, "global_step": 508862, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0641305446624756, "global_step": 508863, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9573708772659302, "global_step": 508864, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.972469449043274, "global_step": 508865, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9510552883148193, "global_step": 508866, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.095252275466919, "global_step": 508867, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.06040620803833, "global_step": 508868, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0760769844055176, "global_step": 508869, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.13101863861084, "global_step": 508870, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9672743082046509, "global_step": 508871, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.085681438446045, "global_step": 508872, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0341923236846924, "global_step": 508873, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0100860595703125, "global_step": 508874, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0678861141204834, "global_step": 508875, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9938817024230957, "global_step": 508876, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.94764244556427, "global_step": 508877, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9909378290176392, "global_step": 508878, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0472047328948975, "global_step": 508879, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.095163106918335, "global_step": 508880, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.087583065032959, "global_step": 508881, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0061404705047607, "global_step": 508882, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.004572868347168, "global_step": 508883, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0895814895629883, "global_step": 508884, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1988065242767334, "global_step": 508885, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9940155744552612, "global_step": 508886, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0894412994384766, "global_step": 508887, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.035003185272217, "global_step": 508888, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.079535484313965, "global_step": 508889, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.002138614654541, "global_step": 508890, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0197863578796387, "global_step": 508891, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.051800489425659, "global_step": 508892, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.968403935432434, "global_step": 508893, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9205206632614136, "global_step": 508894, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.998111367225647, "global_step": 508895, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.050448417663574, "global_step": 508896, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9451489448547363, "global_step": 508897, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0009958744049072, "global_step": 508898, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0538105964660645, "global_step": 508899, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.07714581489563, "global_step": 508900, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.979124903678894, "global_step": 508901, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.038099527359009, "global_step": 508902, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.089627504348755, "global_step": 508903, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.018458127975464, "global_step": 508904, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0836029052734375, "global_step": 508905, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.037700653076172, "global_step": 508906, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.070073127746582, "global_step": 508907, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9522351026535034, "global_step": 508908, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0647096633911133, "global_step": 508909, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.089881658554077, "global_step": 508910, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0721142292022705, "global_step": 508911, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.070821762084961, "global_step": 508912, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0239927768707275, "global_step": 508913, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0195493698120117, "global_step": 508914, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.043257713317871, "global_step": 508915, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0861945152282715, "global_step": 508916, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0644989013671875, "global_step": 508917, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.08667254447937, "global_step": 508918, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9704563617706299, "global_step": 508919, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.020399332046509, "global_step": 508920, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0104494094848633, "global_step": 508921, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0670299530029297, "global_step": 508922, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.13034725189209, "global_step": 508923, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.061803102493286, "global_step": 508924, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0279297828674316, "global_step": 508925, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0342822074890137, "global_step": 508926, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.06453800201416, "global_step": 508927, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0278828144073486, "global_step": 508928, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0455174446105957, "global_step": 508929, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9789314270019531, "global_step": 508930, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0115532875061035, "global_step": 508931, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.004302501678467, "global_step": 508932, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.029893159866333, "global_step": 508933, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0080413818359375, "global_step": 508934, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.084461212158203, "global_step": 508935, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.944737195968628, "global_step": 508936, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.067725896835327, "global_step": 508937, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.145939826965332, "global_step": 508938, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.05373477935791, "global_step": 508939, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0483860969543457, "global_step": 508940, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0955233573913574, "global_step": 508941, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0223264694213867, "global_step": 508942, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.046894073486328, "global_step": 508943, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0673203468322754, "global_step": 508944, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1301512718200684, "global_step": 508945, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.10935640335083, "global_step": 508946, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9705091714859009, "global_step": 508947, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.042816400527954, "global_step": 508948, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9852313995361328, "global_step": 508949, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.061384916305542, "global_step": 508950, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.04110050201416, "global_step": 508951, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.048964023590088, "global_step": 508952, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1114320755004883, "global_step": 508953, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.040390729904175, "global_step": 508954, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0976955890655518, "global_step": 508955, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9998443126678467, "global_step": 508956, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0063061714172363, "global_step": 508957, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0734496116638184, "global_step": 508958, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.079962730407715, "global_step": 508959, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0708181858062744, "global_step": 508960, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0830438137054443, "global_step": 508961, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0181522369384766, "global_step": 508962, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1357181072235107, "global_step": 508963, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0376405715942383, "global_step": 508964, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9886760711669922, "global_step": 508965, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.998870611190796, "global_step": 508966, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.05001163482666, "global_step": 508967, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1526832580566406, "global_step": 508968, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0377860069274902, "global_step": 508969, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9816038608551025, "global_step": 508970, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0639560222625732, "global_step": 508971, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9732403755187988, "global_step": 508972, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.076643466949463, "global_step": 508973, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.130324602127075, "global_step": 508974, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9390279054641724, "global_step": 508975, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0066537857055664, "global_step": 508976, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.007481336593628, "global_step": 508977, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9452728033065796, "global_step": 508978, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9858007431030273, "global_step": 508979, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0200178623199463, "global_step": 508980, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.034937858581543, "global_step": 508981, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1097970008850098, "global_step": 508982, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0816240310668945, "global_step": 508983, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.10526180267334, "global_step": 508984, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0868887901306152, "global_step": 508985, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0625622272491455, "global_step": 508986, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1076364517211914, "global_step": 508987, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.023651361465454, "global_step": 508988, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1099233627319336, "global_step": 508989, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.025066614151001, "global_step": 508990, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9673829078674316, "global_step": 508991, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9649993181228638, "global_step": 508992, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.011202335357666, "global_step": 508993, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9982417821884155, "global_step": 508994, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0435914993286133, "global_step": 508995, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9900586605072021, "global_step": 508996, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.112192392349243, "global_step": 508997, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9812358617782593, "global_step": 508998, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9530748128890991, "global_step": 508999, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.059877395629883, "global_step": 509000, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.04130220413208, "global_step": 509001, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0100021362304688, "global_step": 509002, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1185638904571533, "global_step": 509003, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0616767406463623, "global_step": 509004, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.094939708709717, "global_step": 509005, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9947072267532349, "global_step": 509006, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0210559368133545, "global_step": 509007, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.034210681915283, "global_step": 509008, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0286386013031006, "global_step": 509009, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0607991218566895, "global_step": 509010, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0834739208221436, "global_step": 509011, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.095227003097534, "global_step": 509012, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9870754480361938, "global_step": 509013, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.037393808364868, "global_step": 509014, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.986804485321045, "global_step": 509015, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.064260244369507, "global_step": 509016, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0538880825042725, "global_step": 509017, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0360114574432373, "global_step": 509018, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1396842002868652, "global_step": 509019, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.016209363937378, "global_step": 509020, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.034243106842041, "global_step": 509021, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9931550025939941, "global_step": 509022, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0497989654541016, "global_step": 509023, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0923867225646973, "global_step": 509024, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.012293815612793, "global_step": 509025, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0938925743103027, "global_step": 509026, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0183095932006836, "global_step": 509027, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0767245292663574, "global_step": 509028, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0709073543548584, "global_step": 509029, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.006256103515625, "global_step": 509030, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9961730241775513, "global_step": 509031, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0819292068481445, "global_step": 509032, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.127021551132202, "global_step": 509033, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.08058500289917, "global_step": 509034, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0122551918029785, "global_step": 509035, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0096664428710938, "global_step": 509036, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.060580015182495, "global_step": 509037, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0362765789031982, "global_step": 509038, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.02354097366333, "global_step": 509039, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.988373875617981, "global_step": 509040, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9981260299682617, "global_step": 509041, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9762029647827148, "global_step": 509042, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0413386821746826, "global_step": 509043, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.070209503173828, "global_step": 509044, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.061610221862793, "global_step": 509045, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9497934579849243, "global_step": 509046, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0378458499908447, "global_step": 509047, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9989666938781738, "global_step": 509048, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0686004161834717, "global_step": 509049, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9863427877426147, "global_step": 509050, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.072889566421509, "global_step": 509051, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.064052104949951, "global_step": 509052, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9955662488937378, "global_step": 509053, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0513956546783447, "global_step": 509054, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0768439769744873, "global_step": 509055, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.010629892349243, "global_step": 509056, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0270214080810547, "global_step": 509057, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.041255235671997, "global_step": 509058, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9833108186721802, "global_step": 509059, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0844123363494873, "global_step": 509060, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.047013998031616, "global_step": 509061, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1475160121917725, "global_step": 509062, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0986928939819336, "global_step": 509063, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0586962699890137, "global_step": 509064, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0216803550720215, "global_step": 509065, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.00627064704895, "global_step": 509066, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.060084104537964, "global_step": 509067, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0182039737701416, "global_step": 509068, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1485302448272705, "global_step": 509069, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.021298885345459, "global_step": 509070, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0377795696258545, "global_step": 509071, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.142425298690796, "global_step": 509072, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.082932233810425, "global_step": 509073, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.169386386871338, "global_step": 509074, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0424652099609375, "global_step": 509075, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.03117036819458, "global_step": 509076, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.032853364944458, "global_step": 509077, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.031904697418213, "global_step": 509078, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0533759593963623, "global_step": 509079, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0122427940368652, "global_step": 509080, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0037362575531006, "global_step": 509081, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.022371530532837, "global_step": 509082, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0516653060913086, "global_step": 509083, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1496315002441406, "global_step": 509084, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.098592758178711, "global_step": 509085, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0436408519744873, "global_step": 509086, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1104867458343506, "global_step": 509087, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0643248558044434, "global_step": 509088, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1413912773132324, "global_step": 509089, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9494668245315552, "global_step": 509090, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.016951322555542, "global_step": 509091, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0057058334350586, "global_step": 509092, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.07867693901062, "global_step": 509093, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0290069580078125, "global_step": 509094, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.055795431137085, "global_step": 509095, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.103046178817749, "global_step": 509096, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0973994731903076, "global_step": 509097, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.081437110900879, "global_step": 509098, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.004385232925415, "global_step": 509099, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0388119220733643, "global_step": 509100, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.162475109100342, "global_step": 509101, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0711324214935303, "global_step": 509102, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1237382888793945, "global_step": 509103, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0289487838745117, "global_step": 509104, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9887661933898926, "global_step": 509105, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0131778717041016, "global_step": 509106, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.170649528503418, "global_step": 509107, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.011716842651367, "global_step": 509108, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0607476234436035, "global_step": 509109, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9592760801315308, "global_step": 509110, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9893728494644165, "global_step": 509111, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.050455093383789, "global_step": 509112, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.090327501296997, "global_step": 509113, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.034553289413452, "global_step": 509114, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1109635829925537, "global_step": 509115, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0274226665496826, "global_step": 509116, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.984268307685852, "global_step": 509117, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.097165107727051, "global_step": 509118, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.020643949508667, "global_step": 509119, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.040192127227783, "global_step": 509120, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0837912559509277, "global_step": 509121, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.077878475189209, "global_step": 509122, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9872572422027588, "global_step": 509123, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.005950689315796, "global_step": 509124, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9660903215408325, "global_step": 509125, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.009190797805786, "global_step": 509126, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.955891489982605, "global_step": 509127, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0413763523101807, "global_step": 509128, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9770690202713013, "global_step": 509129, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0929160118103027, "global_step": 509130, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1124160289764404, "global_step": 509131, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0474510192871094, "global_step": 509132, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0002801418304443, "global_step": 509133, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0291595458984375, "global_step": 509134, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.032036304473877, "global_step": 509135, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.061082363128662, "global_step": 509136, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0136005878448486, "global_step": 509137, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0709028244018555, "global_step": 509138, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.045903444290161, "global_step": 509139, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0689728260040283, "global_step": 509140, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0094289779663086, "global_step": 509141, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9877033233642578, "global_step": 509142, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0935516357421875, "global_step": 509143, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.082338333129883, "global_step": 509144, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.052858591079712, "global_step": 509145, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0362443923950195, "global_step": 509146, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9242424964904785, "global_step": 509147, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0167312622070312, "global_step": 509148, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9798784255981445, "global_step": 509149, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0590860843658447, "global_step": 509150, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9628666639328003, "global_step": 509151, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9425153732299805, "global_step": 509152, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0535926818847656, "global_step": 509153, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0660552978515625, "global_step": 509154, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0475478172302246, "global_step": 509155, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.009451150894165, "global_step": 509156, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9844872951507568, "global_step": 509157, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9682987928390503, "global_step": 509158, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0314114093780518, "global_step": 509159, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0590224266052246, "global_step": 509160, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1176207065582275, "global_step": 509161, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0219035148620605, "global_step": 509162, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9995492696762085, "global_step": 509163, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.119105100631714, "global_step": 509164, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.091559410095215, "global_step": 509165, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9922176599502563, "global_step": 509166, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0725622177124023, "global_step": 509167, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.00581431388855, "global_step": 509168, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0163207054138184, "global_step": 509169, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0743799209594727, "global_step": 509170, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0766451358795166, "global_step": 509171, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0045058727264404, "global_step": 509172, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0813040733337402, "global_step": 509173, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.048370361328125, "global_step": 509174, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.011341094970703, "global_step": 509175, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0734877586364746, "global_step": 509176, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1361217498779297, "global_step": 509177, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.051241636276245, "global_step": 509178, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.016306161880493, "global_step": 509179, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0870823860168457, "global_step": 509180, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0583207607269287, "global_step": 509181, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.048678398132324, "global_step": 509182, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.020975112915039, "global_step": 509183, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.015117645263672, "global_step": 509184, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0007829666137695, "global_step": 509185, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1304636001586914, "global_step": 509186, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.004415512084961, "global_step": 509187, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1235404014587402, "global_step": 509188, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.063448667526245, "global_step": 509189, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.00917911529541, "global_step": 509190, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9126744270324707, "global_step": 509191, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0447473526000977, "global_step": 509192, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.010988235473633, "global_step": 509193, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0684170722961426, "global_step": 509194, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9477123022079468, "global_step": 509195, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0339951515197754, "global_step": 509196, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.061089515686035, "global_step": 509197, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0409247875213623, "global_step": 509198, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.100193500518799, "global_step": 509199, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.006852865219116, "global_step": 509200, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9751102924346924, "global_step": 509201, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0697014331817627, "global_step": 509202, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9342106580734253, "global_step": 509203, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1108973026275635, "global_step": 509204, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0177319049835205, "global_step": 509205, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.999000072479248, "global_step": 509206, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0631062984466553, "global_step": 509207, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0111167430877686, "global_step": 509208, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0740907192230225, "global_step": 509209, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.124315023422241, "global_step": 509210, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1088595390319824, "global_step": 509211, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0007882118225098, "global_step": 509212, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0154521465301514, "global_step": 509213, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9536333084106445, "global_step": 509214, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0448648929595947, "global_step": 509215, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.043358325958252, "global_step": 509216, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.055490255355835, "global_step": 509217, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0066394805908203, "global_step": 509218, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0532751083374023, "global_step": 509219, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9557219743728638, "global_step": 509220, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.053117275238037, "global_step": 509221, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.04858660697937, "global_step": 509222, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9341557025909424, "global_step": 509223, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0422942638397217, "global_step": 509224, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0409748554229736, "global_step": 509225, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0053303241729736, "global_step": 509226, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.000016927719116, "global_step": 509227, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.087111711502075, "global_step": 509228, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0906810760498047, "global_step": 509229, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.001633882522583, "global_step": 509230, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.062779188156128, "global_step": 509231, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.051215648651123, "global_step": 509232, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0987460613250732, "global_step": 509233, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0233800411224365, "global_step": 509234, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9932785034179688, "global_step": 509235, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1143269538879395, "global_step": 509236, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0502448081970215, "global_step": 509237, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1050515174865723, "global_step": 509238, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.130920171737671, "global_step": 509239, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.13033127784729, "global_step": 509240, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.077303171157837, "global_step": 509241, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.170999526977539, "global_step": 509242, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0493180751800537, "global_step": 509243, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.041663885116577, "global_step": 509244, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0239999294281006, "global_step": 509245, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1176459789276123, "global_step": 509246, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.984957218170166, "global_step": 509247, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.066499710083008, "global_step": 509248, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0045766830444336, "global_step": 509249, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0787312984466553, "global_step": 509250, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.105045795440674, "global_step": 509251, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0783143043518066, "global_step": 509252, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0655219554901123, "global_step": 509253, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0542328357696533, "global_step": 509254, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1082851886749268, "global_step": 509255, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.107327699661255, "global_step": 509256, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0634148120880127, "global_step": 509257, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.074010133743286, "global_step": 509258, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.07185697555542, "global_step": 509259, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0326337814331055, "global_step": 509260, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0365960597991943, "global_step": 509261, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.001688241958618, "global_step": 509262, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1184911727905273, "global_step": 509263, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.082765817642212, "global_step": 509264, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0873889923095703, "global_step": 509265, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0988314151763916, "global_step": 509266, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.034726858139038, "global_step": 509267, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0131990909576416, "global_step": 509268, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9908037185668945, "global_step": 509269, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.077347755432129, "global_step": 509270, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0133230686187744, "global_step": 509271, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0879812240600586, "global_step": 509272, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0628111362457275, "global_step": 509273, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.002609968185425, "global_step": 509274, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1021294593811035, "global_step": 509275, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0454976558685303, "global_step": 509276, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0291991233825684, "global_step": 509277, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0859243869781494, "global_step": 509278, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.040865421295166, "global_step": 509279, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.060330390930176, "global_step": 509280, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0938966274261475, "global_step": 509281, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0519373416900635, "global_step": 509282, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0017459392547607, "global_step": 509283, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.026073694229126, "global_step": 509284, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.09824275970459, "global_step": 509285, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.036393642425537, "global_step": 509286, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0736491680145264, "global_step": 509287, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.116427421569824, "global_step": 509288, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9494497776031494, "global_step": 509289, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.072805166244507, "global_step": 509290, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.096796989440918, "global_step": 509291, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0719521045684814, "global_step": 509292, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.014319658279419, "global_step": 509293, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9930428266525269, "global_step": 509294, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.045217275619507, "global_step": 509295, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.014087677001953, "global_step": 509296, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.039597988128662, "global_step": 509297, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0053911209106445, "global_step": 509298, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0399224758148193, "global_step": 509299, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.047960042953491, "global_step": 509300, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.990598440170288, "global_step": 509301, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1020092964172363, "global_step": 509302, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0886356830596924, "global_step": 509303, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1470744609832764, "global_step": 509304, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0410871505737305, "global_step": 509305, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0573346614837646, "global_step": 509306, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.115366220474243, "global_step": 509307, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.046497106552124, "global_step": 509308, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1211023330688477, "global_step": 509309, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.054960250854492, "global_step": 509310, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0259928703308105, "global_step": 509311, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.092344045639038, "global_step": 509312, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1071977615356445, "global_step": 509313, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0902068614959717, "global_step": 509314, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0329880714416504, "global_step": 509315, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.08237624168396, "global_step": 509316, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0475029945373535, "global_step": 509317, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0400853157043457, "global_step": 509318, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9648072719573975, "global_step": 509319, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9730194807052612, "global_step": 509320, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.074467658996582, "global_step": 509321, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9507492780685425, "global_step": 509322, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.051497220993042, "global_step": 509323, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.078678846359253, "global_step": 509324, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.899954080581665, "global_step": 509325, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0568244457244873, "global_step": 509326, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0342156887054443, "global_step": 509327, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.038870334625244, "global_step": 509328, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0240931510925293, "global_step": 509329, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.039149522781372, "global_step": 509330, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0264477729797363, "global_step": 509331, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1666154861450195, "global_step": 509332, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.098771572113037, "global_step": 509333, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0774080753326416, "global_step": 509334, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0499963760375977, "global_step": 509335, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.070298910140991, "global_step": 509336, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.085888147354126, "global_step": 509337, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0127925872802734, "global_step": 509338, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9874809980392456, "global_step": 509339, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.050168752670288, "global_step": 509340, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0884878635406494, "global_step": 509341, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0197386741638184, "global_step": 509342, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.046929121017456, "global_step": 509343, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9808577299118042, "global_step": 509344, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.098539113998413, "global_step": 509345, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.016759157180786, "global_step": 509346, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.036088705062866, "global_step": 509347, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.131923198699951, "global_step": 509348, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1019248962402344, "global_step": 509349, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.054762363433838, "global_step": 509350, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9639915227890015, "global_step": 509351, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0796492099761963, "global_step": 509352, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0821404457092285, "global_step": 509353, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0110321044921875, "global_step": 509354, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9896007776260376, "global_step": 509355, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.149205207824707, "global_step": 509356, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.082184314727783, "global_step": 509357, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.2030277252197266, "global_step": 509358, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.085204839706421, "global_step": 509359, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.989263892173767, "global_step": 509360, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9538496732711792, "global_step": 509361, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.005329132080078, "global_step": 509362, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.121722936630249, "global_step": 509363, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0454657077789307, "global_step": 509364, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.120680809020996, "global_step": 509365, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1027987003326416, "global_step": 509366, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0899012088775635, "global_step": 509367, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.070127487182617, "global_step": 509368, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0461056232452393, "global_step": 509369, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0273303985595703, "global_step": 509370, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0960116386413574, "global_step": 509371, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0068557262420654, "global_step": 509372, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0523464679718018, "global_step": 509373, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.051304578781128, "global_step": 509374, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.070783853530884, "global_step": 509375, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.018449068069458, "global_step": 509376, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0551669597625732, "global_step": 509377, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.059699296951294, "global_step": 509378, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0304057598114014, "global_step": 509379, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0993518829345703, "global_step": 509380, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.168400526046753, "global_step": 509381, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1254546642303467, "global_step": 509382, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1631550788879395, "global_step": 509383, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1238913536071777, "global_step": 509384, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1040284633636475, "global_step": 509385, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.094106912612915, "global_step": 509386, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0773682594299316, "global_step": 509387, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1214969158172607, "global_step": 509388, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.022714138031006, "global_step": 509389, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0353760719299316, "global_step": 509390, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0025722980499268, "global_step": 509391, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0471558570861816, "global_step": 509392, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0965824127197266, "global_step": 509393, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.03354549407959, "global_step": 509394, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0733606815338135, "global_step": 509395, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0133779048919678, "global_step": 509396, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1052184104919434, "global_step": 509397, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.045379400253296, "global_step": 509398, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.05187726020813, "global_step": 509399, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1458990573883057, "global_step": 509400, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.073164224624634, "global_step": 509401, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.074010133743286, "global_step": 509402, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0851809978485107, "global_step": 509403, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.019699811935425, "global_step": 509404, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1171398162841797, "global_step": 509405, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.128582239151001, "global_step": 509406, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.124940872192383, "global_step": 509407, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0467898845672607, "global_step": 509408, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9994070529937744, "global_step": 509409, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0414879322052, "global_step": 509410, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9944140911102295, "global_step": 509411, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0004403591156006, "global_step": 509412, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.059523820877075, "global_step": 509413, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.02363920211792, "global_step": 509414, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0302345752716064, "global_step": 509415, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9483327865600586, "global_step": 509416, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.142467737197876, "global_step": 509417, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0575408935546875, "global_step": 509418, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.036850929260254, "global_step": 509419, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.031559944152832, "global_step": 509420, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0848801136016846, "global_step": 509421, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.067166328430176, "global_step": 509422, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.100857734680176, "global_step": 509423, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.096931219100952, "global_step": 509424, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1100003719329834, "global_step": 509425, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.069178342819214, "global_step": 509426, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.925689935684204, "global_step": 509427, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0174081325531006, "global_step": 509428, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.04331374168396, "global_step": 509429, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0540771484375, "global_step": 509430, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0390639305114746, "global_step": 509431, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.022860050201416, "global_step": 509432, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0429439544677734, "global_step": 509433, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.118328809738159, "global_step": 509434, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0182149410247803, "global_step": 509435, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0113611221313477, "global_step": 509436, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.061433792114258, "global_step": 509437, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.06427264213562, "global_step": 509438, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.049638032913208, "global_step": 509439, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0529236793518066, "global_step": 509440, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0924525260925293, "global_step": 509441, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.028339147567749, "global_step": 509442, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1384189128875732, "global_step": 509443, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.098886013031006, "global_step": 509444, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0756900310516357, "global_step": 509445, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.017430305480957, "global_step": 509446, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0491795539855957, "global_step": 509447, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9950101375579834, "global_step": 509448, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0149946212768555, "global_step": 509449, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9682626724243164, "global_step": 509450, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.035677194595337, "global_step": 509451, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.032959461212158, "global_step": 509452, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0598907470703125, "global_step": 509453, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0386760234832764, "global_step": 509454, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9900981187820435, "global_step": 509455, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.988787055015564, "global_step": 509456, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0498175621032715, "global_step": 509457, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0018177032470703, "global_step": 509458, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0834879875183105, "global_step": 509459, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.082120180130005, "global_step": 509460, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0288290977478027, "global_step": 509461, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.101536989212036, "global_step": 509462, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.013309955596924, "global_step": 509463, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9592528343200684, "global_step": 509464, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.165247678756714, "global_step": 509465, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0170533657073975, "global_step": 509466, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9671854972839355, "global_step": 509467, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.069013833999634, "global_step": 509468, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.085338592529297, "global_step": 509469, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1681573390960693, "global_step": 509470, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0087461471557617, "global_step": 509471, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0645413398742676, "global_step": 509472, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.036912441253662, "global_step": 509473, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0212583541870117, "global_step": 509474, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9948508739471436, "global_step": 509475, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9475361108779907, "global_step": 509476, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.010280132293701, "global_step": 509477, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.156304121017456, "global_step": 509478, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.982898235321045, "global_step": 509479, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0503571033477783, "global_step": 509480, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.063239812850952, "global_step": 509481, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.065194606781006, "global_step": 509482, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0702879428863525, "global_step": 509483, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0590157508850098, "global_step": 509484, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.022489070892334, "global_step": 509485, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.060872793197632, "global_step": 509486, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.031175374984741, "global_step": 509487, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1030733585357666, "global_step": 509488, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.074342727661133, "global_step": 509489, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0860555171966553, "global_step": 509490, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0248286724090576, "global_step": 509491, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0938403606414795, "global_step": 509492, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1082401275634766, "global_step": 509493, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0711803436279297, "global_step": 509494, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0811662673950195, "global_step": 509495, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0045056343078613, "global_step": 509496, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.122713565826416, "global_step": 509497, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1291208267211914, "global_step": 509498, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.091442584991455, "global_step": 509499, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9190983772277832, "global_step": 509500, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0753796100616455, "global_step": 509501, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.025552272796631, "global_step": 509502, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0065224170684814, "global_step": 509503, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.047771453857422, "global_step": 509504, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.060349464416504, "global_step": 509505, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.057251453399658, "global_step": 509506, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.091853380203247, "global_step": 509507, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0247647762298584, "global_step": 509508, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.053981304168701, "global_step": 509509, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.019958019256592, "global_step": 509510, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0708165168762207, "global_step": 509511, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.122922420501709, "global_step": 509512, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.057506561279297, "global_step": 509513, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.038240909576416, "global_step": 509514, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.032414674758911, "global_step": 509515, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0269012451171875, "global_step": 509516, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0898094177246094, "global_step": 509517, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9974006414413452, "global_step": 509518, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0297982692718506, "global_step": 509519, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0657811164855957, "global_step": 509520, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9939287900924683, "global_step": 509521, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1219475269317627, "global_step": 509522, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0646889209747314, "global_step": 509523, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1063570976257324, "global_step": 509524, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0466020107269287, "global_step": 509525, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.012042760848999, "global_step": 509526, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0023906230926514, "global_step": 509527, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.082340955734253, "global_step": 509528, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0484366416931152, "global_step": 509529, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0205633640289307, "global_step": 509530, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.106067180633545, "global_step": 509531, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.068394899368286, "global_step": 509532, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9610316753387451, "global_step": 509533, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.084080696105957, "global_step": 509534, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0780975818634033, "global_step": 509535, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0959370136260986, "global_step": 509536, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0100536346435547, "global_step": 509537, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.007932662963867, "global_step": 509538, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9973700046539307, "global_step": 509539, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.081613779067993, "global_step": 509540, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.07574462890625, "global_step": 509541, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.008883476257324, "global_step": 509542, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9995405673980713, "global_step": 509543, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0345137119293213, "global_step": 509544, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0073633193969727, "global_step": 509545, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.037865400314331, "global_step": 509546, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.09040904045105, "global_step": 509547, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9771652221679688, "global_step": 509548, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9802961349487305, "global_step": 509549, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0708436965942383, "global_step": 509550, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1135945320129395, "global_step": 509551, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9764589071273804, "global_step": 509552, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9802838563919067, "global_step": 509553, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0284674167633057, "global_step": 509554, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1101698875427246, "global_step": 509555, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.04184889793396, "global_step": 509556, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.050079107284546, "global_step": 509557, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0203206539154053, "global_step": 509558, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.105030059814453, "global_step": 509559, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0711216926574707, "global_step": 509560, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9835541248321533, "global_step": 509561, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.004997730255127, "global_step": 509562, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9987547397613525, "global_step": 509563, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.104825735092163, "global_step": 509564, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1315553188323975, "global_step": 509565, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.11960768699646, "global_step": 509566, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9948060512542725, "global_step": 509567, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0814242362976074, "global_step": 509568, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.116762161254883, "global_step": 509569, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.029926300048828, "global_step": 509570, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0076403617858887, "global_step": 509571, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0080881118774414, "global_step": 509572, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0238890647888184, "global_step": 509573, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1099371910095215, "global_step": 509574, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0235488414764404, "global_step": 509575, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.05031156539917, "global_step": 509576, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.998306393623352, "global_step": 509577, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.986222743988037, "global_step": 509578, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0046446323394775, "global_step": 509579, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.103567600250244, "global_step": 509580, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.026446580886841, "global_step": 509581, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.093341112136841, "global_step": 509582, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.103135824203491, "global_step": 509583, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0494062900543213, "global_step": 509584, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1024169921875, "global_step": 509585, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0322656631469727, "global_step": 509586, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0174448490142822, "global_step": 509587, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1582586765289307, "global_step": 509588, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0422332286834717, "global_step": 509589, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0466361045837402, "global_step": 509590, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0948472023010254, "global_step": 509591, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1030051708221436, "global_step": 509592, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0867481231689453, "global_step": 509593, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.983320713043213, "global_step": 509594, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0092861652374268, "global_step": 509595, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0991098880767822, "global_step": 509596, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.111663579940796, "global_step": 509597, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.017932653427124, "global_step": 509598, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.037173271179199, "global_step": 509599, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9944313764572144, "global_step": 509600, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.95479154586792, "global_step": 509601, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0130536556243896, "global_step": 509602, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.190537214279175, "global_step": 509603, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0223135948181152, "global_step": 509604, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.009131669998169, "global_step": 509605, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0206480026245117, "global_step": 509606, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0249128341674805, "global_step": 509607, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.962594747543335, "global_step": 509608, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.043454170227051, "global_step": 509609, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.024905204772949, "global_step": 509610, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.016526937484741, "global_step": 509611, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0316319465637207, "global_step": 509612, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0318055152893066, "global_step": 509613, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0242652893066406, "global_step": 509614, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0644171237945557, "global_step": 509615, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9795671701431274, "global_step": 509616, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.052004337310791, "global_step": 509617, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0737595558166504, "global_step": 509618, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9849809408187866, "global_step": 509619, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.026047468185425, "global_step": 509620, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.115934133529663, "global_step": 509621, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.010328531265259, "global_step": 509622, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0092310905456543, "global_step": 509623, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.032337188720703, "global_step": 509624, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9103198051452637, "global_step": 509625, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1143898963928223, "global_step": 509626, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9709761142730713, "global_step": 509627, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0218591690063477, "global_step": 509628, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.023404359817505, "global_step": 509629, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0636744499206543, "global_step": 509630, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.026395797729492, "global_step": 509631, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.023428201675415, "global_step": 509632, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0609068870544434, "global_step": 509633, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0924196243286133, "global_step": 509634, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0904629230499268, "global_step": 509635, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.135305404663086, "global_step": 509636, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0185365676879883, "global_step": 509637, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0616397857666016, "global_step": 509638, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.023460626602173, "global_step": 509639, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0735535621643066, "global_step": 509640, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.144263982772827, "global_step": 509641, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0385186672210693, "global_step": 509642, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0027847290039062, "global_step": 509643, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.069134473800659, "global_step": 509644, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.029534339904785, "global_step": 509645, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1191186904907227, "global_step": 509646, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.107105016708374, "global_step": 509647, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.07608962059021, "global_step": 509648, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1113667488098145, "global_step": 509649, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.142890453338623, "global_step": 509650, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0738203525543213, "global_step": 509651, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9871737957000732, "global_step": 509652, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.109682083129883, "global_step": 509653, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.114419937133789, "global_step": 509654, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0925402641296387, "global_step": 509655, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0813138484954834, "global_step": 509656, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0646493434906006, "global_step": 509657, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.020002841949463, "global_step": 509658, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.042757749557495, "global_step": 509659, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.026247262954712, "global_step": 509660, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.053074836730957, "global_step": 509661, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1411001682281494, "global_step": 509662, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0586845874786377, "global_step": 509663, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0050244331359863, "global_step": 509664, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0919322967529297, "global_step": 509665, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0185678005218506, "global_step": 509666, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1023192405700684, "global_step": 509667, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0202672481536865, "global_step": 509668, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9945487976074219, "global_step": 509669, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0835301876068115, "global_step": 509670, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0354726314544678, "global_step": 509671, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9969426393508911, "global_step": 509672, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0329794883728027, "global_step": 509673, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.097332000732422, "global_step": 509674, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.186757802963257, "global_step": 509675, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0296730995178223, "global_step": 509676, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.018491744995117, "global_step": 509677, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.035191535949707, "global_step": 509678, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0801756381988525, "global_step": 509679, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.029937505722046, "global_step": 509680, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0718321800231934, "global_step": 509681, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.100322723388672, "global_step": 509682, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.031367778778076, "global_step": 509683, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0226712226867676, "global_step": 509684, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9886927604675293, "global_step": 509685, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.072042465209961, "global_step": 509686, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0822250843048096, "global_step": 509687, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0544891357421875, "global_step": 509688, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.007053852081299, "global_step": 509689, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0291848182678223, "global_step": 509690, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.067809581756592, "global_step": 509691, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0408778190612793, "global_step": 509692, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9886507987976074, "global_step": 509693, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0453789234161377, "global_step": 509694, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.126432418823242, "global_step": 509695, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0722272396087646, "global_step": 509696, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0008890628814697, "global_step": 509697, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.095017671585083, "global_step": 509698, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.064500093460083, "global_step": 509699, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.019329071044922, "global_step": 509700, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.049281597137451, "global_step": 509701, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.055429697036743, "global_step": 509702, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0175838470458984, "global_step": 509703, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1652588844299316, "global_step": 509704, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0057802200317383, "global_step": 509705, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9988867044448853, "global_step": 509706, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.015284299850464, "global_step": 509707, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.027925968170166, "global_step": 509708, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9821439981460571, "global_step": 509709, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0418224334716797, "global_step": 509710, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0053305625915527, "global_step": 509711, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0374503135681152, "global_step": 509712, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0179076194763184, "global_step": 509713, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0970983505249023, "global_step": 509714, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9380662441253662, "global_step": 509715, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0970919132232666, "global_step": 509716, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0007851123809814, "global_step": 509717, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.102872133255005, "global_step": 509718, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.020639657974243, "global_step": 509719, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0715417861938477, "global_step": 509720, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.058112859725952, "global_step": 509721, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.067628860473633, "global_step": 509722, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.079575777053833, "global_step": 509723, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.001673460006714, "global_step": 509724, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0657761096954346, "global_step": 509725, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0980172157287598, "global_step": 509726, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.089500665664673, "global_step": 509727, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.088045120239258, "global_step": 509728, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.994718313217163, "global_step": 509729, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.098616361618042, "global_step": 509730, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9674668312072754, "global_step": 509731, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1508371829986572, "global_step": 509732, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.110488176345825, "global_step": 509733, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0762746334075928, "global_step": 509734, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0024187564849854, "global_step": 509735, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.993354320526123, "global_step": 509736, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0392606258392334, "global_step": 509737, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0871243476867676, "global_step": 509738, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.044830322265625, "global_step": 509739, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0569212436676025, "global_step": 509740, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.073063850402832, "global_step": 509741, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.024135112762451, "global_step": 509742, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.058147430419922, "global_step": 509743, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.062013864517212, "global_step": 509744, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.034189462661743, "global_step": 509745, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0407257080078125, "global_step": 509746, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.134208917617798, "global_step": 509747, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.063242197036743, "global_step": 509748, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0298123359680176, "global_step": 509749, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0259125232696533, "global_step": 509750, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0807414054870605, "global_step": 509751, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.091183662414551, "global_step": 509752, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.101304292678833, "global_step": 509753, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0680596828460693, "global_step": 509754, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.052018404006958, "global_step": 509755, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.115236282348633, "global_step": 509756, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.038419485092163, "global_step": 509757, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1489691734313965, "global_step": 509758, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0411036014556885, "global_step": 509759, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.969303011894226, "global_step": 509760, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.068026304244995, "global_step": 509761, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0344693660736084, "global_step": 509762, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.093752861022949, "global_step": 509763, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.979732871055603, "global_step": 509764, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1046125888824463, "global_step": 509765, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0037930011749268, "global_step": 509766, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.037041187286377, "global_step": 509767, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.038884401321411, "global_step": 509768, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9996857643127441, "global_step": 509769, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0722546577453613, "global_step": 509770, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0945510864257812, "global_step": 509771, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0571813583374023, "global_step": 509772, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1343326568603516, "global_step": 509773, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.952269434928894, "global_step": 509774, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.044219732284546, "global_step": 509775, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0910236835479736, "global_step": 509776, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0824930667877197, "global_step": 509777, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.032269239425659, "global_step": 509778, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.120699405670166, "global_step": 509779, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.037698268890381, "global_step": 509780, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9991235733032227, "global_step": 509781, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.021088123321533, "global_step": 509782, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1483702659606934, "global_step": 509783, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0872421264648438, "global_step": 509784, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0318386554718018, "global_step": 509785, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.002213954925537, "global_step": 509786, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0733933448791504, "global_step": 509787, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1150624752044678, "global_step": 509788, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.055657386779785, "global_step": 509789, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1119577884674072, "global_step": 509790, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.031393051147461, "global_step": 509791, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.121157646179199, "global_step": 509792, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0603201389312744, "global_step": 509793, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0541610717773438, "global_step": 509794, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.026911973953247, "global_step": 509795, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0501153469085693, "global_step": 509796, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.062704086303711, "global_step": 509797, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0248165130615234, "global_step": 509798, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.065523386001587, "global_step": 509799, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.018523693084717, "global_step": 509800, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0222725868225098, "global_step": 509801, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0873801708221436, "global_step": 509802, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0859670639038086, "global_step": 509803, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0448286533355713, "global_step": 509804, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.050473213195801, "global_step": 509805, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1206412315368652, "global_step": 509806, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0164966583251953, "global_step": 509807, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.062297821044922, "global_step": 509808, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.123809337615967, "global_step": 509809, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0522501468658447, "global_step": 509810, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.1214311122894287, "global_step": 509811, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.088367462158203, "global_step": 509812, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0899245738983154, "global_step": 509813, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.065599203109741, "global_step": 509814, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.065680742263794, "global_step": 509815, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.014646530151367, "global_step": 509816, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0929830074310303, "global_step": 509817, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.086514711380005, "global_step": 509818, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0122578144073486, "global_step": 509819, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.047415018081665, "global_step": 509820, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0533409118652344, "global_step": 509821, "epoch": 875, "lr": 5e-05}
{"train_loss": 1.9977511167526245, "global_step": 509822, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0798299312591553, "global_step": 509823, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.061662197113037, "global_step": 509824, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.086331605911255, "global_step": 509825, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.049098014831543, "global_step": 509826, "epoch": 875, "lr": 5e-05}
{"train_loss": 2.0613911151885986, "global_step": 509827, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.041242837905884, "global_step": 509828, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9925403594970703, "global_step": 509829, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.115173101425171, "global_step": 509830, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.10718035697937, "global_step": 509831, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0902228355407715, "global_step": 509832, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.082246780395508, "global_step": 509833, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9947900772094727, "global_step": 509834, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.031052827835083, "global_step": 509835, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0723845958709717, "global_step": 509836, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0872037410736084, "global_step": 509837, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.134528160095215, "global_step": 509838, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0134146213531494, "global_step": 509839, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0755629539489746, "global_step": 509840, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.064924716949463, "global_step": 509841, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0628294944763184, "global_step": 509842, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0861082077026367, "global_step": 509843, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9781473875045776, "global_step": 509844, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9185558557510376, "global_step": 509845, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9745882749557495, "global_step": 509846, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.050516366958618, "global_step": 509847, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.077085494995117, "global_step": 509848, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.009387493133545, "global_step": 509849, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.047149896621704, "global_step": 509850, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0172200202941895, "global_step": 509851, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0116307735443115, "global_step": 509852, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.095543146133423, "global_step": 509853, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1546871662139893, "global_step": 509854, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.022517442703247, "global_step": 509855, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.012831449508667, "global_step": 509856, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0474319458007812, "global_step": 509857, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.071955919265747, "global_step": 509858, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.080925226211548, "global_step": 509859, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.048703193664551, "global_step": 509860, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0029547214508057, "global_step": 509861, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9849133491516113, "global_step": 509862, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.076655387878418, "global_step": 509863, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.057258367538452, "global_step": 509864, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.038625717163086, "global_step": 509865, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0823307037353516, "global_step": 509866, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0004899501800537, "global_step": 509867, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0577926635742188, "global_step": 509868, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0226309299468994, "global_step": 509869, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9457281827926636, "global_step": 509870, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.993080735206604, "global_step": 509871, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.050644874572754, "global_step": 509872, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.065063714981079, "global_step": 509873, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9938204288482666, "global_step": 509874, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0236332416534424, "global_step": 509875, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.066603422164917, "global_step": 509876, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9981938600540161, "global_step": 509877, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1109511852264404, "global_step": 509878, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.086672306060791, "global_step": 509879, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.062772274017334, "global_step": 509880, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.030867576599121, "global_step": 509881, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0818378925323486, "global_step": 509882, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0670933723449707, "global_step": 509883, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9905084371566772, "global_step": 509884, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0275824069976807, "global_step": 509885, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9872742891311646, "global_step": 509886, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0049915313720703, "global_step": 509887, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0653388500213623, "global_step": 509888, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0303285121917725, "global_step": 509889, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0072407722473145, "global_step": 509890, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.992140293121338, "global_step": 509891, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.033306837081909, "global_step": 509892, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0577523708343506, "global_step": 509893, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.090787172317505, "global_step": 509894, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0863614082336426, "global_step": 509895, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9970723390579224, "global_step": 509896, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9841612577438354, "global_step": 509897, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0993824005126953, "global_step": 509898, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9988648891448975, "global_step": 509899, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0899863243103027, "global_step": 509900, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0562686920166016, "global_step": 509901, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0461349487304688, "global_step": 509902, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0184311866760254, "global_step": 509903, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9791465997695923, "global_step": 509904, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0784308910369873, "global_step": 509905, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.10518217086792, "global_step": 509906, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0490522384643555, "global_step": 509907, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0541093349456787, "global_step": 509908, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9778201580047607, "global_step": 509909, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9661893844604492, "global_step": 509910, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0196497440338135, "global_step": 509911, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.070613145828247, "global_step": 509912, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1201555728912354, "global_step": 509913, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0516037940979004, "global_step": 509914, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0582451820373535, "global_step": 509915, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0701475143432617, "global_step": 509916, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.025211811065674, "global_step": 509917, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0661404132843018, "global_step": 509918, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0685477256774902, "global_step": 509919, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.034951686859131, "global_step": 509920, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.071254253387451, "global_step": 509921, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.021381139755249, "global_step": 509922, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0408687591552734, "global_step": 509923, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0290110111236572, "global_step": 509924, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0148797035217285, "global_step": 509925, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0546553134918213, "global_step": 509926, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.038950204849243, "global_step": 509927, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.040161609649658, "global_step": 509928, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1606600284576416, "global_step": 509929, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0319814682006836, "global_step": 509930, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0521109104156494, "global_step": 509931, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.016714334487915, "global_step": 509932, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0679454803466797, "global_step": 509933, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9813170433044434, "global_step": 509934, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.053812265396118, "global_step": 509935, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0714404582977295, "global_step": 509936, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.081042528152466, "global_step": 509937, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.008300542831421, "global_step": 509938, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0765771865844727, "global_step": 509939, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.035898447036743, "global_step": 509940, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.02750301361084, "global_step": 509941, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.047975540161133, "global_step": 509942, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.119903802871704, "global_step": 509943, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0613062381744385, "global_step": 509944, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.011814594268799, "global_step": 509945, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1373229026794434, "global_step": 509946, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0299737453460693, "global_step": 509947, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0006420612335205, "global_step": 509948, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0354318618774414, "global_step": 509949, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.108582019805908, "global_step": 509950, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9806804656982422, "global_step": 509951, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0284857749938965, "global_step": 509952, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.103013038635254, "global_step": 509953, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0325300693511963, "global_step": 509954, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.073625087738037, "global_step": 509955, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0657293796539307, "global_step": 509956, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.010624408721924, "global_step": 509957, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1781201362609863, "global_step": 509958, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0987322330474854, "global_step": 509959, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.069582939147949, "global_step": 509960, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.06075382232666, "global_step": 509961, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0271120071411133, "global_step": 509962, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.977614164352417, "global_step": 509963, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0485126972198486, "global_step": 509964, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.087104320526123, "global_step": 509965, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0344202518463135, "global_step": 509966, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0661873817443848, "global_step": 509967, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0350182056427, "global_step": 509968, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.918708324432373, "global_step": 509969, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9843965768814087, "global_step": 509970, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.058655023574829, "global_step": 509971, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0604231357574463, "global_step": 509972, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0593903064727783, "global_step": 509973, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0477592945098877, "global_step": 509974, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0836219787597656, "global_step": 509975, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0201621055603027, "global_step": 509976, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.044471263885498, "global_step": 509977, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.122070550918579, "global_step": 509978, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1032443046569824, "global_step": 509979, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.070580005645752, "global_step": 509980, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.076221227645874, "global_step": 509981, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0680274963378906, "global_step": 509982, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.051264524459839, "global_step": 509983, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.059584856033325, "global_step": 509984, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.114872455596924, "global_step": 509985, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.037747859954834, "global_step": 509986, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9802000522613525, "global_step": 509987, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0303103923797607, "global_step": 509988, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1097490787506104, "global_step": 509989, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1335289478302, "global_step": 509990, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0487282276153564, "global_step": 509991, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9484810829162598, "global_step": 509992, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.081989049911499, "global_step": 509993, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0900866985321045, "global_step": 509994, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0636658668518066, "global_step": 509995, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9982649087905884, "global_step": 509996, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1206512451171875, "global_step": 509997, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9624656438827515, "global_step": 509998, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.086702823638916, "global_step": 509999, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.061986207962036, "global_step": 510000, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9962350130081177, "global_step": 510001, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0132031440734863, "global_step": 510002, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0264155864715576, "global_step": 510003, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0503716468811035, "global_step": 510004, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.07485294342041, "global_step": 510005, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.026271343231201, "global_step": 510006, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.144329071044922, "global_step": 510007, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1183154582977295, "global_step": 510008, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.075361490249634, "global_step": 510009, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.066366195678711, "global_step": 510010, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0285234451293945, "global_step": 510011, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1357483863830566, "global_step": 510012, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.07619309425354, "global_step": 510013, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.06420636177063, "global_step": 510014, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0909156799316406, "global_step": 510015, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0858240127563477, "global_step": 510016, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0593440532684326, "global_step": 510017, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.061210870742798, "global_step": 510018, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.084845542907715, "global_step": 510019, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0410475730895996, "global_step": 510020, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9177374839782715, "global_step": 510021, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0210201740264893, "global_step": 510022, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0977303981781006, "global_step": 510023, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.044384717941284, "global_step": 510024, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9983547925949097, "global_step": 510025, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.083167314529419, "global_step": 510026, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.035731315612793, "global_step": 510027, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0796408653259277, "global_step": 510028, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.009455919265747, "global_step": 510029, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.039785861968994, "global_step": 510030, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.136199951171875, "global_step": 510031, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0563912391662598, "global_step": 510032, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.067352056503296, "global_step": 510033, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9660685062408447, "global_step": 510034, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0388906002044678, "global_step": 510035, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9712673425674438, "global_step": 510036, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9634250402450562, "global_step": 510037, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.019753932952881, "global_step": 510038, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0470168590545654, "global_step": 510039, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0353968143463135, "global_step": 510040, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.01924467086792, "global_step": 510041, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.045128345489502, "global_step": 510042, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0399487018585205, "global_step": 510043, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0771350860595703, "global_step": 510044, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.017554998397827, "global_step": 510045, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1348931789398193, "global_step": 510046, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9418747425079346, "global_step": 510047, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.007883071899414, "global_step": 510048, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.994634747505188, "global_step": 510049, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.054145574569702, "global_step": 510050, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0690033435821533, "global_step": 510051, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0294606685638428, "global_step": 510052, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0780625343322754, "global_step": 510053, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0565690994262695, "global_step": 510054, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9711527824401855, "global_step": 510055, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.078911781311035, "global_step": 510056, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0245561599731445, "global_step": 510057, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9973468780517578, "global_step": 510058, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0728185176849365, "global_step": 510059, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0469307899475098, "global_step": 510060, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9731762409210205, "global_step": 510061, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0629947185516357, "global_step": 510062, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0450327396392822, "global_step": 510063, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.001976251602173, "global_step": 510064, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1138670444488525, "global_step": 510065, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0295498371124268, "global_step": 510066, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.048657178878784, "global_step": 510067, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.051710367202759, "global_step": 510068, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9747545719146729, "global_step": 510069, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0319581031799316, "global_step": 510070, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9637959003448486, "global_step": 510071, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.018414258956909, "global_step": 510072, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0476293563842773, "global_step": 510073, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.083024501800537, "global_step": 510074, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0472936630249023, "global_step": 510075, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0728704929351807, "global_step": 510076, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9318585395812988, "global_step": 510077, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.052798271179199, "global_step": 510078, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1138994693756104, "global_step": 510079, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0650131702423096, "global_step": 510080, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.015801191329956, "global_step": 510081, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0300350189208984, "global_step": 510082, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.058917284011841, "global_step": 510083, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9448820352554321, "global_step": 510084, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0088541507720947, "global_step": 510085, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9668782949447632, "global_step": 510086, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.111253261566162, "global_step": 510087, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.069532632827759, "global_step": 510088, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.111872673034668, "global_step": 510089, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0370895862579346, "global_step": 510090, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.02923321723938, "global_step": 510091, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.120408296585083, "global_step": 510092, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0204811096191406, "global_step": 510093, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0497138500213623, "global_step": 510094, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0354366302490234, "global_step": 510095, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.021920680999756, "global_step": 510096, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1077444553375244, "global_step": 510097, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1095693111419678, "global_step": 510098, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1223299503326416, "global_step": 510099, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0391054153442383, "global_step": 510100, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.123389959335327, "global_step": 510101, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0391831398010254, "global_step": 510102, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.108966588973999, "global_step": 510103, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.101933240890503, "global_step": 510104, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0593113899230957, "global_step": 510105, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9960652589797974, "global_step": 510106, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0074918270111084, "global_step": 510107, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0943071842193604, "global_step": 510108, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.056657552719116, "global_step": 510109, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0952751636505127, "global_step": 510110, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.012856960296631, "global_step": 510111, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0451183319091797, "global_step": 510112, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0886733531951904, "global_step": 510113, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0160951614379883, "global_step": 510114, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0391037464141846, "global_step": 510115, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0424275398254395, "global_step": 510116, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9844566583633423, "global_step": 510117, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0468456745147705, "global_step": 510118, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0651755332946777, "global_step": 510119, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0233585834503174, "global_step": 510120, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.035205841064453, "global_step": 510121, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.056216239929199, "global_step": 510122, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.085155487060547, "global_step": 510123, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.96247398853302, "global_step": 510124, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0601179599761963, "global_step": 510125, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0835862159729004, "global_step": 510126, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1530957221984863, "global_step": 510127, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.063249349594116, "global_step": 510128, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0641872882843018, "global_step": 510129, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0297436714172363, "global_step": 510130, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0334200859069824, "global_step": 510131, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.080979824066162, "global_step": 510132, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9833494424819946, "global_step": 510133, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0429794788360596, "global_step": 510134, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0182807445526123, "global_step": 510135, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0416178703308105, "global_step": 510136, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0085041522979736, "global_step": 510137, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.05084228515625, "global_step": 510138, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0146896839141846, "global_step": 510139, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.018594741821289, "global_step": 510140, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.038278818130493, "global_step": 510141, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.032365322113037, "global_step": 510142, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0892956256866455, "global_step": 510143, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9924689531326294, "global_step": 510144, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0886454582214355, "global_step": 510145, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0943195819854736, "global_step": 510146, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0487771034240723, "global_step": 510147, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0286929607391357, "global_step": 510148, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9076539278030396, "global_step": 510149, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.089216470718384, "global_step": 510150, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0092713832855225, "global_step": 510151, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0005574226379395, "global_step": 510152, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0823235511779785, "global_step": 510153, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1254281997680664, "global_step": 510154, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.059410810470581, "global_step": 510155, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0194954872131348, "global_step": 510156, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.063849925994873, "global_step": 510157, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0386135578155518, "global_step": 510158, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0966811180114746, "global_step": 510159, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0246365070343018, "global_step": 510160, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1162078380584717, "global_step": 510161, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9888875484466553, "global_step": 510162, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.951566219329834, "global_step": 510163, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.047063112258911, "global_step": 510164, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0926103591918945, "global_step": 510165, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.029850959777832, "global_step": 510166, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.94671630859375, "global_step": 510167, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.07503604888916, "global_step": 510168, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9911181926727295, "global_step": 510169, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1312332153320312, "global_step": 510170, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0072429180145264, "global_step": 510171, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.079521656036377, "global_step": 510172, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.998842716217041, "global_step": 510173, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0736074447631836, "global_step": 510174, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.04066801071167, "global_step": 510175, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0868663787841797, "global_step": 510176, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.113708257675171, "global_step": 510177, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1076266765594482, "global_step": 510178, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.043518304824829, "global_step": 510179, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.055419683456421, "global_step": 510180, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.082653045654297, "global_step": 510181, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9665789604187012, "global_step": 510182, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0401346683502197, "global_step": 510183, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.044584274291992, "global_step": 510184, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0345511436462402, "global_step": 510185, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0102157592773438, "global_step": 510186, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1223738193511963, "global_step": 510187, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0702550411224365, "global_step": 510188, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0137104988098145, "global_step": 510189, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9406123161315918, "global_step": 510190, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0377488136291504, "global_step": 510191, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0665810108184814, "global_step": 510192, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0490448474884033, "global_step": 510193, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.157405138015747, "global_step": 510194, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0982446670532227, "global_step": 510195, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.073657751083374, "global_step": 510196, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.978184461593628, "global_step": 510197, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.019686460494995, "global_step": 510198, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9875308275222778, "global_step": 510199, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0066518783569336, "global_step": 510200, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.131049156188965, "global_step": 510201, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.147919178009033, "global_step": 510202, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0977323055267334, "global_step": 510203, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.083486318588257, "global_step": 510204, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9771846532821655, "global_step": 510205, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0017244815826416, "global_step": 510206, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9915599822998047, "global_step": 510207, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1435415744781494, "global_step": 510208, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.046210765838623, "global_step": 510209, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0827596187591553, "global_step": 510210, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1140971183776855, "global_step": 510211, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.018206834793091, "global_step": 510212, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1224935054779053, "global_step": 510213, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0297114849090576, "global_step": 510214, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0604445934295654, "global_step": 510215, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9942560195922852, "global_step": 510216, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0182831287384033, "global_step": 510217, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0258843898773193, "global_step": 510218, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.106790781021118, "global_step": 510219, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1400651931762695, "global_step": 510220, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9887334108352661, "global_step": 510221, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0778496265411377, "global_step": 510222, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0688953399658203, "global_step": 510223, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0746853351593018, "global_step": 510224, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.031446695327759, "global_step": 510225, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9491652250289917, "global_step": 510226, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0315794944763184, "global_step": 510227, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9479109048843384, "global_step": 510228, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1356897354125977, "global_step": 510229, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9655171632766724, "global_step": 510230, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0068447589874268, "global_step": 510231, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.09667706489563, "global_step": 510232, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0251307487487793, "global_step": 510233, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9872620105743408, "global_step": 510234, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.044769287109375, "global_step": 510235, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0022928714752197, "global_step": 510236, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.007720470428467, "global_step": 510237, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.132014036178589, "global_step": 510238, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0146565437316895, "global_step": 510239, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9698911905288696, "global_step": 510240, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0605032444000244, "global_step": 510241, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.082439661026001, "global_step": 510242, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.025341749191284, "global_step": 510243, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9605598449707031, "global_step": 510244, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0635383129119873, "global_step": 510245, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.114901542663574, "global_step": 510246, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0351502895355225, "global_step": 510247, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9990525245666504, "global_step": 510248, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.028502941131592, "global_step": 510249, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.075561761856079, "global_step": 510250, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.919004201889038, "global_step": 510251, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0203731060028076, "global_step": 510252, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.180677890777588, "global_step": 510253, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1420154571533203, "global_step": 510254, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0233922004699707, "global_step": 510255, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0391852855682373, "global_step": 510256, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0367166996002197, "global_step": 510257, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.028404712677002, "global_step": 510258, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.083265542984009, "global_step": 510259, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.03590989112854, "global_step": 510260, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.012047052383423, "global_step": 510261, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.037395477294922, "global_step": 510262, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0680220127105713, "global_step": 510263, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0553250312805176, "global_step": 510264, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0834317207336426, "global_step": 510265, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9433704614639282, "global_step": 510266, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0321600437164307, "global_step": 510267, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9976054430007935, "global_step": 510268, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0482773780822754, "global_step": 510269, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0508322715759277, "global_step": 510270, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.052898406982422, "global_step": 510271, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0701615810394287, "global_step": 510272, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0640323162078857, "global_step": 510273, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.059586763381958, "global_step": 510274, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.008074998855591, "global_step": 510275, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0819475650787354, "global_step": 510276, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.058251142501831, "global_step": 510277, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0475223064422607, "global_step": 510278, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.135411500930786, "global_step": 510279, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9920052289962769, "global_step": 510280, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0489532947540283, "global_step": 510281, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9883359670639038, "global_step": 510282, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.025089979171753, "global_step": 510283, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0869691371917725, "global_step": 510284, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0771915912628174, "global_step": 510285, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.011021375656128, "global_step": 510286, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9884624481201172, "global_step": 510287, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.060786724090576, "global_step": 510288, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.023496150970459, "global_step": 510289, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0571775436401367, "global_step": 510290, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9994086027145386, "global_step": 510291, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.071629762649536, "global_step": 510292, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0432395935058594, "global_step": 510293, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.040257453918457, "global_step": 510294, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.060380220413208, "global_step": 510295, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.020426034927368, "global_step": 510296, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.053910493850708, "global_step": 510297, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.087329149246216, "global_step": 510298, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.046546459197998, "global_step": 510299, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0430028438568115, "global_step": 510300, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.999708652496338, "global_step": 510301, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.116431951522827, "global_step": 510302, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.114745855331421, "global_step": 510303, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0619754791259766, "global_step": 510304, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.058767557144165, "global_step": 510305, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.104576587677002, "global_step": 510306, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0513405799865723, "global_step": 510307, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0466175079345703, "global_step": 510308, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9605973958969116, "global_step": 510309, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0753002166748047, "global_step": 510310, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.8866691589355469, "global_step": 510311, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.08847713470459, "global_step": 510312, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0921764373779297, "global_step": 510313, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.007819414138794, "global_step": 510314, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0264596939086914, "global_step": 510315, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.052759885787964, "global_step": 510316, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0432791709899902, "global_step": 510317, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.090132474899292, "global_step": 510318, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0988543033599854, "global_step": 510319, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0590715408325195, "global_step": 510320, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0382676124572754, "global_step": 510321, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.047783613204956, "global_step": 510322, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1024773120880127, "global_step": 510323, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.008111000061035, "global_step": 510324, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0251386165618896, "global_step": 510325, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0040011405944824, "global_step": 510326, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.051663875579834, "global_step": 510327, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0947396755218506, "global_step": 510328, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0049097537994385, "global_step": 510329, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0487844944000244, "global_step": 510330, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9597183465957642, "global_step": 510331, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0947344303131104, "global_step": 510332, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.054919958114624, "global_step": 510333, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0253541469573975, "global_step": 510334, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0385122299194336, "global_step": 510335, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9803314208984375, "global_step": 510336, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0218915939331055, "global_step": 510337, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.017815589904785, "global_step": 510338, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1381044387817383, "global_step": 510339, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.052112579345703, "global_step": 510340, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.03814697265625, "global_step": 510341, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9870505332946777, "global_step": 510342, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0047683715820312, "global_step": 510343, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0149946212768555, "global_step": 510344, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.039125442504883, "global_step": 510345, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1009721755981445, "global_step": 510346, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.142245054244995, "global_step": 510347, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0883405208587646, "global_step": 510348, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0737297534942627, "global_step": 510349, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0644354820251465, "global_step": 510350, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0649313926696777, "global_step": 510351, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9708902835845947, "global_step": 510352, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0021204948425293, "global_step": 510353, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.026540994644165, "global_step": 510354, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9891642332077026, "global_step": 510355, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.995705485343933, "global_step": 510356, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0299630165100098, "global_step": 510357, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0840704441070557, "global_step": 510358, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0576672554016113, "global_step": 510359, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.046299457550049, "global_step": 510360, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0275518894195557, "global_step": 510361, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.121403455734253, "global_step": 510362, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.061715602874756, "global_step": 510363, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.079754590988159, "global_step": 510364, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0001368522644043, "global_step": 510365, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0248146057128906, "global_step": 510366, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.016892194747925, "global_step": 510367, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.038395643234253, "global_step": 510368, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1080162525177, "global_step": 510369, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.026723623275757, "global_step": 510370, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0879831314086914, "global_step": 510371, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.089733123779297, "global_step": 510372, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9593514204025269, "global_step": 510373, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0630273818969727, "global_step": 510374, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.058610200881958, "global_step": 510375, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0950381755828857, "global_step": 510376, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0684306621551514, "global_step": 510377, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0127053260803223, "global_step": 510378, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.053093910217285, "global_step": 510379, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.095095634460449, "global_step": 510380, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.044835329055786, "global_step": 510381, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0537936687469482, "global_step": 510382, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0680861473083496, "global_step": 510383, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.003709316253662, "global_step": 510384, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.990073323249817, "global_step": 510385, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.063037633895874, "global_step": 510386, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.961470603942871, "global_step": 510387, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.037801504135132, "global_step": 510388, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.141446828842163, "global_step": 510389, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.073370933532715, "global_step": 510390, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.16974139213562, "global_step": 510391, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.032801389694214, "global_step": 510392, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1033880710601807, "global_step": 510393, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0651378631591797, "global_step": 510394, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.059342622756958, "global_step": 510395, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0256221294403076, "global_step": 510396, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.085982322692871, "global_step": 510397, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9738152027130127, "global_step": 510398, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0323121547698975, "global_step": 510399, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0550942420959473, "global_step": 510400, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.069455862045288, "global_step": 510401, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.092180013656616, "global_step": 510402, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0165212154388428, "global_step": 510403, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0281293392181396, "global_step": 510404, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0245604515075684, "global_step": 510405, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1402595043182373, "global_step": 510406, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.019120693206787, "global_step": 510407, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0433175563812256, "global_step": 510408, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.037717580795288, "global_step": 510409, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0191733837127686, "global_step": 510410, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0745153427124023, "global_step": 510411, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0705759525299072, "global_step": 510412, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.027862310409546, "global_step": 510413, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0735654830932617, "global_step": 510414, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0122921466827393, "global_step": 510415, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9829089641571045, "global_step": 510416, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0026679039001465, "global_step": 510417, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0475869178771973, "global_step": 510418, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0019407272338867, "global_step": 510419, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.072240114212036, "global_step": 510420, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.105363607406616, "global_step": 510421, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9670332670211792, "global_step": 510422, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.005054235458374, "global_step": 510423, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1559324264526367, "global_step": 510424, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0507912635803223, "global_step": 510425, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1035990715026855, "global_step": 510426, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0053515434265137, "global_step": 510427, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0076584815979004, "global_step": 510428, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1024019718170166, "global_step": 510429, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.135514497756958, "global_step": 510430, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.062809705734253, "global_step": 510431, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.087336540222168, "global_step": 510432, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0391533374786377, "global_step": 510433, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0366857051849365, "global_step": 510434, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.022294282913208, "global_step": 510435, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.07356333732605, "global_step": 510436, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0210907459259033, "global_step": 510437, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.117709159851074, "global_step": 510438, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9944322109222412, "global_step": 510439, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0860517024993896, "global_step": 510440, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.989997386932373, "global_step": 510441, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.999927282333374, "global_step": 510442, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0796713829040527, "global_step": 510443, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0434603691101074, "global_step": 510444, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9738929271697998, "global_step": 510445, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.061025619506836, "global_step": 510446, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0065836906433105, "global_step": 510447, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0646376609802246, "global_step": 510448, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1301088333129883, "global_step": 510449, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0337204933166504, "global_step": 510450, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.057434320449829, "global_step": 510451, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.056098222732544, "global_step": 510452, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.092578649520874, "global_step": 510453, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0288712978363037, "global_step": 510454, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0691800117492676, "global_step": 510455, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.108466625213623, "global_step": 510456, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0854783058166504, "global_step": 510457, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0293242931365967, "global_step": 510458, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0385520458221436, "global_step": 510459, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0361926555633545, "global_step": 510460, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9894946813583374, "global_step": 510461, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0839271545410156, "global_step": 510462, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0660548210144043, "global_step": 510463, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0767762660980225, "global_step": 510464, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0829944610595703, "global_step": 510465, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0286900997161865, "global_step": 510466, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0712337493896484, "global_step": 510467, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.046359062194824, "global_step": 510468, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.009601593017578, "global_step": 510469, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0138871669769287, "global_step": 510470, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.072373390197754, "global_step": 510471, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0347788333892822, "global_step": 510472, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0133450031280518, "global_step": 510473, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0698928833007812, "global_step": 510474, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.988503336906433, "global_step": 510475, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0869884490966797, "global_step": 510476, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.997698187828064, "global_step": 510477, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.142124891281128, "global_step": 510478, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0780417919158936, "global_step": 510479, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.105706214904785, "global_step": 510480, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0957448482513428, "global_step": 510481, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.980528473854065, "global_step": 510482, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.089087724685669, "global_step": 510483, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.02838134765625, "global_step": 510484, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9795418977737427, "global_step": 510485, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.049067258834839, "global_step": 510486, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.026047468185425, "global_step": 510487, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.117584228515625, "global_step": 510488, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.151674270629883, "global_step": 510489, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.107128858566284, "global_step": 510490, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0255985260009766, "global_step": 510491, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.181657075881958, "global_step": 510492, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0928452014923096, "global_step": 510493, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.043194532394409, "global_step": 510494, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9361521005630493, "global_step": 510495, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.956898808479309, "global_step": 510496, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.108246088027954, "global_step": 510497, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0473899841308594, "global_step": 510498, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0926291942596436, "global_step": 510499, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9984813928604126, "global_step": 510500, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.031034469604492, "global_step": 510501, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0978708267211914, "global_step": 510502, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0267136096954346, "global_step": 510503, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1058011054992676, "global_step": 510504, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9664770364761353, "global_step": 510505, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0485081672668457, "global_step": 510506, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9957783222198486, "global_step": 510507, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0001347064971924, "global_step": 510508, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0518810749053955, "global_step": 510509, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0156781673431396, "global_step": 510510, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.101066827774048, "global_step": 510511, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9757238626480103, "global_step": 510512, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0729994773864746, "global_step": 510513, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0320403575897217, "global_step": 510514, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.045189380645752, "global_step": 510515, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.999612808227539, "global_step": 510516, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.015143632888794, "global_step": 510517, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.10634708404541, "global_step": 510518, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.003037214279175, "global_step": 510519, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0391955375671387, "global_step": 510520, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1374073028564453, "global_step": 510521, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1375041007995605, "global_step": 510522, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.04468035697937, "global_step": 510523, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9938009977340698, "global_step": 510524, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.054720878601074, "global_step": 510525, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0552167892456055, "global_step": 510526, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0996267795562744, "global_step": 510527, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.995814561843872, "global_step": 510528, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9671287536621094, "global_step": 510529, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0489442348480225, "global_step": 510530, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.10542893409729, "global_step": 510531, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0683226585388184, "global_step": 510532, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.157039165496826, "global_step": 510533, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.086972236633301, "global_step": 510534, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0328116416931152, "global_step": 510535, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0811831951141357, "global_step": 510536, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.027147054672241, "global_step": 510537, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0603761672973633, "global_step": 510538, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0072855949401855, "global_step": 510539, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.058100938796997, "global_step": 510540, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0478203296661377, "global_step": 510541, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.020275115966797, "global_step": 510542, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0228869915008545, "global_step": 510543, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0480966567993164, "global_step": 510544, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0042760372161865, "global_step": 510545, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0137760639190674, "global_step": 510546, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.077007293701172, "global_step": 510547, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.033252477645874, "global_step": 510548, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.106767416000366, "global_step": 510549, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0806562900543213, "global_step": 510550, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0221869945526123, "global_step": 510551, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.060598850250244, "global_step": 510552, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.100393772125244, "global_step": 510553, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0397231578826904, "global_step": 510554, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9664969444274902, "global_step": 510555, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.037821054458618, "global_step": 510556, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0525691509246826, "global_step": 510557, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0919442176818848, "global_step": 510558, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0986242294311523, "global_step": 510559, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0804224014282227, "global_step": 510560, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9849904775619507, "global_step": 510561, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0446486473083496, "global_step": 510562, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0284769535064697, "global_step": 510563, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0421853065490723, "global_step": 510564, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.017486572265625, "global_step": 510565, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.096287965774536, "global_step": 510566, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.007779836654663, "global_step": 510567, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0332376956939697, "global_step": 510568, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.070223331451416, "global_step": 510569, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.101402521133423, "global_step": 510570, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0385072231292725, "global_step": 510571, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.058422327041626, "global_step": 510572, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0749590396881104, "global_step": 510573, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0218608379364014, "global_step": 510574, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.8662210702896118, "global_step": 510575, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0766232013702393, "global_step": 510576, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.097069025039673, "global_step": 510577, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1158864498138428, "global_step": 510578, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.018129587173462, "global_step": 510579, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.080540657043457, "global_step": 510580, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0022730827331543, "global_step": 510581, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.121910572052002, "global_step": 510582, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0749270915985107, "global_step": 510583, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.023128032684326, "global_step": 510584, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.027914047241211, "global_step": 510585, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0467047691345215, "global_step": 510586, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0005247592926025, "global_step": 510587, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.02691388130188, "global_step": 510588, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1061043739318848, "global_step": 510589, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9806560277938843, "global_step": 510590, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9620518684387207, "global_step": 510591, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.034501314163208, "global_step": 510592, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0499606132507324, "global_step": 510593, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.017106294631958, "global_step": 510594, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0466504096984863, "global_step": 510595, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.19020676612854, "global_step": 510596, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0779383182525635, "global_step": 510597, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0021142959594727, "global_step": 510598, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1003992557525635, "global_step": 510599, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.108006477355957, "global_step": 510600, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.010701894760132, "global_step": 510601, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0188217163085938, "global_step": 510602, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.105562210083008, "global_step": 510603, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.078871726989746, "global_step": 510604, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.985309362411499, "global_step": 510605, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9917598962783813, "global_step": 510606, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0691792964935303, "global_step": 510607, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0489659309387207, "global_step": 510608, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0213782787323, "global_step": 510609, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1102559566497803, "global_step": 510610, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.105515480041504, "global_step": 510611, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9962489604949951, "global_step": 510612, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0277891159057617, "global_step": 510613, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0716700553894043, "global_step": 510614, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.050750255584717, "global_step": 510615, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9624605178833008, "global_step": 510616, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1586899757385254, "global_step": 510617, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.08014178276062, "global_step": 510618, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1669106483459473, "global_step": 510619, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1291322708129883, "global_step": 510620, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.095827579498291, "global_step": 510621, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0065693855285645, "global_step": 510622, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0038504600524902, "global_step": 510623, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0243773460388184, "global_step": 510624, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0116052627563477, "global_step": 510625, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.061314582824707, "global_step": 510626, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1060400009155273, "global_step": 510627, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.024359941482544, "global_step": 510628, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0740253925323486, "global_step": 510629, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0452094078063965, "global_step": 510630, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0379366874694824, "global_step": 510631, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0169031620025635, "global_step": 510632, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1217079162597656, "global_step": 510633, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0617799758911133, "global_step": 510634, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9781098365783691, "global_step": 510635, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.054018974304199, "global_step": 510636, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9877454042434692, "global_step": 510637, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.092226982116699, "global_step": 510638, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0475659370422363, "global_step": 510639, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.09513258934021, "global_step": 510640, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.034275770187378, "global_step": 510641, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0022456645965576, "global_step": 510642, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0266573429107666, "global_step": 510643, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0107028484344482, "global_step": 510644, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1178715229034424, "global_step": 510645, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1219308376312256, "global_step": 510646, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.126786947250366, "global_step": 510647, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0843913555145264, "global_step": 510648, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0565412044525146, "global_step": 510649, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0291879177093506, "global_step": 510650, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.048581600189209, "global_step": 510651, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.184337854385376, "global_step": 510652, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9837977886199951, "global_step": 510653, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0907208919525146, "global_step": 510654, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.042469024658203, "global_step": 510655, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0399322509765625, "global_step": 510656, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0810024738311768, "global_step": 510657, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0922746658325195, "global_step": 510658, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.095964193344116, "global_step": 510659, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0589423179626465, "global_step": 510660, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.172285556793213, "global_step": 510661, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.982683777809143, "global_step": 510662, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9547404050827026, "global_step": 510663, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0503487586975098, "global_step": 510664, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.075627326965332, "global_step": 510665, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.975213646888733, "global_step": 510666, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0176963806152344, "global_step": 510667, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.034475326538086, "global_step": 510668, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.014007329940796, "global_step": 510669, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.090827465057373, "global_step": 510670, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0190093517303467, "global_step": 510671, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.082592248916626, "global_step": 510672, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.077465772628784, "global_step": 510673, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.013557195663452, "global_step": 510674, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0805277824401855, "global_step": 510675, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0287821292877197, "global_step": 510676, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0772860050201416, "global_step": 510677, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.045757532119751, "global_step": 510678, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0110769271850586, "global_step": 510679, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.049107074737549, "global_step": 510680, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0504653453826904, "global_step": 510681, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1324706077575684, "global_step": 510682, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.051663637161255, "global_step": 510683, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0881311893463135, "global_step": 510684, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0543251037597656, "global_step": 510685, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0388736724853516, "global_step": 510686, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1039164066314697, "global_step": 510687, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0028157234191895, "global_step": 510688, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0078749656677246, "global_step": 510689, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.034158229827881, "global_step": 510690, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9905709028244019, "global_step": 510691, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.016092538833618, "global_step": 510692, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.077378034591675, "global_step": 510693, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0629730224609375, "global_step": 510694, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.064987897872925, "global_step": 510695, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.013786792755127, "global_step": 510696, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1031503677368164, "global_step": 510697, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.071343183517456, "global_step": 510698, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1736278533935547, "global_step": 510699, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1556031703948975, "global_step": 510700, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0274198055267334, "global_step": 510701, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1269736289978027, "global_step": 510702, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.074463367462158, "global_step": 510703, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9781982898712158, "global_step": 510704, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0095736980438232, "global_step": 510705, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.001227378845215, "global_step": 510706, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.040614604949951, "global_step": 510707, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9726532697677612, "global_step": 510708, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0791356563568115, "global_step": 510709, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0244431495666504, "global_step": 510710, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0386288166046143, "global_step": 510711, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0293447971343994, "global_step": 510712, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.054701566696167, "global_step": 510713, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0772175788879395, "global_step": 510714, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1016054153442383, "global_step": 510715, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1216208934783936, "global_step": 510716, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.035020112991333, "global_step": 510717, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9816081523895264, "global_step": 510718, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0667672157287598, "global_step": 510719, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0637075901031494, "global_step": 510720, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9961864948272705, "global_step": 510721, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0734519958496094, "global_step": 510722, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.2362513542175293, "global_step": 510723, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9857065677642822, "global_step": 510724, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0895750522613525, "global_step": 510725, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0964174270629883, "global_step": 510726, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0974812507629395, "global_step": 510727, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0310935974121094, "global_step": 510728, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.005035877227783, "global_step": 510729, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.035954236984253, "global_step": 510730, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.07049298286438, "global_step": 510731, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.064946413040161, "global_step": 510732, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9928793907165527, "global_step": 510733, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0681800842285156, "global_step": 510734, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0279541015625, "global_step": 510735, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1136317253112793, "global_step": 510736, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.003187656402588, "global_step": 510737, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.075493812561035, "global_step": 510738, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.989218831062317, "global_step": 510739, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.057091474533081, "global_step": 510740, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1062166690826416, "global_step": 510741, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9781718254089355, "global_step": 510742, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0226855278015137, "global_step": 510743, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.041912317276001, "global_step": 510744, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.054655075073242, "global_step": 510745, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0370090007781982, "global_step": 510746, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.070005178451538, "global_step": 510747, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0899672508239746, "global_step": 510748, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0163352489471436, "global_step": 510749, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.004242181777954, "global_step": 510750, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0002894401550293, "global_step": 510751, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1549127101898193, "global_step": 510752, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0506982803344727, "global_step": 510753, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1047399044036865, "global_step": 510754, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.012608766555786, "global_step": 510755, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0879616737365723, "global_step": 510756, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0876762866973877, "global_step": 510757, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.051766872406006, "global_step": 510758, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0751993656158447, "global_step": 510759, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.072025775909424, "global_step": 510760, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0758750438690186, "global_step": 510761, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0272276401519775, "global_step": 510762, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.033177375793457, "global_step": 510763, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0164008140563965, "global_step": 510764, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1014654636383057, "global_step": 510765, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0458292961120605, "global_step": 510766, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.08310866355896, "global_step": 510767, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.112093210220337, "global_step": 510768, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.006686210632324, "global_step": 510769, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.039116382598877, "global_step": 510770, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.034946918487549, "global_step": 510771, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.012474536895752, "global_step": 510772, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.135911703109741, "global_step": 510773, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.001824378967285, "global_step": 510774, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.03120756149292, "global_step": 510775, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0447988510131836, "global_step": 510776, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0901827812194824, "global_step": 510777, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.039091110229492, "global_step": 510778, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9836997985839844, "global_step": 510779, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0579984188079834, "global_step": 510780, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1029491424560547, "global_step": 510781, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.045407295227051, "global_step": 510782, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.071702241897583, "global_step": 510783, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1008448600769043, "global_step": 510784, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0230588912963867, "global_step": 510785, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.000495195388794, "global_step": 510786, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0521433353424072, "global_step": 510787, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0106136798858643, "global_step": 510788, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0192971229553223, "global_step": 510789, "epoch": 876, "lr": 5e-05}
{"train_loss": 1.9312129020690918, "global_step": 510790, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0513129234313965, "global_step": 510791, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0427401065826416, "global_step": 510792, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.0419318675994873, "global_step": 510793, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.1897165775299072, "global_step": 510794, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.048811197280884, "global_step": 510795, "epoch": 876, "lr": 5e-05}
{"train_loss": 2.046973943710327, "global_step": 510796, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0780467987060547, "global_step": 510797, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.034367561340332, "global_step": 510798, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1131789684295654, "global_step": 510799, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0801749229431152, "global_step": 510800, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0495808124542236, "global_step": 510801, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9764548540115356, "global_step": 510802, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.027270793914795, "global_step": 510803, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9969937801361084, "global_step": 510804, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0328822135925293, "global_step": 510805, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0629847049713135, "global_step": 510806, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0345723628997803, "global_step": 510807, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0380163192749023, "global_step": 510808, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.029743194580078, "global_step": 510809, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1085689067840576, "global_step": 510810, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0603294372558594, "global_step": 510811, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9952667951583862, "global_step": 510812, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1408891677856445, "global_step": 510813, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0445990562438965, "global_step": 510814, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.078840970993042, "global_step": 510815, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.098339319229126, "global_step": 510816, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.019538164138794, "global_step": 510817, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0099222660064697, "global_step": 510818, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9546077251434326, "global_step": 510819, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.11124587059021, "global_step": 510820, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.066875457763672, "global_step": 510821, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0124638080596924, "global_step": 510822, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.097075939178467, "global_step": 510823, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.983646035194397, "global_step": 510824, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0343422889709473, "global_step": 510825, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9905171394348145, "global_step": 510826, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.081136465072632, "global_step": 510827, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9145312309265137, "global_step": 510828, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.03609037399292, "global_step": 510829, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.080947160720825, "global_step": 510830, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9982969760894775, "global_step": 510831, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9851926565170288, "global_step": 510832, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0479586124420166, "global_step": 510833, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0937986373901367, "global_step": 510834, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0525643825531006, "global_step": 510835, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0368733406066895, "global_step": 510836, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.997753620147705, "global_step": 510837, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9996541738510132, "global_step": 510838, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.995298147201538, "global_step": 510839, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0699856281280518, "global_step": 510840, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9838947057724, "global_step": 510841, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0776140689849854, "global_step": 510842, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0268125534057617, "global_step": 510843, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9913983345031738, "global_step": 510844, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0459752082824707, "global_step": 510845, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0244784355163574, "global_step": 510846, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0038888454437256, "global_step": 510847, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.024798631668091, "global_step": 510848, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0407187938690186, "global_step": 510849, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.952433705329895, "global_step": 510850, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0228991508483887, "global_step": 510851, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.031534194946289, "global_step": 510852, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0648255348205566, "global_step": 510853, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0654642581939697, "global_step": 510854, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0461130142211914, "global_step": 510855, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0064313411712646, "global_step": 510856, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0253565311431885, "global_step": 510857, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0240237712860107, "global_step": 510858, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.056060552597046, "global_step": 510859, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0337815284729004, "global_step": 510860, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0531234741210938, "global_step": 510861, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0705509185791016, "global_step": 510862, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0053558349609375, "global_step": 510863, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1232779026031494, "global_step": 510864, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.035694122314453, "global_step": 510865, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0144119262695312, "global_step": 510866, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0414459705352783, "global_step": 510867, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0769259929656982, "global_step": 510868, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.06002140045166, "global_step": 510869, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0087575912475586, "global_step": 510870, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.016479015350342, "global_step": 510871, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1866872310638428, "global_step": 510872, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.039731979370117, "global_step": 510873, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.990235447883606, "global_step": 510874, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0318126678466797, "global_step": 510875, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9875143766403198, "global_step": 510876, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0854690074920654, "global_step": 510877, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.028764486312866, "global_step": 510878, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0165250301361084, "global_step": 510879, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.119980812072754, "global_step": 510880, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0742173194885254, "global_step": 510881, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1238853931427, "global_step": 510882, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.029082775115967, "global_step": 510883, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9673514366149902, "global_step": 510884, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0269217491149902, "global_step": 510885, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0861148834228516, "global_step": 510886, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0278117656707764, "global_step": 510887, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.021623373031616, "global_step": 510888, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0609147548675537, "global_step": 510889, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0080041885375977, "global_step": 510890, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0152668952941895, "global_step": 510891, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9947786331176758, "global_step": 510892, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.010490894317627, "global_step": 510893, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0000486373901367, "global_step": 510894, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0510077476501465, "global_step": 510895, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0153086185455322, "global_step": 510896, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.123227119445801, "global_step": 510897, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0790023803710938, "global_step": 510898, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.961230754852295, "global_step": 510899, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0075745582580566, "global_step": 510900, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.924460768699646, "global_step": 510901, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.064653158187866, "global_step": 510902, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0629570484161377, "global_step": 510903, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.975948452949524, "global_step": 510904, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0498123168945312, "global_step": 510905, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.089951992034912, "global_step": 510906, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.078200578689575, "global_step": 510907, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1406471729278564, "global_step": 510908, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.089862585067749, "global_step": 510909, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0670344829559326, "global_step": 510910, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.055589199066162, "global_step": 510911, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.047248601913452, "global_step": 510912, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.04581618309021, "global_step": 510913, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.101919174194336, "global_step": 510914, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0586187839508057, "global_step": 510915, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.046393632888794, "global_step": 510916, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0075783729553223, "global_step": 510917, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0700039863586426, "global_step": 510918, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0161986351013184, "global_step": 510919, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.995438814163208, "global_step": 510920, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9636881351470947, "global_step": 510921, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1201868057250977, "global_step": 510922, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0366368293762207, "global_step": 510923, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.080610990524292, "global_step": 510924, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1297876834869385, "global_step": 510925, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0967440605163574, "global_step": 510926, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0551795959472656, "global_step": 510927, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0121378898620605, "global_step": 510928, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.998013973236084, "global_step": 510929, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.115382194519043, "global_step": 510930, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.081491470336914, "global_step": 510931, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0352635383605957, "global_step": 510932, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.018950939178467, "global_step": 510933, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.083364486694336, "global_step": 510934, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0867350101470947, "global_step": 510935, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.000009059906006, "global_step": 510936, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0078072547912598, "global_step": 510937, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9648597240447998, "global_step": 510938, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.074723958969116, "global_step": 510939, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9584927558898926, "global_step": 510940, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9964641332626343, "global_step": 510941, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9811853170394897, "global_step": 510942, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.039546251296997, "global_step": 510943, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0039596557617188, "global_step": 510944, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1188061237335205, "global_step": 510945, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.059776544570923, "global_step": 510946, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0539331436157227, "global_step": 510947, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.10522198677063, "global_step": 510948, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.04734468460083, "global_step": 510949, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.047114849090576, "global_step": 510950, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.08052659034729, "global_step": 510951, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0731217861175537, "global_step": 510952, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.038294553756714, "global_step": 510953, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.091956853866577, "global_step": 510954, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.881780743598938, "global_step": 510955, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0496511459350586, "global_step": 510956, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9930286407470703, "global_step": 510957, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.049046277999878, "global_step": 510958, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.086336612701416, "global_step": 510959, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0540881156921387, "global_step": 510960, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0411102771759033, "global_step": 510961, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0483551025390625, "global_step": 510962, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.067850112915039, "global_step": 510963, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.017427444458008, "global_step": 510964, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9608498811721802, "global_step": 510965, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.084481954574585, "global_step": 510966, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.056455373764038, "global_step": 510967, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0519111156463623, "global_step": 510968, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0494909286499023, "global_step": 510969, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0278499126434326, "global_step": 510970, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0824968814849854, "global_step": 510971, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0835511684417725, "global_step": 510972, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0375726222991943, "global_step": 510973, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0257904529571533, "global_step": 510974, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0653584003448486, "global_step": 510975, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0617823600769043, "global_step": 510976, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.109391450881958, "global_step": 510977, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.983665108680725, "global_step": 510978, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.072171688079834, "global_step": 510979, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.099020004272461, "global_step": 510980, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.006608724594116, "global_step": 510981, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1014487743377686, "global_step": 510982, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9851804971694946, "global_step": 510983, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0726282596588135, "global_step": 510984, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9717384576797485, "global_step": 510985, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.00333833694458, "global_step": 510986, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9575072526931763, "global_step": 510987, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.007202386856079, "global_step": 510988, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.003239393234253, "global_step": 510989, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0110342502593994, "global_step": 510990, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9595301151275635, "global_step": 510991, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.030752658843994, "global_step": 510992, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0315427780151367, "global_step": 510993, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9186502695083618, "global_step": 510994, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9977531433105469, "global_step": 510995, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.052328109741211, "global_step": 510996, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0485928058624268, "global_step": 510997, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0936033725738525, "global_step": 510998, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0914835929870605, "global_step": 510999, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.042513847351074, "global_step": 511000, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0394415855407715, "global_step": 511001, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.007639169692993, "global_step": 511002, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0356624126434326, "global_step": 511003, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0371451377868652, "global_step": 511004, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0020241737365723, "global_step": 511005, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0832605361938477, "global_step": 511006, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0490074157714844, "global_step": 511007, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0224499702453613, "global_step": 511008, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0931811332702637, "global_step": 511009, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1011855602264404, "global_step": 511010, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0246448516845703, "global_step": 511011, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.02132248878479, "global_step": 511012, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.979248285293579, "global_step": 511013, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.138476848602295, "global_step": 511014, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0674798488616943, "global_step": 511015, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.985695242881775, "global_step": 511016, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1382317543029785, "global_step": 511017, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0461838245391846, "global_step": 511018, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.042128324508667, "global_step": 511019, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0945098400115967, "global_step": 511020, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.025207042694092, "global_step": 511021, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.97902512550354, "global_step": 511022, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.11017107963562, "global_step": 511023, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0228185653686523, "global_step": 511024, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0529398918151855, "global_step": 511025, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.075864553451538, "global_step": 511026, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0093140602111816, "global_step": 511027, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.128695011138916, "global_step": 511028, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9507808685302734, "global_step": 511029, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.027003526687622, "global_step": 511030, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0694169998168945, "global_step": 511031, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.073301315307617, "global_step": 511032, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.077544689178467, "global_step": 511033, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.186772346496582, "global_step": 511034, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0755865573883057, "global_step": 511035, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9957952499389648, "global_step": 511036, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0536906719207764, "global_step": 511037, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0281918048858643, "global_step": 511038, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0609874725341797, "global_step": 511039, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0281240940093994, "global_step": 511040, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.041782855987549, "global_step": 511041, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1473026275634766, "global_step": 511042, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.051892042160034, "global_step": 511043, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.003035545349121, "global_step": 511044, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.093484401702881, "global_step": 511045, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0896403789520264, "global_step": 511046, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1083550453186035, "global_step": 511047, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.005937099456787, "global_step": 511048, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0370969772338867, "global_step": 511049, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1127524375915527, "global_step": 511050, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0535058975219727, "global_step": 511051, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9916085004806519, "global_step": 511052, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.970080018043518, "global_step": 511053, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9426112174987793, "global_step": 511054, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0648272037506104, "global_step": 511055, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0169601440429688, "global_step": 511056, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.000364065170288, "global_step": 511057, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.046653985977173, "global_step": 511058, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0041167736053467, "global_step": 511059, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.024252414703369, "global_step": 511060, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9852794408798218, "global_step": 511061, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1048641204833984, "global_step": 511062, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.020521640777588, "global_step": 511063, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9909305572509766, "global_step": 511064, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9827533960342407, "global_step": 511065, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.012922525405884, "global_step": 511066, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1173503398895264, "global_step": 511067, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0906074047088623, "global_step": 511068, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0312001705169678, "global_step": 511069, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0861456394195557, "global_step": 511070, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0494701862335205, "global_step": 511071, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.077518939971924, "global_step": 511072, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.087651491165161, "global_step": 511073, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0149707794189453, "global_step": 511074, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.161707639694214, "global_step": 511075, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0800094604492188, "global_step": 511076, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0639901161193848, "global_step": 511077, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9274215698242188, "global_step": 511078, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.967307686805725, "global_step": 511079, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.059483766555786, "global_step": 511080, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9145411252975464, "global_step": 511081, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.06459641456604, "global_step": 511082, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0112287998199463, "global_step": 511083, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.035468816757202, "global_step": 511084, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1551008224487305, "global_step": 511085, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0567586421966553, "global_step": 511086, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0501487255096436, "global_step": 511087, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0050599575042725, "global_step": 511088, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9957451820373535, "global_step": 511089, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.949461579322815, "global_step": 511090, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0959627628326416, "global_step": 511091, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.114518880844116, "global_step": 511092, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0798325538635254, "global_step": 511093, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0211539268493652, "global_step": 511094, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0733492374420166, "global_step": 511095, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.073568820953369, "global_step": 511096, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0272305011749268, "global_step": 511097, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.077244281768799, "global_step": 511098, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.046135902404785, "global_step": 511099, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1262588500976562, "global_step": 511100, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.067864418029785, "global_step": 511101, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0749142169952393, "global_step": 511102, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0391151905059814, "global_step": 511103, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0154194831848145, "global_step": 511104, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0933737754821777, "global_step": 511105, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1167707443237305, "global_step": 511106, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.995038628578186, "global_step": 511107, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0059452056884766, "global_step": 511108, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0348856449127197, "global_step": 511109, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0396933555603027, "global_step": 511110, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1107337474823, "global_step": 511111, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.112811326980591, "global_step": 511112, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.066049337387085, "global_step": 511113, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9779727458953857, "global_step": 511114, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9932585954666138, "global_step": 511115, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0797972679138184, "global_step": 511116, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.036360263824463, "global_step": 511117, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0203895568847656, "global_step": 511118, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.073159694671631, "global_step": 511119, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0248618125915527, "global_step": 511120, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9608362913131714, "global_step": 511121, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.020134449005127, "global_step": 511122, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0270628929138184, "global_step": 511123, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.003845453262329, "global_step": 511124, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0300073623657227, "global_step": 511125, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0507073402404785, "global_step": 511126, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0870590209960938, "global_step": 511127, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9496471881866455, "global_step": 511128, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.940773844718933, "global_step": 511129, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.134263277053833, "global_step": 511130, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.016737937927246, "global_step": 511131, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9590420722961426, "global_step": 511132, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9960932731628418, "global_step": 511133, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9617887735366821, "global_step": 511134, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9892032146453857, "global_step": 511135, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0052831172943115, "global_step": 511136, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0319690704345703, "global_step": 511137, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0987653732299805, "global_step": 511138, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0981781482696533, "global_step": 511139, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0610296726226807, "global_step": 511140, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1145639419555664, "global_step": 511141, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9155288934707642, "global_step": 511142, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.057028293609619, "global_step": 511143, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.092458486557007, "global_step": 511144, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.033945083618164, "global_step": 511145, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0596766471862793, "global_step": 511146, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.090125322341919, "global_step": 511147, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.064147472381592, "global_step": 511148, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.064176321029663, "global_step": 511149, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.049926519393921, "global_step": 511150, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9933720827102661, "global_step": 511151, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0130369663238525, "global_step": 511152, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0380563735961914, "global_step": 511153, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.035764694213867, "global_step": 511154, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1191203594207764, "global_step": 511155, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9458844661712646, "global_step": 511156, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0340492725372314, "global_step": 511157, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0624477863311768, "global_step": 511158, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.092996597290039, "global_step": 511159, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0170671939849854, "global_step": 511160, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0601696968078613, "global_step": 511161, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1814815998077393, "global_step": 511162, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0186116695404053, "global_step": 511163, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9913086891174316, "global_step": 511164, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0837020874023438, "global_step": 511165, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.001352548599243, "global_step": 511166, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.014303207397461, "global_step": 511167, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0278913974761963, "global_step": 511168, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.02970290184021, "global_step": 511169, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.044811964035034, "global_step": 511170, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0636961460113525, "global_step": 511171, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.083003520965576, "global_step": 511172, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0761971473693848, "global_step": 511173, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0505306720733643, "global_step": 511174, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0029244422912598, "global_step": 511175, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.065768003463745, "global_step": 511176, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0392069816589355, "global_step": 511177, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.059807300567627, "global_step": 511178, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.059042453765869, "global_step": 511179, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.011174201965332, "global_step": 511180, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.070404052734375, "global_step": 511181, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0578527450561523, "global_step": 511182, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.030259609222412, "global_step": 511183, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0937280654907227, "global_step": 511184, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0966084003448486, "global_step": 511185, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.031730890274048, "global_step": 511186, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0416746139526367, "global_step": 511187, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9913121461868286, "global_step": 511188, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0330302715301514, "global_step": 511189, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0439178943634033, "global_step": 511190, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.027056932449341, "global_step": 511191, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.066927433013916, "global_step": 511192, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.130300283432007, "global_step": 511193, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0705530643463135, "global_step": 511194, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0571107864379883, "global_step": 511195, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0427820682525635, "global_step": 511196, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.068369150161743, "global_step": 511197, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0437052249908447, "global_step": 511198, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.126873731613159, "global_step": 511199, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9537512063980103, "global_step": 511200, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9817383289337158, "global_step": 511201, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0735206604003906, "global_step": 511202, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.056122064590454, "global_step": 511203, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0512402057647705, "global_step": 511204, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0187504291534424, "global_step": 511205, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9838320016860962, "global_step": 511206, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.051520824432373, "global_step": 511207, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9843305349349976, "global_step": 511208, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.113929033279419, "global_step": 511209, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.020484447479248, "global_step": 511210, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9926156997680664, "global_step": 511211, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0703091621398926, "global_step": 511212, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.029165029525757, "global_step": 511213, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0571961402893066, "global_step": 511214, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.997345209121704, "global_step": 511215, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0640430450439453, "global_step": 511216, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0545244216918945, "global_step": 511217, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0830373764038086, "global_step": 511218, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.125594139099121, "global_step": 511219, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.043628215789795, "global_step": 511220, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.076537847518921, "global_step": 511221, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0979764461517334, "global_step": 511222, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0681517124176025, "global_step": 511223, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1045773029327393, "global_step": 511224, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.017359733581543, "global_step": 511225, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0624711513519287, "global_step": 511226, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.05058217048645, "global_step": 511227, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.061444044113159, "global_step": 511228, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9571747779846191, "global_step": 511229, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0843284130096436, "global_step": 511230, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.075981616973877, "global_step": 511231, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0134999752044678, "global_step": 511232, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0122995376586914, "global_step": 511233, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1693661212921143, "global_step": 511234, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.077087879180908, "global_step": 511235, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0256550312042236, "global_step": 511236, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9367196559906006, "global_step": 511237, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.127058506011963, "global_step": 511238, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0399093627929688, "global_step": 511239, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9433537721633911, "global_step": 511240, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.068957567214966, "global_step": 511241, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0448148250579834, "global_step": 511242, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1171393394470215, "global_step": 511243, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0786385536193848, "global_step": 511244, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0519678592681885, "global_step": 511245, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0183022022247314, "global_step": 511246, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9992156028747559, "global_step": 511247, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.992286205291748, "global_step": 511248, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.117076873779297, "global_step": 511249, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9849342107772827, "global_step": 511250, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.157125949859619, "global_step": 511251, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0676398277282715, "global_step": 511252, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.126006841659546, "global_step": 511253, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.118021011352539, "global_step": 511254, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0247690677642822, "global_step": 511255, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0341646671295166, "global_step": 511256, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0396010875701904, "global_step": 511257, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.132157564163208, "global_step": 511258, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9925402402877808, "global_step": 511259, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0666449069976807, "global_step": 511260, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.087146043777466, "global_step": 511261, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.038494825363159, "global_step": 511262, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0825653076171875, "global_step": 511263, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0492196083068848, "global_step": 511264, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1102840900421143, "global_step": 511265, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0051565170288086, "global_step": 511266, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0642707347869873, "global_step": 511267, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.961734414100647, "global_step": 511268, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0294134616851807, "global_step": 511269, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.127837657928467, "global_step": 511270, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.060516357421875, "global_step": 511271, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.148143768310547, "global_step": 511272, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.041692018508911, "global_step": 511273, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.079606533050537, "global_step": 511274, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0480716228485107, "global_step": 511275, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9981212615966797, "global_step": 511276, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.084890127182007, "global_step": 511277, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9944555759429932, "global_step": 511278, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0875813961029053, "global_step": 511279, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0520801544189453, "global_step": 511280, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0865917205810547, "global_step": 511281, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.092271089553833, "global_step": 511282, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0891222953796387, "global_step": 511283, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0698492527008057, "global_step": 511284, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.012845516204834, "global_step": 511285, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0720458030700684, "global_step": 511286, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.010542392730713, "global_step": 511287, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0887718200683594, "global_step": 511288, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.02717924118042, "global_step": 511289, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0800797939300537, "global_step": 511290, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9762966632843018, "global_step": 511291, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.95565664768219, "global_step": 511292, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9588289260864258, "global_step": 511293, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.962084412574768, "global_step": 511294, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0191028118133545, "global_step": 511295, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.093893051147461, "global_step": 511296, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1101224422454834, "global_step": 511297, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0038342475891113, "global_step": 511298, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.063614845275879, "global_step": 511299, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9579579830169678, "global_step": 511300, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0449774265289307, "global_step": 511301, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0403687953948975, "global_step": 511302, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0071914196014404, "global_step": 511303, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0147206783294678, "global_step": 511304, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0358269214630127, "global_step": 511305, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1174092292785645, "global_step": 511306, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1079423427581787, "global_step": 511307, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.054208278656006, "global_step": 511308, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.159956932067871, "global_step": 511309, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.042224168777466, "global_step": 511310, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9775272607803345, "global_step": 511311, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9628939628601074, "global_step": 511312, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0433785915374756, "global_step": 511313, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1023926734924316, "global_step": 511314, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.080909252166748, "global_step": 511315, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.033125400543213, "global_step": 511316, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1048829555511475, "global_step": 511317, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0354554653167725, "global_step": 511318, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.07307505607605, "global_step": 511319, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.062333822250366, "global_step": 511320, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.959189534187317, "global_step": 511321, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9973679780960083, "global_step": 511322, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0996408462524414, "global_step": 511323, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1448442935943604, "global_step": 511324, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0540030002593994, "global_step": 511325, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.059314012527466, "global_step": 511326, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0022079944610596, "global_step": 511327, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.124276876449585, "global_step": 511328, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0404410362243652, "global_step": 511329, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1115269660949707, "global_step": 511330, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0428481101989746, "global_step": 511331, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0534744262695312, "global_step": 511332, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.992749810218811, "global_step": 511333, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9909374713897705, "global_step": 511334, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1427559852600098, "global_step": 511335, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0501067638397217, "global_step": 511336, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0201480388641357, "global_step": 511337, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.039327383041382, "global_step": 511338, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.073554754257202, "global_step": 511339, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.112527847290039, "global_step": 511340, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0919437408447266, "global_step": 511341, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0393869876861572, "global_step": 511342, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9821712970733643, "global_step": 511343, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.044034004211426, "global_step": 511344, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0032804012298584, "global_step": 511345, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.080634355545044, "global_step": 511346, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.973212718963623, "global_step": 511347, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9927184581756592, "global_step": 511348, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9404605627059937, "global_step": 511349, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1072781085968018, "global_step": 511350, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9778279066085815, "global_step": 511351, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0520377159118652, "global_step": 511352, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.011892795562744, "global_step": 511353, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.03609561920166, "global_step": 511354, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0724520683288574, "global_step": 511355, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0201199054718018, "global_step": 511356, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.121088743209839, "global_step": 511357, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0694077014923096, "global_step": 511358, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.119384527206421, "global_step": 511359, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9706705808639526, "global_step": 511360, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.090404510498047, "global_step": 511361, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.037372350692749, "global_step": 511362, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.165196657180786, "global_step": 511363, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.003563404083252, "global_step": 511364, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0132334232330322, "global_step": 511365, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.043743848800659, "global_step": 511366, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0554773807525635, "global_step": 511367, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0423035621643066, "global_step": 511368, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0962672233581543, "global_step": 511369, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.060149669647217, "global_step": 511370, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.155985116958618, "global_step": 511371, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.122647762298584, "global_step": 511372, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9525572061538696, "global_step": 511373, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9456638097763062, "global_step": 511374, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.032268762588501, "global_step": 511375, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.063720941543579, "global_step": 511376, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.02201771736145, "global_step": 511377, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0831501483917236, "global_step": 511378, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1464574337005615, "global_step": 511379, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.011432409286499, "global_step": 511380, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0313405990600586, "global_step": 511381, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.987989902496338, "global_step": 511382, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.017179250717163, "global_step": 511383, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0140833854675293, "global_step": 511384, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0494472980499268, "global_step": 511385, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.097933530807495, "global_step": 511386, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.053339719772339, "global_step": 511387, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0216429233551025, "global_step": 511388, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0439367294311523, "global_step": 511389, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.12699556350708, "global_step": 511390, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.133786201477051, "global_step": 511391, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9989160299301147, "global_step": 511392, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.14329195022583, "global_step": 511393, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9785197973251343, "global_step": 511394, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.015848398208618, "global_step": 511395, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.121609687805176, "global_step": 511396, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.998137354850769, "global_step": 511397, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0645132064819336, "global_step": 511398, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.105846643447876, "global_step": 511399, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0767672061920166, "global_step": 511400, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.056488275527954, "global_step": 511401, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.007627010345459, "global_step": 511402, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0995161533355713, "global_step": 511403, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.029249668121338, "global_step": 511404, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1010444164276123, "global_step": 511405, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0552210807800293, "global_step": 511406, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0423078536987305, "global_step": 511407, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0056657791137695, "global_step": 511408, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0518150329589844, "global_step": 511409, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9687044620513916, "global_step": 511410, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9614330530166626, "global_step": 511411, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0029475688934326, "global_step": 511412, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0467209815979004, "global_step": 511413, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0588059425354004, "global_step": 511414, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.091557264328003, "global_step": 511415, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.070699691772461, "global_step": 511416, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.065908432006836, "global_step": 511417, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9148738384246826, "global_step": 511418, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0824713706970215, "global_step": 511419, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0620667934417725, "global_step": 511420, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0170249938964844, "global_step": 511421, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0460290908813477, "global_step": 511422, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9807429313659668, "global_step": 511423, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.041482925415039, "global_step": 511424, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.014893054962158, "global_step": 511425, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9912751913070679, "global_step": 511426, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0260262489318848, "global_step": 511427, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1068992614746094, "global_step": 511428, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0027923583984375, "global_step": 511429, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0266454219818115, "global_step": 511430, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.107422351837158, "global_step": 511431, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1134822368621826, "global_step": 511432, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1338272094726562, "global_step": 511433, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.037417411804199, "global_step": 511434, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9375971555709839, "global_step": 511435, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0150890350341797, "global_step": 511436, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.045764446258545, "global_step": 511437, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0126302242279053, "global_step": 511438, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9995059967041016, "global_step": 511439, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0151517391204834, "global_step": 511440, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1142210960388184, "global_step": 511441, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.089740514755249, "global_step": 511442, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.153369903564453, "global_step": 511443, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1574392318725586, "global_step": 511444, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1216719150543213, "global_step": 511445, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9611960649490356, "global_step": 511446, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0513975620269775, "global_step": 511447, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1455678939819336, "global_step": 511448, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9551459550857544, "global_step": 511449, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1073620319366455, "global_step": 511450, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0594329833984375, "global_step": 511451, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0434670448303223, "global_step": 511452, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.05843186378479, "global_step": 511453, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1100573539733887, "global_step": 511454, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0995116233825684, "global_step": 511455, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1798219680786133, "global_step": 511456, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.031933307647705, "global_step": 511457, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.039273738861084, "global_step": 511458, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.022416591644287, "global_step": 511459, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1991682052612305, "global_step": 511460, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.982804775238037, "global_step": 511461, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.058779001235962, "global_step": 511462, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0340631008148193, "global_step": 511463, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0765562057495117, "global_step": 511464, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9435341358184814, "global_step": 511465, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0289523601531982, "global_step": 511466, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.034560203552246, "global_step": 511467, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0640740394592285, "global_step": 511468, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.026604413986206, "global_step": 511469, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9932200908660889, "global_step": 511470, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1001176834106445, "global_step": 511471, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0186233520507812, "global_step": 511472, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.005729913711548, "global_step": 511473, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.027653694152832, "global_step": 511474, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.118025779724121, "global_step": 511475, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9705156087875366, "global_step": 511476, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.022531747817993, "global_step": 511477, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0667917728424072, "global_step": 511478, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1207120418548584, "global_step": 511479, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1187098026275635, "global_step": 511480, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0402746200561523, "global_step": 511481, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.01198148727417, "global_step": 511482, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0547752380371094, "global_step": 511483, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.012310743331909, "global_step": 511484, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0622000694274902, "global_step": 511485, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.176823616027832, "global_step": 511486, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.14300799369812, "global_step": 511487, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.067941188812256, "global_step": 511488, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.034127712249756, "global_step": 511489, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0223121643066406, "global_step": 511490, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.021433115005493, "global_step": 511491, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0797877311706543, "global_step": 511492, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.00162410736084, "global_step": 511493, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0435829162597656, "global_step": 511494, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.127354860305786, "global_step": 511495, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0575814247131348, "global_step": 511496, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.040539264678955, "global_step": 511497, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.06152081489563, "global_step": 511498, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.004878044128418, "global_step": 511499, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0283117294311523, "global_step": 511500, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0046043395996094, "global_step": 511501, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.06307053565979, "global_step": 511502, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1034679412841797, "global_step": 511503, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1116433143615723, "global_step": 511504, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.067725896835327, "global_step": 511505, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.040900945663452, "global_step": 511506, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.021594524383545, "global_step": 511507, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0745365619659424, "global_step": 511508, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1718292236328125, "global_step": 511509, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9664534330368042, "global_step": 511510, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.067905902862549, "global_step": 511511, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9591822624206543, "global_step": 511512, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0528934001922607, "global_step": 511513, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.074551582336426, "global_step": 511514, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.978432059288025, "global_step": 511515, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0682435035705566, "global_step": 511516, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9676684141159058, "global_step": 511517, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0828444957733154, "global_step": 511518, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1480369567871094, "global_step": 511519, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.167560338973999, "global_step": 511520, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.179931879043579, "global_step": 511521, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0080740451812744, "global_step": 511522, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.057920455932617, "global_step": 511523, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0288453102111816, "global_step": 511524, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0832247734069824, "global_step": 511525, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9866211414337158, "global_step": 511526, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1264798641204834, "global_step": 511527, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.070237636566162, "global_step": 511528, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.963739275932312, "global_step": 511529, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0948266983032227, "global_step": 511530, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0041608810424805, "global_step": 511531, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0949699878692627, "global_step": 511532, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0810182094573975, "global_step": 511533, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.078667163848877, "global_step": 511534, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0512561798095703, "global_step": 511535, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0707414150238037, "global_step": 511536, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.145995616912842, "global_step": 511537, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0237667560577393, "global_step": 511538, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0744829177856445, "global_step": 511539, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0188992023468018, "global_step": 511540, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.971592903137207, "global_step": 511541, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0393362045288086, "global_step": 511542, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0606260299682617, "global_step": 511543, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.02504825592041, "global_step": 511544, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0221476554870605, "global_step": 511545, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.110185146331787, "global_step": 511546, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0894129276275635, "global_step": 511547, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.926468849182129, "global_step": 511548, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.114368200302124, "global_step": 511549, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0842597484588623, "global_step": 511550, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0209193229675293, "global_step": 511551, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0885848999023438, "global_step": 511552, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9536044597625732, "global_step": 511553, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.02785062789917, "global_step": 511554, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.025787591934204, "global_step": 511555, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.025352716445923, "global_step": 511556, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0358736515045166, "global_step": 511557, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.037689447402954, "global_step": 511558, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0597140789031982, "global_step": 511559, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.017678737640381, "global_step": 511560, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0865423679351807, "global_step": 511561, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0740339756011963, "global_step": 511562, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.039820432662964, "global_step": 511563, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1456079483032227, "global_step": 511564, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1065187454223633, "global_step": 511565, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.011674642562866, "global_step": 511566, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.110631227493286, "global_step": 511567, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9410463571548462, "global_step": 511568, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.085965871810913, "global_step": 511569, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0553624629974365, "global_step": 511570, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0398335456848145, "global_step": 511571, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0559401512145996, "global_step": 511572, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0608105659484863, "global_step": 511573, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.075390577316284, "global_step": 511574, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.008286952972412, "global_step": 511575, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1143813133239746, "global_step": 511576, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9836676120758057, "global_step": 511577, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0335161685943604, "global_step": 511578, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9609508514404297, "global_step": 511579, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0100595951080322, "global_step": 511580, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.043900728225708, "global_step": 511581, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9751230478286743, "global_step": 511582, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1048314571380615, "global_step": 511583, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.113340139389038, "global_step": 511584, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0137112140655518, "global_step": 511585, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0073697566986084, "global_step": 511586, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.065734386444092, "global_step": 511587, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.094148635864258, "global_step": 511588, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.024833917617798, "global_step": 511589, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1237125396728516, "global_step": 511590, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.155583620071411, "global_step": 511591, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9929982423782349, "global_step": 511592, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.039074420928955, "global_step": 511593, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.041274070739746, "global_step": 511594, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.040860652923584, "global_step": 511595, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9981966018676758, "global_step": 511596, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0924577713012695, "global_step": 511597, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0823709964752197, "global_step": 511598, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.066375732421875, "global_step": 511599, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.018277406692505, "global_step": 511600, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.2048020362854004, "global_step": 511601, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.053179979324341, "global_step": 511602, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0342979431152344, "global_step": 511603, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0565500259399414, "global_step": 511604, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0196340084075928, "global_step": 511605, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.067099094390869, "global_step": 511606, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0491433143615723, "global_step": 511607, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.030700922012329, "global_step": 511608, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0970165729522705, "global_step": 511609, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.074185848236084, "global_step": 511610, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0490400791168213, "global_step": 511611, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.069622755050659, "global_step": 511612, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0701024532318115, "global_step": 511613, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.134727954864502, "global_step": 511614, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9902762174606323, "global_step": 511615, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.007725477218628, "global_step": 511616, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.059863328933716, "global_step": 511617, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0156891345977783, "global_step": 511618, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.048095703125, "global_step": 511619, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1355276107788086, "global_step": 511620, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.000091552734375, "global_step": 511621, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1194469928741455, "global_step": 511622, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.001166820526123, "global_step": 511623, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.005490779876709, "global_step": 511624, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1392040252685547, "global_step": 511625, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0922489166259766, "global_step": 511626, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0622174739837646, "global_step": 511627, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9822678565979004, "global_step": 511628, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1364598274230957, "global_step": 511629, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1381163597106934, "global_step": 511630, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.073221206665039, "global_step": 511631, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0365171432495117, "global_step": 511632, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1317062377929688, "global_step": 511633, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0121185779571533, "global_step": 511634, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0216643810272217, "global_step": 511635, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.993395209312439, "global_step": 511636, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.998736023902893, "global_step": 511637, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.979360580444336, "global_step": 511638, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0473973751068115, "global_step": 511639, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9775835275650024, "global_step": 511640, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0449345111846924, "global_step": 511641, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0223312377929688, "global_step": 511642, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0860419273376465, "global_step": 511643, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0068914890289307, "global_step": 511644, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1205060482025146, "global_step": 511645, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.048901081085205, "global_step": 511646, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.954854965209961, "global_step": 511647, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.060032367706299, "global_step": 511648, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0076637268066406, "global_step": 511649, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.024169921875, "global_step": 511650, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1207258701324463, "global_step": 511651, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.041151285171509, "global_step": 511652, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0169503688812256, "global_step": 511653, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0952072143554688, "global_step": 511654, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.104961395263672, "global_step": 511655, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.02866268157959, "global_step": 511656, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.08602237701416, "global_step": 511657, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9951205253601074, "global_step": 511658, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.029853105545044, "global_step": 511659, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.142629861831665, "global_step": 511660, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9834463596343994, "global_step": 511661, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.038670301437378, "global_step": 511662, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0496935844421387, "global_step": 511663, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0669689178466797, "global_step": 511664, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.044569730758667, "global_step": 511665, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0734996795654297, "global_step": 511666, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1313061714172363, "global_step": 511667, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0941667556762695, "global_step": 511668, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0027148723602295, "global_step": 511669, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1007933616638184, "global_step": 511670, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.087113380432129, "global_step": 511671, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.115025281906128, "global_step": 511672, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0639662742614746, "global_step": 511673, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.031977891921997, "global_step": 511674, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1077561378479004, "global_step": 511675, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0331664085388184, "global_step": 511676, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0418524742126465, "global_step": 511677, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0501067638397217, "global_step": 511678, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0371265411376953, "global_step": 511679, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0031237602233887, "global_step": 511680, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0330517292022705, "global_step": 511681, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.045820474624634, "global_step": 511682, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.058384895324707, "global_step": 511683, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.2176685333251953, "global_step": 511684, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9985525608062744, "global_step": 511685, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.076523780822754, "global_step": 511686, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.063742160797119, "global_step": 511687, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.041593551635742, "global_step": 511688, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.106081962585449, "global_step": 511689, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.016946315765381, "global_step": 511690, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0622594356536865, "global_step": 511691, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0896594524383545, "global_step": 511692, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0949461460113525, "global_step": 511693, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0737462043762207, "global_step": 511694, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.024695873260498, "global_step": 511695, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.046703577041626, "global_step": 511696, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0723226070404053, "global_step": 511697, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0929534435272217, "global_step": 511698, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0699329376220703, "global_step": 511699, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1024322509765625, "global_step": 511700, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0678579807281494, "global_step": 511701, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1467125415802, "global_step": 511702, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0170280933380127, "global_step": 511703, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0985896587371826, "global_step": 511704, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.19970440864563, "global_step": 511705, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1454756259918213, "global_step": 511706, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.009528398513794, "global_step": 511707, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.033823251724243, "global_step": 511708, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.107883930206299, "global_step": 511709, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9192575216293335, "global_step": 511710, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.056546688079834, "global_step": 511711, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.103914976119995, "global_step": 511712, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0091984272003174, "global_step": 511713, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9434731006622314, "global_step": 511714, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1489784717559814, "global_step": 511715, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0947062969207764, "global_step": 511716, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0227346420288086, "global_step": 511717, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9764279127120972, "global_step": 511718, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0757765769958496, "global_step": 511719, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.067089319229126, "global_step": 511720, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.080256938934326, "global_step": 511721, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9577537775039673, "global_step": 511722, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0819091796875, "global_step": 511723, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.123565435409546, "global_step": 511724, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0925827026367188, "global_step": 511725, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.052497386932373, "global_step": 511726, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0172042846679688, "global_step": 511727, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1713016033172607, "global_step": 511728, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9619470834732056, "global_step": 511729, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.020691156387329, "global_step": 511730, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.116870164871216, "global_step": 511731, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.11484432220459, "global_step": 511732, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.017714023590088, "global_step": 511733, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1100542545318604, "global_step": 511734, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.081573724746704, "global_step": 511735, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.103257179260254, "global_step": 511736, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.99833083152771, "global_step": 511737, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0648293495178223, "global_step": 511738, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.064453363418579, "global_step": 511739, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0146965980529785, "global_step": 511740, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.012904405593872, "global_step": 511741, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0530591011047363, "global_step": 511742, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9862338304519653, "global_step": 511743, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.076842784881592, "global_step": 511744, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.968437671661377, "global_step": 511745, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.077505588531494, "global_step": 511746, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1730453968048096, "global_step": 511747, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.093857526779175, "global_step": 511748, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9949043989181519, "global_step": 511749, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9862843751907349, "global_step": 511750, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.140232801437378, "global_step": 511751, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.992498755455017, "global_step": 511752, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9943875074386597, "global_step": 511753, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.074016571044922, "global_step": 511754, "epoch": 877, "lr": 5e-05}
{"train_loss": 1.9878013134002686, "global_step": 511755, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0804355144500732, "global_step": 511756, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.088029623031616, "global_step": 511757, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.1178412437438965, "global_step": 511758, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0874853134155273, "global_step": 511759, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0541627407073975, "global_step": 511760, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0457608699798584, "global_step": 511761, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0958664417266846, "global_step": 511762, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0324881076812744, "global_step": 511763, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0488271713256836, "global_step": 511764, "epoch": 877, "lr": 5e-05}
{"train_loss": 2.0637903213500977, "global_step": 511765, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0614709854125977, "global_step": 511766, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.002873182296753, "global_step": 511767, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9783406257629395, "global_step": 511768, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0221946239471436, "global_step": 511769, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.019552230834961, "global_step": 511770, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0238873958587646, "global_step": 511771, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.011535406112671, "global_step": 511772, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0500636100769043, "global_step": 511773, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.047532081604004, "global_step": 511774, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1085140705108643, "global_step": 511775, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.061734199523926, "global_step": 511776, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9640296697616577, "global_step": 511777, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0814545154571533, "global_step": 511778, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.06000018119812, "global_step": 511779, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0308237075805664, "global_step": 511780, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.995578408241272, "global_step": 511781, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9868144989013672, "global_step": 511782, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9602832794189453, "global_step": 511783, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.023127794265747, "global_step": 511784, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0421924591064453, "global_step": 511785, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.024015188217163, "global_step": 511786, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.028540849685669, "global_step": 511787, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9891489744186401, "global_step": 511788, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.062373638153076, "global_step": 511789, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.047579526901245, "global_step": 511790, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0562753677368164, "global_step": 511791, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0880799293518066, "global_step": 511792, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.076190233230591, "global_step": 511793, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.946414828300476, "global_step": 511794, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1130247116088867, "global_step": 511795, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.06121563911438, "global_step": 511796, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9989192485809326, "global_step": 511797, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9994388818740845, "global_step": 511798, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0313007831573486, "global_step": 511799, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9801604747772217, "global_step": 511800, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1471197605133057, "global_step": 511801, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.049257755279541, "global_step": 511802, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.027055263519287, "global_step": 511803, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0110621452331543, "global_step": 511804, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9985237121582031, "global_step": 511805, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.043917417526245, "global_step": 511806, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.078174114227295, "global_step": 511807, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9909083843231201, "global_step": 511808, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.986176609992981, "global_step": 511809, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0470809936523438, "global_step": 511810, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.006234645843506, "global_step": 511811, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0914907455444336, "global_step": 511812, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0348570346832275, "global_step": 511813, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0026981830596924, "global_step": 511814, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0065226554870605, "global_step": 511815, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0487499237060547, "global_step": 511816, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.03432297706604, "global_step": 511817, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0900683403015137, "global_step": 511818, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.024636745452881, "global_step": 511819, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.042041778564453, "global_step": 511820, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0096774101257324, "global_step": 511821, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.035691976547241, "global_step": 511822, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.031581401824951, "global_step": 511823, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1001288890838623, "global_step": 511824, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9821993112564087, "global_step": 511825, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0812273025512695, "global_step": 511826, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0165998935699463, "global_step": 511827, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9755600690841675, "global_step": 511828, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.05300235748291, "global_step": 511829, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.005641222000122, "global_step": 511830, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0176548957824707, "global_step": 511831, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1411547660827637, "global_step": 511832, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.921426773071289, "global_step": 511833, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0322773456573486, "global_step": 511834, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0321381092071533, "global_step": 511835, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.010791301727295, "global_step": 511836, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.058095693588257, "global_step": 511837, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0566656589508057, "global_step": 511838, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.082929849624634, "global_step": 511839, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0346972942352295, "global_step": 511840, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9611217975616455, "global_step": 511841, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.984825849533081, "global_step": 511842, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.076652765274048, "global_step": 511843, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.120457172393799, "global_step": 511844, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0231516361236572, "global_step": 511845, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9948607683181763, "global_step": 511846, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.04376482963562, "global_step": 511847, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0132501125335693, "global_step": 511848, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.987918734550476, "global_step": 511849, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0579450130462646, "global_step": 511850, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.019404172897339, "global_step": 511851, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.024376153945923, "global_step": 511852, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.024425983428955, "global_step": 511853, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0538084506988525, "global_step": 511854, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0818254947662354, "global_step": 511855, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.052027463912964, "global_step": 511856, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.051213026046753, "global_step": 511857, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0089688301086426, "global_step": 511858, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9568146467208862, "global_step": 511859, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0653297901153564, "global_step": 511860, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.076298952102661, "global_step": 511861, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0181493759155273, "global_step": 511862, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.080733299255371, "global_step": 511863, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.120706558227539, "global_step": 511864, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0663182735443115, "global_step": 511865, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9440287351608276, "global_step": 511866, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9680088758468628, "global_step": 511867, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0761051177978516, "global_step": 511868, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0364551544189453, "global_step": 511869, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0427966117858887, "global_step": 511870, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.038585662841797, "global_step": 511871, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1029276847839355, "global_step": 511872, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9997622966766357, "global_step": 511873, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9623688459396362, "global_step": 511874, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0465078353881836, "global_step": 511875, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.006770372390747, "global_step": 511876, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.022646188735962, "global_step": 511877, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.094447135925293, "global_step": 511878, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0200979709625244, "global_step": 511879, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9706584215164185, "global_step": 511880, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.942101240158081, "global_step": 511881, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0457422733306885, "global_step": 511882, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0982561111450195, "global_step": 511883, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0849413871765137, "global_step": 511884, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0376691818237305, "global_step": 511885, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0650196075439453, "global_step": 511886, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.058211088180542, "global_step": 511887, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1057517528533936, "global_step": 511888, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9626177549362183, "global_step": 511889, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.08937406539917, "global_step": 511890, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0120418071746826, "global_step": 511891, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0414185523986816, "global_step": 511892, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9956904649734497, "global_step": 511893, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.028632640838623, "global_step": 511894, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.036569118499756, "global_step": 511895, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0315303802490234, "global_step": 511896, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0116336345672607, "global_step": 511897, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.029813289642334, "global_step": 511898, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0306038856506348, "global_step": 511899, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1158792972564697, "global_step": 511900, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0610404014587402, "global_step": 511901, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.032667875289917, "global_step": 511902, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9153082370758057, "global_step": 511903, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.053753137588501, "global_step": 511904, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9888092279434204, "global_step": 511905, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0405213832855225, "global_step": 511906, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.040302276611328, "global_step": 511907, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0116465091705322, "global_step": 511908, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0625369548797607, "global_step": 511909, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.8961892127990723, "global_step": 511910, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9717456102371216, "global_step": 511911, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.026608467102051, "global_step": 511912, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9795863628387451, "global_step": 511913, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.004606008529663, "global_step": 511914, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.030945301055908, "global_step": 511915, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0699994564056396, "global_step": 511916, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1336660385131836, "global_step": 511917, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1495676040649414, "global_step": 511918, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0071189403533936, "global_step": 511919, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.02475643157959, "global_step": 511920, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0412464141845703, "global_step": 511921, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.046562910079956, "global_step": 511922, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0739798545837402, "global_step": 511923, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0646674633026123, "global_step": 511924, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0550811290740967, "global_step": 511925, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9810880422592163, "global_step": 511926, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0567398071289062, "global_step": 511927, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0226738452911377, "global_step": 511928, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9914661645889282, "global_step": 511929, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.006056308746338, "global_step": 511930, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0100579261779785, "global_step": 511931, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0944511890411377, "global_step": 511932, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0493927001953125, "global_step": 511933, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0801196098327637, "global_step": 511934, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1001439094543457, "global_step": 511935, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.988092064857483, "global_step": 511936, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.012375831604004, "global_step": 511937, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.125276565551758, "global_step": 511938, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0538597106933594, "global_step": 511939, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0133142471313477, "global_step": 511940, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0758607387542725, "global_step": 511941, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9470493793487549, "global_step": 511942, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.074315071105957, "global_step": 511943, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9679794311523438, "global_step": 511944, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.997092843055725, "global_step": 511945, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0439705848693848, "global_step": 511946, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0532386302948, "global_step": 511947, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9359543323516846, "global_step": 511948, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.941506266593933, "global_step": 511949, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.034343957901001, "global_step": 511950, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0373592376708984, "global_step": 511951, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.011864423751831, "global_step": 511952, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.061732530593872, "global_step": 511953, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.061699867248535, "global_step": 511954, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0309598445892334, "global_step": 511955, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1093437671661377, "global_step": 511956, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.998814582824707, "global_step": 511957, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0379416942596436, "global_step": 511958, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.019824981689453, "global_step": 511959, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.037792682647705, "global_step": 511960, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.040698528289795, "global_step": 511961, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.040050506591797, "global_step": 511962, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0627059936523438, "global_step": 511963, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0290160179138184, "global_step": 511964, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9980041980743408, "global_step": 511965, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0592052936553955, "global_step": 511966, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9987646341323853, "global_step": 511967, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.042522668838501, "global_step": 511968, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0223865509033203, "global_step": 511969, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.12257981300354, "global_step": 511970, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.071636199951172, "global_step": 511971, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0887982845306396, "global_step": 511972, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0544655323028564, "global_step": 511973, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9875516891479492, "global_step": 511974, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0420589447021484, "global_step": 511975, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0326199531555176, "global_step": 511976, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.043412685394287, "global_step": 511977, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.051309108734131, "global_step": 511978, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0553245544433594, "global_step": 511979, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9345197677612305, "global_step": 511980, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.034571409225464, "global_step": 511981, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.005131721496582, "global_step": 511982, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.06740665435791, "global_step": 511983, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.066254138946533, "global_step": 511984, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.087235450744629, "global_step": 511985, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9832789897918701, "global_step": 511986, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.040260076522827, "global_step": 511987, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0151872634887695, "global_step": 511988, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1313891410827637, "global_step": 511989, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.00813889503479, "global_step": 511990, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.013400077819824, "global_step": 511991, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9653174877166748, "global_step": 511992, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1095268726348877, "global_step": 511993, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.090034246444702, "global_step": 511994, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9405285120010376, "global_step": 511995, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0326104164123535, "global_step": 511996, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9768604040145874, "global_step": 511997, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0331547260284424, "global_step": 511998, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0035529136657715, "global_step": 511999, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.077920436859131, "global_step": 512000, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.977405071258545, "global_step": 512001, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0646750926971436, "global_step": 512002, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.027022361755371, "global_step": 512003, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.063228130340576, "global_step": 512004, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.037240505218506, "global_step": 512005, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.056612253189087, "global_step": 512006, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.056227684020996, "global_step": 512007, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.036045551300049, "global_step": 512008, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.05285906791687, "global_step": 512009, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.031160831451416, "global_step": 512010, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0624160766601562, "global_step": 512011, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1155495643615723, "global_step": 512012, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.990869164466858, "global_step": 512013, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.084848403930664, "global_step": 512014, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.075603485107422, "global_step": 512015, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9692018032073975, "global_step": 512016, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0699548721313477, "global_step": 512017, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0791141986846924, "global_step": 512018, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.056701183319092, "global_step": 512019, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0629420280456543, "global_step": 512020, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9677404165267944, "global_step": 512021, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0047929286956787, "global_step": 512022, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0444858074188232, "global_step": 512023, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0224685668945312, "global_step": 512024, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.096599817276001, "global_step": 512025, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.012110471725464, "global_step": 512026, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9922837018966675, "global_step": 512027, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0628209114074707, "global_step": 512028, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.045771598815918, "global_step": 512029, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0257389545440674, "global_step": 512030, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.037659168243408, "global_step": 512031, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0309040546417236, "global_step": 512032, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9434521198272705, "global_step": 512033, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.070640802383423, "global_step": 512034, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0917375087738037, "global_step": 512035, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9707826375961304, "global_step": 512036, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9930399656295776, "global_step": 512037, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0355234146118164, "global_step": 512038, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0011885166168213, "global_step": 512039, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.071197032928467, "global_step": 512040, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.009108781814575, "global_step": 512041, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.068537473678589, "global_step": 512042, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9445486068725586, "global_step": 512043, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.040055751800537, "global_step": 512044, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0414955615997314, "global_step": 512045, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1224546432495117, "global_step": 512046, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0554897785186768, "global_step": 512047, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.091017484664917, "global_step": 512048, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0495710372924805, "global_step": 512049, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.00331711769104, "global_step": 512050, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.078186273574829, "global_step": 512051, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.143101930618286, "global_step": 512052, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9896079301834106, "global_step": 512053, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0121665000915527, "global_step": 512054, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0529208183288574, "global_step": 512055, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.051447629928589, "global_step": 512056, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1256442070007324, "global_step": 512057, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.014643669128418, "global_step": 512058, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0909550189971924, "global_step": 512059, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0271682739257812, "global_step": 512060, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1166977882385254, "global_step": 512061, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.013349771499634, "global_step": 512062, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.103543758392334, "global_step": 512063, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0266716480255127, "global_step": 512064, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0374233722686768, "global_step": 512065, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1199376583099365, "global_step": 512066, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9885220527648926, "global_step": 512067, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0399389266967773, "global_step": 512068, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0130069255828857, "global_step": 512069, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9795324802398682, "global_step": 512070, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0387842655181885, "global_step": 512071, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9885910749435425, "global_step": 512072, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.993719458580017, "global_step": 512073, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0541629791259766, "global_step": 512074, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9212678670883179, "global_step": 512075, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9963024854660034, "global_step": 512076, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1251330375671387, "global_step": 512077, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0948641300201416, "global_step": 512078, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.060706615447998, "global_step": 512079, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.018705368041992, "global_step": 512080, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.002255439758301, "global_step": 512081, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9953572750091553, "global_step": 512082, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.977715015411377, "global_step": 512083, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.04364275932312, "global_step": 512084, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0798864364624023, "global_step": 512085, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0355823040008545, "global_step": 512086, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0259017944335938, "global_step": 512087, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1122548580169678, "global_step": 512088, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9613176584243774, "global_step": 512089, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0906968116760254, "global_step": 512090, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0948774814605713, "global_step": 512091, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.060608148574829, "global_step": 512092, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.085022449493408, "global_step": 512093, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9596115350723267, "global_step": 512094, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9918378591537476, "global_step": 512095, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.124173879623413, "global_step": 512096, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0866241455078125, "global_step": 512097, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0600945949554443, "global_step": 512098, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.073476552963257, "global_step": 512099, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.101926803588867, "global_step": 512100, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0714402198791504, "global_step": 512101, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0550973415374756, "global_step": 512102, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0544979572296143, "global_step": 512103, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.118159055709839, "global_step": 512104, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9747002124786377, "global_step": 512105, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.046370267868042, "global_step": 512106, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.979396939277649, "global_step": 512107, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.088233232498169, "global_step": 512108, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.192995071411133, "global_step": 512109, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0364339351654053, "global_step": 512110, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.065973997116089, "global_step": 512111, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.057570219039917, "global_step": 512112, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.024292230606079, "global_step": 512113, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.08223819732666, "global_step": 512114, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0261006355285645, "global_step": 512115, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.034501791000366, "global_step": 512116, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.145703077316284, "global_step": 512117, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9915467500686646, "global_step": 512118, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0352654457092285, "global_step": 512119, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0401227474212646, "global_step": 512120, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9560807943344116, "global_step": 512121, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0127370357513428, "global_step": 512122, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9924664497375488, "global_step": 512123, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1225099563598633, "global_step": 512124, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1374552249908447, "global_step": 512125, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.079143524169922, "global_step": 512126, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.976046085357666, "global_step": 512127, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.126824140548706, "global_step": 512128, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.095630407333374, "global_step": 512129, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0147488117218018, "global_step": 512130, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.056978464126587, "global_step": 512131, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.027958631515503, "global_step": 512132, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0870275497436523, "global_step": 512133, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.029996156692505, "global_step": 512134, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.098269462585449, "global_step": 512135, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.128044605255127, "global_step": 512136, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.003735065460205, "global_step": 512137, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.054776191711426, "global_step": 512138, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.062035322189331, "global_step": 512139, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0737552642822266, "global_step": 512140, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.020897388458252, "global_step": 512141, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.121687650680542, "global_step": 512142, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0302658081054688, "global_step": 512143, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0287559032440186, "global_step": 512144, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9696714878082275, "global_step": 512145, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.06549334526062, "global_step": 512146, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.070516586303711, "global_step": 512147, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0779428482055664, "global_step": 512148, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.037069082260132, "global_step": 512149, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0360147953033447, "global_step": 512150, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.089721202850342, "global_step": 512151, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.063368320465088, "global_step": 512152, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.998194932937622, "global_step": 512153, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0677976608276367, "global_step": 512154, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.068769931793213, "global_step": 512155, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.016223907470703, "global_step": 512156, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0861294269561768, "global_step": 512157, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0191192626953125, "global_step": 512158, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.083488702774048, "global_step": 512159, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0765531063079834, "global_step": 512160, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0167720317840576, "global_step": 512161, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1112661361694336, "global_step": 512162, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.025423288345337, "global_step": 512163, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0666017532348633, "global_step": 512164, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.095306396484375, "global_step": 512165, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.058697462081909, "global_step": 512166, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0594143867492676, "global_step": 512167, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.020937919616699, "global_step": 512168, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.986246943473816, "global_step": 512169, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1005911827087402, "global_step": 512170, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0777342319488525, "global_step": 512171, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0046544075012207, "global_step": 512172, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0247702598571777, "global_step": 512173, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0412769317626953, "global_step": 512174, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0582170486450195, "global_step": 512175, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.052736759185791, "global_step": 512176, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.062653064727783, "global_step": 512177, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.019608974456787, "global_step": 512178, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0644519329071045, "global_step": 512179, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0356943607330322, "global_step": 512180, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0678107738494873, "global_step": 512181, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0424671173095703, "global_step": 512182, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1535112857818604, "global_step": 512183, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1598291397094727, "global_step": 512184, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0733540058135986, "global_step": 512185, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.018995761871338, "global_step": 512186, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.030864953994751, "global_step": 512187, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.098510980606079, "global_step": 512188, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.047628402709961, "global_step": 512189, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.964461326599121, "global_step": 512190, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9988712072372437, "global_step": 512191, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1048526763916016, "global_step": 512192, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0504355430603027, "global_step": 512193, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.086073637008667, "global_step": 512194, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.046022891998291, "global_step": 512195, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0316216945648193, "global_step": 512196, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0459258556365967, "global_step": 512197, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.101515293121338, "global_step": 512198, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.024561643600464, "global_step": 512199, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9860258102416992, "global_step": 512200, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.11617374420166, "global_step": 512201, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.046983242034912, "global_step": 512202, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1221742630004883, "global_step": 512203, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.096078872680664, "global_step": 512204, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0963873863220215, "global_step": 512205, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.101810932159424, "global_step": 512206, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0855462551116943, "global_step": 512207, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.028348684310913, "global_step": 512208, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9948856830596924, "global_step": 512209, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.080753803253174, "global_step": 512210, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0915753841400146, "global_step": 512211, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.036278247833252, "global_step": 512212, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0867433547973633, "global_step": 512213, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.065894603729248, "global_step": 512214, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1289138793945312, "global_step": 512215, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1420795917510986, "global_step": 512216, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.035038709640503, "global_step": 512217, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.103626251220703, "global_step": 512218, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1053271293640137, "global_step": 512219, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0818710327148438, "global_step": 512220, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9424633979797363, "global_step": 512221, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0791261196136475, "global_step": 512222, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9943125247955322, "global_step": 512223, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9787384271621704, "global_step": 512224, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0074360370635986, "global_step": 512225, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9794243574142456, "global_step": 512226, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0830512046813965, "global_step": 512227, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1339101791381836, "global_step": 512228, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.007664918899536, "global_step": 512229, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0956666469573975, "global_step": 512230, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0725035667419434, "global_step": 512231, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0357375144958496, "global_step": 512232, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9925872087478638, "global_step": 512233, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0721077919006348, "global_step": 512234, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.154238224029541, "global_step": 512235, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1177077293395996, "global_step": 512236, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1048548221588135, "global_step": 512237, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0769472122192383, "global_step": 512238, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1172475814819336, "global_step": 512239, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.068756580352783, "global_step": 512240, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0860393047332764, "global_step": 512241, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0675833225250244, "global_step": 512242, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.083878755569458, "global_step": 512243, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9959434270858765, "global_step": 512244, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.06052827835083, "global_step": 512245, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0032496452331543, "global_step": 512246, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0387275218963623, "global_step": 512247, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0944430828094482, "global_step": 512248, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9997403621673584, "global_step": 512249, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.062556266784668, "global_step": 512250, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.060375690460205, "global_step": 512251, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0455265045166016, "global_step": 512252, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9696259498596191, "global_step": 512253, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0315611362457275, "global_step": 512254, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0210468769073486, "global_step": 512255, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9575592279434204, "global_step": 512256, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0607051849365234, "global_step": 512257, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0493760108947754, "global_step": 512258, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.019277572631836, "global_step": 512259, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0293309688568115, "global_step": 512260, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9695782661437988, "global_step": 512261, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.094398021697998, "global_step": 512262, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1398158073425293, "global_step": 512263, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0486059188842773, "global_step": 512264, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.059058427810669, "global_step": 512265, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0900285243988037, "global_step": 512266, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0642688274383545, "global_step": 512267, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.094902753829956, "global_step": 512268, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9833283424377441, "global_step": 512269, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9622747898101807, "global_step": 512270, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9819514751434326, "global_step": 512271, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0859789848327637, "global_step": 512272, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0781545639038086, "global_step": 512273, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0098299980163574, "global_step": 512274, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.065711736679077, "global_step": 512275, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.091524362564087, "global_step": 512276, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1423497200012207, "global_step": 512277, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9612911939620972, "global_step": 512278, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0826497077941895, "global_step": 512279, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9475592374801636, "global_step": 512280, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.072313070297241, "global_step": 512281, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9916049242019653, "global_step": 512282, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.024407386779785, "global_step": 512283, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0772643089294434, "global_step": 512284, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1787216663360596, "global_step": 512285, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9932761192321777, "global_step": 512286, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.156271457672119, "global_step": 512287, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.085425615310669, "global_step": 512288, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0548899173736572, "global_step": 512289, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0155222415924072, "global_step": 512290, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0346908569335938, "global_step": 512291, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0489277839660645, "global_step": 512292, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.120927572250366, "global_step": 512293, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1233508586883545, "global_step": 512294, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.098832607269287, "global_step": 512295, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.034621000289917, "global_step": 512296, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0350635051727295, "global_step": 512297, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0124778747558594, "global_step": 512298, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.00227952003479, "global_step": 512299, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9927914142608643, "global_step": 512300, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0077438354492188, "global_step": 512301, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9769339561462402, "global_step": 512302, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1146750450134277, "global_step": 512303, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.055095911026001, "global_step": 512304, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0057718753814697, "global_step": 512305, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9518123865127563, "global_step": 512306, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.044038772583008, "global_step": 512307, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.039769411087036, "global_step": 512308, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9930402040481567, "global_step": 512309, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1402876377105713, "global_step": 512310, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0197484493255615, "global_step": 512311, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.001577854156494, "global_step": 512312, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.06978702545166, "global_step": 512313, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.019014596939087, "global_step": 512314, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0766494274139404, "global_step": 512315, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.043605089187622, "global_step": 512316, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.020583152770996, "global_step": 512317, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0682945251464844, "global_step": 512318, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9355719089508057, "global_step": 512319, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0640740394592285, "global_step": 512320, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0583815574645996, "global_step": 512321, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0336060523986816, "global_step": 512322, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.040239095687866, "global_step": 512323, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.03471040725708, "global_step": 512324, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.055697441101074, "global_step": 512325, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.005460500717163, "global_step": 512326, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.039200782775879, "global_step": 512327, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0860095024108887, "global_step": 512328, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.09889554977417, "global_step": 512329, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1408133506774902, "global_step": 512330, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0800797939300537, "global_step": 512331, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.007103681564331, "global_step": 512332, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9986897706985474, "global_step": 512333, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0628604888916016, "global_step": 512334, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0717592239379883, "global_step": 512335, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0201544761657715, "global_step": 512336, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.075768232345581, "global_step": 512337, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0828635692596436, "global_step": 512338, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0752084255218506, "global_step": 512339, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0852184295654297, "global_step": 512340, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1163876056671143, "global_step": 512341, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0360400676727295, "global_step": 512342, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.097642421722412, "global_step": 512343, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9930658340454102, "global_step": 512344, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0032832622528076, "global_step": 512345, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0117366313934326, "global_step": 512346, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1209487915039062, "global_step": 512347, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0246477127075195, "global_step": 512348, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.114478826522827, "global_step": 512349, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.036313056945801, "global_step": 512350, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0220015048980713, "global_step": 512351, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.031348705291748, "global_step": 512352, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9860819578170776, "global_step": 512353, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.071195363998413, "global_step": 512354, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.020017385482788, "global_step": 512355, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9683411121368408, "global_step": 512356, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0363566875457764, "global_step": 512357, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0213944911956787, "global_step": 512358, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0435636043548584, "global_step": 512359, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0205631256103516, "global_step": 512360, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1408185958862305, "global_step": 512361, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0162160396575928, "global_step": 512362, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0314648151397705, "global_step": 512363, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.070552110671997, "global_step": 512364, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.963935375213623, "global_step": 512365, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.088047504425049, "global_step": 512366, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.137320041656494, "global_step": 512367, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0973973274230957, "global_step": 512368, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0340194702148438, "global_step": 512369, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.082517385482788, "global_step": 512370, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1337900161743164, "global_step": 512371, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.977331519126892, "global_step": 512372, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.017216444015503, "global_step": 512373, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0183844566345215, "global_step": 512374, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0805275440216064, "global_step": 512375, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0209219455718994, "global_step": 512376, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.021908760070801, "global_step": 512377, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0996360778808594, "global_step": 512378, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0193097591400146, "global_step": 512379, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0575497150421143, "global_step": 512380, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0286176204681396, "global_step": 512381, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9532746076583862, "global_step": 512382, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0633046627044678, "global_step": 512383, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0775275230407715, "global_step": 512384, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.072199583053589, "global_step": 512385, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.95883047580719, "global_step": 512386, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0715696811676025, "global_step": 512387, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0599498748779297, "global_step": 512388, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9885635375976562, "global_step": 512389, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1151890754699707, "global_step": 512390, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1313767433166504, "global_step": 512391, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1689236164093018, "global_step": 512392, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.040598154067993, "global_step": 512393, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0061240196228027, "global_step": 512394, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9204989671707153, "global_step": 512395, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.152623176574707, "global_step": 512396, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0986440181732178, "global_step": 512397, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.019624948501587, "global_step": 512398, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.033606767654419, "global_step": 512399, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9767208099365234, "global_step": 512400, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0343868732452393, "global_step": 512401, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0060935020446777, "global_step": 512402, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1203954219818115, "global_step": 512403, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0814778804779053, "global_step": 512404, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0505263805389404, "global_step": 512405, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1391441822052, "global_step": 512406, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0789217948913574, "global_step": 512407, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0441629886627197, "global_step": 512408, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.006283760070801, "global_step": 512409, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0977070331573486, "global_step": 512410, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.116021156311035, "global_step": 512411, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.120025873184204, "global_step": 512412, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0314524173736572, "global_step": 512413, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1702442169189453, "global_step": 512414, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9596728086471558, "global_step": 512415, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.094444990158081, "global_step": 512416, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.02524733543396, "global_step": 512417, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.072746992111206, "global_step": 512418, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9604341983795166, "global_step": 512419, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.017216444015503, "global_step": 512420, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0896003246307373, "global_step": 512421, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1456379890441895, "global_step": 512422, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0093624591827393, "global_step": 512423, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9629756212234497, "global_step": 512424, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0018417835235596, "global_step": 512425, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0892255306243896, "global_step": 512426, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1692144870758057, "global_step": 512427, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.010000467300415, "global_step": 512428, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1245882511138916, "global_step": 512429, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0326950550079346, "global_step": 512430, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9964230060577393, "global_step": 512431, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.018622636795044, "global_step": 512432, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1459665298461914, "global_step": 512433, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.045793294906616, "global_step": 512434, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0725395679473877, "global_step": 512435, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0311219692230225, "global_step": 512436, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.048671007156372, "global_step": 512437, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.009897470474243, "global_step": 512438, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0071592330932617, "global_step": 512439, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0766708850860596, "global_step": 512440, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.018739938735962, "global_step": 512441, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0819034576416016, "global_step": 512442, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1081626415252686, "global_step": 512443, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.090132236480713, "global_step": 512444, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0013325214385986, "global_step": 512445, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1586456298828125, "global_step": 512446, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9969221353530884, "global_step": 512447, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.03726863861084, "global_step": 512448, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1028852462768555, "global_step": 512449, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.932383418083191, "global_step": 512450, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9629020690917969, "global_step": 512451, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9664748907089233, "global_step": 512452, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0449066162109375, "global_step": 512453, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0848443508148193, "global_step": 512454, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0078952312469482, "global_step": 512455, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.112471580505371, "global_step": 512456, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.081681489944458, "global_step": 512457, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0398054122924805, "global_step": 512458, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.986868977546692, "global_step": 512459, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.068716287612915, "global_step": 512460, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0121541023254395, "global_step": 512461, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.057992458343506, "global_step": 512462, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0260515213012695, "global_step": 512463, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0770657062530518, "global_step": 512464, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.979961633682251, "global_step": 512465, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0895116329193115, "global_step": 512466, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0745224952697754, "global_step": 512467, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0424978733062744, "global_step": 512468, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.065838575363159, "global_step": 512469, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.053347110748291, "global_step": 512470, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.017453193664551, "global_step": 512471, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9708449840545654, "global_step": 512472, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1733365058898926, "global_step": 512473, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9611997604370117, "global_step": 512474, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.006547451019287, "global_step": 512475, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.043457508087158, "global_step": 512476, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.136035680770874, "global_step": 512477, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9903134107589722, "global_step": 512478, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0298593044281006, "global_step": 512479, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9942651987075806, "global_step": 512480, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.053985118865967, "global_step": 512481, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.067793607711792, "global_step": 512482, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.043642997741699, "global_step": 512483, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.010878086090088, "global_step": 512484, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0741212368011475, "global_step": 512485, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0778648853302, "global_step": 512486, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.081871509552002, "global_step": 512487, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.055371046066284, "global_step": 512488, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9920202493667603, "global_step": 512489, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.06805419921875, "global_step": 512490, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.014791488647461, "global_step": 512491, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.004287004470825, "global_step": 512492, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.041592597961426, "global_step": 512493, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1277921199798584, "global_step": 512494, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0217936038970947, "global_step": 512495, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0580832958221436, "global_step": 512496, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0943491458892822, "global_step": 512497, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0949013233184814, "global_step": 512498, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.083493232727051, "global_step": 512499, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0735461711883545, "global_step": 512500, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.055222272872925, "global_step": 512501, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9797921180725098, "global_step": 512502, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0218300819396973, "global_step": 512503, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.056544303894043, "global_step": 512504, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0559351444244385, "global_step": 512505, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0121712684631348, "global_step": 512506, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0639359951019287, "global_step": 512507, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0562024116516113, "global_step": 512508, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0671377182006836, "global_step": 512509, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0777604579925537, "global_step": 512510, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.031991958618164, "global_step": 512511, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0439441204071045, "global_step": 512512, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.957342505455017, "global_step": 512513, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9430506229400635, "global_step": 512514, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0385684967041016, "global_step": 512515, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.055274724960327, "global_step": 512516, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.065204381942749, "global_step": 512517, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.082751512527466, "global_step": 512518, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.101155996322632, "global_step": 512519, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.071683168411255, "global_step": 512520, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.040288209915161, "global_step": 512521, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.101250648498535, "global_step": 512522, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0281264781951904, "global_step": 512523, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.027384042739868, "global_step": 512524, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.133599281311035, "global_step": 512525, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.924184799194336, "global_step": 512526, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0575311183929443, "global_step": 512527, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.050260543823242, "global_step": 512528, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0021920204162598, "global_step": 512529, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.090071201324463, "global_step": 512530, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.042741060256958, "global_step": 512531, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1095693111419678, "global_step": 512532, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.998234748840332, "global_step": 512533, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9723821878433228, "global_step": 512534, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.016246795654297, "global_step": 512535, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.025200843811035, "global_step": 512536, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.071661949157715, "global_step": 512537, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9732975959777832, "global_step": 512538, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0851798057556152, "global_step": 512539, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9987595081329346, "global_step": 512540, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0733115673065186, "global_step": 512541, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9732277393341064, "global_step": 512542, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0166897773742676, "global_step": 512543, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.066145420074463, "global_step": 512544, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9917807579040527, "global_step": 512545, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0282061100006104, "global_step": 512546, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.034287929534912, "global_step": 512547, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.063969850540161, "global_step": 512548, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0298867225646973, "global_step": 512549, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0925252437591553, "global_step": 512550, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1698551177978516, "global_step": 512551, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.045626401901245, "global_step": 512552, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.084259510040283, "global_step": 512553, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0468668937683105, "global_step": 512554, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.931218147277832, "global_step": 512555, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.110363721847534, "global_step": 512556, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.069788932800293, "global_step": 512557, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.095651149749756, "global_step": 512558, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0126945972442627, "global_step": 512559, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.10638689994812, "global_step": 512560, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9999961853027344, "global_step": 512561, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9663165807724, "global_step": 512562, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.095215320587158, "global_step": 512563, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.980054259300232, "global_step": 512564, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.046428680419922, "global_step": 512565, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0148274898529053, "global_step": 512566, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0044941902160645, "global_step": 512567, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0165786743164062, "global_step": 512568, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.025435447692871, "global_step": 512569, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0369200706481934, "global_step": 512570, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0653820037841797, "global_step": 512571, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0610275268554688, "global_step": 512572, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0841681957244873, "global_step": 512573, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1147549152374268, "global_step": 512574, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0212900638580322, "global_step": 512575, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0386078357696533, "global_step": 512576, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9669418334960938, "global_step": 512577, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0605106353759766, "global_step": 512578, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0838541984558105, "global_step": 512579, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0595951080322266, "global_step": 512580, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1231069564819336, "global_step": 512581, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.068540096282959, "global_step": 512582, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0562551021575928, "global_step": 512583, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.113787889480591, "global_step": 512584, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0584590435028076, "global_step": 512585, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.989626407623291, "global_step": 512586, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.131866693496704, "global_step": 512587, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.05167555809021, "global_step": 512588, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.999389886856079, "global_step": 512589, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0764424800872803, "global_step": 512590, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.051419734954834, "global_step": 512591, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0710668563842773, "global_step": 512592, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.04599928855896, "global_step": 512593, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.012943983078003, "global_step": 512594, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.058506965637207, "global_step": 512595, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1565394401550293, "global_step": 512596, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0689659118652344, "global_step": 512597, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9193300008773804, "global_step": 512598, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0128748416900635, "global_step": 512599, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9883754253387451, "global_step": 512600, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.011549949645996, "global_step": 512601, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0171713829040527, "global_step": 512602, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.015577554702759, "global_step": 512603, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.081716775894165, "global_step": 512604, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1022417545318604, "global_step": 512605, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.008702039718628, "global_step": 512606, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.112475633621216, "global_step": 512607, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0679993629455566, "global_step": 512608, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0006330013275146, "global_step": 512609, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.069206714630127, "global_step": 512610, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.055327892303467, "global_step": 512611, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.016360282897949, "global_step": 512612, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1009559631347656, "global_step": 512613, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.09966778755188, "global_step": 512614, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1871776580810547, "global_step": 512615, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.068629026412964, "global_step": 512616, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.162914514541626, "global_step": 512617, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.050285577774048, "global_step": 512618, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1154887676239014, "global_step": 512619, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0283889770507812, "global_step": 512620, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.022397994995117, "global_step": 512621, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0244646072387695, "global_step": 512622, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.030099391937256, "global_step": 512623, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.031130790710449, "global_step": 512624, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1167211532592773, "global_step": 512625, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0785155296325684, "global_step": 512626, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.164761543273926, "global_step": 512627, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9632062911987305, "global_step": 512628, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0658838748931885, "global_step": 512629, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0984878540039062, "global_step": 512630, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9638525247573853, "global_step": 512631, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0815930366516113, "global_step": 512632, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.014617681503296, "global_step": 512633, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0368690490722656, "global_step": 512634, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0419795513153076, "global_step": 512635, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.021698474884033, "global_step": 512636, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.150413751602173, "global_step": 512637, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.028045654296875, "global_step": 512638, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.119342803955078, "global_step": 512639, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9897483587265015, "global_step": 512640, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0456604957580566, "global_step": 512641, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.100369453430176, "global_step": 512642, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0559515953063965, "global_step": 512643, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0597541332244873, "global_step": 512644, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1004791259765625, "global_step": 512645, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0984342098236084, "global_step": 512646, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.97866952419281, "global_step": 512647, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0339503288269043, "global_step": 512648, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.134882926940918, "global_step": 512649, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9954525232315063, "global_step": 512650, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9912171363830566, "global_step": 512651, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0783238410949707, "global_step": 512652, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0218048095703125, "global_step": 512653, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.063610315322876, "global_step": 512654, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.042539119720459, "global_step": 512655, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.042231559753418, "global_step": 512656, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0767195224761963, "global_step": 512657, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0219016075134277, "global_step": 512658, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.009579658508301, "global_step": 512659, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.035336494445801, "global_step": 512660, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.111602783203125, "global_step": 512661, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9955888986587524, "global_step": 512662, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9997977018356323, "global_step": 512663, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.11956524848938, "global_step": 512664, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0680148601531982, "global_step": 512665, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0842833518981934, "global_step": 512666, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0420594215393066, "global_step": 512667, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.141619920730591, "global_step": 512668, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9800074100494385, "global_step": 512669, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0094380378723145, "global_step": 512670, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1485111713409424, "global_step": 512671, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.046459674835205, "global_step": 512672, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.049025058746338, "global_step": 512673, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0661890506744385, "global_step": 512674, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0749642848968506, "global_step": 512675, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.060896635055542, "global_step": 512676, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.023030996322632, "global_step": 512677, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0716145038604736, "global_step": 512678, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1138086318969727, "global_step": 512679, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1738176345825195, "global_step": 512680, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0391347408294678, "global_step": 512681, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0545387268066406, "global_step": 512682, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.043874502182007, "global_step": 512683, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9845731258392334, "global_step": 512684, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9526314735412598, "global_step": 512685, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.09035587310791, "global_step": 512686, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0865588188171387, "global_step": 512687, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.094773054122925, "global_step": 512688, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1179771423339844, "global_step": 512689, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0536813735961914, "global_step": 512690, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.054438829421997, "global_step": 512691, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0926451683044434, "global_step": 512692, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0827250480651855, "global_step": 512693, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.043386936187744, "global_step": 512694, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.081211805343628, "global_step": 512695, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9723162651062012, "global_step": 512696, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0190272331237793, "global_step": 512697, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.116905450820923, "global_step": 512698, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0348260402679443, "global_step": 512699, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.004896402359009, "global_step": 512700, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.007282018661499, "global_step": 512701, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0237784385681152, "global_step": 512702, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0061728954315186, "global_step": 512703, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.036114454269409, "global_step": 512704, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.027662754058838, "global_step": 512705, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1527671813964844, "global_step": 512706, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.002730131149292, "global_step": 512707, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.936902642250061, "global_step": 512708, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0102360248565674, "global_step": 512709, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0665886402130127, "global_step": 512710, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0328874588012695, "global_step": 512711, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.09954833984375, "global_step": 512712, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.122838258743286, "global_step": 512713, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9818768501281738, "global_step": 512714, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.04498291015625, "global_step": 512715, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.000885248184204, "global_step": 512716, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0789504051208496, "global_step": 512717, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0031793117523193, "global_step": 512718, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.131988286972046, "global_step": 512719, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.036375045776367, "global_step": 512720, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.010694742202759, "global_step": 512721, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.044379949569702, "global_step": 512722, "epoch": 878, "lr": 5e-05}
{"train_loss": 1.9636549949645996, "global_step": 512723, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0106470584869385, "global_step": 512724, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.142578125, "global_step": 512725, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.046112537384033, "global_step": 512726, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.038156032562256, "global_step": 512727, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0715079307556152, "global_step": 512728, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.054804563522339, "global_step": 512729, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.0775108337402344, "global_step": 512730, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.034212827682495, "global_step": 512731, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.1139373779296875, "global_step": 512732, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.046097755432129, "global_step": 512733, "epoch": 878, "lr": 5e-05}
{"train_loss": 2.102050304412842, "global_step": 512734, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0818841457366943, "global_step": 512735, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0024874210357666, "global_step": 512736, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0470147132873535, "global_step": 512737, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.052520990371704, "global_step": 512738, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.8929322957992554, "global_step": 512739, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.088406801223755, "global_step": 512740, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0393199920654297, "global_step": 512741, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0715060234069824, "global_step": 512742, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.077989101409912, "global_step": 512743, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0512502193450928, "global_step": 512744, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.039930820465088, "global_step": 512745, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.094636917114258, "global_step": 512746, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.047161817550659, "global_step": 512747, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9828447103500366, "global_step": 512748, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.115896224975586, "global_step": 512749, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9512419700622559, "global_step": 512750, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0190675258636475, "global_step": 512751, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.010524034500122, "global_step": 512752, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.037095546722412, "global_step": 512753, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0550730228424072, "global_step": 512754, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0193097591400146, "global_step": 512755, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0954110622406006, "global_step": 512756, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.052563428878784, "global_step": 512757, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0248494148254395, "global_step": 512758, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.949501633644104, "global_step": 512759, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.044282913208008, "global_step": 512760, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9913992881774902, "global_step": 512761, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0409932136535645, "global_step": 512762, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9574370384216309, "global_step": 512763, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0184173583984375, "global_step": 512764, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0325889587402344, "global_step": 512765, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0586485862731934, "global_step": 512766, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9228904247283936, "global_step": 512767, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1184470653533936, "global_step": 512768, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0791518688201904, "global_step": 512769, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.986274242401123, "global_step": 512770, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0222790241241455, "global_step": 512771, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.035391330718994, "global_step": 512772, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.106541395187378, "global_step": 512773, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0862905979156494, "global_step": 512774, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0260281562805176, "global_step": 512775, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1731033325195312, "global_step": 512776, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9169974327087402, "global_step": 512777, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1243505477905273, "global_step": 512778, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0015809535980225, "global_step": 512779, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0294342041015625, "global_step": 512780, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9975413084030151, "global_step": 512781, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0359508991241455, "global_step": 512782, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0104053020477295, "global_step": 512783, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.077683448791504, "global_step": 512784, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0112392902374268, "global_step": 512785, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.012021541595459, "global_step": 512786, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.044393539428711, "global_step": 512787, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0137763023376465, "global_step": 512788, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0188241004943848, "global_step": 512789, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1076645851135254, "global_step": 512790, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9997975826263428, "global_step": 512791, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0726675987243652, "global_step": 512792, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0486044883728027, "global_step": 512793, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.051112174987793, "global_step": 512794, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1121714115142822, "global_step": 512795, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.943156361579895, "global_step": 512796, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.039496421813965, "global_step": 512797, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9478421211242676, "global_step": 512798, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0647599697113037, "global_step": 512799, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9961928129196167, "global_step": 512800, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.010498523712158, "global_step": 512801, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0237674713134766, "global_step": 512802, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.01945424079895, "global_step": 512803, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0427498817443848, "global_step": 512804, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1227340698242188, "global_step": 512805, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.033806324005127, "global_step": 512806, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.054417848587036, "global_step": 512807, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0236666202545166, "global_step": 512808, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9750711917877197, "global_step": 512809, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9451050758361816, "global_step": 512810, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.082672595977783, "global_step": 512811, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9988720417022705, "global_step": 512812, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.013867139816284, "global_step": 512813, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0021986961364746, "global_step": 512814, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.065303325653076, "global_step": 512815, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.985592007637024, "global_step": 512816, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.045581102371216, "global_step": 512817, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0586862564086914, "global_step": 512818, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.076273202896118, "global_step": 512819, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0793607234954834, "global_step": 512820, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0426416397094727, "global_step": 512821, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0250909328460693, "global_step": 512822, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9913482666015625, "global_step": 512823, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.047538995742798, "global_step": 512824, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.016019821166992, "global_step": 512825, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9843168258666992, "global_step": 512826, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.109891176223755, "global_step": 512827, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.008415937423706, "global_step": 512828, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9907606840133667, "global_step": 512829, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0564260482788086, "global_step": 512830, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.960066556930542, "global_step": 512831, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.072746753692627, "global_step": 512832, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0109105110168457, "global_step": 512833, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0891871452331543, "global_step": 512834, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.057915449142456, "global_step": 512835, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1056041717529297, "global_step": 512836, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.044403076171875, "global_step": 512837, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9630908966064453, "global_step": 512838, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.016131639480591, "global_step": 512839, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1431984901428223, "global_step": 512840, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.968454360961914, "global_step": 512841, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9919317960739136, "global_step": 512842, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0862998962402344, "global_step": 512843, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.046344041824341, "global_step": 512844, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.00911545753479, "global_step": 512845, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.8818119764328003, "global_step": 512846, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.998273253440857, "global_step": 512847, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0786705017089844, "global_step": 512848, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1038763523101807, "global_step": 512849, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9404058456420898, "global_step": 512850, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0342164039611816, "global_step": 512851, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.055097818374634, "global_step": 512852, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0139174461364746, "global_step": 512853, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1281564235687256, "global_step": 512854, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0089495182037354, "global_step": 512855, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0453133583068848, "global_step": 512856, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9825316667556763, "global_step": 512857, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.093682289123535, "global_step": 512858, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9914019107818604, "global_step": 512859, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0502302646636963, "global_step": 512860, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.055107593536377, "global_step": 512861, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.089369297027588, "global_step": 512862, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0203194618225098, "global_step": 512863, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9047688245773315, "global_step": 512864, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.065732717514038, "global_step": 512865, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.048550844192505, "global_step": 512866, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9722636938095093, "global_step": 512867, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9894570112228394, "global_step": 512868, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9788731336593628, "global_step": 512869, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1295933723449707, "global_step": 512870, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0678372383117676, "global_step": 512871, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.111485242843628, "global_step": 512872, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0671143531799316, "global_step": 512873, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0453007221221924, "global_step": 512874, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.987540364265442, "global_step": 512875, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.150439500808716, "global_step": 512876, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.017202138900757, "global_step": 512877, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1099324226379395, "global_step": 512878, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.092242956161499, "global_step": 512879, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0831401348114014, "global_step": 512880, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.061511278152466, "global_step": 512881, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9716897010803223, "global_step": 512882, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.010207176208496, "global_step": 512883, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.004042148590088, "global_step": 512884, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.044757127761841, "global_step": 512885, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.033297538757324, "global_step": 512886, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0057473182678223, "global_step": 512887, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0232651233673096, "global_step": 512888, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.992889165878296, "global_step": 512889, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.012666702270508, "global_step": 512890, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.972139596939087, "global_step": 512891, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.046985387802124, "global_step": 512892, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.061264753341675, "global_step": 512893, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.075446605682373, "global_step": 512894, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.945651888847351, "global_step": 512895, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0235891342163086, "global_step": 512896, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0250658988952637, "global_step": 512897, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.957749843597412, "global_step": 512898, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.97804856300354, "global_step": 512899, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0180397033691406, "global_step": 512900, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0464158058166504, "global_step": 512901, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1010029315948486, "global_step": 512902, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1528210639953613, "global_step": 512903, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0483791828155518, "global_step": 512904, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1062591075897217, "global_step": 512905, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.09379243850708, "global_step": 512906, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.067927360534668, "global_step": 512907, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0657474994659424, "global_step": 512908, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0319104194641113, "global_step": 512909, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0059545040130615, "global_step": 512910, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0389046669006348, "global_step": 512911, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.991925835609436, "global_step": 512912, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.043715238571167, "global_step": 512913, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.103909730911255, "global_step": 512914, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.03604793548584, "global_step": 512915, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.062290668487549, "global_step": 512916, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0488100051879883, "global_step": 512917, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0029640197753906, "global_step": 512918, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0665035247802734, "global_step": 512919, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9614596366882324, "global_step": 512920, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.096689224243164, "global_step": 512921, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.034125804901123, "global_step": 512922, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9522264003753662, "global_step": 512923, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.043337106704712, "global_step": 512924, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9933871030807495, "global_step": 512925, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0277180671691895, "global_step": 512926, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0667881965637207, "global_step": 512927, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0286154747009277, "global_step": 512928, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1057944297790527, "global_step": 512929, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9644492864608765, "global_step": 512930, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.073338031768799, "global_step": 512931, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9582284688949585, "global_step": 512932, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1088387966156006, "global_step": 512933, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0157339572906494, "global_step": 512934, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.012446880340576, "global_step": 512935, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.048710346221924, "global_step": 512936, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0666580200195312, "global_step": 512937, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.046773910522461, "global_step": 512938, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.012214183807373, "global_step": 512939, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1342344284057617, "global_step": 512940, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.094911575317383, "global_step": 512941, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9843934774398804, "global_step": 512942, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.006174087524414, "global_step": 512943, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0242817401885986, "global_step": 512944, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.099170207977295, "global_step": 512945, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0611634254455566, "global_step": 512946, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0620806217193604, "global_step": 512947, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0401365756988525, "global_step": 512948, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.039635419845581, "global_step": 512949, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.045902729034424, "global_step": 512950, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.988548994064331, "global_step": 512951, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0151894092559814, "global_step": 512952, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.955285906791687, "global_step": 512953, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9463682174682617, "global_step": 512954, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0158321857452393, "global_step": 512955, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9297691583633423, "global_step": 512956, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0991289615631104, "global_step": 512957, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.050657033920288, "global_step": 512958, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.075385808944702, "global_step": 512959, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.074164628982544, "global_step": 512960, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9876232147216797, "global_step": 512961, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0537075996398926, "global_step": 512962, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.105926752090454, "global_step": 512963, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.943514347076416, "global_step": 512964, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1391713619232178, "global_step": 512965, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0481443405151367, "global_step": 512966, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0329742431640625, "global_step": 512967, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.012601375579834, "global_step": 512968, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9850605726242065, "global_step": 512969, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9570651054382324, "global_step": 512970, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1138858795166016, "global_step": 512971, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0404481887817383, "global_step": 512972, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.037348985671997, "global_step": 512973, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9473966360092163, "global_step": 512974, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9883471727371216, "global_step": 512975, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.065725088119507, "global_step": 512976, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0324037075042725, "global_step": 512977, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0267343521118164, "global_step": 512978, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0641608238220215, "global_step": 512979, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0969882011413574, "global_step": 512980, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0486810207366943, "global_step": 512981, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.073671579360962, "global_step": 512982, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9989975690841675, "global_step": 512983, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0566208362579346, "global_step": 512984, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9373512268066406, "global_step": 512985, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9543278217315674, "global_step": 512986, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.106651782989502, "global_step": 512987, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0339324474334717, "global_step": 512988, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.031714916229248, "global_step": 512989, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.092378616333008, "global_step": 512990, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0469062328338623, "global_step": 512991, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0713021755218506, "global_step": 512992, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.052288055419922, "global_step": 512993, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9778591394424438, "global_step": 512994, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9960439205169678, "global_step": 512995, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.002756118774414, "global_step": 512996, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0024263858795166, "global_step": 512997, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.039546012878418, "global_step": 512998, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0788941383361816, "global_step": 512999, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.005279541015625, "global_step": 513000, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0496037006378174, "global_step": 513001, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.00297212600708, "global_step": 513002, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1034042835235596, "global_step": 513003, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1008307933807373, "global_step": 513004, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0881686210632324, "global_step": 513005, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.998946189880371, "global_step": 513006, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9871599674224854, "global_step": 513007, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.8919035196304321, "global_step": 513008, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0516722202301025, "global_step": 513009, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.10833740234375, "global_step": 513010, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0882208347320557, "global_step": 513011, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0434165000915527, "global_step": 513012, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0842058658599854, "global_step": 513013, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.057943105697632, "global_step": 513014, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.000765323638916, "global_step": 513015, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9713102579116821, "global_step": 513016, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.009706974029541, "global_step": 513017, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9919078350067139, "global_step": 513018, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0276901721954346, "global_step": 513019, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0483179092407227, "global_step": 513020, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0082948207855225, "global_step": 513021, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.074164867401123, "global_step": 513022, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0851922035217285, "global_step": 513023, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1230978965759277, "global_step": 513024, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9812300205230713, "global_step": 513025, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0243115425109863, "global_step": 513026, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9218531847000122, "global_step": 513027, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0227715969085693, "global_step": 513028, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9613001346588135, "global_step": 513029, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.105879306793213, "global_step": 513030, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0926733016967773, "global_step": 513031, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.13909649848938, "global_step": 513032, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9950700998306274, "global_step": 513033, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9761470556259155, "global_step": 513034, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1139509677886963, "global_step": 513035, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0062108039855957, "global_step": 513036, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0594754219055176, "global_step": 513037, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9956657886505127, "global_step": 513038, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0146710872650146, "global_step": 513039, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0954205989837646, "global_step": 513040, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.010342597961426, "global_step": 513041, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0611259937286377, "global_step": 513042, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0332493782043457, "global_step": 513043, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.02028751373291, "global_step": 513044, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.009500741958618, "global_step": 513045, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.066068410873413, "global_step": 513046, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0121207237243652, "global_step": 513047, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0324151515960693, "global_step": 513048, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9960278272628784, "global_step": 513049, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0227744579315186, "global_step": 513050, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0218868255615234, "global_step": 513051, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.077322483062744, "global_step": 513052, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1036744117736816, "global_step": 513053, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1079018115997314, "global_step": 513054, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0257961750030518, "global_step": 513055, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0214357376098633, "global_step": 513056, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.109532594680786, "global_step": 513057, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.025817394256592, "global_step": 513058, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.099480152130127, "global_step": 513059, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0202553272247314, "global_step": 513060, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9998722076416016, "global_step": 513061, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9597159624099731, "global_step": 513062, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.062382221221924, "global_step": 513063, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0873923301696777, "global_step": 513064, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.016559362411499, "global_step": 513065, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.057429075241089, "global_step": 513066, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.036216974258423, "global_step": 513067, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9436873197555542, "global_step": 513068, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0220096111297607, "global_step": 513069, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9989992380142212, "global_step": 513070, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0565366744995117, "global_step": 513071, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0596652030944824, "global_step": 513072, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9597333669662476, "global_step": 513073, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0730879306793213, "global_step": 513074, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.086744785308838, "global_step": 513075, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.028970718383789, "global_step": 513076, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.086956262588501, "global_step": 513077, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0575156211853027, "global_step": 513078, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0566365718841553, "global_step": 513079, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0610556602478027, "global_step": 513080, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.036668300628662, "global_step": 513081, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0515618324279785, "global_step": 513082, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0331342220306396, "global_step": 513083, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9921070337295532, "global_step": 513084, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.074279546737671, "global_step": 513085, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.020277500152588, "global_step": 513086, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.063438892364502, "global_step": 513087, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.988524317741394, "global_step": 513088, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0667827129364014, "global_step": 513089, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1298410892486572, "global_step": 513090, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.066936492919922, "global_step": 513091, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.032888174057007, "global_step": 513092, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0804431438446045, "global_step": 513093, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1123738288879395, "global_step": 513094, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.027428388595581, "global_step": 513095, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.06852388381958, "global_step": 513096, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0374836921691895, "global_step": 513097, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.041757822036743, "global_step": 513098, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9867873191833496, "global_step": 513099, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.139072895050049, "global_step": 513100, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.053406238555908, "global_step": 513101, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.016270637512207, "global_step": 513102, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1523590087890625, "global_step": 513103, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.034205198287964, "global_step": 513104, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.039548397064209, "global_step": 513105, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.091341733932495, "global_step": 513106, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0687475204467773, "global_step": 513107, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0304322242736816, "global_step": 513108, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9963443279266357, "global_step": 513109, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0495107173919678, "global_step": 513110, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.04845929145813, "global_step": 513111, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.092247486114502, "global_step": 513112, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.953641653060913, "global_step": 513113, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.059215784072876, "global_step": 513114, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9751982688903809, "global_step": 513115, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.115762710571289, "global_step": 513116, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0286903381347656, "global_step": 513117, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0805599689483643, "global_step": 513118, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.08905029296875, "global_step": 513119, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.013744831085205, "global_step": 513120, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.016080141067505, "global_step": 513121, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9493768215179443, "global_step": 513122, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9695156812667847, "global_step": 513123, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0259008407592773, "global_step": 513124, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0899250507354736, "global_step": 513125, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0628390312194824, "global_step": 513126, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1090643405914307, "global_step": 513127, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.016385316848755, "global_step": 513128, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0579652786254883, "global_step": 513129, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.060537099838257, "global_step": 513130, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0615406036376953, "global_step": 513131, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0994019508361816, "global_step": 513132, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.065438747406006, "global_step": 513133, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.05078125, "global_step": 513134, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.077199935913086, "global_step": 513135, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.030240535736084, "global_step": 513136, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.009910821914673, "global_step": 513137, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1065964698791504, "global_step": 513138, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0690536499023438, "global_step": 513139, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.082913875579834, "global_step": 513140, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9627838134765625, "global_step": 513141, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0197677612304688, "global_step": 513142, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0917813777923584, "global_step": 513143, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.031062364578247, "global_step": 513144, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0348572731018066, "global_step": 513145, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.088254451751709, "global_step": 513146, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.084841728210449, "global_step": 513147, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9406425952911377, "global_step": 513148, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0162928104400635, "global_step": 513149, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0628864765167236, "global_step": 513150, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0502703189849854, "global_step": 513151, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.070554256439209, "global_step": 513152, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.040903329849243, "global_step": 513153, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.080782413482666, "global_step": 513154, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.036892890930176, "global_step": 513155, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0196948051452637, "global_step": 513156, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.958332896232605, "global_step": 513157, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0029733180999756, "global_step": 513158, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1267528533935547, "global_step": 513159, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.013366222381592, "global_step": 513160, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.03037166595459, "global_step": 513161, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.044785737991333, "global_step": 513162, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.090169906616211, "global_step": 513163, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0194647312164307, "global_step": 513164, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0995516777038574, "global_step": 513165, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.022765636444092, "global_step": 513166, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9837322235107422, "global_step": 513167, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.064094066619873, "global_step": 513168, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9888826608657837, "global_step": 513169, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.975709319114685, "global_step": 513170, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9511624574661255, "global_step": 513171, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.112117290496826, "global_step": 513172, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.023078203201294, "global_step": 513173, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0747501850128174, "global_step": 513174, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0622777938842773, "global_step": 513175, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0854151248931885, "global_step": 513176, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0704424381256104, "global_step": 513177, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.047872304916382, "global_step": 513178, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9923568964004517, "global_step": 513179, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0325546264648438, "global_step": 513180, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9510207176208496, "global_step": 513181, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9613211154937744, "global_step": 513182, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.019907236099243, "global_step": 513183, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9998990297317505, "global_step": 513184, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.002265453338623, "global_step": 513185, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9982798099517822, "global_step": 513186, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.022265911102295, "global_step": 513187, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.984357476234436, "global_step": 513188, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0543901920318604, "global_step": 513189, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.037182331085205, "global_step": 513190, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.000286340713501, "global_step": 513191, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9614291191101074, "global_step": 513192, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.022385358810425, "global_step": 513193, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0047593116760254, "global_step": 513194, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0229997634887695, "global_step": 513195, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9862916469573975, "global_step": 513196, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1143274307250977, "global_step": 513197, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1064963340759277, "global_step": 513198, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.050309419631958, "global_step": 513199, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.997078537940979, "global_step": 513200, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.090862989425659, "global_step": 513201, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.039752960205078, "global_step": 513202, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9715576171875, "global_step": 513203, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.194582223892212, "global_step": 513204, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0196733474731445, "global_step": 513205, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0694024562835693, "global_step": 513206, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0450825691223145, "global_step": 513207, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.099116802215576, "global_step": 513208, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.055007219314575, "global_step": 513209, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0163192749023438, "global_step": 513210, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.015748977661133, "global_step": 513211, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.037479877471924, "global_step": 513212, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0810320377349854, "global_step": 513213, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9115103483200073, "global_step": 513214, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0714666843414307, "global_step": 513215, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0722663402557373, "global_step": 513216, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0872814655303955, "global_step": 513217, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.027979612350464, "global_step": 513218, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.176980972290039, "global_step": 513219, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0249452590942383, "global_step": 513220, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.996578335762024, "global_step": 513221, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9979653358459473, "global_step": 513222, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1637394428253174, "global_step": 513223, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0227925777435303, "global_step": 513224, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1121127605438232, "global_step": 513225, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1075069904327393, "global_step": 513226, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.02803635597229, "global_step": 513227, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.15899920463562, "global_step": 513228, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1012625694274902, "global_step": 513229, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.067451000213623, "global_step": 513230, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0034775733947754, "global_step": 513231, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.067634105682373, "global_step": 513232, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9271754026412964, "global_step": 513233, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0633339881896973, "global_step": 513234, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0930187702178955, "global_step": 513235, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.057039260864258, "global_step": 513236, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.056002616882324, "global_step": 513237, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.056576728820801, "global_step": 513238, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9848308563232422, "global_step": 513239, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0214853286743164, "global_step": 513240, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0839924812316895, "global_step": 513241, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.101393222808838, "global_step": 513242, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9765398502349854, "global_step": 513243, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.020794630050659, "global_step": 513244, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.161593198776245, "global_step": 513245, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1708948612213135, "global_step": 513246, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0181939601898193, "global_step": 513247, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9987245798110962, "global_step": 513248, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9937448501586914, "global_step": 513249, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0294413566589355, "global_step": 513250, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0469179153442383, "global_step": 513251, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9980542659759521, "global_step": 513252, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0716841220855713, "global_step": 513253, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1224417686462402, "global_step": 513254, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0052926540374756, "global_step": 513255, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.10347056388855, "global_step": 513256, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.058215856552124, "global_step": 513257, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0612003803253174, "global_step": 513258, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.048210382461548, "global_step": 513259, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9612030982971191, "global_step": 513260, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9984217882156372, "global_step": 513261, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.085581064224243, "global_step": 513262, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0344128608703613, "global_step": 513263, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0438435077667236, "global_step": 513264, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9934715032577515, "global_step": 513265, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.01269268989563, "global_step": 513266, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0550169944763184, "global_step": 513267, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0511627197265625, "global_step": 513268, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.109847068786621, "global_step": 513269, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.055375814437866, "global_step": 513270, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.068685293197632, "global_step": 513271, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.105555295944214, "global_step": 513272, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0402660369873047, "global_step": 513273, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9866348505020142, "global_step": 513274, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0151124000549316, "global_step": 513275, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0165746212005615, "global_step": 513276, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0521552562713623, "global_step": 513277, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.933869481086731, "global_step": 513278, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.99357271194458, "global_step": 513279, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.997558355331421, "global_step": 513280, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.055737018585205, "global_step": 513281, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0818328857421875, "global_step": 513282, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0371243953704834, "global_step": 513283, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9976351261138916, "global_step": 513284, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.091721534729004, "global_step": 513285, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0872793197631836, "global_step": 513286, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0081381797790527, "global_step": 513287, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.07957124710083, "global_step": 513288, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0459024906158447, "global_step": 513289, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.039632558822632, "global_step": 513290, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0502469539642334, "global_step": 513291, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.016638994216919, "global_step": 513292, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1158578395843506, "global_step": 513293, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.043339252471924, "global_step": 513294, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0417046546936035, "global_step": 513295, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0742597579956055, "global_step": 513296, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.05179500579834, "global_step": 513297, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0974929332733154, "global_step": 513298, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.012129306793213, "global_step": 513299, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.100285291671753, "global_step": 513300, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.052588701248169, "global_step": 513301, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0409810543060303, "global_step": 513302, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1260619163513184, "global_step": 513303, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.017390727996826, "global_step": 513304, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0867702960968018, "global_step": 513305, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.160921812057495, "global_step": 513306, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0645270347595215, "global_step": 513307, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9515390396118164, "global_step": 513308, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.018860101699829, "global_step": 513309, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0829546451568604, "global_step": 513310, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.002784013748169, "global_step": 513311, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.056530475616455, "global_step": 513312, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.00036883354187, "global_step": 513313, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9767436981201172, "global_step": 513314, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0887198448181152, "global_step": 513315, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0715630054473877, "global_step": 513316, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1283912658691406, "global_step": 513317, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0866341590881348, "global_step": 513318, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9884754419326782, "global_step": 513319, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0173873901367188, "global_step": 513320, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.049394130706787, "global_step": 513321, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.053346633911133, "global_step": 513322, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0262200832366943, "global_step": 513323, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.081118583679199, "global_step": 513324, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.028228759765625, "global_step": 513325, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9540207386016846, "global_step": 513326, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0072619915008545, "global_step": 513327, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0942089557647705, "global_step": 513328, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.999841570854187, "global_step": 513329, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.065232038497925, "global_step": 513330, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.061657428741455, "global_step": 513331, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0571722984313965, "global_step": 513332, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9865611791610718, "global_step": 513333, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9874444007873535, "global_step": 513334, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0661139488220215, "global_step": 513335, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.110687732696533, "global_step": 513336, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9315105676651, "global_step": 513337, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9761308431625366, "global_step": 513338, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.079002857208252, "global_step": 513339, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1312689781188965, "global_step": 513340, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.089778423309326, "global_step": 513341, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.01426362991333, "global_step": 513342, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.103569746017456, "global_step": 513343, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0784337520599365, "global_step": 513344, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.038025379180908, "global_step": 513345, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0443313121795654, "global_step": 513346, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0751044750213623, "global_step": 513347, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.089661121368408, "global_step": 513348, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.96573805809021, "global_step": 513349, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.106842279434204, "global_step": 513350, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9688552618026733, "global_step": 513351, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0601799488067627, "global_step": 513352, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0725162029266357, "global_step": 513353, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0448861122131348, "global_step": 513354, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0926742553710938, "global_step": 513355, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1364951133728027, "global_step": 513356, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.072570562362671, "global_step": 513357, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.063290596008301, "global_step": 513358, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0199010372161865, "global_step": 513359, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.018707036972046, "global_step": 513360, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9513590335845947, "global_step": 513361, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.085148334503174, "global_step": 513362, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.072469472885132, "global_step": 513363, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0812575817108154, "global_step": 513364, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9483569860458374, "global_step": 513365, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9511252641677856, "global_step": 513366, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0036942958831787, "global_step": 513367, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.047922372817993, "global_step": 513368, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.039590358734131, "global_step": 513369, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0566794872283936, "global_step": 513370, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9965962171554565, "global_step": 513371, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9699344635009766, "global_step": 513372, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.023513078689575, "global_step": 513373, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.054933547973633, "global_step": 513374, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0241944789886475, "global_step": 513375, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.013261318206787, "global_step": 513376, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.055568218231201, "global_step": 513377, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1498003005981445, "global_step": 513378, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0298428535461426, "global_step": 513379, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0338761806488037, "global_step": 513380, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0644898414611816, "global_step": 513381, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0310449600219727, "global_step": 513382, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.093008518218994, "global_step": 513383, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0351755619049072, "global_step": 513384, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0309858322143555, "global_step": 513385, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0280849933624268, "global_step": 513386, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0828280448913574, "global_step": 513387, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.045081853866577, "global_step": 513388, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0930228233337402, "global_step": 513389, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9615641832351685, "global_step": 513390, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0800435543060303, "global_step": 513391, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1244707107543945, "global_step": 513392, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.100799798965454, "global_step": 513393, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.088139772415161, "global_step": 513394, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.121814012527466, "global_step": 513395, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0546457767486572, "global_step": 513396, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.013592004776001, "global_step": 513397, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.051969051361084, "global_step": 513398, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.07004714012146, "global_step": 513399, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9879155158996582, "global_step": 513400, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.989200472831726, "global_step": 513401, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0334882736206055, "global_step": 513402, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0371084213256836, "global_step": 513403, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.028442144393921, "global_step": 513404, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.979943037033081, "global_step": 513405, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.002593994140625, "global_step": 513406, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.03102707862854, "global_step": 513407, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9970016479492188, "global_step": 513408, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0858662128448486, "global_step": 513409, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0814554691314697, "global_step": 513410, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0009517669677734, "global_step": 513411, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.018244981765747, "global_step": 513412, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.975243091583252, "global_step": 513413, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.062715768814087, "global_step": 513414, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9868264198303223, "global_step": 513415, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0038933753967285, "global_step": 513416, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9707932472229004, "global_step": 513417, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0541985034942627, "global_step": 513418, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.01474928855896, "global_step": 513419, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.017960548400879, "global_step": 513420, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.126324415206909, "global_step": 513421, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.076916217803955, "global_step": 513422, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.939412236213684, "global_step": 513423, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0473358631134033, "global_step": 513424, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.034050464630127, "global_step": 513425, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0607545375823975, "global_step": 513426, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0410609245300293, "global_step": 513427, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0276546478271484, "global_step": 513428, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0809764862060547, "global_step": 513429, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0357155799865723, "global_step": 513430, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.09908390045166, "global_step": 513431, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0343801975250244, "global_step": 513432, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0772392749786377, "global_step": 513433, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.15547776222229, "global_step": 513434, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0639679431915283, "global_step": 513435, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0465197563171387, "global_step": 513436, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.025261163711548, "global_step": 513437, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.088803291320801, "global_step": 513438, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0031931400299072, "global_step": 513439, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0709316730499268, "global_step": 513440, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0702686309814453, "global_step": 513441, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.024477243423462, "global_step": 513442, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.126046895980835, "global_step": 513443, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0506863594055176, "global_step": 513444, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.087022304534912, "global_step": 513445, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.029585838317871, "global_step": 513446, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.040421485900879, "global_step": 513447, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0401623249053955, "global_step": 513448, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0834009647369385, "global_step": 513449, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0241386890411377, "global_step": 513450, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0432257652282715, "global_step": 513451, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0278632640838623, "global_step": 513452, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0234057903289795, "global_step": 513453, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.026275157928467, "global_step": 513454, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.019585132598877, "global_step": 513455, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1078476905822754, "global_step": 513456, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9974725246429443, "global_step": 513457, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.01876163482666, "global_step": 513458, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1218225955963135, "global_step": 513459, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.010136842727661, "global_step": 513460, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0792460441589355, "global_step": 513461, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0605385303497314, "global_step": 513462, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.090632200241089, "global_step": 513463, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.982873797416687, "global_step": 513464, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9687780141830444, "global_step": 513465, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9920415878295898, "global_step": 513466, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9860652685165405, "global_step": 513467, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.064896821975708, "global_step": 513468, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.047523021697998, "global_step": 513469, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.043788433074951, "global_step": 513470, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.048607587814331, "global_step": 513471, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0733609199523926, "global_step": 513472, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0630033016204834, "global_step": 513473, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9464715719223022, "global_step": 513474, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0287816524505615, "global_step": 513475, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9594508409500122, "global_step": 513476, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0021445751190186, "global_step": 513477, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.032712697982788, "global_step": 513478, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.073643445968628, "global_step": 513479, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0422611236572266, "global_step": 513480, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0125555992126465, "global_step": 513481, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.058764696121216, "global_step": 513482, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1080355644226074, "global_step": 513483, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.051595449447632, "global_step": 513484, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.059015989303589, "global_step": 513485, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.02339506149292, "global_step": 513486, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0764617919921875, "global_step": 513487, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.017725706100464, "global_step": 513488, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1020469665527344, "global_step": 513489, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.140092134475708, "global_step": 513490, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.071578025817871, "global_step": 513491, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0390286445617676, "global_step": 513492, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9948590993881226, "global_step": 513493, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1160616874694824, "global_step": 513494, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0687060356140137, "global_step": 513495, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0031843185424805, "global_step": 513496, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.045809268951416, "global_step": 513497, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.044074058532715, "global_step": 513498, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1524577140808105, "global_step": 513499, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0552642345428467, "global_step": 513500, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0362119674682617, "global_step": 513501, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.008821487426758, "global_step": 513502, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9218475818634033, "global_step": 513503, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.974265456199646, "global_step": 513504, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.07087779045105, "global_step": 513505, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.13401460647583, "global_step": 513506, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0369796752929688, "global_step": 513507, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9893214702606201, "global_step": 513508, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1484782695770264, "global_step": 513509, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9765675067901611, "global_step": 513510, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.015960931777954, "global_step": 513511, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.087578773498535, "global_step": 513512, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9794225692749023, "global_step": 513513, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1201066970825195, "global_step": 513514, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.00954008102417, "global_step": 513515, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.063678026199341, "global_step": 513516, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.060112237930298, "global_step": 513517, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.061709403991699, "global_step": 513518, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0685386657714844, "global_step": 513519, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0569989681243896, "global_step": 513520, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.051870584487915, "global_step": 513521, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9986753463745117, "global_step": 513522, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0141713619232178, "global_step": 513523, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1393070220947266, "global_step": 513524, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0552310943603516, "global_step": 513525, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9714701175689697, "global_step": 513526, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0676474571228027, "global_step": 513527, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0549261569976807, "global_step": 513528, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0729799270629883, "global_step": 513529, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.099198818206787, "global_step": 513530, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0412521362304688, "global_step": 513531, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.067952871322632, "global_step": 513532, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.031008005142212, "global_step": 513533, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.096761703491211, "global_step": 513534, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9944456815719604, "global_step": 513535, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0374808311462402, "global_step": 513536, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.039905071258545, "global_step": 513537, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0690343379974365, "global_step": 513538, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0304336547851562, "global_step": 513539, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.044787883758545, "global_step": 513540, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0715699195861816, "global_step": 513541, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9423980712890625, "global_step": 513542, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0224013328552246, "global_step": 513543, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1072092056274414, "global_step": 513544, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0298216342926025, "global_step": 513545, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9530678987503052, "global_step": 513546, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.015611410140991, "global_step": 513547, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0767199993133545, "global_step": 513548, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0283846855163574, "global_step": 513549, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9934324026107788, "global_step": 513550, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0364596843719482, "global_step": 513551, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.044982433319092, "global_step": 513552, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0380313396453857, "global_step": 513553, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0746357440948486, "global_step": 513554, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0240888595581055, "global_step": 513555, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.97578763961792, "global_step": 513556, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1142172813415527, "global_step": 513557, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.011291742324829, "global_step": 513558, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0526514053344727, "global_step": 513559, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.976258635520935, "global_step": 513560, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.129179000854492, "global_step": 513561, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0205576419830322, "global_step": 513562, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.070457696914673, "global_step": 513563, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0059454441070557, "global_step": 513564, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1085188388824463, "global_step": 513565, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.998669147491455, "global_step": 513566, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0801713466644287, "global_step": 513567, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0667810440063477, "global_step": 513568, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0468082427978516, "global_step": 513569, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.128031015396118, "global_step": 513570, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0450639724731445, "global_step": 513571, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0073938369750977, "global_step": 513572, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0490825176239014, "global_step": 513573, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0383033752441406, "global_step": 513574, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9881497621536255, "global_step": 513575, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9972659349441528, "global_step": 513576, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.017958164215088, "global_step": 513577, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0715136528015137, "global_step": 513578, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0556700229644775, "global_step": 513579, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1219701766967773, "global_step": 513580, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1137330532073975, "global_step": 513581, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0660500526428223, "global_step": 513582, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.067772388458252, "global_step": 513583, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.048555850982666, "global_step": 513584, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1222586631774902, "global_step": 513585, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.028916120529175, "global_step": 513586, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0471689701080322, "global_step": 513587, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9354020357131958, "global_step": 513588, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1185948848724365, "global_step": 513589, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0342795848846436, "global_step": 513590, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.080801248550415, "global_step": 513591, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0003809928894043, "global_step": 513592, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0134732723236084, "global_step": 513593, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0210773944854736, "global_step": 513594, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.043940782546997, "global_step": 513595, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0967624187469482, "global_step": 513596, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0009241104125977, "global_step": 513597, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.021817922592163, "global_step": 513598, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.07658052444458, "global_step": 513599, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0663363933563232, "global_step": 513600, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1510181427001953, "global_step": 513601, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9999462366104126, "global_step": 513602, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.062936782836914, "global_step": 513603, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.082728862762451, "global_step": 513604, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9848295450210571, "global_step": 513605, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0480265617370605, "global_step": 513606, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.008357286453247, "global_step": 513607, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9814953804016113, "global_step": 513608, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0019845962524414, "global_step": 513609, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9937820434570312, "global_step": 513610, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.088164806365967, "global_step": 513611, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.127037286758423, "global_step": 513612, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.047226667404175, "global_step": 513613, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0738203525543213, "global_step": 513614, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.029862880706787, "global_step": 513615, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9705297946929932, "global_step": 513616, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0143070220947266, "global_step": 513617, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0340375900268555, "global_step": 513618, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.058713436126709, "global_step": 513619, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0388596057891846, "global_step": 513620, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.097079277038574, "global_step": 513621, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.062654733657837, "global_step": 513622, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.10610032081604, "global_step": 513623, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0336172580718994, "global_step": 513624, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.984958291053772, "global_step": 513625, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.071453809738159, "global_step": 513626, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.12654709815979, "global_step": 513627, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.058135747909546, "global_step": 513628, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0955519676208496, "global_step": 513629, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.983797311782837, "global_step": 513630, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1099159717559814, "global_step": 513631, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.059068202972412, "global_step": 513632, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0203025341033936, "global_step": 513633, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9348965883255005, "global_step": 513634, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.089139938354492, "global_step": 513635, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.072479486465454, "global_step": 513636, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.048518419265747, "global_step": 513637, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.134740114212036, "global_step": 513638, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.06731915473938, "global_step": 513639, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.048701763153076, "global_step": 513640, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0538833141326904, "global_step": 513641, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0335657596588135, "global_step": 513642, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9674327373504639, "global_step": 513643, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.031623125076294, "global_step": 513644, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.109206438064575, "global_step": 513645, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1117491722106934, "global_step": 513646, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.067992687225342, "global_step": 513647, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.997161865234375, "global_step": 513648, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0471835136413574, "global_step": 513649, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0548532009124756, "global_step": 513650, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.8968229293823242, "global_step": 513651, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0599000453948975, "global_step": 513652, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9699244499206543, "global_step": 513653, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0815200805664062, "global_step": 513654, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1517856121063232, "global_step": 513655, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1060879230499268, "global_step": 513656, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0090763568878174, "global_step": 513657, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0870354175567627, "global_step": 513658, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0059995651245117, "global_step": 513659, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.059455394744873, "global_step": 513660, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.019339084625244, "global_step": 513661, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0819766521453857, "global_step": 513662, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0675618648529053, "global_step": 513663, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.101076364517212, "global_step": 513664, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.027038812637329, "global_step": 513665, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0611515045166016, "global_step": 513666, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0779287815093994, "global_step": 513667, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1492443084716797, "global_step": 513668, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0692224502563477, "global_step": 513669, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1187710762023926, "global_step": 513670, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.03420090675354, "global_step": 513671, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0444142818450928, "global_step": 513672, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.961592674255371, "global_step": 513673, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.111863851547241, "global_step": 513674, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0621535778045654, "global_step": 513675, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.9839537143707275, "global_step": 513676, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.023785352706909, "global_step": 513677, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.089742422103882, "global_step": 513678, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0370984077453613, "global_step": 513679, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.089594841003418, "global_step": 513680, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0503454208374023, "global_step": 513681, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.100519895553589, "global_step": 513682, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0589563846588135, "global_step": 513683, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0747838020324707, "global_step": 513684, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.003769636154175, "global_step": 513685, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.013240337371826, "global_step": 513686, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.953926920890808, "global_step": 513687, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.049799919128418, "global_step": 513688, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0807478427886963, "global_step": 513689, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.152571678161621, "global_step": 513690, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0374269485473633, "global_step": 513691, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0329818725585938, "global_step": 513692, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0856761932373047, "global_step": 513693, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.008366823196411, "global_step": 513694, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0851218700408936, "global_step": 513695, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.054673671722412, "global_step": 513696, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0514042377471924, "global_step": 513697, "epoch": 879, "lr": 5e-05}
{"train_loss": 1.920443058013916, "global_step": 513698, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1174325942993164, "global_step": 513699, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0034070014953613, "global_step": 513700, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.0906457901000977, "global_step": 513701, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.042191743850708, "global_step": 513702, "epoch": 879, "lr": 5e-05}
{"train_loss": 2.1041691303253174, "global_step": 513703, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0509674549102783, "global_step": 513704, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.092637300491333, "global_step": 513705, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0725879669189453, "global_step": 513706, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9664568901062012, "global_step": 513707, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9746620655059814, "global_step": 513708, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.964647650718689, "global_step": 513709, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0451323986053467, "global_step": 513710, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.053208589553833, "global_step": 513711, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.091852903366089, "global_step": 513712, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0621159076690674, "global_step": 513713, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.09877610206604, "global_step": 513714, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.056955575942993, "global_step": 513715, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9940935373306274, "global_step": 513716, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9035863876342773, "global_step": 513717, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.067160129547119, "global_step": 513718, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0226855278015137, "global_step": 513719, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.087024211883545, "global_step": 513720, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0540270805358887, "global_step": 513721, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0362436771392822, "global_step": 513722, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0399205684661865, "global_step": 513723, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.976764440536499, "global_step": 513724, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0592684745788574, "global_step": 513725, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0481722354888916, "global_step": 513726, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0478968620300293, "global_step": 513727, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0995430946350098, "global_step": 513728, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.036978006362915, "global_step": 513729, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0728187561035156, "global_step": 513730, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.000114679336548, "global_step": 513731, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9929563999176025, "global_step": 513732, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0116333961486816, "global_step": 513733, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0370867252349854, "global_step": 513734, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0362420082092285, "global_step": 513735, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0628912448883057, "global_step": 513736, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0513956546783447, "global_step": 513737, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.037731409072876, "global_step": 513738, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.926216959953308, "global_step": 513739, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.077378511428833, "global_step": 513740, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.000981092453003, "global_step": 513741, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.040576934814453, "global_step": 513742, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.021869421005249, "global_step": 513743, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0784173011779785, "global_step": 513744, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.011223793029785, "global_step": 513745, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0462071895599365, "global_step": 513746, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.019608736038208, "global_step": 513747, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.058504343032837, "global_step": 513748, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.006788730621338, "global_step": 513749, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9910961389541626, "global_step": 513750, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9786691665649414, "global_step": 513751, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0478837490081787, "global_step": 513752, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0781030654907227, "global_step": 513753, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.041365146636963, "global_step": 513754, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0157129764556885, "global_step": 513755, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1214663982391357, "global_step": 513756, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0407779216766357, "global_step": 513757, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9607406854629517, "global_step": 513758, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0541939735412598, "global_step": 513759, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.009547233581543, "global_step": 513760, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0257701873779297, "global_step": 513761, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0173044204711914, "global_step": 513762, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9916192293167114, "global_step": 513763, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0873124599456787, "global_step": 513764, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0507969856262207, "global_step": 513765, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.040924072265625, "global_step": 513766, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9953523874282837, "global_step": 513767, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.02779483795166, "global_step": 513768, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.013935089111328, "global_step": 513769, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.087970733642578, "global_step": 513770, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.000255823135376, "global_step": 513771, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0505669116973877, "global_step": 513772, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0272645950317383, "global_step": 513773, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.084381103515625, "global_step": 513774, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0427238941192627, "global_step": 513775, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.047191858291626, "global_step": 513776, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.108659029006958, "global_step": 513777, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0995700359344482, "global_step": 513778, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.064087390899658, "global_step": 513779, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0080065727233887, "global_step": 513780, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.083076000213623, "global_step": 513781, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0631766319274902, "global_step": 513782, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.001803398132324, "global_step": 513783, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.055919885635376, "global_step": 513784, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9968340396881104, "global_step": 513785, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9911653995513916, "global_step": 513786, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.088639259338379, "global_step": 513787, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9859808683395386, "global_step": 513788, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0255846977233887, "global_step": 513789, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1405014991760254, "global_step": 513790, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.029025077819824, "global_step": 513791, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.072129249572754, "global_step": 513792, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0825185775756836, "global_step": 513793, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.034498929977417, "global_step": 513794, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0225419998168945, "global_step": 513795, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.122403860092163, "global_step": 513796, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9923145771026611, "global_step": 513797, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.01698899269104, "global_step": 513798, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.02864670753479, "global_step": 513799, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1300318241119385, "global_step": 513800, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0020997524261475, "global_step": 513801, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.045414686203003, "global_step": 513802, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.029761791229248, "global_step": 513803, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0091302394866943, "global_step": 513804, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0221409797668457, "global_step": 513805, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1411972045898438, "global_step": 513806, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.035195827484131, "global_step": 513807, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9854825735092163, "global_step": 513808, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.075350522994995, "global_step": 513809, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0297203063964844, "global_step": 513810, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9849810600280762, "global_step": 513811, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.01836895942688, "global_step": 513812, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0330870151519775, "global_step": 513813, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.002897262573242, "global_step": 513814, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0501139163970947, "global_step": 513815, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9840435981750488, "global_step": 513816, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1035614013671875, "global_step": 513817, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0308048725128174, "global_step": 513818, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0191385746002197, "global_step": 513819, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.068751811981201, "global_step": 513820, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.13454008102417, "global_step": 513821, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.8801085948944092, "global_step": 513822, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0623128414154053, "global_step": 513823, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0229361057281494, "global_step": 513824, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9278597831726074, "global_step": 513825, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9890717267990112, "global_step": 513826, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0601882934570312, "global_step": 513827, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0073986053466797, "global_step": 513828, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0047357082366943, "global_step": 513829, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0052123069763184, "global_step": 513830, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0509254932403564, "global_step": 513831, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0440433025360107, "global_step": 513832, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9758052825927734, "global_step": 513833, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.916318655014038, "global_step": 513834, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1401517391204834, "global_step": 513835, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0647292137145996, "global_step": 513836, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.083865165710449, "global_step": 513837, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0399670600891113, "global_step": 513838, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9543226957321167, "global_step": 513839, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.03745174407959, "global_step": 513840, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9611274003982544, "global_step": 513841, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.99737548828125, "global_step": 513842, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0265276432037354, "global_step": 513843, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.975884199142456, "global_step": 513844, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9947985410690308, "global_step": 513845, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.09468674659729, "global_step": 513846, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.064480781555176, "global_step": 513847, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9799985885620117, "global_step": 513848, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0619916915893555, "global_step": 513849, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.087211847305298, "global_step": 513850, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.190166711807251, "global_step": 513851, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.99886953830719, "global_step": 513852, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.112018346786499, "global_step": 513853, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.005870819091797, "global_step": 513854, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9716627597808838, "global_step": 513855, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0143868923187256, "global_step": 513856, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.080834150314331, "global_step": 513857, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.089587688446045, "global_step": 513858, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0226917266845703, "global_step": 513859, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1251485347747803, "global_step": 513860, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.993544340133667, "global_step": 513861, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0002944469451904, "global_step": 513862, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0633339881896973, "global_step": 513863, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.105435371398926, "global_step": 513864, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0628349781036377, "global_step": 513865, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.119279384613037, "global_step": 513866, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0925068855285645, "global_step": 513867, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0305795669555664, "global_step": 513868, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9795831441879272, "global_step": 513869, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.03946590423584, "global_step": 513870, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0209221839904785, "global_step": 513871, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.061788558959961, "global_step": 513872, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0379889011383057, "global_step": 513873, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.111625909805298, "global_step": 513874, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9656555652618408, "global_step": 513875, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0533761978149414, "global_step": 513876, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.068535804748535, "global_step": 513877, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9578440189361572, "global_step": 513878, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.033559799194336, "global_step": 513879, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0162131786346436, "global_step": 513880, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9931416511535645, "global_step": 513881, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0436289310455322, "global_step": 513882, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.021852970123291, "global_step": 513883, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0829570293426514, "global_step": 513884, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0595779418945312, "global_step": 513885, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.013843059539795, "global_step": 513886, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.08475923538208, "global_step": 513887, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.094874620437622, "global_step": 513888, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9695489406585693, "global_step": 513889, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.083571195602417, "global_step": 513890, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.089925527572632, "global_step": 513891, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9994494915008545, "global_step": 513892, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.034054756164551, "global_step": 513893, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0720431804656982, "global_step": 513894, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.030181646347046, "global_step": 513895, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.187319755554199, "global_step": 513896, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0426483154296875, "global_step": 513897, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0514018535614014, "global_step": 513898, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0927863121032715, "global_step": 513899, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0351877212524414, "global_step": 513900, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.045306921005249, "global_step": 513901, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.046438694000244, "global_step": 513902, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0382425785064697, "global_step": 513903, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1049561500549316, "global_step": 513904, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9901336431503296, "global_step": 513905, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.068655252456665, "global_step": 513906, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.07270884513855, "global_step": 513907, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0512959957122803, "global_step": 513908, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1349940299987793, "global_step": 513909, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0442676544189453, "global_step": 513910, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0082883834838867, "global_step": 513911, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1286962032318115, "global_step": 513912, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0582547187805176, "global_step": 513913, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.094101905822754, "global_step": 513914, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.028960943222046, "global_step": 513915, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9672340154647827, "global_step": 513916, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0720572471618652, "global_step": 513917, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.037644386291504, "global_step": 513918, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.002924919128418, "global_step": 513919, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.021433115005493, "global_step": 513920, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0572245121002197, "global_step": 513921, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0235328674316406, "global_step": 513922, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0444719791412354, "global_step": 513923, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.02424955368042, "global_step": 513924, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0327963829040527, "global_step": 513925, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9619473218917847, "global_step": 513926, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0547075271606445, "global_step": 513927, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0410118103027344, "global_step": 513928, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.090148687362671, "global_step": 513929, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.064110040664673, "global_step": 513930, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.002399206161499, "global_step": 513931, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0420265197753906, "global_step": 513932, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0964510440826416, "global_step": 513933, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9586381912231445, "global_step": 513934, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.079749584197998, "global_step": 513935, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9527482986450195, "global_step": 513936, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1331357955932617, "global_step": 513937, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0246918201446533, "global_step": 513938, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9775948524475098, "global_step": 513939, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0496747493743896, "global_step": 513940, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0108327865600586, "global_step": 513941, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.03678560256958, "global_step": 513942, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.021029472351074, "global_step": 513943, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0170109272003174, "global_step": 513944, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0560638904571533, "global_step": 513945, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.00490665435791, "global_step": 513946, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0261595249176025, "global_step": 513947, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0332984924316406, "global_step": 513948, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.127185344696045, "global_step": 513949, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.086299419403076, "global_step": 513950, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9831396341323853, "global_step": 513951, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0803587436676025, "global_step": 513952, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.060795545578003, "global_step": 513953, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.046689987182617, "global_step": 513954, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0019240379333496, "global_step": 513955, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0359323024749756, "global_step": 513956, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0151102542877197, "global_step": 513957, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9819279909133911, "global_step": 513958, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0037362575531006, "global_step": 513959, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9735159873962402, "global_step": 513960, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.027325391769409, "global_step": 513961, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.966444492340088, "global_step": 513962, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.065551996231079, "global_step": 513963, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.99795663356781, "global_step": 513964, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0410280227661133, "global_step": 513965, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0545308589935303, "global_step": 513966, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0293705463409424, "global_step": 513967, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0470454692840576, "global_step": 513968, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1722991466522217, "global_step": 513969, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9740321636199951, "global_step": 513970, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9744541645050049, "global_step": 513971, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0265018939971924, "global_step": 513972, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.000497341156006, "global_step": 513973, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0952625274658203, "global_step": 513974, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9942717552185059, "global_step": 513975, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9420182704925537, "global_step": 513976, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0671603679656982, "global_step": 513977, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0807526111602783, "global_step": 513978, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0807113647460938, "global_step": 513979, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.062314510345459, "global_step": 513980, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9884452819824219, "global_step": 513981, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0562822818756104, "global_step": 513982, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.037201166152954, "global_step": 513983, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.016472816467285, "global_step": 513984, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1261682510375977, "global_step": 513985, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0927343368530273, "global_step": 513986, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0779218673706055, "global_step": 513987, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.056966781616211, "global_step": 513988, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.94669508934021, "global_step": 513989, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0280630588531494, "global_step": 513990, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.002779006958008, "global_step": 513991, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.113276958465576, "global_step": 513992, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1056020259857178, "global_step": 513993, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0951144695281982, "global_step": 513994, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0740139484405518, "global_step": 513995, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9472883939743042, "global_step": 513996, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0388286113739014, "global_step": 513997, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1334221363067627, "global_step": 513998, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0457234382629395, "global_step": 513999, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0391547679901123, "global_step": 514000, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9957783222198486, "global_step": 514001, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0832395553588867, "global_step": 514002, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.099900722503662, "global_step": 514003, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.136927366256714, "global_step": 514004, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.038546562194824, "global_step": 514005, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0801308155059814, "global_step": 514006, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0430045127868652, "global_step": 514007, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0504891872406006, "global_step": 514008, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9769492149353027, "global_step": 514009, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0452167987823486, "global_step": 514010, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0878825187683105, "global_step": 514011, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9477570056915283, "global_step": 514012, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.101977825164795, "global_step": 514013, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0605201721191406, "global_step": 514014, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0170071125030518, "global_step": 514015, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0590243339538574, "global_step": 514016, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0616607666015625, "global_step": 514017, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0301663875579834, "global_step": 514018, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.101839065551758, "global_step": 514019, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.004406690597534, "global_step": 514020, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.032086133956909, "global_step": 514021, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.050121545791626, "global_step": 514022, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.105125665664673, "global_step": 514023, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.090024709701538, "global_step": 514024, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0430684089660645, "global_step": 514025, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0938608646392822, "global_step": 514026, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0773134231567383, "global_step": 514027, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0257346630096436, "global_step": 514028, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9348613023757935, "global_step": 514029, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9556156396865845, "global_step": 514030, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0028092861175537, "global_step": 514031, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.043614149093628, "global_step": 514032, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.054002285003662, "global_step": 514033, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.051931142807007, "global_step": 514034, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0721518993377686, "global_step": 514035, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1002306938171387, "global_step": 514036, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.157202959060669, "global_step": 514037, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9994703531265259, "global_step": 514038, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0164291858673096, "global_step": 514039, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.068380832672119, "global_step": 514040, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.067429542541504, "global_step": 514041, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.056532859802246, "global_step": 514042, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0992062091827393, "global_step": 514043, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0117995738983154, "global_step": 514044, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0541722774505615, "global_step": 514045, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0272626876831055, "global_step": 514046, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.083549976348877, "global_step": 514047, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.012704849243164, "global_step": 514048, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1113524436950684, "global_step": 514049, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.002789258956909, "global_step": 514050, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0724403858184814, "global_step": 514051, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.039154529571533, "global_step": 514052, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.051027297973633, "global_step": 514053, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.933770775794983, "global_step": 514054, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1459174156188965, "global_step": 514055, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0588290691375732, "global_step": 514056, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.960414171218872, "global_step": 514057, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1132941246032715, "global_step": 514058, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0267467498779297, "global_step": 514059, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9969736337661743, "global_step": 514060, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0353667736053467, "global_step": 514061, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9566718339920044, "global_step": 514062, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0339372158050537, "global_step": 514063, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0423357486724854, "global_step": 514064, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0841565132141113, "global_step": 514065, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0125019550323486, "global_step": 514066, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0003185272216797, "global_step": 514067, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1046395301818848, "global_step": 514068, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.053783655166626, "global_step": 514069, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0713062286376953, "global_step": 514070, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0399224758148193, "global_step": 514071, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0320169925689697, "global_step": 514072, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.032716989517212, "global_step": 514073, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.116936683654785, "global_step": 514074, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9803251028060913, "global_step": 514075, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.065460205078125, "global_step": 514076, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.066206693649292, "global_step": 514077, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0778627395629883, "global_step": 514078, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0601003170013428, "global_step": 514079, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1894760131835938, "global_step": 514080, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.04059100151062, "global_step": 514081, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0744080543518066, "global_step": 514082, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0810091495513916, "global_step": 514083, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.031313419342041, "global_step": 514084, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0349488258361816, "global_step": 514085, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.011080026626587, "global_step": 514086, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0892722606658936, "global_step": 514087, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0292563438415527, "global_step": 514088, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0221447944641113, "global_step": 514089, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9560257196426392, "global_step": 514090, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9838488101959229, "global_step": 514091, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.043626308441162, "global_step": 514092, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0714166164398193, "global_step": 514093, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1090424060821533, "global_step": 514094, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0842859745025635, "global_step": 514095, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0073976516723633, "global_step": 514096, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9187602996826172, "global_step": 514097, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9722356796264648, "global_step": 514098, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0042760372161865, "global_step": 514099, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.043116331100464, "global_step": 514100, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.010251522064209, "global_step": 514101, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9955147504806519, "global_step": 514102, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.037928342819214, "global_step": 514103, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0487565994262695, "global_step": 514104, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0948920249938965, "global_step": 514105, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.973792552947998, "global_step": 514106, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.100741147994995, "global_step": 514107, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0783588886260986, "global_step": 514108, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9945807456970215, "global_step": 514109, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0216915607452393, "global_step": 514110, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.98721444606781, "global_step": 514111, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.051234722137451, "global_step": 514112, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9568486213684082, "global_step": 514113, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.008274555206299, "global_step": 514114, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0871663093566895, "global_step": 514115, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.101837396621704, "global_step": 514116, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0812954902648926, "global_step": 514117, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0961310863494873, "global_step": 514118, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0465030670166016, "global_step": 514119, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1043031215667725, "global_step": 514120, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0148637294769287, "global_step": 514121, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.067056655883789, "global_step": 514122, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0441126823425293, "global_step": 514123, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.054212808609009, "global_step": 514124, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1076252460479736, "global_step": 514125, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0956833362579346, "global_step": 514126, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.01887845993042, "global_step": 514127, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0415451526641846, "global_step": 514128, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.041205406188965, "global_step": 514129, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9767990112304688, "global_step": 514130, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0710959434509277, "global_step": 514131, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0356216430664062, "global_step": 514132, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.056429862976074, "global_step": 514133, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9645984172821045, "global_step": 514134, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0220346450805664, "global_step": 514135, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.109062433242798, "global_step": 514136, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.141558885574341, "global_step": 514137, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0318896770477295, "global_step": 514138, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9916194677352905, "global_step": 514139, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0377590656280518, "global_step": 514140, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.028311014175415, "global_step": 514141, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.132437229156494, "global_step": 514142, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0565366744995117, "global_step": 514143, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1157147884368896, "global_step": 514144, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.057269334793091, "global_step": 514145, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.061365842819214, "global_step": 514146, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0940868854522705, "global_step": 514147, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0040533542633057, "global_step": 514148, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0333750247955322, "global_step": 514149, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.069760322570801, "global_step": 514150, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9509838819503784, "global_step": 514151, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.040163278579712, "global_step": 514152, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.044724464416504, "global_step": 514153, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0202648639678955, "global_step": 514154, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.119814157485962, "global_step": 514155, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.131838083267212, "global_step": 514156, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.011944055557251, "global_step": 514157, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0310378074645996, "global_step": 514158, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0806074142456055, "global_step": 514159, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.07249116897583, "global_step": 514160, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.087423086166382, "global_step": 514161, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.051636219024658, "global_step": 514162, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0632457733154297, "global_step": 514163, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.113325595855713, "global_step": 514164, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1065614223480225, "global_step": 514165, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.10247802734375, "global_step": 514166, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.147355318069458, "global_step": 514167, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0091123580932617, "global_step": 514168, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0646398067474365, "global_step": 514169, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.011408805847168, "global_step": 514170, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1438252925872803, "global_step": 514171, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0769331455230713, "global_step": 514172, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9828773736953735, "global_step": 514173, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.079292058944702, "global_step": 514174, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0667693614959717, "global_step": 514175, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.079393148422241, "global_step": 514176, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.072657346725464, "global_step": 514177, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.099508047103882, "global_step": 514178, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0611488819122314, "global_step": 514179, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9990503787994385, "global_step": 514180, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9764493703842163, "global_step": 514181, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0405662059783936, "global_step": 514182, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.046260356903076, "global_step": 514183, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.076977491378784, "global_step": 514184, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0010581016540527, "global_step": 514185, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0540502071380615, "global_step": 514186, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1095433235168457, "global_step": 514187, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0106117725372314, "global_step": 514188, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.071598529815674, "global_step": 514189, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0721516609191895, "global_step": 514190, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.017585515975952, "global_step": 514191, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1661620140075684, "global_step": 514192, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0859897136688232, "global_step": 514193, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1179580688476562, "global_step": 514194, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0754826068878174, "global_step": 514195, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0853312015533447, "global_step": 514196, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.100162982940674, "global_step": 514197, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.084747076034546, "global_step": 514198, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0294721126556396, "global_step": 514199, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.044926881790161, "global_step": 514200, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0530519485473633, "global_step": 514201, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9232513904571533, "global_step": 514202, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.071408271789551, "global_step": 514203, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0287513732910156, "global_step": 514204, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0248682498931885, "global_step": 514205, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.032998561859131, "global_step": 514206, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.028762102127075, "global_step": 514207, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.169109344482422, "global_step": 514208, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.052116632461548, "global_step": 514209, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1219615936279297, "global_step": 514210, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.018770694732666, "global_step": 514211, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0130863189697266, "global_step": 514212, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.064601421356201, "global_step": 514213, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.993064522743225, "global_step": 514214, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0967869758605957, "global_step": 514215, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9905604124069214, "global_step": 514216, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9272695779800415, "global_step": 514217, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1195342540740967, "global_step": 514218, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0641844272613525, "global_step": 514219, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1263346672058105, "global_step": 514220, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0005035400390625, "global_step": 514221, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0319106578826904, "global_step": 514222, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0685338973999023, "global_step": 514223, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0091614723205566, "global_step": 514224, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1375811100006104, "global_step": 514225, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9672921895980835, "global_step": 514226, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.052685260772705, "global_step": 514227, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1195809841156006, "global_step": 514228, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9992848634719849, "global_step": 514229, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0243661403656006, "global_step": 514230, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.075218915939331, "global_step": 514231, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.05355167388916, "global_step": 514232, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9960575103759766, "global_step": 514233, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9578386545181274, "global_step": 514234, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.006798267364502, "global_step": 514235, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.998940348625183, "global_step": 514236, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0414695739746094, "global_step": 514237, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.048798084259033, "global_step": 514238, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1184003353118896, "global_step": 514239, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0448310375213623, "global_step": 514240, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.024489402770996, "global_step": 514241, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9989213943481445, "global_step": 514242, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1319358348846436, "global_step": 514243, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.05379319190979, "global_step": 514244, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9892299175262451, "global_step": 514245, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0903520584106445, "global_step": 514246, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9669106006622314, "global_step": 514247, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0154879093170166, "global_step": 514248, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.038426160812378, "global_step": 514249, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0155065059661865, "global_step": 514250, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.043149948120117, "global_step": 514251, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0052733421325684, "global_step": 514252, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0170741081237793, "global_step": 514253, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9921619892120361, "global_step": 514254, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.127155303955078, "global_step": 514255, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1422696113586426, "global_step": 514256, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0352976322174072, "global_step": 514257, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0487351417541504, "global_step": 514258, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9748281240463257, "global_step": 514259, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.004589557647705, "global_step": 514260, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9977869987487793, "global_step": 514261, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0629611015319824, "global_step": 514262, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1408824920654297, "global_step": 514263, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.057720422744751, "global_step": 514264, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0095582008361816, "global_step": 514265, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.035446882247925, "global_step": 514266, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.989662528038025, "global_step": 514267, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0220508575439453, "global_step": 514268, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9814627170562744, "global_step": 514269, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0541558265686035, "global_step": 514270, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.980101227760315, "global_step": 514271, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0617058277130127, "global_step": 514272, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.024106025695801, "global_step": 514273, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.052377223968506, "global_step": 514274, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0281553268432617, "global_step": 514275, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0169858932495117, "global_step": 514276, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.152510166168213, "global_step": 514277, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0692124366760254, "global_step": 514278, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0027236938476562, "global_step": 514279, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9982802867889404, "global_step": 514280, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0456185340881348, "global_step": 514281, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0518922805786133, "global_step": 514282, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9955428838729858, "global_step": 514283, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.036238431930542, "global_step": 514284, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0093994140625, "global_step": 514285, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0498111248016357, "global_step": 514286, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0263657569885254, "global_step": 514287, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.020303249359131, "global_step": 514288, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0767314434051514, "global_step": 514289, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.00006103515625, "global_step": 514290, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.070916175842285, "global_step": 514291, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9792962074279785, "global_step": 514292, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.066596508026123, "global_step": 514293, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0634288787841797, "global_step": 514294, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9501583576202393, "global_step": 514295, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0930235385894775, "global_step": 514296, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0134963989257812, "global_step": 514297, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1331093311309814, "global_step": 514298, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0494625568389893, "global_step": 514299, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.090055227279663, "global_step": 514300, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.062506675720215, "global_step": 514301, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0559113025665283, "global_step": 514302, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.116473436355591, "global_step": 514303, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0711100101470947, "global_step": 514304, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9979275465011597, "global_step": 514305, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0248265266418457, "global_step": 514306, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9782638549804688, "global_step": 514307, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0015251636505127, "global_step": 514308, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0526063442230225, "global_step": 514309, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.057490587234497, "global_step": 514310, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1121585369110107, "global_step": 514311, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0489840507507324, "global_step": 514312, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9978097677230835, "global_step": 514313, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0898609161376953, "global_step": 514314, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0540764331817627, "global_step": 514315, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.102808713912964, "global_step": 514316, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.049696922302246, "global_step": 514317, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0071017742156982, "global_step": 514318, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1093170642852783, "global_step": 514319, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1656460762023926, "global_step": 514320, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.010308265686035, "global_step": 514321, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1588470935821533, "global_step": 514322, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0469422340393066, "global_step": 514323, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0125324726104736, "global_step": 514324, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.060337543487549, "global_step": 514325, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0821244716644287, "global_step": 514326, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.042062759399414, "global_step": 514327, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.091094970703125, "global_step": 514328, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.114811897277832, "global_step": 514329, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1034610271453857, "global_step": 514330, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0448312759399414, "global_step": 514331, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1784543991088867, "global_step": 514332, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9814403057098389, "global_step": 514333, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.101836919784546, "global_step": 514334, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.00946307182312, "global_step": 514335, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0336787700653076, "global_step": 514336, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0517756938934326, "global_step": 514337, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.042235851287842, "global_step": 514338, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0850439071655273, "global_step": 514339, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0412869453430176, "global_step": 514340, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1013829708099365, "global_step": 514341, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0255606174468994, "global_step": 514342, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0156495571136475, "global_step": 514343, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0597949028015137, "global_step": 514344, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0399696826934814, "global_step": 514345, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0398406982421875, "global_step": 514346, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.039257764816284, "global_step": 514347, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0510051250457764, "global_step": 514348, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1022682189941406, "global_step": 514349, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.079195022583008, "global_step": 514350, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0170657634735107, "global_step": 514351, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9920451641082764, "global_step": 514352, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0630760192871094, "global_step": 514353, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.048793315887451, "global_step": 514354, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.058384418487549, "global_step": 514355, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0605881214141846, "global_step": 514356, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.992147445678711, "global_step": 514357, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.105433702468872, "global_step": 514358, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0403072834014893, "global_step": 514359, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0511932373046875, "global_step": 514360, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9811880588531494, "global_step": 514361, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0073869228363037, "global_step": 514362, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0338950157165527, "global_step": 514363, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0624494552612305, "global_step": 514364, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.065034866333008, "global_step": 514365, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0052425861358643, "global_step": 514366, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.116300106048584, "global_step": 514367, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9862874746322632, "global_step": 514368, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.083949089050293, "global_step": 514369, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9982355833053589, "global_step": 514370, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9967796802520752, "global_step": 514371, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.008692741394043, "global_step": 514372, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9960296154022217, "global_step": 514373, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.04793643951416, "global_step": 514374, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.097083568572998, "global_step": 514375, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.086642026901245, "global_step": 514376, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0685501098632812, "global_step": 514377, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9662399291992188, "global_step": 514378, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1227500438690186, "global_step": 514379, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0785441398620605, "global_step": 514380, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.096559524536133, "global_step": 514381, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0150973796844482, "global_step": 514382, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.059643268585205, "global_step": 514383, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.070199728012085, "global_step": 514384, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0553224086761475, "global_step": 514385, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.096299409866333, "global_step": 514386, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.040707588195801, "global_step": 514387, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.05759596824646, "global_step": 514388, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1196651458740234, "global_step": 514389, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.129098892211914, "global_step": 514390, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1030497550964355, "global_step": 514391, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0808568000793457, "global_step": 514392, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.965754747390747, "global_step": 514393, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.079195499420166, "global_step": 514394, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0570449829101562, "global_step": 514395, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0486435890197754, "global_step": 514396, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.057528257369995, "global_step": 514397, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.101573944091797, "global_step": 514398, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1498560905456543, "global_step": 514399, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0536861419677734, "global_step": 514400, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9868309497833252, "global_step": 514401, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0346016883850098, "global_step": 514402, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0006725788116455, "global_step": 514403, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0162694454193115, "global_step": 514404, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0729713439941406, "global_step": 514405, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0759034156799316, "global_step": 514406, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0726630687713623, "global_step": 514407, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.053030490875244, "global_step": 514408, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1040847301483154, "global_step": 514409, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0024502277374268, "global_step": 514410, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.034548759460449, "global_step": 514411, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0662386417388916, "global_step": 514412, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0223491191864014, "global_step": 514413, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9928103685379028, "global_step": 514414, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1310534477233887, "global_step": 514415, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0043845176696777, "global_step": 514416, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.058725595474243, "global_step": 514417, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0776095390319824, "global_step": 514418, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1429014205932617, "global_step": 514419, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0502657890319824, "global_step": 514420, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.168804883956909, "global_step": 514421, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0537924766540527, "global_step": 514422, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9511537551879883, "global_step": 514423, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0857272148132324, "global_step": 514424, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0963222980499268, "global_step": 514425, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.99942147731781, "global_step": 514426, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1239430904388428, "global_step": 514427, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.07796049118042, "global_step": 514428, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.036688804626465, "global_step": 514429, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0313374996185303, "global_step": 514430, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.047118902206421, "global_step": 514431, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0330159664154053, "global_step": 514432, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9678975343704224, "global_step": 514433, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0160441398620605, "global_step": 514434, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.076578378677368, "global_step": 514435, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0421578884124756, "global_step": 514436, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9766913652420044, "global_step": 514437, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0463411808013916, "global_step": 514438, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0252490043640137, "global_step": 514439, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0475263595581055, "global_step": 514440, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9696805477142334, "global_step": 514441, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.094994068145752, "global_step": 514442, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0832767486572266, "global_step": 514443, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0442087650299072, "global_step": 514444, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.007737398147583, "global_step": 514445, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0447630882263184, "global_step": 514446, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.110302448272705, "global_step": 514447, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0682590007781982, "global_step": 514448, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1760988235473633, "global_step": 514449, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.01297664642334, "global_step": 514450, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.091327428817749, "global_step": 514451, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0294575691223145, "global_step": 514452, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1664528846740723, "global_step": 514453, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1340479850769043, "global_step": 514454, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1295104026794434, "global_step": 514455, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0505764484405518, "global_step": 514456, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.078667163848877, "global_step": 514457, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9768717288970947, "global_step": 514458, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0786492824554443, "global_step": 514459, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0745251178741455, "global_step": 514460, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0258336067199707, "global_step": 514461, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1090004444122314, "global_step": 514462, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0566253662109375, "global_step": 514463, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.06557035446167, "global_step": 514464, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.070565938949585, "global_step": 514465, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9898287057876587, "global_step": 514466, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.989031195640564, "global_step": 514467, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0224595069885254, "global_step": 514468, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.985106348991394, "global_step": 514469, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.110765218734741, "global_step": 514470, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.045766830444336, "global_step": 514471, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0759589672088623, "global_step": 514472, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0492284297943115, "global_step": 514473, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0840275287628174, "global_step": 514474, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0663368701934814, "global_step": 514475, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.20751690864563, "global_step": 514476, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0875723361968994, "global_step": 514477, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0298984050750732, "global_step": 514478, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.009443998336792, "global_step": 514479, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0224380493164062, "global_step": 514480, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1287682056427, "global_step": 514481, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.030179977416992, "global_step": 514482, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.025822877883911, "global_step": 514483, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.081197738647461, "global_step": 514484, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0448720455169678, "global_step": 514485, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0524613857269287, "global_step": 514486, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0039844512939453, "global_step": 514487, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0664420127868652, "global_step": 514488, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9863181114196777, "global_step": 514489, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.052757740020752, "global_step": 514490, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.030785083770752, "global_step": 514491, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1195504665374756, "global_step": 514492, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0839104652404785, "global_step": 514493, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.045754909515381, "global_step": 514494, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0849242210388184, "global_step": 514495, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9896008968353271, "global_step": 514496, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0045883655548096, "global_step": 514497, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0285470485687256, "global_step": 514498, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.117119312286377, "global_step": 514499, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0831475257873535, "global_step": 514500, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.075650930404663, "global_step": 514501, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0490305423736572, "global_step": 514502, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.049623727798462, "global_step": 514503, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0435128211975098, "global_step": 514504, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.141730546951294, "global_step": 514505, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0463807582855225, "global_step": 514506, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0407674312591553, "global_step": 514507, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.038076877593994, "global_step": 514508, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.030123710632324, "global_step": 514509, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0582785606384277, "global_step": 514510, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0674338340759277, "global_step": 514511, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.05739688873291, "global_step": 514512, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.068835496902466, "global_step": 514513, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9515597820281982, "global_step": 514514, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.974204659461975, "global_step": 514515, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1410953998565674, "global_step": 514516, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0385279655456543, "global_step": 514517, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0476009845733643, "global_step": 514518, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9862427711486816, "global_step": 514519, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.045616865158081, "global_step": 514520, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9743069410324097, "global_step": 514521, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9407973289489746, "global_step": 514522, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.047234296798706, "global_step": 514523, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1368744373321533, "global_step": 514524, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1396255493164062, "global_step": 514525, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1819140911102295, "global_step": 514526, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.095519781112671, "global_step": 514527, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.045450210571289, "global_step": 514528, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0446996688842773, "global_step": 514529, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.037229537963867, "global_step": 514530, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9800646305084229, "global_step": 514531, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0998175144195557, "global_step": 514532, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0617568492889404, "global_step": 514533, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9793972969055176, "global_step": 514534, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9841957092285156, "global_step": 514535, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0535261631011963, "global_step": 514536, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.125227451324463, "global_step": 514537, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9837924242019653, "global_step": 514538, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.203237533569336, "global_step": 514539, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0598154067993164, "global_step": 514540, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0450727939605713, "global_step": 514541, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1261134147644043, "global_step": 514542, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.004124641418457, "global_step": 514543, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.055969715118408, "global_step": 514544, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9706779718399048, "global_step": 514545, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0056803226470947, "global_step": 514546, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.024137258529663, "global_step": 514547, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.010941505432129, "global_step": 514548, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0659921169281006, "global_step": 514549, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.059580087661743, "global_step": 514550, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.238337278366089, "global_step": 514551, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9598596096038818, "global_step": 514552, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9649306535720825, "global_step": 514553, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.096111536026001, "global_step": 514554, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0554800033569336, "global_step": 514555, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.020547866821289, "global_step": 514556, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0457160472869873, "global_step": 514557, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0831682682037354, "global_step": 514558, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9829761981964111, "global_step": 514559, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.989285945892334, "global_step": 514560, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0823614597320557, "global_step": 514561, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1349270343780518, "global_step": 514562, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.06244158744812, "global_step": 514563, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0507874488830566, "global_step": 514564, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1397407054901123, "global_step": 514565, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9926233291625977, "global_step": 514566, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.041813850402832, "global_step": 514567, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.071953535079956, "global_step": 514568, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.074310064315796, "global_step": 514569, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0560197830200195, "global_step": 514570, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0446183681488037, "global_step": 514571, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0886828899383545, "global_step": 514572, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1111507415771484, "global_step": 514573, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0322072505950928, "global_step": 514574, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.03116512298584, "global_step": 514575, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.04093599319458, "global_step": 514576, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0745816230773926, "global_step": 514577, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1017379760742188, "global_step": 514578, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.070991039276123, "global_step": 514579, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0712838172912598, "global_step": 514580, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.068735361099243, "global_step": 514581, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1912992000579834, "global_step": 514582, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0211477279663086, "global_step": 514583, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0234365463256836, "global_step": 514584, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.060589551925659, "global_step": 514585, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0316731929779053, "global_step": 514586, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0170016288757324, "global_step": 514587, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1038200855255127, "global_step": 514588, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0045418739318848, "global_step": 514589, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1324303150177, "global_step": 514590, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1312825679779053, "global_step": 514591, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.059788942337036, "global_step": 514592, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.038723945617676, "global_step": 514593, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1399333477020264, "global_step": 514594, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.10245680809021, "global_step": 514595, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1157243251800537, "global_step": 514596, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.026069402694702, "global_step": 514597, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.046433687210083, "global_step": 514598, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.017212390899658, "global_step": 514599, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.01564359664917, "global_step": 514600, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1376149654388428, "global_step": 514601, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.14988112449646, "global_step": 514602, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9728773832321167, "global_step": 514603, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0084385871887207, "global_step": 514604, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1081762313842773, "global_step": 514605, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1270859241485596, "global_step": 514606, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0362350940704346, "global_step": 514607, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.111593246459961, "global_step": 514608, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0477678775787354, "global_step": 514609, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.986535906791687, "global_step": 514610, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1051573753356934, "global_step": 514611, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0990757942199707, "global_step": 514612, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.030810594558716, "global_step": 514613, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.155900001525879, "global_step": 514614, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0559749603271484, "global_step": 514615, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.141951084136963, "global_step": 514616, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0466933250427246, "global_step": 514617, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9916859865188599, "global_step": 514618, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9767121076583862, "global_step": 514619, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.055192470550537, "global_step": 514620, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.058591842651367, "global_step": 514621, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.064438819885254, "global_step": 514622, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0839691162109375, "global_step": 514623, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0834999084472656, "global_step": 514624, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.056546211242676, "global_step": 514625, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.045163631439209, "global_step": 514626, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0818283557891846, "global_step": 514627, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1100733280181885, "global_step": 514628, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1378257274627686, "global_step": 514629, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9311190843582153, "global_step": 514630, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.097510576248169, "global_step": 514631, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1198482513427734, "global_step": 514632, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0611510276794434, "global_step": 514633, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9827427864074707, "global_step": 514634, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0506513118743896, "global_step": 514635, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0500826835632324, "global_step": 514636, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.148556709289551, "global_step": 514637, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0714356899261475, "global_step": 514638, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9752122163772583, "global_step": 514639, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0416202545166016, "global_step": 514640, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0353379249572754, "global_step": 514641, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9707450866699219, "global_step": 514642, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1407525539398193, "global_step": 514643, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0775768756866455, "global_step": 514644, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.04921293258667, "global_step": 514645, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1065175533294678, "global_step": 514646, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0994560718536377, "global_step": 514647, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0079197883605957, "global_step": 514648, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0179104804992676, "global_step": 514649, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.130979299545288, "global_step": 514650, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.992753505706787, "global_step": 514651, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0030128955841064, "global_step": 514652, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1007158756256104, "global_step": 514653, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.980021595954895, "global_step": 514654, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0798466205596924, "global_step": 514655, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9772148132324219, "global_step": 514656, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1233153343200684, "global_step": 514657, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.074368953704834, "global_step": 514658, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0126144886016846, "global_step": 514659, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.015902280807495, "global_step": 514660, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.115142345428467, "global_step": 514661, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0185787677764893, "global_step": 514662, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9913215637207031, "global_step": 514663, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1181013584136963, "global_step": 514664, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0265109539031982, "global_step": 514665, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0380771160125732, "global_step": 514666, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.1057090759277344, "global_step": 514667, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0757367610931396, "global_step": 514668, "epoch": 880, "lr": 5e-05}
{"train_loss": 1.9776272773742676, "global_step": 514669, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0325114727020264, "global_step": 514670, "epoch": 880, "lr": 5e-05}
{"train_loss": 2.0483713150024414, "global_step": 514671, "epoch": 880, "lr": 5e-05, "val_loss": 5.726424694061279, "test_reconst_mse": 0.07326489686965942}
{"train_loss": 2.0392351150512695, "global_step": 514672, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.026521682739258, "global_step": 514673, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.096219539642334, "global_step": 514674, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9891139268875122, "global_step": 514675, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0557146072387695, "global_step": 514676, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0666050910949707, "global_step": 514677, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1222729682922363, "global_step": 514678, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0484488010406494, "global_step": 514679, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0471131801605225, "global_step": 514680, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9382063150405884, "global_step": 514681, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0932462215423584, "global_step": 514682, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.980294108390808, "global_step": 514683, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0208675861358643, "global_step": 514684, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.008162498474121, "global_step": 514685, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.05492901802063, "global_step": 514686, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0421855449676514, "global_step": 514687, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9255170822143555, "global_step": 514688, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0860447883605957, "global_step": 514689, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.023543357849121, "global_step": 514690, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.041010856628418, "global_step": 514691, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.043273687362671, "global_step": 514692, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.044586658477783, "global_step": 514693, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.025216817855835, "global_step": 514694, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0074312686920166, "global_step": 514695, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0825202465057373, "global_step": 514696, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.067565679550171, "global_step": 514697, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.100820779800415, "global_step": 514698, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.982133150100708, "global_step": 514699, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.041499376296997, "global_step": 514700, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9298717975616455, "global_step": 514701, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9699434041976929, "global_step": 514702, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.034313917160034, "global_step": 514703, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.972875714302063, "global_step": 514704, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.033989906311035, "global_step": 514705, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1352391242980957, "global_step": 514706, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.029879331588745, "global_step": 514707, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.988745927810669, "global_step": 514708, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.055872678756714, "global_step": 514709, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.002645492553711, "global_step": 514710, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0719316005706787, "global_step": 514711, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0274624824523926, "global_step": 514712, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.136669158935547, "global_step": 514713, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.037526845932007, "global_step": 514714, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.94754958152771, "global_step": 514715, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.026846170425415, "global_step": 514716, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0207512378692627, "global_step": 514717, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0702528953552246, "global_step": 514718, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0253043174743652, "global_step": 514719, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9025071859359741, "global_step": 514720, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9811179637908936, "global_step": 514721, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.070234537124634, "global_step": 514722, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9838045835494995, "global_step": 514723, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.028484582901001, "global_step": 514724, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9357075691223145, "global_step": 514725, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.085026741027832, "global_step": 514726, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1080894470214844, "global_step": 514727, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.918054223060608, "global_step": 514728, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9690239429473877, "global_step": 514729, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.038757562637329, "global_step": 514730, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.072694778442383, "global_step": 514731, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.066819906234741, "global_step": 514732, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9941964149475098, "global_step": 514733, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.125741481781006, "global_step": 514734, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0090551376342773, "global_step": 514735, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0983450412750244, "global_step": 514736, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.020775556564331, "global_step": 514737, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0775716304779053, "global_step": 514738, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1598901748657227, "global_step": 514739, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.945665955543518, "global_step": 514740, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0153603553771973, "global_step": 514741, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0730972290039062, "global_step": 514742, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0077106952667236, "global_step": 514743, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9891319274902344, "global_step": 514744, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.087465524673462, "global_step": 514745, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.064620018005371, "global_step": 514746, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.095817804336548, "global_step": 514747, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.006850242614746, "global_step": 514748, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0133118629455566, "global_step": 514749, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0082294940948486, "global_step": 514750, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.091562271118164, "global_step": 514751, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0175487995147705, "global_step": 514752, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0958728790283203, "global_step": 514753, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0231330394744873, "global_step": 514754, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9589308500289917, "global_step": 514755, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.2012922763824463, "global_step": 514756, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.13010835647583, "global_step": 514757, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9668042659759521, "global_step": 514758, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0083060264587402, "global_step": 514759, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0385758876800537, "global_step": 514760, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9385182857513428, "global_step": 514761, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0314652919769287, "global_step": 514762, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0441861152648926, "global_step": 514763, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.076340436935425, "global_step": 514764, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9463154077529907, "global_step": 514765, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9815106391906738, "global_step": 514766, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9460448026657104, "global_step": 514767, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1276752948760986, "global_step": 514768, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0302844047546387, "global_step": 514769, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.932787299156189, "global_step": 514770, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0593159198760986, "global_step": 514771, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0189292430877686, "global_step": 514772, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.059269428253174, "global_step": 514773, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.055821418762207, "global_step": 514774, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.019514560699463, "global_step": 514775, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.053760528564453, "global_step": 514776, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1368870735168457, "global_step": 514777, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0786845684051514, "global_step": 514778, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0189807415008545, "global_step": 514779, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.028228521347046, "global_step": 514780, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.070305585861206, "global_step": 514781, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.01725697517395, "global_step": 514782, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1229991912841797, "global_step": 514783, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9530471563339233, "global_step": 514784, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0769827365875244, "global_step": 514785, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.032771587371826, "global_step": 514786, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.104776382446289, "global_step": 514787, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0414388179779053, "global_step": 514788, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0360827445983887, "global_step": 514789, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9632511138916016, "global_step": 514790, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.051199197769165, "global_step": 514791, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0433664321899414, "global_step": 514792, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0716660022735596, "global_step": 514793, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.012876272201538, "global_step": 514794, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.024965286254883, "global_step": 514795, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.016733169555664, "global_step": 514796, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.02829647064209, "global_step": 514797, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9066030979156494, "global_step": 514798, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.062490224838257, "global_step": 514799, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0772788524627686, "global_step": 514800, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0641791820526123, "global_step": 514801, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0228662490844727, "global_step": 514802, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0722906589508057, "global_step": 514803, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.144285202026367, "global_step": 514804, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.035074472427368, "global_step": 514805, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0755653381347656, "global_step": 514806, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0849545001983643, "global_step": 514807, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.033463954925537, "global_step": 514808, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0237433910369873, "global_step": 514809, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.07132887840271, "global_step": 514810, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.983733057975769, "global_step": 514811, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.011322498321533, "global_step": 514812, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0498929023742676, "global_step": 514813, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9827388525009155, "global_step": 514814, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.030613422393799, "global_step": 514815, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1577236652374268, "global_step": 514816, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.000640869140625, "global_step": 514817, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0706887245178223, "global_step": 514818, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.008334159851074, "global_step": 514819, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1106669902801514, "global_step": 514820, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0755558013916016, "global_step": 514821, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.07674241065979, "global_step": 514822, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.039123773574829, "global_step": 514823, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.034572124481201, "global_step": 514824, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0279226303100586, "global_step": 514825, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.021029472351074, "global_step": 514826, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.035027027130127, "global_step": 514827, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.011836290359497, "global_step": 514828, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.031651020050049, "global_step": 514829, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0902225971221924, "global_step": 514830, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0552573204040527, "global_step": 514831, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0069658756256104, "global_step": 514832, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.065401077270508, "global_step": 514833, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9925161600112915, "global_step": 514834, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1215832233428955, "global_step": 514835, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0317060947418213, "global_step": 514836, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9883712530136108, "global_step": 514837, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.120062828063965, "global_step": 514838, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0446548461914062, "global_step": 514839, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0476386547088623, "global_step": 514840, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0229201316833496, "global_step": 514841, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.03326416015625, "global_step": 514842, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.125825881958008, "global_step": 514843, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9754266738891602, "global_step": 514844, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9929676055908203, "global_step": 514845, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0384621620178223, "global_step": 514846, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9269057512283325, "global_step": 514847, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.068967580795288, "global_step": 514848, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.011341094970703, "global_step": 514849, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0166823863983154, "global_step": 514850, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0195608139038086, "global_step": 514851, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0854010581970215, "global_step": 514852, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0545732975006104, "global_step": 514853, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0474045276641846, "global_step": 514854, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0284624099731445, "global_step": 514855, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0048141479492188, "global_step": 514856, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.134028673171997, "global_step": 514857, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0504283905029297, "global_step": 514858, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.047492265701294, "global_step": 514859, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0553550720214844, "global_step": 514860, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.944218635559082, "global_step": 514861, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0684502124786377, "global_step": 514862, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0491769313812256, "global_step": 514863, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0027718544006348, "global_step": 514864, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.040149211883545, "global_step": 514865, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.036682367324829, "global_step": 514866, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0461490154266357, "global_step": 514867, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0298681259155273, "global_step": 514868, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.102334976196289, "global_step": 514869, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.031069278717041, "global_step": 514870, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.00901460647583, "global_step": 514871, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.063781261444092, "global_step": 514872, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.035968780517578, "global_step": 514873, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9512666463851929, "global_step": 514874, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0876338481903076, "global_step": 514875, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0970122814178467, "global_step": 514876, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.124706983566284, "global_step": 514877, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.042511463165283, "global_step": 514878, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1235857009887695, "global_step": 514879, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0895721912384033, "global_step": 514880, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.004556894302368, "global_step": 514881, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0266191959381104, "global_step": 514882, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.085662841796875, "global_step": 514883, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9650722742080688, "global_step": 514884, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.996793508529663, "global_step": 514885, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.056976079940796, "global_step": 514886, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0141406059265137, "global_step": 514887, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0035552978515625, "global_step": 514888, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0332179069519043, "global_step": 514889, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1209352016448975, "global_step": 514890, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0348763465881348, "global_step": 514891, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1287343502044678, "global_step": 514892, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.067352056503296, "global_step": 514893, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0273947715759277, "global_step": 514894, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.03521990776062, "global_step": 514895, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0261359214782715, "global_step": 514896, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0991621017456055, "global_step": 514897, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0325398445129395, "global_step": 514898, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0897486209869385, "global_step": 514899, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0329980850219727, "global_step": 514900, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.044396162033081, "global_step": 514901, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9608381986618042, "global_step": 514902, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.051734447479248, "global_step": 514903, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9409301280975342, "global_step": 514904, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.031271457672119, "global_step": 514905, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.106508255004883, "global_step": 514906, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0793683528900146, "global_step": 514907, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0295841693878174, "global_step": 514908, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0716309547424316, "global_step": 514909, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0152223110198975, "global_step": 514910, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1207706928253174, "global_step": 514911, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0313806533813477, "global_step": 514912, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.054439067840576, "global_step": 514913, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.035287618637085, "global_step": 514914, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.046260356903076, "global_step": 514915, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.046644687652588, "global_step": 514916, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0784928798675537, "global_step": 514917, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.046660900115967, "global_step": 514918, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0100207328796387, "global_step": 514919, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9950459003448486, "global_step": 514920, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9531350135803223, "global_step": 514921, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0269393920898438, "global_step": 514922, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.031318187713623, "global_step": 514923, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1236441135406494, "global_step": 514924, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0947701930999756, "global_step": 514925, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0335452556610107, "global_step": 514926, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.138207197189331, "global_step": 514927, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.8994085788726807, "global_step": 514928, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.022437334060669, "global_step": 514929, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0911471843719482, "global_step": 514930, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0143067836761475, "global_step": 514931, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.083176851272583, "global_step": 514932, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.005305290222168, "global_step": 514933, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9663889408111572, "global_step": 514934, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9715937376022339, "global_step": 514935, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0082530975341797, "global_step": 514936, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0192577838897705, "global_step": 514937, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0175163745880127, "global_step": 514938, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0736544132232666, "global_step": 514939, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0616180896759033, "global_step": 514940, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.116291046142578, "global_step": 514941, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0815651416778564, "global_step": 514942, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0401782989501953, "global_step": 514943, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0369739532470703, "global_step": 514944, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0871403217315674, "global_step": 514945, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0590038299560547, "global_step": 514946, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.063276767730713, "global_step": 514947, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.109219551086426, "global_step": 514948, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.098813772201538, "global_step": 514949, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0205771923065186, "global_step": 514950, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0101375579833984, "global_step": 514951, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9755527973175049, "global_step": 514952, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0436110496520996, "global_step": 514953, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0417113304138184, "global_step": 514954, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.080812931060791, "global_step": 514955, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.055825710296631, "global_step": 514956, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0392119884490967, "global_step": 514957, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.158684492111206, "global_step": 514958, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.088362455368042, "global_step": 514959, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.010540246963501, "global_step": 514960, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.004648447036743, "global_step": 514961, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0501012802124023, "global_step": 514962, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0179057121276855, "global_step": 514963, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0410733222961426, "global_step": 514964, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.001232624053955, "global_step": 514965, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0264856815338135, "global_step": 514966, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.051892042160034, "global_step": 514967, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0417230129241943, "global_step": 514968, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.031083106994629, "global_step": 514969, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.090304374694824, "global_step": 514970, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.072305679321289, "global_step": 514971, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0007739067077637, "global_step": 514972, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.150908946990967, "global_step": 514973, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.077542543411255, "global_step": 514974, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1898396015167236, "global_step": 514975, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9821126461029053, "global_step": 514976, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.082427501678467, "global_step": 514977, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0754611492156982, "global_step": 514978, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.072631597518921, "global_step": 514979, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9504144191741943, "global_step": 514980, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.021879196166992, "global_step": 514981, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0983362197875977, "global_step": 514982, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0496628284454346, "global_step": 514983, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9525744915008545, "global_step": 514984, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0132226943969727, "global_step": 514985, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.044682025909424, "global_step": 514986, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0296480655670166, "global_step": 514987, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9848506450653076, "global_step": 514988, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1605522632598877, "global_step": 514989, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0057010650634766, "global_step": 514990, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0185396671295166, "global_step": 514991, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.060216188430786, "global_step": 514992, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.083531141281128, "global_step": 514993, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.085770606994629, "global_step": 514994, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1115329265594482, "global_step": 514995, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0830321311950684, "global_step": 514996, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.08122181892395, "global_step": 514997, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.009580373764038, "global_step": 514998, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.084623098373413, "global_step": 514999, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0648059844970703, "global_step": 515000, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0248708724975586, "global_step": 515001, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0236051082611084, "global_step": 515002, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1188862323760986, "global_step": 515003, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9664521217346191, "global_step": 515004, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0538885593414307, "global_step": 515005, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0780422687530518, "global_step": 515006, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0464539527893066, "global_step": 515007, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0118205547332764, "global_step": 515008, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.085209846496582, "global_step": 515009, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0145039558410645, "global_step": 515010, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.125368356704712, "global_step": 515011, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.116152048110962, "global_step": 515012, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9857383966445923, "global_step": 515013, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0750651359558105, "global_step": 515014, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0344667434692383, "global_step": 515015, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.958101511001587, "global_step": 515016, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0559308528900146, "global_step": 515017, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9456305503845215, "global_step": 515018, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0052361488342285, "global_step": 515019, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.057074785232544, "global_step": 515020, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.052757740020752, "global_step": 515021, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9953371286392212, "global_step": 515022, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9534920454025269, "global_step": 515023, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0388972759246826, "global_step": 515024, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0607855319976807, "global_step": 515025, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9701517820358276, "global_step": 515026, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0593793392181396, "global_step": 515027, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0125129222869873, "global_step": 515028, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0004992485046387, "global_step": 515029, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.043963670730591, "global_step": 515030, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.054778814315796, "global_step": 515031, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0866801738739014, "global_step": 515032, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.212270975112915, "global_step": 515033, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.013578414916992, "global_step": 515034, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.038501739501953, "global_step": 515035, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9899002313613892, "global_step": 515036, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.060368537902832, "global_step": 515037, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0320427417755127, "global_step": 515038, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0003573894500732, "global_step": 515039, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0092623233795166, "global_step": 515040, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9926958084106445, "global_step": 515041, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.995911955833435, "global_step": 515042, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.003303050994873, "global_step": 515043, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.014789581298828, "global_step": 515044, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0096654891967773, "global_step": 515045, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.048888921737671, "global_step": 515046, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0832695960998535, "global_step": 515047, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.053755283355713, "global_step": 515048, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0562312602996826, "global_step": 515049, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.090013027191162, "global_step": 515050, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1170239448547363, "global_step": 515051, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.036580801010132, "global_step": 515052, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.149902820587158, "global_step": 515053, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.111210823059082, "global_step": 515054, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9861658811569214, "global_step": 515055, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0963807106018066, "global_step": 515056, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.03340220451355, "global_step": 515057, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0039732456207275, "global_step": 515058, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.102863073348999, "global_step": 515059, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.8836355209350586, "global_step": 515060, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.000849962234497, "global_step": 515061, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9850614070892334, "global_step": 515062, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.125382423400879, "global_step": 515063, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0528757572174072, "global_step": 515064, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0504884719848633, "global_step": 515065, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1066150665283203, "global_step": 515066, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0382068157196045, "global_step": 515067, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0343070030212402, "global_step": 515068, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0967438220977783, "global_step": 515069, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.153996467590332, "global_step": 515070, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.037266731262207, "global_step": 515071, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0241432189941406, "global_step": 515072, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0355517864227295, "global_step": 515073, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0069704055786133, "global_step": 515074, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.095148801803589, "global_step": 515075, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.028777837753296, "global_step": 515076, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9853005409240723, "global_step": 515077, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9782110452651978, "global_step": 515078, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0281260013580322, "global_step": 515079, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1670281887054443, "global_step": 515080, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.013333320617676, "global_step": 515081, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.060615062713623, "global_step": 515082, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0279908180236816, "global_step": 515083, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.000427484512329, "global_step": 515084, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0071911811828613, "global_step": 515085, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.112334966659546, "global_step": 515086, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9491788148880005, "global_step": 515087, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.942129373550415, "global_step": 515088, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.09684157371521, "global_step": 515089, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.005829334259033, "global_step": 515090, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0393288135528564, "global_step": 515091, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.101226329803467, "global_step": 515092, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.02707576751709, "global_step": 515093, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.999325156211853, "global_step": 515094, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1092207431793213, "global_step": 515095, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1232669353485107, "global_step": 515096, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0464587211608887, "global_step": 515097, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0735936164855957, "global_step": 515098, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.063075065612793, "global_step": 515099, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0115742683410645, "global_step": 515100, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.175067901611328, "global_step": 515101, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1045706272125244, "global_step": 515102, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0113604068756104, "global_step": 515103, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0885653495788574, "global_step": 515104, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.140604257583618, "global_step": 515105, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.039701223373413, "global_step": 515106, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0620996952056885, "global_step": 515107, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.028921604156494, "global_step": 515108, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.00978422164917, "global_step": 515109, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9739211797714233, "global_step": 515110, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9904253482818604, "global_step": 515111, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0809895992279053, "global_step": 515112, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0918712615966797, "global_step": 515113, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.042600154876709, "global_step": 515114, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0291309356689453, "global_step": 515115, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0978755950927734, "global_step": 515116, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0149478912353516, "global_step": 515117, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.094940185546875, "global_step": 515118, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.132300615310669, "global_step": 515119, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0118088722229004, "global_step": 515120, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.016422986984253, "global_step": 515121, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1543374061584473, "global_step": 515122, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9418423175811768, "global_step": 515123, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0802834033966064, "global_step": 515124, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9878284931182861, "global_step": 515125, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0658133029937744, "global_step": 515126, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.044306755065918, "global_step": 515127, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0744400024414062, "global_step": 515128, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.098524332046509, "global_step": 515129, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0451343059539795, "global_step": 515130, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.003086805343628, "global_step": 515131, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1010372638702393, "global_step": 515132, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1684155464172363, "global_step": 515133, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.045384168624878, "global_step": 515134, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.057661771774292, "global_step": 515135, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.000696897506714, "global_step": 515136, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.067938804626465, "global_step": 515137, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1156632900238037, "global_step": 515138, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0179708003997803, "global_step": 515139, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9730017185211182, "global_step": 515140, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9671542644500732, "global_step": 515141, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.105767250061035, "global_step": 515142, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.964395523071289, "global_step": 515143, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9805842638015747, "global_step": 515144, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9773781299591064, "global_step": 515145, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.049793004989624, "global_step": 515146, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.105841636657715, "global_step": 515147, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1522889137268066, "global_step": 515148, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0436744689941406, "global_step": 515149, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9670062065124512, "global_step": 515150, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1122279167175293, "global_step": 515151, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.000448226928711, "global_step": 515152, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9927756786346436, "global_step": 515153, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.983069896697998, "global_step": 515154, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.075261354446411, "global_step": 515155, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0307388305664062, "global_step": 515156, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0321874618530273, "global_step": 515157, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9764431715011597, "global_step": 515158, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.044785976409912, "global_step": 515159, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.011324167251587, "global_step": 515160, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.018655776977539, "global_step": 515161, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0129857063293457, "global_step": 515162, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.025418281555176, "global_step": 515163, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0328707695007324, "global_step": 515164, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0635299682617188, "global_step": 515165, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0794248580932617, "global_step": 515166, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9981071949005127, "global_step": 515167, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0084948539733887, "global_step": 515168, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0555174350738525, "global_step": 515169, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.055976152420044, "global_step": 515170, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.033128499984741, "global_step": 515171, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0795440673828125, "global_step": 515172, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0086092948913574, "global_step": 515173, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9959733486175537, "global_step": 515174, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1523447036743164, "global_step": 515175, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9885023832321167, "global_step": 515176, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9999243021011353, "global_step": 515177, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.036059856414795, "global_step": 515178, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.030550718307495, "global_step": 515179, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9770745038986206, "global_step": 515180, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0553107261657715, "global_step": 515181, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0688633918762207, "global_step": 515182, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0549190044403076, "global_step": 515183, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0908422470092773, "global_step": 515184, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9757729768753052, "global_step": 515185, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0152788162231445, "global_step": 515186, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.025209665298462, "global_step": 515187, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.067472457885742, "global_step": 515188, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0087103843688965, "global_step": 515189, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.103982925415039, "global_step": 515190, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0757839679718018, "global_step": 515191, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1300384998321533, "global_step": 515192, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.021328926086426, "global_step": 515193, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0270674228668213, "global_step": 515194, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0035223960876465, "global_step": 515195, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0240771770477295, "global_step": 515196, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0107908248901367, "global_step": 515197, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.061495780944824, "global_step": 515198, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.023447275161743, "global_step": 515199, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0419793128967285, "global_step": 515200, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.034684658050537, "global_step": 515201, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.00430965423584, "global_step": 515202, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0200695991516113, "global_step": 515203, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9293293952941895, "global_step": 515204, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.003070116043091, "global_step": 515205, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1262311935424805, "global_step": 515206, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9458026885986328, "global_step": 515207, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.041973114013672, "global_step": 515208, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.040118932723999, "global_step": 515209, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1380722522735596, "global_step": 515210, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.051884651184082, "global_step": 515211, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.062915563583374, "global_step": 515212, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9931856393814087, "global_step": 515213, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0061235427856445, "global_step": 515214, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9904781579971313, "global_step": 515215, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1369106769561768, "global_step": 515216, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.063887357711792, "global_step": 515217, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.951238751411438, "global_step": 515218, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.045837879180908, "global_step": 515219, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.143364667892456, "global_step": 515220, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.030913829803467, "global_step": 515221, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9742814302444458, "global_step": 515222, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9717258214950562, "global_step": 515223, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.011748790740967, "global_step": 515224, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0367658138275146, "global_step": 515225, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1329245567321777, "global_step": 515226, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.044696092605591, "global_step": 515227, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.028350830078125, "global_step": 515228, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9891357421875, "global_step": 515229, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.045203447341919, "global_step": 515230, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.003993272781372, "global_step": 515231, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.071572780609131, "global_step": 515232, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.064764976501465, "global_step": 515233, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0026779174804688, "global_step": 515234, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.094191789627075, "global_step": 515235, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1326589584350586, "global_step": 515236, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9826066493988037, "global_step": 515237, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0760700702667236, "global_step": 515238, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9159185886383057, "global_step": 515239, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.056178092956543, "global_step": 515240, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0323615074157715, "global_step": 515241, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0423974990844727, "global_step": 515242, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.009974718093872, "global_step": 515243, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.080474853515625, "global_step": 515244, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.088404655456543, "global_step": 515245, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.063784599304199, "global_step": 515246, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1232330799102783, "global_step": 515247, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.07293701171875, "global_step": 515248, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9793514013290405, "global_step": 515249, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0735626220703125, "global_step": 515250, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.066732883453369, "global_step": 515251, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0377988815307617, "global_step": 515252, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9603958129882812, "global_step": 515253, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0956029891967773, "global_step": 515254, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9794458150863647, "global_step": 515255, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.139953851699829, "global_step": 515256, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9988784790039062, "global_step": 515257, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0285682678222656, "global_step": 515258, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0845232009887695, "global_step": 515259, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.104496955871582, "global_step": 515260, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.074418067932129, "global_step": 515261, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0701346397399902, "global_step": 515262, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0628888607025146, "global_step": 515263, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.965026617050171, "global_step": 515264, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0551199913024902, "global_step": 515265, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0243418216705322, "global_step": 515266, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.011349678039551, "global_step": 515267, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0027432441711426, "global_step": 515268, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9170193672180176, "global_step": 515269, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0786266326904297, "global_step": 515270, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0149521827697754, "global_step": 515271, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0561814308166504, "global_step": 515272, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0254955291748047, "global_step": 515273, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0886847972869873, "global_step": 515274, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9521600008010864, "global_step": 515275, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.000950813293457, "global_step": 515276, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9037561416625977, "global_step": 515277, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.044790506362915, "global_step": 515278, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.043262004852295, "global_step": 515279, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9850013256072998, "global_step": 515280, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0799925327301025, "global_step": 515281, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.990019679069519, "global_step": 515282, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0705888271331787, "global_step": 515283, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9879953861236572, "global_step": 515284, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.046035051345825, "global_step": 515285, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0946714878082275, "global_step": 515286, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0293068885803223, "global_step": 515287, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0158493518829346, "global_step": 515288, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.10781192779541, "global_step": 515289, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0517067909240723, "global_step": 515290, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.112042188644409, "global_step": 515291, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0168042182922363, "global_step": 515292, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.026909828186035, "global_step": 515293, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9925780296325684, "global_step": 515294, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9896937608718872, "global_step": 515295, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9889131784439087, "global_step": 515296, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0131607055664062, "global_step": 515297, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.061995506286621, "global_step": 515298, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.099395275115967, "global_step": 515299, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.010542154312134, "global_step": 515300, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0733532905578613, "global_step": 515301, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0379748344421387, "global_step": 515302, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1057181358337402, "global_step": 515303, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0903797149658203, "global_step": 515304, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.111302137374878, "global_step": 515305, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.069610834121704, "global_step": 515306, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0502240657806396, "global_step": 515307, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0673251152038574, "global_step": 515308, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.040229558944702, "global_step": 515309, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.027026891708374, "global_step": 515310, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0414626598358154, "global_step": 515311, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1584677696228027, "global_step": 515312, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.048379421234131, "global_step": 515313, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.009331226348877, "global_step": 515314, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0501115322113037, "global_step": 515315, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.081752061843872, "global_step": 515316, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9750068187713623, "global_step": 515317, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0350685119628906, "global_step": 515318, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.093919038772583, "global_step": 515319, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.124176025390625, "global_step": 515320, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.036778211593628, "global_step": 515321, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9657002687454224, "global_step": 515322, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9752914905548096, "global_step": 515323, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.026733636856079, "global_step": 515324, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9498895406723022, "global_step": 515325, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0133111476898193, "global_step": 515326, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.050525665283203, "global_step": 515327, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1028223037719727, "global_step": 515328, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0118348598480225, "global_step": 515329, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0343434810638428, "global_step": 515330, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.099699020385742, "global_step": 515331, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.038949966430664, "global_step": 515332, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0462093353271484, "global_step": 515333, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.057620048522949, "global_step": 515334, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0621707439422607, "global_step": 515335, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0492095947265625, "global_step": 515336, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.120518684387207, "global_step": 515337, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.07985520362854, "global_step": 515338, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9814249277114868, "global_step": 515339, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.068080186843872, "global_step": 515340, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.123647689819336, "global_step": 515341, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.993489146232605, "global_step": 515342, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9927992820739746, "global_step": 515343, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.036134958267212, "global_step": 515344, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0050957202911377, "global_step": 515345, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.968043565750122, "global_step": 515346, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.916696548461914, "global_step": 515347, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9710816144943237, "global_step": 515348, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.034334659576416, "global_step": 515349, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0254783630371094, "global_step": 515350, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.056269884109497, "global_step": 515351, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9822965860366821, "global_step": 515352, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.044940710067749, "global_step": 515353, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.017761707305908, "global_step": 515354, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9663947820663452, "global_step": 515355, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0067460536956787, "global_step": 515356, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9929152727127075, "global_step": 515357, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0835354328155518, "global_step": 515358, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.064018964767456, "global_step": 515359, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0501062870025635, "global_step": 515360, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1321098804473877, "global_step": 515361, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9885174036026, "global_step": 515362, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0989458560943604, "global_step": 515363, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.025495767593384, "global_step": 515364, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9772132635116577, "global_step": 515365, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0021917819976807, "global_step": 515366, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0634233951568604, "global_step": 515367, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0702905654907227, "global_step": 515368, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9696640968322754, "global_step": 515369, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.108171224594116, "global_step": 515370, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9976215362548828, "global_step": 515371, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1050148010253906, "global_step": 515372, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.095227003097534, "global_step": 515373, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0950896739959717, "global_step": 515374, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0810937881469727, "global_step": 515375, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.015281915664673, "global_step": 515376, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.039053440093994, "global_step": 515377, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0629162788391113, "global_step": 515378, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.048896312713623, "global_step": 515379, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.021557331085205, "global_step": 515380, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0464601516723633, "global_step": 515381, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0425708293914795, "global_step": 515382, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1007776260375977, "global_step": 515383, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.042764902114868, "global_step": 515384, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.165745258331299, "global_step": 515385, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0656893253326416, "global_step": 515386, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0704774856567383, "global_step": 515387, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0492873191833496, "global_step": 515388, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.055333137512207, "global_step": 515389, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0755672454833984, "global_step": 515390, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0299577713012695, "global_step": 515391, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1155505180358887, "global_step": 515392, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.014691114425659, "global_step": 515393, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9685577154159546, "global_step": 515394, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9995324611663818, "global_step": 515395, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0114901065826416, "global_step": 515396, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0425546169281006, "global_step": 515397, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0750060081481934, "global_step": 515398, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0091283321380615, "global_step": 515399, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0563106536865234, "global_step": 515400, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0618700981140137, "global_step": 515401, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.068129062652588, "global_step": 515402, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9966671466827393, "global_step": 515403, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.073460578918457, "global_step": 515404, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1483328342437744, "global_step": 515405, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1246659755706787, "global_step": 515406, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.091827630996704, "global_step": 515407, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.025658130645752, "global_step": 515408, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0193846225738525, "global_step": 515409, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0344924926757812, "global_step": 515410, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.040178060531616, "global_step": 515411, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.069149971008301, "global_step": 515412, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0466909408569336, "global_step": 515413, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0405824184417725, "global_step": 515414, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0932135581970215, "global_step": 515415, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1019530296325684, "global_step": 515416, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0378756523132324, "global_step": 515417, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.060739755630493, "global_step": 515418, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.069427967071533, "global_step": 515419, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0339832305908203, "global_step": 515420, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0486810207366943, "global_step": 515421, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1088054180145264, "global_step": 515422, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1072490215301514, "global_step": 515423, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.026737928390503, "global_step": 515424, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.08931303024292, "global_step": 515425, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.004106283187866, "global_step": 515426, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.161423921585083, "global_step": 515427, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.042888641357422, "global_step": 515428, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0090084075927734, "global_step": 515429, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.032114267349243, "global_step": 515430, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0395171642303467, "global_step": 515431, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.091538190841675, "global_step": 515432, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0331921577453613, "global_step": 515433, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9451584815979004, "global_step": 515434, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.070944309234619, "global_step": 515435, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.033134937286377, "global_step": 515436, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0593104362487793, "global_step": 515437, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0817182064056396, "global_step": 515438, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1807098388671875, "global_step": 515439, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0281405448913574, "global_step": 515440, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0144193172454834, "global_step": 515441, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9960848093032837, "global_step": 515442, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1719272136688232, "global_step": 515443, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.019412040710449, "global_step": 515444, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9930673837661743, "global_step": 515445, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0732903480529785, "global_step": 515446, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.120011329650879, "global_step": 515447, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0604114532470703, "global_step": 515448, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0771522521972656, "global_step": 515449, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0309548377990723, "global_step": 515450, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0326247215270996, "global_step": 515451, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0436644554138184, "global_step": 515452, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.046780586242676, "global_step": 515453, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0058341026306152, "global_step": 515454, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0089049339294434, "global_step": 515455, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0077648162841797, "global_step": 515456, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9387495517730713, "global_step": 515457, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0647058486938477, "global_step": 515458, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.063498020172119, "global_step": 515459, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.097393035888672, "global_step": 515460, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.000396728515625, "global_step": 515461, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.078648567199707, "global_step": 515462, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1024117469787598, "global_step": 515463, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0741207599639893, "global_step": 515464, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0909197330474854, "global_step": 515465, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.131734609603882, "global_step": 515466, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0694596767425537, "global_step": 515467, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0788211822509766, "global_step": 515468, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.100724220275879, "global_step": 515469, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0670316219329834, "global_step": 515470, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0499234199523926, "global_step": 515471, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9894424676895142, "global_step": 515472, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.94333815574646, "global_step": 515473, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.049415111541748, "global_step": 515474, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.067194938659668, "global_step": 515475, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.043811082839966, "global_step": 515476, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9964649677276611, "global_step": 515477, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0738487243652344, "global_step": 515478, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1277692317962646, "global_step": 515479, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1107959747314453, "global_step": 515480, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9950330257415771, "global_step": 515481, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.064940929412842, "global_step": 515482, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.033565044403076, "global_step": 515483, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.115251064300537, "global_step": 515484, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.006115436553955, "global_step": 515485, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.060964345932007, "global_step": 515486, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0351481437683105, "global_step": 515487, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.024374485015869, "global_step": 515488, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0620877742767334, "global_step": 515489, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9605387449264526, "global_step": 515490, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0185723304748535, "global_step": 515491, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0866518020629883, "global_step": 515492, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0133917331695557, "global_step": 515493, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.018906831741333, "global_step": 515494, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0803003311157227, "global_step": 515495, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0905871391296387, "global_step": 515496, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1646127700805664, "global_step": 515497, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0944440364837646, "global_step": 515498, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.999047040939331, "global_step": 515499, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9817454814910889, "global_step": 515500, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9547619819641113, "global_step": 515501, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.084113121032715, "global_step": 515502, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0573208332061768, "global_step": 515503, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.044318199157715, "global_step": 515504, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.047116994857788, "global_step": 515505, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0739223957061768, "global_step": 515506, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0377676486968994, "global_step": 515507, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0559420585632324, "global_step": 515508, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0461182594299316, "global_step": 515509, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.962436318397522, "global_step": 515510, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.024590253829956, "global_step": 515511, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.044285535812378, "global_step": 515512, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.003627061843872, "global_step": 515513, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.97553551197052, "global_step": 515514, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0230886936187744, "global_step": 515515, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1303510665893555, "global_step": 515516, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0856661796569824, "global_step": 515517, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1066505908966064, "global_step": 515518, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0520715713500977, "global_step": 515519, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9780160188674927, "global_step": 515520, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.030442476272583, "global_step": 515521, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0755724906921387, "global_step": 515522, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0018157958984375, "global_step": 515523, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.080655336380005, "global_step": 515524, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0789477825164795, "global_step": 515525, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9699078798294067, "global_step": 515526, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.050471067428589, "global_step": 515527, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.038487434387207, "global_step": 515528, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0371639728546143, "global_step": 515529, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0929722785949707, "global_step": 515530, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.020131826400757, "global_step": 515531, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.081052541732788, "global_step": 515532, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0573394298553467, "global_step": 515533, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.056795120239258, "global_step": 515534, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.996151089668274, "global_step": 515535, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9790847301483154, "global_step": 515536, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.008629083633423, "global_step": 515537, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1079559326171875, "global_step": 515538, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0741939544677734, "global_step": 515539, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1365251541137695, "global_step": 515540, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.078589677810669, "global_step": 515541, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0927906036376953, "global_step": 515542, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.992714524269104, "global_step": 515543, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.007561206817627, "global_step": 515544, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0870018005371094, "global_step": 515545, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0133793354034424, "global_step": 515546, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.011620283126831, "global_step": 515547, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1273603439331055, "global_step": 515548, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0473122596740723, "global_step": 515549, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0198137760162354, "global_step": 515550, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0678369998931885, "global_step": 515551, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.086456060409546, "global_step": 515552, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0543346405029297, "global_step": 515553, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.024749755859375, "global_step": 515554, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.059037446975708, "global_step": 515555, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0665283203125, "global_step": 515556, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0598371028900146, "global_step": 515557, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.067643165588379, "global_step": 515558, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.056004285812378, "global_step": 515559, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0950751304626465, "global_step": 515560, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.124976634979248, "global_step": 515561, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0295040607452393, "global_step": 515562, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.029327154159546, "global_step": 515563, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0265769958496094, "global_step": 515564, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9409229755401611, "global_step": 515565, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.021501302719116, "global_step": 515566, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0690317153930664, "global_step": 515567, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.117745876312256, "global_step": 515568, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.007298707962036, "global_step": 515569, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.069992780685425, "global_step": 515570, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.140382766723633, "global_step": 515571, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0307538509368896, "global_step": 515572, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.062122106552124, "global_step": 515573, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.06241774559021, "global_step": 515574, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.022055149078369, "global_step": 515575, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0347423553466797, "global_step": 515576, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.084613561630249, "global_step": 515577, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1074702739715576, "global_step": 515578, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.132603645324707, "global_step": 515579, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.138976812362671, "global_step": 515580, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9808233976364136, "global_step": 515581, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0876801013946533, "global_step": 515582, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0589799880981445, "global_step": 515583, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0722081661224365, "global_step": 515584, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9971644878387451, "global_step": 515585, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.04130220413208, "global_step": 515586, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0254344940185547, "global_step": 515587, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1006453037261963, "global_step": 515588, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0494143962860107, "global_step": 515589, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0806884765625, "global_step": 515590, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0110552310943604, "global_step": 515591, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0795979499816895, "global_step": 515592, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9951627254486084, "global_step": 515593, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0998942852020264, "global_step": 515594, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0431108474731445, "global_step": 515595, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.043074369430542, "global_step": 515596, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0797624588012695, "global_step": 515597, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9859371185302734, "global_step": 515598, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1171462535858154, "global_step": 515599, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.104099988937378, "global_step": 515600, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0531318187713623, "global_step": 515601, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0973620414733887, "global_step": 515602, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0544590950012207, "global_step": 515603, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.024686336517334, "global_step": 515604, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0794951915740967, "global_step": 515605, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0472898483276367, "global_step": 515606, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.959067463874817, "global_step": 515607, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9819836616516113, "global_step": 515608, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.040316343307495, "global_step": 515609, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9885326623916626, "global_step": 515610, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0917305946350098, "global_step": 515611, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0088460445404053, "global_step": 515612, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0426244735717773, "global_step": 515613, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.022277355194092, "global_step": 515614, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0910727977752686, "global_step": 515615, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0879645347595215, "global_step": 515616, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9936857223510742, "global_step": 515617, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.052461862564087, "global_step": 515618, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.06892728805542, "global_step": 515619, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0791730880737305, "global_step": 515620, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0602352619171143, "global_step": 515621, "epoch": 881, "lr": 5e-05}
{"train_loss": 1.9987256526947021, "global_step": 515622, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.068956136703491, "global_step": 515623, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.112647771835327, "global_step": 515624, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0261058807373047, "global_step": 515625, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0668129920959473, "global_step": 515626, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.143235683441162, "global_step": 515627, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0189974308013916, "global_step": 515628, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.030233860015869, "global_step": 515629, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.017899751663208, "global_step": 515630, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.1823320388793945, "global_step": 515631, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.109717845916748, "global_step": 515632, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.016895294189453, "global_step": 515633, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.069389581680298, "global_step": 515634, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0153379440307617, "global_step": 515635, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0682432651519775, "global_step": 515636, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0146634578704834, "global_step": 515637, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.047024965286255, "global_step": 515638, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0547878742218018, "global_step": 515639, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.0443050861358643, "global_step": 515640, "epoch": 881, "lr": 5e-05}
{"train_loss": 2.052595853805542, "global_step": 515641, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.021587610244751, "global_step": 515642, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0252366065979004, "global_step": 515643, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0676114559173584, "global_step": 515644, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9590709209442139, "global_step": 515645, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0955300331115723, "global_step": 515646, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0888500213623047, "global_step": 515647, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9691110849380493, "global_step": 515648, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0314342975616455, "global_step": 515649, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0383036136627197, "global_step": 515650, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9979227781295776, "global_step": 515651, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9399467706680298, "global_step": 515652, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1666834354400635, "global_step": 515653, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.147580146789551, "global_step": 515654, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0434622764587402, "global_step": 515655, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0378236770629883, "global_step": 515656, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.004457712173462, "global_step": 515657, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9480210542678833, "global_step": 515658, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.097194194793701, "global_step": 515659, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0724825859069824, "global_step": 515660, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9378787279129028, "global_step": 515661, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0443694591522217, "global_step": 515662, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9565273523330688, "global_step": 515663, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0550780296325684, "global_step": 515664, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0175673961639404, "global_step": 515665, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0998852252960205, "global_step": 515666, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9978549480438232, "global_step": 515667, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.05979323387146, "global_step": 515668, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0419065952301025, "global_step": 515669, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.051011800765991, "global_step": 515670, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.00260853767395, "global_step": 515671, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9531224966049194, "global_step": 515672, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9882668256759644, "global_step": 515673, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1009724140167236, "global_step": 515674, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.072272777557373, "global_step": 515675, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.049199104309082, "global_step": 515676, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.130743980407715, "global_step": 515677, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0445168018341064, "global_step": 515678, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0311334133148193, "global_step": 515679, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0786893367767334, "global_step": 515680, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0301854610443115, "global_step": 515681, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1106607913970947, "global_step": 515682, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.056422472000122, "global_step": 515683, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.08015775680542, "global_step": 515684, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.083805799484253, "global_step": 515685, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1151938438415527, "global_step": 515686, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1169545650482178, "global_step": 515687, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.11856746673584, "global_step": 515688, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.127912759780884, "global_step": 515689, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0340332984924316, "global_step": 515690, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0403897762298584, "global_step": 515691, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9030171632766724, "global_step": 515692, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0717527866363525, "global_step": 515693, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9940835237503052, "global_step": 515694, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9857779741287231, "global_step": 515695, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0565314292907715, "global_step": 515696, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0498955249786377, "global_step": 515697, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9688035249710083, "global_step": 515698, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.030165910720825, "global_step": 515699, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.151369094848633, "global_step": 515700, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0426876544952393, "global_step": 515701, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1018002033233643, "global_step": 515702, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.035823106765747, "global_step": 515703, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.963364601135254, "global_step": 515704, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0601940155029297, "global_step": 515705, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9522409439086914, "global_step": 515706, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.025416135787964, "global_step": 515707, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9951962232589722, "global_step": 515708, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.049612283706665, "global_step": 515709, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0348644256591797, "global_step": 515710, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9440444707870483, "global_step": 515711, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0922679901123047, "global_step": 515712, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1294186115264893, "global_step": 515713, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0224432945251465, "global_step": 515714, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.075092315673828, "global_step": 515715, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9910467863082886, "global_step": 515716, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.083281993865967, "global_step": 515717, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.06325626373291, "global_step": 515718, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.020554542541504, "global_step": 515719, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9808064699172974, "global_step": 515720, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0612900257110596, "global_step": 515721, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0908358097076416, "global_step": 515722, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0646209716796875, "global_step": 515723, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.8763012886047363, "global_step": 515724, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.043863296508789, "global_step": 515725, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.016569137573242, "global_step": 515726, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9988133907318115, "global_step": 515727, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.098388910293579, "global_step": 515728, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1111412048339844, "global_step": 515729, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.084662437438965, "global_step": 515730, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0822956562042236, "global_step": 515731, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0779988765716553, "global_step": 515732, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0721962451934814, "global_step": 515733, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0747005939483643, "global_step": 515734, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0600788593292236, "global_step": 515735, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.022956371307373, "global_step": 515736, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9986436367034912, "global_step": 515737, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0205202102661133, "global_step": 515738, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9741101264953613, "global_step": 515739, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0324885845184326, "global_step": 515740, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.068523406982422, "global_step": 515741, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0744807720184326, "global_step": 515742, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0103371143341064, "global_step": 515743, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0320489406585693, "global_step": 515744, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9774682521820068, "global_step": 515745, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0782196521759033, "global_step": 515746, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9960492849349976, "global_step": 515747, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0412704944610596, "global_step": 515748, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.086817502975464, "global_step": 515749, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.904988169670105, "global_step": 515750, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0931296348571777, "global_step": 515751, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0228073596954346, "global_step": 515752, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.016451120376587, "global_step": 515753, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0920653343200684, "global_step": 515754, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0181376934051514, "global_step": 515755, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.111571788787842, "global_step": 515756, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9993793964385986, "global_step": 515757, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9685335159301758, "global_step": 515758, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0163609981536865, "global_step": 515759, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9888169765472412, "global_step": 515760, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.000321626663208, "global_step": 515761, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0340609550476074, "global_step": 515762, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0557637214660645, "global_step": 515763, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.980651617050171, "global_step": 515764, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0093395709991455, "global_step": 515765, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0038485527038574, "global_step": 515766, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0357115268707275, "global_step": 515767, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.083885908126831, "global_step": 515768, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0150277614593506, "global_step": 515769, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0646541118621826, "global_step": 515770, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1355156898498535, "global_step": 515771, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0735630989074707, "global_step": 515772, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0799272060394287, "global_step": 515773, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0234198570251465, "global_step": 515774, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9785797595977783, "global_step": 515775, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9943586587905884, "global_step": 515776, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.8745918273925781, "global_step": 515777, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.061272382736206, "global_step": 515778, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0356223583221436, "global_step": 515779, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1002583503723145, "global_step": 515780, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.028229236602783, "global_step": 515781, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.11645245552063, "global_step": 515782, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1208608150482178, "global_step": 515783, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.137756586074829, "global_step": 515784, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.045732021331787, "global_step": 515785, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.064594030380249, "global_step": 515786, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.047912836074829, "global_step": 515787, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.090914487838745, "global_step": 515788, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1207995414733887, "global_step": 515789, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0890393257141113, "global_step": 515790, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.012119770050049, "global_step": 515791, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.036454677581787, "global_step": 515792, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9625800848007202, "global_step": 515793, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.039149522781372, "global_step": 515794, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1011011600494385, "global_step": 515795, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0745961666107178, "global_step": 515796, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0572760105133057, "global_step": 515797, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.002213954925537, "global_step": 515798, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9993975162506104, "global_step": 515799, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.936098575592041, "global_step": 515800, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0704948902130127, "global_step": 515801, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1281518936157227, "global_step": 515802, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.024606943130493, "global_step": 515803, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0516891479492188, "global_step": 515804, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.053508996963501, "global_step": 515805, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0402932167053223, "global_step": 515806, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.060523509979248, "global_step": 515807, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0782158374786377, "global_step": 515808, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1101396083831787, "global_step": 515809, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0456790924072266, "global_step": 515810, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9813412427902222, "global_step": 515811, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0387163162231445, "global_step": 515812, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9431897401809692, "global_step": 515813, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9981802701950073, "global_step": 515814, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0740528106689453, "global_step": 515815, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.042710065841675, "global_step": 515816, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.001490831375122, "global_step": 515817, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0427889823913574, "global_step": 515818, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.058062791824341, "global_step": 515819, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0906848907470703, "global_step": 515820, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1072723865509033, "global_step": 515821, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.009427309036255, "global_step": 515822, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1003260612487793, "global_step": 515823, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.034433603286743, "global_step": 515824, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.038409948348999, "global_step": 515825, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1488358974456787, "global_step": 515826, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.110050916671753, "global_step": 515827, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.174607753753662, "global_step": 515828, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9573646783828735, "global_step": 515829, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.082411289215088, "global_step": 515830, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0415866374969482, "global_step": 515831, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0214931964874268, "global_step": 515832, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9605011940002441, "global_step": 515833, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0858566761016846, "global_step": 515834, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.067577362060547, "global_step": 515835, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.063021659851074, "global_step": 515836, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.02437162399292, "global_step": 515837, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.996382474899292, "global_step": 515838, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9762051105499268, "global_step": 515839, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.054750442504883, "global_step": 515840, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0657973289489746, "global_step": 515841, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0539796352386475, "global_step": 515842, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.026101589202881, "global_step": 515843, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0406832695007324, "global_step": 515844, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0019428730010986, "global_step": 515845, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9766287803649902, "global_step": 515846, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.004692554473877, "global_step": 515847, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.077728271484375, "global_step": 515848, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0368282794952393, "global_step": 515849, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9827549457550049, "global_step": 515850, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1204745769500732, "global_step": 515851, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.058384418487549, "global_step": 515852, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.098559856414795, "global_step": 515853, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.059013843536377, "global_step": 515854, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.093501329421997, "global_step": 515855, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.967588186264038, "global_step": 515856, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.037090301513672, "global_step": 515857, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0173325538635254, "global_step": 515858, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9811270236968994, "global_step": 515859, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1530280113220215, "global_step": 515860, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9435782432556152, "global_step": 515861, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0587410926818848, "global_step": 515862, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.151930809020996, "global_step": 515863, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0440759658813477, "global_step": 515864, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0407931804656982, "global_step": 515865, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0211844444274902, "global_step": 515866, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.105318307876587, "global_step": 515867, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.062723398208618, "global_step": 515868, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0136375427246094, "global_step": 515869, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1460232734680176, "global_step": 515870, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.052325487136841, "global_step": 515871, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.111295223236084, "global_step": 515872, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0157980918884277, "global_step": 515873, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9916179180145264, "global_step": 515874, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0180797576904297, "global_step": 515875, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0502943992614746, "global_step": 515876, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.102407932281494, "global_step": 515877, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0931622982025146, "global_step": 515878, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.09346342086792, "global_step": 515879, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.077528953552246, "global_step": 515880, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1257026195526123, "global_step": 515881, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0136396884918213, "global_step": 515882, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0442538261413574, "global_step": 515883, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.020742177963257, "global_step": 515884, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9961851835250854, "global_step": 515885, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.040468692779541, "global_step": 515886, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0781869888305664, "global_step": 515887, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9146747589111328, "global_step": 515888, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0401618480682373, "global_step": 515889, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0684561729431152, "global_step": 515890, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0155487060546875, "global_step": 515891, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0884642601013184, "global_step": 515892, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9629026651382446, "global_step": 515893, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0853805541992188, "global_step": 515894, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1595089435577393, "global_step": 515895, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9980530738830566, "global_step": 515896, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9447576999664307, "global_step": 515897, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.062734603881836, "global_step": 515898, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0389528274536133, "global_step": 515899, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0996344089508057, "global_step": 515900, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0764245986938477, "global_step": 515901, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0163254737854004, "global_step": 515902, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.053196668624878, "global_step": 515903, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.018261194229126, "global_step": 515904, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.002272844314575, "global_step": 515905, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9869606494903564, "global_step": 515906, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.995548129081726, "global_step": 515907, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0254218578338623, "global_step": 515908, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0051541328430176, "global_step": 515909, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0605435371398926, "global_step": 515910, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9891581535339355, "global_step": 515911, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1005914211273193, "global_step": 515912, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.092319965362549, "global_step": 515913, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.074100971221924, "global_step": 515914, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0223164558410645, "global_step": 515915, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.932093620300293, "global_step": 515916, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0279836654663086, "global_step": 515917, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0371851921081543, "global_step": 515918, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.983629822731018, "global_step": 515919, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0261566638946533, "global_step": 515920, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.967644453048706, "global_step": 515921, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.005415201187134, "global_step": 515922, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0413715839385986, "global_step": 515923, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0667459964752197, "global_step": 515924, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.145451784133911, "global_step": 515925, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9885584115982056, "global_step": 515926, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9832994937896729, "global_step": 515927, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0404248237609863, "global_step": 515928, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.039236545562744, "global_step": 515929, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0115559101104736, "global_step": 515930, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1064417362213135, "global_step": 515931, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9933348894119263, "global_step": 515932, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.027959108352661, "global_step": 515933, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.104288101196289, "global_step": 515934, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.057190179824829, "global_step": 515935, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9712971448898315, "global_step": 515936, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9998449087142944, "global_step": 515937, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0036282539367676, "global_step": 515938, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0687179565429688, "global_step": 515939, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0317373275756836, "global_step": 515940, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0275719165802, "global_step": 515941, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0275588035583496, "global_step": 515942, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0522119998931885, "global_step": 515943, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9667282104492188, "global_step": 515944, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.026081085205078, "global_step": 515945, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.12321138381958, "global_step": 515946, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.07546067237854, "global_step": 515947, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1411540508270264, "global_step": 515948, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9586148262023926, "global_step": 515949, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0202505588531494, "global_step": 515950, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0255603790283203, "global_step": 515951, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0079424381256104, "global_step": 515952, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.015320301055908, "global_step": 515953, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.093017578125, "global_step": 515954, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0398991107940674, "global_step": 515955, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9727009534835815, "global_step": 515956, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.001856803894043, "global_step": 515957, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.106806755065918, "global_step": 515958, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0000271797180176, "global_step": 515959, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.028773546218872, "global_step": 515960, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9329701662063599, "global_step": 515961, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.076784372329712, "global_step": 515962, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.047361135482788, "global_step": 515963, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9885787963867188, "global_step": 515964, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1056628227233887, "global_step": 515965, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0353293418884277, "global_step": 515966, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0103180408477783, "global_step": 515967, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0562660694122314, "global_step": 515968, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.072415828704834, "global_step": 515969, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9861516952514648, "global_step": 515970, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.002793312072754, "global_step": 515971, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9714711904525757, "global_step": 515972, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.031442642211914, "global_step": 515973, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9711651802062988, "global_step": 515974, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0088393688201904, "global_step": 515975, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.092207908630371, "global_step": 515976, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.000962734222412, "global_step": 515977, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0741798877716064, "global_step": 515978, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.007471799850464, "global_step": 515979, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.042956590652466, "global_step": 515980, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.071540117263794, "global_step": 515981, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1041905879974365, "global_step": 515982, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0683419704437256, "global_step": 515983, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0643301010131836, "global_step": 515984, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.102839231491089, "global_step": 515985, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.020792007446289, "global_step": 515986, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0539324283599854, "global_step": 515987, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.006079912185669, "global_step": 515988, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9939491748809814, "global_step": 515989, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9710999727249146, "global_step": 515990, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9907615184783936, "global_step": 515991, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.082387685775757, "global_step": 515992, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.057119846343994, "global_step": 515993, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.976619005203247, "global_step": 515994, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0291717052459717, "global_step": 515995, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.017914056777954, "global_step": 515996, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0412118434906006, "global_step": 515997, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.005471706390381, "global_step": 515998, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0117993354797363, "global_step": 515999, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9890252351760864, "global_step": 516000, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.231397867202759, "global_step": 516001, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0360469818115234, "global_step": 516002, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9688106775283813, "global_step": 516003, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0505433082580566, "global_step": 516004, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.050179958343506, "global_step": 516005, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.028696298599243, "global_step": 516006, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9862964153289795, "global_step": 516007, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0814409255981445, "global_step": 516008, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.074425220489502, "global_step": 516009, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.968026876449585, "global_step": 516010, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.066958427429199, "global_step": 516011, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0477499961853027, "global_step": 516012, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0556228160858154, "global_step": 516013, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.052241563796997, "global_step": 516014, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1057779788970947, "global_step": 516015, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0228729248046875, "global_step": 516016, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9796721935272217, "global_step": 516017, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0920612812042236, "global_step": 516018, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0580990314483643, "global_step": 516019, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1424267292022705, "global_step": 516020, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.065608024597168, "global_step": 516021, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1042754650115967, "global_step": 516022, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.031301498413086, "global_step": 516023, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0765483379364014, "global_step": 516024, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.054516077041626, "global_step": 516025, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0170321464538574, "global_step": 516026, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0043225288391113, "global_step": 516027, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9236656427383423, "global_step": 516028, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0488293170928955, "global_step": 516029, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.957694411277771, "global_step": 516030, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0155861377716064, "global_step": 516031, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0215096473693848, "global_step": 516032, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.070615530014038, "global_step": 516033, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.05582857131958, "global_step": 516034, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.161431074142456, "global_step": 516035, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.967197299003601, "global_step": 516036, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0652174949645996, "global_step": 516037, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0780868530273438, "global_step": 516038, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.028663158416748, "global_step": 516039, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.079728603363037, "global_step": 516040, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.114647388458252, "global_step": 516041, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0197842121124268, "global_step": 516042, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0549910068511963, "global_step": 516043, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0730717182159424, "global_step": 516044, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.046137809753418, "global_step": 516045, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0563607215881348, "global_step": 516046, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0402650833129883, "global_step": 516047, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1291019916534424, "global_step": 516048, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.993597388267517, "global_step": 516049, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.04905104637146, "global_step": 516050, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.037390947341919, "global_step": 516051, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0851495265960693, "global_step": 516052, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0279595851898193, "global_step": 516053, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0434961318969727, "global_step": 516054, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.07631778717041, "global_step": 516055, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0073366165161133, "global_step": 516056, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.097796678543091, "global_step": 516057, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0271244049072266, "global_step": 516058, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0659186840057373, "global_step": 516059, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.091935873031616, "global_step": 516060, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.023298978805542, "global_step": 516061, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9861022233963013, "global_step": 516062, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0487778186798096, "global_step": 516063, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1677095890045166, "global_step": 516064, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.088637351989746, "global_step": 516065, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1024622917175293, "global_step": 516066, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.071288585662842, "global_step": 516067, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.037628412246704, "global_step": 516068, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1115341186523438, "global_step": 516069, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9834671020507812, "global_step": 516070, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0228896141052246, "global_step": 516071, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.166989803314209, "global_step": 516072, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0001158714294434, "global_step": 516073, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1462972164154053, "global_step": 516074, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9826022386550903, "global_step": 516075, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.035507917404175, "global_step": 516076, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.081437826156616, "global_step": 516077, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0003561973571777, "global_step": 516078, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9839168787002563, "global_step": 516079, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9964464902877808, "global_step": 516080, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.029755115509033, "global_step": 516081, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.131788969039917, "global_step": 516082, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.045194149017334, "global_step": 516083, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0140483379364014, "global_step": 516084, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0464892387390137, "global_step": 516085, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0795676708221436, "global_step": 516086, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.029758930206299, "global_step": 516087, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.054471015930176, "global_step": 516088, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0567214488983154, "global_step": 516089, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.029198169708252, "global_step": 516090, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0442728996276855, "global_step": 516091, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.116177797317505, "global_step": 516092, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0102078914642334, "global_step": 516093, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0414700508117676, "global_step": 516094, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.005455255508423, "global_step": 516095, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0941388607025146, "global_step": 516096, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0444185733795166, "global_step": 516097, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.04301118850708, "global_step": 516098, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0645387172698975, "global_step": 516099, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0457067489624023, "global_step": 516100, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.142488956451416, "global_step": 516101, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1115596294403076, "global_step": 516102, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9928933382034302, "global_step": 516103, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.111212730407715, "global_step": 516104, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0817158222198486, "global_step": 516105, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.031500816345215, "global_step": 516106, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0620217323303223, "global_step": 516107, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0246269702911377, "global_step": 516108, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.037508249282837, "global_step": 516109, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.028578042984009, "global_step": 516110, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0216915607452393, "global_step": 516111, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.039754867553711, "global_step": 516112, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0849454402923584, "global_step": 516113, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0483412742614746, "global_step": 516114, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1030571460723877, "global_step": 516115, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.034066677093506, "global_step": 516116, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.039422035217285, "global_step": 516117, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.009699583053589, "global_step": 516118, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.102992296218872, "global_step": 516119, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0687096118927, "global_step": 516120, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0685853958129883, "global_step": 516121, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.064722776412964, "global_step": 516122, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0186233520507812, "global_step": 516123, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1012682914733887, "global_step": 516124, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9498001337051392, "global_step": 516125, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.027325391769409, "global_step": 516126, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0253775119781494, "global_step": 516127, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.077646017074585, "global_step": 516128, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0840067863464355, "global_step": 516129, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0235025882720947, "global_step": 516130, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0807712078094482, "global_step": 516131, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0984597206115723, "global_step": 516132, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0133016109466553, "global_step": 516133, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.098151683807373, "global_step": 516134, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.976335883140564, "global_step": 516135, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9576013088226318, "global_step": 516136, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.941250205039978, "global_step": 516137, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0702311992645264, "global_step": 516138, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.082185745239258, "global_step": 516139, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0855770111083984, "global_step": 516140, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.031653642654419, "global_step": 516141, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0896244049072266, "global_step": 516142, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.095815420150757, "global_step": 516143, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0584065914154053, "global_step": 516144, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.029741048812866, "global_step": 516145, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.183598518371582, "global_step": 516146, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.039400339126587, "global_step": 516147, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0947659015655518, "global_step": 516148, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0766472816467285, "global_step": 516149, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.043341875076294, "global_step": 516150, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.075986623764038, "global_step": 516151, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0186054706573486, "global_step": 516152, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.048713207244873, "global_step": 516153, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0036604404449463, "global_step": 516154, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9900857210159302, "global_step": 516155, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.117540121078491, "global_step": 516156, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0963587760925293, "global_step": 516157, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0937230587005615, "global_step": 516158, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1282970905303955, "global_step": 516159, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0624966621398926, "global_step": 516160, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1279196739196777, "global_step": 516161, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.99866783618927, "global_step": 516162, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0467469692230225, "global_step": 516163, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.026045322418213, "global_step": 516164, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0901694297790527, "global_step": 516165, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.053377389907837, "global_step": 516166, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0654423236846924, "global_step": 516167, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1183884143829346, "global_step": 516168, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.060293197631836, "global_step": 516169, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9880266189575195, "global_step": 516170, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1279428005218506, "global_step": 516171, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0427303314208984, "global_step": 516172, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.05299711227417, "global_step": 516173, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.049149513244629, "global_step": 516174, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.038165330886841, "global_step": 516175, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1857850551605225, "global_step": 516176, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.04097318649292, "global_step": 516177, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.102839231491089, "global_step": 516178, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0516066551208496, "global_step": 516179, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0204503536224365, "global_step": 516180, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0149495601654053, "global_step": 516181, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0237908363342285, "global_step": 516182, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.068582534790039, "global_step": 516183, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.015444278717041, "global_step": 516184, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0151939392089844, "global_step": 516185, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0794873237609863, "global_step": 516186, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.134509325027466, "global_step": 516187, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.103245496749878, "global_step": 516188, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0545763969421387, "global_step": 516189, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0433359146118164, "global_step": 516190, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.108811616897583, "global_step": 516191, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0218381881713867, "global_step": 516192, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0503716468811035, "global_step": 516193, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1118645668029785, "global_step": 516194, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0694739818573, "global_step": 516195, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0849287509918213, "global_step": 516196, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.934984564781189, "global_step": 516197, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0932605266571045, "global_step": 516198, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0361268520355225, "global_step": 516199, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.991307258605957, "global_step": 516200, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0497310161590576, "global_step": 516201, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.976033091545105, "global_step": 516202, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0392162799835205, "global_step": 516203, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.079590082168579, "global_step": 516204, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.010897159576416, "global_step": 516205, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.050678014755249, "global_step": 516206, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0533790588378906, "global_step": 516207, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.995895504951477, "global_step": 516208, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0398502349853516, "global_step": 516209, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0100107192993164, "global_step": 516210, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.038801670074463, "global_step": 516211, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.015632390975952, "global_step": 516212, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1050045490264893, "global_step": 516213, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9839816093444824, "global_step": 516214, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.000983953475952, "global_step": 516215, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.077582836151123, "global_step": 516216, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1353533267974854, "global_step": 516217, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0060906410217285, "global_step": 516218, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0935776233673096, "global_step": 516219, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0585808753967285, "global_step": 516220, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.014354705810547, "global_step": 516221, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1047470569610596, "global_step": 516222, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.077967405319214, "global_step": 516223, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0234475135803223, "global_step": 516224, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0214014053344727, "global_step": 516225, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1081528663635254, "global_step": 516226, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0580668449401855, "global_step": 516227, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1162924766540527, "global_step": 516228, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.111701250076294, "global_step": 516229, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0781962871551514, "global_step": 516230, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.088536024093628, "global_step": 516231, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1184072494506836, "global_step": 516232, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.012810468673706, "global_step": 516233, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0838284492492676, "global_step": 516234, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.15519118309021, "global_step": 516235, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.022566795349121, "global_step": 516236, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.021606922149658, "global_step": 516237, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0936572551727295, "global_step": 516238, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0493929386138916, "global_step": 516239, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0374441146850586, "global_step": 516240, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0586459636688232, "global_step": 516241, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.11598539352417, "global_step": 516242, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0618209838867188, "global_step": 516243, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.081533193588257, "global_step": 516244, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0135061740875244, "global_step": 516245, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.136125326156616, "global_step": 516246, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9476300477981567, "global_step": 516247, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0497589111328125, "global_step": 516248, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0582242012023926, "global_step": 516249, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1004414558410645, "global_step": 516250, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0639896392822266, "global_step": 516251, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.01676607131958, "global_step": 516252, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9578090906143188, "global_step": 516253, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1535520553588867, "global_step": 516254, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.034795045852661, "global_step": 516255, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.058570384979248, "global_step": 516256, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0777785778045654, "global_step": 516257, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.064032793045044, "global_step": 516258, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0494935512542725, "global_step": 516259, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0838849544525146, "global_step": 516260, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.024027109146118, "global_step": 516261, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.023017406463623, "global_step": 516262, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.033862352371216, "global_step": 516263, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1385891437530518, "global_step": 516264, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9480364322662354, "global_step": 516265, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.075904369354248, "global_step": 516266, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0790624618530273, "global_step": 516267, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.022321939468384, "global_step": 516268, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0933103561401367, "global_step": 516269, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9954257011413574, "global_step": 516270, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0668821334838867, "global_step": 516271, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0238802433013916, "global_step": 516272, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.04887056350708, "global_step": 516273, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.052067995071411, "global_step": 516274, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.024210214614868, "global_step": 516275, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1650028228759766, "global_step": 516276, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0284957885742188, "global_step": 516277, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0326995849609375, "global_step": 516278, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.074394941329956, "global_step": 516279, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0204977989196777, "global_step": 516280, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.027663230895996, "global_step": 516281, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9446663856506348, "global_step": 516282, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.038698673248291, "global_step": 516283, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.959998607635498, "global_step": 516284, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.119725227355957, "global_step": 516285, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.021092414855957, "global_step": 516286, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9940335750579834, "global_step": 516287, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9664113521575928, "global_step": 516288, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.03381085395813, "global_step": 516289, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0299620628356934, "global_step": 516290, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0791404247283936, "global_step": 516291, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.053514242172241, "global_step": 516292, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.2151849269866943, "global_step": 516293, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.040473461151123, "global_step": 516294, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0520849227905273, "global_step": 516295, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.091876983642578, "global_step": 516296, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0502474308013916, "global_step": 516297, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.052560567855835, "global_step": 516298, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0698866844177246, "global_step": 516299, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0672411918640137, "global_step": 516300, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0886571407318115, "global_step": 516301, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.035719156265259, "global_step": 516302, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.029390335083008, "global_step": 516303, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0666797161102295, "global_step": 516304, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.158292531967163, "global_step": 516305, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9609030485153198, "global_step": 516306, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.112989902496338, "global_step": 516307, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1123929023742676, "global_step": 516308, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.016418218612671, "global_step": 516309, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0136823654174805, "global_step": 516310, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0400664806365967, "global_step": 516311, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9793198108673096, "global_step": 516312, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0599186420440674, "global_step": 516313, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0922703742980957, "global_step": 516314, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0956249237060547, "global_step": 516315, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1141326427459717, "global_step": 516316, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0974466800689697, "global_step": 516317, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9822015762329102, "global_step": 516318, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.01427960395813, "global_step": 516319, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9744653701782227, "global_step": 516320, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.059070348739624, "global_step": 516321, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1319127082824707, "global_step": 516322, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0460591316223145, "global_step": 516323, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0349671840667725, "global_step": 516324, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1130762100219727, "global_step": 516325, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0630478858947754, "global_step": 516326, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0506203174591064, "global_step": 516327, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.112107753753662, "global_step": 516328, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0559914112091064, "global_step": 516329, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.050692081451416, "global_step": 516330, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0930511951446533, "global_step": 516331, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.00719952583313, "global_step": 516332, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0652577877044678, "global_step": 516333, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.019702672958374, "global_step": 516334, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1369285583496094, "global_step": 516335, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.969279408454895, "global_step": 516336, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0762805938720703, "global_step": 516337, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0063223838806152, "global_step": 516338, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1047983169555664, "global_step": 516339, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.030576229095459, "global_step": 516340, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0880820751190186, "global_step": 516341, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0486090183258057, "global_step": 516342, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.98750901222229, "global_step": 516343, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9714187383651733, "global_step": 516344, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.115102529525757, "global_step": 516345, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0119831562042236, "global_step": 516346, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.873095989227295, "global_step": 516347, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0074477195739746, "global_step": 516348, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.144242763519287, "global_step": 516349, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.031870126724243, "global_step": 516350, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0353312492370605, "global_step": 516351, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.044518232345581, "global_step": 516352, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0125956535339355, "global_step": 516353, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.085263252258301, "global_step": 516354, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0597221851348877, "global_step": 516355, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.115260362625122, "global_step": 516356, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1044068336486816, "global_step": 516357, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.017690658569336, "global_step": 516358, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.09745717048645, "global_step": 516359, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9858193397521973, "global_step": 516360, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0462958812713623, "global_step": 516361, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.016900062561035, "global_step": 516362, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.045779228210449, "global_step": 516363, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.022210121154785, "global_step": 516364, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1043701171875, "global_step": 516365, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0634560585021973, "global_step": 516366, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0006282329559326, "global_step": 516367, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9730311632156372, "global_step": 516368, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1004323959350586, "global_step": 516369, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0755228996276855, "global_step": 516370, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.033067464828491, "global_step": 516371, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9651894569396973, "global_step": 516372, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.106107234954834, "global_step": 516373, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.025820016860962, "global_step": 516374, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.041774272918701, "global_step": 516375, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.014235734939575, "global_step": 516376, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0254430770874023, "global_step": 516377, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0747814178466797, "global_step": 516378, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1460514068603516, "global_step": 516379, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.094067096710205, "global_step": 516380, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0199460983276367, "global_step": 516381, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0181326866149902, "global_step": 516382, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.107984781265259, "global_step": 516383, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0308592319488525, "global_step": 516384, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0290606021881104, "global_step": 516385, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0504372119903564, "global_step": 516386, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0045018196105957, "global_step": 516387, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0424654483795166, "global_step": 516388, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9756817817687988, "global_step": 516389, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.052838087081909, "global_step": 516390, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.000866651535034, "global_step": 516391, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.97355055809021, "global_step": 516392, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9632984399795532, "global_step": 516393, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.18476939201355, "global_step": 516394, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9979280233383179, "global_step": 516395, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1222386360168457, "global_step": 516396, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.061979293823242, "global_step": 516397, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9440958499908447, "global_step": 516398, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.066230297088623, "global_step": 516399, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.037302255630493, "global_step": 516400, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9597492218017578, "global_step": 516401, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0942299365997314, "global_step": 516402, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0774941444396973, "global_step": 516403, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0188798904418945, "global_step": 516404, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.058242082595825, "global_step": 516405, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.084824562072754, "global_step": 516406, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9741467237472534, "global_step": 516407, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0318894386291504, "global_step": 516408, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9666154384613037, "global_step": 516409, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0498359203338623, "global_step": 516410, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.104246139526367, "global_step": 516411, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0543248653411865, "global_step": 516412, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1672680377960205, "global_step": 516413, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.017951011657715, "global_step": 516414, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.027461290359497, "global_step": 516415, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0128493309020996, "global_step": 516416, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.009037733078003, "global_step": 516417, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.093902587890625, "global_step": 516418, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0118560791015625, "global_step": 516419, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.129051446914673, "global_step": 516420, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9858945608139038, "global_step": 516421, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0455315113067627, "global_step": 516422, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.053062915802002, "global_step": 516423, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.060356855392456, "global_step": 516424, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.987723708152771, "global_step": 516425, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0135538578033447, "global_step": 516426, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0345699787139893, "global_step": 516427, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.977648377418518, "global_step": 516428, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0655877590179443, "global_step": 516429, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0067481994628906, "global_step": 516430, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.988340973854065, "global_step": 516431, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.047776222229004, "global_step": 516432, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.022599458694458, "global_step": 516433, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.087951898574829, "global_step": 516434, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1002771854400635, "global_step": 516435, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.06504225730896, "global_step": 516436, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.011216640472412, "global_step": 516437, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9123659133911133, "global_step": 516438, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.080122232437134, "global_step": 516439, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.023637056350708, "global_step": 516440, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.997920274734497, "global_step": 516441, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0432169437408447, "global_step": 516442, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.10150408744812, "global_step": 516443, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0421290397644043, "global_step": 516444, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0353903770446777, "global_step": 516445, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0496628284454346, "global_step": 516446, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0102739334106445, "global_step": 516447, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.038398027420044, "global_step": 516448, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.069779872894287, "global_step": 516449, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.017726421356201, "global_step": 516450, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1524457931518555, "global_step": 516451, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.976819634437561, "global_step": 516452, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.024188280105591, "global_step": 516453, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.021033763885498, "global_step": 516454, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0304768085479736, "global_step": 516455, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1109516620635986, "global_step": 516456, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0431835651397705, "global_step": 516457, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.070890426635742, "global_step": 516458, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.041050434112549, "global_step": 516459, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0852608680725098, "global_step": 516460, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.001633882522583, "global_step": 516461, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0953898429870605, "global_step": 516462, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0488405227661133, "global_step": 516463, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0508458614349365, "global_step": 516464, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.005890130996704, "global_step": 516465, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.076544761657715, "global_step": 516466, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0798051357269287, "global_step": 516467, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1027424335479736, "global_step": 516468, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0159194469451904, "global_step": 516469, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.032007932662964, "global_step": 516470, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0889296531677246, "global_step": 516471, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0683233737945557, "global_step": 516472, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9759092330932617, "global_step": 516473, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.105872392654419, "global_step": 516474, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9684338569641113, "global_step": 516475, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9877978563308716, "global_step": 516476, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1089413166046143, "global_step": 516477, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.062314748764038, "global_step": 516478, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9470806121826172, "global_step": 516479, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0043118000030518, "global_step": 516480, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0418403148651123, "global_step": 516481, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.004772901535034, "global_step": 516482, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.074575424194336, "global_step": 516483, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0571532249450684, "global_step": 516484, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0875589847564697, "global_step": 516485, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0525898933410645, "global_step": 516486, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.063754081726074, "global_step": 516487, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0396623611450195, "global_step": 516488, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.03784441947937, "global_step": 516489, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.001024007797241, "global_step": 516490, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.060608386993408, "global_step": 516491, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.069089889526367, "global_step": 516492, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0452146530151367, "global_step": 516493, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.116370677947998, "global_step": 516494, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.08729887008667, "global_step": 516495, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0459554195404053, "global_step": 516496, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0984346866607666, "global_step": 516497, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.049842596054077, "global_step": 516498, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0374813079833984, "global_step": 516499, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9640711545944214, "global_step": 516500, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0225367546081543, "global_step": 516501, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1950185298919678, "global_step": 516502, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.110086679458618, "global_step": 516503, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0173356533050537, "global_step": 516504, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0656979084014893, "global_step": 516505, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0506880283355713, "global_step": 516506, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1063003540039062, "global_step": 516507, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1007771492004395, "global_step": 516508, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9597359895706177, "global_step": 516509, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0582566261291504, "global_step": 516510, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1046173572540283, "global_step": 516511, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9746172428131104, "global_step": 516512, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0515689849853516, "global_step": 516513, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0396347045898438, "global_step": 516514, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0266036987304688, "global_step": 516515, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9901349544525146, "global_step": 516516, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.098086357116699, "global_step": 516517, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.018467426300049, "global_step": 516518, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0702719688415527, "global_step": 516519, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.033013105392456, "global_step": 516520, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0848002433776855, "global_step": 516521, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9832797050476074, "global_step": 516522, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1022753715515137, "global_step": 516523, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0545687675476074, "global_step": 516524, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0685737133026123, "global_step": 516525, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.087556838989258, "global_step": 516526, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.063967227935791, "global_step": 516527, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0199496746063232, "global_step": 516528, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0507423877716064, "global_step": 516529, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9783363342285156, "global_step": 516530, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0086581707000732, "global_step": 516531, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.974412202835083, "global_step": 516532, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.041652202606201, "global_step": 516533, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.993166208267212, "global_step": 516534, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.074434280395508, "global_step": 516535, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0690231323242188, "global_step": 516536, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.990134596824646, "global_step": 516537, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.06986665725708, "global_step": 516538, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0302655696868896, "global_step": 516539, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0288257598876953, "global_step": 516540, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9569587707519531, "global_step": 516541, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0754826068878174, "global_step": 516542, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.069140911102295, "global_step": 516543, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0199778079986572, "global_step": 516544, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.061767101287842, "global_step": 516545, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0662224292755127, "global_step": 516546, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.032827377319336, "global_step": 516547, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0384039878845215, "global_step": 516548, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.006834030151367, "global_step": 516549, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1283576488494873, "global_step": 516550, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.06429123878479, "global_step": 516551, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.026862621307373, "global_step": 516552, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0443100929260254, "global_step": 516553, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.035248279571533, "global_step": 516554, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0601694583892822, "global_step": 516555, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.017855167388916, "global_step": 516556, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1041085720062256, "global_step": 516557, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0680758953094482, "global_step": 516558, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0719830989837646, "global_step": 516559, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0934929847717285, "global_step": 516560, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.012847661972046, "global_step": 516561, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0757358074188232, "global_step": 516562, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9856228828430176, "global_step": 516563, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1001951694488525, "global_step": 516564, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.099360704421997, "global_step": 516565, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.086743116378784, "global_step": 516566, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0355632305145264, "global_step": 516567, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0614748001098633, "global_step": 516568, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.109128952026367, "global_step": 516569, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0927011966705322, "global_step": 516570, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0588104724884033, "global_step": 516571, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0395116806030273, "global_step": 516572, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.09185791015625, "global_step": 516573, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0216495990753174, "global_step": 516574, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0940041542053223, "global_step": 516575, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0084052085876465, "global_step": 516576, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1383912563323975, "global_step": 516577, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0890064239501953, "global_step": 516578, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0142319202423096, "global_step": 516579, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0189309120178223, "global_step": 516580, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.111687421798706, "global_step": 516581, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0637612342834473, "global_step": 516582, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.068687677383423, "global_step": 516583, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1116106510162354, "global_step": 516584, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.038968801498413, "global_step": 516585, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0657145977020264, "global_step": 516586, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.185835599899292, "global_step": 516587, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.002291679382324, "global_step": 516588, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9772835969924927, "global_step": 516589, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0091676712036133, "global_step": 516590, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9841045141220093, "global_step": 516591, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0408430099487305, "global_step": 516592, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0951008796691895, "global_step": 516593, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0420374870300293, "global_step": 516594, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.078092098236084, "global_step": 516595, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.061117172241211, "global_step": 516596, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.119295120239258, "global_step": 516597, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.1095850467681885, "global_step": 516598, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.010329008102417, "global_step": 516599, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0658373832702637, "global_step": 516600, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.046854257583618, "global_step": 516601, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.062056541442871, "global_step": 516602, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0350611209869385, "global_step": 516603, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.060631275177002, "global_step": 516604, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0350849628448486, "global_step": 516605, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9557020664215088, "global_step": 516606, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0176644325256348, "global_step": 516607, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.0363166332244873, "global_step": 516608, "epoch": 882, "lr": 5e-05}
{"train_loss": 2.046812057495117, "global_step": 516609, "epoch": 882, "lr": 5e-05}
{"train_loss": 1.9995296001434326, "global_step": 516610, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9930431842803955, "global_step": 516611, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.034640312194824, "global_step": 516612, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0758440494537354, "global_step": 516613, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9995061159133911, "global_step": 516614, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.081083297729492, "global_step": 516615, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9884604215621948, "global_step": 516616, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9585272073745728, "global_step": 516617, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0264406204223633, "global_step": 516618, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0324039459228516, "global_step": 516619, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.05568528175354, "global_step": 516620, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0267550945281982, "global_step": 516621, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0267693996429443, "global_step": 516622, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1006858348846436, "global_step": 516623, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.015951156616211, "global_step": 516624, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0573501586914062, "global_step": 516625, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.127214193344116, "global_step": 516626, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0645523071289062, "global_step": 516627, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.019834041595459, "global_step": 516628, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1276040077209473, "global_step": 516629, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9753707647323608, "global_step": 516630, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1224021911621094, "global_step": 516631, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.009294271469116, "global_step": 516632, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.174975872039795, "global_step": 516633, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.011580467224121, "global_step": 516634, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9668105840682983, "global_step": 516635, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.024728298187256, "global_step": 516636, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9914823770523071, "global_step": 516637, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.095477342605591, "global_step": 516638, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9942692518234253, "global_step": 516639, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.031904458999634, "global_step": 516640, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9594124555587769, "global_step": 516641, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0285890102386475, "global_step": 516642, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0290136337280273, "global_step": 516643, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.010455846786499, "global_step": 516644, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.115215539932251, "global_step": 516645, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0125317573547363, "global_step": 516646, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0795435905456543, "global_step": 516647, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1063392162323, "global_step": 516648, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1013526916503906, "global_step": 516649, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.956136703491211, "global_step": 516650, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.119274854660034, "global_step": 516651, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0577938556671143, "global_step": 516652, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9923526048660278, "global_step": 516653, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.010514497756958, "global_step": 516654, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0094056129455566, "global_step": 516655, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.072673797607422, "global_step": 516656, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0300238132476807, "global_step": 516657, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0167152881622314, "global_step": 516658, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.063021659851074, "global_step": 516659, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0090057849884033, "global_step": 516660, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9306308031082153, "global_step": 516661, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9939885139465332, "global_step": 516662, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0650463104248047, "global_step": 516663, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.050314426422119, "global_step": 516664, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.023221731185913, "global_step": 516665, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0986180305480957, "global_step": 516666, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0513992309570312, "global_step": 516667, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.019981622695923, "global_step": 516668, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9979020357131958, "global_step": 516669, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.011645793914795, "global_step": 516670, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0691335201263428, "global_step": 516671, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.027064561843872, "global_step": 516672, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9790762662887573, "global_step": 516673, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0403859615325928, "global_step": 516674, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0272328853607178, "global_step": 516675, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.083310842514038, "global_step": 516676, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.009580373764038, "global_step": 516677, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9724347591400146, "global_step": 516678, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.928765058517456, "global_step": 516679, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0880520343780518, "global_step": 516680, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1076691150665283, "global_step": 516681, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0478954315185547, "global_step": 516682, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0381460189819336, "global_step": 516683, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.060743570327759, "global_step": 516684, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.008983612060547, "global_step": 516685, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0075559616088867, "global_step": 516686, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0520572662353516, "global_step": 516687, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0852746963500977, "global_step": 516688, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0751588344573975, "global_step": 516689, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.014000415802002, "global_step": 516690, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.979337453842163, "global_step": 516691, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0256118774414062, "global_step": 516692, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.958543300628662, "global_step": 516693, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.089047431945801, "global_step": 516694, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.022022247314453, "global_step": 516695, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.947797417640686, "global_step": 516696, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.99940025806427, "global_step": 516697, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.098139524459839, "global_step": 516698, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9205571413040161, "global_step": 516699, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.045008897781372, "global_step": 516700, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0004305839538574, "global_step": 516701, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9920040369033813, "global_step": 516702, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.131295680999756, "global_step": 516703, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.090301513671875, "global_step": 516704, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9420722723007202, "global_step": 516705, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1407909393310547, "global_step": 516706, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9890646934509277, "global_step": 516707, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0414884090423584, "global_step": 516708, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0938215255737305, "global_step": 516709, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.026129961013794, "global_step": 516710, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0635557174682617, "global_step": 516711, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.083122730255127, "global_step": 516712, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.067464590072632, "global_step": 516713, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0905187129974365, "global_step": 516714, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.996623158454895, "global_step": 516715, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0529065132141113, "global_step": 516716, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9577569961547852, "global_step": 516717, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9762896299362183, "global_step": 516718, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0306596755981445, "global_step": 516719, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9662927389144897, "global_step": 516720, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0190141201019287, "global_step": 516721, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.016335964202881, "global_step": 516722, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.097583770751953, "global_step": 516723, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1005518436431885, "global_step": 516724, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.972963809967041, "global_step": 516725, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0428009033203125, "global_step": 516726, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9234461784362793, "global_step": 516727, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9787468910217285, "global_step": 516728, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0023391246795654, "global_step": 516729, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9689006805419922, "global_step": 516730, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.033280849456787, "global_step": 516731, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.104907751083374, "global_step": 516732, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0827736854553223, "global_step": 516733, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.974204182624817, "global_step": 516734, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.061312675476074, "global_step": 516735, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0753421783447266, "global_step": 516736, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0422518253326416, "global_step": 516737, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9928925037384033, "global_step": 516738, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9587737321853638, "global_step": 516739, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.05618953704834, "global_step": 516740, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.077150821685791, "global_step": 516741, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.029480218887329, "global_step": 516742, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.122586250305176, "global_step": 516743, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0569050312042236, "global_step": 516744, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.004713535308838, "global_step": 516745, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.086787700653076, "global_step": 516746, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0189900398254395, "global_step": 516747, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9477344751358032, "global_step": 516748, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0415823459625244, "global_step": 516749, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.016892910003662, "global_step": 516750, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.04726243019104, "global_step": 516751, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0723586082458496, "global_step": 516752, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1359176635742188, "global_step": 516753, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0979394912719727, "global_step": 516754, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0826711654663086, "global_step": 516755, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0249183177948, "global_step": 516756, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.986674189567566, "global_step": 516757, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.080937147140503, "global_step": 516758, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0004360675811768, "global_step": 516759, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1073837280273438, "global_step": 516760, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9892059564590454, "global_step": 516761, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9404942989349365, "global_step": 516762, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.013242244720459, "global_step": 516763, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1753318309783936, "global_step": 516764, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1088449954986572, "global_step": 516765, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9469630718231201, "global_step": 516766, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0661633014678955, "global_step": 516767, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9833132028579712, "global_step": 516768, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9784592390060425, "global_step": 516769, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0278592109680176, "global_step": 516770, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.086548089981079, "global_step": 516771, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9785521030426025, "global_step": 516772, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.017832040786743, "global_step": 516773, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1345603466033936, "global_step": 516774, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9101487398147583, "global_step": 516775, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.013779640197754, "global_step": 516776, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1058573722839355, "global_step": 516777, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0536155700683594, "global_step": 516778, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.108772039413452, "global_step": 516779, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.061155319213867, "global_step": 516780, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1595265865325928, "global_step": 516781, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.096506357192993, "global_step": 516782, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.032464027404785, "global_step": 516783, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9690907001495361, "global_step": 516784, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.022503614425659, "global_step": 516785, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0255255699157715, "global_step": 516786, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.096248149871826, "global_step": 516787, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0023248195648193, "global_step": 516788, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.031151294708252, "global_step": 516789, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0993590354919434, "global_step": 516790, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9917281866073608, "global_step": 516791, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0882697105407715, "global_step": 516792, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.063659429550171, "global_step": 516793, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9924488067626953, "global_step": 516794, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1246144771575928, "global_step": 516795, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.007683277130127, "global_step": 516796, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0501999855041504, "global_step": 516797, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0012106895446777, "global_step": 516798, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0637717247009277, "global_step": 516799, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.106917381286621, "global_step": 516800, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.12044358253479, "global_step": 516801, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0779500007629395, "global_step": 516802, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.052816152572632, "global_step": 516803, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.008448600769043, "global_step": 516804, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.98971426486969, "global_step": 516805, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0268971920013428, "global_step": 516806, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.132634401321411, "global_step": 516807, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0781562328338623, "global_step": 516808, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.058774471282959, "global_step": 516809, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.03369402885437, "global_step": 516810, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0968434810638428, "global_step": 516811, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0157241821289062, "global_step": 516812, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.090862989425659, "global_step": 516813, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.017796516418457, "global_step": 516814, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0091466903686523, "global_step": 516815, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0355987548828125, "global_step": 516816, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.097358465194702, "global_step": 516817, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.043712615966797, "global_step": 516818, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9450373649597168, "global_step": 516819, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.042780876159668, "global_step": 516820, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0334482192993164, "global_step": 516821, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.008165121078491, "global_step": 516822, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.093566656112671, "global_step": 516823, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.09920597076416, "global_step": 516824, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.022151231765747, "global_step": 516825, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9656764268875122, "global_step": 516826, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0960516929626465, "global_step": 516827, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.055955648422241, "global_step": 516828, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0701663494110107, "global_step": 516829, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1047523021698, "global_step": 516830, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0708210468292236, "global_step": 516831, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9619802236557007, "global_step": 516832, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0140275955200195, "global_step": 516833, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1139469146728516, "global_step": 516834, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0733861923217773, "global_step": 516835, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.008533000946045, "global_step": 516836, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.071018695831299, "global_step": 516837, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0742673873901367, "global_step": 516838, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0259552001953125, "global_step": 516839, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0382537841796875, "global_step": 516840, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9712051153182983, "global_step": 516841, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.041175365447998, "global_step": 516842, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.023963689804077, "global_step": 516843, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.052485942840576, "global_step": 516844, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.122316360473633, "global_step": 516845, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0171432495117188, "global_step": 516846, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0598227977752686, "global_step": 516847, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1000170707702637, "global_step": 516848, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1082210540771484, "global_step": 516849, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0474650859832764, "global_step": 516850, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.050868034362793, "global_step": 516851, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.087653636932373, "global_step": 516852, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0138726234436035, "global_step": 516853, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9892605543136597, "global_step": 516854, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.055119037628174, "global_step": 516855, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0462496280670166, "global_step": 516856, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1096906661987305, "global_step": 516857, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0348756313323975, "global_step": 516858, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.034010410308838, "global_step": 516859, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0925300121307373, "global_step": 516860, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0566153526306152, "global_step": 516861, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.049970865249634, "global_step": 516862, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9792519807815552, "global_step": 516863, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.941580891609192, "global_step": 516864, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.042633295059204, "global_step": 516865, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0888798236846924, "global_step": 516866, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.099602222442627, "global_step": 516867, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0360283851623535, "global_step": 516868, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9975680112838745, "global_step": 516869, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.013091802597046, "global_step": 516870, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1205785274505615, "global_step": 516871, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.157658338546753, "global_step": 516872, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.065000295639038, "global_step": 516873, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9931554794311523, "global_step": 516874, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.029958963394165, "global_step": 516875, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0341784954071045, "global_step": 516876, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0140297412872314, "global_step": 516877, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0545449256896973, "global_step": 516878, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0688867568969727, "global_step": 516879, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.916271686553955, "global_step": 516880, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.055671215057373, "global_step": 516881, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0595507621765137, "global_step": 516882, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0256834030151367, "global_step": 516883, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.988755702972412, "global_step": 516884, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1220250129699707, "global_step": 516885, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0721077919006348, "global_step": 516886, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0838420391082764, "global_step": 516887, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0370776653289795, "global_step": 516888, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.96133553981781, "global_step": 516889, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.075669288635254, "global_step": 516890, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.054597854614258, "global_step": 516891, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0245587825775146, "global_step": 516892, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9790754318237305, "global_step": 516893, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9986518621444702, "global_step": 516894, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0879571437835693, "global_step": 516895, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0281126499176025, "global_step": 516896, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0272791385650635, "global_step": 516897, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9463069438934326, "global_step": 516898, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1103196144104004, "global_step": 516899, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.086200475692749, "global_step": 516900, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.046440601348877, "global_step": 516901, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0779049396514893, "global_step": 516902, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9823063611984253, "global_step": 516903, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0659191608428955, "global_step": 516904, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.041775703430176, "global_step": 516905, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.062110662460327, "global_step": 516906, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.077568531036377, "global_step": 516907, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.083477735519409, "global_step": 516908, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.03751540184021, "global_step": 516909, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0440430641174316, "global_step": 516910, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0471882820129395, "global_step": 516911, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.986232042312622, "global_step": 516912, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.033531665802002, "global_step": 516913, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.110917568206787, "global_step": 516914, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9944849014282227, "global_step": 516915, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0045509338378906, "global_step": 516916, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0660319328308105, "global_step": 516917, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0617177486419678, "global_step": 516918, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0785305500030518, "global_step": 516919, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9884169101715088, "global_step": 516920, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.913477897644043, "global_step": 516921, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0720977783203125, "global_step": 516922, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0870001316070557, "global_step": 516923, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1017680168151855, "global_step": 516924, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.085606098175049, "global_step": 516925, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0632336139678955, "global_step": 516926, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.072087526321411, "global_step": 516927, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.028871774673462, "global_step": 516928, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9221004247665405, "global_step": 516929, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0302205085754395, "global_step": 516930, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9847077131271362, "global_step": 516931, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0402469635009766, "global_step": 516932, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1625924110412598, "global_step": 516933, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0882742404937744, "global_step": 516934, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0474343299865723, "global_step": 516935, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.974464774131775, "global_step": 516936, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0563511848449707, "global_step": 516937, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0556578636169434, "global_step": 516938, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.070711851119995, "global_step": 516939, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0327577590942383, "global_step": 516940, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0730488300323486, "global_step": 516941, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0186824798583984, "global_step": 516942, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0312509536743164, "global_step": 516943, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.117587089538574, "global_step": 516944, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.022324800491333, "global_step": 516945, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1267940998077393, "global_step": 516946, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0602102279663086, "global_step": 516947, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0303585529327393, "global_step": 516948, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.979559302330017, "global_step": 516949, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9766124486923218, "global_step": 516950, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0033071041107178, "global_step": 516951, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0563666820526123, "global_step": 516952, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0872271060943604, "global_step": 516953, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9595476388931274, "global_step": 516954, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9676231145858765, "global_step": 516955, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0756614208221436, "global_step": 516956, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.053004264831543, "global_step": 516957, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0184922218322754, "global_step": 516958, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.029484272003174, "global_step": 516959, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.089064121246338, "global_step": 516960, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0601093769073486, "global_step": 516961, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9856655597686768, "global_step": 516962, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.066365957260132, "global_step": 516963, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0573039054870605, "global_step": 516964, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1037628650665283, "global_step": 516965, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0108256340026855, "global_step": 516966, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1023240089416504, "global_step": 516967, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1104514598846436, "global_step": 516968, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0929324626922607, "global_step": 516969, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1061131954193115, "global_step": 516970, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0024566650390625, "global_step": 516971, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0508980751037598, "global_step": 516972, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0845704078674316, "global_step": 516973, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0419647693634033, "global_step": 516974, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0348870754241943, "global_step": 516975, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.06302809715271, "global_step": 516976, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.052288293838501, "global_step": 516977, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.042076587677002, "global_step": 516978, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.059133291244507, "global_step": 516979, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0694713592529297, "global_step": 516980, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.086383104324341, "global_step": 516981, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0240485668182373, "global_step": 516982, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0477371215820312, "global_step": 516983, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.983530879020691, "global_step": 516984, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.912698745727539, "global_step": 516985, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0091915130615234, "global_step": 516986, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0653834342956543, "global_step": 516987, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.023528814315796, "global_step": 516988, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1168928146362305, "global_step": 516989, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.012460470199585, "global_step": 516990, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.116010904312134, "global_step": 516991, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9746555089950562, "global_step": 516992, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.055992841720581, "global_step": 516993, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.055095911026001, "global_step": 516994, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0229337215423584, "global_step": 516995, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0262293815612793, "global_step": 516996, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.023437261581421, "global_step": 516997, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0353567600250244, "global_step": 516998, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0288124084472656, "global_step": 516999, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0829336643218994, "global_step": 517000, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9573893547058105, "global_step": 517001, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9982401132583618, "global_step": 517002, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0767765045166016, "global_step": 517003, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0420281887054443, "global_step": 517004, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9782313108444214, "global_step": 517005, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0854275226593018, "global_step": 517006, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9650288820266724, "global_step": 517007, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1142356395721436, "global_step": 517008, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0660316944122314, "global_step": 517009, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.060924530029297, "global_step": 517010, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1029980182647705, "global_step": 517011, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0069077014923096, "global_step": 517012, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0149710178375244, "global_step": 517013, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0396370887756348, "global_step": 517014, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.074519634246826, "global_step": 517015, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0302278995513916, "global_step": 517016, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.018984079360962, "global_step": 517017, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0263874530792236, "global_step": 517018, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.973425269126892, "global_step": 517019, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0561134815216064, "global_step": 517020, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.943901777267456, "global_step": 517021, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0446698665618896, "global_step": 517022, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.037980556488037, "global_step": 517023, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.105591058731079, "global_step": 517024, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.017411708831787, "global_step": 517025, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.037304639816284, "global_step": 517026, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.018695831298828, "global_step": 517027, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0668365955352783, "global_step": 517028, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0187268257141113, "global_step": 517029, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0559606552124023, "global_step": 517030, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9785820245742798, "global_step": 517031, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0668959617614746, "global_step": 517032, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0343823432922363, "global_step": 517033, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9747880697250366, "global_step": 517034, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0821099281311035, "global_step": 517035, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.070807456970215, "global_step": 517036, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.050311326980591, "global_step": 517037, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0885565280914307, "global_step": 517038, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0330357551574707, "global_step": 517039, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0404460430145264, "global_step": 517040, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0688586235046387, "global_step": 517041, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9988391399383545, "global_step": 517042, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0995967388153076, "global_step": 517043, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.035050630569458, "global_step": 517044, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0094852447509766, "global_step": 517045, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0236337184906006, "global_step": 517046, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.902527928352356, "global_step": 517047, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0330400466918945, "global_step": 517048, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.009984254837036, "global_step": 517049, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0749294757843018, "global_step": 517050, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9741348028182983, "global_step": 517051, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9371541738510132, "global_step": 517052, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.001300096511841, "global_step": 517053, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.94451904296875, "global_step": 517054, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.063751459121704, "global_step": 517055, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1224257946014404, "global_step": 517056, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9645490646362305, "global_step": 517057, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0282022953033447, "global_step": 517058, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9747737646102905, "global_step": 517059, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.116964817047119, "global_step": 517060, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.107832193374634, "global_step": 517061, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.059856414794922, "global_step": 517062, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0217978954315186, "global_step": 517063, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0215845108032227, "global_step": 517064, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9636670351028442, "global_step": 517065, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0162575244903564, "global_step": 517066, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1075594425201416, "global_step": 517067, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.040283679962158, "global_step": 517068, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0780744552612305, "global_step": 517069, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0462820529937744, "global_step": 517070, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0454092025756836, "global_step": 517071, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0486955642700195, "global_step": 517072, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9831089973449707, "global_step": 517073, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0275559425354004, "global_step": 517074, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.036360025405884, "global_step": 517075, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0847439765930176, "global_step": 517076, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0978195667266846, "global_step": 517077, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.070784091949463, "global_step": 517078, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.048755407333374, "global_step": 517079, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1021790504455566, "global_step": 517080, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.990605354309082, "global_step": 517081, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1068222522735596, "global_step": 517082, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0991828441619873, "global_step": 517083, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9814562797546387, "global_step": 517084, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.016798973083496, "global_step": 517085, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.038682699203491, "global_step": 517086, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.041083812713623, "global_step": 517087, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0494565963745117, "global_step": 517088, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0817973613739014, "global_step": 517089, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9437777996063232, "global_step": 517090, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.016162395477295, "global_step": 517091, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.118041515350342, "global_step": 517092, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.942907691001892, "global_step": 517093, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0463857650756836, "global_step": 517094, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9848660230636597, "global_step": 517095, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9572992324829102, "global_step": 517096, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.118112325668335, "global_step": 517097, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0738368034362793, "global_step": 517098, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0628855228424072, "global_step": 517099, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9537615776062012, "global_step": 517100, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0380563735961914, "global_step": 517101, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.007030963897705, "global_step": 517102, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1112098693847656, "global_step": 517103, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9771610498428345, "global_step": 517104, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.083582639694214, "global_step": 517105, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.001617908477783, "global_step": 517106, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.04298996925354, "global_step": 517107, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0534346103668213, "global_step": 517108, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.050926446914673, "global_step": 517109, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1477303504943848, "global_step": 517110, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0402278900146484, "global_step": 517111, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0383729934692383, "global_step": 517112, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.135118246078491, "global_step": 517113, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9707026481628418, "global_step": 517114, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0807905197143555, "global_step": 517115, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1971545219421387, "global_step": 517116, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9938454627990723, "global_step": 517117, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0553221702575684, "global_step": 517118, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0060415267944336, "global_step": 517119, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.072917938232422, "global_step": 517120, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0012807846069336, "global_step": 517121, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.068915605545044, "global_step": 517122, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.055053472518921, "global_step": 517123, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0713050365448, "global_step": 517124, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.029357433319092, "global_step": 517125, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0030529499053955, "global_step": 517126, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0047249794006348, "global_step": 517127, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0866215229034424, "global_step": 517128, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.032601833343506, "global_step": 517129, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.978197455406189, "global_step": 517130, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.040132999420166, "global_step": 517131, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0183937549591064, "global_step": 517132, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.951831579208374, "global_step": 517133, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.025402307510376, "global_step": 517134, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0798823833465576, "global_step": 517135, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0054757595062256, "global_step": 517136, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.031816005706787, "global_step": 517137, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.040041446685791, "global_step": 517138, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.216641902923584, "global_step": 517139, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0112812519073486, "global_step": 517140, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9717639684677124, "global_step": 517141, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0552525520324707, "global_step": 517142, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0036113262176514, "global_step": 517143, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9347589015960693, "global_step": 517144, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.087716579437256, "global_step": 517145, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0752968788146973, "global_step": 517146, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1415345668792725, "global_step": 517147, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9580632448196411, "global_step": 517148, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0657241344451904, "global_step": 517149, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9901645183563232, "global_step": 517150, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9804121255874634, "global_step": 517151, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.039365530014038, "global_step": 517152, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0244340896606445, "global_step": 517153, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0790646076202393, "global_step": 517154, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.076601982116699, "global_step": 517155, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.011265516281128, "global_step": 517156, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0543160438537598, "global_step": 517157, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0730412006378174, "global_step": 517158, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9964240789413452, "global_step": 517159, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0597944259643555, "global_step": 517160, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0859363079071045, "global_step": 517161, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1055355072021484, "global_step": 517162, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0208775997161865, "global_step": 517163, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.045656681060791, "global_step": 517164, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0899500846862793, "global_step": 517165, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0352025032043457, "global_step": 517166, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9545620679855347, "global_step": 517167, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0636098384857178, "global_step": 517168, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.111891269683838, "global_step": 517169, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0274932384490967, "global_step": 517170, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.048124074935913, "global_step": 517171, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9644825458526611, "global_step": 517172, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0275232791900635, "global_step": 517173, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.053741693496704, "global_step": 517174, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.019474506378174, "global_step": 517175, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0459017753601074, "global_step": 517176, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.947727084159851, "global_step": 517177, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.000959873199463, "global_step": 517178, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.019778251647949, "global_step": 517179, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1354546546936035, "global_step": 517180, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1042864322662354, "global_step": 517181, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.022198438644409, "global_step": 517182, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.06826114654541, "global_step": 517183, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0468153953552246, "global_step": 517184, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0483944416046143, "global_step": 517185, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0804152488708496, "global_step": 517186, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.010526418685913, "global_step": 517187, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.137988328933716, "global_step": 517188, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.116943597793579, "global_step": 517189, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0981454849243164, "global_step": 517190, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.079328775405884, "global_step": 517191, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0390803813934326, "global_step": 517192, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.097043514251709, "global_step": 517193, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.074542760848999, "global_step": 517194, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.011779308319092, "global_step": 517195, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0054190158843994, "global_step": 517196, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1099131107330322, "global_step": 517197, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.031036138534546, "global_step": 517198, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0608575344085693, "global_step": 517199, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0810680389404297, "global_step": 517200, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.007431745529175, "global_step": 517201, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1499178409576416, "global_step": 517202, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0660204887390137, "global_step": 517203, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0685269832611084, "global_step": 517204, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0296871662139893, "global_step": 517205, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.987048864364624, "global_step": 517206, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0669474601745605, "global_step": 517207, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.036135673522949, "global_step": 517208, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1142115592956543, "global_step": 517209, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0040063858032227, "global_step": 517210, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0499649047851562, "global_step": 517211, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.118347406387329, "global_step": 517212, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1050682067871094, "global_step": 517213, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0748605728149414, "global_step": 517214, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.048192262649536, "global_step": 517215, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0199015140533447, "global_step": 517216, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0891408920288086, "global_step": 517217, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.090231418609619, "global_step": 517218, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0694475173950195, "global_step": 517219, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.05370831489563, "global_step": 517220, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9944515228271484, "global_step": 517221, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1153147220611572, "global_step": 517222, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0449633598327637, "global_step": 517223, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0101613998413086, "global_step": 517224, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.936537265777588, "global_step": 517225, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0741453170776367, "global_step": 517226, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0926129817962646, "global_step": 517227, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0669188499450684, "global_step": 517228, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0431830883026123, "global_step": 517229, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.044506788253784, "global_step": 517230, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9660887718200684, "global_step": 517231, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.09480881690979, "global_step": 517232, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.078427314758301, "global_step": 517233, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0552783012390137, "global_step": 517234, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.119075298309326, "global_step": 517235, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0674500465393066, "global_step": 517236, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.063800573348999, "global_step": 517237, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9836422204971313, "global_step": 517238, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0561201572418213, "global_step": 517239, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.017104387283325, "global_step": 517240, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.082444190979004, "global_step": 517241, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0983223915100098, "global_step": 517242, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0220859050750732, "global_step": 517243, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.068840503692627, "global_step": 517244, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0675458908081055, "global_step": 517245, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9759470224380493, "global_step": 517246, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.051684856414795, "global_step": 517247, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9607609510421753, "global_step": 517248, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0237767696380615, "global_step": 517249, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0487663745880127, "global_step": 517250, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9808086156845093, "global_step": 517251, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.114683151245117, "global_step": 517252, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.030869483947754, "global_step": 517253, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.078803062438965, "global_step": 517254, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0617613792419434, "global_step": 517255, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.034799098968506, "global_step": 517256, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0459978580474854, "global_step": 517257, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0132737159729004, "global_step": 517258, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.981396198272705, "global_step": 517259, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0263900756835938, "global_step": 517260, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9898827075958252, "global_step": 517261, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.034933090209961, "global_step": 517262, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.122004508972168, "global_step": 517263, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9835951328277588, "global_step": 517264, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.070457696914673, "global_step": 517265, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.046057939529419, "global_step": 517266, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.120711326599121, "global_step": 517267, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.070720911026001, "global_step": 517268, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0228917598724365, "global_step": 517269, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0113747119903564, "global_step": 517270, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1254889965057373, "global_step": 517271, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.065356492996216, "global_step": 517272, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9763917922973633, "global_step": 517273, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9836008548736572, "global_step": 517274, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0459203720092773, "global_step": 517275, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0351574420928955, "global_step": 517276, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.047039270401001, "global_step": 517277, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.037602186203003, "global_step": 517278, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0927653312683105, "global_step": 517279, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.014075756072998, "global_step": 517280, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0432262420654297, "global_step": 517281, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0288524627685547, "global_step": 517282, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0780982971191406, "global_step": 517283, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0931262969970703, "global_step": 517284, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.991546392440796, "global_step": 517285, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1051673889160156, "global_step": 517286, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1256349086761475, "global_step": 517287, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.044512987136841, "global_step": 517288, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.038419485092163, "global_step": 517289, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0622458457946777, "global_step": 517290, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.999755620956421, "global_step": 517291, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.052241325378418, "global_step": 517292, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0211093425750732, "global_step": 517293, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.002253770828247, "global_step": 517294, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9981138706207275, "global_step": 517295, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0224101543426514, "global_step": 517296, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0395007133483887, "global_step": 517297, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0725810527801514, "global_step": 517298, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0600759983062744, "global_step": 517299, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0095102787017822, "global_step": 517300, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.080261468887329, "global_step": 517301, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.011746406555176, "global_step": 517302, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0842080116271973, "global_step": 517303, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0734400749206543, "global_step": 517304, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.075780153274536, "global_step": 517305, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1303391456604004, "global_step": 517306, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9563480615615845, "global_step": 517307, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.099851369857788, "global_step": 517308, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.985365867614746, "global_step": 517309, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9965718984603882, "global_step": 517310, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1130857467651367, "global_step": 517311, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.100931167602539, "global_step": 517312, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0515496730804443, "global_step": 517313, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0059304237365723, "global_step": 517314, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0041520595550537, "global_step": 517315, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.067819356918335, "global_step": 517316, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0372488498687744, "global_step": 517317, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0557150840759277, "global_step": 517318, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0093822479248047, "global_step": 517319, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.065828561782837, "global_step": 517320, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0600244998931885, "global_step": 517321, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0210745334625244, "global_step": 517322, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0010643005371094, "global_step": 517323, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0880863666534424, "global_step": 517324, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.032581090927124, "global_step": 517325, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.036292314529419, "global_step": 517326, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0259716510772705, "global_step": 517327, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.085908889770508, "global_step": 517328, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0564334392547607, "global_step": 517329, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0061302185058594, "global_step": 517330, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.067502498626709, "global_step": 517331, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9777494668960571, "global_step": 517332, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0337233543395996, "global_step": 517333, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.054166793823242, "global_step": 517334, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0602834224700928, "global_step": 517335, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0586612224578857, "global_step": 517336, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1766796112060547, "global_step": 517337, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0723390579223633, "global_step": 517338, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0153346061706543, "global_step": 517339, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9844309091567993, "global_step": 517340, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.086226224899292, "global_step": 517341, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0511341094970703, "global_step": 517342, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0341217517852783, "global_step": 517343, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9155614376068115, "global_step": 517344, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9675318002700806, "global_step": 517345, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1132214069366455, "global_step": 517346, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0632903575897217, "global_step": 517347, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1039505004882812, "global_step": 517348, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9883865118026733, "global_step": 517349, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0739848613739014, "global_step": 517350, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0293073654174805, "global_step": 517351, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0553009510040283, "global_step": 517352, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0651984214782715, "global_step": 517353, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1197009086608887, "global_step": 517354, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9997804164886475, "global_step": 517355, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.01623272895813, "global_step": 517356, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0812230110168457, "global_step": 517357, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.041947364807129, "global_step": 517358, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0556044578552246, "global_step": 517359, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.055068254470825, "global_step": 517360, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0268590450286865, "global_step": 517361, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1373677253723145, "global_step": 517362, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.016613721847534, "global_step": 517363, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.087657928466797, "global_step": 517364, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0828633308410645, "global_step": 517365, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0121665000915527, "global_step": 517366, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.07365345954895, "global_step": 517367, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9614770412445068, "global_step": 517368, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9835023880004883, "global_step": 517369, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9662343263626099, "global_step": 517370, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.070319175720215, "global_step": 517371, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0706098079681396, "global_step": 517372, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.051253080368042, "global_step": 517373, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0606436729431152, "global_step": 517374, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.054370880126953, "global_step": 517375, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.036432981491089, "global_step": 517376, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0722286701202393, "global_step": 517377, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0813353061676025, "global_step": 517378, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.071226119995117, "global_step": 517379, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0424883365631104, "global_step": 517380, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.051246404647827, "global_step": 517381, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0345993041992188, "global_step": 517382, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9765329360961914, "global_step": 517383, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9934719800949097, "global_step": 517384, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0673351287841797, "global_step": 517385, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1096582412719727, "global_step": 517386, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1027817726135254, "global_step": 517387, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.055819272994995, "global_step": 517388, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1152217388153076, "global_step": 517389, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9739917516708374, "global_step": 517390, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0062034130096436, "global_step": 517391, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.041637420654297, "global_step": 517392, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0920560359954834, "global_step": 517393, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.018418312072754, "global_step": 517394, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9840972423553467, "global_step": 517395, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0922937393188477, "global_step": 517396, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0329790115356445, "global_step": 517397, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1245675086975098, "global_step": 517398, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0449390411376953, "global_step": 517399, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.008894920349121, "global_step": 517400, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.2016491889953613, "global_step": 517401, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.140162706375122, "global_step": 517402, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.148801326751709, "global_step": 517403, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.8544267416000366, "global_step": 517404, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.078562021255493, "global_step": 517405, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.037280559539795, "global_step": 517406, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9985271692276, "global_step": 517407, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.07824969291687, "global_step": 517408, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.043271780014038, "global_step": 517409, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0869994163513184, "global_step": 517410, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0610978603363037, "global_step": 517411, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.057528257369995, "global_step": 517412, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0351829528808594, "global_step": 517413, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.157663583755493, "global_step": 517414, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0357742309570312, "global_step": 517415, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.108567953109741, "global_step": 517416, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.105468511581421, "global_step": 517417, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.013899564743042, "global_step": 517418, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0840439796447754, "global_step": 517419, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0488386154174805, "global_step": 517420, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0509471893310547, "global_step": 517421, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0102007389068604, "global_step": 517422, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9623149633407593, "global_step": 517423, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.010784864425659, "global_step": 517424, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9938539266586304, "global_step": 517425, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9911832809448242, "global_step": 517426, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.008972406387329, "global_step": 517427, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9984947443008423, "global_step": 517428, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0459861755371094, "global_step": 517429, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9995981454849243, "global_step": 517430, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.089108467102051, "global_step": 517431, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.061016082763672, "global_step": 517432, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1760685443878174, "global_step": 517433, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9892817735671997, "global_step": 517434, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1027326583862305, "global_step": 517435, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0232138633728027, "global_step": 517436, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.072455883026123, "global_step": 517437, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.130951404571533, "global_step": 517438, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0771448612213135, "global_step": 517439, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0037741661071777, "global_step": 517440, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.068521738052368, "global_step": 517441, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9886308908462524, "global_step": 517442, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.030460834503174, "global_step": 517443, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0130937099456787, "global_step": 517444, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0215229988098145, "global_step": 517445, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0360472202301025, "global_step": 517446, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0589756965637207, "global_step": 517447, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.065218687057495, "global_step": 517448, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.149850845336914, "global_step": 517449, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0255885124206543, "global_step": 517450, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9887020587921143, "global_step": 517451, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.05047607421875, "global_step": 517452, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0740675926208496, "global_step": 517453, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1452598571777344, "global_step": 517454, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0372188091278076, "global_step": 517455, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0078516006469727, "global_step": 517456, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.144605875015259, "global_step": 517457, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.074397325515747, "global_step": 517458, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9608443975448608, "global_step": 517459, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0720982551574707, "global_step": 517460, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.174823045730591, "global_step": 517461, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1198742389678955, "global_step": 517462, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0067217350006104, "global_step": 517463, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0489842891693115, "global_step": 517464, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.143892765045166, "global_step": 517465, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.06282639503479, "global_step": 517466, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0216076374053955, "global_step": 517467, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.03556227684021, "global_step": 517468, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9973855018615723, "global_step": 517469, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9853864908218384, "global_step": 517470, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0648128986358643, "global_step": 517471, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9880242347717285, "global_step": 517472, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0275886058807373, "global_step": 517473, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.101181745529175, "global_step": 517474, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.972411870956421, "global_step": 517475, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9557160139083862, "global_step": 517476, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.06246018409729, "global_step": 517477, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.038783550262451, "global_step": 517478, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0790698528289795, "global_step": 517479, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.066222906112671, "global_step": 517480, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0193777084350586, "global_step": 517481, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.010798215866089, "global_step": 517482, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1398963928222656, "global_step": 517483, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0013203620910645, "global_step": 517484, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.181110382080078, "global_step": 517485, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.091445207595825, "global_step": 517486, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.127190589904785, "global_step": 517487, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.054499864578247, "global_step": 517488, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0200846195220947, "global_step": 517489, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.060373306274414, "global_step": 517490, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0488805770874023, "global_step": 517491, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1498405933380127, "global_step": 517492, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.053821563720703, "global_step": 517493, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0987484455108643, "global_step": 517494, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1310877799987793, "global_step": 517495, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.030425786972046, "global_step": 517496, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9828293323516846, "global_step": 517497, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0352730751037598, "global_step": 517498, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0631446838378906, "global_step": 517499, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0349903106689453, "global_step": 517500, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.046515464782715, "global_step": 517501, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0646421909332275, "global_step": 517502, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1418020725250244, "global_step": 517503, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0974462032318115, "global_step": 517504, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0065691471099854, "global_step": 517505, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.076373815536499, "global_step": 517506, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0199077129364014, "global_step": 517507, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0893359184265137, "global_step": 517508, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.186829090118408, "global_step": 517509, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0034241676330566, "global_step": 517510, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0654454231262207, "global_step": 517511, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.02474045753479, "global_step": 517512, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0452682971954346, "global_step": 517513, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.056931972503662, "global_step": 517514, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.059134006500244, "global_step": 517515, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9883683919906616, "global_step": 517516, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0453402996063232, "global_step": 517517, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.020263433456421, "global_step": 517518, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0162172317504883, "global_step": 517519, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9906117916107178, "global_step": 517520, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1350016593933105, "global_step": 517521, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.034252643585205, "global_step": 517522, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.024106025695801, "global_step": 517523, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0684902667999268, "global_step": 517524, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1592724323272705, "global_step": 517525, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.108628749847412, "global_step": 517526, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.065878391265869, "global_step": 517527, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9737162590026855, "global_step": 517528, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.052936315536499, "global_step": 517529, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0054848194122314, "global_step": 517530, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0634000301361084, "global_step": 517531, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1037886142730713, "global_step": 517532, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.096834897994995, "global_step": 517533, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0297207832336426, "global_step": 517534, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.06038761138916, "global_step": 517535, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.097482442855835, "global_step": 517536, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0351879596710205, "global_step": 517537, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.040579080581665, "global_step": 517538, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.073385000228882, "global_step": 517539, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.957075595855713, "global_step": 517540, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0594069957733154, "global_step": 517541, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1739163398742676, "global_step": 517542, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.082507371902466, "global_step": 517543, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0112411975860596, "global_step": 517544, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.01481556892395, "global_step": 517545, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.036515235900879, "global_step": 517546, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.012777328491211, "global_step": 517547, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0310990810394287, "global_step": 517548, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1931710243225098, "global_step": 517549, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0590600967407227, "global_step": 517550, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.039721727371216, "global_step": 517551, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0608603954315186, "global_step": 517552, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0783472061157227, "global_step": 517553, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0597870349884033, "global_step": 517554, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.082880735397339, "global_step": 517555, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0447442531585693, "global_step": 517556, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0236704349517822, "global_step": 517557, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.077150583267212, "global_step": 517558, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0206410884857178, "global_step": 517559, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0041682720184326, "global_step": 517560, "epoch": 883, "lr": 5e-05}
{"train_loss": 1.9563837051391602, "global_step": 517561, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.08583927154541, "global_step": 517562, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.120107650756836, "global_step": 517563, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.094498872756958, "global_step": 517564, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0348713397979736, "global_step": 517565, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.099003314971924, "global_step": 517566, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0337491035461426, "global_step": 517567, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.017054557800293, "global_step": 517568, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1045353412628174, "global_step": 517569, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.01180100440979, "global_step": 517570, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1010193824768066, "global_step": 517571, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.069727659225464, "global_step": 517572, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1402015686035156, "global_step": 517573, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.1402924060821533, "global_step": 517574, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.079756736755371, "global_step": 517575, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.110304355621338, "global_step": 517576, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.0048980712890625, "global_step": 517577, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.045156955718994, "global_step": 517578, "epoch": 883, "lr": 5e-05}
{"train_loss": 2.014845132827759, "global_step": 517579, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.022613763809204, "global_step": 517580, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0741419792175293, "global_step": 517581, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9450830221176147, "global_step": 517582, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0904459953308105, "global_step": 517583, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.114123821258545, "global_step": 517584, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9917398691177368, "global_step": 517585, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0908596515655518, "global_step": 517586, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.065980911254883, "global_step": 517587, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9813296794891357, "global_step": 517588, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9919549226760864, "global_step": 517589, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0577356815338135, "global_step": 517590, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.055917501449585, "global_step": 517591, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.994863748550415, "global_step": 517592, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0424511432647705, "global_step": 517593, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0293827056884766, "global_step": 517594, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0526466369628906, "global_step": 517595, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0145976543426514, "global_step": 517596, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.988396167755127, "global_step": 517597, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9817593097686768, "global_step": 517598, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.091639518737793, "global_step": 517599, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0183351039886475, "global_step": 517600, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.047797918319702, "global_step": 517601, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.969918131828308, "global_step": 517602, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.990196943283081, "global_step": 517603, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.038379192352295, "global_step": 517604, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0126497745513916, "global_step": 517605, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9660471677780151, "global_step": 517606, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.960963249206543, "global_step": 517607, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0888147354125977, "global_step": 517608, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0340216159820557, "global_step": 517609, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.020015239715576, "global_step": 517610, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0424532890319824, "global_step": 517611, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.977532148361206, "global_step": 517612, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.020127773284912, "global_step": 517613, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.062901735305786, "global_step": 517614, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9001191854476929, "global_step": 517615, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0452566146850586, "global_step": 517616, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.066941976547241, "global_step": 517617, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9888979196548462, "global_step": 517618, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.002363920211792, "global_step": 517619, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0697429180145264, "global_step": 517620, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9860782623291016, "global_step": 517621, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0766875743865967, "global_step": 517622, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.052924633026123, "global_step": 517623, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0635604858398438, "global_step": 517624, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0146327018737793, "global_step": 517625, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9885200262069702, "global_step": 517626, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0841190814971924, "global_step": 517627, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.123595952987671, "global_step": 517628, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.079298496246338, "global_step": 517629, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.128652572631836, "global_step": 517630, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0655364990234375, "global_step": 517631, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0348737239837646, "global_step": 517632, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.972604751586914, "global_step": 517633, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1002988815307617, "global_step": 517634, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0611605644226074, "global_step": 517635, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0195276737213135, "global_step": 517636, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.081540107727051, "global_step": 517637, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.037655830383301, "global_step": 517638, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.008629560470581, "global_step": 517639, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9637118577957153, "global_step": 517640, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0273470878601074, "global_step": 517641, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0201594829559326, "global_step": 517642, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.02941632270813, "global_step": 517643, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.072852611541748, "global_step": 517644, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0143864154815674, "global_step": 517645, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0639355182647705, "global_step": 517646, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0022165775299072, "global_step": 517647, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0005037784576416, "global_step": 517648, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1270177364349365, "global_step": 517649, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0682761669158936, "global_step": 517650, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9902876615524292, "global_step": 517651, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.05425763130188, "global_step": 517652, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1029090881347656, "global_step": 517653, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0235564708709717, "global_step": 517654, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9819568395614624, "global_step": 517655, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0817179679870605, "global_step": 517656, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.141082286834717, "global_step": 517657, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.087630271911621, "global_step": 517658, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.056124210357666, "global_step": 517659, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0036439895629883, "global_step": 517660, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.086845636367798, "global_step": 517661, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1153008937835693, "global_step": 517662, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0495285987854004, "global_step": 517663, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9832218885421753, "global_step": 517664, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1102445125579834, "global_step": 517665, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9340020418167114, "global_step": 517666, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0648653507232666, "global_step": 517667, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1119043827056885, "global_step": 517668, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0386977195739746, "global_step": 517669, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9678388833999634, "global_step": 517670, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.134188652038574, "global_step": 517671, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.991978645324707, "global_step": 517672, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.047224998474121, "global_step": 517673, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0529727935791016, "global_step": 517674, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0497195720672607, "global_step": 517675, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.023160219192505, "global_step": 517676, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0647823810577393, "global_step": 517677, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.001624584197998, "global_step": 517678, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.040659189224243, "global_step": 517679, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.073154926300049, "global_step": 517680, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0351004600524902, "global_step": 517681, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9999133348464966, "global_step": 517682, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.069509744644165, "global_step": 517683, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.073031425476074, "global_step": 517684, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9838780164718628, "global_step": 517685, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0863845348358154, "global_step": 517686, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.04067063331604, "global_step": 517687, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.080557107925415, "global_step": 517688, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0495660305023193, "global_step": 517689, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0630106925964355, "global_step": 517690, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.020033836364746, "global_step": 517691, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9678303003311157, "global_step": 517692, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0445165634155273, "global_step": 517693, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.096963882446289, "global_step": 517694, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0449652671813965, "global_step": 517695, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1393163204193115, "global_step": 517696, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0711982250213623, "global_step": 517697, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9085075855255127, "global_step": 517698, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9735383987426758, "global_step": 517699, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0214803218841553, "global_step": 517700, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0503954887390137, "global_step": 517701, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.000997304916382, "global_step": 517702, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9961998462677002, "global_step": 517703, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9745360612869263, "global_step": 517704, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9922913312911987, "global_step": 517705, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0876505374908447, "global_step": 517706, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.032334804534912, "global_step": 517707, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9918904304504395, "global_step": 517708, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0337233543395996, "global_step": 517709, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9872031211853027, "global_step": 517710, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.004906177520752, "global_step": 517711, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9756371974945068, "global_step": 517712, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.044951915740967, "global_step": 517713, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1035573482513428, "global_step": 517714, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0087671279907227, "global_step": 517715, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9799987077713013, "global_step": 517716, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.001645565032959, "global_step": 517717, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.104712724685669, "global_step": 517718, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0644404888153076, "global_step": 517719, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.092637062072754, "global_step": 517720, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0426485538482666, "global_step": 517721, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0221753120422363, "global_step": 517722, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0767838954925537, "global_step": 517723, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.095271110534668, "global_step": 517724, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0858302116394043, "global_step": 517725, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0268778800964355, "global_step": 517726, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0227558612823486, "global_step": 517727, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.046849012374878, "global_step": 517728, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0068981647491455, "global_step": 517729, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.045931816101074, "global_step": 517730, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.03448748588562, "global_step": 517731, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.081042528152466, "global_step": 517732, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.054839611053467, "global_step": 517733, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.993668556213379, "global_step": 517734, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.091505289077759, "global_step": 517735, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1424946784973145, "global_step": 517736, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0380308628082275, "global_step": 517737, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0479156970977783, "global_step": 517738, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0204641819000244, "global_step": 517739, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1577610969543457, "global_step": 517740, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.036135673522949, "global_step": 517741, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0248122215270996, "global_step": 517742, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0962414741516113, "global_step": 517743, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0971486568450928, "global_step": 517744, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.001650333404541, "global_step": 517745, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9546496868133545, "global_step": 517746, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.121960163116455, "global_step": 517747, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.04927921295166, "global_step": 517748, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0295073986053467, "global_step": 517749, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0479328632354736, "global_step": 517750, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9931366443634033, "global_step": 517751, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0946619510650635, "global_step": 517752, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.043541193008423, "global_step": 517753, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.950425624847412, "global_step": 517754, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9775919914245605, "global_step": 517755, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9621614217758179, "global_step": 517756, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9880883693695068, "global_step": 517757, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0805532932281494, "global_step": 517758, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.02467679977417, "global_step": 517759, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0191287994384766, "global_step": 517760, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.994111180305481, "global_step": 517761, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.113511562347412, "global_step": 517762, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0197808742523193, "global_step": 517763, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.949533224105835, "global_step": 517764, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9764068126678467, "global_step": 517765, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9989038705825806, "global_step": 517766, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.105827569961548, "global_step": 517767, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0447943210601807, "global_step": 517768, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.07296085357666, "global_step": 517769, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.046076536178589, "global_step": 517770, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9718881845474243, "global_step": 517771, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0788838863372803, "global_step": 517772, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0318827629089355, "global_step": 517773, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.07412052154541, "global_step": 517774, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0441904067993164, "global_step": 517775, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9736512899398804, "global_step": 517776, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0720694065093994, "global_step": 517777, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.980326771736145, "global_step": 517778, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.093932628631592, "global_step": 517779, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0674643516540527, "global_step": 517780, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1644132137298584, "global_step": 517781, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.051637649536133, "global_step": 517782, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0145175457000732, "global_step": 517783, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0416460037231445, "global_step": 517784, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.054107666015625, "global_step": 517785, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0128722190856934, "global_step": 517786, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9839030504226685, "global_step": 517787, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0533599853515625, "global_step": 517788, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.037813186645508, "global_step": 517789, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.064695358276367, "global_step": 517790, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.055083751678467, "global_step": 517791, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0645651817321777, "global_step": 517792, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.985560417175293, "global_step": 517793, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0663208961486816, "global_step": 517794, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.024360179901123, "global_step": 517795, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0910897254943848, "global_step": 517796, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.09114670753479, "global_step": 517797, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0610508918762207, "global_step": 517798, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9939594268798828, "global_step": 517799, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.994424819946289, "global_step": 517800, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0270001888275146, "global_step": 517801, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.030416250228882, "global_step": 517802, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.044801950454712, "global_step": 517803, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.116101026535034, "global_step": 517804, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.070732831954956, "global_step": 517805, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9626545906066895, "global_step": 517806, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.026308298110962, "global_step": 517807, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.021404266357422, "global_step": 517808, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0965638160705566, "global_step": 517809, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.996315360069275, "global_step": 517810, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.053779125213623, "global_step": 517811, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0658626556396484, "global_step": 517812, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.976192593574524, "global_step": 517813, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0524191856384277, "global_step": 517814, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0814342498779297, "global_step": 517815, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9736088514328003, "global_step": 517816, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.056673526763916, "global_step": 517817, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0731558799743652, "global_step": 517818, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0249931812286377, "global_step": 517819, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0300116539001465, "global_step": 517820, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0676167011260986, "global_step": 517821, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.98652982711792, "global_step": 517822, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.064549207687378, "global_step": 517823, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9901682138442993, "global_step": 517824, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.979241967201233, "global_step": 517825, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0100934505462646, "global_step": 517826, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.919665813446045, "global_step": 517827, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0407965183258057, "global_step": 517828, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0532195568084717, "global_step": 517829, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.06654953956604, "global_step": 517830, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9919648170471191, "global_step": 517831, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.059480667114258, "global_step": 517832, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9562976360321045, "global_step": 517833, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.017559051513672, "global_step": 517834, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0940167903900146, "global_step": 517835, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.966841220855713, "global_step": 517836, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.012960910797119, "global_step": 517837, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0735909938812256, "global_step": 517838, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9740166664123535, "global_step": 517839, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.968988060951233, "global_step": 517840, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0345184803009033, "global_step": 517841, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9733235836029053, "global_step": 517842, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0287158489227295, "global_step": 517843, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0006961822509766, "global_step": 517844, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0370934009552, "global_step": 517845, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9780957698822021, "global_step": 517846, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.125933885574341, "global_step": 517847, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0015554428100586, "global_step": 517848, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0822947025299072, "global_step": 517849, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0195791721343994, "global_step": 517850, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0817794799804688, "global_step": 517851, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.112684488296509, "global_step": 517852, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.09920072555542, "global_step": 517853, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0569729804992676, "global_step": 517854, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0049281120300293, "global_step": 517855, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0282251834869385, "global_step": 517856, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9963643550872803, "global_step": 517857, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9503965377807617, "global_step": 517858, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0486414432525635, "global_step": 517859, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0667288303375244, "global_step": 517860, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0346944332122803, "global_step": 517861, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.949857473373413, "global_step": 517862, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.020667791366577, "global_step": 517863, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9834405183792114, "global_step": 517864, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0679314136505127, "global_step": 517865, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0217535495758057, "global_step": 517866, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0634965896606445, "global_step": 517867, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9964550733566284, "global_step": 517868, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1209933757781982, "global_step": 517869, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9993852376937866, "global_step": 517870, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1283257007598877, "global_step": 517871, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.009855270385742, "global_step": 517872, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.097388744354248, "global_step": 517873, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0234944820404053, "global_step": 517874, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0045504570007324, "global_step": 517875, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1013717651367188, "global_step": 517876, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.101447582244873, "global_step": 517877, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0361204147338867, "global_step": 517878, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9640437364578247, "global_step": 517879, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0207808017730713, "global_step": 517880, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.037777900695801, "global_step": 517881, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.053926706314087, "global_step": 517882, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.071492910385132, "global_step": 517883, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.035209894180298, "global_step": 517884, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9681369066238403, "global_step": 517885, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1058573722839355, "global_step": 517886, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.971984624862671, "global_step": 517887, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9906249046325684, "global_step": 517888, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9880635738372803, "global_step": 517889, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0654945373535156, "global_step": 517890, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.066884994506836, "global_step": 517891, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0714426040649414, "global_step": 517892, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9899109601974487, "global_step": 517893, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0600123405456543, "global_step": 517894, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.975898027420044, "global_step": 517895, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0873703956604004, "global_step": 517896, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.016000270843506, "global_step": 517897, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9950854778289795, "global_step": 517898, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.992090106010437, "global_step": 517899, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0211076736450195, "global_step": 517900, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.005981683731079, "global_step": 517901, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0076427459716797, "global_step": 517902, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0637640953063965, "global_step": 517903, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.973778247833252, "global_step": 517904, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9962412118911743, "global_step": 517905, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.011486530303955, "global_step": 517906, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.092397928237915, "global_step": 517907, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0235002040863037, "global_step": 517908, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9468350410461426, "global_step": 517909, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0391106605529785, "global_step": 517910, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.057407855987549, "global_step": 517911, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0457537174224854, "global_step": 517912, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1070594787597656, "global_step": 517913, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.060499668121338, "global_step": 517914, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.086460828781128, "global_step": 517915, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0401246547698975, "global_step": 517916, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.114417791366577, "global_step": 517917, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1514999866485596, "global_step": 517918, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.024308919906616, "global_step": 517919, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.109999418258667, "global_step": 517920, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.077939033508301, "global_step": 517921, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1344311237335205, "global_step": 517922, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.959856629371643, "global_step": 517923, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0080931186676025, "global_step": 517924, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.042867422103882, "global_step": 517925, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.112691879272461, "global_step": 517926, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0159389972686768, "global_step": 517927, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1282310485839844, "global_step": 517928, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.00295090675354, "global_step": 517929, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.003612518310547, "global_step": 517930, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9806413650512695, "global_step": 517931, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0288424491882324, "global_step": 517932, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.099334478378296, "global_step": 517933, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9777038097381592, "global_step": 517934, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.998201608657837, "global_step": 517935, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9848679304122925, "global_step": 517936, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0253543853759766, "global_step": 517937, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.034752368927002, "global_step": 517938, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0830295085906982, "global_step": 517939, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9955635070800781, "global_step": 517940, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0409061908721924, "global_step": 517941, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0689380168914795, "global_step": 517942, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.085615873336792, "global_step": 517943, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0446841716766357, "global_step": 517944, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0842530727386475, "global_step": 517945, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9446927309036255, "global_step": 517946, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.042428731918335, "global_step": 517947, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0701775550842285, "global_step": 517948, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0599350929260254, "global_step": 517949, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9491523504257202, "global_step": 517950, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.049501895904541, "global_step": 517951, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.098003625869751, "global_step": 517952, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0462727546691895, "global_step": 517953, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9187753200531006, "global_step": 517954, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0869369506835938, "global_step": 517955, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9761422872543335, "global_step": 517956, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.011241912841797, "global_step": 517957, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9734981060028076, "global_step": 517958, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.09779953956604, "global_step": 517959, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0281810760498047, "global_step": 517960, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.015134334564209, "global_step": 517961, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1033642292022705, "global_step": 517962, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0301513671875, "global_step": 517963, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.05436372756958, "global_step": 517964, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.05265474319458, "global_step": 517965, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0227320194244385, "global_step": 517966, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0294816493988037, "global_step": 517967, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.019136905670166, "global_step": 517968, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1037850379943848, "global_step": 517969, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0318443775177, "global_step": 517970, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.036975622177124, "global_step": 517971, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.107192277908325, "global_step": 517972, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0289418697357178, "global_step": 517973, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0727365016937256, "global_step": 517974, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0747475624084473, "global_step": 517975, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9896347522735596, "global_step": 517976, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0927817821502686, "global_step": 517977, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1405131816864014, "global_step": 517978, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.018033027648926, "global_step": 517979, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.053563356399536, "global_step": 517980, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0913596153259277, "global_step": 517981, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.137375593185425, "global_step": 517982, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.052356719970703, "global_step": 517983, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1618287563323975, "global_step": 517984, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1485087871551514, "global_step": 517985, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0312955379486084, "global_step": 517986, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9844354391098022, "global_step": 517987, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.05849552154541, "global_step": 517988, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0854499340057373, "global_step": 517989, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0544118881225586, "global_step": 517990, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.067082643508911, "global_step": 517991, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0799224376678467, "global_step": 517992, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0116539001464844, "global_step": 517993, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0154504776000977, "global_step": 517994, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0052475929260254, "global_step": 517995, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0017716884613037, "global_step": 517996, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0058999061584473, "global_step": 517997, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0651423931121826, "global_step": 517998, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0539543628692627, "global_step": 517999, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.108201742172241, "global_step": 518000, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0961480140686035, "global_step": 518001, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1408894062042236, "global_step": 518002, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0534300804138184, "global_step": 518003, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9781898260116577, "global_step": 518004, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1472103595733643, "global_step": 518005, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0351972579956055, "global_step": 518006, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.932842493057251, "global_step": 518007, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0209507942199707, "global_step": 518008, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9945861101150513, "global_step": 518009, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0452632904052734, "global_step": 518010, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1104912757873535, "global_step": 518011, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9559292793273926, "global_step": 518012, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0757052898406982, "global_step": 518013, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.078886032104492, "global_step": 518014, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9852696657180786, "global_step": 518015, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0403740406036377, "global_step": 518016, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9888991117477417, "global_step": 518017, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.072596788406372, "global_step": 518018, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0685455799102783, "global_step": 518019, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1224405765533447, "global_step": 518020, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0106494426727295, "global_step": 518021, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.067362070083618, "global_step": 518022, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0113611221313477, "global_step": 518023, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0618581771850586, "global_step": 518024, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0564792156219482, "global_step": 518025, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0433528423309326, "global_step": 518026, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.08847713470459, "global_step": 518027, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.160848617553711, "global_step": 518028, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9603644609451294, "global_step": 518029, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9628607034683228, "global_step": 518030, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.114757776260376, "global_step": 518031, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0022480487823486, "global_step": 518032, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9969861507415771, "global_step": 518033, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9121019840240479, "global_step": 518034, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9660885334014893, "global_step": 518035, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.060833692550659, "global_step": 518036, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0164053440093994, "global_step": 518037, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1671838760375977, "global_step": 518038, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.073855400085449, "global_step": 518039, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9525384902954102, "global_step": 518040, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0718460083007812, "global_step": 518041, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9285128116607666, "global_step": 518042, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0165374279022217, "global_step": 518043, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9934675693511963, "global_step": 518044, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0602986812591553, "global_step": 518045, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9820882081985474, "global_step": 518046, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9854443073272705, "global_step": 518047, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0154190063476562, "global_step": 518048, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.057152509689331, "global_step": 518049, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.116755962371826, "global_step": 518050, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1011312007904053, "global_step": 518051, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0701727867126465, "global_step": 518052, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.072157144546509, "global_step": 518053, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9835420846939087, "global_step": 518054, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0463531017303467, "global_step": 518055, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0236270427703857, "global_step": 518056, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.138561725616455, "global_step": 518057, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.090972423553467, "global_step": 518058, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.127579689025879, "global_step": 518059, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0605571269989014, "global_step": 518060, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0552568435668945, "global_step": 518061, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.038419723510742, "global_step": 518062, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0413694381713867, "global_step": 518063, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0549488067626953, "global_step": 518064, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1277711391448975, "global_step": 518065, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0584635734558105, "global_step": 518066, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9868793487548828, "global_step": 518067, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9943796396255493, "global_step": 518068, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.070619821548462, "global_step": 518069, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.085082530975342, "global_step": 518070, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.030414581298828, "global_step": 518071, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.06886625289917, "global_step": 518072, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0379602909088135, "global_step": 518073, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0374879837036133, "global_step": 518074, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.064410924911499, "global_step": 518075, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0400550365448, "global_step": 518076, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9378104209899902, "global_step": 518077, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.060858726501465, "global_step": 518078, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0848679542541504, "global_step": 518079, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0279154777526855, "global_step": 518080, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1156556606292725, "global_step": 518081, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.986021876335144, "global_step": 518082, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.031891107559204, "global_step": 518083, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.075225591659546, "global_step": 518084, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1763358116149902, "global_step": 518085, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.006234645843506, "global_step": 518086, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.004096746444702, "global_step": 518087, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1038005352020264, "global_step": 518088, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.059758424758911, "global_step": 518089, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0260486602783203, "global_step": 518090, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9846467971801758, "global_step": 518091, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0782687664031982, "global_step": 518092, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.031869888305664, "global_step": 518093, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.004237174987793, "global_step": 518094, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0178284645080566, "global_step": 518095, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9539743661880493, "global_step": 518096, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9853830337524414, "global_step": 518097, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.00514817237854, "global_step": 518098, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.023408889770508, "global_step": 518099, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.055333137512207, "global_step": 518100, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.061769723892212, "global_step": 518101, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9422285556793213, "global_step": 518102, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.145566463470459, "global_step": 518103, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1608352661132812, "global_step": 518104, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1064722537994385, "global_step": 518105, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0066676139831543, "global_step": 518106, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.047407388687134, "global_step": 518107, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.026451826095581, "global_step": 518108, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0193300247192383, "global_step": 518109, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0361478328704834, "global_step": 518110, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.094205856323242, "global_step": 518111, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.009794235229492, "global_step": 518112, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0137786865234375, "global_step": 518113, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0804991722106934, "global_step": 518114, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9879372119903564, "global_step": 518115, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0514602661132812, "global_step": 518116, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0940496921539307, "global_step": 518117, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0774149894714355, "global_step": 518118, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0015947818756104, "global_step": 518119, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0811171531677246, "global_step": 518120, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.961579442024231, "global_step": 518121, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9568374156951904, "global_step": 518122, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1117868423461914, "global_step": 518123, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9941484928131104, "global_step": 518124, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0680155754089355, "global_step": 518125, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9692480564117432, "global_step": 518126, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0523786544799805, "global_step": 518127, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.054152488708496, "global_step": 518128, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0779526233673096, "global_step": 518129, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0643067359924316, "global_step": 518130, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0749597549438477, "global_step": 518131, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9388582706451416, "global_step": 518132, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.149827241897583, "global_step": 518133, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.008275032043457, "global_step": 518134, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.142383337020874, "global_step": 518135, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9816975593566895, "global_step": 518136, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1150119304656982, "global_step": 518137, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9843790531158447, "global_step": 518138, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0627262592315674, "global_step": 518139, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0081889629364014, "global_step": 518140, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.067552089691162, "global_step": 518141, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1289925575256348, "global_step": 518142, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9838366508483887, "global_step": 518143, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0134036540985107, "global_step": 518144, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0862855911254883, "global_step": 518145, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.124943256378174, "global_step": 518146, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0022692680358887, "global_step": 518147, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.03045916557312, "global_step": 518148, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0464508533477783, "global_step": 518149, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0017647743225098, "global_step": 518150, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.063000202178955, "global_step": 518151, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.03706431388855, "global_step": 518152, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0150299072265625, "global_step": 518153, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0810070037841797, "global_step": 518154, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0434770584106445, "global_step": 518155, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1352128982543945, "global_step": 518156, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0856032371520996, "global_step": 518157, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0031023025512695, "global_step": 518158, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.057494640350342, "global_step": 518159, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.117701530456543, "global_step": 518160, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0660293102264404, "global_step": 518161, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9688539505004883, "global_step": 518162, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.096466302871704, "global_step": 518163, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0340914726257324, "global_step": 518164, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.109048366546631, "global_step": 518165, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.047283411026001, "global_step": 518166, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.134990930557251, "global_step": 518167, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9883859157562256, "global_step": 518168, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.114102602005005, "global_step": 518169, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0831727981567383, "global_step": 518170, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.135842800140381, "global_step": 518171, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0245752334594727, "global_step": 518172, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0215954780578613, "global_step": 518173, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0737786293029785, "global_step": 518174, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.100935459136963, "global_step": 518175, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0623297691345215, "global_step": 518176, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9680360555648804, "global_step": 518177, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0402586460113525, "global_step": 518178, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.05265736579895, "global_step": 518179, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.092717170715332, "global_step": 518180, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.099562644958496, "global_step": 518181, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9596331119537354, "global_step": 518182, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.027181386947632, "global_step": 518183, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0406882762908936, "global_step": 518184, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.99163019657135, "global_step": 518185, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.132952928543091, "global_step": 518186, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1096909046173096, "global_step": 518187, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.052570104598999, "global_step": 518188, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0956737995147705, "global_step": 518189, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0334370136260986, "global_step": 518190, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.032045841217041, "global_step": 518191, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0433003902435303, "global_step": 518192, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.152445077896118, "global_step": 518193, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.03490948677063, "global_step": 518194, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9889440536499023, "global_step": 518195, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0901060104370117, "global_step": 518196, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1461660861968994, "global_step": 518197, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0426127910614014, "global_step": 518198, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.052022933959961, "global_step": 518199, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0589468479156494, "global_step": 518200, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0246644020080566, "global_step": 518201, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.09578800201416, "global_step": 518202, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9968457221984863, "global_step": 518203, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0131642818450928, "global_step": 518204, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.103449583053589, "global_step": 518205, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.085561513900757, "global_step": 518206, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0026841163635254, "global_step": 518207, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0137016773223877, "global_step": 518208, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0645413398742676, "global_step": 518209, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.130864381790161, "global_step": 518210, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.000588893890381, "global_step": 518211, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0257365703582764, "global_step": 518212, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0812489986419678, "global_step": 518213, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.078749895095825, "global_step": 518214, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.112926721572876, "global_step": 518215, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0630602836608887, "global_step": 518216, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.023536443710327, "global_step": 518217, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1138997077941895, "global_step": 518218, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0401008129119873, "global_step": 518219, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9900554418563843, "global_step": 518220, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.011857748031616, "global_step": 518221, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0406572818756104, "global_step": 518222, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.101254463195801, "global_step": 518223, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0940186977386475, "global_step": 518224, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0874314308166504, "global_step": 518225, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0768589973449707, "global_step": 518226, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.073554754257202, "global_step": 518227, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9962443113327026, "global_step": 518228, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0999324321746826, "global_step": 518229, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0275089740753174, "global_step": 518230, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.077132225036621, "global_step": 518231, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.060182809829712, "global_step": 518232, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0069568157196045, "global_step": 518233, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9888290166854858, "global_step": 518234, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9705517292022705, "global_step": 518235, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1041693687438965, "global_step": 518236, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9633960723876953, "global_step": 518237, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0170397758483887, "global_step": 518238, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9853922128677368, "global_step": 518239, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0373191833496094, "global_step": 518240, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9846681356430054, "global_step": 518241, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.026418924331665, "global_step": 518242, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.082185745239258, "global_step": 518243, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.100922107696533, "global_step": 518244, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.096270799636841, "global_step": 518245, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.083554267883301, "global_step": 518246, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.034505844116211, "global_step": 518247, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.032533645629883, "global_step": 518248, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0915606021881104, "global_step": 518249, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0758490562438965, "global_step": 518250, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0339598655700684, "global_step": 518251, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9910963773727417, "global_step": 518252, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.083071708679199, "global_step": 518253, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1036536693573, "global_step": 518254, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0611441135406494, "global_step": 518255, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0458226203918457, "global_step": 518256, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.017172336578369, "global_step": 518257, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1250412464141846, "global_step": 518258, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9963937997817993, "global_step": 518259, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.090353012084961, "global_step": 518260, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.04990291595459, "global_step": 518261, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0545759201049805, "global_step": 518262, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1606831550598145, "global_step": 518263, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9781244993209839, "global_step": 518264, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.084639072418213, "global_step": 518265, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0192251205444336, "global_step": 518266, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1257832050323486, "global_step": 518267, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9496140480041504, "global_step": 518268, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0520904064178467, "global_step": 518269, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.038865804672241, "global_step": 518270, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.006779909133911, "global_step": 518271, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0623717308044434, "global_step": 518272, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0649659633636475, "global_step": 518273, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.034362316131592, "global_step": 518274, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0523576736450195, "global_step": 518275, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0502419471740723, "global_step": 518276, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.063121795654297, "global_step": 518277, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.033961057662964, "global_step": 518278, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.156898260116577, "global_step": 518279, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.091643810272217, "global_step": 518280, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9515299797058105, "global_step": 518281, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0575714111328125, "global_step": 518282, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.059938907623291, "global_step": 518283, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0677731037139893, "global_step": 518284, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0885555744171143, "global_step": 518285, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0723137855529785, "global_step": 518286, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0729832649230957, "global_step": 518287, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0001657009124756, "global_step": 518288, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1283164024353027, "global_step": 518289, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.122438669204712, "global_step": 518290, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9773906469345093, "global_step": 518291, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0246691703796387, "global_step": 518292, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1392457485198975, "global_step": 518293, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0466842651367188, "global_step": 518294, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.042351722717285, "global_step": 518295, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0516257286071777, "global_step": 518296, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9858884811401367, "global_step": 518297, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0754330158233643, "global_step": 518298, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.125126600265503, "global_step": 518299, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.136353015899658, "global_step": 518300, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9960579872131348, "global_step": 518301, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0074574947357178, "global_step": 518302, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1276211738586426, "global_step": 518303, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1195502281188965, "global_step": 518304, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0545434951782227, "global_step": 518305, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0647976398468018, "global_step": 518306, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.132444381713867, "global_step": 518307, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.089245319366455, "global_step": 518308, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0132932662963867, "global_step": 518309, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.087956666946411, "global_step": 518310, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1047089099884033, "global_step": 518311, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0348918437957764, "global_step": 518312, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0680031776428223, "global_step": 518313, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0554559230804443, "global_step": 518314, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.074373245239258, "global_step": 518315, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.057742118835449, "global_step": 518316, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0375075340270996, "global_step": 518317, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1086177825927734, "global_step": 518318, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1720683574676514, "global_step": 518319, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.025214195251465, "global_step": 518320, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.054492712020874, "global_step": 518321, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9676746129989624, "global_step": 518322, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.080953359603882, "global_step": 518323, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0166234970092773, "global_step": 518324, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.085458517074585, "global_step": 518325, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1258480548858643, "global_step": 518326, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.157182216644287, "global_step": 518327, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.109426498413086, "global_step": 518328, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0292043685913086, "global_step": 518329, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9957972764968872, "global_step": 518330, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0118300914764404, "global_step": 518331, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.038020133972168, "global_step": 518332, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.040670871734619, "global_step": 518333, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.018144130706787, "global_step": 518334, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9731675386428833, "global_step": 518335, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0805118083953857, "global_step": 518336, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.095564365386963, "global_step": 518337, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0271458625793457, "global_step": 518338, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0613508224487305, "global_step": 518339, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1077911853790283, "global_step": 518340, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.132828950881958, "global_step": 518341, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.079803943634033, "global_step": 518342, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9554890394210815, "global_step": 518343, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0701968669891357, "global_step": 518344, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.017803907394409, "global_step": 518345, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9487507343292236, "global_step": 518346, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9932544231414795, "global_step": 518347, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0491838455200195, "global_step": 518348, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0488853454589844, "global_step": 518349, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0707743167877197, "global_step": 518350, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0713822841644287, "global_step": 518351, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.051459312438965, "global_step": 518352, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.073809862136841, "global_step": 518353, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.068208932876587, "global_step": 518354, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0283565521240234, "global_step": 518355, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.105625629425049, "global_step": 518356, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.049553871154785, "global_step": 518357, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.060650110244751, "global_step": 518358, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9797886610031128, "global_step": 518359, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.021749496459961, "global_step": 518360, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0285489559173584, "global_step": 518361, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.082212448120117, "global_step": 518362, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.114966869354248, "global_step": 518363, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.886914849281311, "global_step": 518364, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0349807739257812, "global_step": 518365, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9885509014129639, "global_step": 518366, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.033517360687256, "global_step": 518367, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9540512561798096, "global_step": 518368, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9690707921981812, "global_step": 518369, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9837892055511475, "global_step": 518370, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.996482253074646, "global_step": 518371, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.065563201904297, "global_step": 518372, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0461738109588623, "global_step": 518373, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0479578971862793, "global_step": 518374, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0824549198150635, "global_step": 518375, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.020369529724121, "global_step": 518376, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0740854740142822, "global_step": 518377, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9594004154205322, "global_step": 518378, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9809136390686035, "global_step": 518379, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.081516981124878, "global_step": 518380, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9702978134155273, "global_step": 518381, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9346957206726074, "global_step": 518382, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.074687957763672, "global_step": 518383, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.068014621734619, "global_step": 518384, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9863380193710327, "global_step": 518385, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.963639736175537, "global_step": 518386, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.996420979499817, "global_step": 518387, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1318578720092773, "global_step": 518388, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.073333501815796, "global_step": 518389, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0434396266937256, "global_step": 518390, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0323474407196045, "global_step": 518391, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0546069145202637, "global_step": 518392, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.058720827102661, "global_step": 518393, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0674118995666504, "global_step": 518394, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0344340801239014, "global_step": 518395, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9866529703140259, "global_step": 518396, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.961524248123169, "global_step": 518397, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.940011739730835, "global_step": 518398, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.067866802215576, "global_step": 518399, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0765647888183594, "global_step": 518400, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0936715602874756, "global_step": 518401, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.07171630859375, "global_step": 518402, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0585992336273193, "global_step": 518403, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1161868572235107, "global_step": 518404, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0272791385650635, "global_step": 518405, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0091166496276855, "global_step": 518406, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0429694652557373, "global_step": 518407, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0496506690979004, "global_step": 518408, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1019723415374756, "global_step": 518409, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1258811950683594, "global_step": 518410, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1143455505371094, "global_step": 518411, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9971989393234253, "global_step": 518412, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0748584270477295, "global_step": 518413, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1226744651794434, "global_step": 518414, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0205447673797607, "global_step": 518415, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.992874026298523, "global_step": 518416, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0427639484405518, "global_step": 518417, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1178908348083496, "global_step": 518418, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1832973957061768, "global_step": 518419, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0302412509918213, "global_step": 518420, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.113839864730835, "global_step": 518421, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.008598566055298, "global_step": 518422, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0543041229248047, "global_step": 518423, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.079728841781616, "global_step": 518424, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.019418478012085, "global_step": 518425, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1043615341186523, "global_step": 518426, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.152312994003296, "global_step": 518427, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0316879749298096, "global_step": 518428, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.046654462814331, "global_step": 518429, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0743565559387207, "global_step": 518430, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.110330820083618, "global_step": 518431, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0525083541870117, "global_step": 518432, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1122350692749023, "global_step": 518433, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9735233783721924, "global_step": 518434, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0381064414978027, "global_step": 518435, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0997018814086914, "global_step": 518436, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9995614290237427, "global_step": 518437, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0852723121643066, "global_step": 518438, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0273070335388184, "global_step": 518439, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0102200508117676, "global_step": 518440, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0698959827423096, "global_step": 518441, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.087244987487793, "global_step": 518442, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0075438022613525, "global_step": 518443, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.031201124191284, "global_step": 518444, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.111480236053467, "global_step": 518445, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9653242826461792, "global_step": 518446, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0159876346588135, "global_step": 518447, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.138321876525879, "global_step": 518448, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0655384063720703, "global_step": 518449, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.058117628097534, "global_step": 518450, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.031817674636841, "global_step": 518451, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.074354648590088, "global_step": 518452, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0059738159179688, "global_step": 518453, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.134460210800171, "global_step": 518454, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.014413595199585, "global_step": 518455, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.060136079788208, "global_step": 518456, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0906429290771484, "global_step": 518457, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0135035514831543, "global_step": 518458, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.054222583770752, "global_step": 518459, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.974142074584961, "global_step": 518460, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0170466899871826, "global_step": 518461, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0529568195343018, "global_step": 518462, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0469961166381836, "global_step": 518463, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.102900743484497, "global_step": 518464, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0298609733581543, "global_step": 518465, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.039553642272949, "global_step": 518466, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0548250675201416, "global_step": 518467, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.097611904144287, "global_step": 518468, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0191071033477783, "global_step": 518469, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0269899368286133, "global_step": 518470, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0576939582824707, "global_step": 518471, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0803298950195312, "global_step": 518472, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.992315411567688, "global_step": 518473, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.8995099067687988, "global_step": 518474, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.050205945968628, "global_step": 518475, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.967650294303894, "global_step": 518476, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.075460433959961, "global_step": 518477, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0952072143554688, "global_step": 518478, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1002769470214844, "global_step": 518479, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0318050384521484, "global_step": 518480, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.054856300354004, "global_step": 518481, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0061562061309814, "global_step": 518482, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.019543409347534, "global_step": 518483, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.019829511642456, "global_step": 518484, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.026099920272827, "global_step": 518485, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9897987842559814, "global_step": 518486, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.075091600418091, "global_step": 518487, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0547142028808594, "global_step": 518488, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1276259422302246, "global_step": 518489, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.086604356765747, "global_step": 518490, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0149409770965576, "global_step": 518491, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0915069580078125, "global_step": 518492, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9479364156723022, "global_step": 518493, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0600838661193848, "global_step": 518494, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0882115364074707, "global_step": 518495, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.041229486465454, "global_step": 518496, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.073333740234375, "global_step": 518497, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.018613815307617, "global_step": 518498, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0811595916748047, "global_step": 518499, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.010748863220215, "global_step": 518500, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0749671459198, "global_step": 518501, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.94707453250885, "global_step": 518502, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.052727460861206, "global_step": 518503, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.097947597503662, "global_step": 518504, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0804004669189453, "global_step": 518505, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.003009796142578, "global_step": 518506, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.989456295967102, "global_step": 518507, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0742688179016113, "global_step": 518508, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.00834321975708, "global_step": 518509, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0308284759521484, "global_step": 518510, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.032071113586426, "global_step": 518511, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0530269145965576, "global_step": 518512, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0221023559570312, "global_step": 518513, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.072080373764038, "global_step": 518514, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0086798667907715, "global_step": 518515, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9387646913528442, "global_step": 518516, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.098422050476074, "global_step": 518517, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.049934148788452, "global_step": 518518, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1380209922790527, "global_step": 518519, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9634549617767334, "global_step": 518520, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.988606333732605, "global_step": 518521, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9958183765411377, "global_step": 518522, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.122176170349121, "global_step": 518523, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.027775526046753, "global_step": 518524, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.040562868118286, "global_step": 518525, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.033830165863037, "global_step": 518526, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0756568908691406, "global_step": 518527, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9704506397247314, "global_step": 518528, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.9665329456329346, "global_step": 518529, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0839595794677734, "global_step": 518530, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.984033226966858, "global_step": 518531, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.007646322250366, "global_step": 518532, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0735089778900146, "global_step": 518533, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1143627166748047, "global_step": 518534, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.056291103363037, "global_step": 518535, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0401647090911865, "global_step": 518536, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0084409713745117, "global_step": 518537, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.089829921722412, "global_step": 518538, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0649971961975098, "global_step": 518539, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.110830307006836, "global_step": 518540, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.13484263420105, "global_step": 518541, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.062246799468994, "global_step": 518542, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.1248953342437744, "global_step": 518543, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0858120918273926, "global_step": 518544, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.064911365509033, "global_step": 518545, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.063108444213867, "global_step": 518546, "epoch": 884, "lr": 5e-05}
{"train_loss": 2.0444703102111816, "global_step": 518547, "epoch": 884, "lr": 5e-05}
{"train_loss": 1.8882980346679688, "global_step": 518548, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.106372117996216, "global_step": 518549, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0087594985961914, "global_step": 518550, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0129878520965576, "global_step": 518551, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.912868618965149, "global_step": 518552, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0655736923217773, "global_step": 518553, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0775468349456787, "global_step": 518554, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9349864721298218, "global_step": 518555, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1226844787597656, "global_step": 518556, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0596745014190674, "global_step": 518557, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0472254753112793, "global_step": 518558, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.024691581726074, "global_step": 518559, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.127439022064209, "global_step": 518560, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0378923416137695, "global_step": 518561, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0223376750946045, "global_step": 518562, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9861496686935425, "global_step": 518563, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0523338317871094, "global_step": 518564, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.023177146911621, "global_step": 518565, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.988027811050415, "global_step": 518566, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.008242607116699, "global_step": 518567, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0080718994140625, "global_step": 518568, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.95248281955719, "global_step": 518569, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.013169527053833, "global_step": 518570, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9509387016296387, "global_step": 518571, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0971741676330566, "global_step": 518572, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.975220799446106, "global_step": 518573, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9775172472000122, "global_step": 518574, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0286457538604736, "global_step": 518575, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.983652114868164, "global_step": 518576, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.02228045463562, "global_step": 518577, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0008022785186768, "global_step": 518578, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.038332223892212, "global_step": 518579, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0555801391601562, "global_step": 518580, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.074927568435669, "global_step": 518581, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.979097604751587, "global_step": 518582, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9921444654464722, "global_step": 518583, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0885415077209473, "global_step": 518584, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0493478775024414, "global_step": 518585, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.031196117401123, "global_step": 518586, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0439112186431885, "global_step": 518587, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0408987998962402, "global_step": 518588, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.024054527282715, "global_step": 518589, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.025730848312378, "global_step": 518590, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.96254563331604, "global_step": 518591, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0335371494293213, "global_step": 518592, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0536890029907227, "global_step": 518593, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.994317650794983, "global_step": 518594, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9203779697418213, "global_step": 518595, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1404359340667725, "global_step": 518596, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.083798885345459, "global_step": 518597, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.006016492843628, "global_step": 518598, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.934333086013794, "global_step": 518599, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0270519256591797, "global_step": 518600, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0450801849365234, "global_step": 518601, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.095864772796631, "global_step": 518602, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.991524577140808, "global_step": 518603, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9960073232650757, "global_step": 518604, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0131020545959473, "global_step": 518605, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9773062467575073, "global_step": 518606, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9900473356246948, "global_step": 518607, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9853934049606323, "global_step": 518608, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.005328416824341, "global_step": 518609, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0158498287200928, "global_step": 518610, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.066373586654663, "global_step": 518611, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9245766401290894, "global_step": 518612, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0518572330474854, "global_step": 518613, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0431723594665527, "global_step": 518614, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9794042110443115, "global_step": 518615, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.01859188079834, "global_step": 518616, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0205564498901367, "global_step": 518617, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.064236640930176, "global_step": 518618, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9982852935791016, "global_step": 518619, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.094142198562622, "global_step": 518620, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0054819583892822, "global_step": 518621, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0504848957061768, "global_step": 518622, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9998387098312378, "global_step": 518623, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0008633136749268, "global_step": 518624, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9628770351409912, "global_step": 518625, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9986375570297241, "global_step": 518626, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0908119678497314, "global_step": 518627, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.987351655960083, "global_step": 518628, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9905314445495605, "global_step": 518629, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9685784578323364, "global_step": 518630, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9903696775436401, "global_step": 518631, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.945302128791809, "global_step": 518632, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1083426475524902, "global_step": 518633, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0665745735168457, "global_step": 518634, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9299087524414062, "global_step": 518635, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0533814430236816, "global_step": 518636, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0104353427886963, "global_step": 518637, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.092435359954834, "global_step": 518638, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0580527782440186, "global_step": 518639, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0789127349853516, "global_step": 518640, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9891294240951538, "global_step": 518641, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.106492519378662, "global_step": 518642, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.084984540939331, "global_step": 518643, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.010560989379883, "global_step": 518644, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.140315532684326, "global_step": 518645, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9791029691696167, "global_step": 518646, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.026498794555664, "global_step": 518647, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.105745792388916, "global_step": 518648, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0743184089660645, "global_step": 518649, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9824281930923462, "global_step": 518650, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0083916187286377, "global_step": 518651, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0163307189941406, "global_step": 518652, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1115477085113525, "global_step": 518653, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.055666208267212, "global_step": 518654, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.007866382598877, "global_step": 518655, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.02815318107605, "global_step": 518656, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0589611530303955, "global_step": 518657, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.040313243865967, "global_step": 518658, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0831222534179688, "global_step": 518659, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0769882202148438, "global_step": 518660, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.009124517440796, "global_step": 518661, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0312671661376953, "global_step": 518662, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1253974437713623, "global_step": 518663, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.014329433441162, "global_step": 518664, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.066274404525757, "global_step": 518665, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9488246440887451, "global_step": 518666, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.084789514541626, "global_step": 518667, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9950246810913086, "global_step": 518668, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0137088298797607, "global_step": 518669, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9980350732803345, "global_step": 518670, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9581156969070435, "global_step": 518671, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0544612407684326, "global_step": 518672, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.057180404663086, "global_step": 518673, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0090324878692627, "global_step": 518674, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0167245864868164, "global_step": 518675, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0194411277770996, "global_step": 518676, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.074337959289551, "global_step": 518677, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9327068328857422, "global_step": 518678, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.086599588394165, "global_step": 518679, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0483245849609375, "global_step": 518680, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.034088373184204, "global_step": 518681, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0349314212799072, "global_step": 518682, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0605716705322266, "global_step": 518683, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0204265117645264, "global_step": 518684, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0191659927368164, "global_step": 518685, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0858328342437744, "global_step": 518686, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0129144191741943, "global_step": 518687, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0094871520996094, "global_step": 518688, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0626580715179443, "global_step": 518689, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.009833574295044, "global_step": 518690, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9669880867004395, "global_step": 518691, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.062023639678955, "global_step": 518692, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0548672676086426, "global_step": 518693, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.068965435028076, "global_step": 518694, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1136295795440674, "global_step": 518695, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0324268341064453, "global_step": 518696, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0806522369384766, "global_step": 518697, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0766658782958984, "global_step": 518698, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.033529281616211, "global_step": 518699, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0472795963287354, "global_step": 518700, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1193981170654297, "global_step": 518701, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1034786701202393, "global_step": 518702, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0955448150634766, "global_step": 518703, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0968353748321533, "global_step": 518704, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9792497158050537, "global_step": 518705, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0179147720336914, "global_step": 518706, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0577948093414307, "global_step": 518707, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0583412647247314, "global_step": 518708, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0079843997955322, "global_step": 518709, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0266504287719727, "global_step": 518710, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0746593475341797, "global_step": 518711, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9701846837997437, "global_step": 518712, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.107053279876709, "global_step": 518713, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.082026243209839, "global_step": 518714, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.98576819896698, "global_step": 518715, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0194859504699707, "global_step": 518716, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.00864577293396, "global_step": 518717, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.04023814201355, "global_step": 518718, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9666776657104492, "global_step": 518719, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9898929595947266, "global_step": 518720, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9824070930480957, "global_step": 518721, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9874577522277832, "global_step": 518722, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9530353546142578, "global_step": 518723, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.021451234817505, "global_step": 518724, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9851908683776855, "global_step": 518725, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0740203857421875, "global_step": 518726, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0583128929138184, "global_step": 518727, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0235683917999268, "global_step": 518728, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.996636152267456, "global_step": 518729, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0743069648742676, "global_step": 518730, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0601446628570557, "global_step": 518731, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9768714904785156, "global_step": 518732, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9427058696746826, "global_step": 518733, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.023312568664551, "global_step": 518734, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9664318561553955, "global_step": 518735, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0140364170074463, "global_step": 518736, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9216721057891846, "global_step": 518737, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.03637433052063, "global_step": 518738, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.042173147201538, "global_step": 518739, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0728933811187744, "global_step": 518740, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9311360120773315, "global_step": 518741, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9988938570022583, "global_step": 518742, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0067615509033203, "global_step": 518743, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0372564792633057, "global_step": 518744, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1287460327148438, "global_step": 518745, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.065643072128296, "global_step": 518746, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0290350914001465, "global_step": 518747, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9929072856903076, "global_step": 518748, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9527643918991089, "global_step": 518749, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.054833173751831, "global_step": 518750, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0321879386901855, "global_step": 518751, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0323634147644043, "global_step": 518752, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9390153884887695, "global_step": 518753, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.009705066680908, "global_step": 518754, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0782699584960938, "global_step": 518755, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0852272510528564, "global_step": 518756, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0257320404052734, "global_step": 518757, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1419448852539062, "global_step": 518758, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0626308917999268, "global_step": 518759, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.958203911781311, "global_step": 518760, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.034139633178711, "global_step": 518761, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.012277364730835, "global_step": 518762, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.012533187866211, "global_step": 518763, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0036816596984863, "global_step": 518764, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0970232486724854, "global_step": 518765, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0251948833465576, "global_step": 518766, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9531900882720947, "global_step": 518767, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0263571739196777, "global_step": 518768, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.073819160461426, "global_step": 518769, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0960659980773926, "global_step": 518770, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.084604501724243, "global_step": 518771, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.044520378112793, "global_step": 518772, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0409514904022217, "global_step": 518773, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.018489360809326, "global_step": 518774, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.024367094039917, "global_step": 518775, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0454249382019043, "global_step": 518776, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0264763832092285, "global_step": 518777, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.044656753540039, "global_step": 518778, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1236252784729004, "global_step": 518779, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.099093198776245, "global_step": 518780, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0161595344543457, "global_step": 518781, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0617480278015137, "global_step": 518782, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0190577507019043, "global_step": 518783, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9370431900024414, "global_step": 518784, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0058677196502686, "global_step": 518785, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0073227882385254, "global_step": 518786, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.010387897491455, "global_step": 518787, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.095749855041504, "global_step": 518788, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0629220008850098, "global_step": 518789, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0880303382873535, "global_step": 518790, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.996174693107605, "global_step": 518791, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0138516426086426, "global_step": 518792, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9626905918121338, "global_step": 518793, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.951956868171692, "global_step": 518794, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0858452320098877, "global_step": 518795, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0127055644989014, "global_step": 518796, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0302231311798096, "global_step": 518797, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.010298013687134, "global_step": 518798, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.181549310684204, "global_step": 518799, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.047123670578003, "global_step": 518800, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0161213874816895, "global_step": 518801, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0391056537628174, "global_step": 518802, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0204477310180664, "global_step": 518803, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0974032878875732, "global_step": 518804, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.124439239501953, "global_step": 518805, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.035979747772217, "global_step": 518806, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0586986541748047, "global_step": 518807, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0775856971740723, "global_step": 518808, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.084080457687378, "global_step": 518809, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0898122787475586, "global_step": 518810, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.906982660293579, "global_step": 518811, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0037994384765625, "global_step": 518812, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0727622509002686, "global_step": 518813, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9986488819122314, "global_step": 518814, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0972652435302734, "global_step": 518815, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0153346061706543, "global_step": 518816, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.067107677459717, "global_step": 518817, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0796546936035156, "global_step": 518818, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.082869529724121, "global_step": 518819, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9955987930297852, "global_step": 518820, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.072383165359497, "global_step": 518821, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.096371650695801, "global_step": 518822, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.056828498840332, "global_step": 518823, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.965397834777832, "global_step": 518824, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0609281063079834, "global_step": 518825, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.018433094024658, "global_step": 518826, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0533978939056396, "global_step": 518827, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9990684986114502, "global_step": 518828, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0743627548217773, "global_step": 518829, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.121286153793335, "global_step": 518830, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1015477180480957, "global_step": 518831, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.029478073120117, "global_step": 518832, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0135269165039062, "global_step": 518833, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0407373905181885, "global_step": 518834, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1066031455993652, "global_step": 518835, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1368563175201416, "global_step": 518836, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.103149652481079, "global_step": 518837, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.132795810699463, "global_step": 518838, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.02559757232666, "global_step": 518839, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9727071523666382, "global_step": 518840, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0517613887786865, "global_step": 518841, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0724618434906006, "global_step": 518842, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.943820834159851, "global_step": 518843, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9952876567840576, "global_step": 518844, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0557916164398193, "global_step": 518845, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0000758171081543, "global_step": 518846, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.007378101348877, "global_step": 518847, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0474324226379395, "global_step": 518848, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0381593704223633, "global_step": 518849, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0203468799591064, "global_step": 518850, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0739359855651855, "global_step": 518851, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9947781562805176, "global_step": 518852, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0027782917022705, "global_step": 518853, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.072268486022949, "global_step": 518854, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0555691719055176, "global_step": 518855, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.104666233062744, "global_step": 518856, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0091195106506348, "global_step": 518857, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.03353214263916, "global_step": 518858, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9851913452148438, "global_step": 518859, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0694098472595215, "global_step": 518860, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0839145183563232, "global_step": 518861, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.016859531402588, "global_step": 518862, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.036468029022217, "global_step": 518863, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.045454740524292, "global_step": 518864, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0538885593414307, "global_step": 518865, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.050950765609741, "global_step": 518866, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0417773723602295, "global_step": 518867, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0313198566436768, "global_step": 518868, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0294432640075684, "global_step": 518869, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0355474948883057, "global_step": 518870, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.033630609512329, "global_step": 518871, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.038395643234253, "global_step": 518872, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.043826103210449, "global_step": 518873, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.138105869293213, "global_step": 518874, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1073389053344727, "global_step": 518875, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.014324426651001, "global_step": 518876, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.041005849838257, "global_step": 518877, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0207955837249756, "global_step": 518878, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.089566230773926, "global_step": 518879, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0104317665100098, "global_step": 518880, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.046356439590454, "global_step": 518881, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.073275566101074, "global_step": 518882, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.04744291305542, "global_step": 518883, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0232229232788086, "global_step": 518884, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0796866416931152, "global_step": 518885, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0325145721435547, "global_step": 518886, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0431711673736572, "global_step": 518887, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1027731895446777, "global_step": 518888, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.018010377883911, "global_step": 518889, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0766804218292236, "global_step": 518890, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0243632793426514, "global_step": 518891, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.027735471725464, "global_step": 518892, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0211167335510254, "global_step": 518893, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.014580726623535, "global_step": 518894, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0723586082458496, "global_step": 518895, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.012598752975464, "global_step": 518896, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0007994174957275, "global_step": 518897, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0366697311401367, "global_step": 518898, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0576088428497314, "global_step": 518899, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1233482360839844, "global_step": 518900, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.015995740890503, "global_step": 518901, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.011119842529297, "global_step": 518902, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.01969313621521, "global_step": 518903, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0186538696289062, "global_step": 518904, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0287280082702637, "global_step": 518905, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0133049488067627, "global_step": 518906, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0520620346069336, "global_step": 518907, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.091776132583618, "global_step": 518908, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9765901565551758, "global_step": 518909, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0718882083892822, "global_step": 518910, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0812065601348877, "global_step": 518911, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0210793018341064, "global_step": 518912, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.087296724319458, "global_step": 518913, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9576576948165894, "global_step": 518914, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0655486583709717, "global_step": 518915, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.048661231994629, "global_step": 518916, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.00775146484375, "global_step": 518917, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0465240478515625, "global_step": 518918, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.018583059310913, "global_step": 518919, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0010640621185303, "global_step": 518920, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0295119285583496, "global_step": 518921, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0607473850250244, "global_step": 518922, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0616278648376465, "global_step": 518923, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0061700344085693, "global_step": 518924, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.093615770339966, "global_step": 518925, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0109827518463135, "global_step": 518926, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.099785804748535, "global_step": 518927, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0230045318603516, "global_step": 518928, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0376574993133545, "global_step": 518929, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.987204670906067, "global_step": 518930, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1000192165374756, "global_step": 518931, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.102785110473633, "global_step": 518932, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9936295747756958, "global_step": 518933, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0589704513549805, "global_step": 518934, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.006239175796509, "global_step": 518935, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0125584602355957, "global_step": 518936, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9837462902069092, "global_step": 518937, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0150418281555176, "global_step": 518938, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.02901554107666, "global_step": 518939, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0970396995544434, "global_step": 518940, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.08882999420166, "global_step": 518941, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.086703300476074, "global_step": 518942, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1090471744537354, "global_step": 518943, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.142219066619873, "global_step": 518944, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.085669994354248, "global_step": 518945, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0267343521118164, "global_step": 518946, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0041840076446533, "global_step": 518947, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0458011627197266, "global_step": 518948, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.078076124191284, "global_step": 518949, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.060422658920288, "global_step": 518950, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.068162202835083, "global_step": 518951, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.061642646789551, "global_step": 518952, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.051633358001709, "global_step": 518953, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9660030603408813, "global_step": 518954, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.978378415107727, "global_step": 518955, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.96877121925354, "global_step": 518956, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0199708938598633, "global_step": 518957, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0154948234558105, "global_step": 518958, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0537991523742676, "global_step": 518959, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0861613750457764, "global_step": 518960, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.095285177230835, "global_step": 518961, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.022712469100952, "global_step": 518962, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.038832902908325, "global_step": 518963, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0830819606781006, "global_step": 518964, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0344011783599854, "global_step": 518965, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1166188716888428, "global_step": 518966, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1325337886810303, "global_step": 518967, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.014921188354492, "global_step": 518968, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9998881816864014, "global_step": 518969, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.025261402130127, "global_step": 518970, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.059227466583252, "global_step": 518971, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.126451015472412, "global_step": 518972, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9434062242507935, "global_step": 518973, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.04343318939209, "global_step": 518974, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0855023860931396, "global_step": 518975, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9966922998428345, "global_step": 518976, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9983848333358765, "global_step": 518977, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9936567544937134, "global_step": 518978, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1057705879211426, "global_step": 518979, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.069528579711914, "global_step": 518980, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.022409200668335, "global_step": 518981, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9899669885635376, "global_step": 518982, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0469470024108887, "global_step": 518983, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9697391986846924, "global_step": 518984, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.017017364501953, "global_step": 518985, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9739234447479248, "global_step": 518986, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0626182556152344, "global_step": 518987, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0774083137512207, "global_step": 518988, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.978663444519043, "global_step": 518989, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.032245635986328, "global_step": 518990, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0801615715026855, "global_step": 518991, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0666298866271973, "global_step": 518992, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.142436981201172, "global_step": 518993, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.031721591949463, "global_step": 518994, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0342917442321777, "global_step": 518995, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9839533567428589, "global_step": 518996, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.050218343734741, "global_step": 518997, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0312469005584717, "global_step": 518998, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.999988079071045, "global_step": 518999, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0502326488494873, "global_step": 519000, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0572011470794678, "global_step": 519001, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0515012741088867, "global_step": 519002, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.024195909500122, "global_step": 519003, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0579211711883545, "global_step": 519004, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9913655519485474, "global_step": 519005, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0382940769195557, "global_step": 519006, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0489470958709717, "global_step": 519007, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9812806844711304, "global_step": 519008, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9999680519104004, "global_step": 519009, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9776545763015747, "global_step": 519010, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0914785861968994, "global_step": 519011, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.071406126022339, "global_step": 519012, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0021984577178955, "global_step": 519013, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9963510036468506, "global_step": 519014, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.019630193710327, "global_step": 519015, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0420165061950684, "global_step": 519016, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0343260765075684, "global_step": 519017, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0374364852905273, "global_step": 519018, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.095794200897217, "global_step": 519019, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.036245346069336, "global_step": 519020, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9964150190353394, "global_step": 519021, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0988636016845703, "global_step": 519022, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1208322048187256, "global_step": 519023, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0388622283935547, "global_step": 519024, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.104649782180786, "global_step": 519025, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0592920780181885, "global_step": 519026, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.047520637512207, "global_step": 519027, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.104485273361206, "global_step": 519028, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0199811458587646, "global_step": 519029, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1019253730773926, "global_step": 519030, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0339064598083496, "global_step": 519031, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9560062885284424, "global_step": 519032, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9629095792770386, "global_step": 519033, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0448644161224365, "global_step": 519034, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.158179759979248, "global_step": 519035, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.005574941635132, "global_step": 519036, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9959604740142822, "global_step": 519037, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.039057493209839, "global_step": 519038, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.062326192855835, "global_step": 519039, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9892191886901855, "global_step": 519040, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.046128988265991, "global_step": 519041, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.069359064102173, "global_step": 519042, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.991919994354248, "global_step": 519043, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0731706619262695, "global_step": 519044, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.101044178009033, "global_step": 519045, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.129844903945923, "global_step": 519046, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9920241832733154, "global_step": 519047, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0692861080169678, "global_step": 519048, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.123015880584717, "global_step": 519049, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.979034185409546, "global_step": 519050, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0544586181640625, "global_step": 519051, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.114982843399048, "global_step": 519052, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1160173416137695, "global_step": 519053, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0892388820648193, "global_step": 519054, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.062565326690674, "global_step": 519055, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9594168663024902, "global_step": 519056, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0286216735839844, "global_step": 519057, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0759878158569336, "global_step": 519058, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.063769578933716, "global_step": 519059, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0973000526428223, "global_step": 519060, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0676746368408203, "global_step": 519061, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0599312782287598, "global_step": 519062, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.077075958251953, "global_step": 519063, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.021939754486084, "global_step": 519064, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.961303472518921, "global_step": 519065, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.06420636177063, "global_step": 519066, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0924055576324463, "global_step": 519067, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.013962507247925, "global_step": 519068, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1159629821777344, "global_step": 519069, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0903589725494385, "global_step": 519070, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0323967933654785, "global_step": 519071, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1563899517059326, "global_step": 519072, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9883472919464111, "global_step": 519073, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9815466403961182, "global_step": 519074, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.034409761428833, "global_step": 519075, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0517454147338867, "global_step": 519076, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0539228916168213, "global_step": 519077, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0157549381256104, "global_step": 519078, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.056563377380371, "global_step": 519079, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.975085735321045, "global_step": 519080, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.029728889465332, "global_step": 519081, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.022639274597168, "global_step": 519082, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0741958618164062, "global_step": 519083, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0575358867645264, "global_step": 519084, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.09765362739563, "global_step": 519085, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.028529405593872, "global_step": 519086, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0766828060150146, "global_step": 519087, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.038085699081421, "global_step": 519088, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0330517292022705, "global_step": 519089, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.038470506668091, "global_step": 519090, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.025926113128662, "global_step": 519091, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.038496494293213, "global_step": 519092, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9844216108322144, "global_step": 519093, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0303006172180176, "global_step": 519094, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.058459520339966, "global_step": 519095, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0708134174346924, "global_step": 519096, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.030510425567627, "global_step": 519097, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.996620774269104, "global_step": 519098, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9605010747909546, "global_step": 519099, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0382351875305176, "global_step": 519100, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.00573992729187, "global_step": 519101, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1248364448547363, "global_step": 519102, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.070034980773926, "global_step": 519103, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0093929767608643, "global_step": 519104, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9797661304473877, "global_step": 519105, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0451159477233887, "global_step": 519106, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0901927947998047, "global_step": 519107, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.057295799255371, "global_step": 519108, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0255863666534424, "global_step": 519109, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.092287063598633, "global_step": 519110, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0435643196105957, "global_step": 519111, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.059744119644165, "global_step": 519112, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.037189483642578, "global_step": 519113, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9909436702728271, "global_step": 519114, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0575597286224365, "global_step": 519115, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.040661573410034, "global_step": 519116, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0388898849487305, "global_step": 519117, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0215964317321777, "global_step": 519118, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0919711589813232, "global_step": 519119, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0730490684509277, "global_step": 519120, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.065816879272461, "global_step": 519121, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9563028812408447, "global_step": 519122, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.076963186264038, "global_step": 519123, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0988707542419434, "global_step": 519124, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0603690147399902, "global_step": 519125, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.042085886001587, "global_step": 519126, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0093114376068115, "global_step": 519127, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.058054208755493, "global_step": 519128, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.094528913497925, "global_step": 519129, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.097205638885498, "global_step": 519130, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9893606901168823, "global_step": 519131, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.157099723815918, "global_step": 519132, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0754899978637695, "global_step": 519133, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.031708240509033, "global_step": 519134, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0180418491363525, "global_step": 519135, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0565364360809326, "global_step": 519136, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.008452892303467, "global_step": 519137, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1428167819976807, "global_step": 519138, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0218236446380615, "global_step": 519139, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0679895877838135, "global_step": 519140, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.087570905685425, "global_step": 519141, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0947139263153076, "global_step": 519142, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9966281652450562, "global_step": 519143, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.018022060394287, "global_step": 519144, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.066694974899292, "global_step": 519145, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.039454936981201, "global_step": 519146, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0872609615325928, "global_step": 519147, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0180907249450684, "global_step": 519148, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.041792869567871, "global_step": 519149, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.094078302383423, "global_step": 519150, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.104182004928589, "global_step": 519151, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9909923076629639, "global_step": 519152, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.116579055786133, "global_step": 519153, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9579881429672241, "global_step": 519154, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.022648811340332, "global_step": 519155, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9916777610778809, "global_step": 519156, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1066861152648926, "global_step": 519157, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0390281677246094, "global_step": 519158, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.003159999847412, "global_step": 519159, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0320019721984863, "global_step": 519160, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0392842292785645, "global_step": 519161, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.023233413696289, "global_step": 519162, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.973517656326294, "global_step": 519163, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1330041885375977, "global_step": 519164, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.061570644378662, "global_step": 519165, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.009561538696289, "global_step": 519166, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0050063133239746, "global_step": 519167, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.123462438583374, "global_step": 519168, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0248634815216064, "global_step": 519169, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0131709575653076, "global_step": 519170, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0828216075897217, "global_step": 519171, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9192585945129395, "global_step": 519172, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0792551040649414, "global_step": 519173, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.091200113296509, "global_step": 519174, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.029996156692505, "global_step": 519175, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0090150833129883, "global_step": 519176, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.003424882888794, "global_step": 519177, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0698184967041016, "global_step": 519178, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9794152975082397, "global_step": 519179, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0788462162017822, "global_step": 519180, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.087724447250366, "global_step": 519181, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0416784286499023, "global_step": 519182, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0349762439727783, "global_step": 519183, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9603489637374878, "global_step": 519184, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.990973949432373, "global_step": 519185, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0471062660217285, "global_step": 519186, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.993829607963562, "global_step": 519187, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.101806163787842, "global_step": 519188, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.113682985305786, "global_step": 519189, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9812231063842773, "global_step": 519190, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.062088966369629, "global_step": 519191, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0348644256591797, "global_step": 519192, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0400753021240234, "global_step": 519193, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.045085906982422, "global_step": 519194, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0786919593811035, "global_step": 519195, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.084179162979126, "global_step": 519196, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0510566234588623, "global_step": 519197, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0439746379852295, "global_step": 519198, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0913875102996826, "global_step": 519199, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.05346417427063, "global_step": 519200, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.025571346282959, "global_step": 519201, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.096312999725342, "global_step": 519202, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0613272190093994, "global_step": 519203, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9484336376190186, "global_step": 519204, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0147788524627686, "global_step": 519205, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1771669387817383, "global_step": 519206, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0466463565826416, "global_step": 519207, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0329644680023193, "global_step": 519208, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0251853466033936, "global_step": 519209, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.061102867126465, "global_step": 519210, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9754558801651, "global_step": 519211, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.035334348678589, "global_step": 519212, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9755975008010864, "global_step": 519213, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0141658782958984, "global_step": 519214, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.023944616317749, "global_step": 519215, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9556561708450317, "global_step": 519216, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.082547426223755, "global_step": 519217, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1369869709014893, "global_step": 519218, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0075480937957764, "global_step": 519219, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1200449466705322, "global_step": 519220, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0299510955810547, "global_step": 519221, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9847289323806763, "global_step": 519222, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0664525032043457, "global_step": 519223, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0693106651306152, "global_step": 519224, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0520668029785156, "global_step": 519225, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0682907104492188, "global_step": 519226, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9895085096359253, "global_step": 519227, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0104057788848877, "global_step": 519228, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0701491832733154, "global_step": 519229, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.069256067276001, "global_step": 519230, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0980446338653564, "global_step": 519231, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.003465414047241, "global_step": 519232, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.092006206512451, "global_step": 519233, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1090333461761475, "global_step": 519234, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.080840587615967, "global_step": 519235, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0085833072662354, "global_step": 519236, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.051284074783325, "global_step": 519237, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0666773319244385, "global_step": 519238, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.042834520339966, "global_step": 519239, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.095181703567505, "global_step": 519240, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.988133192062378, "global_step": 519241, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.064582347869873, "global_step": 519242, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0105533599853516, "global_step": 519243, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9929406642913818, "global_step": 519244, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.990159511566162, "global_step": 519245, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.016584873199463, "global_step": 519246, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.054659843444824, "global_step": 519247, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0403647422790527, "global_step": 519248, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9746477603912354, "global_step": 519249, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.023102045059204, "global_step": 519250, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1076996326446533, "global_step": 519251, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.048069953918457, "global_step": 519252, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.06571888923645, "global_step": 519253, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9800711870193481, "global_step": 519254, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.015110731124878, "global_step": 519255, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.036156415939331, "global_step": 519256, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.971789836883545, "global_step": 519257, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.15976881980896, "global_step": 519258, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0476465225219727, "global_step": 519259, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0633230209350586, "global_step": 519260, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.031440496444702, "global_step": 519261, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0402169227600098, "global_step": 519262, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0229504108428955, "global_step": 519263, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.077130079269409, "global_step": 519264, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.08719539642334, "global_step": 519265, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0228798389434814, "global_step": 519266, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0361311435699463, "global_step": 519267, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.085019111633301, "global_step": 519268, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9908307790756226, "global_step": 519269, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.032916784286499, "global_step": 519270, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0292580127716064, "global_step": 519271, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0064408779144287, "global_step": 519272, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0054099559783936, "global_step": 519273, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0470807552337646, "global_step": 519274, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0367090702056885, "global_step": 519275, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.998270034790039, "global_step": 519276, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.094015598297119, "global_step": 519277, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9965029954910278, "global_step": 519278, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9518523216247559, "global_step": 519279, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.022465705871582, "global_step": 519280, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.047905683517456, "global_step": 519281, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.032127618789673, "global_step": 519282, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1062729358673096, "global_step": 519283, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0388576984405518, "global_step": 519284, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1087522506713867, "global_step": 519285, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.109945774078369, "global_step": 519286, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.036099910736084, "global_step": 519287, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.020866632461548, "global_step": 519288, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.060849905014038, "global_step": 519289, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0312986373901367, "global_step": 519290, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0314443111419678, "global_step": 519291, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.069850206375122, "global_step": 519292, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.07458758354187, "global_step": 519293, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.062791347503662, "global_step": 519294, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.011810541152954, "global_step": 519295, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.962180256843567, "global_step": 519296, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.060399055480957, "global_step": 519297, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9837843179702759, "global_step": 519298, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.986056923866272, "global_step": 519299, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0530905723571777, "global_step": 519300, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9583699703216553, "global_step": 519301, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.086766242980957, "global_step": 519302, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0020627975463867, "global_step": 519303, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.01859188079834, "global_step": 519304, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.020677328109741, "global_step": 519305, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.027334213256836, "global_step": 519306, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.053870916366577, "global_step": 519307, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.076256036758423, "global_step": 519308, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.008500337600708, "global_step": 519309, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0671277046203613, "global_step": 519310, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.118351936340332, "global_step": 519311, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.104559898376465, "global_step": 519312, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9410066604614258, "global_step": 519313, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0653188228607178, "global_step": 519314, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9979029893875122, "global_step": 519315, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9948886632919312, "global_step": 519316, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.107879877090454, "global_step": 519317, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1103522777557373, "global_step": 519318, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.02445912361145, "global_step": 519319, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.034843921661377, "global_step": 519320, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1347568035125732, "global_step": 519321, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.111417055130005, "global_step": 519322, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1276891231536865, "global_step": 519323, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0248448848724365, "global_step": 519324, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.064563035964966, "global_step": 519325, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9074028730392456, "global_step": 519326, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0463247299194336, "global_step": 519327, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.03666090965271, "global_step": 519328, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9379417896270752, "global_step": 519329, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0586025714874268, "global_step": 519330, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.125835657119751, "global_step": 519331, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0295517444610596, "global_step": 519332, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.09169340133667, "global_step": 519333, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0161099433898926, "global_step": 519334, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0439341068267822, "global_step": 519335, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0245518684387207, "global_step": 519336, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.01112961769104, "global_step": 519337, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.086118459701538, "global_step": 519338, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.040889024734497, "global_step": 519339, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0223796367645264, "global_step": 519340, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1163933277130127, "global_step": 519341, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0404629707336426, "global_step": 519342, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.090390682220459, "global_step": 519343, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.015209674835205, "global_step": 519344, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9875870943069458, "global_step": 519345, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1328539848327637, "global_step": 519346, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.024367094039917, "global_step": 519347, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.125877618789673, "global_step": 519348, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.007986545562744, "global_step": 519349, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0761592388153076, "global_step": 519350, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.166707754135132, "global_step": 519351, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0351784229278564, "global_step": 519352, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.024848461151123, "global_step": 519353, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9637892246246338, "global_step": 519354, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.037986993789673, "global_step": 519355, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0027120113372803, "global_step": 519356, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0670783519744873, "global_step": 519357, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9503233432769775, "global_step": 519358, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.046447992324829, "global_step": 519359, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.027256488800049, "global_step": 519360, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.118497848510742, "global_step": 519361, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1212964057922363, "global_step": 519362, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1190383434295654, "global_step": 519363, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.055694580078125, "global_step": 519364, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.109581470489502, "global_step": 519365, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9705883264541626, "global_step": 519366, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.010587692260742, "global_step": 519367, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.035961389541626, "global_step": 519368, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1031417846679688, "global_step": 519369, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.048651933670044, "global_step": 519370, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9294688701629639, "global_step": 519371, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0191543102264404, "global_step": 519372, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.030195713043213, "global_step": 519373, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.098839044570923, "global_step": 519374, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.08394455909729, "global_step": 519375, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.006824254989624, "global_step": 519376, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1223206520080566, "global_step": 519377, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1028566360473633, "global_step": 519378, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.083723545074463, "global_step": 519379, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0050792694091797, "global_step": 519380, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0680794715881348, "global_step": 519381, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1176531314849854, "global_step": 519382, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0953028202056885, "global_step": 519383, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.046255111694336, "global_step": 519384, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.000896453857422, "global_step": 519385, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.113621234893799, "global_step": 519386, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0542690753936768, "global_step": 519387, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.8720358610153198, "global_step": 519388, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.107912063598633, "global_step": 519389, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9895639419555664, "global_step": 519390, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.002098321914673, "global_step": 519391, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9808733463287354, "global_step": 519392, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.056215286254883, "global_step": 519393, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0174360275268555, "global_step": 519394, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0367588996887207, "global_step": 519395, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.020458698272705, "global_step": 519396, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.111462354660034, "global_step": 519397, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0763492584228516, "global_step": 519398, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0850799083709717, "global_step": 519399, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0352139472961426, "global_step": 519400, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0542831420898438, "global_step": 519401, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0632357597351074, "global_step": 519402, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9599103927612305, "global_step": 519403, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9635061025619507, "global_step": 519404, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.127417802810669, "global_step": 519405, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0654115676879883, "global_step": 519406, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0563926696777344, "global_step": 519407, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0312891006469727, "global_step": 519408, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9854974746704102, "global_step": 519409, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.038367748260498, "global_step": 519410, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0373294353485107, "global_step": 519411, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0976409912109375, "global_step": 519412, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1089553833007812, "global_step": 519413, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0378856658935547, "global_step": 519414, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.035958766937256, "global_step": 519415, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.02201247215271, "global_step": 519416, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.006699562072754, "global_step": 519417, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0609958171844482, "global_step": 519418, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0429458618164062, "global_step": 519419, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9270132780075073, "global_step": 519420, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.03245210647583, "global_step": 519421, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.111814022064209, "global_step": 519422, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.041106939315796, "global_step": 519423, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9952049255371094, "global_step": 519424, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0221362113952637, "global_step": 519425, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.125790596008301, "global_step": 519426, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.142444133758545, "global_step": 519427, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1130034923553467, "global_step": 519428, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0555202960968018, "global_step": 519429, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.021862268447876, "global_step": 519430, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0322930812835693, "global_step": 519431, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0066335201263428, "global_step": 519432, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0105502605438232, "global_step": 519433, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.102586269378662, "global_step": 519434, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0516703128814697, "global_step": 519435, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.172729015350342, "global_step": 519436, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0735559463500977, "global_step": 519437, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0576469898223877, "global_step": 519438, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.09281587600708, "global_step": 519439, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.048564910888672, "global_step": 519440, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.047579288482666, "global_step": 519441, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0261619091033936, "global_step": 519442, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.05601167678833, "global_step": 519443, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.049128293991089, "global_step": 519444, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9869896173477173, "global_step": 519445, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0654807090759277, "global_step": 519446, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0367846488952637, "global_step": 519447, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.047563076019287, "global_step": 519448, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0138041973114014, "global_step": 519449, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.994319200515747, "global_step": 519450, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0695016384124756, "global_step": 519451, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.012237310409546, "global_step": 519452, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.076573371887207, "global_step": 519453, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9527090787887573, "global_step": 519454, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.10732364654541, "global_step": 519455, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0428671836853027, "global_step": 519456, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0572311878204346, "global_step": 519457, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0356884002685547, "global_step": 519458, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0052311420440674, "global_step": 519459, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1272964477539062, "global_step": 519460, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.124706745147705, "global_step": 519461, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.087606430053711, "global_step": 519462, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0264511108398438, "global_step": 519463, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0751852989196777, "global_step": 519464, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.067122459411621, "global_step": 519465, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.095764636993408, "global_step": 519466, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1247079372406006, "global_step": 519467, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1030802726745605, "global_step": 519468, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1105425357818604, "global_step": 519469, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0909154415130615, "global_step": 519470, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9910250902175903, "global_step": 519471, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0605881214141846, "global_step": 519472, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0637245178222656, "global_step": 519473, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0512096881866455, "global_step": 519474, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.050764799118042, "global_step": 519475, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0892221927642822, "global_step": 519476, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0050086975097656, "global_step": 519477, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.1267807483673096, "global_step": 519478, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.103524923324585, "global_step": 519479, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9816316366195679, "global_step": 519480, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0455470085144043, "global_step": 519481, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.099468469619751, "global_step": 519482, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.068373203277588, "global_step": 519483, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0356204509735107, "global_step": 519484, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0730197429656982, "global_step": 519485, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0606770515441895, "global_step": 519486, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0274229049682617, "global_step": 519487, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.000821352005005, "global_step": 519488, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.072882890701294, "global_step": 519489, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9644361734390259, "global_step": 519490, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0945918560028076, "global_step": 519491, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.989634394645691, "global_step": 519492, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.058356523513794, "global_step": 519493, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0792582035064697, "global_step": 519494, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.070586681365967, "global_step": 519495, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.121990919113159, "global_step": 519496, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0347578525543213, "global_step": 519497, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0313363075256348, "global_step": 519498, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.984905481338501, "global_step": 519499, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.015151023864746, "global_step": 519500, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.056511402130127, "global_step": 519501, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.034538507461548, "global_step": 519502, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.040520191192627, "global_step": 519503, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.009688138961792, "global_step": 519504, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0637965202331543, "global_step": 519505, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9950573444366455, "global_step": 519506, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9990366697311401, "global_step": 519507, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0528197288513184, "global_step": 519508, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.141169548034668, "global_step": 519509, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.122222423553467, "global_step": 519510, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.074261426925659, "global_step": 519511, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9513216018676758, "global_step": 519512, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.020486831665039, "global_step": 519513, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.039034366607666, "global_step": 519514, "epoch": 885, "lr": 5e-05}
{"train_loss": 1.9860249757766724, "global_step": 519515, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0412652492523193, "global_step": 519516, "epoch": 885, "lr": 5e-05}
{"train_loss": 2.0200862884521484, "global_step": 519517, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0884804725646973, "global_step": 519518, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.038090229034424, "global_step": 519519, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.050785541534424, "global_step": 519520, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0989322662353516, "global_step": 519521, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.970369815826416, "global_step": 519522, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0162131786346436, "global_step": 519523, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0677757263183594, "global_step": 519524, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0423099994659424, "global_step": 519525, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9973872900009155, "global_step": 519526, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0806119441986084, "global_step": 519527, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0736610889434814, "global_step": 519528, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.945825457572937, "global_step": 519529, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0342671871185303, "global_step": 519530, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.082639694213867, "global_step": 519531, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0322272777557373, "global_step": 519532, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9631199836730957, "global_step": 519533, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.037811756134033, "global_step": 519534, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.995632529258728, "global_step": 519535, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0389909744262695, "global_step": 519536, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0718042850494385, "global_step": 519537, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.038501501083374, "global_step": 519538, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0869715213775635, "global_step": 519539, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.014490842819214, "global_step": 519540, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9738397598266602, "global_step": 519541, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0146048069000244, "global_step": 519542, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.048893690109253, "global_step": 519543, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0446407794952393, "global_step": 519544, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9362144470214844, "global_step": 519545, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.133042097091675, "global_step": 519546, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.089428663253784, "global_step": 519547, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.988527536392212, "global_step": 519548, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0279533863067627, "global_step": 519549, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.014448404312134, "global_step": 519550, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.025008201599121, "global_step": 519551, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0466833114624023, "global_step": 519552, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9953210353851318, "global_step": 519553, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0075032711029053, "global_step": 519554, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9935808181762695, "global_step": 519555, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0645885467529297, "global_step": 519556, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.04518985748291, "global_step": 519557, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9619516134262085, "global_step": 519558, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1116156578063965, "global_step": 519559, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.987127423286438, "global_step": 519560, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.068124294281006, "global_step": 519561, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0078787803649902, "global_step": 519562, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0920255184173584, "global_step": 519563, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9434256553649902, "global_step": 519564, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0409858226776123, "global_step": 519565, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.111783981323242, "global_step": 519566, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0597410202026367, "global_step": 519567, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0361130237579346, "global_step": 519568, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.128817319869995, "global_step": 519569, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0531435012817383, "global_step": 519570, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0020828247070312, "global_step": 519571, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0067803859710693, "global_step": 519572, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.093958854675293, "global_step": 519573, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.00966739654541, "global_step": 519574, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.065911293029785, "global_step": 519575, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.118272066116333, "global_step": 519576, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0392065048217773, "global_step": 519577, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.047189950942993, "global_step": 519578, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9807192087173462, "global_step": 519579, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.077953577041626, "global_step": 519580, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.049574851989746, "global_step": 519581, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9845625162124634, "global_step": 519582, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9953457117080688, "global_step": 519583, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0128707885742188, "global_step": 519584, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0223441123962402, "global_step": 519585, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0467822551727295, "global_step": 519586, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0012896060943604, "global_step": 519587, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0886363983154297, "global_step": 519588, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.989205002784729, "global_step": 519589, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1519265174865723, "global_step": 519590, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.041727066040039, "global_step": 519591, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9739630222320557, "global_step": 519592, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.014223575592041, "global_step": 519593, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9868364334106445, "global_step": 519594, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.03580379486084, "global_step": 519595, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.056805372238159, "global_step": 519596, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0580391883850098, "global_step": 519597, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0130863189697266, "global_step": 519598, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0017123222351074, "global_step": 519599, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0621609687805176, "global_step": 519600, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0362887382507324, "global_step": 519601, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9756815433502197, "global_step": 519602, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0443410873413086, "global_step": 519603, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.016648292541504, "global_step": 519604, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9632680416107178, "global_step": 519605, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.013850450515747, "global_step": 519606, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0546510219573975, "global_step": 519607, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.106952428817749, "global_step": 519608, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.073768377304077, "global_step": 519609, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9573893547058105, "global_step": 519610, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0361249446868896, "global_step": 519611, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1128029823303223, "global_step": 519612, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9282443523406982, "global_step": 519613, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0719335079193115, "global_step": 519614, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0060582160949707, "global_step": 519615, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0936968326568604, "global_step": 519616, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0416758060455322, "global_step": 519617, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9864413738250732, "global_step": 519618, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0225508213043213, "global_step": 519619, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0324254035949707, "global_step": 519620, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0475194454193115, "global_step": 519621, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0344150066375732, "global_step": 519622, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0723891258239746, "global_step": 519623, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.077563762664795, "global_step": 519624, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.071910858154297, "global_step": 519625, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1318421363830566, "global_step": 519626, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.10766863822937, "global_step": 519627, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0041568279266357, "global_step": 519628, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9262399673461914, "global_step": 519629, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0631518363952637, "global_step": 519630, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.023690700531006, "global_step": 519631, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0780506134033203, "global_step": 519632, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.089242696762085, "global_step": 519633, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0995614528656006, "global_step": 519634, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.996294617652893, "global_step": 519635, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0322775840759277, "global_step": 519636, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0955421924591064, "global_step": 519637, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.016853094100952, "global_step": 519638, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.037787437438965, "global_step": 519639, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.02447509765625, "global_step": 519640, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9909621477127075, "global_step": 519641, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0166380405426025, "global_step": 519642, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1123249530792236, "global_step": 519643, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.965959072113037, "global_step": 519644, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.038438320159912, "global_step": 519645, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.102810859680176, "global_step": 519646, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.04543399810791, "global_step": 519647, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9930338859558105, "global_step": 519648, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0208816528320312, "global_step": 519649, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.044010877609253, "global_step": 519650, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1564114093780518, "global_step": 519651, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9624323844909668, "global_step": 519652, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0461792945861816, "global_step": 519653, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.033982038497925, "global_step": 519654, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9903168678283691, "global_step": 519655, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0127921104431152, "global_step": 519656, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9755772352218628, "global_step": 519657, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0792500972747803, "global_step": 519658, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.048922300338745, "global_step": 519659, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.018184185028076, "global_step": 519660, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0696511268615723, "global_step": 519661, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.003394603729248, "global_step": 519662, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.068058967590332, "global_step": 519663, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.028876304626465, "global_step": 519664, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9024633169174194, "global_step": 519665, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0582425594329834, "global_step": 519666, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0141561031341553, "global_step": 519667, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.034916639328003, "global_step": 519668, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.163466215133667, "global_step": 519669, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0305840969085693, "global_step": 519670, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.013418436050415, "global_step": 519671, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0464460849761963, "global_step": 519672, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1086487770080566, "global_step": 519673, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0734193325042725, "global_step": 519674, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1624698638916016, "global_step": 519675, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.12796688079834, "global_step": 519676, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9842185974121094, "global_step": 519677, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.085507869720459, "global_step": 519678, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0701889991760254, "global_step": 519679, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.024768352508545, "global_step": 519680, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.097280740737915, "global_step": 519681, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0089166164398193, "global_step": 519682, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9994637966156006, "global_step": 519683, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0477051734924316, "global_step": 519684, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9965702295303345, "global_step": 519685, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1430578231811523, "global_step": 519686, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9987398386001587, "global_step": 519687, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0222530364990234, "global_step": 519688, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0090136528015137, "global_step": 519689, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0205650329589844, "global_step": 519690, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9960956573486328, "global_step": 519691, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0393567085266113, "global_step": 519692, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9924207925796509, "global_step": 519693, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0466692447662354, "global_step": 519694, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9863871335983276, "global_step": 519695, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0520241260528564, "global_step": 519696, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.022304058074951, "global_step": 519697, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0454201698303223, "global_step": 519698, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0002710819244385, "global_step": 519699, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.037963628768921, "global_step": 519700, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9960452318191528, "global_step": 519701, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.957180142402649, "global_step": 519702, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.071349620819092, "global_step": 519703, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0393354892730713, "global_step": 519704, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9700984954833984, "global_step": 519705, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.049774646759033, "global_step": 519706, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.098769187927246, "global_step": 519707, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9691907167434692, "global_step": 519708, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0562400817871094, "global_step": 519709, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.071537494659424, "global_step": 519710, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0336644649505615, "global_step": 519711, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0113372802734375, "global_step": 519712, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.071547269821167, "global_step": 519713, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.040663242340088, "global_step": 519714, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.064802885055542, "global_step": 519715, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9959675073623657, "global_step": 519716, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0324618816375732, "global_step": 519717, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1199333667755127, "global_step": 519718, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.023829221725464, "global_step": 519719, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9392473697662354, "global_step": 519720, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.112039566040039, "global_step": 519721, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0789663791656494, "global_step": 519722, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.017644166946411, "global_step": 519723, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0493571758270264, "global_step": 519724, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.002594470977783, "global_step": 519725, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9660656452178955, "global_step": 519726, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0302939414978027, "global_step": 519727, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0815789699554443, "global_step": 519728, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0340042114257812, "global_step": 519729, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0555002689361572, "global_step": 519730, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.017078399658203, "global_step": 519731, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.011054754257202, "global_step": 519732, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.031599760055542, "global_step": 519733, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9829165935516357, "global_step": 519734, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0430891513824463, "global_step": 519735, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.061232805252075, "global_step": 519736, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0062241554260254, "global_step": 519737, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.035884380340576, "global_step": 519738, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0488734245300293, "global_step": 519739, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.025639057159424, "global_step": 519740, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0451910495758057, "global_step": 519741, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.045048952102661, "global_step": 519742, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0587122440338135, "global_step": 519743, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9964358806610107, "global_step": 519744, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0589499473571777, "global_step": 519745, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0527596473693848, "global_step": 519746, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0368919372558594, "global_step": 519747, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.056896924972534, "global_step": 519748, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.116750717163086, "global_step": 519749, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0743227005004883, "global_step": 519750, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9325201511383057, "global_step": 519751, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9991233348846436, "global_step": 519752, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9560675621032715, "global_step": 519753, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9973995685577393, "global_step": 519754, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0444326400756836, "global_step": 519755, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.100674629211426, "global_step": 519756, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0707380771636963, "global_step": 519757, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.073723554611206, "global_step": 519758, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0487985610961914, "global_step": 519759, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9399341344833374, "global_step": 519760, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9782613515853882, "global_step": 519761, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.022862434387207, "global_step": 519762, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0021886825561523, "global_step": 519763, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.128690481185913, "global_step": 519764, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.998889684677124, "global_step": 519765, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.099700927734375, "global_step": 519766, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0778937339782715, "global_step": 519767, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9711261987686157, "global_step": 519768, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.040027379989624, "global_step": 519769, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9777823686599731, "global_step": 519770, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0833616256713867, "global_step": 519771, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0046043395996094, "global_step": 519772, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0366737842559814, "global_step": 519773, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0451769828796387, "global_step": 519774, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.979792594909668, "global_step": 519775, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.07441782951355, "global_step": 519776, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.003824234008789, "global_step": 519777, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0238895416259766, "global_step": 519778, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0311594009399414, "global_step": 519779, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.978531837463379, "global_step": 519780, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1125359535217285, "global_step": 519781, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.107163667678833, "global_step": 519782, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.063631534576416, "global_step": 519783, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.037755012512207, "global_step": 519784, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0555648803710938, "global_step": 519785, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9946483373641968, "global_step": 519786, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.05444073677063, "global_step": 519787, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.136197805404663, "global_step": 519788, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0752525329589844, "global_step": 519789, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0943522453308105, "global_step": 519790, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0301547050476074, "global_step": 519791, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0516271591186523, "global_step": 519792, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0029757022857666, "global_step": 519793, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.050733804702759, "global_step": 519794, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0080888271331787, "global_step": 519795, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.068530797958374, "global_step": 519796, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.089775800704956, "global_step": 519797, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0705041885375977, "global_step": 519798, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9924230575561523, "global_step": 519799, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9834785461425781, "global_step": 519800, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0950818061828613, "global_step": 519801, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0144405364990234, "global_step": 519802, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.014176845550537, "global_step": 519803, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1383135318756104, "global_step": 519804, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9500651359558105, "global_step": 519805, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0449390411376953, "global_step": 519806, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.003101348876953, "global_step": 519807, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0556118488311768, "global_step": 519808, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0247437953948975, "global_step": 519809, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0410025119781494, "global_step": 519810, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0153160095214844, "global_step": 519811, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.056436061859131, "global_step": 519812, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0313756465911865, "global_step": 519813, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.052633285522461, "global_step": 519814, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.057199239730835, "global_step": 519815, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0825371742248535, "global_step": 519816, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0437307357788086, "global_step": 519817, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0273373126983643, "global_step": 519818, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.121051549911499, "global_step": 519819, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.038214683532715, "global_step": 519820, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9753116369247437, "global_step": 519821, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.078401803970337, "global_step": 519822, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0584897994995117, "global_step": 519823, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1351001262664795, "global_step": 519824, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.058459997177124, "global_step": 519825, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.064307689666748, "global_step": 519826, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.033709764480591, "global_step": 519827, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0292067527770996, "global_step": 519828, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.098489999771118, "global_step": 519829, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.047515630722046, "global_step": 519830, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0514957904815674, "global_step": 519831, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.060497283935547, "global_step": 519832, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.067408323287964, "global_step": 519833, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.930907130241394, "global_step": 519834, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.986107349395752, "global_step": 519835, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0604286193847656, "global_step": 519836, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1160964965820312, "global_step": 519837, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0794153213500977, "global_step": 519838, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1143603324890137, "global_step": 519839, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1364586353302, "global_step": 519840, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.143096446990967, "global_step": 519841, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.098832368850708, "global_step": 519842, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0407779216766357, "global_step": 519843, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9959715604782104, "global_step": 519844, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0664918422698975, "global_step": 519845, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1133038997650146, "global_step": 519846, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9921818971633911, "global_step": 519847, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.968214988708496, "global_step": 519848, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0312247276306152, "global_step": 519849, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1179518699645996, "global_step": 519850, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0269389152526855, "global_step": 519851, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0744049549102783, "global_step": 519852, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0829269886016846, "global_step": 519853, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0761239528656006, "global_step": 519854, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0256075859069824, "global_step": 519855, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9449821710586548, "global_step": 519856, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.079512596130371, "global_step": 519857, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1313021183013916, "global_step": 519858, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.11228084564209, "global_step": 519859, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.020057201385498, "global_step": 519860, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.08137845993042, "global_step": 519861, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0126423835754395, "global_step": 519862, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0861666202545166, "global_step": 519863, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.07283616065979, "global_step": 519864, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1014554500579834, "global_step": 519865, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.092971086502075, "global_step": 519866, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.947049617767334, "global_step": 519867, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1115562915802, "global_step": 519868, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0563626289367676, "global_step": 519869, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0107078552246094, "global_step": 519870, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.113893985748291, "global_step": 519871, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9788312911987305, "global_step": 519872, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9736275672912598, "global_step": 519873, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0588293075561523, "global_step": 519874, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0311295986175537, "global_step": 519875, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.023077964782715, "global_step": 519876, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0622408390045166, "global_step": 519877, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.992639183998108, "global_step": 519878, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0798983573913574, "global_step": 519879, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9779173135757446, "global_step": 519880, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.113933801651001, "global_step": 519881, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0234384536743164, "global_step": 519882, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.007066011428833, "global_step": 519883, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0529472827911377, "global_step": 519884, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0477335453033447, "global_step": 519885, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9796046018600464, "global_step": 519886, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.982539415359497, "global_step": 519887, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0585715770721436, "global_step": 519888, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0811541080474854, "global_step": 519889, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.048362970352173, "global_step": 519890, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0738768577575684, "global_step": 519891, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9727157354354858, "global_step": 519892, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0216774940490723, "global_step": 519893, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.039060115814209, "global_step": 519894, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.094773054122925, "global_step": 519895, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0938172340393066, "global_step": 519896, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1103994846343994, "global_step": 519897, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9812579154968262, "global_step": 519898, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9468069076538086, "global_step": 519899, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.071432590484619, "global_step": 519900, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9571512937545776, "global_step": 519901, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9962137937545776, "global_step": 519902, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.998292088508606, "global_step": 519903, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0659656524658203, "global_step": 519904, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9958717823028564, "global_step": 519905, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9447208642959595, "global_step": 519906, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0469908714294434, "global_step": 519907, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.113050699234009, "global_step": 519908, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9943294525146484, "global_step": 519909, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0660786628723145, "global_step": 519910, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.134519100189209, "global_step": 519911, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.013188362121582, "global_step": 519912, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9988337755203247, "global_step": 519913, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.085972309112549, "global_step": 519914, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1220169067382812, "global_step": 519915, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.085272789001465, "global_step": 519916, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9892940521240234, "global_step": 519917, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.97611665725708, "global_step": 519918, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0894837379455566, "global_step": 519919, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9872950315475464, "global_step": 519920, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0046722888946533, "global_step": 519921, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0505130290985107, "global_step": 519922, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1115238666534424, "global_step": 519923, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0650947093963623, "global_step": 519924, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0086567401885986, "global_step": 519925, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.085151433944702, "global_step": 519926, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.03570556640625, "global_step": 519927, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.048567295074463, "global_step": 519928, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0281131267547607, "global_step": 519929, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.992651343345642, "global_step": 519930, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9956387281417847, "global_step": 519931, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9484915733337402, "global_step": 519932, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.013808488845825, "global_step": 519933, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1334376335144043, "global_step": 519934, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.049201726913452, "global_step": 519935, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.021151542663574, "global_step": 519936, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0732877254486084, "global_step": 519937, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.00712513923645, "global_step": 519938, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9623079299926758, "global_step": 519939, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9845492839813232, "global_step": 519940, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0546319484710693, "global_step": 519941, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0140771865844727, "global_step": 519942, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9991099834442139, "global_step": 519943, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9736230373382568, "global_step": 519944, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0282299518585205, "global_step": 519945, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.058528184890747, "global_step": 519946, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.991744875907898, "global_step": 519947, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0500783920288086, "global_step": 519948, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.080178737640381, "global_step": 519949, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0026895999908447, "global_step": 519950, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.057292938232422, "global_step": 519951, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0328333377838135, "global_step": 519952, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0740933418273926, "global_step": 519953, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.082329034805298, "global_step": 519954, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.044398069381714, "global_step": 519955, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0385477542877197, "global_step": 519956, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0078227519989014, "global_step": 519957, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.093388557434082, "global_step": 519958, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.075502395629883, "global_step": 519959, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9418129920959473, "global_step": 519960, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.069507360458374, "global_step": 519961, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9814457893371582, "global_step": 519962, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9980098009109497, "global_step": 519963, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.146543025970459, "global_step": 519964, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9626951217651367, "global_step": 519965, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9844197034835815, "global_step": 519966, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1282799243927, "global_step": 519967, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0981576442718506, "global_step": 519968, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.032853126525879, "global_step": 519969, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.021571159362793, "global_step": 519970, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0753746032714844, "global_step": 519971, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.03499698638916, "global_step": 519972, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.046546697616577, "global_step": 519973, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9818800687789917, "global_step": 519974, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.998618483543396, "global_step": 519975, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0960514545440674, "global_step": 519976, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1138346195220947, "global_step": 519977, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0201869010925293, "global_step": 519978, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9743802547454834, "global_step": 519979, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0355775356292725, "global_step": 519980, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.087395191192627, "global_step": 519981, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0123956203460693, "global_step": 519982, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.999871850013733, "global_step": 519983, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.046712636947632, "global_step": 519984, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.112867593765259, "global_step": 519985, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.981405258178711, "global_step": 519986, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9441989660263062, "global_step": 519987, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9980769157409668, "global_step": 519988, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0616743564605713, "global_step": 519989, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0092132091522217, "global_step": 519990, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0591280460357666, "global_step": 519991, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.037564277648926, "global_step": 519992, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9777812957763672, "global_step": 519993, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0535740852355957, "global_step": 519994, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.06304931640625, "global_step": 519995, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.028871774673462, "global_step": 519996, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9987430572509766, "global_step": 519997, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.042388916015625, "global_step": 519998, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0532023906707764, "global_step": 519999, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1003971099853516, "global_step": 520000, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.126826763153076, "global_step": 520001, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9794044494628906, "global_step": 520002, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9662679433822632, "global_step": 520003, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.966426134109497, "global_step": 520004, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.052642822265625, "global_step": 520005, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.004739999771118, "global_step": 520006, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0930252075195312, "global_step": 520007, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1167562007904053, "global_step": 520008, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.052263021469116, "global_step": 520009, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9792159795761108, "global_step": 520010, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.050928831100464, "global_step": 520011, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0095410346984863, "global_step": 520012, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1021218299865723, "global_step": 520013, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.066131114959717, "global_step": 520014, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.003474473953247, "global_step": 520015, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.000796318054199, "global_step": 520016, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.032538414001465, "global_step": 520017, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0599446296691895, "global_step": 520018, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.087327241897583, "global_step": 520019, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0073843002319336, "global_step": 520020, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.910673975944519, "global_step": 520021, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.015475273132324, "global_step": 520022, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0961506366729736, "global_step": 520023, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.138014316558838, "global_step": 520024, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9941117763519287, "global_step": 520025, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9652217626571655, "global_step": 520026, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.012112617492676, "global_step": 520027, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.087733030319214, "global_step": 520028, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.096479654312134, "global_step": 520029, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9977185726165771, "global_step": 520030, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.128464937210083, "global_step": 520031, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0763752460479736, "global_step": 520032, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.113034725189209, "global_step": 520033, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.100773334503174, "global_step": 520034, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0310628414154053, "global_step": 520035, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.111142873764038, "global_step": 520036, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9598780870437622, "global_step": 520037, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0638630390167236, "global_step": 520038, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1098761558532715, "global_step": 520039, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1035003662109375, "global_step": 520040, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0516374111175537, "global_step": 520041, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.093245267868042, "global_step": 520042, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0746312141418457, "global_step": 520043, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0692355632781982, "global_step": 520044, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0538830757141113, "global_step": 520045, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0252420902252197, "global_step": 520046, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0819485187530518, "global_step": 520047, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.041663408279419, "global_step": 520048, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1256911754608154, "global_step": 520049, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.168834924697876, "global_step": 520050, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.029550790786743, "global_step": 520051, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9761451482772827, "global_step": 520052, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9854528903961182, "global_step": 520053, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9962795972824097, "global_step": 520054, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0114753246307373, "global_step": 520055, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0212044715881348, "global_step": 520056, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0593535900115967, "global_step": 520057, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.045994281768799, "global_step": 520058, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.055361747741699, "global_step": 520059, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0636115074157715, "global_step": 520060, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9641664028167725, "global_step": 520061, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9973409175872803, "global_step": 520062, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.022596836090088, "global_step": 520063, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9869182109832764, "global_step": 520064, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1257476806640625, "global_step": 520065, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.041712522506714, "global_step": 520066, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.028122901916504, "global_step": 520067, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0386486053466797, "global_step": 520068, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.073133945465088, "global_step": 520069, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.00384521484375, "global_step": 520070, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.036938190460205, "global_step": 520071, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9961459636688232, "global_step": 520072, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.048088788986206, "global_step": 520073, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.990020513534546, "global_step": 520074, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9108624458312988, "global_step": 520075, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.078653573989868, "global_step": 520076, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.042802095413208, "global_step": 520077, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1169514656066895, "global_step": 520078, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9632176160812378, "global_step": 520079, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.08693790435791, "global_step": 520080, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.046560287475586, "global_step": 520081, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1126508712768555, "global_step": 520082, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9475491046905518, "global_step": 520083, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0134119987487793, "global_step": 520084, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.96311354637146, "global_step": 520085, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.969458818435669, "global_step": 520086, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0796425342559814, "global_step": 520087, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9432107210159302, "global_step": 520088, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.016145706176758, "global_step": 520089, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9378511905670166, "global_step": 520090, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0886428356170654, "global_step": 520091, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.029076337814331, "global_step": 520092, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9885185956954956, "global_step": 520093, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.003480911254883, "global_step": 520094, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0294196605682373, "global_step": 520095, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0118448734283447, "global_step": 520096, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1374130249023438, "global_step": 520097, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0545575618743896, "global_step": 520098, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0093932151794434, "global_step": 520099, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9839868545532227, "global_step": 520100, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0008440017700195, "global_step": 520101, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9944230318069458, "global_step": 520102, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9859269857406616, "global_step": 520103, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9679088592529297, "global_step": 520104, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.092149019241333, "global_step": 520105, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0831356048583984, "global_step": 520106, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.091024875640869, "global_step": 520107, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1259539127349854, "global_step": 520108, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9909226894378662, "global_step": 520109, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.083813428878784, "global_step": 520110, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0476419925689697, "global_step": 520111, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.136906147003174, "global_step": 520112, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.082637071609497, "global_step": 520113, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.045091390609741, "global_step": 520114, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1095387935638428, "global_step": 520115, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.010237216949463, "global_step": 520116, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.075746536254883, "global_step": 520117, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0160741806030273, "global_step": 520118, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.024313449859619, "global_step": 520119, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1110000610351562, "global_step": 520120, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0506093502044678, "global_step": 520121, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0565431118011475, "global_step": 520122, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.028165578842163, "global_step": 520123, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0014052391052246, "global_step": 520124, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.025731086730957, "global_step": 520125, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0740530490875244, "global_step": 520126, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.051295757293701, "global_step": 520127, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9683558940887451, "global_step": 520128, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0875608921051025, "global_step": 520129, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.031982898712158, "global_step": 520130, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9878077507019043, "global_step": 520131, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.025024175643921, "global_step": 520132, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.136667013168335, "global_step": 520133, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0042765140533447, "global_step": 520134, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0604910850524902, "global_step": 520135, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1001224517822266, "global_step": 520136, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9897960424423218, "global_step": 520137, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.020815849304199, "global_step": 520138, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.127234697341919, "global_step": 520139, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0865478515625, "global_step": 520140, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.080564498901367, "global_step": 520141, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0742523670196533, "global_step": 520142, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0901601314544678, "global_step": 520143, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0845911502838135, "global_step": 520144, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0335209369659424, "global_step": 520145, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0468757152557373, "global_step": 520146, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0870323181152344, "global_step": 520147, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0461056232452393, "global_step": 520148, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0378692150115967, "global_step": 520149, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9801746606826782, "global_step": 520150, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9319955110549927, "global_step": 520151, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.013996124267578, "global_step": 520152, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0236594676971436, "global_step": 520153, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.029721736907959, "global_step": 520154, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.019362211227417, "global_step": 520155, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0544161796569824, "global_step": 520156, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1131341457366943, "global_step": 520157, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1151840686798096, "global_step": 520158, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.027768850326538, "global_step": 520159, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.078948736190796, "global_step": 520160, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0452158451080322, "global_step": 520161, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0434141159057617, "global_step": 520162, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.030421495437622, "global_step": 520163, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0305800437927246, "global_step": 520164, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0564911365509033, "global_step": 520165, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.012373685836792, "global_step": 520166, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9805971384048462, "global_step": 520167, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.965508222579956, "global_step": 520168, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.108539342880249, "global_step": 520169, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0573582649230957, "global_step": 520170, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0261552333831787, "global_step": 520171, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0722057819366455, "global_step": 520172, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.056485176086426, "global_step": 520173, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0479159355163574, "global_step": 520174, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.015756845474243, "global_step": 520175, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9594290256500244, "global_step": 520176, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0596587657928467, "global_step": 520177, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0335307121276855, "global_step": 520178, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.012125253677368, "global_step": 520179, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.08329439163208, "global_step": 520180, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0965983867645264, "global_step": 520181, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0316665172576904, "global_step": 520182, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.996225118637085, "global_step": 520183, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0681521892547607, "global_step": 520184, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.110793113708496, "global_step": 520185, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9505853652954102, "global_step": 520186, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0590782165527344, "global_step": 520187, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0361993312835693, "global_step": 520188, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.071307897567749, "global_step": 520189, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.091543197631836, "global_step": 520190, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0273611545562744, "global_step": 520191, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.136660575866699, "global_step": 520192, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.065861940383911, "global_step": 520193, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0275444984436035, "global_step": 520194, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.2100865840911865, "global_step": 520195, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.102097511291504, "global_step": 520196, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9524354934692383, "global_step": 520197, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.151993989944458, "global_step": 520198, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0555331707000732, "global_step": 520199, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9977161884307861, "global_step": 520200, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.053727149963379, "global_step": 520201, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.035672664642334, "global_step": 520202, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.121873617172241, "global_step": 520203, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.024362325668335, "global_step": 520204, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9640088081359863, "global_step": 520205, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.987512469291687, "global_step": 520206, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.078331470489502, "global_step": 520207, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0121700763702393, "global_step": 520208, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9678921699523926, "global_step": 520209, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.015272378921509, "global_step": 520210, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0143136978149414, "global_step": 520211, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.059030294418335, "global_step": 520212, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1208784580230713, "global_step": 520213, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0844058990478516, "global_step": 520214, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.994852066040039, "global_step": 520215, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9858731031417847, "global_step": 520216, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0294101238250732, "global_step": 520217, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.033945083618164, "global_step": 520218, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0443296432495117, "global_step": 520219, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.037839889526367, "global_step": 520220, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0610768795013428, "global_step": 520221, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1098697185516357, "global_step": 520222, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.026716470718384, "global_step": 520223, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9863265752792358, "global_step": 520224, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9684453010559082, "global_step": 520225, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0919787883758545, "global_step": 520226, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.016202688217163, "global_step": 520227, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0275890827178955, "global_step": 520228, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.979282021522522, "global_step": 520229, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.037259578704834, "global_step": 520230, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9915727376937866, "global_step": 520231, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.075827121734619, "global_step": 520232, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.118316173553467, "global_step": 520233, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0878119468688965, "global_step": 520234, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.05465030670166, "global_step": 520235, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0100767612457275, "global_step": 520236, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9809728860855103, "global_step": 520237, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0520401000976562, "global_step": 520238, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9392783641815186, "global_step": 520239, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.014730215072632, "global_step": 520240, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.037828207015991, "global_step": 520241, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.084315776824951, "global_step": 520242, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9550999402999878, "global_step": 520243, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.032517910003662, "global_step": 520244, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9952300786972046, "global_step": 520245, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.162261486053467, "global_step": 520246, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9951543807983398, "global_step": 520247, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.054318428039551, "global_step": 520248, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9636623859405518, "global_step": 520249, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.024643898010254, "global_step": 520250, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.060110569000244, "global_step": 520251, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0537538528442383, "global_step": 520252, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0528907775878906, "global_step": 520253, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0535471439361572, "global_step": 520254, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9961644411087036, "global_step": 520255, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0469765663146973, "global_step": 520256, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.983928918838501, "global_step": 520257, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9809024333953857, "global_step": 520258, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.007988691329956, "global_step": 520259, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.022423267364502, "global_step": 520260, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.8959815502166748, "global_step": 520261, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0271153450012207, "global_step": 520262, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.086998224258423, "global_step": 520263, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.154714345932007, "global_step": 520264, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0382421016693115, "global_step": 520265, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.091398000717163, "global_step": 520266, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.025346517562866, "global_step": 520267, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0744853019714355, "global_step": 520268, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1418511867523193, "global_step": 520269, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0609042644500732, "global_step": 520270, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.026606321334839, "global_step": 520271, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.047804832458496, "global_step": 520272, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0124051570892334, "global_step": 520273, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.015349864959717, "global_step": 520274, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1230130195617676, "global_step": 520275, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0262274742126465, "global_step": 520276, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.073909282684326, "global_step": 520277, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.06583571434021, "global_step": 520278, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0334439277648926, "global_step": 520279, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.082383155822754, "global_step": 520280, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0628063678741455, "global_step": 520281, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.099637269973755, "global_step": 520282, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.033789873123169, "global_step": 520283, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0571858882904053, "global_step": 520284, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9792729616165161, "global_step": 520285, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0605173110961914, "global_step": 520286, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0626773834228516, "global_step": 520287, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0342440605163574, "global_step": 520288, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.028214693069458, "global_step": 520289, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0215296745300293, "global_step": 520290, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0203356742858887, "global_step": 520291, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9781219959259033, "global_step": 520292, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.039062738418579, "global_step": 520293, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9681752920150757, "global_step": 520294, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.051316499710083, "global_step": 520295, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0648465156555176, "global_step": 520296, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.050145149230957, "global_step": 520297, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1149327754974365, "global_step": 520298, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0696263313293457, "global_step": 520299, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9637680053710938, "global_step": 520300, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0315113067626953, "global_step": 520301, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.052589178085327, "global_step": 520302, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.099733829498291, "global_step": 520303, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.083157777786255, "global_step": 520304, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0161852836608887, "global_step": 520305, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.153285264968872, "global_step": 520306, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9710264205932617, "global_step": 520307, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.093632698059082, "global_step": 520308, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.083000659942627, "global_step": 520309, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0430493354797363, "global_step": 520310, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0215089321136475, "global_step": 520311, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0844879150390625, "global_step": 520312, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0039145946502686, "global_step": 520313, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9962332248687744, "global_step": 520314, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.032104730606079, "global_step": 520315, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9927482604980469, "global_step": 520316, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9573369026184082, "global_step": 520317, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.123563528060913, "global_step": 520318, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9972139596939087, "global_step": 520319, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.041800022125244, "global_step": 520320, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1223642826080322, "global_step": 520321, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.134282112121582, "global_step": 520322, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.040555953979492, "global_step": 520323, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.989113450050354, "global_step": 520324, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.133715867996216, "global_step": 520325, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.092233657836914, "global_step": 520326, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0700461864471436, "global_step": 520327, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0388622283935547, "global_step": 520328, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0415425300598145, "global_step": 520329, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.022402048110962, "global_step": 520330, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0700411796569824, "global_step": 520331, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0552754402160645, "global_step": 520332, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.121844530105591, "global_step": 520333, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.078947067260742, "global_step": 520334, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0699260234832764, "global_step": 520335, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.079707622528076, "global_step": 520336, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9942007064819336, "global_step": 520337, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0995848178863525, "global_step": 520338, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.056405544281006, "global_step": 520339, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1024041175842285, "global_step": 520340, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.102534055709839, "global_step": 520341, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.159088611602783, "global_step": 520342, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0713443756103516, "global_step": 520343, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.014774799346924, "global_step": 520344, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9505714178085327, "global_step": 520345, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.025653123855591, "global_step": 520346, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.071049928665161, "global_step": 520347, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0852725505828857, "global_step": 520348, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1394174098968506, "global_step": 520349, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0708167552948, "global_step": 520350, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.032111883163452, "global_step": 520351, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0964255332946777, "global_step": 520352, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.943691372871399, "global_step": 520353, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.054359197616577, "global_step": 520354, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0427210330963135, "global_step": 520355, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.005617141723633, "global_step": 520356, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.998888611793518, "global_step": 520357, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.065411329269409, "global_step": 520358, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0536539554595947, "global_step": 520359, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.084660530090332, "global_step": 520360, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0434107780456543, "global_step": 520361, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0390145778656006, "global_step": 520362, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.055269241333008, "global_step": 520363, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9660706520080566, "global_step": 520364, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.043396472930908, "global_step": 520365, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0153884887695312, "global_step": 520366, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0660605430603027, "global_step": 520367, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0483038425445557, "global_step": 520368, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0204689502716064, "global_step": 520369, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0860953330993652, "global_step": 520370, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.040259838104248, "global_step": 520371, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0738372802734375, "global_step": 520372, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0570616722106934, "global_step": 520373, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0651872158050537, "global_step": 520374, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0542616844177246, "global_step": 520375, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9740501642227173, "global_step": 520376, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.125933885574341, "global_step": 520377, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0534396171569824, "global_step": 520378, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0531857013702393, "global_step": 520379, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.949422836303711, "global_step": 520380, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0233566761016846, "global_step": 520381, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0735340118408203, "global_step": 520382, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0019426345825195, "global_step": 520383, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0249288082122803, "global_step": 520384, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.108030319213867, "global_step": 520385, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0049326419830322, "global_step": 520386, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.022812843322754, "global_step": 520387, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0654850006103516, "global_step": 520388, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1195757389068604, "global_step": 520389, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.013646125793457, "global_step": 520390, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9764604568481445, "global_step": 520391, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0621232986450195, "global_step": 520392, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0601258277893066, "global_step": 520393, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.034274101257324, "global_step": 520394, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0507259368896484, "global_step": 520395, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0691354274749756, "global_step": 520396, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.030146360397339, "global_step": 520397, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9732855558395386, "global_step": 520398, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0308423042297363, "global_step": 520399, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0872738361358643, "global_step": 520400, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0804195404052734, "global_step": 520401, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0357935428619385, "global_step": 520402, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0435526371002197, "global_step": 520403, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9939805269241333, "global_step": 520404, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0258049964904785, "global_step": 520405, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.013277769088745, "global_step": 520406, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0486338138580322, "global_step": 520407, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.063751220703125, "global_step": 520408, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0743515491485596, "global_step": 520409, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0748515129089355, "global_step": 520410, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.031808853149414, "global_step": 520411, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0142667293548584, "global_step": 520412, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.002239465713501, "global_step": 520413, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.090886354446411, "global_step": 520414, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0230236053466797, "global_step": 520415, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1394317150115967, "global_step": 520416, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.132753372192383, "global_step": 520417, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.134432315826416, "global_step": 520418, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0221705436706543, "global_step": 520419, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.150456428527832, "global_step": 520420, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.000636577606201, "global_step": 520421, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0947201251983643, "global_step": 520422, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0126349925994873, "global_step": 520423, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9762933254241943, "global_step": 520424, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.066474676132202, "global_step": 520425, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1236538887023926, "global_step": 520426, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.020371675491333, "global_step": 520427, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0351040363311768, "global_step": 520428, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.991260290145874, "global_step": 520429, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9698951244354248, "global_step": 520430, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0351407527923584, "global_step": 520431, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0202441215515137, "global_step": 520432, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0793979167938232, "global_step": 520433, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.083950996398926, "global_step": 520434, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.043243408203125, "global_step": 520435, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.975663423538208, "global_step": 520436, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0542166233062744, "global_step": 520437, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.127870559692383, "global_step": 520438, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9867290258407593, "global_step": 520439, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0759449005126953, "global_step": 520440, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.05285906791687, "global_step": 520441, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0442521572113037, "global_step": 520442, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.125615358352661, "global_step": 520443, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.012901782989502, "global_step": 520444, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0232014656066895, "global_step": 520445, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9874470233917236, "global_step": 520446, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0922107696533203, "global_step": 520447, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0476839542388916, "global_step": 520448, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0461699962615967, "global_step": 520449, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1222894191741943, "global_step": 520450, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0923306941986084, "global_step": 520451, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.035417318344116, "global_step": 520452, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0474448204040527, "global_step": 520453, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9749704599380493, "global_step": 520454, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1083853244781494, "global_step": 520455, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.055668830871582, "global_step": 520456, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0172548294067383, "global_step": 520457, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1293561458587646, "global_step": 520458, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0744240283966064, "global_step": 520459, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9738470315933228, "global_step": 520460, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1182992458343506, "global_step": 520461, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9982577562332153, "global_step": 520462, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.135709285736084, "global_step": 520463, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9904853105545044, "global_step": 520464, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.042952060699463, "global_step": 520465, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1007492542266846, "global_step": 520466, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.126077175140381, "global_step": 520467, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.1782734394073486, "global_step": 520468, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0268027782440186, "global_step": 520469, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0802457332611084, "global_step": 520470, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9962457418441772, "global_step": 520471, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.083418607711792, "global_step": 520472, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0886611938476562, "global_step": 520473, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0574305057525635, "global_step": 520474, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.957229495048523, "global_step": 520475, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0977673530578613, "global_step": 520476, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.089688301086426, "global_step": 520477, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.086768865585327, "global_step": 520478, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9484490156173706, "global_step": 520479, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.047852039337158, "global_step": 520480, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0560803413391113, "global_step": 520481, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0578417778015137, "global_step": 520482, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.0336790084838867, "global_step": 520483, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.056744337081909, "global_step": 520484, "epoch": 886, "lr": 5e-05}
{"train_loss": 2.042135238647461, "global_step": 520485, "epoch": 886, "lr": 5e-05}
{"train_loss": 1.9171230792999268, "global_step": 520486, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.000783681869507, "global_step": 520487, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.997139811515808, "global_step": 520488, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.029722213745117, "global_step": 520489, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0458271503448486, "global_step": 520490, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.999386191368103, "global_step": 520491, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.002108097076416, "global_step": 520492, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.105360269546509, "global_step": 520493, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.106595516204834, "global_step": 520494, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.073561429977417, "global_step": 520495, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9538395404815674, "global_step": 520496, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.030479669570923, "global_step": 520497, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.059387683868408, "global_step": 520498, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0848004817962646, "global_step": 520499, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0290074348449707, "global_step": 520500, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9799401760101318, "global_step": 520501, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.065077304840088, "global_step": 520502, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.019108772277832, "global_step": 520503, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0621697902679443, "global_step": 520504, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9637863636016846, "global_step": 520505, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0903613567352295, "global_step": 520506, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.025658369064331, "global_step": 520507, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.038684844970703, "global_step": 520508, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0270450115203857, "global_step": 520509, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0561954975128174, "global_step": 520510, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9939446449279785, "global_step": 520511, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9889448881149292, "global_step": 520512, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9761064052581787, "global_step": 520513, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.080594539642334, "global_step": 520514, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0441269874572754, "global_step": 520515, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.996904969215393, "global_step": 520516, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9530185461044312, "global_step": 520517, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9717214107513428, "global_step": 520518, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.041858673095703, "global_step": 520519, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0272607803344727, "global_step": 520520, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.050194263458252, "global_step": 520521, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9105819463729858, "global_step": 520522, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.05245041847229, "global_step": 520523, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0392696857452393, "global_step": 520524, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.974819302558899, "global_step": 520525, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0496697425842285, "global_step": 520526, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0633723735809326, "global_step": 520527, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.083967447280884, "global_step": 520528, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0401816368103027, "global_step": 520529, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.97004234790802, "global_step": 520530, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.040398120880127, "global_step": 520531, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1031887531280518, "global_step": 520532, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.001432180404663, "global_step": 520533, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.014578342437744, "global_step": 520534, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.015054225921631, "global_step": 520535, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0447475910186768, "global_step": 520536, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0017828941345215, "global_step": 520537, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0667920112609863, "global_step": 520538, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.006937026977539, "global_step": 520539, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.005319118499756, "global_step": 520540, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9299713373184204, "global_step": 520541, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.017829418182373, "global_step": 520542, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9829039573669434, "global_step": 520543, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0605366230010986, "global_step": 520544, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0131750106811523, "global_step": 520545, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.088564872741699, "global_step": 520546, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9763736724853516, "global_step": 520547, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0567543506622314, "global_step": 520548, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0370185375213623, "global_step": 520549, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9787765741348267, "global_step": 520550, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9936811923980713, "global_step": 520551, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0321738719940186, "global_step": 520552, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9960687160491943, "global_step": 520553, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.024726152420044, "global_step": 520554, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0139412879943848, "global_step": 520555, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0025267601013184, "global_step": 520556, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0798182487487793, "global_step": 520557, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9524697065353394, "global_step": 520558, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0618200302124023, "global_step": 520559, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9938987493515015, "global_step": 520560, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0226926803588867, "global_step": 520561, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0623366832733154, "global_step": 520562, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9897629022598267, "global_step": 520563, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0447824001312256, "global_step": 520564, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.028878688812256, "global_step": 520565, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0393059253692627, "global_step": 520566, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0368173122406006, "global_step": 520567, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.023824691772461, "global_step": 520568, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0292623043060303, "global_step": 520569, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0052618980407715, "global_step": 520570, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0992772579193115, "global_step": 520571, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0489542484283447, "global_step": 520572, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9742701053619385, "global_step": 520573, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0257625579833984, "global_step": 520574, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.100064277648926, "global_step": 520575, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0305566787719727, "global_step": 520576, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.110008716583252, "global_step": 520577, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9998652935028076, "global_step": 520578, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9844355583190918, "global_step": 520579, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0267574787139893, "global_step": 520580, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9793944358825684, "global_step": 520581, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.96794855594635, "global_step": 520582, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.143325090408325, "global_step": 520583, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0149734020233154, "global_step": 520584, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.075937271118164, "global_step": 520585, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0454835891723633, "global_step": 520586, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.000690221786499, "global_step": 520587, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9759222269058228, "global_step": 520588, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.043590545654297, "global_step": 520589, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9649772644042969, "global_step": 520590, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0036532878875732, "global_step": 520591, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.091315746307373, "global_step": 520592, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.012416362762451, "global_step": 520593, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.964989185333252, "global_step": 520594, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0707027912139893, "global_step": 520595, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0409934520721436, "global_step": 520596, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9790253639221191, "global_step": 520597, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.065082550048828, "global_step": 520598, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0284156799316406, "global_step": 520599, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0123276710510254, "global_step": 520600, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.045564651489258, "global_step": 520601, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.010927200317383, "global_step": 520602, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0799601078033447, "global_step": 520603, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.049704074859619, "global_step": 520604, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.010645866394043, "global_step": 520605, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.016010046005249, "global_step": 520606, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9817776679992676, "global_step": 520607, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0070362091064453, "global_step": 520608, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9936045408248901, "global_step": 520609, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0450618267059326, "global_step": 520610, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9684401750564575, "global_step": 520611, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0810399055480957, "global_step": 520612, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0267374515533447, "global_step": 520613, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0968785285949707, "global_step": 520614, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0389182567596436, "global_step": 520615, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.983237624168396, "global_step": 520616, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.004926919937134, "global_step": 520617, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.046055316925049, "global_step": 520618, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0127439498901367, "global_step": 520619, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0462470054626465, "global_step": 520620, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9490231275558472, "global_step": 520621, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.091231346130371, "global_step": 520622, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.09652042388916, "global_step": 520623, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.072683095932007, "global_step": 520624, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.013481855392456, "global_step": 520625, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.034594774246216, "global_step": 520626, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9900010824203491, "global_step": 520627, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.102856159210205, "global_step": 520628, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.911681056022644, "global_step": 520629, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.04290509223938, "global_step": 520630, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.064535617828369, "global_step": 520631, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1590781211853027, "global_step": 520632, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.047283887863159, "global_step": 520633, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0572259426116943, "global_step": 520634, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9836678504943848, "global_step": 520635, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.051968574523926, "global_step": 520636, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1183416843414307, "global_step": 520637, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.049516439437866, "global_step": 520638, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.037978410720825, "global_step": 520639, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.104114532470703, "global_step": 520640, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9977449178695679, "global_step": 520641, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9690850973129272, "global_step": 520642, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0153908729553223, "global_step": 520643, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.978378176689148, "global_step": 520644, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.05557918548584, "global_step": 520645, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9758551120758057, "global_step": 520646, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.030963659286499, "global_step": 520647, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.039315938949585, "global_step": 520648, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0765202045440674, "global_step": 520649, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0066416263580322, "global_step": 520650, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0125696659088135, "global_step": 520651, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0742785930633545, "global_step": 520652, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.958795428276062, "global_step": 520653, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.073479175567627, "global_step": 520654, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.007798433303833, "global_step": 520655, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.057494640350342, "global_step": 520656, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0064985752105713, "global_step": 520657, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.012160539627075, "global_step": 520658, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1308419704437256, "global_step": 520659, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0577621459960938, "global_step": 520660, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1039135456085205, "global_step": 520661, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0342047214508057, "global_step": 520662, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9465034008026123, "global_step": 520663, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0688209533691406, "global_step": 520664, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.991246223449707, "global_step": 520665, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.029463529586792, "global_step": 520666, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0065605640411377, "global_step": 520667, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0407707691192627, "global_step": 520668, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0699050426483154, "global_step": 520669, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1053924560546875, "global_step": 520670, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0561654567718506, "global_step": 520671, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.019437313079834, "global_step": 520672, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.025765895843506, "global_step": 520673, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0621116161346436, "global_step": 520674, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9103081226348877, "global_step": 520675, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0382349491119385, "global_step": 520676, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.045977830886841, "global_step": 520677, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0912506580352783, "global_step": 520678, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9508215188980103, "global_step": 520679, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9472296237945557, "global_step": 520680, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.032787799835205, "global_step": 520681, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0604066848754883, "global_step": 520682, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9943031072616577, "global_step": 520683, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.988114595413208, "global_step": 520684, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0734059810638428, "global_step": 520685, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.055455446243286, "global_step": 520686, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0788233280181885, "global_step": 520687, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0199058055877686, "global_step": 520688, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0657055377960205, "global_step": 520689, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.108255386352539, "global_step": 520690, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.01120662689209, "global_step": 520691, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0174503326416016, "global_step": 520692, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0554773807525635, "global_step": 520693, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9947800636291504, "global_step": 520694, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0494747161865234, "global_step": 520695, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9693939685821533, "global_step": 520696, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9902654886245728, "global_step": 520697, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0615592002868652, "global_step": 520698, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.023104190826416, "global_step": 520699, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9906916618347168, "global_step": 520700, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.007377862930298, "global_step": 520701, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1091434955596924, "global_step": 520702, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.072557210922241, "global_step": 520703, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0064682960510254, "global_step": 520704, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9900692701339722, "global_step": 520705, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0047237873077393, "global_step": 520706, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0965113639831543, "global_step": 520707, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0723965167999268, "global_step": 520708, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.071002960205078, "global_step": 520709, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1160905361175537, "global_step": 520710, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.956696629524231, "global_step": 520711, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9764033555984497, "global_step": 520712, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9525083303451538, "global_step": 520713, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9524718523025513, "global_step": 520714, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0855352878570557, "global_step": 520715, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0644330978393555, "global_step": 520716, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0661871433258057, "global_step": 520717, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0249180793762207, "global_step": 520718, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.078248977661133, "global_step": 520719, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1270506381988525, "global_step": 520720, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0913453102111816, "global_step": 520721, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.033906936645508, "global_step": 520722, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0464940071105957, "global_step": 520723, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.102910280227661, "global_step": 520724, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.107515573501587, "global_step": 520725, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.055940866470337, "global_step": 520726, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9192074537277222, "global_step": 520727, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9895051717758179, "global_step": 520728, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.980320692062378, "global_step": 520729, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1091387271881104, "global_step": 520730, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.043198823928833, "global_step": 520731, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0247976779937744, "global_step": 520732, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0327813625335693, "global_step": 520733, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0166175365448, "global_step": 520734, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.940745234489441, "global_step": 520735, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9702439308166504, "global_step": 520736, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.004707098007202, "global_step": 520737, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.089128255844116, "global_step": 520738, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0399880409240723, "global_step": 520739, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1012163162231445, "global_step": 520740, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1201112270355225, "global_step": 520741, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9717004299163818, "global_step": 520742, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0305144786834717, "global_step": 520743, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0882937908172607, "global_step": 520744, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1291823387145996, "global_step": 520745, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.008986711502075, "global_step": 520746, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0200812816619873, "global_step": 520747, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0797054767608643, "global_step": 520748, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1138856410980225, "global_step": 520749, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.116824150085449, "global_step": 520750, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.010059356689453, "global_step": 520751, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.032184600830078, "global_step": 520752, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.949265956878662, "global_step": 520753, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0643270015716553, "global_step": 520754, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.095336675643921, "global_step": 520755, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.115478754043579, "global_step": 520756, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.064579725265503, "global_step": 520757, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0700879096984863, "global_step": 520758, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0193521976470947, "global_step": 520759, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0938074588775635, "global_step": 520760, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0473709106445312, "global_step": 520761, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0627119541168213, "global_step": 520762, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.033425807952881, "global_step": 520763, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.120131254196167, "global_step": 520764, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0126547813415527, "global_step": 520765, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0200932025909424, "global_step": 520766, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9545212984085083, "global_step": 520767, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.065319776535034, "global_step": 520768, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.014556407928467, "global_step": 520769, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0717310905456543, "global_step": 520770, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0279781818389893, "global_step": 520771, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.05721378326416, "global_step": 520772, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.092844009399414, "global_step": 520773, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0288052558898926, "global_step": 520774, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0015132427215576, "global_step": 520775, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0620014667510986, "global_step": 520776, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0660147666931152, "global_step": 520777, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0242836475372314, "global_step": 520778, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0825724601745605, "global_step": 520779, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9517816305160522, "global_step": 520780, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9560041427612305, "global_step": 520781, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.031891107559204, "global_step": 520782, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.094057083129883, "global_step": 520783, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0744800567626953, "global_step": 520784, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0221505165100098, "global_step": 520785, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0604186058044434, "global_step": 520786, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.984368085861206, "global_step": 520787, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0683295726776123, "global_step": 520788, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1468136310577393, "global_step": 520789, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9588661193847656, "global_step": 520790, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0916855335235596, "global_step": 520791, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9888603687286377, "global_step": 520792, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.019575834274292, "global_step": 520793, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.021721839904785, "global_step": 520794, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9502415657043457, "global_step": 520795, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0297698974609375, "global_step": 520796, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.981885313987732, "global_step": 520797, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9969996213912964, "global_step": 520798, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0578882694244385, "global_step": 520799, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0262067317962646, "global_step": 520800, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9999914169311523, "global_step": 520801, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9981518983840942, "global_step": 520802, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.09647274017334, "global_step": 520803, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0187997817993164, "global_step": 520804, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1375374794006348, "global_step": 520805, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0411951541900635, "global_step": 520806, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.106337547302246, "global_step": 520807, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0782628059387207, "global_step": 520808, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.983469843864441, "global_step": 520809, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.045971632003784, "global_step": 520810, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.062680959701538, "global_step": 520811, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.059229850769043, "global_step": 520812, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0578532218933105, "global_step": 520813, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0163936614990234, "global_step": 520814, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.987323522567749, "global_step": 520815, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.019749402999878, "global_step": 520816, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9829161167144775, "global_step": 520817, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0543065071105957, "global_step": 520818, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9510802030563354, "global_step": 520819, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.073338031768799, "global_step": 520820, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.077951431274414, "global_step": 520821, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1126840114593506, "global_step": 520822, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1100239753723145, "global_step": 520823, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.02630352973938, "global_step": 520824, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.090024709701538, "global_step": 520825, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.089614152908325, "global_step": 520826, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0268990993499756, "global_step": 520827, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.038759708404541, "global_step": 520828, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.069943428039551, "global_step": 520829, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.020040273666382, "global_step": 520830, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0175440311431885, "global_step": 520831, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.002272129058838, "global_step": 520832, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0577330589294434, "global_step": 520833, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.983983039855957, "global_step": 520834, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.03887939453125, "global_step": 520835, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.027444362640381, "global_step": 520836, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0860466957092285, "global_step": 520837, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9983011484146118, "global_step": 520838, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.053786039352417, "global_step": 520839, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.068058490753174, "global_step": 520840, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9909411668777466, "global_step": 520841, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.045264959335327, "global_step": 520842, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0141029357910156, "global_step": 520843, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.063314437866211, "global_step": 520844, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0030405521392822, "global_step": 520845, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0270276069641113, "global_step": 520846, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0390679836273193, "global_step": 520847, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.007329225540161, "global_step": 520848, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0825552940368652, "global_step": 520849, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.043243885040283, "global_step": 520850, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.043138265609741, "global_step": 520851, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0587477684020996, "global_step": 520852, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0291168689727783, "global_step": 520853, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0169389247894287, "global_step": 520854, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0287394523620605, "global_step": 520855, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0641722679138184, "global_step": 520856, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.06762957572937, "global_step": 520857, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0925254821777344, "global_step": 520858, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1057162284851074, "global_step": 520859, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0544092655181885, "global_step": 520860, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0911216735839844, "global_step": 520861, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0618674755096436, "global_step": 520862, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.126530885696411, "global_step": 520863, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0378127098083496, "global_step": 520864, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0655033588409424, "global_step": 520865, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0100724697113037, "global_step": 520866, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.044283151626587, "global_step": 520867, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.974832534790039, "global_step": 520868, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1314516067504883, "global_step": 520869, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.09682297706604, "global_step": 520870, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.063608169555664, "global_step": 520871, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.082918167114258, "global_step": 520872, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0804238319396973, "global_step": 520873, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0849342346191406, "global_step": 520874, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0441267490386963, "global_step": 520875, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0756988525390625, "global_step": 520876, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9532450437545776, "global_step": 520877, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0094408988952637, "global_step": 520878, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0662715435028076, "global_step": 520879, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1327569484710693, "global_step": 520880, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0380501747131348, "global_step": 520881, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.04289174079895, "global_step": 520882, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0257575511932373, "global_step": 520883, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.108344793319702, "global_step": 520884, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.034148931503296, "global_step": 520885, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0317866802215576, "global_step": 520886, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0588889122009277, "global_step": 520887, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0272092819213867, "global_step": 520888, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9667391777038574, "global_step": 520889, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.018174886703491, "global_step": 520890, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.023205041885376, "global_step": 520891, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.145120620727539, "global_step": 520892, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.081634044647217, "global_step": 520893, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0294363498687744, "global_step": 520894, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1605241298675537, "global_step": 520895, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0201847553253174, "global_step": 520896, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.067598581314087, "global_step": 520897, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.075131893157959, "global_step": 520898, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0171706676483154, "global_step": 520899, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0335135459899902, "global_step": 520900, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9629602432250977, "global_step": 520901, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0419678688049316, "global_step": 520902, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.8957985639572144, "global_step": 520903, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0215723514556885, "global_step": 520904, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0066683292388916, "global_step": 520905, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.076089859008789, "global_step": 520906, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.018916130065918, "global_step": 520907, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0632567405700684, "global_step": 520908, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9569236040115356, "global_step": 520909, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1107075214385986, "global_step": 520910, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0704808235168457, "global_step": 520911, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0901687145233154, "global_step": 520912, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.054018020629883, "global_step": 520913, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0453710556030273, "global_step": 520914, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9960360527038574, "global_step": 520915, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9853112697601318, "global_step": 520916, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0368752479553223, "global_step": 520917, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.958420991897583, "global_step": 520918, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.003746271133423, "global_step": 520919, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0421066284179688, "global_step": 520920, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.059124708175659, "global_step": 520921, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0998337268829346, "global_step": 520922, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0346059799194336, "global_step": 520923, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9672188758850098, "global_step": 520924, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.086240291595459, "global_step": 520925, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1008388996124268, "global_step": 520926, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1049838066101074, "global_step": 520927, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0930283069610596, "global_step": 520928, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0540900230407715, "global_step": 520929, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.038515329360962, "global_step": 520930, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.045626401901245, "global_step": 520931, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0291104316711426, "global_step": 520932, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0627787113189697, "global_step": 520933, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0813493728637695, "global_step": 520934, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0379607677459717, "global_step": 520935, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9905469417572021, "global_step": 520936, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.101477861404419, "global_step": 520937, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0390329360961914, "global_step": 520938, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.065354824066162, "global_step": 520939, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0434253215789795, "global_step": 520940, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0805811882019043, "global_step": 520941, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9910467863082886, "global_step": 520942, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.028225898742676, "global_step": 520943, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0222082138061523, "global_step": 520944, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9909616708755493, "global_step": 520945, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0344486236572266, "global_step": 520946, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0131237506866455, "global_step": 520947, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.055370807647705, "global_step": 520948, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0634965896606445, "global_step": 520949, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.074772834777832, "global_step": 520950, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9888806343078613, "global_step": 520951, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0353174209594727, "global_step": 520952, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0812058448791504, "global_step": 520953, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0420265197753906, "global_step": 520954, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1548166275024414, "global_step": 520955, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0691230297088623, "global_step": 520956, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0638644695281982, "global_step": 520957, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.070115089416504, "global_step": 520958, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0064902305603027, "global_step": 520959, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0206539630889893, "global_step": 520960, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0488855838775635, "global_step": 520961, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0377941131591797, "global_step": 520962, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.946689248085022, "global_step": 520963, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9892657995224, "global_step": 520964, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.090461254119873, "global_step": 520965, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0764167308807373, "global_step": 520966, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0557165145874023, "global_step": 520967, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0111186504364014, "global_step": 520968, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0942065715789795, "global_step": 520969, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0134692192077637, "global_step": 520970, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0358052253723145, "global_step": 520971, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.125711441040039, "global_step": 520972, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.053114652633667, "global_step": 520973, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0681214332580566, "global_step": 520974, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0341403484344482, "global_step": 520975, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.035837411880493, "global_step": 520976, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.007927417755127, "global_step": 520977, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.04624342918396, "global_step": 520978, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1624410152435303, "global_step": 520979, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.124565362930298, "global_step": 520980, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0031049251556396, "global_step": 520981, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.067857265472412, "global_step": 520982, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0699994564056396, "global_step": 520983, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0117132663726807, "global_step": 520984, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0118062496185303, "global_step": 520985, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9653064012527466, "global_step": 520986, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0405094623565674, "global_step": 520987, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0792696475982666, "global_step": 520988, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1074399948120117, "global_step": 520989, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.005225419998169, "global_step": 520990, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.997378945350647, "global_step": 520991, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0817737579345703, "global_step": 520992, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9999536275863647, "global_step": 520993, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0067391395568848, "global_step": 520994, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.040601968765259, "global_step": 520995, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.025916814804077, "global_step": 520996, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0243489742279053, "global_step": 520997, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.085925579071045, "global_step": 520998, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.08988094329834, "global_step": 520999, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0952982902526855, "global_step": 521000, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9598336219787598, "global_step": 521001, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9393974542617798, "global_step": 521002, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0123298168182373, "global_step": 521003, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.004883050918579, "global_step": 521004, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0699024200439453, "global_step": 521005, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9522114992141724, "global_step": 521006, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.978109359741211, "global_step": 521007, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1216845512390137, "global_step": 521008, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.135977029800415, "global_step": 521009, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0220494270324707, "global_step": 521010, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1509242057800293, "global_step": 521011, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.104584217071533, "global_step": 521012, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9329513311386108, "global_step": 521013, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0225765705108643, "global_step": 521014, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.014198064804077, "global_step": 521015, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0731067657470703, "global_step": 521016, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.008470296859741, "global_step": 521017, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9171556234359741, "global_step": 521018, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.966977834701538, "global_step": 521019, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0634055137634277, "global_step": 521020, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0187594890594482, "global_step": 521021, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.070770263671875, "global_step": 521022, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.138305425643921, "global_step": 521023, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0194575786590576, "global_step": 521024, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.022228240966797, "global_step": 521025, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.041114568710327, "global_step": 521026, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0788254737854004, "global_step": 521027, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9893848896026611, "global_step": 521028, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.102602481842041, "global_step": 521029, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0421302318573, "global_step": 521030, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0031068325042725, "global_step": 521031, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0519540309906006, "global_step": 521032, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0493061542510986, "global_step": 521033, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.999912977218628, "global_step": 521034, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.018183469772339, "global_step": 521035, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0043654441833496, "global_step": 521036, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0661258697509766, "global_step": 521037, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.008371114730835, "global_step": 521038, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0761525630950928, "global_step": 521039, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0622286796569824, "global_step": 521040, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9980149269104004, "global_step": 521041, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0882763862609863, "global_step": 521042, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9791467189788818, "global_step": 521043, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.075556516647339, "global_step": 521044, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.050570249557495, "global_step": 521045, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0975842475891113, "global_step": 521046, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.077639102935791, "global_step": 521047, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9885737895965576, "global_step": 521048, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0364861488342285, "global_step": 521049, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.017799139022827, "global_step": 521050, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0044901371002197, "global_step": 521051, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9959948062896729, "global_step": 521052, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0154623985290527, "global_step": 521053, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9946203231811523, "global_step": 521054, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0447988510131836, "global_step": 521055, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9797587394714355, "global_step": 521056, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0486457347869873, "global_step": 521057, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.089130401611328, "global_step": 521058, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0308268070220947, "global_step": 521059, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.08610463142395, "global_step": 521060, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.146515130996704, "global_step": 521061, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.110515832901001, "global_step": 521062, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0465946197509766, "global_step": 521063, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0648488998413086, "global_step": 521064, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1006619930267334, "global_step": 521065, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.086747407913208, "global_step": 521066, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0289695262908936, "global_step": 521067, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0091474056243896, "global_step": 521068, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.11136531829834, "global_step": 521069, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.082412004470825, "global_step": 521070, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.014061689376831, "global_step": 521071, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0634353160858154, "global_step": 521072, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0279324054718018, "global_step": 521073, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.060999870300293, "global_step": 521074, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0333831310272217, "global_step": 521075, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.073761463165283, "global_step": 521076, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9487351179122925, "global_step": 521077, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9970927238464355, "global_step": 521078, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9838910102844238, "global_step": 521079, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.029036045074463, "global_step": 521080, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0363752841949463, "global_step": 521081, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1331193447113037, "global_step": 521082, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0096170902252197, "global_step": 521083, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9824615716934204, "global_step": 521084, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0320816040039062, "global_step": 521085, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.017061710357666, "global_step": 521086, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0011367797851562, "global_step": 521087, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0194485187530518, "global_step": 521088, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.055931329727173, "global_step": 521089, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9987843036651611, "global_step": 521090, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0633695125579834, "global_step": 521091, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.104170560836792, "global_step": 521092, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0794456005096436, "global_step": 521093, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0129446983337402, "global_step": 521094, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.055420398712158, "global_step": 521095, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.011918067932129, "global_step": 521096, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.992164134979248, "global_step": 521097, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1043100357055664, "global_step": 521098, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.104393243789673, "global_step": 521099, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9880162477493286, "global_step": 521100, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.035290479660034, "global_step": 521101, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.053208351135254, "global_step": 521102, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.097566604614258, "global_step": 521103, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0507583618164062, "global_step": 521104, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.023137331008911, "global_step": 521105, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0781972408294678, "global_step": 521106, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.031414270401001, "global_step": 521107, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0272557735443115, "global_step": 521108, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9712268114089966, "global_step": 521109, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9768016338348389, "global_step": 521110, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.039541006088257, "global_step": 521111, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.033278703689575, "global_step": 521112, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1040422916412354, "global_step": 521113, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0720632076263428, "global_step": 521114, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9334203004837036, "global_step": 521115, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0594890117645264, "global_step": 521116, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0821666717529297, "global_step": 521117, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.079245090484619, "global_step": 521118, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0639395713806152, "global_step": 521119, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0102109909057617, "global_step": 521120, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.08388352394104, "global_step": 521121, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9871560335159302, "global_step": 521122, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.012641668319702, "global_step": 521123, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.025559663772583, "global_step": 521124, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9897499084472656, "global_step": 521125, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0005791187286377, "global_step": 521126, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0128798484802246, "global_step": 521127, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0258612632751465, "global_step": 521128, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.088996410369873, "global_step": 521129, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.102888584136963, "global_step": 521130, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.961923360824585, "global_step": 521131, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.084841728210449, "global_step": 521132, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0722100734710693, "global_step": 521133, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.074812889099121, "global_step": 521134, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0845870971679688, "global_step": 521135, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1700453758239746, "global_step": 521136, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.021805763244629, "global_step": 521137, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.017571210861206, "global_step": 521138, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.04380202293396, "global_step": 521139, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9927685260772705, "global_step": 521140, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0636045932769775, "global_step": 521141, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0969791412353516, "global_step": 521142, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.126593589782715, "global_step": 521143, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0422720909118652, "global_step": 521144, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.099151134490967, "global_step": 521145, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0177958011627197, "global_step": 521146, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.994098424911499, "global_step": 521147, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0072691440582275, "global_step": 521148, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.125697374343872, "global_step": 521149, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1214070320129395, "global_step": 521150, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.075430393218994, "global_step": 521151, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.086613655090332, "global_step": 521152, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9778470993041992, "global_step": 521153, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0236799716949463, "global_step": 521154, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9892545938491821, "global_step": 521155, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9728201627731323, "global_step": 521156, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1071314811706543, "global_step": 521157, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1040749549865723, "global_step": 521158, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9836530685424805, "global_step": 521159, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.940921664237976, "global_step": 521160, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0584869384765625, "global_step": 521161, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.161909341812134, "global_step": 521162, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0040924549102783, "global_step": 521163, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1055989265441895, "global_step": 521164, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0874500274658203, "global_step": 521165, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.047846555709839, "global_step": 521166, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.112131357192993, "global_step": 521167, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0320048332214355, "global_step": 521168, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1082334518432617, "global_step": 521169, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0961201190948486, "global_step": 521170, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9876620769500732, "global_step": 521171, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0755255222320557, "global_step": 521172, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.095411777496338, "global_step": 521173, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1018471717834473, "global_step": 521174, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.085977077484131, "global_step": 521175, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0799102783203125, "global_step": 521176, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0572009086608887, "global_step": 521177, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1045236587524414, "global_step": 521178, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0345077514648438, "global_step": 521179, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.015657901763916, "global_step": 521180, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9841759204864502, "global_step": 521181, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.046550989151001, "global_step": 521182, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9896793365478516, "global_step": 521183, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0937483310699463, "global_step": 521184, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0780699253082275, "global_step": 521185, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1115739345550537, "global_step": 521186, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.017637252807617, "global_step": 521187, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9926396608352661, "global_step": 521188, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0213747024536133, "global_step": 521189, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9742809534072876, "global_step": 521190, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1223642826080322, "global_step": 521191, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.084684133529663, "global_step": 521192, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.068605661392212, "global_step": 521193, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0424201488494873, "global_step": 521194, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.047699213027954, "global_step": 521195, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0410757064819336, "global_step": 521196, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.030280113220215, "global_step": 521197, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1417548656463623, "global_step": 521198, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.030125141143799, "global_step": 521199, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.016479253768921, "global_step": 521200, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9503743648529053, "global_step": 521201, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9434428215026855, "global_step": 521202, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0132083892822266, "global_step": 521203, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.024111032485962, "global_step": 521204, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1130356788635254, "global_step": 521205, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.072944164276123, "global_step": 521206, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.024064779281616, "global_step": 521207, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0188000202178955, "global_step": 521208, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0115814208984375, "global_step": 521209, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.038923501968384, "global_step": 521210, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0005407333374023, "global_step": 521211, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0500011444091797, "global_step": 521212, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.002537965774536, "global_step": 521213, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0735554695129395, "global_step": 521214, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.013308048248291, "global_step": 521215, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0419888496398926, "global_step": 521216, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0974934101104736, "global_step": 521217, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1182961463928223, "global_step": 521218, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.988443374633789, "global_step": 521219, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0212836265563965, "global_step": 521220, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.077981472015381, "global_step": 521221, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.004058361053467, "global_step": 521222, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0063602924346924, "global_step": 521223, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.052962064743042, "global_step": 521224, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0086514949798584, "global_step": 521225, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.069305181503296, "global_step": 521226, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.076934814453125, "global_step": 521227, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0379886627197266, "global_step": 521228, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.020869731903076, "global_step": 521229, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0716726779937744, "global_step": 521230, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0710811614990234, "global_step": 521231, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1291959285736084, "global_step": 521232, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.010787010192871, "global_step": 521233, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.929682731628418, "global_step": 521234, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0146560668945312, "global_step": 521235, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.049809694290161, "global_step": 521236, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0656304359436035, "global_step": 521237, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0658881664276123, "global_step": 521238, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9490134716033936, "global_step": 521239, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.044452428817749, "global_step": 521240, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0659947395324707, "global_step": 521241, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.081670045852661, "global_step": 521242, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0507702827453613, "global_step": 521243, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0682647228240967, "global_step": 521244, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0650973320007324, "global_step": 521245, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1721434593200684, "global_step": 521246, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0819530487060547, "global_step": 521247, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.085202693939209, "global_step": 521248, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0269956588745117, "global_step": 521249, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0944457054138184, "global_step": 521250, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.040719747543335, "global_step": 521251, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0330216884613037, "global_step": 521252, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.108609199523926, "global_step": 521253, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0582587718963623, "global_step": 521254, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.06809401512146, "global_step": 521255, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0673105716705322, "global_step": 521256, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0772202014923096, "global_step": 521257, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.056631326675415, "global_step": 521258, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1031622886657715, "global_step": 521259, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0505967140197754, "global_step": 521260, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9841305017471313, "global_step": 521261, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0141642093658447, "global_step": 521262, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.022670269012451, "global_step": 521263, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1235766410827637, "global_step": 521264, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0440003871917725, "global_step": 521265, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0485939979553223, "global_step": 521266, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0113606452941895, "global_step": 521267, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0482869148254395, "global_step": 521268, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1253175735473633, "global_step": 521269, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.066145658493042, "global_step": 521270, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9720039367675781, "global_step": 521271, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.011338472366333, "global_step": 521272, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.024441957473755, "global_step": 521273, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0496745109558105, "global_step": 521274, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0125019550323486, "global_step": 521275, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9322260618209839, "global_step": 521276, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.936887502670288, "global_step": 521277, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0938172340393066, "global_step": 521278, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0786991119384766, "global_step": 521279, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0535402297973633, "global_step": 521280, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9234217405319214, "global_step": 521281, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9922634363174438, "global_step": 521282, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9503593444824219, "global_step": 521283, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9975907802581787, "global_step": 521284, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.113764762878418, "global_step": 521285, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0318524837493896, "global_step": 521286, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.029780864715576, "global_step": 521287, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0941362380981445, "global_step": 521288, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0965805053710938, "global_step": 521289, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0219202041625977, "global_step": 521290, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0445308685302734, "global_step": 521291, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.104964256286621, "global_step": 521292, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0824923515319824, "global_step": 521293, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.037048816680908, "global_step": 521294, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0269036293029785, "global_step": 521295, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1025073528289795, "global_step": 521296, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1022982597351074, "global_step": 521297, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0838139057159424, "global_step": 521298, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1169707775115967, "global_step": 521299, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.8744786977767944, "global_step": 521300, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0633814334869385, "global_step": 521301, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.007113218307495, "global_step": 521302, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0967414379119873, "global_step": 521303, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0637388229370117, "global_step": 521304, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0452444553375244, "global_step": 521305, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.043187379837036, "global_step": 521306, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0970630645751953, "global_step": 521307, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.074247121810913, "global_step": 521308, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9784948825836182, "global_step": 521309, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9436956644058228, "global_step": 521310, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.05172061920166, "global_step": 521311, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.144275188446045, "global_step": 521312, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1254935264587402, "global_step": 521313, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1525473594665527, "global_step": 521314, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0418083667755127, "global_step": 521315, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1351685523986816, "global_step": 521316, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.098500967025757, "global_step": 521317, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0172908306121826, "global_step": 521318, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9867852926254272, "global_step": 521319, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.071237802505493, "global_step": 521320, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.068380117416382, "global_step": 521321, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0966086387634277, "global_step": 521322, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0007314682006836, "global_step": 521323, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9802002906799316, "global_step": 521324, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0695126056671143, "global_step": 521325, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0033318996429443, "global_step": 521326, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.041701316833496, "global_step": 521327, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.015564441680908, "global_step": 521328, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9978997707366943, "global_step": 521329, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.081407070159912, "global_step": 521330, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0535166263580322, "global_step": 521331, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0170769691467285, "global_step": 521332, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0477964878082275, "global_step": 521333, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0546977519989014, "global_step": 521334, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1318535804748535, "global_step": 521335, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9264247417449951, "global_step": 521336, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0485949516296387, "global_step": 521337, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9786019325256348, "global_step": 521338, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0620174407958984, "global_step": 521339, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0218021869659424, "global_step": 521340, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0317606925964355, "global_step": 521341, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0539259910583496, "global_step": 521342, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.028425931930542, "global_step": 521343, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.018864154815674, "global_step": 521344, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.014119863510132, "global_step": 521345, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0497121810913086, "global_step": 521346, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.079453229904175, "global_step": 521347, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0879299640655518, "global_step": 521348, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0727617740631104, "global_step": 521349, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.062657356262207, "global_step": 521350, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.008192777633667, "global_step": 521351, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.066551446914673, "global_step": 521352, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9998465776443481, "global_step": 521353, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.05930757522583, "global_step": 521354, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0582828521728516, "global_step": 521355, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1093451976776123, "global_step": 521356, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.114713430404663, "global_step": 521357, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.094593048095703, "global_step": 521358, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.001230001449585, "global_step": 521359, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0377182960510254, "global_step": 521360, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0793473720550537, "global_step": 521361, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.06142258644104, "global_step": 521362, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0701093673706055, "global_step": 521363, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.985378384590149, "global_step": 521364, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.054661512374878, "global_step": 521365, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0166919231414795, "global_step": 521366, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9704492092132568, "global_step": 521367, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1422879695892334, "global_step": 521368, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.06249737739563, "global_step": 521369, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0072567462921143, "global_step": 521370, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.093417167663574, "global_step": 521371, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.115124225616455, "global_step": 521372, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.998807668685913, "global_step": 521373, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.030164957046509, "global_step": 521374, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.064746141433716, "global_step": 521375, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0482213497161865, "global_step": 521376, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.012470245361328, "global_step": 521377, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0429465770721436, "global_step": 521378, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0763723850250244, "global_step": 521379, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0365519523620605, "global_step": 521380, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1124932765960693, "global_step": 521381, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0210068225860596, "global_step": 521382, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0719847679138184, "global_step": 521383, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0182838439941406, "global_step": 521384, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0075278282165527, "global_step": 521385, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.048872947692871, "global_step": 521386, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.039438247680664, "global_step": 521387, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9815058708190918, "global_step": 521388, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0347936153411865, "global_step": 521389, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0060102939605713, "global_step": 521390, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0741002559661865, "global_step": 521391, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1137993335723877, "global_step": 521392, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.95270836353302, "global_step": 521393, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0816030502319336, "global_step": 521394, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.012486457824707, "global_step": 521395, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.132949113845825, "global_step": 521396, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.044025421142578, "global_step": 521397, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0812227725982666, "global_step": 521398, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9512799978256226, "global_step": 521399, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0661332607269287, "global_step": 521400, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9957151412963867, "global_step": 521401, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1242258548736572, "global_step": 521402, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.029762029647827, "global_step": 521403, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.121598720550537, "global_step": 521404, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0231494903564453, "global_step": 521405, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0851328372955322, "global_step": 521406, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.051480770111084, "global_step": 521407, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.064682722091675, "global_step": 521408, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.151344060897827, "global_step": 521409, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.063401937484741, "global_step": 521410, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1020994186401367, "global_step": 521411, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.048586368560791, "global_step": 521412, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0476324558258057, "global_step": 521413, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1084954738616943, "global_step": 521414, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9930553436279297, "global_step": 521415, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.014204740524292, "global_step": 521416, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0074779987335205, "global_step": 521417, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0939090251922607, "global_step": 521418, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.123243570327759, "global_step": 521419, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.071294069290161, "global_step": 521420, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9982255697250366, "global_step": 521421, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0914902687072754, "global_step": 521422, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.069951057434082, "global_step": 521423, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.055396318435669, "global_step": 521424, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1080992221832275, "global_step": 521425, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0435729026794434, "global_step": 521426, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.096096992492676, "global_step": 521427, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0252721309661865, "global_step": 521428, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.022900104522705, "global_step": 521429, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.099088430404663, "global_step": 521430, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.031318187713623, "global_step": 521431, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0687224864959717, "global_step": 521432, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.064653158187866, "global_step": 521433, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.048485040664673, "global_step": 521434, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0569818019866943, "global_step": 521435, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.047351837158203, "global_step": 521436, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.012601852416992, "global_step": 521437, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0396664142608643, "global_step": 521438, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.069645643234253, "global_step": 521439, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.016970157623291, "global_step": 521440, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0314624309539795, "global_step": 521441, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0084829330444336, "global_step": 521442, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.078181505203247, "global_step": 521443, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.071927785873413, "global_step": 521444, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0460402965545654, "global_step": 521445, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9590578079223633, "global_step": 521446, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0835487842559814, "global_step": 521447, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1060075759887695, "global_step": 521448, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0741782188415527, "global_step": 521449, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0057451725006104, "global_step": 521450, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0371434688568115, "global_step": 521451, "epoch": 887, "lr": 5e-05}
{"train_loss": 1.9516911506652832, "global_step": 521452, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.1025657653808594, "global_step": 521453, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0415968894958496, "global_step": 521454, "epoch": 887, "lr": 5e-05}
{"train_loss": 2.0709362030029297, "global_step": 521455, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.97019362449646, "global_step": 521456, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.095402240753174, "global_step": 521457, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.944936990737915, "global_step": 521458, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.052741050720215, "global_step": 521459, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0866875648498535, "global_step": 521460, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0209434032440186, "global_step": 521461, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9700734615325928, "global_step": 521462, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0465853214263916, "global_step": 521463, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.12040376663208, "global_step": 521464, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.100551128387451, "global_step": 521465, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9813944101333618, "global_step": 521466, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9498292207717896, "global_step": 521467, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0610477924346924, "global_step": 521468, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9832921028137207, "global_step": 521469, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9334299564361572, "global_step": 521470, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.023754835128784, "global_step": 521471, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0352582931518555, "global_step": 521472, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0404105186462402, "global_step": 521473, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0655484199523926, "global_step": 521474, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1100704669952393, "global_step": 521475, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1093878746032715, "global_step": 521476, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0049519538879395, "global_step": 521477, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0290448665618896, "global_step": 521478, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0393717288970947, "global_step": 521479, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1146652698516846, "global_step": 521480, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.996565818786621, "global_step": 521481, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0344221591949463, "global_step": 521482, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0565619468688965, "global_step": 521483, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0469062328338623, "global_step": 521484, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0886406898498535, "global_step": 521485, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0712668895721436, "global_step": 521486, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.011364221572876, "global_step": 521487, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0174598693847656, "global_step": 521488, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9751522541046143, "global_step": 521489, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.029614210128784, "global_step": 521490, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.069276809692383, "global_step": 521491, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0972864627838135, "global_step": 521492, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.087334394454956, "global_step": 521493, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0031275749206543, "global_step": 521494, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0632071495056152, "global_step": 521495, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0046334266662598, "global_step": 521496, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0236332416534424, "global_step": 521497, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0296592712402344, "global_step": 521498, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.096529722213745, "global_step": 521499, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.031550884246826, "global_step": 521500, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.971840739250183, "global_step": 521501, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9941061735153198, "global_step": 521502, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.98501455783844, "global_step": 521503, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9810914993286133, "global_step": 521504, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0693039894104004, "global_step": 521505, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9525266885757446, "global_step": 521506, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0725960731506348, "global_step": 521507, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1798417568206787, "global_step": 521508, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0236902236938477, "global_step": 521509, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0932562351226807, "global_step": 521510, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.062624931335449, "global_step": 521511, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.037773370742798, "global_step": 521512, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.028329372406006, "global_step": 521513, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.956982135772705, "global_step": 521514, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9645743370056152, "global_step": 521515, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0152950286865234, "global_step": 521516, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0907459259033203, "global_step": 521517, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9778302907943726, "global_step": 521518, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1042938232421875, "global_step": 521519, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.016913414001465, "global_step": 521520, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1069376468658447, "global_step": 521521, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1016685962677, "global_step": 521522, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0300967693328857, "global_step": 521523, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0048744678497314, "global_step": 521524, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.107785940170288, "global_step": 521525, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9745023250579834, "global_step": 521526, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9770405292510986, "global_step": 521527, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0347962379455566, "global_step": 521528, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9837332963943481, "global_step": 521529, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.989195704460144, "global_step": 521530, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9434123039245605, "global_step": 521531, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0939412117004395, "global_step": 521532, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.080683469772339, "global_step": 521533, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9857736825942993, "global_step": 521534, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0311391353607178, "global_step": 521535, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1418771743774414, "global_step": 521536, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.079191207885742, "global_step": 521537, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0787649154663086, "global_step": 521538, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9712494611740112, "global_step": 521539, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1173667907714844, "global_step": 521540, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.051927089691162, "global_step": 521541, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9561870098114014, "global_step": 521542, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0373449325561523, "global_step": 521543, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9657973051071167, "global_step": 521544, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.973419427871704, "global_step": 521545, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.043792963027954, "global_step": 521546, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0977022647857666, "global_step": 521547, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.034406900405884, "global_step": 521548, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0957887172698975, "global_step": 521549, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9907119274139404, "global_step": 521550, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9599312543869019, "global_step": 521551, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9862477779388428, "global_step": 521552, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0192759037017822, "global_step": 521553, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.990246057510376, "global_step": 521554, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9968974590301514, "global_step": 521555, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0366716384887695, "global_step": 521556, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0723211765289307, "global_step": 521557, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9894824028015137, "global_step": 521558, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1338436603546143, "global_step": 521559, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.032210111618042, "global_step": 521560, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.067033290863037, "global_step": 521561, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.047869920730591, "global_step": 521562, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1002323627471924, "global_step": 521563, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1036922931671143, "global_step": 521564, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.032949924468994, "global_step": 521565, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.105909824371338, "global_step": 521566, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0397913455963135, "global_step": 521567, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0031518936157227, "global_step": 521568, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.000070333480835, "global_step": 521569, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.025723695755005, "global_step": 521570, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.001417875289917, "global_step": 521571, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.011000633239746, "global_step": 521572, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0584182739257812, "global_step": 521573, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.007479667663574, "global_step": 521574, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0393457412719727, "global_step": 521575, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.987204909324646, "global_step": 521576, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.006880044937134, "global_step": 521577, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.047065258026123, "global_step": 521578, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.052402973175049, "global_step": 521579, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9757627248764038, "global_step": 521580, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.992854356765747, "global_step": 521581, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0047926902770996, "global_step": 521582, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1072332859039307, "global_step": 521583, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9982476234436035, "global_step": 521584, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0094797611236572, "global_step": 521585, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9627810716629028, "global_step": 521586, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0626518726348877, "global_step": 521587, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0233874320983887, "global_step": 521588, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9771363735198975, "global_step": 521589, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.050076484680176, "global_step": 521590, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0567638874053955, "global_step": 521591, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9581612348556519, "global_step": 521592, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9979140758514404, "global_step": 521593, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.064371347427368, "global_step": 521594, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0161335468292236, "global_step": 521595, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.030876636505127, "global_step": 521596, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.017948627471924, "global_step": 521597, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.019132614135742, "global_step": 521598, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9577687978744507, "global_step": 521599, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0481035709381104, "global_step": 521600, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0255136489868164, "global_step": 521601, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9962379932403564, "global_step": 521602, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9737194776535034, "global_step": 521603, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1116998195648193, "global_step": 521604, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.002272129058838, "global_step": 521605, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9879229068756104, "global_step": 521606, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9671072959899902, "global_step": 521607, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0282177925109863, "global_step": 521608, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.07814621925354, "global_step": 521609, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.119697093963623, "global_step": 521610, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0111348628997803, "global_step": 521611, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1161417961120605, "global_step": 521612, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9487448930740356, "global_step": 521613, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0042662620544434, "global_step": 521614, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0642292499542236, "global_step": 521615, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.992159128189087, "global_step": 521616, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1539840698242188, "global_step": 521617, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.994935393333435, "global_step": 521618, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9816713333129883, "global_step": 521619, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0020599365234375, "global_step": 521620, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1148393154144287, "global_step": 521621, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9384191036224365, "global_step": 521622, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1925668716430664, "global_step": 521623, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.033352851867676, "global_step": 521624, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.057332992553711, "global_step": 521625, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9850921630859375, "global_step": 521626, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.02451491355896, "global_step": 521627, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.983094334602356, "global_step": 521628, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.039802312850952, "global_step": 521629, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9898699522018433, "global_step": 521630, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0835635662078857, "global_step": 521631, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.067300796508789, "global_step": 521632, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9989111423492432, "global_step": 521633, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0006520748138428, "global_step": 521634, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0866339206695557, "global_step": 521635, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0015547275543213, "global_step": 521636, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9689297676086426, "global_step": 521637, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0374679565429688, "global_step": 521638, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.06545090675354, "global_step": 521639, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0334279537200928, "global_step": 521640, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.009373188018799, "global_step": 521641, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0592641830444336, "global_step": 521642, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9381996393203735, "global_step": 521643, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9973838329315186, "global_step": 521644, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1094489097595215, "global_step": 521645, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0377676486968994, "global_step": 521646, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1079587936401367, "global_step": 521647, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.027024984359741, "global_step": 521648, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.058566093444824, "global_step": 521649, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.021817922592163, "global_step": 521650, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9267466068267822, "global_step": 521651, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0010366439819336, "global_step": 521652, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.071141004562378, "global_step": 521653, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1348278522491455, "global_step": 521654, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.064793348312378, "global_step": 521655, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0059356689453125, "global_step": 521656, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.052299737930298, "global_step": 521657, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0516014099121094, "global_step": 521658, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.106954574584961, "global_step": 521659, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0614571571350098, "global_step": 521660, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0753371715545654, "global_step": 521661, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.119699716567993, "global_step": 521662, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0096895694732666, "global_step": 521663, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0274219512939453, "global_step": 521664, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.942427635192871, "global_step": 521665, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.084041118621826, "global_step": 521666, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9776175022125244, "global_step": 521667, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.09559965133667, "global_step": 521668, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.061981439590454, "global_step": 521669, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1705386638641357, "global_step": 521670, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.013260841369629, "global_step": 521671, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0441558361053467, "global_step": 521672, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0716819763183594, "global_step": 521673, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.038037061691284, "global_step": 521674, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.065162420272827, "global_step": 521675, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0464296340942383, "global_step": 521676, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.039989709854126, "global_step": 521677, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.111193895339966, "global_step": 521678, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9729018211364746, "global_step": 521679, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1018428802490234, "global_step": 521680, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.020148754119873, "global_step": 521681, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.059206485748291, "global_step": 521682, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.007225751876831, "global_step": 521683, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9716994762420654, "global_step": 521684, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0094149112701416, "global_step": 521685, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.105473756790161, "global_step": 521686, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1049225330352783, "global_step": 521687, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.050819158554077, "global_step": 521688, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0692062377929688, "global_step": 521689, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0581164360046387, "global_step": 521690, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.090461492538452, "global_step": 521691, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.970395565032959, "global_step": 521692, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.048567771911621, "global_step": 521693, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.10135555267334, "global_step": 521694, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.084879159927368, "global_step": 521695, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.028383731842041, "global_step": 521696, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.045588731765747, "global_step": 521697, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.080639600753784, "global_step": 521698, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.989135503768921, "global_step": 521699, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1268937587738037, "global_step": 521700, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0203475952148438, "global_step": 521701, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0020158290863037, "global_step": 521702, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.00689697265625, "global_step": 521703, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.039517402648926, "global_step": 521704, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.989015817642212, "global_step": 521705, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0278637409210205, "global_step": 521706, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0564067363739014, "global_step": 521707, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9506902694702148, "global_step": 521708, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9511176347732544, "global_step": 521709, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0753376483917236, "global_step": 521710, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9842815399169922, "global_step": 521711, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.081174612045288, "global_step": 521712, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.096693992614746, "global_step": 521713, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0424509048461914, "global_step": 521714, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.104797840118408, "global_step": 521715, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.094991445541382, "global_step": 521716, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9191690683364868, "global_step": 521717, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1905250549316406, "global_step": 521718, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.004549026489258, "global_step": 521719, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0088963508605957, "global_step": 521720, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.06357741355896, "global_step": 521721, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.023289680480957, "global_step": 521722, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0212697982788086, "global_step": 521723, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.044887065887451, "global_step": 521724, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0879597663879395, "global_step": 521725, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9670073986053467, "global_step": 521726, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.059643030166626, "global_step": 521727, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.918155312538147, "global_step": 521728, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.060088634490967, "global_step": 521729, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.094691276550293, "global_step": 521730, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0241007804870605, "global_step": 521731, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.095823049545288, "global_step": 521732, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.025660753250122, "global_step": 521733, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.116044044494629, "global_step": 521734, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9788081645965576, "global_step": 521735, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0744130611419678, "global_step": 521736, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0461294651031494, "global_step": 521737, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.097553253173828, "global_step": 521738, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.029654026031494, "global_step": 521739, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.003218650817871, "global_step": 521740, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.030297040939331, "global_step": 521741, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.022603988647461, "global_step": 521742, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9686846733093262, "global_step": 521743, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0182723999023438, "global_step": 521744, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.003139019012451, "global_step": 521745, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1049387454986572, "global_step": 521746, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.002103328704834, "global_step": 521747, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.011884927749634, "global_step": 521748, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.007641077041626, "global_step": 521749, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9948835372924805, "global_step": 521750, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0324110984802246, "global_step": 521751, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1103618144989014, "global_step": 521752, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0489535331726074, "global_step": 521753, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0227668285369873, "global_step": 521754, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9852675199508667, "global_step": 521755, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0037529468536377, "global_step": 521756, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0592639446258545, "global_step": 521757, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.080220937728882, "global_step": 521758, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.016982078552246, "global_step": 521759, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9754528999328613, "global_step": 521760, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.027846574783325, "global_step": 521761, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0615367889404297, "global_step": 521762, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9903993606567383, "global_step": 521763, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0420773029327393, "global_step": 521764, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.951296091079712, "global_step": 521765, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.046226978302002, "global_step": 521766, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.074481725692749, "global_step": 521767, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9893479347229004, "global_step": 521768, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9936801195144653, "global_step": 521769, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0230493545532227, "global_step": 521770, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0507187843322754, "global_step": 521771, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0370688438415527, "global_step": 521772, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.009552240371704, "global_step": 521773, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.04827618598938, "global_step": 521774, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0597686767578125, "global_step": 521775, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.065084934234619, "global_step": 521776, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9780564308166504, "global_step": 521777, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9720242023468018, "global_step": 521778, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9972833395004272, "global_step": 521779, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.928314208984375, "global_step": 521780, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0072922706604004, "global_step": 521781, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.089299440383911, "global_step": 521782, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0526230335235596, "global_step": 521783, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1131715774536133, "global_step": 521784, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0780467987060547, "global_step": 521785, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0839383602142334, "global_step": 521786, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0408473014831543, "global_step": 521787, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.048783302307129, "global_step": 521788, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0269758701324463, "global_step": 521789, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0531418323516846, "global_step": 521790, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1229193210601807, "global_step": 521791, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.027125358581543, "global_step": 521792, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0361955165863037, "global_step": 521793, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9798468351364136, "global_step": 521794, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1027626991271973, "global_step": 521795, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0661067962646484, "global_step": 521796, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.997994303703308, "global_step": 521797, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9821569919586182, "global_step": 521798, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9701465368270874, "global_step": 521799, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.060636281967163, "global_step": 521800, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1062846183776855, "global_step": 521801, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9477343559265137, "global_step": 521802, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.997536301612854, "global_step": 521803, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0899481773376465, "global_step": 521804, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9823132753372192, "global_step": 521805, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0466537475585938, "global_step": 521806, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.028076410293579, "global_step": 521807, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.058306932449341, "global_step": 521808, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0305402278900146, "global_step": 521809, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.070032835006714, "global_step": 521810, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9966833591461182, "global_step": 521811, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.029552936553955, "global_step": 521812, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0048935413360596, "global_step": 521813, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0906529426574707, "global_step": 521814, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.097412586212158, "global_step": 521815, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.07928729057312, "global_step": 521816, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0753910541534424, "global_step": 521817, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.015353202819824, "global_step": 521818, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1001546382904053, "global_step": 521819, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0728206634521484, "global_step": 521820, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.083616018295288, "global_step": 521821, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.994621753692627, "global_step": 521822, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.062279224395752, "global_step": 521823, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0206847190856934, "global_step": 521824, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0520176887512207, "global_step": 521825, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.090111255645752, "global_step": 521826, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9319120645523071, "global_step": 521827, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.046210289001465, "global_step": 521828, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0178372859954834, "global_step": 521829, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0436959266662598, "global_step": 521830, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0095410346984863, "global_step": 521831, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9949392080307007, "global_step": 521832, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0247128009796143, "global_step": 521833, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0154430866241455, "global_step": 521834, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0552315711975098, "global_step": 521835, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0791289806365967, "global_step": 521836, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0200421810150146, "global_step": 521837, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.072389841079712, "global_step": 521838, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9416216611862183, "global_step": 521839, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.057753324508667, "global_step": 521840, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0547189712524414, "global_step": 521841, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0075345039367676, "global_step": 521842, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.012929916381836, "global_step": 521843, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.982703447341919, "global_step": 521844, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0218279361724854, "global_step": 521845, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9638206958770752, "global_step": 521846, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0205371379852295, "global_step": 521847, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0636589527130127, "global_step": 521848, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.066863775253296, "global_step": 521849, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.065739870071411, "global_step": 521850, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0626771450042725, "global_step": 521851, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.069612503051758, "global_step": 521852, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0275988578796387, "global_step": 521853, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9935907125473022, "global_step": 521854, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0565199851989746, "global_step": 521855, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.071521520614624, "global_step": 521856, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0639305114746094, "global_step": 521857, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.035379648208618, "global_step": 521858, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0250561237335205, "global_step": 521859, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0094175338745117, "global_step": 521860, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0789859294891357, "global_step": 521861, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0298357009887695, "global_step": 521862, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.081725835800171, "global_step": 521863, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.005875587463379, "global_step": 521864, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.985722303390503, "global_step": 521865, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0562257766723633, "global_step": 521866, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0955967903137207, "global_step": 521867, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.035686731338501, "global_step": 521868, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.09200119972229, "global_step": 521869, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0275299549102783, "global_step": 521870, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1195316314697266, "global_step": 521871, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.051844835281372, "global_step": 521872, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0868797302246094, "global_step": 521873, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9967960119247437, "global_step": 521874, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0050997734069824, "global_step": 521875, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0243515968322754, "global_step": 521876, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9733891487121582, "global_step": 521877, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9799737930297852, "global_step": 521878, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0435285568237305, "global_step": 521879, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0410876274108887, "global_step": 521880, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.034461259841919, "global_step": 521881, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.996005892753601, "global_step": 521882, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.075141191482544, "global_step": 521883, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.025935649871826, "global_step": 521884, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0391147136688232, "global_step": 521885, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.052666425704956, "global_step": 521886, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.063197374343872, "global_step": 521887, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.056798219680786, "global_step": 521888, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0237767696380615, "global_step": 521889, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9689565896987915, "global_step": 521890, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.053410768508911, "global_step": 521891, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0948562622070312, "global_step": 521892, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0805087089538574, "global_step": 521893, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.003234624862671, "global_step": 521894, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.028019428253174, "global_step": 521895, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9070435762405396, "global_step": 521896, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0562074184417725, "global_step": 521897, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9535174369812012, "global_step": 521898, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.107435464859009, "global_step": 521899, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9638398885726929, "global_step": 521900, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0699269771575928, "global_step": 521901, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1298532485961914, "global_step": 521902, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.010841131210327, "global_step": 521903, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0865602493286133, "global_step": 521904, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0512659549713135, "global_step": 521905, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0275683403015137, "global_step": 521906, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1156699657440186, "global_step": 521907, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.132918119430542, "global_step": 521908, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0265161991119385, "global_step": 521909, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.049001693725586, "global_step": 521910, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0378801822662354, "global_step": 521911, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0067479610443115, "global_step": 521912, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9758938550949097, "global_step": 521913, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.056549549102783, "global_step": 521914, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.031629800796509, "global_step": 521915, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9773746728897095, "global_step": 521916, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.04211163520813, "global_step": 521917, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.039793014526367, "global_step": 521918, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.996842622756958, "global_step": 521919, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.002122163772583, "global_step": 521920, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.044240951538086, "global_step": 521921, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0924201011657715, "global_step": 521922, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0308399200439453, "global_step": 521923, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0604283809661865, "global_step": 521924, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.052440881729126, "global_step": 521925, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.073615074157715, "global_step": 521926, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0459678173065186, "global_step": 521927, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.030215263366699, "global_step": 521928, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9782665967941284, "global_step": 521929, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.061250686645508, "global_step": 521930, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.076964855194092, "global_step": 521931, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.025214910507202, "global_step": 521932, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0415265560150146, "global_step": 521933, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.13559627532959, "global_step": 521934, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.038726806640625, "global_step": 521935, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9551602602005005, "global_step": 521936, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1015219688415527, "global_step": 521937, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.078962564468384, "global_step": 521938, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.124547243118286, "global_step": 521939, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0132980346679688, "global_step": 521940, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0777571201324463, "global_step": 521941, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.02321457862854, "global_step": 521942, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0973193645477295, "global_step": 521943, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.010241985321045, "global_step": 521944, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.020056962966919, "global_step": 521945, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.076256036758423, "global_step": 521946, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.026207447052002, "global_step": 521947, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9871917963027954, "global_step": 521948, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.12747859954834, "global_step": 521949, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0795669555664062, "global_step": 521950, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0336785316467285, "global_step": 521951, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0970091819763184, "global_step": 521952, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.072765350341797, "global_step": 521953, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9929569959640503, "global_step": 521954, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.063718795776367, "global_step": 521955, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0937657356262207, "global_step": 521956, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9909887313842773, "global_step": 521957, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0628814697265625, "global_step": 521958, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.043887138366699, "global_step": 521959, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0849924087524414, "global_step": 521960, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9864835739135742, "global_step": 521961, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0246694087982178, "global_step": 521962, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0318286418914795, "global_step": 521963, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9743446111679077, "global_step": 521964, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9813367128372192, "global_step": 521965, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0747504234313965, "global_step": 521966, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0535025596618652, "global_step": 521967, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0407536029815674, "global_step": 521968, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0550785064697266, "global_step": 521969, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0731709003448486, "global_step": 521970, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9449437856674194, "global_step": 521971, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0202155113220215, "global_step": 521972, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.060865640640259, "global_step": 521973, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.01765513420105, "global_step": 521974, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9524990320205688, "global_step": 521975, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9873249530792236, "global_step": 521976, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9641468524932861, "global_step": 521977, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.984045147895813, "global_step": 521978, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0430147647857666, "global_step": 521979, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.073870897293091, "global_step": 521980, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.027697801589966, "global_step": 521981, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1402456760406494, "global_step": 521982, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.150360107421875, "global_step": 521983, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0166125297546387, "global_step": 521984, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.095271587371826, "global_step": 521985, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.006549835205078, "global_step": 521986, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0221076011657715, "global_step": 521987, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.982258677482605, "global_step": 521988, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0084288120269775, "global_step": 521989, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9884717464447021, "global_step": 521990, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.040191411972046, "global_step": 521991, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9950010776519775, "global_step": 521992, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.918346881866455, "global_step": 521993, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.090930461883545, "global_step": 521994, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0995476245880127, "global_step": 521995, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9523465633392334, "global_step": 521996, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0325398445129395, "global_step": 521997, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.943858027458191, "global_step": 521998, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0427603721618652, "global_step": 521999, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.049893379211426, "global_step": 522000, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0426278114318848, "global_step": 522001, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.002716064453125, "global_step": 522002, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9942213296890259, "global_step": 522003, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9843829870224, "global_step": 522004, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0179145336151123, "global_step": 522005, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0716922283172607, "global_step": 522006, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0560178756713867, "global_step": 522007, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.080791473388672, "global_step": 522008, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.085306406021118, "global_step": 522009, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.094714879989624, "global_step": 522010, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1230337619781494, "global_step": 522011, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1553609371185303, "global_step": 522012, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0455503463745117, "global_step": 522013, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.024482250213623, "global_step": 522014, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0967724323272705, "global_step": 522015, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0192904472351074, "global_step": 522016, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.993801474571228, "global_step": 522017, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0797066688537598, "global_step": 522018, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.018754482269287, "global_step": 522019, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1785991191864014, "global_step": 522020, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0290703773498535, "global_step": 522021, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0291271209716797, "global_step": 522022, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0480854511260986, "global_step": 522023, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.087998867034912, "global_step": 522024, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.106024742126465, "global_step": 522025, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.057131767272949, "global_step": 522026, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0322213172912598, "global_step": 522027, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9811147451400757, "global_step": 522028, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0361452102661133, "global_step": 522029, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.08547043800354, "global_step": 522030, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0513806343078613, "global_step": 522031, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.980741262435913, "global_step": 522032, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0537989139556885, "global_step": 522033, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.946237564086914, "global_step": 522034, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0019140243530273, "global_step": 522035, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0810792446136475, "global_step": 522036, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0824332237243652, "global_step": 522037, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.096806049346924, "global_step": 522038, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.075181722640991, "global_step": 522039, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1300501823425293, "global_step": 522040, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1777572631835938, "global_step": 522041, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.986954927444458, "global_step": 522042, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.095161199569702, "global_step": 522043, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.8777087926864624, "global_step": 522044, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.977805495262146, "global_step": 522045, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.042816162109375, "global_step": 522046, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.054689407348633, "global_step": 522047, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.115767240524292, "global_step": 522048, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0332841873168945, "global_step": 522049, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0836894512176514, "global_step": 522050, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.988349437713623, "global_step": 522051, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.062783718109131, "global_step": 522052, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9857814311981201, "global_step": 522053, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0250422954559326, "global_step": 522054, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0310449600219727, "global_step": 522055, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.018665075302124, "global_step": 522056, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0417299270629883, "global_step": 522057, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.07271409034729, "global_step": 522058, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0599021911621094, "global_step": 522059, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9980753660202026, "global_step": 522060, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.019453287124634, "global_step": 522061, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0066428184509277, "global_step": 522062, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.987778663635254, "global_step": 522063, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0448226928710938, "global_step": 522064, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.042715549468994, "global_step": 522065, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9980626106262207, "global_step": 522066, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0382659435272217, "global_step": 522067, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.979754090309143, "global_step": 522068, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9764432907104492, "global_step": 522069, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.056161403656006, "global_step": 522070, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0611801147460938, "global_step": 522071, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9810377359390259, "global_step": 522072, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9684128761291504, "global_step": 522073, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0933375358581543, "global_step": 522074, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.061037302017212, "global_step": 522075, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0493273735046387, "global_step": 522076, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.964685082435608, "global_step": 522077, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0437982082366943, "global_step": 522078, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9728331565856934, "global_step": 522079, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0530781745910645, "global_step": 522080, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.017183303833008, "global_step": 522081, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.068864107131958, "global_step": 522082, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9880962371826172, "global_step": 522083, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9978550672531128, "global_step": 522084, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9333604574203491, "global_step": 522085, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9533541202545166, "global_step": 522086, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.138645648956299, "global_step": 522087, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.975098729133606, "global_step": 522088, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0618059635162354, "global_step": 522089, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0176780223846436, "global_step": 522090, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1090776920318604, "global_step": 522091, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.053295612335205, "global_step": 522092, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.061943769454956, "global_step": 522093, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0023305416107178, "global_step": 522094, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.123089075088501, "global_step": 522095, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0972390174865723, "global_step": 522096, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0030417442321777, "global_step": 522097, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.000203847885132, "global_step": 522098, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.982715368270874, "global_step": 522099, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9811173677444458, "global_step": 522100, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.137180805206299, "global_step": 522101, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1218791007995605, "global_step": 522102, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.004239320755005, "global_step": 522103, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.019519805908203, "global_step": 522104, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0198166370391846, "global_step": 522105, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0090532302856445, "global_step": 522106, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0103087425231934, "global_step": 522107, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9770992994308472, "global_step": 522108, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0650525093078613, "global_step": 522109, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0752763748168945, "global_step": 522110, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0685834884643555, "global_step": 522111, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0766472816467285, "global_step": 522112, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0850284099578857, "global_step": 522113, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9649057388305664, "global_step": 522114, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0710597038269043, "global_step": 522115, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9459043741226196, "global_step": 522116, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0331757068634033, "global_step": 522117, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.07696533203125, "global_step": 522118, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0130903720855713, "global_step": 522119, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0197112560272217, "global_step": 522120, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0964367389678955, "global_step": 522121, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0529918670654297, "global_step": 522122, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9880119562149048, "global_step": 522123, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9999500513076782, "global_step": 522124, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.068726062774658, "global_step": 522125, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.034881114959717, "global_step": 522126, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0817246437072754, "global_step": 522127, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.057093858718872, "global_step": 522128, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9966238737106323, "global_step": 522129, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1321308612823486, "global_step": 522130, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.048661470413208, "global_step": 522131, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.021496295928955, "global_step": 522132, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0492966175079346, "global_step": 522133, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.070122003555298, "global_step": 522134, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0518903732299805, "global_step": 522135, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.086303234100342, "global_step": 522136, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1151115894317627, "global_step": 522137, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.018010139465332, "global_step": 522138, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0087320804595947, "global_step": 522139, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0138561725616455, "global_step": 522140, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.013824939727783, "global_step": 522141, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1118133068084717, "global_step": 522142, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0404882431030273, "global_step": 522143, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9316024780273438, "global_step": 522144, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0544891357421875, "global_step": 522145, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0152506828308105, "global_step": 522146, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.024538040161133, "global_step": 522147, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.037778615951538, "global_step": 522148, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.098525047302246, "global_step": 522149, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.025606870651245, "global_step": 522150, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9634355306625366, "global_step": 522151, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.033623218536377, "global_step": 522152, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.069833278656006, "global_step": 522153, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9836795330047607, "global_step": 522154, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.121249198913574, "global_step": 522155, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9989250898361206, "global_step": 522156, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.979212760925293, "global_step": 522157, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.004383087158203, "global_step": 522158, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.044696807861328, "global_step": 522159, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.003669023513794, "global_step": 522160, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.061547040939331, "global_step": 522161, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.029186248779297, "global_step": 522162, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1071360111236572, "global_step": 522163, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1143598556518555, "global_step": 522164, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0040838718414307, "global_step": 522165, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0225331783294678, "global_step": 522166, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9670895338058472, "global_step": 522167, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.959137201309204, "global_step": 522168, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0233280658721924, "global_step": 522169, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0562233924865723, "global_step": 522170, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1190569400787354, "global_step": 522171, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.989704966545105, "global_step": 522172, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.022968053817749, "global_step": 522173, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9743826389312744, "global_step": 522174, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9884872436523438, "global_step": 522175, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1093451976776123, "global_step": 522176, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.040224075317383, "global_step": 522177, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0713438987731934, "global_step": 522178, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0422537326812744, "global_step": 522179, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9298290014266968, "global_step": 522180, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.061147451400757, "global_step": 522181, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.103477954864502, "global_step": 522182, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1008005142211914, "global_step": 522183, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1383261680603027, "global_step": 522184, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0860838890075684, "global_step": 522185, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9703937768936157, "global_step": 522186, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9991132020950317, "global_step": 522187, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.093400001525879, "global_step": 522188, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.128298282623291, "global_step": 522189, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.09270977973938, "global_step": 522190, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.009674549102783, "global_step": 522191, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.091637372970581, "global_step": 522192, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.006861925125122, "global_step": 522193, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.127896308898926, "global_step": 522194, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0523595809936523, "global_step": 522195, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9849358797073364, "global_step": 522196, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9230701923370361, "global_step": 522197, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0676350593566895, "global_step": 522198, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.097669839859009, "global_step": 522199, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0360212326049805, "global_step": 522200, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0293540954589844, "global_step": 522201, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.016099452972412, "global_step": 522202, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0031094551086426, "global_step": 522203, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.033360242843628, "global_step": 522204, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.072031259536743, "global_step": 522205, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.109769344329834, "global_step": 522206, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0109572410583496, "global_step": 522207, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.010606050491333, "global_step": 522208, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0778191089630127, "global_step": 522209, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.057856559753418, "global_step": 522210, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.000502586364746, "global_step": 522211, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9838321208953857, "global_step": 522212, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9900648593902588, "global_step": 522213, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0692803859710693, "global_step": 522214, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0873897075653076, "global_step": 522215, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.09806752204895, "global_step": 522216, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.051593065261841, "global_step": 522217, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.032269239425659, "global_step": 522218, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.035782814025879, "global_step": 522219, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0385255813598633, "global_step": 522220, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.108293056488037, "global_step": 522221, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.01997971534729, "global_step": 522222, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.108182430267334, "global_step": 522223, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0639705657958984, "global_step": 522224, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9580681324005127, "global_step": 522225, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0481860637664795, "global_step": 522226, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0874788761138916, "global_step": 522227, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1851441860198975, "global_step": 522228, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.081129312515259, "global_step": 522229, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.029829740524292, "global_step": 522230, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.08573842048645, "global_step": 522231, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1017487049102783, "global_step": 522232, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9661775827407837, "global_step": 522233, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0667614936828613, "global_step": 522234, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0421085357666016, "global_step": 522235, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1034469604492188, "global_step": 522236, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0214145183563232, "global_step": 522237, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.001180648803711, "global_step": 522238, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0841569900512695, "global_step": 522239, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.004024028778076, "global_step": 522240, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0138564109802246, "global_step": 522241, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.044179916381836, "global_step": 522242, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9932881593704224, "global_step": 522243, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0362401008605957, "global_step": 522244, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0799150466918945, "global_step": 522245, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.05646014213562, "global_step": 522246, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.023362874984741, "global_step": 522247, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.035885810852051, "global_step": 522248, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.058324098587036, "global_step": 522249, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9805940389633179, "global_step": 522250, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.018784284591675, "global_step": 522251, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.113507032394409, "global_step": 522252, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.071943521499634, "global_step": 522253, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.069328784942627, "global_step": 522254, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0053718090057373, "global_step": 522255, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0850911140441895, "global_step": 522256, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9398808479309082, "global_step": 522257, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0268869400024414, "global_step": 522258, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1085541248321533, "global_step": 522259, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0168635845184326, "global_step": 522260, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0423669815063477, "global_step": 522261, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0994513034820557, "global_step": 522262, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.101349353790283, "global_step": 522263, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.047332525253296, "global_step": 522264, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0479416847229004, "global_step": 522265, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1091928482055664, "global_step": 522266, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.03617262840271, "global_step": 522267, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0082643032073975, "global_step": 522268, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.045825958251953, "global_step": 522269, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.014230489730835, "global_step": 522270, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.121373414993286, "global_step": 522271, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.079251289367676, "global_step": 522272, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0882554054260254, "global_step": 522273, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0446505546569824, "global_step": 522274, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.031174898147583, "global_step": 522275, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0654664039611816, "global_step": 522276, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9448208808898926, "global_step": 522277, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0283572673797607, "global_step": 522278, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0486860275268555, "global_step": 522279, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0507826805114746, "global_step": 522280, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.055753231048584, "global_step": 522281, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0614211559295654, "global_step": 522282, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0399489402770996, "global_step": 522283, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0909953117370605, "global_step": 522284, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9837477207183838, "global_step": 522285, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.099846363067627, "global_step": 522286, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0174355506896973, "global_step": 522287, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0133862495422363, "global_step": 522288, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.014409065246582, "global_step": 522289, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0017764568328857, "global_step": 522290, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0057971477508545, "global_step": 522291, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.998901605606079, "global_step": 522292, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9745134115219116, "global_step": 522293, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.023585796356201, "global_step": 522294, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0777411460876465, "global_step": 522295, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0292575359344482, "global_step": 522296, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.994710922241211, "global_step": 522297, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9443382024765015, "global_step": 522298, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1086068153381348, "global_step": 522299, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.147097110748291, "global_step": 522300, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9719023704528809, "global_step": 522301, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0522427558898926, "global_step": 522302, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.080841064453125, "global_step": 522303, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0632803440093994, "global_step": 522304, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1551918983459473, "global_step": 522305, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0234522819519043, "global_step": 522306, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.046884059906006, "global_step": 522307, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.030141830444336, "global_step": 522308, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1197900772094727, "global_step": 522309, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1257729530334473, "global_step": 522310, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9770104885101318, "global_step": 522311, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.042022228240967, "global_step": 522312, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0135788917541504, "global_step": 522313, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0685691833496094, "global_step": 522314, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1020150184631348, "global_step": 522315, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0318949222564697, "global_step": 522316, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9296656847000122, "global_step": 522317, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.147761344909668, "global_step": 522318, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0321505069732666, "global_step": 522319, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.081545829772949, "global_step": 522320, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.056609630584717, "global_step": 522321, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1057801246643066, "global_step": 522322, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.087062358856201, "global_step": 522323, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1278505325317383, "global_step": 522324, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0297775268554688, "global_step": 522325, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.099391222000122, "global_step": 522326, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0582478046417236, "global_step": 522327, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1319172382354736, "global_step": 522328, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.151949644088745, "global_step": 522329, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.012409210205078, "global_step": 522330, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.097308397293091, "global_step": 522331, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0213375091552734, "global_step": 522332, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.049550771713257, "global_step": 522333, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0720040798187256, "global_step": 522334, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1320393085479736, "global_step": 522335, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0796995162963867, "global_step": 522336, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0216236114501953, "global_step": 522337, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1538503170013428, "global_step": 522338, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.07395339012146, "global_step": 522339, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.034027576446533, "global_step": 522340, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.104680299758911, "global_step": 522341, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9692572355270386, "global_step": 522342, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0754597187042236, "global_step": 522343, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0365281105041504, "global_step": 522344, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.065133571624756, "global_step": 522345, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0044095516204834, "global_step": 522346, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9852935075759888, "global_step": 522347, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0662081241607666, "global_step": 522348, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0495660305023193, "global_step": 522349, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0140278339385986, "global_step": 522350, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.023587703704834, "global_step": 522351, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.048672676086426, "global_step": 522352, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.008932113647461, "global_step": 522353, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0204479694366455, "global_step": 522354, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.088906764984131, "global_step": 522355, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.104104518890381, "global_step": 522356, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0827202796936035, "global_step": 522357, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0197577476501465, "global_step": 522358, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.101517677307129, "global_step": 522359, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.099177598953247, "global_step": 522360, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0816073417663574, "global_step": 522361, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0500123500823975, "global_step": 522362, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.034980297088623, "global_step": 522363, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0224974155426025, "global_step": 522364, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0217783451080322, "global_step": 522365, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.030161142349243, "global_step": 522366, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9169052839279175, "global_step": 522367, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.043485641479492, "global_step": 522368, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0752663612365723, "global_step": 522369, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.063185691833496, "global_step": 522370, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0089664459228516, "global_step": 522371, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1290907859802246, "global_step": 522372, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0442538261413574, "global_step": 522373, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.041912078857422, "global_step": 522374, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.060128927230835, "global_step": 522375, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0514235496520996, "global_step": 522376, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.049893379211426, "global_step": 522377, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0696663856506348, "global_step": 522378, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0999627113342285, "global_step": 522379, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0494415760040283, "global_step": 522380, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0158498287200928, "global_step": 522381, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0682122707366943, "global_step": 522382, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0245025157928467, "global_step": 522383, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.989679217338562, "global_step": 522384, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9544458389282227, "global_step": 522385, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9528769254684448, "global_step": 522386, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0093319416046143, "global_step": 522387, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.1391396522521973, "global_step": 522388, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.029686212539673, "global_step": 522389, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0838510990142822, "global_step": 522390, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0542092323303223, "global_step": 522391, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0471253395080566, "global_step": 522392, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0300545692443848, "global_step": 522393, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9956766366958618, "global_step": 522394, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.13765549659729, "global_step": 522395, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9767651557922363, "global_step": 522396, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0857298374176025, "global_step": 522397, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0239195823669434, "global_step": 522398, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.01484751701355, "global_step": 522399, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0056183338165283, "global_step": 522400, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0882937908172607, "global_step": 522401, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0040040016174316, "global_step": 522402, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.043567657470703, "global_step": 522403, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.045053005218506, "global_step": 522404, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0786890983581543, "global_step": 522405, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0381038188934326, "global_step": 522406, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0664420127868652, "global_step": 522407, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.005162477493286, "global_step": 522408, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.115175485610962, "global_step": 522409, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0522992610931396, "global_step": 522410, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.125279664993286, "global_step": 522411, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9741299152374268, "global_step": 522412, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0781469345092773, "global_step": 522413, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0571954250335693, "global_step": 522414, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.030475616455078, "global_step": 522415, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0390968322753906, "global_step": 522416, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0365641117095947, "global_step": 522417, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0378313064575195, "global_step": 522418, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.009901762008667, "global_step": 522419, "epoch": 888, "lr": 5e-05}
{"train_loss": 1.9708099365234375, "global_step": 522420, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.17362904548645, "global_step": 522421, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0658857822418213, "global_step": 522422, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0398855209350586, "global_step": 522423, "epoch": 888, "lr": 5e-05}
{"train_loss": 2.0653908252716064, "global_step": 522424, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9985547065734863, "global_step": 522425, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9361282587051392, "global_step": 522426, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.024674892425537, "global_step": 522427, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9786186218261719, "global_step": 522428, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9579176902770996, "global_step": 522429, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0750627517700195, "global_step": 522430, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.032942533493042, "global_step": 522431, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0742154121398926, "global_step": 522432, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0678985118865967, "global_step": 522433, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0041842460632324, "global_step": 522434, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.10390567779541, "global_step": 522435, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.130052089691162, "global_step": 522436, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0445265769958496, "global_step": 522437, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0041658878326416, "global_step": 522438, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0092897415161133, "global_step": 522439, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.072171926498413, "global_step": 522440, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1429009437561035, "global_step": 522441, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0676801204681396, "global_step": 522442, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.973325252532959, "global_step": 522443, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0385215282440186, "global_step": 522444, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0645272731781006, "global_step": 522445, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0666146278381348, "global_step": 522446, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0718977451324463, "global_step": 522447, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9954924583435059, "global_step": 522448, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.055290937423706, "global_step": 522449, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.061167001724243, "global_step": 522450, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0291404724121094, "global_step": 522451, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.098489999771118, "global_step": 522452, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.032498359680176, "global_step": 522453, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9752287864685059, "global_step": 522454, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.056420087814331, "global_step": 522455, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.033998489379883, "global_step": 522456, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.992763876914978, "global_step": 522457, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.054150104522705, "global_step": 522458, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.05889892578125, "global_step": 522459, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0619513988494873, "global_step": 522460, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.941267967224121, "global_step": 522461, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0044288635253906, "global_step": 522462, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0551538467407227, "global_step": 522463, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0377917289733887, "global_step": 522464, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0825140476226807, "global_step": 522465, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9267072677612305, "global_step": 522466, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.091749906539917, "global_step": 522467, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.034024477005005, "global_step": 522468, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.043893575668335, "global_step": 522469, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9893983602523804, "global_step": 522470, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.135709524154663, "global_step": 522471, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.044671058654785, "global_step": 522472, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.072700023651123, "global_step": 522473, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.965378761291504, "global_step": 522474, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.090409278869629, "global_step": 522475, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0608127117156982, "global_step": 522476, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0254874229431152, "global_step": 522477, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0025787353515625, "global_step": 522478, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.141470193862915, "global_step": 522479, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.019876718521118, "global_step": 522480, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9699286222457886, "global_step": 522481, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9923793077468872, "global_step": 522482, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.102280855178833, "global_step": 522483, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.132286310195923, "global_step": 522484, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9558185338974, "global_step": 522485, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0467376708984375, "global_step": 522486, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1010828018188477, "global_step": 522487, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0188562870025635, "global_step": 522488, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.015033483505249, "global_step": 522489, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.056591033935547, "global_step": 522490, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9373579025268555, "global_step": 522491, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0596587657928467, "global_step": 522492, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.023224115371704, "global_step": 522493, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0347816944122314, "global_step": 522494, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9913573265075684, "global_step": 522495, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0888960361480713, "global_step": 522496, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.012648105621338, "global_step": 522497, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.009305238723755, "global_step": 522498, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.043255090713501, "global_step": 522499, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.01658296585083, "global_step": 522500, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0406179428100586, "global_step": 522501, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.052504301071167, "global_step": 522502, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0695865154266357, "global_step": 522503, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.023057460784912, "global_step": 522504, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.049778938293457, "global_step": 522505, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0162971019744873, "global_step": 522506, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9423154592514038, "global_step": 522507, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9912128448486328, "global_step": 522508, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9809906482696533, "global_step": 522509, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.047598123550415, "global_step": 522510, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.027048349380493, "global_step": 522511, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9702363014221191, "global_step": 522512, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0080082416534424, "global_step": 522513, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0118772983551025, "global_step": 522514, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9944337606430054, "global_step": 522515, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0011518001556396, "global_step": 522516, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0053837299346924, "global_step": 522517, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.999104380607605, "global_step": 522518, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0971791744232178, "global_step": 522519, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9746443033218384, "global_step": 522520, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0525379180908203, "global_step": 522521, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.025266170501709, "global_step": 522522, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0321030616760254, "global_step": 522523, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.124107599258423, "global_step": 522524, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.029744863510132, "global_step": 522525, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9533891677856445, "global_step": 522526, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0546457767486572, "global_step": 522527, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0549216270446777, "global_step": 522528, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1241695880889893, "global_step": 522529, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.035090923309326, "global_step": 522530, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0798025131225586, "global_step": 522531, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0331993103027344, "global_step": 522532, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0795884132385254, "global_step": 522533, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.005084991455078, "global_step": 522534, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0497214794158936, "global_step": 522535, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.011430025100708, "global_step": 522536, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.997687816619873, "global_step": 522537, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0113279819488525, "global_step": 522538, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.038916826248169, "global_step": 522539, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0765693187713623, "global_step": 522540, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.030876636505127, "global_step": 522541, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.066697835922241, "global_step": 522542, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.087885618209839, "global_step": 522543, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0381929874420166, "global_step": 522544, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.033893346786499, "global_step": 522545, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.031277894973755, "global_step": 522546, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.103053092956543, "global_step": 522547, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0358943939208984, "global_step": 522548, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9806451797485352, "global_step": 522549, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.132145643234253, "global_step": 522550, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9911351203918457, "global_step": 522551, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9419671297073364, "global_step": 522552, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9744493961334229, "global_step": 522553, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9721431732177734, "global_step": 522554, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.113858461380005, "global_step": 522555, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0028440952301025, "global_step": 522556, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.990439534187317, "global_step": 522557, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.099614381790161, "global_step": 522558, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.986337423324585, "global_step": 522559, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.067704916000366, "global_step": 522560, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0327649116516113, "global_step": 522561, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.014268398284912, "global_step": 522562, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0330557823181152, "global_step": 522563, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.028043031692505, "global_step": 522564, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0309536457061768, "global_step": 522565, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9909522533416748, "global_step": 522566, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.103238105773926, "global_step": 522567, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0269968509674072, "global_step": 522568, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9660861492156982, "global_step": 522569, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.968393087387085, "global_step": 522570, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0852444171905518, "global_step": 522571, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0190727710723877, "global_step": 522572, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1568050384521484, "global_step": 522573, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.079071283340454, "global_step": 522574, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.104656219482422, "global_step": 522575, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.104912281036377, "global_step": 522576, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0337977409362793, "global_step": 522577, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9428668022155762, "global_step": 522578, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0445919036865234, "global_step": 522579, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.023627996444702, "global_step": 522580, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.078580379486084, "global_step": 522581, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9400789737701416, "global_step": 522582, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0409200191497803, "global_step": 522583, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0424623489379883, "global_step": 522584, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0408709049224854, "global_step": 522585, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.983464002609253, "global_step": 522586, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0082974433898926, "global_step": 522587, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.062249183654785, "global_step": 522588, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.075145959854126, "global_step": 522589, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0916872024536133, "global_step": 522590, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0612716674804688, "global_step": 522591, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.031827211380005, "global_step": 522592, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.064639091491699, "global_step": 522593, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0827903747558594, "global_step": 522594, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.055891513824463, "global_step": 522595, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.11753511428833, "global_step": 522596, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1432008743286133, "global_step": 522597, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0003538131713867, "global_step": 522598, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9957925081253052, "global_step": 522599, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0277929306030273, "global_step": 522600, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.051079750061035, "global_step": 522601, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0973331928253174, "global_step": 522602, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0385336875915527, "global_step": 522603, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0771563053131104, "global_step": 522604, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0479488372802734, "global_step": 522605, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9776121377944946, "global_step": 522606, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9506893157958984, "global_step": 522607, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0417001247406006, "global_step": 522608, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9978958368301392, "global_step": 522609, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.072082757949829, "global_step": 522610, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0720856189727783, "global_step": 522611, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1124539375305176, "global_step": 522612, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.101440191268921, "global_step": 522613, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0092830657958984, "global_step": 522614, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0918326377868652, "global_step": 522615, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9899449348449707, "global_step": 522616, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.06227445602417, "global_step": 522617, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0347461700439453, "global_step": 522618, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0248360633850098, "global_step": 522619, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0742127895355225, "global_step": 522620, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0216166973114014, "global_step": 522621, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.008610486984253, "global_step": 522622, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.021925449371338, "global_step": 522623, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1057729721069336, "global_step": 522624, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0556349754333496, "global_step": 522625, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.964139461517334, "global_step": 522626, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0901286602020264, "global_step": 522627, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.064517021179199, "global_step": 522628, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0415761470794678, "global_step": 522629, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.032562255859375, "global_step": 522630, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9939744472503662, "global_step": 522631, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.047377586364746, "global_step": 522632, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0640251636505127, "global_step": 522633, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0019142627716064, "global_step": 522634, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.94363534450531, "global_step": 522635, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.021334648132324, "global_step": 522636, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.102607011795044, "global_step": 522637, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0332722663879395, "global_step": 522638, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0936121940612793, "global_step": 522639, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.076214551925659, "global_step": 522640, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9507898092269897, "global_step": 522641, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0677216053009033, "global_step": 522642, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.073195695877075, "global_step": 522643, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.047747850418091, "global_step": 522644, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0383474826812744, "global_step": 522645, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9842689037322998, "global_step": 522646, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9763339757919312, "global_step": 522647, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0206503868103027, "global_step": 522648, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0708372592926025, "global_step": 522649, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9838650226593018, "global_step": 522650, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0505807399749756, "global_step": 522651, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0483078956604004, "global_step": 522652, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9068247079849243, "global_step": 522653, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9534939527511597, "global_step": 522654, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0371522903442383, "global_step": 522655, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0090935230255127, "global_step": 522656, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.008883476257324, "global_step": 522657, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.012650489807129, "global_step": 522658, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.091235399246216, "global_step": 522659, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0562686920166016, "global_step": 522660, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0048787593841553, "global_step": 522661, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0672483444213867, "global_step": 522662, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.062675952911377, "global_step": 522663, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.080493450164795, "global_step": 522664, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.005157232284546, "global_step": 522665, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0033676624298096, "global_step": 522666, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0043647289276123, "global_step": 522667, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0242249965667725, "global_step": 522668, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9509241580963135, "global_step": 522669, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1085803508758545, "global_step": 522670, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9834495782852173, "global_step": 522671, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.954324722290039, "global_step": 522672, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.075638771057129, "global_step": 522673, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0923280715942383, "global_step": 522674, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0658297538757324, "global_step": 522675, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0797767639160156, "global_step": 522676, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0411112308502197, "global_step": 522677, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0658559799194336, "global_step": 522678, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0197904109954834, "global_step": 522679, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.060063123703003, "global_step": 522680, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9597644805908203, "global_step": 522681, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0581729412078857, "global_step": 522682, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9529204368591309, "global_step": 522683, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0373990535736084, "global_step": 522684, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.022921562194824, "global_step": 522685, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9917263984680176, "global_step": 522686, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.039552927017212, "global_step": 522687, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.090613603591919, "global_step": 522688, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.036696434020996, "global_step": 522689, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0329651832580566, "global_step": 522690, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0249314308166504, "global_step": 522691, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0470974445343018, "global_step": 522692, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0617151260375977, "global_step": 522693, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9959545135498047, "global_step": 522694, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.111588478088379, "global_step": 522695, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.106128454208374, "global_step": 522696, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1124706268310547, "global_step": 522697, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.054537773132324, "global_step": 522698, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.930705189704895, "global_step": 522699, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.04091477394104, "global_step": 522700, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.021641731262207, "global_step": 522701, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0010054111480713, "global_step": 522702, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1623640060424805, "global_step": 522703, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.03550386428833, "global_step": 522704, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9992480278015137, "global_step": 522705, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0877888202667236, "global_step": 522706, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.989474892616272, "global_step": 522707, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.072096586227417, "global_step": 522708, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0767011642456055, "global_step": 522709, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9556159973144531, "global_step": 522710, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.006852388381958, "global_step": 522711, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.064544439315796, "global_step": 522712, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0565826892852783, "global_step": 522713, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0274696350097656, "global_step": 522714, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9852676391601562, "global_step": 522715, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0629358291625977, "global_step": 522716, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1230483055114746, "global_step": 522717, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0628654956817627, "global_step": 522718, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9894511699676514, "global_step": 522719, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0554447174072266, "global_step": 522720, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.026336669921875, "global_step": 522721, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.007852077484131, "global_step": 522722, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.023510456085205, "global_step": 522723, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.061328649520874, "global_step": 522724, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.009960889816284, "global_step": 522725, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9589546918869019, "global_step": 522726, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0555100440979004, "global_step": 522727, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9859691858291626, "global_step": 522728, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0568628311157227, "global_step": 522729, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0162997245788574, "global_step": 522730, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1282806396484375, "global_step": 522731, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0152623653411865, "global_step": 522732, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1061787605285645, "global_step": 522733, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0976366996765137, "global_step": 522734, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0199460983276367, "global_step": 522735, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.141916036605835, "global_step": 522736, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0428152084350586, "global_step": 522737, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.084061861038208, "global_step": 522738, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0683364868164062, "global_step": 522739, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1286537647247314, "global_step": 522740, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1023612022399902, "global_step": 522741, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9904227256774902, "global_step": 522742, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9829504489898682, "global_step": 522743, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.029442310333252, "global_step": 522744, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.02529239654541, "global_step": 522745, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.066815137863159, "global_step": 522746, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9656555652618408, "global_step": 522747, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9835847616195679, "global_step": 522748, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1354031562805176, "global_step": 522749, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.029649257659912, "global_step": 522750, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.942889928817749, "global_step": 522751, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.002429246902466, "global_step": 522752, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0454368591308594, "global_step": 522753, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9663225412368774, "global_step": 522754, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.095632314682007, "global_step": 522755, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.009665012359619, "global_step": 522756, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0568132400512695, "global_step": 522757, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0466482639312744, "global_step": 522758, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0581963062286377, "global_step": 522759, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9704322814941406, "global_step": 522760, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.02744460105896, "global_step": 522761, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0678000450134277, "global_step": 522762, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0599451065063477, "global_step": 522763, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0549662113189697, "global_step": 522764, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0868470668792725, "global_step": 522765, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9550179243087769, "global_step": 522766, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0124523639678955, "global_step": 522767, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.004599094390869, "global_step": 522768, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.063082218170166, "global_step": 522769, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0401241779327393, "global_step": 522770, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.004132032394409, "global_step": 522771, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.991418480873108, "global_step": 522772, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.024946928024292, "global_step": 522773, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.021876811981201, "global_step": 522774, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.096388101577759, "global_step": 522775, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0819361209869385, "global_step": 522776, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.039996862411499, "global_step": 522777, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.024949789047241, "global_step": 522778, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.073481798171997, "global_step": 522779, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.061195135116577, "global_step": 522780, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0916478633880615, "global_step": 522781, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0814976692199707, "global_step": 522782, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.046978235244751, "global_step": 522783, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1421940326690674, "global_step": 522784, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.063124179840088, "global_step": 522785, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.062844753265381, "global_step": 522786, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1174705028533936, "global_step": 522787, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.018375873565674, "global_step": 522788, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9406487941741943, "global_step": 522789, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.031264543533325, "global_step": 522790, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.044971466064453, "global_step": 522791, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.071436882019043, "global_step": 522792, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.141063690185547, "global_step": 522793, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0228796005249023, "global_step": 522794, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0818727016448975, "global_step": 522795, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0765678882598877, "global_step": 522796, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.07715106010437, "global_step": 522797, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0447285175323486, "global_step": 522798, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0630664825439453, "global_step": 522799, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0496559143066406, "global_step": 522800, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.029175043106079, "global_step": 522801, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9935848712921143, "global_step": 522802, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9162042140960693, "global_step": 522803, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.058664321899414, "global_step": 522804, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.095594882965088, "global_step": 522805, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0122129917144775, "global_step": 522806, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.108229160308838, "global_step": 522807, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0437822341918945, "global_step": 522808, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0543811321258545, "global_step": 522809, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.01570987701416, "global_step": 522810, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.028034210205078, "global_step": 522811, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0919313430786133, "global_step": 522812, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0044612884521484, "global_step": 522813, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.144674301147461, "global_step": 522814, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.007938861846924, "global_step": 522815, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9424947500228882, "global_step": 522816, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.098532199859619, "global_step": 522817, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0880472660064697, "global_step": 522818, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0331554412841797, "global_step": 522819, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0582168102264404, "global_step": 522820, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.064135789871216, "global_step": 522821, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0277011394500732, "global_step": 522822, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0588650703430176, "global_step": 522823, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9236118793487549, "global_step": 522824, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1161348819732666, "global_step": 522825, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1167221069335938, "global_step": 522826, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9862169027328491, "global_step": 522827, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.060270071029663, "global_step": 522828, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1048378944396973, "global_step": 522829, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9837998151779175, "global_step": 522830, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9705286026000977, "global_step": 522831, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.058727741241455, "global_step": 522832, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.101013660430908, "global_step": 522833, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0214836597442627, "global_step": 522834, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.099677562713623, "global_step": 522835, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9438124895095825, "global_step": 522836, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.966376543045044, "global_step": 522837, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.038538694381714, "global_step": 522838, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0731143951416016, "global_step": 522839, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0676331520080566, "global_step": 522840, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0550742149353027, "global_step": 522841, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9654991626739502, "global_step": 522842, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0024900436401367, "global_step": 522843, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.066220998764038, "global_step": 522844, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.028282880783081, "global_step": 522845, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.023212194442749, "global_step": 522846, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.063563585281372, "global_step": 522847, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9819999933242798, "global_step": 522848, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.010488510131836, "global_step": 522849, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.002657413482666, "global_step": 522850, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.03877329826355, "global_step": 522851, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.96596360206604, "global_step": 522852, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.948653221130371, "global_step": 522853, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9582027196884155, "global_step": 522854, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0973169803619385, "global_step": 522855, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0196828842163086, "global_step": 522856, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1227855682373047, "global_step": 522857, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0224735736846924, "global_step": 522858, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.062732696533203, "global_step": 522859, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0640087127685547, "global_step": 522860, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0131075382232666, "global_step": 522861, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.071253776550293, "global_step": 522862, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.096369504928589, "global_step": 522863, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0248489379882812, "global_step": 522864, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.048874855041504, "global_step": 522865, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9621081352233887, "global_step": 522866, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0455703735351562, "global_step": 522867, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0699710845947266, "global_step": 522868, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.086770534515381, "global_step": 522869, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0185282230377197, "global_step": 522870, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9643356800079346, "global_step": 522871, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9972028732299805, "global_step": 522872, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.028557062149048, "global_step": 522873, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0041165351867676, "global_step": 522874, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9501173496246338, "global_step": 522875, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9984374046325684, "global_step": 522876, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.029634714126587, "global_step": 522877, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9852044582366943, "global_step": 522878, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0185470581054688, "global_step": 522879, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.101041316986084, "global_step": 522880, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9353008270263672, "global_step": 522881, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0648574829101562, "global_step": 522882, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9869807958602905, "global_step": 522883, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.966017723083496, "global_step": 522884, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9571497440338135, "global_step": 522885, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.023723840713501, "global_step": 522886, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.053027391433716, "global_step": 522887, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0264313220977783, "global_step": 522888, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.057385206222534, "global_step": 522889, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0060036182403564, "global_step": 522890, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0814218521118164, "global_step": 522891, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9785860776901245, "global_step": 522892, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.029557704925537, "global_step": 522893, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0450055599212646, "global_step": 522894, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1166141033172607, "global_step": 522895, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9367823600769043, "global_step": 522896, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0014703273773193, "global_step": 522897, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.064223051071167, "global_step": 522898, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9533021450042725, "global_step": 522899, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0454726219177246, "global_step": 522900, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.08597993850708, "global_step": 522901, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0095746517181396, "global_step": 522902, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.95022714138031, "global_step": 522903, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.027549982070923, "global_step": 522904, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0530946254730225, "global_step": 522905, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0093257427215576, "global_step": 522906, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0658342838287354, "global_step": 522907, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.070697784423828, "global_step": 522908, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.068026542663574, "global_step": 522909, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.052062749862671, "global_step": 522910, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1014320850372314, "global_step": 522911, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.095336437225342, "global_step": 522912, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.07896089553833, "global_step": 522913, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0548760890960693, "global_step": 522914, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0705795288085938, "global_step": 522915, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.046207904815674, "global_step": 522916, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0364513397216797, "global_step": 522917, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0623607635498047, "global_step": 522918, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0648159980773926, "global_step": 522919, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9895026683807373, "global_step": 522920, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0352139472961426, "global_step": 522921, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0396568775177, "global_step": 522922, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0850703716278076, "global_step": 522923, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0083236694335938, "global_step": 522924, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.038862466812134, "global_step": 522925, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.979151964187622, "global_step": 522926, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0560240745544434, "global_step": 522927, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0548994541168213, "global_step": 522928, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1187288761138916, "global_step": 522929, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.095708131790161, "global_step": 522930, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.103209972381592, "global_step": 522931, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.001418113708496, "global_step": 522932, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0325324535369873, "global_step": 522933, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0446560382843018, "global_step": 522934, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1016898155212402, "global_step": 522935, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.086265802383423, "global_step": 522936, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.985214114189148, "global_step": 522937, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1153457164764404, "global_step": 522938, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0404534339904785, "global_step": 522939, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.093566417694092, "global_step": 522940, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.000216007232666, "global_step": 522941, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.067054271697998, "global_step": 522942, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0581037998199463, "global_step": 522943, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0858051776885986, "global_step": 522944, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0847480297088623, "global_step": 522945, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.007244825363159, "global_step": 522946, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0348236560821533, "global_step": 522947, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.03517746925354, "global_step": 522948, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.001681089401245, "global_step": 522949, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0150058269500732, "global_step": 522950, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0273869037628174, "global_step": 522951, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.056218147277832, "global_step": 522952, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9997447729110718, "global_step": 522953, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0144646167755127, "global_step": 522954, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.992329716682434, "global_step": 522955, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9401460886001587, "global_step": 522956, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.054058313369751, "global_step": 522957, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.045825242996216, "global_step": 522958, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.050428867340088, "global_step": 522959, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9995365142822266, "global_step": 522960, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0710129737854004, "global_step": 522961, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9987552165985107, "global_step": 522962, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0533554553985596, "global_step": 522963, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.028735637664795, "global_step": 522964, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.043766498565674, "global_step": 522965, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1419732570648193, "global_step": 522966, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0336852073669434, "global_step": 522967, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.071878671646118, "global_step": 522968, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0432190895080566, "global_step": 522969, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9501999616622925, "global_step": 522970, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1037025451660156, "global_step": 522971, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0935065746307373, "global_step": 522972, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0178771018981934, "global_step": 522973, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0131661891937256, "global_step": 522974, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.052081346511841, "global_step": 522975, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9895204305648804, "global_step": 522976, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.036501407623291, "global_step": 522977, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0012214183807373, "global_step": 522978, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1019678115844727, "global_step": 522979, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.028567314147949, "global_step": 522980, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.003070831298828, "global_step": 522981, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0255367755889893, "global_step": 522982, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.97234046459198, "global_step": 522983, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0502147674560547, "global_step": 522984, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.079383611679077, "global_step": 522985, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.98520827293396, "global_step": 522986, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0623340606689453, "global_step": 522987, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0009045600891113, "global_step": 522988, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9503730535507202, "global_step": 522989, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.064924955368042, "global_step": 522990, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.987770438194275, "global_step": 522991, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.092125415802002, "global_step": 522992, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9733235836029053, "global_step": 522993, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.119490385055542, "global_step": 522994, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0824761390686035, "global_step": 522995, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0385990142822266, "global_step": 522996, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1370351314544678, "global_step": 522997, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0682084560394287, "global_step": 522998, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0337445735931396, "global_step": 522999, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0335497856140137, "global_step": 523000, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.011821985244751, "global_step": 523001, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0047388076782227, "global_step": 523002, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9669502973556519, "global_step": 523003, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.999550461769104, "global_step": 523004, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0725393295288086, "global_step": 523005, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0501632690429688, "global_step": 523006, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0811710357666016, "global_step": 523007, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0850484371185303, "global_step": 523008, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1022849082946777, "global_step": 523009, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.026538610458374, "global_step": 523010, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0445563793182373, "global_step": 523011, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9981272220611572, "global_step": 523012, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1595451831817627, "global_step": 523013, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.080821990966797, "global_step": 523014, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.005361795425415, "global_step": 523015, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.156468152999878, "global_step": 523016, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9321579933166504, "global_step": 523017, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0238118171691895, "global_step": 523018, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.027010917663574, "global_step": 523019, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.033143997192383, "global_step": 523020, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.007878541946411, "global_step": 523021, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0104968547821045, "global_step": 523022, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0567893981933594, "global_step": 523023, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1190075874328613, "global_step": 523024, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1678178310394287, "global_step": 523025, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0283219814300537, "global_step": 523026, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.023806095123291, "global_step": 523027, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0513460636138916, "global_step": 523028, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0297935009002686, "global_step": 523029, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.064375638961792, "global_step": 523030, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0503411293029785, "global_step": 523031, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0413906574249268, "global_step": 523032, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.039238214492798, "global_step": 523033, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.024135112762451, "global_step": 523034, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.03543758392334, "global_step": 523035, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0140085220336914, "global_step": 523036, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.078386068344116, "global_step": 523037, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9963477849960327, "global_step": 523038, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.100214958190918, "global_step": 523039, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0580878257751465, "global_step": 523040, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9647797346115112, "global_step": 523041, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9694064855575562, "global_step": 523042, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0929458141326904, "global_step": 523043, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.010768175125122, "global_step": 523044, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0420703887939453, "global_step": 523045, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9494400024414062, "global_step": 523046, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.008099317550659, "global_step": 523047, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.147012948989868, "global_step": 523048, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1118741035461426, "global_step": 523049, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9691299200057983, "global_step": 523050, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0344059467315674, "global_step": 523051, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9598095417022705, "global_step": 523052, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0458383560180664, "global_step": 523053, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.030876874923706, "global_step": 523054, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0370256900787354, "global_step": 523055, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1075937747955322, "global_step": 523056, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1119678020477295, "global_step": 523057, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0130183696746826, "global_step": 523058, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.125514030456543, "global_step": 523059, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.063321828842163, "global_step": 523060, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0401012897491455, "global_step": 523061, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9854334592819214, "global_step": 523062, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.108111619949341, "global_step": 523063, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1457791328430176, "global_step": 523064, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.082582473754883, "global_step": 523065, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.112077236175537, "global_step": 523066, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0155203342437744, "global_step": 523067, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.057828664779663, "global_step": 523068, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0403671264648438, "global_step": 523069, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.01767635345459, "global_step": 523070, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0483105182647705, "global_step": 523071, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.04294753074646, "global_step": 523072, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0028185844421387, "global_step": 523073, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0089404582977295, "global_step": 523074, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.953331470489502, "global_step": 523075, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.094928503036499, "global_step": 523076, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.075601100921631, "global_step": 523077, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.055938720703125, "global_step": 523078, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.02962589263916, "global_step": 523079, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0449001789093018, "global_step": 523080, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0977237224578857, "global_step": 523081, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0760841369628906, "global_step": 523082, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9552804231643677, "global_step": 523083, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9396123886108398, "global_step": 523084, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0589091777801514, "global_step": 523085, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0450613498687744, "global_step": 523086, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.003234624862671, "global_step": 523087, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0411317348480225, "global_step": 523088, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0177221298217773, "global_step": 523089, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0876145362854004, "global_step": 523090, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.023263931274414, "global_step": 523091, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.007242441177368, "global_step": 523092, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0208847522735596, "global_step": 523093, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.020692825317383, "global_step": 523094, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9825689792633057, "global_step": 523095, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0606513023376465, "global_step": 523096, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.091801404953003, "global_step": 523097, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9779120683670044, "global_step": 523098, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0259337425231934, "global_step": 523099, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0523266792297363, "global_step": 523100, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0126430988311768, "global_step": 523101, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0996408462524414, "global_step": 523102, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.005138874053955, "global_step": 523103, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.088160276412964, "global_step": 523104, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1082234382629395, "global_step": 523105, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0293827056884766, "global_step": 523106, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0304040908813477, "global_step": 523107, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9985027313232422, "global_step": 523108, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0939271450042725, "global_step": 523109, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.008188247680664, "global_step": 523110, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.101940155029297, "global_step": 523111, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9975522756576538, "global_step": 523112, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.066720485687256, "global_step": 523113, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0421574115753174, "global_step": 523114, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1616880893707275, "global_step": 523115, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.052356243133545, "global_step": 523116, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9199299812316895, "global_step": 523117, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1338512897491455, "global_step": 523118, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1170308589935303, "global_step": 523119, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.024108648300171, "global_step": 523120, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.009171962738037, "global_step": 523121, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0397257804870605, "global_step": 523122, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.009660482406616, "global_step": 523123, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0231375694274902, "global_step": 523124, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.079763650894165, "global_step": 523125, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.047466278076172, "global_step": 523126, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.038482189178467, "global_step": 523127, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0275092124938965, "global_step": 523128, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.039999485015869, "global_step": 523129, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0938704013824463, "global_step": 523130, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0534965991973877, "global_step": 523131, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.012004852294922, "global_step": 523132, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0055079460144043, "global_step": 523133, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.066617727279663, "global_step": 523134, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.966163158416748, "global_step": 523135, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1292366981506348, "global_step": 523136, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0258185863494873, "global_step": 523137, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.025346279144287, "global_step": 523138, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.098973035812378, "global_step": 523139, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9538155794143677, "global_step": 523140, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1298327445983887, "global_step": 523141, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0297093391418457, "global_step": 523142, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.023442506790161, "global_step": 523143, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9811428785324097, "global_step": 523144, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.995305061340332, "global_step": 523145, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0334208011627197, "global_step": 523146, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.043246269226074, "global_step": 523147, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9832063913345337, "global_step": 523148, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1609091758728027, "global_step": 523149, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.10410737991333, "global_step": 523150, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.007218360900879, "global_step": 523151, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.095151424407959, "global_step": 523152, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0200326442718506, "global_step": 523153, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9658803939819336, "global_step": 523154, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9492685794830322, "global_step": 523155, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0491886138916016, "global_step": 523156, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.031856060028076, "global_step": 523157, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0138392448425293, "global_step": 523158, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.049255847930908, "global_step": 523159, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0140843391418457, "global_step": 523160, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.057257890701294, "global_step": 523161, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0600693225860596, "global_step": 523162, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0754244327545166, "global_step": 523163, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0263614654541016, "global_step": 523164, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.023914098739624, "global_step": 523165, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0621755123138428, "global_step": 523166, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0248007774353027, "global_step": 523167, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9904277324676514, "global_step": 523168, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9836121797561646, "global_step": 523169, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0179085731506348, "global_step": 523170, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.134359359741211, "global_step": 523171, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.055582046508789, "global_step": 523172, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.006786346435547, "global_step": 523173, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0614001750946045, "global_step": 523174, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9950968027114868, "global_step": 523175, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0616376399993896, "global_step": 523176, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0019359588623047, "global_step": 523177, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0433804988861084, "global_step": 523178, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.004978895187378, "global_step": 523179, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9852033853530884, "global_step": 523180, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.085679054260254, "global_step": 523181, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.07865309715271, "global_step": 523182, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1732449531555176, "global_step": 523183, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0904994010925293, "global_step": 523184, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1041924953460693, "global_step": 523185, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.035181760787964, "global_step": 523186, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0008187294006348, "global_step": 523187, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.109395742416382, "global_step": 523188, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0507946014404297, "global_step": 523189, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9982510805130005, "global_step": 523190, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9701807498931885, "global_step": 523191, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0615174770355225, "global_step": 523192, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.004455804824829, "global_step": 523193, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0364413261413574, "global_step": 523194, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0610125064849854, "global_step": 523195, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.017787218093872, "global_step": 523196, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0332820415496826, "global_step": 523197, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0439445972442627, "global_step": 523198, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.035013437271118, "global_step": 523199, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1389026641845703, "global_step": 523200, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.020047903060913, "global_step": 523201, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0278613567352295, "global_step": 523202, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0357789993286133, "global_step": 523203, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9943256378173828, "global_step": 523204, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0558910369873047, "global_step": 523205, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.97968327999115, "global_step": 523206, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9877291917800903, "global_step": 523207, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0674688816070557, "global_step": 523208, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.129488468170166, "global_step": 523209, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.100083351135254, "global_step": 523210, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0777244567871094, "global_step": 523211, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.999363899230957, "global_step": 523212, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.008207082748413, "global_step": 523213, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.084623336791992, "global_step": 523214, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9843310117721558, "global_step": 523215, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.173192262649536, "global_step": 523216, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0420005321502686, "global_step": 523217, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1059842109680176, "global_step": 523218, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9954954385757446, "global_step": 523219, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.009284257888794, "global_step": 523220, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9714351892471313, "global_step": 523221, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.039135694503784, "global_step": 523222, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0127756595611572, "global_step": 523223, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9741249084472656, "global_step": 523224, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1137993335723877, "global_step": 523225, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.013751983642578, "global_step": 523226, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1103296279907227, "global_step": 523227, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.088615655899048, "global_step": 523228, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9807008504867554, "global_step": 523229, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0291264057159424, "global_step": 523230, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0382328033447266, "global_step": 523231, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.052682876586914, "global_step": 523232, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1162984371185303, "global_step": 523233, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9869006872177124, "global_step": 523234, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.065767526626587, "global_step": 523235, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9894359111785889, "global_step": 523236, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.04934024810791, "global_step": 523237, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.067629337310791, "global_step": 523238, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.071901559829712, "global_step": 523239, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0350897312164307, "global_step": 523240, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9825375080108643, "global_step": 523241, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.11230206489563, "global_step": 523242, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0278842449188232, "global_step": 523243, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.050445318222046, "global_step": 523244, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9977790117263794, "global_step": 523245, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0958852767944336, "global_step": 523246, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.016265869140625, "global_step": 523247, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0421347618103027, "global_step": 523248, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.032052755355835, "global_step": 523249, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.078085422515869, "global_step": 523250, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.124403953552246, "global_step": 523251, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1135952472686768, "global_step": 523252, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.97730553150177, "global_step": 523253, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1000070571899414, "global_step": 523254, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0161242485046387, "global_step": 523255, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0166563987731934, "global_step": 523256, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.046572685241699, "global_step": 523257, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0490245819091797, "global_step": 523258, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0225231647491455, "global_step": 523259, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0969700813293457, "global_step": 523260, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.038926124572754, "global_step": 523261, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1060755252838135, "global_step": 523262, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1382315158843994, "global_step": 523263, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1065289974212646, "global_step": 523264, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0940089225769043, "global_step": 523265, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1042866706848145, "global_step": 523266, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.083766460418701, "global_step": 523267, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.10638165473938, "global_step": 523268, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0663552284240723, "global_step": 523269, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.087641477584839, "global_step": 523270, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0547828674316406, "global_step": 523271, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0595500469207764, "global_step": 523272, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.052885055541992, "global_step": 523273, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0330166816711426, "global_step": 523274, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.061441421508789, "global_step": 523275, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0357422828674316, "global_step": 523276, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.081660032272339, "global_step": 523277, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.102632761001587, "global_step": 523278, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.09124755859375, "global_step": 523279, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0642876625061035, "global_step": 523280, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0293097496032715, "global_step": 523281, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0497515201568604, "global_step": 523282, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1142241954803467, "global_step": 523283, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.109612464904785, "global_step": 523284, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.063937187194824, "global_step": 523285, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0595598220825195, "global_step": 523286, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0388383865356445, "global_step": 523287, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0849575996398926, "global_step": 523288, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.128779411315918, "global_step": 523289, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.161914825439453, "global_step": 523290, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0348470211029053, "global_step": 523291, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0984716415405273, "global_step": 523292, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9878888130187988, "global_step": 523293, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0072708129882812, "global_step": 523294, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.105156660079956, "global_step": 523295, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0952255725860596, "global_step": 523296, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0211293697357178, "global_step": 523297, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.040788173675537, "global_step": 523298, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.946309208869934, "global_step": 523299, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1031861305236816, "global_step": 523300, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.047901153564453, "global_step": 523301, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.043839931488037, "global_step": 523302, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.092349052429199, "global_step": 523303, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0485382080078125, "global_step": 523304, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.091015577316284, "global_step": 523305, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0808422565460205, "global_step": 523306, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0400984287261963, "global_step": 523307, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.041947364807129, "global_step": 523308, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.013113021850586, "global_step": 523309, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0245144367218018, "global_step": 523310, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9727569818496704, "global_step": 523311, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.106421709060669, "global_step": 523312, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.054877519607544, "global_step": 523313, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0500376224517822, "global_step": 523314, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9559273719787598, "global_step": 523315, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0260684490203857, "global_step": 523316, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.019859790802002, "global_step": 523317, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0466830730438232, "global_step": 523318, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0464887619018555, "global_step": 523319, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.092442274093628, "global_step": 523320, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0240044593811035, "global_step": 523321, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.090618848800659, "global_step": 523322, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0910470485687256, "global_step": 523323, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.046937942504883, "global_step": 523324, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.040717363357544, "global_step": 523325, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.993374228477478, "global_step": 523326, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.080139398574829, "global_step": 523327, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1045007705688477, "global_step": 523328, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1185641288757324, "global_step": 523329, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0500998497009277, "global_step": 523330, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0821533203125, "global_step": 523331, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9975568056106567, "global_step": 523332, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0662317276000977, "global_step": 523333, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0339972972869873, "global_step": 523334, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1096534729003906, "global_step": 523335, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0269901752471924, "global_step": 523336, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0794217586517334, "global_step": 523337, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.021432399749756, "global_step": 523338, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.106297016143799, "global_step": 523339, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.038567066192627, "global_step": 523340, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.002412796020508, "global_step": 523341, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.024425745010376, "global_step": 523342, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.091069459915161, "global_step": 523343, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0426323413848877, "global_step": 523344, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0687620639801025, "global_step": 523345, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0478076934814453, "global_step": 523346, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.096783399581909, "global_step": 523347, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0887598991394043, "global_step": 523348, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0444869995117188, "global_step": 523349, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.007056713104248, "global_step": 523350, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1099720001220703, "global_step": 523351, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9671121835708618, "global_step": 523352, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.111928939819336, "global_step": 523353, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.086376190185547, "global_step": 523354, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0922162532806396, "global_step": 523355, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0387606620788574, "global_step": 523356, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.055331230163574, "global_step": 523357, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1050212383270264, "global_step": 523358, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0719380378723145, "global_step": 523359, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0201256275177, "global_step": 523360, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.058541774749756, "global_step": 523361, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.102444648742676, "global_step": 523362, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0151138305664062, "global_step": 523363, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1022655963897705, "global_step": 523364, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0470197200775146, "global_step": 523365, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9932641983032227, "global_step": 523366, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9991282224655151, "global_step": 523367, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9902807474136353, "global_step": 523368, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0414955615997314, "global_step": 523369, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1086275577545166, "global_step": 523370, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9723834991455078, "global_step": 523371, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9917653799057007, "global_step": 523372, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0512523651123047, "global_step": 523373, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.026437997817993, "global_step": 523374, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0439555644989014, "global_step": 523375, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.008025646209717, "global_step": 523376, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.999894380569458, "global_step": 523377, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.076381206512451, "global_step": 523378, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.062570571899414, "global_step": 523379, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.159350633621216, "global_step": 523380, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.036292314529419, "global_step": 523381, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0279054641723633, "global_step": 523382, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0599868297576904, "global_step": 523383, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.9474283456802368, "global_step": 523384, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0977914333343506, "global_step": 523385, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0879480838775635, "global_step": 523386, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0458879470825195, "global_step": 523387, "epoch": 889, "lr": 5e-05}
{"train_loss": 1.957026481628418, "global_step": 523388, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.116417407989502, "global_step": 523389, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0595767498016357, "global_step": 523390, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.0401298999786377, "global_step": 523391, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.041712999343872, "global_step": 523392, "epoch": 889, "lr": 5e-05}
{"train_loss": 2.1300103664398193, "global_step": 523393, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0990912914276123, "global_step": 523394, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0518758296966553, "global_step": 523395, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0737862586975098, "global_step": 523396, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0100224018096924, "global_step": 523397, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0252609252929688, "global_step": 523398, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0526561737060547, "global_step": 523399, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.019861936569214, "global_step": 523400, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1131908893585205, "global_step": 523401, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.080528497695923, "global_step": 523402, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0992727279663086, "global_step": 523403, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9676823616027832, "global_step": 523404, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.119976282119751, "global_step": 523405, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0993149280548096, "global_step": 523406, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0671944618225098, "global_step": 523407, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.00719952583313, "global_step": 523408, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9857096672058105, "global_step": 523409, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0660171508789062, "global_step": 523410, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0366909503936768, "global_step": 523411, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9955552816390991, "global_step": 523412, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9987671375274658, "global_step": 523413, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1056032180786133, "global_step": 523414, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0316147804260254, "global_step": 523415, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0356757640838623, "global_step": 523416, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0672545433044434, "global_step": 523417, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.05362606048584, "global_step": 523418, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.8972194194793701, "global_step": 523419, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.013404369354248, "global_step": 523420, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0130057334899902, "global_step": 523421, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0893523693084717, "global_step": 523422, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0663278102874756, "global_step": 523423, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.000023603439331, "global_step": 523424, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.039602756500244, "global_step": 523425, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.051185131072998, "global_step": 523426, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0579848289489746, "global_step": 523427, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.01039719581604, "global_step": 523428, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9938876628875732, "global_step": 523429, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0568134784698486, "global_step": 523430, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9999536275863647, "global_step": 523431, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.100374698638916, "global_step": 523432, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0666584968566895, "global_step": 523433, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9638090133666992, "global_step": 523434, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0768167972564697, "global_step": 523435, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0501058101654053, "global_step": 523436, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.036836862564087, "global_step": 523437, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9858272075653076, "global_step": 523438, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9987033605575562, "global_step": 523439, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0759291648864746, "global_step": 523440, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0652616024017334, "global_step": 523441, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0497281551361084, "global_step": 523442, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0586767196655273, "global_step": 523443, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.055216073989868, "global_step": 523444, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0229780673980713, "global_step": 523445, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0613224506378174, "global_step": 523446, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9996031522750854, "global_step": 523447, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9475945234298706, "global_step": 523448, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0977277755737305, "global_step": 523449, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.059814929962158, "global_step": 523450, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9845335483551025, "global_step": 523451, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.115241289138794, "global_step": 523452, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9723130464553833, "global_step": 523453, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0423672199249268, "global_step": 523454, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1075291633605957, "global_step": 523455, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9549775123596191, "global_step": 523456, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.029571533203125, "global_step": 523457, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9820235967636108, "global_step": 523458, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0244593620300293, "global_step": 523459, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9718563556671143, "global_step": 523460, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0597941875457764, "global_step": 523461, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.027644157409668, "global_step": 523462, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.073270082473755, "global_step": 523463, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.021815538406372, "global_step": 523464, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0406177043914795, "global_step": 523465, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.067258834838867, "global_step": 523466, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.006831407546997, "global_step": 523467, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9279648065567017, "global_step": 523468, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0074656009674072, "global_step": 523469, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.979814052581787, "global_step": 523470, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.053907632827759, "global_step": 523471, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0563066005706787, "global_step": 523472, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.988730549812317, "global_step": 523473, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.090961456298828, "global_step": 523474, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.058072090148926, "global_step": 523475, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9290101528167725, "global_step": 523476, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.93861985206604, "global_step": 523477, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0431323051452637, "global_step": 523478, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0054824352264404, "global_step": 523479, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0607476234436035, "global_step": 523480, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0472776889801025, "global_step": 523481, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.070838212966919, "global_step": 523482, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.083812952041626, "global_step": 523483, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.027245044708252, "global_step": 523484, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0759754180908203, "global_step": 523485, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.8992071151733398, "global_step": 523486, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0483956336975098, "global_step": 523487, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9911316633224487, "global_step": 523488, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1019325256347656, "global_step": 523489, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0678203105926514, "global_step": 523490, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.989884376525879, "global_step": 523491, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9927997589111328, "global_step": 523492, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.091005325317383, "global_step": 523493, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9870479106903076, "global_step": 523494, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.977670431137085, "global_step": 523495, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0385665893554688, "global_step": 523496, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.04872465133667, "global_step": 523497, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0205960273742676, "global_step": 523498, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9579488039016724, "global_step": 523499, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9768743515014648, "global_step": 523500, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0182628631591797, "global_step": 523501, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0526561737060547, "global_step": 523502, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0922162532806396, "global_step": 523503, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.077862024307251, "global_step": 523504, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0003044605255127, "global_step": 523505, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9967139959335327, "global_step": 523506, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.007664203643799, "global_step": 523507, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.032860279083252, "global_step": 523508, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9599250555038452, "global_step": 523509, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.024512529373169, "global_step": 523510, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9818183183670044, "global_step": 523511, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.065962791442871, "global_step": 523512, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.139169454574585, "global_step": 523513, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9885419607162476, "global_step": 523514, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.128612756729126, "global_step": 523515, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0159711837768555, "global_step": 523516, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0007035732269287, "global_step": 523517, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0660672187805176, "global_step": 523518, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1553659439086914, "global_step": 523519, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.02508544921875, "global_step": 523520, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0965070724487305, "global_step": 523521, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9893460273742676, "global_step": 523522, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.046567916870117, "global_step": 523523, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.005617141723633, "global_step": 523524, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9639328718185425, "global_step": 523525, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0157251358032227, "global_step": 523526, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.015315294265747, "global_step": 523527, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9533882141113281, "global_step": 523528, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.105807065963745, "global_step": 523529, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0573370456695557, "global_step": 523530, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0460562705993652, "global_step": 523531, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.093356132507324, "global_step": 523532, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1138458251953125, "global_step": 523533, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.040860176086426, "global_step": 523534, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9872554540634155, "global_step": 523535, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0910775661468506, "global_step": 523536, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.054338216781616, "global_step": 523537, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.011720895767212, "global_step": 523538, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.879054069519043, "global_step": 523539, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9250013828277588, "global_step": 523540, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9613075256347656, "global_step": 523541, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.024247169494629, "global_step": 523542, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.090306282043457, "global_step": 523543, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.107729196548462, "global_step": 523544, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.019557237625122, "global_step": 523545, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9884008169174194, "global_step": 523546, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0638465881347656, "global_step": 523547, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9787342548370361, "global_step": 523548, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0547053813934326, "global_step": 523549, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.081310510635376, "global_step": 523550, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.039889335632324, "global_step": 523551, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0397655963897705, "global_step": 523552, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0459837913513184, "global_step": 523553, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0585238933563232, "global_step": 523554, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.121598243713379, "global_step": 523555, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.01598858833313, "global_step": 523556, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.991317868232727, "global_step": 523557, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0828399658203125, "global_step": 523558, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.113737106323242, "global_step": 523559, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0962448120117188, "global_step": 523560, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.027994394302368, "global_step": 523561, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.050408363342285, "global_step": 523562, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1092147827148438, "global_step": 523563, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.043901205062866, "global_step": 523564, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.162231206893921, "global_step": 523565, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1158740520477295, "global_step": 523566, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0166032314300537, "global_step": 523567, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0622313022613525, "global_step": 523568, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9721014499664307, "global_step": 523569, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0269622802734375, "global_step": 523570, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0248899459838867, "global_step": 523571, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1307411193847656, "global_step": 523572, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9572919607162476, "global_step": 523573, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0084102153778076, "global_step": 523574, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9960131645202637, "global_step": 523575, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0751779079437256, "global_step": 523576, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.006964683532715, "global_step": 523577, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.014202833175659, "global_step": 523578, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.967410683631897, "global_step": 523579, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.993672251701355, "global_step": 523580, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.011012077331543, "global_step": 523581, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0427191257476807, "global_step": 523582, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.012331247329712, "global_step": 523583, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.994044542312622, "global_step": 523584, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0592949390411377, "global_step": 523585, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9812891483306885, "global_step": 523586, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.013117790222168, "global_step": 523587, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.130234479904175, "global_step": 523588, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0989084243774414, "global_step": 523589, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0501210689544678, "global_step": 523590, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9955660104751587, "global_step": 523591, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0199904441833496, "global_step": 523592, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.001068353652954, "global_step": 523593, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.079892158508301, "global_step": 523594, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.974715232849121, "global_step": 523595, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.054265022277832, "global_step": 523596, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0885250568389893, "global_step": 523597, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0253264904022217, "global_step": 523598, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.94452965259552, "global_step": 523599, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.07977294921875, "global_step": 523600, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9557856321334839, "global_step": 523601, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.053521156311035, "global_step": 523602, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.023214340209961, "global_step": 523603, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0981483459472656, "global_step": 523604, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9923464059829712, "global_step": 523605, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0089478492736816, "global_step": 523606, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0599358081817627, "global_step": 523607, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.041718006134033, "global_step": 523608, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0111300945281982, "global_step": 523609, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.043059825897217, "global_step": 523610, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.066983699798584, "global_step": 523611, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0346503257751465, "global_step": 523612, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9501678943634033, "global_step": 523613, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0562539100646973, "global_step": 523614, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.030891180038452, "global_step": 523615, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0041184425354004, "global_step": 523616, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.011943817138672, "global_step": 523617, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0361666679382324, "global_step": 523618, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.04542875289917, "global_step": 523619, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0376665592193604, "global_step": 523620, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0715298652648926, "global_step": 523621, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0004868507385254, "global_step": 523622, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.061457872390747, "global_step": 523623, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0241754055023193, "global_step": 523624, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.073277235031128, "global_step": 523625, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0605850219726562, "global_step": 523626, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9226819276809692, "global_step": 523627, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.089555501937866, "global_step": 523628, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9814956188201904, "global_step": 523629, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0624659061431885, "global_step": 523630, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0000460147857666, "global_step": 523631, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.015328884124756, "global_step": 523632, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.989711880683899, "global_step": 523633, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0117673873901367, "global_step": 523634, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0492970943450928, "global_step": 523635, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0309267044067383, "global_step": 523636, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9931955337524414, "global_step": 523637, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.037320852279663, "global_step": 523638, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0128653049468994, "global_step": 523639, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.064614772796631, "global_step": 523640, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9739644527435303, "global_step": 523641, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0770695209503174, "global_step": 523642, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0720510482788086, "global_step": 523643, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0047621726989746, "global_step": 523644, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0871334075927734, "global_step": 523645, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.98988938331604, "global_step": 523646, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.046269655227661, "global_step": 523647, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0428082942962646, "global_step": 523648, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0873074531555176, "global_step": 523649, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1531076431274414, "global_step": 523650, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9793205261230469, "global_step": 523651, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.066638946533203, "global_step": 523652, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0104031562805176, "global_step": 523653, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9422688484191895, "global_step": 523654, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0322306156158447, "global_step": 523655, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0844435691833496, "global_step": 523656, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0459442138671875, "global_step": 523657, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0492074489593506, "global_step": 523658, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.052114725112915, "global_step": 523659, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0760788917541504, "global_step": 523660, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.020596504211426, "global_step": 523661, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0817530155181885, "global_step": 523662, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.116878032684326, "global_step": 523663, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.131503105163574, "global_step": 523664, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.078679323196411, "global_step": 523665, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9932074546813965, "global_step": 523666, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.046400785446167, "global_step": 523667, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0369060039520264, "global_step": 523668, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.978200912475586, "global_step": 523669, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0309271812438965, "global_step": 523670, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.058515787124634, "global_step": 523671, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0367496013641357, "global_step": 523672, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.082207202911377, "global_step": 523673, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0581629276275635, "global_step": 523674, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0172247886657715, "global_step": 523675, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0494863986968994, "global_step": 523676, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9949241876602173, "global_step": 523677, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.062615156173706, "global_step": 523678, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0249242782592773, "global_step": 523679, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0515353679656982, "global_step": 523680, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.025838851928711, "global_step": 523681, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0199198722839355, "global_step": 523682, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1754844188690186, "global_step": 523683, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.062875747680664, "global_step": 523684, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.130568742752075, "global_step": 523685, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.054532527923584, "global_step": 523686, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0120034217834473, "global_step": 523687, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.00504994392395, "global_step": 523688, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0181002616882324, "global_step": 523689, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.005354166030884, "global_step": 523690, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.054408073425293, "global_step": 523691, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0229897499084473, "global_step": 523692, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0558228492736816, "global_step": 523693, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.132456064224243, "global_step": 523694, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0669944286346436, "global_step": 523695, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.06770658493042, "global_step": 523696, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.042775869369507, "global_step": 523697, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.049943685531616, "global_step": 523698, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0115034580230713, "global_step": 523699, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9786254167556763, "global_step": 523700, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0097718238830566, "global_step": 523701, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0318455696105957, "global_step": 523702, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0460617542266846, "global_step": 523703, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.008080244064331, "global_step": 523704, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9973081350326538, "global_step": 523705, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0570759773254395, "global_step": 523706, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0172924995422363, "global_step": 523707, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.07533597946167, "global_step": 523708, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0544240474700928, "global_step": 523709, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9915478229522705, "global_step": 523710, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.074350118637085, "global_step": 523711, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.038693428039551, "global_step": 523712, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0385122299194336, "global_step": 523713, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.956504464149475, "global_step": 523714, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1347529888153076, "global_step": 523715, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.061004400253296, "global_step": 523716, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0535266399383545, "global_step": 523717, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.055067777633667, "global_step": 523718, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0457727909088135, "global_step": 523719, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.060835361480713, "global_step": 523720, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1128756999969482, "global_step": 523721, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0236868858337402, "global_step": 523722, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0387067794799805, "global_step": 523723, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.04545259475708, "global_step": 523724, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.095470905303955, "global_step": 523725, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0827410221099854, "global_step": 523726, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.052204132080078, "global_step": 523727, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.030092239379883, "global_step": 523728, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9640893936157227, "global_step": 523729, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0013644695281982, "global_step": 523730, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0382702350616455, "global_step": 523731, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9318978786468506, "global_step": 523732, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.047255039215088, "global_step": 523733, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.028982400894165, "global_step": 523734, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9646718502044678, "global_step": 523735, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9585715532302856, "global_step": 523736, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0588860511779785, "global_step": 523737, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0952234268188477, "global_step": 523738, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0030579566955566, "global_step": 523739, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9832743406295776, "global_step": 523740, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0662710666656494, "global_step": 523741, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0177645683288574, "global_step": 523742, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.976697325706482, "global_step": 523743, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.083782911300659, "global_step": 523744, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.081589937210083, "global_step": 523745, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0212721824645996, "global_step": 523746, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0915310382843018, "global_step": 523747, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.022585391998291, "global_step": 523748, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9933948516845703, "global_step": 523749, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9949946403503418, "global_step": 523750, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.082516670227051, "global_step": 523751, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9483102560043335, "global_step": 523752, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0686941146850586, "global_step": 523753, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0746958255767822, "global_step": 523754, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.100032329559326, "global_step": 523755, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9773821830749512, "global_step": 523756, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0299787521362305, "global_step": 523757, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0046958923339844, "global_step": 523758, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0990912914276123, "global_step": 523759, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.019537925720215, "global_step": 523760, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.016547203063965, "global_step": 523761, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.994943618774414, "global_step": 523762, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0772221088409424, "global_step": 523763, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0833218097686768, "global_step": 523764, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.973286509513855, "global_step": 523765, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.123173713684082, "global_step": 523766, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1142704486846924, "global_step": 523767, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0266568660736084, "global_step": 523768, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0916645526885986, "global_step": 523769, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0304572582244873, "global_step": 523770, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9929449558258057, "global_step": 523771, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9884065389633179, "global_step": 523772, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0741946697235107, "global_step": 523773, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0210323333740234, "global_step": 523774, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0115442276000977, "global_step": 523775, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9992271661758423, "global_step": 523776, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9929015636444092, "global_step": 523777, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9939454793930054, "global_step": 523778, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0496253967285156, "global_step": 523779, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.024517774581909, "global_step": 523780, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9975554943084717, "global_step": 523781, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0852622985839844, "global_step": 523782, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.950087308883667, "global_step": 523783, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.062613010406494, "global_step": 523784, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0238804817199707, "global_step": 523785, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0386600494384766, "global_step": 523786, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9691998958587646, "global_step": 523787, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0080442428588867, "global_step": 523788, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.064929723739624, "global_step": 523789, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.040529727935791, "global_step": 523790, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.065762758255005, "global_step": 523791, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.981615424156189, "global_step": 523792, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0534660816192627, "global_step": 523793, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0514352321624756, "global_step": 523794, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0313053131103516, "global_step": 523795, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1297178268432617, "global_step": 523796, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.05452299118042, "global_step": 523797, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9741050004959106, "global_step": 523798, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0652589797973633, "global_step": 523799, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9764893054962158, "global_step": 523800, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0849320888519287, "global_step": 523801, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0460073947906494, "global_step": 523802, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.079233169555664, "global_step": 523803, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0721912384033203, "global_step": 523804, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.037071704864502, "global_step": 523805, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0394787788391113, "global_step": 523806, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9823096990585327, "global_step": 523807, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1168243885040283, "global_step": 523808, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.066556215286255, "global_step": 523809, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.054401397705078, "global_step": 523810, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0680313110351562, "global_step": 523811, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0751020908355713, "global_step": 523812, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.13193941116333, "global_step": 523813, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0904572010040283, "global_step": 523814, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0508298873901367, "global_step": 523815, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0338940620422363, "global_step": 523816, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0519943237304688, "global_step": 523817, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9449920654296875, "global_step": 523818, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9942349195480347, "global_step": 523819, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0279321670532227, "global_step": 523820, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.048008918762207, "global_step": 523821, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0531768798828125, "global_step": 523822, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.021730899810791, "global_step": 523823, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.98728346824646, "global_step": 523824, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0338807106018066, "global_step": 523825, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.091733694076538, "global_step": 523826, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.059649705886841, "global_step": 523827, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0471880435943604, "global_step": 523828, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1031413078308105, "global_step": 523829, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.108774185180664, "global_step": 523830, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0503292083740234, "global_step": 523831, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0814273357391357, "global_step": 523832, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0182886123657227, "global_step": 523833, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0304768085479736, "global_step": 523834, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9963685274124146, "global_step": 523835, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0510013103485107, "global_step": 523836, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.073096513748169, "global_step": 523837, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0731680393218994, "global_step": 523838, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9568467140197754, "global_step": 523839, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.114635467529297, "global_step": 523840, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0052313804626465, "global_step": 523841, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9559664726257324, "global_step": 523842, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1614842414855957, "global_step": 523843, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0723326206207275, "global_step": 523844, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.028083086013794, "global_step": 523845, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0351595878601074, "global_step": 523846, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.082622766494751, "global_step": 523847, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9760801792144775, "global_step": 523848, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0732581615448, "global_step": 523849, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.049459934234619, "global_step": 523850, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.991792917251587, "global_step": 523851, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.988273024559021, "global_step": 523852, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.025177240371704, "global_step": 523853, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.106854200363159, "global_step": 523854, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1332991123199463, "global_step": 523855, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0723674297332764, "global_step": 523856, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0390024185180664, "global_step": 523857, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9754688739776611, "global_step": 523858, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0987894535064697, "global_step": 523859, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0636374950408936, "global_step": 523860, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9866224527359009, "global_step": 523861, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0670523643493652, "global_step": 523862, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.020515203475952, "global_step": 523863, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.020678997039795, "global_step": 523864, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0889132022857666, "global_step": 523865, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.027407646179199, "global_step": 523866, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.001919984817505, "global_step": 523867, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0418100357055664, "global_step": 523868, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1062614917755127, "global_step": 523869, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.097679615020752, "global_step": 523870, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.938478946685791, "global_step": 523871, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.117527484893799, "global_step": 523872, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0268845558166504, "global_step": 523873, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0857369899749756, "global_step": 523874, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.051276922225952, "global_step": 523875, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9955049753189087, "global_step": 523876, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.985763430595398, "global_step": 523877, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9493588209152222, "global_step": 523878, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.045133590698242, "global_step": 523879, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0664162635803223, "global_step": 523880, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.982272744178772, "global_step": 523881, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0030367374420166, "global_step": 523882, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0031988620758057, "global_step": 523883, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0371265411376953, "global_step": 523884, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.035228967666626, "global_step": 523885, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0300517082214355, "global_step": 523886, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9821492433547974, "global_step": 523887, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1364004611968994, "global_step": 523888, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.072775363922119, "global_step": 523889, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9785740375518799, "global_step": 523890, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0701541900634766, "global_step": 523891, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0857396125793457, "global_step": 523892, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.093040704727173, "global_step": 523893, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.072725534439087, "global_step": 523894, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9711910486221313, "global_step": 523895, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.081357955932617, "global_step": 523896, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0703845024108887, "global_step": 523897, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.029533863067627, "global_step": 523898, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.983254313468933, "global_step": 523899, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.023607015609741, "global_step": 523900, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0650129318237305, "global_step": 523901, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0337343215942383, "global_step": 523902, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0292160511016846, "global_step": 523903, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.08127760887146, "global_step": 523904, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0350613594055176, "global_step": 523905, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.000213384628296, "global_step": 523906, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0615427494049072, "global_step": 523907, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0022971630096436, "global_step": 523908, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.001818895339966, "global_step": 523909, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1116576194763184, "global_step": 523910, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.046940803527832, "global_step": 523911, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.050964593887329, "global_step": 523912, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9880834817886353, "global_step": 523913, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.056643486022949, "global_step": 523914, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.026961088180542, "global_step": 523915, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0161516666412354, "global_step": 523916, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1174981594085693, "global_step": 523917, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.033212184906006, "global_step": 523918, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0483055114746094, "global_step": 523919, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.017160654067993, "global_step": 523920, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.007791042327881, "global_step": 523921, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0882375240325928, "global_step": 523922, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0294406414031982, "global_step": 523923, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0637433528900146, "global_step": 523924, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1402928829193115, "global_step": 523925, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0175352096557617, "global_step": 523926, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0693862438201904, "global_step": 523927, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9919160604476929, "global_step": 523928, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.065915584564209, "global_step": 523929, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0789694786071777, "global_step": 523930, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1430742740631104, "global_step": 523931, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0700719356536865, "global_step": 523932, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9854551553726196, "global_step": 523933, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.071584701538086, "global_step": 523934, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.109165906906128, "global_step": 523935, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0549867153167725, "global_step": 523936, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.027996778488159, "global_step": 523937, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0493323802948, "global_step": 523938, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0258877277374268, "global_step": 523939, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0960586071014404, "global_step": 523940, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.063825845718384, "global_step": 523941, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.986036777496338, "global_step": 523942, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.09599232673645, "global_step": 523943, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1086511611938477, "global_step": 523944, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0576937198638916, "global_step": 523945, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0262584686279297, "global_step": 523946, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9822382926940918, "global_step": 523947, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.099632501602173, "global_step": 523948, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.006368398666382, "global_step": 523949, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9796257019042969, "global_step": 523950, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.107078790664673, "global_step": 523951, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9969024658203125, "global_step": 523952, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1760878562927246, "global_step": 523953, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1188464164733887, "global_step": 523954, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0817079544067383, "global_step": 523955, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0799827575683594, "global_step": 523956, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9953458309173584, "global_step": 523957, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.017199754714966, "global_step": 523958, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0824291706085205, "global_step": 523959, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1248791217803955, "global_step": 523960, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0057239532470703, "global_step": 523961, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.051941394805908, "global_step": 523962, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0984432697296143, "global_step": 523963, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0601093769073486, "global_step": 523964, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.998348355293274, "global_step": 523965, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.052199125289917, "global_step": 523966, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.064181327819824, "global_step": 523967, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0378172397613525, "global_step": 523968, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.035675525665283, "global_step": 523969, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0556294918060303, "global_step": 523970, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0717663764953613, "global_step": 523971, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0485944747924805, "global_step": 523972, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0889275074005127, "global_step": 523973, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.995055913925171, "global_step": 523974, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0250158309936523, "global_step": 523975, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.044503688812256, "global_step": 523976, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.039684534072876, "global_step": 523977, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0396435260772705, "global_step": 523978, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.124969959259033, "global_step": 523979, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.999160647392273, "global_step": 523980, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.013322591781616, "global_step": 523981, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.943033218383789, "global_step": 523982, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.030435800552368, "global_step": 523983, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0609633922576904, "global_step": 523984, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0762710571289062, "global_step": 523985, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.076565980911255, "global_step": 523986, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1194422245025635, "global_step": 523987, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.038076639175415, "global_step": 523988, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.095587730407715, "global_step": 523989, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.027061700820923, "global_step": 523990, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0085649490356445, "global_step": 523991, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1786272525787354, "global_step": 523992, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.915049433708191, "global_step": 523993, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.981117606163025, "global_step": 523994, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.961652159690857, "global_step": 523995, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.04823637008667, "global_step": 523996, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0954978466033936, "global_step": 523997, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9666733741760254, "global_step": 523998, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.014613628387451, "global_step": 523999, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.055880546569824, "global_step": 524000, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0496039390563965, "global_step": 524001, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.068796396255493, "global_step": 524002, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.061087131500244, "global_step": 524003, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1336746215820312, "global_step": 524004, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.090730905532837, "global_step": 524005, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.005695104598999, "global_step": 524006, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0043740272521973, "global_step": 524007, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0842504501342773, "global_step": 524008, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0073111057281494, "global_step": 524009, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1157922744750977, "global_step": 524010, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0837199687957764, "global_step": 524011, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0634102821350098, "global_step": 524012, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.080679416656494, "global_step": 524013, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9957666397094727, "global_step": 524014, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9781391620635986, "global_step": 524015, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.046765089035034, "global_step": 524016, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0135748386383057, "global_step": 524017, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1086668968200684, "global_step": 524018, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.083622694015503, "global_step": 524019, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.096628189086914, "global_step": 524020, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0651230812072754, "global_step": 524021, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0673601627349854, "global_step": 524022, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.972929835319519, "global_step": 524023, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.007840871810913, "global_step": 524024, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.992081880569458, "global_step": 524025, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0265653133392334, "global_step": 524026, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0335781574249268, "global_step": 524027, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.115126371383667, "global_step": 524028, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0095624923706055, "global_step": 524029, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0083296298980713, "global_step": 524030, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0792558193206787, "global_step": 524031, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0411200523376465, "global_step": 524032, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0288305282592773, "global_step": 524033, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0165579319000244, "global_step": 524034, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0546483993530273, "global_step": 524035, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.092407703399658, "global_step": 524036, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9967237710952759, "global_step": 524037, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0216009616851807, "global_step": 524038, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.071854591369629, "global_step": 524039, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0371367931365967, "global_step": 524040, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0176403522491455, "global_step": 524041, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0038182735443115, "global_step": 524042, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.14176082611084, "global_step": 524043, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0983829498291016, "global_step": 524044, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0499610900878906, "global_step": 524045, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0947885513305664, "global_step": 524046, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9270069599151611, "global_step": 524047, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0382046699523926, "global_step": 524048, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0935888290405273, "global_step": 524049, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.014878511428833, "global_step": 524050, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0663540363311768, "global_step": 524051, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.030336380004883, "global_step": 524052, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.076751232147217, "global_step": 524053, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.065265655517578, "global_step": 524054, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9617897272109985, "global_step": 524055, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0433387756347656, "global_step": 524056, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.017059087753296, "global_step": 524057, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1328048706054688, "global_step": 524058, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0167815685272217, "global_step": 524059, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.028651237487793, "global_step": 524060, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.006448984146118, "global_step": 524061, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.003333568572998, "global_step": 524062, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.983571171760559, "global_step": 524063, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9784979820251465, "global_step": 524064, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0667290687561035, "global_step": 524065, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.019789695739746, "global_step": 524066, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.017136812210083, "global_step": 524067, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9785325527191162, "global_step": 524068, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0735702514648438, "global_step": 524069, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0713229179382324, "global_step": 524070, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9843645095825195, "global_step": 524071, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0122036933898926, "global_step": 524072, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.957534909248352, "global_step": 524073, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.026433229446411, "global_step": 524074, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0932419300079346, "global_step": 524075, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.043811082839966, "global_step": 524076, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.108725070953369, "global_step": 524077, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.179687261581421, "global_step": 524078, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0335872173309326, "global_step": 524079, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.028207778930664, "global_step": 524080, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.043276309967041, "global_step": 524081, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.003007173538208, "global_step": 524082, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.114309549331665, "global_step": 524083, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0574352741241455, "global_step": 524084, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.05041766166687, "global_step": 524085, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0500128269195557, "global_step": 524086, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0636730194091797, "global_step": 524087, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0285019874572754, "global_step": 524088, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0173964500427246, "global_step": 524089, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0767085552215576, "global_step": 524090, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0343849658966064, "global_step": 524091, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.086164712905884, "global_step": 524092, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0885725021362305, "global_step": 524093, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0525596141815186, "global_step": 524094, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0670502185821533, "global_step": 524095, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.050750494003296, "global_step": 524096, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0466060638427734, "global_step": 524097, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0573570728302, "global_step": 524098, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0787060260772705, "global_step": 524099, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0678138732910156, "global_step": 524100, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0519518852233887, "global_step": 524101, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0114004611968994, "global_step": 524102, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.014681100845337, "global_step": 524103, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0653514862060547, "global_step": 524104, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0484261512756348, "global_step": 524105, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0362353324890137, "global_step": 524106, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.080888271331787, "global_step": 524107, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.006293535232544, "global_step": 524108, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0925564765930176, "global_step": 524109, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.095466375350952, "global_step": 524110, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.016319990158081, "global_step": 524111, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.083940029144287, "global_step": 524112, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9774959087371826, "global_step": 524113, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9917265176773071, "global_step": 524114, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0571329593658447, "global_step": 524115, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.133263349533081, "global_step": 524116, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0209972858428955, "global_step": 524117, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0347800254821777, "global_step": 524118, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9603289365768433, "global_step": 524119, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0566253662109375, "global_step": 524120, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0390560626983643, "global_step": 524121, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.089635133743286, "global_step": 524122, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0877907276153564, "global_step": 524123, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9353214502334595, "global_step": 524124, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.065732002258301, "global_step": 524125, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.020385980606079, "global_step": 524126, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0743443965911865, "global_step": 524127, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0663888454437256, "global_step": 524128, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0431571006774902, "global_step": 524129, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0676193237304688, "global_step": 524130, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9405057430267334, "global_step": 524131, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9595290422439575, "global_step": 524132, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1238725185394287, "global_step": 524133, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.973355770111084, "global_step": 524134, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0684940814971924, "global_step": 524135, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0789077281951904, "global_step": 524136, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0693745613098145, "global_step": 524137, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.086277484893799, "global_step": 524138, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9963129758834839, "global_step": 524139, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0855538845062256, "global_step": 524140, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.020665407180786, "global_step": 524141, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9732203483581543, "global_step": 524142, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1335558891296387, "global_step": 524143, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0583388805389404, "global_step": 524144, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1065070629119873, "global_step": 524145, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9997003078460693, "global_step": 524146, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.03181791305542, "global_step": 524147, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0158815383911133, "global_step": 524148, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.116753101348877, "global_step": 524149, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1004791259765625, "global_step": 524150, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0047783851623535, "global_step": 524151, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0266501903533936, "global_step": 524152, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0308029651641846, "global_step": 524153, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.01027774810791, "global_step": 524154, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.033824920654297, "global_step": 524155, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.031853437423706, "global_step": 524156, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.126652240753174, "global_step": 524157, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.106703281402588, "global_step": 524158, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0797693729400635, "global_step": 524159, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0602173805236816, "global_step": 524160, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.09002685546875, "global_step": 524161, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9540274143218994, "global_step": 524162, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.112190008163452, "global_step": 524163, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0176262855529785, "global_step": 524164, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.03271746635437, "global_step": 524165, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0176265239715576, "global_step": 524166, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0350046157836914, "global_step": 524167, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.017585515975952, "global_step": 524168, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0904600620269775, "global_step": 524169, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.072719097137451, "global_step": 524170, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0944066047668457, "global_step": 524171, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.022207498550415, "global_step": 524172, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.043116331100464, "global_step": 524173, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0683834552764893, "global_step": 524174, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0747313499450684, "global_step": 524175, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.023183584213257, "global_step": 524176, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.070364475250244, "global_step": 524177, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9485864639282227, "global_step": 524178, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.188136100769043, "global_step": 524179, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1077122688293457, "global_step": 524180, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.069089889526367, "global_step": 524181, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.02421498298645, "global_step": 524182, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.001389503479004, "global_step": 524183, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0595812797546387, "global_step": 524184, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9698618650436401, "global_step": 524185, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.115600824356079, "global_step": 524186, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.046539783477783, "global_step": 524187, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9593513011932373, "global_step": 524188, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.074145793914795, "global_step": 524189, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9921926259994507, "global_step": 524190, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.01859974861145, "global_step": 524191, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1271512508392334, "global_step": 524192, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.96436607837677, "global_step": 524193, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0187132358551025, "global_step": 524194, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.989368200302124, "global_step": 524195, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0118637084960938, "global_step": 524196, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.109705686569214, "global_step": 524197, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.058133363723755, "global_step": 524198, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0599911212921143, "global_step": 524199, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1385295391082764, "global_step": 524200, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.063889980316162, "global_step": 524201, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1251232624053955, "global_step": 524202, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.022498846054077, "global_step": 524203, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0749244689941406, "global_step": 524204, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0903501510620117, "global_step": 524205, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.106926441192627, "global_step": 524206, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0080673694610596, "global_step": 524207, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.057314157485962, "global_step": 524208, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0184483528137207, "global_step": 524209, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.04207444190979, "global_step": 524210, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9887324571609497, "global_step": 524211, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0873334407806396, "global_step": 524212, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.054222583770752, "global_step": 524213, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9552037715911865, "global_step": 524214, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.078294038772583, "global_step": 524215, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.032541036605835, "global_step": 524216, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.962245225906372, "global_step": 524217, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0369396209716797, "global_step": 524218, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.03753399848938, "global_step": 524219, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.085861921310425, "global_step": 524220, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.060153007507324, "global_step": 524221, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.998071551322937, "global_step": 524222, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.148141622543335, "global_step": 524223, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1416051387786865, "global_step": 524224, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.085468053817749, "global_step": 524225, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9722344875335693, "global_step": 524226, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.013463020324707, "global_step": 524227, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0357985496520996, "global_step": 524228, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.154810905456543, "global_step": 524229, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.005976438522339, "global_step": 524230, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.086425542831421, "global_step": 524231, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.033559799194336, "global_step": 524232, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.033543825149536, "global_step": 524233, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0927581787109375, "global_step": 524234, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0441558361053467, "global_step": 524235, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.096529006958008, "global_step": 524236, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0356335639953613, "global_step": 524237, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0193564891815186, "global_step": 524238, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.118328094482422, "global_step": 524239, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.050194025039673, "global_step": 524240, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9622877836227417, "global_step": 524241, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.035853385925293, "global_step": 524242, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0554616451263428, "global_step": 524243, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0075464248657227, "global_step": 524244, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.078950881958008, "global_step": 524245, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0656912326812744, "global_step": 524246, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.102510452270508, "global_step": 524247, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.081535577774048, "global_step": 524248, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9266530275344849, "global_step": 524249, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0739705562591553, "global_step": 524250, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.118847131729126, "global_step": 524251, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0452914237976074, "global_step": 524252, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0526649951934814, "global_step": 524253, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0462090969085693, "global_step": 524254, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.093787670135498, "global_step": 524255, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0074076652526855, "global_step": 524256, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9327677488327026, "global_step": 524257, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.004359722137451, "global_step": 524258, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0305910110473633, "global_step": 524259, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.166586399078369, "global_step": 524260, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.107832431793213, "global_step": 524261, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0706255435943604, "global_step": 524262, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0798685550689697, "global_step": 524263, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0643839836120605, "global_step": 524264, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9810919761657715, "global_step": 524265, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.011552333831787, "global_step": 524266, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0322091579437256, "global_step": 524267, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.089590311050415, "global_step": 524268, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0884079933166504, "global_step": 524269, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1226108074188232, "global_step": 524270, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0582773685455322, "global_step": 524271, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.007011890411377, "global_step": 524272, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0201175212860107, "global_step": 524273, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0664939880371094, "global_step": 524274, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.097438335418701, "global_step": 524275, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.076690435409546, "global_step": 524276, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0602781772613525, "global_step": 524277, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.970485806465149, "global_step": 524278, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.017420768737793, "global_step": 524279, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0061581134796143, "global_step": 524280, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9870671033859253, "global_step": 524281, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1013097763061523, "global_step": 524282, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9650096893310547, "global_step": 524283, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0181362628936768, "global_step": 524284, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.044527530670166, "global_step": 524285, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.001326084136963, "global_step": 524286, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0111300945281982, "global_step": 524287, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0565643310546875, "global_step": 524288, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.072303295135498, "global_step": 524289, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0463600158691406, "global_step": 524290, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0514872074127197, "global_step": 524291, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1236724853515625, "global_step": 524292, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9895554780960083, "global_step": 524293, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.097870111465454, "global_step": 524294, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0275609493255615, "global_step": 524295, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.02962064743042, "global_step": 524296, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.03130841255188, "global_step": 524297, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1016054153442383, "global_step": 524298, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.09934139251709, "global_step": 524299, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.069385290145874, "global_step": 524300, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.040189266204834, "global_step": 524301, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.036773204803467, "global_step": 524302, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.081530809402466, "global_step": 524303, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0747640132904053, "global_step": 524304, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0191149711608887, "global_step": 524305, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.03017258644104, "global_step": 524306, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0242996215820312, "global_step": 524307, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0562233924865723, "global_step": 524308, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9724560976028442, "global_step": 524309, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1547255516052246, "global_step": 524310, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.063105583190918, "global_step": 524311, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0456907749176025, "global_step": 524312, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.051246404647827, "global_step": 524313, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.983034610748291, "global_step": 524314, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.021846294403076, "global_step": 524315, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.052706718444824, "global_step": 524316, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.020143747329712, "global_step": 524317, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0921504497528076, "global_step": 524318, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0150680541992188, "global_step": 524319, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0564911365509033, "global_step": 524320, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9710253477096558, "global_step": 524321, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.958715796470642, "global_step": 524322, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9982988834381104, "global_step": 524323, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.068643093109131, "global_step": 524324, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0758533477783203, "global_step": 524325, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0608625411987305, "global_step": 524326, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9884936809539795, "global_step": 524327, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.077908515930176, "global_step": 524328, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.988900899887085, "global_step": 524329, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.999680519104004, "global_step": 524330, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0557637214660645, "global_step": 524331, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9824485778808594, "global_step": 524332, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9756672382354736, "global_step": 524333, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0588982105255127, "global_step": 524334, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.028512477874756, "global_step": 524335, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0150833129882812, "global_step": 524336, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0354254245758057, "global_step": 524337, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.049813985824585, "global_step": 524338, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.014780044555664, "global_step": 524339, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0811219215393066, "global_step": 524340, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9558632373809814, "global_step": 524341, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9848566055297852, "global_step": 524342, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0154879093170166, "global_step": 524343, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.021188497543335, "global_step": 524344, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0393970012664795, "global_step": 524345, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.081632375717163, "global_step": 524346, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0861096382141113, "global_step": 524347, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.019758462905884, "global_step": 524348, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0376763343811035, "global_step": 524349, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0362913608551025, "global_step": 524350, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.050255537033081, "global_step": 524351, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1278929710388184, "global_step": 524352, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0962765216827393, "global_step": 524353, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.122589588165283, "global_step": 524354, "epoch": 890, "lr": 5e-05}
{"train_loss": 1.9679062366485596, "global_step": 524355, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.1040902137756348, "global_step": 524356, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.013262987136841, "global_step": 524357, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.057166576385498, "global_step": 524358, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.051546812057495, "global_step": 524359, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.0304782390594482, "global_step": 524360, "epoch": 890, "lr": 5e-05}
{"train_loss": 2.041804552078247, "global_step": 524361, "epoch": 890, "lr": 5e-05, "val_loss": 5.7354865074157715, "test_reconst_mse": 0.07405000180006027}
{"train_loss": 2.0271825790405273, "global_step": 524362, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9964603185653687, "global_step": 524363, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9692851305007935, "global_step": 524364, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0234124660491943, "global_step": 524365, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.039336681365967, "global_step": 524366, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.972711205482483, "global_step": 524367, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0434300899505615, "global_step": 524368, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.133002996444702, "global_step": 524369, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.066460609436035, "global_step": 524370, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.131368637084961, "global_step": 524371, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0208632946014404, "global_step": 524372, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0730538368225098, "global_step": 524373, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0660223960876465, "global_step": 524374, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9591463804244995, "global_step": 524375, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0636157989501953, "global_step": 524376, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9564763307571411, "global_step": 524377, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0406737327575684, "global_step": 524378, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0020885467529297, "global_step": 524379, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.051203727722168, "global_step": 524380, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9972498416900635, "global_step": 524381, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0493392944335938, "global_step": 524382, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.009807825088501, "global_step": 524383, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0529587268829346, "global_step": 524384, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9558053016662598, "global_step": 524385, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0017240047454834, "global_step": 524386, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.037630558013916, "global_step": 524387, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0037481784820557, "global_step": 524388, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.995965600013733, "global_step": 524389, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9960395097732544, "global_step": 524390, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0243520736694336, "global_step": 524391, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9691866636276245, "global_step": 524392, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9549262523651123, "global_step": 524393, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.996010422706604, "global_step": 524394, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.020564317703247, "global_step": 524395, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.011651039123535, "global_step": 524396, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1402413845062256, "global_step": 524397, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0512502193450928, "global_step": 524398, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.003556489944458, "global_step": 524399, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.026339292526245, "global_step": 524400, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9540481567382812, "global_step": 524401, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0166513919830322, "global_step": 524402, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.08221435546875, "global_step": 524403, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9851840734481812, "global_step": 524404, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.024979591369629, "global_step": 524405, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.031282663345337, "global_step": 524406, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.110616683959961, "global_step": 524407, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0758299827575684, "global_step": 524408, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0027451515197754, "global_step": 524409, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0511324405670166, "global_step": 524410, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.962607741355896, "global_step": 524411, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0105626583099365, "global_step": 524412, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0638797283172607, "global_step": 524413, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.088824510574341, "global_step": 524414, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0121700763702393, "global_step": 524415, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9806029796600342, "global_step": 524416, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.00919508934021, "global_step": 524417, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.952141284942627, "global_step": 524418, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9845672845840454, "global_step": 524419, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.007016181945801, "global_step": 524420, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.14925217628479, "global_step": 524421, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9387332201004028, "global_step": 524422, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0080618858337402, "global_step": 524423, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.054859161376953, "global_step": 524424, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9497275352478027, "global_step": 524425, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.003842830657959, "global_step": 524426, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9935250282287598, "global_step": 524427, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0858747959136963, "global_step": 524428, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0337958335876465, "global_step": 524429, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.08675217628479, "global_step": 524430, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.091309070587158, "global_step": 524431, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.05828595161438, "global_step": 524432, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.99244225025177, "global_step": 524433, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0661253929138184, "global_step": 524434, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.019254446029663, "global_step": 524435, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9945427179336548, "global_step": 524436, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9353655576705933, "global_step": 524437, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0032310485839844, "global_step": 524438, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9746447801589966, "global_step": 524439, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0531015396118164, "global_step": 524440, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0453758239746094, "global_step": 524441, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.010014533996582, "global_step": 524442, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1350154876708984, "global_step": 524443, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.97025728225708, "global_step": 524444, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0471935272216797, "global_step": 524445, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9965349435806274, "global_step": 524446, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9609416723251343, "global_step": 524447, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.062548875808716, "global_step": 524448, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.064791202545166, "global_step": 524449, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0785884857177734, "global_step": 524450, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.080697536468506, "global_step": 524451, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0462136268615723, "global_step": 524452, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.973486304283142, "global_step": 524453, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0468642711639404, "global_step": 524454, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1286213397979736, "global_step": 524455, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0448946952819824, "global_step": 524456, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0441396236419678, "global_step": 524457, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1034841537475586, "global_step": 524458, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.029758930206299, "global_step": 524459, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0417885780334473, "global_step": 524460, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1241884231567383, "global_step": 524461, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.997737169265747, "global_step": 524462, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9982335567474365, "global_step": 524463, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.012620687484741, "global_step": 524464, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.135969877243042, "global_step": 524465, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.020538091659546, "global_step": 524466, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.023519277572632, "global_step": 524467, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.089416027069092, "global_step": 524468, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9466636180877686, "global_step": 524469, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0859110355377197, "global_step": 524470, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1003782749176025, "global_step": 524471, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.019415855407715, "global_step": 524472, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0531976222991943, "global_step": 524473, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0042786598205566, "global_step": 524474, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.067017078399658, "global_step": 524475, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0371861457824707, "global_step": 524476, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.063255786895752, "global_step": 524477, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.037266254425049, "global_step": 524478, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0231568813323975, "global_step": 524479, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0670485496520996, "global_step": 524480, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0418546199798584, "global_step": 524481, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0572147369384766, "global_step": 524482, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9621607065200806, "global_step": 524483, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0892951488494873, "global_step": 524484, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0358853340148926, "global_step": 524485, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0201454162597656, "global_step": 524486, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0536413192749023, "global_step": 524487, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.082834482192993, "global_step": 524488, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.105341911315918, "global_step": 524489, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.009350538253784, "global_step": 524490, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.997277021408081, "global_step": 524491, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0220794677734375, "global_step": 524492, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9966306686401367, "global_step": 524493, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9646354913711548, "global_step": 524494, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.000736951828003, "global_step": 524495, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.070547580718994, "global_step": 524496, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.10929799079895, "global_step": 524497, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.091968536376953, "global_step": 524498, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.042604446411133, "global_step": 524499, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0590527057647705, "global_step": 524500, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.017064094543457, "global_step": 524501, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.024923801422119, "global_step": 524502, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.064504861831665, "global_step": 524503, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9919434785842896, "global_step": 524504, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.11670184135437, "global_step": 524505, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.036966323852539, "global_step": 524506, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.928360104560852, "global_step": 524507, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.004720449447632, "global_step": 524508, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.105635643005371, "global_step": 524509, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0060079097747803, "global_step": 524510, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0762710571289062, "global_step": 524511, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.033250570297241, "global_step": 524512, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9886772632598877, "global_step": 524513, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0940611362457275, "global_step": 524514, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.01782488822937, "global_step": 524515, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.058131694793701, "global_step": 524516, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9959903955459595, "global_step": 524517, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0374114513397217, "global_step": 524518, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.107856273651123, "global_step": 524519, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.018700122833252, "global_step": 524520, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0210206508636475, "global_step": 524521, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.084526538848877, "global_step": 524522, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9792227745056152, "global_step": 524523, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0970139503479004, "global_step": 524524, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.01522159576416, "global_step": 524525, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.027613401412964, "global_step": 524526, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0481159687042236, "global_step": 524527, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.068749189376831, "global_step": 524528, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.028674602508545, "global_step": 524529, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0682144165039062, "global_step": 524530, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0517497062683105, "global_step": 524531, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.054806709289551, "global_step": 524532, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.003082513809204, "global_step": 524533, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.002379894256592, "global_step": 524534, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0866525173187256, "global_step": 524535, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.030486583709717, "global_step": 524536, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.050041913986206, "global_step": 524537, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9692102670669556, "global_step": 524538, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.044640302658081, "global_step": 524539, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.094970464706421, "global_step": 524540, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0343434810638428, "global_step": 524541, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0402941703796387, "global_step": 524542, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0418527126312256, "global_step": 524543, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0278432369232178, "global_step": 524544, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1163411140441895, "global_step": 524545, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.999444603919983, "global_step": 524546, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.081477642059326, "global_step": 524547, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0724897384643555, "global_step": 524548, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.984349250793457, "global_step": 524549, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0705668926239014, "global_step": 524550, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.007622718811035, "global_step": 524551, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.058257579803467, "global_step": 524552, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.075679063796997, "global_step": 524553, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0492327213287354, "global_step": 524554, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.099169969558716, "global_step": 524555, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.119394302368164, "global_step": 524556, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.003617286682129, "global_step": 524557, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9944403171539307, "global_step": 524558, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0791380405426025, "global_step": 524559, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.088888645172119, "global_step": 524560, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.003774404525757, "global_step": 524561, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.10538911819458, "global_step": 524562, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.05885910987854, "global_step": 524563, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.001441240310669, "global_step": 524564, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.030893564224243, "global_step": 524565, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.078984260559082, "global_step": 524566, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.103412389755249, "global_step": 524567, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0987908840179443, "global_step": 524568, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0184214115142822, "global_step": 524569, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0836851596832275, "global_step": 524570, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0474445819854736, "global_step": 524571, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1106209754943848, "global_step": 524572, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0952961444854736, "global_step": 524573, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0594232082366943, "global_step": 524574, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1019434928894043, "global_step": 524575, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9710886478424072, "global_step": 524576, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0736641883850098, "global_step": 524577, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0355513095855713, "global_step": 524578, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1463944911956787, "global_step": 524579, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.096669912338257, "global_step": 524580, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0891530513763428, "global_step": 524581, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.102987766265869, "global_step": 524582, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0006463527679443, "global_step": 524583, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0346174240112305, "global_step": 524584, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.059833526611328, "global_step": 524585, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.040478467941284, "global_step": 524586, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1033151149749756, "global_step": 524587, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0352768898010254, "global_step": 524588, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0711820125579834, "global_step": 524589, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0549895763397217, "global_step": 524590, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.041961431503296, "global_step": 524591, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9726388454437256, "global_step": 524592, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9903749227523804, "global_step": 524593, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9884517192840576, "global_step": 524594, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.051427125930786, "global_step": 524595, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1523895263671875, "global_step": 524596, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0270512104034424, "global_step": 524597, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0208089351654053, "global_step": 524598, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0909135341644287, "global_step": 524599, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.008213520050049, "global_step": 524600, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0566036701202393, "global_step": 524601, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0238142013549805, "global_step": 524602, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1408588886260986, "global_step": 524603, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.034167528152466, "global_step": 524604, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9588627815246582, "global_step": 524605, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9279634952545166, "global_step": 524606, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0438318252563477, "global_step": 524607, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0352954864501953, "global_step": 524608, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0703511238098145, "global_step": 524609, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0677239894866943, "global_step": 524610, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.028104305267334, "global_step": 524611, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.039620876312256, "global_step": 524612, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9294939041137695, "global_step": 524613, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.051415205001831, "global_step": 524614, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0423295497894287, "global_step": 524615, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0490565299987793, "global_step": 524616, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.038179397583008, "global_step": 524617, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9563158750534058, "global_step": 524618, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0567164421081543, "global_step": 524619, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.031527280807495, "global_step": 524620, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.017472743988037, "global_step": 524621, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0364034175872803, "global_step": 524622, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.02951979637146, "global_step": 524623, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.981071949005127, "global_step": 524624, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0724375247955322, "global_step": 524625, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0080296993255615, "global_step": 524626, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.005626916885376, "global_step": 524627, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0301666259765625, "global_step": 524628, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0281102657318115, "global_step": 524629, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.082397937774658, "global_step": 524630, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9601954221725464, "global_step": 524631, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.032189130783081, "global_step": 524632, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0394997596740723, "global_step": 524633, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0502142906188965, "global_step": 524634, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0488672256469727, "global_step": 524635, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9877680540084839, "global_step": 524636, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0971109867095947, "global_step": 524637, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9804799556732178, "global_step": 524638, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0258681774139404, "global_step": 524639, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0492448806762695, "global_step": 524640, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0053765773773193, "global_step": 524641, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.030961513519287, "global_step": 524642, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9551228284835815, "global_step": 524643, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9837034940719604, "global_step": 524644, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.043966770172119, "global_step": 524645, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0423178672790527, "global_step": 524646, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.014850378036499, "global_step": 524647, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.092315912246704, "global_step": 524648, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.094418525695801, "global_step": 524649, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.051863670349121, "global_step": 524650, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0987610816955566, "global_step": 524651, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.983271598815918, "global_step": 524652, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.03676700592041, "global_step": 524653, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0212438106536865, "global_step": 524654, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.990235686302185, "global_step": 524655, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0604240894317627, "global_step": 524656, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.997902274131775, "global_step": 524657, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9490629434585571, "global_step": 524658, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0617105960845947, "global_step": 524659, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0329017639160156, "global_step": 524660, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9616934061050415, "global_step": 524661, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.001176595687866, "global_step": 524662, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9840846061706543, "global_step": 524663, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0643908977508545, "global_step": 524664, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0503997802734375, "global_step": 524665, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1350462436676025, "global_step": 524666, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0359294414520264, "global_step": 524667, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0280230045318604, "global_step": 524668, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0956904888153076, "global_step": 524669, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.003649950027466, "global_step": 524670, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.017282724380493, "global_step": 524671, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9343360662460327, "global_step": 524672, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.14643931388855, "global_step": 524673, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0051095485687256, "global_step": 524674, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.996122121810913, "global_step": 524675, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.018580913543701, "global_step": 524676, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9302643537521362, "global_step": 524677, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0085577964782715, "global_step": 524678, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9968347549438477, "global_step": 524679, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.044128656387329, "global_step": 524680, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9700270891189575, "global_step": 524681, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.093224048614502, "global_step": 524682, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1002299785614014, "global_step": 524683, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.059933662414551, "global_step": 524684, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0087406635284424, "global_step": 524685, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.147614002227783, "global_step": 524686, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0165340900421143, "global_step": 524687, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0361850261688232, "global_step": 524688, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0458810329437256, "global_step": 524689, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.020576000213623, "global_step": 524690, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.070406198501587, "global_step": 524691, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0739402770996094, "global_step": 524692, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1469266414642334, "global_step": 524693, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0265605449676514, "global_step": 524694, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0482378005981445, "global_step": 524695, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0676183700561523, "global_step": 524696, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1028149127960205, "global_step": 524697, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0105135440826416, "global_step": 524698, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.077362060546875, "global_step": 524699, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.965934157371521, "global_step": 524700, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0243496894836426, "global_step": 524701, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.01509428024292, "global_step": 524702, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0244500637054443, "global_step": 524703, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1182732582092285, "global_step": 524704, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.015324592590332, "global_step": 524705, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0938668251037598, "global_step": 524706, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9830551147460938, "global_step": 524707, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1495819091796875, "global_step": 524708, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9352251291275024, "global_step": 524709, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0737478733062744, "global_step": 524710, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.011087656021118, "global_step": 524711, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9498660564422607, "global_step": 524712, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.963842511177063, "global_step": 524713, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0868828296661377, "global_step": 524714, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.126356601715088, "global_step": 524715, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0193331241607666, "global_step": 524716, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.014885187149048, "global_step": 524717, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9782392978668213, "global_step": 524718, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0592427253723145, "global_step": 524719, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0431947708129883, "global_step": 524720, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.021284580230713, "global_step": 524721, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9940012693405151, "global_step": 524722, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0905165672302246, "global_step": 524723, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0184171199798584, "global_step": 524724, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.03757381439209, "global_step": 524725, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.023244857788086, "global_step": 524726, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0064876079559326, "global_step": 524727, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.027776002883911, "global_step": 524728, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9938843250274658, "global_step": 524729, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9580962657928467, "global_step": 524730, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.082082748413086, "global_step": 524731, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9997128248214722, "global_step": 524732, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.031022787094116, "global_step": 524733, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0563883781433105, "global_step": 524734, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.028859853744507, "global_step": 524735, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.085664749145508, "global_step": 524736, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.130296230316162, "global_step": 524737, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0808417797088623, "global_step": 524738, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0587658882141113, "global_step": 524739, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0032095909118652, "global_step": 524740, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.058668613433838, "global_step": 524741, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.062647581100464, "global_step": 524742, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.045189380645752, "global_step": 524743, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.109992027282715, "global_step": 524744, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.091356039047241, "global_step": 524745, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0837337970733643, "global_step": 524746, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9068950414657593, "global_step": 524747, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.956763505935669, "global_step": 524748, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.050943374633789, "global_step": 524749, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9382303953170776, "global_step": 524750, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9423197507858276, "global_step": 524751, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.026069402694702, "global_step": 524752, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1226677894592285, "global_step": 524753, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9845906496047974, "global_step": 524754, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0638749599456787, "global_step": 524755, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0414867401123047, "global_step": 524756, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0687506198883057, "global_step": 524757, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.080679178237915, "global_step": 524758, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.004507064819336, "global_step": 524759, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.05729341506958, "global_step": 524760, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0128800868988037, "global_step": 524761, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1989734172821045, "global_step": 524762, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.013645887374878, "global_step": 524763, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.971618413925171, "global_step": 524764, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0810186862945557, "global_step": 524765, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0824997425079346, "global_step": 524766, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.101186990737915, "global_step": 524767, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9839617013931274, "global_step": 524768, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.045955181121826, "global_step": 524769, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0999112129211426, "global_step": 524770, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0325045585632324, "global_step": 524771, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0277349948883057, "global_step": 524772, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1322977542877197, "global_step": 524773, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.102257251739502, "global_step": 524774, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.087597608566284, "global_step": 524775, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1498899459838867, "global_step": 524776, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0973289012908936, "global_step": 524777, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.049304246902466, "global_step": 524778, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1965208053588867, "global_step": 524779, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9585371017456055, "global_step": 524780, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.062946319580078, "global_step": 524781, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.029618740081787, "global_step": 524782, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.083981513977051, "global_step": 524783, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0236451625823975, "global_step": 524784, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0917882919311523, "global_step": 524785, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.057635545730591, "global_step": 524786, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.011559009552002, "global_step": 524787, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.089308500289917, "global_step": 524788, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0852558612823486, "global_step": 524789, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1001741886138916, "global_step": 524790, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9575399160385132, "global_step": 524791, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0809733867645264, "global_step": 524792, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.982094168663025, "global_step": 524793, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.071007490158081, "global_step": 524794, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9303251504898071, "global_step": 524795, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0689404010772705, "global_step": 524796, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1154139041900635, "global_step": 524797, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.106933355331421, "global_step": 524798, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0310544967651367, "global_step": 524799, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0240726470947266, "global_step": 524800, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.032670497894287, "global_step": 524801, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9863390922546387, "global_step": 524802, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0778589248657227, "global_step": 524803, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.010733127593994, "global_step": 524804, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1090023517608643, "global_step": 524805, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0847816467285156, "global_step": 524806, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.004150390625, "global_step": 524807, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9730528593063354, "global_step": 524808, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9904899597167969, "global_step": 524809, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.06941556930542, "global_step": 524810, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9816120862960815, "global_step": 524811, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.024744987487793, "global_step": 524812, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0875799655914307, "global_step": 524813, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9148997068405151, "global_step": 524814, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0223772525787354, "global_step": 524815, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0033202171325684, "global_step": 524816, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.012190341949463, "global_step": 524817, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0177760124206543, "global_step": 524818, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9139362573623657, "global_step": 524819, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9877123832702637, "global_step": 524820, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1196303367614746, "global_step": 524821, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0825018882751465, "global_step": 524822, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.100482940673828, "global_step": 524823, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0468733310699463, "global_step": 524824, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.063660144805908, "global_step": 524825, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0767719745635986, "global_step": 524826, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.063258647918701, "global_step": 524827, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9718958139419556, "global_step": 524828, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0557515621185303, "global_step": 524829, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0489583015441895, "global_step": 524830, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.093174934387207, "global_step": 524831, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9936540126800537, "global_step": 524832, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1067006587982178, "global_step": 524833, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0073800086975098, "global_step": 524834, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.048184871673584, "global_step": 524835, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.099843978881836, "global_step": 524836, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0492777824401855, "global_step": 524837, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9670008420944214, "global_step": 524838, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.042097330093384, "global_step": 524839, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0497984886169434, "global_step": 524840, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.974753975868225, "global_step": 524841, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1043102741241455, "global_step": 524842, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.081646680831909, "global_step": 524843, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0649397373199463, "global_step": 524844, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0163986682891846, "global_step": 524845, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0996227264404297, "global_step": 524846, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9401336908340454, "global_step": 524847, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0732381343841553, "global_step": 524848, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.113642692565918, "global_step": 524849, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.084807872772217, "global_step": 524850, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.172122001647949, "global_step": 524851, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.907189130783081, "global_step": 524852, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0706019401550293, "global_step": 524853, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.116603136062622, "global_step": 524854, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0611534118652344, "global_step": 524855, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.041323184967041, "global_step": 524856, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.075101375579834, "global_step": 524857, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.017237663269043, "global_step": 524858, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.068596124649048, "global_step": 524859, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.035644292831421, "global_step": 524860, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1376445293426514, "global_step": 524861, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9639146327972412, "global_step": 524862, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0165765285491943, "global_step": 524863, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0720913410186768, "global_step": 524864, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9658066034317017, "global_step": 524865, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.147392511367798, "global_step": 524866, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1186115741729736, "global_step": 524867, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.050126314163208, "global_step": 524868, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1028919219970703, "global_step": 524869, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1174428462982178, "global_step": 524870, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1366729736328125, "global_step": 524871, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.041811466217041, "global_step": 524872, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0391640663146973, "global_step": 524873, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0016846656799316, "global_step": 524874, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0309908390045166, "global_step": 524875, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.021198034286499, "global_step": 524876, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.108516216278076, "global_step": 524877, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.087341070175171, "global_step": 524878, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9723554849624634, "global_step": 524879, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.089543104171753, "global_step": 524880, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0820810794830322, "global_step": 524881, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0118842124938965, "global_step": 524882, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.048689842224121, "global_step": 524883, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0592238903045654, "global_step": 524884, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0887792110443115, "global_step": 524885, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0543479919433594, "global_step": 524886, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0468931198120117, "global_step": 524887, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9657002687454224, "global_step": 524888, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.004732131958008, "global_step": 524889, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.033365488052368, "global_step": 524890, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.09702730178833, "global_step": 524891, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9646995067596436, "global_step": 524892, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0427448749542236, "global_step": 524893, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.021669864654541, "global_step": 524894, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.001358985900879, "global_step": 524895, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9823880195617676, "global_step": 524896, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.050837993621826, "global_step": 524897, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.06559419631958, "global_step": 524898, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.005546808242798, "global_step": 524899, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0171496868133545, "global_step": 524900, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0641791820526123, "global_step": 524901, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9574047327041626, "global_step": 524902, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1079914569854736, "global_step": 524903, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0590322017669678, "global_step": 524904, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.036518096923828, "global_step": 524905, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.005101203918457, "global_step": 524906, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0043718814849854, "global_step": 524907, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.083151340484619, "global_step": 524908, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0977253913879395, "global_step": 524909, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9895367622375488, "global_step": 524910, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9721258878707886, "global_step": 524911, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0180909633636475, "global_step": 524912, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.946675181388855, "global_step": 524913, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0573840141296387, "global_step": 524914, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.003964900970459, "global_step": 524915, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0526769161224365, "global_step": 524916, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.092068672180176, "global_step": 524917, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0243754386901855, "global_step": 524918, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0310192108154297, "global_step": 524919, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.004552125930786, "global_step": 524920, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0407869815826416, "global_step": 524921, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0879290103912354, "global_step": 524922, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.061939001083374, "global_step": 524923, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0510966777801514, "global_step": 524924, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9204063415527344, "global_step": 524925, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0389158725738525, "global_step": 524926, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.969810962677002, "global_step": 524927, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0645105838775635, "global_step": 524928, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.075305700302124, "global_step": 524929, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0189120769500732, "global_step": 524930, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.055185556411743, "global_step": 524931, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9964861869812012, "global_step": 524932, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0534749031066895, "global_step": 524933, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9903030395507812, "global_step": 524934, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0400638580322266, "global_step": 524935, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0730814933776855, "global_step": 524936, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0469188690185547, "global_step": 524937, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.00954008102417, "global_step": 524938, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0844218730926514, "global_step": 524939, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9976288080215454, "global_step": 524940, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0106685161590576, "global_step": 524941, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0253283977508545, "global_step": 524942, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.051924705505371, "global_step": 524943, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0620815753936768, "global_step": 524944, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0972626209259033, "global_step": 524945, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9801479578018188, "global_step": 524946, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9668558835983276, "global_step": 524947, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0243592262268066, "global_step": 524948, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0280516147613525, "global_step": 524949, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0368683338165283, "global_step": 524950, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0408451557159424, "global_step": 524951, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1156575679779053, "global_step": 524952, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0406839847564697, "global_step": 524953, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.104895830154419, "global_step": 524954, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.04483962059021, "global_step": 524955, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.062004804611206, "global_step": 524956, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.033856153488159, "global_step": 524957, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.091841220855713, "global_step": 524958, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.098154306411743, "global_step": 524959, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0184733867645264, "global_step": 524960, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.030284881591797, "global_step": 524961, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9997100830078125, "global_step": 524962, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0129027366638184, "global_step": 524963, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.037506103515625, "global_step": 524964, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1180686950683594, "global_step": 524965, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1028075218200684, "global_step": 524966, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0300381183624268, "global_step": 524967, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0392863750457764, "global_step": 524968, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.010997772216797, "global_step": 524969, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.132619857788086, "global_step": 524970, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.025587558746338, "global_step": 524971, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0388810634613037, "global_step": 524972, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0392916202545166, "global_step": 524973, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0782198905944824, "global_step": 524974, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.052105665206909, "global_step": 524975, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.092237710952759, "global_step": 524976, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9971510171890259, "global_step": 524977, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.025362730026245, "global_step": 524978, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1301963329315186, "global_step": 524979, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.97934091091156, "global_step": 524980, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0180914402008057, "global_step": 524981, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0202419757843018, "global_step": 524982, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0361692905426025, "global_step": 524983, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.075364589691162, "global_step": 524984, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.060720205307007, "global_step": 524985, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.022381544113159, "global_step": 524986, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9613893032073975, "global_step": 524987, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.080153465270996, "global_step": 524988, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1209988594055176, "global_step": 524989, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1072514057159424, "global_step": 524990, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0795085430145264, "global_step": 524991, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.048090696334839, "global_step": 524992, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0469586849212646, "global_step": 524993, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.002117156982422, "global_step": 524994, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0022284984588623, "global_step": 524995, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1134965419769287, "global_step": 524996, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0904557704925537, "global_step": 524997, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0684618949890137, "global_step": 524998, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.968528389930725, "global_step": 524999, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0965325832366943, "global_step": 525000, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0729856491088867, "global_step": 525001, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0001652240753174, "global_step": 525002, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9963237047195435, "global_step": 525003, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0081865787506104, "global_step": 525004, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.003634214401245, "global_step": 525005, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.069420099258423, "global_step": 525006, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0695037841796875, "global_step": 525007, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.049129009246826, "global_step": 525008, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0732905864715576, "global_step": 525009, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.037458658218384, "global_step": 525010, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0406665802001953, "global_step": 525011, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0409462451934814, "global_step": 525012, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.070329189300537, "global_step": 525013, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0294902324676514, "global_step": 525014, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.024155616760254, "global_step": 525015, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1756696701049805, "global_step": 525016, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.991487979888916, "global_step": 525017, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0572314262390137, "global_step": 525018, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0677008628845215, "global_step": 525019, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9764424562454224, "global_step": 525020, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1416351795196533, "global_step": 525021, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0255770683288574, "global_step": 525022, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.032562017440796, "global_step": 525023, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.016935110092163, "global_step": 525024, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9836041927337646, "global_step": 525025, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.089442491531372, "global_step": 525026, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.08699631690979, "global_step": 525027, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.123600482940674, "global_step": 525028, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9955925941467285, "global_step": 525029, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.112776756286621, "global_step": 525030, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9974359273910522, "global_step": 525031, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0180890560150146, "global_step": 525032, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0688438415527344, "global_step": 525033, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.101334571838379, "global_step": 525034, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.026684045791626, "global_step": 525035, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.069613218307495, "global_step": 525036, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0367069244384766, "global_step": 525037, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0644638538360596, "global_step": 525038, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0041332244873047, "global_step": 525039, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1219067573547363, "global_step": 525040, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.071690082550049, "global_step": 525041, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0290915966033936, "global_step": 525042, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0031611919403076, "global_step": 525043, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.089200258255005, "global_step": 525044, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0698137283325195, "global_step": 525045, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0700526237487793, "global_step": 525046, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.061396360397339, "global_step": 525047, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0632050037384033, "global_step": 525048, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0727951526641846, "global_step": 525049, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1094412803649902, "global_step": 525050, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1053669452667236, "global_step": 525051, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0442872047424316, "global_step": 525052, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9740116596221924, "global_step": 525053, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0812408924102783, "global_step": 525054, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0355257987976074, "global_step": 525055, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.066608428955078, "global_step": 525056, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0462796688079834, "global_step": 525057, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0831961631774902, "global_step": 525058, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.021350622177124, "global_step": 525059, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.085517406463623, "global_step": 525060, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9347500801086426, "global_step": 525061, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0931200981140137, "global_step": 525062, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0841920375823975, "global_step": 525063, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0423896312713623, "global_step": 525064, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9917346239089966, "global_step": 525065, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.038966178894043, "global_step": 525066, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.077693462371826, "global_step": 525067, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0605692863464355, "global_step": 525068, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.030205249786377, "global_step": 525069, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0336389541625977, "global_step": 525070, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0841708183288574, "global_step": 525071, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.075331687927246, "global_step": 525072, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0610270500183105, "global_step": 525073, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0749709606170654, "global_step": 525074, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.023908853530884, "global_step": 525075, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.992849349975586, "global_step": 525076, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0180885791778564, "global_step": 525077, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.039198398590088, "global_step": 525078, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9407551288604736, "global_step": 525079, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0598325729370117, "global_step": 525080, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.099147319793701, "global_step": 525081, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1015989780426025, "global_step": 525082, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0755765438079834, "global_step": 525083, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0619089603424072, "global_step": 525084, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.116771936416626, "global_step": 525085, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0113844871520996, "global_step": 525086, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.069822072982788, "global_step": 525087, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.03550386428833, "global_step": 525088, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9974591732025146, "global_step": 525089, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.10911226272583, "global_step": 525090, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.028959035873413, "global_step": 525091, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.061509609222412, "global_step": 525092, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9960012435913086, "global_step": 525093, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0445148944854736, "global_step": 525094, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.084930896759033, "global_step": 525095, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.058999538421631, "global_step": 525096, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0751171112060547, "global_step": 525097, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0450360774993896, "global_step": 525098, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.084911346435547, "global_step": 525099, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0341360569000244, "global_step": 525100, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0556797981262207, "global_step": 525101, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.039292573928833, "global_step": 525102, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0588271617889404, "global_step": 525103, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.05808687210083, "global_step": 525104, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.079735040664673, "global_step": 525105, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0489916801452637, "global_step": 525106, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1095571517944336, "global_step": 525107, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0507967472076416, "global_step": 525108, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1075358390808105, "global_step": 525109, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0401227474212646, "global_step": 525110, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.069913864135742, "global_step": 525111, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0570194721221924, "global_step": 525112, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9791929721832275, "global_step": 525113, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0500638484954834, "global_step": 525114, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0665669441223145, "global_step": 525115, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.985508680343628, "global_step": 525116, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.10614275932312, "global_step": 525117, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0315535068511963, "global_step": 525118, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.058852434158325, "global_step": 525119, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1268017292022705, "global_step": 525120, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.16927170753479, "global_step": 525121, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0291788578033447, "global_step": 525122, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1571261882781982, "global_step": 525123, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.000699996948242, "global_step": 525124, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.03670072555542, "global_step": 525125, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0173017978668213, "global_step": 525126, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0933685302734375, "global_step": 525127, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9844963550567627, "global_step": 525128, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.035698175430298, "global_step": 525129, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0305275917053223, "global_step": 525130, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.036133289337158, "global_step": 525131, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0317418575286865, "global_step": 525132, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0245182514190674, "global_step": 525133, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9830529689788818, "global_step": 525134, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.137718915939331, "global_step": 525135, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0413739681243896, "global_step": 525136, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.050527334213257, "global_step": 525137, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0095741748809814, "global_step": 525138, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0367705821990967, "global_step": 525139, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0316412448883057, "global_step": 525140, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0972280502319336, "global_step": 525141, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0964818000793457, "global_step": 525142, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.001469373703003, "global_step": 525143, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1106457710266113, "global_step": 525144, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.060554265975952, "global_step": 525145, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1000540256500244, "global_step": 525146, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.052826404571533, "global_step": 525147, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0778889656066895, "global_step": 525148, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0668582916259766, "global_step": 525149, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0886595249176025, "global_step": 525150, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.015812635421753, "global_step": 525151, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.10367751121521, "global_step": 525152, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.013766050338745, "global_step": 525153, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.005209445953369, "global_step": 525154, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1684107780456543, "global_step": 525155, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0589239597320557, "global_step": 525156, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.994871973991394, "global_step": 525157, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0333409309387207, "global_step": 525158, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0796327590942383, "global_step": 525159, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9634811878204346, "global_step": 525160, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0851547718048096, "global_step": 525161, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0646748542785645, "global_step": 525162, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0399227142333984, "global_step": 525163, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0778348445892334, "global_step": 525164, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0296847820281982, "global_step": 525165, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.045722246170044, "global_step": 525166, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0475356578826904, "global_step": 525167, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0557188987731934, "global_step": 525168, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0615017414093018, "global_step": 525169, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9819302558898926, "global_step": 525170, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0163164138793945, "global_step": 525171, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0551674365997314, "global_step": 525172, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9792428016662598, "global_step": 525173, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0931825637817383, "global_step": 525174, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1224365234375, "global_step": 525175, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.001498222351074, "global_step": 525176, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0072450637817383, "global_step": 525177, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0050673484802246, "global_step": 525178, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.020484685897827, "global_step": 525179, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9470542669296265, "global_step": 525180, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.088214159011841, "global_step": 525181, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1143500804901123, "global_step": 525182, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0765678882598877, "global_step": 525183, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9875173568725586, "global_step": 525184, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.064215660095215, "global_step": 525185, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9941102266311646, "global_step": 525186, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9716718196868896, "global_step": 525187, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0160768032073975, "global_step": 525188, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.117703914642334, "global_step": 525189, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0942673683166504, "global_step": 525190, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.10455322265625, "global_step": 525191, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0569825172424316, "global_step": 525192, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0181901454925537, "global_step": 525193, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1040515899658203, "global_step": 525194, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.8771452903747559, "global_step": 525195, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0347976684570312, "global_step": 525196, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.03787899017334, "global_step": 525197, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.043663501739502, "global_step": 525198, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0924794673919678, "global_step": 525199, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0687310695648193, "global_step": 525200, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.052917718887329, "global_step": 525201, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0552332401275635, "global_step": 525202, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1044509410858154, "global_step": 525203, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0509116649627686, "global_step": 525204, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0914831161499023, "global_step": 525205, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.123589277267456, "global_step": 525206, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.083930492401123, "global_step": 525207, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0675415992736816, "global_step": 525208, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.046220541000366, "global_step": 525209, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.018099069595337, "global_step": 525210, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9553357362747192, "global_step": 525211, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.056312084197998, "global_step": 525212, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9940297603607178, "global_step": 525213, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.028169870376587, "global_step": 525214, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1141533851623535, "global_step": 525215, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0123369693756104, "global_step": 525216, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0270049571990967, "global_step": 525217, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.075063705444336, "global_step": 525218, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.075188398361206, "global_step": 525219, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.11865234375, "global_step": 525220, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0941526889801025, "global_step": 525221, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.04293155670166, "global_step": 525222, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.106715202331543, "global_step": 525223, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9254971742630005, "global_step": 525224, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0474343299865723, "global_step": 525225, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0981125831604004, "global_step": 525226, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.126845598220825, "global_step": 525227, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0823798179626465, "global_step": 525228, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0023508071899414, "global_step": 525229, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.053148031234741, "global_step": 525230, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.004971504211426, "global_step": 525231, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1186370849609375, "global_step": 525232, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0138468742370605, "global_step": 525233, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.012904405593872, "global_step": 525234, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0379631519317627, "global_step": 525235, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0280401706695557, "global_step": 525236, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.008471965789795, "global_step": 525237, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.050020456314087, "global_step": 525238, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.08107328414917, "global_step": 525239, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0380139350891113, "global_step": 525240, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.090696096420288, "global_step": 525241, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0186586380004883, "global_step": 525242, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.118018627166748, "global_step": 525243, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0736618041992188, "global_step": 525244, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9590773582458496, "global_step": 525245, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0555574893951416, "global_step": 525246, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.060183048248291, "global_step": 525247, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.090648651123047, "global_step": 525248, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0428552627563477, "global_step": 525249, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.118879795074463, "global_step": 525250, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1043894290924072, "global_step": 525251, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.053269624710083, "global_step": 525252, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.046865940093994, "global_step": 525253, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0673885345458984, "global_step": 525254, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0987958908081055, "global_step": 525255, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1179652214050293, "global_step": 525256, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9649502038955688, "global_step": 525257, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9876203536987305, "global_step": 525258, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0389211177825928, "global_step": 525259, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.949710488319397, "global_step": 525260, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.909334421157837, "global_step": 525261, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1230108737945557, "global_step": 525262, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9143648147583008, "global_step": 525263, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1380257606506348, "global_step": 525264, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.094015598297119, "global_step": 525265, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0463390350341797, "global_step": 525266, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0008513927459717, "global_step": 525267, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.02553129196167, "global_step": 525268, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0069758892059326, "global_step": 525269, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0101003646850586, "global_step": 525270, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9903154373168945, "global_step": 525271, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0617895126342773, "global_step": 525272, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.107238531112671, "global_step": 525273, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.026061534881592, "global_step": 525274, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.114990234375, "global_step": 525275, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9634296894073486, "global_step": 525276, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.982033371925354, "global_step": 525277, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0997869968414307, "global_step": 525278, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.039512872695923, "global_step": 525279, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.035365581512451, "global_step": 525280, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0861949920654297, "global_step": 525281, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0242180824279785, "global_step": 525282, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9971803426742554, "global_step": 525283, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.062898874282837, "global_step": 525284, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0247271060943604, "global_step": 525285, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0971107482910156, "global_step": 525286, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0434274673461914, "global_step": 525287, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0807509422302246, "global_step": 525288, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.018934965133667, "global_step": 525289, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1039814949035645, "global_step": 525290, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.953332543373108, "global_step": 525291, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0167157649993896, "global_step": 525292, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.025925874710083, "global_step": 525293, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0388545989990234, "global_step": 525294, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0443501472473145, "global_step": 525295, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.117469549179077, "global_step": 525296, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0682053565979004, "global_step": 525297, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.029885768890381, "global_step": 525298, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1082446575164795, "global_step": 525299, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0624730587005615, "global_step": 525300, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.997037410736084, "global_step": 525301, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.012303352355957, "global_step": 525302, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0932655334472656, "global_step": 525303, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1810500621795654, "global_step": 525304, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1352884769439697, "global_step": 525305, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.163360357284546, "global_step": 525306, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.040508270263672, "global_step": 525307, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0769519805908203, "global_step": 525308, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1000747680664062, "global_step": 525309, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0634851455688477, "global_step": 525310, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.09232497215271, "global_step": 525311, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0858867168426514, "global_step": 525312, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0410964488983154, "global_step": 525313, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0210447311401367, "global_step": 525314, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0390610694885254, "global_step": 525315, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1516990661621094, "global_step": 525316, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.097701072692871, "global_step": 525317, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0175890922546387, "global_step": 525318, "epoch": 891, "lr": 5e-05}
{"train_loss": 1.9329323768615723, "global_step": 525319, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.049318552017212, "global_step": 525320, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0792605876922607, "global_step": 525321, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.040163278579712, "global_step": 525322, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0704023838043213, "global_step": 525323, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0599379539489746, "global_step": 525324, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0978405475616455, "global_step": 525325, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0039520263671875, "global_step": 525326, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.1314938068389893, "global_step": 525327, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0641424655914307, "global_step": 525328, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.104731321334839, "global_step": 525329, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0441272258758545, "global_step": 525330, "epoch": 891, "lr": 5e-05}
{"train_loss": 2.0520987510681152, "global_step": 525331, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9729841947555542, "global_step": 525332, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0459208488464355, "global_step": 525333, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9455024003982544, "global_step": 525334, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.117218255996704, "global_step": 525335, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.056776523590088, "global_step": 525336, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.98361074924469, "global_step": 525337, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.039057731628418, "global_step": 525338, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.064546585083008, "global_step": 525339, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0577774047851562, "global_step": 525340, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0348706245422363, "global_step": 525341, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9889686107635498, "global_step": 525342, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1001927852630615, "global_step": 525343, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0463078022003174, "global_step": 525344, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.034522771835327, "global_step": 525345, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.060443878173828, "global_step": 525346, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0472252368927, "global_step": 525347, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9891669750213623, "global_step": 525348, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.974832534790039, "global_step": 525349, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0271618366241455, "global_step": 525350, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.998146414756775, "global_step": 525351, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.028201103210449, "global_step": 525352, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.021293878555298, "global_step": 525353, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.020033597946167, "global_step": 525354, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.081369161605835, "global_step": 525355, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9855235815048218, "global_step": 525356, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9521069526672363, "global_step": 525357, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.025573968887329, "global_step": 525358, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9651410579681396, "global_step": 525359, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0367584228515625, "global_step": 525360, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0116186141967773, "global_step": 525361, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0558745861053467, "global_step": 525362, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.030444622039795, "global_step": 525363, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0181970596313477, "global_step": 525364, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9925028085708618, "global_step": 525365, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9885375499725342, "global_step": 525366, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0581939220428467, "global_step": 525367, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9393365383148193, "global_step": 525368, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9985147714614868, "global_step": 525369, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0646703243255615, "global_step": 525370, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0025761127471924, "global_step": 525371, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.038853645324707, "global_step": 525372, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0337953567504883, "global_step": 525373, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9916409254074097, "global_step": 525374, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.031588315963745, "global_step": 525375, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.985743522644043, "global_step": 525376, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.018298387527466, "global_step": 525377, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.040992021560669, "global_step": 525378, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0535805225372314, "global_step": 525379, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9637129306793213, "global_step": 525380, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.097682237625122, "global_step": 525381, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9998382329940796, "global_step": 525382, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0166256427764893, "global_step": 525383, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.034714937210083, "global_step": 525384, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0098984241485596, "global_step": 525385, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9832693338394165, "global_step": 525386, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0610523223876953, "global_step": 525387, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9606668949127197, "global_step": 525388, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9510972499847412, "global_step": 525389, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.067627191543579, "global_step": 525390, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.99007248878479, "global_step": 525391, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0612568855285645, "global_step": 525392, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.06866455078125, "global_step": 525393, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9999802112579346, "global_step": 525394, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9658703804016113, "global_step": 525395, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9406932592391968, "global_step": 525396, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.046919822692871, "global_step": 525397, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1254401206970215, "global_step": 525398, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.027778387069702, "global_step": 525399, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.024176836013794, "global_step": 525400, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0396738052368164, "global_step": 525401, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0109429359436035, "global_step": 525402, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0646426677703857, "global_step": 525403, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1069629192352295, "global_step": 525404, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.11991548538208, "global_step": 525405, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0175256729125977, "global_step": 525406, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.055453062057495, "global_step": 525407, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.091033697128296, "global_step": 525408, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9595296382904053, "global_step": 525409, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0335214138031006, "global_step": 525410, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.042534589767456, "global_step": 525411, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9745692014694214, "global_step": 525412, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.031921863555908, "global_step": 525413, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0534555912017822, "global_step": 525414, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1049082279205322, "global_step": 525415, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.054079294204712, "global_step": 525416, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0199520587921143, "global_step": 525417, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0520336627960205, "global_step": 525418, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0710160732269287, "global_step": 525419, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9911596775054932, "global_step": 525420, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0626087188720703, "global_step": 525421, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.999452829360962, "global_step": 525422, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0532684326171875, "global_step": 525423, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.999925971031189, "global_step": 525424, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.030860185623169, "global_step": 525425, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0768749713897705, "global_step": 525426, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.022771120071411, "global_step": 525427, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9997477531433105, "global_step": 525428, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.973458170890808, "global_step": 525429, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9719393253326416, "global_step": 525430, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0297064781188965, "global_step": 525431, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0747618675231934, "global_step": 525432, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0573534965515137, "global_step": 525433, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9948828220367432, "global_step": 525434, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0931434631347656, "global_step": 525435, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.000267744064331, "global_step": 525436, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1013057231903076, "global_step": 525437, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.981240153312683, "global_step": 525438, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0495293140411377, "global_step": 525439, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0178451538085938, "global_step": 525440, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0402493476867676, "global_step": 525441, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0130138397216797, "global_step": 525442, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1077189445495605, "global_step": 525443, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0799529552459717, "global_step": 525444, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0569777488708496, "global_step": 525445, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.998652458190918, "global_step": 525446, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9537547826766968, "global_step": 525447, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9271821975708008, "global_step": 525448, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0709595680236816, "global_step": 525449, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0972142219543457, "global_step": 525450, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0693981647491455, "global_step": 525451, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.124974250793457, "global_step": 525452, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9894014596939087, "global_step": 525453, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.992023229598999, "global_step": 525454, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.117448091506958, "global_step": 525455, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0152363777160645, "global_step": 525456, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1111464500427246, "global_step": 525457, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.055570602416992, "global_step": 525458, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0035157203674316, "global_step": 525459, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0690665245056152, "global_step": 525460, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.05301570892334, "global_step": 525461, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0285866260528564, "global_step": 525462, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0867066383361816, "global_step": 525463, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0046422481536865, "global_step": 525464, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.023623466491699, "global_step": 525465, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0675675868988037, "global_step": 525466, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.018578290939331, "global_step": 525467, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.96209716796875, "global_step": 525468, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.002163887023926, "global_step": 525469, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.041604518890381, "global_step": 525470, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.996354579925537, "global_step": 525471, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.124861240386963, "global_step": 525472, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.06864595413208, "global_step": 525473, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0213847160339355, "global_step": 525474, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.13401198387146, "global_step": 525475, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9812804460525513, "global_step": 525476, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1004230976104736, "global_step": 525477, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.99968421459198, "global_step": 525478, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.091540575027466, "global_step": 525479, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.065843343734741, "global_step": 525480, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0606167316436768, "global_step": 525481, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.029683828353882, "global_step": 525482, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.00248646736145, "global_step": 525483, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9733085632324219, "global_step": 525484, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.051769495010376, "global_step": 525485, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0688693523406982, "global_step": 525486, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.065767288208008, "global_step": 525487, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9933823347091675, "global_step": 525488, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.085355043411255, "global_step": 525489, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9924808740615845, "global_step": 525490, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.018794536590576, "global_step": 525491, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0306594371795654, "global_step": 525492, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0409462451934814, "global_step": 525493, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0341010093688965, "global_step": 525494, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0606753826141357, "global_step": 525495, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9727073907852173, "global_step": 525496, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.044768810272217, "global_step": 525497, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9616674184799194, "global_step": 525498, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.081080436706543, "global_step": 525499, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.068047523498535, "global_step": 525500, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0036234855651855, "global_step": 525501, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0466601848602295, "global_step": 525502, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1070494651794434, "global_step": 525503, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0150203704833984, "global_step": 525504, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0552520751953125, "global_step": 525505, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0496644973754883, "global_step": 525506, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.050278663635254, "global_step": 525507, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9686665534973145, "global_step": 525508, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9869723320007324, "global_step": 525509, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.109588146209717, "global_step": 525510, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.064790725708008, "global_step": 525511, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0888147354125977, "global_step": 525512, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.080951452255249, "global_step": 525513, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.012927770614624, "global_step": 525514, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9144330024719238, "global_step": 525515, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.009845018386841, "global_step": 525516, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.032064437866211, "global_step": 525517, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0191195011138916, "global_step": 525518, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0727713108062744, "global_step": 525519, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9803115129470825, "global_step": 525520, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.006150245666504, "global_step": 525521, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0533084869384766, "global_step": 525522, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.033780574798584, "global_step": 525523, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.047400951385498, "global_step": 525524, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0805327892303467, "global_step": 525525, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.04185152053833, "global_step": 525526, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0220649242401123, "global_step": 525527, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0320305824279785, "global_step": 525528, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0024542808532715, "global_step": 525529, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.018648386001587, "global_step": 525530, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.006409168243408, "global_step": 525531, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0897228717803955, "global_step": 525532, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.035468101501465, "global_step": 525533, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9915313720703125, "global_step": 525534, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.087122678756714, "global_step": 525535, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0464820861816406, "global_step": 525536, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0946693420410156, "global_step": 525537, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.017641544342041, "global_step": 525538, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0952742099761963, "global_step": 525539, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9746366739273071, "global_step": 525540, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9177923202514648, "global_step": 525541, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.112003803253174, "global_step": 525542, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0102062225341797, "global_step": 525543, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1591989994049072, "global_step": 525544, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0378620624542236, "global_step": 525545, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.055751085281372, "global_step": 525546, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.022139310836792, "global_step": 525547, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9953261613845825, "global_step": 525548, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.058903455734253, "global_step": 525549, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0715208053588867, "global_step": 525550, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9509694576263428, "global_step": 525551, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.962584137916565, "global_step": 525552, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0214381217956543, "global_step": 525553, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0401854515075684, "global_step": 525554, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1066582202911377, "global_step": 525555, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.092015027999878, "global_step": 525556, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0150668621063232, "global_step": 525557, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.035374879837036, "global_step": 525558, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1069023609161377, "global_step": 525559, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.049532175064087, "global_step": 525560, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9968440532684326, "global_step": 525561, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9725546836853027, "global_step": 525562, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0687777996063232, "global_step": 525563, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.918890357017517, "global_step": 525564, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0118179321289062, "global_step": 525565, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0695736408233643, "global_step": 525566, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.038360118865967, "global_step": 525567, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0838186740875244, "global_step": 525568, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.122868061065674, "global_step": 525569, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.022942304611206, "global_step": 525570, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9682741165161133, "global_step": 525571, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0452651977539062, "global_step": 525572, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1151740550994873, "global_step": 525573, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.049708604812622, "global_step": 525574, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.95753812789917, "global_step": 525575, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9985934495925903, "global_step": 525576, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.036154270172119, "global_step": 525577, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.081348180770874, "global_step": 525578, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1048710346221924, "global_step": 525579, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0530638694763184, "global_step": 525580, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.954166293144226, "global_step": 525581, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0243918895721436, "global_step": 525582, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.082014322280884, "global_step": 525583, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0171172618865967, "global_step": 525584, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9939298629760742, "global_step": 525585, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9885777235031128, "global_step": 525586, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.958966851234436, "global_step": 525587, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9973809719085693, "global_step": 525588, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1155457496643066, "global_step": 525589, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.048717975616455, "global_step": 525590, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0023372173309326, "global_step": 525591, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.98263680934906, "global_step": 525592, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.948782205581665, "global_step": 525593, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0189285278320312, "global_step": 525594, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0354857444763184, "global_step": 525595, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.079926013946533, "global_step": 525596, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.072808265686035, "global_step": 525597, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.083566427230835, "global_step": 525598, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0364773273468018, "global_step": 525599, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.062899351119995, "global_step": 525600, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0535247325897217, "global_step": 525601, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0420749187469482, "global_step": 525602, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0586249828338623, "global_step": 525603, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.020026445388794, "global_step": 525604, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.065631628036499, "global_step": 525605, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0740296840667725, "global_step": 525606, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1002559661865234, "global_step": 525607, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.033208131790161, "global_step": 525608, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0347273349761963, "global_step": 525609, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1595330238342285, "global_step": 525610, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0810086727142334, "global_step": 525611, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.088996648788452, "global_step": 525612, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0024313926696777, "global_step": 525613, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0376484394073486, "global_step": 525614, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0214197635650635, "global_step": 525615, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.039233446121216, "global_step": 525616, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.064873695373535, "global_step": 525617, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.119858980178833, "global_step": 525618, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.079798936843872, "global_step": 525619, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.159891128540039, "global_step": 525620, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9702415466308594, "global_step": 525621, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.083042621612549, "global_step": 525622, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.069626569747925, "global_step": 525623, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.015864133834839, "global_step": 525624, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.058159828186035, "global_step": 525625, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0304458141326904, "global_step": 525626, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.043635606765747, "global_step": 525627, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9919123649597168, "global_step": 525628, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.034522533416748, "global_step": 525629, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.135080099105835, "global_step": 525630, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0301239490509033, "global_step": 525631, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.086747646331787, "global_step": 525632, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.013650417327881, "global_step": 525633, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9899075031280518, "global_step": 525634, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.112071990966797, "global_step": 525635, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9638534784317017, "global_step": 525636, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9807791709899902, "global_step": 525637, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.080491304397583, "global_step": 525638, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.044163703918457, "global_step": 525639, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0956192016601562, "global_step": 525640, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.059596061706543, "global_step": 525641, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.167524576187134, "global_step": 525642, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.062051773071289, "global_step": 525643, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0072247982025146, "global_step": 525644, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0842742919921875, "global_step": 525645, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0591049194335938, "global_step": 525646, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0694358348846436, "global_step": 525647, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.002901554107666, "global_step": 525648, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1531200408935547, "global_step": 525649, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9803520441055298, "global_step": 525650, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0849287509918213, "global_step": 525651, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.019953727722168, "global_step": 525652, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.001241683959961, "global_step": 525653, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.08408260345459, "global_step": 525654, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0556232929229736, "global_step": 525655, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1539371013641357, "global_step": 525656, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9660899639129639, "global_step": 525657, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.051090955734253, "global_step": 525658, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.004876136779785, "global_step": 525659, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0539679527282715, "global_step": 525660, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.066012144088745, "global_step": 525661, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0516676902770996, "global_step": 525662, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0672860145568848, "global_step": 525663, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0714449882507324, "global_step": 525664, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9676973819732666, "global_step": 525665, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.09424090385437, "global_step": 525666, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.086867094039917, "global_step": 525667, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.116868019104004, "global_step": 525668, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9814497232437134, "global_step": 525669, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.007716178894043, "global_step": 525670, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.044506549835205, "global_step": 525671, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9765863418579102, "global_step": 525672, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0612993240356445, "global_step": 525673, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.961959958076477, "global_step": 525674, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.051206111907959, "global_step": 525675, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0434279441833496, "global_step": 525676, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.111820936203003, "global_step": 525677, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.060190200805664, "global_step": 525678, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0449252128601074, "global_step": 525679, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0197787284851074, "global_step": 525680, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9625424146652222, "global_step": 525681, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0826070308685303, "global_step": 525682, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0589325428009033, "global_step": 525683, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0097756385803223, "global_step": 525684, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0038044452667236, "global_step": 525685, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0683326721191406, "global_step": 525686, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0766305923461914, "global_step": 525687, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.037733554840088, "global_step": 525688, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0135374069213867, "global_step": 525689, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0417816638946533, "global_step": 525690, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.016737222671509, "global_step": 525691, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1338956356048584, "global_step": 525692, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0091378688812256, "global_step": 525693, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.092432975769043, "global_step": 525694, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.069934606552124, "global_step": 525695, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0509817600250244, "global_step": 525696, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.077528715133667, "global_step": 525697, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0016098022460938, "global_step": 525698, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.018605947494507, "global_step": 525699, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0100834369659424, "global_step": 525700, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.000330924987793, "global_step": 525701, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0403130054473877, "global_step": 525702, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0227880477905273, "global_step": 525703, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9743252992630005, "global_step": 525704, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.069716691970825, "global_step": 525705, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0292820930480957, "global_step": 525706, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.082415819168091, "global_step": 525707, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0032742023468018, "global_step": 525708, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.022880792617798, "global_step": 525709, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0348117351531982, "global_step": 525710, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.05794095993042, "global_step": 525711, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.957604169845581, "global_step": 525712, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0334322452545166, "global_step": 525713, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.987866759300232, "global_step": 525714, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9959608316421509, "global_step": 525715, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0798399448394775, "global_step": 525716, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0110719203948975, "global_step": 525717, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0083436965942383, "global_step": 525718, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.008906364440918, "global_step": 525719, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.087334156036377, "global_step": 525720, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.012454032897949, "global_step": 525721, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9823499917984009, "global_step": 525722, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.044945240020752, "global_step": 525723, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0884242057800293, "global_step": 525724, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.092559814453125, "global_step": 525725, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0270755290985107, "global_step": 525726, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.071629524230957, "global_step": 525727, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.101994514465332, "global_step": 525728, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9747096300125122, "global_step": 525729, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9677190780639648, "global_step": 525730, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0392730236053467, "global_step": 525731, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.026181936264038, "global_step": 525732, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.029961109161377, "global_step": 525733, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.971086859703064, "global_step": 525734, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9646822214126587, "global_step": 525735, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9490224123001099, "global_step": 525736, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.001401424407959, "global_step": 525737, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9919939041137695, "global_step": 525738, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9727786779403687, "global_step": 525739, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.207260847091675, "global_step": 525740, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9769806861877441, "global_step": 525741, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0285305976867676, "global_step": 525742, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.981454849243164, "global_step": 525743, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.049795389175415, "global_step": 525744, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0466091632843018, "global_step": 525745, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.03975510597229, "global_step": 525746, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.98469078540802, "global_step": 525747, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.129563093185425, "global_step": 525748, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.059691905975342, "global_step": 525749, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.951518177986145, "global_step": 525750, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.01444673538208, "global_step": 525751, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.035212755203247, "global_step": 525752, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0381650924682617, "global_step": 525753, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.051211357116699, "global_step": 525754, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0233356952667236, "global_step": 525755, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0480501651763916, "global_step": 525756, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9470256567001343, "global_step": 525757, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0685932636260986, "global_step": 525758, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9537675380706787, "global_step": 525759, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0194034576416016, "global_step": 525760, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0313966274261475, "global_step": 525761, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0675594806671143, "global_step": 525762, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9913008213043213, "global_step": 525763, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0315041542053223, "global_step": 525764, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1100878715515137, "global_step": 525765, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0353143215179443, "global_step": 525766, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0628280639648438, "global_step": 525767, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1510987281799316, "global_step": 525768, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0702147483825684, "global_step": 525769, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0505998134613037, "global_step": 525770, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0298852920532227, "global_step": 525771, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9233428239822388, "global_step": 525772, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.093640089035034, "global_step": 525773, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.033687114715576, "global_step": 525774, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0391812324523926, "global_step": 525775, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.099902868270874, "global_step": 525776, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9692751169204712, "global_step": 525777, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0658204555511475, "global_step": 525778, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.050229072570801, "global_step": 525779, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0729830265045166, "global_step": 525780, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0527267456054688, "global_step": 525781, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9799424409866333, "global_step": 525782, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0265696048736572, "global_step": 525783, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1022512912750244, "global_step": 525784, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.932625651359558, "global_step": 525785, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.081171989440918, "global_step": 525786, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1057231426239014, "global_step": 525787, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0768368244171143, "global_step": 525788, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9797921180725098, "global_step": 525789, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0612833499908447, "global_step": 525790, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.076835870742798, "global_step": 525791, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.104046583175659, "global_step": 525792, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0044808387756348, "global_step": 525793, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.02336049079895, "global_step": 525794, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0275681018829346, "global_step": 525795, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0343987941741943, "global_step": 525796, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0475356578826904, "global_step": 525797, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0499632358551025, "global_step": 525798, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.005262613296509, "global_step": 525799, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.139639139175415, "global_step": 525800, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.95854914188385, "global_step": 525801, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0318195819854736, "global_step": 525802, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9687632322311401, "global_step": 525803, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0737040042877197, "global_step": 525804, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.062007188796997, "global_step": 525805, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.079457998275757, "global_step": 525806, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.017484664916992, "global_step": 525807, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0231151580810547, "global_step": 525808, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9965041875839233, "global_step": 525809, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.012566089630127, "global_step": 525810, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.029949426651001, "global_step": 525811, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9367893934249878, "global_step": 525812, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1151628494262695, "global_step": 525813, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0661258697509766, "global_step": 525814, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0170164108276367, "global_step": 525815, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0278568267822266, "global_step": 525816, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.066304922103882, "global_step": 525817, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.026043176651001, "global_step": 525818, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9575313329696655, "global_step": 525819, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.06012225151062, "global_step": 525820, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.054868698120117, "global_step": 525821, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0341906547546387, "global_step": 525822, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0476832389831543, "global_step": 525823, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0760738849639893, "global_step": 525824, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9971565008163452, "global_step": 525825, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0299034118652344, "global_step": 525826, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0641067028045654, "global_step": 525827, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.026486396789551, "global_step": 525828, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0228271484375, "global_step": 525829, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0807950496673584, "global_step": 525830, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.003314256668091, "global_step": 525831, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.032813787460327, "global_step": 525832, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.136831760406494, "global_step": 525833, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0861732959747314, "global_step": 525834, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.052631139755249, "global_step": 525835, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1158299446105957, "global_step": 525836, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.056455612182617, "global_step": 525837, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.015397071838379, "global_step": 525838, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.070002794265747, "global_step": 525839, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0729124546051025, "global_step": 525840, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.051652193069458, "global_step": 525841, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0345940589904785, "global_step": 525842, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9626003503799438, "global_step": 525843, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.050740957260132, "global_step": 525844, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.001948118209839, "global_step": 525845, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0798728466033936, "global_step": 525846, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.061842203140259, "global_step": 525847, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0708155632019043, "global_step": 525848, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.991254210472107, "global_step": 525849, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9820655584335327, "global_step": 525850, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0652410984039307, "global_step": 525851, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.975382685661316, "global_step": 525852, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.116870164871216, "global_step": 525853, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9782520532608032, "global_step": 525854, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0444788932800293, "global_step": 525855, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.06942081451416, "global_step": 525856, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0158917903900146, "global_step": 525857, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.025420665740967, "global_step": 525858, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0977232456207275, "global_step": 525859, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9763085842132568, "global_step": 525860, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.083606719970703, "global_step": 525861, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0017683506011963, "global_step": 525862, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.07270884513855, "global_step": 525863, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0481927394866943, "global_step": 525864, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0274226665496826, "global_step": 525865, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0225419998168945, "global_step": 525866, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9995861053466797, "global_step": 525867, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.087663412094116, "global_step": 525868, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.975598931312561, "global_step": 525869, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.07790470123291, "global_step": 525870, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0331223011016846, "global_step": 525871, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9699766635894775, "global_step": 525872, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.090195417404175, "global_step": 525873, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9495295286178589, "global_step": 525874, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1483969688415527, "global_step": 525875, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1309120655059814, "global_step": 525876, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1950347423553467, "global_step": 525877, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0139200687408447, "global_step": 525878, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.045363187789917, "global_step": 525879, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9882681369781494, "global_step": 525880, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0186729431152344, "global_step": 525881, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9825479984283447, "global_step": 525882, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0300590991973877, "global_step": 525883, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9579157829284668, "global_step": 525884, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.04030179977417, "global_step": 525885, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0315256118774414, "global_step": 525886, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9871594905853271, "global_step": 525887, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.027808427810669, "global_step": 525888, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.067162036895752, "global_step": 525889, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1092419624328613, "global_step": 525890, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1230316162109375, "global_step": 525891, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9692069292068481, "global_step": 525892, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0935239791870117, "global_step": 525893, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9709959030151367, "global_step": 525894, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0499305725097656, "global_step": 525895, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.04815936088562, "global_step": 525896, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.05831241607666, "global_step": 525897, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0035078525543213, "global_step": 525898, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0457751750946045, "global_step": 525899, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.112753391265869, "global_step": 525900, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0338313579559326, "global_step": 525901, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.015861749649048, "global_step": 525902, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.073665142059326, "global_step": 525903, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1040680408477783, "global_step": 525904, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0107243061065674, "global_step": 525905, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0272743701934814, "global_step": 525906, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.059600591659546, "global_step": 525907, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0149986743927, "global_step": 525908, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.108219861984253, "global_step": 525909, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.00640606880188, "global_step": 525910, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.03369402885437, "global_step": 525911, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.075669527053833, "global_step": 525912, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.041388750076294, "global_step": 525913, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.11790132522583, "global_step": 525914, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0374767780303955, "global_step": 525915, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0755088329315186, "global_step": 525916, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.068835735321045, "global_step": 525917, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0600109100341797, "global_step": 525918, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9504504203796387, "global_step": 525919, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.978763461112976, "global_step": 525920, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.053708553314209, "global_step": 525921, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0715956687927246, "global_step": 525922, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9670053720474243, "global_step": 525923, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0433809757232666, "global_step": 525924, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.094508171081543, "global_step": 525925, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0745737552642822, "global_step": 525926, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.050208330154419, "global_step": 525927, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.034672498703003, "global_step": 525928, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0349550247192383, "global_step": 525929, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0474843978881836, "global_step": 525930, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0689752101898193, "global_step": 525931, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9986436367034912, "global_step": 525932, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.97360360622406, "global_step": 525933, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0182902812957764, "global_step": 525934, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9947720766067505, "global_step": 525935, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.10036301612854, "global_step": 525936, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0598936080932617, "global_step": 525937, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0345346927642822, "global_step": 525938, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0523548126220703, "global_step": 525939, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0403571128845215, "global_step": 525940, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9580107927322388, "global_step": 525941, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0941972732543945, "global_step": 525942, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0793347358703613, "global_step": 525943, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0467379093170166, "global_step": 525944, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.038419723510742, "global_step": 525945, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.059466600418091, "global_step": 525946, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1459097862243652, "global_step": 525947, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0772955417633057, "global_step": 525948, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0363807678222656, "global_step": 525949, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.061239004135132, "global_step": 525950, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.101732015609741, "global_step": 525951, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0222887992858887, "global_step": 525952, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0287203788757324, "global_step": 525953, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9908440113067627, "global_step": 525954, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0576627254486084, "global_step": 525955, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.148710250854492, "global_step": 525956, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0198018550872803, "global_step": 525957, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.075978994369507, "global_step": 525958, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9961122274398804, "global_step": 525959, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.003422975540161, "global_step": 525960, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9605859518051147, "global_step": 525961, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0759482383728027, "global_step": 525962, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9902715682983398, "global_step": 525963, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0179286003112793, "global_step": 525964, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.032949686050415, "global_step": 525965, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.067056894302368, "global_step": 525966, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9815627336502075, "global_step": 525967, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.046597480773926, "global_step": 525968, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.050964832305908, "global_step": 525969, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0354037284851074, "global_step": 525970, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.038376569747925, "global_step": 525971, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0962164402008057, "global_step": 525972, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0382559299468994, "global_step": 525973, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9642082452774048, "global_step": 525974, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0798115730285645, "global_step": 525975, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0261313915252686, "global_step": 525976, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.096390962600708, "global_step": 525977, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0692949295043945, "global_step": 525978, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.080570936203003, "global_step": 525979, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0282058715820312, "global_step": 525980, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.028841733932495, "global_step": 525981, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.084481954574585, "global_step": 525982, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0953445434570312, "global_step": 525983, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9488050937652588, "global_step": 525984, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.052065849304199, "global_step": 525985, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0159525871276855, "global_step": 525986, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9547832012176514, "global_step": 525987, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0298142433166504, "global_step": 525988, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0601792335510254, "global_step": 525989, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.141469717025757, "global_step": 525990, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.039740562438965, "global_step": 525991, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0314152240753174, "global_step": 525992, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.090040922164917, "global_step": 525993, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0242066383361816, "global_step": 525994, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.049302816390991, "global_step": 525995, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.944202184677124, "global_step": 525996, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0524425506591797, "global_step": 525997, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0475316047668457, "global_step": 525998, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9819196462631226, "global_step": 525999, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0629119873046875, "global_step": 526000, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0560269355773926, "global_step": 526001, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.114043712615967, "global_step": 526002, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0352890491485596, "global_step": 526003, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0400309562683105, "global_step": 526004, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9871976375579834, "global_step": 526005, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.981255054473877, "global_step": 526006, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1074953079223633, "global_step": 526007, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.958027720451355, "global_step": 526008, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.026747465133667, "global_step": 526009, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0911290645599365, "global_step": 526010, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0048234462738037, "global_step": 526011, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0435314178466797, "global_step": 526012, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.061239719390869, "global_step": 526013, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.12984561920166, "global_step": 526014, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0016586780548096, "global_step": 526015, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0821900367736816, "global_step": 526016, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.098886489868164, "global_step": 526017, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.072859525680542, "global_step": 526018, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0648224353790283, "global_step": 526019, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0631673336029053, "global_step": 526020, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.067173957824707, "global_step": 526021, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0710644721984863, "global_step": 526022, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1274917125701904, "global_step": 526023, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0486068725585938, "global_step": 526024, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0501770973205566, "global_step": 526025, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.967124581336975, "global_step": 526026, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.038604736328125, "global_step": 526027, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.068150043487549, "global_step": 526028, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.119971990585327, "global_step": 526029, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9909011125564575, "global_step": 526030, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0760180950164795, "global_step": 526031, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.085050106048584, "global_step": 526032, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.082183837890625, "global_step": 526033, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0923142433166504, "global_step": 526034, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.2143445014953613, "global_step": 526035, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.116595506668091, "global_step": 526036, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.067214012145996, "global_step": 526037, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9372859001159668, "global_step": 526038, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.094459295272827, "global_step": 526039, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.988789439201355, "global_step": 526040, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0581817626953125, "global_step": 526041, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1054670810699463, "global_step": 526042, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0604496002197266, "global_step": 526043, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.069058895111084, "global_step": 526044, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9984211921691895, "global_step": 526045, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.051142692565918, "global_step": 526046, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.013164520263672, "global_step": 526047, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0455520153045654, "global_step": 526048, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9319579601287842, "global_step": 526049, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0219411849975586, "global_step": 526050, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.057457685470581, "global_step": 526051, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0166232585906982, "global_step": 526052, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.079813241958618, "global_step": 526053, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0762109756469727, "global_step": 526054, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0777103900909424, "global_step": 526055, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.03314471244812, "global_step": 526056, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9299049377441406, "global_step": 526057, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.022590398788452, "global_step": 526058, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0527758598327637, "global_step": 526059, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9755200147628784, "global_step": 526060, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.019388437271118, "global_step": 526061, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1158335208892822, "global_step": 526062, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.034048557281494, "global_step": 526063, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.026221752166748, "global_step": 526064, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.999619960784912, "global_step": 526065, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0084173679351807, "global_step": 526066, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9733245372772217, "global_step": 526067, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1047000885009766, "global_step": 526068, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0882840156555176, "global_step": 526069, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.016228437423706, "global_step": 526070, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0791356563568115, "global_step": 526071, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0685153007507324, "global_step": 526072, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.00400447845459, "global_step": 526073, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.008256196975708, "global_step": 526074, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.132835865020752, "global_step": 526075, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.096214771270752, "global_step": 526076, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0889785289764404, "global_step": 526077, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0297162532806396, "global_step": 526078, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0278542041778564, "global_step": 526079, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.028428316116333, "global_step": 526080, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0244979858398438, "global_step": 526081, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0574145317077637, "global_step": 526082, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9802812337875366, "global_step": 526083, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.048694372177124, "global_step": 526084, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0736300945281982, "global_step": 526085, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.974959135055542, "global_step": 526086, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.002423048019409, "global_step": 526087, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.035266399383545, "global_step": 526088, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9805350303649902, "global_step": 526089, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.049476146697998, "global_step": 526090, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.048341751098633, "global_step": 526091, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0332839488983154, "global_step": 526092, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.13256573677063, "global_step": 526093, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.049276113510132, "global_step": 526094, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0657739639282227, "global_step": 526095, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0821046829223633, "global_step": 526096, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0172247886657715, "global_step": 526097, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0968987941741943, "global_step": 526098, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1359286308288574, "global_step": 526099, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0341994762420654, "global_step": 526100, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.05259370803833, "global_step": 526101, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0276541709899902, "global_step": 526102, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.035825252532959, "global_step": 526103, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9979097843170166, "global_step": 526104, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0051937103271484, "global_step": 526105, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.018745183944702, "global_step": 526106, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0137383937835693, "global_step": 526107, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0689218044281006, "global_step": 526108, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.036355972290039, "global_step": 526109, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0260608196258545, "global_step": 526110, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.032125949859619, "global_step": 526111, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.999371886253357, "global_step": 526112, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0470285415649414, "global_step": 526113, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.118295431137085, "global_step": 526114, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9855828285217285, "global_step": 526115, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0244598388671875, "global_step": 526116, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.021366834640503, "global_step": 526117, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0357062816619873, "global_step": 526118, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0433359146118164, "global_step": 526119, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0495948791503906, "global_step": 526120, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0212907791137695, "global_step": 526121, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.025419235229492, "global_step": 526122, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.036121129989624, "global_step": 526123, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.088168144226074, "global_step": 526124, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1082422733306885, "global_step": 526125, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0813448429107666, "global_step": 526126, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.051375389099121, "global_step": 526127, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.020986795425415, "global_step": 526128, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0566601753234863, "global_step": 526129, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0356271266937256, "global_step": 526130, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0602574348449707, "global_step": 526131, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0428333282470703, "global_step": 526132, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.092844009399414, "global_step": 526133, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.091498374938965, "global_step": 526134, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.110520362854004, "global_step": 526135, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.958517074584961, "global_step": 526136, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0641136169433594, "global_step": 526137, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9867589473724365, "global_step": 526138, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0772833824157715, "global_step": 526139, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0706071853637695, "global_step": 526140, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0441863536834717, "global_step": 526141, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1332263946533203, "global_step": 526142, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9942785501480103, "global_step": 526143, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.086560010910034, "global_step": 526144, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.019979953765869, "global_step": 526145, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0565969944000244, "global_step": 526146, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9808974266052246, "global_step": 526147, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9820586442947388, "global_step": 526148, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.027419090270996, "global_step": 526149, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0605573654174805, "global_step": 526150, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.08718204498291, "global_step": 526151, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.008479595184326, "global_step": 526152, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9841021299362183, "global_step": 526153, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1971378326416016, "global_step": 526154, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9993475675582886, "global_step": 526155, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.091989278793335, "global_step": 526156, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0278098583221436, "global_step": 526157, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0718414783477783, "global_step": 526158, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.012573480606079, "global_step": 526159, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.059231996536255, "global_step": 526160, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.043550729751587, "global_step": 526161, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0494797229766846, "global_step": 526162, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0575969219207764, "global_step": 526163, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0412466526031494, "global_step": 526164, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0944316387176514, "global_step": 526165, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0368330478668213, "global_step": 526166, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.082970142364502, "global_step": 526167, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.007235288619995, "global_step": 526168, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0428121089935303, "global_step": 526169, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.083017349243164, "global_step": 526170, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0570507049560547, "global_step": 526171, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.95809805393219, "global_step": 526172, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1512584686279297, "global_step": 526173, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0328705310821533, "global_step": 526174, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1244559288024902, "global_step": 526175, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0590569972991943, "global_step": 526176, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.100226879119873, "global_step": 526177, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9931920766830444, "global_step": 526178, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0260732173919678, "global_step": 526179, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1152145862579346, "global_step": 526180, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0332448482513428, "global_step": 526181, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0340723991394043, "global_step": 526182, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9521583318710327, "global_step": 526183, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.057478666305542, "global_step": 526184, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9826006889343262, "global_step": 526185, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0602364540100098, "global_step": 526186, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0500500202178955, "global_step": 526187, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.035097122192383, "global_step": 526188, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9829832315444946, "global_step": 526189, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.039691209793091, "global_step": 526190, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0849530696868896, "global_step": 526191, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.049546003341675, "global_step": 526192, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.021543025970459, "global_step": 526193, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0293309688568115, "global_step": 526194, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1114747524261475, "global_step": 526195, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0319955348968506, "global_step": 526196, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.034174919128418, "global_step": 526197, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9878356456756592, "global_step": 526198, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.060368776321411, "global_step": 526199, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0745294094085693, "global_step": 526200, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0919761657714844, "global_step": 526201, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9708991050720215, "global_step": 526202, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0643365383148193, "global_step": 526203, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0228583812713623, "global_step": 526204, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.981609582901001, "global_step": 526205, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0747435092926025, "global_step": 526206, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.052685022354126, "global_step": 526207, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.113755226135254, "global_step": 526208, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0138139724731445, "global_step": 526209, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.992621898651123, "global_step": 526210, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0663294792175293, "global_step": 526211, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1483044624328613, "global_step": 526212, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0906174182891846, "global_step": 526213, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0873587131500244, "global_step": 526214, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.147908926010132, "global_step": 526215, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0537915229797363, "global_step": 526216, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0402605533599854, "global_step": 526217, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0249619483947754, "global_step": 526218, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.06371808052063, "global_step": 526219, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.029944658279419, "global_step": 526220, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0474164485931396, "global_step": 526221, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0950255393981934, "global_step": 526222, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0653364658355713, "global_step": 526223, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.981902003288269, "global_step": 526224, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0427560806274414, "global_step": 526225, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1833927631378174, "global_step": 526226, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0976309776306152, "global_step": 526227, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9602049589157104, "global_step": 526228, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0497257709503174, "global_step": 526229, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0782628059387207, "global_step": 526230, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0322108268737793, "global_step": 526231, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0701169967651367, "global_step": 526232, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1125648021698, "global_step": 526233, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1173758506774902, "global_step": 526234, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9593915939331055, "global_step": 526235, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.100343942642212, "global_step": 526236, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0550167560577393, "global_step": 526237, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9975826740264893, "global_step": 526238, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.024132490158081, "global_step": 526239, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1204092502593994, "global_step": 526240, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0571181774139404, "global_step": 526241, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0415377616882324, "global_step": 526242, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.98526930809021, "global_step": 526243, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1085445880889893, "global_step": 526244, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9783316850662231, "global_step": 526245, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9823657274246216, "global_step": 526246, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.12753963470459, "global_step": 526247, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0564796924591064, "global_step": 526248, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.005882978439331, "global_step": 526249, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.016981363296509, "global_step": 526250, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0182108879089355, "global_step": 526251, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.025766372680664, "global_step": 526252, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0881052017211914, "global_step": 526253, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9475774765014648, "global_step": 526254, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0754029750823975, "global_step": 526255, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.062490463256836, "global_step": 526256, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.042983055114746, "global_step": 526257, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.030949592590332, "global_step": 526258, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0144026279449463, "global_step": 526259, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.000262975692749, "global_step": 526260, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.941246509552002, "global_step": 526261, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.059236526489258, "global_step": 526262, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1415493488311768, "global_step": 526263, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.055144786834717, "global_step": 526264, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0422592163085938, "global_step": 526265, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.076792001724243, "global_step": 526266, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0462560653686523, "global_step": 526267, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1539974212646484, "global_step": 526268, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.05118727684021, "global_step": 526269, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0252797603607178, "global_step": 526270, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0762829780578613, "global_step": 526271, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.056549310684204, "global_step": 526272, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0123300552368164, "global_step": 526273, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.090489625930786, "global_step": 526274, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0431456565856934, "global_step": 526275, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0454821586608887, "global_step": 526276, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0512304306030273, "global_step": 526277, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0397439002990723, "global_step": 526278, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9652727842330933, "global_step": 526279, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0844051837921143, "global_step": 526280, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.07995867729187, "global_step": 526281, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1132960319519043, "global_step": 526282, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0096609592437744, "global_step": 526283, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0915944576263428, "global_step": 526284, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.9206037521362305, "global_step": 526285, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.045651435852051, "global_step": 526286, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.066089153289795, "global_step": 526287, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0343570709228516, "global_step": 526288, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0746572017669678, "global_step": 526289, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0349018573760986, "global_step": 526290, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.09468936920166, "global_step": 526291, "epoch": 892, "lr": 5e-05}
{"train_loss": 1.979087233543396, "global_step": 526292, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0512139797210693, "global_step": 526293, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.057100296020508, "global_step": 526294, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.1731762886047363, "global_step": 526295, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0379340648651123, "global_step": 526296, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0066003799438477, "global_step": 526297, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.031604290008545, "global_step": 526298, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.041088342666626, "global_step": 526299, "epoch": 892, "lr": 5e-05}
{"train_loss": 2.0016438961029053, "global_step": 526300, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.005601644515991, "global_step": 526301, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.08756947517395, "global_step": 526302, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9760805368423462, "global_step": 526303, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.019991874694824, "global_step": 526304, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.961558222770691, "global_step": 526305, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0443379878997803, "global_step": 526306, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9633346796035767, "global_step": 526307, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0231900215148926, "global_step": 526308, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.057617664337158, "global_step": 526309, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9900609254837036, "global_step": 526310, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0565967559814453, "global_step": 526311, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0616822242736816, "global_step": 526312, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9584872722625732, "global_step": 526313, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.056865692138672, "global_step": 526314, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0644428730010986, "global_step": 526315, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.025676727294922, "global_step": 526316, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.029313564300537, "global_step": 526317, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9950183629989624, "global_step": 526318, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0451929569244385, "global_step": 526319, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1306264400482178, "global_step": 526320, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.00532603263855, "global_step": 526321, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.059986114501953, "global_step": 526322, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9826464653015137, "global_step": 526323, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9717479944229126, "global_step": 526324, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0196166038513184, "global_step": 526325, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0284605026245117, "global_step": 526326, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.922098159790039, "global_step": 526327, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.093904733657837, "global_step": 526328, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.068328857421875, "global_step": 526329, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0438883304595947, "global_step": 526330, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9796298742294312, "global_step": 526331, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9886438846588135, "global_step": 526332, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.067617177963257, "global_step": 526333, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.072540283203125, "global_step": 526334, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9268252849578857, "global_step": 526335, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9850459098815918, "global_step": 526336, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1053380966186523, "global_step": 526337, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0401222705841064, "global_step": 526338, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.030174493789673, "global_step": 526339, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0500152111053467, "global_step": 526340, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.998177170753479, "global_step": 526341, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0371594429016113, "global_step": 526342, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.095738410949707, "global_step": 526343, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.063596487045288, "global_step": 526344, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.081669330596924, "global_step": 526345, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.993523359298706, "global_step": 526346, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.998392105102539, "global_step": 526347, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1189966201782227, "global_step": 526348, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9586237668991089, "global_step": 526349, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9958416223526, "global_step": 526350, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.026512384414673, "global_step": 526351, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.147800922393799, "global_step": 526352, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.056436061859131, "global_step": 526353, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.026149034500122, "global_step": 526354, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.01906418800354, "global_step": 526355, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9815770387649536, "global_step": 526356, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.999943494796753, "global_step": 526357, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9896352291107178, "global_step": 526358, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0074687004089355, "global_step": 526359, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.08801007270813, "global_step": 526360, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0061233043670654, "global_step": 526361, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0770750045776367, "global_step": 526362, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9803749322891235, "global_step": 526363, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0555026531219482, "global_step": 526364, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0922367572784424, "global_step": 526365, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.026081085205078, "global_step": 526366, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9736922979354858, "global_step": 526367, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0182149410247803, "global_step": 526368, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.009996175765991, "global_step": 526369, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9834933280944824, "global_step": 526370, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.044105052947998, "global_step": 526371, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0683562755584717, "global_step": 526372, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.040161609649658, "global_step": 526373, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.06363844871521, "global_step": 526374, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0404748916625977, "global_step": 526375, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0778284072875977, "global_step": 526376, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.081407070159912, "global_step": 526377, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.058406352996826, "global_step": 526378, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.030942678451538, "global_step": 526379, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.037865161895752, "global_step": 526380, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.08396315574646, "global_step": 526381, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0099902153015137, "global_step": 526382, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9456567764282227, "global_step": 526383, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9698312282562256, "global_step": 526384, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1420397758483887, "global_step": 526385, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.132155179977417, "global_step": 526386, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.014254331588745, "global_step": 526387, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.096313714981079, "global_step": 526388, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.069498300552368, "global_step": 526389, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.026416063308716, "global_step": 526390, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1014156341552734, "global_step": 526391, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0699496269226074, "global_step": 526392, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0351920127868652, "global_step": 526393, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9411308765411377, "global_step": 526394, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.089789390563965, "global_step": 526395, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.947282075881958, "global_step": 526396, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9339812994003296, "global_step": 526397, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0647711753845215, "global_step": 526398, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9669370651245117, "global_step": 526399, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9558266401290894, "global_step": 526400, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9603744745254517, "global_step": 526401, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0343410968780518, "global_step": 526402, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0226454734802246, "global_step": 526403, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0128774642944336, "global_step": 526404, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.088468313217163, "global_step": 526405, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9814414978027344, "global_step": 526406, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0682709217071533, "global_step": 526407, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.005511999130249, "global_step": 526408, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.931419014930725, "global_step": 526409, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0804905891418457, "global_step": 526410, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.08412504196167, "global_step": 526411, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.062824010848999, "global_step": 526412, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0543885231018066, "global_step": 526413, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.008422613143921, "global_step": 526414, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.014493942260742, "global_step": 526415, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.080648422241211, "global_step": 526416, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9998033046722412, "global_step": 526417, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.018213987350464, "global_step": 526418, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0202999114990234, "global_step": 526419, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0140161514282227, "global_step": 526420, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0111770629882812, "global_step": 526421, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0376055240631104, "global_step": 526422, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0893807411193848, "global_step": 526423, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9738150835037231, "global_step": 526424, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9970207214355469, "global_step": 526425, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.063241481781006, "global_step": 526426, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1031322479248047, "global_step": 526427, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.008070468902588, "global_step": 526428, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0427889823913574, "global_step": 526429, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9863369464874268, "global_step": 526430, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9446181058883667, "global_step": 526431, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.140028715133667, "global_step": 526432, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0113508701324463, "global_step": 526433, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.056122303009033, "global_step": 526434, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.055162191390991, "global_step": 526435, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.081148386001587, "global_step": 526436, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9461668729782104, "global_step": 526437, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.049772024154663, "global_step": 526438, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.029994010925293, "global_step": 526439, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.085963010787964, "global_step": 526440, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.00607967376709, "global_step": 526441, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0388612747192383, "global_step": 526442, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.05818772315979, "global_step": 526443, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0000298023223877, "global_step": 526444, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0757124423980713, "global_step": 526445, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.981511116027832, "global_step": 526446, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.998333215713501, "global_step": 526447, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0108046531677246, "global_step": 526448, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9753823280334473, "global_step": 526449, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0929760932922363, "global_step": 526450, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.8772015571594238, "global_step": 526451, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0165371894836426, "global_step": 526452, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9891341924667358, "global_step": 526453, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0281054973602295, "global_step": 526454, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0415050983428955, "global_step": 526455, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0386831760406494, "global_step": 526456, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1045804023742676, "global_step": 526457, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0022997856140137, "global_step": 526458, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0158395767211914, "global_step": 526459, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.105191469192505, "global_step": 526460, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1068108081817627, "global_step": 526461, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.045036554336548, "global_step": 526462, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.064192056655884, "global_step": 526463, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9769667387008667, "global_step": 526464, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9771738052368164, "global_step": 526465, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.093837261199951, "global_step": 526466, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.046957015991211, "global_step": 526467, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0212364196777344, "global_step": 526468, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.046015977859497, "global_step": 526469, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0255849361419678, "global_step": 526470, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.072953939437866, "global_step": 526471, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0141441822052, "global_step": 526472, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0435123443603516, "global_step": 526473, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.024355173110962, "global_step": 526474, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.043013572692871, "global_step": 526475, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.016361951828003, "global_step": 526476, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.007967233657837, "global_step": 526477, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9552040100097656, "global_step": 526478, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0202646255493164, "global_step": 526479, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.005990505218506, "global_step": 526480, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.067267417907715, "global_step": 526481, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0286831855773926, "global_step": 526482, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0493671894073486, "global_step": 526483, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.034090518951416, "global_step": 526484, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.028472900390625, "global_step": 526485, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9852858781814575, "global_step": 526486, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0695390701293945, "global_step": 526487, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1089322566986084, "global_step": 526488, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0724823474884033, "global_step": 526489, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9870513677597046, "global_step": 526490, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0604166984558105, "global_step": 526491, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.023113250732422, "global_step": 526492, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.962682843208313, "global_step": 526493, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.025292158126831, "global_step": 526494, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.041109085083008, "global_step": 526495, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0701169967651367, "global_step": 526496, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.069535255432129, "global_step": 526497, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.056591033935547, "global_step": 526498, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9675089120864868, "global_step": 526499, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9811276197433472, "global_step": 526500, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0867416858673096, "global_step": 526501, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0091607570648193, "global_step": 526502, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9965405464172363, "global_step": 526503, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.03377366065979, "global_step": 526504, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9758657217025757, "global_step": 526505, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.101309299468994, "global_step": 526506, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.910845398902893, "global_step": 526507, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.07444429397583, "global_step": 526508, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0263633728027344, "global_step": 526509, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.043999671936035, "global_step": 526510, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.929344892501831, "global_step": 526511, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9762822389602661, "global_step": 526512, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.030003070831299, "global_step": 526513, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1065406799316406, "global_step": 526514, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9278028011322021, "global_step": 526515, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0769221782684326, "global_step": 526516, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9965020418167114, "global_step": 526517, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.093907594680786, "global_step": 526518, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.017083168029785, "global_step": 526519, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9773764610290527, "global_step": 526520, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0861382484436035, "global_step": 526521, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1062119007110596, "global_step": 526522, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1203365325927734, "global_step": 526523, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.020193338394165, "global_step": 526524, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0935778617858887, "global_step": 526525, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9785369634628296, "global_step": 526526, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0660240650177, "global_step": 526527, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0915768146514893, "global_step": 526528, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.081580638885498, "global_step": 526529, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.103468418121338, "global_step": 526530, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9761013984680176, "global_step": 526531, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9645230770111084, "global_step": 526532, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.047941207885742, "global_step": 526533, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.96230947971344, "global_step": 526534, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9965311288833618, "global_step": 526535, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.035268783569336, "global_step": 526536, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0164177417755127, "global_step": 526537, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.028888702392578, "global_step": 526538, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.063100814819336, "global_step": 526539, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.062079906463623, "global_step": 526540, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0244927406311035, "global_step": 526541, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.964983344078064, "global_step": 526542, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9978920221328735, "global_step": 526543, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9388928413391113, "global_step": 526544, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0370757579803467, "global_step": 526545, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0048627853393555, "global_step": 526546, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9904814958572388, "global_step": 526547, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0255541801452637, "global_step": 526548, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9792790412902832, "global_step": 526549, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.993880033493042, "global_step": 526550, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9809350967407227, "global_step": 526551, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9860841035842896, "global_step": 526552, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9964731931686401, "global_step": 526553, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0785510540008545, "global_step": 526554, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.091003179550171, "global_step": 526555, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9585341215133667, "global_step": 526556, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.085170030593872, "global_step": 526557, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.944697618484497, "global_step": 526558, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.966941475868225, "global_step": 526559, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0628185272216797, "global_step": 526560, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9732171297073364, "global_step": 526561, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.069422960281372, "global_step": 526562, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.127258539199829, "global_step": 526563, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.045558214187622, "global_step": 526564, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9825749397277832, "global_step": 526565, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.993512511253357, "global_step": 526566, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0766420364379883, "global_step": 526567, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0639147758483887, "global_step": 526568, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.99951171875, "global_step": 526569, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0564520359039307, "global_step": 526570, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.036673069000244, "global_step": 526571, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0035295486450195, "global_step": 526572, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.071269989013672, "global_step": 526573, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.090468406677246, "global_step": 526574, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9743931293487549, "global_step": 526575, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0940804481506348, "global_step": 526576, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.029453992843628, "global_step": 526577, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0193419456481934, "global_step": 526578, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0971615314483643, "global_step": 526579, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.066890001296997, "global_step": 526580, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0751404762268066, "global_step": 526581, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9703354835510254, "global_step": 526582, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9814306497573853, "global_step": 526583, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9770945310592651, "global_step": 526584, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0176522731781006, "global_step": 526585, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0435078144073486, "global_step": 526586, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0131280422210693, "global_step": 526587, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.036086320877075, "global_step": 526588, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.039783000946045, "global_step": 526589, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0383944511413574, "global_step": 526590, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.010035514831543, "global_step": 526591, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9766525030136108, "global_step": 526592, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0172500610351562, "global_step": 526593, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.070326566696167, "global_step": 526594, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1453053951263428, "global_step": 526595, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0068628787994385, "global_step": 526596, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0292115211486816, "global_step": 526597, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0392093658447266, "global_step": 526598, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1004419326782227, "global_step": 526599, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.950295090675354, "global_step": 526600, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.071700096130371, "global_step": 526601, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9842045307159424, "global_step": 526602, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.021808385848999, "global_step": 526603, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0279626846313477, "global_step": 526604, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0312578678131104, "global_step": 526605, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9790118932724, "global_step": 526606, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0464203357696533, "global_step": 526607, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0957818031311035, "global_step": 526608, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0575997829437256, "global_step": 526609, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9777238368988037, "global_step": 526610, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.101712703704834, "global_step": 526611, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1004974842071533, "global_step": 526612, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.085928440093994, "global_step": 526613, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0904746055603027, "global_step": 526614, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.934524655342102, "global_step": 526615, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0242156982421875, "global_step": 526616, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0595669746398926, "global_step": 526617, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0320773124694824, "global_step": 526618, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0772695541381836, "global_step": 526619, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.113419532775879, "global_step": 526620, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0640041828155518, "global_step": 526621, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.008643627166748, "global_step": 526622, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9716404676437378, "global_step": 526623, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.045814275741577, "global_step": 526624, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1027262210845947, "global_step": 526625, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.052182197570801, "global_step": 526626, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0524866580963135, "global_step": 526627, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.012253761291504, "global_step": 526628, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9969271421432495, "global_step": 526629, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0806984901428223, "global_step": 526630, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0860042572021484, "global_step": 526631, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0497922897338867, "global_step": 526632, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9827778339385986, "global_step": 526633, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0956242084503174, "global_step": 526634, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.006720542907715, "global_step": 526635, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.014775276184082, "global_step": 526636, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.013176918029785, "global_step": 526637, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0914394855499268, "global_step": 526638, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.032444477081299, "global_step": 526639, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0523910522460938, "global_step": 526640, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9732775688171387, "global_step": 526641, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1027517318725586, "global_step": 526642, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0704233646392822, "global_step": 526643, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.000173568725586, "global_step": 526644, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.960188627243042, "global_step": 526645, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.931554913520813, "global_step": 526646, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.073397636413574, "global_step": 526647, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0285825729370117, "global_step": 526648, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.045663356781006, "global_step": 526649, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0598578453063965, "global_step": 526650, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.049386739730835, "global_step": 526651, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9921612739562988, "global_step": 526652, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.051248550415039, "global_step": 526653, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.016791343688965, "global_step": 526654, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.014669179916382, "global_step": 526655, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.000636100769043, "global_step": 526656, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0632457733154297, "global_step": 526657, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.052319049835205, "global_step": 526658, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.090268850326538, "global_step": 526659, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.01422119140625, "global_step": 526660, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0602478981018066, "global_step": 526661, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0498104095458984, "global_step": 526662, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.039574146270752, "global_step": 526663, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1419527530670166, "global_step": 526664, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0488085746765137, "global_step": 526665, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.124441623687744, "global_step": 526666, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9697113037109375, "global_step": 526667, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.017242193222046, "global_step": 526668, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0860776901245117, "global_step": 526669, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9376002550125122, "global_step": 526670, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.131157875061035, "global_step": 526671, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9784104824066162, "global_step": 526672, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0162193775177, "global_step": 526673, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.010052442550659, "global_step": 526674, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0984435081481934, "global_step": 526675, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.019523859024048, "global_step": 526676, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0312862396240234, "global_step": 526677, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0915610790252686, "global_step": 526678, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.969524621963501, "global_step": 526679, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0149831771850586, "global_step": 526680, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0057411193847656, "global_step": 526681, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.048898935317993, "global_step": 526682, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0699100494384766, "global_step": 526683, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9903095960617065, "global_step": 526684, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.093271017074585, "global_step": 526685, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9207324981689453, "global_step": 526686, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1240599155426025, "global_step": 526687, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9991047382354736, "global_step": 526688, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.051844835281372, "global_step": 526689, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0183444023132324, "global_step": 526690, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0432398319244385, "global_step": 526691, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0489296913146973, "global_step": 526692, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1909103393554688, "global_step": 526693, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9835351705551147, "global_step": 526694, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0214157104492188, "global_step": 526695, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.068549394607544, "global_step": 526696, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.049989700317383, "global_step": 526697, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.091662883758545, "global_step": 526698, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.017920970916748, "global_step": 526699, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9565184116363525, "global_step": 526700, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0465948581695557, "global_step": 526701, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.969616413116455, "global_step": 526702, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0651538372039795, "global_step": 526703, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.063124656677246, "global_step": 526704, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0990841388702393, "global_step": 526705, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1610169410705566, "global_step": 526706, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1874501705169678, "global_step": 526707, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0669608116149902, "global_step": 526708, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0742347240448, "global_step": 526709, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.117236375808716, "global_step": 526710, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9834518432617188, "global_step": 526711, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.063187837600708, "global_step": 526712, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.06514310836792, "global_step": 526713, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0033578872680664, "global_step": 526714, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.03489089012146, "global_step": 526715, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0004241466522217, "global_step": 526716, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9802876710891724, "global_step": 526717, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.059465169906616, "global_step": 526718, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1616766452789307, "global_step": 526719, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.057114601135254, "global_step": 526720, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0222976207733154, "global_step": 526721, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1254799365997314, "global_step": 526722, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9974000453948975, "global_step": 526723, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0976908206939697, "global_step": 526724, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.039931297302246, "global_step": 526725, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.093374729156494, "global_step": 526726, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0332119464874268, "global_step": 526727, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0923264026641846, "global_step": 526728, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9978933334350586, "global_step": 526729, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.026136636734009, "global_step": 526730, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0082459449768066, "global_step": 526731, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0210018157958984, "global_step": 526732, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0673880577087402, "global_step": 526733, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9777783155441284, "global_step": 526734, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.107205629348755, "global_step": 526735, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.095824956893921, "global_step": 526736, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1609086990356445, "global_step": 526737, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.029651165008545, "global_step": 526738, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.125818967819214, "global_step": 526739, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.080322742462158, "global_step": 526740, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0928125381469727, "global_step": 526741, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0385406017303467, "global_step": 526742, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0895590782165527, "global_step": 526743, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9924818277359009, "global_step": 526744, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0551812648773193, "global_step": 526745, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1258976459503174, "global_step": 526746, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.968111515045166, "global_step": 526747, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.014889717102051, "global_step": 526748, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.094292402267456, "global_step": 526749, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9628695249557495, "global_step": 526750, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0102343559265137, "global_step": 526751, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.094604969024658, "global_step": 526752, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9954214096069336, "global_step": 526753, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0042648315429688, "global_step": 526754, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9935966730117798, "global_step": 526755, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0429317951202393, "global_step": 526756, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.162353992462158, "global_step": 526757, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9946662187576294, "global_step": 526758, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9892349243164062, "global_step": 526759, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1191508769989014, "global_step": 526760, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.077631711959839, "global_step": 526761, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9812525510787964, "global_step": 526762, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.105456590652466, "global_step": 526763, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0759177207946777, "global_step": 526764, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9940545558929443, "global_step": 526765, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.068962574005127, "global_step": 526766, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9382661581039429, "global_step": 526767, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.015608549118042, "global_step": 526768, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0280516147613525, "global_step": 526769, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1015985012054443, "global_step": 526770, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.018380880355835, "global_step": 526771, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0794355869293213, "global_step": 526772, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9562205076217651, "global_step": 526773, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0364556312561035, "global_step": 526774, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0429749488830566, "global_step": 526775, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0387799739837646, "global_step": 526776, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0040805339813232, "global_step": 526777, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.00907826423645, "global_step": 526778, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0813465118408203, "global_step": 526779, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9734430313110352, "global_step": 526780, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.009960412979126, "global_step": 526781, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.997092843055725, "global_step": 526782, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0910892486572266, "global_step": 526783, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0858592987060547, "global_step": 526784, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.020202159881592, "global_step": 526785, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0536954402923584, "global_step": 526786, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0610759258270264, "global_step": 526787, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0571742057800293, "global_step": 526788, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0116384029388428, "global_step": 526789, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9566106796264648, "global_step": 526790, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0288002490997314, "global_step": 526791, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.049264907836914, "global_step": 526792, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1114068031311035, "global_step": 526793, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.010974884033203, "global_step": 526794, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.038485527038574, "global_step": 526795, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1084587574005127, "global_step": 526796, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0633628368377686, "global_step": 526797, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0203471183776855, "global_step": 526798, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.095400094985962, "global_step": 526799, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.044445514678955, "global_step": 526800, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.936476469039917, "global_step": 526801, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0047600269317627, "global_step": 526802, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.027679920196533, "global_step": 526803, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.984612226486206, "global_step": 526804, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9972221851348877, "global_step": 526805, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1004951000213623, "global_step": 526806, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0546298027038574, "global_step": 526807, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0261118412017822, "global_step": 526808, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0476129055023193, "global_step": 526809, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0719966888427734, "global_step": 526810, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0268373489379883, "global_step": 526811, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.103610038757324, "global_step": 526812, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0079526901245117, "global_step": 526813, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.061680555343628, "global_step": 526814, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.005110740661621, "global_step": 526815, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.037130355834961, "global_step": 526816, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1020429134368896, "global_step": 526817, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1325347423553467, "global_step": 526818, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.02329158782959, "global_step": 526819, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.008385181427002, "global_step": 526820, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0948383808135986, "global_step": 526821, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.009519100189209, "global_step": 526822, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0228946208953857, "global_step": 526823, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9694769382476807, "global_step": 526824, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.045670986175537, "global_step": 526825, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9763572216033936, "global_step": 526826, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.071518659591675, "global_step": 526827, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1317360401153564, "global_step": 526828, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.023496389389038, "global_step": 526829, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9944591522216797, "global_step": 526830, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.007660150527954, "global_step": 526831, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0954599380493164, "global_step": 526832, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.090153694152832, "global_step": 526833, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.079909324645996, "global_step": 526834, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9654070138931274, "global_step": 526835, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0835044384002686, "global_step": 526836, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0063304901123047, "global_step": 526837, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9525026082992554, "global_step": 526838, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9886234998703003, "global_step": 526839, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.038146734237671, "global_step": 526840, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9707316160202026, "global_step": 526841, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9846516847610474, "global_step": 526842, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1094796657562256, "global_step": 526843, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0585598945617676, "global_step": 526844, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0487115383148193, "global_step": 526845, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0867111682891846, "global_step": 526846, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.057925224304199, "global_step": 526847, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1243159770965576, "global_step": 526848, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0662097930908203, "global_step": 526849, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0038185119628906, "global_step": 526850, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9683117866516113, "global_step": 526851, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9964628219604492, "global_step": 526852, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0374562740325928, "global_step": 526853, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.077300786972046, "global_step": 526854, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.117807149887085, "global_step": 526855, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.096623659133911, "global_step": 526856, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0421950817108154, "global_step": 526857, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.059323310852051, "global_step": 526858, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.102389097213745, "global_step": 526859, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1177990436553955, "global_step": 526860, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.015946388244629, "global_step": 526861, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0520293712615967, "global_step": 526862, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1019623279571533, "global_step": 526863, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0515687465667725, "global_step": 526864, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1424190998077393, "global_step": 526865, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.04221773147583, "global_step": 526866, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.079106330871582, "global_step": 526867, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.025820255279541, "global_step": 526868, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0591580867767334, "global_step": 526869, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.030524730682373, "global_step": 526870, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1143300533294678, "global_step": 526871, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.958366870880127, "global_step": 526872, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.10115385055542, "global_step": 526873, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.01326584815979, "global_step": 526874, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0349361896514893, "global_step": 526875, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.047001838684082, "global_step": 526876, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9383478164672852, "global_step": 526877, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.021733522415161, "global_step": 526878, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.088479518890381, "global_step": 526879, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0263092517852783, "global_step": 526880, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0097389221191406, "global_step": 526881, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0457165241241455, "global_step": 526882, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.013270139694214, "global_step": 526883, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0880684852600098, "global_step": 526884, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9622410535812378, "global_step": 526885, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.101518392562866, "global_step": 526886, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.105482339859009, "global_step": 526887, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9830610752105713, "global_step": 526888, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0551300048828125, "global_step": 526889, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9515563249588013, "global_step": 526890, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.021904230117798, "global_step": 526891, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0182559490203857, "global_step": 526892, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9486770629882812, "global_step": 526893, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0693519115448, "global_step": 526894, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.047426462173462, "global_step": 526895, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0954513549804688, "global_step": 526896, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9747552871704102, "global_step": 526897, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9845069646835327, "global_step": 526898, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0323407649993896, "global_step": 526899, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0219204425811768, "global_step": 526900, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9396934509277344, "global_step": 526901, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1349260807037354, "global_step": 526902, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0298385620117188, "global_step": 526903, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.920784592628479, "global_step": 526904, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9839987754821777, "global_step": 526905, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0308995246887207, "global_step": 526906, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0583488941192627, "global_step": 526907, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0769922733306885, "global_step": 526908, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.121137857437134, "global_step": 526909, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9910860061645508, "global_step": 526910, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0019774436950684, "global_step": 526911, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1346781253814697, "global_step": 526912, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1253268718719482, "global_step": 526913, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0942022800445557, "global_step": 526914, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0468029975891113, "global_step": 526915, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.106834650039673, "global_step": 526916, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0916218757629395, "global_step": 526917, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0557358264923096, "global_step": 526918, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1199588775634766, "global_step": 526919, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9787677526474, "global_step": 526920, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1366279125213623, "global_step": 526921, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0336039066314697, "global_step": 526922, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0559136867523193, "global_step": 526923, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.030707359313965, "global_step": 526924, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0271499156951904, "global_step": 526925, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0388290882110596, "global_step": 526926, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9591447114944458, "global_step": 526927, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1046032905578613, "global_step": 526928, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.084209442138672, "global_step": 526929, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.123183488845825, "global_step": 526930, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0732877254486084, "global_step": 526931, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.104351282119751, "global_step": 526932, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.932924747467041, "global_step": 526933, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.016932487487793, "global_step": 526934, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.086622476577759, "global_step": 526935, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0082406997680664, "global_step": 526936, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.073413848876953, "global_step": 526937, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9910980463027954, "global_step": 526938, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.050072431564331, "global_step": 526939, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0649349689483643, "global_step": 526940, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.097248077392578, "global_step": 526941, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9871015548706055, "global_step": 526942, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.053384780883789, "global_step": 526943, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.105687141418457, "global_step": 526944, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1161434650421143, "global_step": 526945, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0578575134277344, "global_step": 526946, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9880818128585815, "global_step": 526947, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0013954639434814, "global_step": 526948, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0393834114074707, "global_step": 526949, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.024613857269287, "global_step": 526950, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.999578595161438, "global_step": 526951, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.038520336151123, "global_step": 526952, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.074498414993286, "global_step": 526953, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0861268043518066, "global_step": 526954, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.996558427810669, "global_step": 526955, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.982947826385498, "global_step": 526956, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.057854413986206, "global_step": 526957, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.017737865447998, "global_step": 526958, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0210278034210205, "global_step": 526959, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.028675079345703, "global_step": 526960, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.153395414352417, "global_step": 526961, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9669466018676758, "global_step": 526962, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0016233921051025, "global_step": 526963, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.032032012939453, "global_step": 526964, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9671738147735596, "global_step": 526965, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1559619903564453, "global_step": 526966, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9988385438919067, "global_step": 526967, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.090217351913452, "global_step": 526968, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.019043445587158, "global_step": 526969, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9093024730682373, "global_step": 526970, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9729000329971313, "global_step": 526971, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.081777572631836, "global_step": 526972, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0144174098968506, "global_step": 526973, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9676908254623413, "global_step": 526974, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.060063600540161, "global_step": 526975, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.03169584274292, "global_step": 526976, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0545268058776855, "global_step": 526977, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.107328414916992, "global_step": 526978, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.938881278038025, "global_step": 526979, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1267600059509277, "global_step": 526980, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.080362558364868, "global_step": 526981, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.158742904663086, "global_step": 526982, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.069047212600708, "global_step": 526983, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.8651776313781738, "global_step": 526984, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0162556171417236, "global_step": 526985, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.036771774291992, "global_step": 526986, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0122618675231934, "global_step": 526987, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.035308837890625, "global_step": 526988, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.054363250732422, "global_step": 526989, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.05031156539917, "global_step": 526990, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.045971632003784, "global_step": 526991, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1332473754882812, "global_step": 526992, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0885796546936035, "global_step": 526993, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.094788074493408, "global_step": 526994, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.084578037261963, "global_step": 526995, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0113654136657715, "global_step": 526996, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0368216037750244, "global_step": 526997, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.118391275405884, "global_step": 526998, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.024045944213867, "global_step": 526999, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9957802295684814, "global_step": 527000, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0523629188537598, "global_step": 527001, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1729795932769775, "global_step": 527002, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.009066343307495, "global_step": 527003, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.01568865776062, "global_step": 527004, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9944612979888916, "global_step": 527005, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.028712511062622, "global_step": 527006, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0432910919189453, "global_step": 527007, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9739723205566406, "global_step": 527008, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1132309436798096, "global_step": 527009, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.06378436088562, "global_step": 527010, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9955919981002808, "global_step": 527011, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.996612548828125, "global_step": 527012, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.050203323364258, "global_step": 527013, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.101820945739746, "global_step": 527014, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0578110218048096, "global_step": 527015, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.173877239227295, "global_step": 527016, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0845110416412354, "global_step": 527017, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.025749921798706, "global_step": 527018, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9831533432006836, "global_step": 527019, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.994386911392212, "global_step": 527020, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0623509883880615, "global_step": 527021, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.115462303161621, "global_step": 527022, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0622119903564453, "global_step": 527023, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0745656490325928, "global_step": 527024, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0698132514953613, "global_step": 527025, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0974411964416504, "global_step": 527026, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.031376838684082, "global_step": 527027, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0975024700164795, "global_step": 527028, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0368621349334717, "global_step": 527029, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.085171937942505, "global_step": 527030, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9902111291885376, "global_step": 527031, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0519020557403564, "global_step": 527032, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.01057767868042, "global_step": 527033, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.066540002822876, "global_step": 527034, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.083177089691162, "global_step": 527035, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.027689218521118, "global_step": 527036, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0601887702941895, "global_step": 527037, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0321686267852783, "global_step": 527038, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.045593738555908, "global_step": 527039, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0050814151763916, "global_step": 527040, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0573456287384033, "global_step": 527041, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0989062786102295, "global_step": 527042, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0242719650268555, "global_step": 527043, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.066270112991333, "global_step": 527044, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0406200885772705, "global_step": 527045, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1231446266174316, "global_step": 527046, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0034987926483154, "global_step": 527047, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.140204906463623, "global_step": 527048, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0653128623962402, "global_step": 527049, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0181310176849365, "global_step": 527050, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.05546236038208, "global_step": 527051, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9966750144958496, "global_step": 527052, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0745489597320557, "global_step": 527053, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.063354015350342, "global_step": 527054, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.06363844871521, "global_step": 527055, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0841825008392334, "global_step": 527056, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9872573614120483, "global_step": 527057, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9895371198654175, "global_step": 527058, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.058244228363037, "global_step": 527059, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0950751304626465, "global_step": 527060, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0578436851501465, "global_step": 527061, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0478618144989014, "global_step": 527062, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.141126871109009, "global_step": 527063, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.119661331176758, "global_step": 527064, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0706605911254883, "global_step": 527065, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0373075008392334, "global_step": 527066, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.051943778991699, "global_step": 527067, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0919909477233887, "global_step": 527068, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9929240942001343, "global_step": 527069, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0972135066986084, "global_step": 527070, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1692163944244385, "global_step": 527071, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9532219171524048, "global_step": 527072, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0899438858032227, "global_step": 527073, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.11391544342041, "global_step": 527074, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.052962303161621, "global_step": 527075, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9920796155929565, "global_step": 527076, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.095133066177368, "global_step": 527077, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0198678970336914, "global_step": 527078, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.040118455886841, "global_step": 527079, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.027623414993286, "global_step": 527080, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.033834218978882, "global_step": 527081, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.092008352279663, "global_step": 527082, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.080526113510132, "global_step": 527083, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.079934597015381, "global_step": 527084, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1478028297424316, "global_step": 527085, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0618720054626465, "global_step": 527086, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.036290168762207, "global_step": 527087, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0615291595458984, "global_step": 527088, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.070180654525757, "global_step": 527089, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.898059606552124, "global_step": 527090, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.083494186401367, "global_step": 527091, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0824368000030518, "global_step": 527092, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.019158363342285, "global_step": 527093, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0173866748809814, "global_step": 527094, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.995119571685791, "global_step": 527095, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.024078130722046, "global_step": 527096, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0294344425201416, "global_step": 527097, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0144612789154053, "global_step": 527098, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.034381866455078, "global_step": 527099, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.012819290161133, "global_step": 527100, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.054053783416748, "global_step": 527101, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.015170097351074, "global_step": 527102, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.036968469619751, "global_step": 527103, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1037745475769043, "global_step": 527104, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0248401165008545, "global_step": 527105, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0366568565368652, "global_step": 527106, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.102682590484619, "global_step": 527107, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.014909505844116, "global_step": 527108, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9924802780151367, "global_step": 527109, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.059460163116455, "global_step": 527110, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9919397830963135, "global_step": 527111, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0882186889648438, "global_step": 527112, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9840608835220337, "global_step": 527113, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.056577682495117, "global_step": 527114, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.056429624557495, "global_step": 527115, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9748802185058594, "global_step": 527116, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.057260751724243, "global_step": 527117, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.084183692932129, "global_step": 527118, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.110624313354492, "global_step": 527119, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0550029277801514, "global_step": 527120, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.030503273010254, "global_step": 527121, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0242717266082764, "global_step": 527122, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0481488704681396, "global_step": 527123, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9566963911056519, "global_step": 527124, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0390357971191406, "global_step": 527125, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0672857761383057, "global_step": 527126, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.021599054336548, "global_step": 527127, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0790042877197266, "global_step": 527128, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0556910037994385, "global_step": 527129, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.017810344696045, "global_step": 527130, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0380234718322754, "global_step": 527131, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9941933155059814, "global_step": 527132, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9843801259994507, "global_step": 527133, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0664432048797607, "global_step": 527134, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9502029418945312, "global_step": 527135, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0487587451934814, "global_step": 527136, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9843018054962158, "global_step": 527137, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.135065793991089, "global_step": 527138, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9924776554107666, "global_step": 527139, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0267064571380615, "global_step": 527140, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.082507848739624, "global_step": 527141, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.062877655029297, "global_step": 527142, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0827860832214355, "global_step": 527143, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.086700677871704, "global_step": 527144, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0255374908447266, "global_step": 527145, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0529510974884033, "global_step": 527146, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.120830774307251, "global_step": 527147, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.006856679916382, "global_step": 527148, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0447797775268555, "global_step": 527149, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0543668270111084, "global_step": 527150, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0164475440979004, "global_step": 527151, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0233840942382812, "global_step": 527152, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0642080307006836, "global_step": 527153, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9420987367630005, "global_step": 527154, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1128933429718018, "global_step": 527155, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0336995124816895, "global_step": 527156, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.032525062561035, "global_step": 527157, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.071336269378662, "global_step": 527158, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9854826927185059, "global_step": 527159, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.090420961380005, "global_step": 527160, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.958466649055481, "global_step": 527161, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.073221206665039, "global_step": 527162, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0981130599975586, "global_step": 527163, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1215882301330566, "global_step": 527164, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1308798789978027, "global_step": 527165, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0625126361846924, "global_step": 527166, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9711973667144775, "global_step": 527167, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9341901540756226, "global_step": 527168, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0648915767669678, "global_step": 527169, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9844012260437012, "global_step": 527170, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.071040153503418, "global_step": 527171, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.130934238433838, "global_step": 527172, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0160906314849854, "global_step": 527173, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0596156120300293, "global_step": 527174, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.026238441467285, "global_step": 527175, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1218931674957275, "global_step": 527176, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1083390712738037, "global_step": 527177, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0575292110443115, "global_step": 527178, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0083186626434326, "global_step": 527179, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0605552196502686, "global_step": 527180, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9972206354141235, "global_step": 527181, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0219051837921143, "global_step": 527182, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9874686002731323, "global_step": 527183, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0198514461517334, "global_step": 527184, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0102250576019287, "global_step": 527185, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0920591354370117, "global_step": 527186, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1450705528259277, "global_step": 527187, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.012948751449585, "global_step": 527188, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9674899578094482, "global_step": 527189, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.021892786026001, "global_step": 527190, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9722508192062378, "global_step": 527191, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0646872520446777, "global_step": 527192, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.091005802154541, "global_step": 527193, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.008297920227051, "global_step": 527194, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0020692348480225, "global_step": 527195, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0760631561279297, "global_step": 527196, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0011723041534424, "global_step": 527197, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.010366678237915, "global_step": 527198, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.059673309326172, "global_step": 527199, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0881943702697754, "global_step": 527200, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.023329734802246, "global_step": 527201, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.993086338043213, "global_step": 527202, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.04300594329834, "global_step": 527203, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.091522216796875, "global_step": 527204, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.088134765625, "global_step": 527205, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.064772367477417, "global_step": 527206, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.074644088745117, "global_step": 527207, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0882763862609863, "global_step": 527208, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1027932167053223, "global_step": 527209, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.002467393875122, "global_step": 527210, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1298868656158447, "global_step": 527211, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0955584049224854, "global_step": 527212, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.055575370788574, "global_step": 527213, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9652419090270996, "global_step": 527214, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.046241283416748, "global_step": 527215, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.992139458656311, "global_step": 527216, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0247862339019775, "global_step": 527217, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.039355754852295, "global_step": 527218, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9903864860534668, "global_step": 527219, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0952672958374023, "global_step": 527220, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9895399808883667, "global_step": 527221, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0026535987854004, "global_step": 527222, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.003234624862671, "global_step": 527223, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0595929622650146, "global_step": 527224, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1190874576568604, "global_step": 527225, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.105245351791382, "global_step": 527226, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9567131996154785, "global_step": 527227, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.063554286956787, "global_step": 527228, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0984864234924316, "global_step": 527229, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.006521701812744, "global_step": 527230, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.033994436264038, "global_step": 527231, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.088216781616211, "global_step": 527232, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.035629987716675, "global_step": 527233, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9965227842330933, "global_step": 527234, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.1285171508789062, "global_step": 527235, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0328192710876465, "global_step": 527236, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.061840772628784, "global_step": 527237, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.02815318107605, "global_step": 527238, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.993770956993103, "global_step": 527239, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0098330974578857, "global_step": 527240, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0808932781219482, "global_step": 527241, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.03190279006958, "global_step": 527242, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.039398193359375, "global_step": 527243, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0505454540252686, "global_step": 527244, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0599558353424072, "global_step": 527245, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0356109142303467, "global_step": 527246, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.01521372795105, "global_step": 527247, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.042062520980835, "global_step": 527248, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0033929347991943, "global_step": 527249, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9572970867156982, "global_step": 527250, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.056157112121582, "global_step": 527251, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.053488254547119, "global_step": 527252, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9729056358337402, "global_step": 527253, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0415451526641846, "global_step": 527254, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.9622478485107422, "global_step": 527255, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0362319946289062, "global_step": 527256, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0883967876434326, "global_step": 527257, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.023285388946533, "global_step": 527258, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.047481060028076, "global_step": 527259, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.072890281677246, "global_step": 527260, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0307435989379883, "global_step": 527261, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0652270317077637, "global_step": 527262, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.030836582183838, "global_step": 527263, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0582802295684814, "global_step": 527264, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0625758171081543, "global_step": 527265, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.083622694015503, "global_step": 527266, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0701756477355957, "global_step": 527267, "epoch": 893, "lr": 5e-05}
{"train_loss": 2.0397653579711914, "global_step": 527268, "epoch": 893, "lr": 5e-05}
{"train_loss": 1.983655571937561, "global_step": 527269, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.965751051902771, "global_step": 527270, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9717161655426025, "global_step": 527271, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.092644453048706, "global_step": 527272, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.033087968826294, "global_step": 527273, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0788629055023193, "global_step": 527274, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9698280096054077, "global_step": 527275, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0859222412109375, "global_step": 527276, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0271077156066895, "global_step": 527277, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.116183280944824, "global_step": 527278, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9837298393249512, "global_step": 527279, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.045379161834717, "global_step": 527280, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0297350883483887, "global_step": 527281, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0494279861450195, "global_step": 527282, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9974347352981567, "global_step": 527283, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0967957973480225, "global_step": 527284, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0926337242126465, "global_step": 527285, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0492780208587646, "global_step": 527286, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.012155532836914, "global_step": 527287, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9435018301010132, "global_step": 527288, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0217483043670654, "global_step": 527289, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.012376546859741, "global_step": 527290, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9884979724884033, "global_step": 527291, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0629560947418213, "global_step": 527292, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0334067344665527, "global_step": 527293, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.062765121459961, "global_step": 527294, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0211455821990967, "global_step": 527295, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.039716958999634, "global_step": 527296, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.085897445678711, "global_step": 527297, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.051929473876953, "global_step": 527298, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.067014694213867, "global_step": 527299, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.025430917739868, "global_step": 527300, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.019007921218872, "global_step": 527301, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.991068959236145, "global_step": 527302, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0338709354400635, "global_step": 527303, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0756750106811523, "global_step": 527304, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0263113975524902, "global_step": 527305, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0121634006500244, "global_step": 527306, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1122071743011475, "global_step": 527307, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0844979286193848, "global_step": 527308, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9731756448745728, "global_step": 527309, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0263025760650635, "global_step": 527310, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.8993499279022217, "global_step": 527311, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.035463333129883, "global_step": 527312, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9841357469558716, "global_step": 527313, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.036914587020874, "global_step": 527314, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0584781169891357, "global_step": 527315, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.978468418121338, "global_step": 527316, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.003455400466919, "global_step": 527317, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0395214557647705, "global_step": 527318, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.01955246925354, "global_step": 527319, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0425426959991455, "global_step": 527320, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0018835067749023, "global_step": 527321, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.006746292114258, "global_step": 527322, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.116046667098999, "global_step": 527323, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9835330247879028, "global_step": 527324, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.003082752227783, "global_step": 527325, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0180788040161133, "global_step": 527326, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0300729274749756, "global_step": 527327, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.021090030670166, "global_step": 527328, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.008467674255371, "global_step": 527329, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9148091077804565, "global_step": 527330, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0916390419006348, "global_step": 527331, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0206191539764404, "global_step": 527332, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.990315556526184, "global_step": 527333, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0255818367004395, "global_step": 527334, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9688446521759033, "global_step": 527335, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0819530487060547, "global_step": 527336, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0277273654937744, "global_step": 527337, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.085148811340332, "global_step": 527338, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9800583124160767, "global_step": 527339, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9989997148513794, "global_step": 527340, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9914096593856812, "global_step": 527341, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9717286825180054, "global_step": 527342, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.039724111557007, "global_step": 527343, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0642178058624268, "global_step": 527344, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.073456048965454, "global_step": 527345, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.059720277786255, "global_step": 527346, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9675627946853638, "global_step": 527347, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9866328239440918, "global_step": 527348, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9654419422149658, "global_step": 527349, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9450575113296509, "global_step": 527350, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.997581958770752, "global_step": 527351, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.08683443069458, "global_step": 527352, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9226001501083374, "global_step": 527353, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0368776321411133, "global_step": 527354, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.016390085220337, "global_step": 527355, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0424087047576904, "global_step": 527356, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.061213493347168, "global_step": 527357, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.161043882369995, "global_step": 527358, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0708956718444824, "global_step": 527359, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.068051815032959, "global_step": 527360, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1122887134552, "global_step": 527361, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9959590435028076, "global_step": 527362, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0836596488952637, "global_step": 527363, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9785839319229126, "global_step": 527364, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.004795551300049, "global_step": 527365, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0438907146453857, "global_step": 527366, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0241076946258545, "global_step": 527367, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9437425136566162, "global_step": 527368, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1300249099731445, "global_step": 527369, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0391018390655518, "global_step": 527370, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0495429039001465, "global_step": 527371, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9855931997299194, "global_step": 527372, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0553348064422607, "global_step": 527373, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0393073558807373, "global_step": 527374, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.115368604660034, "global_step": 527375, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.040360450744629, "global_step": 527376, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.028167724609375, "global_step": 527377, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9941118955612183, "global_step": 527378, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.054215669631958, "global_step": 527379, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.944352388381958, "global_step": 527380, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0441131591796875, "global_step": 527381, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9433352947235107, "global_step": 527382, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.970470666885376, "global_step": 527383, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0804190635681152, "global_step": 527384, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0378313064575195, "global_step": 527385, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.027777671813965, "global_step": 527386, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.062631607055664, "global_step": 527387, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.054734706878662, "global_step": 527388, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.049327850341797, "global_step": 527389, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.962092399597168, "global_step": 527390, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9766120910644531, "global_step": 527391, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0093064308166504, "global_step": 527392, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0659193992614746, "global_step": 527393, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9409492015838623, "global_step": 527394, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0266451835632324, "global_step": 527395, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9629790782928467, "global_step": 527396, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.953853964805603, "global_step": 527397, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0398402214050293, "global_step": 527398, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.088151216506958, "global_step": 527399, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.025698184967041, "global_step": 527400, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.10744571685791, "global_step": 527401, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0523736476898193, "global_step": 527402, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.05086088180542, "global_step": 527403, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1121251583099365, "global_step": 527404, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.113701343536377, "global_step": 527405, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.009270429611206, "global_step": 527406, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0346970558166504, "global_step": 527407, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.004500150680542, "global_step": 527408, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0462849140167236, "global_step": 527409, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.11968994140625, "global_step": 527410, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9092367887496948, "global_step": 527411, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0675456523895264, "global_step": 527412, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.014307975769043, "global_step": 527413, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.97816801071167, "global_step": 527414, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.009028196334839, "global_step": 527415, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9649184942245483, "global_step": 527416, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9742552042007446, "global_step": 527417, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.954732060432434, "global_step": 527418, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.117741346359253, "global_step": 527419, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0170421600341797, "global_step": 527420, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0619726181030273, "global_step": 527421, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0083718299865723, "global_step": 527422, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.047664165496826, "global_step": 527423, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0545921325683594, "global_step": 527424, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0479190349578857, "global_step": 527425, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9828134775161743, "global_step": 527426, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.977026104927063, "global_step": 527427, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0878539085388184, "global_step": 527428, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9878541231155396, "global_step": 527429, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.129812717437744, "global_step": 527430, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0446720123291016, "global_step": 527431, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.046983003616333, "global_step": 527432, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9998441934585571, "global_step": 527433, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.060037136077881, "global_step": 527434, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.04984450340271, "global_step": 527435, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0381503105163574, "global_step": 527436, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.045473337173462, "global_step": 527437, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9556986093521118, "global_step": 527438, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.066030740737915, "global_step": 527439, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0545949935913086, "global_step": 527440, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.008786678314209, "global_step": 527441, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.940843105316162, "global_step": 527442, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.928964376449585, "global_step": 527443, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1152215003967285, "global_step": 527444, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9707406759262085, "global_step": 527445, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9262126684188843, "global_step": 527446, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.083103895187378, "global_step": 527447, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0727295875549316, "global_step": 527448, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0165953636169434, "global_step": 527449, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0085246562957764, "global_step": 527450, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.136793851852417, "global_step": 527451, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.069556713104248, "global_step": 527452, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.044252872467041, "global_step": 527453, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.061086893081665, "global_step": 527454, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.02764630317688, "global_step": 527455, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0721383094787598, "global_step": 527456, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0484602451324463, "global_step": 527457, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9831132888793945, "global_step": 527458, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.027078866958618, "global_step": 527459, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9946366548538208, "global_step": 527460, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.056104898452759, "global_step": 527461, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9639098644256592, "global_step": 527462, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0448460578918457, "global_step": 527463, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9843608140945435, "global_step": 527464, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9796884059906006, "global_step": 527465, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0625481605529785, "global_step": 527466, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0746631622314453, "global_step": 527467, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.051079750061035, "global_step": 527468, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0661656856536865, "global_step": 527469, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.997040867805481, "global_step": 527470, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0815300941467285, "global_step": 527471, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0171597003936768, "global_step": 527472, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9993298053741455, "global_step": 527473, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.106773614883423, "global_step": 527474, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9983413219451904, "global_step": 527475, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.069596767425537, "global_step": 527476, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.062582015991211, "global_step": 527477, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9366062879562378, "global_step": 527478, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.071289539337158, "global_step": 527479, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0265674591064453, "global_step": 527480, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9766284227371216, "global_step": 527481, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0845742225646973, "global_step": 527482, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0727124214172363, "global_step": 527483, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0510449409484863, "global_step": 527484, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0420265197753906, "global_step": 527485, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.919572353363037, "global_step": 527486, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9859848022460938, "global_step": 527487, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9438799619674683, "global_step": 527488, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0254533290863037, "global_step": 527489, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0853078365325928, "global_step": 527490, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0706090927124023, "global_step": 527491, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.99027681350708, "global_step": 527492, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.058048963546753, "global_step": 527493, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0455594062805176, "global_step": 527494, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0626726150512695, "global_step": 527495, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0016942024230957, "global_step": 527496, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.002164602279663, "global_step": 527497, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1186225414276123, "global_step": 527498, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0459563732147217, "global_step": 527499, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.033581256866455, "global_step": 527500, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0695672035217285, "global_step": 527501, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.053586721420288, "global_step": 527502, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0901854038238525, "global_step": 527503, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.039350748062134, "global_step": 527504, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.124542236328125, "global_step": 527505, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0325300693511963, "global_step": 527506, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.964072585105896, "global_step": 527507, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.176035165786743, "global_step": 527508, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.059622049331665, "global_step": 527509, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.936673879623413, "global_step": 527510, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.103095531463623, "global_step": 527511, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9876008033752441, "global_step": 527512, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.968851923942566, "global_step": 527513, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.944564700126648, "global_step": 527514, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9888968467712402, "global_step": 527515, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0194685459136963, "global_step": 527516, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.013685703277588, "global_step": 527517, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0340077877044678, "global_step": 527518, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0313453674316406, "global_step": 527519, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.021226167678833, "global_step": 527520, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.043574333190918, "global_step": 527521, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.057818651199341, "global_step": 527522, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0639312267303467, "global_step": 527523, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0297701358795166, "global_step": 527524, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0549466609954834, "global_step": 527525, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.021890163421631, "global_step": 527526, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0867655277252197, "global_step": 527527, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0191166400909424, "global_step": 527528, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.031747817993164, "global_step": 527529, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9739528894424438, "global_step": 527530, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0221517086029053, "global_step": 527531, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.020676612854004, "global_step": 527532, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.056959867477417, "global_step": 527533, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0629520416259766, "global_step": 527534, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.019657611846924, "global_step": 527535, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0362327098846436, "global_step": 527536, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0966672897338867, "global_step": 527537, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.077505350112915, "global_step": 527538, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.132704019546509, "global_step": 527539, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.027627944946289, "global_step": 527540, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9954006671905518, "global_step": 527541, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.020742654800415, "global_step": 527542, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0239691734313965, "global_step": 527543, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0240931510925293, "global_step": 527544, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9513719081878662, "global_step": 527545, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.090695858001709, "global_step": 527546, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.022752523422241, "global_step": 527547, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0302491188049316, "global_step": 527548, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1096701622009277, "global_step": 527549, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0599188804626465, "global_step": 527550, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0822017192840576, "global_step": 527551, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.05509090423584, "global_step": 527552, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9859910011291504, "global_step": 527553, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0478971004486084, "global_step": 527554, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.004918098449707, "global_step": 527555, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0048928260803223, "global_step": 527556, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0918402671813965, "global_step": 527557, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9497978687286377, "global_step": 527558, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9588156938552856, "global_step": 527559, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.105339527130127, "global_step": 527560, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9824097156524658, "global_step": 527561, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.045452356338501, "global_step": 527562, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.994296908378601, "global_step": 527563, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0205109119415283, "global_step": 527564, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.060121536254883, "global_step": 527565, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.066519021987915, "global_step": 527566, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.060884714126587, "global_step": 527567, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1559908390045166, "global_step": 527568, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.076154947280884, "global_step": 527569, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0260348320007324, "global_step": 527570, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.066499710083008, "global_step": 527571, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.052212953567505, "global_step": 527572, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.024425983428955, "global_step": 527573, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.940360188484192, "global_step": 527574, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.02795672416687, "global_step": 527575, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9850181341171265, "global_step": 527576, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0047693252563477, "global_step": 527577, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.081312656402588, "global_step": 527578, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.016118288040161, "global_step": 527579, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.967604398727417, "global_step": 527580, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.075639009475708, "global_step": 527581, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9859554767608643, "global_step": 527582, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.081075668334961, "global_step": 527583, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.996317982673645, "global_step": 527584, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9772225618362427, "global_step": 527585, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.025080680847168, "global_step": 527586, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0439817905426025, "global_step": 527587, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.002896308898926, "global_step": 527588, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1538851261138916, "global_step": 527589, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.075204849243164, "global_step": 527590, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.109105110168457, "global_step": 527591, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9979524612426758, "global_step": 527592, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.970042109489441, "global_step": 527593, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1044726371765137, "global_step": 527594, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.040928840637207, "global_step": 527595, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1394779682159424, "global_step": 527596, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0562405586242676, "global_step": 527597, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.990708351135254, "global_step": 527598, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9685730934143066, "global_step": 527599, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9899945259094238, "global_step": 527600, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0202486515045166, "global_step": 527601, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9355798959732056, "global_step": 527602, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9890596866607666, "global_step": 527603, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0025689601898193, "global_step": 527604, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.022894859313965, "global_step": 527605, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.070612907409668, "global_step": 527606, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0557148456573486, "global_step": 527607, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.072801351547241, "global_step": 527608, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0666534900665283, "global_step": 527609, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0743660926818848, "global_step": 527610, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.027225971221924, "global_step": 527611, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0403099060058594, "global_step": 527612, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.115476608276367, "global_step": 527613, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.058426856994629, "global_step": 527614, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0563721656799316, "global_step": 527615, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0212981700897217, "global_step": 527616, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0479958057403564, "global_step": 527617, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1081082820892334, "global_step": 527618, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.119466781616211, "global_step": 527619, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9835903644561768, "global_step": 527620, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0098509788513184, "global_step": 527621, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9986364841461182, "global_step": 527622, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0584895610809326, "global_step": 527623, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.056413173675537, "global_step": 527624, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0252411365509033, "global_step": 527625, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9207816123962402, "global_step": 527626, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0825881958007812, "global_step": 527627, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0950767993927, "global_step": 527628, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.027059316635132, "global_step": 527629, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1073226928710938, "global_step": 527630, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.010446786880493, "global_step": 527631, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1211636066436768, "global_step": 527632, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.085418224334717, "global_step": 527633, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.028043508529663, "global_step": 527634, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.021524429321289, "global_step": 527635, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0739307403564453, "global_step": 527636, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0653045177459717, "global_step": 527637, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9636237621307373, "global_step": 527638, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.004892110824585, "global_step": 527639, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.052567481994629, "global_step": 527640, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0038788318634033, "global_step": 527641, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0277163982391357, "global_step": 527642, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0043623447418213, "global_step": 527643, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.139779806137085, "global_step": 527644, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0144317150115967, "global_step": 527645, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0607407093048096, "global_step": 527646, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9613667726516724, "global_step": 527647, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.059617042541504, "global_step": 527648, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.015275478363037, "global_step": 527649, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0778307914733887, "global_step": 527650, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.042534828186035, "global_step": 527651, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0504586696624756, "global_step": 527652, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0886495113372803, "global_step": 527653, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.981319546699524, "global_step": 527654, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9388806819915771, "global_step": 527655, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0482065677642822, "global_step": 527656, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0316343307495117, "global_step": 527657, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0565390586853027, "global_step": 527658, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0330045223236084, "global_step": 527659, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.014885425567627, "global_step": 527660, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0530552864074707, "global_step": 527661, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1452221870422363, "global_step": 527662, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.024508237838745, "global_step": 527663, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0286099910736084, "global_step": 527664, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9879106283187866, "global_step": 527665, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1206905841827393, "global_step": 527666, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0807032585144043, "global_step": 527667, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0315842628479004, "global_step": 527668, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.048321008682251, "global_step": 527669, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0720980167388916, "global_step": 527670, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9632666110992432, "global_step": 527671, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.080343246459961, "global_step": 527672, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0635080337524414, "global_step": 527673, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.99853515625, "global_step": 527674, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0640013217926025, "global_step": 527675, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0703494548797607, "global_step": 527676, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9437352418899536, "global_step": 527677, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9235342741012573, "global_step": 527678, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.971103310585022, "global_step": 527679, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9990630149841309, "global_step": 527680, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.988381028175354, "global_step": 527681, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0856924057006836, "global_step": 527682, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0928821563720703, "global_step": 527683, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.081461191177368, "global_step": 527684, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0758373737335205, "global_step": 527685, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1242332458496094, "global_step": 527686, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0725369453430176, "global_step": 527687, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9926762580871582, "global_step": 527688, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.005154848098755, "global_step": 527689, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0427677631378174, "global_step": 527690, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1305174827575684, "global_step": 527691, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0002763271331787, "global_step": 527692, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0132975578308105, "global_step": 527693, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0372424125671387, "global_step": 527694, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0003745555877686, "global_step": 527695, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0195586681365967, "global_step": 527696, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9863413572311401, "global_step": 527697, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.014735698699951, "global_step": 527698, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9593738317489624, "global_step": 527699, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0385546684265137, "global_step": 527700, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9874485731124878, "global_step": 527701, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9836790561676025, "global_step": 527702, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1153581142425537, "global_step": 527703, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.083296298980713, "global_step": 527704, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0321905612945557, "global_step": 527705, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.058910608291626, "global_step": 527706, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0374059677124023, "global_step": 527707, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0523319244384766, "global_step": 527708, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0288233757019043, "global_step": 527709, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9828869104385376, "global_step": 527710, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1208128929138184, "global_step": 527711, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9563897848129272, "global_step": 527712, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0346243381500244, "global_step": 527713, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.102454900741577, "global_step": 527714, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.035097360610962, "global_step": 527715, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9587620496749878, "global_step": 527716, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9667034149169922, "global_step": 527717, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.044506788253784, "global_step": 527718, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0721938610076904, "global_step": 527719, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0109846591949463, "global_step": 527720, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.039247751235962, "global_step": 527721, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0209500789642334, "global_step": 527722, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0524230003356934, "global_step": 527723, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0125396251678467, "global_step": 527724, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.984804630279541, "global_step": 527725, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.038936138153076, "global_step": 527726, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0408406257629395, "global_step": 527727, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.087519407272339, "global_step": 527728, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0768892765045166, "global_step": 527729, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.048393487930298, "global_step": 527730, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0461888313293457, "global_step": 527731, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.08065128326416, "global_step": 527732, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.029331684112549, "global_step": 527733, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9997478723526, "global_step": 527734, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.082235097885132, "global_step": 527735, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0517284870147705, "global_step": 527736, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1332945823669434, "global_step": 527737, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.03934907913208, "global_step": 527738, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0058510303497314, "global_step": 527739, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.081718683242798, "global_step": 527740, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.097907304763794, "global_step": 527741, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0052061080932617, "global_step": 527742, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9811198711395264, "global_step": 527743, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.019596576690674, "global_step": 527744, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1142776012420654, "global_step": 527745, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0398879051208496, "global_step": 527746, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.075071096420288, "global_step": 527747, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1071109771728516, "global_step": 527748, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.055490016937256, "global_step": 527749, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.007596254348755, "global_step": 527750, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.079038619995117, "global_step": 527751, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9347689151763916, "global_step": 527752, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.112701654434204, "global_step": 527753, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.021595001220703, "global_step": 527754, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1444833278656006, "global_step": 527755, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0460009574890137, "global_step": 527756, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0212340354919434, "global_step": 527757, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.050668239593506, "global_step": 527758, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.049847364425659, "global_step": 527759, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0807814598083496, "global_step": 527760, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0262861251831055, "global_step": 527761, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.049475908279419, "global_step": 527762, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0846946239471436, "global_step": 527763, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9667330980300903, "global_step": 527764, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0718533992767334, "global_step": 527765, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9708800315856934, "global_step": 527766, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.108295440673828, "global_step": 527767, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.093019962310791, "global_step": 527768, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0701358318328857, "global_step": 527769, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1416168212890625, "global_step": 527770, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.046063184738159, "global_step": 527771, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9647002220153809, "global_step": 527772, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.092372417449951, "global_step": 527773, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.028151035308838, "global_step": 527774, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9781773090362549, "global_step": 527775, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0041120052337646, "global_step": 527776, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0170793533325195, "global_step": 527777, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.045976161956787, "global_step": 527778, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.021394729614258, "global_step": 527779, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9928643703460693, "global_step": 527780, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0567052364349365, "global_step": 527781, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0292587280273438, "global_step": 527782, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0785903930664062, "global_step": 527783, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.052950620651245, "global_step": 527784, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0058376789093018, "global_step": 527785, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.01767897605896, "global_step": 527786, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.068361520767212, "global_step": 527787, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0415828227996826, "global_step": 527788, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.065345525741577, "global_step": 527789, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0674076080322266, "global_step": 527790, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.013925313949585, "global_step": 527791, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0416924953460693, "global_step": 527792, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.12060546875, "global_step": 527793, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0879859924316406, "global_step": 527794, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9294216632843018, "global_step": 527795, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0160465240478516, "global_step": 527796, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9621851444244385, "global_step": 527797, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0857760906219482, "global_step": 527798, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9618359804153442, "global_step": 527799, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.04984450340271, "global_step": 527800, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9089298248291016, "global_step": 527801, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.069361686706543, "global_step": 527802, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.073992967605591, "global_step": 527803, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0406458377838135, "global_step": 527804, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0667037963867188, "global_step": 527805, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0445756912231445, "global_step": 527806, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9976495504379272, "global_step": 527807, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0195751190185547, "global_step": 527808, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0039801597595215, "global_step": 527809, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0129623413085938, "global_step": 527810, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.065511703491211, "global_step": 527811, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.053541660308838, "global_step": 527812, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9945831298828125, "global_step": 527813, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0139732360839844, "global_step": 527814, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0809059143066406, "global_step": 527815, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.000014543533325, "global_step": 527816, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0038366317749023, "global_step": 527817, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1349399089813232, "global_step": 527818, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0246875286102295, "global_step": 527819, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9765897989273071, "global_step": 527820, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0621633529663086, "global_step": 527821, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.070101261138916, "global_step": 527822, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0952227115631104, "global_step": 527823, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0638742446899414, "global_step": 527824, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.034705638885498, "global_step": 527825, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.034332036972046, "global_step": 527826, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0884761810302734, "global_step": 527827, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.116847038269043, "global_step": 527828, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.080472946166992, "global_step": 527829, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.080550193786621, "global_step": 527830, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.112161636352539, "global_step": 527831, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9865071773529053, "global_step": 527832, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9319959878921509, "global_step": 527833, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0399420261383057, "global_step": 527834, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0406951904296875, "global_step": 527835, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0359714031219482, "global_step": 527836, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0833797454833984, "global_step": 527837, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.099210500717163, "global_step": 527838, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1209676265716553, "global_step": 527839, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.049370288848877, "global_step": 527840, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.04274582862854, "global_step": 527841, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9531075954437256, "global_step": 527842, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9537776708602905, "global_step": 527843, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0522234439849854, "global_step": 527844, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.050889492034912, "global_step": 527845, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0529279708862305, "global_step": 527846, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.065657377243042, "global_step": 527847, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.02785325050354, "global_step": 527848, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0269265174865723, "global_step": 527849, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9991607666015625, "global_step": 527850, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0982394218444824, "global_step": 527851, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9829851388931274, "global_step": 527852, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.014880657196045, "global_step": 527853, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9773354530334473, "global_step": 527854, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0312249660491943, "global_step": 527855, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.057032585144043, "global_step": 527856, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0777924060821533, "global_step": 527857, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9876625537872314, "global_step": 527858, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.058518886566162, "global_step": 527859, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.03010630607605, "global_step": 527860, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.024747610092163, "global_step": 527861, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.031062602996826, "global_step": 527862, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9967257976531982, "global_step": 527863, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0709428787231445, "global_step": 527864, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.969773530960083, "global_step": 527865, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0431883335113525, "global_step": 527866, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.018017530441284, "global_step": 527867, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0451667308807373, "global_step": 527868, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.102541923522949, "global_step": 527869, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.049215316772461, "global_step": 527870, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.017962694168091, "global_step": 527871, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.06784725189209, "global_step": 527872, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0484673976898193, "global_step": 527873, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0130040645599365, "global_step": 527874, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0625483989715576, "global_step": 527875, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.024362325668335, "global_step": 527876, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9910662174224854, "global_step": 527877, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9913443326950073, "global_step": 527878, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0772480964660645, "global_step": 527879, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.030947208404541, "global_step": 527880, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.138803243637085, "global_step": 527881, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0523362159729004, "global_step": 527882, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.068998098373413, "global_step": 527883, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.941023588180542, "global_step": 527884, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1055612564086914, "global_step": 527885, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.000809907913208, "global_step": 527886, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9758155345916748, "global_step": 527887, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.970725655555725, "global_step": 527888, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0282227993011475, "global_step": 527889, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.016752243041992, "global_step": 527890, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.027981758117676, "global_step": 527891, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.078409433364868, "global_step": 527892, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1002919673919678, "global_step": 527893, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.06959867477417, "global_step": 527894, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0542194843292236, "global_step": 527895, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.036001682281494, "global_step": 527896, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0259644985198975, "global_step": 527897, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0410289764404297, "global_step": 527898, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0680882930755615, "global_step": 527899, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.023449659347534, "global_step": 527900, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9776930809020996, "global_step": 527901, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.019536256790161, "global_step": 527902, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0968222618103027, "global_step": 527903, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.036024332046509, "global_step": 527904, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0946712493896484, "global_step": 527905, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0120086669921875, "global_step": 527906, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0579097270965576, "global_step": 527907, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.056537628173828, "global_step": 527908, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0014336109161377, "global_step": 527909, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0327131748199463, "global_step": 527910, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.011336088180542, "global_step": 527911, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.059072971343994, "global_step": 527912, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.978682041168213, "global_step": 527913, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1183416843414307, "global_step": 527914, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0187723636627197, "global_step": 527915, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0427849292755127, "global_step": 527916, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0734176635742188, "global_step": 527917, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0210177898406982, "global_step": 527918, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0760462284088135, "global_step": 527919, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.087054967880249, "global_step": 527920, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1074345111846924, "global_step": 527921, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0270979404449463, "global_step": 527922, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0533065795898438, "global_step": 527923, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.949890375137329, "global_step": 527924, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.103809356689453, "global_step": 527925, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1210825443267822, "global_step": 527926, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0625078678131104, "global_step": 527927, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0847911834716797, "global_step": 527928, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9863260984420776, "global_step": 527929, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.019845962524414, "global_step": 527930, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1291656494140625, "global_step": 527931, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0893447399139404, "global_step": 527932, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.082582712173462, "global_step": 527933, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0659990310668945, "global_step": 527934, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.07551646232605, "global_step": 527935, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.068448066711426, "global_step": 527936, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0173702239990234, "global_step": 527937, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0396974086761475, "global_step": 527938, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.018695831298828, "global_step": 527939, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.036412477493286, "global_step": 527940, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.07833194732666, "global_step": 527941, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.122246026992798, "global_step": 527942, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0734939575195312, "global_step": 527943, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.015916585922241, "global_step": 527944, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1276915073394775, "global_step": 527945, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.123558521270752, "global_step": 527946, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0575520992279053, "global_step": 527947, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0712125301361084, "global_step": 527948, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0408577919006348, "global_step": 527949, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0164520740509033, "global_step": 527950, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0140533447265625, "global_step": 527951, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.053574562072754, "global_step": 527952, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0666704177856445, "global_step": 527953, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.101872682571411, "global_step": 527954, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0206780433654785, "global_step": 527955, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1453616619110107, "global_step": 527956, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0038092136383057, "global_step": 527957, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0524864196777344, "global_step": 527958, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.998701810836792, "global_step": 527959, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.991889476776123, "global_step": 527960, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.971231460571289, "global_step": 527961, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.927749752998352, "global_step": 527962, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0348970890045166, "global_step": 527963, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9264384508132935, "global_step": 527964, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.019369125366211, "global_step": 527965, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.014594554901123, "global_step": 527966, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9986344575881958, "global_step": 527967, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.058137893676758, "global_step": 527968, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.143218755722046, "global_step": 527969, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.034724712371826, "global_step": 527970, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0896968841552734, "global_step": 527971, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.068251609802246, "global_step": 527972, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1202309131622314, "global_step": 527973, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.098529100418091, "global_step": 527974, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.028726100921631, "global_step": 527975, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9629422426223755, "global_step": 527976, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0609421730041504, "global_step": 527977, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9766789674758911, "global_step": 527978, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0581212043762207, "global_step": 527979, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.036663055419922, "global_step": 527980, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.077338933944702, "global_step": 527981, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.080509662628174, "global_step": 527982, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0412750244140625, "global_step": 527983, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.14516282081604, "global_step": 527984, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.112281322479248, "global_step": 527985, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9677447080612183, "global_step": 527986, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0848238468170166, "global_step": 527987, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0605125427246094, "global_step": 527988, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.042625904083252, "global_step": 527989, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.029233455657959, "global_step": 527990, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0320944786071777, "global_step": 527991, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9909807443618774, "global_step": 527992, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9995251893997192, "global_step": 527993, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0029137134552, "global_step": 527994, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0529208183288574, "global_step": 527995, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0771870613098145, "global_step": 527996, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1222567558288574, "global_step": 527997, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9754664897918701, "global_step": 527998, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0913572311401367, "global_step": 527999, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0457797050476074, "global_step": 528000, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0569069385528564, "global_step": 528001, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.052806854248047, "global_step": 528002, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9978784322738647, "global_step": 528003, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.069678544998169, "global_step": 528004, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9916948080062866, "global_step": 528005, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0554206371307373, "global_step": 528006, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.080568552017212, "global_step": 528007, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1300199031829834, "global_step": 528008, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0631515979766846, "global_step": 528009, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0509254932403564, "global_step": 528010, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.007286548614502, "global_step": 528011, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9985753297805786, "global_step": 528012, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0634965896606445, "global_step": 528013, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9961957931518555, "global_step": 528014, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9668148756027222, "global_step": 528015, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.002640724182129, "global_step": 528016, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.108264207839966, "global_step": 528017, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.036513328552246, "global_step": 528018, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0584216117858887, "global_step": 528019, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0077412128448486, "global_step": 528020, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0924465656280518, "global_step": 528021, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.100130558013916, "global_step": 528022, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.033961534500122, "global_step": 528023, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0708837509155273, "global_step": 528024, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.032775402069092, "global_step": 528025, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.016112804412842, "global_step": 528026, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0196967124938965, "global_step": 528027, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9370670318603516, "global_step": 528028, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.045118570327759, "global_step": 528029, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.120790481567383, "global_step": 528030, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.047806739807129, "global_step": 528031, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.01385498046875, "global_step": 528032, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.04189133644104, "global_step": 528033, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.122299909591675, "global_step": 528034, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0617763996124268, "global_step": 528035, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0774943828582764, "global_step": 528036, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.015597343444824, "global_step": 528037, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0829977989196777, "global_step": 528038, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0041325092315674, "global_step": 528039, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.070674180984497, "global_step": 528040, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9562695026397705, "global_step": 528041, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.093268632888794, "global_step": 528042, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9974762201309204, "global_step": 528043, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9627584218978882, "global_step": 528044, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.059053421020508, "global_step": 528045, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.078239917755127, "global_step": 528046, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9838069677352905, "global_step": 528047, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9880305528640747, "global_step": 528048, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.063521385192871, "global_step": 528049, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0337440967559814, "global_step": 528050, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.077444076538086, "global_step": 528051, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0465211868286133, "global_step": 528052, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.957904577255249, "global_step": 528053, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0566976070404053, "global_step": 528054, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.02697491645813, "global_step": 528055, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9702205657958984, "global_step": 528056, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0756258964538574, "global_step": 528057, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0075857639312744, "global_step": 528058, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.036872625350952, "global_step": 528059, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.014242172241211, "global_step": 528060, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9575107097625732, "global_step": 528061, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.055213451385498, "global_step": 528062, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.043726682662964, "global_step": 528063, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.044039726257324, "global_step": 528064, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0757031440734863, "global_step": 528065, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0574517250061035, "global_step": 528066, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.050690174102783, "global_step": 528067, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.038503885269165, "global_step": 528068, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9972610473632812, "global_step": 528069, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.083341121673584, "global_step": 528070, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.109102725982666, "global_step": 528071, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0306668281555176, "global_step": 528072, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.094197988510132, "global_step": 528073, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.082308769226074, "global_step": 528074, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.033844470977783, "global_step": 528075, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9907432794570923, "global_step": 528076, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0263020992279053, "global_step": 528077, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9998712539672852, "global_step": 528078, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0464816093444824, "global_step": 528079, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0365517139434814, "global_step": 528080, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0676393508911133, "global_step": 528081, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9491901397705078, "global_step": 528082, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0494136810302734, "global_step": 528083, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0807454586029053, "global_step": 528084, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.180727958679199, "global_step": 528085, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.993029236793518, "global_step": 528086, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1000447273254395, "global_step": 528087, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0707590579986572, "global_step": 528088, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.060594081878662, "global_step": 528089, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0430524349212646, "global_step": 528090, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.03169846534729, "global_step": 528091, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1708171367645264, "global_step": 528092, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9702649116516113, "global_step": 528093, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0602946281433105, "global_step": 528094, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9636650085449219, "global_step": 528095, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.047348976135254, "global_step": 528096, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1138453483581543, "global_step": 528097, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9883333444595337, "global_step": 528098, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0530691146850586, "global_step": 528099, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0718939304351807, "global_step": 528100, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9992891550064087, "global_step": 528101, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1233935356140137, "global_step": 528102, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1432998180389404, "global_step": 528103, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.143003463745117, "global_step": 528104, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0386595726013184, "global_step": 528105, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.001676321029663, "global_step": 528106, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.02140474319458, "global_step": 528107, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.026228427886963, "global_step": 528108, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.000196695327759, "global_step": 528109, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0491042137145996, "global_step": 528110, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.039977788925171, "global_step": 528111, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.072381019592285, "global_step": 528112, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0423977375030518, "global_step": 528113, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.057264804840088, "global_step": 528114, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1260757446289062, "global_step": 528115, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.093871831893921, "global_step": 528116, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.011213779449463, "global_step": 528117, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9713698625564575, "global_step": 528118, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1606862545013428, "global_step": 528119, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0384671688079834, "global_step": 528120, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.02949857711792, "global_step": 528121, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0474259853363037, "global_step": 528122, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0681676864624023, "global_step": 528123, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0455706119537354, "global_step": 528124, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0373053550720215, "global_step": 528125, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0694358348846436, "global_step": 528126, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0137135982513428, "global_step": 528127, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0226268768310547, "global_step": 528128, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9275591373443604, "global_step": 528129, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1548140048980713, "global_step": 528130, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0492632389068604, "global_step": 528131, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0750980377197266, "global_step": 528132, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0268826484680176, "global_step": 528133, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.012765884399414, "global_step": 528134, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.092567205429077, "global_step": 528135, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.944582462310791, "global_step": 528136, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0412662029266357, "global_step": 528137, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1161954402923584, "global_step": 528138, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0872957706451416, "global_step": 528139, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1241626739501953, "global_step": 528140, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9337873458862305, "global_step": 528141, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0146327018737793, "global_step": 528142, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0408823490142822, "global_step": 528143, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0199530124664307, "global_step": 528144, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.030489444732666, "global_step": 528145, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.079552412033081, "global_step": 528146, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.077029228210449, "global_step": 528147, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1056876182556152, "global_step": 528148, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1229560375213623, "global_step": 528149, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0422024726867676, "global_step": 528150, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.018386125564575, "global_step": 528151, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0314481258392334, "global_step": 528152, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.022942543029785, "global_step": 528153, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0613503456115723, "global_step": 528154, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0870132446289062, "global_step": 528155, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1236772537231445, "global_step": 528156, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0624372959136963, "global_step": 528157, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0315358638763428, "global_step": 528158, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0959858894348145, "global_step": 528159, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0128657817840576, "global_step": 528160, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9723411798477173, "global_step": 528161, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1326606273651123, "global_step": 528162, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9922375679016113, "global_step": 528163, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.038344383239746, "global_step": 528164, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.050936698913574, "global_step": 528165, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0837936401367188, "global_step": 528166, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.106584310531616, "global_step": 528167, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.042490005493164, "global_step": 528168, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.935948133468628, "global_step": 528169, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.093526840209961, "global_step": 528170, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.116659164428711, "global_step": 528171, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1030068397521973, "global_step": 528172, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.087531328201294, "global_step": 528173, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1416468620300293, "global_step": 528174, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0348355770111084, "global_step": 528175, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.039090156555176, "global_step": 528176, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9803016185760498, "global_step": 528177, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.009274959564209, "global_step": 528178, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1311898231506348, "global_step": 528179, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.146472215652466, "global_step": 528180, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9370347261428833, "global_step": 528181, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0369391441345215, "global_step": 528182, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0227303504943848, "global_step": 528183, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.015308141708374, "global_step": 528184, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0783798694610596, "global_step": 528185, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.057595729827881, "global_step": 528186, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0201146602630615, "global_step": 528187, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0119810104370117, "global_step": 528188, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9737422466278076, "global_step": 528189, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0502498149871826, "global_step": 528190, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.046405792236328, "global_step": 528191, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.109734296798706, "global_step": 528192, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0659327507019043, "global_step": 528193, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9877740144729614, "global_step": 528194, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.03255295753479, "global_step": 528195, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.032984733581543, "global_step": 528196, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.056476354598999, "global_step": 528197, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0457370281219482, "global_step": 528198, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0215251445770264, "global_step": 528199, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9794812202453613, "global_step": 528200, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9665285348892212, "global_step": 528201, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9775476455688477, "global_step": 528202, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1514713764190674, "global_step": 528203, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0474045276641846, "global_step": 528204, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0504109859466553, "global_step": 528205, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1098546981811523, "global_step": 528206, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0319418907165527, "global_step": 528207, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0345170497894287, "global_step": 528208, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0565507411956787, "global_step": 528209, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.069613218307495, "global_step": 528210, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0727694034576416, "global_step": 528211, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9631431102752686, "global_step": 528212, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0121543407440186, "global_step": 528213, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0485036373138428, "global_step": 528214, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0809545516967773, "global_step": 528215, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9339228868484497, "global_step": 528216, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1076953411102295, "global_step": 528217, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1093733310699463, "global_step": 528218, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0943443775177, "global_step": 528219, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9455398321151733, "global_step": 528220, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9853593111038208, "global_step": 528221, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9818893671035767, "global_step": 528222, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1014578342437744, "global_step": 528223, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1082396507263184, "global_step": 528224, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0973689556121826, "global_step": 528225, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1033551692962646, "global_step": 528226, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9916146993637085, "global_step": 528227, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0452661514282227, "global_step": 528228, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.096595287322998, "global_step": 528229, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0933303833007812, "global_step": 528230, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0211384296417236, "global_step": 528231, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.072675943374634, "global_step": 528232, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9927796125411987, "global_step": 528233, "epoch": 894, "lr": 5e-05}
{"train_loss": 1.9528484344482422, "global_step": 528234, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.033259391784668, "global_step": 528235, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0912423133850098, "global_step": 528236, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.0391042232513428, "global_step": 528237, "epoch": 894, "lr": 5e-05}
{"train_loss": 2.1310172080993652, "global_step": 528238, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.121946096420288, "global_step": 528239, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.004502534866333, "global_step": 528240, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.067262649536133, "global_step": 528241, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0745162963867188, "global_step": 528242, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.053138017654419, "global_step": 528243, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.029409646987915, "global_step": 528244, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0556397438049316, "global_step": 528245, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.116894483566284, "global_step": 528246, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0273871421813965, "global_step": 528247, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0997025966644287, "global_step": 528248, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0485432147979736, "global_step": 528249, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9406241178512573, "global_step": 528250, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.026620388031006, "global_step": 528251, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0126423835754395, "global_step": 528252, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9939113855361938, "global_step": 528253, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0604910850524902, "global_step": 528254, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.09744930267334, "global_step": 528255, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0189366340637207, "global_step": 528256, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0677878856658936, "global_step": 528257, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.01812481880188, "global_step": 528258, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0313198566436768, "global_step": 528259, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0928566455841064, "global_step": 528260, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9611409902572632, "global_step": 528261, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0339860916137695, "global_step": 528262, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9596545696258545, "global_step": 528263, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0520946979522705, "global_step": 528264, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9414596557617188, "global_step": 528265, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0217831134796143, "global_step": 528266, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.000884532928467, "global_step": 528267, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0094358921051025, "global_step": 528268, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0860812664031982, "global_step": 528269, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0448951721191406, "global_step": 528270, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1203198432922363, "global_step": 528271, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9855200052261353, "global_step": 528272, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9600692987442017, "global_step": 528273, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9372433423995972, "global_step": 528274, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.118452310562134, "global_step": 528275, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0568299293518066, "global_step": 528276, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.006381034851074, "global_step": 528277, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0097482204437256, "global_step": 528278, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9837552309036255, "global_step": 528279, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0464580059051514, "global_step": 528280, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.923186182975769, "global_step": 528281, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9937503337860107, "global_step": 528282, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.034060001373291, "global_step": 528283, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9609431028366089, "global_step": 528284, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9779101610183716, "global_step": 528285, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.068413734436035, "global_step": 528286, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.02535343170166, "global_step": 528287, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.050414800643921, "global_step": 528288, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.044631242752075, "global_step": 528289, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0830283164978027, "global_step": 528290, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9931162595748901, "global_step": 528291, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9783087968826294, "global_step": 528292, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.024146318435669, "global_step": 528293, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0210397243499756, "global_step": 528294, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9915682077407837, "global_step": 528295, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0157997608184814, "global_step": 528296, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9404278993606567, "global_step": 528297, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0320096015930176, "global_step": 528298, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9616563320159912, "global_step": 528299, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.105759620666504, "global_step": 528300, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0814995765686035, "global_step": 528301, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9758645296096802, "global_step": 528302, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0548787117004395, "global_step": 528303, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9876785278320312, "global_step": 528304, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0634729862213135, "global_step": 528305, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9876426458358765, "global_step": 528306, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.087057113647461, "global_step": 528307, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0960330963134766, "global_step": 528308, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.8488415479660034, "global_step": 528309, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1392805576324463, "global_step": 528310, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0171828269958496, "global_step": 528311, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.060926914215088, "global_step": 528312, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.068131923675537, "global_step": 528313, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.037344217300415, "global_step": 528314, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0355961322784424, "global_step": 528315, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.00069260597229, "global_step": 528316, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.094137668609619, "global_step": 528317, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.997151255607605, "global_step": 528318, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0924320220947266, "global_step": 528319, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0431017875671387, "global_step": 528320, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0221710205078125, "global_step": 528321, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.020576000213623, "global_step": 528322, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.023833751678467, "global_step": 528323, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.082998752593994, "global_step": 528324, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.064633369445801, "global_step": 528325, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9961986541748047, "global_step": 528326, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0262746810913086, "global_step": 528327, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.06235408782959, "global_step": 528328, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.983066439628601, "global_step": 528329, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.033705234527588, "global_step": 528330, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9334652423858643, "global_step": 528331, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.014127016067505, "global_step": 528332, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0582869052886963, "global_step": 528333, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0318965911865234, "global_step": 528334, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0546278953552246, "global_step": 528335, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9628572463989258, "global_step": 528336, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0245635509490967, "global_step": 528337, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0265138149261475, "global_step": 528338, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0483551025390625, "global_step": 528339, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.045915365219116, "global_step": 528340, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0504086017608643, "global_step": 528341, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9727160930633545, "global_step": 528342, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.024888038635254, "global_step": 528343, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0402767658233643, "global_step": 528344, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1092472076416016, "global_step": 528345, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9508522748947144, "global_step": 528346, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.057593584060669, "global_step": 528347, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.043344497680664, "global_step": 528348, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.057729482650757, "global_step": 528349, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0219972133636475, "global_step": 528350, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9713351726531982, "global_step": 528351, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.010409355163574, "global_step": 528352, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.027315616607666, "global_step": 528353, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0709755420684814, "global_step": 528354, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.00659441947937, "global_step": 528355, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0450527667999268, "global_step": 528356, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.016836404800415, "global_step": 528357, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.065514087677002, "global_step": 528358, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1137239933013916, "global_step": 528359, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0562353134155273, "global_step": 528360, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.044638156890869, "global_step": 528361, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9548691511154175, "global_step": 528362, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.028623580932617, "global_step": 528363, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1063051223754883, "global_step": 528364, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0424301624298096, "global_step": 528365, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0476510524749756, "global_step": 528366, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.02144455909729, "global_step": 528367, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.028163194656372, "global_step": 528368, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0549869537353516, "global_step": 528369, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9991681575775146, "global_step": 528370, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.007362127304077, "global_step": 528371, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.011845350265503, "global_step": 528372, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.039524555206299, "global_step": 528373, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1893229484558105, "global_step": 528374, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0589096546173096, "global_step": 528375, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9782065153121948, "global_step": 528376, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0515336990356445, "global_step": 528377, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0485146045684814, "global_step": 528378, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0957720279693604, "global_step": 528379, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9968338012695312, "global_step": 528380, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9889092445373535, "global_step": 528381, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0643625259399414, "global_step": 528382, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0229973793029785, "global_step": 528383, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0673389434814453, "global_step": 528384, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0381546020507812, "global_step": 528385, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0312821865081787, "global_step": 528386, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0351738929748535, "global_step": 528387, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9897295236587524, "global_step": 528388, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0519590377807617, "global_step": 528389, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0448501110076904, "global_step": 528390, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0486104488372803, "global_step": 528391, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.050629138946533, "global_step": 528392, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.009550094604492, "global_step": 528393, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.065831184387207, "global_step": 528394, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0564277172088623, "global_step": 528395, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1003410816192627, "global_step": 528396, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1274075508117676, "global_step": 528397, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0309667587280273, "global_step": 528398, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0130553245544434, "global_step": 528399, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0580854415893555, "global_step": 528400, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0182316303253174, "global_step": 528401, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.022735118865967, "global_step": 528402, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0261099338531494, "global_step": 528403, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0096211433410645, "global_step": 528404, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0801899433135986, "global_step": 528405, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.056997537612915, "global_step": 528406, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1002917289733887, "global_step": 528407, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.029721260070801, "global_step": 528408, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0665740966796875, "global_step": 528409, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0464577674865723, "global_step": 528410, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0914523601531982, "global_step": 528411, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0186779499053955, "global_step": 528412, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0684666633605957, "global_step": 528413, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.028032064437866, "global_step": 528414, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.035731792449951, "global_step": 528415, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1517653465270996, "global_step": 528416, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0596559047698975, "global_step": 528417, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9995825290679932, "global_step": 528418, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.060638189315796, "global_step": 528419, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0037641525268555, "global_step": 528420, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.044722557067871, "global_step": 528421, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.086970567703247, "global_step": 528422, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0330543518066406, "global_step": 528423, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0397443771362305, "global_step": 528424, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0726919174194336, "global_step": 528425, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.027174711227417, "global_step": 528426, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1034772396087646, "global_step": 528427, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0352630615234375, "global_step": 528428, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9772169589996338, "global_step": 528429, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.004319906234741, "global_step": 528430, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0904669761657715, "global_step": 528431, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9438637495040894, "global_step": 528432, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.036182165145874, "global_step": 528433, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1023106575012207, "global_step": 528434, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0756194591522217, "global_step": 528435, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0805504322052, "global_step": 528436, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.007883310317993, "global_step": 528437, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.027172327041626, "global_step": 528438, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0801033973693848, "global_step": 528439, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.051475763320923, "global_step": 528440, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.003563642501831, "global_step": 528441, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.030435800552368, "global_step": 528442, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9336961507797241, "global_step": 528443, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0502054691314697, "global_step": 528444, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.136176824569702, "global_step": 528445, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.080268144607544, "global_step": 528446, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0730812549591064, "global_step": 528447, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0648488998413086, "global_step": 528448, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.074890375137329, "global_step": 528449, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0500690937042236, "global_step": 528450, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9740363359451294, "global_step": 528451, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.026202917098999, "global_step": 528452, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.002769947052002, "global_step": 528453, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9964293241500854, "global_step": 528454, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.010549306869507, "global_step": 528455, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0091793537139893, "global_step": 528456, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.039236545562744, "global_step": 528457, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0402145385742188, "global_step": 528458, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9805229902267456, "global_step": 528459, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9915306568145752, "global_step": 528460, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0455634593963623, "global_step": 528461, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9863617420196533, "global_step": 528462, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0882105827331543, "global_step": 528463, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9862349033355713, "global_step": 528464, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9942684173583984, "global_step": 528465, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.091437578201294, "global_step": 528466, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.108428478240967, "global_step": 528467, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.003492593765259, "global_step": 528468, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0829644203186035, "global_step": 528469, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.060359477996826, "global_step": 528470, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0091216564178467, "global_step": 528471, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.956393837928772, "global_step": 528472, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9777768850326538, "global_step": 528473, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9756354093551636, "global_step": 528474, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.113816261291504, "global_step": 528475, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.024568557739258, "global_step": 528476, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0684876441955566, "global_step": 528477, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.968372106552124, "global_step": 528478, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9832918643951416, "global_step": 528479, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0182464122772217, "global_step": 528480, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9092223644256592, "global_step": 528481, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0757455825805664, "global_step": 528482, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.033658504486084, "global_step": 528483, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9551048278808594, "global_step": 528484, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.014636754989624, "global_step": 528485, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.024670124053955, "global_step": 528486, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.048849105834961, "global_step": 528487, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9706264734268188, "global_step": 528488, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.014789581298828, "global_step": 528489, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0436997413635254, "global_step": 528490, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.963849425315857, "global_step": 528491, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0304031372070312, "global_step": 528492, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.031618356704712, "global_step": 528493, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0572216510772705, "global_step": 528494, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0595171451568604, "global_step": 528495, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9083311557769775, "global_step": 528496, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0619635581970215, "global_step": 528497, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0119776725769043, "global_step": 528498, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9366328716278076, "global_step": 528499, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.990799903869629, "global_step": 528500, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.055168390274048, "global_step": 528501, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.999733567237854, "global_step": 528502, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9757142066955566, "global_step": 528503, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9991025924682617, "global_step": 528504, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9508973360061646, "global_step": 528505, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0097739696502686, "global_step": 528506, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0074875354766846, "global_step": 528507, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0776939392089844, "global_step": 528508, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9809490442276, "global_step": 528509, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9655869007110596, "global_step": 528510, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.047008752822876, "global_step": 528511, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0588321685791016, "global_step": 528512, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9956214427947998, "global_step": 528513, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0340633392333984, "global_step": 528514, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9695613384246826, "global_step": 528515, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0481760501861572, "global_step": 528516, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9164090156555176, "global_step": 528517, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0243852138519287, "global_step": 528518, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0255324840545654, "global_step": 528519, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.185605525970459, "global_step": 528520, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.049741506576538, "global_step": 528521, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.941877841949463, "global_step": 528522, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.041214942932129, "global_step": 528523, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0354716777801514, "global_step": 528524, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0661823749542236, "global_step": 528525, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0762388706207275, "global_step": 528526, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.082491636276245, "global_step": 528527, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0735456943511963, "global_step": 528528, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0217788219451904, "global_step": 528529, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1106019020080566, "global_step": 528530, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.039696455001831, "global_step": 528531, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0201282501220703, "global_step": 528532, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0335333347320557, "global_step": 528533, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.039950370788574, "global_step": 528534, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.162599563598633, "global_step": 528535, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1060264110565186, "global_step": 528536, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0589332580566406, "global_step": 528537, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9605103731155396, "global_step": 528538, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0588700771331787, "global_step": 528539, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9867279529571533, "global_step": 528540, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0757739543914795, "global_step": 528541, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0516574382781982, "global_step": 528542, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.024120569229126, "global_step": 528543, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.023467779159546, "global_step": 528544, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9749349355697632, "global_step": 528545, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.03631591796875, "global_step": 528546, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.013439655303955, "global_step": 528547, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0102176666259766, "global_step": 528548, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0147218704223633, "global_step": 528549, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0982325077056885, "global_step": 528550, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.117936372756958, "global_step": 528551, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.06390643119812, "global_step": 528552, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1037633419036865, "global_step": 528553, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1745619773864746, "global_step": 528554, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0501041412353516, "global_step": 528555, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1524479389190674, "global_step": 528556, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.041360378265381, "global_step": 528557, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0097732543945312, "global_step": 528558, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0404958724975586, "global_step": 528559, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0013577938079834, "global_step": 528560, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0546841621398926, "global_step": 528561, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9961118698120117, "global_step": 528562, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9281272888183594, "global_step": 528563, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.057002067565918, "global_step": 528564, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.041104316711426, "global_step": 528565, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.065809726715088, "global_step": 528566, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.081223964691162, "global_step": 528567, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0274853706359863, "global_step": 528568, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1071674823760986, "global_step": 528569, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.051740884780884, "global_step": 528570, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0459680557250977, "global_step": 528571, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.046315908432007, "global_step": 528572, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.059457540512085, "global_step": 528573, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.083341121673584, "global_step": 528574, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0023772716522217, "global_step": 528575, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.009046792984009, "global_step": 528576, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.037475347518921, "global_step": 528577, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.046194314956665, "global_step": 528578, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9999586343765259, "global_step": 528579, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0954549312591553, "global_step": 528580, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.992301344871521, "global_step": 528581, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.986335277557373, "global_step": 528582, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0500664710998535, "global_step": 528583, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0740654468536377, "global_step": 528584, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1057004928588867, "global_step": 528585, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.121002197265625, "global_step": 528586, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0969252586364746, "global_step": 528587, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.077624559402466, "global_step": 528588, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.030526876449585, "global_step": 528589, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.039027214050293, "global_step": 528590, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0488200187683105, "global_step": 528591, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0644633769989014, "global_step": 528592, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.027143955230713, "global_step": 528593, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9998327493667603, "global_step": 528594, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9950106143951416, "global_step": 528595, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.020639181137085, "global_step": 528596, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.994709849357605, "global_step": 528597, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0048840045928955, "global_step": 528598, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0182721614837646, "global_step": 528599, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9927234649658203, "global_step": 528600, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.98588228225708, "global_step": 528601, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.990580677986145, "global_step": 528602, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0088391304016113, "global_step": 528603, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0299057960510254, "global_step": 528604, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0516438484191895, "global_step": 528605, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.032435178756714, "global_step": 528606, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1482081413269043, "global_step": 528607, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0400514602661133, "global_step": 528608, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.026923656463623, "global_step": 528609, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0663626194000244, "global_step": 528610, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.022937536239624, "global_step": 528611, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.133791446685791, "global_step": 528612, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.059565544128418, "global_step": 528613, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0256690979003906, "global_step": 528614, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.024627685546875, "global_step": 528615, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0370655059814453, "global_step": 528616, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0244085788726807, "global_step": 528617, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0081584453582764, "global_step": 528618, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.148953437805176, "global_step": 528619, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.040952682495117, "global_step": 528620, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.05460262298584, "global_step": 528621, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.034663438796997, "global_step": 528622, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9790054559707642, "global_step": 528623, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.021284580230713, "global_step": 528624, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0331473350524902, "global_step": 528625, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9928879737854004, "global_step": 528626, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0772716999053955, "global_step": 528627, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.993748426437378, "global_step": 528628, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.047717332839966, "global_step": 528629, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9767574071884155, "global_step": 528630, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.169466733932495, "global_step": 528631, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.075157880783081, "global_step": 528632, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.914505958557129, "global_step": 528633, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9776067733764648, "global_step": 528634, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.04380464553833, "global_step": 528635, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1365256309509277, "global_step": 528636, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.071686029434204, "global_step": 528637, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1082139015197754, "global_step": 528638, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.127197742462158, "global_step": 528639, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.980019211769104, "global_step": 528640, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0365138053894043, "global_step": 528641, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0425169467926025, "global_step": 528642, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0939438343048096, "global_step": 528643, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0269410610198975, "global_step": 528644, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1329898834228516, "global_step": 528645, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0331366062164307, "global_step": 528646, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.075166702270508, "global_step": 528647, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.023833751678467, "global_step": 528648, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1333680152893066, "global_step": 528649, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0008084774017334, "global_step": 528650, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0724127292633057, "global_step": 528651, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0416641235351562, "global_step": 528652, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9928160905838013, "global_step": 528653, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.071540594100952, "global_step": 528654, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.134755849838257, "global_step": 528655, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.968751311302185, "global_step": 528656, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.076900005340576, "global_step": 528657, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0312345027923584, "global_step": 528658, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1015312671661377, "global_step": 528659, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0421271324157715, "global_step": 528660, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0007433891296387, "global_step": 528661, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.070235252380371, "global_step": 528662, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.104966878890991, "global_step": 528663, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.978956937789917, "global_step": 528664, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.001539945602417, "global_step": 528665, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.093597888946533, "global_step": 528666, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.045790910720825, "global_step": 528667, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0588796138763428, "global_step": 528668, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.89310622215271, "global_step": 528669, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0940301418304443, "global_step": 528670, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.004526376724243, "global_step": 528671, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.978781819343567, "global_step": 528672, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0466253757476807, "global_step": 528673, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0762569904327393, "global_step": 528674, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9819738864898682, "global_step": 528675, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0033366680145264, "global_step": 528676, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.072652816772461, "global_step": 528677, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.105039358139038, "global_step": 528678, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0682644844055176, "global_step": 528679, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1167218685150146, "global_step": 528680, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.03106951713562, "global_step": 528681, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9794809818267822, "global_step": 528682, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.02978515625, "global_step": 528683, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.060373067855835, "global_step": 528684, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.001049757003784, "global_step": 528685, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.063772201538086, "global_step": 528686, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0600056648254395, "global_step": 528687, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0184919834136963, "global_step": 528688, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9552860260009766, "global_step": 528689, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0502490997314453, "global_step": 528690, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0446367263793945, "global_step": 528691, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.046125888824463, "global_step": 528692, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0579259395599365, "global_step": 528693, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1200098991394043, "global_step": 528694, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.081757068634033, "global_step": 528695, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0689280033111572, "global_step": 528696, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0789172649383545, "global_step": 528697, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9738316535949707, "global_step": 528698, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0603573322296143, "global_step": 528699, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0456981658935547, "global_step": 528700, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9987521171569824, "global_step": 528701, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.973936676979065, "global_step": 528702, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0436160564422607, "global_step": 528703, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0737948417663574, "global_step": 528704, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1199474334716797, "global_step": 528705, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.003469944000244, "global_step": 528706, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0813679695129395, "global_step": 528707, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0906178951263428, "global_step": 528708, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.00254225730896, "global_step": 528709, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.070779323577881, "global_step": 528710, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0926833152770996, "global_step": 528711, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0115139484405518, "global_step": 528712, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.078052520751953, "global_step": 528713, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.984614372253418, "global_step": 528714, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9674056768417358, "global_step": 528715, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0482163429260254, "global_step": 528716, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.09883975982666, "global_step": 528717, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9820888042449951, "global_step": 528718, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.004164934158325, "global_step": 528719, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9866790771484375, "global_step": 528720, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0672144889831543, "global_step": 528721, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1166467666625977, "global_step": 528722, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.028048515319824, "global_step": 528723, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.019928455352783, "global_step": 528724, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9828753471374512, "global_step": 528725, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.12168288230896, "global_step": 528726, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0044479370117188, "global_step": 528727, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0435433387756348, "global_step": 528728, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.064920425415039, "global_step": 528729, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0477027893066406, "global_step": 528730, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.985504150390625, "global_step": 528731, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9918739795684814, "global_step": 528732, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.032658100128174, "global_step": 528733, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0621678829193115, "global_step": 528734, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1739063262939453, "global_step": 528735, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0265347957611084, "global_step": 528736, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.041198968887329, "global_step": 528737, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.048264265060425, "global_step": 528738, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.035062551498413, "global_step": 528739, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0512964725494385, "global_step": 528740, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.13629150390625, "global_step": 528741, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0900559425354004, "global_step": 528742, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0068533420562744, "global_step": 528743, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0177037715911865, "global_step": 528744, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.97773015499115, "global_step": 528745, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0242998600006104, "global_step": 528746, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9851949214935303, "global_step": 528747, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0349555015563965, "global_step": 528748, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.081552267074585, "global_step": 528749, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.182356595993042, "global_step": 528750, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0501537322998047, "global_step": 528751, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.921593189239502, "global_step": 528752, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0300142765045166, "global_step": 528753, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9998137950897217, "global_step": 528754, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0284996032714844, "global_step": 528755, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.078678846359253, "global_step": 528756, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9797208309173584, "global_step": 528757, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9673768281936646, "global_step": 528758, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0706679821014404, "global_step": 528759, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.079946517944336, "global_step": 528760, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1102890968322754, "global_step": 528761, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0938026905059814, "global_step": 528762, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0424652099609375, "global_step": 528763, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0138590335845947, "global_step": 528764, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9408320188522339, "global_step": 528765, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.002521514892578, "global_step": 528766, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9964408874511719, "global_step": 528767, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9457738399505615, "global_step": 528768, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0387580394744873, "global_step": 528769, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1369097232818604, "global_step": 528770, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.073671579360962, "global_step": 528771, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.023176908493042, "global_step": 528772, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.019652843475342, "global_step": 528773, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.066748857498169, "global_step": 528774, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.997515320777893, "global_step": 528775, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.043396234512329, "global_step": 528776, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9906638860702515, "global_step": 528777, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9676978588104248, "global_step": 528778, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.008702278137207, "global_step": 528779, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0013129711151123, "global_step": 528780, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.995574951171875, "global_step": 528781, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.071767568588257, "global_step": 528782, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.012943744659424, "global_step": 528783, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.019979238510132, "global_step": 528784, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1117546558380127, "global_step": 528785, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0005943775177, "global_step": 528786, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.050640344619751, "global_step": 528787, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0142531394958496, "global_step": 528788, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0827012062072754, "global_step": 528789, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.030947208404541, "global_step": 528790, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.023498058319092, "global_step": 528791, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0617523193359375, "global_step": 528792, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1467792987823486, "global_step": 528793, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0955731868743896, "global_step": 528794, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0707623958587646, "global_step": 528795, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0912423133850098, "global_step": 528796, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.057309150695801, "global_step": 528797, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0248570442199707, "global_step": 528798, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0338995456695557, "global_step": 528799, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.015852212905884, "global_step": 528800, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0759966373443604, "global_step": 528801, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9875673055648804, "global_step": 528802, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.990907907485962, "global_step": 528803, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1301023960113525, "global_step": 528804, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.084282159805298, "global_step": 528805, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.051309108734131, "global_step": 528806, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0711963176727295, "global_step": 528807, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.042508363723755, "global_step": 528808, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.066439628601074, "global_step": 528809, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0574452877044678, "global_step": 528810, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.023266077041626, "global_step": 528811, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0030534267425537, "global_step": 528812, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.059666395187378, "global_step": 528813, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9889057874679565, "global_step": 528814, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9700207710266113, "global_step": 528815, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0285630226135254, "global_step": 528816, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.985589623451233, "global_step": 528817, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9789327383041382, "global_step": 528818, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0121281147003174, "global_step": 528819, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0659003257751465, "global_step": 528820, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9899464845657349, "global_step": 528821, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0749447345733643, "global_step": 528822, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0559756755828857, "global_step": 528823, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9872870445251465, "global_step": 528824, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.017190933227539, "global_step": 528825, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0352084636688232, "global_step": 528826, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0012927055358887, "global_step": 528827, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.019714593887329, "global_step": 528828, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1495256423950195, "global_step": 528829, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.04117488861084, "global_step": 528830, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0008411407470703, "global_step": 528831, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.992501139640808, "global_step": 528832, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0317304134368896, "global_step": 528833, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0901081562042236, "global_step": 528834, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1443889141082764, "global_step": 528835, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0377614498138428, "global_step": 528836, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.026550531387329, "global_step": 528837, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1404545307159424, "global_step": 528838, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9867357015609741, "global_step": 528839, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0176758766174316, "global_step": 528840, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9882848262786865, "global_step": 528841, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.025757312774658, "global_step": 528842, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9777132272720337, "global_step": 528843, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1334757804870605, "global_step": 528844, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0236806869506836, "global_step": 528845, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.036026954650879, "global_step": 528846, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1503052711486816, "global_step": 528847, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.082003116607666, "global_step": 528848, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.147434949874878, "global_step": 528849, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0931389331817627, "global_step": 528850, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0462183952331543, "global_step": 528851, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1617345809936523, "global_step": 528852, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0360162258148193, "global_step": 528853, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0449931621551514, "global_step": 528854, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.068373918533325, "global_step": 528855, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0191102027893066, "global_step": 528856, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.078678607940674, "global_step": 528857, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.071868419647217, "global_step": 528858, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.059415340423584, "global_step": 528859, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0403504371643066, "global_step": 528860, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0220773220062256, "global_step": 528861, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0092387199401855, "global_step": 528862, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.054081916809082, "global_step": 528863, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.047316074371338, "global_step": 528864, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0017149448394775, "global_step": 528865, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0167603492736816, "global_step": 528866, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0786893367767334, "global_step": 528867, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1051008701324463, "global_step": 528868, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.04911208152771, "global_step": 528869, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1085500717163086, "global_step": 528870, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.038997173309326, "global_step": 528871, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9968122243881226, "global_step": 528872, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0465893745422363, "global_step": 528873, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.005812883377075, "global_step": 528874, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0041730403900146, "global_step": 528875, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0348851680755615, "global_step": 528876, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.068387746810913, "global_step": 528877, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0570709705352783, "global_step": 528878, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1022140979766846, "global_step": 528879, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0494883060455322, "global_step": 528880, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.032022476196289, "global_step": 528881, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9697091579437256, "global_step": 528882, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.018399715423584, "global_step": 528883, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.06575870513916, "global_step": 528884, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0513877868652344, "global_step": 528885, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0151078701019287, "global_step": 528886, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.072658061981201, "global_step": 528887, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9868619441986084, "global_step": 528888, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.007617950439453, "global_step": 528889, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0038411617279053, "global_step": 528890, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.08327579498291, "global_step": 528891, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.010467529296875, "global_step": 528892, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9815614223480225, "global_step": 528893, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9710242748260498, "global_step": 528894, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0843849182128906, "global_step": 528895, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0700154304504395, "global_step": 528896, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0364177227020264, "global_step": 528897, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0457139015197754, "global_step": 528898, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9730557203292847, "global_step": 528899, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.101613998413086, "global_step": 528900, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0874276161193848, "global_step": 528901, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.050550937652588, "global_step": 528902, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.034452199935913, "global_step": 528903, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1047322750091553, "global_step": 528904, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0463032722473145, "global_step": 528905, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.084282875061035, "global_step": 528906, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1123156547546387, "global_step": 528907, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0423731803894043, "global_step": 528908, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0826239585876465, "global_step": 528909, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.073993444442749, "global_step": 528910, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.003858804702759, "global_step": 528911, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9909578561782837, "global_step": 528912, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0877368450164795, "global_step": 528913, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0156304836273193, "global_step": 528914, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1352434158325195, "global_step": 528915, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0148184299468994, "global_step": 528916, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9953131675720215, "global_step": 528917, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9796844720840454, "global_step": 528918, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9778953790664673, "global_step": 528919, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0565998554229736, "global_step": 528920, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.108468532562256, "global_step": 528921, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.044083833694458, "global_step": 528922, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.066932201385498, "global_step": 528923, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.067378520965576, "global_step": 528924, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0819058418273926, "global_step": 528925, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.081882953643799, "global_step": 528926, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9270836114883423, "global_step": 528927, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.983022928237915, "global_step": 528928, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.058112621307373, "global_step": 528929, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0087459087371826, "global_step": 528930, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0789794921875, "global_step": 528931, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.140449047088623, "global_step": 528932, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.060652256011963, "global_step": 528933, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.074085235595703, "global_step": 528934, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.043365478515625, "global_step": 528935, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.056079864501953, "global_step": 528936, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.059149980545044, "global_step": 528937, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.938010573387146, "global_step": 528938, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0228378772735596, "global_step": 528939, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0322964191436768, "global_step": 528940, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0482776165008545, "global_step": 528941, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.052846670150757, "global_step": 528942, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.084836483001709, "global_step": 528943, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0424089431762695, "global_step": 528944, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0217251777648926, "global_step": 528945, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0580437183380127, "global_step": 528946, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.053617477416992, "global_step": 528947, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0771944522857666, "global_step": 528948, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.057878017425537, "global_step": 528949, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.082887887954712, "global_step": 528950, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1158363819122314, "global_step": 528951, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.077059268951416, "global_step": 528952, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9960886240005493, "global_step": 528953, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1438684463500977, "global_step": 528954, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1248409748077393, "global_step": 528955, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9854503870010376, "global_step": 528956, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0919864177703857, "global_step": 528957, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9905388355255127, "global_step": 528958, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.050654411315918, "global_step": 528959, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1086511611938477, "global_step": 528960, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9447062015533447, "global_step": 528961, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.018467664718628, "global_step": 528962, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0964620113372803, "global_step": 528963, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0935897827148438, "global_step": 528964, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9800904989242554, "global_step": 528965, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0335936546325684, "global_step": 528966, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.09112548828125, "global_step": 528967, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.060044050216675, "global_step": 528968, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9886107444763184, "global_step": 528969, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0962631702423096, "global_step": 528970, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.077176332473755, "global_step": 528971, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.009730815887451, "global_step": 528972, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.072242021560669, "global_step": 528973, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.048043727874756, "global_step": 528974, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9117436408996582, "global_step": 528975, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.092013120651245, "global_step": 528976, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.16467022895813, "global_step": 528977, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9765877723693848, "global_step": 528978, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0292253494262695, "global_step": 528979, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.081683874130249, "global_step": 528980, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.078615427017212, "global_step": 528981, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9379205703735352, "global_step": 528982, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0165765285491943, "global_step": 528983, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.996803879737854, "global_step": 528984, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9944413900375366, "global_step": 528985, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.006413221359253, "global_step": 528986, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.965044617652893, "global_step": 528987, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9733392000198364, "global_step": 528988, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.014199733734131, "global_step": 528989, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0683910846710205, "global_step": 528990, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9499032497406006, "global_step": 528991, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.112759828567505, "global_step": 528992, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.03532075881958, "global_step": 528993, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0256242752075195, "global_step": 528994, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.050964832305908, "global_step": 528995, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.116769552230835, "global_step": 528996, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.056183338165283, "global_step": 528997, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.058997392654419, "global_step": 528998, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0823190212249756, "global_step": 528999, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9682683944702148, "global_step": 529000, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.975620985031128, "global_step": 529001, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.115090847015381, "global_step": 529002, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.059062957763672, "global_step": 529003, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.119335889816284, "global_step": 529004, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.084097385406494, "global_step": 529005, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1461260318756104, "global_step": 529006, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.07248854637146, "global_step": 529007, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.077418088912964, "global_step": 529008, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0156402587890625, "global_step": 529009, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0976366996765137, "global_step": 529010, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0482428073883057, "global_step": 529011, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0431768894195557, "global_step": 529012, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.127495527267456, "global_step": 529013, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.068007469177246, "global_step": 529014, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.105468273162842, "global_step": 529015, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.114309549331665, "global_step": 529016, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.045417547225952, "global_step": 529017, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0534937381744385, "global_step": 529018, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0495834350585938, "global_step": 529019, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.058234453201294, "global_step": 529020, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.966093897819519, "global_step": 529021, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.043280601501465, "global_step": 529022, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.045017719268799, "global_step": 529023, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.077296733856201, "global_step": 529024, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0898427963256836, "global_step": 529025, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.136139154434204, "global_step": 529026, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.053272008895874, "global_step": 529027, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.102550983428955, "global_step": 529028, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0876011848449707, "global_step": 529029, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9694395065307617, "global_step": 529030, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1221537590026855, "global_step": 529031, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0765247344970703, "global_step": 529032, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9991450309753418, "global_step": 529033, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.015307664871216, "global_step": 529034, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0742578506469727, "global_step": 529035, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1585352420806885, "global_step": 529036, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0466055870056152, "global_step": 529037, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0169003009796143, "global_step": 529038, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0697500705718994, "global_step": 529039, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1319973468780518, "global_step": 529040, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0269250869750977, "global_step": 529041, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0831527709960938, "global_step": 529042, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.01098370552063, "global_step": 529043, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.001495599746704, "global_step": 529044, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0855512619018555, "global_step": 529045, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9868584871292114, "global_step": 529046, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0448431968688965, "global_step": 529047, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.080049753189087, "global_step": 529048, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0987513065338135, "global_step": 529049, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0947916507720947, "global_step": 529050, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.103440523147583, "global_step": 529051, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0947253704071045, "global_step": 529052, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9875314235687256, "global_step": 529053, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0162863731384277, "global_step": 529054, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.022951364517212, "global_step": 529055, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0465970039367676, "global_step": 529056, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.2049906253814697, "global_step": 529057, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0783016681671143, "global_step": 529058, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1046786308288574, "global_step": 529059, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.037369966506958, "global_step": 529060, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0418171882629395, "global_step": 529061, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.008737564086914, "global_step": 529062, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.046239137649536, "global_step": 529063, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.060776948928833, "global_step": 529064, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0682871341705322, "global_step": 529065, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.058901071548462, "global_step": 529066, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9844967126846313, "global_step": 529067, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0446505546569824, "global_step": 529068, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0014188289642334, "global_step": 529069, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.083146810531616, "global_step": 529070, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.074646234512329, "global_step": 529071, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9619276523590088, "global_step": 529072, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.060695171356201, "global_step": 529073, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0761501789093018, "global_step": 529074, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0201051235198975, "global_step": 529075, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.007127285003662, "global_step": 529076, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1373088359832764, "global_step": 529077, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.011859893798828, "global_step": 529078, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.090193748474121, "global_step": 529079, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0756726264953613, "global_step": 529080, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.066967725753784, "global_step": 529081, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9625674486160278, "global_step": 529082, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0973243713378906, "global_step": 529083, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9509931802749634, "global_step": 529084, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1085031032562256, "global_step": 529085, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.073460817337036, "global_step": 529086, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.065063953399658, "global_step": 529087, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0569794178009033, "global_step": 529088, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.100400686264038, "global_step": 529089, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9948314428329468, "global_step": 529090, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0743908882141113, "global_step": 529091, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.059621810913086, "global_step": 529092, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0507097244262695, "global_step": 529093, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1385598182678223, "global_step": 529094, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.058152675628662, "global_step": 529095, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1136229038238525, "global_step": 529096, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9862608909606934, "global_step": 529097, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0551295280456543, "global_step": 529098, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.11470365524292, "global_step": 529099, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.083178758621216, "global_step": 529100, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0651986598968506, "global_step": 529101, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.081561803817749, "global_step": 529102, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.09094500541687, "global_step": 529103, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.035655975341797, "global_step": 529104, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9846702814102173, "global_step": 529105, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0893545150756836, "global_step": 529106, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0784380435943604, "global_step": 529107, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1007776260375977, "global_step": 529108, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0522310733795166, "global_step": 529109, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0659773349761963, "global_step": 529110, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9865120649337769, "global_step": 529111, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9895578622817993, "global_step": 529112, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1016769409179688, "global_step": 529113, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0867226123809814, "global_step": 529114, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0273780822753906, "global_step": 529115, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9921833276748657, "global_step": 529116, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.105332136154175, "global_step": 529117, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.142421245574951, "global_step": 529118, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0923609733581543, "global_step": 529119, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1077585220336914, "global_step": 529120, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0327649116516113, "global_step": 529121, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0534873008728027, "global_step": 529122, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.008694887161255, "global_step": 529123, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0974535942077637, "global_step": 529124, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9849631786346436, "global_step": 529125, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1274733543395996, "global_step": 529126, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0639278888702393, "global_step": 529127, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.052257537841797, "global_step": 529128, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9908021688461304, "global_step": 529129, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0382277965545654, "global_step": 529130, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.005552053451538, "global_step": 529131, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9641714096069336, "global_step": 529132, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0177536010742188, "global_step": 529133, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.039273500442505, "global_step": 529134, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0254149436950684, "global_step": 529135, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0346877574920654, "global_step": 529136, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0112690925598145, "global_step": 529137, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.002396821975708, "global_step": 529138, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0902259349823, "global_step": 529139, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.059988021850586, "global_step": 529140, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9862098693847656, "global_step": 529141, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.061147928237915, "global_step": 529142, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0516858100891113, "global_step": 529143, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0555336475372314, "global_step": 529144, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0698330402374268, "global_step": 529145, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0999181270599365, "global_step": 529146, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.108891010284424, "global_step": 529147, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0407252311706543, "global_step": 529148, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9464389085769653, "global_step": 529149, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1035120487213135, "global_step": 529150, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0411157608032227, "global_step": 529151, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0248239040374756, "global_step": 529152, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0117228031158447, "global_step": 529153, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.054513931274414, "global_step": 529154, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0681352615356445, "global_step": 529155, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.044654607772827, "global_step": 529156, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0024256706237793, "global_step": 529157, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.919503092765808, "global_step": 529158, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0580990314483643, "global_step": 529159, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1270530223846436, "global_step": 529160, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0084211826324463, "global_step": 529161, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9175293445587158, "global_step": 529162, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1590068340301514, "global_step": 529163, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.085008382797241, "global_step": 529164, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.015393018722534, "global_step": 529165, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0359065532684326, "global_step": 529166, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0652565956115723, "global_step": 529167, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.023888111114502, "global_step": 529168, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.050459861755371, "global_step": 529169, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.014432668685913, "global_step": 529170, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0922303199768066, "global_step": 529171, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0295300483703613, "global_step": 529172, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0087478160858154, "global_step": 529173, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9675958156585693, "global_step": 529174, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.126291513442993, "global_step": 529175, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9841973781585693, "global_step": 529176, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.152597188949585, "global_step": 529177, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9538304805755615, "global_step": 529178, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.06583833694458, "global_step": 529179, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0447983741760254, "global_step": 529180, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0818300247192383, "global_step": 529181, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9965728521347046, "global_step": 529182, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.075078010559082, "global_step": 529183, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0881567001342773, "global_step": 529184, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0924794673919678, "global_step": 529185, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0067970752716064, "global_step": 529186, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0178639888763428, "global_step": 529187, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0652337074279785, "global_step": 529188, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.115795850753784, "global_step": 529189, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.037243127822876, "global_step": 529190, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0634713172912598, "global_step": 529191, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.023918628692627, "global_step": 529192, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.963951587677002, "global_step": 529193, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.007399559020996, "global_step": 529194, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.063945770263672, "global_step": 529195, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9980031251907349, "global_step": 529196, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0000994205474854, "global_step": 529197, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.15256404876709, "global_step": 529198, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.1014835834503174, "global_step": 529199, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.101226329803467, "global_step": 529200, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.064000368118286, "global_step": 529201, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9950705766677856, "global_step": 529202, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0732498168945312, "global_step": 529203, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.061443328857422, "global_step": 529204, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.014832019805908, "global_step": 529205, "epoch": 895, "lr": 5e-05}
{"train_loss": 2.0421366691589355, "global_step": 529206, "epoch": 895, "lr": 5e-05}
{"train_loss": 1.9785971641540527, "global_step": 529207, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.001776695251465, "global_step": 529208, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9733060598373413, "global_step": 529209, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.8890526294708252, "global_step": 529210, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9690430164337158, "global_step": 529211, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0395030975341797, "global_step": 529212, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.004169225692749, "global_step": 529213, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0030176639556885, "global_step": 529214, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1083405017852783, "global_step": 529215, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.001068353652954, "global_step": 529216, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0777292251586914, "global_step": 529217, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0644571781158447, "global_step": 529218, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9240299463272095, "global_step": 529219, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0457370281219482, "global_step": 529220, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0783944129943848, "global_step": 529221, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.005519151687622, "global_step": 529222, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.003694534301758, "global_step": 529223, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0118918418884277, "global_step": 529224, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0593338012695312, "global_step": 529225, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.014845609664917, "global_step": 529226, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9961004257202148, "global_step": 529227, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0317933559417725, "global_step": 529228, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.998795747756958, "global_step": 529229, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.066309928894043, "global_step": 529230, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9707106351852417, "global_step": 529231, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0312719345092773, "global_step": 529232, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9915605783462524, "global_step": 529233, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.054410219192505, "global_step": 529234, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.04886794090271, "global_step": 529235, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.022595167160034, "global_step": 529236, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.034186363220215, "global_step": 529237, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.98946213722229, "global_step": 529238, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0591390132904053, "global_step": 529239, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1075387001037598, "global_step": 529240, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0549962520599365, "global_step": 529241, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9721633195877075, "global_step": 529242, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.15018630027771, "global_step": 529243, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.028003692626953, "global_step": 529244, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0586700439453125, "global_step": 529245, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0532455444335938, "global_step": 529246, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0241377353668213, "global_step": 529247, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9301553964614868, "global_step": 529248, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0674047470092773, "global_step": 529249, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0459249019622803, "global_step": 529250, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0185890197753906, "global_step": 529251, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9769724607467651, "global_step": 529252, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9411019086837769, "global_step": 529253, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0306520462036133, "global_step": 529254, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9879957437515259, "global_step": 529255, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0156993865966797, "global_step": 529256, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9770156145095825, "global_step": 529257, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.979819655418396, "global_step": 529258, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0630288124084473, "global_step": 529259, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0388457775115967, "global_step": 529260, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.069518804550171, "global_step": 529261, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.015681028366089, "global_step": 529262, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0781338214874268, "global_step": 529263, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.066152334213257, "global_step": 529264, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.013046979904175, "global_step": 529265, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.042712688446045, "global_step": 529266, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.057042360305786, "global_step": 529267, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.966822862625122, "global_step": 529268, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.006742477416992, "global_step": 529269, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.086365222930908, "global_step": 529270, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0116488933563232, "global_step": 529271, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0177161693573, "global_step": 529272, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.929946780204773, "global_step": 529273, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9977738857269287, "global_step": 529274, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.007554292678833, "global_step": 529275, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.979481816291809, "global_step": 529276, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9953036308288574, "global_step": 529277, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9768766164779663, "global_step": 529278, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1045429706573486, "global_step": 529279, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0200765132904053, "global_step": 529280, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9676284790039062, "global_step": 529281, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1614766120910645, "global_step": 529282, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.029651403427124, "global_step": 529283, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0588483810424805, "global_step": 529284, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.04148530960083, "global_step": 529285, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0238375663757324, "global_step": 529286, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.985657811164856, "global_step": 529287, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0668258666992188, "global_step": 529288, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0204551219940186, "global_step": 529289, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9197344779968262, "global_step": 529290, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9863725900650024, "global_step": 529291, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.02870774269104, "global_step": 529292, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0814337730407715, "global_step": 529293, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0926458835601807, "global_step": 529294, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1077892780303955, "global_step": 529295, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9455242156982422, "global_step": 529296, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9898065328598022, "global_step": 529297, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1082522869110107, "global_step": 529298, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.053119421005249, "global_step": 529299, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.06430983543396, "global_step": 529300, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0285329818725586, "global_step": 529301, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0124032497406006, "global_step": 529302, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.935228705406189, "global_step": 529303, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.982727289199829, "global_step": 529304, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0075771808624268, "global_step": 529305, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9743010997772217, "global_step": 529306, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.989172101020813, "global_step": 529307, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1353759765625, "global_step": 529308, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0018482208251953, "global_step": 529309, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.066124200820923, "global_step": 529310, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.105884075164795, "global_step": 529311, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0204250812530518, "global_step": 529312, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.092373847961426, "global_step": 529313, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0310542583465576, "global_step": 529314, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0494649410247803, "global_step": 529315, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9270771741867065, "global_step": 529316, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0709140300750732, "global_step": 529317, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0116546154022217, "global_step": 529318, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.003993511199951, "global_step": 529319, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.012539863586426, "global_step": 529320, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.987121343612671, "global_step": 529321, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0007572174072266, "global_step": 529322, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9920763969421387, "global_step": 529323, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0153355598449707, "global_step": 529324, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.009763717651367, "global_step": 529325, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.194230318069458, "global_step": 529326, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.023430109024048, "global_step": 529327, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0043256282806396, "global_step": 529328, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0913991928100586, "global_step": 529329, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0424304008483887, "global_step": 529330, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.049421787261963, "global_step": 529331, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0213730335235596, "global_step": 529332, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0773983001708984, "global_step": 529333, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9651353359222412, "global_step": 529334, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9917099475860596, "global_step": 529335, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.083627462387085, "global_step": 529336, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0186755657196045, "global_step": 529337, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0605883598327637, "global_step": 529338, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.017151355743408, "global_step": 529339, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.020453929901123, "global_step": 529340, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.192939281463623, "global_step": 529341, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9803084135055542, "global_step": 529342, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9694068431854248, "global_step": 529343, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0019679069519043, "global_step": 529344, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0863428115844727, "global_step": 529345, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.034688711166382, "global_step": 529346, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.041221857070923, "global_step": 529347, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0474069118499756, "global_step": 529348, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9797322750091553, "global_step": 529349, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0446929931640625, "global_step": 529350, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.156996726989746, "global_step": 529351, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.100341558456421, "global_step": 529352, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0346386432647705, "global_step": 529353, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.073927640914917, "global_step": 529354, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0552139282226562, "global_step": 529355, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0892491340637207, "global_step": 529356, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0238664150238037, "global_step": 529357, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1291146278381348, "global_step": 529358, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0767858028411865, "global_step": 529359, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0082547664642334, "global_step": 529360, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9366246461868286, "global_step": 529361, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9696513414382935, "global_step": 529362, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.023577928543091, "global_step": 529363, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9480955600738525, "global_step": 529364, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0131242275238037, "global_step": 529365, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0091028213500977, "global_step": 529366, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.107731342315674, "global_step": 529367, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0389370918273926, "global_step": 529368, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.10378098487854, "global_step": 529369, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0915849208831787, "global_step": 529370, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.020618438720703, "global_step": 529371, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.024543523788452, "global_step": 529372, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0736472606658936, "global_step": 529373, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0961596965789795, "global_step": 529374, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.053100109100342, "global_step": 529375, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0606260299682617, "global_step": 529376, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0645675659179688, "global_step": 529377, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0341715812683105, "global_step": 529378, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.987750768661499, "global_step": 529379, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.971388339996338, "global_step": 529380, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0881993770599365, "global_step": 529381, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.02095365524292, "global_step": 529382, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.051637649536133, "global_step": 529383, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.062283515930176, "global_step": 529384, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.034916639328003, "global_step": 529385, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.080174446105957, "global_step": 529386, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.106294870376587, "global_step": 529387, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.049739122390747, "global_step": 529388, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9494221210479736, "global_step": 529389, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.072910785675049, "global_step": 529390, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0616893768310547, "global_step": 529391, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0002713203430176, "global_step": 529392, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9218971729278564, "global_step": 529393, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9558559656143188, "global_step": 529394, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0220253467559814, "global_step": 529395, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9755451679229736, "global_step": 529396, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0467379093170166, "global_step": 529397, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.074307441711426, "global_step": 529398, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.118501901626587, "global_step": 529399, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0386366844177246, "global_step": 529400, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.055544376373291, "global_step": 529401, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0014569759368896, "global_step": 529402, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0292303562164307, "global_step": 529403, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.000866174697876, "global_step": 529404, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0133988857269287, "global_step": 529405, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9877628087997437, "global_step": 529406, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9594544172286987, "global_step": 529407, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0767061710357666, "global_step": 529408, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0151925086975098, "global_step": 529409, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0950303077697754, "global_step": 529410, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0517876148223877, "global_step": 529411, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0453224182128906, "global_step": 529412, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0224218368530273, "global_step": 529413, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0534093379974365, "global_step": 529414, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0214574337005615, "global_step": 529415, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0433099269866943, "global_step": 529416, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1031596660614014, "global_step": 529417, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9228326082229614, "global_step": 529418, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.023163318634033, "global_step": 529419, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0708119869232178, "global_step": 529420, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0126349925994873, "global_step": 529421, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.017118453979492, "global_step": 529422, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.023552179336548, "global_step": 529423, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0429155826568604, "global_step": 529424, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9570313692092896, "global_step": 529425, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9481825828552246, "global_step": 529426, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0073394775390625, "global_step": 529427, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.018361806869507, "global_step": 529428, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.046825647354126, "global_step": 529429, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0594704151153564, "global_step": 529430, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0180065631866455, "global_step": 529431, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9844181537628174, "global_step": 529432, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9402986764907837, "global_step": 529433, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.083500862121582, "global_step": 529434, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0319623947143555, "global_step": 529435, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.011296272277832, "global_step": 529436, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0128238201141357, "global_step": 529437, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0645523071289062, "global_step": 529438, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0642926692962646, "global_step": 529439, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0738260746002197, "global_step": 529440, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.992497444152832, "global_step": 529441, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0976598262786865, "global_step": 529442, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0024027824401855, "global_step": 529443, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.078580379486084, "global_step": 529444, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9462916851043701, "global_step": 529445, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9453778266906738, "global_step": 529446, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9904638528823853, "global_step": 529447, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0829691886901855, "global_step": 529448, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.000930070877075, "global_step": 529449, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0321943759918213, "global_step": 529450, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0394301414489746, "global_step": 529451, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0312747955322266, "global_step": 529452, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.020754337310791, "global_step": 529453, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0283234119415283, "global_step": 529454, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.009874105453491, "global_step": 529455, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0895636081695557, "global_step": 529456, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0962767601013184, "global_step": 529457, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0581769943237305, "global_step": 529458, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9973005056381226, "global_step": 529459, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.983797311782837, "global_step": 529460, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.121290922164917, "global_step": 529461, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.046372413635254, "global_step": 529462, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.025646448135376, "global_step": 529463, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0044500827789307, "global_step": 529464, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0624992847442627, "global_step": 529465, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9266345500946045, "global_step": 529466, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1086723804473877, "global_step": 529467, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.035332202911377, "global_step": 529468, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1163995265960693, "global_step": 529469, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.026092529296875, "global_step": 529470, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.053805351257324, "global_step": 529471, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9904850721359253, "global_step": 529472, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9482101202011108, "global_step": 529473, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.079747438430786, "global_step": 529474, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.067662239074707, "global_step": 529475, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.035454273223877, "global_step": 529476, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0302278995513916, "global_step": 529477, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.992514729499817, "global_step": 529478, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.015535354614258, "global_step": 529479, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.009047031402588, "global_step": 529480, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0123403072357178, "global_step": 529481, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.013209819793701, "global_step": 529482, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9954814910888672, "global_step": 529483, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9966444969177246, "global_step": 529484, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0452516078948975, "global_step": 529485, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0448668003082275, "global_step": 529486, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.032615900039673, "global_step": 529487, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0562925338745117, "global_step": 529488, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0687365531921387, "global_step": 529489, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0038020610809326, "global_step": 529490, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0630314350128174, "global_step": 529491, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9919320344924927, "global_step": 529492, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.996042251586914, "global_step": 529493, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0025641918182373, "global_step": 529494, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0650410652160645, "global_step": 529495, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1130385398864746, "global_step": 529496, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0803956985473633, "global_step": 529497, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9538023471832275, "global_step": 529498, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.086684226989746, "global_step": 529499, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.086768627166748, "global_step": 529500, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0357141494750977, "global_step": 529501, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0826199054718018, "global_step": 529502, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.049454689025879, "global_step": 529503, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9699410200119019, "global_step": 529504, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0077524185180664, "global_step": 529505, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.014833688735962, "global_step": 529506, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1234092712402344, "global_step": 529507, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.042194128036499, "global_step": 529508, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9367949962615967, "global_step": 529509, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.069511890411377, "global_step": 529510, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.041362762451172, "global_step": 529511, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0622897148132324, "global_step": 529512, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0424957275390625, "global_step": 529513, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.066718816757202, "global_step": 529514, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0202059745788574, "global_step": 529515, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1257996559143066, "global_step": 529516, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0354206562042236, "global_step": 529517, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.012479066848755, "global_step": 529518, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0619707107543945, "global_step": 529519, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9960979223251343, "global_step": 529520, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9732695817947388, "global_step": 529521, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.128035545349121, "global_step": 529522, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0450143814086914, "global_step": 529523, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.106614589691162, "global_step": 529524, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0229105949401855, "global_step": 529525, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.021141767501831, "global_step": 529526, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9843908548355103, "global_step": 529527, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0749869346618652, "global_step": 529528, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0218963623046875, "global_step": 529529, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0651326179504395, "global_step": 529530, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9945850372314453, "global_step": 529531, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.040705919265747, "global_step": 529532, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0375499725341797, "global_step": 529533, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0228981971740723, "global_step": 529534, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0147705078125, "global_step": 529535, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0495758056640625, "global_step": 529536, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.013228416442871, "global_step": 529537, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.884524941444397, "global_step": 529538, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9909281730651855, "global_step": 529539, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1244523525238037, "global_step": 529540, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.037400960922241, "global_step": 529541, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0095338821411133, "global_step": 529542, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9943870306015015, "global_step": 529543, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0353612899780273, "global_step": 529544, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.032805919647217, "global_step": 529545, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0858240127563477, "global_step": 529546, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0491812229156494, "global_step": 529547, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0390536785125732, "global_step": 529548, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.02470326423645, "global_step": 529549, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.04854154586792, "global_step": 529550, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0751144886016846, "global_step": 529551, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0303356647491455, "global_step": 529552, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.072737216949463, "global_step": 529553, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9786306619644165, "global_step": 529554, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.002763509750366, "global_step": 529555, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.96494460105896, "global_step": 529556, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.133976936340332, "global_step": 529557, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.113981246948242, "global_step": 529558, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0586304664611816, "global_step": 529559, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.146798610687256, "global_step": 529560, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9865330457687378, "global_step": 529561, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.026479959487915, "global_step": 529562, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.073984146118164, "global_step": 529563, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0542309284210205, "global_step": 529564, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.994428277015686, "global_step": 529565, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.069624662399292, "global_step": 529566, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9616148471832275, "global_step": 529567, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9928861856460571, "global_step": 529568, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0191140174865723, "global_step": 529569, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9924896955490112, "global_step": 529570, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0368025302886963, "global_step": 529571, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9805219173431396, "global_step": 529572, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9806376695632935, "global_step": 529573, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0033998489379883, "global_step": 529574, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0202033519744873, "global_step": 529575, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0378992557525635, "global_step": 529576, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.036348581314087, "global_step": 529577, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1084563732147217, "global_step": 529578, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.029360055923462, "global_step": 529579, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0494494438171387, "global_step": 529580, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.005965232849121, "global_step": 529581, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.085952043533325, "global_step": 529582, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0773799419403076, "global_step": 529583, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0471038818359375, "global_step": 529584, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0234501361846924, "global_step": 529585, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.002767324447632, "global_step": 529586, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0974783897399902, "global_step": 529587, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.120910406112671, "global_step": 529588, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0506317615509033, "global_step": 529589, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.106794834136963, "global_step": 529590, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9954794645309448, "global_step": 529591, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.008570432662964, "global_step": 529592, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0391414165496826, "global_step": 529593, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9563899040222168, "global_step": 529594, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.115917682647705, "global_step": 529595, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.001066207885742, "global_step": 529596, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0207881927490234, "global_step": 529597, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0666701793670654, "global_step": 529598, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0828347206115723, "global_step": 529599, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9964302778244019, "global_step": 529600, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1851320266723633, "global_step": 529601, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.054187059402466, "global_step": 529602, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.952011227607727, "global_step": 529603, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.045832872390747, "global_step": 529604, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.992372751235962, "global_step": 529605, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0120019912719727, "global_step": 529606, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0333564281463623, "global_step": 529607, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0043697357177734, "global_step": 529608, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.070450782775879, "global_step": 529609, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9719791412353516, "global_step": 529610, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.016582489013672, "global_step": 529611, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.07444167137146, "global_step": 529612, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.022264242172241, "global_step": 529613, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.012664794921875, "global_step": 529614, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.036893844604492, "global_step": 529615, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0434317588806152, "global_step": 529616, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.079838752746582, "global_step": 529617, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1366519927978516, "global_step": 529618, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9560770988464355, "global_step": 529619, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0233776569366455, "global_step": 529620, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.064910411834717, "global_step": 529621, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.052259922027588, "global_step": 529622, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0530169010162354, "global_step": 529623, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0577476024627686, "global_step": 529624, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.060676336288452, "global_step": 529625, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0258259773254395, "global_step": 529626, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0698230266571045, "global_step": 529627, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0696399211883545, "global_step": 529628, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9860674142837524, "global_step": 529629, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1032888889312744, "global_step": 529630, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.016505479812622, "global_step": 529631, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0545666217803955, "global_step": 529632, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.111454725265503, "global_step": 529633, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0517489910125732, "global_step": 529634, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0543835163116455, "global_step": 529635, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0694093704223633, "global_step": 529636, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0978140830993652, "global_step": 529637, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0176422595977783, "global_step": 529638, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.089337110519409, "global_step": 529639, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9835408926010132, "global_step": 529640, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9770139455795288, "global_step": 529641, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.080203056335449, "global_step": 529642, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0514814853668213, "global_step": 529643, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9716107845306396, "global_step": 529644, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.102613687515259, "global_step": 529645, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9894987344741821, "global_step": 529646, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0377285480499268, "global_step": 529647, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.072929859161377, "global_step": 529648, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.998924970626831, "global_step": 529649, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9609781503677368, "global_step": 529650, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.099374771118164, "global_step": 529651, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9560661315917969, "global_step": 529652, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.047043561935425, "global_step": 529653, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.084099292755127, "global_step": 529654, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0889766216278076, "global_step": 529655, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.080794334411621, "global_step": 529656, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0652992725372314, "global_step": 529657, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.943569302558899, "global_step": 529658, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0890843868255615, "global_step": 529659, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0032684803009033, "global_step": 529660, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0843050479888916, "global_step": 529661, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1601641178131104, "global_step": 529662, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0889034271240234, "global_step": 529663, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0942153930664062, "global_step": 529664, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9936190843582153, "global_step": 529665, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0617101192474365, "global_step": 529666, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0920536518096924, "global_step": 529667, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.989389419555664, "global_step": 529668, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0193233489990234, "global_step": 529669, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.05806040763855, "global_step": 529670, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0022315979003906, "global_step": 529671, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.048919677734375, "global_step": 529672, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.003349781036377, "global_step": 529673, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0600907802581787, "global_step": 529674, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0916295051574707, "global_step": 529675, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0601656436920166, "global_step": 529676, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9144282341003418, "global_step": 529677, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.015826463699341, "global_step": 529678, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.124756336212158, "global_step": 529679, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9826419353485107, "global_step": 529680, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.065056085586548, "global_step": 529681, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0275309085845947, "global_step": 529682, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.035094738006592, "global_step": 529683, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9750332832336426, "global_step": 529684, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0795769691467285, "global_step": 529685, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.041829824447632, "global_step": 529686, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0135977268218994, "global_step": 529687, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.091146469116211, "global_step": 529688, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9679994583129883, "global_step": 529689, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.111668825149536, "global_step": 529690, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.102792263031006, "global_step": 529691, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9917895793914795, "global_step": 529692, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0315825939178467, "global_step": 529693, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.061580181121826, "global_step": 529694, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.030364990234375, "global_step": 529695, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9696272611618042, "global_step": 529696, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0577797889709473, "global_step": 529697, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.000722646713257, "global_step": 529698, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.96723473072052, "global_step": 529699, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.040264368057251, "global_step": 529700, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9911255836486816, "global_step": 529701, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.026553153991699, "global_step": 529702, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.047574520111084, "global_step": 529703, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0874087810516357, "global_step": 529704, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0078012943267822, "global_step": 529705, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9443055391311646, "global_step": 529706, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0700721740722656, "global_step": 529707, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0667102336883545, "global_step": 529708, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9640690088272095, "global_step": 529709, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1227126121520996, "global_step": 529710, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9702258110046387, "global_step": 529711, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.030870199203491, "global_step": 529712, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0626380443573, "global_step": 529713, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.997809886932373, "global_step": 529714, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1437087059020996, "global_step": 529715, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0586044788360596, "global_step": 529716, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0671122074127197, "global_step": 529717, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0068864822387695, "global_step": 529718, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.055763006210327, "global_step": 529719, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0420620441436768, "global_step": 529720, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.021322250366211, "global_step": 529721, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0971953868865967, "global_step": 529722, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.063786745071411, "global_step": 529723, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0640788078308105, "global_step": 529724, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0450820922851562, "global_step": 529725, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9989601373672485, "global_step": 529726, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9692752361297607, "global_step": 529727, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0666394233703613, "global_step": 529728, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.072007417678833, "global_step": 529729, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9917240142822266, "global_step": 529730, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9875630140304565, "global_step": 529731, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.057920217514038, "global_step": 529732, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0079538822174072, "global_step": 529733, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.007194757461548, "global_step": 529734, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.024113178253174, "global_step": 529735, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.980079174041748, "global_step": 529736, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0389010906219482, "global_step": 529737, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0374343395233154, "global_step": 529738, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0267770290374756, "global_step": 529739, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0630412101745605, "global_step": 529740, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9756969213485718, "global_step": 529741, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.008711338043213, "global_step": 529742, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9987350702285767, "global_step": 529743, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.987046718597412, "global_step": 529744, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0757710933685303, "global_step": 529745, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9875344038009644, "global_step": 529746, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.041487216949463, "global_step": 529747, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0455307960510254, "global_step": 529748, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.041429281234741, "global_step": 529749, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9653006792068481, "global_step": 529750, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0893592834472656, "global_step": 529751, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9885573387145996, "global_step": 529752, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.05302095413208, "global_step": 529753, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0341055393218994, "global_step": 529754, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0286145210266113, "global_step": 529755, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.020087480545044, "global_step": 529756, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.033712863922119, "global_step": 529757, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9983898401260376, "global_step": 529758, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.079139232635498, "global_step": 529759, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0190038681030273, "global_step": 529760, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.062713146209717, "global_step": 529761, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.076364755630493, "global_step": 529762, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.074798583984375, "global_step": 529763, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0229403972625732, "global_step": 529764, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0136561393737793, "global_step": 529765, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.080047607421875, "global_step": 529766, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0462167263031006, "global_step": 529767, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0884270668029785, "global_step": 529768, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0198919773101807, "global_step": 529769, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.098586320877075, "global_step": 529770, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9902023077011108, "global_step": 529771, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.060438394546509, "global_step": 529772, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0359177589416504, "global_step": 529773, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0145416259765625, "global_step": 529774, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.054611921310425, "global_step": 529775, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0374255180358887, "global_step": 529776, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0864667892456055, "global_step": 529777, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.044727087020874, "global_step": 529778, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.116626024246216, "global_step": 529779, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9821300506591797, "global_step": 529780, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0409433841705322, "global_step": 529781, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0801007747650146, "global_step": 529782, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0453953742980957, "global_step": 529783, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.089385986328125, "global_step": 529784, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0752217769622803, "global_step": 529785, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0381362438201904, "global_step": 529786, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.053715944290161, "global_step": 529787, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.080780029296875, "global_step": 529788, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.026961088180542, "global_step": 529789, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.982972502708435, "global_step": 529790, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0447049140930176, "global_step": 529791, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.976043939590454, "global_step": 529792, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9876525402069092, "global_step": 529793, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0561015605926514, "global_step": 529794, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0800092220306396, "global_step": 529795, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9808048009872437, "global_step": 529796, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1369285583496094, "global_step": 529797, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0172791481018066, "global_step": 529798, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0408923625946045, "global_step": 529799, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.125863552093506, "global_step": 529800, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9789656400680542, "global_step": 529801, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.090013265609741, "global_step": 529802, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.972566843032837, "global_step": 529803, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0673937797546387, "global_step": 529804, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1664700508117676, "global_step": 529805, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0716896057128906, "global_step": 529806, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.101304292678833, "global_step": 529807, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.997542142868042, "global_step": 529808, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.059756278991699, "global_step": 529809, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.083448886871338, "global_step": 529810, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.13163423538208, "global_step": 529811, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1294357776641846, "global_step": 529812, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.02677583694458, "global_step": 529813, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.027167320251465, "global_step": 529814, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.02329683303833, "global_step": 529815, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0088398456573486, "global_step": 529816, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1156558990478516, "global_step": 529817, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.109060287475586, "global_step": 529818, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0974977016448975, "global_step": 529819, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.031416177749634, "global_step": 529820, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0846478939056396, "global_step": 529821, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.022840738296509, "global_step": 529822, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9341015815734863, "global_step": 529823, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.012716054916382, "global_step": 529824, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.008028030395508, "global_step": 529825, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0814130306243896, "global_step": 529826, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9936195611953735, "global_step": 529827, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9904383420944214, "global_step": 529828, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0809621810913086, "global_step": 529829, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9881551265716553, "global_step": 529830, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.015784740447998, "global_step": 529831, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.092621326446533, "global_step": 529832, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1038522720336914, "global_step": 529833, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9874430894851685, "global_step": 529834, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9600286483764648, "global_step": 529835, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.119847059249878, "global_step": 529836, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0397260189056396, "global_step": 529837, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1413707733154297, "global_step": 529838, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0513362884521484, "global_step": 529839, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0344700813293457, "global_step": 529840, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.964704155921936, "global_step": 529841, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0347840785980225, "global_step": 529842, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0687785148620605, "global_step": 529843, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.976214051246643, "global_step": 529844, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0193893909454346, "global_step": 529845, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1683897972106934, "global_step": 529846, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0219810009002686, "global_step": 529847, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9623682498931885, "global_step": 529848, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.098123788833618, "global_step": 529849, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1091222763061523, "global_step": 529850, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.075451135635376, "global_step": 529851, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9822453260421753, "global_step": 529852, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0032896995544434, "global_step": 529853, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0253777503967285, "global_step": 529854, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.001039981842041, "global_step": 529855, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0494401454925537, "global_step": 529856, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0232937335968018, "global_step": 529857, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0549838542938232, "global_step": 529858, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.978442668914795, "global_step": 529859, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0765161514282227, "global_step": 529860, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0410988330841064, "global_step": 529861, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0957820415496826, "global_step": 529862, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0667805671691895, "global_step": 529863, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.114071846008301, "global_step": 529864, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0290441513061523, "global_step": 529865, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.039292812347412, "global_step": 529866, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0633978843688965, "global_step": 529867, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9763877391815186, "global_step": 529868, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1072843074798584, "global_step": 529869, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1308019161224365, "global_step": 529870, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.023902654647827, "global_step": 529871, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.066894292831421, "global_step": 529872, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0824077129364014, "global_step": 529873, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.127805709838867, "global_step": 529874, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.093135118484497, "global_step": 529875, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.072467088699341, "global_step": 529876, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0110788345336914, "global_step": 529877, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.029630184173584, "global_step": 529878, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.042659044265747, "global_step": 529879, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.988605260848999, "global_step": 529880, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0215749740600586, "global_step": 529881, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.042722225189209, "global_step": 529882, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0795533657073975, "global_step": 529883, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0332043170928955, "global_step": 529884, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0254464149475098, "global_step": 529885, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1155338287353516, "global_step": 529886, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0587339401245117, "global_step": 529887, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.015761137008667, "global_step": 529888, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.122321844100952, "global_step": 529889, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0401148796081543, "global_step": 529890, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.083796739578247, "global_step": 529891, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.017815351486206, "global_step": 529892, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.987012267112732, "global_step": 529893, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.026289939880371, "global_step": 529894, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.142061948776245, "global_step": 529895, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0493810176849365, "global_step": 529896, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.045417308807373, "global_step": 529897, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0226621627807617, "global_step": 529898, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0475335121154785, "global_step": 529899, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.032524824142456, "global_step": 529900, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.932551622390747, "global_step": 529901, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.061119556427002, "global_step": 529902, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.00730299949646, "global_step": 529903, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0657646656036377, "global_step": 529904, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0884287357330322, "global_step": 529905, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.089642286300659, "global_step": 529906, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.046647548675537, "global_step": 529907, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.044584274291992, "global_step": 529908, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9853086471557617, "global_step": 529909, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0817320346832275, "global_step": 529910, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0553042888641357, "global_step": 529911, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0494110584259033, "global_step": 529912, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9934321641921997, "global_step": 529913, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0608983039855957, "global_step": 529914, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0440335273742676, "global_step": 529915, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.043440818786621, "global_step": 529916, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1170384883880615, "global_step": 529917, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.969423532485962, "global_step": 529918, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9858441352844238, "global_step": 529919, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.052159547805786, "global_step": 529920, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.12457013130188, "global_step": 529921, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.024477481842041, "global_step": 529922, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0703859329223633, "global_step": 529923, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.021109104156494, "global_step": 529924, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.046475648880005, "global_step": 529925, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9877785444259644, "global_step": 529926, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0067458152770996, "global_step": 529927, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.003099203109741, "global_step": 529928, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0052096843719482, "global_step": 529929, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0117270946502686, "global_step": 529930, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1012747287750244, "global_step": 529931, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.128803014755249, "global_step": 529932, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.153362512588501, "global_step": 529933, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9907913208007812, "global_step": 529934, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9266904592514038, "global_step": 529935, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0450847148895264, "global_step": 529936, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.083568572998047, "global_step": 529937, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0759506225585938, "global_step": 529938, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0442240238189697, "global_step": 529939, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1167469024658203, "global_step": 529940, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0392377376556396, "global_step": 529941, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.157625198364258, "global_step": 529942, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.024480104446411, "global_step": 529943, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.12572979927063, "global_step": 529944, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0424516201019287, "global_step": 529945, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.980301856994629, "global_step": 529946, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9821299314498901, "global_step": 529947, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0528433322906494, "global_step": 529948, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.062575578689575, "global_step": 529949, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.028634786605835, "global_step": 529950, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9981939792633057, "global_step": 529951, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1306405067443848, "global_step": 529952, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.027658224105835, "global_step": 529953, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1007518768310547, "global_step": 529954, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9930192232131958, "global_step": 529955, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.037519931793213, "global_step": 529956, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.088347911834717, "global_step": 529957, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0604963302612305, "global_step": 529958, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1946206092834473, "global_step": 529959, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1073663234710693, "global_step": 529960, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.110626220703125, "global_step": 529961, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9668420553207397, "global_step": 529962, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0481698513031006, "global_step": 529963, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.06217360496521, "global_step": 529964, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1166141033172607, "global_step": 529965, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.020474910736084, "global_step": 529966, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0569045543670654, "global_step": 529967, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.03644061088562, "global_step": 529968, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0529696941375732, "global_step": 529969, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.060263156890869, "global_step": 529970, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9618268013000488, "global_step": 529971, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9518680572509766, "global_step": 529972, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.043596029281616, "global_step": 529973, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.003167152404785, "global_step": 529974, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0954015254974365, "global_step": 529975, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0671520233154297, "global_step": 529976, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0206634998321533, "global_step": 529977, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.041351556777954, "global_step": 529978, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0851943492889404, "global_step": 529979, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.011603355407715, "global_step": 529980, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.008129358291626, "global_step": 529981, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0792038440704346, "global_step": 529982, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.162118673324585, "global_step": 529983, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0136640071868896, "global_step": 529984, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9274948835372925, "global_step": 529985, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0025076866149902, "global_step": 529986, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9829169511795044, "global_step": 529987, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.099135398864746, "global_step": 529988, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0408573150634766, "global_step": 529989, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.079718589782715, "global_step": 529990, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1712911128997803, "global_step": 529991, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1230993270874023, "global_step": 529992, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0952975749969482, "global_step": 529993, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.058734893798828, "global_step": 529994, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0294642448425293, "global_step": 529995, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0131945610046387, "global_step": 529996, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0763866901397705, "global_step": 529997, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1328837871551514, "global_step": 529998, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.062561511993408, "global_step": 529999, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.017364978790283, "global_step": 530000, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0171682834625244, "global_step": 530001, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.013270378112793, "global_step": 530002, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.080636739730835, "global_step": 530003, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9636226892471313, "global_step": 530004, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.039055109024048, "global_step": 530005, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1113662719726562, "global_step": 530006, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.041455030441284, "global_step": 530007, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0640227794647217, "global_step": 530008, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0155527591705322, "global_step": 530009, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.025005340576172, "global_step": 530010, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0316905975341797, "global_step": 530011, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.129911422729492, "global_step": 530012, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.143554449081421, "global_step": 530013, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.050183057785034, "global_step": 530014, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0830729007720947, "global_step": 530015, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.074976921081543, "global_step": 530016, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.027329206466675, "global_step": 530017, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.084339141845703, "global_step": 530018, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0016491413116455, "global_step": 530019, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0370922088623047, "global_step": 530020, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.00046443939209, "global_step": 530021, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.032625913619995, "global_step": 530022, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.113381862640381, "global_step": 530023, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0314228534698486, "global_step": 530024, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.064409017562866, "global_step": 530025, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.080965042114258, "global_step": 530026, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.954609751701355, "global_step": 530027, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.007999897003174, "global_step": 530028, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0864644050598145, "global_step": 530029, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.01830792427063, "global_step": 530030, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0270748138427734, "global_step": 530031, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0703489780426025, "global_step": 530032, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0502803325653076, "global_step": 530033, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.027876615524292, "global_step": 530034, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.042551279067993, "global_step": 530035, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1237261295318604, "global_step": 530036, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0090980529785156, "global_step": 530037, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.013589382171631, "global_step": 530038, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0875980854034424, "global_step": 530039, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.016662836074829, "global_step": 530040, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0834038257598877, "global_step": 530041, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0876986980438232, "global_step": 530042, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0009188652038574, "global_step": 530043, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.040461778640747, "global_step": 530044, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.024904727935791, "global_step": 530045, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0836548805236816, "global_step": 530046, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0121474266052246, "global_step": 530047, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9366576671600342, "global_step": 530048, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1026241779327393, "global_step": 530049, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0599803924560547, "global_step": 530050, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0514845848083496, "global_step": 530051, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9815090894699097, "global_step": 530052, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0875446796417236, "global_step": 530053, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0636250972747803, "global_step": 530054, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0739080905914307, "global_step": 530055, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.074162244796753, "global_step": 530056, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9874427318572998, "global_step": 530057, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0503504276275635, "global_step": 530058, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.046412944793701, "global_step": 530059, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1045680046081543, "global_step": 530060, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0229036808013916, "global_step": 530061, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9927972555160522, "global_step": 530062, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0144941806793213, "global_step": 530063, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.064330816268921, "global_step": 530064, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.03185772895813, "global_step": 530065, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.086904287338257, "global_step": 530066, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0550761222839355, "global_step": 530067, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9805333614349365, "global_step": 530068, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1247711181640625, "global_step": 530069, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1284005641937256, "global_step": 530070, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0800578594207764, "global_step": 530071, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.014646053314209, "global_step": 530072, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9949042797088623, "global_step": 530073, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0697617530822754, "global_step": 530074, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0177085399627686, "global_step": 530075, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1107120513916016, "global_step": 530076, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9845894575119019, "global_step": 530077, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.101740837097168, "global_step": 530078, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.042815685272217, "global_step": 530079, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0751070976257324, "global_step": 530080, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.028524398803711, "global_step": 530081, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.011439085006714, "global_step": 530082, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.114497423171997, "global_step": 530083, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.087299108505249, "global_step": 530084, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0221283435821533, "global_step": 530085, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0697755813598633, "global_step": 530086, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9779616594314575, "global_step": 530087, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.045719861984253, "global_step": 530088, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0438008308410645, "global_step": 530089, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0025296211242676, "global_step": 530090, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0621533393859863, "global_step": 530091, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.080885171890259, "global_step": 530092, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0740880966186523, "global_step": 530093, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.997320532798767, "global_step": 530094, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0984504222869873, "global_step": 530095, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0572941303253174, "global_step": 530096, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.094377040863037, "global_step": 530097, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0302038192749023, "global_step": 530098, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.088785171508789, "global_step": 530099, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9992183446884155, "global_step": 530100, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0284507274627686, "global_step": 530101, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0115702152252197, "global_step": 530102, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.036069631576538, "global_step": 530103, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0056352615356445, "global_step": 530104, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0127298831939697, "global_step": 530105, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9987274408340454, "global_step": 530106, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0130152702331543, "global_step": 530107, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.058048963546753, "global_step": 530108, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0473554134368896, "global_step": 530109, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.095423698425293, "global_step": 530110, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.083698272705078, "global_step": 530111, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.009206771850586, "global_step": 530112, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1117396354675293, "global_step": 530113, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.045151710510254, "global_step": 530114, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.92081618309021, "global_step": 530115, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9967795610427856, "global_step": 530116, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9643118381500244, "global_step": 530117, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9528228044509888, "global_step": 530118, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9763832092285156, "global_step": 530119, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.025485038757324, "global_step": 530120, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0587704181671143, "global_step": 530121, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.992928147315979, "global_step": 530122, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.059912919998169, "global_step": 530123, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0698719024658203, "global_step": 530124, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9445114135742188, "global_step": 530125, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9995436668395996, "global_step": 530126, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9876164197921753, "global_step": 530127, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.002026319503784, "global_step": 530128, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.082033395767212, "global_step": 530129, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0731892585754395, "global_step": 530130, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0795862674713135, "global_step": 530131, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.097877264022827, "global_step": 530132, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.056365489959717, "global_step": 530133, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9974353313446045, "global_step": 530134, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1682114601135254, "global_step": 530135, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.107041597366333, "global_step": 530136, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.996292233467102, "global_step": 530137, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0354888439178467, "global_step": 530138, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.8869662284851074, "global_step": 530139, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0803282260894775, "global_step": 530140, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0549075603485107, "global_step": 530141, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.074920892715454, "global_step": 530142, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.003903865814209, "global_step": 530143, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9816057682037354, "global_step": 530144, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0600738525390625, "global_step": 530145, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0469629764556885, "global_step": 530146, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.101041555404663, "global_step": 530147, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0353565216064453, "global_step": 530148, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1426444053649902, "global_step": 530149, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0889618396759033, "global_step": 530150, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0604805946350098, "global_step": 530151, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0222480297088623, "global_step": 530152, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.075632333755493, "global_step": 530153, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.035404682159424, "global_step": 530154, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0301153659820557, "global_step": 530155, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0211076736450195, "global_step": 530156, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9459786415100098, "global_step": 530157, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.023629665374756, "global_step": 530158, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.014399290084839, "global_step": 530159, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0401477813720703, "global_step": 530160, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.110836982727051, "global_step": 530161, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1237807273864746, "global_step": 530162, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0592293739318848, "global_step": 530163, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.055264711380005, "global_step": 530164, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0186808109283447, "global_step": 530165, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0259299278259277, "global_step": 530166, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9506043195724487, "global_step": 530167, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1360158920288086, "global_step": 530168, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0445704460144043, "global_step": 530169, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.1339054107666016, "global_step": 530170, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0903704166412354, "global_step": 530171, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.082720994949341, "global_step": 530172, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9569077491760254, "global_step": 530173, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.07719349861145, "global_step": 530174, "epoch": 896, "lr": 5e-05}
{"train_loss": 2.0393614768981934, "global_step": 530175, "epoch": 896, "lr": 5e-05}
{"train_loss": 1.9493722915649414, "global_step": 530176, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.104745626449585, "global_step": 530177, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.989612102508545, "global_step": 530178, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9858636856079102, "global_step": 530179, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0881433486938477, "global_step": 530180, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.036623954772949, "global_step": 530181, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9672200679779053, "global_step": 530182, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0648350715637207, "global_step": 530183, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.018362522125244, "global_step": 530184, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9894369840621948, "global_step": 530185, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9927124977111816, "global_step": 530186, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9394441843032837, "global_step": 530187, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9414376020431519, "global_step": 530188, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0266761779785156, "global_step": 530189, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0103392601013184, "global_step": 530190, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.05914568901062, "global_step": 530191, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9876644611358643, "global_step": 530192, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9912549257278442, "global_step": 530193, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9163883924484253, "global_step": 530194, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9269394874572754, "global_step": 530195, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0257580280303955, "global_step": 530196, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0580549240112305, "global_step": 530197, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.078486204147339, "global_step": 530198, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.113471031188965, "global_step": 530199, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9763469696044922, "global_step": 530200, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9644972085952759, "global_step": 530201, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9488916397094727, "global_step": 530202, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9460785388946533, "global_step": 530203, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9629535675048828, "global_step": 530204, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0381662845611572, "global_step": 530205, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9935057163238525, "global_step": 530206, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0220093727111816, "global_step": 530207, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9889994859695435, "global_step": 530208, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0029852390289307, "global_step": 530209, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0986175537109375, "global_step": 530210, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.991456389427185, "global_step": 530211, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.883851170539856, "global_step": 530212, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0606517791748047, "global_step": 530213, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.035992383956909, "global_step": 530214, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9927921295166016, "global_step": 530215, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0270371437072754, "global_step": 530216, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0074057579040527, "global_step": 530217, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.096536159515381, "global_step": 530218, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0518381595611572, "global_step": 530219, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9584654569625854, "global_step": 530220, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.060521125793457, "global_step": 530221, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.023245096206665, "global_step": 530222, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.111901044845581, "global_step": 530223, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.044437885284424, "global_step": 530224, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0737791061401367, "global_step": 530225, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0947117805480957, "global_step": 530226, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9925119876861572, "global_step": 530227, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.026505470275879, "global_step": 530228, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.049320697784424, "global_step": 530229, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0308327674865723, "global_step": 530230, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9656431674957275, "global_step": 530231, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.924892544746399, "global_step": 530232, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9493504762649536, "global_step": 530233, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0952813625335693, "global_step": 530234, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0669569969177246, "global_step": 530235, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0713064670562744, "global_step": 530236, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0716166496276855, "global_step": 530237, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9563316106796265, "global_step": 530238, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.015378713607788, "global_step": 530239, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9772204160690308, "global_step": 530240, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0825326442718506, "global_step": 530241, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.126147985458374, "global_step": 530242, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9687687158584595, "global_step": 530243, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.010425329208374, "global_step": 530244, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.161696434020996, "global_step": 530245, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0532333850860596, "global_step": 530246, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0140252113342285, "global_step": 530247, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.876916766166687, "global_step": 530248, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.014329671859741, "global_step": 530249, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.982041597366333, "global_step": 530250, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.021408796310425, "global_step": 530251, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0412020683288574, "global_step": 530252, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.985616683959961, "global_step": 530253, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9923328161239624, "global_step": 530254, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0445501804351807, "global_step": 530255, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.059434175491333, "global_step": 530256, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1352148056030273, "global_step": 530257, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0761239528656006, "global_step": 530258, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0351853370666504, "global_step": 530259, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.020231246948242, "global_step": 530260, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.097090244293213, "global_step": 530261, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9374134540557861, "global_step": 530262, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.006108045578003, "global_step": 530263, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.113424301147461, "global_step": 530264, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9857410192489624, "global_step": 530265, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.003530740737915, "global_step": 530266, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0531890392303467, "global_step": 530267, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0533804893493652, "global_step": 530268, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9778379201889038, "global_step": 530269, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9600865840911865, "global_step": 530270, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0884366035461426, "global_step": 530271, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0460684299468994, "global_step": 530272, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0291330814361572, "global_step": 530273, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9558250904083252, "global_step": 530274, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1194660663604736, "global_step": 530275, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0360865592956543, "global_step": 530276, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9342029094696045, "global_step": 530277, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0144991874694824, "global_step": 530278, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9778765439987183, "global_step": 530279, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1219067573547363, "global_step": 530280, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0104451179504395, "global_step": 530281, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.052793025970459, "global_step": 530282, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.115858554840088, "global_step": 530283, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9440969228744507, "global_step": 530284, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1008658409118652, "global_step": 530285, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1299002170562744, "global_step": 530286, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.077162027359009, "global_step": 530287, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.037510633468628, "global_step": 530288, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0982134342193604, "global_step": 530289, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9628337621688843, "global_step": 530290, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9808143377304077, "global_step": 530291, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9813834428787231, "global_step": 530292, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9605509042739868, "global_step": 530293, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9888865947723389, "global_step": 530294, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.030111312866211, "global_step": 530295, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1229209899902344, "global_step": 530296, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0206124782562256, "global_step": 530297, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9390451908111572, "global_step": 530298, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.022826671600342, "global_step": 530299, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.068180799484253, "global_step": 530300, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0190868377685547, "global_step": 530301, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9814461469650269, "global_step": 530302, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.091057300567627, "global_step": 530303, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.009819984436035, "global_step": 530304, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.993871808052063, "global_step": 530305, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9996182918548584, "global_step": 530306, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.972913146018982, "global_step": 530307, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.099055051803589, "global_step": 530308, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0020787715911865, "global_step": 530309, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9652787446975708, "global_step": 530310, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.070847749710083, "global_step": 530311, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.009430170059204, "global_step": 530312, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.055418014526367, "global_step": 530313, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0244572162628174, "global_step": 530314, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.101144790649414, "global_step": 530315, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0311477184295654, "global_step": 530316, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0828614234924316, "global_step": 530317, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.938919186592102, "global_step": 530318, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.913092017173767, "global_step": 530319, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9407930374145508, "global_step": 530320, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0600409507751465, "global_step": 530321, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0146126747131348, "global_step": 530322, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0132882595062256, "global_step": 530323, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.052675724029541, "global_step": 530324, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.037090301513672, "global_step": 530325, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.942223310470581, "global_step": 530326, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.006053924560547, "global_step": 530327, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.037806272506714, "global_step": 530328, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0077335834503174, "global_step": 530329, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0240607261657715, "global_step": 530330, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0427489280700684, "global_step": 530331, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0629372596740723, "global_step": 530332, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0488109588623047, "global_step": 530333, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0550968647003174, "global_step": 530334, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.994551181793213, "global_step": 530335, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0533149242401123, "global_step": 530336, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9815680980682373, "global_step": 530337, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0073769092559814, "global_step": 530338, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.121856451034546, "global_step": 530339, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.066988468170166, "global_step": 530340, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0286362171173096, "global_step": 530341, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.047077178955078, "global_step": 530342, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.014042615890503, "global_step": 530343, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9887259006500244, "global_step": 530344, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9534035921096802, "global_step": 530345, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0722882747650146, "global_step": 530346, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9823955297470093, "global_step": 530347, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9829984903335571, "global_step": 530348, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9793826341629028, "global_step": 530349, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0527942180633545, "global_step": 530350, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9988622665405273, "global_step": 530351, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0461347103118896, "global_step": 530352, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9883757829666138, "global_step": 530353, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0171992778778076, "global_step": 530354, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.988023281097412, "global_step": 530355, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9514367580413818, "global_step": 530356, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0750067234039307, "global_step": 530357, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.859771966934204, "global_step": 530358, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0105862617492676, "global_step": 530359, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0339314937591553, "global_step": 530360, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0556845664978027, "global_step": 530361, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.996056318283081, "global_step": 530362, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.035106658935547, "global_step": 530363, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.028665781021118, "global_step": 530364, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.011843204498291, "global_step": 530365, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0050413608551025, "global_step": 530366, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9656023979187012, "global_step": 530367, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.02107834815979, "global_step": 530368, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.987870216369629, "global_step": 530369, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.062364101409912, "global_step": 530370, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.147158145904541, "global_step": 530371, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.066598892211914, "global_step": 530372, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0050926208496094, "global_step": 530373, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.051771640777588, "global_step": 530374, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0464141368865967, "global_step": 530375, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0533154010772705, "global_step": 530376, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0649049282073975, "global_step": 530377, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9894254207611084, "global_step": 530378, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.025792360305786, "global_step": 530379, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0139122009277344, "global_step": 530380, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0592055320739746, "global_step": 530381, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9926223754882812, "global_step": 530382, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9676984548568726, "global_step": 530383, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.933200478553772, "global_step": 530384, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9739892482757568, "global_step": 530385, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1556589603424072, "global_step": 530386, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0787646770477295, "global_step": 530387, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.006713390350342, "global_step": 530388, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9769132137298584, "global_step": 530389, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9229069948196411, "global_step": 530390, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.028123617172241, "global_step": 530391, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0162672996520996, "global_step": 530392, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.092416524887085, "global_step": 530393, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0957911014556885, "global_step": 530394, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.01951265335083, "global_step": 530395, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0022404193878174, "global_step": 530396, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0498170852661133, "global_step": 530397, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0247960090637207, "global_step": 530398, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9726715087890625, "global_step": 530399, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0722405910491943, "global_step": 530400, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.979691743850708, "global_step": 530401, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.100393295288086, "global_step": 530402, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1318957805633545, "global_step": 530403, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0585498809814453, "global_step": 530404, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.013306140899658, "global_step": 530405, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0823957920074463, "global_step": 530406, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0273914337158203, "global_step": 530407, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.991828441619873, "global_step": 530408, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1047704219818115, "global_step": 530409, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1145904064178467, "global_step": 530410, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0884785652160645, "global_step": 530411, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1255462169647217, "global_step": 530412, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.037008047103882, "global_step": 530413, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0261452198028564, "global_step": 530414, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.081094741821289, "global_step": 530415, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9560999870300293, "global_step": 530416, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0570554733276367, "global_step": 530417, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.014850616455078, "global_step": 530418, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0128846168518066, "global_step": 530419, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0402817726135254, "global_step": 530420, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0055747032165527, "global_step": 530421, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.088364839553833, "global_step": 530422, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0680127143859863, "global_step": 530423, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.017897844314575, "global_step": 530424, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.064216136932373, "global_step": 530425, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0444858074188232, "global_step": 530426, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.077284336090088, "global_step": 530427, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.099745273590088, "global_step": 530428, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0899405479431152, "global_step": 530429, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.054241180419922, "global_step": 530430, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.052656650543213, "global_step": 530431, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0464589595794678, "global_step": 530432, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.039696455001831, "global_step": 530433, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.015928030014038, "global_step": 530434, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0571391582489014, "global_step": 530435, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0338852405548096, "global_step": 530436, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.099832534790039, "global_step": 530437, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0814430713653564, "global_step": 530438, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.037595272064209, "global_step": 530439, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0214226245880127, "global_step": 530440, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0333545207977295, "global_step": 530441, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.001988649368286, "global_step": 530442, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0896942615509033, "global_step": 530443, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.003309488296509, "global_step": 530444, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.091933012008667, "global_step": 530445, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.991020917892456, "global_step": 530446, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.09867262840271, "global_step": 530447, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.039510488510132, "global_step": 530448, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1563761234283447, "global_step": 530449, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1077523231506348, "global_step": 530450, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0483789443969727, "global_step": 530451, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9809690713882446, "global_step": 530452, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.047259569168091, "global_step": 530453, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.061818838119507, "global_step": 530454, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0064241886138916, "global_step": 530455, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0351808071136475, "global_step": 530456, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.044527053833008, "global_step": 530457, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0303585529327393, "global_step": 530458, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.011096954345703, "global_step": 530459, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.078211545944214, "global_step": 530460, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.00350284576416, "global_step": 530461, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.059285879135132, "global_step": 530462, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1104233264923096, "global_step": 530463, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9986319541931152, "global_step": 530464, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0492136478424072, "global_step": 530465, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0413267612457275, "global_step": 530466, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9710475206375122, "global_step": 530467, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0316686630249023, "global_step": 530468, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0419609546661377, "global_step": 530469, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.022887706756592, "global_step": 530470, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0348761081695557, "global_step": 530471, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9680594205856323, "global_step": 530472, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0254156589508057, "global_step": 530473, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0878944396972656, "global_step": 530474, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0497686862945557, "global_step": 530475, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0221669673919678, "global_step": 530476, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9911571741104126, "global_step": 530477, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.956253170967102, "global_step": 530478, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.018183708190918, "global_step": 530479, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9964470863342285, "global_step": 530480, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0237929821014404, "global_step": 530481, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9766552448272705, "global_step": 530482, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0370795726776123, "global_step": 530483, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0672059059143066, "global_step": 530484, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.09839129447937, "global_step": 530485, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9982130527496338, "global_step": 530486, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.094068765640259, "global_step": 530487, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1450657844543457, "global_step": 530488, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.986482858657837, "global_step": 530489, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.037524700164795, "global_step": 530490, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.057084560394287, "global_step": 530491, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9739141464233398, "global_step": 530492, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.063560962677002, "global_step": 530493, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9929250478744507, "global_step": 530494, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0497169494628906, "global_step": 530495, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0993332862854004, "global_step": 530496, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9989358186721802, "global_step": 530497, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0426995754241943, "global_step": 530498, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0229506492614746, "global_step": 530499, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.122434139251709, "global_step": 530500, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0721373558044434, "global_step": 530501, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1118111610412598, "global_step": 530502, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0873005390167236, "global_step": 530503, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.071829080581665, "global_step": 530504, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.008821964263916, "global_step": 530505, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.060859203338623, "global_step": 530506, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.059650182723999, "global_step": 530507, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0287859439849854, "global_step": 530508, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.106351852416992, "global_step": 530509, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9585182666778564, "global_step": 530510, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0495667457580566, "global_step": 530511, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0475142002105713, "global_step": 530512, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.143923044204712, "global_step": 530513, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0160441398620605, "global_step": 530514, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9636812210083008, "global_step": 530515, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.027078866958618, "global_step": 530516, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9417961835861206, "global_step": 530517, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.106635093688965, "global_step": 530518, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.016282081604004, "global_step": 530519, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.060635805130005, "global_step": 530520, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0096328258514404, "global_step": 530521, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0314972400665283, "global_step": 530522, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0289247035980225, "global_step": 530523, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.144193172454834, "global_step": 530524, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.046276569366455, "global_step": 530525, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0315377712249756, "global_step": 530526, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1307098865509033, "global_step": 530527, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0678553581237793, "global_step": 530528, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0469677448272705, "global_step": 530529, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0980589389801025, "global_step": 530530, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.076364517211914, "global_step": 530531, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.076472520828247, "global_step": 530532, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0413897037506104, "global_step": 530533, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.09712553024292, "global_step": 530534, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0213465690612793, "global_step": 530535, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.117553234100342, "global_step": 530536, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.026639938354492, "global_step": 530537, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0636348724365234, "global_step": 530538, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.068699359893799, "global_step": 530539, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.007855176925659, "global_step": 530540, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.068268060684204, "global_step": 530541, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.112675428390503, "global_step": 530542, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.030703067779541, "global_step": 530543, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.055321455001831, "global_step": 530544, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0147812366485596, "global_step": 530545, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9556269645690918, "global_step": 530546, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.07243275642395, "global_step": 530547, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.066088914871216, "global_step": 530548, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0220320224761963, "global_step": 530549, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0632340908050537, "global_step": 530550, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0316596031188965, "global_step": 530551, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0316808223724365, "global_step": 530552, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.070957899093628, "global_step": 530553, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0966551303863525, "global_step": 530554, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9832003116607666, "global_step": 530555, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.089967966079712, "global_step": 530556, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9455630779266357, "global_step": 530557, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9996654987335205, "global_step": 530558, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.028322696685791, "global_step": 530559, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.091007709503174, "global_step": 530560, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9471383094787598, "global_step": 530561, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.094586133956909, "global_step": 530562, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0588698387145996, "global_step": 530563, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.054762601852417, "global_step": 530564, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0036942958831787, "global_step": 530565, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.04887056350708, "global_step": 530566, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9939106702804565, "global_step": 530567, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0402233600616455, "global_step": 530568, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.995394229888916, "global_step": 530569, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.022096633911133, "global_step": 530570, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0408267974853516, "global_step": 530571, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.106492042541504, "global_step": 530572, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.089866876602173, "global_step": 530573, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0331778526306152, "global_step": 530574, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0365355014801025, "global_step": 530575, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.012644052505493, "global_step": 530576, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0724916458129883, "global_step": 530577, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.018850803375244, "global_step": 530578, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1341731548309326, "global_step": 530579, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9952460527420044, "global_step": 530580, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.028794765472412, "global_step": 530581, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0615949630737305, "global_step": 530582, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0735361576080322, "global_step": 530583, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.068664073944092, "global_step": 530584, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0794005393981934, "global_step": 530585, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0743374824523926, "global_step": 530586, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0512948036193848, "global_step": 530587, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.032209634780884, "global_step": 530588, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0406792163848877, "global_step": 530589, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.024231195449829, "global_step": 530590, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9761368036270142, "global_step": 530591, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1255991458892822, "global_step": 530592, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0239713191986084, "global_step": 530593, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0380663871765137, "global_step": 530594, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.11582088470459, "global_step": 530595, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0726349353790283, "global_step": 530596, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.093993902206421, "global_step": 530597, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.078209638595581, "global_step": 530598, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0519468784332275, "global_step": 530599, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0675768852233887, "global_step": 530600, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.10642147064209, "global_step": 530601, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0862321853637695, "global_step": 530602, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9609273672103882, "global_step": 530603, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0041439533233643, "global_step": 530604, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0821781158447266, "global_step": 530605, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.116483211517334, "global_step": 530606, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0710904598236084, "global_step": 530607, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0392212867736816, "global_step": 530608, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.091780662536621, "global_step": 530609, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.120760679244995, "global_step": 530610, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.139492988586426, "global_step": 530611, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1108875274658203, "global_step": 530612, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0322837829589844, "global_step": 530613, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0809504985809326, "global_step": 530614, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.054049015045166, "global_step": 530615, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9739913940429688, "global_step": 530616, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0153489112854004, "global_step": 530617, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0442821979522705, "global_step": 530618, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.03584361076355, "global_step": 530619, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0804481506347656, "global_step": 530620, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.10048770904541, "global_step": 530621, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.11979079246521, "global_step": 530622, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0657076835632324, "global_step": 530623, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0027995109558105, "global_step": 530624, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.95363450050354, "global_step": 530625, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0841853618621826, "global_step": 530626, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0290136337280273, "global_step": 530627, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9683523178100586, "global_step": 530628, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9526654481887817, "global_step": 530629, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9897682666778564, "global_step": 530630, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0202858448028564, "global_step": 530631, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0875606536865234, "global_step": 530632, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0334274768829346, "global_step": 530633, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9750834703445435, "global_step": 530634, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1203582286834717, "global_step": 530635, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.170248508453369, "global_step": 530636, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9807493686676025, "global_step": 530637, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0468826293945312, "global_step": 530638, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0729403495788574, "global_step": 530639, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1136555671691895, "global_step": 530640, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9975651502609253, "global_step": 530641, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.943517804145813, "global_step": 530642, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0443115234375, "global_step": 530643, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.003110408782959, "global_step": 530644, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.984725832939148, "global_step": 530645, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9684654474258423, "global_step": 530646, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9746906757354736, "global_step": 530647, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.102426290512085, "global_step": 530648, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0677168369293213, "global_step": 530649, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0140228271484375, "global_step": 530650, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.106508255004883, "global_step": 530651, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.009342908859253, "global_step": 530652, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.077493667602539, "global_step": 530653, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0638911724090576, "global_step": 530654, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.089468479156494, "global_step": 530655, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9567610025405884, "global_step": 530656, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0373077392578125, "global_step": 530657, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.103243112564087, "global_step": 530658, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.01821231842041, "global_step": 530659, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9732564687728882, "global_step": 530660, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.043358087539673, "global_step": 530661, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9888219833374023, "global_step": 530662, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.008922815322876, "global_step": 530663, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0953004360198975, "global_step": 530664, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.032693386077881, "global_step": 530665, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9580464363098145, "global_step": 530666, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0362088680267334, "global_step": 530667, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.129441499710083, "global_step": 530668, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9818249940872192, "global_step": 530669, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9831823110580444, "global_step": 530670, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1846747398376465, "global_step": 530671, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0200231075286865, "global_step": 530672, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.104449987411499, "global_step": 530673, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.060620069503784, "global_step": 530674, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9284021854400635, "global_step": 530675, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9392383098602295, "global_step": 530676, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9929383993148804, "global_step": 530677, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.082688093185425, "global_step": 530678, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0226447582244873, "global_step": 530679, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0396955013275146, "global_step": 530680, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.034919500350952, "global_step": 530681, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.064847707748413, "global_step": 530682, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.058436632156372, "global_step": 530683, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.146679401397705, "global_step": 530684, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.022261619567871, "global_step": 530685, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.137712240219116, "global_step": 530686, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0119969844818115, "global_step": 530687, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9767580032348633, "global_step": 530688, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.065474271774292, "global_step": 530689, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.033066511154175, "global_step": 530690, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.173022747039795, "global_step": 530691, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.082953929901123, "global_step": 530692, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0035409927368164, "global_step": 530693, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0536181926727295, "global_step": 530694, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1180944442749023, "global_step": 530695, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0298960208892822, "global_step": 530696, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.075908899307251, "global_step": 530697, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9855445623397827, "global_step": 530698, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0749237537384033, "global_step": 530699, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9926189184188843, "global_step": 530700, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0926384925842285, "global_step": 530701, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.042675733566284, "global_step": 530702, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.016352891921997, "global_step": 530703, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0191237926483154, "global_step": 530704, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.095724582672119, "global_step": 530705, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.068509817123413, "global_step": 530706, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0919363498687744, "global_step": 530707, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0407004356384277, "global_step": 530708, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9905555248260498, "global_step": 530709, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0693750381469727, "global_step": 530710, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.055712938308716, "global_step": 530711, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0161495208740234, "global_step": 530712, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0555944442749023, "global_step": 530713, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.10445237159729, "global_step": 530714, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.999132513999939, "global_step": 530715, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0504150390625, "global_step": 530716, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.115217924118042, "global_step": 530717, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1128575801849365, "global_step": 530718, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0880625247955322, "global_step": 530719, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.154101848602295, "global_step": 530720, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.005950689315796, "global_step": 530721, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0155091285705566, "global_step": 530722, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.996296763420105, "global_step": 530723, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.097513198852539, "global_step": 530724, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.085390090942383, "global_step": 530725, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0925190448760986, "global_step": 530726, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.010751247406006, "global_step": 530727, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.990652084350586, "global_step": 530728, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0656466484069824, "global_step": 530729, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0150375366210938, "global_step": 530730, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.055382013320923, "global_step": 530731, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9233065843582153, "global_step": 530732, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.001601219177246, "global_step": 530733, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0415263175964355, "global_step": 530734, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0936455726623535, "global_step": 530735, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.050928831100464, "global_step": 530736, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.026031255722046, "global_step": 530737, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.988173246383667, "global_step": 530738, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0313689708709717, "global_step": 530739, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0656824111938477, "global_step": 530740, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0516419410705566, "global_step": 530741, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.994753360748291, "global_step": 530742, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9344619512557983, "global_step": 530743, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0699071884155273, "global_step": 530744, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.047168016433716, "global_step": 530745, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.117313861846924, "global_step": 530746, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9302630424499512, "global_step": 530747, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0815658569335938, "global_step": 530748, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0889275074005127, "global_step": 530749, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.080942392349243, "global_step": 530750, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.093508720397949, "global_step": 530751, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.012028217315674, "global_step": 530752, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9522905349731445, "global_step": 530753, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0786139965057373, "global_step": 530754, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0627520084381104, "global_step": 530755, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9813939332962036, "global_step": 530756, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.031764507293701, "global_step": 530757, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0388312339782715, "global_step": 530758, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.111935615539551, "global_step": 530759, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.076873540878296, "global_step": 530760, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0726537704467773, "global_step": 530761, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.071833610534668, "global_step": 530762, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9674447774887085, "global_step": 530763, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0539135932922363, "global_step": 530764, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.012584686279297, "global_step": 530765, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.996503233909607, "global_step": 530766, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.050339937210083, "global_step": 530767, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.019216775894165, "global_step": 530768, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9518709182739258, "global_step": 530769, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1362903118133545, "global_step": 530770, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9776207208633423, "global_step": 530771, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9653339385986328, "global_step": 530772, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0042381286621094, "global_step": 530773, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1238200664520264, "global_step": 530774, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0723557472229004, "global_step": 530775, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9701608419418335, "global_step": 530776, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9990863800048828, "global_step": 530777, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.044114351272583, "global_step": 530778, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.041438102722168, "global_step": 530779, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.078970193862915, "global_step": 530780, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9999500513076782, "global_step": 530781, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.068976402282715, "global_step": 530782, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.035064458847046, "global_step": 530783, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0308661460876465, "global_step": 530784, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.100346803665161, "global_step": 530785, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.003911018371582, "global_step": 530786, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1516804695129395, "global_step": 530787, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9958070516586304, "global_step": 530788, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1253581047058105, "global_step": 530789, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.16165828704834, "global_step": 530790, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.955522060394287, "global_step": 530791, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0690267086029053, "global_step": 530792, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0425312519073486, "global_step": 530793, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0569286346435547, "global_step": 530794, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0917444229125977, "global_step": 530795, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0620834827423096, "global_step": 530796, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.078705072402954, "global_step": 530797, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0734496116638184, "global_step": 530798, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.182919979095459, "global_step": 530799, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.081510543823242, "global_step": 530800, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0675230026245117, "global_step": 530801, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0632851123809814, "global_step": 530802, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0100460052490234, "global_step": 530803, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9631459712982178, "global_step": 530804, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9506480693817139, "global_step": 530805, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.104365587234497, "global_step": 530806, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0507431030273438, "global_step": 530807, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0408365726470947, "global_step": 530808, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0655062198638916, "global_step": 530809, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.977142333984375, "global_step": 530810, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0865745544433594, "global_step": 530811, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9697185754776, "global_step": 530812, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0698447227478027, "global_step": 530813, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0394082069396973, "global_step": 530814, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9626414775848389, "global_step": 530815, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.102004051208496, "global_step": 530816, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0145275592803955, "global_step": 530817, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.044079542160034, "global_step": 530818, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9846614599227905, "global_step": 530819, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.057342290878296, "global_step": 530820, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.088430881500244, "global_step": 530821, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0040576457977295, "global_step": 530822, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.073472738265991, "global_step": 530823, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.064222812652588, "global_step": 530824, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0798633098602295, "global_step": 530825, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.023540735244751, "global_step": 530826, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.109300136566162, "global_step": 530827, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0958306789398193, "global_step": 530828, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9777051210403442, "global_step": 530829, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.029482126235962, "global_step": 530830, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.04146671295166, "global_step": 530831, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.086397171020508, "global_step": 530832, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9333481788635254, "global_step": 530833, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.11472749710083, "global_step": 530834, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.040114402770996, "global_step": 530835, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9654922485351562, "global_step": 530836, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0879015922546387, "global_step": 530837, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9262158870697021, "global_step": 530838, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0673720836639404, "global_step": 530839, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0800859928131104, "global_step": 530840, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9967862367630005, "global_step": 530841, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.040735960006714, "global_step": 530842, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1505701541900635, "global_step": 530843, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0998544692993164, "global_step": 530844, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9875739812850952, "global_step": 530845, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9904983043670654, "global_step": 530846, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0087244510650635, "global_step": 530847, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9898931980133057, "global_step": 530848, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.052504301071167, "global_step": 530849, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.083163022994995, "global_step": 530850, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.075281858444214, "global_step": 530851, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9932278394699097, "global_step": 530852, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9624310731887817, "global_step": 530853, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9448034763336182, "global_step": 530854, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0481746196746826, "global_step": 530855, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0142109394073486, "global_step": 530856, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9934897422790527, "global_step": 530857, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0499179363250732, "global_step": 530858, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9984484910964966, "global_step": 530859, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9862247705459595, "global_step": 530860, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0526516437530518, "global_step": 530861, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0357015132904053, "global_step": 530862, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0292654037475586, "global_step": 530863, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0582809448242188, "global_step": 530864, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1444709300994873, "global_step": 530865, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9533774852752686, "global_step": 530866, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0139269828796387, "global_step": 530867, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.942628264427185, "global_step": 530868, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9777930974960327, "global_step": 530869, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0700297355651855, "global_step": 530870, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.05342698097229, "global_step": 530871, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.065406560897827, "global_step": 530872, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.059843063354492, "global_step": 530873, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9366869926452637, "global_step": 530874, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1410937309265137, "global_step": 530875, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9708857536315918, "global_step": 530876, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9401988983154297, "global_step": 530877, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0486769676208496, "global_step": 530878, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.034400224685669, "global_step": 530879, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9900490045547485, "global_step": 530880, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.036001682281494, "global_step": 530881, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1270203590393066, "global_step": 530882, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.003481864929199, "global_step": 530883, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.981632113456726, "global_step": 530884, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9652478694915771, "global_step": 530885, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0266788005828857, "global_step": 530886, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0691401958465576, "global_step": 530887, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0409178733825684, "global_step": 530888, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.009652853012085, "global_step": 530889, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0386693477630615, "global_step": 530890, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0093626976013184, "global_step": 530891, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0478057861328125, "global_step": 530892, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.053898334503174, "global_step": 530893, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0096921920776367, "global_step": 530894, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0369858741760254, "global_step": 530895, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.08723783493042, "global_step": 530896, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0463814735412598, "global_step": 530897, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0147509574890137, "global_step": 530898, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.960700511932373, "global_step": 530899, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0239832401275635, "global_step": 530900, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1190531253814697, "global_step": 530901, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.061001777648926, "global_step": 530902, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9609229564666748, "global_step": 530903, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1184098720550537, "global_step": 530904, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0644917488098145, "global_step": 530905, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0449023246765137, "global_step": 530906, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0497140884399414, "global_step": 530907, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0776777267456055, "global_step": 530908, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9751942157745361, "global_step": 530909, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0016353130340576, "global_step": 530910, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.986923098564148, "global_step": 530911, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1512515544891357, "global_step": 530912, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0759761333465576, "global_step": 530913, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0297324657440186, "global_step": 530914, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.96446692943573, "global_step": 530915, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.02850604057312, "global_step": 530916, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0910279750823975, "global_step": 530917, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0934488773345947, "global_step": 530918, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0338985919952393, "global_step": 530919, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0262656211853027, "global_step": 530920, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9688200950622559, "global_step": 530921, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0140480995178223, "global_step": 530922, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.097527027130127, "global_step": 530923, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0954957008361816, "global_step": 530924, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0499725341796875, "global_step": 530925, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.004218339920044, "global_step": 530926, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0224573612213135, "global_step": 530927, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1720240116119385, "global_step": 530928, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9895423650741577, "global_step": 530929, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.026585340499878, "global_step": 530930, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.960270643234253, "global_step": 530931, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.043976068496704, "global_step": 530932, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.040956497192383, "global_step": 530933, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0638809204101562, "global_step": 530934, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.044802188873291, "global_step": 530935, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.035842180252075, "global_step": 530936, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.997788667678833, "global_step": 530937, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0417022705078125, "global_step": 530938, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.057807683944702, "global_step": 530939, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9598726034164429, "global_step": 530940, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.095439910888672, "global_step": 530941, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0927774906158447, "global_step": 530942, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.095534563064575, "global_step": 530943, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.162304162979126, "global_step": 530944, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0361032485961914, "global_step": 530945, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0862395763397217, "global_step": 530946, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0615100860595703, "global_step": 530947, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.991796612739563, "global_step": 530948, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9753059148788452, "global_step": 530949, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0278825759887695, "global_step": 530950, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0245838165283203, "global_step": 530951, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9524084329605103, "global_step": 530952, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.992391586303711, "global_step": 530953, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.011047601699829, "global_step": 530954, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.063913345336914, "global_step": 530955, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0658109188079834, "global_step": 530956, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.066411256790161, "global_step": 530957, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.015247344970703, "global_step": 530958, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0431249141693115, "global_step": 530959, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9904606342315674, "global_step": 530960, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9992841482162476, "global_step": 530961, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.076483964920044, "global_step": 530962, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0253376960754395, "global_step": 530963, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.08316707611084, "global_step": 530964, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.057080030441284, "global_step": 530965, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.113088846206665, "global_step": 530966, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.092254400253296, "global_step": 530967, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9621695280075073, "global_step": 530968, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9938583374023438, "global_step": 530969, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.059715509414673, "global_step": 530970, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0399811267852783, "global_step": 530971, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0337092876434326, "global_step": 530972, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.095906972885132, "global_step": 530973, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.129462242126465, "global_step": 530974, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.951151967048645, "global_step": 530975, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.089536190032959, "global_step": 530976, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0217177867889404, "global_step": 530977, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0245492458343506, "global_step": 530978, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.989859700202942, "global_step": 530979, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.099802017211914, "global_step": 530980, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0120813846588135, "global_step": 530981, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.044285774230957, "global_step": 530982, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9341739416122437, "global_step": 530983, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0060923099517822, "global_step": 530984, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9339240789413452, "global_step": 530985, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9943488836288452, "global_step": 530986, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0614497661590576, "global_step": 530987, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.016047716140747, "global_step": 530988, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.01737117767334, "global_step": 530989, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0855653285980225, "global_step": 530990, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0297203063964844, "global_step": 530991, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1085398197174072, "global_step": 530992, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.069978713989258, "global_step": 530993, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0592613220214844, "global_step": 530994, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.007986068725586, "global_step": 530995, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9737240076065063, "global_step": 530996, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.044677257537842, "global_step": 530997, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.084005117416382, "global_step": 530998, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9898598194122314, "global_step": 530999, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0319507122039795, "global_step": 531000, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0644476413726807, "global_step": 531001, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.039121150970459, "global_step": 531002, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0692481994628906, "global_step": 531003, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9053581953048706, "global_step": 531004, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9655187129974365, "global_step": 531005, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.089817523956299, "global_step": 531006, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.147369861602783, "global_step": 531007, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.022592782974243, "global_step": 531008, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0901987552642822, "global_step": 531009, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0804967880249023, "global_step": 531010, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0685579776763916, "global_step": 531011, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1168429851531982, "global_step": 531012, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0563318729400635, "global_step": 531013, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0374796390533447, "global_step": 531014, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.069934844970703, "global_step": 531015, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9698587656021118, "global_step": 531016, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.099372625350952, "global_step": 531017, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0012705326080322, "global_step": 531018, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0140442848205566, "global_step": 531019, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0311505794525146, "global_step": 531020, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0119893550872803, "global_step": 531021, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0048015117645264, "global_step": 531022, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.051605701446533, "global_step": 531023, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.058136224746704, "global_step": 531024, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.028327226638794, "global_step": 531025, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1238017082214355, "global_step": 531026, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0234739780426025, "global_step": 531027, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0769965648651123, "global_step": 531028, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1021218299865723, "global_step": 531029, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0480761528015137, "global_step": 531030, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.075603485107422, "global_step": 531031, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0065689086914062, "global_step": 531032, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.026552438735962, "global_step": 531033, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.091562271118164, "global_step": 531034, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0655336380004883, "global_step": 531035, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0305075645446777, "global_step": 531036, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.007882595062256, "global_step": 531037, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.055180072784424, "global_step": 531038, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.020641326904297, "global_step": 531039, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0294835567474365, "global_step": 531040, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0529675483703613, "global_step": 531041, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0065155029296875, "global_step": 531042, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.12736439704895, "global_step": 531043, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0199193954467773, "global_step": 531044, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.002063751220703, "global_step": 531045, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0326709747314453, "global_step": 531046, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.990424394607544, "global_step": 531047, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0213959217071533, "global_step": 531048, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0741100311279297, "global_step": 531049, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1125972270965576, "global_step": 531050, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.027827501296997, "global_step": 531051, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1153979301452637, "global_step": 531052, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9972585439682007, "global_step": 531053, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.96431565284729, "global_step": 531054, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.079697370529175, "global_step": 531055, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0753285884857178, "global_step": 531056, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0660386085510254, "global_step": 531057, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.110079050064087, "global_step": 531058, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1473939418792725, "global_step": 531059, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0916588306427, "global_step": 531060, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.953566312789917, "global_step": 531061, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.069519281387329, "global_step": 531062, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0569379329681396, "global_step": 531063, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.054227113723755, "global_step": 531064, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.059295415878296, "global_step": 531065, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.998918056488037, "global_step": 531066, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.012667179107666, "global_step": 531067, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.02781081199646, "global_step": 531068, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.06532621383667, "global_step": 531069, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1018612384796143, "global_step": 531070, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1264641284942627, "global_step": 531071, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.068004608154297, "global_step": 531072, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9834189414978027, "global_step": 531073, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0568606853485107, "global_step": 531074, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1012749671936035, "global_step": 531075, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0138187408447266, "global_step": 531076, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0594253540039062, "global_step": 531077, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0648488998413086, "global_step": 531078, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0216617584228516, "global_step": 531079, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0499672889709473, "global_step": 531080, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.055501937866211, "global_step": 531081, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9627933502197266, "global_step": 531082, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0457918643951416, "global_step": 531083, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1077256202697754, "global_step": 531084, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9547841548919678, "global_step": 531085, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0204691886901855, "global_step": 531086, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1626906394958496, "global_step": 531087, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.006932497024536, "global_step": 531088, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.053755044937134, "global_step": 531089, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0429983139038086, "global_step": 531090, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0223968029022217, "global_step": 531091, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.114485502243042, "global_step": 531092, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9350320100784302, "global_step": 531093, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0589301586151123, "global_step": 531094, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.02884578704834, "global_step": 531095, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0808563232421875, "global_step": 531096, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0332396030426025, "global_step": 531097, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0078980922698975, "global_step": 531098, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.946885585784912, "global_step": 531099, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1066954135894775, "global_step": 531100, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0544016361236572, "global_step": 531101, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0536506175994873, "global_step": 531102, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.069985866546631, "global_step": 531103, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0584566593170166, "global_step": 531104, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9411976337432861, "global_step": 531105, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.040933847427368, "global_step": 531106, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9990885257720947, "global_step": 531107, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.116922616958618, "global_step": 531108, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.159646987915039, "global_step": 531109, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.09006929397583, "global_step": 531110, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.110685348510742, "global_step": 531111, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.055917978286743, "global_step": 531112, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1354589462280273, "global_step": 531113, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.085808753967285, "global_step": 531114, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.140437364578247, "global_step": 531115, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.109299659729004, "global_step": 531116, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0124752521514893, "global_step": 531117, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.091610908508301, "global_step": 531118, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.092393398284912, "global_step": 531119, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9751551151275635, "global_step": 531120, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.9242898225784302, "global_step": 531121, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.069596767425537, "global_step": 531122, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1457834243774414, "global_step": 531123, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.983345866203308, "global_step": 531124, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.058609962463379, "global_step": 531125, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.040140151977539, "global_step": 531126, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.089470624923706, "global_step": 531127, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0420031547546387, "global_step": 531128, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.070897340774536, "global_step": 531129, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.066267251968384, "global_step": 531130, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.017594575881958, "global_step": 531131, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.167725086212158, "global_step": 531132, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.09832501411438, "global_step": 531133, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.1626617908477783, "global_step": 531134, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.017601251602173, "global_step": 531135, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.037099838256836, "global_step": 531136, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0357441902160645, "global_step": 531137, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.032707452774048, "global_step": 531138, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0437679290771484, "global_step": 531139, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.056917905807495, "global_step": 531140, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.0885331630706787, "global_step": 531141, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.064656972885132, "global_step": 531142, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.035959005355835, "global_step": 531143, "epoch": 897, "lr": 5e-05}
{"train_loss": 2.039151191711426, "global_step": 531144, "epoch": 897, "lr": 5e-05}
{"train_loss": 1.995104193687439, "global_step": 531145, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9674216508865356, "global_step": 531146, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1010818481445312, "global_step": 531147, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.090017080307007, "global_step": 531148, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.050436496734619, "global_step": 531149, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.049031972885132, "global_step": 531150, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0104520320892334, "global_step": 531151, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1072421073913574, "global_step": 531152, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.038038492202759, "global_step": 531153, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0548057556152344, "global_step": 531154, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0444581508636475, "global_step": 531155, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.021685838699341, "global_step": 531156, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.03169846534729, "global_step": 531157, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9143564701080322, "global_step": 531158, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0570154190063477, "global_step": 531159, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.042745351791382, "global_step": 531160, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9843271970748901, "global_step": 531161, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.058485269546509, "global_step": 531162, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0199265480041504, "global_step": 531163, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.01206111907959, "global_step": 531164, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9695158004760742, "global_step": 531165, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.962589144706726, "global_step": 531166, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.937923550605774, "global_step": 531167, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.051631450653076, "global_step": 531168, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0930087566375732, "global_step": 531169, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.042428493499756, "global_step": 531170, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9747103452682495, "global_step": 531171, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0231072902679443, "global_step": 531172, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1096439361572266, "global_step": 531173, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9949134588241577, "global_step": 531174, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0971274375915527, "global_step": 531175, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0004079341888428, "global_step": 531176, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9943647384643555, "global_step": 531177, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0168793201446533, "global_step": 531178, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.096914529800415, "global_step": 531179, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.058384656906128, "global_step": 531180, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0616092681884766, "global_step": 531181, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.149366617202759, "global_step": 531182, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.05104660987854, "global_step": 531183, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0093884468078613, "global_step": 531184, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0034737586975098, "global_step": 531185, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0514461994171143, "global_step": 531186, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0371365547180176, "global_step": 531187, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0120561122894287, "global_step": 531188, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.993044376373291, "global_step": 531189, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9498369693756104, "global_step": 531190, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0866434574127197, "global_step": 531191, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0468430519104004, "global_step": 531192, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0772743225097656, "global_step": 531193, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.992204189300537, "global_step": 531194, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.006636619567871, "global_step": 531195, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.004005193710327, "global_step": 531196, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0818703174591064, "global_step": 531197, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1562206745147705, "global_step": 531198, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.041567802429199, "global_step": 531199, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.032621145248413, "global_step": 531200, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9674715995788574, "global_step": 531201, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.037672758102417, "global_step": 531202, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9702681303024292, "global_step": 531203, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.073674201965332, "global_step": 531204, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.040315866470337, "global_step": 531205, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.036477565765381, "global_step": 531206, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.967044472694397, "global_step": 531207, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0266072750091553, "global_step": 531208, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9585453271865845, "global_step": 531209, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.086346387863159, "global_step": 531210, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0697438716888428, "global_step": 531211, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9728649854660034, "global_step": 531212, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0367021560668945, "global_step": 531213, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0521724224090576, "global_step": 531214, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.966211199760437, "global_step": 531215, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0241892337799072, "global_step": 531216, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.070829391479492, "global_step": 531217, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0182533264160156, "global_step": 531218, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0368638038635254, "global_step": 531219, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.998537540435791, "global_step": 531220, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.046603202819824, "global_step": 531221, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.010333299636841, "global_step": 531222, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.07582688331604, "global_step": 531223, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9601900577545166, "global_step": 531224, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0828425884246826, "global_step": 531225, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.026455879211426, "global_step": 531226, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0671916007995605, "global_step": 531227, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.028129816055298, "global_step": 531228, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9799089431762695, "global_step": 531229, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1165144443511963, "global_step": 531230, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9578317403793335, "global_step": 531231, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9465422630310059, "global_step": 531232, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.004307508468628, "global_step": 531233, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0722010135650635, "global_step": 531234, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1232640743255615, "global_step": 531235, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1422359943389893, "global_step": 531236, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9856947660446167, "global_step": 531237, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0268406867980957, "global_step": 531238, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0038201808929443, "global_step": 531239, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.974991798400879, "global_step": 531240, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0425281524658203, "global_step": 531241, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.102745532989502, "global_step": 531242, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.997610092163086, "global_step": 531243, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0170702934265137, "global_step": 531244, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9774259328842163, "global_step": 531245, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.093954563140869, "global_step": 531246, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0433473587036133, "global_step": 531247, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.023451566696167, "global_step": 531248, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0516953468322754, "global_step": 531249, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.071260929107666, "global_step": 531250, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0896215438842773, "global_step": 531251, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1004202365875244, "global_step": 531252, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1041975021362305, "global_step": 531253, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.055558204650879, "global_step": 531254, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1494810581207275, "global_step": 531255, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0114428997039795, "global_step": 531256, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0433530807495117, "global_step": 531257, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.02596378326416, "global_step": 531258, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.033175468444824, "global_step": 531259, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9605969190597534, "global_step": 531260, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.041482448577881, "global_step": 531261, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0534660816192627, "global_step": 531262, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.937016487121582, "global_step": 531263, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.118406057357788, "global_step": 531264, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9636342525482178, "global_step": 531265, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.975205659866333, "global_step": 531266, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1097142696380615, "global_step": 531267, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9952104091644287, "global_step": 531268, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0305447578430176, "global_step": 531269, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.010244131088257, "global_step": 531270, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9744197130203247, "global_step": 531271, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.072075605392456, "global_step": 531272, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0200297832489014, "global_step": 531273, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.004077911376953, "global_step": 531274, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.101335048675537, "global_step": 531275, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.018871307373047, "global_step": 531276, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.993152379989624, "global_step": 531277, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0872087478637695, "global_step": 531278, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0271565914154053, "global_step": 531279, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.96856689453125, "global_step": 531280, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0458638668060303, "global_step": 531281, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0513107776641846, "global_step": 531282, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0994935035705566, "global_step": 531283, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.022395372390747, "global_step": 531284, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0010826587677, "global_step": 531285, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.052842140197754, "global_step": 531286, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.080050468444824, "global_step": 531287, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9886159896850586, "global_step": 531288, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9996458292007446, "global_step": 531289, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9508042335510254, "global_step": 531290, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0969624519348145, "global_step": 531291, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9891688823699951, "global_step": 531292, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.153826951980591, "global_step": 531293, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9790327548980713, "global_step": 531294, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9710198640823364, "global_step": 531295, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.126995801925659, "global_step": 531296, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9685815572738647, "global_step": 531297, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.986241102218628, "global_step": 531298, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9343219995498657, "global_step": 531299, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0528414249420166, "global_step": 531300, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0412888526916504, "global_step": 531301, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9778939485549927, "global_step": 531302, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1325716972351074, "global_step": 531303, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.004349708557129, "global_step": 531304, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.043794631958008, "global_step": 531305, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0582034587860107, "global_step": 531306, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.084717273712158, "global_step": 531307, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0155911445617676, "global_step": 531308, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.071338653564453, "global_step": 531309, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.021890163421631, "global_step": 531310, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0503194332122803, "global_step": 531311, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.037255048751831, "global_step": 531312, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0939218997955322, "global_step": 531313, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.058807134628296, "global_step": 531314, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0309367179870605, "global_step": 531315, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.000368356704712, "global_step": 531316, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0092215538024902, "global_step": 531317, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0856738090515137, "global_step": 531318, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0808470249176025, "global_step": 531319, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0815069675445557, "global_step": 531320, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0050275325775146, "global_step": 531321, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9429737329483032, "global_step": 531322, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9312776327133179, "global_step": 531323, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.092216730117798, "global_step": 531324, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9302860498428345, "global_step": 531325, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0719571113586426, "global_step": 531326, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0624020099639893, "global_step": 531327, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0795042514801025, "global_step": 531328, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0476787090301514, "global_step": 531329, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9974949359893799, "global_step": 531330, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.991378664970398, "global_step": 531331, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.110682725906372, "global_step": 531332, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0410053730010986, "global_step": 531333, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.002840995788574, "global_step": 531334, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0798556804656982, "global_step": 531335, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.109520673751831, "global_step": 531336, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.109454393386841, "global_step": 531337, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0939924716949463, "global_step": 531338, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.016491413116455, "global_step": 531339, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9146728515625, "global_step": 531340, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0322258472442627, "global_step": 531341, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.035087823867798, "global_step": 531342, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0465335845947266, "global_step": 531343, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9613726139068604, "global_step": 531344, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0676605701446533, "global_step": 531345, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.06955885887146, "global_step": 531346, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9657005071640015, "global_step": 531347, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9787629842758179, "global_step": 531348, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.08945369720459, "global_step": 531349, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9917632341384888, "global_step": 531350, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9506617784500122, "global_step": 531351, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.052905559539795, "global_step": 531352, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0786705017089844, "global_step": 531353, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0715348720550537, "global_step": 531354, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.957641839981079, "global_step": 531355, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0639731884002686, "global_step": 531356, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.062493085861206, "global_step": 531357, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.032562732696533, "global_step": 531358, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9907680749893188, "global_step": 531359, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0067923069000244, "global_step": 531360, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.035733938217163, "global_step": 531361, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0123307704925537, "global_step": 531362, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9836561679840088, "global_step": 531363, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.012901544570923, "global_step": 531364, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0535006523132324, "global_step": 531365, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0725085735321045, "global_step": 531366, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.091332197189331, "global_step": 531367, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0293848514556885, "global_step": 531368, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9658437967300415, "global_step": 531369, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.048456907272339, "global_step": 531370, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9930943250656128, "global_step": 531371, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0529208183288574, "global_step": 531372, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.053269386291504, "global_step": 531373, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9726905822753906, "global_step": 531374, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0343081951141357, "global_step": 531375, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0110623836517334, "global_step": 531376, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9799821376800537, "global_step": 531377, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1159236431121826, "global_step": 531378, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0173778533935547, "global_step": 531379, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1313514709472656, "global_step": 531380, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0852465629577637, "global_step": 531381, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0149288177490234, "global_step": 531382, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0551352500915527, "global_step": 531383, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9950765371322632, "global_step": 531384, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0107948780059814, "global_step": 531385, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.98328697681427, "global_step": 531386, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.968022108078003, "global_step": 531387, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0006754398345947, "global_step": 531388, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0350661277770996, "global_step": 531389, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0274815559387207, "global_step": 531390, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.012786388397217, "global_step": 531391, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9842872619628906, "global_step": 531392, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.024256706237793, "global_step": 531393, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0570666790008545, "global_step": 531394, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.005237340927124, "global_step": 531395, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.069244146347046, "global_step": 531396, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.966357946395874, "global_step": 531397, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.056881904602051, "global_step": 531398, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.060898780822754, "global_step": 531399, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9955639839172363, "global_step": 531400, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0062692165374756, "global_step": 531401, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9962764978408813, "global_step": 531402, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.069195508956909, "global_step": 531403, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1082921028137207, "global_step": 531404, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.108275890350342, "global_step": 531405, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0026168823242188, "global_step": 531406, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9531375169754028, "global_step": 531407, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0696706771850586, "global_step": 531408, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0604283809661865, "global_step": 531409, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9758855104446411, "global_step": 531410, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.049104928970337, "global_step": 531411, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1862738132476807, "global_step": 531412, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0539231300354004, "global_step": 531413, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.098883867263794, "global_step": 531414, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.049253463745117, "global_step": 531415, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0061988830566406, "global_step": 531416, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9994322061538696, "global_step": 531417, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.940879464149475, "global_step": 531418, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9673410654067993, "global_step": 531419, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1387808322906494, "global_step": 531420, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0179717540740967, "global_step": 531421, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.02651309967041, "global_step": 531422, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.023420810699463, "global_step": 531423, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.000347375869751, "global_step": 531424, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0465846061706543, "global_step": 531425, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.044198989868164, "global_step": 531426, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.090207099914551, "global_step": 531427, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.007054567337036, "global_step": 531428, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.020355701446533, "global_step": 531429, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9968371391296387, "global_step": 531430, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9582898616790771, "global_step": 531431, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9923492670059204, "global_step": 531432, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.93770432472229, "global_step": 531433, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0888900756835938, "global_step": 531434, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.005798578262329, "global_step": 531435, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.049839973449707, "global_step": 531436, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0317108631134033, "global_step": 531437, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.069837808609009, "global_step": 531438, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.007530927658081, "global_step": 531439, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9668331146240234, "global_step": 531440, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.106994390487671, "global_step": 531441, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.114821434020996, "global_step": 531442, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9704891443252563, "global_step": 531443, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.046888828277588, "global_step": 531444, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9607698917388916, "global_step": 531445, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9966381788253784, "global_step": 531446, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0878713130950928, "global_step": 531447, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.109241485595703, "global_step": 531448, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0317249298095703, "global_step": 531449, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0391292572021484, "global_step": 531450, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0009284019470215, "global_step": 531451, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.965614914894104, "global_step": 531452, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0574049949645996, "global_step": 531453, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0412609577178955, "global_step": 531454, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.011028528213501, "global_step": 531455, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0141677856445312, "global_step": 531456, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.032589912414551, "global_step": 531457, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.02833890914917, "global_step": 531458, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9817743301391602, "global_step": 531459, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0393412113189697, "global_step": 531460, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9788509607315063, "global_step": 531461, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9947402477264404, "global_step": 531462, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9741110801696777, "global_step": 531463, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0496528148651123, "global_step": 531464, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.054903984069824, "global_step": 531465, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.161126136779785, "global_step": 531466, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0376782417297363, "global_step": 531467, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9558463096618652, "global_step": 531468, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9900203943252563, "global_step": 531469, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0333330631256104, "global_step": 531470, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0635318756103516, "global_step": 531471, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0480659008026123, "global_step": 531472, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0619754791259766, "global_step": 531473, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.056614875793457, "global_step": 531474, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9886375665664673, "global_step": 531475, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.963126540184021, "global_step": 531476, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0687384605407715, "global_step": 531477, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.041407823562622, "global_step": 531478, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.027790069580078, "global_step": 531479, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9741753339767456, "global_step": 531480, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0114426612854004, "global_step": 531481, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.009063243865967, "global_step": 531482, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.07275390625, "global_step": 531483, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1736581325531006, "global_step": 531484, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.071284770965576, "global_step": 531485, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9831020832061768, "global_step": 531486, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0837361812591553, "global_step": 531487, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9526671171188354, "global_step": 531488, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0112133026123047, "global_step": 531489, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0015807151794434, "global_step": 531490, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1154117584228516, "global_step": 531491, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.019534111022949, "global_step": 531492, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9563552141189575, "global_step": 531493, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.125027894973755, "global_step": 531494, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1299431324005127, "global_step": 531495, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0869500637054443, "global_step": 531496, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0297653675079346, "global_step": 531497, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9326589107513428, "global_step": 531498, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0306737422943115, "global_step": 531499, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0194032192230225, "global_step": 531500, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.140113592147827, "global_step": 531501, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0211427211761475, "global_step": 531502, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0458624362945557, "global_step": 531503, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.098686695098877, "global_step": 531504, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9708032608032227, "global_step": 531505, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0574193000793457, "global_step": 531506, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9265413284301758, "global_step": 531507, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.129404306411743, "global_step": 531508, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0826687812805176, "global_step": 531509, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.028613328933716, "global_step": 531510, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.07033634185791, "global_step": 531511, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0865626335144043, "global_step": 531512, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0672988891601562, "global_step": 531513, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0193092823028564, "global_step": 531514, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9491888284683228, "global_step": 531515, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.068091869354248, "global_step": 531516, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0953409671783447, "global_step": 531517, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0928878784179688, "global_step": 531518, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9864006042480469, "global_step": 531519, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9416205883026123, "global_step": 531520, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.000175952911377, "global_step": 531521, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0210580825805664, "global_step": 531522, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.108682155609131, "global_step": 531523, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1137163639068604, "global_step": 531524, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0242769718170166, "global_step": 531525, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0881989002227783, "global_step": 531526, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0886425971984863, "global_step": 531527, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0303075313568115, "global_step": 531528, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.042764902114868, "global_step": 531529, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.05393648147583, "global_step": 531530, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0413730144500732, "global_step": 531531, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9645887613296509, "global_step": 531532, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0110061168670654, "global_step": 531533, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0482592582702637, "global_step": 531534, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0540292263031006, "global_step": 531535, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.01802134513855, "global_step": 531536, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.053420305252075, "global_step": 531537, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0188944339752197, "global_step": 531538, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.093552589416504, "global_step": 531539, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9828637838363647, "global_step": 531540, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0446596145629883, "global_step": 531541, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0718390941619873, "global_step": 531542, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.948968529701233, "global_step": 531543, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0310444831848145, "global_step": 531544, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0817339420318604, "global_step": 531545, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.029021739959717, "global_step": 531546, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0275137424468994, "global_step": 531547, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9532557725906372, "global_step": 531548, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1062183380126953, "global_step": 531549, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0790750980377197, "global_step": 531550, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9981001615524292, "global_step": 531551, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0284368991851807, "global_step": 531552, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.980455756187439, "global_step": 531553, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0526249408721924, "global_step": 531554, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.089920997619629, "global_step": 531555, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0274436473846436, "global_step": 531556, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.112396001815796, "global_step": 531557, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0659122467041016, "global_step": 531558, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.072355031967163, "global_step": 531559, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9725154638290405, "global_step": 531560, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0273685455322266, "global_step": 531561, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.019789218902588, "global_step": 531562, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9680166244506836, "global_step": 531563, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.069078207015991, "global_step": 531564, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1183063983917236, "global_step": 531565, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.00836443901062, "global_step": 531566, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.020258665084839, "global_step": 531567, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0258119106292725, "global_step": 531568, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.047776937484741, "global_step": 531569, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0137555599212646, "global_step": 531570, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9970366954803467, "global_step": 531571, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0412983894348145, "global_step": 531572, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0596628189086914, "global_step": 531573, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0843677520751953, "global_step": 531574, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0654866695404053, "global_step": 531575, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9338456392288208, "global_step": 531576, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0619969367980957, "global_step": 531577, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.087656259536743, "global_step": 531578, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0409529209136963, "global_step": 531579, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0712788105010986, "global_step": 531580, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0710995197296143, "global_step": 531581, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.030561923980713, "global_step": 531582, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0031347274780273, "global_step": 531583, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1068003177642822, "global_step": 531584, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1064329147338867, "global_step": 531585, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0644562244415283, "global_step": 531586, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9870412349700928, "global_step": 531587, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.086627244949341, "global_step": 531588, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.030388832092285, "global_step": 531589, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0348305702209473, "global_step": 531590, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0904617309570312, "global_step": 531591, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0548293590545654, "global_step": 531592, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0075161457061768, "global_step": 531593, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9852701425552368, "global_step": 531594, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1032559871673584, "global_step": 531595, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.038703203201294, "global_step": 531596, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0898330211639404, "global_step": 531597, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1103997230529785, "global_step": 531598, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9584050178527832, "global_step": 531599, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.028963565826416, "global_step": 531600, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1124844551086426, "global_step": 531601, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9524558782577515, "global_step": 531602, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.020962715148926, "global_step": 531603, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1087305545806885, "global_step": 531604, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.064387321472168, "global_step": 531605, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.044936418533325, "global_step": 531606, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9909697771072388, "global_step": 531607, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0341591835021973, "global_step": 531608, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0302693843841553, "global_step": 531609, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0779998302459717, "global_step": 531610, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.111457109451294, "global_step": 531611, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0662076473236084, "global_step": 531612, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.014998197555542, "global_step": 531613, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9538785219192505, "global_step": 531614, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0060129165649414, "global_step": 531615, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.013394355773926, "global_step": 531616, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.04138445854187, "global_step": 531617, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.088352680206299, "global_step": 531618, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0871381759643555, "global_step": 531619, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9958384037017822, "global_step": 531620, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0962073802948, "global_step": 531621, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0421977043151855, "global_step": 531622, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.024785280227661, "global_step": 531623, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9737685918807983, "global_step": 531624, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0842437744140625, "global_step": 531625, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9667372703552246, "global_step": 531626, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9779727458953857, "global_step": 531627, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9778846502304077, "global_step": 531628, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.136704683303833, "global_step": 531629, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.095627546310425, "global_step": 531630, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.027869939804077, "global_step": 531631, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.060764789581299, "global_step": 531632, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9909107685089111, "global_step": 531633, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.090130567550659, "global_step": 531634, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.10164475440979, "global_step": 531635, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0200536251068115, "global_step": 531636, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.063901424407959, "global_step": 531637, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9881409406661987, "global_step": 531638, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0893959999084473, "global_step": 531639, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9994302988052368, "global_step": 531640, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.073021650314331, "global_step": 531641, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0585684776306152, "global_step": 531642, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0850584506988525, "global_step": 531643, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0526654720306396, "global_step": 531644, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1123955249786377, "global_step": 531645, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0287394523620605, "global_step": 531646, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.973249077796936, "global_step": 531647, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.051832675933838, "global_step": 531648, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.051302909851074, "global_step": 531649, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.032872200012207, "global_step": 531650, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1030561923980713, "global_step": 531651, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.054523468017578, "global_step": 531652, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.106431484222412, "global_step": 531653, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0547170639038086, "global_step": 531654, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1153206825256348, "global_step": 531655, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.093045234680176, "global_step": 531656, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0709969997406006, "global_step": 531657, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9826922416687012, "global_step": 531658, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0090184211730957, "global_step": 531659, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0212113857269287, "global_step": 531660, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9830663204193115, "global_step": 531661, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.131685256958008, "global_step": 531662, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0915729999542236, "global_step": 531663, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.967689871788025, "global_step": 531664, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.044926881790161, "global_step": 531665, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.103515625, "global_step": 531666, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.160442590713501, "global_step": 531667, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.986656904220581, "global_step": 531668, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9969596862792969, "global_step": 531669, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.037379503250122, "global_step": 531670, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.123755931854248, "global_step": 531671, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0712099075317383, "global_step": 531672, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9997243881225586, "global_step": 531673, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0754177570343018, "global_step": 531674, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9587922096252441, "global_step": 531675, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0988383293151855, "global_step": 531676, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0510952472686768, "global_step": 531677, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0719728469848633, "global_step": 531678, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9641480445861816, "global_step": 531679, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9795243740081787, "global_step": 531680, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0761866569519043, "global_step": 531681, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.985363483428955, "global_step": 531682, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0055134296417236, "global_step": 531683, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0254364013671875, "global_step": 531684, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.095212459564209, "global_step": 531685, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.004099130630493, "global_step": 531686, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0159661769866943, "global_step": 531687, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9498025178909302, "global_step": 531688, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.057708740234375, "global_step": 531689, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.040736198425293, "global_step": 531690, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0431106090545654, "global_step": 531691, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.998234510421753, "global_step": 531692, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.054715156555176, "global_step": 531693, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.104712963104248, "global_step": 531694, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0389275550842285, "global_step": 531695, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0545716285705566, "global_step": 531696, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0338146686553955, "global_step": 531697, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0639102458953857, "global_step": 531698, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0281970500946045, "global_step": 531699, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.970771074295044, "global_step": 531700, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0371971130371094, "global_step": 531701, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.949092984199524, "global_step": 531702, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.012723684310913, "global_step": 531703, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.004701852798462, "global_step": 531704, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0721471309661865, "global_step": 531705, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0771119594573975, "global_step": 531706, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.07639479637146, "global_step": 531707, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.083343744277954, "global_step": 531708, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0233659744262695, "global_step": 531709, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.072176218032837, "global_step": 531710, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.115952968597412, "global_step": 531711, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.040212631225586, "global_step": 531712, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0235726833343506, "global_step": 531713, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.028998374938965, "global_step": 531714, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.052290916442871, "global_step": 531715, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9887442588806152, "global_step": 531716, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0221519470214844, "global_step": 531717, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0156736373901367, "global_step": 531718, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1274404525756836, "global_step": 531719, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.010615110397339, "global_step": 531720, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0020008087158203, "global_step": 531721, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.099693536758423, "global_step": 531722, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0377652645111084, "global_step": 531723, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9886605739593506, "global_step": 531724, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1197309494018555, "global_step": 531725, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9775502681732178, "global_step": 531726, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.167400360107422, "global_step": 531727, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0318353176116943, "global_step": 531728, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0222291946411133, "global_step": 531729, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0499744415283203, "global_step": 531730, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0346837043762207, "global_step": 531731, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.966816782951355, "global_step": 531732, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0292458534240723, "global_step": 531733, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1195623874664307, "global_step": 531734, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.072124481201172, "global_step": 531735, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.008577585220337, "global_step": 531736, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0104432106018066, "global_step": 531737, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.058373212814331, "global_step": 531738, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0410945415496826, "global_step": 531739, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0828537940979004, "global_step": 531740, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0144453048706055, "global_step": 531741, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.103980541229248, "global_step": 531742, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0242364406585693, "global_step": 531743, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.019801378250122, "global_step": 531744, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.023024082183838, "global_step": 531745, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0756404399871826, "global_step": 531746, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0341527462005615, "global_step": 531747, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0072150230407715, "global_step": 531748, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0988218784332275, "global_step": 531749, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9997460842132568, "global_step": 531750, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.008786916732788, "global_step": 531751, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0907740592956543, "global_step": 531752, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.003767251968384, "global_step": 531753, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.041975975036621, "global_step": 531754, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.091987371444702, "global_step": 531755, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9682358503341675, "global_step": 531756, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9394164085388184, "global_step": 531757, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0692105293273926, "global_step": 531758, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.107659101486206, "global_step": 531759, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0927999019622803, "global_step": 531760, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0331575870513916, "global_step": 531761, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.068284749984741, "global_step": 531762, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0597379207611084, "global_step": 531763, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.045339584350586, "global_step": 531764, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.037886142730713, "global_step": 531765, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0153355598449707, "global_step": 531766, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.033841848373413, "global_step": 531767, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0636816024780273, "global_step": 531768, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9953285455703735, "global_step": 531769, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.066328525543213, "global_step": 531770, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0953354835510254, "global_step": 531771, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0903706550598145, "global_step": 531772, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.930648922920227, "global_step": 531773, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1195883750915527, "global_step": 531774, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.014317512512207, "global_step": 531775, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.095738172531128, "global_step": 531776, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.05145263671875, "global_step": 531777, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.005032777786255, "global_step": 531778, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.060279369354248, "global_step": 531779, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1202633380889893, "global_step": 531780, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1317431926727295, "global_step": 531781, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0180609226226807, "global_step": 531782, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0472702980041504, "global_step": 531783, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.068223476409912, "global_step": 531784, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0181939601898193, "global_step": 531785, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.14449405670166, "global_step": 531786, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.015873432159424, "global_step": 531787, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0253653526306152, "global_step": 531788, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.099634885787964, "global_step": 531789, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.072319507598877, "global_step": 531790, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0753276348114014, "global_step": 531791, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0204057693481445, "global_step": 531792, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9885179996490479, "global_step": 531793, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0168769359588623, "global_step": 531794, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0650815963745117, "global_step": 531795, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0619263648986816, "global_step": 531796, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.04819655418396, "global_step": 531797, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9660154581069946, "global_step": 531798, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9929375648498535, "global_step": 531799, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0963449478149414, "global_step": 531800, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.089285373687744, "global_step": 531801, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.040661573410034, "global_step": 531802, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.07783842086792, "global_step": 531803, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9941251277923584, "global_step": 531804, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.025987386703491, "global_step": 531805, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.001634359359741, "global_step": 531806, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0750479698181152, "global_step": 531807, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0298309326171875, "global_step": 531808, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1206157207489014, "global_step": 531809, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.051177740097046, "global_step": 531810, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0360827445983887, "global_step": 531811, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.079411029815674, "global_step": 531812, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.01601505279541, "global_step": 531813, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.051643133163452, "global_step": 531814, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1301331520080566, "global_step": 531815, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9885629415512085, "global_step": 531816, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9477145671844482, "global_step": 531817, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0676684379577637, "global_step": 531818, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0732247829437256, "global_step": 531819, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0577986240386963, "global_step": 531820, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0403268337249756, "global_step": 531821, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.042867422103882, "global_step": 531822, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9595947265625, "global_step": 531823, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0137317180633545, "global_step": 531824, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.054593086242676, "global_step": 531825, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.096574306488037, "global_step": 531826, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0344390869140625, "global_step": 531827, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.035787582397461, "global_step": 531828, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.017094850540161, "global_step": 531829, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1072471141815186, "global_step": 531830, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1471238136291504, "global_step": 531831, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9717750549316406, "global_step": 531832, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9454724788665771, "global_step": 531833, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0307834148406982, "global_step": 531834, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0997891426086426, "global_step": 531835, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.052757978439331, "global_step": 531836, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.965073823928833, "global_step": 531837, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1118710041046143, "global_step": 531838, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0797922611236572, "global_step": 531839, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0598530769348145, "global_step": 531840, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.01638126373291, "global_step": 531841, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0635623931884766, "global_step": 531842, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.024912118911743, "global_step": 531843, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0634632110595703, "global_step": 531844, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1060590744018555, "global_step": 531845, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.089811325073242, "global_step": 531846, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9949535131454468, "global_step": 531847, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0225212574005127, "global_step": 531848, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0203449726104736, "global_step": 531849, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.020216226577759, "global_step": 531850, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.023362636566162, "global_step": 531851, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0539486408233643, "global_step": 531852, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.00883150100708, "global_step": 531853, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.055811643600464, "global_step": 531854, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0705268383026123, "global_step": 531855, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1066477298736572, "global_step": 531856, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9623994827270508, "global_step": 531857, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.999623417854309, "global_step": 531858, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0512335300445557, "global_step": 531859, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0783753395080566, "global_step": 531860, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.037484645843506, "global_step": 531861, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0522375106811523, "global_step": 531862, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0612432956695557, "global_step": 531863, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.038483142852783, "global_step": 531864, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0386784076690674, "global_step": 531865, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0108628273010254, "global_step": 531866, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1295762062072754, "global_step": 531867, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1212942600250244, "global_step": 531868, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.010850191116333, "global_step": 531869, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0582191944122314, "global_step": 531870, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9396196603775024, "global_step": 531871, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0208983421325684, "global_step": 531872, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1063640117645264, "global_step": 531873, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1254892349243164, "global_step": 531874, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0080103874206543, "global_step": 531875, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.984706997871399, "global_step": 531876, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.102128028869629, "global_step": 531877, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.040250539779663, "global_step": 531878, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0751235485076904, "global_step": 531879, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0774660110473633, "global_step": 531880, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.080834150314331, "global_step": 531881, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9936318397521973, "global_step": 531882, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.007362127304077, "global_step": 531883, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.09355092048645, "global_step": 531884, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0982329845428467, "global_step": 531885, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0030810832977295, "global_step": 531886, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9745755195617676, "global_step": 531887, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9958337545394897, "global_step": 531888, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.047485113143921, "global_step": 531889, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0719833374023438, "global_step": 531890, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9678730964660645, "global_step": 531891, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0453457832336426, "global_step": 531892, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0273630619049072, "global_step": 531893, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9851349592208862, "global_step": 531894, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.063596487045288, "global_step": 531895, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0103304386138916, "global_step": 531896, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.043987512588501, "global_step": 531897, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.080314874649048, "global_step": 531898, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.063555955886841, "global_step": 531899, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.956453561782837, "global_step": 531900, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.081113815307617, "global_step": 531901, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0678656101226807, "global_step": 531902, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9527171850204468, "global_step": 531903, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.975790023803711, "global_step": 531904, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.103849172592163, "global_step": 531905, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0571563243865967, "global_step": 531906, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9347376823425293, "global_step": 531907, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0243232250213623, "global_step": 531908, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.059746265411377, "global_step": 531909, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.037776470184326, "global_step": 531910, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0642590522766113, "global_step": 531911, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.108525037765503, "global_step": 531912, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0022835731506348, "global_step": 531913, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1119630336761475, "global_step": 531914, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9838886260986328, "global_step": 531915, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1089160442352295, "global_step": 531916, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9962871074676514, "global_step": 531917, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.08345890045166, "global_step": 531918, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0278804302215576, "global_step": 531919, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0631115436553955, "global_step": 531920, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.104203939437866, "global_step": 531921, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.007229804992676, "global_step": 531922, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.001844644546509, "global_step": 531923, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0729312896728516, "global_step": 531924, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0674550533294678, "global_step": 531925, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0253376960754395, "global_step": 531926, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0230624675750732, "global_step": 531927, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.082705020904541, "global_step": 531928, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0200510025024414, "global_step": 531929, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0284974575042725, "global_step": 531930, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0473995208740234, "global_step": 531931, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.137951612472534, "global_step": 531932, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0984790325164795, "global_step": 531933, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0473201274871826, "global_step": 531934, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9912134408950806, "global_step": 531935, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.975671648979187, "global_step": 531936, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0548579692840576, "global_step": 531937, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0060651302337646, "global_step": 531938, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.052523136138916, "global_step": 531939, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0957107543945312, "global_step": 531940, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1046981811523438, "global_step": 531941, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9750242233276367, "global_step": 531942, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0303308963775635, "global_step": 531943, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.001201629638672, "global_step": 531944, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0192067623138428, "global_step": 531945, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.022244691848755, "global_step": 531946, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.08201265335083, "global_step": 531947, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9916460514068604, "global_step": 531948, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.057661771774292, "global_step": 531949, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.051008701324463, "global_step": 531950, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0943260192871094, "global_step": 531951, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.031475067138672, "global_step": 531952, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.074883222579956, "global_step": 531953, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.061671733856201, "global_step": 531954, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.017183780670166, "global_step": 531955, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0422494411468506, "global_step": 531956, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0610382556915283, "global_step": 531957, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0807619094848633, "global_step": 531958, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.062959909439087, "global_step": 531959, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.192272663116455, "global_step": 531960, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0666792392730713, "global_step": 531961, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.032318592071533, "global_step": 531962, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.057774066925049, "global_step": 531963, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0292294025421143, "global_step": 531964, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.039513111114502, "global_step": 531965, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0365943908691406, "global_step": 531966, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0644168853759766, "global_step": 531967, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0545713901519775, "global_step": 531968, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0444488525390625, "global_step": 531969, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0576066970825195, "global_step": 531970, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.045790433883667, "global_step": 531971, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0542709827423096, "global_step": 531972, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.010226011276245, "global_step": 531973, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.109618902206421, "global_step": 531974, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0252604484558105, "global_step": 531975, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.061762809753418, "global_step": 531976, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0702884197235107, "global_step": 531977, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.002711057662964, "global_step": 531978, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9959571361541748, "global_step": 531979, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.075254440307617, "global_step": 531980, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0240089893341064, "global_step": 531981, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0246381759643555, "global_step": 531982, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.043058156967163, "global_step": 531983, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0391738414764404, "global_step": 531984, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.096794366836548, "global_step": 531985, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9937770366668701, "global_step": 531986, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9570026397705078, "global_step": 531987, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0404648780822754, "global_step": 531988, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9977073669433594, "global_step": 531989, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0243685245513916, "global_step": 531990, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0303361415863037, "global_step": 531991, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.018728733062744, "global_step": 531992, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0577683448791504, "global_step": 531993, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.083221673965454, "global_step": 531994, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9325600862503052, "global_step": 531995, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0274651050567627, "global_step": 531996, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9991137981414795, "global_step": 531997, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9791572093963623, "global_step": 531998, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0597431659698486, "global_step": 531999, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0348470211029053, "global_step": 532000, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9203965663909912, "global_step": 532001, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0050175189971924, "global_step": 532002, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.015368938446045, "global_step": 532003, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.00122332572937, "global_step": 532004, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.108091354370117, "global_step": 532005, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.044955253601074, "global_step": 532006, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.035351514816284, "global_step": 532007, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0799672603607178, "global_step": 532008, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.03513503074646, "global_step": 532009, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9780752658843994, "global_step": 532010, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.055940628051758, "global_step": 532011, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.05550479888916, "global_step": 532012, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.012927293777466, "global_step": 532013, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0457451343536377, "global_step": 532014, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.009775400161743, "global_step": 532015, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9762777090072632, "global_step": 532016, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0825464725494385, "global_step": 532017, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.008345127105713, "global_step": 532018, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0249595642089844, "global_step": 532019, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.08312726020813, "global_step": 532020, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.10495924949646, "global_step": 532021, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0252435207366943, "global_step": 532022, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9973732233047485, "global_step": 532023, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0279669761657715, "global_step": 532024, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.088921070098877, "global_step": 532025, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0171027183532715, "global_step": 532026, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0725345611572266, "global_step": 532027, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.020181894302368, "global_step": 532028, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0204215049743652, "global_step": 532029, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9793436527252197, "global_step": 532030, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0196945667266846, "global_step": 532031, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.989020824432373, "global_step": 532032, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9413472414016724, "global_step": 532033, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9959217309951782, "global_step": 532034, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0189714431762695, "global_step": 532035, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0237534046173096, "global_step": 532036, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9725401401519775, "global_step": 532037, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.078651189804077, "global_step": 532038, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1027672290802, "global_step": 532039, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.057656764984131, "global_step": 532040, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.034503936767578, "global_step": 532041, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.082472562789917, "global_step": 532042, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.058488368988037, "global_step": 532043, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0595452785491943, "global_step": 532044, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0032577514648438, "global_step": 532045, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9642021656036377, "global_step": 532046, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0288045406341553, "global_step": 532047, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.070895195007324, "global_step": 532048, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9931796789169312, "global_step": 532049, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0359926223754883, "global_step": 532050, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.005272626876831, "global_step": 532051, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0739336013793945, "global_step": 532052, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.065277576446533, "global_step": 532053, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0702688694000244, "global_step": 532054, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9656625986099243, "global_step": 532055, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.066239833831787, "global_step": 532056, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.061490058898926, "global_step": 532057, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.063656806945801, "global_step": 532058, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0283446311950684, "global_step": 532059, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.133915662765503, "global_step": 532060, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.039996385574341, "global_step": 532061, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.045353889465332, "global_step": 532062, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.078718423843384, "global_step": 532063, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.016383409500122, "global_step": 532064, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.990294098854065, "global_step": 532065, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9919319152832031, "global_step": 532066, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9646583795547485, "global_step": 532067, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0536043643951416, "global_step": 532068, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0265111923217773, "global_step": 532069, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1534085273742676, "global_step": 532070, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0173487663269043, "global_step": 532071, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.052788019180298, "global_step": 532072, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.034794330596924, "global_step": 532073, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.120133399963379, "global_step": 532074, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0416057109832764, "global_step": 532075, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.159158945083618, "global_step": 532076, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0499579906463623, "global_step": 532077, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9936250448226929, "global_step": 532078, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.077037811279297, "global_step": 532079, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9907898902893066, "global_step": 532080, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.116241693496704, "global_step": 532081, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9577981233596802, "global_step": 532082, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0088748931884766, "global_step": 532083, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.00685453414917, "global_step": 532084, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0101771354675293, "global_step": 532085, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.098170518875122, "global_step": 532086, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0059313774108887, "global_step": 532087, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0725345611572266, "global_step": 532088, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.090339422225952, "global_step": 532089, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.054476022720337, "global_step": 532090, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.009549856185913, "global_step": 532091, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0167863368988037, "global_step": 532092, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.984531283378601, "global_step": 532093, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.090070962905884, "global_step": 532094, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.994590163230896, "global_step": 532095, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0238280296325684, "global_step": 532096, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.1033918857574463, "global_step": 532097, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.061490297317505, "global_step": 532098, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.067460298538208, "global_step": 532099, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.067898988723755, "global_step": 532100, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.047320604324341, "global_step": 532101, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0535199642181396, "global_step": 532102, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.970712661743164, "global_step": 532103, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0185258388519287, "global_step": 532104, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0069892406463623, "global_step": 532105, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9261832237243652, "global_step": 532106, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.089129686355591, "global_step": 532107, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0097508430480957, "global_step": 532108, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0308477878570557, "global_step": 532109, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.002307653427124, "global_step": 532110, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0813887119293213, "global_step": 532111, "epoch": 898, "lr": 5e-05}
{"train_loss": 1.9987527132034302, "global_step": 532112, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.0381762981414795, "global_step": 532113, "epoch": 898, "lr": 5e-05}
{"train_loss": 2.047604560852051, "global_step": 532114, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0912697315216064, "global_step": 532115, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.8606313467025757, "global_step": 532116, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.000650405883789, "global_step": 532117, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.03469181060791, "global_step": 532118, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0465102195739746, "global_step": 532119, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0400187969207764, "global_step": 532120, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9942512512207031, "global_step": 532121, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.086578130722046, "global_step": 532122, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.019582748413086, "global_step": 532123, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0112695693969727, "global_step": 532124, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9529660940170288, "global_step": 532125, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.030613422393799, "global_step": 532126, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0881271362304688, "global_step": 532127, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.010793685913086, "global_step": 532128, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9271762371063232, "global_step": 532129, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.053600549697876, "global_step": 532130, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.036736011505127, "global_step": 532131, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9113049507141113, "global_step": 532132, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.066542625427246, "global_step": 532133, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9387102127075195, "global_step": 532134, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0255279541015625, "global_step": 532135, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0598883628845215, "global_step": 532136, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0526938438415527, "global_step": 532137, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0064241886138916, "global_step": 532138, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9963165521621704, "global_step": 532139, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0153024196624756, "global_step": 532140, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.027679443359375, "global_step": 532141, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.000864267349243, "global_step": 532142, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0413732528686523, "global_step": 532143, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0028557777404785, "global_step": 532144, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0872254371643066, "global_step": 532145, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9905697107315063, "global_step": 532146, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.025254011154175, "global_step": 532147, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9749926328659058, "global_step": 532148, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0871176719665527, "global_step": 532149, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.053283929824829, "global_step": 532150, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0322959423065186, "global_step": 532151, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9966859817504883, "global_step": 532152, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9849331378936768, "global_step": 532153, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1016974449157715, "global_step": 532154, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9699710607528687, "global_step": 532155, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0516138076782227, "global_step": 532156, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0695202350616455, "global_step": 532157, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0503060817718506, "global_step": 532158, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0948991775512695, "global_step": 532159, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.946481466293335, "global_step": 532160, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0985262393951416, "global_step": 532161, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0359129905700684, "global_step": 532162, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9910993576049805, "global_step": 532163, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9753376245498657, "global_step": 532164, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0241453647613525, "global_step": 532165, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0742669105529785, "global_step": 532166, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9973851442337036, "global_step": 532167, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.003290891647339, "global_step": 532168, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.048393726348877, "global_step": 532169, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.029585599899292, "global_step": 532170, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9918007850646973, "global_step": 532171, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0741336345672607, "global_step": 532172, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9957363605499268, "global_step": 532173, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0897769927978516, "global_step": 532174, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.000229597091675, "global_step": 532175, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.989971399307251, "global_step": 532176, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.955904245376587, "global_step": 532177, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.003011465072632, "global_step": 532178, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9576091766357422, "global_step": 532179, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0441300868988037, "global_step": 532180, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.091574192047119, "global_step": 532181, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0144479274749756, "global_step": 532182, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.000483751296997, "global_step": 532183, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9794864654541016, "global_step": 532184, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.037069320678711, "global_step": 532185, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0821409225463867, "global_step": 532186, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9999173879623413, "global_step": 532187, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0556890964508057, "global_step": 532188, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0729968547821045, "global_step": 532189, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0487117767333984, "global_step": 532190, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.086440324783325, "global_step": 532191, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0045835971832275, "global_step": 532192, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9752914905548096, "global_step": 532193, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1355011463165283, "global_step": 532194, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.957922339439392, "global_step": 532195, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.043222665786743, "global_step": 532196, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9911165237426758, "global_step": 532197, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.100701093673706, "global_step": 532198, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0770440101623535, "global_step": 532199, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.990860104560852, "global_step": 532200, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.00349497795105, "global_step": 532201, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0190014839172363, "global_step": 532202, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9778239727020264, "global_step": 532203, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9868906736373901, "global_step": 532204, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.009624481201172, "global_step": 532205, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0786101818084717, "global_step": 532206, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.006993532180786, "global_step": 532207, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0653936862945557, "global_step": 532208, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1205050945281982, "global_step": 532209, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.027768611907959, "global_step": 532210, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9607911109924316, "global_step": 532211, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0328054428100586, "global_step": 532212, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.038966417312622, "global_step": 532213, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.020164966583252, "global_step": 532214, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.024385690689087, "global_step": 532215, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0299997329711914, "global_step": 532216, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.010361433029175, "global_step": 532217, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.000946283340454, "global_step": 532218, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0030953884124756, "global_step": 532219, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9758734703063965, "global_step": 532220, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0166454315185547, "global_step": 532221, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1325011253356934, "global_step": 532222, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0365474224090576, "global_step": 532223, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.991818904876709, "global_step": 532224, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9564764499664307, "global_step": 532225, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0691652297973633, "global_step": 532226, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9310524463653564, "global_step": 532227, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0247347354888916, "global_step": 532228, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.008469820022583, "global_step": 532229, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0417566299438477, "global_step": 532230, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0286691188812256, "global_step": 532231, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0201759338378906, "global_step": 532232, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0990331172943115, "global_step": 532233, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0073986053466797, "global_step": 532234, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0664825439453125, "global_step": 532235, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.034156322479248, "global_step": 532236, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.028031826019287, "global_step": 532237, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0140438079833984, "global_step": 532238, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.066838264465332, "global_step": 532239, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.121711254119873, "global_step": 532240, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.032505512237549, "global_step": 532241, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0821807384490967, "global_step": 532242, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9719252586364746, "global_step": 532243, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9899543523788452, "global_step": 532244, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9656469821929932, "global_step": 532245, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.03704571723938, "global_step": 532246, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.015153646469116, "global_step": 532247, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.054978370666504, "global_step": 532248, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.000784397125244, "global_step": 532249, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.010024309158325, "global_step": 532250, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1191916465759277, "global_step": 532251, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0062272548675537, "global_step": 532252, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.138370990753174, "global_step": 532253, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.044408082962036, "global_step": 532254, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.034795045852661, "global_step": 532255, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.050943374633789, "global_step": 532256, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0131139755249023, "global_step": 532257, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.036508321762085, "global_step": 532258, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.03363299369812, "global_step": 532259, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0334372520446777, "global_step": 532260, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9759303331375122, "global_step": 532261, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0298564434051514, "global_step": 532262, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.104804754257202, "global_step": 532263, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.074154853820801, "global_step": 532264, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.003103733062744, "global_step": 532265, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9808719158172607, "global_step": 532266, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9978623390197754, "global_step": 532267, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.097587823867798, "global_step": 532268, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9513951539993286, "global_step": 532269, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9951412677764893, "global_step": 532270, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.998737096786499, "global_step": 532271, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0234878063201904, "global_step": 532272, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.070892810821533, "global_step": 532273, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0340394973754883, "global_step": 532274, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.035522699356079, "global_step": 532275, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.034848928451538, "global_step": 532276, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9708431959152222, "global_step": 532277, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.063154935836792, "global_step": 532278, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0606322288513184, "global_step": 532279, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.006624937057495, "global_step": 532280, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0813727378845215, "global_step": 532281, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9314424991607666, "global_step": 532282, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.089860439300537, "global_step": 532283, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.027139902114868, "global_step": 532284, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0301108360290527, "global_step": 532285, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0522146224975586, "global_step": 532286, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.021836996078491, "global_step": 532287, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0181031227111816, "global_step": 532288, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0759437084198, "global_step": 532289, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0214955806732178, "global_step": 532290, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0384154319763184, "global_step": 532291, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0706844329833984, "global_step": 532292, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.117806911468506, "global_step": 532293, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.07281756401062, "global_step": 532294, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9682923555374146, "global_step": 532295, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.051455020904541, "global_step": 532296, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0241103172302246, "global_step": 532297, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.000072956085205, "global_step": 532298, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1644093990325928, "global_step": 532299, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0389485359191895, "global_step": 532300, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.100468158721924, "global_step": 532301, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.017719030380249, "global_step": 532302, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0180089473724365, "global_step": 532303, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.990149974822998, "global_step": 532304, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.010101556777954, "global_step": 532305, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0117013454437256, "global_step": 532306, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0095653533935547, "global_step": 532307, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0128157138824463, "global_step": 532308, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9835829734802246, "global_step": 532309, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0352492332458496, "global_step": 532310, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9857898950576782, "global_step": 532311, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.043951988220215, "global_step": 532312, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9536643028259277, "global_step": 532313, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9490439891815186, "global_step": 532314, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0338165760040283, "global_step": 532315, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9651775360107422, "global_step": 532316, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0978310108184814, "global_step": 532317, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9485853910446167, "global_step": 532318, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9912441968917847, "global_step": 532319, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.96876060962677, "global_step": 532320, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9816609621047974, "global_step": 532321, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9875410795211792, "global_step": 532322, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0701277256011963, "global_step": 532323, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0733978748321533, "global_step": 532324, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9865144491195679, "global_step": 532325, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.134606122970581, "global_step": 532326, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.057558298110962, "global_step": 532327, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9853414297103882, "global_step": 532328, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0438883304595947, "global_step": 532329, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9841147661209106, "global_step": 532330, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.067486047744751, "global_step": 532331, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0708680152893066, "global_step": 532332, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9864503145217896, "global_step": 532333, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0106120109558105, "global_step": 532334, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0741145610809326, "global_step": 532335, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0205230712890625, "global_step": 532336, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.063784122467041, "global_step": 532337, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0363545417785645, "global_step": 532338, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.104649305343628, "global_step": 532339, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9920464754104614, "global_step": 532340, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9684557914733887, "global_step": 532341, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.040470838546753, "global_step": 532342, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.10962176322937, "global_step": 532343, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0830349922180176, "global_step": 532344, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.006373643875122, "global_step": 532345, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9921882152557373, "global_step": 532346, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0544581413269043, "global_step": 532347, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.014835834503174, "global_step": 532348, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.095461845397949, "global_step": 532349, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0617899894714355, "global_step": 532350, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.948573112487793, "global_step": 532351, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0772931575775146, "global_step": 532352, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9783464670181274, "global_step": 532353, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.07411527633667, "global_step": 532354, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0414199829101562, "global_step": 532355, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0724937915802, "global_step": 532356, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0988197326660156, "global_step": 532357, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.057656764984131, "global_step": 532358, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.034149646759033, "global_step": 532359, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0026934146881104, "global_step": 532360, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0860049724578857, "global_step": 532361, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0506527423858643, "global_step": 532362, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0231552124023438, "global_step": 532363, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9792355298995972, "global_step": 532364, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1552133560180664, "global_step": 532365, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0136027336120605, "global_step": 532366, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.05500864982605, "global_step": 532367, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0823922157287598, "global_step": 532368, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9974501132965088, "global_step": 532369, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0485939979553223, "global_step": 532370, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9662253856658936, "global_step": 532371, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.009150505065918, "global_step": 532372, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.099428415298462, "global_step": 532373, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.116779327392578, "global_step": 532374, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9971814155578613, "global_step": 532375, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9872361421585083, "global_step": 532376, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9746737480163574, "global_step": 532377, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0311505794525146, "global_step": 532378, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.082293748855591, "global_step": 532379, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0293567180633545, "global_step": 532380, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0342159271240234, "global_step": 532381, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0226895809173584, "global_step": 532382, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9621833562850952, "global_step": 532383, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0027527809143066, "global_step": 532384, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.075002431869507, "global_step": 532385, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9872113466262817, "global_step": 532386, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0684468746185303, "global_step": 532387, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.028394937515259, "global_step": 532388, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.093615770339966, "global_step": 532389, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.07029128074646, "global_step": 532390, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.052220582962036, "global_step": 532391, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.03708553314209, "global_step": 532392, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9567790031433105, "global_step": 532393, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.041260242462158, "global_step": 532394, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9801486730575562, "global_step": 532395, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.923668622970581, "global_step": 532396, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.041337728500366, "global_step": 532397, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.066530227661133, "global_step": 532398, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.999200463294983, "global_step": 532399, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0727334022521973, "global_step": 532400, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.025214195251465, "global_step": 532401, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0220916271209717, "global_step": 532402, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.138132095336914, "global_step": 532403, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9961493015289307, "global_step": 532404, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9985713958740234, "global_step": 532405, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0187363624572754, "global_step": 532406, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9680018424987793, "global_step": 532407, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0853278636932373, "global_step": 532408, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9656628370285034, "global_step": 532409, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9999089241027832, "global_step": 532410, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9774937629699707, "global_step": 532411, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0772881507873535, "global_step": 532412, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0302932262420654, "global_step": 532413, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0574791431427, "global_step": 532414, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0820977687835693, "global_step": 532415, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0252861976623535, "global_step": 532416, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1017568111419678, "global_step": 532417, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.913720726966858, "global_step": 532418, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.041560649871826, "global_step": 532419, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0366787910461426, "global_step": 532420, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0085794925689697, "global_step": 532421, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0754342079162598, "global_step": 532422, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.043945550918579, "global_step": 532423, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.026038885116577, "global_step": 532424, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9863320589065552, "global_step": 532425, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.049333095550537, "global_step": 532426, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.039161443710327, "global_step": 532427, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.091494083404541, "global_step": 532428, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.06577730178833, "global_step": 532429, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0223488807678223, "global_step": 532430, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.03165340423584, "global_step": 532431, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1307661533355713, "global_step": 532432, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0915415287017822, "global_step": 532433, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.063974618911743, "global_step": 532434, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9768168926239014, "global_step": 532435, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.079720973968506, "global_step": 532436, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1252529621124268, "global_step": 532437, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.055492877960205, "global_step": 532438, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9819307327270508, "global_step": 532439, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9303539991378784, "global_step": 532440, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.149138927459717, "global_step": 532441, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.028754711151123, "global_step": 532442, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0250842571258545, "global_step": 532443, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0052618980407715, "global_step": 532444, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9793068170547485, "global_step": 532445, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1556599140167236, "global_step": 532446, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0320277214050293, "global_step": 532447, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.088672399520874, "global_step": 532448, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.085726737976074, "global_step": 532449, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.061849355697632, "global_step": 532450, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0428121089935303, "global_step": 532451, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.050272226333618, "global_step": 532452, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.024174451828003, "global_step": 532453, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1327574253082275, "global_step": 532454, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.071274995803833, "global_step": 532455, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0470645427703857, "global_step": 532456, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9673374891281128, "global_step": 532457, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.051970958709717, "global_step": 532458, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0572028160095215, "global_step": 532459, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0286238193511963, "global_step": 532460, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.076005220413208, "global_step": 532461, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.088040590286255, "global_step": 532462, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0168826580047607, "global_step": 532463, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0996286869049072, "global_step": 532464, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.110001564025879, "global_step": 532465, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.073941707611084, "global_step": 532466, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9414010047912598, "global_step": 532467, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0320465564727783, "global_step": 532468, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9934810400009155, "global_step": 532469, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1739501953125, "global_step": 532470, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9871985912322998, "global_step": 532471, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9608445167541504, "global_step": 532472, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.011246919631958, "global_step": 532473, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0673115253448486, "global_step": 532474, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.983535647392273, "global_step": 532475, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0373497009277344, "global_step": 532476, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.005845785140991, "global_step": 532477, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1265997886657715, "global_step": 532478, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0833802223205566, "global_step": 532479, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1044559478759766, "global_step": 532480, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.116126775741577, "global_step": 532481, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.036292314529419, "global_step": 532482, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.007951498031616, "global_step": 532483, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0867362022399902, "global_step": 532484, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0188236236572266, "global_step": 532485, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.037888288497925, "global_step": 532486, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0625507831573486, "global_step": 532487, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9933923482894897, "global_step": 532488, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0185937881469727, "global_step": 532489, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9204307794570923, "global_step": 532490, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.028010129928589, "global_step": 532491, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0946335792541504, "global_step": 532492, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.046588897705078, "global_step": 532493, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0343003273010254, "global_step": 532494, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1195380687713623, "global_step": 532495, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.023364543914795, "global_step": 532496, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.052701711654663, "global_step": 532497, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0273396968841553, "global_step": 532498, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0784571170806885, "global_step": 532499, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.099663496017456, "global_step": 532500, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.024791955947876, "global_step": 532501, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9922493696212769, "global_step": 532502, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.116910696029663, "global_step": 532503, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.032883644104004, "global_step": 532504, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0372087955474854, "global_step": 532505, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0514092445373535, "global_step": 532506, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0288572311401367, "global_step": 532507, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.120596170425415, "global_step": 532508, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0334837436676025, "global_step": 532509, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.092250347137451, "global_step": 532510, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0252933502197266, "global_step": 532511, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0431160926818848, "global_step": 532512, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1268515586853027, "global_step": 532513, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0296173095703125, "global_step": 532514, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.039433717727661, "global_step": 532515, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1032984256744385, "global_step": 532516, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0609097480773926, "global_step": 532517, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.045527458190918, "global_step": 532518, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9771798849105835, "global_step": 532519, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1009769439697266, "global_step": 532520, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.025330066680908, "global_step": 532521, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0359833240509033, "global_step": 532522, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1824123859405518, "global_step": 532523, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.990593671798706, "global_step": 532524, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.048206329345703, "global_step": 532525, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0415380001068115, "global_step": 532526, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0406486988067627, "global_step": 532527, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.043567657470703, "global_step": 532528, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.980621337890625, "global_step": 532529, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9815818071365356, "global_step": 532530, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9972782135009766, "global_step": 532531, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9809681177139282, "global_step": 532532, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.139219284057617, "global_step": 532533, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.108250856399536, "global_step": 532534, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.098076343536377, "global_step": 532535, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9884982109069824, "global_step": 532536, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.02303147315979, "global_step": 532537, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.05338191986084, "global_step": 532538, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0347280502319336, "global_step": 532539, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9968928098678589, "global_step": 532540, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9587795734405518, "global_step": 532541, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.085610866546631, "global_step": 532542, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0335347652435303, "global_step": 532543, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9818315505981445, "global_step": 532544, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.058946132659912, "global_step": 532545, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.038149833679199, "global_step": 532546, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.013584852218628, "global_step": 532547, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.015369176864624, "global_step": 532548, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.930586814880371, "global_step": 532549, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0042381286621094, "global_step": 532550, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9555128812789917, "global_step": 532551, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.094879627227783, "global_step": 532552, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.096461296081543, "global_step": 532553, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.052313804626465, "global_step": 532554, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.969938039779663, "global_step": 532555, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9898557662963867, "global_step": 532556, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.026853084564209, "global_step": 532557, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.025869131088257, "global_step": 532558, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9521948099136353, "global_step": 532559, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0946850776672363, "global_step": 532560, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0966598987579346, "global_step": 532561, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0563693046569824, "global_step": 532562, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0587515830993652, "global_step": 532563, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.003798246383667, "global_step": 532564, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.002877712249756, "global_step": 532565, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1019787788391113, "global_step": 532566, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0554864406585693, "global_step": 532567, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.021632671356201, "global_step": 532568, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0307352542877197, "global_step": 532569, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.086501121520996, "global_step": 532570, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9866266250610352, "global_step": 532571, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0826306343078613, "global_step": 532572, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.094302177429199, "global_step": 532573, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0010359287261963, "global_step": 532574, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.98581862449646, "global_step": 532575, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0603063106536865, "global_step": 532576, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0043721199035645, "global_step": 532577, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0208117961883545, "global_step": 532578, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.024806499481201, "global_step": 532579, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9792877435684204, "global_step": 532580, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.100687265396118, "global_step": 532581, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1207025051116943, "global_step": 532582, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.021467924118042, "global_step": 532583, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.991250991821289, "global_step": 532584, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0186729431152344, "global_step": 532585, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.038620710372925, "global_step": 532586, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9972524642944336, "global_step": 532587, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1075878143310547, "global_step": 532588, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.12581467628479, "global_step": 532589, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.940553903579712, "global_step": 532590, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0508687496185303, "global_step": 532591, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9718639850616455, "global_step": 532592, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0441226959228516, "global_step": 532593, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9780645370483398, "global_step": 532594, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0574636459350586, "global_step": 532595, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.03132963180542, "global_step": 532596, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.025735855102539, "global_step": 532597, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0293145179748535, "global_step": 532598, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.111682415008545, "global_step": 532599, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.025054693222046, "global_step": 532600, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.127399206161499, "global_step": 532601, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0671794414520264, "global_step": 532602, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1271133422851562, "global_step": 532603, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9710103273391724, "global_step": 532604, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.066970109939575, "global_step": 532605, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0676944255828857, "global_step": 532606, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9105406999588013, "global_step": 532607, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0488405227661133, "global_step": 532608, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1668741703033447, "global_step": 532609, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0245792865753174, "global_step": 532610, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9571272134780884, "global_step": 532611, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0666143894195557, "global_step": 532612, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.033139705657959, "global_step": 532613, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0001559257507324, "global_step": 532614, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0686838626861572, "global_step": 532615, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9800550937652588, "global_step": 532616, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0001773834228516, "global_step": 532617, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0323641300201416, "global_step": 532618, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.108315944671631, "global_step": 532619, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.063190460205078, "global_step": 532620, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9957212209701538, "global_step": 532621, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9858413934707642, "global_step": 532622, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.017111301422119, "global_step": 532623, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0986812114715576, "global_step": 532624, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.020937919616699, "global_step": 532625, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0997650623321533, "global_step": 532626, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9677101373672485, "global_step": 532627, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.009255886077881, "global_step": 532628, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9993630647659302, "global_step": 532629, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.01351261138916, "global_step": 532630, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.997842788696289, "global_step": 532631, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.019534111022949, "global_step": 532632, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1294705867767334, "global_step": 532633, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0192556381225586, "global_step": 532634, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.097961187362671, "global_step": 532635, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9968801736831665, "global_step": 532636, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.070458173751831, "global_step": 532637, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.007556676864624, "global_step": 532638, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0415408611297607, "global_step": 532639, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.017864227294922, "global_step": 532640, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0661628246307373, "global_step": 532641, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.037846088409424, "global_step": 532642, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0074374675750732, "global_step": 532643, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0656542778015137, "global_step": 532644, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.041105270385742, "global_step": 532645, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9995871782302856, "global_step": 532646, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.029698133468628, "global_step": 532647, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.04192852973938, "global_step": 532648, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.053670644760132, "global_step": 532649, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0127789974212646, "global_step": 532650, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0832958221435547, "global_step": 532651, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0774574279785156, "global_step": 532652, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9686472415924072, "global_step": 532653, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9830570220947266, "global_step": 532654, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.134148597717285, "global_step": 532655, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0788464546203613, "global_step": 532656, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0792617797851562, "global_step": 532657, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0429935455322266, "global_step": 532658, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9862793684005737, "global_step": 532659, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9308524131774902, "global_step": 532660, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.071352958679199, "global_step": 532661, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0717291831970215, "global_step": 532662, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.986976146697998, "global_step": 532663, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9810729026794434, "global_step": 532664, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0530824661254883, "global_step": 532665, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.027824640274048, "global_step": 532666, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9878002405166626, "global_step": 532667, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0549402236938477, "global_step": 532668, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0728206634521484, "global_step": 532669, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9756006002426147, "global_step": 532670, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0389277935028076, "global_step": 532671, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0514943599700928, "global_step": 532672, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.987236499786377, "global_step": 532673, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.04906964302063, "global_step": 532674, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1721689701080322, "global_step": 532675, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0362539291381836, "global_step": 532676, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.057676315307617, "global_step": 532677, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0276851654052734, "global_step": 532678, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.098916530609131, "global_step": 532679, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.018925189971924, "global_step": 532680, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.024853229522705, "global_step": 532681, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.036083698272705, "global_step": 532682, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1051313877105713, "global_step": 532683, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.128836154937744, "global_step": 532684, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0621306896209717, "global_step": 532685, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0273866653442383, "global_step": 532686, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1108710765838623, "global_step": 532687, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0723536014556885, "global_step": 532688, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0417749881744385, "global_step": 532689, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.012892246246338, "global_step": 532690, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0474369525909424, "global_step": 532691, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0394184589385986, "global_step": 532692, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.098656177520752, "global_step": 532693, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0687780380249023, "global_step": 532694, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.032470226287842, "global_step": 532695, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9605036973953247, "global_step": 532696, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0224132537841797, "global_step": 532697, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.092264413833618, "global_step": 532698, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.041320323944092, "global_step": 532699, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0725300312042236, "global_step": 532700, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0249738693237305, "global_step": 532701, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0286974906921387, "global_step": 532702, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1501100063323975, "global_step": 532703, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.990728735923767, "global_step": 532704, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9991053342819214, "global_step": 532705, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0314245223999023, "global_step": 532706, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1289753913879395, "global_step": 532707, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0360093116760254, "global_step": 532708, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.982672095298767, "global_step": 532709, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.949960708618164, "global_step": 532710, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1134066581726074, "global_step": 532711, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0185232162475586, "global_step": 532712, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0187644958496094, "global_step": 532713, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0891075134277344, "global_step": 532714, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0158965587615967, "global_step": 532715, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.042269229888916, "global_step": 532716, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.041987419128418, "global_step": 532717, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.055690050125122, "global_step": 532718, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.952907919883728, "global_step": 532719, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.007551670074463, "global_step": 532720, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1601929664611816, "global_step": 532721, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.035672187805176, "global_step": 532722, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0056684017181396, "global_step": 532723, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0902767181396484, "global_step": 532724, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1776201725006104, "global_step": 532725, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.082857370376587, "global_step": 532726, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0899252891540527, "global_step": 532727, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.034121036529541, "global_step": 532728, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0270144939422607, "global_step": 532729, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.986133098602295, "global_step": 532730, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0147767066955566, "global_step": 532731, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0935471057891846, "global_step": 532732, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0661027431488037, "global_step": 532733, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9678966999053955, "global_step": 532734, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.041412591934204, "global_step": 532735, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0123021602630615, "global_step": 532736, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0389866828918457, "global_step": 532737, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0763020515441895, "global_step": 532738, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.082332134246826, "global_step": 532739, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.020326614379883, "global_step": 532740, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.968164086341858, "global_step": 532741, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.97443425655365, "global_step": 532742, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0196430683135986, "global_step": 532743, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0500948429107666, "global_step": 532744, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0635478496551514, "global_step": 532745, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.054612398147583, "global_step": 532746, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.043355941772461, "global_step": 532747, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.071718215942383, "global_step": 532748, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9581258296966553, "global_step": 532749, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0449256896972656, "global_step": 532750, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9616445302963257, "global_step": 532751, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0199532508850098, "global_step": 532752, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.095189332962036, "global_step": 532753, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.097445011138916, "global_step": 532754, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1164910793304443, "global_step": 532755, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0548911094665527, "global_step": 532756, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.063324213027954, "global_step": 532757, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0407960414886475, "global_step": 532758, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0596210956573486, "global_step": 532759, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.029280662536621, "global_step": 532760, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.060765504837036, "global_step": 532761, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0110785961151123, "global_step": 532762, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.066375255584717, "global_step": 532763, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0055665969848633, "global_step": 532764, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0932822227478027, "global_step": 532765, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9652142524719238, "global_step": 532766, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0699949264526367, "global_step": 532767, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0500288009643555, "global_step": 532768, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.019798994064331, "global_step": 532769, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0629019737243652, "global_step": 532770, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.005448341369629, "global_step": 532771, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0149240493774414, "global_step": 532772, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.012235164642334, "global_step": 532773, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0495681762695312, "global_step": 532774, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0386219024658203, "global_step": 532775, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.071197986602783, "global_step": 532776, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0221261978149414, "global_step": 532777, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.034820079803467, "global_step": 532778, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.089031219482422, "global_step": 532779, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0193119049072266, "global_step": 532780, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.015838384628296, "global_step": 532781, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0935041904449463, "global_step": 532782, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0500648021698, "global_step": 532783, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0632176399230957, "global_step": 532784, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0332350730895996, "global_step": 532785, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0258445739746094, "global_step": 532786, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0668046474456787, "global_step": 532787, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.151715040206909, "global_step": 532788, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1140096187591553, "global_step": 532789, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.017899513244629, "global_step": 532790, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0083706378936768, "global_step": 532791, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0473294258117676, "global_step": 532792, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.026648759841919, "global_step": 532793, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0567424297332764, "global_step": 532794, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9554829597473145, "global_step": 532795, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9411550760269165, "global_step": 532796, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0454049110412598, "global_step": 532797, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0249826908111572, "global_step": 532798, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0630340576171875, "global_step": 532799, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0600697994232178, "global_step": 532800, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.04606556892395, "global_step": 532801, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9535781145095825, "global_step": 532802, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.012896776199341, "global_step": 532803, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.062645673751831, "global_step": 532804, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0631966590881348, "global_step": 532805, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.943058729171753, "global_step": 532806, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0211386680603027, "global_step": 532807, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.024334192276001, "global_step": 532808, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9509998559951782, "global_step": 532809, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.078481912612915, "global_step": 532810, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9863333702087402, "global_step": 532811, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0017294883728027, "global_step": 532812, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0458950996398926, "global_step": 532813, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.021822214126587, "global_step": 532814, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0967941284179688, "global_step": 532815, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0904364585876465, "global_step": 532816, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0157206058502197, "global_step": 532817, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.100672721862793, "global_step": 532818, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9422433376312256, "global_step": 532819, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.988089919090271, "global_step": 532820, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.027641773223877, "global_step": 532821, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0432662963867188, "global_step": 532822, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0644805431365967, "global_step": 532823, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.039778709411621, "global_step": 532824, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0699312686920166, "global_step": 532825, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0115573406219482, "global_step": 532826, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.066922426223755, "global_step": 532827, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1171114444732666, "global_step": 532828, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0888521671295166, "global_step": 532829, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.025752305984497, "global_step": 532830, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0264763832092285, "global_step": 532831, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.991178035736084, "global_step": 532832, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.053959846496582, "global_step": 532833, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0157012939453125, "global_step": 532834, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0068085193634033, "global_step": 532835, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0687496662139893, "global_step": 532836, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.102947473526001, "global_step": 532837, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0798258781433105, "global_step": 532838, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.112238645553589, "global_step": 532839, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.117616653442383, "global_step": 532840, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.032104253768921, "global_step": 532841, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0195045471191406, "global_step": 532842, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0933878421783447, "global_step": 532843, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1200263500213623, "global_step": 532844, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.049055337905884, "global_step": 532845, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.007002115249634, "global_step": 532846, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.148388385772705, "global_step": 532847, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0340824127197266, "global_step": 532848, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1370537281036377, "global_step": 532849, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0746524333953857, "global_step": 532850, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.163029909133911, "global_step": 532851, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.038797616958618, "global_step": 532852, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.025953531265259, "global_step": 532853, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1590819358825684, "global_step": 532854, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9936333894729614, "global_step": 532855, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.059318780899048, "global_step": 532856, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1282765865325928, "global_step": 532857, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0695831775665283, "global_step": 532858, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0024704933166504, "global_step": 532859, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.996212363243103, "global_step": 532860, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0311477184295654, "global_step": 532861, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0411698818206787, "global_step": 532862, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0259695053100586, "global_step": 532863, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.033291816711426, "global_step": 532864, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9596831798553467, "global_step": 532865, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.054154396057129, "global_step": 532866, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0562052726745605, "global_step": 532867, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0056543350219727, "global_step": 532868, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.073793411254883, "global_step": 532869, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0035274028778076, "global_step": 532870, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0322346687316895, "global_step": 532871, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9647290706634521, "global_step": 532872, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0687074661254883, "global_step": 532873, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.035240888595581, "global_step": 532874, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0600407123565674, "global_step": 532875, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0058112144470215, "global_step": 532876, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0284061431884766, "global_step": 532877, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.035426616668701, "global_step": 532878, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.06715989112854, "global_step": 532879, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.079098701477051, "global_step": 532880, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9965341091156006, "global_step": 532881, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.039018154144287, "global_step": 532882, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0167791843414307, "global_step": 532883, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0115911960601807, "global_step": 532884, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0574376583099365, "global_step": 532885, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9689971208572388, "global_step": 532886, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.032329797744751, "global_step": 532887, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0557894706726074, "global_step": 532888, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.992119550704956, "global_step": 532889, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0557620525360107, "global_step": 532890, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.076195240020752, "global_step": 532891, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9370990991592407, "global_step": 532892, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1949470043182373, "global_step": 532893, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.044337749481201, "global_step": 532894, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0479328632354736, "global_step": 532895, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0444095134735107, "global_step": 532896, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0550007820129395, "global_step": 532897, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9702705144882202, "global_step": 532898, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.003267288208008, "global_step": 532899, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0653488636016846, "global_step": 532900, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0060842037200928, "global_step": 532901, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.040544271469116, "global_step": 532902, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0426313877105713, "global_step": 532903, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.032102108001709, "global_step": 532904, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0801000595092773, "global_step": 532905, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1197097301483154, "global_step": 532906, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1092662811279297, "global_step": 532907, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1072611808776855, "global_step": 532908, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.94239342212677, "global_step": 532909, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.089301109313965, "global_step": 532910, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.034146308898926, "global_step": 532911, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.133146047592163, "global_step": 532912, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0278055667877197, "global_step": 532913, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0082337856292725, "global_step": 532914, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.129451036453247, "global_step": 532915, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0808939933776855, "global_step": 532916, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.076766014099121, "global_step": 532917, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.027423620223999, "global_step": 532918, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0626144409179688, "global_step": 532919, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.061678171157837, "global_step": 532920, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1087703704833984, "global_step": 532921, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0184519290924072, "global_step": 532922, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.010180950164795, "global_step": 532923, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0095534324645996, "global_step": 532924, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0127975940704346, "global_step": 532925, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0215611457824707, "global_step": 532926, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9927974939346313, "global_step": 532927, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0948448181152344, "global_step": 532928, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.979217529296875, "global_step": 532929, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.939435601234436, "global_step": 532930, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.027803897857666, "global_step": 532931, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9388868808746338, "global_step": 532932, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0167717933654785, "global_step": 532933, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9981611967086792, "global_step": 532934, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0120866298675537, "global_step": 532935, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0769057273864746, "global_step": 532936, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0656983852386475, "global_step": 532937, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9799937009811401, "global_step": 532938, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9998993873596191, "global_step": 532939, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9954732656478882, "global_step": 532940, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.045379161834717, "global_step": 532941, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1028921604156494, "global_step": 532942, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0354273319244385, "global_step": 532943, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.131247043609619, "global_step": 532944, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.05161190032959, "global_step": 532945, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.034282922744751, "global_step": 532946, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.117100715637207, "global_step": 532947, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0955326557159424, "global_step": 532948, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.001187324523926, "global_step": 532949, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.970826268196106, "global_step": 532950, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0796804428100586, "global_step": 532951, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0606765747070312, "global_step": 532952, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9868392944335938, "global_step": 532953, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0183515548706055, "global_step": 532954, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0678670406341553, "global_step": 532955, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9998080730438232, "global_step": 532956, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.021430253982544, "global_step": 532957, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.097831964492798, "global_step": 532958, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.106487989425659, "global_step": 532959, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.051037311553955, "global_step": 532960, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9912943840026855, "global_step": 532961, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0476841926574707, "global_step": 532962, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.053480863571167, "global_step": 532963, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.059645891189575, "global_step": 532964, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0510876178741455, "global_step": 532965, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0837225914001465, "global_step": 532966, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.085233449935913, "global_step": 532967, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0210134983062744, "global_step": 532968, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0067334175109863, "global_step": 532969, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.088102102279663, "global_step": 532970, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0153777599334717, "global_step": 532971, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0669198036193848, "global_step": 532972, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0635828971862793, "global_step": 532973, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1118526458740234, "global_step": 532974, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9813772439956665, "global_step": 532975, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.072721004486084, "global_step": 532976, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0324528217315674, "global_step": 532977, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0251224040985107, "global_step": 532978, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0693867206573486, "global_step": 532979, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9634968042373657, "global_step": 532980, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0148417949676514, "global_step": 532981, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9004496335983276, "global_step": 532982, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9554246664047241, "global_step": 532983, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9704898595809937, "global_step": 532984, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0035581588745117, "global_step": 532985, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9957125186920166, "global_step": 532986, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0301482677459717, "global_step": 532987, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.069127082824707, "global_step": 532988, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.046220541000366, "global_step": 532989, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0434396266937256, "global_step": 532990, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0726215839385986, "global_step": 532991, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.045611619949341, "global_step": 532992, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.095648765563965, "global_step": 532993, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0435261726379395, "global_step": 532994, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.130628824234009, "global_step": 532995, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0110745429992676, "global_step": 532996, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9563686847686768, "global_step": 532997, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9682695865631104, "global_step": 532998, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.063861131668091, "global_step": 532999, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0353245735168457, "global_step": 533000, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0565524101257324, "global_step": 533001, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.039285659790039, "global_step": 533002, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9541513919830322, "global_step": 533003, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9702248573303223, "global_step": 533004, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0386672019958496, "global_step": 533005, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0659689903259277, "global_step": 533006, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.028351068496704, "global_step": 533007, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0277554988861084, "global_step": 533008, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.078113555908203, "global_step": 533009, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.04345965385437, "global_step": 533010, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.074309825897217, "global_step": 533011, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.020256280899048, "global_step": 533012, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0429718494415283, "global_step": 533013, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1525840759277344, "global_step": 533014, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.083695411682129, "global_step": 533015, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9853867292404175, "global_step": 533016, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0682930946350098, "global_step": 533017, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0323593616485596, "global_step": 533018, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.021953821182251, "global_step": 533019, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.018608808517456, "global_step": 533020, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9947398900985718, "global_step": 533021, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.062126636505127, "global_step": 533022, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9999403953552246, "global_step": 533023, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.042222499847412, "global_step": 533024, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0545694828033447, "global_step": 533025, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9774646759033203, "global_step": 533026, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.067355155944824, "global_step": 533027, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.00181245803833, "global_step": 533028, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0340864658355713, "global_step": 533029, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0228216648101807, "global_step": 533030, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0602409839630127, "global_step": 533031, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0571775436401367, "global_step": 533032, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1029484272003174, "global_step": 533033, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0028176307678223, "global_step": 533034, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.051759719848633, "global_step": 533035, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.968321681022644, "global_step": 533036, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0292985439300537, "global_step": 533037, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.102924346923828, "global_step": 533038, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.123709201812744, "global_step": 533039, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.067793846130371, "global_step": 533040, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0617027282714844, "global_step": 533041, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.013521432876587, "global_step": 533042, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.984357237815857, "global_step": 533043, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.088958263397217, "global_step": 533044, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.024432420730591, "global_step": 533045, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0356924533843994, "global_step": 533046, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9733411073684692, "global_step": 533047, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9741854667663574, "global_step": 533048, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0506203174591064, "global_step": 533049, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.069936990737915, "global_step": 533050, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.070631980895996, "global_step": 533051, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.032949686050415, "global_step": 533052, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.1707749366760254, "global_step": 533053, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0911452770233154, "global_step": 533054, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.027479410171509, "global_step": 533055, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.045595407485962, "global_step": 533056, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.035893201828003, "global_step": 533057, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0104763507843018, "global_step": 533058, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9902721643447876, "global_step": 533059, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0487191677093506, "global_step": 533060, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0763397216796875, "global_step": 533061, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0109922885894775, "global_step": 533062, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.067084789276123, "global_step": 533063, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0479705333709717, "global_step": 533064, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.005775213241577, "global_step": 533065, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0626325607299805, "global_step": 533066, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.049359083175659, "global_step": 533067, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0270047187805176, "global_step": 533068, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0447802543640137, "global_step": 533069, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.150135040283203, "global_step": 533070, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.046684503555298, "global_step": 533071, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0195226669311523, "global_step": 533072, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.073737144470215, "global_step": 533073, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.06078839302063, "global_step": 533074, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0482747554779053, "global_step": 533075, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0493807792663574, "global_step": 533076, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0619471073150635, "global_step": 533077, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0775701999664307, "global_step": 533078, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.02667236328125, "global_step": 533079, "epoch": 899, "lr": 5e-05}
{"train_loss": 1.9590847492218018, "global_step": 533080, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0903687477111816, "global_step": 533081, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.0376603603363037, "global_step": 533082, "epoch": 899, "lr": 5e-05}
{"train_loss": 2.044346332550049, "global_step": 533083, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1090190410614014, "global_step": 533084, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.066664934158325, "global_step": 533085, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0638270378112793, "global_step": 533086, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.072721242904663, "global_step": 533087, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.027477502822876, "global_step": 533088, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9690607786178589, "global_step": 533089, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.030937910079956, "global_step": 533090, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9878531694412231, "global_step": 533091, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.052492141723633, "global_step": 533092, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9566839933395386, "global_step": 533093, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.053619384765625, "global_step": 533094, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.995722770690918, "global_step": 533095, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.06046986579895, "global_step": 533096, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0486934185028076, "global_step": 533097, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.966829538345337, "global_step": 533098, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.103771924972534, "global_step": 533099, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9728440046310425, "global_step": 533100, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0719504356384277, "global_step": 533101, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9729481935501099, "global_step": 533102, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.067798614501953, "global_step": 533103, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0016980171203613, "global_step": 533104, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.041417121887207, "global_step": 533105, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.014305830001831, "global_step": 533106, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0545012950897217, "global_step": 533107, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.095355749130249, "global_step": 533108, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9432716369628906, "global_step": 533109, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9745627641677856, "global_step": 533110, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.064955234527588, "global_step": 533111, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.000047206878662, "global_step": 533112, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.025939702987671, "global_step": 533113, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1372523307800293, "global_step": 533114, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.997540831565857, "global_step": 533115, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9699082374572754, "global_step": 533116, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.97147798538208, "global_step": 533117, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.989295244216919, "global_step": 533118, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.046011447906494, "global_step": 533119, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9503839015960693, "global_step": 533120, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0840470790863037, "global_step": 533121, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0611047744750977, "global_step": 533122, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9824788570404053, "global_step": 533123, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.8831467628479004, "global_step": 533124, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0516083240509033, "global_step": 533125, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.02528977394104, "global_step": 533126, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0255613327026367, "global_step": 533127, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9448717832565308, "global_step": 533128, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0427582263946533, "global_step": 533129, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.093568801879883, "global_step": 533130, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9821299314498901, "global_step": 533131, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9937515258789062, "global_step": 533132, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9655803442001343, "global_step": 533133, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1077117919921875, "global_step": 533134, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9968936443328857, "global_step": 533135, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.030390501022339, "global_step": 533136, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.111443519592285, "global_step": 533137, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9823973178863525, "global_step": 533138, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0206258296966553, "global_step": 533139, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.006612539291382, "global_step": 533140, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.082411050796509, "global_step": 533141, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.056546688079834, "global_step": 533142, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9624333381652832, "global_step": 533143, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0813560485839844, "global_step": 533144, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.043107748031616, "global_step": 533145, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9934024810791016, "global_step": 533146, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0158324241638184, "global_step": 533147, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.947913408279419, "global_step": 533148, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0892558097839355, "global_step": 533149, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0535829067230225, "global_step": 533150, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.033398151397705, "global_step": 533151, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1097843647003174, "global_step": 533152, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9729984998703003, "global_step": 533153, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0356109142303467, "global_step": 533154, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9563992023468018, "global_step": 533155, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.936089277267456, "global_step": 533156, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.028947114944458, "global_step": 533157, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.091311454772949, "global_step": 533158, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.005068063735962, "global_step": 533159, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0194191932678223, "global_step": 533160, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0621962547302246, "global_step": 533161, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0719780921936035, "global_step": 533162, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.988188624382019, "global_step": 533163, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0205273628234863, "global_step": 533164, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0078723430633545, "global_step": 533165, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0102269649505615, "global_step": 533166, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0026302337646484, "global_step": 533167, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.041592836380005, "global_step": 533168, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0724363327026367, "global_step": 533169, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.050525188446045, "global_step": 533170, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9869874715805054, "global_step": 533171, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9940372705459595, "global_step": 533172, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9632312059402466, "global_step": 533173, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0734500885009766, "global_step": 533174, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9602880477905273, "global_step": 533175, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.094304323196411, "global_step": 533176, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0303432941436768, "global_step": 533177, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0709190368652344, "global_step": 533178, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9238409996032715, "global_step": 533179, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0394554138183594, "global_step": 533180, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.08760142326355, "global_step": 533181, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9607644081115723, "global_step": 533182, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9818172454833984, "global_step": 533183, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1295058727264404, "global_step": 533184, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0428247451782227, "global_step": 533185, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.016702175140381, "global_step": 533186, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9875671863555908, "global_step": 533187, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.035227060317993, "global_step": 533188, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9530725479125977, "global_step": 533189, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.073927164077759, "global_step": 533190, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.086277723312378, "global_step": 533191, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0887389183044434, "global_step": 533192, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0159034729003906, "global_step": 533193, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0572776794433594, "global_step": 533194, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.095795154571533, "global_step": 533195, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.083418369293213, "global_step": 533196, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0710325241088867, "global_step": 533197, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0159823894500732, "global_step": 533198, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0651612281799316, "global_step": 533199, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0848777294158936, "global_step": 533200, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0263683795928955, "global_step": 533201, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9629143476486206, "global_step": 533202, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0438244342803955, "global_step": 533203, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0478012561798096, "global_step": 533204, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.029956817626953, "global_step": 533205, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9213857650756836, "global_step": 533206, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9538793563842773, "global_step": 533207, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.061746835708618, "global_step": 533208, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.016815662384033, "global_step": 533209, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9873793125152588, "global_step": 533210, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0255961418151855, "global_step": 533211, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0597593784332275, "global_step": 533212, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0540196895599365, "global_step": 533213, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9543529748916626, "global_step": 533214, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.068718433380127, "global_step": 533215, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.015211582183838, "global_step": 533216, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0137903690338135, "global_step": 533217, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1203536987304688, "global_step": 533218, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0616016387939453, "global_step": 533219, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9849070310592651, "global_step": 533220, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.034900665283203, "global_step": 533221, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0786964893341064, "global_step": 533222, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1032814979553223, "global_step": 533223, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.00042724609375, "global_step": 533224, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0297021865844727, "global_step": 533225, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0120012760162354, "global_step": 533226, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.072009801864624, "global_step": 533227, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0397698879241943, "global_step": 533228, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.966477870941162, "global_step": 533229, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0341708660125732, "global_step": 533230, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0706615447998047, "global_step": 533231, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.095271587371826, "global_step": 533232, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0450997352600098, "global_step": 533233, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1053779125213623, "global_step": 533234, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0131466388702393, "global_step": 533235, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0217158794403076, "global_step": 533236, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.050229787826538, "global_step": 533237, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.068098306655884, "global_step": 533238, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0492868423461914, "global_step": 533239, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0131051540374756, "global_step": 533240, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.021857976913452, "global_step": 533241, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.015676736831665, "global_step": 533242, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.033971071243286, "global_step": 533243, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0602002143859863, "global_step": 533244, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9989454746246338, "global_step": 533245, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9258581399917603, "global_step": 533246, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.036243438720703, "global_step": 533247, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9845340251922607, "global_step": 533248, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9716624021530151, "global_step": 533249, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1236748695373535, "global_step": 533250, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1118626594543457, "global_step": 533251, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.068598985671997, "global_step": 533252, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9967137575149536, "global_step": 533253, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0640761852264404, "global_step": 533254, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0050134658813477, "global_step": 533255, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0628139972686768, "global_step": 533256, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0741331577301025, "global_step": 533257, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.035717010498047, "global_step": 533258, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0141801834106445, "global_step": 533259, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0077173709869385, "global_step": 533260, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.999813437461853, "global_step": 533261, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0181937217712402, "global_step": 533262, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0924813747406006, "global_step": 533263, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9929134845733643, "global_step": 533264, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.097151517868042, "global_step": 533265, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9649821519851685, "global_step": 533266, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.084139108657837, "global_step": 533267, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0605578422546387, "global_step": 533268, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.034198522567749, "global_step": 533269, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.074653148651123, "global_step": 533270, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.023721694946289, "global_step": 533271, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0332565307617188, "global_step": 533272, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9345676898956299, "global_step": 533273, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9964039325714111, "global_step": 533274, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.008692979812622, "global_step": 533275, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0106256008148193, "global_step": 533276, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.085057497024536, "global_step": 533277, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0279886722564697, "global_step": 533278, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.8875795602798462, "global_step": 533279, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.03544282913208, "global_step": 533280, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.025563955307007, "global_step": 533281, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0266685485839844, "global_step": 533282, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.148864507675171, "global_step": 533283, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.029567241668701, "global_step": 533284, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0037193298339844, "global_step": 533285, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0290818214416504, "global_step": 533286, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0970613956451416, "global_step": 533287, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.044835329055786, "global_step": 533288, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0654025077819824, "global_step": 533289, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0363504886627197, "global_step": 533290, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0132224559783936, "global_step": 533291, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0450735092163086, "global_step": 533292, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0127007961273193, "global_step": 533293, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9742153882980347, "global_step": 533294, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.000180721282959, "global_step": 533295, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1047143936157227, "global_step": 533296, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0541234016418457, "global_step": 533297, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0818774700164795, "global_step": 533298, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.003302574157715, "global_step": 533299, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0521771907806396, "global_step": 533300, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.090723991394043, "global_step": 533301, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9610048532485962, "global_step": 533302, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0511813163757324, "global_step": 533303, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.941490650177002, "global_step": 533304, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.031851291656494, "global_step": 533305, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.04960560798645, "global_step": 533306, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1025729179382324, "global_step": 533307, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9887233972549438, "global_step": 533308, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0150694847106934, "global_step": 533309, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0337579250335693, "global_step": 533310, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0404469966888428, "global_step": 533311, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0316295623779297, "global_step": 533312, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0062320232391357, "global_step": 533313, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0220000743865967, "global_step": 533314, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.026323080062866, "global_step": 533315, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.006606101989746, "global_step": 533316, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0136070251464844, "global_step": 533317, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0199077129364014, "global_step": 533318, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9745368957519531, "global_step": 533319, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.138420343399048, "global_step": 533320, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9953306913375854, "global_step": 533321, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0525333881378174, "global_step": 533322, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.055091619491577, "global_step": 533323, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0977485179901123, "global_step": 533324, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0417985916137695, "global_step": 533325, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9353203773498535, "global_step": 533326, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.037078619003296, "global_step": 533327, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0358076095581055, "global_step": 533328, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0077810287475586, "global_step": 533329, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.06205153465271, "global_step": 533330, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.024538278579712, "global_step": 533331, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0387072563171387, "global_step": 533332, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.049420118331909, "global_step": 533333, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9843029975891113, "global_step": 533334, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.08439302444458, "global_step": 533335, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0923731327056885, "global_step": 533336, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.956180453300476, "global_step": 533337, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0672619342803955, "global_step": 533338, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0605828762054443, "global_step": 533339, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.098034143447876, "global_step": 533340, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.094601631164551, "global_step": 533341, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0501301288604736, "global_step": 533342, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.000194549560547, "global_step": 533343, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0121750831604004, "global_step": 533344, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0305514335632324, "global_step": 533345, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9686188697814941, "global_step": 533346, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1009302139282227, "global_step": 533347, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.086529493331909, "global_step": 533348, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0700435638427734, "global_step": 533349, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.018244743347168, "global_step": 533350, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0428669452667236, "global_step": 533351, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0588717460632324, "global_step": 533352, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0404112339019775, "global_step": 533353, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0061042308807373, "global_step": 533354, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.10520076751709, "global_step": 533355, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9799199104309082, "global_step": 533356, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0394370555877686, "global_step": 533357, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.083728313446045, "global_step": 533358, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0432465076446533, "global_step": 533359, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9187718629837036, "global_step": 533360, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.051816940307617, "global_step": 533361, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.130979299545288, "global_step": 533362, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0357494354248047, "global_step": 533363, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.040677070617676, "global_step": 533364, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0538225173950195, "global_step": 533365, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0642783641815186, "global_step": 533366, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0122904777526855, "global_step": 533367, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0665271282196045, "global_step": 533368, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.034986972808838, "global_step": 533369, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9766534566879272, "global_step": 533370, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0608057975769043, "global_step": 533371, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9434013366699219, "global_step": 533372, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1093366146087646, "global_step": 533373, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.060185194015503, "global_step": 533374, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.048560380935669, "global_step": 533375, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1311724185943604, "global_step": 533376, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.022498846054077, "global_step": 533377, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.009768009185791, "global_step": 533378, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.030466079711914, "global_step": 533379, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.000023603439331, "global_step": 533380, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0605156421661377, "global_step": 533381, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.077794075012207, "global_step": 533382, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1066384315490723, "global_step": 533383, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0355963706970215, "global_step": 533384, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9007947444915771, "global_step": 533385, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1015639305114746, "global_step": 533386, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0424201488494873, "global_step": 533387, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.055184841156006, "global_step": 533388, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0449936389923096, "global_step": 533389, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9572153091430664, "global_step": 533390, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.012307643890381, "global_step": 533391, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0267727375030518, "global_step": 533392, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0201077461242676, "global_step": 533393, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.998052716255188, "global_step": 533394, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.8984010219573975, "global_step": 533395, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9656424522399902, "global_step": 533396, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.032093048095703, "global_step": 533397, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0161423683166504, "global_step": 533398, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9566301107406616, "global_step": 533399, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0246474742889404, "global_step": 533400, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9577877521514893, "global_step": 533401, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9917789697647095, "global_step": 533402, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.032327651977539, "global_step": 533403, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.089738368988037, "global_step": 533404, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9809343814849854, "global_step": 533405, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0035877227783203, "global_step": 533406, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.029822587966919, "global_step": 533407, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9396594762802124, "global_step": 533408, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0479538440704346, "global_step": 533409, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.032423734664917, "global_step": 533410, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.967758059501648, "global_step": 533411, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.096160650253296, "global_step": 533412, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.071558952331543, "global_step": 533413, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.031287670135498, "global_step": 533414, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.952109694480896, "global_step": 533415, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0862624645233154, "global_step": 533416, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9193445444107056, "global_step": 533417, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.063239097595215, "global_step": 533418, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0325052738189697, "global_step": 533419, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.033531427383423, "global_step": 533420, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.083007574081421, "global_step": 533421, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.041050672531128, "global_step": 533422, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.07649827003479, "global_step": 533423, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.02435564994812, "global_step": 533424, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9003828763961792, "global_step": 533425, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0158910751342773, "global_step": 533426, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9371637105941772, "global_step": 533427, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9700082540512085, "global_step": 533428, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1068623065948486, "global_step": 533429, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0856313705444336, "global_step": 533430, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0983314514160156, "global_step": 533431, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0235507488250732, "global_step": 533432, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9588305950164795, "global_step": 533433, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0803818702697754, "global_step": 533434, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0627658367156982, "global_step": 533435, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0719492435455322, "global_step": 533436, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0762391090393066, "global_step": 533437, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0165815353393555, "global_step": 533438, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0977303981781006, "global_step": 533439, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0102248191833496, "global_step": 533440, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.004655599594116, "global_step": 533441, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0376651287078857, "global_step": 533442, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0422229766845703, "global_step": 533443, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.055772304534912, "global_step": 533444, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0520691871643066, "global_step": 533445, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0312886238098145, "global_step": 533446, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0793159008026123, "global_step": 533447, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0602402687072754, "global_step": 533448, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9625223875045776, "global_step": 533449, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0356061458587646, "global_step": 533450, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0414578914642334, "global_step": 533451, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9865485429763794, "global_step": 533452, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0711896419525146, "global_step": 533453, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0031988620758057, "global_step": 533454, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.031053066253662, "global_step": 533455, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.099593162536621, "global_step": 533456, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.013801097869873, "global_step": 533457, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9987260103225708, "global_step": 533458, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0088889598846436, "global_step": 533459, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.014059543609619, "global_step": 533460, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9856603145599365, "global_step": 533461, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.028860330581665, "global_step": 533462, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1092653274536133, "global_step": 533463, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.09690523147583, "global_step": 533464, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1078853607177734, "global_step": 533465, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.040623664855957, "global_step": 533466, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9671512842178345, "global_step": 533467, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.016846179962158, "global_step": 533468, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0304605960845947, "global_step": 533469, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9740031957626343, "global_step": 533470, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9762325286865234, "global_step": 533471, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0478286743164062, "global_step": 533472, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9570645093917847, "global_step": 533473, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0344042778015137, "global_step": 533474, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9420831203460693, "global_step": 533475, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0140833854675293, "global_step": 533476, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0917694568634033, "global_step": 533477, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9935003519058228, "global_step": 533478, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.096205711364746, "global_step": 533479, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0694406032562256, "global_step": 533480, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.117800235748291, "global_step": 533481, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.061160087585449, "global_step": 533482, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9957267045974731, "global_step": 533483, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0329430103302, "global_step": 533484, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0152463912963867, "global_step": 533485, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9938113689422607, "global_step": 533486, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.004490375518799, "global_step": 533487, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9719457626342773, "global_step": 533488, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.90363609790802, "global_step": 533489, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0707101821899414, "global_step": 533490, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.013129711151123, "global_step": 533491, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.080787181854248, "global_step": 533492, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9776149988174438, "global_step": 533493, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.028336763381958, "global_step": 533494, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9703530073165894, "global_step": 533495, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9318571090698242, "global_step": 533496, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9923855066299438, "global_step": 533497, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0547261238098145, "global_step": 533498, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1422107219696045, "global_step": 533499, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.057919979095459, "global_step": 533500, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0215725898742676, "global_step": 533501, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9488966464996338, "global_step": 533502, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0691068172454834, "global_step": 533503, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.046138286590576, "global_step": 533504, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0184714794158936, "global_step": 533505, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9867199659347534, "global_step": 533506, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.053680181503296, "global_step": 533507, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0458807945251465, "global_step": 533508, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.954108476638794, "global_step": 533509, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0571811199188232, "global_step": 533510, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0023717880249023, "global_step": 533511, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.054940938949585, "global_step": 533512, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0441930294036865, "global_step": 533513, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0395843982696533, "global_step": 533514, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0674946308135986, "global_step": 533515, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0293502807617188, "global_step": 533516, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0345075130462646, "global_step": 533517, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.023127794265747, "global_step": 533518, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.031456470489502, "global_step": 533519, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9945334196090698, "global_step": 533520, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1088309288024902, "global_step": 533521, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0322983264923096, "global_step": 533522, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9901330471038818, "global_step": 533523, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0382442474365234, "global_step": 533524, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0754950046539307, "global_step": 533525, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0541529655456543, "global_step": 533526, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0118045806884766, "global_step": 533527, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.013967752456665, "global_step": 533528, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.049245595932007, "global_step": 533529, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0027897357940674, "global_step": 533530, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.041073799133301, "global_step": 533531, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.039949893951416, "global_step": 533532, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0769615173339844, "global_step": 533533, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0817630290985107, "global_step": 533534, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.046760082244873, "global_step": 533535, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9700185060501099, "global_step": 533536, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.052095651626587, "global_step": 533537, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1266417503356934, "global_step": 533538, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0001699924468994, "global_step": 533539, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.014866828918457, "global_step": 533540, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.166583776473999, "global_step": 533541, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.044769048690796, "global_step": 533542, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.049454689025879, "global_step": 533543, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9471914768218994, "global_step": 533544, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.087454319000244, "global_step": 533545, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0606439113616943, "global_step": 533546, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9880242347717285, "global_step": 533547, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0201830863952637, "global_step": 533548, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.07165789604187, "global_step": 533549, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0877578258514404, "global_step": 533550, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9406462907791138, "global_step": 533551, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0016565322875977, "global_step": 533552, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9926897287368774, "global_step": 533553, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9778950214385986, "global_step": 533554, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0124332904815674, "global_step": 533555, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.028000831604004, "global_step": 533556, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.086617946624756, "global_step": 533557, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.037283182144165, "global_step": 533558, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.060408353805542, "global_step": 533559, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.107398271560669, "global_step": 533560, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.058711051940918, "global_step": 533561, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0918314456939697, "global_step": 533562, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1097209453582764, "global_step": 533563, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0878186225891113, "global_step": 533564, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9415556192398071, "global_step": 533565, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.005389451980591, "global_step": 533566, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9698295593261719, "global_step": 533567, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1053247451782227, "global_step": 533568, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0114691257476807, "global_step": 533569, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.998515009880066, "global_step": 533570, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0180962085723877, "global_step": 533571, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0933218002319336, "global_step": 533572, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0048470497131348, "global_step": 533573, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.074544906616211, "global_step": 533574, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.068406105041504, "global_step": 533575, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0973544120788574, "global_step": 533576, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.07688307762146, "global_step": 533577, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.000548839569092, "global_step": 533578, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1081900596618652, "global_step": 533579, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9553688764572144, "global_step": 533580, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0443918704986572, "global_step": 533581, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9358539581298828, "global_step": 533582, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.042055606842041, "global_step": 533583, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.958164930343628, "global_step": 533584, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.04131817817688, "global_step": 533585, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9965943098068237, "global_step": 533586, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.035789966583252, "global_step": 533587, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0191962718963623, "global_step": 533588, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9125834703445435, "global_step": 533589, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0999064445495605, "global_step": 533590, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0897867679595947, "global_step": 533591, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9473909139633179, "global_step": 533592, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9966917037963867, "global_step": 533593, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.086174249649048, "global_step": 533594, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0542681217193604, "global_step": 533595, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0931954383850098, "global_step": 533596, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9786710739135742, "global_step": 533597, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1093575954437256, "global_step": 533598, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0144124031066895, "global_step": 533599, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.020613431930542, "global_step": 533600, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0283432006835938, "global_step": 533601, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0574421882629395, "global_step": 533602, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.069382667541504, "global_step": 533603, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0225229263305664, "global_step": 533604, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.057990550994873, "global_step": 533605, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0142264366149902, "global_step": 533606, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0491504669189453, "global_step": 533607, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0948574542999268, "global_step": 533608, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0113236904144287, "global_step": 533609, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9712873697280884, "global_step": 533610, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.098372220993042, "global_step": 533611, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0741896629333496, "global_step": 533612, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.033345937728882, "global_step": 533613, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9702894687652588, "global_step": 533614, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9397695064544678, "global_step": 533615, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0571417808532715, "global_step": 533616, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9681042432785034, "global_step": 533617, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9699852466583252, "global_step": 533618, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1324002742767334, "global_step": 533619, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0698602199554443, "global_step": 533620, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.100109100341797, "global_step": 533621, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.093338966369629, "global_step": 533622, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.067835807800293, "global_step": 533623, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.108454465866089, "global_step": 533624, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.916437029838562, "global_step": 533625, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0769424438476562, "global_step": 533626, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.059553623199463, "global_step": 533627, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.099292516708374, "global_step": 533628, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9896831512451172, "global_step": 533629, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0490565299987793, "global_step": 533630, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.147418975830078, "global_step": 533631, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0040135383605957, "global_step": 533632, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.088261127471924, "global_step": 533633, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9858466386795044, "global_step": 533634, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9819324016571045, "global_step": 533635, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0637617111206055, "global_step": 533636, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.041822910308838, "global_step": 533637, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9223510026931763, "global_step": 533638, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0669326782226562, "global_step": 533639, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.061058282852173, "global_step": 533640, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0121335983276367, "global_step": 533641, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0426993370056152, "global_step": 533642, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9478763341903687, "global_step": 533643, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.071178436279297, "global_step": 533644, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.013793706893921, "global_step": 533645, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0260119438171387, "global_step": 533646, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9529949426651, "global_step": 533647, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.070279836654663, "global_step": 533648, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0216360092163086, "global_step": 533649, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.024393081665039, "global_step": 533650, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1205966472625732, "global_step": 533651, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.19980788230896, "global_step": 533652, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.039550542831421, "global_step": 533653, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.004589557647705, "global_step": 533654, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9835453033447266, "global_step": 533655, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0864739418029785, "global_step": 533656, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.051706552505493, "global_step": 533657, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.130089282989502, "global_step": 533658, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.022902727127075, "global_step": 533659, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0517070293426514, "global_step": 533660, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.919703483581543, "global_step": 533661, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.020064353942871, "global_step": 533662, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.022879123687744, "global_step": 533663, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0420870780944824, "global_step": 533664, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0441834926605225, "global_step": 533665, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1284308433532715, "global_step": 533666, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9844400882720947, "global_step": 533667, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.111684799194336, "global_step": 533668, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1227731704711914, "global_step": 533669, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9825918674468994, "global_step": 533670, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1048173904418945, "global_step": 533671, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9551341533660889, "global_step": 533672, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9740511178970337, "global_step": 533673, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0123343467712402, "global_step": 533674, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.047027587890625, "global_step": 533675, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.047442674636841, "global_step": 533676, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0112297534942627, "global_step": 533677, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0708096027374268, "global_step": 533678, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.042034149169922, "global_step": 533679, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.058603525161743, "global_step": 533680, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0134336948394775, "global_step": 533681, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.018968343734741, "global_step": 533682, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.000556230545044, "global_step": 533683, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.080787181854248, "global_step": 533684, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.005746364593506, "global_step": 533685, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.028306484222412, "global_step": 533686, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1123437881469727, "global_step": 533687, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0576534271240234, "global_step": 533688, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0402607917785645, "global_step": 533689, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.035109519958496, "global_step": 533690, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.143839120864868, "global_step": 533691, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.024254322052002, "global_step": 533692, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1127943992614746, "global_step": 533693, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.062913656234741, "global_step": 533694, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0649781227111816, "global_step": 533695, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0699775218963623, "global_step": 533696, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9880255460739136, "global_step": 533697, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9525725841522217, "global_step": 533698, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0903995037078857, "global_step": 533699, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0213184356689453, "global_step": 533700, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0240414142608643, "global_step": 533701, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.127962350845337, "global_step": 533702, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0454909801483154, "global_step": 533703, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.985318899154663, "global_step": 533704, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.133542776107788, "global_step": 533705, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9868165254592896, "global_step": 533706, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.065788745880127, "global_step": 533707, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1033477783203125, "global_step": 533708, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.046234369277954, "global_step": 533709, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.073157787322998, "global_step": 533710, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1294479370117188, "global_step": 533711, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.013636350631714, "global_step": 533712, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.049259662628174, "global_step": 533713, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9938485622406006, "global_step": 533714, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0501294136047363, "global_step": 533715, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.995153784751892, "global_step": 533716, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0530598163604736, "global_step": 533717, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.068612575531006, "global_step": 533718, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9990788698196411, "global_step": 533719, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9981871843338013, "global_step": 533720, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.010622978210449, "global_step": 533721, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0773143768310547, "global_step": 533722, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.094698905944824, "global_step": 533723, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.088078260421753, "global_step": 533724, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0656774044036865, "global_step": 533725, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1326613426208496, "global_step": 533726, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.032519817352295, "global_step": 533727, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.94334077835083, "global_step": 533728, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9973958730697632, "global_step": 533729, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0496158599853516, "global_step": 533730, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0406177043914795, "global_step": 533731, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9878371953964233, "global_step": 533732, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.038836717605591, "global_step": 533733, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.086934804916382, "global_step": 533734, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0623040199279785, "global_step": 533735, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.005213975906372, "global_step": 533736, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9513591527938843, "global_step": 533737, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9934968948364258, "global_step": 533738, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0639259815216064, "global_step": 533739, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0261313915252686, "global_step": 533740, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0389297008514404, "global_step": 533741, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0728187561035156, "global_step": 533742, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.07692813873291, "global_step": 533743, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9650332927703857, "global_step": 533744, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.037379741668701, "global_step": 533745, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0279347896575928, "global_step": 533746, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.094407081604004, "global_step": 533747, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0525267124176025, "global_step": 533748, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0738091468811035, "global_step": 533749, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.093764305114746, "global_step": 533750, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0537126064300537, "global_step": 533751, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9632550477981567, "global_step": 533752, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1650407314300537, "global_step": 533753, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.034290313720703, "global_step": 533754, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9486658573150635, "global_step": 533755, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0766000747680664, "global_step": 533756, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0489723682403564, "global_step": 533757, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.032766819000244, "global_step": 533758, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9345225095748901, "global_step": 533759, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0263004302978516, "global_step": 533760, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0937204360961914, "global_step": 533761, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0683393478393555, "global_step": 533762, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.994080901145935, "global_step": 533763, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.036405324935913, "global_step": 533764, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.036512851715088, "global_step": 533765, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0140137672424316, "global_step": 533766, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.146024465560913, "global_step": 533767, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0826833248138428, "global_step": 533768, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.003647565841675, "global_step": 533769, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.039095878601074, "global_step": 533770, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9861493110656738, "global_step": 533771, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9469856023788452, "global_step": 533772, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0964159965515137, "global_step": 533773, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.139181613922119, "global_step": 533774, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.068870782852173, "global_step": 533775, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.11836314201355, "global_step": 533776, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0341053009033203, "global_step": 533777, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.022573471069336, "global_step": 533778, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.026519298553467, "global_step": 533779, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0986526012420654, "global_step": 533780, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9906504154205322, "global_step": 533781, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.041510820388794, "global_step": 533782, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0917694568634033, "global_step": 533783, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0056393146514893, "global_step": 533784, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0466151237487793, "global_step": 533785, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.069178819656372, "global_step": 533786, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.98219633102417, "global_step": 533787, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0595741271972656, "global_step": 533788, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.984150767326355, "global_step": 533789, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.04386043548584, "global_step": 533790, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0664708614349365, "global_step": 533791, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0285580158233643, "global_step": 533792, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0167770385742188, "global_step": 533793, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.068880558013916, "global_step": 533794, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.116664171218872, "global_step": 533795, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.057673215866089, "global_step": 533796, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0571835041046143, "global_step": 533797, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0688655376434326, "global_step": 533798, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0236406326293945, "global_step": 533799, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1198766231536865, "global_step": 533800, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.049346923828125, "global_step": 533801, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.052940845489502, "global_step": 533802, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0548038482666016, "global_step": 533803, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0159194469451904, "global_step": 533804, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9619688987731934, "global_step": 533805, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0202324390411377, "global_step": 533806, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0518946647644043, "global_step": 533807, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.014619827270508, "global_step": 533808, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9502136707305908, "global_step": 533809, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9744035005569458, "global_step": 533810, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.073659658432007, "global_step": 533811, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.026639223098755, "global_step": 533812, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0838124752044678, "global_step": 533813, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0997703075408936, "global_step": 533814, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1100759506225586, "global_step": 533815, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9733983278274536, "global_step": 533816, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0894548892974854, "global_step": 533817, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9568898677825928, "global_step": 533818, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0734457969665527, "global_step": 533819, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.020951509475708, "global_step": 533820, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.142730951309204, "global_step": 533821, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0078558921813965, "global_step": 533822, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.036494493484497, "global_step": 533823, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.084423065185547, "global_step": 533824, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9812774658203125, "global_step": 533825, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0721075534820557, "global_step": 533826, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0751919746398926, "global_step": 533827, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.111319065093994, "global_step": 533828, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.147388219833374, "global_step": 533829, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0612144470214844, "global_step": 533830, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.069060802459717, "global_step": 533831, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0443592071533203, "global_step": 533832, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.973557472229004, "global_step": 533833, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.043126344680786, "global_step": 533834, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0169880390167236, "global_step": 533835, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9283454418182373, "global_step": 533836, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9628236293792725, "global_step": 533837, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.079542636871338, "global_step": 533838, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0973761081695557, "global_step": 533839, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.002739429473877, "global_step": 533840, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0603935718536377, "global_step": 533841, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.96416437625885, "global_step": 533842, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.058596611022949, "global_step": 533843, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9701310396194458, "global_step": 533844, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0694339275360107, "global_step": 533845, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0291388034820557, "global_step": 533846, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0352582931518555, "global_step": 533847, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.97469162940979, "global_step": 533848, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9611557722091675, "global_step": 533849, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1016225814819336, "global_step": 533850, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.088369846343994, "global_step": 533851, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.114828109741211, "global_step": 533852, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9938702583312988, "global_step": 533853, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0182902812957764, "global_step": 533854, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.188781499862671, "global_step": 533855, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0376739501953125, "global_step": 533856, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0352609157562256, "global_step": 533857, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9587535858154297, "global_step": 533858, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9831721782684326, "global_step": 533859, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0893428325653076, "global_step": 533860, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0752322673797607, "global_step": 533861, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0879969596862793, "global_step": 533862, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.063946008682251, "global_step": 533863, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0912818908691406, "global_step": 533864, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.125365734100342, "global_step": 533865, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0987987518310547, "global_step": 533866, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0073182582855225, "global_step": 533867, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.038759231567383, "global_step": 533868, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.923949122428894, "global_step": 533869, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.98323392868042, "global_step": 533870, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.011692523956299, "global_step": 533871, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.061288833618164, "global_step": 533872, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0587949752807617, "global_step": 533873, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.043647289276123, "global_step": 533874, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0628433227539062, "global_step": 533875, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.104823589324951, "global_step": 533876, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.091522216796875, "global_step": 533877, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0544049739837646, "global_step": 533878, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.03995943069458, "global_step": 533879, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9456560611724854, "global_step": 533880, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9883021116256714, "global_step": 533881, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.05126953125, "global_step": 533882, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0932559967041016, "global_step": 533883, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9981917142868042, "global_step": 533884, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.065572500228882, "global_step": 533885, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9682583808898926, "global_step": 533886, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0875229835510254, "global_step": 533887, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0573720932006836, "global_step": 533888, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9944190979003906, "global_step": 533889, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0584967136383057, "global_step": 533890, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.105705976486206, "global_step": 533891, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.028721570968628, "global_step": 533892, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0242080688476562, "global_step": 533893, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0689446926116943, "global_step": 533894, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.066598892211914, "global_step": 533895, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.047070026397705, "global_step": 533896, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0618882179260254, "global_step": 533897, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0687479972839355, "global_step": 533898, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.001852035522461, "global_step": 533899, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9986498355865479, "global_step": 533900, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0378565788269043, "global_step": 533901, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0192551612854004, "global_step": 533902, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0775625705718994, "global_step": 533903, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.014219284057617, "global_step": 533904, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.021129846572876, "global_step": 533905, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0050344467163086, "global_step": 533906, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9637469053268433, "global_step": 533907, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.063948631286621, "global_step": 533908, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.051745653152466, "global_step": 533909, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0530829429626465, "global_step": 533910, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0103158950805664, "global_step": 533911, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9962739944458008, "global_step": 533912, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9640618562698364, "global_step": 533913, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0342540740966797, "global_step": 533914, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.100715398788452, "global_step": 533915, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0592427253723145, "global_step": 533916, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.082589626312256, "global_step": 533917, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.070842742919922, "global_step": 533918, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0397911071777344, "global_step": 533919, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.065164804458618, "global_step": 533920, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.023397207260132, "global_step": 533921, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0402913093566895, "global_step": 533922, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.050976514816284, "global_step": 533923, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9833379983901978, "global_step": 533924, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0975663661956787, "global_step": 533925, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.059791326522827, "global_step": 533926, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.023303270339966, "global_step": 533927, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9693819284439087, "global_step": 533928, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1520333290100098, "global_step": 533929, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.057288408279419, "global_step": 533930, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.063450813293457, "global_step": 533931, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.151857614517212, "global_step": 533932, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0234365463256836, "global_step": 533933, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1138174533843994, "global_step": 533934, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.045508623123169, "global_step": 533935, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.075327157974243, "global_step": 533936, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.043002128601074, "global_step": 533937, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0404000282287598, "global_step": 533938, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0878350734710693, "global_step": 533939, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.981652021408081, "global_step": 533940, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0731067657470703, "global_step": 533941, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.04473614692688, "global_step": 533942, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0413191318511963, "global_step": 533943, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1213414669036865, "global_step": 533944, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0728533267974854, "global_step": 533945, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.055053234100342, "global_step": 533946, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0943779945373535, "global_step": 533947, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9816162586212158, "global_step": 533948, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.077279806137085, "global_step": 533949, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.99797523021698, "global_step": 533950, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9926319122314453, "global_step": 533951, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.037313222885132, "global_step": 533952, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.023038148880005, "global_step": 533953, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.063946485519409, "global_step": 533954, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.047010660171509, "global_step": 533955, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.050384521484375, "global_step": 533956, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.089127540588379, "global_step": 533957, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0162715911865234, "global_step": 533958, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.010868787765503, "global_step": 533959, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.056704044342041, "global_step": 533960, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.007974624633789, "global_step": 533961, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0576553344726562, "global_step": 533962, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0896832942962646, "global_step": 533963, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.085404872894287, "global_step": 533964, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.03800106048584, "global_step": 533965, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.976811408996582, "global_step": 533966, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0884509086608887, "global_step": 533967, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.05023455619812, "global_step": 533968, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0884854793548584, "global_step": 533969, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1570589542388916, "global_step": 533970, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.062206506729126, "global_step": 533971, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0255632400512695, "global_step": 533972, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0339245796203613, "global_step": 533973, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0777862071990967, "global_step": 533974, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.124779462814331, "global_step": 533975, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0712649822235107, "global_step": 533976, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9983007907867432, "global_step": 533977, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.023141860961914, "global_step": 533978, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9842133522033691, "global_step": 533979, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.061539888381958, "global_step": 533980, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0566601753234863, "global_step": 533981, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0161337852478027, "global_step": 533982, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9860376119613647, "global_step": 533983, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0268394947052, "global_step": 533984, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0246734619140625, "global_step": 533985, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0538856983184814, "global_step": 533986, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0501699447631836, "global_step": 533987, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9304418563842773, "global_step": 533988, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0457706451416016, "global_step": 533989, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0486295223236084, "global_step": 533990, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.005998373031616, "global_step": 533991, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.050847291946411, "global_step": 533992, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.035872220993042, "global_step": 533993, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.069462776184082, "global_step": 533994, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9650912284851074, "global_step": 533995, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0685908794403076, "global_step": 533996, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0442495346069336, "global_step": 533997, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1368980407714844, "global_step": 533998, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.009997844696045, "global_step": 533999, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0881540775299072, "global_step": 534000, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.004641532897949, "global_step": 534001, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.109510898590088, "global_step": 534002, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.06754994392395, "global_step": 534003, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0862321853637695, "global_step": 534004, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9494044780731201, "global_step": 534005, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.077270269393921, "global_step": 534006, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9923887252807617, "global_step": 534007, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9250251054763794, "global_step": 534008, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.189523935317993, "global_step": 534009, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1033847332000732, "global_step": 534010, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.025278091430664, "global_step": 534011, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0785417556762695, "global_step": 534012, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.059075355529785, "global_step": 534013, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0898523330688477, "global_step": 534014, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0789551734924316, "global_step": 534015, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.961474061012268, "global_step": 534016, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.178081750869751, "global_step": 534017, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1003899574279785, "global_step": 534018, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.057246685028076, "global_step": 534019, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0708587169647217, "global_step": 534020, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.046840190887451, "global_step": 534021, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0278825759887695, "global_step": 534022, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.045020818710327, "global_step": 534023, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9830049276351929, "global_step": 534024, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.08876633644104, "global_step": 534025, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1588284969329834, "global_step": 534026, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9593106508255005, "global_step": 534027, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9778214693069458, "global_step": 534028, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0676698684692383, "global_step": 534029, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0228230953216553, "global_step": 534030, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9409102201461792, "global_step": 534031, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0480730533599854, "global_step": 534032, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0745182037353516, "global_step": 534033, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.09134840965271, "global_step": 534034, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1048836708068848, "global_step": 534035, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0340752601623535, "global_step": 534036, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9961193799972534, "global_step": 534037, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9745160341262817, "global_step": 534038, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.036165237426758, "global_step": 534039, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0661535263061523, "global_step": 534040, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0125391483306885, "global_step": 534041, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.110527992248535, "global_step": 534042, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0850274562835693, "global_step": 534043, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.034069776535034, "global_step": 534044, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9921702146530151, "global_step": 534045, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.038379669189453, "global_step": 534046, "epoch": 900, "lr": 5e-05}
{"train_loss": 1.9985604286193848, "global_step": 534047, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.0717129707336426, "global_step": 534048, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.1054532527923584, "global_step": 534049, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.021470785140991, "global_step": 534050, "epoch": 900, "lr": 5e-05}
{"train_loss": 2.03694486618042, "global_step": 534051, "epoch": 900, "lr": 5e-05, "KITCHEN_SCENE6_put_the_yellow_and_white_mug_in_the_microwave_and_close_it/mean_success_rate": 0.7666666666666667, "LIVING_ROOM_SCENE2_put_both_the_alphabet_soup_and_the_tomato_sauce_in_the_basket/mean_success_rate": 0.0, "STUDY_SCENE1_pick_up_the_book_and_place_it_in_the_back_compartment_of_the_caddy/mean_success_rate": 0.5, "KITCHEN_SCENE8_put_both_moka_pots_on_the_stove/mean_success_rate": 0.6, "LIVING_ROOM_SCENE5_put_the_white_mug_on_the_left_plate_and_put_the_yellow_and_white_mug_on_the_right_plate/mean_success_rate": 0.5, "LIVING_ROOM_SCENE6_put_the_white_mug_on_the_plate_and_put_the_chocolate_pudding_to_the_right_of_the_plate/mean_success_rate": 0.23333333333333334, "KITCHEN_SCENE4_put_the_black_bowl_in_the_bottom_drawer_of_the_cabinet_and_close_it/mean_success_rate": 0.9, "LIVING_ROOM_SCENE2_put_both_the_cream_cheese_box_and_the_butter_in_the_basket/mean_success_rate": 0.36666666666666664, "LIVING_ROOM_SCENE1_put_both_the_alphabet_soup_and_the_cream_cheese_box_in_the_basket/mean_success_rate": 0.0, "KITCHEN_SCENE3_turn_on_the_stove_and_put_the_moka_pot_on_it/mean_success_rate": 0.9, "mean_success_rate": 0.4766666666666667, "val_loss": 5.7416791915893555, "test_reconst_mse": 0.07394882291555405}
{"train_loss": 2.042336940765381, "global_step": 534052, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.991407036781311, "global_step": 534053, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.044708251953125, "global_step": 534054, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.028348207473755, "global_step": 534055, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9777390956878662, "global_step": 534056, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0275957584381104, "global_step": 534057, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0502068996429443, "global_step": 534058, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.048774003982544, "global_step": 534059, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9953683614730835, "global_step": 534060, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0467026233673096, "global_step": 534061, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0543718338012695, "global_step": 534062, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0462021827697754, "global_step": 534063, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0631048679351807, "global_step": 534064, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.024575710296631, "global_step": 534065, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.001410722732544, "global_step": 534066, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.08164644241333, "global_step": 534067, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.060581684112549, "global_step": 534068, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0674734115600586, "global_step": 534069, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0002493858337402, "global_step": 534070, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.063634157180786, "global_step": 534071, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9882417917251587, "global_step": 534072, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.09018611907959, "global_step": 534073, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.001981735229492, "global_step": 534074, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0357513427734375, "global_step": 534075, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0447616577148438, "global_step": 534076, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.072441577911377, "global_step": 534077, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.076172351837158, "global_step": 534078, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9596375226974487, "global_step": 534079, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0494937896728516, "global_step": 534080, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9886600971221924, "global_step": 534081, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0616657733917236, "global_step": 534082, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.971401572227478, "global_step": 534083, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.09556245803833, "global_step": 534084, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9374964237213135, "global_step": 534085, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.090330123901367, "global_step": 534086, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.930056095123291, "global_step": 534087, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0843567848205566, "global_step": 534088, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.049633741378784, "global_step": 534089, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0090410709381104, "global_step": 534090, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0036535263061523, "global_step": 534091, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.995805025100708, "global_step": 534092, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0373997688293457, "global_step": 534093, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.100109338760376, "global_step": 534094, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0428481101989746, "global_step": 534095, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0369575023651123, "global_step": 534096, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.101473093032837, "global_step": 534097, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.034003257751465, "global_step": 534098, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1090431213378906, "global_step": 534099, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9893684387207031, "global_step": 534100, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0854909420013428, "global_step": 534101, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0414559841156006, "global_step": 534102, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.047666549682617, "global_step": 534103, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.045412540435791, "global_step": 534104, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0676238536834717, "global_step": 534105, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.13462495803833, "global_step": 534106, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.071873188018799, "global_step": 534107, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0834920406341553, "global_step": 534108, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0320374965667725, "global_step": 534109, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0563225746154785, "global_step": 534110, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9503873586654663, "global_step": 534111, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9282294511795044, "global_step": 534112, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0365259647369385, "global_step": 534113, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.058267593383789, "global_step": 534114, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9965490102767944, "global_step": 534115, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.072737455368042, "global_step": 534116, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.053776741027832, "global_step": 534117, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.99455988407135, "global_step": 534118, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.066758394241333, "global_step": 534119, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0294058322906494, "global_step": 534120, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9463990926742554, "global_step": 534121, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.007758140563965, "global_step": 534122, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9988075494766235, "global_step": 534123, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9443918466567993, "global_step": 534124, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9581818580627441, "global_step": 534125, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.007719039916992, "global_step": 534126, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.998663067817688, "global_step": 534127, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.964093804359436, "global_step": 534128, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0410168170928955, "global_step": 534129, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.089672565460205, "global_step": 534130, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1217095851898193, "global_step": 534131, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1213042736053467, "global_step": 534132, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0236120223999023, "global_step": 534133, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0101802349090576, "global_step": 534134, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0359199047088623, "global_step": 534135, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0403261184692383, "global_step": 534136, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.021125316619873, "global_step": 534137, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0539116859436035, "global_step": 534138, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9940248727798462, "global_step": 534139, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.963887333869934, "global_step": 534140, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0597238540649414, "global_step": 534141, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9257535934448242, "global_step": 534142, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9911003112792969, "global_step": 534143, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9449760913848877, "global_step": 534144, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0289642810821533, "global_step": 534145, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.8940536975860596, "global_step": 534146, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.044581890106201, "global_step": 534147, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9979150295257568, "global_step": 534148, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9366002082824707, "global_step": 534149, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.091125249862671, "global_step": 534150, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.095627784729004, "global_step": 534151, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.026141405105591, "global_step": 534152, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.13405704498291, "global_step": 534153, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.992268681526184, "global_step": 534154, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0173161029815674, "global_step": 534155, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0540428161621094, "global_step": 534156, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0970535278320312, "global_step": 534157, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.003255605697632, "global_step": 534158, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.04292631149292, "global_step": 534159, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9423611164093018, "global_step": 534160, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0127651691436768, "global_step": 534161, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9894349575042725, "global_step": 534162, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0268325805664062, "global_step": 534163, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0016982555389404, "global_step": 534164, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9659502506256104, "global_step": 534165, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.056511640548706, "global_step": 534166, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9783679246902466, "global_step": 534167, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0364990234375, "global_step": 534168, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0547337532043457, "global_step": 534169, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.131993532180786, "global_step": 534170, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1065633296966553, "global_step": 534171, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.007779836654663, "global_step": 534172, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0255188941955566, "global_step": 534173, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.010396957397461, "global_step": 534174, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0151524543762207, "global_step": 534175, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0379490852355957, "global_step": 534176, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9669252634048462, "global_step": 534177, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0267221927642822, "global_step": 534178, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9993377923965454, "global_step": 534179, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0484657287597656, "global_step": 534180, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9931025505065918, "global_step": 534181, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.962307333946228, "global_step": 534182, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.034048557281494, "global_step": 534183, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.039144277572632, "global_step": 534184, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0470893383026123, "global_step": 534185, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9652494192123413, "global_step": 534186, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0714714527130127, "global_step": 534187, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9708404541015625, "global_step": 534188, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9738917350769043, "global_step": 534189, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0495922565460205, "global_step": 534190, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.057447671890259, "global_step": 534191, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0922460556030273, "global_step": 534192, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.010222911834717, "global_step": 534193, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.039865493774414, "global_step": 534194, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1074259281158447, "global_step": 534195, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.086427688598633, "global_step": 534196, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0565643310546875, "global_step": 534197, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9853782653808594, "global_step": 534198, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.074955940246582, "global_step": 534199, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9972394704818726, "global_step": 534200, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0535826683044434, "global_step": 534201, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.019382953643799, "global_step": 534202, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1453664302825928, "global_step": 534203, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.990781545639038, "global_step": 534204, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.082381248474121, "global_step": 534205, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0863308906555176, "global_step": 534206, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9838014841079712, "global_step": 534207, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0714571475982666, "global_step": 534208, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9233750104904175, "global_step": 534209, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0194694995880127, "global_step": 534210, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0582685470581055, "global_step": 534211, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0439724922180176, "global_step": 534212, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.049440622329712, "global_step": 534213, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.08718204498291, "global_step": 534214, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9683496952056885, "global_step": 534215, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0816123485565186, "global_step": 534216, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.091019868850708, "global_step": 534217, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9593167304992676, "global_step": 534218, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9411394596099854, "global_step": 534219, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.029229164123535, "global_step": 534220, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9925885200500488, "global_step": 534221, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.033113956451416, "global_step": 534222, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9516315460205078, "global_step": 534223, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1292197704315186, "global_step": 534224, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.052849531173706, "global_step": 534225, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.061683416366577, "global_step": 534226, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.120546340942383, "global_step": 534227, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.072737693786621, "global_step": 534228, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9975076913833618, "global_step": 534229, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0454869270324707, "global_step": 534230, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1019651889801025, "global_step": 534231, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0352070331573486, "global_step": 534232, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9588855504989624, "global_step": 534233, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9669320583343506, "global_step": 534234, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0002360343933105, "global_step": 534235, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0051791667938232, "global_step": 534236, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9599477052688599, "global_step": 534237, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1373393535614014, "global_step": 534238, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0614776611328125, "global_step": 534239, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0409646034240723, "global_step": 534240, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.037306308746338, "global_step": 534241, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0272419452667236, "global_step": 534242, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1017706394195557, "global_step": 534243, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0912461280822754, "global_step": 534244, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.07144832611084, "global_step": 534245, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9995771646499634, "global_step": 534246, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.035762071609497, "global_step": 534247, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0302975177764893, "global_step": 534248, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.019740104675293, "global_step": 534249, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0988314151763916, "global_step": 534250, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.966869831085205, "global_step": 534251, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0042483806610107, "global_step": 534252, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.030008316040039, "global_step": 534253, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.031757116317749, "global_step": 534254, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.090515613555908, "global_step": 534255, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.083178758621216, "global_step": 534256, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.99753737449646, "global_step": 534257, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0010159015655518, "global_step": 534258, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0386831760406494, "global_step": 534259, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.983590006828308, "global_step": 534260, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.037097692489624, "global_step": 534261, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.015503168106079, "global_step": 534262, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9858838319778442, "global_step": 534263, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0573015213012695, "global_step": 534264, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.083317756652832, "global_step": 534265, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.04372239112854, "global_step": 534266, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0688745975494385, "global_step": 534267, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.2048122882843018, "global_step": 534268, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.038999080657959, "global_step": 534269, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9218536615371704, "global_step": 534270, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.121533155441284, "global_step": 534271, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9325522184371948, "global_step": 534272, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.095582962036133, "global_step": 534273, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.038558006286621, "global_step": 534274, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.061160087585449, "global_step": 534275, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0085952281951904, "global_step": 534276, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0452563762664795, "global_step": 534277, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9856035709381104, "global_step": 534278, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.106405258178711, "global_step": 534279, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0372519493103027, "global_step": 534280, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0627284049987793, "global_step": 534281, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0545036792755127, "global_step": 534282, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9908864498138428, "global_step": 534283, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0704355239868164, "global_step": 534284, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.098283529281616, "global_step": 534285, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0182223320007324, "global_step": 534286, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0813510417938232, "global_step": 534287, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.069558620452881, "global_step": 534288, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0512232780456543, "global_step": 534289, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.065840005874634, "global_step": 534290, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0041697025299072, "global_step": 534291, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.129742383956909, "global_step": 534292, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0924696922302246, "global_step": 534293, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9952360391616821, "global_step": 534294, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0009264945983887, "global_step": 534295, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.094505548477173, "global_step": 534296, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9553990364074707, "global_step": 534297, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9763691425323486, "global_step": 534298, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.961830496788025, "global_step": 534299, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0495080947875977, "global_step": 534300, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0165951251983643, "global_step": 534301, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0039775371551514, "global_step": 534302, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0302915573120117, "global_step": 534303, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0787272453308105, "global_step": 534304, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9602370262145996, "global_step": 534305, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9983505010604858, "global_step": 534306, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0789358615875244, "global_step": 534307, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0585227012634277, "global_step": 534308, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0268609523773193, "global_step": 534309, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0428578853607178, "global_step": 534310, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.117926597595215, "global_step": 534311, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0406570434570312, "global_step": 534312, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0545108318328857, "global_step": 534313, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9913386106491089, "global_step": 534314, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0322446823120117, "global_step": 534315, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0381274223327637, "global_step": 534316, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0282649993896484, "global_step": 534317, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.034912109375, "global_step": 534318, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.065134286880493, "global_step": 534319, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0095105171203613, "global_step": 534320, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0936155319213867, "global_step": 534321, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0252718925476074, "global_step": 534322, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0514299869537354, "global_step": 534323, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9767690896987915, "global_step": 534324, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0627479553222656, "global_step": 534325, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9735373258590698, "global_step": 534326, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0526490211486816, "global_step": 534327, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.069700241088867, "global_step": 534328, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0658531188964844, "global_step": 534329, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9979480504989624, "global_step": 534330, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0590388774871826, "global_step": 534331, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0233211517333984, "global_step": 534332, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9851740598678589, "global_step": 534333, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0906405448913574, "global_step": 534334, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.02168345451355, "global_step": 534335, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9694643020629883, "global_step": 534336, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0383880138397217, "global_step": 534337, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.003789186477661, "global_step": 534338, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.018231153488159, "global_step": 534339, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.045006275177002, "global_step": 534340, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1068203449249268, "global_step": 534341, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0566961765289307, "global_step": 534342, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9652999639511108, "global_step": 534343, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0937397480010986, "global_step": 534344, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9881683588027954, "global_step": 534345, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0487074851989746, "global_step": 534346, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0705010890960693, "global_step": 534347, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.091313362121582, "global_step": 534348, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.989625096321106, "global_step": 534349, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.040234327316284, "global_step": 534350, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0873305797576904, "global_step": 534351, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0830886363983154, "global_step": 534352, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.092061758041382, "global_step": 534353, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9810998439788818, "global_step": 534354, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0755386352539062, "global_step": 534355, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.067777395248413, "global_step": 534356, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.012483596801758, "global_step": 534357, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.04402756690979, "global_step": 534358, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.927979588508606, "global_step": 534359, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0314345359802246, "global_step": 534360, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9540133476257324, "global_step": 534361, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.024108409881592, "global_step": 534362, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.8940372467041016, "global_step": 534363, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0777571201324463, "global_step": 534364, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0733165740966797, "global_step": 534365, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.022883653640747, "global_step": 534366, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.086803436279297, "global_step": 534367, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0128490924835205, "global_step": 534368, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9958488941192627, "global_step": 534369, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0234923362731934, "global_step": 534370, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0653018951416016, "global_step": 534371, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.082716941833496, "global_step": 534372, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9873665571212769, "global_step": 534373, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0722997188568115, "global_step": 534374, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.034834146499634, "global_step": 534375, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9311708211898804, "global_step": 534376, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.989176630973816, "global_step": 534377, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0160627365112305, "global_step": 534378, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9866820573806763, "global_step": 534379, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9972285032272339, "global_step": 534380, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0871081352233887, "global_step": 534381, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.130493640899658, "global_step": 534382, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0441877841949463, "global_step": 534383, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.024991989135742, "global_step": 534384, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1164050102233887, "global_step": 534385, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0701844692230225, "global_step": 534386, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0789055824279785, "global_step": 534387, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.078751802444458, "global_step": 534388, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0338802337646484, "global_step": 534389, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0966670513153076, "global_step": 534390, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.095024585723877, "global_step": 534391, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9991662502288818, "global_step": 534392, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0030415058135986, "global_step": 534393, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9975330829620361, "global_step": 534394, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.969582200050354, "global_step": 534395, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.037626266479492, "global_step": 534396, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9670579433441162, "global_step": 534397, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.024174928665161, "global_step": 534398, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0144095420837402, "global_step": 534399, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.076568841934204, "global_step": 534400, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0697665214538574, "global_step": 534401, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.910723328590393, "global_step": 534402, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9644993543624878, "global_step": 534403, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.033073902130127, "global_step": 534404, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0046234130859375, "global_step": 534405, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9743263721466064, "global_step": 534406, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9686335325241089, "global_step": 534407, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9671918153762817, "global_step": 534408, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.056938409805298, "global_step": 534409, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9960386753082275, "global_step": 534410, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9524418115615845, "global_step": 534411, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0218327045440674, "global_step": 534412, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0488550662994385, "global_step": 534413, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.06441068649292, "global_step": 534414, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0327980518341064, "global_step": 534415, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0726382732391357, "global_step": 534416, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.990476131439209, "global_step": 534417, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.02073335647583, "global_step": 534418, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9978684186935425, "global_step": 534419, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0423662662506104, "global_step": 534420, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9558708667755127, "global_step": 534421, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.030629873275757, "global_step": 534422, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0341622829437256, "global_step": 534423, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.117182731628418, "global_step": 534424, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9505969285964966, "global_step": 534425, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0756115913391113, "global_step": 534426, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.968401551246643, "global_step": 534427, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1178183555603027, "global_step": 534428, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0612618923187256, "global_step": 534429, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.03185772895813, "global_step": 534430, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0187418460845947, "global_step": 534431, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.055145502090454, "global_step": 534432, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0387039184570312, "global_step": 534433, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.092305898666382, "global_step": 534434, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.014904260635376, "global_step": 534435, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.085798501968384, "global_step": 534436, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.016754150390625, "global_step": 534437, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9975494146347046, "global_step": 534438, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.986831545829773, "global_step": 534439, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.106091260910034, "global_step": 534440, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.130401849746704, "global_step": 534441, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.034898042678833, "global_step": 534442, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.046424150466919, "global_step": 534443, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.029219388961792, "global_step": 534444, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1279456615448, "global_step": 534445, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0584564208984375, "global_step": 534446, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9086087942123413, "global_step": 534447, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0511648654937744, "global_step": 534448, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1679041385650635, "global_step": 534449, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1411774158477783, "global_step": 534450, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.052150011062622, "global_step": 534451, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9065539836883545, "global_step": 534452, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0363643169403076, "global_step": 534453, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.992190957069397, "global_step": 534454, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.016188144683838, "global_step": 534455, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9763461351394653, "global_step": 534456, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.033655881881714, "global_step": 534457, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.147038221359253, "global_step": 534458, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.008357286453247, "global_step": 534459, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0648117065429688, "global_step": 534460, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.002129077911377, "global_step": 534461, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.985790491104126, "global_step": 534462, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0957088470458984, "global_step": 534463, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.066828727722168, "global_step": 534464, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9912781715393066, "global_step": 534465, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.050924777984619, "global_step": 534466, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.041437864303589, "global_step": 534467, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.024644374847412, "global_step": 534468, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0770015716552734, "global_step": 534469, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9747521877288818, "global_step": 534470, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.013482093811035, "global_step": 534471, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1624596118927, "global_step": 534472, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0497260093688965, "global_step": 534473, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.036614179611206, "global_step": 534474, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0773398876190186, "global_step": 534475, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0703601837158203, "global_step": 534476, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9069108963012695, "global_step": 534477, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0747718811035156, "global_step": 534478, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9844523668289185, "global_step": 534479, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.10597562789917, "global_step": 534480, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.083836078643799, "global_step": 534481, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.040773868560791, "global_step": 534482, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.016998767852783, "global_step": 534483, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9323093891143799, "global_step": 534484, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.924647569656372, "global_step": 534485, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0090889930725098, "global_step": 534486, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9258012771606445, "global_step": 534487, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.078948497772217, "global_step": 534488, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0413336753845215, "global_step": 534489, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9519180059432983, "global_step": 534490, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9885157346725464, "global_step": 534491, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1142513751983643, "global_step": 534492, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0790157318115234, "global_step": 534493, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9526829719543457, "global_step": 534494, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0628631114959717, "global_step": 534495, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9832003116607666, "global_step": 534496, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1203207969665527, "global_step": 534497, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0840845108032227, "global_step": 534498, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.090311288833618, "global_step": 534499, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9409207105636597, "global_step": 534500, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0962111949920654, "global_step": 534501, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.055039167404175, "global_step": 534502, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.8983869552612305, "global_step": 534503, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1141693592071533, "global_step": 534504, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0323853492736816, "global_step": 534505, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0383334159851074, "global_step": 534506, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1082818508148193, "global_step": 534507, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.061666965484619, "global_step": 534508, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9590837955474854, "global_step": 534509, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9376510381698608, "global_step": 534510, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1071503162384033, "global_step": 534511, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0629608631134033, "global_step": 534512, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1032216548919678, "global_step": 534513, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0411274433135986, "global_step": 534514, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9921756982803345, "global_step": 534515, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9095096588134766, "global_step": 534516, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.067580223083496, "global_step": 534517, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.033918857574463, "global_step": 534518, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.020415782928467, "global_step": 534519, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.093949794769287, "global_step": 534520, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.134857416152954, "global_step": 534521, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.088411808013916, "global_step": 534522, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0077743530273438, "global_step": 534523, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0547549724578857, "global_step": 534524, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.05733585357666, "global_step": 534525, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.001063585281372, "global_step": 534526, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.031583309173584, "global_step": 534527, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0366203784942627, "global_step": 534528, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.069730281829834, "global_step": 534529, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0318386554718018, "global_step": 534530, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9808214902877808, "global_step": 534531, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9770880937576294, "global_step": 534532, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.043721914291382, "global_step": 534533, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0849921703338623, "global_step": 534534, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0537760257720947, "global_step": 534535, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0096778869628906, "global_step": 534536, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.022338390350342, "global_step": 534537, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.007960796356201, "global_step": 534538, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9819127321243286, "global_step": 534539, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.030095338821411, "global_step": 534540, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0823264122009277, "global_step": 534541, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9493881464004517, "global_step": 534542, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.067673444747925, "global_step": 534543, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.084120750427246, "global_step": 534544, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1282665729522705, "global_step": 534545, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0318171977996826, "global_step": 534546, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.960920810699463, "global_step": 534547, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.043087959289551, "global_step": 534548, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0172924995422363, "global_step": 534549, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.102062463760376, "global_step": 534550, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0311226844787598, "global_step": 534551, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0058276653289795, "global_step": 534552, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9503581523895264, "global_step": 534553, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9863190650939941, "global_step": 534554, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.045264720916748, "global_step": 534555, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.049119710922241, "global_step": 534556, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9876110553741455, "global_step": 534557, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0132458209991455, "global_step": 534558, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9948174953460693, "global_step": 534559, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0811667442321777, "global_step": 534560, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.068942070007324, "global_step": 534561, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0089712142944336, "global_step": 534562, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9688563346862793, "global_step": 534563, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.024754762649536, "global_step": 534564, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.007938861846924, "global_step": 534565, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.120269775390625, "global_step": 534566, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9934144020080566, "global_step": 534567, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.005851984024048, "global_step": 534568, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0037343502044678, "global_step": 534569, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0899195671081543, "global_step": 534570, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0138580799102783, "global_step": 534571, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9996671676635742, "global_step": 534572, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0845181941986084, "global_step": 534573, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0664288997650146, "global_step": 534574, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.011512279510498, "global_step": 534575, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0707147121429443, "global_step": 534576, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0271990299224854, "global_step": 534577, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0503134727478027, "global_step": 534578, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0582892894744873, "global_step": 534579, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.003580093383789, "global_step": 534580, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0989229679107666, "global_step": 534581, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0979857444763184, "global_step": 534582, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.006988048553467, "global_step": 534583, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.934816837310791, "global_step": 534584, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9451624155044556, "global_step": 534585, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1278417110443115, "global_step": 534586, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0906853675842285, "global_step": 534587, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0464510917663574, "global_step": 534588, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0131874084472656, "global_step": 534589, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.129304885864258, "global_step": 534590, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9626471996307373, "global_step": 534591, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0411975383758545, "global_step": 534592, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9946010112762451, "global_step": 534593, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1541380882263184, "global_step": 534594, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9906944036483765, "global_step": 534595, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.002235174179077, "global_step": 534596, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0673704147338867, "global_step": 534597, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0493216514587402, "global_step": 534598, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.995052695274353, "global_step": 534599, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.039262533187866, "global_step": 534600, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0219666957855225, "global_step": 534601, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.006842613220215, "global_step": 534602, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0228168964385986, "global_step": 534603, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0700345039367676, "global_step": 534604, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0915210247039795, "global_step": 534605, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.013998031616211, "global_step": 534606, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.019620656967163, "global_step": 534607, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1280596256256104, "global_step": 534608, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9926780462265015, "global_step": 534609, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.042797565460205, "global_step": 534610, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.083770990371704, "global_step": 534611, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0334858894348145, "global_step": 534612, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0549492835998535, "global_step": 534613, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.016294240951538, "global_step": 534614, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1030116081237793, "global_step": 534615, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0231032371520996, "global_step": 534616, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.088918685913086, "global_step": 534617, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.191856861114502, "global_step": 534618, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0563771724700928, "global_step": 534619, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0130436420440674, "global_step": 534620, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0508639812469482, "global_step": 534621, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1264050006866455, "global_step": 534622, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0460588932037354, "global_step": 534623, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0276196002960205, "global_step": 534624, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0263473987579346, "global_step": 534625, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0336315631866455, "global_step": 534626, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.069279909133911, "global_step": 534627, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0350277423858643, "global_step": 534628, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1508545875549316, "global_step": 534629, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0315139293670654, "global_step": 534630, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.087735652923584, "global_step": 534631, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0493953227996826, "global_step": 534632, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.039778232574463, "global_step": 534633, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0903074741363525, "global_step": 534634, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.046565532684326, "global_step": 534635, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0578348636627197, "global_step": 534636, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0629003047943115, "global_step": 534637, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0400543212890625, "global_step": 534638, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9742108583450317, "global_step": 534639, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.037163257598877, "global_step": 534640, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0822346210479736, "global_step": 534641, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0302703380584717, "global_step": 534642, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0649683475494385, "global_step": 534643, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9832042455673218, "global_step": 534644, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.065617322921753, "global_step": 534645, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.030118227005005, "global_step": 534646, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0301828384399414, "global_step": 534647, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9573860168457031, "global_step": 534648, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0642402172088623, "global_step": 534649, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.005979061126709, "global_step": 534650, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0324478149414062, "global_step": 534651, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.047257900238037, "global_step": 534652, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.05181622505188, "global_step": 534653, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0400946140289307, "global_step": 534654, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0672531127929688, "global_step": 534655, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9805936813354492, "global_step": 534656, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0995419025421143, "global_step": 534657, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0513036251068115, "global_step": 534658, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.059077262878418, "global_step": 534659, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0555226802825928, "global_step": 534660, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0287559032440186, "global_step": 534661, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.085589647293091, "global_step": 534662, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0633625984191895, "global_step": 534663, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0437843799591064, "global_step": 534664, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0809099674224854, "global_step": 534665, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9730805158615112, "global_step": 534666, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0413506031036377, "global_step": 534667, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0939927101135254, "global_step": 534668, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0332725048065186, "global_step": 534669, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.004636526107788, "global_step": 534670, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9552892446517944, "global_step": 534671, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.093273878097534, "global_step": 534672, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.028909921646118, "global_step": 534673, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.082815170288086, "global_step": 534674, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0547215938568115, "global_step": 534675, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0521905422210693, "global_step": 534676, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.028669595718384, "global_step": 534677, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.044909954071045, "global_step": 534678, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.983210802078247, "global_step": 534679, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0938689708709717, "global_step": 534680, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.036142349243164, "global_step": 534681, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.023451566696167, "global_step": 534682, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9959228038787842, "global_step": 534683, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0865249633789062, "global_step": 534684, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1469779014587402, "global_step": 534685, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0075411796569824, "global_step": 534686, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.112082004547119, "global_step": 534687, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.034489631652832, "global_step": 534688, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.049159288406372, "global_step": 534689, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.097444534301758, "global_step": 534690, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9387903213500977, "global_step": 534691, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0899481773376465, "global_step": 534692, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.061206102371216, "global_step": 534693, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1109769344329834, "global_step": 534694, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9824271202087402, "global_step": 534695, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.095127582550049, "global_step": 534696, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.057612419128418, "global_step": 534697, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.067291259765625, "global_step": 534698, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.045780897140503, "global_step": 534699, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9996047019958496, "global_step": 534700, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0132765769958496, "global_step": 534701, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0747246742248535, "global_step": 534702, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9615061283111572, "global_step": 534703, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.074188709259033, "global_step": 534704, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.066409111022949, "global_step": 534705, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1013007164001465, "global_step": 534706, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.080583333969116, "global_step": 534707, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.044933557510376, "global_step": 534708, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.07710337638855, "global_step": 534709, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.001901149749756, "global_step": 534710, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.102787971496582, "global_step": 534711, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.030789852142334, "global_step": 534712, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.951560378074646, "global_step": 534713, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.918259859085083, "global_step": 534714, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9835951328277588, "global_step": 534715, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.058403968811035, "global_step": 534716, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.033623456954956, "global_step": 534717, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.00285005569458, "global_step": 534718, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1099517345428467, "global_step": 534719, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0624303817749023, "global_step": 534720, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.041332244873047, "global_step": 534721, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0310239791870117, "global_step": 534722, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0899009704589844, "global_step": 534723, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0313258171081543, "global_step": 534724, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0532379150390625, "global_step": 534725, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.076949119567871, "global_step": 534726, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0960381031036377, "global_step": 534727, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.068368911743164, "global_step": 534728, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.04398250579834, "global_step": 534729, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.028738260269165, "global_step": 534730, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.097071886062622, "global_step": 534731, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.071892738342285, "global_step": 534732, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.049579620361328, "global_step": 534733, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.087245225906372, "global_step": 534734, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.040259599685669, "global_step": 534735, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.054086685180664, "global_step": 534736, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0735061168670654, "global_step": 534737, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0100150108337402, "global_step": 534738, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.04787278175354, "global_step": 534739, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0162675380706787, "global_step": 534740, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.099982976913452, "global_step": 534741, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0939583778381348, "global_step": 534742, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0387892723083496, "global_step": 534743, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0509374141693115, "global_step": 534744, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0622572898864746, "global_step": 534745, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0446419715881348, "global_step": 534746, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0651395320892334, "global_step": 534747, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.000123977661133, "global_step": 534748, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.042715311050415, "global_step": 534749, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0320417881011963, "global_step": 534750, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.052018404006958, "global_step": 534751, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.088289260864258, "global_step": 534752, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1460561752319336, "global_step": 534753, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.186993360519409, "global_step": 534754, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.031080722808838, "global_step": 534755, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.095046043395996, "global_step": 534756, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.945968508720398, "global_step": 534757, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0194225311279297, "global_step": 534758, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0126895904541016, "global_step": 534759, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1080358028411865, "global_step": 534760, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.002157688140869, "global_step": 534761, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.047072410583496, "global_step": 534762, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0709311962127686, "global_step": 534763, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.001108407974243, "global_step": 534764, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1250243186950684, "global_step": 534765, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0842294692993164, "global_step": 534766, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.033135414123535, "global_step": 534767, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0402672290802, "global_step": 534768, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.038255214691162, "global_step": 534769, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1501755714416504, "global_step": 534770, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.064112663269043, "global_step": 534771, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9974461793899536, "global_step": 534772, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0068674087524414, "global_step": 534773, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1128358840942383, "global_step": 534774, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0189218521118164, "global_step": 534775, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.021343231201172, "global_step": 534776, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.14982271194458, "global_step": 534777, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9822829961776733, "global_step": 534778, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.123026132583618, "global_step": 534779, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0495047569274902, "global_step": 534780, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.018362045288086, "global_step": 534781, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0112857818603516, "global_step": 534782, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1471009254455566, "global_step": 534783, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.132124423980713, "global_step": 534784, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0381152629852295, "global_step": 534785, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.056061029434204, "global_step": 534786, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0809924602508545, "global_step": 534787, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.964243769645691, "global_step": 534788, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.034475803375244, "global_step": 534789, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1219379901885986, "global_step": 534790, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.00646710395813, "global_step": 534791, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0967414379119873, "global_step": 534792, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0378942489624023, "global_step": 534793, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0210156440734863, "global_step": 534794, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.028735637664795, "global_step": 534795, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0821967124938965, "global_step": 534796, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0026803016662598, "global_step": 534797, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9993184804916382, "global_step": 534798, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0673646926879883, "global_step": 534799, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.086606502532959, "global_step": 534800, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0575363636016846, "global_step": 534801, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.007507801055908, "global_step": 534802, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0298004150390625, "global_step": 534803, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0628502368927, "global_step": 534804, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0561766624450684, "global_step": 534805, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.042294979095459, "global_step": 534806, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.060541868209839, "global_step": 534807, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.004582166671753, "global_step": 534808, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.930596947669983, "global_step": 534809, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.057131052017212, "global_step": 534810, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0886342525482178, "global_step": 534811, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.022472858428955, "global_step": 534812, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9415688514709473, "global_step": 534813, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.052152156829834, "global_step": 534814, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.040381908416748, "global_step": 534815, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0617902278900146, "global_step": 534816, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.952415108680725, "global_step": 534817, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.14381742477417, "global_step": 534818, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0458974838256836, "global_step": 534819, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0378243923187256, "global_step": 534820, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9712955951690674, "global_step": 534821, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.008788824081421, "global_step": 534822, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0516555309295654, "global_step": 534823, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.029296398162842, "global_step": 534824, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0437119007110596, "global_step": 534825, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0736730098724365, "global_step": 534826, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9226195812225342, "global_step": 534827, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1096749305725098, "global_step": 534828, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9602961540222168, "global_step": 534829, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1322522163391113, "global_step": 534830, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0492594242095947, "global_step": 534831, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0933167934417725, "global_step": 534832, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0825138092041016, "global_step": 534833, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.94650399684906, "global_step": 534834, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0303118228912354, "global_step": 534835, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0557165145874023, "global_step": 534836, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0017757415771484, "global_step": 534837, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0177361965179443, "global_step": 534838, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0611555576324463, "global_step": 534839, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.073590040206909, "global_step": 534840, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0935730934143066, "global_step": 534841, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9610695838928223, "global_step": 534842, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.026859760284424, "global_step": 534843, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9975879192352295, "global_step": 534844, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0702733993530273, "global_step": 534845, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0486059188842773, "global_step": 534846, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0660548210144043, "global_step": 534847, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.034675359725952, "global_step": 534848, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9800068140029907, "global_step": 534849, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0273385047912598, "global_step": 534850, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0824825763702393, "global_step": 534851, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9828073978424072, "global_step": 534852, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0478358268737793, "global_step": 534853, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.038688898086548, "global_step": 534854, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9854462146759033, "global_step": 534855, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.981836199760437, "global_step": 534856, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.013763189315796, "global_step": 534857, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0162954330444336, "global_step": 534858, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.104970932006836, "global_step": 534859, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0826926231384277, "global_step": 534860, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0945558547973633, "global_step": 534861, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.037933588027954, "global_step": 534862, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0560789108276367, "global_step": 534863, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.061828851699829, "global_step": 534864, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.122347593307495, "global_step": 534865, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0783982276916504, "global_step": 534866, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.059353828430176, "global_step": 534867, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0676956176757812, "global_step": 534868, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9829456806182861, "global_step": 534869, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9817031621932983, "global_step": 534870, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0913429260253906, "global_step": 534871, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0164849758148193, "global_step": 534872, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0218968391418457, "global_step": 534873, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.022103786468506, "global_step": 534874, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.117948532104492, "global_step": 534875, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9958163499832153, "global_step": 534876, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1056249141693115, "global_step": 534877, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0068938732147217, "global_step": 534878, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.048814058303833, "global_step": 534879, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0553081035614014, "global_step": 534880, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.078418254852295, "global_step": 534881, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.020904779434204, "global_step": 534882, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0750234127044678, "global_step": 534883, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1757302284240723, "global_step": 534884, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0404977798461914, "global_step": 534885, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.083451509475708, "global_step": 534886, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.069847822189331, "global_step": 534887, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0701000690460205, "global_step": 534888, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.036526918411255, "global_step": 534889, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.101205587387085, "global_step": 534890, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0762197971343994, "global_step": 534891, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.049987316131592, "global_step": 534892, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9188423156738281, "global_step": 534893, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9753628969192505, "global_step": 534894, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.131599187850952, "global_step": 534895, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0726075172424316, "global_step": 534896, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.025679588317871, "global_step": 534897, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0677833557128906, "global_step": 534898, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0930120944976807, "global_step": 534899, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.009188652038574, "global_step": 534900, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0366122722625732, "global_step": 534901, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0197393894195557, "global_step": 534902, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0667660236358643, "global_step": 534903, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1106345653533936, "global_step": 534904, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.026428699493408, "global_step": 534905, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.041884422302246, "global_step": 534906, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0457494258880615, "global_step": 534907, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9395698308944702, "global_step": 534908, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.003134250640869, "global_step": 534909, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0165247917175293, "global_step": 534910, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0555169582366943, "global_step": 534911, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.00764799118042, "global_step": 534912, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.027460813522339, "global_step": 534913, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.04181170463562, "global_step": 534914, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0471065044403076, "global_step": 534915, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.043287992477417, "global_step": 534916, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.114537000656128, "global_step": 534917, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.064706325531006, "global_step": 534918, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.057694673538208, "global_step": 534919, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0437583923339844, "global_step": 534920, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9660879373550415, "global_step": 534921, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.049269914627075, "global_step": 534922, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.066267490386963, "global_step": 534923, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9843720197677612, "global_step": 534924, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.020638942718506, "global_step": 534925, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.971631407737732, "global_step": 534926, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.101469039916992, "global_step": 534927, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0876545906066895, "global_step": 534928, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0753366947174072, "global_step": 534929, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0289337635040283, "global_step": 534930, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0164785385131836, "global_step": 534931, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1340928077697754, "global_step": 534932, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.026263475418091, "global_step": 534933, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9759867191314697, "global_step": 534934, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0781562328338623, "global_step": 534935, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0131590366363525, "global_step": 534936, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.006293535232544, "global_step": 534937, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9573560953140259, "global_step": 534938, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9659554958343506, "global_step": 534939, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0740978717803955, "global_step": 534940, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.043994903564453, "global_step": 534941, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.012850046157837, "global_step": 534942, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9541964530944824, "global_step": 534943, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0212080478668213, "global_step": 534944, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9481427669525146, "global_step": 534945, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0001590251922607, "global_step": 534946, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9910476207733154, "global_step": 534947, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.043571710586548, "global_step": 534948, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.103975772857666, "global_step": 534949, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.061245918273926, "global_step": 534950, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0687930583953857, "global_step": 534951, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0001657009124756, "global_step": 534952, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.070862293243408, "global_step": 534953, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0489063262939453, "global_step": 534954, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0706965923309326, "global_step": 534955, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0081067085266113, "global_step": 534956, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.115483045578003, "global_step": 534957, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9843723773956299, "global_step": 534958, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.005898952484131, "global_step": 534959, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0828068256378174, "global_step": 534960, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1064951419830322, "global_step": 534961, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9936405420303345, "global_step": 534962, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.07003116607666, "global_step": 534963, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.008420944213867, "global_step": 534964, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0143682956695557, "global_step": 534965, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.060957908630371, "global_step": 534966, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.055771827697754, "global_step": 534967, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.072685480117798, "global_step": 534968, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.021883487701416, "global_step": 534969, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.02516508102417, "global_step": 534970, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0902185440063477, "global_step": 534971, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9972679615020752, "global_step": 534972, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0298218727111816, "global_step": 534973, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.024798631668091, "global_step": 534974, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.033163070678711, "global_step": 534975, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0137553215026855, "global_step": 534976, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.040775775909424, "global_step": 534977, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.07468581199646, "global_step": 534978, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.102459192276001, "global_step": 534979, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0833332538604736, "global_step": 534980, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.98263418674469, "global_step": 534981, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0697684288024902, "global_step": 534982, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0121750831604004, "global_step": 534983, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9545865058898926, "global_step": 534984, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.034055471420288, "global_step": 534985, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1272552013397217, "global_step": 534986, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.068577527999878, "global_step": 534987, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.076066017150879, "global_step": 534988, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0380430221557617, "global_step": 534989, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0074870586395264, "global_step": 534990, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0274271965026855, "global_step": 534991, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.06367826461792, "global_step": 534992, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0424320697784424, "global_step": 534993, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0804545879364014, "global_step": 534994, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0732662677764893, "global_step": 534995, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.013432025909424, "global_step": 534996, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0387003421783447, "global_step": 534997, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9329184293746948, "global_step": 534998, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.023638963699341, "global_step": 534999, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0472428798675537, "global_step": 535000, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0364904403686523, "global_step": 535001, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.975588083267212, "global_step": 535002, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0723211765289307, "global_step": 535003, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0768086910247803, "global_step": 535004, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0696587562561035, "global_step": 535005, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9762269258499146, "global_step": 535006, "epoch": 901, "lr": 5e-05}
{"train_loss": 1.9962263107299805, "global_step": 535007, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.039966344833374, "global_step": 535008, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.052757501602173, "global_step": 535009, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0973188877105713, "global_step": 535010, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.056457281112671, "global_step": 535011, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.016064167022705, "global_step": 535012, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.140822649002075, "global_step": 535013, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.075047016143799, "global_step": 535014, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.047140121459961, "global_step": 535015, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.013972282409668, "global_step": 535016, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.051740884780884, "global_step": 535017, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.1008641719818115, "global_step": 535018, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0883724689483643, "global_step": 535019, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.038560390472412, "global_step": 535020, "epoch": 901, "lr": 5e-05}
{"train_loss": 2.0098068714141846, "global_step": 535021, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.991646647453308, "global_step": 535022, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9484485387802124, "global_step": 535023, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0111031532287598, "global_step": 535024, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.026076078414917, "global_step": 535025, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9930202960968018, "global_step": 535026, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9711015224456787, "global_step": 535027, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0556721687316895, "global_step": 535028, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9920337200164795, "global_step": 535029, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9245696067810059, "global_step": 535030, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.978733777999878, "global_step": 535031, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0413994789123535, "global_step": 535032, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0053019523620605, "global_step": 535033, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.109142780303955, "global_step": 535034, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.118579149246216, "global_step": 535035, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.037114143371582, "global_step": 535036, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.992063045501709, "global_step": 535037, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9545038938522339, "global_step": 535038, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0073983669281006, "global_step": 535039, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0701470375061035, "global_step": 535040, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0937376022338867, "global_step": 535041, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1234283447265625, "global_step": 535042, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0432043075561523, "global_step": 535043, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0616188049316406, "global_step": 535044, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.107966423034668, "global_step": 535045, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.018918752670288, "global_step": 535046, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.064300775527954, "global_step": 535047, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.066065788269043, "global_step": 535048, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0894014835357666, "global_step": 535049, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0732357501983643, "global_step": 535050, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0097084045410156, "global_step": 535051, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9821611642837524, "global_step": 535052, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9427943229675293, "global_step": 535053, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1210086345672607, "global_step": 535054, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.993172287940979, "global_step": 535055, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0797619819641113, "global_step": 535056, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0655975341796875, "global_step": 535057, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9708011150360107, "global_step": 535058, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.008138418197632, "global_step": 535059, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1233229637145996, "global_step": 535060, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9696820974349976, "global_step": 535061, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.109665870666504, "global_step": 535062, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0069823265075684, "global_step": 535063, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9837723970413208, "global_step": 535064, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.063598871231079, "global_step": 535065, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1705408096313477, "global_step": 535066, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0035574436187744, "global_step": 535067, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.031155824661255, "global_step": 535068, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0173301696777344, "global_step": 535069, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9817287921905518, "global_step": 535070, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.015683174133301, "global_step": 535071, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.012930393218994, "global_step": 535072, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.079704999923706, "global_step": 535073, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.148265838623047, "global_step": 535074, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0189707279205322, "global_step": 535075, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9937478303909302, "global_step": 535076, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9743098020553589, "global_step": 535077, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.051098108291626, "global_step": 535078, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.108811378479004, "global_step": 535079, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.027371406555176, "global_step": 535080, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.991831660270691, "global_step": 535081, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9946725368499756, "global_step": 535082, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0599923133850098, "global_step": 535083, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9704400300979614, "global_step": 535084, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1121673583984375, "global_step": 535085, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.994543433189392, "global_step": 535086, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0391523838043213, "global_step": 535087, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.057647228240967, "global_step": 535088, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9909420013427734, "global_step": 535089, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9844948053359985, "global_step": 535090, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.090752601623535, "global_step": 535091, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9788048267364502, "global_step": 535092, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.918984055519104, "global_step": 535093, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0740489959716797, "global_step": 535094, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0226526260375977, "global_step": 535095, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.043269634246826, "global_step": 535096, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9765056371688843, "global_step": 535097, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0259013175964355, "global_step": 535098, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9777345657348633, "global_step": 535099, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9743883609771729, "global_step": 535100, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.117810010910034, "global_step": 535101, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9915636777877808, "global_step": 535102, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.026992082595825, "global_step": 535103, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.072402000427246, "global_step": 535104, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9958034753799438, "global_step": 535105, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.998030662536621, "global_step": 535106, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0318193435668945, "global_step": 535107, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0632379055023193, "global_step": 535108, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0346436500549316, "global_step": 535109, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.014390707015991, "global_step": 535110, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.90964674949646, "global_step": 535111, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0157735347747803, "global_step": 535112, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.085188388824463, "global_step": 535113, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0610427856445312, "global_step": 535114, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.056119680404663, "global_step": 535115, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0366368293762207, "global_step": 535116, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9637185335159302, "global_step": 535117, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9718763828277588, "global_step": 535118, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.144254207611084, "global_step": 535119, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.065035343170166, "global_step": 535120, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9842246770858765, "global_step": 535121, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0974040031433105, "global_step": 535122, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1019179821014404, "global_step": 535123, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.056839942932129, "global_step": 535124, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9545278549194336, "global_step": 535125, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0640227794647217, "global_step": 535126, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0250537395477295, "global_step": 535127, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0279786586761475, "global_step": 535128, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1226367950439453, "global_step": 535129, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0232160091400146, "global_step": 535130, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0746660232543945, "global_step": 535131, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0392324924468994, "global_step": 535132, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9786877632141113, "global_step": 535133, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9776978492736816, "global_step": 535134, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.049492359161377, "global_step": 535135, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0278680324554443, "global_step": 535136, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0522165298461914, "global_step": 535137, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.034806251525879, "global_step": 535138, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.06670880317688, "global_step": 535139, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.076753854751587, "global_step": 535140, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0247983932495117, "global_step": 535141, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0170791149139404, "global_step": 535142, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.066091775894165, "global_step": 535143, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0019469261169434, "global_step": 535144, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.045790672302246, "global_step": 535145, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9955004453659058, "global_step": 535146, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.05487060546875, "global_step": 535147, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0543971061706543, "global_step": 535148, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9191018342971802, "global_step": 535149, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1600162982940674, "global_step": 535150, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0760385990142822, "global_step": 535151, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0617775917053223, "global_step": 535152, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0381858348846436, "global_step": 535153, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9736615419387817, "global_step": 535154, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.068458318710327, "global_step": 535155, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.968101978302002, "global_step": 535156, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.078564405441284, "global_step": 535157, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0833375453948975, "global_step": 535158, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9681612253189087, "global_step": 535159, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9742838144302368, "global_step": 535160, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0384178161621094, "global_step": 535161, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0569815635681152, "global_step": 535162, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0609757900238037, "global_step": 535163, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9737417697906494, "global_step": 535164, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0023598670959473, "global_step": 535165, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.95662522315979, "global_step": 535166, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9347347021102905, "global_step": 535167, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1101744174957275, "global_step": 535168, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.027691602706909, "global_step": 535169, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.101614236831665, "global_step": 535170, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9410775899887085, "global_step": 535171, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.057488203048706, "global_step": 535172, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1034491062164307, "global_step": 535173, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.012415647506714, "global_step": 535174, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.013017416000366, "global_step": 535175, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.045663833618164, "global_step": 535176, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.962485909461975, "global_step": 535177, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1678853034973145, "global_step": 535178, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9872275590896606, "global_step": 535179, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.123765468597412, "global_step": 535180, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.03608775138855, "global_step": 535181, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9930577278137207, "global_step": 535182, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0583913326263428, "global_step": 535183, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9674196243286133, "global_step": 535184, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.946001648902893, "global_step": 535185, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9980180263519287, "global_step": 535186, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0047836303710938, "global_step": 535187, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9941269159317017, "global_step": 535188, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.987009048461914, "global_step": 535189, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0768558979034424, "global_step": 535190, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0472519397735596, "global_step": 535191, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9599543809890747, "global_step": 535192, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.095477819442749, "global_step": 535193, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0264737606048584, "global_step": 535194, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1032965183258057, "global_step": 535195, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9902957677841187, "global_step": 535196, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.089374542236328, "global_step": 535197, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9780710935592651, "global_step": 535198, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0365161895751953, "global_step": 535199, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.016808032989502, "global_step": 535200, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.042628526687622, "global_step": 535201, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.031827449798584, "global_step": 535202, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9431568384170532, "global_step": 535203, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1046335697174072, "global_step": 535204, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.019709348678589, "global_step": 535205, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.042059898376465, "global_step": 535206, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0166501998901367, "global_step": 535207, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0321590900421143, "global_step": 535208, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.971411943435669, "global_step": 535209, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.02596378326416, "global_step": 535210, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.009732723236084, "global_step": 535211, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0150835514068604, "global_step": 535212, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0557899475097656, "global_step": 535213, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0161821842193604, "global_step": 535214, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0057051181793213, "global_step": 535215, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0320146083831787, "global_step": 535216, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0340003967285156, "global_step": 535217, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0321710109710693, "global_step": 535218, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9595714807510376, "global_step": 535219, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9773324728012085, "global_step": 535220, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9761379957199097, "global_step": 535221, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.037778377532959, "global_step": 535222, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0744035243988037, "global_step": 535223, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.937253713607788, "global_step": 535224, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.061617851257324, "global_step": 535225, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0012855529785156, "global_step": 535226, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0969793796539307, "global_step": 535227, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.005460739135742, "global_step": 535228, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.059450149536133, "global_step": 535229, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.068288803100586, "global_step": 535230, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0803041458129883, "global_step": 535231, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9967050552368164, "global_step": 535232, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9803438186645508, "global_step": 535233, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9980759620666504, "global_step": 535234, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.990074634552002, "global_step": 535235, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0019690990448, "global_step": 535236, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9633477926254272, "global_step": 535237, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.132380723953247, "global_step": 535238, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.046482801437378, "global_step": 535239, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0891664028167725, "global_step": 535240, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.048367738723755, "global_step": 535241, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9887733459472656, "global_step": 535242, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.002624988555908, "global_step": 535243, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.182588815689087, "global_step": 535244, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0411500930786133, "global_step": 535245, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9712960720062256, "global_step": 535246, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0181403160095215, "global_step": 535247, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0011563301086426, "global_step": 535248, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.002472400665283, "global_step": 535249, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0543088912963867, "global_step": 535250, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.00071382522583, "global_step": 535251, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0094876289367676, "global_step": 535252, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.020392656326294, "global_step": 535253, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.077986001968384, "global_step": 535254, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0178792476654053, "global_step": 535255, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0238161087036133, "global_step": 535256, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0793936252593994, "global_step": 535257, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0346803665161133, "global_step": 535258, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0329904556274414, "global_step": 535259, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0712409019470215, "global_step": 535260, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.985119342803955, "global_step": 535261, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9648488759994507, "global_step": 535262, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.035099506378174, "global_step": 535263, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0233945846557617, "global_step": 535264, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0237600803375244, "global_step": 535265, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.052154541015625, "global_step": 535266, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.088254451751709, "global_step": 535267, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1635220050811768, "global_step": 535268, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9954776763916016, "global_step": 535269, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0643250942230225, "global_step": 535270, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9659509658813477, "global_step": 535271, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.004709243774414, "global_step": 535272, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0425519943237305, "global_step": 535273, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0404250621795654, "global_step": 535274, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9921365976333618, "global_step": 535275, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9721194505691528, "global_step": 535276, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0895028114318848, "global_step": 535277, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9519731998443604, "global_step": 535278, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.032433271408081, "global_step": 535279, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.992098331451416, "global_step": 535280, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9671145677566528, "global_step": 535281, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.964572548866272, "global_step": 535282, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0525171756744385, "global_step": 535283, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.069509506225586, "global_step": 535284, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9473918676376343, "global_step": 535285, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9908040761947632, "global_step": 535286, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9581263065338135, "global_step": 535287, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1147406101226807, "global_step": 535288, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9770004749298096, "global_step": 535289, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0717010498046875, "global_step": 535290, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0780060291290283, "global_step": 535291, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.046617031097412, "global_step": 535292, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9883594512939453, "global_step": 535293, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0357508659362793, "global_step": 535294, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.077158212661743, "global_step": 535295, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9582443237304688, "global_step": 535296, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0756702423095703, "global_step": 535297, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0160017013549805, "global_step": 535298, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0185632705688477, "global_step": 535299, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0353617668151855, "global_step": 535300, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.986953616142273, "global_step": 535301, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.013759136199951, "global_step": 535302, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9791538715362549, "global_step": 535303, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0494766235351562, "global_step": 535304, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.070327043533325, "global_step": 535305, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0448036193847656, "global_step": 535306, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0927305221557617, "global_step": 535307, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.958070993423462, "global_step": 535308, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.941282868385315, "global_step": 535309, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.044466257095337, "global_step": 535310, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.081413984298706, "global_step": 535311, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.036879777908325, "global_step": 535312, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9355322122573853, "global_step": 535313, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0370750427246094, "global_step": 535314, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0254878997802734, "global_step": 535315, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9103490114212036, "global_step": 535316, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0451619625091553, "global_step": 535317, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0021936893463135, "global_step": 535318, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1079213619232178, "global_step": 535319, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.06078839302063, "global_step": 535320, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.993888020515442, "global_step": 535321, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9581259489059448, "global_step": 535322, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.036255121231079, "global_step": 535323, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.029085397720337, "global_step": 535324, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0432519912719727, "global_step": 535325, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0128731727600098, "global_step": 535326, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1226418018341064, "global_step": 535327, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.084423542022705, "global_step": 535328, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0127408504486084, "global_step": 535329, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.983723759651184, "global_step": 535330, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1025607585906982, "global_step": 535331, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.119001626968384, "global_step": 535332, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.962415337562561, "global_step": 535333, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.066145181655884, "global_step": 535334, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9561660289764404, "global_step": 535335, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9954209327697754, "global_step": 535336, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.049936532974243, "global_step": 535337, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9421944618225098, "global_step": 535338, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9820561408996582, "global_step": 535339, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9658616781234741, "global_step": 535340, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0746634006500244, "global_step": 535341, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0036885738372803, "global_step": 535342, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.052971124649048, "global_step": 535343, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.987510323524475, "global_step": 535344, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0254578590393066, "global_step": 535345, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.00579571723938, "global_step": 535346, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.066063165664673, "global_step": 535347, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9737849235534668, "global_step": 535348, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0586936473846436, "global_step": 535349, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.095869541168213, "global_step": 535350, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.048429250717163, "global_step": 535351, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1157429218292236, "global_step": 535352, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0463273525238037, "global_step": 535353, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.991947889328003, "global_step": 535354, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0751068592071533, "global_step": 535355, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.049647331237793, "global_step": 535356, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.024829626083374, "global_step": 535357, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0681874752044678, "global_step": 535358, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0824825763702393, "global_step": 535359, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9637525081634521, "global_step": 535360, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.028886318206787, "global_step": 535361, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9815059900283813, "global_step": 535362, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.033548355102539, "global_step": 535363, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0707173347473145, "global_step": 535364, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0004658699035645, "global_step": 535365, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.992720603942871, "global_step": 535366, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9909722805023193, "global_step": 535367, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.088789224624634, "global_step": 535368, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0087602138519287, "global_step": 535369, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0803565979003906, "global_step": 535370, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0564236640930176, "global_step": 535371, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9428019523620605, "global_step": 535372, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.113872766494751, "global_step": 535373, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9889416694641113, "global_step": 535374, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0344903469085693, "global_step": 535375, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.110546827316284, "global_step": 535376, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.067457914352417, "global_step": 535377, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0350747108459473, "global_step": 535378, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.061645030975342, "global_step": 535379, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9173583984375, "global_step": 535380, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9528472423553467, "global_step": 535381, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0496108531951904, "global_step": 535382, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.047929048538208, "global_step": 535383, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1180567741394043, "global_step": 535384, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0660288333892822, "global_step": 535385, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9433393478393555, "global_step": 535386, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9861187934875488, "global_step": 535387, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9788131713867188, "global_step": 535388, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0329713821411133, "global_step": 535389, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.078702449798584, "global_step": 535390, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0592639446258545, "global_step": 535391, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0442702770233154, "global_step": 535392, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.022963285446167, "global_step": 535393, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0110087394714355, "global_step": 535394, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0792059898376465, "global_step": 535395, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0108275413513184, "global_step": 535396, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1040890216827393, "global_step": 535397, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.084167242050171, "global_step": 535398, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.107307195663452, "global_step": 535399, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9909398555755615, "global_step": 535400, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0350534915924072, "global_step": 535401, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0842552185058594, "global_step": 535402, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.010699510574341, "global_step": 535403, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0133249759674072, "global_step": 535404, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.071404218673706, "global_step": 535405, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1015377044677734, "global_step": 535406, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9676464796066284, "global_step": 535407, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9898208379745483, "global_step": 535408, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9704264402389526, "global_step": 535409, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.00834584236145, "global_step": 535410, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.119765520095825, "global_step": 535411, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9488126039505005, "global_step": 535412, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0685956478118896, "global_step": 535413, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.024022102355957, "global_step": 535414, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0428152084350586, "global_step": 535415, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.092991590499878, "global_step": 535416, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.055342197418213, "global_step": 535417, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0802249908447266, "global_step": 535418, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.009462356567383, "global_step": 535419, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0128984451293945, "global_step": 535420, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0216901302337646, "global_step": 535421, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1367812156677246, "global_step": 535422, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0362396240234375, "global_step": 535423, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9530616998672485, "global_step": 535424, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9655678272247314, "global_step": 535425, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.010373115539551, "global_step": 535426, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0139598846435547, "global_step": 535427, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1109540462493896, "global_step": 535428, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.079411506652832, "global_step": 535429, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.088104009628296, "global_step": 535430, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0165083408355713, "global_step": 535431, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.037419557571411, "global_step": 535432, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0230326652526855, "global_step": 535433, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.075389862060547, "global_step": 535434, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1449992656707764, "global_step": 535435, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9973779916763306, "global_step": 535436, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0713703632354736, "global_step": 535437, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0986878871917725, "global_step": 535438, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0247931480407715, "global_step": 535439, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.012045383453369, "global_step": 535440, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0297582149505615, "global_step": 535441, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0664849281311035, "global_step": 535442, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.096938371658325, "global_step": 535443, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.071312665939331, "global_step": 535444, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1065313816070557, "global_step": 535445, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.009669065475464, "global_step": 535446, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.060650110244751, "global_step": 535447, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.017987012863159, "global_step": 535448, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.977604627609253, "global_step": 535449, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1102356910705566, "global_step": 535450, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1036195755004883, "global_step": 535451, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.948782205581665, "global_step": 535452, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.051621198654175, "global_step": 535453, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0031092166900635, "global_step": 535454, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.99771249294281, "global_step": 535455, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0253584384918213, "global_step": 535456, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9901100397109985, "global_step": 535457, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0900566577911377, "global_step": 535458, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.147270917892456, "global_step": 535459, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0237035751342773, "global_step": 535460, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9867244958877563, "global_step": 535461, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.997668981552124, "global_step": 535462, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.060009241104126, "global_step": 535463, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.011699914932251, "global_step": 535464, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0045008659362793, "global_step": 535465, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1339850425720215, "global_step": 535466, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0392825603485107, "global_step": 535467, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0421931743621826, "global_step": 535468, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0645205974578857, "global_step": 535469, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0501534938812256, "global_step": 535470, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1251323223114014, "global_step": 535471, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.035290479660034, "global_step": 535472, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.01045560836792, "global_step": 535473, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9694477319717407, "global_step": 535474, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0614373683929443, "global_step": 535475, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1092963218688965, "global_step": 535476, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0530741214752197, "global_step": 535477, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9717472791671753, "global_step": 535478, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.078028440475464, "global_step": 535479, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.001770496368408, "global_step": 535480, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.04247784614563, "global_step": 535481, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0111141204833984, "global_step": 535482, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.009981632232666, "global_step": 535483, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0132150650024414, "global_step": 535484, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0534698963165283, "global_step": 535485, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.038970708847046, "global_step": 535486, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0007481575012207, "global_step": 535487, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0665788650512695, "global_step": 535488, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0663018226623535, "global_step": 535489, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9217535257339478, "global_step": 535490, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.019987106323242, "global_step": 535491, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.95510733127594, "global_step": 535492, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.007631301879883, "global_step": 535493, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9920274019241333, "global_step": 535494, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0479323863983154, "global_step": 535495, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0718235969543457, "global_step": 535496, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.026024103164673, "global_step": 535497, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0367400646209717, "global_step": 535498, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0487070083618164, "global_step": 535499, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1250152587890625, "global_step": 535500, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0331521034240723, "global_step": 535501, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1089348793029785, "global_step": 535502, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.025714159011841, "global_step": 535503, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0232067108154297, "global_step": 535504, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.085479974746704, "global_step": 535505, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.039133310317993, "global_step": 535506, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0066335201263428, "global_step": 535507, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.128680467605591, "global_step": 535508, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0341262817382812, "global_step": 535509, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.051759958267212, "global_step": 535510, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.047499895095825, "global_step": 535511, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9803783893585205, "global_step": 535512, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0675837993621826, "global_step": 535513, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0176703929901123, "global_step": 535514, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.047954559326172, "global_step": 535515, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9854083061218262, "global_step": 535516, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.077698230743408, "global_step": 535517, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0644540786743164, "global_step": 535518, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0591881275177, "global_step": 535519, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.051574230194092, "global_step": 535520, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9914637804031372, "global_step": 535521, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0126073360443115, "global_step": 535522, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0641486644744873, "global_step": 535523, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.01031231880188, "global_step": 535524, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0743234157562256, "global_step": 535525, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.996553659439087, "global_step": 535526, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.04443621635437, "global_step": 535527, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.070996046066284, "global_step": 535528, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.048069953918457, "global_step": 535529, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0420451164245605, "global_step": 535530, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0008881092071533, "global_step": 535531, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1438565254211426, "global_step": 535532, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.002258777618408, "global_step": 535533, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0617098808288574, "global_step": 535534, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0746419429779053, "global_step": 535535, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0348403453826904, "global_step": 535536, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0292165279388428, "global_step": 535537, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.092205047607422, "global_step": 535538, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0686633586883545, "global_step": 535539, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.020564317703247, "global_step": 535540, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9840258359909058, "global_step": 535541, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0720748901367188, "global_step": 535542, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0119009017944336, "global_step": 535543, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0349316596984863, "global_step": 535544, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9767591953277588, "global_step": 535545, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0082221031188965, "global_step": 535546, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0208072662353516, "global_step": 535547, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0167768001556396, "global_step": 535548, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1284773349761963, "global_step": 535549, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.055230140686035, "global_step": 535550, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.042275905609131, "global_step": 535551, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9461047649383545, "global_step": 535552, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9863401651382446, "global_step": 535553, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0897932052612305, "global_step": 535554, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.020275592803955, "global_step": 535555, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0753023624420166, "global_step": 535556, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0055296421051025, "global_step": 535557, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.05456805229187, "global_step": 535558, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9957436323165894, "global_step": 535559, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.067739725112915, "global_step": 535560, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1045870780944824, "global_step": 535561, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.041360378265381, "global_step": 535562, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.017171621322632, "global_step": 535563, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.062021255493164, "global_step": 535564, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9646636247634888, "global_step": 535565, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9530152082443237, "global_step": 535566, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.076493501663208, "global_step": 535567, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.111102819442749, "global_step": 535568, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.014044761657715, "global_step": 535569, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.139923095703125, "global_step": 535570, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9881322383880615, "global_step": 535571, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1122360229492188, "global_step": 535572, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.982640027999878, "global_step": 535573, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0572147369384766, "global_step": 535574, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.035910129547119, "global_step": 535575, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0101139545440674, "global_step": 535576, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.038355827331543, "global_step": 535577, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.018315076828003, "global_step": 535578, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0886433124542236, "global_step": 535579, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0441782474517822, "global_step": 535580, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.93435537815094, "global_step": 535581, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0121898651123047, "global_step": 535582, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.099174737930298, "global_step": 535583, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0645623207092285, "global_step": 535584, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9818785190582275, "global_step": 535585, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0053765773773193, "global_step": 535586, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.03659987449646, "global_step": 535587, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0471863746643066, "global_step": 535588, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.06858229637146, "global_step": 535589, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0614726543426514, "global_step": 535590, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9944623708724976, "global_step": 535591, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.031609296798706, "global_step": 535592, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0079739093780518, "global_step": 535593, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.025897741317749, "global_step": 535594, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.024420976638794, "global_step": 535595, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0780820846557617, "global_step": 535596, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.129077434539795, "global_step": 535597, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1016416549682617, "global_step": 535598, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0723392963409424, "global_step": 535599, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.018120527267456, "global_step": 535600, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9607341289520264, "global_step": 535601, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9834944009780884, "global_step": 535602, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9589059352874756, "global_step": 535603, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.041872501373291, "global_step": 535604, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0870392322540283, "global_step": 535605, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.948238730430603, "global_step": 535606, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0877456665039062, "global_step": 535607, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0868959426879883, "global_step": 535608, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9987825155258179, "global_step": 535609, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9821970462799072, "global_step": 535610, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9087694883346558, "global_step": 535611, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.084528684616089, "global_step": 535612, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.057648181915283, "global_step": 535613, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.007208824157715, "global_step": 535614, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.973549485206604, "global_step": 535615, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0741822719573975, "global_step": 535616, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.08023738861084, "global_step": 535617, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.094895124435425, "global_step": 535618, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0759437084198, "global_step": 535619, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.016514539718628, "global_step": 535620, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0368008613586426, "global_step": 535621, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1105692386627197, "global_step": 535622, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0914466381073, "global_step": 535623, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1000382900238037, "global_step": 535624, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.043898105621338, "global_step": 535625, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0707297325134277, "global_step": 535626, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.044173240661621, "global_step": 535627, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.049945592880249, "global_step": 535628, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9859181642532349, "global_step": 535629, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.049936056137085, "global_step": 535630, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9223464727401733, "global_step": 535631, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9751969575881958, "global_step": 535632, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.052800178527832, "global_step": 535633, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1196470260620117, "global_step": 535634, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0429821014404297, "global_step": 535635, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0350594520568848, "global_step": 535636, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0768213272094727, "global_step": 535637, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0035200119018555, "global_step": 535638, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0382206439971924, "global_step": 535639, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.030454635620117, "global_step": 535640, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0395283699035645, "global_step": 535641, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.008376359939575, "global_step": 535642, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.049267292022705, "global_step": 535643, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9984073638916016, "global_step": 535644, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.040013074874878, "global_step": 535645, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0683069229125977, "global_step": 535646, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0346570014953613, "global_step": 535647, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1414220333099365, "global_step": 535648, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0349817276000977, "global_step": 535649, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.023467779159546, "global_step": 535650, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.049006700515747, "global_step": 535651, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1320719718933105, "global_step": 535652, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1305174827575684, "global_step": 535653, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.06083083152771, "global_step": 535654, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1002724170684814, "global_step": 535655, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.068729877471924, "global_step": 535656, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.080359935760498, "global_step": 535657, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0248770713806152, "global_step": 535658, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.047994375228882, "global_step": 535659, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0587658882141113, "global_step": 535660, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.03780198097229, "global_step": 535661, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.025634765625, "global_step": 535662, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.030590772628784, "global_step": 535663, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9960371255874634, "global_step": 535664, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9991233348846436, "global_step": 535665, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0968399047851562, "global_step": 535666, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.051668643951416, "global_step": 535667, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0947937965393066, "global_step": 535668, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0127737522125244, "global_step": 535669, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9765291213989258, "global_step": 535670, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0486207008361816, "global_step": 535671, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.037412166595459, "global_step": 535672, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.976676106452942, "global_step": 535673, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.033313274383545, "global_step": 535674, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0402095317840576, "global_step": 535675, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0315804481506348, "global_step": 535676, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1242969036102295, "global_step": 535677, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.944698691368103, "global_step": 535678, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9791650772094727, "global_step": 535679, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0198700428009033, "global_step": 535680, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.030369520187378, "global_step": 535681, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.046212673187256, "global_step": 535682, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.039151906967163, "global_step": 535683, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9843018054962158, "global_step": 535684, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0727994441986084, "global_step": 535685, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0417110919952393, "global_step": 535686, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0380077362060547, "global_step": 535687, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.158470869064331, "global_step": 535688, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1133556365966797, "global_step": 535689, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0330286026000977, "global_step": 535690, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.928074598312378, "global_step": 535691, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0249505043029785, "global_step": 535692, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0063817501068115, "global_step": 535693, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0759873390197754, "global_step": 535694, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0507652759552, "global_step": 535695, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0842223167419434, "global_step": 535696, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.072580099105835, "global_step": 535697, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0804216861724854, "global_step": 535698, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.109510660171509, "global_step": 535699, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9242300987243652, "global_step": 535700, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0071206092834473, "global_step": 535701, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.093245267868042, "global_step": 535702, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9899860620498657, "global_step": 535703, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0559074878692627, "global_step": 535704, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0826973915100098, "global_step": 535705, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.070208787918091, "global_step": 535706, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1435556411743164, "global_step": 535707, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.057715654373169, "global_step": 535708, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.052175521850586, "global_step": 535709, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0574464797973633, "global_step": 535710, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0639941692352295, "global_step": 535711, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9930777549743652, "global_step": 535712, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0178442001342773, "global_step": 535713, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0788488388061523, "global_step": 535714, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9625134468078613, "global_step": 535715, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9389710426330566, "global_step": 535716, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9695266485214233, "global_step": 535717, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9484847784042358, "global_step": 535718, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0754661560058594, "global_step": 535719, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.195190668106079, "global_step": 535720, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.026278495788574, "global_step": 535721, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.043245553970337, "global_step": 535722, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.073699712753296, "global_step": 535723, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9402347803115845, "global_step": 535724, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0306239128112793, "global_step": 535725, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1043379306793213, "global_step": 535726, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0300204753875732, "global_step": 535727, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0683650970458984, "global_step": 535728, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9257620573043823, "global_step": 535729, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.107823133468628, "global_step": 535730, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0267789363861084, "global_step": 535731, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9695262908935547, "global_step": 535732, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.052037239074707, "global_step": 535733, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9416072368621826, "global_step": 535734, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.036998748779297, "global_step": 535735, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0682461261749268, "global_step": 535736, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9724736213684082, "global_step": 535737, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.984520435333252, "global_step": 535738, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.051079273223877, "global_step": 535739, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1083550453186035, "global_step": 535740, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.050994634628296, "global_step": 535741, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.07253360748291, "global_step": 535742, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.044874668121338, "global_step": 535743, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0406503677368164, "global_step": 535744, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0075626373291016, "global_step": 535745, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.112332344055176, "global_step": 535746, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0344176292419434, "global_step": 535747, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9717226028442383, "global_step": 535748, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1466259956359863, "global_step": 535749, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9786816835403442, "global_step": 535750, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0564332008361816, "global_step": 535751, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9756619930267334, "global_step": 535752, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.004917621612549, "global_step": 535753, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0282976627349854, "global_step": 535754, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0524418354034424, "global_step": 535755, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.006121873855591, "global_step": 535756, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0127217769622803, "global_step": 535757, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.046874761581421, "global_step": 535758, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9728072881698608, "global_step": 535759, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.039074659347534, "global_step": 535760, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9515289068222046, "global_step": 535761, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1120803356170654, "global_step": 535762, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9984773397445679, "global_step": 535763, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0213253498077393, "global_step": 535764, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0923824310302734, "global_step": 535765, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0476324558258057, "global_step": 535766, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0587596893310547, "global_step": 535767, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0320119857788086, "global_step": 535768, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0530550479888916, "global_step": 535769, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0494613647460938, "global_step": 535770, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0918445587158203, "global_step": 535771, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9879772663116455, "global_step": 535772, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.131588935852051, "global_step": 535773, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.101241111755371, "global_step": 535774, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9705872535705566, "global_step": 535775, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0143165588378906, "global_step": 535776, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.047041654586792, "global_step": 535777, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.055060386657715, "global_step": 535778, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9930211305618286, "global_step": 535779, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.027698516845703, "global_step": 535780, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0501980781555176, "global_step": 535781, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0166900157928467, "global_step": 535782, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9729936122894287, "global_step": 535783, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0349907875061035, "global_step": 535784, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1620168685913086, "global_step": 535785, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9788634777069092, "global_step": 535786, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0437581539154053, "global_step": 535787, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0267434120178223, "global_step": 535788, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0306553840637207, "global_step": 535789, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0862936973571777, "global_step": 535790, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.095996856689453, "global_step": 535791, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9379639625549316, "global_step": 535792, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9773420095443726, "global_step": 535793, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0318522453308105, "global_step": 535794, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.037919759750366, "global_step": 535795, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.011845111846924, "global_step": 535796, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9789599180221558, "global_step": 535797, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0802721977233887, "global_step": 535798, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.163515567779541, "global_step": 535799, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1131162643432617, "global_step": 535800, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0383129119873047, "global_step": 535801, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.025200366973877, "global_step": 535802, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0348751544952393, "global_step": 535803, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.032012939453125, "global_step": 535804, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.079533100128174, "global_step": 535805, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1031360626220703, "global_step": 535806, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.027550458908081, "global_step": 535807, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0670578479766846, "global_step": 535808, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.037959098815918, "global_step": 535809, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0323381423950195, "global_step": 535810, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0471951961517334, "global_step": 535811, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.13535475730896, "global_step": 535812, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0351767539978027, "global_step": 535813, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9637806415557861, "global_step": 535814, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.08280873298645, "global_step": 535815, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1319797039031982, "global_step": 535816, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0725464820861816, "global_step": 535817, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.069136142730713, "global_step": 535818, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0418665409088135, "global_step": 535819, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.026921510696411, "global_step": 535820, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.045809745788574, "global_step": 535821, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0615360736846924, "global_step": 535822, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0276458263397217, "global_step": 535823, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1019082069396973, "global_step": 535824, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.994946002960205, "global_step": 535825, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.034538507461548, "global_step": 535826, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0422797203063965, "global_step": 535827, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.085071325302124, "global_step": 535828, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.06321382522583, "global_step": 535829, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0148985385894775, "global_step": 535830, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0052356719970703, "global_step": 535831, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0978026390075684, "global_step": 535832, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.992230772972107, "global_step": 535833, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.066760301589966, "global_step": 535834, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.951933741569519, "global_step": 535835, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.019212484359741, "global_step": 535836, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.070256233215332, "global_step": 535837, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0708861351013184, "global_step": 535838, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.194652557373047, "global_step": 535839, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0466148853302, "global_step": 535840, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.008150815963745, "global_step": 535841, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.119218349456787, "global_step": 535842, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9772496223449707, "global_step": 535843, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0383684635162354, "global_step": 535844, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0349462032318115, "global_step": 535845, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0014069080352783, "global_step": 535846, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0637876987457275, "global_step": 535847, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.059149980545044, "global_step": 535848, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.00581693649292, "global_step": 535849, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.093491315841675, "global_step": 535850, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0074679851531982, "global_step": 535851, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9984092712402344, "global_step": 535852, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9896454811096191, "global_step": 535853, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.049962043762207, "global_step": 535854, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9557583332061768, "global_step": 535855, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0495717525482178, "global_step": 535856, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9600147008895874, "global_step": 535857, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1069397926330566, "global_step": 535858, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.214179277420044, "global_step": 535859, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0306453704833984, "global_step": 535860, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.002098560333252, "global_step": 535861, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0511817932128906, "global_step": 535862, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.070509910583496, "global_step": 535863, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.051340341567993, "global_step": 535864, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9842443466186523, "global_step": 535865, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0595786571502686, "global_step": 535866, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9719001054763794, "global_step": 535867, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.024156093597412, "global_step": 535868, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.128807783126831, "global_step": 535869, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0191705226898193, "global_step": 535870, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.045144557952881, "global_step": 535871, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.013002395629883, "global_step": 535872, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0192887783050537, "global_step": 535873, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.086683511734009, "global_step": 535874, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0782108306884766, "global_step": 535875, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.025343179702759, "global_step": 535876, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0520260334014893, "global_step": 535877, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9351511001586914, "global_step": 535878, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.133044958114624, "global_step": 535879, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.041646718978882, "global_step": 535880, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0536768436431885, "global_step": 535881, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.102006435394287, "global_step": 535882, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9971147775650024, "global_step": 535883, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0818705558776855, "global_step": 535884, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0710203647613525, "global_step": 535885, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0145552158355713, "global_step": 535886, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1230597496032715, "global_step": 535887, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.057255506515503, "global_step": 535888, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0072450637817383, "global_step": 535889, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.048006057739258, "global_step": 535890, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.07122802734375, "global_step": 535891, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0902724266052246, "global_step": 535892, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.098923921585083, "global_step": 535893, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.036433458328247, "global_step": 535894, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0534865856170654, "global_step": 535895, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0037012100219727, "global_step": 535896, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.039372682571411, "global_step": 535897, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0933597087860107, "global_step": 535898, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0688600540161133, "global_step": 535899, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.994872808456421, "global_step": 535900, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9801926612854004, "global_step": 535901, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0793347358703613, "global_step": 535902, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0138120651245117, "global_step": 535903, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.000673770904541, "global_step": 535904, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.015385389328003, "global_step": 535905, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.046405076980591, "global_step": 535906, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.035489797592163, "global_step": 535907, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0624377727508545, "global_step": 535908, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0748744010925293, "global_step": 535909, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.149564027786255, "global_step": 535910, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0036072731018066, "global_step": 535911, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0124385356903076, "global_step": 535912, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0597615242004395, "global_step": 535913, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0554826259613037, "global_step": 535914, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0382778644561768, "global_step": 535915, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.030315399169922, "global_step": 535916, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9643528461456299, "global_step": 535917, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.026315212249756, "global_step": 535918, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.106593608856201, "global_step": 535919, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.071554660797119, "global_step": 535920, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.061028242111206, "global_step": 535921, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0190322399139404, "global_step": 535922, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.188683271408081, "global_step": 535923, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.042977809906006, "global_step": 535924, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.074453830718994, "global_step": 535925, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0611844062805176, "global_step": 535926, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.945791244506836, "global_step": 535927, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.020642042160034, "global_step": 535928, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0935535430908203, "global_step": 535929, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0439717769622803, "global_step": 535930, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9479607343673706, "global_step": 535931, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0848805904388428, "global_step": 535932, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.111621141433716, "global_step": 535933, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.171027421951294, "global_step": 535934, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.008063793182373, "global_step": 535935, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.014417886734009, "global_step": 535936, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0439553260803223, "global_step": 535937, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0052831172943115, "global_step": 535938, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0784592628479004, "global_step": 535939, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1311287879943848, "global_step": 535940, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0051162242889404, "global_step": 535941, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.037052631378174, "global_step": 535942, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9959850311279297, "global_step": 535943, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1197357177734375, "global_step": 535944, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0161924362182617, "global_step": 535945, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9963452816009521, "global_step": 535946, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9948465824127197, "global_step": 535947, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0289182662963867, "global_step": 535948, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0480380058288574, "global_step": 535949, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.187737464904785, "global_step": 535950, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1136984825134277, "global_step": 535951, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.017338514328003, "global_step": 535952, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.012714147567749, "global_step": 535953, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0698654651641846, "global_step": 535954, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0636725425720215, "global_step": 535955, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.027711868286133, "global_step": 535956, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0765485763549805, "global_step": 535957, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0006003379821777, "global_step": 535958, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.073090076446533, "global_step": 535959, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.026992082595825, "global_step": 535960, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9834953546524048, "global_step": 535961, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0280346870422363, "global_step": 535962, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9989060163497925, "global_step": 535963, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9407821893692017, "global_step": 535964, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0961172580718994, "global_step": 535965, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0807485580444336, "global_step": 535966, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0652103424072266, "global_step": 535967, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.059457540512085, "global_step": 535968, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0259644985198975, "global_step": 535969, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.107520341873169, "global_step": 535970, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0020337104797363, "global_step": 535971, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.075421094894409, "global_step": 535972, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0536749362945557, "global_step": 535973, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9912995100021362, "global_step": 535974, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.1067094802856445, "global_step": 535975, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0389347076416016, "global_step": 535976, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0865650177001953, "global_step": 535977, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0431714057922363, "global_step": 535978, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.969327688217163, "global_step": 535979, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9734880924224854, "global_step": 535980, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9753509759902954, "global_step": 535981, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.992772102355957, "global_step": 535982, "epoch": 902, "lr": 5e-05}
{"train_loss": 1.9838193655014038, "global_step": 535983, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0488808155059814, "global_step": 535984, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.039243221282959, "global_step": 535985, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0260567665100098, "global_step": 535986, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.073704242706299, "global_step": 535987, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.0734786987304688, "global_step": 535988, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.036611318588257, "global_step": 535989, "epoch": 902, "lr": 5e-05}
{"train_loss": 2.084444522857666, "global_step": 535990, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0522561073303223, "global_step": 535991, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9854965209960938, "global_step": 535992, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.127650499343872, "global_step": 535993, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.988566279411316, "global_step": 535994, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9460828304290771, "global_step": 535995, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.003018617630005, "global_step": 535996, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0509872436523438, "global_step": 535997, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0462284088134766, "global_step": 535998, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0536868572235107, "global_step": 535999, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.123178720474243, "global_step": 536000, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9849181175231934, "global_step": 536001, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1082937717437744, "global_step": 536002, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0046019554138184, "global_step": 536003, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0231542587280273, "global_step": 536004, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0527396202087402, "global_step": 536005, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.107041358947754, "global_step": 536006, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0581727027893066, "global_step": 536007, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0115466117858887, "global_step": 536008, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.067295551300049, "global_step": 536009, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.982969045639038, "global_step": 536010, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0581655502319336, "global_step": 536011, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.037020444869995, "global_step": 536012, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.027991771697998, "global_step": 536013, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9746018648147583, "global_step": 536014, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9130083322525024, "global_step": 536015, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.028869152069092, "global_step": 536016, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9853612184524536, "global_step": 536017, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.094221830368042, "global_step": 536018, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.042318820953369, "global_step": 536019, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0320796966552734, "global_step": 536020, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0805976390838623, "global_step": 536021, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0120720863342285, "global_step": 536022, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0093860626220703, "global_step": 536023, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0147135257720947, "global_step": 536024, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9822437763214111, "global_step": 536025, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9767918586730957, "global_step": 536026, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9976950883865356, "global_step": 536027, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0561139583587646, "global_step": 536028, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1122260093688965, "global_step": 536029, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1057217121124268, "global_step": 536030, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9715710878372192, "global_step": 536031, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.981750249862671, "global_step": 536032, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9988665580749512, "global_step": 536033, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0449512004852295, "global_step": 536034, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.048482656478882, "global_step": 536035, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.011289596557617, "global_step": 536036, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9919028282165527, "global_step": 536037, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9914354085922241, "global_step": 536038, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.971650242805481, "global_step": 536039, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9967952966690063, "global_step": 536040, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.124354600906372, "global_step": 536041, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.967885971069336, "global_step": 536042, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9880009889602661, "global_step": 536043, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.017622947692871, "global_step": 536044, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.007148265838623, "global_step": 536045, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.040766477584839, "global_step": 536046, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.968829870223999, "global_step": 536047, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0294408798217773, "global_step": 536048, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0160257816314697, "global_step": 536049, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.050405740737915, "global_step": 536050, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0003232955932617, "global_step": 536051, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0551164150238037, "global_step": 536052, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.022261381149292, "global_step": 536053, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9586858749389648, "global_step": 536054, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.038156509399414, "global_step": 536055, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9419747591018677, "global_step": 536056, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9815654754638672, "global_step": 536057, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.001044273376465, "global_step": 536058, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.046112298965454, "global_step": 536059, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0876896381378174, "global_step": 536060, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0241544246673584, "global_step": 536061, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9814777374267578, "global_step": 536062, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9885402917861938, "global_step": 536063, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9917585849761963, "global_step": 536064, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.06018328666687, "global_step": 536065, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.045560359954834, "global_step": 536066, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.956533432006836, "global_step": 536067, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.110041618347168, "global_step": 536068, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.055866003036499, "global_step": 536069, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9991918802261353, "global_step": 536070, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.079922676086426, "global_step": 536071, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0615530014038086, "global_step": 536072, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0516552925109863, "global_step": 536073, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.06278133392334, "global_step": 536074, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.041576623916626, "global_step": 536075, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.039285898208618, "global_step": 536076, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9428592920303345, "global_step": 536077, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.945594310760498, "global_step": 536078, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9978320598602295, "global_step": 536079, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1200883388519287, "global_step": 536080, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.016876697540283, "global_step": 536081, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.958497166633606, "global_step": 536082, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9752132892608643, "global_step": 536083, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0678892135620117, "global_step": 536084, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.116014242172241, "global_step": 536085, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0232887268066406, "global_step": 536086, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0222949981689453, "global_step": 536087, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.019763708114624, "global_step": 536088, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.067136526107788, "global_step": 536089, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.091412305831909, "global_step": 536090, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.985582709312439, "global_step": 536091, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.025167226791382, "global_step": 536092, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1501779556274414, "global_step": 536093, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0495007038116455, "global_step": 536094, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0548293590545654, "global_step": 536095, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0706820487976074, "global_step": 536096, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.043057918548584, "global_step": 536097, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0497794151306152, "global_step": 536098, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.030092239379883, "global_step": 536099, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0413107872009277, "global_step": 536100, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0203006267547607, "global_step": 536101, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9790807962417603, "global_step": 536102, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9668796062469482, "global_step": 536103, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0433871746063232, "global_step": 536104, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9498895406723022, "global_step": 536105, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.062770128250122, "global_step": 536106, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1301636695861816, "global_step": 536107, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.001514434814453, "global_step": 536108, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9559886455535889, "global_step": 536109, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0330076217651367, "global_step": 536110, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0417532920837402, "global_step": 536111, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.048914670944214, "global_step": 536112, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0049986839294434, "global_step": 536113, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.076622724533081, "global_step": 536114, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0541746616363525, "global_step": 536115, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0230534076690674, "global_step": 536116, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0140268802642822, "global_step": 536117, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.02980637550354, "global_step": 536118, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.038717746734619, "global_step": 536119, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.040642023086548, "global_step": 536120, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0441794395446777, "global_step": 536121, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.122683048248291, "global_step": 536122, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9916324615478516, "global_step": 536123, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.997584581375122, "global_step": 536124, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9333044290542603, "global_step": 536125, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.999177098274231, "global_step": 536126, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0096089839935303, "global_step": 536127, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0928795337677, "global_step": 536128, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0604772567749023, "global_step": 536129, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0909225940704346, "global_step": 536130, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9473761320114136, "global_step": 536131, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.085329532623291, "global_step": 536132, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0762035846710205, "global_step": 536133, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.048373222351074, "global_step": 536134, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9986157417297363, "global_step": 536135, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0195388793945312, "global_step": 536136, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0755491256713867, "global_step": 536137, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.033557176589966, "global_step": 536138, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9709277153015137, "global_step": 536139, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.103994131088257, "global_step": 536140, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9810210466384888, "global_step": 536141, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.948553442955017, "global_step": 536142, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9999597072601318, "global_step": 536143, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.965167760848999, "global_step": 536144, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0982306003570557, "global_step": 536145, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0603671073913574, "global_step": 536146, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1089391708374023, "global_step": 536147, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0462005138397217, "global_step": 536148, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.033310890197754, "global_step": 536149, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.034224510192871, "global_step": 536150, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.028895854949951, "global_step": 536151, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.980224847793579, "global_step": 536152, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.061372995376587, "global_step": 536153, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.031442642211914, "global_step": 536154, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0096383094787598, "global_step": 536155, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.014833450317383, "global_step": 536156, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0559287071228027, "global_step": 536157, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.017235040664673, "global_step": 536158, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.06817889213562, "global_step": 536159, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9855972528457642, "global_step": 536160, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9809337854385376, "global_step": 536161, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1429481506347656, "global_step": 536162, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.945801019668579, "global_step": 536163, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0685675144195557, "global_step": 536164, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1125965118408203, "global_step": 536165, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9383717775344849, "global_step": 536166, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0222513675689697, "global_step": 536167, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.97018563747406, "global_step": 536168, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0396978855133057, "global_step": 536169, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9616596698760986, "global_step": 536170, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.974768042564392, "global_step": 536171, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0688161849975586, "global_step": 536172, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0809922218322754, "global_step": 536173, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.028214931488037, "global_step": 536174, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0565383434295654, "global_step": 536175, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0738189220428467, "global_step": 536176, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9509913921356201, "global_step": 536177, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.005183696746826, "global_step": 536178, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.996485948562622, "global_step": 536179, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9864957332611084, "global_step": 536180, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.040349245071411, "global_step": 536181, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9682799577713013, "global_step": 536182, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0343432426452637, "global_step": 536183, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0258405208587646, "global_step": 536184, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0231542587280273, "global_step": 536185, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9874165058135986, "global_step": 536186, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0447754859924316, "global_step": 536187, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.045154333114624, "global_step": 536188, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0912725925445557, "global_step": 536189, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0542774200439453, "global_step": 536190, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9325639009475708, "global_step": 536191, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1006264686584473, "global_step": 536192, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9936201572418213, "global_step": 536193, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0776753425598145, "global_step": 536194, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9448580741882324, "global_step": 536195, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9632370471954346, "global_step": 536196, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1037538051605225, "global_step": 536197, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0554819107055664, "global_step": 536198, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9807708263397217, "global_step": 536199, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9705132246017456, "global_step": 536200, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.012821674346924, "global_step": 536201, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.024129867553711, "global_step": 536202, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.969733715057373, "global_step": 536203, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0304689407348633, "global_step": 536204, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.96649968624115, "global_step": 536205, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0316648483276367, "global_step": 536206, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.030944585800171, "global_step": 536207, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0603227615356445, "global_step": 536208, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.043457508087158, "global_step": 536209, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.017488479614258, "global_step": 536210, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.094763994216919, "global_step": 536211, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.107715129852295, "global_step": 536212, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.053914785385132, "global_step": 536213, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.03136944770813, "global_step": 536214, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0344557762145996, "global_step": 536215, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1284141540527344, "global_step": 536216, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0298240184783936, "global_step": 536217, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0212795734405518, "global_step": 536218, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.008047580718994, "global_step": 536219, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0845937728881836, "global_step": 536220, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9730695486068726, "global_step": 536221, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.084613561630249, "global_step": 536222, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.031325101852417, "global_step": 536223, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0810017585754395, "global_step": 536224, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9937031269073486, "global_step": 536225, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0466041564941406, "global_step": 536226, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9466471672058105, "global_step": 536227, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0086183547973633, "global_step": 536228, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0198774337768555, "global_step": 536229, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9863280057907104, "global_step": 536230, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.032184600830078, "global_step": 536231, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0352206230163574, "global_step": 536232, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.150907516479492, "global_step": 536233, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0308048725128174, "global_step": 536234, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0069541931152344, "global_step": 536235, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0050101280212402, "global_step": 536236, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.035160779953003, "global_step": 536237, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0319273471832275, "global_step": 536238, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9742534160614014, "global_step": 536239, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.955212950706482, "global_step": 536240, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.080702781677246, "global_step": 536241, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0564472675323486, "global_step": 536242, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0784823894500732, "global_step": 536243, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0574405193328857, "global_step": 536244, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.055978298187256, "global_step": 536245, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.039781093597412, "global_step": 536246, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0105698108673096, "global_step": 536247, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.020613670349121, "global_step": 536248, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9610705375671387, "global_step": 536249, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.027467727661133, "global_step": 536250, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.056274175643921, "global_step": 536251, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.064460515975952, "global_step": 536252, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1516642570495605, "global_step": 536253, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9939604997634888, "global_step": 536254, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9915732145309448, "global_step": 536255, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0278756618499756, "global_step": 536256, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.068906784057617, "global_step": 536257, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0409765243530273, "global_step": 536258, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.963668704032898, "global_step": 536259, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0770602226257324, "global_step": 536260, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9959712028503418, "global_step": 536261, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.058577537536621, "global_step": 536262, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.069065809249878, "global_step": 536263, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0782675743103027, "global_step": 536264, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0513010025024414, "global_step": 536265, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.970770001411438, "global_step": 536266, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0703744888305664, "global_step": 536267, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.038675308227539, "global_step": 536268, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0578887462615967, "global_step": 536269, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.092780351638794, "global_step": 536270, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.105767011642456, "global_step": 536271, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.05668568611145, "global_step": 536272, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.017094612121582, "global_step": 536273, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0193276405334473, "global_step": 536274, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1352627277374268, "global_step": 536275, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0744996070861816, "global_step": 536276, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0687859058380127, "global_step": 536277, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9900137186050415, "global_step": 536278, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9762213230133057, "global_step": 536279, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9521160125732422, "global_step": 536280, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.952937126159668, "global_step": 536281, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0360331535339355, "global_step": 536282, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1054162979125977, "global_step": 536283, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.01481556892395, "global_step": 536284, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.074178457260132, "global_step": 536285, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0399856567382812, "global_step": 536286, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0666024684906006, "global_step": 536287, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.100898504257202, "global_step": 536288, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0114595890045166, "global_step": 536289, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0642974376678467, "global_step": 536290, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0557782649993896, "global_step": 536291, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0004630088806152, "global_step": 536292, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1287789344787598, "global_step": 536293, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0230178833007812, "global_step": 536294, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0187206268310547, "global_step": 536295, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0463805198669434, "global_step": 536296, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0118026733398438, "global_step": 536297, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9967783689498901, "global_step": 536298, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.108596086502075, "global_step": 536299, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9934499263763428, "global_step": 536300, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.000469207763672, "global_step": 536301, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.062891721725464, "global_step": 536302, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0434980392456055, "global_step": 536303, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.055776834487915, "global_step": 536304, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.086888313293457, "global_step": 536305, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0118203163146973, "global_step": 536306, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.098496675491333, "global_step": 536307, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.978881597518921, "global_step": 536308, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9830056428909302, "global_step": 536309, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0546109676361084, "global_step": 536310, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.070382833480835, "global_step": 536311, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1793863773345947, "global_step": 536312, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.035032033920288, "global_step": 536313, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0192158222198486, "global_step": 536314, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0298779010772705, "global_step": 536315, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0418386459350586, "global_step": 536316, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0167360305786133, "global_step": 536317, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0483384132385254, "global_step": 536318, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0132012367248535, "global_step": 536319, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.023481607437134, "global_step": 536320, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0648345947265625, "global_step": 536321, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9855363368988037, "global_step": 536322, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9443960189819336, "global_step": 536323, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0618014335632324, "global_step": 536324, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0576555728912354, "global_step": 536325, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.918332576751709, "global_step": 536326, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.102647066116333, "global_step": 536327, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9675655364990234, "global_step": 536328, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.033707618713379, "global_step": 536329, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0141594409942627, "global_step": 536330, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9666402339935303, "global_step": 536331, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1374573707580566, "global_step": 536332, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0453999042510986, "global_step": 536333, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.079425096511841, "global_step": 536334, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0124690532684326, "global_step": 536335, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.069831609725952, "global_step": 536336, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0666604042053223, "global_step": 536337, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.011497735977173, "global_step": 536338, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9900777339935303, "global_step": 536339, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0249202251434326, "global_step": 536340, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0087828636169434, "global_step": 536341, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.018747091293335, "global_step": 536342, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.068918466567993, "global_step": 536343, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0466325283050537, "global_step": 536344, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.038648843765259, "global_step": 536345, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0363545417785645, "global_step": 536346, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9529685974121094, "global_step": 536347, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0426526069641113, "global_step": 536348, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0083749294281006, "global_step": 536349, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0257863998413086, "global_step": 536350, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9876720905303955, "global_step": 536351, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.990668535232544, "global_step": 536352, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0045597553253174, "global_step": 536353, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1157572269439697, "global_step": 536354, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9897940158843994, "global_step": 536355, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0748414993286133, "global_step": 536356, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0361328125, "global_step": 536357, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9858708381652832, "global_step": 536358, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.009376049041748, "global_step": 536359, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.022566080093384, "global_step": 536360, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0822298526763916, "global_step": 536361, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9871742725372314, "global_step": 536362, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.024040699005127, "global_step": 536363, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9534578323364258, "global_step": 536364, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.046988010406494, "global_step": 536365, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.069369316101074, "global_step": 536366, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.967763900756836, "global_step": 536367, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0293898582458496, "global_step": 536368, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0429296493530273, "global_step": 536369, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.035639762878418, "global_step": 536370, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0877349376678467, "global_step": 536371, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9912045001983643, "global_step": 536372, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.06852126121521, "global_step": 536373, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.05189847946167, "global_step": 536374, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.162156820297241, "global_step": 536375, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9532362222671509, "global_step": 536376, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0593817234039307, "global_step": 536377, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0007009506225586, "global_step": 536378, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0197741985321045, "global_step": 536379, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9601906538009644, "global_step": 536380, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.067065954208374, "global_step": 536381, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.992545485496521, "global_step": 536382, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0659265518188477, "global_step": 536383, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.034528970718384, "global_step": 536384, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.019528388977051, "global_step": 536385, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1193058490753174, "global_step": 536386, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0312340259552, "global_step": 536387, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9487136602401733, "global_step": 536388, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.069972038269043, "global_step": 536389, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.140328884124756, "global_step": 536390, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0156638622283936, "global_step": 536391, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0076916217803955, "global_step": 536392, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.986518144607544, "global_step": 536393, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.069551467895508, "global_step": 536394, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0245816707611084, "global_step": 536395, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0667552947998047, "global_step": 536396, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1050198078155518, "global_step": 536397, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1232707500457764, "global_step": 536398, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0470619201660156, "global_step": 536399, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9424580335617065, "global_step": 536400, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0780320167541504, "global_step": 536401, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0041635036468506, "global_step": 536402, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0710842609405518, "global_step": 536403, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.972962498664856, "global_step": 536404, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9964224100112915, "global_step": 536405, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1264469623565674, "global_step": 536406, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.088593006134033, "global_step": 536407, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0918173789978027, "global_step": 536408, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0806679725646973, "global_step": 536409, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9906002283096313, "global_step": 536410, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0213382244110107, "global_step": 536411, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9759509563446045, "global_step": 536412, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.215399980545044, "global_step": 536413, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9924695491790771, "global_step": 536414, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0094544887542725, "global_step": 536415, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.085714340209961, "global_step": 536416, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.091336727142334, "global_step": 536417, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1026506423950195, "global_step": 536418, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.004366636276245, "global_step": 536419, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.039905309677124, "global_step": 536420, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0915286540985107, "global_step": 536421, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.038968086242676, "global_step": 536422, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0726969242095947, "global_step": 536423, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0475387573242188, "global_step": 536424, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.04459547996521, "global_step": 536425, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9574453830718994, "global_step": 536426, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0244805812835693, "global_step": 536427, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0593395233154297, "global_step": 536428, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0865345001220703, "global_step": 536429, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.005197763442993, "global_step": 536430, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9880377054214478, "global_step": 536431, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0036332607269287, "global_step": 536432, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.053473949432373, "global_step": 536433, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.118983745574951, "global_step": 536434, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0292985439300537, "global_step": 536435, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.030041456222534, "global_step": 536436, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9601575136184692, "global_step": 536437, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.067392349243164, "global_step": 536438, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1030430793762207, "global_step": 536439, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0877394676208496, "global_step": 536440, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0327975749969482, "global_step": 536441, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0678718090057373, "global_step": 536442, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0243308544158936, "global_step": 536443, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0673515796661377, "global_step": 536444, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.064955472946167, "global_step": 536445, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.07790207862854, "global_step": 536446, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.969651222229004, "global_step": 536447, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.082162618637085, "global_step": 536448, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.029597759246826, "global_step": 536449, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0503337383270264, "global_step": 536450, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.043076753616333, "global_step": 536451, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1075634956359863, "global_step": 536452, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9973849058151245, "global_step": 536453, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0861728191375732, "global_step": 536454, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.950221061706543, "global_step": 536455, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.019164800643921, "global_step": 536456, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0475380420684814, "global_step": 536457, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0842337608337402, "global_step": 536458, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9559085369110107, "global_step": 536459, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0302538871765137, "global_step": 536460, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.003019094467163, "global_step": 536461, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.051532030105591, "global_step": 536462, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.00754714012146, "global_step": 536463, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0200374126434326, "global_step": 536464, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0322701930999756, "global_step": 536465, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.024280309677124, "global_step": 536466, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.958266019821167, "global_step": 536467, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.05206036567688, "global_step": 536468, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.036820411682129, "global_step": 536469, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.110938310623169, "global_step": 536470, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0098485946655273, "global_step": 536471, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0301151275634766, "global_step": 536472, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1100611686706543, "global_step": 536473, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.087620973587036, "global_step": 536474, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0910532474517822, "global_step": 536475, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9862476587295532, "global_step": 536476, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0554468631744385, "global_step": 536477, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0656518936157227, "global_step": 536478, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9971933364868164, "global_step": 536479, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.089122772216797, "global_step": 536480, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9279497861862183, "global_step": 536481, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0352840423583984, "global_step": 536482, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.066927671432495, "global_step": 536483, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.071597099304199, "global_step": 536484, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.026876926422119, "global_step": 536485, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0337018966674805, "global_step": 536486, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0662941932678223, "global_step": 536487, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0488295555114746, "global_step": 536488, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1518306732177734, "global_step": 536489, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0980169773101807, "global_step": 536490, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0851330757141113, "global_step": 536491, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9428813457489014, "global_step": 536492, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.005199909210205, "global_step": 536493, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.074349880218506, "global_step": 536494, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.066230297088623, "global_step": 536495, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9916698932647705, "global_step": 536496, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0053794384002686, "global_step": 536497, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.084503412246704, "global_step": 536498, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.09424090385437, "global_step": 536499, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0880000591278076, "global_step": 536500, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.013254404067993, "global_step": 536501, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.01737117767334, "global_step": 536502, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1359481811523438, "global_step": 536503, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1480894088745117, "global_step": 536504, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0376791954040527, "global_step": 536505, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9833015203475952, "global_step": 536506, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.014500856399536, "global_step": 536507, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9971373081207275, "global_step": 536508, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0457100868225098, "global_step": 536509, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.078348159790039, "global_step": 536510, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.993470311164856, "global_step": 536511, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0481345653533936, "global_step": 536512, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.022589683532715, "global_step": 536513, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0409862995147705, "global_step": 536514, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.020582675933838, "global_step": 536515, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0029735565185547, "global_step": 536516, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0312583446502686, "global_step": 536517, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.002645969390869, "global_step": 536518, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9364959001541138, "global_step": 536519, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.019749641418457, "global_step": 536520, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.007779121398926, "global_step": 536521, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0086333751678467, "global_step": 536522, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9699057340621948, "global_step": 536523, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.020761251449585, "global_step": 536524, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.09026837348938, "global_step": 536525, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0190491676330566, "global_step": 536526, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0485341548919678, "global_step": 536527, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9827743768692017, "global_step": 536528, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0871174335479736, "global_step": 536529, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.058742046356201, "global_step": 536530, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0349514484405518, "global_step": 536531, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9318283796310425, "global_step": 536532, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.115206003189087, "global_step": 536533, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.071117639541626, "global_step": 536534, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.114875555038452, "global_step": 536535, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9961665868759155, "global_step": 536536, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.015159845352173, "global_step": 536537, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9958420991897583, "global_step": 536538, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0778989791870117, "global_step": 536539, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.973189115524292, "global_step": 536540, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9575462341308594, "global_step": 536541, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1003005504608154, "global_step": 536542, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.011549472808838, "global_step": 536543, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0806946754455566, "global_step": 536544, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.041210889816284, "global_step": 536545, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.003170967102051, "global_step": 536546, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.092104434967041, "global_step": 536547, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9823918342590332, "global_step": 536548, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0327138900756836, "global_step": 536549, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0094172954559326, "global_step": 536550, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0341761112213135, "global_step": 536551, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.005854368209839, "global_step": 536552, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.97189199924469, "global_step": 536553, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.006685972213745, "global_step": 536554, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.051414966583252, "global_step": 536555, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.101372241973877, "global_step": 536556, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0289700031280518, "global_step": 536557, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0242013931274414, "global_step": 536558, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.011688232421875, "global_step": 536559, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9941227436065674, "global_step": 536560, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9778447151184082, "global_step": 536561, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.022285223007202, "global_step": 536562, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1033051013946533, "global_step": 536563, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0744378566741943, "global_step": 536564, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.006526231765747, "global_step": 536565, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.06101655960083, "global_step": 536566, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0441884994506836, "global_step": 536567, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0385663509368896, "global_step": 536568, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9763429164886475, "global_step": 536569, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.155790090560913, "global_step": 536570, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.009437322616577, "global_step": 536571, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.064768075942993, "global_step": 536572, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.082418918609619, "global_step": 536573, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0793368816375732, "global_step": 536574, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0703790187835693, "global_step": 536575, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0708303451538086, "global_step": 536576, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9338809251785278, "global_step": 536577, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.086402654647827, "global_step": 536578, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1095755100250244, "global_step": 536579, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0444281101226807, "global_step": 536580, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.01826810836792, "global_step": 536581, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.131761074066162, "global_step": 536582, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1052820682525635, "global_step": 536583, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.002671241760254, "global_step": 536584, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9511011838912964, "global_step": 536585, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9395705461502075, "global_step": 536586, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0387439727783203, "global_step": 536587, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0267505645751953, "global_step": 536588, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.084929943084717, "global_step": 536589, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1088802814483643, "global_step": 536590, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.059541702270508, "global_step": 536591, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0758097171783447, "global_step": 536592, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0368993282318115, "global_step": 536593, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0060298442840576, "global_step": 536594, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0280768871307373, "global_step": 536595, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.009390354156494, "global_step": 536596, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0460638999938965, "global_step": 536597, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9995231628417969, "global_step": 536598, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.099623203277588, "global_step": 536599, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.113344192504883, "global_step": 536600, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.923029899597168, "global_step": 536601, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0503640174865723, "global_step": 536602, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9959644079208374, "global_step": 536603, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1275181770324707, "global_step": 536604, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0775015354156494, "global_step": 536605, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0497376918792725, "global_step": 536606, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9860249757766724, "global_step": 536607, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0654542446136475, "global_step": 536608, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0369014739990234, "global_step": 536609, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.088353395462036, "global_step": 536610, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0784878730773926, "global_step": 536611, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0422143936157227, "global_step": 536612, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.045564889907837, "global_step": 536613, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0913643836975098, "global_step": 536614, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.089240550994873, "global_step": 536615, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0066919326782227, "global_step": 536616, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.108276844024658, "global_step": 536617, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.056123971939087, "global_step": 536618, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.063337564468384, "global_step": 536619, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0567657947540283, "global_step": 536620, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1060941219329834, "global_step": 536621, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9941648244857788, "global_step": 536622, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0075347423553467, "global_step": 536623, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.109998941421509, "global_step": 536624, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0757110118865967, "global_step": 536625, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9830920696258545, "global_step": 536626, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9898829460144043, "global_step": 536627, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.947589635848999, "global_step": 536628, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0329060554504395, "global_step": 536629, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.13146710395813, "global_step": 536630, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9952446222305298, "global_step": 536631, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.082146644592285, "global_step": 536632, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.041292667388916, "global_step": 536633, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.042092800140381, "global_step": 536634, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.039215564727783, "global_step": 536635, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.056446075439453, "global_step": 536636, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9708410501480103, "global_step": 536637, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9813120365142822, "global_step": 536638, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0052192211151123, "global_step": 536639, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1154673099517822, "global_step": 536640, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0195353031158447, "global_step": 536641, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.049034595489502, "global_step": 536642, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9798080921173096, "global_step": 536643, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0112204551696777, "global_step": 536644, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9954895973205566, "global_step": 536645, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9993895292282104, "global_step": 536646, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.009700059890747, "global_step": 536647, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0465431213378906, "global_step": 536648, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0190482139587402, "global_step": 536649, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0496232509613037, "global_step": 536650, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0095674991607666, "global_step": 536651, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0059776306152344, "global_step": 536652, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9959853887557983, "global_step": 536653, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9902721643447876, "global_step": 536654, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0424768924713135, "global_step": 536655, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.12890887260437, "global_step": 536656, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0525500774383545, "global_step": 536657, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.036508321762085, "global_step": 536658, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0365970134735107, "global_step": 536659, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0605452060699463, "global_step": 536660, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.047358751296997, "global_step": 536661, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.033853054046631, "global_step": 536662, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1270551681518555, "global_step": 536663, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0754616260528564, "global_step": 536664, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.144214391708374, "global_step": 536665, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0825345516204834, "global_step": 536666, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.052013874053955, "global_step": 536667, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.00905704498291, "global_step": 536668, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0267016887664795, "global_step": 536669, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0231475830078125, "global_step": 536670, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0086796283721924, "global_step": 536671, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0374133586883545, "global_step": 536672, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.099090099334717, "global_step": 536673, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.066701889038086, "global_step": 536674, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0436484813690186, "global_step": 536675, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9488048553466797, "global_step": 536676, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0226104259490967, "global_step": 536677, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.075638771057129, "global_step": 536678, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0961265563964844, "global_step": 536679, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.060624837875366, "global_step": 536680, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0487825870513916, "global_step": 536681, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1009302139282227, "global_step": 536682, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0056281089782715, "global_step": 536683, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0606820583343506, "global_step": 536684, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9881080389022827, "global_step": 536685, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0245938301086426, "global_step": 536686, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0448215007781982, "global_step": 536687, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.129488706588745, "global_step": 536688, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0194897651672363, "global_step": 536689, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0629260540008545, "global_step": 536690, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0026941299438477, "global_step": 536691, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.056206703186035, "global_step": 536692, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9940531253814697, "global_step": 536693, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.076545000076294, "global_step": 536694, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.01609206199646, "global_step": 536695, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0388636589050293, "global_step": 536696, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.03019380569458, "global_step": 536697, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.048218011856079, "global_step": 536698, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9889202117919922, "global_step": 536699, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.082636594772339, "global_step": 536700, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9416985511779785, "global_step": 536701, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0539040565490723, "global_step": 536702, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.028271436691284, "global_step": 536703, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.984535813331604, "global_step": 536704, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0043082237243652, "global_step": 536705, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9983700513839722, "global_step": 536706, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.966674566268921, "global_step": 536707, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.078686475753784, "global_step": 536708, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0287022590637207, "global_step": 536709, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1584601402282715, "global_step": 536710, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.027290105819702, "global_step": 536711, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.096823215484619, "global_step": 536712, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0776073932647705, "global_step": 536713, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0286026000976562, "global_step": 536714, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0547852516174316, "global_step": 536715, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0616018772125244, "global_step": 536716, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.039910078048706, "global_step": 536717, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9976179599761963, "global_step": 536718, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9665790796279907, "global_step": 536719, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0259389877319336, "global_step": 536720, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0640501976013184, "global_step": 536721, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0415101051330566, "global_step": 536722, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.082742691040039, "global_step": 536723, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.078192949295044, "global_step": 536724, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.048888683319092, "global_step": 536725, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9428751468658447, "global_step": 536726, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.033996105194092, "global_step": 536727, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0055108070373535, "global_step": 536728, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9611247777938843, "global_step": 536729, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0541677474975586, "global_step": 536730, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.995846152305603, "global_step": 536731, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9945626258850098, "global_step": 536732, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9893231391906738, "global_step": 536733, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9750620126724243, "global_step": 536734, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0109996795654297, "global_step": 536735, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.048548460006714, "global_step": 536736, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0008323192596436, "global_step": 536737, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9892433881759644, "global_step": 536738, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0666723251342773, "global_step": 536739, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.073411703109741, "global_step": 536740, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.016298294067383, "global_step": 536741, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.102104425430298, "global_step": 536742, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.078035593032837, "global_step": 536743, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1275739669799805, "global_step": 536744, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.953580617904663, "global_step": 536745, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.081421375274658, "global_step": 536746, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0971736907958984, "global_step": 536747, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0534844398498535, "global_step": 536748, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0644235610961914, "global_step": 536749, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0833444595336914, "global_step": 536750, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9504886865615845, "global_step": 536751, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.05118465423584, "global_step": 536752, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.948101282119751, "global_step": 536753, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.001737356185913, "global_step": 536754, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.072780132293701, "global_step": 536755, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.2003462314605713, "global_step": 536756, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1424968242645264, "global_step": 536757, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.077894687652588, "global_step": 536758, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.022524833679199, "global_step": 536759, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.09234356880188, "global_step": 536760, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9878771305084229, "global_step": 536761, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.000896692276001, "global_step": 536762, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0866000652313232, "global_step": 536763, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1336474418640137, "global_step": 536764, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0801608562469482, "global_step": 536765, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.066779375076294, "global_step": 536766, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0792691707611084, "global_step": 536767, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.020998001098633, "global_step": 536768, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.959823727607727, "global_step": 536769, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9393059015274048, "global_step": 536770, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0745341777801514, "global_step": 536771, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0063254833221436, "global_step": 536772, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0849380493164062, "global_step": 536773, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0686964988708496, "global_step": 536774, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0164949893951416, "global_step": 536775, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0340144634246826, "global_step": 536776, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9675345420837402, "global_step": 536777, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9685535430908203, "global_step": 536778, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0472207069396973, "global_step": 536779, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9676072597503662, "global_step": 536780, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.121954917907715, "global_step": 536781, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.049633264541626, "global_step": 536782, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.073754072189331, "global_step": 536783, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0113728046417236, "global_step": 536784, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9870030879974365, "global_step": 536785, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0754425525665283, "global_step": 536786, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0682053565979004, "global_step": 536787, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0850417613983154, "global_step": 536788, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9740955829620361, "global_step": 536789, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9297398328781128, "global_step": 536790, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9725497961044312, "global_step": 536791, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0952186584472656, "global_step": 536792, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.042412519454956, "global_step": 536793, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0212926864624023, "global_step": 536794, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9696053266525269, "global_step": 536795, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0405590534210205, "global_step": 536796, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.067035675048828, "global_step": 536797, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0839715003967285, "global_step": 536798, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0643045902252197, "global_step": 536799, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0596883296966553, "global_step": 536800, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.009093761444092, "global_step": 536801, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9743221998214722, "global_step": 536802, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1203808784484863, "global_step": 536803, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0257558822631836, "global_step": 536804, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0092287063598633, "global_step": 536805, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.066401481628418, "global_step": 536806, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9593201875686646, "global_step": 536807, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0801985263824463, "global_step": 536808, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0748307704925537, "global_step": 536809, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9411615133285522, "global_step": 536810, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1294291019439697, "global_step": 536811, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.048185110092163, "global_step": 536812, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9816269874572754, "global_step": 536813, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0630877017974854, "global_step": 536814, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0253922939300537, "global_step": 536815, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0415947437286377, "global_step": 536816, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9766883850097656, "global_step": 536817, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.983906626701355, "global_step": 536818, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0599429607391357, "global_step": 536819, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.022977590560913, "global_step": 536820, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.027906656265259, "global_step": 536821, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.009671926498413, "global_step": 536822, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.054682493209839, "global_step": 536823, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.977725625038147, "global_step": 536824, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9499348402023315, "global_step": 536825, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0093183517456055, "global_step": 536826, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.054328203201294, "global_step": 536827, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1273884773254395, "global_step": 536828, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0219130516052246, "global_step": 536829, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0850439071655273, "global_step": 536830, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.056964159011841, "global_step": 536831, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9075078964233398, "global_step": 536832, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0367672443389893, "global_step": 536833, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.000714063644409, "global_step": 536834, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.040471315383911, "global_step": 536835, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.070175886154175, "global_step": 536836, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9691025018692017, "global_step": 536837, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.064002275466919, "global_step": 536838, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0013484954833984, "global_step": 536839, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.104579448699951, "global_step": 536840, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0438385009765625, "global_step": 536841, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0300395488739014, "global_step": 536842, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.036226987838745, "global_step": 536843, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9989556074142456, "global_step": 536844, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0305418968200684, "global_step": 536845, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9467191696166992, "global_step": 536846, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0017199516296387, "global_step": 536847, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0778746604919434, "global_step": 536848, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.076847553253174, "global_step": 536849, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1441969871520996, "global_step": 536850, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.060272693634033, "global_step": 536851, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.090153932571411, "global_step": 536852, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1417593955993652, "global_step": 536853, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.002654790878296, "global_step": 536854, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.020348310470581, "global_step": 536855, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0409653186798096, "global_step": 536856, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.010775089263916, "global_step": 536857, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.10673451423645, "global_step": 536858, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.033761501312256, "global_step": 536859, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.069556713104248, "global_step": 536860, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0730509757995605, "global_step": 536861, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9824796915054321, "global_step": 536862, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.097569465637207, "global_step": 536863, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.107908248901367, "global_step": 536864, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0492103099823, "global_step": 536865, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0093796253204346, "global_step": 536866, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0403084754943848, "global_step": 536867, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9300427436828613, "global_step": 536868, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.090829849243164, "global_step": 536869, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.027913808822632, "global_step": 536870, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0817251205444336, "global_step": 536871, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1813085079193115, "global_step": 536872, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0749309062957764, "global_step": 536873, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9764058589935303, "global_step": 536874, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.031346082687378, "global_step": 536875, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.081956386566162, "global_step": 536876, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.13539457321167, "global_step": 536877, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0879054069519043, "global_step": 536878, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0417098999023438, "global_step": 536879, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0489628314971924, "global_step": 536880, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.981465220451355, "global_step": 536881, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0440542697906494, "global_step": 536882, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9918526411056519, "global_step": 536883, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.004936456680298, "global_step": 536884, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9692147970199585, "global_step": 536885, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.072732448577881, "global_step": 536886, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9793964624404907, "global_step": 536887, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0699257850646973, "global_step": 536888, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0689167976379395, "global_step": 536889, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.086901903152466, "global_step": 536890, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9905120134353638, "global_step": 536891, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9944267272949219, "global_step": 536892, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.2203593254089355, "global_step": 536893, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.059831142425537, "global_step": 536894, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1005678176879883, "global_step": 536895, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0070338249206543, "global_step": 536896, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.167512893676758, "global_step": 536897, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.056229591369629, "global_step": 536898, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9796879291534424, "global_step": 536899, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.041321277618408, "global_step": 536900, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.092909336090088, "global_step": 536901, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.110056161880493, "global_step": 536902, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0301215648651123, "global_step": 536903, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.09566068649292, "global_step": 536904, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0567643642425537, "global_step": 536905, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.028977870941162, "global_step": 536906, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.079101800918579, "global_step": 536907, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0126218795776367, "global_step": 536908, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.057737112045288, "global_step": 536909, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.065937042236328, "global_step": 536910, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1410539150238037, "global_step": 536911, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0764012336730957, "global_step": 536912, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.080097198486328, "global_step": 536913, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.040800094604492, "global_step": 536914, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0102450847625732, "global_step": 536915, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1485183238983154, "global_step": 536916, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.136017084121704, "global_step": 536917, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0266363620758057, "global_step": 536918, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9916130304336548, "global_step": 536919, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1079938411712646, "global_step": 536920, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1093740463256836, "global_step": 536921, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0994057655334473, "global_step": 536922, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0130200386047363, "global_step": 536923, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0158772468566895, "global_step": 536924, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0241410732269287, "global_step": 536925, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.099471092224121, "global_step": 536926, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.045957088470459, "global_step": 536927, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.18780517578125, "global_step": 536928, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0795743465423584, "global_step": 536929, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.000617504119873, "global_step": 536930, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0904994010925293, "global_step": 536931, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0275495052337646, "global_step": 536932, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0789575576782227, "global_step": 536933, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.044569253921509, "global_step": 536934, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0091028213500977, "global_step": 536935, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.948895812034607, "global_step": 536936, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.088285446166992, "global_step": 536937, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.1219358444213867, "global_step": 536938, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0323598384857178, "global_step": 536939, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0158889293670654, "global_step": 536940, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0485382080078125, "global_step": 536941, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0288848876953125, "global_step": 536942, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9787191152572632, "global_step": 536943, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9605389833450317, "global_step": 536944, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.022606611251831, "global_step": 536945, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.055147886276245, "global_step": 536946, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0358245372772217, "global_step": 536947, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.064373254776001, "global_step": 536948, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9655288457870483, "global_step": 536949, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0090956687927246, "global_step": 536950, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9961544275283813, "global_step": 536951, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.008639335632324, "global_step": 536952, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9875209331512451, "global_step": 536953, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.9719436168670654, "global_step": 536954, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0991246700286865, "global_step": 536955, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0817606449127197, "global_step": 536956, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0217366218566895, "global_step": 536957, "epoch": 903, "lr": 5e-05}
{"train_loss": 2.0371313095092773, "global_step": 536958, "epoch": 903, "lr": 5e-05}
{"train_loss": 1.966365933418274, "global_step": 536959, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0625674724578857, "global_step": 536960, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.073535442352295, "global_step": 536961, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0143070220947266, "global_step": 536962, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9944324493408203, "global_step": 536963, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.071040391921997, "global_step": 536964, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9522157907485962, "global_step": 536965, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0207793712615967, "global_step": 536966, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9816131591796875, "global_step": 536967, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.089102029800415, "global_step": 536968, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1106622219085693, "global_step": 536969, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.048896312713623, "global_step": 536970, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0876781940460205, "global_step": 536971, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0710957050323486, "global_step": 536972, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.013763666152954, "global_step": 536973, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0217721462249756, "global_step": 536974, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0090930461883545, "global_step": 536975, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0032129287719727, "global_step": 536976, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9284838438034058, "global_step": 536977, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0230712890625, "global_step": 536978, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0768392086029053, "global_step": 536979, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.017556667327881, "global_step": 536980, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0121471881866455, "global_step": 536981, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.056943416595459, "global_step": 536982, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0684471130371094, "global_step": 536983, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.059946060180664, "global_step": 536984, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.023470640182495, "global_step": 536985, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0341806411743164, "global_step": 536986, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9732996225357056, "global_step": 536987, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0013668537139893, "global_step": 536988, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0386576652526855, "global_step": 536989, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9773858785629272, "global_step": 536990, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9964444637298584, "global_step": 536991, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0052578449249268, "global_step": 536992, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.053349018096924, "global_step": 536993, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.075021505355835, "global_step": 536994, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9399871826171875, "global_step": 536995, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9606354236602783, "global_step": 536996, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9784877300262451, "global_step": 536997, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.030818462371826, "global_step": 536998, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.964724063873291, "global_step": 536999, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.003096580505371, "global_step": 537000, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0455563068389893, "global_step": 537001, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.027678966522217, "global_step": 537002, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9817804098129272, "global_step": 537003, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0197551250457764, "global_step": 537004, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.044443368911743, "global_step": 537005, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.072396993637085, "global_step": 537006, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.03251576423645, "global_step": 537007, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0929715633392334, "global_step": 537008, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9316269159317017, "global_step": 537009, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.970786690711975, "global_step": 537010, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0148961544036865, "global_step": 537011, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.08221435546875, "global_step": 537012, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9662501811981201, "global_step": 537013, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9968336820602417, "global_step": 537014, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0643692016601562, "global_step": 537015, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.067112922668457, "global_step": 537016, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0152876377105713, "global_step": 537017, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.033324956893921, "global_step": 537018, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0323283672332764, "global_step": 537019, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0943689346313477, "global_step": 537020, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0263442993164062, "global_step": 537021, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0829339027404785, "global_step": 537022, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9505926370620728, "global_step": 537023, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0967154502868652, "global_step": 537024, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.954314112663269, "global_step": 537025, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0655386447906494, "global_step": 537026, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0197131633758545, "global_step": 537027, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9166991710662842, "global_step": 537028, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9812078475952148, "global_step": 537029, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.047314167022705, "global_step": 537030, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.092808246612549, "global_step": 537031, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.072665214538574, "global_step": 537032, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9551829099655151, "global_step": 537033, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9696862697601318, "global_step": 537034, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0902791023254395, "global_step": 537035, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.05031418800354, "global_step": 537036, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.8915181159973145, "global_step": 537037, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0013022422790527, "global_step": 537038, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.027428150177002, "global_step": 537039, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0127005577087402, "global_step": 537040, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9954050779342651, "global_step": 537041, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.083294153213501, "global_step": 537042, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.08532977104187, "global_step": 537043, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0764312744140625, "global_step": 537044, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0002708435058594, "global_step": 537045, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0546023845672607, "global_step": 537046, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0830085277557373, "global_step": 537047, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9725029468536377, "global_step": 537048, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0605101585388184, "global_step": 537049, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9779249429702759, "global_step": 537050, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0342719554901123, "global_step": 537051, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9805303812026978, "global_step": 537052, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0483624935150146, "global_step": 537053, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1060547828674316, "global_step": 537054, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0812013149261475, "global_step": 537055, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.049743413925171, "global_step": 537056, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.060673713684082, "global_step": 537057, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0359325408935547, "global_step": 537058, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0206429958343506, "global_step": 537059, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.028677463531494, "global_step": 537060, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9920728206634521, "global_step": 537061, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0810110569000244, "global_step": 537062, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9542131423950195, "global_step": 537063, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9965424537658691, "global_step": 537064, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0449368953704834, "global_step": 537065, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0256290435791016, "global_step": 537066, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.024993896484375, "global_step": 537067, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.071423292160034, "global_step": 537068, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9358872175216675, "global_step": 537069, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0741405487060547, "global_step": 537070, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.055872917175293, "global_step": 537071, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0054805278778076, "global_step": 537072, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.98857581615448, "global_step": 537073, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9636859893798828, "global_step": 537074, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0373260974884033, "global_step": 537075, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0700576305389404, "global_step": 537076, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.140014171600342, "global_step": 537077, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0816268920898438, "global_step": 537078, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0530731678009033, "global_step": 537079, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0160913467407227, "global_step": 537080, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1102383136749268, "global_step": 537081, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9620962142944336, "global_step": 537082, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0460243225097656, "global_step": 537083, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.049471855163574, "global_step": 537084, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1287808418273926, "global_step": 537085, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0228846073150635, "global_step": 537086, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.010444164276123, "global_step": 537087, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1169686317443848, "global_step": 537088, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0144309997558594, "global_step": 537089, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.988408088684082, "global_step": 537090, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0027081966400146, "global_step": 537091, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.09084153175354, "global_step": 537092, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.967160701751709, "global_step": 537093, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9758782386779785, "global_step": 537094, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.06888747215271, "global_step": 537095, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.999592661857605, "global_step": 537096, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.071033000946045, "global_step": 537097, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0132179260253906, "global_step": 537098, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9249969720840454, "global_step": 537099, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.013382911682129, "global_step": 537100, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.056426763534546, "global_step": 537101, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.054760694503784, "global_step": 537102, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0820038318634033, "global_step": 537103, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.002506732940674, "global_step": 537104, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.033656120300293, "global_step": 537105, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0535221099853516, "global_step": 537106, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0304484367370605, "global_step": 537107, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9660581350326538, "global_step": 537108, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9846763610839844, "global_step": 537109, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.125464677810669, "global_step": 537110, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9844809770584106, "global_step": 537111, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.012714385986328, "global_step": 537112, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0392708778381348, "global_step": 537113, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0848944187164307, "global_step": 537114, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.009972333908081, "global_step": 537115, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0121607780456543, "global_step": 537116, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1049580574035645, "global_step": 537117, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.057234287261963, "global_step": 537118, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.032217502593994, "global_step": 537119, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.01143741607666, "global_step": 537120, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0842690467834473, "global_step": 537121, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.950601577758789, "global_step": 537122, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9627541303634644, "global_step": 537123, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0011074542999268, "global_step": 537124, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.042776346206665, "global_step": 537125, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.01425838470459, "global_step": 537126, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.026459217071533, "global_step": 537127, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.027254819869995, "global_step": 537128, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1157350540161133, "global_step": 537129, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0335397720336914, "global_step": 537130, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9839351177215576, "global_step": 537131, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0499420166015625, "global_step": 537132, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.014803886413574, "global_step": 537133, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.023369073867798, "global_step": 537134, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1352243423461914, "global_step": 537135, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1134872436523438, "global_step": 537136, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0779836177825928, "global_step": 537137, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0797412395477295, "global_step": 537138, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.981466293334961, "global_step": 537139, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0793795585632324, "global_step": 537140, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1232895851135254, "global_step": 537141, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0487382411956787, "global_step": 537142, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0725748538970947, "global_step": 537143, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0394935607910156, "global_step": 537144, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0478434562683105, "global_step": 537145, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9718706607818604, "global_step": 537146, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.030405044555664, "global_step": 537147, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9944103956222534, "global_step": 537148, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.019733190536499, "global_step": 537149, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.059317111968994, "global_step": 537150, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.044023275375366, "global_step": 537151, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9843436479568481, "global_step": 537152, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9868360757827759, "global_step": 537153, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0615978240966797, "global_step": 537154, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0737953186035156, "global_step": 537155, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0362894535064697, "global_step": 537156, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9835125207901, "global_step": 537157, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.108442783355713, "global_step": 537158, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0267884731292725, "global_step": 537159, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.118384599685669, "global_step": 537160, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0326993465423584, "global_step": 537161, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.036360740661621, "global_step": 537162, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9549927711486816, "global_step": 537163, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9294109344482422, "global_step": 537164, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.977332592010498, "global_step": 537165, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9960600137710571, "global_step": 537166, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0170047283172607, "global_step": 537167, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.051697254180908, "global_step": 537168, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0433835983276367, "global_step": 537169, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.019279718399048, "global_step": 537170, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0028772354125977, "global_step": 537171, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9805591106414795, "global_step": 537172, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0156710147857666, "global_step": 537173, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.04377818107605, "global_step": 537174, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0370073318481445, "global_step": 537175, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.052927255630493, "global_step": 537176, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0575103759765625, "global_step": 537177, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9948170185089111, "global_step": 537178, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.005481243133545, "global_step": 537179, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1413068771362305, "global_step": 537180, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.052412271499634, "global_step": 537181, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.09311842918396, "global_step": 537182, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9801390171051025, "global_step": 537183, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1723668575286865, "global_step": 537184, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.954599380493164, "global_step": 537185, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0014288425445557, "global_step": 537186, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0361390113830566, "global_step": 537187, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0352816581726074, "global_step": 537188, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0000052452087402, "global_step": 537189, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0747880935668945, "global_step": 537190, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9765698909759521, "global_step": 537191, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0574069023132324, "global_step": 537192, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9863044023513794, "global_step": 537193, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1442575454711914, "global_step": 537194, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9916752576828003, "global_step": 537195, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0614421367645264, "global_step": 537196, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0351693630218506, "global_step": 537197, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0270018577575684, "global_step": 537198, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9984407424926758, "global_step": 537199, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.106306314468384, "global_step": 537200, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0834503173828125, "global_step": 537201, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.05639386177063, "global_step": 537202, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.038119077682495, "global_step": 537203, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.065077781677246, "global_step": 537204, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.066171646118164, "global_step": 537205, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9694602489471436, "global_step": 537206, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0146188735961914, "global_step": 537207, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.896651029586792, "global_step": 537208, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.018845319747925, "global_step": 537209, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9329043626785278, "global_step": 537210, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0231881141662598, "global_step": 537211, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9273254871368408, "global_step": 537212, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0955357551574707, "global_step": 537213, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.129211187362671, "global_step": 537214, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.046747922897339, "global_step": 537215, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.994834542274475, "global_step": 537216, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9437448978424072, "global_step": 537217, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0726735591888428, "global_step": 537218, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0579910278320312, "global_step": 537219, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0615100860595703, "global_step": 537220, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9615434408187866, "global_step": 537221, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.178804397583008, "global_step": 537222, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.121833324432373, "global_step": 537223, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.000812292098999, "global_step": 537224, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.008023738861084, "global_step": 537225, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.099823474884033, "global_step": 537226, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.033489227294922, "global_step": 537227, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9949899911880493, "global_step": 537228, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0693812370300293, "global_step": 537229, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.037874698638916, "global_step": 537230, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.971774935722351, "global_step": 537231, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.004912853240967, "global_step": 537232, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9511606693267822, "global_step": 537233, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.121243953704834, "global_step": 537234, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0328445434570312, "global_step": 537235, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0999321937561035, "global_step": 537236, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0562872886657715, "global_step": 537237, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0247788429260254, "global_step": 537238, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1355748176574707, "global_step": 537239, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.032438278198242, "global_step": 537240, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1070103645324707, "global_step": 537241, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.032315492630005, "global_step": 537242, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.933983564376831, "global_step": 537243, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9696574211120605, "global_step": 537244, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0369973182678223, "global_step": 537245, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.121971607208252, "global_step": 537246, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.034595489501953, "global_step": 537247, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0088155269622803, "global_step": 537248, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0571887493133545, "global_step": 537249, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.041116952896118, "global_step": 537250, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.143958806991577, "global_step": 537251, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.997440218925476, "global_step": 537252, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.001437187194824, "global_step": 537253, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.12379789352417, "global_step": 537254, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.102614402770996, "global_step": 537255, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.976940631866455, "global_step": 537256, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.092420816421509, "global_step": 537257, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.142825126647949, "global_step": 537258, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.054713487625122, "global_step": 537259, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.126433849334717, "global_step": 537260, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0259387493133545, "global_step": 537261, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.037309408187866, "global_step": 537262, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0499253273010254, "global_step": 537263, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0557689666748047, "global_step": 537264, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0256195068359375, "global_step": 537265, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.039346694946289, "global_step": 537266, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1081185340881348, "global_step": 537267, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0772697925567627, "global_step": 537268, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0526468753814697, "global_step": 537269, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0062544345855713, "global_step": 537270, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.039401054382324, "global_step": 537271, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9984147548675537, "global_step": 537272, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9619289636611938, "global_step": 537273, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9689507484436035, "global_step": 537274, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0231003761291504, "global_step": 537275, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.017942190170288, "global_step": 537276, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0483362674713135, "global_step": 537277, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0956480503082275, "global_step": 537278, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.102299928665161, "global_step": 537279, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0766191482543945, "global_step": 537280, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0666801929473877, "global_step": 537281, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.087526321411133, "global_step": 537282, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.078569173812866, "global_step": 537283, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.055819511413574, "global_step": 537284, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9469177722930908, "global_step": 537285, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.076580047607422, "global_step": 537286, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.097548723220825, "global_step": 537287, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.036975860595703, "global_step": 537288, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.064301013946533, "global_step": 537289, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0191140174865723, "global_step": 537290, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9876128435134888, "global_step": 537291, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.072065830230713, "global_step": 537292, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0387699604034424, "global_step": 537293, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.030092477798462, "global_step": 537294, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.128589630126953, "global_step": 537295, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.058922290802002, "global_step": 537296, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.099020004272461, "global_step": 537297, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.061896800994873, "global_step": 537298, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0775976181030273, "global_step": 537299, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.111626386642456, "global_step": 537300, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.025031089782715, "global_step": 537301, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.944743275642395, "global_step": 537302, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.03395676612854, "global_step": 537303, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.02642822265625, "global_step": 537304, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9715077877044678, "global_step": 537305, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0215415954589844, "global_step": 537306, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0901341438293457, "global_step": 537307, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.043649196624756, "global_step": 537308, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0154268741607666, "global_step": 537309, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0290191173553467, "global_step": 537310, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.060366630554199, "global_step": 537311, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9886690378189087, "global_step": 537312, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0667364597320557, "global_step": 537313, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0157337188720703, "global_step": 537314, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0240163803100586, "global_step": 537315, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.954423189163208, "global_step": 537316, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.058210849761963, "global_step": 537317, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.139392375946045, "global_step": 537318, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.085482358932495, "global_step": 537319, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.019237518310547, "global_step": 537320, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0964596271514893, "global_step": 537321, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9914661645889282, "global_step": 537322, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9404007196426392, "global_step": 537323, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9606096744537354, "global_step": 537324, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0410966873168945, "global_step": 537325, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0961697101593018, "global_step": 537326, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0606136322021484, "global_step": 537327, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0655534267425537, "global_step": 537328, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.000406265258789, "global_step": 537329, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.996970534324646, "global_step": 537330, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9936366081237793, "global_step": 537331, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.037748098373413, "global_step": 537332, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.989806890487671, "global_step": 537333, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.011235475540161, "global_step": 537334, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1174986362457275, "global_step": 537335, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0058929920196533, "global_step": 537336, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0443453788757324, "global_step": 537337, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0472350120544434, "global_step": 537338, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.01870059967041, "global_step": 537339, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.997793436050415, "global_step": 537340, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0055816173553467, "global_step": 537341, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.053931474685669, "global_step": 537342, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0498383045196533, "global_step": 537343, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0395407676696777, "global_step": 537344, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9488050937652588, "global_step": 537345, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.041489601135254, "global_step": 537346, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.188164710998535, "global_step": 537347, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9920642375946045, "global_step": 537348, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.07936954498291, "global_step": 537349, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0285286903381348, "global_step": 537350, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.058640480041504, "global_step": 537351, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9682486057281494, "global_step": 537352, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.046234130859375, "global_step": 537353, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.010796070098877, "global_step": 537354, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.126375198364258, "global_step": 537355, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0693678855895996, "global_step": 537356, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.079420566558838, "global_step": 537357, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.020689010620117, "global_step": 537358, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0055203437805176, "global_step": 537359, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0215282440185547, "global_step": 537360, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.938834547996521, "global_step": 537361, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.061039686203003, "global_step": 537362, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9271035194396973, "global_step": 537363, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0316271781921387, "global_step": 537364, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.020252227783203, "global_step": 537365, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.082378625869751, "global_step": 537366, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.109863758087158, "global_step": 537367, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.014094352722168, "global_step": 537368, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0216219425201416, "global_step": 537369, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0649209022521973, "global_step": 537370, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.013298511505127, "global_step": 537371, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.01426362991333, "global_step": 537372, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0370614528656006, "global_step": 537373, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.081362009048462, "global_step": 537374, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1497323513031006, "global_step": 537375, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.043663263320923, "global_step": 537376, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1041922569274902, "global_step": 537377, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9704598188400269, "global_step": 537378, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.977736473083496, "global_step": 537379, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1117966175079346, "global_step": 537380, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1347718238830566, "global_step": 537381, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1202590465545654, "global_step": 537382, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.094327211380005, "global_step": 537383, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9799736738204956, "global_step": 537384, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1112051010131836, "global_step": 537385, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9946023225784302, "global_step": 537386, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.051388740539551, "global_step": 537387, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.005950927734375, "global_step": 537388, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0081841945648193, "global_step": 537389, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0916571617126465, "global_step": 537390, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0983471870422363, "global_step": 537391, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9537986516952515, "global_step": 537392, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0601933002471924, "global_step": 537393, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9857569932937622, "global_step": 537394, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0593440532684326, "global_step": 537395, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0165839195251465, "global_step": 537396, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.018514394760132, "global_step": 537397, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.055049419403076, "global_step": 537398, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9827271699905396, "global_step": 537399, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0246942043304443, "global_step": 537400, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9489662647247314, "global_step": 537401, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0375843048095703, "global_step": 537402, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.966890811920166, "global_step": 537403, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.058825731277466, "global_step": 537404, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.080321788787842, "global_step": 537405, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0883355140686035, "global_step": 537406, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0154151916503906, "global_step": 537407, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.011587381362915, "global_step": 537408, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0251996517181396, "global_step": 537409, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0326693058013916, "global_step": 537410, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9888479709625244, "global_step": 537411, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0494279861450195, "global_step": 537412, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0289173126220703, "global_step": 537413, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.018592119216919, "global_step": 537414, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0115809440612793, "global_step": 537415, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0775949954986572, "global_step": 537416, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.059070348739624, "global_step": 537417, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.078139066696167, "global_step": 537418, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9717469215393066, "global_step": 537419, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0175769329071045, "global_step": 537420, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0883562564849854, "global_step": 537421, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9747557640075684, "global_step": 537422, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0554304122924805, "global_step": 537423, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.063171863555908, "global_step": 537424, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0125820636749268, "global_step": 537425, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1233882904052734, "global_step": 537426, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0312373638153076, "global_step": 537427, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9981616735458374, "global_step": 537428, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.079010248184204, "global_step": 537429, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.07973313331604, "global_step": 537430, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.067274808883667, "global_step": 537431, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9382779598236084, "global_step": 537432, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0348618030548096, "global_step": 537433, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0607759952545166, "global_step": 537434, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.044393539428711, "global_step": 537435, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0268213748931885, "global_step": 537436, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0222043991088867, "global_step": 537437, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.040698766708374, "global_step": 537438, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9971647262573242, "global_step": 537439, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0965840816497803, "global_step": 537440, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0550360679626465, "global_step": 537441, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0662295818328857, "global_step": 537442, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0493226051330566, "global_step": 537443, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0703396797180176, "global_step": 537444, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9811187982559204, "global_step": 537445, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9692254066467285, "global_step": 537446, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1194427013397217, "global_step": 537447, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.102962017059326, "global_step": 537448, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.000521421432495, "global_step": 537449, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0083303451538086, "global_step": 537450, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0611636638641357, "global_step": 537451, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.013414144515991, "global_step": 537452, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.977964162826538, "global_step": 537453, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0856237411499023, "global_step": 537454, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.082610607147217, "global_step": 537455, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0604004859924316, "global_step": 537456, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.077437400817871, "global_step": 537457, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0017282962799072, "global_step": 537458, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.085728406906128, "global_step": 537459, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0733137130737305, "global_step": 537460, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0214974880218506, "global_step": 537461, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9505695104599, "global_step": 537462, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1188862323760986, "global_step": 537463, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0710079669952393, "global_step": 537464, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.00716233253479, "global_step": 537465, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.965089201927185, "global_step": 537466, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.013657569885254, "global_step": 537467, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9764792919158936, "global_step": 537468, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.051377058029175, "global_step": 537469, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0393259525299072, "global_step": 537470, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.070190191268921, "global_step": 537471, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.045088052749634, "global_step": 537472, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.075185775756836, "global_step": 537473, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.041140556335449, "global_step": 537474, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0699477195739746, "global_step": 537475, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.029953956604004, "global_step": 537476, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9779046773910522, "global_step": 537477, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.986558437347412, "global_step": 537478, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1083436012268066, "global_step": 537479, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9708327054977417, "global_step": 537480, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.040174961090088, "global_step": 537481, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.951043963432312, "global_step": 537482, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0359175205230713, "global_step": 537483, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.068031072616577, "global_step": 537484, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9475511312484741, "global_step": 537485, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0666184425354004, "global_step": 537486, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0757672786712646, "global_step": 537487, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0102298259735107, "global_step": 537488, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0549254417419434, "global_step": 537489, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.028778076171875, "global_step": 537490, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.067554235458374, "global_step": 537491, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.952490210533142, "global_step": 537492, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9758390188217163, "global_step": 537493, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0602047443389893, "global_step": 537494, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0178816318511963, "global_step": 537495, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0040507316589355, "global_step": 537496, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.051069498062134, "global_step": 537497, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.055053472518921, "global_step": 537498, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9221805334091187, "global_step": 537499, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9562724828720093, "global_step": 537500, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.112880229949951, "global_step": 537501, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1233785152435303, "global_step": 537502, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9851458072662354, "global_step": 537503, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9725946187973022, "global_step": 537504, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0554535388946533, "global_step": 537505, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.051410436630249, "global_step": 537506, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0503809452056885, "global_step": 537507, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.015947103500366, "global_step": 537508, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.020413875579834, "global_step": 537509, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0591354370117188, "global_step": 537510, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.021862030029297, "global_step": 537511, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0637426376342773, "global_step": 537512, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.997765064239502, "global_step": 537513, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9613741636276245, "global_step": 537514, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0336687564849854, "global_step": 537515, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.090893507003784, "global_step": 537516, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.959212303161621, "global_step": 537517, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0324087142944336, "global_step": 537518, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0594780445098877, "global_step": 537519, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0823161602020264, "global_step": 537520, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.8926479816436768, "global_step": 537521, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.045560359954834, "global_step": 537522, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0384726524353027, "global_step": 537523, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9567060470581055, "global_step": 537524, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.052034616470337, "global_step": 537525, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0093398094177246, "global_step": 537526, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.052457571029663, "global_step": 537527, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.111410617828369, "global_step": 537528, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0178091526031494, "global_step": 537529, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.131084442138672, "global_step": 537530, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0260608196258545, "global_step": 537531, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0519421100616455, "global_step": 537532, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.053574323654175, "global_step": 537533, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.026961326599121, "global_step": 537534, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9514623880386353, "global_step": 537535, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.006481170654297, "global_step": 537536, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.044990062713623, "global_step": 537537, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.068213701248169, "global_step": 537538, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0135178565979004, "global_step": 537539, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.080686092376709, "global_step": 537540, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1040501594543457, "global_step": 537541, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.009305953979492, "global_step": 537542, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1632111072540283, "global_step": 537543, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0127148628234863, "global_step": 537544, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.045921802520752, "global_step": 537545, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0755763053894043, "global_step": 537546, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9434559345245361, "global_step": 537547, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9996905326843262, "global_step": 537548, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0479955673217773, "global_step": 537549, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0440075397491455, "global_step": 537550, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0531911849975586, "global_step": 537551, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.042365312576294, "global_step": 537552, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.065793514251709, "global_step": 537553, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.994437336921692, "global_step": 537554, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.067458152770996, "global_step": 537555, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0780844688415527, "global_step": 537556, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0282130241394043, "global_step": 537557, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.076403856277466, "global_step": 537558, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0241847038269043, "global_step": 537559, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0544986724853516, "global_step": 537560, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0937001705169678, "global_step": 537561, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9726537466049194, "global_step": 537562, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0213782787323, "global_step": 537563, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.057832717895508, "global_step": 537564, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.080690622329712, "global_step": 537565, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0179998874664307, "global_step": 537566, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9894953966140747, "global_step": 537567, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9834668636322021, "global_step": 537568, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0796303749084473, "global_step": 537569, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0559210777282715, "global_step": 537570, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.139915704727173, "global_step": 537571, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.080341100692749, "global_step": 537572, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0112318992614746, "global_step": 537573, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9532430171966553, "global_step": 537574, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9481619596481323, "global_step": 537575, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.049037456512451, "global_step": 537576, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0237600803375244, "global_step": 537577, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0089848041534424, "global_step": 537578, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0094645023345947, "global_step": 537579, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.085022211074829, "global_step": 537580, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.053860902786255, "global_step": 537581, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.037489414215088, "global_step": 537582, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9678703546524048, "global_step": 537583, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9790165424346924, "global_step": 537584, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0682671070098877, "global_step": 537585, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.022522449493408, "global_step": 537586, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.014467716217041, "global_step": 537587, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.041208028793335, "global_step": 537588, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0571393966674805, "global_step": 537589, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9912697076797485, "global_step": 537590, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0190160274505615, "global_step": 537591, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.124689817428589, "global_step": 537592, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.999915599822998, "global_step": 537593, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0222039222717285, "global_step": 537594, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0500388145446777, "global_step": 537595, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.017219305038452, "global_step": 537596, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.051422119140625, "global_step": 537597, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.009821653366089, "global_step": 537598, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.061527967453003, "global_step": 537599, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9581379890441895, "global_step": 537600, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0223824977874756, "global_step": 537601, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0445988178253174, "global_step": 537602, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0255839824676514, "global_step": 537603, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9610191583633423, "global_step": 537604, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0617151260375977, "global_step": 537605, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0667202472686768, "global_step": 537606, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1427741050720215, "global_step": 537607, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.996767520904541, "global_step": 537608, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0319206714630127, "global_step": 537609, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1355350017547607, "global_step": 537610, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0609312057495117, "global_step": 537611, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0636985301971436, "global_step": 537612, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.061976432800293, "global_step": 537613, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0208585262298584, "global_step": 537614, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0551605224609375, "global_step": 537615, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9874924421310425, "global_step": 537616, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.055790901184082, "global_step": 537617, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.129822015762329, "global_step": 537618, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0337445735931396, "global_step": 537619, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1149702072143555, "global_step": 537620, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9495705366134644, "global_step": 537621, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.016961097717285, "global_step": 537622, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0996086597442627, "global_step": 537623, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0457727909088135, "global_step": 537624, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.030562162399292, "global_step": 537625, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.044760227203369, "global_step": 537626, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9654369354248047, "global_step": 537627, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0002260208129883, "global_step": 537628, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.087153196334839, "global_step": 537629, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.063322067260742, "global_step": 537630, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9995105266571045, "global_step": 537631, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.034334421157837, "global_step": 537632, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0441877841949463, "global_step": 537633, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0439324378967285, "global_step": 537634, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1036510467529297, "global_step": 537635, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.009430408477783, "global_step": 537636, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.018725633621216, "global_step": 537637, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9697935581207275, "global_step": 537638, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1426146030426025, "global_step": 537639, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9322466850280762, "global_step": 537640, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0541718006134033, "global_step": 537641, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.022963523864746, "global_step": 537642, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0392701625823975, "global_step": 537643, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9777858257293701, "global_step": 537644, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.967060923576355, "global_step": 537645, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.067751884460449, "global_step": 537646, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0885305404663086, "global_step": 537647, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0643138885498047, "global_step": 537648, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0304317474365234, "global_step": 537649, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9838303327560425, "global_step": 537650, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9749348163604736, "global_step": 537651, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.036170244216919, "global_step": 537652, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0804636478424072, "global_step": 537653, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9911949634552002, "global_step": 537654, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9876387119293213, "global_step": 537655, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9766138792037964, "global_step": 537656, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.137690544128418, "global_step": 537657, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9302157163619995, "global_step": 537658, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0277607440948486, "global_step": 537659, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0457372665405273, "global_step": 537660, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.061152219772339, "global_step": 537661, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0411219596862793, "global_step": 537662, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.078583002090454, "global_step": 537663, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1276466846466064, "global_step": 537664, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1250483989715576, "global_step": 537665, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.007256507873535, "global_step": 537666, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0023460388183594, "global_step": 537667, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0428671836853027, "global_step": 537668, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0867114067077637, "global_step": 537669, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.027228593826294, "global_step": 537670, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9790217876434326, "global_step": 537671, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9782825708389282, "global_step": 537672, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0641379356384277, "global_step": 537673, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.117542028427124, "global_step": 537674, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.014023780822754, "global_step": 537675, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0429656505584717, "global_step": 537676, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0256149768829346, "global_step": 537677, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.091893196105957, "global_step": 537678, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.066521167755127, "global_step": 537679, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.006298303604126, "global_step": 537680, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0448176860809326, "global_step": 537681, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9900474548339844, "global_step": 537682, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9971433877944946, "global_step": 537683, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9906387329101562, "global_step": 537684, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.062906265258789, "global_step": 537685, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.054070234298706, "global_step": 537686, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.027646064758301, "global_step": 537687, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.059779644012451, "global_step": 537688, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0580081939697266, "global_step": 537689, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.021176815032959, "global_step": 537690, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0941576957702637, "global_step": 537691, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.055037260055542, "global_step": 537692, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.137603282928467, "global_step": 537693, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.001142978668213, "global_step": 537694, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0753636360168457, "global_step": 537695, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1043105125427246, "global_step": 537696, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0783774852752686, "global_step": 537697, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.036956310272217, "global_step": 537698, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1410534381866455, "global_step": 537699, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0499415397644043, "global_step": 537700, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9450435638427734, "global_step": 537701, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.972251057624817, "global_step": 537702, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0694515705108643, "global_step": 537703, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0502665042877197, "global_step": 537704, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.078237295150757, "global_step": 537705, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.086784839630127, "global_step": 537706, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.005941867828369, "global_step": 537707, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.004265546798706, "global_step": 537708, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9764569997787476, "global_step": 537709, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0349197387695312, "global_step": 537710, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9859272241592407, "global_step": 537711, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.082367181777954, "global_step": 537712, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0336244106292725, "global_step": 537713, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0779788494110107, "global_step": 537714, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0261189937591553, "global_step": 537715, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.033933162689209, "global_step": 537716, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0534610748291016, "global_step": 537717, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1115920543670654, "global_step": 537718, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0618412494659424, "global_step": 537719, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.042280435562134, "global_step": 537720, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9833569526672363, "global_step": 537721, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9383820295333862, "global_step": 537722, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.99660325050354, "global_step": 537723, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.115588903427124, "global_step": 537724, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0403459072113037, "global_step": 537725, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0065500736236572, "global_step": 537726, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1018171310424805, "global_step": 537727, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.027353286743164, "global_step": 537728, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0419318675994873, "global_step": 537729, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0799946784973145, "global_step": 537730, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.017186164855957, "global_step": 537731, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.018453359603882, "global_step": 537732, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1194474697113037, "global_step": 537733, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1849656105041504, "global_step": 537734, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0659070014953613, "global_step": 537735, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0493266582489014, "global_step": 537736, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9688490629196167, "global_step": 537737, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.050671100616455, "global_step": 537738, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.125786781311035, "global_step": 537739, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0185914039611816, "global_step": 537740, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9766234159469604, "global_step": 537741, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1227941513061523, "global_step": 537742, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0854241847991943, "global_step": 537743, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9942095279693604, "global_step": 537744, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1349854469299316, "global_step": 537745, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.061516761779785, "global_step": 537746, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0298333168029785, "global_step": 537747, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0097813606262207, "global_step": 537748, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0490245819091797, "global_step": 537749, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.095430374145508, "global_step": 537750, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0601422786712646, "global_step": 537751, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0617423057556152, "global_step": 537752, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9764456748962402, "global_step": 537753, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9712163209915161, "global_step": 537754, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9831169843673706, "global_step": 537755, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0304064750671387, "global_step": 537756, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.064499855041504, "global_step": 537757, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9519953727722168, "global_step": 537758, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0669782161712646, "global_step": 537759, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0385634899139404, "global_step": 537760, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9359153509140015, "global_step": 537761, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.10426664352417, "global_step": 537762, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.069798707962036, "global_step": 537763, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0709922313690186, "global_step": 537764, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0070366859436035, "global_step": 537765, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.068181276321411, "global_step": 537766, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0783557891845703, "global_step": 537767, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0595977306365967, "global_step": 537768, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.092087507247925, "global_step": 537769, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.04417085647583, "global_step": 537770, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.095608711242676, "global_step": 537771, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.048389434814453, "global_step": 537772, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.062940835952759, "global_step": 537773, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9910211563110352, "global_step": 537774, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.120957374572754, "global_step": 537775, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.069415330886841, "global_step": 537776, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.043034315109253, "global_step": 537777, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.042125701904297, "global_step": 537778, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0893447399139404, "global_step": 537779, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.020094156265259, "global_step": 537780, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0410141944885254, "global_step": 537781, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.056753635406494, "global_step": 537782, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0865087509155273, "global_step": 537783, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.034323215484619, "global_step": 537784, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9842140674591064, "global_step": 537785, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.011066198348999, "global_step": 537786, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0204904079437256, "global_step": 537787, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0235495567321777, "global_step": 537788, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.042104721069336, "global_step": 537789, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.011610507965088, "global_step": 537790, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.058098793029785, "global_step": 537791, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.020425319671631, "global_step": 537792, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.013857364654541, "global_step": 537793, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.031771659851074, "global_step": 537794, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9939244985580444, "global_step": 537795, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.018136978149414, "global_step": 537796, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.040776252746582, "global_step": 537797, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9564754962921143, "global_step": 537798, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0634543895721436, "global_step": 537799, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9422433376312256, "global_step": 537800, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9072967767715454, "global_step": 537801, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.023653268814087, "global_step": 537802, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0625557899475098, "global_step": 537803, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0565712451934814, "global_step": 537804, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0083181858062744, "global_step": 537805, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.121612071990967, "global_step": 537806, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.081088066101074, "global_step": 537807, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0823614597320557, "global_step": 537808, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1043179035186768, "global_step": 537809, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.048638343811035, "global_step": 537810, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.069169044494629, "global_step": 537811, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0737602710723877, "global_step": 537812, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0524659156799316, "global_step": 537813, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.055299997329712, "global_step": 537814, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.048454761505127, "global_step": 537815, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0902554988861084, "global_step": 537816, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0078511238098145, "global_step": 537817, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9849965572357178, "global_step": 537818, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0072367191314697, "global_step": 537819, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.013448715209961, "global_step": 537820, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.020219326019287, "global_step": 537821, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0289547443389893, "global_step": 537822, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9631686210632324, "global_step": 537823, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0812036991119385, "global_step": 537824, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0487496852874756, "global_step": 537825, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0792107582092285, "global_step": 537826, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0662782192230225, "global_step": 537827, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9510170221328735, "global_step": 537828, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.018415927886963, "global_step": 537829, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0241219997406006, "global_step": 537830, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9723186492919922, "global_step": 537831, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0660560131073, "global_step": 537832, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0878584384918213, "global_step": 537833, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0424604415893555, "global_step": 537834, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.99679434299469, "global_step": 537835, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.038111925125122, "global_step": 537836, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0122296810150146, "global_step": 537837, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0311310291290283, "global_step": 537838, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.082848072052002, "global_step": 537839, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0557382106781006, "global_step": 537840, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.130040407180786, "global_step": 537841, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.029067277908325, "global_step": 537842, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.063983917236328, "global_step": 537843, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9801247119903564, "global_step": 537844, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.048201084136963, "global_step": 537845, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.091679096221924, "global_step": 537846, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.05781626701355, "global_step": 537847, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0643463134765625, "global_step": 537848, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.107760190963745, "global_step": 537849, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.030388832092285, "global_step": 537850, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.025251626968384, "global_step": 537851, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9851433038711548, "global_step": 537852, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0245273113250732, "global_step": 537853, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1134963035583496, "global_step": 537854, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1064059734344482, "global_step": 537855, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0532114505767822, "global_step": 537856, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.124405860900879, "global_step": 537857, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9298902750015259, "global_step": 537858, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0493276119232178, "global_step": 537859, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0428335666656494, "global_step": 537860, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.969468593597412, "global_step": 537861, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0249557495117188, "global_step": 537862, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0252797603607178, "global_step": 537863, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0762414932250977, "global_step": 537864, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.021007776260376, "global_step": 537865, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0150086879730225, "global_step": 537866, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.10748553276062, "global_step": 537867, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.991534948348999, "global_step": 537868, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0861153602600098, "global_step": 537869, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.059183120727539, "global_step": 537870, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0814218521118164, "global_step": 537871, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.038513660430908, "global_step": 537872, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.031359910964966, "global_step": 537873, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0468180179595947, "global_step": 537874, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9499492645263672, "global_step": 537875, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9427647590637207, "global_step": 537876, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0015389919281006, "global_step": 537877, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0668928623199463, "global_step": 537878, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0456531047821045, "global_step": 537879, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9625481367111206, "global_step": 537880, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.052175521850586, "global_step": 537881, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.960944414138794, "global_step": 537882, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9981629848480225, "global_step": 537883, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0087194442749023, "global_step": 537884, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.066218376159668, "global_step": 537885, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.062391519546509, "global_step": 537886, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0862841606140137, "global_step": 537887, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0161044597625732, "global_step": 537888, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.052351713180542, "global_step": 537889, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0407118797302246, "global_step": 537890, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0478124618530273, "global_step": 537891, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.079594612121582, "global_step": 537892, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.039041519165039, "global_step": 537893, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9949488639831543, "global_step": 537894, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1511805057525635, "global_step": 537895, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1498751640319824, "global_step": 537896, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0605227947235107, "global_step": 537897, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.047656774520874, "global_step": 537898, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0300800800323486, "global_step": 537899, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1119203567504883, "global_step": 537900, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0385360717773438, "global_step": 537901, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.069701910018921, "global_step": 537902, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9971833229064941, "global_step": 537903, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.030399799346924, "global_step": 537904, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.050398349761963, "global_step": 537905, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0090153217315674, "global_step": 537906, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0608012676239014, "global_step": 537907, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.073655605316162, "global_step": 537908, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1446995735168457, "global_step": 537909, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.079638957977295, "global_step": 537910, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9767690896987915, "global_step": 537911, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.001652479171753, "global_step": 537912, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0199532508850098, "global_step": 537913, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0486600399017334, "global_step": 537914, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.114036798477173, "global_step": 537915, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.1275062561035156, "global_step": 537916, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9229700565338135, "global_step": 537917, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.125093460083008, "global_step": 537918, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9721438884735107, "global_step": 537919, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9854320287704468, "global_step": 537920, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.074937343597412, "global_step": 537921, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.068317413330078, "global_step": 537922, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.106968402862549, "global_step": 537923, "epoch": 904, "lr": 5e-05}
{"train_loss": 1.9807257652282715, "global_step": 537924, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0689401626586914, "global_step": 537925, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.108105421066284, "global_step": 537926, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.0371580123901367, "global_step": 537927, "epoch": 904, "lr": 5e-05}
{"train_loss": 2.026179075241089, "global_step": 537928, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1138153076171875, "global_step": 537929, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1354641914367676, "global_step": 537930, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.018235206604004, "global_step": 537931, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.116199254989624, "global_step": 537932, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9735620021820068, "global_step": 537933, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9902558326721191, "global_step": 537934, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9595822095870972, "global_step": 537935, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.091616153717041, "global_step": 537936, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0329020023345947, "global_step": 537937, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.039454221725464, "global_step": 537938, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0883922576904297, "global_step": 537939, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.004458427429199, "global_step": 537940, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.008124589920044, "global_step": 537941, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.046937942504883, "global_step": 537942, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.031313180923462, "global_step": 537943, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0304436683654785, "global_step": 537944, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.067722797393799, "global_step": 537945, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.049973726272583, "global_step": 537946, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0189461708068848, "global_step": 537947, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0440444946289062, "global_step": 537948, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0673184394836426, "global_step": 537949, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9991447925567627, "global_step": 537950, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0546445846557617, "global_step": 537951, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9860293865203857, "global_step": 537952, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9758538007736206, "global_step": 537953, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9794094562530518, "global_step": 537954, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9380931854248047, "global_step": 537955, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0047590732574463, "global_step": 537956, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0564193725585938, "global_step": 537957, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.023257255554199, "global_step": 537958, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0093913078308105, "global_step": 537959, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.073117256164551, "global_step": 537960, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.958118200302124, "global_step": 537961, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9842246770858765, "global_step": 537962, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0456976890563965, "global_step": 537963, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0672767162323, "global_step": 537964, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9806220531463623, "global_step": 537965, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9886996746063232, "global_step": 537966, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.006556272506714, "global_step": 537967, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9422799348831177, "global_step": 537968, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9471527338027954, "global_step": 537969, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1657235622406006, "global_step": 537970, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.015876531600952, "global_step": 537971, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.027374267578125, "global_step": 537972, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9337364435195923, "global_step": 537973, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9923709630966187, "global_step": 537974, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0178136825561523, "global_step": 537975, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.979151725769043, "global_step": 537976, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0898220539093018, "global_step": 537977, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.070084571838379, "global_step": 537978, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.022547483444214, "global_step": 537979, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9985601902008057, "global_step": 537980, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9853990077972412, "global_step": 537981, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0833070278167725, "global_step": 537982, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.062274217605591, "global_step": 537983, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.009000778198242, "global_step": 537984, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.060399055480957, "global_step": 537985, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0801007747650146, "global_step": 537986, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9588911533355713, "global_step": 537987, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9915695190429688, "global_step": 537988, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9609218835830688, "global_step": 537989, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0044913291931152, "global_step": 537990, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9937901496887207, "global_step": 537991, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.8676406145095825, "global_step": 537992, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.084662437438965, "global_step": 537993, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0584588050842285, "global_step": 537994, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0603039264678955, "global_step": 537995, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.065359592437744, "global_step": 537996, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.975379467010498, "global_step": 537997, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9636346101760864, "global_step": 537998, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9714900255203247, "global_step": 537999, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9571956396102905, "global_step": 538000, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.125218152999878, "global_step": 538001, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9651386737823486, "global_step": 538002, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9868457317352295, "global_step": 538003, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.009221076965332, "global_step": 538004, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0664851665496826, "global_step": 538005, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.034215211868286, "global_step": 538006, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.038395404815674, "global_step": 538007, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0217981338500977, "global_step": 538008, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0350024700164795, "global_step": 538009, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.08039927482605, "global_step": 538010, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.999921202659607, "global_step": 538011, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.005673408508301, "global_step": 538012, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9960331916809082, "global_step": 538013, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.00571346282959, "global_step": 538014, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0467610359191895, "global_step": 538015, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.081181287765503, "global_step": 538016, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.005122661590576, "global_step": 538017, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.078702211380005, "global_step": 538018, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9867844581604004, "global_step": 538019, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0388095378875732, "global_step": 538020, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.00488018989563, "global_step": 538021, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0355474948883057, "global_step": 538022, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.985885739326477, "global_step": 538023, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0502521991729736, "global_step": 538024, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0381035804748535, "global_step": 538025, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0363047122955322, "global_step": 538026, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9816745519638062, "global_step": 538027, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9992005825042725, "global_step": 538028, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.076565742492676, "global_step": 538029, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9970996379852295, "global_step": 538030, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0212459564208984, "global_step": 538031, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.957277536392212, "global_step": 538032, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9856640100479126, "global_step": 538033, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.010941505432129, "global_step": 538034, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9728047847747803, "global_step": 538035, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1183485984802246, "global_step": 538036, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0419840812683105, "global_step": 538037, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9975191354751587, "global_step": 538038, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0205183029174805, "global_step": 538039, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.037323474884033, "global_step": 538040, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.974275827407837, "global_step": 538041, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0564472675323486, "global_step": 538042, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.000588893890381, "global_step": 538043, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.984641432762146, "global_step": 538044, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.06282901763916, "global_step": 538045, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0903923511505127, "global_step": 538046, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0010242462158203, "global_step": 538047, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0746748447418213, "global_step": 538048, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0428385734558105, "global_step": 538049, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.037075996398926, "global_step": 538050, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.976423740386963, "global_step": 538051, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.020073413848877, "global_step": 538052, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0919761657714844, "global_step": 538053, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0178894996643066, "global_step": 538054, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1135623455047607, "global_step": 538055, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0044164657592773, "global_step": 538056, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0726206302642822, "global_step": 538057, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1722521781921387, "global_step": 538058, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0634820461273193, "global_step": 538059, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9753649234771729, "global_step": 538060, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0839977264404297, "global_step": 538061, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.058948278427124, "global_step": 538062, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1151468753814697, "global_step": 538063, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0562944412231445, "global_step": 538064, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.021562099456787, "global_step": 538065, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.094494342803955, "global_step": 538066, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.092273712158203, "global_step": 538067, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9948489665985107, "global_step": 538068, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.924172043800354, "global_step": 538069, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0255777835845947, "global_step": 538070, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0127322673797607, "global_step": 538071, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0065577030181885, "global_step": 538072, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.044377088546753, "global_step": 538073, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9317713975906372, "global_step": 538074, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9774706363677979, "global_step": 538075, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.037513256072998, "global_step": 538076, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9461596012115479, "global_step": 538077, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0182220935821533, "global_step": 538078, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.144652843475342, "global_step": 538079, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0317320823669434, "global_step": 538080, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9946128129959106, "global_step": 538081, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9830230474472046, "global_step": 538082, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1102073192596436, "global_step": 538083, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0967750549316406, "global_step": 538084, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.047434091567993, "global_step": 538085, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0731425285339355, "global_step": 538086, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.074622869491577, "global_step": 538087, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0563347339630127, "global_step": 538088, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.114527463912964, "global_step": 538089, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.052248001098633, "global_step": 538090, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.083343744277954, "global_step": 538091, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.041414976119995, "global_step": 538092, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9770296812057495, "global_step": 538093, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.078233242034912, "global_step": 538094, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0254220962524414, "global_step": 538095, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0878238677978516, "global_step": 538096, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0401453971862793, "global_step": 538097, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.973967432975769, "global_step": 538098, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9776058197021484, "global_step": 538099, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0819571018218994, "global_step": 538100, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.045468330383301, "global_step": 538101, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.065805673599243, "global_step": 538102, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.109806537628174, "global_step": 538103, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9707680940628052, "global_step": 538104, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.115230083465576, "global_step": 538105, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.044710874557495, "global_step": 538106, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9718858003616333, "global_step": 538107, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9655615091323853, "global_step": 538108, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.043787717819214, "global_step": 538109, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.049530029296875, "global_step": 538110, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9410167932510376, "global_step": 538111, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0321967601776123, "global_step": 538112, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.10249924659729, "global_step": 538113, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0404746532440186, "global_step": 538114, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9812451601028442, "global_step": 538115, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.005598306655884, "global_step": 538116, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.02347731590271, "global_step": 538117, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9353214502334595, "global_step": 538118, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0473341941833496, "global_step": 538119, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9879804849624634, "global_step": 538120, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9842805862426758, "global_step": 538121, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0035815238952637, "global_step": 538122, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.177896022796631, "global_step": 538123, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0570476055145264, "global_step": 538124, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1105618476867676, "global_step": 538125, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0690369606018066, "global_step": 538126, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0852558612823486, "global_step": 538127, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0384161472320557, "global_step": 538128, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0108025074005127, "global_step": 538129, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0273802280426025, "global_step": 538130, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0513060092926025, "global_step": 538131, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0169601440429688, "global_step": 538132, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0062339305877686, "global_step": 538133, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.067653179168701, "global_step": 538134, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0006015300750732, "global_step": 538135, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0313262939453125, "global_step": 538136, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.09503173828125, "global_step": 538137, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9726786613464355, "global_step": 538138, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0994949340820312, "global_step": 538139, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.024991750717163, "global_step": 538140, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0334489345550537, "global_step": 538141, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0168840885162354, "global_step": 538142, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.087432622909546, "global_step": 538143, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.009840250015259, "global_step": 538144, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.036050319671631, "global_step": 538145, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1161305904388428, "global_step": 538146, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0524935722351074, "global_step": 538147, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0243146419525146, "global_step": 538148, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.046292781829834, "global_step": 538149, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0528318881988525, "global_step": 538150, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9547510147094727, "global_step": 538151, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.978214979171753, "global_step": 538152, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9932458400726318, "global_step": 538153, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0364763736724854, "global_step": 538154, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.009517192840576, "global_step": 538155, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.042844533920288, "global_step": 538156, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.974814772605896, "global_step": 538157, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0618960857391357, "global_step": 538158, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9796513319015503, "global_step": 538159, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.079742431640625, "global_step": 538160, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0218164920806885, "global_step": 538161, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.987592101097107, "global_step": 538162, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.073908805847168, "global_step": 538163, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0287201404571533, "global_step": 538164, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9377208948135376, "global_step": 538165, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9570324420928955, "global_step": 538166, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.03848934173584, "global_step": 538167, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.114039421081543, "global_step": 538168, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0362439155578613, "global_step": 538169, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0362155437469482, "global_step": 538170, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.067910671234131, "global_step": 538171, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.024345874786377, "global_step": 538172, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.12947416305542, "global_step": 538173, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.043010711669922, "global_step": 538174, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.062406301498413, "global_step": 538175, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9851748943328857, "global_step": 538176, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.076441526412964, "global_step": 538177, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0409786701202393, "global_step": 538178, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0825414657592773, "global_step": 538179, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9986177682876587, "global_step": 538180, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0615921020507812, "global_step": 538181, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0021262168884277, "global_step": 538182, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0694024562835693, "global_step": 538183, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0346429347991943, "global_step": 538184, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.03420352935791, "global_step": 538185, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.045823097229004, "global_step": 538186, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0466551780700684, "global_step": 538187, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.143049478530884, "global_step": 538188, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9936163425445557, "global_step": 538189, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.058845281600952, "global_step": 538190, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0627329349517822, "global_step": 538191, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.018132209777832, "global_step": 538192, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.985378623008728, "global_step": 538193, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9514951705932617, "global_step": 538194, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.037909507751465, "global_step": 538195, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9706076383590698, "global_step": 538196, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0275187492370605, "global_step": 538197, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9838192462921143, "global_step": 538198, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0168204307556152, "global_step": 538199, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0094523429870605, "global_step": 538200, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.037597179412842, "global_step": 538201, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9709084033966064, "global_step": 538202, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1294143199920654, "global_step": 538203, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0000641345977783, "global_step": 538204, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0763776302337646, "global_step": 538205, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.028327465057373, "global_step": 538206, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.006129264831543, "global_step": 538207, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.030414581298828, "global_step": 538208, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.105311870574951, "global_step": 538209, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0990805625915527, "global_step": 538210, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1031713485717773, "global_step": 538211, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0587964057922363, "global_step": 538212, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.102086305618286, "global_step": 538213, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0275421142578125, "global_step": 538214, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0163726806640625, "global_step": 538215, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.025482654571533, "global_step": 538216, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9472355842590332, "global_step": 538217, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9706993103027344, "global_step": 538218, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9689466953277588, "global_step": 538219, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.070822238922119, "global_step": 538220, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.056009531021118, "global_step": 538221, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0044968128204346, "global_step": 538222, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.027458429336548, "global_step": 538223, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0421509742736816, "global_step": 538224, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.955028772354126, "global_step": 538225, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.985793113708496, "global_step": 538226, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.022068738937378, "global_step": 538227, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.032702922821045, "global_step": 538228, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.041806697845459, "global_step": 538229, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0143120288848877, "global_step": 538230, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.000798225402832, "global_step": 538231, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.077486991882324, "global_step": 538232, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.059898853302002, "global_step": 538233, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.085099697113037, "global_step": 538234, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.07686448097229, "global_step": 538235, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9619611501693726, "global_step": 538236, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.044879913330078, "global_step": 538237, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.031219005584717, "global_step": 538238, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0857200622558594, "global_step": 538239, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.044468879699707, "global_step": 538240, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0187394618988037, "global_step": 538241, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0464563369750977, "global_step": 538242, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.040919542312622, "global_step": 538243, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.108983039855957, "global_step": 538244, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.053272008895874, "global_step": 538245, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9907236099243164, "global_step": 538246, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9768598079681396, "global_step": 538247, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0126824378967285, "global_step": 538248, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.183976888656616, "global_step": 538249, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0735480785369873, "global_step": 538250, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0478453636169434, "global_step": 538251, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0550537109375, "global_step": 538252, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.037461996078491, "global_step": 538253, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.957619309425354, "global_step": 538254, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0262866020202637, "global_step": 538255, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9902610778808594, "global_step": 538256, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.075216770172119, "global_step": 538257, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.042743444442749, "global_step": 538258, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0230801105499268, "global_step": 538259, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9845815896987915, "global_step": 538260, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9457975625991821, "global_step": 538261, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.094572067260742, "global_step": 538262, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0400736331939697, "global_step": 538263, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0344271659851074, "global_step": 538264, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0092856884002686, "global_step": 538265, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.173947334289551, "global_step": 538266, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1013474464416504, "global_step": 538267, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1326730251312256, "global_step": 538268, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0547878742218018, "global_step": 538269, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.008437156677246, "global_step": 538270, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.049426317214966, "global_step": 538271, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1302425861358643, "global_step": 538272, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.136918067932129, "global_step": 538273, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.034036159515381, "global_step": 538274, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0076351165771484, "global_step": 538275, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.009190320968628, "global_step": 538276, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0509469509124756, "global_step": 538277, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0032730102539062, "global_step": 538278, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.046670913696289, "global_step": 538279, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.04190993309021, "global_step": 538280, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0177526473999023, "global_step": 538281, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.023686170578003, "global_step": 538282, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0552773475646973, "global_step": 538283, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0564751625061035, "global_step": 538284, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1080210208892822, "global_step": 538285, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.088494300842285, "global_step": 538286, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1012582778930664, "global_step": 538287, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9725533723831177, "global_step": 538288, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0460712909698486, "global_step": 538289, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1190788745880127, "global_step": 538290, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0042684078216553, "global_step": 538291, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0016889572143555, "global_step": 538292, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.025378465652466, "global_step": 538293, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0260796546936035, "global_step": 538294, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0057854652404785, "global_step": 538295, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.048163890838623, "global_step": 538296, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9943302869796753, "global_step": 538297, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0026447772979736, "global_step": 538298, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.068305492401123, "global_step": 538299, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9929183721542358, "global_step": 538300, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.137798547744751, "global_step": 538301, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0919666290283203, "global_step": 538302, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.051943063735962, "global_step": 538303, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.033018112182617, "global_step": 538304, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.092508316040039, "global_step": 538305, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9828546047210693, "global_step": 538306, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.017082929611206, "global_step": 538307, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9637659788131714, "global_step": 538308, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0448203086853027, "global_step": 538309, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.007826566696167, "global_step": 538310, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0810062885284424, "global_step": 538311, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9966038465499878, "global_step": 538312, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0910444259643555, "global_step": 538313, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9380133152008057, "global_step": 538314, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0257513523101807, "global_step": 538315, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0196361541748047, "global_step": 538316, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.167706251144409, "global_step": 538317, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0215396881103516, "global_step": 538318, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.014033794403076, "global_step": 538319, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.044569730758667, "global_step": 538320, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.117743968963623, "global_step": 538321, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9434893131256104, "global_step": 538322, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0245189666748047, "global_step": 538323, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0827972888946533, "global_step": 538324, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0955617427825928, "global_step": 538325, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.978074073791504, "global_step": 538326, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.062443494796753, "global_step": 538327, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0105881690979004, "global_step": 538328, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0890953540802, "global_step": 538329, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.052377223968506, "global_step": 538330, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9968185424804688, "global_step": 538331, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9623578786849976, "global_step": 538332, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.009166717529297, "global_step": 538333, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9501211643218994, "global_step": 538334, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0768916606903076, "global_step": 538335, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.953844428062439, "global_step": 538336, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0236122608184814, "global_step": 538337, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0212900638580322, "global_step": 538338, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.022554397583008, "global_step": 538339, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0120046138763428, "global_step": 538340, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0259716510772705, "global_step": 538341, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0594067573547363, "global_step": 538342, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.129958152770996, "global_step": 538343, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.037365674972534, "global_step": 538344, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0661909580230713, "global_step": 538345, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9123579263687134, "global_step": 538346, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.027007579803467, "global_step": 538347, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.108738660812378, "global_step": 538348, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0627052783966064, "global_step": 538349, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.071532964706421, "global_step": 538350, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0317132472991943, "global_step": 538351, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.020806074142456, "global_step": 538352, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.997206687927246, "global_step": 538353, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.00207781791687, "global_step": 538354, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.121936559677124, "global_step": 538355, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9909276962280273, "global_step": 538356, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0563745498657227, "global_step": 538357, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.983035683631897, "global_step": 538358, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0135815143585205, "global_step": 538359, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.037601947784424, "global_step": 538360, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.024057149887085, "global_step": 538361, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.005631685256958, "global_step": 538362, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0050947666168213, "global_step": 538363, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0749545097351074, "global_step": 538364, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.061410665512085, "global_step": 538365, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.018009662628174, "global_step": 538366, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1434481143951416, "global_step": 538367, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.080531120300293, "global_step": 538368, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.050194263458252, "global_step": 538369, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.067174196243286, "global_step": 538370, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0405113697052, "global_step": 538371, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0396413803100586, "global_step": 538372, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.074918031692505, "global_step": 538373, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.036696195602417, "global_step": 538374, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.060462474822998, "global_step": 538375, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.007509708404541, "global_step": 538376, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9388684034347534, "global_step": 538377, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9861212968826294, "global_step": 538378, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0069053173065186, "global_step": 538379, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.007007122039795, "global_step": 538380, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9547240734100342, "global_step": 538381, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.959897756576538, "global_step": 538382, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.057149887084961, "global_step": 538383, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0513343811035156, "global_step": 538384, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9836018085479736, "global_step": 538385, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.059856653213501, "global_step": 538386, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.091761589050293, "global_step": 538387, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.979471206665039, "global_step": 538388, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9799385070800781, "global_step": 538389, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.103332281112671, "global_step": 538390, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9971120357513428, "global_step": 538391, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.112154006958008, "global_step": 538392, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.030346155166626, "global_step": 538393, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0237233638763428, "global_step": 538394, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0843846797943115, "global_step": 538395, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0101613998413086, "global_step": 538396, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1547937393188477, "global_step": 538397, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.088721990585327, "global_step": 538398, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1295409202575684, "global_step": 538399, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.973308801651001, "global_step": 538400, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.978865623474121, "global_step": 538401, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.09694504737854, "global_step": 538402, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9574698209762573, "global_step": 538403, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0228350162506104, "global_step": 538404, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.049896717071533, "global_step": 538405, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0807607173919678, "global_step": 538406, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.017343282699585, "global_step": 538407, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.05730938911438, "global_step": 538408, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.049151659011841, "global_step": 538409, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0720677375793457, "global_step": 538410, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0251870155334473, "global_step": 538411, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.045633554458618, "global_step": 538412, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.97825026512146, "global_step": 538413, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0195512771606445, "global_step": 538414, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.055154323577881, "global_step": 538415, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0122244358062744, "global_step": 538416, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0533394813537598, "global_step": 538417, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9676674604415894, "global_step": 538418, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0119729042053223, "global_step": 538419, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9936575889587402, "global_step": 538420, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.088466167449951, "global_step": 538421, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0795602798461914, "global_step": 538422, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.072572946548462, "global_step": 538423, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0639634132385254, "global_step": 538424, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.035128593444824, "global_step": 538425, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9331411123275757, "global_step": 538426, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9834152460098267, "global_step": 538427, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.112581968307495, "global_step": 538428, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0302815437316895, "global_step": 538429, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9857980012893677, "global_step": 538430, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.033971071243286, "global_step": 538431, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.174903631210327, "global_step": 538432, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0841500759124756, "global_step": 538433, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.963879942893982, "global_step": 538434, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0179977416992188, "global_step": 538435, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.040081739425659, "global_step": 538436, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9860700368881226, "global_step": 538437, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1247923374176025, "global_step": 538438, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.999002456665039, "global_step": 538439, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.046208143234253, "global_step": 538440, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0198962688446045, "global_step": 538441, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0535032749176025, "global_step": 538442, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9997676610946655, "global_step": 538443, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1145246028900146, "global_step": 538444, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0728580951690674, "global_step": 538445, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.019151449203491, "global_step": 538446, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0370190143585205, "global_step": 538447, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0264620780944824, "global_step": 538448, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0724427700042725, "global_step": 538449, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9502944946289062, "global_step": 538450, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9801830053329468, "global_step": 538451, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0835509300231934, "global_step": 538452, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0141875743865967, "global_step": 538453, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.015848159790039, "global_step": 538454, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.019245147705078, "global_step": 538455, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9822595119476318, "global_step": 538456, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0784897804260254, "global_step": 538457, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0050711631774902, "global_step": 538458, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.064065933227539, "global_step": 538459, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0210955142974854, "global_step": 538460, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0282695293426514, "global_step": 538461, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.009572744369507, "global_step": 538462, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.046660900115967, "global_step": 538463, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0502407550811768, "global_step": 538464, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0602810382843018, "global_step": 538465, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.065080165863037, "global_step": 538466, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0506107807159424, "global_step": 538467, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.049635648727417, "global_step": 538468, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0496764183044434, "global_step": 538469, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.022697925567627, "global_step": 538470, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.05436635017395, "global_step": 538471, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9404687881469727, "global_step": 538472, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.012110948562622, "global_step": 538473, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.097595691680908, "global_step": 538474, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0542306900024414, "global_step": 538475, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.088944911956787, "global_step": 538476, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.104172706604004, "global_step": 538477, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.012115240097046, "global_step": 538478, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.058027982711792, "global_step": 538479, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1016011238098145, "global_step": 538480, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.033013343811035, "global_step": 538481, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.106389284133911, "global_step": 538482, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0131568908691406, "global_step": 538483, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0309040546417236, "global_step": 538484, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.018338441848755, "global_step": 538485, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0656778812408447, "global_step": 538486, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.087402582168579, "global_step": 538487, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.082285165786743, "global_step": 538488, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.959174633026123, "global_step": 538489, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.037576675415039, "global_step": 538490, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9472676515579224, "global_step": 538491, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9883527755737305, "global_step": 538492, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.989993929862976, "global_step": 538493, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.107213258743286, "global_step": 538494, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0941383838653564, "global_step": 538495, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0253655910491943, "global_step": 538496, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0900943279266357, "global_step": 538497, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.107529878616333, "global_step": 538498, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.013948440551758, "global_step": 538499, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.03275990486145, "global_step": 538500, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9871641397476196, "global_step": 538501, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.985430121421814, "global_step": 538502, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0463974475860596, "global_step": 538503, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.054194450378418, "global_step": 538504, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0753657817840576, "global_step": 538505, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.008988380432129, "global_step": 538506, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9956871271133423, "global_step": 538507, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9558409452438354, "global_step": 538508, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.116915464401245, "global_step": 538509, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0339229106903076, "global_step": 538510, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.056645393371582, "global_step": 538511, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.025702714920044, "global_step": 538512, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0139520168304443, "global_step": 538513, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0180296897888184, "global_step": 538514, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0312914848327637, "global_step": 538515, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.009780168533325, "global_step": 538516, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9571685791015625, "global_step": 538517, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9830374717712402, "global_step": 538518, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0525782108306885, "global_step": 538519, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.026189088821411, "global_step": 538520, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0901200771331787, "global_step": 538521, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0176379680633545, "global_step": 538522, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0380616188049316, "global_step": 538523, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.023423910140991, "global_step": 538524, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.020261764526367, "global_step": 538525, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9684869050979614, "global_step": 538526, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9489301443099976, "global_step": 538527, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.050004243850708, "global_step": 538528, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.974368691444397, "global_step": 538529, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.038114547729492, "global_step": 538530, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0584585666656494, "global_step": 538531, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1110599040985107, "global_step": 538532, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.119356632232666, "global_step": 538533, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.145651340484619, "global_step": 538534, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0350732803344727, "global_step": 538535, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0970230102539062, "global_step": 538536, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9962040185928345, "global_step": 538537, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0098226070404053, "global_step": 538538, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1078944206237793, "global_step": 538539, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.034163236618042, "global_step": 538540, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.062704086303711, "global_step": 538541, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0827016830444336, "global_step": 538542, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9806782007217407, "global_step": 538543, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.080517530441284, "global_step": 538544, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0255749225616455, "global_step": 538545, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.06195068359375, "global_step": 538546, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0041046142578125, "global_step": 538547, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.981126308441162, "global_step": 538548, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.073141098022461, "global_step": 538549, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.983789324760437, "global_step": 538550, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.046755790710449, "global_step": 538551, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1124699115753174, "global_step": 538552, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9620931148529053, "global_step": 538553, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.126391887664795, "global_step": 538554, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0192794799804688, "global_step": 538555, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.008134365081787, "global_step": 538556, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9684697389602661, "global_step": 538557, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9781246185302734, "global_step": 538558, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.037419080734253, "global_step": 538559, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9541414976119995, "global_step": 538560, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.001774549484253, "global_step": 538561, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.065140962600708, "global_step": 538562, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.051501512527466, "global_step": 538563, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0788016319274902, "global_step": 538564, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9642879962921143, "global_step": 538565, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0787734985351562, "global_step": 538566, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.04380202293396, "global_step": 538567, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0999979972839355, "global_step": 538568, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.051093101501465, "global_step": 538569, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0140349864959717, "global_step": 538570, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.013782024383545, "global_step": 538571, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0470004081726074, "global_step": 538572, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.075181007385254, "global_step": 538573, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1294617652893066, "global_step": 538574, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0101630687713623, "global_step": 538575, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.047593116760254, "global_step": 538576, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0694985389709473, "global_step": 538577, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0336742401123047, "global_step": 538578, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1291232109069824, "global_step": 538579, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.044095277786255, "global_step": 538580, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0142810344696045, "global_step": 538581, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.049461841583252, "global_step": 538582, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0837762355804443, "global_step": 538583, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0520365238189697, "global_step": 538584, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.8823379278182983, "global_step": 538585, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0051844120025635, "global_step": 538586, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9376462697982788, "global_step": 538587, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9872868061065674, "global_step": 538588, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9925116300582886, "global_step": 538589, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9290368556976318, "global_step": 538590, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0474352836608887, "global_step": 538591, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.145672559738159, "global_step": 538592, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9944343566894531, "global_step": 538593, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0599594116210938, "global_step": 538594, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9984922409057617, "global_step": 538595, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9393633604049683, "global_step": 538596, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0441269874572754, "global_step": 538597, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.01590633392334, "global_step": 538598, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0002288818359375, "global_step": 538599, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.896073818206787, "global_step": 538600, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.003753423690796, "global_step": 538601, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0072314739227295, "global_step": 538602, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0057711601257324, "global_step": 538603, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.958109974861145, "global_step": 538604, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0429229736328125, "global_step": 538605, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0551745891571045, "global_step": 538606, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0314064025878906, "global_step": 538607, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.140559673309326, "global_step": 538608, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0613696575164795, "global_step": 538609, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0609793663024902, "global_step": 538610, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1172351837158203, "global_step": 538611, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9868377447128296, "global_step": 538612, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.097017526626587, "global_step": 538613, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9683363437652588, "global_step": 538614, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0193917751312256, "global_step": 538615, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.990329623222351, "global_step": 538616, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.007376194000244, "global_step": 538617, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9950727224349976, "global_step": 538618, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.077216148376465, "global_step": 538619, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0590851306915283, "global_step": 538620, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9779458045959473, "global_step": 538621, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9999653100967407, "global_step": 538622, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.036729335784912, "global_step": 538623, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.978363037109375, "global_step": 538624, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1026408672332764, "global_step": 538625, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0202643871307373, "global_step": 538626, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.922875165939331, "global_step": 538627, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0090739727020264, "global_step": 538628, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0233089923858643, "global_step": 538629, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9815605878829956, "global_step": 538630, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0171570777893066, "global_step": 538631, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.09159779548645, "global_step": 538632, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0205743312835693, "global_step": 538633, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0006542205810547, "global_step": 538634, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.149747610092163, "global_step": 538635, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0839948654174805, "global_step": 538636, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0848634243011475, "global_step": 538637, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0519285202026367, "global_step": 538638, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0029819011688232, "global_step": 538639, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9429222345352173, "global_step": 538640, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9234322309494019, "global_step": 538641, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0082926750183105, "global_step": 538642, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.98062264919281, "global_step": 538643, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0890591144561768, "global_step": 538644, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0004990100860596, "global_step": 538645, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.992971658706665, "global_step": 538646, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0482587814331055, "global_step": 538647, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9513133764266968, "global_step": 538648, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.083380937576294, "global_step": 538649, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0767202377319336, "global_step": 538650, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.085411787033081, "global_step": 538651, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9758819341659546, "global_step": 538652, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.127634048461914, "global_step": 538653, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0546107292175293, "global_step": 538654, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.03999400138855, "global_step": 538655, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0678789615631104, "global_step": 538656, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0113906860351562, "global_step": 538657, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0237796306610107, "global_step": 538658, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1024439334869385, "global_step": 538659, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.098031520843506, "global_step": 538660, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.036020040512085, "global_step": 538661, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0569522380828857, "global_step": 538662, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0132901668548584, "global_step": 538663, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9892656803131104, "global_step": 538664, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.017092227935791, "global_step": 538665, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0662996768951416, "global_step": 538666, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0410890579223633, "global_step": 538667, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9789032936096191, "global_step": 538668, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0899386405944824, "global_step": 538669, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0010077953338623, "global_step": 538670, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9655970335006714, "global_step": 538671, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0494766235351562, "global_step": 538672, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9822882413864136, "global_step": 538673, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0473523139953613, "global_step": 538674, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.054959535598755, "global_step": 538675, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0567357540130615, "global_step": 538676, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0017552375793457, "global_step": 538677, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.048264741897583, "global_step": 538678, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0254950523376465, "global_step": 538679, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.981012225151062, "global_step": 538680, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.066432237625122, "global_step": 538681, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.034952163696289, "global_step": 538682, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9628630876541138, "global_step": 538683, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0180258750915527, "global_step": 538684, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.082900047302246, "global_step": 538685, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.083263397216797, "global_step": 538686, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1015830039978027, "global_step": 538687, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0024430751800537, "global_step": 538688, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1196043491363525, "global_step": 538689, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.040562868118286, "global_step": 538690, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.119314670562744, "global_step": 538691, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.025891065597534, "global_step": 538692, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.088141441345215, "global_step": 538693, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9979606866836548, "global_step": 538694, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.064762592315674, "global_step": 538695, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0562686920166016, "global_step": 538696, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9817943572998047, "global_step": 538697, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.054600477218628, "global_step": 538698, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.023493766784668, "global_step": 538699, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9987586736679077, "global_step": 538700, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0392284393310547, "global_step": 538701, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.016953229904175, "global_step": 538702, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.071268081665039, "global_step": 538703, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0275042057037354, "global_step": 538704, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0013914108276367, "global_step": 538705, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.114960193634033, "global_step": 538706, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1244308948516846, "global_step": 538707, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.057950258255005, "global_step": 538708, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9934735298156738, "global_step": 538709, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0243818759918213, "global_step": 538710, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.081897735595703, "global_step": 538711, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0322773456573486, "global_step": 538712, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.034979820251465, "global_step": 538713, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.054593086242676, "global_step": 538714, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0705230236053467, "global_step": 538715, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9379260540008545, "global_step": 538716, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9880023002624512, "global_step": 538717, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.048030376434326, "global_step": 538718, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.080138921737671, "global_step": 538719, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.065171957015991, "global_step": 538720, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1677372455596924, "global_step": 538721, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9923120737075806, "global_step": 538722, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0714573860168457, "global_step": 538723, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.97018563747406, "global_step": 538724, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9657161235809326, "global_step": 538725, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0759007930755615, "global_step": 538726, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.2126448154449463, "global_step": 538727, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0056004524230957, "global_step": 538728, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.016507863998413, "global_step": 538729, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.044938087463379, "global_step": 538730, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.116671323776245, "global_step": 538731, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1288771629333496, "global_step": 538732, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.049006223678589, "global_step": 538733, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0715298652648926, "global_step": 538734, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0516927242279053, "global_step": 538735, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0840444564819336, "global_step": 538736, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1219065189361572, "global_step": 538737, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.051051616668701, "global_step": 538738, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0159242153167725, "global_step": 538739, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.017548084259033, "global_step": 538740, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9513564109802246, "global_step": 538741, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0180485248565674, "global_step": 538742, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0370185375213623, "global_step": 538743, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.063408851623535, "global_step": 538744, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1227474212646484, "global_step": 538745, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.074793815612793, "global_step": 538746, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.040132761001587, "global_step": 538747, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0581040382385254, "global_step": 538748, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.013762950897217, "global_step": 538749, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.101425886154175, "global_step": 538750, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.064316987991333, "global_step": 538751, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0687668323516846, "global_step": 538752, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0165209770202637, "global_step": 538753, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.082221269607544, "global_step": 538754, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0830414295196533, "global_step": 538755, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0989842414855957, "global_step": 538756, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0488550662994385, "global_step": 538757, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9085232019424438, "global_step": 538758, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.085543155670166, "global_step": 538759, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0438473224639893, "global_step": 538760, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.062875986099243, "global_step": 538761, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9549118280410767, "global_step": 538762, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0087854862213135, "global_step": 538763, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.086235761642456, "global_step": 538764, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0174505710601807, "global_step": 538765, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.05241060256958, "global_step": 538766, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0990116596221924, "global_step": 538767, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.991806149482727, "global_step": 538768, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.000133514404297, "global_step": 538769, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.061687469482422, "global_step": 538770, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0535709857940674, "global_step": 538771, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.043119192123413, "global_step": 538772, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.026550769805908, "global_step": 538773, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.053877115249634, "global_step": 538774, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0570297241210938, "global_step": 538775, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.091076374053955, "global_step": 538776, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0060603618621826, "global_step": 538777, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.039634943008423, "global_step": 538778, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0963823795318604, "global_step": 538779, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0487289428710938, "global_step": 538780, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.121739387512207, "global_step": 538781, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.008467674255371, "global_step": 538782, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.107799530029297, "global_step": 538783, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.075479507446289, "global_step": 538784, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0760812759399414, "global_step": 538785, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0472922325134277, "global_step": 538786, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0645406246185303, "global_step": 538787, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0679452419281006, "global_step": 538788, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0230021476745605, "global_step": 538789, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.995604395866394, "global_step": 538790, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0284507274627686, "global_step": 538791, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0312368869781494, "global_step": 538792, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0186195373535156, "global_step": 538793, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.095733880996704, "global_step": 538794, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.992519497871399, "global_step": 538795, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.01294207572937, "global_step": 538796, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0738768577575684, "global_step": 538797, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0139400959014893, "global_step": 538798, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9980740547180176, "global_step": 538799, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0812764167785645, "global_step": 538800, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0957894325256348, "global_step": 538801, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.071155071258545, "global_step": 538802, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0440282821655273, "global_step": 538803, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0682921409606934, "global_step": 538804, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9944937229156494, "global_step": 538805, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.067723035812378, "global_step": 538806, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0494954586029053, "global_step": 538807, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1546733379364014, "global_step": 538808, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0626912117004395, "global_step": 538809, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0363948345184326, "global_step": 538810, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0000698566436768, "global_step": 538811, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0522892475128174, "global_step": 538812, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9860444068908691, "global_step": 538813, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0629518032073975, "global_step": 538814, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0762035846710205, "global_step": 538815, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0312693119049072, "global_step": 538816, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0960745811462402, "global_step": 538817, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9846041202545166, "global_step": 538818, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0685536861419678, "global_step": 538819, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9605169296264648, "global_step": 538820, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0110645294189453, "global_step": 538821, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.101365566253662, "global_step": 538822, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.025932550430298, "global_step": 538823, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.003146171569824, "global_step": 538824, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0964536666870117, "global_step": 538825, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0608139038085938, "global_step": 538826, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.076902151107788, "global_step": 538827, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0180485248565674, "global_step": 538828, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0253305435180664, "global_step": 538829, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.020946979522705, "global_step": 538830, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.002495527267456, "global_step": 538831, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0130789279937744, "global_step": 538832, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.028982400894165, "global_step": 538833, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.006084442138672, "global_step": 538834, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.125561237335205, "global_step": 538835, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.100421190261841, "global_step": 538836, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.063723087310791, "global_step": 538837, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0356996059417725, "global_step": 538838, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.099487781524658, "global_step": 538839, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0812435150146484, "global_step": 538840, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0334954261779785, "global_step": 538841, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.102262258529663, "global_step": 538842, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0387284755706787, "global_step": 538843, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0029871463775635, "global_step": 538844, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0644776821136475, "global_step": 538845, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.100529193878174, "global_step": 538846, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1156387329101562, "global_step": 538847, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.01596736907959, "global_step": 538848, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.053288698196411, "global_step": 538849, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0979270935058594, "global_step": 538850, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9557383060455322, "global_step": 538851, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.079042911529541, "global_step": 538852, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.225707530975342, "global_step": 538853, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.056859016418457, "global_step": 538854, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0561017990112305, "global_step": 538855, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.027712345123291, "global_step": 538856, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.043539524078369, "global_step": 538857, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9715216159820557, "global_step": 538858, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9922305345535278, "global_step": 538859, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0382256507873535, "global_step": 538860, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.050854206085205, "global_step": 538861, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0947654247283936, "global_step": 538862, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0036120414733887, "global_step": 538863, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.997790813446045, "global_step": 538864, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.048691987991333, "global_step": 538865, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9877769947052002, "global_step": 538866, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.997381329536438, "global_step": 538867, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.059485673904419, "global_step": 538868, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0383713245391846, "global_step": 538869, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0312840938568115, "global_step": 538870, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0713319778442383, "global_step": 538871, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9564297199249268, "global_step": 538872, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0136361122131348, "global_step": 538873, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9752426147460938, "global_step": 538874, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.201716661453247, "global_step": 538875, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.01442551612854, "global_step": 538876, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1098670959472656, "global_step": 538877, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.118776321411133, "global_step": 538878, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.036757230758667, "global_step": 538879, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0060718059539795, "global_step": 538880, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.04093599319458, "global_step": 538881, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0979652404785156, "global_step": 538882, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.067209482192993, "global_step": 538883, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9444435834884644, "global_step": 538884, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0095527172088623, "global_step": 538885, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0280942916870117, "global_step": 538886, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.1792995929718018, "global_step": 538887, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.037975311279297, "global_step": 538888, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0299291610717773, "global_step": 538889, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0668227672576904, "global_step": 538890, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0226871967315674, "global_step": 538891, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.932051420211792, "global_step": 538892, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0569398403167725, "global_step": 538893, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.060554027557373, "global_step": 538894, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9821335077285767, "global_step": 538895, "epoch": 905, "lr": 5e-05}
{"train_loss": 2.0365021228790283, "global_step": 538896, "epoch": 905, "lr": 5e-05}
{"train_loss": 1.9975230693817139, "global_step": 538897, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.055682897567749, "global_step": 538898, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.042419910430908, "global_step": 538899, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.035423755645752, "global_step": 538900, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.019160032272339, "global_step": 538901, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9923738241195679, "global_step": 538902, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.075670003890991, "global_step": 538903, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9455900192260742, "global_step": 538904, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.053150177001953, "global_step": 538905, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.060455560684204, "global_step": 538906, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9708887338638306, "global_step": 538907, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0124502182006836, "global_step": 538908, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.01554799079895, "global_step": 538909, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9628725051879883, "global_step": 538910, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9130724668502808, "global_step": 538911, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9603899717330933, "global_step": 538912, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0296785831451416, "global_step": 538913, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0800232887268066, "global_step": 538914, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9066532850265503, "global_step": 538915, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.984572172164917, "global_step": 538916, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.989547848701477, "global_step": 538917, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0447163581848145, "global_step": 538918, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0043373107910156, "global_step": 538919, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.091174840927124, "global_step": 538920, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9489206075668335, "global_step": 538921, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0780210494995117, "global_step": 538922, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9248559474945068, "global_step": 538923, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0055716037750244, "global_step": 538924, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.058753728866577, "global_step": 538925, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0662646293640137, "global_step": 538926, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9855973720550537, "global_step": 538927, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9981372356414795, "global_step": 538928, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0465688705444336, "global_step": 538929, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9762482643127441, "global_step": 538930, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1466472148895264, "global_step": 538931, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.04896879196167, "global_step": 538932, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0783114433288574, "global_step": 538933, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9680665731430054, "global_step": 538934, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.088486671447754, "global_step": 538935, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0433008670806885, "global_step": 538936, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.093931198120117, "global_step": 538937, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0158281326293945, "global_step": 538938, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9511091709136963, "global_step": 538939, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9991614818572998, "global_step": 538940, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.977068305015564, "global_step": 538941, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9522827863693237, "global_step": 538942, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0304672718048096, "global_step": 538943, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0998079776763916, "global_step": 538944, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0824382305145264, "global_step": 538945, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0345168113708496, "global_step": 538946, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.02573561668396, "global_step": 538947, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0597927570343018, "global_step": 538948, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.03275728225708, "global_step": 538949, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.009876012802124, "global_step": 538950, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9378957748413086, "global_step": 538951, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0500850677490234, "global_step": 538952, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.051741123199463, "global_step": 538953, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0180470943450928, "global_step": 538954, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0774641036987305, "global_step": 538955, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9210090637207031, "global_step": 538956, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0416619777679443, "global_step": 538957, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.078914165496826, "global_step": 538958, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9586807489395142, "global_step": 538959, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.005143165588379, "global_step": 538960, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0386431217193604, "global_step": 538961, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0608808994293213, "global_step": 538962, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9836457967758179, "global_step": 538963, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9594535827636719, "global_step": 538964, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.017435073852539, "global_step": 538965, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0718958377838135, "global_step": 538966, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1039533615112305, "global_step": 538967, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.94606614112854, "global_step": 538968, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0095012187957764, "global_step": 538969, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0335490703582764, "global_step": 538970, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0568253993988037, "global_step": 538971, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9682199954986572, "global_step": 538972, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.998441457748413, "global_step": 538973, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1052308082580566, "global_step": 538974, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0006914138793945, "global_step": 538975, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0471043586730957, "global_step": 538976, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9814388751983643, "global_step": 538977, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0385329723358154, "global_step": 538978, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9651718139648438, "global_step": 538979, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9969782829284668, "global_step": 538980, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.061960458755493, "global_step": 538981, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0022218227386475, "global_step": 538982, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.924234390258789, "global_step": 538983, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0641791820526123, "global_step": 538984, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0079166889190674, "global_step": 538985, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0625462532043457, "global_step": 538986, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.089345932006836, "global_step": 538987, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9831054210662842, "global_step": 538988, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1029255390167236, "global_step": 538989, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.069016695022583, "global_step": 538990, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0711469650268555, "global_step": 538991, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.012768507003784, "global_step": 538992, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.021026134490967, "global_step": 538993, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0726253986358643, "global_step": 538994, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.055807590484619, "global_step": 538995, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9961671829223633, "global_step": 538996, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9600669145584106, "global_step": 538997, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9568465948104858, "global_step": 538998, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.017040491104126, "global_step": 538999, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0093560218811035, "global_step": 539000, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9993277788162231, "global_step": 539001, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.044171094894409, "global_step": 539002, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9917482137680054, "global_step": 539003, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1177191734313965, "global_step": 539004, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0541181564331055, "global_step": 539005, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9232714176177979, "global_step": 539006, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9820719957351685, "global_step": 539007, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.8958595991134644, "global_step": 539008, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.013176441192627, "global_step": 539009, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1161255836486816, "global_step": 539010, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0537729263305664, "global_step": 539011, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.06685733795166, "global_step": 539012, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.8896068334579468, "global_step": 539013, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9841995239257812, "global_step": 539014, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0189144611358643, "global_step": 539015, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0045223236083984, "global_step": 539016, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9946140050888062, "global_step": 539017, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.073477029800415, "global_step": 539018, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0213541984558105, "global_step": 539019, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9915231466293335, "global_step": 539020, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0051896572113037, "global_step": 539021, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.986452341079712, "global_step": 539022, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0452682971954346, "global_step": 539023, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.998437523841858, "global_step": 539024, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0766520500183105, "global_step": 539025, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9800125360488892, "global_step": 539026, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.999025583267212, "global_step": 539027, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0041377544403076, "global_step": 539028, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.019958019256592, "global_step": 539029, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.055027961730957, "global_step": 539030, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.052657127380371, "global_step": 539031, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.032136917114258, "global_step": 539032, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9813597202301025, "global_step": 539033, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.179598093032837, "global_step": 539034, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0372884273529053, "global_step": 539035, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1150336265563965, "global_step": 539036, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.036602020263672, "global_step": 539037, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.984561800956726, "global_step": 539038, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.97762131690979, "global_step": 539039, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9515738487243652, "global_step": 539040, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9776718616485596, "global_step": 539041, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.991762638092041, "global_step": 539042, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9651304483413696, "global_step": 539043, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9957903623580933, "global_step": 539044, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0203371047973633, "global_step": 539045, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0333991050720215, "global_step": 539046, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.013352870941162, "global_step": 539047, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.046156406402588, "global_step": 539048, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0656683444976807, "global_step": 539049, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.969783902168274, "global_step": 539050, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9954997301101685, "global_step": 539051, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.062598466873169, "global_step": 539052, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9716302156448364, "global_step": 539053, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9605298042297363, "global_step": 539054, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9903347492218018, "global_step": 539055, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0430104732513428, "global_step": 539056, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.005685567855835, "global_step": 539057, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.974117398262024, "global_step": 539058, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0363993644714355, "global_step": 539059, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.090786933898926, "global_step": 539060, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9514037370681763, "global_step": 539061, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.044363260269165, "global_step": 539062, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0808751583099365, "global_step": 539063, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.049311876296997, "global_step": 539064, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9849785566329956, "global_step": 539065, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0239014625549316, "global_step": 539066, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0179336071014404, "global_step": 539067, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.04935884475708, "global_step": 539068, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9916330575942993, "global_step": 539069, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.057577133178711, "global_step": 539070, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9613317251205444, "global_step": 539071, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0094821453094482, "global_step": 539072, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0272607803344727, "global_step": 539073, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0346736907958984, "global_step": 539074, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0432374477386475, "global_step": 539075, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0382497310638428, "global_step": 539076, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.122032642364502, "global_step": 539077, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0007219314575195, "global_step": 539078, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.042285442352295, "global_step": 539079, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0314600467681885, "global_step": 539080, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0923352241516113, "global_step": 539081, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1081390380859375, "global_step": 539082, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.071775197982788, "global_step": 539083, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0828351974487305, "global_step": 539084, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.088339328765869, "global_step": 539085, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0114712715148926, "global_step": 539086, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9813193082809448, "global_step": 539087, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9968316555023193, "global_step": 539088, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.974609613418579, "global_step": 539089, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0621695518493652, "global_step": 539090, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.087456703186035, "global_step": 539091, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0701467990875244, "global_step": 539092, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9945943355560303, "global_step": 539093, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0458309650421143, "global_step": 539094, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0391697883605957, "global_step": 539095, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.061553716659546, "global_step": 539096, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0335071086883545, "global_step": 539097, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9577933549880981, "global_step": 539098, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0320146083831787, "global_step": 539099, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0286524295806885, "global_step": 539100, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0233750343322754, "global_step": 539101, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.072235584259033, "global_step": 539102, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0952136516571045, "global_step": 539103, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0757176876068115, "global_step": 539104, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0221896171569824, "global_step": 539105, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0158028602600098, "global_step": 539106, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.050072431564331, "global_step": 539107, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9905595779418945, "global_step": 539108, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9059677124023438, "global_step": 539109, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0041706562042236, "global_step": 539110, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9647265672683716, "global_step": 539111, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0641679763793945, "global_step": 539112, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0906741619110107, "global_step": 539113, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.081555128097534, "global_step": 539114, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9366791248321533, "global_step": 539115, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.025509834289551, "global_step": 539116, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.014064311981201, "global_step": 539117, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0898778438568115, "global_step": 539118, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9633780717849731, "global_step": 539119, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0414769649505615, "global_step": 539120, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9866293668746948, "global_step": 539121, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.121577024459839, "global_step": 539122, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0067837238311768, "global_step": 539123, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0185821056365967, "global_step": 539124, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9669591188430786, "global_step": 539125, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0904312133789062, "global_step": 539126, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.05417537689209, "global_step": 539127, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0209386348724365, "global_step": 539128, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9915919303894043, "global_step": 539129, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9812147617340088, "global_step": 539130, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.022282838821411, "global_step": 539131, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.027184009552002, "global_step": 539132, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0828328132629395, "global_step": 539133, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0533790588378906, "global_step": 539134, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0185415744781494, "global_step": 539135, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.04093861579895, "global_step": 539136, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.013031482696533, "global_step": 539137, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.104283094406128, "global_step": 539138, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.049999713897705, "global_step": 539139, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.033505916595459, "global_step": 539140, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9639980792999268, "global_step": 539141, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0883800983428955, "global_step": 539142, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.009347438812256, "global_step": 539143, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.061187744140625, "global_step": 539144, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.981128215789795, "global_step": 539145, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1095402240753174, "global_step": 539146, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0626888275146484, "global_step": 539147, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.062232255935669, "global_step": 539148, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.048027992248535, "global_step": 539149, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.102597951889038, "global_step": 539150, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.008418083190918, "global_step": 539151, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.044496774673462, "global_step": 539152, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9911404848098755, "global_step": 539153, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.062986135482788, "global_step": 539154, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.072732925415039, "global_step": 539155, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0974912643432617, "global_step": 539156, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0176775455474854, "global_step": 539157, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.050218105316162, "global_step": 539158, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.045889377593994, "global_step": 539159, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.111272096633911, "global_step": 539160, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0583789348602295, "global_step": 539161, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0474226474761963, "global_step": 539162, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1328277587890625, "global_step": 539163, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9637993574142456, "global_step": 539164, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0731959342956543, "global_step": 539165, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0906362533569336, "global_step": 539166, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9763987064361572, "global_step": 539167, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9886600971221924, "global_step": 539168, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0042312145233154, "global_step": 539169, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.968677043914795, "global_step": 539170, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.972977638244629, "global_step": 539171, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1098008155822754, "global_step": 539172, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0435876846313477, "global_step": 539173, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.078395366668701, "global_step": 539174, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0457727909088135, "global_step": 539175, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1238670349121094, "global_step": 539176, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.038105010986328, "global_step": 539177, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9837126731872559, "global_step": 539178, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9373462200164795, "global_step": 539179, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0148491859436035, "global_step": 539180, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.988703727722168, "global_step": 539181, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0751025676727295, "global_step": 539182, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9844706058502197, "global_step": 539183, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.135993719100952, "global_step": 539184, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.138723611831665, "global_step": 539185, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0591652393341064, "global_step": 539186, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0381174087524414, "global_step": 539187, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.08152174949646, "global_step": 539188, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9939731359481812, "global_step": 539189, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1177735328674316, "global_step": 539190, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.058140754699707, "global_step": 539191, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0426158905029297, "global_step": 539192, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0550267696380615, "global_step": 539193, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9690678119659424, "global_step": 539194, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0712101459503174, "global_step": 539195, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1242852210998535, "global_step": 539196, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0413200855255127, "global_step": 539197, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9916352033615112, "global_step": 539198, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.965061902999878, "global_step": 539199, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.053797721862793, "global_step": 539200, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0586328506469727, "global_step": 539201, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0293986797332764, "global_step": 539202, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0418167114257812, "global_step": 539203, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0061044692993164, "global_step": 539204, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9971165657043457, "global_step": 539205, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.011718988418579, "global_step": 539206, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.044097900390625, "global_step": 539207, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.020878791809082, "global_step": 539208, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0615267753601074, "global_step": 539209, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0480518341064453, "global_step": 539210, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0688138008117676, "global_step": 539211, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0748538970947266, "global_step": 539212, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0462498664855957, "global_step": 539213, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0865864753723145, "global_step": 539214, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.000457525253296, "global_step": 539215, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.90300452709198, "global_step": 539216, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.055515766143799, "global_step": 539217, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9696323871612549, "global_step": 539218, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0790212154388428, "global_step": 539219, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0666942596435547, "global_step": 539220, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0289745330810547, "global_step": 539221, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.097356081008911, "global_step": 539222, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9853724241256714, "global_step": 539223, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.005840539932251, "global_step": 539224, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0079855918884277, "global_step": 539225, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0419740676879883, "global_step": 539226, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9444990158081055, "global_step": 539227, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0113837718963623, "global_step": 539228, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.004836320877075, "global_step": 539229, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9537038803100586, "global_step": 539230, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0482826232910156, "global_step": 539231, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.082641839981079, "global_step": 539232, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0715930461883545, "global_step": 539233, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.08026123046875, "global_step": 539234, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0324883460998535, "global_step": 539235, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0315778255462646, "global_step": 539236, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1271846294403076, "global_step": 539237, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0262207984924316, "global_step": 539238, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9907479286193848, "global_step": 539239, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.062971353530884, "global_step": 539240, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.063645839691162, "global_step": 539241, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.083834171295166, "global_step": 539242, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.047480344772339, "global_step": 539243, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0496573448181152, "global_step": 539244, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0679261684417725, "global_step": 539245, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9757479429244995, "global_step": 539246, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0580272674560547, "global_step": 539247, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.081540107727051, "global_step": 539248, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9439928531646729, "global_step": 539249, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.06390118598938, "global_step": 539250, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.96144437789917, "global_step": 539251, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0464417934417725, "global_step": 539252, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0178515911102295, "global_step": 539253, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1014533042907715, "global_step": 539254, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0782058238983154, "global_step": 539255, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9874725341796875, "global_step": 539256, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0240612030029297, "global_step": 539257, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.066455602645874, "global_step": 539258, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.057650089263916, "global_step": 539259, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.998321294784546, "global_step": 539260, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0189883708953857, "global_step": 539261, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.042201042175293, "global_step": 539262, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9949039220809937, "global_step": 539263, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0685348510742188, "global_step": 539264, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0205469131469727, "global_step": 539265, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9620286226272583, "global_step": 539266, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.008908748626709, "global_step": 539267, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0433781147003174, "global_step": 539268, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.136075973510742, "global_step": 539269, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9970935583114624, "global_step": 539270, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.026839256286621, "global_step": 539271, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9955753087997437, "global_step": 539272, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9922939538955688, "global_step": 539273, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.021358013153076, "global_step": 539274, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0028345584869385, "global_step": 539275, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.053722620010376, "global_step": 539276, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0870344638824463, "global_step": 539277, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9964258670806885, "global_step": 539278, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.937503457069397, "global_step": 539279, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0642411708831787, "global_step": 539280, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0683650970458984, "global_step": 539281, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0666327476501465, "global_step": 539282, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.053061008453369, "global_step": 539283, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1422955989837646, "global_step": 539284, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.04990816116333, "global_step": 539285, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.98256254196167, "global_step": 539286, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.075207233428955, "global_step": 539287, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9491827487945557, "global_step": 539288, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0659289360046387, "global_step": 539289, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0883822441101074, "global_step": 539290, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0799708366394043, "global_step": 539291, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0800602436065674, "global_step": 539292, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0120060443878174, "global_step": 539293, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0237700939178467, "global_step": 539294, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.954956293106079, "global_step": 539295, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9627538919448853, "global_step": 539296, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9663290977478027, "global_step": 539297, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0569589138031006, "global_step": 539298, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.003917932510376, "global_step": 539299, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.000406503677368, "global_step": 539300, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0719544887542725, "global_step": 539301, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0141561031341553, "global_step": 539302, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.034264326095581, "global_step": 539303, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.094796657562256, "global_step": 539304, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0665178298950195, "global_step": 539305, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0064432621002197, "global_step": 539306, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9841562509536743, "global_step": 539307, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0349314212799072, "global_step": 539308, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1007823944091797, "global_step": 539309, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.051006317138672, "global_step": 539310, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.07026743888855, "global_step": 539311, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0922045707702637, "global_step": 539312, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0099847316741943, "global_step": 539313, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.973441481590271, "global_step": 539314, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0391106605529785, "global_step": 539315, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0959441661834717, "global_step": 539316, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9575918912887573, "global_step": 539317, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.990405559539795, "global_step": 539318, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.005220413208008, "global_step": 539319, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.010744333267212, "global_step": 539320, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0786688327789307, "global_step": 539321, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0480833053588867, "global_step": 539322, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.14687442779541, "global_step": 539323, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0519051551818848, "global_step": 539324, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.043581247329712, "global_step": 539325, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0431599617004395, "global_step": 539326, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0682713985443115, "global_step": 539327, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.936344861984253, "global_step": 539328, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.072761297225952, "global_step": 539329, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9853122234344482, "global_step": 539330, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.06219220161438, "global_step": 539331, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.046750545501709, "global_step": 539332, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.084977388381958, "global_step": 539333, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.067474603652954, "global_step": 539334, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9818668365478516, "global_step": 539335, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0488407611846924, "global_step": 539336, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.131294012069702, "global_step": 539337, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0112240314483643, "global_step": 539338, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9609698057174683, "global_step": 539339, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0817320346832275, "global_step": 539340, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0239486694335938, "global_step": 539341, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0217983722686768, "global_step": 539342, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0531723499298096, "global_step": 539343, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0424060821533203, "global_step": 539344, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.053619861602783, "global_step": 539345, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0008716583251953, "global_step": 539346, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0639731884002686, "global_step": 539347, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.01775860786438, "global_step": 539348, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0224695205688477, "global_step": 539349, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.957768440246582, "global_step": 539350, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.016583204269409, "global_step": 539351, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0643961429595947, "global_step": 539352, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1186842918395996, "global_step": 539353, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.980931282043457, "global_step": 539354, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9533430337905884, "global_step": 539355, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.061981678009033, "global_step": 539356, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.990665078163147, "global_step": 539357, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0992650985717773, "global_step": 539358, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.095003604888916, "global_step": 539359, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.031073808670044, "global_step": 539360, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9580050706863403, "global_step": 539361, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9802712202072144, "global_step": 539362, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0649688243865967, "global_step": 539363, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1270949840545654, "global_step": 539364, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.037095785140991, "global_step": 539365, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0071895122528076, "global_step": 539366, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0621066093444824, "global_step": 539367, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.020103931427002, "global_step": 539368, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0331082344055176, "global_step": 539369, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9595714807510376, "global_step": 539370, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.099916458129883, "global_step": 539371, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0477635860443115, "global_step": 539372, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.042964220046997, "global_step": 539373, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.021929979324341, "global_step": 539374, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0679192543029785, "global_step": 539375, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9823520183563232, "global_step": 539376, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.056708574295044, "global_step": 539377, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.038810968399048, "global_step": 539378, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.993279218673706, "global_step": 539379, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0847702026367188, "global_step": 539380, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9313483238220215, "global_step": 539381, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9534809589385986, "global_step": 539382, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1566765308380127, "global_step": 539383, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1166298389434814, "global_step": 539384, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.037177801132202, "global_step": 539385, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0766191482543945, "global_step": 539386, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.043997287750244, "global_step": 539387, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9333703517913818, "global_step": 539388, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0472946166992188, "global_step": 539389, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.013622760772705, "global_step": 539390, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.044503688812256, "global_step": 539391, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0112907886505127, "global_step": 539392, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.05928635597229, "global_step": 539393, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9225592613220215, "global_step": 539394, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1124064922332764, "global_step": 539395, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0439860820770264, "global_step": 539396, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9952890872955322, "global_step": 539397, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.107222080230713, "global_step": 539398, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1178290843963623, "global_step": 539399, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0872247219085693, "global_step": 539400, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9887810945510864, "global_step": 539401, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1498823165893555, "global_step": 539402, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0687897205352783, "global_step": 539403, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9200654029846191, "global_step": 539404, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0916948318481445, "global_step": 539405, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0511512756347656, "global_step": 539406, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0701189041137695, "global_step": 539407, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0850284099578857, "global_step": 539408, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.001774311065674, "global_step": 539409, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9944629669189453, "global_step": 539410, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.049102306365967, "global_step": 539411, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.017530679702759, "global_step": 539412, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.029439687728882, "global_step": 539413, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0826046466827393, "global_step": 539414, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1668758392333984, "global_step": 539415, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1050174236297607, "global_step": 539416, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9803106784820557, "global_step": 539417, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.013970375061035, "global_step": 539418, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0810887813568115, "global_step": 539419, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.026034116744995, "global_step": 539420, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0521154403686523, "global_step": 539421, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.04156756401062, "global_step": 539422, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.028259515762329, "global_step": 539423, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9457701444625854, "global_step": 539424, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.104971170425415, "global_step": 539425, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0744693279266357, "global_step": 539426, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.065378427505493, "global_step": 539427, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.056807518005371, "global_step": 539428, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9956282377243042, "global_step": 539429, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.102618455886841, "global_step": 539430, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9629361629486084, "global_step": 539431, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9988423585891724, "global_step": 539432, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.059551477432251, "global_step": 539433, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9687483310699463, "global_step": 539434, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0469040870666504, "global_step": 539435, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0032992362976074, "global_step": 539436, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9981050491333008, "global_step": 539437, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0271310806274414, "global_step": 539438, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9684275388717651, "global_step": 539439, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0838608741760254, "global_step": 539440, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.111311435699463, "global_step": 539441, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.116001844406128, "global_step": 539442, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0029282569885254, "global_step": 539443, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0398051738739014, "global_step": 539444, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0385286808013916, "global_step": 539445, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9532462358474731, "global_step": 539446, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0718109607696533, "global_step": 539447, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.030620813369751, "global_step": 539448, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0887808799743652, "global_step": 539449, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.093034029006958, "global_step": 539450, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.04549503326416, "global_step": 539451, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0658273696899414, "global_step": 539452, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0154898166656494, "global_step": 539453, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0243630409240723, "global_step": 539454, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0465681552886963, "global_step": 539455, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.045942783355713, "global_step": 539456, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.012089967727661, "global_step": 539457, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0639235973358154, "global_step": 539458, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1103386878967285, "global_step": 539459, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.026301622390747, "global_step": 539460, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9680652618408203, "global_step": 539461, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9589736461639404, "global_step": 539462, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.046001672744751, "global_step": 539463, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.063723087310791, "global_step": 539464, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.029165744781494, "global_step": 539465, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.067793369293213, "global_step": 539466, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.941208839416504, "global_step": 539467, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0693938732147217, "global_step": 539468, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0307059288024902, "global_step": 539469, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0020360946655273, "global_step": 539470, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.101905584335327, "global_step": 539471, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0848004817962646, "global_step": 539472, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.00128436088562, "global_step": 539473, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.941752314567566, "global_step": 539474, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9122765064239502, "global_step": 539475, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.970633864402771, "global_step": 539476, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0327088832855225, "global_step": 539477, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0060017108917236, "global_step": 539478, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1054158210754395, "global_step": 539479, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0695364475250244, "global_step": 539480, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.009903907775879, "global_step": 539481, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.040762424468994, "global_step": 539482, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9790186882019043, "global_step": 539483, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.097078561782837, "global_step": 539484, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.07072377204895, "global_step": 539485, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.056079387664795, "global_step": 539486, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1679182052612305, "global_step": 539487, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9794526100158691, "global_step": 539488, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.059027671813965, "global_step": 539489, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0103044509887695, "global_step": 539490, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0460023880004883, "global_step": 539491, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9977977275848389, "global_step": 539492, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0162360668182373, "global_step": 539493, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0144598484039307, "global_step": 539494, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0199296474456787, "global_step": 539495, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.000735282897949, "global_step": 539496, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.13634991645813, "global_step": 539497, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9895914793014526, "global_step": 539498, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9800028800964355, "global_step": 539499, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0310702323913574, "global_step": 539500, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9438377618789673, "global_step": 539501, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.105344295501709, "global_step": 539502, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.136075258255005, "global_step": 539503, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0132641792297363, "global_step": 539504, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0065038204193115, "global_step": 539505, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9916164875030518, "global_step": 539506, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0067837238311768, "global_step": 539507, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.113093137741089, "global_step": 539508, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0058865547180176, "global_step": 539509, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0018770694732666, "global_step": 539510, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.073462724685669, "global_step": 539511, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0117902755737305, "global_step": 539512, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.996336817741394, "global_step": 539513, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0698153972625732, "global_step": 539514, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.10684871673584, "global_step": 539515, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.984616994857788, "global_step": 539516, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.039815664291382, "global_step": 539517, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0737500190734863, "global_step": 539518, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.021066188812256, "global_step": 539519, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.063457489013672, "global_step": 539520, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0875210762023926, "global_step": 539521, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0876810550689697, "global_step": 539522, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.020895481109619, "global_step": 539523, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0851285457611084, "global_step": 539524, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.052799701690674, "global_step": 539525, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.044121026992798, "global_step": 539526, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0829830169677734, "global_step": 539527, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.020146369934082, "global_step": 539528, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0758867263793945, "global_step": 539529, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.099308967590332, "global_step": 539530, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1476526260375977, "global_step": 539531, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0830016136169434, "global_step": 539532, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9643187522888184, "global_step": 539533, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.085904121398926, "global_step": 539534, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0076916217803955, "global_step": 539535, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.032066583633423, "global_step": 539536, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0417087078094482, "global_step": 539537, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.963468313217163, "global_step": 539538, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0976712703704834, "global_step": 539539, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0104658603668213, "global_step": 539540, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.078362464904785, "global_step": 539541, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.045117139816284, "global_step": 539542, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0819592475891113, "global_step": 539543, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.039133071899414, "global_step": 539544, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.104055643081665, "global_step": 539545, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0637171268463135, "global_step": 539546, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.990865707397461, "global_step": 539547, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1302597522735596, "global_step": 539548, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0935306549072266, "global_step": 539549, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1385133266448975, "global_step": 539550, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0209004878997803, "global_step": 539551, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0153212547302246, "global_step": 539552, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9874515533447266, "global_step": 539553, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0297183990478516, "global_step": 539554, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.041921377182007, "global_step": 539555, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0228078365325928, "global_step": 539556, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9452404975891113, "global_step": 539557, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.000101089477539, "global_step": 539558, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.951081395149231, "global_step": 539559, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0351271629333496, "global_step": 539560, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9963586330413818, "global_step": 539561, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.025144100189209, "global_step": 539562, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.037397861480713, "global_step": 539563, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.070760726928711, "global_step": 539564, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9825385808944702, "global_step": 539565, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0269548892974854, "global_step": 539566, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.093402862548828, "global_step": 539567, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0228400230407715, "global_step": 539568, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.044113874435425, "global_step": 539569, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.052964210510254, "global_step": 539570, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0049614906311035, "global_step": 539571, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9672119617462158, "global_step": 539572, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0173285007476807, "global_step": 539573, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0819954872131348, "global_step": 539574, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0282747745513916, "global_step": 539575, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0293915271759033, "global_step": 539576, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9389375448226929, "global_step": 539577, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1119630336761475, "global_step": 539578, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0636119842529297, "global_step": 539579, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.002715587615967, "global_step": 539580, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.084981679916382, "global_step": 539581, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1081795692443848, "global_step": 539582, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9764214754104614, "global_step": 539583, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.2030088901519775, "global_step": 539584, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0792720317840576, "global_step": 539585, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.101165294647217, "global_step": 539586, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9991122484207153, "global_step": 539587, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.023589611053467, "global_step": 539588, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.057845115661621, "global_step": 539589, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0177218914031982, "global_step": 539590, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.049633502960205, "global_step": 539591, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9966363906860352, "global_step": 539592, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.058310031890869, "global_step": 539593, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.001619815826416, "global_step": 539594, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9732507467269897, "global_step": 539595, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0159060955047607, "global_step": 539596, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.027411699295044, "global_step": 539597, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0761301517486572, "global_step": 539598, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9607716798782349, "global_step": 539599, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0673301219940186, "global_step": 539600, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.079141855239868, "global_step": 539601, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.992390513420105, "global_step": 539602, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.067009210586548, "global_step": 539603, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.013327121734619, "global_step": 539604, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9505400657653809, "global_step": 539605, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0511887073516846, "global_step": 539606, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.958417534828186, "global_step": 539607, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0496792793273926, "global_step": 539608, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9932852983474731, "global_step": 539609, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.02923583984375, "global_step": 539610, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1071670055389404, "global_step": 539611, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9519692659378052, "global_step": 539612, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.068490743637085, "global_step": 539613, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0311150550842285, "global_step": 539614, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.012835741043091, "global_step": 539615, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.047571897506714, "global_step": 539616, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0173871517181396, "global_step": 539617, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0420730113983154, "global_step": 539618, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9857351779937744, "global_step": 539619, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9708234071731567, "global_step": 539620, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.08454966545105, "global_step": 539621, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.089977264404297, "global_step": 539622, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.041780471801758, "global_step": 539623, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9951343536376953, "global_step": 539624, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9639523029327393, "global_step": 539625, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1394405364990234, "global_step": 539626, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0440680980682373, "global_step": 539627, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0398221015930176, "global_step": 539628, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.993322730064392, "global_step": 539629, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.030068874359131, "global_step": 539630, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.045499086380005, "global_step": 539631, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.070547103881836, "global_step": 539632, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9877090454101562, "global_step": 539633, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1174333095550537, "global_step": 539634, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.140218496322632, "global_step": 539635, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9764636754989624, "global_step": 539636, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9728477001190186, "global_step": 539637, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9909584522247314, "global_step": 539638, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.001756429672241, "global_step": 539639, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0681204795837402, "global_step": 539640, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.035773277282715, "global_step": 539641, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0080068111419678, "global_step": 539642, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.061025619506836, "global_step": 539643, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.019960403442383, "global_step": 539644, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0789530277252197, "global_step": 539645, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.100825548171997, "global_step": 539646, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.034710168838501, "global_step": 539647, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.983199119567871, "global_step": 539648, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.056673765182495, "global_step": 539649, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.982620358467102, "global_step": 539650, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0489072799682617, "global_step": 539651, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.072143316268921, "global_step": 539652, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0214881896972656, "global_step": 539653, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0525200366973877, "global_step": 539654, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0639991760253906, "global_step": 539655, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1411566734313965, "global_step": 539656, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0630342960357666, "global_step": 539657, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0531210899353027, "global_step": 539658, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.025238037109375, "global_step": 539659, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.028736114501953, "global_step": 539660, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.01489520072937, "global_step": 539661, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1131904125213623, "global_step": 539662, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.082369804382324, "global_step": 539663, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0891284942626953, "global_step": 539664, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0432255268096924, "global_step": 539665, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0413358211517334, "global_step": 539666, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9716283082962036, "global_step": 539667, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.048820734024048, "global_step": 539668, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0454320907592773, "global_step": 539669, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.028949737548828, "global_step": 539670, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.022921562194824, "global_step": 539671, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0373282432556152, "global_step": 539672, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0772998332977295, "global_step": 539673, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0137717723846436, "global_step": 539674, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.085662603378296, "global_step": 539675, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0335702896118164, "global_step": 539676, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.084501028060913, "global_step": 539677, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.012686014175415, "global_step": 539678, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9832016229629517, "global_step": 539679, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.03781795501709, "global_step": 539680, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.038712501525879, "global_step": 539681, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1603341102600098, "global_step": 539682, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.064347743988037, "global_step": 539683, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0845861434936523, "global_step": 539684, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.037860155105591, "global_step": 539685, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.996650218963623, "global_step": 539686, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9861007928848267, "global_step": 539687, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.020153045654297, "global_step": 539688, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.934322714805603, "global_step": 539689, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9996291399002075, "global_step": 539690, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0322253704071045, "global_step": 539691, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0576553344726562, "global_step": 539692, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0386698246002197, "global_step": 539693, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.043447971343994, "global_step": 539694, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1319985389709473, "global_step": 539695, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.021792411804199, "global_step": 539696, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0095691680908203, "global_step": 539697, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0903871059417725, "global_step": 539698, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.96562659740448, "global_step": 539699, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0695269107818604, "global_step": 539700, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.044461965560913, "global_step": 539701, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.046635866165161, "global_step": 539702, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0021445751190186, "global_step": 539703, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9940062761306763, "global_step": 539704, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0832679271698, "global_step": 539705, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.996408462524414, "global_step": 539706, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.054929256439209, "global_step": 539707, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9919514656066895, "global_step": 539708, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9972153902053833, "global_step": 539709, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.973057746887207, "global_step": 539710, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9770658016204834, "global_step": 539711, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9761346578598022, "global_step": 539712, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0574679374694824, "global_step": 539713, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.161184310913086, "global_step": 539714, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.087425947189331, "global_step": 539715, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9995808601379395, "global_step": 539716, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.092571258544922, "global_step": 539717, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0731523036956787, "global_step": 539718, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9272212982177734, "global_step": 539719, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.049600124359131, "global_step": 539720, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.051126480102539, "global_step": 539721, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.045715808868408, "global_step": 539722, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.065683126449585, "global_step": 539723, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0431456565856934, "global_step": 539724, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.012260675430298, "global_step": 539725, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.989637017250061, "global_step": 539726, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.093689441680908, "global_step": 539727, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0169177055358887, "global_step": 539728, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.022979974746704, "global_step": 539729, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9863237142562866, "global_step": 539730, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.12768816947937, "global_step": 539731, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0085220336914062, "global_step": 539732, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0297088623046875, "global_step": 539733, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9867124557495117, "global_step": 539734, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0934152603149414, "global_step": 539735, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0055367946624756, "global_step": 539736, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9816405773162842, "global_step": 539737, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0531649589538574, "global_step": 539738, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1101675033569336, "global_step": 539739, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1359505653381348, "global_step": 539740, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.005504608154297, "global_step": 539741, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0638482570648193, "global_step": 539742, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0243277549743652, "global_step": 539743, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0909509658813477, "global_step": 539744, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1486880779266357, "global_step": 539745, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9832576513290405, "global_step": 539746, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0581157207489014, "global_step": 539747, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9688186645507812, "global_step": 539748, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9936649799346924, "global_step": 539749, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.022923707962036, "global_step": 539750, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0538642406463623, "global_step": 539751, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9508821964263916, "global_step": 539752, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9910836219787598, "global_step": 539753, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9651596546173096, "global_step": 539754, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0783321857452393, "global_step": 539755, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9871346950531006, "global_step": 539756, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0054171085357666, "global_step": 539757, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0310754776000977, "global_step": 539758, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.012528896331787, "global_step": 539759, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.095064640045166, "global_step": 539760, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9995510578155518, "global_step": 539761, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.024583339691162, "global_step": 539762, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.023700714111328, "global_step": 539763, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.977168321609497, "global_step": 539764, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.032836675643921, "global_step": 539765, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0456604957580566, "global_step": 539766, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.059784412384033, "global_step": 539767, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1309096813201904, "global_step": 539768, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9355835914611816, "global_step": 539769, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0057947635650635, "global_step": 539770, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0266973972320557, "global_step": 539771, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1016883850097656, "global_step": 539772, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9875799417495728, "global_step": 539773, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.093888521194458, "global_step": 539774, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0031628608703613, "global_step": 539775, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0683460235595703, "global_step": 539776, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0354599952697754, "global_step": 539777, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9764912128448486, "global_step": 539778, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9386802911758423, "global_step": 539779, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.082782506942749, "global_step": 539780, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9607188701629639, "global_step": 539781, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.996835708618164, "global_step": 539782, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0200743675231934, "global_step": 539783, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0835726261138916, "global_step": 539784, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0465683937072754, "global_step": 539785, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.008653402328491, "global_step": 539786, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.012653112411499, "global_step": 539787, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9978605508804321, "global_step": 539788, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.009042263031006, "global_step": 539789, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0701348781585693, "global_step": 539790, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.013263463973999, "global_step": 539791, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0471630096435547, "global_step": 539792, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.06074595451355, "global_step": 539793, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.997605323791504, "global_step": 539794, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1111702919006348, "global_step": 539795, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0517892837524414, "global_step": 539796, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0276761054992676, "global_step": 539797, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9990803003311157, "global_step": 539798, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0415749549865723, "global_step": 539799, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0449724197387695, "global_step": 539800, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9764446020126343, "global_step": 539801, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0220706462860107, "global_step": 539802, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.023972272872925, "global_step": 539803, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.028968095779419, "global_step": 539804, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.063199758529663, "global_step": 539805, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.999077558517456, "global_step": 539806, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.03562068939209, "global_step": 539807, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0322344303131104, "global_step": 539808, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.10048246383667, "global_step": 539809, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0537431240081787, "global_step": 539810, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.058910369873047, "global_step": 539811, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.005570411682129, "global_step": 539812, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.974568247795105, "global_step": 539813, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0612165927886963, "global_step": 539814, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0059237480163574, "global_step": 539815, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.051215410232544, "global_step": 539816, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0638222694396973, "global_step": 539817, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0165674686431885, "global_step": 539818, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0232656002044678, "global_step": 539819, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0295846462249756, "global_step": 539820, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0183210372924805, "global_step": 539821, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0901272296905518, "global_step": 539822, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1123390197753906, "global_step": 539823, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.035783052444458, "global_step": 539824, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.979655146598816, "global_step": 539825, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.024423837661743, "global_step": 539826, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1217615604400635, "global_step": 539827, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9990556240081787, "global_step": 539828, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9544053077697754, "global_step": 539829, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0203754901885986, "global_step": 539830, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0540692806243896, "global_step": 539831, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0799736976623535, "global_step": 539832, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0807113647460938, "global_step": 539833, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0678179264068604, "global_step": 539834, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0981178283691406, "global_step": 539835, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.084717273712158, "global_step": 539836, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.084289073944092, "global_step": 539837, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0737643241882324, "global_step": 539838, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0604612827301025, "global_step": 539839, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.042313814163208, "global_step": 539840, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.989583969116211, "global_step": 539841, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0025017261505127, "global_step": 539842, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0847842693328857, "global_step": 539843, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.075589895248413, "global_step": 539844, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0677053928375244, "global_step": 539845, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0201194286346436, "global_step": 539846, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0151772499084473, "global_step": 539847, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1415083408355713, "global_step": 539848, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.018153190612793, "global_step": 539849, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0151991844177246, "global_step": 539850, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.066204309463501, "global_step": 539851, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.06575083732605, "global_step": 539852, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.1401007175445557, "global_step": 539853, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9831634759902954, "global_step": 539854, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0959835052490234, "global_step": 539855, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0272481441497803, "global_step": 539856, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.053913116455078, "global_step": 539857, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9785425662994385, "global_step": 539858, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9468530416488647, "global_step": 539859, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9691239595413208, "global_step": 539860, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9928743839263916, "global_step": 539861, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.9089760780334473, "global_step": 539862, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.065157413482666, "global_step": 539863, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.99784517288208, "global_step": 539864, "epoch": 906, "lr": 5e-05}
{"train_loss": 2.0335724353790283, "global_step": 539865, "epoch": 906, "lr": 5e-05}
{"train_loss": 1.982053518295288, "global_step": 539866, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0670626163482666, "global_step": 539867, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9989064931869507, "global_step": 539868, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.919210433959961, "global_step": 539869, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9915997982025146, "global_step": 539870, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.082967519760132, "global_step": 539871, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.14754056930542, "global_step": 539872, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0767643451690674, "global_step": 539873, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.952613353729248, "global_step": 539874, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0413424968719482, "global_step": 539875, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9909170866012573, "global_step": 539876, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.061873197555542, "global_step": 539877, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0724925994873047, "global_step": 539878, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0488297939300537, "global_step": 539879, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.072735548019409, "global_step": 539880, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.016211986541748, "global_step": 539881, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9410951137542725, "global_step": 539882, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0371577739715576, "global_step": 539883, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.000640630722046, "global_step": 539884, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.978151559829712, "global_step": 539885, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0372464656829834, "global_step": 539886, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0621938705444336, "global_step": 539887, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.103992462158203, "global_step": 539888, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0576975345611572, "global_step": 539889, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9809943437576294, "global_step": 539890, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9452214241027832, "global_step": 539891, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.134613037109375, "global_step": 539892, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0500597953796387, "global_step": 539893, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0079383850097656, "global_step": 539894, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.029115915298462, "global_step": 539895, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0508899688720703, "global_step": 539896, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9777910709381104, "global_step": 539897, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0421695709228516, "global_step": 539898, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0112316608428955, "global_step": 539899, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0489816665649414, "global_step": 539900, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9522905349731445, "global_step": 539901, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9943931102752686, "global_step": 539902, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9629693031311035, "global_step": 539903, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.019606113433838, "global_step": 539904, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.067593574523926, "global_step": 539905, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.991885781288147, "global_step": 539906, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0815165042877197, "global_step": 539907, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0117850303649902, "global_step": 539908, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1007866859436035, "global_step": 539909, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.063321828842163, "global_step": 539910, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9666146039962769, "global_step": 539911, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9997036457061768, "global_step": 539912, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.021230459213257, "global_step": 539913, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.034266471862793, "global_step": 539914, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.968520164489746, "global_step": 539915, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0495803356170654, "global_step": 539916, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0239341259002686, "global_step": 539917, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.074079751968384, "global_step": 539918, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.958131194114685, "global_step": 539919, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0092880725860596, "global_step": 539920, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0602545738220215, "global_step": 539921, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0602478981018066, "global_step": 539922, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0316803455352783, "global_step": 539923, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.001619815826416, "global_step": 539924, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0058798789978027, "global_step": 539925, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.937926173210144, "global_step": 539926, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.034557819366455, "global_step": 539927, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.008296012878418, "global_step": 539928, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0627782344818115, "global_step": 539929, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.972507357597351, "global_step": 539930, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9552770853042603, "global_step": 539931, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9588024616241455, "global_step": 539932, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.881697654724121, "global_step": 539933, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0235445499420166, "global_step": 539934, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.043489933013916, "global_step": 539935, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9801417589187622, "global_step": 539936, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9717003107070923, "global_step": 539937, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9977214336395264, "global_step": 539938, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9751605987548828, "global_step": 539939, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0266523361206055, "global_step": 539940, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9861226081848145, "global_step": 539941, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.090259313583374, "global_step": 539942, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9982801675796509, "global_step": 539943, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9742281436920166, "global_step": 539944, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9946523904800415, "global_step": 539945, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.983264684677124, "global_step": 539946, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0436086654663086, "global_step": 539947, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.004812240600586, "global_step": 539948, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0207252502441406, "global_step": 539949, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0298116207122803, "global_step": 539950, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9660121202468872, "global_step": 539951, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.109353542327881, "global_step": 539952, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.031545639038086, "global_step": 539953, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.957205057144165, "global_step": 539954, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9504679441452026, "global_step": 539955, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0787715911865234, "global_step": 539956, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0100462436676025, "global_step": 539957, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0324440002441406, "global_step": 539958, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.028128147125244, "global_step": 539959, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9783165454864502, "global_step": 539960, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.966206669807434, "global_step": 539961, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0797507762908936, "global_step": 539962, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0362443923950195, "global_step": 539963, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1478240489959717, "global_step": 539964, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.094670057296753, "global_step": 539965, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.009822130203247, "global_step": 539966, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0130910873413086, "global_step": 539967, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9469162225723267, "global_step": 539968, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.026308536529541, "global_step": 539969, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.045766830444336, "global_step": 539970, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.004972457885742, "global_step": 539971, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9703377485275269, "global_step": 539972, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0412490367889404, "global_step": 539973, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9944366216659546, "global_step": 539974, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.04848575592041, "global_step": 539975, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0338408946990967, "global_step": 539976, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.035585880279541, "global_step": 539977, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.994737148284912, "global_step": 539978, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9852558374404907, "global_step": 539979, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.982741117477417, "global_step": 539980, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9615145921707153, "global_step": 539981, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.91859769821167, "global_step": 539982, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0213165283203125, "global_step": 539983, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9792916774749756, "global_step": 539984, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1014230251312256, "global_step": 539985, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.085364818572998, "global_step": 539986, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.097940444946289, "global_step": 539987, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.994072675704956, "global_step": 539988, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0275115966796875, "global_step": 539989, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0071916580200195, "global_step": 539990, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.040175676345825, "global_step": 539991, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.002863645553589, "global_step": 539992, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.046379804611206, "global_step": 539993, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.074840545654297, "global_step": 539994, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9898806810379028, "global_step": 539995, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0371110439300537, "global_step": 539996, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0452682971954346, "global_step": 539997, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.137007713317871, "global_step": 539998, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.005608558654785, "global_step": 539999, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.009702682495117, "global_step": 540000, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9915952682495117, "global_step": 540001, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.009793996810913, "global_step": 540002, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.049156427383423, "global_step": 540003, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9839677810668945, "global_step": 540004, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.8770394325256348, "global_step": 540005, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0664284229278564, "global_step": 540006, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9728611707687378, "global_step": 540007, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0942087173461914, "global_step": 540008, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9883780479431152, "global_step": 540009, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.938604712486267, "global_step": 540010, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.123133897781372, "global_step": 540011, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.043869733810425, "global_step": 540012, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.046482801437378, "global_step": 540013, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0460922718048096, "global_step": 540014, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.074248790740967, "global_step": 540015, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1036455631256104, "global_step": 540016, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9483336210250854, "global_step": 540017, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0651984214782715, "global_step": 540018, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.975949764251709, "global_step": 540019, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.944866418838501, "global_step": 540020, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.043301820755005, "global_step": 540021, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.00697922706604, "global_step": 540022, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.006155490875244, "global_step": 540023, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0006160736083984, "global_step": 540024, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9545735120773315, "global_step": 540025, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0537164211273193, "global_step": 540026, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9591012001037598, "global_step": 540027, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.106260061264038, "global_step": 540028, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0760769844055176, "global_step": 540029, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.044733762741089, "global_step": 540030, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.048640251159668, "global_step": 540031, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0012426376342773, "global_step": 540032, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.071073532104492, "global_step": 540033, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0250141620635986, "global_step": 540034, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0116405487060547, "global_step": 540035, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1036808490753174, "global_step": 540036, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.044424533843994, "global_step": 540037, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.000609874725342, "global_step": 540038, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1228325366973877, "global_step": 540039, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0262348651885986, "global_step": 540040, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0227718353271484, "global_step": 540041, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.071807861328125, "global_step": 540042, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.034465789794922, "global_step": 540043, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.012014389038086, "global_step": 540044, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.068812847137451, "global_step": 540045, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9605222940444946, "global_step": 540046, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0770866870880127, "global_step": 540047, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0811896324157715, "global_step": 540048, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0286459922790527, "global_step": 540049, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9919167757034302, "global_step": 540050, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.955238699913025, "global_step": 540051, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0655949115753174, "global_step": 540052, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0067620277404785, "global_step": 540053, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9396353960037231, "global_step": 540054, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0911149978637695, "global_step": 540055, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.144659996032715, "global_step": 540056, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9456373453140259, "global_step": 540057, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.976067304611206, "global_step": 540058, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.973127841949463, "global_step": 540059, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.037632703781128, "global_step": 540060, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.023089647293091, "global_step": 540061, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0627431869506836, "global_step": 540062, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.017246961593628, "global_step": 540063, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9711776971817017, "global_step": 540064, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9861347675323486, "global_step": 540065, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.96783447265625, "global_step": 540066, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0702970027923584, "global_step": 540067, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.131385326385498, "global_step": 540068, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9917919635772705, "global_step": 540069, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.023709297180176, "global_step": 540070, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0318098068237305, "global_step": 540071, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0661308765411377, "global_step": 540072, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0383570194244385, "global_step": 540073, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.044598340988159, "global_step": 540074, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0226197242736816, "global_step": 540075, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9511808156967163, "global_step": 540076, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.050593852996826, "global_step": 540077, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9663262367248535, "global_step": 540078, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0129940509796143, "global_step": 540079, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.092686414718628, "global_step": 540080, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0072953701019287, "global_step": 540081, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0406370162963867, "global_step": 540082, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0002012252807617, "global_step": 540083, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.001382350921631, "global_step": 540084, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.172877311706543, "global_step": 540085, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.025482654571533, "global_step": 540086, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9096635580062866, "global_step": 540087, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1060140132904053, "global_step": 540088, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0589544773101807, "global_step": 540089, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9936580657958984, "global_step": 540090, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.077831268310547, "global_step": 540091, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9740527868270874, "global_step": 540092, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.009539842605591, "global_step": 540093, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0904321670532227, "global_step": 540094, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9965561628341675, "global_step": 540095, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9726630449295044, "global_step": 540096, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0015859603881836, "global_step": 540097, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9671313762664795, "global_step": 540098, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.06009578704834, "global_step": 540099, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.047041416168213, "global_step": 540100, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0128185749053955, "global_step": 540101, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0472331047058105, "global_step": 540102, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9428291320800781, "global_step": 540103, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0110270977020264, "global_step": 540104, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9855148792266846, "global_step": 540105, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0112922191619873, "global_step": 540106, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9472895860671997, "global_step": 540107, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9775470495224, "global_step": 540108, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.020568609237671, "global_step": 540109, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.031280994415283, "global_step": 540110, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0971789360046387, "global_step": 540111, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9825953245162964, "global_step": 540112, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9627842903137207, "global_step": 540113, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0512535572052, "global_step": 540114, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.039701223373413, "global_step": 540115, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.082420587539673, "global_step": 540116, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0084376335144043, "global_step": 540117, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9860261678695679, "global_step": 540118, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.021462917327881, "global_step": 540119, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0978283882141113, "global_step": 540120, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0718023777008057, "global_step": 540121, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9613500833511353, "global_step": 540122, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0028741359710693, "global_step": 540123, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0251235961914062, "global_step": 540124, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.061939001083374, "global_step": 540125, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0329771041870117, "global_step": 540126, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9995973110198975, "global_step": 540127, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9736114740371704, "global_step": 540128, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.093357563018799, "global_step": 540129, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9994287490844727, "global_step": 540130, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1547341346740723, "global_step": 540131, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0686123371124268, "global_step": 540132, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0125784873962402, "global_step": 540133, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0483968257904053, "global_step": 540134, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0362627506256104, "global_step": 540135, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.068453550338745, "global_step": 540136, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.014521360397339, "global_step": 540137, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0744802951812744, "global_step": 540138, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.99858558177948, "global_step": 540139, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0492193698883057, "global_step": 540140, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0773818492889404, "global_step": 540141, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9375214576721191, "global_step": 540142, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0759692192077637, "global_step": 540143, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0454514026641846, "global_step": 540144, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.040027141571045, "global_step": 540145, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0566956996917725, "global_step": 540146, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.959224820137024, "global_step": 540147, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0471534729003906, "global_step": 540148, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.963510274887085, "global_step": 540149, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9469224214553833, "global_step": 540150, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0792958736419678, "global_step": 540151, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0419676303863525, "global_step": 540152, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0504024028778076, "global_step": 540153, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.000946283340454, "global_step": 540154, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.049764394760132, "global_step": 540155, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.056577682495117, "global_step": 540156, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9858379364013672, "global_step": 540157, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.172154664993286, "global_step": 540158, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0286028385162354, "global_step": 540159, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9703720808029175, "global_step": 540160, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0235595703125, "global_step": 540161, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.041346788406372, "global_step": 540162, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1593494415283203, "global_step": 540163, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0355894565582275, "global_step": 540164, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.967399001121521, "global_step": 540165, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9914970397949219, "global_step": 540166, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.996338129043579, "global_step": 540167, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.032541513442993, "global_step": 540168, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0764288902282715, "global_step": 540169, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.059173345565796, "global_step": 540170, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0724754333496094, "global_step": 540171, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1092891693115234, "global_step": 540172, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.030059337615967, "global_step": 540173, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0655922889709473, "global_step": 540174, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.035545825958252, "global_step": 540175, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1194353103637695, "global_step": 540176, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.009709119796753, "global_step": 540177, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.077162981033325, "global_step": 540178, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0927422046661377, "global_step": 540179, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0505330562591553, "global_step": 540180, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.057342529296875, "global_step": 540181, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.041651964187622, "global_step": 540182, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.004173994064331, "global_step": 540183, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9660385847091675, "global_step": 540184, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.031400442123413, "global_step": 540185, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.093466281890869, "global_step": 540186, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0354607105255127, "global_step": 540187, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9603235721588135, "global_step": 540188, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9648066759109497, "global_step": 540189, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.107858180999756, "global_step": 540190, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0258781909942627, "global_step": 540191, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9731340408325195, "global_step": 540192, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0631420612335205, "global_step": 540193, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9313960075378418, "global_step": 540194, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.059605360031128, "global_step": 540195, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.075941801071167, "global_step": 540196, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9908438920974731, "global_step": 540197, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.095231294631958, "global_step": 540198, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0344045162200928, "global_step": 540199, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1247851848602295, "global_step": 540200, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1022818088531494, "global_step": 540201, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0254502296447754, "global_step": 540202, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9000612497329712, "global_step": 540203, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.981262445449829, "global_step": 540204, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0836994647979736, "global_step": 540205, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0105466842651367, "global_step": 540206, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1116247177124023, "global_step": 540207, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0170223712921143, "global_step": 540208, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.980407476425171, "global_step": 540209, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0835437774658203, "global_step": 540210, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.089142084121704, "global_step": 540211, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0395896434783936, "global_step": 540212, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.079975128173828, "global_step": 540213, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0129497051239014, "global_step": 540214, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.078298330307007, "global_step": 540215, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0850672721862793, "global_step": 540216, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0134975910186768, "global_step": 540217, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0190622806549072, "global_step": 540218, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0725150108337402, "global_step": 540219, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1767940521240234, "global_step": 540220, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.035905599594116, "global_step": 540221, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9732624292373657, "global_step": 540222, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.046942710876465, "global_step": 540223, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.054354429244995, "global_step": 540224, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.035182237625122, "global_step": 540225, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9836148023605347, "global_step": 540226, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.986266851425171, "global_step": 540227, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.965050220489502, "global_step": 540228, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9976240396499634, "global_step": 540229, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.077831268310547, "global_step": 540230, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9893194437026978, "global_step": 540231, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0672268867492676, "global_step": 540232, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.103710651397705, "global_step": 540233, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.037777900695801, "global_step": 540234, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0120794773101807, "global_step": 540235, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0366721153259277, "global_step": 540236, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0724940299987793, "global_step": 540237, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9658913612365723, "global_step": 540238, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0489110946655273, "global_step": 540239, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0146329402923584, "global_step": 540240, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0163028240203857, "global_step": 540241, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.060030460357666, "global_step": 540242, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9886070489883423, "global_step": 540243, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.068955421447754, "global_step": 540244, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.994228482246399, "global_step": 540245, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.123643159866333, "global_step": 540246, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0490198135375977, "global_step": 540247, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0929219722747803, "global_step": 540248, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0872159004211426, "global_step": 540249, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0457587242126465, "global_step": 540250, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.026381731033325, "global_step": 540251, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0675454139709473, "global_step": 540252, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9771195650100708, "global_step": 540253, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9656983613967896, "global_step": 540254, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9711886644363403, "global_step": 540255, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.078653335571289, "global_step": 540256, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.051610231399536, "global_step": 540257, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0746231079101562, "global_step": 540258, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.003497362136841, "global_step": 540259, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0918922424316406, "global_step": 540260, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0055887699127197, "global_step": 540261, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0061769485473633, "global_step": 540262, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.042306423187256, "global_step": 540263, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0273079872131348, "global_step": 540264, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9139971733093262, "global_step": 540265, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1106956005096436, "global_step": 540266, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.02778697013855, "global_step": 540267, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0559561252593994, "global_step": 540268, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9871236085891724, "global_step": 540269, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0186386108398438, "global_step": 540270, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9632221460342407, "global_step": 540271, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.059391736984253, "global_step": 540272, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0312697887420654, "global_step": 540273, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.039384126663208, "global_step": 540274, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0701498985290527, "global_step": 540275, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0248992443084717, "global_step": 540276, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9834051132202148, "global_step": 540277, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.122831344604492, "global_step": 540278, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.094266414642334, "global_step": 540279, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.044067859649658, "global_step": 540280, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9849756956100464, "global_step": 540281, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0935921669006348, "global_step": 540282, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0131027698516846, "global_step": 540283, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9852288961410522, "global_step": 540284, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0284242630004883, "global_step": 540285, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.034853935241699, "global_step": 540286, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.114392042160034, "global_step": 540287, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.037707567214966, "global_step": 540288, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0509276390075684, "global_step": 540289, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.089890480041504, "global_step": 540290, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0677196979522705, "global_step": 540291, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.030733346939087, "global_step": 540292, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.023005962371826, "global_step": 540293, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0144848823547363, "global_step": 540294, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0712897777557373, "global_step": 540295, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.034106969833374, "global_step": 540296, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9950298070907593, "global_step": 540297, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.025811195373535, "global_step": 540298, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9761154651641846, "global_step": 540299, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9895446300506592, "global_step": 540300, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.965849757194519, "global_step": 540301, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0887718200683594, "global_step": 540302, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0500330924987793, "global_step": 540303, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9499900341033936, "global_step": 540304, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0050971508026123, "global_step": 540305, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.131324291229248, "global_step": 540306, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0933592319488525, "global_step": 540307, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9604387283325195, "global_step": 540308, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0176639556884766, "global_step": 540309, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.978186845779419, "global_step": 540310, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1244215965270996, "global_step": 540311, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9709521532058716, "global_step": 540312, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0536417961120605, "global_step": 540313, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0585076808929443, "global_step": 540314, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0649824142456055, "global_step": 540315, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.048312187194824, "global_step": 540316, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9799915552139282, "global_step": 540317, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.007375717163086, "global_step": 540318, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.148709774017334, "global_step": 540319, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0553667545318604, "global_step": 540320, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0634384155273438, "global_step": 540321, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.003842353820801, "global_step": 540322, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0256638526916504, "global_step": 540323, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.12406849861145, "global_step": 540324, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.032168388366699, "global_step": 540325, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0538876056671143, "global_step": 540326, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.167983055114746, "global_step": 540327, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0370376110076904, "global_step": 540328, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.07218599319458, "global_step": 540329, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0620992183685303, "global_step": 540330, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1790456771850586, "global_step": 540331, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1152613162994385, "global_step": 540332, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9643449783325195, "global_step": 540333, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0441837310791016, "global_step": 540334, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9495699405670166, "global_step": 540335, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0064969062805176, "global_step": 540336, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9968974590301514, "global_step": 540337, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.067793846130371, "global_step": 540338, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9789786338806152, "global_step": 540339, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9785324335098267, "global_step": 540340, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0867292881011963, "global_step": 540341, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.09010910987854, "global_step": 540342, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0366952419281006, "global_step": 540343, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.962279200553894, "global_step": 540344, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0134215354919434, "global_step": 540345, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9417681694030762, "global_step": 540346, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.061985731124878, "global_step": 540347, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0483474731445312, "global_step": 540348, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0641286373138428, "global_step": 540349, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0215790271759033, "global_step": 540350, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9515810012817383, "global_step": 540351, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0333876609802246, "global_step": 540352, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.040928602218628, "global_step": 540353, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0442185401916504, "global_step": 540354, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0150411128997803, "global_step": 540355, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0411124229431152, "global_step": 540356, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.053593158721924, "global_step": 540357, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.090649366378784, "global_step": 540358, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0088634490966797, "global_step": 540359, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9586251974105835, "global_step": 540360, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0540249347686768, "global_step": 540361, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.093050956726074, "global_step": 540362, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.039478302001953, "global_step": 540363, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.08957576751709, "global_step": 540364, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0471386909484863, "global_step": 540365, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.019850969314575, "global_step": 540366, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0339972972869873, "global_step": 540367, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.054502487182617, "global_step": 540368, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9992284774780273, "global_step": 540369, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9215468168258667, "global_step": 540370, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.005230188369751, "global_step": 540371, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.120211601257324, "global_step": 540372, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.969305396080017, "global_step": 540373, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9279403686523438, "global_step": 540374, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.975054144859314, "global_step": 540375, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9722434282302856, "global_step": 540376, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.078770160675049, "global_step": 540377, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.053558588027954, "global_step": 540378, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0026209354400635, "global_step": 540379, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9568417072296143, "global_step": 540380, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0918257236480713, "global_step": 540381, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.073434591293335, "global_step": 540382, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.061490297317505, "global_step": 540383, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.962481141090393, "global_step": 540384, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.136704683303833, "global_step": 540385, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9689732789993286, "global_step": 540386, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0229666233062744, "global_step": 540387, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0521771907806396, "global_step": 540388, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9829275608062744, "global_step": 540389, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.016334295272827, "global_step": 540390, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.123507499694824, "global_step": 540391, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9592082500457764, "global_step": 540392, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0041918754577637, "global_step": 540393, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.129782199859619, "global_step": 540394, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9767053127288818, "global_step": 540395, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0584282875061035, "global_step": 540396, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0674667358398438, "global_step": 540397, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0315072536468506, "global_step": 540398, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0672242641448975, "global_step": 540399, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9675437211990356, "global_step": 540400, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0054218769073486, "global_step": 540401, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0845437049865723, "global_step": 540402, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9650429487228394, "global_step": 540403, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0254039764404297, "global_step": 540404, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0373027324676514, "global_step": 540405, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.074763298034668, "global_step": 540406, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.039602279663086, "global_step": 540407, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0494027137756348, "global_step": 540408, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0183608531951904, "global_step": 540409, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0242574214935303, "global_step": 540410, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0388917922973633, "global_step": 540411, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0889053344726562, "global_step": 540412, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.049199104309082, "global_step": 540413, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0884318351745605, "global_step": 540414, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0275840759277344, "global_step": 540415, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9981489181518555, "global_step": 540416, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.039292097091675, "global_step": 540417, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0168919563293457, "global_step": 540418, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0909125804901123, "global_step": 540419, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9585756063461304, "global_step": 540420, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0692780017852783, "global_step": 540421, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0139222145080566, "global_step": 540422, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.034961223602295, "global_step": 540423, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0015413761138916, "global_step": 540424, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0244815349578857, "global_step": 540425, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0001816749572754, "global_step": 540426, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.13338565826416, "global_step": 540427, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9683866500854492, "global_step": 540428, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.970259666442871, "global_step": 540429, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0766842365264893, "global_step": 540430, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.031398296356201, "global_step": 540431, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0672473907470703, "global_step": 540432, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0107412338256836, "global_step": 540433, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.01957368850708, "global_step": 540434, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.141998052597046, "global_step": 540435, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9586658477783203, "global_step": 540436, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0302536487579346, "global_step": 540437, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.11051082611084, "global_step": 540438, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9804770946502686, "global_step": 540439, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0015323162078857, "global_step": 540440, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.12738037109375, "global_step": 540441, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9646413326263428, "global_step": 540442, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.043626546859741, "global_step": 540443, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.055298089981079, "global_step": 540444, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.030393123626709, "global_step": 540445, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.072122097015381, "global_step": 540446, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.096473217010498, "global_step": 540447, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.005427122116089, "global_step": 540448, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0609920024871826, "global_step": 540449, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0525355339050293, "global_step": 540450, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.01859712600708, "global_step": 540451, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.104597330093384, "global_step": 540452, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9957720041275024, "global_step": 540453, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9886844158172607, "global_step": 540454, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.046480655670166, "global_step": 540455, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1367835998535156, "global_step": 540456, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.047346830368042, "global_step": 540457, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1443068981170654, "global_step": 540458, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9947584867477417, "global_step": 540459, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0530173778533936, "global_step": 540460, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0888068675994873, "global_step": 540461, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0728893280029297, "global_step": 540462, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9917843341827393, "global_step": 540463, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9831910133361816, "global_step": 540464, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0019891262054443, "global_step": 540465, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9734636545181274, "global_step": 540466, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.94562828540802, "global_step": 540467, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0112454891204834, "global_step": 540468, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.964298129081726, "global_step": 540469, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9442023038864136, "global_step": 540470, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0028717517852783, "global_step": 540471, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0253970623016357, "global_step": 540472, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.152196168899536, "global_step": 540473, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0218324661254883, "global_step": 540474, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1043882369995117, "global_step": 540475, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.007472038269043, "global_step": 540476, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0553202629089355, "global_step": 540477, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.995071530342102, "global_step": 540478, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9799251556396484, "global_step": 540479, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.055856704711914, "global_step": 540480, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.034341812133789, "global_step": 540481, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.116159677505493, "global_step": 540482, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9969725608825684, "global_step": 540483, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0263137817382812, "global_step": 540484, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.030951499938965, "global_step": 540485, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9677733182907104, "global_step": 540486, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.049121856689453, "global_step": 540487, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.947952389717102, "global_step": 540488, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0105230808258057, "global_step": 540489, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0579922199249268, "global_step": 540490, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.065312385559082, "global_step": 540491, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0833215713500977, "global_step": 540492, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9597433805465698, "global_step": 540493, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0454511642456055, "global_step": 540494, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9753820896148682, "global_step": 540495, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.079728364944458, "global_step": 540496, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.020099639892578, "global_step": 540497, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.005006790161133, "global_step": 540498, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0615475177764893, "global_step": 540499, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.086158275604248, "global_step": 540500, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9881136417388916, "global_step": 540501, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.021427869796753, "global_step": 540502, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9469605684280396, "global_step": 540503, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9484715461730957, "global_step": 540504, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9661279916763306, "global_step": 540505, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.076505184173584, "global_step": 540506, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0863237380981445, "global_step": 540507, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0586979389190674, "global_step": 540508, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0147244930267334, "global_step": 540509, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.090640068054199, "global_step": 540510, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0731935501098633, "global_step": 540511, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.072594165802002, "global_step": 540512, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.009876012802124, "global_step": 540513, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0785982608795166, "global_step": 540514, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0103464126586914, "global_step": 540515, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9870705604553223, "global_step": 540516, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0083677768707275, "global_step": 540517, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.050848960876465, "global_step": 540518, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9772928953170776, "global_step": 540519, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0696983337402344, "global_step": 540520, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.056805372238159, "global_step": 540521, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0597195625305176, "global_step": 540522, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0213136672973633, "global_step": 540523, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.219728946685791, "global_step": 540524, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0516624450683594, "global_step": 540525, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0386264324188232, "global_step": 540526, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0395455360412598, "global_step": 540527, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9796171188354492, "global_step": 540528, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9980158805847168, "global_step": 540529, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0782992839813232, "global_step": 540530, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.004974126815796, "global_step": 540531, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0759260654449463, "global_step": 540532, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.03227162361145, "global_step": 540533, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0463106632232666, "global_step": 540534, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.004692554473877, "global_step": 540535, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1493120193481445, "global_step": 540536, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.989466667175293, "global_step": 540537, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0067214965820312, "global_step": 540538, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0260679721832275, "global_step": 540539, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.029939889907837, "global_step": 540540, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0731964111328125, "global_step": 540541, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9805830717086792, "global_step": 540542, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.040743589401245, "global_step": 540543, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0931026935577393, "global_step": 540544, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.034226179122925, "global_step": 540545, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.081571102142334, "global_step": 540546, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.06065034866333, "global_step": 540547, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.109675645828247, "global_step": 540548, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9157757759094238, "global_step": 540549, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9982103109359741, "global_step": 540550, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9864109754562378, "global_step": 540551, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0341339111328125, "global_step": 540552, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.017545700073242, "global_step": 540553, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1281416416168213, "global_step": 540554, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9491403102874756, "global_step": 540555, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.156466245651245, "global_step": 540556, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0577585697174072, "global_step": 540557, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.048954725265503, "global_step": 540558, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9832748174667358, "global_step": 540559, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9916654825210571, "global_step": 540560, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.034468412399292, "global_step": 540561, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9735139608383179, "global_step": 540562, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1659042835235596, "global_step": 540563, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.094841241836548, "global_step": 540564, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0870304107666016, "global_step": 540565, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9970290660858154, "global_step": 540566, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.042956829071045, "global_step": 540567, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.115259885787964, "global_step": 540568, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.015981912612915, "global_step": 540569, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9984557628631592, "global_step": 540570, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9733972549438477, "global_step": 540571, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9129128456115723, "global_step": 540572, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.107591152191162, "global_step": 540573, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.06142258644104, "global_step": 540574, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9926739931106567, "global_step": 540575, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.11767578125, "global_step": 540576, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.076810598373413, "global_step": 540577, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9980549812316895, "global_step": 540578, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.988439917564392, "global_step": 540579, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0270466804504395, "global_step": 540580, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.036327838897705, "global_step": 540581, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1325628757476807, "global_step": 540582, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.97509765625, "global_step": 540583, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.052710771560669, "global_step": 540584, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0511257648468018, "global_step": 540585, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.055612564086914, "global_step": 540586, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9791712760925293, "global_step": 540587, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9888801574707031, "global_step": 540588, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.122692584991455, "global_step": 540589, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9632588624954224, "global_step": 540590, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.039015531539917, "global_step": 540591, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.05244779586792, "global_step": 540592, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.025611639022827, "global_step": 540593, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.991766095161438, "global_step": 540594, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9970738887786865, "global_step": 540595, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9622629880905151, "global_step": 540596, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0538930892944336, "global_step": 540597, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0286405086517334, "global_step": 540598, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9919309616088867, "global_step": 540599, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0621652603149414, "global_step": 540600, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.098790407180786, "global_step": 540601, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.006328582763672, "global_step": 540602, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9602270126342773, "global_step": 540603, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0303826332092285, "global_step": 540604, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0029497146606445, "global_step": 540605, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0142288208007812, "global_step": 540606, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.049943208694458, "global_step": 540607, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0207858085632324, "global_step": 540608, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0387091636657715, "global_step": 540609, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.089836835861206, "global_step": 540610, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.113361120223999, "global_step": 540611, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9504364728927612, "global_step": 540612, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.101058006286621, "global_step": 540613, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.021679401397705, "global_step": 540614, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.072643756866455, "global_step": 540615, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.053889513015747, "global_step": 540616, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1243844032287598, "global_step": 540617, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0721685886383057, "global_step": 540618, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.004779577255249, "global_step": 540619, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1594955921173096, "global_step": 540620, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.986653447151184, "global_step": 540621, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.083502769470215, "global_step": 540622, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0729820728302, "global_step": 540623, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.037417411804199, "global_step": 540624, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0097458362579346, "global_step": 540625, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.006675958633423, "global_step": 540626, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.133403778076172, "global_step": 540627, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0288994312286377, "global_step": 540628, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0365042686462402, "global_step": 540629, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0725584030151367, "global_step": 540630, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0287163257598877, "global_step": 540631, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.067805051803589, "global_step": 540632, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0628998279571533, "global_step": 540633, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.12454891204834, "global_step": 540634, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0570499897003174, "global_step": 540635, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0564942359924316, "global_step": 540636, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0544116497039795, "global_step": 540637, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0268850326538086, "global_step": 540638, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.08762526512146, "global_step": 540639, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.009131908416748, "global_step": 540640, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1674177646636963, "global_step": 540641, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.101550817489624, "global_step": 540642, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.056778907775879, "global_step": 540643, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.038600206375122, "global_step": 540644, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0155985355377197, "global_step": 540645, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0006539821624756, "global_step": 540646, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0126562118530273, "global_step": 540647, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.012424945831299, "global_step": 540648, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9980363845825195, "global_step": 540649, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.027242422103882, "global_step": 540650, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0348305702209473, "global_step": 540651, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.071959972381592, "global_step": 540652, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9289394617080688, "global_step": 540653, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.028251886367798, "global_step": 540654, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0777835845947266, "global_step": 540655, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9675029516220093, "global_step": 540656, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.043574333190918, "global_step": 540657, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.010773181915283, "global_step": 540658, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.94500732421875, "global_step": 540659, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.106027364730835, "global_step": 540660, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0538530349731445, "global_step": 540661, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9930185079574585, "global_step": 540662, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1096677780151367, "global_step": 540663, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0859005451202393, "global_step": 540664, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.167593479156494, "global_step": 540665, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0667264461517334, "global_step": 540666, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.039536476135254, "global_step": 540667, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0820186138153076, "global_step": 540668, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9715899229049683, "global_step": 540669, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.040679454803467, "global_step": 540670, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.050231456756592, "global_step": 540671, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.005129814147949, "global_step": 540672, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.085756301879883, "global_step": 540673, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.061279535293579, "global_step": 540674, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.022028684616089, "global_step": 540675, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0343289375305176, "global_step": 540676, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.039930582046509, "global_step": 540677, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1154143810272217, "global_step": 540678, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.024686098098755, "global_step": 540679, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9805439710617065, "global_step": 540680, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.023928642272949, "global_step": 540681, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0574729442596436, "global_step": 540682, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9893584251403809, "global_step": 540683, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.913596510887146, "global_step": 540684, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0696804523468018, "global_step": 540685, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0301425457000732, "global_step": 540686, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0034544467926025, "global_step": 540687, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.073239326477051, "global_step": 540688, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0343821048736572, "global_step": 540689, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.022869348526001, "global_step": 540690, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.048114061355591, "global_step": 540691, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.067399263381958, "global_step": 540692, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0251259803771973, "global_step": 540693, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.019216299057007, "global_step": 540694, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0755467414855957, "global_step": 540695, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.022552728652954, "global_step": 540696, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1178438663482666, "global_step": 540697, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9665762186050415, "global_step": 540698, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.032618761062622, "global_step": 540699, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9474371671676636, "global_step": 540700, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.020148515701294, "global_step": 540701, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0054991245269775, "global_step": 540702, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.981614112854004, "global_step": 540703, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0825693607330322, "global_step": 540704, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.042482614517212, "global_step": 540705, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.099107027053833, "global_step": 540706, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.037339925765991, "global_step": 540707, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1153979301452637, "global_step": 540708, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.992543339729309, "global_step": 540709, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9271782636642456, "global_step": 540710, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0149431228637695, "global_step": 540711, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.949774980545044, "global_step": 540712, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0193309783935547, "global_step": 540713, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1082353591918945, "global_step": 540714, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.063394784927368, "global_step": 540715, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0555920600891113, "global_step": 540716, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0836236476898193, "global_step": 540717, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.933672308921814, "global_step": 540718, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.031322717666626, "global_step": 540719, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.037992000579834, "global_step": 540720, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1214981079101562, "global_step": 540721, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.036099672317505, "global_step": 540722, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0887622833251953, "global_step": 540723, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0526697635650635, "global_step": 540724, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9781709909439087, "global_step": 540725, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0472123622894287, "global_step": 540726, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0476672649383545, "global_step": 540727, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.992201328277588, "global_step": 540728, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0526392459869385, "global_step": 540729, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9515981674194336, "global_step": 540730, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.083804130554199, "global_step": 540731, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9450689554214478, "global_step": 540732, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9648196697235107, "global_step": 540733, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1112060546875, "global_step": 540734, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1119914054870605, "global_step": 540735, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1045303344726562, "global_step": 540736, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.06783390045166, "global_step": 540737, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0634799003601074, "global_step": 540738, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9277825355529785, "global_step": 540739, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9890235662460327, "global_step": 540740, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.033585548400879, "global_step": 540741, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.061431407928467, "global_step": 540742, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0628321170806885, "global_step": 540743, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.017550230026245, "global_step": 540744, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0478057861328125, "global_step": 540745, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9738353490829468, "global_step": 540746, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0437209606170654, "global_step": 540747, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1142871379852295, "global_step": 540748, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0990076065063477, "global_step": 540749, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0203123092651367, "global_step": 540750, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0118236541748047, "global_step": 540751, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1025888919830322, "global_step": 540752, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9683817625045776, "global_step": 540753, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.08463191986084, "global_step": 540754, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.036188840866089, "global_step": 540755, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0492210388183594, "global_step": 540756, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.006805896759033, "global_step": 540757, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0085604190826416, "global_step": 540758, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.088754415512085, "global_step": 540759, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0378293991088867, "global_step": 540760, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0458145141601562, "global_step": 540761, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0505588054656982, "global_step": 540762, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.077610969543457, "global_step": 540763, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.086103677749634, "global_step": 540764, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9699941873550415, "global_step": 540765, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0115034580230713, "global_step": 540766, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1118249893188477, "global_step": 540767, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.004741907119751, "global_step": 540768, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0113558769226074, "global_step": 540769, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.028153657913208, "global_step": 540770, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0047390460968018, "global_step": 540771, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0255258083343506, "global_step": 540772, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.049919605255127, "global_step": 540773, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0159738063812256, "global_step": 540774, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0402605533599854, "global_step": 540775, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.982110857963562, "global_step": 540776, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9695073366165161, "global_step": 540777, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.081589937210083, "global_step": 540778, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.005213975906372, "global_step": 540779, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.013455867767334, "global_step": 540780, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0503854751586914, "global_step": 540781, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.012327194213867, "global_step": 540782, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.959008812904358, "global_step": 540783, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.078239917755127, "global_step": 540784, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.035754442214966, "global_step": 540785, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.025057792663574, "global_step": 540786, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1122477054595947, "global_step": 540787, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9875898361206055, "global_step": 540788, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.080591917037964, "global_step": 540789, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.076324224472046, "global_step": 540790, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.026582956314087, "global_step": 540791, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9955211877822876, "global_step": 540792, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9614835977554321, "global_step": 540793, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9734610319137573, "global_step": 540794, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.030604362487793, "global_step": 540795, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0281214714050293, "global_step": 540796, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.072629928588867, "global_step": 540797, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0199522972106934, "global_step": 540798, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.099334955215454, "global_step": 540799, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0833847522735596, "global_step": 540800, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.05734920501709, "global_step": 540801, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.044090509414673, "global_step": 540802, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0743768215179443, "global_step": 540803, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0559988021850586, "global_step": 540804, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.057209014892578, "global_step": 540805, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9898436069488525, "global_step": 540806, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.023768186569214, "global_step": 540807, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.008866786956787, "global_step": 540808, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1237635612487793, "global_step": 540809, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.042397975921631, "global_step": 540810, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.004943609237671, "global_step": 540811, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0199332237243652, "global_step": 540812, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0583789348602295, "global_step": 540813, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0530076026916504, "global_step": 540814, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9976098537445068, "global_step": 540815, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9907058477401733, "global_step": 540816, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0437090396881104, "global_step": 540817, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0581247806549072, "global_step": 540818, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.046874761581421, "global_step": 540819, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0760974884033203, "global_step": 540820, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.059415817260742, "global_step": 540821, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.031573534011841, "global_step": 540822, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.005679130554199, "global_step": 540823, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0842576026916504, "global_step": 540824, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.110887289047241, "global_step": 540825, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.00661563873291, "global_step": 540826, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.01385235786438, "global_step": 540827, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9651511907577515, "global_step": 540828, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0722031593322754, "global_step": 540829, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0382378101348877, "global_step": 540830, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.1171579360961914, "global_step": 540831, "epoch": 907, "lr": 5e-05}
{"train_loss": 1.9856295585632324, "global_step": 540832, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0542538166046143, "global_step": 540833, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.032684564590454, "global_step": 540834, "epoch": 907, "lr": 5e-05}
{"train_loss": 2.0772438049316406, "global_step": 540835, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9625390768051147, "global_step": 540836, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.045766830444336, "global_step": 540837, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0502305030822754, "global_step": 540838, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.986812949180603, "global_step": 540839, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.082880973815918, "global_step": 540840, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0055487155914307, "global_step": 540841, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.031923532485962, "global_step": 540842, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.002117395401001, "global_step": 540843, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.991900086402893, "global_step": 540844, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9674136638641357, "global_step": 540845, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9381738901138306, "global_step": 540846, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9793671369552612, "global_step": 540847, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.034649133682251, "global_step": 540848, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0145249366760254, "global_step": 540849, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.996683955192566, "global_step": 540850, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.014188766479492, "global_step": 540851, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.076735734939575, "global_step": 540852, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0225789546966553, "global_step": 540853, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9935847520828247, "global_step": 540854, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0181427001953125, "global_step": 540855, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0434770584106445, "global_step": 540856, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0474042892456055, "global_step": 540857, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0246005058288574, "global_step": 540858, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9854426383972168, "global_step": 540859, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0026252269744873, "global_step": 540860, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.01466703414917, "global_step": 540861, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.05497670173645, "global_step": 540862, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.020524501800537, "global_step": 540863, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9423476457595825, "global_step": 540864, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9878767728805542, "global_step": 540865, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0290133953094482, "global_step": 540866, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.076537609100342, "global_step": 540867, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.047811508178711, "global_step": 540868, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9684275388717651, "global_step": 540869, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.03939151763916, "global_step": 540870, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0320699214935303, "global_step": 540871, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0080370903015137, "global_step": 540872, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9554064273834229, "global_step": 540873, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9923548698425293, "global_step": 540874, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.065746307373047, "global_step": 540875, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.00455904006958, "global_step": 540876, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0211713314056396, "global_step": 540877, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.958397388458252, "global_step": 540878, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9881541728973389, "global_step": 540879, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9803814888000488, "global_step": 540880, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.931072473526001, "global_step": 540881, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.094573974609375, "global_step": 540882, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.989169955253601, "global_step": 540883, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.098228931427002, "global_step": 540884, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0479366779327393, "global_step": 540885, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0627894401550293, "global_step": 540886, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.011000394821167, "global_step": 540887, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.992974877357483, "global_step": 540888, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.959177851676941, "global_step": 540889, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.995741844177246, "global_step": 540890, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.065948009490967, "global_step": 540891, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0725884437561035, "global_step": 540892, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.01383900642395, "global_step": 540893, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0512783527374268, "global_step": 540894, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.031202793121338, "global_step": 540895, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0019752979278564, "global_step": 540896, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.02891206741333, "global_step": 540897, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.97942316532135, "global_step": 540898, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1313366889953613, "global_step": 540899, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.8934166431427002, "global_step": 540900, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.945135474205017, "global_step": 540901, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.051964282989502, "global_step": 540902, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.083932638168335, "global_step": 540903, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0501880645751953, "global_step": 540904, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9859795570373535, "global_step": 540905, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9478294849395752, "global_step": 540906, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0044870376586914, "global_step": 540907, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0836637020111084, "global_step": 540908, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0213623046875, "global_step": 540909, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0572376251220703, "global_step": 540910, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0532188415527344, "global_step": 540911, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.056264638900757, "global_step": 540912, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9734735488891602, "global_step": 540913, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9664812088012695, "global_step": 540914, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.002300500869751, "global_step": 540915, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.061039924621582, "global_step": 540916, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.072939872741699, "global_step": 540917, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.094426393508911, "global_step": 540918, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9934020042419434, "global_step": 540919, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0523345470428467, "global_step": 540920, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.996975064277649, "global_step": 540921, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.041699171066284, "global_step": 540922, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0516557693481445, "global_step": 540923, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.047192335128784, "global_step": 540924, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.035602569580078, "global_step": 540925, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9862265586853027, "global_step": 540926, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.102639675140381, "global_step": 540927, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.061530590057373, "global_step": 540928, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9722490310668945, "global_step": 540929, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0114479064941406, "global_step": 540930, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.01059627532959, "global_step": 540931, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.102832555770874, "global_step": 540932, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0896224975585938, "global_step": 540933, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9868321418762207, "global_step": 540934, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0157337188720703, "global_step": 540935, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.073927164077759, "global_step": 540936, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.03941011428833, "global_step": 540937, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9835225343704224, "global_step": 540938, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0238869190216064, "global_step": 540939, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9587434530258179, "global_step": 540940, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.047646999359131, "global_step": 540941, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0527753829956055, "global_step": 540942, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9759864807128906, "global_step": 540943, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0009982585906982, "global_step": 540944, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0179271697998047, "global_step": 540945, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0589447021484375, "global_step": 540946, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.961949348449707, "global_step": 540947, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0041744709014893, "global_step": 540948, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0672924518585205, "global_step": 540949, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.032207489013672, "global_step": 540950, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0800623893737793, "global_step": 540951, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0706446170806885, "global_step": 540952, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0293567180633545, "global_step": 540953, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.028221607208252, "global_step": 540954, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1024045944213867, "global_step": 540955, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.028120994567871, "global_step": 540956, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9738810062408447, "global_step": 540957, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0104146003723145, "global_step": 540958, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0338122844696045, "global_step": 540959, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0293843746185303, "global_step": 540960, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0454704761505127, "global_step": 540961, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0261971950531006, "global_step": 540962, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0149388313293457, "global_step": 540963, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0653464794158936, "global_step": 540964, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9142199754714966, "global_step": 540965, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0169997215270996, "global_step": 540966, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.011270761489868, "global_step": 540967, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9652576446533203, "global_step": 540968, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9367382526397705, "global_step": 540969, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.012925148010254, "global_step": 540970, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.05804181098938, "global_step": 540971, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0975260734558105, "global_step": 540972, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.074782133102417, "global_step": 540973, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9735795259475708, "global_step": 540974, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.963780403137207, "global_step": 540975, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9722028970718384, "global_step": 540976, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0576634407043457, "global_step": 540977, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9635618925094604, "global_step": 540978, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9942952394485474, "global_step": 540979, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.030425786972046, "global_step": 540980, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9013335704803467, "global_step": 540981, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1042795181274414, "global_step": 540982, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0440189838409424, "global_step": 540983, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9499790668487549, "global_step": 540984, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0724823474884033, "global_step": 540985, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9950647354125977, "global_step": 540986, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0082905292510986, "global_step": 540987, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.98039710521698, "global_step": 540988, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.083876371383667, "global_step": 540989, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.105926036834717, "global_step": 540990, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.048964262008667, "global_step": 540991, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1316113471984863, "global_step": 540992, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9847005605697632, "global_step": 540993, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9354575872421265, "global_step": 540994, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9876718521118164, "global_step": 540995, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.001383066177368, "global_step": 540996, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0470001697540283, "global_step": 540997, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1031248569488525, "global_step": 540998, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9964197874069214, "global_step": 540999, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1023366451263428, "global_step": 541000, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.072596311569214, "global_step": 541001, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.057704448699951, "global_step": 541002, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.973695993423462, "global_step": 541003, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0373854637145996, "global_step": 541004, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1554064750671387, "global_step": 541005, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0087218284606934, "global_step": 541006, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9209609031677246, "global_step": 541007, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0473763942718506, "global_step": 541008, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9958499670028687, "global_step": 541009, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0954461097717285, "global_step": 541010, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.006058931350708, "global_step": 541011, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0372118949890137, "global_step": 541012, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.044647216796875, "global_step": 541013, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9678441286087036, "global_step": 541014, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.972364902496338, "global_step": 541015, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0191051959991455, "global_step": 541016, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.040041446685791, "global_step": 541017, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.968612790107727, "global_step": 541018, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.969830870628357, "global_step": 541019, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9952129125595093, "global_step": 541020, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0062801837921143, "global_step": 541021, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.065058708190918, "global_step": 541022, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.958065390586853, "global_step": 541023, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9513670206069946, "global_step": 541024, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9871244430541992, "global_step": 541025, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9833369255065918, "global_step": 541026, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0029709339141846, "global_step": 541027, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0168848037719727, "global_step": 541028, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.034433603286743, "global_step": 541029, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9617918729782104, "global_step": 541030, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0466432571411133, "global_step": 541031, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0946285724639893, "global_step": 541032, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.012556314468384, "global_step": 541033, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0330750942230225, "global_step": 541034, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.091987133026123, "global_step": 541035, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0616188049316406, "global_step": 541036, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.067279577255249, "global_step": 541037, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1093404293060303, "global_step": 541038, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.124049425125122, "global_step": 541039, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0401394367218018, "global_step": 541040, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.070070505142212, "global_step": 541041, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0071518421173096, "global_step": 541042, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.027385950088501, "global_step": 541043, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.004758834838867, "global_step": 541044, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9322649240493774, "global_step": 541045, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.017426013946533, "global_step": 541046, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.056171178817749, "global_step": 541047, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.042156457901001, "global_step": 541048, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0410423278808594, "global_step": 541049, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.004342555999756, "global_step": 541050, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.077479839324951, "global_step": 541051, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0000438690185547, "global_step": 541052, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0609240531921387, "global_step": 541053, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0571787357330322, "global_step": 541054, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.071957588195801, "global_step": 541055, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9778791666030884, "global_step": 541056, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.072861433029175, "global_step": 541057, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0556387901306152, "global_step": 541058, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.052319049835205, "global_step": 541059, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0999109745025635, "global_step": 541060, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9940464496612549, "global_step": 541061, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.035827159881592, "global_step": 541062, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.005845546722412, "global_step": 541063, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0990030765533447, "global_step": 541064, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0284533500671387, "global_step": 541065, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.080569267272949, "global_step": 541066, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.8962972164154053, "global_step": 541067, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0709168910980225, "global_step": 541068, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0827910900115967, "global_step": 541069, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0361578464508057, "global_step": 541070, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9944236278533936, "global_step": 541071, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.043009042739868, "global_step": 541072, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.058783531188965, "global_step": 541073, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0997860431671143, "global_step": 541074, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0714027881622314, "global_step": 541075, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0616445541381836, "global_step": 541076, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0877726078033447, "global_step": 541077, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0011982917785645, "global_step": 541078, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1352145671844482, "global_step": 541079, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0135207176208496, "global_step": 541080, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9723773002624512, "global_step": 541081, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.016544818878174, "global_step": 541082, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0312395095825195, "global_step": 541083, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0254390239715576, "global_step": 541084, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.046487808227539, "global_step": 541085, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0373549461364746, "global_step": 541086, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9933667182922363, "global_step": 541087, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1049842834472656, "global_step": 541088, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.996256709098816, "global_step": 541089, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0669188499450684, "global_step": 541090, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.012476682662964, "global_step": 541091, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9903771877288818, "global_step": 541092, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.071506977081299, "global_step": 541093, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1023545265197754, "global_step": 541094, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9935296773910522, "global_step": 541095, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.007735252380371, "global_step": 541096, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0847063064575195, "global_step": 541097, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9832333326339722, "global_step": 541098, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.128392219543457, "global_step": 541099, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.05074405670166, "global_step": 541100, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0221333503723145, "global_step": 541101, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0458333492279053, "global_step": 541102, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.060487747192383, "global_step": 541103, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.031541347503662, "global_step": 541104, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.083899736404419, "global_step": 541105, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0084874629974365, "global_step": 541106, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.064775228500366, "global_step": 541107, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.010641574859619, "global_step": 541108, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.019265651702881, "global_step": 541109, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9707014560699463, "global_step": 541110, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9754517078399658, "global_step": 541111, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.024132490158081, "global_step": 541112, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9503772258758545, "global_step": 541113, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.075525999069214, "global_step": 541114, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0635933876037598, "global_step": 541115, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0921030044555664, "global_step": 541116, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.062201738357544, "global_step": 541117, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.019120931625366, "global_step": 541118, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.986780047416687, "global_step": 541119, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0558085441589355, "global_step": 541120, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.036353826522827, "global_step": 541121, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.092823028564453, "global_step": 541122, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.069854497909546, "global_step": 541123, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0320961475372314, "global_step": 541124, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.938849925994873, "global_step": 541125, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0580430030822754, "global_step": 541126, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.019066333770752, "global_step": 541127, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1323513984680176, "global_step": 541128, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0672335624694824, "global_step": 541129, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.023097515106201, "global_step": 541130, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0735201835632324, "global_step": 541131, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0330889225006104, "global_step": 541132, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0075604915618896, "global_step": 541133, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0427844524383545, "global_step": 541134, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0197887420654297, "global_step": 541135, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9413154125213623, "global_step": 541136, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9247496128082275, "global_step": 541137, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0208699703216553, "global_step": 541138, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.091007947921753, "global_step": 541139, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0138449668884277, "global_step": 541140, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0267698764801025, "global_step": 541141, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0120863914489746, "global_step": 541142, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0459554195404053, "global_step": 541143, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1069560050964355, "global_step": 541144, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0309574604034424, "global_step": 541145, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9991486072540283, "global_step": 541146, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0175247192382812, "global_step": 541147, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9803516864776611, "global_step": 541148, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9808411598205566, "global_step": 541149, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0599424839019775, "global_step": 541150, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0353901386260986, "global_step": 541151, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9727871417999268, "global_step": 541152, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.031726121902466, "global_step": 541153, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.045086622238159, "global_step": 541154, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.068979024887085, "global_step": 541155, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9445741176605225, "global_step": 541156, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.144993305206299, "global_step": 541157, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.081242561340332, "global_step": 541158, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.14119553565979, "global_step": 541159, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.157144069671631, "global_step": 541160, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.063368082046509, "global_step": 541161, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0454275608062744, "global_step": 541162, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.957780361175537, "global_step": 541163, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.022282600402832, "global_step": 541164, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0239627361297607, "global_step": 541165, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0278921127319336, "global_step": 541166, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0128328800201416, "global_step": 541167, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9990944862365723, "global_step": 541168, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9951186180114746, "global_step": 541169, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9979230165481567, "global_step": 541170, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.028829336166382, "global_step": 541171, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.026118040084839, "global_step": 541172, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0275261402130127, "global_step": 541173, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1207616329193115, "global_step": 541174, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9992234706878662, "global_step": 541175, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9858938455581665, "global_step": 541176, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.000687837600708, "global_step": 541177, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0301246643066406, "global_step": 541178, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0091748237609863, "global_step": 541179, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.033721446990967, "global_step": 541180, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.081136703491211, "global_step": 541181, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.078160285949707, "global_step": 541182, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9992163181304932, "global_step": 541183, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0709471702575684, "global_step": 541184, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0523271560668945, "global_step": 541185, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9382548332214355, "global_step": 541186, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9680821895599365, "global_step": 541187, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.079228401184082, "global_step": 541188, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0437240600585938, "global_step": 541189, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.005741834640503, "global_step": 541190, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9964466094970703, "global_step": 541191, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0245697498321533, "global_step": 541192, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.020827293395996, "global_step": 541193, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.046180009841919, "global_step": 541194, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.978235125541687, "global_step": 541195, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.902060866355896, "global_step": 541196, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.010948657989502, "global_step": 541197, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9234919548034668, "global_step": 541198, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9908688068389893, "global_step": 541199, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0575449466705322, "global_step": 541200, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.956128478050232, "global_step": 541201, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9607855081558228, "global_step": 541202, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.035698413848877, "global_step": 541203, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.007709264755249, "global_step": 541204, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0475974082946777, "global_step": 541205, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.025902032852173, "global_step": 541206, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0029430389404297, "global_step": 541207, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9953476190567017, "global_step": 541208, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9721356630325317, "global_step": 541209, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1135776042938232, "global_step": 541210, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0425450801849365, "global_step": 541211, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.091188430786133, "global_step": 541212, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0752367973327637, "global_step": 541213, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0540239810943604, "global_step": 541214, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0012004375457764, "global_step": 541215, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9851962327957153, "global_step": 541216, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.020451068878174, "global_step": 541217, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0300114154815674, "global_step": 541218, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0892868041992188, "global_step": 541219, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9824824333190918, "global_step": 541220, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.03902530670166, "global_step": 541221, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0204529762268066, "global_step": 541222, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.106165647506714, "global_step": 541223, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.031313180923462, "global_step": 541224, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9812698364257812, "global_step": 541225, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0085721015930176, "global_step": 541226, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.020237922668457, "global_step": 541227, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.037003755569458, "global_step": 541228, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.007596254348755, "global_step": 541229, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.102658748626709, "global_step": 541230, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0078988075256348, "global_step": 541231, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9601706266403198, "global_step": 541232, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0540645122528076, "global_step": 541233, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0446925163269043, "global_step": 541234, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0343785285949707, "global_step": 541235, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0140483379364014, "global_step": 541236, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0400021076202393, "global_step": 541237, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9509344100952148, "global_step": 541238, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9941060543060303, "global_step": 541239, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0192131996154785, "global_step": 541240, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9317896366119385, "global_step": 541241, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9666415452957153, "global_step": 541242, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.006052255630493, "global_step": 541243, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.015526294708252, "global_step": 541244, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.984275221824646, "global_step": 541245, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9219653606414795, "global_step": 541246, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.045741558074951, "global_step": 541247, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.069301128387451, "global_step": 541248, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0733726024627686, "global_step": 541249, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9997899532318115, "global_step": 541250, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0378501415252686, "global_step": 541251, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9309825897216797, "global_step": 541252, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.079728603363037, "global_step": 541253, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.035701274871826, "global_step": 541254, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9283865690231323, "global_step": 541255, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0281448364257812, "global_step": 541256, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9874954223632812, "global_step": 541257, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9792349338531494, "global_step": 541258, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.024261713027954, "global_step": 541259, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0062971115112305, "global_step": 541260, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9854216575622559, "global_step": 541261, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.089892864227295, "global_step": 541262, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.087905168533325, "global_step": 541263, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9598721265792847, "global_step": 541264, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0735726356506348, "global_step": 541265, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0247066020965576, "global_step": 541266, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0975759029388428, "global_step": 541267, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9482203722000122, "global_step": 541268, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0457191467285156, "global_step": 541269, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0168192386627197, "global_step": 541270, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1434073448181152, "global_step": 541271, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9655580520629883, "global_step": 541272, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.029381275177002, "global_step": 541273, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.049467086791992, "global_step": 541274, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.973763108253479, "global_step": 541275, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9941072463989258, "global_step": 541276, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0504348278045654, "global_step": 541277, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0226407051086426, "global_step": 541278, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.017637252807617, "global_step": 541279, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0471765995025635, "global_step": 541280, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0674381256103516, "global_step": 541281, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9689571857452393, "global_step": 541282, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.025524139404297, "global_step": 541283, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0477559566497803, "global_step": 541284, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0600552558898926, "global_step": 541285, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.020472764968872, "global_step": 541286, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9862329959869385, "global_step": 541287, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9910218715667725, "global_step": 541288, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.132077693939209, "global_step": 541289, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.934796690940857, "global_step": 541290, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9730507135391235, "global_step": 541291, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0516321659088135, "global_step": 541292, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.073925495147705, "global_step": 541293, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9845519065856934, "global_step": 541294, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0041892528533936, "global_step": 541295, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.030085325241089, "global_step": 541296, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0246567726135254, "global_step": 541297, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0740113258361816, "global_step": 541298, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0897674560546875, "global_step": 541299, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0457005500793457, "global_step": 541300, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.002277374267578, "global_step": 541301, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.027486562728882, "global_step": 541302, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.027658224105835, "global_step": 541303, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0107061862945557, "global_step": 541304, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.011770725250244, "global_step": 541305, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9611551761627197, "global_step": 541306, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0878849029541016, "global_step": 541307, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.043529987335205, "global_step": 541308, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0012640953063965, "global_step": 541309, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0599842071533203, "global_step": 541310, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.089460849761963, "global_step": 541311, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1218478679656982, "global_step": 541312, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0997626781463623, "global_step": 541313, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0093345642089844, "global_step": 541314, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0565764904022217, "global_step": 541315, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.048752546310425, "global_step": 541316, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0210959911346436, "global_step": 541317, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0007500648498535, "global_step": 541318, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0470130443573, "global_step": 541319, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0240917205810547, "global_step": 541320, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.97586190700531, "global_step": 541321, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.073626756668091, "global_step": 541322, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0137343406677246, "global_step": 541323, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9801114797592163, "global_step": 541324, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9973284006118774, "global_step": 541325, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.059509515762329, "global_step": 541326, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0196759700775146, "global_step": 541327, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.087229013442993, "global_step": 541328, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.049398899078369, "global_step": 541329, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.036173105239868, "global_step": 541330, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0589756965637207, "global_step": 541331, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0289347171783447, "global_step": 541332, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.088024377822876, "global_step": 541333, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.072429656982422, "global_step": 541334, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1023526191711426, "global_step": 541335, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0897650718688965, "global_step": 541336, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.082857847213745, "global_step": 541337, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.086435317993164, "global_step": 541338, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0473475456237793, "global_step": 541339, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0317671298980713, "global_step": 541340, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0225281715393066, "global_step": 541341, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0556986331939697, "global_step": 541342, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.083343505859375, "global_step": 541343, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0706429481506348, "global_step": 541344, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.093041181564331, "global_step": 541345, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0349762439727783, "global_step": 541346, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0044641494750977, "global_step": 541347, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.048933744430542, "global_step": 541348, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9877002239227295, "global_step": 541349, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9848713874816895, "global_step": 541350, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0639398097991943, "global_step": 541351, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1490254402160645, "global_step": 541352, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.022155284881592, "global_step": 541353, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1192023754119873, "global_step": 541354, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0723087787628174, "global_step": 541355, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.049652576446533, "global_step": 541356, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0609512329101562, "global_step": 541357, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.029802083969116, "global_step": 541358, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9704170227050781, "global_step": 541359, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9799528121948242, "global_step": 541360, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.065291166305542, "global_step": 541361, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0962772369384766, "global_step": 541362, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9710637331008911, "global_step": 541363, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0266783237457275, "global_step": 541364, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.055370330810547, "global_step": 541365, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0542869567871094, "global_step": 541366, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0137953758239746, "global_step": 541367, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0924317836761475, "global_step": 541368, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.902923822402954, "global_step": 541369, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.980799674987793, "global_step": 541370, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.114779472351074, "global_step": 541371, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9900928735733032, "global_step": 541372, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.039475440979004, "global_step": 541373, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0491888523101807, "global_step": 541374, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0324764251708984, "global_step": 541375, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.042175769805908, "global_step": 541376, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0877890586853027, "global_step": 541377, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9926908016204834, "global_step": 541378, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9614306688308716, "global_step": 541379, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.09429931640625, "global_step": 541380, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9748280048370361, "global_step": 541381, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.056051731109619, "global_step": 541382, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0545082092285156, "global_step": 541383, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9751439094543457, "global_step": 541384, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0223143100738525, "global_step": 541385, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0132992267608643, "global_step": 541386, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0125582218170166, "global_step": 541387, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0466721057891846, "global_step": 541388, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.006143808364868, "global_step": 541389, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0602810382843018, "global_step": 541390, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.084548234939575, "global_step": 541391, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.116262674331665, "global_step": 541392, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9895230531692505, "global_step": 541393, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.004345655441284, "global_step": 541394, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.082535743713379, "global_step": 541395, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0962133407592773, "global_step": 541396, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.04862117767334, "global_step": 541397, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9756914377212524, "global_step": 541398, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.950016975402832, "global_step": 541399, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9355331659317017, "global_step": 541400, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.105276346206665, "global_step": 541401, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0382120609283447, "global_step": 541402, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.180325984954834, "global_step": 541403, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9952062368392944, "global_step": 541404, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.113048553466797, "global_step": 541405, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.056162118911743, "global_step": 541406, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0127482414245605, "global_step": 541407, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.036888837814331, "global_step": 541408, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0756068229675293, "global_step": 541409, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0447778701782227, "global_step": 541410, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9831503629684448, "global_step": 541411, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9988477230072021, "global_step": 541412, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9438453912734985, "global_step": 541413, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9586031436920166, "global_step": 541414, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0939950942993164, "global_step": 541415, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.104137659072876, "global_step": 541416, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.073859930038452, "global_step": 541417, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0398240089416504, "global_step": 541418, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.043452739715576, "global_step": 541419, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.058161735534668, "global_step": 541420, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0147578716278076, "global_step": 541421, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.023460626602173, "global_step": 541422, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0452523231506348, "global_step": 541423, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0312726497650146, "global_step": 541424, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.011270761489868, "global_step": 541425, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0518813133239746, "global_step": 541426, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.100316286087036, "global_step": 541427, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.050774097442627, "global_step": 541428, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.065019130706787, "global_step": 541429, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9358177185058594, "global_step": 541430, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0466573238372803, "global_step": 541431, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0454750061035156, "global_step": 541432, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1067886352539062, "global_step": 541433, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.072209119796753, "global_step": 541434, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1010165214538574, "global_step": 541435, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.063746690750122, "global_step": 541436, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0250136852264404, "global_step": 541437, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0270607471466064, "global_step": 541438, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0114526748657227, "global_step": 541439, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.940230131149292, "global_step": 541440, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.15431547164917, "global_step": 541441, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0943775177001953, "global_step": 541442, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9824076890945435, "global_step": 541443, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.174062967300415, "global_step": 541444, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0859856605529785, "global_step": 541445, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0543212890625, "global_step": 541446, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0504679679870605, "global_step": 541447, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.029813289642334, "global_step": 541448, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9806843996047974, "global_step": 541449, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.084639310836792, "global_step": 541450, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.988897442817688, "global_step": 541451, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0391480922698975, "global_step": 541452, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0109703540802, "global_step": 541453, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.077944278717041, "global_step": 541454, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9881607294082642, "global_step": 541455, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.984956979751587, "global_step": 541456, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9708517789840698, "global_step": 541457, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.127749443054199, "global_step": 541458, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1068005561828613, "global_step": 541459, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0595521926879883, "global_step": 541460, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0033323764801025, "global_step": 541461, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0416083335876465, "global_step": 541462, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.980000376701355, "global_step": 541463, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0697617530822754, "global_step": 541464, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.049409866333008, "global_step": 541465, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9718974828720093, "global_step": 541466, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.002167224884033, "global_step": 541467, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9780222177505493, "global_step": 541468, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0302915573120117, "global_step": 541469, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9852157831192017, "global_step": 541470, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9526063203811646, "global_step": 541471, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.017160177230835, "global_step": 541472, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.081360340118408, "global_step": 541473, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0216948986053467, "global_step": 541474, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0186169147491455, "global_step": 541475, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0555427074432373, "global_step": 541476, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0295352935791016, "global_step": 541477, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1063616275787354, "global_step": 541478, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.030693531036377, "global_step": 541479, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.058403253555298, "global_step": 541480, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0518064498901367, "global_step": 541481, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9658989906311035, "global_step": 541482, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0970864295959473, "global_step": 541483, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0808143615722656, "global_step": 541484, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0544800758361816, "global_step": 541485, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1108129024505615, "global_step": 541486, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0453383922576904, "global_step": 541487, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.020909070968628, "global_step": 541488, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.068776845932007, "global_step": 541489, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.001485824584961, "global_step": 541490, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0469441413879395, "global_step": 541491, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.051583766937256, "global_step": 541492, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9997817277908325, "global_step": 541493, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.080110549926758, "global_step": 541494, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0161147117614746, "global_step": 541495, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0548133850097656, "global_step": 541496, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.060896873474121, "global_step": 541497, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9988412857055664, "global_step": 541498, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0952489376068115, "global_step": 541499, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.075869560241699, "global_step": 541500, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.024991273880005, "global_step": 541501, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.094954490661621, "global_step": 541502, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0157222747802734, "global_step": 541503, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.009904146194458, "global_step": 541504, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.018282651901245, "global_step": 541505, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0696911811828613, "global_step": 541506, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0038340091705322, "global_step": 541507, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.033565044403076, "global_step": 541508, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0396268367767334, "global_step": 541509, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9512354135513306, "global_step": 541510, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0207390785217285, "global_step": 541511, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0601799488067627, "global_step": 541512, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0521042346954346, "global_step": 541513, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0333945751190186, "global_step": 541514, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.002767324447632, "global_step": 541515, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9740748405456543, "global_step": 541516, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.995556354522705, "global_step": 541517, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0321927070617676, "global_step": 541518, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9784150123596191, "global_step": 541519, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9629889726638794, "global_step": 541520, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.95084810256958, "global_step": 541521, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0142385959625244, "global_step": 541522, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.002408981323242, "global_step": 541523, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.081650495529175, "global_step": 541524, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1198503971099854, "global_step": 541525, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.990991234779358, "global_step": 541526, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0355615615844727, "global_step": 541527, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1418395042419434, "global_step": 541528, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0156266689300537, "global_step": 541529, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.087831974029541, "global_step": 541530, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0684831142425537, "global_step": 541531, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0183537006378174, "global_step": 541532, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0561141967773438, "global_step": 541533, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.056833267211914, "global_step": 541534, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9908233880996704, "global_step": 541535, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0578453540802, "global_step": 541536, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.005139112472534, "global_step": 541537, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.04011607170105, "global_step": 541538, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0740058422088623, "global_step": 541539, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9446028470993042, "global_step": 541540, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0374836921691895, "global_step": 541541, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0388987064361572, "global_step": 541542, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.005632162094116, "global_step": 541543, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0234193801879883, "global_step": 541544, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.13004207611084, "global_step": 541545, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0301332473754883, "global_step": 541546, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1047191619873047, "global_step": 541547, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.079425573348999, "global_step": 541548, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1272239685058594, "global_step": 541549, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1610186100006104, "global_step": 541550, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.073852777481079, "global_step": 541551, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0896615982055664, "global_step": 541552, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.8942817449569702, "global_step": 541553, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0034193992614746, "global_step": 541554, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.010566473007202, "global_step": 541555, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0524778366088867, "global_step": 541556, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.117567300796509, "global_step": 541557, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.06231951713562, "global_step": 541558, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0530574321746826, "global_step": 541559, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.035501003265381, "global_step": 541560, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.045356273651123, "global_step": 541561, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.178417682647705, "global_step": 541562, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0355021953582764, "global_step": 541563, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0190770626068115, "global_step": 541564, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.038780450820923, "global_step": 541565, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.018744707107544, "global_step": 541566, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9626137018203735, "global_step": 541567, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1009838581085205, "global_step": 541568, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.033525228500366, "global_step": 541569, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9955883026123047, "global_step": 541570, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9990479946136475, "global_step": 541571, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.11255145072937, "global_step": 541572, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.018167018890381, "global_step": 541573, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9913147687911987, "global_step": 541574, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0886693000793457, "global_step": 541575, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0433380603790283, "global_step": 541576, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.990200400352478, "global_step": 541577, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.040583848953247, "global_step": 541578, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1085660457611084, "global_step": 541579, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.082223892211914, "global_step": 541580, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.05074405670166, "global_step": 541581, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0691161155700684, "global_step": 541582, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.031109094619751, "global_step": 541583, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0525875091552734, "global_step": 541584, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1131808757781982, "global_step": 541585, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0708298683166504, "global_step": 541586, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9563735723495483, "global_step": 541587, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.094943046569824, "global_step": 541588, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.972810983657837, "global_step": 541589, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.074787139892578, "global_step": 541590, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0891218185424805, "global_step": 541591, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9722298383712769, "global_step": 541592, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9998559951782227, "global_step": 541593, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9887393712997437, "global_step": 541594, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0655083656311035, "global_step": 541595, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0478808879852295, "global_step": 541596, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.049623966217041, "global_step": 541597, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0792288780212402, "global_step": 541598, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0182268619537354, "global_step": 541599, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0357167720794678, "global_step": 541600, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.118230104446411, "global_step": 541601, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0145785808563232, "global_step": 541602, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1543262004852295, "global_step": 541603, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9895802736282349, "global_step": 541604, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.087625503540039, "global_step": 541605, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.956119179725647, "global_step": 541606, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1019952297210693, "global_step": 541607, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0881381034851074, "global_step": 541608, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.020268440246582, "global_step": 541609, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0761284828186035, "global_step": 541610, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0637006759643555, "global_step": 541611, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0808441638946533, "global_step": 541612, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0474023818969727, "global_step": 541613, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0639402866363525, "global_step": 541614, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9633394479751587, "global_step": 541615, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9820849895477295, "global_step": 541616, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1162915229797363, "global_step": 541617, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.024458885192871, "global_step": 541618, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.043586015701294, "global_step": 541619, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0534205436706543, "global_step": 541620, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0055081844329834, "global_step": 541621, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9379184246063232, "global_step": 541622, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9956815242767334, "global_step": 541623, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.09359073638916, "global_step": 541624, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0422961711883545, "global_step": 541625, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.996741533279419, "global_step": 541626, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9981642961502075, "global_step": 541627, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9883652925491333, "global_step": 541628, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.015929698944092, "global_step": 541629, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0149190425872803, "global_step": 541630, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0624935626983643, "global_step": 541631, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.084000825881958, "global_step": 541632, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.986899495124817, "global_step": 541633, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0869357585906982, "global_step": 541634, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0616657733917236, "global_step": 541635, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.036871910095215, "global_step": 541636, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9836771488189697, "global_step": 541637, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0317137241363525, "global_step": 541638, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0818095207214355, "global_step": 541639, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0101871490478516, "global_step": 541640, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0540781021118164, "global_step": 541641, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0893442630767822, "global_step": 541642, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.010591506958008, "global_step": 541643, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.046480655670166, "global_step": 541644, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.025789260864258, "global_step": 541645, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0000758171081543, "global_step": 541646, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0586462020874023, "global_step": 541647, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.065324068069458, "global_step": 541648, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0779411792755127, "global_step": 541649, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.084923028945923, "global_step": 541650, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.022737979888916, "global_step": 541651, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.086671829223633, "global_step": 541652, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.012162923812866, "global_step": 541653, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.072925329208374, "global_step": 541654, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.068633556365967, "global_step": 541655, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0717499256134033, "global_step": 541656, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.08377742767334, "global_step": 541657, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0314548015594482, "global_step": 541658, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0596067905426025, "global_step": 541659, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0403459072113037, "global_step": 541660, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.043755531311035, "global_step": 541661, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9801993370056152, "global_step": 541662, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0225844383239746, "global_step": 541663, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0408434867858887, "global_step": 541664, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.027109146118164, "global_step": 541665, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.077059745788574, "global_step": 541666, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.045184373855591, "global_step": 541667, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.044443368911743, "global_step": 541668, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0497846603393555, "global_step": 541669, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.104128360748291, "global_step": 541670, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.022747755050659, "global_step": 541671, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9781979322433472, "global_step": 541672, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.051074266433716, "global_step": 541673, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.037191867828369, "global_step": 541674, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.007232189178467, "global_step": 541675, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.983028769493103, "global_step": 541676, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9922852516174316, "global_step": 541677, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0371322631835938, "global_step": 541678, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0046775341033936, "global_step": 541679, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9459642171859741, "global_step": 541680, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0675857067108154, "global_step": 541681, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1366522312164307, "global_step": 541682, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0736701488494873, "global_step": 541683, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0293588638305664, "global_step": 541684, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0586061477661133, "global_step": 541685, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0171921253204346, "global_step": 541686, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0646133422851562, "global_step": 541687, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0629091262817383, "global_step": 541688, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0848989486694336, "global_step": 541689, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1003222465515137, "global_step": 541690, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.059213399887085, "global_step": 541691, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9668885469436646, "global_step": 541692, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.012112617492676, "global_step": 541693, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9807208776474, "global_step": 541694, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.06319522857666, "global_step": 541695, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0566272735595703, "global_step": 541696, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.083638906478882, "global_step": 541697, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.028459310531616, "global_step": 541698, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0129215717315674, "global_step": 541699, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.118544340133667, "global_step": 541700, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0585978031158447, "global_step": 541701, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0314321517944336, "global_step": 541702, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0637292861938477, "global_step": 541703, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0124828815460205, "global_step": 541704, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9129953384399414, "global_step": 541705, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9914101362228394, "global_step": 541706, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.054537057876587, "global_step": 541707, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.084549903869629, "global_step": 541708, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9296661615371704, "global_step": 541709, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0257070064544678, "global_step": 541710, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9555795192718506, "global_step": 541711, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9968832731246948, "global_step": 541712, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.041064500808716, "global_step": 541713, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0582363605499268, "global_step": 541714, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0534939765930176, "global_step": 541715, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.122023820877075, "global_step": 541716, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0212783813476562, "global_step": 541717, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.127471923828125, "global_step": 541718, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0241661071777344, "global_step": 541719, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9773951768875122, "global_step": 541720, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.07370662689209, "global_step": 541721, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0742716789245605, "global_step": 541722, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.033277750015259, "global_step": 541723, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9751076698303223, "global_step": 541724, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0753870010375977, "global_step": 541725, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.131230354309082, "global_step": 541726, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.045058012008667, "global_step": 541727, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.05299711227417, "global_step": 541728, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9818669557571411, "global_step": 541729, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0413565635681152, "global_step": 541730, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9957716464996338, "global_step": 541731, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.020480155944824, "global_step": 541732, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0712616443634033, "global_step": 541733, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.142430305480957, "global_step": 541734, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0339951515197754, "global_step": 541735, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.020311117172241, "global_step": 541736, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9746344089508057, "global_step": 541737, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.065718173980713, "global_step": 541738, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9995248317718506, "global_step": 541739, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.994989275932312, "global_step": 541740, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.091256618499756, "global_step": 541741, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.044860363006592, "global_step": 541742, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.099419116973877, "global_step": 541743, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0306310653686523, "global_step": 541744, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0540425777435303, "global_step": 541745, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0596115589141846, "global_step": 541746, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0387353897094727, "global_step": 541747, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9999091625213623, "global_step": 541748, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0197219848632812, "global_step": 541749, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.060148239135742, "global_step": 541750, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9964568614959717, "global_step": 541751, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.052272319793701, "global_step": 541752, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9724842309951782, "global_step": 541753, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.044485092163086, "global_step": 541754, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0492444038391113, "global_step": 541755, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0500521659851074, "global_step": 541756, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9725974798202515, "global_step": 541757, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0719122886657715, "global_step": 541758, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9904552698135376, "global_step": 541759, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.118831157684326, "global_step": 541760, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.003755569458008, "global_step": 541761, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.031435251235962, "global_step": 541762, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1401093006134033, "global_step": 541763, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.053673505783081, "global_step": 541764, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.044790744781494, "global_step": 541765, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0165817737579346, "global_step": 541766, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0522072315216064, "global_step": 541767, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0316720008850098, "global_step": 541768, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.052131414413452, "global_step": 541769, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0593695640563965, "global_step": 541770, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1037826538085938, "global_step": 541771, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.081346273422241, "global_step": 541772, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1179447174072266, "global_step": 541773, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0362164974212646, "global_step": 541774, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1113858222961426, "global_step": 541775, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.039107322692871, "global_step": 541776, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0087175369262695, "global_step": 541777, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1288392543792725, "global_step": 541778, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9511958360671997, "global_step": 541779, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0213887691497803, "global_step": 541780, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.012510061264038, "global_step": 541781, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.96998131275177, "global_step": 541782, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9435571432113647, "global_step": 541783, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9884693622589111, "global_step": 541784, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0148913860321045, "global_step": 541785, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.029802083969116, "global_step": 541786, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.104433059692383, "global_step": 541787, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0810842514038086, "global_step": 541788, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9991097450256348, "global_step": 541789, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.015188217163086, "global_step": 541790, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9831656217575073, "global_step": 541791, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.957176685333252, "global_step": 541792, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.062180519104004, "global_step": 541793, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.120846748352051, "global_step": 541794, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0973589420318604, "global_step": 541795, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0949034690856934, "global_step": 541796, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.161658763885498, "global_step": 541797, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.1032490730285645, "global_step": 541798, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0952579975128174, "global_step": 541799, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.934614658355713, "global_step": 541800, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0958468914031982, "global_step": 541801, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0238728523254395, "global_step": 541802, "epoch": 908, "lr": 5e-05}
{"train_loss": 2.0334482192993164, "global_step": 541803, "epoch": 908, "lr": 5e-05}
{"train_loss": 1.9979475736618042, "global_step": 541804, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0553770065307617, "global_step": 541805, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.08321213722229, "global_step": 541806, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9568511247634888, "global_step": 541807, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0461831092834473, "global_step": 541808, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.085249900817871, "global_step": 541809, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.002836227416992, "global_step": 541810, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.023876190185547, "global_step": 541811, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0338752269744873, "global_step": 541812, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0526654720306396, "global_step": 541813, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0106403827667236, "global_step": 541814, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9639290571212769, "global_step": 541815, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.004368782043457, "global_step": 541816, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9958456754684448, "global_step": 541817, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9762024879455566, "global_step": 541818, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.087097644805908, "global_step": 541819, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.057053804397583, "global_step": 541820, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0219337940216064, "global_step": 541821, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0276334285736084, "global_step": 541822, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.994995355606079, "global_step": 541823, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.073044538497925, "global_step": 541824, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0456018447875977, "global_step": 541825, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0253212451934814, "global_step": 541826, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.036001443862915, "global_step": 541827, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.028892993927002, "global_step": 541828, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9133884906768799, "global_step": 541829, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.111673355102539, "global_step": 541830, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0171148777008057, "global_step": 541831, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0311169624328613, "global_step": 541832, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9580609798431396, "global_step": 541833, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0824062824249268, "global_step": 541834, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0018982887268066, "global_step": 541835, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.009636402130127, "global_step": 541836, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0626697540283203, "global_step": 541837, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0058274269104004, "global_step": 541838, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0154776573181152, "global_step": 541839, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.041842222213745, "global_step": 541840, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9998294115066528, "global_step": 541841, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.965648889541626, "global_step": 541842, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.017428398132324, "global_step": 541843, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0409228801727295, "global_step": 541844, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.009160041809082, "global_step": 541845, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.040515184402466, "global_step": 541846, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1088693141937256, "global_step": 541847, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9856470823287964, "global_step": 541848, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9999216794967651, "global_step": 541849, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.059195041656494, "global_step": 541850, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.068185567855835, "global_step": 541851, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0496158599853516, "global_step": 541852, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.033926486968994, "global_step": 541853, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.102376937866211, "global_step": 541854, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9981811046600342, "global_step": 541855, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0236473083496094, "global_step": 541856, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0572097301483154, "global_step": 541857, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9502216577529907, "global_step": 541858, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0579042434692383, "global_step": 541859, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0233829021453857, "global_step": 541860, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0277326107025146, "global_step": 541861, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0387136936187744, "global_step": 541862, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0287184715270996, "global_step": 541863, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.991690754890442, "global_step": 541864, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.034897804260254, "global_step": 541865, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0488226413726807, "global_step": 541866, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0263357162475586, "global_step": 541867, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.013751268386841, "global_step": 541868, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0224220752716064, "global_step": 541869, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.008936643600464, "global_step": 541870, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0035879611968994, "global_step": 541871, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0298829078674316, "global_step": 541872, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9754587411880493, "global_step": 541873, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9711929559707642, "global_step": 541874, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9101685285568237, "global_step": 541875, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0361382961273193, "global_step": 541876, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0136735439300537, "global_step": 541877, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.060150384902954, "global_step": 541878, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1030051708221436, "global_step": 541879, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9711023569107056, "global_step": 541880, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0166451930999756, "global_step": 541881, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0243444442749023, "global_step": 541882, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0303220748901367, "global_step": 541883, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.08449649810791, "global_step": 541884, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9717819690704346, "global_step": 541885, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9324672222137451, "global_step": 541886, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9671294689178467, "global_step": 541887, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.03410267829895, "global_step": 541888, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0194766521453857, "global_step": 541889, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9779974222183228, "global_step": 541890, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0659027099609375, "global_step": 541891, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.077746868133545, "global_step": 541892, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.044961452484131, "global_step": 541893, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9452906847000122, "global_step": 541894, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.979899525642395, "global_step": 541895, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9861193895339966, "global_step": 541896, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.060793161392212, "global_step": 541897, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.083101749420166, "global_step": 541898, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0796985626220703, "global_step": 541899, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9740701913833618, "global_step": 541900, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9840538501739502, "global_step": 541901, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.075469970703125, "global_step": 541902, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0218687057495117, "global_step": 541903, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.081825017929077, "global_step": 541904, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.010923147201538, "global_step": 541905, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9741395711898804, "global_step": 541906, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.095644235610962, "global_step": 541907, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.075103282928467, "global_step": 541908, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.879793643951416, "global_step": 541909, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.04854416847229, "global_step": 541910, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9548245668411255, "global_step": 541911, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9860730171203613, "global_step": 541912, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0593631267547607, "global_step": 541913, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0477890968322754, "global_step": 541914, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9808310270309448, "global_step": 541915, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0229451656341553, "global_step": 541916, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9723786115646362, "global_step": 541917, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0723259449005127, "global_step": 541918, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.934006690979004, "global_step": 541919, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0983757972717285, "global_step": 541920, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0423619747161865, "global_step": 541921, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.067953109741211, "global_step": 541922, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0489017963409424, "global_step": 541923, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0689258575439453, "global_step": 541924, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9461607933044434, "global_step": 541925, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.092855930328369, "global_step": 541926, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.057576894760132, "global_step": 541927, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9723433256149292, "global_step": 541928, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0384364128112793, "global_step": 541929, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1098146438598633, "global_step": 541930, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.178508758544922, "global_step": 541931, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.991486668586731, "global_step": 541932, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0373330116271973, "global_step": 541933, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9081774950027466, "global_step": 541934, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0995500087738037, "global_step": 541935, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0864341259002686, "global_step": 541936, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9540448188781738, "global_step": 541937, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9147874116897583, "global_step": 541938, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.098369836807251, "global_step": 541939, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.116058826446533, "global_step": 541940, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0548901557922363, "global_step": 541941, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0484983921051025, "global_step": 541942, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.113095283508301, "global_step": 541943, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1040198802948, "global_step": 541944, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.01251220703125, "global_step": 541945, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.079829454421997, "global_step": 541946, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.027644157409668, "global_step": 541947, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0313687324523926, "global_step": 541948, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.037672519683838, "global_step": 541949, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.009129047393799, "global_step": 541950, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0149741172790527, "global_step": 541951, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.019054412841797, "global_step": 541952, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.048874616622925, "global_step": 541953, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9880679845809937, "global_step": 541954, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0922162532806396, "global_step": 541955, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9932608604431152, "global_step": 541956, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1100263595581055, "global_step": 541957, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.970350980758667, "global_step": 541958, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.084258556365967, "global_step": 541959, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0403389930725098, "global_step": 541960, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9730565547943115, "global_step": 541961, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0625569820404053, "global_step": 541962, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9563682079315186, "global_step": 541963, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.933182716369629, "global_step": 541964, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0430588722229004, "global_step": 541965, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.021864414215088, "global_step": 541966, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.044253349304199, "global_step": 541967, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9623851776123047, "global_step": 541968, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.106963634490967, "global_step": 541969, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0766894817352295, "global_step": 541970, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.073988437652588, "global_step": 541971, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9812310934066772, "global_step": 541972, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9876865148544312, "global_step": 541973, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0538623332977295, "global_step": 541974, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0400428771972656, "global_step": 541975, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0120363235473633, "global_step": 541976, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.027500629425049, "global_step": 541977, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.044729709625244, "global_step": 541978, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0332417488098145, "global_step": 541979, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0304999351501465, "global_step": 541980, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9931941032409668, "global_step": 541981, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0436530113220215, "global_step": 541982, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0828213691711426, "global_step": 541983, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0529003143310547, "global_step": 541984, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0226926803588867, "global_step": 541985, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9882910251617432, "global_step": 541986, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9535576105117798, "global_step": 541987, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.04066801071167, "global_step": 541988, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1021158695220947, "global_step": 541989, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0849437713623047, "global_step": 541990, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.038133144378662, "global_step": 541991, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0217363834381104, "global_step": 541992, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.014859437942505, "global_step": 541993, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9923492670059204, "global_step": 541994, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.061127185821533, "global_step": 541995, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.041288375854492, "global_step": 541996, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0815422534942627, "global_step": 541997, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0183732509613037, "global_step": 541998, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9449208974838257, "global_step": 541999, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0415704250335693, "global_step": 542000, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.99476957321167, "global_step": 542001, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1055655479431152, "global_step": 542002, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.959027647972107, "global_step": 542003, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0419445037841797, "global_step": 542004, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.041942596435547, "global_step": 542005, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.032362461090088, "global_step": 542006, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0956575870513916, "global_step": 542007, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0905425548553467, "global_step": 542008, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0669257640838623, "global_step": 542009, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0603368282318115, "global_step": 542010, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0123398303985596, "global_step": 542011, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.078230619430542, "global_step": 542012, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.09635853767395, "global_step": 542013, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9860528707504272, "global_step": 542014, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.047281265258789, "global_step": 542015, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.08298921585083, "global_step": 542016, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0542960166931152, "global_step": 542017, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0346434116363525, "global_step": 542018, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9358494281768799, "global_step": 542019, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9795162677764893, "global_step": 542020, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0093882083892822, "global_step": 542021, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9766868352890015, "global_step": 542022, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.079052448272705, "global_step": 542023, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9928269386291504, "global_step": 542024, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.062913656234741, "global_step": 542025, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.8836439847946167, "global_step": 542026, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.009943723678589, "global_step": 542027, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1145901679992676, "global_step": 542028, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0198123455047607, "global_step": 542029, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9757022857666016, "global_step": 542030, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0580055713653564, "global_step": 542031, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1246180534362793, "global_step": 542032, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0250658988952637, "global_step": 542033, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0858097076416016, "global_step": 542034, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1105968952178955, "global_step": 542035, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0761921405792236, "global_step": 542036, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0714502334594727, "global_step": 542037, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0518722534179688, "global_step": 542038, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.060407876968384, "global_step": 542039, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0411651134490967, "global_step": 542040, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.019047975540161, "global_step": 542041, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.039907932281494, "global_step": 542042, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0153629779815674, "global_step": 542043, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0509564876556396, "global_step": 542044, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.109902858734131, "global_step": 542045, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9945695400238037, "global_step": 542046, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.009610652923584, "global_step": 542047, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.052156925201416, "global_step": 542048, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0732760429382324, "global_step": 542049, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9972559213638306, "global_step": 542050, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0732967853546143, "global_step": 542051, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0495574474334717, "global_step": 542052, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.998078465461731, "global_step": 542053, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9897218942642212, "global_step": 542054, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.959077000617981, "global_step": 542055, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0002524852752686, "global_step": 542056, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9685273170471191, "global_step": 542057, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.008620500564575, "global_step": 542058, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.97160005569458, "global_step": 542059, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0021207332611084, "global_step": 542060, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9842759370803833, "global_step": 542061, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0778884887695312, "global_step": 542062, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.020610809326172, "global_step": 542063, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9996100664138794, "global_step": 542064, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0159759521484375, "global_step": 542065, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.099485158920288, "global_step": 542066, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1042568683624268, "global_step": 542067, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.001577377319336, "global_step": 542068, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9582405090332031, "global_step": 542069, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0189528465270996, "global_step": 542070, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0494439601898193, "global_step": 542071, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0422191619873047, "global_step": 542072, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.059809446334839, "global_step": 542073, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.127495288848877, "global_step": 542074, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0853140354156494, "global_step": 542075, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.021897554397583, "global_step": 542076, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0675816535949707, "global_step": 542077, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0505118370056152, "global_step": 542078, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.044905662536621, "global_step": 542079, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.015305280685425, "global_step": 542080, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.084437847137451, "global_step": 542081, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.033172845840454, "global_step": 542082, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9922442436218262, "global_step": 542083, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9818940162658691, "global_step": 542084, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1001460552215576, "global_step": 542085, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0768816471099854, "global_step": 542086, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0000221729278564, "global_step": 542087, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0815138816833496, "global_step": 542088, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9836466312408447, "global_step": 542089, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1605842113494873, "global_step": 542090, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1159937381744385, "global_step": 542091, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.021022319793701, "global_step": 542092, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.096160411834717, "global_step": 542093, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0807037353515625, "global_step": 542094, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.954853892326355, "global_step": 542095, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0111334323883057, "global_step": 542096, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0500576496124268, "global_step": 542097, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0667855739593506, "global_step": 542098, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.035374641418457, "global_step": 542099, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.010545253753662, "global_step": 542100, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0515127182006836, "global_step": 542101, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9621812105178833, "global_step": 542102, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.000027894973755, "global_step": 542103, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.066565752029419, "global_step": 542104, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.116044759750366, "global_step": 542105, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9884623289108276, "global_step": 542106, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0476491451263428, "global_step": 542107, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9758281707763672, "global_step": 542108, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9700068235397339, "global_step": 542109, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.052283525466919, "global_step": 542110, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0186312198638916, "global_step": 542111, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0314853191375732, "global_step": 542112, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0115280151367188, "global_step": 542113, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.039335012435913, "global_step": 542114, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9853887557983398, "global_step": 542115, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9773067235946655, "global_step": 542116, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9976228475570679, "global_step": 542117, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9597187042236328, "global_step": 542118, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0652518272399902, "global_step": 542119, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0244600772857666, "global_step": 542120, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1051220893859863, "global_step": 542121, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.995853304862976, "global_step": 542122, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0748775005340576, "global_step": 542123, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0333189964294434, "global_step": 542124, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.029235601425171, "global_step": 542125, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0030481815338135, "global_step": 542126, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.004369020462036, "global_step": 542127, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.022012948989868, "global_step": 542128, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0143933296203613, "global_step": 542129, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.071382999420166, "global_step": 542130, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9870415925979614, "global_step": 542131, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.001879930496216, "global_step": 542132, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9909886121749878, "global_step": 542133, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.007344961166382, "global_step": 542134, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9772106409072876, "global_step": 542135, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0664596557617188, "global_step": 542136, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.026914596557617, "global_step": 542137, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0250611305236816, "global_step": 542138, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.042495012283325, "global_step": 542139, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.055840253829956, "global_step": 542140, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0906524658203125, "global_step": 542141, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.064767837524414, "global_step": 542142, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.990179419517517, "global_step": 542143, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0434701442718506, "global_step": 542144, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0808117389678955, "global_step": 542145, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1066367626190186, "global_step": 542146, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0151124000549316, "global_step": 542147, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0150558948516846, "global_step": 542148, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0834169387817383, "global_step": 542149, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.027430772781372, "global_step": 542150, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1738786697387695, "global_step": 542151, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0111589431762695, "global_step": 542152, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.99586820602417, "global_step": 542153, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9729549884796143, "global_step": 542154, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.037616014480591, "global_step": 542155, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0273470878601074, "global_step": 542156, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9630568027496338, "global_step": 542157, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9656574726104736, "global_step": 542158, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.116154432296753, "global_step": 542159, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.032182455062866, "global_step": 542160, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.075975179672241, "global_step": 542161, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.993977665901184, "global_step": 542162, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9412683248519897, "global_step": 542163, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0994722843170166, "global_step": 542164, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.065812826156616, "global_step": 542165, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0687811374664307, "global_step": 542166, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0236401557922363, "global_step": 542167, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0239412784576416, "global_step": 542168, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.014237880706787, "global_step": 542169, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1284523010253906, "global_step": 542170, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0340170860290527, "global_step": 542171, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9966623783111572, "global_step": 542172, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.037576198577881, "global_step": 542173, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9964276552200317, "global_step": 542174, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0752992630004883, "global_step": 542175, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0326592922210693, "global_step": 542176, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0826821327209473, "global_step": 542177, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0539393424987793, "global_step": 542178, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0163729190826416, "global_step": 542179, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.989133596420288, "global_step": 542180, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.99273681640625, "global_step": 542181, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.014427900314331, "global_step": 542182, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1066513061523438, "global_step": 542183, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.008711099624634, "global_step": 542184, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0069539546966553, "global_step": 542185, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.038541078567505, "global_step": 542186, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0324418544769287, "global_step": 542187, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0277860164642334, "global_step": 542188, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0442371368408203, "global_step": 542189, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.001742124557495, "global_step": 542190, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0208685398101807, "global_step": 542191, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0214040279388428, "global_step": 542192, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1078715324401855, "global_step": 542193, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0103039741516113, "global_step": 542194, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.055462598800659, "global_step": 542195, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.019110918045044, "global_step": 542196, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0146188735961914, "global_step": 542197, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9866775274276733, "global_step": 542198, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0277626514434814, "global_step": 542199, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0882859230041504, "global_step": 542200, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9919289350509644, "global_step": 542201, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.012911558151245, "global_step": 542202, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0387227535247803, "global_step": 542203, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.176689386367798, "global_step": 542204, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0135953426361084, "global_step": 542205, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1282458305358887, "global_step": 542206, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9886456727981567, "global_step": 542207, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0407512187957764, "global_step": 542208, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.933268666267395, "global_step": 542209, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0044190883636475, "global_step": 542210, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.041808843612671, "global_step": 542211, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9602384567260742, "global_step": 542212, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0509023666381836, "global_step": 542213, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9845668077468872, "global_step": 542214, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0036723613739014, "global_step": 542215, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0330650806427, "global_step": 542216, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.999624252319336, "global_step": 542217, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0587024688720703, "global_step": 542218, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0592234134674072, "global_step": 542219, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.086143732070923, "global_step": 542220, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0292651653289795, "global_step": 542221, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9626339673995972, "global_step": 542222, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.969289779663086, "global_step": 542223, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0579586029052734, "global_step": 542224, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0705394744873047, "global_step": 542225, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1316027641296387, "global_step": 542226, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.042508363723755, "global_step": 542227, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.031095266342163, "global_step": 542228, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0505359172821045, "global_step": 542229, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1033339500427246, "global_step": 542230, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0933268070220947, "global_step": 542231, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.019716262817383, "global_step": 542232, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0982284545898438, "global_step": 542233, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.074413537979126, "global_step": 542234, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0411267280578613, "global_step": 542235, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9766335487365723, "global_step": 542236, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.048992395401001, "global_step": 542237, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0199620723724365, "global_step": 542238, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.005500078201294, "global_step": 542239, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9845829010009766, "global_step": 542240, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.022998809814453, "global_step": 542241, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9723938703536987, "global_step": 542242, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.098551034927368, "global_step": 542243, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0253567695617676, "global_step": 542244, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9551986455917358, "global_step": 542245, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9823843240737915, "global_step": 542246, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.135566234588623, "global_step": 542247, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.948014259338379, "global_step": 542248, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.143134593963623, "global_step": 542249, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9431231021881104, "global_step": 542250, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.984044075012207, "global_step": 542251, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.036672353744507, "global_step": 542252, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0483968257904053, "global_step": 542253, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9920357465744019, "global_step": 542254, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.988051176071167, "global_step": 542255, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.996003270149231, "global_step": 542256, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0466554164886475, "global_step": 542257, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0284039974212646, "global_step": 542258, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.095316171646118, "global_step": 542259, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0030503273010254, "global_step": 542260, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0165960788726807, "global_step": 542261, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9393864870071411, "global_step": 542262, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0452659130096436, "global_step": 542263, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.084650993347168, "global_step": 542264, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0244126319885254, "global_step": 542265, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0417277812957764, "global_step": 542266, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.009734869003296, "global_step": 542267, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1558849811553955, "global_step": 542268, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0810811519622803, "global_step": 542269, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9715497493743896, "global_step": 542270, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9833760261535645, "global_step": 542271, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.952507495880127, "global_step": 542272, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.08298921585083, "global_step": 542273, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9971541166305542, "global_step": 542274, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0532729625701904, "global_step": 542275, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.008084535598755, "global_step": 542276, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9362348318099976, "global_step": 542277, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0063750743865967, "global_step": 542278, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.046567440032959, "global_step": 542279, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0375678539276123, "global_step": 542280, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.05507230758667, "global_step": 542281, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1091604232788086, "global_step": 542282, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.072046995162964, "global_step": 542283, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9986735582351685, "global_step": 542284, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1184279918670654, "global_step": 542285, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9385356903076172, "global_step": 542286, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9888572692871094, "global_step": 542287, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0356552600860596, "global_step": 542288, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.028627395629883, "global_step": 542289, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9416189193725586, "global_step": 542290, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.084481716156006, "global_step": 542291, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1583592891693115, "global_step": 542292, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0875449180603027, "global_step": 542293, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.037470579147339, "global_step": 542294, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0588486194610596, "global_step": 542295, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0046498775482178, "global_step": 542296, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.055093288421631, "global_step": 542297, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9535125494003296, "global_step": 542298, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.073155403137207, "global_step": 542299, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.008286237716675, "global_step": 542300, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.116586685180664, "global_step": 542301, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0228466987609863, "global_step": 542302, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.090867519378662, "global_step": 542303, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.010227680206299, "global_step": 542304, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.000124931335449, "global_step": 542305, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0443310737609863, "global_step": 542306, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0587570667266846, "global_step": 542307, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0359995365142822, "global_step": 542308, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.041437864303589, "global_step": 542309, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9539350271224976, "global_step": 542310, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.980944275856018, "global_step": 542311, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9564108848571777, "global_step": 542312, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.004383087158203, "global_step": 542313, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0584757328033447, "global_step": 542314, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1358935832977295, "global_step": 542315, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0536773204803467, "global_step": 542316, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9732818603515625, "global_step": 542317, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0050320625305176, "global_step": 542318, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.054330348968506, "global_step": 542319, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9712824821472168, "global_step": 542320, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.039402484893799, "global_step": 542321, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.091439962387085, "global_step": 542322, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.111785650253296, "global_step": 542323, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.111037492752075, "global_step": 542324, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.028238296508789, "global_step": 542325, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0613977909088135, "global_step": 542326, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9569566249847412, "global_step": 542327, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9991120100021362, "global_step": 542328, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.01167368888855, "global_step": 542329, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.04423189163208, "global_step": 542330, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1145615577697754, "global_step": 542331, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0639617443084717, "global_step": 542332, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.122917890548706, "global_step": 542333, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0222878456115723, "global_step": 542334, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.041348457336426, "global_step": 542335, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.017690658569336, "global_step": 542336, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.105347156524658, "global_step": 542337, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9941495656967163, "global_step": 542338, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.056256055831909, "global_step": 542339, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.03403902053833, "global_step": 542340, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0724387168884277, "global_step": 542341, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.071847438812256, "global_step": 542342, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.980730652809143, "global_step": 542343, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9866306781768799, "global_step": 542344, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.01434326171875, "global_step": 542345, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0493202209472656, "global_step": 542346, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9983303546905518, "global_step": 542347, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.113224506378174, "global_step": 542348, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0333304405212402, "global_step": 542349, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1076579093933105, "global_step": 542350, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9555509090423584, "global_step": 542351, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.006162405014038, "global_step": 542352, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0290398597717285, "global_step": 542353, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1000757217407227, "global_step": 542354, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0217933654785156, "global_step": 542355, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.041980028152466, "global_step": 542356, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9875562191009521, "global_step": 542357, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9895484447479248, "global_step": 542358, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0232977867126465, "global_step": 542359, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.06588077545166, "global_step": 542360, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0998008251190186, "global_step": 542361, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.009138584136963, "global_step": 542362, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9743413925170898, "global_step": 542363, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1407742500305176, "global_step": 542364, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0221307277679443, "global_step": 542365, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.065056562423706, "global_step": 542366, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0935170650482178, "global_step": 542367, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1091434955596924, "global_step": 542368, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.050818681716919, "global_step": 542369, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.040818691253662, "global_step": 542370, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0137414932250977, "global_step": 542371, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9139785766601562, "global_step": 542372, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.997951626777649, "global_step": 542373, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9894789457321167, "global_step": 542374, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9916346073150635, "global_step": 542375, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.020876884460449, "global_step": 542376, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1234617233276367, "global_step": 542377, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0524771213531494, "global_step": 542378, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1043753623962402, "global_step": 542379, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9737967252731323, "global_step": 542380, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0178751945495605, "global_step": 542381, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0615875720977783, "global_step": 542382, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.040600299835205, "global_step": 542383, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0765132904052734, "global_step": 542384, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0193557739257812, "global_step": 542385, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.058300018310547, "global_step": 542386, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.029317855834961, "global_step": 542387, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.014986038208008, "global_step": 542388, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0304365158081055, "global_step": 542389, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0565404891967773, "global_step": 542390, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.133084774017334, "global_step": 542391, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.076753616333008, "global_step": 542392, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0268383026123047, "global_step": 542393, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.147817850112915, "global_step": 542394, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.068629026412964, "global_step": 542395, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0709919929504395, "global_step": 542396, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.09051775932312, "global_step": 542397, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.069042444229126, "global_step": 542398, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.069049119949341, "global_step": 542399, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.985237956047058, "global_step": 542400, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0296711921691895, "global_step": 542401, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1367573738098145, "global_step": 542402, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9914169311523438, "global_step": 542403, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9983601570129395, "global_step": 542404, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9831138849258423, "global_step": 542405, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0598928928375244, "global_step": 542406, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0307722091674805, "global_step": 542407, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.027000904083252, "global_step": 542408, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.982565999031067, "global_step": 542409, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0469558238983154, "global_step": 542410, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0323803424835205, "global_step": 542411, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0169119834899902, "global_step": 542412, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.088733434677124, "global_step": 542413, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9701327085494995, "global_step": 542414, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.043851137161255, "global_step": 542415, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.007190704345703, "global_step": 542416, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0122792720794678, "global_step": 542417, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0015053749084473, "global_step": 542418, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.081693410873413, "global_step": 542419, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.011411428451538, "global_step": 542420, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.030709743499756, "global_step": 542421, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0883231163024902, "global_step": 542422, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9957046508789062, "global_step": 542423, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0431525707244873, "global_step": 542424, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0341172218322754, "global_step": 542425, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0936551094055176, "global_step": 542426, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.025805711746216, "global_step": 542427, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9976729154586792, "global_step": 542428, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9896286725997925, "global_step": 542429, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9844046831130981, "global_step": 542430, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0033116340637207, "global_step": 542431, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1602540016174316, "global_step": 542432, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0798089504241943, "global_step": 542433, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.019002914428711, "global_step": 542434, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9454389810562134, "global_step": 542435, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0232365131378174, "global_step": 542436, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0362813472747803, "global_step": 542437, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0340757369995117, "global_step": 542438, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9938578605651855, "global_step": 542439, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.931411623954773, "global_step": 542440, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0217082500457764, "global_step": 542441, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9409064054489136, "global_step": 542442, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0196852684020996, "global_step": 542443, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0139706134796143, "global_step": 542444, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0282845497131348, "global_step": 542445, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0723752975463867, "global_step": 542446, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0093297958374023, "global_step": 542447, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0717430114746094, "global_step": 542448, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.095559597015381, "global_step": 542449, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0207130908966064, "global_step": 542450, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.106008291244507, "global_step": 542451, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.020084857940674, "global_step": 542452, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9956351518630981, "global_step": 542453, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0019383430480957, "global_step": 542454, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.025195837020874, "global_step": 542455, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.05938982963562, "global_step": 542456, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.095052719116211, "global_step": 542457, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0177600383758545, "global_step": 542458, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9823845624923706, "global_step": 542459, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9563729763031006, "global_step": 542460, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0793769359588623, "global_step": 542461, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0661489963531494, "global_step": 542462, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0375399589538574, "global_step": 542463, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9868441820144653, "global_step": 542464, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0942575931549072, "global_step": 542465, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0086872577667236, "global_step": 542466, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.044556140899658, "global_step": 542467, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.986240267753601, "global_step": 542468, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.034559726715088, "global_step": 542469, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0740885734558105, "global_step": 542470, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9843103885650635, "global_step": 542471, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.986727237701416, "global_step": 542472, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0398736000061035, "global_step": 542473, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9873974323272705, "global_step": 542474, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0069687366485596, "global_step": 542475, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0997378826141357, "global_step": 542476, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.038280487060547, "global_step": 542477, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0378596782684326, "global_step": 542478, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9947082996368408, "global_step": 542479, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1247997283935547, "global_step": 542480, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0032217502593994, "global_step": 542481, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.046306610107422, "global_step": 542482, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0142364501953125, "global_step": 542483, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.99785315990448, "global_step": 542484, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9342528581619263, "global_step": 542485, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9677271842956543, "global_step": 542486, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.046602487564087, "global_step": 542487, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9711017608642578, "global_step": 542488, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.012951135635376, "global_step": 542489, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9916667938232422, "global_step": 542490, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9862189292907715, "global_step": 542491, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.144859552383423, "global_step": 542492, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0704925060272217, "global_step": 542493, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0691237449645996, "global_step": 542494, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0856149196624756, "global_step": 542495, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9783568382263184, "global_step": 542496, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.068396806716919, "global_step": 542497, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0320491790771484, "global_step": 542498, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9792723655700684, "global_step": 542499, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0726215839385986, "global_step": 542500, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0118567943573, "global_step": 542501, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0170364379882812, "global_step": 542502, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.069164752960205, "global_step": 542503, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.016038656234741, "global_step": 542504, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0552263259887695, "global_step": 542505, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.021632194519043, "global_step": 542506, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.018845796585083, "global_step": 542507, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.100393295288086, "global_step": 542508, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0634171962738037, "global_step": 542509, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.06697416305542, "global_step": 542510, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0234904289245605, "global_step": 542511, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0642082691192627, "global_step": 542512, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.998175024986267, "global_step": 542513, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0322225093841553, "global_step": 542514, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0349864959716797, "global_step": 542515, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1542396545410156, "global_step": 542516, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0847361087799072, "global_step": 542517, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9805189371109009, "global_step": 542518, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.996741771697998, "global_step": 542519, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0165202617645264, "global_step": 542520, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.035832405090332, "global_step": 542521, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1097240447998047, "global_step": 542522, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.082282304763794, "global_step": 542523, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9728986024856567, "global_step": 542524, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0406711101531982, "global_step": 542525, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0434329509735107, "global_step": 542526, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.119800567626953, "global_step": 542527, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0505919456481934, "global_step": 542528, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9228068590164185, "global_step": 542529, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.01200795173645, "global_step": 542530, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0104079246520996, "global_step": 542531, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.136711597442627, "global_step": 542532, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.167574405670166, "global_step": 542533, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.090841054916382, "global_step": 542534, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0570056438446045, "global_step": 542535, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0678067207336426, "global_step": 542536, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0609331130981445, "global_step": 542537, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.039337635040283, "global_step": 542538, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0045347213745117, "global_step": 542539, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9723083972930908, "global_step": 542540, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0894832611083984, "global_step": 542541, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0294740200042725, "global_step": 542542, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1508235931396484, "global_step": 542543, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0961320400238037, "global_step": 542544, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0620973110198975, "global_step": 542545, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0430097579956055, "global_step": 542546, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.15924334526062, "global_step": 542547, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0438637733459473, "global_step": 542548, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9689220190048218, "global_step": 542549, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.13967227935791, "global_step": 542550, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9942259788513184, "global_step": 542551, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.076331377029419, "global_step": 542552, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0016298294067383, "global_step": 542553, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.059563636779785, "global_step": 542554, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0821194648742676, "global_step": 542555, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.933759331703186, "global_step": 542556, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.076470375061035, "global_step": 542557, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0267446041107178, "global_step": 542558, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9840294122695923, "global_step": 542559, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.086634397506714, "global_step": 542560, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.045698404312134, "global_step": 542561, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.073903799057007, "global_step": 542562, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0434648990631104, "global_step": 542563, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0954506397247314, "global_step": 542564, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.919532060623169, "global_step": 542565, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.102290630340576, "global_step": 542566, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0238702297210693, "global_step": 542567, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.098156452178955, "global_step": 542568, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0635955333709717, "global_step": 542569, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9945082664489746, "global_step": 542570, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.01001238822937, "global_step": 542571, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0768086910247803, "global_step": 542572, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1140501499176025, "global_step": 542573, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9458191394805908, "global_step": 542574, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0252137184143066, "global_step": 542575, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0391271114349365, "global_step": 542576, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9990174770355225, "global_step": 542577, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9999912977218628, "global_step": 542578, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.066478729248047, "global_step": 542579, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.982541799545288, "global_step": 542580, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1145479679107666, "global_step": 542581, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.019395589828491, "global_step": 542582, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.981339931488037, "global_step": 542583, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9832204580307007, "global_step": 542584, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.14601993560791, "global_step": 542585, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9639272689819336, "global_step": 542586, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0421392917633057, "global_step": 542587, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.017335891723633, "global_step": 542588, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.025710105895996, "global_step": 542589, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.025975227355957, "global_step": 542590, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9537073373794556, "global_step": 542591, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.97110915184021, "global_step": 542592, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9985657930374146, "global_step": 542593, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.064892292022705, "global_step": 542594, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0345282554626465, "global_step": 542595, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0148770809173584, "global_step": 542596, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.000965118408203, "global_step": 542597, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0904786586761475, "global_step": 542598, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.052131414413452, "global_step": 542599, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0374038219451904, "global_step": 542600, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9771130084991455, "global_step": 542601, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9772684574127197, "global_step": 542602, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0651586055755615, "global_step": 542603, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0128302574157715, "global_step": 542604, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9155869483947754, "global_step": 542605, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.035705804824829, "global_step": 542606, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.099210500717163, "global_step": 542607, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.962761640548706, "global_step": 542608, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9178324937820435, "global_step": 542609, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9842416048049927, "global_step": 542610, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9533984661102295, "global_step": 542611, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9670430421829224, "global_step": 542612, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0172111988067627, "global_step": 542613, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.059680938720703, "global_step": 542614, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.049870014190674, "global_step": 542615, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.073760747909546, "global_step": 542616, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0513956546783447, "global_step": 542617, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.956453800201416, "global_step": 542618, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9586728811264038, "global_step": 542619, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9603989124298096, "global_step": 542620, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9848765134811401, "global_step": 542621, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1298446655273438, "global_step": 542622, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0021557807922363, "global_step": 542623, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9652583599090576, "global_step": 542624, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1434500217437744, "global_step": 542625, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0708565711975098, "global_step": 542626, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.026758909225464, "global_step": 542627, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9960317611694336, "global_step": 542628, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.08189058303833, "global_step": 542629, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0496950149536133, "global_step": 542630, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.070039987564087, "global_step": 542631, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1101629734039307, "global_step": 542632, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0105395317077637, "global_step": 542633, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9556591510772705, "global_step": 542634, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0986998081207275, "global_step": 542635, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0111029148101807, "global_step": 542636, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0761687755584717, "global_step": 542637, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0394747257232666, "global_step": 542638, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.113703966140747, "global_step": 542639, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9528108835220337, "global_step": 542640, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.005634069442749, "global_step": 542641, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9586193561553955, "global_step": 542642, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.055410861968994, "global_step": 542643, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0997726917266846, "global_step": 542644, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1542608737945557, "global_step": 542645, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.058614730834961, "global_step": 542646, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0132529735565186, "global_step": 542647, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0622832775115967, "global_step": 542648, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.061234474182129, "global_step": 542649, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.105462074279785, "global_step": 542650, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9731093645095825, "global_step": 542651, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0920114517211914, "global_step": 542652, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.134387254714966, "global_step": 542653, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0367543697357178, "global_step": 542654, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9192110300064087, "global_step": 542655, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0840086936950684, "global_step": 542656, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.06081485748291, "global_step": 542657, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0258703231811523, "global_step": 542658, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0711824893951416, "global_step": 542659, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0609591007232666, "global_step": 542660, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0414156913757324, "global_step": 542661, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.916222333908081, "global_step": 542662, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9935204982757568, "global_step": 542663, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0478217601776123, "global_step": 542664, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1205148696899414, "global_step": 542665, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0272533893585205, "global_step": 542666, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0293939113616943, "global_step": 542667, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.072012186050415, "global_step": 542668, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0517923831939697, "global_step": 542669, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9791778326034546, "global_step": 542670, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9562809467315674, "global_step": 542671, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9907135963439941, "global_step": 542672, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.006098508834839, "global_step": 542673, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.052464008331299, "global_step": 542674, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0325117111206055, "global_step": 542675, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9395314455032349, "global_step": 542676, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9774892330169678, "global_step": 542677, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0980873107910156, "global_step": 542678, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.086674213409424, "global_step": 542679, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.185817003250122, "global_step": 542680, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.032122850418091, "global_step": 542681, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0594100952148438, "global_step": 542682, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.12841796875, "global_step": 542683, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.12359356880188, "global_step": 542684, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.056245803833008, "global_step": 542685, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.033592700958252, "global_step": 542686, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0492022037506104, "global_step": 542687, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.112001657485962, "global_step": 542688, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.116356134414673, "global_step": 542689, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.020188570022583, "global_step": 542690, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0682640075683594, "global_step": 542691, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.097612142562866, "global_step": 542692, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0500597953796387, "global_step": 542693, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1136114597320557, "global_step": 542694, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0612378120422363, "global_step": 542695, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.011310577392578, "global_step": 542696, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1101365089416504, "global_step": 542697, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0610291957855225, "global_step": 542698, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0633468627929688, "global_step": 542699, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0573511123657227, "global_step": 542700, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9732005596160889, "global_step": 542701, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0137887001037598, "global_step": 542702, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0278663635253906, "global_step": 542703, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9931334257125854, "global_step": 542704, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9572460651397705, "global_step": 542705, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0301828384399414, "global_step": 542706, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0465097427368164, "global_step": 542707, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.004030227661133, "global_step": 542708, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.095653533935547, "global_step": 542709, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9983341693878174, "global_step": 542710, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.083631992340088, "global_step": 542711, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.971147060394287, "global_step": 542712, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0671472549438477, "global_step": 542713, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0303890705108643, "global_step": 542714, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9838206768035889, "global_step": 542715, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9338328838348389, "global_step": 542716, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0282411575317383, "global_step": 542717, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.00803542137146, "global_step": 542718, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0795087814331055, "global_step": 542719, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.127549886703491, "global_step": 542720, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.019172191619873, "global_step": 542721, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0158419609069824, "global_step": 542722, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0344045162200928, "global_step": 542723, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.031972885131836, "global_step": 542724, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0185179710388184, "global_step": 542725, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9879591464996338, "global_step": 542726, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.038748025894165, "global_step": 542727, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.986081838607788, "global_step": 542728, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.025496006011963, "global_step": 542729, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1224489212036133, "global_step": 542730, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9449632167816162, "global_step": 542731, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9987763166427612, "global_step": 542732, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.071523904800415, "global_step": 542733, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0186915397644043, "global_step": 542734, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.152921676635742, "global_step": 542735, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9870208501815796, "global_step": 542736, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0022225379943848, "global_step": 542737, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1410627365112305, "global_step": 542738, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.055946111679077, "global_step": 542739, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.028452157974243, "global_step": 542740, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.078356981277466, "global_step": 542741, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1282572746276855, "global_step": 542742, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.027545928955078, "global_step": 542743, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0762014389038086, "global_step": 542744, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0671725273132324, "global_step": 542745, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.070194721221924, "global_step": 542746, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0740315914154053, "global_step": 542747, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0158112049102783, "global_step": 542748, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.105637788772583, "global_step": 542749, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0098330974578857, "global_step": 542750, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.974430799484253, "global_step": 542751, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9844200611114502, "global_step": 542752, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.088341474533081, "global_step": 542753, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9461467266082764, "global_step": 542754, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9918750524520874, "global_step": 542755, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0506484508514404, "global_step": 542756, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0612144470214844, "global_step": 542757, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0420000553131104, "global_step": 542758, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.03690505027771, "global_step": 542759, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.015775442123413, "global_step": 542760, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.022325038909912, "global_step": 542761, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9880170822143555, "global_step": 542762, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0297722816467285, "global_step": 542763, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.018989086151123, "global_step": 542764, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.010812282562256, "global_step": 542765, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1406753063201904, "global_step": 542766, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0705699920654297, "global_step": 542767, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.0510847568511963, "global_step": 542768, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.058520793914795, "global_step": 542769, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.019887924194336, "global_step": 542770, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.1418144702911377, "global_step": 542771, "epoch": 909, "lr": 5e-05}
{"train_loss": 2.034078598022461, "global_step": 542772, "epoch": 909, "lr": 5e-05}
{"train_loss": 1.9897996187210083, "global_step": 542773, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.005951404571533, "global_step": 542774, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9864472150802612, "global_step": 542775, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.004188060760498, "global_step": 542776, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0565574169158936, "global_step": 542777, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9764258861541748, "global_step": 542778, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0114386081695557, "global_step": 542779, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1054093837738037, "global_step": 542780, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.98795747756958, "global_step": 542781, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9851486682891846, "global_step": 542782, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.96678626537323, "global_step": 542783, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9967100620269775, "global_step": 542784, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.022728443145752, "global_step": 542785, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.029125452041626, "global_step": 542786, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0538134574890137, "global_step": 542787, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9905128479003906, "global_step": 542788, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0190963745117188, "global_step": 542789, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.003427743911743, "global_step": 542790, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0775742530822754, "global_step": 542791, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.034332752227783, "global_step": 542792, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9760844707489014, "global_step": 542793, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9821902513504028, "global_step": 542794, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9943698644638062, "global_step": 542795, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9770050048828125, "global_step": 542796, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0137691497802734, "global_step": 542797, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9975459575653076, "global_step": 542798, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0451645851135254, "global_step": 542799, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0175843238830566, "global_step": 542800, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9801090955734253, "global_step": 542801, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9871647357940674, "global_step": 542802, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.974290132522583, "global_step": 542803, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.002260208129883, "global_step": 542804, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.031231641769409, "global_step": 542805, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0624914169311523, "global_step": 542806, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.98824143409729, "global_step": 542807, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0486361980438232, "global_step": 542808, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0086958408355713, "global_step": 542809, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0692830085754395, "global_step": 542810, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9796749353408813, "global_step": 542811, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9852226972579956, "global_step": 542812, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0826823711395264, "global_step": 542813, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9968360662460327, "global_step": 542814, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0882463455200195, "global_step": 542815, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9978995323181152, "global_step": 542816, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9968018531799316, "global_step": 542817, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9829822778701782, "global_step": 542818, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0025970935821533, "global_step": 542819, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9726500511169434, "global_step": 542820, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9288301467895508, "global_step": 542821, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.092344045639038, "global_step": 542822, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.089186191558838, "global_step": 542823, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0851616859436035, "global_step": 542824, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0013017654418945, "global_step": 542825, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0305964946746826, "global_step": 542826, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0578293800354004, "global_step": 542827, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.029803514480591, "global_step": 542828, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.994937777519226, "global_step": 542829, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0749568939208984, "global_step": 542830, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0534496307373047, "global_step": 542831, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.031050205230713, "global_step": 542832, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0397982597351074, "global_step": 542833, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9488365650177002, "global_step": 542834, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.086467742919922, "global_step": 542835, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0513625144958496, "global_step": 542836, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.989368200302124, "global_step": 542837, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9973362684249878, "global_step": 542838, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.024480104446411, "global_step": 542839, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.997008204460144, "global_step": 542840, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0686967372894287, "global_step": 542841, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.024172306060791, "global_step": 542842, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0579495429992676, "global_step": 542843, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0519256591796875, "global_step": 542844, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.106839656829834, "global_step": 542845, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.942542314529419, "global_step": 542846, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9542038440704346, "global_step": 542847, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.074042320251465, "global_step": 542848, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0068256855010986, "global_step": 542849, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9890543222427368, "global_step": 542850, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0082364082336426, "global_step": 542851, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0501723289489746, "global_step": 542852, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9851746559143066, "global_step": 542853, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.971191644668579, "global_step": 542854, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.000220537185669, "global_step": 542855, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0654847621917725, "global_step": 542856, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.057705879211426, "global_step": 542857, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0363223552703857, "global_step": 542858, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.915960431098938, "global_step": 542859, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0299243927001953, "global_step": 542860, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.059574842453003, "global_step": 542861, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.05588436126709, "global_step": 542862, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0701982975006104, "global_step": 542863, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9312481880187988, "global_step": 542864, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.039074659347534, "global_step": 542865, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9551913738250732, "global_step": 542866, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0607008934020996, "global_step": 542867, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0681707859039307, "global_step": 542868, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0202653408050537, "global_step": 542869, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.10781192779541, "global_step": 542870, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0444869995117188, "global_step": 542871, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9999704360961914, "global_step": 542872, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1094303131103516, "global_step": 542873, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9962238073349, "global_step": 542874, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0346057415008545, "global_step": 542875, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9993577003479004, "global_step": 542876, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9750913381576538, "global_step": 542877, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.938225507736206, "global_step": 542878, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.00998592376709, "global_step": 542879, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0787627696990967, "global_step": 542880, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.936502456665039, "global_step": 542881, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9494335651397705, "global_step": 542882, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1319704055786133, "global_step": 542883, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9871217012405396, "global_step": 542884, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0983176231384277, "global_step": 542885, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.114271879196167, "global_step": 542886, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.095241069793701, "global_step": 542887, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0454537868499756, "global_step": 542888, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0436649322509766, "global_step": 542889, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.047362804412842, "global_step": 542890, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0730204582214355, "global_step": 542891, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0212082862854004, "global_step": 542892, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.082573413848877, "global_step": 542893, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9701869487762451, "global_step": 542894, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.080681800842285, "global_step": 542895, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1559910774230957, "global_step": 542896, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9588546752929688, "global_step": 542897, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0359504222869873, "global_step": 542898, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.096747636795044, "global_step": 542899, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9801162481307983, "global_step": 542900, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.039329767227173, "global_step": 542901, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.010892629623413, "global_step": 542902, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.04818058013916, "global_step": 542903, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.009911060333252, "global_step": 542904, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0952625274658203, "global_step": 542905, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0435802936553955, "global_step": 542906, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0256922245025635, "global_step": 542907, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.078068256378174, "global_step": 542908, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9944959878921509, "global_step": 542909, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.8821955919265747, "global_step": 542910, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.016295909881592, "global_step": 542911, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.976300835609436, "global_step": 542912, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0669052600860596, "global_step": 542913, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0298259258270264, "global_step": 542914, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.083181619644165, "global_step": 542915, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.022383213043213, "global_step": 542916, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1161270141601562, "global_step": 542917, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0076467990875244, "global_step": 542918, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.014735221862793, "global_step": 542919, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.033503770828247, "global_step": 542920, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.064983367919922, "global_step": 542921, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1250479221343994, "global_step": 542922, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9837000370025635, "global_step": 542923, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.121199607849121, "global_step": 542924, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9936362504959106, "global_step": 542925, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.043464422225952, "global_step": 542926, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.997191071510315, "global_step": 542927, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.996570110321045, "global_step": 542928, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.048125743865967, "global_step": 542929, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.062318801879883, "global_step": 542930, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.115870237350464, "global_step": 542931, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0678341388702393, "global_step": 542932, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.114168882369995, "global_step": 542933, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.057544708251953, "global_step": 542934, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0354971885681152, "global_step": 542935, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.032585382461548, "global_step": 542936, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9640624523162842, "global_step": 542937, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.103858232498169, "global_step": 542938, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.019625425338745, "global_step": 542939, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.04995059967041, "global_step": 542940, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.120687961578369, "global_step": 542941, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0285418033599854, "global_step": 542942, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0408976078033447, "global_step": 542943, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.019418478012085, "global_step": 542944, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.111945629119873, "global_step": 542945, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0048465728759766, "global_step": 542946, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0373709201812744, "global_step": 542947, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9887672662734985, "global_step": 542948, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0395874977111816, "global_step": 542949, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0279290676116943, "global_step": 542950, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0614848136901855, "global_step": 542951, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9391454458236694, "global_step": 542952, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1097054481506348, "global_step": 542953, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0243375301361084, "global_step": 542954, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.011634349822998, "global_step": 542955, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9322903156280518, "global_step": 542956, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0204830169677734, "global_step": 542957, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0398499965667725, "global_step": 542958, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.026954412460327, "global_step": 542959, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.009464979171753, "global_step": 542960, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9954179525375366, "global_step": 542961, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.007242441177368, "global_step": 542962, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9727391004562378, "global_step": 542963, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0655710697174072, "global_step": 542964, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0661234855651855, "global_step": 542965, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9658232927322388, "global_step": 542966, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.02463436126709, "global_step": 542967, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0812814235687256, "global_step": 542968, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0268893241882324, "global_step": 542969, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9489269256591797, "global_step": 542970, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0134899616241455, "global_step": 542971, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.054671049118042, "global_step": 542972, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0534884929656982, "global_step": 542973, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0052552223205566, "global_step": 542974, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.015430450439453, "global_step": 542975, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0463497638702393, "global_step": 542976, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0554614067077637, "global_step": 542977, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.085986852645874, "global_step": 542978, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.059762716293335, "global_step": 542979, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.025817394256592, "global_step": 542980, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.102581024169922, "global_step": 542981, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0941176414489746, "global_step": 542982, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.01297926902771, "global_step": 542983, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.063364028930664, "global_step": 542984, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9864264726638794, "global_step": 542985, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.016082286834717, "global_step": 542986, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9562463760375977, "global_step": 542987, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.038301706314087, "global_step": 542988, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.059947967529297, "global_step": 542989, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0749993324279785, "global_step": 542990, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.069246530532837, "global_step": 542991, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0068953037261963, "global_step": 542992, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0268795490264893, "global_step": 542993, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.080190896987915, "global_step": 542994, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0001206398010254, "global_step": 542995, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.032620429992676, "global_step": 542996, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.058702230453491, "global_step": 542997, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9469382762908936, "global_step": 542998, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1007256507873535, "global_step": 542999, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.07743763923645, "global_step": 543000, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9345158338546753, "global_step": 543001, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0032153129577637, "global_step": 543002, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.03560733795166, "global_step": 543003, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0176093578338623, "global_step": 543004, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.083474636077881, "global_step": 543005, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.012465238571167, "global_step": 543006, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.043605089187622, "global_step": 543007, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0461089611053467, "global_step": 543008, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0523624420166016, "global_step": 543009, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0303285121917725, "global_step": 543010, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.981151819229126, "global_step": 543011, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9930499792099, "global_step": 543012, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0992095470428467, "global_step": 543013, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.025038242340088, "global_step": 543014, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0413320064544678, "global_step": 543015, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1122162342071533, "global_step": 543016, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9972280263900757, "global_step": 543017, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0479626655578613, "global_step": 543018, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.078892469406128, "global_step": 543019, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0418806076049805, "global_step": 543020, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9765782356262207, "global_step": 543021, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9693498611450195, "global_step": 543022, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0622148513793945, "global_step": 543023, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.99124014377594, "global_step": 543024, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0152313709259033, "global_step": 543025, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.072723388671875, "global_step": 543026, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.012967348098755, "global_step": 543027, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0816073417663574, "global_step": 543028, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0260860919952393, "global_step": 543029, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.055203676223755, "global_step": 543030, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0488462448120117, "global_step": 543031, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9964995384216309, "global_step": 543032, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.975723385810852, "global_step": 543033, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0043389797210693, "global_step": 543034, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.095642328262329, "global_step": 543035, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.005861520767212, "global_step": 543036, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.992349624633789, "global_step": 543037, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0742573738098145, "global_step": 543038, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0692760944366455, "global_step": 543039, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.014601230621338, "global_step": 543040, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1135783195495605, "global_step": 543041, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9818751811981201, "global_step": 543042, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.031928300857544, "global_step": 543043, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.8688100576400757, "global_step": 543044, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.055914878845215, "global_step": 543045, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9433742761611938, "global_step": 543046, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9635199308395386, "global_step": 543047, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9784587621688843, "global_step": 543048, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9898121356964111, "global_step": 543049, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9788838624954224, "global_step": 543050, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0049121379852295, "global_step": 543051, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.112025022506714, "global_step": 543052, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0426220893859863, "global_step": 543053, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0498785972595215, "global_step": 543054, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0108766555786133, "global_step": 543055, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.059241771697998, "global_step": 543056, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0320546627044678, "global_step": 543057, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.016329765319824, "global_step": 543058, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0403330326080322, "global_step": 543059, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9764009714126587, "global_step": 543060, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.098468542098999, "global_step": 543061, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1017813682556152, "global_step": 543062, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9816372394561768, "global_step": 543063, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.038386106491089, "global_step": 543064, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0670831203460693, "global_step": 543065, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.051652669906616, "global_step": 543066, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.081998825073242, "global_step": 543067, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0370376110076904, "global_step": 543068, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.999511480331421, "global_step": 543069, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9947296380996704, "global_step": 543070, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1105828285217285, "global_step": 543071, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9842886924743652, "global_step": 543072, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9814813137054443, "global_step": 543073, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0032947063446045, "global_step": 543074, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9521241188049316, "global_step": 543075, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9676868915557861, "global_step": 543076, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0581719875335693, "global_step": 543077, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.062755823135376, "global_step": 543078, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9669396877288818, "global_step": 543079, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.06136155128479, "global_step": 543080, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0694751739501953, "global_step": 543081, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0280935764312744, "global_step": 543082, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9828178882598877, "global_step": 543083, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0941054821014404, "global_step": 543084, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.034234046936035, "global_step": 543085, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.067762851715088, "global_step": 543086, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.07296085357666, "global_step": 543087, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.038714647293091, "global_step": 543088, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0096023082733154, "global_step": 543089, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9728940725326538, "global_step": 543090, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0676567554473877, "global_step": 543091, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0183262825012207, "global_step": 543092, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9916448593139648, "global_step": 543093, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.107891082763672, "global_step": 543094, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9909332990646362, "global_step": 543095, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0055601596832275, "global_step": 543096, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0183258056640625, "global_step": 543097, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0711004734039307, "global_step": 543098, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9890962839126587, "global_step": 543099, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9863924980163574, "global_step": 543100, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9152898788452148, "global_step": 543101, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0694665908813477, "global_step": 543102, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9617459774017334, "global_step": 543103, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0706088542938232, "global_step": 543104, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0396664142608643, "global_step": 543105, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0305392742156982, "global_step": 543106, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9657964706420898, "global_step": 543107, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.999022364616394, "global_step": 543108, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9836180210113525, "global_step": 543109, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.986339807510376, "global_step": 543110, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9751273393630981, "global_step": 543111, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0726511478424072, "global_step": 543112, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.953317403793335, "global_step": 543113, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0198616981506348, "global_step": 543114, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1094887256622314, "global_step": 543115, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.025648593902588, "global_step": 543116, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.092503070831299, "global_step": 543117, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0599048137664795, "global_step": 543118, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0474648475646973, "global_step": 543119, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0431878566741943, "global_step": 543120, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0430424213409424, "global_step": 543121, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.029803514480591, "global_step": 543122, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0638322830200195, "global_step": 543123, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.97374427318573, "global_step": 543124, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0238592624664307, "global_step": 543125, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9928747415542603, "global_step": 543126, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.072920083999634, "global_step": 543127, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0305593013763428, "global_step": 543128, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9524890184402466, "global_step": 543129, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1000185012817383, "global_step": 543130, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0610270500183105, "global_step": 543131, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.041836738586426, "global_step": 543132, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9634487628936768, "global_step": 543133, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1123125553131104, "global_step": 543134, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1020922660827637, "global_step": 543135, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0484983921051025, "global_step": 543136, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1731925010681152, "global_step": 543137, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.099459648132324, "global_step": 543138, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0017006397247314, "global_step": 543139, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.111692190170288, "global_step": 543140, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0720291137695312, "global_step": 543141, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.017178535461426, "global_step": 543142, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9951859712600708, "global_step": 543143, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0216493606567383, "global_step": 543144, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0323679447174072, "global_step": 543145, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.029780626296997, "global_step": 543146, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0138676166534424, "global_step": 543147, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1031153202056885, "global_step": 543148, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.058640480041504, "global_step": 543149, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.072286605834961, "global_step": 543150, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9933348894119263, "global_step": 543151, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.074143171310425, "global_step": 543152, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1140270233154297, "global_step": 543153, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.025237560272217, "global_step": 543154, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9661970138549805, "global_step": 543155, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9934375286102295, "global_step": 543156, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0438785552978516, "global_step": 543157, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9558777809143066, "global_step": 543158, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.07041072845459, "global_step": 543159, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9959254264831543, "global_step": 543160, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9975078105926514, "global_step": 543161, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0550358295440674, "global_step": 543162, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.8989654779434204, "global_step": 543163, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0502631664276123, "global_step": 543164, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0571115016937256, "global_step": 543165, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.02154541015625, "global_step": 543166, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0503077507019043, "global_step": 543167, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1181414127349854, "global_step": 543168, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9500757455825806, "global_step": 543169, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.034024477005005, "global_step": 543170, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.063354015350342, "global_step": 543171, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9114937782287598, "global_step": 543172, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0173041820526123, "global_step": 543173, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.076932907104492, "global_step": 543174, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1596882343292236, "global_step": 543175, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.098151922225952, "global_step": 543176, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.07914137840271, "global_step": 543177, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.012873888015747, "global_step": 543178, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.082184076309204, "global_step": 543179, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9482945203781128, "global_step": 543180, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9997460842132568, "global_step": 543181, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0506179332733154, "global_step": 543182, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0120315551757812, "global_step": 543183, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0284571647644043, "global_step": 543184, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0817906856536865, "global_step": 543185, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9809329509735107, "global_step": 543186, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.021371603012085, "global_step": 543187, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9751431941986084, "global_step": 543188, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9555857181549072, "global_step": 543189, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0382235050201416, "global_step": 543190, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9687960147857666, "global_step": 543191, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0934202671051025, "global_step": 543192, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0061702728271484, "global_step": 543193, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0151400566101074, "global_step": 543194, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0533900260925293, "global_step": 543195, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.030163049697876, "global_step": 543196, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.071507215499878, "global_step": 543197, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.039076089859009, "global_step": 543198, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0077004432678223, "global_step": 543199, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.000917673110962, "global_step": 543200, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.966456651687622, "global_step": 543201, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9705368280410767, "global_step": 543202, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9718245267868042, "global_step": 543203, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0183300971984863, "global_step": 543204, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0558009147644043, "global_step": 543205, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0468904972076416, "global_step": 543206, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0692403316497803, "global_step": 543207, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9710899591445923, "global_step": 543208, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0150885581970215, "global_step": 543209, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0219578742980957, "global_step": 543210, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0825955867767334, "global_step": 543211, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.036752223968506, "global_step": 543212, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0797276496887207, "global_step": 543213, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.026364803314209, "global_step": 543214, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.034385919570923, "global_step": 543215, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1162397861480713, "global_step": 543216, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9484319686889648, "global_step": 543217, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0828604698181152, "global_step": 543218, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9773356914520264, "global_step": 543219, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9911434650421143, "global_step": 543220, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0284855365753174, "global_step": 543221, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0362331867218018, "global_step": 543222, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.062962293624878, "global_step": 543223, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0925915241241455, "global_step": 543224, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9818936586380005, "global_step": 543225, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0079057216644287, "global_step": 543226, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9655168056488037, "global_step": 543227, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.992745041847229, "global_step": 543228, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.936674952507019, "global_step": 543229, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9924300909042358, "global_step": 543230, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0769405364990234, "global_step": 543231, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9977046251296997, "global_step": 543232, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.039724111557007, "global_step": 543233, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0335428714752197, "global_step": 543234, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9736011028289795, "global_step": 543235, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.097179412841797, "global_step": 543236, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9763535261154175, "global_step": 543237, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9712920188903809, "global_step": 543238, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0585920810699463, "global_step": 543239, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.074512243270874, "global_step": 543240, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0263378620147705, "global_step": 543241, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0722475051879883, "global_step": 543242, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.100137948989868, "global_step": 543243, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9905809164047241, "global_step": 543244, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0207808017730713, "global_step": 543245, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1394290924072266, "global_step": 543246, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.026367425918579, "global_step": 543247, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1137654781341553, "global_step": 543248, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0551271438598633, "global_step": 543249, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0021708011627197, "global_step": 543250, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0667977333068848, "global_step": 543251, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.038407802581787, "global_step": 543252, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.092471122741699, "global_step": 543253, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.02653431892395, "global_step": 543254, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0751023292541504, "global_step": 543255, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0351600646972656, "global_step": 543256, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0081045627593994, "global_step": 543257, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9335949420928955, "global_step": 543258, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1056456565856934, "global_step": 543259, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9845805168151855, "global_step": 543260, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.053297281265259, "global_step": 543261, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0401062965393066, "global_step": 543262, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9959242343902588, "global_step": 543263, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.028395652770996, "global_step": 543264, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1008615493774414, "global_step": 543265, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.065778970718384, "global_step": 543266, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9891066551208496, "global_step": 543267, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9897671937942505, "global_step": 543268, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0596368312835693, "global_step": 543269, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9964981079101562, "global_step": 543270, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0801751613616943, "global_step": 543271, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0111007690429688, "global_step": 543272, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9432848691940308, "global_step": 543273, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.03315806388855, "global_step": 543274, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.919816493988037, "global_step": 543275, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9833755493164062, "global_step": 543276, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9504947662353516, "global_step": 543277, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.054656505584717, "global_step": 543278, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9557924270629883, "global_step": 543279, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0479981899261475, "global_step": 543280, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.078904390335083, "global_step": 543281, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0377256870269775, "global_step": 543282, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0152807235717773, "global_step": 543283, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9963706731796265, "global_step": 543284, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9875479936599731, "global_step": 543285, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1502251625061035, "global_step": 543286, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.095574378967285, "global_step": 543287, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0224387645721436, "global_step": 543288, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.044694662094116, "global_step": 543289, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0416336059570312, "global_step": 543290, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0091497898101807, "global_step": 543291, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0967483520507812, "global_step": 543292, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0935473442077637, "global_step": 543293, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0853946208953857, "global_step": 543294, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9929282665252686, "global_step": 543295, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.034426212310791, "global_step": 543296, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0497488975524902, "global_step": 543297, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9828660488128662, "global_step": 543298, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.052535057067871, "global_step": 543299, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.073242425918579, "global_step": 543300, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.097480058670044, "global_step": 543301, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0729687213897705, "global_step": 543302, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0924875736236572, "global_step": 543303, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9729737043380737, "global_step": 543304, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0413379669189453, "global_step": 543305, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0148050785064697, "global_step": 543306, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.011337995529175, "global_step": 543307, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.956852674484253, "global_step": 543308, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9935740232467651, "global_step": 543309, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1047160625457764, "global_step": 543310, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.031938314437866, "global_step": 543311, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.986680269241333, "global_step": 543312, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.123568534851074, "global_step": 543313, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.060154676437378, "global_step": 543314, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.094832181930542, "global_step": 543315, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.08681583404541, "global_step": 543316, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.046562671661377, "global_step": 543317, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0097503662109375, "global_step": 543318, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0450663566589355, "global_step": 543319, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9662888050079346, "global_step": 543320, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.039921522140503, "global_step": 543321, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.043665885925293, "global_step": 543322, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0274927616119385, "global_step": 543323, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.051255941390991, "global_step": 543324, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0500903129577637, "global_step": 543325, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0039665699005127, "global_step": 543326, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.020346164703369, "global_step": 543327, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.081263303756714, "global_step": 543328, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.070385217666626, "global_step": 543329, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0232410430908203, "global_step": 543330, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.160834789276123, "global_step": 543331, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0776915550231934, "global_step": 543332, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0867812633514404, "global_step": 543333, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9996765851974487, "global_step": 543334, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.027888059616089, "global_step": 543335, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.985832929611206, "global_step": 543336, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.003556966781616, "global_step": 543337, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.020112991333008, "global_step": 543338, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.996591329574585, "global_step": 543339, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0330607891082764, "global_step": 543340, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0266668796539307, "global_step": 543341, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.033000946044922, "global_step": 543342, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9918900728225708, "global_step": 543343, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0095860958099365, "global_step": 543344, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0473952293395996, "global_step": 543345, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.068145275115967, "global_step": 543346, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9826518297195435, "global_step": 543347, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9932175874710083, "global_step": 543348, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0107052326202393, "global_step": 543349, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0556721687316895, "global_step": 543350, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0507490634918213, "global_step": 543351, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0036635398864746, "global_step": 543352, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0202836990356445, "global_step": 543353, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.000551462173462, "global_step": 543354, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.084874153137207, "global_step": 543355, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9869202375411987, "global_step": 543356, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.047232151031494, "global_step": 543357, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0397515296936035, "global_step": 543358, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0026988983154297, "global_step": 543359, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0435211658477783, "global_step": 543360, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0476670265197754, "global_step": 543361, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0098655223846436, "global_step": 543362, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.023603677749634, "global_step": 543363, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0193049907684326, "global_step": 543364, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.995225429534912, "global_step": 543365, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.179844856262207, "global_step": 543366, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.018706798553467, "global_step": 543367, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.050471067428589, "global_step": 543368, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.070680856704712, "global_step": 543369, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.065976619720459, "global_step": 543370, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.114110231399536, "global_step": 543371, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9949898719787598, "global_step": 543372, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.116213798522949, "global_step": 543373, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0403192043304443, "global_step": 543374, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.118330240249634, "global_step": 543375, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0143797397613525, "global_step": 543376, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0797300338745117, "global_step": 543377, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.2164463996887207, "global_step": 543378, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.043011426925659, "global_step": 543379, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.042820930480957, "global_step": 543380, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0159237384796143, "global_step": 543381, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.013361930847168, "global_step": 543382, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9635087251663208, "global_step": 543383, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0354888439178467, "global_step": 543384, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.053823471069336, "global_step": 543385, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0204172134399414, "global_step": 543386, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0019631385803223, "global_step": 543387, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0282108783721924, "global_step": 543388, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.969633936882019, "global_step": 543389, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0362300872802734, "global_step": 543390, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9679001569747925, "global_step": 543391, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9833534955978394, "global_step": 543392, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1281697750091553, "global_step": 543393, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0286927223205566, "global_step": 543394, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.023690700531006, "global_step": 543395, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0786213874816895, "global_step": 543396, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.987740159034729, "global_step": 543397, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9939682483673096, "global_step": 543398, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0407440662384033, "global_step": 543399, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9877623319625854, "global_step": 543400, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.051664113998413, "global_step": 543401, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0280344486236572, "global_step": 543402, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.030343532562256, "global_step": 543403, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.074042797088623, "global_step": 543404, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9801244735717773, "global_step": 543405, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0044047832489014, "global_step": 543406, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.033062219619751, "global_step": 543407, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9835031032562256, "global_step": 543408, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9878281354904175, "global_step": 543409, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.109694004058838, "global_step": 543410, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9958398342132568, "global_step": 543411, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.033360004425049, "global_step": 543412, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9735044240951538, "global_step": 543413, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0948376655578613, "global_step": 543414, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0774383544921875, "global_step": 543415, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0480852127075195, "global_step": 543416, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9808980226516724, "global_step": 543417, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0633580684661865, "global_step": 543418, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.049471139907837, "global_step": 543419, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0300168991088867, "global_step": 543420, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0220539569854736, "global_step": 543421, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0424742698669434, "global_step": 543422, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.032277822494507, "global_step": 543423, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0092196464538574, "global_step": 543424, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9628548622131348, "global_step": 543425, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.95809805393219, "global_step": 543426, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.081312417984009, "global_step": 543427, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0887343883514404, "global_step": 543428, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.104710578918457, "global_step": 543429, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.033555507659912, "global_step": 543430, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.014277696609497, "global_step": 543431, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0191147327423096, "global_step": 543432, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0008127689361572, "global_step": 543433, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1439595222473145, "global_step": 543434, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.03324294090271, "global_step": 543435, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.063312530517578, "global_step": 543436, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.067709445953369, "global_step": 543437, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.00703763961792, "global_step": 543438, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9727671146392822, "global_step": 543439, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.020961284637451, "global_step": 543440, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0581164360046387, "global_step": 543441, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0131428241729736, "global_step": 543442, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.070416212081909, "global_step": 543443, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.025205373764038, "global_step": 543444, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0878498554229736, "global_step": 543445, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0505855083465576, "global_step": 543446, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0596227645874023, "global_step": 543447, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0327727794647217, "global_step": 543448, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.066586971282959, "global_step": 543449, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.073509454727173, "global_step": 543450, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.04223370552063, "global_step": 543451, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0549051761627197, "global_step": 543452, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0009825229644775, "global_step": 543453, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.044398307800293, "global_step": 543454, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0926876068115234, "global_step": 543455, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.075937509536743, "global_step": 543456, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9853144884109497, "global_step": 543457, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.00376296043396, "global_step": 543458, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9725505113601685, "global_step": 543459, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.985109806060791, "global_step": 543460, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.06833815574646, "global_step": 543461, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0173423290252686, "global_step": 543462, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0560660362243652, "global_step": 543463, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0063469409942627, "global_step": 543464, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.010045289993286, "global_step": 543465, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9894431829452515, "global_step": 543466, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.092040777206421, "global_step": 543467, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0096616744995117, "global_step": 543468, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0193939208984375, "global_step": 543469, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.083207130432129, "global_step": 543470, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.118896245956421, "global_step": 543471, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0317165851593018, "global_step": 543472, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9499255418777466, "global_step": 543473, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.001340627670288, "global_step": 543474, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.168320655822754, "global_step": 543475, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.025066375732422, "global_step": 543476, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9744346141815186, "global_step": 543477, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.107623815536499, "global_step": 543478, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.065042018890381, "global_step": 543479, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.975507140159607, "global_step": 543480, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1403110027313232, "global_step": 543481, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9772632122039795, "global_step": 543482, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1491293907165527, "global_step": 543483, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0611166954040527, "global_step": 543484, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0421507358551025, "global_step": 543485, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0862245559692383, "global_step": 543486, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0360164642333984, "global_step": 543487, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0409276485443115, "global_step": 543488, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.006394624710083, "global_step": 543489, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0037736892700195, "global_step": 543490, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0322771072387695, "global_step": 543491, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.009812593460083, "global_step": 543492, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9952678680419922, "global_step": 543493, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9415611028671265, "global_step": 543494, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.13279390335083, "global_step": 543495, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9707852602005005, "global_step": 543496, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0598416328430176, "global_step": 543497, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.03930401802063, "global_step": 543498, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9276015758514404, "global_step": 543499, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9433646202087402, "global_step": 543500, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.952152132987976, "global_step": 543501, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.054661989212036, "global_step": 543502, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.024958610534668, "global_step": 543503, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9823721647262573, "global_step": 543504, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0906424522399902, "global_step": 543505, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9831533432006836, "global_step": 543506, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0736029148101807, "global_step": 543507, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9902507066726685, "global_step": 543508, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0297186374664307, "global_step": 543509, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0360066890716553, "global_step": 543510, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0026378631591797, "global_step": 543511, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.017194986343384, "global_step": 543512, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0020925998687744, "global_step": 543513, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.094741106033325, "global_step": 543514, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.133650541305542, "global_step": 543515, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0449819564819336, "global_step": 543516, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0591845512390137, "global_step": 543517, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0017077922821045, "global_step": 543518, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0102813243865967, "global_step": 543519, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9988216161727905, "global_step": 543520, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.022308826446533, "global_step": 543521, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.116321325302124, "global_step": 543522, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0050253868103027, "global_step": 543523, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9313536882400513, "global_step": 543524, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0560224056243896, "global_step": 543525, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0835938453674316, "global_step": 543526, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0714542865753174, "global_step": 543527, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.02786922454834, "global_step": 543528, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0511178970336914, "global_step": 543529, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.091001272201538, "global_step": 543530, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.030503511428833, "global_step": 543531, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.131364107131958, "global_step": 543532, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.070354461669922, "global_step": 543533, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.104094982147217, "global_step": 543534, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.063055992126465, "global_step": 543535, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0531342029571533, "global_step": 543536, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0693013668060303, "global_step": 543537, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.082536458969116, "global_step": 543538, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.126338005065918, "global_step": 543539, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0266478061676025, "global_step": 543540, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.096356153488159, "global_step": 543541, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0869619846343994, "global_step": 543542, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0022218227386475, "global_step": 543543, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9812276363372803, "global_step": 543544, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0200626850128174, "global_step": 543545, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9785473346710205, "global_step": 543546, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0518076419830322, "global_step": 543547, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0002455711364746, "global_step": 543548, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0236740112304688, "global_step": 543549, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.993816614151001, "global_step": 543550, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9888756275177002, "global_step": 543551, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9853490591049194, "global_step": 543552, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.058429002761841, "global_step": 543553, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1008107662200928, "global_step": 543554, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.056828260421753, "global_step": 543555, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1222403049468994, "global_step": 543556, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1251728534698486, "global_step": 543557, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0162155628204346, "global_step": 543558, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9225163459777832, "global_step": 543559, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0335211753845215, "global_step": 543560, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9902862310409546, "global_step": 543561, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.040226459503174, "global_step": 543562, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.001006603240967, "global_step": 543563, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0515148639678955, "global_step": 543564, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9788259267807007, "global_step": 543565, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9529998302459717, "global_step": 543566, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0497355461120605, "global_step": 543567, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0120720863342285, "global_step": 543568, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9642137289047241, "global_step": 543569, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9489474296569824, "global_step": 543570, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.096257448196411, "global_step": 543571, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.985870599746704, "global_step": 543572, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0531387329101562, "global_step": 543573, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.013392210006714, "global_step": 543574, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1651558876037598, "global_step": 543575, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.007253408432007, "global_step": 543576, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.130638360977173, "global_step": 543577, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0768299102783203, "global_step": 543578, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0077714920043945, "global_step": 543579, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0441465377807617, "global_step": 543580, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0068342685699463, "global_step": 543581, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.040355682373047, "global_step": 543582, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1218717098236084, "global_step": 543583, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.029794931411743, "global_step": 543584, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0582985877990723, "global_step": 543585, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0660793781280518, "global_step": 543586, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.001756429672241, "global_step": 543587, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.01815128326416, "global_step": 543588, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.019324541091919, "global_step": 543589, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0774149894714355, "global_step": 543590, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0619184970855713, "global_step": 543591, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0417404174804688, "global_step": 543592, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.941896677017212, "global_step": 543593, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9847135543823242, "global_step": 543594, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.099000930786133, "global_step": 543595, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.058943510055542, "global_step": 543596, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.047403573989868, "global_step": 543597, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0387017726898193, "global_step": 543598, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0532119274139404, "global_step": 543599, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0437469482421875, "global_step": 543600, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.098975658416748, "global_step": 543601, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0534913539886475, "global_step": 543602, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.95333993434906, "global_step": 543603, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.025700092315674, "global_step": 543604, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0136196613311768, "global_step": 543605, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0804929733276367, "global_step": 543606, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.050482988357544, "global_step": 543607, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9869799613952637, "global_step": 543608, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.95500910282135, "global_step": 543609, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.072003126144409, "global_step": 543610, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.923912525177002, "global_step": 543611, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.036916732788086, "global_step": 543612, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0606613159179688, "global_step": 543613, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.016082525253296, "global_step": 543614, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9353853464126587, "global_step": 543615, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9685888290405273, "global_step": 543616, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0865652561187744, "global_step": 543617, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.024306058883667, "global_step": 543618, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0153660774230957, "global_step": 543619, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0385241508483887, "global_step": 543620, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.011587142944336, "global_step": 543621, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9795403480529785, "global_step": 543622, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9620674848556519, "global_step": 543623, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0592050552368164, "global_step": 543624, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.111407518386841, "global_step": 543625, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1019794940948486, "global_step": 543626, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0366599559783936, "global_step": 543627, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1080141067504883, "global_step": 543628, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.051804780960083, "global_step": 543629, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.104656219482422, "global_step": 543630, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9865659475326538, "global_step": 543631, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.151599884033203, "global_step": 543632, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0289266109466553, "global_step": 543633, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0669453144073486, "global_step": 543634, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0479252338409424, "global_step": 543635, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.001042366027832, "global_step": 543636, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9974066019058228, "global_step": 543637, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0826117992401123, "global_step": 543638, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.155106544494629, "global_step": 543639, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1123127937316895, "global_step": 543640, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0965120792388916, "global_step": 543641, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0621204376220703, "global_step": 543642, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.069469451904297, "global_step": 543643, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.02360200881958, "global_step": 543644, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.085691452026367, "global_step": 543645, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0611836910247803, "global_step": 543646, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.048504114151001, "global_step": 543647, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0267655849456787, "global_step": 543648, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0342259407043457, "global_step": 543649, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0914711952209473, "global_step": 543650, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.05403208732605, "global_step": 543651, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0694217681884766, "global_step": 543652, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0721335411071777, "global_step": 543653, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0261988639831543, "global_step": 543654, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0065853595733643, "global_step": 543655, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0756871700286865, "global_step": 543656, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0218751430511475, "global_step": 543657, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9834145307540894, "global_step": 543658, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0224268436431885, "global_step": 543659, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.085242748260498, "global_step": 543660, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0113420486450195, "global_step": 543661, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0513100624084473, "global_step": 543662, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9979190826416016, "global_step": 543663, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.009495735168457, "global_step": 543664, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.094425916671753, "global_step": 543665, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9833029508590698, "global_step": 543666, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0249526500701904, "global_step": 543667, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.102421283721924, "global_step": 543668, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0520122051239014, "global_step": 543669, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9648462533950806, "global_step": 543670, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.96968412399292, "global_step": 543671, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.054941415786743, "global_step": 543672, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1126930713653564, "global_step": 543673, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.022231340408325, "global_step": 543674, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.044172763824463, "global_step": 543675, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0714950561523438, "global_step": 543676, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0755527019500732, "global_step": 543677, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0380191802978516, "global_step": 543678, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1191883087158203, "global_step": 543679, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.143598794937134, "global_step": 543680, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9998416900634766, "global_step": 543681, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.085853338241577, "global_step": 543682, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.066415309906006, "global_step": 543683, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9901361465454102, "global_step": 543684, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.06905198097229, "global_step": 543685, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9859298467636108, "global_step": 543686, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.049590826034546, "global_step": 543687, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.080179214477539, "global_step": 543688, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.064995050430298, "global_step": 543689, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0812556743621826, "global_step": 543690, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0458624362945557, "global_step": 543691, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.96891450881958, "global_step": 543692, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0253238677978516, "global_step": 543693, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0223641395568848, "global_step": 543694, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0447535514831543, "global_step": 543695, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1133053302764893, "global_step": 543696, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0670952796936035, "global_step": 543697, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0661587715148926, "global_step": 543698, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0424070358276367, "global_step": 543699, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.041687250137329, "global_step": 543700, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0206758975982666, "global_step": 543701, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.054931163787842, "global_step": 543702, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.002429246902466, "global_step": 543703, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0026636123657227, "global_step": 543704, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0451362133026123, "global_step": 543705, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0570709705352783, "global_step": 543706, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0460681915283203, "global_step": 543707, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0181164741516113, "global_step": 543708, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.08131742477417, "global_step": 543709, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.041645050048828, "global_step": 543710, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0255439281463623, "global_step": 543711, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.035912275314331, "global_step": 543712, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0251944065093994, "global_step": 543713, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9502359628677368, "global_step": 543714, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0027472972869873, "global_step": 543715, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0689117908477783, "global_step": 543716, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.000559091567993, "global_step": 543717, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9593074321746826, "global_step": 543718, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9744776487350464, "global_step": 543719, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.082343339920044, "global_step": 543720, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.011397123336792, "global_step": 543721, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0048179626464844, "global_step": 543722, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.080167055130005, "global_step": 543723, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0805165767669678, "global_step": 543724, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0697755813598633, "global_step": 543725, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.018221855163574, "global_step": 543726, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.11301851272583, "global_step": 543727, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0712673664093018, "global_step": 543728, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0344622135162354, "global_step": 543729, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.004859447479248, "global_step": 543730, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0808818340301514, "global_step": 543731, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.1442131996154785, "global_step": 543732, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.099853038787842, "global_step": 543733, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0265262126922607, "global_step": 543734, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0172059535980225, "global_step": 543735, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.076169490814209, "global_step": 543736, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.0061426162719727, "global_step": 543737, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9632091522216797, "global_step": 543738, "epoch": 910, "lr": 5e-05}
{"train_loss": 1.9536932706832886, "global_step": 543739, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.123396635055542, "global_step": 543740, "epoch": 910, "lr": 5e-05}
{"train_loss": 2.033468246459961, "global_step": 543741, "epoch": 910, "lr": 5e-05, "val_loss": 5.745885372161865, "test_reconst_mse": 0.07380340248346329}
{"train_loss": 2.0325658321380615, "global_step": 543742, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9967713356018066, "global_step": 543743, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9636164903640747, "global_step": 543744, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.008505344390869, "global_step": 543745, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.04738450050354, "global_step": 543746, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0466573238372803, "global_step": 543747, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9716806411743164, "global_step": 543748, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.096407413482666, "global_step": 543749, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0979268550872803, "global_step": 543750, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.94826340675354, "global_step": 543751, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.937718391418457, "global_step": 543752, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9702874422073364, "global_step": 543753, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0837626457214355, "global_step": 543754, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1002659797668457, "global_step": 543755, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.008044481277466, "global_step": 543756, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0343990325927734, "global_step": 543757, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0067200660705566, "global_step": 543758, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9984239339828491, "global_step": 543759, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0093190670013428, "global_step": 543760, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9774105548858643, "global_step": 543761, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9739329814910889, "global_step": 543762, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.985554814338684, "global_step": 543763, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0093603134155273, "global_step": 543764, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.997882604598999, "global_step": 543765, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9728376865386963, "global_step": 543766, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.995227575302124, "global_step": 543767, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1199469566345215, "global_step": 543768, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.978743076324463, "global_step": 543769, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9829504489898682, "global_step": 543770, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0026865005493164, "global_step": 543771, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.988477349281311, "global_step": 543772, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9879192113876343, "global_step": 543773, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.041494846343994, "global_step": 543774, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9909592866897583, "global_step": 543775, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.096870183944702, "global_step": 543776, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9634730815887451, "global_step": 543777, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9705474376678467, "global_step": 543778, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0689003467559814, "global_step": 543779, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.078218936920166, "global_step": 543780, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.009134292602539, "global_step": 543781, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9037437438964844, "global_step": 543782, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.983339786529541, "global_step": 543783, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0471301078796387, "global_step": 543784, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.041422128677368, "global_step": 543785, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.01078724861145, "global_step": 543786, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9315251111984253, "global_step": 543787, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.01381778717041, "global_step": 543788, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0497329235076904, "global_step": 543789, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9804219007492065, "global_step": 543790, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9004164934158325, "global_step": 543791, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9399333000183105, "global_step": 543792, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.087660551071167, "global_step": 543793, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.048501491546631, "global_step": 543794, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.993200659751892, "global_step": 543795, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.017059326171875, "global_step": 543796, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9822794198989868, "global_step": 543797, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9898301362991333, "global_step": 543798, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9682602882385254, "global_step": 543799, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.023085594177246, "global_step": 543800, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0480759143829346, "global_step": 543801, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.007383108139038, "global_step": 543802, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9736511707305908, "global_step": 543803, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0628974437713623, "global_step": 543804, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9916236400604248, "global_step": 543805, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0826640129089355, "global_step": 543806, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.004159927368164, "global_step": 543807, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9690768718719482, "global_step": 543808, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.978884220123291, "global_step": 543809, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.006178140640259, "global_step": 543810, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0376176834106445, "global_step": 543811, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9635207653045654, "global_step": 543812, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.012824058532715, "global_step": 543813, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9791868925094604, "global_step": 543814, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1073882579803467, "global_step": 543815, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.00103759765625, "global_step": 543816, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.029054880142212, "global_step": 543817, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9851704835891724, "global_step": 543818, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.013641357421875, "global_step": 543819, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0261952877044678, "global_step": 543820, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9861607551574707, "global_step": 543821, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.051692008972168, "global_step": 543822, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.064656972885132, "global_step": 543823, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0004680156707764, "global_step": 543824, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0285732746124268, "global_step": 543825, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0519471168518066, "global_step": 543826, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.038529634475708, "global_step": 543827, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.988024353981018, "global_step": 543828, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9391165971755981, "global_step": 543829, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.00341796875, "global_step": 543830, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0854740142822266, "global_step": 543831, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0626862049102783, "global_step": 543832, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0078399181365967, "global_step": 543833, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.061638832092285, "global_step": 543834, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.067918539047241, "global_step": 543835, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.006038188934326, "global_step": 543836, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9685969352722168, "global_step": 543837, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.954534888267517, "global_step": 543838, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.014291524887085, "global_step": 543839, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9852709770202637, "global_step": 543840, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9967693090438843, "global_step": 543841, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.991559386253357, "global_step": 543842, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0109121799468994, "global_step": 543843, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.077036142349243, "global_step": 543844, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0386645793914795, "global_step": 543845, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0845584869384766, "global_step": 543846, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9495468139648438, "global_step": 543847, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.954240083694458, "global_step": 543848, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.034550428390503, "global_step": 543849, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.027033805847168, "global_step": 543850, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0009562969207764, "global_step": 543851, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0563607215881348, "global_step": 543852, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0373356342315674, "global_step": 543853, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.064650535583496, "global_step": 543854, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0688700675964355, "global_step": 543855, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9819340705871582, "global_step": 543856, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.99289071559906, "global_step": 543857, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9101674556732178, "global_step": 543858, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.979903221130371, "global_step": 543859, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.032010793685913, "global_step": 543860, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9992176294326782, "global_step": 543861, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9813240766525269, "global_step": 543862, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9816312789916992, "global_step": 543863, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.959229588508606, "global_step": 543864, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.042717695236206, "global_step": 543865, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0327413082122803, "global_step": 543866, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.00650691986084, "global_step": 543867, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9987256526947021, "global_step": 543868, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0289559364318848, "global_step": 543869, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.115936756134033, "global_step": 543870, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9956560134887695, "global_step": 543871, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.021934986114502, "global_step": 543872, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0311570167541504, "global_step": 543873, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.054051399230957, "global_step": 543874, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0281729698181152, "global_step": 543875, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9848874807357788, "global_step": 543876, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0341296195983887, "global_step": 543877, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.062901258468628, "global_step": 543878, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.036092519760132, "global_step": 543879, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9732602834701538, "global_step": 543880, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0606603622436523, "global_step": 543881, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0505995750427246, "global_step": 543882, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9809293746948242, "global_step": 543883, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0803680419921875, "global_step": 543884, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0990796089172363, "global_step": 543885, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0154616832733154, "global_step": 543886, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.021021842956543, "global_step": 543887, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0639400482177734, "global_step": 543888, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9950798749923706, "global_step": 543889, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.032815456390381, "global_step": 543890, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.081669807434082, "global_step": 543891, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.125133991241455, "global_step": 543892, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9724597930908203, "global_step": 543893, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0853238105773926, "global_step": 543894, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9770630598068237, "global_step": 543895, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0696053504943848, "global_step": 543896, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0166685581207275, "global_step": 543897, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0078186988830566, "global_step": 543898, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9325922727584839, "global_step": 543899, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9668022394180298, "global_step": 543900, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0082356929779053, "global_step": 543901, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.00039005279541, "global_step": 543902, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.026233196258545, "global_step": 543903, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.992799162864685, "global_step": 543904, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0495848655700684, "global_step": 543905, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.011486053466797, "global_step": 543906, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9603767395019531, "global_step": 543907, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0230023860931396, "global_step": 543908, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0818469524383545, "global_step": 543909, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9954955577850342, "global_step": 543910, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0249135494232178, "global_step": 543911, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.074610948562622, "global_step": 543912, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0344369411468506, "global_step": 543913, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9966275691986084, "global_step": 543914, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0967068672180176, "global_step": 543915, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9541964530944824, "global_step": 543916, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0064499378204346, "global_step": 543917, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.11725115776062, "global_step": 543918, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0444865226745605, "global_step": 543919, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.049164295196533, "global_step": 543920, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0084927082061768, "global_step": 543921, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.034425735473633, "global_step": 543922, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0207276344299316, "global_step": 543923, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1042420864105225, "global_step": 543924, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0004968643188477, "global_step": 543925, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9762091636657715, "global_step": 543926, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9323612451553345, "global_step": 543927, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9581815004348755, "global_step": 543928, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0749244689941406, "global_step": 543929, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.069228410720825, "global_step": 543930, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.052003860473633, "global_step": 543931, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9917746782302856, "global_step": 543932, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0307822227478027, "global_step": 543933, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.052166700363159, "global_step": 543934, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.068307638168335, "global_step": 543935, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0373926162719727, "global_step": 543936, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0952510833740234, "global_step": 543937, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1450021266937256, "global_step": 543938, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.044018030166626, "global_step": 543939, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9610583782196045, "global_step": 543940, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9726886749267578, "global_step": 543941, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0220754146575928, "global_step": 543942, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9831560850143433, "global_step": 543943, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9837456941604614, "global_step": 543944, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.039778470993042, "global_step": 543945, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.003159999847412, "global_step": 543946, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.044454336166382, "global_step": 543947, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.128554582595825, "global_step": 543948, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.049015760421753, "global_step": 543949, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.046516180038452, "global_step": 543950, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9451295137405396, "global_step": 543951, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.040473461151123, "global_step": 543952, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0084779262542725, "global_step": 543953, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0972914695739746, "global_step": 543954, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9518799781799316, "global_step": 543955, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.110076427459717, "global_step": 543956, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0466232299804688, "global_step": 543957, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.010002374649048, "global_step": 543958, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.021632671356201, "global_step": 543959, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0105271339416504, "global_step": 543960, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1553237438201904, "global_step": 543961, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.049237012863159, "global_step": 543962, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.015012502670288, "global_step": 543963, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0141260623931885, "global_step": 543964, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0693764686584473, "global_step": 543965, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0405898094177246, "global_step": 543966, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0638036727905273, "global_step": 543967, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0574402809143066, "global_step": 543968, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1183149814605713, "global_step": 543969, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.038210391998291, "global_step": 543970, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0425307750701904, "global_step": 543971, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0486960411071777, "global_step": 543972, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.046510696411133, "global_step": 543973, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9662961959838867, "global_step": 543974, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.025057315826416, "global_step": 543975, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9765657186508179, "global_step": 543976, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0882434844970703, "global_step": 543977, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9748519659042358, "global_step": 543978, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.054520606994629, "global_step": 543979, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.949371576309204, "global_step": 543980, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0488152503967285, "global_step": 543981, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9959936141967773, "global_step": 543982, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0330123901367188, "global_step": 543983, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9900461435317993, "global_step": 543984, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0058398246765137, "global_step": 543985, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.997251272201538, "global_step": 543986, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0462427139282227, "global_step": 543987, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.063885450363159, "global_step": 543988, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.014972686767578, "global_step": 543989, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.04681396484375, "global_step": 543990, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.025217056274414, "global_step": 543991, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.05025577545166, "global_step": 543992, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0550270080566406, "global_step": 543993, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0198230743408203, "global_step": 543994, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0409843921661377, "global_step": 543995, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9953728914260864, "global_step": 543996, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.011218547821045, "global_step": 543997, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0158066749572754, "global_step": 543998, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0191051959991455, "global_step": 543999, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9484047889709473, "global_step": 544000, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.05728816986084, "global_step": 544001, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0319008827209473, "global_step": 544002, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.012033700942993, "global_step": 544003, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0490756034851074, "global_step": 544004, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0435235500335693, "global_step": 544005, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0528769493103027, "global_step": 544006, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.040379524230957, "global_step": 544007, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.974779486656189, "global_step": 544008, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9310965538024902, "global_step": 544009, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9346824884414673, "global_step": 544010, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0404374599456787, "global_step": 544011, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.001427173614502, "global_step": 544012, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1095547676086426, "global_step": 544013, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9566290378570557, "global_step": 544014, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.032365322113037, "global_step": 544015, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.040694236755371, "global_step": 544016, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.078218698501587, "global_step": 544017, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0752971172332764, "global_step": 544018, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.000831127166748, "global_step": 544019, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.978448510169983, "global_step": 544020, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0413084030151367, "global_step": 544021, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.071302890777588, "global_step": 544022, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.072688341140747, "global_step": 544023, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.964026689529419, "global_step": 544024, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9710041284561157, "global_step": 544025, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0570390224456787, "global_step": 544026, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.046860694885254, "global_step": 544027, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9912196397781372, "global_step": 544028, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0377838611602783, "global_step": 544029, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9872232675552368, "global_step": 544030, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9513418674468994, "global_step": 544031, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.997011423110962, "global_step": 544032, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.038801908493042, "global_step": 544033, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0310935974121094, "global_step": 544034, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9284995794296265, "global_step": 544035, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1179189682006836, "global_step": 544036, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0401642322540283, "global_step": 544037, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9762475490570068, "global_step": 544038, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.017174482345581, "global_step": 544039, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.065749168395996, "global_step": 544040, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0093491077423096, "global_step": 544041, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.084780216217041, "global_step": 544042, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.010220527648926, "global_step": 544043, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.006476879119873, "global_step": 544044, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1061582565307617, "global_step": 544045, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.020643472671509, "global_step": 544046, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0066375732421875, "global_step": 544047, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0690314769744873, "global_step": 544048, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.116096019744873, "global_step": 544049, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9817955493927002, "global_step": 544050, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.022181272506714, "global_step": 544051, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.045391321182251, "global_step": 544052, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.14715576171875, "global_step": 544053, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1083502769470215, "global_step": 544054, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0416290760040283, "global_step": 544055, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9833555221557617, "global_step": 544056, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.089282989501953, "global_step": 544057, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9508531093597412, "global_step": 544058, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9537477493286133, "global_step": 544059, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.091745138168335, "global_step": 544060, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0277373790740967, "global_step": 544061, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9887248277664185, "global_step": 544062, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.046767473220825, "global_step": 544063, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.075881242752075, "global_step": 544064, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0054311752319336, "global_step": 544065, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.056950330734253, "global_step": 544066, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.025146484375, "global_step": 544067, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9278229475021362, "global_step": 544068, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0788145065307617, "global_step": 544069, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9590040445327759, "global_step": 544070, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.06961989402771, "global_step": 544071, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.074540615081787, "global_step": 544072, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0421054363250732, "global_step": 544073, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0942978858947754, "global_step": 544074, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0171127319335938, "global_step": 544075, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9837287664413452, "global_step": 544076, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.012538433074951, "global_step": 544077, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0548250675201416, "global_step": 544078, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.932578444480896, "global_step": 544079, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0607750415802, "global_step": 544080, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0543746948242188, "global_step": 544081, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9800772666931152, "global_step": 544082, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9805649518966675, "global_step": 544083, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9749219417572021, "global_step": 544084, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.049269914627075, "global_step": 544085, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0051169395446777, "global_step": 544086, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1196444034576416, "global_step": 544087, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9990599155426025, "global_step": 544088, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0705244541168213, "global_step": 544089, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.02653169631958, "global_step": 544090, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.130676507949829, "global_step": 544091, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.013803482055664, "global_step": 544092, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0898962020874023, "global_step": 544093, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.067479372024536, "global_step": 544094, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.074742555618286, "global_step": 544095, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9890061616897583, "global_step": 544096, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.072201728820801, "global_step": 544097, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.073158025741577, "global_step": 544098, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1028218269348145, "global_step": 544099, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.054513692855835, "global_step": 544100, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0313539505004883, "global_step": 544101, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9348607063293457, "global_step": 544102, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0567996501922607, "global_step": 544103, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9892961978912354, "global_step": 544104, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.992978572845459, "global_step": 544105, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9895813465118408, "global_step": 544106, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9877815246582031, "global_step": 544107, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.024228572845459, "global_step": 544108, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0226850509643555, "global_step": 544109, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.053314447402954, "global_step": 544110, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.044008731842041, "global_step": 544111, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0217368602752686, "global_step": 544112, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0857152938842773, "global_step": 544113, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.085257053375244, "global_step": 544114, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.026341438293457, "global_step": 544115, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.012827157974243, "global_step": 544116, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0814368724823, "global_step": 544117, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9946552515029907, "global_step": 544118, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9497380256652832, "global_step": 544119, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0397226810455322, "global_step": 544120, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0932884216308594, "global_step": 544121, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0568604469299316, "global_step": 544122, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0179660320281982, "global_step": 544123, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0538039207458496, "global_step": 544124, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0979254245758057, "global_step": 544125, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.004948139190674, "global_step": 544126, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.099818229675293, "global_step": 544127, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0740463733673096, "global_step": 544128, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.108081579208374, "global_step": 544129, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9893581867218018, "global_step": 544130, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0796306133270264, "global_step": 544131, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.079043388366699, "global_step": 544132, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0093579292297363, "global_step": 544133, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0172057151794434, "global_step": 544134, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9498151540756226, "global_step": 544135, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.977943778038025, "global_step": 544136, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0577003955841064, "global_step": 544137, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9381870031356812, "global_step": 544138, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0415022373199463, "global_step": 544139, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0522117614746094, "global_step": 544140, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1409809589385986, "global_step": 544141, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0752575397491455, "global_step": 544142, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0046212673187256, "global_step": 544143, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.053654432296753, "global_step": 544144, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9973981380462646, "global_step": 544145, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9636404514312744, "global_step": 544146, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9694396257400513, "global_step": 544147, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9582329988479614, "global_step": 544148, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9702513217926025, "global_step": 544149, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0506720542907715, "global_step": 544150, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.052504062652588, "global_step": 544151, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0571436882019043, "global_step": 544152, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1083824634552, "global_step": 544153, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.092273473739624, "global_step": 544154, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.063527822494507, "global_step": 544155, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.017996072769165, "global_step": 544156, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0228397846221924, "global_step": 544157, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9710156917572021, "global_step": 544158, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0252435207366943, "global_step": 544159, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0126900672912598, "global_step": 544160, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0631492137908936, "global_step": 544161, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0261030197143555, "global_step": 544162, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0585227012634277, "global_step": 544163, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0464556217193604, "global_step": 544164, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9564846754074097, "global_step": 544165, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.024492025375366, "global_step": 544166, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.962133765220642, "global_step": 544167, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.068051815032959, "global_step": 544168, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0494515895843506, "global_step": 544169, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9995934963226318, "global_step": 544170, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.096564769744873, "global_step": 544171, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0183398723602295, "global_step": 544172, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9675148725509644, "global_step": 544173, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0282483100891113, "global_step": 544174, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.970244288444519, "global_step": 544175, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.022613525390625, "global_step": 544176, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.034553289413452, "global_step": 544177, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0831713676452637, "global_step": 544178, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.013315439224243, "global_step": 544179, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0318801403045654, "global_step": 544180, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.103888750076294, "global_step": 544181, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0591886043548584, "global_step": 544182, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1172540187835693, "global_step": 544183, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9787354469299316, "global_step": 544184, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0274336338043213, "global_step": 544185, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0407683849334717, "global_step": 544186, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9497872591018677, "global_step": 544187, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.023184299468994, "global_step": 544188, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9640896320343018, "global_step": 544189, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0256097316741943, "global_step": 544190, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9957386255264282, "global_step": 544191, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0092828273773193, "global_step": 544192, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0780248641967773, "global_step": 544193, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.998557686805725, "global_step": 544194, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0677599906921387, "global_step": 544195, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.880014419555664, "global_step": 544196, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0471653938293457, "global_step": 544197, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0526416301727295, "global_step": 544198, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0842370986938477, "global_step": 544199, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0702147483825684, "global_step": 544200, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.067814350128174, "global_step": 544201, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.002497911453247, "global_step": 544202, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0359227657318115, "global_step": 544203, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.131178617477417, "global_step": 544204, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9430649280548096, "global_step": 544205, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.083965539932251, "global_step": 544206, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0536744594573975, "global_step": 544207, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0942959785461426, "global_step": 544208, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9325759410858154, "global_step": 544209, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.8980686664581299, "global_step": 544210, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.033116102218628, "global_step": 544211, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.960913062095642, "global_step": 544212, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0936505794525146, "global_step": 544213, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.062812089920044, "global_step": 544214, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0722367763519287, "global_step": 544215, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9003667831420898, "global_step": 544216, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0147688388824463, "global_step": 544217, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.045283794403076, "global_step": 544218, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9680359363555908, "global_step": 544219, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9605011940002441, "global_step": 544220, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9923323392868042, "global_step": 544221, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.078611135482788, "global_step": 544222, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.035231351852417, "global_step": 544223, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9896153211593628, "global_step": 544224, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.121613025665283, "global_step": 544225, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.044234037399292, "global_step": 544226, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0995025634765625, "global_step": 544227, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0245537757873535, "global_step": 544228, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0221798419952393, "global_step": 544229, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.99125075340271, "global_step": 544230, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.096118450164795, "global_step": 544231, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0570967197418213, "global_step": 544232, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.066426992416382, "global_step": 544233, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9225369691848755, "global_step": 544234, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1302547454833984, "global_step": 544235, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0706822872161865, "global_step": 544236, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.967850923538208, "global_step": 544237, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.00888729095459, "global_step": 544238, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9810022115707397, "global_step": 544239, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.038226366043091, "global_step": 544240, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.996427297592163, "global_step": 544241, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9409747123718262, "global_step": 544242, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.098891019821167, "global_step": 544243, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0816361904144287, "global_step": 544244, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9806134700775146, "global_step": 544245, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1143460273742676, "global_step": 544246, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0750529766082764, "global_step": 544247, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.022761583328247, "global_step": 544248, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9910011291503906, "global_step": 544249, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0486907958984375, "global_step": 544250, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0659990310668945, "global_step": 544251, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1324236392974854, "global_step": 544252, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0359654426574707, "global_step": 544253, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.058239221572876, "global_step": 544254, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0397090911865234, "global_step": 544255, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9589155912399292, "global_step": 544256, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9263267517089844, "global_step": 544257, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.126885175704956, "global_step": 544258, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0530014038085938, "global_step": 544259, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0427045822143555, "global_step": 544260, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0661780834198, "global_step": 544261, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.979396104812622, "global_step": 544262, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.040458917617798, "global_step": 544263, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.028238296508789, "global_step": 544264, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.068173885345459, "global_step": 544265, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.017321825027466, "global_step": 544266, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0176711082458496, "global_step": 544267, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9861594438552856, "global_step": 544268, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0684354305267334, "global_step": 544269, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0975589752197266, "global_step": 544270, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.069977045059204, "global_step": 544271, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.11307692527771, "global_step": 544272, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1769843101501465, "global_step": 544273, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0416533946990967, "global_step": 544274, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.07029128074646, "global_step": 544275, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9821357727050781, "global_step": 544276, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0584537982940674, "global_step": 544277, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.015413999557495, "global_step": 544278, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.048428773880005, "global_step": 544279, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.095184803009033, "global_step": 544280, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.955338716506958, "global_step": 544281, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0702297687530518, "global_step": 544282, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9622337818145752, "global_step": 544283, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9199496507644653, "global_step": 544284, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0015993118286133, "global_step": 544285, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0323116779327393, "global_step": 544286, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0016047954559326, "global_step": 544287, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0054702758789062, "global_step": 544288, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.124493360519409, "global_step": 544289, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0812160968780518, "global_step": 544290, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9926830530166626, "global_step": 544291, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0374369621276855, "global_step": 544292, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0231518745422363, "global_step": 544293, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9919942617416382, "global_step": 544294, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.89712655544281, "global_step": 544295, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0455844402313232, "global_step": 544296, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.015798568725586, "global_step": 544297, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.142592430114746, "global_step": 544298, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0527801513671875, "global_step": 544299, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0319690704345703, "global_step": 544300, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0484983921051025, "global_step": 544301, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.022240161895752, "global_step": 544302, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.928318977355957, "global_step": 544303, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9849573373794556, "global_step": 544304, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0634100437164307, "global_step": 544305, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.8952449560165405, "global_step": 544306, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9838334321975708, "global_step": 544307, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.002476930618286, "global_step": 544308, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.012269973754883, "global_step": 544309, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.070704698562622, "global_step": 544310, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.121807098388672, "global_step": 544311, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0649876594543457, "global_step": 544312, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9780857563018799, "global_step": 544313, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0158467292785645, "global_step": 544314, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.060244083404541, "global_step": 544315, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0278358459472656, "global_step": 544316, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.007129669189453, "global_step": 544317, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.022064447402954, "global_step": 544318, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1068882942199707, "global_step": 544319, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0659894943237305, "global_step": 544320, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.012092113494873, "global_step": 544321, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.062680959701538, "global_step": 544322, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0505728721618652, "global_step": 544323, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.060026168823242, "global_step": 544324, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0039596557617188, "global_step": 544325, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9786629676818848, "global_step": 544326, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0493593215942383, "global_step": 544327, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9330977201461792, "global_step": 544328, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0135445594787598, "global_step": 544329, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.033061981201172, "global_step": 544330, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0212695598602295, "global_step": 544331, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.145864725112915, "global_step": 544332, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.986504316329956, "global_step": 544333, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0359721183776855, "global_step": 544334, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0332021713256836, "global_step": 544335, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0588555335998535, "global_step": 544336, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.953256368637085, "global_step": 544337, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.042905807495117, "global_step": 544338, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9963726997375488, "global_step": 544339, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0962958335876465, "global_step": 544340, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.078843116760254, "global_step": 544341, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.048546552658081, "global_step": 544342, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9351091384887695, "global_step": 544343, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.944068431854248, "global_step": 544344, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0454275608062744, "global_step": 544345, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0008556842803955, "global_step": 544346, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.996484398841858, "global_step": 544347, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.096513271331787, "global_step": 544348, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.027735948562622, "global_step": 544349, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.061797618865967, "global_step": 544350, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.088496446609497, "global_step": 544351, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0326836109161377, "global_step": 544352, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0223746299743652, "global_step": 544353, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0527849197387695, "global_step": 544354, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1161797046661377, "global_step": 544355, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0437490940093994, "global_step": 544356, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0091397762298584, "global_step": 544357, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.012681007385254, "global_step": 544358, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9156616926193237, "global_step": 544359, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.038006067276001, "global_step": 544360, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0583784580230713, "global_step": 544361, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0699808597564697, "global_step": 544362, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9171674251556396, "global_step": 544363, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.057070732116699, "global_step": 544364, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0383498668670654, "global_step": 544365, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.071582555770874, "global_step": 544366, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.037985324859619, "global_step": 544367, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.993205189704895, "global_step": 544368, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9745410680770874, "global_step": 544369, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.066162347793579, "global_step": 544370, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1253669261932373, "global_step": 544371, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.992919683456421, "global_step": 544372, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0285391807556152, "global_step": 544373, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9999818801879883, "global_step": 544374, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.057419776916504, "global_step": 544375, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9656723737716675, "global_step": 544376, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.066074848175049, "global_step": 544377, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.061600923538208, "global_step": 544378, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.169219493865967, "global_step": 544379, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.047309160232544, "global_step": 544380, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0122697353363037, "global_step": 544381, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9479451179504395, "global_step": 544382, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.963141679763794, "global_step": 544383, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.046191692352295, "global_step": 544384, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0519957542419434, "global_step": 544385, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0411605834960938, "global_step": 544386, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.975826382637024, "global_step": 544387, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.091151237487793, "global_step": 544388, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.09411358833313, "global_step": 544389, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0196402072906494, "global_step": 544390, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.078413963317871, "global_step": 544391, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.017758846282959, "global_step": 544392, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.968977689743042, "global_step": 544393, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0467782020568848, "global_step": 544394, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1589555740356445, "global_step": 544395, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.01094388961792, "global_step": 544396, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.008775234222412, "global_step": 544397, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9863848686218262, "global_step": 544398, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.050138473510742, "global_step": 544399, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0123438835144043, "global_step": 544400, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0096304416656494, "global_step": 544401, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.088367462158203, "global_step": 544402, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0011355876922607, "global_step": 544403, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0077693462371826, "global_step": 544404, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9913136959075928, "global_step": 544405, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9939651489257812, "global_step": 544406, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.038053274154663, "global_step": 544407, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0570244789123535, "global_step": 544408, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.989211082458496, "global_step": 544409, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.060159683227539, "global_step": 544410, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0360562801361084, "global_step": 544411, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0093908309936523, "global_step": 544412, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.970450520515442, "global_step": 544413, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0670976638793945, "global_step": 544414, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.075594902038574, "global_step": 544415, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9735331535339355, "global_step": 544416, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0680816173553467, "global_step": 544417, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.172710657119751, "global_step": 544418, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0744431018829346, "global_step": 544419, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.047227144241333, "global_step": 544420, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9989619255065918, "global_step": 544421, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.046727180480957, "global_step": 544422, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.020087718963623, "global_step": 544423, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.045720100402832, "global_step": 544424, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1251766681671143, "global_step": 544425, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0701229572296143, "global_step": 544426, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.030155658721924, "global_step": 544427, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0269956588745117, "global_step": 544428, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1173152923583984, "global_step": 544429, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0737736225128174, "global_step": 544430, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0444204807281494, "global_step": 544431, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.039081335067749, "global_step": 544432, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.077923059463501, "global_step": 544433, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0116939544677734, "global_step": 544434, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0367355346679688, "global_step": 544435, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0542526245117188, "global_step": 544436, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9406887292861938, "global_step": 544437, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.142578601837158, "global_step": 544438, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.09920072555542, "global_step": 544439, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0492024421691895, "global_step": 544440, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9675748348236084, "global_step": 544441, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0418317317962646, "global_step": 544442, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9508252143859863, "global_step": 544443, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0209901332855225, "global_step": 544444, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0567660331726074, "global_step": 544445, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0888140201568604, "global_step": 544446, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0112264156341553, "global_step": 544447, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.046391487121582, "global_step": 544448, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.117342948913574, "global_step": 544449, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1103498935699463, "global_step": 544450, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0740342140197754, "global_step": 544451, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.975168228149414, "global_step": 544452, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0620555877685547, "global_step": 544453, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0411298274993896, "global_step": 544454, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.097317934036255, "global_step": 544455, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.103405714035034, "global_step": 544456, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9779342412948608, "global_step": 544457, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.937941074371338, "global_step": 544458, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.055145263671875, "global_step": 544459, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.086473226547241, "global_step": 544460, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.993052363395691, "global_step": 544461, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.059410333633423, "global_step": 544462, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.00242280960083, "global_step": 544463, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.05910587310791, "global_step": 544464, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9682508707046509, "global_step": 544465, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.014038562774658, "global_step": 544466, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0947587490081787, "global_step": 544467, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.933421015739441, "global_step": 544468, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.025984048843384, "global_step": 544469, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0200388431549072, "global_step": 544470, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0569326877593994, "global_step": 544471, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.101151466369629, "global_step": 544472, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.047559976577759, "global_step": 544473, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0345728397369385, "global_step": 544474, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.062659502029419, "global_step": 544475, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.016904354095459, "global_step": 544476, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1868951320648193, "global_step": 544477, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0127933025360107, "global_step": 544478, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1094930171966553, "global_step": 544479, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9920724630355835, "global_step": 544480, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0251736640930176, "global_step": 544481, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0479252338409424, "global_step": 544482, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0707952976226807, "global_step": 544483, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0934760570526123, "global_step": 544484, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0359222888946533, "global_step": 544485, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.998763918876648, "global_step": 544486, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9786044359207153, "global_step": 544487, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0296688079833984, "global_step": 544488, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0131723880767822, "global_step": 544489, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.049999237060547, "global_step": 544490, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.023728847503662, "global_step": 544491, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0587754249572754, "global_step": 544492, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9884955883026123, "global_step": 544493, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0838725566864014, "global_step": 544494, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.077446222305298, "global_step": 544495, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1491758823394775, "global_step": 544496, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0115787982940674, "global_step": 544497, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.018843173980713, "global_step": 544498, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.963431715965271, "global_step": 544499, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0253045558929443, "global_step": 544500, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0244452953338623, "global_step": 544501, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0481107234954834, "global_step": 544502, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0725600719451904, "global_step": 544503, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.021932363510132, "global_step": 544504, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9487671852111816, "global_step": 544505, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9722707271575928, "global_step": 544506, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9447904825210571, "global_step": 544507, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0397820472717285, "global_step": 544508, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0065793991088867, "global_step": 544509, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0308427810668945, "global_step": 544510, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9851460456848145, "global_step": 544511, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.10282039642334, "global_step": 544512, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0154976844787598, "global_step": 544513, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0399606227874756, "global_step": 544514, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0747129917144775, "global_step": 544515, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.081575393676758, "global_step": 544516, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0256974697113037, "global_step": 544517, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.8629010915756226, "global_step": 544518, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0282950401306152, "global_step": 544519, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.109952211380005, "global_step": 544520, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0482046604156494, "global_step": 544521, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.051374673843384, "global_step": 544522, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0514211654663086, "global_step": 544523, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0415267944335938, "global_step": 544524, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.941058874130249, "global_step": 544525, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1281940937042236, "global_step": 544526, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1009669303894043, "global_step": 544527, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0576610565185547, "global_step": 544528, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0552244186401367, "global_step": 544529, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0025031566619873, "global_step": 544530, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.182619094848633, "global_step": 544531, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9920510053634644, "global_step": 544532, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0028598308563232, "global_step": 544533, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0178732872009277, "global_step": 544534, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9976489543914795, "global_step": 544535, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0350582599639893, "global_step": 544536, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0327155590057373, "global_step": 544537, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9878898859024048, "global_step": 544538, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.958054542541504, "global_step": 544539, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0529439449310303, "global_step": 544540, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1056342124938965, "global_step": 544541, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.055152177810669, "global_step": 544542, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.002553939819336, "global_step": 544543, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.012054204940796, "global_step": 544544, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.057309865951538, "global_step": 544545, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0632236003875732, "global_step": 544546, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9839715957641602, "global_step": 544547, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0160255432128906, "global_step": 544548, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9960566759109497, "global_step": 544549, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0017905235290527, "global_step": 544550, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.058035135269165, "global_step": 544551, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.039992332458496, "global_step": 544552, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0171711444854736, "global_step": 544553, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.128413438796997, "global_step": 544554, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0960795879364014, "global_step": 544555, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0253493785858154, "global_step": 544556, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.104645013809204, "global_step": 544557, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0109481811523438, "global_step": 544558, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.079615354537964, "global_step": 544559, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1249589920043945, "global_step": 544560, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0908384323120117, "global_step": 544561, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.993285894393921, "global_step": 544562, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0776610374450684, "global_step": 544563, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.020813226699829, "global_step": 544564, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0586016178131104, "global_step": 544565, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.108853340148926, "global_step": 544566, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.077833414077759, "global_step": 544567, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.017831325531006, "global_step": 544568, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.015695810317993, "global_step": 544569, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0172832012176514, "global_step": 544570, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1588921546936035, "global_step": 544571, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9897210597991943, "global_step": 544572, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.995488166809082, "global_step": 544573, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.072634696960449, "global_step": 544574, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.078888416290283, "global_step": 544575, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0224521160125732, "global_step": 544576, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.057873487472534, "global_step": 544577, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9740705490112305, "global_step": 544578, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9956916570663452, "global_step": 544579, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0462148189544678, "global_step": 544580, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0357823371887207, "global_step": 544581, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0519461631774902, "global_step": 544582, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.069225549697876, "global_step": 544583, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0936245918273926, "global_step": 544584, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.019257068634033, "global_step": 544585, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9514997005462646, "global_step": 544586, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0827796459198, "global_step": 544587, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0181891918182373, "global_step": 544588, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.016692876815796, "global_step": 544589, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0728631019592285, "global_step": 544590, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.023452043533325, "global_step": 544591, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.153015375137329, "global_step": 544592, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1195600032806396, "global_step": 544593, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0012383460998535, "global_step": 544594, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.085442304611206, "global_step": 544595, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.01764178276062, "global_step": 544596, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0526864528656006, "global_step": 544597, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0333993434906006, "global_step": 544598, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.8718229532241821, "global_step": 544599, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0284478664398193, "global_step": 544600, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9444772005081177, "global_step": 544601, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.972334623336792, "global_step": 544602, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0983364582061768, "global_step": 544603, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.036060333251953, "global_step": 544604, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9793248176574707, "global_step": 544605, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.054053544998169, "global_step": 544606, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0149004459381104, "global_step": 544607, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.040952205657959, "global_step": 544608, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9793033599853516, "global_step": 544609, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.081845760345459, "global_step": 544610, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0158169269561768, "global_step": 544611, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1314697265625, "global_step": 544612, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.99262535572052, "global_step": 544613, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9807904958724976, "global_step": 544614, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.955745816230774, "global_step": 544615, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0764076709747314, "global_step": 544616, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0404269695281982, "global_step": 544617, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0069515705108643, "global_step": 544618, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.001323699951172, "global_step": 544619, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0036842823028564, "global_step": 544620, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0286667346954346, "global_step": 544621, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0711495876312256, "global_step": 544622, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9684736728668213, "global_step": 544623, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9123845100402832, "global_step": 544624, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.108516216278076, "global_step": 544625, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.084360361099243, "global_step": 544626, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.083376169204712, "global_step": 544627, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0935373306274414, "global_step": 544628, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0090417861938477, "global_step": 544629, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.994786024093628, "global_step": 544630, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9737753868103027, "global_step": 544631, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.054076910018921, "global_step": 544632, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.084386110305786, "global_step": 544633, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0470917224884033, "global_step": 544634, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0744073390960693, "global_step": 544635, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9515727758407593, "global_step": 544636, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0624144077301025, "global_step": 544637, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0585243701934814, "global_step": 544638, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0499682426452637, "global_step": 544639, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0298585891723633, "global_step": 544640, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.064344882965088, "global_step": 544641, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.027057647705078, "global_step": 544642, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0583837032318115, "global_step": 544643, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0276801586151123, "global_step": 544644, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0155458450317383, "global_step": 544645, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9982140064239502, "global_step": 544646, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0810444355010986, "global_step": 544647, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0892341136932373, "global_step": 544648, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0724258422851562, "global_step": 544649, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.086937427520752, "global_step": 544650, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9831738471984863, "global_step": 544651, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0285608768463135, "global_step": 544652, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0634396076202393, "global_step": 544653, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0053672790527344, "global_step": 544654, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.048240900039673, "global_step": 544655, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.082577705383301, "global_step": 544656, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9788669347763062, "global_step": 544657, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.998763084411621, "global_step": 544658, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.033972978591919, "global_step": 544659, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9301762580871582, "global_step": 544660, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.071491241455078, "global_step": 544661, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9842240810394287, "global_step": 544662, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0785164833068848, "global_step": 544663, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0877137184143066, "global_step": 544664, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.098571538925171, "global_step": 544665, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.031740665435791, "global_step": 544666, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0854251384735107, "global_step": 544667, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.050642967224121, "global_step": 544668, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0558695793151855, "global_step": 544669, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.992547631263733, "global_step": 544670, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0839180946350098, "global_step": 544671, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0153119564056396, "global_step": 544672, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0482125282287598, "global_step": 544673, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9990893602371216, "global_step": 544674, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0469727516174316, "global_step": 544675, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.05112361907959, "global_step": 544676, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0564892292022705, "global_step": 544677, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.023742437362671, "global_step": 544678, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.059924364089966, "global_step": 544679, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.034217119216919, "global_step": 544680, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0118331909179688, "global_step": 544681, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.033935070037842, "global_step": 544682, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0364389419555664, "global_step": 544683, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.076005697250366, "global_step": 544684, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0633671283721924, "global_step": 544685, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0743298530578613, "global_step": 544686, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.004131555557251, "global_step": 544687, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0871405601501465, "global_step": 544688, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.017474412918091, "global_step": 544689, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.051790952682495, "global_step": 544690, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.1267452239990234, "global_step": 544691, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.098034143447876, "global_step": 544692, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9743549823760986, "global_step": 544693, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0407681465148926, "global_step": 544694, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.121065139770508, "global_step": 544695, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0058507919311523, "global_step": 544696, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0589094161987305, "global_step": 544697, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0251762866973877, "global_step": 544698, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0300543308258057, "global_step": 544699, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.106318950653076, "global_step": 544700, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.02351450920105, "global_step": 544701, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0470454692840576, "global_step": 544702, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.93512761592865, "global_step": 544703, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9213037490844727, "global_step": 544704, "epoch": 911, "lr": 5e-05}
{"train_loss": 1.9986765384674072, "global_step": 544705, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0928869247436523, "global_step": 544706, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.033921480178833, "global_step": 544707, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0613420009613037, "global_step": 544708, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0396804809570312, "global_step": 544709, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.0306830406188965, "global_step": 544710, "epoch": 911, "lr": 5e-05}
{"train_loss": 2.063242197036743, "global_step": 544711, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.022202968597412, "global_step": 544712, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.031736135482788, "global_step": 544713, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0213377475738525, "global_step": 544714, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.051379442214966, "global_step": 544715, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0070371627807617, "global_step": 544716, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0559985637664795, "global_step": 544717, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.063525915145874, "global_step": 544718, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0439627170562744, "global_step": 544719, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0166127681732178, "global_step": 544720, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.036058187484741, "global_step": 544721, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0710155963897705, "global_step": 544722, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9465519189834595, "global_step": 544723, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9168100357055664, "global_step": 544724, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0960888862609863, "global_step": 544725, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.018369436264038, "global_step": 544726, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.146449327468872, "global_step": 544727, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.027963638305664, "global_step": 544728, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0047121047973633, "global_step": 544729, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.081496477127075, "global_step": 544730, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.052222728729248, "global_step": 544731, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9870562553405762, "global_step": 544732, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9390729665756226, "global_step": 544733, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9961711168289185, "global_step": 544734, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0555169582366943, "global_step": 544735, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.998213768005371, "global_step": 544736, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0117905139923096, "global_step": 544737, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0443058013916016, "global_step": 544738, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0264225006103516, "global_step": 544739, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0741899013519287, "global_step": 544740, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0554399490356445, "global_step": 544741, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1026933193206787, "global_step": 544742, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0495972633361816, "global_step": 544743, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9860466718673706, "global_step": 544744, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0882976055145264, "global_step": 544745, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0401077270507812, "global_step": 544746, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9549847841262817, "global_step": 544747, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.998123049736023, "global_step": 544748, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0209970474243164, "global_step": 544749, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0476927757263184, "global_step": 544750, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9751337766647339, "global_step": 544751, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.111955165863037, "global_step": 544752, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0477054119110107, "global_step": 544753, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9521737098693848, "global_step": 544754, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0109105110168457, "global_step": 544755, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.02781081199646, "global_step": 544756, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.078561305999756, "global_step": 544757, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0612382888793945, "global_step": 544758, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.045001983642578, "global_step": 544759, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9335646629333496, "global_step": 544760, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.065035581588745, "global_step": 544761, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0026068687438965, "global_step": 544762, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.023134708404541, "global_step": 544763, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.027061939239502, "global_step": 544764, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0488994121551514, "global_step": 544765, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0250697135925293, "global_step": 544766, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.045121908187866, "global_step": 544767, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.991467833518982, "global_step": 544768, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0062804222106934, "global_step": 544769, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9648537635803223, "global_step": 544770, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.975877285003662, "global_step": 544771, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0215976238250732, "global_step": 544772, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9999605417251587, "global_step": 544773, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0012221336364746, "global_step": 544774, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.042855978012085, "global_step": 544775, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9313675165176392, "global_step": 544776, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.003366470336914, "global_step": 544777, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.073897123336792, "global_step": 544778, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0380442142486572, "global_step": 544779, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0841383934020996, "global_step": 544780, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.027545690536499, "global_step": 544781, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0094997882843018, "global_step": 544782, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0292046070098877, "global_step": 544783, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9460276365280151, "global_step": 544784, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.997517466545105, "global_step": 544785, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.000755786895752, "global_step": 544786, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0721399784088135, "global_step": 544787, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0517947673797607, "global_step": 544788, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0445640087127686, "global_step": 544789, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0013248920440674, "global_step": 544790, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.991629719734192, "global_step": 544791, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9067445993423462, "global_step": 544792, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.946353554725647, "global_step": 544793, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1065845489501953, "global_step": 544794, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.011237621307373, "global_step": 544795, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0672876834869385, "global_step": 544796, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0549674034118652, "global_step": 544797, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0052337646484375, "global_step": 544798, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1088709831237793, "global_step": 544799, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9766961336135864, "global_step": 544800, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9993103742599487, "global_step": 544801, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9904783964157104, "global_step": 544802, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9658416509628296, "global_step": 544803, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9986040592193604, "global_step": 544804, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9765334129333496, "global_step": 544805, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0099613666534424, "global_step": 544806, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9266412258148193, "global_step": 544807, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9917234182357788, "global_step": 544808, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.112215518951416, "global_step": 544809, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0170207023620605, "global_step": 544810, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0751266479492188, "global_step": 544811, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0105016231536865, "global_step": 544812, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0267176628112793, "global_step": 544813, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.003769636154175, "global_step": 544814, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9454504251480103, "global_step": 544815, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.961951732635498, "global_step": 544816, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1159536838531494, "global_step": 544817, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0365521907806396, "global_step": 544818, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.059206485748291, "global_step": 544819, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0336883068084717, "global_step": 544820, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0860843658447266, "global_step": 544821, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0283358097076416, "global_step": 544822, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0252084732055664, "global_step": 544823, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9054386615753174, "global_step": 544824, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9875144958496094, "global_step": 544825, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9422845840454102, "global_step": 544826, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0475287437438965, "global_step": 544827, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9689486026763916, "global_step": 544828, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0244736671447754, "global_step": 544829, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9759143590927124, "global_step": 544830, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.022050380706787, "global_step": 544831, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.035092830657959, "global_step": 544832, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.082892417907715, "global_step": 544833, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1082489490509033, "global_step": 544834, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9820504188537598, "global_step": 544835, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.059041976928711, "global_step": 544836, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.92473566532135, "global_step": 544837, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.000662088394165, "global_step": 544838, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.068639039993286, "global_step": 544839, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9661438465118408, "global_step": 544840, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0673370361328125, "global_step": 544841, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.008155345916748, "global_step": 544842, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0294570922851562, "global_step": 544843, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.955701470375061, "global_step": 544844, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0279600620269775, "global_step": 544845, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0093507766723633, "global_step": 544846, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0093493461608887, "global_step": 544847, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0071353912353516, "global_step": 544848, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.088454484939575, "global_step": 544849, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.032895565032959, "global_step": 544850, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0174763202667236, "global_step": 544851, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.061185359954834, "global_step": 544852, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.079906702041626, "global_step": 544853, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0494940280914307, "global_step": 544854, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9604504108428955, "global_step": 544855, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0620944499969482, "global_step": 544856, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0859923362731934, "global_step": 544857, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.038578748703003, "global_step": 544858, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0329408645629883, "global_step": 544859, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.958571195602417, "global_step": 544860, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0751428604125977, "global_step": 544861, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.972508430480957, "global_step": 544862, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9624141454696655, "global_step": 544863, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.064018964767456, "global_step": 544864, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0628838539123535, "global_step": 544865, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9214026927947998, "global_step": 544866, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0226545333862305, "global_step": 544867, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0046515464782715, "global_step": 544868, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.013792037963867, "global_step": 544869, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.044572114944458, "global_step": 544870, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9966790676116943, "global_step": 544871, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.036832094192505, "global_step": 544872, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0345418453216553, "global_step": 544873, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.8979929685592651, "global_step": 544874, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0285212993621826, "global_step": 544875, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9984947443008423, "global_step": 544876, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0922274589538574, "global_step": 544877, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.990609049797058, "global_step": 544878, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.048095226287842, "global_step": 544879, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.041214942932129, "global_step": 544880, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9921098947525024, "global_step": 544881, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.043403148651123, "global_step": 544882, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.978155493736267, "global_step": 544883, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0333876609802246, "global_step": 544884, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.063840866088867, "global_step": 544885, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0663042068481445, "global_step": 544886, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9560164213180542, "global_step": 544887, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1335506439208984, "global_step": 544888, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0349268913269043, "global_step": 544889, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9837737083435059, "global_step": 544890, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.019519805908203, "global_step": 544891, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.07377028465271, "global_step": 544892, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1024529933929443, "global_step": 544893, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0130677223205566, "global_step": 544894, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.05359148979187, "global_step": 544895, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.037992238998413, "global_step": 544896, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.033198595046997, "global_step": 544897, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.980488657951355, "global_step": 544898, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.077845573425293, "global_step": 544899, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.041995048522949, "global_step": 544900, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0384762287139893, "global_step": 544901, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0315818786621094, "global_step": 544902, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0686142444610596, "global_step": 544903, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0201847553253174, "global_step": 544904, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0540854930877686, "global_step": 544905, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9832075834274292, "global_step": 544906, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0343427658081055, "global_step": 544907, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0343291759490967, "global_step": 544908, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0866317749023438, "global_step": 544909, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0910682678222656, "global_step": 544910, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0408308506011963, "global_step": 544911, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9899351596832275, "global_step": 544912, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0214266777038574, "global_step": 544913, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9715725183486938, "global_step": 544914, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9589612483978271, "global_step": 544915, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.093817949295044, "global_step": 544916, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0674855709075928, "global_step": 544917, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9896210432052612, "global_step": 544918, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.009010076522827, "global_step": 544919, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0376474857330322, "global_step": 544920, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.100572109222412, "global_step": 544921, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0209059715270996, "global_step": 544922, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9982916116714478, "global_step": 544923, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9770073890686035, "global_step": 544924, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.051063060760498, "global_step": 544925, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.065892219543457, "global_step": 544926, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0495123863220215, "global_step": 544927, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.095015525817871, "global_step": 544928, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9937900304794312, "global_step": 544929, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.029250383377075, "global_step": 544930, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1802754402160645, "global_step": 544931, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.034987688064575, "global_step": 544932, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9798845052719116, "global_step": 544933, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.081366777420044, "global_step": 544934, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.001314878463745, "global_step": 544935, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.159313201904297, "global_step": 544936, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.035804510116577, "global_step": 544937, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9415404796600342, "global_step": 544938, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.044978618621826, "global_step": 544939, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1975748538970947, "global_step": 544940, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.067012071609497, "global_step": 544941, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9675899744033813, "global_step": 544942, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.030367374420166, "global_step": 544943, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0871453285217285, "global_step": 544944, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.993282437324524, "global_step": 544945, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0555942058563232, "global_step": 544946, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.012366533279419, "global_step": 544947, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0469391345977783, "global_step": 544948, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0234830379486084, "global_step": 544949, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0429680347442627, "global_step": 544950, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.021742105484009, "global_step": 544951, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9534823894500732, "global_step": 544952, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0122904777526855, "global_step": 544953, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.058255195617676, "global_step": 544954, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9415395259857178, "global_step": 544955, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0511231422424316, "global_step": 544956, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0307083129882812, "global_step": 544957, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0836455821990967, "global_step": 544958, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.101841926574707, "global_step": 544959, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9515010118484497, "global_step": 544960, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9937992095947266, "global_step": 544961, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.097801685333252, "global_step": 544962, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1327340602874756, "global_step": 544963, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9680125713348389, "global_step": 544964, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.872775912284851, "global_step": 544965, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.044825315475464, "global_step": 544966, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0339088439941406, "global_step": 544967, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0279994010925293, "global_step": 544968, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9915844202041626, "global_step": 544969, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0352189540863037, "global_step": 544970, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9605762958526611, "global_step": 544971, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.984500527381897, "global_step": 544972, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9936562776565552, "global_step": 544973, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9809199571609497, "global_step": 544974, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9888969659805298, "global_step": 544975, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9825387001037598, "global_step": 544976, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9644291400909424, "global_step": 544977, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0642287731170654, "global_step": 544978, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0356285572052, "global_step": 544979, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9611845016479492, "global_step": 544980, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0608270168304443, "global_step": 544981, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.030210018157959, "global_step": 544982, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.03104829788208, "global_step": 544983, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.081808567047119, "global_step": 544984, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9569838047027588, "global_step": 544985, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0669195652008057, "global_step": 544986, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.055161237716675, "global_step": 544987, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0384836196899414, "global_step": 544988, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9771419763565063, "global_step": 544989, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.042768955230713, "global_step": 544990, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9626827239990234, "global_step": 544991, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9545663595199585, "global_step": 544992, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9962971210479736, "global_step": 544993, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0678493976593018, "global_step": 544994, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.040045976638794, "global_step": 544995, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0245144367218018, "global_step": 544996, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9802181720733643, "global_step": 544997, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0143985748291016, "global_step": 544998, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.011882781982422, "global_step": 544999, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.118708848953247, "global_step": 545000, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0340237617492676, "global_step": 545001, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9787940979003906, "global_step": 545002, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0851547718048096, "global_step": 545003, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9702811241149902, "global_step": 545004, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.015094518661499, "global_step": 545005, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.043429136276245, "global_step": 545006, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9822441339492798, "global_step": 545007, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.992286205291748, "global_step": 545008, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.143145799636841, "global_step": 545009, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.967592477798462, "global_step": 545010, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9603208303451538, "global_step": 545011, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0943899154663086, "global_step": 545012, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9898425340652466, "global_step": 545013, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9683181047439575, "global_step": 545014, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9575622081756592, "global_step": 545015, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0916035175323486, "global_step": 545016, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.012957811355591, "global_step": 545017, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1258201599121094, "global_step": 545018, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9726791381835938, "global_step": 545019, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0272982120513916, "global_step": 545020, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.051654815673828, "global_step": 545021, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.091463327407837, "global_step": 545022, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0476434230804443, "global_step": 545023, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0826635360717773, "global_step": 545024, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.02190899848938, "global_step": 545025, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0947375297546387, "global_step": 545026, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0218868255615234, "global_step": 545027, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0551042556762695, "global_step": 545028, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.03952956199646, "global_step": 545029, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0954301357269287, "global_step": 545030, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0696921348571777, "global_step": 545031, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.969171404838562, "global_step": 545032, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0085654258728027, "global_step": 545033, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.043973445892334, "global_step": 545034, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0153284072875977, "global_step": 545035, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9363425970077515, "global_step": 545036, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0185158252716064, "global_step": 545037, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0063233375549316, "global_step": 545038, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.035653591156006, "global_step": 545039, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0468201637268066, "global_step": 545040, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1068613529205322, "global_step": 545041, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0434439182281494, "global_step": 545042, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0485286712646484, "global_step": 545043, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0140652656555176, "global_step": 545044, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0901072025299072, "global_step": 545045, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0134570598602295, "global_step": 545046, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0372259616851807, "global_step": 545047, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9671021699905396, "global_step": 545048, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0100510120391846, "global_step": 545049, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0555264949798584, "global_step": 545050, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.063260793685913, "global_step": 545051, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0176334381103516, "global_step": 545052, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.110541343688965, "global_step": 545053, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0615458488464355, "global_step": 545054, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.023106098175049, "global_step": 545055, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.04494309425354, "global_step": 545056, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0335500240325928, "global_step": 545057, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.974578619003296, "global_step": 545058, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9695594310760498, "global_step": 545059, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.00722074508667, "global_step": 545060, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9429028034210205, "global_step": 545061, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.012972831726074, "global_step": 545062, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0978171825408936, "global_step": 545063, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9967529773712158, "global_step": 545064, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1259334087371826, "global_step": 545065, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.003751754760742, "global_step": 545066, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9918510913848877, "global_step": 545067, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0439088344573975, "global_step": 545068, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0886740684509277, "global_step": 545069, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0745043754577637, "global_step": 545070, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.014955997467041, "global_step": 545071, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0747411251068115, "global_step": 545072, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0297279357910156, "global_step": 545073, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.132175922393799, "global_step": 545074, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.15163254737854, "global_step": 545075, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.047424077987671, "global_step": 545076, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0379891395568848, "global_step": 545077, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0099825859069824, "global_step": 545078, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.037754774093628, "global_step": 545079, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0574557781219482, "global_step": 545080, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.091996669769287, "global_step": 545081, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.031553268432617, "global_step": 545082, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0042030811309814, "global_step": 545083, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.015549898147583, "global_step": 545084, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9771097898483276, "global_step": 545085, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.037139415740967, "global_step": 545086, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.985450029373169, "global_step": 545087, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0553293228149414, "global_step": 545088, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0249152183532715, "global_step": 545089, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.00055193901062, "global_step": 545090, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0510191917419434, "global_step": 545091, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0488438606262207, "global_step": 545092, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.003293514251709, "global_step": 545093, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0498032569885254, "global_step": 545094, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0373177528381348, "global_step": 545095, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9765427112579346, "global_step": 545096, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9858453273773193, "global_step": 545097, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9753680229187012, "global_step": 545098, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0413804054260254, "global_step": 545099, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0056352615356445, "global_step": 545100, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.118048906326294, "global_step": 545101, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0373337268829346, "global_step": 545102, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.083293914794922, "global_step": 545103, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.061316728591919, "global_step": 545104, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.043067455291748, "global_step": 545105, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1494030952453613, "global_step": 545106, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0910792350769043, "global_step": 545107, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0876893997192383, "global_step": 545108, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0639679431915283, "global_step": 545109, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0147671699523926, "global_step": 545110, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9952110052108765, "global_step": 545111, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.949743628501892, "global_step": 545112, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9919698238372803, "global_step": 545113, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9842422008514404, "global_step": 545114, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.013617992401123, "global_step": 545115, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0087625980377197, "global_step": 545116, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0968234539031982, "global_step": 545117, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.076983690261841, "global_step": 545118, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.066678285598755, "global_step": 545119, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.076587438583374, "global_step": 545120, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.003415584564209, "global_step": 545121, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.104442596435547, "global_step": 545122, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0611026287078857, "global_step": 545123, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9956233501434326, "global_step": 545124, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9540494680404663, "global_step": 545125, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.022639751434326, "global_step": 545126, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0046894550323486, "global_step": 545127, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.011791706085205, "global_step": 545128, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0444176197052, "global_step": 545129, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.036931276321411, "global_step": 545130, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.980233907699585, "global_step": 545131, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.966793179512024, "global_step": 545132, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.029528856277466, "global_step": 545133, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1033382415771484, "global_step": 545134, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.000044345855713, "global_step": 545135, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0142428874969482, "global_step": 545136, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0853543281555176, "global_step": 545137, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0348191261291504, "global_step": 545138, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9951233863830566, "global_step": 545139, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.096235513687134, "global_step": 545140, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.066521644592285, "global_step": 545141, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0412981510162354, "global_step": 545142, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0841572284698486, "global_step": 545143, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0289618968963623, "global_step": 545144, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.02378511428833, "global_step": 545145, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.109111785888672, "global_step": 545146, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.077775239944458, "global_step": 545147, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9958314895629883, "global_step": 545148, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9561253786087036, "global_step": 545149, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.00840425491333, "global_step": 545150, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.062084197998047, "global_step": 545151, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.033700704574585, "global_step": 545152, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0862326622009277, "global_step": 545153, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.08528995513916, "global_step": 545154, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.048179864883423, "global_step": 545155, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.039463520050049, "global_step": 545156, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.070657253265381, "global_step": 545157, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.976769208908081, "global_step": 545158, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0663719177246094, "global_step": 545159, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.056589365005493, "global_step": 545160, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.078141689300537, "global_step": 545161, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0346202850341797, "global_step": 545162, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0317304134368896, "global_step": 545163, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.094787120819092, "global_step": 545164, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9870330095291138, "global_step": 545165, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0438215732574463, "global_step": 545166, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0740981101989746, "global_step": 545167, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.024270534515381, "global_step": 545168, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9612497091293335, "global_step": 545169, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.996406078338623, "global_step": 545170, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.947352647781372, "global_step": 545171, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0728886127471924, "global_step": 545172, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.100893259048462, "global_step": 545173, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.963922142982483, "global_step": 545174, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0097198486328125, "global_step": 545175, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.021790027618408, "global_step": 545176, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1614224910736084, "global_step": 545177, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0328259468078613, "global_step": 545178, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0312201976776123, "global_step": 545179, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0684456825256348, "global_step": 545180, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9848390817642212, "global_step": 545181, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.015779972076416, "global_step": 545182, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.033454179763794, "global_step": 545183, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0424563884735107, "global_step": 545184, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0933313369750977, "global_step": 545185, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.054610013961792, "global_step": 545186, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.007836103439331, "global_step": 545187, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.042618751525879, "global_step": 545188, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0699498653411865, "global_step": 545189, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9626399278640747, "global_step": 545190, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.086435556411743, "global_step": 545191, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0252749919891357, "global_step": 545192, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1204113960266113, "global_step": 545193, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0831642150878906, "global_step": 545194, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.98178231716156, "global_step": 545195, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0572049617767334, "global_step": 545196, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.025343179702759, "global_step": 545197, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9818187952041626, "global_step": 545198, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0264883041381836, "global_step": 545199, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.99681556224823, "global_step": 545200, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9948631525039673, "global_step": 545201, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0415189266204834, "global_step": 545202, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9742460250854492, "global_step": 545203, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.979189157485962, "global_step": 545204, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.136507272720337, "global_step": 545205, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0475780963897705, "global_step": 545206, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.067169427871704, "global_step": 545207, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9832227230072021, "global_step": 545208, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0076420307159424, "global_step": 545209, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9347267150878906, "global_step": 545210, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0059714317321777, "global_step": 545211, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9702837467193604, "global_step": 545212, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0838534832000732, "global_step": 545213, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0383176803588867, "global_step": 545214, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.100700616836548, "global_step": 545215, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0450329780578613, "global_step": 545216, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.039447546005249, "global_step": 545217, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0395402908325195, "global_step": 545218, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0274181365966797, "global_step": 545219, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.028930187225342, "global_step": 545220, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.059016227722168, "global_step": 545221, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.033362627029419, "global_step": 545222, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9597034454345703, "global_step": 545223, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9469835758209229, "global_step": 545224, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.052400827407837, "global_step": 545225, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9890741109848022, "global_step": 545226, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1361429691314697, "global_step": 545227, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1209352016448975, "global_step": 545228, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0115904808044434, "global_step": 545229, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9980472326278687, "global_step": 545230, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0493087768554688, "global_step": 545231, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.050220251083374, "global_step": 545232, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0032763481140137, "global_step": 545233, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0334627628326416, "global_step": 545234, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.05717396736145, "global_step": 545235, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0820207595825195, "global_step": 545236, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.088242530822754, "global_step": 545237, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0115787982940674, "global_step": 545238, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1246399879455566, "global_step": 545239, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9741122722625732, "global_step": 545240, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0385730266571045, "global_step": 545241, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0646262168884277, "global_step": 545242, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0452895164489746, "global_step": 545243, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9844955205917358, "global_step": 545244, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.018470525741577, "global_step": 545245, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0001978874206543, "global_step": 545246, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.019632577896118, "global_step": 545247, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9529249668121338, "global_step": 545248, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.078700304031372, "global_step": 545249, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.033582925796509, "global_step": 545250, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0937318801879883, "global_step": 545251, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9781112670898438, "global_step": 545252, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0507891178131104, "global_step": 545253, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0720279216766357, "global_step": 545254, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.03251576423645, "global_step": 545255, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0325992107391357, "global_step": 545256, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0567731857299805, "global_step": 545257, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0244088172912598, "global_step": 545258, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.046257495880127, "global_step": 545259, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0833921432495117, "global_step": 545260, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.123213052749634, "global_step": 545261, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.045119047164917, "global_step": 545262, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1515018939971924, "global_step": 545263, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0503454208374023, "global_step": 545264, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.11609148979187, "global_step": 545265, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.064767837524414, "global_step": 545266, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0726499557495117, "global_step": 545267, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.104522466659546, "global_step": 545268, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0516626834869385, "global_step": 545269, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.020939350128174, "global_step": 545270, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0002052783966064, "global_step": 545271, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.023817300796509, "global_step": 545272, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.071099281311035, "global_step": 545273, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0496225357055664, "global_step": 545274, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.006889820098877, "global_step": 545275, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0605669021606445, "global_step": 545276, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.094621419906616, "global_step": 545277, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.97098970413208, "global_step": 545278, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.961748719215393, "global_step": 545279, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0373129844665527, "global_step": 545280, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.082796335220337, "global_step": 545281, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0581369400024414, "global_step": 545282, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.060206174850464, "global_step": 545283, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.069007158279419, "global_step": 545284, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.038972854614258, "global_step": 545285, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1518421173095703, "global_step": 545286, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0232748985290527, "global_step": 545287, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9701567888259888, "global_step": 545288, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9803736209869385, "global_step": 545289, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0380303859710693, "global_step": 545290, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0476906299591064, "global_step": 545291, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0125954151153564, "global_step": 545292, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.048558235168457, "global_step": 545293, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9372345209121704, "global_step": 545294, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9859238862991333, "global_step": 545295, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0745856761932373, "global_step": 545296, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9355934858322144, "global_step": 545297, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0402939319610596, "global_step": 545298, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0399467945098877, "global_step": 545299, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0199472904205322, "global_step": 545300, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.047461986541748, "global_step": 545301, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.098073720932007, "global_step": 545302, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0125272274017334, "global_step": 545303, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0394670963287354, "global_step": 545304, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.170619249343872, "global_step": 545305, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0311968326568604, "global_step": 545306, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.009107828140259, "global_step": 545307, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.000584840774536, "global_step": 545308, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0269501209259033, "global_step": 545309, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.02234148979187, "global_step": 545310, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0056867599487305, "global_step": 545311, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9569059610366821, "global_step": 545312, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0203664302825928, "global_step": 545313, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0583834648132324, "global_step": 545314, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.035954713821411, "global_step": 545315, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9859015941619873, "global_step": 545316, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.8996479511260986, "global_step": 545317, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.998839020729065, "global_step": 545318, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0122201442718506, "global_step": 545319, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9575895071029663, "global_step": 545320, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.110194206237793, "global_step": 545321, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9943532943725586, "global_step": 545322, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0417213439941406, "global_step": 545323, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.036045551300049, "global_step": 545324, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0251946449279785, "global_step": 545325, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.123551607131958, "global_step": 545326, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0672285556793213, "global_step": 545327, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1277246475219727, "global_step": 545328, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0746989250183105, "global_step": 545329, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0757060050964355, "global_step": 545330, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9920190572738647, "global_step": 545331, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0060813426971436, "global_step": 545332, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.017242193222046, "global_step": 545333, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1005849838256836, "global_step": 545334, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1007304191589355, "global_step": 545335, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9904701709747314, "global_step": 545336, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0119705200195312, "global_step": 545337, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0916588306427, "global_step": 545338, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0559017658233643, "global_step": 545339, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9828523397445679, "global_step": 545340, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0204269886016846, "global_step": 545341, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9808241128921509, "global_step": 545342, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0574803352355957, "global_step": 545343, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0078747272491455, "global_step": 545344, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.089560031890869, "global_step": 545345, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0004894733428955, "global_step": 545346, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9732019901275635, "global_step": 545347, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9919464588165283, "global_step": 545348, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.044152021408081, "global_step": 545349, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.030296802520752, "global_step": 545350, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.02531361579895, "global_step": 545351, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1324362754821777, "global_step": 545352, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0172886848449707, "global_step": 545353, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0190470218658447, "global_step": 545354, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.126171350479126, "global_step": 545355, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0766806602478027, "global_step": 545356, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.005044460296631, "global_step": 545357, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.039496421813965, "global_step": 545358, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.036884307861328, "global_step": 545359, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.959694743156433, "global_step": 545360, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0546634197235107, "global_step": 545361, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.012498378753662, "global_step": 545362, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.006493091583252, "global_step": 545363, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1009347438812256, "global_step": 545364, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.030000686645508, "global_step": 545365, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.090695858001709, "global_step": 545366, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1139540672302246, "global_step": 545367, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.060337781906128, "global_step": 545368, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9993869066238403, "global_step": 545369, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.059237241744995, "global_step": 545370, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0373594760894775, "global_step": 545371, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.025186061859131, "global_step": 545372, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0291073322296143, "global_step": 545373, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.009303569793701, "global_step": 545374, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1070311069488525, "global_step": 545375, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.061441659927368, "global_step": 545376, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0362794399261475, "global_step": 545377, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9992170333862305, "global_step": 545378, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.030381441116333, "global_step": 545379, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0365946292877197, "global_step": 545380, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9805680513381958, "global_step": 545381, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.975364327430725, "global_step": 545382, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.07201886177063, "global_step": 545383, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.977018117904663, "global_step": 545384, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0714006423950195, "global_step": 545385, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9642181396484375, "global_step": 545386, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.058861017227173, "global_step": 545387, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.142312526702881, "global_step": 545388, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0402679443359375, "global_step": 545389, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9874348640441895, "global_step": 545390, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.022477626800537, "global_step": 545391, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0653235912323, "global_step": 545392, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.012650489807129, "global_step": 545393, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0316030979156494, "global_step": 545394, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0279688835144043, "global_step": 545395, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9785473346710205, "global_step": 545396, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.00998854637146, "global_step": 545397, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0034372806549072, "global_step": 545398, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0277459621429443, "global_step": 545399, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0456230640411377, "global_step": 545400, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1473405361175537, "global_step": 545401, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.012540817260742, "global_step": 545402, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0769309997558594, "global_step": 545403, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0748279094696045, "global_step": 545404, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9661844968795776, "global_step": 545405, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.009817123413086, "global_step": 545406, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0496838092803955, "global_step": 545407, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.042733669281006, "global_step": 545408, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0642077922821045, "global_step": 545409, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9931907653808594, "global_step": 545410, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9371109008789062, "global_step": 545411, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.981439232826233, "global_step": 545412, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.006012201309204, "global_step": 545413, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0582633018493652, "global_step": 545414, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.004861354827881, "global_step": 545415, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0845396518707275, "global_step": 545416, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.98795747756958, "global_step": 545417, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.970259666442871, "global_step": 545418, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9739423990249634, "global_step": 545419, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0759317874908447, "global_step": 545420, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9759565591812134, "global_step": 545421, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0947043895721436, "global_step": 545422, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0212230682373047, "global_step": 545423, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9959858655929565, "global_step": 545424, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.056018590927124, "global_step": 545425, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9786916971206665, "global_step": 545426, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9949473142623901, "global_step": 545427, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1310455799102783, "global_step": 545428, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0675151348114014, "global_step": 545429, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1337811946868896, "global_step": 545430, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0779991149902344, "global_step": 545431, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9687591791152954, "global_step": 545432, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0042827129364014, "global_step": 545433, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0385241508483887, "global_step": 545434, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.100522756576538, "global_step": 545435, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0549566745758057, "global_step": 545436, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9927877187728882, "global_step": 545437, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.07820725440979, "global_step": 545438, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0434131622314453, "global_step": 545439, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0583302974700928, "global_step": 545440, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.025050401687622, "global_step": 545441, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0000600814819336, "global_step": 545442, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.02522611618042, "global_step": 545443, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0369367599487305, "global_step": 545444, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.046372652053833, "global_step": 545445, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.036928176879883, "global_step": 545446, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.005190134048462, "global_step": 545447, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.056302309036255, "global_step": 545448, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.002911329269409, "global_step": 545449, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.022672176361084, "global_step": 545450, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0605785846710205, "global_step": 545451, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0169267654418945, "global_step": 545452, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0362846851348877, "global_step": 545453, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0472326278686523, "global_step": 545454, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.057398557662964, "global_step": 545455, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.08212947845459, "global_step": 545456, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9967135190963745, "global_step": 545457, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0694901943206787, "global_step": 545458, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.12423038482666, "global_step": 545459, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0469088554382324, "global_step": 545460, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.984509825706482, "global_step": 545461, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0110602378845215, "global_step": 545462, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0247962474823, "global_step": 545463, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0113611221313477, "global_step": 545464, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.05100417137146, "global_step": 545465, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.00250506401062, "global_step": 545466, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1296603679656982, "global_step": 545467, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0708351135253906, "global_step": 545468, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.986952304840088, "global_step": 545469, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0183165073394775, "global_step": 545470, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.041001081466675, "global_step": 545471, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.006244659423828, "global_step": 545472, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.992021083831787, "global_step": 545473, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.033284902572632, "global_step": 545474, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.012075901031494, "global_step": 545475, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.007158041000366, "global_step": 545476, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.058666229248047, "global_step": 545477, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.016542911529541, "global_step": 545478, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1766111850738525, "global_step": 545479, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.985067367553711, "global_step": 545480, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0423266887664795, "global_step": 545481, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.039883852005005, "global_step": 545482, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.093249797821045, "global_step": 545483, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0452284812927246, "global_step": 545484, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.074781656265259, "global_step": 545485, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.074660062789917, "global_step": 545486, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1355741024017334, "global_step": 545487, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.009208917617798, "global_step": 545488, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0664727687835693, "global_step": 545489, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0691449642181396, "global_step": 545490, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0738513469696045, "global_step": 545491, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9817239046096802, "global_step": 545492, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.085958480834961, "global_step": 545493, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0071966648101807, "global_step": 545494, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0330734252929688, "global_step": 545495, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0058319568634033, "global_step": 545496, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9961880445480347, "global_step": 545497, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0172641277313232, "global_step": 545498, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.989310622215271, "global_step": 545499, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.01155424118042, "global_step": 545500, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9733625650405884, "global_step": 545501, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0426812171936035, "global_step": 545502, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0186119079589844, "global_step": 545503, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0757977962493896, "global_step": 545504, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0781967639923096, "global_step": 545505, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0188815593719482, "global_step": 545506, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1266391277313232, "global_step": 545507, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1047286987304688, "global_step": 545508, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0530364513397217, "global_step": 545509, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9921625852584839, "global_step": 545510, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.101574659347534, "global_step": 545511, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0998737812042236, "global_step": 545512, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0863687992095947, "global_step": 545513, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0289435386657715, "global_step": 545514, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.015562057495117, "global_step": 545515, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.00829815864563, "global_step": 545516, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.01712965965271, "global_step": 545517, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9673471450805664, "global_step": 545518, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.062209129333496, "global_step": 545519, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0596461296081543, "global_step": 545520, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.094043254852295, "global_step": 545521, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.00713849067688, "global_step": 545522, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9845867156982422, "global_step": 545523, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0229716300964355, "global_step": 545524, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0923683643341064, "global_step": 545525, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0634238719940186, "global_step": 545526, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9683843851089478, "global_step": 545527, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.029846429824829, "global_step": 545528, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.070279836654663, "global_step": 545529, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.062710762023926, "global_step": 545530, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.004232406616211, "global_step": 545531, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.024392604827881, "global_step": 545532, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.960195779800415, "global_step": 545533, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0064892768859863, "global_step": 545534, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0767107009887695, "global_step": 545535, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0220978260040283, "global_step": 545536, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.091545820236206, "global_step": 545537, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.069324493408203, "global_step": 545538, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0464305877685547, "global_step": 545539, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0931754112243652, "global_step": 545540, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.099428176879883, "global_step": 545541, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0714871883392334, "global_step": 545542, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.142120838165283, "global_step": 545543, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.092656373977661, "global_step": 545544, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9836902618408203, "global_step": 545545, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0862481594085693, "global_step": 545546, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9927667379379272, "global_step": 545547, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0197107791900635, "global_step": 545548, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9853088855743408, "global_step": 545549, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.991357445716858, "global_step": 545550, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0288302898406982, "global_step": 545551, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.021589756011963, "global_step": 545552, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9994245767593384, "global_step": 545553, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0980961322784424, "global_step": 545554, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9707326889038086, "global_step": 545555, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0248897075653076, "global_step": 545556, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.107729196548462, "global_step": 545557, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.075324773788452, "global_step": 545558, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.046616315841675, "global_step": 545559, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0349769592285156, "global_step": 545560, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0344486236572266, "global_step": 545561, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1449646949768066, "global_step": 545562, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.989699125289917, "global_step": 545563, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9673343896865845, "global_step": 545564, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1682751178741455, "global_step": 545565, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0294599533081055, "global_step": 545566, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9825884103775024, "global_step": 545567, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9266211986541748, "global_step": 545568, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.027399778366089, "global_step": 545569, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.163490056991577, "global_step": 545570, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.059882879257202, "global_step": 545571, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9905215501785278, "global_step": 545572, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0441861152648926, "global_step": 545573, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.958378553390503, "global_step": 545574, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0196592807769775, "global_step": 545575, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.042710065841675, "global_step": 545576, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.038867473602295, "global_step": 545577, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.064938545227051, "global_step": 545578, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0092732906341553, "global_step": 545579, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.926568627357483, "global_step": 545580, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9400079250335693, "global_step": 545581, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.043672561645508, "global_step": 545582, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.070971965789795, "global_step": 545583, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9991214275360107, "global_step": 545584, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.020251750946045, "global_step": 545585, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.101546049118042, "global_step": 545586, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9352489709854126, "global_step": 545587, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9970661401748657, "global_step": 545588, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9851833581924438, "global_step": 545589, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9729350805282593, "global_step": 545590, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0157220363616943, "global_step": 545591, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9975523948669434, "global_step": 545592, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0321123600006104, "global_step": 545593, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1510980129241943, "global_step": 545594, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1391093730926514, "global_step": 545595, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0530717372894287, "global_step": 545596, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.155048131942749, "global_step": 545597, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0733935832977295, "global_step": 545598, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9877889156341553, "global_step": 545599, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0797927379608154, "global_step": 545600, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0479676723480225, "global_step": 545601, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0625393390655518, "global_step": 545602, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.085268020629883, "global_step": 545603, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0433974266052246, "global_step": 545604, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.018371105194092, "global_step": 545605, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0559310913085938, "global_step": 545606, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0699057579040527, "global_step": 545607, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9753170013427734, "global_step": 545608, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9968013763427734, "global_step": 545609, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0829882621765137, "global_step": 545610, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.980587363243103, "global_step": 545611, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.025019407272339, "global_step": 545612, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.081312656402588, "global_step": 545613, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.986627221107483, "global_step": 545614, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.084930896759033, "global_step": 545615, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1353847980499268, "global_step": 545616, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9857946634292603, "global_step": 545617, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.058729887008667, "global_step": 545618, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9402621984481812, "global_step": 545619, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.054124355316162, "global_step": 545620, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.068281650543213, "global_step": 545621, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.000629425048828, "global_step": 545622, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.040574073791504, "global_step": 545623, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.11289381980896, "global_step": 545624, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9409964084625244, "global_step": 545625, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.043384552001953, "global_step": 545626, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.030484676361084, "global_step": 545627, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.113128185272217, "global_step": 545628, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.034438133239746, "global_step": 545629, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.057600736618042, "global_step": 545630, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.030052661895752, "global_step": 545631, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.123521089553833, "global_step": 545632, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.071697473526001, "global_step": 545633, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0808091163635254, "global_step": 545634, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.039275884628296, "global_step": 545635, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.057302236557007, "global_step": 545636, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.119246244430542, "global_step": 545637, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.053867816925049, "global_step": 545638, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.001014471054077, "global_step": 545639, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.01039981842041, "global_step": 545640, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9732283353805542, "global_step": 545641, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.054650068283081, "global_step": 545642, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.078848361968994, "global_step": 545643, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0791501998901367, "global_step": 545644, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.124347686767578, "global_step": 545645, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0031211376190186, "global_step": 545646, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.988181233406067, "global_step": 545647, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1054301261901855, "global_step": 545648, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0478835105895996, "global_step": 545649, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0123932361602783, "global_step": 545650, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.102648973464966, "global_step": 545651, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.012646436691284, "global_step": 545652, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0728771686553955, "global_step": 545653, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0493862628936768, "global_step": 545654, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.06046199798584, "global_step": 545655, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.065382480621338, "global_step": 545656, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0066890716552734, "global_step": 545657, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0653929710388184, "global_step": 545658, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0119528770446777, "global_step": 545659, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.1054866313934326, "global_step": 545660, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9867841005325317, "global_step": 545661, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0043976306915283, "global_step": 545662, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0014920234680176, "global_step": 545663, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.02988862991333, "global_step": 545664, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0820884704589844, "global_step": 545665, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0250353813171387, "global_step": 545666, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.95501708984375, "global_step": 545667, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.010765552520752, "global_step": 545668, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.981994867324829, "global_step": 545669, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0562312602996826, "global_step": 545670, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.120781660079956, "global_step": 545671, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0827507972717285, "global_step": 545672, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0034546852111816, "global_step": 545673, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0044784545898438, "global_step": 545674, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.025444269180298, "global_step": 545675, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.025826930999756, "global_step": 545676, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0543606281280518, "global_step": 545677, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.017000436782837, "global_step": 545678, "epoch": 912, "lr": 5e-05}
{"train_loss": 2.0334103107452393, "global_step": 545679, "epoch": 912, "lr": 5e-05}
{"train_loss": 1.9816137552261353, "global_step": 545680, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9947363138198853, "global_step": 545681, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0113279819488525, "global_step": 545682, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.062129497528076, "global_step": 545683, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.029432535171509, "global_step": 545684, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.030693769454956, "global_step": 545685, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9676862955093384, "global_step": 545686, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0195207595825195, "global_step": 545687, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.971599817276001, "global_step": 545688, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.10689640045166, "global_step": 545689, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0707783699035645, "global_step": 545690, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.006352424621582, "global_step": 545691, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.008770227432251, "global_step": 545692, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.00398325920105, "global_step": 545693, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9950779676437378, "global_step": 545694, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0184166431427, "global_step": 545695, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.016605854034424, "global_step": 545696, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9813562631607056, "global_step": 545697, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9595537185668945, "global_step": 545698, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.104417562484741, "global_step": 545699, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9371196031570435, "global_step": 545700, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9885375499725342, "global_step": 545701, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.032402276992798, "global_step": 545702, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9975240230560303, "global_step": 545703, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.033245801925659, "global_step": 545704, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9809727668762207, "global_step": 545705, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.004833459854126, "global_step": 545706, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0257763862609863, "global_step": 545707, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0293562412261963, "global_step": 545708, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0055038928985596, "global_step": 545709, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.019930362701416, "global_step": 545710, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9886301755905151, "global_step": 545711, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9205808639526367, "global_step": 545712, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.084777593612671, "global_step": 545713, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0002083778381348, "global_step": 545714, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.040217161178589, "global_step": 545715, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0001914501190186, "global_step": 545716, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9763911962509155, "global_step": 545717, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.978874683380127, "global_step": 545718, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0732009410858154, "global_step": 545719, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9442362785339355, "global_step": 545720, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.932220458984375, "global_step": 545721, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9850221872329712, "global_step": 545722, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1110987663269043, "global_step": 545723, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0503785610198975, "global_step": 545724, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.052530288696289, "global_step": 545725, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.037435293197632, "global_step": 545726, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0266172885894775, "global_step": 545727, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0614285469055176, "global_step": 545728, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.040600299835205, "global_step": 545729, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.011894464492798, "global_step": 545730, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.01879620552063, "global_step": 545731, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0856430530548096, "global_step": 545732, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9779235124588013, "global_step": 545733, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1261489391326904, "global_step": 545734, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0618300437927246, "global_step": 545735, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0418190956115723, "global_step": 545736, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.968444585800171, "global_step": 545737, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9659266471862793, "global_step": 545738, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0299272537231445, "global_step": 545739, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0808615684509277, "global_step": 545740, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.982043743133545, "global_step": 545741, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0708158016204834, "global_step": 545742, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0837268829345703, "global_step": 545743, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0212154388427734, "global_step": 545744, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0325427055358887, "global_step": 545745, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9944480657577515, "global_step": 545746, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.980180025100708, "global_step": 545747, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0007526874542236, "global_step": 545748, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.101658344268799, "global_step": 545749, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9893524646759033, "global_step": 545750, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0157902240753174, "global_step": 545751, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0728647708892822, "global_step": 545752, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.087601661682129, "global_step": 545753, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9499653577804565, "global_step": 545754, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1415576934814453, "global_step": 545755, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0692265033721924, "global_step": 545756, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0556936264038086, "global_step": 545757, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9925695657730103, "global_step": 545758, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0182385444641113, "global_step": 545759, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1050939559936523, "global_step": 545760, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9937390089035034, "global_step": 545761, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9552574157714844, "global_step": 545762, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9609816074371338, "global_step": 545763, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0613484382629395, "global_step": 545764, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9361313581466675, "global_step": 545765, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0018248558044434, "global_step": 545766, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0334620475769043, "global_step": 545767, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9722590446472168, "global_step": 545768, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.050905704498291, "global_step": 545769, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0365371704101562, "global_step": 545770, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.007509469985962, "global_step": 545771, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.044210195541382, "global_step": 545772, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.965401291847229, "global_step": 545773, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.068490505218506, "global_step": 545774, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.060077428817749, "global_step": 545775, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.097503185272217, "global_step": 545776, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1121435165405273, "global_step": 545777, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.052027702331543, "global_step": 545778, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.029235363006592, "global_step": 545779, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0044891834259033, "global_step": 545780, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0580475330352783, "global_step": 545781, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.101039171218872, "global_step": 545782, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9387197494506836, "global_step": 545783, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0050084590911865, "global_step": 545784, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0235934257507324, "global_step": 545785, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.059769630432129, "global_step": 545786, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.059279680252075, "global_step": 545787, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.032900333404541, "global_step": 545788, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0512139797210693, "global_step": 545789, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0417277812957764, "global_step": 545790, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1051268577575684, "global_step": 545791, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.076286792755127, "global_step": 545792, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0737650394439697, "global_step": 545793, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.061537265777588, "global_step": 545794, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0152807235717773, "global_step": 545795, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9460548162460327, "global_step": 545796, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0153727531433105, "global_step": 545797, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0378293991088867, "global_step": 545798, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.059739112854004, "global_step": 545799, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9817596673965454, "global_step": 545800, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.00838565826416, "global_step": 545801, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0860798358917236, "global_step": 545802, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.141251564025879, "global_step": 545803, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9658317565917969, "global_step": 545804, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9974236488342285, "global_step": 545805, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9997793436050415, "global_step": 545806, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0349886417388916, "global_step": 545807, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9919252395629883, "global_step": 545808, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.930948257446289, "global_step": 545809, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.050011157989502, "global_step": 545810, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9416892528533936, "global_step": 545811, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9755990505218506, "global_step": 545812, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.060391664505005, "global_step": 545813, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0174551010131836, "global_step": 545814, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.08833909034729, "global_step": 545815, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0332205295562744, "global_step": 545816, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.018904209136963, "global_step": 545817, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0248587131500244, "global_step": 545818, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.045623302459717, "global_step": 545819, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.08705735206604, "global_step": 545820, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.909275770187378, "global_step": 545821, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.04050612449646, "global_step": 545822, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9891602993011475, "global_step": 545823, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.037531852722168, "global_step": 545824, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0693440437316895, "global_step": 545825, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9758883714675903, "global_step": 545826, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9598695039749146, "global_step": 545827, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0703604221343994, "global_step": 545828, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9954848289489746, "global_step": 545829, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9631187915802002, "global_step": 545830, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9700918197631836, "global_step": 545831, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9761662483215332, "global_step": 545832, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0094833374023438, "global_step": 545833, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0005645751953125, "global_step": 545834, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0460047721862793, "global_step": 545835, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9852721691131592, "global_step": 545836, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.044163227081299, "global_step": 545837, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0029923915863037, "global_step": 545838, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0104176998138428, "global_step": 545839, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9842965602874756, "global_step": 545840, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9873155355453491, "global_step": 545841, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.003697395324707, "global_step": 545842, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9299359321594238, "global_step": 545843, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9944255352020264, "global_step": 545844, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.019859552383423, "global_step": 545845, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.057079553604126, "global_step": 545846, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0655739307403564, "global_step": 545847, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9558364152908325, "global_step": 545848, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.08709454536438, "global_step": 545849, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.034877300262451, "global_step": 545850, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9938023090362549, "global_step": 545851, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0149989128112793, "global_step": 545852, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0220143795013428, "global_step": 545853, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0731701850891113, "global_step": 545854, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0393435955047607, "global_step": 545855, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0285682678222656, "global_step": 545856, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.022793769836426, "global_step": 545857, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0197842121124268, "global_step": 545858, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0198569297790527, "global_step": 545859, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0490610599517822, "global_step": 545860, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9885339736938477, "global_step": 545861, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0388901233673096, "global_step": 545862, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.014946460723877, "global_step": 545863, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0007636547088623, "global_step": 545864, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0859649181365967, "global_step": 545865, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9982705116271973, "global_step": 545866, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.021021604537964, "global_step": 545867, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.053880214691162, "global_step": 545868, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0368237495422363, "global_step": 545869, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.064939498901367, "global_step": 545870, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0653390884399414, "global_step": 545871, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0108535289764404, "global_step": 545872, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0060505867004395, "global_step": 545873, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0397403240203857, "global_step": 545874, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9353911876678467, "global_step": 545875, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.028428792953491, "global_step": 545876, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0067291259765625, "global_step": 545877, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9673720598220825, "global_step": 545878, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0518856048583984, "global_step": 545879, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.030992031097412, "global_step": 545880, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.98308527469635, "global_step": 545881, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0956242084503174, "global_step": 545882, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1084353923797607, "global_step": 545883, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9930607080459595, "global_step": 545884, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0559165477752686, "global_step": 545885, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9449495077133179, "global_step": 545886, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9712989330291748, "global_step": 545887, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0488393306732178, "global_step": 545888, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.040170431137085, "global_step": 545889, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.014021396636963, "global_step": 545890, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.011949062347412, "global_step": 545891, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.034316301345825, "global_step": 545892, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0868024826049805, "global_step": 545893, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0426950454711914, "global_step": 545894, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.100834846496582, "global_step": 545895, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0784413814544678, "global_step": 545896, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0038557052612305, "global_step": 545897, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0732421875, "global_step": 545898, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.052274227142334, "global_step": 545899, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0203511714935303, "global_step": 545900, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0007588863372803, "global_step": 545901, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.086038589477539, "global_step": 545902, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0702860355377197, "global_step": 545903, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0468504428863525, "global_step": 545904, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9781689643859863, "global_step": 545905, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0368845462799072, "global_step": 545906, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0004336833953857, "global_step": 545907, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0391204357147217, "global_step": 545908, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.023118495941162, "global_step": 545909, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9930000305175781, "global_step": 545910, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.967207908630371, "global_step": 545911, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0343151092529297, "global_step": 545912, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9895625114440918, "global_step": 545913, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9758821725845337, "global_step": 545914, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0942039489746094, "global_step": 545915, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.994742751121521, "global_step": 545916, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0085721015930176, "global_step": 545917, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9359323978424072, "global_step": 545918, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0669286251068115, "global_step": 545919, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0275321006774902, "global_step": 545920, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0239667892456055, "global_step": 545921, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.153496503829956, "global_step": 545922, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.058465003967285, "global_step": 545923, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9762558937072754, "global_step": 545924, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0840561389923096, "global_step": 545925, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.015733480453491, "global_step": 545926, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9538559913635254, "global_step": 545927, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.002361536026001, "global_step": 545928, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0562636852264404, "global_step": 545929, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.015869617462158, "global_step": 545930, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.027137517929077, "global_step": 545931, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1119284629821777, "global_step": 545932, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.000035524368286, "global_step": 545933, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.033989191055298, "global_step": 545934, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.007603883743286, "global_step": 545935, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.130213499069214, "global_step": 545936, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0141372680664062, "global_step": 545937, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.033872365951538, "global_step": 545938, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.152956485748291, "global_step": 545939, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9769291877746582, "global_step": 545940, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.973276138305664, "global_step": 545941, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9604215621948242, "global_step": 545942, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.08417010307312, "global_step": 545943, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9582810401916504, "global_step": 545944, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.127351999282837, "global_step": 545945, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.066603422164917, "global_step": 545946, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.043686628341675, "global_step": 545947, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1145989894866943, "global_step": 545948, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0194292068481445, "global_step": 545949, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9678418636322021, "global_step": 545950, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0638718605041504, "global_step": 545951, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0288476943969727, "global_step": 545952, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0890793800354004, "global_step": 545953, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0116970539093018, "global_step": 545954, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9815329313278198, "global_step": 545955, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0897510051727295, "global_step": 545956, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.04852294921875, "global_step": 545957, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0115208625793457, "global_step": 545958, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.05391788482666, "global_step": 545959, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.037107467651367, "global_step": 545960, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.019343376159668, "global_step": 545961, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0814995765686035, "global_step": 545962, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.068211793899536, "global_step": 545963, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0041868686676025, "global_step": 545964, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9829542636871338, "global_step": 545965, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.027006149291992, "global_step": 545966, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9863914251327515, "global_step": 545967, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.066791534423828, "global_step": 545968, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.998473882675171, "global_step": 545969, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0137386322021484, "global_step": 545970, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0901691913604736, "global_step": 545971, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9286079406738281, "global_step": 545972, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9645649194717407, "global_step": 545973, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9705249071121216, "global_step": 545974, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.055100440979004, "global_step": 545975, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.073411226272583, "global_step": 545976, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0620694160461426, "global_step": 545977, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.07365345954895, "global_step": 545978, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0580201148986816, "global_step": 545979, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9737777709960938, "global_step": 545980, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0557518005371094, "global_step": 545981, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.06467604637146, "global_step": 545982, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9934197664260864, "global_step": 545983, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.040679693222046, "global_step": 545984, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.057967185974121, "global_step": 545985, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.057138204574585, "global_step": 545986, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9931670427322388, "global_step": 545987, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9742745161056519, "global_step": 545988, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0127978324890137, "global_step": 545989, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0650999546051025, "global_step": 545990, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0268609523773193, "global_step": 545991, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1055619716644287, "global_step": 545992, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0908303260803223, "global_step": 545993, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0027904510498047, "global_step": 545994, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0205025672912598, "global_step": 545995, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.080831527709961, "global_step": 545996, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0796637535095215, "global_step": 545997, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0192224979400635, "global_step": 545998, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.10274338722229, "global_step": 545999, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.022247552871704, "global_step": 546000, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0565552711486816, "global_step": 546001, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.031625270843506, "global_step": 546002, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0212810039520264, "global_step": 546003, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.08303165435791, "global_step": 546004, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0243706703186035, "global_step": 546005, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.055102825164795, "global_step": 546006, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0708370208740234, "global_step": 546007, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9443359375, "global_step": 546008, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0316522121429443, "global_step": 546009, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0997631549835205, "global_step": 546010, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0014655590057373, "global_step": 546011, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0213241577148438, "global_step": 546012, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.075578451156616, "global_step": 546013, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1481494903564453, "global_step": 546014, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9866952896118164, "global_step": 546015, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.003495931625366, "global_step": 546016, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9902409315109253, "global_step": 546017, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0674397945404053, "global_step": 546018, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0960514545440674, "global_step": 546019, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0863959789276123, "global_step": 546020, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.065457820892334, "global_step": 546021, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.015350103378296, "global_step": 546022, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0529353618621826, "global_step": 546023, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.060535430908203, "global_step": 546024, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.037105083465576, "global_step": 546025, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9594850540161133, "global_step": 546026, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0036892890930176, "global_step": 546027, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.941983699798584, "global_step": 546028, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0497894287109375, "global_step": 546029, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.083404064178467, "global_step": 546030, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0708160400390625, "global_step": 546031, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0200307369232178, "global_step": 546032, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9571869373321533, "global_step": 546033, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0323486328125, "global_step": 546034, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1101651191711426, "global_step": 546035, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1074094772338867, "global_step": 546036, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1376805305480957, "global_step": 546037, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9931830167770386, "global_step": 546038, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9595468044281006, "global_step": 546039, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0401158332824707, "global_step": 546040, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0326738357543945, "global_step": 546041, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9793040752410889, "global_step": 546042, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9702167510986328, "global_step": 546043, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9584063291549683, "global_step": 546044, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.063567638397217, "global_step": 546045, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.977136254310608, "global_step": 546046, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0453805923461914, "global_step": 546047, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0601723194122314, "global_step": 546048, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0185317993164062, "global_step": 546049, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.010714054107666, "global_step": 546050, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.011101484298706, "global_step": 546051, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0349297523498535, "global_step": 546052, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0017876625061035, "global_step": 546053, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9769126176834106, "global_step": 546054, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0045766830444336, "global_step": 546055, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.099048614501953, "global_step": 546056, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0002448558807373, "global_step": 546057, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9902684688568115, "global_step": 546058, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9584600925445557, "global_step": 546059, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9514344930648804, "global_step": 546060, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0864334106445312, "global_step": 546061, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0571234226226807, "global_step": 546062, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.018820285797119, "global_step": 546063, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0578863620758057, "global_step": 546064, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0696749687194824, "global_step": 546065, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0231571197509766, "global_step": 546066, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9827697277069092, "global_step": 546067, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0254385471343994, "global_step": 546068, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0467517375946045, "global_step": 546069, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9915144443511963, "global_step": 546070, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0703256130218506, "global_step": 546071, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.8883757591247559, "global_step": 546072, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9838756322860718, "global_step": 546073, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9733936786651611, "global_step": 546074, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.949866533279419, "global_step": 546075, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9929773807525635, "global_step": 546076, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.032068967819214, "global_step": 546077, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.02596378326416, "global_step": 546078, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.09033465385437, "global_step": 546079, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0196549892425537, "global_step": 546080, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.039314031600952, "global_step": 546081, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0658586025238037, "global_step": 546082, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9767186641693115, "global_step": 546083, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0573198795318604, "global_step": 546084, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0704894065856934, "global_step": 546085, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0574796199798584, "global_step": 546086, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9739947319030762, "global_step": 546087, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.068793773651123, "global_step": 546088, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.028182029724121, "global_step": 546089, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.128602981567383, "global_step": 546090, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.126246929168701, "global_step": 546091, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.095111608505249, "global_step": 546092, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0347766876220703, "global_step": 546093, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9523643255233765, "global_step": 546094, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0163300037384033, "global_step": 546095, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.005678415298462, "global_step": 546096, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0322983264923096, "global_step": 546097, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0839781761169434, "global_step": 546098, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.037562131881714, "global_step": 546099, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.000330686569214, "global_step": 546100, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.028949022293091, "global_step": 546101, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9692065715789795, "global_step": 546102, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9819424152374268, "global_step": 546103, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.054481267929077, "global_step": 546104, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.04630708694458, "global_step": 546105, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0467426776885986, "global_step": 546106, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.057358741760254, "global_step": 546107, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1061177253723145, "global_step": 546108, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.011728525161743, "global_step": 546109, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0789883136749268, "global_step": 546110, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.08547043800354, "global_step": 546111, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0728719234466553, "global_step": 546112, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0543243885040283, "global_step": 546113, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.044059991836548, "global_step": 546114, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0776023864746094, "global_step": 546115, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.05098032951355, "global_step": 546116, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9804308414459229, "global_step": 546117, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0115673542022705, "global_step": 546118, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.125868558883667, "global_step": 546119, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.120654344558716, "global_step": 546120, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9925737380981445, "global_step": 546121, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0093531608581543, "global_step": 546122, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9860759973526, "global_step": 546123, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.036196708679199, "global_step": 546124, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0567166805267334, "global_step": 546125, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9392950534820557, "global_step": 546126, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.091446876525879, "global_step": 546127, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1238532066345215, "global_step": 546128, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.088747024536133, "global_step": 546129, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.018404722213745, "global_step": 546130, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0583925247192383, "global_step": 546131, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.01654052734375, "global_step": 546132, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.063838005065918, "global_step": 546133, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0169899463653564, "global_step": 546134, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.061443328857422, "global_step": 546135, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0652425289154053, "global_step": 546136, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.930139183998108, "global_step": 546137, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.038670778274536, "global_step": 546138, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.072171926498413, "global_step": 546139, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0222549438476562, "global_step": 546140, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1025562286376953, "global_step": 546141, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0644521713256836, "global_step": 546142, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.067017078399658, "global_step": 546143, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0695130825042725, "global_step": 546144, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.077617645263672, "global_step": 546145, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.019852876663208, "global_step": 546146, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0786917209625244, "global_step": 546147, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0754687786102295, "global_step": 546148, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0451009273529053, "global_step": 546149, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0278985500335693, "global_step": 546150, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0371968746185303, "global_step": 546151, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1116368770599365, "global_step": 546152, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9251387119293213, "global_step": 546153, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.088040828704834, "global_step": 546154, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.948207139968872, "global_step": 546155, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0875930786132812, "global_step": 546156, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9770314693450928, "global_step": 546157, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9291259050369263, "global_step": 546158, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0481786727905273, "global_step": 546159, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0686392784118652, "global_step": 546160, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0431253910064697, "global_step": 546161, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.06675386428833, "global_step": 546162, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0913496017456055, "global_step": 546163, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1180012226104736, "global_step": 546164, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9766733646392822, "global_step": 546165, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9708561897277832, "global_step": 546166, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.009333848953247, "global_step": 546167, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0737268924713135, "global_step": 546168, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9730910062789917, "global_step": 546169, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1400046348571777, "global_step": 546170, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0512938499450684, "global_step": 546171, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.041973114013672, "global_step": 546172, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9897631406784058, "global_step": 546173, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.948071002960205, "global_step": 546174, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0842535495758057, "global_step": 546175, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.073215961456299, "global_step": 546176, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0721490383148193, "global_step": 546177, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9920322895050049, "global_step": 546178, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0581893920898438, "global_step": 546179, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.064082145690918, "global_step": 546180, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.047700881958008, "global_step": 546181, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.066649913787842, "global_step": 546182, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0250773429870605, "global_step": 546183, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.999545693397522, "global_step": 546184, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.161886215209961, "global_step": 546185, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1617393493652344, "global_step": 546186, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.052687406539917, "global_step": 546187, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9891690015792847, "global_step": 546188, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0803921222686768, "global_step": 546189, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.022429943084717, "global_step": 546190, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.029582977294922, "global_step": 546191, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0513229370117188, "global_step": 546192, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1143059730529785, "global_step": 546193, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.014266014099121, "global_step": 546194, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.03239107131958, "global_step": 546195, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.050238847732544, "global_step": 546196, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0279054641723633, "global_step": 546197, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0215823650360107, "global_step": 546198, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0521278381347656, "global_step": 546199, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9815798997879028, "global_step": 546200, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9994010925292969, "global_step": 546201, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1059954166412354, "global_step": 546202, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.029571056365967, "global_step": 546203, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0006165504455566, "global_step": 546204, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0368340015411377, "global_step": 546205, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.120837926864624, "global_step": 546206, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9941110610961914, "global_step": 546207, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.030813217163086, "global_step": 546208, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9901105165481567, "global_step": 546209, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.111696481704712, "global_step": 546210, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9685877561569214, "global_step": 546211, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.048650026321411, "global_step": 546212, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.108241319656372, "global_step": 546213, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.105973958969116, "global_step": 546214, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0620334148406982, "global_step": 546215, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9941744804382324, "global_step": 546216, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1016108989715576, "global_step": 546217, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.077563524246216, "global_step": 546218, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0703420639038086, "global_step": 546219, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9936598539352417, "global_step": 546220, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0632128715515137, "global_step": 546221, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0968165397644043, "global_step": 546222, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0435633659362793, "global_step": 546223, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0503101348876953, "global_step": 546224, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0743789672851562, "global_step": 546225, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.048004627227783, "global_step": 546226, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0598957538604736, "global_step": 546227, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.089402198791504, "global_step": 546228, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.054217576980591, "global_step": 546229, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0292751789093018, "global_step": 546230, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1092259883880615, "global_step": 546231, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0680735111236572, "global_step": 546232, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.957689642906189, "global_step": 546233, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0035500526428223, "global_step": 546234, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0399317741394043, "global_step": 546235, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0036513805389404, "global_step": 546236, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.948353886604309, "global_step": 546237, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0069239139556885, "global_step": 546238, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1214118003845215, "global_step": 546239, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0019190311431885, "global_step": 546240, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.080374002456665, "global_step": 546241, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9953871965408325, "global_step": 546242, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0150043964385986, "global_step": 546243, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.02582049369812, "global_step": 546244, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.985950231552124, "global_step": 546245, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.06602144241333, "global_step": 546246, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0795607566833496, "global_step": 546247, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0736782550811768, "global_step": 546248, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0757460594177246, "global_step": 546249, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.064584493637085, "global_step": 546250, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0093493461608887, "global_step": 546251, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1108875274658203, "global_step": 546252, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9664615392684937, "global_step": 546253, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9781184196472168, "global_step": 546254, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0687530040740967, "global_step": 546255, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0762228965759277, "global_step": 546256, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.099910259246826, "global_step": 546257, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0088322162628174, "global_step": 546258, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0275049209594727, "global_step": 546259, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.110747814178467, "global_step": 546260, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.031259775161743, "global_step": 546261, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.016738176345825, "global_step": 546262, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.056881904602051, "global_step": 546263, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.041628122329712, "global_step": 546264, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0287387371063232, "global_step": 546265, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0164272785186768, "global_step": 546266, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0189526081085205, "global_step": 546267, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.029878616333008, "global_step": 546268, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.100398302078247, "global_step": 546269, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1116201877593994, "global_step": 546270, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.979455590248108, "global_step": 546271, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0278313159942627, "global_step": 546272, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1047024726867676, "global_step": 546273, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9849576950073242, "global_step": 546274, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1212716102600098, "global_step": 546275, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0161826610565186, "global_step": 546276, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0196473598480225, "global_step": 546277, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.005632162094116, "global_step": 546278, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0818991661071777, "global_step": 546279, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0116467475891113, "global_step": 546280, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.980578064918518, "global_step": 546281, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0920536518096924, "global_step": 546282, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9397529363632202, "global_step": 546283, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0108609199523926, "global_step": 546284, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9832813739776611, "global_step": 546285, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0508341789245605, "global_step": 546286, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0100600719451904, "global_step": 546287, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9867686033248901, "global_step": 546288, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9872552156448364, "global_step": 546289, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0174460411071777, "global_step": 546290, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.04388427734375, "global_step": 546291, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0782437324523926, "global_step": 546292, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9993573427200317, "global_step": 546293, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.044949769973755, "global_step": 546294, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.091517686843872, "global_step": 546295, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0021684169769287, "global_step": 546296, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.078355550765991, "global_step": 546297, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.072920799255371, "global_step": 546298, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.019407033920288, "global_step": 546299, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9938132762908936, "global_step": 546300, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0731043815612793, "global_step": 546301, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.048346519470215, "global_step": 546302, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1243977546691895, "global_step": 546303, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.03277325630188, "global_step": 546304, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.037477731704712, "global_step": 546305, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.051406145095825, "global_step": 546306, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0874133110046387, "global_step": 546307, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9680324792861938, "global_step": 546308, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.128746747970581, "global_step": 546309, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0066044330596924, "global_step": 546310, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0470621585845947, "global_step": 546311, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1092939376831055, "global_step": 546312, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.988637924194336, "global_step": 546313, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.989814043045044, "global_step": 546314, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0807909965515137, "global_step": 546315, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0369975566864014, "global_step": 546316, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.013505220413208, "global_step": 546317, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.022087574005127, "global_step": 546318, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9984745979309082, "global_step": 546319, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1021993160247803, "global_step": 546320, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0059103965759277, "global_step": 546321, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1170902252197266, "global_step": 546322, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0099599361419678, "global_step": 546323, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0799176692962646, "global_step": 546324, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0522446632385254, "global_step": 546325, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.035893440246582, "global_step": 546326, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9770814180374146, "global_step": 546327, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0506505966186523, "global_step": 546328, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.089921236038208, "global_step": 546329, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0293684005737305, "global_step": 546330, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1427793502807617, "global_step": 546331, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0337657928466797, "global_step": 546332, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.094930410385132, "global_step": 546333, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9450767040252686, "global_step": 546334, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9969948530197144, "global_step": 546335, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0582528114318848, "global_step": 546336, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0315871238708496, "global_step": 546337, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9624412059783936, "global_step": 546338, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9760582447052002, "global_step": 546339, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.029543876647949, "global_step": 546340, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.072817087173462, "global_step": 546341, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0906832218170166, "global_step": 546342, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.146815776824951, "global_step": 546343, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9849733114242554, "global_step": 546344, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.156057357788086, "global_step": 546345, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9755339622497559, "global_step": 546346, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.133666515350342, "global_step": 546347, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0027647018432617, "global_step": 546348, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.038647174835205, "global_step": 546349, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0197982788085938, "global_step": 546350, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.058793783187866, "global_step": 546351, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0461902618408203, "global_step": 546352, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0083794593811035, "global_step": 546353, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9691143035888672, "global_step": 546354, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0301477909088135, "global_step": 546355, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0231220722198486, "global_step": 546356, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.058554172515869, "global_step": 546357, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1242871284484863, "global_step": 546358, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.015679121017456, "global_step": 546359, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.053938388824463, "global_step": 546360, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9391835927963257, "global_step": 546361, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0120327472686768, "global_step": 546362, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0518505573272705, "global_step": 546363, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0563409328460693, "global_step": 546364, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0795178413391113, "global_step": 546365, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.018585205078125, "global_step": 546366, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.109365224838257, "global_step": 546367, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.051658868789673, "global_step": 546368, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1684911251068115, "global_step": 546369, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9977651834487915, "global_step": 546370, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0281424522399902, "global_step": 546371, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0186963081359863, "global_step": 546372, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0637080669403076, "global_step": 546373, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.061459541320801, "global_step": 546374, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0680043697357178, "global_step": 546375, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9915482997894287, "global_step": 546376, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1026198863983154, "global_step": 546377, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9814691543579102, "global_step": 546378, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0155956745147705, "global_step": 546379, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.044978380203247, "global_step": 546380, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0305967330932617, "global_step": 546381, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.04838228225708, "global_step": 546382, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9365615844726562, "global_step": 546383, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.042689323425293, "global_step": 546384, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.050389289855957, "global_step": 546385, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.087982177734375, "global_step": 546386, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.035356283187866, "global_step": 546387, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.036642074584961, "global_step": 546388, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9666943550109863, "global_step": 546389, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.034336566925049, "global_step": 546390, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9871708154678345, "global_step": 546391, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9679319858551025, "global_step": 546392, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9998679161071777, "global_step": 546393, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9435545206069946, "global_step": 546394, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9824395179748535, "global_step": 546395, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0031800270080566, "global_step": 546396, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0361132621765137, "global_step": 546397, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.8964413404464722, "global_step": 546398, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0120463371276855, "global_step": 546399, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.032698154449463, "global_step": 546400, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0073928833007812, "global_step": 546401, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9957636594772339, "global_step": 546402, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.07258939743042, "global_step": 546403, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.125576972961426, "global_step": 546404, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9801826477050781, "global_step": 546405, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.007136106491089, "global_step": 546406, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1471569538116455, "global_step": 546407, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0260510444641113, "global_step": 546408, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0530667304992676, "global_step": 546409, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9984840154647827, "global_step": 546410, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.159144401550293, "global_step": 546411, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.02901029586792, "global_step": 546412, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9972230195999146, "global_step": 546413, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.011244773864746, "global_step": 546414, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.076908826828003, "global_step": 546415, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.072796583175659, "global_step": 546416, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9226018190383911, "global_step": 546417, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.048933506011963, "global_step": 546418, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0370137691497803, "global_step": 546419, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0840468406677246, "global_step": 546420, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1507768630981445, "global_step": 546421, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0704715251922607, "global_step": 546422, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0882222652435303, "global_step": 546423, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9520634412765503, "global_step": 546424, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.049015522003174, "global_step": 546425, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.033693313598633, "global_step": 546426, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0827221870422363, "global_step": 546427, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0921196937561035, "global_step": 546428, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0157761573791504, "global_step": 546429, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.037564754486084, "global_step": 546430, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0044126510620117, "global_step": 546431, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.030322551727295, "global_step": 546432, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9496703147888184, "global_step": 546433, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0643396377563477, "global_step": 546434, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0438425540924072, "global_step": 546435, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0014102458953857, "global_step": 546436, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0607705116271973, "global_step": 546437, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.094184160232544, "global_step": 546438, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.067370653152466, "global_step": 546439, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.040515899658203, "global_step": 546440, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.016680955886841, "global_step": 546441, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1195623874664307, "global_step": 546442, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.999555230140686, "global_step": 546443, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.066033363342285, "global_step": 546444, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0755624771118164, "global_step": 546445, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.024528980255127, "global_step": 546446, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.956355333328247, "global_step": 546447, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0042667388916016, "global_step": 546448, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0701024532318115, "global_step": 546449, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0463054180145264, "global_step": 546450, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9827278852462769, "global_step": 546451, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0592164993286133, "global_step": 546452, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9903125762939453, "global_step": 546453, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0301263332366943, "global_step": 546454, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0436911582946777, "global_step": 546455, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0463380813598633, "global_step": 546456, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0587146282196045, "global_step": 546457, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.053318500518799, "global_step": 546458, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0012366771698, "global_step": 546459, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9415241479873657, "global_step": 546460, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9621769189834595, "global_step": 546461, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0832672119140625, "global_step": 546462, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.031386613845825, "global_step": 546463, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9683490991592407, "global_step": 546464, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.137690782546997, "global_step": 546465, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0590858459472656, "global_step": 546466, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0818681716918945, "global_step": 546467, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9786889553070068, "global_step": 546468, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0016610622406006, "global_step": 546469, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.8982983827590942, "global_step": 546470, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0645201206207275, "global_step": 546471, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0564873218536377, "global_step": 546472, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0535707473754883, "global_step": 546473, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.092236042022705, "global_step": 546474, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.042142868041992, "global_step": 546475, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9523998498916626, "global_step": 546476, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0317764282226562, "global_step": 546477, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0725436210632324, "global_step": 546478, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0118448734283447, "global_step": 546479, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1247119903564453, "global_step": 546480, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9782589673995972, "global_step": 546481, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.08402681350708, "global_step": 546482, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9892756938934326, "global_step": 546483, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0411181449890137, "global_step": 546484, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1133289337158203, "global_step": 546485, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0585343837738037, "global_step": 546486, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.15244197845459, "global_step": 546487, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9843376874923706, "global_step": 546488, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0911598205566406, "global_step": 546489, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.107746124267578, "global_step": 546490, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.075220823287964, "global_step": 546491, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9887083768844604, "global_step": 546492, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0533885955810547, "global_step": 546493, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0996806621551514, "global_step": 546494, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0975937843322754, "global_step": 546495, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1010358333587646, "global_step": 546496, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.020937919616699, "global_step": 546497, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0604240894317627, "global_step": 546498, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0897202491760254, "global_step": 546499, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9854545593261719, "global_step": 546500, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.112968921661377, "global_step": 546501, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0884499549865723, "global_step": 546502, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0699782371520996, "global_step": 546503, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9060531854629517, "global_step": 546504, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.07554292678833, "global_step": 546505, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.035581588745117, "global_step": 546506, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1305410861968994, "global_step": 546507, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0182783603668213, "global_step": 546508, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0127124786376953, "global_step": 546509, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9774248600006104, "global_step": 546510, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0289838314056396, "global_step": 546511, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.063615560531616, "global_step": 546512, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.011341094970703, "global_step": 546513, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0174129009246826, "global_step": 546514, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.055297613143921, "global_step": 546515, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.075232744216919, "global_step": 546516, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.077238082885742, "global_step": 546517, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0352158546447754, "global_step": 546518, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0284903049468994, "global_step": 546519, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9872428178787231, "global_step": 546520, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.005685567855835, "global_step": 546521, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9061366319656372, "global_step": 546522, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9704595804214478, "global_step": 546523, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9972736835479736, "global_step": 546524, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9918819665908813, "global_step": 546525, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0926620960235596, "global_step": 546526, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9979981184005737, "global_step": 546527, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.085289716720581, "global_step": 546528, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.101870059967041, "global_step": 546529, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.98460853099823, "global_step": 546530, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0115091800689697, "global_step": 546531, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9974086284637451, "global_step": 546532, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0900347232818604, "global_step": 546533, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9830427169799805, "global_step": 546534, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0687270164489746, "global_step": 546535, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9777764081954956, "global_step": 546536, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.019716501235962, "global_step": 546537, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0686757564544678, "global_step": 546538, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.2226555347442627, "global_step": 546539, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0311105251312256, "global_step": 546540, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0536434650421143, "global_step": 546541, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.057098150253296, "global_step": 546542, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0098135471343994, "global_step": 546543, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.05735445022583, "global_step": 546544, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.011323928833008, "global_step": 546545, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9830348491668701, "global_step": 546546, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.038470983505249, "global_step": 546547, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.937053918838501, "global_step": 546548, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.042161464691162, "global_step": 546549, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.065225601196289, "global_step": 546550, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0607471466064453, "global_step": 546551, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1320688724517822, "global_step": 546552, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.004896402359009, "global_step": 546553, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.072885513305664, "global_step": 546554, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.037877321243286, "global_step": 546555, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9792534112930298, "global_step": 546556, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.015216827392578, "global_step": 546557, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9986075162887573, "global_step": 546558, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.993157148361206, "global_step": 546559, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9954026937484741, "global_step": 546560, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1156928539276123, "global_step": 546561, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9618185758590698, "global_step": 546562, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9936134815216064, "global_step": 546563, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0688047409057617, "global_step": 546564, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0197274684906006, "global_step": 546565, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0290963649749756, "global_step": 546566, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.11830472946167, "global_step": 546567, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9818668365478516, "global_step": 546568, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9988069534301758, "global_step": 546569, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0410118103027344, "global_step": 546570, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9654461145401, "global_step": 546571, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.037432909011841, "global_step": 546572, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.072507381439209, "global_step": 546573, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9561634063720703, "global_step": 546574, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.098736047744751, "global_step": 546575, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0047924518585205, "global_step": 546576, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0337584018707275, "global_step": 546577, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.110590696334839, "global_step": 546578, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0804409980773926, "global_step": 546579, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0174474716186523, "global_step": 546580, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.977760672569275, "global_step": 546581, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9927984476089478, "global_step": 546582, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.1044020652770996, "global_step": 546583, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0518479347229004, "global_step": 546584, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.039949417114258, "global_step": 546585, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9899117946624756, "global_step": 546586, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0334882736206055, "global_step": 546587, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0520503520965576, "global_step": 546588, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.990057110786438, "global_step": 546589, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0864510536193848, "global_step": 546590, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.042823553085327, "global_step": 546591, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9933451414108276, "global_step": 546592, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9901267290115356, "global_step": 546593, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9897129535675049, "global_step": 546594, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0474908351898193, "global_step": 546595, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9404782056808472, "global_step": 546596, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.077251672744751, "global_step": 546597, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0514371395111084, "global_step": 546598, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9366556406021118, "global_step": 546599, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0123941898345947, "global_step": 546600, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0309975147247314, "global_step": 546601, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0391364097595215, "global_step": 546602, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0319526195526123, "global_step": 546603, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9802978038787842, "global_step": 546604, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.927042007446289, "global_step": 546605, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9895763397216797, "global_step": 546606, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0398905277252197, "global_step": 546607, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.043710231781006, "global_step": 546608, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.04966139793396, "global_step": 546609, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0783324241638184, "global_step": 546610, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9696128368377686, "global_step": 546611, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.003452777862549, "global_step": 546612, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0678412914276123, "global_step": 546613, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.035573720932007, "global_step": 546614, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0758755207061768, "global_step": 546615, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.106769323348999, "global_step": 546616, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9802284240722656, "global_step": 546617, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.999662160873413, "global_step": 546618, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.017507553100586, "global_step": 546619, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9627963304519653, "global_step": 546620, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0836052894592285, "global_step": 546621, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0399415493011475, "global_step": 546622, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0408694744110107, "global_step": 546623, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.010136365890503, "global_step": 546624, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0697555541992188, "global_step": 546625, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0231146812438965, "global_step": 546626, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.102287530899048, "global_step": 546627, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9506301879882812, "global_step": 546628, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.039614677429199, "global_step": 546629, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0816895961761475, "global_step": 546630, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.025251865386963, "global_step": 546631, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.077326774597168, "global_step": 546632, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.946887731552124, "global_step": 546633, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.091938018798828, "global_step": 546634, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.107344388961792, "global_step": 546635, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0791077613830566, "global_step": 546636, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.066943645477295, "global_step": 546637, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.005826473236084, "global_step": 546638, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.013725519180298, "global_step": 546639, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9532697200775146, "global_step": 546640, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.028939723968506, "global_step": 546641, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9853179454803467, "global_step": 546642, "epoch": 913, "lr": 5e-05}
{"train_loss": 1.9584370851516724, "global_step": 546643, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0425755977630615, "global_step": 546644, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.07900333404541, "global_step": 546645, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.125537633895874, "global_step": 546646, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0711116790771484, "global_step": 546647, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.0334832668304443, "global_step": 546648, "epoch": 913, "lr": 5e-05}
{"train_loss": 2.029958486557007, "global_step": 546649, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.09922456741333, "global_step": 546650, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.032819986343384, "global_step": 546651, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.027294874191284, "global_step": 546652, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.043138027191162, "global_step": 546653, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9925851821899414, "global_step": 546654, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0517046451568604, "global_step": 546655, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0515007972717285, "global_step": 546656, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.016186475753784, "global_step": 546657, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0178301334381104, "global_step": 546658, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9229198694229126, "global_step": 546659, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9923287630081177, "global_step": 546660, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1283376216888428, "global_step": 546661, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0130813121795654, "global_step": 546662, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9700318574905396, "global_step": 546663, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.069774866104126, "global_step": 546664, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.98807954788208, "global_step": 546665, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0647099018096924, "global_step": 546666, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.998439073562622, "global_step": 546667, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0155844688415527, "global_step": 546668, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.033158779144287, "global_step": 546669, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0194289684295654, "global_step": 546670, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9616096019744873, "global_step": 546671, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.956615924835205, "global_step": 546672, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.102653741836548, "global_step": 546673, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.028113603591919, "global_step": 546674, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0412657260894775, "global_step": 546675, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.996025800704956, "global_step": 546676, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0289816856384277, "global_step": 546677, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.043867349624634, "global_step": 546678, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0808122158050537, "global_step": 546679, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.01127552986145, "global_step": 546680, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0669541358947754, "global_step": 546681, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0499067306518555, "global_step": 546682, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0637474060058594, "global_step": 546683, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9494905471801758, "global_step": 546684, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.010272979736328, "global_step": 546685, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0160772800445557, "global_step": 546686, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.030136823654175, "global_step": 546687, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.044595956802368, "global_step": 546688, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.092123508453369, "global_step": 546689, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9962862730026245, "global_step": 546690, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0041189193725586, "global_step": 546691, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0238640308380127, "global_step": 546692, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9699265956878662, "global_step": 546693, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9701244831085205, "global_step": 546694, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.011019229888916, "global_step": 546695, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.035754680633545, "global_step": 546696, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0305685997009277, "global_step": 546697, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0463924407958984, "global_step": 546698, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9774607419967651, "global_step": 546699, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.066328763961792, "global_step": 546700, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.015648365020752, "global_step": 546701, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.042363166809082, "global_step": 546702, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0888419151306152, "global_step": 546703, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.027313709259033, "global_step": 546704, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0173568725585938, "global_step": 546705, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.103081703186035, "global_step": 546706, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0429399013519287, "global_step": 546707, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.085932731628418, "global_step": 546708, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9667552709579468, "global_step": 546709, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0717785358428955, "global_step": 546710, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9992051124572754, "global_step": 546711, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9832043647766113, "global_step": 546712, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.927108883857727, "global_step": 546713, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9596967697143555, "global_step": 546714, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0583558082580566, "global_step": 546715, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9871431589126587, "global_step": 546716, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.003608226776123, "global_step": 546717, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9318302869796753, "global_step": 546718, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9714024066925049, "global_step": 546719, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9780311584472656, "global_step": 546720, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0421905517578125, "global_step": 546721, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0162312984466553, "global_step": 546722, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.051208257675171, "global_step": 546723, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9729068279266357, "global_step": 546724, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.034451961517334, "global_step": 546725, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.041724920272827, "global_step": 546726, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.015125036239624, "global_step": 546727, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.02260684967041, "global_step": 546728, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0249757766723633, "global_step": 546729, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0387611389160156, "global_step": 546730, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0062968730926514, "global_step": 546731, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9870750904083252, "global_step": 546732, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9381225109100342, "global_step": 546733, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0275802612304688, "global_step": 546734, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9756958484649658, "global_step": 546735, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9408453702926636, "global_step": 546736, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9938726425170898, "global_step": 546737, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9637460708618164, "global_step": 546738, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0570485591888428, "global_step": 546739, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9629122018814087, "global_step": 546740, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.053058624267578, "global_step": 546741, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0379693508148193, "global_step": 546742, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1382219791412354, "global_step": 546743, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9654804468154907, "global_step": 546744, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9451606273651123, "global_step": 546745, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0115227699279785, "global_step": 546746, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0560622215270996, "global_step": 546747, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0607573986053467, "global_step": 546748, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0366787910461426, "global_step": 546749, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.045591354370117, "global_step": 546750, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.004392385482788, "global_step": 546751, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.022390365600586, "global_step": 546752, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.04396390914917, "global_step": 546753, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9808988571166992, "global_step": 546754, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0520482063293457, "global_step": 546755, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9779608249664307, "global_step": 546756, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0675907135009766, "global_step": 546757, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0943260192871094, "global_step": 546758, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9840373992919922, "global_step": 546759, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.040524959564209, "global_step": 546760, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.036317825317383, "global_step": 546761, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.039541482925415, "global_step": 546762, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0203781127929688, "global_step": 546763, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0852699279785156, "global_step": 546764, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.063678026199341, "global_step": 546765, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9817123413085938, "global_step": 546766, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.089219570159912, "global_step": 546767, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.933720588684082, "global_step": 546768, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9952130317687988, "global_step": 546769, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0555267333984375, "global_step": 546770, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9521546363830566, "global_step": 546771, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0300331115722656, "global_step": 546772, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9448440074920654, "global_step": 546773, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.034667491912842, "global_step": 546774, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0179877281188965, "global_step": 546775, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9675660133361816, "global_step": 546776, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9891748428344727, "global_step": 546777, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9880504608154297, "global_step": 546778, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9637227058410645, "global_step": 546779, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.98012375831604, "global_step": 546780, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9765373468399048, "global_step": 546781, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.010399341583252, "global_step": 546782, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0000009536743164, "global_step": 546783, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.022359609603882, "global_step": 546784, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0916764736175537, "global_step": 546785, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0034656524658203, "global_step": 546786, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.963032841682434, "global_step": 546787, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0074105262756348, "global_step": 546788, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9809036254882812, "global_step": 546789, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.053236961364746, "global_step": 546790, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0708115100860596, "global_step": 546791, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.994857668876648, "global_step": 546792, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9332711696624756, "global_step": 546793, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9864275455474854, "global_step": 546794, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0587174892425537, "global_step": 546795, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9570131301879883, "global_step": 546796, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9506869316101074, "global_step": 546797, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0519065856933594, "global_step": 546798, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9881383180618286, "global_step": 546799, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0607550144195557, "global_step": 546800, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0347628593444824, "global_step": 546801, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0296249389648438, "global_step": 546802, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0124802589416504, "global_step": 546803, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9588639736175537, "global_step": 546804, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0816450119018555, "global_step": 546805, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.067105293273926, "global_step": 546806, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.048731803894043, "global_step": 546807, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.023084878921509, "global_step": 546808, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.063220262527466, "global_step": 546809, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9268807172775269, "global_step": 546810, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9550505876541138, "global_step": 546811, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0447239875793457, "global_step": 546812, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.037487268447876, "global_step": 546813, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0055196285247803, "global_step": 546814, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.112975597381592, "global_step": 546815, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0682272911071777, "global_step": 546816, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9995096921920776, "global_step": 546817, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9911205768585205, "global_step": 546818, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.965354323387146, "global_step": 546819, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.06149959564209, "global_step": 546820, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.074005365371704, "global_step": 546821, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0946760177612305, "global_step": 546822, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0428452491760254, "global_step": 546823, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9712905883789062, "global_step": 546824, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9418258666992188, "global_step": 546825, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9416773319244385, "global_step": 546826, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0034496784210205, "global_step": 546827, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9566946029663086, "global_step": 546828, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0570569038391113, "global_step": 546829, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9980815649032593, "global_step": 546830, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.057588577270508, "global_step": 546831, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0462899208068848, "global_step": 546832, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.018242597579956, "global_step": 546833, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.120342493057251, "global_step": 546834, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0843145847320557, "global_step": 546835, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.004638195037842, "global_step": 546836, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9483914375305176, "global_step": 546837, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.058748960494995, "global_step": 546838, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.969491958618164, "global_step": 546839, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0204787254333496, "global_step": 546840, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0188636779785156, "global_step": 546841, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9967442750930786, "global_step": 546842, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.025052547454834, "global_step": 546843, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.097813844680786, "global_step": 546844, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9237914085388184, "global_step": 546845, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.931843638420105, "global_step": 546846, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.005241632461548, "global_step": 546847, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.049853563308716, "global_step": 546848, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9999274015426636, "global_step": 546849, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.07559871673584, "global_step": 546850, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.955272912979126, "global_step": 546851, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0231943130493164, "global_step": 546852, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.086332321166992, "global_step": 546853, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0477793216705322, "global_step": 546854, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0797579288482666, "global_step": 546855, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.015014410018921, "global_step": 546856, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0425939559936523, "global_step": 546857, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0461456775665283, "global_step": 546858, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.083878993988037, "global_step": 546859, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9284592866897583, "global_step": 546860, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9990007877349854, "global_step": 546861, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9260027408599854, "global_step": 546862, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.004894733428955, "global_step": 546863, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.014514684677124, "global_step": 546864, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9484609365463257, "global_step": 546865, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0555663108825684, "global_step": 546866, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9831806421279907, "global_step": 546867, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0115807056427, "global_step": 546868, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.094633102416992, "global_step": 546869, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9409821033477783, "global_step": 546870, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0995941162109375, "global_step": 546871, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.040510892868042, "global_step": 546872, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0638608932495117, "global_step": 546873, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9334187507629395, "global_step": 546874, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1064751148223877, "global_step": 546875, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0236010551452637, "global_step": 546876, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0584704875946045, "global_step": 546877, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0615830421447754, "global_step": 546878, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.040393590927124, "global_step": 546879, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.961167573928833, "global_step": 546880, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.07476544380188, "global_step": 546881, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.128984212875366, "global_step": 546882, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.102315664291382, "global_step": 546883, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0779151916503906, "global_step": 546884, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.022308588027954, "global_step": 546885, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9965764284133911, "global_step": 546886, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0253591537475586, "global_step": 546887, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.990912914276123, "global_step": 546888, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0268211364746094, "global_step": 546889, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0227913856506348, "global_step": 546890, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.043215274810791, "global_step": 546891, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0723633766174316, "global_step": 546892, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0958855152130127, "global_step": 546893, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0447700023651123, "global_step": 546894, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0256729125976562, "global_step": 546895, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.117342948913574, "global_step": 546896, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0521240234375, "global_step": 546897, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0537023544311523, "global_step": 546898, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.027965784072876, "global_step": 546899, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.964538812637329, "global_step": 546900, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9932372570037842, "global_step": 546901, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0852162837982178, "global_step": 546902, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.076587677001953, "global_step": 546903, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9293649196624756, "global_step": 546904, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0787105560302734, "global_step": 546905, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0212905406951904, "global_step": 546906, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0459327697753906, "global_step": 546907, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0366134643554688, "global_step": 546908, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9796183109283447, "global_step": 546909, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0866761207580566, "global_step": 546910, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.032076835632324, "global_step": 546911, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9773207902908325, "global_step": 546912, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.105963706970215, "global_step": 546913, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9913362264633179, "global_step": 546914, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.8904038667678833, "global_step": 546915, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.940335750579834, "global_step": 546916, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0293238162994385, "global_step": 546917, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0464255809783936, "global_step": 546918, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9967926740646362, "global_step": 546919, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0406064987182617, "global_step": 546920, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.002063751220703, "global_step": 546921, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0329158306121826, "global_step": 546922, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.959092617034912, "global_step": 546923, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0781264305114746, "global_step": 546924, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.060253620147705, "global_step": 546925, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0899405479431152, "global_step": 546926, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9902063608169556, "global_step": 546927, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0216281414031982, "global_step": 546928, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1050305366516113, "global_step": 546929, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.017251968383789, "global_step": 546930, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.104848861694336, "global_step": 546931, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0530951023101807, "global_step": 546932, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0455448627471924, "global_step": 546933, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0147531032562256, "global_step": 546934, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.037435531616211, "global_step": 546935, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.976095199584961, "global_step": 546936, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.058058738708496, "global_step": 546937, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.029719829559326, "global_step": 546938, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9664326906204224, "global_step": 546939, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9455907344818115, "global_step": 546940, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.082444429397583, "global_step": 546941, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.062173366546631, "global_step": 546942, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.020857334136963, "global_step": 546943, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.075608968734741, "global_step": 546944, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.12465238571167, "global_step": 546945, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0712597370147705, "global_step": 546946, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.035961866378784, "global_step": 546947, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0726470947265625, "global_step": 546948, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.105170726776123, "global_step": 546949, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9361746311187744, "global_step": 546950, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.963141679763794, "global_step": 546951, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9624171257019043, "global_step": 546952, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1060924530029297, "global_step": 546953, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9733127355575562, "global_step": 546954, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.031419277191162, "global_step": 546955, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0442943572998047, "global_step": 546956, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9828753471374512, "global_step": 546957, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1242868900299072, "global_step": 546958, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1371774673461914, "global_step": 546959, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0091552734375, "global_step": 546960, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9866517782211304, "global_step": 546961, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.081385374069214, "global_step": 546962, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0352213382720947, "global_step": 546963, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1364476680755615, "global_step": 546964, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9739172458648682, "global_step": 546965, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.002761125564575, "global_step": 546966, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0020360946655273, "global_step": 546967, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0669047832489014, "global_step": 546968, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.961931824684143, "global_step": 546969, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0396010875701904, "global_step": 546970, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.048471212387085, "global_step": 546971, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0590922832489014, "global_step": 546972, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9778879880905151, "global_step": 546973, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9854669570922852, "global_step": 546974, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.087118625640869, "global_step": 546975, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.080296277999878, "global_step": 546976, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0909104347229004, "global_step": 546977, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0529754161834717, "global_step": 546978, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9821604490280151, "global_step": 546979, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.018115282058716, "global_step": 546980, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9251015186309814, "global_step": 546981, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0751285552978516, "global_step": 546982, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0226194858551025, "global_step": 546983, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.001755952835083, "global_step": 546984, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.023369073867798, "global_step": 546985, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0304410457611084, "global_step": 546986, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.105172634124756, "global_step": 546987, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.036003351211548, "global_step": 546988, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0567638874053955, "global_step": 546989, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9806755781173706, "global_step": 546990, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9782789945602417, "global_step": 546991, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.937154769897461, "global_step": 546992, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0505285263061523, "global_step": 546993, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9926373958587646, "global_step": 546994, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.007737159729004, "global_step": 546995, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0548038482666016, "global_step": 546996, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9777888059616089, "global_step": 546997, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9654252529144287, "global_step": 546998, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1197779178619385, "global_step": 546999, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9830564260482788, "global_step": 547000, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9866206645965576, "global_step": 547001, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.981446385383606, "global_step": 547002, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9939616918563843, "global_step": 547003, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0993266105651855, "global_step": 547004, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.934757113456726, "global_step": 547005, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0779104232788086, "global_step": 547006, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.071392297744751, "global_step": 547007, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.980825662612915, "global_step": 547008, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0180957317352295, "global_step": 547009, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0180435180664062, "global_step": 547010, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0647215843200684, "global_step": 547011, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9842581748962402, "global_step": 547012, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.970501184463501, "global_step": 547013, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1057825088500977, "global_step": 547014, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.034801721572876, "global_step": 547015, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0380618572235107, "global_step": 547016, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0284197330474854, "global_step": 547017, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0234131813049316, "global_step": 547018, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1678268909454346, "global_step": 547019, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9994450807571411, "global_step": 547020, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0466315746307373, "global_step": 547021, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.077284336090088, "global_step": 547022, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0323030948638916, "global_step": 547023, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0425455570220947, "global_step": 547024, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.042837142944336, "global_step": 547025, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0433461666107178, "global_step": 547026, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0694589614868164, "global_step": 547027, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0233840942382812, "global_step": 547028, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0190258026123047, "global_step": 547029, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.097007989883423, "global_step": 547030, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9397131204605103, "global_step": 547031, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0771560668945312, "global_step": 547032, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0020997524261475, "global_step": 547033, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0025901794433594, "global_step": 547034, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.939548134803772, "global_step": 547035, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0435309410095215, "global_step": 547036, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.053487539291382, "global_step": 547037, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0947329998016357, "global_step": 547038, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0597920417785645, "global_step": 547039, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1035048961639404, "global_step": 547040, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9730162620544434, "global_step": 547041, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0091166496276855, "global_step": 547042, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.000148057937622, "global_step": 547043, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.091538667678833, "global_step": 547044, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0799996852874756, "global_step": 547045, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0419256687164307, "global_step": 547046, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1279077529907227, "global_step": 547047, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0524163246154785, "global_step": 547048, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9809600114822388, "global_step": 547049, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.052356481552124, "global_step": 547050, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.071742057800293, "global_step": 547051, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0377650260925293, "global_step": 547052, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9753004312515259, "global_step": 547053, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.08843994140625, "global_step": 547054, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9968559741973877, "global_step": 547055, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0068116188049316, "global_step": 547056, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.013063430786133, "global_step": 547057, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0003931522369385, "global_step": 547058, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0049309730529785, "global_step": 547059, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.034837007522583, "global_step": 547060, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9731249809265137, "global_step": 547061, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.111211061477661, "global_step": 547062, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.010706901550293, "global_step": 547063, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0861902236938477, "global_step": 547064, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.088322162628174, "global_step": 547065, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.059647560119629, "global_step": 547066, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.076023578643799, "global_step": 547067, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.019080877304077, "global_step": 547068, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0668513774871826, "global_step": 547069, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0074622631073, "global_step": 547070, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0024986267089844, "global_step": 547071, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.136305809020996, "global_step": 547072, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0571091175079346, "global_step": 547073, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.951805830001831, "global_step": 547074, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9981660842895508, "global_step": 547075, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0148468017578125, "global_step": 547076, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0179450511932373, "global_step": 547077, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.029646873474121, "global_step": 547078, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0936660766601562, "global_step": 547079, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9734104871749878, "global_step": 547080, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0851314067840576, "global_step": 547081, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0125019550323486, "global_step": 547082, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.056300640106201, "global_step": 547083, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0295398235321045, "global_step": 547084, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.031529426574707, "global_step": 547085, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.931583285331726, "global_step": 547086, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0443825721740723, "global_step": 547087, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9121001958847046, "global_step": 547088, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0452733039855957, "global_step": 547089, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.001514434814453, "global_step": 547090, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9545308351516724, "global_step": 547091, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0322132110595703, "global_step": 547092, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.086883068084717, "global_step": 547093, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.04054856300354, "global_step": 547094, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9497103691101074, "global_step": 547095, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1217832565307617, "global_step": 547096, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1256775856018066, "global_step": 547097, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.05178165435791, "global_step": 547098, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9859638214111328, "global_step": 547099, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.128842353820801, "global_step": 547100, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.158629894256592, "global_step": 547101, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.09507155418396, "global_step": 547102, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0091443061828613, "global_step": 547103, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9888582229614258, "global_step": 547104, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9452332258224487, "global_step": 547105, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0014266967773438, "global_step": 547106, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0159759521484375, "global_step": 547107, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.076153516769409, "global_step": 547108, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.079573392868042, "global_step": 547109, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.981652021408081, "global_step": 547110, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.121354341506958, "global_step": 547111, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0918939113616943, "global_step": 547112, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.009915351867676, "global_step": 547113, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.019136428833008, "global_step": 547114, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9756669998168945, "global_step": 547115, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0859367847442627, "global_step": 547116, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.029557466506958, "global_step": 547117, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0375099182128906, "global_step": 547118, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9957340955734253, "global_step": 547119, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0579490661621094, "global_step": 547120, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0585532188415527, "global_step": 547121, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0750088691711426, "global_step": 547122, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0323588848114014, "global_step": 547123, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.943141222000122, "global_step": 547124, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0240426063537598, "global_step": 547125, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0022706985473633, "global_step": 547126, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0169243812561035, "global_step": 547127, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9887382984161377, "global_step": 547128, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0416250228881836, "global_step": 547129, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0554468631744385, "global_step": 547130, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1188101768493652, "global_step": 547131, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.050693988800049, "global_step": 547132, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.113083839416504, "global_step": 547133, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.92892587184906, "global_step": 547134, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0457849502563477, "global_step": 547135, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0923023223876953, "global_step": 547136, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0283315181732178, "global_step": 547137, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0895774364471436, "global_step": 547138, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9582622051239014, "global_step": 547139, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0570168495178223, "global_step": 547140, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.090662717819214, "global_step": 547141, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0635833740234375, "global_step": 547142, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0895495414733887, "global_step": 547143, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9680266380310059, "global_step": 547144, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.073392629623413, "global_step": 547145, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9861500263214111, "global_step": 547146, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9260066747665405, "global_step": 547147, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9206448793411255, "global_step": 547148, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.018653392791748, "global_step": 547149, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.003291606903076, "global_step": 547150, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.948901653289795, "global_step": 547151, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.017975330352783, "global_step": 547152, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0800464153289795, "global_step": 547153, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1203224658966064, "global_step": 547154, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9765877723693848, "global_step": 547155, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9716877937316895, "global_step": 547156, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0922043323516846, "global_step": 547157, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.979636788368225, "global_step": 547158, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.020531177520752, "global_step": 547159, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9921138286590576, "global_step": 547160, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9238622188568115, "global_step": 547161, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9296799898147583, "global_step": 547162, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0427088737487793, "global_step": 547163, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0626814365386963, "global_step": 547164, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0386719703674316, "global_step": 547165, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9929612874984741, "global_step": 547166, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.066260576248169, "global_step": 547167, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.034151315689087, "global_step": 547168, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.102330446243286, "global_step": 547169, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0176215171813965, "global_step": 547170, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0392937660217285, "global_step": 547171, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0242180824279785, "global_step": 547172, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.113126516342163, "global_step": 547173, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0079078674316406, "global_step": 547174, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0660979747772217, "global_step": 547175, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.175751209259033, "global_step": 547176, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9745795726776123, "global_step": 547177, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.978479266166687, "global_step": 547178, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.158417224884033, "global_step": 547179, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0195326805114746, "global_step": 547180, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.095153570175171, "global_step": 547181, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0502121448516846, "global_step": 547182, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0565898418426514, "global_step": 547183, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.020097255706787, "global_step": 547184, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9806842803955078, "global_step": 547185, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9815725088119507, "global_step": 547186, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0688655376434326, "global_step": 547187, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0691535472869873, "global_step": 547188, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.010930299758911, "global_step": 547189, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0527231693267822, "global_step": 547190, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0631556510925293, "global_step": 547191, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.051199197769165, "global_step": 547192, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.087658166885376, "global_step": 547193, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0572869777679443, "global_step": 547194, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.097724199295044, "global_step": 547195, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.095912456512451, "global_step": 547196, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.060231924057007, "global_step": 547197, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.095932960510254, "global_step": 547198, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.079699993133545, "global_step": 547199, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.023113489151001, "global_step": 547200, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.001722812652588, "global_step": 547201, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1098439693450928, "global_step": 547202, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.043666362762451, "global_step": 547203, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0124759674072266, "global_step": 547204, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0388474464416504, "global_step": 547205, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9636144638061523, "global_step": 547206, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0297718048095703, "global_step": 547207, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.03261661529541, "global_step": 547208, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.042642116546631, "global_step": 547209, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0245866775512695, "global_step": 547210, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0490198135375977, "global_step": 547211, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.072507858276367, "global_step": 547212, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0958197116851807, "global_step": 547213, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.028925657272339, "global_step": 547214, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0409085750579834, "global_step": 547215, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.059741258621216, "global_step": 547216, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9719277620315552, "global_step": 547217, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9925551414489746, "global_step": 547218, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9499632120132446, "global_step": 547219, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0560481548309326, "global_step": 547220, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0203230381011963, "global_step": 547221, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9854187965393066, "global_step": 547222, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.060737133026123, "global_step": 547223, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0334537029266357, "global_step": 547224, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0313661098480225, "global_step": 547225, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.026496648788452, "global_step": 547226, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.059251546859741, "global_step": 547227, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.074221611022949, "global_step": 547228, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.010413646697998, "global_step": 547229, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0381479263305664, "global_step": 547230, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9547039270401, "global_step": 547231, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0466771125793457, "global_step": 547232, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.016774892807007, "global_step": 547233, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.057528018951416, "global_step": 547234, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0336384773254395, "global_step": 547235, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0728704929351807, "global_step": 547236, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0281822681427, "global_step": 547237, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0427842140197754, "global_step": 547238, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0904605388641357, "global_step": 547239, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0514302253723145, "global_step": 547240, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.016216993331909, "global_step": 547241, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.064319610595703, "global_step": 547242, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0506768226623535, "global_step": 547243, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0578298568725586, "global_step": 547244, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0604240894317627, "global_step": 547245, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.095586061477661, "global_step": 547246, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.082761526107788, "global_step": 547247, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.004849433898926, "global_step": 547248, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9696166515350342, "global_step": 547249, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0992178916931152, "global_step": 547250, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0384750366210938, "global_step": 547251, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.032116651535034, "global_step": 547252, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9873727560043335, "global_step": 547253, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.026047706604004, "global_step": 547254, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0403459072113037, "global_step": 547255, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0303966999053955, "global_step": 547256, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.052492380142212, "global_step": 547257, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0296072959899902, "global_step": 547258, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0441133975982666, "global_step": 547259, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.020021438598633, "global_step": 547260, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.015717029571533, "global_step": 547261, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0459189414978027, "global_step": 547262, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0439531803131104, "global_step": 547263, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9849060773849487, "global_step": 547264, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0842926502227783, "global_step": 547265, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9919166564941406, "global_step": 547266, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.120485782623291, "global_step": 547267, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0484731197357178, "global_step": 547268, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.978254795074463, "global_step": 547269, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.961930751800537, "global_step": 547270, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0475914478302, "global_step": 547271, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9427298307418823, "global_step": 547272, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9889476299285889, "global_step": 547273, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9779844284057617, "global_step": 547274, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1197328567504883, "global_step": 547275, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.040369749069214, "global_step": 547276, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0643978118896484, "global_step": 547277, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.052175760269165, "global_step": 547278, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0394768714904785, "global_step": 547279, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9987695217132568, "global_step": 547280, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0780415534973145, "global_step": 547281, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.116392135620117, "global_step": 547282, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0899882316589355, "global_step": 547283, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.2007720470428467, "global_step": 547284, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.046309471130371, "global_step": 547285, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.05621337890625, "global_step": 547286, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.012070894241333, "global_step": 547287, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.122859477996826, "global_step": 547288, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0511105060577393, "global_step": 547289, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.002619981765747, "global_step": 547290, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9446016550064087, "global_step": 547291, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0258193016052246, "global_step": 547292, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0612552165985107, "global_step": 547293, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.032440185546875, "global_step": 547294, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.049940824508667, "global_step": 547295, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9722284078598022, "global_step": 547296, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.022049903869629, "global_step": 547297, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0050618648529053, "global_step": 547298, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.967085838317871, "global_step": 547299, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0177876949310303, "global_step": 547300, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.050509214401245, "global_step": 547301, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.100369930267334, "global_step": 547302, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.957815170288086, "global_step": 547303, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0296437740325928, "global_step": 547304, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.101785659790039, "global_step": 547305, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9774718284606934, "global_step": 547306, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.8649379014968872, "global_step": 547307, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0116899013519287, "global_step": 547308, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9621354341506958, "global_step": 547309, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.036332130432129, "global_step": 547310, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0968234539031982, "global_step": 547311, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9916114807128906, "global_step": 547312, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0424633026123047, "global_step": 547313, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1171913146972656, "global_step": 547314, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.055006742477417, "global_step": 547315, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0202953815460205, "global_step": 547316, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.004070997238159, "global_step": 547317, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.039229393005371, "global_step": 547318, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0415165424346924, "global_step": 547319, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.078972339630127, "global_step": 547320, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0164005756378174, "global_step": 547321, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9824848175048828, "global_step": 547322, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0768179893493652, "global_step": 547323, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9967355728149414, "global_step": 547324, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.107858657836914, "global_step": 547325, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0365586280822754, "global_step": 547326, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0764920711517334, "global_step": 547327, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0604403018951416, "global_step": 547328, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0102221965789795, "global_step": 547329, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1171109676361084, "global_step": 547330, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0258595943450928, "global_step": 547331, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9729032516479492, "global_step": 547332, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1230199337005615, "global_step": 547333, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9387503862380981, "global_step": 547334, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0957486629486084, "global_step": 547335, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.037097692489624, "global_step": 547336, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0051486492156982, "global_step": 547337, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9499664306640625, "global_step": 547338, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.020354747772217, "global_step": 547339, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.07196044921875, "global_step": 547340, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.009909152984619, "global_step": 547341, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.016710042953491, "global_step": 547342, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9570013284683228, "global_step": 547343, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1070384979248047, "global_step": 547344, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.015615224838257, "global_step": 547345, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0530261993408203, "global_step": 547346, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0430023670196533, "global_step": 547347, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.103358268737793, "global_step": 547348, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0652387142181396, "global_step": 547349, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.98172128200531, "global_step": 547350, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.014378547668457, "global_step": 547351, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0779194831848145, "global_step": 547352, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.030036211013794, "global_step": 547353, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.102468729019165, "global_step": 547354, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.019078493118286, "global_step": 547355, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.062347412109375, "global_step": 547356, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.115779161453247, "global_step": 547357, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0212347507476807, "global_step": 547358, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0806281566619873, "global_step": 547359, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0308384895324707, "global_step": 547360, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0152409076690674, "global_step": 547361, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.023923635482788, "global_step": 547362, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0842552185058594, "global_step": 547363, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1041274070739746, "global_step": 547364, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0616612434387207, "global_step": 547365, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.94986093044281, "global_step": 547366, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.048990249633789, "global_step": 547367, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1171627044677734, "global_step": 547368, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9817663431167603, "global_step": 547369, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.007859230041504, "global_step": 547370, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0173754692077637, "global_step": 547371, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9631261825561523, "global_step": 547372, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0551021099090576, "global_step": 547373, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9632830619812012, "global_step": 547374, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9963815212249756, "global_step": 547375, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9955326318740845, "global_step": 547376, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0948565006256104, "global_step": 547377, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.044276237487793, "global_step": 547378, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9972392320632935, "global_step": 547379, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.017378807067871, "global_step": 547380, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0305466651916504, "global_step": 547381, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.041513681411743, "global_step": 547382, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0542471408843994, "global_step": 547383, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.020749568939209, "global_step": 547384, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0198616981506348, "global_step": 547385, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.085932970046997, "global_step": 547386, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9035824537277222, "global_step": 547387, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0632455348968506, "global_step": 547388, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.030620574951172, "global_step": 547389, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9846311807632446, "global_step": 547390, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.057651996612549, "global_step": 547391, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.105788469314575, "global_step": 547392, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0187594890594482, "global_step": 547393, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.121100664138794, "global_step": 547394, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.024676561355591, "global_step": 547395, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.054612874984741, "global_step": 547396, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9587663412094116, "global_step": 547397, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0304009914398193, "global_step": 547398, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9960027933120728, "global_step": 547399, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.008061408996582, "global_step": 547400, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0115914344787598, "global_step": 547401, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0671520233154297, "global_step": 547402, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.089569091796875, "global_step": 547403, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.066206693649292, "global_step": 547404, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.996774435043335, "global_step": 547405, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0202934741973877, "global_step": 547406, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0557658672332764, "global_step": 547407, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.994093656539917, "global_step": 547408, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0176749229431152, "global_step": 547409, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0096943378448486, "global_step": 547410, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0740418434143066, "global_step": 547411, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.055957078933716, "global_step": 547412, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.076439380645752, "global_step": 547413, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9964473247528076, "global_step": 547414, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0253050327301025, "global_step": 547415, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.089242935180664, "global_step": 547416, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.025731325149536, "global_step": 547417, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0749237537384033, "global_step": 547418, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0118961334228516, "global_step": 547419, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0365536212921143, "global_step": 547420, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0185201168060303, "global_step": 547421, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.000241756439209, "global_step": 547422, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0095112323760986, "global_step": 547423, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0663280487060547, "global_step": 547424, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0804226398468018, "global_step": 547425, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9838404655456543, "global_step": 547426, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.045402765274048, "global_step": 547427, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0449249744415283, "global_step": 547428, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0993475914001465, "global_step": 547429, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.084829092025757, "global_step": 547430, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9953973293304443, "global_step": 547431, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0592527389526367, "global_step": 547432, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1803412437438965, "global_step": 547433, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0258841514587402, "global_step": 547434, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0485360622406006, "global_step": 547435, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0754318237304688, "global_step": 547436, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0079097747802734, "global_step": 547437, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9517338275909424, "global_step": 547438, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.011118173599243, "global_step": 547439, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.094370126724243, "global_step": 547440, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9956477880477905, "global_step": 547441, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.060861110687256, "global_step": 547442, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0674197673797607, "global_step": 547443, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9855632781982422, "global_step": 547444, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.030634880065918, "global_step": 547445, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.085690498352051, "global_step": 547446, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0661425590515137, "global_step": 547447, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0527267456054688, "global_step": 547448, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0318820476531982, "global_step": 547449, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1335854530334473, "global_step": 547450, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.060568332672119, "global_step": 547451, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0331318378448486, "global_step": 547452, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9775445461273193, "global_step": 547453, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9891877174377441, "global_step": 547454, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0120174884796143, "global_step": 547455, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.046443223953247, "global_step": 547456, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0525920391082764, "global_step": 547457, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.106001853942871, "global_step": 547458, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.063328981399536, "global_step": 547459, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.093724489212036, "global_step": 547460, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9902924299240112, "global_step": 547461, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0054540634155273, "global_step": 547462, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9993975162506104, "global_step": 547463, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9600553512573242, "global_step": 547464, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0319418907165527, "global_step": 547465, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0681920051574707, "global_step": 547466, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0757455825805664, "global_step": 547467, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0026779174804688, "global_step": 547468, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.108060359954834, "global_step": 547469, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.021599769592285, "global_step": 547470, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.047417402267456, "global_step": 547471, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9981871843338013, "global_step": 547472, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.030813694000244, "global_step": 547473, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.056185007095337, "global_step": 547474, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0407721996307373, "global_step": 547475, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.07788348197937, "global_step": 547476, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.12019419670105, "global_step": 547477, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9814890623092651, "global_step": 547478, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.149890899658203, "global_step": 547479, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.04866099357605, "global_step": 547480, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9680854082107544, "global_step": 547481, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.01809024810791, "global_step": 547482, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0079543590545654, "global_step": 547483, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0606069564819336, "global_step": 547484, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.979515790939331, "global_step": 547485, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.00260853767395, "global_step": 547486, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0755865573883057, "global_step": 547487, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.030007839202881, "global_step": 547488, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0216639041900635, "global_step": 547489, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9838544130325317, "global_step": 547490, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.119055986404419, "global_step": 547491, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0521106719970703, "global_step": 547492, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9754116535186768, "global_step": 547493, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.97421133518219, "global_step": 547494, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0763301849365234, "global_step": 547495, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9888904094696045, "global_step": 547496, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0163233280181885, "global_step": 547497, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9847983121871948, "global_step": 547498, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9973423480987549, "global_step": 547499, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0553834438323975, "global_step": 547500, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0724093914031982, "global_step": 547501, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1055471897125244, "global_step": 547502, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.070375442504883, "global_step": 547503, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.108781099319458, "global_step": 547504, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.998489499092102, "global_step": 547505, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9885151386260986, "global_step": 547506, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9790964126586914, "global_step": 547507, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.942098617553711, "global_step": 547508, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.064228057861328, "global_step": 547509, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9775340557098389, "global_step": 547510, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9850484132766724, "global_step": 547511, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.03300404548645, "global_step": 547512, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9310593605041504, "global_step": 547513, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.042933940887451, "global_step": 547514, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0963001251220703, "global_step": 547515, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.099783182144165, "global_step": 547516, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.944590449333191, "global_step": 547517, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1737730503082275, "global_step": 547518, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0500340461730957, "global_step": 547519, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.056312084197998, "global_step": 547520, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0065207481384277, "global_step": 547521, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9612650871276855, "global_step": 547522, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.997131586074829, "global_step": 547523, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9888908863067627, "global_step": 547524, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9843708276748657, "global_step": 547525, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0597198009490967, "global_step": 547526, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.022106647491455, "global_step": 547527, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0611071586608887, "global_step": 547528, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0074164867401123, "global_step": 547529, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0331361293792725, "global_step": 547530, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.981255054473877, "global_step": 547531, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.009618043899536, "global_step": 547532, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0510923862457275, "global_step": 547533, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0183091163635254, "global_step": 547534, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9923346042633057, "global_step": 547535, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0843753814697266, "global_step": 547536, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9460536241531372, "global_step": 547537, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1304643154144287, "global_step": 547538, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.002882242202759, "global_step": 547539, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.001511335372925, "global_step": 547540, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0060980319976807, "global_step": 547541, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9945776462554932, "global_step": 547542, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9970711469650269, "global_step": 547543, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.053483724594116, "global_step": 547544, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0547327995300293, "global_step": 547545, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9709941148757935, "global_step": 547546, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.064089059829712, "global_step": 547547, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.992677927017212, "global_step": 547548, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0209715366363525, "global_step": 547549, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1559958457946777, "global_step": 547550, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1113266944885254, "global_step": 547551, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.018176794052124, "global_step": 547552, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9687596559524536, "global_step": 547553, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.000589609146118, "global_step": 547554, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.000767946243286, "global_step": 547555, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.004734992980957, "global_step": 547556, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0185940265655518, "global_step": 547557, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9705861806869507, "global_step": 547558, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0407238006591797, "global_step": 547559, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0248522758483887, "global_step": 547560, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.157026529312134, "global_step": 547561, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.06193208694458, "global_step": 547562, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0484421253204346, "global_step": 547563, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0840868949890137, "global_step": 547564, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0386290550231934, "global_step": 547565, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.058363437652588, "global_step": 547566, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9847724437713623, "global_step": 547567, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1064531803131104, "global_step": 547568, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9685429334640503, "global_step": 547569, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0708305835723877, "global_step": 547570, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.054408311843872, "global_step": 547571, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.99422287940979, "global_step": 547572, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9292657375335693, "global_step": 547573, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0530171394348145, "global_step": 547574, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0405149459838867, "global_step": 547575, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9443780183792114, "global_step": 547576, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0250244140625, "global_step": 547577, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0890400409698486, "global_step": 547578, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.053748846054077, "global_step": 547579, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.119767189025879, "global_step": 547580, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.040302038192749, "global_step": 547581, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9907947778701782, "global_step": 547582, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.075751304626465, "global_step": 547583, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9951711893081665, "global_step": 547584, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0678515434265137, "global_step": 547585, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1349236965179443, "global_step": 547586, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9747391939163208, "global_step": 547587, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9788318872451782, "global_step": 547588, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0589563846588135, "global_step": 547589, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.038599967956543, "global_step": 547590, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9875853061676025, "global_step": 547591, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0629007816314697, "global_step": 547592, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0742011070251465, "global_step": 547593, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.079878091812134, "global_step": 547594, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0547056198120117, "global_step": 547595, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0840659141540527, "global_step": 547596, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.024099826812744, "global_step": 547597, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.043114423751831, "global_step": 547598, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.032386302947998, "global_step": 547599, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.062640428543091, "global_step": 547600, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1013221740722656, "global_step": 547601, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.044614315032959, "global_step": 547602, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0757980346679688, "global_step": 547603, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9843785762786865, "global_step": 547604, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9689258337020874, "global_step": 547605, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.055180311203003, "global_step": 547606, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0772719383239746, "global_step": 547607, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.121919870376587, "global_step": 547608, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.011049509048462, "global_step": 547609, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1511528491973877, "global_step": 547610, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0364181995391846, "global_step": 547611, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.1171512603759766, "global_step": 547612, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.108379364013672, "global_step": 547613, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.0625743865966797, "global_step": 547614, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9954177141189575, "global_step": 547615, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9940892457962036, "global_step": 547616, "epoch": 914, "lr": 5e-05}
{"train_loss": 2.031207323074341, "global_step": 547617, "epoch": 914, "lr": 5e-05}
{"train_loss": 1.9584712982177734, "global_step": 547618, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9872865676879883, "global_step": 547619, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0674428939819336, "global_step": 547620, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1315927505493164, "global_step": 547621, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.076756000518799, "global_step": 547622, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0845844745635986, "global_step": 547623, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0364186763763428, "global_step": 547624, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.133218765258789, "global_step": 547625, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9582315683364868, "global_step": 547626, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.010484457015991, "global_step": 547627, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.8779823780059814, "global_step": 547628, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9857549667358398, "global_step": 547629, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0796964168548584, "global_step": 547630, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.058668613433838, "global_step": 547631, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9850153923034668, "global_step": 547632, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9820791482925415, "global_step": 547633, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0139265060424805, "global_step": 547634, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.934943675994873, "global_step": 547635, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.097433090209961, "global_step": 547636, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.006261110305786, "global_step": 547637, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0274813175201416, "global_step": 547638, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.038323402404785, "global_step": 547639, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9603092670440674, "global_step": 547640, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0181403160095215, "global_step": 547641, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9747389554977417, "global_step": 547642, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0182132720947266, "global_step": 547643, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.061089038848877, "global_step": 547644, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0274362564086914, "global_step": 547645, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9926170110702515, "global_step": 547646, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1111881732940674, "global_step": 547647, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0996780395507812, "global_step": 547648, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.024015188217163, "global_step": 547649, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9396787881851196, "global_step": 547650, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.044609546661377, "global_step": 547651, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.10280179977417, "global_step": 547652, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0234923362731934, "global_step": 547653, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.008596181869507, "global_step": 547654, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0002644062042236, "global_step": 547655, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.009004831314087, "global_step": 547656, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9956551790237427, "global_step": 547657, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.180116653442383, "global_step": 547658, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9933894872665405, "global_step": 547659, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.068326473236084, "global_step": 547660, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9901777505874634, "global_step": 547661, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0342531204223633, "global_step": 547662, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0381109714508057, "global_step": 547663, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.032578706741333, "global_step": 547664, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.048234701156616, "global_step": 547665, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.051391839981079, "global_step": 547666, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0333921909332275, "global_step": 547667, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.073169231414795, "global_step": 547668, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.998990774154663, "global_step": 547669, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9443106651306152, "global_step": 547670, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.986218810081482, "global_step": 547671, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.004314422607422, "global_step": 547672, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0576910972595215, "global_step": 547673, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0284101963043213, "global_step": 547674, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0355584621429443, "global_step": 547675, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.032865047454834, "global_step": 547676, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0364530086517334, "global_step": 547677, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1386003494262695, "global_step": 547678, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.034274101257324, "global_step": 547679, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9856675863265991, "global_step": 547680, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9549310207366943, "global_step": 547681, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1240546703338623, "global_step": 547682, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0096051692962646, "global_step": 547683, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1579902172088623, "global_step": 547684, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0313072204589844, "global_step": 547685, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.029352903366089, "global_step": 547686, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.033613681793213, "global_step": 547687, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0885424613952637, "global_step": 547688, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9877790212631226, "global_step": 547689, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0593578815460205, "global_step": 547690, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0638577938079834, "global_step": 547691, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0291810035705566, "global_step": 547692, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.085069417953491, "global_step": 547693, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0753064155578613, "global_step": 547694, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.037970781326294, "global_step": 547695, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.936569094657898, "global_step": 547696, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0554416179656982, "global_step": 547697, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9549858570098877, "global_step": 547698, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.029285430908203, "global_step": 547699, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9981772899627686, "global_step": 547700, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0038435459136963, "global_step": 547701, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.046597957611084, "global_step": 547702, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.06477427482605, "global_step": 547703, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.051532745361328, "global_step": 547704, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.046792507171631, "global_step": 547705, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0634403228759766, "global_step": 547706, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0840466022491455, "global_step": 547707, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.031916618347168, "global_step": 547708, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.005309581756592, "global_step": 547709, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9761956930160522, "global_step": 547710, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9672755002975464, "global_step": 547711, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.121659755706787, "global_step": 547712, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0381808280944824, "global_step": 547713, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.029846429824829, "global_step": 547714, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.100193977355957, "global_step": 547715, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9742454290390015, "global_step": 547716, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0036303997039795, "global_step": 547717, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9782347679138184, "global_step": 547718, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0226023197174072, "global_step": 547719, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0094122886657715, "global_step": 547720, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0306169986724854, "global_step": 547721, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0035080909729004, "global_step": 547722, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0034775733947754, "global_step": 547723, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9543697834014893, "global_step": 547724, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9669122695922852, "global_step": 547725, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.090278148651123, "global_step": 547726, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.119950771331787, "global_step": 547727, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.981250286102295, "global_step": 547728, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0781731605529785, "global_step": 547729, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.992145299911499, "global_step": 547730, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0243406295776367, "global_step": 547731, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9571709632873535, "global_step": 547732, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0359292030334473, "global_step": 547733, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.023777723312378, "global_step": 547734, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.08004093170166, "global_step": 547735, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.051692008972168, "global_step": 547736, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0301170349121094, "global_step": 547737, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.082204818725586, "global_step": 547738, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9852125644683838, "global_step": 547739, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0423290729522705, "global_step": 547740, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.110180139541626, "global_step": 547741, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.002896308898926, "global_step": 547742, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0556857585906982, "global_step": 547743, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.018902063369751, "global_step": 547744, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1167407035827637, "global_step": 547745, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0132758617401123, "global_step": 547746, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0948333740234375, "global_step": 547747, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9865527153015137, "global_step": 547748, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9360698461532593, "global_step": 547749, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9626351594924927, "global_step": 547750, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9474374055862427, "global_step": 547751, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0606939792633057, "global_step": 547752, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.073437452316284, "global_step": 547753, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0325000286102295, "global_step": 547754, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.03149151802063, "global_step": 547755, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.039599657058716, "global_step": 547756, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.04541277885437, "global_step": 547757, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0048418045043945, "global_step": 547758, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0357871055603027, "global_step": 547759, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.01535701751709, "global_step": 547760, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.125460386276245, "global_step": 547761, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0757622718811035, "global_step": 547762, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.097100257873535, "global_step": 547763, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9793025255203247, "global_step": 547764, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.950923204421997, "global_step": 547765, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0471274852752686, "global_step": 547766, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0298373699188232, "global_step": 547767, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.015624761581421, "global_step": 547768, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0685970783233643, "global_step": 547769, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.061821937561035, "global_step": 547770, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.002401113510132, "global_step": 547771, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9757091999053955, "global_step": 547772, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0342071056365967, "global_step": 547773, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.066129207611084, "global_step": 547774, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9960031509399414, "global_step": 547775, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9965243339538574, "global_step": 547776, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0033669471740723, "global_step": 547777, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.034684658050537, "global_step": 547778, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.052663564682007, "global_step": 547779, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0841121673583984, "global_step": 547780, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0453953742980957, "global_step": 547781, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.043100357055664, "global_step": 547782, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0598092079162598, "global_step": 547783, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9913966655731201, "global_step": 547784, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9823130369186401, "global_step": 547785, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.963718295097351, "global_step": 547786, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.050424098968506, "global_step": 547787, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.920343041419983, "global_step": 547788, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.068023920059204, "global_step": 547789, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0892226696014404, "global_step": 547790, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0631203651428223, "global_step": 547791, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0569825172424316, "global_step": 547792, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9821217060089111, "global_step": 547793, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1091299057006836, "global_step": 547794, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0151851177215576, "global_step": 547795, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.002842664718628, "global_step": 547796, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0278356075286865, "global_step": 547797, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0446698665618896, "global_step": 547798, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0092132091522217, "global_step": 547799, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9707189798355103, "global_step": 547800, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.023362159729004, "global_step": 547801, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.140265941619873, "global_step": 547802, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.97885000705719, "global_step": 547803, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0363874435424805, "global_step": 547804, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.03429913520813, "global_step": 547805, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.05379319190979, "global_step": 547806, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.008901834487915, "global_step": 547807, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.956876516342163, "global_step": 547808, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.020963668823242, "global_step": 547809, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9690208435058594, "global_step": 547810, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.073721170425415, "global_step": 547811, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.943808913230896, "global_step": 547812, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.064833641052246, "global_step": 547813, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0313549041748047, "global_step": 547814, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.8935295343399048, "global_step": 547815, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9668354988098145, "global_step": 547816, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9497463703155518, "global_step": 547817, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.085249423980713, "global_step": 547818, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.090548276901245, "global_step": 547819, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.014977216720581, "global_step": 547820, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9778530597686768, "global_step": 547821, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0476043224334717, "global_step": 547822, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.107490301132202, "global_step": 547823, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0894346237182617, "global_step": 547824, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.987593650817871, "global_step": 547825, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.053734302520752, "global_step": 547826, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1281306743621826, "global_step": 547827, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0965793132781982, "global_step": 547828, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0239338874816895, "global_step": 547829, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0287251472473145, "global_step": 547830, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.077385663986206, "global_step": 547831, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0203914642333984, "global_step": 547832, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.096949815750122, "global_step": 547833, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0362303256988525, "global_step": 547834, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0384466648101807, "global_step": 547835, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0083372592926025, "global_step": 547836, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.039130687713623, "global_step": 547837, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0117084980010986, "global_step": 547838, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0818533897399902, "global_step": 547839, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0300545692443848, "global_step": 547840, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.050074338912964, "global_step": 547841, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0711324214935303, "global_step": 547842, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9815247058868408, "global_step": 547843, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9927587509155273, "global_step": 547844, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.997368335723877, "global_step": 547845, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0537030696868896, "global_step": 547846, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.990224003791809, "global_step": 547847, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.986098051071167, "global_step": 547848, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.025923252105713, "global_step": 547849, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.961869716644287, "global_step": 547850, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.045891523361206, "global_step": 547851, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.019364356994629, "global_step": 547852, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.045680046081543, "global_step": 547853, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9597159624099731, "global_step": 547854, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.091489791870117, "global_step": 547855, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.049388885498047, "global_step": 547856, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9727367162704468, "global_step": 547857, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.055067539215088, "global_step": 547858, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0145528316497803, "global_step": 547859, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0109760761260986, "global_step": 547860, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0308687686920166, "global_step": 547861, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.036811113357544, "global_step": 547862, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.026621103286743, "global_step": 547863, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.022474765777588, "global_step": 547864, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.031632900238037, "global_step": 547865, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0636544227600098, "global_step": 547866, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9588316679000854, "global_step": 547867, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.009730100631714, "global_step": 547868, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0029008388519287, "global_step": 547869, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.06381893157959, "global_step": 547870, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0245230197906494, "global_step": 547871, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9475339651107788, "global_step": 547872, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.037626028060913, "global_step": 547873, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.031937837600708, "global_step": 547874, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0278589725494385, "global_step": 547875, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0982916355133057, "global_step": 547876, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0618057250976562, "global_step": 547877, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.003880500793457, "global_step": 547878, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.094454765319824, "global_step": 547879, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9743613004684448, "global_step": 547880, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0113344192504883, "global_step": 547881, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0187795162200928, "global_step": 547882, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.104266881942749, "global_step": 547883, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9359771013259888, "global_step": 547884, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0356459617614746, "global_step": 547885, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0283989906311035, "global_step": 547886, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.989733338356018, "global_step": 547887, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.010847806930542, "global_step": 547888, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0224790573120117, "global_step": 547889, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0583691596984863, "global_step": 547890, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0235865116119385, "global_step": 547891, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.03863525390625, "global_step": 547892, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0701956748962402, "global_step": 547893, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.053250789642334, "global_step": 547894, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9396061897277832, "global_step": 547895, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.016789436340332, "global_step": 547896, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9360573291778564, "global_step": 547897, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0350232124328613, "global_step": 547898, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.011263132095337, "global_step": 547899, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0341010093688965, "global_step": 547900, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9561386108398438, "global_step": 547901, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9911131858825684, "global_step": 547902, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.019792079925537, "global_step": 547903, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9653384685516357, "global_step": 547904, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.999981164932251, "global_step": 547905, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0193846225738525, "global_step": 547906, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.019705295562744, "global_step": 547907, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9602956771850586, "global_step": 547908, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0474891662597656, "global_step": 547909, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0190370082855225, "global_step": 547910, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.036569595336914, "global_step": 547911, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.086076021194458, "global_step": 547912, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.086726665496826, "global_step": 547913, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9887738227844238, "global_step": 547914, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.026848793029785, "global_step": 547915, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.098836898803711, "global_step": 547916, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.05790376663208, "global_step": 547917, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9879937171936035, "global_step": 547918, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.018066644668579, "global_step": 547919, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0674757957458496, "global_step": 547920, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0041775703430176, "global_step": 547921, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.015937566757202, "global_step": 547922, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.025676727294922, "global_step": 547923, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9475938081741333, "global_step": 547924, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0571954250335693, "global_step": 547925, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0340030193328857, "global_step": 547926, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.8740350008010864, "global_step": 547927, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0242185592651367, "global_step": 547928, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0504448413848877, "global_step": 547929, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0557713508605957, "global_step": 547930, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0092082023620605, "global_step": 547931, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.026414394378662, "global_step": 547932, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1130077838897705, "global_step": 547933, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.011549472808838, "global_step": 547934, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0505456924438477, "global_step": 547935, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0378806591033936, "global_step": 547936, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0485804080963135, "global_step": 547937, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0295112133026123, "global_step": 547938, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9462411403656006, "global_step": 547939, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.041018009185791, "global_step": 547940, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.03804087638855, "global_step": 547941, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0487093925476074, "global_step": 547942, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0520241260528564, "global_step": 547943, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0330862998962402, "global_step": 547944, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.977872610092163, "global_step": 547945, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0748445987701416, "global_step": 547946, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0435333251953125, "global_step": 547947, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1092305183410645, "global_step": 547948, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.037797212600708, "global_step": 547949, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0465517044067383, "global_step": 547950, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0107204914093018, "global_step": 547951, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.966731309890747, "global_step": 547952, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0868752002716064, "global_step": 547953, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.046613931655884, "global_step": 547954, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0752408504486084, "global_step": 547955, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.025693893432617, "global_step": 547956, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9280331134796143, "global_step": 547957, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0842089653015137, "global_step": 547958, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.005532741546631, "global_step": 547959, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0926826000213623, "global_step": 547960, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.992834448814392, "global_step": 547961, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9621697664260864, "global_step": 547962, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1398158073425293, "global_step": 547963, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0766332149505615, "global_step": 547964, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.014982223510742, "global_step": 547965, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.002685070037842, "global_step": 547966, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9669172763824463, "global_step": 547967, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0123748779296875, "global_step": 547968, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.047926664352417, "global_step": 547969, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1756722927093506, "global_step": 547970, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.975076675415039, "global_step": 547971, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0541436672210693, "global_step": 547972, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.036011219024658, "global_step": 547973, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.024402141571045, "global_step": 547974, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9729068279266357, "global_step": 547975, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0425493717193604, "global_step": 547976, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9908227920532227, "global_step": 547977, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9963719844818115, "global_step": 547978, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.991796612739563, "global_step": 547979, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0002644062042236, "global_step": 547980, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.981695532798767, "global_step": 547981, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.075378894805908, "global_step": 547982, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0782673358917236, "global_step": 547983, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9820661544799805, "global_step": 547984, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0058200359344482, "global_step": 547985, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0155110359191895, "global_step": 547986, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.97061026096344, "global_step": 547987, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0250625610351562, "global_step": 547988, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.002774715423584, "global_step": 547989, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.981243371963501, "global_step": 547990, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.073526382446289, "global_step": 547991, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.009599208831787, "global_step": 547992, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0898568630218506, "global_step": 547993, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.017592191696167, "global_step": 547994, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.949491262435913, "global_step": 547995, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.910646677017212, "global_step": 547996, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0479726791381836, "global_step": 547997, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1014013290405273, "global_step": 547998, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0883774757385254, "global_step": 547999, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0826687812805176, "global_step": 548000, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0518059730529785, "global_step": 548001, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0527095794677734, "global_step": 548002, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.085833787918091, "global_step": 548003, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9974015951156616, "global_step": 548004, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0417909622192383, "global_step": 548005, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9963892698287964, "global_step": 548006, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.933496117591858, "global_step": 548007, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.976154088973999, "global_step": 548008, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.094575881958008, "global_step": 548009, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0160746574401855, "global_step": 548010, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.952146053314209, "global_step": 548011, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.035984754562378, "global_step": 548012, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0534486770629883, "global_step": 548013, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0784687995910645, "global_step": 548014, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0560641288757324, "global_step": 548015, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0547847747802734, "global_step": 548016, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.129253387451172, "global_step": 548017, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9524773359298706, "global_step": 548018, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.158391237258911, "global_step": 548019, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0398430824279785, "global_step": 548020, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0023093223571777, "global_step": 548021, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0313334465026855, "global_step": 548022, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1057043075561523, "global_step": 548023, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.021603584289551, "global_step": 548024, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0393872261047363, "global_step": 548025, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0913703441619873, "global_step": 548026, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1190433502197266, "global_step": 548027, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0523033142089844, "global_step": 548028, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0296261310577393, "global_step": 548029, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.041381597518921, "global_step": 548030, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0705952644348145, "global_step": 548031, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9598264694213867, "global_step": 548032, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9541754722595215, "global_step": 548033, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0339431762695312, "global_step": 548034, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0191054344177246, "global_step": 548035, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.004754066467285, "global_step": 548036, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9526728391647339, "global_step": 548037, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.032362461090088, "global_step": 548038, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.015043258666992, "global_step": 548039, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0609610080718994, "global_step": 548040, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0759165287017822, "global_step": 548041, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0186100006103516, "global_step": 548042, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.132920980453491, "global_step": 548043, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.060276508331299, "global_step": 548044, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.018738269805908, "global_step": 548045, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.039564609527588, "global_step": 548046, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9656150341033936, "global_step": 548047, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9664103984832764, "global_step": 548048, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.008960485458374, "global_step": 548049, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0139198303222656, "global_step": 548050, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.027362108230591, "global_step": 548051, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.063112497329712, "global_step": 548052, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0252881050109863, "global_step": 548053, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0750579833984375, "global_step": 548054, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0270018577575684, "global_step": 548055, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.993286371231079, "global_step": 548056, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.967743158340454, "global_step": 548057, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.110197067260742, "global_step": 548058, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.093456983566284, "global_step": 548059, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0347158908843994, "global_step": 548060, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0210752487182617, "global_step": 548061, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.099541187286377, "global_step": 548062, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.024860382080078, "global_step": 548063, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1132168769836426, "global_step": 548064, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.083564519882202, "global_step": 548065, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.040112018585205, "global_step": 548066, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0798585414886475, "global_step": 548067, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.063878297805786, "global_step": 548068, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.080723285675049, "global_step": 548069, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0570261478424072, "global_step": 548070, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.025268077850342, "global_step": 548071, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0674641132354736, "global_step": 548072, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9840812683105469, "global_step": 548073, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.026947498321533, "global_step": 548074, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.041114568710327, "global_step": 548075, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.007535934448242, "global_step": 548076, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.024073362350464, "global_step": 548077, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9959102869033813, "global_step": 548078, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9976965188980103, "global_step": 548079, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.036287784576416, "global_step": 548080, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.046241283416748, "global_step": 548081, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.150883913040161, "global_step": 548082, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.019646644592285, "global_step": 548083, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0458526611328125, "global_step": 548084, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0203583240509033, "global_step": 548085, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.014864444732666, "global_step": 548086, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.039661407470703, "global_step": 548087, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0246150493621826, "global_step": 548088, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0021846294403076, "global_step": 548089, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0316600799560547, "global_step": 548090, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0300991535186768, "global_step": 548091, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.150348663330078, "global_step": 548092, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0471813678741455, "global_step": 548093, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9791721105575562, "global_step": 548094, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1183865070343018, "global_step": 548095, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0014522075653076, "global_step": 548096, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.047214984893799, "global_step": 548097, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0201828479766846, "global_step": 548098, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0674989223480225, "global_step": 548099, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9854077100753784, "global_step": 548100, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9434702396392822, "global_step": 548101, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.019956111907959, "global_step": 548102, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0438902378082275, "global_step": 548103, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0201518535614014, "global_step": 548104, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9787627458572388, "global_step": 548105, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.976033329963684, "global_step": 548106, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0102970600128174, "global_step": 548107, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0470187664031982, "global_step": 548108, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0496180057525635, "global_step": 548109, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.04406476020813, "global_step": 548110, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9234774112701416, "global_step": 548111, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.056089162826538, "global_step": 548112, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.019707202911377, "global_step": 548113, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0172736644744873, "global_step": 548114, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.012751340866089, "global_step": 548115, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0404915809631348, "global_step": 548116, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.006891965866089, "global_step": 548117, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9948902130126953, "global_step": 548118, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0771384239196777, "global_step": 548119, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.017733573913574, "global_step": 548120, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1119563579559326, "global_step": 548121, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9924453496932983, "global_step": 548122, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0314321517944336, "global_step": 548123, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.014225721359253, "global_step": 548124, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0782086849212646, "global_step": 548125, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0214569568634033, "global_step": 548126, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9903929233551025, "global_step": 548127, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.033752679824829, "global_step": 548128, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9546092748641968, "global_step": 548129, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.037302255630493, "global_step": 548130, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.018294334411621, "global_step": 548131, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0649566650390625, "global_step": 548132, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.054431676864624, "global_step": 548133, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0836498737335205, "global_step": 548134, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0514626502990723, "global_step": 548135, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0465524196624756, "global_step": 548136, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9804097414016724, "global_step": 548137, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0506837368011475, "global_step": 548138, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9089233875274658, "global_step": 548139, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1010515689849854, "global_step": 548140, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.129462242126465, "global_step": 548141, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0819926261901855, "global_step": 548142, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.011730194091797, "global_step": 548143, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.93535578250885, "global_step": 548144, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9150882959365845, "global_step": 548145, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9087094068527222, "global_step": 548146, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.067112922668457, "global_step": 548147, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9717133045196533, "global_step": 548148, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0371432304382324, "global_step": 548149, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.978886604309082, "global_step": 548150, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0840179920196533, "global_step": 548151, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.080223321914673, "global_step": 548152, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9615895748138428, "global_step": 548153, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.098689556121826, "global_step": 548154, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.994132161140442, "global_step": 548155, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.020977020263672, "global_step": 548156, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9800622463226318, "global_step": 548157, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0618436336517334, "global_step": 548158, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1498610973358154, "global_step": 548159, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9399502277374268, "global_step": 548160, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.997096300125122, "global_step": 548161, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0990023612976074, "global_step": 548162, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0565097332000732, "global_step": 548163, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9947855472564697, "global_step": 548164, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0356523990631104, "global_step": 548165, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.041317939758301, "global_step": 548166, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.034240245819092, "global_step": 548167, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0980868339538574, "global_step": 548168, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0828566551208496, "global_step": 548169, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.007493257522583, "global_step": 548170, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.003401517868042, "global_step": 548171, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.038844585418701, "global_step": 548172, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.05110764503479, "global_step": 548173, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.024042844772339, "global_step": 548174, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0310986042022705, "global_step": 548175, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0489866733551025, "global_step": 548176, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0698375701904297, "global_step": 548177, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1175217628479004, "global_step": 548178, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9982707500457764, "global_step": 548179, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.117033004760742, "global_step": 548180, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0366756916046143, "global_step": 548181, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.061001777648926, "global_step": 548182, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.048539161682129, "global_step": 548183, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9801138639450073, "global_step": 548184, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0693180561065674, "global_step": 548185, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0680465698242188, "global_step": 548186, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9600012302398682, "global_step": 548187, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.043065309524536, "global_step": 548188, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0193281173706055, "global_step": 548189, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9927695989608765, "global_step": 548190, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.995314121246338, "global_step": 548191, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.025440216064453, "global_step": 548192, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0863137245178223, "global_step": 548193, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9813785552978516, "global_step": 548194, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.014165163040161, "global_step": 548195, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.012532949447632, "global_step": 548196, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0428524017333984, "global_step": 548197, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0349409580230713, "global_step": 548198, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9974113702774048, "global_step": 548199, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.108205556869507, "global_step": 548200, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.058436870574951, "global_step": 548201, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.048227310180664, "global_step": 548202, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0603673458099365, "global_step": 548203, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0092976093292236, "global_step": 548204, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9874639511108398, "global_step": 548205, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9679347276687622, "global_step": 548206, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.047166109085083, "global_step": 548207, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.962223768234253, "global_step": 548208, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.071265697479248, "global_step": 548209, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1456191539764404, "global_step": 548210, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.929006576538086, "global_step": 548211, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.069530487060547, "global_step": 548212, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0810906887054443, "global_step": 548213, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.936076283454895, "global_step": 548214, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9732110500335693, "global_step": 548215, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0971105098724365, "global_step": 548216, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9545235633850098, "global_step": 548217, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0511109828948975, "global_step": 548218, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.067617177963257, "global_step": 548219, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9583559036254883, "global_step": 548220, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0083510875701904, "global_step": 548221, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.952042579650879, "global_step": 548222, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1893680095672607, "global_step": 548223, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0673282146453857, "global_step": 548224, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9919929504394531, "global_step": 548225, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0889029502868652, "global_step": 548226, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0566163063049316, "global_step": 548227, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0699148178100586, "global_step": 548228, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.134033441543579, "global_step": 548229, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.041116714477539, "global_step": 548230, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9672681093215942, "global_step": 548231, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.011850357055664, "global_step": 548232, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0155131816864014, "global_step": 548233, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.097780466079712, "global_step": 548234, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0107250213623047, "global_step": 548235, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9518803358078003, "global_step": 548236, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0780422687530518, "global_step": 548237, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.042933225631714, "global_step": 548238, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.006622791290283, "global_step": 548239, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9907796382904053, "global_step": 548240, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.014094114303589, "global_step": 548241, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0848753452301025, "global_step": 548242, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.054021120071411, "global_step": 548243, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0712697505950928, "global_step": 548244, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0482983589172363, "global_step": 548245, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0479931831359863, "global_step": 548246, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0099050998687744, "global_step": 548247, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.042405128479004, "global_step": 548248, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.024068832397461, "global_step": 548249, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.036583185195923, "global_step": 548250, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.108494997024536, "global_step": 548251, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.028934955596924, "global_step": 548252, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.058610439300537, "global_step": 548253, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.07381272315979, "global_step": 548254, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9654183387756348, "global_step": 548255, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.058088779449463, "global_step": 548256, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0530319213867188, "global_step": 548257, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9518463611602783, "global_step": 548258, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0617144107818604, "global_step": 548259, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0409111976623535, "global_step": 548260, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0123870372772217, "global_step": 548261, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.984351396560669, "global_step": 548262, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0414037704467773, "global_step": 548263, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1485342979431152, "global_step": 548264, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0234436988830566, "global_step": 548265, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9956852197647095, "global_step": 548266, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.02555513381958, "global_step": 548267, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0028929710388184, "global_step": 548268, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0001232624053955, "global_step": 548269, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1236493587493896, "global_step": 548270, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9775216579437256, "global_step": 548271, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.011599063873291, "global_step": 548272, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0671944618225098, "global_step": 548273, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.044374704360962, "global_step": 548274, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.026947498321533, "global_step": 548275, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0218584537506104, "global_step": 548276, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.049269437789917, "global_step": 548277, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.051471471786499, "global_step": 548278, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.051640748977661, "global_step": 548279, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0649561882019043, "global_step": 548280, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9890657663345337, "global_step": 548281, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0409936904907227, "global_step": 548282, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.088326930999756, "global_step": 548283, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9863691329956055, "global_step": 548284, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.070523738861084, "global_step": 548285, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.026561975479126, "global_step": 548286, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.041794776916504, "global_step": 548287, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9767032861709595, "global_step": 548288, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9883497953414917, "global_step": 548289, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0156426429748535, "global_step": 548290, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.042273759841919, "global_step": 548291, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0478150844573975, "global_step": 548292, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0404984951019287, "global_step": 548293, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9643080234527588, "global_step": 548294, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0069644451141357, "global_step": 548295, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.021367311477661, "global_step": 548296, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0404577255249023, "global_step": 548297, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0302398204803467, "global_step": 548298, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0762054920196533, "global_step": 548299, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.072305917739868, "global_step": 548300, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.067762613296509, "global_step": 548301, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0829787254333496, "global_step": 548302, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9982784986495972, "global_step": 548303, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.003537654876709, "global_step": 548304, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0479397773742676, "global_step": 548305, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0001614093780518, "global_step": 548306, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0366945266723633, "global_step": 548307, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0033137798309326, "global_step": 548308, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0785839557647705, "global_step": 548309, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.088469982147217, "global_step": 548310, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0152766704559326, "global_step": 548311, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0849123001098633, "global_step": 548312, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1217663288116455, "global_step": 548313, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0452799797058105, "global_step": 548314, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.02378511428833, "global_step": 548315, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.105494976043701, "global_step": 548316, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.088242292404175, "global_step": 548317, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0511691570281982, "global_step": 548318, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.987667441368103, "global_step": 548319, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.021174192428589, "global_step": 548320, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9687296152114868, "global_step": 548321, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0815560817718506, "global_step": 548322, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0245413780212402, "global_step": 548323, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0294268131256104, "global_step": 548324, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.084531784057617, "global_step": 548325, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.967198371887207, "global_step": 548326, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9895572662353516, "global_step": 548327, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.034820556640625, "global_step": 548328, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9789881706237793, "global_step": 548329, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0748953819274902, "global_step": 548330, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9980556964874268, "global_step": 548331, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.008474349975586, "global_step": 548332, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.010972499847412, "global_step": 548333, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.060887098312378, "global_step": 548334, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.058727502822876, "global_step": 548335, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.055262565612793, "global_step": 548336, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.033884286880493, "global_step": 548337, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0769083499908447, "global_step": 548338, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.2047576904296875, "global_step": 548339, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9821362495422363, "global_step": 548340, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.053318738937378, "global_step": 548341, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.033475875854492, "global_step": 548342, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0350122451782227, "global_step": 548343, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.024631977081299, "global_step": 548344, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9955793619155884, "global_step": 548345, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9129544496536255, "global_step": 548346, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9915448427200317, "global_step": 548347, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.027996778488159, "global_step": 548348, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.089803457260132, "global_step": 548349, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.009181022644043, "global_step": 548350, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0186030864715576, "global_step": 548351, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9759588241577148, "global_step": 548352, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9929461479187012, "global_step": 548353, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0366930961608887, "global_step": 548354, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0169005393981934, "global_step": 548355, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1654322147369385, "global_step": 548356, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.011950969696045, "global_step": 548357, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0200393199920654, "global_step": 548358, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.924608826637268, "global_step": 548359, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0528769493103027, "global_step": 548360, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0460662841796875, "global_step": 548361, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9936670064926147, "global_step": 548362, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0624074935913086, "global_step": 548363, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0420756340026855, "global_step": 548364, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9523160457611084, "global_step": 548365, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0442187786102295, "global_step": 548366, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0687410831451416, "global_step": 548367, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9887232780456543, "global_step": 548368, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9889029264450073, "global_step": 548369, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0775933265686035, "global_step": 548370, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0758614540100098, "global_step": 548371, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0568137168884277, "global_step": 548372, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.090616226196289, "global_step": 548373, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1276938915252686, "global_step": 548374, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.979069709777832, "global_step": 548375, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.960975170135498, "global_step": 548376, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9958523511886597, "global_step": 548377, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.060389757156372, "global_step": 548378, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0650837421417236, "global_step": 548379, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.062227487564087, "global_step": 548380, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9684712886810303, "global_step": 548381, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0842678546905518, "global_step": 548382, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1375231742858887, "global_step": 548383, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.005159616470337, "global_step": 548384, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9749921560287476, "global_step": 548385, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9490429162979126, "global_step": 548386, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0912394523620605, "global_step": 548387, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.026721954345703, "global_step": 548388, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9824929237365723, "global_step": 548389, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0322372913360596, "global_step": 548390, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0954086780548096, "global_step": 548391, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.052488088607788, "global_step": 548392, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0552377700805664, "global_step": 548393, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.010389566421509, "global_step": 548394, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.05399489402771, "global_step": 548395, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0063183307647705, "global_step": 548396, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.066469669342041, "global_step": 548397, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.043632745742798, "global_step": 548398, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0589468479156494, "global_step": 548399, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.060973882675171, "global_step": 548400, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.037012815475464, "global_step": 548401, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.118767261505127, "global_step": 548402, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0680572986602783, "global_step": 548403, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9322350025177002, "global_step": 548404, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.005251407623291, "global_step": 548405, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.003777027130127, "global_step": 548406, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1006667613983154, "global_step": 548407, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0148913860321045, "global_step": 548408, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.036242723464966, "global_step": 548409, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.035545825958252, "global_step": 548410, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9925591945648193, "global_step": 548411, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.076068639755249, "global_step": 548412, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0986239910125732, "global_step": 548413, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0036978721618652, "global_step": 548414, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9855308532714844, "global_step": 548415, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.01474666595459, "global_step": 548416, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9937798976898193, "global_step": 548417, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.105769395828247, "global_step": 548418, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1374614238739014, "global_step": 548419, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0692129135131836, "global_step": 548420, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.062730550765991, "global_step": 548421, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9897900819778442, "global_step": 548422, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0602169036865234, "global_step": 548423, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9722652435302734, "global_step": 548424, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0593020915985107, "global_step": 548425, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9661701917648315, "global_step": 548426, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.141144037246704, "global_step": 548427, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0127551555633545, "global_step": 548428, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0131075382232666, "global_step": 548429, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9803409576416016, "global_step": 548430, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.046586036682129, "global_step": 548431, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0660502910614014, "global_step": 548432, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.044818878173828, "global_step": 548433, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.113961696624756, "global_step": 548434, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.066850185394287, "global_step": 548435, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0863583087921143, "global_step": 548436, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.011791944503784, "global_step": 548437, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0198867321014404, "global_step": 548438, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.133580446243286, "global_step": 548439, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.063582181930542, "global_step": 548440, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9319300651550293, "global_step": 548441, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.025794744491577, "global_step": 548442, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9563300609588623, "global_step": 548443, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0314295291900635, "global_step": 548444, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0373318195343018, "global_step": 548445, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0344443321228027, "global_step": 548446, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.037074089050293, "global_step": 548447, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9982898235321045, "global_step": 548448, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0205423831939697, "global_step": 548449, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.023474931716919, "global_step": 548450, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0103466510772705, "global_step": 548451, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0067977905273438, "global_step": 548452, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9735784530639648, "global_step": 548453, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9874227046966553, "global_step": 548454, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0799105167388916, "global_step": 548455, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9887166023254395, "global_step": 548456, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0858888626098633, "global_step": 548457, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.067673921585083, "global_step": 548458, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.044196128845215, "global_step": 548459, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0570569038391113, "global_step": 548460, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0302300453186035, "global_step": 548461, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0249390602111816, "global_step": 548462, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.045973539352417, "global_step": 548463, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.970001459121704, "global_step": 548464, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0406289100646973, "global_step": 548465, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.122514486312866, "global_step": 548466, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.124016284942627, "global_step": 548467, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9658912420272827, "global_step": 548468, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0360491275787354, "global_step": 548469, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.070472002029419, "global_step": 548470, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1172304153442383, "global_step": 548471, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1130499839782715, "global_step": 548472, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0626986026763916, "global_step": 548473, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.020902633666992, "global_step": 548474, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0841574668884277, "global_step": 548475, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0331761837005615, "global_step": 548476, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0526082515716553, "global_step": 548477, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0529427528381348, "global_step": 548478, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9791408777236938, "global_step": 548479, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.036619186401367, "global_step": 548480, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0559499263763428, "global_step": 548481, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9260165691375732, "global_step": 548482, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9838629961013794, "global_step": 548483, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.033327579498291, "global_step": 548484, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.039914131164551, "global_step": 548485, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0084710121154785, "global_step": 548486, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.053771495819092, "global_step": 548487, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0475285053253174, "global_step": 548488, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.057486057281494, "global_step": 548489, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0347914695739746, "global_step": 548490, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.035708427429199, "global_step": 548491, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9784268140792847, "global_step": 548492, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.996199607849121, "global_step": 548493, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.003114938735962, "global_step": 548494, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1235125064849854, "global_step": 548495, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9736552238464355, "global_step": 548496, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.964949131011963, "global_step": 548497, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9952203035354614, "global_step": 548498, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.026822805404663, "global_step": 548499, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1160097122192383, "global_step": 548500, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0320920944213867, "global_step": 548501, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.080026865005493, "global_step": 548502, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0642600059509277, "global_step": 548503, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0569119453430176, "global_step": 548504, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.141850709915161, "global_step": 548505, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1154894828796387, "global_step": 548506, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.039224863052368, "global_step": 548507, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.159127712249756, "global_step": 548508, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0540249347686768, "global_step": 548509, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0881927013397217, "global_step": 548510, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.070188045501709, "global_step": 548511, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0304388999938965, "global_step": 548512, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9883596897125244, "global_step": 548513, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0710904598236084, "global_step": 548514, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0616860389709473, "global_step": 548515, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9590659141540527, "global_step": 548516, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0423531532287598, "global_step": 548517, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.011705160140991, "global_step": 548518, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.023792028427124, "global_step": 548519, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.09610915184021, "global_step": 548520, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9384493827819824, "global_step": 548521, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0529472827911377, "global_step": 548522, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0989253520965576, "global_step": 548523, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0809028148651123, "global_step": 548524, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0896706581115723, "global_step": 548525, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0906667709350586, "global_step": 548526, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9808770418167114, "global_step": 548527, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.152151346206665, "global_step": 548528, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.037929058074951, "global_step": 548529, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0496280193328857, "global_step": 548530, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9522017240524292, "global_step": 548531, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9844430685043335, "global_step": 548532, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.057798385620117, "global_step": 548533, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.021319627761841, "global_step": 548534, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.073469877243042, "global_step": 548535, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.103374481201172, "global_step": 548536, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.123814821243286, "global_step": 548537, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0572197437286377, "global_step": 548538, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.084610939025879, "global_step": 548539, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.034170389175415, "global_step": 548540, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.077922821044922, "global_step": 548541, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.003486394882202, "global_step": 548542, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.033724784851074, "global_step": 548543, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0067331790924072, "global_step": 548544, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.052433490753174, "global_step": 548545, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.066960334777832, "global_step": 548546, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0500996112823486, "global_step": 548547, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1062333583831787, "global_step": 548548, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0231025218963623, "global_step": 548549, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0561323165893555, "global_step": 548550, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.091229200363159, "global_step": 548551, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0578269958496094, "global_step": 548552, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0239713191986084, "global_step": 548553, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9740806818008423, "global_step": 548554, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.056424140930176, "global_step": 548555, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0382192134857178, "global_step": 548556, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.034209966659546, "global_step": 548557, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0547497272491455, "global_step": 548558, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9875329732894897, "global_step": 548559, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.088716983795166, "global_step": 548560, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.980881690979004, "global_step": 548561, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.052766799926758, "global_step": 548562, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.130190134048462, "global_step": 548563, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0214080810546875, "global_step": 548564, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1274890899658203, "global_step": 548565, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0366458892822266, "global_step": 548566, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9977773427963257, "global_step": 548567, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1225156784057617, "global_step": 548568, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.058915615081787, "global_step": 548569, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.1141910552978516, "global_step": 548570, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9940773248672485, "global_step": 548571, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.036298990249634, "global_step": 548572, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0419790744781494, "global_step": 548573, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0632922649383545, "global_step": 548574, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9783134460449219, "global_step": 548575, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0089967250823975, "global_step": 548576, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.120755195617676, "global_step": 548577, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9914308786392212, "global_step": 548578, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.020317554473877, "global_step": 548579, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.017864465713501, "global_step": 548580, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0356318950653076, "global_step": 548581, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.047278642654419, "global_step": 548582, "epoch": 915, "lr": 5e-05}
{"train_loss": 1.9801647663116455, "global_step": 548583, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0349819660186768, "global_step": 548584, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.090639352798462, "global_step": 548585, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.0330867767333984, "global_step": 548586, "epoch": 915, "lr": 5e-05}
{"train_loss": 2.046013832092285, "global_step": 548587, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0334270000457764, "global_step": 548588, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9867424964904785, "global_step": 548589, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9709233045578003, "global_step": 548590, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9361963272094727, "global_step": 548591, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.98615562915802, "global_step": 548592, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0033040046691895, "global_step": 548593, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9819974899291992, "global_step": 548594, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.036407947540283, "global_step": 548595, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0884287357330322, "global_step": 548596, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0905935764312744, "global_step": 548597, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9750515222549438, "global_step": 548598, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0224077701568604, "global_step": 548599, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0950732231140137, "global_step": 548600, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.037745475769043, "global_step": 548601, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.011826515197754, "global_step": 548602, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.086138963699341, "global_step": 548603, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9796500205993652, "global_step": 548604, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9908941984176636, "global_step": 548605, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9995383024215698, "global_step": 548606, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.063516855239868, "global_step": 548607, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.020291566848755, "global_step": 548608, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.117852210998535, "global_step": 548609, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0808277130126953, "global_step": 548610, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.036257743835449, "global_step": 548611, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.084684371948242, "global_step": 548612, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9701764583587646, "global_step": 548613, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0516109466552734, "global_step": 548614, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0695953369140625, "global_step": 548615, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9870916604995728, "global_step": 548616, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.070194959640503, "global_step": 548617, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.039266347885132, "global_step": 548618, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0380165576934814, "global_step": 548619, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0336954593658447, "global_step": 548620, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.025266408920288, "global_step": 548621, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.07242488861084, "global_step": 548622, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0057034492492676, "global_step": 548623, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0330193042755127, "global_step": 548624, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.994146704673767, "global_step": 548625, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0021002292633057, "global_step": 548626, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.09421443939209, "global_step": 548627, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.076749086380005, "global_step": 548628, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.016818046569824, "global_step": 548629, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.934867262840271, "global_step": 548630, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.049098014831543, "global_step": 548631, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0441219806671143, "global_step": 548632, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.068354845046997, "global_step": 548633, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9822582006454468, "global_step": 548634, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0248830318450928, "global_step": 548635, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.076216220855713, "global_step": 548636, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9924579858779907, "global_step": 548637, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9542776346206665, "global_step": 548638, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0919225215911865, "global_step": 548639, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.026280641555786, "global_step": 548640, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0854134559631348, "global_step": 548641, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0366311073303223, "global_step": 548642, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9886292219161987, "global_step": 548643, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0134575366973877, "global_step": 548644, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9690111875534058, "global_step": 548645, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.046048641204834, "global_step": 548646, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.054633140563965, "global_step": 548647, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.948795199394226, "global_step": 548648, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.060368776321411, "global_step": 548649, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0428287982940674, "global_step": 548650, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0677266120910645, "global_step": 548651, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.076467514038086, "global_step": 548652, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0062642097473145, "global_step": 548653, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9807523488998413, "global_step": 548654, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.016903877258301, "global_step": 548655, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9917079210281372, "global_step": 548656, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1038053035736084, "global_step": 548657, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9745110273361206, "global_step": 548658, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0627799034118652, "global_step": 548659, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.087254524230957, "global_step": 548660, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0164289474487305, "global_step": 548661, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.035942554473877, "global_step": 548662, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0577380657196045, "global_step": 548663, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9586033821105957, "global_step": 548664, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.060105323791504, "global_step": 548665, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.023664712905884, "global_step": 548666, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0253565311431885, "global_step": 548667, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.06026029586792, "global_step": 548668, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.001384735107422, "global_step": 548669, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9940218925476074, "global_step": 548670, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0985138416290283, "global_step": 548671, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.053679943084717, "global_step": 548672, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9884953498840332, "global_step": 548673, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0224432945251465, "global_step": 548674, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0133450031280518, "global_step": 548675, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.026402711868286, "global_step": 548676, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9651378393173218, "global_step": 548677, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.032630443572998, "global_step": 548678, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9761412143707275, "global_step": 548679, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.016439437866211, "global_step": 548680, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.030576705932617, "global_step": 548681, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9733508825302124, "global_step": 548682, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9798113107681274, "global_step": 548683, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9558584690093994, "global_step": 548684, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9555517435073853, "global_step": 548685, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0514533519744873, "global_step": 548686, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0970327854156494, "global_step": 548687, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.032130718231201, "global_step": 548688, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9975507259368896, "global_step": 548689, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.983489751815796, "global_step": 548690, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9469846487045288, "global_step": 548691, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0733535289764404, "global_step": 548692, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9840023517608643, "global_step": 548693, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.052041530609131, "global_step": 548694, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9438016414642334, "global_step": 548695, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0038928985595703, "global_step": 548696, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9805595874786377, "global_step": 548697, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9307506084442139, "global_step": 548698, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9566720724105835, "global_step": 548699, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.089437246322632, "global_step": 548700, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9536161422729492, "global_step": 548701, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0424180030822754, "global_step": 548702, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9986571073532104, "global_step": 548703, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0174803733825684, "global_step": 548704, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0721964836120605, "global_step": 548705, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0136053562164307, "global_step": 548706, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.067613363265991, "global_step": 548707, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0400333404541016, "global_step": 548708, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0409369468688965, "global_step": 548709, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.055112600326538, "global_step": 548710, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9706634283065796, "global_step": 548711, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9583028554916382, "global_step": 548712, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.996281385421753, "global_step": 548713, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0589914321899414, "global_step": 548714, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9853968620300293, "global_step": 548715, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.027388334274292, "global_step": 548716, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9688270092010498, "global_step": 548717, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0345993041992188, "global_step": 548718, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9657740592956543, "global_step": 548719, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.896509051322937, "global_step": 548720, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0307445526123047, "global_step": 548721, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.032707691192627, "global_step": 548722, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9056185483932495, "global_step": 548723, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.008852481842041, "global_step": 548724, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9614534378051758, "global_step": 548725, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.99105703830719, "global_step": 548726, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.130187749862671, "global_step": 548727, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.09958553314209, "global_step": 548728, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0147814750671387, "global_step": 548729, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.960873007774353, "global_step": 548730, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0055253505706787, "global_step": 548731, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.025359630584717, "global_step": 548732, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.134045362472534, "global_step": 548733, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0066301822662354, "global_step": 548734, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9987174272537231, "global_step": 548735, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.039001703262329, "global_step": 548736, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9902660846710205, "global_step": 548737, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.059878349304199, "global_step": 548738, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.035318613052368, "global_step": 548739, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9066699743270874, "global_step": 548740, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9691742658615112, "global_step": 548741, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.984336018562317, "global_step": 548742, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0921220779418945, "global_step": 548743, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.05902099609375, "global_step": 548744, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0862529277801514, "global_step": 548745, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0627214908599854, "global_step": 548746, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0919439792633057, "global_step": 548747, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.042747974395752, "global_step": 548748, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.009190559387207, "global_step": 548749, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.050010919570923, "global_step": 548750, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.011301279067993, "global_step": 548751, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.022749423980713, "global_step": 548752, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9998971223831177, "global_step": 548753, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.095998525619507, "global_step": 548754, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.009634256362915, "global_step": 548755, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.03483247756958, "global_step": 548756, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0617237091064453, "global_step": 548757, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1396636962890625, "global_step": 548758, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0107803344726562, "global_step": 548759, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9767495393753052, "global_step": 548760, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0341811180114746, "global_step": 548761, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0133678913116455, "global_step": 548762, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.104266405105591, "global_step": 548763, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9677263498306274, "global_step": 548764, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9994275569915771, "global_step": 548765, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.988847255706787, "global_step": 548766, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.061803102493286, "global_step": 548767, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.04974102973938, "global_step": 548768, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0196502208709717, "global_step": 548769, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.006666898727417, "global_step": 548770, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.993520736694336, "global_step": 548771, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0560836791992188, "global_step": 548772, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.987693190574646, "global_step": 548773, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0240275859832764, "global_step": 548774, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.074333429336548, "global_step": 548775, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.015984296798706, "global_step": 548776, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.975824236869812, "global_step": 548777, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0613181591033936, "global_step": 548778, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.033515453338623, "global_step": 548779, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9841469526290894, "global_step": 548780, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0094523429870605, "global_step": 548781, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.023003101348877, "global_step": 548782, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0039114952087402, "global_step": 548783, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9165771007537842, "global_step": 548784, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9791836738586426, "global_step": 548785, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0345962047576904, "global_step": 548786, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.064560890197754, "global_step": 548787, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9675531387329102, "global_step": 548788, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0355007648468018, "global_step": 548789, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.041301965713501, "global_step": 548790, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.966235876083374, "global_step": 548791, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0013294219970703, "global_step": 548792, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0399582386016846, "global_step": 548793, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9940799474716187, "global_step": 548794, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.100101947784424, "global_step": 548795, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.099865436553955, "global_step": 548796, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9797762632369995, "global_step": 548797, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0338048934936523, "global_step": 548798, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0374019145965576, "global_step": 548799, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9702963829040527, "global_step": 548800, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0141148567199707, "global_step": 548801, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0328354835510254, "global_step": 548802, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9700019359588623, "global_step": 548803, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9965900182724, "global_step": 548804, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9866868257522583, "global_step": 548805, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9774245023727417, "global_step": 548806, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.990787386894226, "global_step": 548807, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0233371257781982, "global_step": 548808, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9934183359146118, "global_step": 548809, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0250027179718018, "global_step": 548810, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0002880096435547, "global_step": 548811, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.09635066986084, "global_step": 548812, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9876987934112549, "global_step": 548813, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0607216358184814, "global_step": 548814, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.079375743865967, "global_step": 548815, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.978158712387085, "global_step": 548816, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0233211517333984, "global_step": 548817, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.072277545928955, "global_step": 548818, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9826462268829346, "global_step": 548819, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9979469776153564, "global_step": 548820, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.98154878616333, "global_step": 548821, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9415349960327148, "global_step": 548822, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0286295413970947, "global_step": 548823, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0393407344818115, "global_step": 548824, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0846614837646484, "global_step": 548825, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.053159713745117, "global_step": 548826, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0518441200256348, "global_step": 548827, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0176289081573486, "global_step": 548828, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0728795528411865, "global_step": 548829, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0125746726989746, "global_step": 548830, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0124707221984863, "global_step": 548831, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.005824327468872, "global_step": 548832, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0019092559814453, "global_step": 548833, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0268826484680176, "global_step": 548834, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.09561824798584, "global_step": 548835, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9303984642028809, "global_step": 548836, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1178858280181885, "global_step": 548837, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1336095333099365, "global_step": 548838, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.989878535270691, "global_step": 548839, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0184555053710938, "global_step": 548840, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0343918800354004, "global_step": 548841, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0319535732269287, "global_step": 548842, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0421876907348633, "global_step": 548843, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.001720666885376, "global_step": 548844, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.053645610809326, "global_step": 548845, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.042778730392456, "global_step": 548846, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0532824993133545, "global_step": 548847, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0449745655059814, "global_step": 548848, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9641425609588623, "global_step": 548849, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1284823417663574, "global_step": 548850, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9721770286560059, "global_step": 548851, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0622737407684326, "global_step": 548852, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0345942974090576, "global_step": 548853, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0136098861694336, "global_step": 548854, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9891115427017212, "global_step": 548855, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9977766275405884, "global_step": 548856, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9561481475830078, "global_step": 548857, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9706767797470093, "global_step": 548858, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9829816818237305, "global_step": 548859, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0155718326568604, "global_step": 548860, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.912095546722412, "global_step": 548861, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0737619400024414, "global_step": 548862, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9622955322265625, "global_step": 548863, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.059378147125244, "global_step": 548864, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1601784229278564, "global_step": 548865, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.019937753677368, "global_step": 548866, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.041774272918701, "global_step": 548867, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.027242422103882, "global_step": 548868, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.016383647918701, "global_step": 548869, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0487165451049805, "global_step": 548870, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.021139621734619, "global_step": 548871, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.041764497756958, "global_step": 548872, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.968071699142456, "global_step": 548873, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.047806739807129, "global_step": 548874, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0472500324249268, "global_step": 548875, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0531582832336426, "global_step": 548876, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.045973777770996, "global_step": 548877, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0058140754699707, "global_step": 548878, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.013735294342041, "global_step": 548879, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9844558238983154, "global_step": 548880, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.016695737838745, "global_step": 548881, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.053921699523926, "global_step": 548882, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.051236867904663, "global_step": 548883, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.006596326828003, "global_step": 548884, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0472371578216553, "global_step": 548885, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0096004009246826, "global_step": 548886, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9865820407867432, "global_step": 548887, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9994862079620361, "global_step": 548888, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.087912082672119, "global_step": 548889, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0072476863861084, "global_step": 548890, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0544848442077637, "global_step": 548891, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.030560255050659, "global_step": 548892, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0597736835479736, "global_step": 548893, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.978510856628418, "global_step": 548894, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.000528335571289, "global_step": 548895, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9694432020187378, "global_step": 548896, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9804505109786987, "global_step": 548897, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9983619451522827, "global_step": 548898, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.135265588760376, "global_step": 548899, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9498218297958374, "global_step": 548900, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9422892332077026, "global_step": 548901, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.067227602005005, "global_step": 548902, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0362319946289062, "global_step": 548903, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.066302537918091, "global_step": 548904, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.017143726348877, "global_step": 548905, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0958151817321777, "global_step": 548906, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.022324323654175, "global_step": 548907, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0564143657684326, "global_step": 548908, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9400676488876343, "global_step": 548909, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0508902072906494, "global_step": 548910, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0445542335510254, "global_step": 548911, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9395843744277954, "global_step": 548912, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.00594162940979, "global_step": 548913, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.011195421218872, "global_step": 548914, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0281829833984375, "global_step": 548915, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0263071060180664, "global_step": 548916, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.037834405899048, "global_step": 548917, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.032083511352539, "global_step": 548918, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1494359970092773, "global_step": 548919, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9587675333023071, "global_step": 548920, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1015520095825195, "global_step": 548921, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0133957862854004, "global_step": 548922, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9772906303405762, "global_step": 548923, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1147778034210205, "global_step": 548924, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.052690029144287, "global_step": 548925, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0053648948669434, "global_step": 548926, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9882707595825195, "global_step": 548927, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9768801927566528, "global_step": 548928, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0138494968414307, "global_step": 548929, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0304062366485596, "global_step": 548930, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.048443555831909, "global_step": 548931, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0784523487091064, "global_step": 548932, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0696189403533936, "global_step": 548933, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9667577743530273, "global_step": 548934, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0332021713256836, "global_step": 548935, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0604336261749268, "global_step": 548936, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9897661209106445, "global_step": 548937, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1100430488586426, "global_step": 548938, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0452888011932373, "global_step": 548939, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.997366189956665, "global_step": 548940, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.007889986038208, "global_step": 548941, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.056020975112915, "global_step": 548942, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0748865604400635, "global_step": 548943, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0117108821868896, "global_step": 548944, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0313048362731934, "global_step": 548945, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0038416385650635, "global_step": 548946, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0350067615509033, "global_step": 548947, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.095917224884033, "global_step": 548948, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9932059049606323, "global_step": 548949, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.109196662902832, "global_step": 548950, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9791213274002075, "global_step": 548951, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0118322372436523, "global_step": 548952, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.028078317642212, "global_step": 548953, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0585274696350098, "global_step": 548954, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0086426734924316, "global_step": 548955, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9783613681793213, "global_step": 548956, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9923806190490723, "global_step": 548957, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.036773920059204, "global_step": 548958, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9680249691009521, "global_step": 548959, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.03525710105896, "global_step": 548960, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9440885782241821, "global_step": 548961, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.051457405090332, "global_step": 548962, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0473570823669434, "global_step": 548963, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.062954902648926, "global_step": 548964, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0227925777435303, "global_step": 548965, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.069225549697876, "global_step": 548966, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.982622742652893, "global_step": 548967, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.011688232421875, "global_step": 548968, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9561163187026978, "global_step": 548969, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0240402221679688, "global_step": 548970, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0376298427581787, "global_step": 548971, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9365899562835693, "global_step": 548972, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0388143062591553, "global_step": 548973, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0144879817962646, "global_step": 548974, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0088303089141846, "global_step": 548975, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0686917304992676, "global_step": 548976, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.041168689727783, "global_step": 548977, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0054593086242676, "global_step": 548978, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.010810613632202, "global_step": 548979, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0358731746673584, "global_step": 548980, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.062863349914551, "global_step": 548981, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0966126918792725, "global_step": 548982, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0701475143432617, "global_step": 548983, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.953323245048523, "global_step": 548984, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0477352142333984, "global_step": 548985, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.975821614265442, "global_step": 548986, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0025808811187744, "global_step": 548987, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.078239917755127, "global_step": 548988, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0838375091552734, "global_step": 548989, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.027050733566284, "global_step": 548990, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0649213790893555, "global_step": 548991, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.021111011505127, "global_step": 548992, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.169616222381592, "global_step": 548993, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.968116283416748, "global_step": 548994, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.980974555015564, "global_step": 548995, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9955666065216064, "global_step": 548996, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1137237548828125, "global_step": 548997, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.142195224761963, "global_step": 548998, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9853554964065552, "global_step": 548999, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0800445079803467, "global_step": 549000, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0732321739196777, "global_step": 549001, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.966895341873169, "global_step": 549002, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9803763628005981, "global_step": 549003, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.031075954437256, "global_step": 549004, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9380674362182617, "global_step": 549005, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.986254096031189, "global_step": 549006, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0352559089660645, "global_step": 549007, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0036001205444336, "global_step": 549008, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.099749803543091, "global_step": 549009, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9676307439804077, "global_step": 549010, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0385968685150146, "global_step": 549011, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0031003952026367, "global_step": 549012, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0041675567626953, "global_step": 549013, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0929179191589355, "global_step": 549014, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.049649953842163, "global_step": 549015, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0778403282165527, "global_step": 549016, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1064767837524414, "global_step": 549017, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9874184131622314, "global_step": 549018, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0389490127563477, "global_step": 549019, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0493619441986084, "global_step": 549020, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0397770404815674, "global_step": 549021, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9724586009979248, "global_step": 549022, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9235354661941528, "global_step": 549023, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0257506370544434, "global_step": 549024, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.007732629776001, "global_step": 549025, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.041794776916504, "global_step": 549026, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.979771375656128, "global_step": 549027, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0927109718322754, "global_step": 549028, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.080437183380127, "global_step": 549029, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.089261054992676, "global_step": 549030, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.025679111480713, "global_step": 549031, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.082223892211914, "global_step": 549032, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.049729585647583, "global_step": 549033, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0366687774658203, "global_step": 549034, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.033186197280884, "global_step": 549035, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.016564130783081, "global_step": 549036, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.031808853149414, "global_step": 549037, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0591633319854736, "global_step": 549038, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0583834648132324, "global_step": 549039, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.023624897003174, "global_step": 549040, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0188546180725098, "global_step": 549041, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9750784635543823, "global_step": 549042, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.086925506591797, "global_step": 549043, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9290226697921753, "global_step": 549044, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0481033325195312, "global_step": 549045, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.039637565612793, "global_step": 549046, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0327982902526855, "global_step": 549047, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.04754376411438, "global_step": 549048, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.127429962158203, "global_step": 549049, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0665762424468994, "global_step": 549050, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.080109119415283, "global_step": 549051, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.029956340789795, "global_step": 549052, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.055907726287842, "global_step": 549053, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1396942138671875, "global_step": 549054, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0889413356781006, "global_step": 549055, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.017610788345337, "global_step": 549056, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9254047870635986, "global_step": 549057, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0566000938415527, "global_step": 549058, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0368812084198, "global_step": 549059, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9379700422286987, "global_step": 549060, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9479279518127441, "global_step": 549061, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0132594108581543, "global_step": 549062, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9763498306274414, "global_step": 549063, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0897703170776367, "global_step": 549064, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0686757564544678, "global_step": 549065, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0404417514801025, "global_step": 549066, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.017819404602051, "global_step": 549067, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1095101833343506, "global_step": 549068, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.025453805923462, "global_step": 549069, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.999618411064148, "global_step": 549070, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9132944345474243, "global_step": 549071, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0938448905944824, "global_step": 549072, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.009399890899658, "global_step": 549073, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.01151704788208, "global_step": 549074, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0322399139404297, "global_step": 549075, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.019725799560547, "global_step": 549076, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9619358777999878, "global_step": 549077, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.049248218536377, "global_step": 549078, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1061768531799316, "global_step": 549079, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0381100177764893, "global_step": 549080, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.99180269241333, "global_step": 549081, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.029247760772705, "global_step": 549082, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1431002616882324, "global_step": 549083, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9895970821380615, "global_step": 549084, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0522620677948, "global_step": 549085, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0791420936584473, "global_step": 549086, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0275497436523438, "global_step": 549087, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.067444324493408, "global_step": 549088, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0603625774383545, "global_step": 549089, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0022804737091064, "global_step": 549090, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.055915355682373, "global_step": 549091, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1329355239868164, "global_step": 549092, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.100210428237915, "global_step": 549093, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9962958097457886, "global_step": 549094, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.035637855529785, "global_step": 549095, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0128977298736572, "global_step": 549096, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.953607439994812, "global_step": 549097, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0391757488250732, "global_step": 549098, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0008537769317627, "global_step": 549099, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1434531211853027, "global_step": 549100, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0700607299804688, "global_step": 549101, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0514559745788574, "global_step": 549102, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9592516422271729, "global_step": 549103, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9758015871047974, "global_step": 549104, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.133586883544922, "global_step": 549105, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.999746322631836, "global_step": 549106, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.013345956802368, "global_step": 549107, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9997358322143555, "global_step": 549108, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9592390060424805, "global_step": 549109, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.070344924926758, "global_step": 549110, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0273544788360596, "global_step": 549111, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1054372787475586, "global_step": 549112, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.971527099609375, "global_step": 549113, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.997672200202942, "global_step": 549114, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9905869960784912, "global_step": 549115, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0191142559051514, "global_step": 549116, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0390634536743164, "global_step": 549117, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.042124032974243, "global_step": 549118, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.114595413208008, "global_step": 549119, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.092683792114258, "global_step": 549120, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9977993965148926, "global_step": 549121, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0446267127990723, "global_step": 549122, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0844318866729736, "global_step": 549123, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9869532585144043, "global_step": 549124, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.997790813446045, "global_step": 549125, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9948941469192505, "global_step": 549126, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.061917543411255, "global_step": 549127, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0865399837493896, "global_step": 549128, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0680673122406006, "global_step": 549129, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0625498294830322, "global_step": 549130, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9854927062988281, "global_step": 549131, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0472757816314697, "global_step": 549132, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.069654703140259, "global_step": 549133, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.049560785293579, "global_step": 549134, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0099689960479736, "global_step": 549135, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0737082958221436, "global_step": 549136, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.016806125640869, "global_step": 549137, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0208373069763184, "global_step": 549138, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.001462459564209, "global_step": 549139, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0451321601867676, "global_step": 549140, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.051070213317871, "global_step": 549141, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0425548553466797, "global_step": 549142, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0436480045318604, "global_step": 549143, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.047650098800659, "global_step": 549144, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.996110439300537, "global_step": 549145, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9808889627456665, "global_step": 549146, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.069876194000244, "global_step": 549147, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0065176486968994, "global_step": 549148, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0089995861053467, "global_step": 549149, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.034853935241699, "global_step": 549150, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.060930013656616, "global_step": 549151, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0132250785827637, "global_step": 549152, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9965617656707764, "global_step": 549153, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.099290370941162, "global_step": 549154, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1254074573516846, "global_step": 549155, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.056285858154297, "global_step": 549156, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.052861213684082, "global_step": 549157, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.130143642425537, "global_step": 549158, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0387449264526367, "global_step": 549159, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9481232166290283, "global_step": 549160, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.994354486465454, "global_step": 549161, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.095496416091919, "global_step": 549162, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.045994997024536, "global_step": 549163, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9858769178390503, "global_step": 549164, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.094247817993164, "global_step": 549165, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.04335355758667, "global_step": 549166, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0140364170074463, "global_step": 549167, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9679867029190063, "global_step": 549168, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0222601890563965, "global_step": 549169, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9874117374420166, "global_step": 549170, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.045559883117676, "global_step": 549171, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9762836694717407, "global_step": 549172, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0194644927978516, "global_step": 549173, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0549185276031494, "global_step": 549174, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.13594913482666, "global_step": 549175, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0562546253204346, "global_step": 549176, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9447602033615112, "global_step": 549177, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1021199226379395, "global_step": 549178, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9305270910263062, "global_step": 549179, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.037599802017212, "global_step": 549180, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0931150913238525, "global_step": 549181, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0436251163482666, "global_step": 549182, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.038341522216797, "global_step": 549183, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0329151153564453, "global_step": 549184, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9697726964950562, "global_step": 549185, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.024883508682251, "global_step": 549186, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0164687633514404, "global_step": 549187, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0062854290008545, "global_step": 549188, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0276153087615967, "global_step": 549189, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0943760871887207, "global_step": 549190, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0027198791503906, "global_step": 549191, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9498066902160645, "global_step": 549192, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0696158409118652, "global_step": 549193, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.018824815750122, "global_step": 549194, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.06203293800354, "global_step": 549195, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0618999004364014, "global_step": 549196, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9205944538116455, "global_step": 549197, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.044440269470215, "global_step": 549198, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9876604080200195, "global_step": 549199, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0331974029541016, "global_step": 549200, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0080630779266357, "global_step": 549201, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0068674087524414, "global_step": 549202, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0488083362579346, "global_step": 549203, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9834513664245605, "global_step": 549204, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.023062229156494, "global_step": 549205, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0840697288513184, "global_step": 549206, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0253498554229736, "global_step": 549207, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.981880784034729, "global_step": 549208, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.002551555633545, "global_step": 549209, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0289199352264404, "global_step": 549210, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.076977014541626, "global_step": 549211, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.956656575202942, "global_step": 549212, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0662715435028076, "global_step": 549213, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0513718128204346, "global_step": 549214, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9804404973983765, "global_step": 549215, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9958263635635376, "global_step": 549216, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.992422103881836, "global_step": 549217, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.053318738937378, "global_step": 549218, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0287067890167236, "global_step": 549219, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0532400608062744, "global_step": 549220, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.049333333969116, "global_step": 549221, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.956252932548523, "global_step": 549222, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0633962154388428, "global_step": 549223, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0309219360351562, "global_step": 549224, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.975785493850708, "global_step": 549225, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.107264518737793, "global_step": 549226, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0857949256896973, "global_step": 549227, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1221866607666016, "global_step": 549228, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9772851467132568, "global_step": 549229, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0965652465820312, "global_step": 549230, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.116621494293213, "global_step": 549231, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.069169521331787, "global_step": 549232, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9580134153366089, "global_step": 549233, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0457212924957275, "global_step": 549234, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.08695387840271, "global_step": 549235, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.008192777633667, "global_step": 549236, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0130555629730225, "global_step": 549237, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9894078969955444, "global_step": 549238, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.000999689102173, "global_step": 549239, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.085118532180786, "global_step": 549240, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.027144432067871, "global_step": 549241, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.028528928756714, "global_step": 549242, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9592984914779663, "global_step": 549243, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0093438625335693, "global_step": 549244, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0551671981811523, "global_step": 549245, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0718863010406494, "global_step": 549246, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9399791955947876, "global_step": 549247, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0049970149993896, "global_step": 549248, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0276525020599365, "global_step": 549249, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0737502574920654, "global_step": 549250, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9937646389007568, "global_step": 549251, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9972106218338013, "global_step": 549252, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0849506855010986, "global_step": 549253, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.005549669265747, "global_step": 549254, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0542962551116943, "global_step": 549255, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.043811798095703, "global_step": 549256, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9810056686401367, "global_step": 549257, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.05238676071167, "global_step": 549258, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9813613891601562, "global_step": 549259, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.086688756942749, "global_step": 549260, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0521366596221924, "global_step": 549261, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0279693603515625, "global_step": 549262, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9772535562515259, "global_step": 549263, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0493454933166504, "global_step": 549264, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.038508892059326, "global_step": 549265, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.090691566467285, "global_step": 549266, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.062304973602295, "global_step": 549267, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0829055309295654, "global_step": 549268, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0267791748046875, "global_step": 549269, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0689332485198975, "global_step": 549270, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0310630798339844, "global_step": 549271, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9435386657714844, "global_step": 549272, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1025805473327637, "global_step": 549273, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0916943550109863, "global_step": 549274, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.080583333969116, "global_step": 549275, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9995970726013184, "global_step": 549276, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.036872386932373, "global_step": 549277, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0490262508392334, "global_step": 549278, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0118157863616943, "global_step": 549279, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0319035053253174, "global_step": 549280, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0488452911376953, "global_step": 549281, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0428740978240967, "global_step": 549282, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9609347581863403, "global_step": 549283, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.053889751434326, "global_step": 549284, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0121333599090576, "global_step": 549285, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9801379442214966, "global_step": 549286, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9038128852844238, "global_step": 549287, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9941892623901367, "global_step": 549288, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0512499809265137, "global_step": 549289, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0511510372161865, "global_step": 549290, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1100940704345703, "global_step": 549291, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9737645387649536, "global_step": 549292, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9544920921325684, "global_step": 549293, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.018779993057251, "global_step": 549294, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0483992099761963, "global_step": 549295, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.022709608078003, "global_step": 549296, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.066591501235962, "global_step": 549297, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0183372497558594, "global_step": 549298, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.051649332046509, "global_step": 549299, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0544345378875732, "global_step": 549300, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.979017734527588, "global_step": 549301, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9872318506240845, "global_step": 549302, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.007615089416504, "global_step": 549303, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0290093421936035, "global_step": 549304, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.018599510192871, "global_step": 549305, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.022188663482666, "global_step": 549306, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.08085036277771, "global_step": 549307, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0979325771331787, "global_step": 549308, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1020472049713135, "global_step": 549309, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.103464126586914, "global_step": 549310, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9860790967941284, "global_step": 549311, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0639729499816895, "global_step": 549312, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0470383167266846, "global_step": 549313, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9723069667816162, "global_step": 549314, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9570709466934204, "global_step": 549315, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0033416748046875, "global_step": 549316, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0744705200195312, "global_step": 549317, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.077418088912964, "global_step": 549318, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0724055767059326, "global_step": 549319, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.031752586364746, "global_step": 549320, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.039569854736328, "global_step": 549321, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0418498516082764, "global_step": 549322, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.987911343574524, "global_step": 549323, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.021784782409668, "global_step": 549324, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9882175922393799, "global_step": 549325, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0446584224700928, "global_step": 549326, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.058811664581299, "global_step": 549327, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.999982476234436, "global_step": 549328, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.096534252166748, "global_step": 549329, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.098583698272705, "global_step": 549330, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9836397171020508, "global_step": 549331, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.980099081993103, "global_step": 549332, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9856351613998413, "global_step": 549333, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.998563528060913, "global_step": 549334, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.057781457901001, "global_step": 549335, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.999188780784607, "global_step": 549336, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.005572557449341, "global_step": 549337, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9883720874786377, "global_step": 549338, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0538365840911865, "global_step": 549339, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0076332092285156, "global_step": 549340, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.019994020462036, "global_step": 549341, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9152240753173828, "global_step": 549342, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9346470832824707, "global_step": 549343, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.122048854827881, "global_step": 549344, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1400339603424072, "global_step": 549345, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.041166067123413, "global_step": 549346, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9997202157974243, "global_step": 549347, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0439209938049316, "global_step": 549348, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.050654411315918, "global_step": 549349, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.067061424255371, "global_step": 549350, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.034722089767456, "global_step": 549351, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0473833084106445, "global_step": 549352, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.004690408706665, "global_step": 549353, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.075570583343506, "global_step": 549354, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.996870756149292, "global_step": 549355, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.025397539138794, "global_step": 549356, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.067784547805786, "global_step": 549357, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0073885917663574, "global_step": 549358, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0802552700042725, "global_step": 549359, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0787458419799805, "global_step": 549360, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1119933128356934, "global_step": 549361, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.114957332611084, "global_step": 549362, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9760637283325195, "global_step": 549363, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9946527481079102, "global_step": 549364, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0222878456115723, "global_step": 549365, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.089243173599243, "global_step": 549366, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.032355308532715, "global_step": 549367, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.2003493309020996, "global_step": 549368, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.015467643737793, "global_step": 549369, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.03131365776062, "global_step": 549370, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0362050533294678, "global_step": 549371, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0841410160064697, "global_step": 549372, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.045799493789673, "global_step": 549373, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9614906311035156, "global_step": 549374, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.043816566467285, "global_step": 549375, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.142822742462158, "global_step": 549376, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.064011335372925, "global_step": 549377, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.09328556060791, "global_step": 549378, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9497429132461548, "global_step": 549379, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0474324226379395, "global_step": 549380, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0598177909851074, "global_step": 549381, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.981343150138855, "global_step": 549382, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.061836004257202, "global_step": 549383, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0430965423583984, "global_step": 549384, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9989891052246094, "global_step": 549385, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0055437088012695, "global_step": 549386, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.986524224281311, "global_step": 549387, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1177077293395996, "global_step": 549388, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.054608106613159, "global_step": 549389, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.104665517807007, "global_step": 549390, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.995141625404358, "global_step": 549391, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0760014057159424, "global_step": 549392, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.112502098083496, "global_step": 549393, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0495526790618896, "global_step": 549394, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.00787353515625, "global_step": 549395, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0324833393096924, "global_step": 549396, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.063561201095581, "global_step": 549397, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.088970184326172, "global_step": 549398, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0694005489349365, "global_step": 549399, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0648374557495117, "global_step": 549400, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9762053489685059, "global_step": 549401, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0449185371398926, "global_step": 549402, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0825858116149902, "global_step": 549403, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.09334397315979, "global_step": 549404, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.150226354598999, "global_step": 549405, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0256083011627197, "global_step": 549406, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9813016653060913, "global_step": 549407, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0740466117858887, "global_step": 549408, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1299729347229004, "global_step": 549409, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.019942045211792, "global_step": 549410, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.094151020050049, "global_step": 549411, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0358314514160156, "global_step": 549412, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.029873847961426, "global_step": 549413, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0818419456481934, "global_step": 549414, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.047945499420166, "global_step": 549415, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.062593698501587, "global_step": 549416, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0012974739074707, "global_step": 549417, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0897858142852783, "global_step": 549418, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.149660587310791, "global_step": 549419, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.098468542098999, "global_step": 549420, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9441533088684082, "global_step": 549421, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1054258346557617, "global_step": 549422, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.000786066055298, "global_step": 549423, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.032451868057251, "global_step": 549424, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.977698564529419, "global_step": 549425, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.091142177581787, "global_step": 549426, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1152071952819824, "global_step": 549427, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0435237884521484, "global_step": 549428, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9450817108154297, "global_step": 549429, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.034334659576416, "global_step": 549430, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0119075775146484, "global_step": 549431, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.024872064590454, "global_step": 549432, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9927691221237183, "global_step": 549433, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0270586013793945, "global_step": 549434, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.978337287902832, "global_step": 549435, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9854745864868164, "global_step": 549436, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.067664384841919, "global_step": 549437, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0037713050842285, "global_step": 549438, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.044055223464966, "global_step": 549439, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.033154010772705, "global_step": 549440, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0412757396698, "global_step": 549441, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.08109712600708, "global_step": 549442, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.082571268081665, "global_step": 549443, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.113046646118164, "global_step": 549444, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0438849925994873, "global_step": 549445, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.064770460128784, "global_step": 549446, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.022724151611328, "global_step": 549447, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.137586832046509, "global_step": 549448, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.045772075653076, "global_step": 549449, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.007446765899658, "global_step": 549450, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9904708862304688, "global_step": 549451, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.085442304611206, "global_step": 549452, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0608255863189697, "global_step": 549453, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9384548664093018, "global_step": 549454, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.059298038482666, "global_step": 549455, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0588490962982178, "global_step": 549456, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0677003860473633, "global_step": 549457, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.11929988861084, "global_step": 549458, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0777194499969482, "global_step": 549459, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.113459587097168, "global_step": 549460, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0229005813598633, "global_step": 549461, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.022139549255371, "global_step": 549462, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0880565643310547, "global_step": 549463, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.032921552658081, "global_step": 549464, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.042797088623047, "global_step": 549465, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.948507308959961, "global_step": 549466, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9750598669052124, "global_step": 549467, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0205609798431396, "global_step": 549468, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.019998550415039, "global_step": 549469, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0772078037261963, "global_step": 549470, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.07279372215271, "global_step": 549471, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.960646629333496, "global_step": 549472, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9960851669311523, "global_step": 549473, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.030125141143799, "global_step": 549474, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9888087511062622, "global_step": 549475, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0564324855804443, "global_step": 549476, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1047112941741943, "global_step": 549477, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0240273475646973, "global_step": 549478, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9985557794570923, "global_step": 549479, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0576162338256836, "global_step": 549480, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1098296642303467, "global_step": 549481, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9686708450317383, "global_step": 549482, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0200743675231934, "global_step": 549483, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9876185655593872, "global_step": 549484, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1098411083221436, "global_step": 549485, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0199191570281982, "global_step": 549486, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0200552940368652, "global_step": 549487, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9799443483352661, "global_step": 549488, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.006610870361328, "global_step": 549489, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.977492094039917, "global_step": 549490, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0228424072265625, "global_step": 549491, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.166182518005371, "global_step": 549492, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.085686206817627, "global_step": 549493, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0431089401245117, "global_step": 549494, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0809054374694824, "global_step": 549495, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1240451335906982, "global_step": 549496, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9919124841690063, "global_step": 549497, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.088130474090576, "global_step": 549498, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0365028381347656, "global_step": 549499, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0071566104888916, "global_step": 549500, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0756616592407227, "global_step": 549501, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.079943895339966, "global_step": 549502, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0804648399353027, "global_step": 549503, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.10317063331604, "global_step": 549504, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9452342987060547, "global_step": 549505, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9775280952453613, "global_step": 549506, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0025994777679443, "global_step": 549507, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.117166519165039, "global_step": 549508, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.048232316970825, "global_step": 549509, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0800633430480957, "global_step": 549510, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.990393877029419, "global_step": 549511, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9999490976333618, "global_step": 549512, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.044296979904175, "global_step": 549513, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.032522201538086, "global_step": 549514, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.059593439102173, "global_step": 549515, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.078460931777954, "global_step": 549516, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.032029151916504, "global_step": 549517, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.106168270111084, "global_step": 549518, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.086998224258423, "global_step": 549519, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.050565242767334, "global_step": 549520, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0543432235717773, "global_step": 549521, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9497169256210327, "global_step": 549522, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.016711711883545, "global_step": 549523, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0237905979156494, "global_step": 549524, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.034944534301758, "global_step": 549525, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0127601623535156, "global_step": 549526, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0564284324645996, "global_step": 549527, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0953774452209473, "global_step": 549528, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.102921485900879, "global_step": 549529, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.105102300643921, "global_step": 549530, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.051072120666504, "global_step": 549531, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9970271587371826, "global_step": 549532, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.054985761642456, "global_step": 549533, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1010987758636475, "global_step": 549534, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.06130313873291, "global_step": 549535, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0883662700653076, "global_step": 549536, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.931266188621521, "global_step": 549537, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.040736198425293, "global_step": 549538, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0766077041625977, "global_step": 549539, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.009218692779541, "global_step": 549540, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0660817623138428, "global_step": 549541, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0562148094177246, "global_step": 549542, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.05495023727417, "global_step": 549543, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1069657802581787, "global_step": 549544, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.042555570602417, "global_step": 549545, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.038184881210327, "global_step": 549546, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.1205735206604004, "global_step": 549547, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.051347494125366, "global_step": 549548, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0406649112701416, "global_step": 549549, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0118730068206787, "global_step": 549550, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0655527114868164, "global_step": 549551, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.028334379196167, "global_step": 549552, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9874829053878784, "global_step": 549553, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.0606069564819336, "global_step": 549554, "epoch": 916, "lr": 5e-05}
{"train_loss": 2.031426191329956, "global_step": 549555, "epoch": 916, "lr": 5e-05}
{"train_loss": 1.9336040019989014, "global_step": 549556, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0359323024749756, "global_step": 549557, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0018274784088135, "global_step": 549558, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.10333251953125, "global_step": 549559, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.018167018890381, "global_step": 549560, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9483119249343872, "global_step": 549561, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.012036085128784, "global_step": 549562, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.004429340362549, "global_step": 549563, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.949489712715149, "global_step": 549564, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0110089778900146, "global_step": 549565, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.035860776901245, "global_step": 549566, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0142226219177246, "global_step": 549567, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0035006999969482, "global_step": 549568, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9578410387039185, "global_step": 549569, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9983253479003906, "global_step": 549570, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.067884922027588, "global_step": 549571, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.076162815093994, "global_step": 549572, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.040200710296631, "global_step": 549573, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0060298442840576, "global_step": 549574, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9834673404693604, "global_step": 549575, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.001328229904175, "global_step": 549576, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.053398847579956, "global_step": 549577, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9779845476150513, "global_step": 549578, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9929766654968262, "global_step": 549579, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9554083347320557, "global_step": 549580, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.8566865921020508, "global_step": 549581, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.101560354232788, "global_step": 549582, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0256123542785645, "global_step": 549583, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.009852409362793, "global_step": 549584, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.019404888153076, "global_step": 549585, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.021897554397583, "global_step": 549586, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.083461046218872, "global_step": 549587, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.027729034423828, "global_step": 549588, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1028802394866943, "global_step": 549589, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9719277620315552, "global_step": 549590, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0062530040740967, "global_step": 549591, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9861202239990234, "global_step": 549592, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1162235736846924, "global_step": 549593, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0828464031219482, "global_step": 549594, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0235259532928467, "global_step": 549595, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0226426124572754, "global_step": 549596, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.002150774002075, "global_step": 549597, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9809695482254028, "global_step": 549598, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.024852991104126, "global_step": 549599, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0187320709228516, "global_step": 549600, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0043017864227295, "global_step": 549601, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0007433891296387, "global_step": 549602, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0219521522521973, "global_step": 549603, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0839626789093018, "global_step": 549604, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.10396409034729, "global_step": 549605, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9911688566207886, "global_step": 549606, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0173370838165283, "global_step": 549607, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0637192726135254, "global_step": 549608, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9912919998168945, "global_step": 549609, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0088584423065186, "global_step": 549610, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1147947311401367, "global_step": 549611, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9814331531524658, "global_step": 549612, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9573594331741333, "global_step": 549613, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9879398345947266, "global_step": 549614, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0497405529022217, "global_step": 549615, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9693093299865723, "global_step": 549616, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.001220226287842, "global_step": 549617, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0293097496032715, "global_step": 549618, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9912368059158325, "global_step": 549619, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0768141746520996, "global_step": 549620, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.071683645248413, "global_step": 549621, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0286552906036377, "global_step": 549622, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9800145626068115, "global_step": 549623, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0350120067596436, "global_step": 549624, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.045477867126465, "global_step": 549625, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.01016902923584, "global_step": 549626, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.045135021209717, "global_step": 549627, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0367591381073, "global_step": 549628, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0299746990203857, "global_step": 549629, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.09015154838562, "global_step": 549630, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0240843296051025, "global_step": 549631, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.023472547531128, "global_step": 549632, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0106403827667236, "global_step": 549633, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0202558040618896, "global_step": 549634, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0445098876953125, "global_step": 549635, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0425941944122314, "global_step": 549636, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.002793073654175, "global_step": 549637, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9926090240478516, "global_step": 549638, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0894808769226074, "global_step": 549639, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9416282176971436, "global_step": 549640, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0475614070892334, "global_step": 549641, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0125677585601807, "global_step": 549642, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0656468868255615, "global_step": 549643, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.987231731414795, "global_step": 549644, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.981062889099121, "global_step": 549645, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.069897413253784, "global_step": 549646, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.992318868637085, "global_step": 549647, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0070369243621826, "global_step": 549648, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.999571681022644, "global_step": 549649, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0457324981689453, "global_step": 549650, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.015714645385742, "global_step": 549651, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0505661964416504, "global_step": 549652, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.092373847961426, "global_step": 549653, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0398459434509277, "global_step": 549654, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0424177646636963, "global_step": 549655, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0418784618377686, "global_step": 549656, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0055041313171387, "global_step": 549657, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9742828607559204, "global_step": 549658, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.016016960144043, "global_step": 549659, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0321714878082275, "global_step": 549660, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0448975563049316, "global_step": 549661, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0446088314056396, "global_step": 549662, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9868829250335693, "global_step": 549663, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.139702558517456, "global_step": 549664, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0001018047332764, "global_step": 549665, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0599589347839355, "global_step": 549666, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.031114101409912, "global_step": 549667, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9989038705825806, "global_step": 549668, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0529255867004395, "global_step": 549669, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9790716171264648, "global_step": 549670, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.015504837036133, "global_step": 549671, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0176658630371094, "global_step": 549672, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.999307632446289, "global_step": 549673, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9686824083328247, "global_step": 549674, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.013200521469116, "global_step": 549675, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9711337089538574, "global_step": 549676, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.913345217704773, "global_step": 549677, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9886937141418457, "global_step": 549678, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.017638921737671, "global_step": 549679, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.990275263786316, "global_step": 549680, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9733197689056396, "global_step": 549681, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0143227577209473, "global_step": 549682, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.078558921813965, "global_step": 549683, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9999202489852905, "global_step": 549684, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.099867820739746, "global_step": 549685, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9743852615356445, "global_step": 549686, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.916640043258667, "global_step": 549687, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.076411008834839, "global_step": 549688, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0297441482543945, "global_step": 549689, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9667859077453613, "global_step": 549690, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9629313945770264, "global_step": 549691, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1424686908721924, "global_step": 549692, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0058417320251465, "global_step": 549693, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9652334451675415, "global_step": 549694, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9525699615478516, "global_step": 549695, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0275676250457764, "global_step": 549696, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.031838893890381, "global_step": 549697, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0330724716186523, "global_step": 549698, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.015305519104004, "global_step": 549699, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.95866858959198, "global_step": 549700, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9860267639160156, "global_step": 549701, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.122788190841675, "global_step": 549702, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0191755294799805, "global_step": 549703, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9887257814407349, "global_step": 549704, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0039258003234863, "global_step": 549705, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0933775901794434, "global_step": 549706, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0755631923675537, "global_step": 549707, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9505434036254883, "global_step": 549708, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.081810474395752, "global_step": 549709, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0698461532592773, "global_step": 549710, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0479001998901367, "global_step": 549711, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.115121603012085, "global_step": 549712, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9539388418197632, "global_step": 549713, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0315091609954834, "global_step": 549714, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.059668779373169, "global_step": 549715, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0165657997131348, "global_step": 549716, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0275399684906006, "global_step": 549717, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0041565895080566, "global_step": 549718, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1132776737213135, "global_step": 549719, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.943374752998352, "global_step": 549720, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0202558040618896, "global_step": 549721, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0989773273468018, "global_step": 549722, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.022120237350464, "global_step": 549723, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0355663299560547, "global_step": 549724, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0836758613586426, "global_step": 549725, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0715746879577637, "global_step": 549726, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9906997680664062, "global_step": 549727, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9362623691558838, "global_step": 549728, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0510435104370117, "global_step": 549729, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9541513919830322, "global_step": 549730, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0688858032226562, "global_step": 549731, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0655081272125244, "global_step": 549732, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0346295833587646, "global_step": 549733, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.977564811706543, "global_step": 549734, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9918396472930908, "global_step": 549735, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.084239959716797, "global_step": 549736, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0410237312316895, "global_step": 549737, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9972336292266846, "global_step": 549738, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0426177978515625, "global_step": 549739, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9869228601455688, "global_step": 549740, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0150718688964844, "global_step": 549741, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.023993730545044, "global_step": 549742, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.109668016433716, "global_step": 549743, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9460405111312866, "global_step": 549744, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9626518487930298, "global_step": 549745, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.940570592880249, "global_step": 549746, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.101308584213257, "global_step": 549747, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.934510350227356, "global_step": 549748, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.018385410308838, "global_step": 549749, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.079076051712036, "global_step": 549750, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9951170682907104, "global_step": 549751, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.104205846786499, "global_step": 549752, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.031954526901245, "global_step": 549753, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9640940427780151, "global_step": 549754, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0340323448181152, "global_step": 549755, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9273180961608887, "global_step": 549756, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1438002586364746, "global_step": 549757, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.075640916824341, "global_step": 549758, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0349204540252686, "global_step": 549759, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0888071060180664, "global_step": 549760, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.006868600845337, "global_step": 549761, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9618779420852661, "global_step": 549762, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.041024684906006, "global_step": 549763, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9675787687301636, "global_step": 549764, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0069949626922607, "global_step": 549765, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0477194786071777, "global_step": 549766, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0353808403015137, "global_step": 549767, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.049078941345215, "global_step": 549768, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9715248346328735, "global_step": 549769, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0286900997161865, "global_step": 549770, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9735342264175415, "global_step": 549771, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0538032054901123, "global_step": 549772, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.022221565246582, "global_step": 549773, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9974441528320312, "global_step": 549774, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0757393836975098, "global_step": 549775, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.958586573600769, "global_step": 549776, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.031599998474121, "global_step": 549777, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0534682273864746, "global_step": 549778, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0127289295196533, "global_step": 549779, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.958371639251709, "global_step": 549780, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.984390377998352, "global_step": 549781, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.022935152053833, "global_step": 549782, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0799858570098877, "global_step": 549783, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0001394748687744, "global_step": 549784, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.045703172683716, "global_step": 549785, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9837298393249512, "global_step": 549786, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.14703631401062, "global_step": 549787, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9900665283203125, "global_step": 549788, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9451031684875488, "global_step": 549789, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.018465280532837, "global_step": 549790, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0380938053131104, "global_step": 549791, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9361615180969238, "global_step": 549792, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0260438919067383, "global_step": 549793, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.052694082260132, "global_step": 549794, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.038133144378662, "global_step": 549795, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9755172729492188, "global_step": 549796, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9529212713241577, "global_step": 549797, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0170371532440186, "global_step": 549798, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0194637775421143, "global_step": 549799, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9899559020996094, "global_step": 549800, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0077102184295654, "global_step": 549801, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9766958951950073, "global_step": 549802, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1200907230377197, "global_step": 549803, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.068000078201294, "global_step": 549804, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0601930618286133, "global_step": 549805, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0213258266448975, "global_step": 549806, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.112334966659546, "global_step": 549807, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0606253147125244, "global_step": 549808, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9958715438842773, "global_step": 549809, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9670742750167847, "global_step": 549810, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.053149938583374, "global_step": 549811, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9865524768829346, "global_step": 549812, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0797739028930664, "global_step": 549813, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0189225673675537, "global_step": 549814, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0835604667663574, "global_step": 549815, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9211187362670898, "global_step": 549816, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0479745864868164, "global_step": 549817, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9825719594955444, "global_step": 549818, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9690423011779785, "global_step": 549819, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0964391231536865, "global_step": 549820, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.021249771118164, "global_step": 549821, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0578269958496094, "global_step": 549822, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9918419122695923, "global_step": 549823, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0086894035339355, "global_step": 549824, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.054723024368286, "global_step": 549825, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.033909797668457, "global_step": 549826, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0315659046173096, "global_step": 549827, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0887527465820312, "global_step": 549828, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.058156728744507, "global_step": 549829, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.104464292526245, "global_step": 549830, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9725720882415771, "global_step": 549831, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.064908504486084, "global_step": 549832, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9903552532196045, "global_step": 549833, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.05863881111145, "global_step": 549834, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.004075527191162, "global_step": 549835, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9852498769760132, "global_step": 549836, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.947037696838379, "global_step": 549837, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9715873003005981, "global_step": 549838, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0865392684936523, "global_step": 549839, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9404869079589844, "global_step": 549840, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9763617515563965, "global_step": 549841, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9587767124176025, "global_step": 549842, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.009660482406616, "global_step": 549843, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0100982189178467, "global_step": 549844, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9897059202194214, "global_step": 549845, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.02205228805542, "global_step": 549846, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9766453504562378, "global_step": 549847, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.043715238571167, "global_step": 549848, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9996989965438843, "global_step": 549849, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9792741537094116, "global_step": 549850, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0209381580352783, "global_step": 549851, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9604580402374268, "global_step": 549852, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.044995069503784, "global_step": 549853, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0291240215301514, "global_step": 549854, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.976062536239624, "global_step": 549855, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9681901931762695, "global_step": 549856, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0138769149780273, "global_step": 549857, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0094189643859863, "global_step": 549858, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0153210163116455, "global_step": 549859, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0885143280029297, "global_step": 549860, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.076112747192383, "global_step": 549861, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.033815622329712, "global_step": 549862, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.030336380004883, "global_step": 549863, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9681200981140137, "global_step": 549864, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9899101257324219, "global_step": 549865, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.025747776031494, "global_step": 549866, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0652077198028564, "global_step": 549867, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.058335542678833, "global_step": 549868, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9741740226745605, "global_step": 549869, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.096182346343994, "global_step": 549870, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9897655248641968, "global_step": 549871, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9692423343658447, "global_step": 549872, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0078563690185547, "global_step": 549873, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9396172761917114, "global_step": 549874, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0605835914611816, "global_step": 549875, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.107130765914917, "global_step": 549876, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0937111377716064, "global_step": 549877, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9904417991638184, "global_step": 549878, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.025056838989258, "global_step": 549879, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0176079273223877, "global_step": 549880, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9750094413757324, "global_step": 549881, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.091238260269165, "global_step": 549882, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0420517921447754, "global_step": 549883, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0290606021881104, "global_step": 549884, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0380911827087402, "global_step": 549885, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.132862091064453, "global_step": 549886, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0233371257781982, "global_step": 549887, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9880212545394897, "global_step": 549888, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.141641139984131, "global_step": 549889, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0195136070251465, "global_step": 549890, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9241093397140503, "global_step": 549891, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1439099311828613, "global_step": 549892, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1533024311065674, "global_step": 549893, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9432936906814575, "global_step": 549894, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0145137310028076, "global_step": 549895, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0001556873321533, "global_step": 549896, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0715808868408203, "global_step": 549897, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0640876293182373, "global_step": 549898, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0014681816101074, "global_step": 549899, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.034341335296631, "global_step": 549900, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.014752149581909, "global_step": 549901, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0343384742736816, "global_step": 549902, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.018972635269165, "global_step": 549903, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.072026014328003, "global_step": 549904, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0393519401550293, "global_step": 549905, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0539984703063965, "global_step": 549906, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0393714904785156, "global_step": 549907, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.992082118988037, "global_step": 549908, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.988599181175232, "global_step": 549909, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.024223566055298, "global_step": 549910, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0102264881134033, "global_step": 549911, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0731258392333984, "global_step": 549912, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.021322011947632, "global_step": 549913, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.083462953567505, "global_step": 549914, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9777007102966309, "global_step": 549915, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9754167795181274, "global_step": 549916, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.039952516555786, "global_step": 549917, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0155906677246094, "global_step": 549918, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.940488338470459, "global_step": 549919, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.055572986602783, "global_step": 549920, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0934038162231445, "global_step": 549921, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0515637397766113, "global_step": 549922, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9424201250076294, "global_step": 549923, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.038795232772827, "global_step": 549924, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0838563442230225, "global_step": 549925, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9960728883743286, "global_step": 549926, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.071894884109497, "global_step": 549927, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9772552251815796, "global_step": 549928, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9907422065734863, "global_step": 549929, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0243332386016846, "global_step": 549930, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1148805618286133, "global_step": 549931, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1052799224853516, "global_step": 549932, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0431015491485596, "global_step": 549933, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.036332607269287, "global_step": 549934, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1303374767303467, "global_step": 549935, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9772506952285767, "global_step": 549936, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1180365085601807, "global_step": 549937, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.006960868835449, "global_step": 549938, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.950311541557312, "global_step": 549939, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.036698341369629, "global_step": 549940, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0378246307373047, "global_step": 549941, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.042440414428711, "global_step": 549942, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.052743434906006, "global_step": 549943, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0247888565063477, "global_step": 549944, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.051896333694458, "global_step": 549945, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9039440155029297, "global_step": 549946, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9530283212661743, "global_step": 549947, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9624125957489014, "global_step": 549948, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1078317165374756, "global_step": 549949, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0188186168670654, "global_step": 549950, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9821813106536865, "global_step": 549951, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9755969047546387, "global_step": 549952, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.009026050567627, "global_step": 549953, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0117976665496826, "global_step": 549954, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.065187454223633, "global_step": 549955, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.037968397140503, "global_step": 549956, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.056326150894165, "global_step": 549957, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.020845890045166, "global_step": 549958, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9640798568725586, "global_step": 549959, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.087378740310669, "global_step": 549960, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0379478931427, "global_step": 549961, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.038583993911743, "global_step": 549962, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0591652393341064, "global_step": 549963, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9272056818008423, "global_step": 549964, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.020111560821533, "global_step": 549965, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9737671613693237, "global_step": 549966, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.131354808807373, "global_step": 549967, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9972453117370605, "global_step": 549968, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0883724689483643, "global_step": 549969, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.127542018890381, "global_step": 549970, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0299036502838135, "global_step": 549971, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0354297161102295, "global_step": 549972, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1967639923095703, "global_step": 549973, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.083862543106079, "global_step": 549974, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9640305042266846, "global_step": 549975, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0310425758361816, "global_step": 549976, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.035832166671753, "global_step": 549977, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1014835834503174, "global_step": 549978, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.036985397338867, "global_step": 549979, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9905006885528564, "global_step": 549980, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.060328960418701, "global_step": 549981, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.022500991821289, "global_step": 549982, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.061014175415039, "global_step": 549983, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9581836462020874, "global_step": 549984, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.062898874282837, "global_step": 549985, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.079990863800049, "global_step": 549986, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9722647666931152, "global_step": 549987, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.06656551361084, "global_step": 549988, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0593419075012207, "global_step": 549989, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.071092128753662, "global_step": 549990, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.100306272506714, "global_step": 549991, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0476479530334473, "global_step": 549992, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0047523975372314, "global_step": 549993, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.984320044517517, "global_step": 549994, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.039888858795166, "global_step": 549995, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.028745174407959, "global_step": 549996, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0073630809783936, "global_step": 549997, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0308334827423096, "global_step": 549998, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0262622833251953, "global_step": 549999, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.052863359451294, "global_step": 550000, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.060006618499756, "global_step": 550001, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9692761898040771, "global_step": 550002, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9742475748062134, "global_step": 550003, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9802647829055786, "global_step": 550004, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.007674217224121, "global_step": 550005, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.069084644317627, "global_step": 550006, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.084604263305664, "global_step": 550007, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9840540885925293, "global_step": 550008, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0271003246307373, "global_step": 550009, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.002167224884033, "global_step": 550010, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1009836196899414, "global_step": 550011, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0343122482299805, "global_step": 550012, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.900580883026123, "global_step": 550013, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9915564060211182, "global_step": 550014, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0783839225769043, "global_step": 550015, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0423965454101562, "global_step": 550016, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1029627323150635, "global_step": 550017, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0937387943267822, "global_step": 550018, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0422255992889404, "global_step": 550019, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.013636589050293, "global_step": 550020, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.054598331451416, "global_step": 550021, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1119532585144043, "global_step": 550022, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9773962497711182, "global_step": 550023, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9947702884674072, "global_step": 550024, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0370211601257324, "global_step": 550025, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.061110496520996, "global_step": 550026, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.022451400756836, "global_step": 550027, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0063915252685547, "global_step": 550028, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.028864622116089, "global_step": 550029, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9635381698608398, "global_step": 550030, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0570831298828125, "global_step": 550031, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.001526355743408, "global_step": 550032, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0586118698120117, "global_step": 550033, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0477535724639893, "global_step": 550034, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9905105829238892, "global_step": 550035, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0443813800811768, "global_step": 550036, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0355520248413086, "global_step": 550037, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.091310977935791, "global_step": 550038, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.020589828491211, "global_step": 550039, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0271191596984863, "global_step": 550040, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0532641410827637, "global_step": 550041, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.978472352027893, "global_step": 550042, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0685367584228516, "global_step": 550043, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.964951992034912, "global_step": 550044, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0025579929351807, "global_step": 550045, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0842652320861816, "global_step": 550046, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0226833820343018, "global_step": 550047, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0162360668182373, "global_step": 550048, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.002957582473755, "global_step": 550049, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9986472129821777, "global_step": 550050, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0892162322998047, "global_step": 550051, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.05879282951355, "global_step": 550052, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.122612953186035, "global_step": 550053, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0779738426208496, "global_step": 550054, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0826077461242676, "global_step": 550055, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9120924472808838, "global_step": 550056, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0812721252441406, "global_step": 550057, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0848548412323, "global_step": 550058, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.03279447555542, "global_step": 550059, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0246846675872803, "global_step": 550060, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.041208267211914, "global_step": 550061, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0100066661834717, "global_step": 550062, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.051684617996216, "global_step": 550063, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0051262378692627, "global_step": 550064, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0921826362609863, "global_step": 550065, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0367202758789062, "global_step": 550066, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0023348331451416, "global_step": 550067, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9949767589569092, "global_step": 550068, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.028463840484619, "global_step": 550069, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.019636869430542, "global_step": 550070, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0347328186035156, "global_step": 550071, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9887666702270508, "global_step": 550072, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9565426111221313, "global_step": 550073, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.040957450866699, "global_step": 550074, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0553531646728516, "global_step": 550075, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.002483606338501, "global_step": 550076, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9551042318344116, "global_step": 550077, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0204524993896484, "global_step": 550078, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0727522373199463, "global_step": 550079, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9946262836456299, "global_step": 550080, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0502500534057617, "global_step": 550081, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.952080488204956, "global_step": 550082, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0528564453125, "global_step": 550083, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.162672758102417, "global_step": 550084, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9812380075454712, "global_step": 550085, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9754154682159424, "global_step": 550086, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.118206739425659, "global_step": 550087, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1145365238189697, "global_step": 550088, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0060932636260986, "global_step": 550089, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0872626304626465, "global_step": 550090, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9888033866882324, "global_step": 550091, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.031177520751953, "global_step": 550092, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.989126205444336, "global_step": 550093, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9331380128860474, "global_step": 550094, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.029414653778076, "global_step": 550095, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9617847204208374, "global_step": 550096, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9568583965301514, "global_step": 550097, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0648293495178223, "global_step": 550098, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.018502950668335, "global_step": 550099, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.06241512298584, "global_step": 550100, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.020068407058716, "global_step": 550101, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.008678436279297, "global_step": 550102, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1080057621002197, "global_step": 550103, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9764589071273804, "global_step": 550104, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0737826824188232, "global_step": 550105, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0661041736602783, "global_step": 550106, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.97348952293396, "global_step": 550107, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.002890110015869, "global_step": 550108, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9960110187530518, "global_step": 550109, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.032855749130249, "global_step": 550110, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.100003480911255, "global_step": 550111, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.095885753631592, "global_step": 550112, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.168994188308716, "global_step": 550113, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.061141014099121, "global_step": 550114, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0554440021514893, "global_step": 550115, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0813426971435547, "global_step": 550116, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9836910963058472, "global_step": 550117, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0116569995880127, "global_step": 550118, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9204106330871582, "global_step": 550119, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0307912826538086, "global_step": 550120, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.00785756111145, "global_step": 550121, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9736377000808716, "global_step": 550122, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9906350374221802, "global_step": 550123, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0477681159973145, "global_step": 550124, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0331077575683594, "global_step": 550125, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0261456966400146, "global_step": 550126, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.06636905670166, "global_step": 550127, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.027175188064575, "global_step": 550128, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9796767234802246, "global_step": 550129, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.999215006828308, "global_step": 550130, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0657315254211426, "global_step": 550131, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0449788570404053, "global_step": 550132, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0781917572021484, "global_step": 550133, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.01769757270813, "global_step": 550134, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.016496181488037, "global_step": 550135, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0902934074401855, "global_step": 550136, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.932911992073059, "global_step": 550137, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0902390480041504, "global_step": 550138, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0899276733398438, "global_step": 550139, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.051548719406128, "global_step": 550140, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.061511993408203, "global_step": 550141, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0244688987731934, "global_step": 550142, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0551247596740723, "global_step": 550143, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.016836166381836, "global_step": 550144, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0588269233703613, "global_step": 550145, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9797818660736084, "global_step": 550146, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0497384071350098, "global_step": 550147, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.067897319793701, "global_step": 550148, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.989162802696228, "global_step": 550149, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.991904616355896, "global_step": 550150, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9902540445327759, "global_step": 550151, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0270540714263916, "global_step": 550152, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.996397852897644, "global_step": 550153, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0299229621887207, "global_step": 550154, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.08731746673584, "global_step": 550155, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1514668464660645, "global_step": 550156, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0338516235351562, "global_step": 550157, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.028817892074585, "global_step": 550158, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.048630714416504, "global_step": 550159, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.028334379196167, "global_step": 550160, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9720046520233154, "global_step": 550161, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9867900609970093, "global_step": 550162, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.055666923522949, "global_step": 550163, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0373024940490723, "global_step": 550164, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.030836582183838, "global_step": 550165, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0252270698547363, "global_step": 550166, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0001273155212402, "global_step": 550167, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0566182136535645, "global_step": 550168, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.043149471282959, "global_step": 550169, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.106228828430176, "global_step": 550170, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.084596872329712, "global_step": 550171, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0560290813446045, "global_step": 550172, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0376510620117188, "global_step": 550173, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0325918197631836, "global_step": 550174, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0404653549194336, "global_step": 550175, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0803191661834717, "global_step": 550176, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0218517780303955, "global_step": 550177, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.035397529602051, "global_step": 550178, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.071056604385376, "global_step": 550179, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.029766321182251, "global_step": 550180, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.097430467605591, "global_step": 550181, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.01901912689209, "global_step": 550182, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0608294010162354, "global_step": 550183, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.941145658493042, "global_step": 550184, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.024580717086792, "global_step": 550185, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0170207023620605, "global_step": 550186, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0331082344055176, "global_step": 550187, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.964368462562561, "global_step": 550188, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.015448808670044, "global_step": 550189, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.071094512939453, "global_step": 550190, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0709526538848877, "global_step": 550191, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0144870281219482, "global_step": 550192, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0184273719787598, "global_step": 550193, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.072932720184326, "global_step": 550194, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0002105236053467, "global_step": 550195, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9208707809448242, "global_step": 550196, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.987687110900879, "global_step": 550197, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9683524370193481, "global_step": 550198, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0629491806030273, "global_step": 550199, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.088454246520996, "global_step": 550200, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.067251682281494, "global_step": 550201, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.008178234100342, "global_step": 550202, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0690526962280273, "global_step": 550203, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1424474716186523, "global_step": 550204, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0621795654296875, "global_step": 550205, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.077857494354248, "global_step": 550206, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0292441844940186, "global_step": 550207, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0885660648345947, "global_step": 550208, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.977717399597168, "global_step": 550209, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0557949542999268, "global_step": 550210, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.928658127784729, "global_step": 550211, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0183968544006348, "global_step": 550212, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1328630447387695, "global_step": 550213, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.068917989730835, "global_step": 550214, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0973007678985596, "global_step": 550215, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9632915258407593, "global_step": 550216, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.007429361343384, "global_step": 550217, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9950960874557495, "global_step": 550218, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.017512083053589, "global_step": 550219, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0984244346618652, "global_step": 550220, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.124156951904297, "global_step": 550221, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.118856191635132, "global_step": 550222, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.980027437210083, "global_step": 550223, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0177788734436035, "global_step": 550224, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1037471294403076, "global_step": 550225, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9157615900039673, "global_step": 550226, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.010408878326416, "global_step": 550227, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.027409791946411, "global_step": 550228, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.067087411880493, "global_step": 550229, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.102071523666382, "global_step": 550230, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.99637770652771, "global_step": 550231, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1084117889404297, "global_step": 550232, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.037959575653076, "global_step": 550233, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1390507221221924, "global_step": 550234, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.085721015930176, "global_step": 550235, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0444982051849365, "global_step": 550236, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0735254287719727, "global_step": 550237, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9922630786895752, "global_step": 550238, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0507333278656006, "global_step": 550239, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.019428014755249, "global_step": 550240, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.934923529624939, "global_step": 550241, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0845203399658203, "global_step": 550242, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0437188148498535, "global_step": 550243, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.066167116165161, "global_step": 550244, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9931235313415527, "global_step": 550245, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0346665382385254, "global_step": 550246, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9751321077346802, "global_step": 550247, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.010789394378662, "global_step": 550248, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.069261312484741, "global_step": 550249, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0836713314056396, "global_step": 550250, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9950820207595825, "global_step": 550251, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9947737455368042, "global_step": 550252, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1015784740448, "global_step": 550253, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0970394611358643, "global_step": 550254, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0478944778442383, "global_step": 550255, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1238889694213867, "global_step": 550256, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9655781984329224, "global_step": 550257, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0199086666107178, "global_step": 550258, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0653882026672363, "global_step": 550259, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.09537410736084, "global_step": 550260, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0009729862213135, "global_step": 550261, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.021817684173584, "global_step": 550262, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0793983936309814, "global_step": 550263, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9486485719680786, "global_step": 550264, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9689290523529053, "global_step": 550265, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0239877700805664, "global_step": 550266, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.079923629760742, "global_step": 550267, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1001663208007812, "global_step": 550268, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0947651863098145, "global_step": 550269, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.048351764678955, "global_step": 550270, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9755759239196777, "global_step": 550271, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.057788372039795, "global_step": 550272, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0395009517669678, "global_step": 550273, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.022716522216797, "global_step": 550274, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0578038692474365, "global_step": 550275, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0240252017974854, "global_step": 550276, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.078761577606201, "global_step": 550277, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.047170639038086, "global_step": 550278, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0959978103637695, "global_step": 550279, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9565662145614624, "global_step": 550280, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.086569309234619, "global_step": 550281, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.997879147529602, "global_step": 550282, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.007155179977417, "global_step": 550283, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.108306884765625, "global_step": 550284, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.052997350692749, "global_step": 550285, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0713839530944824, "global_step": 550286, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.049471378326416, "global_step": 550287, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0193028450012207, "global_step": 550288, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.063861608505249, "global_step": 550289, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.004371166229248, "global_step": 550290, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.104332685470581, "global_step": 550291, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.980271577835083, "global_step": 550292, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.093583583831787, "global_step": 550293, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.053493022918701, "global_step": 550294, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9949774742126465, "global_step": 550295, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0410962104797363, "global_step": 550296, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.056591033935547, "global_step": 550297, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0202574729919434, "global_step": 550298, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.071603775024414, "global_step": 550299, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.052903652191162, "global_step": 550300, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0396316051483154, "global_step": 550301, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9822880029678345, "global_step": 550302, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.999914526939392, "global_step": 550303, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1068084239959717, "global_step": 550304, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.058319568634033, "global_step": 550305, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.003926992416382, "global_step": 550306, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.082494020462036, "global_step": 550307, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.032813310623169, "global_step": 550308, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0444798469543457, "global_step": 550309, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.103294610977173, "global_step": 550310, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.108713388442993, "global_step": 550311, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.09413743019104, "global_step": 550312, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0506834983825684, "global_step": 550313, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.01359486579895, "global_step": 550314, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0236213207244873, "global_step": 550315, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1105527877807617, "global_step": 550316, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0368151664733887, "global_step": 550317, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1245572566986084, "global_step": 550318, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.031505823135376, "global_step": 550319, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.081591844558716, "global_step": 550320, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.049375534057617, "global_step": 550321, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0296103954315186, "global_step": 550322, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.026445150375366, "global_step": 550323, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0678560733795166, "global_step": 550324, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0148797035217285, "global_step": 550325, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9707963466644287, "global_step": 550326, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9924794435501099, "global_step": 550327, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.141143321990967, "global_step": 550328, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0600132942199707, "global_step": 550329, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.040139675140381, "global_step": 550330, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.992295503616333, "global_step": 550331, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0744640827178955, "global_step": 550332, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9626388549804688, "global_step": 550333, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1229043006896973, "global_step": 550334, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0561065673828125, "global_step": 550335, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.078402042388916, "global_step": 550336, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0341169834136963, "global_step": 550337, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.007880926132202, "global_step": 550338, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0222067832946777, "global_step": 550339, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0421392917633057, "global_step": 550340, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.00380539894104, "global_step": 550341, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9676406383514404, "global_step": 550342, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.095482110977173, "global_step": 550343, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0407419204711914, "global_step": 550344, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0339066982269287, "global_step": 550345, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1153976917266846, "global_step": 550346, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.060234785079956, "global_step": 550347, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0840508937835693, "global_step": 550348, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0297796726226807, "global_step": 550349, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.014435052871704, "global_step": 550350, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0263636112213135, "global_step": 550351, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0877182483673096, "global_step": 550352, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.007812261581421, "global_step": 550353, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9297008514404297, "global_step": 550354, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0901105403900146, "global_step": 550355, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.035501718521118, "global_step": 550356, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.986343264579773, "global_step": 550357, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0213828086853027, "global_step": 550358, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9692286252975464, "global_step": 550359, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.995893120765686, "global_step": 550360, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0654714107513428, "global_step": 550361, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9857500791549683, "global_step": 550362, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9851244688034058, "global_step": 550363, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.049180507659912, "global_step": 550364, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.985636830329895, "global_step": 550365, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.157940149307251, "global_step": 550366, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9758015871047974, "global_step": 550367, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.047863721847534, "global_step": 550368, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9817734956741333, "global_step": 550369, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.058955669403076, "global_step": 550370, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0367305278778076, "global_step": 550371, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0690181255340576, "global_step": 550372, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.090517282485962, "global_step": 550373, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.094132900238037, "global_step": 550374, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.990261435508728, "global_step": 550375, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0757272243499756, "global_step": 550376, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9920307397842407, "global_step": 550377, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0281600952148438, "global_step": 550378, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9425857067108154, "global_step": 550379, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.043976068496704, "global_step": 550380, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0603647232055664, "global_step": 550381, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0254628658294678, "global_step": 550382, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.013206720352173, "global_step": 550383, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.987958550453186, "global_step": 550384, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9974141120910645, "global_step": 550385, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0517566204071045, "global_step": 550386, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9957650899887085, "global_step": 550387, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0415172576904297, "global_step": 550388, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.046821117401123, "global_step": 550389, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.088735580444336, "global_step": 550390, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.023346424102783, "global_step": 550391, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0728979110717773, "global_step": 550392, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.01309871673584, "global_step": 550393, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.034489393234253, "global_step": 550394, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.048630475997925, "global_step": 550395, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.00138521194458, "global_step": 550396, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0573627948760986, "global_step": 550397, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0467445850372314, "global_step": 550398, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0621118545532227, "global_step": 550399, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1095993518829346, "global_step": 550400, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.041672945022583, "global_step": 550401, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.010157346725464, "global_step": 550402, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0918564796447754, "global_step": 550403, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9846264123916626, "global_step": 550404, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.01242995262146, "global_step": 550405, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1149513721466064, "global_step": 550406, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.97147798538208, "global_step": 550407, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0129709243774414, "global_step": 550408, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9634122848510742, "global_step": 550409, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0016984939575195, "global_step": 550410, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0857677459716797, "global_step": 550411, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.069901704788208, "global_step": 550412, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0770041942596436, "global_step": 550413, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0927984714508057, "global_step": 550414, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.046868085861206, "global_step": 550415, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.023228168487549, "global_step": 550416, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.04878568649292, "global_step": 550417, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0322988033294678, "global_step": 550418, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.014634847640991, "global_step": 550419, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0219411849975586, "global_step": 550420, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0230085849761963, "global_step": 550421, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.025383710861206, "global_step": 550422, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9727187156677246, "global_step": 550423, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0439584255218506, "global_step": 550424, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9867826700210571, "global_step": 550425, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0459303855895996, "global_step": 550426, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0246400833129883, "global_step": 550427, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.99380362033844, "global_step": 550428, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9879035949707031, "global_step": 550429, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0320045948028564, "global_step": 550430, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9827189445495605, "global_step": 550431, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.150635242462158, "global_step": 550432, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9891504049301147, "global_step": 550433, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0141496658325195, "global_step": 550434, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.091536521911621, "global_step": 550435, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.013713836669922, "global_step": 550436, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.07041072845459, "global_step": 550437, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.017845869064331, "global_step": 550438, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.027625322341919, "global_step": 550439, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.018897294998169, "global_step": 550440, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9492995738983154, "global_step": 550441, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0533642768859863, "global_step": 550442, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.102264404296875, "global_step": 550443, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0917859077453613, "global_step": 550444, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9911097288131714, "global_step": 550445, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.097430467605591, "global_step": 550446, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0860137939453125, "global_step": 550447, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9996095895767212, "global_step": 550448, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0585825443267822, "global_step": 550449, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0750620365142822, "global_step": 550450, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0447864532470703, "global_step": 550451, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1436846256256104, "global_step": 550452, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.023080587387085, "global_step": 550453, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9287866353988647, "global_step": 550454, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.074082136154175, "global_step": 550455, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0758304595947266, "global_step": 550456, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.053354024887085, "global_step": 550457, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0656344890594482, "global_step": 550458, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9943987131118774, "global_step": 550459, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0402936935424805, "global_step": 550460, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0127251148223877, "global_step": 550461, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0152511596679688, "global_step": 550462, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0348806381225586, "global_step": 550463, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.075937509536743, "global_step": 550464, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9844304323196411, "global_step": 550465, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9579623937606812, "global_step": 550466, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9703068733215332, "global_step": 550467, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0496432781219482, "global_step": 550468, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0737733840942383, "global_step": 550469, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0154800415039062, "global_step": 550470, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.007444381713867, "global_step": 550471, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9881891012191772, "global_step": 550472, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.000631332397461, "global_step": 550473, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9448626041412354, "global_step": 550474, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.05472731590271, "global_step": 550475, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0265514850616455, "global_step": 550476, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.038830041885376, "global_step": 550477, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0296435356140137, "global_step": 550478, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.055947780609131, "global_step": 550479, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0058796405792236, "global_step": 550480, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0974583625793457, "global_step": 550481, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1542084217071533, "global_step": 550482, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0014758110046387, "global_step": 550483, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0488200187683105, "global_step": 550484, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9385310411453247, "global_step": 550485, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.06482195854187, "global_step": 550486, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9734374284744263, "global_step": 550487, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.073026418685913, "global_step": 550488, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.079481363296509, "global_step": 550489, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.03890061378479, "global_step": 550490, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0579378604888916, "global_step": 550491, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.114218235015869, "global_step": 550492, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.115814685821533, "global_step": 550493, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1253507137298584, "global_step": 550494, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.067394495010376, "global_step": 550495, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0605709552764893, "global_step": 550496, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0267045497894287, "global_step": 550497, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9933289289474487, "global_step": 550498, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.001699447631836, "global_step": 550499, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.117821216583252, "global_step": 550500, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.062138080596924, "global_step": 550501, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9543085098266602, "global_step": 550502, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0359625816345215, "global_step": 550503, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9479353427886963, "global_step": 550504, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.041576385498047, "global_step": 550505, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.095442295074463, "global_step": 550506, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0392022132873535, "global_step": 550507, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0975141525268555, "global_step": 550508, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.010620355606079, "global_step": 550509, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9787677526474, "global_step": 550510, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.1239912509918213, "global_step": 550511, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.033623456954956, "global_step": 550512, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9720873832702637, "global_step": 550513, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0038506984710693, "global_step": 550514, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.044502019882202, "global_step": 550515, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.028926134109497, "global_step": 550516, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9921201467514038, "global_step": 550517, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.102111577987671, "global_step": 550518, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0441081523895264, "global_step": 550519, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9786659479141235, "global_step": 550520, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.03204083442688, "global_step": 550521, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.048095941543579, "global_step": 550522, "epoch": 917, "lr": 5e-05}
{"train_loss": 1.9888252019882202, "global_step": 550523, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0307092666625977, "global_step": 550524, "epoch": 917, "lr": 5e-05}
{"train_loss": 2.0345566272735596, "global_step": 550525, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0400917530059814, "global_step": 550526, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9831945896148682, "global_step": 550527, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9925960302352905, "global_step": 550528, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9740351438522339, "global_step": 550529, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.049300193786621, "global_step": 550530, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9976133108139038, "global_step": 550531, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9573073387145996, "global_step": 550532, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.8962026834487915, "global_step": 550533, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.065577507019043, "global_step": 550534, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.99403715133667, "global_step": 550535, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.068986654281616, "global_step": 550536, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0893588066101074, "global_step": 550537, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.014835834503174, "global_step": 550538, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.063525676727295, "global_step": 550539, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.97111177444458, "global_step": 550540, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9490389823913574, "global_step": 550541, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.015770435333252, "global_step": 550542, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0553689002990723, "global_step": 550543, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.064228057861328, "global_step": 550544, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.015122175216675, "global_step": 550545, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.030510187149048, "global_step": 550546, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0483405590057373, "global_step": 550547, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1038005352020264, "global_step": 550548, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0452721118927, "global_step": 550549, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.042282819747925, "global_step": 550550, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9735827445983887, "global_step": 550551, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.031479597091675, "global_step": 550552, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0541794300079346, "global_step": 550553, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0329039096832275, "global_step": 550554, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0476386547088623, "global_step": 550555, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.002549648284912, "global_step": 550556, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9322203397750854, "global_step": 550557, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0342698097229004, "global_step": 550558, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.057966947555542, "global_step": 550559, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.005290985107422, "global_step": 550560, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0152428150177, "global_step": 550561, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.12030291557312, "global_step": 550562, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.958101511001587, "global_step": 550563, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.111259937286377, "global_step": 550564, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.061663866043091, "global_step": 550565, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.149841547012329, "global_step": 550566, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.055544376373291, "global_step": 550567, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0541341304779053, "global_step": 550568, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0018060207366943, "global_step": 550569, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0258021354675293, "global_step": 550570, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0034918785095215, "global_step": 550571, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.044497489929199, "global_step": 550572, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0317296981811523, "global_step": 550573, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0324103832244873, "global_step": 550574, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.040501117706299, "global_step": 550575, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9631296396255493, "global_step": 550576, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9833561182022095, "global_step": 550577, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.05629825592041, "global_step": 550578, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0952837467193604, "global_step": 550579, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.050969123840332, "global_step": 550580, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.108203172683716, "global_step": 550581, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.083878755569458, "global_step": 550582, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0257296562194824, "global_step": 550583, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1235899925231934, "global_step": 550584, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9827874898910522, "global_step": 550585, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9309229850769043, "global_step": 550586, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0530529022216797, "global_step": 550587, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0861587524414062, "global_step": 550588, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0277304649353027, "global_step": 550589, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.906050443649292, "global_step": 550590, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.967307686805725, "global_step": 550591, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.016587257385254, "global_step": 550592, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0176241397857666, "global_step": 550593, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.976788878440857, "global_step": 550594, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.079961061477661, "global_step": 550595, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9670583009719849, "global_step": 550596, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0915048122406006, "global_step": 550597, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0535717010498047, "global_step": 550598, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0111758708953857, "global_step": 550599, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9996527433395386, "global_step": 550600, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.951685905456543, "global_step": 550601, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9962431192398071, "global_step": 550602, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.95851469039917, "global_step": 550603, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0203018188476562, "global_step": 550604, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.948641300201416, "global_step": 550605, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0425662994384766, "global_step": 550606, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9746427536010742, "global_step": 550607, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.047534227371216, "global_step": 550608, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0104517936706543, "global_step": 550609, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.046443462371826, "global_step": 550610, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.977774739265442, "global_step": 550611, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0006587505340576, "global_step": 550612, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.009342670440674, "global_step": 550613, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0096755027770996, "global_step": 550614, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0977320671081543, "global_step": 550615, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9888736009597778, "global_step": 550616, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9427024126052856, "global_step": 550617, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.05212664604187, "global_step": 550618, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1256768703460693, "global_step": 550619, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9764047861099243, "global_step": 550620, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9465487003326416, "global_step": 550621, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9337334632873535, "global_step": 550622, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0102767944335938, "global_step": 550623, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.01125431060791, "global_step": 550624, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1109728813171387, "global_step": 550625, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0738940238952637, "global_step": 550626, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.033428192138672, "global_step": 550627, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.99495530128479, "global_step": 550628, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.03859806060791, "global_step": 550629, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0354769229888916, "global_step": 550630, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.040321111679077, "global_step": 550631, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9894732236862183, "global_step": 550632, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.088430881500244, "global_step": 550633, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.979891061782837, "global_step": 550634, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9672833681106567, "global_step": 550635, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0224318504333496, "global_step": 550636, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.060716390609741, "global_step": 550637, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0296781063079834, "global_step": 550638, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.045192003250122, "global_step": 550639, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0495760440826416, "global_step": 550640, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0484492778778076, "global_step": 550641, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9846237897872925, "global_step": 550642, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.043726682662964, "global_step": 550643, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0011284351348877, "global_step": 550644, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.065295934677124, "global_step": 550645, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.03006911277771, "global_step": 550646, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0102410316467285, "global_step": 550647, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0373361110687256, "global_step": 550648, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9642078876495361, "global_step": 550649, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.991029143333435, "global_step": 550650, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.02091908454895, "global_step": 550651, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0291690826416016, "global_step": 550652, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.989264965057373, "global_step": 550653, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9481507539749146, "global_step": 550654, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.057659387588501, "global_step": 550655, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1005663871765137, "global_step": 550656, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0818822383880615, "global_step": 550657, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.029855966567993, "global_step": 550658, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.003971576690674, "global_step": 550659, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0046162605285645, "global_step": 550660, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0330634117126465, "global_step": 550661, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0563666820526123, "global_step": 550662, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9699915647506714, "global_step": 550663, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9740285873413086, "global_step": 550664, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.942195177078247, "global_step": 550665, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0201833248138428, "global_step": 550666, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.080460786819458, "global_step": 550667, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0691938400268555, "global_step": 550668, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0215156078338623, "global_step": 550669, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.01949143409729, "global_step": 550670, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0132458209991455, "global_step": 550671, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9000462293624878, "global_step": 550672, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9691851139068604, "global_step": 550673, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.957269310951233, "global_step": 550674, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9795281887054443, "global_step": 550675, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.019753932952881, "global_step": 550676, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9892133474349976, "global_step": 550677, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9754323959350586, "global_step": 550678, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.002347469329834, "global_step": 550679, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.998672604560852, "global_step": 550680, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0558834075927734, "global_step": 550681, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0450854301452637, "global_step": 550682, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0094430446624756, "global_step": 550683, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9351110458374023, "global_step": 550684, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.080671548843384, "global_step": 550685, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0759029388427734, "global_step": 550686, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.019303560256958, "global_step": 550687, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9780375957489014, "global_step": 550688, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.986714482307434, "global_step": 550689, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.010596990585327, "global_step": 550690, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.010044574737549, "global_step": 550691, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.989534616470337, "global_step": 550692, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0467684268951416, "global_step": 550693, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0666210651397705, "global_step": 550694, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0317389965057373, "global_step": 550695, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0661985874176025, "global_step": 550696, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9813374280929565, "global_step": 550697, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.016066551208496, "global_step": 550698, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0020101070404053, "global_step": 550699, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0049452781677246, "global_step": 550700, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0456783771514893, "global_step": 550701, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.035346031188965, "global_step": 550702, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.990988850593567, "global_step": 550703, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9915683269500732, "global_step": 550704, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.09915828704834, "global_step": 550705, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.043651580810547, "global_step": 550706, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9997225999832153, "global_step": 550707, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.003265857696533, "global_step": 550708, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.006547689437866, "global_step": 550709, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0327980518341064, "global_step": 550710, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0548925399780273, "global_step": 550711, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.046483039855957, "global_step": 550712, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.048753261566162, "global_step": 550713, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9951496124267578, "global_step": 550714, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9567773342132568, "global_step": 550715, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.008068561553955, "global_step": 550716, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0281319618225098, "global_step": 550717, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1132335662841797, "global_step": 550718, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1075491905212402, "global_step": 550719, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0351064205169678, "global_step": 550720, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0011537075042725, "global_step": 550721, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0352096557617188, "global_step": 550722, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0457184314727783, "global_step": 550723, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0721588134765625, "global_step": 550724, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9961596727371216, "global_step": 550725, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.044861316680908, "global_step": 550726, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0379912853240967, "global_step": 550727, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9324010610580444, "global_step": 550728, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0314812660217285, "global_step": 550729, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1143603324890137, "global_step": 550730, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9907935857772827, "global_step": 550731, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1079182624816895, "global_step": 550732, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.011838674545288, "global_step": 550733, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9231231212615967, "global_step": 550734, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.085332155227661, "global_step": 550735, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9611836671829224, "global_step": 550736, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.045912742614746, "global_step": 550737, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0856451988220215, "global_step": 550738, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.029541492462158, "global_step": 550739, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0047144889831543, "global_step": 550740, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.042480707168579, "global_step": 550741, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0961835384368896, "global_step": 550742, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0033504962921143, "global_step": 550743, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0151302814483643, "global_step": 550744, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9567441940307617, "global_step": 550745, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9124680757522583, "global_step": 550746, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0220673084259033, "global_step": 550747, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0806381702423096, "global_step": 550748, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.979762077331543, "global_step": 550749, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.061516761779785, "global_step": 550750, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9125633239746094, "global_step": 550751, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0203709602355957, "global_step": 550752, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0358521938323975, "global_step": 550753, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1334972381591797, "global_step": 550754, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.033747911453247, "global_step": 550755, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0520591735839844, "global_step": 550756, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.995803952217102, "global_step": 550757, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.084733724594116, "global_step": 550758, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0226612091064453, "global_step": 550759, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9835116863250732, "global_step": 550760, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.097367525100708, "global_step": 550761, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9588613510131836, "global_step": 550762, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.000865936279297, "global_step": 550763, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.993098258972168, "global_step": 550764, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.064008951187134, "global_step": 550765, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9870456457138062, "global_step": 550766, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0644826889038086, "global_step": 550767, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0180680751800537, "global_step": 550768, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.00997257232666, "global_step": 550769, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.941389560699463, "global_step": 550770, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0984227657318115, "global_step": 550771, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.027925968170166, "global_step": 550772, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.011991024017334, "global_step": 550773, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0898287296295166, "global_step": 550774, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9732874631881714, "global_step": 550775, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9511926174163818, "global_step": 550776, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1165621280670166, "global_step": 550777, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.00703763961792, "global_step": 550778, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.007697582244873, "global_step": 550779, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0135579109191895, "global_step": 550780, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0507912635803223, "global_step": 550781, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1548361778259277, "global_step": 550782, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9921956062316895, "global_step": 550783, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0564403533935547, "global_step": 550784, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0338711738586426, "global_step": 550785, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0507473945617676, "global_step": 550786, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0220723152160645, "global_step": 550787, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9399616718292236, "global_step": 550788, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9353059530258179, "global_step": 550789, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.01098895072937, "global_step": 550790, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9431779384613037, "global_step": 550791, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0172536373138428, "global_step": 550792, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0308592319488525, "global_step": 550793, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9854390621185303, "global_step": 550794, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.079149007797241, "global_step": 550795, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.052042245864868, "global_step": 550796, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0073812007904053, "global_step": 550797, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9297915697097778, "global_step": 550798, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.961135745048523, "global_step": 550799, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9864226579666138, "global_step": 550800, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.053553342819214, "global_step": 550801, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0717945098876953, "global_step": 550802, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0762171745300293, "global_step": 550803, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.017042398452759, "global_step": 550804, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.031653881072998, "global_step": 550805, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.97750985622406, "global_step": 550806, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1724793910980225, "global_step": 550807, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.063406467437744, "global_step": 550808, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9982883930206299, "global_step": 550809, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.975682020187378, "global_step": 550810, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0475807189941406, "global_step": 550811, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.034532308578491, "global_step": 550812, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1057708263397217, "global_step": 550813, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0758726596832275, "global_step": 550814, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9871504306793213, "global_step": 550815, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.053344964981079, "global_step": 550816, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0134899616241455, "global_step": 550817, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.020728349685669, "global_step": 550818, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9926239252090454, "global_step": 550819, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0182583332061768, "global_step": 550820, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0207414627075195, "global_step": 550821, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0234429836273193, "global_step": 550822, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0665829181671143, "global_step": 550823, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0199782848358154, "global_step": 550824, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.019242763519287, "global_step": 550825, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.01428484916687, "global_step": 550826, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9929779767990112, "global_step": 550827, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.072510242462158, "global_step": 550828, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9543482065200806, "global_step": 550829, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.160447835922241, "global_step": 550830, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0410449504852295, "global_step": 550831, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0693936347961426, "global_step": 550832, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0407843589782715, "global_step": 550833, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.054126501083374, "global_step": 550834, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9737458229064941, "global_step": 550835, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0130109786987305, "global_step": 550836, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9802302122116089, "global_step": 550837, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0767064094543457, "global_step": 550838, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.072767496109009, "global_step": 550839, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9960887432098389, "global_step": 550840, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0600943565368652, "global_step": 550841, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0628392696380615, "global_step": 550842, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0282397270202637, "global_step": 550843, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.031904697418213, "global_step": 550844, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9549037218093872, "global_step": 550845, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9463144540786743, "global_step": 550846, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.042311429977417, "global_step": 550847, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0411086082458496, "global_step": 550848, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0207183361053467, "global_step": 550849, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.015064001083374, "global_step": 550850, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9922468662261963, "global_step": 550851, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.023280382156372, "global_step": 550852, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0059163570404053, "global_step": 550853, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9607559442520142, "global_step": 550854, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0280447006225586, "global_step": 550855, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9984140396118164, "global_step": 550856, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.988584041595459, "global_step": 550857, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.070023536682129, "global_step": 550858, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0430970191955566, "global_step": 550859, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9996311664581299, "global_step": 550860, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0774295330047607, "global_step": 550861, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1069905757904053, "global_step": 550862, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9545531272888184, "global_step": 550863, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.030641794204712, "global_step": 550864, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0877206325531006, "global_step": 550865, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9692156314849854, "global_step": 550866, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9779943227767944, "global_step": 550867, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0366954803466797, "global_step": 550868, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.019948959350586, "global_step": 550869, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.974847674369812, "global_step": 550870, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.08518123626709, "global_step": 550871, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0249104499816895, "global_step": 550872, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.050471305847168, "global_step": 550873, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9741135835647583, "global_step": 550874, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0651254653930664, "global_step": 550875, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.035243511199951, "global_step": 550876, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0572922229766846, "global_step": 550877, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0794050693511963, "global_step": 550878, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0129871368408203, "global_step": 550879, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0011773109436035, "global_step": 550880, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.076906681060791, "global_step": 550881, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0169730186462402, "global_step": 550882, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0459377765655518, "global_step": 550883, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.108614444732666, "global_step": 550884, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.099313259124756, "global_step": 550885, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0627527236938477, "global_step": 550886, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9869743585586548, "global_step": 550887, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9736833572387695, "global_step": 550888, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9435126781463623, "global_step": 550889, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9936110973358154, "global_step": 550890, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0570268630981445, "global_step": 550891, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0219297409057617, "global_step": 550892, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.069132089614868, "global_step": 550893, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0593421459198, "global_step": 550894, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0347654819488525, "global_step": 550895, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0779428482055664, "global_step": 550896, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0363810062408447, "global_step": 550897, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0542988777160645, "global_step": 550898, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.101294755935669, "global_step": 550899, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9831570386886597, "global_step": 550900, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0766823291778564, "global_step": 550901, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9967107772827148, "global_step": 550902, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0594334602355957, "global_step": 550903, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.007547378540039, "global_step": 550904, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.052368402481079, "global_step": 550905, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0308265686035156, "global_step": 550906, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1183674335479736, "global_step": 550907, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.161372661590576, "global_step": 550908, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.065232038497925, "global_step": 550909, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0410375595092773, "global_step": 550910, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9834175109863281, "global_step": 550911, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0205442905426025, "global_step": 550912, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9952080249786377, "global_step": 550913, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.022308111190796, "global_step": 550914, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.007337808609009, "global_step": 550915, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0006346702575684, "global_step": 550916, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9523813724517822, "global_step": 550917, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1060495376586914, "global_step": 550918, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.014580011367798, "global_step": 550919, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0460333824157715, "global_step": 550920, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.104865074157715, "global_step": 550921, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.00062894821167, "global_step": 550922, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.03818416595459, "global_step": 550923, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.046761989593506, "global_step": 550924, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9975932836532593, "global_step": 550925, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9807902574539185, "global_step": 550926, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0345311164855957, "global_step": 550927, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.069631576538086, "global_step": 550928, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.028092861175537, "global_step": 550929, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0718889236450195, "global_step": 550930, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.001250982284546, "global_step": 550931, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.027890205383301, "global_step": 550932, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9952671527862549, "global_step": 550933, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.080742835998535, "global_step": 550934, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0227391719818115, "global_step": 550935, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0891971588134766, "global_step": 550936, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.093118906021118, "global_step": 550937, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.100900173187256, "global_step": 550938, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9347344636917114, "global_step": 550939, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.021723508834839, "global_step": 550940, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0019373893737793, "global_step": 550941, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0075464248657227, "global_step": 550942, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0598251819610596, "global_step": 550943, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.025543689727783, "global_step": 550944, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9947385787963867, "global_step": 550945, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0259034633636475, "global_step": 550946, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9823083877563477, "global_step": 550947, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.052034378051758, "global_step": 550948, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.077698230743408, "global_step": 550949, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.121213912963867, "global_step": 550950, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0604825019836426, "global_step": 550951, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.8397064208984375, "global_step": 550952, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.077754020690918, "global_step": 550953, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0492091178894043, "global_step": 550954, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0601260662078857, "global_step": 550955, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.012125015258789, "global_step": 550956, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.006770133972168, "global_step": 550957, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1153221130371094, "global_step": 550958, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.071406126022339, "global_step": 550959, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0788049697875977, "global_step": 550960, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.02349591255188, "global_step": 550961, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.066878318786621, "global_step": 550962, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0931780338287354, "global_step": 550963, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.049889326095581, "global_step": 550964, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.028099775314331, "global_step": 550965, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0231566429138184, "global_step": 550966, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1224453449249268, "global_step": 550967, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.949780821800232, "global_step": 550968, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0676631927490234, "global_step": 550969, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9950014352798462, "global_step": 550970, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0717475414276123, "global_step": 550971, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0305287837982178, "global_step": 550972, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0120444297790527, "global_step": 550973, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9898109436035156, "global_step": 550974, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.08891224861145, "global_step": 550975, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0113847255706787, "global_step": 550976, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9439656734466553, "global_step": 550977, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9342234134674072, "global_step": 550978, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.089001178741455, "global_step": 550979, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0267014503479004, "global_step": 550980, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0620157718658447, "global_step": 550981, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0683562755584717, "global_step": 550982, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.032465934753418, "global_step": 550983, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1279375553131104, "global_step": 550984, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.072005033493042, "global_step": 550985, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.042811870574951, "global_step": 550986, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9600262641906738, "global_step": 550987, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.030381441116333, "global_step": 550988, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0682754516601562, "global_step": 550989, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0295307636260986, "global_step": 550990, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0539965629577637, "global_step": 550991, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0111401081085205, "global_step": 550992, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1090314388275146, "global_step": 550993, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9532564878463745, "global_step": 550994, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.054422378540039, "global_step": 550995, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.121967077255249, "global_step": 550996, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0547072887420654, "global_step": 550997, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1091365814208984, "global_step": 550998, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0034286975860596, "global_step": 550999, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0213418006896973, "global_step": 551000, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.960766077041626, "global_step": 551001, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1401290893554688, "global_step": 551002, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9583990573883057, "global_step": 551003, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1251630783081055, "global_step": 551004, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.078028678894043, "global_step": 551005, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0401155948638916, "global_step": 551006, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0327162742614746, "global_step": 551007, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1009745597839355, "global_step": 551008, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0654897689819336, "global_step": 551009, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.02416729927063, "global_step": 551010, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.983799695968628, "global_step": 551011, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.053114175796509, "global_step": 551012, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.028214454650879, "global_step": 551013, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.044609785079956, "global_step": 551014, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.022921323776245, "global_step": 551015, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0899670124053955, "global_step": 551016, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.000450611114502, "global_step": 551017, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.028987407684326, "global_step": 551018, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9067531824111938, "global_step": 551019, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0648629665374756, "global_step": 551020, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.086718797683716, "global_step": 551021, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.012035846710205, "global_step": 551022, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0115020275115967, "global_step": 551023, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9715135097503662, "global_step": 551024, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.066312074661255, "global_step": 551025, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9733253717422485, "global_step": 551026, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0679707527160645, "global_step": 551027, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0123629570007324, "global_step": 551028, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0978269577026367, "global_step": 551029, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0464117527008057, "global_step": 551030, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0205602645874023, "global_step": 551031, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9715113639831543, "global_step": 551032, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.011850595474243, "global_step": 551033, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9328463077545166, "global_step": 551034, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0427446365356445, "global_step": 551035, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.107506275177002, "global_step": 551036, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9651762247085571, "global_step": 551037, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.05830454826355, "global_step": 551038, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.063478708267212, "global_step": 551039, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9678819179534912, "global_step": 551040, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0164058208465576, "global_step": 551041, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0073933601379395, "global_step": 551042, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.067377805709839, "global_step": 551043, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0910418033599854, "global_step": 551044, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0256850719451904, "global_step": 551045, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9393264055252075, "global_step": 551046, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.013873815536499, "global_step": 551047, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0558884143829346, "global_step": 551048, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.097231388092041, "global_step": 551049, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.135350465774536, "global_step": 551050, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9477275609970093, "global_step": 551051, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0149765014648438, "global_step": 551052, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0589540004730225, "global_step": 551053, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1291344165802, "global_step": 551054, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1565544605255127, "global_step": 551055, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.00449538230896, "global_step": 551056, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.975585699081421, "global_step": 551057, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.072390556335449, "global_step": 551058, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0851669311523438, "global_step": 551059, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0244598388671875, "global_step": 551060, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.032041072845459, "global_step": 551061, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.044874668121338, "global_step": 551062, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0060811042785645, "global_step": 551063, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.045100688934326, "global_step": 551064, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0674166679382324, "global_step": 551065, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9664652347564697, "global_step": 551066, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.145862102508545, "global_step": 551067, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.038114309310913, "global_step": 551068, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9462308883666992, "global_step": 551069, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9803413152694702, "global_step": 551070, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0103492736816406, "global_step": 551071, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0659918785095215, "global_step": 551072, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0716636180877686, "global_step": 551073, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.047884941101074, "global_step": 551074, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.013200044631958, "global_step": 551075, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0971269607543945, "global_step": 551076, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.092829704284668, "global_step": 551077, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0329599380493164, "global_step": 551078, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1355528831481934, "global_step": 551079, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0606327056884766, "global_step": 551080, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.8968173265457153, "global_step": 551081, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.045332193374634, "global_step": 551082, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0108702182769775, "global_step": 551083, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9951175451278687, "global_step": 551084, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0540754795074463, "global_step": 551085, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9593843221664429, "global_step": 551086, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.026956081390381, "global_step": 551087, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0229132175445557, "global_step": 551088, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0772202014923096, "global_step": 551089, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0573675632476807, "global_step": 551090, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9651463031768799, "global_step": 551091, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0756263732910156, "global_step": 551092, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0397560596466064, "global_step": 551093, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0533628463745117, "global_step": 551094, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.060100555419922, "global_step": 551095, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0064697265625, "global_step": 551096, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9838484525680542, "global_step": 551097, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.103966236114502, "global_step": 551098, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9558663368225098, "global_step": 551099, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.081458806991577, "global_step": 551100, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.976730465888977, "global_step": 551101, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.931523323059082, "global_step": 551102, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.01194167137146, "global_step": 551103, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0744550228118896, "global_step": 551104, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0977566242218018, "global_step": 551105, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0992062091827393, "global_step": 551106, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.020007610321045, "global_step": 551107, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.093632221221924, "global_step": 551108, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9824022054672241, "global_step": 551109, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9586585760116577, "global_step": 551110, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1048085689544678, "global_step": 551111, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.079612970352173, "global_step": 551112, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9158952236175537, "global_step": 551113, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0140633583068848, "global_step": 551114, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0466725826263428, "global_step": 551115, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9768277406692505, "global_step": 551116, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0592739582061768, "global_step": 551117, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0075790882110596, "global_step": 551118, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0660064220428467, "global_step": 551119, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9745891094207764, "global_step": 551120, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1322097778320312, "global_step": 551121, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.07310152053833, "global_step": 551122, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0626649856567383, "global_step": 551123, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9537266492843628, "global_step": 551124, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9738829135894775, "global_step": 551125, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0491106510162354, "global_step": 551126, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0366461277008057, "global_step": 551127, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9909107685089111, "global_step": 551128, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0458362102508545, "global_step": 551129, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.035384178161621, "global_step": 551130, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.006227731704712, "global_step": 551131, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0341522693634033, "global_step": 551132, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0121076107025146, "global_step": 551133, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9943161010742188, "global_step": 551134, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0069291591644287, "global_step": 551135, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.047086477279663, "global_step": 551136, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.076822280883789, "global_step": 551137, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.02834415435791, "global_step": 551138, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0111608505249023, "global_step": 551139, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0202581882476807, "global_step": 551140, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0120272636413574, "global_step": 551141, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1205761432647705, "global_step": 551142, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.011857748031616, "global_step": 551143, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.043581247329712, "global_step": 551144, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0113143920898438, "global_step": 551145, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0334854125976562, "global_step": 551146, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.029193878173828, "global_step": 551147, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0077409744262695, "global_step": 551148, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.051950454711914, "global_step": 551149, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0735199451446533, "global_step": 551150, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9640792608261108, "global_step": 551151, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.006481170654297, "global_step": 551152, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9818512201309204, "global_step": 551153, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.032076835632324, "global_step": 551154, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.038019895553589, "global_step": 551155, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9667985439300537, "global_step": 551156, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9852794408798218, "global_step": 551157, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0059878826141357, "global_step": 551158, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0089850425720215, "global_step": 551159, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9609602689743042, "global_step": 551160, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9829565286636353, "global_step": 551161, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0052554607391357, "global_step": 551162, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.03849196434021, "global_step": 551163, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0879721641540527, "global_step": 551164, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0158944129943848, "global_step": 551165, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.073047161102295, "global_step": 551166, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9493918418884277, "global_step": 551167, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.034628391265869, "global_step": 551168, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0872740745544434, "global_step": 551169, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1083321571350098, "global_step": 551170, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.994820237159729, "global_step": 551171, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9517613649368286, "global_step": 551172, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0174741744995117, "global_step": 551173, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9976013898849487, "global_step": 551174, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.076345920562744, "global_step": 551175, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9832000732421875, "global_step": 551176, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.999454379081726, "global_step": 551177, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.001366138458252, "global_step": 551178, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0575473308563232, "global_step": 551179, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0904293060302734, "global_step": 551180, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9908586740493774, "global_step": 551181, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0222933292388916, "global_step": 551182, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9847254753112793, "global_step": 551183, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.973386526107788, "global_step": 551184, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1291754245758057, "global_step": 551185, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.051054000854492, "global_step": 551186, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1346065998077393, "global_step": 551187, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.016493320465088, "global_step": 551188, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.00307559967041, "global_step": 551189, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0124611854553223, "global_step": 551190, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.038057804107666, "global_step": 551191, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.048398017883301, "global_step": 551192, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.092984437942505, "global_step": 551193, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0613508224487305, "global_step": 551194, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9941080808639526, "global_step": 551195, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1211678981781006, "global_step": 551196, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0194976329803467, "global_step": 551197, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.05488920211792, "global_step": 551198, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1037330627441406, "global_step": 551199, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0212438106536865, "global_step": 551200, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9481172561645508, "global_step": 551201, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9569412469863892, "global_step": 551202, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.05214786529541, "global_step": 551203, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.133208751678467, "global_step": 551204, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9409573078155518, "global_step": 551205, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9882357120513916, "global_step": 551206, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.046387195587158, "global_step": 551207, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0469799041748047, "global_step": 551208, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0412228107452393, "global_step": 551209, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1259732246398926, "global_step": 551210, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.017552137374878, "global_step": 551211, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.061248540878296, "global_step": 551212, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.961670160293579, "global_step": 551213, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0724191665649414, "global_step": 551214, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9541053771972656, "global_step": 551215, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.064112424850464, "global_step": 551216, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.019839286804199, "global_step": 551217, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.984021782875061, "global_step": 551218, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.042959451675415, "global_step": 551219, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1259067058563232, "global_step": 551220, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0402073860168457, "global_step": 551221, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.946579933166504, "global_step": 551222, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9472882747650146, "global_step": 551223, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.077425718307495, "global_step": 551224, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9870905876159668, "global_step": 551225, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0174076557159424, "global_step": 551226, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1163175106048584, "global_step": 551227, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.096776008605957, "global_step": 551228, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9965059757232666, "global_step": 551229, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.060492753982544, "global_step": 551230, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0401055812835693, "global_step": 551231, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9793325662612915, "global_step": 551232, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0588538646698, "global_step": 551233, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.099287509918213, "global_step": 551234, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9781352281570435, "global_step": 551235, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0524792671203613, "global_step": 551236, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0224449634552, "global_step": 551237, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0816972255706787, "global_step": 551238, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0229315757751465, "global_step": 551239, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0595316886901855, "global_step": 551240, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1575851440429688, "global_step": 551241, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.148364305496216, "global_step": 551242, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0345585346221924, "global_step": 551243, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0479936599731445, "global_step": 551244, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9845534563064575, "global_step": 551245, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0723533630371094, "global_step": 551246, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0191211700439453, "global_step": 551247, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9789708852767944, "global_step": 551248, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0823845863342285, "global_step": 551249, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9910237789154053, "global_step": 551250, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1180918216705322, "global_step": 551251, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0368454456329346, "global_step": 551252, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0294177532196045, "global_step": 551253, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.022845506668091, "global_step": 551254, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1120259761810303, "global_step": 551255, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0745983123779297, "global_step": 551256, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.098602771759033, "global_step": 551257, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0631377696990967, "global_step": 551258, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0168957710266113, "global_step": 551259, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.157396078109741, "global_step": 551260, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0252127647399902, "global_step": 551261, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.009425401687622, "global_step": 551262, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.042128086090088, "global_step": 551263, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.038149833679199, "global_step": 551264, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.058479070663452, "global_step": 551265, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0089569091796875, "global_step": 551266, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0743982791900635, "global_step": 551267, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0462684631347656, "global_step": 551268, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0173189640045166, "global_step": 551269, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.910778284072876, "global_step": 551270, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.045264720916748, "global_step": 551271, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9830697774887085, "global_step": 551272, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0523133277893066, "global_step": 551273, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1577670574188232, "global_step": 551274, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0118889808654785, "global_step": 551275, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.12606143951416, "global_step": 551276, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0387377738952637, "global_step": 551277, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9870266914367676, "global_step": 551278, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.068450927734375, "global_step": 551279, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9737485647201538, "global_step": 551280, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0160176753997803, "global_step": 551281, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1065075397491455, "global_step": 551282, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9987796545028687, "global_step": 551283, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9855092763900757, "global_step": 551284, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0477421283721924, "global_step": 551285, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.076538562774658, "global_step": 551286, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0358035564422607, "global_step": 551287, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.984697699546814, "global_step": 551288, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.003445625305176, "global_step": 551289, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9642627239227295, "global_step": 551290, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9944634437561035, "global_step": 551291, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1109278202056885, "global_step": 551292, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9551512002944946, "global_step": 551293, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0003604888916016, "global_step": 551294, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.102932929992676, "global_step": 551295, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.001478672027588, "global_step": 551296, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9526046514511108, "global_step": 551297, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0144050121307373, "global_step": 551298, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0456631183624268, "global_step": 551299, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1155130863189697, "global_step": 551300, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0014166831970215, "global_step": 551301, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9664376974105835, "global_step": 551302, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0643203258514404, "global_step": 551303, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.019845724105835, "global_step": 551304, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.078274965286255, "global_step": 551305, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.021413564682007, "global_step": 551306, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0387556552886963, "global_step": 551307, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.931326985359192, "global_step": 551308, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.994054913520813, "global_step": 551309, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.014007568359375, "global_step": 551310, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9794784784317017, "global_step": 551311, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9871522188186646, "global_step": 551312, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.138418436050415, "global_step": 551313, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.065021276473999, "global_step": 551314, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.087083578109741, "global_step": 551315, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1502702236175537, "global_step": 551316, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9926517009735107, "global_step": 551317, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.045316696166992, "global_step": 551318, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0652997493743896, "global_step": 551319, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9351563453674316, "global_step": 551320, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9189209938049316, "global_step": 551321, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.011932134628296, "global_step": 551322, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.05191707611084, "global_step": 551323, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.122775077819824, "global_step": 551324, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0449888706207275, "global_step": 551325, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.983660340309143, "global_step": 551326, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0819056034088135, "global_step": 551327, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.068767547607422, "global_step": 551328, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9716945886611938, "global_step": 551329, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9407743215560913, "global_step": 551330, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0755717754364014, "global_step": 551331, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9771708250045776, "global_step": 551332, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0582938194274902, "global_step": 551333, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0270678997039795, "global_step": 551334, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.129899740219116, "global_step": 551335, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0590057373046875, "global_step": 551336, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.080533504486084, "global_step": 551337, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0655455589294434, "global_step": 551338, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0486721992492676, "global_step": 551339, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.019212007522583, "global_step": 551340, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.033967971801758, "global_step": 551341, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0652916431427, "global_step": 551342, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0717337131500244, "global_step": 551343, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.117102861404419, "global_step": 551344, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.029149293899536, "global_step": 551345, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.980154037475586, "global_step": 551346, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1288535594940186, "global_step": 551347, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0752367973327637, "global_step": 551348, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.046128749847412, "global_step": 551349, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.043043851852417, "global_step": 551350, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0649526119232178, "global_step": 551351, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0965240001678467, "global_step": 551352, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0506510734558105, "global_step": 551353, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.082944631576538, "global_step": 551354, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.072855234146118, "global_step": 551355, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0873773097991943, "global_step": 551356, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.08211612701416, "global_step": 551357, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0470054149627686, "global_step": 551358, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0125012397766113, "global_step": 551359, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0485048294067383, "global_step": 551360, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9561768770217896, "global_step": 551361, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.056210517883301, "global_step": 551362, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9539716243743896, "global_step": 551363, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9515777826309204, "global_step": 551364, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0546951293945312, "global_step": 551365, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9641348123550415, "global_step": 551366, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9666235446929932, "global_step": 551367, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.073249578475952, "global_step": 551368, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0527732372283936, "global_step": 551369, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0387203693389893, "global_step": 551370, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0401017665863037, "global_step": 551371, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.992424726486206, "global_step": 551372, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.029728412628174, "global_step": 551373, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.043771743774414, "global_step": 551374, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.999685525894165, "global_step": 551375, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1083641052246094, "global_step": 551376, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0237512588500977, "global_step": 551377, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0790657997131348, "global_step": 551378, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0244662761688232, "global_step": 551379, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9672353267669678, "global_step": 551380, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9705501794815063, "global_step": 551381, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9516549110412598, "global_step": 551382, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0866074562072754, "global_step": 551383, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9894530773162842, "global_step": 551384, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.038492202758789, "global_step": 551385, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9704619646072388, "global_step": 551386, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0864505767822266, "global_step": 551387, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0278117656707764, "global_step": 551388, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0947742462158203, "global_step": 551389, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9622535705566406, "global_step": 551390, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0302326679229736, "global_step": 551391, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.083228349685669, "global_step": 551392, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0901896953582764, "global_step": 551393, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9531173706054688, "global_step": 551394, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.070767641067505, "global_step": 551395, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0768866539001465, "global_step": 551396, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.015040874481201, "global_step": 551397, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.050347089767456, "global_step": 551398, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9666366577148438, "global_step": 551399, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0645713806152344, "global_step": 551400, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.981500506401062, "global_step": 551401, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9627203941345215, "global_step": 551402, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.903752326965332, "global_step": 551403, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0979247093200684, "global_step": 551404, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.089170455932617, "global_step": 551405, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0109429359436035, "global_step": 551406, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0225675106048584, "global_step": 551407, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0639195442199707, "global_step": 551408, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.024202823638916, "global_step": 551409, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9830386638641357, "global_step": 551410, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.009638547897339, "global_step": 551411, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.985122799873352, "global_step": 551412, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.042755365371704, "global_step": 551413, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0328361988067627, "global_step": 551414, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9810940027236938, "global_step": 551415, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9749242067337036, "global_step": 551416, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9820139408111572, "global_step": 551417, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0258119106292725, "global_step": 551418, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0678517818450928, "global_step": 551419, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0833094120025635, "global_step": 551420, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0715651512145996, "global_step": 551421, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0520694255828857, "global_step": 551422, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.99398672580719, "global_step": 551423, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.031177043914795, "global_step": 551424, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9816948175430298, "global_step": 551425, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.072500228881836, "global_step": 551426, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9943830966949463, "global_step": 551427, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.016244888305664, "global_step": 551428, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0262398719787598, "global_step": 551429, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0266356468200684, "global_step": 551430, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0607151985168457, "global_step": 551431, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.042764186859131, "global_step": 551432, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0866189002990723, "global_step": 551433, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0328123569488525, "global_step": 551434, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9765183925628662, "global_step": 551435, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9366035461425781, "global_step": 551436, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.052588701248169, "global_step": 551437, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1080996990203857, "global_step": 551438, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.06266188621521, "global_step": 551439, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.004206418991089, "global_step": 551440, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.001457929611206, "global_step": 551441, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0417771339416504, "global_step": 551442, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0194082260131836, "global_step": 551443, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.138657331466675, "global_step": 551444, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.037128448486328, "global_step": 551445, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.003791093826294, "global_step": 551446, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9975532293319702, "global_step": 551447, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9993304014205933, "global_step": 551448, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.088571071624756, "global_step": 551449, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0238068103790283, "global_step": 551450, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1419081687927246, "global_step": 551451, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0548408031463623, "global_step": 551452, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0822205543518066, "global_step": 551453, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0711700916290283, "global_step": 551454, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.947086215019226, "global_step": 551455, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.061852216720581, "global_step": 551456, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0029678344726562, "global_step": 551457, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9906264543533325, "global_step": 551458, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.966001033782959, "global_step": 551459, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9985475540161133, "global_step": 551460, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9883241653442383, "global_step": 551461, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.015385389328003, "global_step": 551462, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.100280523300171, "global_step": 551463, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.999025821685791, "global_step": 551464, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0865554809570312, "global_step": 551465, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0290687084198, "global_step": 551466, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9856171607971191, "global_step": 551467, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0560131072998047, "global_step": 551468, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.020965576171875, "global_step": 551469, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.007002830505371, "global_step": 551470, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0778074264526367, "global_step": 551471, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.1293563842773438, "global_step": 551472, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.019467830657959, "global_step": 551473, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.072070360183716, "global_step": 551474, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.012057304382324, "global_step": 551475, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0054595470428467, "global_step": 551476, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0244035720825195, "global_step": 551477, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.073866367340088, "global_step": 551478, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9980753660202026, "global_step": 551479, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.004589319229126, "global_step": 551480, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0069124698638916, "global_step": 551481, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0213773250579834, "global_step": 551482, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0005135536193848, "global_step": 551483, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.049548864364624, "global_step": 551484, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9939053058624268, "global_step": 551485, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0168793201446533, "global_step": 551486, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.076932668685913, "global_step": 551487, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0614380836486816, "global_step": 551488, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.037598133087158, "global_step": 551489, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0419981479644775, "global_step": 551490, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0747060775756836, "global_step": 551491, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0658836364746094, "global_step": 551492, "epoch": 918, "lr": 5e-05}
{"train_loss": 2.0303072929382324, "global_step": 551493, "epoch": 918, "lr": 5e-05}
{"train_loss": 1.9909495115280151, "global_step": 551494, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.030134439468384, "global_step": 551495, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9684772491455078, "global_step": 551496, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.973670244216919, "global_step": 551497, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.035813570022583, "global_step": 551498, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.015726089477539, "global_step": 551499, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0040018558502197, "global_step": 551500, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1009809970855713, "global_step": 551501, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9974696636199951, "global_step": 551502, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.980453610420227, "global_step": 551503, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0697906017303467, "global_step": 551504, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0131995677948, "global_step": 551505, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.051133155822754, "global_step": 551506, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0412473678588867, "global_step": 551507, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.001399517059326, "global_step": 551508, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.075993299484253, "global_step": 551509, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0188539028167725, "global_step": 551510, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9936745166778564, "global_step": 551511, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9290753602981567, "global_step": 551512, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.094109058380127, "global_step": 551513, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9646466970443726, "global_step": 551514, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0167388916015625, "global_step": 551515, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9595633745193481, "global_step": 551516, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.024303674697876, "global_step": 551517, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0507845878601074, "global_step": 551518, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0369925498962402, "global_step": 551519, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.01228666305542, "global_step": 551520, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.057872772216797, "global_step": 551521, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.061098337173462, "global_step": 551522, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9819045066833496, "global_step": 551523, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.080610990524292, "global_step": 551524, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0573391914367676, "global_step": 551525, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0405967235565186, "global_step": 551526, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0809457302093506, "global_step": 551527, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9923874139785767, "global_step": 551528, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9801697731018066, "global_step": 551529, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9966517686843872, "global_step": 551530, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9721637964248657, "global_step": 551531, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.07717227935791, "global_step": 551532, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.079172134399414, "global_step": 551533, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.066459894180298, "global_step": 551534, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.99906587600708, "global_step": 551535, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0963149070739746, "global_step": 551536, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9664390087127686, "global_step": 551537, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0354883670806885, "global_step": 551538, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0025975704193115, "global_step": 551539, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.01170015335083, "global_step": 551540, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0161802768707275, "global_step": 551541, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9704793691635132, "global_step": 551542, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.069891929626465, "global_step": 551543, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9748475551605225, "global_step": 551544, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.029916524887085, "global_step": 551545, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0116686820983887, "global_step": 551546, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0096216201782227, "global_step": 551547, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.039705991744995, "global_step": 551548, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.023822784423828, "global_step": 551549, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9677587747573853, "global_step": 551550, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9935307502746582, "global_step": 551551, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.028609275817871, "global_step": 551552, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0373966693878174, "global_step": 551553, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.007181167602539, "global_step": 551554, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.029712438583374, "global_step": 551555, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0287325382232666, "global_step": 551556, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0303924083709717, "global_step": 551557, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9976308345794678, "global_step": 551558, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.018503427505493, "global_step": 551559, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0388245582580566, "global_step": 551560, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.053899049758911, "global_step": 551561, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9755998849868774, "global_step": 551562, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0126824378967285, "global_step": 551563, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.011521577835083, "global_step": 551564, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0725226402282715, "global_step": 551565, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9653735160827637, "global_step": 551566, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0800905227661133, "global_step": 551567, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9835591316223145, "global_step": 551568, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.007253885269165, "global_step": 551569, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0733978748321533, "global_step": 551570, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9211019277572632, "global_step": 551571, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9854353666305542, "global_step": 551572, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9311636686325073, "global_step": 551573, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9335365295410156, "global_step": 551574, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9566965103149414, "global_step": 551575, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0569190979003906, "global_step": 551576, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0438344478607178, "global_step": 551577, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.036747694015503, "global_step": 551578, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0533058643341064, "global_step": 551579, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.01814866065979, "global_step": 551580, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0338637828826904, "global_step": 551581, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0414063930511475, "global_step": 551582, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.065335512161255, "global_step": 551583, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0179903507232666, "global_step": 551584, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0659773349761963, "global_step": 551585, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9945237636566162, "global_step": 551586, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0491554737091064, "global_step": 551587, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9831268787384033, "global_step": 551588, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9797650575637817, "global_step": 551589, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.051769971847534, "global_step": 551590, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0424768924713135, "global_step": 551591, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9554243087768555, "global_step": 551592, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.01586651802063, "global_step": 551593, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.095423698425293, "global_step": 551594, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.080259323120117, "global_step": 551595, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0892128944396973, "global_step": 551596, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0643656253814697, "global_step": 551597, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.968629002571106, "global_step": 551598, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0778658390045166, "global_step": 551599, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.052987575531006, "global_step": 551600, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9490063190460205, "global_step": 551601, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.007079601287842, "global_step": 551602, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.065124750137329, "global_step": 551603, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0668208599090576, "global_step": 551604, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0508880615234375, "global_step": 551605, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0100040435791016, "global_step": 551606, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.951521873474121, "global_step": 551607, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.082488536834717, "global_step": 551608, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.139826536178589, "global_step": 551609, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9832955598831177, "global_step": 551610, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0519940853118896, "global_step": 551611, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0427300930023193, "global_step": 551612, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0835492610931396, "global_step": 551613, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.018778085708618, "global_step": 551614, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.05312442779541, "global_step": 551615, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.983058214187622, "global_step": 551616, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0245232582092285, "global_step": 551617, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9624971151351929, "global_step": 551618, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9968235492706299, "global_step": 551619, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9989807605743408, "global_step": 551620, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9778382778167725, "global_step": 551621, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0018856525421143, "global_step": 551622, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9730373620986938, "global_step": 551623, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0036404132843018, "global_step": 551624, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9727972745895386, "global_step": 551625, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.104588270187378, "global_step": 551626, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0163230895996094, "global_step": 551627, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0082483291625977, "global_step": 551628, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0033862590789795, "global_step": 551629, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0423009395599365, "global_step": 551630, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9580821990966797, "global_step": 551631, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0356943607330322, "global_step": 551632, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9911465644836426, "global_step": 551633, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.063411235809326, "global_step": 551634, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.964890956878662, "global_step": 551635, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0105326175689697, "global_step": 551636, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.035149335861206, "global_step": 551637, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9202213287353516, "global_step": 551638, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0888590812683105, "global_step": 551639, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1227188110351562, "global_step": 551640, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.060326099395752, "global_step": 551641, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0097858905792236, "global_step": 551642, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9987810850143433, "global_step": 551643, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.8975799083709717, "global_step": 551644, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9917763471603394, "global_step": 551645, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0391509532928467, "global_step": 551646, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0605380535125732, "global_step": 551647, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0402603149414062, "global_step": 551648, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9586408138275146, "global_step": 551649, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.045409917831421, "global_step": 551650, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0613417625427246, "global_step": 551651, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9959861040115356, "global_step": 551652, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0930936336517334, "global_step": 551653, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.986298680305481, "global_step": 551654, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.958999514579773, "global_step": 551655, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.046673536300659, "global_step": 551656, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.005307197570801, "global_step": 551657, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9881054162979126, "global_step": 551658, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0497922897338867, "global_step": 551659, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0201077461242676, "global_step": 551660, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0490686893463135, "global_step": 551661, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.067499876022339, "global_step": 551662, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9191564321517944, "global_step": 551663, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.068336248397827, "global_step": 551664, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0364768505096436, "global_step": 551665, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9830907583236694, "global_step": 551666, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0133917331695557, "global_step": 551667, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9442311525344849, "global_step": 551668, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9458298683166504, "global_step": 551669, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.929667353630066, "global_step": 551670, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.029794692993164, "global_step": 551671, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.056131601333618, "global_step": 551672, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.064164876937866, "global_step": 551673, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9787795543670654, "global_step": 551674, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.01611328125, "global_step": 551675, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.019388198852539, "global_step": 551676, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.062371015548706, "global_step": 551677, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.063671112060547, "global_step": 551678, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0644497871398926, "global_step": 551679, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.011735439300537, "global_step": 551680, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.080253839492798, "global_step": 551681, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0085244178771973, "global_step": 551682, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0242156982421875, "global_step": 551683, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9647780656814575, "global_step": 551684, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0464115142822266, "global_step": 551685, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9861665964126587, "global_step": 551686, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.077512264251709, "global_step": 551687, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.02382230758667, "global_step": 551688, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0096776485443115, "global_step": 551689, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0623016357421875, "global_step": 551690, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.039872646331787, "global_step": 551691, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.071408748626709, "global_step": 551692, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.985913872718811, "global_step": 551693, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0450453758239746, "global_step": 551694, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1198348999023438, "global_step": 551695, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9408165216445923, "global_step": 551696, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1179511547088623, "global_step": 551697, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0120186805725098, "global_step": 551698, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0541279315948486, "global_step": 551699, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0526599884033203, "global_step": 551700, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9538534879684448, "global_step": 551701, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0190937519073486, "global_step": 551702, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0528149604797363, "global_step": 551703, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.034574270248413, "global_step": 551704, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.074666976928711, "global_step": 551705, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9462496042251587, "global_step": 551706, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.053302764892578, "global_step": 551707, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0493998527526855, "global_step": 551708, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0253708362579346, "global_step": 551709, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0151877403259277, "global_step": 551710, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.028125762939453, "global_step": 551711, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9593093395233154, "global_step": 551712, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.997196912765503, "global_step": 551713, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.023583173751831, "global_step": 551714, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0064072608947754, "global_step": 551715, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9762641191482544, "global_step": 551716, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9816385507583618, "global_step": 551717, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9691115617752075, "global_step": 551718, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.048281192779541, "global_step": 551719, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0921452045440674, "global_step": 551720, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.058314085006714, "global_step": 551721, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0445125102996826, "global_step": 551722, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0259060859680176, "global_step": 551723, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0222184658050537, "global_step": 551724, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0301196575164795, "global_step": 551725, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.012965679168701, "global_step": 551726, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.089498996734619, "global_step": 551727, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0516672134399414, "global_step": 551728, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1092543601989746, "global_step": 551729, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.018049478530884, "global_step": 551730, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1434340476989746, "global_step": 551731, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0209484100341797, "global_step": 551732, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9879341125488281, "global_step": 551733, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9609944820404053, "global_step": 551734, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.977662205696106, "global_step": 551735, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.010533094406128, "global_step": 551736, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0940589904785156, "global_step": 551737, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.005680799484253, "global_step": 551738, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0520527362823486, "global_step": 551739, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9902883768081665, "global_step": 551740, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9389193058013916, "global_step": 551741, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0400633811950684, "global_step": 551742, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9824273586273193, "global_step": 551743, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.038989543914795, "global_step": 551744, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.083509683609009, "global_step": 551745, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.037830114364624, "global_step": 551746, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.035050392150879, "global_step": 551747, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9154118299484253, "global_step": 551748, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9709675312042236, "global_step": 551749, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9766404628753662, "global_step": 551750, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0022101402282715, "global_step": 551751, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0391228199005127, "global_step": 551752, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0078368186950684, "global_step": 551753, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0353052616119385, "global_step": 551754, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.075855016708374, "global_step": 551755, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9984045028686523, "global_step": 551756, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9920578002929688, "global_step": 551757, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9888622760772705, "global_step": 551758, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9706928730010986, "global_step": 551759, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0047121047973633, "global_step": 551760, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0305793285369873, "global_step": 551761, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.887803077697754, "global_step": 551762, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0165114402770996, "global_step": 551763, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.04461669921875, "global_step": 551764, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0406570434570312, "global_step": 551765, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0518181324005127, "global_step": 551766, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.027397871017456, "global_step": 551767, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9811309576034546, "global_step": 551768, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.082557439804077, "global_step": 551769, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9747728109359741, "global_step": 551770, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9441170692443848, "global_step": 551771, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0256006717681885, "global_step": 551772, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1130058765411377, "global_step": 551773, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9759091138839722, "global_step": 551774, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9946515560150146, "global_step": 551775, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.986202597618103, "global_step": 551776, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0238704681396484, "global_step": 551777, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9581358432769775, "global_step": 551778, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.982320785522461, "global_step": 551779, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9850746393203735, "global_step": 551780, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0249247550964355, "global_step": 551781, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0014426708221436, "global_step": 551782, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0574843883514404, "global_step": 551783, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.109220027923584, "global_step": 551784, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9693530797958374, "global_step": 551785, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0043766498565674, "global_step": 551786, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0513315200805664, "global_step": 551787, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9524435997009277, "global_step": 551788, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.014158248901367, "global_step": 551789, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9910589456558228, "global_step": 551790, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0348386764526367, "global_step": 551791, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0030198097229004, "global_step": 551792, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0462942123413086, "global_step": 551793, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0487825870513916, "global_step": 551794, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.025871515274048, "global_step": 551795, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0086607933044434, "global_step": 551796, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.8850951194763184, "global_step": 551797, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.008741855621338, "global_step": 551798, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1749377250671387, "global_step": 551799, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.025411605834961, "global_step": 551800, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1106362342834473, "global_step": 551801, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0594468116760254, "global_step": 551802, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1146621704101562, "global_step": 551803, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0369629859924316, "global_step": 551804, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1075031757354736, "global_step": 551805, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1170294284820557, "global_step": 551806, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9926694631576538, "global_step": 551807, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9676600694656372, "global_step": 551808, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9898394346237183, "global_step": 551809, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.119497060775757, "global_step": 551810, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.111292600631714, "global_step": 551811, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.028956174850464, "global_step": 551812, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0832979679107666, "global_step": 551813, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.051056146621704, "global_step": 551814, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0400614738464355, "global_step": 551815, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.12009334564209, "global_step": 551816, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9792888164520264, "global_step": 551817, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.059812307357788, "global_step": 551818, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0231266021728516, "global_step": 551819, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0412044525146484, "global_step": 551820, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.046224355697632, "global_step": 551821, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.046542167663574, "global_step": 551822, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.037043333053589, "global_step": 551823, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0653538703918457, "global_step": 551824, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0436198711395264, "global_step": 551825, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0119686126708984, "global_step": 551826, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.005459785461426, "global_step": 551827, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.008014440536499, "global_step": 551828, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9408243894577026, "global_step": 551829, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.016502857208252, "global_step": 551830, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0210909843444824, "global_step": 551831, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.100349187850952, "global_step": 551832, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.022620677947998, "global_step": 551833, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1082825660705566, "global_step": 551834, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.072232246398926, "global_step": 551835, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9916224479675293, "global_step": 551836, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9295070171356201, "global_step": 551837, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.908854603767395, "global_step": 551838, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9696571826934814, "global_step": 551839, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0899081230163574, "global_step": 551840, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.043215751647949, "global_step": 551841, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.030430793762207, "global_step": 551842, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.921905279159546, "global_step": 551843, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.949864149093628, "global_step": 551844, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.107851505279541, "global_step": 551845, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.033024787902832, "global_step": 551846, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.065969467163086, "global_step": 551847, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0748207569122314, "global_step": 551848, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0469093322753906, "global_step": 551849, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0653297901153564, "global_step": 551850, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.027057409286499, "global_step": 551851, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.043290138244629, "global_step": 551852, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0406131744384766, "global_step": 551853, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.048156261444092, "global_step": 551854, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.025965690612793, "global_step": 551855, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0711660385131836, "global_step": 551856, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0119822025299072, "global_step": 551857, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.078252077102661, "global_step": 551858, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9625935554504395, "global_step": 551859, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.038994789123535, "global_step": 551860, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.99185049533844, "global_step": 551861, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9435244798660278, "global_step": 551862, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.026002883911133, "global_step": 551863, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.042612075805664, "global_step": 551864, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.098583221435547, "global_step": 551865, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.010833501815796, "global_step": 551866, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0692028999328613, "global_step": 551867, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.038895845413208, "global_step": 551868, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9733883142471313, "global_step": 551869, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.072047472000122, "global_step": 551870, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9694242477416992, "global_step": 551871, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.025737762451172, "global_step": 551872, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.012752056121826, "global_step": 551873, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.036933183670044, "global_step": 551874, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.008406639099121, "global_step": 551875, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.047182083129883, "global_step": 551876, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.976745367050171, "global_step": 551877, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1033201217651367, "global_step": 551878, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0706722736358643, "global_step": 551879, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.031606674194336, "global_step": 551880, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9916640520095825, "global_step": 551881, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.037317991256714, "global_step": 551882, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9665133953094482, "global_step": 551883, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0705435276031494, "global_step": 551884, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0357089042663574, "global_step": 551885, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.056705951690674, "global_step": 551886, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9660606384277344, "global_step": 551887, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.931115984916687, "global_step": 551888, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.052922487258911, "global_step": 551889, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0357589721679688, "global_step": 551890, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9983258247375488, "global_step": 551891, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9752695560455322, "global_step": 551892, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9621012210845947, "global_step": 551893, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0658602714538574, "global_step": 551894, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.034262180328369, "global_step": 551895, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.062201738357544, "global_step": 551896, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1358959674835205, "global_step": 551897, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.071315050125122, "global_step": 551898, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0404303073883057, "global_step": 551899, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.043410539627075, "global_step": 551900, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.035187005996704, "global_step": 551901, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.012334108352661, "global_step": 551902, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0253827571868896, "global_step": 551903, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.073293685913086, "global_step": 551904, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9898179769515991, "global_step": 551905, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0187301635742188, "global_step": 551906, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0520880222320557, "global_step": 551907, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0304887294769287, "global_step": 551908, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9940344095230103, "global_step": 551909, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.01536226272583, "global_step": 551910, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.8892337083816528, "global_step": 551911, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.007863998413086, "global_step": 551912, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9670227766036987, "global_step": 551913, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0055766105651855, "global_step": 551914, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0918352603912354, "global_step": 551915, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9633264541625977, "global_step": 551916, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0574758052825928, "global_step": 551917, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1112332344055176, "global_step": 551918, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0570125579833984, "global_step": 551919, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0771234035491943, "global_step": 551920, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0041608810424805, "global_step": 551921, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9874976873397827, "global_step": 551922, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0678157806396484, "global_step": 551923, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0226197242736816, "global_step": 551924, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.049726963043213, "global_step": 551925, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9385740756988525, "global_step": 551926, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0263173580169678, "global_step": 551927, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0594820976257324, "global_step": 551928, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0506720542907715, "global_step": 551929, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0052597522735596, "global_step": 551930, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0573577880859375, "global_step": 551931, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9829953908920288, "global_step": 551932, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.976014256477356, "global_step": 551933, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.992595911026001, "global_step": 551934, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0020644664764404, "global_step": 551935, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.025291681289673, "global_step": 551936, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.029017448425293, "global_step": 551937, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.154039144515991, "global_step": 551938, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.062129020690918, "global_step": 551939, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.8973901271820068, "global_step": 551940, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9699666500091553, "global_step": 551941, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.108149766921997, "global_step": 551942, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.014775037765503, "global_step": 551943, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0124783515930176, "global_step": 551944, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.125232219696045, "global_step": 551945, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.966036081314087, "global_step": 551946, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0498523712158203, "global_step": 551947, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0648558139801025, "global_step": 551948, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9556009769439697, "global_step": 551949, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9472252130508423, "global_step": 551950, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.035400152206421, "global_step": 551951, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.087985038757324, "global_step": 551952, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0181150436401367, "global_step": 551953, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0011627674102783, "global_step": 551954, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0385823249816895, "global_step": 551955, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0305728912353516, "global_step": 551956, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0802412033081055, "global_step": 551957, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0463991165161133, "global_step": 551958, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0450069904327393, "global_step": 551959, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0647456645965576, "global_step": 551960, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9770013093948364, "global_step": 551961, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1110610961914062, "global_step": 551962, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0533158779144287, "global_step": 551963, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0085010528564453, "global_step": 551964, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0267505645751953, "global_step": 551965, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0570068359375, "global_step": 551966, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.177427291870117, "global_step": 551967, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0795257091522217, "global_step": 551968, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.059551954269409, "global_step": 551969, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.085275411605835, "global_step": 551970, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0260257720947266, "global_step": 551971, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0771775245666504, "global_step": 551972, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.085631847381592, "global_step": 551973, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.098520040512085, "global_step": 551974, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9872641563415527, "global_step": 551975, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.003913640975952, "global_step": 551976, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0753884315490723, "global_step": 551977, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0186686515808105, "global_step": 551978, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9778175354003906, "global_step": 551979, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0190608501434326, "global_step": 551980, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.04927134513855, "global_step": 551981, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1339666843414307, "global_step": 551982, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9151231050491333, "global_step": 551983, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0512101650238037, "global_step": 551984, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.064573287963867, "global_step": 551985, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.971166729927063, "global_step": 551986, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.001727342605591, "global_step": 551987, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.964583158493042, "global_step": 551988, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0561399459838867, "global_step": 551989, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.101935625076294, "global_step": 551990, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0622329711914062, "global_step": 551991, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9781404733657837, "global_step": 551992, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9878102540969849, "global_step": 551993, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0815956592559814, "global_step": 551994, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9915342330932617, "global_step": 551995, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0720372200012207, "global_step": 551996, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.073458194732666, "global_step": 551997, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9674506187438965, "global_step": 551998, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0626308917999268, "global_step": 551999, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0509345531463623, "global_step": 552000, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.04653000831604, "global_step": 552001, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.065490961074829, "global_step": 552002, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0703046321868896, "global_step": 552003, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0258216857910156, "global_step": 552004, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0695343017578125, "global_step": 552005, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1154122352600098, "global_step": 552006, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.061460018157959, "global_step": 552007, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9838887453079224, "global_step": 552008, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0154969692230225, "global_step": 552009, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0484352111816406, "global_step": 552010, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.080570936203003, "global_step": 552011, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0720136165618896, "global_step": 552012, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.036194086074829, "global_step": 552013, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9715917110443115, "global_step": 552014, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0576388835906982, "global_step": 552015, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.001797676086426, "global_step": 552016, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0002694129943848, "global_step": 552017, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.075474977493286, "global_step": 552018, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.049062967300415, "global_step": 552019, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9694291353225708, "global_step": 552020, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0422942638397217, "global_step": 552021, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9864192008972168, "global_step": 552022, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.991437554359436, "global_step": 552023, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.060276508331299, "global_step": 552024, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0261363983154297, "global_step": 552025, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0611495971679688, "global_step": 552026, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0561068058013916, "global_step": 552027, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.105628490447998, "global_step": 552028, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.987489938735962, "global_step": 552029, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.055187702178955, "global_step": 552030, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0307533740997314, "global_step": 552031, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.994657039642334, "global_step": 552032, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0501911640167236, "global_step": 552033, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0554890632629395, "global_step": 552034, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0587432384490967, "global_step": 552035, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.022477388381958, "global_step": 552036, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.055072546005249, "global_step": 552037, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0189576148986816, "global_step": 552038, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.046250581741333, "global_step": 552039, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9951640367507935, "global_step": 552040, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1059961318969727, "global_step": 552041, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.12911057472229, "global_step": 552042, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0089528560638428, "global_step": 552043, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.015728712081909, "global_step": 552044, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9722594022750854, "global_step": 552045, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9953936338424683, "global_step": 552046, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0034773349761963, "global_step": 552047, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.060649871826172, "global_step": 552048, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9854968786239624, "global_step": 552049, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0366039276123047, "global_step": 552050, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0844950675964355, "global_step": 552051, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.935933232307434, "global_step": 552052, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0520637035369873, "global_step": 552053, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0129997730255127, "global_step": 552054, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1320831775665283, "global_step": 552055, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1137335300445557, "global_step": 552056, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0263030529022217, "global_step": 552057, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0590484142303467, "global_step": 552058, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0152299404144287, "global_step": 552059, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.089282751083374, "global_step": 552060, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.00395131111145, "global_step": 552061, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0306687355041504, "global_step": 552062, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1224513053894043, "global_step": 552063, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0243756771087646, "global_step": 552064, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.144150733947754, "global_step": 552065, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.034158706665039, "global_step": 552066, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0014424324035645, "global_step": 552067, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0355730056762695, "global_step": 552068, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9813196659088135, "global_step": 552069, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1266472339630127, "global_step": 552070, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0364675521850586, "global_step": 552071, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0179152488708496, "global_step": 552072, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9970802068710327, "global_step": 552073, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.913204550743103, "global_step": 552074, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0673775672912598, "global_step": 552075, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0131173133850098, "global_step": 552076, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9979313611984253, "global_step": 552077, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.075813055038452, "global_step": 552078, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.054513931274414, "global_step": 552079, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0286290645599365, "global_step": 552080, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0340328216552734, "global_step": 552081, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9992283582687378, "global_step": 552082, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9667507410049438, "global_step": 552083, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0846188068389893, "global_step": 552084, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9387083053588867, "global_step": 552085, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0467371940612793, "global_step": 552086, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.05903697013855, "global_step": 552087, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.001549243927002, "global_step": 552088, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9686628580093384, "global_step": 552089, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.085106611251831, "global_step": 552090, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1079790592193604, "global_step": 552091, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.054594039916992, "global_step": 552092, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0764482021331787, "global_step": 552093, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.059175968170166, "global_step": 552094, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.974493145942688, "global_step": 552095, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0167665481567383, "global_step": 552096, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.037327766418457, "global_step": 552097, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.088205099105835, "global_step": 552098, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.008492946624756, "global_step": 552099, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.044269561767578, "global_step": 552100, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1163792610168457, "global_step": 552101, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0074193477630615, "global_step": 552102, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0854620933532715, "global_step": 552103, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.092546224594116, "global_step": 552104, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0983927249908447, "global_step": 552105, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0003066062927246, "global_step": 552106, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0196785926818848, "global_step": 552107, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.049623727798462, "global_step": 552108, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0595057010650635, "global_step": 552109, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9888544082641602, "global_step": 552110, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0080320835113525, "global_step": 552111, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.069702386856079, "global_step": 552112, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0042741298675537, "global_step": 552113, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.038156509399414, "global_step": 552114, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0480093955993652, "global_step": 552115, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0537357330322266, "global_step": 552116, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.151228904724121, "global_step": 552117, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0397486686706543, "global_step": 552118, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.051469087600708, "global_step": 552119, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1136860847473145, "global_step": 552120, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0066628456115723, "global_step": 552121, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0854876041412354, "global_step": 552122, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.974090814590454, "global_step": 552123, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9870036840438843, "global_step": 552124, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0595877170562744, "global_step": 552125, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9701147079467773, "global_step": 552126, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.145158052444458, "global_step": 552127, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0862221717834473, "global_step": 552128, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0577728748321533, "global_step": 552129, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9392473697662354, "global_step": 552130, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9874614477157593, "global_step": 552131, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.007960081100464, "global_step": 552132, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0779590606689453, "global_step": 552133, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0237410068511963, "global_step": 552134, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.033808946609497, "global_step": 552135, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.036546468734741, "global_step": 552136, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.061211585998535, "global_step": 552137, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0811171531677246, "global_step": 552138, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9971433877944946, "global_step": 552139, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0751469135284424, "global_step": 552140, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.040034770965576, "global_step": 552141, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.021782398223877, "global_step": 552142, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.030836582183838, "global_step": 552143, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.026756763458252, "global_step": 552144, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.025658130645752, "global_step": 552145, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0369884967803955, "global_step": 552146, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0491344928741455, "global_step": 552147, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0591814517974854, "global_step": 552148, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0745625495910645, "global_step": 552149, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.034702777862549, "global_step": 552150, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9803379774093628, "global_step": 552151, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0662121772766113, "global_step": 552152, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9936225414276123, "global_step": 552153, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.064817428588867, "global_step": 552154, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9780278205871582, "global_step": 552155, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0025248527526855, "global_step": 552156, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9689127206802368, "global_step": 552157, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.085951805114746, "global_step": 552158, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.974420189857483, "global_step": 552159, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9957828521728516, "global_step": 552160, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.050076484680176, "global_step": 552161, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.106905698776245, "global_step": 552162, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0128087997436523, "global_step": 552163, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0922434329986572, "global_step": 552164, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0592663288116455, "global_step": 552165, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.093594551086426, "global_step": 552166, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9744036197662354, "global_step": 552167, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.040025234222412, "global_step": 552168, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.000023365020752, "global_step": 552169, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0475988388061523, "global_step": 552170, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.030951976776123, "global_step": 552171, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0067315101623535, "global_step": 552172, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0541296005249023, "global_step": 552173, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.938338041305542, "global_step": 552174, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0581817626953125, "global_step": 552175, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.03006649017334, "global_step": 552176, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0105385780334473, "global_step": 552177, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.018657922744751, "global_step": 552178, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9788142442703247, "global_step": 552179, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0990264415740967, "global_step": 552180, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0567541122436523, "global_step": 552181, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1141421794891357, "global_step": 552182, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0238449573516846, "global_step": 552183, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0641286373138428, "global_step": 552184, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.017435312271118, "global_step": 552185, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.990399718284607, "global_step": 552186, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.083615779876709, "global_step": 552187, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1316115856170654, "global_step": 552188, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9944202899932861, "global_step": 552189, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.089060068130493, "global_step": 552190, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0026845932006836, "global_step": 552191, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0577805042266846, "global_step": 552192, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0026299953460693, "global_step": 552193, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9573508501052856, "global_step": 552194, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9265642166137695, "global_step": 552195, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.095881700515747, "global_step": 552196, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9607150554656982, "global_step": 552197, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0459048748016357, "global_step": 552198, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.060326337814331, "global_step": 552199, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0487635135650635, "global_step": 552200, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0610604286193848, "global_step": 552201, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0640904903411865, "global_step": 552202, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0295090675354004, "global_step": 552203, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9615504741668701, "global_step": 552204, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9616540670394897, "global_step": 552205, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.065927028656006, "global_step": 552206, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0738346576690674, "global_step": 552207, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.120814800262451, "global_step": 552208, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0408685207366943, "global_step": 552209, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0884206295013428, "global_step": 552210, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.03830885887146, "global_step": 552211, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.029115915298462, "global_step": 552212, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0004639625549316, "global_step": 552213, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.032534599304199, "global_step": 552214, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9024901390075684, "global_step": 552215, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9863990545272827, "global_step": 552216, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0884687900543213, "global_step": 552217, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0230767726898193, "global_step": 552218, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.8820607662200928, "global_step": 552219, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.074535608291626, "global_step": 552220, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9578492641448975, "global_step": 552221, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.994745135307312, "global_step": 552222, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1122875213623047, "global_step": 552223, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0104329586029053, "global_step": 552224, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0485243797302246, "global_step": 552225, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9333109855651855, "global_step": 552226, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9692192077636719, "global_step": 552227, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0188920497894287, "global_step": 552228, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.09968638420105, "global_step": 552229, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9840564727783203, "global_step": 552230, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.071392059326172, "global_step": 552231, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.081249237060547, "global_step": 552232, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.992104411125183, "global_step": 552233, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0167503356933594, "global_step": 552234, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.077873468399048, "global_step": 552235, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0706987380981445, "global_step": 552236, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.020570993423462, "global_step": 552237, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9592108726501465, "global_step": 552238, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0198872089385986, "global_step": 552239, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.000498056411743, "global_step": 552240, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0938172340393066, "global_step": 552241, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.003365993499756, "global_step": 552242, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.034454345703125, "global_step": 552243, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0107266902923584, "global_step": 552244, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.081580400466919, "global_step": 552245, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9880971908569336, "global_step": 552246, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.076800584793091, "global_step": 552247, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9978890419006348, "global_step": 552248, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9628846645355225, "global_step": 552249, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.082592248916626, "global_step": 552250, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0021276473999023, "global_step": 552251, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.039665937423706, "global_step": 552252, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.972713828086853, "global_step": 552253, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0675508975982666, "global_step": 552254, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.043255567550659, "global_step": 552255, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.042492389678955, "global_step": 552256, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9661802053451538, "global_step": 552257, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0799622535705566, "global_step": 552258, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9787659645080566, "global_step": 552259, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9992144107818604, "global_step": 552260, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1058006286621094, "global_step": 552261, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.072660207748413, "global_step": 552262, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1301374435424805, "global_step": 552263, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.007082462310791, "global_step": 552264, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.034888982772827, "global_step": 552265, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0454516410827637, "global_step": 552266, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.071108341217041, "global_step": 552267, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1202564239501953, "global_step": 552268, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9632596969604492, "global_step": 552269, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.038853168487549, "global_step": 552270, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9707849025726318, "global_step": 552271, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.027928113937378, "global_step": 552272, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.031716823577881, "global_step": 552273, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.050220489501953, "global_step": 552274, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.028937339782715, "global_step": 552275, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.03664231300354, "global_step": 552276, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0064454078674316, "global_step": 552277, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0323476791381836, "global_step": 552278, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.01139235496521, "global_step": 552279, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.036938428878784, "global_step": 552280, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.00925874710083, "global_step": 552281, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.020995855331421, "global_step": 552282, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0205464363098145, "global_step": 552283, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0543112754821777, "global_step": 552284, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9889400005340576, "global_step": 552285, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0663299560546875, "global_step": 552286, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.061042547225952, "global_step": 552287, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.028350353240967, "global_step": 552288, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9671748876571655, "global_step": 552289, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.03279972076416, "global_step": 552290, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0040838718414307, "global_step": 552291, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.983839988708496, "global_step": 552292, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0178096294403076, "global_step": 552293, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.063131809234619, "global_step": 552294, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.089001417160034, "global_step": 552295, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9678349494934082, "global_step": 552296, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.031869888305664, "global_step": 552297, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.036726713180542, "global_step": 552298, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0272586345672607, "global_step": 552299, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0044329166412354, "global_step": 552300, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.020387887954712, "global_step": 552301, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0824191570281982, "global_step": 552302, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9414788484573364, "global_step": 552303, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0907702445983887, "global_step": 552304, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0981271266937256, "global_step": 552305, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.071719169616699, "global_step": 552306, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0493335723876953, "global_step": 552307, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.126335620880127, "global_step": 552308, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.969953179359436, "global_step": 552309, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9769545793533325, "global_step": 552310, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.03499436378479, "global_step": 552311, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9613168239593506, "global_step": 552312, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9707248210906982, "global_step": 552313, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.028934955596924, "global_step": 552314, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0221645832061768, "global_step": 552315, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0702903270721436, "global_step": 552316, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0467216968536377, "global_step": 552317, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0887067317962646, "global_step": 552318, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.073861837387085, "global_step": 552319, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0654029846191406, "global_step": 552320, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1478829383850098, "global_step": 552321, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.025650978088379, "global_step": 552322, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1039481163024902, "global_step": 552323, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0688886642456055, "global_step": 552324, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.004007339477539, "global_step": 552325, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.007244348526001, "global_step": 552326, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.970820665359497, "global_step": 552327, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.030318260192871, "global_step": 552328, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.055850028991699, "global_step": 552329, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9703258275985718, "global_step": 552330, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0007870197296143, "global_step": 552331, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0702450275421143, "global_step": 552332, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9644125699996948, "global_step": 552333, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.038062810897827, "global_step": 552334, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.032198190689087, "global_step": 552335, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.023280382156372, "global_step": 552336, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0154078006744385, "global_step": 552337, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9334659576416016, "global_step": 552338, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9959145784378052, "global_step": 552339, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.028841733932495, "global_step": 552340, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0402331352233887, "global_step": 552341, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0122485160827637, "global_step": 552342, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.066089153289795, "global_step": 552343, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0213963985443115, "global_step": 552344, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.024855613708496, "global_step": 552345, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9659780263900757, "global_step": 552346, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9647072553634644, "global_step": 552347, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0986075401306152, "global_step": 552348, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0967135429382324, "global_step": 552349, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0600390434265137, "global_step": 552350, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0059924125671387, "global_step": 552351, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9878376722335815, "global_step": 552352, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0054919719696045, "global_step": 552353, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0006887912750244, "global_step": 552354, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0451884269714355, "global_step": 552355, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9837623834609985, "global_step": 552356, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1197011470794678, "global_step": 552357, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0794739723205566, "global_step": 552358, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.007584571838379, "global_step": 552359, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.084444522857666, "global_step": 552360, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9499456882476807, "global_step": 552361, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.045182228088379, "global_step": 552362, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0786185264587402, "global_step": 552363, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0834014415740967, "global_step": 552364, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.066762924194336, "global_step": 552365, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.022986888885498, "global_step": 552366, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9423115253448486, "global_step": 552367, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9826691150665283, "global_step": 552368, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.078073024749756, "global_step": 552369, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9677625894546509, "global_step": 552370, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.076554536819458, "global_step": 552371, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0224437713623047, "global_step": 552372, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.002615451812744, "global_step": 552373, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9613747596740723, "global_step": 552374, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0418591499328613, "global_step": 552375, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1066884994506836, "global_step": 552376, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.032839298248291, "global_step": 552377, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.090928316116333, "global_step": 552378, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9956347942352295, "global_step": 552379, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.022503137588501, "global_step": 552380, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0299365520477295, "global_step": 552381, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.092327356338501, "global_step": 552382, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.058234214782715, "global_step": 552383, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.006063222885132, "global_step": 552384, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0863094329833984, "global_step": 552385, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.042633533477783, "global_step": 552386, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.048029899597168, "global_step": 552387, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9326475858688354, "global_step": 552388, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.924115538597107, "global_step": 552389, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1106367111206055, "global_step": 552390, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.061598539352417, "global_step": 552391, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0326623916625977, "global_step": 552392, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9539222717285156, "global_step": 552393, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9974716901779175, "global_step": 552394, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.076200008392334, "global_step": 552395, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0300779342651367, "global_step": 552396, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0537312030792236, "global_step": 552397, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0261824131011963, "global_step": 552398, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0593113899230957, "global_step": 552399, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.09660267829895, "global_step": 552400, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0595386028289795, "global_step": 552401, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0035812854766846, "global_step": 552402, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9865833520889282, "global_step": 552403, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0389652252197266, "global_step": 552404, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1068363189697266, "global_step": 552405, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0207979679107666, "global_step": 552406, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.952500820159912, "global_step": 552407, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.982591986656189, "global_step": 552408, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0643563270568848, "global_step": 552409, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9965370893478394, "global_step": 552410, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.081308603286743, "global_step": 552411, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.089568853378296, "global_step": 552412, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0273842811584473, "global_step": 552413, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.030693292617798, "global_step": 552414, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.004169464111328, "global_step": 552415, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.05789852142334, "global_step": 552416, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0481061935424805, "global_step": 552417, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.030775308609009, "global_step": 552418, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9579768180847168, "global_step": 552419, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9481178522109985, "global_step": 552420, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0267436504364014, "global_step": 552421, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.039454936981201, "global_step": 552422, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9556806087493896, "global_step": 552423, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9741438627243042, "global_step": 552424, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0199012756347656, "global_step": 552425, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.036998987197876, "global_step": 552426, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0417168140411377, "global_step": 552427, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0835039615631104, "global_step": 552428, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0407822132110596, "global_step": 552429, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0271289348602295, "global_step": 552430, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9705342054367065, "global_step": 552431, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.128866672515869, "global_step": 552432, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0201117992401123, "global_step": 552433, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.064800500869751, "global_step": 552434, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.108578681945801, "global_step": 552435, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.072977304458618, "global_step": 552436, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0049033164978027, "global_step": 552437, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.089038610458374, "global_step": 552438, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.080575704574585, "global_step": 552439, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.050560235977173, "global_step": 552440, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0187482833862305, "global_step": 552441, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.085867166519165, "global_step": 552442, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9621024131774902, "global_step": 552443, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9977666139602661, "global_step": 552444, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9033693075180054, "global_step": 552445, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9847999811172485, "global_step": 552446, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.022430658340454, "global_step": 552447, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.063664436340332, "global_step": 552448, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.1316094398498535, "global_step": 552449, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9344364404678345, "global_step": 552450, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.033431053161621, "global_step": 552451, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.043471336364746, "global_step": 552452, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0144853591918945, "global_step": 552453, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.03432559967041, "global_step": 552454, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9852838516235352, "global_step": 552455, "epoch": 919, "lr": 5e-05}
{"train_loss": 1.9887583255767822, "global_step": 552456, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0978074073791504, "global_step": 552457, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.017313241958618, "global_step": 552458, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0878286361694336, "global_step": 552459, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0590062141418457, "global_step": 552460, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0663580894470215, "global_step": 552461, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.0290329456329346, "global_step": 552462, "epoch": 919, "lr": 5e-05}
{"train_loss": 2.024163246154785, "global_step": 552463, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9405847787857056, "global_step": 552464, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.004657745361328, "global_step": 552465, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9772815704345703, "global_step": 552466, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0049989223480225, "global_step": 552467, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9798238277435303, "global_step": 552468, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0949959754943848, "global_step": 552469, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.097306489944458, "global_step": 552470, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0751051902770996, "global_step": 552471, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0250132083892822, "global_step": 552472, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0173377990722656, "global_step": 552473, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.98492431640625, "global_step": 552474, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0209121704101562, "global_step": 552475, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.067502975463867, "global_step": 552476, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0646884441375732, "global_step": 552477, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9135715961456299, "global_step": 552478, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9146355390548706, "global_step": 552479, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1147379875183105, "global_step": 552480, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9760838747024536, "global_step": 552481, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.023738384246826, "global_step": 552482, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9648785591125488, "global_step": 552483, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.888679027557373, "global_step": 552484, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0578420162200928, "global_step": 552485, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0159497261047363, "global_step": 552486, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.993758201599121, "global_step": 552487, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9945372343063354, "global_step": 552488, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1008760929107666, "global_step": 552489, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0389721393585205, "global_step": 552490, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.026649236679077, "global_step": 552491, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0343525409698486, "global_step": 552492, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0629687309265137, "global_step": 552493, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9685888290405273, "global_step": 552494, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9349865913391113, "global_step": 552495, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9417316913604736, "global_step": 552496, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.029829263687134, "global_step": 552497, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0112171173095703, "global_step": 552498, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.087134599685669, "global_step": 552499, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0394651889801025, "global_step": 552500, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0455660820007324, "global_step": 552501, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9986441135406494, "global_step": 552502, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0012006759643555, "global_step": 552503, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.8979988098144531, "global_step": 552504, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9304884672164917, "global_step": 552505, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0480477809906006, "global_step": 552506, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.107328176498413, "global_step": 552507, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.978258490562439, "global_step": 552508, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0609445571899414, "global_step": 552509, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0720088481903076, "global_step": 552510, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0251564979553223, "global_step": 552511, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.025257110595703, "global_step": 552512, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9991389513015747, "global_step": 552513, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0418334007263184, "global_step": 552514, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.092815637588501, "global_step": 552515, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.001424789428711, "global_step": 552516, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9769006967544556, "global_step": 552517, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.022465229034424, "global_step": 552518, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0153913497924805, "global_step": 552519, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.050086736679077, "global_step": 552520, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.070897340774536, "global_step": 552521, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0522615909576416, "global_step": 552522, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0401296615600586, "global_step": 552523, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0795974731445312, "global_step": 552524, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0002918243408203, "global_step": 552525, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9453277587890625, "global_step": 552526, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9505528211593628, "global_step": 552527, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9178078174591064, "global_step": 552528, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0532853603363037, "global_step": 552529, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9930464029312134, "global_step": 552530, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.031297206878662, "global_step": 552531, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0664355754852295, "global_step": 552532, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9842753410339355, "global_step": 552533, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.011925220489502, "global_step": 552534, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0592219829559326, "global_step": 552535, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.025972843170166, "global_step": 552536, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0360324382781982, "global_step": 552537, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0090243816375732, "global_step": 552538, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9528416395187378, "global_step": 552539, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9983155727386475, "global_step": 552540, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9790898561477661, "global_step": 552541, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.067729949951172, "global_step": 552542, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.982019066810608, "global_step": 552543, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9837710857391357, "global_step": 552544, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1275792121887207, "global_step": 552545, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.994882345199585, "global_step": 552546, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0219507217407227, "global_step": 552547, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0648956298828125, "global_step": 552548, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0520830154418945, "global_step": 552549, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.008533239364624, "global_step": 552550, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0854685306549072, "global_step": 552551, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.091860055923462, "global_step": 552552, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9725415706634521, "global_step": 552553, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9735491275787354, "global_step": 552554, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0357792377471924, "global_step": 552555, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.028080940246582, "global_step": 552556, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.015359401702881, "global_step": 552557, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0135202407836914, "global_step": 552558, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0479912757873535, "global_step": 552559, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9574381113052368, "global_step": 552560, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9732966423034668, "global_step": 552561, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0615785121917725, "global_step": 552562, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.06093168258667, "global_step": 552563, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.083611488342285, "global_step": 552564, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.982985496520996, "global_step": 552565, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0916988849639893, "global_step": 552566, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.968297004699707, "global_step": 552567, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0024588108062744, "global_step": 552568, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.008366107940674, "global_step": 552569, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.974389672279358, "global_step": 552570, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9881718158721924, "global_step": 552571, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9794656038284302, "global_step": 552572, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.040661334991455, "global_step": 552573, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.004006862640381, "global_step": 552574, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0768816471099854, "global_step": 552575, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9576464891433716, "global_step": 552576, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0344488620758057, "global_step": 552577, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0364389419555664, "global_step": 552578, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.102595329284668, "global_step": 552579, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0256242752075195, "global_step": 552580, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0366005897521973, "global_step": 552581, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1346397399902344, "global_step": 552582, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.018073558807373, "global_step": 552583, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0711965560913086, "global_step": 552584, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0840859413146973, "global_step": 552585, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9359314441680908, "global_step": 552586, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9515891075134277, "global_step": 552587, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.012937545776367, "global_step": 552588, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9709771871566772, "global_step": 552589, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9819793701171875, "global_step": 552590, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0813517570495605, "global_step": 552591, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9930871725082397, "global_step": 552592, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.943188190460205, "global_step": 552593, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.017028331756592, "global_step": 552594, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.100508451461792, "global_step": 552595, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0652477741241455, "global_step": 552596, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9897751808166504, "global_step": 552597, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9849212169647217, "global_step": 552598, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0060925483703613, "global_step": 552599, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0317459106445312, "global_step": 552600, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.086228132247925, "global_step": 552601, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9869543313980103, "global_step": 552602, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.106326103210449, "global_step": 552603, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9754467010498047, "global_step": 552604, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.023019790649414, "global_step": 552605, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9706168174743652, "global_step": 552606, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.029623508453369, "global_step": 552607, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9191186428070068, "global_step": 552608, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0629310607910156, "global_step": 552609, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.06612229347229, "global_step": 552610, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.049363136291504, "global_step": 552611, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0015761852264404, "global_step": 552612, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0205721855163574, "global_step": 552613, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9671146869659424, "global_step": 552614, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.062765121459961, "global_step": 552615, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.017826795578003, "global_step": 552616, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9392554759979248, "global_step": 552617, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.047226667404175, "global_step": 552618, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1052916049957275, "global_step": 552619, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0807712078094482, "global_step": 552620, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.961187720298767, "global_step": 552621, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.952470064163208, "global_step": 552622, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9932568073272705, "global_step": 552623, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9619743824005127, "global_step": 552624, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.032484292984009, "global_step": 552625, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9979712963104248, "global_step": 552626, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0284862518310547, "global_step": 552627, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0160634517669678, "global_step": 552628, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9941531419754028, "global_step": 552629, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.033458948135376, "global_step": 552630, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1027040481567383, "global_step": 552631, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0367541313171387, "global_step": 552632, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.069518566131592, "global_step": 552633, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9671227931976318, "global_step": 552634, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0004258155822754, "global_step": 552635, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.057518482208252, "global_step": 552636, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0270538330078125, "global_step": 552637, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0241432189941406, "global_step": 552638, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.132657766342163, "global_step": 552639, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0386579036712646, "global_step": 552640, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9474656581878662, "global_step": 552641, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0740976333618164, "global_step": 552642, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0034596920013428, "global_step": 552643, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.021575927734375, "global_step": 552644, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9877920150756836, "global_step": 552645, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0316874980926514, "global_step": 552646, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0325939655303955, "global_step": 552647, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0662708282470703, "global_step": 552648, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.040470600128174, "global_step": 552649, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9925835132598877, "global_step": 552650, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0335652828216553, "global_step": 552651, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.028648853302002, "global_step": 552652, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.982254981994629, "global_step": 552653, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0249311923980713, "global_step": 552654, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9985004663467407, "global_step": 552655, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.048149585723877, "global_step": 552656, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.988136887550354, "global_step": 552657, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.108149766921997, "global_step": 552658, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9629064798355103, "global_step": 552659, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.042841911315918, "global_step": 552660, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.087222099304199, "global_step": 552661, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9650659561157227, "global_step": 552662, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9356648921966553, "global_step": 552663, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0037944316864014, "global_step": 552664, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9965571165084839, "global_step": 552665, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9751365184783936, "global_step": 552666, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0155391693115234, "global_step": 552667, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9374651908874512, "global_step": 552668, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.061342477798462, "global_step": 552669, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0268373489379883, "global_step": 552670, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.064649820327759, "global_step": 552671, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9835652112960815, "global_step": 552672, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.028730630874634, "global_step": 552673, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.09405255317688, "global_step": 552674, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.017651081085205, "global_step": 552675, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0757381916046143, "global_step": 552676, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0464556217193604, "global_step": 552677, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9981529712677002, "global_step": 552678, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9863266944885254, "global_step": 552679, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9916795492172241, "global_step": 552680, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.949800968170166, "global_step": 552681, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.112950086593628, "global_step": 552682, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1163594722747803, "global_step": 552683, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1037802696228027, "global_step": 552684, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9832104444503784, "global_step": 552685, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.108057975769043, "global_step": 552686, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0202524662017822, "global_step": 552687, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0523500442504883, "global_step": 552688, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0256292819976807, "global_step": 552689, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.999120831489563, "global_step": 552690, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9114395380020142, "global_step": 552691, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9873231649398804, "global_step": 552692, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9480611085891724, "global_step": 552693, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0409929752349854, "global_step": 552694, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9568334817886353, "global_step": 552695, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0466694831848145, "global_step": 552696, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.8886319398880005, "global_step": 552697, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9985536336898804, "global_step": 552698, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9924993515014648, "global_step": 552699, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0212254524230957, "global_step": 552700, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.984948754310608, "global_step": 552701, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.081389904022217, "global_step": 552702, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.021423578262329, "global_step": 552703, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0081119537353516, "global_step": 552704, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0154924392700195, "global_step": 552705, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.111995220184326, "global_step": 552706, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0743589401245117, "global_step": 552707, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.035313606262207, "global_step": 552708, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0535824298858643, "global_step": 552709, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9606353044509888, "global_step": 552710, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.052056312561035, "global_step": 552711, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0391011238098145, "global_step": 552712, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0865132808685303, "global_step": 552713, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.079315423965454, "global_step": 552714, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0630311965942383, "global_step": 552715, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0684008598327637, "global_step": 552716, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0444469451904297, "global_step": 552717, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0471160411834717, "global_step": 552718, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.979304552078247, "global_step": 552719, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.033365249633789, "global_step": 552720, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9868818521499634, "global_step": 552721, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.041200637817383, "global_step": 552722, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.009383201599121, "global_step": 552723, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.042814254760742, "global_step": 552724, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0400803089141846, "global_step": 552725, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0598206520080566, "global_step": 552726, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.080977439880371, "global_step": 552727, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9890145063400269, "global_step": 552728, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9506232738494873, "global_step": 552729, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.018123149871826, "global_step": 552730, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9748846292495728, "global_step": 552731, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.078681468963623, "global_step": 552732, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.083857536315918, "global_step": 552733, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9691070318222046, "global_step": 552734, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.069382429122925, "global_step": 552735, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1080162525177, "global_step": 552736, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.012723922729492, "global_step": 552737, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0329647064208984, "global_step": 552738, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.018172264099121, "global_step": 552739, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0099599361419678, "global_step": 552740, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0029783248901367, "global_step": 552741, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.030477523803711, "global_step": 552742, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.031111240386963, "global_step": 552743, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9766266345977783, "global_step": 552744, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.013537645339966, "global_step": 552745, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0287134647369385, "global_step": 552746, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.022569179534912, "global_step": 552747, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.11327862739563, "global_step": 552748, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.996005892753601, "global_step": 552749, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0441501140594482, "global_step": 552750, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9806302785873413, "global_step": 552751, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.051337718963623, "global_step": 552752, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0049452781677246, "global_step": 552753, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.117140054702759, "global_step": 552754, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.047203540802002, "global_step": 552755, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0568177700042725, "global_step": 552756, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0064220428466797, "global_step": 552757, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.029982805252075, "global_step": 552758, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.075019598007202, "global_step": 552759, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9775598049163818, "global_step": 552760, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9994926452636719, "global_step": 552761, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0110747814178467, "global_step": 552762, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9935100078582764, "global_step": 552763, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.065932512283325, "global_step": 552764, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0016379356384277, "global_step": 552765, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.964816927909851, "global_step": 552766, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.033818244934082, "global_step": 552767, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0582449436187744, "global_step": 552768, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1375157833099365, "global_step": 552769, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.002594232559204, "global_step": 552770, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9701656103134155, "global_step": 552771, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0467686653137207, "global_step": 552772, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1002392768859863, "global_step": 552773, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.078390598297119, "global_step": 552774, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.061493396759033, "global_step": 552775, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.043597936630249, "global_step": 552776, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0268826484680176, "global_step": 552777, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.034528970718384, "global_step": 552778, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.079087257385254, "global_step": 552779, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0384891033172607, "global_step": 552780, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0753934383392334, "global_step": 552781, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9617083072662354, "global_step": 552782, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.055891752243042, "global_step": 552783, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0776865482330322, "global_step": 552784, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.965834379196167, "global_step": 552785, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.058583974838257, "global_step": 552786, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.022298812866211, "global_step": 552787, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9908849000930786, "global_step": 552788, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.077059507369995, "global_step": 552789, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1158862113952637, "global_step": 552790, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0335190296173096, "global_step": 552791, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0100765228271484, "global_step": 552792, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9790951013565063, "global_step": 552793, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9235031604766846, "global_step": 552794, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0164787769317627, "global_step": 552795, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0205233097076416, "global_step": 552796, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9616128206253052, "global_step": 552797, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0624444484710693, "global_step": 552798, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0063083171844482, "global_step": 552799, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1085972785949707, "global_step": 552800, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.117438793182373, "global_step": 552801, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.055161237716675, "global_step": 552802, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.069958448410034, "global_step": 552803, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0214946269989014, "global_step": 552804, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.050206422805786, "global_step": 552805, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0231406688690186, "global_step": 552806, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0310699939727783, "global_step": 552807, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0459771156311035, "global_step": 552808, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9703792333602905, "global_step": 552809, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.133230209350586, "global_step": 552810, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.119663953781128, "global_step": 552811, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9892462491989136, "global_step": 552812, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.113290309906006, "global_step": 552813, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0118191242218018, "global_step": 552814, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0410540103912354, "global_step": 552815, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9625544548034668, "global_step": 552816, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9861950874328613, "global_step": 552817, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0798137187957764, "global_step": 552818, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0422234535217285, "global_step": 552819, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.095156192779541, "global_step": 552820, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9692823886871338, "global_step": 552821, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9517704248428345, "global_step": 552822, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.973405361175537, "global_step": 552823, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0826966762542725, "global_step": 552824, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.082453489303589, "global_step": 552825, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0585293769836426, "global_step": 552826, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0285532474517822, "global_step": 552827, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0242807865142822, "global_step": 552828, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.04243540763855, "global_step": 552829, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.072685480117798, "global_step": 552830, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.021657705307007, "global_step": 552831, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0306262969970703, "global_step": 552832, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.018230438232422, "global_step": 552833, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0222878456115723, "global_step": 552834, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0382070541381836, "global_step": 552835, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0148415565490723, "global_step": 552836, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.065612554550171, "global_step": 552837, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0677735805511475, "global_step": 552838, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1576974391937256, "global_step": 552839, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.055426597595215, "global_step": 552840, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.064851760864258, "global_step": 552841, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0547292232513428, "global_step": 552842, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.034695863723755, "global_step": 552843, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0513851642608643, "global_step": 552844, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9626779556274414, "global_step": 552845, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0488362312316895, "global_step": 552846, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1253106594085693, "global_step": 552847, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.936160922050476, "global_step": 552848, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.040196418762207, "global_step": 552849, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.139638662338257, "global_step": 552850, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0666840076446533, "global_step": 552851, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9451992511749268, "global_step": 552852, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0501062870025635, "global_step": 552853, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.031769037246704, "global_step": 552854, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0379438400268555, "global_step": 552855, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0691099166870117, "global_step": 552856, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9758694171905518, "global_step": 552857, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9325170516967773, "global_step": 552858, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9985918998718262, "global_step": 552859, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9732623100280762, "global_step": 552860, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9127392768859863, "global_step": 552861, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0542373657226562, "global_step": 552862, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.041738271713257, "global_step": 552863, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.052029848098755, "global_step": 552864, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.070934772491455, "global_step": 552865, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0684051513671875, "global_step": 552866, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0850377082824707, "global_step": 552867, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1062254905700684, "global_step": 552868, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.994585394859314, "global_step": 552869, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0033750534057617, "global_step": 552870, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.03167462348938, "global_step": 552871, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.035515785217285, "global_step": 552872, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.026102304458618, "global_step": 552873, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0119941234588623, "global_step": 552874, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0242819786071777, "global_step": 552875, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0318031311035156, "global_step": 552876, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9894028902053833, "global_step": 552877, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.937325358390808, "global_step": 552878, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.057436466217041, "global_step": 552879, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.025904655456543, "global_step": 552880, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9858084917068481, "global_step": 552881, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9903748035430908, "global_step": 552882, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0310420989990234, "global_step": 552883, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9964981079101562, "global_step": 552884, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.05861496925354, "global_step": 552885, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0658671855926514, "global_step": 552886, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.006009578704834, "global_step": 552887, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9653953313827515, "global_step": 552888, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9804091453552246, "global_step": 552889, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1144943237304688, "global_step": 552890, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0385003089904785, "global_step": 552891, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9763076305389404, "global_step": 552892, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.026953935623169, "global_step": 552893, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.977743148803711, "global_step": 552894, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0191993713378906, "global_step": 552895, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9887031316757202, "global_step": 552896, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0451176166534424, "global_step": 552897, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0246200561523438, "global_step": 552898, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.2073960304260254, "global_step": 552899, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9981459379196167, "global_step": 552900, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0152904987335205, "global_step": 552901, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9938015937805176, "global_step": 552902, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0149574279785156, "global_step": 552903, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0523734092712402, "global_step": 552904, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.01369047164917, "global_step": 552905, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0330238342285156, "global_step": 552906, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0021443367004395, "global_step": 552907, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0261452198028564, "global_step": 552908, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0676987171173096, "global_step": 552909, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0426292419433594, "global_step": 552910, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0574936866760254, "global_step": 552911, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9743026494979858, "global_step": 552912, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.057553768157959, "global_step": 552913, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0884904861450195, "global_step": 552914, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.98139488697052, "global_step": 552915, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9841772317886353, "global_step": 552916, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0109751224517822, "global_step": 552917, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9871270656585693, "global_step": 552918, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.09366774559021, "global_step": 552919, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0018937587738037, "global_step": 552920, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1015052795410156, "global_step": 552921, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9871699810028076, "global_step": 552922, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0363855361938477, "global_step": 552923, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.011880874633789, "global_step": 552924, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9897388219833374, "global_step": 552925, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.077108860015869, "global_step": 552926, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.03791880607605, "global_step": 552927, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0764150619506836, "global_step": 552928, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0105254650115967, "global_step": 552929, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9799212217330933, "global_step": 552930, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.953168272972107, "global_step": 552931, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.995492935180664, "global_step": 552932, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0928924083709717, "global_step": 552933, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.129831552505493, "global_step": 552934, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.990883231163025, "global_step": 552935, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.029156446456909, "global_step": 552936, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0605502128601074, "global_step": 552937, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.94594407081604, "global_step": 552938, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.115199089050293, "global_step": 552939, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.024836778640747, "global_step": 552940, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.985472559928894, "global_step": 552941, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0157270431518555, "global_step": 552942, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.060415506362915, "global_step": 552943, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0349674224853516, "global_step": 552944, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0069937705993652, "global_step": 552945, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0134389400482178, "global_step": 552946, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.956611156463623, "global_step": 552947, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.986194372177124, "global_step": 552948, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.077819585800171, "global_step": 552949, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0762224197387695, "global_step": 552950, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.009904384613037, "global_step": 552951, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.021453857421875, "global_step": 552952, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0966708660125732, "global_step": 552953, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.041282892227173, "global_step": 552954, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.019561529159546, "global_step": 552955, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9499341249465942, "global_step": 552956, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.994922399520874, "global_step": 552957, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9402967691421509, "global_step": 552958, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0439810752868652, "global_step": 552959, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.044696569442749, "global_step": 552960, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.912155270576477, "global_step": 552961, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.974107027053833, "global_step": 552962, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9677037000656128, "global_step": 552963, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.002699136734009, "global_step": 552964, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9806259870529175, "global_step": 552965, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.048368215560913, "global_step": 552966, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.098827838897705, "global_step": 552967, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0214669704437256, "global_step": 552968, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9654396772384644, "global_step": 552969, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9664638042449951, "global_step": 552970, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0279574394226074, "global_step": 552971, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.99966299533844, "global_step": 552972, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.954318881034851, "global_step": 552973, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9777010679244995, "global_step": 552974, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9461201429367065, "global_step": 552975, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0031118392944336, "global_step": 552976, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9609295129776, "global_step": 552977, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0258498191833496, "global_step": 552978, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9926607608795166, "global_step": 552979, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9694836139678955, "global_step": 552980, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.021566390991211, "global_step": 552981, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.081451416015625, "global_step": 552982, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.043832540512085, "global_step": 552983, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9436981678009033, "global_step": 552984, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0832631587982178, "global_step": 552985, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.096060037612915, "global_step": 552986, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.004916191101074, "global_step": 552987, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1052846908569336, "global_step": 552988, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.064406394958496, "global_step": 552989, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9949437379837036, "global_step": 552990, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.085810422897339, "global_step": 552991, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1451566219329834, "global_step": 552992, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.998473048210144, "global_step": 552993, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.977439522743225, "global_step": 552994, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1071536540985107, "global_step": 552995, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1035995483398438, "global_step": 552996, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9957401752471924, "global_step": 552997, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0235233306884766, "global_step": 552998, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0348312854766846, "global_step": 552999, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.034125328063965, "global_step": 553000, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9817529916763306, "global_step": 553001, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.967138409614563, "global_step": 553002, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.024855136871338, "global_step": 553003, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.028804302215576, "global_step": 553004, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0220744609832764, "global_step": 553005, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0400125980377197, "global_step": 553006, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.043274164199829, "global_step": 553007, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9816803932189941, "global_step": 553008, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0378196239471436, "global_step": 553009, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9834599494934082, "global_step": 553010, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.03452730178833, "global_step": 553011, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.984817385673523, "global_step": 553012, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0645649433135986, "global_step": 553013, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.087857723236084, "global_step": 553014, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0016987323760986, "global_step": 553015, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9903024435043335, "global_step": 553016, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.059998035430908, "global_step": 553017, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0582315921783447, "global_step": 553018, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.061920404434204, "global_step": 553019, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0066819190979004, "global_step": 553020, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0253360271453857, "global_step": 553021, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1022286415100098, "global_step": 553022, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0245251655578613, "global_step": 553023, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0427613258361816, "global_step": 553024, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9803587198257446, "global_step": 553025, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0480079650878906, "global_step": 553026, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0818512439727783, "global_step": 553027, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0220131874084473, "global_step": 553028, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9804491996765137, "global_step": 553029, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0633528232574463, "global_step": 553030, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.8605271577835083, "global_step": 553031, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.027377128601074, "global_step": 553032, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0495848655700684, "global_step": 553033, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0908384323120117, "global_step": 553034, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.013284206390381, "global_step": 553035, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0374839305877686, "global_step": 553036, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.008648633956909, "global_step": 553037, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1003551483154297, "global_step": 553038, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9988093376159668, "global_step": 553039, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.983120322227478, "global_step": 553040, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0146071910858154, "global_step": 553041, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.010730266571045, "global_step": 553042, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0994389057159424, "global_step": 553043, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0280535221099854, "global_step": 553044, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.007855176925659, "global_step": 553045, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.011068105697632, "global_step": 553046, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.963040828704834, "global_step": 553047, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.8944462537765503, "global_step": 553048, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0051445960998535, "global_step": 553049, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9593923091888428, "global_step": 553050, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9932154417037964, "global_step": 553051, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.945924997329712, "global_step": 553052, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0540084838867188, "global_step": 553053, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.089658737182617, "global_step": 553054, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.10746169090271, "global_step": 553055, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.082612991333008, "global_step": 553056, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9253342151641846, "global_step": 553057, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.015437364578247, "global_step": 553058, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.087275743484497, "global_step": 553059, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0616836547851562, "global_step": 553060, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.022789716720581, "global_step": 553061, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9906405210494995, "global_step": 553062, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.968988060951233, "global_step": 553063, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.021139144897461, "global_step": 553064, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0802977085113525, "global_step": 553065, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.031608819961548, "global_step": 553066, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.07676100730896, "global_step": 553067, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0383412837982178, "global_step": 553068, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0525505542755127, "global_step": 553069, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.036341905593872, "global_step": 553070, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0636138916015625, "global_step": 553071, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.057209014892578, "global_step": 553072, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0573160648345947, "global_step": 553073, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9647445678710938, "global_step": 553074, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.132533550262451, "global_step": 553075, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9572430849075317, "global_step": 553076, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0210013389587402, "global_step": 553077, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.041684150695801, "global_step": 553078, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.001228094100952, "global_step": 553079, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.106534719467163, "global_step": 553080, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0892751216888428, "global_step": 553081, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.020045518875122, "global_step": 553082, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.975915551185608, "global_step": 553083, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0134382247924805, "global_step": 553084, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0541210174560547, "global_step": 553085, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.96044921875, "global_step": 553086, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.146407127380371, "global_step": 553087, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0482308864593506, "global_step": 553088, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0907700061798096, "global_step": 553089, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9657739400863647, "global_step": 553090, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0246708393096924, "global_step": 553091, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9381468296051025, "global_step": 553092, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.121912956237793, "global_step": 553093, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0561141967773438, "global_step": 553094, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.122861385345459, "global_step": 553095, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.015643835067749, "global_step": 553096, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.071282148361206, "global_step": 553097, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0320534706115723, "global_step": 553098, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0567409992218018, "global_step": 553099, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1155853271484375, "global_step": 553100, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0568525791168213, "global_step": 553101, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.945377230644226, "global_step": 553102, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0384302139282227, "global_step": 553103, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.994003176689148, "global_step": 553104, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.030663251876831, "global_step": 553105, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0333588123321533, "global_step": 553106, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.066321849822998, "global_step": 553107, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.068720817565918, "global_step": 553108, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9857902526855469, "global_step": 553109, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0232162475585938, "global_step": 553110, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.001570701599121, "global_step": 553111, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9898396730422974, "global_step": 553112, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1220898628234863, "global_step": 553113, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.011075973510742, "global_step": 553114, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0095362663269043, "global_step": 553115, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.061570882797241, "global_step": 553116, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.056870937347412, "global_step": 553117, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0184662342071533, "global_step": 553118, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0480566024780273, "global_step": 553119, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0355002880096436, "global_step": 553120, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0091445446014404, "global_step": 553121, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1234562397003174, "global_step": 553122, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9491676092147827, "global_step": 553123, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.096895456314087, "global_step": 553124, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0532023906707764, "global_step": 553125, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0257010459899902, "global_step": 553126, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0094399452209473, "global_step": 553127, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9689229726791382, "global_step": 553128, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9906409978866577, "global_step": 553129, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9989442825317383, "global_step": 553130, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.079345226287842, "global_step": 553131, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0676920413970947, "global_step": 553132, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0699236392974854, "global_step": 553133, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.033689260482788, "global_step": 553134, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9336762428283691, "global_step": 553135, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.063826322555542, "global_step": 553136, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0678229331970215, "global_step": 553137, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.033338785171509, "global_step": 553138, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9126827716827393, "global_step": 553139, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.045724868774414, "global_step": 553140, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.984567642211914, "global_step": 553141, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0540356636047363, "global_step": 553142, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0589895248413086, "global_step": 553143, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0555367469787598, "global_step": 553144, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9957890510559082, "global_step": 553145, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9860999584197998, "global_step": 553146, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9856535196304321, "global_step": 553147, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.007159948348999, "global_step": 553148, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0318660736083984, "global_step": 553149, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.059715747833252, "global_step": 553150, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0488555431365967, "global_step": 553151, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.953147053718567, "global_step": 553152, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0483572483062744, "global_step": 553153, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.031458616256714, "global_step": 553154, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0885000228881836, "global_step": 553155, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.095714569091797, "global_step": 553156, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.105372905731201, "global_step": 553157, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0654547214508057, "global_step": 553158, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.013641834259033, "global_step": 553159, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.006948232650757, "global_step": 553160, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.979848861694336, "global_step": 553161, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0304722785949707, "global_step": 553162, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9841649532318115, "global_step": 553163, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.075012445449829, "global_step": 553164, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.079252243041992, "global_step": 553165, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.002864122390747, "global_step": 553166, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.965694785118103, "global_step": 553167, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.114797592163086, "global_step": 553168, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.963842749595642, "global_step": 553169, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.027360439300537, "global_step": 553170, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.071927785873413, "global_step": 553171, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9026211500167847, "global_step": 553172, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9449280500411987, "global_step": 553173, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.032959222793579, "global_step": 553174, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0790581703186035, "global_step": 553175, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.040666341781616, "global_step": 553176, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1595818996429443, "global_step": 553177, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.039898157119751, "global_step": 553178, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.048983573913574, "global_step": 553179, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0665905475616455, "global_step": 553180, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.051466703414917, "global_step": 553181, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.025735855102539, "global_step": 553182, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.106781244277954, "global_step": 553183, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0082051753997803, "global_step": 553184, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.048450469970703, "global_step": 553185, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.00862455368042, "global_step": 553186, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.093290328979492, "global_step": 553187, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.071760416030884, "global_step": 553188, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1308984756469727, "global_step": 553189, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0782470703125, "global_step": 553190, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0568556785583496, "global_step": 553191, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1108858585357666, "global_step": 553192, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0546162128448486, "global_step": 553193, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.023437261581421, "global_step": 553194, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1115455627441406, "global_step": 553195, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.108746290206909, "global_step": 553196, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0463593006134033, "global_step": 553197, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0046093463897705, "global_step": 553198, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0632269382476807, "global_step": 553199, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.083061456680298, "global_step": 553200, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.088773012161255, "global_step": 553201, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.979193925857544, "global_step": 553202, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0222909450531006, "global_step": 553203, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.044670820236206, "global_step": 553204, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0155816078186035, "global_step": 553205, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.046196460723877, "global_step": 553206, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.047790050506592, "global_step": 553207, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0506627559661865, "global_step": 553208, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9523471593856812, "global_step": 553209, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9649986028671265, "global_step": 553210, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.098881244659424, "global_step": 553211, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0807290077209473, "global_step": 553212, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9772154092788696, "global_step": 553213, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9611202478408813, "global_step": 553214, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.008068084716797, "global_step": 553215, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0942187309265137, "global_step": 553216, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.020686626434326, "global_step": 553217, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.02185320854187, "global_step": 553218, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.123387575149536, "global_step": 553219, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.052086114883423, "global_step": 553220, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.958402156829834, "global_step": 553221, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0493826866149902, "global_step": 553222, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.10052490234375, "global_step": 553223, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0549962520599365, "global_step": 553224, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9698598384857178, "global_step": 553225, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9862395524978638, "global_step": 553226, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.021167278289795, "global_step": 553227, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0467281341552734, "global_step": 553228, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9908537864685059, "global_step": 553229, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0039925575256348, "global_step": 553230, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.020352602005005, "global_step": 553231, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.082357883453369, "global_step": 553232, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0313615798950195, "global_step": 553233, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.998923659324646, "global_step": 553234, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0839593410491943, "global_step": 553235, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.135162591934204, "global_step": 553236, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.062760829925537, "global_step": 553237, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0870156288146973, "global_step": 553238, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.013493299484253, "global_step": 553239, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9879521131515503, "global_step": 553240, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0646984577178955, "global_step": 553241, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.067589044570923, "global_step": 553242, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9397047758102417, "global_step": 553243, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0607733726501465, "global_step": 553244, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0689518451690674, "global_step": 553245, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0010385513305664, "global_step": 553246, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0129456520080566, "global_step": 553247, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.020624876022339, "global_step": 553248, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9595692157745361, "global_step": 553249, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0244805812835693, "global_step": 553250, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.023348093032837, "global_step": 553251, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.10947585105896, "global_step": 553252, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.055555582046509, "global_step": 553253, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.093278646469116, "global_step": 553254, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.090421199798584, "global_step": 553255, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.011381149291992, "global_step": 553256, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9881162643432617, "global_step": 553257, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9826805591583252, "global_step": 553258, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0829508304595947, "global_step": 553259, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0909006595611572, "global_step": 553260, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.987201452255249, "global_step": 553261, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.999433159828186, "global_step": 553262, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9339179992675781, "global_step": 553263, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0364434719085693, "global_step": 553264, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0462799072265625, "global_step": 553265, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0303637981414795, "global_step": 553266, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9884674549102783, "global_step": 553267, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.077962636947632, "global_step": 553268, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.080904960632324, "global_step": 553269, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1030147075653076, "global_step": 553270, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.061056613922119, "global_step": 553271, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.990705966949463, "global_step": 553272, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9778614044189453, "global_step": 553273, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0110738277435303, "global_step": 553274, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1044936180114746, "global_step": 553275, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0025877952575684, "global_step": 553276, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0474860668182373, "global_step": 553277, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9520759582519531, "global_step": 553278, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9634208679199219, "global_step": 553279, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0258543491363525, "global_step": 553280, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.060147762298584, "global_step": 553281, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1246111392974854, "global_step": 553282, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.023629903793335, "global_step": 553283, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0418782234191895, "global_step": 553284, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.022315502166748, "global_step": 553285, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9985893964767456, "global_step": 553286, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9848181009292603, "global_step": 553287, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0746092796325684, "global_step": 553288, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.022963523864746, "global_step": 553289, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.030198812484741, "global_step": 553290, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0178017616271973, "global_step": 553291, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0212531089782715, "global_step": 553292, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.06111741065979, "global_step": 553293, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0529937744140625, "global_step": 553294, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0576932430267334, "global_step": 553295, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0657873153686523, "global_step": 553296, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0619192123413086, "global_step": 553297, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0166397094726562, "global_step": 553298, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0712506771087646, "global_step": 553299, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0921740531921387, "global_step": 553300, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.942397117614746, "global_step": 553301, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9633522033691406, "global_step": 553302, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.024195671081543, "global_step": 553303, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.068607807159424, "global_step": 553304, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0114023685455322, "global_step": 553305, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.987113356590271, "global_step": 553306, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.029388427734375, "global_step": 553307, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0595574378967285, "global_step": 553308, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.005350351333618, "global_step": 553309, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.063080310821533, "global_step": 553310, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.076850175857544, "global_step": 553311, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.09138822555542, "global_step": 553312, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0597426891326904, "global_step": 553313, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0382306575775146, "global_step": 553314, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9951575994491577, "global_step": 553315, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.157136917114258, "global_step": 553316, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9478052854537964, "global_step": 553317, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0093162059783936, "global_step": 553318, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0833704471588135, "global_step": 553319, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9836961030960083, "global_step": 553320, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.08604097366333, "global_step": 553321, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0741922855377197, "global_step": 553322, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0900352001190186, "global_step": 553323, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0445497035980225, "global_step": 553324, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9900888204574585, "global_step": 553325, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9892643690109253, "global_step": 553326, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0224127769470215, "global_step": 553327, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.009190559387207, "global_step": 553328, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9512605667114258, "global_step": 553329, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.093540906906128, "global_step": 553330, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0958685874938965, "global_step": 553331, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0574004650115967, "global_step": 553332, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0952539443969727, "global_step": 553333, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0617706775665283, "global_step": 553334, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9919551610946655, "global_step": 553335, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.024332046508789, "global_step": 553336, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.029341220855713, "global_step": 553337, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.041264772415161, "global_step": 553338, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0331871509552, "global_step": 553339, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.053367853164673, "global_step": 553340, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0072457790374756, "global_step": 553341, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9662903547286987, "global_step": 553342, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9991154670715332, "global_step": 553343, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0857439041137695, "global_step": 553344, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0853376388549805, "global_step": 553345, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.053506851196289, "global_step": 553346, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0343077182769775, "global_step": 553347, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.110372304916382, "global_step": 553348, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.068711042404175, "global_step": 553349, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9481350183486938, "global_step": 553350, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.019054651260376, "global_step": 553351, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9567071199417114, "global_step": 553352, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0681023597717285, "global_step": 553353, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1080095767974854, "global_step": 553354, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.025606155395508, "global_step": 553355, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0928852558135986, "global_step": 553356, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.080734968185425, "global_step": 553357, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.063386917114258, "global_step": 553358, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.049133539199829, "global_step": 553359, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.034491777420044, "global_step": 553360, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.090573310852051, "global_step": 553361, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0169670581817627, "global_step": 553362, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.080723524093628, "global_step": 553363, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0323147773742676, "global_step": 553364, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9770435094833374, "global_step": 553365, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9769375324249268, "global_step": 553366, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9920074939727783, "global_step": 553367, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.974010705947876, "global_step": 553368, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9843811988830566, "global_step": 553369, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0594887733459473, "global_step": 553370, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9730085134506226, "global_step": 553371, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.088965654373169, "global_step": 553372, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.064797878265381, "global_step": 553373, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0613338947296143, "global_step": 553374, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.068669319152832, "global_step": 553375, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.990684151649475, "global_step": 553376, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9941048622131348, "global_step": 553377, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0163674354553223, "global_step": 553378, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0723352432250977, "global_step": 553379, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.033224582672119, "global_step": 553380, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9724006652832031, "global_step": 553381, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.042461395263672, "global_step": 553382, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0231683254241943, "global_step": 553383, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9618314504623413, "global_step": 553384, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1001458168029785, "global_step": 553385, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9257186651229858, "global_step": 553386, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9936686754226685, "global_step": 553387, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1131298542022705, "global_step": 553388, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.105518102645874, "global_step": 553389, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.1318438053131104, "global_step": 553390, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.07342267036438, "global_step": 553391, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9939401149749756, "global_step": 553392, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0200438499450684, "global_step": 553393, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0968010425567627, "global_step": 553394, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.014312982559204, "global_step": 553395, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9469488859176636, "global_step": 553396, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.012653350830078, "global_step": 553397, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0767464637756348, "global_step": 553398, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.090221881866455, "global_step": 553399, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.134495973587036, "global_step": 553400, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0240421295166016, "global_step": 553401, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0518269538879395, "global_step": 553402, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.144211769104004, "global_step": 553403, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0318899154663086, "global_step": 553404, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0887019634246826, "global_step": 553405, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0526323318481445, "global_step": 553406, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9913556575775146, "global_step": 553407, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.98642098903656, "global_step": 553408, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.00346040725708, "global_step": 553409, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0142505168914795, "global_step": 553410, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.006936550140381, "global_step": 553411, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0661799907684326, "global_step": 553412, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.045175552368164, "global_step": 553413, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.078890323638916, "global_step": 553414, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0553553104400635, "global_step": 553415, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.015418291091919, "global_step": 553416, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9785487651824951, "global_step": 553417, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.055785655975342, "global_step": 553418, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9985355138778687, "global_step": 553419, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0543153285980225, "global_step": 553420, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0499417781829834, "global_step": 553421, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0390162467956543, "global_step": 553422, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0251593589782715, "global_step": 553423, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9766156673431396, "global_step": 553424, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0543880462646484, "global_step": 553425, "epoch": 920, "lr": 5e-05}
{"train_loss": 1.9926846027374268, "global_step": 553426, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.101546287536621, "global_step": 553427, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.066089630126953, "global_step": 553428, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0502054691314697, "global_step": 553429, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0563466548919678, "global_step": 553430, "epoch": 920, "lr": 5e-05}
{"train_loss": 2.0292110443115234, "global_step": 553431, "epoch": 920, "lr": 5e-05, "val_loss": 5.756349563598633, "test_reconst_mse": 0.07418626546859741}
{"train_loss": 2.0148909091949463, "global_step": 553432, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.072462797164917, "global_step": 553433, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.982125163078308, "global_step": 553434, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0785038471221924, "global_step": 553435, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.021233320236206, "global_step": 553436, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.955833077430725, "global_step": 553437, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.993736743927002, "global_step": 553438, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.115035057067871, "global_step": 553439, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0133330821990967, "global_step": 553440, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.020846128463745, "global_step": 553441, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0398144721984863, "global_step": 553442, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.994276523590088, "global_step": 553443, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0615715980529785, "global_step": 553444, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.055295944213867, "global_step": 553445, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0757758617401123, "global_step": 553446, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0228586196899414, "global_step": 553447, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9997488260269165, "global_step": 553448, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.994126558303833, "global_step": 553449, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.024761199951172, "global_step": 553450, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9373003244400024, "global_step": 553451, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0066001415252686, "global_step": 553452, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.035292863845825, "global_step": 553453, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.013247013092041, "global_step": 553454, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0648250579833984, "global_step": 553455, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.060281991958618, "global_step": 553456, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9968575239181519, "global_step": 553457, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0489370822906494, "global_step": 553458, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9964380264282227, "global_step": 553459, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.992843508720398, "global_step": 553460, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.018672466278076, "global_step": 553461, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9637739658355713, "global_step": 553462, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1255135536193848, "global_step": 553463, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.056680917739868, "global_step": 553464, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9468175172805786, "global_step": 553465, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.049567222595215, "global_step": 553466, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9947384595870972, "global_step": 553467, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.970165729522705, "global_step": 553468, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9432862997055054, "global_step": 553469, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9562301635742188, "global_step": 553470, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0902493000030518, "global_step": 553471, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0096170902252197, "global_step": 553472, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.967952013015747, "global_step": 553473, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.09782338142395, "global_step": 553474, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.978186011314392, "global_step": 553475, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.007906675338745, "global_step": 553476, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.096256971359253, "global_step": 553477, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0569210052490234, "global_step": 553478, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0166990756988525, "global_step": 553479, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0334348678588867, "global_step": 553480, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0281388759613037, "global_step": 553481, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.081388473510742, "global_step": 553482, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0159823894500732, "global_step": 553483, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.027770757675171, "global_step": 553484, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9928596019744873, "global_step": 553485, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0657172203063965, "global_step": 553486, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.8859363794326782, "global_step": 553487, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0300190448760986, "global_step": 553488, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.027146100997925, "global_step": 553489, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.000678777694702, "global_step": 553490, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.059108257293701, "global_step": 553491, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9832149744033813, "global_step": 553492, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9784725904464722, "global_step": 553493, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.967108964920044, "global_step": 553494, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0167293548583984, "global_step": 553495, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9821316003799438, "global_step": 553496, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.012714147567749, "global_step": 553497, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9704424142837524, "global_step": 553498, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.988664150238037, "global_step": 553499, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0573978424072266, "global_step": 553500, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9919757843017578, "global_step": 553501, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0824074745178223, "global_step": 553502, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0361886024475098, "global_step": 553503, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0781943798065186, "global_step": 553504, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.065222978591919, "global_step": 553505, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.029439687728882, "global_step": 553506, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0040721893310547, "global_step": 553507, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.043339252471924, "global_step": 553508, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0980052947998047, "global_step": 553509, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9058821201324463, "global_step": 553510, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0752904415130615, "global_step": 553511, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.046565055847168, "global_step": 553512, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0563955307006836, "global_step": 553513, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0225067138671875, "global_step": 553514, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.059593915939331, "global_step": 553515, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9621397256851196, "global_step": 553516, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.034118890762329, "global_step": 553517, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9571350812911987, "global_step": 553518, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.019566535949707, "global_step": 553519, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0260517597198486, "global_step": 553520, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0849876403808594, "global_step": 553521, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0184688568115234, "global_step": 553522, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.975648045539856, "global_step": 553523, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.953826665878296, "global_step": 553524, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9875843524932861, "global_step": 553525, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0362188816070557, "global_step": 553526, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9866985082626343, "global_step": 553527, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0044939517974854, "global_step": 553528, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0895237922668457, "global_step": 553529, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9625370502471924, "global_step": 553530, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9424514770507812, "global_step": 553531, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.048389434814453, "global_step": 553532, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0669217109680176, "global_step": 553533, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.952047348022461, "global_step": 553534, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0104146003723145, "global_step": 553535, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.040036916732788, "global_step": 553536, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.058931589126587, "global_step": 553537, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0021519660949707, "global_step": 553538, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.039823055267334, "global_step": 553539, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0163207054138184, "global_step": 553540, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.035576105117798, "global_step": 553541, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9616646766662598, "global_step": 553542, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9620336294174194, "global_step": 553543, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0532889366149902, "global_step": 553544, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0192036628723145, "global_step": 553545, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0016770362854004, "global_step": 553546, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0324594974517822, "global_step": 553547, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.042126417160034, "global_step": 553548, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9470449686050415, "global_step": 553549, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9558062553405762, "global_step": 553550, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.014608383178711, "global_step": 553551, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9496209621429443, "global_step": 553552, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.00337815284729, "global_step": 553553, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.022960901260376, "global_step": 553554, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9809274673461914, "global_step": 553555, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0731191635131836, "global_step": 553556, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0900487899780273, "global_step": 553557, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.067957639694214, "global_step": 553558, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.997601866722107, "global_step": 553559, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.049778938293457, "global_step": 553560, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0605785846710205, "global_step": 553561, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.97683584690094, "global_step": 553562, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.03586483001709, "global_step": 553563, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.072417974472046, "global_step": 553564, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.023684024810791, "global_step": 553565, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1032779216766357, "global_step": 553566, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.031850814819336, "global_step": 553567, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.885938048362732, "global_step": 553568, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.007866382598877, "global_step": 553569, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.054356575012207, "global_step": 553570, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1057064533233643, "global_step": 553571, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.019683361053467, "global_step": 553572, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9590266942977905, "global_step": 553573, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.028188943862915, "global_step": 553574, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.012725353240967, "global_step": 553575, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0530014038085938, "global_step": 553576, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0415120124816895, "global_step": 553577, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.023557186126709, "global_step": 553578, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0807321071624756, "global_step": 553579, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.030590534210205, "global_step": 553580, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.965165615081787, "global_step": 553581, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.025665760040283, "global_step": 553582, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0978808403015137, "global_step": 553583, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0023038387298584, "global_step": 553584, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.950641393661499, "global_step": 553585, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0449604988098145, "global_step": 553586, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0550308227539062, "global_step": 553587, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0000967979431152, "global_step": 553588, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0566751956939697, "global_step": 553589, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0364110469818115, "global_step": 553590, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0428073406219482, "global_step": 553591, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.99026620388031, "global_step": 553592, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.041686534881592, "global_step": 553593, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9758706092834473, "global_step": 553594, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9913157224655151, "global_step": 553595, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.976877212524414, "global_step": 553596, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0329296588897705, "global_step": 553597, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.028550863265991, "global_step": 553598, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0614547729492188, "global_step": 553599, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0624144077301025, "global_step": 553600, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.006162643432617, "global_step": 553601, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9582304954528809, "global_step": 553602, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.022205114364624, "global_step": 553603, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.081576108932495, "global_step": 553604, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0534510612487793, "global_step": 553605, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9713857173919678, "global_step": 553606, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9770444631576538, "global_step": 553607, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.041073799133301, "global_step": 553608, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.050624132156372, "global_step": 553609, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0657877922058105, "global_step": 553610, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9750034809112549, "global_step": 553611, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.071237802505493, "global_step": 553612, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.016831398010254, "global_step": 553613, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9553320407867432, "global_step": 553614, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9398351907730103, "global_step": 553615, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0065338611602783, "global_step": 553616, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0122005939483643, "global_step": 553617, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.001690149307251, "global_step": 553618, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0497937202453613, "global_step": 553619, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.092397689819336, "global_step": 553620, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.987403154373169, "global_step": 553621, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0278537273406982, "global_step": 553622, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.043041467666626, "global_step": 553623, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9916706085205078, "global_step": 553624, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.039384126663208, "global_step": 553625, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9605093002319336, "global_step": 553626, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9431543350219727, "global_step": 553627, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9496252536773682, "global_step": 553628, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0395805835723877, "global_step": 553629, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0215389728546143, "global_step": 553630, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0280675888061523, "global_step": 553631, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0272750854492188, "global_step": 553632, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9776326417922974, "global_step": 553633, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.147064208984375, "global_step": 553634, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9737269878387451, "global_step": 553635, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.005119562149048, "global_step": 553636, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9502966403961182, "global_step": 553637, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9705959558486938, "global_step": 553638, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.060635566711426, "global_step": 553639, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9615763425827026, "global_step": 553640, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.042206287384033, "global_step": 553641, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.013683557510376, "global_step": 553642, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.008983612060547, "global_step": 553643, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9589104652404785, "global_step": 553644, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0316712856292725, "global_step": 553645, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.029423713684082, "global_step": 553646, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.000887632369995, "global_step": 553647, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1247432231903076, "global_step": 553648, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9313137531280518, "global_step": 553649, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.058701276779175, "global_step": 553650, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0619876384735107, "global_step": 553651, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.105003595352173, "global_step": 553652, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9942026138305664, "global_step": 553653, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0284252166748047, "global_step": 553654, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.020509958267212, "global_step": 553655, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.034153938293457, "global_step": 553656, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.061816453933716, "global_step": 553657, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9885298013687134, "global_step": 553658, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0160162448883057, "global_step": 553659, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0867316722869873, "global_step": 553660, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1151647567749023, "global_step": 553661, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9831352233886719, "global_step": 553662, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1350553035736084, "global_step": 553663, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9843498468399048, "global_step": 553664, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9961366653442383, "global_step": 553665, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0512022972106934, "global_step": 553666, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0594050884246826, "global_step": 553667, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9664782285690308, "global_step": 553668, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9281997680664062, "global_step": 553669, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.982838749885559, "global_step": 553670, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.022878408432007, "global_step": 553671, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0407309532165527, "global_step": 553672, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.001418352127075, "global_step": 553673, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0723795890808105, "global_step": 553674, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.078504800796509, "global_step": 553675, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9880956411361694, "global_step": 553676, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0221352577209473, "global_step": 553677, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.099174976348877, "global_step": 553678, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.957257628440857, "global_step": 553679, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0426652431488037, "global_step": 553680, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.069122552871704, "global_step": 553681, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.055084228515625, "global_step": 553682, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9811351299285889, "global_step": 553683, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.15997052192688, "global_step": 553684, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0397934913635254, "global_step": 553685, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0729684829711914, "global_step": 553686, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.056272268295288, "global_step": 553687, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0222175121307373, "global_step": 553688, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0214638710021973, "global_step": 553689, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.068222999572754, "global_step": 553690, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0576493740081787, "global_step": 553691, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1034486293792725, "global_step": 553692, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9478520154953003, "global_step": 553693, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0704245567321777, "global_step": 553694, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9685676097869873, "global_step": 553695, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9568616151809692, "global_step": 553696, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0199391841888428, "global_step": 553697, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9855701923370361, "global_step": 553698, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.030911922454834, "global_step": 553699, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0663325786590576, "global_step": 553700, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9887194633483887, "global_step": 553701, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9663689136505127, "global_step": 553702, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.090409278869629, "global_step": 553703, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9594144821166992, "global_step": 553704, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0578300952911377, "global_step": 553705, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0546910762786865, "global_step": 553706, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9813657999038696, "global_step": 553707, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0264546871185303, "global_step": 553708, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.057558059692383, "global_step": 553709, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.919895887374878, "global_step": 553710, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.023284435272217, "global_step": 553711, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.029940128326416, "global_step": 553712, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9924737215042114, "global_step": 553713, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0262138843536377, "global_step": 553714, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0424697399139404, "global_step": 553715, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0317625999450684, "global_step": 553716, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0543158054351807, "global_step": 553717, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9998300075531006, "global_step": 553718, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0266900062561035, "global_step": 553719, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9130498170852661, "global_step": 553720, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0993118286132812, "global_step": 553721, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0331802368164062, "global_step": 553722, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.977378487586975, "global_step": 553723, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0702335834503174, "global_step": 553724, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.009995460510254, "global_step": 553725, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9988192319869995, "global_step": 553726, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9607512950897217, "global_step": 553727, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.056199550628662, "global_step": 553728, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.986890435218811, "global_step": 553729, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9617066383361816, "global_step": 553730, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.917689561843872, "global_step": 553731, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9655132293701172, "global_step": 553732, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.011547327041626, "global_step": 553733, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0184683799743652, "global_step": 553734, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.023452043533325, "global_step": 553735, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0263631343841553, "global_step": 553736, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9982792139053345, "global_step": 553737, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1549084186553955, "global_step": 553738, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0545661449432373, "global_step": 553739, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.008524179458618, "global_step": 553740, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.062861680984497, "global_step": 553741, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9764485359191895, "global_step": 553742, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.047226667404175, "global_step": 553743, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0055339336395264, "global_step": 553744, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0405008792877197, "global_step": 553745, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.009711742401123, "global_step": 553746, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0468578338623047, "global_step": 553747, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0867810249328613, "global_step": 553748, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0577099323272705, "global_step": 553749, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0659472942352295, "global_step": 553750, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0616414546966553, "global_step": 553751, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0055370330810547, "global_step": 553752, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.989659070968628, "global_step": 553753, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0651955604553223, "global_step": 553754, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.042367696762085, "global_step": 553755, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0719361305236816, "global_step": 553756, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.021737575531006, "global_step": 553757, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.977007508277893, "global_step": 553758, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.018394947052002, "global_step": 553759, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9758186340332031, "global_step": 553760, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.982120394706726, "global_step": 553761, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.04756760597229, "global_step": 553762, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.008218765258789, "global_step": 553763, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.02483868598938, "global_step": 553764, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.06514310836792, "global_step": 553765, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9976714849472046, "global_step": 553766, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.038414478302002, "global_step": 553767, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.111539602279663, "global_step": 553768, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0157134532928467, "global_step": 553769, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0314292907714844, "global_step": 553770, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0546016693115234, "global_step": 553771, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.036313772201538, "global_step": 553772, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9951989650726318, "global_step": 553773, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.093322515487671, "global_step": 553774, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0051076412200928, "global_step": 553775, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.078655242919922, "global_step": 553776, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.991999626159668, "global_step": 553777, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0714657306671143, "global_step": 553778, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9995087385177612, "global_step": 553779, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0815765857696533, "global_step": 553780, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0053653717041016, "global_step": 553781, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9835084676742554, "global_step": 553782, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9279758930206299, "global_step": 553783, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0129215717315674, "global_step": 553784, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9540218114852905, "global_step": 553785, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9707393646240234, "global_step": 553786, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.048435926437378, "global_step": 553787, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.001167058944702, "global_step": 553788, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.101360559463501, "global_step": 553789, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9600721597671509, "global_step": 553790, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.008540630340576, "global_step": 553791, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9612935781478882, "global_step": 553792, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0490591526031494, "global_step": 553793, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.071078062057495, "global_step": 553794, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.088345527648926, "global_step": 553795, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0492312908172607, "global_step": 553796, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0436463356018066, "global_step": 553797, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0158371925354004, "global_step": 553798, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0434272289276123, "global_step": 553799, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0824697017669678, "global_step": 553800, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.022120237350464, "global_step": 553801, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.056504726409912, "global_step": 553802, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.036102056503296, "global_step": 553803, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.111996650695801, "global_step": 553804, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0024216175079346, "global_step": 553805, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.063649892807007, "global_step": 553806, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9736970663070679, "global_step": 553807, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9555420875549316, "global_step": 553808, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0427680015563965, "global_step": 553809, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.049198627471924, "global_step": 553810, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9961469173431396, "global_step": 553811, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.05599045753479, "global_step": 553812, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1097593307495117, "global_step": 553813, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.948883295059204, "global_step": 553814, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9128937721252441, "global_step": 553815, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.014259099960327, "global_step": 553816, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0626204013824463, "global_step": 553817, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9724199771881104, "global_step": 553818, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0507609844207764, "global_step": 553819, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9852159023284912, "global_step": 553820, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9775502681732178, "global_step": 553821, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.049645185470581, "global_step": 553822, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9918909072875977, "global_step": 553823, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.026458501815796, "global_step": 553824, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9934089183807373, "global_step": 553825, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0380399227142334, "global_step": 553826, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0369160175323486, "global_step": 553827, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.010488271713257, "global_step": 553828, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.067312479019165, "global_step": 553829, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0753090381622314, "global_step": 553830, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9818211793899536, "global_step": 553831, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.050180673599243, "global_step": 553832, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.044353723526001, "global_step": 553833, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0161986351013184, "global_step": 553834, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0476975440979004, "global_step": 553835, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9332759380340576, "global_step": 553836, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9758983850479126, "global_step": 553837, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.070065498352051, "global_step": 553838, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0223586559295654, "global_step": 553839, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.029292583465576, "global_step": 553840, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.984462022781372, "global_step": 553841, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.058563232421875, "global_step": 553842, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9841622114181519, "global_step": 553843, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0835258960723877, "global_step": 553844, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0256547927856445, "global_step": 553845, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9112553596496582, "global_step": 553846, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0514028072357178, "global_step": 553847, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0314111709594727, "global_step": 553848, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0585649013519287, "global_step": 553849, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.038957357406616, "global_step": 553850, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9742927551269531, "global_step": 553851, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0192108154296875, "global_step": 553852, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9424418210983276, "global_step": 553853, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.116267204284668, "global_step": 553854, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.117572069168091, "global_step": 553855, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.016322612762451, "global_step": 553856, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9989370107650757, "global_step": 553857, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0942327976226807, "global_step": 553858, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.115208387374878, "global_step": 553859, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.063209295272827, "global_step": 553860, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1311092376708984, "global_step": 553861, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0258851051330566, "global_step": 553862, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.018874406814575, "global_step": 553863, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0703935623168945, "global_step": 553864, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0145716667175293, "global_step": 553865, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9730844497680664, "global_step": 553866, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.031952142715454, "global_step": 553867, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.00142502784729, "global_step": 553868, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.026021957397461, "global_step": 553869, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0591304302215576, "global_step": 553870, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1372318267822266, "global_step": 553871, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.047940492630005, "global_step": 553872, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0085690021514893, "global_step": 553873, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0255987644195557, "global_step": 553874, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0202744007110596, "global_step": 553875, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1115901470184326, "global_step": 553876, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0160179138183594, "global_step": 553877, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.052856683731079, "global_step": 553878, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.110257863998413, "global_step": 553879, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.128260850906372, "global_step": 553880, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.044050455093384, "global_step": 553881, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9772868156433105, "global_step": 553882, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0311319828033447, "global_step": 553883, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.060316801071167, "global_step": 553884, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.006908893585205, "global_step": 553885, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.049398422241211, "global_step": 553886, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.007709503173828, "global_step": 553887, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0802619457244873, "global_step": 553888, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.010471820831299, "global_step": 553889, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0847315788269043, "global_step": 553890, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.001728057861328, "global_step": 553891, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.975535273551941, "global_step": 553892, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0880351066589355, "global_step": 553893, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.978052020072937, "global_step": 553894, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.11897349357605, "global_step": 553895, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0315470695495605, "global_step": 553896, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.971691370010376, "global_step": 553897, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0393760204315186, "global_step": 553898, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.05289363861084, "global_step": 553899, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0397250652313232, "global_step": 553900, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0504558086395264, "global_step": 553901, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0974068641662598, "global_step": 553902, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.965216875076294, "global_step": 553903, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0061638355255127, "global_step": 553904, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0177712440490723, "global_step": 553905, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0516698360443115, "global_step": 553906, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9358116388320923, "global_step": 553907, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0240674018859863, "global_step": 553908, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.077348470687866, "global_step": 553909, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0202667713165283, "global_step": 553910, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9865930080413818, "global_step": 553911, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.106996774673462, "global_step": 553912, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1094815731048584, "global_step": 553913, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0114192962646484, "global_step": 553914, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.016946315765381, "global_step": 553915, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.092424154281616, "global_step": 553916, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0142693519592285, "global_step": 553917, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0402841567993164, "global_step": 553918, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.991126298904419, "global_step": 553919, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0759410858154297, "global_step": 553920, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.006197690963745, "global_step": 553921, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9531580209732056, "global_step": 553922, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9772329330444336, "global_step": 553923, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9831844568252563, "global_step": 553924, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.120586395263672, "global_step": 553925, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0034594535827637, "global_step": 553926, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0743446350097656, "global_step": 553927, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0901031494140625, "global_step": 553928, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0623409748077393, "global_step": 553929, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9903583526611328, "global_step": 553930, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0650806427001953, "global_step": 553931, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9499157667160034, "global_step": 553932, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0652568340301514, "global_step": 553933, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9856679439544678, "global_step": 553934, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0194544792175293, "global_step": 553935, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.023712158203125, "global_step": 553936, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.102590799331665, "global_step": 553937, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.954127311706543, "global_step": 553938, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0769577026367188, "global_step": 553939, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.029470920562744, "global_step": 553940, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0591976642608643, "global_step": 553941, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0753660202026367, "global_step": 553942, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0569000244140625, "global_step": 553943, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1161139011383057, "global_step": 553944, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.070927143096924, "global_step": 553945, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.003013849258423, "global_step": 553946, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0523722171783447, "global_step": 553947, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.039259672164917, "global_step": 553948, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.055972099304199, "global_step": 553949, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1237363815307617, "global_step": 553950, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9732882976531982, "global_step": 553951, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0937275886535645, "global_step": 553952, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9792146682739258, "global_step": 553953, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9583466053009033, "global_step": 553954, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.082374334335327, "global_step": 553955, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.046099901199341, "global_step": 553956, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0908358097076416, "global_step": 553957, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9161123037338257, "global_step": 553958, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.004791021347046, "global_step": 553959, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.991072654724121, "global_step": 553960, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0034782886505127, "global_step": 553961, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0096306800842285, "global_step": 553962, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9934014081954956, "global_step": 553963, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9723773002624512, "global_step": 553964, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0551211833953857, "global_step": 553965, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9851433038711548, "global_step": 553966, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9837796688079834, "global_step": 553967, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9668045043945312, "global_step": 553968, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9240363836288452, "global_step": 553969, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.95662260055542, "global_step": 553970, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.985252857208252, "global_step": 553971, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0272305011749268, "global_step": 553972, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.089134693145752, "global_step": 553973, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9827896356582642, "global_step": 553974, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0723016262054443, "global_step": 553975, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9728204011917114, "global_step": 553976, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9942058324813843, "global_step": 553977, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0441482067108154, "global_step": 553978, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0364012718200684, "global_step": 553979, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0952677726745605, "global_step": 553980, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.090637445449829, "global_step": 553981, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9419772624969482, "global_step": 553982, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0571129322052, "global_step": 553983, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.015402317047119, "global_step": 553984, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9829760789871216, "global_step": 553985, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.01733136177063, "global_step": 553986, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.043025493621826, "global_step": 553987, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.037184000015259, "global_step": 553988, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9595251083374023, "global_step": 553989, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9876070022583008, "global_step": 553990, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.014747381210327, "global_step": 553991, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0917489528656006, "global_step": 553992, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9658753871917725, "global_step": 553993, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1250498294830322, "global_step": 553994, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.059584617614746, "global_step": 553995, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9892346858978271, "global_step": 553996, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0698442459106445, "global_step": 553997, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.04858136177063, "global_step": 553998, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.084725856781006, "global_step": 553999, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.022742748260498, "global_step": 554000, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9484496116638184, "global_step": 554001, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0737686157226562, "global_step": 554002, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0128111839294434, "global_step": 554003, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.8895454406738281, "global_step": 554004, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0554730892181396, "global_step": 554005, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0438151359558105, "global_step": 554006, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0802290439605713, "global_step": 554007, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9720197916030884, "global_step": 554008, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0977485179901123, "global_step": 554009, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.8549518585205078, "global_step": 554010, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.011796236038208, "global_step": 554011, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0428357124328613, "global_step": 554012, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.022730827331543, "global_step": 554013, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.011237859725952, "global_step": 554014, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9731154441833496, "global_step": 554015, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0533571243286133, "global_step": 554016, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9983705282211304, "global_step": 554017, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.065976858139038, "global_step": 554018, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0549869537353516, "global_step": 554019, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0145857334136963, "global_step": 554020, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9403924942016602, "global_step": 554021, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0429344177246094, "global_step": 554022, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.938673496246338, "global_step": 554023, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.108245372772217, "global_step": 554024, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0689589977264404, "global_step": 554025, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9887765645980835, "global_step": 554026, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9360791444778442, "global_step": 554027, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0564510822296143, "global_step": 554028, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0646255016326904, "global_step": 554029, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0143327713012695, "global_step": 554030, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0099024772644043, "global_step": 554031, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.014524459838867, "global_step": 554032, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.013742446899414, "global_step": 554033, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.029294729232788, "global_step": 554034, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0615439414978027, "global_step": 554035, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0420758724212646, "global_step": 554036, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.072826385498047, "global_step": 554037, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.042407274246216, "global_step": 554038, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0104293823242188, "global_step": 554039, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0534939765930176, "global_step": 554040, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9260036945343018, "global_step": 554041, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9935373067855835, "global_step": 554042, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.049426317214966, "global_step": 554043, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9495073556900024, "global_step": 554044, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0141868591308594, "global_step": 554045, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9948934316635132, "global_step": 554046, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.019960403442383, "global_step": 554047, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0656638145446777, "global_step": 554048, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9480911493301392, "global_step": 554049, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.03206467628479, "global_step": 554050, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.988846778869629, "global_step": 554051, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.053936243057251, "global_step": 554052, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.038282632827759, "global_step": 554053, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0628459453582764, "global_step": 554054, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.091744899749756, "global_step": 554055, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0385217666625977, "global_step": 554056, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9028737545013428, "global_step": 554057, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.017037868499756, "global_step": 554058, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9606902599334717, "global_step": 554059, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0864927768707275, "global_step": 554060, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9504806995391846, "global_step": 554061, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0985565185546875, "global_step": 554062, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0554637908935547, "global_step": 554063, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.109400749206543, "global_step": 554064, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.948466181755066, "global_step": 554065, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9816482067108154, "global_step": 554066, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.068161964416504, "global_step": 554067, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9571248292922974, "global_step": 554068, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0608980655670166, "global_step": 554069, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.073133945465088, "global_step": 554070, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0603675842285156, "global_step": 554071, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0114452838897705, "global_step": 554072, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.029081344604492, "global_step": 554073, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9811406135559082, "global_step": 554074, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0965163707733154, "global_step": 554075, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.081852912902832, "global_step": 554076, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0146238803863525, "global_step": 554077, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.069242000579834, "global_step": 554078, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1084728240966797, "global_step": 554079, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9722774028778076, "global_step": 554080, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1156508922576904, "global_step": 554081, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1213364601135254, "global_step": 554082, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0078413486480713, "global_step": 554083, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9843865633010864, "global_step": 554084, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1312034130096436, "global_step": 554085, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9680947065353394, "global_step": 554086, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.066743850708008, "global_step": 554087, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.013544797897339, "global_step": 554088, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0245399475097656, "global_step": 554089, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.008415937423706, "global_step": 554090, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9631984233856201, "global_step": 554091, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0177783966064453, "global_step": 554092, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0016255378723145, "global_step": 554093, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.107849597930908, "global_step": 554094, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1179375648498535, "global_step": 554095, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.094485282897949, "global_step": 554096, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9664469957351685, "global_step": 554097, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0200929641723633, "global_step": 554098, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0659573078155518, "global_step": 554099, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0967142581939697, "global_step": 554100, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.012705087661743, "global_step": 554101, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0407772064208984, "global_step": 554102, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.039519786834717, "global_step": 554103, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.107788324356079, "global_step": 554104, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.048642873764038, "global_step": 554105, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.062861680984497, "global_step": 554106, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.074465751647949, "global_step": 554107, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0782408714294434, "global_step": 554108, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0654141902923584, "global_step": 554109, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0138068199157715, "global_step": 554110, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9111188650131226, "global_step": 554111, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.022277355194092, "global_step": 554112, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0251271724700928, "global_step": 554113, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9699084758758545, "global_step": 554114, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0935070514678955, "global_step": 554115, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0961389541625977, "global_step": 554116, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.047452926635742, "global_step": 554117, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9850573539733887, "global_step": 554118, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1659975051879883, "global_step": 554119, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.084956407546997, "global_step": 554120, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.952994704246521, "global_step": 554121, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.132211446762085, "global_step": 554122, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0347862243652344, "global_step": 554123, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.102940320968628, "global_step": 554124, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9791057109832764, "global_step": 554125, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.033936023712158, "global_step": 554126, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.017585515975952, "global_step": 554127, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.026151657104492, "global_step": 554128, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0181477069854736, "global_step": 554129, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0393760204315186, "global_step": 554130, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.072333812713623, "global_step": 554131, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.03886079788208, "global_step": 554132, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.013669490814209, "global_step": 554133, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.070443868637085, "global_step": 554134, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.089049816131592, "global_step": 554135, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9917521476745605, "global_step": 554136, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9646612405776978, "global_step": 554137, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0514872074127197, "global_step": 554138, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.008105754852295, "global_step": 554139, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9826942682266235, "global_step": 554140, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.063573122024536, "global_step": 554141, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.05218505859375, "global_step": 554142, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.056051731109619, "global_step": 554143, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0786447525024414, "global_step": 554144, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0390045642852783, "global_step": 554145, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.121241331100464, "global_step": 554146, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.000614643096924, "global_step": 554147, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.054934501647949, "global_step": 554148, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0244672298431396, "global_step": 554149, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0011777877807617, "global_step": 554150, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0432679653167725, "global_step": 554151, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9579591751098633, "global_step": 554152, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9922175407409668, "global_step": 554153, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9776376485824585, "global_step": 554154, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0737063884735107, "global_step": 554155, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0389604568481445, "global_step": 554156, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.058966636657715, "global_step": 554157, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0958755016326904, "global_step": 554158, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9631141424179077, "global_step": 554159, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9954123497009277, "global_step": 554160, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9562053680419922, "global_step": 554161, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0723581314086914, "global_step": 554162, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0978362560272217, "global_step": 554163, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0662636756896973, "global_step": 554164, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.037123203277588, "global_step": 554165, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.083052635192871, "global_step": 554166, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0895917415618896, "global_step": 554167, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.039170980453491, "global_step": 554168, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0214743614196777, "global_step": 554169, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0332322120666504, "global_step": 554170, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.002155065536499, "global_step": 554171, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0744330883026123, "global_step": 554172, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0059585571289062, "global_step": 554173, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0804708003997803, "global_step": 554174, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.081599712371826, "global_step": 554175, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0291788578033447, "global_step": 554176, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.147733211517334, "global_step": 554177, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0403618812561035, "global_step": 554178, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0742413997650146, "global_step": 554179, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9799922704696655, "global_step": 554180, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.039853096008301, "global_step": 554181, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.056480884552002, "global_step": 554182, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0348196029663086, "global_step": 554183, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.082643747329712, "global_step": 554184, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.005873918533325, "global_step": 554185, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.055760145187378, "global_step": 554186, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9764326810836792, "global_step": 554187, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0203135013580322, "global_step": 554188, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.097771644592285, "global_step": 554189, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0056896209716797, "global_step": 554190, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9536994695663452, "global_step": 554191, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0828795433044434, "global_step": 554192, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.984732985496521, "global_step": 554193, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9325412511825562, "global_step": 554194, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9250036478042603, "global_step": 554195, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0909438133239746, "global_step": 554196, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9927774667739868, "global_step": 554197, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.066559314727783, "global_step": 554198, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.03645658493042, "global_step": 554199, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1149213314056396, "global_step": 554200, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.973160982131958, "global_step": 554201, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0606703758239746, "global_step": 554202, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.042224884033203, "global_step": 554203, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.007680654525757, "global_step": 554204, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9515379667282104, "global_step": 554205, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.968632698059082, "global_step": 554206, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0481224060058594, "global_step": 554207, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1008827686309814, "global_step": 554208, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0193471908569336, "global_step": 554209, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0671398639678955, "global_step": 554210, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0168797969818115, "global_step": 554211, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.143266439437866, "global_step": 554212, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0467982292175293, "global_step": 554213, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0224385261535645, "global_step": 554214, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9735580682754517, "global_step": 554215, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0495314598083496, "global_step": 554216, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0064094066619873, "global_step": 554217, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0690176486968994, "global_step": 554218, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.038954734802246, "global_step": 554219, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0503427982330322, "global_step": 554220, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.096923828125, "global_step": 554221, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9573886394500732, "global_step": 554222, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1289849281311035, "global_step": 554223, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0971240997314453, "global_step": 554224, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.065896987915039, "global_step": 554225, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.033757209777832, "global_step": 554226, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1030051708221436, "global_step": 554227, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9877992868423462, "global_step": 554228, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0923876762390137, "global_step": 554229, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9638798236846924, "global_step": 554230, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0700724124908447, "global_step": 554231, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1012144088745117, "global_step": 554232, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9284578561782837, "global_step": 554233, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.125833034515381, "global_step": 554234, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.069291114807129, "global_step": 554235, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0281810760498047, "global_step": 554236, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9888900518417358, "global_step": 554237, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.129290819168091, "global_step": 554238, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.000689744949341, "global_step": 554239, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0934152603149414, "global_step": 554240, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0396339893341064, "global_step": 554241, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9858378171920776, "global_step": 554242, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0024471282958984, "global_step": 554243, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.060248374938965, "global_step": 554244, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9553658962249756, "global_step": 554245, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.003018856048584, "global_step": 554246, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0898962020874023, "global_step": 554247, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0265398025512695, "global_step": 554248, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.074000120162964, "global_step": 554249, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0544285774230957, "global_step": 554250, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9806748628616333, "global_step": 554251, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.024209976196289, "global_step": 554252, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.043604850769043, "global_step": 554253, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0165493488311768, "global_step": 554254, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9404466152191162, "global_step": 554255, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0522007942199707, "global_step": 554256, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.162170171737671, "global_step": 554257, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0563764572143555, "global_step": 554258, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0752103328704834, "global_step": 554259, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0640292167663574, "global_step": 554260, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0383691787719727, "global_step": 554261, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0340983867645264, "global_step": 554262, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0551435947418213, "global_step": 554263, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0210111141204834, "global_step": 554264, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9672589302062988, "global_step": 554265, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0349388122558594, "global_step": 554266, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0413544178009033, "global_step": 554267, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0423452854156494, "global_step": 554268, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1225335597991943, "global_step": 554269, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0551044940948486, "global_step": 554270, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.068450927734375, "global_step": 554271, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0411465167999268, "global_step": 554272, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0501391887664795, "global_step": 554273, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0191547870635986, "global_step": 554274, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.991243839263916, "global_step": 554275, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0637850761413574, "global_step": 554276, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.180380344390869, "global_step": 554277, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0245492458343506, "global_step": 554278, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0814032554626465, "global_step": 554279, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.072613000869751, "global_step": 554280, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9799469709396362, "global_step": 554281, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.038699150085449, "global_step": 554282, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0959582328796387, "global_step": 554283, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.033622980117798, "global_step": 554284, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.038408041000366, "global_step": 554285, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.050575017929077, "global_step": 554286, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9660464525222778, "global_step": 554287, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.012820243835449, "global_step": 554288, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0086371898651123, "global_step": 554289, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.995140790939331, "global_step": 554290, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0509121417999268, "global_step": 554291, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.028493642807007, "global_step": 554292, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.963077187538147, "global_step": 554293, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.055018663406372, "global_step": 554294, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.136707067489624, "global_step": 554295, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.155478000640869, "global_step": 554296, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.083859920501709, "global_step": 554297, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0456509590148926, "global_step": 554298, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0131478309631348, "global_step": 554299, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9453153610229492, "global_step": 554300, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0849008560180664, "global_step": 554301, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0968384742736816, "global_step": 554302, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0347237586975098, "global_step": 554303, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0528564453125, "global_step": 554304, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0940072536468506, "global_step": 554305, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9922317266464233, "global_step": 554306, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.021188974380493, "global_step": 554307, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.102123737335205, "global_step": 554308, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.06744122505188, "global_step": 554309, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.076746702194214, "global_step": 554310, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1279304027557373, "global_step": 554311, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0142500400543213, "global_step": 554312, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0209569931030273, "global_step": 554313, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.07023549079895, "global_step": 554314, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9569653272628784, "global_step": 554315, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.015866994857788, "global_step": 554316, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0676283836364746, "global_step": 554317, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0291547775268555, "global_step": 554318, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0937492847442627, "global_step": 554319, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0934481620788574, "global_step": 554320, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.038419246673584, "global_step": 554321, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.992516040802002, "global_step": 554322, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.056922197341919, "global_step": 554323, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9862234592437744, "global_step": 554324, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.986830472946167, "global_step": 554325, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9680434465408325, "global_step": 554326, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.923844814300537, "global_step": 554327, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.067437171936035, "global_step": 554328, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0028698444366455, "global_step": 554329, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.062548875808716, "global_step": 554330, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.066962957382202, "global_step": 554331, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9677064418792725, "global_step": 554332, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9970412254333496, "global_step": 554333, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.992067575454712, "global_step": 554334, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0434327125549316, "global_step": 554335, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.8924496173858643, "global_step": 554336, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.044261932373047, "global_step": 554337, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0114128589630127, "global_step": 554338, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0493791103363037, "global_step": 554339, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.015519857406616, "global_step": 554340, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0994603633880615, "global_step": 554341, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0517032146453857, "global_step": 554342, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.088108777999878, "global_step": 554343, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.069113254547119, "global_step": 554344, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0497679710388184, "global_step": 554345, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.066896438598633, "global_step": 554346, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.006503105163574, "global_step": 554347, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.102461338043213, "global_step": 554348, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0924859046936035, "global_step": 554349, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1159868240356445, "global_step": 554350, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.019958019256592, "global_step": 554351, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9806643724441528, "global_step": 554352, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0266165733337402, "global_step": 554353, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0214366912841797, "global_step": 554354, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9888299703598022, "global_step": 554355, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0362818241119385, "global_step": 554356, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.051023483276367, "global_step": 554357, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0463287830352783, "global_step": 554358, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0431888103485107, "global_step": 554359, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1069495677948, "global_step": 554360, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0715200901031494, "global_step": 554361, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.029228448867798, "global_step": 554362, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.035935878753662, "global_step": 554363, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.988986611366272, "global_step": 554364, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0385398864746094, "global_step": 554365, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9583122730255127, "global_step": 554366, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.140174388885498, "global_step": 554367, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0659539699554443, "global_step": 554368, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.074434280395508, "global_step": 554369, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.068594455718994, "global_step": 554370, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0635063648223877, "global_step": 554371, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0232417583465576, "global_step": 554372, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.066448926925659, "global_step": 554373, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0082552433013916, "global_step": 554374, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0510964393615723, "global_step": 554375, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.080328941345215, "global_step": 554376, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.054304838180542, "global_step": 554377, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.017503261566162, "global_step": 554378, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.020266532897949, "global_step": 554379, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9995235204696655, "global_step": 554380, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1277408599853516, "global_step": 554381, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9892948865890503, "global_step": 554382, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0361032485961914, "global_step": 554383, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.040365219116211, "global_step": 554384, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.1159000396728516, "global_step": 554385, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.041508674621582, "global_step": 554386, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.049708604812622, "global_step": 554387, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9787652492523193, "global_step": 554388, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.110078811645508, "global_step": 554389, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.908245325088501, "global_step": 554390, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.204338550567627, "global_step": 554391, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9839993715286255, "global_step": 554392, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0337610244750977, "global_step": 554393, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9739949703216553, "global_step": 554394, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0274250507354736, "global_step": 554395, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.003077507019043, "global_step": 554396, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.976506233215332, "global_step": 554397, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.021843433380127, "global_step": 554398, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.058919906616211, "global_step": 554399, "epoch": 921, "lr": 5e-05}
{"train_loss": 2.0294687747955322, "global_step": 554400, "epoch": 921, "lr": 5e-05}
{"train_loss": 1.9868111610412598, "global_step": 554401, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9436275959014893, "global_step": 554402, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0845396518707275, "global_step": 554403, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0489189624786377, "global_step": 554404, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.89826238155365, "global_step": 554405, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9701286554336548, "global_step": 554406, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.043083906173706, "global_step": 554407, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.014810085296631, "global_step": 554408, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9915796518325806, "global_step": 554409, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9923920631408691, "global_step": 554410, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.034820795059204, "global_step": 554411, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.053056240081787, "global_step": 554412, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0273969173431396, "global_step": 554413, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0271711349487305, "global_step": 554414, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.059652090072632, "global_step": 554415, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0666017532348633, "global_step": 554416, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0257561206817627, "global_step": 554417, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.009908676147461, "global_step": 554418, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.054413080215454, "global_step": 554419, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.026794195175171, "global_step": 554420, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.078310489654541, "global_step": 554421, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0577809810638428, "global_step": 554422, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0258891582489014, "global_step": 554423, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9780040979385376, "global_step": 554424, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0173065662384033, "global_step": 554425, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.058199882507324, "global_step": 554426, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.984505295753479, "global_step": 554427, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.951413869857788, "global_step": 554428, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.953671932220459, "global_step": 554429, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1264140605926514, "global_step": 554430, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9885989427566528, "global_step": 554431, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0363686084747314, "global_step": 554432, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.8995953798294067, "global_step": 554433, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0156733989715576, "global_step": 554434, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0102412700653076, "global_step": 554435, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0838544368743896, "global_step": 554436, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.036708116531372, "global_step": 554437, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9871010780334473, "global_step": 554438, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9927699565887451, "global_step": 554439, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0394287109375, "global_step": 554440, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0257649421691895, "global_step": 554441, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0690345764160156, "global_step": 554442, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.949582576751709, "global_step": 554443, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.020221710205078, "global_step": 554444, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.003201961517334, "global_step": 554445, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0597586631774902, "global_step": 554446, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.991984248161316, "global_step": 554447, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.055452585220337, "global_step": 554448, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0059332847595215, "global_step": 554449, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0355372428894043, "global_step": 554450, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0649991035461426, "global_step": 554451, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.019611120223999, "global_step": 554452, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0357296466827393, "global_step": 554453, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9929394721984863, "global_step": 554454, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0207908153533936, "global_step": 554455, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9798345565795898, "global_step": 554456, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9741183519363403, "global_step": 554457, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9852094650268555, "global_step": 554458, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.096137285232544, "global_step": 554459, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0040297508239746, "global_step": 554460, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.026357650756836, "global_step": 554461, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9957201480865479, "global_step": 554462, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9932156801223755, "global_step": 554463, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.105706214904785, "global_step": 554464, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.041527271270752, "global_step": 554465, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1132142543792725, "global_step": 554466, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0771970748901367, "global_step": 554467, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1666176319122314, "global_step": 554468, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9845383167266846, "global_step": 554469, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.062251567840576, "global_step": 554470, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0572922229766846, "global_step": 554471, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0590224266052246, "global_step": 554472, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0460121631622314, "global_step": 554473, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0186045169830322, "global_step": 554474, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9703764915466309, "global_step": 554475, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0904691219329834, "global_step": 554476, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0744338035583496, "global_step": 554477, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.940898060798645, "global_step": 554478, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.051649808883667, "global_step": 554479, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9957526922225952, "global_step": 554480, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0515785217285156, "global_step": 554481, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0526561737060547, "global_step": 554482, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0456275939941406, "global_step": 554483, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0880284309387207, "global_step": 554484, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0382232666015625, "global_step": 554485, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9950350522994995, "global_step": 554486, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9982491731643677, "global_step": 554487, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.926600694656372, "global_step": 554488, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0819218158721924, "global_step": 554489, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.01383376121521, "global_step": 554490, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9996732473373413, "global_step": 554491, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.978564739227295, "global_step": 554492, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9745094776153564, "global_step": 554493, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0043492317199707, "global_step": 554494, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.044644594192505, "global_step": 554495, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0968918800354004, "global_step": 554496, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0181663036346436, "global_step": 554497, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0277042388916016, "global_step": 554498, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9323935508728027, "global_step": 554499, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0366640090942383, "global_step": 554500, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9884963035583496, "global_step": 554501, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9830682277679443, "global_step": 554502, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0512354373931885, "global_step": 554503, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0228219032287598, "global_step": 554504, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9836699962615967, "global_step": 554505, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.02561616897583, "global_step": 554506, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0441832542419434, "global_step": 554507, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0440821647644043, "global_step": 554508, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1154415607452393, "global_step": 554509, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.073216438293457, "global_step": 554510, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.129990816116333, "global_step": 554511, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.003509283065796, "global_step": 554512, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0010414123535156, "global_step": 554513, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.061366081237793, "global_step": 554514, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1138827800750732, "global_step": 554515, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9672589302062988, "global_step": 554516, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1219687461853027, "global_step": 554517, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0158474445343018, "global_step": 554518, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9719269275665283, "global_step": 554519, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0215911865234375, "global_step": 554520, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9872673749923706, "global_step": 554521, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0607357025146484, "global_step": 554522, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.928606390953064, "global_step": 554523, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9954203367233276, "global_step": 554524, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.926059365272522, "global_step": 554525, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.037153720855713, "global_step": 554526, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0145058631896973, "global_step": 554527, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9593536853790283, "global_step": 554528, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9802147150039673, "global_step": 554529, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0787341594696045, "global_step": 554530, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9437263011932373, "global_step": 554531, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.986182689666748, "global_step": 554532, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.021247625350952, "global_step": 554533, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0530200004577637, "global_step": 554534, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0525903701782227, "global_step": 554535, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9552953243255615, "global_step": 554536, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0524535179138184, "global_step": 554537, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0453379154205322, "global_step": 554538, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0111024379730225, "global_step": 554539, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0939905643463135, "global_step": 554540, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9766863584518433, "global_step": 554541, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.996863842010498, "global_step": 554542, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.978489875793457, "global_step": 554543, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9945932626724243, "global_step": 554544, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1064231395721436, "global_step": 554545, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0249929428100586, "global_step": 554546, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9760267734527588, "global_step": 554547, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.073126792907715, "global_step": 554548, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9918344020843506, "global_step": 554549, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0164566040039062, "global_step": 554550, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9632925987243652, "global_step": 554551, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0095272064208984, "global_step": 554552, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9895298480987549, "global_step": 554553, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9816639423370361, "global_step": 554554, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9908229112625122, "global_step": 554555, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0458948612213135, "global_step": 554556, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0884242057800293, "global_step": 554557, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.027740240097046, "global_step": 554558, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0419530868530273, "global_step": 554559, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0051534175872803, "global_step": 554560, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0139095783233643, "global_step": 554561, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.988389253616333, "global_step": 554562, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0891685485839844, "global_step": 554563, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.069967269897461, "global_step": 554564, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.970088005065918, "global_step": 554565, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0114245414733887, "global_step": 554566, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0322234630584717, "global_step": 554567, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.135125160217285, "global_step": 554568, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.023174524307251, "global_step": 554569, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.005492925643921, "global_step": 554570, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0301926136016846, "global_step": 554571, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0436558723449707, "global_step": 554572, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9792790412902832, "global_step": 554573, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.930037021636963, "global_step": 554574, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0932538509368896, "global_step": 554575, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.113967180252075, "global_step": 554576, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.062060594558716, "global_step": 554577, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.058438539505005, "global_step": 554578, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.95424485206604, "global_step": 554579, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.026726007461548, "global_step": 554580, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9447696208953857, "global_step": 554581, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9301830530166626, "global_step": 554582, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.053926467895508, "global_step": 554583, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0324785709381104, "global_step": 554584, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.091519832611084, "global_step": 554585, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9802416563034058, "global_step": 554586, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.925597906112671, "global_step": 554587, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0354974269866943, "global_step": 554588, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9511997699737549, "global_step": 554589, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0204741954803467, "global_step": 554590, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9787309169769287, "global_step": 554591, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9923338890075684, "global_step": 554592, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9810158014297485, "global_step": 554593, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9329501390457153, "global_step": 554594, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9846739768981934, "global_step": 554595, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.941372036933899, "global_step": 554596, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.024168014526367, "global_step": 554597, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9601835012435913, "global_step": 554598, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0026466846466064, "global_step": 554599, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.05142879486084, "global_step": 554600, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0864627361297607, "global_step": 554601, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.034165382385254, "global_step": 554602, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0643789768218994, "global_step": 554603, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.971384882926941, "global_step": 554604, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.072183609008789, "global_step": 554605, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.019955635070801, "global_step": 554606, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9982736110687256, "global_step": 554607, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.084867000579834, "global_step": 554608, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9768837690353394, "global_step": 554609, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.077638626098633, "global_step": 554610, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0112195014953613, "global_step": 554611, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9660229682922363, "global_step": 554612, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.075254201889038, "global_step": 554613, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9765312671661377, "global_step": 554614, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1067893505096436, "global_step": 554615, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.009558916091919, "global_step": 554616, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.980380892753601, "global_step": 554617, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.027738332748413, "global_step": 554618, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0603134632110596, "global_step": 554619, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0057435035705566, "global_step": 554620, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.998997688293457, "global_step": 554621, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.044671058654785, "global_step": 554622, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.044814348220825, "global_step": 554623, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9829328060150146, "global_step": 554624, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.957065463066101, "global_step": 554625, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.049229383468628, "global_step": 554626, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.006089925765991, "global_step": 554627, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0202221870422363, "global_step": 554628, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9968390464782715, "global_step": 554629, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0310120582580566, "global_step": 554630, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.002383232116699, "global_step": 554631, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.079392194747925, "global_step": 554632, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.046259641647339, "global_step": 554633, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0084738731384277, "global_step": 554634, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0423667430877686, "global_step": 554635, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.979227066040039, "global_step": 554636, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0314645767211914, "global_step": 554637, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0273592472076416, "global_step": 554638, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0385191440582275, "global_step": 554639, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.05220103263855, "global_step": 554640, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.033907651901245, "global_step": 554641, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9843471050262451, "global_step": 554642, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0428736209869385, "global_step": 554643, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.052109479904175, "global_step": 554644, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.054990530014038, "global_step": 554645, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.004460096359253, "global_step": 554646, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9753401279449463, "global_step": 554647, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0120959281921387, "global_step": 554648, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.040530204772949, "global_step": 554649, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0158803462982178, "global_step": 554650, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.953168511390686, "global_step": 554651, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.991235613822937, "global_step": 554652, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0173394680023193, "global_step": 554653, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9907759428024292, "global_step": 554654, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9985160827636719, "global_step": 554655, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0596539974212646, "global_step": 554656, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.051302909851074, "global_step": 554657, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.011876106262207, "global_step": 554658, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0861034393310547, "global_step": 554659, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0396881103515625, "global_step": 554660, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0234763622283936, "global_step": 554661, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9390318393707275, "global_step": 554662, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0153956413269043, "global_step": 554663, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.070587158203125, "global_step": 554664, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0431010723114014, "global_step": 554665, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.977004885673523, "global_step": 554666, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.060072898864746, "global_step": 554667, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9136978387832642, "global_step": 554668, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.111074686050415, "global_step": 554669, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0323190689086914, "global_step": 554670, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0197439193725586, "global_step": 554671, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.948088526725769, "global_step": 554672, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.062202215194702, "global_step": 554673, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.054400682449341, "global_step": 554674, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0902299880981445, "global_step": 554675, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.072394847869873, "global_step": 554676, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9334132671356201, "global_step": 554677, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0489163398742676, "global_step": 554678, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0068295001983643, "global_step": 554679, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0112478733062744, "global_step": 554680, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0564825534820557, "global_step": 554681, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9937772750854492, "global_step": 554682, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0862486362457275, "global_step": 554683, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9978628158569336, "global_step": 554684, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.021259069442749, "global_step": 554685, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.10390305519104, "global_step": 554686, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0414280891418457, "global_step": 554687, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.016658067703247, "global_step": 554688, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0871357917785645, "global_step": 554689, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9942525625228882, "global_step": 554690, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0237174034118652, "global_step": 554691, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9748458862304688, "global_step": 554692, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1478724479675293, "global_step": 554693, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0631425380706787, "global_step": 554694, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0320804119110107, "global_step": 554695, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9662965536117554, "global_step": 554696, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0192790031433105, "global_step": 554697, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9783724546432495, "global_step": 554698, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0376665592193604, "global_step": 554699, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1052494049072266, "global_step": 554700, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9862396717071533, "global_step": 554701, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.944528579711914, "global_step": 554702, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0151116847991943, "global_step": 554703, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0533652305603027, "global_step": 554704, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.041358470916748, "global_step": 554705, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0425877571105957, "global_step": 554706, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0195486545562744, "global_step": 554707, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9215378761291504, "global_step": 554708, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.001978874206543, "global_step": 554709, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0243043899536133, "global_step": 554710, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.032968044281006, "global_step": 554711, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9909698963165283, "global_step": 554712, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.022526979446411, "global_step": 554713, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1567115783691406, "global_step": 554714, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9995312690734863, "global_step": 554715, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0759596824645996, "global_step": 554716, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.978589653968811, "global_step": 554717, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.076239824295044, "global_step": 554718, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0276079177856445, "global_step": 554719, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.042127847671509, "global_step": 554720, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9674208164215088, "global_step": 554721, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.015699625015259, "global_step": 554722, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9516654014587402, "global_step": 554723, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9844883680343628, "global_step": 554724, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0806071758270264, "global_step": 554725, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.092440366744995, "global_step": 554726, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.040821075439453, "global_step": 554727, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0245959758758545, "global_step": 554728, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0741281509399414, "global_step": 554729, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0011048316955566, "global_step": 554730, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0690958499908447, "global_step": 554731, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.056567430496216, "global_step": 554732, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0118422508239746, "global_step": 554733, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.022686243057251, "global_step": 554734, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9650306701660156, "global_step": 554735, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0574276447296143, "global_step": 554736, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.043776512145996, "global_step": 554737, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.877777338027954, "global_step": 554738, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.038478374481201, "global_step": 554739, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0867421627044678, "global_step": 554740, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9977415800094604, "global_step": 554741, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.012427806854248, "global_step": 554742, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.044978618621826, "global_step": 554743, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.029600143432617, "global_step": 554744, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.94102144241333, "global_step": 554745, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9947571754455566, "global_step": 554746, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0887696743011475, "global_step": 554747, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9823864698410034, "global_step": 554748, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0946342945098877, "global_step": 554749, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0051627159118652, "global_step": 554750, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.022477149963379, "global_step": 554751, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.070760726928711, "global_step": 554752, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.076442003250122, "global_step": 554753, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9597210884094238, "global_step": 554754, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.064305305480957, "global_step": 554755, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.017507553100586, "global_step": 554756, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.013753890991211, "global_step": 554757, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9945605993270874, "global_step": 554758, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9457720518112183, "global_step": 554759, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1070945262908936, "global_step": 554760, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.02176833152771, "global_step": 554761, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.006849765777588, "global_step": 554762, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9233156442642212, "global_step": 554763, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.889784812927246, "global_step": 554764, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0284790992736816, "global_step": 554765, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0648062229156494, "global_step": 554766, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.005101203918457, "global_step": 554767, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9809389114379883, "global_step": 554768, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9853665828704834, "global_step": 554769, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0864059925079346, "global_step": 554770, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0394163131713867, "global_step": 554771, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.018362522125244, "global_step": 554772, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0147080421447754, "global_step": 554773, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0165982246398926, "global_step": 554774, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9938926696777344, "global_step": 554775, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.936477541923523, "global_step": 554776, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0799500942230225, "global_step": 554777, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0319106578826904, "global_step": 554778, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.938038945198059, "global_step": 554779, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0198402404785156, "global_step": 554780, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0364181995391846, "global_step": 554781, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.026228189468384, "global_step": 554782, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1033663749694824, "global_step": 554783, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0165088176727295, "global_step": 554784, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0557775497436523, "global_step": 554785, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.04848051071167, "global_step": 554786, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9508432149887085, "global_step": 554787, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0484321117401123, "global_step": 554788, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.06209659576416, "global_step": 554789, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.046715259552002, "global_step": 554790, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.061417579650879, "global_step": 554791, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0612406730651855, "global_step": 554792, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0726473331451416, "global_step": 554793, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.990315318107605, "global_step": 554794, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0082550048828125, "global_step": 554795, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9643669128417969, "global_step": 554796, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0326995849609375, "global_step": 554797, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.053276777267456, "global_step": 554798, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9720122814178467, "global_step": 554799, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0849530696868896, "global_step": 554800, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9771512746810913, "global_step": 554801, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9373961687088013, "global_step": 554802, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9520851373672485, "global_step": 554803, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.021252393722534, "global_step": 554804, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0690741539001465, "global_step": 554805, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9624847173690796, "global_step": 554806, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9550693035125732, "global_step": 554807, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.052083969116211, "global_step": 554808, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9778761863708496, "global_step": 554809, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0756421089172363, "global_step": 554810, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.031381368637085, "global_step": 554811, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.072321891784668, "global_step": 554812, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.060211420059204, "global_step": 554813, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.013658046722412, "global_step": 554814, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.043273448944092, "global_step": 554815, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.114957571029663, "global_step": 554816, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.030003070831299, "global_step": 554817, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.094655990600586, "global_step": 554818, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.024181365966797, "global_step": 554819, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0145039558410645, "global_step": 554820, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.098832368850708, "global_step": 554821, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0464301109313965, "global_step": 554822, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0698471069335938, "global_step": 554823, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9948976039886475, "global_step": 554824, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.078383207321167, "global_step": 554825, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9780782461166382, "global_step": 554826, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0142507553100586, "global_step": 554827, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.033602237701416, "global_step": 554828, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.10939621925354, "global_step": 554829, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0493364334106445, "global_step": 554830, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9849512577056885, "global_step": 554831, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9350135326385498, "global_step": 554832, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0031936168670654, "global_step": 554833, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0724353790283203, "global_step": 554834, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0254392623901367, "global_step": 554835, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.999851942062378, "global_step": 554836, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.023566246032715, "global_step": 554837, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9091050624847412, "global_step": 554838, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.046539068222046, "global_step": 554839, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0104176998138428, "global_step": 554840, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.032010793685913, "global_step": 554841, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0358691215515137, "global_step": 554842, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0055081844329834, "global_step": 554843, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.016672134399414, "global_step": 554844, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9645278453826904, "global_step": 554845, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.043009042739868, "global_step": 554846, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.155656099319458, "global_step": 554847, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9782577753067017, "global_step": 554848, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.025334596633911, "global_step": 554849, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0507612228393555, "global_step": 554850, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0426583290100098, "global_step": 554851, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9599108695983887, "global_step": 554852, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0849828720092773, "global_step": 554853, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.001970052719116, "global_step": 554854, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.92877197265625, "global_step": 554855, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.988217830657959, "global_step": 554856, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9584739208221436, "global_step": 554857, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0676040649414062, "global_step": 554858, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.968328595161438, "global_step": 554859, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.188770294189453, "global_step": 554860, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0697872638702393, "global_step": 554861, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.019742488861084, "global_step": 554862, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.075714588165283, "global_step": 554863, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0028772354125977, "global_step": 554864, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.027693271636963, "global_step": 554865, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9464538097381592, "global_step": 554866, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1238460540771484, "global_step": 554867, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.045294761657715, "global_step": 554868, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0151760578155518, "global_step": 554869, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9514710903167725, "global_step": 554870, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.061086654663086, "global_step": 554871, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9908686876296997, "global_step": 554872, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.065770387649536, "global_step": 554873, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0958476066589355, "global_step": 554874, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0402071475982666, "global_step": 554875, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.053617477416992, "global_step": 554876, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0989322662353516, "global_step": 554877, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0058586597442627, "global_step": 554878, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1101608276367188, "global_step": 554879, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.032216787338257, "global_step": 554880, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9863760471343994, "global_step": 554881, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.093048095703125, "global_step": 554882, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.036639928817749, "global_step": 554883, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.917781949043274, "global_step": 554884, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0435702800750732, "global_step": 554885, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.018129587173462, "global_step": 554886, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.033975124359131, "global_step": 554887, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.043367385864258, "global_step": 554888, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.07305908203125, "global_step": 554889, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0053279399871826, "global_step": 554890, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0012009143829346, "global_step": 554891, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0101029872894287, "global_step": 554892, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0387110710144043, "global_step": 554893, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0006234645843506, "global_step": 554894, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1308319568634033, "global_step": 554895, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0184755325317383, "global_step": 554896, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.038853168487549, "global_step": 554897, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.922777533531189, "global_step": 554898, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9969538450241089, "global_step": 554899, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0315911769866943, "global_step": 554900, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.127532958984375, "global_step": 554901, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.006969928741455, "global_step": 554902, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0437636375427246, "global_step": 554903, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.034717321395874, "global_step": 554904, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.988736629486084, "global_step": 554905, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9526985883712769, "global_step": 554906, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.015693187713623, "global_step": 554907, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.027006149291992, "global_step": 554908, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.043586492538452, "global_step": 554909, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9895280599594116, "global_step": 554910, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9970605373382568, "global_step": 554911, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.01155161857605, "global_step": 554912, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9822211265563965, "global_step": 554913, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9967660903930664, "global_step": 554914, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.073103904724121, "global_step": 554915, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0868000984191895, "global_step": 554916, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0445895195007324, "global_step": 554917, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.058664321899414, "global_step": 554918, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0528147220611572, "global_step": 554919, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0796585083007812, "global_step": 554920, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0411574840545654, "global_step": 554921, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.966971516609192, "global_step": 554922, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.046006917953491, "global_step": 554923, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9563452005386353, "global_step": 554924, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9774576425552368, "global_step": 554925, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.034106969833374, "global_step": 554926, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9856246709823608, "global_step": 554927, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.92844557762146, "global_step": 554928, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.950689435005188, "global_step": 554929, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9482535123825073, "global_step": 554930, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0571177005767822, "global_step": 554931, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.032316207885742, "global_step": 554932, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.000359296798706, "global_step": 554933, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.067859649658203, "global_step": 554934, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.066112518310547, "global_step": 554935, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.97213613986969, "global_step": 554936, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0556960105895996, "global_step": 554937, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0361273288726807, "global_step": 554938, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.011573076248169, "global_step": 554939, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0291459560394287, "global_step": 554940, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.070218324661255, "global_step": 554941, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.992423415184021, "global_step": 554942, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0048320293426514, "global_step": 554943, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9644067287445068, "global_step": 554944, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.01865553855896, "global_step": 554945, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9957964420318604, "global_step": 554946, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.974371075630188, "global_step": 554947, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0246076583862305, "global_step": 554948, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.038614511489868, "global_step": 554949, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9481675624847412, "global_step": 554950, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.035879373550415, "global_step": 554951, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0010905265808105, "global_step": 554952, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.096052646636963, "global_step": 554953, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0221662521362305, "global_step": 554954, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0583908557891846, "global_step": 554955, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0683727264404297, "global_step": 554956, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1047379970550537, "global_step": 554957, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9399734735488892, "global_step": 554958, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1464014053344727, "global_step": 554959, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.021439552307129, "global_step": 554960, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.057983875274658, "global_step": 554961, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.031933307647705, "global_step": 554962, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.047051429748535, "global_step": 554963, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0356431007385254, "global_step": 554964, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0706892013549805, "global_step": 554965, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.074827194213867, "global_step": 554966, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0761215686798096, "global_step": 554967, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.000382900238037, "global_step": 554968, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.007704257965088, "global_step": 554969, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.070815086364746, "global_step": 554970, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.019998550415039, "global_step": 554971, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9941540956497192, "global_step": 554972, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.072070360183716, "global_step": 554973, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.024718999862671, "global_step": 554974, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.00523042678833, "global_step": 554975, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.98874032497406, "global_step": 554976, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9918475151062012, "global_step": 554977, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0333497524261475, "global_step": 554978, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9720226526260376, "global_step": 554979, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.005478620529175, "global_step": 554980, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.056966781616211, "global_step": 554981, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.077902317047119, "global_step": 554982, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0292510986328125, "global_step": 554983, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9921226501464844, "global_step": 554984, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.117806911468506, "global_step": 554985, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9801205396652222, "global_step": 554986, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.009007692337036, "global_step": 554987, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0136778354644775, "global_step": 554988, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0489308834075928, "global_step": 554989, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.058030366897583, "global_step": 554990, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.033252239227295, "global_step": 554991, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.091306209564209, "global_step": 554992, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9777129888534546, "global_step": 554993, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0632498264312744, "global_step": 554994, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.062973737716675, "global_step": 554995, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0469679832458496, "global_step": 554996, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0113747119903564, "global_step": 554997, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0295040607452393, "global_step": 554998, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.08988881111145, "global_step": 554999, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0483486652374268, "global_step": 555000, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.043280839920044, "global_step": 555001, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0002381801605225, "global_step": 555002, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9890000820159912, "global_step": 555003, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0191192626953125, "global_step": 555004, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0280935764312744, "global_step": 555005, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9546692371368408, "global_step": 555006, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.022787570953369, "global_step": 555007, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0934293270111084, "global_step": 555008, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9952565431594849, "global_step": 555009, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1119792461395264, "global_step": 555010, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.053199291229248, "global_step": 555011, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.129396677017212, "global_step": 555012, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.157626152038574, "global_step": 555013, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0141069889068604, "global_step": 555014, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.029233932495117, "global_step": 555015, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1543641090393066, "global_step": 555016, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0733442306518555, "global_step": 555017, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.014773368835449, "global_step": 555018, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0137698650360107, "global_step": 555019, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.020904064178467, "global_step": 555020, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.059626817703247, "global_step": 555021, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0298707485198975, "global_step": 555022, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.074693202972412, "global_step": 555023, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.062448024749756, "global_step": 555024, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.058565139770508, "global_step": 555025, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.911441683769226, "global_step": 555026, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.112046241760254, "global_step": 555027, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0098304748535156, "global_step": 555028, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9744479656219482, "global_step": 555029, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0220038890838623, "global_step": 555030, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.016969680786133, "global_step": 555031, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9892125129699707, "global_step": 555032, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.065481662750244, "global_step": 555033, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9805970191955566, "global_step": 555034, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0145862102508545, "global_step": 555035, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9479061365127563, "global_step": 555036, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.074096202850342, "global_step": 555037, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0631585121154785, "global_step": 555038, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.006941556930542, "global_step": 555039, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0028717517852783, "global_step": 555040, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0552427768707275, "global_step": 555041, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0434205532073975, "global_step": 555042, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9377866983413696, "global_step": 555043, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0580408573150635, "global_step": 555044, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0040042400360107, "global_step": 555045, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9705440998077393, "global_step": 555046, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0348660945892334, "global_step": 555047, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0267879962921143, "global_step": 555048, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9531773328781128, "global_step": 555049, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9912935495376587, "global_step": 555050, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.014233350753784, "global_step": 555051, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9862412214279175, "global_step": 555052, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9665377140045166, "global_step": 555053, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.08009672164917, "global_step": 555054, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9952301979064941, "global_step": 555055, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9827722311019897, "global_step": 555056, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9600224494934082, "global_step": 555057, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0319197177886963, "global_step": 555058, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9183554649353027, "global_step": 555059, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0586633682250977, "global_step": 555060, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.029463291168213, "global_step": 555061, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9779654741287231, "global_step": 555062, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.133317232131958, "global_step": 555063, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0659825801849365, "global_step": 555064, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.096717357635498, "global_step": 555065, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.044494152069092, "global_step": 555066, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.044935703277588, "global_step": 555067, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.962899923324585, "global_step": 555068, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0542263984680176, "global_step": 555069, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.007432222366333, "global_step": 555070, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.026649236679077, "global_step": 555071, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9903115034103394, "global_step": 555072, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.050555467605591, "global_step": 555073, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0232303142547607, "global_step": 555074, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0331902503967285, "global_step": 555075, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1267411708831787, "global_step": 555076, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.100865602493286, "global_step": 555077, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.048405170440674, "global_step": 555078, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0408434867858887, "global_step": 555079, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0058484077453613, "global_step": 555080, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.020785331726074, "global_step": 555081, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9951691627502441, "global_step": 555082, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0037620067596436, "global_step": 555083, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9722723960876465, "global_step": 555084, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.066582679748535, "global_step": 555085, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0465946197509766, "global_step": 555086, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0166192054748535, "global_step": 555087, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.146381139755249, "global_step": 555088, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0335803031921387, "global_step": 555089, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0235302448272705, "global_step": 555090, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9922391176223755, "global_step": 555091, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1031980514526367, "global_step": 555092, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0167641639709473, "global_step": 555093, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0325233936309814, "global_step": 555094, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.041497230529785, "global_step": 555095, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.060887336730957, "global_step": 555096, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0572712421417236, "global_step": 555097, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9399672746658325, "global_step": 555098, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0104706287384033, "global_step": 555099, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.094268798828125, "global_step": 555100, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9503809213638306, "global_step": 555101, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.10634446144104, "global_step": 555102, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9835494756698608, "global_step": 555103, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.090588331222534, "global_step": 555104, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9748455286026, "global_step": 555105, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9961150884628296, "global_step": 555106, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.041379928588867, "global_step": 555107, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1093015670776367, "global_step": 555108, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.01001238822937, "global_step": 555109, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1211585998535156, "global_step": 555110, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9914366006851196, "global_step": 555111, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0040123462677, "global_step": 555112, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.051077127456665, "global_step": 555113, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0295584201812744, "global_step": 555114, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.041147232055664, "global_step": 555115, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9862152338027954, "global_step": 555116, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.028188943862915, "global_step": 555117, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.024951219558716, "global_step": 555118, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.064030647277832, "global_step": 555119, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9836403131484985, "global_step": 555120, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9888471364974976, "global_step": 555121, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0450408458709717, "global_step": 555122, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9842220544815063, "global_step": 555123, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.049191474914551, "global_step": 555124, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1019861698150635, "global_step": 555125, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.079592227935791, "global_step": 555126, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.014312982559204, "global_step": 555127, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1115262508392334, "global_step": 555128, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.07865834236145, "global_step": 555129, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9721206426620483, "global_step": 555130, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.112769365310669, "global_step": 555131, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0325629711151123, "global_step": 555132, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.091294527053833, "global_step": 555133, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0111069679260254, "global_step": 555134, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.010012626647949, "global_step": 555135, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.076920986175537, "global_step": 555136, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.063594341278076, "global_step": 555137, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0122666358947754, "global_step": 555138, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.074064016342163, "global_step": 555139, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.952332854270935, "global_step": 555140, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.017011880874634, "global_step": 555141, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.030918598175049, "global_step": 555142, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1446547508239746, "global_step": 555143, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.002340793609619, "global_step": 555144, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9817880392074585, "global_step": 555145, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0468966960906982, "global_step": 555146, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9000258445739746, "global_step": 555147, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9546802043914795, "global_step": 555148, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9505650997161865, "global_step": 555149, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0373287200927734, "global_step": 555150, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0293829441070557, "global_step": 555151, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0109286308288574, "global_step": 555152, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.019620418548584, "global_step": 555153, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9845213890075684, "global_step": 555154, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0635485649108887, "global_step": 555155, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.019495964050293, "global_step": 555156, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.048454999923706, "global_step": 555157, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.002551555633545, "global_step": 555158, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0540502071380615, "global_step": 555159, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0135319232940674, "global_step": 555160, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.150777578353882, "global_step": 555161, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9893152713775635, "global_step": 555162, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.068415880203247, "global_step": 555163, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.058145761489868, "global_step": 555164, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0654406547546387, "global_step": 555165, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1004583835601807, "global_step": 555166, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.065046548843384, "global_step": 555167, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9994211196899414, "global_step": 555168, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9758102893829346, "global_step": 555169, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0430068969726562, "global_step": 555170, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0637598037719727, "global_step": 555171, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.010040044784546, "global_step": 555172, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0220882892608643, "global_step": 555173, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.020148515701294, "global_step": 555174, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.033705234527588, "global_step": 555175, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.144240379333496, "global_step": 555176, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9841094017028809, "global_step": 555177, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9805079698562622, "global_step": 555178, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0647783279418945, "global_step": 555179, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0088553428649902, "global_step": 555180, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0567095279693604, "global_step": 555181, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1016180515289307, "global_step": 555182, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.010164976119995, "global_step": 555183, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.075333833694458, "global_step": 555184, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9913617372512817, "global_step": 555185, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0318527221679688, "global_step": 555186, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.073429822921753, "global_step": 555187, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.123945713043213, "global_step": 555188, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0106987953186035, "global_step": 555189, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0484399795532227, "global_step": 555190, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9842456579208374, "global_step": 555191, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.045443534851074, "global_step": 555192, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9944849014282227, "global_step": 555193, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0784542560577393, "global_step": 555194, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0004825592041016, "global_step": 555195, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0865278244018555, "global_step": 555196, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9982216358184814, "global_step": 555197, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0849409103393555, "global_step": 555198, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.123539447784424, "global_step": 555199, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.041485548019409, "global_step": 555200, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.028580904006958, "global_step": 555201, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0084192752838135, "global_step": 555202, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0378973484039307, "global_step": 555203, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0606510639190674, "global_step": 555204, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9881495237350464, "global_step": 555205, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0311901569366455, "global_step": 555206, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9920971393585205, "global_step": 555207, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0804009437561035, "global_step": 555208, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9835989475250244, "global_step": 555209, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0392303466796875, "global_step": 555210, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9457569122314453, "global_step": 555211, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0028693675994873, "global_step": 555212, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0353806018829346, "global_step": 555213, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.959416151046753, "global_step": 555214, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0843112468719482, "global_step": 555215, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.027998208999634, "global_step": 555216, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.026942729949951, "global_step": 555217, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0770795345306396, "global_step": 555218, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.099987745285034, "global_step": 555219, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.008000135421753, "global_step": 555220, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9848477840423584, "global_step": 555221, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.050912380218506, "global_step": 555222, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.026489734649658, "global_step": 555223, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9954490661621094, "global_step": 555224, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.19462251663208, "global_step": 555225, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.078739643096924, "global_step": 555226, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.082106828689575, "global_step": 555227, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.08935546875, "global_step": 555228, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.030275821685791, "global_step": 555229, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.063075304031372, "global_step": 555230, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0204648971557617, "global_step": 555231, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0438175201416016, "global_step": 555232, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1559183597564697, "global_step": 555233, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.968078374862671, "global_step": 555234, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9343852996826172, "global_step": 555235, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1118483543395996, "global_step": 555236, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0898959636688232, "global_step": 555237, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.044020652770996, "global_step": 555238, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.028681755065918, "global_step": 555239, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0662546157836914, "global_step": 555240, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0398757457733154, "global_step": 555241, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0059778690338135, "global_step": 555242, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0703344345092773, "global_step": 555243, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0121889114379883, "global_step": 555244, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.101693630218506, "global_step": 555245, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.028817892074585, "global_step": 555246, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9960001707077026, "global_step": 555247, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0456290245056152, "global_step": 555248, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0948486328125, "global_step": 555249, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.03908109664917, "global_step": 555250, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.078631639480591, "global_step": 555251, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.022787094116211, "global_step": 555252, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0995569229125977, "global_step": 555253, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9920775890350342, "global_step": 555254, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9633694887161255, "global_step": 555255, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9869937896728516, "global_step": 555256, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0366744995117188, "global_step": 555257, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9689353704452515, "global_step": 555258, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0336475372314453, "global_step": 555259, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0364341735839844, "global_step": 555260, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9897993803024292, "global_step": 555261, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0517404079437256, "global_step": 555262, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9830186367034912, "global_step": 555263, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.998695731163025, "global_step": 555264, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0714855194091797, "global_step": 555265, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.113759756088257, "global_step": 555266, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0128262042999268, "global_step": 555267, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9839991331100464, "global_step": 555268, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.011495590209961, "global_step": 555269, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.059990406036377, "global_step": 555270, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.080327033996582, "global_step": 555271, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9710487127304077, "global_step": 555272, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.01137638092041, "global_step": 555273, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.026630163192749, "global_step": 555274, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0420210361480713, "global_step": 555275, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0186655521392822, "global_step": 555276, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9619839191436768, "global_step": 555277, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9284394979476929, "global_step": 555278, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0929527282714844, "global_step": 555279, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.001310348510742, "global_step": 555280, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9892828464508057, "global_step": 555281, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0094594955444336, "global_step": 555282, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0482053756713867, "global_step": 555283, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.059468984603882, "global_step": 555284, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9736785888671875, "global_step": 555285, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.037616491317749, "global_step": 555286, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.006436824798584, "global_step": 555287, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.041588068008423, "global_step": 555288, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.979554295539856, "global_step": 555289, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.039843797683716, "global_step": 555290, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0500926971435547, "global_step": 555291, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0525803565979004, "global_step": 555292, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0199122428894043, "global_step": 555293, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1079225540161133, "global_step": 555294, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0188920497894287, "global_step": 555295, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0922939777374268, "global_step": 555296, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.024113893508911, "global_step": 555297, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1015095710754395, "global_step": 555298, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.074228048324585, "global_step": 555299, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9880194664001465, "global_step": 555300, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.094799757003784, "global_step": 555301, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.072200298309326, "global_step": 555302, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1200246810913086, "global_step": 555303, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.101876735687256, "global_step": 555304, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.081780433654785, "global_step": 555305, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0125503540039062, "global_step": 555306, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.038996696472168, "global_step": 555307, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.064375877380371, "global_step": 555308, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1132075786590576, "global_step": 555309, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.055422306060791, "global_step": 555310, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0041654109954834, "global_step": 555311, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.061725616455078, "global_step": 555312, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0087432861328125, "global_step": 555313, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9633564949035645, "global_step": 555314, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.976059913635254, "global_step": 555315, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.04477858543396, "global_step": 555316, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.029388666152954, "global_step": 555317, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0019075870513916, "global_step": 555318, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.095078468322754, "global_step": 555319, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.10215425491333, "global_step": 555320, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.013519048690796, "global_step": 555321, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.010836601257324, "global_step": 555322, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0771617889404297, "global_step": 555323, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.97626793384552, "global_step": 555324, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.05747127532959, "global_step": 555325, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.071274757385254, "global_step": 555326, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9659897089004517, "global_step": 555327, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.944328784942627, "global_step": 555328, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9871257543563843, "global_step": 555329, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0058581829071045, "global_step": 555330, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0299746990203857, "global_step": 555331, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9892103672027588, "global_step": 555332, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9914491176605225, "global_step": 555333, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.042206048965454, "global_step": 555334, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0849945545196533, "global_step": 555335, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0599706172943115, "global_step": 555336, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.959305763244629, "global_step": 555337, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.11906361579895, "global_step": 555338, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.043907403945923, "global_step": 555339, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9235246181488037, "global_step": 555340, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9747051000595093, "global_step": 555341, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0777478218078613, "global_step": 555342, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0416769981384277, "global_step": 555343, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0855515003204346, "global_step": 555344, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.009765863418579, "global_step": 555345, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0486602783203125, "global_step": 555346, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.060122489929199, "global_step": 555347, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0363378524780273, "global_step": 555348, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0337612628936768, "global_step": 555349, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.018982410430908, "global_step": 555350, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.027277708053589, "global_step": 555351, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9876466989517212, "global_step": 555352, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1122493743896484, "global_step": 555353, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.900683045387268, "global_step": 555354, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.08368182182312, "global_step": 555355, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.044433116912842, "global_step": 555356, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0649585723876953, "global_step": 555357, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9930016994476318, "global_step": 555358, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.004927396774292, "global_step": 555359, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.060366153717041, "global_step": 555360, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.1182761192321777, "global_step": 555361, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.998792052268982, "global_step": 555362, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0117485523223877, "global_step": 555363, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9916170835494995, "global_step": 555364, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.0350253582000732, "global_step": 555365, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9475177526474, "global_step": 555366, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.066004753112793, "global_step": 555367, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9494901895523071, "global_step": 555368, "epoch": 922, "lr": 5e-05}
{"train_loss": 2.02724027633667, "global_step": 555369, "epoch": 922, "lr": 5e-05}
{"train_loss": 1.9874513149261475, "global_step": 555370, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.062877893447876, "global_step": 555371, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9445350170135498, "global_step": 555372, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.026106357574463, "global_step": 555373, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9649909734725952, "global_step": 555374, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0118958950042725, "global_step": 555375, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.091564893722534, "global_step": 555376, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0210227966308594, "global_step": 555377, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0099377632141113, "global_step": 555378, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0099263191223145, "global_step": 555379, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9789403676986694, "global_step": 555380, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0588114261627197, "global_step": 555381, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0344038009643555, "global_step": 555382, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.98502516746521, "global_step": 555383, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0169456005096436, "global_step": 555384, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.006450653076172, "global_step": 555385, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9744154214859009, "global_step": 555386, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0060808658599854, "global_step": 555387, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0451714992523193, "global_step": 555388, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0985403060913086, "global_step": 555389, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.990360140800476, "global_step": 555390, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0143909454345703, "global_step": 555391, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.969230055809021, "global_step": 555392, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9944498538970947, "global_step": 555393, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0598363876342773, "global_step": 555394, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.030085802078247, "global_step": 555395, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9308972358703613, "global_step": 555396, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.075079917907715, "global_step": 555397, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.033118963241577, "global_step": 555398, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.074883460998535, "global_step": 555399, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.973388671875, "global_step": 555400, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9897762537002563, "global_step": 555401, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9669305086135864, "global_step": 555402, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.043416738510132, "global_step": 555403, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1095738410949707, "global_step": 555404, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0077900886535645, "global_step": 555405, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1214613914489746, "global_step": 555406, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0267856121063232, "global_step": 555407, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9746874570846558, "global_step": 555408, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0920870304107666, "global_step": 555409, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0650618076324463, "global_step": 555410, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9730026721954346, "global_step": 555411, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0454728603363037, "global_step": 555412, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0430362224578857, "global_step": 555413, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0941171646118164, "global_step": 555414, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9945749044418335, "global_step": 555415, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0949928760528564, "global_step": 555416, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9983656406402588, "global_step": 555417, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0616536140441895, "global_step": 555418, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.069917917251587, "global_step": 555419, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.040407419204712, "global_step": 555420, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.98792564868927, "global_step": 555421, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9728608131408691, "global_step": 555422, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.121137857437134, "global_step": 555423, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.976602554321289, "global_step": 555424, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.98662269115448, "global_step": 555425, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.066411256790161, "global_step": 555426, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0125622749328613, "global_step": 555427, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0071489810943604, "global_step": 555428, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.014106512069702, "global_step": 555429, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9744099378585815, "global_step": 555430, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9690685272216797, "global_step": 555431, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.017897129058838, "global_step": 555432, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0823779106140137, "global_step": 555433, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.002882242202759, "global_step": 555434, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9550882577896118, "global_step": 555435, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.042041063308716, "global_step": 555436, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.008009195327759, "global_step": 555437, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9744750261306763, "global_step": 555438, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9876922369003296, "global_step": 555439, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0015616416931152, "global_step": 555440, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9696128368377686, "global_step": 555441, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9657539129257202, "global_step": 555442, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.993354082107544, "global_step": 555443, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0249576568603516, "global_step": 555444, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.031198263168335, "global_step": 555445, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9487158060073853, "global_step": 555446, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1178762912750244, "global_step": 555447, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.083362579345703, "global_step": 555448, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9865020513534546, "global_step": 555449, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9794164896011353, "global_step": 555450, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.001121759414673, "global_step": 555451, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9390662908554077, "global_step": 555452, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0298125743865967, "global_step": 555453, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9609060287475586, "global_step": 555454, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.941389799118042, "global_step": 555455, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0025370121002197, "global_step": 555456, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.010664463043213, "global_step": 555457, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0310311317443848, "global_step": 555458, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0130839347839355, "global_step": 555459, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.077188014984131, "global_step": 555460, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9892240762710571, "global_step": 555461, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.050593376159668, "global_step": 555462, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9270411729812622, "global_step": 555463, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9443886280059814, "global_step": 555464, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.008962631225586, "global_step": 555465, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0312230587005615, "global_step": 555466, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9908796548843384, "global_step": 555467, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9727439880371094, "global_step": 555468, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1428704261779785, "global_step": 555469, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9870012998580933, "global_step": 555470, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9028916358947754, "global_step": 555471, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0201568603515625, "global_step": 555472, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0286102294921875, "global_step": 555473, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.05496883392334, "global_step": 555474, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0621609687805176, "global_step": 555475, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0246026515960693, "global_step": 555476, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9177042245864868, "global_step": 555477, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0120065212249756, "global_step": 555478, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0423431396484375, "global_step": 555479, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9874218702316284, "global_step": 555480, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.011418581008911, "global_step": 555481, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0499372482299805, "global_step": 555482, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9978792667388916, "global_step": 555483, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0568654537200928, "global_step": 555484, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.001516819000244, "global_step": 555485, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.008665084838867, "global_step": 555486, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0771360397338867, "global_step": 555487, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1338839530944824, "global_step": 555488, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.005300998687744, "global_step": 555489, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.8865797519683838, "global_step": 555490, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0245301723480225, "global_step": 555491, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0203728675842285, "global_step": 555492, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.020043134689331, "global_step": 555493, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0678462982177734, "global_step": 555494, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0835201740264893, "global_step": 555495, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9773005247116089, "global_step": 555496, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.036189079284668, "global_step": 555497, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.932417392730713, "global_step": 555498, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9836161136627197, "global_step": 555499, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9783886671066284, "global_step": 555500, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9369628429412842, "global_step": 555501, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0718939304351807, "global_step": 555502, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0182366371154785, "global_step": 555503, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0040290355682373, "global_step": 555504, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0539398193359375, "global_step": 555505, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9949870109558105, "global_step": 555506, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0845484733581543, "global_step": 555507, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0708625316619873, "global_step": 555508, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0521931648254395, "global_step": 555509, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9699156284332275, "global_step": 555510, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0688304901123047, "global_step": 555511, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0579237937927246, "global_step": 555512, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.032938003540039, "global_step": 555513, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.105334758758545, "global_step": 555514, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.007981300354004, "global_step": 555515, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0206596851348877, "global_step": 555516, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0542123317718506, "global_step": 555517, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0640532970428467, "global_step": 555518, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.102527618408203, "global_step": 555519, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1234421730041504, "global_step": 555520, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0487632751464844, "global_step": 555521, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9561519622802734, "global_step": 555522, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0215916633605957, "global_step": 555523, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.005025625228882, "global_step": 555524, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0394082069396973, "global_step": 555525, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0124351978302, "global_step": 555526, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9740393161773682, "global_step": 555527, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.016756296157837, "global_step": 555528, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.980056643486023, "global_step": 555529, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9640655517578125, "global_step": 555530, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9284871816635132, "global_step": 555531, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0304322242736816, "global_step": 555532, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.076892137527466, "global_step": 555533, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9991059303283691, "global_step": 555534, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.21379017829895, "global_step": 555535, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9752107858657837, "global_step": 555536, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9639121294021606, "global_step": 555537, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9723541736602783, "global_step": 555538, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9996834993362427, "global_step": 555539, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1080944538116455, "global_step": 555540, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9221842288970947, "global_step": 555541, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0384628772735596, "global_step": 555542, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0373053550720215, "global_step": 555543, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9856762886047363, "global_step": 555544, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9678914546966553, "global_step": 555545, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.018202066421509, "global_step": 555546, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0558414459228516, "global_step": 555547, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.030266046524048, "global_step": 555548, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0278031826019287, "global_step": 555549, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.980722188949585, "global_step": 555550, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0085816383361816, "global_step": 555551, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9089547395706177, "global_step": 555552, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9973785877227783, "global_step": 555553, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.02428936958313, "global_step": 555554, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.047332525253296, "global_step": 555555, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9581067562103271, "global_step": 555556, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0473434925079346, "global_step": 555557, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.995656132698059, "global_step": 555558, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0204145908355713, "global_step": 555559, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0969433784484863, "global_step": 555560, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.108199119567871, "global_step": 555561, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0512845516204834, "global_step": 555562, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9908998012542725, "global_step": 555563, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0272841453552246, "global_step": 555564, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0729193687438965, "global_step": 555565, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.044617176055908, "global_step": 555566, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.982399821281433, "global_step": 555567, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9462262392044067, "global_step": 555568, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.096287250518799, "global_step": 555569, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0498695373535156, "global_step": 555570, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9842630624771118, "global_step": 555571, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9560778141021729, "global_step": 555572, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.11460018157959, "global_step": 555573, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0574820041656494, "global_step": 555574, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0804545879364014, "global_step": 555575, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1639108657836914, "global_step": 555576, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.122642755508423, "global_step": 555577, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0013136863708496, "global_step": 555578, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1379013061523438, "global_step": 555579, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.015097141265869, "global_step": 555580, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0763368606567383, "global_step": 555581, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0034735202789307, "global_step": 555582, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.931007742881775, "global_step": 555583, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.999405860900879, "global_step": 555584, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.996947169303894, "global_step": 555585, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0573408603668213, "global_step": 555586, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9723085165023804, "global_step": 555587, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0163216590881348, "global_step": 555588, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0253655910491943, "global_step": 555589, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.042616128921509, "global_step": 555590, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0291764736175537, "global_step": 555591, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.136868715286255, "global_step": 555592, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0393807888031006, "global_step": 555593, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.023716688156128, "global_step": 555594, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.972364902496338, "global_step": 555595, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0035479068756104, "global_step": 555596, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9444295167922974, "global_step": 555597, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9951025247573853, "global_step": 555598, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0447187423706055, "global_step": 555599, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.076561212539673, "global_step": 555600, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0547330379486084, "global_step": 555601, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0217552185058594, "global_step": 555602, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9850232601165771, "global_step": 555603, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0213115215301514, "global_step": 555604, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.964796543121338, "global_step": 555605, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0430495738983154, "global_step": 555606, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.996264100074768, "global_step": 555607, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.066580057144165, "global_step": 555608, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9291565418243408, "global_step": 555609, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9348626136779785, "global_step": 555610, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.02544903755188, "global_step": 555611, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9970341920852661, "global_step": 555612, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9509623050689697, "global_step": 555613, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.049140453338623, "global_step": 555614, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.052605628967285, "global_step": 555615, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0386643409729004, "global_step": 555616, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.002234935760498, "global_step": 555617, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.981987476348877, "global_step": 555618, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0772852897644043, "global_step": 555619, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.040693998336792, "global_step": 555620, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0430376529693604, "global_step": 555621, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.021141767501831, "global_step": 555622, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.00150728225708, "global_step": 555623, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9666186571121216, "global_step": 555624, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9756957292556763, "global_step": 555625, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.020763397216797, "global_step": 555626, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.989092469215393, "global_step": 555627, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0602099895477295, "global_step": 555628, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.034592628479004, "global_step": 555629, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9727849960327148, "global_step": 555630, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0630056858062744, "global_step": 555631, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9650208950042725, "global_step": 555632, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0565366744995117, "global_step": 555633, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9827016592025757, "global_step": 555634, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.003692626953125, "global_step": 555635, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0482044219970703, "global_step": 555636, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9613420963287354, "global_step": 555637, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.075148344039917, "global_step": 555638, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9890804290771484, "global_step": 555639, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9993386268615723, "global_step": 555640, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9956746101379395, "global_step": 555641, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0286803245544434, "global_step": 555642, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0302765369415283, "global_step": 555643, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9976252317428589, "global_step": 555644, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.99871027469635, "global_step": 555645, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.077606678009033, "global_step": 555646, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9024708271026611, "global_step": 555647, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9873427152633667, "global_step": 555648, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.079519510269165, "global_step": 555649, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9919794797897339, "global_step": 555650, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0508615970611572, "global_step": 555651, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.026184558868408, "global_step": 555652, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9476639032363892, "global_step": 555653, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.080451250076294, "global_step": 555654, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9567734003067017, "global_step": 555655, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0198020935058594, "global_step": 555656, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0190610885620117, "global_step": 555657, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0781798362731934, "global_step": 555658, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.05322003364563, "global_step": 555659, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.037461996078491, "global_step": 555660, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9670531749725342, "global_step": 555661, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.098301410675049, "global_step": 555662, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9983793497085571, "global_step": 555663, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0632071495056152, "global_step": 555664, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0480594635009766, "global_step": 555665, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9986525774002075, "global_step": 555666, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0300748348236084, "global_step": 555667, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.063328981399536, "global_step": 555668, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.007103204727173, "global_step": 555669, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.027362823486328, "global_step": 555670, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0899834632873535, "global_step": 555671, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0754990577697754, "global_step": 555672, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.12972354888916, "global_step": 555673, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.057162046432495, "global_step": 555674, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0838465690612793, "global_step": 555675, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.033658742904663, "global_step": 555676, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.149909496307373, "global_step": 555677, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.090078592300415, "global_step": 555678, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0517356395721436, "global_step": 555679, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0739188194274902, "global_step": 555680, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0132718086242676, "global_step": 555681, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0074498653411865, "global_step": 555682, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.056640148162842, "global_step": 555683, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.02109694480896, "global_step": 555684, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0766658782958984, "global_step": 555685, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.161241292953491, "global_step": 555686, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.045140266418457, "global_step": 555687, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0978128910064697, "global_step": 555688, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0827534198760986, "global_step": 555689, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0541460514068604, "global_step": 555690, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0083813667297363, "global_step": 555691, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0304811000823975, "global_step": 555692, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.037895917892456, "global_step": 555693, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0542795658111572, "global_step": 555694, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0374886989593506, "global_step": 555695, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0726828575134277, "global_step": 555696, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.019724130630493, "global_step": 555697, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9759844541549683, "global_step": 555698, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.05247163772583, "global_step": 555699, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0896108150482178, "global_step": 555700, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.018878221511841, "global_step": 555701, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.058424234390259, "global_step": 555702, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9976129531860352, "global_step": 555703, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.981053352355957, "global_step": 555704, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9707579612731934, "global_step": 555705, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.022373676300049, "global_step": 555706, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0338361263275146, "global_step": 555707, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0491743087768555, "global_step": 555708, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9956010580062866, "global_step": 555709, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.96989107131958, "global_step": 555710, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.106851816177368, "global_step": 555711, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0431571006774902, "global_step": 555712, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9524015188217163, "global_step": 555713, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9710434675216675, "global_step": 555714, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0244107246398926, "global_step": 555715, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0538408756256104, "global_step": 555716, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0474867820739746, "global_step": 555717, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0213680267333984, "global_step": 555718, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.996407389640808, "global_step": 555719, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.052412509918213, "global_step": 555720, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9899696111679077, "global_step": 555721, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.105733633041382, "global_step": 555722, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0337631702423096, "global_step": 555723, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1325056552886963, "global_step": 555724, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.06831693649292, "global_step": 555725, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.987743854522705, "global_step": 555726, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.085318088531494, "global_step": 555727, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9966163635253906, "global_step": 555728, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.016181468963623, "global_step": 555729, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0035455226898193, "global_step": 555730, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.943506121635437, "global_step": 555731, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9419995546340942, "global_step": 555732, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0873007774353027, "global_step": 555733, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.128455400466919, "global_step": 555734, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9668166637420654, "global_step": 555735, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.115159511566162, "global_step": 555736, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.106475830078125, "global_step": 555737, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.010540246963501, "global_step": 555738, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0114493370056152, "global_step": 555739, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0496456623077393, "global_step": 555740, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1260979175567627, "global_step": 555741, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.050562620162964, "global_step": 555742, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.033754348754883, "global_step": 555743, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.009892702102661, "global_step": 555744, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9747064113616943, "global_step": 555745, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1727468967437744, "global_step": 555746, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0881683826446533, "global_step": 555747, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.022552251815796, "global_step": 555748, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.069505453109741, "global_step": 555749, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.031717300415039, "global_step": 555750, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.015009880065918, "global_step": 555751, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0068931579589844, "global_step": 555752, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.069775104522705, "global_step": 555753, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0941309928894043, "global_step": 555754, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0362322330474854, "global_step": 555755, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0389745235443115, "global_step": 555756, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0280661582946777, "global_step": 555757, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0618784427642822, "global_step": 555758, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0153634548187256, "global_step": 555759, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.069788694381714, "global_step": 555760, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0701582431793213, "global_step": 555761, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.016422748565674, "global_step": 555762, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9981145858764648, "global_step": 555763, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9584925174713135, "global_step": 555764, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.082064151763916, "global_step": 555765, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0782620906829834, "global_step": 555766, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9974262714385986, "global_step": 555767, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0376274585723877, "global_step": 555768, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0480525493621826, "global_step": 555769, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9907323122024536, "global_step": 555770, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0438830852508545, "global_step": 555771, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9830085039138794, "global_step": 555772, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0724003314971924, "global_step": 555773, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9560447931289673, "global_step": 555774, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0347344875335693, "global_step": 555775, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0285608768463135, "global_step": 555776, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0644545555114746, "global_step": 555777, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1061763763427734, "global_step": 555778, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.006999969482422, "global_step": 555779, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.996222734451294, "global_step": 555780, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0725605487823486, "global_step": 555781, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.081740617752075, "global_step": 555782, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0041661262512207, "global_step": 555783, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0248961448669434, "global_step": 555784, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9772616624832153, "global_step": 555785, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.066993236541748, "global_step": 555786, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0658745765686035, "global_step": 555787, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0504729747772217, "global_step": 555788, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.023308038711548, "global_step": 555789, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.049379587173462, "global_step": 555790, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.041797637939453, "global_step": 555791, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9684638977050781, "global_step": 555792, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.037651538848877, "global_step": 555793, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9946544170379639, "global_step": 555794, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0047109127044678, "global_step": 555795, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0480055809020996, "global_step": 555796, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1016294956207275, "global_step": 555797, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0686638355255127, "global_step": 555798, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9921947717666626, "global_step": 555799, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.047497510910034, "global_step": 555800, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9544918537139893, "global_step": 555801, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0241172313690186, "global_step": 555802, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0311827659606934, "global_step": 555803, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0263257026672363, "global_step": 555804, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9470583200454712, "global_step": 555805, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0473759174346924, "global_step": 555806, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0830307006835938, "global_step": 555807, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9569374322891235, "global_step": 555808, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0351665019989014, "global_step": 555809, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.125133514404297, "global_step": 555810, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0473477840423584, "global_step": 555811, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.041807174682617, "global_step": 555812, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0379271507263184, "global_step": 555813, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9917211532592773, "global_step": 555814, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.111900806427002, "global_step": 555815, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9805829524993896, "global_step": 555816, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.07478404045105, "global_step": 555817, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9709025621414185, "global_step": 555818, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.043900728225708, "global_step": 555819, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0542714595794678, "global_step": 555820, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0666019916534424, "global_step": 555821, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0211284160614014, "global_step": 555822, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0461130142211914, "global_step": 555823, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.993631362915039, "global_step": 555824, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.065509796142578, "global_step": 555825, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.997487187385559, "global_step": 555826, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0231547355651855, "global_step": 555827, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0064966678619385, "global_step": 555828, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9898159503936768, "global_step": 555829, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.994821548461914, "global_step": 555830, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0974507331848145, "global_step": 555831, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9784313440322876, "global_step": 555832, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.013286828994751, "global_step": 555833, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.07150936126709, "global_step": 555834, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0267152786254883, "global_step": 555835, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1314425468444824, "global_step": 555836, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.993044376373291, "global_step": 555837, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9344897270202637, "global_step": 555838, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.049983501434326, "global_step": 555839, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0261640548706055, "global_step": 555840, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.932675838470459, "global_step": 555841, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9299349784851074, "global_step": 555842, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.043503761291504, "global_step": 555843, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9339814186096191, "global_step": 555844, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0602025985717773, "global_step": 555845, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0089235305786133, "global_step": 555846, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1000325679779053, "global_step": 555847, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9719047546386719, "global_step": 555848, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0554330348968506, "global_step": 555849, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.009270429611206, "global_step": 555850, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9598006010055542, "global_step": 555851, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.09161639213562, "global_step": 555852, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0473639965057373, "global_step": 555853, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9873409271240234, "global_step": 555854, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0001935958862305, "global_step": 555855, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.023702621459961, "global_step": 555856, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0717110633850098, "global_step": 555857, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0563902854919434, "global_step": 555858, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0021774768829346, "global_step": 555859, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.039632558822632, "global_step": 555860, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.055781126022339, "global_step": 555861, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.016089677810669, "global_step": 555862, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.003706693649292, "global_step": 555863, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0378942489624023, "global_step": 555864, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0537941455841064, "global_step": 555865, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9851558208465576, "global_step": 555866, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0140316486358643, "global_step": 555867, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0138707160949707, "global_step": 555868, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.04807186126709, "global_step": 555869, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9832322597503662, "global_step": 555870, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9910674095153809, "global_step": 555871, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.033386468887329, "global_step": 555872, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0196471214294434, "global_step": 555873, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9738866090774536, "global_step": 555874, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0420916080474854, "global_step": 555875, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.084033727645874, "global_step": 555876, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0305545330047607, "global_step": 555877, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0506644248962402, "global_step": 555878, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0969789028167725, "global_step": 555879, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.089463472366333, "global_step": 555880, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9963207244873047, "global_step": 555881, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0091803073883057, "global_step": 555882, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.901219129562378, "global_step": 555883, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0347213745117188, "global_step": 555884, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9953347444534302, "global_step": 555885, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9627974033355713, "global_step": 555886, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0581533908843994, "global_step": 555887, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0019702911376953, "global_step": 555888, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9632717370986938, "global_step": 555889, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9961975812911987, "global_step": 555890, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0455236434936523, "global_step": 555891, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.8989431858062744, "global_step": 555892, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0406320095062256, "global_step": 555893, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0049662590026855, "global_step": 555894, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.080162286758423, "global_step": 555895, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9365183115005493, "global_step": 555896, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.933096170425415, "global_step": 555897, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0388376712799072, "global_step": 555898, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0742311477661133, "global_step": 555899, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0909998416900635, "global_step": 555900, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.8906077146530151, "global_step": 555901, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1067380905151367, "global_step": 555902, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.976747989654541, "global_step": 555903, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.000047206878662, "global_step": 555904, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.077759265899658, "global_step": 555905, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.042664051055908, "global_step": 555906, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0290768146514893, "global_step": 555907, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.025569438934326, "global_step": 555908, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0446228981018066, "global_step": 555909, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.985280156135559, "global_step": 555910, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0570876598358154, "global_step": 555911, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9899340867996216, "global_step": 555912, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9747133255004883, "global_step": 555913, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.985382080078125, "global_step": 555914, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0530953407287598, "global_step": 555915, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0142998695373535, "global_step": 555916, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0443365573883057, "global_step": 555917, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.040924072265625, "global_step": 555918, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.062540292739868, "global_step": 555919, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0454657077789307, "global_step": 555920, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0211284160614014, "global_step": 555921, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1048593521118164, "global_step": 555922, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.998604416847229, "global_step": 555923, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.992124319076538, "global_step": 555924, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0002944469451904, "global_step": 555925, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.061051607131958, "global_step": 555926, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0541515350341797, "global_step": 555927, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1099414825439453, "global_step": 555928, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0054168701171875, "global_step": 555929, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.009042739868164, "global_step": 555930, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.042102098464966, "global_step": 555931, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0410819053649902, "global_step": 555932, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0401015281677246, "global_step": 555933, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9997180700302124, "global_step": 555934, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0423593521118164, "global_step": 555935, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0889079570770264, "global_step": 555936, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0295112133026123, "global_step": 555937, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.001129388809204, "global_step": 555938, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.006625175476074, "global_step": 555939, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9961369037628174, "global_step": 555940, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9864717721939087, "global_step": 555941, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.096453905105591, "global_step": 555942, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0696158409118652, "global_step": 555943, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0892107486724854, "global_step": 555944, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9897677898406982, "global_step": 555945, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.069185733795166, "global_step": 555946, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0055017471313477, "global_step": 555947, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.02759051322937, "global_step": 555948, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.032259225845337, "global_step": 555949, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0662050247192383, "global_step": 555950, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9925392866134644, "global_step": 555951, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0774521827697754, "global_step": 555952, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0359463691711426, "global_step": 555953, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.049650192260742, "global_step": 555954, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0614070892333984, "global_step": 555955, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.056288003921509, "global_step": 555956, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0185933113098145, "global_step": 555957, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.045672655105591, "global_step": 555958, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0729804039001465, "global_step": 555959, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.045555830001831, "global_step": 555960, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0119128227233887, "global_step": 555961, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.103320360183716, "global_step": 555962, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9117305278778076, "global_step": 555963, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.035515308380127, "global_step": 555964, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0226783752441406, "global_step": 555965, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0315165519714355, "global_step": 555966, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.012075901031494, "global_step": 555967, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0638813972473145, "global_step": 555968, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.936987280845642, "global_step": 555969, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.066647529602051, "global_step": 555970, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0119991302490234, "global_step": 555971, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.980271339416504, "global_step": 555972, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.032564401626587, "global_step": 555973, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.034893274307251, "global_step": 555974, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9481780529022217, "global_step": 555975, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1428768634796143, "global_step": 555976, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.03623628616333, "global_step": 555977, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1199235916137695, "global_step": 555978, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.991367220878601, "global_step": 555979, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1144039630889893, "global_step": 555980, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.045086622238159, "global_step": 555981, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.000553607940674, "global_step": 555982, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9530081748962402, "global_step": 555983, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0077970027923584, "global_step": 555984, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0064573287963867, "global_step": 555985, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.044198751449585, "global_step": 555986, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.039043664932251, "global_step": 555987, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.992767095565796, "global_step": 555988, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.075949192047119, "global_step": 555989, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.960451602935791, "global_step": 555990, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9844976663589478, "global_step": 555991, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.059387683868408, "global_step": 555992, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9547693729400635, "global_step": 555993, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.951663613319397, "global_step": 555994, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.010869026184082, "global_step": 555995, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0482349395751953, "global_step": 555996, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.099604368209839, "global_step": 555997, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.09177827835083, "global_step": 555998, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.098048448562622, "global_step": 555999, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.009568929672241, "global_step": 556000, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9414511919021606, "global_step": 556001, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.971853256225586, "global_step": 556002, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0878725051879883, "global_step": 556003, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0547025203704834, "global_step": 556004, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.039825916290283, "global_step": 556005, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.040400266647339, "global_step": 556006, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0736474990844727, "global_step": 556007, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1067380905151367, "global_step": 556008, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.983581304550171, "global_step": 556009, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.03765869140625, "global_step": 556010, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1020729541778564, "global_step": 556011, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9650031328201294, "global_step": 556012, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9878034591674805, "global_step": 556013, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9732238054275513, "global_step": 556014, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.024372100830078, "global_step": 556015, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0163815021514893, "global_step": 556016, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.012066602706909, "global_step": 556017, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0345916748046875, "global_step": 556018, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.08195161819458, "global_step": 556019, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0195462703704834, "global_step": 556020, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0488407611846924, "global_step": 556021, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.00700044631958, "global_step": 556022, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0530357360839844, "global_step": 556023, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.940388560295105, "global_step": 556024, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0599348545074463, "global_step": 556025, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.037651538848877, "global_step": 556026, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9998677968978882, "global_step": 556027, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.016770601272583, "global_step": 556028, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.034592866897583, "global_step": 556029, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.027397394180298, "global_step": 556030, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9941357374191284, "global_step": 556031, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9580769538879395, "global_step": 556032, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9051750898361206, "global_step": 556033, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0183072090148926, "global_step": 556034, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.101165294647217, "global_step": 556035, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0586328506469727, "global_step": 556036, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0232324600219727, "global_step": 556037, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.026557683944702, "global_step": 556038, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0696959495544434, "global_step": 556039, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9729082584381104, "global_step": 556040, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.044387102127075, "global_step": 556041, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0448882579803467, "global_step": 556042, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.055500030517578, "global_step": 556043, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.074141502380371, "global_step": 556044, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9331899881362915, "global_step": 556045, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0730128288269043, "global_step": 556046, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.037905693054199, "global_step": 556047, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.127296209335327, "global_step": 556048, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.073791742324829, "global_step": 556049, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.985623836517334, "global_step": 556050, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9748700857162476, "global_step": 556051, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.087357521057129, "global_step": 556052, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.053236484527588, "global_step": 556053, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.004420757293701, "global_step": 556054, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0412323474884033, "global_step": 556055, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9745832681655884, "global_step": 556056, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.058837890625, "global_step": 556057, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0228774547576904, "global_step": 556058, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0316269397735596, "global_step": 556059, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.058849573135376, "global_step": 556060, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.050222635269165, "global_step": 556061, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.056229591369629, "global_step": 556062, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.022977828979492, "global_step": 556063, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9947779178619385, "global_step": 556064, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0352723598480225, "global_step": 556065, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.078631639480591, "global_step": 556066, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.027864694595337, "global_step": 556067, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.077012777328491, "global_step": 556068, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0129904747009277, "global_step": 556069, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.000514268875122, "global_step": 556070, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9909639358520508, "global_step": 556071, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0710034370422363, "global_step": 556072, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9890007972717285, "global_step": 556073, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0489985942840576, "global_step": 556074, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9955506324768066, "global_step": 556075, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9538935422897339, "global_step": 556076, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.995534062385559, "global_step": 556077, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.129652261734009, "global_step": 556078, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0794425010681152, "global_step": 556079, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9837428331375122, "global_step": 556080, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.015683174133301, "global_step": 556081, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0429751873016357, "global_step": 556082, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0562570095062256, "global_step": 556083, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.084472179412842, "global_step": 556084, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9912751913070679, "global_step": 556085, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0753676891326904, "global_step": 556086, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.021672487258911, "global_step": 556087, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0914769172668457, "global_step": 556088, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.006808280944824, "global_step": 556089, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9818488359451294, "global_step": 556090, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0570268630981445, "global_step": 556091, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0001108646392822, "global_step": 556092, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0482118129730225, "global_step": 556093, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.040086507797241, "global_step": 556094, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0618696212768555, "global_step": 556095, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1575074195861816, "global_step": 556096, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9244740009307861, "global_step": 556097, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.080460548400879, "global_step": 556098, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0251286029815674, "global_step": 556099, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0184144973754883, "global_step": 556100, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0507240295410156, "global_step": 556101, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0250346660614014, "global_step": 556102, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0390849113464355, "global_step": 556103, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1211912631988525, "global_step": 556104, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0157108306884766, "global_step": 556105, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0379772186279297, "global_step": 556106, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0531554222106934, "global_step": 556107, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0846641063690186, "global_step": 556108, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0311105251312256, "global_step": 556109, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.955497145652771, "global_step": 556110, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.091634511947632, "global_step": 556111, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.00264310836792, "global_step": 556112, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.067816972732544, "global_step": 556113, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0549464225769043, "global_step": 556114, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9937975406646729, "global_step": 556115, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0341567993164062, "global_step": 556116, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.024935007095337, "global_step": 556117, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0450234413146973, "global_step": 556118, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1335928440093994, "global_step": 556119, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.031982421875, "global_step": 556120, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0636465549468994, "global_step": 556121, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0738372802734375, "global_step": 556122, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0016839504241943, "global_step": 556123, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.040717840194702, "global_step": 556124, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9943946599960327, "global_step": 556125, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.036203622817993, "global_step": 556126, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.991072654724121, "global_step": 556127, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9770034551620483, "global_step": 556128, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.06064510345459, "global_step": 556129, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.112421989440918, "global_step": 556130, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.132085084915161, "global_step": 556131, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.080047130584717, "global_step": 556132, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.100329637527466, "global_step": 556133, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.029709577560425, "global_step": 556134, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1093578338623047, "global_step": 556135, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.039292812347412, "global_step": 556136, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.009351968765259, "global_step": 556137, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.049561023712158, "global_step": 556138, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9664069414138794, "global_step": 556139, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0050182342529297, "global_step": 556140, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9997363090515137, "global_step": 556141, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0920112133026123, "global_step": 556142, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0041165351867676, "global_step": 556143, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9885058403015137, "global_step": 556144, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0837528705596924, "global_step": 556145, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.04256272315979, "global_step": 556146, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.018667459487915, "global_step": 556147, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.102348566055298, "global_step": 556148, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9615155458450317, "global_step": 556149, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.159611701965332, "global_step": 556150, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0115158557891846, "global_step": 556151, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0428266525268555, "global_step": 556152, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0650813579559326, "global_step": 556153, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.070037603378296, "global_step": 556154, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9929869174957275, "global_step": 556155, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0061473846435547, "global_step": 556156, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.126519203186035, "global_step": 556157, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0286178588867188, "global_step": 556158, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9932423830032349, "global_step": 556159, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.046447992324829, "global_step": 556160, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9080942869186401, "global_step": 556161, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.002262830734253, "global_step": 556162, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.087994337081909, "global_step": 556163, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0525963306427, "global_step": 556164, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.044835090637207, "global_step": 556165, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0065269470214844, "global_step": 556166, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0652554035186768, "global_step": 556167, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0774269104003906, "global_step": 556168, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.043109655380249, "global_step": 556169, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0281035900115967, "global_step": 556170, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9278161525726318, "global_step": 556171, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.125737190246582, "global_step": 556172, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9311727285385132, "global_step": 556173, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.112987995147705, "global_step": 556174, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9803476333618164, "global_step": 556175, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9965250492095947, "global_step": 556176, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1245980262756348, "global_step": 556177, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1153554916381836, "global_step": 556178, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9996223449707031, "global_step": 556179, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.10910964012146, "global_step": 556180, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.062741994857788, "global_step": 556181, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1312849521636963, "global_step": 556182, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1205530166625977, "global_step": 556183, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9752686023712158, "global_step": 556184, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9744600057601929, "global_step": 556185, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.023332357406616, "global_step": 556186, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.158926248550415, "global_step": 556187, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.057697296142578, "global_step": 556188, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.090951442718506, "global_step": 556189, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9666132926940918, "global_step": 556190, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0245180130004883, "global_step": 556191, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0203945636749268, "global_step": 556192, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9632213115692139, "global_step": 556193, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9988619089126587, "global_step": 556194, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.08209228515625, "global_step": 556195, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0619029998779297, "global_step": 556196, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0113933086395264, "global_step": 556197, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9814176559448242, "global_step": 556198, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1352038383483887, "global_step": 556199, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.042113780975342, "global_step": 556200, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9824522733688354, "global_step": 556201, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.993392825126648, "global_step": 556202, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9726492166519165, "global_step": 556203, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.059990167617798, "global_step": 556204, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.132140874862671, "global_step": 556205, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0265567302703857, "global_step": 556206, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1276941299438477, "global_step": 556207, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0091147422790527, "global_step": 556208, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.993043065071106, "global_step": 556209, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.174800395965576, "global_step": 556210, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.033156394958496, "global_step": 556211, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9663047790527344, "global_step": 556212, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.932318925857544, "global_step": 556213, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0920228958129883, "global_step": 556214, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0596413612365723, "global_step": 556215, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9603080749511719, "global_step": 556216, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0685946941375732, "global_step": 556217, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0603344440460205, "global_step": 556218, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0231916904449463, "global_step": 556219, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1017308235168457, "global_step": 556220, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9984766244888306, "global_step": 556221, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.009913206100464, "global_step": 556222, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9921795129776, "global_step": 556223, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.111727237701416, "global_step": 556224, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0003979206085205, "global_step": 556225, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.053617477416992, "global_step": 556226, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9903854131698608, "global_step": 556227, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0310921669006348, "global_step": 556228, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.01003098487854, "global_step": 556229, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0664525032043457, "global_step": 556230, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1657371520996094, "global_step": 556231, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0492653846740723, "global_step": 556232, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.091860771179199, "global_step": 556233, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0183610916137695, "global_step": 556234, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9722214937210083, "global_step": 556235, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.060547351837158, "global_step": 556236, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0745978355407715, "global_step": 556237, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.066092014312744, "global_step": 556238, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.012592315673828, "global_step": 556239, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0227959156036377, "global_step": 556240, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0792155265808105, "global_step": 556241, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0894343852996826, "global_step": 556242, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0822460651397705, "global_step": 556243, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0721566677093506, "global_step": 556244, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0354397296905518, "global_step": 556245, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0026943683624268, "global_step": 556246, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.007985830307007, "global_step": 556247, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.061519145965576, "global_step": 556248, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0765204429626465, "global_step": 556249, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.026703119277954, "global_step": 556250, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.091738700866699, "global_step": 556251, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0621936321258545, "global_step": 556252, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0335965156555176, "global_step": 556253, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0273702144622803, "global_step": 556254, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9954434633255005, "global_step": 556255, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0767736434936523, "global_step": 556256, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.206071376800537, "global_step": 556257, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.002878427505493, "global_step": 556258, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1332225799560547, "global_step": 556259, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.066952705383301, "global_step": 556260, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.110226631164551, "global_step": 556261, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9489532709121704, "global_step": 556262, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0297021865844727, "global_step": 556263, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9516559839248657, "global_step": 556264, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0220048427581787, "global_step": 556265, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0560944080352783, "global_step": 556266, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.059464931488037, "global_step": 556267, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.110258102416992, "global_step": 556268, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9794832468032837, "global_step": 556269, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0358848571777344, "global_step": 556270, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0781893730163574, "global_step": 556271, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0361757278442383, "global_step": 556272, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0189034938812256, "global_step": 556273, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.165872573852539, "global_step": 556274, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.144360065460205, "global_step": 556275, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9279896020889282, "global_step": 556276, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0189297199249268, "global_step": 556277, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.097153663635254, "global_step": 556278, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0541911125183105, "global_step": 556279, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0332884788513184, "global_step": 556280, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9753094911575317, "global_step": 556281, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0427236557006836, "global_step": 556282, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.942319631576538, "global_step": 556283, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0315258502960205, "global_step": 556284, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.01149320602417, "global_step": 556285, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0617856979370117, "global_step": 556286, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0492422580718994, "global_step": 556287, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0204086303710938, "global_step": 556288, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0119011402130127, "global_step": 556289, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.022951126098633, "global_step": 556290, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.084242105484009, "global_step": 556291, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0031025409698486, "global_step": 556292, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0462660789489746, "global_step": 556293, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.037898302078247, "global_step": 556294, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.058373212814331, "global_step": 556295, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.027489185333252, "global_step": 556296, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0306830406188965, "global_step": 556297, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9706062078475952, "global_step": 556298, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0658624172210693, "global_step": 556299, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.030789613723755, "global_step": 556300, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0981435775756836, "global_step": 556301, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9934186935424805, "global_step": 556302, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.082510232925415, "global_step": 556303, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.068758726119995, "global_step": 556304, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.096869468688965, "global_step": 556305, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.050924301147461, "global_step": 556306, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0916576385498047, "global_step": 556307, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0369808673858643, "global_step": 556308, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0074269771575928, "global_step": 556309, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0788211822509766, "global_step": 556310, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.090275526046753, "global_step": 556311, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9505499601364136, "global_step": 556312, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0963127613067627, "global_step": 556313, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.034937858581543, "global_step": 556314, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.986754059791565, "global_step": 556315, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1144514083862305, "global_step": 556316, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0387847423553467, "global_step": 556317, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1338064670562744, "global_step": 556318, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.019594669342041, "global_step": 556319, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.067232847213745, "global_step": 556320, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9982465505599976, "global_step": 556321, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1376407146453857, "global_step": 556322, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0956225395202637, "global_step": 556323, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0406317710876465, "global_step": 556324, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.003899097442627, "global_step": 556325, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.096001386642456, "global_step": 556326, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.035182476043701, "global_step": 556327, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.007941722869873, "global_step": 556328, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0135622024536133, "global_step": 556329, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0188891887664795, "global_step": 556330, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0017967224121094, "global_step": 556331, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9603242874145508, "global_step": 556332, "epoch": 923, "lr": 5e-05}
{"train_loss": 1.9960899353027344, "global_step": 556333, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1299216747283936, "global_step": 556334, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0641300678253174, "global_step": 556335, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.074594020843506, "global_step": 556336, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0832877159118652, "global_step": 556337, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.0307114124298096, "global_step": 556338, "epoch": 923, "lr": 5e-05}
{"train_loss": 2.1104772090911865, "global_step": 556339, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9684034585952759, "global_step": 556340, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9840342998504639, "global_step": 556341, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0277178287506104, "global_step": 556342, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0033633708953857, "global_step": 556343, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9939215183258057, "global_step": 556344, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9605534076690674, "global_step": 556345, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0141077041625977, "global_step": 556346, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9979772567749023, "global_step": 556347, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9985214471817017, "global_step": 556348, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0017881393432617, "global_step": 556349, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.060983896255493, "global_step": 556350, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9782326221466064, "global_step": 556351, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9598783254623413, "global_step": 556352, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.956416130065918, "global_step": 556353, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1738405227661133, "global_step": 556354, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0062036514282227, "global_step": 556355, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.048471689224243, "global_step": 556356, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0784645080566406, "global_step": 556357, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.998982548713684, "global_step": 556358, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9730994701385498, "global_step": 556359, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1286303997039795, "global_step": 556360, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.051292896270752, "global_step": 556361, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0230278968811035, "global_step": 556362, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.098586082458496, "global_step": 556363, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.093451738357544, "global_step": 556364, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.023951768875122, "global_step": 556365, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.145684003829956, "global_step": 556366, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0510504245758057, "global_step": 556367, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9642908573150635, "global_step": 556368, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0232996940612793, "global_step": 556369, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.020016670227051, "global_step": 556370, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0306286811828613, "global_step": 556371, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0083096027374268, "global_step": 556372, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9802361726760864, "global_step": 556373, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0949723720550537, "global_step": 556374, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0859408378601074, "global_step": 556375, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.039231538772583, "global_step": 556376, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.015594482421875, "global_step": 556377, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1036667823791504, "global_step": 556378, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9600576162338257, "global_step": 556379, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0213451385498047, "global_step": 556380, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.074244260787964, "global_step": 556381, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0305113792419434, "global_step": 556382, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9541501998901367, "global_step": 556383, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0545401573181152, "global_step": 556384, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.030653953552246, "global_step": 556385, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9827008247375488, "global_step": 556386, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0087103843688965, "global_step": 556387, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0515925884246826, "global_step": 556388, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.01564359664917, "global_step": 556389, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.031562089920044, "global_step": 556390, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0596675872802734, "global_step": 556391, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0785956382751465, "global_step": 556392, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9595489501953125, "global_step": 556393, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.125070810317993, "global_step": 556394, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0429513454437256, "global_step": 556395, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.023383378982544, "global_step": 556396, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0494730472564697, "global_step": 556397, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.098672389984131, "global_step": 556398, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0892527103424072, "global_step": 556399, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0676376819610596, "global_step": 556400, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.012648820877075, "global_step": 556401, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9991812705993652, "global_step": 556402, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0282704830169678, "global_step": 556403, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0297582149505615, "global_step": 556404, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.018533229827881, "global_step": 556405, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9672191143035889, "global_step": 556406, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.009093761444092, "global_step": 556407, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.072316884994507, "global_step": 556408, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9223755598068237, "global_step": 556409, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.982315182685852, "global_step": 556410, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9963051080703735, "global_step": 556411, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1057512760162354, "global_step": 556412, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0146429538726807, "global_step": 556413, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.010502576828003, "global_step": 556414, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0033884048461914, "global_step": 556415, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0075109004974365, "global_step": 556416, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.968769907951355, "global_step": 556417, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9360989332199097, "global_step": 556418, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9558532238006592, "global_step": 556419, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.928774356842041, "global_step": 556420, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.06184983253479, "global_step": 556421, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.98082435131073, "global_step": 556422, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0374436378479004, "global_step": 556423, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9564001560211182, "global_step": 556424, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.037355422973633, "global_step": 556425, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.006890296936035, "global_step": 556426, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.016745090484619, "global_step": 556427, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.141583204269409, "global_step": 556428, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.087503433227539, "global_step": 556429, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0536749362945557, "global_step": 556430, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0006027221679688, "global_step": 556431, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0574069023132324, "global_step": 556432, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.099954843521118, "global_step": 556433, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.055279493331909, "global_step": 556434, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9893147945404053, "global_step": 556435, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9736027717590332, "global_step": 556436, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9957869052886963, "global_step": 556437, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.066660165786743, "global_step": 556438, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0155625343322754, "global_step": 556439, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0018742084503174, "global_step": 556440, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.052278757095337, "global_step": 556441, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.172628879547119, "global_step": 556442, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9899731874465942, "global_step": 556443, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0390470027923584, "global_step": 556444, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.002467632293701, "global_step": 556445, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0423667430877686, "global_step": 556446, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.029158353805542, "global_step": 556447, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.992774486541748, "global_step": 556448, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.048574447631836, "global_step": 556449, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9656145572662354, "global_step": 556450, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.010761260986328, "global_step": 556451, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.069166421890259, "global_step": 556452, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.975875735282898, "global_step": 556453, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0208704471588135, "global_step": 556454, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.025189161300659, "global_step": 556455, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.002613067626953, "global_step": 556456, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0843422412872314, "global_step": 556457, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.039792060852051, "global_step": 556458, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9906195402145386, "global_step": 556459, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0401980876922607, "global_step": 556460, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.065218448638916, "global_step": 556461, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0203983783721924, "global_step": 556462, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.99043607711792, "global_step": 556463, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9838149547576904, "global_step": 556464, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.096118211746216, "global_step": 556465, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.045475959777832, "global_step": 556466, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0772719383239746, "global_step": 556467, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.950603723526001, "global_step": 556468, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.006495714187622, "global_step": 556469, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.033282518386841, "global_step": 556470, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0136618614196777, "global_step": 556471, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.945848822593689, "global_step": 556472, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.986092209815979, "global_step": 556473, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.002561092376709, "global_step": 556474, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0597646236419678, "global_step": 556475, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.020345687866211, "global_step": 556476, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9764915704727173, "global_step": 556477, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9675025939941406, "global_step": 556478, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0710206031799316, "global_step": 556479, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0979278087615967, "global_step": 556480, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.055379867553711, "global_step": 556481, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9927629232406616, "global_step": 556482, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.977101445198059, "global_step": 556483, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9674934148788452, "global_step": 556484, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0025904178619385, "global_step": 556485, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1123533248901367, "global_step": 556486, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.083625555038452, "global_step": 556487, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9758307933807373, "global_step": 556488, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9903481006622314, "global_step": 556489, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0216684341430664, "global_step": 556490, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0547919273376465, "global_step": 556491, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9529829025268555, "global_step": 556492, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.066640853881836, "global_step": 556493, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0464606285095215, "global_step": 556494, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9811556339263916, "global_step": 556495, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.06579327583313, "global_step": 556496, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9919910430908203, "global_step": 556497, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9580923318862915, "global_step": 556498, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0018553733825684, "global_step": 556499, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9763184785842896, "global_step": 556500, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.036827325820923, "global_step": 556501, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.096925973892212, "global_step": 556502, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0007169246673584, "global_step": 556503, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0168440341949463, "global_step": 556504, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.947304606437683, "global_step": 556505, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0604162216186523, "global_step": 556506, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.051133871078491, "global_step": 556507, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.994126319885254, "global_step": 556508, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0384738445281982, "global_step": 556509, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0473198890686035, "global_step": 556510, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.03043270111084, "global_step": 556511, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.013538122177124, "global_step": 556512, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0057759284973145, "global_step": 556513, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.079286575317383, "global_step": 556514, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0175437927246094, "global_step": 556515, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1099328994750977, "global_step": 556516, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.068385362625122, "global_step": 556517, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0191431045532227, "global_step": 556518, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.109292507171631, "global_step": 556519, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0147616863250732, "global_step": 556520, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9031847715377808, "global_step": 556521, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9865564107894897, "global_step": 556522, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0895135402679443, "global_step": 556523, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9722386598587036, "global_step": 556524, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0271224975585938, "global_step": 556525, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.965235948562622, "global_step": 556526, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9353227615356445, "global_step": 556527, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.97041654586792, "global_step": 556528, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0325815677642822, "global_step": 556529, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9972646236419678, "global_step": 556530, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.010978937149048, "global_step": 556531, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0338616371154785, "global_step": 556532, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.044743299484253, "global_step": 556533, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.8934593200683594, "global_step": 556534, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.022784948348999, "global_step": 556535, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.047081470489502, "global_step": 556536, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.999385118484497, "global_step": 556537, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0508933067321777, "global_step": 556538, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0902137756347656, "global_step": 556539, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.967342495918274, "global_step": 556540, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9919896125793457, "global_step": 556541, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9826693534851074, "global_step": 556542, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0178403854370117, "global_step": 556543, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.157106399536133, "global_step": 556544, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0241808891296387, "global_step": 556545, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0117292404174805, "global_step": 556546, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0447568893432617, "global_step": 556547, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0161662101745605, "global_step": 556548, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9873361587524414, "global_step": 556549, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.006037950515747, "global_step": 556550, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.049029588699341, "global_step": 556551, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9604908227920532, "global_step": 556552, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1192126274108887, "global_step": 556553, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.02822208404541, "global_step": 556554, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0278050899505615, "global_step": 556555, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0272748470306396, "global_step": 556556, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.06316876411438, "global_step": 556557, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9696208238601685, "global_step": 556558, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0744731426239014, "global_step": 556559, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0563182830810547, "global_step": 556560, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9972554445266724, "global_step": 556561, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.056786298751831, "global_step": 556562, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.06986403465271, "global_step": 556563, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0614991188049316, "global_step": 556564, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.967410683631897, "global_step": 556565, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0495848655700684, "global_step": 556566, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9703330993652344, "global_step": 556567, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9410332441329956, "global_step": 556568, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.04048228263855, "global_step": 556569, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.075765609741211, "global_step": 556570, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0295519828796387, "global_step": 556571, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.930014967918396, "global_step": 556572, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0243027210235596, "global_step": 556573, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9533588886260986, "global_step": 556574, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9652737379074097, "global_step": 556575, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0208041667938232, "global_step": 556576, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.004683256149292, "global_step": 556577, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9714760780334473, "global_step": 556578, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9340389966964722, "global_step": 556579, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9690907001495361, "global_step": 556580, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9752893447875977, "global_step": 556581, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.015653371810913, "global_step": 556582, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0184834003448486, "global_step": 556583, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9852548837661743, "global_step": 556584, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9827936887741089, "global_step": 556585, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.017176628112793, "global_step": 556586, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0582308769226074, "global_step": 556587, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.038252592086792, "global_step": 556588, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0167622566223145, "global_step": 556589, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9923452138900757, "global_step": 556590, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9754887819290161, "global_step": 556591, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0126264095306396, "global_step": 556592, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9886058568954468, "global_step": 556593, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.010772705078125, "global_step": 556594, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9918516874313354, "global_step": 556595, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9559075832366943, "global_step": 556596, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0493664741516113, "global_step": 556597, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.003084182739258, "global_step": 556598, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.013622760772705, "global_step": 556599, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0285120010375977, "global_step": 556600, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1149425506591797, "global_step": 556601, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.028656482696533, "global_step": 556602, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0352203845977783, "global_step": 556603, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0126848220825195, "global_step": 556604, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9702750444412231, "global_step": 556605, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0943281650543213, "global_step": 556606, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1086270809173584, "global_step": 556607, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9995417594909668, "global_step": 556608, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0191152095794678, "global_step": 556609, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0124034881591797, "global_step": 556610, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0060336589813232, "global_step": 556611, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9710040092468262, "global_step": 556612, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0266191959381104, "global_step": 556613, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.956618070602417, "global_step": 556614, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.039985179901123, "global_step": 556615, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0285966396331787, "global_step": 556616, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.04966139793396, "global_step": 556617, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.083153247833252, "global_step": 556618, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.000318765640259, "global_step": 556619, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0526387691497803, "global_step": 556620, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0325756072998047, "global_step": 556621, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.061199188232422, "global_step": 556622, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9442507028579712, "global_step": 556623, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9913241863250732, "global_step": 556624, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0256729125976562, "global_step": 556625, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.031647205352783, "global_step": 556626, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0174813270568848, "global_step": 556627, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9759657382965088, "global_step": 556628, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0418174266815186, "global_step": 556629, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.045441150665283, "global_step": 556630, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9824674129486084, "global_step": 556631, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1339802742004395, "global_step": 556632, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.055661201477051, "global_step": 556633, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.003136396408081, "global_step": 556634, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.091639280319214, "global_step": 556635, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.053800582885742, "global_step": 556636, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9747940301895142, "global_step": 556637, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9900099039077759, "global_step": 556638, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9364280700683594, "global_step": 556639, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0215389728546143, "global_step": 556640, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.012387275695801, "global_step": 556641, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9753918647766113, "global_step": 556642, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1016557216644287, "global_step": 556643, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.111842632293701, "global_step": 556644, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9657200574874878, "global_step": 556645, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9704294204711914, "global_step": 556646, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.016655683517456, "global_step": 556647, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0228919982910156, "global_step": 556648, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.014324188232422, "global_step": 556649, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9739470481872559, "global_step": 556650, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1343328952789307, "global_step": 556651, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9935864210128784, "global_step": 556652, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0336320400238037, "global_step": 556653, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.022061824798584, "global_step": 556654, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0087156295776367, "global_step": 556655, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0755085945129395, "global_step": 556656, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0826680660247803, "global_step": 556657, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.071410655975342, "global_step": 556658, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0213675498962402, "global_step": 556659, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.982613205909729, "global_step": 556660, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.925134539604187, "global_step": 556661, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0524463653564453, "global_step": 556662, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.020054817199707, "global_step": 556663, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.949618935585022, "global_step": 556664, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9848204851150513, "global_step": 556665, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.008495807647705, "global_step": 556666, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.101459503173828, "global_step": 556667, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9817836284637451, "global_step": 556668, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.054372787475586, "global_step": 556669, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0377838611602783, "global_step": 556670, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9396506547927856, "global_step": 556671, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.002401828765869, "global_step": 556672, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0164225101470947, "global_step": 556673, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0471572875976562, "global_step": 556674, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0480544567108154, "global_step": 556675, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.015713691711426, "global_step": 556676, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0935544967651367, "global_step": 556677, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0210790634155273, "global_step": 556678, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.024914026260376, "global_step": 556679, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.976330041885376, "global_step": 556680, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.157473564147949, "global_step": 556681, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0025429725646973, "global_step": 556682, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.069793224334717, "global_step": 556683, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9577475786209106, "global_step": 556684, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.194864511489868, "global_step": 556685, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.097870111465454, "global_step": 556686, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0612833499908447, "global_step": 556687, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.048236846923828, "global_step": 556688, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.065626382827759, "global_step": 556689, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0241572856903076, "global_step": 556690, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0024197101593018, "global_step": 556691, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.966692566871643, "global_step": 556692, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.045870304107666, "global_step": 556693, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.057661533355713, "global_step": 556694, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0520224571228027, "global_step": 556695, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.054760217666626, "global_step": 556696, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0619945526123047, "global_step": 556697, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0608747005462646, "global_step": 556698, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0424563884735107, "global_step": 556699, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.989295482635498, "global_step": 556700, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.138066530227661, "global_step": 556701, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.048194169998169, "global_step": 556702, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9633747339248657, "global_step": 556703, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.045023202896118, "global_step": 556704, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.021009922027588, "global_step": 556705, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.12613582611084, "global_step": 556706, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.081155300140381, "global_step": 556707, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0291688442230225, "global_step": 556708, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9782804250717163, "global_step": 556709, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9880127906799316, "global_step": 556710, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.998464822769165, "global_step": 556711, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0649850368499756, "global_step": 556712, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.132505178451538, "global_step": 556713, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.085970878601074, "global_step": 556714, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.058417558670044, "global_step": 556715, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.038102865219116, "global_step": 556716, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9569987058639526, "global_step": 556717, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9633709192276, "global_step": 556718, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.033924102783203, "global_step": 556719, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.089604616165161, "global_step": 556720, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0216102600097656, "global_step": 556721, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0812795162200928, "global_step": 556722, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0039236545562744, "global_step": 556723, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1057112216949463, "global_step": 556724, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0006844997406006, "global_step": 556725, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.027845859527588, "global_step": 556726, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.987944483757019, "global_step": 556727, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0040104389190674, "global_step": 556728, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.055678129196167, "global_step": 556729, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0437886714935303, "global_step": 556730, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0248024463653564, "global_step": 556731, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0480704307556152, "global_step": 556732, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.991437554359436, "global_step": 556733, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.059873104095459, "global_step": 556734, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1291775703430176, "global_step": 556735, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0957868099212646, "global_step": 556736, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0093929767608643, "global_step": 556737, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.015867233276367, "global_step": 556738, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9437658786773682, "global_step": 556739, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0306954383850098, "global_step": 556740, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.107024908065796, "global_step": 556741, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0979039669036865, "global_step": 556742, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9990888833999634, "global_step": 556743, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0403313636779785, "global_step": 556744, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.101435422897339, "global_step": 556745, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0149126052856445, "global_step": 556746, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0090556144714355, "global_step": 556747, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0385332107543945, "global_step": 556748, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0920424461364746, "global_step": 556749, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.014106035232544, "global_step": 556750, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9854226112365723, "global_step": 556751, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0217835903167725, "global_step": 556752, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.04642653465271, "global_step": 556753, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0476605892181396, "global_step": 556754, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.011580467224121, "global_step": 556755, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9328367710113525, "global_step": 556756, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.983262300491333, "global_step": 556757, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0341548919677734, "global_step": 556758, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0592830181121826, "global_step": 556759, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.016409158706665, "global_step": 556760, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0904109477996826, "global_step": 556761, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9369966983795166, "global_step": 556762, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0306003093719482, "global_step": 556763, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0633046627044678, "global_step": 556764, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0077946186065674, "global_step": 556765, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9482358694076538, "global_step": 556766, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1040902137756348, "global_step": 556767, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0673415660858154, "global_step": 556768, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0514376163482666, "global_step": 556769, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9362925291061401, "global_step": 556770, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0371406078338623, "global_step": 556771, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0441715717315674, "global_step": 556772, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.069801092147827, "global_step": 556773, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0533392429351807, "global_step": 556774, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0155844688415527, "global_step": 556775, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9673815965652466, "global_step": 556776, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0150644779205322, "global_step": 556777, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0771310329437256, "global_step": 556778, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9677447080612183, "global_step": 556779, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9922857284545898, "global_step": 556780, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.983160138130188, "global_step": 556781, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0473599433898926, "global_step": 556782, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9956237077713013, "global_step": 556783, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.035963535308838, "global_step": 556784, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9992918968200684, "global_step": 556785, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0144591331481934, "global_step": 556786, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0765273571014404, "global_step": 556787, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.017390489578247, "global_step": 556788, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0395584106445312, "global_step": 556789, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9860433340072632, "global_step": 556790, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.01436185836792, "global_step": 556791, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0273356437683105, "global_step": 556792, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.064126491546631, "global_step": 556793, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9743010997772217, "global_step": 556794, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.997876763343811, "global_step": 556795, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0212550163269043, "global_step": 556796, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0209238529205322, "global_step": 556797, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0964126586914062, "global_step": 556798, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0685482025146484, "global_step": 556799, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9546120166778564, "global_step": 556800, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.073707103729248, "global_step": 556801, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.028731346130371, "global_step": 556802, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.014899969100952, "global_step": 556803, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0776233673095703, "global_step": 556804, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.982658863067627, "global_step": 556805, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0428056716918945, "global_step": 556806, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.022958993911743, "global_step": 556807, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9622118473052979, "global_step": 556808, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1008853912353516, "global_step": 556809, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9552860260009766, "global_step": 556810, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.019752025604248, "global_step": 556811, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.027437448501587, "global_step": 556812, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0280661582946777, "global_step": 556813, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9951671361923218, "global_step": 556814, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0102548599243164, "global_step": 556815, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9892373085021973, "global_step": 556816, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.120638132095337, "global_step": 556817, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.081836700439453, "global_step": 556818, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9777344465255737, "global_step": 556819, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1010210514068604, "global_step": 556820, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0893747806549072, "global_step": 556821, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.029432773590088, "global_step": 556822, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9797711372375488, "global_step": 556823, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0143847465515137, "global_step": 556824, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0998075008392334, "global_step": 556825, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0193068981170654, "global_step": 556826, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0301244258880615, "global_step": 556827, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.111618757247925, "global_step": 556828, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.062549114227295, "global_step": 556829, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0192718505859375, "global_step": 556830, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.098217010498047, "global_step": 556831, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.032686233520508, "global_step": 556832, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0640604496002197, "global_step": 556833, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.009763240814209, "global_step": 556834, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0652549266815186, "global_step": 556835, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0995490550994873, "global_step": 556836, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0800039768218994, "global_step": 556837, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.992193341255188, "global_step": 556838, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9967478513717651, "global_step": 556839, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0065245628356934, "global_step": 556840, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0676345825195312, "global_step": 556841, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0552785396575928, "global_step": 556842, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.989545464515686, "global_step": 556843, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0289313793182373, "global_step": 556844, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.086437940597534, "global_step": 556845, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9390435218811035, "global_step": 556846, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.055349588394165, "global_step": 556847, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0396382808685303, "global_step": 556848, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1090927124023438, "global_step": 556849, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0254452228546143, "global_step": 556850, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0232112407684326, "global_step": 556851, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.027980089187622, "global_step": 556852, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.027191638946533, "global_step": 556853, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.056218385696411, "global_step": 556854, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.072133779525757, "global_step": 556855, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9988073110580444, "global_step": 556856, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0803942680358887, "global_step": 556857, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.006176471710205, "global_step": 556858, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0454282760620117, "global_step": 556859, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9940605163574219, "global_step": 556860, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0720717906951904, "global_step": 556861, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.03190541267395, "global_step": 556862, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0695009231567383, "global_step": 556863, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9562292098999023, "global_step": 556864, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9873473644256592, "global_step": 556865, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9750244617462158, "global_step": 556866, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1235125064849854, "global_step": 556867, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.078864812850952, "global_step": 556868, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0279688835144043, "global_step": 556869, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.042362689971924, "global_step": 556870, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0868172645568848, "global_step": 556871, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1107001304626465, "global_step": 556872, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0169317722320557, "global_step": 556873, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0607821941375732, "global_step": 556874, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9511629343032837, "global_step": 556875, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0259175300598145, "global_step": 556876, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1126699447631836, "global_step": 556877, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.010754108428955, "global_step": 556878, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9743428230285645, "global_step": 556879, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0595948696136475, "global_step": 556880, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9576458930969238, "global_step": 556881, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0944652557373047, "global_step": 556882, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0407216548919678, "global_step": 556883, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9290393590927124, "global_step": 556884, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.979507327079773, "global_step": 556885, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.055748462677002, "global_step": 556886, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0014500617980957, "global_step": 556887, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0831785202026367, "global_step": 556888, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.005491018295288, "global_step": 556889, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.061326026916504, "global_step": 556890, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.991245985031128, "global_step": 556891, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0560407638549805, "global_step": 556892, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.060168743133545, "global_step": 556893, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9935098886489868, "global_step": 556894, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.013918876647949, "global_step": 556895, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1163833141326904, "global_step": 556896, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9502079486846924, "global_step": 556897, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.047244071960449, "global_step": 556898, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0829172134399414, "global_step": 556899, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9540908336639404, "global_step": 556900, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.067412853240967, "global_step": 556901, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9324312210083008, "global_step": 556902, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0254838466644287, "global_step": 556903, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9800091981887817, "global_step": 556904, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0273797512054443, "global_step": 556905, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0666022300720215, "global_step": 556906, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9168654680252075, "global_step": 556907, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9777286052703857, "global_step": 556908, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0083718299865723, "global_step": 556909, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.08583664894104, "global_step": 556910, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1209731101989746, "global_step": 556911, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0809664726257324, "global_step": 556912, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9693655967712402, "global_step": 556913, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1236917972564697, "global_step": 556914, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.022587776184082, "global_step": 556915, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9607791900634766, "global_step": 556916, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0540177822113037, "global_step": 556917, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0446879863739014, "global_step": 556918, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0200936794281006, "global_step": 556919, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0806448459625244, "global_step": 556920, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.056950807571411, "global_step": 556921, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.036592483520508, "global_step": 556922, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9975956678390503, "global_step": 556923, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.025038242340088, "global_step": 556924, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0688724517822266, "global_step": 556925, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.984417200088501, "global_step": 556926, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9593687057495117, "global_step": 556927, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.012531042098999, "global_step": 556928, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.980731725692749, "global_step": 556929, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0816187858581543, "global_step": 556930, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.031934976577759, "global_step": 556931, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0466763973236084, "global_step": 556932, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0432887077331543, "global_step": 556933, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0275766849517822, "global_step": 556934, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.09562349319458, "global_step": 556935, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.008474349975586, "global_step": 556936, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.022566795349121, "global_step": 556937, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9907128810882568, "global_step": 556938, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.007878065109253, "global_step": 556939, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.053464651107788, "global_step": 556940, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0998315811157227, "global_step": 556941, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0365397930145264, "global_step": 556942, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9912865161895752, "global_step": 556943, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.033114194869995, "global_step": 556944, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.05973219871521, "global_step": 556945, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9600584506988525, "global_step": 556946, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9864856004714966, "global_step": 556947, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0574190616607666, "global_step": 556948, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.029517650604248, "global_step": 556949, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0552752017974854, "global_step": 556950, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0069117546081543, "global_step": 556951, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.065739631652832, "global_step": 556952, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.048013687133789, "global_step": 556953, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1084227561950684, "global_step": 556954, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9856133460998535, "global_step": 556955, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0157456398010254, "global_step": 556956, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.07209849357605, "global_step": 556957, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0604796409606934, "global_step": 556958, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0563747882843018, "global_step": 556959, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.035214900970459, "global_step": 556960, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0219831466674805, "global_step": 556961, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9866206645965576, "global_step": 556962, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.001478910446167, "global_step": 556963, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0905890464782715, "global_step": 556964, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0357818603515625, "global_step": 556965, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0915355682373047, "global_step": 556966, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0584466457366943, "global_step": 556967, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.02866530418396, "global_step": 556968, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0410523414611816, "global_step": 556969, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.037835121154785, "global_step": 556970, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.038804769515991, "global_step": 556971, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9536395072937012, "global_step": 556972, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0258116722106934, "global_step": 556973, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0369277000427246, "global_step": 556974, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0380709171295166, "global_step": 556975, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0226101875305176, "global_step": 556976, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.05486798286438, "global_step": 556977, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0005946159362793, "global_step": 556978, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.8871322870254517, "global_step": 556979, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0060789585113525, "global_step": 556980, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9776992797851562, "global_step": 556981, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9407122135162354, "global_step": 556982, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9738742113113403, "global_step": 556983, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0142130851745605, "global_step": 556984, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.963987112045288, "global_step": 556985, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0293691158294678, "global_step": 556986, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9175617694854736, "global_step": 556987, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0674948692321777, "global_step": 556988, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.037301540374756, "global_step": 556989, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.993728518486023, "global_step": 556990, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0493276119232178, "global_step": 556991, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.051943778991699, "global_step": 556992, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0334389209747314, "global_step": 556993, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.075619697570801, "global_step": 556994, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.000917434692383, "global_step": 556995, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0305728912353516, "global_step": 556996, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0679917335510254, "global_step": 556997, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9773626327514648, "global_step": 556998, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0363433361053467, "global_step": 556999, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9401966333389282, "global_step": 557000, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0298452377319336, "global_step": 557001, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0885355472564697, "global_step": 557002, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0205161571502686, "global_step": 557003, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0617215633392334, "global_step": 557004, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0610063076019287, "global_step": 557005, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9680227041244507, "global_step": 557006, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.061875343322754, "global_step": 557007, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.081817626953125, "global_step": 557008, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0036041736602783, "global_step": 557009, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0486037731170654, "global_step": 557010, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0005075931549072, "global_step": 557011, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.06876540184021, "global_step": 557012, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.040499687194824, "global_step": 557013, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.103450298309326, "global_step": 557014, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.059664487838745, "global_step": 557015, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0775983333587646, "global_step": 557016, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9818322658538818, "global_step": 557017, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.973427653312683, "global_step": 557018, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0437405109405518, "global_step": 557019, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.099130392074585, "global_step": 557020, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0780370235443115, "global_step": 557021, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0298590660095215, "global_step": 557022, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9143375158309937, "global_step": 557023, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.089766263961792, "global_step": 557024, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.061603307723999, "global_step": 557025, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9643447399139404, "global_step": 557026, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9917919635772705, "global_step": 557027, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.101874589920044, "global_step": 557028, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9559550285339355, "global_step": 557029, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.001203775405884, "global_step": 557030, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9831373691558838, "global_step": 557031, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9893845319747925, "global_step": 557032, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0616705417633057, "global_step": 557033, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.047530174255371, "global_step": 557034, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0488502979278564, "global_step": 557035, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.057683229446411, "global_step": 557036, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.091946601867676, "global_step": 557037, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.031160831451416, "global_step": 557038, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0337135791778564, "global_step": 557039, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0505237579345703, "global_step": 557040, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0911030769348145, "global_step": 557041, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.078535556793213, "global_step": 557042, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9962738752365112, "global_step": 557043, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9691725969314575, "global_step": 557044, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0702874660491943, "global_step": 557045, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.066103935241699, "global_step": 557046, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.100128412246704, "global_step": 557047, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9965364933013916, "global_step": 557048, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0159287452697754, "global_step": 557049, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.8968348503112793, "global_step": 557050, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9924681186676025, "global_step": 557051, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.967466950416565, "global_step": 557052, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.050816297531128, "global_step": 557053, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.000584602355957, "global_step": 557054, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.008256435394287, "global_step": 557055, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9900505542755127, "global_step": 557056, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.051115036010742, "global_step": 557057, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9371273517608643, "global_step": 557058, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.01513409614563, "global_step": 557059, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0485079288482666, "global_step": 557060, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9741909503936768, "global_step": 557061, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0312962532043457, "global_step": 557062, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9532618522644043, "global_step": 557063, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0813205242156982, "global_step": 557064, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9468975067138672, "global_step": 557065, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9975011348724365, "global_step": 557066, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9959051609039307, "global_step": 557067, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.044861078262329, "global_step": 557068, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.034432888031006, "global_step": 557069, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0790903568267822, "global_step": 557070, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9474543333053589, "global_step": 557071, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0046935081481934, "global_step": 557072, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0477330684661865, "global_step": 557073, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.985731840133667, "global_step": 557074, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0375564098358154, "global_step": 557075, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.031949758529663, "global_step": 557076, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9824179410934448, "global_step": 557077, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0056161880493164, "global_step": 557078, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9823088645935059, "global_step": 557079, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.014719009399414, "global_step": 557080, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0180411338806152, "global_step": 557081, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.036853075027466, "global_step": 557082, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.021984100341797, "global_step": 557083, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.025628089904785, "global_step": 557084, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9976799488067627, "global_step": 557085, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.050443649291992, "global_step": 557086, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.099301815032959, "global_step": 557087, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.978814721107483, "global_step": 557088, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.05490779876709, "global_step": 557089, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0395236015319824, "global_step": 557090, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9967049360275269, "global_step": 557091, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0756518840789795, "global_step": 557092, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0649259090423584, "global_step": 557093, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.003861427307129, "global_step": 557094, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.065800905227661, "global_step": 557095, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0247952938079834, "global_step": 557096, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.981005311012268, "global_step": 557097, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.995537281036377, "global_step": 557098, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0171139240264893, "global_step": 557099, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.070539951324463, "global_step": 557100, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.03039813041687, "global_step": 557101, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0217509269714355, "global_step": 557102, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1319799423217773, "global_step": 557103, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1574959754943848, "global_step": 557104, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.029569625854492, "global_step": 557105, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9665296077728271, "global_step": 557106, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.107041358947754, "global_step": 557107, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0111687183380127, "global_step": 557108, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9921683073043823, "global_step": 557109, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.03141713142395, "global_step": 557110, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.981938123703003, "global_step": 557111, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9672832489013672, "global_step": 557112, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.06943416595459, "global_step": 557113, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0080225467681885, "global_step": 557114, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9990278482437134, "global_step": 557115, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.008342981338501, "global_step": 557116, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0217223167419434, "global_step": 557117, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9856511354446411, "global_step": 557118, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.06730580329895, "global_step": 557119, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.027163505554199, "global_step": 557120, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.012200355529785, "global_step": 557121, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0693676471710205, "global_step": 557122, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9676192998886108, "global_step": 557123, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0686216354370117, "global_step": 557124, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.073780059814453, "global_step": 557125, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.972137212753296, "global_step": 557126, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9414732456207275, "global_step": 557127, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.067260980606079, "global_step": 557128, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0239248275756836, "global_step": 557129, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0367214679718018, "global_step": 557130, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.060894727706909, "global_step": 557131, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0476808547973633, "global_step": 557132, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.057865858078003, "global_step": 557133, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0316362380981445, "global_step": 557134, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0382485389709473, "global_step": 557135, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.032755136489868, "global_step": 557136, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9657632112503052, "global_step": 557137, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0575335025787354, "global_step": 557138, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0078725814819336, "global_step": 557139, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9800647497177124, "global_step": 557140, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.8936094045639038, "global_step": 557141, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9973068237304688, "global_step": 557142, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0742135047912598, "global_step": 557143, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.050004720687866, "global_step": 557144, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9613500833511353, "global_step": 557145, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.045921564102173, "global_step": 557146, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9288136959075928, "global_step": 557147, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1008286476135254, "global_step": 557148, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0452628135681152, "global_step": 557149, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0296196937561035, "global_step": 557150, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9620293378829956, "global_step": 557151, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1143836975097656, "global_step": 557152, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0312206745147705, "global_step": 557153, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.083289623260498, "global_step": 557154, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0435469150543213, "global_step": 557155, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9963749647140503, "global_step": 557156, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9894667863845825, "global_step": 557157, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.011146306991577, "global_step": 557158, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.005714178085327, "global_step": 557159, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.073261022567749, "global_step": 557160, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.063206911087036, "global_step": 557161, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.068488597869873, "global_step": 557162, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0128655433654785, "global_step": 557163, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.117586374282837, "global_step": 557164, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1069233417510986, "global_step": 557165, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0155441761016846, "global_step": 557166, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0709304809570312, "global_step": 557167, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9554413557052612, "global_step": 557168, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.127673864364624, "global_step": 557169, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0103518962860107, "global_step": 557170, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0496749877929688, "global_step": 557171, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0565574169158936, "global_step": 557172, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0342986583709717, "global_step": 557173, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0160319805145264, "global_step": 557174, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.025226593017578, "global_step": 557175, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0520193576812744, "global_step": 557176, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9985061883926392, "global_step": 557177, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.008516311645508, "global_step": 557178, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0293421745300293, "global_step": 557179, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.043353319168091, "global_step": 557180, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.061561107635498, "global_step": 557181, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0990703105926514, "global_step": 557182, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.142841339111328, "global_step": 557183, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.075368881225586, "global_step": 557184, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0703561305999756, "global_step": 557185, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.008643388748169, "global_step": 557186, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.080366611480713, "global_step": 557187, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.99611496925354, "global_step": 557188, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9666869640350342, "global_step": 557189, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.105240821838379, "global_step": 557190, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.041994333267212, "global_step": 557191, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9109805822372437, "global_step": 557192, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.097686767578125, "global_step": 557193, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.007904291152954, "global_step": 557194, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0271565914154053, "global_step": 557195, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0346813201904297, "global_step": 557196, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9143753051757812, "global_step": 557197, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.000577688217163, "global_step": 557198, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9850386381149292, "global_step": 557199, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0896382331848145, "global_step": 557200, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1461474895477295, "global_step": 557201, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.041767120361328, "global_step": 557202, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.143125534057617, "global_step": 557203, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0431649684906006, "global_step": 557204, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.938254952430725, "global_step": 557205, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0396568775177, "global_step": 557206, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.046372413635254, "global_step": 557207, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9846813678741455, "global_step": 557208, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.045954465866089, "global_step": 557209, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0364208221435547, "global_step": 557210, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0455820560455322, "global_step": 557211, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0611422061920166, "global_step": 557212, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.930959701538086, "global_step": 557213, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.048626184463501, "global_step": 557214, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0649871826171875, "global_step": 557215, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0163872241973877, "global_step": 557216, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.066218137741089, "global_step": 557217, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9276556968688965, "global_step": 557218, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0679779052734375, "global_step": 557219, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0828537940979004, "global_step": 557220, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0806424617767334, "global_step": 557221, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9570645093917847, "global_step": 557222, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9904391765594482, "global_step": 557223, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.053830146789551, "global_step": 557224, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0981528759002686, "global_step": 557225, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0689094066619873, "global_step": 557226, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0167016983032227, "global_step": 557227, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.07141375541687, "global_step": 557228, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.060723304748535, "global_step": 557229, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9961639642715454, "global_step": 557230, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.946277379989624, "global_step": 557231, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0266926288604736, "global_step": 557232, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0956621170043945, "global_step": 557233, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9791831970214844, "global_step": 557234, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.04950213432312, "global_step": 557235, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0755457878112793, "global_step": 557236, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0412437915802, "global_step": 557237, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.075625419616699, "global_step": 557238, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.062594413757324, "global_step": 557239, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1062638759613037, "global_step": 557240, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.048830986022949, "global_step": 557241, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.982656478881836, "global_step": 557242, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0316638946533203, "global_step": 557243, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.050067186355591, "global_step": 557244, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0158748626708984, "global_step": 557245, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.024981737136841, "global_step": 557246, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.094665050506592, "global_step": 557247, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0700249671936035, "global_step": 557248, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.070470094680786, "global_step": 557249, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0056920051574707, "global_step": 557250, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0835883617401123, "global_step": 557251, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0293002128601074, "global_step": 557252, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.999100685119629, "global_step": 557253, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0491223335266113, "global_step": 557254, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0664167404174805, "global_step": 557255, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0902607440948486, "global_step": 557256, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9511278867721558, "global_step": 557257, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.088710069656372, "global_step": 557258, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.042811632156372, "global_step": 557259, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9809437990188599, "global_step": 557260, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9533995389938354, "global_step": 557261, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0005669593811035, "global_step": 557262, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0298688411712646, "global_step": 557263, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.999961018562317, "global_step": 557264, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0594065189361572, "global_step": 557265, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0386199951171875, "global_step": 557266, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.049626111984253, "global_step": 557267, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.014674663543701, "global_step": 557268, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9882756471633911, "global_step": 557269, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1204652786254883, "global_step": 557270, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.063194513320923, "global_step": 557271, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0960752964019775, "global_step": 557272, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0613644123077393, "global_step": 557273, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0786895751953125, "global_step": 557274, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0207111835479736, "global_step": 557275, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9785428047180176, "global_step": 557276, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9926379919052124, "global_step": 557277, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.056640386581421, "global_step": 557278, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.13930344581604, "global_step": 557279, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.011078357696533, "global_step": 557280, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0675692558288574, "global_step": 557281, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.024611234664917, "global_step": 557282, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0346462726593018, "global_step": 557283, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0388882160186768, "global_step": 557284, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0161211490631104, "global_step": 557285, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0473549365997314, "global_step": 557286, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.054891347885132, "global_step": 557287, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0156893730163574, "global_step": 557288, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.074608087539673, "global_step": 557289, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0356240272521973, "global_step": 557290, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.085325002670288, "global_step": 557291, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9332046508789062, "global_step": 557292, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.095001697540283, "global_step": 557293, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.005052089691162, "global_step": 557294, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.02840256690979, "global_step": 557295, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.034308433532715, "global_step": 557296, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.064068555831909, "global_step": 557297, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.043318510055542, "global_step": 557298, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.074597120285034, "global_step": 557299, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0689241886138916, "global_step": 557300, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1369776725769043, "global_step": 557301, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.9890036582946777, "global_step": 557302, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.905817985534668, "global_step": 557303, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.021212577819824, "global_step": 557304, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.1551997661590576, "global_step": 557305, "epoch": 924, "lr": 5e-05}
{"train_loss": 1.936349630355835, "global_step": 557306, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.0284364223480225, "global_step": 557307, "epoch": 924, "lr": 5e-05}
{"train_loss": 2.078296184539795, "global_step": 557308, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9964501857757568, "global_step": 557309, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9974013566970825, "global_step": 557310, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9859604835510254, "global_step": 557311, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1131787300109863, "global_step": 557312, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.112027406692505, "global_step": 557313, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0355939865112305, "global_step": 557314, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.002324342727661, "global_step": 557315, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.016604423522949, "global_step": 557316, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0855209827423096, "global_step": 557317, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.959941029548645, "global_step": 557318, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.045628786087036, "global_step": 557319, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.945505976676941, "global_step": 557320, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0063648223876953, "global_step": 557321, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0162947177886963, "global_step": 557322, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0119335651397705, "global_step": 557323, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0414934158325195, "global_step": 557324, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.98472261428833, "global_step": 557325, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9996438026428223, "global_step": 557326, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.951919436454773, "global_step": 557327, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.028155565261841, "global_step": 557328, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0198874473571777, "global_step": 557329, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0181126594543457, "global_step": 557330, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0236170291900635, "global_step": 557331, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.110952377319336, "global_step": 557332, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.02881121635437, "global_step": 557333, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1085774898529053, "global_step": 557334, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.114668130874634, "global_step": 557335, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.03574275970459, "global_step": 557336, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9831125736236572, "global_step": 557337, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0061123371124268, "global_step": 557338, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9107259511947632, "global_step": 557339, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0591964721679688, "global_step": 557340, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.007343053817749, "global_step": 557341, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.066603660583496, "global_step": 557342, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9854596853256226, "global_step": 557343, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9953250885009766, "global_step": 557344, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.93113374710083, "global_step": 557345, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0435256958007812, "global_step": 557346, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0890252590179443, "global_step": 557347, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0853188037872314, "global_step": 557348, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.050680160522461, "global_step": 557349, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0206291675567627, "global_step": 557350, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0724244117736816, "global_step": 557351, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.013658285140991, "global_step": 557352, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9237854480743408, "global_step": 557353, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9651577472686768, "global_step": 557354, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9666002988815308, "global_step": 557355, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0117287635803223, "global_step": 557356, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.036858320236206, "global_step": 557357, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9649629592895508, "global_step": 557358, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.112316846847534, "global_step": 557359, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0542848110198975, "global_step": 557360, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0587682723999023, "global_step": 557361, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9528932571411133, "global_step": 557362, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.081002950668335, "global_step": 557363, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.114445209503174, "global_step": 557364, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.019209146499634, "global_step": 557365, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0805397033691406, "global_step": 557366, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.061469078063965, "global_step": 557367, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.012333393096924, "global_step": 557368, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.943551778793335, "global_step": 557369, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.027578353881836, "global_step": 557370, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9933602809906006, "global_step": 557371, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0230698585510254, "global_step": 557372, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0631494522094727, "global_step": 557373, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9628080129623413, "global_step": 557374, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1213371753692627, "global_step": 557375, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.033745527267456, "global_step": 557376, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0794434547424316, "global_step": 557377, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0153181552886963, "global_step": 557378, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9949742555618286, "global_step": 557379, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.060645580291748, "global_step": 557380, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9396905899047852, "global_step": 557381, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9917116165161133, "global_step": 557382, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9762189388275146, "global_step": 557383, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9327597618103027, "global_step": 557384, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9943875074386597, "global_step": 557385, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9706963300704956, "global_step": 557386, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9685271978378296, "global_step": 557387, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9382941722869873, "global_step": 557388, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.076323986053467, "global_step": 557389, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.069371223449707, "global_step": 557390, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9882513284683228, "global_step": 557391, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.055171012878418, "global_step": 557392, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.026599884033203, "global_step": 557393, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9666260480880737, "global_step": 557394, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0732977390289307, "global_step": 557395, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0294108390808105, "global_step": 557396, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9562209844589233, "global_step": 557397, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9882699251174927, "global_step": 557398, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.041645050048828, "global_step": 557399, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0808401107788086, "global_step": 557400, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.003931999206543, "global_step": 557401, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0519156455993652, "global_step": 557402, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9785054922103882, "global_step": 557403, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0847039222717285, "global_step": 557404, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0461411476135254, "global_step": 557405, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.057507276535034, "global_step": 557406, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0498948097229004, "global_step": 557407, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1556038856506348, "global_step": 557408, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9216901063919067, "global_step": 557409, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1083574295043945, "global_step": 557410, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9479402303695679, "global_step": 557411, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9706705808639526, "global_step": 557412, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.033830165863037, "global_step": 557413, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1013102531433105, "global_step": 557414, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9729619026184082, "global_step": 557415, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0301287174224854, "global_step": 557416, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.102976083755493, "global_step": 557417, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0749926567077637, "global_step": 557418, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9938908815383911, "global_step": 557419, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0731163024902344, "global_step": 557420, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0370755195617676, "global_step": 557421, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9965779781341553, "global_step": 557422, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9431113004684448, "global_step": 557423, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.030487298965454, "global_step": 557424, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0436599254608154, "global_step": 557425, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0301475524902344, "global_step": 557426, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0358028411865234, "global_step": 557427, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9975838661193848, "global_step": 557428, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0734331607818604, "global_step": 557429, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9799827337265015, "global_step": 557430, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.001999855041504, "global_step": 557431, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9561210870742798, "global_step": 557432, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.047619342803955, "global_step": 557433, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0551981925964355, "global_step": 557434, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0266273021698, "global_step": 557435, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9992663860321045, "global_step": 557436, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9719762802124023, "global_step": 557437, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9881665706634521, "global_step": 557438, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0081465244293213, "global_step": 557439, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0898497104644775, "global_step": 557440, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9986563920974731, "global_step": 557441, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1047916412353516, "global_step": 557442, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.009129285812378, "global_step": 557443, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9728869199752808, "global_step": 557444, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.012922525405884, "global_step": 557445, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0595388412475586, "global_step": 557446, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0029141902923584, "global_step": 557447, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.033599615097046, "global_step": 557448, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0723040103912354, "global_step": 557449, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.038820505142212, "global_step": 557450, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0441532135009766, "global_step": 557451, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0507659912109375, "global_step": 557452, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.10068941116333, "global_step": 557453, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0246293544769287, "global_step": 557454, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0404269695281982, "global_step": 557455, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.062971353530884, "global_step": 557456, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1019861698150635, "global_step": 557457, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9591397047042847, "global_step": 557458, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9625983238220215, "global_step": 557459, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.036527395248413, "global_step": 557460, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0464706420898438, "global_step": 557461, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0359768867492676, "global_step": 557462, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0045504570007324, "global_step": 557463, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9712893962860107, "global_step": 557464, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.073737382888794, "global_step": 557465, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.042391061782837, "global_step": 557466, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9728909730911255, "global_step": 557467, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0074939727783203, "global_step": 557468, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9653058052062988, "global_step": 557469, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.071720838546753, "global_step": 557470, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9906009435653687, "global_step": 557471, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9744700193405151, "global_step": 557472, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0163397789001465, "global_step": 557473, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9992437362670898, "global_step": 557474, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9989064931869507, "global_step": 557475, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.068525552749634, "global_step": 557476, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9197334051132202, "global_step": 557477, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0844104290008545, "global_step": 557478, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9356766939163208, "global_step": 557479, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9865806102752686, "global_step": 557480, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.003980875015259, "global_step": 557481, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0022711753845215, "global_step": 557482, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.054661512374878, "global_step": 557483, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.967670202255249, "global_step": 557484, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0226967334747314, "global_step": 557485, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.013610363006592, "global_step": 557486, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0560688972473145, "global_step": 557487, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9093101024627686, "global_step": 557488, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0371596813201904, "global_step": 557489, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0535521507263184, "global_step": 557490, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0390491485595703, "global_step": 557491, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.973803162574768, "global_step": 557492, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9384431838989258, "global_step": 557493, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9653571844100952, "global_step": 557494, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.016292095184326, "global_step": 557495, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.029981851577759, "global_step": 557496, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.101290225982666, "global_step": 557497, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.068819046020508, "global_step": 557498, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1015024185180664, "global_step": 557499, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0132596492767334, "global_step": 557500, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0351390838623047, "global_step": 557501, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1261000633239746, "global_step": 557502, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0414116382598877, "global_step": 557503, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0824129581451416, "global_step": 557504, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0607733726501465, "global_step": 557505, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0448577404022217, "global_step": 557506, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.079467296600342, "global_step": 557507, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9577122926712036, "global_step": 557508, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9571419954299927, "global_step": 557509, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9770616292953491, "global_step": 557510, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1207172870635986, "global_step": 557511, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9845455884933472, "global_step": 557512, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.047555685043335, "global_step": 557513, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.014622926712036, "global_step": 557514, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.95868980884552, "global_step": 557515, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0385584831237793, "global_step": 557516, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9494619369506836, "global_step": 557517, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0304648876190186, "global_step": 557518, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0090649127960205, "global_step": 557519, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0331618785858154, "global_step": 557520, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.016892433166504, "global_step": 557521, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0393126010894775, "global_step": 557522, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0756280422210693, "global_step": 557523, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.070436716079712, "global_step": 557524, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0267555713653564, "global_step": 557525, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0601613521575928, "global_step": 557526, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9608690738677979, "global_step": 557527, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.060279607772827, "global_step": 557528, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0882246494293213, "global_step": 557529, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.97727370262146, "global_step": 557530, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0150835514068604, "global_step": 557531, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.076889991760254, "global_step": 557532, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0439136028289795, "global_step": 557533, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0317740440368652, "global_step": 557534, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.019167423248291, "global_step": 557535, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.023890495300293, "global_step": 557536, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9939243793487549, "global_step": 557537, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0317604541778564, "global_step": 557538, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0470633506774902, "global_step": 557539, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.979169487953186, "global_step": 557540, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9688317775726318, "global_step": 557541, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0498483180999756, "global_step": 557542, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9729429483413696, "global_step": 557543, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0057308673858643, "global_step": 557544, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.059274673461914, "global_step": 557545, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.078819990158081, "global_step": 557546, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0347535610198975, "global_step": 557547, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.94508957862854, "global_step": 557548, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.026803731918335, "global_step": 557549, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0228495597839355, "global_step": 557550, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9703240394592285, "global_step": 557551, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.069136381149292, "global_step": 557552, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0041277408599854, "global_step": 557553, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1453745365142822, "global_step": 557554, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9965145587921143, "global_step": 557555, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.050546884536743, "global_step": 557556, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9836547374725342, "global_step": 557557, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9662456512451172, "global_step": 557558, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0610673427581787, "global_step": 557559, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.130173921585083, "global_step": 557560, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0375728607177734, "global_step": 557561, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0492377281188965, "global_step": 557562, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0527594089508057, "global_step": 557563, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0109212398529053, "global_step": 557564, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9620144367218018, "global_step": 557565, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.962136149406433, "global_step": 557566, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9794349670410156, "global_step": 557567, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.109722137451172, "global_step": 557568, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1032915115356445, "global_step": 557569, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.990626573562622, "global_step": 557570, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0534000396728516, "global_step": 557571, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0229310989379883, "global_step": 557572, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0158817768096924, "global_step": 557573, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.021512269973755, "global_step": 557574, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.053865432739258, "global_step": 557575, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0396506786346436, "global_step": 557576, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0201218128204346, "global_step": 557577, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.084078788757324, "global_step": 557578, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0258398056030273, "global_step": 557579, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9399794340133667, "global_step": 557580, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.042457342147827, "global_step": 557581, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0059189796447754, "global_step": 557582, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0481796264648438, "global_step": 557583, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9676358699798584, "global_step": 557584, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0306472778320312, "global_step": 557585, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.012613534927368, "global_step": 557586, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0147182941436768, "global_step": 557587, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.001288414001465, "global_step": 557588, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9554296731948853, "global_step": 557589, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9762624502182007, "global_step": 557590, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9922759532928467, "global_step": 557591, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.994383692741394, "global_step": 557592, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.016836643218994, "global_step": 557593, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9723567962646484, "global_step": 557594, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.015165328979492, "global_step": 557595, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.959189772605896, "global_step": 557596, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.053466796875, "global_step": 557597, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9325257539749146, "global_step": 557598, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9834210872650146, "global_step": 557599, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0690112113952637, "global_step": 557600, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0887248516082764, "global_step": 557601, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0282065868377686, "global_step": 557602, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9794689416885376, "global_step": 557603, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.011770486831665, "global_step": 557604, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.112605333328247, "global_step": 557605, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0566906929016113, "global_step": 557606, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.013566493988037, "global_step": 557607, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.039642810821533, "global_step": 557608, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0201210975646973, "global_step": 557609, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9818083047866821, "global_step": 557610, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9767197370529175, "global_step": 557611, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.012007236480713, "global_step": 557612, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9921108484268188, "global_step": 557613, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.057398557662964, "global_step": 557614, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0764997005462646, "global_step": 557615, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.04606032371521, "global_step": 557616, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0892562866210938, "global_step": 557617, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9712200164794922, "global_step": 557618, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0936391353607178, "global_step": 557619, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9594111442565918, "global_step": 557620, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9733260869979858, "global_step": 557621, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.128798246383667, "global_step": 557622, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.03951358795166, "global_step": 557623, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.076385974884033, "global_step": 557624, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0966439247131348, "global_step": 557625, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.016219139099121, "global_step": 557626, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.04290509223938, "global_step": 557627, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.095649242401123, "global_step": 557628, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9867277145385742, "global_step": 557629, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.023136615753174, "global_step": 557630, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.105113983154297, "global_step": 557631, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0018341541290283, "global_step": 557632, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0491480827331543, "global_step": 557633, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0271639823913574, "global_step": 557634, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0043697357177734, "global_step": 557635, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9577099084854126, "global_step": 557636, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9927603006362915, "global_step": 557637, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9693315029144287, "global_step": 557638, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0932865142822266, "global_step": 557639, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9774279594421387, "global_step": 557640, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9368939399719238, "global_step": 557641, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9761558771133423, "global_step": 557642, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9723916053771973, "global_step": 557643, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9521929025650024, "global_step": 557644, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.024630069732666, "global_step": 557645, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.039870500564575, "global_step": 557646, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0845630168914795, "global_step": 557647, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.085278272628784, "global_step": 557648, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9810731410980225, "global_step": 557649, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9998388290405273, "global_step": 557650, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9393959045410156, "global_step": 557651, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.039254903793335, "global_step": 557652, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.106198310852051, "global_step": 557653, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0536258220672607, "global_step": 557654, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.083595037460327, "global_step": 557655, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0351336002349854, "global_step": 557656, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.012373447418213, "global_step": 557657, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.061472177505493, "global_step": 557658, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9724032878875732, "global_step": 557659, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9986436367034912, "global_step": 557660, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0972883701324463, "global_step": 557661, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0818002223968506, "global_step": 557662, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.041640043258667, "global_step": 557663, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.036792755126953, "global_step": 557664, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0154449939727783, "global_step": 557665, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.026571035385132, "global_step": 557666, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.040231943130493, "global_step": 557667, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0672860145568848, "global_step": 557668, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0289125442504883, "global_step": 557669, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.02553391456604, "global_step": 557670, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0283799171447754, "global_step": 557671, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9714676141738892, "global_step": 557672, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0310235023498535, "global_step": 557673, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9997323751449585, "global_step": 557674, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0302987098693848, "global_step": 557675, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.013632297515869, "global_step": 557676, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.052351474761963, "global_step": 557677, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0338118076324463, "global_step": 557678, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0233476161956787, "global_step": 557679, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9613254070281982, "global_step": 557680, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.02462100982666, "global_step": 557681, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0828983783721924, "global_step": 557682, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.017082452774048, "global_step": 557683, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.8669347763061523, "global_step": 557684, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0512702465057373, "global_step": 557685, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9875131845474243, "global_step": 557686, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.978495717048645, "global_step": 557687, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9726407527923584, "global_step": 557688, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.972460389137268, "global_step": 557689, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1405389308929443, "global_step": 557690, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.024134635925293, "global_step": 557691, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.045630931854248, "global_step": 557692, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9405819177627563, "global_step": 557693, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0431087017059326, "global_step": 557694, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.030210494995117, "global_step": 557695, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0096657276153564, "global_step": 557696, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9747802019119263, "global_step": 557697, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.123730182647705, "global_step": 557698, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.068507671356201, "global_step": 557699, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9890077114105225, "global_step": 557700, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.058624029159546, "global_step": 557701, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0141680240631104, "global_step": 557702, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.062549352645874, "global_step": 557703, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0898070335388184, "global_step": 557704, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.017185926437378, "global_step": 557705, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0280678272247314, "global_step": 557706, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.083042860031128, "global_step": 557707, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.073749303817749, "global_step": 557708, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9887510538101196, "global_step": 557709, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9319915771484375, "global_step": 557710, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0385565757751465, "global_step": 557711, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.051220178604126, "global_step": 557712, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9808417558670044, "global_step": 557713, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9813971519470215, "global_step": 557714, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.002943754196167, "global_step": 557715, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9621046781539917, "global_step": 557716, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9229882955551147, "global_step": 557717, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.079150915145874, "global_step": 557718, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0026392936706543, "global_step": 557719, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0753631591796875, "global_step": 557720, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0931200981140137, "global_step": 557721, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.063711404800415, "global_step": 557722, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0892441272735596, "global_step": 557723, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.074723482131958, "global_step": 557724, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0897157192230225, "global_step": 557725, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9836740493774414, "global_step": 557726, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9921804666519165, "global_step": 557727, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9842911958694458, "global_step": 557728, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9851093292236328, "global_step": 557729, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.135995864868164, "global_step": 557730, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.068682909011841, "global_step": 557731, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.022400140762329, "global_step": 557732, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.002474546432495, "global_step": 557733, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9723024368286133, "global_step": 557734, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.070362091064453, "global_step": 557735, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.044318437576294, "global_step": 557736, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9994406700134277, "global_step": 557737, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.020904779434204, "global_step": 557738, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0735814571380615, "global_step": 557739, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.029872417449951, "global_step": 557740, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9953334331512451, "global_step": 557741, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0096912384033203, "global_step": 557742, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9843153953552246, "global_step": 557743, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9555538892745972, "global_step": 557744, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0332565307617188, "global_step": 557745, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0871927738189697, "global_step": 557746, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0281901359558105, "global_step": 557747, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1274123191833496, "global_step": 557748, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.049276828765869, "global_step": 557749, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0065510272979736, "global_step": 557750, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0321831703186035, "global_step": 557751, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0218710899353027, "global_step": 557752, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0820298194885254, "global_step": 557753, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0003840923309326, "global_step": 557754, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9682538509368896, "global_step": 557755, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0868561267852783, "global_step": 557756, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.034539222717285, "global_step": 557757, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9721426963806152, "global_step": 557758, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.954803228378296, "global_step": 557759, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.008249044418335, "global_step": 557760, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0886104106903076, "global_step": 557761, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0307374000549316, "global_step": 557762, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1684865951538086, "global_step": 557763, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.975766897201538, "global_step": 557764, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9758734703063965, "global_step": 557765, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1009905338287354, "global_step": 557766, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1187968254089355, "global_step": 557767, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0239017009735107, "global_step": 557768, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0032272338867188, "global_step": 557769, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9545557498931885, "global_step": 557770, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.062617778778076, "global_step": 557771, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9929206371307373, "global_step": 557772, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.935583472251892, "global_step": 557773, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.012995958328247, "global_step": 557774, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.964298963546753, "global_step": 557775, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.01981520652771, "global_step": 557776, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0694847106933594, "global_step": 557777, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.105010986328125, "global_step": 557778, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9773473739624023, "global_step": 557779, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.989996314048767, "global_step": 557780, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0577621459960938, "global_step": 557781, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.08257794380188, "global_step": 557782, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9824638366699219, "global_step": 557783, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9649436473846436, "global_step": 557784, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.107375144958496, "global_step": 557785, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.143340826034546, "global_step": 557786, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.04256534576416, "global_step": 557787, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0200607776641846, "global_step": 557788, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0017683506011963, "global_step": 557789, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.002145528793335, "global_step": 557790, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0542445182800293, "global_step": 557791, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0045018196105957, "global_step": 557792, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.010847806930542, "global_step": 557793, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.093597888946533, "global_step": 557794, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.069150447845459, "global_step": 557795, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9250365495681763, "global_step": 557796, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0753626823425293, "global_step": 557797, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0711920261383057, "global_step": 557798, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0539608001708984, "global_step": 557799, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0414187908172607, "global_step": 557800, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9452906847000122, "global_step": 557801, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.007232904434204, "global_step": 557802, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.016803741455078, "global_step": 557803, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.196650266647339, "global_step": 557804, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.084498405456543, "global_step": 557805, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0574564933776855, "global_step": 557806, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.034012794494629, "global_step": 557807, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9946331977844238, "global_step": 557808, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0190439224243164, "global_step": 557809, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.00632643699646, "global_step": 557810, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9694616794586182, "global_step": 557811, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0975801944732666, "global_step": 557812, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9816676378250122, "global_step": 557813, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1066524982452393, "global_step": 557814, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1230525970458984, "global_step": 557815, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.036144971847534, "global_step": 557816, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0425198078155518, "global_step": 557817, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.082003116607666, "global_step": 557818, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1331794261932373, "global_step": 557819, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9858028888702393, "global_step": 557820, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9081135988235474, "global_step": 557821, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0817179679870605, "global_step": 557822, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0326426029205322, "global_step": 557823, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.037038803100586, "global_step": 557824, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.026423215866089, "global_step": 557825, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.012993574142456, "global_step": 557826, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0857577323913574, "global_step": 557827, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.068384885787964, "global_step": 557828, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0090396404266357, "global_step": 557829, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0535733699798584, "global_step": 557830, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0089786052703857, "global_step": 557831, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0755817890167236, "global_step": 557832, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0425217151641846, "global_step": 557833, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9970831871032715, "global_step": 557834, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.087554931640625, "global_step": 557835, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.035444974899292, "global_step": 557836, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0718674659729004, "global_step": 557837, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9886419773101807, "global_step": 557838, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0761260986328125, "global_step": 557839, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.079181671142578, "global_step": 557840, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9695323705673218, "global_step": 557841, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1095705032348633, "global_step": 557842, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0023603439331055, "global_step": 557843, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.080101728439331, "global_step": 557844, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.028397798538208, "global_step": 557845, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.052732467651367, "global_step": 557846, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0317492485046387, "global_step": 557847, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9347119331359863, "global_step": 557848, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.944855809211731, "global_step": 557849, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0783748626708984, "global_step": 557850, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9888149499893188, "global_step": 557851, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.994589924812317, "global_step": 557852, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.057356595993042, "global_step": 557853, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.034364700317383, "global_step": 557854, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0748631954193115, "global_step": 557855, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9824836254119873, "global_step": 557856, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.09698486328125, "global_step": 557857, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0760462284088135, "global_step": 557858, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0516090393066406, "global_step": 557859, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.047358751296997, "global_step": 557860, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0096566677093506, "global_step": 557861, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.063741445541382, "global_step": 557862, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0268115997314453, "global_step": 557863, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.977587103843689, "global_step": 557864, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0520551204681396, "global_step": 557865, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0065126419067383, "global_step": 557866, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9745899438858032, "global_step": 557867, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.041656970977783, "global_step": 557868, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0574021339416504, "global_step": 557869, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0676157474517822, "global_step": 557870, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.06583309173584, "global_step": 557871, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.048069477081299, "global_step": 557872, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0720582008361816, "global_step": 557873, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0172979831695557, "global_step": 557874, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.000610113143921, "global_step": 557875, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.037283420562744, "global_step": 557876, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0627024173736572, "global_step": 557877, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1083438396453857, "global_step": 557878, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0005202293395996, "global_step": 557879, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9538936614990234, "global_step": 557880, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.077672243118286, "global_step": 557881, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.023860216140747, "global_step": 557882, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.053225517272949, "global_step": 557883, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.077521324157715, "global_step": 557884, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.026167392730713, "global_step": 557885, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.035151243209839, "global_step": 557886, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0427536964416504, "global_step": 557887, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.994605302810669, "global_step": 557888, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9845752716064453, "global_step": 557889, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.038365125656128, "global_step": 557890, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.151582717895508, "global_step": 557891, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.074266195297241, "global_step": 557892, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.036219835281372, "global_step": 557893, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0971832275390625, "global_step": 557894, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0835633277893066, "global_step": 557895, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.8660223484039307, "global_step": 557896, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9955202341079712, "global_step": 557897, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0086207389831543, "global_step": 557898, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0613322257995605, "global_step": 557899, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9125666618347168, "global_step": 557900, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.117779493331909, "global_step": 557901, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.04490327835083, "global_step": 557902, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9923580884933472, "global_step": 557903, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.967590570449829, "global_step": 557904, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9938699007034302, "global_step": 557905, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.96950101852417, "global_step": 557906, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9889369010925293, "global_step": 557907, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9500553607940674, "global_step": 557908, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9895727634429932, "global_step": 557909, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9855858087539673, "global_step": 557910, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1416985988616943, "global_step": 557911, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.048241138458252, "global_step": 557912, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.127267599105835, "global_step": 557913, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0580222606658936, "global_step": 557914, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0544257164001465, "global_step": 557915, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.061506986618042, "global_step": 557916, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.110779285430908, "global_step": 557917, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.044980525970459, "global_step": 557918, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0909628868103027, "global_step": 557919, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0338478088378906, "global_step": 557920, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0361483097076416, "global_step": 557921, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1204428672790527, "global_step": 557922, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.05782413482666, "global_step": 557923, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0488057136535645, "global_step": 557924, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0211293697357178, "global_step": 557925, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1436684131622314, "global_step": 557926, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9749391078948975, "global_step": 557927, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.026205539703369, "global_step": 557928, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1686480045318604, "global_step": 557929, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.057929277420044, "global_step": 557930, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0466365814208984, "global_step": 557931, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1329469680786133, "global_step": 557932, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.046175241470337, "global_step": 557933, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0052874088287354, "global_step": 557934, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0148770809173584, "global_step": 557935, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.006803035736084, "global_step": 557936, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.001917600631714, "global_step": 557937, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.095104455947876, "global_step": 557938, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.133086681365967, "global_step": 557939, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0398378372192383, "global_step": 557940, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1118736267089844, "global_step": 557941, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0480635166168213, "global_step": 557942, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0027315616607666, "global_step": 557943, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.039491653442383, "global_step": 557944, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.087831974029541, "global_step": 557945, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0373425483703613, "global_step": 557946, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.071786403656006, "global_step": 557947, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0259599685668945, "global_step": 557948, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1066067218780518, "global_step": 557949, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9750117063522339, "global_step": 557950, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.031200408935547, "global_step": 557951, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0877785682678223, "global_step": 557952, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0728671550750732, "global_step": 557953, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.035593271255493, "global_step": 557954, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0016582012176514, "global_step": 557955, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0299134254455566, "global_step": 557956, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0945162773132324, "global_step": 557957, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9367287158966064, "global_step": 557958, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0281057357788086, "global_step": 557959, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1269495487213135, "global_step": 557960, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.996749997138977, "global_step": 557961, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.07545804977417, "global_step": 557962, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9615609645843506, "global_step": 557963, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0804426670074463, "global_step": 557964, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0069386959075928, "global_step": 557965, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9889274835586548, "global_step": 557966, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9980746507644653, "global_step": 557967, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.145404100418091, "global_step": 557968, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.060274124145508, "global_step": 557969, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0658440589904785, "global_step": 557970, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0783579349517822, "global_step": 557971, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0499725341796875, "global_step": 557972, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0400121212005615, "global_step": 557973, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9759635925292969, "global_step": 557974, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0856757164001465, "global_step": 557975, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0503995418548584, "global_step": 557976, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.000497341156006, "global_step": 557977, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0347564220428467, "global_step": 557978, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0190536975860596, "global_step": 557979, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0117881298065186, "global_step": 557980, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9756406545639038, "global_step": 557981, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.021430492401123, "global_step": 557982, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1554908752441406, "global_step": 557983, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0303874015808105, "global_step": 557984, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9557431936264038, "global_step": 557985, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9710761308670044, "global_step": 557986, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0705904960632324, "global_step": 557987, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9871269464492798, "global_step": 557988, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1524977684020996, "global_step": 557989, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.059584856033325, "global_step": 557990, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1396305561065674, "global_step": 557991, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.022808313369751, "global_step": 557992, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.980420470237732, "global_step": 557993, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.058619976043701, "global_step": 557994, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0548996925354004, "global_step": 557995, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.987120270729065, "global_step": 557996, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.004422903060913, "global_step": 557997, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9923275709152222, "global_step": 557998, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0819737911224365, "global_step": 557999, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.042940378189087, "global_step": 558000, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0844199657440186, "global_step": 558001, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0511176586151123, "global_step": 558002, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.946108102798462, "global_step": 558003, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9917088747024536, "global_step": 558004, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0738961696624756, "global_step": 558005, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.126445770263672, "global_step": 558006, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9536638259887695, "global_step": 558007, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.021265745162964, "global_step": 558008, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9690808057785034, "global_step": 558009, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.03399658203125, "global_step": 558010, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0508906841278076, "global_step": 558011, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9803569316864014, "global_step": 558012, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.994786024093628, "global_step": 558013, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9626563787460327, "global_step": 558014, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0222856998443604, "global_step": 558015, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.032512903213501, "global_step": 558016, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0076661109924316, "global_step": 558017, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.005629301071167, "global_step": 558018, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.93063223361969, "global_step": 558019, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.136876106262207, "global_step": 558020, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.006592273712158, "global_step": 558021, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0372276306152344, "global_step": 558022, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0054094791412354, "global_step": 558023, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0374867916107178, "global_step": 558024, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.010899066925049, "global_step": 558025, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9832979440689087, "global_step": 558026, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0823915004730225, "global_step": 558027, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9175326824188232, "global_step": 558028, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.100327730178833, "global_step": 558029, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.106534004211426, "global_step": 558030, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.987577199935913, "global_step": 558031, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.032691478729248, "global_step": 558032, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0336649417877197, "global_step": 558033, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0333621501922607, "global_step": 558034, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0677402019500732, "global_step": 558035, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9918758869171143, "global_step": 558036, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.042018413543701, "global_step": 558037, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0775578022003174, "global_step": 558038, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0783865451812744, "global_step": 558039, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0043411254882812, "global_step": 558040, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0477561950683594, "global_step": 558041, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.143235683441162, "global_step": 558042, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0550496578216553, "global_step": 558043, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.011561155319214, "global_step": 558044, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.997658610343933, "global_step": 558045, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0781867504119873, "global_step": 558046, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.037654161453247, "global_step": 558047, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0599863529205322, "global_step": 558048, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0504884719848633, "global_step": 558049, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.028116226196289, "global_step": 558050, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.049849271774292, "global_step": 558051, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0338375568389893, "global_step": 558052, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0476644039154053, "global_step": 558053, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.027930974960327, "global_step": 558054, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9442784786224365, "global_step": 558055, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9808037281036377, "global_step": 558056, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.066821813583374, "global_step": 558057, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0336172580718994, "global_step": 558058, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0364272594451904, "global_step": 558059, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.020721912384033, "global_step": 558060, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9756749868392944, "global_step": 558061, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9930588006973267, "global_step": 558062, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0766170024871826, "global_step": 558063, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0327308177948, "global_step": 558064, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0328545570373535, "global_step": 558065, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.964690089225769, "global_step": 558066, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.068915843963623, "global_step": 558067, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0471315383911133, "global_step": 558068, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9835553169250488, "global_step": 558069, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9963626861572266, "global_step": 558070, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.060706853866577, "global_step": 558071, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0014171600341797, "global_step": 558072, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9273711442947388, "global_step": 558073, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0744919776916504, "global_step": 558074, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9971531629562378, "global_step": 558075, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9560319185256958, "global_step": 558076, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.029358386993408, "global_step": 558077, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.080446481704712, "global_step": 558078, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.004033327102661, "global_step": 558079, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0889945030212402, "global_step": 558080, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.995392918586731, "global_step": 558081, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9903417825698853, "global_step": 558082, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9821327924728394, "global_step": 558083, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0506837368011475, "global_step": 558084, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0348575115203857, "global_step": 558085, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1229052543640137, "global_step": 558086, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1114461421966553, "global_step": 558087, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.054457187652588, "global_step": 558088, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.020017147064209, "global_step": 558089, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1064178943634033, "global_step": 558090, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.096900224685669, "global_step": 558091, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0590412616729736, "global_step": 558092, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.96851646900177, "global_step": 558093, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.026249408721924, "global_step": 558094, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1048343181610107, "global_step": 558095, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0159244537353516, "global_step": 558096, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0175998210906982, "global_step": 558097, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0809144973754883, "global_step": 558098, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9858983755111694, "global_step": 558099, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9709607362747192, "global_step": 558100, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.050537347793579, "global_step": 558101, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.066138505935669, "global_step": 558102, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0479795932769775, "global_step": 558103, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.035954475402832, "global_step": 558104, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0794084072113037, "global_step": 558105, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9499921798706055, "global_step": 558106, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9556878805160522, "global_step": 558107, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0684750080108643, "global_step": 558108, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0444555282592773, "global_step": 558109, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.009521484375, "global_step": 558110, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.050607204437256, "global_step": 558111, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1120078563690186, "global_step": 558112, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.003601312637329, "global_step": 558113, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.029585599899292, "global_step": 558114, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0949153900146484, "global_step": 558115, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0283150672912598, "global_step": 558116, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0086207389831543, "global_step": 558117, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.079179286956787, "global_step": 558118, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.079389810562134, "global_step": 558119, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0290448665618896, "global_step": 558120, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.090745687484741, "global_step": 558121, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.075615167617798, "global_step": 558122, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.996888518333435, "global_step": 558123, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.044290065765381, "global_step": 558124, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0549397468566895, "global_step": 558125, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0451738834381104, "global_step": 558126, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.097949504852295, "global_step": 558127, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0395443439483643, "global_step": 558128, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0841825008392334, "global_step": 558129, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9618793725967407, "global_step": 558130, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0636892318725586, "global_step": 558131, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1258509159088135, "global_step": 558132, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.046405076980591, "global_step": 558133, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9840105772018433, "global_step": 558134, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.038327217102051, "global_step": 558135, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9442477226257324, "global_step": 558136, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0677852630615234, "global_step": 558137, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9916437864303589, "global_step": 558138, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.096205949783325, "global_step": 558139, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0778145790100098, "global_step": 558140, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9670161008834839, "global_step": 558141, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.095564365386963, "global_step": 558142, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0122244358062744, "global_step": 558143, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0850818157196045, "global_step": 558144, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0913479328155518, "global_step": 558145, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.011448621749878, "global_step": 558146, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9897867441177368, "global_step": 558147, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0729949474334717, "global_step": 558148, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9923598766326904, "global_step": 558149, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.011387586593628, "global_step": 558150, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.072317361831665, "global_step": 558151, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.015615701675415, "global_step": 558152, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9761394262313843, "global_step": 558153, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9568853378295898, "global_step": 558154, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0671603679656982, "global_step": 558155, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0441248416900635, "global_step": 558156, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0255913734436035, "global_step": 558157, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0139670372009277, "global_step": 558158, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0575335025787354, "global_step": 558159, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0387260913848877, "global_step": 558160, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.98861563205719, "global_step": 558161, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0552382469177246, "global_step": 558162, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0202255249023438, "global_step": 558163, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0356829166412354, "global_step": 558164, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0704197883605957, "global_step": 558165, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0338635444641113, "global_step": 558166, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9468379020690918, "global_step": 558167, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9893949031829834, "global_step": 558168, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.947426199913025, "global_step": 558169, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.036580801010132, "global_step": 558170, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0493524074554443, "global_step": 558171, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.015300750732422, "global_step": 558172, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.00848388671875, "global_step": 558173, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.937610149383545, "global_step": 558174, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0138580799102783, "global_step": 558175, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.005592107772827, "global_step": 558176, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.063384532928467, "global_step": 558177, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.037118673324585, "global_step": 558178, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1066102981567383, "global_step": 558179, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0876779556274414, "global_step": 558180, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0615224838256836, "global_step": 558181, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0782368183135986, "global_step": 558182, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0498409271240234, "global_step": 558183, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9778767824172974, "global_step": 558184, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.01442289352417, "global_step": 558185, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.07745099067688, "global_step": 558186, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9245021343231201, "global_step": 558187, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9738976955413818, "global_step": 558188, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.084822416305542, "global_step": 558189, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.065173387527466, "global_step": 558190, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.127896547317505, "global_step": 558191, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.133341073989868, "global_step": 558192, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1130573749542236, "global_step": 558193, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0201315879821777, "global_step": 558194, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9464601278305054, "global_step": 558195, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9886322021484375, "global_step": 558196, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0589678287506104, "global_step": 558197, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.962081789970398, "global_step": 558198, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.096357583999634, "global_step": 558199, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.947033166885376, "global_step": 558200, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.958721399307251, "global_step": 558201, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.034445285797119, "global_step": 558202, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0559091567993164, "global_step": 558203, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.06333327293396, "global_step": 558204, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0563831329345703, "global_step": 558205, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.037019968032837, "global_step": 558206, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9845359325408936, "global_step": 558207, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.004988193511963, "global_step": 558208, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0532608032226562, "global_step": 558209, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0647192001342773, "global_step": 558210, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.001793384552002, "global_step": 558211, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.081742525100708, "global_step": 558212, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0476174354553223, "global_step": 558213, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9887773990631104, "global_step": 558214, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.033125400543213, "global_step": 558215, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9510693550109863, "global_step": 558216, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0125465393066406, "global_step": 558217, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0622265338897705, "global_step": 558218, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.107285737991333, "global_step": 558219, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0697109699249268, "global_step": 558220, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1040637493133545, "global_step": 558221, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9544951915740967, "global_step": 558222, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.043278694152832, "global_step": 558223, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.031472682952881, "global_step": 558224, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.040426731109619, "global_step": 558225, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0834801197052, "global_step": 558226, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.013913869857788, "global_step": 558227, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9623292684555054, "global_step": 558228, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0066165924072266, "global_step": 558229, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9872311353683472, "global_step": 558230, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9555268287658691, "global_step": 558231, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9815049171447754, "global_step": 558232, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9484766721725464, "global_step": 558233, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9798588752746582, "global_step": 558234, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.057551622390747, "global_step": 558235, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.026383399963379, "global_step": 558236, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0619235038757324, "global_step": 558237, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.084963321685791, "global_step": 558238, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9813323020935059, "global_step": 558239, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9418727159500122, "global_step": 558240, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.040564775466919, "global_step": 558241, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0468671321868896, "global_step": 558242, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9849116802215576, "global_step": 558243, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0561413764953613, "global_step": 558244, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.01850962638855, "global_step": 558245, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1180472373962402, "global_step": 558246, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9950977563858032, "global_step": 558247, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.021423578262329, "global_step": 558248, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9686424732208252, "global_step": 558249, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0641236305236816, "global_step": 558250, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.013622760772705, "global_step": 558251, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.127209424972534, "global_step": 558252, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.017296314239502, "global_step": 558253, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.052269697189331, "global_step": 558254, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0597541332244873, "global_step": 558255, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.927032709121704, "global_step": 558256, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0080533027648926, "global_step": 558257, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.9965567588806152, "global_step": 558258, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.118014097213745, "global_step": 558259, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0817859172821045, "global_step": 558260, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.070270538330078, "global_step": 558261, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0276596546173096, "global_step": 558262, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0320699214935303, "global_step": 558263, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.086625814437866, "global_step": 558264, "epoch": 925, "lr": 5e-05}
{"train_loss": 1.974879264831543, "global_step": 558265, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0571370124816895, "global_step": 558266, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.001307964324951, "global_step": 558267, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0341522693634033, "global_step": 558268, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1139049530029297, "global_step": 558269, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0059354305267334, "global_step": 558270, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0592825412750244, "global_step": 558271, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.061677932739258, "global_step": 558272, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.106487989425659, "global_step": 558273, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0671403408050537, "global_step": 558274, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0463979244232178, "global_step": 558275, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.0299739837646484, "global_step": 558276, "epoch": 925, "lr": 5e-05}
{"train_loss": 2.1098103523254395, "global_step": 558277, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.095634937286377, "global_step": 558278, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9386729001998901, "global_step": 558279, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0049386024475098, "global_step": 558280, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0770084857940674, "global_step": 558281, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9529396295547485, "global_step": 558282, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0531961917877197, "global_step": 558283, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0433080196380615, "global_step": 558284, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0197510719299316, "global_step": 558285, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9270668029785156, "global_step": 558286, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0784873962402344, "global_step": 558287, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.954659342765808, "global_step": 558288, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0221805572509766, "global_step": 558289, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0044896602630615, "global_step": 558290, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0453057289123535, "global_step": 558291, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9403365850448608, "global_step": 558292, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0310564041137695, "global_step": 558293, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0121285915374756, "global_step": 558294, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.025810956954956, "global_step": 558295, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9482743740081787, "global_step": 558296, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.065528631210327, "global_step": 558297, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9982376098632812, "global_step": 558298, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.990138292312622, "global_step": 558299, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0757923126220703, "global_step": 558300, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9568208456039429, "global_step": 558301, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.920703649520874, "global_step": 558302, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9830448627471924, "global_step": 558303, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.069784641265869, "global_step": 558304, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9755301475524902, "global_step": 558305, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9650771617889404, "global_step": 558306, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9736429452896118, "global_step": 558307, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0452487468719482, "global_step": 558308, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9924637079238892, "global_step": 558309, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9701552391052246, "global_step": 558310, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9252963066101074, "global_step": 558311, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0414090156555176, "global_step": 558312, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0468666553497314, "global_step": 558313, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.070566177368164, "global_step": 558314, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0419270992279053, "global_step": 558315, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9957993030548096, "global_step": 558316, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.106529712677002, "global_step": 558317, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0201587677001953, "global_step": 558318, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9923864603042603, "global_step": 558319, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.033811092376709, "global_step": 558320, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.08009934425354, "global_step": 558321, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9764001369476318, "global_step": 558322, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.003325939178467, "global_step": 558323, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.091689109802246, "global_step": 558324, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.044182300567627, "global_step": 558325, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0154950618743896, "global_step": 558326, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9984142780303955, "global_step": 558327, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0402939319610596, "global_step": 558328, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0088720321655273, "global_step": 558329, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.060451030731201, "global_step": 558330, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0123932361602783, "global_step": 558331, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0736160278320312, "global_step": 558332, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0646615028381348, "global_step": 558333, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0064377784729004, "global_step": 558334, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.072603702545166, "global_step": 558335, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.133267879486084, "global_step": 558336, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9800615310668945, "global_step": 558337, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.91953444480896, "global_step": 558338, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0442731380462646, "global_step": 558339, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.017489433288574, "global_step": 558340, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9919307231903076, "global_step": 558341, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0329477787017822, "global_step": 558342, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0957844257354736, "global_step": 558343, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9846007823944092, "global_step": 558344, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.014115333557129, "global_step": 558345, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0397815704345703, "global_step": 558346, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9470000267028809, "global_step": 558347, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9619711637496948, "global_step": 558348, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0328283309936523, "global_step": 558349, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.056461811065674, "global_step": 558350, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9846363067626953, "global_step": 558351, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9798181056976318, "global_step": 558352, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0401413440704346, "global_step": 558353, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0442657470703125, "global_step": 558354, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9959051609039307, "global_step": 558355, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.954591155052185, "global_step": 558356, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0145349502563477, "global_step": 558357, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0327348709106445, "global_step": 558358, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9900062084197998, "global_step": 558359, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9713144302368164, "global_step": 558360, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9258837699890137, "global_step": 558361, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0408122539520264, "global_step": 558362, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0783584117889404, "global_step": 558363, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0862181186676025, "global_step": 558364, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9752967357635498, "global_step": 558365, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9865375757217407, "global_step": 558366, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.063962936401367, "global_step": 558367, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1382431983947754, "global_step": 558368, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9226608276367188, "global_step": 558369, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0094242095947266, "global_step": 558370, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0123071670532227, "global_step": 558371, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9598033428192139, "global_step": 558372, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.984502911567688, "global_step": 558373, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.971353530883789, "global_step": 558374, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1069886684417725, "global_step": 558375, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0025246143341064, "global_step": 558376, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9747847318649292, "global_step": 558377, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9451671838760376, "global_step": 558378, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.043311834335327, "global_step": 558379, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0190067291259766, "global_step": 558380, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0312998294830322, "global_step": 558381, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9776811599731445, "global_step": 558382, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1007800102233887, "global_step": 558383, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.03609299659729, "global_step": 558384, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0381529331207275, "global_step": 558385, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9763396978378296, "global_step": 558386, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0098838806152344, "global_step": 558387, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0449509620666504, "global_step": 558388, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0002214908599854, "global_step": 558389, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.064502000808716, "global_step": 558390, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.004575490951538, "global_step": 558391, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9862947463989258, "global_step": 558392, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9761966466903687, "global_step": 558393, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9736210107803345, "global_step": 558394, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.055727481842041, "global_step": 558395, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0085461139678955, "global_step": 558396, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9926971197128296, "global_step": 558397, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.952060341835022, "global_step": 558398, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.953308343887329, "global_step": 558399, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.057217836380005, "global_step": 558400, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.030136823654175, "global_step": 558401, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0000951290130615, "global_step": 558402, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9990222454071045, "global_step": 558403, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.012089490890503, "global_step": 558404, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0300700664520264, "global_step": 558405, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.015270233154297, "global_step": 558406, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0676982402801514, "global_step": 558407, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9806145429611206, "global_step": 558408, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0377256870269775, "global_step": 558409, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9879952669143677, "global_step": 558410, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9850847721099854, "global_step": 558411, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.018462896347046, "global_step": 558412, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0051372051239014, "global_step": 558413, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.041152238845825, "global_step": 558414, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0289361476898193, "global_step": 558415, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.102487087249756, "global_step": 558416, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0164802074432373, "global_step": 558417, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9663231372833252, "global_step": 558418, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.103290319442749, "global_step": 558419, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.067598342895508, "global_step": 558420, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.130235195159912, "global_step": 558421, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9299455881118774, "global_step": 558422, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.072575807571411, "global_step": 558423, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.046541213989258, "global_step": 558424, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.985149621963501, "global_step": 558425, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.020430326461792, "global_step": 558426, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9699079990386963, "global_step": 558427, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.065293073654175, "global_step": 558428, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.106750726699829, "global_step": 558429, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9939656257629395, "global_step": 558430, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0002942085266113, "global_step": 558431, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0621914863586426, "global_step": 558432, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0326156616210938, "global_step": 558433, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9414547681808472, "global_step": 558434, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0041630268096924, "global_step": 558435, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0999279022216797, "global_step": 558436, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9958912134170532, "global_step": 558437, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.063624858856201, "global_step": 558438, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.136104106903076, "global_step": 558439, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.010406732559204, "global_step": 558440, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0645954608917236, "global_step": 558441, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.029783010482788, "global_step": 558442, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.050853967666626, "global_step": 558443, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0389907360076904, "global_step": 558444, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0075998306274414, "global_step": 558445, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.023746967315674, "global_step": 558446, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9816169738769531, "global_step": 558447, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.04807186126709, "global_step": 558448, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.072859764099121, "global_step": 558449, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0884151458740234, "global_step": 558450, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9637445211410522, "global_step": 558451, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9697892665863037, "global_step": 558452, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0467727184295654, "global_step": 558453, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.032510280609131, "global_step": 558454, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9531407356262207, "global_step": 558455, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0170516967773438, "global_step": 558456, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.089909315109253, "global_step": 558457, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9773924350738525, "global_step": 558458, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9791063070297241, "global_step": 558459, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.118403434753418, "global_step": 558460, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0054874420166016, "global_step": 558461, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.996160864830017, "global_step": 558462, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9327142238616943, "global_step": 558463, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0487611293792725, "global_step": 558464, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0592260360717773, "global_step": 558465, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0278570652008057, "global_step": 558466, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9566529989242554, "global_step": 558467, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0026936531066895, "global_step": 558468, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9314188957214355, "global_step": 558469, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.098339796066284, "global_step": 558470, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0853888988494873, "global_step": 558471, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0169925689697266, "global_step": 558472, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.027662992477417, "global_step": 558473, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.987561821937561, "global_step": 558474, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9628404378890991, "global_step": 558475, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0433390140533447, "global_step": 558476, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0645830631256104, "global_step": 558477, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9943506717681885, "global_step": 558478, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.026002883911133, "global_step": 558479, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0192668437957764, "global_step": 558480, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0190279483795166, "global_step": 558481, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.123988628387451, "global_step": 558482, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.013134717941284, "global_step": 558483, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9706989526748657, "global_step": 558484, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9627209901809692, "global_step": 558485, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0642855167388916, "global_step": 558486, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0218703746795654, "global_step": 558487, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.015026807785034, "global_step": 558488, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0621137619018555, "global_step": 558489, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.065284490585327, "global_step": 558490, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9797873497009277, "global_step": 558491, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.993308186531067, "global_step": 558492, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9638893604278564, "global_step": 558493, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.073918342590332, "global_step": 558494, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0053601264953613, "global_step": 558495, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0741422176361084, "global_step": 558496, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.07987380027771, "global_step": 558497, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0383005142211914, "global_step": 558498, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9825488328933716, "global_step": 558499, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0510945320129395, "global_step": 558500, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.033721685409546, "global_step": 558501, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0592777729034424, "global_step": 558502, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0260348320007324, "global_step": 558503, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.025406837463379, "global_step": 558504, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0134434700012207, "global_step": 558505, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.068934440612793, "global_step": 558506, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0435943603515625, "global_step": 558507, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0545814037323, "global_step": 558508, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9853794574737549, "global_step": 558509, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.098130941390991, "global_step": 558510, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0174667835235596, "global_step": 558511, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0443949699401855, "global_step": 558512, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.975055456161499, "global_step": 558513, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9437869787216187, "global_step": 558514, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0109024047851562, "global_step": 558515, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9725068807601929, "global_step": 558516, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9572441577911377, "global_step": 558517, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.025458335876465, "global_step": 558518, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.033231258392334, "global_step": 558519, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.016761064529419, "global_step": 558520, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9901493787765503, "global_step": 558521, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.023054838180542, "global_step": 558522, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.998843789100647, "global_step": 558523, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1167454719543457, "global_step": 558524, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.058121681213379, "global_step": 558525, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9353646039962769, "global_step": 558526, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0553221702575684, "global_step": 558527, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0194590091705322, "global_step": 558528, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9372433423995972, "global_step": 558529, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0332064628601074, "global_step": 558530, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0327446460723877, "global_step": 558531, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0435314178466797, "global_step": 558532, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9020817279815674, "global_step": 558533, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0263264179229736, "global_step": 558534, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.065256118774414, "global_step": 558535, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0274064540863037, "global_step": 558536, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.030975818634033, "global_step": 558537, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0398340225219727, "global_step": 558538, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.953748345375061, "global_step": 558539, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0418851375579834, "global_step": 558540, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0052194595336914, "global_step": 558541, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0399391651153564, "global_step": 558542, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0512986183166504, "global_step": 558543, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1089940071105957, "global_step": 558544, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0169432163238525, "global_step": 558545, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.030573844909668, "global_step": 558546, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0132651329040527, "global_step": 558547, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.08624267578125, "global_step": 558548, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9795817136764526, "global_step": 558549, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0958666801452637, "global_step": 558550, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9502414464950562, "global_step": 558551, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0017149448394775, "global_step": 558552, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0007224082946777, "global_step": 558553, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.120067596435547, "global_step": 558554, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0668492317199707, "global_step": 558555, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.05242657661438, "global_step": 558556, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9827747344970703, "global_step": 558557, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.119335889816284, "global_step": 558558, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.003431558609009, "global_step": 558559, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.009038209915161, "global_step": 558560, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9848182201385498, "global_step": 558561, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.018087387084961, "global_step": 558562, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9585919380187988, "global_step": 558563, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0360021591186523, "global_step": 558564, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0142951011657715, "global_step": 558565, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.996182918548584, "global_step": 558566, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0266830921173096, "global_step": 558567, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0689244270324707, "global_step": 558568, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.04524564743042, "global_step": 558569, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9805316925048828, "global_step": 558570, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9318923950195312, "global_step": 558571, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0495996475219727, "global_step": 558572, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.018852472305298, "global_step": 558573, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.03269100189209, "global_step": 558574, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0738155841827393, "global_step": 558575, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.987593173980713, "global_step": 558576, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9476550817489624, "global_step": 558577, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0249736309051514, "global_step": 558578, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.970141887664795, "global_step": 558579, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.046311140060425, "global_step": 558580, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9773238897323608, "global_step": 558581, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.055182695388794, "global_step": 558582, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0121943950653076, "global_step": 558583, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.031829357147217, "global_step": 558584, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0544769763946533, "global_step": 558585, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.027967691421509, "global_step": 558586, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.014617443084717, "global_step": 558587, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0984373092651367, "global_step": 558588, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0024311542510986, "global_step": 558589, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9446066617965698, "global_step": 558590, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0403714179992676, "global_step": 558591, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9853332042694092, "global_step": 558592, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0689096450805664, "global_step": 558593, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0182414054870605, "global_step": 558594, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9540444612503052, "global_step": 558595, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.05379319190979, "global_step": 558596, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.082148313522339, "global_step": 558597, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9819566011428833, "global_step": 558598, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1667211055755615, "global_step": 558599, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0434632301330566, "global_step": 558600, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0556511878967285, "global_step": 558601, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0299947261810303, "global_step": 558602, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9624804258346558, "global_step": 558603, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.02079176902771, "global_step": 558604, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9448845386505127, "global_step": 558605, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0363810062408447, "global_step": 558606, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9248456954956055, "global_step": 558607, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.050584077835083, "global_step": 558608, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.076005458831787, "global_step": 558609, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0435643196105957, "global_step": 558610, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0867600440979004, "global_step": 558611, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.985000729560852, "global_step": 558612, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0366158485412598, "global_step": 558613, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0228030681610107, "global_step": 558614, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.084007740020752, "global_step": 558615, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0174312591552734, "global_step": 558616, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0331034660339355, "global_step": 558617, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0792014598846436, "global_step": 558618, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9816101789474487, "global_step": 558619, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0761866569519043, "global_step": 558620, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.094733953475952, "global_step": 558621, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.052090644836426, "global_step": 558622, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0135505199432373, "global_step": 558623, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0898163318634033, "global_step": 558624, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.8980950117111206, "global_step": 558625, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0376055240631104, "global_step": 558626, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.02592134475708, "global_step": 558627, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.088808536529541, "global_step": 558628, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.980171799659729, "global_step": 558629, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9888172149658203, "global_step": 558630, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0339548587799072, "global_step": 558631, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0312132835388184, "global_step": 558632, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9902143478393555, "global_step": 558633, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1076457500457764, "global_step": 558634, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0368306636810303, "global_step": 558635, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.082874298095703, "global_step": 558636, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9954698085784912, "global_step": 558637, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.03244686126709, "global_step": 558638, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.089534282684326, "global_step": 558639, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0509891510009766, "global_step": 558640, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0213472843170166, "global_step": 558641, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0181615352630615, "global_step": 558642, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0271873474121094, "global_step": 558643, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0785083770751953, "global_step": 558644, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.021130084991455, "global_step": 558645, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1154568195343018, "global_step": 558646, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9417163133621216, "global_step": 558647, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.039039373397827, "global_step": 558648, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9920213222503662, "global_step": 558649, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.010712146759033, "global_step": 558650, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0001072883605957, "global_step": 558651, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.999642252922058, "global_step": 558652, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0302700996398926, "global_step": 558653, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9690181016921997, "global_step": 558654, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0206687450408936, "global_step": 558655, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.985484004020691, "global_step": 558656, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.990163803100586, "global_step": 558657, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.048860788345337, "global_step": 558658, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.029623508453369, "global_step": 558659, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1073665618896484, "global_step": 558660, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.007113456726074, "global_step": 558661, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0932915210723877, "global_step": 558662, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0816473960876465, "global_step": 558663, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.989832878112793, "global_step": 558664, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9857475757598877, "global_step": 558665, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9578286409378052, "global_step": 558666, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0148584842681885, "global_step": 558667, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.106863498687744, "global_step": 558668, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9877548217773438, "global_step": 558669, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9430696964263916, "global_step": 558670, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.013798713684082, "global_step": 558671, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0713536739349365, "global_step": 558672, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.122821569442749, "global_step": 558673, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.079279899597168, "global_step": 558674, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.074997901916504, "global_step": 558675, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.019094467163086, "global_step": 558676, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0134079456329346, "global_step": 558677, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9903475046157837, "global_step": 558678, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.014042615890503, "global_step": 558679, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.004380941390991, "global_step": 558680, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9919934272766113, "global_step": 558681, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.960567831993103, "global_step": 558682, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.052037239074707, "global_step": 558683, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0556674003601074, "global_step": 558684, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0213255882263184, "global_step": 558685, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0321836471557617, "global_step": 558686, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0079450607299805, "global_step": 558687, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.076664924621582, "global_step": 558688, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0490195751190186, "global_step": 558689, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0118138790130615, "global_step": 558690, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.05849027633667, "global_step": 558691, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9919846057891846, "global_step": 558692, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9740419387817383, "global_step": 558693, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.047173500061035, "global_step": 558694, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0239415168762207, "global_step": 558695, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0268192291259766, "global_step": 558696, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1455070972442627, "global_step": 558697, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.103634834289551, "global_step": 558698, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0951244831085205, "global_step": 558699, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0594239234924316, "global_step": 558700, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.054558753967285, "global_step": 558701, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1158831119537354, "global_step": 558702, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0601937770843506, "global_step": 558703, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0828001499176025, "global_step": 558704, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0200817584991455, "global_step": 558705, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.004124164581299, "global_step": 558706, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.994822382926941, "global_step": 558707, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.919766902923584, "global_step": 558708, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.000559091567993, "global_step": 558709, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.051844835281372, "global_step": 558710, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0702950954437256, "global_step": 558711, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9906753301620483, "global_step": 558712, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9977762699127197, "global_step": 558713, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0034303665161133, "global_step": 558714, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0466480255126953, "global_step": 558715, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.969154715538025, "global_step": 558716, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0628719329833984, "global_step": 558717, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.089294672012329, "global_step": 558718, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0187125205993652, "global_step": 558719, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0697879791259766, "global_step": 558720, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.077207088470459, "global_step": 558721, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9348320960998535, "global_step": 558722, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.02350115776062, "global_step": 558723, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9812740087509155, "global_step": 558724, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0839908123016357, "global_step": 558725, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.027996301651001, "global_step": 558726, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0909268856048584, "global_step": 558727, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9840174913406372, "global_step": 558728, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9977201223373413, "global_step": 558729, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0764353275299072, "global_step": 558730, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0580573081970215, "global_step": 558731, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0763115882873535, "global_step": 558732, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0325839519500732, "global_step": 558733, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.976380705833435, "global_step": 558734, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.006432294845581, "global_step": 558735, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0176095962524414, "global_step": 558736, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9960644245147705, "global_step": 558737, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1079862117767334, "global_step": 558738, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0306098461151123, "global_step": 558739, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.013709783554077, "global_step": 558740, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.062676429748535, "global_step": 558741, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0753886699676514, "global_step": 558742, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.067328929901123, "global_step": 558743, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1506171226501465, "global_step": 558744, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9887667894363403, "global_step": 558745, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0975053310394287, "global_step": 558746, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9265081882476807, "global_step": 558747, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.007823944091797, "global_step": 558748, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.05572509765625, "global_step": 558749, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9739817380905151, "global_step": 558750, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.107210874557495, "global_step": 558751, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0094714164733887, "global_step": 558752, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.001211404800415, "global_step": 558753, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0719192028045654, "global_step": 558754, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0266692638397217, "global_step": 558755, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0585200786590576, "global_step": 558756, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.066251754760742, "global_step": 558757, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.978367805480957, "global_step": 558758, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0097291469573975, "global_step": 558759, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0495786666870117, "global_step": 558760, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1016368865966797, "global_step": 558761, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.062242269515991, "global_step": 558762, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9733667373657227, "global_step": 558763, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0225605964660645, "global_step": 558764, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0113611221313477, "global_step": 558765, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.006347179412842, "global_step": 558766, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.083585023880005, "global_step": 558767, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0263359546661377, "global_step": 558768, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9461889266967773, "global_step": 558769, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0837185382843018, "global_step": 558770, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.024996757507324, "global_step": 558771, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0382463932037354, "global_step": 558772, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0357799530029297, "global_step": 558773, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.091567039489746, "global_step": 558774, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.100153923034668, "global_step": 558775, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9429155588150024, "global_step": 558776, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9977813959121704, "global_step": 558777, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.042619466781616, "global_step": 558778, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.02884578704834, "global_step": 558779, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0054261684417725, "global_step": 558780, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.079359531402588, "global_step": 558781, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.023787498474121, "global_step": 558782, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0555434226989746, "global_step": 558783, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0403833389282227, "global_step": 558784, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0488815307617188, "global_step": 558785, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.94705069065094, "global_step": 558786, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.117766857147217, "global_step": 558787, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.993906021118164, "global_step": 558788, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0292727947235107, "global_step": 558789, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.075956344604492, "global_step": 558790, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.012338876724243, "global_step": 558791, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0208940505981445, "global_step": 558792, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.127203941345215, "global_step": 558793, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.010678768157959, "global_step": 558794, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0320324897766113, "global_step": 558795, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0567896366119385, "global_step": 558796, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.075721263885498, "global_step": 558797, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0292258262634277, "global_step": 558798, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9312554597854614, "global_step": 558799, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0734140872955322, "global_step": 558800, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.091610908508301, "global_step": 558801, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0153613090515137, "global_step": 558802, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.030233860015869, "global_step": 558803, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0192813873291016, "global_step": 558804, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0537638664245605, "global_step": 558805, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9908138513565063, "global_step": 558806, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.958506464958191, "global_step": 558807, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9940775632858276, "global_step": 558808, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.046189785003662, "global_step": 558809, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0078396797180176, "global_step": 558810, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0370633602142334, "global_step": 558811, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0690035820007324, "global_step": 558812, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0296614170074463, "global_step": 558813, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0690598487854004, "global_step": 558814, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0096874237060547, "global_step": 558815, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9916763305664062, "global_step": 558816, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.045968532562256, "global_step": 558817, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.058281183242798, "global_step": 558818, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1318979263305664, "global_step": 558819, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.092571973800659, "global_step": 558820, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0813984870910645, "global_step": 558821, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0349321365356445, "global_step": 558822, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9992645978927612, "global_step": 558823, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.066483974456787, "global_step": 558824, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.984235405921936, "global_step": 558825, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.071831226348877, "global_step": 558826, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.045654773712158, "global_step": 558827, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0134129524230957, "global_step": 558828, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.032749652862549, "global_step": 558829, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9687244892120361, "global_step": 558830, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.000711441040039, "global_step": 558831, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.010589361190796, "global_step": 558832, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9401582479476929, "global_step": 558833, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9621047973632812, "global_step": 558834, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.173673152923584, "global_step": 558835, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0870280265808105, "global_step": 558836, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.033482313156128, "global_step": 558837, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9863433837890625, "global_step": 558838, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0554161071777344, "global_step": 558839, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1386289596557617, "global_step": 558840, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.033426284790039, "global_step": 558841, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.117218255996704, "global_step": 558842, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.050227403640747, "global_step": 558843, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.027597665786743, "global_step": 558844, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1094417572021484, "global_step": 558845, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9481542110443115, "global_step": 558846, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.00270938873291, "global_step": 558847, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0245189666748047, "global_step": 558848, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0201339721679688, "global_step": 558849, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0041263103485107, "global_step": 558850, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0618109703063965, "global_step": 558851, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0647084712982178, "global_step": 558852, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9389981031417847, "global_step": 558853, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9928274154663086, "global_step": 558854, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9771746397018433, "global_step": 558855, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9879753589630127, "global_step": 558856, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0682947635650635, "global_step": 558857, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.057284355163574, "global_step": 558858, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0606210231781006, "global_step": 558859, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9518749713897705, "global_step": 558860, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.020094156265259, "global_step": 558861, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9670027494430542, "global_step": 558862, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0155067443847656, "global_step": 558863, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.014427423477173, "global_step": 558864, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0321192741394043, "global_step": 558865, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.01430082321167, "global_step": 558866, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.098900079727173, "global_step": 558867, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9919484853744507, "global_step": 558868, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.084066867828369, "global_step": 558869, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0600931644439697, "global_step": 558870, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9567680358886719, "global_step": 558871, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0048391819000244, "global_step": 558872, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0134570598602295, "global_step": 558873, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1108458042144775, "global_step": 558874, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.000591516494751, "global_step": 558875, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.033353328704834, "global_step": 558876, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.055948495864868, "global_step": 558877, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1047914028167725, "global_step": 558878, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0099940299987793, "global_step": 558879, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1536965370178223, "global_step": 558880, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9748759269714355, "global_step": 558881, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0587828159332275, "global_step": 558882, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9847456216812134, "global_step": 558883, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9888116121292114, "global_step": 558884, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.013462543487549, "global_step": 558885, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9110702276229858, "global_step": 558886, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0646557807922363, "global_step": 558887, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0560712814331055, "global_step": 558888, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9585506916046143, "global_step": 558889, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9865742921829224, "global_step": 558890, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9765738248825073, "global_step": 558891, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0282065868377686, "global_step": 558892, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.981992483139038, "global_step": 558893, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.048152446746826, "global_step": 558894, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.95491361618042, "global_step": 558895, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0653228759765625, "global_step": 558896, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0280442237854004, "global_step": 558897, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9988374710083008, "global_step": 558898, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.046151876449585, "global_step": 558899, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.10823655128479, "global_step": 558900, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9191040992736816, "global_step": 558901, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0041797161102295, "global_step": 558902, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0122718811035156, "global_step": 558903, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.126812219619751, "global_step": 558904, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0400593280792236, "global_step": 558905, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0058813095092773, "global_step": 558906, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0186190605163574, "global_step": 558907, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9999866485595703, "global_step": 558908, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0114519596099854, "global_step": 558909, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.037478446960449, "global_step": 558910, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0356900691986084, "global_step": 558911, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0216734409332275, "global_step": 558912, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0474472045898438, "global_step": 558913, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9840574264526367, "global_step": 558914, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.994031310081482, "global_step": 558915, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0434184074401855, "global_step": 558916, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.032940626144409, "global_step": 558917, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.054232120513916, "global_step": 558918, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.132364511489868, "global_step": 558919, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.053185224533081, "global_step": 558920, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0195209980010986, "global_step": 558921, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9767100811004639, "global_step": 558922, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0410268306732178, "global_step": 558923, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9713876247406006, "global_step": 558924, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.045889139175415, "global_step": 558925, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0974104404449463, "global_step": 558926, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9611332416534424, "global_step": 558927, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9491524696350098, "global_step": 558928, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0878891944885254, "global_step": 558929, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0790648460388184, "global_step": 558930, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.054719924926758, "global_step": 558931, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0091845989227295, "global_step": 558932, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.112083911895752, "global_step": 558933, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.026024580001831, "global_step": 558934, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.988817572593689, "global_step": 558935, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0208401679992676, "global_step": 558936, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.058833122253418, "global_step": 558937, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.053344488143921, "global_step": 558938, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1327664852142334, "global_step": 558939, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1031413078308105, "global_step": 558940, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0126168727874756, "global_step": 558941, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.046311616897583, "global_step": 558942, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.011342763900757, "global_step": 558943, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9940654039382935, "global_step": 558944, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9869283437728882, "global_step": 558945, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0002286434173584, "global_step": 558946, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.006289005279541, "global_step": 558947, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.020083427429199, "global_step": 558948, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0268607139587402, "global_step": 558949, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.074148178100586, "global_step": 558950, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9636504650115967, "global_step": 558951, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.029480218887329, "global_step": 558952, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9786070585250854, "global_step": 558953, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9871214628219604, "global_step": 558954, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0733797550201416, "global_step": 558955, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0490808486938477, "global_step": 558956, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.071723699569702, "global_step": 558957, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.07425856590271, "global_step": 558958, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.981229543685913, "global_step": 558959, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0514883995056152, "global_step": 558960, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.016584873199463, "global_step": 558961, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.01467227935791, "global_step": 558962, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.975568175315857, "global_step": 558963, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.023327350616455, "global_step": 558964, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.121976375579834, "global_step": 558965, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0556347370147705, "global_step": 558966, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.060640335083008, "global_step": 558967, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0739595890045166, "global_step": 558968, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0749878883361816, "global_step": 558969, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0109236240386963, "global_step": 558970, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.053255081176758, "global_step": 558971, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0293333530426025, "global_step": 558972, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0406036376953125, "global_step": 558973, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0415565967559814, "global_step": 558974, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.045217990875244, "global_step": 558975, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.096283435821533, "global_step": 558976, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.079530715942383, "global_step": 558977, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.111063003540039, "global_step": 558978, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1372385025024414, "global_step": 558979, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0399978160858154, "global_step": 558980, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0420145988464355, "global_step": 558981, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.013697862625122, "global_step": 558982, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.072272300720215, "global_step": 558983, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.047837257385254, "global_step": 558984, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9739692211151123, "global_step": 558985, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.031620740890503, "global_step": 558986, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.023926258087158, "global_step": 558987, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.005488157272339, "global_step": 558988, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0806875228881836, "global_step": 558989, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9588524103164673, "global_step": 558990, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.013190746307373, "global_step": 558991, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.035904884338379, "global_step": 558992, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.106825590133667, "global_step": 558993, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0570693016052246, "global_step": 558994, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.060495376586914, "global_step": 558995, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.004425048828125, "global_step": 558996, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1396331787109375, "global_step": 558997, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0583608150482178, "global_step": 558998, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1512460708618164, "global_step": 558999, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0851361751556396, "global_step": 559000, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9626871347427368, "global_step": 559001, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0249593257904053, "global_step": 559002, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9789894819259644, "global_step": 559003, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9576208591461182, "global_step": 559004, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.067042112350464, "global_step": 559005, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0524063110351562, "global_step": 559006, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9791980981826782, "global_step": 559007, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9447803497314453, "global_step": 559008, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.034468173980713, "global_step": 559009, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9975191354751587, "global_step": 559010, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.085536003112793, "global_step": 559011, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0257151126861572, "global_step": 559012, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0247080326080322, "global_step": 559013, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.006641387939453, "global_step": 559014, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.021980047225952, "global_step": 559015, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9828968048095703, "global_step": 559016, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9739388227462769, "global_step": 559017, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0514917373657227, "global_step": 559018, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.060509204864502, "global_step": 559019, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9916484355926514, "global_step": 559020, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0554442405700684, "global_step": 559021, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0266928672790527, "global_step": 559022, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.059774875640869, "global_step": 559023, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9798831939697266, "global_step": 559024, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0107977390289307, "global_step": 559025, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9970717430114746, "global_step": 559026, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0224337577819824, "global_step": 559027, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.050642728805542, "global_step": 559028, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1024606227874756, "global_step": 559029, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.034057855606079, "global_step": 559030, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.043555736541748, "global_step": 559031, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.020132541656494, "global_step": 559032, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0059754848480225, "global_step": 559033, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.008513927459717, "global_step": 559034, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9735606908798218, "global_step": 559035, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.034281015396118, "global_step": 559036, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.031277894973755, "global_step": 559037, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0459132194519043, "global_step": 559038, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.106229782104492, "global_step": 559039, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0340375900268555, "global_step": 559040, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0344924926757812, "global_step": 559041, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0729501247406006, "global_step": 559042, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0367090702056885, "global_step": 559043, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.047058582305908, "global_step": 559044, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9872009754180908, "global_step": 559045, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0374999046325684, "global_step": 559046, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0552451610565186, "global_step": 559047, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0177836418151855, "global_step": 559048, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0771634578704834, "global_step": 559049, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0174126625061035, "global_step": 559050, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.990269660949707, "global_step": 559051, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.005925178527832, "global_step": 559052, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9813203811645508, "global_step": 559053, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0360047817230225, "global_step": 559054, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9842413663864136, "global_step": 559055, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.018357038497925, "global_step": 559056, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.960452675819397, "global_step": 559057, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.042259693145752, "global_step": 559058, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0493524074554443, "global_step": 559059, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0798072814941406, "global_step": 559060, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0008702278137207, "global_step": 559061, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9803661108016968, "global_step": 559062, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0544543266296387, "global_step": 559063, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0177695751190186, "global_step": 559064, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.975920557975769, "global_step": 559065, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.019585371017456, "global_step": 559066, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0005221366882324, "global_step": 559067, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1091604232788086, "global_step": 559068, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.982980728149414, "global_step": 559069, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9979112148284912, "global_step": 559070, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0120060443878174, "global_step": 559071, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0220584869384766, "global_step": 559072, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.01104474067688, "global_step": 559073, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9612072706222534, "global_step": 559074, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9704852104187012, "global_step": 559075, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9932187795639038, "global_step": 559076, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0796992778778076, "global_step": 559077, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9879902601242065, "global_step": 559078, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0451061725616455, "global_step": 559079, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.999856948852539, "global_step": 559080, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.973247766494751, "global_step": 559081, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1237070560455322, "global_step": 559082, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0889227390289307, "global_step": 559083, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0019595623016357, "global_step": 559084, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1110596656799316, "global_step": 559085, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0529065132141113, "global_step": 559086, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0789802074432373, "global_step": 559087, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.094806671142578, "global_step": 559088, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.017801523208618, "global_step": 559089, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0711886882781982, "global_step": 559090, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.995410680770874, "global_step": 559091, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.034536838531494, "global_step": 559092, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9914603233337402, "global_step": 559093, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9552239179611206, "global_step": 559094, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9586052894592285, "global_step": 559095, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.091534376144409, "global_step": 559096, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.000779390335083, "global_step": 559097, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.081782579421997, "global_step": 559098, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.053694248199463, "global_step": 559099, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.961259126663208, "global_step": 559100, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.019207239151001, "global_step": 559101, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.119148015975952, "global_step": 559102, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0814077854156494, "global_step": 559103, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0223631858825684, "global_step": 559104, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1017322540283203, "global_step": 559105, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0873961448669434, "global_step": 559106, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0405876636505127, "global_step": 559107, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9563796520233154, "global_step": 559108, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.018735408782959, "global_step": 559109, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.014920949935913, "global_step": 559110, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0823283195495605, "global_step": 559111, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9921237230300903, "global_step": 559112, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.049900531768799, "global_step": 559113, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9880009889602661, "global_step": 559114, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.023167610168457, "global_step": 559115, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.95220947265625, "global_step": 559116, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.069587230682373, "global_step": 559117, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9985707998275757, "global_step": 559118, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.145575761795044, "global_step": 559119, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.016970634460449, "global_step": 559120, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9005073308944702, "global_step": 559121, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0456862449645996, "global_step": 559122, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0890657901763916, "global_step": 559123, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0484564304351807, "global_step": 559124, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0625357627868652, "global_step": 559125, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9757018089294434, "global_step": 559126, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.063992977142334, "global_step": 559127, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1181485652923584, "global_step": 559128, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.000286340713501, "global_step": 559129, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.010080337524414, "global_step": 559130, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1519393920898438, "global_step": 559131, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0110504627227783, "global_step": 559132, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.020590305328369, "global_step": 559133, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0059750080108643, "global_step": 559134, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0150527954101562, "global_step": 559135, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.999361515045166, "global_step": 559136, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0438930988311768, "global_step": 559137, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0118978023529053, "global_step": 559138, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0373380184173584, "global_step": 559139, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.038459300994873, "global_step": 559140, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.054523229598999, "global_step": 559141, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.025362491607666, "global_step": 559142, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1226792335510254, "global_step": 559143, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9916547536849976, "global_step": 559144, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0598559379577637, "global_step": 559145, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0678651332855225, "global_step": 559146, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.976318597793579, "global_step": 559147, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9962714910507202, "global_step": 559148, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0692203044891357, "global_step": 559149, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0614733695983887, "global_step": 559150, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1427459716796875, "global_step": 559151, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0718960762023926, "global_step": 559152, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.074538469314575, "global_step": 559153, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0820775032043457, "global_step": 559154, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9879339933395386, "global_step": 559155, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0636110305786133, "global_step": 559156, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.008028984069824, "global_step": 559157, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0459766387939453, "global_step": 559158, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.061267852783203, "global_step": 559159, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0402915477752686, "global_step": 559160, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.999857783317566, "global_step": 559161, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0391461849212646, "global_step": 559162, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9612377882003784, "global_step": 559163, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.089118242263794, "global_step": 559164, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0627472400665283, "global_step": 559165, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0923545360565186, "global_step": 559166, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0601933002471924, "global_step": 559167, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.026134729385376, "global_step": 559168, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9483144283294678, "global_step": 559169, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.953613519668579, "global_step": 559170, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9285531044006348, "global_step": 559171, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0079076290130615, "global_step": 559172, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9777647256851196, "global_step": 559173, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.99673330783844, "global_step": 559174, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0313730239868164, "global_step": 559175, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0216434001922607, "global_step": 559176, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.060427665710449, "global_step": 559177, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.043485641479492, "global_step": 559178, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.000454902648926, "global_step": 559179, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.015103816986084, "global_step": 559180, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0198609828948975, "global_step": 559181, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.033352851867676, "global_step": 559182, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0326600074768066, "global_step": 559183, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.053778648376465, "global_step": 559184, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.035166025161743, "global_step": 559185, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.004060745239258, "global_step": 559186, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0494537353515625, "global_step": 559187, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.993709921836853, "global_step": 559188, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.04294490814209, "global_step": 559189, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0437724590301514, "global_step": 559190, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9983476400375366, "global_step": 559191, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.090822696685791, "global_step": 559192, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0768659114837646, "global_step": 559193, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.919472575187683, "global_step": 559194, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.015103816986084, "global_step": 559195, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0438320636749268, "global_step": 559196, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.032896041870117, "global_step": 559197, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9686793088912964, "global_step": 559198, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0635440349578857, "global_step": 559199, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.050244092941284, "global_step": 559200, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0891523361206055, "global_step": 559201, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.051072120666504, "global_step": 559202, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.000540256500244, "global_step": 559203, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0349903106689453, "global_step": 559204, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0536653995513916, "global_step": 559205, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0781311988830566, "global_step": 559206, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9916926622390747, "global_step": 559207, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0247437953948975, "global_step": 559208, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9394371509552002, "global_step": 559209, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.017036199569702, "global_step": 559210, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0350260734558105, "global_step": 559211, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9315534830093384, "global_step": 559212, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.00948166847229, "global_step": 559213, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.021310806274414, "global_step": 559214, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.083195924758911, "global_step": 559215, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.016475200653076, "global_step": 559216, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0218136310577393, "global_step": 559217, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0771243572235107, "global_step": 559218, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1109566688537598, "global_step": 559219, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.038308620452881, "global_step": 559220, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0198450088500977, "global_step": 559221, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0244035720825195, "global_step": 559222, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1078109741210938, "global_step": 559223, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1588168144226074, "global_step": 559224, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.032466173171997, "global_step": 559225, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1025075912475586, "global_step": 559226, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0339608192443848, "global_step": 559227, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0506811141967773, "global_step": 559228, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.112740993499756, "global_step": 559229, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0006797313690186, "global_step": 559230, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0260744094848633, "global_step": 559231, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.059284210205078, "global_step": 559232, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9828799962997437, "global_step": 559233, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.9925801753997803, "global_step": 559234, "epoch": 926, "lr": 5e-05}
{"train_loss": 1.983675241470337, "global_step": 559235, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0377819538116455, "global_step": 559236, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0196120738983154, "global_step": 559237, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0232994556427, "global_step": 559238, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0176312923431396, "global_step": 559239, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0348453521728516, "global_step": 559240, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0399558544158936, "global_step": 559241, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0040528774261475, "global_step": 559242, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.049656867980957, "global_step": 559243, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.022554397583008, "global_step": 559244, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.0280420780181885, "global_step": 559245, "epoch": 926, "lr": 5e-05}
{"train_loss": 2.1119887828826904, "global_step": 559246, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.025419235229492, "global_step": 559247, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.042429208755493, "global_step": 559248, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1032707691192627, "global_step": 559249, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.002657413482666, "global_step": 559250, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0248889923095703, "global_step": 559251, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.084352731704712, "global_step": 559252, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.00296688079834, "global_step": 559253, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0253002643585205, "global_step": 559254, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0495333671569824, "global_step": 559255, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.022763967514038, "global_step": 559256, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.079296827316284, "global_step": 559257, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.018155097961426, "global_step": 559258, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9843227863311768, "global_step": 559259, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.984069585800171, "global_step": 559260, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0101919174194336, "global_step": 559261, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9891691207885742, "global_step": 559262, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9626622200012207, "global_step": 559263, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.013758897781372, "global_step": 559264, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.025367259979248, "global_step": 559265, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9475812911987305, "global_step": 559266, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9824272394180298, "global_step": 559267, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9889863729476929, "global_step": 559268, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.07010817527771, "global_step": 559269, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.005056619644165, "global_step": 559270, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0440773963928223, "global_step": 559271, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0558152198791504, "global_step": 559272, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0433332920074463, "global_step": 559273, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0617332458496094, "global_step": 559274, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9809092283248901, "global_step": 559275, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.019881248474121, "global_step": 559276, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.012006998062134, "global_step": 559277, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.043098211288452, "global_step": 559278, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0558574199676514, "global_step": 559279, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0613577365875244, "global_step": 559280, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9992902278900146, "global_step": 559281, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0608837604522705, "global_step": 559282, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0034422874450684, "global_step": 559283, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.005633592605591, "global_step": 559284, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9509731531143188, "global_step": 559285, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9392303228378296, "global_step": 559286, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0135865211486816, "global_step": 559287, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0541348457336426, "global_step": 559288, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.037175416946411, "global_step": 559289, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0121827125549316, "global_step": 559290, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.020594835281372, "global_step": 559291, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1012611389160156, "global_step": 559292, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.048239231109619, "global_step": 559293, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0203683376312256, "global_step": 559294, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0124340057373047, "global_step": 559295, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.999955415725708, "global_step": 559296, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9344639778137207, "global_step": 559297, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0162808895111084, "global_step": 559298, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.957777976989746, "global_step": 559299, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.082599639892578, "global_step": 559300, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.04399037361145, "global_step": 559301, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0174543857574463, "global_step": 559302, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9966174364089966, "global_step": 559303, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9469536542892456, "global_step": 559304, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0785415172576904, "global_step": 559305, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0506863594055176, "global_step": 559306, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9867870807647705, "global_step": 559307, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.05580997467041, "global_step": 559308, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0093917846679688, "global_step": 559309, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0075931549072266, "global_step": 559310, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0413951873779297, "global_step": 559311, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9900410175323486, "global_step": 559312, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.057985544204712, "global_step": 559313, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0135457515716553, "global_step": 559314, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.013878583908081, "global_step": 559315, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0802054405212402, "global_step": 559316, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0040197372436523, "global_step": 559317, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9858156442642212, "global_step": 559318, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9730333089828491, "global_step": 559319, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.04935884475708, "global_step": 559320, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9224188327789307, "global_step": 559321, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0820770263671875, "global_step": 559322, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9935317039489746, "global_step": 559323, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0670688152313232, "global_step": 559324, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0988996028900146, "global_step": 559325, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0239603519439697, "global_step": 559326, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0162084102630615, "global_step": 559327, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.068669557571411, "global_step": 559328, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0631203651428223, "global_step": 559329, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9782859086990356, "global_step": 559330, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.023292303085327, "global_step": 559331, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.029609203338623, "global_step": 559332, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.996368408203125, "global_step": 559333, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9732855558395386, "global_step": 559334, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0211496353149414, "global_step": 559335, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9548581838607788, "global_step": 559336, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0722060203552246, "global_step": 559337, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0120463371276855, "global_step": 559338, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0378477573394775, "global_step": 559339, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9991170167922974, "global_step": 559340, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0173192024230957, "global_step": 559341, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0589406490325928, "global_step": 559342, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0341179370880127, "global_step": 559343, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.941874623298645, "global_step": 559344, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9630297422409058, "global_step": 559345, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0050103664398193, "global_step": 559346, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0005686283111572, "global_step": 559347, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9169422388076782, "global_step": 559348, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.020554542541504, "global_step": 559349, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.944011926651001, "global_step": 559350, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0821025371551514, "global_step": 559351, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.153275728225708, "global_step": 559352, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9731696844100952, "global_step": 559353, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9129303693771362, "global_step": 559354, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0049986839294434, "global_step": 559355, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9903218746185303, "global_step": 559356, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0413265228271484, "global_step": 559357, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0417635440826416, "global_step": 559358, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.050961971282959, "global_step": 559359, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9963672161102295, "global_step": 559360, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.971916675567627, "global_step": 559361, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9778999090194702, "global_step": 559362, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0154950618743896, "global_step": 559363, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.958446741104126, "global_step": 559364, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.044109582901001, "global_step": 559365, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1176865100860596, "global_step": 559366, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0271012783050537, "global_step": 559367, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0089378356933594, "global_step": 559368, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9943580627441406, "global_step": 559369, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0186164379119873, "global_step": 559370, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.024080514907837, "global_step": 559371, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9878923892974854, "global_step": 559372, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.001230239868164, "global_step": 559373, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9414825439453125, "global_step": 559374, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0437064170837402, "global_step": 559375, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0942206382751465, "global_step": 559376, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.037328004837036, "global_step": 559377, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9845170974731445, "global_step": 559378, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.016541004180908, "global_step": 559379, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0825958251953125, "global_step": 559380, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.080458641052246, "global_step": 559381, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0412354469299316, "global_step": 559382, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9747252464294434, "global_step": 559383, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0668246746063232, "global_step": 559384, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9323350191116333, "global_step": 559385, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0256400108337402, "global_step": 559386, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9902514219284058, "global_step": 559387, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0308303833007812, "global_step": 559388, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9762603044509888, "global_step": 559389, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.08068585395813, "global_step": 559390, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.059898614883423, "global_step": 559391, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9044740200042725, "global_step": 559392, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.019986152648926, "global_step": 559393, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.056474208831787, "global_step": 559394, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9658300876617432, "global_step": 559395, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.039278030395508, "global_step": 559396, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0500426292419434, "global_step": 559397, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0863535404205322, "global_step": 559398, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0876262187957764, "global_step": 559399, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.009547710418701, "global_step": 559400, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.034747838973999, "global_step": 559401, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9796388149261475, "global_step": 559402, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9964778423309326, "global_step": 559403, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0060007572174072, "global_step": 559404, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.999959111213684, "global_step": 559405, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9625004529953003, "global_step": 559406, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.074119806289673, "global_step": 559407, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9360162019729614, "global_step": 559408, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9979838132858276, "global_step": 559409, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0009989738464355, "global_step": 559410, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.065758466720581, "global_step": 559411, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9279614686965942, "global_step": 559412, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.942947506904602, "global_step": 559413, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0567750930786133, "global_step": 559414, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0507636070251465, "global_step": 559415, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1281793117523193, "global_step": 559416, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0045247077941895, "global_step": 559417, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.041781187057495, "global_step": 559418, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0675065517425537, "global_step": 559419, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0494749546051025, "global_step": 559420, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.098188638687134, "global_step": 559421, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0490431785583496, "global_step": 559422, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9465577602386475, "global_step": 559423, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.015763759613037, "global_step": 559424, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9735008478164673, "global_step": 559425, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.010603427886963, "global_step": 559426, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0516979694366455, "global_step": 559427, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0117714405059814, "global_step": 559428, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9771332740783691, "global_step": 559429, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.995052695274353, "global_step": 559430, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0821337699890137, "global_step": 559431, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.08187198638916, "global_step": 559432, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9984489679336548, "global_step": 559433, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.075354814529419, "global_step": 559434, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9143873453140259, "global_step": 559435, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.058119535446167, "global_step": 559436, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9897723197937012, "global_step": 559437, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0294179916381836, "global_step": 559438, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0158798694610596, "global_step": 559439, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.001481771469116, "global_step": 559440, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9592530727386475, "global_step": 559441, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9904335737228394, "global_step": 559442, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9695680141448975, "global_step": 559443, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0127077102661133, "global_step": 559444, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9887744188308716, "global_step": 559445, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0222437381744385, "global_step": 559446, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.948790192604065, "global_step": 559447, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1686742305755615, "global_step": 559448, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9888715744018555, "global_step": 559449, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0599887371063232, "global_step": 559450, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.96639883518219, "global_step": 559451, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.014655351638794, "global_step": 559452, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0537707805633545, "global_step": 559453, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.143655776977539, "global_step": 559454, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0109591484069824, "global_step": 559455, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9756838083267212, "global_step": 559456, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0423102378845215, "global_step": 559457, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9434164762496948, "global_step": 559458, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0537362098693848, "global_step": 559459, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.040097713470459, "global_step": 559460, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0036470890045166, "global_step": 559461, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9723796844482422, "global_step": 559462, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0462229251861572, "global_step": 559463, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0473105907440186, "global_step": 559464, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0235610008239746, "global_step": 559465, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0900654792785645, "global_step": 559466, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0160675048828125, "global_step": 559467, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.052429676055908, "global_step": 559468, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0440146923065186, "global_step": 559469, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.071700096130371, "global_step": 559470, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9458043575286865, "global_step": 559471, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.073770046234131, "global_step": 559472, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0131824016571045, "global_step": 559473, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.065246820449829, "global_step": 559474, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.018890142440796, "global_step": 559475, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0223982334136963, "global_step": 559476, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9382531642913818, "global_step": 559477, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0330677032470703, "global_step": 559478, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.054898262023926, "global_step": 559479, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9680120944976807, "global_step": 559480, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.996660828590393, "global_step": 559481, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9483425617218018, "global_step": 559482, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0140371322631836, "global_step": 559483, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0912044048309326, "global_step": 559484, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0492117404937744, "global_step": 559485, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9373809099197388, "global_step": 559486, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1015799045562744, "global_step": 559487, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1211371421813965, "global_step": 559488, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0470051765441895, "global_step": 559489, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.058917999267578, "global_step": 559490, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0451390743255615, "global_step": 559491, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0786802768707275, "global_step": 559492, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9869933128356934, "global_step": 559493, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.043721914291382, "global_step": 559494, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.047412395477295, "global_step": 559495, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.978192925453186, "global_step": 559496, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.03611421585083, "global_step": 559497, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9662801027297974, "global_step": 559498, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9741867780685425, "global_step": 559499, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.019683599472046, "global_step": 559500, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0495219230651855, "global_step": 559501, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9576501846313477, "global_step": 559502, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9816925525665283, "global_step": 559503, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.054785966873169, "global_step": 559504, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.019270181655884, "global_step": 559505, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0489420890808105, "global_step": 559506, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0309934616088867, "global_step": 559507, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.020930528640747, "global_step": 559508, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9779821634292603, "global_step": 559509, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.061131238937378, "global_step": 559510, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0448925495147705, "global_step": 559511, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.03188419342041, "global_step": 559512, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9775179624557495, "global_step": 559513, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.080759048461914, "global_step": 559514, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0998282432556152, "global_step": 559515, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.896461844444275, "global_step": 559516, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0856103897094727, "global_step": 559517, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9911220073699951, "global_step": 559518, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0524673461914062, "global_step": 559519, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0300791263580322, "global_step": 559520, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9909868240356445, "global_step": 559521, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.962230920791626, "global_step": 559522, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0598866939544678, "global_step": 559523, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.015927791595459, "global_step": 559524, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0193533897399902, "global_step": 559525, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.994985818862915, "global_step": 559526, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.030425548553467, "global_step": 559527, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0467307567596436, "global_step": 559528, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.926769733428955, "global_step": 559529, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.983250617980957, "global_step": 559530, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.020966053009033, "global_step": 559531, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9884190559387207, "global_step": 559532, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9652950763702393, "global_step": 559533, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9433611631393433, "global_step": 559534, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0004444122314453, "global_step": 559535, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9952428340911865, "global_step": 559536, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.001507520675659, "global_step": 559537, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9570561647415161, "global_step": 559538, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9708828926086426, "global_step": 559539, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.065338373184204, "global_step": 559540, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9791761636734009, "global_step": 559541, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0373315811157227, "global_step": 559542, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1896471977233887, "global_step": 559543, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9770172834396362, "global_step": 559544, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.073887825012207, "global_step": 559545, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9617269039154053, "global_step": 559546, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9713826179504395, "global_step": 559547, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9384713172912598, "global_step": 559548, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0369668006896973, "global_step": 559549, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.027723789215088, "global_step": 559550, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9889532327651978, "global_step": 559551, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.054974317550659, "global_step": 559552, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0341498851776123, "global_step": 559553, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9750840663909912, "global_step": 559554, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0226688385009766, "global_step": 559555, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9647963047027588, "global_step": 559556, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9755735397338867, "global_step": 559557, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0493433475494385, "global_step": 559558, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.032428503036499, "global_step": 559559, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9239267110824585, "global_step": 559560, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.024219512939453, "global_step": 559561, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.067591905593872, "global_step": 559562, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.026059865951538, "global_step": 559563, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0589466094970703, "global_step": 559564, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9848302602767944, "global_step": 559565, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0476903915405273, "global_step": 559566, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.104707717895508, "global_step": 559567, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.080064296722412, "global_step": 559568, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0129292011260986, "global_step": 559569, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0738282203674316, "global_step": 559570, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.058397054672241, "global_step": 559571, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.91899836063385, "global_step": 559572, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9883545637130737, "global_step": 559573, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.085286855697632, "global_step": 559574, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.025784730911255, "global_step": 559575, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.934800386428833, "global_step": 559576, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.043820381164551, "global_step": 559577, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.018552541732788, "global_step": 559578, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9658238887786865, "global_step": 559579, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.045722484588623, "global_step": 559580, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1130778789520264, "global_step": 559581, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.090230941772461, "global_step": 559582, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0660085678100586, "global_step": 559583, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9537155628204346, "global_step": 559584, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9919612407684326, "global_step": 559585, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9913538694381714, "global_step": 559586, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0738885402679443, "global_step": 559587, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0013391971588135, "global_step": 559588, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.063798666000366, "global_step": 559589, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.025752544403076, "global_step": 559590, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.015218734741211, "global_step": 559591, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.031733512878418, "global_step": 559592, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.081031322479248, "global_step": 559593, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0620100498199463, "global_step": 559594, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0791447162628174, "global_step": 559595, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0708730220794678, "global_step": 559596, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9936720132827759, "global_step": 559597, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0229034423828125, "global_step": 559598, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.046600818634033, "global_step": 559599, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.078427791595459, "global_step": 559600, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.10148286819458, "global_step": 559601, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.064120054244995, "global_step": 559602, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0003068447113037, "global_step": 559603, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.075169324874878, "global_step": 559604, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9971715211868286, "global_step": 559605, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.117083787918091, "global_step": 559606, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.992048978805542, "global_step": 559607, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.008634328842163, "global_step": 559608, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0321762561798096, "global_step": 559609, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9854815006256104, "global_step": 559610, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9723185300827026, "global_step": 559611, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0364181995391846, "global_step": 559612, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0767252445220947, "global_step": 559613, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9481693506240845, "global_step": 559614, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.087114095687866, "global_step": 559615, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0095150470733643, "global_step": 559616, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9628883600234985, "global_step": 559617, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0306878089904785, "global_step": 559618, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.012286424636841, "global_step": 559619, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0852584838867188, "global_step": 559620, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0577189922332764, "global_step": 559621, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0659570693969727, "global_step": 559622, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9915120601654053, "global_step": 559623, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0354418754577637, "global_step": 559624, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9847888946533203, "global_step": 559625, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.985596776008606, "global_step": 559626, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0711121559143066, "global_step": 559627, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.099439859390259, "global_step": 559628, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9764304161071777, "global_step": 559629, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0705015659332275, "global_step": 559630, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.11812686920166, "global_step": 559631, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.031130075454712, "global_step": 559632, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0731005668640137, "global_step": 559633, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9882984161376953, "global_step": 559634, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9403254985809326, "global_step": 559635, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.011474370956421, "global_step": 559636, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.072603464126587, "global_step": 559637, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.027108907699585, "global_step": 559638, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.081143617630005, "global_step": 559639, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.000951051712036, "global_step": 559640, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0623855590820312, "global_step": 559641, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9890556335449219, "global_step": 559642, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9403076171875, "global_step": 559643, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0065088272094727, "global_step": 559644, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.03277850151062, "global_step": 559645, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0224194526672363, "global_step": 559646, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0534112453460693, "global_step": 559647, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0443553924560547, "global_step": 559648, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0005979537963867, "global_step": 559649, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0682082176208496, "global_step": 559650, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0280346870422363, "global_step": 559651, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.072687864303589, "global_step": 559652, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0348880290985107, "global_step": 559653, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9535930156707764, "global_step": 559654, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.066833257675171, "global_step": 559655, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.014986038208008, "global_step": 559656, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.028643846511841, "global_step": 559657, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.040964126586914, "global_step": 559658, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0811753273010254, "global_step": 559659, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9451701641082764, "global_step": 559660, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.074164628982544, "global_step": 559661, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0339653491973877, "global_step": 559662, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.996204137802124, "global_step": 559663, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.030797243118286, "global_step": 559664, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1153571605682373, "global_step": 559665, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9605674743652344, "global_step": 559666, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1148996353149414, "global_step": 559667, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9427510499954224, "global_step": 559668, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9659106731414795, "global_step": 559669, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.045971632003784, "global_step": 559670, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9597722291946411, "global_step": 559671, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.022400140762329, "global_step": 559672, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.069605588912964, "global_step": 559673, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0351991653442383, "global_step": 559674, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9995760917663574, "global_step": 559675, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.089567184448242, "global_step": 559676, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.006875514984131, "global_step": 559677, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.034528970718384, "global_step": 559678, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.027287721633911, "global_step": 559679, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0232648849487305, "global_step": 559680, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0664117336273193, "global_step": 559681, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0355591773986816, "global_step": 559682, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9648840427398682, "global_step": 559683, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.008225679397583, "global_step": 559684, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.090390920639038, "global_step": 559685, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9342974424362183, "global_step": 559686, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.994465947151184, "global_step": 559687, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0079362392425537, "global_step": 559688, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.061929702758789, "global_step": 559689, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.031620979309082, "global_step": 559690, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1026413440704346, "global_step": 559691, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.952702283859253, "global_step": 559692, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9847135543823242, "global_step": 559693, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9882533550262451, "global_step": 559694, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0778212547302246, "global_step": 559695, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9812963008880615, "global_step": 559696, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.001145839691162, "global_step": 559697, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0026392936706543, "global_step": 559698, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.059629201889038, "global_step": 559699, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.04386043548584, "global_step": 559700, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0361435413360596, "global_step": 559701, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0568130016326904, "global_step": 559702, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0168228149414062, "global_step": 559703, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9919490814208984, "global_step": 559704, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0930280685424805, "global_step": 559705, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.038593292236328, "global_step": 559706, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9760349988937378, "global_step": 559707, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0269992351531982, "global_step": 559708, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0907561779022217, "global_step": 559709, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9821852445602417, "global_step": 559710, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0356357097625732, "global_step": 559711, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0461530685424805, "global_step": 559712, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.02118182182312, "global_step": 559713, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.054605484008789, "global_step": 559714, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9717377424240112, "global_step": 559715, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0398108959198, "global_step": 559716, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.094313383102417, "global_step": 559717, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9762085676193237, "global_step": 559718, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1058008670806885, "global_step": 559719, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9567759037017822, "global_step": 559720, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.931134581565857, "global_step": 559721, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.021408796310425, "global_step": 559722, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0095889568328857, "global_step": 559723, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0298266410827637, "global_step": 559724, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0262227058410645, "global_step": 559725, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.032968759536743, "global_step": 559726, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0962750911712646, "global_step": 559727, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.026740789413452, "global_step": 559728, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.05059814453125, "global_step": 559729, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9725972414016724, "global_step": 559730, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9999053478240967, "global_step": 559731, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.034181594848633, "global_step": 559732, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.01462721824646, "global_step": 559733, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1080498695373535, "global_step": 559734, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.951369047164917, "global_step": 559735, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9252614974975586, "global_step": 559736, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0197997093200684, "global_step": 559737, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1072230339050293, "global_step": 559738, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0730347633361816, "global_step": 559739, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.062298536300659, "global_step": 559740, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9877485036849976, "global_step": 559741, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9495673179626465, "global_step": 559742, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9841569662094116, "global_step": 559743, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0036394596099854, "global_step": 559744, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9532827138900757, "global_step": 559745, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.062329053878784, "global_step": 559746, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0268502235412598, "global_step": 559747, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0370664596557617, "global_step": 559748, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0766501426696777, "global_step": 559749, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0705151557922363, "global_step": 559750, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.975677490234375, "global_step": 559751, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0957024097442627, "global_step": 559752, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0148487091064453, "global_step": 559753, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0983946323394775, "global_step": 559754, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0525522232055664, "global_step": 559755, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.027409076690674, "global_step": 559756, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.009268283843994, "global_step": 559757, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0688562393188477, "global_step": 559758, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9682250022888184, "global_step": 559759, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1080574989318848, "global_step": 559760, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0491013526916504, "global_step": 559761, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9819532632827759, "global_step": 559762, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.999368667602539, "global_step": 559763, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9360711574554443, "global_step": 559764, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9713634252548218, "global_step": 559765, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0780553817749023, "global_step": 559766, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.035985231399536, "global_step": 559767, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9811584949493408, "global_step": 559768, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0647192001342773, "global_step": 559769, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0622048377990723, "global_step": 559770, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0800795555114746, "global_step": 559771, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0651371479034424, "global_step": 559772, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.000098705291748, "global_step": 559773, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0487256050109863, "global_step": 559774, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9786505699157715, "global_step": 559775, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0905072689056396, "global_step": 559776, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0119667053222656, "global_step": 559777, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.023214340209961, "global_step": 559778, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9853646755218506, "global_step": 559779, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.970700740814209, "global_step": 559780, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9272054433822632, "global_step": 559781, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.107431650161743, "global_step": 559782, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0236570835113525, "global_step": 559783, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.000826358795166, "global_step": 559784, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.040370225906372, "global_step": 559785, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9985007047653198, "global_step": 559786, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.980216383934021, "global_step": 559787, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1363821029663086, "global_step": 559788, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9982635974884033, "global_step": 559789, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9775347709655762, "global_step": 559790, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0847880840301514, "global_step": 559791, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0953657627105713, "global_step": 559792, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.977271318435669, "global_step": 559793, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.009197473526001, "global_step": 559794, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.038444995880127, "global_step": 559795, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0165982246398926, "global_step": 559796, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0114176273345947, "global_step": 559797, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9934178590774536, "global_step": 559798, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0827620029449463, "global_step": 559799, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0008983612060547, "global_step": 559800, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.05531644821167, "global_step": 559801, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0565059185028076, "global_step": 559802, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1269052028656006, "global_step": 559803, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0124096870422363, "global_step": 559804, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9851441383361816, "global_step": 559805, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0239412784576416, "global_step": 559806, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0233964920043945, "global_step": 559807, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.996224045753479, "global_step": 559808, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.978121042251587, "global_step": 559809, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9588301181793213, "global_step": 559810, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.975099802017212, "global_step": 559811, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.010127544403076, "global_step": 559812, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0561909675598145, "global_step": 559813, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0107901096343994, "global_step": 559814, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.03810977935791, "global_step": 559815, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.985257863998413, "global_step": 559816, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9677809476852417, "global_step": 559817, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.022524356842041, "global_step": 559818, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9944785833358765, "global_step": 559819, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0439085960388184, "global_step": 559820, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0180182456970215, "global_step": 559821, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9635506868362427, "global_step": 559822, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0565881729125977, "global_step": 559823, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.058933734893799, "global_step": 559824, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9861153364181519, "global_step": 559825, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0409998893737793, "global_step": 559826, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9714456796646118, "global_step": 559827, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9344953298568726, "global_step": 559828, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0370097160339355, "global_step": 559829, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9380168914794922, "global_step": 559830, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.067384958267212, "global_step": 559831, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.026827573776245, "global_step": 559832, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.07316517829895, "global_step": 559833, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0293664932250977, "global_step": 559834, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0634055137634277, "global_step": 559835, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.023724317550659, "global_step": 559836, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.03696870803833, "global_step": 559837, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0394394397735596, "global_step": 559838, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.05659556388855, "global_step": 559839, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.115015983581543, "global_step": 559840, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.033123016357422, "global_step": 559841, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0548758506774902, "global_step": 559842, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0593032836914062, "global_step": 559843, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.001847267150879, "global_step": 559844, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.044938325881958, "global_step": 559845, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9657026529312134, "global_step": 559846, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0166099071502686, "global_step": 559847, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.084686756134033, "global_step": 559848, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.102308750152588, "global_step": 559849, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0346474647521973, "global_step": 559850, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9540222883224487, "global_step": 559851, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.057433605194092, "global_step": 559852, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.016838550567627, "global_step": 559853, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1038482189178467, "global_step": 559854, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0808653831481934, "global_step": 559855, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.064620018005371, "global_step": 559856, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0387356281280518, "global_step": 559857, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0499536991119385, "global_step": 559858, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0750174522399902, "global_step": 559859, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0427744388580322, "global_step": 559860, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.957534670829773, "global_step": 559861, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0188207626342773, "global_step": 559862, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9829363822937012, "global_step": 559863, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.034268856048584, "global_step": 559864, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.115527868270874, "global_step": 559865, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0473551750183105, "global_step": 559866, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1065497398376465, "global_step": 559867, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0421502590179443, "global_step": 559868, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.087830066680908, "global_step": 559869, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9616612195968628, "global_step": 559870, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.989864468574524, "global_step": 559871, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1061208248138428, "global_step": 559872, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9702590703964233, "global_step": 559873, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9847034215927124, "global_step": 559874, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0633513927459717, "global_step": 559875, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9409440755844116, "global_step": 559876, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9801687002182007, "global_step": 559877, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9786938428878784, "global_step": 559878, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.09836483001709, "global_step": 559879, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.05741548538208, "global_step": 559880, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9828920364379883, "global_step": 559881, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0689094066619873, "global_step": 559882, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9463412761688232, "global_step": 559883, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.007603883743286, "global_step": 559884, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0538785457611084, "global_step": 559885, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.022986888885498, "global_step": 559886, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.124485969543457, "global_step": 559887, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9963679313659668, "global_step": 559888, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.139409065246582, "global_step": 559889, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.028594732284546, "global_step": 559890, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0648443698883057, "global_step": 559891, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1088356971740723, "global_step": 559892, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.039577007293701, "global_step": 559893, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.081127882003784, "global_step": 559894, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9873429536819458, "global_step": 559895, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.070206642150879, "global_step": 559896, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0138731002807617, "global_step": 559897, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.123955726623535, "global_step": 559898, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.069141387939453, "global_step": 559899, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.074150323867798, "global_step": 559900, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9805498123168945, "global_step": 559901, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.05021595954895, "global_step": 559902, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9589552879333496, "global_step": 559903, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.060429573059082, "global_step": 559904, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.02386736869812, "global_step": 559905, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0129172801971436, "global_step": 559906, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9828258752822876, "global_step": 559907, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.045351505279541, "global_step": 559908, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0925962924957275, "global_step": 559909, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0388340950012207, "global_step": 559910, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0318832397460938, "global_step": 559911, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9674301147460938, "global_step": 559912, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.061336040496826, "global_step": 559913, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9579585790634155, "global_step": 559914, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0479378700256348, "global_step": 559915, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9865138530731201, "global_step": 559916, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0239827632904053, "global_step": 559917, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1113314628601074, "global_step": 559918, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0508227348327637, "global_step": 559919, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.077390670776367, "global_step": 559920, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0254697799682617, "global_step": 559921, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.071307420730591, "global_step": 559922, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9456032514572144, "global_step": 559923, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.94340181350708, "global_step": 559924, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0610196590423584, "global_step": 559925, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1108319759368896, "global_step": 559926, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9956133365631104, "global_step": 559927, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0261898040771484, "global_step": 559928, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9653419256210327, "global_step": 559929, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0909223556518555, "global_step": 559930, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9906561374664307, "global_step": 559931, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.014554977416992, "global_step": 559932, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0662713050842285, "global_step": 559933, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0295310020446777, "global_step": 559934, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.980149269104004, "global_step": 559935, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.034606456756592, "global_step": 559936, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.146146774291992, "global_step": 559937, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0813937187194824, "global_step": 559938, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9570410251617432, "global_step": 559939, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0473592281341553, "global_step": 559940, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.024709939956665, "global_step": 559941, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.109342575073242, "global_step": 559942, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0972909927368164, "global_step": 559943, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9966042041778564, "global_step": 559944, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0516390800476074, "global_step": 559945, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.047396183013916, "global_step": 559946, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9922070503234863, "global_step": 559947, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9963449239730835, "global_step": 559948, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.97383713722229, "global_step": 559949, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0130133628845215, "global_step": 559950, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9794405698776245, "global_step": 559951, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0516395568847656, "global_step": 559952, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0654850006103516, "global_step": 559953, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.049776792526245, "global_step": 559954, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.008368968963623, "global_step": 559955, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0482845306396484, "global_step": 559956, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.030897855758667, "global_step": 559957, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.090132236480713, "global_step": 559958, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9909443855285645, "global_step": 559959, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.068598985671997, "global_step": 559960, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0089051723480225, "global_step": 559961, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.031583786010742, "global_step": 559962, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.006516218185425, "global_step": 559963, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0180916786193848, "global_step": 559964, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9875822067260742, "global_step": 559965, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.053511142730713, "global_step": 559966, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.063232660293579, "global_step": 559967, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.043718099594116, "global_step": 559968, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0130960941314697, "global_step": 559969, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0311973094940186, "global_step": 559970, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.034994125366211, "global_step": 559971, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.033231735229492, "global_step": 559972, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1025912761688232, "global_step": 559973, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0678672790527344, "global_step": 559974, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0753467082977295, "global_step": 559975, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.061589241027832, "global_step": 559976, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.024641275405884, "global_step": 559977, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.076063394546509, "global_step": 559978, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.029876708984375, "global_step": 559979, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9925508499145508, "global_step": 559980, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0182361602783203, "global_step": 559981, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9541563987731934, "global_step": 559982, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.014997959136963, "global_step": 559983, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9876909255981445, "global_step": 559984, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.006129741668701, "global_step": 559985, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0323212146759033, "global_step": 559986, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0236971378326416, "global_step": 559987, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9730820655822754, "global_step": 559988, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9923571348190308, "global_step": 559989, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.147805690765381, "global_step": 559990, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0517594814300537, "global_step": 559991, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9793970584869385, "global_step": 559992, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.008840560913086, "global_step": 559993, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9581602811813354, "global_step": 559994, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.05206561088562, "global_step": 559995, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9829243421554565, "global_step": 559996, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9944554567337036, "global_step": 559997, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.092366933822632, "global_step": 559998, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.013456344604492, "global_step": 559999, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0481574535369873, "global_step": 560000, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9710006713867188, "global_step": 560001, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.038814067840576, "global_step": 560002, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.104666233062744, "global_step": 560003, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.047813892364502, "global_step": 560004, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.058629274368286, "global_step": 560005, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0273280143737793, "global_step": 560006, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0696299076080322, "global_step": 560007, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0694074630737305, "global_step": 560008, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.004647970199585, "global_step": 560009, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0478627681732178, "global_step": 560010, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0706236362457275, "global_step": 560011, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.090189218521118, "global_step": 560012, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.027949810028076, "global_step": 560013, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.005328416824341, "global_step": 560014, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9375789165496826, "global_step": 560015, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.98152756690979, "global_step": 560016, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.083702325820923, "global_step": 560017, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0719738006591797, "global_step": 560018, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0297093391418457, "global_step": 560019, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.065960168838501, "global_step": 560020, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0847890377044678, "global_step": 560021, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.022124767303467, "global_step": 560022, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.082054376602173, "global_step": 560023, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0252177715301514, "global_step": 560024, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9840402603149414, "global_step": 560025, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.03157114982605, "global_step": 560026, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0072529315948486, "global_step": 560027, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0667264461517334, "global_step": 560028, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0150864124298096, "global_step": 560029, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0824520587921143, "global_step": 560030, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9960508346557617, "global_step": 560031, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0296618938446045, "global_step": 560032, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.979886531829834, "global_step": 560033, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0957376956939697, "global_step": 560034, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0195600986480713, "global_step": 560035, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0561368465423584, "global_step": 560036, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.083031177520752, "global_step": 560037, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9658749103546143, "global_step": 560038, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9891481399536133, "global_step": 560039, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0138344764709473, "global_step": 560040, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9576071500778198, "global_step": 560041, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9968206882476807, "global_step": 560042, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0408716201782227, "global_step": 560043, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.014565944671631, "global_step": 560044, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9190573692321777, "global_step": 560045, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1003944873809814, "global_step": 560046, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0105292797088623, "global_step": 560047, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.108696460723877, "global_step": 560048, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0391697883605957, "global_step": 560049, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0498204231262207, "global_step": 560050, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9867422580718994, "global_step": 560051, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.061532497406006, "global_step": 560052, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.00254487991333, "global_step": 560053, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.00217866897583, "global_step": 560054, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0402870178222656, "global_step": 560055, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.14802622795105, "global_step": 560056, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9795589447021484, "global_step": 560057, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.088766574859619, "global_step": 560058, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9800540208816528, "global_step": 560059, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0781893730163574, "global_step": 560060, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9603431224822998, "global_step": 560061, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.024688959121704, "global_step": 560062, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.936966896057129, "global_step": 560063, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0056698322296143, "global_step": 560064, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0419538021087646, "global_step": 560065, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9997309446334839, "global_step": 560066, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9583591222763062, "global_step": 560067, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9677106142044067, "global_step": 560068, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.051051139831543, "global_step": 560069, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.052938938140869, "global_step": 560070, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.034536600112915, "global_step": 560071, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0523293018341064, "global_step": 560072, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.091937303543091, "global_step": 560073, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0384504795074463, "global_step": 560074, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.028390645980835, "global_step": 560075, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0531296730041504, "global_step": 560076, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.059894323348999, "global_step": 560077, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0065224170684814, "global_step": 560078, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0512049198150635, "global_step": 560079, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.030341625213623, "global_step": 560080, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.026317834854126, "global_step": 560081, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9959346055984497, "global_step": 560082, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0481250286102295, "global_step": 560083, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9798792600631714, "global_step": 560084, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9534265995025635, "global_step": 560085, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0745198726654053, "global_step": 560086, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.128866672515869, "global_step": 560087, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.057147741317749, "global_step": 560088, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.036959171295166, "global_step": 560089, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0618205070495605, "global_step": 560090, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.032057762145996, "global_step": 560091, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0698468685150146, "global_step": 560092, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0532479286193848, "global_step": 560093, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0051379203796387, "global_step": 560094, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.029592275619507, "global_step": 560095, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0506763458251953, "global_step": 560096, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.084444522857666, "global_step": 560097, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0615627765655518, "global_step": 560098, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0087971687316895, "global_step": 560099, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.016777992248535, "global_step": 560100, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.030092239379883, "global_step": 560101, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9913699626922607, "global_step": 560102, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9432342052459717, "global_step": 560103, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0553061962127686, "global_step": 560104, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0613420009613037, "global_step": 560105, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.060258388519287, "global_step": 560106, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.057365894317627, "global_step": 560107, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1068150997161865, "global_step": 560108, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.086695432662964, "global_step": 560109, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1320571899414062, "global_step": 560110, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.064634323120117, "global_step": 560111, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.096940755844116, "global_step": 560112, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0350284576416016, "global_step": 560113, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.02681303024292, "global_step": 560114, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0278568267822266, "global_step": 560115, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1302168369293213, "global_step": 560116, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.098433256149292, "global_step": 560117, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9793397188186646, "global_step": 560118, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0479042530059814, "global_step": 560119, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.002636671066284, "global_step": 560120, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9805076122283936, "global_step": 560121, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9897066354751587, "global_step": 560122, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.027113914489746, "global_step": 560123, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.945860505104065, "global_step": 560124, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0133183002471924, "global_step": 560125, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0722789764404297, "global_step": 560126, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.018965721130371, "global_step": 560127, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9969837665557861, "global_step": 560128, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0423004627227783, "global_step": 560129, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9627107381820679, "global_step": 560130, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.017160177230835, "global_step": 560131, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.073716878890991, "global_step": 560132, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0105979442596436, "global_step": 560133, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0056350231170654, "global_step": 560134, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9802535772323608, "global_step": 560135, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0268425941467285, "global_step": 560136, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0309159755706787, "global_step": 560137, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.021517276763916, "global_step": 560138, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.029115676879883, "global_step": 560139, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9859482049942017, "global_step": 560140, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9807798862457275, "global_step": 560141, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0212388038635254, "global_step": 560142, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0869760513305664, "global_step": 560143, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0188117027282715, "global_step": 560144, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.010181188583374, "global_step": 560145, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0414834022521973, "global_step": 560146, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0708303451538086, "global_step": 560147, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9896336793899536, "global_step": 560148, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0138590335845947, "global_step": 560149, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9525954723358154, "global_step": 560150, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0608391761779785, "global_step": 560151, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.016484498977661, "global_step": 560152, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.038675546646118, "global_step": 560153, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9736595153808594, "global_step": 560154, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9284433126449585, "global_step": 560155, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9930719137191772, "global_step": 560156, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.079659938812256, "global_step": 560157, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0292491912841797, "global_step": 560158, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0911474227905273, "global_step": 560159, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9608124494552612, "global_step": 560160, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9733598232269287, "global_step": 560161, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0221540927886963, "global_step": 560162, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0588061809539795, "global_step": 560163, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.029198408126831, "global_step": 560164, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9521751403808594, "global_step": 560165, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0378260612487793, "global_step": 560166, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9563132524490356, "global_step": 560167, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.057223081588745, "global_step": 560168, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0343966484069824, "global_step": 560169, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9732128381729126, "global_step": 560170, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0272598266601562, "global_step": 560171, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.009458303451538, "global_step": 560172, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0870232582092285, "global_step": 560173, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9872643947601318, "global_step": 560174, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0926156044006348, "global_step": 560175, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1141412258148193, "global_step": 560176, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.008105993270874, "global_step": 560177, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.029161214828491, "global_step": 560178, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0617315769195557, "global_step": 560179, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0826923847198486, "global_step": 560180, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.037152051925659, "global_step": 560181, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1043131351470947, "global_step": 560182, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0591061115264893, "global_step": 560183, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0249946117401123, "global_step": 560184, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9272661209106445, "global_step": 560185, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1000328063964844, "global_step": 560186, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1069326400756836, "global_step": 560187, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.076159954071045, "global_step": 560188, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.087553024291992, "global_step": 560189, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.027202844619751, "global_step": 560190, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0633745193481445, "global_step": 560191, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.059783697128296, "global_step": 560192, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.051137685775757, "global_step": 560193, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0656497478485107, "global_step": 560194, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0365238189697266, "global_step": 560195, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0087828636169434, "global_step": 560196, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.052497625350952, "global_step": 560197, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0267791748046875, "global_step": 560198, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.007253408432007, "global_step": 560199, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0512659549713135, "global_step": 560200, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1425232887268066, "global_step": 560201, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0020811557769775, "global_step": 560202, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9984886646270752, "global_step": 560203, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0487709045410156, "global_step": 560204, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9549064636230469, "global_step": 560205, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9501242637634277, "global_step": 560206, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.1370980739593506, "global_step": 560207, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0831449031829834, "global_step": 560208, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0239813327789307, "global_step": 560209, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.072399854660034, "global_step": 560210, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.077880620956421, "global_step": 560211, "epoch": 927, "lr": 5e-05}
{"train_loss": 1.9844212532043457, "global_step": 560212, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0288639068603516, "global_step": 560213, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0264856815338135, "global_step": 560214, "epoch": 927, "lr": 5e-05}
{"train_loss": 2.0502147674560547, "global_step": 560215, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.050737142562866, "global_step": 560216, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0278871059417725, "global_step": 560217, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.071744680404663, "global_step": 560218, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0281100273132324, "global_step": 560219, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9615398645401, "global_step": 560220, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0436298847198486, "global_step": 560221, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0632030963897705, "global_step": 560222, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.936349868774414, "global_step": 560223, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0854649543762207, "global_step": 560224, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0276429653167725, "global_step": 560225, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9941600561141968, "global_step": 560226, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0747532844543457, "global_step": 560227, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.961621880531311, "global_step": 560228, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0885908603668213, "global_step": 560229, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0791876316070557, "global_step": 560230, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0572636127471924, "global_step": 560231, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9851118326187134, "global_step": 560232, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9688705205917358, "global_step": 560233, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9508776664733887, "global_step": 560234, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.042325496673584, "global_step": 560235, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9556992053985596, "global_step": 560236, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9472460746765137, "global_step": 560237, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.944140911102295, "global_step": 560238, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0421714782714844, "global_step": 560239, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0506296157836914, "global_step": 560240, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0529191493988037, "global_step": 560241, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0367467403411865, "global_step": 560242, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0667316913604736, "global_step": 560243, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.044771909713745, "global_step": 560244, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9836609363555908, "global_step": 560245, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.081348419189453, "global_step": 560246, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0252997875213623, "global_step": 560247, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9322904348373413, "global_step": 560248, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9711618423461914, "global_step": 560249, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0257747173309326, "global_step": 560250, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0407028198242188, "global_step": 560251, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0506627559661865, "global_step": 560252, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.050893783569336, "global_step": 560253, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9694550037384033, "global_step": 560254, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9810967445373535, "global_step": 560255, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9574354887008667, "global_step": 560256, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.968989610671997, "global_step": 560257, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.053978204727173, "global_step": 560258, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0680432319641113, "global_step": 560259, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.021186113357544, "global_step": 560260, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.020948886871338, "global_step": 560261, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.950289011001587, "global_step": 560262, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.00711989402771, "global_step": 560263, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.002828359603882, "global_step": 560264, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0093657970428467, "global_step": 560265, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0260353088378906, "global_step": 560266, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0242600440979004, "global_step": 560267, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.026888847351074, "global_step": 560268, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0815627574920654, "global_step": 560269, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9942048788070679, "global_step": 560270, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.008521795272827, "global_step": 560271, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.072139263153076, "global_step": 560272, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.022214889526367, "global_step": 560273, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.112947702407837, "global_step": 560274, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0098488330841064, "global_step": 560275, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9292930364608765, "global_step": 560276, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9848272800445557, "global_step": 560277, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.963768720626831, "global_step": 560278, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9918314218521118, "global_step": 560279, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0381689071655273, "global_step": 560280, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0512993335723877, "global_step": 560281, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9274494647979736, "global_step": 560282, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0349671840667725, "global_step": 560283, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0289201736450195, "global_step": 560284, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.04516339302063, "global_step": 560285, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0383856296539307, "global_step": 560286, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0181846618652344, "global_step": 560287, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.987962007522583, "global_step": 560288, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.053884506225586, "global_step": 560289, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9908998012542725, "global_step": 560290, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0283493995666504, "global_step": 560291, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0303125381469727, "global_step": 560292, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0083630084991455, "global_step": 560293, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0154685974121094, "global_step": 560294, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.012359857559204, "global_step": 560295, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0639567375183105, "global_step": 560296, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0357608795166016, "global_step": 560297, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0018227100372314, "global_step": 560298, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.068408250808716, "global_step": 560299, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9719727039337158, "global_step": 560300, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0773234367370605, "global_step": 560301, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9293771982192993, "global_step": 560302, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1408700942993164, "global_step": 560303, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.014927864074707, "global_step": 560304, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.027783155441284, "global_step": 560305, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.968956708908081, "global_step": 560306, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0222716331481934, "global_step": 560307, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9638487100601196, "global_step": 560308, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9942495822906494, "global_step": 560309, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0465171337127686, "global_step": 560310, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9268361330032349, "global_step": 560311, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0468547344207764, "global_step": 560312, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0000059604644775, "global_step": 560313, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0454092025756836, "global_step": 560314, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0582759380340576, "global_step": 560315, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1025445461273193, "global_step": 560316, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0848004817962646, "global_step": 560317, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9151575565338135, "global_step": 560318, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0057411193847656, "global_step": 560319, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0372064113616943, "global_step": 560320, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0435259342193604, "global_step": 560321, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9824316501617432, "global_step": 560322, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.010082721710205, "global_step": 560323, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.938321590423584, "global_step": 560324, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.976567268371582, "global_step": 560325, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9344176054000854, "global_step": 560326, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0505552291870117, "global_step": 560327, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9908409118652344, "global_step": 560328, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.042666435241699, "global_step": 560329, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9727107286453247, "global_step": 560330, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.078817129135132, "global_step": 560331, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.992315411567688, "global_step": 560332, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.01735520362854, "global_step": 560333, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0088071823120117, "global_step": 560334, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9773869514465332, "global_step": 560335, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.991822361946106, "global_step": 560336, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.027653455734253, "global_step": 560337, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9291120767593384, "global_step": 560338, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.068617343902588, "global_step": 560339, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9546459913253784, "global_step": 560340, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0190391540527344, "global_step": 560341, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.020358085632324, "global_step": 560342, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1028852462768555, "global_step": 560343, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0030007362365723, "global_step": 560344, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.012587070465088, "global_step": 560345, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.065070629119873, "global_step": 560346, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0999979972839355, "global_step": 560347, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9971071481704712, "global_step": 560348, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.032501459121704, "global_step": 560349, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0917255878448486, "global_step": 560350, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0922489166259766, "global_step": 560351, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.018436908721924, "global_step": 560352, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0625996589660645, "global_step": 560353, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.062319278717041, "global_step": 560354, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9372544288635254, "global_step": 560355, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0332279205322266, "global_step": 560356, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0772738456726074, "global_step": 560357, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9323545694351196, "global_step": 560358, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.055299997329712, "global_step": 560359, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0263519287109375, "global_step": 560360, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.056957483291626, "global_step": 560361, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0821287631988525, "global_step": 560362, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9240546226501465, "global_step": 560363, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.026984214782715, "global_step": 560364, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.075944662094116, "global_step": 560365, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.049583673477173, "global_step": 560366, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0915729999542236, "global_step": 560367, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0892837047576904, "global_step": 560368, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.964840054512024, "global_step": 560369, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.986185073852539, "global_step": 560370, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.006237030029297, "global_step": 560371, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0860676765441895, "global_step": 560372, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9547293186187744, "global_step": 560373, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0667965412139893, "global_step": 560374, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0404908657073975, "global_step": 560375, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0105862617492676, "global_step": 560376, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.068338394165039, "global_step": 560377, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9928693771362305, "global_step": 560378, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0591907501220703, "global_step": 560379, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1195924282073975, "global_step": 560380, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9737262725830078, "global_step": 560381, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9675369262695312, "global_step": 560382, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.041593551635742, "global_step": 560383, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0294034481048584, "global_step": 560384, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9966402053833008, "global_step": 560385, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.990156650543213, "global_step": 560386, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0851359367370605, "global_step": 560387, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.039278984069824, "global_step": 560388, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1541996002197266, "global_step": 560389, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9906538724899292, "global_step": 560390, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9165133237838745, "global_step": 560391, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.984550952911377, "global_step": 560392, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.005261182785034, "global_step": 560393, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9819402694702148, "global_step": 560394, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0340776443481445, "global_step": 560395, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.019941806793213, "global_step": 560396, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9216734170913696, "global_step": 560397, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.998095989227295, "global_step": 560398, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.141216278076172, "global_step": 560399, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.069030284881592, "global_step": 560400, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0475914478302, "global_step": 560401, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0408363342285156, "global_step": 560402, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9875786304473877, "global_step": 560403, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9417259693145752, "global_step": 560404, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9991306066513062, "global_step": 560405, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.035618305206299, "global_step": 560406, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.007425546646118, "global_step": 560407, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.96123468875885, "global_step": 560408, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.025916337966919, "global_step": 560409, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9925386905670166, "global_step": 560410, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.009796142578125, "global_step": 560411, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9825645685195923, "global_step": 560412, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.021716356277466, "global_step": 560413, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0522968769073486, "global_step": 560414, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9590643644332886, "global_step": 560415, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0747628211975098, "global_step": 560416, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9882885217666626, "global_step": 560417, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0092852115631104, "global_step": 560418, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0682477951049805, "global_step": 560419, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0126373767852783, "global_step": 560420, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9706087112426758, "global_step": 560421, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0095839500427246, "global_step": 560422, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0390303134918213, "global_step": 560423, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.053966522216797, "global_step": 560424, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9682929515838623, "global_step": 560425, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0714871883392334, "global_step": 560426, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0589489936828613, "global_step": 560427, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1037588119506836, "global_step": 560428, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9956309795379639, "global_step": 560429, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.953029990196228, "global_step": 560430, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0232551097869873, "global_step": 560431, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.035220146179199, "global_step": 560432, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0246448516845703, "global_step": 560433, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9662220478057861, "global_step": 560434, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.098071575164795, "global_step": 560435, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9407199621200562, "global_step": 560436, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.032907247543335, "global_step": 560437, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9578678607940674, "global_step": 560438, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0296216011047363, "global_step": 560439, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.055643320083618, "global_step": 560440, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0414721965789795, "global_step": 560441, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.098405599594116, "global_step": 560442, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1108932495117188, "global_step": 560443, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.022426128387451, "global_step": 560444, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0356953144073486, "global_step": 560445, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9836660623550415, "global_step": 560446, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0091285705566406, "global_step": 560447, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9980945587158203, "global_step": 560448, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.00706148147583, "global_step": 560449, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.032395362854004, "global_step": 560450, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9762016534805298, "global_step": 560451, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0121610164642334, "global_step": 560452, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.063762664794922, "global_step": 560453, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.075667142868042, "global_step": 560454, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0583479404449463, "global_step": 560455, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9923096895217896, "global_step": 560456, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.081479549407959, "global_step": 560457, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0453269481658936, "global_step": 560458, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.028775453567505, "global_step": 560459, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.049567461013794, "global_step": 560460, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.8672502040863037, "global_step": 560461, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.049494981765747, "global_step": 560462, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.038086175918579, "global_step": 560463, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.065920352935791, "global_step": 560464, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0664031505584717, "global_step": 560465, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.043482780456543, "global_step": 560466, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.02622652053833, "global_step": 560467, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9806315898895264, "global_step": 560468, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9434049129486084, "global_step": 560469, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0113115310668945, "global_step": 560470, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.996816635131836, "global_step": 560471, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0653955936431885, "global_step": 560472, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.009547472000122, "global_step": 560473, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0078318119049072, "global_step": 560474, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.059805154800415, "global_step": 560475, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9935752153396606, "global_step": 560476, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1277003288269043, "global_step": 560477, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0135416984558105, "global_step": 560478, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0061168670654297, "global_step": 560479, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0816104412078857, "global_step": 560480, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0191521644592285, "global_step": 560481, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9830420017242432, "global_step": 560482, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0516815185546875, "global_step": 560483, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0351521968841553, "global_step": 560484, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0311033725738525, "global_step": 560485, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0254569053649902, "global_step": 560486, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.053539752960205, "global_step": 560487, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0723488330841064, "global_step": 560488, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.927313208580017, "global_step": 560489, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0700385570526123, "global_step": 560490, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.059051752090454, "global_step": 560491, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0360617637634277, "global_step": 560492, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.90785813331604, "global_step": 560493, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9860646724700928, "global_step": 560494, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.064885139465332, "global_step": 560495, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0029006004333496, "global_step": 560496, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9971797466278076, "global_step": 560497, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0655553340911865, "global_step": 560498, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.009293794631958, "global_step": 560499, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.990513801574707, "global_step": 560500, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.016221046447754, "global_step": 560501, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0194902420043945, "global_step": 560502, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.10296368598938, "global_step": 560503, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9761537313461304, "global_step": 560504, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.036552906036377, "global_step": 560505, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.061361789703369, "global_step": 560506, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.083580732345581, "global_step": 560507, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1203718185424805, "global_step": 560508, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.072260856628418, "global_step": 560509, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9678627252578735, "global_step": 560510, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0390992164611816, "global_step": 560511, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.975251317024231, "global_step": 560512, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9946376085281372, "global_step": 560513, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.097165822982788, "global_step": 560514, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.029343605041504, "global_step": 560515, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0808768272399902, "global_step": 560516, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0121772289276123, "global_step": 560517, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9631294012069702, "global_step": 560518, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.000014543533325, "global_step": 560519, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0481534004211426, "global_step": 560520, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.080784797668457, "global_step": 560521, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9933274984359741, "global_step": 560522, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9617317914962769, "global_step": 560523, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9712855815887451, "global_step": 560524, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.024726629257202, "global_step": 560525, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.987702488899231, "global_step": 560526, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.061903953552246, "global_step": 560527, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.004823923110962, "global_step": 560528, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0205435752868652, "global_step": 560529, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.023139715194702, "global_step": 560530, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9636809825897217, "global_step": 560531, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.014177083969116, "global_step": 560532, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0291690826416016, "global_step": 560533, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0383949279785156, "global_step": 560534, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.019197940826416, "global_step": 560535, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.045823574066162, "global_step": 560536, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0560801029205322, "global_step": 560537, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9924235343933105, "global_step": 560538, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.08996844291687, "global_step": 560539, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.001079797744751, "global_step": 560540, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.074075222015381, "global_step": 560541, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0568923950195312, "global_step": 560542, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.042919397354126, "global_step": 560543, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0348141193389893, "global_step": 560544, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.051868200302124, "global_step": 560545, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0102553367614746, "global_step": 560546, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9804356098175049, "global_step": 560547, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.02401065826416, "global_step": 560548, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.971268892288208, "global_step": 560549, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1317811012268066, "global_step": 560550, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.081406831741333, "global_step": 560551, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9838892221450806, "global_step": 560552, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.008056879043579, "global_step": 560553, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.028438091278076, "global_step": 560554, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.015033721923828, "global_step": 560555, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9979583024978638, "global_step": 560556, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9964888095855713, "global_step": 560557, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0257925987243652, "global_step": 560558, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0752205848693848, "global_step": 560559, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.037926435470581, "global_step": 560560, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0230624675750732, "global_step": 560561, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0194339752197266, "global_step": 560562, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9836703538894653, "global_step": 560563, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0566799640655518, "global_step": 560564, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9238959550857544, "global_step": 560565, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0527029037475586, "global_step": 560566, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9385420083999634, "global_step": 560567, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0443694591522217, "global_step": 560568, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.03054141998291, "global_step": 560569, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0867695808410645, "global_step": 560570, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.019470691680908, "global_step": 560571, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0439302921295166, "global_step": 560572, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.044858694076538, "global_step": 560573, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.075373888015747, "global_step": 560574, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0033915042877197, "global_step": 560575, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.940272569656372, "global_step": 560576, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9866609573364258, "global_step": 560577, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.051903486251831, "global_step": 560578, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0697550773620605, "global_step": 560579, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.039673328399658, "global_step": 560580, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0403740406036377, "global_step": 560581, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0352351665496826, "global_step": 560582, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0779683589935303, "global_step": 560583, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0781972408294678, "global_step": 560584, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9454392194747925, "global_step": 560585, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.027557611465454, "global_step": 560586, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.023773431777954, "global_step": 560587, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.097008228302002, "global_step": 560588, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9743291139602661, "global_step": 560589, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.033828020095825, "global_step": 560590, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9914047718048096, "global_step": 560591, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.08406138420105, "global_step": 560592, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0645384788513184, "global_step": 560593, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.052549123764038, "global_step": 560594, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0183446407318115, "global_step": 560595, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.067981719970703, "global_step": 560596, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0640368461608887, "global_step": 560597, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0311038494110107, "global_step": 560598, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.015908718109131, "global_step": 560599, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.041851043701172, "global_step": 560600, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0043575763702393, "global_step": 560601, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0073907375335693, "global_step": 560602, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0250401496887207, "global_step": 560603, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9751379489898682, "global_step": 560604, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0775277614593506, "global_step": 560605, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9547629356384277, "global_step": 560606, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.088381290435791, "global_step": 560607, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0549283027648926, "global_step": 560608, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.091885566711426, "global_step": 560609, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0101943016052246, "global_step": 560610, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0216872692108154, "global_step": 560611, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.001513957977295, "global_step": 560612, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.06453537940979, "global_step": 560613, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.064120292663574, "global_step": 560614, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0201680660247803, "global_step": 560615, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0465281009674072, "global_step": 560616, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.000345468521118, "global_step": 560617, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0351452827453613, "global_step": 560618, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.015810251235962, "global_step": 560619, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0896811485290527, "global_step": 560620, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.081082820892334, "global_step": 560621, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.021721124649048, "global_step": 560622, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0082154273986816, "global_step": 560623, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.071011781692505, "global_step": 560624, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1148674488067627, "global_step": 560625, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.967879295349121, "global_step": 560626, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.014808416366577, "global_step": 560627, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.939279556274414, "global_step": 560628, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0576419830322266, "global_step": 560629, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0298588275909424, "global_step": 560630, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.058370590209961, "global_step": 560631, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.943434238433838, "global_step": 560632, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.000307083129883, "global_step": 560633, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.069953680038452, "global_step": 560634, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.087336540222168, "global_step": 560635, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0282387733459473, "global_step": 560636, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0119376182556152, "global_step": 560637, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9931163787841797, "global_step": 560638, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0095341205596924, "global_step": 560639, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9981755018234253, "global_step": 560640, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.931267261505127, "global_step": 560641, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0938611030578613, "global_step": 560642, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0396881103515625, "global_step": 560643, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9788821935653687, "global_step": 560644, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0617456436157227, "global_step": 560645, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0291361808776855, "global_step": 560646, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.029236316680908, "global_step": 560647, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0087504386901855, "global_step": 560648, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.02170991897583, "global_step": 560649, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9866597652435303, "global_step": 560650, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.014965295791626, "global_step": 560651, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.997269630432129, "global_step": 560652, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0257017612457275, "global_step": 560653, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.030078172683716, "global_step": 560654, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.01908802986145, "global_step": 560655, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.029325485229492, "global_step": 560656, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0024871826171875, "global_step": 560657, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.077378988265991, "global_step": 560658, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9983597993850708, "global_step": 560659, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9627574682235718, "global_step": 560660, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.038093328475952, "global_step": 560661, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0811824798583984, "global_step": 560662, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.06488037109375, "global_step": 560663, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9484305381774902, "global_step": 560664, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0767993927001953, "global_step": 560665, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.982167363166809, "global_step": 560666, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9897406101226807, "global_step": 560667, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.087315320968628, "global_step": 560668, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.060166835784912, "global_step": 560669, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0769829750061035, "global_step": 560670, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.07413649559021, "global_step": 560671, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0513877868652344, "global_step": 560672, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0272719860076904, "global_step": 560673, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.036669969558716, "global_step": 560674, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.088799238204956, "global_step": 560675, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9529814720153809, "global_step": 560676, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9791969060897827, "global_step": 560677, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0642080307006836, "global_step": 560678, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.899544358253479, "global_step": 560679, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0079777240753174, "global_step": 560680, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9311294555664062, "global_step": 560681, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.078894853591919, "global_step": 560682, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.059901714324951, "global_step": 560683, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.985191822052002, "global_step": 560684, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.009378433227539, "global_step": 560685, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0128426551818848, "global_step": 560686, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9952176809310913, "global_step": 560687, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0270023345947266, "global_step": 560688, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.061122417449951, "global_step": 560689, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0063536167144775, "global_step": 560690, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.019852876663208, "global_step": 560691, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0709030628204346, "global_step": 560692, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.042604923248291, "global_step": 560693, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9671934843063354, "global_step": 560694, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.043410062789917, "global_step": 560695, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.040961980819702, "global_step": 560696, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.884687900543213, "global_step": 560697, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9952759742736816, "global_step": 560698, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0056941509246826, "global_step": 560699, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0362884998321533, "global_step": 560700, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.924233078956604, "global_step": 560701, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1122324466705322, "global_step": 560702, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9360162019729614, "global_step": 560703, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0062808990478516, "global_step": 560704, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0144472122192383, "global_step": 560705, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.022826671600342, "global_step": 560706, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.012887477874756, "global_step": 560707, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9787694215774536, "global_step": 560708, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0490221977233887, "global_step": 560709, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0926663875579834, "global_step": 560710, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0593905448913574, "global_step": 560711, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0555360317230225, "global_step": 560712, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0241539478302, "global_step": 560713, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.060882329940796, "global_step": 560714, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1057398319244385, "global_step": 560715, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.031033992767334, "global_step": 560716, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0652127265930176, "global_step": 560717, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.002922534942627, "global_step": 560718, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0328798294067383, "global_step": 560719, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.946092963218689, "global_step": 560720, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.051845073699951, "global_step": 560721, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9996100664138794, "global_step": 560722, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.081747531890869, "global_step": 560723, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.085536241531372, "global_step": 560724, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9158074855804443, "global_step": 560725, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0772783756256104, "global_step": 560726, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0856094360351562, "global_step": 560727, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9934139251708984, "global_step": 560728, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0313994884490967, "global_step": 560729, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1238811016082764, "global_step": 560730, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9172381162643433, "global_step": 560731, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9508403539657593, "global_step": 560732, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9543110132217407, "global_step": 560733, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0308094024658203, "global_step": 560734, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0183897018432617, "global_step": 560735, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.058654308319092, "global_step": 560736, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0482470989227295, "global_step": 560737, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9905269145965576, "global_step": 560738, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9992527961730957, "global_step": 560739, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0254218578338623, "global_step": 560740, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.058743476867676, "global_step": 560741, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0297200679779053, "global_step": 560742, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9515281915664673, "global_step": 560743, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9724299907684326, "global_step": 560744, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.051302671432495, "global_step": 560745, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0429561138153076, "global_step": 560746, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.949514627456665, "global_step": 560747, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.058516025543213, "global_step": 560748, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.063858985900879, "global_step": 560749, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0332202911376953, "global_step": 560750, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9895974397659302, "global_step": 560751, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1179490089416504, "global_step": 560752, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0456416606903076, "global_step": 560753, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9823520183563232, "global_step": 560754, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0700199604034424, "global_step": 560755, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.036130428314209, "global_step": 560756, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0004661083221436, "global_step": 560757, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0005481243133545, "global_step": 560758, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9898042678833008, "global_step": 560759, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9987038373947144, "global_step": 560760, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0938220024108887, "global_step": 560761, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.023411273956299, "global_step": 560762, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.003070116043091, "global_step": 560763, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1704955101013184, "global_step": 560764, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9264310598373413, "global_step": 560765, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0363590717315674, "global_step": 560766, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0463109016418457, "global_step": 560767, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.028388738632202, "global_step": 560768, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.022895097732544, "global_step": 560769, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.905248761177063, "global_step": 560770, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0929694175720215, "global_step": 560771, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0844030380249023, "global_step": 560772, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0810546875, "global_step": 560773, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0123062133789062, "global_step": 560774, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0735034942626953, "global_step": 560775, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.067361831665039, "global_step": 560776, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.101818323135376, "global_step": 560777, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.12416934967041, "global_step": 560778, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9758938550949097, "global_step": 560779, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.047422170639038, "global_step": 560780, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.973387360572815, "global_step": 560781, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.082038402557373, "global_step": 560782, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9630448818206787, "global_step": 560783, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.052255392074585, "global_step": 560784, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1538755893707275, "global_step": 560785, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0914998054504395, "global_step": 560786, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.113795280456543, "global_step": 560787, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.034860849380493, "global_step": 560788, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0091190338134766, "global_step": 560789, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9739818572998047, "global_step": 560790, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0310308933258057, "global_step": 560791, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.989403247833252, "global_step": 560792, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.034308910369873, "global_step": 560793, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0331177711486816, "global_step": 560794, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0831735134124756, "global_step": 560795, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.998342514038086, "global_step": 560796, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.086456537246704, "global_step": 560797, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0666661262512207, "global_step": 560798, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9868663549423218, "global_step": 560799, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9561291933059692, "global_step": 560800, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.02839994430542, "global_step": 560801, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0253970623016357, "global_step": 560802, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1159708499908447, "global_step": 560803, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.070621967315674, "global_step": 560804, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0400807857513428, "global_step": 560805, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9514174461364746, "global_step": 560806, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.032431125640869, "global_step": 560807, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0991156101226807, "global_step": 560808, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9878742694854736, "global_step": 560809, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.041027545928955, "global_step": 560810, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9811590909957886, "global_step": 560811, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9205940961837769, "global_step": 560812, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.991803526878357, "global_step": 560813, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0787994861602783, "global_step": 560814, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0021347999572754, "global_step": 560815, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0013136863708496, "global_step": 560816, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1012935638427734, "global_step": 560817, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0348286628723145, "global_step": 560818, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9904279708862305, "global_step": 560819, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0402750968933105, "global_step": 560820, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0308310985565186, "global_step": 560821, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.989790916442871, "global_step": 560822, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.055584192276001, "global_step": 560823, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0587265491485596, "global_step": 560824, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0020267963409424, "global_step": 560825, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0093319416046143, "global_step": 560826, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0359935760498047, "global_step": 560827, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9765410423278809, "global_step": 560828, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0465376377105713, "global_step": 560829, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0184478759765625, "global_step": 560830, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.090541362762451, "global_step": 560831, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9812742471694946, "global_step": 560832, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9941538572311401, "global_step": 560833, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0426647663116455, "global_step": 560834, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.016329765319824, "global_step": 560835, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0446767807006836, "global_step": 560836, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.060220241546631, "global_step": 560837, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.061140537261963, "global_step": 560838, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9503406286239624, "global_step": 560839, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0562806129455566, "global_step": 560840, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9542741775512695, "global_step": 560841, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0317957401275635, "global_step": 560842, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0907645225524902, "global_step": 560843, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.048229694366455, "global_step": 560844, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.98856782913208, "global_step": 560845, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.063551425933838, "global_step": 560846, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.072699546813965, "global_step": 560847, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9572527408599854, "global_step": 560848, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9612672328948975, "global_step": 560849, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0429799556732178, "global_step": 560850, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0452558994293213, "global_step": 560851, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9808298349380493, "global_step": 560852, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0930216312408447, "global_step": 560853, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0360283851623535, "global_step": 560854, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.081806182861328, "global_step": 560855, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9857335090637207, "global_step": 560856, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0254480838775635, "global_step": 560857, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.081573724746704, "global_step": 560858, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9678387641906738, "global_step": 560859, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.052316904067993, "global_step": 560860, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1067981719970703, "global_step": 560861, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0860679149627686, "global_step": 560862, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0879886150360107, "global_step": 560863, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9789024591445923, "global_step": 560864, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0486130714416504, "global_step": 560865, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0118021965026855, "global_step": 560866, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9989253282546997, "global_step": 560867, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9859415292739868, "global_step": 560868, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9991346597671509, "global_step": 560869, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0390682220458984, "global_step": 560870, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.058504581451416, "global_step": 560871, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0184881687164307, "global_step": 560872, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0990748405456543, "global_step": 560873, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.044276475906372, "global_step": 560874, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0060248374938965, "global_step": 560875, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0874476432800293, "global_step": 560876, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0698843002319336, "global_step": 560877, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0227484703063965, "global_step": 560878, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.047964334487915, "global_step": 560879, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0038344860076904, "global_step": 560880, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0573503971099854, "global_step": 560881, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.955637812614441, "global_step": 560882, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0334789752960205, "global_step": 560883, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0624465942382812, "global_step": 560884, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.086254835128784, "global_step": 560885, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.025662899017334, "global_step": 560886, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9902074337005615, "global_step": 560887, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0732808113098145, "global_step": 560888, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.045958995819092, "global_step": 560889, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0001306533813477, "global_step": 560890, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0325727462768555, "global_step": 560891, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0597634315490723, "global_step": 560892, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1030914783477783, "global_step": 560893, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9986753463745117, "global_step": 560894, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9383113384246826, "global_step": 560895, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0222623348236084, "global_step": 560896, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.085409641265869, "global_step": 560897, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0619301795959473, "global_step": 560898, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9685758352279663, "global_step": 560899, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0769741535186768, "global_step": 560900, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0851290225982666, "global_step": 560901, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.061490774154663, "global_step": 560902, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.099693536758423, "global_step": 560903, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0086658000946045, "global_step": 560904, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0772016048431396, "global_step": 560905, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9711095094680786, "global_step": 560906, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1122264862060547, "global_step": 560907, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9888334274291992, "global_step": 560908, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9829730987548828, "global_step": 560909, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.046785831451416, "global_step": 560910, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0214502811431885, "global_step": 560911, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.949821949005127, "global_step": 560912, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.020707845687866, "global_step": 560913, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9333302974700928, "global_step": 560914, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0506105422973633, "global_step": 560915, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9763938188552856, "global_step": 560916, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.070974349975586, "global_step": 560917, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.144063949584961, "global_step": 560918, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0112850666046143, "global_step": 560919, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1081275939941406, "global_step": 560920, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0764901638031006, "global_step": 560921, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0910332202911377, "global_step": 560922, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0829641819000244, "global_step": 560923, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.053925037384033, "global_step": 560924, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.106076717376709, "global_step": 560925, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.950744390487671, "global_step": 560926, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.065035581588745, "global_step": 560927, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.001007556915283, "global_step": 560928, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9062118530273438, "global_step": 560929, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9521137475967407, "global_step": 560930, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.072845458984375, "global_step": 560931, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.062812566757202, "global_step": 560932, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.017401933670044, "global_step": 560933, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9909394979476929, "global_step": 560934, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.083054780960083, "global_step": 560935, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.070010185241699, "global_step": 560936, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.961823582649231, "global_step": 560937, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0563340187072754, "global_step": 560938, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.091322898864746, "global_step": 560939, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0594356060028076, "global_step": 560940, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.031536102294922, "global_step": 560941, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9787697792053223, "global_step": 560942, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0139358043670654, "global_step": 560943, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0247650146484375, "global_step": 560944, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0517897605895996, "global_step": 560945, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9352664947509766, "global_step": 560946, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0122039318084717, "global_step": 560947, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.026146173477173, "global_step": 560948, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0677459239959717, "global_step": 560949, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0082027912139893, "global_step": 560950, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0472373962402344, "global_step": 560951, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.92841374874115, "global_step": 560952, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.040943145751953, "global_step": 560953, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.029240369796753, "global_step": 560954, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0045223236083984, "global_step": 560955, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0191891193389893, "global_step": 560956, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0798180103302, "global_step": 560957, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0019748210906982, "global_step": 560958, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0796942710876465, "global_step": 560959, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.044891595840454, "global_step": 560960, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0126476287841797, "global_step": 560961, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0673627853393555, "global_step": 560962, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.085878372192383, "global_step": 560963, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.048309564590454, "global_step": 560964, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9939570426940918, "global_step": 560965, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9738162755966187, "global_step": 560966, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.09779953956604, "global_step": 560967, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0266754627227783, "global_step": 560968, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.044222116470337, "global_step": 560969, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.021419048309326, "global_step": 560970, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.107121467590332, "global_step": 560971, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0087294578552246, "global_step": 560972, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.023588180541992, "global_step": 560973, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9849132299423218, "global_step": 560974, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0323123931884766, "global_step": 560975, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.08442759513855, "global_step": 560976, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0645923614501953, "global_step": 560977, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.040891408920288, "global_step": 560978, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0255465507507324, "global_step": 560979, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0933563709259033, "global_step": 560980, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9901548624038696, "global_step": 560981, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0808169841766357, "global_step": 560982, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0471909046173096, "global_step": 560983, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.093561887741089, "global_step": 560984, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.023127317428589, "global_step": 560985, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0823943614959717, "global_step": 560986, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0837061405181885, "global_step": 560987, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0639517307281494, "global_step": 560988, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.022677183151245, "global_step": 560989, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0334432125091553, "global_step": 560990, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.960504174232483, "global_step": 560991, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.02225661277771, "global_step": 560992, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.018280267715454, "global_step": 560993, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9586704969406128, "global_step": 560994, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0013768672943115, "global_step": 560995, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0139360427856445, "global_step": 560996, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.918088436126709, "global_step": 560997, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.024193525314331, "global_step": 560998, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0607054233551025, "global_step": 560999, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0352416038513184, "global_step": 561000, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9755170345306396, "global_step": 561001, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0285778045654297, "global_step": 561002, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.028176784515381, "global_step": 561003, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0198864936828613, "global_step": 561004, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0462241172790527, "global_step": 561005, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0495986938476562, "global_step": 561006, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0979855060577393, "global_step": 561007, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.085394859313965, "global_step": 561008, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.995274543762207, "global_step": 561009, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0766866207122803, "global_step": 561010, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.079268217086792, "global_step": 561011, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0376806259155273, "global_step": 561012, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0085387229919434, "global_step": 561013, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0184507369995117, "global_step": 561014, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9691989421844482, "global_step": 561015, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0500693321228027, "global_step": 561016, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0167996883392334, "global_step": 561017, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0907742977142334, "global_step": 561018, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9837276935577393, "global_step": 561019, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1178336143493652, "global_step": 561020, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.053307056427002, "global_step": 561021, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0369231700897217, "global_step": 561022, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.046135902404785, "global_step": 561023, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9648324251174927, "global_step": 561024, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9975941181182861, "global_step": 561025, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0296926498413086, "global_step": 561026, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0399484634399414, "global_step": 561027, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0110538005828857, "global_step": 561028, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.8914142847061157, "global_step": 561029, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0532162189483643, "global_step": 561030, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9721142053604126, "global_step": 561031, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.075110912322998, "global_step": 561032, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0418994426727295, "global_step": 561033, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0683860778808594, "global_step": 561034, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0608339309692383, "global_step": 561035, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9975155591964722, "global_step": 561036, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.055762529373169, "global_step": 561037, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0821151733398438, "global_step": 561038, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9938945770263672, "global_step": 561039, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.03000545501709, "global_step": 561040, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0283422470092773, "global_step": 561041, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0201964378356934, "global_step": 561042, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1098573207855225, "global_step": 561043, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0216188430786133, "global_step": 561044, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1275839805603027, "global_step": 561045, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0396106243133545, "global_step": 561046, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0996510982513428, "global_step": 561047, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0049080848693848, "global_step": 561048, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9921424388885498, "global_step": 561049, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0824012756347656, "global_step": 561050, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.099912643432617, "global_step": 561051, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.004068374633789, "global_step": 561052, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1132607460021973, "global_step": 561053, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.01562762260437, "global_step": 561054, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0848498344421387, "global_step": 561055, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1964335441589355, "global_step": 561056, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0139899253845215, "global_step": 561057, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0552549362182617, "global_step": 561058, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.027315139770508, "global_step": 561059, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.043654441833496, "global_step": 561060, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.060650587081909, "global_step": 561061, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.129312515258789, "global_step": 561062, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1330442428588867, "global_step": 561063, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9986114501953125, "global_step": 561064, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0511491298675537, "global_step": 561065, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.053417682647705, "global_step": 561066, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.015148162841797, "global_step": 561067, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9847526550292969, "global_step": 561068, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0642380714416504, "global_step": 561069, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0326485633850098, "global_step": 561070, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.076350212097168, "global_step": 561071, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0580902099609375, "global_step": 561072, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0684356689453125, "global_step": 561073, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0544793605804443, "global_step": 561074, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0613038539886475, "global_step": 561075, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.022101402282715, "global_step": 561076, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.163029432296753, "global_step": 561077, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0636584758758545, "global_step": 561078, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9104300737380981, "global_step": 561079, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0110976696014404, "global_step": 561080, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.966239094734192, "global_step": 561081, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.101468324661255, "global_step": 561082, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9945205450057983, "global_step": 561083, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.107513904571533, "global_step": 561084, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.050326347351074, "global_step": 561085, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.003436326980591, "global_step": 561086, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0492687225341797, "global_step": 561087, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.04776668548584, "global_step": 561088, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9427117109298706, "global_step": 561089, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.053825855255127, "global_step": 561090, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1629018783569336, "global_step": 561091, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0100693702697754, "global_step": 561092, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0532803535461426, "global_step": 561093, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.977124810218811, "global_step": 561094, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1168577671051025, "global_step": 561095, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9676322937011719, "global_step": 561096, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9326165914535522, "global_step": 561097, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.012826919555664, "global_step": 561098, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.063234567642212, "global_step": 561099, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.03440523147583, "global_step": 561100, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0390567779541016, "global_step": 561101, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9393914937973022, "global_step": 561102, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9908294677734375, "global_step": 561103, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0650737285614014, "global_step": 561104, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.015536308288574, "global_step": 561105, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9971246719360352, "global_step": 561106, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9820027351379395, "global_step": 561107, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9787466526031494, "global_step": 561108, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.10640025138855, "global_step": 561109, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.104311466217041, "global_step": 561110, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9809993505477905, "global_step": 561111, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.071251153945923, "global_step": 561112, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0095372200012207, "global_step": 561113, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9961819648742676, "global_step": 561114, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9390416145324707, "global_step": 561115, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9930187463760376, "global_step": 561116, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9864447116851807, "global_step": 561117, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0841455459594727, "global_step": 561118, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.069127082824707, "global_step": 561119, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0069339275360107, "global_step": 561120, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.01515531539917, "global_step": 561121, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1106841564178467, "global_step": 561122, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.014605760574341, "global_step": 561123, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.047285795211792, "global_step": 561124, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.125877857208252, "global_step": 561125, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1005167961120605, "global_step": 561126, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0640275478363037, "global_step": 561127, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9797650575637817, "global_step": 561128, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.984649658203125, "global_step": 561129, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.990822196006775, "global_step": 561130, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0495641231536865, "global_step": 561131, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0230355262756348, "global_step": 561132, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9862531423568726, "global_step": 561133, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0258066654205322, "global_step": 561134, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9903258085250854, "global_step": 561135, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9989454746246338, "global_step": 561136, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.137925624847412, "global_step": 561137, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.005702018737793, "global_step": 561138, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0405640602111816, "global_step": 561139, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.1156747341156006, "global_step": 561140, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0794131755828857, "global_step": 561141, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0030877590179443, "global_step": 561142, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.998903751373291, "global_step": 561143, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.994533896446228, "global_step": 561144, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9688270092010498, "global_step": 561145, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.062476873397827, "global_step": 561146, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9752012491226196, "global_step": 561147, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9637552499771118, "global_step": 561148, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0613160133361816, "global_step": 561149, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.042853832244873, "global_step": 561150, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.00923228263855, "global_step": 561151, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.112471580505371, "global_step": 561152, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.068938732147217, "global_step": 561153, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0694284439086914, "global_step": 561154, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9973000288009644, "global_step": 561155, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0719292163848877, "global_step": 561156, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.073796510696411, "global_step": 561157, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9345078468322754, "global_step": 561158, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9355005025863647, "global_step": 561159, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9901130199432373, "global_step": 561160, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0513932704925537, "global_step": 561161, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0531911849975586, "global_step": 561162, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9796360731124878, "global_step": 561163, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9943468570709229, "global_step": 561164, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9943912029266357, "global_step": 561165, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9771404266357422, "global_step": 561166, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.016108512878418, "global_step": 561167, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9671375751495361, "global_step": 561168, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0251991748809814, "global_step": 561169, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.061133861541748, "global_step": 561170, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.926743745803833, "global_step": 561171, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9881178140640259, "global_step": 561172, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9749586582183838, "global_step": 561173, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9609441757202148, "global_step": 561174, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0099174976348877, "global_step": 561175, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.037039041519165, "global_step": 561176, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0350167751312256, "global_step": 561177, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.086444854736328, "global_step": 561178, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0989835262298584, "global_step": 561179, "epoch": 928, "lr": 5e-05}
{"train_loss": 1.9158935546875, "global_step": 561180, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0394701957702637, "global_step": 561181, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.0503506660461426, "global_step": 561182, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.027406930923462, "global_step": 561183, "epoch": 928, "lr": 5e-05}
{"train_loss": 2.042250156402588, "global_step": 561184, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.09281063079834, "global_step": 561185, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0553176403045654, "global_step": 561186, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0193052291870117, "global_step": 561187, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.09769344329834, "global_step": 561188, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0879344940185547, "global_step": 561189, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0602476596832275, "global_step": 561190, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1270153522491455, "global_step": 561191, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9206336736679077, "global_step": 561192, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0781843662261963, "global_step": 561193, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.119349241256714, "global_step": 561194, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0627949237823486, "global_step": 561195, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0141873359680176, "global_step": 561196, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9847415685653687, "global_step": 561197, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.070972204208374, "global_step": 561198, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0823731422424316, "global_step": 561199, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0042800903320312, "global_step": 561200, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0005667209625244, "global_step": 561201, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.039566993713379, "global_step": 561202, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0582666397094727, "global_step": 561203, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.916126012802124, "global_step": 561204, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.990964412689209, "global_step": 561205, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0776305198669434, "global_step": 561206, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9042835235595703, "global_step": 561207, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9814503192901611, "global_step": 561208, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0086565017700195, "global_step": 561209, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0395631790161133, "global_step": 561210, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0451250076293945, "global_step": 561211, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.015608310699463, "global_step": 561212, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9613476991653442, "global_step": 561213, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.076364278793335, "global_step": 561214, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9559260606765747, "global_step": 561215, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0714244842529297, "global_step": 561216, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9446781873703003, "global_step": 561217, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9348511695861816, "global_step": 561218, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0170674324035645, "global_step": 561219, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.017134428024292, "global_step": 561220, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.049062728881836, "global_step": 561221, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0216286182403564, "global_step": 561222, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0002150535583496, "global_step": 561223, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.996350884437561, "global_step": 561224, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.06607985496521, "global_step": 561225, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9462846517562866, "global_step": 561226, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.971023678779602, "global_step": 561227, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.015127182006836, "global_step": 561228, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9640309810638428, "global_step": 561229, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9477581977844238, "global_step": 561230, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0494654178619385, "global_step": 561231, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1010351181030273, "global_step": 561232, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0472283363342285, "global_step": 561233, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9310779571533203, "global_step": 561234, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.053044557571411, "global_step": 561235, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.02067494392395, "global_step": 561236, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0216116905212402, "global_step": 561237, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0965213775634766, "global_step": 561238, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.969692587852478, "global_step": 561239, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.050199508666992, "global_step": 561240, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0189077854156494, "global_step": 561241, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.942354440689087, "global_step": 561242, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9445929527282715, "global_step": 561243, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0223443508148193, "global_step": 561244, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1057803630828857, "global_step": 561245, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0283408164978027, "global_step": 561246, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.948824405670166, "global_step": 561247, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0985875129699707, "global_step": 561248, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.061204433441162, "global_step": 561249, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0597355365753174, "global_step": 561250, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9746760129928589, "global_step": 561251, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0167248249053955, "global_step": 561252, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.983884334564209, "global_step": 561253, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0205254554748535, "global_step": 561254, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9123972654342651, "global_step": 561255, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0476198196411133, "global_step": 561256, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0169246196746826, "global_step": 561257, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.029048204421997, "global_step": 561258, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0828986167907715, "global_step": 561259, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.050588607788086, "global_step": 561260, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0085089206695557, "global_step": 561261, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.08967924118042, "global_step": 561262, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9797521829605103, "global_step": 561263, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0318000316619873, "global_step": 561264, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.029702663421631, "global_step": 561265, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0152995586395264, "global_step": 561266, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.043173313140869, "global_step": 561267, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.045074462890625, "global_step": 561268, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9797241687774658, "global_step": 561269, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.013317584991455, "global_step": 561270, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0637032985687256, "global_step": 561271, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.961090326309204, "global_step": 561272, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.003268241882324, "global_step": 561273, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0115158557891846, "global_step": 561274, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9671169519424438, "global_step": 561275, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.02978253364563, "global_step": 561276, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0728399753570557, "global_step": 561277, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9718194007873535, "global_step": 561278, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9784200191497803, "global_step": 561279, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0774312019348145, "global_step": 561280, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.019663095474243, "global_step": 561281, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.045311212539673, "global_step": 561282, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9915752410888672, "global_step": 561283, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0358593463897705, "global_step": 561284, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0385704040527344, "global_step": 561285, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.064146041870117, "global_step": 561286, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.973246693611145, "global_step": 561287, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0100860595703125, "global_step": 561288, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0029866695404053, "global_step": 561289, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9882303476333618, "global_step": 561290, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0253524780273438, "global_step": 561291, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9694116115570068, "global_step": 561292, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.032768487930298, "global_step": 561293, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0017473697662354, "global_step": 561294, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9536923170089722, "global_step": 561295, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0504860877990723, "global_step": 561296, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0407330989837646, "global_step": 561297, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9678146839141846, "global_step": 561298, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9337384700775146, "global_step": 561299, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.035017490386963, "global_step": 561300, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1052212715148926, "global_step": 561301, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.012624740600586, "global_step": 561302, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.975694179534912, "global_step": 561303, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0629727840423584, "global_step": 561304, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9824440479278564, "global_step": 561305, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.069498062133789, "global_step": 561306, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0682454109191895, "global_step": 561307, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0344042778015137, "global_step": 561308, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9464268684387207, "global_step": 561309, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.000866413116455, "global_step": 561310, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0346884727478027, "global_step": 561311, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.985716462135315, "global_step": 561312, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.079141855239868, "global_step": 561313, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.978513479232788, "global_step": 561314, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9870381355285645, "global_step": 561315, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9463306665420532, "global_step": 561316, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0973973274230957, "global_step": 561317, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.028663158416748, "global_step": 561318, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0177371501922607, "global_step": 561319, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0728602409362793, "global_step": 561320, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.925426721572876, "global_step": 561321, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0346148014068604, "global_step": 561322, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.039374351501465, "global_step": 561323, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0317840576171875, "global_step": 561324, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0789718627929688, "global_step": 561325, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.951863408088684, "global_step": 561326, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.970744013786316, "global_step": 561327, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0529215335845947, "global_step": 561328, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0598537921905518, "global_step": 561329, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0478038787841797, "global_step": 561330, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.11592173576355, "global_step": 561331, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9293982982635498, "global_step": 561332, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.972223162651062, "global_step": 561333, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0072977542877197, "global_step": 561334, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.035911798477173, "global_step": 561335, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9659068584442139, "global_step": 561336, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.040156602859497, "global_step": 561337, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0093741416931152, "global_step": 561338, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0453946590423584, "global_step": 561339, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.00284481048584, "global_step": 561340, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0726749897003174, "global_step": 561341, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0517523288726807, "global_step": 561342, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0422277450561523, "global_step": 561343, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.020771026611328, "global_step": 561344, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.035606861114502, "global_step": 561345, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9220528602600098, "global_step": 561346, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9865710735321045, "global_step": 561347, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.064282178878784, "global_step": 561348, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0258233547210693, "global_step": 561349, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9568581581115723, "global_step": 561350, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0319249629974365, "global_step": 561351, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0043585300445557, "global_step": 561352, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1195602416992188, "global_step": 561353, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9900461435317993, "global_step": 561354, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.005974292755127, "global_step": 561355, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9455039501190186, "global_step": 561356, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0845868587493896, "global_step": 561357, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.093379020690918, "global_step": 561358, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1072778701782227, "global_step": 561359, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0219738483428955, "global_step": 561360, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0178847312927246, "global_step": 561361, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.975870966911316, "global_step": 561362, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0222182273864746, "global_step": 561363, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0263454914093018, "global_step": 561364, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.001371145248413, "global_step": 561365, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0151240825653076, "global_step": 561366, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1184422969818115, "global_step": 561367, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9935579299926758, "global_step": 561368, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0166213512420654, "global_step": 561369, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0169456005096436, "global_step": 561370, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.984190583229065, "global_step": 561371, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.11562442779541, "global_step": 561372, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0663630962371826, "global_step": 561373, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0028254985809326, "global_step": 561374, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0050458908081055, "global_step": 561375, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9940767288208008, "global_step": 561376, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1295526027679443, "global_step": 561377, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.989835262298584, "global_step": 561378, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.002138137817383, "global_step": 561379, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0757415294647217, "global_step": 561380, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0131919384002686, "global_step": 561381, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.002351760864258, "global_step": 561382, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9973139762878418, "global_step": 561383, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9970284700393677, "global_step": 561384, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0347437858581543, "global_step": 561385, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.023286819458008, "global_step": 561386, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.105910301208496, "global_step": 561387, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9858391284942627, "global_step": 561388, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0231847763061523, "global_step": 561389, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.030440092086792, "global_step": 561390, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.047538995742798, "global_step": 561391, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0733754634857178, "global_step": 561392, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9122719764709473, "global_step": 561393, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9428305625915527, "global_step": 561394, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.05120587348938, "global_step": 561395, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0675618648529053, "global_step": 561396, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9253389835357666, "global_step": 561397, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.001441240310669, "global_step": 561398, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0971779823303223, "global_step": 561399, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9884556531906128, "global_step": 561400, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.102583646774292, "global_step": 561401, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9939442873001099, "global_step": 561402, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.048332691192627, "global_step": 561403, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0108628273010254, "global_step": 561404, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9744908809661865, "global_step": 561405, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9972238540649414, "global_step": 561406, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0304148197174072, "global_step": 561407, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.044370412826538, "global_step": 561408, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0168516635894775, "global_step": 561409, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.077399492263794, "global_step": 561410, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9978728294372559, "global_step": 561411, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.014362096786499, "global_step": 561412, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.053645372390747, "global_step": 561413, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9704121351242065, "global_step": 561414, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0414464473724365, "global_step": 561415, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9827595949172974, "global_step": 561416, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1594204902648926, "global_step": 561417, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.046828031539917, "global_step": 561418, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0275650024414062, "global_step": 561419, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0770347118377686, "global_step": 561420, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.008450984954834, "global_step": 561421, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.021073341369629, "global_step": 561422, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.084317922592163, "global_step": 561423, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9113000631332397, "global_step": 561424, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9303600788116455, "global_step": 561425, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0665009021759033, "global_step": 561426, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.990732192993164, "global_step": 561427, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.059636116027832, "global_step": 561428, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9680274724960327, "global_step": 561429, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0822083950042725, "global_step": 561430, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.048949956893921, "global_step": 561431, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.945944905281067, "global_step": 561432, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9786770343780518, "global_step": 561433, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0485448837280273, "global_step": 561434, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0861928462982178, "global_step": 561435, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.065718412399292, "global_step": 561436, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.997023344039917, "global_step": 561437, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0633351802825928, "global_step": 561438, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9734376668930054, "global_step": 561439, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9722851514816284, "global_step": 561440, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9560250043869019, "global_step": 561441, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0199737548828125, "global_step": 561442, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1040756702423096, "global_step": 561443, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.006963014602661, "global_step": 561444, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.072277784347534, "global_step": 561445, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9561944007873535, "global_step": 561446, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9624072313308716, "global_step": 561447, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0641732215881348, "global_step": 561448, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.070258855819702, "global_step": 561449, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.050166606903076, "global_step": 561450, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9926992654800415, "global_step": 561451, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0868594646453857, "global_step": 561452, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.083956003189087, "global_step": 561453, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.991005778312683, "global_step": 561454, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.939822793006897, "global_step": 561455, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.006927728652954, "global_step": 561456, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0686140060424805, "global_step": 561457, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0703742504119873, "global_step": 561458, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0394864082336426, "global_step": 561459, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0353689193725586, "global_step": 561460, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1029951572418213, "global_step": 561461, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9981424808502197, "global_step": 561462, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9857975244522095, "global_step": 561463, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.123725414276123, "global_step": 561464, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0762295722961426, "global_step": 561465, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0427603721618652, "global_step": 561466, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.972481369972229, "global_step": 561467, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0066092014312744, "global_step": 561468, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0422563552856445, "global_step": 561469, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9756243228912354, "global_step": 561470, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0264055728912354, "global_step": 561471, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0873663425445557, "global_step": 561472, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0631980895996094, "global_step": 561473, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0323355197906494, "global_step": 561474, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.068727731704712, "global_step": 561475, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.100813150405884, "global_step": 561476, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.961695671081543, "global_step": 561477, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.97348153591156, "global_step": 561478, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9754090309143066, "global_step": 561479, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0480990409851074, "global_step": 561480, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9789892435073853, "global_step": 561481, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9360473155975342, "global_step": 561482, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0516278743743896, "global_step": 561483, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0331027507781982, "global_step": 561484, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0344746112823486, "global_step": 561485, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0694284439086914, "global_step": 561486, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0588066577911377, "global_step": 561487, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1056344509124756, "global_step": 561488, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9636478424072266, "global_step": 561489, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0096116065979004, "global_step": 561490, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.055863618850708, "global_step": 561491, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0588700771331787, "global_step": 561492, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9444891214370728, "global_step": 561493, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.026270866394043, "global_step": 561494, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.942549228668213, "global_step": 561495, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.972188115119934, "global_step": 561496, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1384427547454834, "global_step": 561497, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.979922890663147, "global_step": 561498, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9857555627822876, "global_step": 561499, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0739123821258545, "global_step": 561500, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.054178237915039, "global_step": 561501, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.977506160736084, "global_step": 561502, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.049259662628174, "global_step": 561503, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0757017135620117, "global_step": 561504, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.984647512435913, "global_step": 561505, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0342636108398438, "global_step": 561506, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9693470001220703, "global_step": 561507, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.97684907913208, "global_step": 561508, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0059633255004883, "global_step": 561509, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.99045991897583, "global_step": 561510, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0353288650512695, "global_step": 561511, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0374903678894043, "global_step": 561512, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.096353054046631, "global_step": 561513, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.01534104347229, "global_step": 561514, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0239169597625732, "global_step": 561515, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9347699880599976, "global_step": 561516, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.006688117980957, "global_step": 561517, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9900949001312256, "global_step": 561518, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.005537271499634, "global_step": 561519, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0219643115997314, "global_step": 561520, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0082521438598633, "global_step": 561521, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.088998317718506, "global_step": 561522, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9700669050216675, "global_step": 561523, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0153281688690186, "global_step": 561524, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.039228916168213, "global_step": 561525, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.956906795501709, "global_step": 561526, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9602751731872559, "global_step": 561527, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0801546573638916, "global_step": 561528, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9503591060638428, "global_step": 561529, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9875431060791016, "global_step": 561530, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0062294006347656, "global_step": 561531, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.062804698944092, "global_step": 561532, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0717124938964844, "global_step": 561533, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.011977195739746, "global_step": 561534, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.072378158569336, "global_step": 561535, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9989397525787354, "global_step": 561536, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0413239002227783, "global_step": 561537, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9697213172912598, "global_step": 561538, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0939996242523193, "global_step": 561539, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.014758348464966, "global_step": 561540, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.088120222091675, "global_step": 561541, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.044264793395996, "global_step": 561542, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0133702754974365, "global_step": 561543, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9977136850357056, "global_step": 561544, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9506632089614868, "global_step": 561545, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0247576236724854, "global_step": 561546, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.101062774658203, "global_step": 561547, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0510060787200928, "global_step": 561548, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.036986827850342, "global_step": 561549, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.096470594406128, "global_step": 561550, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0016629695892334, "global_step": 561551, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.045583724975586, "global_step": 561552, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.961539387702942, "global_step": 561553, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0198159217834473, "global_step": 561554, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.02506947517395, "global_step": 561555, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1243197917938232, "global_step": 561556, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0630910396575928, "global_step": 561557, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.045766592025757, "global_step": 561558, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0285608768463135, "global_step": 561559, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.073061943054199, "global_step": 561560, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.064805030822754, "global_step": 561561, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.076267957687378, "global_step": 561562, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.999125599861145, "global_step": 561563, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1046454906463623, "global_step": 561564, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0165412425994873, "global_step": 561565, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.001753091812134, "global_step": 561566, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.016223669052124, "global_step": 561567, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9174219369888306, "global_step": 561568, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0676074028015137, "global_step": 561569, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0534563064575195, "global_step": 561570, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.059394359588623, "global_step": 561571, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0189290046691895, "global_step": 561572, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0273919105529785, "global_step": 561573, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0518381595611572, "global_step": 561574, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9666738510131836, "global_step": 561575, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0560619831085205, "global_step": 561576, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.028202533721924, "global_step": 561577, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.068223714828491, "global_step": 561578, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.053039073944092, "global_step": 561579, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0259366035461426, "global_step": 561580, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.060311794281006, "global_step": 561581, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0677490234375, "global_step": 561582, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0551986694335938, "global_step": 561583, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.017995834350586, "global_step": 561584, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1008646488189697, "global_step": 561585, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9710887670516968, "global_step": 561586, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.050814390182495, "global_step": 561587, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0439865589141846, "global_step": 561588, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0432381629943848, "global_step": 561589, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9865084886550903, "global_step": 561590, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.012387275695801, "global_step": 561591, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.032723903656006, "global_step": 561592, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0443460941314697, "global_step": 561593, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9698221683502197, "global_step": 561594, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9808801412582397, "global_step": 561595, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0336508750915527, "global_step": 561596, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0305917263031006, "global_step": 561597, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0392560958862305, "global_step": 561598, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.074894905090332, "global_step": 561599, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.996678352355957, "global_step": 561600, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1665921211242676, "global_step": 561601, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0451912879943848, "global_step": 561602, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.049055814743042, "global_step": 561603, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0306644439697266, "global_step": 561604, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0629825592041016, "global_step": 561605, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0910725593566895, "global_step": 561606, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9732884168624878, "global_step": 561607, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9886424541473389, "global_step": 561608, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0006980895996094, "global_step": 561609, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9556152820587158, "global_step": 561610, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.008436679840088, "global_step": 561611, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0394093990325928, "global_step": 561612, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.97223699092865, "global_step": 561613, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0089399814605713, "global_step": 561614, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9563994407653809, "global_step": 561615, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9898650646209717, "global_step": 561616, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1049327850341797, "global_step": 561617, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.061007499694824, "global_step": 561618, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0265238285064697, "global_step": 561619, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0842270851135254, "global_step": 561620, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9943619966506958, "global_step": 561621, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0567312240600586, "global_step": 561622, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.005915641784668, "global_step": 561623, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9483025074005127, "global_step": 561624, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0513839721679688, "global_step": 561625, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9918198585510254, "global_step": 561626, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9540208578109741, "global_step": 561627, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0459022521972656, "global_step": 561628, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0074944496154785, "global_step": 561629, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1116747856140137, "global_step": 561630, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.010169506072998, "global_step": 561631, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.081144094467163, "global_step": 561632, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.014444589614868, "global_step": 561633, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9454131126403809, "global_step": 561634, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.13608717918396, "global_step": 561635, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9866629838943481, "global_step": 561636, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0988340377807617, "global_step": 561637, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.978365421295166, "global_step": 561638, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9369114637374878, "global_step": 561639, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0318305492401123, "global_step": 561640, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.000185489654541, "global_step": 561641, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0190277099609375, "global_step": 561642, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.007326126098633, "global_step": 561643, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.00400710105896, "global_step": 561644, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9872621297836304, "global_step": 561645, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.057541608810425, "global_step": 561646, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.913205862045288, "global_step": 561647, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0655856132507324, "global_step": 561648, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9337528944015503, "global_step": 561649, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9666736125946045, "global_step": 561650, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1058926582336426, "global_step": 561651, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0235109329223633, "global_step": 561652, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0554358959198, "global_step": 561653, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0013232231140137, "global_step": 561654, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.080430746078491, "global_step": 561655, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0522115230560303, "global_step": 561656, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.971268892288208, "global_step": 561657, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0104572772979736, "global_step": 561658, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.040933847427368, "global_step": 561659, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.029869556427002, "global_step": 561660, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0184385776519775, "global_step": 561661, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0240187644958496, "global_step": 561662, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0218350887298584, "global_step": 561663, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.065417766571045, "global_step": 561664, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.108409881591797, "global_step": 561665, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.125964641571045, "global_step": 561666, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0553271770477295, "global_step": 561667, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.064005136489868, "global_step": 561668, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0058958530426025, "global_step": 561669, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0775840282440186, "global_step": 561670, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.016282320022583, "global_step": 561671, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.024181842803955, "global_step": 561672, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.06526255607605, "global_step": 561673, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.117048501968384, "global_step": 561674, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.951220154762268, "global_step": 561675, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.8831559419631958, "global_step": 561676, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.024848461151123, "global_step": 561677, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0905556678771973, "global_step": 561678, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0132405757904053, "global_step": 561679, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.005857229232788, "global_step": 561680, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.019467830657959, "global_step": 561681, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0589356422424316, "global_step": 561682, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0524144172668457, "global_step": 561683, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.035740375518799, "global_step": 561684, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.007493495941162, "global_step": 561685, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.097954273223877, "global_step": 561686, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.02117657661438, "global_step": 561687, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0446436405181885, "global_step": 561688, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9959291219711304, "global_step": 561689, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9850293397903442, "global_step": 561690, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.006417751312256, "global_step": 561691, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.057893753051758, "global_step": 561692, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.005531072616577, "global_step": 561693, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0644288063049316, "global_step": 561694, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.000575304031372, "global_step": 561695, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.084411859512329, "global_step": 561696, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9963921308517456, "global_step": 561697, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0345585346221924, "global_step": 561698, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.000478982925415, "global_step": 561699, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0006654262542725, "global_step": 561700, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9024277925491333, "global_step": 561701, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.00087571144104, "global_step": 561702, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0030956268310547, "global_step": 561703, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0432796478271484, "global_step": 561704, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.057267665863037, "global_step": 561705, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.035656452178955, "global_step": 561706, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0314841270446777, "global_step": 561707, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.010077953338623, "global_step": 561708, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9614291191101074, "global_step": 561709, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0245816707611084, "global_step": 561710, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0704221725463867, "global_step": 561711, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9968575239181519, "global_step": 561712, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.057292938232422, "global_step": 561713, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0014781951904297, "global_step": 561714, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9967365264892578, "global_step": 561715, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0140466690063477, "global_step": 561716, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0011322498321533, "global_step": 561717, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.021476984024048, "global_step": 561718, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9753674268722534, "global_step": 561719, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0500388145446777, "global_step": 561720, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9548448324203491, "global_step": 561721, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.033557415008545, "global_step": 561722, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0517680644989014, "global_step": 561723, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9938822984695435, "global_step": 561724, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1379024982452393, "global_step": 561725, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0420897006988525, "global_step": 561726, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9606505632400513, "global_step": 561727, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0180721282958984, "global_step": 561728, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9880937337875366, "global_step": 561729, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0534772872924805, "global_step": 561730, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9611576795578003, "global_step": 561731, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0615100860595703, "global_step": 561732, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.06146240234375, "global_step": 561733, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1509366035461426, "global_step": 561734, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.040741443634033, "global_step": 561735, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.09647798538208, "global_step": 561736, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.052568197250366, "global_step": 561737, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.023524522781372, "global_step": 561738, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.043686866760254, "global_step": 561739, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0538618564605713, "global_step": 561740, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0851120948791504, "global_step": 561741, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.098113536834717, "global_step": 561742, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9578626155853271, "global_step": 561743, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0491199493408203, "global_step": 561744, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.113692283630371, "global_step": 561745, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0001461505889893, "global_step": 561746, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0341079235076904, "global_step": 561747, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.038316011428833, "global_step": 561748, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.055219888687134, "global_step": 561749, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0748989582061768, "global_step": 561750, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0008182525634766, "global_step": 561751, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0153539180755615, "global_step": 561752, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9945226907730103, "global_step": 561753, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.018240213394165, "global_step": 561754, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1136603355407715, "global_step": 561755, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.082193613052368, "global_step": 561756, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1336047649383545, "global_step": 561757, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.051835060119629, "global_step": 561758, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.028925657272339, "global_step": 561759, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.017266273498535, "global_step": 561760, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9706971645355225, "global_step": 561761, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.051393985748291, "global_step": 561762, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0154523849487305, "global_step": 561763, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9575108289718628, "global_step": 561764, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0174460411071777, "global_step": 561765, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.065174102783203, "global_step": 561766, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1117751598358154, "global_step": 561767, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0586695671081543, "global_step": 561768, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0948879718780518, "global_step": 561769, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.987056851387024, "global_step": 561770, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.066091299057007, "global_step": 561771, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0538442134857178, "global_step": 561772, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.018451452255249, "global_step": 561773, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.059455394744873, "global_step": 561774, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9923986196517944, "global_step": 561775, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9892284870147705, "global_step": 561776, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.071197748184204, "global_step": 561777, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.026052713394165, "global_step": 561778, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.020901918411255, "global_step": 561779, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0131266117095947, "global_step": 561780, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9857569932937622, "global_step": 561781, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.061432361602783, "global_step": 561782, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0733072757720947, "global_step": 561783, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0527548789978027, "global_step": 561784, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.041378974914551, "global_step": 561785, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1592142581939697, "global_step": 561786, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0771772861480713, "global_step": 561787, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0076208114624023, "global_step": 561788, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1015870571136475, "global_step": 561789, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.047520875930786, "global_step": 561790, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9690823554992676, "global_step": 561791, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.07068133354187, "global_step": 561792, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9301170110702515, "global_step": 561793, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0978777408599854, "global_step": 561794, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.112186908721924, "global_step": 561795, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.039111614227295, "global_step": 561796, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0791208744049072, "global_step": 561797, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9960962533950806, "global_step": 561798, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0602285861968994, "global_step": 561799, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9928332567214966, "global_step": 561800, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0903093814849854, "global_step": 561801, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0546021461486816, "global_step": 561802, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0343379974365234, "global_step": 561803, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.027381658554077, "global_step": 561804, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.022587299346924, "global_step": 561805, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9645888805389404, "global_step": 561806, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0511929988861084, "global_step": 561807, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0270538330078125, "global_step": 561808, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0781474113464355, "global_step": 561809, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9932280778884888, "global_step": 561810, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.041637897491455, "global_step": 561811, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1099510192871094, "global_step": 561812, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9640108346939087, "global_step": 561813, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0368728637695312, "global_step": 561814, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.962674856185913, "global_step": 561815, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.042536973953247, "global_step": 561816, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.090398073196411, "global_step": 561817, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.043861150741577, "global_step": 561818, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0461318492889404, "global_step": 561819, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.017251968383789, "global_step": 561820, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0194859504699707, "global_step": 561821, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.008460283279419, "global_step": 561822, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.925516963005066, "global_step": 561823, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.058089017868042, "global_step": 561824, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9336711168289185, "global_step": 561825, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0246472358703613, "global_step": 561826, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9198603630065918, "global_step": 561827, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0237057209014893, "global_step": 561828, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.8968453407287598, "global_step": 561829, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.147096872329712, "global_step": 561830, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.135204792022705, "global_step": 561831, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.013167142868042, "global_step": 561832, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0952069759368896, "global_step": 561833, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9959344863891602, "global_step": 561834, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0965802669525146, "global_step": 561835, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.036337375640869, "global_step": 561836, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9817235469818115, "global_step": 561837, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9974910020828247, "global_step": 561838, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1394903659820557, "global_step": 561839, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.014798164367676, "global_step": 561840, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0625510215759277, "global_step": 561841, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.956964135169983, "global_step": 561842, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.035325765609741, "global_step": 561843, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0611376762390137, "global_step": 561844, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9691225290298462, "global_step": 561845, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.063920021057129, "global_step": 561846, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9446922540664673, "global_step": 561847, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0341506004333496, "global_step": 561848, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0249409675598145, "global_step": 561849, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.010786294937134, "global_step": 561850, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9614455699920654, "global_step": 561851, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.072979211807251, "global_step": 561852, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9367464780807495, "global_step": 561853, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0542964935302734, "global_step": 561854, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.033076047897339, "global_step": 561855, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0220446586608887, "global_step": 561856, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9908242225646973, "global_step": 561857, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0390076637268066, "global_step": 561858, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.039318084716797, "global_step": 561859, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1219570636749268, "global_step": 561860, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9456545114517212, "global_step": 561861, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1001577377319336, "global_step": 561862, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0380334854125977, "global_step": 561863, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.019500255584717, "global_step": 561864, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0664432048797607, "global_step": 561865, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0450050830841064, "global_step": 561866, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0467374324798584, "global_step": 561867, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0526814460754395, "global_step": 561868, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0304131507873535, "global_step": 561869, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.041620969772339, "global_step": 561870, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1114935874938965, "global_step": 561871, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.071204900741577, "global_step": 561872, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0143332481384277, "global_step": 561873, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0560553073883057, "global_step": 561874, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0285844802856445, "global_step": 561875, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.072157144546509, "global_step": 561876, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0869414806365967, "global_step": 561877, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.004326820373535, "global_step": 561878, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9797660112380981, "global_step": 561879, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.02681827545166, "global_step": 561880, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.055450916290283, "global_step": 561881, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9685802459716797, "global_step": 561882, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0307776927948, "global_step": 561883, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9941939115524292, "global_step": 561884, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9879741668701172, "global_step": 561885, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9977943897247314, "global_step": 561886, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.032869577407837, "global_step": 561887, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.123284101486206, "global_step": 561888, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.8862249851226807, "global_step": 561889, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0065977573394775, "global_step": 561890, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0776164531707764, "global_step": 561891, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.081476926803589, "global_step": 561892, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9805889129638672, "global_step": 561893, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.992606520652771, "global_step": 561894, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.059232473373413, "global_step": 561895, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0132193565368652, "global_step": 561896, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0032577514648438, "global_step": 561897, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0225677490234375, "global_step": 561898, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.8991621732711792, "global_step": 561899, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.021756887435913, "global_step": 561900, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.002272605895996, "global_step": 561901, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0899550914764404, "global_step": 561902, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0538697242736816, "global_step": 561903, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0712168216705322, "global_step": 561904, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0020992755889893, "global_step": 561905, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.041189670562744, "global_step": 561906, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9562197923660278, "global_step": 561907, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.986482858657837, "global_step": 561908, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0128934383392334, "global_step": 561909, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.021466016769409, "global_step": 561910, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9725489616394043, "global_step": 561911, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.009211540222168, "global_step": 561912, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.069159507751465, "global_step": 561913, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0719916820526123, "global_step": 561914, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.980588674545288, "global_step": 561915, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.091428279876709, "global_step": 561916, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0293490886688232, "global_step": 561917, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9863224029541016, "global_step": 561918, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0395352840423584, "global_step": 561919, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1275367736816406, "global_step": 561920, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0124404430389404, "global_step": 561921, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0074405670166016, "global_step": 561922, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.061707019805908, "global_step": 561923, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.060786485671997, "global_step": 561924, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0130269527435303, "global_step": 561925, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.05466365814209, "global_step": 561926, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.009173631668091, "global_step": 561927, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.065589427947998, "global_step": 561928, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.000025749206543, "global_step": 561929, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0611772537231445, "global_step": 561930, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9844156503677368, "global_step": 561931, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.044356346130371, "global_step": 561932, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.102313995361328, "global_step": 561933, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0153470039367676, "global_step": 561934, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9552001953125, "global_step": 561935, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0504846572875977, "global_step": 561936, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9835609197616577, "global_step": 561937, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.975105881690979, "global_step": 561938, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.079813241958618, "global_step": 561939, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.062021017074585, "global_step": 561940, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0049757957458496, "global_step": 561941, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0439181327819824, "global_step": 561942, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.040766477584839, "global_step": 561943, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.054370403289795, "global_step": 561944, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0434277057647705, "global_step": 561945, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9970539808273315, "global_step": 561946, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.030858039855957, "global_step": 561947, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0370423793792725, "global_step": 561948, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1281063556671143, "global_step": 561949, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9809871912002563, "global_step": 561950, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0531115531921387, "global_step": 561951, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0484752655029297, "global_step": 561952, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9462890625, "global_step": 561953, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0084359645843506, "global_step": 561954, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0148186683654785, "global_step": 561955, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.080538749694824, "global_step": 561956, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.017707109451294, "global_step": 561957, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9476492404937744, "global_step": 561958, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0633206367492676, "global_step": 561959, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0152673721313477, "global_step": 561960, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.025397300720215, "global_step": 561961, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0019516944885254, "global_step": 561962, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0069732666015625, "global_step": 561963, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.000047206878662, "global_step": 561964, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0753986835479736, "global_step": 561965, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0332906246185303, "global_step": 561966, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.016921281814575, "global_step": 561967, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.023560047149658, "global_step": 561968, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.02221417427063, "global_step": 561969, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0700292587280273, "global_step": 561970, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9746177196502686, "global_step": 561971, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9839742183685303, "global_step": 561972, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9694112539291382, "global_step": 561973, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0161352157592773, "global_step": 561974, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.966497778892517, "global_step": 561975, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.030390501022339, "global_step": 561976, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9615941047668457, "global_step": 561977, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.032762050628662, "global_step": 561978, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0551652908325195, "global_step": 561979, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.985446572303772, "global_step": 561980, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.046142578125, "global_step": 561981, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0127193927764893, "global_step": 561982, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0354363918304443, "global_step": 561983, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.996529221534729, "global_step": 561984, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0785069465637207, "global_step": 561985, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0256354808807373, "global_step": 561986, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0186004638671875, "global_step": 561987, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9439184665679932, "global_step": 561988, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0474777221679688, "global_step": 561989, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.097985029220581, "global_step": 561990, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.997301697731018, "global_step": 561991, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9880255460739136, "global_step": 561992, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0511691570281982, "global_step": 561993, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9324939250946045, "global_step": 561994, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.015139102935791, "global_step": 561995, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0843446254730225, "global_step": 561996, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.965584397315979, "global_step": 561997, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9821826219558716, "global_step": 561998, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0338377952575684, "global_step": 561999, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0565025806427, "global_step": 562000, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.015827178955078, "global_step": 562001, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.05976939201355, "global_step": 562002, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0587477684020996, "global_step": 562003, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9796088933944702, "global_step": 562004, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9625154733657837, "global_step": 562005, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9978665113449097, "global_step": 562006, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0052597522735596, "global_step": 562007, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.046438217163086, "global_step": 562008, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.016550302505493, "global_step": 562009, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.004891872406006, "global_step": 562010, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0103297233581543, "global_step": 562011, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9785895347595215, "global_step": 562012, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0126779079437256, "global_step": 562013, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0071969032287598, "global_step": 562014, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.090766668319702, "global_step": 562015, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.00580096244812, "global_step": 562016, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1045236587524414, "global_step": 562017, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0643224716186523, "global_step": 562018, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.010383367538452, "global_step": 562019, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.053083658218384, "global_step": 562020, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0717873573303223, "global_step": 562021, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.053788185119629, "global_step": 562022, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.108639717102051, "global_step": 562023, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0302915573120117, "global_step": 562024, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0973753929138184, "global_step": 562025, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0839717388153076, "global_step": 562026, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.06115460395813, "global_step": 562027, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.95011305809021, "global_step": 562028, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9972128868103027, "global_step": 562029, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.066253662109375, "global_step": 562030, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9863779544830322, "global_step": 562031, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0358095169067383, "global_step": 562032, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.998593807220459, "global_step": 562033, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0958151817321777, "global_step": 562034, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0136241912841797, "global_step": 562035, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.16227126121521, "global_step": 562036, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0092711448669434, "global_step": 562037, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9855036735534668, "global_step": 562038, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9628052711486816, "global_step": 562039, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9392478466033936, "global_step": 562040, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0207231044769287, "global_step": 562041, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.017808198928833, "global_step": 562042, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9670377969741821, "global_step": 562043, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0448825359344482, "global_step": 562044, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0274603366851807, "global_step": 562045, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1153249740600586, "global_step": 562046, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0258121490478516, "global_step": 562047, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9977017641067505, "global_step": 562048, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0047712326049805, "global_step": 562049, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0295159816741943, "global_step": 562050, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.074007272720337, "global_step": 562051, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.118705987930298, "global_step": 562052, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9841058254241943, "global_step": 562053, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.109412431716919, "global_step": 562054, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.006464958190918, "global_step": 562055, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0373175144195557, "global_step": 562056, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0991528034210205, "global_step": 562057, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.059239387512207, "global_step": 562058, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9798157215118408, "global_step": 562059, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1303017139434814, "global_step": 562060, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.021372079849243, "global_step": 562061, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9539663791656494, "global_step": 562062, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9526093006134033, "global_step": 562063, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0384693145751953, "global_step": 562064, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0314974784851074, "global_step": 562065, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.100968360900879, "global_step": 562066, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9974548816680908, "global_step": 562067, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0296568870544434, "global_step": 562068, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0523979663848877, "global_step": 562069, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.071052312850952, "global_step": 562070, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0577921867370605, "global_step": 562071, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.98452627658844, "global_step": 562072, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.020310878753662, "global_step": 562073, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9861661195755005, "global_step": 562074, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.025569438934326, "global_step": 562075, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0387723445892334, "global_step": 562076, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1395342350006104, "global_step": 562077, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0728304386138916, "global_step": 562078, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.995345950126648, "global_step": 562079, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0222067832946777, "global_step": 562080, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0737297534942627, "global_step": 562081, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.138714551925659, "global_step": 562082, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9905664920806885, "global_step": 562083, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0141046047210693, "global_step": 562084, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.010960817337036, "global_step": 562085, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0777735710144043, "global_step": 562086, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0660388469696045, "global_step": 562087, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.8939738273620605, "global_step": 562088, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0582683086395264, "global_step": 562089, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.035562038421631, "global_step": 562090, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.922634482383728, "global_step": 562091, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0757429599761963, "global_step": 562092, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.041382074356079, "global_step": 562093, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9917746782302856, "global_step": 562094, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0522079467773438, "global_step": 562095, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1323459148406982, "global_step": 562096, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.040496587753296, "global_step": 562097, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0215463638305664, "global_step": 562098, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0232293605804443, "global_step": 562099, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.016998529434204, "global_step": 562100, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0632071495056152, "global_step": 562101, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9706608057022095, "global_step": 562102, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0586447715759277, "global_step": 562103, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0136730670928955, "global_step": 562104, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0885651111602783, "global_step": 562105, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0929832458496094, "global_step": 562106, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.031620740890503, "global_step": 562107, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.053981065750122, "global_step": 562108, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.066783905029297, "global_step": 562109, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0329418182373047, "global_step": 562110, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0349438190460205, "global_step": 562111, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1141164302825928, "global_step": 562112, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.999295711517334, "global_step": 562113, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0252461433410645, "global_step": 562114, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0819637775421143, "global_step": 562115, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.128873586654663, "global_step": 562116, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9810506105422974, "global_step": 562117, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9705464839935303, "global_step": 562118, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0432116985321045, "global_step": 562119, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9662233591079712, "global_step": 562120, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9724286794662476, "global_step": 562121, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.042754888534546, "global_step": 562122, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9568703174591064, "global_step": 562123, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.983596682548523, "global_step": 562124, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.014420509338379, "global_step": 562125, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9711556434631348, "global_step": 562126, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1226143836975098, "global_step": 562127, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0500199794769287, "global_step": 562128, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0123450756073, "global_step": 562129, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.074904203414917, "global_step": 562130, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0116498470306396, "global_step": 562131, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0962092876434326, "global_step": 562132, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.01814341545105, "global_step": 562133, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9644052982330322, "global_step": 562134, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0142080783843994, "global_step": 562135, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.955214023590088, "global_step": 562136, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0250449180603027, "global_step": 562137, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0391900539398193, "global_step": 562138, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9728482961654663, "global_step": 562139, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.079939126968384, "global_step": 562140, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.1308164596557617, "global_step": 562141, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.9145363569259644, "global_step": 562142, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0700459480285645, "global_step": 562143, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0420825481414795, "global_step": 562144, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0449588298797607, "global_step": 562145, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0193989276885986, "global_step": 562146, "epoch": 929, "lr": 5e-05}
{"train_loss": 1.999443769454956, "global_step": 562147, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0559659004211426, "global_step": 562148, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0028562545776367, "global_step": 562149, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.106226921081543, "global_step": 562150, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0579686164855957, "global_step": 562151, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.027094841003418, "global_step": 562152, "epoch": 929, "lr": 5e-05}
{"train_loss": 2.0829498767852783, "global_step": 562153, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0723764896392822, "global_step": 562154, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.05315899848938, "global_step": 562155, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.03528094291687, "global_step": 562156, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0084378719329834, "global_step": 562157, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9638735055923462, "global_step": 562158, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0405611991882324, "global_step": 562159, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.936660885810852, "global_step": 562160, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9739497900009155, "global_step": 562161, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0041794776916504, "global_step": 562162, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9818313121795654, "global_step": 562163, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.083739757537842, "global_step": 562164, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0221011638641357, "global_step": 562165, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.049245834350586, "global_step": 562166, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9760701656341553, "global_step": 562167, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0808017253875732, "global_step": 562168, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0091915130615234, "global_step": 562169, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9597183465957642, "global_step": 562170, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0581183433532715, "global_step": 562171, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9637936353683472, "global_step": 562172, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0136919021606445, "global_step": 562173, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.021702766418457, "global_step": 562174, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9116578102111816, "global_step": 562175, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0430266857147217, "global_step": 562176, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9219319820404053, "global_step": 562177, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9768123626708984, "global_step": 562178, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9817776679992676, "global_step": 562179, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.988440990447998, "global_step": 562180, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.960722804069519, "global_step": 562181, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0399842262268066, "global_step": 562182, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9181040525436401, "global_step": 562183, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1274607181549072, "global_step": 562184, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0202929973602295, "global_step": 562185, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0003457069396973, "global_step": 562186, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.033545970916748, "global_step": 562187, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0010435581207275, "global_step": 562188, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.986686110496521, "global_step": 562189, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0244345664978027, "global_step": 562190, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9584490060806274, "global_step": 562191, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9847266674041748, "global_step": 562192, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0037827491760254, "global_step": 562193, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0632059574127197, "global_step": 562194, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1080472469329834, "global_step": 562195, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0172066688537598, "global_step": 562196, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.017261266708374, "global_step": 562197, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9728246927261353, "global_step": 562198, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.951654076576233, "global_step": 562199, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.052077293395996, "global_step": 562200, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0783793926239014, "global_step": 562201, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.031986951828003, "global_step": 562202, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.092183828353882, "global_step": 562203, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0365452766418457, "global_step": 562204, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9387511014938354, "global_step": 562205, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.072690486907959, "global_step": 562206, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9473246335983276, "global_step": 562207, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0594801902770996, "global_step": 562208, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0103578567504883, "global_step": 562209, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.000377893447876, "global_step": 562210, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.00578236579895, "global_step": 562211, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9353938102722168, "global_step": 562212, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.955786943435669, "global_step": 562213, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.06558895111084, "global_step": 562214, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9888440370559692, "global_step": 562215, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9497178792953491, "global_step": 562216, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.110191822052002, "global_step": 562217, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0858805179595947, "global_step": 562218, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.063093662261963, "global_step": 562219, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0210180282592773, "global_step": 562220, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9929546117782593, "global_step": 562221, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9413790702819824, "global_step": 562222, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0310885906219482, "global_step": 562223, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0919876098632812, "global_step": 562224, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9706193208694458, "global_step": 562225, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9340503215789795, "global_step": 562226, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9773082733154297, "global_step": 562227, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0712602138519287, "global_step": 562228, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9619909524917603, "global_step": 562229, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9614784717559814, "global_step": 562230, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.031661033630371, "global_step": 562231, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0020601749420166, "global_step": 562232, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9434196949005127, "global_step": 562233, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.016740083694458, "global_step": 562234, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.073215961456299, "global_step": 562235, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.030527114868164, "global_step": 562236, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.05912184715271, "global_step": 562237, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9542567729949951, "global_step": 562238, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.125864267349243, "global_step": 562239, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9913957118988037, "global_step": 562240, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0599632263183594, "global_step": 562241, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9511600732803345, "global_step": 562242, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.996952772140503, "global_step": 562243, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.062180519104004, "global_step": 562244, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.969411015510559, "global_step": 562245, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.996061086654663, "global_step": 562246, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.081667423248291, "global_step": 562247, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0695080757141113, "global_step": 562248, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0337772369384766, "global_step": 562249, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.208040237426758, "global_step": 562250, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0479774475097656, "global_step": 562251, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.941112995147705, "global_step": 562252, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.045097589492798, "global_step": 562253, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.940134882926941, "global_step": 562254, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0434353351593018, "global_step": 562255, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.116307497024536, "global_step": 562256, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9900376796722412, "global_step": 562257, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0749714374542236, "global_step": 562258, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1241507530212402, "global_step": 562259, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9920684099197388, "global_step": 562260, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0347940921783447, "global_step": 562261, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.961303472518921, "global_step": 562262, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.954493522644043, "global_step": 562263, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9744914770126343, "global_step": 562264, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.004159450531006, "global_step": 562265, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0182347297668457, "global_step": 562266, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0476808547973633, "global_step": 562267, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9993786811828613, "global_step": 562268, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9797405004501343, "global_step": 562269, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0514309406280518, "global_step": 562270, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.086785316467285, "global_step": 562271, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0228919982910156, "global_step": 562272, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0616748332977295, "global_step": 562273, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.082411050796509, "global_step": 562274, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9736568927764893, "global_step": 562275, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0202770233154297, "global_step": 562276, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.057091474533081, "global_step": 562277, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9721120595932007, "global_step": 562278, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.00929856300354, "global_step": 562279, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9492555856704712, "global_step": 562280, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.055717945098877, "global_step": 562281, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0516598224639893, "global_step": 562282, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0086939334869385, "global_step": 562283, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.124023199081421, "global_step": 562284, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0994086265563965, "global_step": 562285, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.010451555252075, "global_step": 562286, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.053285598754883, "global_step": 562287, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.042215347290039, "global_step": 562288, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.019132614135742, "global_step": 562289, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.984394907951355, "global_step": 562290, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0475399494171143, "global_step": 562291, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0694143772125244, "global_step": 562292, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.049783945083618, "global_step": 562293, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.044264554977417, "global_step": 562294, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9872615337371826, "global_step": 562295, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1299924850463867, "global_step": 562296, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.108471393585205, "global_step": 562297, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0853989124298096, "global_step": 562298, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0113983154296875, "global_step": 562299, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.054525375366211, "global_step": 562300, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.994866967201233, "global_step": 562301, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.023388147354126, "global_step": 562302, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9806933403015137, "global_step": 562303, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0298147201538086, "global_step": 562304, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0227866172790527, "global_step": 562305, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0024731159210205, "global_step": 562306, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.027069091796875, "global_step": 562307, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.939479112625122, "global_step": 562308, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.059743881225586, "global_step": 562309, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.034313201904297, "global_step": 562310, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.925744891166687, "global_step": 562311, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9826701879501343, "global_step": 562312, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0409977436065674, "global_step": 562313, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0811030864715576, "global_step": 562314, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0321462154388428, "global_step": 562315, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1388626098632812, "global_step": 562316, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0377840995788574, "global_step": 562317, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.012542247772217, "global_step": 562318, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0506412982940674, "global_step": 562319, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.01084566116333, "global_step": 562320, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0989837646484375, "global_step": 562321, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.063962936401367, "global_step": 562322, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0233218669891357, "global_step": 562323, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.067624807357788, "global_step": 562324, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.101750373840332, "global_step": 562325, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1021809577941895, "global_step": 562326, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9961901903152466, "global_step": 562327, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9823685884475708, "global_step": 562328, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0583901405334473, "global_step": 562329, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.053354263305664, "global_step": 562330, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0916552543640137, "global_step": 562331, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9924458265304565, "global_step": 562332, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0041186809539795, "global_step": 562333, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9688529968261719, "global_step": 562334, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9810307025909424, "global_step": 562335, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9106111526489258, "global_step": 562336, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.046785354614258, "global_step": 562337, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9528741836547852, "global_step": 562338, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9762850999832153, "global_step": 562339, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0291261672973633, "global_step": 562340, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1064698696136475, "global_step": 562341, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0292727947235107, "global_step": 562342, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.958872675895691, "global_step": 562343, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.033507823944092, "global_step": 562344, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0023982524871826, "global_step": 562345, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0446770191192627, "global_step": 562346, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0842444896698, "global_step": 562347, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9762476682662964, "global_step": 562348, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9383699893951416, "global_step": 562349, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.020190954208374, "global_step": 562350, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.008103609085083, "global_step": 562351, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0378832817077637, "global_step": 562352, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.991754412651062, "global_step": 562353, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0489258766174316, "global_step": 562354, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0838212966918945, "global_step": 562355, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.949174165725708, "global_step": 562356, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0321097373962402, "global_step": 562357, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.089865207672119, "global_step": 562358, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9891011714935303, "global_step": 562359, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.037794351577759, "global_step": 562360, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0352306365966797, "global_step": 562361, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.039752244949341, "global_step": 562362, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0678961277008057, "global_step": 562363, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9874632358551025, "global_step": 562364, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0718276500701904, "global_step": 562365, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.045092821121216, "global_step": 562366, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9967501163482666, "global_step": 562367, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0273375511169434, "global_step": 562368, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.974036693572998, "global_step": 562369, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.028679847717285, "global_step": 562370, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.059164524078369, "global_step": 562371, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9263179302215576, "global_step": 562372, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.060504674911499, "global_step": 562373, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0142886638641357, "global_step": 562374, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9466403722763062, "global_step": 562375, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0149364471435547, "global_step": 562376, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0211904048919678, "global_step": 562377, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.004025459289551, "global_step": 562378, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0027849674224854, "global_step": 562379, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0408713817596436, "global_step": 562380, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.002950429916382, "global_step": 562381, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0163094997406006, "global_step": 562382, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0291011333465576, "global_step": 562383, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9386882781982422, "global_step": 562384, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0186984539031982, "global_step": 562385, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0121941566467285, "global_step": 562386, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9710807800292969, "global_step": 562387, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.042487859725952, "global_step": 562388, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9984815120697021, "global_step": 562389, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0808265209198, "global_step": 562390, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0376815795898438, "global_step": 562391, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0320651531219482, "global_step": 562392, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.060173988342285, "global_step": 562393, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.993067979812622, "global_step": 562394, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9915794134140015, "global_step": 562395, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.096158981323242, "global_step": 562396, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.996833086013794, "global_step": 562397, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.002211093902588, "global_step": 562398, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0395939350128174, "global_step": 562399, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.944211483001709, "global_step": 562400, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.061570167541504, "global_step": 562401, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9725193977355957, "global_step": 562402, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.98817777633667, "global_step": 562403, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.006173610687256, "global_step": 562404, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0219197273254395, "global_step": 562405, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0036396980285645, "global_step": 562406, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9695976972579956, "global_step": 562407, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9292434453964233, "global_step": 562408, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9904226064682007, "global_step": 562409, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.029116630554199, "global_step": 562410, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.013615608215332, "global_step": 562411, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.025911808013916, "global_step": 562412, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9943753480911255, "global_step": 562413, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.032468318939209, "global_step": 562414, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9525659084320068, "global_step": 562415, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.029878854751587, "global_step": 562416, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.97515070438385, "global_step": 562417, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9915040731430054, "global_step": 562418, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.060126543045044, "global_step": 562419, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0447933673858643, "global_step": 562420, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0070505142211914, "global_step": 562421, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.090055465698242, "global_step": 562422, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0476887226104736, "global_step": 562423, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0732414722442627, "global_step": 562424, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9858616590499878, "global_step": 562425, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.993018627166748, "global_step": 562426, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0232248306274414, "global_step": 562427, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9580026865005493, "global_step": 562428, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0643584728240967, "global_step": 562429, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.98123300075531, "global_step": 562430, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.911571741104126, "global_step": 562431, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.034818172454834, "global_step": 562432, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9717859029769897, "global_step": 562433, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0157673358917236, "global_step": 562434, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9366371631622314, "global_step": 562435, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9731128215789795, "global_step": 562436, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.127147674560547, "global_step": 562437, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9538472890853882, "global_step": 562438, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.947058081626892, "global_step": 562439, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.084047555923462, "global_step": 562440, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0522570610046387, "global_step": 562441, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.039091110229492, "global_step": 562442, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.013362407684326, "global_step": 562443, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9775859117507935, "global_step": 562444, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0604841709136963, "global_step": 562445, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0622973442077637, "global_step": 562446, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.113921880722046, "global_step": 562447, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9817500114440918, "global_step": 562448, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0321788787841797, "global_step": 562449, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.992522954940796, "global_step": 562450, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0234813690185547, "global_step": 562451, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.973221778869629, "global_step": 562452, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.020622968673706, "global_step": 562453, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.001675844192505, "global_step": 562454, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.032054901123047, "global_step": 562455, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.013482093811035, "global_step": 562456, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9728753566741943, "global_step": 562457, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0222346782684326, "global_step": 562458, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.8891875743865967, "global_step": 562459, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.022303581237793, "global_step": 562460, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0623815059661865, "global_step": 562461, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.98715078830719, "global_step": 562462, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.020554542541504, "global_step": 562463, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0326082706451416, "global_step": 562464, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0396766662597656, "global_step": 562465, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0115773677825928, "global_step": 562466, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.100308418273926, "global_step": 562467, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0186755657196045, "global_step": 562468, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9797863960266113, "global_step": 562469, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.024585247039795, "global_step": 562470, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9427878856658936, "global_step": 562471, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.017305850982666, "global_step": 562472, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0175857543945312, "global_step": 562473, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9857089519500732, "global_step": 562474, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.002870798110962, "global_step": 562475, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0580151081085205, "global_step": 562476, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9928871393203735, "global_step": 562477, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.03090238571167, "global_step": 562478, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.044865369796753, "global_step": 562479, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.103537082672119, "global_step": 562480, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.917120099067688, "global_step": 562481, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.037386417388916, "global_step": 562482, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0650315284729004, "global_step": 562483, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0041050910949707, "global_step": 562484, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0079751014709473, "global_step": 562485, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0279810428619385, "global_step": 562486, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.093019723892212, "global_step": 562487, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9749878644943237, "global_step": 562488, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.052759885787964, "global_step": 562489, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9709938764572144, "global_step": 562490, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9808740615844727, "global_step": 562491, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.127047300338745, "global_step": 562492, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.028359889984131, "global_step": 562493, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0423293113708496, "global_step": 562494, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0004618167877197, "global_step": 562495, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0567467212677, "global_step": 562496, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0248117446899414, "global_step": 562497, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0487823486328125, "global_step": 562498, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0322322845458984, "global_step": 562499, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9752720594406128, "global_step": 562500, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.134983539581299, "global_step": 562501, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.02217698097229, "global_step": 562502, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0900299549102783, "global_step": 562503, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.061695098876953, "global_step": 562504, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0245068073272705, "global_step": 562505, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9849843978881836, "global_step": 562506, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.987726092338562, "global_step": 562507, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1029410362243652, "global_step": 562508, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0311317443847656, "global_step": 562509, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.013474941253662, "global_step": 562510, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.006889581680298, "global_step": 562511, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9921931028366089, "global_step": 562512, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9862154722213745, "global_step": 562513, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0869171619415283, "global_step": 562514, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1261720657348633, "global_step": 562515, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9762622117996216, "global_step": 562516, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0886974334716797, "global_step": 562517, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1189422607421875, "global_step": 562518, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0656402111053467, "global_step": 562519, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0239968299865723, "global_step": 562520, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9866375923156738, "global_step": 562521, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.050025463104248, "global_step": 562522, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.019273519515991, "global_step": 562523, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0281734466552734, "global_step": 562524, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.969996690750122, "global_step": 562525, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9955567121505737, "global_step": 562526, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9761908054351807, "global_step": 562527, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.050889492034912, "global_step": 562528, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0477848052978516, "global_step": 562529, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.962878704071045, "global_step": 562530, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0396735668182373, "global_step": 562531, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.12017822265625, "global_step": 562532, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1368227005004883, "global_step": 562533, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0845038890838623, "global_step": 562534, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.005531072616577, "global_step": 562535, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.003441333770752, "global_step": 562536, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9536954164505005, "global_step": 562537, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0901169776916504, "global_step": 562538, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0894272327423096, "global_step": 562539, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0026049613952637, "global_step": 562540, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0193674564361572, "global_step": 562541, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0063135623931885, "global_step": 562542, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0417637825012207, "global_step": 562543, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9935585260391235, "global_step": 562544, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.007356882095337, "global_step": 562545, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.112074136734009, "global_step": 562546, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0525996685028076, "global_step": 562547, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.018221616744995, "global_step": 562548, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.067655563354492, "global_step": 562549, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0674638748168945, "global_step": 562550, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9928582906723022, "global_step": 562551, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0004377365112305, "global_step": 562552, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0428757667541504, "global_step": 562553, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.117201328277588, "global_step": 562554, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0237178802490234, "global_step": 562555, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.061522960662842, "global_step": 562556, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0357236862182617, "global_step": 562557, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.086228132247925, "global_step": 562558, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9972833395004272, "global_step": 562559, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.046694278717041, "global_step": 562560, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.020249128341675, "global_step": 562561, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.002166748046875, "global_step": 562562, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.969942331314087, "global_step": 562563, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.069742202758789, "global_step": 562564, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.088674545288086, "global_step": 562565, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.072079658508301, "global_step": 562566, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.059805154800415, "global_step": 562567, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.992646336555481, "global_step": 562568, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0922372341156006, "global_step": 562569, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9759149551391602, "global_step": 562570, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0463333129882812, "global_step": 562571, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0404598712921143, "global_step": 562572, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0619935989379883, "global_step": 562573, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9917209148406982, "global_step": 562574, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0260543823242188, "global_step": 562575, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0585293769836426, "global_step": 562576, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0616157054901123, "global_step": 562577, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9847936630249023, "global_step": 562578, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.028298854827881, "global_step": 562579, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0357611179351807, "global_step": 562580, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0275354385375977, "global_step": 562581, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0338516235351562, "global_step": 562582, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.032528877258301, "global_step": 562583, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0889170169830322, "global_step": 562584, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.052257776260376, "global_step": 562585, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1127572059631348, "global_step": 562586, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.015422821044922, "global_step": 562587, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0546844005584717, "global_step": 562588, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0685219764709473, "global_step": 562589, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1058509349823, "global_step": 562590, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.052555799484253, "global_step": 562591, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0650038719177246, "global_step": 562592, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9509779214859009, "global_step": 562593, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.04017972946167, "global_step": 562594, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.029324531555176, "global_step": 562595, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.02586030960083, "global_step": 562596, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9923640489578247, "global_step": 562597, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.070605993270874, "global_step": 562598, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0195772647857666, "global_step": 562599, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9993853569030762, "global_step": 562600, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9971740245819092, "global_step": 562601, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9689109325408936, "global_step": 562602, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0873820781707764, "global_step": 562603, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9597046375274658, "global_step": 562604, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9928224086761475, "global_step": 562605, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9935026168823242, "global_step": 562606, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.036623477935791, "global_step": 562607, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.073561906814575, "global_step": 562608, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.055344343185425, "global_step": 562609, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0270702838897705, "global_step": 562610, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9952691793441772, "global_step": 562611, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0833399295806885, "global_step": 562612, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.030975580215454, "global_step": 562613, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0552127361297607, "global_step": 562614, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.018195867538452, "global_step": 562615, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.925719976425171, "global_step": 562616, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0670034885406494, "global_step": 562617, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.037947177886963, "global_step": 562618, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0191774368286133, "global_step": 562619, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9916318655014038, "global_step": 562620, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0357258319854736, "global_step": 562621, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.119013786315918, "global_step": 562622, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.058464288711548, "global_step": 562623, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9430757761001587, "global_step": 562624, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0569357872009277, "global_step": 562625, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.007537364959717, "global_step": 562626, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0043134689331055, "global_step": 562627, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.06317138671875, "global_step": 562628, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9949992895126343, "global_step": 562629, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.915170669555664, "global_step": 562630, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.073267698287964, "global_step": 562631, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.017171859741211, "global_step": 562632, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.005314826965332, "global_step": 562633, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9913824796676636, "global_step": 562634, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9136477708816528, "global_step": 562635, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.095639228820801, "global_step": 562636, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0729496479034424, "global_step": 562637, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9200451374053955, "global_step": 562638, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0225720405578613, "global_step": 562639, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.023081064224243, "global_step": 562640, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9852879047393799, "global_step": 562641, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0845882892608643, "global_step": 562642, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1130642890930176, "global_step": 562643, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9896043539047241, "global_step": 562644, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9582226276397705, "global_step": 562645, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0607738494873047, "global_step": 562646, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.134734869003296, "global_step": 562647, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.114436149597168, "global_step": 562648, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.075178384780884, "global_step": 562649, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0037426948547363, "global_step": 562650, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.970030665397644, "global_step": 562651, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.046351432800293, "global_step": 562652, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.10271954536438, "global_step": 562653, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9861924648284912, "global_step": 562654, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0055947303771973, "global_step": 562655, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.016738176345825, "global_step": 562656, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.037283182144165, "global_step": 562657, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.970201015472412, "global_step": 562658, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9972487688064575, "global_step": 562659, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0706939697265625, "global_step": 562660, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.026813268661499, "global_step": 562661, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9960612058639526, "global_step": 562662, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1167526245117188, "global_step": 562663, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0701711177825928, "global_step": 562664, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0006306171417236, "global_step": 562665, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1175270080566406, "global_step": 562666, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0782337188720703, "global_step": 562667, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0355188846588135, "global_step": 562668, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9994823932647705, "global_step": 562669, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0470337867736816, "global_step": 562670, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1110570430755615, "global_step": 562671, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1445047855377197, "global_step": 562672, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.113168478012085, "global_step": 562673, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0576975345611572, "global_step": 562674, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.05899977684021, "global_step": 562675, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.046454906463623, "global_step": 562676, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.09763765335083, "global_step": 562677, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9226226806640625, "global_step": 562678, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0310025215148926, "global_step": 562679, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9799396991729736, "global_step": 562680, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.987642526626587, "global_step": 562681, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0234992504119873, "global_step": 562682, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.05881404876709, "global_step": 562683, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0679025650024414, "global_step": 562684, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.982122540473938, "global_step": 562685, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9899096488952637, "global_step": 562686, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0665390491485596, "global_step": 562687, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0057809352874756, "global_step": 562688, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0664799213409424, "global_step": 562689, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0325264930725098, "global_step": 562690, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0583088397979736, "global_step": 562691, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.004305362701416, "global_step": 562692, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.009779214859009, "global_step": 562693, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.05241060256958, "global_step": 562694, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.041264295578003, "global_step": 562695, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.042271852493286, "global_step": 562696, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.984692931175232, "global_step": 562697, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0222036838531494, "global_step": 562698, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.09194016456604, "global_step": 562699, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.012972831726074, "global_step": 562700, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.099834680557251, "global_step": 562701, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0880823135375977, "global_step": 562702, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0257039070129395, "global_step": 562703, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.011679172515869, "global_step": 562704, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.993809700012207, "global_step": 562705, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.052119016647339, "global_step": 562706, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0293123722076416, "global_step": 562707, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9963300228118896, "global_step": 562708, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.047464609146118, "global_step": 562709, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.00504994392395, "global_step": 562710, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1476821899414062, "global_step": 562711, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9978410005569458, "global_step": 562712, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0274221897125244, "global_step": 562713, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.057741641998291, "global_step": 562714, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0342109203338623, "global_step": 562715, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.115931987762451, "global_step": 562716, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0658199787139893, "global_step": 562717, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1020100116729736, "global_step": 562718, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0947835445404053, "global_step": 562719, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0522964000701904, "global_step": 562720, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0032224655151367, "global_step": 562721, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0360865592956543, "global_step": 562722, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0215418338775635, "global_step": 562723, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.043592929840088, "global_step": 562724, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.079486846923828, "global_step": 562725, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.031024217605591, "global_step": 562726, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9599133729934692, "global_step": 562727, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9362170696258545, "global_step": 562728, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.002203941345215, "global_step": 562729, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9654399156570435, "global_step": 562730, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.955355167388916, "global_step": 562731, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.072324752807617, "global_step": 562732, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9733840227127075, "global_step": 562733, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.044740915298462, "global_step": 562734, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9243462085723877, "global_step": 562735, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.969201922416687, "global_step": 562736, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.00304913520813, "global_step": 562737, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9915721416473389, "global_step": 562738, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0476436614990234, "global_step": 562739, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0590336322784424, "global_step": 562740, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.039663314819336, "global_step": 562741, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.098590612411499, "global_step": 562742, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0077569484710693, "global_step": 562743, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9895306825637817, "global_step": 562744, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.99708890914917, "global_step": 562745, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0414676666259766, "global_step": 562746, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9637384414672852, "global_step": 562747, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0165982246398926, "global_step": 562748, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0511281490325928, "global_step": 562749, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.052680730819702, "global_step": 562750, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.071551561355591, "global_step": 562751, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.044842481613159, "global_step": 562752, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.038247585296631, "global_step": 562753, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0583879947662354, "global_step": 562754, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.066575050354004, "global_step": 562755, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0824477672576904, "global_step": 562756, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.062025547027588, "global_step": 562757, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0167319774627686, "global_step": 562758, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0335896015167236, "global_step": 562759, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9520045518875122, "global_step": 562760, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0333046913146973, "global_step": 562761, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9364537000656128, "global_step": 562762, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9876010417938232, "global_step": 562763, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0777575969696045, "global_step": 562764, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0194928646087646, "global_step": 562765, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9681916236877441, "global_step": 562766, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.012498617172241, "global_step": 562767, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9740203619003296, "global_step": 562768, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.99819016456604, "global_step": 562769, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9851222038269043, "global_step": 562770, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9763635396957397, "global_step": 562771, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0395145416259766, "global_step": 562772, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0812647342681885, "global_step": 562773, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0242552757263184, "global_step": 562774, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.080479145050049, "global_step": 562775, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.100611925125122, "global_step": 562776, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0032496452331543, "global_step": 562777, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0697107315063477, "global_step": 562778, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.057647466659546, "global_step": 562779, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0391695499420166, "global_step": 562780, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9848462343215942, "global_step": 562781, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9544808864593506, "global_step": 562782, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.078988552093506, "global_step": 562783, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.981343150138855, "global_step": 562784, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.020690679550171, "global_step": 562785, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.056650400161743, "global_step": 562786, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.054802179336548, "global_step": 562787, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.147254228591919, "global_step": 562788, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0315256118774414, "global_step": 562789, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9627537727355957, "global_step": 562790, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1510274410247803, "global_step": 562791, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9911571741104126, "global_step": 562792, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.998256802558899, "global_step": 562793, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0380852222442627, "global_step": 562794, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.026285171508789, "global_step": 562795, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9679100513458252, "global_step": 562796, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9966952800750732, "global_step": 562797, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.038018226623535, "global_step": 562798, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9934730529785156, "global_step": 562799, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0097689628601074, "global_step": 562800, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0083305835723877, "global_step": 562801, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0433223247528076, "global_step": 562802, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9985604286193848, "global_step": 562803, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0067734718322754, "global_step": 562804, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9485344886779785, "global_step": 562805, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0103204250335693, "global_step": 562806, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9864349365234375, "global_step": 562807, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0172295570373535, "global_step": 562808, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.059410572052002, "global_step": 562809, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.058112859725952, "global_step": 562810, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9911667108535767, "global_step": 562811, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.030991315841675, "global_step": 562812, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9803706407546997, "global_step": 562813, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0842692852020264, "global_step": 562814, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.033870220184326, "global_step": 562815, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.149050712585449, "global_step": 562816, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9980626106262207, "global_step": 562817, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.11405086517334, "global_step": 562818, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.051056385040283, "global_step": 562819, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.004528284072876, "global_step": 562820, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0764968395233154, "global_step": 562821, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9928605556488037, "global_step": 562822, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0609424114227295, "global_step": 562823, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9818089008331299, "global_step": 562824, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0233421325683594, "global_step": 562825, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.974165916442871, "global_step": 562826, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9872496128082275, "global_step": 562827, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0644750595092773, "global_step": 562828, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9607480764389038, "global_step": 562829, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.017612934112549, "global_step": 562830, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.074129104614258, "global_step": 562831, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.062502145767212, "global_step": 562832, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.017030954360962, "global_step": 562833, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.019300937652588, "global_step": 562834, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0645835399627686, "global_step": 562835, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.028977870941162, "global_step": 562836, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0450878143310547, "global_step": 562837, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.026216983795166, "global_step": 562838, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1185340881347656, "global_step": 562839, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.008141279220581, "global_step": 562840, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0540943145751953, "global_step": 562841, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.09547758102417, "global_step": 562842, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0418710708618164, "global_step": 562843, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0131654739379883, "global_step": 562844, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0930049419403076, "global_step": 562845, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9855983257293701, "global_step": 562846, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.022874593734741, "global_step": 562847, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.034045696258545, "global_step": 562848, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9844317436218262, "global_step": 562849, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.033567190170288, "global_step": 562850, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0759453773498535, "global_step": 562851, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9876514673233032, "global_step": 562852, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0896108150482178, "global_step": 562853, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9988982677459717, "global_step": 562854, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0237982273101807, "global_step": 562855, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0165693759918213, "global_step": 562856, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.090510606765747, "global_step": 562857, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0091400146484375, "global_step": 562858, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.062865734100342, "global_step": 562859, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9879169464111328, "global_step": 562860, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1126651763916016, "global_step": 562861, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.063722848892212, "global_step": 562862, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9589214324951172, "global_step": 562863, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0603880882263184, "global_step": 562864, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0340068340301514, "global_step": 562865, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1886587142944336, "global_step": 562866, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0249531269073486, "global_step": 562867, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9750884771347046, "global_step": 562868, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.046478509902954, "global_step": 562869, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.049147367477417, "global_step": 562870, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0889320373535156, "global_step": 562871, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1203575134277344, "global_step": 562872, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1147422790527344, "global_step": 562873, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.039088487625122, "global_step": 562874, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.998589277267456, "global_step": 562875, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1062257289886475, "global_step": 562876, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9721429347991943, "global_step": 562877, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.05354642868042, "global_step": 562878, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.017301082611084, "global_step": 562879, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9534010887145996, "global_step": 562880, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.988386869430542, "global_step": 562881, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.123213052749634, "global_step": 562882, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1291773319244385, "global_step": 562883, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0197858810424805, "global_step": 562884, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0012130737304688, "global_step": 562885, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0500946044921875, "global_step": 562886, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.970804214477539, "global_step": 562887, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.98170006275177, "global_step": 562888, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0376007556915283, "global_step": 562889, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.043548345565796, "global_step": 562890, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0693442821502686, "global_step": 562891, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.012284755706787, "global_step": 562892, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9660059213638306, "global_step": 562893, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.136523723602295, "global_step": 562894, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9951531887054443, "global_step": 562895, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0202159881591797, "global_step": 562896, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0466721057891846, "global_step": 562897, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.009244918823242, "global_step": 562898, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0269358158111572, "global_step": 562899, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.027684211730957, "global_step": 562900, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0847363471984863, "global_step": 562901, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0275344848632812, "global_step": 562902, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0027530193328857, "global_step": 562903, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0705626010894775, "global_step": 562904, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0698068141937256, "global_step": 562905, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0630884170532227, "global_step": 562906, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0863184928894043, "global_step": 562907, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.036752700805664, "global_step": 562908, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.025294065475464, "global_step": 562909, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9967535734176636, "global_step": 562910, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.013598680496216, "global_step": 562911, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9809492826461792, "global_step": 562912, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0727405548095703, "global_step": 562913, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0289316177368164, "global_step": 562914, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9179584980010986, "global_step": 562915, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.044954776763916, "global_step": 562916, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9600646495819092, "global_step": 562917, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0902488231658936, "global_step": 562918, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0658090114593506, "global_step": 562919, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1376121044158936, "global_step": 562920, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0984549522399902, "global_step": 562921, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.092860698699951, "global_step": 562922, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9923231601715088, "global_step": 562923, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.986647367477417, "global_step": 562924, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9379825592041016, "global_step": 562925, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.010145664215088, "global_step": 562926, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0239040851593018, "global_step": 562927, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.022425889968872, "global_step": 562928, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0421242713928223, "global_step": 562929, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.103605031967163, "global_step": 562930, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.068352699279785, "global_step": 562931, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0810625553131104, "global_step": 562932, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9437823295593262, "global_step": 562933, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0318312644958496, "global_step": 562934, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9738155603408813, "global_step": 562935, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9305353164672852, "global_step": 562936, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9997609853744507, "global_step": 562937, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.08528470993042, "global_step": 562938, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0313613414764404, "global_step": 562939, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.069398880004883, "global_step": 562940, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.002296209335327, "global_step": 562941, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0440173149108887, "global_step": 562942, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.113163948059082, "global_step": 562943, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0280303955078125, "global_step": 562944, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.960046648979187, "global_step": 562945, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.059796094894409, "global_step": 562946, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9485608339309692, "global_step": 562947, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0549705028533936, "global_step": 562948, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0059874057769775, "global_step": 562949, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0126023292541504, "global_step": 562950, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0272834300994873, "global_step": 562951, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0528852939605713, "global_step": 562952, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1738946437835693, "global_step": 562953, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.036029577255249, "global_step": 562954, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.010209321975708, "global_step": 562955, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0665831565856934, "global_step": 562956, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.105642557144165, "global_step": 562957, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.003614664077759, "global_step": 562958, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0307624340057373, "global_step": 562959, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0423600673675537, "global_step": 562960, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9672377109527588, "global_step": 562961, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9742330312728882, "global_step": 562962, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9362895488739014, "global_step": 562963, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.015806198120117, "global_step": 562964, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1193811893463135, "global_step": 562965, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9984182119369507, "global_step": 562966, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1355371475219727, "global_step": 562967, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.051825761795044, "global_step": 562968, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0215983390808105, "global_step": 562969, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0856895446777344, "global_step": 562970, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0814149379730225, "global_step": 562971, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0735583305358887, "global_step": 562972, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.011115312576294, "global_step": 562973, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.06314754486084, "global_step": 562974, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9741491079330444, "global_step": 562975, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0948219299316406, "global_step": 562976, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0426955223083496, "global_step": 562977, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9916335344314575, "global_step": 562978, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0766067504882812, "global_step": 562979, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.034593343734741, "global_step": 562980, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0227158069610596, "global_step": 562981, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.014955997467041, "global_step": 562982, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0107789039611816, "global_step": 562983, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.015721082687378, "global_step": 562984, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.000750780105591, "global_step": 562985, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9194014072418213, "global_step": 562986, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.003936529159546, "global_step": 562987, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.039006233215332, "global_step": 562988, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9628204107284546, "global_step": 562989, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.006469488143921, "global_step": 562990, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0031237602233887, "global_step": 562991, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0313024520874023, "global_step": 562992, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.092273473739624, "global_step": 562993, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0252604484558105, "global_step": 562994, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.007344961166382, "global_step": 562995, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.939393401145935, "global_step": 562996, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0804214477539062, "global_step": 562997, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0299484729766846, "global_step": 562998, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0661511421203613, "global_step": 562999, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0256917476654053, "global_step": 563000, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9727271795272827, "global_step": 563001, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9512157440185547, "global_step": 563002, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9778245687484741, "global_step": 563003, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0097732543945312, "global_step": 563004, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.160429000854492, "global_step": 563005, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0673670768737793, "global_step": 563006, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9736918210983276, "global_step": 563007, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.051225423812866, "global_step": 563008, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.097017526626587, "global_step": 563009, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9837075471878052, "global_step": 563010, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1203315258026123, "global_step": 563011, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9829094409942627, "global_step": 563012, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0194814205169678, "global_step": 563013, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0469553470611572, "global_step": 563014, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.030719518661499, "global_step": 563015, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0483736991882324, "global_step": 563016, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.058288097381592, "global_step": 563017, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9707436561584473, "global_step": 563018, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9712225198745728, "global_step": 563019, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9590437412261963, "global_step": 563020, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9755572080612183, "global_step": 563021, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9822187423706055, "global_step": 563022, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.020843982696533, "global_step": 563023, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.055396795272827, "global_step": 563024, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9895581007003784, "global_step": 563025, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.133317232131958, "global_step": 563026, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.94420325756073, "global_step": 563027, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9961634874343872, "global_step": 563028, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9597514867782593, "global_step": 563029, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9648746252059937, "global_step": 563030, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.092390775680542, "global_step": 563031, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9493099451065063, "global_step": 563032, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.006673812866211, "global_step": 563033, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9697012901306152, "global_step": 563034, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9694209098815918, "global_step": 563035, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.955378770828247, "global_step": 563036, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0327718257904053, "global_step": 563037, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9059633016586304, "global_step": 563038, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.010615825653076, "global_step": 563039, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.109042167663574, "global_step": 563040, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0644712448120117, "global_step": 563041, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9474421739578247, "global_step": 563042, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0689871311187744, "global_step": 563043, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.054049491882324, "global_step": 563044, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.063368558883667, "global_step": 563045, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9412610530853271, "global_step": 563046, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.04180908203125, "global_step": 563047, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1332688331604004, "global_step": 563048, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0658462047576904, "global_step": 563049, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0480854511260986, "global_step": 563050, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.027937412261963, "global_step": 563051, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.017160177230835, "global_step": 563052, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.073218822479248, "global_step": 563053, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0161077976226807, "global_step": 563054, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.049821615219116, "global_step": 563055, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.06489634513855, "global_step": 563056, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9662511348724365, "global_step": 563057, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.013671875, "global_step": 563058, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0655596256256104, "global_step": 563059, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0167360305786133, "global_step": 563060, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.108670711517334, "global_step": 563061, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9762849807739258, "global_step": 563062, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0127787590026855, "global_step": 563063, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.024122476577759, "global_step": 563064, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0387606620788574, "global_step": 563065, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0458059310913086, "global_step": 563066, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.079766273498535, "global_step": 563067, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9498920440673828, "global_step": 563068, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.8775323629379272, "global_step": 563069, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0199203491210938, "global_step": 563070, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.980098843574524, "global_step": 563071, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0306406021118164, "global_step": 563072, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.932247281074524, "global_step": 563073, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1069796085357666, "global_step": 563074, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.022723913192749, "global_step": 563075, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.063387632369995, "global_step": 563076, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.045114755630493, "global_step": 563077, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0502614974975586, "global_step": 563078, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9723044633865356, "global_step": 563079, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0711991786956787, "global_step": 563080, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0176801681518555, "global_step": 563081, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.010108470916748, "global_step": 563082, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0746042728424072, "global_step": 563083, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.056887626647949, "global_step": 563084, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0438332557678223, "global_step": 563085, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1072750091552734, "global_step": 563086, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.2025630474090576, "global_step": 563087, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0185763835906982, "global_step": 563088, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.095935821533203, "global_step": 563089, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.1043567657470703, "global_step": 563090, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.166020393371582, "global_step": 563091, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0323245525360107, "global_step": 563092, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0469467639923096, "global_step": 563093, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0029425621032715, "global_step": 563094, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9007327556610107, "global_step": 563095, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.035737991333008, "global_step": 563096, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0927209854125977, "global_step": 563097, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.073948621749878, "global_step": 563098, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0226056575775146, "global_step": 563099, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0017881393432617, "global_step": 563100, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0973708629608154, "global_step": 563101, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0122432708740234, "global_step": 563102, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.032191514968872, "global_step": 563103, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9413585662841797, "global_step": 563104, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.125235080718994, "global_step": 563105, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0317041873931885, "global_step": 563106, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.000006675720215, "global_step": 563107, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0275425910949707, "global_step": 563108, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0192275047302246, "global_step": 563109, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0293829441070557, "global_step": 563110, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9199241399765015, "global_step": 563111, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0375709533691406, "global_step": 563112, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0750579833984375, "global_step": 563113, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0040173530578613, "global_step": 563114, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9487149715423584, "global_step": 563115, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9550328254699707, "global_step": 563116, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.013950824737549, "global_step": 563117, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9806655645370483, "global_step": 563118, "epoch": 930, "lr": 5e-05}
{"train_loss": 1.9524248838424683, "global_step": 563119, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0055747032165527, "global_step": 563120, "epoch": 930, "lr": 5e-05}
{"train_loss": 2.0269150733947754, "global_step": 563121, "epoch": 930, "lr": 5e-05, "val_loss": 5.764522552490234, "test_reconst_mse": 0.07388350367546082}
{"train_loss": 2.042044162750244, "global_step": 563122, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.010355234146118, "global_step": 563123, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.065886974334717, "global_step": 563124, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.971442461013794, "global_step": 563125, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0486676692962646, "global_step": 563126, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0576627254486084, "global_step": 563127, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0126049518585205, "global_step": 563128, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.953908920288086, "global_step": 563129, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9892559051513672, "global_step": 563130, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9675801992416382, "global_step": 563131, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.895208716392517, "global_step": 563132, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.051154136657715, "global_step": 563133, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0649220943450928, "global_step": 563134, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9987242221832275, "global_step": 563135, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0250635147094727, "global_step": 563136, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0096848011016846, "global_step": 563137, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9955066442489624, "global_step": 563138, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0234272480010986, "global_step": 563139, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.067408561706543, "global_step": 563140, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.049185037612915, "global_step": 563141, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0095880031585693, "global_step": 563142, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.034536123275757, "global_step": 563143, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.8957977294921875, "global_step": 563144, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1090400218963623, "global_step": 563145, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.028878688812256, "global_step": 563146, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0171613693237305, "global_step": 563147, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0334842205047607, "global_step": 563148, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9959901571273804, "global_step": 563149, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9706239700317383, "global_step": 563150, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9492582082748413, "global_step": 563151, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.929690957069397, "global_step": 563152, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9589686393737793, "global_step": 563153, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9914770126342773, "global_step": 563154, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0273444652557373, "global_step": 563155, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.002448320388794, "global_step": 563156, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.994688630104065, "global_step": 563157, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0210132598876953, "global_step": 563158, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.95709228515625, "global_step": 563159, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0036780834198, "global_step": 563160, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9385735988616943, "global_step": 563161, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.16121506690979, "global_step": 563162, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0095536708831787, "global_step": 563163, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9664709568023682, "global_step": 563164, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0394363403320312, "global_step": 563165, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.004477024078369, "global_step": 563166, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0043883323669434, "global_step": 563167, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0660998821258545, "global_step": 563168, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1221542358398438, "global_step": 563169, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.989585280418396, "global_step": 563170, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0489914417266846, "global_step": 563171, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9583320617675781, "global_step": 563172, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0299713611602783, "global_step": 563173, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9996341466903687, "global_step": 563174, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.064305067062378, "global_step": 563175, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.047752618789673, "global_step": 563176, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.052816152572632, "global_step": 563177, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.952046275138855, "global_step": 563178, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0253758430480957, "global_step": 563179, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0512075424194336, "global_step": 563180, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9879469871520996, "global_step": 563181, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9919776916503906, "global_step": 563182, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.984783411026001, "global_step": 563183, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.108646869659424, "global_step": 563184, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9637213945388794, "global_step": 563185, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0023162364959717, "global_step": 563186, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0744998455047607, "global_step": 563187, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.012561082839966, "global_step": 563188, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.017599105834961, "global_step": 563189, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.999863624572754, "global_step": 563190, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0038039684295654, "global_step": 563191, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0276291370391846, "global_step": 563192, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9767110347747803, "global_step": 563193, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.058231830596924, "global_step": 563194, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.047574043273926, "global_step": 563195, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.972890019416809, "global_step": 563196, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0469934940338135, "global_step": 563197, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0013692378997803, "global_step": 563198, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9545023441314697, "global_step": 563199, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.964025855064392, "global_step": 563200, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0376293659210205, "global_step": 563201, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.02815318107605, "global_step": 563202, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.123453140258789, "global_step": 563203, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0851545333862305, "global_step": 563204, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.117706775665283, "global_step": 563205, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0137076377868652, "global_step": 563206, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.038553237915039, "global_step": 563207, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0085318088531494, "global_step": 563208, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0117926597595215, "global_step": 563209, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9764676094055176, "global_step": 563210, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9979496002197266, "global_step": 563211, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0623064041137695, "global_step": 563212, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.036992073059082, "global_step": 563213, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0645365715026855, "global_step": 563214, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.077918291091919, "global_step": 563215, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0090370178222656, "global_step": 563216, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0128817558288574, "global_step": 563217, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.007850170135498, "global_step": 563218, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9944318532943726, "global_step": 563219, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.015587091445923, "global_step": 563220, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.099315881729126, "global_step": 563221, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0184123516082764, "global_step": 563222, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0116889476776123, "global_step": 563223, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0974667072296143, "global_step": 563224, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.014673948287964, "global_step": 563225, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.976613163948059, "global_step": 563226, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9603551626205444, "global_step": 563227, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9341347217559814, "global_step": 563228, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.01016902923584, "global_step": 563229, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0345699787139893, "global_step": 563230, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0630152225494385, "global_step": 563231, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9778215885162354, "global_step": 563232, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9542938470840454, "global_step": 563233, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.036004066467285, "global_step": 563234, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.065455436706543, "global_step": 563235, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.077741861343384, "global_step": 563236, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.025174379348755, "global_step": 563237, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.952687382698059, "global_step": 563238, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1162116527557373, "global_step": 563239, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9884536266326904, "global_step": 563240, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9795465469360352, "global_step": 563241, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0956931114196777, "global_step": 563242, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9788419008255005, "global_step": 563243, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.091339111328125, "global_step": 563244, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0549848079681396, "global_step": 563245, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9697904586791992, "global_step": 563246, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.147169351577759, "global_step": 563247, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0883662700653076, "global_step": 563248, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0282063484191895, "global_step": 563249, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0593554973602295, "global_step": 563250, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9697977304458618, "global_step": 563251, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0571677684783936, "global_step": 563252, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0668954849243164, "global_step": 563253, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0107476711273193, "global_step": 563254, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.108809232711792, "global_step": 563255, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9671317338943481, "global_step": 563256, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9924731254577637, "global_step": 563257, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.039031505584717, "global_step": 563258, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0381240844726562, "global_step": 563259, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0184133052825928, "global_step": 563260, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9959337711334229, "global_step": 563261, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9738612174987793, "global_step": 563262, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0290870666503906, "global_step": 563263, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.040754556655884, "global_step": 563264, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9734773635864258, "global_step": 563265, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0250203609466553, "global_step": 563266, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.026498556137085, "global_step": 563267, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.017378568649292, "global_step": 563268, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9268088340759277, "global_step": 563269, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0728867053985596, "global_step": 563270, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.022632360458374, "global_step": 563271, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0061120986938477, "global_step": 563272, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0062808990478516, "global_step": 563273, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.984492301940918, "global_step": 563274, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9609910249710083, "global_step": 563275, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.053992748260498, "global_step": 563276, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0574018955230713, "global_step": 563277, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.982053518295288, "global_step": 563278, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0528461933135986, "global_step": 563279, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9865760803222656, "global_step": 563280, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0460212230682373, "global_step": 563281, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.999177098274231, "global_step": 563282, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.981651782989502, "global_step": 563283, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.007652521133423, "global_step": 563284, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0767831802368164, "global_step": 563285, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0438053607940674, "global_step": 563286, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.956394910812378, "global_step": 563287, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0441339015960693, "global_step": 563288, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0189292430877686, "global_step": 563289, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.036421537399292, "global_step": 563290, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9500747919082642, "global_step": 563291, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0144288539886475, "global_step": 563292, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9670729637145996, "global_step": 563293, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.978959560394287, "global_step": 563294, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0421407222747803, "global_step": 563295, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0112383365631104, "global_step": 563296, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.063687801361084, "global_step": 563297, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0773987770080566, "global_step": 563298, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0377867221832275, "global_step": 563299, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.03083872795105, "global_step": 563300, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9725346565246582, "global_step": 563301, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0332767963409424, "global_step": 563302, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.961275577545166, "global_step": 563303, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0238850116729736, "global_step": 563304, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0357024669647217, "global_step": 563305, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0915493965148926, "global_step": 563306, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0263729095458984, "global_step": 563307, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9632505178451538, "global_step": 563308, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.002352476119995, "global_step": 563309, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.993543267250061, "global_step": 563310, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0580897331237793, "global_step": 563311, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1025211811065674, "global_step": 563312, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.8898215293884277, "global_step": 563313, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9967780113220215, "global_step": 563314, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0237653255462646, "global_step": 563315, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9607113599777222, "global_step": 563316, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.13332462310791, "global_step": 563317, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.000300645828247, "global_step": 563318, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.954362154006958, "global_step": 563319, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.050119161605835, "global_step": 563320, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0401463508605957, "global_step": 563321, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.088881254196167, "global_step": 563322, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.875494122505188, "global_step": 563323, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9894150495529175, "global_step": 563324, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.8843063116073608, "global_step": 563325, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0641274452209473, "global_step": 563326, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.056847333908081, "global_step": 563327, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0351526737213135, "global_step": 563328, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.031914234161377, "global_step": 563329, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0350253582000732, "global_step": 563330, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1430764198303223, "global_step": 563331, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0143892765045166, "global_step": 563332, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9800314903259277, "global_step": 563333, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1332340240478516, "global_step": 563334, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.015747547149658, "global_step": 563335, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.056295871734619, "global_step": 563336, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0284206867218018, "global_step": 563337, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9359601736068726, "global_step": 563338, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9722894430160522, "global_step": 563339, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9424445629119873, "global_step": 563340, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0330324172973633, "global_step": 563341, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0666234493255615, "global_step": 563342, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.092742443084717, "global_step": 563343, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9974855184555054, "global_step": 563344, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.025117874145508, "global_step": 563345, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.997883677482605, "global_step": 563346, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0309600830078125, "global_step": 563347, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9129809141159058, "global_step": 563348, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0016515254974365, "global_step": 563349, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9086188077926636, "global_step": 563350, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0988686084747314, "global_step": 563351, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9804211854934692, "global_step": 563352, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.01952862739563, "global_step": 563353, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9589934349060059, "global_step": 563354, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.000140905380249, "global_step": 563355, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.022977352142334, "global_step": 563356, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0167179107666016, "global_step": 563357, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.13692045211792, "global_step": 563358, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1584279537200928, "global_step": 563359, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1345553398132324, "global_step": 563360, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0576915740966797, "global_step": 563361, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.066464900970459, "global_step": 563362, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.094083309173584, "global_step": 563363, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9895765781402588, "global_step": 563364, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9847533702850342, "global_step": 563365, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.025177001953125, "global_step": 563366, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0295751094818115, "global_step": 563367, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0181267261505127, "global_step": 563368, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0313544273376465, "global_step": 563369, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9907563924789429, "global_step": 563370, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9598084688186646, "global_step": 563371, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.01229190826416, "global_step": 563372, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.046029567718506, "global_step": 563373, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.001253366470337, "global_step": 563374, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.058115005493164, "global_step": 563375, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.09395170211792, "global_step": 563376, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9647026062011719, "global_step": 563377, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.057220458984375, "global_step": 563378, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.111567974090576, "global_step": 563379, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0243923664093018, "global_step": 563380, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.15175724029541, "global_step": 563381, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0175256729125977, "global_step": 563382, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.054608106613159, "global_step": 563383, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.077333450317383, "global_step": 563384, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.074484348297119, "global_step": 563385, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1315600872039795, "global_step": 563386, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0280613899230957, "global_step": 563387, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0139081478118896, "global_step": 563388, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.064181327819824, "global_step": 563389, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.998186469078064, "global_step": 563390, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9906461238861084, "global_step": 563391, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1528782844543457, "global_step": 563392, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9729005098342896, "global_step": 563393, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9567099809646606, "global_step": 563394, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.018706798553467, "global_step": 563395, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.00095796585083, "global_step": 563396, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9419035911560059, "global_step": 563397, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.034205436706543, "global_step": 563398, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1253163814544678, "global_step": 563399, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.989142894744873, "global_step": 563400, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.020430326461792, "global_step": 563401, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0561487674713135, "global_step": 563402, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.114297866821289, "global_step": 563403, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9479912519454956, "global_step": 563404, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1031811237335205, "global_step": 563405, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9314286708831787, "global_step": 563406, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9748231172561646, "global_step": 563407, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.972416639328003, "global_step": 563408, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9923746585845947, "global_step": 563409, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9748508930206299, "global_step": 563410, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9498578310012817, "global_step": 563411, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9887573719024658, "global_step": 563412, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0664167404174805, "global_step": 563413, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.997861385345459, "global_step": 563414, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9835659265518188, "global_step": 563415, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.012439012527466, "global_step": 563416, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.016012668609619, "global_step": 563417, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.995800495147705, "global_step": 563418, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9368950128555298, "global_step": 563419, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.01770281791687, "global_step": 563420, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.085268974304199, "global_step": 563421, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.036336898803711, "global_step": 563422, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9926462173461914, "global_step": 563423, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9932941198349, "global_step": 563424, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.064357280731201, "global_step": 563425, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9768785238265991, "global_step": 563426, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9919527769088745, "global_step": 563427, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.086482286453247, "global_step": 563428, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0214130878448486, "global_step": 563429, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.919081687927246, "global_step": 563430, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0674309730529785, "global_step": 563431, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.01523756980896, "global_step": 563432, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1262166500091553, "global_step": 563433, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.005523443222046, "global_step": 563434, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9796279668807983, "global_step": 563435, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.002613067626953, "global_step": 563436, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.028470754623413, "global_step": 563437, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.025907516479492, "global_step": 563438, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0043349266052246, "global_step": 563439, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0679008960723877, "global_step": 563440, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.117497682571411, "global_step": 563441, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.068204641342163, "global_step": 563442, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.989641785621643, "global_step": 563443, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9945147037506104, "global_step": 563444, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0197834968566895, "global_step": 563445, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.052281618118286, "global_step": 563446, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9980921745300293, "global_step": 563447, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.010845184326172, "global_step": 563448, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0482497215270996, "global_step": 563449, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.07033634185791, "global_step": 563450, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.029677629470825, "global_step": 563451, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0101206302642822, "global_step": 563452, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0748538970947266, "global_step": 563453, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.977993130683899, "global_step": 563454, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0366179943084717, "global_step": 563455, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0819973945617676, "global_step": 563456, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.080380439758301, "global_step": 563457, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0420236587524414, "global_step": 563458, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0849826335906982, "global_step": 563459, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0720534324645996, "global_step": 563460, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0637214183807373, "global_step": 563461, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.996510624885559, "global_step": 563462, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0600550174713135, "global_step": 563463, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9608818292617798, "global_step": 563464, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0442631244659424, "global_step": 563465, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.085949659347534, "global_step": 563466, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.050647735595703, "global_step": 563467, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9847404956817627, "global_step": 563468, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.073579788208008, "global_step": 563469, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.054297924041748, "global_step": 563470, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.036350727081299, "global_step": 563471, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9941496849060059, "global_step": 563472, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9913355112075806, "global_step": 563473, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.8934547901153564, "global_step": 563474, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9589321613311768, "global_step": 563475, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0315287113189697, "global_step": 563476, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.943289875984192, "global_step": 563477, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9466450214385986, "global_step": 563478, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.005127429962158, "global_step": 563479, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.036522626876831, "global_step": 563480, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0765836238861084, "global_step": 563481, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.011448621749878, "global_step": 563482, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0822997093200684, "global_step": 563483, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9505445957183838, "global_step": 563484, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0864596366882324, "global_step": 563485, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.059335947036743, "global_step": 563486, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0410380363464355, "global_step": 563487, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0325379371643066, "global_step": 563488, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9280366897583008, "global_step": 563489, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9686368703842163, "global_step": 563490, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.116823196411133, "global_step": 563491, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.075904607772827, "global_step": 563492, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.02311635017395, "global_step": 563493, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9422295093536377, "global_step": 563494, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1940810680389404, "global_step": 563495, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0974881649017334, "global_step": 563496, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0982017517089844, "global_step": 563497, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.013242483139038, "global_step": 563498, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.000675678253174, "global_step": 563499, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.098688840866089, "global_step": 563500, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1166512966156006, "global_step": 563501, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0109376907348633, "global_step": 563502, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0643303394317627, "global_step": 563503, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.99745512008667, "global_step": 563504, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0702121257781982, "global_step": 563505, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.968206524848938, "global_step": 563506, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0724236965179443, "global_step": 563507, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9943418502807617, "global_step": 563508, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.014641761779785, "global_step": 563509, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0320992469787598, "global_step": 563510, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.019136905670166, "global_step": 563511, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.037614345550537, "global_step": 563512, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.047980546951294, "global_step": 563513, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9368033409118652, "global_step": 563514, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0738184452056885, "global_step": 563515, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.049832582473755, "global_step": 563516, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.016400098800659, "global_step": 563517, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.007568597793579, "global_step": 563518, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9835366010665894, "global_step": 563519, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0522124767303467, "global_step": 563520, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.965882658958435, "global_step": 563521, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0348236560821533, "global_step": 563522, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1230568885803223, "global_step": 563523, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.080974578857422, "global_step": 563524, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9915432929992676, "global_step": 563525, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.032899856567383, "global_step": 563526, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0759811401367188, "global_step": 563527, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.057089328765869, "global_step": 563528, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.015475273132324, "global_step": 563529, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9644732475280762, "global_step": 563530, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0211167335510254, "global_step": 563531, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0485589504241943, "global_step": 563532, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0746140480041504, "global_step": 563533, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0809783935546875, "global_step": 563534, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.081101655960083, "global_step": 563535, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0488059520721436, "global_step": 563536, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.092712879180908, "global_step": 563537, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.057511806488037, "global_step": 563538, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9921680688858032, "global_step": 563539, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0591444969177246, "global_step": 563540, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0239717960357666, "global_step": 563541, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0551958084106445, "global_step": 563542, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.950130581855774, "global_step": 563543, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9397255182266235, "global_step": 563544, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.95299232006073, "global_step": 563545, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9558602571487427, "global_step": 563546, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9338109493255615, "global_step": 563547, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.014155626296997, "global_step": 563548, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0503365993499756, "global_step": 563549, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0089030265808105, "global_step": 563550, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0443832874298096, "global_step": 563551, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.101616144180298, "global_step": 563552, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0530343055725098, "global_step": 563553, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9648305177688599, "global_step": 563554, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0699524879455566, "global_step": 563555, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.053539514541626, "global_step": 563556, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0114572048187256, "global_step": 563557, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0234806537628174, "global_step": 563558, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9666539430618286, "global_step": 563559, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0341506004333496, "global_step": 563560, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9848201274871826, "global_step": 563561, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.124824047088623, "global_step": 563562, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.043928623199463, "global_step": 563563, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0749597549438477, "global_step": 563564, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.975993275642395, "global_step": 563565, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9996732473373413, "global_step": 563566, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0465292930603027, "global_step": 563567, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9684712886810303, "global_step": 563568, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0390279293060303, "global_step": 563569, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.035667896270752, "global_step": 563570, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.009620189666748, "global_step": 563571, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9783216714859009, "global_step": 563572, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0106780529022217, "global_step": 563573, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.041651487350464, "global_step": 563574, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.127420663833618, "global_step": 563575, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9661542177200317, "global_step": 563576, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9838074445724487, "global_step": 563577, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.027310848236084, "global_step": 563578, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.001896858215332, "global_step": 563579, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9412137269973755, "global_step": 563580, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.040468692779541, "global_step": 563581, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0861849784851074, "global_step": 563582, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.053276300430298, "global_step": 563583, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.037869930267334, "global_step": 563584, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0175211429595947, "global_step": 563585, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0396223068237305, "global_step": 563586, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0882792472839355, "global_step": 563587, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0760068893432617, "global_step": 563588, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0196597576141357, "global_step": 563589, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.096601724624634, "global_step": 563590, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.023686647415161, "global_step": 563591, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9897363185882568, "global_step": 563592, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.02665114402771, "global_step": 563593, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.91292405128479, "global_step": 563594, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.040126323699951, "global_step": 563595, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9668785333633423, "global_step": 563596, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.048696994781494, "global_step": 563597, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.994460105895996, "global_step": 563598, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.017578363418579, "global_step": 563599, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.976765751838684, "global_step": 563600, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.079422950744629, "global_step": 563601, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0569305419921875, "global_step": 563602, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0583086013793945, "global_step": 563603, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0150396823883057, "global_step": 563604, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9782562255859375, "global_step": 563605, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0485339164733887, "global_step": 563606, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.051494836807251, "global_step": 563607, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0002946853637695, "global_step": 563608, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0041520595550537, "global_step": 563609, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0730698108673096, "global_step": 563610, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.065678358078003, "global_step": 563611, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9686983823776245, "global_step": 563612, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.035694122314453, "global_step": 563613, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.022186756134033, "global_step": 563614, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.021921157836914, "global_step": 563615, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0277392864227295, "global_step": 563616, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0709517002105713, "global_step": 563617, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9680755138397217, "global_step": 563618, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0485241413116455, "global_step": 563619, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0762875080108643, "global_step": 563620, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.016641855239868, "global_step": 563621, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0738182067871094, "global_step": 563622, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.051588296890259, "global_step": 563623, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0521936416625977, "global_step": 563624, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.046496868133545, "global_step": 563625, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.105435371398926, "global_step": 563626, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9849600791931152, "global_step": 563627, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.07503080368042, "global_step": 563628, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0294432640075684, "global_step": 563629, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9881654977798462, "global_step": 563630, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.082838773727417, "global_step": 563631, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0545573234558105, "global_step": 563632, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.033784866333008, "global_step": 563633, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0205109119415283, "global_step": 563634, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9818732738494873, "global_step": 563635, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0300872325897217, "global_step": 563636, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.082980155944824, "global_step": 563637, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0234906673431396, "global_step": 563638, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.092104434967041, "global_step": 563639, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0462472438812256, "global_step": 563640, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.106753349304199, "global_step": 563641, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.048283338546753, "global_step": 563642, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.949920415878296, "global_step": 563643, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.054816246032715, "global_step": 563644, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.02117657661438, "global_step": 563645, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9985088109970093, "global_step": 563646, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0437264442443848, "global_step": 563647, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1026906967163086, "global_step": 563648, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.008678436279297, "global_step": 563649, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0787079334259033, "global_step": 563650, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.943691611289978, "global_step": 563651, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.002093553543091, "global_step": 563652, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.002061605453491, "global_step": 563653, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9878822565078735, "global_step": 563654, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9282519817352295, "global_step": 563655, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9274905920028687, "global_step": 563656, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9284433126449585, "global_step": 563657, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0237762928009033, "global_step": 563658, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.011223077774048, "global_step": 563659, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.041076183319092, "global_step": 563660, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9379101991653442, "global_step": 563661, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0908799171447754, "global_step": 563662, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0814402103424072, "global_step": 563663, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0829713344573975, "global_step": 563664, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.017075538635254, "global_step": 563665, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9471393823623657, "global_step": 563666, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9743009805679321, "global_step": 563667, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0258936882019043, "global_step": 563668, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0113673210144043, "global_step": 563669, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0796947479248047, "global_step": 563670, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0327365398406982, "global_step": 563671, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.051115036010742, "global_step": 563672, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.028205394744873, "global_step": 563673, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1062352657318115, "global_step": 563674, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9962904453277588, "global_step": 563675, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0884196758270264, "global_step": 563676, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0808961391448975, "global_step": 563677, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9782471656799316, "global_step": 563678, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.125934600830078, "global_step": 563679, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9066686630249023, "global_step": 563680, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.067432165145874, "global_step": 563681, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0889546871185303, "global_step": 563682, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9256904125213623, "global_step": 563683, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.150789499282837, "global_step": 563684, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0138309001922607, "global_step": 563685, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9919722080230713, "global_step": 563686, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0283827781677246, "global_step": 563687, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0249016284942627, "global_step": 563688, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9797452688217163, "global_step": 563689, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.007995367050171, "global_step": 563690, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.071075201034546, "global_step": 563691, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0732669830322266, "global_step": 563692, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.053781509399414, "global_step": 563693, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.025521755218506, "global_step": 563694, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.995578408241272, "global_step": 563695, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0207321643829346, "global_step": 563696, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0433435440063477, "global_step": 563697, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.074207305908203, "global_step": 563698, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9456249475479126, "global_step": 563699, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0003085136413574, "global_step": 563700, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0365400314331055, "global_step": 563701, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0941808223724365, "global_step": 563702, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.087040662765503, "global_step": 563703, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9263461828231812, "global_step": 563704, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.039585590362549, "global_step": 563705, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0952367782592773, "global_step": 563706, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1990087032318115, "global_step": 563707, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.011725425720215, "global_step": 563708, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.064138174057007, "global_step": 563709, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.045977830886841, "global_step": 563710, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.147157907485962, "global_step": 563711, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9851632118225098, "global_step": 563712, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0650391578674316, "global_step": 563713, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9792166948318481, "global_step": 563714, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9249627590179443, "global_step": 563715, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0573244094848633, "global_step": 563716, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.085629463195801, "global_step": 563717, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.083950996398926, "global_step": 563718, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0531046390533447, "global_step": 563719, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.088947296142578, "global_step": 563720, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1254374980926514, "global_step": 563721, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0455219745635986, "global_step": 563722, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0126986503601074, "global_step": 563723, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0849223136901855, "global_step": 563724, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9898028373718262, "global_step": 563725, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9844114780426025, "global_step": 563726, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0066041946411133, "global_step": 563727, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0552399158477783, "global_step": 563728, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0905513763427734, "global_step": 563729, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0642292499542236, "global_step": 563730, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.009220600128174, "global_step": 563731, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.94661283493042, "global_step": 563732, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.04168963432312, "global_step": 563733, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9903082847595215, "global_step": 563734, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.03798770904541, "global_step": 563735, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0771114826202393, "global_step": 563736, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9615389108657837, "global_step": 563737, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1405069828033447, "global_step": 563738, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.019624710083008, "global_step": 563739, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0452651977539062, "global_step": 563740, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.986656904220581, "global_step": 563741, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.07222843170166, "global_step": 563742, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0369770526885986, "global_step": 563743, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.073410749435425, "global_step": 563744, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0132250785827637, "global_step": 563745, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.990432858467102, "global_step": 563746, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9565259218215942, "global_step": 563747, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.091790199279785, "global_step": 563748, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.966346263885498, "global_step": 563749, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.141446590423584, "global_step": 563750, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9902616739273071, "global_step": 563751, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0060813426971436, "global_step": 563752, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.074355125427246, "global_step": 563753, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0275557041168213, "global_step": 563754, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0405473709106445, "global_step": 563755, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9567474126815796, "global_step": 563756, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9727938175201416, "global_step": 563757, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.008073329925537, "global_step": 563758, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.064574718475342, "global_step": 563759, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0430922508239746, "global_step": 563760, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.02878737449646, "global_step": 563761, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.029167413711548, "global_step": 563762, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0035247802734375, "global_step": 563763, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.998929738998413, "global_step": 563764, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.8960222005844116, "global_step": 563765, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.066784381866455, "global_step": 563766, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.035623550415039, "global_step": 563767, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9931153059005737, "global_step": 563768, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9871141910552979, "global_step": 563769, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1592025756835938, "global_step": 563770, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9204381704330444, "global_step": 563771, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.019434928894043, "global_step": 563772, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0000686645507812, "global_step": 563773, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0669376850128174, "global_step": 563774, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.995656967163086, "global_step": 563775, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9847173690795898, "global_step": 563776, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.048372983932495, "global_step": 563777, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.013169527053833, "global_step": 563778, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9463332891464233, "global_step": 563779, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0580270290374756, "global_step": 563780, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0683515071868896, "global_step": 563781, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.036064386367798, "global_step": 563782, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0845096111297607, "global_step": 563783, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.083592176437378, "global_step": 563784, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0710294246673584, "global_step": 563785, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.010467290878296, "global_step": 563786, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0073347091674805, "global_step": 563787, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9905245304107666, "global_step": 563788, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9993549585342407, "global_step": 563789, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.063014268875122, "global_step": 563790, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.019073963165283, "global_step": 563791, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9742350578308105, "global_step": 563792, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.988124132156372, "global_step": 563793, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0655343532562256, "global_step": 563794, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9244558811187744, "global_step": 563795, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9863065481185913, "global_step": 563796, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0865988731384277, "global_step": 563797, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.007504463195801, "global_step": 563798, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.00179386138916, "global_step": 563799, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0644357204437256, "global_step": 563800, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9464737176895142, "global_step": 563801, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.058112144470215, "global_step": 563802, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0520522594451904, "global_step": 563803, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.052999496459961, "global_step": 563804, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.022690534591675, "global_step": 563805, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0558245182037354, "global_step": 563806, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0296971797943115, "global_step": 563807, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.074810743331909, "global_step": 563808, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9847623109817505, "global_step": 563809, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0405237674713135, "global_step": 563810, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9542440176010132, "global_step": 563811, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.004141092300415, "global_step": 563812, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0867562294006348, "global_step": 563813, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.057968854904175, "global_step": 563814, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0032804012298584, "global_step": 563815, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.035043239593506, "global_step": 563816, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9888473749160767, "global_step": 563817, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0432546138763428, "global_step": 563818, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9994827508926392, "global_step": 563819, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9972482919692993, "global_step": 563820, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9819023609161377, "global_step": 563821, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0489144325256348, "global_step": 563822, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0021634101867676, "global_step": 563823, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0160164833068848, "global_step": 563824, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0254619121551514, "global_step": 563825, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.06937837600708, "global_step": 563826, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0586447715759277, "global_step": 563827, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0339906215667725, "global_step": 563828, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0252525806427, "global_step": 563829, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0137360095977783, "global_step": 563830, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.028230667114258, "global_step": 563831, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.12619948387146, "global_step": 563832, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0493552684783936, "global_step": 563833, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9347813129425049, "global_step": 563834, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0837905406951904, "global_step": 563835, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.048431634902954, "global_step": 563836, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0027730464935303, "global_step": 563837, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.074425220489502, "global_step": 563838, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.03550124168396, "global_step": 563839, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.052629232406616, "global_step": 563840, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9708980321884155, "global_step": 563841, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.096196413040161, "global_step": 563842, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.045773506164551, "global_step": 563843, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9802995920181274, "global_step": 563844, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9606379270553589, "global_step": 563845, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9634209871292114, "global_step": 563846, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.093801736831665, "global_step": 563847, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.014760732650757, "global_step": 563848, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0573949813842773, "global_step": 563849, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.043999671936035, "global_step": 563850, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9543346166610718, "global_step": 563851, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.078004837036133, "global_step": 563852, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0379557609558105, "global_step": 563853, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9740318059921265, "global_step": 563854, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.066927433013916, "global_step": 563855, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0228323936462402, "global_step": 563856, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0497896671295166, "global_step": 563857, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.000849962234497, "global_step": 563858, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0818681716918945, "global_step": 563859, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.050222635269165, "global_step": 563860, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9913334846496582, "global_step": 563861, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0401017665863037, "global_step": 563862, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0594377517700195, "global_step": 563863, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1411685943603516, "global_step": 563864, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0120341777801514, "global_step": 563865, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0220894813537598, "global_step": 563866, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1534924507141113, "global_step": 563867, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.024205207824707, "global_step": 563868, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0166738033294678, "global_step": 563869, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.994518518447876, "global_step": 563870, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9655616283416748, "global_step": 563871, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.057426929473877, "global_step": 563872, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.044227361679077, "global_step": 563873, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9759817123413086, "global_step": 563874, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.022646427154541, "global_step": 563875, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.011523723602295, "global_step": 563876, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9980932474136353, "global_step": 563877, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9352327585220337, "global_step": 563878, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.104153633117676, "global_step": 563879, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.102585792541504, "global_step": 563880, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.006235122680664, "global_step": 563881, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0811145305633545, "global_step": 563882, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9384866952896118, "global_step": 563883, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0025811195373535, "global_step": 563884, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9983400106430054, "global_step": 563885, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0010626316070557, "global_step": 563886, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.003296375274658, "global_step": 563887, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.946428894996643, "global_step": 563888, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.010624647140503, "global_step": 563889, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9986460208892822, "global_step": 563890, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0351614952087402, "global_step": 563891, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9887665510177612, "global_step": 563892, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.058986186981201, "global_step": 563893, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0270817279815674, "global_step": 563894, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.049221992492676, "global_step": 563895, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9847782850265503, "global_step": 563896, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0138020515441895, "global_step": 563897, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0586390495300293, "global_step": 563898, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9790353775024414, "global_step": 563899, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0228683948516846, "global_step": 563900, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.033167839050293, "global_step": 563901, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0571858882904053, "global_step": 563902, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.948599934577942, "global_step": 563903, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0403964519500732, "global_step": 563904, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0499815940856934, "global_step": 563905, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9741300344467163, "global_step": 563906, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9915248155593872, "global_step": 563907, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9999576807022095, "global_step": 563908, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.062241554260254, "global_step": 563909, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9979041814804077, "global_step": 563910, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9876726865768433, "global_step": 563911, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.031020164489746, "global_step": 563912, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.926788091659546, "global_step": 563913, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1090431213378906, "global_step": 563914, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9671353101730347, "global_step": 563915, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.009983539581299, "global_step": 563916, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0103259086608887, "global_step": 563917, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9549144506454468, "global_step": 563918, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.981667399406433, "global_step": 563919, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.980531096458435, "global_step": 563920, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.020010471343994, "global_step": 563921, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9563488960266113, "global_step": 563922, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.082307815551758, "global_step": 563923, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0132923126220703, "global_step": 563924, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9317402839660645, "global_step": 563925, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0185201168060303, "global_step": 563926, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0703601837158203, "global_step": 563927, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0446860790252686, "global_step": 563928, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0798895359039307, "global_step": 563929, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.001373767852783, "global_step": 563930, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.07136607170105, "global_step": 563931, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9578962326049805, "global_step": 563932, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0245625972747803, "global_step": 563933, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1044769287109375, "global_step": 563934, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0393333435058594, "global_step": 563935, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0687990188598633, "global_step": 563936, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.023703098297119, "global_step": 563937, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.101519823074341, "global_step": 563938, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9835010766983032, "global_step": 563939, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9218274354934692, "global_step": 563940, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9981333017349243, "global_step": 563941, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.05816912651062, "global_step": 563942, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9610927104949951, "global_step": 563943, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0175716876983643, "global_step": 563944, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.055410146713257, "global_step": 563945, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.052737236022949, "global_step": 563946, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0621588230133057, "global_step": 563947, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.065659999847412, "global_step": 563948, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9531644582748413, "global_step": 563949, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.013352155685425, "global_step": 563950, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9945176839828491, "global_step": 563951, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0423314571380615, "global_step": 563952, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0008857250213623, "global_step": 563953, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.988336205482483, "global_step": 563954, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0060107707977295, "global_step": 563955, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0460803508758545, "global_step": 563956, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.062635898590088, "global_step": 563957, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.024132013320923, "global_step": 563958, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.069148540496826, "global_step": 563959, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.004453420639038, "global_step": 563960, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0093436241149902, "global_step": 563961, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.8987348079681396, "global_step": 563962, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0291526317596436, "global_step": 563963, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9770245552062988, "global_step": 563964, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.025923252105713, "global_step": 563965, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0488827228546143, "global_step": 563966, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0396509170532227, "global_step": 563967, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.121964931488037, "global_step": 563968, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.036557197570801, "global_step": 563969, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0280985832214355, "global_step": 563970, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.003253221511841, "global_step": 563971, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0915274620056152, "global_step": 563972, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.045173168182373, "global_step": 563973, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9961410760879517, "global_step": 563974, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0953216552734375, "global_step": 563975, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0619094371795654, "global_step": 563976, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.010389566421509, "global_step": 563977, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.104194164276123, "global_step": 563978, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0704803466796875, "global_step": 563979, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0428385734558105, "global_step": 563980, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9287501573562622, "global_step": 563981, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1325814723968506, "global_step": 563982, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0389246940612793, "global_step": 563983, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9229036569595337, "global_step": 563984, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.067142963409424, "global_step": 563985, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0273666381835938, "global_step": 563986, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.994323492050171, "global_step": 563987, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9658395051956177, "global_step": 563988, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.062563180923462, "global_step": 563989, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9705443382263184, "global_step": 563990, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0543999671936035, "global_step": 563991, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.033836603164673, "global_step": 563992, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9269942045211792, "global_step": 563993, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9369349479675293, "global_step": 563994, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0437536239624023, "global_step": 563995, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0126278400421143, "global_step": 563996, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0354504585266113, "global_step": 563997, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0611844062805176, "global_step": 563998, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9686121940612793, "global_step": 563999, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.932217001914978, "global_step": 564000, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0423076152801514, "global_step": 564001, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0203378200531006, "global_step": 564002, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9852021932601929, "global_step": 564003, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9495347738265991, "global_step": 564004, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9589866399765015, "global_step": 564005, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0541813373565674, "global_step": 564006, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0408718585968018, "global_step": 564007, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9805876016616821, "global_step": 564008, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.004059314727783, "global_step": 564009, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0760273933410645, "global_step": 564010, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1106042861938477, "global_step": 564011, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0424909591674805, "global_step": 564012, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9910385608673096, "global_step": 564013, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0090246200561523, "global_step": 564014, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1162116527557373, "global_step": 564015, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9507477283477783, "global_step": 564016, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.083451271057129, "global_step": 564017, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.069511651992798, "global_step": 564018, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9213666915893555, "global_step": 564019, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9972894191741943, "global_step": 564020, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0168800354003906, "global_step": 564021, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.013430118560791, "global_step": 564022, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.04278564453125, "global_step": 564023, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.071859836578369, "global_step": 564024, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.985281229019165, "global_step": 564025, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.039665699005127, "global_step": 564026, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.047146797180176, "global_step": 564027, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9584749937057495, "global_step": 564028, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9639602899551392, "global_step": 564029, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0163049697875977, "global_step": 564030, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.020766019821167, "global_step": 564031, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0127086639404297, "global_step": 564032, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9455666542053223, "global_step": 564033, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0774905681610107, "global_step": 564034, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0279173851013184, "global_step": 564035, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.056865930557251, "global_step": 564036, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9897422790527344, "global_step": 564037, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9866145849227905, "global_step": 564038, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.005608081817627, "global_step": 564039, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.096724033355713, "global_step": 564040, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0169219970703125, "global_step": 564041, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.026761054992676, "global_step": 564042, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9638046026229858, "global_step": 564043, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0476136207580566, "global_step": 564044, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9211252927780151, "global_step": 564045, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0992414951324463, "global_step": 564046, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0688438415527344, "global_step": 564047, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0622265338897705, "global_step": 564048, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0455455780029297, "global_step": 564049, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0237865447998047, "global_step": 564050, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.067565441131592, "global_step": 564051, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0477795600891113, "global_step": 564052, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0780298709869385, "global_step": 564053, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0506398677825928, "global_step": 564054, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.105349063873291, "global_step": 564055, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0461204051971436, "global_step": 564056, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.01908802986145, "global_step": 564057, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.019092321395874, "global_step": 564058, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.123134136199951, "global_step": 564059, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.047333002090454, "global_step": 564060, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1262946128845215, "global_step": 564061, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.002525806427002, "global_step": 564062, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.065502405166626, "global_step": 564063, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0592916011810303, "global_step": 564064, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.007723808288574, "global_step": 564065, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.012047052383423, "global_step": 564066, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.930998682975769, "global_step": 564067, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.045264482498169, "global_step": 564068, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0407841205596924, "global_step": 564069, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0677902698516846, "global_step": 564070, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.01139235496521, "global_step": 564071, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0430855751037598, "global_step": 564072, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0179038047790527, "global_step": 564073, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9936803579330444, "global_step": 564074, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0891990661621094, "global_step": 564075, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0865979194641113, "global_step": 564076, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0952656269073486, "global_step": 564077, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9838379621505737, "global_step": 564078, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9785590171813965, "global_step": 564079, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.008695363998413, "global_step": 564080, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.1180896759033203, "global_step": 564081, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0428249835968018, "global_step": 564082, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0447750091552734, "global_step": 564083, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.022695541381836, "global_step": 564084, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.047844171524048, "global_step": 564085, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.035165548324585, "global_step": 564086, "epoch": 931, "lr": 5e-05}
{"train_loss": 1.9847660064697266, "global_step": 564087, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.092161178588867, "global_step": 564088, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.12699556350708, "global_step": 564089, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.0255234241485596, "global_step": 564090, "epoch": 931, "lr": 5e-05}
{"train_loss": 2.097308874130249, "global_step": 564091, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9947943687438965, "global_step": 564092, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0259907245635986, "global_step": 564093, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0360453128814697, "global_step": 564094, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.978206992149353, "global_step": 564095, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0236635208129883, "global_step": 564096, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.002542018890381, "global_step": 564097, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9808818101882935, "global_step": 564098, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1190054416656494, "global_step": 564099, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.004944324493408, "global_step": 564100, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.061811685562134, "global_step": 564101, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0372402667999268, "global_step": 564102, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0173492431640625, "global_step": 564103, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.000753402709961, "global_step": 564104, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9321345090866089, "global_step": 564105, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9204010963439941, "global_step": 564106, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9564419984817505, "global_step": 564107, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.027503490447998, "global_step": 564108, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1198906898498535, "global_step": 564109, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0117011070251465, "global_step": 564110, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0939383506774902, "global_step": 564111, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.01796293258667, "global_step": 564112, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0785844326019287, "global_step": 564113, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.108816146850586, "global_step": 564114, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9838007688522339, "global_step": 564115, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9760923385620117, "global_step": 564116, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0372631549835205, "global_step": 564117, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.8889600038528442, "global_step": 564118, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0372867584228516, "global_step": 564119, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.046584129333496, "global_step": 564120, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9422136545181274, "global_step": 564121, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9835160970687866, "global_step": 564122, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.017108678817749, "global_step": 564123, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0950591564178467, "global_step": 564124, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.103349447250366, "global_step": 564125, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0503716468811035, "global_step": 564126, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0597805976867676, "global_step": 564127, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0043628215789795, "global_step": 564128, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.017462730407715, "global_step": 564129, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0589780807495117, "global_step": 564130, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9298441410064697, "global_step": 564131, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.082057237625122, "global_step": 564132, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0150680541992188, "global_step": 564133, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.02095103263855, "global_step": 564134, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.992837905883789, "global_step": 564135, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9613319635391235, "global_step": 564136, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.163233518600464, "global_step": 564137, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9497795104980469, "global_step": 564138, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9818243980407715, "global_step": 564139, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0557029247283936, "global_step": 564140, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9761961698532104, "global_step": 564141, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9991942644119263, "global_step": 564142, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.001277208328247, "global_step": 564143, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9607207775115967, "global_step": 564144, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.945833444595337, "global_step": 564145, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.038391590118408, "global_step": 564146, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9647613763809204, "global_step": 564147, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.037891387939453, "global_step": 564148, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.021003007888794, "global_step": 564149, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9673875570297241, "global_step": 564150, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1114256381988525, "global_step": 564151, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0601909160614014, "global_step": 564152, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9988378286361694, "global_step": 564153, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.013640880584717, "global_step": 564154, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9643821716308594, "global_step": 564155, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0394246578216553, "global_step": 564156, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9942286014556885, "global_step": 564157, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9717340469360352, "global_step": 564158, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9600632190704346, "global_step": 564159, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.152195930480957, "global_step": 564160, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0088281631469727, "global_step": 564161, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0390756130218506, "global_step": 564162, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0555896759033203, "global_step": 564163, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.056804656982422, "global_step": 564164, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9914520978927612, "global_step": 564165, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0432591438293457, "global_step": 564166, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.052544116973877, "global_step": 564167, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9884207248687744, "global_step": 564168, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0279576778411865, "global_step": 564169, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9770995378494263, "global_step": 564170, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0586965084075928, "global_step": 564171, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.043386697769165, "global_step": 564172, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0054283142089844, "global_step": 564173, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0229930877685547, "global_step": 564174, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.972771406173706, "global_step": 564175, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.008143424987793, "global_step": 564176, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0524072647094727, "global_step": 564177, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.975657343864441, "global_step": 564178, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.014267683029175, "global_step": 564179, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0002048015594482, "global_step": 564180, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9949434995651245, "global_step": 564181, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0088090896606445, "global_step": 564182, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0667874813079834, "global_step": 564183, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.056607484817505, "global_step": 564184, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0515074729919434, "global_step": 564185, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0083885192871094, "global_step": 564186, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9857553243637085, "global_step": 564187, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0167810916900635, "global_step": 564188, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.036221742630005, "global_step": 564189, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9925425052642822, "global_step": 564190, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.015406847000122, "global_step": 564191, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0025014877319336, "global_step": 564192, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.993403673171997, "global_step": 564193, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9728848934173584, "global_step": 564194, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9737434387207031, "global_step": 564195, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9874948263168335, "global_step": 564196, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9294633865356445, "global_step": 564197, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0298573970794678, "global_step": 564198, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9230602979660034, "global_step": 564199, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0453224182128906, "global_step": 564200, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9699153900146484, "global_step": 564201, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.986072063446045, "global_step": 564202, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.055880069732666, "global_step": 564203, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.070608615875244, "global_step": 564204, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1176769733428955, "global_step": 564205, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0391712188720703, "global_step": 564206, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.966506838798523, "global_step": 564207, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9596755504608154, "global_step": 564208, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.056997776031494, "global_step": 564209, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9930305480957031, "global_step": 564210, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.049622058868408, "global_step": 564211, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9874722957611084, "global_step": 564212, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1520631313323975, "global_step": 564213, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9866230487823486, "global_step": 564214, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.911750316619873, "global_step": 564215, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0686068534851074, "global_step": 564216, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9854124784469604, "global_step": 564217, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9987194538116455, "global_step": 564218, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9930660724639893, "global_step": 564219, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9816622734069824, "global_step": 564220, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.939302921295166, "global_step": 564221, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0156776905059814, "global_step": 564222, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0839505195617676, "global_step": 564223, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0604584217071533, "global_step": 564224, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0963261127471924, "global_step": 564225, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9622892141342163, "global_step": 564226, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9307036399841309, "global_step": 564227, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0724315643310547, "global_step": 564228, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.060838222503662, "global_step": 564229, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1639244556427, "global_step": 564230, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.031175374984741, "global_step": 564231, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9857794046401978, "global_step": 564232, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9789389371871948, "global_step": 564233, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.020993232727051, "global_step": 564234, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9622883796691895, "global_step": 564235, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1154637336730957, "global_step": 564236, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9891184568405151, "global_step": 564237, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9623253345489502, "global_step": 564238, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.964721918106079, "global_step": 564239, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0005857944488525, "global_step": 564240, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0666298866271973, "global_step": 564241, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0016937255859375, "global_step": 564242, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9513392448425293, "global_step": 564243, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9784609079360962, "global_step": 564244, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9621347188949585, "global_step": 564245, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0411376953125, "global_step": 564246, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.97405207157135, "global_step": 564247, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0806140899658203, "global_step": 564248, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.936246395111084, "global_step": 564249, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0375216007232666, "global_step": 564250, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.980202078819275, "global_step": 564251, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.998915433883667, "global_step": 564252, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1004714965820312, "global_step": 564253, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0146162509918213, "global_step": 564254, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9839993715286255, "global_step": 564255, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0406241416931152, "global_step": 564256, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0667507648468018, "global_step": 564257, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.006208658218384, "global_step": 564258, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.950239896774292, "global_step": 564259, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.050523519515991, "global_step": 564260, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9600603580474854, "global_step": 564261, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0433082580566406, "global_step": 564262, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.034663438796997, "global_step": 564263, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0741682052612305, "global_step": 564264, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.034207820892334, "global_step": 564265, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0571346282958984, "global_step": 564266, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.07895565032959, "global_step": 564267, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0325026512145996, "global_step": 564268, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0388433933258057, "global_step": 564269, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.002760410308838, "global_step": 564270, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9868334531784058, "global_step": 564271, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.000809669494629, "global_step": 564272, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0052099227905273, "global_step": 564273, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9410648345947266, "global_step": 564274, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.089064836502075, "global_step": 564275, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.97959566116333, "global_step": 564276, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0409317016601562, "global_step": 564277, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9515444040298462, "global_step": 564278, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.031463146209717, "global_step": 564279, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0814692974090576, "global_step": 564280, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9939379692077637, "global_step": 564281, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.999907374382019, "global_step": 564282, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9753077030181885, "global_step": 564283, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0645620822906494, "global_step": 564284, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0252463817596436, "global_step": 564285, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.046644687652588, "global_step": 564286, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0112786293029785, "global_step": 564287, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.021121025085449, "global_step": 564288, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.015183925628662, "global_step": 564289, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.075645685195923, "global_step": 564290, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9631998538970947, "global_step": 564291, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9590749740600586, "global_step": 564292, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0160553455352783, "global_step": 564293, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0958409309387207, "global_step": 564294, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0252935886383057, "global_step": 564295, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9283664226531982, "global_step": 564296, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9751561880111694, "global_step": 564297, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9712058305740356, "global_step": 564298, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9634535312652588, "global_step": 564299, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.003005266189575, "global_step": 564300, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.982771635055542, "global_step": 564301, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9742426872253418, "global_step": 564302, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0538489818573, "global_step": 564303, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9769268035888672, "global_step": 564304, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9788379669189453, "global_step": 564305, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.012295722961426, "global_step": 564306, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.008371114730835, "global_step": 564307, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9963120222091675, "global_step": 564308, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9877665042877197, "global_step": 564309, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0434811115264893, "global_step": 564310, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.066709518432617, "global_step": 564311, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.114412307739258, "global_step": 564312, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0313608646392822, "global_step": 564313, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0179646015167236, "global_step": 564314, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0714118480682373, "global_step": 564315, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.972461223602295, "global_step": 564316, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0343587398529053, "global_step": 564317, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0448989868164062, "global_step": 564318, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0171868801116943, "global_step": 564319, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.891886830329895, "global_step": 564320, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.987046480178833, "global_step": 564321, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.03559947013855, "global_step": 564322, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9074803590774536, "global_step": 564323, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9683074951171875, "global_step": 564324, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1527087688446045, "global_step": 564325, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9699699878692627, "global_step": 564326, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.057563066482544, "global_step": 564327, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.983764886856079, "global_step": 564328, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0268197059631348, "global_step": 564329, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.004380226135254, "global_step": 564330, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.001347303390503, "global_step": 564331, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0623602867126465, "global_step": 564332, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9914119243621826, "global_step": 564333, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0930299758911133, "global_step": 564334, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.061547040939331, "global_step": 564335, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9648377895355225, "global_step": 564336, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9872279167175293, "global_step": 564337, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.056252956390381, "global_step": 564338, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0163187980651855, "global_step": 564339, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.916729211807251, "global_step": 564340, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.019801378250122, "global_step": 564341, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9861729145050049, "global_step": 564342, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9877020120620728, "global_step": 564343, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0498154163360596, "global_step": 564344, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.129906415939331, "global_step": 564345, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0863678455352783, "global_step": 564346, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.10791015625, "global_step": 564347, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9965567588806152, "global_step": 564348, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.020324468612671, "global_step": 564349, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.051084280014038, "global_step": 564350, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0385971069335938, "global_step": 564351, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9573954343795776, "global_step": 564352, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.037890911102295, "global_step": 564353, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.053511142730713, "global_step": 564354, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0305323600769043, "global_step": 564355, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.057310104370117, "global_step": 564356, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9587208032608032, "global_step": 564357, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0446274280548096, "global_step": 564358, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.968279242515564, "global_step": 564359, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0065839290618896, "global_step": 564360, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.988722801208496, "global_step": 564361, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.047879219055176, "global_step": 564362, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0531582832336426, "global_step": 564363, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0244946479797363, "global_step": 564364, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0488383769989014, "global_step": 564365, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9659810066223145, "global_step": 564366, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0712339878082275, "global_step": 564367, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0074965953826904, "global_step": 564368, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0339648723602295, "global_step": 564369, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9836034774780273, "global_step": 564370, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9882197380065918, "global_step": 564371, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.078420400619507, "global_step": 564372, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.033510446548462, "global_step": 564373, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0715365409851074, "global_step": 564374, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9853829145431519, "global_step": 564375, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0631518363952637, "global_step": 564376, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.081145763397217, "global_step": 564377, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0059332847595215, "global_step": 564378, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9935269355773926, "global_step": 564379, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0100927352905273, "global_step": 564380, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9659407138824463, "global_step": 564381, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.045665979385376, "global_step": 564382, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.125134229660034, "global_step": 564383, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.122696876525879, "global_step": 564384, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.959949016571045, "global_step": 564385, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0626683235168457, "global_step": 564386, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0786194801330566, "global_step": 564387, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0344583988189697, "global_step": 564388, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9795795679092407, "global_step": 564389, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9641326665878296, "global_step": 564390, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.050307035446167, "global_step": 564391, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.00976824760437, "global_step": 564392, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.076070547103882, "global_step": 564393, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0173258781433105, "global_step": 564394, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.068554639816284, "global_step": 564395, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9850654602050781, "global_step": 564396, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.113245964050293, "global_step": 564397, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.045166254043579, "global_step": 564398, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.048065423965454, "global_step": 564399, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0955138206481934, "global_step": 564400, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.050906181335449, "global_step": 564401, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0150036811828613, "global_step": 564402, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.098905324935913, "global_step": 564403, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0116684436798096, "global_step": 564404, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.981384038925171, "global_step": 564405, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.085099697113037, "global_step": 564406, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9858752489089966, "global_step": 564407, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.957145094871521, "global_step": 564408, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9745304584503174, "global_step": 564409, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0664100646972656, "global_step": 564410, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9241251945495605, "global_step": 564411, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.993263602256775, "global_step": 564412, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.014216661453247, "global_step": 564413, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9907885789871216, "global_step": 564414, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0317413806915283, "global_step": 564415, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0082123279571533, "global_step": 564416, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.028364658355713, "global_step": 564417, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.958224892616272, "global_step": 564418, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9182922840118408, "global_step": 564419, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.126476764678955, "global_step": 564420, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0708682537078857, "global_step": 564421, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9587067365646362, "global_step": 564422, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0382585525512695, "global_step": 564423, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0474793910980225, "global_step": 564424, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.988521933555603, "global_step": 564425, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.093979835510254, "global_step": 564426, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.953078269958496, "global_step": 564427, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.006270170211792, "global_step": 564428, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0802829265594482, "global_step": 564429, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.956770896911621, "global_step": 564430, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9069329500198364, "global_step": 564431, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9991004467010498, "global_step": 564432, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9965864419937134, "global_step": 564433, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9300978183746338, "global_step": 564434, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0036542415618896, "global_step": 564435, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0374879837036133, "global_step": 564436, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9368847608566284, "global_step": 564437, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.063598155975342, "global_step": 564438, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0077531337738037, "global_step": 564439, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0840418338775635, "global_step": 564440, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.024722099304199, "global_step": 564441, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0946285724639893, "global_step": 564442, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0321602821350098, "global_step": 564443, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.018930673599243, "global_step": 564444, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.985799789428711, "global_step": 564445, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.990561604499817, "global_step": 564446, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9691152572631836, "global_step": 564447, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9808902740478516, "global_step": 564448, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.064086675643921, "global_step": 564449, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9691659212112427, "global_step": 564450, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0861172676086426, "global_step": 564451, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.002923011779785, "global_step": 564452, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0127291679382324, "global_step": 564453, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.089160442352295, "global_step": 564454, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9532095193862915, "global_step": 564455, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0511696338653564, "global_step": 564456, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0301260948181152, "global_step": 564457, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.022243022918701, "global_step": 564458, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9995555877685547, "global_step": 564459, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.038694143295288, "global_step": 564460, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.015064239501953, "global_step": 564461, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9778108596801758, "global_step": 564462, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0717592239379883, "global_step": 564463, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.949452519416809, "global_step": 564464, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.041224241256714, "global_step": 564465, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.8884743452072144, "global_step": 564466, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0127406120300293, "global_step": 564467, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0204122066497803, "global_step": 564468, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9484825134277344, "global_step": 564469, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9911918640136719, "global_step": 564470, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.982960820198059, "global_step": 564471, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0448074340820312, "global_step": 564472, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9663667678833008, "global_step": 564473, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.101778030395508, "global_step": 564474, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.988620638847351, "global_step": 564475, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.104571580886841, "global_step": 564476, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9694576263427734, "global_step": 564477, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9705603122711182, "global_step": 564478, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0752112865448, "global_step": 564479, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.966548204421997, "global_step": 564480, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.01877760887146, "global_step": 564481, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0331203937530518, "global_step": 564482, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.044917345046997, "global_step": 564483, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0450398921966553, "global_step": 564484, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9785537719726562, "global_step": 564485, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1058189868927, "global_step": 564486, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.021681070327759, "global_step": 564487, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0231900215148926, "global_step": 564488, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.092092990875244, "global_step": 564489, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0640649795532227, "global_step": 564490, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0528688430786133, "global_step": 564491, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.072991371154785, "global_step": 564492, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.8887643814086914, "global_step": 564493, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.071280002593994, "global_step": 564494, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9885895252227783, "global_step": 564495, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0911567211151123, "global_step": 564496, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.007822036743164, "global_step": 564497, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.053395986557007, "global_step": 564498, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.977281928062439, "global_step": 564499, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.009913206100464, "global_step": 564500, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.09671688079834, "global_step": 564501, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.972760796546936, "global_step": 564502, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.055351495742798, "global_step": 564503, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.025129556655884, "global_step": 564504, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9896485805511475, "global_step": 564505, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.023300886154175, "global_step": 564506, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.058225393295288, "global_step": 564507, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.016958713531494, "global_step": 564508, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9759749174118042, "global_step": 564509, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.030089855194092, "global_step": 564510, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0813283920288086, "global_step": 564511, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0268003940582275, "global_step": 564512, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.013444662094116, "global_step": 564513, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.004486083984375, "global_step": 564514, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.018744468688965, "global_step": 564515, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.970505952835083, "global_step": 564516, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0505430698394775, "global_step": 564517, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.102834701538086, "global_step": 564518, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.07757306098938, "global_step": 564519, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0275537967681885, "global_step": 564520, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.09043025970459, "global_step": 564521, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.930500864982605, "global_step": 564522, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0429956912994385, "global_step": 564523, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0703375339508057, "global_step": 564524, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0355749130249023, "global_step": 564525, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0513617992401123, "global_step": 564526, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.116722345352173, "global_step": 564527, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.125655174255371, "global_step": 564528, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0613577365875244, "global_step": 564529, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0557265281677246, "global_step": 564530, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9972816705703735, "global_step": 564531, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9679522514343262, "global_step": 564532, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0196242332458496, "global_step": 564533, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.014256715774536, "global_step": 564534, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.086493730545044, "global_step": 564535, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0126543045043945, "global_step": 564536, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.066098213195801, "global_step": 564537, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0639090538024902, "global_step": 564538, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9965204000473022, "global_step": 564539, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.974411964416504, "global_step": 564540, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.995114803314209, "global_step": 564541, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0732851028442383, "global_step": 564542, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.080819606781006, "global_step": 564543, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.035952568054199, "global_step": 564544, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9360264539718628, "global_step": 564545, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0289173126220703, "global_step": 564546, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0925116539001465, "global_step": 564547, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0233495235443115, "global_step": 564548, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.057915687561035, "global_step": 564549, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0240285396575928, "global_step": 564550, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.991891860961914, "global_step": 564551, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1095025539398193, "global_step": 564552, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0417051315307617, "global_step": 564553, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.109240770339966, "global_step": 564554, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0596659183502197, "global_step": 564555, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0487759113311768, "global_step": 564556, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0462000370025635, "global_step": 564557, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0558457374572754, "global_step": 564558, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1154427528381348, "global_step": 564559, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.008272647857666, "global_step": 564560, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0976598262786865, "global_step": 564561, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0446321964263916, "global_step": 564562, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0505776405334473, "global_step": 564563, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9128800630569458, "global_step": 564564, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.013608455657959, "global_step": 564565, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.00266432762146, "global_step": 564566, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0668745040893555, "global_step": 564567, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.080317258834839, "global_step": 564568, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.996332049369812, "global_step": 564569, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0014407634735107, "global_step": 564570, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.909603238105774, "global_step": 564571, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9343703985214233, "global_step": 564572, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0380074977874756, "global_step": 564573, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0075619220733643, "global_step": 564574, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9357985258102417, "global_step": 564575, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9882112741470337, "global_step": 564576, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0004332065582275, "global_step": 564577, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0684032440185547, "global_step": 564578, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9744213819503784, "global_step": 564579, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0276246070861816, "global_step": 564580, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.966431975364685, "global_step": 564581, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9682730436325073, "global_step": 564582, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9780147075653076, "global_step": 564583, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0623180866241455, "global_step": 564584, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.959116816520691, "global_step": 564585, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.108039379119873, "global_step": 564586, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0759801864624023, "global_step": 564587, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0251243114471436, "global_step": 564588, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0041167736053467, "global_step": 564589, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0794527530670166, "global_step": 564590, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0188558101654053, "global_step": 564591, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.015662431716919, "global_step": 564592, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0157535076141357, "global_step": 564593, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0312931537628174, "global_step": 564594, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.032055139541626, "global_step": 564595, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0285956859588623, "global_step": 564596, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.955074667930603, "global_step": 564597, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0365564823150635, "global_step": 564598, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.057079792022705, "global_step": 564599, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.973870038986206, "global_step": 564600, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.09796404838562, "global_step": 564601, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9821370840072632, "global_step": 564602, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0991477966308594, "global_step": 564603, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.068100690841675, "global_step": 564604, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.026841402053833, "global_step": 564605, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.077895402908325, "global_step": 564606, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0584888458251953, "global_step": 564607, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9284954071044922, "global_step": 564608, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9865977764129639, "global_step": 564609, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.917141318321228, "global_step": 564610, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.020662307739258, "global_step": 564611, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0910792350769043, "global_step": 564612, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.115630865097046, "global_step": 564613, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9239742755889893, "global_step": 564614, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0045197010040283, "global_step": 564615, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0127673149108887, "global_step": 564616, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9222931861877441, "global_step": 564617, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0634708404541016, "global_step": 564618, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9581552743911743, "global_step": 564619, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.065006732940674, "global_step": 564620, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0225374698638916, "global_step": 564621, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9950997829437256, "global_step": 564622, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9704525470733643, "global_step": 564623, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9895389080047607, "global_step": 564624, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9561984539031982, "global_step": 564625, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9957815408706665, "global_step": 564626, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0503604412078857, "global_step": 564627, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.030888557434082, "global_step": 564628, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9865914583206177, "global_step": 564629, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.035496950149536, "global_step": 564630, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.093053102493286, "global_step": 564631, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.05509877204895, "global_step": 564632, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.963333249092102, "global_step": 564633, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0431108474731445, "global_step": 564634, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0804171562194824, "global_step": 564635, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.020745277404785, "global_step": 564636, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9592121839523315, "global_step": 564637, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0326731204986572, "global_step": 564638, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.070460796356201, "global_step": 564639, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0359461307525635, "global_step": 564640, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.03062105178833, "global_step": 564641, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.165792465209961, "global_step": 564642, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0632126331329346, "global_step": 564643, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.031297206878662, "global_step": 564644, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1012423038482666, "global_step": 564645, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9910094738006592, "global_step": 564646, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.040299892425537, "global_step": 564647, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1196866035461426, "global_step": 564648, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0366477966308594, "global_step": 564649, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0572495460510254, "global_step": 564650, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9710724353790283, "global_step": 564651, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9373440742492676, "global_step": 564652, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0799479484558105, "global_step": 564653, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0029687881469727, "global_step": 564654, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0367093086242676, "global_step": 564655, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0138778686523438, "global_step": 564656, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9861454963684082, "global_step": 564657, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9695228338241577, "global_step": 564658, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0772647857666016, "global_step": 564659, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0184521675109863, "global_step": 564660, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0622551441192627, "global_step": 564661, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0087571144104004, "global_step": 564662, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1300833225250244, "global_step": 564663, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.001244068145752, "global_step": 564664, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.064328193664551, "global_step": 564665, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0569937229156494, "global_step": 564666, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.091806411743164, "global_step": 564667, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0865845680236816, "global_step": 564668, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.052978038787842, "global_step": 564669, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.114563226699829, "global_step": 564670, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0271477699279785, "global_step": 564671, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0243754386901855, "global_step": 564672, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.019489288330078, "global_step": 564673, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0960774421691895, "global_step": 564674, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.973756194114685, "global_step": 564675, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1220643520355225, "global_step": 564676, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9931377172470093, "global_step": 564677, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9496796131134033, "global_step": 564678, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0240840911865234, "global_step": 564679, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.032221555709839, "global_step": 564680, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0519096851348877, "global_step": 564681, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.030376672744751, "global_step": 564682, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0890088081359863, "global_step": 564683, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0882320404052734, "global_step": 564684, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0208253860473633, "global_step": 564685, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0782225131988525, "global_step": 564686, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9443174600601196, "global_step": 564687, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1441986560821533, "global_step": 564688, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0345089435577393, "global_step": 564689, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.090477228164673, "global_step": 564690, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0567500591278076, "global_step": 564691, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.035017251968384, "global_step": 564692, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.017190456390381, "global_step": 564693, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0045106410980225, "global_step": 564694, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0876309871673584, "global_step": 564695, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0992205142974854, "global_step": 564696, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0053107738494873, "global_step": 564697, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9661237001419067, "global_step": 564698, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.978760004043579, "global_step": 564699, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1124064922332764, "global_step": 564700, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9941526651382446, "global_step": 564701, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.06099796295166, "global_step": 564702, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.050657272338867, "global_step": 564703, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9656295776367188, "global_step": 564704, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9297754764556885, "global_step": 564705, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9985119104385376, "global_step": 564706, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.993284821510315, "global_step": 564707, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0776562690734863, "global_step": 564708, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0679264068603516, "global_step": 564709, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.993056297302246, "global_step": 564710, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.02197265625, "global_step": 564711, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9828816652297974, "global_step": 564712, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0561182498931885, "global_step": 564713, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.050337314605713, "global_step": 564714, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.974755048751831, "global_step": 564715, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0839154720306396, "global_step": 564716, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.992787480354309, "global_step": 564717, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0035486221313477, "global_step": 564718, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.032578945159912, "global_step": 564719, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.060995578765869, "global_step": 564720, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.048126697540283, "global_step": 564721, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0280323028564453, "global_step": 564722, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.04638409614563, "global_step": 564723, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.014437437057495, "global_step": 564724, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0228278636932373, "global_step": 564725, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.049013137817383, "global_step": 564726, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1355488300323486, "global_step": 564727, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9870777130126953, "global_step": 564728, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.8852958679199219, "global_step": 564729, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9726585149765015, "global_step": 564730, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.000962495803833, "global_step": 564731, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0387628078460693, "global_step": 564732, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0482280254364014, "global_step": 564733, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0541067123413086, "global_step": 564734, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.034424304962158, "global_step": 564735, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.056732177734375, "global_step": 564736, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.031702995300293, "global_step": 564737, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9387191534042358, "global_step": 564738, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0126729011535645, "global_step": 564739, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9544624090194702, "global_step": 564740, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.972451090812683, "global_step": 564741, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0624566078186035, "global_step": 564742, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.992368221282959, "global_step": 564743, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0385797023773193, "global_step": 564744, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9630820751190186, "global_step": 564745, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.044788360595703, "global_step": 564746, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9544880390167236, "global_step": 564747, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0273122787475586, "global_step": 564748, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0490500926971436, "global_step": 564749, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9666645526885986, "global_step": 564750, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0832011699676514, "global_step": 564751, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.011491060256958, "global_step": 564752, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9600653648376465, "global_step": 564753, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0191473960876465, "global_step": 564754, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9980831146240234, "global_step": 564755, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0978176593780518, "global_step": 564756, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0114684104919434, "global_step": 564757, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9836952686309814, "global_step": 564758, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1462533473968506, "global_step": 564759, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0618252754211426, "global_step": 564760, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.978853464126587, "global_step": 564761, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.013211488723755, "global_step": 564762, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9788378477096558, "global_step": 564763, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9381715059280396, "global_step": 564764, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.040863275527954, "global_step": 564765, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9752382040023804, "global_step": 564766, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.021726369857788, "global_step": 564767, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0798702239990234, "global_step": 564768, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0192372798919678, "global_step": 564769, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0242385864257812, "global_step": 564770, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9871456623077393, "global_step": 564771, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9887409210205078, "global_step": 564772, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.025747537612915, "global_step": 564773, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0341410636901855, "global_step": 564774, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9803242683410645, "global_step": 564775, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0064055919647217, "global_step": 564776, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.909908652305603, "global_step": 564777, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0063295364379883, "global_step": 564778, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0217394828796387, "global_step": 564779, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0933330059051514, "global_step": 564780, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9925310611724854, "global_step": 564781, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.995339035987854, "global_step": 564782, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.077202320098877, "global_step": 564783, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.124051809310913, "global_step": 564784, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.05372953414917, "global_step": 564785, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9678584337234497, "global_step": 564786, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.079075813293457, "global_step": 564787, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9727182388305664, "global_step": 564788, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0272252559661865, "global_step": 564789, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0724778175354004, "global_step": 564790, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0234761238098145, "global_step": 564791, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9839407205581665, "global_step": 564792, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9844651222229004, "global_step": 564793, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1664891242980957, "global_step": 564794, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0264296531677246, "global_step": 564795, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0358006954193115, "global_step": 564796, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9523935317993164, "global_step": 564797, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9290220737457275, "global_step": 564798, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0862081050872803, "global_step": 564799, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0678491592407227, "global_step": 564800, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0980052947998047, "global_step": 564801, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0802459716796875, "global_step": 564802, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1684815883636475, "global_step": 564803, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0313796997070312, "global_step": 564804, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0671730041503906, "global_step": 564805, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.072838068008423, "global_step": 564806, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0595433712005615, "global_step": 564807, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0584969520568848, "global_step": 564808, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0411036014556885, "global_step": 564809, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9959279298782349, "global_step": 564810, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0283546447753906, "global_step": 564811, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0086348056793213, "global_step": 564812, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9949966669082642, "global_step": 564813, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.989446997642517, "global_step": 564814, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.060476064682007, "global_step": 564815, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0427448749542236, "global_step": 564816, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.09429931640625, "global_step": 564817, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1222524642944336, "global_step": 564818, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9779078960418701, "global_step": 564819, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.031663179397583, "global_step": 564820, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9676928520202637, "global_step": 564821, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0144619941711426, "global_step": 564822, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0156641006469727, "global_step": 564823, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9861000776290894, "global_step": 564824, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0652804374694824, "global_step": 564825, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9982281923294067, "global_step": 564826, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.080104351043701, "global_step": 564827, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0151278972625732, "global_step": 564828, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.095669984817505, "global_step": 564829, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9539881944656372, "global_step": 564830, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0239031314849854, "global_step": 564831, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0393271446228027, "global_step": 564832, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.119767665863037, "global_step": 564833, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.036055564880371, "global_step": 564834, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.995172142982483, "global_step": 564835, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0249054431915283, "global_step": 564836, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0180294513702393, "global_step": 564837, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.055508613586426, "global_step": 564838, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0113799571990967, "global_step": 564839, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9495304822921753, "global_step": 564840, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0242061614990234, "global_step": 564841, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9719947576522827, "global_step": 564842, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9591238498687744, "global_step": 564843, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.129812240600586, "global_step": 564844, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9458001852035522, "global_step": 564845, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0857088565826416, "global_step": 564846, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0125739574432373, "global_step": 564847, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0024564266204834, "global_step": 564848, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9763941764831543, "global_step": 564849, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0751798152923584, "global_step": 564850, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9856821298599243, "global_step": 564851, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9931819438934326, "global_step": 564852, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0545742511749268, "global_step": 564853, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.004227638244629, "global_step": 564854, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0726778507232666, "global_step": 564855, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.031869649887085, "global_step": 564856, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9937760829925537, "global_step": 564857, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0184905529022217, "global_step": 564858, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0969908237457275, "global_step": 564859, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.125115156173706, "global_step": 564860, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0078189373016357, "global_step": 564861, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9715592861175537, "global_step": 564862, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0103206634521484, "global_step": 564863, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9364384412765503, "global_step": 564864, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.031794786453247, "global_step": 564865, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9908270835876465, "global_step": 564866, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.136338710784912, "global_step": 564867, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9767080545425415, "global_step": 564868, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.043257474899292, "global_step": 564869, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0408525466918945, "global_step": 564870, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.068587303161621, "global_step": 564871, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0609676837921143, "global_step": 564872, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0570991039276123, "global_step": 564873, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.033555507659912, "global_step": 564874, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0504655838012695, "global_step": 564875, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0826797485351562, "global_step": 564876, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9725403785705566, "global_step": 564877, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0551981925964355, "global_step": 564878, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.064811944961548, "global_step": 564879, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0526483058929443, "global_step": 564880, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0638535022735596, "global_step": 564881, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9538036584854126, "global_step": 564882, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0628726482391357, "global_step": 564883, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.966231346130371, "global_step": 564884, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0218923091888428, "global_step": 564885, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.02665376663208, "global_step": 564886, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1307520866394043, "global_step": 564887, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0150532722473145, "global_step": 564888, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9154047966003418, "global_step": 564889, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0671212673187256, "global_step": 564890, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0593149662017822, "global_step": 564891, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9991543292999268, "global_step": 564892, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0066051483154297, "global_step": 564893, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.038170337677002, "global_step": 564894, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.064023494720459, "global_step": 564895, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0465357303619385, "global_step": 564896, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.023684501647949, "global_step": 564897, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0920157432556152, "global_step": 564898, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0271143913269043, "global_step": 564899, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9603856801986694, "global_step": 564900, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9967596530914307, "global_step": 564901, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.019082546234131, "global_step": 564902, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.022979736328125, "global_step": 564903, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0447564125061035, "global_step": 564904, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9542725086212158, "global_step": 564905, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0648140907287598, "global_step": 564906, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.036195993423462, "global_step": 564907, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0131497383117676, "global_step": 564908, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9127434492111206, "global_step": 564909, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9487959146499634, "global_step": 564910, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.053661584854126, "global_step": 564911, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0973947048187256, "global_step": 564912, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0512659549713135, "global_step": 564913, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0461559295654297, "global_step": 564914, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.074995517730713, "global_step": 564915, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0615029335021973, "global_step": 564916, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.021763324737549, "global_step": 564917, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9605846405029297, "global_step": 564918, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.027082920074463, "global_step": 564919, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.00097918510437, "global_step": 564920, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9895600080490112, "global_step": 564921, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0816431045532227, "global_step": 564922, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.091732978820801, "global_step": 564923, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0586934089660645, "global_step": 564924, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.091571092605591, "global_step": 564925, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0343620777130127, "global_step": 564926, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9452860355377197, "global_step": 564927, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9909393787384033, "global_step": 564928, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0440194606781006, "global_step": 564929, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.037726879119873, "global_step": 564930, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.086509943008423, "global_step": 564931, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.064234495162964, "global_step": 564932, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.039008140563965, "global_step": 564933, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1210803985595703, "global_step": 564934, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1481738090515137, "global_step": 564935, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.051151990890503, "global_step": 564936, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.03122878074646, "global_step": 564937, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0519673824310303, "global_step": 564938, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0504672527313232, "global_step": 564939, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.070297956466675, "global_step": 564940, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0004513263702393, "global_step": 564941, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0881645679473877, "global_step": 564942, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.06903338432312, "global_step": 564943, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.031482696533203, "global_step": 564944, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0400516986846924, "global_step": 564945, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9457749128341675, "global_step": 564946, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9691585302352905, "global_step": 564947, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1323623657226562, "global_step": 564948, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0898687839508057, "global_step": 564949, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.018521308898926, "global_step": 564950, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0890872478485107, "global_step": 564951, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.040956735610962, "global_step": 564952, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.089726686477661, "global_step": 564953, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.039412021636963, "global_step": 564954, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.945593237876892, "global_step": 564955, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9787535667419434, "global_step": 564956, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9825172424316406, "global_step": 564957, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0745277404785156, "global_step": 564958, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9903839826583862, "global_step": 564959, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.979408860206604, "global_step": 564960, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9802383184432983, "global_step": 564961, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0184032917022705, "global_step": 564962, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.994537591934204, "global_step": 564963, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.055168390274048, "global_step": 564964, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.029411554336548, "global_step": 564965, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0827250480651855, "global_step": 564966, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.077707529067993, "global_step": 564967, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0275678634643555, "global_step": 564968, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9589005708694458, "global_step": 564969, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.056614875793457, "global_step": 564970, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9893624782562256, "global_step": 564971, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9645711183547974, "global_step": 564972, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0093917846679688, "global_step": 564973, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.03078556060791, "global_step": 564974, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9329719543457031, "global_step": 564975, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0598514080047607, "global_step": 564976, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.094799280166626, "global_step": 564977, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.090111255645752, "global_step": 564978, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1305627822875977, "global_step": 564979, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0129430294036865, "global_step": 564980, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.039120674133301, "global_step": 564981, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0151021480560303, "global_step": 564982, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.049222707748413, "global_step": 564983, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0565409660339355, "global_step": 564984, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9916305541992188, "global_step": 564985, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0697779655456543, "global_step": 564986, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1332318782806396, "global_step": 564987, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9779857397079468, "global_step": 564988, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.017031192779541, "global_step": 564989, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9861012697219849, "global_step": 564990, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.048689126968384, "global_step": 564991, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0348894596099854, "global_step": 564992, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.078831195831299, "global_step": 564993, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.038019895553589, "global_step": 564994, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.083313465118408, "global_step": 564995, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9574031829833984, "global_step": 564996, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.054593563079834, "global_step": 564997, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0402209758758545, "global_step": 564998, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.023324966430664, "global_step": 564999, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0392441749572754, "global_step": 565000, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0753464698791504, "global_step": 565001, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0353665351867676, "global_step": 565002, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.978268027305603, "global_step": 565003, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9877967834472656, "global_step": 565004, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9727667570114136, "global_step": 565005, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0801525115966797, "global_step": 565006, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0971126556396484, "global_step": 565007, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0533955097198486, "global_step": 565008, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0552923679351807, "global_step": 565009, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9807138442993164, "global_step": 565010, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.054401397705078, "global_step": 565011, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.972716212272644, "global_step": 565012, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0890848636627197, "global_step": 565013, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9974210262298584, "global_step": 565014, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0333526134490967, "global_step": 565015, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0233216285705566, "global_step": 565016, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0329113006591797, "global_step": 565017, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.115669012069702, "global_step": 565018, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.096050500869751, "global_step": 565019, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0224177837371826, "global_step": 565020, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0379528999328613, "global_step": 565021, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9996616840362549, "global_step": 565022, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0014777183532715, "global_step": 565023, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.081998586654663, "global_step": 565024, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0604970455169678, "global_step": 565025, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9500445127487183, "global_step": 565026, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.050912380218506, "global_step": 565027, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1061148643493652, "global_step": 565028, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1196537017822266, "global_step": 565029, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9556939601898193, "global_step": 565030, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0441243648529053, "global_step": 565031, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.983594536781311, "global_step": 565032, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0405778884887695, "global_step": 565033, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.048088312149048, "global_step": 565034, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.8866246938705444, "global_step": 565035, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.009965419769287, "global_step": 565036, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9801942110061646, "global_step": 565037, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.081083059310913, "global_step": 565038, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0070202350616455, "global_step": 565039, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0078775882720947, "global_step": 565040, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.949209451675415, "global_step": 565041, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.1633083820343018, "global_step": 565042, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.005619764328003, "global_step": 565043, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.925065040588379, "global_step": 565044, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0972814559936523, "global_step": 565045, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0086989402770996, "global_step": 565046, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.019638776779175, "global_step": 565047, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.125293493270874, "global_step": 565048, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.051481246948242, "global_step": 565049, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0477850437164307, "global_step": 565050, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.9472819566726685, "global_step": 565051, "epoch": 932, "lr": 5e-05}
{"train_loss": 1.99275541305542, "global_step": 565052, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0828299522399902, "global_step": 565053, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.022397518157959, "global_step": 565054, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.071648597717285, "global_step": 565055, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.031672716140747, "global_step": 565056, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.076505184173584, "global_step": 565057, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.07818603515625, "global_step": 565058, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.024998188018799, "global_step": 565059, "epoch": 932, "lr": 5e-05}
{"train_loss": 2.0284183025360107, "global_step": 565060, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9851346015930176, "global_step": 565061, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.001011371612549, "global_step": 565062, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0262413024902344, "global_step": 565063, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.096071720123291, "global_step": 565064, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.969765305519104, "global_step": 565065, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0011415481567383, "global_step": 565066, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0055923461914062, "global_step": 565067, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.073871374130249, "global_step": 565068, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9575356245040894, "global_step": 565069, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.99933660030365, "global_step": 565070, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9596431255340576, "global_step": 565071, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.001378297805786, "global_step": 565072, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.08012056350708, "global_step": 565073, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9947696924209595, "global_step": 565074, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.981131672859192, "global_step": 565075, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9612793922424316, "global_step": 565076, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.039506673812866, "global_step": 565077, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0599465370178223, "global_step": 565078, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9574580192565918, "global_step": 565079, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.920569658279419, "global_step": 565080, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.031154155731201, "global_step": 565081, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9777891635894775, "global_step": 565082, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9496463537216187, "global_step": 565083, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.054812431335449, "global_step": 565084, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0847432613372803, "global_step": 565085, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0157723426818848, "global_step": 565086, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9549756050109863, "global_step": 565087, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.011829376220703, "global_step": 565088, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0593838691711426, "global_step": 565089, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.029144525527954, "global_step": 565090, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0118815898895264, "global_step": 565091, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9623174667358398, "global_step": 565092, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0353567600250244, "global_step": 565093, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9678850173950195, "global_step": 565094, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9807255268096924, "global_step": 565095, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.051529884338379, "global_step": 565096, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9849604368209839, "global_step": 565097, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.003169059753418, "global_step": 565098, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0448498725891113, "global_step": 565099, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0049469470977783, "global_step": 565100, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9222925901412964, "global_step": 565101, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.04931378364563, "global_step": 565102, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0796873569488525, "global_step": 565103, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0184013843536377, "global_step": 565104, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0242645740509033, "global_step": 565105, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.021552085876465, "global_step": 565106, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0212063789367676, "global_step": 565107, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0054566860198975, "global_step": 565108, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0228230953216553, "global_step": 565109, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9886337518692017, "global_step": 565110, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0544466972351074, "global_step": 565111, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9738796949386597, "global_step": 565112, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.966909408569336, "global_step": 565113, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.031033754348755, "global_step": 565114, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.001044273376465, "global_step": 565115, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9908918142318726, "global_step": 565116, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.047499656677246, "global_step": 565117, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9945294857025146, "global_step": 565118, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0633411407470703, "global_step": 565119, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.082819938659668, "global_step": 565120, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9330660104751587, "global_step": 565121, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0106325149536133, "global_step": 565122, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0091519355773926, "global_step": 565123, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0076377391815186, "global_step": 565124, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0464022159576416, "global_step": 565125, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.986053466796875, "global_step": 565126, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.047667980194092, "global_step": 565127, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0401976108551025, "global_step": 565128, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.016629934310913, "global_step": 565129, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0707061290740967, "global_step": 565130, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0314853191375732, "global_step": 565131, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.072733163833618, "global_step": 565132, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9933527708053589, "global_step": 565133, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9422112703323364, "global_step": 565134, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9947792291641235, "global_step": 565135, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.013176918029785, "global_step": 565136, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.968825101852417, "global_step": 565137, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.972412109375, "global_step": 565138, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9982088804244995, "global_step": 565139, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.038174867630005, "global_step": 565140, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9751232862472534, "global_step": 565141, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0001866817474365, "global_step": 565142, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9451028108596802, "global_step": 565143, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.95737624168396, "global_step": 565144, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0682976245880127, "global_step": 565145, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9892081022262573, "global_step": 565146, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9688174724578857, "global_step": 565147, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.040971040725708, "global_step": 565148, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0630061626434326, "global_step": 565149, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9809038639068604, "global_step": 565150, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.024258613586426, "global_step": 565151, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9714031219482422, "global_step": 565152, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.038836717605591, "global_step": 565153, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9550508260726929, "global_step": 565154, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.111037492752075, "global_step": 565155, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.072007417678833, "global_step": 565156, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.024078607559204, "global_step": 565157, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.091578483581543, "global_step": 565158, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0218160152435303, "global_step": 565159, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0647335052490234, "global_step": 565160, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.037503480911255, "global_step": 565161, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0261318683624268, "global_step": 565162, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9093880653381348, "global_step": 565163, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.085242509841919, "global_step": 565164, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0926401615142822, "global_step": 565165, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.036668300628662, "global_step": 565166, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0045950412750244, "global_step": 565167, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.994430422782898, "global_step": 565168, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0184969902038574, "global_step": 565169, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0465149879455566, "global_step": 565170, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.013465166091919, "global_step": 565171, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.907850980758667, "global_step": 565172, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9953508377075195, "global_step": 565173, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.05855655670166, "global_step": 565174, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9327929019927979, "global_step": 565175, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0491154193878174, "global_step": 565176, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.040527582168579, "global_step": 565177, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9933438301086426, "global_step": 565178, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.005718469619751, "global_step": 565179, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.014845371246338, "global_step": 565180, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0149333477020264, "global_step": 565181, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.037641763687134, "global_step": 565182, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0121774673461914, "global_step": 565183, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0104517936706543, "global_step": 565184, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.03456449508667, "global_step": 565185, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.998350739479065, "global_step": 565186, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1064071655273438, "global_step": 565187, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9540331363677979, "global_step": 565188, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0245378017425537, "global_step": 565189, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9793416261672974, "global_step": 565190, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0446536540985107, "global_step": 565191, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.028144359588623, "global_step": 565192, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9811513423919678, "global_step": 565193, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0594496726989746, "global_step": 565194, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9534337520599365, "global_step": 565195, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.143162965774536, "global_step": 565196, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.059699773788452, "global_step": 565197, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9437289237976074, "global_step": 565198, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9572495222091675, "global_step": 565199, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0002846717834473, "global_step": 565200, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0259642601013184, "global_step": 565201, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0142154693603516, "global_step": 565202, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.000074863433838, "global_step": 565203, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0587756633758545, "global_step": 565204, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.065035581588745, "global_step": 565205, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0339784622192383, "global_step": 565206, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.04133677482605, "global_step": 565207, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0682501792907715, "global_step": 565208, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9400321245193481, "global_step": 565209, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0585272312164307, "global_step": 565210, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9569729566574097, "global_step": 565211, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0305137634277344, "global_step": 565212, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9985450506210327, "global_step": 565213, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.041283130645752, "global_step": 565214, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.01233172416687, "global_step": 565215, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9844321012496948, "global_step": 565216, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9451113939285278, "global_step": 565217, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0894737243652344, "global_step": 565218, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.116525411605835, "global_step": 565219, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9867472648620605, "global_step": 565220, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0828354358673096, "global_step": 565221, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9890189170837402, "global_step": 565222, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9998301267623901, "global_step": 565223, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.048975706100464, "global_step": 565224, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0432004928588867, "global_step": 565225, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.084718942642212, "global_step": 565226, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.104536533355713, "global_step": 565227, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.03200626373291, "global_step": 565228, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.042095184326172, "global_step": 565229, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0635693073272705, "global_step": 565230, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.026958465576172, "global_step": 565231, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.067836284637451, "global_step": 565232, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.961179494857788, "global_step": 565233, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0095560550689697, "global_step": 565234, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0107626914978027, "global_step": 565235, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0249404907226562, "global_step": 565236, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9411152601242065, "global_step": 565237, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9792457818984985, "global_step": 565238, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.074751615524292, "global_step": 565239, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.006901979446411, "global_step": 565240, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0745837688446045, "global_step": 565241, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.082188844680786, "global_step": 565242, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0817348957061768, "global_step": 565243, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0704121589660645, "global_step": 565244, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1142210960388184, "global_step": 565245, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0270473957061768, "global_step": 565246, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0489463806152344, "global_step": 565247, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9947798252105713, "global_step": 565248, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.087047576904297, "global_step": 565249, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9523661136627197, "global_step": 565250, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.004793643951416, "global_step": 565251, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0514676570892334, "global_step": 565252, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0734527111053467, "global_step": 565253, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.03834867477417, "global_step": 565254, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.058877944946289, "global_step": 565255, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9921928644180298, "global_step": 565256, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0178062915802, "global_step": 565257, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9411060810089111, "global_step": 565258, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0544509887695312, "global_step": 565259, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.044391632080078, "global_step": 565260, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9554405212402344, "global_step": 565261, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.004563808441162, "global_step": 565262, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0040340423583984, "global_step": 565263, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0077176094055176, "global_step": 565264, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.937459945678711, "global_step": 565265, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.073925018310547, "global_step": 565266, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.033390522003174, "global_step": 565267, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.010629892349243, "global_step": 565268, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0404486656188965, "global_step": 565269, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.999753713607788, "global_step": 565270, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1011300086975098, "global_step": 565271, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0050249099731445, "global_step": 565272, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.005171060562134, "global_step": 565273, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9805585145950317, "global_step": 565274, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.044926643371582, "global_step": 565275, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0625381469726562, "global_step": 565276, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.014148235321045, "global_step": 565277, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.003138303756714, "global_step": 565278, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.998928189277649, "global_step": 565279, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0838122367858887, "global_step": 565280, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.028735876083374, "global_step": 565281, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.032228469848633, "global_step": 565282, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0108425617218018, "global_step": 565283, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9970239400863647, "global_step": 565284, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.002263069152832, "global_step": 565285, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.006505012512207, "global_step": 565286, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.953138828277588, "global_step": 565287, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9420247077941895, "global_step": 565288, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.003622531890869, "global_step": 565289, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0038297176361084, "global_step": 565290, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.134587287902832, "global_step": 565291, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0004830360412598, "global_step": 565292, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0081140995025635, "global_step": 565293, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0100202560424805, "global_step": 565294, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.947396159172058, "global_step": 565295, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.982600450515747, "global_step": 565296, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.009967803955078, "global_step": 565297, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.017075777053833, "global_step": 565298, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0496671199798584, "global_step": 565299, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0710256099700928, "global_step": 565300, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0055038928985596, "global_step": 565301, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0276718139648438, "global_step": 565302, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.030668258666992, "global_step": 565303, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9552044868469238, "global_step": 565304, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.018202304840088, "global_step": 565305, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0150113105773926, "global_step": 565306, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0750153064727783, "global_step": 565307, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9651931524276733, "global_step": 565308, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.12094783782959, "global_step": 565309, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0567691326141357, "global_step": 565310, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.006042957305908, "global_step": 565311, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0316152572631836, "global_step": 565312, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0323352813720703, "global_step": 565313, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9444223642349243, "global_step": 565314, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0461349487304688, "global_step": 565315, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0030159950256348, "global_step": 565316, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0266025066375732, "global_step": 565317, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0129175186157227, "global_step": 565318, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0241007804870605, "global_step": 565319, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0769684314727783, "global_step": 565320, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0590713024139404, "global_step": 565321, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.119704246520996, "global_step": 565322, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0172226428985596, "global_step": 565323, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.004199504852295, "global_step": 565324, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9396564960479736, "global_step": 565325, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9787696599960327, "global_step": 565326, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0520806312561035, "global_step": 565327, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9232678413391113, "global_step": 565328, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.104809045791626, "global_step": 565329, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.074502944946289, "global_step": 565330, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0764172077178955, "global_step": 565331, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.066481351852417, "global_step": 565332, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0306928157806396, "global_step": 565333, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0460522174835205, "global_step": 565334, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9753131866455078, "global_step": 565335, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.00766921043396, "global_step": 565336, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.124630928039551, "global_step": 565337, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0367724895477295, "global_step": 565338, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.023740768432617, "global_step": 565339, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9952514171600342, "global_step": 565340, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0214929580688477, "global_step": 565341, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.007728099822998, "global_step": 565342, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.013216257095337, "global_step": 565343, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.007988691329956, "global_step": 565344, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9983751773834229, "global_step": 565345, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9459404945373535, "global_step": 565346, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0185699462890625, "global_step": 565347, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9684516191482544, "global_step": 565348, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.985472559928894, "global_step": 565349, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.941074013710022, "global_step": 565350, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0477793216705322, "global_step": 565351, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9968597888946533, "global_step": 565352, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.064037799835205, "global_step": 565353, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9871045351028442, "global_step": 565354, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0142335891723633, "global_step": 565355, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.027341842651367, "global_step": 565356, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0287959575653076, "global_step": 565357, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1833081245422363, "global_step": 565358, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.063075304031372, "global_step": 565359, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1376900672912598, "global_step": 565360, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0649023056030273, "global_step": 565361, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9924513101577759, "global_step": 565362, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0242488384246826, "global_step": 565363, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9266393184661865, "global_step": 565364, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9832396507263184, "global_step": 565365, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.02276873588562, "global_step": 565366, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.995687484741211, "global_step": 565367, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.982588291168213, "global_step": 565368, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.069277763366699, "global_step": 565369, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0755555629730225, "global_step": 565370, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0484447479248047, "global_step": 565371, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0758206844329834, "global_step": 565372, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.991032600402832, "global_step": 565373, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0391845703125, "global_step": 565374, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9682351350784302, "global_step": 565375, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.039815902709961, "global_step": 565376, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0858798027038574, "global_step": 565377, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.017211675643921, "global_step": 565378, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9719696044921875, "global_step": 565379, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9825356006622314, "global_step": 565380, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.041612386703491, "global_step": 565381, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.094930648803711, "global_step": 565382, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.097144365310669, "global_step": 565383, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0073976516723633, "global_step": 565384, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.031846046447754, "global_step": 565385, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.972862958908081, "global_step": 565386, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0885138511657715, "global_step": 565387, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.007333993911743, "global_step": 565388, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.003162145614624, "global_step": 565389, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.040818214416504, "global_step": 565390, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.962808609008789, "global_step": 565391, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.982426643371582, "global_step": 565392, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0355334281921387, "global_step": 565393, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0459601879119873, "global_step": 565394, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0488996505737305, "global_step": 565395, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0098085403442383, "global_step": 565396, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.002032518386841, "global_step": 565397, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.954154372215271, "global_step": 565398, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9874184131622314, "global_step": 565399, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1117396354675293, "global_step": 565400, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9579062461853027, "global_step": 565401, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0491583347320557, "global_step": 565402, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.064770221710205, "global_step": 565403, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0951151847839355, "global_step": 565404, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9675527811050415, "global_step": 565405, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0156688690185547, "global_step": 565406, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0551364421844482, "global_step": 565407, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9551267623901367, "global_step": 565408, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9890408515930176, "global_step": 565409, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1368775367736816, "global_step": 565410, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.083280086517334, "global_step": 565411, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.009161949157715, "global_step": 565412, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0055935382843018, "global_step": 565413, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0390429496765137, "global_step": 565414, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0843029022216797, "global_step": 565415, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.014202356338501, "global_step": 565416, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9703729152679443, "global_step": 565417, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0531389713287354, "global_step": 565418, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.963428020477295, "global_step": 565419, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0052361488342285, "global_step": 565420, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.090891122817993, "global_step": 565421, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.011849880218506, "global_step": 565422, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.053980827331543, "global_step": 565423, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0379135608673096, "global_step": 565424, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.060406446456909, "global_step": 565425, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0665488243103027, "global_step": 565426, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0023207664489746, "global_step": 565427, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0703611373901367, "global_step": 565428, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0561275482177734, "global_step": 565429, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9850400686264038, "global_step": 565430, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.945157766342163, "global_step": 565431, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9675383567810059, "global_step": 565432, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.989353895187378, "global_step": 565433, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9583958387374878, "global_step": 565434, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1062705516815186, "global_step": 565435, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.015791893005371, "global_step": 565436, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9978610277175903, "global_step": 565437, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.977866530418396, "global_step": 565438, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9815670251846313, "global_step": 565439, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.123084545135498, "global_step": 565440, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.026458263397217, "global_step": 565441, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.069398880004883, "global_step": 565442, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9705344438552856, "global_step": 565443, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0259249210357666, "global_step": 565444, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0288949012756348, "global_step": 565445, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.019922971725464, "global_step": 565446, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.989235281944275, "global_step": 565447, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1082987785339355, "global_step": 565448, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0044243335723877, "global_step": 565449, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.011059045791626, "global_step": 565450, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0875205993652344, "global_step": 565451, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0572853088378906, "global_step": 565452, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0525059700012207, "global_step": 565453, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9560962915420532, "global_step": 565454, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0524611473083496, "global_step": 565455, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9697345495224, "global_step": 565456, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9757589101791382, "global_step": 565457, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.995528221130371, "global_step": 565458, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0582213401794434, "global_step": 565459, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.073516845703125, "global_step": 565460, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0817739963531494, "global_step": 565461, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0412745475769043, "global_step": 565462, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.049133062362671, "global_step": 565463, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.8963279724121094, "global_step": 565464, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.023676872253418, "global_step": 565465, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0354063510894775, "global_step": 565466, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9913603067398071, "global_step": 565467, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0532796382904053, "global_step": 565468, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1624741554260254, "global_step": 565469, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.003347158432007, "global_step": 565470, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0708298683166504, "global_step": 565471, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.074359893798828, "global_step": 565472, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9780203104019165, "global_step": 565473, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0575006008148193, "global_step": 565474, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1056525707244873, "global_step": 565475, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0061943531036377, "global_step": 565476, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1082775592803955, "global_step": 565477, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.058638572692871, "global_step": 565478, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.022153377532959, "global_step": 565479, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0508415699005127, "global_step": 565480, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0222830772399902, "global_step": 565481, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0527236461639404, "global_step": 565482, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.00943660736084, "global_step": 565483, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.014366626739502, "global_step": 565484, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.032409906387329, "global_step": 565485, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9463640451431274, "global_step": 565486, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9603931903839111, "global_step": 565487, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0351548194885254, "global_step": 565488, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9797950983047485, "global_step": 565489, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0061752796173096, "global_step": 565490, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0047495365142822, "global_step": 565491, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9988352060317993, "global_step": 565492, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.12781023979187, "global_step": 565493, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0583760738372803, "global_step": 565494, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.055695056915283, "global_step": 565495, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0924129486083984, "global_step": 565496, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.067429304122925, "global_step": 565497, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9009767770767212, "global_step": 565498, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0239386558532715, "global_step": 565499, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.028458833694458, "global_step": 565500, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0919318199157715, "global_step": 565501, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9723687171936035, "global_step": 565502, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0630500316619873, "global_step": 565503, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.075875997543335, "global_step": 565504, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0682225227355957, "global_step": 565505, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.050175428390503, "global_step": 565506, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0307719707489014, "global_step": 565507, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9718798398971558, "global_step": 565508, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.986462950706482, "global_step": 565509, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.068678855895996, "global_step": 565510, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9775524139404297, "global_step": 565511, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9926753044128418, "global_step": 565512, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0314536094665527, "global_step": 565513, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9572430849075317, "global_step": 565514, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1045610904693604, "global_step": 565515, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0652239322662354, "global_step": 565516, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0068094730377197, "global_step": 565517, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0890262126922607, "global_step": 565518, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9892711639404297, "global_step": 565519, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0937271118164062, "global_step": 565520, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.112128973007202, "global_step": 565521, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0799567699432373, "global_step": 565522, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0100319385528564, "global_step": 565523, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.065885543823242, "global_step": 565524, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0067241191864014, "global_step": 565525, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0145063400268555, "global_step": 565526, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9380098581314087, "global_step": 565527, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0145668983459473, "global_step": 565528, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.010672092437744, "global_step": 565529, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.018723726272583, "global_step": 565530, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0215516090393066, "global_step": 565531, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.974565029144287, "global_step": 565532, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.006775379180908, "global_step": 565533, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0144147872924805, "global_step": 565534, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0294981002807617, "global_step": 565535, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0635135173797607, "global_step": 565536, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.10782790184021, "global_step": 565537, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0028884410858154, "global_step": 565538, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9625084400177002, "global_step": 565539, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9607532024383545, "global_step": 565540, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.991288661956787, "global_step": 565541, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0050628185272217, "global_step": 565542, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9753848314285278, "global_step": 565543, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.007639169692993, "global_step": 565544, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.005913257598877, "global_step": 565545, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.005258083343506, "global_step": 565546, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.007735252380371, "global_step": 565547, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.086294174194336, "global_step": 565548, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9962117671966553, "global_step": 565549, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.036414384841919, "global_step": 565550, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.019925117492676, "global_step": 565551, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.086832046508789, "global_step": 565552, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0519449710845947, "global_step": 565553, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0383291244506836, "global_step": 565554, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9987365007400513, "global_step": 565555, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0535671710968018, "global_step": 565556, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0359342098236084, "global_step": 565557, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0395925045013428, "global_step": 565558, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0140178203582764, "global_step": 565559, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0169146060943604, "global_step": 565560, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.002824544906616, "global_step": 565561, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.98475980758667, "global_step": 565562, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0543885231018066, "global_step": 565563, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9984092712402344, "global_step": 565564, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0689632892608643, "global_step": 565565, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9350947141647339, "global_step": 565566, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0044126510620117, "global_step": 565567, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1157734394073486, "global_step": 565568, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.01562237739563, "global_step": 565569, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9546493291854858, "global_step": 565570, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9738723039627075, "global_step": 565571, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9846712350845337, "global_step": 565572, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.023895263671875, "global_step": 565573, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9816700220108032, "global_step": 565574, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9561662673950195, "global_step": 565575, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9505137205123901, "global_step": 565576, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.01716685295105, "global_step": 565577, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.050474166870117, "global_step": 565578, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9960135221481323, "global_step": 565579, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9927136898040771, "global_step": 565580, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9883246421813965, "global_step": 565581, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9997920989990234, "global_step": 565582, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.970206618309021, "global_step": 565583, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1365222930908203, "global_step": 565584, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9951245784759521, "global_step": 565585, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0290920734405518, "global_step": 565586, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0524282455444336, "global_step": 565587, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.035069465637207, "global_step": 565588, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0433926582336426, "global_step": 565589, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.058645725250244, "global_step": 565590, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9589180946350098, "global_step": 565591, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0922834873199463, "global_step": 565592, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.012281894683838, "global_step": 565593, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9989056587219238, "global_step": 565594, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.083909749984741, "global_step": 565595, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0999529361724854, "global_step": 565596, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0335566997528076, "global_step": 565597, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9999319314956665, "global_step": 565598, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.050509452819824, "global_step": 565599, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.960705041885376, "global_step": 565600, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0929501056671143, "global_step": 565601, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.013742685317993, "global_step": 565602, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.09017276763916, "global_step": 565603, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0236897468566895, "global_step": 565604, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1110212802886963, "global_step": 565605, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9919095039367676, "global_step": 565606, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9634099006652832, "global_step": 565607, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1002769470214844, "global_step": 565608, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0559885501861572, "global_step": 565609, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.122891426086426, "global_step": 565610, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0236315727233887, "global_step": 565611, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.033708095550537, "global_step": 565612, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0936968326568604, "global_step": 565613, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0327069759368896, "global_step": 565614, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0331826210021973, "global_step": 565615, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.033313512802124, "global_step": 565616, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0766656398773193, "global_step": 565617, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0882699489593506, "global_step": 565618, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9794925451278687, "global_step": 565619, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9310827255249023, "global_step": 565620, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9429705142974854, "global_step": 565621, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.982265830039978, "global_step": 565622, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0660040378570557, "global_step": 565623, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.000258207321167, "global_step": 565624, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0685997009277344, "global_step": 565625, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0059053897857666, "global_step": 565626, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.072084665298462, "global_step": 565627, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0373144149780273, "global_step": 565628, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0056192874908447, "global_step": 565629, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.987661361694336, "global_step": 565630, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.003300189971924, "global_step": 565631, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1279358863830566, "global_step": 565632, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.943374752998352, "global_step": 565633, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0026752948760986, "global_step": 565634, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1568219661712646, "global_step": 565635, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1114678382873535, "global_step": 565636, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9961519241333008, "global_step": 565637, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0610263347625732, "global_step": 565638, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.013873815536499, "global_step": 565639, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.019970655441284, "global_step": 565640, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.022416830062866, "global_step": 565641, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.92733895778656, "global_step": 565642, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0265491008758545, "global_step": 565643, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0649631023406982, "global_step": 565644, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9934455156326294, "global_step": 565645, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0547876358032227, "global_step": 565646, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.009166955947876, "global_step": 565647, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.065969705581665, "global_step": 565648, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.956952452659607, "global_step": 565649, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.080998659133911, "global_step": 565650, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9813357591629028, "global_step": 565651, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0188701152801514, "global_step": 565652, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9768112897872925, "global_step": 565653, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9649019241333008, "global_step": 565654, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0256595611572266, "global_step": 565655, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9833711385726929, "global_step": 565656, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0256521701812744, "global_step": 565657, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9396694898605347, "global_step": 565658, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0226306915283203, "global_step": 565659, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0514168739318848, "global_step": 565660, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.008531093597412, "global_step": 565661, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.007734537124634, "global_step": 565662, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0733916759490967, "global_step": 565663, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9848159551620483, "global_step": 565664, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0563433170318604, "global_step": 565665, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9906421899795532, "global_step": 565666, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0174670219421387, "global_step": 565667, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9862589836120605, "global_step": 565668, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9904568195343018, "global_step": 565669, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1026792526245117, "global_step": 565670, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1211376190185547, "global_step": 565671, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.023002862930298, "global_step": 565672, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0561153888702393, "global_step": 565673, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.011765241622925, "global_step": 565674, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.075751543045044, "global_step": 565675, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0211477279663086, "global_step": 565676, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9436410665512085, "global_step": 565677, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.087611675262451, "global_step": 565678, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.070143461227417, "global_step": 565679, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9510712623596191, "global_step": 565680, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.070291757583618, "global_step": 565681, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0929462909698486, "global_step": 565682, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.038332462310791, "global_step": 565683, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.048661231994629, "global_step": 565684, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9935650825500488, "global_step": 565685, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9662034511566162, "global_step": 565686, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9321173429489136, "global_step": 565687, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0729305744171143, "global_step": 565688, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0929572582244873, "global_step": 565689, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0713717937469482, "global_step": 565690, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.006239414215088, "global_step": 565691, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1323585510253906, "global_step": 565692, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.988558053970337, "global_step": 565693, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0753695964813232, "global_step": 565694, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0043721199035645, "global_step": 565695, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9694209098815918, "global_step": 565696, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.055473804473877, "global_step": 565697, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9723179340362549, "global_step": 565698, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1026015281677246, "global_step": 565699, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.119934558868408, "global_step": 565700, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.051255464553833, "global_step": 565701, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.019253730773926, "global_step": 565702, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9861973524093628, "global_step": 565703, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.953609585762024, "global_step": 565704, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.037249803543091, "global_step": 565705, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9773515462875366, "global_step": 565706, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0506815910339355, "global_step": 565707, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9957249164581299, "global_step": 565708, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.022815465927124, "global_step": 565709, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0434606075286865, "global_step": 565710, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9899837970733643, "global_step": 565711, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9953970909118652, "global_step": 565712, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0015358924865723, "global_step": 565713, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0000956058502197, "global_step": 565714, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0912985801696777, "global_step": 565715, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9822789430618286, "global_step": 565716, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0357630252838135, "global_step": 565717, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9767663478851318, "global_step": 565718, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9543981552124023, "global_step": 565719, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.013951301574707, "global_step": 565720, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.962900996208191, "global_step": 565721, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0365958213806152, "global_step": 565722, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.071345806121826, "global_step": 565723, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9810049533843994, "global_step": 565724, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0307376384735107, "global_step": 565725, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0534145832061768, "global_step": 565726, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0495822429656982, "global_step": 565727, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9848512411117554, "global_step": 565728, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0484817028045654, "global_step": 565729, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0349936485290527, "global_step": 565730, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9224143028259277, "global_step": 565731, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0342721939086914, "global_step": 565732, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0057806968688965, "global_step": 565733, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.063936948776245, "global_step": 565734, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.007493734359741, "global_step": 565735, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9463701248168945, "global_step": 565736, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.997230052947998, "global_step": 565737, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9535133838653564, "global_step": 565738, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0952401161193848, "global_step": 565739, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0638720989227295, "global_step": 565740, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.062265396118164, "global_step": 565741, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0681369304656982, "global_step": 565742, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0000507831573486, "global_step": 565743, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.8837302923202515, "global_step": 565744, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0513412952423096, "global_step": 565745, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.002831220626831, "global_step": 565746, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.994511365890503, "global_step": 565747, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.951926589012146, "global_step": 565748, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9963626861572266, "global_step": 565749, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.976520299911499, "global_step": 565750, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.063655138015747, "global_step": 565751, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.016737699508667, "global_step": 565752, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.057631492614746, "global_step": 565753, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.014885663986206, "global_step": 565754, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0486044883728027, "global_step": 565755, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1109297275543213, "global_step": 565756, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0091681480407715, "global_step": 565757, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.007874011993408, "global_step": 565758, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0637447834014893, "global_step": 565759, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9797030687332153, "global_step": 565760, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9778022766113281, "global_step": 565761, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0748419761657715, "global_step": 565762, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9751156568527222, "global_step": 565763, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9279087781906128, "global_step": 565764, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.060633897781372, "global_step": 565765, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.997213363647461, "global_step": 565766, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.057255268096924, "global_step": 565767, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.052886962890625, "global_step": 565768, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9875411987304688, "global_step": 565769, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0401663780212402, "global_step": 565770, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.004525899887085, "global_step": 565771, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0839099884033203, "global_step": 565772, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0353498458862305, "global_step": 565773, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0562026500701904, "global_step": 565774, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.010759115219116, "global_step": 565775, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.015867233276367, "global_step": 565776, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0264086723327637, "global_step": 565777, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1296684741973877, "global_step": 565778, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.029916286468506, "global_step": 565779, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0452427864074707, "global_step": 565780, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.068727731704712, "global_step": 565781, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0235800743103027, "global_step": 565782, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9620707035064697, "global_step": 565783, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.030088424682617, "global_step": 565784, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.021703004837036, "global_step": 565785, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0347840785980225, "global_step": 565786, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.06158185005188, "global_step": 565787, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.063793420791626, "global_step": 565788, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.050504446029663, "global_step": 565789, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0945162773132324, "global_step": 565790, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0403811931610107, "global_step": 565791, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0835371017456055, "global_step": 565792, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0010387897491455, "global_step": 565793, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.00876784324646, "global_step": 565794, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0275015830993652, "global_step": 565795, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9546486139297485, "global_step": 565796, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0011417865753174, "global_step": 565797, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.000819683074951, "global_step": 565798, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.015974283218384, "global_step": 565799, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9983322620391846, "global_step": 565800, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.007580041885376, "global_step": 565801, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.032212734222412, "global_step": 565802, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9584163427352905, "global_step": 565803, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9605445861816406, "global_step": 565804, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0982847213745117, "global_step": 565805, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.051352024078369, "global_step": 565806, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.046834707260132, "global_step": 565807, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.93376624584198, "global_step": 565808, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9595948457717896, "global_step": 565809, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0388569831848145, "global_step": 565810, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0225918292999268, "global_step": 565811, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.981571912765503, "global_step": 565812, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.956291675567627, "global_step": 565813, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.025620222091675, "global_step": 565814, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.027399778366089, "global_step": 565815, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9953062534332275, "global_step": 565816, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.057720899581909, "global_step": 565817, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9269245862960815, "global_step": 565818, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9818791151046753, "global_step": 565819, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.013543128967285, "global_step": 565820, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9089844226837158, "global_step": 565821, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9975813627243042, "global_step": 565822, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9997478723526, "global_step": 565823, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.945757508277893, "global_step": 565824, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9705767631530762, "global_step": 565825, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0447874069213867, "global_step": 565826, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0953574180603027, "global_step": 565827, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0389420986175537, "global_step": 565828, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9557747840881348, "global_step": 565829, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9585803747177124, "global_step": 565830, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0357401371002197, "global_step": 565831, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.060091018676758, "global_step": 565832, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.94700026512146, "global_step": 565833, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.125805616378784, "global_step": 565834, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0999393463134766, "global_step": 565835, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.025952100753784, "global_step": 565836, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9491580724716187, "global_step": 565837, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.01896595954895, "global_step": 565838, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.058448553085327, "global_step": 565839, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.900868535041809, "global_step": 565840, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0500986576080322, "global_step": 565841, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.924380898475647, "global_step": 565842, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.005831480026245, "global_step": 565843, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.039463520050049, "global_step": 565844, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.159219741821289, "global_step": 565845, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0484652519226074, "global_step": 565846, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9753628969192505, "global_step": 565847, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0562283992767334, "global_step": 565848, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0408105850219727, "global_step": 565849, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.990038514137268, "global_step": 565850, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0194077491760254, "global_step": 565851, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0584988594055176, "global_step": 565852, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.113447427749634, "global_step": 565853, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9882220029830933, "global_step": 565854, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0442330837249756, "global_step": 565855, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.081631898880005, "global_step": 565856, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.041656732559204, "global_step": 565857, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.132054328918457, "global_step": 565858, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0039851665496826, "global_step": 565859, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.027430295944214, "global_step": 565860, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.064251184463501, "global_step": 565861, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.036534547805786, "global_step": 565862, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.113765001296997, "global_step": 565863, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9829013347625732, "global_step": 565864, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0053093433380127, "global_step": 565865, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0430915355682373, "global_step": 565866, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0420782566070557, "global_step": 565867, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0374550819396973, "global_step": 565868, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0577285289764404, "global_step": 565869, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.057835102081299, "global_step": 565870, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9942307472229004, "global_step": 565871, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.99690580368042, "global_step": 565872, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.141674757003784, "global_step": 565873, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9590001106262207, "global_step": 565874, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0512313842773438, "global_step": 565875, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0106494426727295, "global_step": 565876, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9781670570373535, "global_step": 565877, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.013141632080078, "global_step": 565878, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0244765281677246, "global_step": 565879, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.032851457595825, "global_step": 565880, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0969042778015137, "global_step": 565881, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9806413650512695, "global_step": 565882, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0782341957092285, "global_step": 565883, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0081372261047363, "global_step": 565884, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.062094211578369, "global_step": 565885, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.07131290435791, "global_step": 565886, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.086488723754883, "global_step": 565887, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0228559970855713, "global_step": 565888, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.061342477798462, "global_step": 565889, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.007654905319214, "global_step": 565890, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0663533210754395, "global_step": 565891, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0258915424346924, "global_step": 565892, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9221510887145996, "global_step": 565893, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.002542495727539, "global_step": 565894, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.053273916244507, "global_step": 565895, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0450363159179688, "global_step": 565896, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9114220142364502, "global_step": 565897, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9565298557281494, "global_step": 565898, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.054624080657959, "global_step": 565899, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9913609027862549, "global_step": 565900, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9609326124191284, "global_step": 565901, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0229406356811523, "global_step": 565902, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0686793327331543, "global_step": 565903, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0708072185516357, "global_step": 565904, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.061147451400757, "global_step": 565905, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1092841625213623, "global_step": 565906, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.043494701385498, "global_step": 565907, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9877251386642456, "global_step": 565908, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.094057083129883, "global_step": 565909, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.070502758026123, "global_step": 565910, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.973849892616272, "global_step": 565911, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.088073492050171, "global_step": 565912, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0993733406066895, "global_step": 565913, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.088136672973633, "global_step": 565914, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.962701439857483, "global_step": 565915, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.095080614089966, "global_step": 565916, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.044693946838379, "global_step": 565917, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.111759662628174, "global_step": 565918, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0399954319000244, "global_step": 565919, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0986852645874023, "global_step": 565920, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0143814086914062, "global_step": 565921, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.118006706237793, "global_step": 565922, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.044055461883545, "global_step": 565923, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0077192783355713, "global_step": 565924, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.007746458053589, "global_step": 565925, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0613157749176025, "global_step": 565926, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1192944049835205, "global_step": 565927, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.064178943634033, "global_step": 565928, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9767277240753174, "global_step": 565929, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0057899951934814, "global_step": 565930, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1013519763946533, "global_step": 565931, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9973273277282715, "global_step": 565932, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9615371227264404, "global_step": 565933, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0474047660827637, "global_step": 565934, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9773262739181519, "global_step": 565935, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.95029616355896, "global_step": 565936, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9807379245758057, "global_step": 565937, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0038857460021973, "global_step": 565938, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9839458465576172, "global_step": 565939, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0282514095306396, "global_step": 565940, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.027371644973755, "global_step": 565941, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0740365982055664, "global_step": 565942, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9295496940612793, "global_step": 565943, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.038708448410034, "global_step": 565944, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.052708625793457, "global_step": 565945, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0142722129821777, "global_step": 565946, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.979115605354309, "global_step": 565947, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0234932899475098, "global_step": 565948, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0433881282806396, "global_step": 565949, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.062859058380127, "global_step": 565950, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9777073860168457, "global_step": 565951, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9972306489944458, "global_step": 565952, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9691636562347412, "global_step": 565953, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9651479721069336, "global_step": 565954, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9946630001068115, "global_step": 565955, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0335841178894043, "global_step": 565956, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0674495697021484, "global_step": 565957, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0373337268829346, "global_step": 565958, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.057904005050659, "global_step": 565959, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0263216495513916, "global_step": 565960, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0808422565460205, "global_step": 565961, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.960715889930725, "global_step": 565962, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0024845600128174, "global_step": 565963, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.106329917907715, "global_step": 565964, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0019900798797607, "global_step": 565965, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.024365186691284, "global_step": 565966, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0546462535858154, "global_step": 565967, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0796215534210205, "global_step": 565968, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0678904056549072, "global_step": 565969, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.008636474609375, "global_step": 565970, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.026024103164673, "global_step": 565971, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.007699489593506, "global_step": 565972, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.078991651535034, "global_step": 565973, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.061026096343994, "global_step": 565974, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.029538154602051, "global_step": 565975, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.060772180557251, "global_step": 565976, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.087948799133301, "global_step": 565977, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.022228956222534, "global_step": 565978, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0859599113464355, "global_step": 565979, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9658923149108887, "global_step": 565980, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.071040391921997, "global_step": 565981, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9932000637054443, "global_step": 565982, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0513715744018555, "global_step": 565983, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9970166683197021, "global_step": 565984, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.040740966796875, "global_step": 565985, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.056558847427368, "global_step": 565986, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9794448614120483, "global_step": 565987, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9829192161560059, "global_step": 565988, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1078567504882812, "global_step": 565989, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.009902000427246, "global_step": 565990, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0782129764556885, "global_step": 565991, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0230696201324463, "global_step": 565992, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.984139323234558, "global_step": 565993, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0447230339050293, "global_step": 565994, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.022892475128174, "global_step": 565995, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0922234058380127, "global_step": 565996, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0368285179138184, "global_step": 565997, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0959126949310303, "global_step": 565998, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1594455242156982, "global_step": 565999, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9911490678787231, "global_step": 566000, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0457234382629395, "global_step": 566001, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.028076648712158, "global_step": 566002, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.998937726020813, "global_step": 566003, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.065704107284546, "global_step": 566004, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.068634510040283, "global_step": 566005, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0269813537597656, "global_step": 566006, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9998719692230225, "global_step": 566007, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.094613552093506, "global_step": 566008, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.888146996498108, "global_step": 566009, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0493667125701904, "global_step": 566010, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.023425817489624, "global_step": 566011, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0100948810577393, "global_step": 566012, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0364890098571777, "global_step": 566013, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.009983777999878, "global_step": 566014, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0029401779174805, "global_step": 566015, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0611777305603027, "global_step": 566016, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1421456336975098, "global_step": 566017, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.006842851638794, "global_step": 566018, "epoch": 933, "lr": 5e-05}
{"train_loss": 1.9805700778961182, "global_step": 566019, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.149996042251587, "global_step": 566020, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.042586088180542, "global_step": 566021, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.11275577545166, "global_step": 566022, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.1371898651123047, "global_step": 566023, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0933847427368164, "global_step": 566024, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.011159896850586, "global_step": 566025, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.044312000274658, "global_step": 566026, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0024285316467285, "global_step": 566027, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0245814323425293, "global_step": 566028, "epoch": 933, "lr": 5e-05}
{"train_loss": 2.0038089752197266, "global_step": 566029, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0048060417175293, "global_step": 566030, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0034964084625244, "global_step": 566031, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9923851490020752, "global_step": 566032, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0628697872161865, "global_step": 566033, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.037813425064087, "global_step": 566034, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0028741359710693, "global_step": 566035, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9643360376358032, "global_step": 566036, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9637961387634277, "global_step": 566037, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0033180713653564, "global_step": 566038, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.936169981956482, "global_step": 566039, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9221817255020142, "global_step": 566040, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0394699573516846, "global_step": 566041, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.058133602142334, "global_step": 566042, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9098488092422485, "global_step": 566043, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.017136335372925, "global_step": 566044, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9734125137329102, "global_step": 566045, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.068310022354126, "global_step": 566046, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.8804887533187866, "global_step": 566047, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.087010622024536, "global_step": 566048, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9665675163269043, "global_step": 566049, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0789365768432617, "global_step": 566050, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9974451065063477, "global_step": 566051, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9802899360656738, "global_step": 566052, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0272834300994873, "global_step": 566053, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9028815031051636, "global_step": 566054, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.091712236404419, "global_step": 566055, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0492382049560547, "global_step": 566056, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9988932609558105, "global_step": 566057, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9522464275360107, "global_step": 566058, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.990082859992981, "global_step": 566059, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.039675712585449, "global_step": 566060, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0243873596191406, "global_step": 566061, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.066622495651245, "global_step": 566062, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.086834669113159, "global_step": 566063, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.083184242248535, "global_step": 566064, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.95609450340271, "global_step": 566065, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.011913299560547, "global_step": 566066, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0089221000671387, "global_step": 566067, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9932193756103516, "global_step": 566068, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.911745309829712, "global_step": 566069, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.030122995376587, "global_step": 566070, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9835257530212402, "global_step": 566071, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0096659660339355, "global_step": 566072, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.085935592651367, "global_step": 566073, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.022509813308716, "global_step": 566074, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9718509912490845, "global_step": 566075, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0783910751342773, "global_step": 566076, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0496864318847656, "global_step": 566077, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1138243675231934, "global_step": 566078, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0715975761413574, "global_step": 566079, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9535112380981445, "global_step": 566080, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0003550052642822, "global_step": 566081, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.017679214477539, "global_step": 566082, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0703985691070557, "global_step": 566083, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9833130836486816, "global_step": 566084, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.141680955886841, "global_step": 566085, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.020437479019165, "global_step": 566086, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.029715061187744, "global_step": 566087, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9213577508926392, "global_step": 566088, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0223162174224854, "global_step": 566089, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9838436841964722, "global_step": 566090, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9979017972946167, "global_step": 566091, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0462915897369385, "global_step": 566092, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9851902723312378, "global_step": 566093, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9302351474761963, "global_step": 566094, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.117971897125244, "global_step": 566095, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1213550567626953, "global_step": 566096, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.003790855407715, "global_step": 566097, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.065563201904297, "global_step": 566098, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.073152542114258, "global_step": 566099, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.083904504776001, "global_step": 566100, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0264134407043457, "global_step": 566101, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0246996879577637, "global_step": 566102, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9902445077896118, "global_step": 566103, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1034884452819824, "global_step": 566104, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9826031923294067, "global_step": 566105, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0137581825256348, "global_step": 566106, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0259451866149902, "global_step": 566107, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0474984645843506, "global_step": 566108, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1087772846221924, "global_step": 566109, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0760257244110107, "global_step": 566110, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0603489875793457, "global_step": 566111, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0738580226898193, "global_step": 566112, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.167313575744629, "global_step": 566113, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.017911911010742, "global_step": 566114, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9904319047927856, "global_step": 566115, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0227887630462646, "global_step": 566116, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0062637329101562, "global_step": 566117, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.070885181427002, "global_step": 566118, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.096555233001709, "global_step": 566119, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9623208045959473, "global_step": 566120, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0844051837921143, "global_step": 566121, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.959795594215393, "global_step": 566122, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9475539922714233, "global_step": 566123, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0309083461761475, "global_step": 566124, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1045212745666504, "global_step": 566125, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0792815685272217, "global_step": 566126, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.987729787826538, "global_step": 566127, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0397748947143555, "global_step": 566128, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0470283031463623, "global_step": 566129, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9601969718933105, "global_step": 566130, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.049431562423706, "global_step": 566131, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.04384183883667, "global_step": 566132, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.067939281463623, "global_step": 566133, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9742496013641357, "global_step": 566134, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9229236841201782, "global_step": 566135, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.951112985610962, "global_step": 566136, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0283701419830322, "global_step": 566137, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9940309524536133, "global_step": 566138, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.899438500404358, "global_step": 566139, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9565682411193848, "global_step": 566140, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.125246047973633, "global_step": 566141, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.999513864517212, "global_step": 566142, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9794297218322754, "global_step": 566143, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0892510414123535, "global_step": 566144, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.006009101867676, "global_step": 566145, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9981393814086914, "global_step": 566146, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0209555625915527, "global_step": 566147, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.045827627182007, "global_step": 566148, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.043773651123047, "global_step": 566149, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0007355213165283, "global_step": 566150, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.019423007965088, "global_step": 566151, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9706250429153442, "global_step": 566152, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0299558639526367, "global_step": 566153, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9742258787155151, "global_step": 566154, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0745790004730225, "global_step": 566155, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9773800373077393, "global_step": 566156, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.967543363571167, "global_step": 566157, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9854607582092285, "global_step": 566158, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9456063508987427, "global_step": 566159, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.057899236679077, "global_step": 566160, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9905027151107788, "global_step": 566161, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0319509506225586, "global_step": 566162, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.955366849899292, "global_step": 566163, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1883254051208496, "global_step": 566164, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.021892547607422, "global_step": 566165, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9670333862304688, "global_step": 566166, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0037355422973633, "global_step": 566167, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0569772720336914, "global_step": 566168, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9819777011871338, "global_step": 566169, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0421910285949707, "global_step": 566170, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0775866508483887, "global_step": 566171, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.061227560043335, "global_step": 566172, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.998238205909729, "global_step": 566173, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0321338176727295, "global_step": 566174, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0687198638916016, "global_step": 566175, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.071974515914917, "global_step": 566176, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.048182249069214, "global_step": 566177, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.036259889602661, "global_step": 566178, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0644283294677734, "global_step": 566179, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1536335945129395, "global_step": 566180, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0446810722351074, "global_step": 566181, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9994503259658813, "global_step": 566182, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.077777147293091, "global_step": 566183, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.024909496307373, "global_step": 566184, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9638969898223877, "global_step": 566185, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.927234411239624, "global_step": 566186, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.036850690841675, "global_step": 566187, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.94485604763031, "global_step": 566188, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.07460880279541, "global_step": 566189, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.015357732772827, "global_step": 566190, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0414609909057617, "global_step": 566191, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9996685981750488, "global_step": 566192, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.057584047317505, "global_step": 566193, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0362963676452637, "global_step": 566194, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.067007064819336, "global_step": 566195, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9574754238128662, "global_step": 566196, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0589756965637207, "global_step": 566197, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.061189889907837, "global_step": 566198, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.062238931655884, "global_step": 566199, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9660545587539673, "global_step": 566200, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.08235502243042, "global_step": 566201, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9446611404418945, "global_step": 566202, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.950125813484192, "global_step": 566203, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0290675163269043, "global_step": 566204, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1130268573760986, "global_step": 566205, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9701058864593506, "global_step": 566206, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.953963041305542, "global_step": 566207, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0016515254974365, "global_step": 566208, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0803582668304443, "global_step": 566209, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0198845863342285, "global_step": 566210, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.116027593612671, "global_step": 566211, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.038238286972046, "global_step": 566212, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9283599853515625, "global_step": 566213, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9719411134719849, "global_step": 566214, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.075894832611084, "global_step": 566215, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0895612239837646, "global_step": 566216, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0495831966400146, "global_step": 566217, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.002058744430542, "global_step": 566218, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9628876447677612, "global_step": 566219, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.02228045463562, "global_step": 566220, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0434670448303223, "global_step": 566221, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0369091033935547, "global_step": 566222, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.147491693496704, "global_step": 566223, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.053184986114502, "global_step": 566224, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0399553775787354, "global_step": 566225, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9639500379562378, "global_step": 566226, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.008657932281494, "global_step": 566227, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9935123920440674, "global_step": 566228, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.007509708404541, "global_step": 566229, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0192768573760986, "global_step": 566230, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.045647382736206, "global_step": 566231, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9106998443603516, "global_step": 566232, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0712499618530273, "global_step": 566233, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.075026750564575, "global_step": 566234, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0429158210754395, "global_step": 566235, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0229201316833496, "global_step": 566236, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.006718397140503, "global_step": 566237, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.051387071609497, "global_step": 566238, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9829624891281128, "global_step": 566239, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.074429750442505, "global_step": 566240, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0390784740448, "global_step": 566241, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.970104694366455, "global_step": 566242, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9458308219909668, "global_step": 566243, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9590225219726562, "global_step": 566244, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9993388652801514, "global_step": 566245, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.015878200531006, "global_step": 566246, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.040581703186035, "global_step": 566247, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.034512996673584, "global_step": 566248, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9897576570510864, "global_step": 566249, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0016286373138428, "global_step": 566250, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9703770875930786, "global_step": 566251, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9304991960525513, "global_step": 566252, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.955421805381775, "global_step": 566253, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.05767560005188, "global_step": 566254, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0271401405334473, "global_step": 566255, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0621039867401123, "global_step": 566256, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9885858297348022, "global_step": 566257, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0291907787323, "global_step": 566258, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.038179874420166, "global_step": 566259, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.072277545928955, "global_step": 566260, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.072873830795288, "global_step": 566261, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0695993900299072, "global_step": 566262, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.043787956237793, "global_step": 566263, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9809304475784302, "global_step": 566264, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0063464641571045, "global_step": 566265, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9890788793563843, "global_step": 566266, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9158998727798462, "global_step": 566267, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.070415735244751, "global_step": 566268, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9687364101409912, "global_step": 566269, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.03214430809021, "global_step": 566270, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.080724000930786, "global_step": 566271, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0289254188537598, "global_step": 566272, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0217936038970947, "global_step": 566273, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9844833612442017, "global_step": 566274, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1048545837402344, "global_step": 566275, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.083484172821045, "global_step": 566276, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9757388830184937, "global_step": 566277, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.977570652961731, "global_step": 566278, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0658626556396484, "global_step": 566279, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9727987051010132, "global_step": 566280, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9674932956695557, "global_step": 566281, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.018756628036499, "global_step": 566282, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9686295986175537, "global_step": 566283, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9252698421478271, "global_step": 566284, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1039440631866455, "global_step": 566285, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.168745994567871, "global_step": 566286, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0055058002471924, "global_step": 566287, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9310661554336548, "global_step": 566288, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.975685477256775, "global_step": 566289, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9970145225524902, "global_step": 566290, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0121090412139893, "global_step": 566291, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0322163105010986, "global_step": 566292, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9263012409210205, "global_step": 566293, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0229737758636475, "global_step": 566294, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9774284362792969, "global_step": 566295, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.959709644317627, "global_step": 566296, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.074277639389038, "global_step": 566297, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0552663803100586, "global_step": 566298, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0076558589935303, "global_step": 566299, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1521098613739014, "global_step": 566300, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.056230306625366, "global_step": 566301, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.084444761276245, "global_step": 566302, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9555948972702026, "global_step": 566303, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0267088413238525, "global_step": 566304, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9902435541152954, "global_step": 566305, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0434701442718506, "global_step": 566306, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.022042989730835, "global_step": 566307, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0744426250457764, "global_step": 566308, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.075117588043213, "global_step": 566309, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9834473133087158, "global_step": 566310, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0724663734436035, "global_step": 566311, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.055950880050659, "global_step": 566312, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.05596661567688, "global_step": 566313, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1204519271850586, "global_step": 566314, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0528581142425537, "global_step": 566315, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.950377345085144, "global_step": 566316, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0236387252807617, "global_step": 566317, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9437001943588257, "global_step": 566318, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0237081050872803, "global_step": 566319, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.084590435028076, "global_step": 566320, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.075099468231201, "global_step": 566321, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9656257629394531, "global_step": 566322, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0127787590026855, "global_step": 566323, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.028151750564575, "global_step": 566324, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.091338872909546, "global_step": 566325, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0555214881896973, "global_step": 566326, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.002403736114502, "global_step": 566327, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0687062740325928, "global_step": 566328, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0107533931732178, "global_step": 566329, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0252461433410645, "global_step": 566330, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9772132635116577, "global_step": 566331, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0683393478393555, "global_step": 566332, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.931296467781067, "global_step": 566333, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1009268760681152, "global_step": 566334, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.055234670639038, "global_step": 566335, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.078554391860962, "global_step": 566336, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9863059520721436, "global_step": 566337, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9044891595840454, "global_step": 566338, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0489983558654785, "global_step": 566339, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9852817058563232, "global_step": 566340, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9716547727584839, "global_step": 566341, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0167317390441895, "global_step": 566342, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.983185052871704, "global_step": 566343, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0287396907806396, "global_step": 566344, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.062843084335327, "global_step": 566345, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9472243785858154, "global_step": 566346, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.013925552368164, "global_step": 566347, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0258069038391113, "global_step": 566348, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0376667976379395, "global_step": 566349, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0331194400787354, "global_step": 566350, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.037757158279419, "global_step": 566351, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0862324237823486, "global_step": 566352, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.028193473815918, "global_step": 566353, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0906949043273926, "global_step": 566354, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0466835498809814, "global_step": 566355, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0789883136749268, "global_step": 566356, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0533580780029297, "global_step": 566357, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.060504674911499, "global_step": 566358, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9967519044876099, "global_step": 566359, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0855836868286133, "global_step": 566360, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.063159942626953, "global_step": 566361, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0284087657928467, "global_step": 566362, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.017810106277466, "global_step": 566363, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1450908184051514, "global_step": 566364, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.053011655807495, "global_step": 566365, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9902280569076538, "global_step": 566366, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0665855407714844, "global_step": 566367, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9904903173446655, "global_step": 566368, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9881255626678467, "global_step": 566369, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.080854654312134, "global_step": 566370, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.971798300743103, "global_step": 566371, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.076967477798462, "global_step": 566372, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.077622175216675, "global_step": 566373, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.135371208190918, "global_step": 566374, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9690698385238647, "global_step": 566375, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0243160724639893, "global_step": 566376, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0016567707061768, "global_step": 566377, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0218698978424072, "global_step": 566378, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9969033002853394, "global_step": 566379, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.06386399269104, "global_step": 566380, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9697681665420532, "global_step": 566381, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.052999496459961, "global_step": 566382, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0728609561920166, "global_step": 566383, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.110079288482666, "global_step": 566384, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.987053632736206, "global_step": 566385, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9710803031921387, "global_step": 566386, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.027475118637085, "global_step": 566387, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0854337215423584, "global_step": 566388, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.048945665359497, "global_step": 566389, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.8803476095199585, "global_step": 566390, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.996878743171692, "global_step": 566391, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.037864923477173, "global_step": 566392, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9875776767730713, "global_step": 566393, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9879282712936401, "global_step": 566394, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0206737518310547, "global_step": 566395, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9418466091156006, "global_step": 566396, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.054060697555542, "global_step": 566397, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.004112720489502, "global_step": 566398, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.009183406829834, "global_step": 566399, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0285396575927734, "global_step": 566400, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9964410066604614, "global_step": 566401, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.977255940437317, "global_step": 566402, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.990138292312622, "global_step": 566403, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.060365915298462, "global_step": 566404, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0319395065307617, "global_step": 566405, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.008352041244507, "global_step": 566406, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.022279739379883, "global_step": 566407, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0001296997070312, "global_step": 566408, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9234243631362915, "global_step": 566409, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0689773559570312, "global_step": 566410, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0454697608947754, "global_step": 566411, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0009496212005615, "global_step": 566412, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.066861152648926, "global_step": 566413, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.052699327468872, "global_step": 566414, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9667901992797852, "global_step": 566415, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9920573234558105, "global_step": 566416, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.014439105987549, "global_step": 566417, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.010122776031494, "global_step": 566418, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9575920104980469, "global_step": 566419, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.978208303451538, "global_step": 566420, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.009507417678833, "global_step": 566421, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.976946234703064, "global_step": 566422, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.072739362716675, "global_step": 566423, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.051999568939209, "global_step": 566424, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.041728973388672, "global_step": 566425, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.080639362335205, "global_step": 566426, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0678796768188477, "global_step": 566427, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.01908540725708, "global_step": 566428, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.049636125564575, "global_step": 566429, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.981221318244934, "global_step": 566430, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.006781578063965, "global_step": 566431, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9922946691513062, "global_step": 566432, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.012484312057495, "global_step": 566433, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0757062435150146, "global_step": 566434, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9515389204025269, "global_step": 566435, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.967820167541504, "global_step": 566436, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.049135208129883, "global_step": 566437, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.868228554725647, "global_step": 566438, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.004288673400879, "global_step": 566439, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0212836265563965, "global_step": 566440, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9844657182693481, "global_step": 566441, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9452852010726929, "global_step": 566442, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.070927381515503, "global_step": 566443, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9946701526641846, "global_step": 566444, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0517663955688477, "global_step": 566445, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.072002649307251, "global_step": 566446, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0592005252838135, "global_step": 566447, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.079462766647339, "global_step": 566448, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.04048228263855, "global_step": 566449, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.987121820449829, "global_step": 566450, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.052438735961914, "global_step": 566451, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1005189418792725, "global_step": 566452, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9842760562896729, "global_step": 566453, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0086333751678467, "global_step": 566454, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0696370601654053, "global_step": 566455, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9434071779251099, "global_step": 566456, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0615129470825195, "global_step": 566457, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9938750267028809, "global_step": 566458, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.086078643798828, "global_step": 566459, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.078038454055786, "global_step": 566460, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.072404146194458, "global_step": 566461, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1084210872650146, "global_step": 566462, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0150532722473145, "global_step": 566463, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0026166439056396, "global_step": 566464, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0315356254577637, "global_step": 566465, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0569839477539062, "global_step": 566466, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0412495136260986, "global_step": 566467, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.026451587677002, "global_step": 566468, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0043723583221436, "global_step": 566469, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0135343074798584, "global_step": 566470, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0516719818115234, "global_step": 566471, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9254926443099976, "global_step": 566472, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9883428812026978, "global_step": 566473, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.020136594772339, "global_step": 566474, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0717973709106445, "global_step": 566475, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9611132144927979, "global_step": 566476, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1186389923095703, "global_step": 566477, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.091623306274414, "global_step": 566478, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0921404361724854, "global_step": 566479, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.049640417098999, "global_step": 566480, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0486302375793457, "global_step": 566481, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9212909936904907, "global_step": 566482, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9878208637237549, "global_step": 566483, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0624701976776123, "global_step": 566484, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.115211248397827, "global_step": 566485, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0567445755004883, "global_step": 566486, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0346813201904297, "global_step": 566487, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9863086938858032, "global_step": 566488, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9276525974273682, "global_step": 566489, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0306220054626465, "global_step": 566490, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.106809139251709, "global_step": 566491, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.079684257507324, "global_step": 566492, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1074395179748535, "global_step": 566493, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9914178848266602, "global_step": 566494, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9843623638153076, "global_step": 566495, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0012404918670654, "global_step": 566496, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0457701683044434, "global_step": 566497, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0574049949645996, "global_step": 566498, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.940717339515686, "global_step": 566499, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.005199670791626, "global_step": 566500, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.044046401977539, "global_step": 566501, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.04421067237854, "global_step": 566502, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.925590991973877, "global_step": 566503, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9582058191299438, "global_step": 566504, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0515403747558594, "global_step": 566505, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0284407138824463, "global_step": 566506, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0505411624908447, "global_step": 566507, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.049283027648926, "global_step": 566508, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.020374298095703, "global_step": 566509, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.073465347290039, "global_step": 566510, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9945164918899536, "global_step": 566511, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.009106159210205, "global_step": 566512, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0402002334594727, "global_step": 566513, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.085130453109741, "global_step": 566514, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.022235870361328, "global_step": 566515, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.980499029159546, "global_step": 566516, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0738120079040527, "global_step": 566517, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0177507400512695, "global_step": 566518, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0400798320770264, "global_step": 566519, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1152567863464355, "global_step": 566520, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0256569385528564, "global_step": 566521, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9830445051193237, "global_step": 566522, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9966264963150024, "global_step": 566523, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9991158246994019, "global_step": 566524, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0773792266845703, "global_step": 566525, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9907230138778687, "global_step": 566526, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9891186952590942, "global_step": 566527, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0529634952545166, "global_step": 566528, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0349345207214355, "global_step": 566529, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1023032665252686, "global_step": 566530, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0393762588500977, "global_step": 566531, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0548207759857178, "global_step": 566532, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1200950145721436, "global_step": 566533, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9861094951629639, "global_step": 566534, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9959796667099, "global_step": 566535, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0879759788513184, "global_step": 566536, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.019465446472168, "global_step": 566537, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0457851886749268, "global_step": 566538, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.964812159538269, "global_step": 566539, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0683984756469727, "global_step": 566540, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1642165184020996, "global_step": 566541, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0307016372680664, "global_step": 566542, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9891777038574219, "global_step": 566543, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1215572357177734, "global_step": 566544, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.050598382949829, "global_step": 566545, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0980818271636963, "global_step": 566546, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.942260980606079, "global_step": 566547, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0582194328308105, "global_step": 566548, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9853132963180542, "global_step": 566549, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9682971239089966, "global_step": 566550, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9556218385696411, "global_step": 566551, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0018489360809326, "global_step": 566552, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9356484413146973, "global_step": 566553, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.121460199356079, "global_step": 566554, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1019184589385986, "global_step": 566555, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.074185371398926, "global_step": 566556, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.002922534942627, "global_step": 566557, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.028151750564575, "global_step": 566558, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0368812084198, "global_step": 566559, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.950097680091858, "global_step": 566560, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.012251138687134, "global_step": 566561, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9378409385681152, "global_step": 566562, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0412306785583496, "global_step": 566563, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9580382108688354, "global_step": 566564, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0201423168182373, "global_step": 566565, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9975488185882568, "global_step": 566566, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9967358112335205, "global_step": 566567, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9791580438613892, "global_step": 566568, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.116539716720581, "global_step": 566569, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.036024332046509, "global_step": 566570, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.048827886581421, "global_step": 566571, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9709210395812988, "global_step": 566572, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.050100088119507, "global_step": 566573, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.003892183303833, "global_step": 566574, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.123387336730957, "global_step": 566575, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.99661386013031, "global_step": 566576, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.017378330230713, "global_step": 566577, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9732013940811157, "global_step": 566578, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9724382162094116, "global_step": 566579, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0248870849609375, "global_step": 566580, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.001278877258301, "global_step": 566581, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9486584663391113, "global_step": 566582, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.953285574913025, "global_step": 566583, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0041635036468506, "global_step": 566584, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.028810977935791, "global_step": 566585, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.020254611968994, "global_step": 566586, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9238077402114868, "global_step": 566587, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9786911010742188, "global_step": 566588, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0863494873046875, "global_step": 566589, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.020899534225464, "global_step": 566590, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0245981216430664, "global_step": 566591, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0189223289489746, "global_step": 566592, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0585577487945557, "global_step": 566593, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1378121376037598, "global_step": 566594, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9460145235061646, "global_step": 566595, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.054572343826294, "global_step": 566596, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9946002960205078, "global_step": 566597, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9786076545715332, "global_step": 566598, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.970012903213501, "global_step": 566599, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0728909969329834, "global_step": 566600, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.933057427406311, "global_step": 566601, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9927582740783691, "global_step": 566602, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0061564445495605, "global_step": 566603, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.032013416290283, "global_step": 566604, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0308895111083984, "global_step": 566605, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.01637864112854, "global_step": 566606, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0949206352233887, "global_step": 566607, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9831888675689697, "global_step": 566608, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.099046468734741, "global_step": 566609, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1262917518615723, "global_step": 566610, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.04337477684021, "global_step": 566611, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.050320625305176, "global_step": 566612, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.125154733657837, "global_step": 566613, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.151787281036377, "global_step": 566614, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9746721982955933, "global_step": 566615, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.057976484298706, "global_step": 566616, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.092341899871826, "global_step": 566617, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.042970657348633, "global_step": 566618, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0447185039520264, "global_step": 566619, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9832593202590942, "global_step": 566620, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1534969806671143, "global_step": 566621, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0830435752868652, "global_step": 566622, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.080650568008423, "global_step": 566623, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9618171453475952, "global_step": 566624, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0411362648010254, "global_step": 566625, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.002222776412964, "global_step": 566626, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0836052894592285, "global_step": 566627, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0921754837036133, "global_step": 566628, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0427184104919434, "global_step": 566629, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.053575277328491, "global_step": 566630, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9367749691009521, "global_step": 566631, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.968785047531128, "global_step": 566632, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0544567108154297, "global_step": 566633, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.96784245967865, "global_step": 566634, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9666188955307007, "global_step": 566635, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9212393760681152, "global_step": 566636, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0881969928741455, "global_step": 566637, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.062605619430542, "global_step": 566638, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.967275857925415, "global_step": 566639, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9684853553771973, "global_step": 566640, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9631024599075317, "global_step": 566641, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9137848615646362, "global_step": 566642, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.036933183670044, "global_step": 566643, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9582173824310303, "global_step": 566644, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.059101104736328, "global_step": 566645, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.8684073686599731, "global_step": 566646, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0491912364959717, "global_step": 566647, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0171430110931396, "global_step": 566648, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.011401891708374, "global_step": 566649, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0004160404205322, "global_step": 566650, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9925497770309448, "global_step": 566651, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0098748207092285, "global_step": 566652, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0852954387664795, "global_step": 566653, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0110578536987305, "global_step": 566654, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0015206336975098, "global_step": 566655, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9830338954925537, "global_step": 566656, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0285098552703857, "global_step": 566657, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0368218421936035, "global_step": 566658, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0548768043518066, "global_step": 566659, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.928195834159851, "global_step": 566660, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0752575397491455, "global_step": 566661, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0452375411987305, "global_step": 566662, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9670641422271729, "global_step": 566663, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9471060037612915, "global_step": 566664, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0098423957824707, "global_step": 566665, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9889402389526367, "global_step": 566666, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.035113573074341, "global_step": 566667, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0606024265289307, "global_step": 566668, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.873765468597412, "global_step": 566669, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9705164432525635, "global_step": 566670, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0137100219726562, "global_step": 566671, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9759080410003662, "global_step": 566672, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0693814754486084, "global_step": 566673, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0485999584198, "global_step": 566674, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.038137674331665, "global_step": 566675, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0128164291381836, "global_step": 566676, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9932010173797607, "global_step": 566677, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9533953666687012, "global_step": 566678, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0475692749023438, "global_step": 566679, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0725457668304443, "global_step": 566680, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0025970935821533, "global_step": 566681, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0299625396728516, "global_step": 566682, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0217275619506836, "global_step": 566683, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.018388509750366, "global_step": 566684, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0123493671417236, "global_step": 566685, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0273866653442383, "global_step": 566686, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.073404312133789, "global_step": 566687, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.045182704925537, "global_step": 566688, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0700576305389404, "global_step": 566689, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.05195951461792, "global_step": 566690, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9522156715393066, "global_step": 566691, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9617078304290771, "global_step": 566692, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0296270847320557, "global_step": 566693, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0690877437591553, "global_step": 566694, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.03121280670166, "global_step": 566695, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.987478256225586, "global_step": 566696, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0523135662078857, "global_step": 566697, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9358575344085693, "global_step": 566698, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9774867296218872, "global_step": 566699, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9020615816116333, "global_step": 566700, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0278899669647217, "global_step": 566701, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0859272480010986, "global_step": 566702, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.099050521850586, "global_step": 566703, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0043067932128906, "global_step": 566704, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0252835750579834, "global_step": 566705, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0606062412261963, "global_step": 566706, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.008739709854126, "global_step": 566707, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0514090061187744, "global_step": 566708, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.051191568374634, "global_step": 566709, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9677104949951172, "global_step": 566710, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.022883176803589, "global_step": 566711, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.966451644897461, "global_step": 566712, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0043694972991943, "global_step": 566713, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.017981767654419, "global_step": 566714, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9791210889816284, "global_step": 566715, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9794989824295044, "global_step": 566716, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0555853843688965, "global_step": 566717, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.967366337776184, "global_step": 566718, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0048770904541016, "global_step": 566719, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.088092088699341, "global_step": 566720, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.036116123199463, "global_step": 566721, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9386022090911865, "global_step": 566722, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0425631999969482, "global_step": 566723, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0680429935455322, "global_step": 566724, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.046050548553467, "global_step": 566725, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0162689685821533, "global_step": 566726, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.065537929534912, "global_step": 566727, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.012932062149048, "global_step": 566728, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.008565664291382, "global_step": 566729, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.055556297302246, "global_step": 566730, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0384860038757324, "global_step": 566731, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0635766983032227, "global_step": 566732, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9770331382751465, "global_step": 566733, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0185329914093018, "global_step": 566734, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.041886568069458, "global_step": 566735, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0313565731048584, "global_step": 566736, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0345380306243896, "global_step": 566737, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0900309085845947, "global_step": 566738, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0115156173706055, "global_step": 566739, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9676843881607056, "global_step": 566740, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0431699752807617, "global_step": 566741, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0185811519622803, "global_step": 566742, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.075758934020996, "global_step": 566743, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.961525321006775, "global_step": 566744, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.922419548034668, "global_step": 566745, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0689163208007812, "global_step": 566746, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9692331552505493, "global_step": 566747, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.101539373397827, "global_step": 566748, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.064157247543335, "global_step": 566749, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9537521600723267, "global_step": 566750, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0492289066314697, "global_step": 566751, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9846992492675781, "global_step": 566752, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.989761471748352, "global_step": 566753, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0341804027557373, "global_step": 566754, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0293772220611572, "global_step": 566755, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9792686700820923, "global_step": 566756, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9845670461654663, "global_step": 566757, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0794975757598877, "global_step": 566758, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0380988121032715, "global_step": 566759, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.096421003341675, "global_step": 566760, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.033611536026001, "global_step": 566761, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.099614143371582, "global_step": 566762, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9787495136260986, "global_step": 566763, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0441172122955322, "global_step": 566764, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1363930702209473, "global_step": 566765, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9964114427566528, "global_step": 566766, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0421087741851807, "global_step": 566767, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0874195098876953, "global_step": 566768, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.034580945968628, "global_step": 566769, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1659927368164062, "global_step": 566770, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1408793926239014, "global_step": 566771, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9724066257476807, "global_step": 566772, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0275747776031494, "global_step": 566773, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0614800453186035, "global_step": 566774, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0537729263305664, "global_step": 566775, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9952847957611084, "global_step": 566776, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.999060034751892, "global_step": 566777, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0150604248046875, "global_step": 566778, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.075474500656128, "global_step": 566779, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0383081436157227, "global_step": 566780, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0874440670013428, "global_step": 566781, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.990776538848877, "global_step": 566782, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9441825151443481, "global_step": 566783, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.097020387649536, "global_step": 566784, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0315663814544678, "global_step": 566785, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.040855884552002, "global_step": 566786, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9556828737258911, "global_step": 566787, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.969999074935913, "global_step": 566788, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.055182456970215, "global_step": 566789, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9759266376495361, "global_step": 566790, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.026752471923828, "global_step": 566791, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9859365224838257, "global_step": 566792, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.12614107131958, "global_step": 566793, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0942461490631104, "global_step": 566794, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0048577785491943, "global_step": 566795, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.030690908432007, "global_step": 566796, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.97654128074646, "global_step": 566797, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.060023307800293, "global_step": 566798, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0393755435943604, "global_step": 566799, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.979158878326416, "global_step": 566800, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.14330792427063, "global_step": 566801, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9988036155700684, "global_step": 566802, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9539507627487183, "global_step": 566803, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9315924644470215, "global_step": 566804, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0124807357788086, "global_step": 566805, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9748082160949707, "global_step": 566806, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0049009323120117, "global_step": 566807, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0300331115722656, "global_step": 566808, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.008075475692749, "global_step": 566809, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9775713682174683, "global_step": 566810, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.061603307723999, "global_step": 566811, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0240747928619385, "global_step": 566812, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0009052753448486, "global_step": 566813, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9317362308502197, "global_step": 566814, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9351530075073242, "global_step": 566815, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0182695388793945, "global_step": 566816, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9975420236587524, "global_step": 566817, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.097182273864746, "global_step": 566818, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0443544387817383, "global_step": 566819, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0612564086914062, "global_step": 566820, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.128610610961914, "global_step": 566821, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9820961952209473, "global_step": 566822, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.063387155532837, "global_step": 566823, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0324485301971436, "global_step": 566824, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0042884349823, "global_step": 566825, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.992100477218628, "global_step": 566826, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0075535774230957, "global_step": 566827, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.013118028640747, "global_step": 566828, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0898244380950928, "global_step": 566829, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9927537441253662, "global_step": 566830, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9830291271209717, "global_step": 566831, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9635496139526367, "global_step": 566832, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.058934211730957, "global_step": 566833, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.971832513809204, "global_step": 566834, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9762340784072876, "global_step": 566835, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1074435710906982, "global_step": 566836, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.016650676727295, "global_step": 566837, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9179818630218506, "global_step": 566838, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.978920340538025, "global_step": 566839, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9976606369018555, "global_step": 566840, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.013335943222046, "global_step": 566841, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0569255352020264, "global_step": 566842, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0528109073638916, "global_step": 566843, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0560946464538574, "global_step": 566844, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9898185729980469, "global_step": 566845, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1083195209503174, "global_step": 566846, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.062894344329834, "global_step": 566847, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.098850965499878, "global_step": 566848, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9775474071502686, "global_step": 566849, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0889744758605957, "global_step": 566850, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0799734592437744, "global_step": 566851, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.054556369781494, "global_step": 566852, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.991224765777588, "global_step": 566853, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9864262342453003, "global_step": 566854, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9083974361419678, "global_step": 566855, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0646631717681885, "global_step": 566856, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9796578884124756, "global_step": 566857, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0922040939331055, "global_step": 566858, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.052170515060425, "global_step": 566859, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0493428707122803, "global_step": 566860, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9488579034805298, "global_step": 566861, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.889732003211975, "global_step": 566862, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.970766305923462, "global_step": 566863, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9868614673614502, "global_step": 566864, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9416640996932983, "global_step": 566865, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9898549318313599, "global_step": 566866, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0152828693389893, "global_step": 566867, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0257651805877686, "global_step": 566868, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9722959995269775, "global_step": 566869, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.008897542953491, "global_step": 566870, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9582585096359253, "global_step": 566871, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9534276723861694, "global_step": 566872, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0077028274536133, "global_step": 566873, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.126272201538086, "global_step": 566874, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0690057277679443, "global_step": 566875, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9689065217971802, "global_step": 566876, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0113754272460938, "global_step": 566877, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.020247459411621, "global_step": 566878, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.040292263031006, "global_step": 566879, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.054133892059326, "global_step": 566880, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.028282403945923, "global_step": 566881, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.11452054977417, "global_step": 566882, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9714208841323853, "global_step": 566883, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0024850368499756, "global_step": 566884, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.017444133758545, "global_step": 566885, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.065467357635498, "global_step": 566886, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0903327465057373, "global_step": 566887, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9271854162216187, "global_step": 566888, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0083961486816406, "global_step": 566889, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.065286159515381, "global_step": 566890, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.961637020111084, "global_step": 566891, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.008829355239868, "global_step": 566892, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9791903495788574, "global_step": 566893, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9795619249343872, "global_step": 566894, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0136730670928955, "global_step": 566895, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.018232583999634, "global_step": 566896, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9375075101852417, "global_step": 566897, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0534446239471436, "global_step": 566898, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.053985834121704, "global_step": 566899, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1055822372436523, "global_step": 566900, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9937058687210083, "global_step": 566901, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0602073669433594, "global_step": 566902, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9845690727233887, "global_step": 566903, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.077427387237549, "global_step": 566904, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.033663749694824, "global_step": 566905, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0063459873199463, "global_step": 566906, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0528523921966553, "global_step": 566907, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.076247215270996, "global_step": 566908, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0953292846679688, "global_step": 566909, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9153764247894287, "global_step": 566910, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0321273803710938, "global_step": 566911, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1031980514526367, "global_step": 566912, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.045363426208496, "global_step": 566913, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0181899070739746, "global_step": 566914, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.091108560562134, "global_step": 566915, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1045384407043457, "global_step": 566916, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9648321866989136, "global_step": 566917, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.051050901412964, "global_step": 566918, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.026118755340576, "global_step": 566919, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9017683267593384, "global_step": 566920, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9729959964752197, "global_step": 566921, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.073155641555786, "global_step": 566922, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9452729225158691, "global_step": 566923, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.989606499671936, "global_step": 566924, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0176126956939697, "global_step": 566925, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0529122352600098, "global_step": 566926, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9220925569534302, "global_step": 566927, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9247593879699707, "global_step": 566928, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9824230670928955, "global_step": 566929, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.01102614402771, "global_step": 566930, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.013258934020996, "global_step": 566931, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.069471597671509, "global_step": 566932, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0406265258789062, "global_step": 566933, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0231282711029053, "global_step": 566934, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9961919784545898, "global_step": 566935, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9663883447647095, "global_step": 566936, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.008864641189575, "global_step": 566937, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9463411569595337, "global_step": 566938, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9830739498138428, "global_step": 566939, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9737755060195923, "global_step": 566940, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.108987331390381, "global_step": 566941, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.087448835372925, "global_step": 566942, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.000364065170288, "global_step": 566943, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9978623390197754, "global_step": 566944, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.003525733947754, "global_step": 566945, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.107272148132324, "global_step": 566946, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.079995632171631, "global_step": 566947, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.009885311126709, "global_step": 566948, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0336999893188477, "global_step": 566949, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0261056423187256, "global_step": 566950, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0555851459503174, "global_step": 566951, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0777103900909424, "global_step": 566952, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0990283489227295, "global_step": 566953, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0196306705474854, "global_step": 566954, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0815389156341553, "global_step": 566955, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9861507415771484, "global_step": 566956, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9950133562088013, "global_step": 566957, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.018836259841919, "global_step": 566958, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.000610589981079, "global_step": 566959, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.883894443511963, "global_step": 566960, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9948344230651855, "global_step": 566961, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0208041667938232, "global_step": 566962, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.062190055847168, "global_step": 566963, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0519227981567383, "global_step": 566964, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0892810821533203, "global_step": 566965, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.028097629547119, "global_step": 566966, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1108927726745605, "global_step": 566967, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0295910835266113, "global_step": 566968, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9683103561401367, "global_step": 566969, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0983943939208984, "global_step": 566970, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.064812421798706, "global_step": 566971, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.010043144226074, "global_step": 566972, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0851516723632812, "global_step": 566973, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1005091667175293, "global_step": 566974, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.983560562133789, "global_step": 566975, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0103182792663574, "global_step": 566976, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.020430088043213, "global_step": 566977, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9767439365386963, "global_step": 566978, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1391894817352295, "global_step": 566979, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.040567398071289, "global_step": 566980, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.058746337890625, "global_step": 566981, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.1298367977142334, "global_step": 566982, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9654030799865723, "global_step": 566983, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0678913593292236, "global_step": 566984, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.097170114517212, "global_step": 566985, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.017413854598999, "global_step": 566986, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0540130138397217, "global_step": 566987, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0163495540618896, "global_step": 566988, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9773355722427368, "global_step": 566989, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0371479988098145, "global_step": 566990, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0727477073669434, "global_step": 566991, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0527234077453613, "global_step": 566992, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0637660026550293, "global_step": 566993, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.02380108833313, "global_step": 566994, "epoch": 934, "lr": 5e-05}
{"train_loss": 1.9930260181427002, "global_step": 566995, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0205037593841553, "global_step": 566996, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.023113250732422, "global_step": 566997, "epoch": 934, "lr": 5e-05}
{"train_loss": 2.0699591636657715, "global_step": 566998, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9778534173965454, "global_step": 566999, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0418381690979004, "global_step": 567000, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.065575122833252, "global_step": 567001, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0647730827331543, "global_step": 567002, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.958774447441101, "global_step": 567003, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.069620132446289, "global_step": 567004, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0943410396575928, "global_step": 567005, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.001117467880249, "global_step": 567006, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9148553609848022, "global_step": 567007, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9588137865066528, "global_step": 567008, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0864977836608887, "global_step": 567009, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0443904399871826, "global_step": 567010, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0355918407440186, "global_step": 567011, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0757675170898438, "global_step": 567012, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.032963752746582, "global_step": 567013, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9659435749053955, "global_step": 567014, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.051894426345825, "global_step": 567015, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0672035217285156, "global_step": 567016, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0204007625579834, "global_step": 567017, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0575101375579834, "global_step": 567018, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0379128456115723, "global_step": 567019, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.001476764678955, "global_step": 567020, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.035050630569458, "global_step": 567021, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0377981662750244, "global_step": 567022, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9554920196533203, "global_step": 567023, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.999169111251831, "global_step": 567024, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9984729290008545, "global_step": 567025, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.023752212524414, "global_step": 567026, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9537055492401123, "global_step": 567027, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9953278303146362, "global_step": 567028, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.105652332305908, "global_step": 567029, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.022066354751587, "global_step": 567030, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9588083028793335, "global_step": 567031, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.035778522491455, "global_step": 567032, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0505595207214355, "global_step": 567033, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.062042713165283, "global_step": 567034, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9186447858810425, "global_step": 567035, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9672622680664062, "global_step": 567036, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0099399089813232, "global_step": 567037, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9864673614501953, "global_step": 567038, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.083979368209839, "global_step": 567039, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9921454191207886, "global_step": 567040, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0036747455596924, "global_step": 567041, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0149447917938232, "global_step": 567042, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.131063222885132, "global_step": 567043, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.020014762878418, "global_step": 567044, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0418684482574463, "global_step": 567045, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0003390312194824, "global_step": 567046, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.992642879486084, "global_step": 567047, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9894914627075195, "global_step": 567048, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0570719242095947, "global_step": 567049, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9982385635375977, "global_step": 567050, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.8862820863723755, "global_step": 567051, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9476711750030518, "global_step": 567052, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9762383699417114, "global_step": 567053, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9762110710144043, "global_step": 567054, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.081273078918457, "global_step": 567055, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0237505435943604, "global_step": 567056, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0169780254364014, "global_step": 567057, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9985053539276123, "global_step": 567058, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9848116636276245, "global_step": 567059, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9021623134613037, "global_step": 567060, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9620076417922974, "global_step": 567061, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.982831597328186, "global_step": 567062, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0482544898986816, "global_step": 567063, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1217973232269287, "global_step": 567064, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.018763780593872, "global_step": 567065, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0679404735565186, "global_step": 567066, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0710716247558594, "global_step": 567067, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0851409435272217, "global_step": 567068, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0966787338256836, "global_step": 567069, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0422799587249756, "global_step": 567070, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9878147840499878, "global_step": 567071, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9248075485229492, "global_step": 567072, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1017699241638184, "global_step": 567073, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9076826572418213, "global_step": 567074, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.062894582748413, "global_step": 567075, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0261852741241455, "global_step": 567076, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.026970148086548, "global_step": 567077, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.053342580795288, "global_step": 567078, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9970359802246094, "global_step": 567079, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0608270168304443, "global_step": 567080, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0433804988861084, "global_step": 567081, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9951289892196655, "global_step": 567082, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9255553483963013, "global_step": 567083, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.034179925918579, "global_step": 567084, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9974770545959473, "global_step": 567085, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9677460193634033, "global_step": 567086, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9571605920791626, "global_step": 567087, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.021275758743286, "global_step": 567088, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0524067878723145, "global_step": 567089, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.929373860359192, "global_step": 567090, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.006911516189575, "global_step": 567091, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9969295263290405, "global_step": 567092, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9748343229293823, "global_step": 567093, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0503435134887695, "global_step": 567094, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0221498012542725, "global_step": 567095, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9436473846435547, "global_step": 567096, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.060189962387085, "global_step": 567097, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.935344934463501, "global_step": 567098, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0093324184417725, "global_step": 567099, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9824029207229614, "global_step": 567100, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0343258380889893, "global_step": 567101, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9682408571243286, "global_step": 567102, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.039565086364746, "global_step": 567103, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0482165813446045, "global_step": 567104, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.049140691757202, "global_step": 567105, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.078460454940796, "global_step": 567106, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0294103622436523, "global_step": 567107, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.079951524734497, "global_step": 567108, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9936189651489258, "global_step": 567109, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9473992586135864, "global_step": 567110, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.085089921951294, "global_step": 567111, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.051571846008301, "global_step": 567112, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.009584665298462, "global_step": 567113, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9239567518234253, "global_step": 567114, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.968363881111145, "global_step": 567115, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1035573482513428, "global_step": 567116, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.040829658508301, "global_step": 567117, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0317888259887695, "global_step": 567118, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9868621826171875, "global_step": 567119, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1062967777252197, "global_step": 567120, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9253414869308472, "global_step": 567121, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9887253046035767, "global_step": 567122, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9880459308624268, "global_step": 567123, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0492095947265625, "global_step": 567124, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.054319143295288, "global_step": 567125, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9681884050369263, "global_step": 567126, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0018417835235596, "global_step": 567127, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.031619071960449, "global_step": 567128, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.040735960006714, "global_step": 567129, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0040197372436523, "global_step": 567130, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0180091857910156, "global_step": 567131, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.031702995300293, "global_step": 567132, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.008411169052124, "global_step": 567133, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9535244703292847, "global_step": 567134, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9343323707580566, "global_step": 567135, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9614568948745728, "global_step": 567136, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0382542610168457, "global_step": 567137, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0176239013671875, "global_step": 567138, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9816348552703857, "global_step": 567139, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0713133811950684, "global_step": 567140, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.010662078857422, "global_step": 567141, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9572157859802246, "global_step": 567142, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1086599826812744, "global_step": 567143, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.082449436187744, "global_step": 567144, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0516998767852783, "global_step": 567145, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.952057123184204, "global_step": 567146, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9569740295410156, "global_step": 567147, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1185035705566406, "global_step": 567148, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.032382011413574, "global_step": 567149, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.00181245803833, "global_step": 567150, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.099391460418701, "global_step": 567151, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0274884700775146, "global_step": 567152, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.045961856842041, "global_step": 567153, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.044664144515991, "global_step": 567154, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0415430068969727, "global_step": 567155, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.036421537399292, "global_step": 567156, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.024545907974243, "global_step": 567157, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0894644260406494, "global_step": 567158, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0995407104492188, "global_step": 567159, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9914573431015015, "global_step": 567160, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.046804428100586, "global_step": 567161, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9737391471862793, "global_step": 567162, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9458601474761963, "global_step": 567163, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.024920701980591, "global_step": 567164, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.031874179840088, "global_step": 567165, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.014413833618164, "global_step": 567166, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.005521774291992, "global_step": 567167, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9668551683425903, "global_step": 567168, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9559195041656494, "global_step": 567169, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.073058843612671, "global_step": 567170, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9915004968643188, "global_step": 567171, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9385066032409668, "global_step": 567172, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.025782346725464, "global_step": 567173, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0270910263061523, "global_step": 567174, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0305070877075195, "global_step": 567175, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0515003204345703, "global_step": 567176, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9092305898666382, "global_step": 567177, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9247767925262451, "global_step": 567178, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.962249994277954, "global_step": 567179, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0133135318756104, "global_step": 567180, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.958729863166809, "global_step": 567181, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0487565994262695, "global_step": 567182, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.960450291633606, "global_step": 567183, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9616694450378418, "global_step": 567184, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0174598693847656, "global_step": 567185, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.01181960105896, "global_step": 567186, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.014383554458618, "global_step": 567187, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.018585443496704, "global_step": 567188, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0477588176727295, "global_step": 567189, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0364720821380615, "global_step": 567190, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.059819221496582, "global_step": 567191, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0899152755737305, "global_step": 567192, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0281050205230713, "global_step": 567193, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.048711061477661, "global_step": 567194, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0171561241149902, "global_step": 567195, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0455210208892822, "global_step": 567196, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9343037605285645, "global_step": 567197, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.050529718399048, "global_step": 567198, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0543346405029297, "global_step": 567199, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9740440845489502, "global_step": 567200, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.053649663925171, "global_step": 567201, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.013490915298462, "global_step": 567202, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0575122833251953, "global_step": 567203, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9629446268081665, "global_step": 567204, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0429766178131104, "global_step": 567205, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9688867330551147, "global_step": 567206, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.048743486404419, "global_step": 567207, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9936414957046509, "global_step": 567208, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0420563220977783, "global_step": 567209, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9635528326034546, "global_step": 567210, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.2157390117645264, "global_step": 567211, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0020127296447754, "global_step": 567212, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.935017466545105, "global_step": 567213, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9480587244033813, "global_step": 567214, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0764901638031006, "global_step": 567215, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.007267951965332, "global_step": 567216, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0488057136535645, "global_step": 567217, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9810129404067993, "global_step": 567218, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.053924560546875, "global_step": 567219, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.95729660987854, "global_step": 567220, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9376287460327148, "global_step": 567221, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.004838705062866, "global_step": 567222, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9939652681350708, "global_step": 567223, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0025229454040527, "global_step": 567224, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9528682231903076, "global_step": 567225, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9999927282333374, "global_step": 567226, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9924613237380981, "global_step": 567227, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0005404949188232, "global_step": 567228, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.034541368484497, "global_step": 567229, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9724904298782349, "global_step": 567230, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9387905597686768, "global_step": 567231, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0170929431915283, "global_step": 567232, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0631816387176514, "global_step": 567233, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1153223514556885, "global_step": 567234, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9821345806121826, "global_step": 567235, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.047149419784546, "global_step": 567236, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0098936557769775, "global_step": 567237, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9637449979782104, "global_step": 567238, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0668816566467285, "global_step": 567239, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0115444660186768, "global_step": 567240, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9607175588607788, "global_step": 567241, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0561039447784424, "global_step": 567242, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9759474992752075, "global_step": 567243, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9679977893829346, "global_step": 567244, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.981476068496704, "global_step": 567245, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9460809230804443, "global_step": 567246, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9857152700424194, "global_step": 567247, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.074608325958252, "global_step": 567248, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.064584255218506, "global_step": 567249, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.021710157394409, "global_step": 567250, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9863688945770264, "global_step": 567251, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.109102964401245, "global_step": 567252, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.146139621734619, "global_step": 567253, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9634473323822021, "global_step": 567254, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0094637870788574, "global_step": 567255, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.995937466621399, "global_step": 567256, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.015195846557617, "global_step": 567257, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0049023628234863, "global_step": 567258, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0538971424102783, "global_step": 567259, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0750796794891357, "global_step": 567260, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0331783294677734, "global_step": 567261, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.987785816192627, "global_step": 567262, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9728575944900513, "global_step": 567263, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0719738006591797, "global_step": 567264, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0809295177459717, "global_step": 567265, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.987573266029358, "global_step": 567266, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.053435802459717, "global_step": 567267, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0836405754089355, "global_step": 567268, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1394340991973877, "global_step": 567269, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9995161294937134, "global_step": 567270, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0168237686157227, "global_step": 567271, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9526245594024658, "global_step": 567272, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0060906410217285, "global_step": 567273, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0142996311187744, "global_step": 567274, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.11472225189209, "global_step": 567275, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.937482237815857, "global_step": 567276, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9509780406951904, "global_step": 567277, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.02871036529541, "global_step": 567278, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9950435161590576, "global_step": 567279, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0203468799591064, "global_step": 567280, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.088434934616089, "global_step": 567281, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0604052543640137, "global_step": 567282, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.032000780105591, "global_step": 567283, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.015968084335327, "global_step": 567284, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9819105863571167, "global_step": 567285, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1111679077148438, "global_step": 567286, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.991620659828186, "global_step": 567287, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.008063316345215, "global_step": 567288, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0333309173583984, "global_step": 567289, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.057173490524292, "global_step": 567290, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9246751070022583, "global_step": 567291, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0054352283477783, "global_step": 567292, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.98933744430542, "global_step": 567293, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0117597579956055, "global_step": 567294, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.020414352416992, "global_step": 567295, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0262949466705322, "global_step": 567296, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.00763201713562, "global_step": 567297, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0089879035949707, "global_step": 567298, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9721882343292236, "global_step": 567299, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.014105796813965, "global_step": 567300, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.079090118408203, "global_step": 567301, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.11308217048645, "global_step": 567302, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.079162836074829, "global_step": 567303, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.024815797805786, "global_step": 567304, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0201916694641113, "global_step": 567305, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0548672676086426, "global_step": 567306, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.032108783721924, "global_step": 567307, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9805071353912354, "global_step": 567308, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9973273277282715, "global_step": 567309, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0751402378082275, "global_step": 567310, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.957263708114624, "global_step": 567311, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0280370712280273, "global_step": 567312, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0237057209014893, "global_step": 567313, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9963263273239136, "global_step": 567314, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.077942371368408, "global_step": 567315, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.043088436126709, "global_step": 567316, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.001401901245117, "global_step": 567317, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0493812561035156, "global_step": 567318, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9986228942871094, "global_step": 567319, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.047842025756836, "global_step": 567320, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9173436164855957, "global_step": 567321, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0435550212860107, "global_step": 567322, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9499027729034424, "global_step": 567323, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.992067813873291, "global_step": 567324, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9557397365570068, "global_step": 567325, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.015029191970825, "global_step": 567326, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9941437244415283, "global_step": 567327, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.074871301651001, "global_step": 567328, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0999691486358643, "global_step": 567329, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9526474475860596, "global_step": 567330, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9330191612243652, "global_step": 567331, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.078916072845459, "global_step": 567332, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9788554906845093, "global_step": 567333, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9998116493225098, "global_step": 567334, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0174522399902344, "global_step": 567335, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9998842477798462, "global_step": 567336, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0873425006866455, "global_step": 567337, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0047194957733154, "global_step": 567338, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.985493779182434, "global_step": 567339, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.035538673400879, "global_step": 567340, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.014864206314087, "global_step": 567341, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0649023056030273, "global_step": 567342, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0238044261932373, "global_step": 567343, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.045825242996216, "global_step": 567344, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9332112073898315, "global_step": 567345, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0211915969848633, "global_step": 567346, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.006483793258667, "global_step": 567347, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.037144422531128, "global_step": 567348, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0537221431732178, "global_step": 567349, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0504865646362305, "global_step": 567350, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9471697807312012, "global_step": 567351, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0524699687957764, "global_step": 567352, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.952775239944458, "global_step": 567353, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0417380332946777, "global_step": 567354, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0170271396636963, "global_step": 567355, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0180108547210693, "global_step": 567356, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0379672050476074, "global_step": 567357, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.125474691390991, "global_step": 567358, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0480706691741943, "global_step": 567359, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0253970623016357, "global_step": 567360, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.072200298309326, "global_step": 567361, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.044829845428467, "global_step": 567362, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0611279010772705, "global_step": 567363, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.961798071861267, "global_step": 567364, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0673866271972656, "global_step": 567365, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0680556297302246, "global_step": 567366, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.040731430053711, "global_step": 567367, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9953937530517578, "global_step": 567368, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0273375511169434, "global_step": 567369, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0064289569854736, "global_step": 567370, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0182857513427734, "global_step": 567371, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.10197377204895, "global_step": 567372, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0091562271118164, "global_step": 567373, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.96303129196167, "global_step": 567374, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0243184566497803, "global_step": 567375, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.009688138961792, "global_step": 567376, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0461947917938232, "global_step": 567377, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0052542686462402, "global_step": 567378, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0902938842773438, "global_step": 567379, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.052793025970459, "global_step": 567380, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9662418365478516, "global_step": 567381, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.037997245788574, "global_step": 567382, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9947093725204468, "global_step": 567383, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.026014804840088, "global_step": 567384, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.057626247406006, "global_step": 567385, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9478508234024048, "global_step": 567386, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9783507585525513, "global_step": 567387, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0208640098571777, "global_step": 567388, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.080031156539917, "global_step": 567389, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.026207685470581, "global_step": 567390, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0467939376831055, "global_step": 567391, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.002380847930908, "global_step": 567392, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.070847749710083, "global_step": 567393, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1177475452423096, "global_step": 567394, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.056406021118164, "global_step": 567395, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.067729949951172, "global_step": 567396, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0445823669433594, "global_step": 567397, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.029006004333496, "global_step": 567398, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.027695655822754, "global_step": 567399, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0314903259277344, "global_step": 567400, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9706673622131348, "global_step": 567401, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9670268297195435, "global_step": 567402, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0251550674438477, "global_step": 567403, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9223426580429077, "global_step": 567404, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9924657344818115, "global_step": 567405, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9973043203353882, "global_step": 567406, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9324579238891602, "global_step": 567407, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9082247018814087, "global_step": 567408, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0629119873046875, "global_step": 567409, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0391886234283447, "global_step": 567410, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.071424722671509, "global_step": 567411, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0668203830718994, "global_step": 567412, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0468320846557617, "global_step": 567413, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0420050621032715, "global_step": 567414, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.051583766937256, "global_step": 567415, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.082981824874878, "global_step": 567416, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1429994106292725, "global_step": 567417, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0314691066741943, "global_step": 567418, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9922665357589722, "global_step": 567419, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0558369159698486, "global_step": 567420, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.035421848297119, "global_step": 567421, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9984897375106812, "global_step": 567422, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0343570709228516, "global_step": 567423, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0278890132904053, "global_step": 567424, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.055297374725342, "global_step": 567425, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9975374937057495, "global_step": 567426, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0031282901763916, "global_step": 567427, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9933792352676392, "global_step": 567428, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0448365211486816, "global_step": 567429, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0887413024902344, "global_step": 567430, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.07629656791687, "global_step": 567431, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0751519203186035, "global_step": 567432, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0651376247406006, "global_step": 567433, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0737555027008057, "global_step": 567434, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9740231037139893, "global_step": 567435, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.952959656715393, "global_step": 567436, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9563627243041992, "global_step": 567437, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0220108032226562, "global_step": 567438, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1507766246795654, "global_step": 567439, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9648616313934326, "global_step": 567440, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.026397943496704, "global_step": 567441, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.983001947402954, "global_step": 567442, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9619922637939453, "global_step": 567443, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9796916246414185, "global_step": 567444, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.009960651397705, "global_step": 567445, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.053903341293335, "global_step": 567446, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9703481197357178, "global_step": 567447, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0422141551971436, "global_step": 567448, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9802216291427612, "global_step": 567449, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0294973850250244, "global_step": 567450, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9792828559875488, "global_step": 567451, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9612128734588623, "global_step": 567452, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0564844608306885, "global_step": 567453, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9956179857254028, "global_step": 567454, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.982297658920288, "global_step": 567455, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0439836978912354, "global_step": 567456, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0360541343688965, "global_step": 567457, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.092205762863159, "global_step": 567458, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.06314754486084, "global_step": 567459, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.012253999710083, "global_step": 567460, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0553553104400635, "global_step": 567461, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.056257963180542, "global_step": 567462, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0816071033477783, "global_step": 567463, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.048327922821045, "global_step": 567464, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9912440776824951, "global_step": 567465, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1569266319274902, "global_step": 567466, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0502331256866455, "global_step": 567467, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0604565143585205, "global_step": 567468, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0946602821350098, "global_step": 567469, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0383293628692627, "global_step": 567470, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0376267433166504, "global_step": 567471, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9646492004394531, "global_step": 567472, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9835447072982788, "global_step": 567473, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.030832529067993, "global_step": 567474, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9741160869598389, "global_step": 567475, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.024151563644409, "global_step": 567476, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0333356857299805, "global_step": 567477, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.058988332748413, "global_step": 567478, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.029832601547241, "global_step": 567479, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9484697580337524, "global_step": 567480, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.077242374420166, "global_step": 567481, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0385146141052246, "global_step": 567482, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9963018894195557, "global_step": 567483, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0662009716033936, "global_step": 567484, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0125346183776855, "global_step": 567485, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.069549798965454, "global_step": 567486, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9967268705368042, "global_step": 567487, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.064403533935547, "global_step": 567488, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9897875785827637, "global_step": 567489, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0858120918273926, "global_step": 567490, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9741114377975464, "global_step": 567491, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9856318235397339, "global_step": 567492, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0823917388916016, "global_step": 567493, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0810585021972656, "global_step": 567494, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0190794467926025, "global_step": 567495, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0414068698883057, "global_step": 567496, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0210001468658447, "global_step": 567497, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.05104923248291, "global_step": 567498, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.007873058319092, "global_step": 567499, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9976012706756592, "global_step": 567500, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0557680130004883, "global_step": 567501, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0731332302093506, "global_step": 567502, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0145394802093506, "global_step": 567503, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.105138063430786, "global_step": 567504, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.000859022140503, "global_step": 567505, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.968469500541687, "global_step": 567506, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1116764545440674, "global_step": 567507, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0895931720733643, "global_step": 567508, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.8750468492507935, "global_step": 567509, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.004955530166626, "global_step": 567510, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.133174180984497, "global_step": 567511, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.043870449066162, "global_step": 567512, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.045910596847534, "global_step": 567513, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0729753971099854, "global_step": 567514, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0817813873291016, "global_step": 567515, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0266737937927246, "global_step": 567516, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0528805255889893, "global_step": 567517, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.091569423675537, "global_step": 567518, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.02986216545105, "global_step": 567519, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0588157176971436, "global_step": 567520, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9570555686950684, "global_step": 567521, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.059978485107422, "global_step": 567522, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.935058832168579, "global_step": 567523, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0972185134887695, "global_step": 567524, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.026299476623535, "global_step": 567525, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.05649995803833, "global_step": 567526, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0825307369232178, "global_step": 567527, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.061021089553833, "global_step": 567528, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0183815956115723, "global_step": 567529, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.976138710975647, "global_step": 567530, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0864524841308594, "global_step": 567531, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0068864822387695, "global_step": 567532, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.059375524520874, "global_step": 567533, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0558218955993652, "global_step": 567534, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0508341789245605, "global_step": 567535, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0860073566436768, "global_step": 567536, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0461668968200684, "global_step": 567537, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.996025562286377, "global_step": 567538, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.037156820297241, "global_step": 567539, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.036555290222168, "global_step": 567540, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0414512157440186, "global_step": 567541, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0953328609466553, "global_step": 567542, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.019087076187134, "global_step": 567543, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0930819511413574, "global_step": 567544, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.012655019760132, "global_step": 567545, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0583596229553223, "global_step": 567546, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9970813989639282, "global_step": 567547, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9223556518554688, "global_step": 567548, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.021517038345337, "global_step": 567549, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0150578022003174, "global_step": 567550, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9874554872512817, "global_step": 567551, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.024052143096924, "global_step": 567552, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9984210729599, "global_step": 567553, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0414397716522217, "global_step": 567554, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9624443054199219, "global_step": 567555, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9917445182800293, "global_step": 567556, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0891964435577393, "global_step": 567557, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.050938606262207, "global_step": 567558, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0194718837738037, "global_step": 567559, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.962234377861023, "global_step": 567560, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.994623064994812, "global_step": 567561, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.000058650970459, "global_step": 567562, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9882320165634155, "global_step": 567563, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9660564661026, "global_step": 567564, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.007582664489746, "global_step": 567565, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.065018892288208, "global_step": 567566, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0487051010131836, "global_step": 567567, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1052026748657227, "global_step": 567568, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.989517092704773, "global_step": 567569, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0212090015411377, "global_step": 567570, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0227928161621094, "global_step": 567571, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.122593879699707, "global_step": 567572, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.048996925354004, "global_step": 567573, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.087332010269165, "global_step": 567574, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0025508403778076, "global_step": 567575, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9982985258102417, "global_step": 567576, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.001446485519409, "global_step": 567577, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0329246520996094, "global_step": 567578, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.014507532119751, "global_step": 567579, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.034574508666992, "global_step": 567580, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0619404315948486, "global_step": 567581, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0657365322113037, "global_step": 567582, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.033327102661133, "global_step": 567583, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0058200359344482, "global_step": 567584, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0143702030181885, "global_step": 567585, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0594863891601562, "global_step": 567586, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.041825294494629, "global_step": 567587, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.071514129638672, "global_step": 567588, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0723979473114014, "global_step": 567589, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.08894944190979, "global_step": 567590, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.042234420776367, "global_step": 567591, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.059083938598633, "global_step": 567592, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9888142347335815, "global_step": 567593, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9929460287094116, "global_step": 567594, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.023940086364746, "global_step": 567595, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0448899269104004, "global_step": 567596, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.05791974067688, "global_step": 567597, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9724360704421997, "global_step": 567598, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9732214212417603, "global_step": 567599, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9912872314453125, "global_step": 567600, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.058232545852661, "global_step": 567601, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1148452758789062, "global_step": 567602, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0720105171203613, "global_step": 567603, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.066781520843506, "global_step": 567604, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.027566432952881, "global_step": 567605, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.050696611404419, "global_step": 567606, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9647585153579712, "global_step": 567607, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.027867555618286, "global_step": 567608, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0116913318634033, "global_step": 567609, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9870617389678955, "global_step": 567610, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1037871837615967, "global_step": 567611, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0671050548553467, "global_step": 567612, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9250508546829224, "global_step": 567613, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.961031436920166, "global_step": 567614, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.032886028289795, "global_step": 567615, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.042306423187256, "global_step": 567616, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.064945697784424, "global_step": 567617, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.918975591659546, "global_step": 567618, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9724915027618408, "global_step": 567619, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.147202253341675, "global_step": 567620, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0311851501464844, "global_step": 567621, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0816102027893066, "global_step": 567622, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.037945032119751, "global_step": 567623, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9629631042480469, "global_step": 567624, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0550897121429443, "global_step": 567625, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.055696964263916, "global_step": 567626, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.053995370864868, "global_step": 567627, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.028583288192749, "global_step": 567628, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.011592149734497, "global_step": 567629, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9888942241668701, "global_step": 567630, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1411561965942383, "global_step": 567631, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.995639443397522, "global_step": 567632, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0205166339874268, "global_step": 567633, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0297179222106934, "global_step": 567634, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.104114294052124, "global_step": 567635, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.022512912750244, "global_step": 567636, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1108083724975586, "global_step": 567637, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1055665016174316, "global_step": 567638, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.015610456466675, "global_step": 567639, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9705893993377686, "global_step": 567640, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.057569742202759, "global_step": 567641, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9939900636672974, "global_step": 567642, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.023238182067871, "global_step": 567643, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.929028034210205, "global_step": 567644, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0366601943969727, "global_step": 567645, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.090806007385254, "global_step": 567646, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.126152276992798, "global_step": 567647, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0061135292053223, "global_step": 567648, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0444624423980713, "global_step": 567649, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.074821949005127, "global_step": 567650, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.023286819458008, "global_step": 567651, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.031815528869629, "global_step": 567652, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.040703058242798, "global_step": 567653, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0004589557647705, "global_step": 567654, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9821211099624634, "global_step": 567655, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.044670581817627, "global_step": 567656, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9914289712905884, "global_step": 567657, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0362117290496826, "global_step": 567658, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.034757375717163, "global_step": 567659, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0125160217285156, "global_step": 567660, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.02663254737854, "global_step": 567661, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.039469003677368, "global_step": 567662, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.017773389816284, "global_step": 567663, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.08335542678833, "global_step": 567664, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0584170818328857, "global_step": 567665, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.054316997528076, "global_step": 567666, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0267834663391113, "global_step": 567667, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9500583410263062, "global_step": 567668, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.999994158744812, "global_step": 567669, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0650384426116943, "global_step": 567670, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9620683193206787, "global_step": 567671, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9699621200561523, "global_step": 567672, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1216940879821777, "global_step": 567673, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0794944763183594, "global_step": 567674, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9773203134536743, "global_step": 567675, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0017459392547607, "global_step": 567676, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9498080015182495, "global_step": 567677, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9781835079193115, "global_step": 567678, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0912160873413086, "global_step": 567679, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.044363260269165, "global_step": 567680, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.99921715259552, "global_step": 567681, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.080435037612915, "global_step": 567682, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0554609298706055, "global_step": 567683, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.006754159927368, "global_step": 567684, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9482662677764893, "global_step": 567685, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.025435209274292, "global_step": 567686, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.040436029434204, "global_step": 567687, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0698020458221436, "global_step": 567688, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0188941955566406, "global_step": 567689, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0661284923553467, "global_step": 567690, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.07024884223938, "global_step": 567691, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0011088848114014, "global_step": 567692, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9065884351730347, "global_step": 567693, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9530144929885864, "global_step": 567694, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1021080017089844, "global_step": 567695, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9522204399108887, "global_step": 567696, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.982138991355896, "global_step": 567697, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.046538829803467, "global_step": 567698, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9619742631912231, "global_step": 567699, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0178582668304443, "global_step": 567700, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0288658142089844, "global_step": 567701, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0313429832458496, "global_step": 567702, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.965498447418213, "global_step": 567703, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9508908987045288, "global_step": 567704, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0726237297058105, "global_step": 567705, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.019667387008667, "global_step": 567706, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.056715250015259, "global_step": 567707, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.018965005874634, "global_step": 567708, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0261759757995605, "global_step": 567709, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.001911163330078, "global_step": 567710, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.018824815750122, "global_step": 567711, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9295042753219604, "global_step": 567712, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.058060884475708, "global_step": 567713, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0052523612976074, "global_step": 567714, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.031074285507202, "global_step": 567715, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0700206756591797, "global_step": 567716, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0795950889587402, "global_step": 567717, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.095698356628418, "global_step": 567718, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0185766220092773, "global_step": 567719, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0487234592437744, "global_step": 567720, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0390872955322266, "global_step": 567721, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.060894727706909, "global_step": 567722, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.067384958267212, "global_step": 567723, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.034550666809082, "global_step": 567724, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0276215076446533, "global_step": 567725, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0662150382995605, "global_step": 567726, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.124098062515259, "global_step": 567727, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0847413539886475, "global_step": 567728, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.062399387359619, "global_step": 567729, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.038957118988037, "global_step": 567730, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9677050113677979, "global_step": 567731, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9441099166870117, "global_step": 567732, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0077996253967285, "global_step": 567733, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0686535835266113, "global_step": 567734, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9629979133605957, "global_step": 567735, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.049187660217285, "global_step": 567736, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9691967964172363, "global_step": 567737, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.007575035095215, "global_step": 567738, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9972039461135864, "global_step": 567739, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0055506229400635, "global_step": 567740, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0202620029449463, "global_step": 567741, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0542407035827637, "global_step": 567742, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0106348991394043, "global_step": 567743, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.055034637451172, "global_step": 567744, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0980682373046875, "global_step": 567745, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0303916931152344, "global_step": 567746, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.065455675125122, "global_step": 567747, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0317654609680176, "global_step": 567748, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0325992107391357, "global_step": 567749, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0978012084960938, "global_step": 567750, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.090646505355835, "global_step": 567751, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.041123151779175, "global_step": 567752, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.06150221824646, "global_step": 567753, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9913798570632935, "global_step": 567754, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.057286500930786, "global_step": 567755, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0056257247924805, "global_step": 567756, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9671978950500488, "global_step": 567757, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.945114016532898, "global_step": 567758, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.964884877204895, "global_step": 567759, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1263070106506348, "global_step": 567760, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.978261113166809, "global_step": 567761, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9896636009216309, "global_step": 567762, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0481693744659424, "global_step": 567763, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9687508344650269, "global_step": 567764, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.004911184310913, "global_step": 567765, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0221753120422363, "global_step": 567766, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.065547227859497, "global_step": 567767, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0053346157073975, "global_step": 567768, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9630274772644043, "global_step": 567769, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9793081283569336, "global_step": 567770, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0119380950927734, "global_step": 567771, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0468056201934814, "global_step": 567772, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0481913089752197, "global_step": 567773, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0674691200256348, "global_step": 567774, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9784746170043945, "global_step": 567775, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0065243244171143, "global_step": 567776, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9130955934524536, "global_step": 567777, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1009671688079834, "global_step": 567778, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.060375928878784, "global_step": 567779, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.994752049446106, "global_step": 567780, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0812625885009766, "global_step": 567781, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.010101079940796, "global_step": 567782, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.050917625427246, "global_step": 567783, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9593652486801147, "global_step": 567784, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0392870903015137, "global_step": 567785, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9710108041763306, "global_step": 567786, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0226638317108154, "global_step": 567787, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9994441270828247, "global_step": 567788, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9894580841064453, "global_step": 567789, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.033691644668579, "global_step": 567790, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9498811960220337, "global_step": 567791, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.012777090072632, "global_step": 567792, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9940681457519531, "global_step": 567793, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0175857543945312, "global_step": 567794, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.028287649154663, "global_step": 567795, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.05336594581604, "global_step": 567796, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.071181297302246, "global_step": 567797, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9458762407302856, "global_step": 567798, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0472075939178467, "global_step": 567799, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1575238704681396, "global_step": 567800, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0130884647369385, "global_step": 567801, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0270166397094727, "global_step": 567802, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.035114288330078, "global_step": 567803, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.107896566390991, "global_step": 567804, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0012190341949463, "global_step": 567805, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9979543685913086, "global_step": 567806, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9851716756820679, "global_step": 567807, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.007350444793701, "global_step": 567808, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.003040313720703, "global_step": 567809, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0798466205596924, "global_step": 567810, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9473768472671509, "global_step": 567811, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9833589792251587, "global_step": 567812, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0724918842315674, "global_step": 567813, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0689826011657715, "global_step": 567814, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0323433876037598, "global_step": 567815, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0786943435668945, "global_step": 567816, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9686871767044067, "global_step": 567817, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.063541889190674, "global_step": 567818, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0078659057617188, "global_step": 567819, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.071488380432129, "global_step": 567820, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9904470443725586, "global_step": 567821, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.894448161125183, "global_step": 567822, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0929980278015137, "global_step": 567823, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0149035453796387, "global_step": 567824, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9221001863479614, "global_step": 567825, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0322699546813965, "global_step": 567826, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0740675926208496, "global_step": 567827, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.024799346923828, "global_step": 567828, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9838974475860596, "global_step": 567829, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0946500301361084, "global_step": 567830, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.973459005355835, "global_step": 567831, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9684834480285645, "global_step": 567832, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0042619705200195, "global_step": 567833, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.036478042602539, "global_step": 567834, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9821723699569702, "global_step": 567835, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.002577781677246, "global_step": 567836, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0355982780456543, "global_step": 567837, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.027941942214966, "global_step": 567838, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1247968673706055, "global_step": 567839, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.034911870956421, "global_step": 567840, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.027909994125366, "global_step": 567841, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0110630989074707, "global_step": 567842, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0624823570251465, "global_step": 567843, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9850033521652222, "global_step": 567844, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9878566265106201, "global_step": 567845, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9861198663711548, "global_step": 567846, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.063356399536133, "global_step": 567847, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0784685611724854, "global_step": 567848, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0263545513153076, "global_step": 567849, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0108461380004883, "global_step": 567850, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.080395221710205, "global_step": 567851, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0637011528015137, "global_step": 567852, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.985047459602356, "global_step": 567853, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0234861373901367, "global_step": 567854, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1214072704315186, "global_step": 567855, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9610097408294678, "global_step": 567856, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0350825786590576, "global_step": 567857, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.00095534324646, "global_step": 567858, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.102724313735962, "global_step": 567859, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9503028392791748, "global_step": 567860, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0065417289733887, "global_step": 567861, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0382614135742188, "global_step": 567862, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.966483473777771, "global_step": 567863, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.094841480255127, "global_step": 567864, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9859248399734497, "global_step": 567865, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.001024007797241, "global_step": 567866, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0478012561798096, "global_step": 567867, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0335958003997803, "global_step": 567868, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9819430112838745, "global_step": 567869, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0644383430480957, "global_step": 567870, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9997482299804688, "global_step": 567871, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.070668935775757, "global_step": 567872, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0085513591766357, "global_step": 567873, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9628582000732422, "global_step": 567874, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0560367107391357, "global_step": 567875, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.021364688873291, "global_step": 567876, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.981058955192566, "global_step": 567877, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0093917846679688, "global_step": 567878, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9585626125335693, "global_step": 567879, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.051710367202759, "global_step": 567880, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0784735679626465, "global_step": 567881, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.001617670059204, "global_step": 567882, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9582748413085938, "global_step": 567883, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.098780632019043, "global_step": 567884, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0623106956481934, "global_step": 567885, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.014293909072876, "global_step": 567886, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9663913249969482, "global_step": 567887, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0448100566864014, "global_step": 567888, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.065183162689209, "global_step": 567889, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.009073257446289, "global_step": 567890, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0143074989318848, "global_step": 567891, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9529472589492798, "global_step": 567892, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0377302169799805, "global_step": 567893, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.06406569480896, "global_step": 567894, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0332343578338623, "global_step": 567895, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.074651002883911, "global_step": 567896, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9689555168151855, "global_step": 567897, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9936414957046509, "global_step": 567898, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.025294303894043, "global_step": 567899, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0109176635742188, "global_step": 567900, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.047390937805176, "global_step": 567901, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9695205688476562, "global_step": 567902, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.985098123550415, "global_step": 567903, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.005790948867798, "global_step": 567904, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.960545301437378, "global_step": 567905, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.124516487121582, "global_step": 567906, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0517611503601074, "global_step": 567907, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.075652837753296, "global_step": 567908, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0078248977661133, "global_step": 567909, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9756896495819092, "global_step": 567910, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0118587017059326, "global_step": 567911, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0829780101776123, "global_step": 567912, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0184245109558105, "global_step": 567913, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1177051067352295, "global_step": 567914, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.048835515975952, "global_step": 567915, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0796468257904053, "global_step": 567916, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0632927417755127, "global_step": 567917, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9450792074203491, "global_step": 567918, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.95586097240448, "global_step": 567919, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9840518236160278, "global_step": 567920, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9708948135375977, "global_step": 567921, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9795856475830078, "global_step": 567922, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.041367769241333, "global_step": 567923, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0853590965270996, "global_step": 567924, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0518343448638916, "global_step": 567925, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1371917724609375, "global_step": 567926, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.030808925628662, "global_step": 567927, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9971957206726074, "global_step": 567928, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.025275945663452, "global_step": 567929, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.984153151512146, "global_step": 567930, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9920519590377808, "global_step": 567931, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.056487560272217, "global_step": 567932, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.979201316833496, "global_step": 567933, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.079587936401367, "global_step": 567934, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.093285083770752, "global_step": 567935, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0544207096099854, "global_step": 567936, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9430880546569824, "global_step": 567937, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0375850200653076, "global_step": 567938, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9842687845230103, "global_step": 567939, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9584616422653198, "global_step": 567940, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.065911293029785, "global_step": 567941, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.002485513687134, "global_step": 567942, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0114641189575195, "global_step": 567943, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.054769992828369, "global_step": 567944, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.962450623512268, "global_step": 567945, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.026763916015625, "global_step": 567946, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0225563049316406, "global_step": 567947, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0208373069763184, "global_step": 567948, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0193378925323486, "global_step": 567949, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9969820976257324, "global_step": 567950, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.111640691757202, "global_step": 567951, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0582029819488525, "global_step": 567952, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1126837730407715, "global_step": 567953, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.134558916091919, "global_step": 567954, "epoch": 935, "lr": 5e-05}
{"train_loss": 1.9564969539642334, "global_step": 567955, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0743730068206787, "global_step": 567956, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.1321725845336914, "global_step": 567957, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.10347580909729, "global_step": 567958, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0363879203796387, "global_step": 567959, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.077547550201416, "global_step": 567960, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0255815982818604, "global_step": 567961, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.078770637512207, "global_step": 567962, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.090420722961426, "global_step": 567963, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.040536403656006, "global_step": 567964, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0593740940093994, "global_step": 567965, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.0240564346313477, "global_step": 567966, "epoch": 935, "lr": 5e-05}
{"train_loss": 2.009030342102051, "global_step": 567967, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.047311544418335, "global_step": 567968, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.028839111328125, "global_step": 567969, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9690537452697754, "global_step": 567970, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9501515626907349, "global_step": 567971, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9939535856246948, "global_step": 567972, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0268821716308594, "global_step": 567973, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.924468755722046, "global_step": 567974, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9830373525619507, "global_step": 567975, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0526130199432373, "global_step": 567976, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.059067726135254, "global_step": 567977, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.038207769393921, "global_step": 567978, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0198445320129395, "global_step": 567979, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.045837163925171, "global_step": 567980, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.939357876777649, "global_step": 567981, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0080533027648926, "global_step": 567982, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0506811141967773, "global_step": 567983, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0762062072753906, "global_step": 567984, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9894708395004272, "global_step": 567985, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.92862069606781, "global_step": 567986, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0429909229278564, "global_step": 567987, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1172897815704346, "global_step": 567988, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.069068670272827, "global_step": 567989, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0195999145507812, "global_step": 567990, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9641621112823486, "global_step": 567991, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9591832160949707, "global_step": 567992, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.002246856689453, "global_step": 567993, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.049283504486084, "global_step": 567994, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.038522481918335, "global_step": 567995, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9898463487625122, "global_step": 567996, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.093496799468994, "global_step": 567997, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.056108236312866, "global_step": 567998, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.104013204574585, "global_step": 567999, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9699925184249878, "global_step": 568000, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.044867992401123, "global_step": 568001, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9298685789108276, "global_step": 568002, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.063580274581909, "global_step": 568003, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0201711654663086, "global_step": 568004, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.012077569961548, "global_step": 568005, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.028780460357666, "global_step": 568006, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9915655851364136, "global_step": 568007, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.04243540763855, "global_step": 568008, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.067443609237671, "global_step": 568009, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.028963804244995, "global_step": 568010, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9861646890640259, "global_step": 568011, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0121097564697266, "global_step": 568012, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.016808271408081, "global_step": 568013, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.034125804901123, "global_step": 568014, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9631932973861694, "global_step": 568015, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.049145460128784, "global_step": 568016, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0537829399108887, "global_step": 568017, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0236005783081055, "global_step": 568018, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.040884017944336, "global_step": 568019, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9225338697433472, "global_step": 568020, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1289784908294678, "global_step": 568021, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9605780839920044, "global_step": 568022, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0558979511260986, "global_step": 568023, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.123457670211792, "global_step": 568024, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0584356784820557, "global_step": 568025, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.018895149230957, "global_step": 568026, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.08734130859375, "global_step": 568027, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.044065237045288, "global_step": 568028, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.042675733566284, "global_step": 568029, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9799479246139526, "global_step": 568030, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.016948699951172, "global_step": 568031, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0236411094665527, "global_step": 568032, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.978212594985962, "global_step": 568033, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0497219562530518, "global_step": 568034, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0071611404418945, "global_step": 568035, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9939430952072144, "global_step": 568036, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9665162563323975, "global_step": 568037, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9832923412322998, "global_step": 568038, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0096988677978516, "global_step": 568039, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9394365549087524, "global_step": 568040, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0219011306762695, "global_step": 568041, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0324857234954834, "global_step": 568042, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9807593822479248, "global_step": 568043, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0720713138580322, "global_step": 568044, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.163095474243164, "global_step": 568045, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0452423095703125, "global_step": 568046, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0529658794403076, "global_step": 568047, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.027482748031616, "global_step": 568048, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.008835792541504, "global_step": 568049, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.014357805252075, "global_step": 568050, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0444045066833496, "global_step": 568051, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.019174575805664, "global_step": 568052, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.065235137939453, "global_step": 568053, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9968624114990234, "global_step": 568054, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9781768321990967, "global_step": 568055, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0001697540283203, "global_step": 568056, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9936063289642334, "global_step": 568057, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9732341766357422, "global_step": 568058, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0569379329681396, "global_step": 568059, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9868779182434082, "global_step": 568060, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.995929479598999, "global_step": 568061, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.043689489364624, "global_step": 568062, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9907716512680054, "global_step": 568063, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.038418769836426, "global_step": 568064, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.031602382659912, "global_step": 568065, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9793509244918823, "global_step": 568066, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9794868230819702, "global_step": 568067, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.8855791091918945, "global_step": 568068, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0742626190185547, "global_step": 568069, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0436336994171143, "global_step": 568070, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9511550664901733, "global_step": 568071, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9930148124694824, "global_step": 568072, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0073318481445312, "global_step": 568073, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.115006923675537, "global_step": 568074, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.950746774673462, "global_step": 568075, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0690605640411377, "global_step": 568076, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.994908332824707, "global_step": 568077, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9959462881088257, "global_step": 568078, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9239015579223633, "global_step": 568079, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9780234098434448, "global_step": 568080, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.173410654067993, "global_step": 568081, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9875211715698242, "global_step": 568082, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.037409543991089, "global_step": 568083, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.995365858078003, "global_step": 568084, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0038981437683105, "global_step": 568085, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9454538822174072, "global_step": 568086, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.985328197479248, "global_step": 568087, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0471794605255127, "global_step": 568088, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9641791582107544, "global_step": 568089, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0010361671447754, "global_step": 568090, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0164685249328613, "global_step": 568091, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0064051151275635, "global_step": 568092, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9922579526901245, "global_step": 568093, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0163614749908447, "global_step": 568094, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0215604305267334, "global_step": 568095, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.149317741394043, "global_step": 568096, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9906120300292969, "global_step": 568097, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0435574054718018, "global_step": 568098, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0082199573516846, "global_step": 568099, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9206212759017944, "global_step": 568100, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9845653772354126, "global_step": 568101, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.999936580657959, "global_step": 568102, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.069347858428955, "global_step": 568103, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.01425838470459, "global_step": 568104, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9692610502243042, "global_step": 568105, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.015162944793701, "global_step": 568106, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.107774257659912, "global_step": 568107, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9559271335601807, "global_step": 568108, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9979376792907715, "global_step": 568109, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9844746589660645, "global_step": 568110, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9664067029953003, "global_step": 568111, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9458668231964111, "global_step": 568112, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.025543451309204, "global_step": 568113, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0067765712738037, "global_step": 568114, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9662405252456665, "global_step": 568115, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0079827308654785, "global_step": 568116, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9626413583755493, "global_step": 568117, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9335726499557495, "global_step": 568118, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9298874139785767, "global_step": 568119, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.035027503967285, "global_step": 568120, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.998293161392212, "global_step": 568121, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1135611534118652, "global_step": 568122, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.083339214324951, "global_step": 568123, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1007885932922363, "global_step": 568124, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0155839920043945, "global_step": 568125, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9958508014678955, "global_step": 568126, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.013566493988037, "global_step": 568127, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0829379558563232, "global_step": 568128, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.063399076461792, "global_step": 568129, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9860097169876099, "global_step": 568130, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9764243364334106, "global_step": 568131, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.047703742980957, "global_step": 568132, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9176857471466064, "global_step": 568133, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9944250583648682, "global_step": 568134, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0298681259155273, "global_step": 568135, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.987170934677124, "global_step": 568136, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.979880690574646, "global_step": 568137, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0066936016082764, "global_step": 568138, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.979079008102417, "global_step": 568139, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0268499851226807, "global_step": 568140, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9783661365509033, "global_step": 568141, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0177090167999268, "global_step": 568142, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0911622047424316, "global_step": 568143, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0837154388427734, "global_step": 568144, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9861209392547607, "global_step": 568145, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9772663116455078, "global_step": 568146, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9880434274673462, "global_step": 568147, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9996392726898193, "global_step": 568148, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.001281499862671, "global_step": 568149, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0986132621765137, "global_step": 568150, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.025125741958618, "global_step": 568151, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.067255735397339, "global_step": 568152, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0267510414123535, "global_step": 568153, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.051010847091675, "global_step": 568154, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.958464503288269, "global_step": 568155, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9774041175842285, "global_step": 568156, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0062286853790283, "global_step": 568157, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.042903423309326, "global_step": 568158, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0135133266448975, "global_step": 568159, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.082617998123169, "global_step": 568160, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9968377351760864, "global_step": 568161, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0384414196014404, "global_step": 568162, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.098790168762207, "global_step": 568163, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9985861778259277, "global_step": 568164, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9253830909729004, "global_step": 568165, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.963876485824585, "global_step": 568166, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0866615772247314, "global_step": 568167, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0069692134857178, "global_step": 568168, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.056955337524414, "global_step": 568169, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.042050361633301, "global_step": 568170, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0532174110412598, "global_step": 568171, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0339295864105225, "global_step": 568172, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.982447862625122, "global_step": 568173, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.96928071975708, "global_step": 568174, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0626323223114014, "global_step": 568175, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0187888145446777, "global_step": 568176, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.066632032394409, "global_step": 568177, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.048257350921631, "global_step": 568178, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9678295850753784, "global_step": 568179, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1054763793945312, "global_step": 568180, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.088592290878296, "global_step": 568181, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9519740343093872, "global_step": 568182, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9444724321365356, "global_step": 568183, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9707614183425903, "global_step": 568184, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0540947914123535, "global_step": 568185, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0976765155792236, "global_step": 568186, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9051390886306763, "global_step": 568187, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0432863235473633, "global_step": 568188, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0223615169525146, "global_step": 568189, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0017738342285156, "global_step": 568190, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9928412437438965, "global_step": 568191, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.979518175125122, "global_step": 568192, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9917253255844116, "global_step": 568193, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.069260835647583, "global_step": 568194, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.046997547149658, "global_step": 568195, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.05787992477417, "global_step": 568196, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9830386638641357, "global_step": 568197, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9772615432739258, "global_step": 568198, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0560455322265625, "global_step": 568199, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9460537433624268, "global_step": 568200, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9951581954956055, "global_step": 568201, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.008453369140625, "global_step": 568202, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0741119384765625, "global_step": 568203, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.04532790184021, "global_step": 568204, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.982065200805664, "global_step": 568205, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9637086391448975, "global_step": 568206, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9712929725646973, "global_step": 568207, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0058789253234863, "global_step": 568208, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.917556881904602, "global_step": 568209, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9904263019561768, "global_step": 568210, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.044095039367676, "global_step": 568211, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0082955360412598, "global_step": 568212, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9792418479919434, "global_step": 568213, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9765021800994873, "global_step": 568214, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.985823392868042, "global_step": 568215, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.057126760482788, "global_step": 568216, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0195515155792236, "global_step": 568217, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.011162281036377, "global_step": 568218, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.061053514480591, "global_step": 568219, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9833831787109375, "global_step": 568220, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0150036811828613, "global_step": 568221, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.014206647872925, "global_step": 568222, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0599749088287354, "global_step": 568223, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.067355155944824, "global_step": 568224, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9833009243011475, "global_step": 568225, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0653226375579834, "global_step": 568226, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.973606824874878, "global_step": 568227, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9566656351089478, "global_step": 568228, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0045347213745117, "global_step": 568229, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0157454013824463, "global_step": 568230, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0253002643585205, "global_step": 568231, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.005816698074341, "global_step": 568232, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9411227703094482, "global_step": 568233, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0671746730804443, "global_step": 568234, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1044719219207764, "global_step": 568235, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.018057346343994, "global_step": 568236, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.011646032333374, "global_step": 568237, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.046218156814575, "global_step": 568238, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0674617290496826, "global_step": 568239, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.025078296661377, "global_step": 568240, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9517769813537598, "global_step": 568241, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.051508903503418, "global_step": 568242, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0566956996917725, "global_step": 568243, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9908443689346313, "global_step": 568244, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.033297538757324, "global_step": 568245, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0328643321990967, "global_step": 568246, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0170557498931885, "global_step": 568247, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1039164066314697, "global_step": 568248, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.000314235687256, "global_step": 568249, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0579445362091064, "global_step": 568250, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0427544116973877, "global_step": 568251, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9486337900161743, "global_step": 568252, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9668077230453491, "global_step": 568253, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0669257640838623, "global_step": 568254, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9563740491867065, "global_step": 568255, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.093219041824341, "global_step": 568256, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.995752215385437, "global_step": 568257, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.08587646484375, "global_step": 568258, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9984750747680664, "global_step": 568259, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.082242965698242, "global_step": 568260, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.002365827560425, "global_step": 568261, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9981610774993896, "global_step": 568262, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0506591796875, "global_step": 568263, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0665793418884277, "global_step": 568264, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9342180490493774, "global_step": 568265, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9929176568984985, "global_step": 568266, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0713727474212646, "global_step": 568267, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0324933528900146, "global_step": 568268, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0922799110412598, "global_step": 568269, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0098891258239746, "global_step": 568270, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.980066180229187, "global_step": 568271, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.930094599723816, "global_step": 568272, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0542678833007812, "global_step": 568273, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.977889060974121, "global_step": 568274, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.957474708557129, "global_step": 568275, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.103520631790161, "global_step": 568276, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.010986328125, "global_step": 568277, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0135934352874756, "global_step": 568278, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9857866764068604, "global_step": 568279, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9649434089660645, "global_step": 568280, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.01432728767395, "global_step": 568281, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0082218647003174, "global_step": 568282, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9967560768127441, "global_step": 568283, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9718234539031982, "global_step": 568284, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.987391710281372, "global_step": 568285, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9832658767700195, "global_step": 568286, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0367112159729004, "global_step": 568287, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9748204946517944, "global_step": 568288, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0161397457122803, "global_step": 568289, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9797143936157227, "global_step": 568290, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0112123489379883, "global_step": 568291, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1007630825042725, "global_step": 568292, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.954960823059082, "global_step": 568293, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0218894481658936, "global_step": 568294, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9716684818267822, "global_step": 568295, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0090012550354004, "global_step": 568296, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0667672157287598, "global_step": 568297, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.972763180732727, "global_step": 568298, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0115771293640137, "global_step": 568299, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0547919273376465, "global_step": 568300, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9720916748046875, "global_step": 568301, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0563085079193115, "global_step": 568302, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.976560354232788, "global_step": 568303, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.941288709640503, "global_step": 568304, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0378968715667725, "global_step": 568305, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.064014196395874, "global_step": 568306, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.014789342880249, "global_step": 568307, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.012515068054199, "global_step": 568308, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0317842960357666, "global_step": 568309, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0383119583129883, "global_step": 568310, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.003615379333496, "global_step": 568311, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0196914672851562, "global_step": 568312, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9442696571350098, "global_step": 568313, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.013017416000366, "global_step": 568314, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.043515205383301, "global_step": 568315, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.963753581047058, "global_step": 568316, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0447192192077637, "global_step": 568317, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9446333646774292, "global_step": 568318, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0254156589508057, "global_step": 568319, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.000675916671753, "global_step": 568320, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9687753915786743, "global_step": 568321, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9860305786132812, "global_step": 568322, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.003145217895508, "global_step": 568323, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.061006784439087, "global_step": 568324, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9941047430038452, "global_step": 568325, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0897674560546875, "global_step": 568326, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.01792049407959, "global_step": 568327, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.040630578994751, "global_step": 568328, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0332531929016113, "global_step": 568329, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.989188551902771, "global_step": 568330, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0554311275482178, "global_step": 568331, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.116760015487671, "global_step": 568332, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.021026134490967, "global_step": 568333, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.028352975845337, "global_step": 568334, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9893620014190674, "global_step": 568335, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.907641053199768, "global_step": 568336, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.999642252922058, "global_step": 568337, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0339269638061523, "global_step": 568338, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0456626415252686, "global_step": 568339, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.985000729560852, "global_step": 568340, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.020193338394165, "global_step": 568341, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.984938144683838, "global_step": 568342, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0678765773773193, "global_step": 568343, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0396575927734375, "global_step": 568344, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9833308458328247, "global_step": 568345, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.066563844680786, "global_step": 568346, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9751336574554443, "global_step": 568347, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0584864616394043, "global_step": 568348, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0320165157318115, "global_step": 568349, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0742347240448, "global_step": 568350, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.091702699661255, "global_step": 568351, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.048604965209961, "global_step": 568352, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.027094602584839, "global_step": 568353, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0310020446777344, "global_step": 568354, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.055227041244507, "global_step": 568355, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.039198398590088, "global_step": 568356, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0335843563079834, "global_step": 568357, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.042759895324707, "global_step": 568358, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9886475801467896, "global_step": 568359, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0713448524475098, "global_step": 568360, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0272934436798096, "global_step": 568361, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.027798891067505, "global_step": 568362, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0441579818725586, "global_step": 568363, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9616966247558594, "global_step": 568364, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.042771816253662, "global_step": 568365, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0394394397735596, "global_step": 568366, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0331785678863525, "global_step": 568367, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9919607639312744, "global_step": 568368, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9775766134262085, "global_step": 568369, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9675899744033813, "global_step": 568370, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9670451879501343, "global_step": 568371, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9919536113739014, "global_step": 568372, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9294121265411377, "global_step": 568373, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0059072971343994, "global_step": 568374, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.058864116668701, "global_step": 568375, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9370884895324707, "global_step": 568376, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9948525428771973, "global_step": 568377, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0472171306610107, "global_step": 568378, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.045734167098999, "global_step": 568379, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0446219444274902, "global_step": 568380, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0846939086914062, "global_step": 568381, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.035731315612793, "global_step": 568382, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0093202590942383, "global_step": 568383, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9835007190704346, "global_step": 568384, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0626847743988037, "global_step": 568385, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9910296201705933, "global_step": 568386, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9923309087753296, "global_step": 568387, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.058727979660034, "global_step": 568388, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.019184112548828, "global_step": 568389, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.039689302444458, "global_step": 568390, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.005844831466675, "global_step": 568391, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0564074516296387, "global_step": 568392, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9287903308868408, "global_step": 568393, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.081364631652832, "global_step": 568394, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.987093210220337, "global_step": 568395, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0773754119873047, "global_step": 568396, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0580122470855713, "global_step": 568397, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0269641876220703, "global_step": 568398, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9929814338684082, "global_step": 568399, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.995198369026184, "global_step": 568400, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9550331830978394, "global_step": 568401, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9369717836380005, "global_step": 568402, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0167996883392334, "global_step": 568403, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.047140598297119, "global_step": 568404, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0325779914855957, "global_step": 568405, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.02644944190979, "global_step": 568406, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9690475463867188, "global_step": 568407, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.028341054916382, "global_step": 568408, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9975574016571045, "global_step": 568409, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0293381214141846, "global_step": 568410, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9912235736846924, "global_step": 568411, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.003995656967163, "global_step": 568412, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0480055809020996, "global_step": 568413, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.020531415939331, "global_step": 568414, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0490121841430664, "global_step": 568415, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9717061519622803, "global_step": 568416, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9939745664596558, "global_step": 568417, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9907405376434326, "global_step": 568418, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1260595321655273, "global_step": 568419, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.052866220474243, "global_step": 568420, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.034101724624634, "global_step": 568421, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.002941370010376, "global_step": 568422, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9682514667510986, "global_step": 568423, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9351991415023804, "global_step": 568424, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0640735626220703, "global_step": 568425, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0428519248962402, "global_step": 568426, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0025174617767334, "global_step": 568427, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.041268825531006, "global_step": 568428, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9879008531570435, "global_step": 568429, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9995986223220825, "global_step": 568430, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.038005828857422, "global_step": 568431, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0879480838775635, "global_step": 568432, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1009624004364014, "global_step": 568433, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9991400241851807, "global_step": 568434, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.089681625366211, "global_step": 568435, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0491387844085693, "global_step": 568436, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.051755905151367, "global_step": 568437, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0138909816741943, "global_step": 568438, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9647923707962036, "global_step": 568439, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9302618503570557, "global_step": 568440, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.085430145263672, "global_step": 568441, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9992287158966064, "global_step": 568442, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0367231369018555, "global_step": 568443, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.026536464691162, "global_step": 568444, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9843711853027344, "global_step": 568445, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9283862113952637, "global_step": 568446, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0304954051971436, "global_step": 568447, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0430142879486084, "global_step": 568448, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9745126962661743, "global_step": 568449, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.019299030303955, "global_step": 568450, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9406192302703857, "global_step": 568451, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.010692596435547, "global_step": 568452, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.009063959121704, "global_step": 568453, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9711898565292358, "global_step": 568454, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0037930011749268, "global_step": 568455, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.102832555770874, "global_step": 568456, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0225231647491455, "global_step": 568457, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9498333930969238, "global_step": 568458, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0201377868652344, "global_step": 568459, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9886797666549683, "global_step": 568460, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0365023612976074, "global_step": 568461, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9262940883636475, "global_step": 568462, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.002096176147461, "global_step": 568463, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9988185167312622, "global_step": 568464, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.073662281036377, "global_step": 568465, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0615086555480957, "global_step": 568466, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.980540156364441, "global_step": 568467, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.054172992706299, "global_step": 568468, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0933661460876465, "global_step": 568469, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9624468088150024, "global_step": 568470, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0435378551483154, "global_step": 568471, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0912790298461914, "global_step": 568472, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.113503932952881, "global_step": 568473, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.080371856689453, "global_step": 568474, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9269503355026245, "global_step": 568475, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0186567306518555, "global_step": 568476, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0275321006774902, "global_step": 568477, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.123032331466675, "global_step": 568478, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.017082691192627, "global_step": 568479, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0181307792663574, "global_step": 568480, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0001559257507324, "global_step": 568481, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.990010380744934, "global_step": 568482, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.050884246826172, "global_step": 568483, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.007833480834961, "global_step": 568484, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.033968448638916, "global_step": 568485, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0064022541046143, "global_step": 568486, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0563125610351562, "global_step": 568487, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9668076038360596, "global_step": 568488, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9680981636047363, "global_step": 568489, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9682575464248657, "global_step": 568490, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0349929332733154, "global_step": 568491, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0475082397460938, "global_step": 568492, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0204198360443115, "global_step": 568493, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9886505603790283, "global_step": 568494, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0077872276306152, "global_step": 568495, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0209264755249023, "global_step": 568496, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0379393100738525, "global_step": 568497, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.016892194747925, "global_step": 568498, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0282347202301025, "global_step": 568499, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.986340045928955, "global_step": 568500, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9163577556610107, "global_step": 568501, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0878450870513916, "global_step": 568502, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9885404109954834, "global_step": 568503, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.054975748062134, "global_step": 568504, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.071983814239502, "global_step": 568505, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.110548257827759, "global_step": 568506, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.032170534133911, "global_step": 568507, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9688876867294312, "global_step": 568508, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.034214973449707, "global_step": 568509, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.040337324142456, "global_step": 568510, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0170440673828125, "global_step": 568511, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0415546894073486, "global_step": 568512, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0598483085632324, "global_step": 568513, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0199778079986572, "global_step": 568514, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0469958782196045, "global_step": 568515, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0208284854888916, "global_step": 568516, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.115489959716797, "global_step": 568517, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.079477548599243, "global_step": 568518, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9529811143875122, "global_step": 568519, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0190796852111816, "global_step": 568520, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9590991735458374, "global_step": 568521, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0486249923706055, "global_step": 568522, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.060213565826416, "global_step": 568523, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0604259967803955, "global_step": 568524, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.014341354370117, "global_step": 568525, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0460031032562256, "global_step": 568526, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1098148822784424, "global_step": 568527, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.007251262664795, "global_step": 568528, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.166081190109253, "global_step": 568529, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0165576934814453, "global_step": 568530, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0518391132354736, "global_step": 568531, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0823581218719482, "global_step": 568532, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.027352809906006, "global_step": 568533, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9482611417770386, "global_step": 568534, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9173942804336548, "global_step": 568535, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9930691719055176, "global_step": 568536, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0124740600585938, "global_step": 568537, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.07300066947937, "global_step": 568538, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0102617740631104, "global_step": 568539, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.958605408668518, "global_step": 568540, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0755178928375244, "global_step": 568541, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0671117305755615, "global_step": 568542, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9379322528839111, "global_step": 568543, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0386013984680176, "global_step": 568544, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0008468627929688, "global_step": 568545, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.014007568359375, "global_step": 568546, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9230504035949707, "global_step": 568547, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.03631329536438, "global_step": 568548, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.091151237487793, "global_step": 568549, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.106720209121704, "global_step": 568550, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.03975248336792, "global_step": 568551, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0495097637176514, "global_step": 568552, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.017881393432617, "global_step": 568553, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.086172342300415, "global_step": 568554, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0689520835876465, "global_step": 568555, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9917935132980347, "global_step": 568556, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0455074310302734, "global_step": 568557, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9000470638275146, "global_step": 568558, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.052578926086426, "global_step": 568559, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0223031044006348, "global_step": 568560, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9472463130950928, "global_step": 568561, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9824864864349365, "global_step": 568562, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0565688610076904, "global_step": 568563, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0195417404174805, "global_step": 568564, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0947940349578857, "global_step": 568565, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.98636794090271, "global_step": 568566, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9735276699066162, "global_step": 568567, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.030073642730713, "global_step": 568568, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0607776641845703, "global_step": 568569, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9818990230560303, "global_step": 568570, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0401968955993652, "global_step": 568571, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.004894495010376, "global_step": 568572, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9792349338531494, "global_step": 568573, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9707409143447876, "global_step": 568574, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9585810899734497, "global_step": 568575, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9682315587997437, "global_step": 568576, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0287046432495117, "global_step": 568577, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0632498264312744, "global_step": 568578, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.128129482269287, "global_step": 568579, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9670705795288086, "global_step": 568580, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.957234263420105, "global_step": 568581, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0317437648773193, "global_step": 568582, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0641520023345947, "global_step": 568583, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9555264711380005, "global_step": 568584, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.01131272315979, "global_step": 568585, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0773234367370605, "global_step": 568586, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9713232517242432, "global_step": 568587, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.059898614883423, "global_step": 568588, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9687124490737915, "global_step": 568589, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.12839937210083, "global_step": 568590, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.006654739379883, "global_step": 568591, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.105134963989258, "global_step": 568592, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9370622634887695, "global_step": 568593, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0996930599212646, "global_step": 568594, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.041926622390747, "global_step": 568595, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0744659900665283, "global_step": 568596, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.065457582473755, "global_step": 568597, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.016566514968872, "global_step": 568598, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0531747341156006, "global_step": 568599, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.008708953857422, "global_step": 568600, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9678959846496582, "global_step": 568601, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0277445316314697, "global_step": 568602, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9711753129959106, "global_step": 568603, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0369765758514404, "global_step": 568604, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0440080165863037, "global_step": 568605, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0078330039978027, "global_step": 568606, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.037501811981201, "global_step": 568607, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9997305870056152, "global_step": 568608, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0466785430908203, "global_step": 568609, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9958343505859375, "global_step": 568610, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0294220447540283, "global_step": 568611, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.97176194190979, "global_step": 568612, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.048161506652832, "global_step": 568613, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9980567693710327, "global_step": 568614, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9684028625488281, "global_step": 568615, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.027599811553955, "global_step": 568616, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0094258785247803, "global_step": 568617, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9683459997177124, "global_step": 568618, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9987468719482422, "global_step": 568619, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9947319030761719, "global_step": 568620, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0033159255981445, "global_step": 568621, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.04447340965271, "global_step": 568622, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.105074405670166, "global_step": 568623, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9646724462509155, "global_step": 568624, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9837307929992676, "global_step": 568625, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.08217453956604, "global_step": 568626, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0934035778045654, "global_step": 568627, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.114225149154663, "global_step": 568628, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9784003496170044, "global_step": 568629, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0873148441314697, "global_step": 568630, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.008972406387329, "global_step": 568631, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.081568479537964, "global_step": 568632, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0015835762023926, "global_step": 568633, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9885698556900024, "global_step": 568634, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.995828628540039, "global_step": 568635, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0202760696411133, "global_step": 568636, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9948703050613403, "global_step": 568637, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.995928406715393, "global_step": 568638, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9793552160263062, "global_step": 568639, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.172321081161499, "global_step": 568640, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0197560787200928, "global_step": 568641, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0093274116516113, "global_step": 568642, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.004493236541748, "global_step": 568643, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9491156339645386, "global_step": 568644, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9334447383880615, "global_step": 568645, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.944798469543457, "global_step": 568646, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.125969886779785, "global_step": 568647, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.006474256515503, "global_step": 568648, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0654685497283936, "global_step": 568649, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0813560485839844, "global_step": 568650, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.106137990951538, "global_step": 568651, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0314927101135254, "global_step": 568652, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0641794204711914, "global_step": 568653, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.12359619140625, "global_step": 568654, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.04233455657959, "global_step": 568655, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0329596996307373, "global_step": 568656, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.034992218017578, "global_step": 568657, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.999719500541687, "global_step": 568658, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0935323238372803, "global_step": 568659, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9975069761276245, "global_step": 568660, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1465320587158203, "global_step": 568661, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0338897705078125, "global_step": 568662, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.029802083969116, "global_step": 568663, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0976595878601074, "global_step": 568664, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0612874031066895, "global_step": 568665, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.04162335395813, "global_step": 568666, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.121408700942993, "global_step": 568667, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0868711471557617, "global_step": 568668, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.00050950050354, "global_step": 568669, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9815583229064941, "global_step": 568670, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.05598783493042, "global_step": 568671, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0483920574188232, "global_step": 568672, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.988049030303955, "global_step": 568673, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.99167799949646, "global_step": 568674, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.092245578765869, "global_step": 568675, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0293893814086914, "global_step": 568676, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.029475450515747, "global_step": 568677, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0250251293182373, "global_step": 568678, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0129289627075195, "global_step": 568679, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.008599042892456, "global_step": 568680, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0160815715789795, "global_step": 568681, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0871763229370117, "global_step": 568682, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9913543462753296, "global_step": 568683, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.107447862625122, "global_step": 568684, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.053551435470581, "global_step": 568685, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.130525588989258, "global_step": 568686, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0013110637664795, "global_step": 568687, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.023019313812256, "global_step": 568688, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.8986165523529053, "global_step": 568689, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0894687175750732, "global_step": 568690, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0244834423065186, "global_step": 568691, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0064806938171387, "global_step": 568692, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.001765727996826, "global_step": 568693, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.05403733253479, "global_step": 568694, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0396153926849365, "global_step": 568695, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0266568660736084, "global_step": 568696, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9646477699279785, "global_step": 568697, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.045053243637085, "global_step": 568698, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.014507532119751, "global_step": 568699, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.023698091506958, "global_step": 568700, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9942972660064697, "global_step": 568701, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9425634145736694, "global_step": 568702, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0926809310913086, "global_step": 568703, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.978116512298584, "global_step": 568704, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0480167865753174, "global_step": 568705, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.082627773284912, "global_step": 568706, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0093579292297363, "global_step": 568707, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9599683284759521, "global_step": 568708, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1501731872558594, "global_step": 568709, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.03922176361084, "global_step": 568710, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.042483329772949, "global_step": 568711, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9857921600341797, "global_step": 568712, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.041196346282959, "global_step": 568713, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.042558193206787, "global_step": 568714, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9717258214950562, "global_step": 568715, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1034653186798096, "global_step": 568716, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.063838243484497, "global_step": 568717, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9605633020401, "global_step": 568718, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9718677997589111, "global_step": 568719, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9768452644348145, "global_step": 568720, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0096688270568848, "global_step": 568721, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.939173698425293, "global_step": 568722, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0712804794311523, "global_step": 568723, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0196897983551025, "global_step": 568724, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.037930727005005, "global_step": 568725, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.115250587463379, "global_step": 568726, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.047166585922241, "global_step": 568727, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9879246950149536, "global_step": 568728, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9589418172836304, "global_step": 568729, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.026024341583252, "global_step": 568730, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9426764249801636, "global_step": 568731, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0094614028930664, "global_step": 568732, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9799230098724365, "global_step": 568733, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.010962724685669, "global_step": 568734, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0563220977783203, "global_step": 568735, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0431313514709473, "global_step": 568736, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9803494215011597, "global_step": 568737, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9637418985366821, "global_step": 568738, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.990394115447998, "global_step": 568739, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9855773448944092, "global_step": 568740, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.021461248397827, "global_step": 568741, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0412497520446777, "global_step": 568742, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0655064582824707, "global_step": 568743, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9666703939437866, "global_step": 568744, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0492842197418213, "global_step": 568745, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.036811590194702, "global_step": 568746, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0262532234191895, "global_step": 568747, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0736796855926514, "global_step": 568748, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.075951337814331, "global_step": 568749, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.104092836380005, "global_step": 568750, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9843603372573853, "global_step": 568751, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0720229148864746, "global_step": 568752, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.072061777114868, "global_step": 568753, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.029305934906006, "global_step": 568754, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.074204921722412, "global_step": 568755, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9262503385543823, "global_step": 568756, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.099074602127075, "global_step": 568757, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.038184642791748, "global_step": 568758, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9768543243408203, "global_step": 568759, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.094492197036743, "global_step": 568760, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.071624517440796, "global_step": 568761, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0287675857543945, "global_step": 568762, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.008718490600586, "global_step": 568763, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9630203247070312, "global_step": 568764, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0260496139526367, "global_step": 568765, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0211336612701416, "global_step": 568766, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.071847915649414, "global_step": 568767, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.064917802810669, "global_step": 568768, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0554287433624268, "global_step": 568769, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0065391063690186, "global_step": 568770, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9627151489257812, "global_step": 568771, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0781631469726562, "global_step": 568772, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9997076988220215, "global_step": 568773, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.954535961151123, "global_step": 568774, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9949471950531006, "global_step": 568775, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.07746958732605, "global_step": 568776, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0521674156188965, "global_step": 568777, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9392929077148438, "global_step": 568778, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9800866842269897, "global_step": 568779, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1051735877990723, "global_step": 568780, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0003483295440674, "global_step": 568781, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0071468353271484, "global_step": 568782, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9716644287109375, "global_step": 568783, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.09670352935791, "global_step": 568784, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0363497734069824, "global_step": 568785, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.057816505432129, "global_step": 568786, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.038348913192749, "global_step": 568787, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.008955478668213, "global_step": 568788, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.075894594192505, "global_step": 568789, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.012681007385254, "global_step": 568790, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.078463554382324, "global_step": 568791, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.053762674331665, "global_step": 568792, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0427300930023193, "global_step": 568793, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.047962188720703, "global_step": 568794, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9815468788146973, "global_step": 568795, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.019395589828491, "global_step": 568796, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9912272691726685, "global_step": 568797, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0045838356018066, "global_step": 568798, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.039842128753662, "global_step": 568799, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.042368173599243, "global_step": 568800, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9568381309509277, "global_step": 568801, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0606322288513184, "global_step": 568802, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9984437227249146, "global_step": 568803, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0548861026763916, "global_step": 568804, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9945011138916016, "global_step": 568805, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.073718786239624, "global_step": 568806, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0029661655426025, "global_step": 568807, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.161763906478882, "global_step": 568808, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0036072731018066, "global_step": 568809, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0736753940582275, "global_step": 568810, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0420591831207275, "global_step": 568811, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0695242881774902, "global_step": 568812, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.994246244430542, "global_step": 568813, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.051973581314087, "global_step": 568814, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0155932903289795, "global_step": 568815, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.084144115447998, "global_step": 568816, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.068542242050171, "global_step": 568817, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0555121898651123, "global_step": 568818, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0022456645965576, "global_step": 568819, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9631866216659546, "global_step": 568820, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0590686798095703, "global_step": 568821, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.982945203781128, "global_step": 568822, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0535287857055664, "global_step": 568823, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.986470103263855, "global_step": 568824, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.023977518081665, "global_step": 568825, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.032985210418701, "global_step": 568826, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0504021644592285, "global_step": 568827, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1125645637512207, "global_step": 568828, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0029795169830322, "global_step": 568829, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.032750368118286, "global_step": 568830, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9723142385482788, "global_step": 568831, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9940128326416016, "global_step": 568832, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0285792350769043, "global_step": 568833, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9597828388214111, "global_step": 568834, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0516040325164795, "global_step": 568835, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.969581961631775, "global_step": 568836, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.008033275604248, "global_step": 568837, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0596165657043457, "global_step": 568838, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9713335037231445, "global_step": 568839, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0671286582946777, "global_step": 568840, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9787811040878296, "global_step": 568841, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0629587173461914, "global_step": 568842, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0894217491149902, "global_step": 568843, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0806784629821777, "global_step": 568844, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0662007331848145, "global_step": 568845, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0540645122528076, "global_step": 568846, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0467076301574707, "global_step": 568847, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.060817003250122, "global_step": 568848, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1075730323791504, "global_step": 568849, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9731273651123047, "global_step": 568850, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9820719957351685, "global_step": 568851, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0626399517059326, "global_step": 568852, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.082270383834839, "global_step": 568853, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0652332305908203, "global_step": 568854, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0563533306121826, "global_step": 568855, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0207762718200684, "global_step": 568856, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9434068202972412, "global_step": 568857, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.017683267593384, "global_step": 568858, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.035083293914795, "global_step": 568859, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.149712085723877, "global_step": 568860, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0638763904571533, "global_step": 568861, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.036432981491089, "global_step": 568862, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9503381252288818, "global_step": 568863, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0565223693847656, "global_step": 568864, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0596861839294434, "global_step": 568865, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.067385196685791, "global_step": 568866, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0210189819335938, "global_step": 568867, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0452849864959717, "global_step": 568868, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9811593294143677, "global_step": 568869, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.000861406326294, "global_step": 568870, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0435678958892822, "global_step": 568871, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0207254886627197, "global_step": 568872, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0261998176574707, "global_step": 568873, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0072789192199707, "global_step": 568874, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9394326210021973, "global_step": 568875, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0117571353912354, "global_step": 568876, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9626500606536865, "global_step": 568877, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0664494037628174, "global_step": 568878, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9498118162155151, "global_step": 568879, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9993155002593994, "global_step": 568880, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0425896644592285, "global_step": 568881, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9485077857971191, "global_step": 568882, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.004319667816162, "global_step": 568883, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.00203800201416, "global_step": 568884, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.027902364730835, "global_step": 568885, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0269322395324707, "global_step": 568886, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.016356945037842, "global_step": 568887, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0541489124298096, "global_step": 568888, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0236613750457764, "global_step": 568889, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0803732872009277, "global_step": 568890, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0357511043548584, "global_step": 568891, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.951417326927185, "global_step": 568892, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.047665596008301, "global_step": 568893, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.988887906074524, "global_step": 568894, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1243603229522705, "global_step": 568895, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0357158184051514, "global_step": 568896, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0208535194396973, "global_step": 568897, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0005736351013184, "global_step": 568898, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0473403930664062, "global_step": 568899, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.034179925918579, "global_step": 568900, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9936739206314087, "global_step": 568901, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0526368618011475, "global_step": 568902, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1334569454193115, "global_step": 568903, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0347769260406494, "global_step": 568904, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0381124019622803, "global_step": 568905, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.068286180496216, "global_step": 568906, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9459083080291748, "global_step": 568907, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0392725467681885, "global_step": 568908, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9782928228378296, "global_step": 568909, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1023080348968506, "global_step": 568910, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0494191646575928, "global_step": 568911, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9682790040969849, "global_step": 568912, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0152676105499268, "global_step": 568913, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1017580032348633, "global_step": 568914, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0536110401153564, "global_step": 568915, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9732489585876465, "global_step": 568916, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.044858932495117, "global_step": 568917, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0358641147613525, "global_step": 568918, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9986543655395508, "global_step": 568919, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0721867084503174, "global_step": 568920, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1016881465911865, "global_step": 568921, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.027953624725342, "global_step": 568922, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9480154514312744, "global_step": 568923, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0895180702209473, "global_step": 568924, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.128488063812256, "global_step": 568925, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9623048305511475, "global_step": 568926, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0361063480377197, "global_step": 568927, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0158658027648926, "global_step": 568928, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.1074318885803223, "global_step": 568929, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.960618495941162, "global_step": 568930, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0413570404052734, "global_step": 568931, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.0238282680511475, "global_step": 568932, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.019028425216675, "global_step": 568933, "epoch": 936, "lr": 5e-05}
{"train_loss": 1.9475220441818237, "global_step": 568934, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.021705150604248, "global_step": 568935, "epoch": 936, "lr": 5e-05}
{"train_loss": 2.056232213973999, "global_step": 568936, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0196585655212402, "global_step": 568937, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9451487064361572, "global_step": 568938, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9824498891830444, "global_step": 568939, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.045592784881592, "global_step": 568940, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.048860788345337, "global_step": 568941, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.023451089859009, "global_step": 568942, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9784822463989258, "global_step": 568943, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.023776054382324, "global_step": 568944, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0430967807769775, "global_step": 568945, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9575684070587158, "global_step": 568946, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.045506000518799, "global_step": 568947, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.955491065979004, "global_step": 568948, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1031763553619385, "global_step": 568949, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0561156272888184, "global_step": 568950, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0676729679107666, "global_step": 568951, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9885369539260864, "global_step": 568952, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0920627117156982, "global_step": 568953, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.001882553100586, "global_step": 568954, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9991315603256226, "global_step": 568955, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9798916578292847, "global_step": 568956, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0014870166778564, "global_step": 568957, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.008462905883789, "global_step": 568958, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0379953384399414, "global_step": 568959, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0233259201049805, "global_step": 568960, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.07015061378479, "global_step": 568961, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0151736736297607, "global_step": 568962, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9862022399902344, "global_step": 568963, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0781209468841553, "global_step": 568964, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.03165864944458, "global_step": 568965, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.967797875404358, "global_step": 568966, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0475568771362305, "global_step": 568967, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9977660179138184, "global_step": 568968, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.037276029586792, "global_step": 568969, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9638924598693848, "global_step": 568970, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.997489094734192, "global_step": 568971, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0676016807556152, "global_step": 568972, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.080383062362671, "global_step": 568973, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0320587158203125, "global_step": 568974, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1069071292877197, "global_step": 568975, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.099252223968506, "global_step": 568976, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9623960256576538, "global_step": 568977, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1051418781280518, "global_step": 568978, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.008007764816284, "global_step": 568979, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9694329500198364, "global_step": 568980, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.039882183074951, "global_step": 568981, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0119552612304688, "global_step": 568982, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.8665152788162231, "global_step": 568983, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9443795680999756, "global_step": 568984, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9811021089553833, "global_step": 568985, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0319862365722656, "global_step": 568986, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.025956869125366, "global_step": 568987, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.007143259048462, "global_step": 568988, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0429959297180176, "global_step": 568989, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0666871070861816, "global_step": 568990, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0205209255218506, "global_step": 568991, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9831804037094116, "global_step": 568992, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.099665403366089, "global_step": 568993, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0637526512145996, "global_step": 568994, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.049715995788574, "global_step": 568995, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9925249814987183, "global_step": 568996, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.001326322555542, "global_step": 568997, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0172624588012695, "global_step": 568998, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.968898892402649, "global_step": 568999, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.026047945022583, "global_step": 569000, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.932677149772644, "global_step": 569001, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0098061561584473, "global_step": 569002, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.014866590499878, "global_step": 569003, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9292255640029907, "global_step": 569004, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9871251583099365, "global_step": 569005, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1090970039367676, "global_step": 569006, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9239672422409058, "global_step": 569007, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9620572328567505, "global_step": 569008, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9996018409729004, "global_step": 569009, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0109148025512695, "global_step": 569010, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.040163516998291, "global_step": 569011, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1366846561431885, "global_step": 569012, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0465755462646484, "global_step": 569013, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0664966106414795, "global_step": 569014, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0035810470581055, "global_step": 569015, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0052220821380615, "global_step": 569016, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9493306875228882, "global_step": 569017, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0213775634765625, "global_step": 569018, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.98024320602417, "global_step": 569019, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9509681463241577, "global_step": 569020, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.009190320968628, "global_step": 569021, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0068085193634033, "global_step": 569022, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0068411827087402, "global_step": 569023, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.030885696411133, "global_step": 569024, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9629907608032227, "global_step": 569025, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1058878898620605, "global_step": 569026, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0448367595672607, "global_step": 569027, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9781168699264526, "global_step": 569028, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0026776790618896, "global_step": 569029, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0245978832244873, "global_step": 569030, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0108118057250977, "global_step": 569031, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0746681690216064, "global_step": 569032, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9477909803390503, "global_step": 569033, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9287009239196777, "global_step": 569034, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.980048656463623, "global_step": 569035, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0688588619232178, "global_step": 569036, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0245790481567383, "global_step": 569037, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0496771335601807, "global_step": 569038, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9781972169876099, "global_step": 569039, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9892350435256958, "global_step": 569040, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.076115846633911, "global_step": 569041, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9457846879959106, "global_step": 569042, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.019078016281128, "global_step": 569043, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9536718130111694, "global_step": 569044, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.009005069732666, "global_step": 569045, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.012669086456299, "global_step": 569046, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0645201206207275, "global_step": 569047, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9927223920822144, "global_step": 569048, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.106199264526367, "global_step": 569049, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.006831407546997, "global_step": 569050, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.002412796020508, "global_step": 569051, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.026965618133545, "global_step": 569052, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.040680408477783, "global_step": 569053, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0270543098449707, "global_step": 569054, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0488200187683105, "global_step": 569055, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.02553129196167, "global_step": 569056, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0791871547698975, "global_step": 569057, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0372650623321533, "global_step": 569058, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0396976470947266, "global_step": 569059, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.011699676513672, "global_step": 569060, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.988397479057312, "global_step": 569061, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9836113452911377, "global_step": 569062, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.033137083053589, "global_step": 569063, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9974392652511597, "global_step": 569064, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0552332401275635, "global_step": 569065, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0637621879577637, "global_step": 569066, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.065922260284424, "global_step": 569067, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.968646764755249, "global_step": 569068, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9006717205047607, "global_step": 569069, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.079310417175293, "global_step": 569070, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9861087799072266, "global_step": 569071, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.097623348236084, "global_step": 569072, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0911262035369873, "global_step": 569073, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9449577331542969, "global_step": 569074, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.034571886062622, "global_step": 569075, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.001297950744629, "global_step": 569076, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.090607166290283, "global_step": 569077, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9641433954238892, "global_step": 569078, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0189967155456543, "global_step": 569079, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0943422317504883, "global_step": 569080, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.025235176086426, "global_step": 569081, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1105434894561768, "global_step": 569082, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.06827712059021, "global_step": 569083, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.049164295196533, "global_step": 569084, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.096717596054077, "global_step": 569085, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9855425357818604, "global_step": 569086, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1083781719207764, "global_step": 569087, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9436229467391968, "global_step": 569088, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0291733741760254, "global_step": 569089, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0619864463806152, "global_step": 569090, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0984818935394287, "global_step": 569091, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9956624507904053, "global_step": 569092, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.097496271133423, "global_step": 569093, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0303077697753906, "global_step": 569094, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9622176885604858, "global_step": 569095, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.034221887588501, "global_step": 569096, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9997655153274536, "global_step": 569097, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9284441471099854, "global_step": 569098, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0088882446289062, "global_step": 569099, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9733232259750366, "global_step": 569100, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0921471118927, "global_step": 569101, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.8854241371154785, "global_step": 569102, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.166651964187622, "global_step": 569103, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.002445936203003, "global_step": 569104, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0483038425445557, "global_step": 569105, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.072819232940674, "global_step": 569106, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.077238082885742, "global_step": 569107, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.032705783843994, "global_step": 569108, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.042076349258423, "global_step": 569109, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9692763090133667, "global_step": 569110, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9992475509643555, "global_step": 569111, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0478429794311523, "global_step": 569112, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9500595331192017, "global_step": 569113, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.942152976989746, "global_step": 569114, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9417439699172974, "global_step": 569115, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0227816104888916, "global_step": 569116, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9600476026535034, "global_step": 569117, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9957265853881836, "global_step": 569118, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.007534980773926, "global_step": 569119, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0734150409698486, "global_step": 569120, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0992331504821777, "global_step": 569121, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0163629055023193, "global_step": 569122, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0818986892700195, "global_step": 569123, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.059154987335205, "global_step": 569124, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.15865421295166, "global_step": 569125, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0272979736328125, "global_step": 569126, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9768816232681274, "global_step": 569127, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.09775710105896, "global_step": 569128, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9658855199813843, "global_step": 569129, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9762145280838013, "global_step": 569130, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.03528094291687, "global_step": 569131, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9946554899215698, "global_step": 569132, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.991429090499878, "global_step": 569133, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0644638538360596, "global_step": 569134, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9630273580551147, "global_step": 569135, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.016939163208008, "global_step": 569136, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0286664962768555, "global_step": 569137, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.135685682296753, "global_step": 569138, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9984941482543945, "global_step": 569139, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9932210445404053, "global_step": 569140, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9853684902191162, "global_step": 569141, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.043243885040283, "global_step": 569142, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9907641410827637, "global_step": 569143, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9180015325546265, "global_step": 569144, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0496723651885986, "global_step": 569145, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9850068092346191, "global_step": 569146, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0452568531036377, "global_step": 569147, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9831211566925049, "global_step": 569148, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9400075674057007, "global_step": 569149, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0909574031829834, "global_step": 569150, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.026022434234619, "global_step": 569151, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0209238529205322, "global_step": 569152, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.974596619606018, "global_step": 569153, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0694408416748047, "global_step": 569154, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.116429328918457, "global_step": 569155, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0666897296905518, "global_step": 569156, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.031604051589966, "global_step": 569157, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9805254936218262, "global_step": 569158, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0544209480285645, "global_step": 569159, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9949743747711182, "global_step": 569160, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.008635997772217, "global_step": 569161, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0856475830078125, "global_step": 569162, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9988796710968018, "global_step": 569163, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.077784538269043, "global_step": 569164, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.041100025177002, "global_step": 569165, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.089390516281128, "global_step": 569166, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0538830757141113, "global_step": 569167, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9843847751617432, "global_step": 569168, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.133652448654175, "global_step": 569169, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0450332164764404, "global_step": 569170, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9479514360427856, "global_step": 569171, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.026679277420044, "global_step": 569172, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.014467716217041, "global_step": 569173, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0567729473114014, "global_step": 569174, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9565389156341553, "global_step": 569175, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0197203159332275, "global_step": 569176, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9567861557006836, "global_step": 569177, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.052619457244873, "global_step": 569178, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9930291175842285, "global_step": 569179, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1331863403320312, "global_step": 569180, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0423521995544434, "global_step": 569181, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9180536270141602, "global_step": 569182, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.038755416870117, "global_step": 569183, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.088625907897949, "global_step": 569184, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.94881010055542, "global_step": 569185, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.03666353225708, "global_step": 569186, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0499048233032227, "global_step": 569187, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0853939056396484, "global_step": 569188, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.036435127258301, "global_step": 569189, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.031690835952759, "global_step": 569190, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9568567276000977, "global_step": 569191, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9904067516326904, "global_step": 569192, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9793568849563599, "global_step": 569193, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0348105430603027, "global_step": 569194, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.095630168914795, "global_step": 569195, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0599794387817383, "global_step": 569196, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0456204414367676, "global_step": 569197, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9975314140319824, "global_step": 569198, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9635601043701172, "global_step": 569199, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.07060170173645, "global_step": 569200, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0216403007507324, "global_step": 569201, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0231497287750244, "global_step": 569202, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.111495018005371, "global_step": 569203, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0343480110168457, "global_step": 569204, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9656782150268555, "global_step": 569205, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.011319398880005, "global_step": 569206, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9596796035766602, "global_step": 569207, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0768752098083496, "global_step": 569208, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0514957904815674, "global_step": 569209, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9935104846954346, "global_step": 569210, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.004696846008301, "global_step": 569211, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0184874534606934, "global_step": 569212, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9711147546768188, "global_step": 569213, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0261223316192627, "global_step": 569214, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0420634746551514, "global_step": 569215, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0693302154541016, "global_step": 569216, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.991594910621643, "global_step": 569217, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0833163261413574, "global_step": 569218, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9973958730697632, "global_step": 569219, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.037677526473999, "global_step": 569220, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9954071044921875, "global_step": 569221, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.010590076446533, "global_step": 569222, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9983323812484741, "global_step": 569223, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.994005560874939, "global_step": 569224, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9327248334884644, "global_step": 569225, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.046501636505127, "global_step": 569226, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0661847591400146, "global_step": 569227, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0870587825775146, "global_step": 569228, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0448338985443115, "global_step": 569229, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0413613319396973, "global_step": 569230, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9598568677902222, "global_step": 569231, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.954483985900879, "global_step": 569232, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9391775131225586, "global_step": 569233, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.08954119682312, "global_step": 569234, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.026766300201416, "global_step": 569235, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.07392954826355, "global_step": 569236, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0379438400268555, "global_step": 569237, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.046010971069336, "global_step": 569238, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0791544914245605, "global_step": 569239, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0300259590148926, "global_step": 569240, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0440139770507812, "global_step": 569241, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9596649408340454, "global_step": 569242, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.928280234336853, "global_step": 569243, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.022139549255371, "global_step": 569244, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9858613014221191, "global_step": 569245, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0147387981414795, "global_step": 569246, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9893076419830322, "global_step": 569247, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.076561212539673, "global_step": 569248, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.988425850868225, "global_step": 569249, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.978665828704834, "global_step": 569250, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0466911792755127, "global_step": 569251, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9547829627990723, "global_step": 569252, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9394657611846924, "global_step": 569253, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0692646503448486, "global_step": 569254, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9817028045654297, "global_step": 569255, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.14719295501709, "global_step": 569256, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0551013946533203, "global_step": 569257, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0606813430786133, "global_step": 569258, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0024571418762207, "global_step": 569259, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.033925771713257, "global_step": 569260, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.041339635848999, "global_step": 569261, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.011549234390259, "global_step": 569262, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.028393507003784, "global_step": 569263, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0310885906219482, "global_step": 569264, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0340213775634766, "global_step": 569265, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9969197511672974, "global_step": 569266, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.019587516784668, "global_step": 569267, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9867265224456787, "global_step": 569268, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.059171199798584, "global_step": 569269, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.039097785949707, "global_step": 569270, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.957635521888733, "global_step": 569271, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.050626516342163, "global_step": 569272, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9581592082977295, "global_step": 569273, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.084602117538452, "global_step": 569274, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0410678386688232, "global_step": 569275, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0966906547546387, "global_step": 569276, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.917576789855957, "global_step": 569277, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9114335775375366, "global_step": 569278, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.059849739074707, "global_step": 569279, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9842357635498047, "global_step": 569280, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0096187591552734, "global_step": 569281, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0153279304504395, "global_step": 569282, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.979590892791748, "global_step": 569283, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.013188600540161, "global_step": 569284, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.125579357147217, "global_step": 569285, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9930708408355713, "global_step": 569286, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0156149864196777, "global_step": 569287, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0185346603393555, "global_step": 569288, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9649592638015747, "global_step": 569289, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0239322185516357, "global_step": 569290, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0610218048095703, "global_step": 569291, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0533618927001953, "global_step": 569292, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9845335483551025, "global_step": 569293, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.941285252571106, "global_step": 569294, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.05940580368042, "global_step": 569295, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9868186712265015, "global_step": 569296, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9694390296936035, "global_step": 569297, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9965388774871826, "global_step": 569298, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.178489923477173, "global_step": 569299, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0383341312408447, "global_step": 569300, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.048940420150757, "global_step": 569301, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.084723711013794, "global_step": 569302, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0300042629241943, "global_step": 569303, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.018056869506836, "global_step": 569304, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.93937349319458, "global_step": 569305, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9912909269332886, "global_step": 569306, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9479610919952393, "global_step": 569307, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0291690826416016, "global_step": 569308, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.047210454940796, "global_step": 569309, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0630972385406494, "global_step": 569310, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0556094646453857, "global_step": 569311, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9247406721115112, "global_step": 569312, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0205986499786377, "global_step": 569313, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0447752475738525, "global_step": 569314, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.016895294189453, "global_step": 569315, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0151469707489014, "global_step": 569316, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.087155818939209, "global_step": 569317, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.065113067626953, "global_step": 569318, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.005971670150757, "global_step": 569319, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0313351154327393, "global_step": 569320, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.03918719291687, "global_step": 569321, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.016472101211548, "global_step": 569322, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0164713859558105, "global_step": 569323, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.076885223388672, "global_step": 569324, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.042224407196045, "global_step": 569325, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.023958206176758, "global_step": 569326, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9621400833129883, "global_step": 569327, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1278581619262695, "global_step": 569328, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0221970081329346, "global_step": 569329, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9384833574295044, "global_step": 569330, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0405309200286865, "global_step": 569331, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0702872276306152, "global_step": 569332, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9860827922821045, "global_step": 569333, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.052755355834961, "global_step": 569334, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0572807788848877, "global_step": 569335, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.014604330062866, "global_step": 569336, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9848296642303467, "global_step": 569337, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0550832748413086, "global_step": 569338, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0403287410736084, "global_step": 569339, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9520742893218994, "global_step": 569340, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0433521270751953, "global_step": 569341, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0623300075531006, "global_step": 569342, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0342319011688232, "global_step": 569343, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0058770179748535, "global_step": 569344, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0025885105133057, "global_step": 569345, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0516648292541504, "global_step": 569346, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9534151554107666, "global_step": 569347, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0136680603027344, "global_step": 569348, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.082834005355835, "global_step": 569349, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.039675712585449, "global_step": 569350, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0164291858673096, "global_step": 569351, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.022696018218994, "global_step": 569352, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.949342966079712, "global_step": 569353, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.981346845626831, "global_step": 569354, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0344014167785645, "global_step": 569355, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9458222389221191, "global_step": 569356, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9870164394378662, "global_step": 569357, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0403120517730713, "global_step": 569358, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.038116931915283, "global_step": 569359, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.150588274002075, "global_step": 569360, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9925357103347778, "global_step": 569361, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.8996553421020508, "global_step": 569362, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.121086835861206, "global_step": 569363, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.049826145172119, "global_step": 569364, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0296201705932617, "global_step": 569365, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.985234022140503, "global_step": 569366, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.134272575378418, "global_step": 569367, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0461549758911133, "global_step": 569368, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9313762187957764, "global_step": 569369, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.046449899673462, "global_step": 569370, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9762707948684692, "global_step": 569371, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.080735921859741, "global_step": 569372, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.014265775680542, "global_step": 569373, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.00264573097229, "global_step": 569374, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0182437896728516, "global_step": 569375, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9883532524108887, "global_step": 569376, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9888176918029785, "global_step": 569377, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9718695878982544, "global_step": 569378, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.960860252380371, "global_step": 569379, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0412464141845703, "global_step": 569380, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9943445920944214, "global_step": 569381, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.018563985824585, "global_step": 569382, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0468735694885254, "global_step": 569383, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.982041835784912, "global_step": 569384, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9459728002548218, "global_step": 569385, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.038158893585205, "global_step": 569386, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.046321392059326, "global_step": 569387, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9320521354675293, "global_step": 569388, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.983084797859192, "global_step": 569389, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.070981025695801, "global_step": 569390, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.988900899887085, "global_step": 569391, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0650265216827393, "global_step": 569392, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0414347648620605, "global_step": 569393, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.070992946624756, "global_step": 569394, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.03001070022583, "global_step": 569395, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.077847957611084, "global_step": 569396, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.045999526977539, "global_step": 569397, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0687713623046875, "global_step": 569398, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9247032403945923, "global_step": 569399, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.110175132751465, "global_step": 569400, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0236873626708984, "global_step": 569401, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9995989799499512, "global_step": 569402, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.052964210510254, "global_step": 569403, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0108892917633057, "global_step": 569404, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.038675308227539, "global_step": 569405, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.019416570663452, "global_step": 569406, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0472660064697266, "global_step": 569407, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.986190915107727, "global_step": 569408, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.070746421813965, "global_step": 569409, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0140116214752197, "global_step": 569410, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9859521389007568, "global_step": 569411, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.06784987449646, "global_step": 569412, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.110042095184326, "global_step": 569413, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.108534812927246, "global_step": 569414, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.037280321121216, "global_step": 569415, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0925400257110596, "global_step": 569416, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9831786155700684, "global_step": 569417, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0234808921813965, "global_step": 569418, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0033934116363525, "global_step": 569419, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0232858657836914, "global_step": 569420, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.030299186706543, "global_step": 569421, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.983230471611023, "global_step": 569422, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9750229120254517, "global_step": 569423, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.083827257156372, "global_step": 569424, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0022571086883545, "global_step": 569425, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.018674373626709, "global_step": 569426, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.078005790710449, "global_step": 569427, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0003230571746826, "global_step": 569428, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.046807289123535, "global_step": 569429, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9744077920913696, "global_step": 569430, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1299667358398438, "global_step": 569431, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0101072788238525, "global_step": 569432, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9851689338684082, "global_step": 569433, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9915271997451782, "global_step": 569434, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0166404247283936, "global_step": 569435, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.947388768196106, "global_step": 569436, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.039860963821411, "global_step": 569437, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9888166189193726, "global_step": 569438, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.000506639480591, "global_step": 569439, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0109992027282715, "global_step": 569440, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9324090480804443, "global_step": 569441, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0698904991149902, "global_step": 569442, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0475900173187256, "global_step": 569443, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0301969051361084, "global_step": 569444, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9838790893554688, "global_step": 569445, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.038637399673462, "global_step": 569446, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9979498386383057, "global_step": 569447, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0025715827941895, "global_step": 569448, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9390019178390503, "global_step": 569449, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9820547103881836, "global_step": 569450, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.024174213409424, "global_step": 569451, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0178189277648926, "global_step": 569452, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0244369506835938, "global_step": 569453, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9449034929275513, "global_step": 569454, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.10406756401062, "global_step": 569455, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0004382133483887, "global_step": 569456, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.982386827468872, "global_step": 569457, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.017742872238159, "global_step": 569458, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.973164677619934, "global_step": 569459, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.01731538772583, "global_step": 569460, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0437467098236084, "global_step": 569461, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1257081031799316, "global_step": 569462, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.047335386276245, "global_step": 569463, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9987837076187134, "global_step": 569464, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0316388607025146, "global_step": 569465, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.079101800918579, "global_step": 569466, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.116231679916382, "global_step": 569467, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0847411155700684, "global_step": 569468, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9645212888717651, "global_step": 569469, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0656588077545166, "global_step": 569470, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1517221927642822, "global_step": 569471, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9355030059814453, "global_step": 569472, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9435005187988281, "global_step": 569473, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0490496158599854, "global_step": 569474, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0018322467803955, "global_step": 569475, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.029344081878662, "global_step": 569476, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.026402235031128, "global_step": 569477, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0442936420440674, "global_step": 569478, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0893349647521973, "global_step": 569479, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0523736476898193, "global_step": 569480, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.066204309463501, "global_step": 569481, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.048264265060425, "global_step": 569482, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.011847496032715, "global_step": 569483, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.019503593444824, "global_step": 569484, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.00614070892334, "global_step": 569485, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0485260486602783, "global_step": 569486, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.027833938598633, "global_step": 569487, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.071613311767578, "global_step": 569488, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.98549222946167, "global_step": 569489, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9999680519104004, "global_step": 569490, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0250110626220703, "global_step": 569491, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0734150409698486, "global_step": 569492, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.030717372894287, "global_step": 569493, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.013467311859131, "global_step": 569494, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0377004146575928, "global_step": 569495, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0823638439178467, "global_step": 569496, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0081658363342285, "global_step": 569497, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0498428344726562, "global_step": 569498, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0250608921051025, "global_step": 569499, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1296064853668213, "global_step": 569500, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0300683975219727, "global_step": 569501, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1171586513519287, "global_step": 569502, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0248167514801025, "global_step": 569503, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0623257160186768, "global_step": 569504, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0797252655029297, "global_step": 569505, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0226221084594727, "global_step": 569506, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9136223793029785, "global_step": 569507, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0927350521087646, "global_step": 569508, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.008770704269409, "global_step": 569509, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.003095865249634, "global_step": 569510, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.081601858139038, "global_step": 569511, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0704407691955566, "global_step": 569512, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9993863105773926, "global_step": 569513, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0005881786346436, "global_step": 569514, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.055074453353882, "global_step": 569515, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9854635000228882, "global_step": 569516, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9643664360046387, "global_step": 569517, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.03398060798645, "global_step": 569518, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0395359992980957, "global_step": 569519, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9459706544876099, "global_step": 569520, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.041351795196533, "global_step": 569521, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9596190452575684, "global_step": 569522, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0474374294281006, "global_step": 569523, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0093367099761963, "global_step": 569524, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0574278831481934, "global_step": 569525, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.02358078956604, "global_step": 569526, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9955849647521973, "global_step": 569527, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0407981872558594, "global_step": 569528, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0442347526550293, "global_step": 569529, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9060699939727783, "global_step": 569530, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9887667894363403, "global_step": 569531, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0314602851867676, "global_step": 569532, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.079749345779419, "global_step": 569533, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9589118957519531, "global_step": 569534, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9480904340744019, "global_step": 569535, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.043701410293579, "global_step": 569536, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.100996255874634, "global_step": 569537, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0062167644500732, "global_step": 569538, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9628946781158447, "global_step": 569539, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.005373001098633, "global_step": 569540, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0472636222839355, "global_step": 569541, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9907811880111694, "global_step": 569542, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.014636278152466, "global_step": 569543, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0686285495758057, "global_step": 569544, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0554637908935547, "global_step": 569545, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9547550678253174, "global_step": 569546, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.022308349609375, "global_step": 569547, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0232861042022705, "global_step": 569548, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1082193851470947, "global_step": 569549, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0506207942962646, "global_step": 569550, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0325400829315186, "global_step": 569551, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0136191844940186, "global_step": 569552, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0229380130767822, "global_step": 569553, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0240976810455322, "global_step": 569554, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.093397378921509, "global_step": 569555, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9518190622329712, "global_step": 569556, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.042231321334839, "global_step": 569557, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0612401962280273, "global_step": 569558, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.009977340698242, "global_step": 569559, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0149409770965576, "global_step": 569560, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1092562675476074, "global_step": 569561, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9307760000228882, "global_step": 569562, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.011709451675415, "global_step": 569563, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0423340797424316, "global_step": 569564, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.994093894958496, "global_step": 569565, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9570866823196411, "global_step": 569566, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9728002548217773, "global_step": 569567, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1049320697784424, "global_step": 569568, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9420042037963867, "global_step": 569569, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.029848575592041, "global_step": 569570, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0909955501556396, "global_step": 569571, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0639679431915283, "global_step": 569572, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.071251153945923, "global_step": 569573, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.052164077758789, "global_step": 569574, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0175352096557617, "global_step": 569575, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.155319929122925, "global_step": 569576, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9572948217391968, "global_step": 569577, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.001713514328003, "global_step": 569578, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.060899257659912, "global_step": 569579, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9687882661819458, "global_step": 569580, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.059584140777588, "global_step": 569581, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.057347536087036, "global_step": 569582, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0272138118743896, "global_step": 569583, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0416438579559326, "global_step": 569584, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.049297332763672, "global_step": 569585, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.025916576385498, "global_step": 569586, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0656001567840576, "global_step": 569587, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.014509916305542, "global_step": 569588, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.036663293838501, "global_step": 569589, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.933276653289795, "global_step": 569590, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0431885719299316, "global_step": 569591, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0325615406036377, "global_step": 569592, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0523264408111572, "global_step": 569593, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0256588459014893, "global_step": 569594, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9280996322631836, "global_step": 569595, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.060074806213379, "global_step": 569596, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.976359248161316, "global_step": 569597, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.056089401245117, "global_step": 569598, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0334012508392334, "global_step": 569599, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.09891414642334, "global_step": 569600, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9451030492782593, "global_step": 569601, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0138132572174072, "global_step": 569602, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9956589937210083, "global_step": 569603, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9988116025924683, "global_step": 569604, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.912734866142273, "global_step": 569605, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.040311336517334, "global_step": 569606, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0558359622955322, "global_step": 569607, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0590927600860596, "global_step": 569608, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9422221183776855, "global_step": 569609, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.031848192214966, "global_step": 569610, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.02205228805542, "global_step": 569611, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.954085111618042, "global_step": 569612, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9892586469650269, "global_step": 569613, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0634102821350098, "global_step": 569614, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9948012828826904, "global_step": 569615, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.039942502975464, "global_step": 569616, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0777394771575928, "global_step": 569617, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9447789192199707, "global_step": 569618, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.054771900177002, "global_step": 569619, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.026461601257324, "global_step": 569620, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.047584056854248, "global_step": 569621, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.989807367324829, "global_step": 569622, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.062802791595459, "global_step": 569623, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.076887607574463, "global_step": 569624, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.072401762008667, "global_step": 569625, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1349542140960693, "global_step": 569626, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9540259838104248, "global_step": 569627, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1200063228607178, "global_step": 569628, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9628181457519531, "global_step": 569629, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.057973861694336, "global_step": 569630, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0197176933288574, "global_step": 569631, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.006129264831543, "global_step": 569632, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0854852199554443, "global_step": 569633, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.100252151489258, "global_step": 569634, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0291147232055664, "global_step": 569635, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0873303413391113, "global_step": 569636, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.053438186645508, "global_step": 569637, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0353636741638184, "global_step": 569638, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0196616649627686, "global_step": 569639, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0292913913726807, "global_step": 569640, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.06272029876709, "global_step": 569641, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0366508960723877, "global_step": 569642, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0048108100891113, "global_step": 569643, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9788596630096436, "global_step": 569644, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.112553596496582, "global_step": 569645, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0518174171447754, "global_step": 569646, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.950540542602539, "global_step": 569647, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.048039674758911, "global_step": 569648, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1098241806030273, "global_step": 569649, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0196971893310547, "global_step": 569650, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0350561141967773, "global_step": 569651, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9287879467010498, "global_step": 569652, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.976762294769287, "global_step": 569653, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0676259994506836, "global_step": 569654, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0476021766662598, "global_step": 569655, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.072347640991211, "global_step": 569656, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0549204349517822, "global_step": 569657, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9600417613983154, "global_step": 569658, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.021329879760742, "global_step": 569659, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0542714595794678, "global_step": 569660, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9900126457214355, "global_step": 569661, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.996443510055542, "global_step": 569662, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0056521892547607, "global_step": 569663, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0184309482574463, "global_step": 569664, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.075514078140259, "global_step": 569665, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0832841396331787, "global_step": 569666, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0130789279937744, "global_step": 569667, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0092689990997314, "global_step": 569668, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9682338237762451, "global_step": 569669, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1306746006011963, "global_step": 569670, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.962045669555664, "global_step": 569671, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.067692756652832, "global_step": 569672, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0506436824798584, "global_step": 569673, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0050106048583984, "global_step": 569674, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.991083025932312, "global_step": 569675, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.008727788925171, "global_step": 569676, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.040699005126953, "global_step": 569677, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.066493034362793, "global_step": 569678, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.010674476623535, "global_step": 569679, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.921115517616272, "global_step": 569680, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0366203784942627, "global_step": 569681, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9863401651382446, "global_step": 569682, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.030667781829834, "global_step": 569683, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9804245233535767, "global_step": 569684, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0011134147644043, "global_step": 569685, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.012219190597534, "global_step": 569686, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9238945245742798, "global_step": 569687, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9581469297409058, "global_step": 569688, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9646514654159546, "global_step": 569689, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0772829055786133, "global_step": 569690, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0045337677001953, "global_step": 569691, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.981411337852478, "global_step": 569692, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0189778804779053, "global_step": 569693, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0239977836608887, "global_step": 569694, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.158306121826172, "global_step": 569695, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9956358671188354, "global_step": 569696, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0466668605804443, "global_step": 569697, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.022815704345703, "global_step": 569698, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0773980617523193, "global_step": 569699, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0199790000915527, "global_step": 569700, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.979114294052124, "global_step": 569701, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.8773322105407715, "global_step": 569702, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.022442102432251, "global_step": 569703, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0091452598571777, "global_step": 569704, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0191757678985596, "global_step": 569705, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.001912832260132, "global_step": 569706, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.039341926574707, "global_step": 569707, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9654148817062378, "global_step": 569708, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0972182750701904, "global_step": 569709, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9570473432540894, "global_step": 569710, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0801448822021484, "global_step": 569711, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.045706272125244, "global_step": 569712, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0918502807617188, "global_step": 569713, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0529205799102783, "global_step": 569714, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.031383514404297, "global_step": 569715, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.060382604598999, "global_step": 569716, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.068481206893921, "global_step": 569717, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0230417251586914, "global_step": 569718, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.055751085281372, "global_step": 569719, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0368964672088623, "global_step": 569720, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.945504069328308, "global_step": 569721, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9778679609298706, "global_step": 569722, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.000373363494873, "global_step": 569723, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.027646541595459, "global_step": 569724, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1230828762054443, "global_step": 569725, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.089567184448242, "global_step": 569726, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.075695037841797, "global_step": 569727, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.088118076324463, "global_step": 569728, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0786991119384766, "global_step": 569729, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1397557258605957, "global_step": 569730, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0731184482574463, "global_step": 569731, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0040953159332275, "global_step": 569732, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0642476081848145, "global_step": 569733, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.078230857849121, "global_step": 569734, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0448429584503174, "global_step": 569735, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.018277168273926, "global_step": 569736, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9676333665847778, "global_step": 569737, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0844125747680664, "global_step": 569738, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9808619022369385, "global_step": 569739, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.12166166305542, "global_step": 569740, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0478439331054688, "global_step": 569741, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0217671394348145, "global_step": 569742, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9857416152954102, "global_step": 569743, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9395875930786133, "global_step": 569744, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9277050495147705, "global_step": 569745, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0516960620880127, "global_step": 569746, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9778406620025635, "global_step": 569747, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.046211004257202, "global_step": 569748, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.062441110610962, "global_step": 569749, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0982794761657715, "global_step": 569750, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9860270023345947, "global_step": 569751, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.053316831588745, "global_step": 569752, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.030597448348999, "global_step": 569753, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0719423294067383, "global_step": 569754, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0374481678009033, "global_step": 569755, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0729482173919678, "global_step": 569756, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0168466567993164, "global_step": 569757, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0789451599121094, "global_step": 569758, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.961435317993164, "global_step": 569759, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.899208426475525, "global_step": 569760, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0030953884124756, "global_step": 569761, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9988471269607544, "global_step": 569762, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.009661912918091, "global_step": 569763, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0393106937408447, "global_step": 569764, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0357139110565186, "global_step": 569765, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9356123208999634, "global_step": 569766, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0621743202209473, "global_step": 569767, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0516951084136963, "global_step": 569768, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9894709587097168, "global_step": 569769, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9849793910980225, "global_step": 569770, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.056034564971924, "global_step": 569771, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0180182456970215, "global_step": 569772, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0318548679351807, "global_step": 569773, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0692386627197266, "global_step": 569774, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9903374910354614, "global_step": 569775, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0898537635803223, "global_step": 569776, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.015791416168213, "global_step": 569777, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.037635564804077, "global_step": 569778, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.116976499557495, "global_step": 569779, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0038533210754395, "global_step": 569780, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.028972625732422, "global_step": 569781, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.124206781387329, "global_step": 569782, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.023805856704712, "global_step": 569783, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9901599884033203, "global_step": 569784, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0216801166534424, "global_step": 569785, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.024142026901245, "global_step": 569786, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.024790048599243, "global_step": 569787, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9347994327545166, "global_step": 569788, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9506824016571045, "global_step": 569789, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.994840145111084, "global_step": 569790, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9884952306747437, "global_step": 569791, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.030921220779419, "global_step": 569792, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.066509485244751, "global_step": 569793, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0614607334136963, "global_step": 569794, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.018432140350342, "global_step": 569795, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.994134783744812, "global_step": 569796, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9967941045761108, "global_step": 569797, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9880592823028564, "global_step": 569798, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0639100074768066, "global_step": 569799, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9390835762023926, "global_step": 569800, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.985745906829834, "global_step": 569801, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9571951627731323, "global_step": 569802, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.088792562484741, "global_step": 569803, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0152766704559326, "global_step": 569804, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9826186895370483, "global_step": 569805, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.026205062866211, "global_step": 569806, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.066603899002075, "global_step": 569807, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.032233715057373, "global_step": 569808, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.999202013015747, "global_step": 569809, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0203702449798584, "global_step": 569810, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9462761878967285, "global_step": 569811, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0140771865844727, "global_step": 569812, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.080780267715454, "global_step": 569813, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0272958278656006, "global_step": 569814, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.108959913253784, "global_step": 569815, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0298914909362793, "global_step": 569816, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0532145500183105, "global_step": 569817, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.043342351913452, "global_step": 569818, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9587458372116089, "global_step": 569819, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9991878271102905, "global_step": 569820, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.040194034576416, "global_step": 569821, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9975298643112183, "global_step": 569822, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.991099238395691, "global_step": 569823, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0037853717803955, "global_step": 569824, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.031679391860962, "global_step": 569825, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.037611484527588, "global_step": 569826, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0509824752807617, "global_step": 569827, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9689488410949707, "global_step": 569828, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1499221324920654, "global_step": 569829, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.052827835083008, "global_step": 569830, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0069079399108887, "global_step": 569831, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0014150142669678, "global_step": 569832, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1066789627075195, "global_step": 569833, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9984434843063354, "global_step": 569834, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9398642778396606, "global_step": 569835, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1306965351104736, "global_step": 569836, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.06248140335083, "global_step": 569837, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9819833040237427, "global_step": 569838, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9415926933288574, "global_step": 569839, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.10431170463562, "global_step": 569840, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.074479818344116, "global_step": 569841, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1341655254364014, "global_step": 569842, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0493016242980957, "global_step": 569843, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.005096912384033, "global_step": 569844, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0077028274536133, "global_step": 569845, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0321600437164307, "global_step": 569846, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.011979103088379, "global_step": 569847, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0729382038116455, "global_step": 569848, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.108151435852051, "global_step": 569849, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.087155818939209, "global_step": 569850, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0311641693115234, "global_step": 569851, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0241916179656982, "global_step": 569852, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.997658133506775, "global_step": 569853, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0256807804107666, "global_step": 569854, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.021613121032715, "global_step": 569855, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.057131052017212, "global_step": 569856, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.8822314739227295, "global_step": 569857, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0563273429870605, "global_step": 569858, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0000176429748535, "global_step": 569859, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0108633041381836, "global_step": 569860, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.007237195968628, "global_step": 569861, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0572569370269775, "global_step": 569862, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0966439247131348, "global_step": 569863, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.066687822341919, "global_step": 569864, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.076014280319214, "global_step": 569865, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1247522830963135, "global_step": 569866, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0562360286712646, "global_step": 569867, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9813408851623535, "global_step": 569868, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0561256408691406, "global_step": 569869, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9787040948867798, "global_step": 569870, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0167431831359863, "global_step": 569871, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.070174217224121, "global_step": 569872, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0359230041503906, "global_step": 569873, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0496184825897217, "global_step": 569874, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.021688461303711, "global_step": 569875, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0244786739349365, "global_step": 569876, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.998018741607666, "global_step": 569877, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9601116180419922, "global_step": 569878, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9554228782653809, "global_step": 569879, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0336573123931885, "global_step": 569880, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.084684371948242, "global_step": 569881, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.051146984100342, "global_step": 569882, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.973428726196289, "global_step": 569883, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9619076251983643, "global_step": 569884, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.01423978805542, "global_step": 569885, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0341289043426514, "global_step": 569886, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9756202697753906, "global_step": 569887, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.110720634460449, "global_step": 569888, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.8948438167572021, "global_step": 569889, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1015892028808594, "global_step": 569890, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9987319707870483, "global_step": 569891, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0178425312042236, "global_step": 569892, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.010279655456543, "global_step": 569893, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.9702038764953613, "global_step": 569894, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0574753284454346, "global_step": 569895, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.928557276725769, "global_step": 569896, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0788466930389404, "global_step": 569897, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.983220100402832, "global_step": 569898, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0826072692871094, "global_step": 569899, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.1033260822296143, "global_step": 569900, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.015244245529175, "global_step": 569901, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.0341548919677734, "global_step": 569902, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.026186227798462, "global_step": 569903, "epoch": 937, "lr": 5e-05}
{"train_loss": 2.024050235748291, "global_step": 569904, "epoch": 937, "lr": 5e-05}
{"train_loss": 1.986284852027893, "global_step": 569905, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1303699016571045, "global_step": 569906, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9875702857971191, "global_step": 569907, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.045618772506714, "global_step": 569908, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.048562526702881, "global_step": 569909, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1114165782928467, "global_step": 569910, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0065369606018066, "global_step": 569911, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9235035181045532, "global_step": 569912, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0623607635498047, "global_step": 569913, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0211105346679688, "global_step": 569914, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0611319541931152, "global_step": 569915, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9723395109176636, "global_step": 569916, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9584949016571045, "global_step": 569917, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.006894826889038, "global_step": 569918, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0122337341308594, "global_step": 569919, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9896451234817505, "global_step": 569920, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0820822715759277, "global_step": 569921, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.018726348876953, "global_step": 569922, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9867141246795654, "global_step": 569923, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.084385871887207, "global_step": 569924, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0710909366607666, "global_step": 569925, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0584981441497803, "global_step": 569926, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0807321071624756, "global_step": 569927, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.00406813621521, "global_step": 569928, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0247349739074707, "global_step": 569929, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9110424518585205, "global_step": 569930, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9983692169189453, "global_step": 569931, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0042359828948975, "global_step": 569932, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.01495361328125, "global_step": 569933, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.023461103439331, "global_step": 569934, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0074846744537354, "global_step": 569935, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0645813941955566, "global_step": 569936, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.988985538482666, "global_step": 569937, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0088493824005127, "global_step": 569938, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1025242805480957, "global_step": 569939, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0239875316619873, "global_step": 569940, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9700582027435303, "global_step": 569941, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.074831962585449, "global_step": 569942, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9364290237426758, "global_step": 569943, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.06060528755188, "global_step": 569944, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.980777382850647, "global_step": 569945, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0558860301971436, "global_step": 569946, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.997448205947876, "global_step": 569947, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0267086029052734, "global_step": 569948, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9275239706039429, "global_step": 569949, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.930030345916748, "global_step": 569950, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.007568359375, "global_step": 569951, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.049377202987671, "global_step": 569952, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9906337261199951, "global_step": 569953, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9800127744674683, "global_step": 569954, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.956600308418274, "global_step": 569955, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.003131628036499, "global_step": 569956, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9746540784835815, "global_step": 569957, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9607868194580078, "global_step": 569958, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0295472145080566, "global_step": 569959, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0534396171569824, "global_step": 569960, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9580495357513428, "global_step": 569961, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9384126663208008, "global_step": 569962, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9794286489486694, "global_step": 569963, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9068410396575928, "global_step": 569964, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9882696866989136, "global_step": 569965, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.027501344680786, "global_step": 569966, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.942251443862915, "global_step": 569967, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0115442276000977, "global_step": 569968, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0240414142608643, "global_step": 569969, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0104286670684814, "global_step": 569970, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0600082874298096, "global_step": 569971, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0177619457244873, "global_step": 569972, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0998873710632324, "global_step": 569973, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.00718092918396, "global_step": 569974, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9935585260391235, "global_step": 569975, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.040642738342285, "global_step": 569976, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9854121208190918, "global_step": 569977, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0096213817596436, "global_step": 569978, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9771734476089478, "global_step": 569979, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9670301675796509, "global_step": 569980, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.049668073654175, "global_step": 569981, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9562344551086426, "global_step": 569982, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.946160078048706, "global_step": 569983, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9372869729995728, "global_step": 569984, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.961843729019165, "global_step": 569985, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0411343574523926, "global_step": 569986, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0926144123077393, "global_step": 569987, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9626110792160034, "global_step": 569988, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9766572713851929, "global_step": 569989, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.062732458114624, "global_step": 569990, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.094742774963379, "global_step": 569991, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.987621784210205, "global_step": 569992, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0428059101104736, "global_step": 569993, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9504504203796387, "global_step": 569994, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1144602298736572, "global_step": 569995, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9968055486679077, "global_step": 569996, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0124688148498535, "global_step": 569997, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9541640281677246, "global_step": 569998, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0230138301849365, "global_step": 569999, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.047081470489502, "global_step": 570000, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.976535439491272, "global_step": 570001, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.019160270690918, "global_step": 570002, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0442395210266113, "global_step": 570003, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.023003339767456, "global_step": 570004, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0038998126983643, "global_step": 570005, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9670804738998413, "global_step": 570006, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.09478759765625, "global_step": 570007, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0641682147979736, "global_step": 570008, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.003824234008789, "global_step": 570009, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.106804132461548, "global_step": 570010, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9966740608215332, "global_step": 570011, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.929883599281311, "global_step": 570012, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9528276920318604, "global_step": 570013, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0397868156433105, "global_step": 570014, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.968105673789978, "global_step": 570015, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.971320629119873, "global_step": 570016, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9909478425979614, "global_step": 570017, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.048438549041748, "global_step": 570018, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9752908945083618, "global_step": 570019, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.074662446975708, "global_step": 570020, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0805211067199707, "global_step": 570021, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9832695722579956, "global_step": 570022, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9798475503921509, "global_step": 570023, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.118708610534668, "global_step": 570024, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0759999752044678, "global_step": 570025, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0010006427764893, "global_step": 570026, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0133001804351807, "global_step": 570027, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0358872413635254, "global_step": 570028, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.014047384262085, "global_step": 570029, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.95901620388031, "global_step": 570030, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0379858016967773, "global_step": 570031, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9906162023544312, "global_step": 570032, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9790265560150146, "global_step": 570033, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9788540601730347, "global_step": 570034, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.007046699523926, "global_step": 570035, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.073930501937866, "global_step": 570036, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1149911880493164, "global_step": 570037, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.03816294670105, "global_step": 570038, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0034449100494385, "global_step": 570039, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0409507751464844, "global_step": 570040, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0722479820251465, "global_step": 570041, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.029374599456787, "global_step": 570042, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.073147773742676, "global_step": 570043, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.020246982574463, "global_step": 570044, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0467357635498047, "global_step": 570045, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.057445526123047, "global_step": 570046, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.04793643951416, "global_step": 570047, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0529377460479736, "global_step": 570048, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.973368525505066, "global_step": 570049, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9928643703460693, "global_step": 570050, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9998773336410522, "global_step": 570051, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0706262588500977, "global_step": 570052, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.058415174484253, "global_step": 570053, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0225677490234375, "global_step": 570054, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0172832012176514, "global_step": 570055, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9494800567626953, "global_step": 570056, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0260796546936035, "global_step": 570057, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9658451080322266, "global_step": 570058, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0065128803253174, "global_step": 570059, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0541374683380127, "global_step": 570060, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.069962978363037, "global_step": 570061, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0453827381134033, "global_step": 570062, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.061657667160034, "global_step": 570063, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9950472116470337, "global_step": 570064, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0103726387023926, "global_step": 570065, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.059034824371338, "global_step": 570066, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9714860916137695, "global_step": 570067, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0336525440216064, "global_step": 570068, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9838647842407227, "global_step": 570069, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.064945936203003, "global_step": 570070, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0687177181243896, "global_step": 570071, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.094048500061035, "global_step": 570072, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.072864055633545, "global_step": 570073, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9824597835540771, "global_step": 570074, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0088016986846924, "global_step": 570075, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0054304599761963, "global_step": 570076, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.038435220718384, "global_step": 570077, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.039080858230591, "global_step": 570078, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9632370471954346, "global_step": 570079, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0025107860565186, "global_step": 570080, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0304665565490723, "global_step": 570081, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.050248384475708, "global_step": 570082, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1074047088623047, "global_step": 570083, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9725462198257446, "global_step": 570084, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.138310670852661, "global_step": 570085, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1292290687561035, "global_step": 570086, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9692716598510742, "global_step": 570087, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.001605749130249, "global_step": 570088, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9840209484100342, "global_step": 570089, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0183911323547363, "global_step": 570090, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.967416524887085, "global_step": 570091, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.915605902671814, "global_step": 570092, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0310912132263184, "global_step": 570093, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9990836381912231, "global_step": 570094, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0770115852355957, "global_step": 570095, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9978777170181274, "global_step": 570096, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0566442012786865, "global_step": 570097, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0941333770751953, "global_step": 570098, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.022162437438965, "global_step": 570099, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.002443552017212, "global_step": 570100, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.109142303466797, "global_step": 570101, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0249593257904053, "global_step": 570102, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9523130655288696, "global_step": 570103, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.027827501296997, "global_step": 570104, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0563745498657227, "global_step": 570105, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.941667079925537, "global_step": 570106, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0466578006744385, "global_step": 570107, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0330896377563477, "global_step": 570108, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.001305103302002, "global_step": 570109, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0649521350860596, "global_step": 570110, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0068721771240234, "global_step": 570111, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9748975038528442, "global_step": 570112, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.037693500518799, "global_step": 570113, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9766862392425537, "global_step": 570114, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9265384674072266, "global_step": 570115, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0569045543670654, "global_step": 570116, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9808756113052368, "global_step": 570117, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0617570877075195, "global_step": 570118, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0049445629119873, "global_step": 570119, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9704935550689697, "global_step": 570120, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0868945121765137, "global_step": 570121, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9864110946655273, "global_step": 570122, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.053786516189575, "global_step": 570123, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.995798110961914, "global_step": 570124, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.136848211288452, "global_step": 570125, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.110396385192871, "global_step": 570126, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.090733051300049, "global_step": 570127, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9127320051193237, "global_step": 570128, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.025050401687622, "global_step": 570129, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9600517749786377, "global_step": 570130, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.088207483291626, "global_step": 570131, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0689804553985596, "global_step": 570132, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0495965480804443, "global_step": 570133, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9592070579528809, "global_step": 570134, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0579638481140137, "global_step": 570135, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.911941409111023, "global_step": 570136, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0733702182769775, "global_step": 570137, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9579155445098877, "global_step": 570138, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.053054094314575, "global_step": 570139, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9518235921859741, "global_step": 570140, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.040052890777588, "global_step": 570141, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0174217224121094, "global_step": 570142, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.953637719154358, "global_step": 570143, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9989615678787231, "global_step": 570144, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9884251356124878, "global_step": 570145, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0268750190734863, "global_step": 570146, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9024851322174072, "global_step": 570147, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9830166101455688, "global_step": 570148, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9276766777038574, "global_step": 570149, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.092357635498047, "global_step": 570150, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9349607229232788, "global_step": 570151, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1070685386657715, "global_step": 570152, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.981666922569275, "global_step": 570153, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.007274627685547, "global_step": 570154, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0452229976654053, "global_step": 570155, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0000414848327637, "global_step": 570156, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0356640815734863, "global_step": 570157, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.032715320587158, "global_step": 570158, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0863471031188965, "global_step": 570159, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0101335048675537, "global_step": 570160, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.048572301864624, "global_step": 570161, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0420541763305664, "global_step": 570162, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.006481409072876, "global_step": 570163, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0244243144989014, "global_step": 570164, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.040778875350952, "global_step": 570165, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.95195472240448, "global_step": 570166, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.939075231552124, "global_step": 570167, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9609462022781372, "global_step": 570168, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.992063045501709, "global_step": 570169, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0638835430145264, "global_step": 570170, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0588481426239014, "global_step": 570171, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9830245971679688, "global_step": 570172, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.046064615249634, "global_step": 570173, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0246775150299072, "global_step": 570174, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.03279185295105, "global_step": 570175, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9890968799591064, "global_step": 570176, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9550777673721313, "global_step": 570177, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.97685706615448, "global_step": 570178, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0647854804992676, "global_step": 570179, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.036864757537842, "global_step": 570180, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1005518436431885, "global_step": 570181, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9587593078613281, "global_step": 570182, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.093693494796753, "global_step": 570183, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.027141571044922, "global_step": 570184, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.014240264892578, "global_step": 570185, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9580050706863403, "global_step": 570186, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.983997106552124, "global_step": 570187, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0402719974517822, "global_step": 570188, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0655410289764404, "global_step": 570189, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.03881573677063, "global_step": 570190, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1067888736724854, "global_step": 570191, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0494751930236816, "global_step": 570192, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9837177991867065, "global_step": 570193, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.973848581314087, "global_step": 570194, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.988115906715393, "global_step": 570195, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0160892009735107, "global_step": 570196, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0583841800689697, "global_step": 570197, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0867509841918945, "global_step": 570198, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.952939748764038, "global_step": 570199, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9959239959716797, "global_step": 570200, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.089280843734741, "global_step": 570201, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0361201763153076, "global_step": 570202, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0514514446258545, "global_step": 570203, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9420024156570435, "global_step": 570204, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.080545663833618, "global_step": 570205, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9700390100479126, "global_step": 570206, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.998962640762329, "global_step": 570207, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0357460975646973, "global_step": 570208, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.978523850440979, "global_step": 570209, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0283007621765137, "global_step": 570210, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.031508445739746, "global_step": 570211, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.032799005508423, "global_step": 570212, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.073817253112793, "global_step": 570213, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9989559650421143, "global_step": 570214, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0912575721740723, "global_step": 570215, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.929726004600525, "global_step": 570216, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0157365798950195, "global_step": 570217, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9424290657043457, "global_step": 570218, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.058399200439453, "global_step": 570219, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.97862708568573, "global_step": 570220, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.072185516357422, "global_step": 570221, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0351200103759766, "global_step": 570222, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.059011459350586, "global_step": 570223, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9529377222061157, "global_step": 570224, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.985258936882019, "global_step": 570225, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0620317459106445, "global_step": 570226, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0357935428619385, "global_step": 570227, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9883780479431152, "global_step": 570228, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0077879428863525, "global_step": 570229, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.034142017364502, "global_step": 570230, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.961343765258789, "global_step": 570231, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0352437496185303, "global_step": 570232, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.096898078918457, "global_step": 570233, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9458415508270264, "global_step": 570234, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.095755100250244, "global_step": 570235, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0162429809570312, "global_step": 570236, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.888980746269226, "global_step": 570237, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1097412109375, "global_step": 570238, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.956227421760559, "global_step": 570239, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.061786413192749, "global_step": 570240, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.096189022064209, "global_step": 570241, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0596163272857666, "global_step": 570242, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.064063549041748, "global_step": 570243, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0466203689575195, "global_step": 570244, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0376992225646973, "global_step": 570245, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0431666374206543, "global_step": 570246, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1066484451293945, "global_step": 570247, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.059328079223633, "global_step": 570248, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0127274990081787, "global_step": 570249, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9620907306671143, "global_step": 570250, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1053905487060547, "global_step": 570251, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9864579439163208, "global_step": 570252, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0585925579071045, "global_step": 570253, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9568769931793213, "global_step": 570254, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.084669351577759, "global_step": 570255, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.05312442779541, "global_step": 570256, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0594637393951416, "global_step": 570257, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0127100944519043, "global_step": 570258, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0276894569396973, "global_step": 570259, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.989546298980713, "global_step": 570260, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.088291883468628, "global_step": 570261, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9668374061584473, "global_step": 570262, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.079953193664551, "global_step": 570263, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.954101324081421, "global_step": 570264, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0543181896209717, "global_step": 570265, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0443947315216064, "global_step": 570266, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.067857503890991, "global_step": 570267, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0007691383361816, "global_step": 570268, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9713551998138428, "global_step": 570269, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.060307502746582, "global_step": 570270, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9258440732955933, "global_step": 570271, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.042217254638672, "global_step": 570272, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.082016944885254, "global_step": 570273, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0150885581970215, "global_step": 570274, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9878063201904297, "global_step": 570275, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0661773681640625, "global_step": 570276, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.967846393585205, "global_step": 570277, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0177087783813477, "global_step": 570278, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.035764694213867, "global_step": 570279, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0594780445098877, "global_step": 570280, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9998486042022705, "global_step": 570281, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.02341628074646, "global_step": 570282, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0116944313049316, "global_step": 570283, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9772251844406128, "global_step": 570284, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.070246458053589, "global_step": 570285, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0047104358673096, "global_step": 570286, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9970520734786987, "global_step": 570287, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0646772384643555, "global_step": 570288, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0224270820617676, "global_step": 570289, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9738963842391968, "global_step": 570290, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9775915145874023, "global_step": 570291, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1288318634033203, "global_step": 570292, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.079143524169922, "global_step": 570293, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9812290668487549, "global_step": 570294, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.056622266769409, "global_step": 570295, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0359065532684326, "global_step": 570296, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1142160892486572, "global_step": 570297, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9802720546722412, "global_step": 570298, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.034802198410034, "global_step": 570299, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.994808316230774, "global_step": 570300, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0548999309539795, "global_step": 570301, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9920620918273926, "global_step": 570302, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.96902596950531, "global_step": 570303, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.073216676712036, "global_step": 570304, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0005245208740234, "global_step": 570305, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.061671495437622, "global_step": 570306, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9780898094177246, "global_step": 570307, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0906994342803955, "global_step": 570308, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1113622188568115, "global_step": 570309, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0455167293548584, "global_step": 570310, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.001383066177368, "global_step": 570311, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0234551429748535, "global_step": 570312, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0187063217163086, "global_step": 570313, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.081197738647461, "global_step": 570314, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0327634811401367, "global_step": 570315, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0145657062530518, "global_step": 570316, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0214152336120605, "global_step": 570317, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.070774555206299, "global_step": 570318, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.030170440673828, "global_step": 570319, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9943851232528687, "global_step": 570320, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9175379276275635, "global_step": 570321, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0368154048919678, "global_step": 570322, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0191235542297363, "global_step": 570323, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9582384824752808, "global_step": 570324, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9917560815811157, "global_step": 570325, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9998918771743774, "global_step": 570326, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.092722177505493, "global_step": 570327, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0990149974823, "global_step": 570328, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0552291870117188, "global_step": 570329, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.993630051612854, "global_step": 570330, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9952150583267212, "global_step": 570331, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.038651704788208, "global_step": 570332, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.020080804824829, "global_step": 570333, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0470528602600098, "global_step": 570334, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.948000192642212, "global_step": 570335, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.141706943511963, "global_step": 570336, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0378952026367188, "global_step": 570337, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9969135522842407, "global_step": 570338, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9658794403076172, "global_step": 570339, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.027392864227295, "global_step": 570340, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0577545166015625, "global_step": 570341, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9686079025268555, "global_step": 570342, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9791311025619507, "global_step": 570343, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.05412220954895, "global_step": 570344, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0668835639953613, "global_step": 570345, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0800650119781494, "global_step": 570346, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9723604917526245, "global_step": 570347, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9583390951156616, "global_step": 570348, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9097175598144531, "global_step": 570349, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9688541889190674, "global_step": 570350, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0272634029388428, "global_step": 570351, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9873491525650024, "global_step": 570352, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.013434410095215, "global_step": 570353, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0443131923675537, "global_step": 570354, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9791713953018188, "global_step": 570355, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9841829538345337, "global_step": 570356, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0884313583374023, "global_step": 570357, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0280275344848633, "global_step": 570358, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0318334102630615, "global_step": 570359, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0153121948242188, "global_step": 570360, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.962489366531372, "global_step": 570361, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0287320613861084, "global_step": 570362, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.007965326309204, "global_step": 570363, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.035367488861084, "global_step": 570364, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9695427417755127, "global_step": 570365, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0371816158294678, "global_step": 570366, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.003664255142212, "global_step": 570367, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.077420473098755, "global_step": 570368, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.036741256713867, "global_step": 570369, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.137874126434326, "global_step": 570370, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9987081289291382, "global_step": 570371, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0991148948669434, "global_step": 570372, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.995966911315918, "global_step": 570373, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9650211334228516, "global_step": 570374, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.002389669418335, "global_step": 570375, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0777242183685303, "global_step": 570376, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0054962635040283, "global_step": 570377, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.990551233291626, "global_step": 570378, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0113565921783447, "global_step": 570379, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0296223163604736, "global_step": 570380, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.039564847946167, "global_step": 570381, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0667479038238525, "global_step": 570382, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0781750679016113, "global_step": 570383, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9768129587173462, "global_step": 570384, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.085066556930542, "global_step": 570385, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0099992752075195, "global_step": 570386, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.070099115371704, "global_step": 570387, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.083280086517334, "global_step": 570388, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0217044353485107, "global_step": 570389, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9786369800567627, "global_step": 570390, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0176289081573486, "global_step": 570391, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.000728130340576, "global_step": 570392, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0733656883239746, "global_step": 570393, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.966341495513916, "global_step": 570394, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.957432746887207, "global_step": 570395, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.042163848876953, "global_step": 570396, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.08296537399292, "global_step": 570397, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.06095814704895, "global_step": 570398, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.103597402572632, "global_step": 570399, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.060295581817627, "global_step": 570400, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9339815378189087, "global_step": 570401, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0756430625915527, "global_step": 570402, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.938625693321228, "global_step": 570403, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.979325532913208, "global_step": 570404, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9340951442718506, "global_step": 570405, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.082301378250122, "global_step": 570406, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0193593502044678, "global_step": 570407, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0231809616088867, "global_step": 570408, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.022888660430908, "global_step": 570409, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0523159503936768, "global_step": 570410, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0391156673431396, "global_step": 570411, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.036391496658325, "global_step": 570412, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.051278829574585, "global_step": 570413, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.112795829772949, "global_step": 570414, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0372586250305176, "global_step": 570415, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9996060132980347, "global_step": 570416, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.000060796737671, "global_step": 570417, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9753607511520386, "global_step": 570418, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.03352952003479, "global_step": 570419, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0095462799072266, "global_step": 570420, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0295112133026123, "global_step": 570421, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0692362785339355, "global_step": 570422, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.022580862045288, "global_step": 570423, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9607656002044678, "global_step": 570424, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.045560359954834, "global_step": 570425, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0643980503082275, "global_step": 570426, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.027984619140625, "global_step": 570427, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1626060009002686, "global_step": 570428, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.005316734313965, "global_step": 570429, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0087292194366455, "global_step": 570430, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1805968284606934, "global_step": 570431, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0203194618225098, "global_step": 570432, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.921907663345337, "global_step": 570433, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.082773208618164, "global_step": 570434, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9803889989852905, "global_step": 570435, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1175169944763184, "global_step": 570436, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0402963161468506, "global_step": 570437, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9478204250335693, "global_step": 570438, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1258432865142822, "global_step": 570439, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9656493663787842, "global_step": 570440, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.026616096496582, "global_step": 570441, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.976301670074463, "global_step": 570442, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9763455390930176, "global_step": 570443, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0351173877716064, "global_step": 570444, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0623221397399902, "global_step": 570445, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.947628140449524, "global_step": 570446, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0323662757873535, "global_step": 570447, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9869648218154907, "global_step": 570448, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0575950145721436, "global_step": 570449, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.094957113265991, "global_step": 570450, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.035198450088501, "global_step": 570451, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.071321487426758, "global_step": 570452, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0056679248809814, "global_step": 570453, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.03620982170105, "global_step": 570454, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9821747541427612, "global_step": 570455, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0327181816101074, "global_step": 570456, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0576300621032715, "global_step": 570457, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0073752403259277, "global_step": 570458, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1009325981140137, "global_step": 570459, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9531580209732056, "global_step": 570460, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.035311222076416, "global_step": 570461, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9407970905303955, "global_step": 570462, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0497851371765137, "global_step": 570463, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0792346000671387, "global_step": 570464, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.045400381088257, "global_step": 570465, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0091710090637207, "global_step": 570466, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0246942043304443, "global_step": 570467, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9344593286514282, "global_step": 570468, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.993698000907898, "global_step": 570469, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1151084899902344, "global_step": 570470, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.017585039138794, "global_step": 570471, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.027604103088379, "global_step": 570472, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0209052562713623, "global_step": 570473, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0116848945617676, "global_step": 570474, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9806751012802124, "global_step": 570475, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0207576751708984, "global_step": 570476, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.017451286315918, "global_step": 570477, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9638397693634033, "global_step": 570478, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.02575945854187, "global_step": 570479, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.036402940750122, "global_step": 570480, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0451765060424805, "global_step": 570481, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0337092876434326, "global_step": 570482, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0153450965881348, "global_step": 570483, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0122339725494385, "global_step": 570484, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0226519107818604, "global_step": 570485, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0335052013397217, "global_step": 570486, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.066805124282837, "global_step": 570487, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.957419753074646, "global_step": 570488, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0419631004333496, "global_step": 570489, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9891818761825562, "global_step": 570490, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0652272701263428, "global_step": 570491, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9891520738601685, "global_step": 570492, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.131088972091675, "global_step": 570493, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0700509548187256, "global_step": 570494, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.076011896133423, "global_step": 570495, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9797223806381226, "global_step": 570496, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9825034141540527, "global_step": 570497, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.068103313446045, "global_step": 570498, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.056246757507324, "global_step": 570499, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9957860708236694, "global_step": 570500, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9846478700637817, "global_step": 570501, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.038900375366211, "global_step": 570502, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.080115556716919, "global_step": 570503, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9965388774871826, "global_step": 570504, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0155563354492188, "global_step": 570505, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.074162483215332, "global_step": 570506, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.083857536315918, "global_step": 570507, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9652260541915894, "global_step": 570508, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.015277147293091, "global_step": 570509, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0277328491210938, "global_step": 570510, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0062241554260254, "global_step": 570511, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.028878688812256, "global_step": 570512, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.984361171722412, "global_step": 570513, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.05856990814209, "global_step": 570514, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9511655569076538, "global_step": 570515, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9986461400985718, "global_step": 570516, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.992234468460083, "global_step": 570517, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0910544395446777, "global_step": 570518, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.009061813354492, "global_step": 570519, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.032104015350342, "global_step": 570520, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0862197875976562, "global_step": 570521, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0244321823120117, "global_step": 570522, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0085842609405518, "global_step": 570523, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9664297103881836, "global_step": 570524, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9836962223052979, "global_step": 570525, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9355978965759277, "global_step": 570526, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9832431077957153, "global_step": 570527, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.940840482711792, "global_step": 570528, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0758228302001953, "global_step": 570529, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0325710773468018, "global_step": 570530, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0275819301605225, "global_step": 570531, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0524344444274902, "global_step": 570532, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0075199604034424, "global_step": 570533, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.061093330383301, "global_step": 570534, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0225603580474854, "global_step": 570535, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9851959943771362, "global_step": 570536, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1028988361358643, "global_step": 570537, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.8854551315307617, "global_step": 570538, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9677953720092773, "global_step": 570539, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.028900146484375, "global_step": 570540, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9486502408981323, "global_step": 570541, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.103675365447998, "global_step": 570542, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9962868690490723, "global_step": 570543, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.966814637184143, "global_step": 570544, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.978250503540039, "global_step": 570545, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9275225400924683, "global_step": 570546, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.997072458267212, "global_step": 570547, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0517983436584473, "global_step": 570548, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0459444522857666, "global_step": 570549, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0363876819610596, "global_step": 570550, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.006573438644409, "global_step": 570551, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.073835849761963, "global_step": 570552, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0176894664764404, "global_step": 570553, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9379985332489014, "global_step": 570554, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.010305881500244, "global_step": 570555, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0513641834259033, "global_step": 570556, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9761871099472046, "global_step": 570557, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0352823734283447, "global_step": 570558, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0791215896606445, "global_step": 570559, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.049966335296631, "global_step": 570560, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0631539821624756, "global_step": 570561, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.091156244277954, "global_step": 570562, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.080803394317627, "global_step": 570563, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0219385623931885, "global_step": 570564, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9964570999145508, "global_step": 570565, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.025338649749756, "global_step": 570566, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.011194944381714, "global_step": 570567, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9909887313842773, "global_step": 570568, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9557362794876099, "global_step": 570569, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1134793758392334, "global_step": 570570, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0328636169433594, "global_step": 570571, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.053387403488159, "global_step": 570572, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.037281036376953, "global_step": 570573, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0382285118103027, "global_step": 570574, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.005178451538086, "global_step": 570575, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0156190395355225, "global_step": 570576, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0187454223632812, "global_step": 570577, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.003641128540039, "global_step": 570578, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1455798149108887, "global_step": 570579, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.011237621307373, "global_step": 570580, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9738787412643433, "global_step": 570581, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9783161878585815, "global_step": 570582, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0437748432159424, "global_step": 570583, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.012111186981201, "global_step": 570584, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0330750942230225, "global_step": 570585, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0948708057403564, "global_step": 570586, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.935817003250122, "global_step": 570587, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0034306049346924, "global_step": 570588, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0226805210113525, "global_step": 570589, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9705543518066406, "global_step": 570590, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9752506017684937, "global_step": 570591, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.004617691040039, "global_step": 570592, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.050205707550049, "global_step": 570593, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1307904720306396, "global_step": 570594, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0422439575195312, "global_step": 570595, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.075139045715332, "global_step": 570596, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9770570993423462, "global_step": 570597, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.8673648834228516, "global_step": 570598, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1157867908477783, "global_step": 570599, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.02876353263855, "global_step": 570600, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0505642890930176, "global_step": 570601, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0289487838745117, "global_step": 570602, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.013500213623047, "global_step": 570603, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0434460639953613, "global_step": 570604, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0828680992126465, "global_step": 570605, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9993104934692383, "global_step": 570606, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.021207571029663, "global_step": 570607, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0535976886749268, "global_step": 570608, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0191097259521484, "global_step": 570609, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.082207679748535, "global_step": 570610, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0692391395568848, "global_step": 570611, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0466978549957275, "global_step": 570612, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.056288719177246, "global_step": 570613, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0193395614624023, "global_step": 570614, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0211472511291504, "global_step": 570615, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9917933940887451, "global_step": 570616, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.035632848739624, "global_step": 570617, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.950034737586975, "global_step": 570618, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9562017917633057, "global_step": 570619, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.948172926902771, "global_step": 570620, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9682273864746094, "global_step": 570621, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.995711088180542, "global_step": 570622, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.019627094268799, "global_step": 570623, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0693013668060303, "global_step": 570624, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.082282066345215, "global_step": 570625, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.040599822998047, "global_step": 570626, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0362062454223633, "global_step": 570627, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.104998826980591, "global_step": 570628, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0126566886901855, "global_step": 570629, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.083728313446045, "global_step": 570630, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0771729946136475, "global_step": 570631, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0357155799865723, "global_step": 570632, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.125735282897949, "global_step": 570633, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1096489429473877, "global_step": 570634, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9825010299682617, "global_step": 570635, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.060037851333618, "global_step": 570636, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0938408374786377, "global_step": 570637, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9990217685699463, "global_step": 570638, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0184171199798584, "global_step": 570639, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0565459728240967, "global_step": 570640, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.020017147064209, "global_step": 570641, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0456392765045166, "global_step": 570642, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0009286403656006, "global_step": 570643, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.910009503364563, "global_step": 570644, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.996130347251892, "global_step": 570645, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0010859966278076, "global_step": 570646, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9264471530914307, "global_step": 570647, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.042229175567627, "global_step": 570648, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0897183418273926, "global_step": 570649, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.027808427810669, "global_step": 570650, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9803444147109985, "global_step": 570651, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.8800175189971924, "global_step": 570652, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.003539562225342, "global_step": 570653, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9753906726837158, "global_step": 570654, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.010751962661743, "global_step": 570655, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0093648433685303, "global_step": 570656, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9067312479019165, "global_step": 570657, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0702550411224365, "global_step": 570658, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0127182006835938, "global_step": 570659, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9740263223648071, "global_step": 570660, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0199825763702393, "global_step": 570661, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9899671077728271, "global_step": 570662, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.019580364227295, "global_step": 570663, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.077399253845215, "global_step": 570664, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.030395746231079, "global_step": 570665, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.01363468170166, "global_step": 570666, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1352546215057373, "global_step": 570667, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9868003129959106, "global_step": 570668, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9750312566757202, "global_step": 570669, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0293235778808594, "global_step": 570670, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.036367177963257, "global_step": 570671, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.018864154815674, "global_step": 570672, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9774327278137207, "global_step": 570673, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9753152132034302, "global_step": 570674, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.038591146469116, "global_step": 570675, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.062098503112793, "global_step": 570676, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.028870105743408, "global_step": 570677, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9791921377182007, "global_step": 570678, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.042487621307373, "global_step": 570679, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.04183292388916, "global_step": 570680, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.045728921890259, "global_step": 570681, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0145280361175537, "global_step": 570682, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9807381629943848, "global_step": 570683, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9722944498062134, "global_step": 570684, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0497570037841797, "global_step": 570685, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0391323566436768, "global_step": 570686, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0376601219177246, "global_step": 570687, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.071439504623413, "global_step": 570688, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.083939552307129, "global_step": 570689, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.016676425933838, "global_step": 570690, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.072843313217163, "global_step": 570691, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.080911636352539, "global_step": 570692, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0983996391296387, "global_step": 570693, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.98062264919281, "global_step": 570694, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9751663208007812, "global_step": 570695, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9175457954406738, "global_step": 570696, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9971656799316406, "global_step": 570697, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1467974185943604, "global_step": 570698, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.074119806289673, "global_step": 570699, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0654075145721436, "global_step": 570700, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0612852573394775, "global_step": 570701, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0545945167541504, "global_step": 570702, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0494794845581055, "global_step": 570703, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.026876211166382, "global_step": 570704, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.037191867828369, "global_step": 570705, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1157546043395996, "global_step": 570706, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1446306705474854, "global_step": 570707, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0581586360931396, "global_step": 570708, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0222761631011963, "global_step": 570709, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.056284189224243, "global_step": 570710, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0101678371429443, "global_step": 570711, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0568723678588867, "global_step": 570712, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9872550964355469, "global_step": 570713, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0306570529937744, "global_step": 570714, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1179723739624023, "global_step": 570715, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.056680679321289, "global_step": 570716, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0292880535125732, "global_step": 570717, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.997865080833435, "global_step": 570718, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.016171932220459, "global_step": 570719, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9378079175949097, "global_step": 570720, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0597963333129883, "global_step": 570721, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.010453224182129, "global_step": 570722, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.086549758911133, "global_step": 570723, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.084252119064331, "global_step": 570724, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9998365640640259, "global_step": 570725, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9557411670684814, "global_step": 570726, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.084223985671997, "global_step": 570727, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.000694513320923, "global_step": 570728, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0062363147735596, "global_step": 570729, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9607341289520264, "global_step": 570730, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.040123224258423, "global_step": 570731, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0846030712127686, "global_step": 570732, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.00439190864563, "global_step": 570733, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.992116928100586, "global_step": 570734, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.068110466003418, "global_step": 570735, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9949331283569336, "global_step": 570736, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.004351854324341, "global_step": 570737, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1549999713897705, "global_step": 570738, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.052363157272339, "global_step": 570739, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.003582239151001, "global_step": 570740, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0029468536376953, "global_step": 570741, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.057135581970215, "global_step": 570742, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.01104474067688, "global_step": 570743, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0968987941741943, "global_step": 570744, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0288963317871094, "global_step": 570745, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.960319995880127, "global_step": 570746, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0180232524871826, "global_step": 570747, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0052804946899414, "global_step": 570748, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.061354160308838, "global_step": 570749, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.089637279510498, "global_step": 570750, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0427699089050293, "global_step": 570751, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.009861707687378, "global_step": 570752, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0180423259735107, "global_step": 570753, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.058513641357422, "global_step": 570754, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0341618061065674, "global_step": 570755, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.040276527404785, "global_step": 570756, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0561444759368896, "global_step": 570757, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9446895122528076, "global_step": 570758, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0713794231414795, "global_step": 570759, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9859275817871094, "global_step": 570760, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.082653760910034, "global_step": 570761, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0107839107513428, "global_step": 570762, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0021209716796875, "global_step": 570763, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9990804195404053, "global_step": 570764, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0040283203125, "global_step": 570765, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.057508945465088, "global_step": 570766, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.094393491744995, "global_step": 570767, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.035259962081909, "global_step": 570768, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9559067487716675, "global_step": 570769, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0159640312194824, "global_step": 570770, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0361804962158203, "global_step": 570771, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0626730918884277, "global_step": 570772, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9677770137786865, "global_step": 570773, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.015014886856079, "global_step": 570774, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.035186767578125, "global_step": 570775, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.975706934928894, "global_step": 570776, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0189125537872314, "global_step": 570777, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0043041706085205, "global_step": 570778, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0264382362365723, "global_step": 570779, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.010763168334961, "global_step": 570780, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0750346183776855, "global_step": 570781, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.040419816970825, "global_step": 570782, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.014829158782959, "global_step": 570783, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9111264944076538, "global_step": 570784, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9793459177017212, "global_step": 570785, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9884504079818726, "global_step": 570786, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.013378620147705, "global_step": 570787, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0185813903808594, "global_step": 570788, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.027977228164673, "global_step": 570789, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0429587364196777, "global_step": 570790, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0035221576690674, "global_step": 570791, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.014744758605957, "global_step": 570792, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0290675163269043, "global_step": 570793, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0399086475372314, "global_step": 570794, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9943314790725708, "global_step": 570795, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0429723262786865, "global_step": 570796, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.074505567550659, "global_step": 570797, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.094306230545044, "global_step": 570798, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.025146484375, "global_step": 570799, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1039600372314453, "global_step": 570800, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9891283512115479, "global_step": 570801, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.064460277557373, "global_step": 570802, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.994616150856018, "global_step": 570803, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0845820903778076, "global_step": 570804, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9822906255722046, "global_step": 570805, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.083411693572998, "global_step": 570806, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.997767448425293, "global_step": 570807, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.059805154800415, "global_step": 570808, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.010146141052246, "global_step": 570809, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9964568614959717, "global_step": 570810, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9859585762023926, "global_step": 570811, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.053903579711914, "global_step": 570812, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9773523807525635, "global_step": 570813, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.094097137451172, "global_step": 570814, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.101154088973999, "global_step": 570815, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0728633403778076, "global_step": 570816, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0609207153320312, "global_step": 570817, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1309525966644287, "global_step": 570818, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9919475317001343, "global_step": 570819, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9919066429138184, "global_step": 570820, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0321204662323, "global_step": 570821, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9537352323532104, "global_step": 570822, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.06614351272583, "global_step": 570823, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9931071996688843, "global_step": 570824, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0395257472991943, "global_step": 570825, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.000689744949341, "global_step": 570826, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.1268980503082275, "global_step": 570827, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0170018672943115, "global_step": 570828, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9875071048736572, "global_step": 570829, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.037949800491333, "global_step": 570830, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0715091228485107, "global_step": 570831, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.091655969619751, "global_step": 570832, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9910396337509155, "global_step": 570833, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.010741949081421, "global_step": 570834, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9479507207870483, "global_step": 570835, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.013928174972534, "global_step": 570836, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9887100458145142, "global_step": 570837, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.027468681335449, "global_step": 570838, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0408811569213867, "global_step": 570839, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0721559524536133, "global_step": 570840, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.050889492034912, "global_step": 570841, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9705004692077637, "global_step": 570842, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9738686084747314, "global_step": 570843, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0282366275787354, "global_step": 570844, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0184333324432373, "global_step": 570845, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9590349197387695, "global_step": 570846, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.055452823638916, "global_step": 570847, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.049192428588867, "global_step": 570848, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.063901424407959, "global_step": 570849, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.016289472579956, "global_step": 570850, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9960459470748901, "global_step": 570851, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.090238571166992, "global_step": 570852, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0775787830352783, "global_step": 570853, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9771606922149658, "global_step": 570854, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.104322910308838, "global_step": 570855, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.006931781768799, "global_step": 570856, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0244507789611816, "global_step": 570857, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0908851623535156, "global_step": 570858, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0435738563537598, "global_step": 570859, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0543084144592285, "global_step": 570860, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9390398263931274, "global_step": 570861, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0254149436950684, "global_step": 570862, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.035362720489502, "global_step": 570863, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9740533828735352, "global_step": 570864, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0308542251586914, "global_step": 570865, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0123937129974365, "global_step": 570866, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0374622344970703, "global_step": 570867, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.8857256174087524, "global_step": 570868, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9981307983398438, "global_step": 570869, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0747792720794678, "global_step": 570870, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.004615306854248, "global_step": 570871, "epoch": 938, "lr": 5e-05}
{"train_loss": 1.9783889055252075, "global_step": 570872, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.022934675216675, "global_step": 570873, "epoch": 938, "lr": 5e-05}
{"train_loss": 2.0008788108825684, "global_step": 570874, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0330848693847656, "global_step": 570875, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0319323539733887, "global_step": 570876, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.051011323928833, "global_step": 570877, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0163533687591553, "global_step": 570878, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9096784591674805, "global_step": 570879, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.057767391204834, "global_step": 570880, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.02683424949646, "global_step": 570881, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9796942472457886, "global_step": 570882, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9273595809936523, "global_step": 570883, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9796262979507446, "global_step": 570884, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9623583555221558, "global_step": 570885, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.015237331390381, "global_step": 570886, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.030609369277954, "global_step": 570887, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0486040115356445, "global_step": 570888, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.071892023086548, "global_step": 570889, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9939459562301636, "global_step": 570890, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0423359870910645, "global_step": 570891, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9738661050796509, "global_step": 570892, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0035488605499268, "global_step": 570893, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0537500381469727, "global_step": 570894, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.051791191101074, "global_step": 570895, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.01857590675354, "global_step": 570896, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.011042356491089, "global_step": 570897, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.111841917037964, "global_step": 570898, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.027735948562622, "global_step": 570899, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9858022928237915, "global_step": 570900, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.017035484313965, "global_step": 570901, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9916653633117676, "global_step": 570902, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0313286781311035, "global_step": 570903, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1001479625701904, "global_step": 570904, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0630130767822266, "global_step": 570905, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.986377477645874, "global_step": 570906, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.946402907371521, "global_step": 570907, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0408449172973633, "global_step": 570908, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9922462701797485, "global_step": 570909, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0000295639038086, "global_step": 570910, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.013153553009033, "global_step": 570911, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.977830171585083, "global_step": 570912, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9162517786026, "global_step": 570913, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.137669801712036, "global_step": 570914, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0278701782226562, "global_step": 570915, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0350966453552246, "global_step": 570916, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.056673526763916, "global_step": 570917, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.043339490890503, "global_step": 570918, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9312571287155151, "global_step": 570919, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.044146776199341, "global_step": 570920, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9712613821029663, "global_step": 570921, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0091006755828857, "global_step": 570922, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9773975610733032, "global_step": 570923, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0378613471984863, "global_step": 570924, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.035212278366089, "global_step": 570925, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9186089038848877, "global_step": 570926, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0126447677612305, "global_step": 570927, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0373950004577637, "global_step": 570928, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.043447971343994, "global_step": 570929, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.984001874923706, "global_step": 570930, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0040206909179688, "global_step": 570931, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.074207067489624, "global_step": 570932, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.958208680152893, "global_step": 570933, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0463719367980957, "global_step": 570934, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.066852331161499, "global_step": 570935, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.886063575744629, "global_step": 570936, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.007399797439575, "global_step": 570937, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9305483102798462, "global_step": 570938, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9863039255142212, "global_step": 570939, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.961345911026001, "global_step": 570940, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1060867309570312, "global_step": 570941, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9702177047729492, "global_step": 570942, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9125118255615234, "global_step": 570943, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0004889965057373, "global_step": 570944, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0031542778015137, "global_step": 570945, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0429201126098633, "global_step": 570946, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.01448392868042, "global_step": 570947, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9906327724456787, "global_step": 570948, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.008915901184082, "global_step": 570949, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0043272972106934, "global_step": 570950, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0608460903167725, "global_step": 570951, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0205793380737305, "global_step": 570952, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0063862800598145, "global_step": 570953, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0075581073760986, "global_step": 570954, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0264313220977783, "global_step": 570955, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9685442447662354, "global_step": 570956, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9364471435546875, "global_step": 570957, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0443599224090576, "global_step": 570958, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.08809757232666, "global_step": 570959, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9669440984725952, "global_step": 570960, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.07253360748291, "global_step": 570961, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0485341548919678, "global_step": 570962, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.043464183807373, "global_step": 570963, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9722623825073242, "global_step": 570964, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0179967880249023, "global_step": 570965, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0042710304260254, "global_step": 570966, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.055148124694824, "global_step": 570967, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9659299850463867, "global_step": 570968, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0782763957977295, "global_step": 570969, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0210111141204834, "global_step": 570970, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9541943073272705, "global_step": 570971, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.989086389541626, "global_step": 570972, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9120944738388062, "global_step": 570973, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0093703269958496, "global_step": 570974, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9780759811401367, "global_step": 570975, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.00064754486084, "global_step": 570976, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.87052321434021, "global_step": 570977, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.984049916267395, "global_step": 570978, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.042517900466919, "global_step": 570979, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9969675540924072, "global_step": 570980, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0475246906280518, "global_step": 570981, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.010134220123291, "global_step": 570982, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.002354860305786, "global_step": 570983, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9128588438034058, "global_step": 570984, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0039188861846924, "global_step": 570985, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0512118339538574, "global_step": 570986, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9552669525146484, "global_step": 570987, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0285465717315674, "global_step": 570988, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0053253173828125, "global_step": 570989, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9880784749984741, "global_step": 570990, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9601577520370483, "global_step": 570991, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.017051935195923, "global_step": 570992, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9281545877456665, "global_step": 570993, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.030029058456421, "global_step": 570994, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.8903483152389526, "global_step": 570995, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.017955780029297, "global_step": 570996, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0868964195251465, "global_step": 570997, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0417301654815674, "global_step": 570998, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.026547431945801, "global_step": 570999, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9959369897842407, "global_step": 571000, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9154545068740845, "global_step": 571001, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9920016527175903, "global_step": 571002, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0624091625213623, "global_step": 571003, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9793875217437744, "global_step": 571004, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.082624673843384, "global_step": 571005, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.122246503829956, "global_step": 571006, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.00203800201416, "global_step": 571007, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9897971153259277, "global_step": 571008, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0394036769866943, "global_step": 571009, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0185024738311768, "global_step": 571010, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.074857234954834, "global_step": 571011, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9167016744613647, "global_step": 571012, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.046137809753418, "global_step": 571013, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.03727388381958, "global_step": 571014, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9985039234161377, "global_step": 571015, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9663110971450806, "global_step": 571016, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0913755893707275, "global_step": 571017, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.031785249710083, "global_step": 571018, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0380616188049316, "global_step": 571019, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.001314401626587, "global_step": 571020, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9836422204971313, "global_step": 571021, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0303847789764404, "global_step": 571022, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9731476306915283, "global_step": 571023, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.08919620513916, "global_step": 571024, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0208327770233154, "global_step": 571025, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9952478408813477, "global_step": 571026, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.041816473007202, "global_step": 571027, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.958786129951477, "global_step": 571028, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9976134300231934, "global_step": 571029, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.060340642929077, "global_step": 571030, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0404841899871826, "global_step": 571031, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0434417724609375, "global_step": 571032, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.084996461868286, "global_step": 571033, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0009124279022217, "global_step": 571034, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9895905256271362, "global_step": 571035, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0597965717315674, "global_step": 571036, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.045987844467163, "global_step": 571037, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.952352523803711, "global_step": 571038, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.060797691345215, "global_step": 571039, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0980145931243896, "global_step": 571040, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0736091136932373, "global_step": 571041, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9592115879058838, "global_step": 571042, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0569002628326416, "global_step": 571043, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0143985748291016, "global_step": 571044, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.067882537841797, "global_step": 571045, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0255768299102783, "global_step": 571046, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9573421478271484, "global_step": 571047, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0274178981781006, "global_step": 571048, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.012880325317383, "global_step": 571049, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.020037889480591, "global_step": 571050, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9742461442947388, "global_step": 571051, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9263392686843872, "global_step": 571052, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0342695713043213, "global_step": 571053, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.065556764602661, "global_step": 571054, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.048758029937744, "global_step": 571055, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0445635318756104, "global_step": 571056, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1159896850585938, "global_step": 571057, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0212559700012207, "global_step": 571058, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0395569801330566, "global_step": 571059, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.960444450378418, "global_step": 571060, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0497617721557617, "global_step": 571061, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.082796573638916, "global_step": 571062, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9962666034698486, "global_step": 571063, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.90072500705719, "global_step": 571064, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0955638885498047, "global_step": 571065, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9423298835754395, "global_step": 571066, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.061762809753418, "global_step": 571067, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9868676662445068, "global_step": 571068, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.078115463256836, "global_step": 571069, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9965715408325195, "global_step": 571070, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0799736976623535, "global_step": 571071, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9774644374847412, "global_step": 571072, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9894083738327026, "global_step": 571073, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0339150428771973, "global_step": 571074, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9431756734848022, "global_step": 571075, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.980291485786438, "global_step": 571076, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0611062049865723, "global_step": 571077, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.043753147125244, "global_step": 571078, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9536540508270264, "global_step": 571079, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.075256586074829, "global_step": 571080, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0717625617980957, "global_step": 571081, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0449655055999756, "global_step": 571082, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.066302537918091, "global_step": 571083, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9896860122680664, "global_step": 571084, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1173529624938965, "global_step": 571085, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0923259258270264, "global_step": 571086, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9587677717208862, "global_step": 571087, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.010935068130493, "global_step": 571088, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0560617446899414, "global_step": 571089, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0074708461761475, "global_step": 571090, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9769880771636963, "global_step": 571091, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.035804510116577, "global_step": 571092, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9781347513198853, "global_step": 571093, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9656096696853638, "global_step": 571094, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0266242027282715, "global_step": 571095, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.02756667137146, "global_step": 571096, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0368216037750244, "global_step": 571097, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9848730564117432, "global_step": 571098, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.981902837753296, "global_step": 571099, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9749921560287476, "global_step": 571100, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0358128547668457, "global_step": 571101, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.048927068710327, "global_step": 571102, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0917809009552, "global_step": 571103, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.986537218093872, "global_step": 571104, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9382275342941284, "global_step": 571105, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0147945880889893, "global_step": 571106, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0144691467285156, "global_step": 571107, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9765100479125977, "global_step": 571108, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9446687698364258, "global_step": 571109, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9543159008026123, "global_step": 571110, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9990509748458862, "global_step": 571111, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0104589462280273, "global_step": 571112, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.047595500946045, "global_step": 571113, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.968801498413086, "global_step": 571114, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0935494899749756, "global_step": 571115, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.037048816680908, "global_step": 571116, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0229222774505615, "global_step": 571117, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0510787963867188, "global_step": 571118, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.022843837738037, "global_step": 571119, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.026201009750366, "global_step": 571120, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.037461757659912, "global_step": 571121, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.8921600580215454, "global_step": 571122, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.100306510925293, "global_step": 571123, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9562402963638306, "global_step": 571124, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.016648530960083, "global_step": 571125, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9093594551086426, "global_step": 571126, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.936646819114685, "global_step": 571127, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.053140878677368, "global_step": 571128, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9906643629074097, "global_step": 571129, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.936141848564148, "global_step": 571130, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.999563455581665, "global_step": 571131, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0432817935943604, "global_step": 571132, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0519936084747314, "global_step": 571133, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.012457847595215, "global_step": 571134, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9447473287582397, "global_step": 571135, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0082194805145264, "global_step": 571136, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0031280517578125, "global_step": 571137, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0080113410949707, "global_step": 571138, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0269598960876465, "global_step": 571139, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9713932275772095, "global_step": 571140, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1184988021850586, "global_step": 571141, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0650649070739746, "global_step": 571142, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0108978748321533, "global_step": 571143, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9510669708251953, "global_step": 571144, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.006502389907837, "global_step": 571145, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0230565071105957, "global_step": 571146, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0601284503936768, "global_step": 571147, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9867385625839233, "global_step": 571148, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9656026363372803, "global_step": 571149, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.047705888748169, "global_step": 571150, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0841124057769775, "global_step": 571151, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1115760803222656, "global_step": 571152, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9991014003753662, "global_step": 571153, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9486693143844604, "global_step": 571154, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0737082958221436, "global_step": 571155, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9788604974746704, "global_step": 571156, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.007143259048462, "global_step": 571157, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.029571771621704, "global_step": 571158, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0761773586273193, "global_step": 571159, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.981046199798584, "global_step": 571160, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.043818235397339, "global_step": 571161, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.041595220565796, "global_step": 571162, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.109790086746216, "global_step": 571163, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0946707725524902, "global_step": 571164, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.942191481590271, "global_step": 571165, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0715105533599854, "global_step": 571166, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9544860124588013, "global_step": 571167, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9362895488739014, "global_step": 571168, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.049245834350586, "global_step": 571169, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0409529209136963, "global_step": 571170, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0722765922546387, "global_step": 571171, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0499320030212402, "global_step": 571172, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.050637722015381, "global_step": 571173, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0427627563476562, "global_step": 571174, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.047783136367798, "global_step": 571175, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0617542266845703, "global_step": 571176, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0614802837371826, "global_step": 571177, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9808714389801025, "global_step": 571178, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.907923698425293, "global_step": 571179, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.04538893699646, "global_step": 571180, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0354349613189697, "global_step": 571181, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0596282482147217, "global_step": 571182, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.099337577819824, "global_step": 571183, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.027209997177124, "global_step": 571184, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.99351966381073, "global_step": 571185, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.993908166885376, "global_step": 571186, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.013049840927124, "global_step": 571187, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9866828918457031, "global_step": 571188, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0649962425231934, "global_step": 571189, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9875069856643677, "global_step": 571190, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.10567307472229, "global_step": 571191, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.038820743560791, "global_step": 571192, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.114598035812378, "global_step": 571193, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9723910093307495, "global_step": 571194, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9182745218276978, "global_step": 571195, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0565927028656006, "global_step": 571196, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.988542079925537, "global_step": 571197, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0467724800109863, "global_step": 571198, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0240280628204346, "global_step": 571199, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0860660076141357, "global_step": 571200, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0542659759521484, "global_step": 571201, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.061129331588745, "global_step": 571202, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.088143825531006, "global_step": 571203, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0858771800994873, "global_step": 571204, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0792057514190674, "global_step": 571205, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.124330997467041, "global_step": 571206, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.02266263961792, "global_step": 571207, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0096187591552734, "global_step": 571208, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0073904991149902, "global_step": 571209, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0307085514068604, "global_step": 571210, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0115885734558105, "global_step": 571211, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0153889656066895, "global_step": 571212, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0461719036102295, "global_step": 571213, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0672545433044434, "global_step": 571214, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9707987308502197, "global_step": 571215, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9397979974746704, "global_step": 571216, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0060901641845703, "global_step": 571217, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9545278549194336, "global_step": 571218, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0308215618133545, "global_step": 571219, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9830031394958496, "global_step": 571220, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9262162446975708, "global_step": 571221, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.010371208190918, "global_step": 571222, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.017855405807495, "global_step": 571223, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.012291669845581, "global_step": 571224, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9782354831695557, "global_step": 571225, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0062527656555176, "global_step": 571226, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.959887981414795, "global_step": 571227, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.058265447616577, "global_step": 571228, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1066014766693115, "global_step": 571229, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9563522338867188, "global_step": 571230, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9961479902267456, "global_step": 571231, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.969826340675354, "global_step": 571232, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9523253440856934, "global_step": 571233, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9945368766784668, "global_step": 571234, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0670275688171387, "global_step": 571235, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0236899852752686, "global_step": 571236, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9430314302444458, "global_step": 571237, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9982918500900269, "global_step": 571238, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0037708282470703, "global_step": 571239, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9899078607559204, "global_step": 571240, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9697915315628052, "global_step": 571241, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0146536827087402, "global_step": 571242, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9939509630203247, "global_step": 571243, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0415823459625244, "global_step": 571244, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9200729131698608, "global_step": 571245, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0688469409942627, "global_step": 571246, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.959897518157959, "global_step": 571247, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.037872076034546, "global_step": 571248, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9792267084121704, "global_step": 571249, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0441737174987793, "global_step": 571250, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.049018383026123, "global_step": 571251, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.096480369567871, "global_step": 571252, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0595364570617676, "global_step": 571253, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0050606727600098, "global_step": 571254, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.963170051574707, "global_step": 571255, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0427303314208984, "global_step": 571256, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0602498054504395, "global_step": 571257, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0910251140594482, "global_step": 571258, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.040313959121704, "global_step": 571259, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.028447389602661, "global_step": 571260, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0821261405944824, "global_step": 571261, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0431854724884033, "global_step": 571262, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0825698375701904, "global_step": 571263, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0515668392181396, "global_step": 571264, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0655465126037598, "global_step": 571265, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1255104541778564, "global_step": 571266, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.046849489212036, "global_step": 571267, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0241005420684814, "global_step": 571268, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0159428119659424, "global_step": 571269, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.043501615524292, "global_step": 571270, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.066218614578247, "global_step": 571271, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0577552318573, "global_step": 571272, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.037588357925415, "global_step": 571273, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.034590244293213, "global_step": 571274, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.022264242172241, "global_step": 571275, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0066022872924805, "global_step": 571276, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9646155834197998, "global_step": 571277, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9584681987762451, "global_step": 571278, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.043092727661133, "global_step": 571279, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.150663137435913, "global_step": 571280, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0426950454711914, "global_step": 571281, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0728819370269775, "global_step": 571282, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9711236953735352, "global_step": 571283, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.079296112060547, "global_step": 571284, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.100996255874634, "global_step": 571285, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9931504726409912, "global_step": 571286, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9245408773422241, "global_step": 571287, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9592078924179077, "global_step": 571288, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.046290397644043, "global_step": 571289, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0101423263549805, "global_step": 571290, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.027815580368042, "global_step": 571291, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0371246337890625, "global_step": 571292, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0013484954833984, "global_step": 571293, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1070075035095215, "global_step": 571294, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.005873680114746, "global_step": 571295, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.117548704147339, "global_step": 571296, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9785561561584473, "global_step": 571297, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9791837930679321, "global_step": 571298, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9751653671264648, "global_step": 571299, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0576391220092773, "global_step": 571300, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0807533264160156, "global_step": 571301, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.947737693786621, "global_step": 571302, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.053328037261963, "global_step": 571303, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.092705249786377, "global_step": 571304, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0483529567718506, "global_step": 571305, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9676016569137573, "global_step": 571306, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.998373031616211, "global_step": 571307, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0235893726348877, "global_step": 571308, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9837791919708252, "global_step": 571309, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0110974311828613, "global_step": 571310, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.114651918411255, "global_step": 571311, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.988344430923462, "global_step": 571312, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0698657035827637, "global_step": 571313, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0312349796295166, "global_step": 571314, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.084017753601074, "global_step": 571315, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.021393299102783, "global_step": 571316, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.933908224105835, "global_step": 571317, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0528383255004883, "global_step": 571318, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9527438879013062, "global_step": 571319, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.056868076324463, "global_step": 571320, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0484514236450195, "global_step": 571321, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.066072702407837, "global_step": 571322, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0881950855255127, "global_step": 571323, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.102963447570801, "global_step": 571324, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0646839141845703, "global_step": 571325, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.060183525085449, "global_step": 571326, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0084803104400635, "global_step": 571327, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0133397579193115, "global_step": 571328, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9727507829666138, "global_step": 571329, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9627118110656738, "global_step": 571330, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9502469301223755, "global_step": 571331, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.031590700149536, "global_step": 571332, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.028238534927368, "global_step": 571333, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0204179286956787, "global_step": 571334, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.075509786605835, "global_step": 571335, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9994168281555176, "global_step": 571336, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.997283697128296, "global_step": 571337, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9926354885101318, "global_step": 571338, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.078892707824707, "global_step": 571339, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.03002667427063, "global_step": 571340, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9943355321884155, "global_step": 571341, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0346217155456543, "global_step": 571342, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.032474994659424, "global_step": 571343, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0602712631225586, "global_step": 571344, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.990395188331604, "global_step": 571345, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.028179407119751, "global_step": 571346, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0392067432403564, "global_step": 571347, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0140128135681152, "global_step": 571348, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0052242279052734, "global_step": 571349, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.003732919692993, "global_step": 571350, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.031768798828125, "global_step": 571351, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9870269298553467, "global_step": 571352, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9481850862503052, "global_step": 571353, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9028737545013428, "global_step": 571354, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.001478672027588, "global_step": 571355, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0346755981445312, "global_step": 571356, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.032313108444214, "global_step": 571357, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0548603534698486, "global_step": 571358, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.104445219039917, "global_step": 571359, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.973496913909912, "global_step": 571360, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0374810695648193, "global_step": 571361, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0949087142944336, "global_step": 571362, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0305747985839844, "global_step": 571363, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9940720796585083, "global_step": 571364, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.043694257736206, "global_step": 571365, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1138858795166016, "global_step": 571366, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9802035093307495, "global_step": 571367, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0260517597198486, "global_step": 571368, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.999197244644165, "global_step": 571369, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0416669845581055, "global_step": 571370, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9892035722732544, "global_step": 571371, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0065176486968994, "global_step": 571372, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0630929470062256, "global_step": 571373, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0564842224121094, "global_step": 571374, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0817759037017822, "global_step": 571375, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.000943660736084, "global_step": 571376, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.007579803466797, "global_step": 571377, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9816263914108276, "global_step": 571378, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.968189001083374, "global_step": 571379, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9697346687316895, "global_step": 571380, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.965021014213562, "global_step": 571381, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0186049938201904, "global_step": 571382, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.032399892807007, "global_step": 571383, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9837815761566162, "global_step": 571384, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0345187187194824, "global_step": 571385, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0455119609832764, "global_step": 571386, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.056087017059326, "global_step": 571387, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.102517604827881, "global_step": 571388, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0145411491394043, "global_step": 571389, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.14408278465271, "global_step": 571390, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0485053062438965, "global_step": 571391, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.034449577331543, "global_step": 571392, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0301361083984375, "global_step": 571393, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.986268401145935, "global_step": 571394, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9755840301513672, "global_step": 571395, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0396788120269775, "global_step": 571396, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.043917179107666, "global_step": 571397, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.043466091156006, "global_step": 571398, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.055638313293457, "global_step": 571399, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0322823524475098, "global_step": 571400, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.123262882232666, "global_step": 571401, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0567448139190674, "global_step": 571402, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0250799655914307, "global_step": 571403, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0130808353424072, "global_step": 571404, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9406485557556152, "global_step": 571405, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1168627738952637, "global_step": 571406, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9890602827072144, "global_step": 571407, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0373518466949463, "global_step": 571408, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.03471040725708, "global_step": 571409, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9849056005477905, "global_step": 571410, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.068094253540039, "global_step": 571411, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9884319305419922, "global_step": 571412, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9743564128875732, "global_step": 571413, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9910181760787964, "global_step": 571414, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0002548694610596, "global_step": 571415, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0606095790863037, "global_step": 571416, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0475709438323975, "global_step": 571417, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.068072557449341, "global_step": 571418, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.125962734222412, "global_step": 571419, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9939841032028198, "global_step": 571420, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0300540924072266, "global_step": 571421, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0103399753570557, "global_step": 571422, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.056993007659912, "global_step": 571423, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0232696533203125, "global_step": 571424, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.022800922393799, "global_step": 571425, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9942736625671387, "global_step": 571426, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.028278112411499, "global_step": 571427, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.001497507095337, "global_step": 571428, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0633909702301025, "global_step": 571429, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.061933994293213, "global_step": 571430, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1362926959991455, "global_step": 571431, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0321264266967773, "global_step": 571432, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0095255374908447, "global_step": 571433, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9863914251327515, "global_step": 571434, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.016921043395996, "global_step": 571435, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0191147327423096, "global_step": 571436, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.023148775100708, "global_step": 571437, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0647220611572266, "global_step": 571438, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0796234607696533, "global_step": 571439, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0305659770965576, "global_step": 571440, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.964104413986206, "global_step": 571441, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.011770009994507, "global_step": 571442, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9737117290496826, "global_step": 571443, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.054316759109497, "global_step": 571444, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.047697067260742, "global_step": 571445, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9705815315246582, "global_step": 571446, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.998687982559204, "global_step": 571447, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0059666633605957, "global_step": 571448, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0222537517547607, "global_step": 571449, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9642605781555176, "global_step": 571450, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.109031915664673, "global_step": 571451, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9783539772033691, "global_step": 571452, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.103313446044922, "global_step": 571453, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0960395336151123, "global_step": 571454, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0085134506225586, "global_step": 571455, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0161421298980713, "global_step": 571456, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.108396530151367, "global_step": 571457, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9625722169876099, "global_step": 571458, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.02946138381958, "global_step": 571459, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.024834156036377, "global_step": 571460, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9753060340881348, "global_step": 571461, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1146156787872314, "global_step": 571462, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.042811393737793, "global_step": 571463, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0498507022857666, "global_step": 571464, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.00520396232605, "global_step": 571465, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0555272102355957, "global_step": 571466, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9789196252822876, "global_step": 571467, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0036401748657227, "global_step": 571468, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0629050731658936, "global_step": 571469, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0218875408172607, "global_step": 571470, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0645127296447754, "global_step": 571471, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0434041023254395, "global_step": 571472, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0334270000457764, "global_step": 571473, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.01505970954895, "global_step": 571474, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.087986469268799, "global_step": 571475, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9842803478240967, "global_step": 571476, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0188329219818115, "global_step": 571477, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.039634943008423, "global_step": 571478, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.097405195236206, "global_step": 571479, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0352182388305664, "global_step": 571480, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0916032791137695, "global_step": 571481, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9636467695236206, "global_step": 571482, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9111143350601196, "global_step": 571483, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9488924741744995, "global_step": 571484, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0016167163848877, "global_step": 571485, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.090567111968994, "global_step": 571486, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.042255401611328, "global_step": 571487, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0403923988342285, "global_step": 571488, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0968573093414307, "global_step": 571489, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.001410722732544, "global_step": 571490, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0402350425720215, "global_step": 571491, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0392189025878906, "global_step": 571492, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.023921251296997, "global_step": 571493, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0837974548339844, "global_step": 571494, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0615172386169434, "global_step": 571495, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0044100284576416, "global_step": 571496, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9960532188415527, "global_step": 571497, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.003485679626465, "global_step": 571498, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0034775733947754, "global_step": 571499, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1036205291748047, "global_step": 571500, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.041529417037964, "global_step": 571501, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9697753190994263, "global_step": 571502, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.024876594543457, "global_step": 571503, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0422608852386475, "global_step": 571504, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0396265983581543, "global_step": 571505, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0096333026885986, "global_step": 571506, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.993761658668518, "global_step": 571507, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.021878480911255, "global_step": 571508, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.032817840576172, "global_step": 571509, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.014693260192871, "global_step": 571510, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9539101123809814, "global_step": 571511, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0857419967651367, "global_step": 571512, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.024500608444214, "global_step": 571513, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.043621301651001, "global_step": 571514, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9982097148895264, "global_step": 571515, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0463106632232666, "global_step": 571516, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9845325946807861, "global_step": 571517, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0604631900787354, "global_step": 571518, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.076723098754883, "global_step": 571519, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1231141090393066, "global_step": 571520, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0328691005706787, "global_step": 571521, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.010707139968872, "global_step": 571522, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9698190689086914, "global_step": 571523, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9820270538330078, "global_step": 571524, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.050856828689575, "global_step": 571525, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.992566704750061, "global_step": 571526, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.997749924659729, "global_step": 571527, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0076427459716797, "global_step": 571528, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0241782665252686, "global_step": 571529, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9826717376708984, "global_step": 571530, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0498545169830322, "global_step": 571531, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.088063955307007, "global_step": 571532, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.001237154006958, "global_step": 571533, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0709338188171387, "global_step": 571534, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9783155918121338, "global_step": 571535, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.033024787902832, "global_step": 571536, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0827558040618896, "global_step": 571537, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0246806144714355, "global_step": 571538, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9660488367080688, "global_step": 571539, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.022735595703125, "global_step": 571540, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.083522081375122, "global_step": 571541, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.012500762939453, "global_step": 571542, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.000236749649048, "global_step": 571543, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0411624908447266, "global_step": 571544, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.942212462425232, "global_step": 571545, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9397804737091064, "global_step": 571546, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0839760303497314, "global_step": 571547, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0654540061950684, "global_step": 571548, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.99325692653656, "global_step": 571549, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9923677444458008, "global_step": 571550, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0729072093963623, "global_step": 571551, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0602991580963135, "global_step": 571552, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9506460428237915, "global_step": 571553, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0540881156921387, "global_step": 571554, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0455451011657715, "global_step": 571555, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.016623020172119, "global_step": 571556, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.080211639404297, "global_step": 571557, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1160240173339844, "global_step": 571558, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9646353721618652, "global_step": 571559, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0091471672058105, "global_step": 571560, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9856353998184204, "global_step": 571561, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0904664993286133, "global_step": 571562, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0299088954925537, "global_step": 571563, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1257822513580322, "global_step": 571564, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0523521900177, "global_step": 571565, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0180559158325195, "global_step": 571566, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9956181049346924, "global_step": 571567, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0516223907470703, "global_step": 571568, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.010375499725342, "global_step": 571569, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.922149896621704, "global_step": 571570, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0472042560577393, "global_step": 571571, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9859294891357422, "global_step": 571572, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9823942184448242, "global_step": 571573, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0154242515563965, "global_step": 571574, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0665957927703857, "global_step": 571575, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0321528911590576, "global_step": 571576, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.002016067504883, "global_step": 571577, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9708001613616943, "global_step": 571578, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.8994832038879395, "global_step": 571579, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0247535705566406, "global_step": 571580, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.026623010635376, "global_step": 571581, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9804143905639648, "global_step": 571582, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0115020275115967, "global_step": 571583, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.972820520401001, "global_step": 571584, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.070600986480713, "global_step": 571585, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0826175212860107, "global_step": 571586, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9861998558044434, "global_step": 571587, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9419244527816772, "global_step": 571588, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9991449117660522, "global_step": 571589, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.073357105255127, "global_step": 571590, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0529513359069824, "global_step": 571591, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.044659376144409, "global_step": 571592, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.979217767715454, "global_step": 571593, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9992797374725342, "global_step": 571594, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.038728952407837, "global_step": 571595, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0998456478118896, "global_step": 571596, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0981502532958984, "global_step": 571597, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.01174259185791, "global_step": 571598, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1819992065429688, "global_step": 571599, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9094692468643188, "global_step": 571600, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9635112285614014, "global_step": 571601, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.073991537094116, "global_step": 571602, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0975379943847656, "global_step": 571603, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.954211950302124, "global_step": 571604, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.121340036392212, "global_step": 571605, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9235100746154785, "global_step": 571606, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0197455883026123, "global_step": 571607, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.027893304824829, "global_step": 571608, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0221192836761475, "global_step": 571609, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.026087522506714, "global_step": 571610, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.034400224685669, "global_step": 571611, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.006521463394165, "global_step": 571612, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.060392379760742, "global_step": 571613, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.002971649169922, "global_step": 571614, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9943268299102783, "global_step": 571615, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0288145542144775, "global_step": 571616, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0523862838745117, "global_step": 571617, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.063502073287964, "global_step": 571618, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.012082099914551, "global_step": 571619, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1209802627563477, "global_step": 571620, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0770978927612305, "global_step": 571621, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0143864154815674, "global_step": 571622, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.10625958442688, "global_step": 571623, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.048748254776001, "global_step": 571624, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9978458881378174, "global_step": 571625, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.016367197036743, "global_step": 571626, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9933756589889526, "global_step": 571627, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0009572505950928, "global_step": 571628, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0768394470214844, "global_step": 571629, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9711031913757324, "global_step": 571630, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0321743488311768, "global_step": 571631, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.066190719604492, "global_step": 571632, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.022848129272461, "global_step": 571633, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9981597661972046, "global_step": 571634, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.002441883087158, "global_step": 571635, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0046725273132324, "global_step": 571636, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0193703174591064, "global_step": 571637, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.080033302307129, "global_step": 571638, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.041107416152954, "global_step": 571639, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.015435218811035, "global_step": 571640, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0955517292022705, "global_step": 571641, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9381861686706543, "global_step": 571642, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0194883346557617, "global_step": 571643, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.033869981765747, "global_step": 571644, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.157217502593994, "global_step": 571645, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0427112579345703, "global_step": 571646, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.039271593093872, "global_step": 571647, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0575520992279053, "global_step": 571648, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0008630752563477, "global_step": 571649, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9792238473892212, "global_step": 571650, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9887547492980957, "global_step": 571651, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.06120228767395, "global_step": 571652, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9716644287109375, "global_step": 571653, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.013078212738037, "global_step": 571654, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9850988388061523, "global_step": 571655, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.112967014312744, "global_step": 571656, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1241343021392822, "global_step": 571657, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0374224185943604, "global_step": 571658, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9964162111282349, "global_step": 571659, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9815675020217896, "global_step": 571660, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.065150737762451, "global_step": 571661, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9584338665008545, "global_step": 571662, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0179860591888428, "global_step": 571663, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.994354248046875, "global_step": 571664, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0200533866882324, "global_step": 571665, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0464909076690674, "global_step": 571666, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0152809619903564, "global_step": 571667, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9320759773254395, "global_step": 571668, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9951857328414917, "global_step": 571669, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0534956455230713, "global_step": 571670, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9171289205551147, "global_step": 571671, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.081756114959717, "global_step": 571672, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.082698106765747, "global_step": 571673, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0398247241973877, "global_step": 571674, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.054694175720215, "global_step": 571675, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9697786569595337, "global_step": 571676, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9486463069915771, "global_step": 571677, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0392327308654785, "global_step": 571678, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9720683097839355, "global_step": 571679, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.996206283569336, "global_step": 571680, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0277702808380127, "global_step": 571681, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0918314456939697, "global_step": 571682, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0450894832611084, "global_step": 571683, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9592713117599487, "global_step": 571684, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0916969776153564, "global_step": 571685, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9843873977661133, "global_step": 571686, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9899423122406006, "global_step": 571687, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9771640300750732, "global_step": 571688, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0790810585021973, "global_step": 571689, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0788536071777344, "global_step": 571690, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0752434730529785, "global_step": 571691, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0962815284729004, "global_step": 571692, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.024657964706421, "global_step": 571693, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9995770454406738, "global_step": 571694, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.003798723220825, "global_step": 571695, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.954553246498108, "global_step": 571696, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1115033626556396, "global_step": 571697, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0480539798736572, "global_step": 571698, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.00974178314209, "global_step": 571699, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0197384357452393, "global_step": 571700, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.074409008026123, "global_step": 571701, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.973878026008606, "global_step": 571702, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0970025062561035, "global_step": 571703, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0429165363311768, "global_step": 571704, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0408318042755127, "global_step": 571705, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0159871578216553, "global_step": 571706, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.105626344680786, "global_step": 571707, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.010465383529663, "global_step": 571708, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.01603364944458, "global_step": 571709, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0048816204071045, "global_step": 571710, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.047215461730957, "global_step": 571711, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.038691282272339, "global_step": 571712, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0317258834838867, "global_step": 571713, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9894908666610718, "global_step": 571714, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0218164920806885, "global_step": 571715, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1490437984466553, "global_step": 571716, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0714633464813232, "global_step": 571717, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9923765659332275, "global_step": 571718, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9824637174606323, "global_step": 571719, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9160847663879395, "global_step": 571720, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9929578304290771, "global_step": 571721, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0115389823913574, "global_step": 571722, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0932209491729736, "global_step": 571723, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0287883281707764, "global_step": 571724, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.968152642250061, "global_step": 571725, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9913530349731445, "global_step": 571726, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0020155906677246, "global_step": 571727, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9560482501983643, "global_step": 571728, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1285197734832764, "global_step": 571729, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.997294545173645, "global_step": 571730, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0115339756011963, "global_step": 571731, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0527124404907227, "global_step": 571732, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.159531354904175, "global_step": 571733, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.984726071357727, "global_step": 571734, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.985032558441162, "global_step": 571735, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0570924282073975, "global_step": 571736, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0849740505218506, "global_step": 571737, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.115320920944214, "global_step": 571738, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.034951686859131, "global_step": 571739, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.984291911125183, "global_step": 571740, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0691113471984863, "global_step": 571741, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.059429168701172, "global_step": 571742, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.026881456375122, "global_step": 571743, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1111156940460205, "global_step": 571744, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9308977127075195, "global_step": 571745, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0340754985809326, "global_step": 571746, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.005493640899658, "global_step": 571747, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.022702217102051, "global_step": 571748, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9342317581176758, "global_step": 571749, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.046173572540283, "global_step": 571750, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0019896030426025, "global_step": 571751, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.001985549926758, "global_step": 571752, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.937252402305603, "global_step": 571753, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.983550786972046, "global_step": 571754, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.025646686553955, "global_step": 571755, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0641510486602783, "global_step": 571756, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9942563772201538, "global_step": 571757, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1128711700439453, "global_step": 571758, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0731942653656006, "global_step": 571759, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0761287212371826, "global_step": 571760, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0602610111236572, "global_step": 571761, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0374503135681152, "global_step": 571762, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0127246379852295, "global_step": 571763, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.010012149810791, "global_step": 571764, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9986352920532227, "global_step": 571765, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0514423847198486, "global_step": 571766, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.027752161026001, "global_step": 571767, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9807734489440918, "global_step": 571768, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.047741651535034, "global_step": 571769, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9777381420135498, "global_step": 571770, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.110337734222412, "global_step": 571771, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.036926746368408, "global_step": 571772, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0801849365234375, "global_step": 571773, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1041643619537354, "global_step": 571774, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.04549503326416, "global_step": 571775, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1086671352386475, "global_step": 571776, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.064993143081665, "global_step": 571777, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0156588554382324, "global_step": 571778, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.108114004135132, "global_step": 571779, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0051965713500977, "global_step": 571780, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9885443449020386, "global_step": 571781, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9904296398162842, "global_step": 571782, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.073315143585205, "global_step": 571783, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0357284545898438, "global_step": 571784, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.017185688018799, "global_step": 571785, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0910658836364746, "global_step": 571786, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0365467071533203, "global_step": 571787, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.061047315597534, "global_step": 571788, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.00148868560791, "global_step": 571789, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9587903022766113, "global_step": 571790, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0884292125701904, "global_step": 571791, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.039053440093994, "global_step": 571792, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0812933444976807, "global_step": 571793, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9299848079681396, "global_step": 571794, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0282537937164307, "global_step": 571795, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.002096652984619, "global_step": 571796, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9477988481521606, "global_step": 571797, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0108089447021484, "global_step": 571798, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0338964462280273, "global_step": 571799, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.98956298828125, "global_step": 571800, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0295732021331787, "global_step": 571801, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0188405513763428, "global_step": 571802, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0284526348114014, "global_step": 571803, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9652955532073975, "global_step": 571804, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0550503730773926, "global_step": 571805, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.030918836593628, "global_step": 571806, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.07708477973938, "global_step": 571807, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0457475185394287, "global_step": 571808, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.050001859664917, "global_step": 571809, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0038275718688965, "global_step": 571810, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0193686485290527, "global_step": 571811, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9749338626861572, "global_step": 571812, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1511051654815674, "global_step": 571813, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9640907049179077, "global_step": 571814, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.046861171722412, "global_step": 571815, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0111286640167236, "global_step": 571816, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0294454097747803, "global_step": 571817, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0239524841308594, "global_step": 571818, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.015545606613159, "global_step": 571819, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9567784070968628, "global_step": 571820, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.051323413848877, "global_step": 571821, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9774984121322632, "global_step": 571822, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9442492723464966, "global_step": 571823, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0131354331970215, "global_step": 571824, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9203722476959229, "global_step": 571825, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9828553199768066, "global_step": 571826, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.940707802772522, "global_step": 571827, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.061269521713257, "global_step": 571828, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.1318199634552, "global_step": 571829, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.054635763168335, "global_step": 571830, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9982221126556396, "global_step": 571831, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0102593898773193, "global_step": 571832, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.079073905944824, "global_step": 571833, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0522267818450928, "global_step": 571834, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.2020466327667236, "global_step": 571835, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0570414066314697, "global_step": 571836, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.9691252708435059, "global_step": 571837, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0558018684387207, "global_step": 571838, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.119889497756958, "global_step": 571839, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.0499868392944336, "global_step": 571840, "epoch": 939, "lr": 5e-05}
{"train_loss": 1.949325442314148, "global_step": 571841, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.022977113723755, "global_step": 571842, "epoch": 939, "lr": 5e-05}
{"train_loss": 2.041560411453247, "global_step": 571843, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.095736265182495, "global_step": 571844, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.952418327331543, "global_step": 571845, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9472646713256836, "global_step": 571846, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.900178074836731, "global_step": 571847, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1117358207702637, "global_step": 571848, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0674550533294678, "global_step": 571849, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0411195755004883, "global_step": 571850, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0965638160705566, "global_step": 571851, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9870129823684692, "global_step": 571852, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.069458246231079, "global_step": 571853, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0350546836853027, "global_step": 571854, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.104206085205078, "global_step": 571855, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9657648801803589, "global_step": 571856, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.039677143096924, "global_step": 571857, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9986307621002197, "global_step": 571858, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0505316257476807, "global_step": 571859, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.167135715484619, "global_step": 571860, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0609500408172607, "global_step": 571861, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.965364694595337, "global_step": 571862, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0902838706970215, "global_step": 571863, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.028841018676758, "global_step": 571864, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.003845453262329, "global_step": 571865, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.038686513900757, "global_step": 571866, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9570306539535522, "global_step": 571867, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9650144577026367, "global_step": 571868, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0335636138916016, "global_step": 571869, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0242855548858643, "global_step": 571870, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0100021362304688, "global_step": 571871, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9868385791778564, "global_step": 571872, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9226223230361938, "global_step": 571873, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.013399362564087, "global_step": 571874, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9741753339767456, "global_step": 571875, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.990810513496399, "global_step": 571876, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0472843647003174, "global_step": 571877, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9358338117599487, "global_step": 571878, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0261576175689697, "global_step": 571879, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0672199726104736, "global_step": 571880, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9804844856262207, "global_step": 571881, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.031378746032715, "global_step": 571882, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9983270168304443, "global_step": 571883, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9698034524917603, "global_step": 571884, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9606462717056274, "global_step": 571885, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1000258922576904, "global_step": 571886, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9710105657577515, "global_step": 571887, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.975033164024353, "global_step": 571888, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9581929445266724, "global_step": 571889, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9846800565719604, "global_step": 571890, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9990572929382324, "global_step": 571891, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.01037859916687, "global_step": 571892, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0535526275634766, "global_step": 571893, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9837801456451416, "global_step": 571894, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.034356117248535, "global_step": 571895, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0877387523651123, "global_step": 571896, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0422894954681396, "global_step": 571897, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.10906720161438, "global_step": 571898, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0656397342681885, "global_step": 571899, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.025385856628418, "global_step": 571900, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0392298698425293, "global_step": 571901, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0094544887542725, "global_step": 571902, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1037631034851074, "global_step": 571903, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0032613277435303, "global_step": 571904, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.023973226547241, "global_step": 571905, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0125255584716797, "global_step": 571906, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0597524642944336, "global_step": 571907, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.048795461654663, "global_step": 571908, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9503045082092285, "global_step": 571909, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0244102478027344, "global_step": 571910, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9829188585281372, "global_step": 571911, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.046307325363159, "global_step": 571912, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0452699661254883, "global_step": 571913, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9567232131958008, "global_step": 571914, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9948691129684448, "global_step": 571915, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.065941572189331, "global_step": 571916, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9999845027923584, "global_step": 571917, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0025148391723633, "global_step": 571918, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9148739576339722, "global_step": 571919, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.015101432800293, "global_step": 571920, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9909424781799316, "global_step": 571921, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9786697626113892, "global_step": 571922, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0163769721984863, "global_step": 571923, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9254755973815918, "global_step": 571924, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.070225715637207, "global_step": 571925, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.146998643875122, "global_step": 571926, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.060356855392456, "global_step": 571927, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0848100185394287, "global_step": 571928, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9909802675247192, "global_step": 571929, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9844906330108643, "global_step": 571930, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0451979637145996, "global_step": 571931, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9535939693450928, "global_step": 571932, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.212266206741333, "global_step": 571933, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9089106321334839, "global_step": 571934, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.017930507659912, "global_step": 571935, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9880329370498657, "global_step": 571936, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0799450874328613, "global_step": 571937, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.010850191116333, "global_step": 571938, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.8488917350769043, "global_step": 571939, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.053046703338623, "global_step": 571940, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0709500312805176, "global_step": 571941, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.987024188041687, "global_step": 571942, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.031560182571411, "global_step": 571943, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0867557525634766, "global_step": 571944, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.037877321243286, "global_step": 571945, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.933560848236084, "global_step": 571946, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0069406032562256, "global_step": 571947, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9935662746429443, "global_step": 571948, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9633146524429321, "global_step": 571949, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9013981819152832, "global_step": 571950, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9693831205368042, "global_step": 571951, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0463385581970215, "global_step": 571952, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.050776481628418, "global_step": 571953, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9938308000564575, "global_step": 571954, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9827170372009277, "global_step": 571955, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9696190357208252, "global_step": 571956, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1035048961639404, "global_step": 571957, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.025465250015259, "global_step": 571958, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.988023281097412, "global_step": 571959, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.022916078567505, "global_step": 571960, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9779075384140015, "global_step": 571961, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.024491786956787, "global_step": 571962, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.108603000640869, "global_step": 571963, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.007829189300537, "global_step": 571964, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9883923530578613, "global_step": 571965, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0445902347564697, "global_step": 571966, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0294458866119385, "global_step": 571967, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.976014494895935, "global_step": 571968, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9948219060897827, "global_step": 571969, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9924614429473877, "global_step": 571970, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0269527435302734, "global_step": 571971, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.042983055114746, "global_step": 571972, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9770878553390503, "global_step": 571973, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.009688138961792, "global_step": 571974, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.026979923248291, "global_step": 571975, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9639705419540405, "global_step": 571976, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9668796062469482, "global_step": 571977, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0457284450531006, "global_step": 571978, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9971853494644165, "global_step": 571979, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9984185695648193, "global_step": 571980, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0375680923461914, "global_step": 571981, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0080227851867676, "global_step": 571982, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0149991512298584, "global_step": 571983, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9985663890838623, "global_step": 571984, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0253334045410156, "global_step": 571985, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9407533407211304, "global_step": 571986, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.038435459136963, "global_step": 571987, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.042546033859253, "global_step": 571988, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.065462350845337, "global_step": 571989, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.078909397125244, "global_step": 571990, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9440357685089111, "global_step": 571991, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.086189031600952, "global_step": 571992, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.926125168800354, "global_step": 571993, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.018160820007324, "global_step": 571994, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9911731481552124, "global_step": 571995, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0332159996032715, "global_step": 571996, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9764429330825806, "global_step": 571997, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0912177562713623, "global_step": 571998, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9597536325454712, "global_step": 571999, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9755350351333618, "global_step": 572000, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0892903804779053, "global_step": 572001, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.030759572982788, "global_step": 572002, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.06766676902771, "global_step": 572003, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.93122136592865, "global_step": 572004, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0484466552734375, "global_step": 572005, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9707202911376953, "global_step": 572006, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.072957992553711, "global_step": 572007, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0724897384643555, "global_step": 572008, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.030731439590454, "global_step": 572009, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9947094917297363, "global_step": 572010, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9778918027877808, "global_step": 572011, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9887895584106445, "global_step": 572012, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.052649974822998, "global_step": 572013, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0024216175079346, "global_step": 572014, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0264971256256104, "global_step": 572015, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0380618572235107, "global_step": 572016, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.954648494720459, "global_step": 572017, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.007763624191284, "global_step": 572018, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9841868877410889, "global_step": 572019, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9737317562103271, "global_step": 572020, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0676252841949463, "global_step": 572021, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0554070472717285, "global_step": 572022, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0015721321105957, "global_step": 572023, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0760369300842285, "global_step": 572024, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.010241985321045, "global_step": 572025, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.03202223777771, "global_step": 572026, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9998600482940674, "global_step": 572027, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0167360305786133, "global_step": 572028, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0153751373291016, "global_step": 572029, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9754427671432495, "global_step": 572030, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9852373600006104, "global_step": 572031, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0552608966827393, "global_step": 572032, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9624109268188477, "global_step": 572033, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.060378074645996, "global_step": 572034, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.011180877685547, "global_step": 572035, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0233538150787354, "global_step": 572036, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0602872371673584, "global_step": 572037, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1121556758880615, "global_step": 572038, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.004629135131836, "global_step": 572039, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0282845497131348, "global_step": 572040, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.026674747467041, "global_step": 572041, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0622873306274414, "global_step": 572042, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0381925106048584, "global_step": 572043, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0846107006073, "global_step": 572044, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0541326999664307, "global_step": 572045, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.916539192199707, "global_step": 572046, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0207571983337402, "global_step": 572047, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9933791160583496, "global_step": 572048, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9492340087890625, "global_step": 572049, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0454564094543457, "global_step": 572050, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.076366424560547, "global_step": 572051, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9731996059417725, "global_step": 572052, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0783660411834717, "global_step": 572053, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0623652935028076, "global_step": 572054, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.02862548828125, "global_step": 572055, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.080467700958252, "global_step": 572056, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0664305686950684, "global_step": 572057, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0252368450164795, "global_step": 572058, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0204131603240967, "global_step": 572059, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9794542789459229, "global_step": 572060, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.001251459121704, "global_step": 572061, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0527350902557373, "global_step": 572062, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0132150650024414, "global_step": 572063, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0454599857330322, "global_step": 572064, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1222329139709473, "global_step": 572065, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9911694526672363, "global_step": 572066, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.958794355392456, "global_step": 572067, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.072659730911255, "global_step": 572068, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9825422763824463, "global_step": 572069, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.951322317123413, "global_step": 572070, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0846378803253174, "global_step": 572071, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.054422616958618, "global_step": 572072, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.038243293762207, "global_step": 572073, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0359020233154297, "global_step": 572074, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0035901069641113, "global_step": 572075, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.022057056427002, "global_step": 572076, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0649542808532715, "global_step": 572077, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.994260311126709, "global_step": 572078, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.044034004211426, "global_step": 572079, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1053314208984375, "global_step": 572080, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.081578016281128, "global_step": 572081, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9934768676757812, "global_step": 572082, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.017502546310425, "global_step": 572083, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0631587505340576, "global_step": 572084, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9967964887619019, "global_step": 572085, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.026214122772217, "global_step": 572086, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9064685106277466, "global_step": 572087, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0193533897399902, "global_step": 572088, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9666972160339355, "global_step": 572089, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9696580171585083, "global_step": 572090, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.112182855606079, "global_step": 572091, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0417778491973877, "global_step": 572092, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0277934074401855, "global_step": 572093, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.074577808380127, "global_step": 572094, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0612049102783203, "global_step": 572095, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9825336933135986, "global_step": 572096, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.06011700630188, "global_step": 572097, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9708833694458008, "global_step": 572098, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.017183303833008, "global_step": 572099, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.041714906692505, "global_step": 572100, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9487183094024658, "global_step": 572101, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0297162532806396, "global_step": 572102, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9102715253829956, "global_step": 572103, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9994215965270996, "global_step": 572104, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1023597717285156, "global_step": 572105, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0551698207855225, "global_step": 572106, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0901246070861816, "global_step": 572107, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1226541996002197, "global_step": 572108, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0697853565216064, "global_step": 572109, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0901026725769043, "global_step": 572110, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.021177053451538, "global_step": 572111, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0549728870391846, "global_step": 572112, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.063706636428833, "global_step": 572113, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.016650438308716, "global_step": 572114, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9968030452728271, "global_step": 572115, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.125802755355835, "global_step": 572116, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0404531955718994, "global_step": 572117, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0149543285369873, "global_step": 572118, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0282697677612305, "global_step": 572119, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.000065803527832, "global_step": 572120, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9818730354309082, "global_step": 572121, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9443604946136475, "global_step": 572122, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.033520221710205, "global_step": 572123, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9588035345077515, "global_step": 572124, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0195300579071045, "global_step": 572125, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1522090435028076, "global_step": 572126, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0176501274108887, "global_step": 572127, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.023606538772583, "global_step": 572128, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9990116357803345, "global_step": 572129, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9599498510360718, "global_step": 572130, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0672974586486816, "global_step": 572131, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.083972215652466, "global_step": 572132, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9683679342269897, "global_step": 572133, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9592283964157104, "global_step": 572134, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.060284376144409, "global_step": 572135, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9526443481445312, "global_step": 572136, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.046882152557373, "global_step": 572137, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9597243070602417, "global_step": 572138, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9649238586425781, "global_step": 572139, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0780065059661865, "global_step": 572140, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0533530712127686, "global_step": 572141, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9392120838165283, "global_step": 572142, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0716845989227295, "global_step": 572143, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.019561767578125, "global_step": 572144, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.052065849304199, "global_step": 572145, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9677131175994873, "global_step": 572146, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.003563404083252, "global_step": 572147, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.098539113998413, "global_step": 572148, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0432043075561523, "global_step": 572149, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0099196434020996, "global_step": 572150, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0198488235473633, "global_step": 572151, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0919744968414307, "global_step": 572152, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.030848503112793, "global_step": 572153, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9601895809173584, "global_step": 572154, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9852044582366943, "global_step": 572155, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.033665418624878, "global_step": 572156, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0060558319091797, "global_step": 572157, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9306658506393433, "global_step": 572158, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0180652141571045, "global_step": 572159, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0429952144622803, "global_step": 572160, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9797203540802002, "global_step": 572161, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.003310441970825, "global_step": 572162, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0239791870117188, "global_step": 572163, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0249855518341064, "global_step": 572164, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0593738555908203, "global_step": 572165, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0496087074279785, "global_step": 572166, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.055589199066162, "global_step": 572167, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.993025779724121, "global_step": 572168, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0559334754943848, "global_step": 572169, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.026425361633301, "global_step": 572170, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0594844818115234, "global_step": 572171, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9570435285568237, "global_step": 572172, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.017538547515869, "global_step": 572173, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0692965984344482, "global_step": 572174, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9635460376739502, "global_step": 572175, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0166375637054443, "global_step": 572176, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9514009952545166, "global_step": 572177, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9855225086212158, "global_step": 572178, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0050840377807617, "global_step": 572179, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0408356189727783, "global_step": 572180, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.032261371612549, "global_step": 572181, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0842132568359375, "global_step": 572182, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0645930767059326, "global_step": 572183, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0119643211364746, "global_step": 572184, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.997847080230713, "global_step": 572185, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9756964445114136, "global_step": 572186, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0367705821990967, "global_step": 572187, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1109962463378906, "global_step": 572188, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.008085012435913, "global_step": 572189, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0502824783325195, "global_step": 572190, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.074981451034546, "global_step": 572191, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9795429706573486, "global_step": 572192, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9590352773666382, "global_step": 572193, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.07187557220459, "global_step": 572194, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.927709937095642, "global_step": 572195, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0490503311157227, "global_step": 572196, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0841004848480225, "global_step": 572197, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9742952585220337, "global_step": 572198, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0741281509399414, "global_step": 572199, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0490803718566895, "global_step": 572200, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0013980865478516, "global_step": 572201, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9912947416305542, "global_step": 572202, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.098755121231079, "global_step": 572203, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9635831117630005, "global_step": 572204, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9822455644607544, "global_step": 572205, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.021623373031616, "global_step": 572206, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9539728164672852, "global_step": 572207, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9879618883132935, "global_step": 572208, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9565691947937012, "global_step": 572209, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.8940643072128296, "global_step": 572210, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0306553840637207, "global_step": 572211, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.037419080734253, "global_step": 572212, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9296408891677856, "global_step": 572213, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.033620595932007, "global_step": 572214, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.008211374282837, "global_step": 572215, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0550642013549805, "global_step": 572216, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.025428295135498, "global_step": 572217, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.957228183746338, "global_step": 572218, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0041773319244385, "global_step": 572219, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0588631629943848, "global_step": 572220, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.007690668106079, "global_step": 572221, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.048784017562866, "global_step": 572222, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.047544479370117, "global_step": 572223, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9839979410171509, "global_step": 572224, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0153558254241943, "global_step": 572225, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0919435024261475, "global_step": 572226, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.02187180519104, "global_step": 572227, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.920485258102417, "global_step": 572228, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0795094966888428, "global_step": 572229, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.03853178024292, "global_step": 572230, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9354982376098633, "global_step": 572231, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1148056983947754, "global_step": 572232, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0421674251556396, "global_step": 572233, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0704777240753174, "global_step": 572234, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0184402465820312, "global_step": 572235, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9290868043899536, "global_step": 572236, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0856759548187256, "global_step": 572237, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.092257022857666, "global_step": 572238, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.912743091583252, "global_step": 572239, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.989228367805481, "global_step": 572240, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0291965007781982, "global_step": 572241, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9793140888214111, "global_step": 572242, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0123910903930664, "global_step": 572243, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.012272834777832, "global_step": 572244, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0554027557373047, "global_step": 572245, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0450778007507324, "global_step": 572246, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1020748615264893, "global_step": 572247, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.966444730758667, "global_step": 572248, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9337193965911865, "global_step": 572249, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.001411199569702, "global_step": 572250, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9235572814941406, "global_step": 572251, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0317933559417725, "global_step": 572252, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0593836307525635, "global_step": 572253, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0046303272247314, "global_step": 572254, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9226150512695312, "global_step": 572255, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.955486536026001, "global_step": 572256, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.979915976524353, "global_step": 572257, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.008310317993164, "global_step": 572258, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9832346439361572, "global_step": 572259, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0132179260253906, "global_step": 572260, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.06372332572937, "global_step": 572261, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.004199266433716, "global_step": 572262, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0605602264404297, "global_step": 572263, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.959869623184204, "global_step": 572264, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0440175533294678, "global_step": 572265, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0609304904937744, "global_step": 572266, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0447378158569336, "global_step": 572267, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.074124336242676, "global_step": 572268, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9620704650878906, "global_step": 572269, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0809247493743896, "global_step": 572270, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9698189496994019, "global_step": 572271, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0945112705230713, "global_step": 572272, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9802383184432983, "global_step": 572273, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0158936977386475, "global_step": 572274, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0276761054992676, "global_step": 572275, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0167653560638428, "global_step": 572276, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.041121482849121, "global_step": 572277, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.007181406021118, "global_step": 572278, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.103370428085327, "global_step": 572279, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.054891347885132, "global_step": 572280, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.097825765609741, "global_step": 572281, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.011408805847168, "global_step": 572282, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.980374813079834, "global_step": 572283, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0407395362854004, "global_step": 572284, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9757994413375854, "global_step": 572285, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0248305797576904, "global_step": 572286, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9440364837646484, "global_step": 572287, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0496673583984375, "global_step": 572288, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9998576641082764, "global_step": 572289, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.009706974029541, "global_step": 572290, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.076569080352783, "global_step": 572291, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0533406734466553, "global_step": 572292, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.072528600692749, "global_step": 572293, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.112443208694458, "global_step": 572294, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9986448287963867, "global_step": 572295, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9820500612258911, "global_step": 572296, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9935057163238525, "global_step": 572297, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9978156089782715, "global_step": 572298, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1100192070007324, "global_step": 572299, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.035287618637085, "global_step": 572300, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0548253059387207, "global_step": 572301, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0388426780700684, "global_step": 572302, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.020508050918579, "global_step": 572303, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.05304217338562, "global_step": 572304, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.077512741088867, "global_step": 572305, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0896964073181152, "global_step": 572306, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0178706645965576, "global_step": 572307, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0201034545898438, "global_step": 572308, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9340624809265137, "global_step": 572309, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0244240760803223, "global_step": 572310, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9981797933578491, "global_step": 572311, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0382449626922607, "global_step": 572312, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0106351375579834, "global_step": 572313, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9828239679336548, "global_step": 572314, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0178818702697754, "global_step": 572315, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.105556011199951, "global_step": 572316, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.003023147583008, "global_step": 572317, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.079127550125122, "global_step": 572318, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.024766206741333, "global_step": 572319, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9438925981521606, "global_step": 572320, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0448555946350098, "global_step": 572321, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0154614448547363, "global_step": 572322, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9761403799057007, "global_step": 572323, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0040364265441895, "global_step": 572324, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.074605941772461, "global_step": 572325, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0396249294281006, "global_step": 572326, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.961250901222229, "global_step": 572327, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0549309253692627, "global_step": 572328, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.062129497528076, "global_step": 572329, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0588762760162354, "global_step": 572330, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.100621461868286, "global_step": 572331, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9461886882781982, "global_step": 572332, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.007385730743408, "global_step": 572333, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.127779960632324, "global_step": 572334, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0370490550994873, "global_step": 572335, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1407203674316406, "global_step": 572336, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9692625999450684, "global_step": 572337, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9709243774414062, "global_step": 572338, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0149412155151367, "global_step": 572339, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.108370304107666, "global_step": 572340, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.036750316619873, "global_step": 572341, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9696972370147705, "global_step": 572342, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.096984386444092, "global_step": 572343, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.988337755203247, "global_step": 572344, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.050245523452759, "global_step": 572345, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.961510181427002, "global_step": 572346, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.022655963897705, "global_step": 572347, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0120601654052734, "global_step": 572348, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.995118498802185, "global_step": 572349, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0747902393341064, "global_step": 572350, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0049657821655273, "global_step": 572351, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0151875019073486, "global_step": 572352, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9929862022399902, "global_step": 572353, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.018420696258545, "global_step": 572354, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.106558322906494, "global_step": 572355, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.964836597442627, "global_step": 572356, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.999708890914917, "global_step": 572357, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0447330474853516, "global_step": 572358, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0403189659118652, "global_step": 572359, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.955633521080017, "global_step": 572360, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.009857654571533, "global_step": 572361, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.978644609451294, "global_step": 572362, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9770691394805908, "global_step": 572363, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.081987142562866, "global_step": 572364, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.961196780204773, "global_step": 572365, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0328896045684814, "global_step": 572366, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.025754690170288, "global_step": 572367, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9860283136367798, "global_step": 572368, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.004040241241455, "global_step": 572369, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.092905282974243, "global_step": 572370, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9981048107147217, "global_step": 572371, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9401941299438477, "global_step": 572372, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0253758430480957, "global_step": 572373, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.954993724822998, "global_step": 572374, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9728217124938965, "global_step": 572375, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0127575397491455, "global_step": 572376, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.013779878616333, "global_step": 572377, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9805229902267456, "global_step": 572378, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0053961277008057, "global_step": 572379, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9712783098220825, "global_step": 572380, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.089050769805908, "global_step": 572381, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0286242961883545, "global_step": 572382, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0226728916168213, "global_step": 572383, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9696811437606812, "global_step": 572384, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0973873138427734, "global_step": 572385, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9846030473709106, "global_step": 572386, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.038027763366699, "global_step": 572387, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0014870166778564, "global_step": 572388, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0647990703582764, "global_step": 572389, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0239622592926025, "global_step": 572390, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0654637813568115, "global_step": 572391, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1418118476867676, "global_step": 572392, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0501837730407715, "global_step": 572393, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0718696117401123, "global_step": 572394, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0874345302581787, "global_step": 572395, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9760488271713257, "global_step": 572396, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9982458353042603, "global_step": 572397, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0068042278289795, "global_step": 572398, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0528018474578857, "global_step": 572399, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0009024143218994, "global_step": 572400, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9959162473678589, "global_step": 572401, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0999491214752197, "global_step": 572402, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9459301233291626, "global_step": 572403, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0230252742767334, "global_step": 572404, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0650813579559326, "global_step": 572405, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0342519283294678, "global_step": 572406, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0832650661468506, "global_step": 572407, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9295285940170288, "global_step": 572408, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.030761241912842, "global_step": 572409, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9695181846618652, "global_step": 572410, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9785971641540527, "global_step": 572411, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1124494075775146, "global_step": 572412, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9776760339736938, "global_step": 572413, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0750603675842285, "global_step": 572414, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9393177032470703, "global_step": 572415, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.073030948638916, "global_step": 572416, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0595622062683105, "global_step": 572417, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9697993993759155, "global_step": 572418, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.998291254043579, "global_step": 572419, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.084963798522949, "global_step": 572420, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1186022758483887, "global_step": 572421, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0078418254852295, "global_step": 572422, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9536839723587036, "global_step": 572423, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0391881465911865, "global_step": 572424, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9553585052490234, "global_step": 572425, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0522515773773193, "global_step": 572426, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9248158931732178, "global_step": 572427, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0707242488861084, "global_step": 572428, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9841125011444092, "global_step": 572429, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.031546115875244, "global_step": 572430, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0219154357910156, "global_step": 572431, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0167038440704346, "global_step": 572432, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.106201171875, "global_step": 572433, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.093226194381714, "global_step": 572434, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0816829204559326, "global_step": 572435, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0193936824798584, "global_step": 572436, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.01023006439209, "global_step": 572437, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.018663167953491, "global_step": 572438, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0177810192108154, "global_step": 572439, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.038492441177368, "global_step": 572440, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.100715398788452, "global_step": 572441, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.07287859916687, "global_step": 572442, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0114176273345947, "global_step": 572443, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1006267070770264, "global_step": 572444, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0378737449645996, "global_step": 572445, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.055180788040161, "global_step": 572446, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.00961971282959, "global_step": 572447, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0714452266693115, "global_step": 572448, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0405282974243164, "global_step": 572449, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9651808738708496, "global_step": 572450, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.988436222076416, "global_step": 572451, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9192874431610107, "global_step": 572452, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0557217597961426, "global_step": 572453, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0793581008911133, "global_step": 572454, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9731227159500122, "global_step": 572455, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.00136661529541, "global_step": 572456, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1375784873962402, "global_step": 572457, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9625581502914429, "global_step": 572458, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0859413146972656, "global_step": 572459, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1348466873168945, "global_step": 572460, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9887899160385132, "global_step": 572461, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0337839126586914, "global_step": 572462, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.025937080383301, "global_step": 572463, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0637848377227783, "global_step": 572464, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9771549701690674, "global_step": 572465, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.012761116027832, "global_step": 572466, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9760453701019287, "global_step": 572467, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9876924753189087, "global_step": 572468, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0479159355163574, "global_step": 572469, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.024338483810425, "global_step": 572470, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9920982122421265, "global_step": 572471, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.023855447769165, "global_step": 572472, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0511295795440674, "global_step": 572473, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9963167905807495, "global_step": 572474, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9212114810943604, "global_step": 572475, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9844928979873657, "global_step": 572476, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1224427223205566, "global_step": 572477, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.08414363861084, "global_step": 572478, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.960188627243042, "global_step": 572479, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.077336311340332, "global_step": 572480, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.998658537864685, "global_step": 572481, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0174083709716797, "global_step": 572482, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.963860034942627, "global_step": 572483, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.017855167388916, "global_step": 572484, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0515036582946777, "global_step": 572485, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0115890502929688, "global_step": 572486, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9676103591918945, "global_step": 572487, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1147289276123047, "global_step": 572488, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.083181619644165, "global_step": 572489, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.994871735572815, "global_step": 572490, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9947632551193237, "global_step": 572491, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9733765125274658, "global_step": 572492, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.005962371826172, "global_step": 572493, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.023996591567993, "global_step": 572494, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9885295629501343, "global_step": 572495, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0442054271698, "global_step": 572496, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0129072666168213, "global_step": 572497, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1740360260009766, "global_step": 572498, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9805558919906616, "global_step": 572499, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0649337768554688, "global_step": 572500, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9873526096343994, "global_step": 572501, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9480472803115845, "global_step": 572502, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0305936336517334, "global_step": 572503, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.003530502319336, "global_step": 572504, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0733110904693604, "global_step": 572505, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0709645748138428, "global_step": 572506, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0007495880126953, "global_step": 572507, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.080946445465088, "global_step": 572508, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9545724391937256, "global_step": 572509, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.03147029876709, "global_step": 572510, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0266013145446777, "global_step": 572511, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.015214681625366, "global_step": 572512, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9945803880691528, "global_step": 572513, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.015104293823242, "global_step": 572514, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0801663398742676, "global_step": 572515, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1104984283447266, "global_step": 572516, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0214812755584717, "global_step": 572517, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.995546579360962, "global_step": 572518, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.017683744430542, "global_step": 572519, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0119268894195557, "global_step": 572520, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.012963056564331, "global_step": 572521, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9873032569885254, "global_step": 572522, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0308260917663574, "global_step": 572523, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.000894784927368, "global_step": 572524, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.003174066543579, "global_step": 572525, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9972957372665405, "global_step": 572526, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0545246601104736, "global_step": 572527, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.010577440261841, "global_step": 572528, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.021373748779297, "global_step": 572529, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.095818281173706, "global_step": 572530, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0017406940460205, "global_step": 572531, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.973466396331787, "global_step": 572532, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0796594619750977, "global_step": 572533, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.009422540664673, "global_step": 572534, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.032524347305298, "global_step": 572535, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0693318843841553, "global_step": 572536, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9761677980422974, "global_step": 572537, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9727445840835571, "global_step": 572538, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.012333869934082, "global_step": 572539, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9312392473220825, "global_step": 572540, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0959901809692383, "global_step": 572541, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.062739610671997, "global_step": 572542, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.078450918197632, "global_step": 572543, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.98642098903656, "global_step": 572544, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1290030479431152, "global_step": 572545, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0419323444366455, "global_step": 572546, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.146103620529175, "global_step": 572547, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.048532485961914, "global_step": 572548, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9753774404525757, "global_step": 572549, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9743996858596802, "global_step": 572550, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0032167434692383, "global_step": 572551, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.058385133743286, "global_step": 572552, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.023607015609741, "global_step": 572553, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9836015701293945, "global_step": 572554, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0713629722595215, "global_step": 572555, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.041414260864258, "global_step": 572556, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0102999210357666, "global_step": 572557, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0055177211761475, "global_step": 572558, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.046241283416748, "global_step": 572559, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.031923294067383, "global_step": 572560, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.987741470336914, "global_step": 572561, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9784553050994873, "global_step": 572562, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0310609340667725, "global_step": 572563, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.053112268447876, "global_step": 572564, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.153862476348877, "global_step": 572565, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0245392322540283, "global_step": 572566, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.032864809036255, "global_step": 572567, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0732905864715576, "global_step": 572568, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0023415088653564, "global_step": 572569, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9899719953536987, "global_step": 572570, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0892527103424072, "global_step": 572571, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.059135913848877, "global_step": 572572, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9405083656311035, "global_step": 572573, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0607008934020996, "global_step": 572574, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.030043840408325, "global_step": 572575, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0456316471099854, "global_step": 572576, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0225486755371094, "global_step": 572577, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.124952554702759, "global_step": 572578, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9959274530410767, "global_step": 572579, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9850494861602783, "global_step": 572580, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9749430418014526, "global_step": 572581, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0111238956451416, "global_step": 572582, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.029498815536499, "global_step": 572583, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0881385803222656, "global_step": 572584, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0304148197174072, "global_step": 572585, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.023254871368408, "global_step": 572586, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0898256301879883, "global_step": 572587, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.974956750869751, "global_step": 572588, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9739773273468018, "global_step": 572589, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9776161909103394, "global_step": 572590, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.045837163925171, "global_step": 572591, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9603955745697021, "global_step": 572592, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.036085605621338, "global_step": 572593, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.066967725753784, "global_step": 572594, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0086519718170166, "global_step": 572595, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0164384841918945, "global_step": 572596, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.084514856338501, "global_step": 572597, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1177797317504883, "global_step": 572598, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.074147939682007, "global_step": 572599, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0657784938812256, "global_step": 572600, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9484772682189941, "global_step": 572601, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9141883850097656, "global_step": 572602, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.995794415473938, "global_step": 572603, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1180503368377686, "global_step": 572604, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0757625102996826, "global_step": 572605, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.056636333465576, "global_step": 572606, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.057107448577881, "global_step": 572607, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0437746047973633, "global_step": 572608, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0276193618774414, "global_step": 572609, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.020674467086792, "global_step": 572610, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9837170839309692, "global_step": 572611, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1137397289276123, "global_step": 572612, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0258724689483643, "global_step": 572613, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9327176809310913, "global_step": 572614, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.997562289237976, "global_step": 572615, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.002979278564453, "global_step": 572616, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0025837421417236, "global_step": 572617, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0297305583953857, "global_step": 572618, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0455563068389893, "global_step": 572619, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9675456285476685, "global_step": 572620, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9388166666030884, "global_step": 572621, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9463554620742798, "global_step": 572622, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9566717147827148, "global_step": 572623, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1345386505126953, "global_step": 572624, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0055601596832275, "global_step": 572625, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9733368158340454, "global_step": 572626, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0385818481445312, "global_step": 572627, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9762178659439087, "global_step": 572628, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.059896469116211, "global_step": 572629, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9747955799102783, "global_step": 572630, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.011263370513916, "global_step": 572631, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.082608222961426, "global_step": 572632, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.111295700073242, "global_step": 572633, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.094834327697754, "global_step": 572634, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.046647310256958, "global_step": 572635, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9679594039916992, "global_step": 572636, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9740617275238037, "global_step": 572637, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.054511070251465, "global_step": 572638, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1004135608673096, "global_step": 572639, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.930916666984558, "global_step": 572640, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9603023529052734, "global_step": 572641, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.086606502532959, "global_step": 572642, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0354883670806885, "global_step": 572643, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0697734355926514, "global_step": 572644, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.008533239364624, "global_step": 572645, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.070160150527954, "global_step": 572646, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.949054479598999, "global_step": 572647, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.052473306655884, "global_step": 572648, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.022179365158081, "global_step": 572649, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.029773235321045, "global_step": 572650, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.03924298286438, "global_step": 572651, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0184738636016846, "global_step": 572652, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1144320964813232, "global_step": 572653, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0035719871520996, "global_step": 572654, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.032698631286621, "global_step": 572655, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0902292728424072, "global_step": 572656, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0790624618530273, "global_step": 572657, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0045394897460938, "global_step": 572658, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0231800079345703, "global_step": 572659, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9919683933258057, "global_step": 572660, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.027056932449341, "global_step": 572661, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9682910442352295, "global_step": 572662, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.135877847671509, "global_step": 572663, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.003596782684326, "global_step": 572664, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.036043882369995, "global_step": 572665, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0653743743896484, "global_step": 572666, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0171267986297607, "global_step": 572667, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9967130422592163, "global_step": 572668, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.10693621635437, "global_step": 572669, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0042457580566406, "global_step": 572670, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0260982513427734, "global_step": 572671, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9882354736328125, "global_step": 572672, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.09987473487854, "global_step": 572673, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0208821296691895, "global_step": 572674, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.026418685913086, "global_step": 572675, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0058929920196533, "global_step": 572676, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0224761962890625, "global_step": 572677, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0145163536071777, "global_step": 572678, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0400326251983643, "global_step": 572679, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.071028709411621, "global_step": 572680, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.064472198486328, "global_step": 572681, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0751869678497314, "global_step": 572682, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.090517997741699, "global_step": 572683, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0004589557647705, "global_step": 572684, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0638482570648193, "global_step": 572685, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.143610954284668, "global_step": 572686, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.071565628051758, "global_step": 572687, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.026123046875, "global_step": 572688, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0327043533325195, "global_step": 572689, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0905773639678955, "global_step": 572690, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0683765411376953, "global_step": 572691, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0444753170013428, "global_step": 572692, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.035526990890503, "global_step": 572693, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.035093069076538, "global_step": 572694, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0440025329589844, "global_step": 572695, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0095717906951904, "global_step": 572696, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.980562686920166, "global_step": 572697, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0142388343811035, "global_step": 572698, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9322835206985474, "global_step": 572699, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9928505420684814, "global_step": 572700, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.995951771736145, "global_step": 572701, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0051674842834473, "global_step": 572702, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0347654819488525, "global_step": 572703, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0841195583343506, "global_step": 572704, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.086848020553589, "global_step": 572705, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0452802181243896, "global_step": 572706, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0522897243499756, "global_step": 572707, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0051302909851074, "global_step": 572708, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.101038932800293, "global_step": 572709, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0099754333496094, "global_step": 572710, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.063037633895874, "global_step": 572711, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9972118139266968, "global_step": 572712, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0257742404937744, "global_step": 572713, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0668632984161377, "global_step": 572714, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9194562435150146, "global_step": 572715, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9663994312286377, "global_step": 572716, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9946300983428955, "global_step": 572717, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9846100807189941, "global_step": 572718, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.008932113647461, "global_step": 572719, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0244979858398438, "global_step": 572720, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.059983968734741, "global_step": 572721, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.00917649269104, "global_step": 572722, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0189645290374756, "global_step": 572723, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.069728374481201, "global_step": 572724, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0399842262268066, "global_step": 572725, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9464620351791382, "global_step": 572726, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.971053123474121, "global_step": 572727, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.003634214401245, "global_step": 572728, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9794678688049316, "global_step": 572729, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9484999179840088, "global_step": 572730, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9547441005706787, "global_step": 572731, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9962199926376343, "global_step": 572732, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9581129550933838, "global_step": 572733, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.976781964302063, "global_step": 572734, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0970215797424316, "global_step": 572735, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.039269208908081, "global_step": 572736, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0635032653808594, "global_step": 572737, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0202338695526123, "global_step": 572738, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.046097755432129, "global_step": 572739, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.00056529045105, "global_step": 572740, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.120954990386963, "global_step": 572741, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0147879123687744, "global_step": 572742, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.081996440887451, "global_step": 572743, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0267326831817627, "global_step": 572744, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.046011209487915, "global_step": 572745, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0407838821411133, "global_step": 572746, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1008048057556152, "global_step": 572747, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.073237419128418, "global_step": 572748, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.123483180999756, "global_step": 572749, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0738415718078613, "global_step": 572750, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0509064197540283, "global_step": 572751, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.055516242980957, "global_step": 572752, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1093509197235107, "global_step": 572753, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0483672618865967, "global_step": 572754, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0087640285491943, "global_step": 572755, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1218488216400146, "global_step": 572756, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.953426718711853, "global_step": 572757, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.047273874282837, "global_step": 572758, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0258519649505615, "global_step": 572759, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0419609546661377, "global_step": 572760, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.062264919281006, "global_step": 572761, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9721800088882446, "global_step": 572762, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0244250297546387, "global_step": 572763, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0583548545837402, "global_step": 572764, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.000351667404175, "global_step": 572765, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0255508422851562, "global_step": 572766, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.114193916320801, "global_step": 572767, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.124382734298706, "global_step": 572768, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.07757568359375, "global_step": 572769, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0541608333587646, "global_step": 572770, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.060112953186035, "global_step": 572771, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0255956649780273, "global_step": 572772, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9454925060272217, "global_step": 572773, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0528199672698975, "global_step": 572774, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0986452102661133, "global_step": 572775, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.052572250366211, "global_step": 572776, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0200581550598145, "global_step": 572777, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0978493690490723, "global_step": 572778, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9962674379348755, "global_step": 572779, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0259366035461426, "global_step": 572780, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9690858125686646, "global_step": 572781, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0014050006866455, "global_step": 572782, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.031928777694702, "global_step": 572783, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.03139591217041, "global_step": 572784, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0017571449279785, "global_step": 572785, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.042043924331665, "global_step": 572786, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9295644760131836, "global_step": 572787, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.1096339225769043, "global_step": 572788, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0558598041534424, "global_step": 572789, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9600536823272705, "global_step": 572790, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0375216007232666, "global_step": 572791, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.021477460861206, "global_step": 572792, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.940950870513916, "global_step": 572793, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0638134479522705, "global_step": 572794, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0039191246032715, "global_step": 572795, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0100648403167725, "global_step": 572796, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.021153211593628, "global_step": 572797, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0628774166107178, "global_step": 572798, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0162832736968994, "global_step": 572799, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.04398250579834, "global_step": 572800, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.015110969543457, "global_step": 572801, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0368692874908447, "global_step": 572802, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.993619680404663, "global_step": 572803, "epoch": 940, "lr": 5e-05}
{"train_loss": 1.9824613332748413, "global_step": 572804, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0101006031036377, "global_step": 572805, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0966947078704834, "global_step": 572806, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.050856351852417, "global_step": 572807, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0732107162475586, "global_step": 572808, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.023089647293091, "global_step": 572809, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0054385662078857, "global_step": 572810, "epoch": 940, "lr": 5e-05}
{"train_loss": 2.0241177082061768, "global_step": 572811, "epoch": 940, "lr": 5e-05, "val_loss": 5.777681350708008, "test_reconst_mse": 0.0734332799911499}
{"train_loss": 1.9669427871704102, "global_step": 572812, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9971413612365723, "global_step": 572813, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9924242496490479, "global_step": 572814, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9801230430603027, "global_step": 572815, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0841524600982666, "global_step": 572816, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9833173751831055, "global_step": 572817, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9171916246414185, "global_step": 572818, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0082454681396484, "global_step": 572819, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.937827706336975, "global_step": 572820, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9208447933197021, "global_step": 572821, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.021904468536377, "global_step": 572822, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9537036418914795, "global_step": 572823, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9919244050979614, "global_step": 572824, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9843995571136475, "global_step": 572825, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9925159215927124, "global_step": 572826, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.022083282470703, "global_step": 572827, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9705495834350586, "global_step": 572828, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0651044845581055, "global_step": 572829, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9533734321594238, "global_step": 572830, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9903262853622437, "global_step": 572831, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0639729499816895, "global_step": 572832, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0783021450042725, "global_step": 572833, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.035411834716797, "global_step": 572834, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.095970392227173, "global_step": 572835, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.041515827178955, "global_step": 572836, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0287740230560303, "global_step": 572837, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.113767623901367, "global_step": 572838, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.008544921875, "global_step": 572839, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9488779306411743, "global_step": 572840, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0857343673706055, "global_step": 572841, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0875682830810547, "global_step": 572842, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9552860260009766, "global_step": 572843, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.058675527572632, "global_step": 572844, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9715168476104736, "global_step": 572845, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.002601146697998, "global_step": 572846, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.000782012939453, "global_step": 572847, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9685890674591064, "global_step": 572848, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9229731559753418, "global_step": 572849, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9530020952224731, "global_step": 572850, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0100932121276855, "global_step": 572851, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9787176847457886, "global_step": 572852, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9705709218978882, "global_step": 572853, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1344504356384277, "global_step": 572854, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9527732133865356, "global_step": 572855, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.037717342376709, "global_step": 572856, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9863543510437012, "global_step": 572857, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.092128038406372, "global_step": 572858, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.000441312789917, "global_step": 572859, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0066945552825928, "global_step": 572860, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0704379081726074, "global_step": 572861, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9011818170547485, "global_step": 572862, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.92157781124115, "global_step": 572863, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.088979482650757, "global_step": 572864, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.035005807876587, "global_step": 572865, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9793362617492676, "global_step": 572866, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.8703410625457764, "global_step": 572867, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.003586769104004, "global_step": 572868, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9934581518173218, "global_step": 572869, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0042004585266113, "global_step": 572870, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.000976085662842, "global_step": 572871, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0846333503723145, "global_step": 572872, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.020148515701294, "global_step": 572873, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9778555631637573, "global_step": 572874, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9568994045257568, "global_step": 572875, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.037963628768921, "global_step": 572876, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9897454977035522, "global_step": 572877, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9844379425048828, "global_step": 572878, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9295756816864014, "global_step": 572879, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9501937627792358, "global_step": 572880, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.051347494125366, "global_step": 572881, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0646812915802, "global_step": 572882, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0200586318969727, "global_step": 572883, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1024134159088135, "global_step": 572884, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.014101982116699, "global_step": 572885, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.005782127380371, "global_step": 572886, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.068966865539551, "global_step": 572887, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1000659465789795, "global_step": 572888, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0046403408050537, "global_step": 572889, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.002124309539795, "global_step": 572890, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.8775230646133423, "global_step": 572891, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0545389652252197, "global_step": 572892, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.050370216369629, "global_step": 572893, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0263359546661377, "global_step": 572894, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0044422149658203, "global_step": 572895, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9425885677337646, "global_step": 572896, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9550617933273315, "global_step": 572897, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9703820943832397, "global_step": 572898, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.034062623977661, "global_step": 572899, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9334437847137451, "global_step": 572900, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0222179889678955, "global_step": 572901, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0589113235473633, "global_step": 572902, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0929603576660156, "global_step": 572903, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9733844995498657, "global_step": 572904, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9611517190933228, "global_step": 572905, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0135035514831543, "global_step": 572906, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0269227027893066, "global_step": 572907, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0402233600616455, "global_step": 572908, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0617661476135254, "global_step": 572909, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0726020336151123, "global_step": 572910, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.03166127204895, "global_step": 572911, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.063218116760254, "global_step": 572912, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9654597043991089, "global_step": 572913, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0018200874328613, "global_step": 572914, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0262789726257324, "global_step": 572915, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.080613613128662, "global_step": 572916, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.89263916015625, "global_step": 572917, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.033931255340576, "global_step": 572918, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0096609592437744, "global_step": 572919, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9888352155685425, "global_step": 572920, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9155267477035522, "global_step": 572921, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.043121576309204, "global_step": 572922, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0255286693573, "global_step": 572923, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0392723083496094, "global_step": 572924, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9819039106369019, "global_step": 572925, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9728072881698608, "global_step": 572926, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9927482604980469, "global_step": 572927, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.109605312347412, "global_step": 572928, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.083549976348877, "global_step": 572929, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9788082838058472, "global_step": 572930, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.075648546218872, "global_step": 572931, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9891321659088135, "global_step": 572932, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0090410709381104, "global_step": 572933, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0444188117980957, "global_step": 572934, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.003345251083374, "global_step": 572935, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.024135112762451, "global_step": 572936, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9767669439315796, "global_step": 572937, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.071065902709961, "global_step": 572938, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9847464561462402, "global_step": 572939, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0782647132873535, "global_step": 572940, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.053908109664917, "global_step": 572941, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.016387462615967, "global_step": 572942, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0125815868377686, "global_step": 572943, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9804985523223877, "global_step": 572944, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0148143768310547, "global_step": 572945, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.024427652359009, "global_step": 572946, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.019118070602417, "global_step": 572947, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0103700160980225, "global_step": 572948, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9913556575775146, "global_step": 572949, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.077958822250366, "global_step": 572950, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.006728172302246, "global_step": 572951, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0412707328796387, "global_step": 572952, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9700714349746704, "global_step": 572953, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9845246076583862, "global_step": 572954, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.955731987953186, "global_step": 572955, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0232901573181152, "global_step": 572956, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9388830661773682, "global_step": 572957, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0797033309936523, "global_step": 572958, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0889370441436768, "global_step": 572959, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9289226531982422, "global_step": 572960, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9736602306365967, "global_step": 572961, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0218656063079834, "global_step": 572962, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.004754066467285, "global_step": 572963, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0887598991394043, "global_step": 572964, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0823099613189697, "global_step": 572965, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0441596508026123, "global_step": 572966, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.026430606842041, "global_step": 572967, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9310222864151, "global_step": 572968, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9811161756515503, "global_step": 572969, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.95850670337677, "global_step": 572970, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9591917991638184, "global_step": 572971, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0327322483062744, "global_step": 572972, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1280324459075928, "global_step": 572973, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9992315769195557, "global_step": 572974, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0124106407165527, "global_step": 572975, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.002502679824829, "global_step": 572976, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.004741668701172, "global_step": 572977, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0626046657562256, "global_step": 572978, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9964544773101807, "global_step": 572979, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0720674991607666, "global_step": 572980, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.012746810913086, "global_step": 572981, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9691669940948486, "global_step": 572982, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0963451862335205, "global_step": 572983, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.015852451324463, "global_step": 572984, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.154130220413208, "global_step": 572985, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0208492279052734, "global_step": 572986, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9867234230041504, "global_step": 572987, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.096907138824463, "global_step": 572988, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0294289588928223, "global_step": 572989, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9884213209152222, "global_step": 572990, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.075498580932617, "global_step": 572991, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9097121953964233, "global_step": 572992, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.976681113243103, "global_step": 572993, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0067780017852783, "global_step": 572994, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9895225763320923, "global_step": 572995, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.103116035461426, "global_step": 572996, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9881987571716309, "global_step": 572997, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0398881435394287, "global_step": 572998, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0283467769622803, "global_step": 572999, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.002509117126465, "global_step": 573000, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0797057151794434, "global_step": 573001, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0170023441314697, "global_step": 573002, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9859627485275269, "global_step": 573003, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.000298023223877, "global_step": 573004, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9962241649627686, "global_step": 573005, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0596580505371094, "global_step": 573006, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.02278995513916, "global_step": 573007, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9417924880981445, "global_step": 573008, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.969314455986023, "global_step": 573009, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0804216861724854, "global_step": 573010, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.983513593673706, "global_step": 573011, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.098895788192749, "global_step": 573012, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9666203260421753, "global_step": 573013, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0317089557647705, "global_step": 573014, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0419259071350098, "global_step": 573015, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9750477075576782, "global_step": 573016, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0034096240997314, "global_step": 573017, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.073258399963379, "global_step": 573018, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0159502029418945, "global_step": 573019, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0234251022338867, "global_step": 573020, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9586745500564575, "global_step": 573021, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0836198329925537, "global_step": 573022, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.982253909111023, "global_step": 573023, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.02578067779541, "global_step": 573024, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.004282236099243, "global_step": 573025, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0520918369293213, "global_step": 573026, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0899384021759033, "global_step": 573027, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1124348640441895, "global_step": 573028, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0084400177001953, "global_step": 573029, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0474536418914795, "global_step": 573030, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9564056396484375, "global_step": 573031, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.036912441253662, "global_step": 573032, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0563242435455322, "global_step": 573033, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.996687889099121, "global_step": 573034, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.12166166305542, "global_step": 573035, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9881742000579834, "global_step": 573036, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.014166831970215, "global_step": 573037, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.098306655883789, "global_step": 573038, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.006309747695923, "global_step": 573039, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.011744260787964, "global_step": 573040, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.006593942642212, "global_step": 573041, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0256361961364746, "global_step": 573042, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.987747073173523, "global_step": 573043, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9725489616394043, "global_step": 573044, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0130796432495117, "global_step": 573045, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0648367404937744, "global_step": 573046, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9844261407852173, "global_step": 573047, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.013720989227295, "global_step": 573048, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.983897089958191, "global_step": 573049, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0266857147216797, "global_step": 573050, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9821197986602783, "global_step": 573051, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.116281747817993, "global_step": 573052, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0951762199401855, "global_step": 573053, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9972738027572632, "global_step": 573054, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9908527135849, "global_step": 573055, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.038364887237549, "global_step": 573056, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9794872999191284, "global_step": 573057, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0139920711517334, "global_step": 573058, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9922621250152588, "global_step": 573059, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9972777366638184, "global_step": 573060, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0206942558288574, "global_step": 573061, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0664587020874023, "global_step": 573062, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0111725330352783, "global_step": 573063, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9508631229400635, "global_step": 573064, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0429344177246094, "global_step": 573065, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0402016639709473, "global_step": 573066, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0574629306793213, "global_step": 573067, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0497071743011475, "global_step": 573068, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9961724281311035, "global_step": 573069, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.8937872648239136, "global_step": 573070, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9988627433776855, "global_step": 573071, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.048898458480835, "global_step": 573072, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9792288541793823, "global_step": 573073, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0573153495788574, "global_step": 573074, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0283021926879883, "global_step": 573075, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.022024393081665, "global_step": 573076, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0739736557006836, "global_step": 573077, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1030380725860596, "global_step": 573078, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.050203800201416, "global_step": 573079, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9600584506988525, "global_step": 573080, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0657551288604736, "global_step": 573081, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0783944129943848, "global_step": 573082, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.024991035461426, "global_step": 573083, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0639631748199463, "global_step": 573084, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0658633708953857, "global_step": 573085, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9768211841583252, "global_step": 573086, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0438222885131836, "global_step": 573087, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.01652455329895, "global_step": 573088, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0864338874816895, "global_step": 573089, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.023862838745117, "global_step": 573090, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.031665563583374, "global_step": 573091, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.076916217803955, "global_step": 573092, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.072728157043457, "global_step": 573093, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0488507747650146, "global_step": 573094, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1000418663024902, "global_step": 573095, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9754250049591064, "global_step": 573096, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1678760051727295, "global_step": 573097, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9953094720840454, "global_step": 573098, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.13580584526062, "global_step": 573099, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.013261079788208, "global_step": 573100, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.994354248046875, "global_step": 573101, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.948762059211731, "global_step": 573102, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.025125503540039, "global_step": 573103, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9622180461883545, "global_step": 573104, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.05997633934021, "global_step": 573105, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.988000512123108, "global_step": 573106, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.966886281967163, "global_step": 573107, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9538474082946777, "global_step": 573108, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9935791492462158, "global_step": 573109, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9714072942733765, "global_step": 573110, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.074061155319214, "global_step": 573111, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0433435440063477, "global_step": 573112, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0369784832000732, "global_step": 573113, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.034287214279175, "global_step": 573114, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9977236986160278, "global_step": 573115, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9702849388122559, "global_step": 573116, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.090843439102173, "global_step": 573117, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9882676601409912, "global_step": 573118, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.13086199760437, "global_step": 573119, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.995741844177246, "global_step": 573120, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9770817756652832, "global_step": 573121, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9677239656448364, "global_step": 573122, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0704944133758545, "global_step": 573123, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9469510316848755, "global_step": 573124, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0396547317504883, "global_step": 573125, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.026836395263672, "global_step": 573126, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0128366947174072, "global_step": 573127, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.015432119369507, "global_step": 573128, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0084547996520996, "global_step": 573129, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9931975603103638, "global_step": 573130, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0297579765319824, "global_step": 573131, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9800465106964111, "global_step": 573132, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.055208683013916, "global_step": 573133, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.060328483581543, "global_step": 573134, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9734867811203003, "global_step": 573135, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0504207611083984, "global_step": 573136, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9184774160385132, "global_step": 573137, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.971885085105896, "global_step": 573138, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0162220001220703, "global_step": 573139, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.998828649520874, "global_step": 573140, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0253958702087402, "global_step": 573141, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.945285439491272, "global_step": 573142, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0264523029327393, "global_step": 573143, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.954239010810852, "global_step": 573144, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.024790048599243, "global_step": 573145, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0667340755462646, "global_step": 573146, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.054560422897339, "global_step": 573147, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9266263246536255, "global_step": 573148, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.086620807647705, "global_step": 573149, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.000638484954834, "global_step": 573150, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0343716144561768, "global_step": 573151, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0376906394958496, "global_step": 573152, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.067258358001709, "global_step": 573153, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.059929370880127, "global_step": 573154, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9577391147613525, "global_step": 573155, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9725065231323242, "global_step": 573156, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.096517324447632, "global_step": 573157, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.026249647140503, "global_step": 573158, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9926379919052124, "global_step": 573159, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.043959617614746, "global_step": 573160, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1443090438842773, "global_step": 573161, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9681193828582764, "global_step": 573162, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1040520668029785, "global_step": 573163, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9680086374282837, "global_step": 573164, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.988052248954773, "global_step": 573165, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.06805682182312, "global_step": 573166, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0353758335113525, "global_step": 573167, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.985735535621643, "global_step": 573168, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0733225345611572, "global_step": 573169, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.043182611465454, "global_step": 573170, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0619633197784424, "global_step": 573171, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9968819618225098, "global_step": 573172, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.063244104385376, "global_step": 573173, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.042642116546631, "global_step": 573174, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9953105449676514, "global_step": 573175, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0414822101593018, "global_step": 573176, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.116339683532715, "global_step": 573177, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.075248956680298, "global_step": 573178, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9207006692886353, "global_step": 573179, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0503852367401123, "global_step": 573180, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.133512496948242, "global_step": 573181, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0484619140625, "global_step": 573182, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9970325231552124, "global_step": 573183, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0316145420074463, "global_step": 573184, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9819567203521729, "global_step": 573185, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9028831720352173, "global_step": 573186, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9999735355377197, "global_step": 573187, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9896860122680664, "global_step": 573188, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0061378479003906, "global_step": 573189, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0113871097564697, "global_step": 573190, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9689825773239136, "global_step": 573191, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9992846250534058, "global_step": 573192, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0954596996307373, "global_step": 573193, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9958720207214355, "global_step": 573194, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.981005311012268, "global_step": 573195, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.040529727935791, "global_step": 573196, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9912165403366089, "global_step": 573197, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.012986660003662, "global_step": 573198, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0508604049682617, "global_step": 573199, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.027465343475342, "global_step": 573200, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9663797616958618, "global_step": 573201, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0354106426239014, "global_step": 573202, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9247673749923706, "global_step": 573203, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0507287979125977, "global_step": 573204, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.048529863357544, "global_step": 573205, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.04164719581604, "global_step": 573206, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1203367710113525, "global_step": 573207, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1042561531066895, "global_step": 573208, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.08769154548645, "global_step": 573209, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9832500219345093, "global_step": 573210, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9690905809402466, "global_step": 573211, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.064793586730957, "global_step": 573212, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0439157485961914, "global_step": 573213, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.162306070327759, "global_step": 573214, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0337252616882324, "global_step": 573215, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9956536293029785, "global_step": 573216, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.009361982345581, "global_step": 573217, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0314652919769287, "global_step": 573218, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9770554304122925, "global_step": 573219, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9463510513305664, "global_step": 573220, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.02980899810791, "global_step": 573221, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9358794689178467, "global_step": 573222, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0755138397216797, "global_step": 573223, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9588080644607544, "global_step": 573224, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.080108165740967, "global_step": 573225, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0520317554473877, "global_step": 573226, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.039860486984253, "global_step": 573227, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0346195697784424, "global_step": 573228, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9267178773880005, "global_step": 573229, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0199875831604004, "global_step": 573230, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.089859962463379, "global_step": 573231, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9927047491073608, "global_step": 573232, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0045666694641113, "global_step": 573233, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0121068954467773, "global_step": 573234, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.959814190864563, "global_step": 573235, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9721157550811768, "global_step": 573236, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0230295658111572, "global_step": 573237, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0111985206604004, "global_step": 573238, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.084667205810547, "global_step": 573239, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0431032180786133, "global_step": 573240, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0281286239624023, "global_step": 573241, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0129826068878174, "global_step": 573242, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9819353818893433, "global_step": 573243, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9757084846496582, "global_step": 573244, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9803211688995361, "global_step": 573245, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9782414436340332, "global_step": 573246, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.084639310836792, "global_step": 573247, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.997573733329773, "global_step": 573248, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.8891308307647705, "global_step": 573249, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.048517942428589, "global_step": 573250, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9647034406661987, "global_step": 573251, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.015287160873413, "global_step": 573252, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.046341896057129, "global_step": 573253, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0305182933807373, "global_step": 573254, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.006453037261963, "global_step": 573255, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.966331958770752, "global_step": 573256, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0566844940185547, "global_step": 573257, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.974324107170105, "global_step": 573258, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9946867227554321, "global_step": 573259, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.015763282775879, "global_step": 573260, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.037323236465454, "global_step": 573261, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.028073310852051, "global_step": 573262, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9736875295639038, "global_step": 573263, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9788668155670166, "global_step": 573264, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.058927059173584, "global_step": 573265, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9339977502822876, "global_step": 573266, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0469913482666016, "global_step": 573267, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0056660175323486, "global_step": 573268, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.077988624572754, "global_step": 573269, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0053486824035645, "global_step": 573270, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.022191286087036, "global_step": 573271, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.002995491027832, "global_step": 573272, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9266862869262695, "global_step": 573273, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0115725994110107, "global_step": 573274, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.047165632247925, "global_step": 573275, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0466387271881104, "global_step": 573276, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9711978435516357, "global_step": 573277, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9667906761169434, "global_step": 573278, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.016939401626587, "global_step": 573279, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.013420343399048, "global_step": 573280, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0382087230682373, "global_step": 573281, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.03806209564209, "global_step": 573282, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.077603340148926, "global_step": 573283, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0555379390716553, "global_step": 573284, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9690498113632202, "global_step": 573285, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1298069953918457, "global_step": 573286, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9753166437149048, "global_step": 573287, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.959871530532837, "global_step": 573288, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0176773071289062, "global_step": 573289, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0085396766662598, "global_step": 573290, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9975643157958984, "global_step": 573291, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.056248426437378, "global_step": 573292, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0504977703094482, "global_step": 573293, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.013213634490967, "global_step": 573294, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9560120105743408, "global_step": 573295, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.939207911491394, "global_step": 573296, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0794174671173096, "global_step": 573297, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.107320785522461, "global_step": 573298, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.031524658203125, "global_step": 573299, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0752105712890625, "global_step": 573300, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0177884101867676, "global_step": 573301, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.085259437561035, "global_step": 573302, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9646390676498413, "global_step": 573303, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9701939821243286, "global_step": 573304, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0278406143188477, "global_step": 573305, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9348351955413818, "global_step": 573306, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9990108013153076, "global_step": 573307, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0027060508728027, "global_step": 573308, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0571675300598145, "global_step": 573309, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.020256757736206, "global_step": 573310, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0075693130493164, "global_step": 573311, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.036280870437622, "global_step": 573312, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.005192756652832, "global_step": 573313, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.01186203956604, "global_step": 573314, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9984270334243774, "global_step": 573315, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9864299297332764, "global_step": 573316, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.003476619720459, "global_step": 573317, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9924299716949463, "global_step": 573318, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0654778480529785, "global_step": 573319, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0437986850738525, "global_step": 573320, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9982521533966064, "global_step": 573321, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0250468254089355, "global_step": 573322, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0353856086730957, "global_step": 573323, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.019444227218628, "global_step": 573324, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.988208532333374, "global_step": 573325, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0127763748168945, "global_step": 573326, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.122713565826416, "global_step": 573327, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.961025357246399, "global_step": 573328, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0901970863342285, "global_step": 573329, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.002138376235962, "global_step": 573330, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0504379272460938, "global_step": 573331, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9893617630004883, "global_step": 573332, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0543622970581055, "global_step": 573333, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0462090969085693, "global_step": 573334, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.016756534576416, "global_step": 573335, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0080554485321045, "global_step": 573336, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9686661958694458, "global_step": 573337, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1042261123657227, "global_step": 573338, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0251076221466064, "global_step": 573339, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.03977108001709, "global_step": 573340, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.011956214904785, "global_step": 573341, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.068460464477539, "global_step": 573342, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.046613931655884, "global_step": 573343, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.031114101409912, "global_step": 573344, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1120874881744385, "global_step": 573345, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0477383136749268, "global_step": 573346, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0190269947052, "global_step": 573347, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.058030366897583, "global_step": 573348, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.107221841812134, "global_step": 573349, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9909621477127075, "global_step": 573350, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0304245948791504, "global_step": 573351, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0299603939056396, "global_step": 573352, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.000401020050049, "global_step": 573353, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9966444969177246, "global_step": 573354, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1095521450042725, "global_step": 573355, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.025675058364868, "global_step": 573356, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9883458614349365, "global_step": 573357, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0801541805267334, "global_step": 573358, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0704505443573, "global_step": 573359, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9697389602661133, "global_step": 573360, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9696259498596191, "global_step": 573361, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9673972129821777, "global_step": 573362, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9527019262313843, "global_step": 573363, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.023225784301758, "global_step": 573364, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1122989654541016, "global_step": 573365, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.95343816280365, "global_step": 573366, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0987627506256104, "global_step": 573367, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0594120025634766, "global_step": 573368, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9621295928955078, "global_step": 573369, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.078660011291504, "global_step": 573370, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.988124966621399, "global_step": 573371, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9855111837387085, "global_step": 573372, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0497994422912598, "global_step": 573373, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0731277465820312, "global_step": 573374, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9525810480117798, "global_step": 573375, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0520522594451904, "global_step": 573376, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.053713798522949, "global_step": 573377, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.036738634109497, "global_step": 573378, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0276527404785156, "global_step": 573379, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9786149263381958, "global_step": 573380, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.049128532409668, "global_step": 573381, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0648365020751953, "global_step": 573382, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.063166856765747, "global_step": 573383, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.038252830505371, "global_step": 573384, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.001594305038452, "global_step": 573385, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9764759540557861, "global_step": 573386, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0592501163482666, "global_step": 573387, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.015404224395752, "global_step": 573388, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9692554473876953, "global_step": 573389, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.014450788497925, "global_step": 573390, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0115678310394287, "global_step": 573391, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0434184074401855, "global_step": 573392, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9948172569274902, "global_step": 573393, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.985313892364502, "global_step": 573394, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9712806940078735, "global_step": 573395, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.002444267272949, "global_step": 573396, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1474485397338867, "global_step": 573397, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.093731164932251, "global_step": 573398, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9898829460144043, "global_step": 573399, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.12906551361084, "global_step": 573400, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.012087821960449, "global_step": 573401, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.946766972541809, "global_step": 573402, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1229162216186523, "global_step": 573403, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9566487073898315, "global_step": 573404, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.147413730621338, "global_step": 573405, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.104604721069336, "global_step": 573406, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.942724585533142, "global_step": 573407, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9859771728515625, "global_step": 573408, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0694587230682373, "global_step": 573409, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0280673503875732, "global_step": 573410, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0725982189178467, "global_step": 573411, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9853814840316772, "global_step": 573412, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.122323513031006, "global_step": 573413, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9714664220809937, "global_step": 573414, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.037604331970215, "global_step": 573415, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.952288031578064, "global_step": 573416, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9812887907028198, "global_step": 573417, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1017279624938965, "global_step": 573418, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0208382606506348, "global_step": 573419, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.090226650238037, "global_step": 573420, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0932276248931885, "global_step": 573421, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9822039604187012, "global_step": 573422, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9777346849441528, "global_step": 573423, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0168135166168213, "global_step": 573424, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9829710721969604, "global_step": 573425, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9893786907196045, "global_step": 573426, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.09390926361084, "global_step": 573427, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0244357585906982, "global_step": 573428, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0037341117858887, "global_step": 573429, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.054600477218628, "global_step": 573430, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0015125274658203, "global_step": 573431, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9558889865875244, "global_step": 573432, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.983839750289917, "global_step": 573433, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0556113719940186, "global_step": 573434, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.052271604537964, "global_step": 573435, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.966604232788086, "global_step": 573436, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0156960487365723, "global_step": 573437, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0011157989501953, "global_step": 573438, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0335159301757812, "global_step": 573439, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.033071994781494, "global_step": 573440, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0547962188720703, "global_step": 573441, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9978100061416626, "global_step": 573442, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.087218999862671, "global_step": 573443, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0294899940490723, "global_step": 573444, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9794347286224365, "global_step": 573445, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0533649921417236, "global_step": 573446, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0158238410949707, "global_step": 573447, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0902626514434814, "global_step": 573448, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.01839542388916, "global_step": 573449, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.965022325515747, "global_step": 573450, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9922831058502197, "global_step": 573451, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.022437810897827, "global_step": 573452, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.001786708831787, "global_step": 573453, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9559080600738525, "global_step": 573454, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9880403280258179, "global_step": 573455, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.046283483505249, "global_step": 573456, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.004345178604126, "global_step": 573457, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0281028747558594, "global_step": 573458, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0351831912994385, "global_step": 573459, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0200355052948, "global_step": 573460, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9769153594970703, "global_step": 573461, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1087427139282227, "global_step": 573462, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.007904529571533, "global_step": 573463, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.054009437561035, "global_step": 573464, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0298423767089844, "global_step": 573465, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.033055543899536, "global_step": 573466, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0452451705932617, "global_step": 573467, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1097755432128906, "global_step": 573468, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0523524284362793, "global_step": 573469, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.058539867401123, "global_step": 573470, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0009543895721436, "global_step": 573471, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0209105014801025, "global_step": 573472, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.075012445449829, "global_step": 573473, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9769656658172607, "global_step": 573474, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0294551849365234, "global_step": 573475, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0771028995513916, "global_step": 573476, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9682835340499878, "global_step": 573477, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0291223526000977, "global_step": 573478, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9838541746139526, "global_step": 573479, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.111406087875366, "global_step": 573480, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.062800168991089, "global_step": 573481, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0453603267669678, "global_step": 573482, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.019697666168213, "global_step": 573483, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0677411556243896, "global_step": 573484, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0133297443389893, "global_step": 573485, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.102257251739502, "global_step": 573486, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.023198127746582, "global_step": 573487, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.02750563621521, "global_step": 573488, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.09591007232666, "global_step": 573489, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9294331073760986, "global_step": 573490, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.022448778152466, "global_step": 573491, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.074819803237915, "global_step": 573492, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0356662273406982, "global_step": 573493, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9898208379745483, "global_step": 573494, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.965067744255066, "global_step": 573495, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.066601514816284, "global_step": 573496, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9898205995559692, "global_step": 573497, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0576066970825195, "global_step": 573498, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9041221141815186, "global_step": 573499, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0750319957733154, "global_step": 573500, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9763388633728027, "global_step": 573501, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.100098133087158, "global_step": 573502, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.13680362701416, "global_step": 573503, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.02551007270813, "global_step": 573504, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9676085710525513, "global_step": 573505, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0748534202575684, "global_step": 573506, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.016221046447754, "global_step": 573507, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.080791473388672, "global_step": 573508, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0693790912628174, "global_step": 573509, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0305161476135254, "global_step": 573510, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9611077308654785, "global_step": 573511, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.022658348083496, "global_step": 573512, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0206902027130127, "global_step": 573513, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0677871704101562, "global_step": 573514, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9913992881774902, "global_step": 573515, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9633822441101074, "global_step": 573516, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.068387746810913, "global_step": 573517, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0500714778900146, "global_step": 573518, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0121779441833496, "global_step": 573519, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.046724796295166, "global_step": 573520, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.08296799659729, "global_step": 573521, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0549569129943848, "global_step": 573522, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0941309928894043, "global_step": 573523, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.025913953781128, "global_step": 573524, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0003790855407715, "global_step": 573525, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.023052930831909, "global_step": 573526, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9911284446716309, "global_step": 573527, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0062742233276367, "global_step": 573528, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.028517007827759, "global_step": 573529, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.037932872772217, "global_step": 573530, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.055386781692505, "global_step": 573531, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0567965507507324, "global_step": 573532, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.062563896179199, "global_step": 573533, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.064375400543213, "global_step": 573534, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0369656085968018, "global_step": 573535, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.95963716506958, "global_step": 573536, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0373833179473877, "global_step": 573537, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.064988613128662, "global_step": 573538, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0851666927337646, "global_step": 573539, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.084000587463379, "global_step": 573540, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1389880180358887, "global_step": 573541, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.065706968307495, "global_step": 573542, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9580621719360352, "global_step": 573543, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0302679538726807, "global_step": 573544, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.8982365131378174, "global_step": 573545, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.048546075820923, "global_step": 573546, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0486152172088623, "global_step": 573547, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0021705627441406, "global_step": 573548, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.151273488998413, "global_step": 573549, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0869736671447754, "global_step": 573550, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.056852340698242, "global_step": 573551, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.957804799079895, "global_step": 573552, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9440172910690308, "global_step": 573553, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0806801319122314, "global_step": 573554, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0521388053894043, "global_step": 573555, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9767576456069946, "global_step": 573556, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0666768550872803, "global_step": 573557, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.10249400138855, "global_step": 573558, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0668249130249023, "global_step": 573559, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0128729343414307, "global_step": 573560, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0324041843414307, "global_step": 573561, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9930273294448853, "global_step": 573562, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.018939256668091, "global_step": 573563, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.02618145942688, "global_step": 573564, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.069722890853882, "global_step": 573565, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.042163848876953, "global_step": 573566, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9944911003112793, "global_step": 573567, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9897048473358154, "global_step": 573568, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1276581287384033, "global_step": 573569, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.049717664718628, "global_step": 573570, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.037631034851074, "global_step": 573571, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0766870975494385, "global_step": 573572, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0269510746002197, "global_step": 573573, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9881844520568848, "global_step": 573574, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.158454418182373, "global_step": 573575, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9688035249710083, "global_step": 573576, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.002027750015259, "global_step": 573577, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1477603912353516, "global_step": 573578, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0124807357788086, "global_step": 573579, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.009432077407837, "global_step": 573580, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9491758346557617, "global_step": 573581, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0555949211120605, "global_step": 573582, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9466489553451538, "global_step": 573583, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0585126876831055, "global_step": 573584, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.011787176132202, "global_step": 573585, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1012187004089355, "global_step": 573586, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.012892961502075, "global_step": 573587, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9780669212341309, "global_step": 573588, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.006136417388916, "global_step": 573589, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0288169384002686, "global_step": 573590, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.077634572982788, "global_step": 573591, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0100369453430176, "global_step": 573592, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.026401996612549, "global_step": 573593, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0606706142425537, "global_step": 573594, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0293076038360596, "global_step": 573595, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0053911209106445, "global_step": 573596, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.076335906982422, "global_step": 573597, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9523656368255615, "global_step": 573598, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9225728511810303, "global_step": 573599, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.019514560699463, "global_step": 573600, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1077511310577393, "global_step": 573601, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0011346340179443, "global_step": 573602, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0137369632720947, "global_step": 573603, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0670597553253174, "global_step": 573604, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.080474376678467, "global_step": 573605, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0564465522766113, "global_step": 573606, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.010314702987671, "global_step": 573607, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9937549829483032, "global_step": 573608, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9354496002197266, "global_step": 573609, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0488758087158203, "global_step": 573610, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0185608863830566, "global_step": 573611, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0964367389678955, "global_step": 573612, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9730846881866455, "global_step": 573613, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0290613174438477, "global_step": 573614, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0451273918151855, "global_step": 573615, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.058988332748413, "global_step": 573616, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0239861011505127, "global_step": 573617, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9582279920578003, "global_step": 573618, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9631751775741577, "global_step": 573619, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.011141777038574, "global_step": 573620, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9276195764541626, "global_step": 573621, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0263218879699707, "global_step": 573622, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.904465675354004, "global_step": 573623, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9705157279968262, "global_step": 573624, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.095702648162842, "global_step": 573625, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9890282154083252, "global_step": 573626, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0022661685943604, "global_step": 573627, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.994217038154602, "global_step": 573628, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.990559458732605, "global_step": 573629, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.029937744140625, "global_step": 573630, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0002050399780273, "global_step": 573631, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.004214286804199, "global_step": 573632, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9956915378570557, "global_step": 573633, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9797273874282837, "global_step": 573634, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9750436544418335, "global_step": 573635, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.074981689453125, "global_step": 573636, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.935153841972351, "global_step": 573637, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.012619733810425, "global_step": 573638, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.070840358734131, "global_step": 573639, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0419178009033203, "global_step": 573640, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0472092628479004, "global_step": 573641, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.022632598876953, "global_step": 573642, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9825451374053955, "global_step": 573643, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0021612644195557, "global_step": 573644, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0432887077331543, "global_step": 573645, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.018000602722168, "global_step": 573646, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.056948184967041, "global_step": 573647, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.977659821510315, "global_step": 573648, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.036693811416626, "global_step": 573649, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.038386106491089, "global_step": 573650, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1180434226989746, "global_step": 573651, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.004696846008301, "global_step": 573652, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0357089042663574, "global_step": 573653, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0806381702423096, "global_step": 573654, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.100919723510742, "global_step": 573655, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9608923196792603, "global_step": 573656, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9574073553085327, "global_step": 573657, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.952272891998291, "global_step": 573658, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.019742727279663, "global_step": 573659, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0156285762786865, "global_step": 573660, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0823144912719727, "global_step": 573661, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9880483150482178, "global_step": 573662, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.047701120376587, "global_step": 573663, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0648109912872314, "global_step": 573664, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9672359228134155, "global_step": 573665, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9932466745376587, "global_step": 573666, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0151588916778564, "global_step": 573667, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.115453004837036, "global_step": 573668, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9196910858154297, "global_step": 573669, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9379255771636963, "global_step": 573670, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.100393533706665, "global_step": 573671, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0182812213897705, "global_step": 573672, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0317704677581787, "global_step": 573673, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0772008895874023, "global_step": 573674, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9636592864990234, "global_step": 573675, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.081610679626465, "global_step": 573676, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.071261405944824, "global_step": 573677, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.066957950592041, "global_step": 573678, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0157687664031982, "global_step": 573679, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9534903764724731, "global_step": 573680, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.969797968864441, "global_step": 573681, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.035353422164917, "global_step": 573682, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.99281644821167, "global_step": 573683, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0572476387023926, "global_step": 573684, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9908071756362915, "global_step": 573685, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.039461612701416, "global_step": 573686, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0622949600219727, "global_step": 573687, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9828733205795288, "global_step": 573688, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9678901433944702, "global_step": 573689, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.075348377227783, "global_step": 573690, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9844015836715698, "global_step": 573691, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1028659343719482, "global_step": 573692, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0160317420959473, "global_step": 573693, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9782867431640625, "global_step": 573694, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0586469173431396, "global_step": 573695, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0437183380126953, "global_step": 573696, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9695055484771729, "global_step": 573697, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9303733110427856, "global_step": 573698, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0276906490325928, "global_step": 573699, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.091576337814331, "global_step": 573700, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0275583267211914, "global_step": 573701, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0574734210968018, "global_step": 573702, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.03326416015625, "global_step": 573703, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.064112901687622, "global_step": 573704, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9919356107711792, "global_step": 573705, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1244325637817383, "global_step": 573706, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.971157431602478, "global_step": 573707, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.92941153049469, "global_step": 573708, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0654993057250977, "global_step": 573709, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1141068935394287, "global_step": 573710, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.106691598892212, "global_step": 573711, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.062392234802246, "global_step": 573712, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0281834602355957, "global_step": 573713, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0131006240844727, "global_step": 573714, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0072765350341797, "global_step": 573715, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9261168241500854, "global_step": 573716, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.019253730773926, "global_step": 573717, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0842347145080566, "global_step": 573718, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9812140464782715, "global_step": 573719, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0697498321533203, "global_step": 573720, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0690114498138428, "global_step": 573721, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.106856107711792, "global_step": 573722, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.036895275115967, "global_step": 573723, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.13338303565979, "global_step": 573724, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9644882678985596, "global_step": 573725, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.045480251312256, "global_step": 573726, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0020508766174316, "global_step": 573727, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.985954761505127, "global_step": 573728, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0951411724090576, "global_step": 573729, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0524120330810547, "global_step": 573730, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.021185874938965, "global_step": 573731, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0445902347564697, "global_step": 573732, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9925881624221802, "global_step": 573733, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9802579879760742, "global_step": 573734, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0570061206817627, "global_step": 573735, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0138463973999023, "global_step": 573736, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0114262104034424, "global_step": 573737, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9872809648513794, "global_step": 573738, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0032360553741455, "global_step": 573739, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.959938645362854, "global_step": 573740, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0433201789855957, "global_step": 573741, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.052433729171753, "global_step": 573742, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0576376914978027, "global_step": 573743, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.085009813308716, "global_step": 573744, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1061041355133057, "global_step": 573745, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.010437250137329, "global_step": 573746, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0337038040161133, "global_step": 573747, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0309715270996094, "global_step": 573748, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.070625066757202, "global_step": 573749, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.044898271560669, "global_step": 573750, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.1477749347686768, "global_step": 573751, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9717323780059814, "global_step": 573752, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0869979858398438, "global_step": 573753, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.938233733177185, "global_step": 573754, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0141985416412354, "global_step": 573755, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.059439182281494, "global_step": 573756, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0299997329711914, "global_step": 573757, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.040029525756836, "global_step": 573758, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.044529438018799, "global_step": 573759, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0774571895599365, "global_step": 573760, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.987656831741333, "global_step": 573761, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0760693550109863, "global_step": 573762, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.107304811477661, "global_step": 573763, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0697696208953857, "global_step": 573764, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9941699504852295, "global_step": 573765, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0632638931274414, "global_step": 573766, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.941950798034668, "global_step": 573767, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.011263132095337, "global_step": 573768, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.061866044998169, "global_step": 573769, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.9125256538391113, "global_step": 573770, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.033400297164917, "global_step": 573771, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0690150260925293, "global_step": 573772, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.944307804107666, "global_step": 573773, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.053581953048706, "global_step": 573774, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.976605772972107, "global_step": 573775, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0252909660339355, "global_step": 573776, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.015110492706299, "global_step": 573777, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.0039024353027344, "global_step": 573778, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.043095350265503, "global_step": 573779, "epoch": 941, "lr": 5e-05}
{"train_loss": 2.022472381591797, "global_step": 573780, "epoch": 941, "lr": 5e-05}
{"train_loss": 1.975520133972168, "global_step": 573781, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.951358437538147, "global_step": 573782, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9912621974945068, "global_step": 573783, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9978560209274292, "global_step": 573784, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0218539237976074, "global_step": 573785, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.008392333984375, "global_step": 573786, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0125198364257812, "global_step": 573787, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.086678981781006, "global_step": 573788, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.946177363395691, "global_step": 573789, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0435049533843994, "global_step": 573790, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.996629238128662, "global_step": 573791, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9883867502212524, "global_step": 573792, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.034320116043091, "global_step": 573793, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.000676155090332, "global_step": 573794, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0781829357147217, "global_step": 573795, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0422110557556152, "global_step": 573796, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.022484064102173, "global_step": 573797, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.997152328491211, "global_step": 573798, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9146405458450317, "global_step": 573799, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.097609758377075, "global_step": 573800, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0107431411743164, "global_step": 573801, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0602340698242188, "global_step": 573802, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.963728666305542, "global_step": 573803, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0953774452209473, "global_step": 573804, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0526516437530518, "global_step": 573805, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.966012954711914, "global_step": 573806, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.039375066757202, "global_step": 573807, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1024062633514404, "global_step": 573808, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9516098499298096, "global_step": 573809, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9623229503631592, "global_step": 573810, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0314621925354004, "global_step": 573811, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9876184463500977, "global_step": 573812, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9329222440719604, "global_step": 573813, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0246329307556152, "global_step": 573814, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0213537216186523, "global_step": 573815, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0371925830841064, "global_step": 573816, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9718294143676758, "global_step": 573817, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0385208129882812, "global_step": 573818, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.069986343383789, "global_step": 573819, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9579018354415894, "global_step": 573820, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.043262004852295, "global_step": 573821, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9963879585266113, "global_step": 573822, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9383596181869507, "global_step": 573823, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.099832534790039, "global_step": 573824, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.003086566925049, "global_step": 573825, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0173659324645996, "global_step": 573826, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9859036207199097, "global_step": 573827, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.054001808166504, "global_step": 573828, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0477850437164307, "global_step": 573829, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9612256288528442, "global_step": 573830, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.8920506238937378, "global_step": 573831, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9903076887130737, "global_step": 573832, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9924213886260986, "global_step": 573833, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.034228563308716, "global_step": 573834, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9849547147750854, "global_step": 573835, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9473261833190918, "global_step": 573836, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.8971303701400757, "global_step": 573837, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0526676177978516, "global_step": 573838, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1083171367645264, "global_step": 573839, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9431688785552979, "global_step": 573840, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0332913398742676, "global_step": 573841, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0599706172943115, "global_step": 573842, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0024757385253906, "global_step": 573843, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0183417797088623, "global_step": 573844, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.94459068775177, "global_step": 573845, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0452232360839844, "global_step": 573846, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0019216537475586, "global_step": 573847, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9592671394348145, "global_step": 573848, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9262381792068481, "global_step": 573849, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9874608516693115, "global_step": 573850, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9524171352386475, "global_step": 573851, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.070127487182617, "global_step": 573852, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9988611936569214, "global_step": 573853, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.037006139755249, "global_step": 573854, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.055234670639038, "global_step": 573855, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9809613227844238, "global_step": 573856, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.01031231880188, "global_step": 573857, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0140888690948486, "global_step": 573858, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9648544788360596, "global_step": 573859, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9578324556350708, "global_step": 573860, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1186811923980713, "global_step": 573861, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.06421160697937, "global_step": 573862, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0660417079925537, "global_step": 573863, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0373854637145996, "global_step": 573864, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.01882266998291, "global_step": 573865, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.963978886604309, "global_step": 573866, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.917965292930603, "global_step": 573867, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9751359224319458, "global_step": 573868, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9788354635238647, "global_step": 573869, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.966600775718689, "global_step": 573870, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.966850996017456, "global_step": 573871, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1020169258117676, "global_step": 573872, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9088270664215088, "global_step": 573873, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0887420177459717, "global_step": 573874, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9850929975509644, "global_step": 573875, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9798321723937988, "global_step": 573876, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.95499587059021, "global_step": 573877, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9863485097885132, "global_step": 573878, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1064679622650146, "global_step": 573879, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9633028507232666, "global_step": 573880, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0086498260498047, "global_step": 573881, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0830254554748535, "global_step": 573882, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9628576040267944, "global_step": 573883, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.952418327331543, "global_step": 573884, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.994800090789795, "global_step": 573885, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9094473123550415, "global_step": 573886, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9581928253173828, "global_step": 573887, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0544416904449463, "global_step": 573888, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0111968517303467, "global_step": 573889, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0378966331481934, "global_step": 573890, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0161728858947754, "global_step": 573891, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9654115438461304, "global_step": 573892, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9813822507858276, "global_step": 573893, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1033554077148438, "global_step": 573894, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9560166597366333, "global_step": 573895, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0279691219329834, "global_step": 573896, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.022181987762451, "global_step": 573897, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1099555492401123, "global_step": 573898, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0099427700042725, "global_step": 573899, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.13254976272583, "global_step": 573900, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0811002254486084, "global_step": 573901, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0341625213623047, "global_step": 573902, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0036206245422363, "global_step": 573903, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.030435562133789, "global_step": 573904, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.991690754890442, "global_step": 573905, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.012129068374634, "global_step": 573906, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9989993572235107, "global_step": 573907, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.973839282989502, "global_step": 573908, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9972862005233765, "global_step": 573909, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0834853649139404, "global_step": 573910, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9643489122390747, "global_step": 573911, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0158255100250244, "global_step": 573912, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0095252990722656, "global_step": 573913, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0132298469543457, "global_step": 573914, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0189049243927, "global_step": 573915, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.047279119491577, "global_step": 573916, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0016486644744873, "global_step": 573917, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0161259174346924, "global_step": 573918, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0431108474731445, "global_step": 573919, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.007892370223999, "global_step": 573920, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.056347370147705, "global_step": 573921, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9276342391967773, "global_step": 573922, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0090556144714355, "global_step": 573923, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0089573860168457, "global_step": 573924, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9290661811828613, "global_step": 573925, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.027311325073242, "global_step": 573926, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.095982313156128, "global_step": 573927, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0801503658294678, "global_step": 573928, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.033480644226074, "global_step": 573929, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.040193796157837, "global_step": 573930, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0042083263397217, "global_step": 573931, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0738778114318848, "global_step": 573932, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9995249509811401, "global_step": 573933, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.987004041671753, "global_step": 573934, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9154765605926514, "global_step": 573935, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0476362705230713, "global_step": 573936, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9971076250076294, "global_step": 573937, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9676018953323364, "global_step": 573938, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9614307880401611, "global_step": 573939, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.026968002319336, "global_step": 573940, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0085809230804443, "global_step": 573941, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.195754289627075, "global_step": 573942, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0883874893188477, "global_step": 573943, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9638159275054932, "global_step": 573944, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9686349630355835, "global_step": 573945, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9727681875228882, "global_step": 573946, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9640628099441528, "global_step": 573947, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9888465404510498, "global_step": 573948, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9707170724868774, "global_step": 573949, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.028224229812622, "global_step": 573950, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0439538955688477, "global_step": 573951, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.017099618911743, "global_step": 573952, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0602879524230957, "global_step": 573953, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.931763768196106, "global_step": 573954, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.010772466659546, "global_step": 573955, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0282771587371826, "global_step": 573956, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.059570789337158, "global_step": 573957, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.130842924118042, "global_step": 573958, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0816702842712402, "global_step": 573959, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9998501539230347, "global_step": 573960, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0606155395507812, "global_step": 573961, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9724030494689941, "global_step": 573962, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9898529052734375, "global_step": 573963, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0582962036132812, "global_step": 573964, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9322234392166138, "global_step": 573965, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.037013292312622, "global_step": 573966, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.018127202987671, "global_step": 573967, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9780884981155396, "global_step": 573968, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.998139500617981, "global_step": 573969, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9221076965332031, "global_step": 573970, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0091710090637207, "global_step": 573971, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0737082958221436, "global_step": 573972, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9650037288665771, "global_step": 573973, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0361990928649902, "global_step": 573974, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.070207357406616, "global_step": 573975, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.019890785217285, "global_step": 573976, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0013344287872314, "global_step": 573977, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9992276430130005, "global_step": 573978, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9911184310913086, "global_step": 573979, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.059579610824585, "global_step": 573980, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0287606716156006, "global_step": 573981, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9200406074523926, "global_step": 573982, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.037717819213867, "global_step": 573983, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9834043979644775, "global_step": 573984, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0527424812316895, "global_step": 573985, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9753458499908447, "global_step": 573986, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9329652786254883, "global_step": 573987, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9730136394500732, "global_step": 573988, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.018028974533081, "global_step": 573989, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.017159938812256, "global_step": 573990, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9705957174301147, "global_step": 573991, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.028346300125122, "global_step": 573992, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.002974510192871, "global_step": 573993, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.053891897201538, "global_step": 573994, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.956173300743103, "global_step": 573995, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0030770301818848, "global_step": 573996, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0887041091918945, "global_step": 573997, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.995357632637024, "global_step": 573998, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0222816467285156, "global_step": 573999, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9747369289398193, "global_step": 574000, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.026677370071411, "global_step": 574001, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0485475063323975, "global_step": 574002, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9783360958099365, "global_step": 574003, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.05544376373291, "global_step": 574004, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.034536838531494, "global_step": 574005, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.023031234741211, "global_step": 574006, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9992198944091797, "global_step": 574007, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9587652683258057, "global_step": 574008, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9903006553649902, "global_step": 574009, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0059354305267334, "global_step": 574010, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9657166004180908, "global_step": 574011, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9889909029006958, "global_step": 574012, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0901026725769043, "global_step": 574013, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0113511085510254, "global_step": 574014, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.069838523864746, "global_step": 574015, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.992297649383545, "global_step": 574016, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0343425273895264, "global_step": 574017, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0222628116607666, "global_step": 574018, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.006298065185547, "global_step": 574019, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9909999370574951, "global_step": 574020, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0571694374084473, "global_step": 574021, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0473785400390625, "global_step": 574022, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0028269290924072, "global_step": 574023, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0505034923553467, "global_step": 574024, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0291900634765625, "global_step": 574025, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9577195644378662, "global_step": 574026, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0357956886291504, "global_step": 574027, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0235238075256348, "global_step": 574028, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9765496253967285, "global_step": 574029, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0631186962127686, "global_step": 574030, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0423717498779297, "global_step": 574031, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0980136394500732, "global_step": 574032, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.061471462249756, "global_step": 574033, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0140223503112793, "global_step": 574034, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.011364698410034, "global_step": 574035, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0650339126586914, "global_step": 574036, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0520639419555664, "global_step": 574037, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9954723119735718, "global_step": 574038, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0049521923065186, "global_step": 574039, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.068328857421875, "global_step": 574040, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0000815391540527, "global_step": 574041, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9610286951065063, "global_step": 574042, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.012265205383301, "global_step": 574043, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0347185134887695, "global_step": 574044, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0586745738983154, "global_step": 574045, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.024945020675659, "global_step": 574046, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.979972243309021, "global_step": 574047, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9927279949188232, "global_step": 574048, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0614562034606934, "global_step": 574049, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0072996616363525, "global_step": 574050, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9770593643188477, "global_step": 574051, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9589802026748657, "global_step": 574052, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.076653003692627, "global_step": 574053, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0145010948181152, "global_step": 574054, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0306456089019775, "global_step": 574055, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0652759075164795, "global_step": 574056, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9511594772338867, "global_step": 574057, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0397136211395264, "global_step": 574058, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.064213991165161, "global_step": 574059, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.043795108795166, "global_step": 574060, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0300467014312744, "global_step": 574061, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9694467782974243, "global_step": 574062, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0217132568359375, "global_step": 574063, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1044180393218994, "global_step": 574064, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.062844753265381, "global_step": 574065, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.030892848968506, "global_step": 574066, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0916669368743896, "global_step": 574067, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0401782989501953, "global_step": 574068, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.926798701286316, "global_step": 574069, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0746889114379883, "global_step": 574070, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0674540996551514, "global_step": 574071, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.971071720123291, "global_step": 574072, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.092087745666504, "global_step": 574073, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.023577928543091, "global_step": 574074, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9586304426193237, "global_step": 574075, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.028822660446167, "global_step": 574076, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9897892475128174, "global_step": 574077, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.00575852394104, "global_step": 574078, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0399210453033447, "global_step": 574079, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.041408061981201, "global_step": 574080, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9947619438171387, "global_step": 574081, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9909769296646118, "global_step": 574082, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0502188205718994, "global_step": 574083, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.058305025100708, "global_step": 574084, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9407559633255005, "global_step": 574085, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.050884485244751, "global_step": 574086, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.029229164123535, "global_step": 574087, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9777525663375854, "global_step": 574088, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9656012058258057, "global_step": 574089, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.998571753501892, "global_step": 574090, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0377798080444336, "global_step": 574091, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0189895629882812, "global_step": 574092, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0387978553771973, "global_step": 574093, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9536099433898926, "global_step": 574094, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.958764672279358, "global_step": 574095, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.048171281814575, "global_step": 574096, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9438703060150146, "global_step": 574097, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1095168590545654, "global_step": 574098, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9465199708938599, "global_step": 574099, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.924698829650879, "global_step": 574100, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0266592502593994, "global_step": 574101, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0758795738220215, "global_step": 574102, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.043424606323242, "global_step": 574103, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0414717197418213, "global_step": 574104, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9489598274230957, "global_step": 574105, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0317800045013428, "global_step": 574106, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.055020809173584, "global_step": 574107, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9829380512237549, "global_step": 574108, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.143186092376709, "global_step": 574109, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0054080486297607, "global_step": 574110, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.021980047225952, "global_step": 574111, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9741895198822021, "global_step": 574112, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0415477752685547, "global_step": 574113, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0477094650268555, "global_step": 574114, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0117006301879883, "global_step": 574115, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1137866973876953, "global_step": 574116, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9977738857269287, "global_step": 574117, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0029497146606445, "global_step": 574118, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.995123267173767, "global_step": 574119, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0246965885162354, "global_step": 574120, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.990153431892395, "global_step": 574121, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.087844133377075, "global_step": 574122, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.012854814529419, "global_step": 574123, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.042154550552368, "global_step": 574124, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9964275360107422, "global_step": 574125, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1547794342041016, "global_step": 574126, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0649571418762207, "global_step": 574127, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.033031702041626, "global_step": 574128, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0457048416137695, "global_step": 574129, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0708305835723877, "global_step": 574130, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0697312355041504, "global_step": 574131, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.05673885345459, "global_step": 574132, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9527589082717896, "global_step": 574133, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0362675189971924, "global_step": 574134, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0024631023406982, "global_step": 574135, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9376829862594604, "global_step": 574136, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.051361560821533, "global_step": 574137, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9612746238708496, "global_step": 574138, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0712406635284424, "global_step": 574139, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.052968740463257, "global_step": 574140, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1417393684387207, "global_step": 574141, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0027472972869873, "global_step": 574142, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9836360216140747, "global_step": 574143, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0815627574920654, "global_step": 574144, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9557033777236938, "global_step": 574145, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.033994436264038, "global_step": 574146, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.012561798095703, "global_step": 574147, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.01617169380188, "global_step": 574148, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9960014820098877, "global_step": 574149, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9949774742126465, "global_step": 574150, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9969770908355713, "global_step": 574151, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.039919853210449, "global_step": 574152, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0219898223876953, "global_step": 574153, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.043743133544922, "global_step": 574154, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0370616912841797, "global_step": 574155, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9666849374771118, "global_step": 574156, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.055948257446289, "global_step": 574157, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0006134510040283, "global_step": 574158, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.069990634918213, "global_step": 574159, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9412426948547363, "global_step": 574160, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.8950238227844238, "global_step": 574161, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.05106258392334, "global_step": 574162, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.974452018737793, "global_step": 574163, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.983211636543274, "global_step": 574164, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0296854972839355, "global_step": 574165, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9928733110427856, "global_step": 574166, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0838165283203125, "global_step": 574167, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9909107685089111, "global_step": 574168, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0135045051574707, "global_step": 574169, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9944759607315063, "global_step": 574170, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9824399948120117, "global_step": 574171, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0820155143737793, "global_step": 574172, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9379366636276245, "global_step": 574173, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.144468069076538, "global_step": 574174, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9828300476074219, "global_step": 574175, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.067922353744507, "global_step": 574176, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0420331954956055, "global_step": 574177, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1064295768737793, "global_step": 574178, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0153634548187256, "global_step": 574179, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0327939987182617, "global_step": 574180, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.050391435623169, "global_step": 574181, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.059168577194214, "global_step": 574182, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0316572189331055, "global_step": 574183, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0154449939727783, "global_step": 574184, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0551836490631104, "global_step": 574185, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0778863430023193, "global_step": 574186, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9792256355285645, "global_step": 574187, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.071403980255127, "global_step": 574188, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0225772857666016, "global_step": 574189, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9923075437545776, "global_step": 574190, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.018946647644043, "global_step": 574191, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1062562465667725, "global_step": 574192, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.040297031402588, "global_step": 574193, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9262908697128296, "global_step": 574194, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0206151008605957, "global_step": 574195, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0767714977264404, "global_step": 574196, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0901007652282715, "global_step": 574197, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.979755163192749, "global_step": 574198, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.023585319519043, "global_step": 574199, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0052053928375244, "global_step": 574200, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.901381492614746, "global_step": 574201, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.069941520690918, "global_step": 574202, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.00590443611145, "global_step": 574203, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9824321269989014, "global_step": 574204, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0478127002716064, "global_step": 574205, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.060062885284424, "global_step": 574206, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1274287700653076, "global_step": 574207, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9586259126663208, "global_step": 574208, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9910814762115479, "global_step": 574209, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9808458089828491, "global_step": 574210, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.970273494720459, "global_step": 574211, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.036876678466797, "global_step": 574212, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0070300102233887, "global_step": 574213, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0264780521392822, "global_step": 574214, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.081343173980713, "global_step": 574215, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9679752588272095, "global_step": 574216, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9899119138717651, "global_step": 574217, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.078700304031372, "global_step": 574218, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.116971254348755, "global_step": 574219, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.065051794052124, "global_step": 574220, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9482427835464478, "global_step": 574221, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.924412488937378, "global_step": 574222, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0593888759613037, "global_step": 574223, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9082695245742798, "global_step": 574224, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0117273330688477, "global_step": 574225, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0186269283294678, "global_step": 574226, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0485501289367676, "global_step": 574227, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0146536827087402, "global_step": 574228, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0735650062561035, "global_step": 574229, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9528669118881226, "global_step": 574230, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.010636806488037, "global_step": 574231, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.049220561981201, "global_step": 574232, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0652735233306885, "global_step": 574233, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.988128423690796, "global_step": 574234, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9894695281982422, "global_step": 574235, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0264248847961426, "global_step": 574236, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.989065408706665, "global_step": 574237, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9451498985290527, "global_step": 574238, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.090027332305908, "global_step": 574239, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0160207748413086, "global_step": 574240, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1417229175567627, "global_step": 574241, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.091275691986084, "global_step": 574242, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9883294105529785, "global_step": 574243, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.052337169647217, "global_step": 574244, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1017909049987793, "global_step": 574245, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0225045680999756, "global_step": 574246, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0220375061035156, "global_step": 574247, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1521756649017334, "global_step": 574248, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.004803419113159, "global_step": 574249, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.059312105178833, "global_step": 574250, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0064454078674316, "global_step": 574251, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.022101879119873, "global_step": 574252, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.037898540496826, "global_step": 574253, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9637418985366821, "global_step": 574254, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.892946720123291, "global_step": 574255, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.970859408378601, "global_step": 574256, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9915512800216675, "global_step": 574257, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0445988178253174, "global_step": 574258, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.064469814300537, "global_step": 574259, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.045828342437744, "global_step": 574260, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.094555139541626, "global_step": 574261, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0590131282806396, "global_step": 574262, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9907132387161255, "global_step": 574263, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.984346866607666, "global_step": 574264, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0408143997192383, "global_step": 574265, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0137782096862793, "global_step": 574266, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0464134216308594, "global_step": 574267, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.958361268043518, "global_step": 574268, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0626091957092285, "global_step": 574269, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0464866161346436, "global_step": 574270, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.005098342895508, "global_step": 574271, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9599722623825073, "global_step": 574272, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.979425072669983, "global_step": 574273, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9648271799087524, "global_step": 574274, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0070366859436035, "global_step": 574275, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.975656270980835, "global_step": 574276, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0597126483917236, "global_step": 574277, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.004472494125366, "global_step": 574278, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.05342960357666, "global_step": 574279, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.079498767852783, "global_step": 574280, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9463441371917725, "global_step": 574281, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.964128017425537, "global_step": 574282, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.161452293395996, "global_step": 574283, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.001948833465576, "global_step": 574284, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9825422763824463, "global_step": 574285, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.99258291721344, "global_step": 574286, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.015329122543335, "global_step": 574287, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9856879711151123, "global_step": 574288, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0358245372772217, "global_step": 574289, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0221786499023438, "global_step": 574290, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.072728157043457, "global_step": 574291, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0836634635925293, "global_step": 574292, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0553832054138184, "global_step": 574293, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9571647644042969, "global_step": 574294, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.949639081954956, "global_step": 574295, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1084845066070557, "global_step": 574296, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0330824851989746, "global_step": 574297, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0425710678100586, "global_step": 574298, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9803645610809326, "global_step": 574299, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0171353816986084, "global_step": 574300, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1152329444885254, "global_step": 574301, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0148255825042725, "global_step": 574302, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9709593057632446, "global_step": 574303, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.07619571685791, "global_step": 574304, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0681443214416504, "global_step": 574305, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0641839504241943, "global_step": 574306, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0070114135742188, "global_step": 574307, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.057924509048462, "global_step": 574308, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9808844327926636, "global_step": 574309, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0934579372406006, "global_step": 574310, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9704076051712036, "global_step": 574311, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0228936672210693, "global_step": 574312, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9940725564956665, "global_step": 574313, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9754960536956787, "global_step": 574314, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0641956329345703, "global_step": 574315, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.02410888671875, "global_step": 574316, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0170955657958984, "global_step": 574317, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.020618438720703, "global_step": 574318, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9847403764724731, "global_step": 574319, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9687198400497437, "global_step": 574320, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.951017141342163, "global_step": 574321, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.018280029296875, "global_step": 574322, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.024761915206909, "global_step": 574323, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0346384048461914, "global_step": 574324, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0083184242248535, "global_step": 574325, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.040539503097534, "global_step": 574326, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0094258785247803, "global_step": 574327, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.055408000946045, "global_step": 574328, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0964128971099854, "global_step": 574329, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.06243896484375, "global_step": 574330, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.020256996154785, "global_step": 574331, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0320279598236084, "global_step": 574332, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0378639698028564, "global_step": 574333, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9569028615951538, "global_step": 574334, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.899610996246338, "global_step": 574335, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0396690368652344, "global_step": 574336, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0078747272491455, "global_step": 574337, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.027568817138672, "global_step": 574338, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9466792345046997, "global_step": 574339, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0202584266662598, "global_step": 574340, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1337077617645264, "global_step": 574341, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0450048446655273, "global_step": 574342, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0063045024871826, "global_step": 574343, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.967641830444336, "global_step": 574344, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.084899663925171, "global_step": 574345, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0166735649108887, "global_step": 574346, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.026278257369995, "global_step": 574347, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9417638778686523, "global_step": 574348, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0476183891296387, "global_step": 574349, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.080261468887329, "global_step": 574350, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9731030464172363, "global_step": 574351, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9541280269622803, "global_step": 574352, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.067542552947998, "global_step": 574353, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0046305656433105, "global_step": 574354, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0588138103485107, "global_step": 574355, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.023066282272339, "global_step": 574356, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.039796829223633, "global_step": 574357, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.046443462371826, "global_step": 574358, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9538124799728394, "global_step": 574359, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0608983039855957, "global_step": 574360, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0930936336517334, "global_step": 574361, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.069981098175049, "global_step": 574362, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0010182857513428, "global_step": 574363, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.073535919189453, "global_step": 574364, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0060348510742188, "global_step": 574365, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.999855875968933, "global_step": 574366, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9668562412261963, "global_step": 574367, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.003024101257324, "global_step": 574368, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9963006973266602, "global_step": 574369, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0717406272888184, "global_step": 574370, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0831265449523926, "global_step": 574371, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0233941078186035, "global_step": 574372, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0365114212036133, "global_step": 574373, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9964646100997925, "global_step": 574374, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1092023849487305, "global_step": 574375, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0450282096862793, "global_step": 574376, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.02217173576355, "global_step": 574377, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.04476261138916, "global_step": 574378, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.096235752105713, "global_step": 574379, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0311803817749023, "global_step": 574380, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9304029941558838, "global_step": 574381, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9764667749404907, "global_step": 574382, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.056774854660034, "global_step": 574383, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0417792797088623, "global_step": 574384, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0045788288116455, "global_step": 574385, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0445103645324707, "global_step": 574386, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.073025703430176, "global_step": 574387, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0478882789611816, "global_step": 574388, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.970683217048645, "global_step": 574389, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.079758882522583, "global_step": 574390, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.087043523788452, "global_step": 574391, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0682997703552246, "global_step": 574392, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.995326280593872, "global_step": 574393, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.980526089668274, "global_step": 574394, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9301363229751587, "global_step": 574395, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0194108486175537, "global_step": 574396, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9739367961883545, "global_step": 574397, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9706778526306152, "global_step": 574398, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0299453735351562, "global_step": 574399, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9946712255477905, "global_step": 574400, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.028555393218994, "global_step": 574401, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9988422393798828, "global_step": 574402, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.039238929748535, "global_step": 574403, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.039525270462036, "global_step": 574404, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1018176078796387, "global_step": 574405, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0404510498046875, "global_step": 574406, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9278053045272827, "global_step": 574407, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0927000045776367, "global_step": 574408, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.04893159866333, "global_step": 574409, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9719460010528564, "global_step": 574410, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9501948356628418, "global_step": 574411, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1182568073272705, "global_step": 574412, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.04302978515625, "global_step": 574413, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9878727197647095, "global_step": 574414, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0864195823669434, "global_step": 574415, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.068704605102539, "global_step": 574416, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.064035177230835, "global_step": 574417, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9674725532531738, "global_step": 574418, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.013092041015625, "global_step": 574419, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0336754322052, "global_step": 574420, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.020644426345825, "global_step": 574421, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.013970136642456, "global_step": 574422, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.044295072555542, "global_step": 574423, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0843770503997803, "global_step": 574424, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1006596088409424, "global_step": 574425, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0051798820495605, "global_step": 574426, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.062819480895996, "global_step": 574427, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.026977777481079, "global_step": 574428, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9541734457015991, "global_step": 574429, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9228571653366089, "global_step": 574430, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0905516147613525, "global_step": 574431, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.060365676879883, "global_step": 574432, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9775089025497437, "global_step": 574433, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9317291975021362, "global_step": 574434, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0550553798675537, "global_step": 574435, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.023484706878662, "global_step": 574436, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9910619258880615, "global_step": 574437, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0725343227386475, "global_step": 574438, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1447649002075195, "global_step": 574439, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.97590970993042, "global_step": 574440, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.096334934234619, "global_step": 574441, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.934464454650879, "global_step": 574442, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.034742593765259, "global_step": 574443, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9748259782791138, "global_step": 574444, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9712239503860474, "global_step": 574445, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0260775089263916, "global_step": 574446, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.12878680229187, "global_step": 574447, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.088322639465332, "global_step": 574448, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9353983402252197, "global_step": 574449, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.015108823776245, "global_step": 574450, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9811806678771973, "global_step": 574451, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.100895881652832, "global_step": 574452, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0179147720336914, "global_step": 574453, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9930830001831055, "global_step": 574454, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9447102546691895, "global_step": 574455, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.000964641571045, "global_step": 574456, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0470757484436035, "global_step": 574457, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0370309352874756, "global_step": 574458, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9747124910354614, "global_step": 574459, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.012982130050659, "global_step": 574460, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.98807692527771, "global_step": 574461, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.00828218460083, "global_step": 574462, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1167778968811035, "global_step": 574463, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.019972324371338, "global_step": 574464, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0408596992492676, "global_step": 574465, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.092435359954834, "global_step": 574466, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.989516019821167, "global_step": 574467, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0128629207611084, "global_step": 574468, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9493595361709595, "global_step": 574469, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0170905590057373, "global_step": 574470, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.062786817550659, "global_step": 574471, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0087084770202637, "global_step": 574472, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.006026029586792, "global_step": 574473, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1096363067626953, "global_step": 574474, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0771665573120117, "global_step": 574475, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.047283411026001, "global_step": 574476, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9802428483963013, "global_step": 574477, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.969861388206482, "global_step": 574478, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9918466806411743, "global_step": 574479, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0471341609954834, "global_step": 574480, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.053619623184204, "global_step": 574481, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0910537242889404, "global_step": 574482, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.013532876968384, "global_step": 574483, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0155270099639893, "global_step": 574484, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0358614921569824, "global_step": 574485, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.094146251678467, "global_step": 574486, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.032318353652954, "global_step": 574487, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9504107236862183, "global_step": 574488, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.8618794679641724, "global_step": 574489, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9707481861114502, "global_step": 574490, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.079456090927124, "global_step": 574491, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.998531699180603, "global_step": 574492, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.102705717086792, "global_step": 574493, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9956672191619873, "global_step": 574494, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.019861936569214, "global_step": 574495, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0628182888031006, "global_step": 574496, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0606470108032227, "global_step": 574497, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0749828815460205, "global_step": 574498, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0127508640289307, "global_step": 574499, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.051118850708008, "global_step": 574500, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.04703426361084, "global_step": 574501, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0291249752044678, "global_step": 574502, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9524297714233398, "global_step": 574503, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.110213041305542, "global_step": 574504, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9633361101150513, "global_step": 574505, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.03133487701416, "global_step": 574506, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.055582046508789, "global_step": 574507, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0892527103424072, "global_step": 574508, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.007913589477539, "global_step": 574509, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.89781653881073, "global_step": 574510, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0727500915527344, "global_step": 574511, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0136091709136963, "global_step": 574512, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9993045330047607, "global_step": 574513, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.093271255493164, "global_step": 574514, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0938427448272705, "global_step": 574515, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9661921262741089, "global_step": 574516, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.049318790435791, "global_step": 574517, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.986211895942688, "global_step": 574518, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0003085136413574, "global_step": 574519, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0288217067718506, "global_step": 574520, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.101210594177246, "global_step": 574521, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.2036774158477783, "global_step": 574522, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0332674980163574, "global_step": 574523, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9510916471481323, "global_step": 574524, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.014047384262085, "global_step": 574525, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.013901710510254, "global_step": 574526, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0737555027008057, "global_step": 574527, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.031881093978882, "global_step": 574528, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0538530349731445, "global_step": 574529, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.113428831100464, "global_step": 574530, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9497787952423096, "global_step": 574531, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0121817588806152, "global_step": 574532, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0208544731140137, "global_step": 574533, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.047250747680664, "global_step": 574534, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0339133739471436, "global_step": 574535, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.94127357006073, "global_step": 574536, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0538671016693115, "global_step": 574537, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0421347618103027, "global_step": 574538, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.044342517852783, "global_step": 574539, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.998373031616211, "global_step": 574540, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9696773290634155, "global_step": 574541, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0250139236450195, "global_step": 574542, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9860782623291016, "global_step": 574543, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.034379720687866, "global_step": 574544, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.994322657585144, "global_step": 574545, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0332674980163574, "global_step": 574546, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0624043941497803, "global_step": 574547, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0287187099456787, "global_step": 574548, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.101846218109131, "global_step": 574549, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.099360704421997, "global_step": 574550, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.028514862060547, "global_step": 574551, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0353591442108154, "global_step": 574552, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.111022710800171, "global_step": 574553, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.119297742843628, "global_step": 574554, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9828922748565674, "global_step": 574555, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9974565505981445, "global_step": 574556, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.031144142150879, "global_step": 574557, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0248522758483887, "global_step": 574558, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9877742528915405, "global_step": 574559, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1604576110839844, "global_step": 574560, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.008211135864258, "global_step": 574561, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.03891658782959, "global_step": 574562, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9706957340240479, "global_step": 574563, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0740063190460205, "global_step": 574564, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.107034683227539, "global_step": 574565, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0438756942749023, "global_step": 574566, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.007073402404785, "global_step": 574567, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9873846769332886, "global_step": 574568, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.026124954223633, "global_step": 574569, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.002197265625, "global_step": 574570, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0082008838653564, "global_step": 574571, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0736265182495117, "global_step": 574572, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.094527244567871, "global_step": 574573, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9887945652008057, "global_step": 574574, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1113173961639404, "global_step": 574575, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9873405694961548, "global_step": 574576, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0466678142547607, "global_step": 574577, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.05159330368042, "global_step": 574578, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.082470655441284, "global_step": 574579, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.073681116104126, "global_step": 574580, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0392658710479736, "global_step": 574581, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.076066255569458, "global_step": 574582, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0274908542633057, "global_step": 574583, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.035186767578125, "global_step": 574584, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0401594638824463, "global_step": 574585, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0072267055511475, "global_step": 574586, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.104329824447632, "global_step": 574587, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0234429836273193, "global_step": 574588, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.097867250442505, "global_step": 574589, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.999570369720459, "global_step": 574590, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.093644857406616, "global_step": 574591, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0265426635742188, "global_step": 574592, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1600470542907715, "global_step": 574593, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0063695907592773, "global_step": 574594, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0770554542541504, "global_step": 574595, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.034437417984009, "global_step": 574596, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.003711462020874, "global_step": 574597, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9855525493621826, "global_step": 574598, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0352442264556885, "global_step": 574599, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9859610795974731, "global_step": 574600, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0393731594085693, "global_step": 574601, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9650336503982544, "global_step": 574602, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.036278009414673, "global_step": 574603, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.003943920135498, "global_step": 574604, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9799985885620117, "global_step": 574605, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0369715690612793, "global_step": 574606, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.004534959793091, "global_step": 574607, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0434720516204834, "global_step": 574608, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.071794271469116, "global_step": 574609, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9164220094680786, "global_step": 574610, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0049166679382324, "global_step": 574611, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.033926010131836, "global_step": 574612, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0511579513549805, "global_step": 574613, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.955852746963501, "global_step": 574614, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.08852481842041, "global_step": 574615, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0737340450286865, "global_step": 574616, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.022921323776245, "global_step": 574617, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9958456754684448, "global_step": 574618, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0532286167144775, "global_step": 574619, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0897490978240967, "global_step": 574620, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.023711919784546, "global_step": 574621, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9665285348892212, "global_step": 574622, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9917244911193848, "global_step": 574623, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0627100467681885, "global_step": 574624, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1059775352478027, "global_step": 574625, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.060004472732544, "global_step": 574626, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.111032485961914, "global_step": 574627, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.055170774459839, "global_step": 574628, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9627609252929688, "global_step": 574629, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.093658685684204, "global_step": 574630, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0151524543762207, "global_step": 574631, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.049304485321045, "global_step": 574632, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9952266216278076, "global_step": 574633, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9728931188583374, "global_step": 574634, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9948571920394897, "global_step": 574635, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0878257751464844, "global_step": 574636, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9701851606369019, "global_step": 574637, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.971938133239746, "global_step": 574638, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9855331182479858, "global_step": 574639, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9479012489318848, "global_step": 574640, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0101678371429443, "global_step": 574641, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.11319899559021, "global_step": 574642, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0429821014404297, "global_step": 574643, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.090561866760254, "global_step": 574644, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0989742279052734, "global_step": 574645, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0418152809143066, "global_step": 574646, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9511361122131348, "global_step": 574647, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0753331184387207, "global_step": 574648, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0929970741271973, "global_step": 574649, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9929721355438232, "global_step": 574650, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0131595134735107, "global_step": 574651, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0865087509155273, "global_step": 574652, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0670740604400635, "global_step": 574653, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.058310031890869, "global_step": 574654, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0271053314208984, "global_step": 574655, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1225459575653076, "global_step": 574656, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0231194496154785, "global_step": 574657, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0645194053649902, "global_step": 574658, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.013216733932495, "global_step": 574659, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0464086532592773, "global_step": 574660, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.971105694770813, "global_step": 574661, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0334742069244385, "global_step": 574662, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0422070026397705, "global_step": 574663, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.990738034248352, "global_step": 574664, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9789944887161255, "global_step": 574665, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0248830318450928, "global_step": 574666, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.016356945037842, "global_step": 574667, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0020816326141357, "global_step": 574668, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0104148387908936, "global_step": 574669, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9375046491622925, "global_step": 574670, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.934949517250061, "global_step": 574671, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.01273775100708, "global_step": 574672, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0221357345581055, "global_step": 574673, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.985707402229309, "global_step": 574674, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.1087021827697754, "global_step": 574675, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0463666915893555, "global_step": 574676, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0917952060699463, "global_step": 574677, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9282646179199219, "global_step": 574678, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9448314905166626, "global_step": 574679, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0518808364868164, "global_step": 574680, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9782782793045044, "global_step": 574681, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0535786151885986, "global_step": 574682, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9804812669754028, "global_step": 574683, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0448267459869385, "global_step": 574684, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.014065742492676, "global_step": 574685, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.075195789337158, "global_step": 574686, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.041722059249878, "global_step": 574687, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9505343437194824, "global_step": 574688, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.084207057952881, "global_step": 574689, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0708203315734863, "global_step": 574690, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.156203269958496, "global_step": 574691, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0296294689178467, "global_step": 574692, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0147111415863037, "global_step": 574693, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9659456014633179, "global_step": 574694, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0358235836029053, "global_step": 574695, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.978119134902954, "global_step": 574696, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.037271499633789, "global_step": 574697, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9338231086730957, "global_step": 574698, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9681804180145264, "global_step": 574699, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0314292907714844, "global_step": 574700, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.021458387374878, "global_step": 574701, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9857676029205322, "global_step": 574702, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.052659034729004, "global_step": 574703, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.068570613861084, "global_step": 574704, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9650824069976807, "global_step": 574705, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9797996282577515, "global_step": 574706, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0685548782348633, "global_step": 574707, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9466768503189087, "global_step": 574708, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.070629119873047, "global_step": 574709, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0686540603637695, "global_step": 574710, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.030707359313965, "global_step": 574711, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.982669472694397, "global_step": 574712, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0067391395568848, "global_step": 574713, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0237362384796143, "global_step": 574714, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.005660057067871, "global_step": 574715, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9097239971160889, "global_step": 574716, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9814109802246094, "global_step": 574717, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0607216358184814, "global_step": 574718, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0779879093170166, "global_step": 574719, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0395641326904297, "global_step": 574720, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.009920358657837, "global_step": 574721, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.087390422821045, "global_step": 574722, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9205892086029053, "global_step": 574723, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9702078104019165, "global_step": 574724, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.969286322593689, "global_step": 574725, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0891222953796387, "global_step": 574726, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9469923973083496, "global_step": 574727, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.023031711578369, "global_step": 574728, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.00661301612854, "global_step": 574729, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.126577615737915, "global_step": 574730, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.050809383392334, "global_step": 574731, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0882368087768555, "global_step": 574732, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.978023648262024, "global_step": 574733, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.102277994155884, "global_step": 574734, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9690853357315063, "global_step": 574735, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.02182936668396, "global_step": 574736, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.055828809738159, "global_step": 574737, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0295636653900146, "global_step": 574738, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.9737908840179443, "global_step": 574739, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0960581302642822, "global_step": 574740, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0784895420074463, "global_step": 574741, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0090322494506836, "global_step": 574742, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0650136470794678, "global_step": 574743, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0887022018432617, "global_step": 574744, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0643603801727295, "global_step": 574745, "epoch": 942, "lr": 5e-05}
{"train_loss": 1.979324460029602, "global_step": 574746, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0766987800598145, "global_step": 574747, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0240352153778076, "global_step": 574748, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.021993637084961, "global_step": 574749, "epoch": 942, "lr": 5e-05}
{"train_loss": 2.0132596492767334, "global_step": 574750, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.082442283630371, "global_step": 574751, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.995214819908142, "global_step": 574752, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0212347507476807, "global_step": 574753, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0159597396850586, "global_step": 574754, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0549471378326416, "global_step": 574755, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9276139736175537, "global_step": 574756, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9336748123168945, "global_step": 574757, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9725497961044312, "global_step": 574758, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9197837114334106, "global_step": 574759, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.8848496675491333, "global_step": 574760, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.974231243133545, "global_step": 574761, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9809247255325317, "global_step": 574762, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.065865993499756, "global_step": 574763, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9642822742462158, "global_step": 574764, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.084770917892456, "global_step": 574765, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9401271343231201, "global_step": 574766, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.067587375640869, "global_step": 574767, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.009587526321411, "global_step": 574768, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.076136827468872, "global_step": 574769, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9723659753799438, "global_step": 574770, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.953541874885559, "global_step": 574771, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0440585613250732, "global_step": 574772, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0665175914764404, "global_step": 574773, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0743322372436523, "global_step": 574774, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.984226942062378, "global_step": 574775, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0259900093078613, "global_step": 574776, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0475199222564697, "global_step": 574777, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.956592321395874, "global_step": 574778, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0056002140045166, "global_step": 574779, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0130703449249268, "global_step": 574780, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9614232778549194, "global_step": 574781, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.012887954711914, "global_step": 574782, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9430781602859497, "global_step": 574783, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0270938873291016, "global_step": 574784, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.054612398147583, "global_step": 574785, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.060870409011841, "global_step": 574786, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.055445909500122, "global_step": 574787, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9394279718399048, "global_step": 574788, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0137500762939453, "global_step": 574789, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.002138614654541, "global_step": 574790, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9589582681655884, "global_step": 574791, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0240538120269775, "global_step": 574792, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0236611366271973, "global_step": 574793, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9970526695251465, "global_step": 574794, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0731122493743896, "global_step": 574795, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0732994079589844, "global_step": 574796, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0094428062438965, "global_step": 574797, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9044945240020752, "global_step": 574798, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9752734899520874, "global_step": 574799, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.088881254196167, "global_step": 574800, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0151314735412598, "global_step": 574801, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0471556186676025, "global_step": 574802, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1220428943634033, "global_step": 574803, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0324814319610596, "global_step": 574804, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9033887386322021, "global_step": 574805, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9253357648849487, "global_step": 574806, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0508430004119873, "global_step": 574807, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9571301937103271, "global_step": 574808, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9325183629989624, "global_step": 574809, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9270517826080322, "global_step": 574810, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.969981074333191, "global_step": 574811, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0400753021240234, "global_step": 574812, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0395264625549316, "global_step": 574813, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9786667823791504, "global_step": 574814, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9185357093811035, "global_step": 574815, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.055623769760132, "global_step": 574816, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.959021806716919, "global_step": 574817, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0574302673339844, "global_step": 574818, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9737615585327148, "global_step": 574819, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0200178623199463, "global_step": 574820, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9617387056350708, "global_step": 574821, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0549659729003906, "global_step": 574822, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.860050916671753, "global_step": 574823, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0191848278045654, "global_step": 574824, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.117882013320923, "global_step": 574825, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0025393962860107, "global_step": 574826, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0022478103637695, "global_step": 574827, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9931182861328125, "global_step": 574828, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9898761510849, "global_step": 574829, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.060565233230591, "global_step": 574830, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9739080667495728, "global_step": 574831, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.000786781311035, "global_step": 574832, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.085803985595703, "global_step": 574833, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9851266145706177, "global_step": 574834, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9948127269744873, "global_step": 574835, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9951187372207642, "global_step": 574836, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.8503597974777222, "global_step": 574837, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.013972043991089, "global_step": 574838, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1074631214141846, "global_step": 574839, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0107264518737793, "global_step": 574840, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1074211597442627, "global_step": 574841, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.011476755142212, "global_step": 574842, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0201735496520996, "global_step": 574843, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.031381845474243, "global_step": 574844, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.946816086769104, "global_step": 574845, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9520078897476196, "global_step": 574846, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9974054098129272, "global_step": 574847, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0438640117645264, "global_step": 574848, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9924627542495728, "global_step": 574849, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9921903610229492, "global_step": 574850, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0301811695098877, "global_step": 574851, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0672616958618164, "global_step": 574852, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.078157663345337, "global_step": 574853, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0085761547088623, "global_step": 574854, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0186519622802734, "global_step": 574855, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.037588119506836, "global_step": 574856, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.083939552307129, "global_step": 574857, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0313880443573, "global_step": 574858, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.974035620689392, "global_step": 574859, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.956533432006836, "global_step": 574860, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.030597686767578, "global_step": 574861, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.94221830368042, "global_step": 574862, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.900767207145691, "global_step": 574863, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9284746646881104, "global_step": 574864, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9680349826812744, "global_step": 574865, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9923015832901, "global_step": 574866, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9310038089752197, "global_step": 574867, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9968668222427368, "global_step": 574868, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9896326065063477, "global_step": 574869, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.004296064376831, "global_step": 574870, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0359582901000977, "global_step": 574871, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0382320880889893, "global_step": 574872, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9962679147720337, "global_step": 574873, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0578157901763916, "global_step": 574874, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9824579954147339, "global_step": 574875, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.994046688079834, "global_step": 574876, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.059767723083496, "global_step": 574877, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9936083555221558, "global_step": 574878, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.956817626953125, "global_step": 574879, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.962117075920105, "global_step": 574880, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9381749629974365, "global_step": 574881, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0045323371887207, "global_step": 574882, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.026461601257324, "global_step": 574883, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0101046562194824, "global_step": 574884, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0691075325012207, "global_step": 574885, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.055924892425537, "global_step": 574886, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.961172103881836, "global_step": 574887, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0200083255767822, "global_step": 574888, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.913243055343628, "global_step": 574889, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9667692184448242, "global_step": 574890, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1598973274230957, "global_step": 574891, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9795185327529907, "global_step": 574892, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1016275882720947, "global_step": 574893, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0134596824645996, "global_step": 574894, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9997531175613403, "global_step": 574895, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0532495975494385, "global_step": 574896, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0433220863342285, "global_step": 574897, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.005340337753296, "global_step": 574898, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0265581607818604, "global_step": 574899, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.016806125640869, "global_step": 574900, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9604688882827759, "global_step": 574901, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9809026718139648, "global_step": 574902, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9812381267547607, "global_step": 574903, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.12223482131958, "global_step": 574904, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9794141054153442, "global_step": 574905, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0534706115722656, "global_step": 574906, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9962536096572876, "global_step": 574907, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0258095264434814, "global_step": 574908, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.002108097076416, "global_step": 574909, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0681159496307373, "global_step": 574910, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.053349018096924, "global_step": 574911, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0242536067962646, "global_step": 574912, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0021960735321045, "global_step": 574913, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0179195404052734, "global_step": 574914, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.077491521835327, "global_step": 574915, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0581579208374023, "global_step": 574916, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9987165927886963, "global_step": 574917, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9280753135681152, "global_step": 574918, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.060529947280884, "global_step": 574919, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.094247579574585, "global_step": 574920, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9921635389328003, "global_step": 574921, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9746781587600708, "global_step": 574922, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0368142127990723, "global_step": 574923, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0013837814331055, "global_step": 574924, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9778178930282593, "global_step": 574925, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0802764892578125, "global_step": 574926, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0022237300872803, "global_step": 574927, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0030107498168945, "global_step": 574928, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0573551654815674, "global_step": 574929, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.008730888366699, "global_step": 574930, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.03670072555542, "global_step": 574931, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9092756509780884, "global_step": 574932, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0177993774414062, "global_step": 574933, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.955268383026123, "global_step": 574934, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9334189891815186, "global_step": 574935, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0196573734283447, "global_step": 574936, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.004279851913452, "global_step": 574937, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9621721506118774, "global_step": 574938, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.051396608352661, "global_step": 574939, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.030108690261841, "global_step": 574940, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.053816318511963, "global_step": 574941, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.024770975112915, "global_step": 574942, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.979071855545044, "global_step": 574943, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0316002368927, "global_step": 574944, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0674593448638916, "global_step": 574945, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0174782276153564, "global_step": 574946, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.005859613418579, "global_step": 574947, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0155651569366455, "global_step": 574948, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.033860206604004, "global_step": 574949, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.019582509994507, "global_step": 574950, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0019659996032715, "global_step": 574951, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.054173231124878, "global_step": 574952, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0415537357330322, "global_step": 574953, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.012683868408203, "global_step": 574954, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.036738395690918, "global_step": 574955, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.993831753730774, "global_step": 574956, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.009141445159912, "global_step": 574957, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9974417686462402, "global_step": 574958, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.005830764770508, "global_step": 574959, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9586409330368042, "global_step": 574960, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.01096248626709, "global_step": 574961, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.060122013092041, "global_step": 574962, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9864517450332642, "global_step": 574963, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0824480056762695, "global_step": 574964, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.114729166030884, "global_step": 574965, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.090834140777588, "global_step": 574966, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0802202224731445, "global_step": 574967, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0776796340942383, "global_step": 574968, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.952252984046936, "global_step": 574969, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0560879707336426, "global_step": 574970, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.990248680114746, "global_step": 574971, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9955334663391113, "global_step": 574972, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.92978036403656, "global_step": 574973, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9937633275985718, "global_step": 574974, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9578790664672852, "global_step": 574975, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.018441677093506, "global_step": 574976, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9805264472961426, "global_step": 574977, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0422170162200928, "global_step": 574978, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9904028177261353, "global_step": 574979, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0555522441864014, "global_step": 574980, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.061063766479492, "global_step": 574981, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9978139400482178, "global_step": 574982, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9757192134857178, "global_step": 574983, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0229756832122803, "global_step": 574984, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9807357788085938, "global_step": 574985, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0282952785491943, "global_step": 574986, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.003013849258423, "global_step": 574987, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.028676986694336, "global_step": 574988, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9988081455230713, "global_step": 574989, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9398268461227417, "global_step": 574990, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0740272998809814, "global_step": 574991, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.08251690864563, "global_step": 574992, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9417638778686523, "global_step": 574993, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0196735858917236, "global_step": 574994, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9592578411102295, "global_step": 574995, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0739376544952393, "global_step": 574996, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0802881717681885, "global_step": 574997, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0023858547210693, "global_step": 574998, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0294885635375977, "global_step": 574999, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0690529346466064, "global_step": 575000, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0163729190826416, "global_step": 575001, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.067920207977295, "global_step": 575002, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9834542274475098, "global_step": 575003, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9860255718231201, "global_step": 575004, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9924547672271729, "global_step": 575005, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9965264797210693, "global_step": 575006, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.012674570083618, "global_step": 575007, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.004603147506714, "global_step": 575008, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.034426689147949, "global_step": 575009, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0443921089172363, "global_step": 575010, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9851081371307373, "global_step": 575011, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0322043895721436, "global_step": 575012, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0703697204589844, "global_step": 575013, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.008869171142578, "global_step": 575014, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.088315486907959, "global_step": 575015, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0012238025665283, "global_step": 575016, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0158698558807373, "global_step": 575017, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9853473901748657, "global_step": 575018, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0827362537384033, "global_step": 575019, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0448083877563477, "global_step": 575020, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9643361568450928, "global_step": 575021, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.00077486038208, "global_step": 575022, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9648913145065308, "global_step": 575023, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0522234439849854, "global_step": 575024, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0348355770111084, "global_step": 575025, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.015306234359741, "global_step": 575026, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.026702404022217, "global_step": 575027, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.994718074798584, "global_step": 575028, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.040435552597046, "global_step": 575029, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.016481876373291, "global_step": 575030, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.989708423614502, "global_step": 575031, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9894148111343384, "global_step": 575032, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9713640213012695, "global_step": 575033, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9697494506835938, "global_step": 575034, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0080833435058594, "global_step": 575035, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.98760986328125, "global_step": 575036, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.091520309448242, "global_step": 575037, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9514812231063843, "global_step": 575038, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.068514823913574, "global_step": 575039, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0586893558502197, "global_step": 575040, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9991230964660645, "global_step": 575041, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0499987602233887, "global_step": 575042, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.099074602127075, "global_step": 575043, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.098585367202759, "global_step": 575044, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.038388252258301, "global_step": 575045, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.972383737564087, "global_step": 575046, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0047357082366943, "global_step": 575047, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0092415809631348, "global_step": 575048, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0053491592407227, "global_step": 575049, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9678150415420532, "global_step": 575050, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0477607250213623, "global_step": 575051, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0391204357147217, "global_step": 575052, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.042449712753296, "global_step": 575053, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.039541006088257, "global_step": 575054, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.125420331954956, "global_step": 575055, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0179433822631836, "global_step": 575056, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.06524920463562, "global_step": 575057, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9885996580123901, "global_step": 575058, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.034677743911743, "global_step": 575059, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0604054927825928, "global_step": 575060, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9917675256729126, "global_step": 575061, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.059096574783325, "global_step": 575062, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9694119691848755, "global_step": 575063, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9780142307281494, "global_step": 575064, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9665937423706055, "global_step": 575065, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0018787384033203, "global_step": 575066, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.056091070175171, "global_step": 575067, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9498809576034546, "global_step": 575068, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9745622873306274, "global_step": 575069, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9371258020401, "global_step": 575070, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9956624507904053, "global_step": 575071, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0467545986175537, "global_step": 575072, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1093082427978516, "global_step": 575073, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0465548038482666, "global_step": 575074, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0301361083984375, "global_step": 575075, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.054983615875244, "global_step": 575076, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9713749885559082, "global_step": 575077, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.018071174621582, "global_step": 575078, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1586341857910156, "global_step": 575079, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0797441005706787, "global_step": 575080, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0215699672698975, "global_step": 575081, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1133005619049072, "global_step": 575082, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9939510822296143, "global_step": 575083, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0396807193756104, "global_step": 575084, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0938735008239746, "global_step": 575085, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9736220836639404, "global_step": 575086, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.951077938079834, "global_step": 575087, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.986670970916748, "global_step": 575088, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0667243003845215, "global_step": 575089, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0150394439697266, "global_step": 575090, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.983440637588501, "global_step": 575091, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0588245391845703, "global_step": 575092, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9536653757095337, "global_step": 575093, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.019418954849243, "global_step": 575094, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0036423206329346, "global_step": 575095, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.109998941421509, "global_step": 575096, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0283329486846924, "global_step": 575097, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9925700426101685, "global_step": 575098, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0103225708007812, "global_step": 575099, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.061145782470703, "global_step": 575100, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0449888706207275, "global_step": 575101, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.031816005706787, "global_step": 575102, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.044140100479126, "global_step": 575103, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9904711246490479, "global_step": 575104, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9983749389648438, "global_step": 575105, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0552823543548584, "global_step": 575106, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.011453866958618, "global_step": 575107, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0548722743988037, "global_step": 575108, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.043466806411743, "global_step": 575109, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.064995050430298, "global_step": 575110, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0465288162231445, "global_step": 575111, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0445938110351562, "global_step": 575112, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.003664493560791, "global_step": 575113, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9786701202392578, "global_step": 575114, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.023670196533203, "global_step": 575115, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9446433782577515, "global_step": 575116, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.074192523956299, "global_step": 575117, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9486409425735474, "global_step": 575118, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0848352909088135, "global_step": 575119, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.04571533203125, "global_step": 575120, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.93257474899292, "global_step": 575121, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9780614376068115, "global_step": 575122, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9443507194519043, "global_step": 575123, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0350091457366943, "global_step": 575124, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9679033756256104, "global_step": 575125, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0881810188293457, "global_step": 575126, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0235981941223145, "global_step": 575127, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.020220994949341, "global_step": 575128, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0689940452575684, "global_step": 575129, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.029442548751831, "global_step": 575130, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0247931480407715, "global_step": 575131, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.042633295059204, "global_step": 575132, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0438196659088135, "global_step": 575133, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0750179290771484, "global_step": 575134, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0093324184417725, "global_step": 575135, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.99726140499115, "global_step": 575136, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.992865800857544, "global_step": 575137, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9784903526306152, "global_step": 575138, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9723249673843384, "global_step": 575139, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0033481121063232, "global_step": 575140, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.087722063064575, "global_step": 575141, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9422203302383423, "global_step": 575142, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.025918960571289, "global_step": 575143, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0292234420776367, "global_step": 575144, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0291199684143066, "global_step": 575145, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0659618377685547, "global_step": 575146, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.064502477645874, "global_step": 575147, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.098362684249878, "global_step": 575148, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9706929922103882, "global_step": 575149, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.032515287399292, "global_step": 575150, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9926822185516357, "global_step": 575151, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0330471992492676, "global_step": 575152, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0352680683135986, "global_step": 575153, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9585140943527222, "global_step": 575154, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1159775257110596, "global_step": 575155, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9221603870391846, "global_step": 575156, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9597499370574951, "global_step": 575157, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.966188669204712, "global_step": 575158, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9958146810531616, "global_step": 575159, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.011539936065674, "global_step": 575160, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.037928342819214, "global_step": 575161, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.017055034637451, "global_step": 575162, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9419325590133667, "global_step": 575163, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0485737323760986, "global_step": 575164, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9868121147155762, "global_step": 575165, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9821816682815552, "global_step": 575166, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.001737594604492, "global_step": 575167, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0634238719940186, "global_step": 575168, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.029120922088623, "global_step": 575169, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9978961944580078, "global_step": 575170, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0495355129241943, "global_step": 575171, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0652382373809814, "global_step": 575172, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.002840042114258, "global_step": 575173, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0136663913726807, "global_step": 575174, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.041314125061035, "global_step": 575175, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0634398460388184, "global_step": 575176, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.019183397293091, "global_step": 575177, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0763323307037354, "global_step": 575178, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9942874908447266, "global_step": 575179, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0516810417175293, "global_step": 575180, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0439319610595703, "global_step": 575181, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.117762327194214, "global_step": 575182, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0104990005493164, "global_step": 575183, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9543390274047852, "global_step": 575184, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.069742202758789, "global_step": 575185, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.96379554271698, "global_step": 575186, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0212652683258057, "global_step": 575187, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9980744123458862, "global_step": 575188, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.056171417236328, "global_step": 575189, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.094777822494507, "global_step": 575190, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9809221029281616, "global_step": 575191, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.002838611602783, "global_step": 575192, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0354647636413574, "global_step": 575193, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1196229457855225, "global_step": 575194, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.057676315307617, "global_step": 575195, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0361735820770264, "global_step": 575196, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0106048583984375, "global_step": 575197, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.042476177215576, "global_step": 575198, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1049959659576416, "global_step": 575199, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1382360458374023, "global_step": 575200, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.029876232147217, "global_step": 575201, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9670130014419556, "global_step": 575202, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0088963508605957, "global_step": 575203, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.002401113510132, "global_step": 575204, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0053493976593018, "global_step": 575205, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.053041458129883, "global_step": 575206, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0679450035095215, "global_step": 575207, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.068727970123291, "global_step": 575208, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.087470531463623, "global_step": 575209, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0830905437469482, "global_step": 575210, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.062004327774048, "global_step": 575211, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.127849578857422, "global_step": 575212, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0286264419555664, "global_step": 575213, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0019965171813965, "global_step": 575214, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0163979530334473, "global_step": 575215, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.003756046295166, "global_step": 575216, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0165328979492188, "global_step": 575217, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9178168773651123, "global_step": 575218, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0088841915130615, "global_step": 575219, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0068788528442383, "global_step": 575220, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.032879590988159, "global_step": 575221, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0543553829193115, "global_step": 575222, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0284409523010254, "global_step": 575223, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0122320652008057, "global_step": 575224, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0273044109344482, "global_step": 575225, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1229207515716553, "global_step": 575226, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.086216688156128, "global_step": 575227, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.030651569366455, "global_step": 575228, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0383119583129883, "global_step": 575229, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0373363494873047, "global_step": 575230, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0783872604370117, "global_step": 575231, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0987977981567383, "global_step": 575232, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0547711849212646, "global_step": 575233, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0314319133758545, "global_step": 575234, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.026266574859619, "global_step": 575235, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9985265731811523, "global_step": 575236, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.950287103652954, "global_step": 575237, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0457863807678223, "global_step": 575238, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0880563259124756, "global_step": 575239, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0239133834838867, "global_step": 575240, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0063366889953613, "global_step": 575241, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.092146158218384, "global_step": 575242, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.026655435562134, "global_step": 575243, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0558345317840576, "global_step": 575244, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0177011489868164, "global_step": 575245, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.066070079803467, "global_step": 575246, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.084085702896118, "global_step": 575247, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0857656002044678, "global_step": 575248, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0484399795532227, "global_step": 575249, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.028151512145996, "global_step": 575250, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0924510955810547, "global_step": 575251, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9847224950790405, "global_step": 575252, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9974533319473267, "global_step": 575253, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1554789543151855, "global_step": 575254, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0567398071289062, "global_step": 575255, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9915999174118042, "global_step": 575256, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.984445571899414, "global_step": 575257, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9938684701919556, "global_step": 575258, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0133721828460693, "global_step": 575259, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0112884044647217, "global_step": 575260, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0622475147247314, "global_step": 575261, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9484632015228271, "global_step": 575262, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.014857530593872, "global_step": 575263, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.034363031387329, "global_step": 575264, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.042285442352295, "global_step": 575265, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9946401119232178, "global_step": 575266, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0064311027526855, "global_step": 575267, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0360538959503174, "global_step": 575268, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.003495693206787, "global_step": 575269, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0511562824249268, "global_step": 575270, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0514743328094482, "global_step": 575271, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0650951862335205, "global_step": 575272, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.003002643585205, "global_step": 575273, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0383267402648926, "global_step": 575274, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9256364107131958, "global_step": 575275, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0677785873413086, "global_step": 575276, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9973645210266113, "global_step": 575277, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0395314693450928, "global_step": 575278, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0246095657348633, "global_step": 575279, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9588251113891602, "global_step": 575280, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0879077911376953, "global_step": 575281, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0316193103790283, "global_step": 575282, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0156466960906982, "global_step": 575283, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.958719253540039, "global_step": 575284, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0313944816589355, "global_step": 575285, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9696234464645386, "global_step": 575286, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9528710842132568, "global_step": 575287, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0463898181915283, "global_step": 575288, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.051978349685669, "global_step": 575289, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.024486780166626, "global_step": 575290, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9685695171356201, "global_step": 575291, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.04276180267334, "global_step": 575292, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0133981704711914, "global_step": 575293, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9928961992263794, "global_step": 575294, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.029916763305664, "global_step": 575295, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9767558574676514, "global_step": 575296, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.071800470352173, "global_step": 575297, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0050370693206787, "global_step": 575298, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.073923349380493, "global_step": 575299, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1419219970703125, "global_step": 575300, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.944181203842163, "global_step": 575301, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1363131999969482, "global_step": 575302, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.995711088180542, "global_step": 575303, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9943090677261353, "global_step": 575304, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9716887474060059, "global_step": 575305, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9808942079544067, "global_step": 575306, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0473663806915283, "global_step": 575307, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0032432079315186, "global_step": 575308, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0578224658966064, "global_step": 575309, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9486802816390991, "global_step": 575310, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.071831703186035, "global_step": 575311, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0042202472686768, "global_step": 575312, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9827930927276611, "global_step": 575313, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.033231496810913, "global_step": 575314, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.989246129989624, "global_step": 575315, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.958764672279358, "global_step": 575316, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0309031009674072, "global_step": 575317, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9344007968902588, "global_step": 575318, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0649664402008057, "global_step": 575319, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9897183179855347, "global_step": 575320, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.014686107635498, "global_step": 575321, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.012211799621582, "global_step": 575322, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0232021808624268, "global_step": 575323, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0695409774780273, "global_step": 575324, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9313410520553589, "global_step": 575325, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0613021850585938, "global_step": 575326, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.06050705909729, "global_step": 575327, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0547428131103516, "global_step": 575328, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0892841815948486, "global_step": 575329, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.05570912361145, "global_step": 575330, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.054802656173706, "global_step": 575331, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.028216600418091, "global_step": 575332, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0138518810272217, "global_step": 575333, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9675614833831787, "global_step": 575334, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0011000633239746, "global_step": 575335, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.016267776489258, "global_step": 575336, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.961788296699524, "global_step": 575337, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.972426414489746, "global_step": 575338, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.060546398162842, "global_step": 575339, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.004784345626831, "global_step": 575340, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9788720607757568, "global_step": 575341, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1021692752838135, "global_step": 575342, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.031517267227173, "global_step": 575343, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0379910469055176, "global_step": 575344, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0694997310638428, "global_step": 575345, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.935422658920288, "global_step": 575346, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0397489070892334, "global_step": 575347, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0021541118621826, "global_step": 575348, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9861794710159302, "global_step": 575349, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.039482831954956, "global_step": 575350, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9958921670913696, "global_step": 575351, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9557348489761353, "global_step": 575352, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0320472717285156, "global_step": 575353, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0557382106781006, "global_step": 575354, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0116426944732666, "global_step": 575355, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0612473487854004, "global_step": 575356, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.075169086456299, "global_step": 575357, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0656371116638184, "global_step": 575358, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0320773124694824, "global_step": 575359, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.02286434173584, "global_step": 575360, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0354039669036865, "global_step": 575361, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0215444564819336, "global_step": 575362, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0166711807250977, "global_step": 575363, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9608569145202637, "global_step": 575364, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0582468509674072, "global_step": 575365, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.055004835128784, "global_step": 575366, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0657663345336914, "global_step": 575367, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0642590522766113, "global_step": 575368, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9914426803588867, "global_step": 575369, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0361850261688232, "global_step": 575370, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0270891189575195, "global_step": 575371, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.071385622024536, "global_step": 575372, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.025181531906128, "global_step": 575373, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.978893518447876, "global_step": 575374, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0792553424835205, "global_step": 575375, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9747496843338013, "global_step": 575376, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0278162956237793, "global_step": 575377, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.026897430419922, "global_step": 575378, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.902691125869751, "global_step": 575379, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.050640106201172, "global_step": 575380, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0461504459381104, "global_step": 575381, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0078094005584717, "global_step": 575382, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.071718215942383, "global_step": 575383, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0165905952453613, "global_step": 575384, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.014707565307617, "global_step": 575385, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0077481269836426, "global_step": 575386, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9516206979751587, "global_step": 575387, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1224324703216553, "global_step": 575388, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9505454301834106, "global_step": 575389, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0232884883880615, "global_step": 575390, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.034595012664795, "global_step": 575391, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9989334344863892, "global_step": 575392, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.017317295074463, "global_step": 575393, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9578156471252441, "global_step": 575394, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.039085626602173, "global_step": 575395, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0223026275634766, "global_step": 575396, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.01743221282959, "global_step": 575397, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.992946982383728, "global_step": 575398, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.005328416824341, "global_step": 575399, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9668909311294556, "global_step": 575400, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.982115387916565, "global_step": 575401, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.056260108947754, "global_step": 575402, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.019171714782715, "global_step": 575403, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0131993293762207, "global_step": 575404, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9485204219818115, "global_step": 575405, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0213146209716797, "global_step": 575406, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0005500316619873, "global_step": 575407, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0453402996063232, "global_step": 575408, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.131047010421753, "global_step": 575409, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.06498646736145, "global_step": 575410, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.026885509490967, "global_step": 575411, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9998198747634888, "global_step": 575412, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.094327688217163, "global_step": 575413, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0556230545043945, "global_step": 575414, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9464174509048462, "global_step": 575415, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0860323905944824, "global_step": 575416, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0721535682678223, "global_step": 575417, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.8786736726760864, "global_step": 575418, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1210267543792725, "global_step": 575419, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9491840600967407, "global_step": 575420, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.118748188018799, "global_step": 575421, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9737279415130615, "global_step": 575422, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0296449661254883, "global_step": 575423, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0831050872802734, "global_step": 575424, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0056936740875244, "global_step": 575425, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.941732406616211, "global_step": 575426, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.994493007659912, "global_step": 575427, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0519626140594482, "global_step": 575428, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.030862808227539, "global_step": 575429, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0799427032470703, "global_step": 575430, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.03733229637146, "global_step": 575431, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0230298042297363, "global_step": 575432, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0036559104919434, "global_step": 575433, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.021390676498413, "global_step": 575434, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0777323246002197, "global_step": 575435, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1172518730163574, "global_step": 575436, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.084317922592163, "global_step": 575437, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0006589889526367, "global_step": 575438, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.086519479751587, "global_step": 575439, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.057480573654175, "global_step": 575440, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.021430730819702, "global_step": 575441, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9296808242797852, "global_step": 575442, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9760708808898926, "global_step": 575443, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0164201259613037, "global_step": 575444, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0356266498565674, "global_step": 575445, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.055534839630127, "global_step": 575446, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.055419445037842, "global_step": 575447, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9831206798553467, "global_step": 575448, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9569205045700073, "global_step": 575449, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.990839958190918, "global_step": 575450, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.020805597305298, "global_step": 575451, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9657392501831055, "global_step": 575452, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0428333282470703, "global_step": 575453, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0595123767852783, "global_step": 575454, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0950050354003906, "global_step": 575455, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0369186401367188, "global_step": 575456, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0906741619110107, "global_step": 575457, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9971832036972046, "global_step": 575458, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.000434160232544, "global_step": 575459, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.030320644378662, "global_step": 575460, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9880348443984985, "global_step": 575461, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.026653528213501, "global_step": 575462, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9849873781204224, "global_step": 575463, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0813658237457275, "global_step": 575464, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0276997089385986, "global_step": 575465, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9043331146240234, "global_step": 575466, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.059619903564453, "global_step": 575467, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0280325412750244, "global_step": 575468, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0574092864990234, "global_step": 575469, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0185155868530273, "global_step": 575470, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0415050983428955, "global_step": 575471, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9997342824935913, "global_step": 575472, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.036468744277954, "global_step": 575473, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0037901401519775, "global_step": 575474, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9999760389328003, "global_step": 575475, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0600764751434326, "global_step": 575476, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9500786066055298, "global_step": 575477, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0323381423950195, "global_step": 575478, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9916497468948364, "global_step": 575479, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.088407039642334, "global_step": 575480, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9595650434494019, "global_step": 575481, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9824944734573364, "global_step": 575482, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.05574369430542, "global_step": 575483, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.098942279815674, "global_step": 575484, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.026524543762207, "global_step": 575485, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.062598466873169, "global_step": 575486, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1293883323669434, "global_step": 575487, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.955406665802002, "global_step": 575488, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0227761268615723, "global_step": 575489, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9697167873382568, "global_step": 575490, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.962621808052063, "global_step": 575491, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0687811374664307, "global_step": 575492, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.060134172439575, "global_step": 575493, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0073792934417725, "global_step": 575494, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0575296878814697, "global_step": 575495, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0645289421081543, "global_step": 575496, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9240206480026245, "global_step": 575497, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0654542446136475, "global_step": 575498, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9978368282318115, "global_step": 575499, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.033531904220581, "global_step": 575500, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.924743890762329, "global_step": 575501, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0755579471588135, "global_step": 575502, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0426692962646484, "global_step": 575503, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.130512237548828, "global_step": 575504, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9357850551605225, "global_step": 575505, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.993682622909546, "global_step": 575506, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.077343702316284, "global_step": 575507, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0836243629455566, "global_step": 575508, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0513713359832764, "global_step": 575509, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0079426765441895, "global_step": 575510, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0846714973449707, "global_step": 575511, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9795303344726562, "global_step": 575512, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.133932113647461, "global_step": 575513, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0110623836517334, "global_step": 575514, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1168997287750244, "global_step": 575515, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1615488529205322, "global_step": 575516, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0274012088775635, "global_step": 575517, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.052018404006958, "global_step": 575518, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.037445545196533, "global_step": 575519, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.039700984954834, "global_step": 575520, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.026082754135132, "global_step": 575521, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0327718257904053, "global_step": 575522, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.022552013397217, "global_step": 575523, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0778729915618896, "global_step": 575524, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0925941467285156, "global_step": 575525, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0308022499084473, "global_step": 575526, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.027944803237915, "global_step": 575527, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0148653984069824, "global_step": 575528, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0012030601501465, "global_step": 575529, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.012916088104248, "global_step": 575530, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.076404094696045, "global_step": 575531, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9947361946105957, "global_step": 575532, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.02478289604187, "global_step": 575533, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.076117992401123, "global_step": 575534, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0957014560699463, "global_step": 575535, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.014932870864868, "global_step": 575536, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.999794840812683, "global_step": 575537, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0082948207855225, "global_step": 575538, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.935643196105957, "global_step": 575539, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0398550033569336, "global_step": 575540, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0956814289093018, "global_step": 575541, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0721168518066406, "global_step": 575542, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9723223447799683, "global_step": 575543, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0931601524353027, "global_step": 575544, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.061379909515381, "global_step": 575545, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.013950824737549, "global_step": 575546, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0251376628875732, "global_step": 575547, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1468396186828613, "global_step": 575548, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.017490863800049, "global_step": 575549, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.021838903427124, "global_step": 575550, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0606281757354736, "global_step": 575551, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0323071479797363, "global_step": 575552, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.088423252105713, "global_step": 575553, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9842479228973389, "global_step": 575554, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.138519763946533, "global_step": 575555, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0470893383026123, "global_step": 575556, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0078821182250977, "global_step": 575557, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9916175603866577, "global_step": 575558, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.131812334060669, "global_step": 575559, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0477135181427, "global_step": 575560, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.02754807472229, "global_step": 575561, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.083566188812256, "global_step": 575562, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9723442792892456, "global_step": 575563, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.999377965927124, "global_step": 575564, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0119211673736572, "global_step": 575565, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0116360187530518, "global_step": 575566, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9816786050796509, "global_step": 575567, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0798521041870117, "global_step": 575568, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0392463207244873, "global_step": 575569, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.026951789855957, "global_step": 575570, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.088031530380249, "global_step": 575571, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.155673027038574, "global_step": 575572, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.057138681411743, "global_step": 575573, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9739614725112915, "global_step": 575574, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.946193814277649, "global_step": 575575, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0093722343444824, "global_step": 575576, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.038234233856201, "global_step": 575577, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0603060722351074, "global_step": 575578, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0361366271972656, "global_step": 575579, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.178687810897827, "global_step": 575580, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.084104537963867, "global_step": 575581, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0293056964874268, "global_step": 575582, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0378365516662598, "global_step": 575583, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0348012447357178, "global_step": 575584, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0596301555633545, "global_step": 575585, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9561710357666016, "global_step": 575586, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0537197589874268, "global_step": 575587, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0880937576293945, "global_step": 575588, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9565914869308472, "global_step": 575589, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9562156200408936, "global_step": 575590, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9136184453964233, "global_step": 575591, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0704684257507324, "global_step": 575592, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.080623149871826, "global_step": 575593, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0373528003692627, "global_step": 575594, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9812674522399902, "global_step": 575595, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.027226209640503, "global_step": 575596, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9669617414474487, "global_step": 575597, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0391368865966797, "global_step": 575598, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0066070556640625, "global_step": 575599, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.011260986328125, "global_step": 575600, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0443220138549805, "global_step": 575601, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0580029487609863, "global_step": 575602, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1153101921081543, "global_step": 575603, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.082149028778076, "global_step": 575604, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.017977714538574, "global_step": 575605, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0774831771850586, "global_step": 575606, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0916953086853027, "global_step": 575607, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9964849948883057, "global_step": 575608, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9946510791778564, "global_step": 575609, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.057903528213501, "global_step": 575610, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.011559247970581, "global_step": 575611, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9955347776412964, "global_step": 575612, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.8599236011505127, "global_step": 575613, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9916329383850098, "global_step": 575614, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9070007801055908, "global_step": 575615, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1022772789001465, "global_step": 575616, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0406947135925293, "global_step": 575617, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0475895404815674, "global_step": 575618, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0562283992767334, "global_step": 575619, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.995528221130371, "global_step": 575620, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.021456480026245, "global_step": 575621, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0435235500335693, "global_step": 575622, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.972034215927124, "global_step": 575623, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0641632080078125, "global_step": 575624, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1040725708007812, "global_step": 575625, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9882382154464722, "global_step": 575626, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.030346632003784, "global_step": 575627, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.092766046524048, "global_step": 575628, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0275208950042725, "global_step": 575629, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1184778213500977, "global_step": 575630, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0577023029327393, "global_step": 575631, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.059840202331543, "global_step": 575632, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.048090696334839, "global_step": 575633, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.054358720779419, "global_step": 575634, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9809062480926514, "global_step": 575635, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.021838903427124, "global_step": 575636, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.975171685218811, "global_step": 575637, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.035024404525757, "global_step": 575638, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.977996587753296, "global_step": 575639, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0527098178863525, "global_step": 575640, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0825297832489014, "global_step": 575641, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9338997602462769, "global_step": 575642, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0356712341308594, "global_step": 575643, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.003126621246338, "global_step": 575644, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0360047817230225, "global_step": 575645, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.102677583694458, "global_step": 575646, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0685791969299316, "global_step": 575647, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9583625793457031, "global_step": 575648, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9672306776046753, "global_step": 575649, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.039116382598877, "global_step": 575650, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9943671226501465, "global_step": 575651, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9690122604370117, "global_step": 575652, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0604047775268555, "global_step": 575653, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0344934463500977, "global_step": 575654, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.029277801513672, "global_step": 575655, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.026068687438965, "global_step": 575656, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.054069995880127, "global_step": 575657, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9902554750442505, "global_step": 575658, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.8985868692398071, "global_step": 575659, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1041574478149414, "global_step": 575660, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0554280281066895, "global_step": 575661, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.043149709701538, "global_step": 575662, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1313247680664062, "global_step": 575663, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.060080051422119, "global_step": 575664, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.104820966720581, "global_step": 575665, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0506420135498047, "global_step": 575666, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.024157762527466, "global_step": 575667, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.047241687774658, "global_step": 575668, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.045328378677368, "global_step": 575669, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.081296682357788, "global_step": 575670, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0081045627593994, "global_step": 575671, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0574796199798584, "global_step": 575672, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9958839416503906, "global_step": 575673, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0641796588897705, "global_step": 575674, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.046844959259033, "global_step": 575675, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0896191596984863, "global_step": 575676, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0100626945495605, "global_step": 575677, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9557393789291382, "global_step": 575678, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9996942281723022, "global_step": 575679, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0204150676727295, "global_step": 575680, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9942448139190674, "global_step": 575681, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9277336597442627, "global_step": 575682, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9402815103530884, "global_step": 575683, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0594451427459717, "global_step": 575684, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0377702713012695, "global_step": 575685, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.005506753921509, "global_step": 575686, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.959620714187622, "global_step": 575687, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0471580028533936, "global_step": 575688, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.049278497695923, "global_step": 575689, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9986340999603271, "global_step": 575690, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.996801495552063, "global_step": 575691, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0082507133483887, "global_step": 575692, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.074176549911499, "global_step": 575693, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9510489702224731, "global_step": 575694, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1048543453216553, "global_step": 575695, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0215325355529785, "global_step": 575696, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0327913761138916, "global_step": 575697, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.991417407989502, "global_step": 575698, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0228307247161865, "global_step": 575699, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.012615203857422, "global_step": 575700, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0631439685821533, "global_step": 575701, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.071577310562134, "global_step": 575702, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.075815200805664, "global_step": 575703, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0558509826660156, "global_step": 575704, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9841233491897583, "global_step": 575705, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.080819845199585, "global_step": 575706, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.965856909751892, "global_step": 575707, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0599915981292725, "global_step": 575708, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0082831382751465, "global_step": 575709, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0409746170043945, "global_step": 575710, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.067481279373169, "global_step": 575711, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.997348427772522, "global_step": 575712, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.1113381385803223, "global_step": 575713, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.009895086288452, "global_step": 575714, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9838200807571411, "global_step": 575715, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0487794876098633, "global_step": 575716, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0302000045776367, "global_step": 575717, "epoch": 943, "lr": 5e-05}
{"train_loss": 2.0227277278900146, "global_step": 575718, "epoch": 943, "lr": 5e-05}
{"train_loss": 1.9913063049316406, "global_step": 575719, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0017073154449463, "global_step": 575720, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9712190628051758, "global_step": 575721, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9885141849517822, "global_step": 575722, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9739395380020142, "global_step": 575723, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.074619770050049, "global_step": 575724, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0749471187591553, "global_step": 575725, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0316367149353027, "global_step": 575726, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.069969654083252, "global_step": 575727, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.062959671020508, "global_step": 575728, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9961565732955933, "global_step": 575729, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.056614398956299, "global_step": 575730, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.03892183303833, "global_step": 575731, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0606865882873535, "global_step": 575732, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9646365642547607, "global_step": 575733, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9467074871063232, "global_step": 575734, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0662732124328613, "global_step": 575735, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9672844409942627, "global_step": 575736, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9979032278060913, "global_step": 575737, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9921895265579224, "global_step": 575738, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0553812980651855, "global_step": 575739, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0258960723876953, "global_step": 575740, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.006566047668457, "global_step": 575741, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.01829195022583, "global_step": 575742, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.023021936416626, "global_step": 575743, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0379765033721924, "global_step": 575744, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.034515619277954, "global_step": 575745, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9727226495742798, "global_step": 575746, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9729276895523071, "global_step": 575747, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.015630006790161, "global_step": 575748, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0497689247131348, "global_step": 575749, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1345536708831787, "global_step": 575750, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.98980712890625, "global_step": 575751, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0651798248291016, "global_step": 575752, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9584072828292847, "global_step": 575753, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9864387512207031, "global_step": 575754, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9491961002349854, "global_step": 575755, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0536890029907227, "global_step": 575756, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.024404287338257, "global_step": 575757, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.966214895248413, "global_step": 575758, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0025436878204346, "global_step": 575759, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9949440956115723, "global_step": 575760, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0523276329040527, "global_step": 575761, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.004711866378784, "global_step": 575762, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0219364166259766, "global_step": 575763, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.950562596321106, "global_step": 575764, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0078659057617188, "global_step": 575765, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9483555555343628, "global_step": 575766, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9574071168899536, "global_step": 575767, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0422134399414062, "global_step": 575768, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0359675884246826, "global_step": 575769, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1132636070251465, "global_step": 575770, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9524754285812378, "global_step": 575771, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0382192134857178, "global_step": 575772, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9646357297897339, "global_step": 575773, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0312891006469727, "global_step": 575774, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.047252893447876, "global_step": 575775, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9930155277252197, "global_step": 575776, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9918967485427856, "global_step": 575777, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9665271043777466, "global_step": 575778, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9753758907318115, "global_step": 575779, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9243444204330444, "global_step": 575780, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.080775260925293, "global_step": 575781, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9960089921951294, "global_step": 575782, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9403237104415894, "global_step": 575783, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.003410816192627, "global_step": 575784, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.000049352645874, "global_step": 575785, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.033407211303711, "global_step": 575786, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.057040214538574, "global_step": 575787, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.024600028991699, "global_step": 575788, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.006324291229248, "global_step": 575789, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9790290594100952, "global_step": 575790, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0221524238586426, "global_step": 575791, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.944483995437622, "global_step": 575792, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0070362091064453, "global_step": 575793, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.035041332244873, "global_step": 575794, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.989106297492981, "global_step": 575795, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9783340692520142, "global_step": 575796, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0007731914520264, "global_step": 575797, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.001742124557495, "global_step": 575798, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0027272701263428, "global_step": 575799, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.98038649559021, "global_step": 575800, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0230937004089355, "global_step": 575801, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0473766326904297, "global_step": 575802, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0342509746551514, "global_step": 575803, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.936719536781311, "global_step": 575804, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9512110948562622, "global_step": 575805, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.011536121368408, "global_step": 575806, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9898033142089844, "global_step": 575807, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.048405408859253, "global_step": 575808, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.009937286376953, "global_step": 575809, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0087223052978516, "global_step": 575810, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9842549562454224, "global_step": 575811, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9876431226730347, "global_step": 575812, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.008793354034424, "global_step": 575813, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0747249126434326, "global_step": 575814, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.983583688735962, "global_step": 575815, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9591833353042603, "global_step": 575816, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0259456634521484, "global_step": 575817, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9688628911972046, "global_step": 575818, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.010312795639038, "global_step": 575819, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.018226385116577, "global_step": 575820, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9793412685394287, "global_step": 575821, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9956897497177124, "global_step": 575822, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9311764240264893, "global_step": 575823, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0158891677856445, "global_step": 575824, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.993394136428833, "global_step": 575825, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.076525926589966, "global_step": 575826, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.8918274641036987, "global_step": 575827, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.944062352180481, "global_step": 575828, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9234992265701294, "global_step": 575829, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0307226181030273, "global_step": 575830, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0007519721984863, "global_step": 575831, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9127367734909058, "global_step": 575832, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0002825260162354, "global_step": 575833, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9793074131011963, "global_step": 575834, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0359983444213867, "global_step": 575835, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9864505529403687, "global_step": 575836, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9797470569610596, "global_step": 575837, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.03950834274292, "global_step": 575838, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0198113918304443, "global_step": 575839, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.022615671157837, "global_step": 575840, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9424238204956055, "global_step": 575841, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0248539447784424, "global_step": 575842, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0262153148651123, "global_step": 575843, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0001118183135986, "global_step": 575844, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.898220181465149, "global_step": 575845, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0275604724884033, "global_step": 575846, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.025545120239258, "global_step": 575847, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.024259328842163, "global_step": 575848, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1006078720092773, "global_step": 575849, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0578911304473877, "global_step": 575850, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.041290521621704, "global_step": 575851, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9972689151763916, "global_step": 575852, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0990467071533203, "global_step": 575853, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0659432411193848, "global_step": 575854, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0334694385528564, "global_step": 575855, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.061553478240967, "global_step": 575856, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.013234853744507, "global_step": 575857, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.011756420135498, "global_step": 575858, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.007556200027466, "global_step": 575859, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0208094120025635, "global_step": 575860, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.02937388420105, "global_step": 575861, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1046624183654785, "global_step": 575862, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0525152683258057, "global_step": 575863, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9959806203842163, "global_step": 575864, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1070706844329834, "global_step": 575865, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0930941104888916, "global_step": 575866, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0603621006011963, "global_step": 575867, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9840004444122314, "global_step": 575868, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.052670955657959, "global_step": 575869, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9649826288223267, "global_step": 575870, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.050133228302002, "global_step": 575871, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.004828691482544, "global_step": 575872, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0407559871673584, "global_step": 575873, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.974268913269043, "global_step": 575874, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0801331996917725, "global_step": 575875, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0554516315460205, "global_step": 575876, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9216978549957275, "global_step": 575877, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9728951454162598, "global_step": 575878, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0290346145629883, "global_step": 575879, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.014598846435547, "global_step": 575880, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0509326457977295, "global_step": 575881, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0169615745544434, "global_step": 575882, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0342869758605957, "global_step": 575883, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.054957389831543, "global_step": 575884, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.018517017364502, "global_step": 575885, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0626935958862305, "global_step": 575886, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0362486839294434, "global_step": 575887, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.042673349380493, "global_step": 575888, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0158746242523193, "global_step": 575889, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.08742094039917, "global_step": 575890, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0460593700408936, "global_step": 575891, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.933772325515747, "global_step": 575892, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0492899417877197, "global_step": 575893, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.082840919494629, "global_step": 575894, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.05488657951355, "global_step": 575895, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.001800298690796, "global_step": 575896, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9508676528930664, "global_step": 575897, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9601929187774658, "global_step": 575898, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9679372310638428, "global_step": 575899, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.069474935531616, "global_step": 575900, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.128666877746582, "global_step": 575901, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0250654220581055, "global_step": 575902, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0218453407287598, "global_step": 575903, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9847111701965332, "global_step": 575904, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0205845832824707, "global_step": 575905, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.080474853515625, "global_step": 575906, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.035567283630371, "global_step": 575907, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.012129783630371, "global_step": 575908, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0196328163146973, "global_step": 575909, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9938732385635376, "global_step": 575910, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0339980125427246, "global_step": 575911, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9966593980789185, "global_step": 575912, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.015993118286133, "global_step": 575913, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.067739963531494, "global_step": 575914, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0244014263153076, "global_step": 575915, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0581681728363037, "global_step": 575916, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.011129856109619, "global_step": 575917, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9915146827697754, "global_step": 575918, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.911295771598816, "global_step": 575919, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1061246395111084, "global_step": 575920, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0199482440948486, "global_step": 575921, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.100862503051758, "global_step": 575922, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.045973539352417, "global_step": 575923, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.037426471710205, "global_step": 575924, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0404610633850098, "global_step": 575925, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9266493320465088, "global_step": 575926, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9855713844299316, "global_step": 575927, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.014282703399658, "global_step": 575928, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.014263868331909, "global_step": 575929, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0120410919189453, "global_step": 575930, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9809170961380005, "global_step": 575931, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0879247188568115, "global_step": 575932, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.094184160232544, "global_step": 575933, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.024853229522705, "global_step": 575934, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9794797897338867, "global_step": 575935, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9051933288574219, "global_step": 575936, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0621261596679688, "global_step": 575937, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0926880836486816, "global_step": 575938, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0115697383880615, "global_step": 575939, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9740763902664185, "global_step": 575940, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.996381163597107, "global_step": 575941, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0050206184387207, "global_step": 575942, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0450408458709717, "global_step": 575943, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.080899715423584, "global_step": 575944, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.000469446182251, "global_step": 575945, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0630850791931152, "global_step": 575946, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9464341402053833, "global_step": 575947, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.002923011779785, "global_step": 575948, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0129141807556152, "global_step": 575949, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0721397399902344, "global_step": 575950, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9628955125808716, "global_step": 575951, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0432214736938477, "global_step": 575952, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.023108959197998, "global_step": 575953, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.085634708404541, "global_step": 575954, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0219414234161377, "global_step": 575955, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.112849712371826, "global_step": 575956, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1445188522338867, "global_step": 575957, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0242366790771484, "global_step": 575958, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0092897415161133, "global_step": 575959, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.029129981994629, "global_step": 575960, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0288870334625244, "global_step": 575961, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9977030754089355, "global_step": 575962, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.041893720626831, "global_step": 575963, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9386504888534546, "global_step": 575964, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.078535318374634, "global_step": 575965, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0109331607818604, "global_step": 575966, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.072693109512329, "global_step": 575967, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.05537486076355, "global_step": 575968, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.024324893951416, "global_step": 575969, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1796507835388184, "global_step": 575970, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0957205295562744, "global_step": 575971, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9532814025878906, "global_step": 575972, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0951943397521973, "global_step": 575973, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0495336055755615, "global_step": 575974, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.04028582572937, "global_step": 575975, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0306613445281982, "global_step": 575976, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.03998064994812, "global_step": 575977, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.012845516204834, "global_step": 575978, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.989682674407959, "global_step": 575979, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.976161003112793, "global_step": 575980, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9511189460754395, "global_step": 575981, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.04489803314209, "global_step": 575982, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.039008140563965, "global_step": 575983, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9813328981399536, "global_step": 575984, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.129305601119995, "global_step": 575985, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.090421438217163, "global_step": 575986, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0397021770477295, "global_step": 575987, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.99443519115448, "global_step": 575988, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.003297805786133, "global_step": 575989, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0115506649017334, "global_step": 575990, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0671634674072266, "global_step": 575991, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0424349308013916, "global_step": 575992, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.005967378616333, "global_step": 575993, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.975569248199463, "global_step": 575994, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0980663299560547, "global_step": 575995, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.016846179962158, "global_step": 575996, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.100048065185547, "global_step": 575997, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.083805561065674, "global_step": 575998, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0773978233337402, "global_step": 575999, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0268311500549316, "global_step": 576000, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9427655935287476, "global_step": 576001, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0912938117980957, "global_step": 576002, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9928803443908691, "global_step": 576003, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.028721332550049, "global_step": 576004, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.002671957015991, "global_step": 576005, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9693431854248047, "global_step": 576006, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0284368991851807, "global_step": 576007, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0039401054382324, "global_step": 576008, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0924456119537354, "global_step": 576009, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9360493421554565, "global_step": 576010, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9909589290618896, "global_step": 576011, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0448687076568604, "global_step": 576012, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.086613893508911, "global_step": 576013, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.008979558944702, "global_step": 576014, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.028503894805908, "global_step": 576015, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.8952269554138184, "global_step": 576016, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0025501251220703, "global_step": 576017, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9937936067581177, "global_step": 576018, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0044760704040527, "global_step": 576019, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.002277135848999, "global_step": 576020, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0281882286071777, "global_step": 576021, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9342583417892456, "global_step": 576022, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0613245964050293, "global_step": 576023, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.117083787918091, "global_step": 576024, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0352120399475098, "global_step": 576025, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0451579093933105, "global_step": 576026, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9718044996261597, "global_step": 576027, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9884096384048462, "global_step": 576028, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9389313459396362, "global_step": 576029, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0321619510650635, "global_step": 576030, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9627219438552856, "global_step": 576031, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0401177406311035, "global_step": 576032, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0123507976531982, "global_step": 576033, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.010929584503174, "global_step": 576034, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.06198787689209, "global_step": 576035, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9716717004776, "global_step": 576036, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0068492889404297, "global_step": 576037, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0127384662628174, "global_step": 576038, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0397162437438965, "global_step": 576039, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0033977031707764, "global_step": 576040, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9810266494750977, "global_step": 576041, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9735183715820312, "global_step": 576042, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0396528244018555, "global_step": 576043, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.99567449092865, "global_step": 576044, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.008422613143921, "global_step": 576045, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0267186164855957, "global_step": 576046, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9939552545547485, "global_step": 576047, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.111626386642456, "global_step": 576048, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0300705432891846, "global_step": 576049, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9579170942306519, "global_step": 576050, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.049118757247925, "global_step": 576051, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.122699022293091, "global_step": 576052, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0866036415100098, "global_step": 576053, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0491209030151367, "global_step": 576054, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0237221717834473, "global_step": 576055, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.054074287414551, "global_step": 576056, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.103388786315918, "global_step": 576057, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0272927284240723, "global_step": 576058, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9887021780014038, "global_step": 576059, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0760276317596436, "global_step": 576060, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.028745651245117, "global_step": 576061, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.031843900680542, "global_step": 576062, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9999330043792725, "global_step": 576063, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.8949289321899414, "global_step": 576064, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0059142112731934, "global_step": 576065, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9781161546707153, "global_step": 576066, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9918341636657715, "global_step": 576067, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0102219581604004, "global_step": 576068, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.048248291015625, "global_step": 576069, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.922162413597107, "global_step": 576070, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9780062437057495, "global_step": 576071, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.033708333969116, "global_step": 576072, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.099771499633789, "global_step": 576073, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.046719551086426, "global_step": 576074, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9224539995193481, "global_step": 576075, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0982558727264404, "global_step": 576076, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9633170366287231, "global_step": 576077, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.992087960243225, "global_step": 576078, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0897345542907715, "global_step": 576079, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1301941871643066, "global_step": 576080, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.111387014389038, "global_step": 576081, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0610404014587402, "global_step": 576082, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9966251850128174, "global_step": 576083, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0991034507751465, "global_step": 576084, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9907206296920776, "global_step": 576085, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9685384035110474, "global_step": 576086, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9645249843597412, "global_step": 576087, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0575757026672363, "global_step": 576088, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.002168655395508, "global_step": 576089, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0780868530273438, "global_step": 576090, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9894886016845703, "global_step": 576091, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.097291946411133, "global_step": 576092, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9841291904449463, "global_step": 576093, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.969794511795044, "global_step": 576094, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.065425395965576, "global_step": 576095, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0488040447235107, "global_step": 576096, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9570980072021484, "global_step": 576097, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0475656986236572, "global_step": 576098, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.020627498626709, "global_step": 576099, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.954534649848938, "global_step": 576100, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.017512559890747, "global_step": 576101, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.009342908859253, "global_step": 576102, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0211548805236816, "global_step": 576103, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0631394386291504, "global_step": 576104, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9222601652145386, "global_step": 576105, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9941749572753906, "global_step": 576106, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0525870323181152, "global_step": 576107, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9856818914413452, "global_step": 576108, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0624265670776367, "global_step": 576109, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9503567218780518, "global_step": 576110, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9652169942855835, "global_step": 576111, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9437445402145386, "global_step": 576112, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.011045455932617, "global_step": 576113, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.080118417739868, "global_step": 576114, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0250351428985596, "global_step": 576115, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0367932319641113, "global_step": 576116, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0353119373321533, "global_step": 576117, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.000805377960205, "global_step": 576118, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9951953887939453, "global_step": 576119, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9737913608551025, "global_step": 576120, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0309505462646484, "global_step": 576121, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9773850440979004, "global_step": 576122, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0092902183532715, "global_step": 576123, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0689404010772705, "global_step": 576124, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.024437665939331, "global_step": 576125, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9430513381958008, "global_step": 576126, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.099992275238037, "global_step": 576127, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0895354747772217, "global_step": 576128, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0628323554992676, "global_step": 576129, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0529978275299072, "global_step": 576130, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.060009479522705, "global_step": 576131, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.050055503845215, "global_step": 576132, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0079829692840576, "global_step": 576133, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0645787715911865, "global_step": 576134, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0807178020477295, "global_step": 576135, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.097087860107422, "global_step": 576136, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.997854232788086, "global_step": 576137, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0425093173980713, "global_step": 576138, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.025604724884033, "global_step": 576139, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.035048007965088, "global_step": 576140, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9909383058547974, "global_step": 576141, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0552239418029785, "global_step": 576142, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.046426296234131, "global_step": 576143, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.984912395477295, "global_step": 576144, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0002057552337646, "global_step": 576145, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.072610378265381, "global_step": 576146, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.101344108581543, "global_step": 576147, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.8803808689117432, "global_step": 576148, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.01322340965271, "global_step": 576149, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0079116821289062, "global_step": 576150, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.058520555496216, "global_step": 576151, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9850162267684937, "global_step": 576152, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0803091526031494, "global_step": 576153, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9886879920959473, "global_step": 576154, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.915198564529419, "global_step": 576155, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0985076427459717, "global_step": 576156, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9687610864639282, "global_step": 576157, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9924697875976562, "global_step": 576158, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0909807682037354, "global_step": 576159, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.032134532928467, "global_step": 576160, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0156443119049072, "global_step": 576161, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0372695922851562, "global_step": 576162, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.083843946456909, "global_step": 576163, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9972524642944336, "global_step": 576164, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0228989124298096, "global_step": 576165, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.015104055404663, "global_step": 576166, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.8946139812469482, "global_step": 576167, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.007086992263794, "global_step": 576168, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9579977989196777, "global_step": 576169, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0926671028137207, "global_step": 576170, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.041754961013794, "global_step": 576171, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0816586017608643, "global_step": 576172, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.054734706878662, "global_step": 576173, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9657139778137207, "global_step": 576174, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9851869344711304, "global_step": 576175, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0532658100128174, "global_step": 576176, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0026662349700928, "global_step": 576177, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0500223636627197, "global_step": 576178, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0408718585968018, "global_step": 576179, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0401840209960938, "global_step": 576180, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.042665719985962, "global_step": 576181, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.000354766845703, "global_step": 576182, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0159249305725098, "global_step": 576183, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.07476806640625, "global_step": 576184, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.026855230331421, "global_step": 576185, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9857271909713745, "global_step": 576186, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.058936357498169, "global_step": 576187, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9261096715927124, "global_step": 576188, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0910680294036865, "global_step": 576189, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.039764642715454, "global_step": 576190, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.083043098449707, "global_step": 576191, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0327417850494385, "global_step": 576192, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9373005628585815, "global_step": 576193, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.042914390563965, "global_step": 576194, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0329058170318604, "global_step": 576195, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9550977945327759, "global_step": 576196, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.111640691757202, "global_step": 576197, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9695745706558228, "global_step": 576198, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0624570846557617, "global_step": 576199, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9945652484893799, "global_step": 576200, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.004263162612915, "global_step": 576201, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9490981101989746, "global_step": 576202, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9948762655258179, "global_step": 576203, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0286076068878174, "global_step": 576204, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0377910137176514, "global_step": 576205, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0559957027435303, "global_step": 576206, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9927740097045898, "global_step": 576207, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9727463722229004, "global_step": 576208, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1119658946990967, "global_step": 576209, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9740657806396484, "global_step": 576210, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.138298273086548, "global_step": 576211, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.973545789718628, "global_step": 576212, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.015012264251709, "global_step": 576213, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0110630989074707, "global_step": 576214, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0219318866729736, "global_step": 576215, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9904993772506714, "global_step": 576216, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.032055616378784, "global_step": 576217, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0197629928588867, "global_step": 576218, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.041745662689209, "global_step": 576219, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0918798446655273, "global_step": 576220, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9624886512756348, "global_step": 576221, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.061347246170044, "global_step": 576222, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.001894474029541, "global_step": 576223, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.015532970428467, "global_step": 576224, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.072514772415161, "global_step": 576225, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0066628456115723, "global_step": 576226, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0489203929901123, "global_step": 576227, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0741894245147705, "global_step": 576228, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0174922943115234, "global_step": 576229, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9718518257141113, "global_step": 576230, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9912110567092896, "global_step": 576231, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.974793791770935, "global_step": 576232, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9301694631576538, "global_step": 576233, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.063927412033081, "global_step": 576234, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9631917476654053, "global_step": 576235, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0091946125030518, "global_step": 576236, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.976423740386963, "global_step": 576237, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.091350793838501, "global_step": 576238, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.018770217895508, "global_step": 576239, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9602627754211426, "global_step": 576240, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0930891036987305, "global_step": 576241, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.999922752380371, "global_step": 576242, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0141758918762207, "global_step": 576243, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9843690395355225, "global_step": 576244, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1126415729522705, "global_step": 576245, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0318093299865723, "global_step": 576246, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0706334114074707, "global_step": 576247, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.048811435699463, "global_step": 576248, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9642728567123413, "global_step": 576249, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0513393878936768, "global_step": 576250, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0791592597961426, "global_step": 576251, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9651827812194824, "global_step": 576252, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0031306743621826, "global_step": 576253, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0684635639190674, "global_step": 576254, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.017448663711548, "global_step": 576255, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0395901203155518, "global_step": 576256, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9398937225341797, "global_step": 576257, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.902050256729126, "global_step": 576258, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.05047869682312, "global_step": 576259, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9910995960235596, "global_step": 576260, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9958869218826294, "global_step": 576261, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.009442090988159, "global_step": 576262, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9981474876403809, "global_step": 576263, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0289130210876465, "global_step": 576264, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.02227520942688, "global_step": 576265, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0417473316192627, "global_step": 576266, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9695966243743896, "global_step": 576267, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.018397092819214, "global_step": 576268, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.975592017173767, "global_step": 576269, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9654057025909424, "global_step": 576270, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9905821084976196, "global_step": 576271, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.041412591934204, "global_step": 576272, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0608503818511963, "global_step": 576273, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.916959285736084, "global_step": 576274, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9526606798171997, "global_step": 576275, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0261032581329346, "global_step": 576276, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.084517002105713, "global_step": 576277, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0178990364074707, "global_step": 576278, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0500423908233643, "global_step": 576279, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.963160753250122, "global_step": 576280, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.075493335723877, "global_step": 576281, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.027045965194702, "global_step": 576282, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9592595100402832, "global_step": 576283, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.041372776031494, "global_step": 576284, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0338680744171143, "global_step": 576285, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0781331062316895, "global_step": 576286, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0755832195281982, "global_step": 576287, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0364553928375244, "global_step": 576288, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0467684268951416, "global_step": 576289, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0067038536071777, "global_step": 576290, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.941444754600525, "global_step": 576291, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.017713785171509, "global_step": 576292, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0202298164367676, "global_step": 576293, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0959322452545166, "global_step": 576294, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9968940019607544, "global_step": 576295, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1094508171081543, "global_step": 576296, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9428329467773438, "global_step": 576297, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0487451553344727, "global_step": 576298, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.06166934967041, "global_step": 576299, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9783518314361572, "global_step": 576300, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9990051984786987, "global_step": 576301, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9853332042694092, "global_step": 576302, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0186727046966553, "global_step": 576303, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9171808958053589, "global_step": 576304, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9697809219360352, "global_step": 576305, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9662394523620605, "global_step": 576306, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.012296438217163, "global_step": 576307, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.116398811340332, "global_step": 576308, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0710935592651367, "global_step": 576309, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.012115478515625, "global_step": 576310, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9884421825408936, "global_step": 576311, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.110854387283325, "global_step": 576312, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.12886381149292, "global_step": 576313, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0667805671691895, "global_step": 576314, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.027212142944336, "global_step": 576315, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0894320011138916, "global_step": 576316, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.972616195678711, "global_step": 576317, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.116389751434326, "global_step": 576318, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.079854965209961, "global_step": 576319, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.027557373046875, "global_step": 576320, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9954782724380493, "global_step": 576321, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9795429706573486, "global_step": 576322, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0139942169189453, "global_step": 576323, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0641682147979736, "global_step": 576324, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9769611358642578, "global_step": 576325, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.011687755584717, "global_step": 576326, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.025712490081787, "global_step": 576327, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9826480150222778, "global_step": 576328, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0766994953155518, "global_step": 576329, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.847190499305725, "global_step": 576330, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9713208675384521, "global_step": 576331, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.003885269165039, "global_step": 576332, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0294384956359863, "global_step": 576333, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.039412021636963, "global_step": 576334, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9666082859039307, "global_step": 576335, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0300025939941406, "global_step": 576336, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.044581890106201, "global_step": 576337, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0360403060913086, "global_step": 576338, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.912055253982544, "global_step": 576339, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.027224063873291, "global_step": 576340, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0694117546081543, "global_step": 576341, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1234986782073975, "global_step": 576342, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0300350189208984, "global_step": 576343, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0884106159210205, "global_step": 576344, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.023536205291748, "global_step": 576345, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9717530012130737, "global_step": 576346, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0519795417785645, "global_step": 576347, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0816245079040527, "global_step": 576348, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9896695613861084, "global_step": 576349, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1310391426086426, "global_step": 576350, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9565883874893188, "global_step": 576351, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9166537523269653, "global_step": 576352, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0123183727264404, "global_step": 576353, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.064162492752075, "global_step": 576354, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.999085545539856, "global_step": 576355, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9464138746261597, "global_step": 576356, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.072458028793335, "global_step": 576357, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.028904438018799, "global_step": 576358, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0147647857666016, "global_step": 576359, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0737040042877197, "global_step": 576360, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.009042978286743, "global_step": 576361, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0400898456573486, "global_step": 576362, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0368492603302, "global_step": 576363, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.986979603767395, "global_step": 576364, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9704320430755615, "global_step": 576365, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0073819160461426, "global_step": 576366, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0028462409973145, "global_step": 576367, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1701571941375732, "global_step": 576368, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9961682558059692, "global_step": 576369, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0077788829803467, "global_step": 576370, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.997320294380188, "global_step": 576371, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.049708366394043, "global_step": 576372, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9811559915542603, "global_step": 576373, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0006673336029053, "global_step": 576374, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.045712471008301, "global_step": 576375, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.938925862312317, "global_step": 576376, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9816473722457886, "global_step": 576377, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0569961071014404, "global_step": 576378, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0606462955474854, "global_step": 576379, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9846882820129395, "global_step": 576380, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0668623447418213, "global_step": 576381, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9972587823867798, "global_step": 576382, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.015451431274414, "global_step": 576383, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0134878158569336, "global_step": 576384, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9532668590545654, "global_step": 576385, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9260056018829346, "global_step": 576386, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.98317551612854, "global_step": 576387, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0229783058166504, "global_step": 576388, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9372578859329224, "global_step": 576389, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.052035093307495, "global_step": 576390, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0484437942504883, "global_step": 576391, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9825633764266968, "global_step": 576392, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9986860752105713, "global_step": 576393, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9825712442398071, "global_step": 576394, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0306272506713867, "global_step": 576395, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9939337968826294, "global_step": 576396, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0292716026306152, "global_step": 576397, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.037975549697876, "global_step": 576398, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.101536989212036, "global_step": 576399, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9845778942108154, "global_step": 576400, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.037522554397583, "global_step": 576401, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9936856031417847, "global_step": 576402, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.996789574623108, "global_step": 576403, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0091240406036377, "global_step": 576404, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.988261342048645, "global_step": 576405, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0510802268981934, "global_step": 576406, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.992556095123291, "global_step": 576407, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.105325698852539, "global_step": 576408, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9867664575576782, "global_step": 576409, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.00927472114563, "global_step": 576410, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0734379291534424, "global_step": 576411, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.017524003982544, "global_step": 576412, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9865838289260864, "global_step": 576413, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0551998615264893, "global_step": 576414, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0476667881011963, "global_step": 576415, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0392954349517822, "global_step": 576416, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.955258846282959, "global_step": 576417, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9476773738861084, "global_step": 576418, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9935963153839111, "global_step": 576419, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0075020790100098, "global_step": 576420, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.074021339416504, "global_step": 576421, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0228302478790283, "global_step": 576422, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0569064617156982, "global_step": 576423, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.091073751449585, "global_step": 576424, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0419156551361084, "global_step": 576425, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.047929286956787, "global_step": 576426, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9926151037216187, "global_step": 576427, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9997960329055786, "global_step": 576428, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0211479663848877, "global_step": 576429, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.092322587966919, "global_step": 576430, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0845232009887695, "global_step": 576431, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.036930561065674, "global_step": 576432, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9931062459945679, "global_step": 576433, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0190858840942383, "global_step": 576434, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9697879552841187, "global_step": 576435, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.004687786102295, "global_step": 576436, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.043829917907715, "global_step": 576437, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.070641279220581, "global_step": 576438, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9755009412765503, "global_step": 576439, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.055055856704712, "global_step": 576440, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.079122543334961, "global_step": 576441, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.061413049697876, "global_step": 576442, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.974665880203247, "global_step": 576443, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.890669345855713, "global_step": 576444, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.030395984649658, "global_step": 576445, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9042340517044067, "global_step": 576446, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0306756496429443, "global_step": 576447, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.089862108230591, "global_step": 576448, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9911924600601196, "global_step": 576449, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9854093790054321, "global_step": 576450, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0822207927703857, "global_step": 576451, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9497302770614624, "global_step": 576452, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1093358993530273, "global_step": 576453, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.946738362312317, "global_step": 576454, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0843899250030518, "global_step": 576455, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9276864528656006, "global_step": 576456, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9743095636367798, "global_step": 576457, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0000836849212646, "global_step": 576458, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0693507194519043, "global_step": 576459, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0780062675476074, "global_step": 576460, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0507543087005615, "global_step": 576461, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9607223272323608, "global_step": 576462, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0586559772491455, "global_step": 576463, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9687988758087158, "global_step": 576464, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0201056003570557, "global_step": 576465, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1383838653564453, "global_step": 576466, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9834519624710083, "global_step": 576467, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0012118816375732, "global_step": 576468, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0306081771850586, "global_step": 576469, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.058270215988159, "global_step": 576470, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.125379800796509, "global_step": 576471, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9636468887329102, "global_step": 576472, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.101586103439331, "global_step": 576473, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.00911545753479, "global_step": 576474, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.074270248413086, "global_step": 576475, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9657690525054932, "global_step": 576476, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.008547067642212, "global_step": 576477, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.075688123703003, "global_step": 576478, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0530495643615723, "global_step": 576479, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9730181694030762, "global_step": 576480, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.096550226211548, "global_step": 576481, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.088567018508911, "global_step": 576482, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0048584938049316, "global_step": 576483, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.022752523422241, "global_step": 576484, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9404867887496948, "global_step": 576485, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0626039505004883, "global_step": 576486, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0334324836730957, "global_step": 576487, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.034959316253662, "global_step": 576488, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.038365364074707, "global_step": 576489, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0412354469299316, "global_step": 576490, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9997025728225708, "global_step": 576491, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0369691848754883, "global_step": 576492, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1379566192626953, "global_step": 576493, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.093871831893921, "global_step": 576494, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.023815870285034, "global_step": 576495, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.027499198913574, "global_step": 576496, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.058920383453369, "global_step": 576497, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.003056764602661, "global_step": 576498, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9902856349945068, "global_step": 576499, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.068946123123169, "global_step": 576500, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.009948492050171, "global_step": 576501, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9879214763641357, "global_step": 576502, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9733525514602661, "global_step": 576503, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0576367378234863, "global_step": 576504, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9926656484603882, "global_step": 576505, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9332138299942017, "global_step": 576506, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.133772134780884, "global_step": 576507, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.079319715499878, "global_step": 576508, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0685160160064697, "global_step": 576509, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.076972484588623, "global_step": 576510, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.015777349472046, "global_step": 576511, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0511746406555176, "global_step": 576512, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0239806175231934, "global_step": 576513, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0630135536193848, "global_step": 576514, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0656070709228516, "global_step": 576515, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0923099517822266, "global_step": 576516, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0226902961730957, "global_step": 576517, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.008500099182129, "global_step": 576518, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0311100482940674, "global_step": 576519, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0723278522491455, "global_step": 576520, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0211050510406494, "global_step": 576521, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.049433708190918, "global_step": 576522, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0260326862335205, "global_step": 576523, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9175912141799927, "global_step": 576524, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0054757595062256, "global_step": 576525, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9669444561004639, "global_step": 576526, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.033285140991211, "global_step": 576527, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.131415367126465, "global_step": 576528, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0010738372802734, "global_step": 576529, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.092250347137451, "global_step": 576530, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.106677532196045, "global_step": 576531, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0406529903411865, "global_step": 576532, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0473856925964355, "global_step": 576533, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0154776573181152, "global_step": 576534, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.011723279953003, "global_step": 576535, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.033003568649292, "global_step": 576536, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.05625057220459, "global_step": 576537, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.058199644088745, "global_step": 576538, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0384480953216553, "global_step": 576539, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.006747245788574, "global_step": 576540, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9635533094406128, "global_step": 576541, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.054046392440796, "global_step": 576542, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.017404794692993, "global_step": 576543, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9656636714935303, "global_step": 576544, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9465051889419556, "global_step": 576545, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0675933361053467, "global_step": 576546, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.013587474822998, "global_step": 576547, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.053821086883545, "global_step": 576548, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.031306505203247, "global_step": 576549, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0607569217681885, "global_step": 576550, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9131468534469604, "global_step": 576551, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9596672058105469, "global_step": 576552, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1020333766937256, "global_step": 576553, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.09462308883667, "global_step": 576554, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.058652400970459, "global_step": 576555, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.030477285385132, "global_step": 576556, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9743473529815674, "global_step": 576557, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9992711544036865, "global_step": 576558, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0860326290130615, "global_step": 576559, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0022099018096924, "global_step": 576560, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9440393447875977, "global_step": 576561, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0372071266174316, "global_step": 576562, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.024622678756714, "global_step": 576563, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0034282207489014, "global_step": 576564, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.015195608139038, "global_step": 576565, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0976719856262207, "global_step": 576566, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.040013074874878, "global_step": 576567, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9578254222869873, "global_step": 576568, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.978358268737793, "global_step": 576569, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0072250366210938, "global_step": 576570, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.995739459991455, "global_step": 576571, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9899359941482544, "global_step": 576572, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9691611528396606, "global_step": 576573, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0949349403381348, "global_step": 576574, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0435681343078613, "global_step": 576575, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0062079429626465, "global_step": 576576, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9521583318710327, "global_step": 576577, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.943099021911621, "global_step": 576578, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.034681797027588, "global_step": 576579, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.04577898979187, "global_step": 576580, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.072793960571289, "global_step": 576581, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0448238849639893, "global_step": 576582, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9479163885116577, "global_step": 576583, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.020590305328369, "global_step": 576584, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.034968852996826, "global_step": 576585, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0719876289367676, "global_step": 576586, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.893346905708313, "global_step": 576587, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0003552436828613, "global_step": 576588, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0593912601470947, "global_step": 576589, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.053318738937378, "global_step": 576590, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0583980083465576, "global_step": 576591, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0245776176452637, "global_step": 576592, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9342764616012573, "global_step": 576593, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9578355550765991, "global_step": 576594, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.988545298576355, "global_step": 576595, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9359245300292969, "global_step": 576596, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9931188821792603, "global_step": 576597, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0403780937194824, "global_step": 576598, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0455384254455566, "global_step": 576599, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0816867351531982, "global_step": 576600, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0165839195251465, "global_step": 576601, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9469547271728516, "global_step": 576602, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0610222816467285, "global_step": 576603, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9889825582504272, "global_step": 576604, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9652471542358398, "global_step": 576605, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.022392511367798, "global_step": 576606, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.079143524169922, "global_step": 576607, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9925209283828735, "global_step": 576608, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0530178546905518, "global_step": 576609, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.013753890991211, "global_step": 576610, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9752185344696045, "global_step": 576611, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9425034523010254, "global_step": 576612, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0610852241516113, "global_step": 576613, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0660367012023926, "global_step": 576614, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9613205194473267, "global_step": 576615, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.108490467071533, "global_step": 576616, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0408074855804443, "global_step": 576617, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.01751446723938, "global_step": 576618, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9669573307037354, "global_step": 576619, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0837273597717285, "global_step": 576620, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.970494270324707, "global_step": 576621, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.016084671020508, "global_step": 576622, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9649486541748047, "global_step": 576623, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0380795001983643, "global_step": 576624, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.113147258758545, "global_step": 576625, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0409116744995117, "global_step": 576626, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.047800064086914, "global_step": 576627, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.009465456008911, "global_step": 576628, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0235276222229004, "global_step": 576629, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.007504463195801, "global_step": 576630, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.088543176651001, "global_step": 576631, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9781229496002197, "global_step": 576632, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0975916385650635, "global_step": 576633, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9608045816421509, "global_step": 576634, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0615663528442383, "global_step": 576635, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9539142847061157, "global_step": 576636, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0277256965637207, "global_step": 576637, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.021975040435791, "global_step": 576638, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0215091705322266, "global_step": 576639, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0219311714172363, "global_step": 576640, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0331473350524902, "global_step": 576641, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.021479845046997, "global_step": 576642, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.042518138885498, "global_step": 576643, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.001899480819702, "global_step": 576644, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.062316656112671, "global_step": 576645, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9803789854049683, "global_step": 576646, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.034489870071411, "global_step": 576647, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.084913730621338, "global_step": 576648, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0592257976531982, "global_step": 576649, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0784735679626465, "global_step": 576650, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9802991151809692, "global_step": 576651, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.062497138977051, "global_step": 576652, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.026693820953369, "global_step": 576653, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0493690967559814, "global_step": 576654, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.081056594848633, "global_step": 576655, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0174801349639893, "global_step": 576656, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9785047769546509, "global_step": 576657, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0079634189605713, "global_step": 576658, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.073881149291992, "global_step": 576659, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.95012629032135, "global_step": 576660, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1048786640167236, "global_step": 576661, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9457560777664185, "global_step": 576662, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9988868236541748, "global_step": 576663, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0038938522338867, "global_step": 576664, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.06917142868042, "global_step": 576665, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0280447006225586, "global_step": 576666, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0279266834259033, "global_step": 576667, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9628385305404663, "global_step": 576668, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0045852661132812, "global_step": 576669, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.072857141494751, "global_step": 576670, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.955402135848999, "global_step": 576671, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.070329189300537, "global_step": 576672, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9378468990325928, "global_step": 576673, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9897620677947998, "global_step": 576674, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.006906032562256, "global_step": 576675, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9991265535354614, "global_step": 576676, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9980977773666382, "global_step": 576677, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9667731523513794, "global_step": 576678, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.020738124847412, "global_step": 576679, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.061707019805908, "global_step": 576680, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.927169919013977, "global_step": 576681, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.1219544410705566, "global_step": 576682, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0718560218811035, "global_step": 576683, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.022336483001709, "global_step": 576684, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.040362596511841, "global_step": 576685, "epoch": 944, "lr": 5e-05}
{"train_loss": 1.9780983924865723, "global_step": 576686, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.020562171936035, "global_step": 576687, "epoch": 944, "lr": 5e-05}
{"train_loss": 2.0240578651428223, "global_step": 576688, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9728119373321533, "global_step": 576689, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0226211547851562, "global_step": 576690, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9540125131607056, "global_step": 576691, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.947860598564148, "global_step": 576692, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.97774076461792, "global_step": 576693, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0690248012542725, "global_step": 576694, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0148797035217285, "global_step": 576695, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.982134222984314, "global_step": 576696, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.005377769470215, "global_step": 576697, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0764129161834717, "global_step": 576698, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.004138946533203, "global_step": 576699, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9463354349136353, "global_step": 576700, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9839762449264526, "global_step": 576701, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.106550693511963, "global_step": 576702, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9950127601623535, "global_step": 576703, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.062469005584717, "global_step": 576704, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.019620180130005, "global_step": 576705, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9564087390899658, "global_step": 576706, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.039937973022461, "global_step": 576707, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9976450204849243, "global_step": 576708, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9538744688034058, "global_step": 576709, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0250799655914307, "global_step": 576710, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9920995235443115, "global_step": 576711, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.957606315612793, "global_step": 576712, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9905381202697754, "global_step": 576713, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9773201942443848, "global_step": 576714, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0655934810638428, "global_step": 576715, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9524450302124023, "global_step": 576716, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0379116535186768, "global_step": 576717, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.031700849533081, "global_step": 576718, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9770057201385498, "global_step": 576719, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0148727893829346, "global_step": 576720, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0223300457000732, "global_step": 576721, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.951229453086853, "global_step": 576722, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.941306233406067, "global_step": 576723, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0561866760253906, "global_step": 576724, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.013582944869995, "global_step": 576725, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.027479648590088, "global_step": 576726, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.990389347076416, "global_step": 576727, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9492543935775757, "global_step": 576728, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.05177640914917, "global_step": 576729, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0388689041137695, "global_step": 576730, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.046710729598999, "global_step": 576731, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0074820518493652, "global_step": 576732, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0406837463378906, "global_step": 576733, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0773634910583496, "global_step": 576734, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.076662302017212, "global_step": 576735, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9729632139205933, "global_step": 576736, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0576541423797607, "global_step": 576737, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9808502197265625, "global_step": 576738, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0357460975646973, "global_step": 576739, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0138213634490967, "global_step": 576740, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.995337963104248, "global_step": 576741, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0159339904785156, "global_step": 576742, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.978318214416504, "global_step": 576743, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.095212459564209, "global_step": 576744, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0442237854003906, "global_step": 576745, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1188602447509766, "global_step": 576746, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.067671298980713, "global_step": 576747, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0970401763916016, "global_step": 576748, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.011131525039673, "global_step": 576749, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0691874027252197, "global_step": 576750, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9403868913650513, "global_step": 576751, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.094681978225708, "global_step": 576752, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0375187397003174, "global_step": 576753, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.027812957763672, "global_step": 576754, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.036936044692993, "global_step": 576755, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9873807430267334, "global_step": 576756, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0251781940460205, "global_step": 576757, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9502573013305664, "global_step": 576758, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9394856691360474, "global_step": 576759, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.032303810119629, "global_step": 576760, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.970155954360962, "global_step": 576761, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0363271236419678, "global_step": 576762, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0052011013031006, "global_step": 576763, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9386597871780396, "global_step": 576764, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1308658123016357, "global_step": 576765, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.017430543899536, "global_step": 576766, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0673556327819824, "global_step": 576767, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9944584369659424, "global_step": 576768, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0351638793945312, "global_step": 576769, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9401443004608154, "global_step": 576770, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.038670063018799, "global_step": 576771, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9599896669387817, "global_step": 576772, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.063406229019165, "global_step": 576773, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.939103126525879, "global_step": 576774, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0043163299560547, "global_step": 576775, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.081620216369629, "global_step": 576776, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0500409603118896, "global_step": 576777, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0842788219451904, "global_step": 576778, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9525898694992065, "global_step": 576779, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9736289978027344, "global_step": 576780, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0259571075439453, "global_step": 576781, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9956636428833008, "global_step": 576782, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9821078777313232, "global_step": 576783, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0381457805633545, "global_step": 576784, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0062808990478516, "global_step": 576785, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9509156942367554, "global_step": 576786, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9994502067565918, "global_step": 576787, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.8772867918014526, "global_step": 576788, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9524270296096802, "global_step": 576789, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0116751194000244, "global_step": 576790, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0505528450012207, "global_step": 576791, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.059790849685669, "global_step": 576792, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0734970569610596, "global_step": 576793, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0830602645874023, "global_step": 576794, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0309479236602783, "global_step": 576795, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.036400318145752, "global_step": 576796, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0504050254821777, "global_step": 576797, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.966895580291748, "global_step": 576798, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.920982837677002, "global_step": 576799, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9761147499084473, "global_step": 576800, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0468504428863525, "global_step": 576801, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.015805959701538, "global_step": 576802, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0405917167663574, "global_step": 576803, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9938620328903198, "global_step": 576804, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0706591606140137, "global_step": 576805, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1171059608459473, "global_step": 576806, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.950188159942627, "global_step": 576807, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9409795999526978, "global_step": 576808, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.091984987258911, "global_step": 576809, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9446669816970825, "global_step": 576810, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9866856336593628, "global_step": 576811, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0489389896392822, "global_step": 576812, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9681276082992554, "global_step": 576813, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0463593006134033, "global_step": 576814, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.063058614730835, "global_step": 576815, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.016103982925415, "global_step": 576816, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9683215618133545, "global_step": 576817, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0019161701202393, "global_step": 576818, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9127111434936523, "global_step": 576819, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0071861743927, "global_step": 576820, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.037572145462036, "global_step": 576821, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0710246562957764, "global_step": 576822, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9877573251724243, "global_step": 576823, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0275001525878906, "global_step": 576824, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0243773460388184, "global_step": 576825, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9669872522354126, "global_step": 576826, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.901847243309021, "global_step": 576827, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.010591983795166, "global_step": 576828, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9941096305847168, "global_step": 576829, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0491349697113037, "global_step": 576830, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.012730598449707, "global_step": 576831, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.067190408706665, "global_step": 576832, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0755841732025146, "global_step": 576833, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.989086627960205, "global_step": 576834, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0328428745269775, "global_step": 576835, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0897653102874756, "global_step": 576836, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.112861156463623, "global_step": 576837, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0053720474243164, "global_step": 576838, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9343595504760742, "global_step": 576839, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.072387933731079, "global_step": 576840, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.012026786804199, "global_step": 576841, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9943705797195435, "global_step": 576842, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.058504581451416, "global_step": 576843, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9591470956802368, "global_step": 576844, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.957155466079712, "global_step": 576845, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0085861682891846, "global_step": 576846, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9706432819366455, "global_step": 576847, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0268332958221436, "global_step": 576848, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.007521629333496, "global_step": 576849, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0673933029174805, "global_step": 576850, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.969894528388977, "global_step": 576851, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0265185832977295, "global_step": 576852, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.105881929397583, "global_step": 576853, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9937018156051636, "global_step": 576854, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0538434982299805, "global_step": 576855, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9851998090744019, "global_step": 576856, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.020052194595337, "global_step": 576857, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.02528977394104, "global_step": 576858, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9995243549346924, "global_step": 576859, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.047302722930908, "global_step": 576860, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.006495237350464, "global_step": 576861, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.979814052581787, "global_step": 576862, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.046546459197998, "global_step": 576863, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9831362962722778, "global_step": 576864, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0068483352661133, "global_step": 576865, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0575685501098633, "global_step": 576866, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0698540210723877, "global_step": 576867, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0319724082946777, "global_step": 576868, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.01354718208313, "global_step": 576869, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9535183906555176, "global_step": 576870, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.973292350769043, "global_step": 576871, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0109522342681885, "global_step": 576872, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0437352657318115, "global_step": 576873, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.15092396736145, "global_step": 576874, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.962120771408081, "global_step": 576875, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9489558935165405, "global_step": 576876, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.060798168182373, "global_step": 576877, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.063401699066162, "global_step": 576878, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.954350233078003, "global_step": 576879, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.114711284637451, "global_step": 576880, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0401182174682617, "global_step": 576881, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0244410037994385, "global_step": 576882, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0330464839935303, "global_step": 576883, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1592817306518555, "global_step": 576884, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9728094339370728, "global_step": 576885, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.99118173122406, "global_step": 576886, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.05908465385437, "global_step": 576887, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0671756267547607, "global_step": 576888, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0911941528320312, "global_step": 576889, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.078944683074951, "global_step": 576890, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9497313499450684, "global_step": 576891, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0027973651885986, "global_step": 576892, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.053764820098877, "global_step": 576893, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.032440423965454, "global_step": 576894, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0395374298095703, "global_step": 576895, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0449633598327637, "global_step": 576896, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.060394525527954, "global_step": 576897, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.065293550491333, "global_step": 576898, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.007490634918213, "global_step": 576899, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0356860160827637, "global_step": 576900, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0864415168762207, "global_step": 576901, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0046191215515137, "global_step": 576902, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9835164546966553, "global_step": 576903, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9788562059402466, "global_step": 576904, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0764291286468506, "global_step": 576905, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0748038291931152, "global_step": 576906, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.031525135040283, "global_step": 576907, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.001447916030884, "global_step": 576908, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9571144580841064, "global_step": 576909, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0433199405670166, "global_step": 576910, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1085078716278076, "global_step": 576911, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9882404804229736, "global_step": 576912, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9510520696640015, "global_step": 576913, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9609410762786865, "global_step": 576914, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0151290893554688, "global_step": 576915, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.957042932510376, "global_step": 576916, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.952154517173767, "global_step": 576917, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0321202278137207, "global_step": 576918, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9523918628692627, "global_step": 576919, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9653518199920654, "global_step": 576920, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9244402647018433, "global_step": 576921, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.044651746749878, "global_step": 576922, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1464200019836426, "global_step": 576923, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.089376926422119, "global_step": 576924, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9840730428695679, "global_step": 576925, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0542962551116943, "global_step": 576926, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9351853132247925, "global_step": 576927, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9613289833068848, "global_step": 576928, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0241808891296387, "global_step": 576929, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9917681217193604, "global_step": 576930, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0085277557373047, "global_step": 576931, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9970300197601318, "global_step": 576932, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.070587396621704, "global_step": 576933, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0051677227020264, "global_step": 576934, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9288086891174316, "global_step": 576935, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0096445083618164, "global_step": 576936, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0996456146240234, "global_step": 576937, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.026477098464966, "global_step": 576938, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9690744876861572, "global_step": 576939, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0342376232147217, "global_step": 576940, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.046203374862671, "global_step": 576941, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9896548986434937, "global_step": 576942, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.966118574142456, "global_step": 576943, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0414493083953857, "global_step": 576944, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0403151512145996, "global_step": 576945, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9898972511291504, "global_step": 576946, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0232386589050293, "global_step": 576947, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9173377752304077, "global_step": 576948, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0607290267944336, "global_step": 576949, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.026594877243042, "global_step": 576950, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9586073160171509, "global_step": 576951, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.050386905670166, "global_step": 576952, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9025511741638184, "global_step": 576953, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.086071729660034, "global_step": 576954, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.029737949371338, "global_step": 576955, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9103872776031494, "global_step": 576956, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9249851703643799, "global_step": 576957, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9742412567138672, "global_step": 576958, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.058349847793579, "global_step": 576959, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.992490530014038, "global_step": 576960, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.994685173034668, "global_step": 576961, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.017040729522705, "global_step": 576962, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0311121940612793, "global_step": 576963, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9823750257492065, "global_step": 576964, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9956282377243042, "global_step": 576965, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.965003490447998, "global_step": 576966, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.00974702835083, "global_step": 576967, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0219757556915283, "global_step": 576968, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.086949586868286, "global_step": 576969, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9940505027770996, "global_step": 576970, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0393989086151123, "global_step": 576971, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1057214736938477, "global_step": 576972, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0809404850006104, "global_step": 576973, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0109002590179443, "global_step": 576974, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.107970714569092, "global_step": 576975, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0519566535949707, "global_step": 576976, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.914283275604248, "global_step": 576977, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0228960514068604, "global_step": 576978, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9904066324234009, "global_step": 576979, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.964233160018921, "global_step": 576980, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.008962869644165, "global_step": 576981, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9752082824707031, "global_step": 576982, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.085888624191284, "global_step": 576983, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0286617279052734, "global_step": 576984, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.018348217010498, "global_step": 576985, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0797924995422363, "global_step": 576986, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.8994877338409424, "global_step": 576987, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9849656820297241, "global_step": 576988, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.059946298599243, "global_step": 576989, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.014801263809204, "global_step": 576990, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.07920503616333, "global_step": 576991, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0368709564208984, "global_step": 576992, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.168599843978882, "global_step": 576993, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9879169464111328, "global_step": 576994, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0053389072418213, "global_step": 576995, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.008357286453247, "global_step": 576996, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0220255851745605, "global_step": 576997, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9915852546691895, "global_step": 576998, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0332863330841064, "global_step": 576999, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0060760974884033, "global_step": 577000, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.073117971420288, "global_step": 577001, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.045178174972534, "global_step": 577002, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9677026271820068, "global_step": 577003, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9747052192687988, "global_step": 577004, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9572553634643555, "global_step": 577005, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9734538793563843, "global_step": 577006, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0122060775756836, "global_step": 577007, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0772011280059814, "global_step": 577008, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.056065320968628, "global_step": 577009, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9517699480056763, "global_step": 577010, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9806944131851196, "global_step": 577011, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9853547811508179, "global_step": 577012, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0474398136138916, "global_step": 577013, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1565191745758057, "global_step": 577014, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1114935874938965, "global_step": 577015, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0287723541259766, "global_step": 577016, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9461987018585205, "global_step": 577017, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.077113628387451, "global_step": 577018, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.058230400085449, "global_step": 577019, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9886597394943237, "global_step": 577020, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9922780990600586, "global_step": 577021, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9844541549682617, "global_step": 577022, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0999929904937744, "global_step": 577023, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.015324831008911, "global_step": 577024, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.047333002090454, "global_step": 577025, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.012399673461914, "global_step": 577026, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9990081787109375, "global_step": 577027, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.999864101409912, "global_step": 577028, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.033646583557129, "global_step": 577029, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9726974964141846, "global_step": 577030, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0165979862213135, "global_step": 577031, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0062787532806396, "global_step": 577032, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9378162622451782, "global_step": 577033, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0208616256713867, "global_step": 577034, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0092499256134033, "global_step": 577035, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.027090311050415, "global_step": 577036, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0672881603240967, "global_step": 577037, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.962142825126648, "global_step": 577038, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.073927879333496, "global_step": 577039, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0178894996643066, "global_step": 577040, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0366997718811035, "global_step": 577041, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.06803560256958, "global_step": 577042, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1174521446228027, "global_step": 577043, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1208040714263916, "global_step": 577044, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0285048484802246, "global_step": 577045, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0496439933776855, "global_step": 577046, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0122900009155273, "global_step": 577047, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0410706996917725, "global_step": 577048, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0173025131225586, "global_step": 577049, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9565393924713135, "global_step": 577050, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0125744342803955, "global_step": 577051, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0263233184814453, "global_step": 577052, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.077209949493408, "global_step": 577053, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.00856351852417, "global_step": 577054, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9434510469436646, "global_step": 577055, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0251681804656982, "global_step": 577056, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.050316333770752, "global_step": 577057, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.025299310684204, "global_step": 577058, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.051718235015869, "global_step": 577059, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9944112300872803, "global_step": 577060, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.121103048324585, "global_step": 577061, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.121941089630127, "global_step": 577062, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0166220664978027, "global_step": 577063, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9338890314102173, "global_step": 577064, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.970832109451294, "global_step": 577065, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1063594818115234, "global_step": 577066, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0639870166778564, "global_step": 577067, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9421523809432983, "global_step": 577068, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.8802156448364258, "global_step": 577069, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9650055170059204, "global_step": 577070, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.000011920928955, "global_step": 577071, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9946000576019287, "global_step": 577072, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.059187173843384, "global_step": 577073, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0484352111816406, "global_step": 577074, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9798221588134766, "global_step": 577075, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9863293170928955, "global_step": 577076, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9987335205078125, "global_step": 577077, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0095081329345703, "global_step": 577078, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9292415380477905, "global_step": 577079, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9853848218917847, "global_step": 577080, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0644471645355225, "global_step": 577081, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0552408695220947, "global_step": 577082, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0554580688476562, "global_step": 577083, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0506362915039062, "global_step": 577084, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.014479398727417, "global_step": 577085, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.01248836517334, "global_step": 577086, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.054598093032837, "global_step": 577087, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0553112030029297, "global_step": 577088, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0307018756866455, "global_step": 577089, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.033719301223755, "global_step": 577090, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.00541353225708, "global_step": 577091, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0409183502197266, "global_step": 577092, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1265738010406494, "global_step": 577093, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9029393196105957, "global_step": 577094, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.107667922973633, "global_step": 577095, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0423004627227783, "global_step": 577096, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9162334203720093, "global_step": 577097, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0495214462280273, "global_step": 577098, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0543758869171143, "global_step": 577099, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0350382328033447, "global_step": 577100, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0098185539245605, "global_step": 577101, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.089399814605713, "global_step": 577102, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.017571449279785, "global_step": 577103, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0336973667144775, "global_step": 577104, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9674173593521118, "global_step": 577105, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.073805809020996, "global_step": 577106, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.046185255050659, "global_step": 577107, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1350882053375244, "global_step": 577108, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.015655517578125, "global_step": 577109, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9553017616271973, "global_step": 577110, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9951289892196655, "global_step": 577111, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.8885809183120728, "global_step": 577112, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.085510730743408, "global_step": 577113, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.991373062133789, "global_step": 577114, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9747287034988403, "global_step": 577115, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0512876510620117, "global_step": 577116, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.01670241355896, "global_step": 577117, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9340232610702515, "global_step": 577118, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.975536823272705, "global_step": 577119, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0688188076019287, "global_step": 577120, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9582221508026123, "global_step": 577121, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.030085802078247, "global_step": 577122, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0167548656463623, "global_step": 577123, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9372228384017944, "global_step": 577124, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.091979503631592, "global_step": 577125, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9813454151153564, "global_step": 577126, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0550992488861084, "global_step": 577127, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0055387020111084, "global_step": 577128, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0497725009918213, "global_step": 577129, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.071261405944824, "global_step": 577130, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0812771320343018, "global_step": 577131, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.963846206665039, "global_step": 577132, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.981982707977295, "global_step": 577133, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9820090532302856, "global_step": 577134, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0578904151916504, "global_step": 577135, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9855990409851074, "global_step": 577136, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9648422002792358, "global_step": 577137, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9289363622665405, "global_step": 577138, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0737619400024414, "global_step": 577139, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.937815546989441, "global_step": 577140, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9780176877975464, "global_step": 577141, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1366848945617676, "global_step": 577142, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.08076548576355, "global_step": 577143, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1098456382751465, "global_step": 577144, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0215485095977783, "global_step": 577145, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0021674633026123, "global_step": 577146, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0036184787750244, "global_step": 577147, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1027727127075195, "global_step": 577148, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.021360158920288, "global_step": 577149, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.014108657836914, "global_step": 577150, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9755622148513794, "global_step": 577151, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0486888885498047, "global_step": 577152, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9849447011947632, "global_step": 577153, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0515120029449463, "global_step": 577154, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0254805088043213, "global_step": 577155, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.998476266860962, "global_step": 577156, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.014303207397461, "global_step": 577157, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9884837865829468, "global_step": 577158, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0253689289093018, "global_step": 577159, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.009063720703125, "global_step": 577160, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0291473865509033, "global_step": 577161, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.081380844116211, "global_step": 577162, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9615678787231445, "global_step": 577163, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0530011653900146, "global_step": 577164, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9307215213775635, "global_step": 577165, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9819023609161377, "global_step": 577166, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.053359031677246, "global_step": 577167, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.040861129760742, "global_step": 577168, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.001540422439575, "global_step": 577169, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0031464099884033, "global_step": 577170, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.950921893119812, "global_step": 577171, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9201736450195312, "global_step": 577172, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0390267372131348, "global_step": 577173, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9915401935577393, "global_step": 577174, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0431036949157715, "global_step": 577175, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9776660203933716, "global_step": 577176, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0257809162139893, "global_step": 577177, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9860635995864868, "global_step": 577178, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9401692152023315, "global_step": 577179, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0253889560699463, "global_step": 577180, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9958792924880981, "global_step": 577181, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9957497119903564, "global_step": 577182, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9898830652236938, "global_step": 577183, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0481836795806885, "global_step": 577184, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9740593433380127, "global_step": 577185, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0538344383239746, "global_step": 577186, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.007392406463623, "global_step": 577187, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0386292934417725, "global_step": 577188, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9864106178283691, "global_step": 577189, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.05535626411438, "global_step": 577190, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.064868450164795, "global_step": 577191, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9609116315841675, "global_step": 577192, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9433923959732056, "global_step": 577193, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.052513599395752, "global_step": 577194, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.027681350708008, "global_step": 577195, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0441534519195557, "global_step": 577196, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0176403522491455, "global_step": 577197, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0297746658325195, "global_step": 577198, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0279135704040527, "global_step": 577199, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0126752853393555, "global_step": 577200, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.099385976791382, "global_step": 577201, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1077582836151123, "global_step": 577202, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0342249870300293, "global_step": 577203, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.058384656906128, "global_step": 577204, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0579333305358887, "global_step": 577205, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0279033184051514, "global_step": 577206, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.962912917137146, "global_step": 577207, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0078563690185547, "global_step": 577208, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0067837238311768, "global_step": 577209, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.018961191177368, "global_step": 577210, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0147266387939453, "global_step": 577211, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.033273696899414, "global_step": 577212, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9725350141525269, "global_step": 577213, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9812464714050293, "global_step": 577214, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0329484939575195, "global_step": 577215, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9985944032669067, "global_step": 577216, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9452885389328003, "global_step": 577217, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0679423809051514, "global_step": 577218, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.053838014602661, "global_step": 577219, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.02312970161438, "global_step": 577220, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.035623073577881, "global_step": 577221, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0393009185791016, "global_step": 577222, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0567216873168945, "global_step": 577223, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0412728786468506, "global_step": 577224, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.014726400375366, "global_step": 577225, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0694198608398438, "global_step": 577226, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0186355113983154, "global_step": 577227, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9843363761901855, "global_step": 577228, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.024826765060425, "global_step": 577229, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.077620029449463, "global_step": 577230, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9418584108352661, "global_step": 577231, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9631595611572266, "global_step": 577232, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9955204725265503, "global_step": 577233, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0514626502990723, "global_step": 577234, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.037632942199707, "global_step": 577235, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1150736808776855, "global_step": 577236, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0295615196228027, "global_step": 577237, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0211410522460938, "global_step": 577238, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.957396149635315, "global_step": 577239, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.068647861480713, "global_step": 577240, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9472334384918213, "global_step": 577241, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.042405366897583, "global_step": 577242, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9627938270568848, "global_step": 577243, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9986375570297241, "global_step": 577244, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0220143795013428, "global_step": 577245, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.975290298461914, "global_step": 577246, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.961277961730957, "global_step": 577247, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0646612644195557, "global_step": 577248, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.025786876678467, "global_step": 577249, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9910807609558105, "global_step": 577250, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.040780782699585, "global_step": 577251, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9911783933639526, "global_step": 577252, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0353333950042725, "global_step": 577253, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9890384674072266, "global_step": 577254, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.048772096633911, "global_step": 577255, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9996472597122192, "global_step": 577256, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9891568422317505, "global_step": 577257, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0684666633605957, "global_step": 577258, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.02386474609375, "global_step": 577259, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.024994134902954, "global_step": 577260, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1001198291778564, "global_step": 577261, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9478691816329956, "global_step": 577262, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.105832099914551, "global_step": 577263, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0647172927856445, "global_step": 577264, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9051928520202637, "global_step": 577265, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9838401079177856, "global_step": 577266, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.021054983139038, "global_step": 577267, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.04691743850708, "global_step": 577268, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.015824317932129, "global_step": 577269, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9966373443603516, "global_step": 577270, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9789258241653442, "global_step": 577271, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9614121913909912, "global_step": 577272, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9704785346984863, "global_step": 577273, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.007216215133667, "global_step": 577274, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9994785785675049, "global_step": 577275, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.056837797164917, "global_step": 577276, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9568655490875244, "global_step": 577277, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9935197830200195, "global_step": 577278, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.124030113220215, "global_step": 577279, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0274996757507324, "global_step": 577280, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.10136342048645, "global_step": 577281, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9558387994766235, "global_step": 577282, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0380351543426514, "global_step": 577283, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9078285694122314, "global_step": 577284, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9913135766983032, "global_step": 577285, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0169456005096436, "global_step": 577286, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9803553819656372, "global_step": 577287, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.99885892868042, "global_step": 577288, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1038143634796143, "global_step": 577289, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.074204921722412, "global_step": 577290, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.058152437210083, "global_step": 577291, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9882501363754272, "global_step": 577292, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.992307186126709, "global_step": 577293, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9697754383087158, "global_step": 577294, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.046618700027466, "global_step": 577295, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0833499431610107, "global_step": 577296, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.997463345527649, "global_step": 577297, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0805349349975586, "global_step": 577298, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.939591884613037, "global_step": 577299, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0942270755767822, "global_step": 577300, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9915258884429932, "global_step": 577301, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.015268564224243, "global_step": 577302, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0864779949188232, "global_step": 577303, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0341830253601074, "global_step": 577304, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0319650173187256, "global_step": 577305, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9170396327972412, "global_step": 577306, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0365633964538574, "global_step": 577307, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.047394037246704, "global_step": 577308, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9800467491149902, "global_step": 577309, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9940751791000366, "global_step": 577310, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0578341484069824, "global_step": 577311, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0234086513519287, "global_step": 577312, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.103569746017456, "global_step": 577313, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0694358348846436, "global_step": 577314, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9884272813796997, "global_step": 577315, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0264012813568115, "global_step": 577316, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.079946994781494, "global_step": 577317, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9805721044540405, "global_step": 577318, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9047014713287354, "global_step": 577319, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9521915912628174, "global_step": 577320, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.082871675491333, "global_step": 577321, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.010673999786377, "global_step": 577322, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.068671703338623, "global_step": 577323, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.01708984375, "global_step": 577324, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0398991107940674, "global_step": 577325, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0996360778808594, "global_step": 577326, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.020962953567505, "global_step": 577327, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0085599422454834, "global_step": 577328, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0870132446289062, "global_step": 577329, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0680551528930664, "global_step": 577330, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0156002044677734, "global_step": 577331, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9984697103500366, "global_step": 577332, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.961274266242981, "global_step": 577333, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9941935539245605, "global_step": 577334, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0255625247955322, "global_step": 577335, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9760717153549194, "global_step": 577336, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0998501777648926, "global_step": 577337, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9653234481811523, "global_step": 577338, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9585570096969604, "global_step": 577339, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9554951190948486, "global_step": 577340, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0825839042663574, "global_step": 577341, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0388755798339844, "global_step": 577342, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.005868673324585, "global_step": 577343, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.049211263656616, "global_step": 577344, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0000839233398438, "global_step": 577345, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.084771156311035, "global_step": 577346, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0130600929260254, "global_step": 577347, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9407556056976318, "global_step": 577348, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0215864181518555, "global_step": 577349, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9445229768753052, "global_step": 577350, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0761537551879883, "global_step": 577351, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0731077194213867, "global_step": 577352, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9668993949890137, "global_step": 577353, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.990086317062378, "global_step": 577354, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.010891914367676, "global_step": 577355, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9967169761657715, "global_step": 577356, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9518557786941528, "global_step": 577357, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9748048782348633, "global_step": 577358, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.076902389526367, "global_step": 577359, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.125936269760132, "global_step": 577360, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1042749881744385, "global_step": 577361, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0889151096343994, "global_step": 577362, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9820901155471802, "global_step": 577363, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9376028776168823, "global_step": 577364, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.032327175140381, "global_step": 577365, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.017977237701416, "global_step": 577366, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.028560161590576, "global_step": 577367, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1673715114593506, "global_step": 577368, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9881643056869507, "global_step": 577369, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.077209949493408, "global_step": 577370, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0330698490142822, "global_step": 577371, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9937074184417725, "global_step": 577372, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.002599000930786, "global_step": 577373, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9922692775726318, "global_step": 577374, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.019760847091675, "global_step": 577375, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9461708068847656, "global_step": 577376, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9746249914169312, "global_step": 577377, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0645041465759277, "global_step": 577378, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.058349370956421, "global_step": 577379, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9569631814956665, "global_step": 577380, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9347416162490845, "global_step": 577381, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.065779447555542, "global_step": 577382, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9977306127548218, "global_step": 577383, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.046441078186035, "global_step": 577384, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.083876371383667, "global_step": 577385, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.089617967605591, "global_step": 577386, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.981721043586731, "global_step": 577387, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.985101342201233, "global_step": 577388, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.148700475692749, "global_step": 577389, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0659308433532715, "global_step": 577390, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.022428512573242, "global_step": 577391, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9996919631958008, "global_step": 577392, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0088882446289062, "global_step": 577393, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.009941339492798, "global_step": 577394, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0425000190734863, "global_step": 577395, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.102684736251831, "global_step": 577396, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.011847496032715, "global_step": 577397, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.075749635696411, "global_step": 577398, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.977794885635376, "global_step": 577399, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0633609294891357, "global_step": 577400, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0998616218566895, "global_step": 577401, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1000537872314453, "global_step": 577402, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1220943927764893, "global_step": 577403, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.015230417251587, "global_step": 577404, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.101288318634033, "global_step": 577405, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9434785842895508, "global_step": 577406, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.051290988922119, "global_step": 577407, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.039458990097046, "global_step": 577408, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0476624965667725, "global_step": 577409, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.014955759048462, "global_step": 577410, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0241215229034424, "global_step": 577411, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9462518692016602, "global_step": 577412, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0518152713775635, "global_step": 577413, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0073299407958984, "global_step": 577414, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.07029390335083, "global_step": 577415, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.030719757080078, "global_step": 577416, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0805561542510986, "global_step": 577417, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.062422037124634, "global_step": 577418, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.011018991470337, "global_step": 577419, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.033181667327881, "global_step": 577420, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.062256336212158, "global_step": 577421, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0815067291259766, "global_step": 577422, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0430572032928467, "global_step": 577423, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0114946365356445, "global_step": 577424, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.029771089553833, "global_step": 577425, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.064418315887451, "global_step": 577426, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0724236965179443, "global_step": 577427, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0132288932800293, "global_step": 577428, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9902675151824951, "global_step": 577429, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0107369422912598, "global_step": 577430, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.007658004760742, "global_step": 577431, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9868913888931274, "global_step": 577432, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0227460861206055, "global_step": 577433, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.99880850315094, "global_step": 577434, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0347883701324463, "global_step": 577435, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0430002212524414, "global_step": 577436, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9862736463546753, "global_step": 577437, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0424299240112305, "global_step": 577438, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0966577529907227, "global_step": 577439, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.070819139480591, "global_step": 577440, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9877901077270508, "global_step": 577441, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9428609609603882, "global_step": 577442, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9478116035461426, "global_step": 577443, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9788812398910522, "global_step": 577444, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0699539184570312, "global_step": 577445, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9546672105789185, "global_step": 577446, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0230133533477783, "global_step": 577447, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.989501953125, "global_step": 577448, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.039269208908081, "global_step": 577449, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0204339027404785, "global_step": 577450, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.998022198677063, "global_step": 577451, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0547845363616943, "global_step": 577452, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.037691116333008, "global_step": 577453, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.037208080291748, "global_step": 577454, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0701394081115723, "global_step": 577455, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.950258731842041, "global_step": 577456, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9148834943771362, "global_step": 577457, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0770862102508545, "global_step": 577458, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.027822494506836, "global_step": 577459, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1031334400177, "global_step": 577460, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0446736812591553, "global_step": 577461, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0142035484313965, "global_step": 577462, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0079524517059326, "global_step": 577463, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9728938341140747, "global_step": 577464, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9828953742980957, "global_step": 577465, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9902427196502686, "global_step": 577466, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.967557430267334, "global_step": 577467, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9906363487243652, "global_step": 577468, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0564558506011963, "global_step": 577469, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9417667388916016, "global_step": 577470, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9653691053390503, "global_step": 577471, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9698560237884521, "global_step": 577472, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0299291610717773, "global_step": 577473, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0719709396362305, "global_step": 577474, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.060344934463501, "global_step": 577475, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.050480604171753, "global_step": 577476, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0002920627593994, "global_step": 577477, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.010422945022583, "global_step": 577478, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.080735683441162, "global_step": 577479, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.8872170448303223, "global_step": 577480, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0525929927825928, "global_step": 577481, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0336456298828125, "global_step": 577482, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0248873233795166, "global_step": 577483, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.048541307449341, "global_step": 577484, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1053085327148438, "global_step": 577485, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0276529788970947, "global_step": 577486, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.993891954421997, "global_step": 577487, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.918169617652893, "global_step": 577488, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.122223377227783, "global_step": 577489, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9838567972183228, "global_step": 577490, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.104147434234619, "global_step": 577491, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.058624029159546, "global_step": 577492, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.050916910171509, "global_step": 577493, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.953989028930664, "global_step": 577494, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9546177387237549, "global_step": 577495, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.01611328125, "global_step": 577496, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.086005926132202, "global_step": 577497, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.95589280128479, "global_step": 577498, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9900330305099487, "global_step": 577499, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9996472597122192, "global_step": 577500, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.019322633743286, "global_step": 577501, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9687144756317139, "global_step": 577502, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.075679302215576, "global_step": 577503, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0793211460113525, "global_step": 577504, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.058340311050415, "global_step": 577505, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.077317237854004, "global_step": 577506, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9941500425338745, "global_step": 577507, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.093731164932251, "global_step": 577508, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0097036361694336, "global_step": 577509, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0441107749938965, "global_step": 577510, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.898871898651123, "global_step": 577511, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.037505626678467, "global_step": 577512, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9698116779327393, "global_step": 577513, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.021717071533203, "global_step": 577514, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.995841145515442, "global_step": 577515, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.004631757736206, "global_step": 577516, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.060359477996826, "global_step": 577517, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.995529294013977, "global_step": 577518, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.040414810180664, "global_step": 577519, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.07547664642334, "global_step": 577520, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.040117025375366, "global_step": 577521, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.949699878692627, "global_step": 577522, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.047468900680542, "global_step": 577523, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0160460472106934, "global_step": 577524, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9404196739196777, "global_step": 577525, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0573880672454834, "global_step": 577526, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.001922369003296, "global_step": 577527, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9939088821411133, "global_step": 577528, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.029268264770508, "global_step": 577529, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0331287384033203, "global_step": 577530, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9734240770339966, "global_step": 577531, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0901589393615723, "global_step": 577532, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9878095388412476, "global_step": 577533, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.069744110107422, "global_step": 577534, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0361692905426025, "global_step": 577535, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.968022346496582, "global_step": 577536, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9491291046142578, "global_step": 577537, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9798773527145386, "global_step": 577538, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.077899217605591, "global_step": 577539, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0118350982666016, "global_step": 577540, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0154683589935303, "global_step": 577541, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0201735496520996, "global_step": 577542, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.006951332092285, "global_step": 577543, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0717310905456543, "global_step": 577544, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.955985426902771, "global_step": 577545, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0018813610076904, "global_step": 577546, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9773445129394531, "global_step": 577547, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0158073902130127, "global_step": 577548, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.009244918823242, "global_step": 577549, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0010321140289307, "global_step": 577550, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.053212881088257, "global_step": 577551, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9679920673370361, "global_step": 577552, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1045613288879395, "global_step": 577553, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9535542726516724, "global_step": 577554, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.8646173477172852, "global_step": 577555, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0140063762664795, "global_step": 577556, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.997226357460022, "global_step": 577557, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9842194318771362, "global_step": 577558, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9832199811935425, "global_step": 577559, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0117101669311523, "global_step": 577560, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.035283327102661, "global_step": 577561, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0048978328704834, "global_step": 577562, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.057541847229004, "global_step": 577563, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0870144367218018, "global_step": 577564, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1146645545959473, "global_step": 577565, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1635801792144775, "global_step": 577566, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.042984962463379, "global_step": 577567, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0425190925598145, "global_step": 577568, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.047544240951538, "global_step": 577569, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0373332500457764, "global_step": 577570, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.996298909187317, "global_step": 577571, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9573349952697754, "global_step": 577572, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0610885620117188, "global_step": 577573, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.092107057571411, "global_step": 577574, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0045554637908936, "global_step": 577575, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0576045513153076, "global_step": 577576, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.072988510131836, "global_step": 577577, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0737507343292236, "global_step": 577578, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.019413471221924, "global_step": 577579, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.024113416671753, "global_step": 577580, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9730859994888306, "global_step": 577581, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.995474934577942, "global_step": 577582, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9871188402175903, "global_step": 577583, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0384774208068848, "global_step": 577584, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9577691555023193, "global_step": 577585, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.055863380432129, "global_step": 577586, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0064644813537598, "global_step": 577587, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9781817197799683, "global_step": 577588, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9950058460235596, "global_step": 577589, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.049544095993042, "global_step": 577590, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.065610885620117, "global_step": 577591, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0570192337036133, "global_step": 577592, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.057807207107544, "global_step": 577593, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9715834856033325, "global_step": 577594, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0196971893310547, "global_step": 577595, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9470739364624023, "global_step": 577596, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.999984622001648, "global_step": 577597, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9434446096420288, "global_step": 577598, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9576061964035034, "global_step": 577599, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.00055193901062, "global_step": 577600, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9737491607666016, "global_step": 577601, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0266289710998535, "global_step": 577602, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0985312461853027, "global_step": 577603, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0970470905303955, "global_step": 577604, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9683586359024048, "global_step": 577605, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.006568193435669, "global_step": 577606, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.060168743133545, "global_step": 577607, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0520565509796143, "global_step": 577608, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0167579650878906, "global_step": 577609, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1448638439178467, "global_step": 577610, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0656561851501465, "global_step": 577611, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0376687049865723, "global_step": 577612, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0898125171661377, "global_step": 577613, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9697099924087524, "global_step": 577614, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9877487421035767, "global_step": 577615, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0059924125671387, "global_step": 577616, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9763332605361938, "global_step": 577617, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.998765468597412, "global_step": 577618, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0672354698181152, "global_step": 577619, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0419116020202637, "global_step": 577620, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0909759998321533, "global_step": 577621, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9866853952407837, "global_step": 577622, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.994278073310852, "global_step": 577623, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9716746807098389, "global_step": 577624, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.009733200073242, "global_step": 577625, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.046293258666992, "global_step": 577626, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.983919620513916, "global_step": 577627, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0263137817382812, "global_step": 577628, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0300145149230957, "global_step": 577629, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.017949342727661, "global_step": 577630, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.125894784927368, "global_step": 577631, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9436061382293701, "global_step": 577632, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0210044384002686, "global_step": 577633, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9522061347961426, "global_step": 577634, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.021047353744507, "global_step": 577635, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.983345866203308, "global_step": 577636, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.152623176574707, "global_step": 577637, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9973382949829102, "global_step": 577638, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9611988067626953, "global_step": 577639, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.137193441390991, "global_step": 577640, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0393223762512207, "global_step": 577641, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0571627616882324, "global_step": 577642, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9994988441467285, "global_step": 577643, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0360043048858643, "global_step": 577644, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.107327461242676, "global_step": 577645, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9968100786209106, "global_step": 577646, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9585069417953491, "global_step": 577647, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9546438455581665, "global_step": 577648, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.088613748550415, "global_step": 577649, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0078461170196533, "global_step": 577650, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0622403621673584, "global_step": 577651, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0469202995300293, "global_step": 577652, "epoch": 945, "lr": 5e-05}
{"train_loss": 1.9890707731246948, "global_step": 577653, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.1244399547576904, "global_step": 577654, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.020819902420044, "global_step": 577655, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.019334077835083, "global_step": 577656, "epoch": 945, "lr": 5e-05}
{"train_loss": 2.0107815265655518, "global_step": 577657, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9223679304122925, "global_step": 577658, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9754588603973389, "global_step": 577659, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.937272310256958, "global_step": 577660, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.047327995300293, "global_step": 577661, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9320604801177979, "global_step": 577662, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9876233339309692, "global_step": 577663, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9343416690826416, "global_step": 577664, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9593313932418823, "global_step": 577665, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0432982444763184, "global_step": 577666, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9547276496887207, "global_step": 577667, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9359275102615356, "global_step": 577668, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.000211715698242, "global_step": 577669, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9552193880081177, "global_step": 577670, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0610480308532715, "global_step": 577671, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.954042911529541, "global_step": 577672, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0203797817230225, "global_step": 577673, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.05090594291687, "global_step": 577674, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.03975510597229, "global_step": 577675, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9906550645828247, "global_step": 577676, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0796656608581543, "global_step": 577677, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9957540035247803, "global_step": 577678, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0947680473327637, "global_step": 577679, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.997856855392456, "global_step": 577680, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9878933429718018, "global_step": 577681, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9220099449157715, "global_step": 577682, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9703902006149292, "global_step": 577683, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0250585079193115, "global_step": 577684, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.084970712661743, "global_step": 577685, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1068859100341797, "global_step": 577686, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.972756266593933, "global_step": 577687, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1027050018310547, "global_step": 577688, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9840092658996582, "global_step": 577689, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9620959758758545, "global_step": 577690, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0462396144866943, "global_step": 577691, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.061866044998169, "global_step": 577692, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0839974880218506, "global_step": 577693, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.025088310241699, "global_step": 577694, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0766942501068115, "global_step": 577695, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.061239719390869, "global_step": 577696, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9921677112579346, "global_step": 577697, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.046905994415283, "global_step": 577698, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0413992404937744, "global_step": 577699, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9766069650650024, "global_step": 577700, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.052882194519043, "global_step": 577701, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.014507532119751, "global_step": 577702, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1114823818206787, "global_step": 577703, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.935705542564392, "global_step": 577704, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0052976608276367, "global_step": 577705, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.070936918258667, "global_step": 577706, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0448269844055176, "global_step": 577707, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9956800937652588, "global_step": 577708, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0271761417388916, "global_step": 577709, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.02561092376709, "global_step": 577710, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9960657358169556, "global_step": 577711, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.004892110824585, "global_step": 577712, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.042609453201294, "global_step": 577713, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1011884212493896, "global_step": 577714, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9917293787002563, "global_step": 577715, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.014212131500244, "global_step": 577716, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9812465906143188, "global_step": 577717, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9525434970855713, "global_step": 577718, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0895044803619385, "global_step": 577719, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9551057815551758, "global_step": 577720, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0286173820495605, "global_step": 577721, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9893501996994019, "global_step": 577722, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.09714937210083, "global_step": 577723, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9930411577224731, "global_step": 577724, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.045806407928467, "global_step": 577725, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9569447040557861, "global_step": 577726, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9803225994110107, "global_step": 577727, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9761310815811157, "global_step": 577728, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.014997720718384, "global_step": 577729, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9832985401153564, "global_step": 577730, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9991830587387085, "global_step": 577731, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9763973951339722, "global_step": 577732, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.051016092300415, "global_step": 577733, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0022809505462646, "global_step": 577734, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.053743600845337, "global_step": 577735, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.002929449081421, "global_step": 577736, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0021562576293945, "global_step": 577737, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1142563819885254, "global_step": 577738, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9534008502960205, "global_step": 577739, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0327134132385254, "global_step": 577740, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0667436122894287, "global_step": 577741, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0373361110687256, "global_step": 577742, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0275766849517822, "global_step": 577743, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.021775484085083, "global_step": 577744, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.081061601638794, "global_step": 577745, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.072751045227051, "global_step": 577746, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.038982629776001, "global_step": 577747, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1056265830993652, "global_step": 577748, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0461418628692627, "global_step": 577749, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9745076894760132, "global_step": 577750, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9796273708343506, "global_step": 577751, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0491416454315186, "global_step": 577752, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0262882709503174, "global_step": 577753, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9614640474319458, "global_step": 577754, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1201906204223633, "global_step": 577755, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.005739450454712, "global_step": 577756, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0341148376464844, "global_step": 577757, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0139353275299072, "global_step": 577758, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9856675863265991, "global_step": 577759, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.8835458755493164, "global_step": 577760, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0053441524505615, "global_step": 577761, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.8978103399276733, "global_step": 577762, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.012460470199585, "global_step": 577763, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1307120323181152, "global_step": 577764, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9584155082702637, "global_step": 577765, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9621387720108032, "global_step": 577766, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0654358863830566, "global_step": 577767, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.978678584098816, "global_step": 577768, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9826908111572266, "global_step": 577769, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0015757083892822, "global_step": 577770, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9777108430862427, "global_step": 577771, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9833155870437622, "global_step": 577772, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.001026153564453, "global_step": 577773, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.017744779586792, "global_step": 577774, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9260945320129395, "global_step": 577775, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.04793643951416, "global_step": 577776, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.990822196006775, "global_step": 577777, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0853397846221924, "global_step": 577778, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.012443780899048, "global_step": 577779, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9715008735656738, "global_step": 577780, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.011864423751831, "global_step": 577781, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.006786823272705, "global_step": 577782, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9586385488510132, "global_step": 577783, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9685437679290771, "global_step": 577784, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.045701503753662, "global_step": 577785, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0675389766693115, "global_step": 577786, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0591881275177, "global_step": 577787, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.041466236114502, "global_step": 577788, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.013838529586792, "global_step": 577789, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.020089626312256, "global_step": 577790, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.999911904335022, "global_step": 577791, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0343480110168457, "global_step": 577792, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0540521144866943, "global_step": 577793, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0143918991088867, "global_step": 577794, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.013507127761841, "global_step": 577795, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9393584728240967, "global_step": 577796, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9915368556976318, "global_step": 577797, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0819451808929443, "global_step": 577798, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0525312423706055, "global_step": 577799, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0170865058898926, "global_step": 577800, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0200002193450928, "global_step": 577801, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0740139484405518, "global_step": 577802, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0482077598571777, "global_step": 577803, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0264346599578857, "global_step": 577804, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0424160957336426, "global_step": 577805, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.082528591156006, "global_step": 577806, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0744283199310303, "global_step": 577807, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9399570226669312, "global_step": 577808, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.058279275894165, "global_step": 577809, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0870330333709717, "global_step": 577810, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.98980712890625, "global_step": 577811, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0455706119537354, "global_step": 577812, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0328288078308105, "global_step": 577813, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0022432804107666, "global_step": 577814, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9735153913497925, "global_step": 577815, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0123374462127686, "global_step": 577816, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.018709897994995, "global_step": 577817, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0446765422821045, "global_step": 577818, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.942431926727295, "global_step": 577819, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9627552032470703, "global_step": 577820, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.042945146560669, "global_step": 577821, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0052294731140137, "global_step": 577822, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9655134677886963, "global_step": 577823, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.942112684249878, "global_step": 577824, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.108137845993042, "global_step": 577825, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.001526117324829, "global_step": 577826, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9976627826690674, "global_step": 577827, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9903993606567383, "global_step": 577828, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1121528148651123, "global_step": 577829, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0292177200317383, "global_step": 577830, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.056760549545288, "global_step": 577831, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9950979948043823, "global_step": 577832, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.006380081176758, "global_step": 577833, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9856220483779907, "global_step": 577834, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.041926860809326, "global_step": 577835, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0866332054138184, "global_step": 577836, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.050178289413452, "global_step": 577837, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0085439682006836, "global_step": 577838, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.02986478805542, "global_step": 577839, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.016807794570923, "global_step": 577840, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.034093141555786, "global_step": 577841, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.981249451637268, "global_step": 577842, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.02250337600708, "global_step": 577843, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.057799816131592, "global_step": 577844, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9384077787399292, "global_step": 577845, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0739874839782715, "global_step": 577846, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.937353253364563, "global_step": 577847, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0784616470336914, "global_step": 577848, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0399811267852783, "global_step": 577849, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0089244842529297, "global_step": 577850, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0089497566223145, "global_step": 577851, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0390892028808594, "global_step": 577852, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0722296237945557, "global_step": 577853, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9741063117980957, "global_step": 577854, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.042168378829956, "global_step": 577855, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.052933692932129, "global_step": 577856, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1132731437683105, "global_step": 577857, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9126259088516235, "global_step": 577858, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0551674365997314, "global_step": 577859, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0251967906951904, "global_step": 577860, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.037273645401001, "global_step": 577861, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.026001453399658, "global_step": 577862, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.97146475315094, "global_step": 577863, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0082011222839355, "global_step": 577864, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.056868076324463, "global_step": 577865, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9230283498764038, "global_step": 577866, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9797039031982422, "global_step": 577867, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0202760696411133, "global_step": 577868, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9713287353515625, "global_step": 577869, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.005988121032715, "global_step": 577870, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0580458641052246, "global_step": 577871, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.928364872932434, "global_step": 577872, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.027297258377075, "global_step": 577873, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0236308574676514, "global_step": 577874, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9644839763641357, "global_step": 577875, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9547247886657715, "global_step": 577876, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9376108646392822, "global_step": 577877, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0106756687164307, "global_step": 577878, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9405235052108765, "global_step": 577879, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0760464668273926, "global_step": 577880, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0429306030273438, "global_step": 577881, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9981694221496582, "global_step": 577882, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.011833429336548, "global_step": 577883, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.963344693183899, "global_step": 577884, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.036153554916382, "global_step": 577885, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.065870523452759, "global_step": 577886, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0235517024993896, "global_step": 577887, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9614464044570923, "global_step": 577888, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1304550170898438, "global_step": 577889, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.018392562866211, "global_step": 577890, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0168938636779785, "global_step": 577891, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9968739748001099, "global_step": 577892, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.923339605331421, "global_step": 577893, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0304222106933594, "global_step": 577894, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0233335494995117, "global_step": 577895, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0193943977355957, "global_step": 577896, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9852129220962524, "global_step": 577897, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9247970581054688, "global_step": 577898, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.8770519495010376, "global_step": 577899, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.039076805114746, "global_step": 577900, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.061046600341797, "global_step": 577901, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0727877616882324, "global_step": 577902, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9513920545578003, "global_step": 577903, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9842702150344849, "global_step": 577904, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9397884607315063, "global_step": 577905, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.044093370437622, "global_step": 577906, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.005502462387085, "global_step": 577907, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9440375566482544, "global_step": 577908, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9892549514770508, "global_step": 577909, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9940465688705444, "global_step": 577910, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.102451801300049, "global_step": 577911, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0122156143188477, "global_step": 577912, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.038999080657959, "global_step": 577913, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.997376799583435, "global_step": 577914, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9834957122802734, "global_step": 577915, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.095057725906372, "global_step": 577916, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0042788982391357, "global_step": 577917, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.011925220489502, "global_step": 577918, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9361718893051147, "global_step": 577919, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.027458906173706, "global_step": 577920, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0391478538513184, "global_step": 577921, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0003650188446045, "global_step": 577922, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.99984610080719, "global_step": 577923, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9774795770645142, "global_step": 577924, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.03952956199646, "global_step": 577925, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0794677734375, "global_step": 577926, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0639843940734863, "global_step": 577927, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9838337898254395, "global_step": 577928, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.057729721069336, "global_step": 577929, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.110797882080078, "global_step": 577930, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.103794813156128, "global_step": 577931, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0143394470214844, "global_step": 577932, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.043081045150757, "global_step": 577933, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.048750877380371, "global_step": 577934, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0599851608276367, "global_step": 577935, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.020641803741455, "global_step": 577936, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.00205659866333, "global_step": 577937, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9730994701385498, "global_step": 577938, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1115317344665527, "global_step": 577939, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0482990741729736, "global_step": 577940, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0369207859039307, "global_step": 577941, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.072618246078491, "global_step": 577942, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0576865673065186, "global_step": 577943, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0414981842041016, "global_step": 577944, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0048513412475586, "global_step": 577945, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.8863606452941895, "global_step": 577946, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0053725242614746, "global_step": 577947, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.043323040008545, "global_step": 577948, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0663275718688965, "global_step": 577949, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.074401378631592, "global_step": 577950, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0002706050872803, "global_step": 577951, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0622923374176025, "global_step": 577952, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.994397521018982, "global_step": 577953, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0858535766601562, "global_step": 577954, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9562630653381348, "global_step": 577955, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9561115503311157, "global_step": 577956, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9802497625350952, "global_step": 577957, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9592558145523071, "global_step": 577958, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1068058013916016, "global_step": 577959, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.045652389526367, "global_step": 577960, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0150890350341797, "global_step": 577961, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.059814691543579, "global_step": 577962, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.010847568511963, "global_step": 577963, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9746558666229248, "global_step": 577964, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9614375829696655, "global_step": 577965, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0048880577087402, "global_step": 577966, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0157830715179443, "global_step": 577967, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.026906967163086, "global_step": 577968, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.023003339767456, "global_step": 577969, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0501344203948975, "global_step": 577970, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.008936882019043, "global_step": 577971, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.121103286743164, "global_step": 577972, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0423498153686523, "global_step": 577973, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.094872236251831, "global_step": 577974, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9868571758270264, "global_step": 577975, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9978790283203125, "global_step": 577976, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0301249027252197, "global_step": 577977, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0426719188690186, "global_step": 577978, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9944862127304077, "global_step": 577979, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0817086696624756, "global_step": 577980, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.977364182472229, "global_step": 577981, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9765888452529907, "global_step": 577982, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9353901147842407, "global_step": 577983, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0042331218719482, "global_step": 577984, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.981549620628357, "global_step": 577985, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0756945610046387, "global_step": 577986, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.004361867904663, "global_step": 577987, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9654803276062012, "global_step": 577988, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9849056005477905, "global_step": 577989, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0692949295043945, "global_step": 577990, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.957464575767517, "global_step": 577991, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9709306955337524, "global_step": 577992, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1039958000183105, "global_step": 577993, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.064409017562866, "global_step": 577994, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.05237078666687, "global_step": 577995, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.031797170639038, "global_step": 577996, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1272900104522705, "global_step": 577997, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.981712818145752, "global_step": 577998, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0926425457000732, "global_step": 577999, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.001432180404663, "global_step": 578000, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0366687774658203, "global_step": 578001, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0106263160705566, "global_step": 578002, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.055582284927368, "global_step": 578003, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0217361450195312, "global_step": 578004, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.009591579437256, "global_step": 578005, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.026907205581665, "global_step": 578006, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0765206813812256, "global_step": 578007, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0875205993652344, "global_step": 578008, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9409884214401245, "global_step": 578009, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.04668927192688, "global_step": 578010, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9293729066848755, "global_step": 578011, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9737306833267212, "global_step": 578012, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9657124280929565, "global_step": 578013, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0720043182373047, "global_step": 578014, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0587170124053955, "global_step": 578015, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9744168519973755, "global_step": 578016, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.009014129638672, "global_step": 578017, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.992899775505066, "global_step": 578018, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0512287616729736, "global_step": 578019, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0490050315856934, "global_step": 578020, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0696966648101807, "global_step": 578021, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0942564010620117, "global_step": 578022, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0332958698272705, "global_step": 578023, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9343043565750122, "global_step": 578024, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.947702169418335, "global_step": 578025, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0259203910827637, "global_step": 578026, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.985576868057251, "global_step": 578027, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9824142456054688, "global_step": 578028, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0450098514556885, "global_step": 578029, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.985528588294983, "global_step": 578030, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.99153733253479, "global_step": 578031, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.010582447052002, "global_step": 578032, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0841617584228516, "global_step": 578033, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.10011887550354, "global_step": 578034, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.978615403175354, "global_step": 578035, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.045875072479248, "global_step": 578036, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0818421840667725, "global_step": 578037, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.01820969581604, "global_step": 578038, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0084545612335205, "global_step": 578039, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.09774112701416, "global_step": 578040, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9774751663208008, "global_step": 578041, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.091059446334839, "global_step": 578042, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0397777557373047, "global_step": 578043, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0819084644317627, "global_step": 578044, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.014288902282715, "global_step": 578045, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0647315979003906, "global_step": 578046, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9735673666000366, "global_step": 578047, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0329535007476807, "global_step": 578048, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.051694393157959, "global_step": 578049, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.013840436935425, "global_step": 578050, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.966953158378601, "global_step": 578051, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9504828453063965, "global_step": 578052, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0412020683288574, "global_step": 578053, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0123486518859863, "global_step": 578054, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0256292819976807, "global_step": 578055, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9205286502838135, "global_step": 578056, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0368545055389404, "global_step": 578057, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9572926759719849, "global_step": 578058, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.977200984954834, "global_step": 578059, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9918560981750488, "global_step": 578060, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0999596118927, "global_step": 578061, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.086894989013672, "global_step": 578062, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0503785610198975, "global_step": 578063, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0469553470611572, "global_step": 578064, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.09725022315979, "global_step": 578065, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9721285104751587, "global_step": 578066, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.011461019515991, "global_step": 578067, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0143609046936035, "global_step": 578068, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0176401138305664, "global_step": 578069, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0270838737487793, "global_step": 578070, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.090799331665039, "global_step": 578071, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.107149600982666, "global_step": 578072, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0481417179107666, "global_step": 578073, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.097259283065796, "global_step": 578074, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.991013765335083, "global_step": 578075, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1185498237609863, "global_step": 578076, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9876701831817627, "global_step": 578077, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0008716583251953, "global_step": 578078, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9865597486495972, "global_step": 578079, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.012373685836792, "global_step": 578080, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9844788312911987, "global_step": 578081, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.088165044784546, "global_step": 578082, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9916880130767822, "global_step": 578083, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.012152671813965, "global_step": 578084, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.089895725250244, "global_step": 578085, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0376193523406982, "global_step": 578086, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9504506587982178, "global_step": 578087, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.931502103805542, "global_step": 578088, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0524792671203613, "global_step": 578089, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9467442035675049, "global_step": 578090, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.009373188018799, "global_step": 578091, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0542237758636475, "global_step": 578092, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.077681303024292, "global_step": 578093, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9987598657608032, "global_step": 578094, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0658583641052246, "global_step": 578095, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.88044011592865, "global_step": 578096, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.075265884399414, "global_step": 578097, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0173676013946533, "global_step": 578098, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9691448211669922, "global_step": 578099, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9547663927078247, "global_step": 578100, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9469060897827148, "global_step": 578101, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0709128379821777, "global_step": 578102, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0609676837921143, "global_step": 578103, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.949203610420227, "global_step": 578104, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9842913150787354, "global_step": 578105, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9743186235427856, "global_step": 578106, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0371270179748535, "global_step": 578107, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9602932929992676, "global_step": 578108, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0471067428588867, "global_step": 578109, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.984815239906311, "global_step": 578110, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0910439491271973, "global_step": 578111, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0352530479431152, "global_step": 578112, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9892857074737549, "global_step": 578113, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.12343168258667, "global_step": 578114, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.014861822128296, "global_step": 578115, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0164177417755127, "global_step": 578116, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9956049919128418, "global_step": 578117, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0567092895507812, "global_step": 578118, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.013148069381714, "global_step": 578119, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.058206558227539, "global_step": 578120, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.028578758239746, "global_step": 578121, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.980098009109497, "global_step": 578122, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.129089593887329, "global_step": 578123, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1095640659332275, "global_step": 578124, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0282928943634033, "global_step": 578125, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.065398931503296, "global_step": 578126, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.020137310028076, "global_step": 578127, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0091049671173096, "global_step": 578128, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9853861331939697, "global_step": 578129, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.043332815170288, "global_step": 578130, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0105857849121094, "global_step": 578131, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0724525451660156, "global_step": 578132, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.021702766418457, "global_step": 578133, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9360413551330566, "global_step": 578134, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0049192905426025, "global_step": 578135, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1123247146606445, "global_step": 578136, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9205132722854614, "global_step": 578137, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0720319747924805, "global_step": 578138, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1070668697357178, "global_step": 578139, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0119621753692627, "global_step": 578140, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9611501693725586, "global_step": 578141, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9492472410202026, "global_step": 578142, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.00388765335083, "global_step": 578143, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0503153800964355, "global_step": 578144, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.00785231590271, "global_step": 578145, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.03234601020813, "global_step": 578146, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0238993167877197, "global_step": 578147, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0307986736297607, "global_step": 578148, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.037285327911377, "global_step": 578149, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0173261165618896, "global_step": 578150, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.057279586791992, "global_step": 578151, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.089958906173706, "global_step": 578152, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.103196144104004, "global_step": 578153, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9431737661361694, "global_step": 578154, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9780139923095703, "global_step": 578155, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9664602279663086, "global_step": 578156, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0070414543151855, "global_step": 578157, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0561084747314453, "global_step": 578158, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.012251615524292, "global_step": 578159, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0697922706604004, "global_step": 578160, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.935426950454712, "global_step": 578161, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0248754024505615, "global_step": 578162, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0191969871520996, "global_step": 578163, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9749292135238647, "global_step": 578164, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.047941207885742, "global_step": 578165, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.010578155517578, "global_step": 578166, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0137274265289307, "global_step": 578167, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9699219465255737, "global_step": 578168, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.10215425491333, "global_step": 578169, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0353615283966064, "global_step": 578170, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0750317573547363, "global_step": 578171, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0319581031799316, "global_step": 578172, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0217950344085693, "global_step": 578173, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9624755382537842, "global_step": 578174, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9424160718917847, "global_step": 578175, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0139718055725098, "global_step": 578176, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0376203060150146, "global_step": 578177, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0179927349090576, "global_step": 578178, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.007084846496582, "global_step": 578179, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9859086275100708, "global_step": 578180, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.053861141204834, "global_step": 578181, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9282846450805664, "global_step": 578182, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0284993648529053, "global_step": 578183, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0385658740997314, "global_step": 578184, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.078029155731201, "global_step": 578185, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9328010082244873, "global_step": 578186, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9925955533981323, "global_step": 578187, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.019087314605713, "global_step": 578188, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9244838953018188, "global_step": 578189, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0694220066070557, "global_step": 578190, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0278141498565674, "global_step": 578191, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0938827991485596, "global_step": 578192, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0182864665985107, "global_step": 578193, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0046708583831787, "global_step": 578194, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9486010074615479, "global_step": 578195, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9970407485961914, "global_step": 578196, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0498714447021484, "global_step": 578197, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0680010318756104, "global_step": 578198, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9522733688354492, "global_step": 578199, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0439798831939697, "global_step": 578200, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0045270919799805, "global_step": 578201, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0024189949035645, "global_step": 578202, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.003633499145508, "global_step": 578203, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0522725582122803, "global_step": 578204, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0135858058929443, "global_step": 578205, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9982982873916626, "global_step": 578206, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0786292552948, "global_step": 578207, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9952197074890137, "global_step": 578208, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0054619312286377, "global_step": 578209, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.031623363494873, "global_step": 578210, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0721993446350098, "global_step": 578211, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.030925750732422, "global_step": 578212, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9741179943084717, "global_step": 578213, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0494093894958496, "global_step": 578214, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.048837184906006, "global_step": 578215, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.049762010574341, "global_step": 578216, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9984720945358276, "global_step": 578217, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9884443283081055, "global_step": 578218, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.028106689453125, "global_step": 578219, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.02254319190979, "global_step": 578220, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.000335693359375, "global_step": 578221, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.005366325378418, "global_step": 578222, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0165939331054688, "global_step": 578223, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.020230770111084, "global_step": 578224, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0021610260009766, "global_step": 578225, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.01128888130188, "global_step": 578226, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0472331047058105, "global_step": 578227, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9863957166671753, "global_step": 578228, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.061347246170044, "global_step": 578229, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9724500179290771, "global_step": 578230, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9840303659439087, "global_step": 578231, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.942909836769104, "global_step": 578232, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0863208770751953, "global_step": 578233, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0152571201324463, "global_step": 578234, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.015902280807495, "global_step": 578235, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0469586849212646, "global_step": 578236, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0626466274261475, "global_step": 578237, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.96629798412323, "global_step": 578238, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.052875280380249, "global_step": 578239, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9617388248443604, "global_step": 578240, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0416321754455566, "global_step": 578241, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0816965103149414, "global_step": 578242, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0914289951324463, "global_step": 578243, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9521138668060303, "global_step": 578244, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.017864227294922, "global_step": 578245, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.102708101272583, "global_step": 578246, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.047868251800537, "global_step": 578247, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.112679958343506, "global_step": 578248, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.069890260696411, "global_step": 578249, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1154825687408447, "global_step": 578250, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9426603317260742, "global_step": 578251, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.046464443206787, "global_step": 578252, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1152827739715576, "global_step": 578253, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9947925806045532, "global_step": 578254, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9899348020553589, "global_step": 578255, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.092668056488037, "global_step": 578256, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9578434228897095, "global_step": 578257, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1042778491973877, "global_step": 578258, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.048297643661499, "global_step": 578259, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9897583723068237, "global_step": 578260, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9917632341384888, "global_step": 578261, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9679856300354004, "global_step": 578262, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.049356460571289, "global_step": 578263, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.056820869445801, "global_step": 578264, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.014188528060913, "global_step": 578265, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0613694190979004, "global_step": 578266, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.032252788543701, "global_step": 578267, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0703024864196777, "global_step": 578268, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.097720146179199, "global_step": 578269, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0043044090270996, "global_step": 578270, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0707786083221436, "global_step": 578271, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0927417278289795, "global_step": 578272, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.109395980834961, "global_step": 578273, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0538830757141113, "global_step": 578274, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9831372499465942, "global_step": 578275, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.035419464111328, "global_step": 578276, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9379942417144775, "global_step": 578277, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.912980556488037, "global_step": 578278, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0444836616516113, "global_step": 578279, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0870461463928223, "global_step": 578280, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.047117233276367, "global_step": 578281, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9828951358795166, "global_step": 578282, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0921497344970703, "global_step": 578283, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9725428819656372, "global_step": 578284, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.953822135925293, "global_step": 578285, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0439910888671875, "global_step": 578286, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9352085590362549, "global_step": 578287, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.01713228225708, "global_step": 578288, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.072810411453247, "global_step": 578289, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0020484924316406, "global_step": 578290, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1187796592712402, "global_step": 578291, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9699862003326416, "global_step": 578292, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9760905504226685, "global_step": 578293, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.077275514602661, "global_step": 578294, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9477180242538452, "global_step": 578295, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.032733917236328, "global_step": 578296, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.063629388809204, "global_step": 578297, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9961127042770386, "global_step": 578298, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9930545091629028, "global_step": 578299, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9046958684921265, "global_step": 578300, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9874833822250366, "global_step": 578301, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9481195211410522, "global_step": 578302, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0152831077575684, "global_step": 578303, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.059372901916504, "global_step": 578304, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9678865671157837, "global_step": 578305, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0243022441864014, "global_step": 578306, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9487149715423584, "global_step": 578307, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.098252296447754, "global_step": 578308, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9360456466674805, "global_step": 578309, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0591650009155273, "global_step": 578310, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.991243600845337, "global_step": 578311, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0494725704193115, "global_step": 578312, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.002488851547241, "global_step": 578313, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9915021657943726, "global_step": 578314, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1009953022003174, "global_step": 578315, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0752570629119873, "global_step": 578316, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9499187469482422, "global_step": 578317, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9937524795532227, "global_step": 578318, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.039118528366089, "global_step": 578319, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0001776218414307, "global_step": 578320, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0354037284851074, "global_step": 578321, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9707990884780884, "global_step": 578322, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.033590793609619, "global_step": 578323, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.083510637283325, "global_step": 578324, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9757307767868042, "global_step": 578325, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0847554206848145, "global_step": 578326, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.072565793991089, "global_step": 578327, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0000381469726562, "global_step": 578328, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.010802984237671, "global_step": 578329, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.009521245956421, "global_step": 578330, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9694448709487915, "global_step": 578331, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0529680252075195, "global_step": 578332, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.991958737373352, "global_step": 578333, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.999545693397522, "global_step": 578334, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0424952507019043, "global_step": 578335, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0460336208343506, "global_step": 578336, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.016087293624878, "global_step": 578337, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9175492525100708, "global_step": 578338, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.184192657470703, "global_step": 578339, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0175766944885254, "global_step": 578340, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.993111491203308, "global_step": 578341, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.974281907081604, "global_step": 578342, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0398194789886475, "global_step": 578343, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.929315447807312, "global_step": 578344, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0245532989501953, "global_step": 578345, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0552594661712646, "global_step": 578346, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0558061599731445, "global_step": 578347, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.023637056350708, "global_step": 578348, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.026951789855957, "global_step": 578349, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.002347230911255, "global_step": 578350, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0151824951171875, "global_step": 578351, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0726962089538574, "global_step": 578352, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.054431200027466, "global_step": 578353, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.047030448913574, "global_step": 578354, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1241300106048584, "global_step": 578355, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.046694278717041, "global_step": 578356, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.027621030807495, "global_step": 578357, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9364925622940063, "global_step": 578358, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.044009208679199, "global_step": 578359, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.991786241531372, "global_step": 578360, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0633811950683594, "global_step": 578361, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9930589199066162, "global_step": 578362, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.024353265762329, "global_step": 578363, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0451347827911377, "global_step": 578364, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0056803226470947, "global_step": 578365, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.030904531478882, "global_step": 578366, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9703465700149536, "global_step": 578367, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.037888765335083, "global_step": 578368, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9798332452774048, "global_step": 578369, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0583877563476562, "global_step": 578370, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0886929035186768, "global_step": 578371, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0167617797851562, "global_step": 578372, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.058814764022827, "global_step": 578373, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.02339506149292, "global_step": 578374, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.013314723968506, "global_step": 578375, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.944339632987976, "global_step": 578376, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0019304752349854, "global_step": 578377, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0346460342407227, "global_step": 578378, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.982322335243225, "global_step": 578379, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9264663457870483, "global_step": 578380, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.034133195877075, "global_step": 578381, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.001694917678833, "global_step": 578382, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9944990873336792, "global_step": 578383, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0212626457214355, "global_step": 578384, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.078651189804077, "global_step": 578385, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.981101155281067, "global_step": 578386, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9318066835403442, "global_step": 578387, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.066396951675415, "global_step": 578388, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9083452224731445, "global_step": 578389, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0367062091827393, "global_step": 578390, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.048980951309204, "global_step": 578391, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9267330169677734, "global_step": 578392, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0415308475494385, "global_step": 578393, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.07148814201355, "global_step": 578394, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.131638526916504, "global_step": 578395, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.048139810562134, "global_step": 578396, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.08733868598938, "global_step": 578397, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0065879821777344, "global_step": 578398, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9430978298187256, "global_step": 578399, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0115861892700195, "global_step": 578400, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0175583362579346, "global_step": 578401, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.075735330581665, "global_step": 578402, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0177206993103027, "global_step": 578403, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9423781633377075, "global_step": 578404, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.980404257774353, "global_step": 578405, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.019623041152954, "global_step": 578406, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0341556072235107, "global_step": 578407, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0624401569366455, "global_step": 578408, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.029388427734375, "global_step": 578409, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.050504684448242, "global_step": 578410, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9794467687606812, "global_step": 578411, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0419352054595947, "global_step": 578412, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.032639503479004, "global_step": 578413, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.996268630027771, "global_step": 578414, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0779075622558594, "global_step": 578415, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0232770442962646, "global_step": 578416, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9931600093841553, "global_step": 578417, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.047154426574707, "global_step": 578418, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.068047046661377, "global_step": 578419, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.069098949432373, "global_step": 578420, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1139214038848877, "global_step": 578421, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.04197359085083, "global_step": 578422, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.04946231842041, "global_step": 578423, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.024702548980713, "global_step": 578424, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0785365104675293, "global_step": 578425, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.061138153076172, "global_step": 578426, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0263867378234863, "global_step": 578427, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1190378665924072, "global_step": 578428, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.031752109527588, "global_step": 578429, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.002197504043579, "global_step": 578430, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0822575092315674, "global_step": 578431, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.010446071624756, "global_step": 578432, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0857110023498535, "global_step": 578433, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.00254225730896, "global_step": 578434, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0317935943603516, "global_step": 578435, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.073202610015869, "global_step": 578436, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.019794464111328, "global_step": 578437, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.003787040710449, "global_step": 578438, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1647372245788574, "global_step": 578439, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0672788619995117, "global_step": 578440, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0043540000915527, "global_step": 578441, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9851731061935425, "global_step": 578442, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0223872661590576, "global_step": 578443, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9968681335449219, "global_step": 578444, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.97048020362854, "global_step": 578445, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0309197902679443, "global_step": 578446, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0968761444091797, "global_step": 578447, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9975303411483765, "global_step": 578448, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0274229049682617, "global_step": 578449, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0469043254852295, "global_step": 578450, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0778253078460693, "global_step": 578451, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.061427116394043, "global_step": 578452, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.044050455093384, "global_step": 578453, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.021916151046753, "global_step": 578454, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0379371643066406, "global_step": 578455, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.082428455352783, "global_step": 578456, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.940245509147644, "global_step": 578457, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.976537823677063, "global_step": 578458, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9948011636734009, "global_step": 578459, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.010673761367798, "global_step": 578460, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9461301565170288, "global_step": 578461, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0373589992523193, "global_step": 578462, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.021719455718994, "global_step": 578463, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.999137043952942, "global_step": 578464, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9881645441055298, "global_step": 578465, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.957719087600708, "global_step": 578466, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9919716119766235, "global_step": 578467, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.042492628097534, "global_step": 578468, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9592986106872559, "global_step": 578469, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1167941093444824, "global_step": 578470, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0065975189208984, "global_step": 578471, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0321269035339355, "global_step": 578472, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9978482723236084, "global_step": 578473, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0496163368225098, "global_step": 578474, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.991549015045166, "global_step": 578475, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1223807334899902, "global_step": 578476, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.02667236328125, "global_step": 578477, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0332908630371094, "global_step": 578478, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.977346658706665, "global_step": 578479, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0371508598327637, "global_step": 578480, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0751311779022217, "global_step": 578481, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0575661659240723, "global_step": 578482, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0578930377960205, "global_step": 578483, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9767298698425293, "global_step": 578484, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9899626970291138, "global_step": 578485, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9884464740753174, "global_step": 578486, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.009998083114624, "global_step": 578487, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9874612092971802, "global_step": 578488, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1050729751586914, "global_step": 578489, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0072593688964844, "global_step": 578490, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0122547149658203, "global_step": 578491, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.006901264190674, "global_step": 578492, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9430633783340454, "global_step": 578493, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1396281719207764, "global_step": 578494, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.098529100418091, "global_step": 578495, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.007767677307129, "global_step": 578496, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.092977523803711, "global_step": 578497, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0076184272766113, "global_step": 578498, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0681025981903076, "global_step": 578499, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.060000419616699, "global_step": 578500, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.068915843963623, "global_step": 578501, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.100708484649658, "global_step": 578502, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1110997200012207, "global_step": 578503, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.081716775894165, "global_step": 578504, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.014336585998535, "global_step": 578505, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9898760318756104, "global_step": 578506, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0967862606048584, "global_step": 578507, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0402541160583496, "global_step": 578508, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.060452461242676, "global_step": 578509, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.03973388671875, "global_step": 578510, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0277209281921387, "global_step": 578511, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.040449857711792, "global_step": 578512, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.96178138256073, "global_step": 578513, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1165332794189453, "global_step": 578514, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0212740898132324, "global_step": 578515, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.14056134223938, "global_step": 578516, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.045377731323242, "global_step": 578517, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1616933345794678, "global_step": 578518, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.053729772567749, "global_step": 578519, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0377721786499023, "global_step": 578520, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0728580951690674, "global_step": 578521, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.028522491455078, "global_step": 578522, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9043983221054077, "global_step": 578523, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.014988899230957, "global_step": 578524, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9233133792877197, "global_step": 578525, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0574402809143066, "global_step": 578526, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.063154935836792, "global_step": 578527, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.032047748565674, "global_step": 578528, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0687754154205322, "global_step": 578529, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0499532222747803, "global_step": 578530, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.043459177017212, "global_step": 578531, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0348803997039795, "global_step": 578532, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.920717477798462, "global_step": 578533, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9758964776992798, "global_step": 578534, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9811979532241821, "global_step": 578535, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.07527494430542, "global_step": 578536, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.074906587600708, "global_step": 578537, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.111717939376831, "global_step": 578538, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9660793542861938, "global_step": 578539, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.019022226333618, "global_step": 578540, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9705288410186768, "global_step": 578541, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.013915538787842, "global_step": 578542, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.009765386581421, "global_step": 578543, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0286386013031006, "global_step": 578544, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.023049831390381, "global_step": 578545, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0827858448028564, "global_step": 578546, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.017146348953247, "global_step": 578547, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0528810024261475, "global_step": 578548, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9682508707046509, "global_step": 578549, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0827765464782715, "global_step": 578550, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1037392616271973, "global_step": 578551, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0570449829101562, "global_step": 578552, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9529962539672852, "global_step": 578553, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.031420946121216, "global_step": 578554, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9330459833145142, "global_step": 578555, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1104750633239746, "global_step": 578556, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0470452308654785, "global_step": 578557, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0117294788360596, "global_step": 578558, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.99188232421875, "global_step": 578559, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.974868893623352, "global_step": 578560, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9997425079345703, "global_step": 578561, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.046658515930176, "global_step": 578562, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0324225425720215, "global_step": 578563, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0552895069122314, "global_step": 578564, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.032935857772827, "global_step": 578565, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0483477115631104, "global_step": 578566, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0581417083740234, "global_step": 578567, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.069396734237671, "global_step": 578568, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1114346981048584, "global_step": 578569, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.038952112197876, "global_step": 578570, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0137996673583984, "global_step": 578571, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0169858932495117, "global_step": 578572, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.116389036178589, "global_step": 578573, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0152127742767334, "global_step": 578574, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9806896448135376, "global_step": 578575, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1125338077545166, "global_step": 578576, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.949553370475769, "global_step": 578577, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9709620475769043, "global_step": 578578, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0612845420837402, "global_step": 578579, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0369999408721924, "global_step": 578580, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9906904697418213, "global_step": 578581, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9932329654693604, "global_step": 578582, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1204397678375244, "global_step": 578583, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9243266582489014, "global_step": 578584, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9613142013549805, "global_step": 578585, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.093592643737793, "global_step": 578586, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0123534202575684, "global_step": 578587, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.15802264213562, "global_step": 578588, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.037470579147339, "global_step": 578589, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0089621543884277, "global_step": 578590, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9209860563278198, "global_step": 578591, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.032738208770752, "global_step": 578592, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0643749237060547, "global_step": 578593, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9552022218704224, "global_step": 578594, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0824332237243652, "global_step": 578595, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9646857976913452, "global_step": 578596, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.006882905960083, "global_step": 578597, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9997973442077637, "global_step": 578598, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0399973392486572, "global_step": 578599, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.981796383857727, "global_step": 578600, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0616047382354736, "global_step": 578601, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1115283966064453, "global_step": 578602, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0040929317474365, "global_step": 578603, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0336782932281494, "global_step": 578604, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0338313579559326, "global_step": 578605, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0562493801116943, "global_step": 578606, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9859670400619507, "global_step": 578607, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.002640962600708, "global_step": 578608, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.020907402038574, "global_step": 578609, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.016909599304199, "global_step": 578610, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0234410762786865, "global_step": 578611, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.048715591430664, "global_step": 578612, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0615644454956055, "global_step": 578613, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0367281436920166, "global_step": 578614, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9292490482330322, "global_step": 578615, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0599191188812256, "global_step": 578616, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.021693468093872, "global_step": 578617, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.018505573272705, "global_step": 578618, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1435959339141846, "global_step": 578619, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9493567943572998, "global_step": 578620, "epoch": 946, "lr": 5e-05}
{"train_loss": 1.9673434495925903, "global_step": 578621, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.032175302505493, "global_step": 578622, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.1089680194854736, "global_step": 578623, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0778355598449707, "global_step": 578624, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0221753120422363, "global_step": 578625, "epoch": 946, "lr": 5e-05}
{"train_loss": 2.0068938732147217, "global_step": 578626, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9421396255493164, "global_step": 578627, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.000535726547241, "global_step": 578628, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0540149211883545, "global_step": 578629, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9738049507141113, "global_step": 578630, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0983643531799316, "global_step": 578631, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9380799531936646, "global_step": 578632, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9678773880004883, "global_step": 578633, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9999232292175293, "global_step": 578634, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1112208366394043, "global_step": 578635, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0332465171813965, "global_step": 578636, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0105221271514893, "global_step": 578637, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.974666714668274, "global_step": 578638, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.99104642868042, "global_step": 578639, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9865750074386597, "global_step": 578640, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.036266803741455, "global_step": 578641, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.998956561088562, "global_step": 578642, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.007693290710449, "global_step": 578643, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9575221538543701, "global_step": 578644, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9856146574020386, "global_step": 578645, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9677419662475586, "global_step": 578646, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0571987628936768, "global_step": 578647, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.03527569770813, "global_step": 578648, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0407514572143555, "global_step": 578649, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0342397689819336, "global_step": 578650, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.922520399093628, "global_step": 578651, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.04996395111084, "global_step": 578652, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0198824405670166, "global_step": 578653, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.952879786491394, "global_step": 578654, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9606351852416992, "global_step": 578655, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.015401601791382, "global_step": 578656, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.025559902191162, "global_step": 578657, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9850281476974487, "global_step": 578658, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.001288414001465, "global_step": 578659, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.019315481185913, "global_step": 578660, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.066554069519043, "global_step": 578661, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0067031383514404, "global_step": 578662, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9701062440872192, "global_step": 578663, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9860519170761108, "global_step": 578664, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.00980544090271, "global_step": 578665, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9719008207321167, "global_step": 578666, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9507582187652588, "global_step": 578667, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0743863582611084, "global_step": 578668, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0054633617401123, "global_step": 578669, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.8928765058517456, "global_step": 578670, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0021071434020996, "global_step": 578671, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.001677989959717, "global_step": 578672, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9183564186096191, "global_step": 578673, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0500242710113525, "global_step": 578674, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9847356081008911, "global_step": 578675, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9792698621749878, "global_step": 578676, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9847999811172485, "global_step": 578677, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9933743476867676, "global_step": 578678, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.083932399749756, "global_step": 578679, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.993738055229187, "global_step": 578680, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.014432907104492, "global_step": 578681, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9963786602020264, "global_step": 578682, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9919966459274292, "global_step": 578683, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0197153091430664, "global_step": 578684, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0891313552856445, "global_step": 578685, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0417754650115967, "global_step": 578686, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9979761838912964, "global_step": 578687, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0045130252838135, "global_step": 578688, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0425336360931396, "global_step": 578689, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.015535354614258, "global_step": 578690, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0007989406585693, "global_step": 578691, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9975594282150269, "global_step": 578692, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9444606304168701, "global_step": 578693, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.109992265701294, "global_step": 578694, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9750232696533203, "global_step": 578695, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9848663806915283, "global_step": 578696, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.03733491897583, "global_step": 578697, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.064829111099243, "global_step": 578698, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.995180368423462, "global_step": 578699, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0795106887817383, "global_step": 578700, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.079611301422119, "global_step": 578701, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.968234896659851, "global_step": 578702, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9842121601104736, "global_step": 578703, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9450058937072754, "global_step": 578704, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9950777292251587, "global_step": 578705, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0492985248565674, "global_step": 578706, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.023697853088379, "global_step": 578707, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.005713701248169, "global_step": 578708, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9807184934616089, "global_step": 578709, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9011857509613037, "global_step": 578710, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.042961359024048, "global_step": 578711, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.017329216003418, "global_step": 578712, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0075559616088867, "global_step": 578713, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0448267459869385, "global_step": 578714, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0476155281066895, "global_step": 578715, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9833166599273682, "global_step": 578716, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0249414443969727, "global_step": 578717, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.02609920501709, "global_step": 578718, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9854177236557007, "global_step": 578719, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9448158740997314, "global_step": 578720, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9402662515640259, "global_step": 578721, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0741844177246094, "global_step": 578722, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.019881248474121, "global_step": 578723, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.031677007675171, "global_step": 578724, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0139036178588867, "global_step": 578725, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1158552169799805, "global_step": 578726, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9770798683166504, "global_step": 578727, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.069303274154663, "global_step": 578728, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9908082485198975, "global_step": 578729, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9875460863113403, "global_step": 578730, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.8980417251586914, "global_step": 578731, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.010247230529785, "global_step": 578732, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0401875972747803, "global_step": 578733, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.088690757751465, "global_step": 578734, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0293943881988525, "global_step": 578735, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0158562660217285, "global_step": 578736, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.953939437866211, "global_step": 578737, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9983446598052979, "global_step": 578738, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9795117378234863, "global_step": 578739, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.057079315185547, "global_step": 578740, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1096129417419434, "global_step": 578741, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9874510765075684, "global_step": 578742, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0049521923065186, "global_step": 578743, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9639731645584106, "global_step": 578744, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9865692853927612, "global_step": 578745, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9579275846481323, "global_step": 578746, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0259146690368652, "global_step": 578747, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.021864414215088, "global_step": 578748, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9901728630065918, "global_step": 578749, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.074387788772583, "global_step": 578750, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9808920621871948, "global_step": 578751, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.058885097503662, "global_step": 578752, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0046963691711426, "global_step": 578753, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0354106426239014, "global_step": 578754, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0454492568969727, "global_step": 578755, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0758492946624756, "global_step": 578756, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.977036952972412, "global_step": 578757, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0682950019836426, "global_step": 578758, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9184091091156006, "global_step": 578759, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0057387351989746, "global_step": 578760, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0502395629882812, "global_step": 578761, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.06156849861145, "global_step": 578762, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0189411640167236, "global_step": 578763, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0749423503875732, "global_step": 578764, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.028498888015747, "global_step": 578765, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9833253622055054, "global_step": 578766, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.871419072151184, "global_step": 578767, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.982285499572754, "global_step": 578768, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.017519235610962, "global_step": 578769, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.976846694946289, "global_step": 578770, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9867225885391235, "global_step": 578771, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9582271575927734, "global_step": 578772, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0181596279144287, "global_step": 578773, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.047076940536499, "global_step": 578774, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.989820122718811, "global_step": 578775, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9880647659301758, "global_step": 578776, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9671911001205444, "global_step": 578777, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9838511943817139, "global_step": 578778, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0589282512664795, "global_step": 578779, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9941130876541138, "global_step": 578780, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0401344299316406, "global_step": 578781, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.030769109725952, "global_step": 578782, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0207087993621826, "global_step": 578783, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0309667587280273, "global_step": 578784, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0332705974578857, "global_step": 578785, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9990472793579102, "global_step": 578786, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9649598598480225, "global_step": 578787, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9825726747512817, "global_step": 578788, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9963548183441162, "global_step": 578789, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0452301502227783, "global_step": 578790, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0523111820220947, "global_step": 578791, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0453062057495117, "global_step": 578792, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.941975712776184, "global_step": 578793, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9654219150543213, "global_step": 578794, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.8732960224151611, "global_step": 578795, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0509839057922363, "global_step": 578796, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0310349464416504, "global_step": 578797, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.068620204925537, "global_step": 578798, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.011197805404663, "global_step": 578799, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0408194065093994, "global_step": 578800, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.061525821685791, "global_step": 578801, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.067803382873535, "global_step": 578802, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.051234483718872, "global_step": 578803, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0433642864227295, "global_step": 578804, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.095440626144409, "global_step": 578805, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.043544054031372, "global_step": 578806, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0148067474365234, "global_step": 578807, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0231573581695557, "global_step": 578808, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.049917697906494, "global_step": 578809, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.043649673461914, "global_step": 578810, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9849574565887451, "global_step": 578811, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9628956317901611, "global_step": 578812, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.988453984260559, "global_step": 578813, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0506019592285156, "global_step": 578814, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.008410930633545, "global_step": 578815, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.03523850440979, "global_step": 578816, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.070389986038208, "global_step": 578817, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0707592964172363, "global_step": 578818, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9212924242019653, "global_step": 578819, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9931182861328125, "global_step": 578820, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.02424693107605, "global_step": 578821, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9606019258499146, "global_step": 578822, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9728267192840576, "global_step": 578823, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0364208221435547, "global_step": 578824, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.053570508956909, "global_step": 578825, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9384340047836304, "global_step": 578826, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9902844429016113, "global_step": 578827, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9883654117584229, "global_step": 578828, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0676651000976562, "global_step": 578829, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9899518489837646, "global_step": 578830, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9229356050491333, "global_step": 578831, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0341827869415283, "global_step": 578832, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0767662525177, "global_step": 578833, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.950827717781067, "global_step": 578834, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9879071712493896, "global_step": 578835, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0002434253692627, "global_step": 578836, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0110480785369873, "global_step": 578837, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.049053192138672, "global_step": 578838, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.043916702270508, "global_step": 578839, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9653406143188477, "global_step": 578840, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9909733533859253, "global_step": 578841, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.066810131072998, "global_step": 578842, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.066335678100586, "global_step": 578843, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.034165382385254, "global_step": 578844, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9636880159378052, "global_step": 578845, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.029923677444458, "global_step": 578846, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.994244933128357, "global_step": 578847, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0120162963867188, "global_step": 578848, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.056443929672241, "global_step": 578849, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0582222938537598, "global_step": 578850, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0492660999298096, "global_step": 578851, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9711359739303589, "global_step": 578852, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0147862434387207, "global_step": 578853, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.981573224067688, "global_step": 578854, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0113320350646973, "global_step": 578855, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0852017402648926, "global_step": 578856, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9018688201904297, "global_step": 578857, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0182549953460693, "global_step": 578858, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0700106620788574, "global_step": 578859, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0113027095794678, "global_step": 578860, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0158069133758545, "global_step": 578861, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9634970426559448, "global_step": 578862, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9702833890914917, "global_step": 578863, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0558836460113525, "global_step": 578864, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0298657417297363, "global_step": 578865, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0324625968933105, "global_step": 578866, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9795129299163818, "global_step": 578867, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0186617374420166, "global_step": 578868, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0010275840759277, "global_step": 578869, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9982507228851318, "global_step": 578870, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.057302474975586, "global_step": 578871, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9315346479415894, "global_step": 578872, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9920141696929932, "global_step": 578873, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.926711082458496, "global_step": 578874, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.056990146636963, "global_step": 578875, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9910953044891357, "global_step": 578876, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.003026247024536, "global_step": 578877, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.931766152381897, "global_step": 578878, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9624148607254028, "global_step": 578879, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9724998474121094, "global_step": 578880, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.043846368789673, "global_step": 578881, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.000255584716797, "global_step": 578882, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0915210247039795, "global_step": 578883, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9282617568969727, "global_step": 578884, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9685739278793335, "global_step": 578885, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0384345054626465, "global_step": 578886, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9727604389190674, "global_step": 578887, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.057185173034668, "global_step": 578888, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0209314823150635, "global_step": 578889, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9915194511413574, "global_step": 578890, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9926193952560425, "global_step": 578891, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0752224922180176, "global_step": 578892, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0634310245513916, "global_step": 578893, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0252792835235596, "global_step": 578894, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.141000747680664, "global_step": 578895, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.8607239723205566, "global_step": 578896, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.032680034637451, "global_step": 578897, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.035942792892456, "global_step": 578898, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0087525844573975, "global_step": 578899, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0320377349853516, "global_step": 578900, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.112074375152588, "global_step": 578901, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.060889959335327, "global_step": 578902, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.94394850730896, "global_step": 578903, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9797009229660034, "global_step": 578904, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9803798198699951, "global_step": 578905, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0900936126708984, "global_step": 578906, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0484604835510254, "global_step": 578907, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9083887338638306, "global_step": 578908, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.064551591873169, "global_step": 578909, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.994425654411316, "global_step": 578910, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9722728729248047, "global_step": 578911, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0195326805114746, "global_step": 578912, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.08785343170166, "global_step": 578913, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0045437812805176, "global_step": 578914, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0021941661834717, "global_step": 578915, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.947557806968689, "global_step": 578916, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9600121974945068, "global_step": 578917, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.07869553565979, "global_step": 578918, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.968565821647644, "global_step": 578919, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9677867889404297, "global_step": 578920, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9079877138137817, "global_step": 578921, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0375137329101562, "global_step": 578922, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9907255172729492, "global_step": 578923, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0463180541992188, "global_step": 578924, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.009363889694214, "global_step": 578925, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0701777935028076, "global_step": 578926, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9160566329956055, "global_step": 578927, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.043621063232422, "global_step": 578928, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9739540815353394, "global_step": 578929, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.040149450302124, "global_step": 578930, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1225364208221436, "global_step": 578931, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1448280811309814, "global_step": 578932, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0035743713378906, "global_step": 578933, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9458143711090088, "global_step": 578934, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.022467851638794, "global_step": 578935, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9829351902008057, "global_step": 578936, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.00938081741333, "global_step": 578937, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9714114665985107, "global_step": 578938, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0746994018554688, "global_step": 578939, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9072755575180054, "global_step": 578940, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.058257579803467, "global_step": 578941, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.920567274093628, "global_step": 578942, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.02213716506958, "global_step": 578943, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0869946479797363, "global_step": 578944, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1059720516204834, "global_step": 578945, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0119385719299316, "global_step": 578946, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.927477240562439, "global_step": 578947, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.006135940551758, "global_step": 578948, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0196218490600586, "global_step": 578949, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0380544662475586, "global_step": 578950, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0173232555389404, "global_step": 578951, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9524556398391724, "global_step": 578952, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.062551498413086, "global_step": 578953, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.025477886199951, "global_step": 578954, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9150768518447876, "global_step": 578955, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9496058225631714, "global_step": 578956, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9608919620513916, "global_step": 578957, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9974279403686523, "global_step": 578958, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9588005542755127, "global_step": 578959, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9375642538070679, "global_step": 578960, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0833888053894043, "global_step": 578961, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.07717227935791, "global_step": 578962, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.051758289337158, "global_step": 578963, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0130019187927246, "global_step": 578964, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9553886651992798, "global_step": 578965, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0135929584503174, "global_step": 578966, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1128902435302734, "global_step": 578967, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9459447860717773, "global_step": 578968, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9624320268630981, "global_step": 578969, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9778021574020386, "global_step": 578970, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9939347505569458, "global_step": 578971, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0279600620269775, "global_step": 578972, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0705058574676514, "global_step": 578973, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.043959379196167, "global_step": 578974, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.036115884780884, "global_step": 578975, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0075058937072754, "global_step": 578976, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0475099086761475, "global_step": 578977, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.108753204345703, "global_step": 578978, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0093729496002197, "global_step": 578979, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.075183391571045, "global_step": 578980, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.049480676651001, "global_step": 578981, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.044663429260254, "global_step": 578982, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0610578060150146, "global_step": 578983, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0882174968719482, "global_step": 578984, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.089843273162842, "global_step": 578985, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9803239107131958, "global_step": 578986, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9808969497680664, "global_step": 578987, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0369300842285156, "global_step": 578988, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9870717525482178, "global_step": 578989, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.966748833656311, "global_step": 578990, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9525306224822998, "global_step": 578991, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.990813136100769, "global_step": 578992, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0085606575012207, "global_step": 578993, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0335609912872314, "global_step": 578994, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0291748046875, "global_step": 578995, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0262932777404785, "global_step": 578996, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0800156593322754, "global_step": 578997, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0321388244628906, "global_step": 578998, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0256404876708984, "global_step": 578999, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.016470432281494, "global_step": 579000, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0261409282684326, "global_step": 579001, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0429751873016357, "global_step": 579002, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.017594814300537, "global_step": 579003, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9542945623397827, "global_step": 579004, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9850400686264038, "global_step": 579005, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.030927896499634, "global_step": 579006, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.075355052947998, "global_step": 579007, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9276306629180908, "global_step": 579008, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9294512271881104, "global_step": 579009, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0040788650512695, "global_step": 579010, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.064856767654419, "global_step": 579011, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0608716011047363, "global_step": 579012, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.999350905418396, "global_step": 579013, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9986552000045776, "global_step": 579014, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0350778102874756, "global_step": 579015, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.010207176208496, "global_step": 579016, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.989518165588379, "global_step": 579017, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0446090698242188, "global_step": 579018, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9997907876968384, "global_step": 579019, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0327839851379395, "global_step": 579020, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.096311569213867, "global_step": 579021, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9913917779922485, "global_step": 579022, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1107587814331055, "global_step": 579023, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0114309787750244, "global_step": 579024, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9920357465744019, "global_step": 579025, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0418121814727783, "global_step": 579026, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0365874767303467, "global_step": 579027, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0048329830169678, "global_step": 579028, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0104219913482666, "global_step": 579029, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.981397271156311, "global_step": 579030, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.090911626815796, "global_step": 579031, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0041515827178955, "global_step": 579032, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.961243987083435, "global_step": 579033, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0802760124206543, "global_step": 579034, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.007087469100952, "global_step": 579035, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0317258834838867, "global_step": 579036, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0414652824401855, "global_step": 579037, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.973404884338379, "global_step": 579038, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0424418449401855, "global_step": 579039, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0093817710876465, "global_step": 579040, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0118491649627686, "global_step": 579041, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.102381467819214, "global_step": 579042, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0145108699798584, "global_step": 579043, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.079677104949951, "global_step": 579044, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9390504360198975, "global_step": 579045, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9701570272445679, "global_step": 579046, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.046342134475708, "global_step": 579047, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0254995822906494, "global_step": 579048, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.078291416168213, "global_step": 579049, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9716589450836182, "global_step": 579050, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.017160415649414, "global_step": 579051, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0184264183044434, "global_step": 579052, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9430596828460693, "global_step": 579053, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0262885093688965, "global_step": 579054, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9573384523391724, "global_step": 579055, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.006483554840088, "global_step": 579056, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.023127317428589, "global_step": 579057, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.940091609954834, "global_step": 579058, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.081002950668335, "global_step": 579059, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0616960525512695, "global_step": 579060, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9805784225463867, "global_step": 579061, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9617811441421509, "global_step": 579062, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1294822692871094, "global_step": 579063, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.051527261734009, "global_step": 579064, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9866997003555298, "global_step": 579065, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0098540782928467, "global_step": 579066, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.019441843032837, "global_step": 579067, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9586446285247803, "global_step": 579068, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.013939142227173, "global_step": 579069, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9725455045700073, "global_step": 579070, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0700981616973877, "global_step": 579071, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.007591485977173, "global_step": 579072, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9392536878585815, "global_step": 579073, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0179896354675293, "global_step": 579074, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0292556285858154, "global_step": 579075, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1231231689453125, "global_step": 579076, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.108175277709961, "global_step": 579077, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1004273891448975, "global_step": 579078, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9879461526870728, "global_step": 579079, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.975742220878601, "global_step": 579080, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.954228162765503, "global_step": 579081, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9621638059616089, "global_step": 579082, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0940256118774414, "global_step": 579083, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0464446544647217, "global_step": 579084, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0115833282470703, "global_step": 579085, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0835773944854736, "global_step": 579086, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.065577983856201, "global_step": 579087, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0435428619384766, "global_step": 579088, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0564627647399902, "global_step": 579089, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9866355657577515, "global_step": 579090, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.050138473510742, "global_step": 579091, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.937851071357727, "global_step": 579092, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0152034759521484, "global_step": 579093, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.085207223892212, "global_step": 579094, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.00504732131958, "global_step": 579095, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.006873607635498, "global_step": 579096, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0779998302459717, "global_step": 579097, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0211362838745117, "global_step": 579098, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1096372604370117, "global_step": 579099, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0081920623779297, "global_step": 579100, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.008657217025757, "global_step": 579101, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0442252159118652, "global_step": 579102, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.939818024635315, "global_step": 579103, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0240206718444824, "global_step": 579104, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9666897058486938, "global_step": 579105, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9865102767944336, "global_step": 579106, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.962135672569275, "global_step": 579107, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0159335136413574, "global_step": 579108, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0252106189727783, "global_step": 579109, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0219178199768066, "global_step": 579110, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0121519565582275, "global_step": 579111, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.015779972076416, "global_step": 579112, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.019369125366211, "global_step": 579113, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9791080951690674, "global_step": 579114, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9992175102233887, "global_step": 579115, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0516223907470703, "global_step": 579116, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0169007778167725, "global_step": 579117, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9768847227096558, "global_step": 579118, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.060739755630493, "global_step": 579119, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.960505723953247, "global_step": 579120, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9998010396957397, "global_step": 579121, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0568621158599854, "global_step": 579122, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9722622632980347, "global_step": 579123, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9939385652542114, "global_step": 579124, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0002894401550293, "global_step": 579125, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1037209033966064, "global_step": 579126, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0386619567871094, "global_step": 579127, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9526937007904053, "global_step": 579128, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.980014681816101, "global_step": 579129, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.069608688354492, "global_step": 579130, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.01289701461792, "global_step": 579131, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.039659023284912, "global_step": 579132, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1136014461517334, "global_step": 579133, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.064087152481079, "global_step": 579134, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9456877708435059, "global_step": 579135, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.082105875015259, "global_step": 579136, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0333588123321533, "global_step": 579137, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9899513721466064, "global_step": 579138, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.001887083053589, "global_step": 579139, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.083861827850342, "global_step": 579140, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.074023723602295, "global_step": 579141, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.107682704925537, "global_step": 579142, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.030388832092285, "global_step": 579143, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0987775325775146, "global_step": 579144, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0685763359069824, "global_step": 579145, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0406363010406494, "global_step": 579146, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.028367519378662, "global_step": 579147, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9407668113708496, "global_step": 579148, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.91815984249115, "global_step": 579149, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9831839799880981, "global_step": 579150, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.055115222930908, "global_step": 579151, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9356435537338257, "global_step": 579152, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0468688011169434, "global_step": 579153, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.007028102874756, "global_step": 579154, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1166207790374756, "global_step": 579155, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9587888717651367, "global_step": 579156, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9757568836212158, "global_step": 579157, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.971212387084961, "global_step": 579158, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1405084133148193, "global_step": 579159, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9742732048034668, "global_step": 579160, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.024989366531372, "global_step": 579161, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0356643199920654, "global_step": 579162, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9992841482162476, "global_step": 579163, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0665299892425537, "global_step": 579164, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.026423692703247, "global_step": 579165, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.055424928665161, "global_step": 579166, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.074512243270874, "global_step": 579167, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.065147638320923, "global_step": 579168, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1013684272766113, "global_step": 579169, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9357937574386597, "global_step": 579170, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9723186492919922, "global_step": 579171, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9954911470413208, "global_step": 579172, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0100977420806885, "global_step": 579173, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0328469276428223, "global_step": 579174, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.038332939147949, "global_step": 579175, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0331692695617676, "global_step": 579176, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0524911880493164, "global_step": 579177, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9915708303451538, "global_step": 579178, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.169198989868164, "global_step": 579179, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0588719844818115, "global_step": 579180, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.895127534866333, "global_step": 579181, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.044818878173828, "global_step": 579182, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1972451210021973, "global_step": 579183, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.144538402557373, "global_step": 579184, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0525593757629395, "global_step": 579185, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.070298910140991, "global_step": 579186, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0397465229034424, "global_step": 579187, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0282018184661865, "global_step": 579188, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.070399522781372, "global_step": 579189, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.073371171951294, "global_step": 579190, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9746298789978027, "global_step": 579191, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1443910598754883, "global_step": 579192, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9848655462265015, "global_step": 579193, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9727084636688232, "global_step": 579194, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.943095326423645, "global_step": 579195, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9756360054016113, "global_step": 579196, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0549230575561523, "global_step": 579197, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.062107801437378, "global_step": 579198, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9745607376098633, "global_step": 579199, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.019517660140991, "global_step": 579200, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0888607501983643, "global_step": 579201, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9326303005218506, "global_step": 579202, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.051642417907715, "global_step": 579203, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.075084686279297, "global_step": 579204, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9879966974258423, "global_step": 579205, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0366837978363037, "global_step": 579206, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0469746589660645, "global_step": 579207, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1421539783477783, "global_step": 579208, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0259201526641846, "global_step": 579209, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0804927349090576, "global_step": 579210, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.031803607940674, "global_step": 579211, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9945398569107056, "global_step": 579212, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0355405807495117, "global_step": 579213, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.991870403289795, "global_step": 579214, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0607988834381104, "global_step": 579215, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.03741192817688, "global_step": 579216, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0570430755615234, "global_step": 579217, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0589520931243896, "global_step": 579218, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0363378524780273, "global_step": 579219, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.013348340988159, "global_step": 579220, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0357913970947266, "global_step": 579221, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0896570682525635, "global_step": 579222, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1071038246154785, "global_step": 579223, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9212104082107544, "global_step": 579224, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9141467809677124, "global_step": 579225, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9249136447906494, "global_step": 579226, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0856730937957764, "global_step": 579227, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.032806396484375, "global_step": 579228, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.998494267463684, "global_step": 579229, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0104830265045166, "global_step": 579230, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.044013023376465, "global_step": 579231, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.108163595199585, "global_step": 579232, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.065617084503174, "global_step": 579233, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0763278007507324, "global_step": 579234, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0504777431488037, "global_step": 579235, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.006049156188965, "global_step": 579236, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0240862369537354, "global_step": 579237, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.013490915298462, "global_step": 579238, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9915279150009155, "global_step": 579239, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9992493391036987, "global_step": 579240, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0391652584075928, "global_step": 579241, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9576905965805054, "global_step": 579242, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.056830644607544, "global_step": 579243, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.071737051010132, "global_step": 579244, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9974497556686401, "global_step": 579245, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.087489128112793, "global_step": 579246, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.10273814201355, "global_step": 579247, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9559048414230347, "global_step": 579248, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.987095594406128, "global_step": 579249, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.027653455734253, "global_step": 579250, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9819213151931763, "global_step": 579251, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9713281393051147, "global_step": 579252, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1164045333862305, "global_step": 579253, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.067234516143799, "global_step": 579254, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.974945068359375, "global_step": 579255, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.020594358444214, "global_step": 579256, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0641794204711914, "global_step": 579257, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0588645935058594, "global_step": 579258, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.056795835494995, "global_step": 579259, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0539169311523438, "global_step": 579260, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.069600820541382, "global_step": 579261, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.039552688598633, "global_step": 579262, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0032589435577393, "global_step": 579263, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0249640941619873, "global_step": 579264, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.060046434402466, "global_step": 579265, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.909003734588623, "global_step": 579266, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9398168325424194, "global_step": 579267, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9689949750900269, "global_step": 579268, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.016918182373047, "global_step": 579269, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0248148441314697, "global_step": 579270, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0452396869659424, "global_step": 579271, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0352354049682617, "global_step": 579272, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.005354404449463, "global_step": 579273, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.003471851348877, "global_step": 579274, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.122023105621338, "global_step": 579275, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1151134967803955, "global_step": 579276, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9824318885803223, "global_step": 579277, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9584293365478516, "global_step": 579278, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9586145877838135, "global_step": 579279, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9438680410385132, "global_step": 579280, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0690739154815674, "global_step": 579281, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.076873540878296, "global_step": 579282, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0565755367279053, "global_step": 579283, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0382676124572754, "global_step": 579284, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.990112066268921, "global_step": 579285, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0423424243927, "global_step": 579286, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.034202814102173, "global_step": 579287, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0168745517730713, "global_step": 579288, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0526483058929443, "global_step": 579289, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.018329620361328, "global_step": 579290, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.952831506729126, "global_step": 579291, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.028862953186035, "global_step": 579292, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0968356132507324, "global_step": 579293, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0089328289031982, "global_step": 579294, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.012709617614746, "global_step": 579295, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1699464321136475, "global_step": 579296, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.07187557220459, "global_step": 579297, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9665106534957886, "global_step": 579298, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0477263927459717, "global_step": 579299, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0641820430755615, "global_step": 579300, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9761203527450562, "global_step": 579301, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.059539318084717, "global_step": 579302, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9941128492355347, "global_step": 579303, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.030405044555664, "global_step": 579304, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0807595252990723, "global_step": 579305, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1083264350891113, "global_step": 579306, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.942838430404663, "global_step": 579307, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.041330099105835, "global_step": 579308, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0314979553222656, "global_step": 579309, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0247015953063965, "global_step": 579310, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0005335807800293, "global_step": 579311, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9230749607086182, "global_step": 579312, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.035433053970337, "global_step": 579313, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9417507648468018, "global_step": 579314, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9869298934936523, "global_step": 579315, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0188097953796387, "global_step": 579316, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.047051191329956, "global_step": 579317, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.028223752975464, "global_step": 579318, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0319509506225586, "global_step": 579319, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.043055534362793, "global_step": 579320, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.011577844619751, "global_step": 579321, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9963109493255615, "global_step": 579322, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0064101219177246, "global_step": 579323, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.994889259338379, "global_step": 579324, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.064086437225342, "global_step": 579325, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0746490955352783, "global_step": 579326, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.030625343322754, "global_step": 579327, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.032353401184082, "global_step": 579328, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1060750484466553, "global_step": 579329, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.979610562324524, "global_step": 579330, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9863917827606201, "global_step": 579331, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0476486682891846, "global_step": 579332, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9177038669586182, "global_step": 579333, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.998947024345398, "global_step": 579334, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.01041841506958, "global_step": 579335, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.058764696121216, "global_step": 579336, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0331764221191406, "global_step": 579337, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9943227767944336, "global_step": 579338, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9707075357437134, "global_step": 579339, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.084164619445801, "global_step": 579340, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9892051219940186, "global_step": 579341, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0647430419921875, "global_step": 579342, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0523202419281006, "global_step": 579343, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.976222038269043, "global_step": 579344, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0727171897888184, "global_step": 579345, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.080186605453491, "global_step": 579346, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.111804723739624, "global_step": 579347, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0266776084899902, "global_step": 579348, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.021115303039551, "global_step": 579349, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0741944313049316, "global_step": 579350, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9376823902130127, "global_step": 579351, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0251736640930176, "global_step": 579352, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.040614366531372, "global_step": 579353, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0809926986694336, "global_step": 579354, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.986185908317566, "global_step": 579355, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.086764335632324, "global_step": 579356, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.075098991394043, "global_step": 579357, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9791489839553833, "global_step": 579358, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1016745567321777, "global_step": 579359, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9607032537460327, "global_step": 579360, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.033541440963745, "global_step": 579361, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0362205505371094, "global_step": 579362, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0583741664886475, "global_step": 579363, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0214829444885254, "global_step": 579364, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.057443141937256, "global_step": 579365, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.922316074371338, "global_step": 579366, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.087236166000366, "global_step": 579367, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0388612747192383, "global_step": 579368, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.987778663635254, "global_step": 579369, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.059901475906372, "global_step": 579370, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.037260055541992, "global_step": 579371, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9955077171325684, "global_step": 579372, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9789286851882935, "global_step": 579373, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0669779777526855, "global_step": 579374, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0345025062561035, "global_step": 579375, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0089054107666016, "global_step": 579376, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0939126014709473, "global_step": 579377, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.001537799835205, "global_step": 579378, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0208346843719482, "global_step": 579379, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.056379795074463, "global_step": 579380, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.936128854751587, "global_step": 579381, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0838918685913086, "global_step": 579382, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0362799167633057, "global_step": 579383, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0855817794799805, "global_step": 579384, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9766671657562256, "global_step": 579385, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.100264549255371, "global_step": 579386, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.018671989440918, "global_step": 579387, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0433006286621094, "global_step": 579388, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0861754417419434, "global_step": 579389, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9911131858825684, "global_step": 579390, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.961810827255249, "global_step": 579391, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.045469284057617, "global_step": 579392, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0824880599975586, "global_step": 579393, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9627304077148438, "global_step": 579394, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9382673501968384, "global_step": 579395, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9989415407180786, "global_step": 579396, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0000548362731934, "global_step": 579397, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.072995662689209, "global_step": 579398, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.070396900177002, "global_step": 579399, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0197527408599854, "global_step": 579400, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0152323246002197, "global_step": 579401, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0952377319335938, "global_step": 579402, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9835225343704224, "global_step": 579403, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9911410808563232, "global_step": 579404, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0494885444641113, "global_step": 579405, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1601667404174805, "global_step": 579406, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0288193225860596, "global_step": 579407, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.976078748703003, "global_step": 579408, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.040132761001587, "global_step": 579409, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.027329444885254, "global_step": 579410, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.965781807899475, "global_step": 579411, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0346710681915283, "global_step": 579412, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.021839141845703, "global_step": 579413, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.085034132003784, "global_step": 579414, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9889466762542725, "global_step": 579415, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9926047325134277, "global_step": 579416, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.029433488845825, "global_step": 579417, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0694057941436768, "global_step": 579418, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0540125370025635, "global_step": 579419, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.006322145462036, "global_step": 579420, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.079002857208252, "global_step": 579421, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.025129556655884, "global_step": 579422, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9897924661636353, "global_step": 579423, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9421199560165405, "global_step": 579424, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0494003295898438, "global_step": 579425, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.97383451461792, "global_step": 579426, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0843284130096436, "global_step": 579427, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9856725931167603, "global_step": 579428, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1134655475616455, "global_step": 579429, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9899399280548096, "global_step": 579430, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.944956660270691, "global_step": 579431, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9472992420196533, "global_step": 579432, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.062061309814453, "global_step": 579433, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.047208309173584, "global_step": 579434, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.099902629852295, "global_step": 579435, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.999651312828064, "global_step": 579436, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9886025190353394, "global_step": 579437, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.029510736465454, "global_step": 579438, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9632229804992676, "global_step": 579439, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0958802700042725, "global_step": 579440, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0018372535705566, "global_step": 579441, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0553627014160156, "global_step": 579442, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0738890171051025, "global_step": 579443, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.121844530105591, "global_step": 579444, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9944401979446411, "global_step": 579445, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0274829864501953, "global_step": 579446, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.06428861618042, "global_step": 579447, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.998172640800476, "global_step": 579448, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0338244438171387, "global_step": 579449, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.160149574279785, "global_step": 579450, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.029981851577759, "global_step": 579451, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.985140085220337, "global_step": 579452, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.017709255218506, "global_step": 579453, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0072224140167236, "global_step": 579454, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9768065214157104, "global_step": 579455, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.984816074371338, "global_step": 579456, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.02630877494812, "global_step": 579457, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.919847846031189, "global_step": 579458, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.065107583999634, "global_step": 579459, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.034902811050415, "global_step": 579460, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0062975883483887, "global_step": 579461, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.102851390838623, "global_step": 579462, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9616714715957642, "global_step": 579463, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.088402509689331, "global_step": 579464, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9522953033447266, "global_step": 579465, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.081923007965088, "global_step": 579466, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.115959882736206, "global_step": 579467, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.001262903213501, "global_step": 579468, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0043089389801025, "global_step": 579469, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.013016939163208, "global_step": 579470, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0121207237243652, "global_step": 579471, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.979844331741333, "global_step": 579472, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0477118492126465, "global_step": 579473, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9629663228988647, "global_step": 579474, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0562286376953125, "global_step": 579475, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.089726448059082, "global_step": 579476, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0491461753845215, "global_step": 579477, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0130503177642822, "global_step": 579478, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9503512382507324, "global_step": 579479, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0271735191345215, "global_step": 579480, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9976189136505127, "global_step": 579481, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0258235931396484, "global_step": 579482, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9854060411453247, "global_step": 579483, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1070735454559326, "global_step": 579484, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0393176078796387, "global_step": 579485, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0269601345062256, "global_step": 579486, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.014019727706909, "global_step": 579487, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9646434783935547, "global_step": 579488, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0700697898864746, "global_step": 579489, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0403079986572266, "global_step": 579490, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0231194496154785, "global_step": 579491, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.043135404586792, "global_step": 579492, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0073719024658203, "global_step": 579493, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.028519868850708, "global_step": 579494, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0012385845184326, "global_step": 579495, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0464181900024414, "global_step": 579496, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9683171510696411, "global_step": 579497, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9875789880752563, "global_step": 579498, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.071141242980957, "global_step": 579499, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9818538427352905, "global_step": 579500, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9686262607574463, "global_step": 579501, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9640520811080933, "global_step": 579502, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.129422187805176, "global_step": 579503, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.064077854156494, "global_step": 579504, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0084574222564697, "global_step": 579505, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0834128856658936, "global_step": 579506, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.954913854598999, "global_step": 579507, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.127155065536499, "global_step": 579508, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.160080671310425, "global_step": 579509, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0371761322021484, "global_step": 579510, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.043870687484741, "global_step": 579511, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.922340750694275, "global_step": 579512, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9858548641204834, "global_step": 579513, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.05495285987854, "global_step": 579514, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9737502336502075, "global_step": 579515, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0366196632385254, "global_step": 579516, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.109445810317993, "global_step": 579517, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.084263801574707, "global_step": 579518, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0244979858398438, "global_step": 579519, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.01041841506958, "global_step": 579520, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0229625701904297, "global_step": 579521, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.053692579269409, "global_step": 579522, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.054631471633911, "global_step": 579523, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0289647579193115, "global_step": 579524, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0726091861724854, "global_step": 579525, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9972621202468872, "global_step": 579526, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0207245349884033, "global_step": 579527, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.970175862312317, "global_step": 579528, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.106668472290039, "global_step": 579529, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.088386297225952, "global_step": 579530, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9713813066482544, "global_step": 579531, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0580601692199707, "global_step": 579532, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9711639881134033, "global_step": 579533, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.024733543395996, "global_step": 579534, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0871264934539795, "global_step": 579535, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1293625831604004, "global_step": 579536, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.06817889213562, "global_step": 579537, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9371497631072998, "global_step": 579538, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.031466484069824, "global_step": 579539, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.046133279800415, "global_step": 579540, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0474276542663574, "global_step": 579541, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9763612747192383, "global_step": 579542, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0215706825256348, "global_step": 579543, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0637688636779785, "global_step": 579544, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0351784229278564, "global_step": 579545, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0332937240600586, "global_step": 579546, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0131900310516357, "global_step": 579547, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.076267957687378, "global_step": 579548, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0914878845214844, "global_step": 579549, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.99708092212677, "global_step": 579550, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9615187644958496, "global_step": 579551, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0781383514404297, "global_step": 579552, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0070533752441406, "global_step": 579553, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.005490303039551, "global_step": 579554, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0075931549072266, "global_step": 579555, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9901707172393799, "global_step": 579556, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1231393814086914, "global_step": 579557, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.123642921447754, "global_step": 579558, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.058027982711792, "global_step": 579559, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9849753379821777, "global_step": 579560, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9997069835662842, "global_step": 579561, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.940753698348999, "global_step": 579562, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9467109441757202, "global_step": 579563, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.990059733390808, "global_step": 579564, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.925187349319458, "global_step": 579565, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0715136528015137, "global_step": 579566, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.956956148147583, "global_step": 579567, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.00077486038208, "global_step": 579568, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9412180185317993, "global_step": 579569, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9465901851654053, "global_step": 579570, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9748899936676025, "global_step": 579571, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.922900915145874, "global_step": 579572, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0080740451812744, "global_step": 579573, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.081665515899658, "global_step": 579574, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.984525203704834, "global_step": 579575, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.14442777633667, "global_step": 579576, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.043363332748413, "global_step": 579577, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0440456867218018, "global_step": 579578, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9650466442108154, "global_step": 579579, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9781278371810913, "global_step": 579580, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.094787836074829, "global_step": 579581, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0322277545928955, "global_step": 579582, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.037419557571411, "global_step": 579583, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.09928560256958, "global_step": 579584, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0481817722320557, "global_step": 579585, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.1216378211975098, "global_step": 579586, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0755455493927, "global_step": 579587, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.006314992904663, "global_step": 579588, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.022608995437622, "global_step": 579589, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0378823280334473, "global_step": 579590, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0895626544952393, "global_step": 579591, "epoch": 947, "lr": 5e-05}
{"train_loss": 1.9938114881515503, "global_step": 579592, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0919559001922607, "global_step": 579593, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.0204110145568848, "global_step": 579594, "epoch": 947, "lr": 5e-05}
{"train_loss": 2.019282102584839, "global_step": 579595, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.043267011642456, "global_step": 579596, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0708165168762207, "global_step": 579597, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.001540422439575, "global_step": 579598, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.924311876296997, "global_step": 579599, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.078247308731079, "global_step": 579600, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0017249584198, "global_step": 579601, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9747320413589478, "global_step": 579602, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0980594158172607, "global_step": 579603, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.022376298904419, "global_step": 579604, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9341373443603516, "global_step": 579605, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.01969051361084, "global_step": 579606, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0173585414886475, "global_step": 579607, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9714652299880981, "global_step": 579608, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9893343448638916, "global_step": 579609, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9696154594421387, "global_step": 579610, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.04278564453125, "global_step": 579611, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.042489767074585, "global_step": 579612, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.011068344116211, "global_step": 579613, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0124833583831787, "global_step": 579614, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.977548360824585, "global_step": 579615, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.08610463142395, "global_step": 579616, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9643354415893555, "global_step": 579617, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9609767198562622, "global_step": 579618, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9838855266571045, "global_step": 579619, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.985775351524353, "global_step": 579620, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0857739448547363, "global_step": 579621, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.8952914476394653, "global_step": 579622, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.925139307975769, "global_step": 579623, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1064810752868652, "global_step": 579624, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.023336172103882, "global_step": 579625, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0262181758880615, "global_step": 579626, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9000351428985596, "global_step": 579627, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0633578300476074, "global_step": 579628, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9670792818069458, "global_step": 579629, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.999781847000122, "global_step": 579630, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0057876110076904, "global_step": 579631, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.044095516204834, "global_step": 579632, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.016536235809326, "global_step": 579633, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.970941424369812, "global_step": 579634, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.042818784713745, "global_step": 579635, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0961341857910156, "global_step": 579636, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0049643516540527, "global_step": 579637, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.000138998031616, "global_step": 579638, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9773167371749878, "global_step": 579639, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.939534306526184, "global_step": 579640, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9574137926101685, "global_step": 579641, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.044390916824341, "global_step": 579642, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.071436882019043, "global_step": 579643, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0315372943878174, "global_step": 579644, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0214972496032715, "global_step": 579645, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.001286745071411, "global_step": 579646, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9666571617126465, "global_step": 579647, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9611899852752686, "global_step": 579648, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9557056427001953, "global_step": 579649, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9931795597076416, "global_step": 579650, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.057204484939575, "global_step": 579651, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9665234088897705, "global_step": 579652, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0565011501312256, "global_step": 579653, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1106903553009033, "global_step": 579654, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0833394527435303, "global_step": 579655, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1143012046813965, "global_step": 579656, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0692484378814697, "global_step": 579657, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.068396806716919, "global_step": 579658, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0356953144073486, "global_step": 579659, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0641331672668457, "global_step": 579660, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0505568981170654, "global_step": 579661, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.020909070968628, "global_step": 579662, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0550315380096436, "global_step": 579663, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9694032669067383, "global_step": 579664, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.03373384475708, "global_step": 579665, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9966230392456055, "global_step": 579666, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0346758365631104, "global_step": 579667, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9922593832015991, "global_step": 579668, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.042188882827759, "global_step": 579669, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9457303285598755, "global_step": 579670, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9769452810287476, "global_step": 579671, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.07947039604187, "global_step": 579672, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.068916082382202, "global_step": 579673, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.97249436378479, "global_step": 579674, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0699150562286377, "global_step": 579675, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9858859777450562, "global_step": 579676, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.048125982284546, "global_step": 579677, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9730441570281982, "global_step": 579678, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0143299102783203, "global_step": 579679, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0448994636535645, "global_step": 579680, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9787077903747559, "global_step": 579681, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.992893099784851, "global_step": 579682, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0441296100616455, "global_step": 579683, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0512797832489014, "global_step": 579684, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0678305625915527, "global_step": 579685, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0042548179626465, "global_step": 579686, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9736862182617188, "global_step": 579687, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0471906661987305, "global_step": 579688, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9986289739608765, "global_step": 579689, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9863961935043335, "global_step": 579690, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.033018112182617, "global_step": 579691, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.094348907470703, "global_step": 579692, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.086789846420288, "global_step": 579693, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9403327703475952, "global_step": 579694, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9800913333892822, "global_step": 579695, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9977952241897583, "global_step": 579696, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9593473672866821, "global_step": 579697, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0417890548706055, "global_step": 579698, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0016815662384033, "global_step": 579699, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.953198790550232, "global_step": 579700, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.000187635421753, "global_step": 579701, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0008583068847656, "global_step": 579702, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0071663856506348, "global_step": 579703, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9429675340652466, "global_step": 579704, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9992507696151733, "global_step": 579705, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0157289505004883, "global_step": 579706, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0423686504364014, "global_step": 579707, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0034122467041016, "global_step": 579708, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.020073413848877, "global_step": 579709, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.018986940383911, "global_step": 579710, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.994246482849121, "global_step": 579711, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.030369281768799, "global_step": 579712, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1037144660949707, "global_step": 579713, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0146310329437256, "global_step": 579714, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.007225513458252, "global_step": 579715, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0105013847351074, "global_step": 579716, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.070126533508301, "global_step": 579717, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9736008644104004, "global_step": 579718, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.023230791091919, "global_step": 579719, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0464465618133545, "global_step": 579720, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0234971046447754, "global_step": 579721, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9975626468658447, "global_step": 579722, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0105576515197754, "global_step": 579723, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9815784692764282, "global_step": 579724, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.004971981048584, "global_step": 579725, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9495502710342407, "global_step": 579726, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0485684871673584, "global_step": 579727, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0043580532073975, "global_step": 579728, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9775657653808594, "global_step": 579729, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.959970235824585, "global_step": 579730, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.066206455230713, "global_step": 579731, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9648772478103638, "global_step": 579732, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.054828643798828, "global_step": 579733, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.051478385925293, "global_step": 579734, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0172038078308105, "global_step": 579735, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1179187297821045, "global_step": 579736, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.058332920074463, "global_step": 579737, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0185046195983887, "global_step": 579738, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9890955686569214, "global_step": 579739, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0488808155059814, "global_step": 579740, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.021740674972534, "global_step": 579741, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1149330139160156, "global_step": 579742, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.07783842086792, "global_step": 579743, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0238962173461914, "global_step": 579744, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9613817930221558, "global_step": 579745, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9679558277130127, "global_step": 579746, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.031512975692749, "global_step": 579747, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.03262996673584, "global_step": 579748, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9608898162841797, "global_step": 579749, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.995837926864624, "global_step": 579750, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9561386108398438, "global_step": 579751, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0176260471343994, "global_step": 579752, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.051795721054077, "global_step": 579753, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9293112754821777, "global_step": 579754, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0249884128570557, "global_step": 579755, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0813987255096436, "global_step": 579756, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9730641841888428, "global_step": 579757, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0582613945007324, "global_step": 579758, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0353193283081055, "global_step": 579759, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0408613681793213, "global_step": 579760, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0324647426605225, "global_step": 579761, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.057788372039795, "global_step": 579762, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.049315929412842, "global_step": 579763, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0174262523651123, "global_step": 579764, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9226878881454468, "global_step": 579765, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.001631021499634, "global_step": 579766, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9728946685791016, "global_step": 579767, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9443057775497437, "global_step": 579768, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9997193813323975, "global_step": 579769, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.971625566482544, "global_step": 579770, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.132736921310425, "global_step": 579771, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0071558952331543, "global_step": 579772, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0092289447784424, "global_step": 579773, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.011361598968506, "global_step": 579774, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0724072456359863, "global_step": 579775, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0353288650512695, "global_step": 579776, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.932897686958313, "global_step": 579777, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.03725528717041, "global_step": 579778, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0769128799438477, "global_step": 579779, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9741344451904297, "global_step": 579780, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0188112258911133, "global_step": 579781, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0146539211273193, "global_step": 579782, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1163313388824463, "global_step": 579783, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0168278217315674, "global_step": 579784, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9950790405273438, "global_step": 579785, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1032168865203857, "global_step": 579786, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0142974853515625, "global_step": 579787, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0153446197509766, "global_step": 579788, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.021409511566162, "global_step": 579789, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.000883102416992, "global_step": 579790, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9893287420272827, "global_step": 579791, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9450119733810425, "global_step": 579792, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1183478832244873, "global_step": 579793, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.07106614112854, "global_step": 579794, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9796037673950195, "global_step": 579795, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9940226078033447, "global_step": 579796, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0100433826446533, "global_step": 579797, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9999783039093018, "global_step": 579798, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0896551609039307, "global_step": 579799, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0106539726257324, "global_step": 579800, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.097877264022827, "global_step": 579801, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9519498348236084, "global_step": 579802, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9706106185913086, "global_step": 579803, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9691020250320435, "global_step": 579804, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9677698612213135, "global_step": 579805, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.015141248703003, "global_step": 579806, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.057065010070801, "global_step": 579807, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9757801294326782, "global_step": 579808, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0272634029388428, "global_step": 579809, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0669643878936768, "global_step": 579810, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0117626190185547, "global_step": 579811, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9126715660095215, "global_step": 579812, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.044434070587158, "global_step": 579813, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.978757381439209, "global_step": 579814, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0127406120300293, "global_step": 579815, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9507569074630737, "global_step": 579816, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.057039499282837, "global_step": 579817, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.02512526512146, "global_step": 579818, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0266833305358887, "global_step": 579819, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.042571783065796, "global_step": 579820, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.957761287689209, "global_step": 579821, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9912357330322266, "global_step": 579822, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0160679817199707, "global_step": 579823, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9952597618103027, "global_step": 579824, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.076195001602173, "global_step": 579825, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9883123636245728, "global_step": 579826, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0070321559906006, "global_step": 579827, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.016118049621582, "global_step": 579828, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0485947132110596, "global_step": 579829, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.090935230255127, "global_step": 579830, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.127434730529785, "global_step": 579831, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9681446552276611, "global_step": 579832, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0732781887054443, "global_step": 579833, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.8900421857833862, "global_step": 579834, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.083772659301758, "global_step": 579835, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.056184768676758, "global_step": 579836, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9970461130142212, "global_step": 579837, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.101478338241577, "global_step": 579838, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0646846294403076, "global_step": 579839, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.016860246658325, "global_step": 579840, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0818471908569336, "global_step": 579841, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.030428171157837, "global_step": 579842, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.911600947380066, "global_step": 579843, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9642812013626099, "global_step": 579844, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9434304237365723, "global_step": 579845, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0931179523468018, "global_step": 579846, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0533950328826904, "global_step": 579847, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0507662296295166, "global_step": 579848, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9794752597808838, "global_step": 579849, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.088266372680664, "global_step": 579850, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0307233333587646, "global_step": 579851, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9678385257720947, "global_step": 579852, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.960675835609436, "global_step": 579853, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0758960247039795, "global_step": 579854, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.070823907852173, "global_step": 579855, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.017181396484375, "global_step": 579856, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.091193914413452, "global_step": 579857, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0204017162323, "global_step": 579858, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.062620162963867, "global_step": 579859, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0250461101531982, "global_step": 579860, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9061533212661743, "global_step": 579861, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9343632459640503, "global_step": 579862, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9902087450027466, "global_step": 579863, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0228190422058105, "global_step": 579864, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.05570125579834, "global_step": 579865, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1173017024993896, "global_step": 579866, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0202395915985107, "global_step": 579867, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0299770832061768, "global_step": 579868, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1028685569763184, "global_step": 579869, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.031348705291748, "global_step": 579870, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0004336833953857, "global_step": 579871, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.089412212371826, "global_step": 579872, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0550484657287598, "global_step": 579873, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.000540018081665, "global_step": 579874, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9493145942687988, "global_step": 579875, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9427329301834106, "global_step": 579876, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.006355047225952, "global_step": 579877, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.025195598602295, "global_step": 579878, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0871729850769043, "global_step": 579879, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.100598096847534, "global_step": 579880, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9727368354797363, "global_step": 579881, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0030157566070557, "global_step": 579882, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0003585815429688, "global_step": 579883, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.002687692642212, "global_step": 579884, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.03800892829895, "global_step": 579885, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.041595220565796, "global_step": 579886, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0512282848358154, "global_step": 579887, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9965457916259766, "global_step": 579888, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1144347190856934, "global_step": 579889, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0736520290374756, "global_step": 579890, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0633294582366943, "global_step": 579891, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.988097071647644, "global_step": 579892, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9354547262191772, "global_step": 579893, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0551745891571045, "global_step": 579894, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9397590160369873, "global_step": 579895, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.007924795150757, "global_step": 579896, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9374028444290161, "global_step": 579897, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9879504442214966, "global_step": 579898, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0286152362823486, "global_step": 579899, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0546867847442627, "global_step": 579900, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9569664001464844, "global_step": 579901, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0247528553009033, "global_step": 579902, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9764944314956665, "global_step": 579903, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0630462169647217, "global_step": 579904, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0408384799957275, "global_step": 579905, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.100508689880371, "global_step": 579906, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0008509159088135, "global_step": 579907, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.001561164855957, "global_step": 579908, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0358574390411377, "global_step": 579909, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.069763422012329, "global_step": 579910, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0361127853393555, "global_step": 579911, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.016141414642334, "global_step": 579912, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.088101863861084, "global_step": 579913, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0393240451812744, "global_step": 579914, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0709662437438965, "global_step": 579915, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0550436973571777, "global_step": 579916, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9908660650253296, "global_step": 579917, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.083249807357788, "global_step": 579918, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0550220012664795, "global_step": 579919, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0295214653015137, "global_step": 579920, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.977126955986023, "global_step": 579921, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9606186151504517, "global_step": 579922, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.017083168029785, "global_step": 579923, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0033435821533203, "global_step": 579924, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0114552974700928, "global_step": 579925, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9930965900421143, "global_step": 579926, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.032270908355713, "global_step": 579927, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0011329650878906, "global_step": 579928, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9954909086227417, "global_step": 579929, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9374042749404907, "global_step": 579930, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0678646564483643, "global_step": 579931, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9508551359176636, "global_step": 579932, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0790982246398926, "global_step": 579933, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.095088481903076, "global_step": 579934, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.054532527923584, "global_step": 579935, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9587676525115967, "global_step": 579936, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9933831691741943, "global_step": 579937, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1038339138031006, "global_step": 579938, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9945281744003296, "global_step": 579939, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.00158429145813, "global_step": 579940, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0072999000549316, "global_step": 579941, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.040367841720581, "global_step": 579942, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9437975883483887, "global_step": 579943, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.019692897796631, "global_step": 579944, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9353846311569214, "global_step": 579945, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9228179454803467, "global_step": 579946, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9758169651031494, "global_step": 579947, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0172781944274902, "global_step": 579948, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0475707054138184, "global_step": 579949, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0793707370758057, "global_step": 579950, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.980647087097168, "global_step": 579951, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9878463745117188, "global_step": 579952, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0468060970306396, "global_step": 579953, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0267879962921143, "global_step": 579954, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9709193706512451, "global_step": 579955, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.03774356842041, "global_step": 579956, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0356199741363525, "global_step": 579957, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0339670181274414, "global_step": 579958, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9976232051849365, "global_step": 579959, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9721850156784058, "global_step": 579960, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.018235206604004, "global_step": 579961, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.039638042449951, "global_step": 579962, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.064185619354248, "global_step": 579963, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0269293785095215, "global_step": 579964, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1267616748809814, "global_step": 579965, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0007412433624268, "global_step": 579966, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9407585859298706, "global_step": 579967, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9452683925628662, "global_step": 579968, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0541224479675293, "global_step": 579969, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0661730766296387, "global_step": 579970, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9845901727676392, "global_step": 579971, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0388071537017822, "global_step": 579972, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0261378288269043, "global_step": 579973, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.022364616394043, "global_step": 579974, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.119380235671997, "global_step": 579975, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9238507747650146, "global_step": 579976, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9948935508728027, "global_step": 579977, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.074613571166992, "global_step": 579978, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0462701320648193, "global_step": 579979, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0639383792877197, "global_step": 579980, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9982035160064697, "global_step": 579981, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.077096939086914, "global_step": 579982, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.002058267593384, "global_step": 579983, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0372602939605713, "global_step": 579984, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0135960578918457, "global_step": 579985, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9483659267425537, "global_step": 579986, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0500245094299316, "global_step": 579987, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.046053647994995, "global_step": 579988, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9427813291549683, "global_step": 579989, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0530216693878174, "global_step": 579990, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0340499877929688, "global_step": 579991, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0391995906829834, "global_step": 579992, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.994401454925537, "global_step": 579993, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9911067485809326, "global_step": 579994, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9663400650024414, "global_step": 579995, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9760608673095703, "global_step": 579996, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0689563751220703, "global_step": 579997, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0612118244171143, "global_step": 579998, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9603344202041626, "global_step": 579999, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.993190884590149, "global_step": 580000, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0480575561523438, "global_step": 580001, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.984403371810913, "global_step": 580002, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9009995460510254, "global_step": 580003, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.994152545928955, "global_step": 580004, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0717670917510986, "global_step": 580005, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.026177406311035, "global_step": 580006, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0074431896209717, "global_step": 580007, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9803928136825562, "global_step": 580008, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0759189128875732, "global_step": 580009, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0350265502929688, "global_step": 580010, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.964381217956543, "global_step": 580011, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0243804454803467, "global_step": 580012, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.060464382171631, "global_step": 580013, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1194100379943848, "global_step": 580014, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9558544158935547, "global_step": 580015, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.10174298286438, "global_step": 580016, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.045334577560425, "global_step": 580017, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.040113925933838, "global_step": 580018, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.079660177230835, "global_step": 580019, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.99504554271698, "global_step": 580020, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9976426362991333, "global_step": 580021, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0660717487335205, "global_step": 580022, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.065903902053833, "global_step": 580023, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.039632797241211, "global_step": 580024, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0029714107513428, "global_step": 580025, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0694527626037598, "global_step": 580026, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9606345891952515, "global_step": 580027, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0527162551879883, "global_step": 580028, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9946808815002441, "global_step": 580029, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9851669073104858, "global_step": 580030, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0190629959106445, "global_step": 580031, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0617153644561768, "global_step": 580032, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.017998695373535, "global_step": 580033, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.110598564147949, "global_step": 580034, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9915937185287476, "global_step": 580035, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9713232517242432, "global_step": 580036, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0096583366394043, "global_step": 580037, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0883331298828125, "global_step": 580038, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.094862937927246, "global_step": 580039, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.032897472381592, "global_step": 580040, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.019137144088745, "global_step": 580041, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0499863624572754, "global_step": 580042, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9550830125808716, "global_step": 580043, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9704164266586304, "global_step": 580044, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9946264028549194, "global_step": 580045, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0784928798675537, "global_step": 580046, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9194891452789307, "global_step": 580047, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9462412595748901, "global_step": 580048, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9619287252426147, "global_step": 580049, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.025312900543213, "global_step": 580050, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9999374151229858, "global_step": 580051, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0037174224853516, "global_step": 580052, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.028165340423584, "global_step": 580053, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0296835899353027, "global_step": 580054, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0611987113952637, "global_step": 580055, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.013453960418701, "global_step": 580056, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.038699150085449, "global_step": 580057, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.056225061416626, "global_step": 580058, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9933160543441772, "global_step": 580059, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1182873249053955, "global_step": 580060, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9979642629623413, "global_step": 580061, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9606796503067017, "global_step": 580062, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9606620073318481, "global_step": 580063, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.97042715549469, "global_step": 580064, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.119598627090454, "global_step": 580065, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0290074348449707, "global_step": 580066, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0390095710754395, "global_step": 580067, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.029913902282715, "global_step": 580068, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9797425270080566, "global_step": 580069, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9468913078308105, "global_step": 580070, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0725109577178955, "global_step": 580071, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.996177315711975, "global_step": 580072, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9521464109420776, "global_step": 580073, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9879661798477173, "global_step": 580074, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.003047227859497, "global_step": 580075, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0679142475128174, "global_step": 580076, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9323099851608276, "global_step": 580077, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9484165906906128, "global_step": 580078, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0091404914855957, "global_step": 580079, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.003767251968384, "global_step": 580080, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9794286489486694, "global_step": 580081, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9790655374526978, "global_step": 580082, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.00311279296875, "global_step": 580083, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.95500648021698, "global_step": 580084, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.045597791671753, "global_step": 580085, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9814536571502686, "global_step": 580086, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.003453493118286, "global_step": 580087, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0010552406311035, "global_step": 580088, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.935874342918396, "global_step": 580089, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9486807584762573, "global_step": 580090, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.013458013534546, "global_step": 580091, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.041220188140869, "global_step": 580092, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0759904384613037, "global_step": 580093, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0827887058258057, "global_step": 580094, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.06833553314209, "global_step": 580095, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.010530471801758, "global_step": 580096, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.968288779258728, "global_step": 580097, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0581531524658203, "global_step": 580098, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.056896686553955, "global_step": 580099, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.950534701347351, "global_step": 580100, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9850208759307861, "global_step": 580101, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9860323667526245, "global_step": 580102, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0707008838653564, "global_step": 580103, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.979175090789795, "global_step": 580104, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.033799409866333, "global_step": 580105, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0745956897735596, "global_step": 580106, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0413577556610107, "global_step": 580107, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0240418910980225, "global_step": 580108, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9955353736877441, "global_step": 580109, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0594301223754883, "global_step": 580110, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0813019275665283, "global_step": 580111, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.028324604034424, "global_step": 580112, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9932429790496826, "global_step": 580113, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.995061993598938, "global_step": 580114, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0311367511749268, "global_step": 580115, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.032435655593872, "global_step": 580116, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0463221073150635, "global_step": 580117, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9962844848632812, "global_step": 580118, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.022848129272461, "global_step": 580119, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9029699563980103, "global_step": 580120, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0544071197509766, "global_step": 580121, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9793596267700195, "global_step": 580122, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.047936201095581, "global_step": 580123, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0269997119903564, "global_step": 580124, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0123801231384277, "global_step": 580125, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.054985523223877, "global_step": 580126, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.020765781402588, "global_step": 580127, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0018937587738037, "global_step": 580128, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.91733980178833, "global_step": 580129, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9709327220916748, "global_step": 580130, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.902977466583252, "global_step": 580131, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0675456523895264, "global_step": 580132, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.02913236618042, "global_step": 580133, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.005760431289673, "global_step": 580134, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1071839332580566, "global_step": 580135, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0146961212158203, "global_step": 580136, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0853004455566406, "global_step": 580137, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0397605895996094, "global_step": 580138, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0155718326568604, "global_step": 580139, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9780206680297852, "global_step": 580140, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0089187622070312, "global_step": 580141, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.011653423309326, "global_step": 580142, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0200982093811035, "global_step": 580143, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0523622035980225, "global_step": 580144, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.060913324356079, "global_step": 580145, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0959980487823486, "global_step": 580146, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0167300701141357, "global_step": 580147, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1027719974517822, "global_step": 580148, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0427017211914062, "global_step": 580149, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.01814866065979, "global_step": 580150, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9738073348999023, "global_step": 580151, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.950469970703125, "global_step": 580152, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9668149948120117, "global_step": 580153, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.980942964553833, "global_step": 580154, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0498273372650146, "global_step": 580155, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.043438196182251, "global_step": 580156, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0403125286102295, "global_step": 580157, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.965874433517456, "global_step": 580158, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9482731819152832, "global_step": 580159, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0448851585388184, "global_step": 580160, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9956300258636475, "global_step": 580161, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.00887393951416, "global_step": 580162, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9959415197372437, "global_step": 580163, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.020443916320801, "global_step": 580164, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.995914101600647, "global_step": 580165, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9589316844940186, "global_step": 580166, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0065970420837402, "global_step": 580167, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9900113344192505, "global_step": 580168, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0449061393737793, "global_step": 580169, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9745910167694092, "global_step": 580170, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.019176483154297, "global_step": 580171, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.088979959487915, "global_step": 580172, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9139604568481445, "global_step": 580173, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0250043869018555, "global_step": 580174, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.024972915649414, "global_step": 580175, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0262207984924316, "global_step": 580176, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.089853525161743, "global_step": 580177, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0353124141693115, "global_step": 580178, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9835140705108643, "global_step": 580179, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0663251876831055, "global_step": 580180, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0516085624694824, "global_step": 580181, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.026801347732544, "global_step": 580182, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0437564849853516, "global_step": 580183, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1037681102752686, "global_step": 580184, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.090898036956787, "global_step": 580185, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1208629608154297, "global_step": 580186, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9674837589263916, "global_step": 580187, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9369269609451294, "global_step": 580188, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9751499891281128, "global_step": 580189, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0461483001708984, "global_step": 580190, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9468722343444824, "global_step": 580191, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0394434928894043, "global_step": 580192, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9954472780227661, "global_step": 580193, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0195257663726807, "global_step": 580194, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9671666622161865, "global_step": 580195, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9994051456451416, "global_step": 580196, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0761008262634277, "global_step": 580197, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0000059604644775, "global_step": 580198, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.999165654182434, "global_step": 580199, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.049819231033325, "global_step": 580200, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9922192096710205, "global_step": 580201, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9464043378829956, "global_step": 580202, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9863629341125488, "global_step": 580203, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9636880159378052, "global_step": 580204, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1150624752044678, "global_step": 580205, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.035451650619507, "global_step": 580206, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.042588710784912, "global_step": 580207, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.023564577102661, "global_step": 580208, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9795761108398438, "global_step": 580209, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9327037334442139, "global_step": 580210, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0570929050445557, "global_step": 580211, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9262824058532715, "global_step": 580212, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9854258298873901, "global_step": 580213, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.059553861618042, "global_step": 580214, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0207149982452393, "global_step": 580215, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0324513912200928, "global_step": 580216, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0122625827789307, "global_step": 580217, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.973196268081665, "global_step": 580218, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0292305946350098, "global_step": 580219, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1057350635528564, "global_step": 580220, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.980610966682434, "global_step": 580221, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9809545278549194, "global_step": 580222, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9793025255203247, "global_step": 580223, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9987128973007202, "global_step": 580224, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0042552947998047, "global_step": 580225, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0102763175964355, "global_step": 580226, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.079850673675537, "global_step": 580227, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.961562156677246, "global_step": 580228, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.056708574295044, "global_step": 580229, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9662096500396729, "global_step": 580230, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1054792404174805, "global_step": 580231, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.005392074584961, "global_step": 580232, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.11641001701355, "global_step": 580233, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9768306016921997, "global_step": 580234, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.042635440826416, "global_step": 580235, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9607887268066406, "global_step": 580236, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9765318632125854, "global_step": 580237, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.006059408187866, "global_step": 580238, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.014963150024414, "global_step": 580239, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9565861225128174, "global_step": 580240, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.099782943725586, "global_step": 580241, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0538761615753174, "global_step": 580242, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0007853507995605, "global_step": 580243, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9893546104431152, "global_step": 580244, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0754826068878174, "global_step": 580245, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.04331111907959, "global_step": 580246, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0215466022491455, "global_step": 580247, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0060038566589355, "global_step": 580248, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0776894092559814, "global_step": 580249, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9657336473464966, "global_step": 580250, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0616073608398438, "global_step": 580251, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0430805683135986, "global_step": 580252, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.041280746459961, "global_step": 580253, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0230653285980225, "global_step": 580254, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.043052911758423, "global_step": 580255, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9394840002059937, "global_step": 580256, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0002856254577637, "global_step": 580257, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.018571615219116, "global_step": 580258, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0700039863586426, "global_step": 580259, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9978324174880981, "global_step": 580260, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0412325859069824, "global_step": 580261, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0096540451049805, "global_step": 580262, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0025172233581543, "global_step": 580263, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9356884956359863, "global_step": 580264, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0197317600250244, "global_step": 580265, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0063364505767822, "global_step": 580266, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0848820209503174, "global_step": 580267, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.054504632949829, "global_step": 580268, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9854815006256104, "global_step": 580269, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.989172101020813, "global_step": 580270, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.114060401916504, "global_step": 580271, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9592669010162354, "global_step": 580272, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0489962100982666, "global_step": 580273, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9565539360046387, "global_step": 580274, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9668877124786377, "global_step": 580275, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.079806327819824, "global_step": 580276, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0345027446746826, "global_step": 580277, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0448970794677734, "global_step": 580278, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.067087411880493, "global_step": 580279, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0416128635406494, "global_step": 580280, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.006795644760132, "global_step": 580281, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0067639350891113, "global_step": 580282, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.071458339691162, "global_step": 580283, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.083146572113037, "global_step": 580284, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9768372774124146, "global_step": 580285, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1038169860839844, "global_step": 580286, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9875470399856567, "global_step": 580287, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9551026821136475, "global_step": 580288, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1002957820892334, "global_step": 580289, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.009948968887329, "global_step": 580290, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9705621004104614, "global_step": 580291, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.013963460922241, "global_step": 580292, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0895497798919678, "global_step": 580293, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0004703998565674, "global_step": 580294, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0641965866088867, "global_step": 580295, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9187633991241455, "global_step": 580296, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0373735427856445, "global_step": 580297, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.063971519470215, "global_step": 580298, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9909394979476929, "global_step": 580299, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.029703378677368, "global_step": 580300, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0131373405456543, "global_step": 580301, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0918328762054443, "global_step": 580302, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.047658920288086, "global_step": 580303, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0123486518859863, "global_step": 580304, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.072148561477661, "global_step": 580305, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.140544891357422, "global_step": 580306, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.034450054168701, "global_step": 580307, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9512299299240112, "global_step": 580308, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0038130283355713, "global_step": 580309, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0761990547180176, "global_step": 580310, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0277960300445557, "global_step": 580311, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0462350845336914, "global_step": 580312, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.970992922782898, "global_step": 580313, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0383543968200684, "global_step": 580314, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9364959001541138, "global_step": 580315, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9586137533187866, "global_step": 580316, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.014805316925049, "global_step": 580317, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.046455144882202, "global_step": 580318, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0261569023132324, "global_step": 580319, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0268545150756836, "global_step": 580320, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.91077721118927, "global_step": 580321, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0408990383148193, "global_step": 580322, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0814812183380127, "global_step": 580323, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.057452440261841, "global_step": 580324, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.081653118133545, "global_step": 580325, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.958114504814148, "global_step": 580326, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.003171682357788, "global_step": 580327, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.090564489364624, "global_step": 580328, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0319395065307617, "global_step": 580329, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9981659650802612, "global_step": 580330, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.041989803314209, "global_step": 580331, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.033308744430542, "global_step": 580332, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.030776023864746, "global_step": 580333, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0377089977264404, "global_step": 580334, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9893840551376343, "global_step": 580335, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0130581855773926, "global_step": 580336, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.019709348678589, "global_step": 580337, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0921051502227783, "global_step": 580338, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0292611122131348, "global_step": 580339, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.136552572250366, "global_step": 580340, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0684616565704346, "global_step": 580341, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0719053745269775, "global_step": 580342, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1203665733337402, "global_step": 580343, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0631566047668457, "global_step": 580344, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0470898151397705, "global_step": 580345, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.036193609237671, "global_step": 580346, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9522982835769653, "global_step": 580347, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.040637493133545, "global_step": 580348, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9559775590896606, "global_step": 580349, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0213794708251953, "global_step": 580350, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0189383029937744, "global_step": 580351, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9952446222305298, "global_step": 580352, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.898935079574585, "global_step": 580353, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0256261825561523, "global_step": 580354, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9940611124038696, "global_step": 580355, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0982303619384766, "global_step": 580356, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1163105964660645, "global_step": 580357, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.037144660949707, "global_step": 580358, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.983628749847412, "global_step": 580359, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9923666715621948, "global_step": 580360, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0065107345581055, "global_step": 580361, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9515305757522583, "global_step": 580362, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0395405292510986, "global_step": 580363, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9993287324905396, "global_step": 580364, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.048548698425293, "global_step": 580365, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0302727222442627, "global_step": 580366, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0088982582092285, "global_step": 580367, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.990344524383545, "global_step": 580368, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.002545118331909, "global_step": 580369, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.091907501220703, "global_step": 580370, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0610334873199463, "global_step": 580371, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.993973731994629, "global_step": 580372, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.06874680519104, "global_step": 580373, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0574350357055664, "global_step": 580374, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9694056510925293, "global_step": 580375, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0125234127044678, "global_step": 580376, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.038264036178589, "global_step": 580377, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.113121509552002, "global_step": 580378, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9724559783935547, "global_step": 580379, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.050166606903076, "global_step": 580380, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0828135013580322, "global_step": 580381, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0244572162628174, "global_step": 580382, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9911322593688965, "global_step": 580383, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.050856351852417, "global_step": 580384, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0759027004241943, "global_step": 580385, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9798210859298706, "global_step": 580386, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.084430694580078, "global_step": 580387, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1074585914611816, "global_step": 580388, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.059044361114502, "global_step": 580389, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.019350051879883, "global_step": 580390, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9689085483551025, "global_step": 580391, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.941253662109375, "global_step": 580392, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0366485118865967, "global_step": 580393, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0670573711395264, "global_step": 580394, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9577434062957764, "global_step": 580395, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9647290706634521, "global_step": 580396, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.05782413482666, "global_step": 580397, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.053234100341797, "global_step": 580398, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9863954782485962, "global_step": 580399, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9947502613067627, "global_step": 580400, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0169968605041504, "global_step": 580401, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9756325483322144, "global_step": 580402, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.988579273223877, "global_step": 580403, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0649068355560303, "global_step": 580404, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.028496503829956, "global_step": 580405, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0297091007232666, "global_step": 580406, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0507490634918213, "global_step": 580407, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.004167079925537, "global_step": 580408, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0742316246032715, "global_step": 580409, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0676114559173584, "global_step": 580410, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0282912254333496, "global_step": 580411, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0074586868286133, "global_step": 580412, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0566787719726562, "global_step": 580413, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9846711158752441, "global_step": 580414, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0370278358459473, "global_step": 580415, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.012850284576416, "global_step": 580416, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.04585337638855, "global_step": 580417, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0034050941467285, "global_step": 580418, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.051896095275879, "global_step": 580419, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0170235633850098, "global_step": 580420, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0578970909118652, "global_step": 580421, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9525178670883179, "global_step": 580422, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.059171676635742, "global_step": 580423, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.082719564437866, "global_step": 580424, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0139760971069336, "global_step": 580425, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0400168895721436, "global_step": 580426, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.069546699523926, "global_step": 580427, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.998023509979248, "global_step": 580428, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.054724931716919, "global_step": 580429, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9737985134124756, "global_step": 580430, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0739378929138184, "global_step": 580431, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0046582221984863, "global_step": 580432, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.101091146469116, "global_step": 580433, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9972552061080933, "global_step": 580434, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0831503868103027, "global_step": 580435, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.966111183166504, "global_step": 580436, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0728023052215576, "global_step": 580437, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0090198516845703, "global_step": 580438, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.99601149559021, "global_step": 580439, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.036637306213379, "global_step": 580440, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0177817344665527, "global_step": 580441, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.042572021484375, "global_step": 580442, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9343290328979492, "global_step": 580443, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9993518590927124, "global_step": 580444, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0442099571228027, "global_step": 580445, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9802297353744507, "global_step": 580446, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.030623435974121, "global_step": 580447, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9471608400344849, "global_step": 580448, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.037524700164795, "global_step": 580449, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0360100269317627, "global_step": 580450, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.063760757446289, "global_step": 580451, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9326330423355103, "global_step": 580452, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9949041604995728, "global_step": 580453, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0852057933807373, "global_step": 580454, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0563457012176514, "global_step": 580455, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0145442485809326, "global_step": 580456, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0103206634521484, "global_step": 580457, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9898103475570679, "global_step": 580458, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9209381341934204, "global_step": 580459, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9861611127853394, "global_step": 580460, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9963103532791138, "global_step": 580461, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.035717487335205, "global_step": 580462, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0565707683563232, "global_step": 580463, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0873749256134033, "global_step": 580464, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0541439056396484, "global_step": 580465, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.023531913757324, "global_step": 580466, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0128767490386963, "global_step": 580467, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1172289848327637, "global_step": 580468, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0919761657714844, "global_step": 580469, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.017160415649414, "global_step": 580470, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.058077096939087, "global_step": 580471, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0477662086486816, "global_step": 580472, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.986119031906128, "global_step": 580473, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.049950361251831, "global_step": 580474, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.894415020942688, "global_step": 580475, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.984384298324585, "global_step": 580476, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0449845790863037, "global_step": 580477, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.100548505783081, "global_step": 580478, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0755960941314697, "global_step": 580479, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.05014967918396, "global_step": 580480, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0211293697357178, "global_step": 580481, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0014965534210205, "global_step": 580482, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9957355260849, "global_step": 580483, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0163981914520264, "global_step": 580484, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0899267196655273, "global_step": 580485, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.947265863418579, "global_step": 580486, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.969070315361023, "global_step": 580487, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9194899797439575, "global_step": 580488, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0004684925079346, "global_step": 580489, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9856696128845215, "global_step": 580490, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0160701274871826, "global_step": 580491, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0039422512054443, "global_step": 580492, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9681583642959595, "global_step": 580493, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0121235847473145, "global_step": 580494, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0797860622406006, "global_step": 580495, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.062818765640259, "global_step": 580496, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0455894470214844, "global_step": 580497, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0365242958068848, "global_step": 580498, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.011047124862671, "global_step": 580499, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.03537654876709, "global_step": 580500, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.053415536880493, "global_step": 580501, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0366344451904297, "global_step": 580502, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.094075918197632, "global_step": 580503, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9890775680541992, "global_step": 580504, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9867916107177734, "global_step": 580505, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.057542562484741, "global_step": 580506, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.05647873878479, "global_step": 580507, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9787307977676392, "global_step": 580508, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.043027400970459, "global_step": 580509, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.956298828125, "global_step": 580510, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9881858825683594, "global_step": 580511, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.997935175895691, "global_step": 580512, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.005300521850586, "global_step": 580513, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.147859573364258, "global_step": 580514, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1236207485198975, "global_step": 580515, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9668582677841187, "global_step": 580516, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.010594129562378, "global_step": 580517, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9593290090560913, "global_step": 580518, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.072376251220703, "global_step": 580519, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0299184322357178, "global_step": 580520, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0008792877197266, "global_step": 580521, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.996370792388916, "global_step": 580522, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9210398197174072, "global_step": 580523, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9742305278778076, "global_step": 580524, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.953802466392517, "global_step": 580525, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9843388795852661, "global_step": 580526, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.063751220703125, "global_step": 580527, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9977203607559204, "global_step": 580528, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.067054510116577, "global_step": 580529, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.006819725036621, "global_step": 580530, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.085829734802246, "global_step": 580531, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.100811243057251, "global_step": 580532, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0344369411468506, "global_step": 580533, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1207921504974365, "global_step": 580534, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.002413749694824, "global_step": 580535, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9955332279205322, "global_step": 580536, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.140014171600342, "global_step": 580537, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1121718883514404, "global_step": 580538, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.049424171447754, "global_step": 580539, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.1544556617736816, "global_step": 580540, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0666913986206055, "global_step": 580541, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.048123836517334, "global_step": 580542, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0536301136016846, "global_step": 580543, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.030951976776123, "global_step": 580544, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9206936359405518, "global_step": 580545, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.111900568008423, "global_step": 580546, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.994443655014038, "global_step": 580547, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0209250450134277, "global_step": 580548, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9830306768417358, "global_step": 580549, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.97145676612854, "global_step": 580550, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.999693512916565, "global_step": 580551, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9457979202270508, "global_step": 580552, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.988753318786621, "global_step": 580553, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.001129388809204, "global_step": 580554, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9990274906158447, "global_step": 580555, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0431132316589355, "global_step": 580556, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0375070571899414, "global_step": 580557, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.034797191619873, "global_step": 580558, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9637513160705566, "global_step": 580559, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.061491012573242, "global_step": 580560, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.037818193435669, "global_step": 580561, "epoch": 948, "lr": 5e-05}
{"train_loss": 1.9885449409484863, "global_step": 580562, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0199356079101562, "global_step": 580563, "epoch": 948, "lr": 5e-05}
{"train_loss": 2.0178916454315186, "global_step": 580564, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9764437675476074, "global_step": 580565, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9669831991195679, "global_step": 580566, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.916507363319397, "global_step": 580567, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.026353120803833, "global_step": 580568, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.099738597869873, "global_step": 580569, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0123655796051025, "global_step": 580570, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0893239974975586, "global_step": 580571, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0633223056793213, "global_step": 580572, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9853425025939941, "global_step": 580573, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.999435544013977, "global_step": 580574, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0244672298431396, "global_step": 580575, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.955021619796753, "global_step": 580576, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.047611951828003, "global_step": 580577, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0052988529205322, "global_step": 580578, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9859801530838013, "global_step": 580579, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9346915483474731, "global_step": 580580, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0340304374694824, "global_step": 580581, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.997031807899475, "global_step": 580582, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9595025777816772, "global_step": 580583, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9363670349121094, "global_step": 580584, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9832642078399658, "global_step": 580585, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.064424514770508, "global_step": 580586, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0413529872894287, "global_step": 580587, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.093691110610962, "global_step": 580588, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9950792789459229, "global_step": 580589, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0418975353240967, "global_step": 580590, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0615954399108887, "global_step": 580591, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0671043395996094, "global_step": 580592, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.009491443634033, "global_step": 580593, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.035679817199707, "global_step": 580594, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9680863618850708, "global_step": 580595, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9429537057876587, "global_step": 580596, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9579432010650635, "global_step": 580597, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9342321157455444, "global_step": 580598, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9881287813186646, "global_step": 580599, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.001922845840454, "global_step": 580600, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1272311210632324, "global_step": 580601, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0088672637939453, "global_step": 580602, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.978785514831543, "global_step": 580603, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.019299030303955, "global_step": 580604, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9708192348480225, "global_step": 580605, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.956466794013977, "global_step": 580606, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.059678792953491, "global_step": 580607, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0952582359313965, "global_step": 580608, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0313422679901123, "global_step": 580609, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.025447130203247, "global_step": 580610, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0015358924865723, "global_step": 580611, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0623509883880615, "global_step": 580612, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9833587408065796, "global_step": 580613, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0417802333831787, "global_step": 580614, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0058040618896484, "global_step": 580615, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.033514976501465, "global_step": 580616, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.059476852416992, "global_step": 580617, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.000823974609375, "global_step": 580618, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9705125093460083, "global_step": 580619, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0813345909118652, "global_step": 580620, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9297693967819214, "global_step": 580621, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.029003858566284, "global_step": 580622, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.978522539138794, "global_step": 580623, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.973957896232605, "global_step": 580624, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9957380294799805, "global_step": 580625, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0014917850494385, "global_step": 580626, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0277528762817383, "global_step": 580627, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9681593179702759, "global_step": 580628, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.99104905128479, "global_step": 580629, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.052008628845215, "global_step": 580630, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.98527193069458, "global_step": 580631, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0837152004241943, "global_step": 580632, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9889307022094727, "global_step": 580633, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0039591789245605, "global_step": 580634, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.095944881439209, "global_step": 580635, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.057142972946167, "global_step": 580636, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0357115268707275, "global_step": 580637, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.044928550720215, "global_step": 580638, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9180099964141846, "global_step": 580639, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.063769817352295, "global_step": 580640, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9703880548477173, "global_step": 580641, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.955629587173462, "global_step": 580642, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9577176570892334, "global_step": 580643, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.068976879119873, "global_step": 580644, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9913312196731567, "global_step": 580645, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.070582389831543, "global_step": 580646, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.07798433303833, "global_step": 580647, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.022946834564209, "global_step": 580648, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9806747436523438, "global_step": 580649, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0379090309143066, "global_step": 580650, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.014723777770996, "global_step": 580651, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0685274600982666, "global_step": 580652, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0679874420166016, "global_step": 580653, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.032869338989258, "global_step": 580654, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.989722728729248, "global_step": 580655, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.086967706680298, "global_step": 580656, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0293450355529785, "global_step": 580657, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9424563646316528, "global_step": 580658, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9644339084625244, "global_step": 580659, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.056311845779419, "global_step": 580660, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.081355333328247, "global_step": 580661, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9583749771118164, "global_step": 580662, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0284266471862793, "global_step": 580663, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0037972927093506, "global_step": 580664, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9959824085235596, "global_step": 580665, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.051285743713379, "global_step": 580666, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0274555683135986, "global_step": 580667, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9664779901504517, "global_step": 580668, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0250988006591797, "global_step": 580669, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0291507244110107, "global_step": 580670, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0715293884277344, "global_step": 580671, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0325822830200195, "global_step": 580672, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1007142066955566, "global_step": 580673, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.915291666984558, "global_step": 580674, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0065135955810547, "global_step": 580675, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0208137035369873, "global_step": 580676, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9863545894622803, "global_step": 580677, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9043970108032227, "global_step": 580678, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9203346967697144, "global_step": 580679, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.990157127380371, "global_step": 580680, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0047128200531006, "global_step": 580681, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9679632186889648, "global_step": 580682, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.064743757247925, "global_step": 580683, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.080315589904785, "global_step": 580684, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0230612754821777, "global_step": 580685, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.969495177268982, "global_step": 580686, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0764119625091553, "global_step": 580687, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0047972202301025, "global_step": 580688, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0252256393432617, "global_step": 580689, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.055572032928467, "global_step": 580690, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9314651489257812, "global_step": 580691, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9935457706451416, "global_step": 580692, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9620411396026611, "global_step": 580693, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.081824541091919, "global_step": 580694, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.991790771484375, "global_step": 580695, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9767930507659912, "global_step": 580696, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.024380922317505, "global_step": 580697, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9475680589675903, "global_step": 580698, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9248532056808472, "global_step": 580699, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0252573490142822, "global_step": 580700, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1611809730529785, "global_step": 580701, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.989054799079895, "global_step": 580702, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0594120025634766, "global_step": 580703, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.10274076461792, "global_step": 580704, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.048593044281006, "global_step": 580705, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0128512382507324, "global_step": 580706, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.062282085418701, "global_step": 580707, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.02758526802063, "global_step": 580708, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9715898036956787, "global_step": 580709, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9839167594909668, "global_step": 580710, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.089592456817627, "global_step": 580711, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0282416343688965, "global_step": 580712, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9457427263259888, "global_step": 580713, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9337437152862549, "global_step": 580714, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.051192283630371, "global_step": 580715, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0018835067749023, "global_step": 580716, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.020934581756592, "global_step": 580717, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9959434270858765, "global_step": 580718, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9435415267944336, "global_step": 580719, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9192817211151123, "global_step": 580720, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0557408332824707, "global_step": 580721, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.980366826057434, "global_step": 580722, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.984477162361145, "global_step": 580723, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0055911540985107, "global_step": 580724, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9919288158416748, "global_step": 580725, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9559484720230103, "global_step": 580726, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0346672534942627, "global_step": 580727, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.009690761566162, "global_step": 580728, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1386635303497314, "global_step": 580729, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9941483736038208, "global_step": 580730, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0026192665100098, "global_step": 580731, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.088437795639038, "global_step": 580732, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.071476697921753, "global_step": 580733, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9703295230865479, "global_step": 580734, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9926159381866455, "global_step": 580735, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9617197513580322, "global_step": 580736, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.038661241531372, "global_step": 580737, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.005929470062256, "global_step": 580738, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9866111278533936, "global_step": 580739, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9467089176177979, "global_step": 580740, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0422956943511963, "global_step": 580741, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1424543857574463, "global_step": 580742, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.017786741256714, "global_step": 580743, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0463433265686035, "global_step": 580744, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.110692262649536, "global_step": 580745, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0719077587127686, "global_step": 580746, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9611623287200928, "global_step": 580747, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9508898258209229, "global_step": 580748, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.905456781387329, "global_step": 580749, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9994651079177856, "global_step": 580750, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9948225021362305, "global_step": 580751, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9797297716140747, "global_step": 580752, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0528910160064697, "global_step": 580753, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0208547115325928, "global_step": 580754, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.018099069595337, "global_step": 580755, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9826104640960693, "global_step": 580756, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1196656227111816, "global_step": 580757, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0407769680023193, "global_step": 580758, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9989337921142578, "global_step": 580759, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0548362731933594, "global_step": 580760, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.966529130935669, "global_step": 580761, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9816597700119019, "global_step": 580762, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.059687614440918, "global_step": 580763, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9437147378921509, "global_step": 580764, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.931239366531372, "global_step": 580765, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.010096788406372, "global_step": 580766, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.943793773651123, "global_step": 580767, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.04939341545105, "global_step": 580768, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.012164354324341, "global_step": 580769, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0204086303710938, "global_step": 580770, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.045321464538574, "global_step": 580771, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0532517433166504, "global_step": 580772, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.026520013809204, "global_step": 580773, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.106236219406128, "global_step": 580774, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9651941061019897, "global_step": 580775, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9513996839523315, "global_step": 580776, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9867249727249146, "global_step": 580777, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.033517360687256, "global_step": 580778, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9160010814666748, "global_step": 580779, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0564024448394775, "global_step": 580780, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0233469009399414, "global_step": 580781, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.080435037612915, "global_step": 580782, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0081210136413574, "global_step": 580783, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0607175827026367, "global_step": 580784, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.121002197265625, "global_step": 580785, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0290658473968506, "global_step": 580786, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.039745330810547, "global_step": 580787, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.055859327316284, "global_step": 580788, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9710737466812134, "global_step": 580789, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0598926544189453, "global_step": 580790, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0083348751068115, "global_step": 580791, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.065023422241211, "global_step": 580792, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.02776837348938, "global_step": 580793, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0593514442443848, "global_step": 580794, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.952040672302246, "global_step": 580795, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9971818923950195, "global_step": 580796, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.00994873046875, "global_step": 580797, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0193424224853516, "global_step": 580798, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0755157470703125, "global_step": 580799, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0270636081695557, "global_step": 580800, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9378341436386108, "global_step": 580801, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.109102725982666, "global_step": 580802, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9723891019821167, "global_step": 580803, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9676467180252075, "global_step": 580804, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0251405239105225, "global_step": 580805, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9290070533752441, "global_step": 580806, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.958277940750122, "global_step": 580807, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0402135848999023, "global_step": 580808, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.991737723350525, "global_step": 580809, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.012845516204834, "global_step": 580810, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.024972677230835, "global_step": 580811, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1146628856658936, "global_step": 580812, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9356688261032104, "global_step": 580813, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.137277364730835, "global_step": 580814, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0012898445129395, "global_step": 580815, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.029667854309082, "global_step": 580816, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0357184410095215, "global_step": 580817, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.022925853729248, "global_step": 580818, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.026862859725952, "global_step": 580819, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.023564100265503, "global_step": 580820, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9380089044570923, "global_step": 580821, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.936232566833496, "global_step": 580822, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.03071928024292, "global_step": 580823, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9887971878051758, "global_step": 580824, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.04719877243042, "global_step": 580825, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0166003704071045, "global_step": 580826, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0187501907348633, "global_step": 580827, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0069799423217773, "global_step": 580828, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9604133367538452, "global_step": 580829, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.99557363986969, "global_step": 580830, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0726966857910156, "global_step": 580831, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9969812631607056, "global_step": 580832, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0202674865722656, "global_step": 580833, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9518253803253174, "global_step": 580834, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0669472217559814, "global_step": 580835, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9768528938293457, "global_step": 580836, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9800678491592407, "global_step": 580837, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.021090030670166, "global_step": 580838, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.100423812866211, "global_step": 580839, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.996856689453125, "global_step": 580840, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9236682653427124, "global_step": 580841, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.046898126602173, "global_step": 580842, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0591840744018555, "global_step": 580843, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0095365047454834, "global_step": 580844, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0872809886932373, "global_step": 580845, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0934221744537354, "global_step": 580846, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.000190496444702, "global_step": 580847, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.074352741241455, "global_step": 580848, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0136911869049072, "global_step": 580849, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0252914428710938, "global_step": 580850, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9316527843475342, "global_step": 580851, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.028020143508911, "global_step": 580852, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.062440872192383, "global_step": 580853, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.047703266143799, "global_step": 580854, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.101719617843628, "global_step": 580855, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9772588014602661, "global_step": 580856, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0575475692749023, "global_step": 580857, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9888101816177368, "global_step": 580858, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9393501281738281, "global_step": 580859, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1284000873565674, "global_step": 580860, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9820278882980347, "global_step": 580861, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0369956493377686, "global_step": 580862, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.07797908782959, "global_step": 580863, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0274405479431152, "global_step": 580864, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9878077507019043, "global_step": 580865, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0059127807617188, "global_step": 580866, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.00636625289917, "global_step": 580867, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.052095413208008, "global_step": 580868, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9779882431030273, "global_step": 580869, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9587008953094482, "global_step": 580870, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.931791067123413, "global_step": 580871, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0186283588409424, "global_step": 580872, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0445683002471924, "global_step": 580873, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9825776815414429, "global_step": 580874, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0125162601470947, "global_step": 580875, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9894336462020874, "global_step": 580876, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9847939014434814, "global_step": 580877, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0768909454345703, "global_step": 580878, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9337352514266968, "global_step": 580879, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0067877769470215, "global_step": 580880, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9113973379135132, "global_step": 580881, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0043394565582275, "global_step": 580882, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.02714204788208, "global_step": 580883, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.00852370262146, "global_step": 580884, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.01352858543396, "global_step": 580885, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9459220170974731, "global_step": 580886, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.059635639190674, "global_step": 580887, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.005537271499634, "global_step": 580888, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.951149821281433, "global_step": 580889, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9083588123321533, "global_step": 580890, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0532310009002686, "global_step": 580891, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0509371757507324, "global_step": 580892, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9923129081726074, "global_step": 580893, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9693025350570679, "global_step": 580894, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0727756023406982, "global_step": 580895, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.085042715072632, "global_step": 580896, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9963287115097046, "global_step": 580897, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.016343832015991, "global_step": 580898, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9966511726379395, "global_step": 580899, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9268025159835815, "global_step": 580900, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0767924785614014, "global_step": 580901, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9938849210739136, "global_step": 580902, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0346744060516357, "global_step": 580903, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9960360527038574, "global_step": 580904, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9999444484710693, "global_step": 580905, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0106115341186523, "global_step": 580906, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0429980754852295, "global_step": 580907, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0596258640289307, "global_step": 580908, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.050337076187134, "global_step": 580909, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9921290874481201, "global_step": 580910, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.026512861251831, "global_step": 580911, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9419573545455933, "global_step": 580912, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9931764602661133, "global_step": 580913, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.995701789855957, "global_step": 580914, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0771677494049072, "global_step": 580915, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9227863550186157, "global_step": 580916, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.081925868988037, "global_step": 580917, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0230495929718018, "global_step": 580918, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0274016857147217, "global_step": 580919, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0171797275543213, "global_step": 580920, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9798239469528198, "global_step": 580921, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.016399621963501, "global_step": 580922, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9746955633163452, "global_step": 580923, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.054671049118042, "global_step": 580924, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.057366132736206, "global_step": 580925, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9799538850784302, "global_step": 580926, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0319325923919678, "global_step": 580927, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1075639724731445, "global_step": 580928, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.129483938217163, "global_step": 580929, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0973150730133057, "global_step": 580930, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9674662351608276, "global_step": 580931, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.029822826385498, "global_step": 580932, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.964639663696289, "global_step": 580933, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.073411226272583, "global_step": 580934, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9446948766708374, "global_step": 580935, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9880311489105225, "global_step": 580936, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0335824489593506, "global_step": 580937, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.008815050125122, "global_step": 580938, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9529931545257568, "global_step": 580939, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.061307191848755, "global_step": 580940, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0849251747131348, "global_step": 580941, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9763731956481934, "global_step": 580942, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0292646884918213, "global_step": 580943, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.034517288208008, "global_step": 580944, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0123891830444336, "global_step": 580945, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.031014919281006, "global_step": 580946, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9681975841522217, "global_step": 580947, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0071005821228027, "global_step": 580948, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0594985485076904, "global_step": 580949, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9197460412979126, "global_step": 580950, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0481064319610596, "global_step": 580951, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9739220142364502, "global_step": 580952, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.055478572845459, "global_step": 580953, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0661635398864746, "global_step": 580954, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0497796535491943, "global_step": 580955, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.046002149581909, "global_step": 580956, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.040924072265625, "global_step": 580957, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9684395790100098, "global_step": 580958, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9803637266159058, "global_step": 580959, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.08038592338562, "global_step": 580960, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0464766025543213, "global_step": 580961, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0072574615478516, "global_step": 580962, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.102843761444092, "global_step": 580963, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.123624086380005, "global_step": 580964, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0838894844055176, "global_step": 580965, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0784335136413574, "global_step": 580966, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.038972854614258, "global_step": 580967, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.949395775794983, "global_step": 580968, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0800623893737793, "global_step": 580969, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9648702144622803, "global_step": 580970, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9119716882705688, "global_step": 580971, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.949620008468628, "global_step": 580972, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.091831922531128, "global_step": 580973, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0584957599639893, "global_step": 580974, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.981344223022461, "global_step": 580975, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.995423436164856, "global_step": 580976, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0421581268310547, "global_step": 580977, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0579872131347656, "global_step": 580978, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0263304710388184, "global_step": 580979, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.024182081222534, "global_step": 580980, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0568010807037354, "global_step": 580981, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.069101572036743, "global_step": 580982, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.039721965789795, "global_step": 580983, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0483598709106445, "global_step": 580984, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.976202130317688, "global_step": 580985, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9937349557876587, "global_step": 580986, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.049880266189575, "global_step": 580987, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.105769157409668, "global_step": 580988, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9663647413253784, "global_step": 580989, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.03196382522583, "global_step": 580990, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9737423658370972, "global_step": 580991, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0017993450164795, "global_step": 580992, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.053257703781128, "global_step": 580993, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.042919158935547, "global_step": 580994, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.097412347793579, "global_step": 580995, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.01192045211792, "global_step": 580996, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0255863666534424, "global_step": 580997, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.011000156402588, "global_step": 580998, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9883612394332886, "global_step": 580999, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0604662895202637, "global_step": 581000, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.997882604598999, "global_step": 581001, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.129758358001709, "global_step": 581002, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9163917303085327, "global_step": 581003, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0042636394500732, "global_step": 581004, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.035888671875, "global_step": 581005, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9868654012680054, "global_step": 581006, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0389716625213623, "global_step": 581007, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1085991859436035, "global_step": 581008, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0379607677459717, "global_step": 581009, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0645971298217773, "global_step": 581010, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.002929925918579, "global_step": 581011, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.016281843185425, "global_step": 581012, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0223615169525146, "global_step": 581013, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9863463640213013, "global_step": 581014, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0080766677856445, "global_step": 581015, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0985586643218994, "global_step": 581016, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.014772653579712, "global_step": 581017, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0304954051971436, "global_step": 581018, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0812528133392334, "global_step": 581019, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0420329570770264, "global_step": 581020, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0073413848876953, "global_step": 581021, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0425949096679688, "global_step": 581022, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.036888599395752, "global_step": 581023, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0347177982330322, "global_step": 581024, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.105184555053711, "global_step": 581025, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9436273574829102, "global_step": 581026, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0032167434692383, "global_step": 581027, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.8830811977386475, "global_step": 581028, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9867295026779175, "global_step": 581029, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.030812978744507, "global_step": 581030, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.035597801208496, "global_step": 581031, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0486881732940674, "global_step": 581032, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9697253704071045, "global_step": 581033, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0717921257019043, "global_step": 581034, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9750007390975952, "global_step": 581035, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.059659481048584, "global_step": 581036, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0136358737945557, "global_step": 581037, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0624959468841553, "global_step": 581038, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0771687030792236, "global_step": 581039, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.018857479095459, "global_step": 581040, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.025969982147217, "global_step": 581041, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.031477451324463, "global_step": 581042, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0622246265411377, "global_step": 581043, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9678577184677124, "global_step": 581044, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.118300199508667, "global_step": 581045, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0337016582489014, "global_step": 581046, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.008204698562622, "global_step": 581047, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.049299716949463, "global_step": 581048, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.971315622329712, "global_step": 581049, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0045700073242188, "global_step": 581050, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9345996379852295, "global_step": 581051, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.003288507461548, "global_step": 581052, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.999495029449463, "global_step": 581053, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9909390211105347, "global_step": 581054, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.05264949798584, "global_step": 581055, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0201220512390137, "global_step": 581056, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9988222122192383, "global_step": 581057, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.055741310119629, "global_step": 581058, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.110560417175293, "global_step": 581059, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0310444831848145, "global_step": 581060, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9822545051574707, "global_step": 581061, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0147905349731445, "global_step": 581062, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.960405945777893, "global_step": 581063, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0297696590423584, "global_step": 581064, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0078482627868652, "global_step": 581065, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9653747081756592, "global_step": 581066, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0163915157318115, "global_step": 581067, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.113140344619751, "global_step": 581068, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9523355960845947, "global_step": 581069, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.046531915664673, "global_step": 581070, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0180914402008057, "global_step": 581071, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.119417428970337, "global_step": 581072, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.011528253555298, "global_step": 581073, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1169891357421875, "global_step": 581074, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9884878396987915, "global_step": 581075, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0381100177764893, "global_step": 581076, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.016301155090332, "global_step": 581077, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.939283847808838, "global_step": 581078, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.052947998046875, "global_step": 581079, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0844292640686035, "global_step": 581080, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0136265754699707, "global_step": 581081, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9088972806930542, "global_step": 581082, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0900790691375732, "global_step": 581083, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9700497388839722, "global_step": 581084, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.97930109500885, "global_step": 581085, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9993239641189575, "global_step": 581086, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9925692081451416, "global_step": 581087, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0125317573547363, "global_step": 581088, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0317599773406982, "global_step": 581089, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0203566551208496, "global_step": 581090, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.044558048248291, "global_step": 581091, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0529372692108154, "global_step": 581092, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9937032461166382, "global_step": 581093, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.058444023132324, "global_step": 581094, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9466954469680786, "global_step": 581095, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.084334135055542, "global_step": 581096, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0240302085876465, "global_step": 581097, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9936131238937378, "global_step": 581098, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9384815692901611, "global_step": 581099, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9566981792449951, "global_step": 581100, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0416674613952637, "global_step": 581101, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.011944055557251, "global_step": 581102, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9705283641815186, "global_step": 581103, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.064267635345459, "global_step": 581104, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9827126264572144, "global_step": 581105, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.014824867248535, "global_step": 581106, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.114304542541504, "global_step": 581107, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.090000629425049, "global_step": 581108, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.005026340484619, "global_step": 581109, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.959550142288208, "global_step": 581110, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1004445552825928, "global_step": 581111, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9946770668029785, "global_step": 581112, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0564165115356445, "global_step": 581113, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.07820200920105, "global_step": 581114, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.038774013519287, "global_step": 581115, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0184848308563232, "global_step": 581116, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.055543899536133, "global_step": 581117, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9737696647644043, "global_step": 581118, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0195534229278564, "global_step": 581119, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9862477779388428, "global_step": 581120, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0284361839294434, "global_step": 581121, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0314908027648926, "global_step": 581122, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1234850883483887, "global_step": 581123, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9981642961502075, "global_step": 581124, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0902812480926514, "global_step": 581125, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.05491042137146, "global_step": 581126, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9674471616744995, "global_step": 581127, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9109644889831543, "global_step": 581128, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.050476312637329, "global_step": 581129, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1111435890197754, "global_step": 581130, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.033280372619629, "global_step": 581131, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9832817316055298, "global_step": 581132, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1143527030944824, "global_step": 581133, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0269222259521484, "global_step": 581134, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9974870681762695, "global_step": 581135, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0415594577789307, "global_step": 581136, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0487868785858154, "global_step": 581137, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0267043113708496, "global_step": 581138, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9604895114898682, "global_step": 581139, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1178202629089355, "global_step": 581140, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9427484273910522, "global_step": 581141, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0307209491729736, "global_step": 581142, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.008312702178955, "global_step": 581143, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9468472003936768, "global_step": 581144, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9679750204086304, "global_step": 581145, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1066877841949463, "global_step": 581146, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9335987567901611, "global_step": 581147, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9568613767623901, "global_step": 581148, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.037783622741699, "global_step": 581149, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0280911922454834, "global_step": 581150, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1010982990264893, "global_step": 581151, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.016838550567627, "global_step": 581152, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.019693374633789, "global_step": 581153, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0558390617370605, "global_step": 581154, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1470141410827637, "global_step": 581155, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.007640838623047, "global_step": 581156, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.019698143005371, "global_step": 581157, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0141549110412598, "global_step": 581158, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0235695838928223, "global_step": 581159, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.977439284324646, "global_step": 581160, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9912428855895996, "global_step": 581161, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.053222894668579, "global_step": 581162, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9837210178375244, "global_step": 581163, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9944126605987549, "global_step": 581164, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9015308618545532, "global_step": 581165, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9591609239578247, "global_step": 581166, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0081846714019775, "global_step": 581167, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0242178440093994, "global_step": 581168, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9896702766418457, "global_step": 581169, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9944952726364136, "global_step": 581170, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.008810520172119, "global_step": 581171, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0240116119384766, "global_step": 581172, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.997349739074707, "global_step": 581173, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0069334506988525, "global_step": 581174, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.020557403564453, "global_step": 581175, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0305631160736084, "global_step": 581176, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9147717952728271, "global_step": 581177, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0856471061706543, "global_step": 581178, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0472869873046875, "global_step": 581179, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.008782148361206, "global_step": 581180, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.060267925262451, "global_step": 581181, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0415875911712646, "global_step": 581182, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.079002857208252, "global_step": 581183, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.057250738143921, "global_step": 581184, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.093350410461426, "global_step": 581185, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9961034059524536, "global_step": 581186, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.043226957321167, "global_step": 581187, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.92210054397583, "global_step": 581188, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9727373123168945, "global_step": 581189, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.084764003753662, "global_step": 581190, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0662143230438232, "global_step": 581191, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.033013105392456, "global_step": 581192, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0757532119750977, "global_step": 581193, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.044203996658325, "global_step": 581194, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1033802032470703, "global_step": 581195, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.051501512527466, "global_step": 581196, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0112075805664062, "global_step": 581197, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9345693588256836, "global_step": 581198, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9641332626342773, "global_step": 581199, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0387234687805176, "global_step": 581200, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0029714107513428, "global_step": 581201, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0119168758392334, "global_step": 581202, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9815635681152344, "global_step": 581203, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9138169288635254, "global_step": 581204, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0434439182281494, "global_step": 581205, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.010589599609375, "global_step": 581206, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0676167011260986, "global_step": 581207, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.115032434463501, "global_step": 581208, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9557900428771973, "global_step": 581209, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0086112022399902, "global_step": 581210, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1091935634613037, "global_step": 581211, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.8857754468917847, "global_step": 581212, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0010790824890137, "global_step": 581213, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.029203414916992, "global_step": 581214, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.020599126815796, "global_step": 581215, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.054670572280884, "global_step": 581216, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.111194610595703, "global_step": 581217, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9505658149719238, "global_step": 581218, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9690383672714233, "global_step": 581219, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.044877767562866, "global_step": 581220, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0127017498016357, "global_step": 581221, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.057121515274048, "global_step": 581222, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.036731719970703, "global_step": 581223, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.024064064025879, "global_step": 581224, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9471644163131714, "global_step": 581225, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9650112390518188, "global_step": 581226, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0684709548950195, "global_step": 581227, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.039552927017212, "global_step": 581228, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.959252119064331, "global_step": 581229, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.087538957595825, "global_step": 581230, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9837621450424194, "global_step": 581231, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1108062267303467, "global_step": 581232, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9816758632659912, "global_step": 581233, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.073759078979492, "global_step": 581234, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0005173683166504, "global_step": 581235, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.989990234375, "global_step": 581236, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9948079586029053, "global_step": 581237, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0927388668060303, "global_step": 581238, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.030277729034424, "global_step": 581239, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0791842937469482, "global_step": 581240, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.065117597579956, "global_step": 581241, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9454289674758911, "global_step": 581242, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0458602905273438, "global_step": 581243, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.983016848564148, "global_step": 581244, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.065830707550049, "global_step": 581245, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.008234977722168, "global_step": 581246, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.125659942626953, "global_step": 581247, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.073167085647583, "global_step": 581248, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0806591510772705, "global_step": 581249, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.018440008163452, "global_step": 581250, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.070601224899292, "global_step": 581251, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.011788845062256, "global_step": 581252, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.055417776107788, "global_step": 581253, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.041080951690674, "global_step": 581254, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.8907986879348755, "global_step": 581255, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.084765672683716, "global_step": 581256, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9734394550323486, "global_step": 581257, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0512077808380127, "global_step": 581258, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0690956115722656, "global_step": 581259, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9972058534622192, "global_step": 581260, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.058626174926758, "global_step": 581261, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.039304733276367, "global_step": 581262, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9786267280578613, "global_step": 581263, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.066634178161621, "global_step": 581264, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0678598880767822, "global_step": 581265, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.999197244644165, "global_step": 581266, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0601539611816406, "global_step": 581267, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.080446481704712, "global_step": 581268, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9504393339157104, "global_step": 581269, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9048012495040894, "global_step": 581270, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.8857227563858032, "global_step": 581271, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.106172561645508, "global_step": 581272, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0188393592834473, "global_step": 581273, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.08473801612854, "global_step": 581274, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9579722881317139, "global_step": 581275, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.093327045440674, "global_step": 581276, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0437018871307373, "global_step": 581277, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0130953788757324, "global_step": 581278, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.072305679321289, "global_step": 581279, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9978611469268799, "global_step": 581280, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.07590651512146, "global_step": 581281, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0614356994628906, "global_step": 581282, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9030425548553467, "global_step": 581283, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0106945037841797, "global_step": 581284, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0329928398132324, "global_step": 581285, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.029682159423828, "global_step": 581286, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.105604410171509, "global_step": 581287, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.013796329498291, "global_step": 581288, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0209579467773438, "global_step": 581289, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.031826972961426, "global_step": 581290, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9740169048309326, "global_step": 581291, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0512614250183105, "global_step": 581292, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9981839656829834, "global_step": 581293, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9701710939407349, "global_step": 581294, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0908336639404297, "global_step": 581295, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.038370370864868, "global_step": 581296, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.017975330352783, "global_step": 581297, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0101799964904785, "global_step": 581298, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.007889986038208, "global_step": 581299, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0095150470733643, "global_step": 581300, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0976126194000244, "global_step": 581301, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0140199661254883, "global_step": 581302, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.048778772354126, "global_step": 581303, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.038444757461548, "global_step": 581304, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.083017587661743, "global_step": 581305, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0687146186828613, "global_step": 581306, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.022995710372925, "global_step": 581307, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0446455478668213, "global_step": 581308, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.051852226257324, "global_step": 581309, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.046721935272217, "global_step": 581310, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9634361267089844, "global_step": 581311, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9963877201080322, "global_step": 581312, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.028841257095337, "global_step": 581313, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.081240177154541, "global_step": 581314, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.190411329269409, "global_step": 581315, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0064940452575684, "global_step": 581316, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9722657203674316, "global_step": 581317, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0148065090179443, "global_step": 581318, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0695672035217285, "global_step": 581319, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.03281569480896, "global_step": 581320, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0104174613952637, "global_step": 581321, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0482354164123535, "global_step": 581322, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0934505462646484, "global_step": 581323, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.931410312652588, "global_step": 581324, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0047519207000732, "global_step": 581325, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.054826021194458, "global_step": 581326, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.043830394744873, "global_step": 581327, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0013675689697266, "global_step": 581328, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.020777463912964, "global_step": 581329, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9326454401016235, "global_step": 581330, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0947985649108887, "global_step": 581331, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9969552755355835, "global_step": 581332, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0119307041168213, "global_step": 581333, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.982845664024353, "global_step": 581334, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0221166610717773, "global_step": 581335, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0621628761291504, "global_step": 581336, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0141658782958984, "global_step": 581337, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0393624305725098, "global_step": 581338, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.995220422744751, "global_step": 581339, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.955735206604004, "global_step": 581340, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0717926025390625, "global_step": 581341, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9697262048721313, "global_step": 581342, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1381959915161133, "global_step": 581343, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9949541091918945, "global_step": 581344, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9901973009109497, "global_step": 581345, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0087506771087646, "global_step": 581346, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0488600730895996, "global_step": 581347, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0796971321105957, "global_step": 581348, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9867525100708008, "global_step": 581349, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9781477451324463, "global_step": 581350, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9758814573287964, "global_step": 581351, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.075165271759033, "global_step": 581352, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9933359622955322, "global_step": 581353, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1703007221221924, "global_step": 581354, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0473554134368896, "global_step": 581355, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9584773778915405, "global_step": 581356, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9702188968658447, "global_step": 581357, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9852608442306519, "global_step": 581358, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.069800853729248, "global_step": 581359, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9313709735870361, "global_step": 581360, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9964163303375244, "global_step": 581361, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.996993064880371, "global_step": 581362, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.044316291809082, "global_step": 581363, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9234098196029663, "global_step": 581364, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0466535091400146, "global_step": 581365, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0282928943634033, "global_step": 581366, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0298449993133545, "global_step": 581367, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.021515130996704, "global_step": 581368, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.99599027633667, "global_step": 581369, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0326216220855713, "global_step": 581370, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.977418303489685, "global_step": 581371, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.095890760421753, "global_step": 581372, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0572006702423096, "global_step": 581373, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0501503944396973, "global_step": 581374, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9182531833648682, "global_step": 581375, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0036981105804443, "global_step": 581376, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0711019039154053, "global_step": 581377, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0125350952148438, "global_step": 581378, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.945035457611084, "global_step": 581379, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0005266666412354, "global_step": 581380, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0347836017608643, "global_step": 581381, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9510157108306885, "global_step": 581382, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0610175132751465, "global_step": 581383, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0451107025146484, "global_step": 581384, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0268681049346924, "global_step": 581385, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9653205871582031, "global_step": 581386, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0835342407226562, "global_step": 581387, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0284032821655273, "global_step": 581388, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.96596360206604, "global_step": 581389, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.090238094329834, "global_step": 581390, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9673161506652832, "global_step": 581391, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.075012683868408, "global_step": 581392, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0377037525177, "global_step": 581393, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9530560970306396, "global_step": 581394, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0342161655426025, "global_step": 581395, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.000663995742798, "global_step": 581396, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9862091541290283, "global_step": 581397, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0835540294647217, "global_step": 581398, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9715288877487183, "global_step": 581399, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0526764392852783, "global_step": 581400, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0410773754119873, "global_step": 581401, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0599799156188965, "global_step": 581402, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0997281074523926, "global_step": 581403, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.027712345123291, "global_step": 581404, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.063047170639038, "global_step": 581405, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0170788764953613, "global_step": 581406, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.997693419456482, "global_step": 581407, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0180485248565674, "global_step": 581408, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9728354215621948, "global_step": 581409, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0849711894989014, "global_step": 581410, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1471757888793945, "global_step": 581411, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0377020835876465, "global_step": 581412, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.026768684387207, "global_step": 581413, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9984982013702393, "global_step": 581414, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0449626445770264, "global_step": 581415, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0240044593811035, "global_step": 581416, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.049985408782959, "global_step": 581417, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.10829496383667, "global_step": 581418, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9990485906600952, "global_step": 581419, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0646018981933594, "global_step": 581420, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9949400424957275, "global_step": 581421, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0803022384643555, "global_step": 581422, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0041778087615967, "global_step": 581423, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0265281200408936, "global_step": 581424, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.040801763534546, "global_step": 581425, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9622501134872437, "global_step": 581426, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.924354910850525, "global_step": 581427, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0226173400878906, "global_step": 581428, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.901491641998291, "global_step": 581429, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9848588705062866, "global_step": 581430, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.069525957107544, "global_step": 581431, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.027784585952759, "global_step": 581432, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0635251998901367, "global_step": 581433, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.089066743850708, "global_step": 581434, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0202324390411377, "global_step": 581435, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0276222229003906, "global_step": 581436, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0263800621032715, "global_step": 581437, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.967154860496521, "global_step": 581438, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.039595127105713, "global_step": 581439, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0221521854400635, "global_step": 581440, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.021639108657837, "global_step": 581441, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.965528964996338, "global_step": 581442, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.963815689086914, "global_step": 581443, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.030902147293091, "global_step": 581444, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9771108627319336, "global_step": 581445, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.963700771331787, "global_step": 581446, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9809595346450806, "global_step": 581447, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.034669876098633, "global_step": 581448, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0429327487945557, "global_step": 581449, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9689134359359741, "global_step": 581450, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.073472499847412, "global_step": 581451, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.038405418395996, "global_step": 581452, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1072804927825928, "global_step": 581453, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9776374101638794, "global_step": 581454, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.001922130584717, "global_step": 581455, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.087693929672241, "global_step": 581456, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9754854440689087, "global_step": 581457, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0543229579925537, "global_step": 581458, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0629684925079346, "global_step": 581459, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0473737716674805, "global_step": 581460, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0113141536712646, "global_step": 581461, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0019147396087646, "global_step": 581462, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0348238945007324, "global_step": 581463, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0112552642822266, "global_step": 581464, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0107688903808594, "global_step": 581465, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0738260746002197, "global_step": 581466, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.059438705444336, "global_step": 581467, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0095555782318115, "global_step": 581468, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0342042446136475, "global_step": 581469, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.030078411102295, "global_step": 581470, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9352138042449951, "global_step": 581471, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.116973876953125, "global_step": 581472, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.963948369026184, "global_step": 581473, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0857605934143066, "global_step": 581474, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9588162899017334, "global_step": 581475, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.145746946334839, "global_step": 581476, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.018850564956665, "global_step": 581477, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9806643724441528, "global_step": 581478, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0376930236816406, "global_step": 581479, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.029189109802246, "global_step": 581480, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.041306972503662, "global_step": 581481, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0398080348968506, "global_step": 581482, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9384154081344604, "global_step": 581483, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0799803733825684, "global_step": 581484, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.007700204849243, "global_step": 581485, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.051947832107544, "global_step": 581486, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.044408082962036, "global_step": 581487, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9708702564239502, "global_step": 581488, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.076547861099243, "global_step": 581489, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.018527030944824, "global_step": 581490, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0824978351593018, "global_step": 581491, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9933676719665527, "global_step": 581492, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9721274375915527, "global_step": 581493, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0535736083984375, "global_step": 581494, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0248844623565674, "global_step": 581495, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.038797616958618, "global_step": 581496, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.078819513320923, "global_step": 581497, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0336711406707764, "global_step": 581498, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.044389486312866, "global_step": 581499, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0323486328125, "global_step": 581500, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9887641668319702, "global_step": 581501, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0933313369750977, "global_step": 581502, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0389175415039062, "global_step": 581503, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0014455318450928, "global_step": 581504, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.017838954925537, "global_step": 581505, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.998725414276123, "global_step": 581506, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.03415584564209, "global_step": 581507, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.1282801628112793, "global_step": 581508, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0000879764556885, "global_step": 581509, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0143930912017822, "global_step": 581510, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0129148960113525, "global_step": 581511, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.035783290863037, "global_step": 581512, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0792078971862793, "global_step": 581513, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9920049905776978, "global_step": 581514, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0828003883361816, "global_step": 581515, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.046611785888672, "global_step": 581516, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.987075924873352, "global_step": 581517, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.047017812728882, "global_step": 581518, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0512523651123047, "global_step": 581519, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0264744758605957, "global_step": 581520, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0089833736419678, "global_step": 581521, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0799777507781982, "global_step": 581522, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9967451095581055, "global_step": 581523, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0569210052490234, "global_step": 581524, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.046274185180664, "global_step": 581525, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9760879278182983, "global_step": 581526, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.103694200515747, "global_step": 581527, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0981197357177734, "global_step": 581528, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0394625663757324, "global_step": 581529, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.997104287147522, "global_step": 581530, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.0227739810943604, "global_step": 581531, "epoch": 949, "lr": 5e-05}
{"train_loss": 2.020622730255127, "global_step": 581532, "epoch": 949, "lr": 5e-05}
{"train_loss": 1.9460171461105347, "global_step": 581533, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9298644065856934, "global_step": 581534, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0265347957611084, "global_step": 581535, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9560134410858154, "global_step": 581536, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9686400890350342, "global_step": 581537, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9634579420089722, "global_step": 581538, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0651533603668213, "global_step": 581539, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.059556722640991, "global_step": 581540, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9684786796569824, "global_step": 581541, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0221567153930664, "global_step": 581542, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0066142082214355, "global_step": 581543, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.052382469177246, "global_step": 581544, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.036482334136963, "global_step": 581545, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9914823770523071, "global_step": 581546, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.033989191055298, "global_step": 581547, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0172953605651855, "global_step": 581548, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9771804809570312, "global_step": 581549, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.921313762664795, "global_step": 581550, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.967415690422058, "global_step": 581551, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9673740863800049, "global_step": 581552, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9885112047195435, "global_step": 581553, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.046994686126709, "global_step": 581554, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9771392345428467, "global_step": 581555, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.042518138885498, "global_step": 581556, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0251917839050293, "global_step": 581557, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9781705141067505, "global_step": 581558, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9883038997650146, "global_step": 581559, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9512895345687866, "global_step": 581560, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9629204273223877, "global_step": 581561, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0579371452331543, "global_step": 581562, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0140492916107178, "global_step": 581563, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9960455894470215, "global_step": 581564, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9644911289215088, "global_step": 581565, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0911078453063965, "global_step": 581566, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9136923551559448, "global_step": 581567, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9553097486495972, "global_step": 581568, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.996375322341919, "global_step": 581569, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9864073991775513, "global_step": 581570, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0443379878997803, "global_step": 581571, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.944168210029602, "global_step": 581572, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0448873043060303, "global_step": 581573, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9934223890304565, "global_step": 581574, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9922860860824585, "global_step": 581575, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9768537282943726, "global_step": 581576, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0711984634399414, "global_step": 581577, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9994091987609863, "global_step": 581578, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0078701972961426, "global_step": 581579, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.040673017501831, "global_step": 581580, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9945114850997925, "global_step": 581581, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9413257837295532, "global_step": 581582, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.97050142288208, "global_step": 581583, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9581077098846436, "global_step": 581584, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9941672086715698, "global_step": 581585, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9851183891296387, "global_step": 581586, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.048877239227295, "global_step": 581587, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0092148780822754, "global_step": 581588, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9280561208724976, "global_step": 581589, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9317381381988525, "global_step": 581590, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0454931259155273, "global_step": 581591, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9623934030532837, "global_step": 581592, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0304412841796875, "global_step": 581593, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.007704973220825, "global_step": 581594, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9642294645309448, "global_step": 581595, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.039763927459717, "global_step": 581596, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0427403450012207, "global_step": 581597, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.040790557861328, "global_step": 581598, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.018242120742798, "global_step": 581599, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0444016456604004, "global_step": 581600, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.984627366065979, "global_step": 581601, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0511653423309326, "global_step": 581602, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0966601371765137, "global_step": 581603, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0631251335144043, "global_step": 581604, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.018737316131592, "global_step": 581605, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1467480659484863, "global_step": 581606, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0452330112457275, "global_step": 581607, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9106343984603882, "global_step": 581608, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0421664714813232, "global_step": 581609, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0192747116088867, "global_step": 581610, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9445387125015259, "global_step": 581611, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9106454849243164, "global_step": 581612, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0199995040893555, "global_step": 581613, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.058422327041626, "global_step": 581614, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1038269996643066, "global_step": 581615, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.986112356185913, "global_step": 581616, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0227034091949463, "global_step": 581617, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0076897144317627, "global_step": 581618, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0132784843444824, "global_step": 581619, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.97861909866333, "global_step": 581620, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9385550022125244, "global_step": 581621, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.084014654159546, "global_step": 581622, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0194199085235596, "global_step": 581623, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0231740474700928, "global_step": 581624, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.003958225250244, "global_step": 581625, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.038632869720459, "global_step": 581626, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9801028966903687, "global_step": 581627, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9848806858062744, "global_step": 581628, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9890151023864746, "global_step": 581629, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9307584762573242, "global_step": 581630, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9966278076171875, "global_step": 581631, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.033013105392456, "global_step": 581632, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0247130393981934, "global_step": 581633, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9947863817214966, "global_step": 581634, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0374720096588135, "global_step": 581635, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0678489208221436, "global_step": 581636, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.059903621673584, "global_step": 581637, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0249273777008057, "global_step": 581638, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0102789402008057, "global_step": 581639, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.031771659851074, "global_step": 581640, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0342466831207275, "global_step": 581641, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9211984872817993, "global_step": 581642, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9888004064559937, "global_step": 581643, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9948763847351074, "global_step": 581644, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.983638048171997, "global_step": 581645, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.062080144882202, "global_step": 581646, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9241573810577393, "global_step": 581647, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.062319755554199, "global_step": 581648, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.969552993774414, "global_step": 581649, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0486838817596436, "global_step": 581650, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9554829597473145, "global_step": 581651, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.058039665222168, "global_step": 581652, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.982412576675415, "global_step": 581653, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.05474591255188, "global_step": 581654, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.001680850982666, "global_step": 581655, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0020556449890137, "global_step": 581656, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9559729099273682, "global_step": 581657, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0262115001678467, "global_step": 581658, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0312082767486572, "global_step": 581659, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0435736179351807, "global_step": 581660, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.973673701286316, "global_step": 581661, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.042595863342285, "global_step": 581662, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9595129489898682, "global_step": 581663, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.059443235397339, "global_step": 581664, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.987874984741211, "global_step": 581665, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0099620819091797, "global_step": 581666, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9608019590377808, "global_step": 581667, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0575015544891357, "global_step": 581668, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0120129585266113, "global_step": 581669, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0021908283233643, "global_step": 581670, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9253497123718262, "global_step": 581671, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.020885944366455, "global_step": 581672, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.961759090423584, "global_step": 581673, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.025134563446045, "global_step": 581674, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.032073497772217, "global_step": 581675, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.936392068862915, "global_step": 581676, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9814980030059814, "global_step": 581677, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.095672369003296, "global_step": 581678, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0644755363464355, "global_step": 581679, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9626309871673584, "global_step": 581680, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0334482192993164, "global_step": 581681, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.137868881225586, "global_step": 581682, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0826616287231445, "global_step": 581683, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.097280979156494, "global_step": 581684, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0325679779052734, "global_step": 581685, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9590356349945068, "global_step": 581686, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0630390644073486, "global_step": 581687, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9945275783538818, "global_step": 581688, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9291393756866455, "global_step": 581689, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0249710083007812, "global_step": 581690, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.065491199493408, "global_step": 581691, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0442285537719727, "global_step": 581692, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9730757474899292, "global_step": 581693, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9885790348052979, "global_step": 581694, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.068251609802246, "global_step": 581695, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9849611520767212, "global_step": 581696, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.985891342163086, "global_step": 581697, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0425901412963867, "global_step": 581698, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0961127281188965, "global_step": 581699, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.997011423110962, "global_step": 581700, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9936455488204956, "global_step": 581701, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9949790239334106, "global_step": 581702, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0037167072296143, "global_step": 581703, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.005601644515991, "global_step": 581704, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0502240657806396, "global_step": 581705, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.933681845664978, "global_step": 581706, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0151915550231934, "global_step": 581707, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0578300952911377, "global_step": 581708, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0021400451660156, "global_step": 581709, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.029503345489502, "global_step": 581710, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9860771894454956, "global_step": 581711, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.026482105255127, "global_step": 581712, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.08687162399292, "global_step": 581713, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9898178577423096, "global_step": 581714, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9702479839324951, "global_step": 581715, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0547120571136475, "global_step": 581716, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.948186993598938, "global_step": 581717, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.055379629135132, "global_step": 581718, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.970497727394104, "global_step": 581719, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0321741104125977, "global_step": 581720, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9976698160171509, "global_step": 581721, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1164233684539795, "global_step": 581722, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0426993370056152, "global_step": 581723, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9887590408325195, "global_step": 581724, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0559260845184326, "global_step": 581725, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0160343647003174, "global_step": 581726, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.005619525909424, "global_step": 581727, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0083250999450684, "global_step": 581728, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9616700410842896, "global_step": 581729, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.054161548614502, "global_step": 581730, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0345864295959473, "global_step": 581731, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9828468561172485, "global_step": 581732, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9802478551864624, "global_step": 581733, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0767946243286133, "global_step": 581734, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.025278091430664, "global_step": 581735, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.986661434173584, "global_step": 581736, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.000537633895874, "global_step": 581737, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9923322200775146, "global_step": 581738, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.036972761154175, "global_step": 581739, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9727011919021606, "global_step": 581740, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.049804449081421, "global_step": 581741, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.026773452758789, "global_step": 581742, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.092783212661743, "global_step": 581743, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0891990661621094, "global_step": 581744, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.072547435760498, "global_step": 581745, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0614092350006104, "global_step": 581746, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.089246988296509, "global_step": 581747, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0530707836151123, "global_step": 581748, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.980612874031067, "global_step": 581749, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.053252696990967, "global_step": 581750, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9984467029571533, "global_step": 581751, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0922298431396484, "global_step": 581752, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.081238269805908, "global_step": 581753, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.059417724609375, "global_step": 581754, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9770082235336304, "global_step": 581755, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0322911739349365, "global_step": 581756, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0461878776550293, "global_step": 581757, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.053148031234741, "global_step": 581758, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0375094413757324, "global_step": 581759, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.122427225112915, "global_step": 581760, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0376036167144775, "global_step": 581761, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.984370231628418, "global_step": 581762, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.004197120666504, "global_step": 581763, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9654954671859741, "global_step": 581764, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9863862991333008, "global_step": 581765, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0097055435180664, "global_step": 581766, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.056884288787842, "global_step": 581767, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9970827102661133, "global_step": 581768, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0487020015716553, "global_step": 581769, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.001394510269165, "global_step": 581770, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0571820735931396, "global_step": 581771, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9348888397216797, "global_step": 581772, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9672306776046753, "global_step": 581773, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0557901859283447, "global_step": 581774, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9824481010437012, "global_step": 581775, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0545051097869873, "global_step": 581776, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0933055877685547, "global_step": 581777, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9360071420669556, "global_step": 581778, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0168838500976562, "global_step": 581779, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0578482151031494, "global_step": 581780, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.06341290473938, "global_step": 581781, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0307440757751465, "global_step": 581782, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.006237745285034, "global_step": 581783, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.8999810218811035, "global_step": 581784, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0247769355773926, "global_step": 581785, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.037569761276245, "global_step": 581786, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.042847156524658, "global_step": 581787, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.967430830001831, "global_step": 581788, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0121190547943115, "global_step": 581789, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.027334451675415, "global_step": 581790, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0440986156463623, "global_step": 581791, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9906601905822754, "global_step": 581792, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0042073726654053, "global_step": 581793, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1218762397766113, "global_step": 581794, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9735208749771118, "global_step": 581795, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0075130462646484, "global_step": 581796, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0828335285186768, "global_step": 581797, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.029041051864624, "global_step": 581798, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.958203673362732, "global_step": 581799, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0725104808807373, "global_step": 581800, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0061256885528564, "global_step": 581801, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0428967475891113, "global_step": 581802, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9814327955245972, "global_step": 581803, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.926033854484558, "global_step": 581804, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.952650785446167, "global_step": 581805, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9544267654418945, "global_step": 581806, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.927083134651184, "global_step": 581807, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.980229377746582, "global_step": 581808, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.037769317626953, "global_step": 581809, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.941546082496643, "global_step": 581810, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.058985710144043, "global_step": 581811, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.006021738052368, "global_step": 581812, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.967732310295105, "global_step": 581813, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0259666442871094, "global_step": 581814, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.031766653060913, "global_step": 581815, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.953671932220459, "global_step": 581816, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.077704668045044, "global_step": 581817, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.971234917640686, "global_step": 581818, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0457944869995117, "global_step": 581819, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0136449337005615, "global_step": 581820, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.029500961303711, "global_step": 581821, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0499565601348877, "global_step": 581822, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.119487762451172, "global_step": 581823, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.01240611076355, "global_step": 581824, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0472946166992188, "global_step": 581825, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1139230728149414, "global_step": 581826, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0958926677703857, "global_step": 581827, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.971961498260498, "global_step": 581828, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.019793748855591, "global_step": 581829, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0125820636749268, "global_step": 581830, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.03594970703125, "global_step": 581831, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9887744188308716, "global_step": 581832, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.987702488899231, "global_step": 581833, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.087266206741333, "global_step": 581834, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.966287612915039, "global_step": 581835, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0075266361236572, "global_step": 581836, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.103104829788208, "global_step": 581837, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0123045444488525, "global_step": 581838, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.01645565032959, "global_step": 581839, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0145959854125977, "global_step": 581840, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9727039337158203, "global_step": 581841, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9496593475341797, "global_step": 581842, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.071094274520874, "global_step": 581843, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.971635341644287, "global_step": 581844, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.949370265007019, "global_step": 581845, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0141429901123047, "global_step": 581846, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.018953800201416, "global_step": 581847, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.064584255218506, "global_step": 581848, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.140425443649292, "global_step": 581849, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9536808729171753, "global_step": 581850, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.990883231163025, "global_step": 581851, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.020033359527588, "global_step": 581852, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0364863872528076, "global_step": 581853, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9460705518722534, "global_step": 581854, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0600481033325195, "global_step": 581855, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0311880111694336, "global_step": 581856, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0260143280029297, "global_step": 581857, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.956363320350647, "global_step": 581858, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9376320838928223, "global_step": 581859, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9521750211715698, "global_step": 581860, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9667131900787354, "global_step": 581861, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0141351222991943, "global_step": 581862, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9991141557693481, "global_step": 581863, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.8878931999206543, "global_step": 581864, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9828667640686035, "global_step": 581865, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1062405109405518, "global_step": 581866, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9772396087646484, "global_step": 581867, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0863349437713623, "global_step": 581868, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9607030153274536, "global_step": 581869, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9831218719482422, "global_step": 581870, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0315728187561035, "global_step": 581871, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0197131633758545, "global_step": 581872, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0141401290893555, "global_step": 581873, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0455565452575684, "global_step": 581874, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0463316440582275, "global_step": 581875, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0185158252716064, "global_step": 581876, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.063610792160034, "global_step": 581877, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0123870372772217, "global_step": 581878, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0169005393981934, "global_step": 581879, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0321390628814697, "global_step": 581880, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9932029247283936, "global_step": 581881, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0619163513183594, "global_step": 581882, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.005357265472412, "global_step": 581883, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9946410655975342, "global_step": 581884, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.979759931564331, "global_step": 581885, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0632033348083496, "global_step": 581886, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.008791446685791, "global_step": 581887, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.8752801418304443, "global_step": 581888, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0436713695526123, "global_step": 581889, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9467204809188843, "global_step": 581890, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.083277702331543, "global_step": 581891, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.008669853210449, "global_step": 581892, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0515077114105225, "global_step": 581893, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.037376880645752, "global_step": 581894, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.048708438873291, "global_step": 581895, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.026367425918579, "global_step": 581896, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0156352519989014, "global_step": 581897, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0634169578552246, "global_step": 581898, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9195377826690674, "global_step": 581899, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0652828216552734, "global_step": 581900, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9829362630844116, "global_step": 581901, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.024940252304077, "global_step": 581902, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0841829776763916, "global_step": 581903, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9993211030960083, "global_step": 581904, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.000072479248047, "global_step": 581905, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9457234144210815, "global_step": 581906, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0389821529388428, "global_step": 581907, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.031494140625, "global_step": 581908, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9703831672668457, "global_step": 581909, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.002742290496826, "global_step": 581910, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9970026016235352, "global_step": 581911, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.114445447921753, "global_step": 581912, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1610612869262695, "global_step": 581913, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9805344343185425, "global_step": 581914, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0324437618255615, "global_step": 581915, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9883736371994019, "global_step": 581916, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9808930158615112, "global_step": 581917, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0350534915924072, "global_step": 581918, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0406060218811035, "global_step": 581919, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.028704881668091, "global_step": 581920, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.047914981842041, "global_step": 581921, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.924489140510559, "global_step": 581922, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9971709251403809, "global_step": 581923, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9589487314224243, "global_step": 581924, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9964487552642822, "global_step": 581925, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.981420874595642, "global_step": 581926, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9866801500320435, "global_step": 581927, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9901295900344849, "global_step": 581928, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9633691310882568, "global_step": 581929, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.041006326675415, "global_step": 581930, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0299673080444336, "global_step": 581931, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0506012439727783, "global_step": 581932, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.036968946456909, "global_step": 581933, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9929611682891846, "global_step": 581934, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9550371170043945, "global_step": 581935, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0255062580108643, "global_step": 581936, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0017099380493164, "global_step": 581937, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9797698259353638, "global_step": 581938, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9989396333694458, "global_step": 581939, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0328218936920166, "global_step": 581940, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0015926361083984, "global_step": 581941, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9629603624343872, "global_step": 581942, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9407273530960083, "global_step": 581943, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.060690402984619, "global_step": 581944, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0155622959136963, "global_step": 581945, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9995665550231934, "global_step": 581946, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0268118381500244, "global_step": 581947, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0335047245025635, "global_step": 581948, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0110585689544678, "global_step": 581949, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9823287725448608, "global_step": 581950, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0539116859436035, "global_step": 581951, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.948358416557312, "global_step": 581952, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.063849687576294, "global_step": 581953, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.07004976272583, "global_step": 581954, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9574772119522095, "global_step": 581955, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1238701343536377, "global_step": 581956, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0103538036346436, "global_step": 581957, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9584236145019531, "global_step": 581958, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0589702129364014, "global_step": 581959, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9914470911026, "global_step": 581960, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0486643314361572, "global_step": 581961, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.010936975479126, "global_step": 581962, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9920977354049683, "global_step": 581963, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.979621171951294, "global_step": 581964, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.083362102508545, "global_step": 581965, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9761377573013306, "global_step": 581966, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.038477659225464, "global_step": 581967, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.075298309326172, "global_step": 581968, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9578319787979126, "global_step": 581969, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9760663509368896, "global_step": 581970, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1153481006622314, "global_step": 581971, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.008629083633423, "global_step": 581972, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0863747596740723, "global_step": 581973, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9933396577835083, "global_step": 581974, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1309118270874023, "global_step": 581975, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0727944374084473, "global_step": 581976, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9646410942077637, "global_step": 581977, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.054722785949707, "global_step": 581978, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9966223239898682, "global_step": 581979, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0526461601257324, "global_step": 581980, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0208113193511963, "global_step": 581981, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.002302885055542, "global_step": 581982, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.032315731048584, "global_step": 581983, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0097644329071045, "global_step": 581984, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9819157123565674, "global_step": 581985, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.034207344055176, "global_step": 581986, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.93167245388031, "global_step": 581987, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0242233276367188, "global_step": 581988, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0803449153900146, "global_step": 581989, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.089556932449341, "global_step": 581990, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9849848747253418, "global_step": 581991, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0477685928344727, "global_step": 581992, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.01318359375, "global_step": 581993, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.098389148712158, "global_step": 581994, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0745105743408203, "global_step": 581995, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.030146360397339, "global_step": 581996, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.050734519958496, "global_step": 581997, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0760657787323, "global_step": 581998, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0136728286743164, "global_step": 581999, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.066711902618408, "global_step": 582000, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.127918243408203, "global_step": 582001, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0471551418304443, "global_step": 582002, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.126235008239746, "global_step": 582003, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.00622820854187, "global_step": 582004, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.989648699760437, "global_step": 582005, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0101587772369385, "global_step": 582006, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.032898426055908, "global_step": 582007, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9211022853851318, "global_step": 582008, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.009467601776123, "global_step": 582009, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.044728994369507, "global_step": 582010, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0659666061401367, "global_step": 582011, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0221025943756104, "global_step": 582012, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9010180234909058, "global_step": 582013, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.06976056098938, "global_step": 582014, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0075411796569824, "global_step": 582015, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.8888732194900513, "global_step": 582016, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0497443675994873, "global_step": 582017, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0890142917633057, "global_step": 582018, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9432477951049805, "global_step": 582019, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0708658695220947, "global_step": 582020, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9241315126419067, "global_step": 582021, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0181987285614014, "global_step": 582022, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0238864421844482, "global_step": 582023, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.022696018218994, "global_step": 582024, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0783486366271973, "global_step": 582025, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.021380662918091, "global_step": 582026, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0444302558898926, "global_step": 582027, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0353519916534424, "global_step": 582028, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0077269077301025, "global_step": 582029, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9644800424575806, "global_step": 582030, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0268568992614746, "global_step": 582031, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9635133743286133, "global_step": 582032, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.113086462020874, "global_step": 582033, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0208070278167725, "global_step": 582034, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.098961114883423, "global_step": 582035, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.002384662628174, "global_step": 582036, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.024113416671753, "global_step": 582037, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.08034086227417, "global_step": 582038, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9993044137954712, "global_step": 582039, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.099191665649414, "global_step": 582040, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9628719091415405, "global_step": 582041, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0304365158081055, "global_step": 582042, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.036705255508423, "global_step": 582043, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.048920154571533, "global_step": 582044, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9537746906280518, "global_step": 582045, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.089040756225586, "global_step": 582046, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0358633995056152, "global_step": 582047, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0809006690979004, "global_step": 582048, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.045552968978882, "global_step": 582049, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1326780319213867, "global_step": 582050, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9796812534332275, "global_step": 582051, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9346476793289185, "global_step": 582052, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1043877601623535, "global_step": 582053, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0496790409088135, "global_step": 582054, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9625383615493774, "global_step": 582055, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.030189275741577, "global_step": 582056, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0271055698394775, "global_step": 582057, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9385817050933838, "global_step": 582058, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0034141540527344, "global_step": 582059, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9297088384628296, "global_step": 582060, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9621738195419312, "global_step": 582061, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1198906898498535, "global_step": 582062, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.952500581741333, "global_step": 582063, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9709700345993042, "global_step": 582064, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9449198246002197, "global_step": 582065, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.031802177429199, "global_step": 582066, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0546133518218994, "global_step": 582067, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.020756721496582, "global_step": 582068, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.051328420639038, "global_step": 582069, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.026596784591675, "global_step": 582070, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.029385805130005, "global_step": 582071, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0519649982452393, "global_step": 582072, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9089248180389404, "global_step": 582073, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9599213600158691, "global_step": 582074, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9911494255065918, "global_step": 582075, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0900073051452637, "global_step": 582076, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.004279375076294, "global_step": 582077, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0241782665252686, "global_step": 582078, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9688633680343628, "global_step": 582079, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0086355209350586, "global_step": 582080, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.940204381942749, "global_step": 582081, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9925286769866943, "global_step": 582082, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.082223653793335, "global_step": 582083, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0271708965301514, "global_step": 582084, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9753953218460083, "global_step": 582085, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9775352478027344, "global_step": 582086, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0424890518188477, "global_step": 582087, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.032705307006836, "global_step": 582088, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0032105445861816, "global_step": 582089, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9854998588562012, "global_step": 582090, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0485334396362305, "global_step": 582091, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9872914552688599, "global_step": 582092, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.037203073501587, "global_step": 582093, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9780288934707642, "global_step": 582094, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9568426609039307, "global_step": 582095, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.975677490234375, "global_step": 582096, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.044800281524658, "global_step": 582097, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9593561887741089, "global_step": 582098, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9621589183807373, "global_step": 582099, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9091880321502686, "global_step": 582100, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.064181089401245, "global_step": 582101, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1161415576934814, "global_step": 582102, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9923690557479858, "global_step": 582103, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.041203498840332, "global_step": 582104, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.042107582092285, "global_step": 582105, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.992202639579773, "global_step": 582106, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0668246746063232, "global_step": 582107, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9620903730392456, "global_step": 582108, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9763294458389282, "global_step": 582109, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9718849658966064, "global_step": 582110, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9837541580200195, "global_step": 582111, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.081458568572998, "global_step": 582112, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0366857051849365, "global_step": 582113, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.067671537399292, "global_step": 582114, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.059370517730713, "global_step": 582115, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9595040082931519, "global_step": 582116, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0360758304595947, "global_step": 582117, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0335865020751953, "global_step": 582118, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9113842248916626, "global_step": 582119, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0213465690612793, "global_step": 582120, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0102505683898926, "global_step": 582121, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9023520946502686, "global_step": 582122, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0117528438568115, "global_step": 582123, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0838472843170166, "global_step": 582124, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9694359302520752, "global_step": 582125, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.031832695007324, "global_step": 582126, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.020808458328247, "global_step": 582127, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0697927474975586, "global_step": 582128, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0296061038970947, "global_step": 582129, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9056986570358276, "global_step": 582130, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.09000563621521, "global_step": 582131, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9779231548309326, "global_step": 582132, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0976204872131348, "global_step": 582133, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0066962242126465, "global_step": 582134, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9365922212600708, "global_step": 582135, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9056370258331299, "global_step": 582136, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0062713623046875, "global_step": 582137, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0890979766845703, "global_step": 582138, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0044972896575928, "global_step": 582139, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.019371271133423, "global_step": 582140, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.045614004135132, "global_step": 582141, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0815908908843994, "global_step": 582142, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0809075832366943, "global_step": 582143, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.022162437438965, "global_step": 582144, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.072434902191162, "global_step": 582145, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.936170220375061, "global_step": 582146, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9187880754470825, "global_step": 582147, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.018359422683716, "global_step": 582148, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.957082986831665, "global_step": 582149, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0098674297332764, "global_step": 582150, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0228524208068848, "global_step": 582151, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.995806097984314, "global_step": 582152, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.996675729751587, "global_step": 582153, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9255495071411133, "global_step": 582154, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.078338861465454, "global_step": 582155, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.038588762283325, "global_step": 582156, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0348639488220215, "global_step": 582157, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.042050361633301, "global_step": 582158, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9936186075210571, "global_step": 582159, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0656003952026367, "global_step": 582160, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.038942575454712, "global_step": 582161, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.047377586364746, "global_step": 582162, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.033979654312134, "global_step": 582163, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.95566725730896, "global_step": 582164, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.044700860977173, "global_step": 582165, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0689587593078613, "global_step": 582166, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0250015258789062, "global_step": 582167, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0029313564300537, "global_step": 582168, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.00516939163208, "global_step": 582169, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9838385581970215, "global_step": 582170, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.95487642288208, "global_step": 582171, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.101837635040283, "global_step": 582172, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.05088210105896, "global_step": 582173, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9926040172576904, "global_step": 582174, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1063008308410645, "global_step": 582175, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.05051851272583, "global_step": 582176, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.045107364654541, "global_step": 582177, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.096020460128784, "global_step": 582178, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0958564281463623, "global_step": 582179, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9909346103668213, "global_step": 582180, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0519094467163086, "global_step": 582181, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0300726890563965, "global_step": 582182, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0187954902648926, "global_step": 582183, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.049833059310913, "global_step": 582184, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0686874389648438, "global_step": 582185, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.074538469314575, "global_step": 582186, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0446908473968506, "global_step": 582187, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0576729774475098, "global_step": 582188, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9445528984069824, "global_step": 582189, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0618362426757812, "global_step": 582190, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0758771896362305, "global_step": 582191, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.008328437805176, "global_step": 582192, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9785163402557373, "global_step": 582193, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.955745816230774, "global_step": 582194, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9797441959381104, "global_step": 582195, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.01102876663208, "global_step": 582196, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0196471214294434, "global_step": 582197, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.039188861846924, "global_step": 582198, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.015219211578369, "global_step": 582199, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.114316701889038, "global_step": 582200, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0352158546447754, "global_step": 582201, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.961401104927063, "global_step": 582202, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0326263904571533, "global_step": 582203, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9724634885787964, "global_step": 582204, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.007327079772949, "global_step": 582205, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.994473934173584, "global_step": 582206, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.969491720199585, "global_step": 582207, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9999511241912842, "global_step": 582208, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0802645683288574, "global_step": 582209, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.095494270324707, "global_step": 582210, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0841000080108643, "global_step": 582211, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.04770565032959, "global_step": 582212, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1015419960021973, "global_step": 582213, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.996252417564392, "global_step": 582214, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0704081058502197, "global_step": 582215, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0119380950927734, "global_step": 582216, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.040187358856201, "global_step": 582217, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9559277296066284, "global_step": 582218, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0028634071350098, "global_step": 582219, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9565072059631348, "global_step": 582220, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.018157720565796, "global_step": 582221, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.025500774383545, "global_step": 582222, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0651800632476807, "global_step": 582223, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.109881639480591, "global_step": 582224, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9784011840820312, "global_step": 582225, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9737805128097534, "global_step": 582226, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.004014015197754, "global_step": 582227, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.026200771331787, "global_step": 582228, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9786145687103271, "global_step": 582229, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0803170204162598, "global_step": 582230, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0927274227142334, "global_step": 582231, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0331807136535645, "global_step": 582232, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.993259072303772, "global_step": 582233, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9872658252716064, "global_step": 582234, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.011904001235962, "global_step": 582235, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.008497714996338, "global_step": 582236, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.085089921951294, "global_step": 582237, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.004215717315674, "global_step": 582238, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9384275674819946, "global_step": 582239, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0370521545410156, "global_step": 582240, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.012329578399658, "global_step": 582241, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.008305072784424, "global_step": 582242, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9497236013412476, "global_step": 582243, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.142648696899414, "global_step": 582244, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.02620267868042, "global_step": 582245, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.975243330001831, "global_step": 582246, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0534679889678955, "global_step": 582247, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.019670009613037, "global_step": 582248, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9921562671661377, "global_step": 582249, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.150451898574829, "global_step": 582250, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9800856113433838, "global_step": 582251, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.957340955734253, "global_step": 582252, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0561676025390625, "global_step": 582253, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9698917865753174, "global_step": 582254, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9791566133499146, "global_step": 582255, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0564589500427246, "global_step": 582256, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.036245107650757, "global_step": 582257, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0856897830963135, "global_step": 582258, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0046141147613525, "global_step": 582259, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0170276165008545, "global_step": 582260, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0384833812713623, "global_step": 582261, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0785090923309326, "global_step": 582262, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0630791187286377, "global_step": 582263, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0272302627563477, "global_step": 582264, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0949974060058594, "global_step": 582265, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0877764225006104, "global_step": 582266, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0374109745025635, "global_step": 582267, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.999098777770996, "global_step": 582268, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.98638916015625, "global_step": 582269, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.02612566947937, "global_step": 582270, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.951709270477295, "global_step": 582271, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9371275901794434, "global_step": 582272, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.995230793952942, "global_step": 582273, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.000267267227173, "global_step": 582274, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.055662155151367, "global_step": 582275, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0216140747070312, "global_step": 582276, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.002082109451294, "global_step": 582277, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0276005268096924, "global_step": 582278, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0078186988830566, "global_step": 582279, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9928141832351685, "global_step": 582280, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9529011249542236, "global_step": 582281, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9828814268112183, "global_step": 582282, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0342376232147217, "global_step": 582283, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0903773307800293, "global_step": 582284, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9352649450302124, "global_step": 582285, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.079864501953125, "global_step": 582286, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0748982429504395, "global_step": 582287, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.017446517944336, "global_step": 582288, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0361809730529785, "global_step": 582289, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.104893684387207, "global_step": 582290, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.127873420715332, "global_step": 582291, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0202746391296387, "global_step": 582292, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.053309202194214, "global_step": 582293, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.017190933227539, "global_step": 582294, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.131333589553833, "global_step": 582295, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0398313999176025, "global_step": 582296, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0587475299835205, "global_step": 582297, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.986728549003601, "global_step": 582298, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0920910835266113, "global_step": 582299, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9749425649642944, "global_step": 582300, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.966454267501831, "global_step": 582301, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9931650161743164, "global_step": 582302, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0663065910339355, "global_step": 582303, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.052414655685425, "global_step": 582304, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0038864612579346, "global_step": 582305, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0162758827209473, "global_step": 582306, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.082736015319824, "global_step": 582307, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9091873168945312, "global_step": 582308, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.060727596282959, "global_step": 582309, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.006675958633423, "global_step": 582310, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0293962955474854, "global_step": 582311, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9920904636383057, "global_step": 582312, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9659018516540527, "global_step": 582313, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0360472202301025, "global_step": 582314, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1028170585632324, "global_step": 582315, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0326218605041504, "global_step": 582316, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0886337757110596, "global_step": 582317, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1217660903930664, "global_step": 582318, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9661904573440552, "global_step": 582319, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1081583499908447, "global_step": 582320, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0646233558654785, "global_step": 582321, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.975786566734314, "global_step": 582322, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.997624158859253, "global_step": 582323, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0395562648773193, "global_step": 582324, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0856611728668213, "global_step": 582325, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.047001838684082, "global_step": 582326, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0472166538238525, "global_step": 582327, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.02630352973938, "global_step": 582328, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0778188705444336, "global_step": 582329, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.97832453250885, "global_step": 582330, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0001461505889893, "global_step": 582331, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.002605438232422, "global_step": 582332, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.927830457687378, "global_step": 582333, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.082878589630127, "global_step": 582334, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9740203619003296, "global_step": 582335, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0331597328186035, "global_step": 582336, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0388572216033936, "global_step": 582337, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0492584705352783, "global_step": 582338, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9111175537109375, "global_step": 582339, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.980064868927002, "global_step": 582340, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9938548803329468, "global_step": 582341, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0042238235473633, "global_step": 582342, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9896522760391235, "global_step": 582343, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.010089159011841, "global_step": 582344, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0044729709625244, "global_step": 582345, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0163865089416504, "global_step": 582346, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0215559005737305, "global_step": 582347, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.031641721725464, "global_step": 582348, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.039236307144165, "global_step": 582349, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9958477020263672, "global_step": 582350, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0582568645477295, "global_step": 582351, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.065244436264038, "global_step": 582352, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.058927536010742, "global_step": 582353, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0584001541137695, "global_step": 582354, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.100476026535034, "global_step": 582355, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.064681053161621, "global_step": 582356, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0092906951904297, "global_step": 582357, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.966122031211853, "global_step": 582358, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9431716203689575, "global_step": 582359, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0515947341918945, "global_step": 582360, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0433952808380127, "global_step": 582361, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9508426189422607, "global_step": 582362, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0681509971618652, "global_step": 582363, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.093538761138916, "global_step": 582364, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0978689193725586, "global_step": 582365, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.023162364959717, "global_step": 582366, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9755078554153442, "global_step": 582367, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0760867595672607, "global_step": 582368, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.03220796585083, "global_step": 582369, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9985321760177612, "global_step": 582370, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.02921462059021, "global_step": 582371, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1150920391082764, "global_step": 582372, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.028108835220337, "global_step": 582373, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0098390579223633, "global_step": 582374, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9998204708099365, "global_step": 582375, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9482874870300293, "global_step": 582376, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0569303035736084, "global_step": 582377, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0296971797943115, "global_step": 582378, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9378634691238403, "global_step": 582379, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.976441502571106, "global_step": 582380, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.00396990776062, "global_step": 582381, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0315022468566895, "global_step": 582382, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9124047756195068, "global_step": 582383, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9733470678329468, "global_step": 582384, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1113429069519043, "global_step": 582385, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.97471284866333, "global_step": 582386, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9437254667282104, "global_step": 582387, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.038081169128418, "global_step": 582388, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9898501634597778, "global_step": 582389, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0554916858673096, "global_step": 582390, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9789036512374878, "global_step": 582391, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.939357876777649, "global_step": 582392, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9950733184814453, "global_step": 582393, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.078299045562744, "global_step": 582394, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1198787689208984, "global_step": 582395, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.061086893081665, "global_step": 582396, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.048900604248047, "global_step": 582397, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.146204948425293, "global_step": 582398, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.074521064758301, "global_step": 582399, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0161893367767334, "global_step": 582400, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.034792184829712, "global_step": 582401, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9971257448196411, "global_step": 582402, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9977906942367554, "global_step": 582403, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.094376802444458, "global_step": 582404, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.120680093765259, "global_step": 582405, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0565671920776367, "global_step": 582406, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.094273328781128, "global_step": 582407, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.031196117401123, "global_step": 582408, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1087124347686768, "global_step": 582409, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.922105312347412, "global_step": 582410, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0617761611938477, "global_step": 582411, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.016801357269287, "global_step": 582412, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0276269912719727, "global_step": 582413, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9992011785507202, "global_step": 582414, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.079275131225586, "global_step": 582415, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.03024959564209, "global_step": 582416, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9754880666732788, "global_step": 582417, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.057145595550537, "global_step": 582418, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0021698474884033, "global_step": 582419, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1162030696868896, "global_step": 582420, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9774620532989502, "global_step": 582421, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9848023653030396, "global_step": 582422, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0122897624969482, "global_step": 582423, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.101799488067627, "global_step": 582424, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9781463146209717, "global_step": 582425, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0859670639038086, "global_step": 582426, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0448250770568848, "global_step": 582427, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9761853218078613, "global_step": 582428, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.022385358810425, "global_step": 582429, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.964084506034851, "global_step": 582430, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9635335206985474, "global_step": 582431, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.087094783782959, "global_step": 582432, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.999843716621399, "global_step": 582433, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.004572629928589, "global_step": 582434, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0430538654327393, "global_step": 582435, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.014068126678467, "global_step": 582436, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0933172702789307, "global_step": 582437, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0917420387268066, "global_step": 582438, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0253148078918457, "global_step": 582439, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9852465391159058, "global_step": 582440, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.937611699104309, "global_step": 582441, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.048863410949707, "global_step": 582442, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9859280586242676, "global_step": 582443, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9582772254943848, "global_step": 582444, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.011467933654785, "global_step": 582445, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9613878726959229, "global_step": 582446, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.104919672012329, "global_step": 582447, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0352330207824707, "global_step": 582448, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0136454105377197, "global_step": 582449, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.081803798675537, "global_step": 582450, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.958604335784912, "global_step": 582451, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9968856573104858, "global_step": 582452, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9390379190444946, "global_step": 582453, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9727883338928223, "global_step": 582454, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0374953746795654, "global_step": 582455, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0155303478240967, "global_step": 582456, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9717146158218384, "global_step": 582457, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9717687368392944, "global_step": 582458, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0560953617095947, "global_step": 582459, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9954519271850586, "global_step": 582460, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0291175842285156, "global_step": 582461, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0044939517974854, "global_step": 582462, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0563929080963135, "global_step": 582463, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.975305199623108, "global_step": 582464, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.047189474105835, "global_step": 582465, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0075180530548096, "global_step": 582466, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9688456058502197, "global_step": 582467, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0661280155181885, "global_step": 582468, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0651001930236816, "global_step": 582469, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9854212999343872, "global_step": 582470, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.067328453063965, "global_step": 582471, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.1095776557922363, "global_step": 582472, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.066692352294922, "global_step": 582473, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0443170070648193, "global_step": 582474, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0666604042053223, "global_step": 582475, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9882490634918213, "global_step": 582476, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.020732879638672, "global_step": 582477, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9995105266571045, "global_step": 582478, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9403057098388672, "global_step": 582479, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9617350101470947, "global_step": 582480, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.071519136428833, "global_step": 582481, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9864541292190552, "global_step": 582482, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.112816333770752, "global_step": 582483, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0490736961364746, "global_step": 582484, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0392632484436035, "global_step": 582485, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.018068790435791, "global_step": 582486, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0079281330108643, "global_step": 582487, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0546822547912598, "global_step": 582488, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0021276473999023, "global_step": 582489, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9960172176361084, "global_step": 582490, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.922258973121643, "global_step": 582491, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.002514362335205, "global_step": 582492, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9737540483474731, "global_step": 582493, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.054945468902588, "global_step": 582494, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0545477867126465, "global_step": 582495, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9791653156280518, "global_step": 582496, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9718793630599976, "global_step": 582497, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9842047691345215, "global_step": 582498, "epoch": 950, "lr": 5e-05}
{"train_loss": 1.9699499607086182, "global_step": 582499, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.067124128341675, "global_step": 582500, "epoch": 950, "lr": 5e-05}
{"train_loss": 2.0182993412017822, "global_step": 582501, "epoch": 950, "lr": 5e-05, "KITCHEN_SCENE6_put_the_yellow_and_white_mug_in_the_microwave_and_close_it/mean_success_rate": 0.8666666666666667, "LIVING_ROOM_SCENE2_put_both_the_alphabet_soup_and_the_tomato_sauce_in_the_basket/mean_success_rate": 0.03333333333333333, "STUDY_SCENE1_pick_up_the_book_and_place_it_in_the_back_compartment_of_the_caddy/mean_success_rate": 0.6666666666666666, "KITCHEN_SCENE8_put_both_moka_pots_on_the_stove/mean_success_rate": 0.5333333333333333, "LIVING_ROOM_SCENE5_put_the_white_mug_on_the_left_plate_and_put_the_yellow_and_white_mug_on_the_right_plate/mean_success_rate": 0.5333333333333333, "LIVING_ROOM_SCENE6_put_the_white_mug_on_the_plate_and_put_the_chocolate_pudding_to_the_right_of_the_plate/mean_success_rate": 0.2, "KITCHEN_SCENE4_put_the_black_bowl_in_the_bottom_drawer_of_the_cabinet_and_close_it/mean_success_rate": 0.8666666666666667, "LIVING_ROOM_SCENE2_put_both_the_cream_cheese_box_and_the_butter_in_the_basket/mean_success_rate": 0.7333333333333333, "LIVING_ROOM_SCENE1_put_both_the_alphabet_soup_and_the_cream_cheese_box_in_the_basket/mean_success_rate": 0.0, "KITCHEN_SCENE3_turn_on_the_stove_and_put_the_moka_pot_on_it/mean_success_rate": 0.8333333333333334, "mean_success_rate": 0.5266666666666666, "val_loss": 5.783568859100342, "test_reconst_mse": 0.07388626039028168}
{"train_loss": 1.9899736642837524, "global_step": 582502, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.016223192214966, "global_step": 582503, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9910935163497925, "global_step": 582504, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9990167617797852, "global_step": 582505, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0453171730041504, "global_step": 582506, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0394656658172607, "global_step": 582507, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.015350341796875, "global_step": 582508, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.969331979751587, "global_step": 582509, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0408103466033936, "global_step": 582510, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9413957595825195, "global_step": 582511, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9417537450790405, "global_step": 582512, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.999390959739685, "global_step": 582513, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.01314640045166, "global_step": 582514, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9865010976791382, "global_step": 582515, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.987879991531372, "global_step": 582516, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9877374172210693, "global_step": 582517, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9037489891052246, "global_step": 582518, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9288862943649292, "global_step": 582519, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0038394927978516, "global_step": 582520, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9083455801010132, "global_step": 582521, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9869589805603027, "global_step": 582522, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.048816680908203, "global_step": 582523, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.084970474243164, "global_step": 582524, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0186901092529297, "global_step": 582525, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0199248790740967, "global_step": 582526, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.04457688331604, "global_step": 582527, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.120771884918213, "global_step": 582528, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9660685062408447, "global_step": 582529, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9520971775054932, "global_step": 582530, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9914274215698242, "global_step": 582531, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0604195594787598, "global_step": 582532, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1315038204193115, "global_step": 582533, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.018186569213867, "global_step": 582534, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0064148902893066, "global_step": 582535, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9989807605743408, "global_step": 582536, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.8891699314117432, "global_step": 582537, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0710344314575195, "global_step": 582538, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.028190851211548, "global_step": 582539, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.034648895263672, "global_step": 582540, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0123722553253174, "global_step": 582541, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0446877479553223, "global_step": 582542, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.019634962081909, "global_step": 582543, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.044353723526001, "global_step": 582544, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9604588747024536, "global_step": 582545, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.049828290939331, "global_step": 582546, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1212520599365234, "global_step": 582547, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9624158143997192, "global_step": 582548, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9901294708251953, "global_step": 582549, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9881606101989746, "global_step": 582550, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0309269428253174, "global_step": 582551, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9742727279663086, "global_step": 582552, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9322736263275146, "global_step": 582553, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.937371015548706, "global_step": 582554, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1020302772521973, "global_step": 582555, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9981892108917236, "global_step": 582556, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.007939338684082, "global_step": 582557, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0240635871887207, "global_step": 582558, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9750128984451294, "global_step": 582559, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0056865215301514, "global_step": 582560, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0279438495635986, "global_step": 582561, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0055887699127197, "global_step": 582562, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0388858318328857, "global_step": 582563, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0309536457061768, "global_step": 582564, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9596035480499268, "global_step": 582565, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0853493213653564, "global_step": 582566, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.034536123275757, "global_step": 582567, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0438108444213867, "global_step": 582568, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9556162357330322, "global_step": 582569, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.05375337600708, "global_step": 582570, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9800529479980469, "global_step": 582571, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0160117149353027, "global_step": 582572, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9492931365966797, "global_step": 582573, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0011065006256104, "global_step": 582574, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0857760906219482, "global_step": 582575, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9868264198303223, "global_step": 582576, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0264904499053955, "global_step": 582577, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.032207489013672, "global_step": 582578, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.127462387084961, "global_step": 582579, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.02675724029541, "global_step": 582580, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9728846549987793, "global_step": 582581, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1048288345336914, "global_step": 582582, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.051875114440918, "global_step": 582583, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0527772903442383, "global_step": 582584, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9912673234939575, "global_step": 582585, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0563249588012695, "global_step": 582586, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.96058189868927, "global_step": 582587, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.8980982303619385, "global_step": 582588, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0362086296081543, "global_step": 582589, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9488301277160645, "global_step": 582590, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.970421552658081, "global_step": 582591, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.106407403945923, "global_step": 582592, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9969916343688965, "global_step": 582593, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.026475429534912, "global_step": 582594, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9620391130447388, "global_step": 582595, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0317277908325195, "global_step": 582596, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9793920516967773, "global_step": 582597, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.010733127593994, "global_step": 582598, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.047268867492676, "global_step": 582599, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9935775995254517, "global_step": 582600, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.013842821121216, "global_step": 582601, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0205183029174805, "global_step": 582602, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.097238063812256, "global_step": 582603, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.952027678489685, "global_step": 582604, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.03300404548645, "global_step": 582605, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.051236867904663, "global_step": 582606, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.023500680923462, "global_step": 582607, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9322813749313354, "global_step": 582608, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.060343027114868, "global_step": 582609, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.067573070526123, "global_step": 582610, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9753916263580322, "global_step": 582611, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9490398168563843, "global_step": 582612, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.027688980102539, "global_step": 582613, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0278568267822266, "global_step": 582614, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0060267448425293, "global_step": 582615, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.042919874191284, "global_step": 582616, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0057930946350098, "global_step": 582617, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9814479351043701, "global_step": 582618, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.082380533218384, "global_step": 582619, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1082887649536133, "global_step": 582620, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.061856985092163, "global_step": 582621, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0007894039154053, "global_step": 582622, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.955129861831665, "global_step": 582623, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0321226119995117, "global_step": 582624, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0141398906707764, "global_step": 582625, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9547241926193237, "global_step": 582626, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0409533977508545, "global_step": 582627, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0305299758911133, "global_step": 582628, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.022629499435425, "global_step": 582629, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.019496440887451, "global_step": 582630, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.004854679107666, "global_step": 582631, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0911452770233154, "global_step": 582632, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.06178617477417, "global_step": 582633, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1200904846191406, "global_step": 582634, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9010683298110962, "global_step": 582635, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.942911148071289, "global_step": 582636, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9938381910324097, "global_step": 582637, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0058088302612305, "global_step": 582638, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0076751708984375, "global_step": 582639, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0447781085968018, "global_step": 582640, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0774638652801514, "global_step": 582641, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1438326835632324, "global_step": 582642, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0042004585266113, "global_step": 582643, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0949387550354004, "global_step": 582644, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0224108695983887, "global_step": 582645, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0009560585021973, "global_step": 582646, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.017272472381592, "global_step": 582647, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1254563331604004, "global_step": 582648, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9801298379898071, "global_step": 582649, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9981266260147095, "global_step": 582650, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.028348922729492, "global_step": 582651, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.917686939239502, "global_step": 582652, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0948143005371094, "global_step": 582653, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.997751235961914, "global_step": 582654, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.052990198135376, "global_step": 582655, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.010735034942627, "global_step": 582656, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.991081714630127, "global_step": 582657, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0118820667266846, "global_step": 582658, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.955971121788025, "global_step": 582659, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.016383171081543, "global_step": 582660, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0727663040161133, "global_step": 582661, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.01090669631958, "global_step": 582662, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9579375982284546, "global_step": 582663, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0285046100616455, "global_step": 582664, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0084996223449707, "global_step": 582665, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0078794956207275, "global_step": 582666, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9330705404281616, "global_step": 582667, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.067376136779785, "global_step": 582668, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1208114624023438, "global_step": 582669, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0459299087524414, "global_step": 582670, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0009047985076904, "global_step": 582671, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.026533365249634, "global_step": 582672, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0545201301574707, "global_step": 582673, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0062334537506104, "global_step": 582674, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.064574718475342, "global_step": 582675, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.032485246658325, "global_step": 582676, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9859706163406372, "global_step": 582677, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0635714530944824, "global_step": 582678, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0828561782836914, "global_step": 582679, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0594828128814697, "global_step": 582680, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.016355037689209, "global_step": 582681, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0210673809051514, "global_step": 582682, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.983647346496582, "global_step": 582683, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.910507082939148, "global_step": 582684, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0233073234558105, "global_step": 582685, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.018328905105591, "global_step": 582686, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9984383583068848, "global_step": 582687, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.003566265106201, "global_step": 582688, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.985766053199768, "global_step": 582689, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.055795431137085, "global_step": 582690, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.008274793624878, "global_step": 582691, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9431968927383423, "global_step": 582692, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.011599540710449, "global_step": 582693, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9917528629302979, "global_step": 582694, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.040614604949951, "global_step": 582695, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9009690284729004, "global_step": 582696, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9728326797485352, "global_step": 582697, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0025253295898438, "global_step": 582698, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9639925956726074, "global_step": 582699, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.8931432962417603, "global_step": 582700, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0481433868408203, "global_step": 582701, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9918500185012817, "global_step": 582702, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0448036193847656, "global_step": 582703, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.013176679611206, "global_step": 582704, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0192699432373047, "global_step": 582705, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9893882274627686, "global_step": 582706, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0515663623809814, "global_step": 582707, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.874714732170105, "global_step": 582708, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0554234981536865, "global_step": 582709, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9338384866714478, "global_step": 582710, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9714975357055664, "global_step": 582711, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9245011806488037, "global_step": 582712, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9974796772003174, "global_step": 582713, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.076939821243286, "global_step": 582714, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9568448066711426, "global_step": 582715, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.086683511734009, "global_step": 582716, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0456061363220215, "global_step": 582717, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.096602439880371, "global_step": 582718, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9652535915374756, "global_step": 582719, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.055490732192993, "global_step": 582720, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9881571531295776, "global_step": 582721, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.998852014541626, "global_step": 582722, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0969913005828857, "global_step": 582723, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9960542917251587, "global_step": 582724, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0509212017059326, "global_step": 582725, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0300679206848145, "global_step": 582726, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0275042057037354, "global_step": 582727, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.038753032684326, "global_step": 582728, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0674002170562744, "global_step": 582729, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0482804775238037, "global_step": 582730, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0059847831726074, "global_step": 582731, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0634074211120605, "global_step": 582732, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9714244604110718, "global_step": 582733, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.017383575439453, "global_step": 582734, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0843613147735596, "global_step": 582735, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9490762948989868, "global_step": 582736, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.047891855239868, "global_step": 582737, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.022937774658203, "global_step": 582738, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1073343753814697, "global_step": 582739, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0763022899627686, "global_step": 582740, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0608198642730713, "global_step": 582741, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9877407550811768, "global_step": 582742, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0782458782196045, "global_step": 582743, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9908156394958496, "global_step": 582744, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.973836064338684, "global_step": 582745, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0684831142425537, "global_step": 582746, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0294952392578125, "global_step": 582747, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.000102996826172, "global_step": 582748, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0442628860473633, "global_step": 582749, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0160598754882812, "global_step": 582750, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.02949857711792, "global_step": 582751, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0181121826171875, "global_step": 582752, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.050851345062256, "global_step": 582753, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9776976108551025, "global_step": 582754, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0125746726989746, "global_step": 582755, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9941481351852417, "global_step": 582756, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.051668405532837, "global_step": 582757, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.033069133758545, "global_step": 582758, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.144721508026123, "global_step": 582759, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0097463130950928, "global_step": 582760, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0209908485412598, "global_step": 582761, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.060246706008911, "global_step": 582762, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0558977127075195, "global_step": 582763, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.012535810470581, "global_step": 582764, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0396134853363037, "global_step": 582765, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9622994661331177, "global_step": 582766, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.052790403366089, "global_step": 582767, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0140931606292725, "global_step": 582768, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0386579036712646, "global_step": 582769, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.083054542541504, "global_step": 582770, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.062995672225952, "global_step": 582771, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9960232973098755, "global_step": 582772, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0501208305358887, "global_step": 582773, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9854055643081665, "global_step": 582774, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.955780029296875, "global_step": 582775, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0822010040283203, "global_step": 582776, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9533171653747559, "global_step": 582777, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9449700117111206, "global_step": 582778, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0632781982421875, "global_step": 582779, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.96037757396698, "global_step": 582780, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9826691150665283, "global_step": 582781, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9974868297576904, "global_step": 582782, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.077699899673462, "global_step": 582783, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1002492904663086, "global_step": 582784, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9683927297592163, "global_step": 582785, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0493316650390625, "global_step": 582786, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.079550266265869, "global_step": 582787, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9790689945220947, "global_step": 582788, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.015345811843872, "global_step": 582789, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9977936744689941, "global_step": 582790, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.041368007659912, "global_step": 582791, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.92780339717865, "global_step": 582792, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0003857612609863, "global_step": 582793, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0388286113739014, "global_step": 582794, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.047010898590088, "global_step": 582795, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0699148178100586, "global_step": 582796, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.990839958190918, "global_step": 582797, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9798959493637085, "global_step": 582798, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9799809455871582, "global_step": 582799, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.058154582977295, "global_step": 582800, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0656590461730957, "global_step": 582801, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0197391510009766, "global_step": 582802, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0372917652130127, "global_step": 582803, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.07224178314209, "global_step": 582804, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9931238889694214, "global_step": 582805, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.081155776977539, "global_step": 582806, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0385899543762207, "global_step": 582807, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.8984429836273193, "global_step": 582808, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9930739402770996, "global_step": 582809, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.8847968578338623, "global_step": 582810, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9382418394088745, "global_step": 582811, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0056629180908203, "global_step": 582812, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.061689615249634, "global_step": 582813, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0308210849761963, "global_step": 582814, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.013324022293091, "global_step": 582815, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.06585431098938, "global_step": 582816, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9844162464141846, "global_step": 582817, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.097925901412964, "global_step": 582818, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0048744678497314, "global_step": 582819, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.028438091278076, "global_step": 582820, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9921892881393433, "global_step": 582821, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.094330310821533, "global_step": 582822, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0369203090667725, "global_step": 582823, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9999840259552002, "global_step": 582824, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.023869752883911, "global_step": 582825, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.056690216064453, "global_step": 582826, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.055077314376831, "global_step": 582827, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9516639709472656, "global_step": 582828, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0107836723327637, "global_step": 582829, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9961298704147339, "global_step": 582830, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9700678586959839, "global_step": 582831, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9791862964630127, "global_step": 582832, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0726730823516846, "global_step": 582833, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0293660163879395, "global_step": 582834, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1153459548950195, "global_step": 582835, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0196027755737305, "global_step": 582836, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0775012969970703, "global_step": 582837, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0137364864349365, "global_step": 582838, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.029038906097412, "global_step": 582839, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0343880653381348, "global_step": 582840, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.900076150894165, "global_step": 582841, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0404844284057617, "global_step": 582842, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9994525909423828, "global_step": 582843, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0612878799438477, "global_step": 582844, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1102800369262695, "global_step": 582845, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0271670818328857, "global_step": 582846, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9954869747161865, "global_step": 582847, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9867501258850098, "global_step": 582848, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9459936618804932, "global_step": 582849, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.029338836669922, "global_step": 582850, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9958264827728271, "global_step": 582851, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.050337791442871, "global_step": 582852, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.010754346847534, "global_step": 582853, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9616127014160156, "global_step": 582854, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0277812480926514, "global_step": 582855, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.936110019683838, "global_step": 582856, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0101499557495117, "global_step": 582857, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.050692081451416, "global_step": 582858, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0274765491485596, "global_step": 582859, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0105090141296387, "global_step": 582860, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9973012208938599, "global_step": 582861, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9990198612213135, "global_step": 582862, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0779216289520264, "global_step": 582863, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9863086938858032, "global_step": 582864, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.00956130027771, "global_step": 582865, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0610220432281494, "global_step": 582866, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9469287395477295, "global_step": 582867, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0272583961486816, "global_step": 582868, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.991908311843872, "global_step": 582869, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.033705472946167, "global_step": 582870, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.051762819290161, "global_step": 582871, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0483450889587402, "global_step": 582872, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9662322998046875, "global_step": 582873, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.983859658241272, "global_step": 582874, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.10628604888916, "global_step": 582875, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0381171703338623, "global_step": 582876, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0244061946868896, "global_step": 582877, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.074641704559326, "global_step": 582878, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.071611166000366, "global_step": 582879, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0333032608032227, "global_step": 582880, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0289149284362793, "global_step": 582881, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.983652114868164, "global_step": 582882, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1149730682373047, "global_step": 582883, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.056196689605713, "global_step": 582884, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.943959355354309, "global_step": 582885, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9573577642440796, "global_step": 582886, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9483550786972046, "global_step": 582887, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9881949424743652, "global_step": 582888, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.051023483276367, "global_step": 582889, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.020538568496704, "global_step": 582890, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9887604713439941, "global_step": 582891, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0451529026031494, "global_step": 582892, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.998371958732605, "global_step": 582893, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1206252574920654, "global_step": 582894, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0171284675598145, "global_step": 582895, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9733623266220093, "global_step": 582896, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9860471487045288, "global_step": 582897, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9706679582595825, "global_step": 582898, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0035767555236816, "global_step": 582899, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0295522212982178, "global_step": 582900, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.062936544418335, "global_step": 582901, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.092909812927246, "global_step": 582902, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.974212646484375, "global_step": 582903, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.072425127029419, "global_step": 582904, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.999516248703003, "global_step": 582905, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.016639471054077, "global_step": 582906, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0388693809509277, "global_step": 582907, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9750845432281494, "global_step": 582908, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9844403266906738, "global_step": 582909, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.072782278060913, "global_step": 582910, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.976458191871643, "global_step": 582911, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9603118896484375, "global_step": 582912, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9501919746398926, "global_step": 582913, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9590731859207153, "global_step": 582914, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9853732585906982, "global_step": 582915, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0568394660949707, "global_step": 582916, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0016584396362305, "global_step": 582917, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.015197515487671, "global_step": 582918, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9504209756851196, "global_step": 582919, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.132979154586792, "global_step": 582920, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1094439029693604, "global_step": 582921, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0477712154388428, "global_step": 582922, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9578866958618164, "global_step": 582923, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0163543224334717, "global_step": 582924, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9647464752197266, "global_step": 582925, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.009221076965332, "global_step": 582926, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0242745876312256, "global_step": 582927, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0241615772247314, "global_step": 582928, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9282389879226685, "global_step": 582929, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.008599281311035, "global_step": 582930, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0082244873046875, "global_step": 582931, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9812743663787842, "global_step": 582932, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.021530866622925, "global_step": 582933, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9885094165802002, "global_step": 582934, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.024559259414673, "global_step": 582935, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9062399864196777, "global_step": 582936, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.001096487045288, "global_step": 582937, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0115163326263428, "global_step": 582938, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.100229024887085, "global_step": 582939, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.080251693725586, "global_step": 582940, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0371651649475098, "global_step": 582941, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0059707164764404, "global_step": 582942, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0187439918518066, "global_step": 582943, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0956966876983643, "global_step": 582944, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.038428544998169, "global_step": 582945, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0437324047088623, "global_step": 582946, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0466039180755615, "global_step": 582947, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0096213817596436, "global_step": 582948, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0865495204925537, "global_step": 582949, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.967993140220642, "global_step": 582950, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0357625484466553, "global_step": 582951, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0597102642059326, "global_step": 582952, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.94674551486969, "global_step": 582953, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.113661289215088, "global_step": 582954, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.003732681274414, "global_step": 582955, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0216329097747803, "global_step": 582956, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9823133945465088, "global_step": 582957, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9593298435211182, "global_step": 582958, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9689242839813232, "global_step": 582959, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.001418113708496, "global_step": 582960, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.005549430847168, "global_step": 582961, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0819685459136963, "global_step": 582962, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.07586407661438, "global_step": 582963, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.049798011779785, "global_step": 582964, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9560495615005493, "global_step": 582965, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0151219367980957, "global_step": 582966, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0357718467712402, "global_step": 582967, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.953259825706482, "global_step": 582968, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0429060459136963, "global_step": 582969, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0646259784698486, "global_step": 582970, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.051877021789551, "global_step": 582971, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.033562421798706, "global_step": 582972, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0691049098968506, "global_step": 582973, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9116798639297485, "global_step": 582974, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.040576219558716, "global_step": 582975, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9409886598587036, "global_step": 582976, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0338399410247803, "global_step": 582977, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.033118724822998, "global_step": 582978, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.067578077316284, "global_step": 582979, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.979874610900879, "global_step": 582980, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9733669757843018, "global_step": 582981, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.016249656677246, "global_step": 582982, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.034106492996216, "global_step": 582983, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0350582599639893, "global_step": 582984, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0442917346954346, "global_step": 582985, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.033100128173828, "global_step": 582986, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.941125750541687, "global_step": 582987, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0102736949920654, "global_step": 582988, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9579089879989624, "global_step": 582989, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9771158695220947, "global_step": 582990, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9880695343017578, "global_step": 582991, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9882216453552246, "global_step": 582992, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.037076234817505, "global_step": 582993, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9657279253005981, "global_step": 582994, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0563206672668457, "global_step": 582995, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0208866596221924, "global_step": 582996, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9874403476715088, "global_step": 582997, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.027646064758301, "global_step": 582998, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0385122299194336, "global_step": 582999, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0182416439056396, "global_step": 583000, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.063638925552368, "global_step": 583001, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0040643215179443, "global_step": 583002, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9869476556777954, "global_step": 583003, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.048732280731201, "global_step": 583004, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0111875534057617, "global_step": 583005, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0233383178710938, "global_step": 583006, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.008183479309082, "global_step": 583007, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0287749767303467, "global_step": 583008, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.8867532014846802, "global_step": 583009, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0314269065856934, "global_step": 583010, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0159971714019775, "global_step": 583011, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9327116012573242, "global_step": 583012, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9502620697021484, "global_step": 583013, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9997951984405518, "global_step": 583014, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0791923999786377, "global_step": 583015, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0127127170562744, "global_step": 583016, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.991196870803833, "global_step": 583017, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9940319061279297, "global_step": 583018, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0179874897003174, "global_step": 583019, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.021911382675171, "global_step": 583020, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9987008571624756, "global_step": 583021, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.045206308364868, "global_step": 583022, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0355613231658936, "global_step": 583023, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9957478046417236, "global_step": 583024, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9522658586502075, "global_step": 583025, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9582628011703491, "global_step": 583026, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9617657661437988, "global_step": 583027, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0474741458892822, "global_step": 583028, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9456000328063965, "global_step": 583029, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.034785270690918, "global_step": 583030, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.054054021835327, "global_step": 583031, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9815349578857422, "global_step": 583032, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.8846328258514404, "global_step": 583033, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.082120895385742, "global_step": 583034, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0762295722961426, "global_step": 583035, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.949792742729187, "global_step": 583036, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0219953060150146, "global_step": 583037, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1386444568634033, "global_step": 583038, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0943663120269775, "global_step": 583039, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9479154348373413, "global_step": 583040, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.949337363243103, "global_step": 583041, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0424604415893555, "global_step": 583042, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.965844988822937, "global_step": 583043, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9957647323608398, "global_step": 583044, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0677735805511475, "global_step": 583045, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9906247854232788, "global_step": 583046, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0815911293029785, "global_step": 583047, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0661072731018066, "global_step": 583048, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1147282123565674, "global_step": 583049, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9626805782318115, "global_step": 583050, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0098493099212646, "global_step": 583051, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0434324741363525, "global_step": 583052, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.085251808166504, "global_step": 583053, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9995204210281372, "global_step": 583054, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0162196159362793, "global_step": 583055, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9728800058364868, "global_step": 583056, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0059943199157715, "global_step": 583057, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.988244891166687, "global_step": 583058, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9989639520645142, "global_step": 583059, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9530898332595825, "global_step": 583060, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9677183628082275, "global_step": 583061, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0235958099365234, "global_step": 583062, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0525848865509033, "global_step": 583063, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.957357406616211, "global_step": 583064, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.106370210647583, "global_step": 583065, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0480217933654785, "global_step": 583066, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0340516567230225, "global_step": 583067, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0107481479644775, "global_step": 583068, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0602400302886963, "global_step": 583069, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.021129846572876, "global_step": 583070, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9833968877792358, "global_step": 583071, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0638904571533203, "global_step": 583072, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1243369579315186, "global_step": 583073, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9594289064407349, "global_step": 583074, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0207810401916504, "global_step": 583075, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9135526418685913, "global_step": 583076, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.023745059967041, "global_step": 583077, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.005728006362915, "global_step": 583078, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9856678247451782, "global_step": 583079, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.993948221206665, "global_step": 583080, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.974238634109497, "global_step": 583081, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.978843331336975, "global_step": 583082, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0083296298980713, "global_step": 583083, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.007831573486328, "global_step": 583084, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0602869987487793, "global_step": 583085, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0243937969207764, "global_step": 583086, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0237932205200195, "global_step": 583087, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0467092990875244, "global_step": 583088, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.997016191482544, "global_step": 583089, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0641398429870605, "global_step": 583090, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.034916639328003, "global_step": 583091, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9875762462615967, "global_step": 583092, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9960477352142334, "global_step": 583093, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.936755895614624, "global_step": 583094, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0848727226257324, "global_step": 583095, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0195460319519043, "global_step": 583096, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9809449911117554, "global_step": 583097, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0010788440704346, "global_step": 583098, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9959369897842407, "global_step": 583099, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9554364681243896, "global_step": 583100, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.035809278488159, "global_step": 583101, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0550854206085205, "global_step": 583102, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.940490484237671, "global_step": 583103, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.985215187072754, "global_step": 583104, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0599217414855957, "global_step": 583105, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1208767890930176, "global_step": 583106, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9805420637130737, "global_step": 583107, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9444169998168945, "global_step": 583108, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0319910049438477, "global_step": 583109, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9770268201828003, "global_step": 583110, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.044743061065674, "global_step": 583111, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9855475425720215, "global_step": 583112, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.030291795730591, "global_step": 583113, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.057358980178833, "global_step": 583114, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.962497353553772, "global_step": 583115, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9961572885513306, "global_step": 583116, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0670394897460938, "global_step": 583117, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.938297986984253, "global_step": 583118, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.00134539604187, "global_step": 583119, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0817973613739014, "global_step": 583120, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9988691806793213, "global_step": 583121, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.010518789291382, "global_step": 583122, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9562551975250244, "global_step": 583123, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0136666297912598, "global_step": 583124, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.107236862182617, "global_step": 583125, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0745322704315186, "global_step": 583126, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.042604446411133, "global_step": 583127, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9571329355239868, "global_step": 583128, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.01066517829895, "global_step": 583129, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0562660694122314, "global_step": 583130, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.032848834991455, "global_step": 583131, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9725723266601562, "global_step": 583132, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0182061195373535, "global_step": 583133, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.8907724618911743, "global_step": 583134, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.049079418182373, "global_step": 583135, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0710113048553467, "global_step": 583136, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0940446853637695, "global_step": 583137, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.087275505065918, "global_step": 583138, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9813436269760132, "global_step": 583139, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.029785394668579, "global_step": 583140, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.998392939567566, "global_step": 583141, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0749664306640625, "global_step": 583142, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0930871963500977, "global_step": 583143, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9857453107833862, "global_step": 583144, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.052940607070923, "global_step": 583145, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9972813129425049, "global_step": 583146, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.010004997253418, "global_step": 583147, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0494143962860107, "global_step": 583148, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0314626693725586, "global_step": 583149, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9311314821243286, "global_step": 583150, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9624625444412231, "global_step": 583151, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.052288293838501, "global_step": 583152, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0428686141967773, "global_step": 583153, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.066746711730957, "global_step": 583154, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.068173408508301, "global_step": 583155, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0145459175109863, "global_step": 583156, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.084684133529663, "global_step": 583157, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0218827724456787, "global_step": 583158, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.069427967071533, "global_step": 583159, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9865219593048096, "global_step": 583160, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.024399995803833, "global_step": 583161, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9355225563049316, "global_step": 583162, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.063446283340454, "global_step": 583163, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9635777473449707, "global_step": 583164, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0337729454040527, "global_step": 583165, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.023582935333252, "global_step": 583166, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0305135250091553, "global_step": 583167, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0138356685638428, "global_step": 583168, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9647748470306396, "global_step": 583169, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0687222480773926, "global_step": 583170, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0605287551879883, "global_step": 583171, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.093801736831665, "global_step": 583172, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9598357677459717, "global_step": 583173, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9550801515579224, "global_step": 583174, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9948720932006836, "global_step": 583175, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.980047583580017, "global_step": 583176, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.003683090209961, "global_step": 583177, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.980997085571289, "global_step": 583178, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0406336784362793, "global_step": 583179, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.026735305786133, "global_step": 583180, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9792969226837158, "global_step": 583181, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0034074783325195, "global_step": 583182, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0376782417297363, "global_step": 583183, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.072049379348755, "global_step": 583184, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0750374794006348, "global_step": 583185, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.064361333847046, "global_step": 583186, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9469718933105469, "global_step": 583187, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.969467043876648, "global_step": 583188, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9940733909606934, "global_step": 583189, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0965702533721924, "global_step": 583190, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.008185625076294, "global_step": 583191, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0140161514282227, "global_step": 583192, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0715036392211914, "global_step": 583193, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9694207906723022, "global_step": 583194, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.056072235107422, "global_step": 583195, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.069579839706421, "global_step": 583196, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9008533954620361, "global_step": 583197, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9943488836288452, "global_step": 583198, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9651718139648438, "global_step": 583199, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0374927520751953, "global_step": 583200, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.059504985809326, "global_step": 583201, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9520972967147827, "global_step": 583202, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.057401418685913, "global_step": 583203, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9693106412887573, "global_step": 583204, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.022759199142456, "global_step": 583205, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.087414503097534, "global_step": 583206, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.028733015060425, "global_step": 583207, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.004364490509033, "global_step": 583208, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.04068660736084, "global_step": 583209, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9892327785491943, "global_step": 583210, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.02170467376709, "global_step": 583211, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9820529222488403, "global_step": 583212, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9809682369232178, "global_step": 583213, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0708532333374023, "global_step": 583214, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.013674020767212, "global_step": 583215, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9588110446929932, "global_step": 583216, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.039024829864502, "global_step": 583217, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0566117763519287, "global_step": 583218, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.984946370124817, "global_step": 583219, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.019458770751953, "global_step": 583220, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0183677673339844, "global_step": 583221, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9256973266601562, "global_step": 583222, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9315329790115356, "global_step": 583223, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0128538608551025, "global_step": 583224, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.054835319519043, "global_step": 583225, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.111248016357422, "global_step": 583226, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0299785137176514, "global_step": 583227, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.153312921524048, "global_step": 583228, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.096290349960327, "global_step": 583229, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0007967948913574, "global_step": 583230, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.959384560585022, "global_step": 583231, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.962638020515442, "global_step": 583232, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.007842779159546, "global_step": 583233, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.027998447418213, "global_step": 583234, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0320115089416504, "global_step": 583235, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.971498727798462, "global_step": 583236, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9415912628173828, "global_step": 583237, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.967670202255249, "global_step": 583238, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.036327838897705, "global_step": 583239, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.06992769241333, "global_step": 583240, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0169832706451416, "global_step": 583241, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.019526958465576, "global_step": 583242, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0014727115631104, "global_step": 583243, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.929828405380249, "global_step": 583244, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0118401050567627, "global_step": 583245, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.02512264251709, "global_step": 583246, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9407590627670288, "global_step": 583247, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0641493797302246, "global_step": 583248, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0468287467956543, "global_step": 583249, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.040815591812134, "global_step": 583250, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0392990112304688, "global_step": 583251, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0961410999298096, "global_step": 583252, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.011122465133667, "global_step": 583253, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0194125175476074, "global_step": 583254, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9914087057113647, "global_step": 583255, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.071546792984009, "global_step": 583256, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.025919198989868, "global_step": 583257, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.05081844329834, "global_step": 583258, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.061133861541748, "global_step": 583259, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0965521335601807, "global_step": 583260, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9534108638763428, "global_step": 583261, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.09786319732666, "global_step": 583262, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0635714530944824, "global_step": 583263, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0099997520446777, "global_step": 583264, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.045346975326538, "global_step": 583265, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0398333072662354, "global_step": 583266, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0071775913238525, "global_step": 583267, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9961633682250977, "global_step": 583268, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0291547775268555, "global_step": 583269, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0609567165374756, "global_step": 583270, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.014101266860962, "global_step": 583271, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0129923820495605, "global_step": 583272, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0455636978149414, "global_step": 583273, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.993260383605957, "global_step": 583274, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0404958724975586, "global_step": 583275, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.060701847076416, "global_step": 583276, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0957324504852295, "global_step": 583277, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9326398372650146, "global_step": 583278, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0431931018829346, "global_step": 583279, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0249664783477783, "global_step": 583280, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0060982704162598, "global_step": 583281, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9801537990570068, "global_step": 583282, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.053264617919922, "global_step": 583283, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.017481803894043, "global_step": 583284, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.018601179122925, "global_step": 583285, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9924898147583008, "global_step": 583286, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0640995502471924, "global_step": 583287, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.032942533493042, "global_step": 583288, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0206124782562256, "global_step": 583289, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9707664251327515, "global_step": 583290, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0592758655548096, "global_step": 583291, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.017831563949585, "global_step": 583292, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9516732692718506, "global_step": 583293, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9731534719467163, "global_step": 583294, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.025224208831787, "global_step": 583295, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0074377059936523, "global_step": 583296, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0181708335876465, "global_step": 583297, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.945243239402771, "global_step": 583298, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.027540922164917, "global_step": 583299, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9577192068099976, "global_step": 583300, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9845389127731323, "global_step": 583301, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0293431282043457, "global_step": 583302, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0318517684936523, "global_step": 583303, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0178558826446533, "global_step": 583304, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.018733501434326, "global_step": 583305, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.08701491355896, "global_step": 583306, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0468499660491943, "global_step": 583307, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.024467706680298, "global_step": 583308, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.034721612930298, "global_step": 583309, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9589647054672241, "global_step": 583310, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0699665546417236, "global_step": 583311, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.010103702545166, "global_step": 583312, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0343713760375977, "global_step": 583313, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9787930250167847, "global_step": 583314, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9738692045211792, "global_step": 583315, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.014082431793213, "global_step": 583316, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9514365196228027, "global_step": 583317, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.11194109916687, "global_step": 583318, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0480053424835205, "global_step": 583319, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9994179010391235, "global_step": 583320, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9792563915252686, "global_step": 583321, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0721347332000732, "global_step": 583322, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0680105686187744, "global_step": 583323, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0386126041412354, "global_step": 583324, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9911116361618042, "global_step": 583325, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0393927097320557, "global_step": 583326, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.00281023979187, "global_step": 583327, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0324220657348633, "global_step": 583328, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9608815908432007, "global_step": 583329, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.115272045135498, "global_step": 583330, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.088474988937378, "global_step": 583331, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.971228003501892, "global_step": 583332, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.061393976211548, "global_step": 583333, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.101778507232666, "global_step": 583334, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0641109943389893, "global_step": 583335, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.060777425765991, "global_step": 583336, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.032707691192627, "global_step": 583337, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9930459260940552, "global_step": 583338, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9914509057998657, "global_step": 583339, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.944617509841919, "global_step": 583340, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.049431324005127, "global_step": 583341, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.139500856399536, "global_step": 583342, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.052525043487549, "global_step": 583343, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0106265544891357, "global_step": 583344, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0363962650299072, "global_step": 583345, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.062061071395874, "global_step": 583346, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.105661630630493, "global_step": 583347, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.037367105484009, "global_step": 583348, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0724689960479736, "global_step": 583349, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.010201930999756, "global_step": 583350, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0769314765930176, "global_step": 583351, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.023496627807617, "global_step": 583352, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.886370301246643, "global_step": 583353, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9988510608673096, "global_step": 583354, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.984859585762024, "global_step": 583355, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.000520944595337, "global_step": 583356, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.026700973510742, "global_step": 583357, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0061516761779785, "global_step": 583358, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9839370250701904, "global_step": 583359, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0375728607177734, "global_step": 583360, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9156709909439087, "global_step": 583361, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.085900068283081, "global_step": 583362, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.975114107131958, "global_step": 583363, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9731522798538208, "global_step": 583364, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.958289623260498, "global_step": 583365, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.927086591720581, "global_step": 583366, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0304923057556152, "global_step": 583367, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0437610149383545, "global_step": 583368, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.984735369682312, "global_step": 583369, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9750300645828247, "global_step": 583370, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0283946990966797, "global_step": 583371, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.049281120300293, "global_step": 583372, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.006235122680664, "global_step": 583373, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0061395168304443, "global_step": 583374, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0359997749328613, "global_step": 583375, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0465638637542725, "global_step": 583376, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9854965209960938, "global_step": 583377, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0483367443084717, "global_step": 583378, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.05781626701355, "global_step": 583379, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.956673502922058, "global_step": 583380, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0093326568603516, "global_step": 583381, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.022185802459717, "global_step": 583382, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9843037128448486, "global_step": 583383, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.031188488006592, "global_step": 583384, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9519407749176025, "global_step": 583385, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9767346382141113, "global_step": 583386, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9857150316238403, "global_step": 583387, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.00419020652771, "global_step": 583388, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0158300399780273, "global_step": 583389, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0243759155273438, "global_step": 583390, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.069167137145996, "global_step": 583391, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.003859281539917, "global_step": 583392, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.072849750518799, "global_step": 583393, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.086341142654419, "global_step": 583394, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.092090129852295, "global_step": 583395, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.075483560562134, "global_step": 583396, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.001847505569458, "global_step": 583397, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9077558517456055, "global_step": 583398, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0300440788269043, "global_step": 583399, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.092233657836914, "global_step": 583400, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.027909517288208, "global_step": 583401, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0157055854797363, "global_step": 583402, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0146844387054443, "global_step": 583403, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.016512632369995, "global_step": 583404, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0059597492218018, "global_step": 583405, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.059778928756714, "global_step": 583406, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0345704555511475, "global_step": 583407, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.073655843734741, "global_step": 583408, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.1536874771118164, "global_step": 583409, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0045647621154785, "global_step": 583410, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9644066095352173, "global_step": 583411, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9986215829849243, "global_step": 583412, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0421977043151855, "global_step": 583413, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.032949924468994, "global_step": 583414, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.111715316772461, "global_step": 583415, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.022426128387451, "global_step": 583416, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.022515058517456, "global_step": 583417, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0758185386657715, "global_step": 583418, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.008504629135132, "global_step": 583419, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.026263475418091, "global_step": 583420, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.93372642993927, "global_step": 583421, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.024536609649658, "global_step": 583422, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9836372137069702, "global_step": 583423, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9838054180145264, "global_step": 583424, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9833617210388184, "global_step": 583425, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.090071678161621, "global_step": 583426, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.102060317993164, "global_step": 583427, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0494046211242676, "global_step": 583428, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.005943536758423, "global_step": 583429, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9221731424331665, "global_step": 583430, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.999124526977539, "global_step": 583431, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0313029289245605, "global_step": 583432, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.920592188835144, "global_step": 583433, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.927964210510254, "global_step": 583434, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0388927459716797, "global_step": 583435, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0243630409240723, "global_step": 583436, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0826685428619385, "global_step": 583437, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0180633068084717, "global_step": 583438, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9733333587646484, "global_step": 583439, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.995072364807129, "global_step": 583440, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.055617094039917, "global_step": 583441, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0860540866851807, "global_step": 583442, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.029639959335327, "global_step": 583443, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.070370674133301, "global_step": 583444, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0111658573150635, "global_step": 583445, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0476937294006348, "global_step": 583446, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9864622354507446, "global_step": 583447, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0909292697906494, "global_step": 583448, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.99277925491333, "global_step": 583449, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9661388397216797, "global_step": 583450, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9723292589187622, "global_step": 583451, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.136625051498413, "global_step": 583452, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.082026720046997, "global_step": 583453, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0013315677642822, "global_step": 583454, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.045677661895752, "global_step": 583455, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0293121337890625, "global_step": 583456, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.008617401123047, "global_step": 583457, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.06593918800354, "global_step": 583458, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.095503568649292, "global_step": 583459, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0023539066314697, "global_step": 583460, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.050403594970703, "global_step": 583461, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0173442363739014, "global_step": 583462, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0238165855407715, "global_step": 583463, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0809438228607178, "global_step": 583464, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.065979242324829, "global_step": 583465, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0828328132629395, "global_step": 583466, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9435499906539917, "global_step": 583467, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.0139946937561035, "global_step": 583468, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.9778989553451538, "global_step": 583469, "epoch": 951, "lr": 5e-05}
{"train_loss": 2.017794370651245, "global_step": 583470, "epoch": 951, "lr": 5e-05}
{"train_loss": 1.998887300491333, "global_step": 583471, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0591962337493896, "global_step": 583472, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0031750202178955, "global_step": 583473, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0798282623291016, "global_step": 583474, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.99709153175354, "global_step": 583475, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9688447713851929, "global_step": 583476, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.027275800704956, "global_step": 583477, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9827067852020264, "global_step": 583478, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.035405158996582, "global_step": 583479, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0038938522338867, "global_step": 583480, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0595362186431885, "global_step": 583481, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.007260799407959, "global_step": 583482, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.015831232070923, "global_step": 583483, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0404934883117676, "global_step": 583484, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0590996742248535, "global_step": 583485, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0393009185791016, "global_step": 583486, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.963769555091858, "global_step": 583487, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0746216773986816, "global_step": 583488, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.03413724899292, "global_step": 583489, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0420315265655518, "global_step": 583490, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0299031734466553, "global_step": 583491, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9764553308486938, "global_step": 583492, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.066399335861206, "global_step": 583493, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9735103845596313, "global_step": 583494, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9664463996887207, "global_step": 583495, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.06272292137146, "global_step": 583496, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9373438358306885, "global_step": 583497, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9777392148971558, "global_step": 583498, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.975064992904663, "global_step": 583499, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9275907278060913, "global_step": 583500, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9708224534988403, "global_step": 583501, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1509604454040527, "global_step": 583502, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0478262901306152, "global_step": 583503, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.013705015182495, "global_step": 583504, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.006875991821289, "global_step": 583505, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.001600503921509, "global_step": 583506, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9582728147506714, "global_step": 583507, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9999769926071167, "global_step": 583508, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0080740451812744, "global_step": 583509, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9434411525726318, "global_step": 583510, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.015685796737671, "global_step": 583511, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9914648532867432, "global_step": 583512, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0630950927734375, "global_step": 583513, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0386743545532227, "global_step": 583514, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0735840797424316, "global_step": 583515, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0993614196777344, "global_step": 583516, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9436331987380981, "global_step": 583517, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9595292806625366, "global_step": 583518, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0552287101745605, "global_step": 583519, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0746984481811523, "global_step": 583520, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0895891189575195, "global_step": 583521, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0801351070404053, "global_step": 583522, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.931942343711853, "global_step": 583523, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.049506664276123, "global_step": 583524, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.047945022583008, "global_step": 583525, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9448223114013672, "global_step": 583526, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.018338680267334, "global_step": 583527, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.8962358236312866, "global_step": 583528, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0663745403289795, "global_step": 583529, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.00693678855896, "global_step": 583530, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.020911931991577, "global_step": 583531, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9879745244979858, "global_step": 583532, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.933598518371582, "global_step": 583533, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9900667667388916, "global_step": 583534, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.044022560119629, "global_step": 583535, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0720181465148926, "global_step": 583536, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9961433410644531, "global_step": 583537, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.048600435256958, "global_step": 583538, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.039456844329834, "global_step": 583539, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1064088344573975, "global_step": 583540, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.035506248474121, "global_step": 583541, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9827909469604492, "global_step": 583542, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0583486557006836, "global_step": 583543, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9513401985168457, "global_step": 583544, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0770859718322754, "global_step": 583545, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.014601469039917, "global_step": 583546, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.064781427383423, "global_step": 583547, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.988028883934021, "global_step": 583548, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.028869152069092, "global_step": 583549, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0089943408966064, "global_step": 583550, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0478928089141846, "global_step": 583551, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0557737350463867, "global_step": 583552, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.025089979171753, "global_step": 583553, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0025343894958496, "global_step": 583554, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0104732513427734, "global_step": 583555, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9994755983352661, "global_step": 583556, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9693033695220947, "global_step": 583557, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9490097761154175, "global_step": 583558, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.959159016609192, "global_step": 583559, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9783399105072021, "global_step": 583560, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.978502869606018, "global_step": 583561, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9821702241897583, "global_step": 583562, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9850845336914062, "global_step": 583563, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.052722454071045, "global_step": 583564, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.936589241027832, "global_step": 583565, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0339457988739014, "global_step": 583566, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0027952194213867, "global_step": 583567, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0341525077819824, "global_step": 583568, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9653254747390747, "global_step": 583569, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9487727880477905, "global_step": 583570, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.034358263015747, "global_step": 583571, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.04179310798645, "global_step": 583572, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.8979852199554443, "global_step": 583573, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0346274375915527, "global_step": 583574, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0696895122528076, "global_step": 583575, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.032449245452881, "global_step": 583576, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0288338661193848, "global_step": 583577, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0174219608306885, "global_step": 583578, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9717503786087036, "global_step": 583579, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9862918853759766, "global_step": 583580, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1219637393951416, "global_step": 583581, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.043294668197632, "global_step": 583582, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9924672842025757, "global_step": 583583, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0005831718444824, "global_step": 583584, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.021472215652466, "global_step": 583585, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0479114055633545, "global_step": 583586, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.120586395263672, "global_step": 583587, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0228540897369385, "global_step": 583588, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.047578811645508, "global_step": 583589, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0178349018096924, "global_step": 583590, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9691181182861328, "global_step": 583591, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.039398670196533, "global_step": 583592, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9577627182006836, "global_step": 583593, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0983569622039795, "global_step": 583594, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.020487070083618, "global_step": 583595, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1131410598754883, "global_step": 583596, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9665905237197876, "global_step": 583597, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9311670064926147, "global_step": 583598, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0310609340667725, "global_step": 583599, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9624946117401123, "global_step": 583600, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9895085096359253, "global_step": 583601, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0638046264648438, "global_step": 583602, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0029447078704834, "global_step": 583603, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9488471746444702, "global_step": 583604, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.044288396835327, "global_step": 583605, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9809939861297607, "global_step": 583606, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.981545329093933, "global_step": 583607, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0165529251098633, "global_step": 583608, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0131590366363525, "global_step": 583609, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9405637979507446, "global_step": 583610, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9475809335708618, "global_step": 583611, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9476423263549805, "global_step": 583612, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9932079315185547, "global_step": 583613, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0814762115478516, "global_step": 583614, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9967719316482544, "global_step": 583615, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9918947219848633, "global_step": 583616, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9294837713241577, "global_step": 583617, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9694777727127075, "global_step": 583618, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0769917964935303, "global_step": 583619, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9825048446655273, "global_step": 583620, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1049282550811768, "global_step": 583621, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.969200611114502, "global_step": 583622, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0384440422058105, "global_step": 583623, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9746301174163818, "global_step": 583624, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9857673645019531, "global_step": 583625, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0250813961029053, "global_step": 583626, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0449421405792236, "global_step": 583627, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.064756155014038, "global_step": 583628, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0491011142730713, "global_step": 583629, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.062183141708374, "global_step": 583630, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0271382331848145, "global_step": 583631, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9983819723129272, "global_step": 583632, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0059361457824707, "global_step": 583633, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0807883739471436, "global_step": 583634, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.091554641723633, "global_step": 583635, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0906081199645996, "global_step": 583636, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9811251163482666, "global_step": 583637, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9498320817947388, "global_step": 583638, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0426366329193115, "global_step": 583639, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9952850341796875, "global_step": 583640, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.868407964706421, "global_step": 583641, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9696494340896606, "global_step": 583642, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0301353931427, "global_step": 583643, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0254507064819336, "global_step": 583644, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0785622596740723, "global_step": 583645, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0130534172058105, "global_step": 583646, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.021665334701538, "global_step": 583647, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9173872470855713, "global_step": 583648, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9936399459838867, "global_step": 583649, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.116953134536743, "global_step": 583650, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9882351160049438, "global_step": 583651, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9780515432357788, "global_step": 583652, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.062866687774658, "global_step": 583653, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9922103881835938, "global_step": 583654, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.993245244026184, "global_step": 583655, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.045342206954956, "global_step": 583656, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.8796334266662598, "global_step": 583657, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.06001353263855, "global_step": 583658, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.140383243560791, "global_step": 583659, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9915169477462769, "global_step": 583660, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1457712650299072, "global_step": 583661, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.037277936935425, "global_step": 583662, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9574100971221924, "global_step": 583663, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.957594871520996, "global_step": 583664, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.98775315284729, "global_step": 583665, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9401072263717651, "global_step": 583666, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0264220237731934, "global_step": 583667, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9458346366882324, "global_step": 583668, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0193734169006348, "global_step": 583669, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.955175757408142, "global_step": 583670, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0413818359375, "global_step": 583671, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0377089977264404, "global_step": 583672, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0186946392059326, "global_step": 583673, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.056335687637329, "global_step": 583674, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0514652729034424, "global_step": 583675, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9792981147766113, "global_step": 583676, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.046614646911621, "global_step": 583677, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.996787667274475, "global_step": 583678, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9714792966842651, "global_step": 583679, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.021644115447998, "global_step": 583680, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.034029722213745, "global_step": 583681, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.8955284357070923, "global_step": 583682, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0716140270233154, "global_step": 583683, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9717698097229004, "global_step": 583684, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0421605110168457, "global_step": 583685, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.98823881149292, "global_step": 583686, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.104365348815918, "global_step": 583687, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0297904014587402, "global_step": 583688, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9196535348892212, "global_step": 583689, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0070643424987793, "global_step": 583690, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9905338287353516, "global_step": 583691, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0014116764068604, "global_step": 583692, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.019211530685425, "global_step": 583693, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.090414047241211, "global_step": 583694, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0480315685272217, "global_step": 583695, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.036402463912964, "global_step": 583696, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.015197277069092, "global_step": 583697, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0059568881988525, "global_step": 583698, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0441906452178955, "global_step": 583699, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0081350803375244, "global_step": 583700, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0692715644836426, "global_step": 583701, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.102585792541504, "global_step": 583702, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0347931385040283, "global_step": 583703, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9677561521530151, "global_step": 583704, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.024437665939331, "global_step": 583705, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.994917392730713, "global_step": 583706, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.987164855003357, "global_step": 583707, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9957692623138428, "global_step": 583708, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9772669076919556, "global_step": 583709, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9536782503128052, "global_step": 583710, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9820489883422852, "global_step": 583711, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.030604600906372, "global_step": 583712, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.893677830696106, "global_step": 583713, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.068787097930908, "global_step": 583714, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.054720401763916, "global_step": 583715, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9995291233062744, "global_step": 583716, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9797929525375366, "global_step": 583717, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0563838481903076, "global_step": 583718, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.968135118484497, "global_step": 583719, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.988890290260315, "global_step": 583720, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.001202344894409, "global_step": 583721, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0291249752044678, "global_step": 583722, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9703713655471802, "global_step": 583723, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.103389263153076, "global_step": 583724, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0463976860046387, "global_step": 583725, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9141230583190918, "global_step": 583726, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0368945598602295, "global_step": 583727, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9984564781188965, "global_step": 583728, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9525550603866577, "global_step": 583729, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.014197587966919, "global_step": 583730, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9466561079025269, "global_step": 583731, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0619406700134277, "global_step": 583732, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.003096580505371, "global_step": 583733, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.061488628387451, "global_step": 583734, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.003953218460083, "global_step": 583735, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0768661499023438, "global_step": 583736, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0847997665405273, "global_step": 583737, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0600404739379883, "global_step": 583738, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0994598865509033, "global_step": 583739, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0371193885803223, "global_step": 583740, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0612497329711914, "global_step": 583741, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.068135976791382, "global_step": 583742, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9854978322982788, "global_step": 583743, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9494367837905884, "global_step": 583744, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.07731556892395, "global_step": 583745, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0830514430999756, "global_step": 583746, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.026167869567871, "global_step": 583747, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0207321643829346, "global_step": 583748, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0141279697418213, "global_step": 583749, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.056049346923828, "global_step": 583750, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9971011877059937, "global_step": 583751, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.02803373336792, "global_step": 583752, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.020615339279175, "global_step": 583753, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0827348232269287, "global_step": 583754, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.004733085632324, "global_step": 583755, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0404186248779297, "global_step": 583756, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.014495372772217, "global_step": 583757, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9736851453781128, "global_step": 583758, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.053417444229126, "global_step": 583759, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.021225690841675, "global_step": 583760, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.8966785669326782, "global_step": 583761, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0211403369903564, "global_step": 583762, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.914984107017517, "global_step": 583763, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.051368236541748, "global_step": 583764, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.967514991760254, "global_step": 583765, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.010028839111328, "global_step": 583766, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9850776195526123, "global_step": 583767, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9657225608825684, "global_step": 583768, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.976814866065979, "global_step": 583769, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.111954689025879, "global_step": 583770, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9544636011123657, "global_step": 583771, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9966331720352173, "global_step": 583772, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.053806781768799, "global_step": 583773, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.003028631210327, "global_step": 583774, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.011014938354492, "global_step": 583775, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0554087162017822, "global_step": 583776, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9627679586410522, "global_step": 583777, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9799988269805908, "global_step": 583778, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0630953311920166, "global_step": 583779, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.048740863800049, "global_step": 583780, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0468544960021973, "global_step": 583781, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0110867023468018, "global_step": 583782, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0003437995910645, "global_step": 583783, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0128817558288574, "global_step": 583784, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0130093097686768, "global_step": 583785, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9856035709381104, "global_step": 583786, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.069164752960205, "global_step": 583787, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0066986083984375, "global_step": 583788, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9373254776000977, "global_step": 583789, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.077728509902954, "global_step": 583790, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0575954914093018, "global_step": 583791, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0506927967071533, "global_step": 583792, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9953055381774902, "global_step": 583793, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.041698455810547, "global_step": 583794, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.999732255935669, "global_step": 583795, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9816545248031616, "global_step": 583796, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.014852285385132, "global_step": 583797, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0266685485839844, "global_step": 583798, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9941766262054443, "global_step": 583799, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0180611610412598, "global_step": 583800, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.017942428588867, "global_step": 583801, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.994831919670105, "global_step": 583802, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.062837839126587, "global_step": 583803, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9617586135864258, "global_step": 583804, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0258288383483887, "global_step": 583805, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9891308546066284, "global_step": 583806, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9899654388427734, "global_step": 583807, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9874606132507324, "global_step": 583808, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9947246313095093, "global_step": 583809, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0305309295654297, "global_step": 583810, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0721607208251953, "global_step": 583811, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.989670991897583, "global_step": 583812, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1153359413146973, "global_step": 583813, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.046891212463379, "global_step": 583814, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.088615894317627, "global_step": 583815, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.000415086746216, "global_step": 583816, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9830355644226074, "global_step": 583817, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.030298948287964, "global_step": 583818, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9936152696609497, "global_step": 583819, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1138105392456055, "global_step": 583820, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0514566898345947, "global_step": 583821, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.089218854904175, "global_step": 583822, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9761316776275635, "global_step": 583823, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.054816484451294, "global_step": 583824, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.085925817489624, "global_step": 583825, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.050910472869873, "global_step": 583826, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0466718673706055, "global_step": 583827, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.991431713104248, "global_step": 583828, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.047175407409668, "global_step": 583829, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0212063789367676, "global_step": 583830, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0106265544891357, "global_step": 583831, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9966249465942383, "global_step": 583832, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0175583362579346, "global_step": 583833, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0171260833740234, "global_step": 583834, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.001455545425415, "global_step": 583835, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9820829629898071, "global_step": 583836, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.113898992538452, "global_step": 583837, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0700345039367676, "global_step": 583838, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.96660578250885, "global_step": 583839, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0343668460845947, "global_step": 583840, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.017580270767212, "global_step": 583841, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0374646186828613, "global_step": 583842, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9376022815704346, "global_step": 583843, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9752874374389648, "global_step": 583844, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9782068729400635, "global_step": 583845, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9649535417556763, "global_step": 583846, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.077082633972168, "global_step": 583847, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0302610397338867, "global_step": 583848, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9990062713623047, "global_step": 583849, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0270309448242188, "global_step": 583850, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9053725004196167, "global_step": 583851, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9516328573226929, "global_step": 583852, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9817349910736084, "global_step": 583853, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9607138633728027, "global_step": 583854, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.009488821029663, "global_step": 583855, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0424890518188477, "global_step": 583856, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0797677040100098, "global_step": 583857, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0679445266723633, "global_step": 583858, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9922068119049072, "global_step": 583859, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0778040885925293, "global_step": 583860, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1413915157318115, "global_step": 583861, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9555377960205078, "global_step": 583862, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.030602216720581, "global_step": 583863, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.036527395248413, "global_step": 583864, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.03460431098938, "global_step": 583865, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0261597633361816, "global_step": 583866, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9976924657821655, "global_step": 583867, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9725735187530518, "global_step": 583868, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9945591688156128, "global_step": 583869, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.018069267272949, "global_step": 583870, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.068876266479492, "global_step": 583871, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9922027587890625, "global_step": 583872, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0534133911132812, "global_step": 583873, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.019310235977173, "global_step": 583874, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0118308067321777, "global_step": 583875, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0166220664978027, "global_step": 583876, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0071310997009277, "global_step": 583877, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.00563645362854, "global_step": 583878, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.013033628463745, "global_step": 583879, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9815524816513062, "global_step": 583880, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.103724241256714, "global_step": 583881, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9975125789642334, "global_step": 583882, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9418796300888062, "global_step": 583883, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9686827659606934, "global_step": 583884, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.02982759475708, "global_step": 583885, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0327651500701904, "global_step": 583886, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.017766237258911, "global_step": 583887, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0349185466766357, "global_step": 583888, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0370261669158936, "global_step": 583889, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.005305290222168, "global_step": 583890, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1549999713897705, "global_step": 583891, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.029797077178955, "global_step": 583892, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.991799235343933, "global_step": 583893, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9564603567123413, "global_step": 583894, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.078252077102661, "global_step": 583895, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.058424472808838, "global_step": 583896, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9724442958831787, "global_step": 583897, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.983799695968628, "global_step": 583898, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9809404611587524, "global_step": 583899, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0354726314544678, "global_step": 583900, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9640674591064453, "global_step": 583901, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0540151596069336, "global_step": 583902, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.067718029022217, "global_step": 583903, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.07889461517334, "global_step": 583904, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0664100646972656, "global_step": 583905, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.075347900390625, "global_step": 583906, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0938830375671387, "global_step": 583907, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0082554817199707, "global_step": 583908, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.967492938041687, "global_step": 583909, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0565550327301025, "global_step": 583910, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.080077648162842, "global_step": 583911, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9123636484146118, "global_step": 583912, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9477028846740723, "global_step": 583913, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.99857759475708, "global_step": 583914, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9666533470153809, "global_step": 583915, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0533318519592285, "global_step": 583916, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9565104246139526, "global_step": 583917, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.928836703300476, "global_step": 583918, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9460886716842651, "global_step": 583919, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.002883195877075, "global_step": 583920, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0758984088897705, "global_step": 583921, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0016491413116455, "global_step": 583922, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9776629209518433, "global_step": 583923, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.009368658065796, "global_step": 583924, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.958565592765808, "global_step": 583925, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9973747730255127, "global_step": 583926, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0359058380126953, "global_step": 583927, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.911389946937561, "global_step": 583928, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.03688907623291, "global_step": 583929, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0071518421173096, "global_step": 583930, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0628714561462402, "global_step": 583931, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0581018924713135, "global_step": 583932, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0353662967681885, "global_step": 583933, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.07755184173584, "global_step": 583934, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0898191928863525, "global_step": 583935, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.059478759765625, "global_step": 583936, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0285134315490723, "global_step": 583937, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.000974178314209, "global_step": 583938, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.023463249206543, "global_step": 583939, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0292725563049316, "global_step": 583940, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0322530269622803, "global_step": 583941, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0057129859924316, "global_step": 583942, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0166361331939697, "global_step": 583943, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0723657608032227, "global_step": 583944, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9971024990081787, "global_step": 583945, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0183777809143066, "global_step": 583946, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0399763584136963, "global_step": 583947, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9962671995162964, "global_step": 583948, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0981087684631348, "global_step": 583949, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0053932666778564, "global_step": 583950, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9570045471191406, "global_step": 583951, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.093764066696167, "global_step": 583952, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.040431499481201, "global_step": 583953, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9754576683044434, "global_step": 583954, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.062861204147339, "global_step": 583955, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.00282883644104, "global_step": 583956, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0583295822143555, "global_step": 583957, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.939540982246399, "global_step": 583958, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0513386726379395, "global_step": 583959, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0247647762298584, "global_step": 583960, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.028409242630005, "global_step": 583961, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.00286865234375, "global_step": 583962, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9987326860427856, "global_step": 583963, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1243066787719727, "global_step": 583964, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9451016187667847, "global_step": 583965, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.058645009994507, "global_step": 583966, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9309561252593994, "global_step": 583967, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.011172294616699, "global_step": 583968, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.044312000274658, "global_step": 583969, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0138657093048096, "global_step": 583970, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.044079065322876, "global_step": 583971, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9471409320831299, "global_step": 583972, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0003082752227783, "global_step": 583973, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0264594554901123, "global_step": 583974, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.037137985229492, "global_step": 583975, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9657566547393799, "global_step": 583976, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9477201700210571, "global_step": 583977, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0142340660095215, "global_step": 583978, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0283095836639404, "global_step": 583979, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0371105670928955, "global_step": 583980, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9758718013763428, "global_step": 583981, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.05194354057312, "global_step": 583982, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9714456796646118, "global_step": 583983, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0769240856170654, "global_step": 583984, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9557719230651855, "global_step": 583985, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.033020257949829, "global_step": 583986, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.11434006690979, "global_step": 583987, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.037414312362671, "global_step": 583988, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1952292919158936, "global_step": 583989, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.011295795440674, "global_step": 583990, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9819105863571167, "global_step": 583991, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0067548751831055, "global_step": 583992, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0580387115478516, "global_step": 583993, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9438222646713257, "global_step": 583994, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9955121278762817, "global_step": 583995, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0054972171783447, "global_step": 583996, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0812034606933594, "global_step": 583997, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9402470588684082, "global_step": 583998, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9706284999847412, "global_step": 583999, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9946492910385132, "global_step": 584000, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.023853302001953, "global_step": 584001, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9416887760162354, "global_step": 584002, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0182652473449707, "global_step": 584003, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0729000568389893, "global_step": 584004, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0340237617492676, "global_step": 584005, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0251879692077637, "global_step": 584006, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.027716636657715, "global_step": 584007, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0185468196868896, "global_step": 584008, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9904801845550537, "global_step": 584009, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.003600835800171, "global_step": 584010, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.952609658241272, "global_step": 584011, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9278154373168945, "global_step": 584012, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9973549842834473, "global_step": 584013, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9440016746520996, "global_step": 584014, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1028501987457275, "global_step": 584015, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0062830448150635, "global_step": 584016, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9731941223144531, "global_step": 584017, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.053550958633423, "global_step": 584018, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0355095863342285, "global_step": 584019, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9739357233047485, "global_step": 584020, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0123839378356934, "global_step": 584021, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9680424928665161, "global_step": 584022, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0064942836761475, "global_step": 584023, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.051723003387451, "global_step": 584024, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0483529567718506, "global_step": 584025, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9468368291854858, "global_step": 584026, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.062873601913452, "global_step": 584027, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.064282178878784, "global_step": 584028, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.040226936340332, "global_step": 584029, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1371939182281494, "global_step": 584030, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.105118751525879, "global_step": 584031, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.979515552520752, "global_step": 584032, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.990279197692871, "global_step": 584033, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9797066450119019, "global_step": 584034, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.071394443511963, "global_step": 584035, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0095980167388916, "global_step": 584036, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0403928756713867, "global_step": 584037, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.975078821182251, "global_step": 584038, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.063295841217041, "global_step": 584039, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1236460208892822, "global_step": 584040, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.040339231491089, "global_step": 584041, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.044438600540161, "global_step": 584042, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0280394554138184, "global_step": 584043, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.008942127227783, "global_step": 584044, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.108893394470215, "global_step": 584045, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.007256507873535, "global_step": 584046, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0258846282958984, "global_step": 584047, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1067235469818115, "global_step": 584048, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0234644412994385, "global_step": 584049, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.009953498840332, "global_step": 584050, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0587170124053955, "global_step": 584051, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0108203887939453, "global_step": 584052, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0475902557373047, "global_step": 584053, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9952623844146729, "global_step": 584054, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9513298273086548, "global_step": 584055, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0159037113189697, "global_step": 584056, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.069697856903076, "global_step": 584057, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0514636039733887, "global_step": 584058, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.05045747756958, "global_step": 584059, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.064803123474121, "global_step": 584060, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0329697132110596, "global_step": 584061, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.002706527709961, "global_step": 584062, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0155105590820312, "global_step": 584063, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.102679491043091, "global_step": 584064, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9482409954071045, "global_step": 584065, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9817614555358887, "global_step": 584066, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0630784034729004, "global_step": 584067, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0762274265289307, "global_step": 584068, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1092746257781982, "global_step": 584069, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.090181827545166, "global_step": 584070, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.026418447494507, "global_step": 584071, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0203399658203125, "global_step": 584072, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.009812593460083, "global_step": 584073, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9781502485275269, "global_step": 584074, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.969455599784851, "global_step": 584075, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9669190645217896, "global_step": 584076, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.990886926651001, "global_step": 584077, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.004370927810669, "global_step": 584078, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0570859909057617, "global_step": 584079, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9765156507492065, "global_step": 584080, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0089926719665527, "global_step": 584081, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0839710235595703, "global_step": 584082, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.011822462081909, "global_step": 584083, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0417332649230957, "global_step": 584084, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9844175577163696, "global_step": 584085, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9573180675506592, "global_step": 584086, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0184710025787354, "global_step": 584087, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0390496253967285, "global_step": 584088, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.021979808807373, "global_step": 584089, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0320303440093994, "global_step": 584090, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.050422191619873, "global_step": 584091, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.026845932006836, "global_step": 584092, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.968984842300415, "global_step": 584093, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.979688048362732, "global_step": 584094, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9928483963012695, "global_step": 584095, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0424461364746094, "global_step": 584096, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.019584894180298, "global_step": 584097, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0686395168304443, "global_step": 584098, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0434486865997314, "global_step": 584099, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.052903652191162, "global_step": 584100, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0171594619750977, "global_step": 584101, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0576767921447754, "global_step": 584102, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0616190433502197, "global_step": 584103, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.015504837036133, "global_step": 584104, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0348575115203857, "global_step": 584105, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0252597332000732, "global_step": 584106, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9562597274780273, "global_step": 584107, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9758228063583374, "global_step": 584108, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0225305557250977, "global_step": 584109, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.949540376663208, "global_step": 584110, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.8807518482208252, "global_step": 584111, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.013352155685425, "global_step": 584112, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.02838397026062, "global_step": 584113, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.022657632827759, "global_step": 584114, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0556485652923584, "global_step": 584115, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.048807144165039, "global_step": 584116, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.038477897644043, "global_step": 584117, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.063753366470337, "global_step": 584118, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.053600311279297, "global_step": 584119, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0956287384033203, "global_step": 584120, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0633630752563477, "global_step": 584121, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0858259201049805, "global_step": 584122, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0384349822998047, "global_step": 584123, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.03808856010437, "global_step": 584124, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.043238878250122, "global_step": 584125, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0301625728607178, "global_step": 584126, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.052300214767456, "global_step": 584127, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0533809661865234, "global_step": 584128, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0328235626220703, "global_step": 584129, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0285120010375977, "global_step": 584130, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.990071177482605, "global_step": 584131, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.962121844291687, "global_step": 584132, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0817511081695557, "global_step": 584133, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0048184394836426, "global_step": 584134, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9730780124664307, "global_step": 584135, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.034364700317383, "global_step": 584136, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0663208961486816, "global_step": 584137, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0236995220184326, "global_step": 584138, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0452122688293457, "global_step": 584139, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0362696647644043, "global_step": 584140, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9856609106063843, "global_step": 584141, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.049989938735962, "global_step": 584142, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9558168649673462, "global_step": 584143, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0981531143188477, "global_step": 584144, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.107637405395508, "global_step": 584145, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0153965950012207, "global_step": 584146, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0394845008850098, "global_step": 584147, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.023998260498047, "global_step": 584148, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.962094783782959, "global_step": 584149, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0119142532348633, "global_step": 584150, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0666275024414062, "global_step": 584151, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0371487140655518, "global_step": 584152, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0649166107177734, "global_step": 584153, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.014585018157959, "global_step": 584154, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9755715131759644, "global_step": 584155, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.031811475753784, "global_step": 584156, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.087310791015625, "global_step": 584157, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9658854007720947, "global_step": 584158, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9079617261886597, "global_step": 584159, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.125382900238037, "global_step": 584160, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9837534427642822, "global_step": 584161, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.091161012649536, "global_step": 584162, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0437119007110596, "global_step": 584163, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.137716770172119, "global_step": 584164, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9691320657730103, "global_step": 584165, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0525591373443604, "global_step": 584166, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0604426860809326, "global_step": 584167, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.103381633758545, "global_step": 584168, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.062030076980591, "global_step": 584169, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.020627498626709, "global_step": 584170, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.094892740249634, "global_step": 584171, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9580073356628418, "global_step": 584172, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.980960726737976, "global_step": 584173, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.038353681564331, "global_step": 584174, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.011013984680176, "global_step": 584175, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0550296306610107, "global_step": 584176, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.071373462677002, "global_step": 584177, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0154340267181396, "global_step": 584178, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.011146068572998, "global_step": 584179, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.98639976978302, "global_step": 584180, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0207626819610596, "global_step": 584181, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0605344772338867, "global_step": 584182, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0333616733551025, "global_step": 584183, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9888721704483032, "global_step": 584184, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0421016216278076, "global_step": 584185, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9319748878479004, "global_step": 584186, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9908130168914795, "global_step": 584187, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0428314208984375, "global_step": 584188, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.946920394897461, "global_step": 584189, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.068666934967041, "global_step": 584190, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0795300006866455, "global_step": 584191, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0316615104675293, "global_step": 584192, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0404114723205566, "global_step": 584193, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9976168870925903, "global_step": 584194, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0034544467926025, "global_step": 584195, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.081299066543579, "global_step": 584196, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0292718410491943, "global_step": 584197, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0115115642547607, "global_step": 584198, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0663673877716064, "global_step": 584199, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.018610715866089, "global_step": 584200, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9436801671981812, "global_step": 584201, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0290184020996094, "global_step": 584202, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.088087558746338, "global_step": 584203, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0759127140045166, "global_step": 584204, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9535194635391235, "global_step": 584205, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9819495677947998, "global_step": 584206, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0052742958068848, "global_step": 584207, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.99911367893219, "global_step": 584208, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.020845890045166, "global_step": 584209, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0283830165863037, "global_step": 584210, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.001938581466675, "global_step": 584211, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0365724563598633, "global_step": 584212, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9365452527999878, "global_step": 584213, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.093961477279663, "global_step": 584214, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.028517246246338, "global_step": 584215, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.001481294631958, "global_step": 584216, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0593438148498535, "global_step": 584217, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9728846549987793, "global_step": 584218, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9441626071929932, "global_step": 584219, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9471347332000732, "global_step": 584220, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.976691722869873, "global_step": 584221, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0573482513427734, "global_step": 584222, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0584654808044434, "global_step": 584223, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9655154943466187, "global_step": 584224, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.037433385848999, "global_step": 584225, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9721078872680664, "global_step": 584226, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1065196990966797, "global_step": 584227, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0754215717315674, "global_step": 584228, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.051015853881836, "global_step": 584229, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.981094479560852, "global_step": 584230, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9787013530731201, "global_step": 584231, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9376881122589111, "global_step": 584232, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9855228662490845, "global_step": 584233, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0068650245666504, "global_step": 584234, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1004140377044678, "global_step": 584235, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9879084825515747, "global_step": 584236, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0669171810150146, "global_step": 584237, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9487566947937012, "global_step": 584238, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0289344787597656, "global_step": 584239, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0339183807373047, "global_step": 584240, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.142824649810791, "global_step": 584241, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0342276096343994, "global_step": 584242, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.062899112701416, "global_step": 584243, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9857715368270874, "global_step": 584244, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9398056268692017, "global_step": 584245, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0468971729278564, "global_step": 584246, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0130982398986816, "global_step": 584247, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9616141319274902, "global_step": 584248, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0832531452178955, "global_step": 584249, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0155434608459473, "global_step": 584250, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9976288080215454, "global_step": 584251, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9727696180343628, "global_step": 584252, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9490374326705933, "global_step": 584253, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.004488229751587, "global_step": 584254, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.972089409828186, "global_step": 584255, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.024661064147949, "global_step": 584256, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.002033233642578, "global_step": 584257, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.064307451248169, "global_step": 584258, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0184242725372314, "global_step": 584259, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0299625396728516, "global_step": 584260, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0630271434783936, "global_step": 584261, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.925101399421692, "global_step": 584262, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.074841260910034, "global_step": 584263, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.004232168197632, "global_step": 584264, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.017388343811035, "global_step": 584265, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9454329013824463, "global_step": 584266, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0306475162506104, "global_step": 584267, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9852566719055176, "global_step": 584268, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0865087509155273, "global_step": 584269, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9519343376159668, "global_step": 584270, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9501739740371704, "global_step": 584271, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9797956943511963, "global_step": 584272, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0427045822143555, "global_step": 584273, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9615665674209595, "global_step": 584274, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.987352728843689, "global_step": 584275, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.988158106803894, "global_step": 584276, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0026605129241943, "global_step": 584277, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.004929542541504, "global_step": 584278, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0641133785247803, "global_step": 584279, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0264899730682373, "global_step": 584280, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0198464393615723, "global_step": 584281, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0278329849243164, "global_step": 584282, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9545211791992188, "global_step": 584283, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0523767471313477, "global_step": 584284, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.943547248840332, "global_step": 584285, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.018190383911133, "global_step": 584286, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.994524598121643, "global_step": 584287, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9942468404769897, "global_step": 584288, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.104628324508667, "global_step": 584289, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.063156843185425, "global_step": 584290, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.02673602104187, "global_step": 584291, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.04067063331604, "global_step": 584292, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.001112699508667, "global_step": 584293, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0145559310913086, "global_step": 584294, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0062789916992188, "global_step": 584295, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1033935546875, "global_step": 584296, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9886525869369507, "global_step": 584297, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9721543788909912, "global_step": 584298, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0508909225463867, "global_step": 584299, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.065772771835327, "global_step": 584300, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9925585985183716, "global_step": 584301, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0618231296539307, "global_step": 584302, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9591633081436157, "global_step": 584303, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.991491436958313, "global_step": 584304, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0075318813323975, "global_step": 584305, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9985458850860596, "global_step": 584306, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.028122663497925, "global_step": 584307, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.937540888786316, "global_step": 584308, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0136687755584717, "global_step": 584309, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9999909400939941, "global_step": 584310, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0835587978363037, "global_step": 584311, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9921826124191284, "global_step": 584312, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.901247501373291, "global_step": 584313, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.047560214996338, "global_step": 584314, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.985687494277954, "global_step": 584315, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0441651344299316, "global_step": 584316, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9741183519363403, "global_step": 584317, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0793838500976562, "global_step": 584318, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0422298908233643, "global_step": 584319, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.037477731704712, "global_step": 584320, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9452338218688965, "global_step": 584321, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.009286880493164, "global_step": 584322, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0522561073303223, "global_step": 584323, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.049375057220459, "global_step": 584324, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.05576229095459, "global_step": 584325, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0121982097625732, "global_step": 584326, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0105016231536865, "global_step": 584327, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0256187915802, "global_step": 584328, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0090348720550537, "global_step": 584329, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0869035720825195, "global_step": 584330, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.132406711578369, "global_step": 584331, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9964717626571655, "global_step": 584332, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0206689834594727, "global_step": 584333, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.072770595550537, "global_step": 584334, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0225110054016113, "global_step": 584335, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.092820882797241, "global_step": 584336, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.118490695953369, "global_step": 584337, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0236167907714844, "global_step": 584338, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0668606758117676, "global_step": 584339, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.086838722229004, "global_step": 584340, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.099844455718994, "global_step": 584341, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0447897911071777, "global_step": 584342, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9985181093215942, "global_step": 584343, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9480249881744385, "global_step": 584344, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.998168706893921, "global_step": 584345, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0073893070220947, "global_step": 584346, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9695346355438232, "global_step": 584347, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.018068313598633, "global_step": 584348, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9971287250518799, "global_step": 584349, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.900327444076538, "global_step": 584350, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.10518217086792, "global_step": 584351, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.084606885910034, "global_step": 584352, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9828068017959595, "global_step": 584353, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9797091484069824, "global_step": 584354, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9790637493133545, "global_step": 584355, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.044949769973755, "global_step": 584356, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.998918890953064, "global_step": 584357, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.966100811958313, "global_step": 584358, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0426571369171143, "global_step": 584359, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0574729442596436, "global_step": 584360, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0043156147003174, "global_step": 584361, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.119260311126709, "global_step": 584362, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0205836296081543, "global_step": 584363, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9691734313964844, "global_step": 584364, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0074868202209473, "global_step": 584365, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.031351327896118, "global_step": 584366, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0725297927856445, "global_step": 584367, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.037461280822754, "global_step": 584368, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0030181407928467, "global_step": 584369, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.963986873626709, "global_step": 584370, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0137059688568115, "global_step": 584371, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1616415977478027, "global_step": 584372, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9821093082427979, "global_step": 584373, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0034825801849365, "global_step": 584374, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9716835021972656, "global_step": 584375, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0754175186157227, "global_step": 584376, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9644664525985718, "global_step": 584377, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0116117000579834, "global_step": 584378, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9936741590499878, "global_step": 584379, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9257501363754272, "global_step": 584380, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.051413059234619, "global_step": 584381, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9954307079315186, "global_step": 584382, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9780781269073486, "global_step": 584383, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.089832067489624, "global_step": 584384, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0694875717163086, "global_step": 584385, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0469048023223877, "global_step": 584386, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.017747640609741, "global_step": 584387, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0369720458984375, "global_step": 584388, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.009268045425415, "global_step": 584389, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0418460369110107, "global_step": 584390, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9817460775375366, "global_step": 584391, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1411027908325195, "global_step": 584392, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.969032883644104, "global_step": 584393, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.034064531326294, "global_step": 584394, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.007378339767456, "global_step": 584395, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.001856803894043, "global_step": 584396, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0913748741149902, "global_step": 584397, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0046656131744385, "global_step": 584398, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.920006513595581, "global_step": 584399, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9880393743515015, "global_step": 584400, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.018876791000366, "global_step": 584401, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.047478437423706, "global_step": 584402, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0067617893218994, "global_step": 584403, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0996174812316895, "global_step": 584404, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0414865016937256, "global_step": 584405, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9682432413101196, "global_step": 584406, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.976609468460083, "global_step": 584407, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.010148525238037, "global_step": 584408, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0150363445281982, "global_step": 584409, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9774848222732544, "global_step": 584410, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9652996063232422, "global_step": 584411, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0727765560150146, "global_step": 584412, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.022305727005005, "global_step": 584413, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9860546588897705, "global_step": 584414, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9792571067810059, "global_step": 584415, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9425104856491089, "global_step": 584416, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0440168380737305, "global_step": 584417, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.015650987625122, "global_step": 584418, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.1017630100250244, "global_step": 584419, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0446767807006836, "global_step": 584420, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.02107834815979, "global_step": 584421, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9838106632232666, "global_step": 584422, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.977067470550537, "global_step": 584423, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9800505638122559, "global_step": 584424, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9823644161224365, "global_step": 584425, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.051032543182373, "global_step": 584426, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0160441398620605, "global_step": 584427, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.926048755645752, "global_step": 584428, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0055465698242188, "global_step": 584429, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9947322607040405, "global_step": 584430, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9281580448150635, "global_step": 584431, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.0418620109558105, "global_step": 584432, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.994172215461731, "global_step": 584433, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9982130527496338, "global_step": 584434, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9421473741531372, "global_step": 584435, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.08890700340271, "global_step": 584436, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.9669407606124878, "global_step": 584437, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.047975778579712, "global_step": 584438, "epoch": 952, "lr": 5e-05}
{"train_loss": 2.018141269683838, "global_step": 584439, "epoch": 952, "lr": 5e-05}
{"train_loss": 1.8806086778640747, "global_step": 584440, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0705835819244385, "global_step": 584441, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.039498805999756, "global_step": 584442, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0493862628936768, "global_step": 584443, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9808058738708496, "global_step": 584444, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9854652881622314, "global_step": 584445, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.035947322845459, "global_step": 584446, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0187606811523438, "global_step": 584447, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0226266384124756, "global_step": 584448, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9813060760498047, "global_step": 584449, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9490690231323242, "global_step": 584450, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.019024610519409, "global_step": 584451, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0236265659332275, "global_step": 584452, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.025482654571533, "global_step": 584453, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.038325786590576, "global_step": 584454, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.012153148651123, "global_step": 584455, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9876536130905151, "global_step": 584456, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0603408813476562, "global_step": 584457, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9812216758728027, "global_step": 584458, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9951938390731812, "global_step": 584459, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1033637523651123, "global_step": 584460, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.034323215484619, "global_step": 584461, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9911248683929443, "global_step": 584462, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.032611131668091, "global_step": 584463, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.058701992034912, "global_step": 584464, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0561256408691406, "global_step": 584465, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.086698293685913, "global_step": 584466, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9625167846679688, "global_step": 584467, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0592997074127197, "global_step": 584468, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.013795852661133, "global_step": 584469, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9838045835494995, "global_step": 584470, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.027942657470703, "global_step": 584471, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9123378992080688, "global_step": 584472, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.01832914352417, "global_step": 584473, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.8847311735153198, "global_step": 584474, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.904403805732727, "global_step": 584475, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.067350149154663, "global_step": 584476, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9303172826766968, "global_step": 584477, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9546794891357422, "global_step": 584478, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9683876037597656, "global_step": 584479, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.004039764404297, "global_step": 584480, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0453577041625977, "global_step": 584481, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9670166969299316, "global_step": 584482, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.96821928024292, "global_step": 584483, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9123613834381104, "global_step": 584484, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9533394575119019, "global_step": 584485, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.067124366760254, "global_step": 584486, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9248573780059814, "global_step": 584487, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.022305488586426, "global_step": 584488, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0095362663269043, "global_step": 584489, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9354784488677979, "global_step": 584490, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0663034915924072, "global_step": 584491, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9722384214401245, "global_step": 584492, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.976395845413208, "global_step": 584493, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9816184043884277, "global_step": 584494, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9619752168655396, "global_step": 584495, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0560500621795654, "global_step": 584496, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.050147771835327, "global_step": 584497, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.8878589868545532, "global_step": 584498, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0534260272979736, "global_step": 584499, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0096335411071777, "global_step": 584500, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.016494035720825, "global_step": 584501, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9416521787643433, "global_step": 584502, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.011119842529297, "global_step": 584503, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.019688844680786, "global_step": 584504, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.050102472305298, "global_step": 584505, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0016684532165527, "global_step": 584506, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.130582809448242, "global_step": 584507, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.007349729537964, "global_step": 584508, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.007209300994873, "global_step": 584509, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.004007339477539, "global_step": 584510, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0037715435028076, "global_step": 584511, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0317296981811523, "global_step": 584512, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9737701416015625, "global_step": 584513, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.995901346206665, "global_step": 584514, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0418310165405273, "global_step": 584515, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9853935241699219, "global_step": 584516, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0005910396575928, "global_step": 584517, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0267128944396973, "global_step": 584518, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9950982332229614, "global_step": 584519, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0768256187438965, "global_step": 584520, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9962042570114136, "global_step": 584521, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0414257049560547, "global_step": 584522, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1274237632751465, "global_step": 584523, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9960025548934937, "global_step": 584524, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.070605516433716, "global_step": 584525, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.944171667098999, "global_step": 584526, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0556681156158447, "global_step": 584527, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9679726362228394, "global_step": 584528, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9728214740753174, "global_step": 584529, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9238594770431519, "global_step": 584530, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.980604648590088, "global_step": 584531, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9997272491455078, "global_step": 584532, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0018343925476074, "global_step": 584533, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9354796409606934, "global_step": 584534, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9562201499938965, "global_step": 584535, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9414796829223633, "global_step": 584536, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.007465362548828, "global_step": 584537, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.029170274734497, "global_step": 584538, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.097372055053711, "global_step": 584539, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9936972856521606, "global_step": 584540, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.063049554824829, "global_step": 584541, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.006260871887207, "global_step": 584542, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9581931829452515, "global_step": 584543, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.006842851638794, "global_step": 584544, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.948221206665039, "global_step": 584545, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9935235977172852, "global_step": 584546, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.034773588180542, "global_step": 584547, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9748163223266602, "global_step": 584548, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.000075340270996, "global_step": 584549, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0103344917297363, "global_step": 584550, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0936174392700195, "global_step": 584551, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9739938974380493, "global_step": 584552, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0171103477478027, "global_step": 584553, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0274407863616943, "global_step": 584554, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9632874727249146, "global_step": 584555, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0377721786499023, "global_step": 584556, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9965919256210327, "global_step": 584557, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.034789562225342, "global_step": 584558, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9979972839355469, "global_step": 584559, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.011739730834961, "global_step": 584560, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.036782741546631, "global_step": 584561, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0141866207122803, "global_step": 584562, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9851998090744019, "global_step": 584563, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9656236171722412, "global_step": 584564, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9068793058395386, "global_step": 584565, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1588780879974365, "global_step": 584566, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9863665103912354, "global_step": 584567, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.095187187194824, "global_step": 584568, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1205203533172607, "global_step": 584569, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0194883346557617, "global_step": 584570, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0020952224731445, "global_step": 584571, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9676445722579956, "global_step": 584572, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.951699137687683, "global_step": 584573, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0305263996124268, "global_step": 584574, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.055907726287842, "global_step": 584575, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.969636082649231, "global_step": 584576, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.002720594406128, "global_step": 584577, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.908165693283081, "global_step": 584578, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0338692665100098, "global_step": 584579, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9027652740478516, "global_step": 584580, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.010253667831421, "global_step": 584581, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0511021614074707, "global_step": 584582, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0312347412109375, "global_step": 584583, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0031518936157227, "global_step": 584584, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9483879804611206, "global_step": 584585, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9593523740768433, "global_step": 584586, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.009666919708252, "global_step": 584587, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9771556854248047, "global_step": 584588, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0241856575012207, "global_step": 584589, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0517680644989014, "global_step": 584590, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0528361797332764, "global_step": 584591, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9630144834518433, "global_step": 584592, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.96728515625, "global_step": 584593, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.038703441619873, "global_step": 584594, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.024071216583252, "global_step": 584595, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.975600242614746, "global_step": 584596, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.046788454055786, "global_step": 584597, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0714080333709717, "global_step": 584598, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.061617612838745, "global_step": 584599, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9820103645324707, "global_step": 584600, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.096222400665283, "global_step": 584601, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1257214546203613, "global_step": 584602, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0256571769714355, "global_step": 584603, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0540084838867188, "global_step": 584604, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0190277099609375, "global_step": 584605, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9980568885803223, "global_step": 584606, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0627591609954834, "global_step": 584607, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9905791282653809, "global_step": 584608, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.970514178276062, "global_step": 584609, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.04123854637146, "global_step": 584610, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0233852863311768, "global_step": 584611, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.079017400741577, "global_step": 584612, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9687579870224, "global_step": 584613, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0483670234680176, "global_step": 584614, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1084837913513184, "global_step": 584615, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0686609745025635, "global_step": 584616, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.016874074935913, "global_step": 584617, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0329067707061768, "global_step": 584618, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0066206455230713, "global_step": 584619, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.023991107940674, "global_step": 584620, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.071873426437378, "global_step": 584621, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9768744707107544, "global_step": 584622, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0204453468322754, "global_step": 584623, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.022858142852783, "global_step": 584624, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.06419038772583, "global_step": 584625, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.979201078414917, "global_step": 584626, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.953167200088501, "global_step": 584627, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0514333248138428, "global_step": 584628, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9384381771087646, "global_step": 584629, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9861961603164673, "global_step": 584630, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.01688551902771, "global_step": 584631, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9989415407180786, "global_step": 584632, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9793498516082764, "global_step": 584633, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.956601619720459, "global_step": 584634, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9682273864746094, "global_step": 584635, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.004063606262207, "global_step": 584636, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.940168023109436, "global_step": 584637, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9755815267562866, "global_step": 584638, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.053678035736084, "global_step": 584639, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.021131992340088, "global_step": 584640, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0076346397399902, "global_step": 584641, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.042654037475586, "global_step": 584642, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.989108920097351, "global_step": 584643, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0225670337677, "global_step": 584644, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0188446044921875, "global_step": 584645, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.048323154449463, "global_step": 584646, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.998515009880066, "global_step": 584647, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.023094654083252, "global_step": 584648, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9658873081207275, "global_step": 584649, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0403387546539307, "global_step": 584650, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9673817157745361, "global_step": 584651, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0545461177825928, "global_step": 584652, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.942840576171875, "global_step": 584653, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.050323009490967, "global_step": 584654, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9730408191680908, "global_step": 584655, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9778010845184326, "global_step": 584656, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0567169189453125, "global_step": 584657, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9749161005020142, "global_step": 584658, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0379128456115723, "global_step": 584659, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.977624773979187, "global_step": 584660, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.003828525543213, "global_step": 584661, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9805365800857544, "global_step": 584662, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9700759649276733, "global_step": 584663, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.076179265975952, "global_step": 584664, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.090045928955078, "global_step": 584665, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.117358684539795, "global_step": 584666, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9663938283920288, "global_step": 584667, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.010157346725464, "global_step": 584668, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9853777885437012, "global_step": 584669, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0503790378570557, "global_step": 584670, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.990451693534851, "global_step": 584671, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.010031223297119, "global_step": 584672, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0089659690856934, "global_step": 584673, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.986432433128357, "global_step": 584674, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.030158519744873, "global_step": 584675, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.975329041481018, "global_step": 584676, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.023291826248169, "global_step": 584677, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.990314245223999, "global_step": 584678, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0265979766845703, "global_step": 584679, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0420053005218506, "global_step": 584680, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0069804191589355, "global_step": 584681, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0159144401550293, "global_step": 584682, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0100157260894775, "global_step": 584683, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0243732929229736, "global_step": 584684, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0187461376190186, "global_step": 584685, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0824379920959473, "global_step": 584686, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.053212881088257, "global_step": 584687, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0546696186065674, "global_step": 584688, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.931579351425171, "global_step": 584689, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9729375839233398, "global_step": 584690, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9619009494781494, "global_step": 584691, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0473639965057373, "global_step": 584692, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.055548667907715, "global_step": 584693, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0358519554138184, "global_step": 584694, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.005368232727051, "global_step": 584695, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0330257415771484, "global_step": 584696, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0822272300720215, "global_step": 584697, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9851202964782715, "global_step": 584698, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9750078916549683, "global_step": 584699, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.959349274635315, "global_step": 584700, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.039530038833618, "global_step": 584701, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0083820819854736, "global_step": 584702, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9917694330215454, "global_step": 584703, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0584638118743896, "global_step": 584704, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.134732961654663, "global_step": 584705, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9986438751220703, "global_step": 584706, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9552444219589233, "global_step": 584707, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.992811679840088, "global_step": 584708, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.991927981376648, "global_step": 584709, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0611090660095215, "global_step": 584710, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.006619691848755, "global_step": 584711, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9862035512924194, "global_step": 584712, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.056145668029785, "global_step": 584713, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.060666084289551, "global_step": 584714, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9469451904296875, "global_step": 584715, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.100468635559082, "global_step": 584716, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0446932315826416, "global_step": 584717, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9786674976348877, "global_step": 584718, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.041456699371338, "global_step": 584719, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.915245771408081, "global_step": 584720, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.009450912475586, "global_step": 584721, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.068056106567383, "global_step": 584722, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.047846794128418, "global_step": 584723, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.038384437561035, "global_step": 584724, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0741705894470215, "global_step": 584725, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0219948291778564, "global_step": 584726, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9712635278701782, "global_step": 584727, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0439319610595703, "global_step": 584728, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.044650077819824, "global_step": 584729, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.964615821838379, "global_step": 584730, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9980204105377197, "global_step": 584731, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0366363525390625, "global_step": 584732, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9412752389907837, "global_step": 584733, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0056560039520264, "global_step": 584734, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9829185009002686, "global_step": 584735, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0209572315216064, "global_step": 584736, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.045724868774414, "global_step": 584737, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9376208782196045, "global_step": 584738, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9761947393417358, "global_step": 584739, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0586211681365967, "global_step": 584740, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1024041175842285, "global_step": 584741, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.10439395904541, "global_step": 584742, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0408072471618652, "global_step": 584743, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.096635580062866, "global_step": 584744, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0214731693267822, "global_step": 584745, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0081822872161865, "global_step": 584746, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9221512079238892, "global_step": 584747, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0026519298553467, "global_step": 584748, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9626952409744263, "global_step": 584749, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.013209581375122, "global_step": 584750, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0199427604675293, "global_step": 584751, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.075295925140381, "global_step": 584752, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.989989995956421, "global_step": 584753, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.103804111480713, "global_step": 584754, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9883546829223633, "global_step": 584755, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0095114707946777, "global_step": 584756, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.019822597503662, "global_step": 584757, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.8426626920700073, "global_step": 584758, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.061471939086914, "global_step": 584759, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9414238929748535, "global_step": 584760, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9826626777648926, "global_step": 584761, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0060040950775146, "global_step": 584762, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.025968074798584, "global_step": 584763, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.092005968093872, "global_step": 584764, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0100796222686768, "global_step": 584765, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.956606149673462, "global_step": 584766, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0387978553771973, "global_step": 584767, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9694105386734009, "global_step": 584768, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.085556983947754, "global_step": 584769, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.090312957763672, "global_step": 584770, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9677072763442993, "global_step": 584771, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0918941497802734, "global_step": 584772, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0309994220733643, "global_step": 584773, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9896321296691895, "global_step": 584774, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9022977352142334, "global_step": 584775, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0214250087738037, "global_step": 584776, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.8966338634490967, "global_step": 584777, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.051077127456665, "global_step": 584778, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9772964715957642, "global_step": 584779, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9927881956100464, "global_step": 584780, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0624289512634277, "global_step": 584781, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0044288635253906, "global_step": 584782, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.099015474319458, "global_step": 584783, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.116666793823242, "global_step": 584784, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9591983556747437, "global_step": 584785, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.07361102104187, "global_step": 584786, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9999892711639404, "global_step": 584787, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1132640838623047, "global_step": 584788, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9760655164718628, "global_step": 584789, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0326480865478516, "global_step": 584790, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0336058139801025, "global_step": 584791, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.001490592956543, "global_step": 584792, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.146482229232788, "global_step": 584793, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9866918325424194, "global_step": 584794, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9800077676773071, "global_step": 584795, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9697927236557007, "global_step": 584796, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1065762042999268, "global_step": 584797, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0156190395355225, "global_step": 584798, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.057724952697754, "global_step": 584799, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.039463520050049, "global_step": 584800, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.044039487838745, "global_step": 584801, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0176186561584473, "global_step": 584802, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9650579690933228, "global_step": 584803, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.975237488746643, "global_step": 584804, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.064544200897217, "global_step": 584805, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9788395166397095, "global_step": 584806, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0118558406829834, "global_step": 584807, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9937368631362915, "global_step": 584808, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.088942527770996, "global_step": 584809, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9704933166503906, "global_step": 584810, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.948158860206604, "global_step": 584811, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9680981636047363, "global_step": 584812, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0871660709381104, "global_step": 584813, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9120845794677734, "global_step": 584814, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9524208307266235, "global_step": 584815, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0687575340270996, "global_step": 584816, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0484554767608643, "global_step": 584817, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0375802516937256, "global_step": 584818, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0956549644470215, "global_step": 584819, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9096101522445679, "global_step": 584820, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9851312637329102, "global_step": 584821, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0858676433563232, "global_step": 584822, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9755958318710327, "global_step": 584823, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0468955039978027, "global_step": 584824, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.13839054107666, "global_step": 584825, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0377562046051025, "global_step": 584826, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9857935905456543, "global_step": 584827, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.038287878036499, "global_step": 584828, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.033245086669922, "global_step": 584829, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9039322137832642, "global_step": 584830, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.089186429977417, "global_step": 584831, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9726333618164062, "global_step": 584832, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9479565620422363, "global_step": 584833, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.986316442489624, "global_step": 584834, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9446704387664795, "global_step": 584835, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9868003129959106, "global_step": 584836, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9922932386398315, "global_step": 584837, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.014716148376465, "global_step": 584838, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.013516426086426, "global_step": 584839, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9945992231369019, "global_step": 584840, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0793044567108154, "global_step": 584841, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.044626235961914, "global_step": 584842, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9439600706100464, "global_step": 584843, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9795082807540894, "global_step": 584844, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0177016258239746, "global_step": 584845, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9797422885894775, "global_step": 584846, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0028934478759766, "global_step": 584847, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0322885513305664, "global_step": 584848, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0804402828216553, "global_step": 584849, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0088951587677, "global_step": 584850, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.072688102722168, "global_step": 584851, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9664113521575928, "global_step": 584852, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9937745332717896, "global_step": 584853, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0744738578796387, "global_step": 584854, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.994063138961792, "global_step": 584855, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9765781164169312, "global_step": 584856, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.031996488571167, "global_step": 584857, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0698797702789307, "global_step": 584858, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1511282920837402, "global_step": 584859, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.068878173828125, "global_step": 584860, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.021078109741211, "global_step": 584861, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0221803188323975, "global_step": 584862, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0295395851135254, "global_step": 584863, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0341899394989014, "global_step": 584864, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.038351058959961, "global_step": 584865, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.092059373855591, "global_step": 584866, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0498015880584717, "global_step": 584867, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.06062912940979, "global_step": 584868, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0560736656188965, "global_step": 584869, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.025346279144287, "global_step": 584870, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.034468412399292, "global_step": 584871, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.972921371459961, "global_step": 584872, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0267624855041504, "global_step": 584873, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0538523197174072, "global_step": 584874, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.05566143989563, "global_step": 584875, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.109576463699341, "global_step": 584876, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.01619553565979, "global_step": 584877, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1502039432525635, "global_step": 584878, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.034062147140503, "global_step": 584879, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.110095739364624, "global_step": 584880, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0567843914031982, "global_step": 584881, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0765037536621094, "global_step": 584882, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0181515216827393, "global_step": 584883, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9930715560913086, "global_step": 584884, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0649235248565674, "global_step": 584885, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.018174648284912, "global_step": 584886, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.007690906524658, "global_step": 584887, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.051790237426758, "global_step": 584888, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9573495388031006, "global_step": 584889, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0709660053253174, "global_step": 584890, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0376555919647217, "global_step": 584891, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.004829168319702, "global_step": 584892, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0487308502197266, "global_step": 584893, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.944524884223938, "global_step": 584894, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.047363042831421, "global_step": 584895, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0578129291534424, "global_step": 584896, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9387357234954834, "global_step": 584897, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0592737197875977, "global_step": 584898, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0408477783203125, "global_step": 584899, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.967543601989746, "global_step": 584900, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.038144111633301, "global_step": 584901, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0371954441070557, "global_step": 584902, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9692898988723755, "global_step": 584903, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9979830980300903, "global_step": 584904, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.031205654144287, "global_step": 584905, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.010863780975342, "global_step": 584906, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0129048824310303, "global_step": 584907, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1461682319641113, "global_step": 584908, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.064279317855835, "global_step": 584909, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0769927501678467, "global_step": 584910, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9413625001907349, "global_step": 584911, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9363898038864136, "global_step": 584912, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.936667561531067, "global_step": 584913, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0115854740142822, "global_step": 584914, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9421725273132324, "global_step": 584915, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0576891899108887, "global_step": 584916, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.020005226135254, "global_step": 584917, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.032073974609375, "global_step": 584918, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0638041496276855, "global_step": 584919, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0169756412506104, "global_step": 584920, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9594961404800415, "global_step": 584921, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9895825386047363, "global_step": 584922, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1060009002685547, "global_step": 584923, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0775747299194336, "global_step": 584924, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.913161277770996, "global_step": 584925, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9465386867523193, "global_step": 584926, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.048382520675659, "global_step": 584927, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0590856075286865, "global_step": 584928, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9694349765777588, "global_step": 584929, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.043198585510254, "global_step": 584930, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.035966157913208, "global_step": 584931, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.015439987182617, "global_step": 584932, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0612761974334717, "global_step": 584933, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0152525901794434, "global_step": 584934, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.088440179824829, "global_step": 584935, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0404319763183594, "global_step": 584936, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0953454971313477, "global_step": 584937, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.078901529312134, "global_step": 584938, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0046441555023193, "global_step": 584939, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9437801837921143, "global_step": 584940, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0809671878814697, "global_step": 584941, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0493483543395996, "global_step": 584942, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0471603870391846, "global_step": 584943, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.022744655609131, "global_step": 584944, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9350130558013916, "global_step": 584945, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9617050886154175, "global_step": 584946, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.077878713607788, "global_step": 584947, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0800726413726807, "global_step": 584948, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.997853398323059, "global_step": 584949, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9393234252929688, "global_step": 584950, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0239522457122803, "global_step": 584951, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.968961238861084, "global_step": 584952, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.078575849533081, "global_step": 584953, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.055030584335327, "global_step": 584954, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0157086849212646, "global_step": 584955, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.017859697341919, "global_step": 584956, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0559778213500977, "global_step": 584957, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0567870140075684, "global_step": 584958, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.000601291656494, "global_step": 584959, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.061109781265259, "global_step": 584960, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.044243812561035, "global_step": 584961, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0527420043945312, "global_step": 584962, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9974501132965088, "global_step": 584963, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9635653495788574, "global_step": 584964, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.8958698511123657, "global_step": 584965, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9751803874969482, "global_step": 584966, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.05549693107605, "global_step": 584967, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.018364906311035, "global_step": 584968, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9992659091949463, "global_step": 584969, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0195159912109375, "global_step": 584970, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.976027250289917, "global_step": 584971, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.043729305267334, "global_step": 584972, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9570233821868896, "global_step": 584973, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.067531108856201, "global_step": 584974, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0309696197509766, "global_step": 584975, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9965717792510986, "global_step": 584976, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.110301971435547, "global_step": 584977, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9829846620559692, "global_step": 584978, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0537614822387695, "global_step": 584979, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1079676151275635, "global_step": 584980, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0039939880371094, "global_step": 584981, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9584877490997314, "global_step": 584982, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0609123706817627, "global_step": 584983, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9793678522109985, "global_step": 584984, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0264673233032227, "global_step": 584985, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.918512225151062, "global_step": 584986, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0569958686828613, "global_step": 584987, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0040829181671143, "global_step": 584988, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.002091884613037, "global_step": 584989, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.105178117752075, "global_step": 584990, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0635836124420166, "global_step": 584991, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0121545791625977, "global_step": 584992, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.004215955734253, "global_step": 584993, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.038299322128296, "global_step": 584994, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0262014865875244, "global_step": 584995, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.985841155052185, "global_step": 584996, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0129752159118652, "global_step": 584997, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9748899936676025, "global_step": 584998, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0475943088531494, "global_step": 584999, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0104846954345703, "global_step": 585000, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9336620569229126, "global_step": 585001, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.091797351837158, "global_step": 585002, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9690041542053223, "global_step": 585003, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.001547336578369, "global_step": 585004, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0162720680236816, "global_step": 585005, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0220508575439453, "global_step": 585006, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0586373805999756, "global_step": 585007, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0964865684509277, "global_step": 585008, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9725421667099, "global_step": 585009, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0483360290527344, "global_step": 585010, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1116864681243896, "global_step": 585011, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0388543605804443, "global_step": 585012, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.044447660446167, "global_step": 585013, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9638087749481201, "global_step": 585014, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.028989315032959, "global_step": 585015, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.051926851272583, "global_step": 585016, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.126436471939087, "global_step": 585017, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.143752336502075, "global_step": 585018, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9761444330215454, "global_step": 585019, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.997848629951477, "global_step": 585020, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.046560525894165, "global_step": 585021, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.017512321472168, "global_step": 585022, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.052767038345337, "global_step": 585023, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.062389373779297, "global_step": 585024, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9849330186843872, "global_step": 585025, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9937952756881714, "global_step": 585026, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.136399745941162, "global_step": 585027, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.080178737640381, "global_step": 585028, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.023890495300293, "global_step": 585029, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.043877124786377, "global_step": 585030, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1075172424316406, "global_step": 585031, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0332858562469482, "global_step": 585032, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9813307523727417, "global_step": 585033, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9688527584075928, "global_step": 585034, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1867141723632812, "global_step": 585035, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.071732759475708, "global_step": 585036, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.063297986984253, "global_step": 585037, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9494267702102661, "global_step": 585038, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.965643048286438, "global_step": 585039, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0052096843719482, "global_step": 585040, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.906807541847229, "global_step": 585041, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0561344623565674, "global_step": 585042, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.026500701904297, "global_step": 585043, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0513477325439453, "global_step": 585044, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.084730863571167, "global_step": 585045, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9832587242126465, "global_step": 585046, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0070478916168213, "global_step": 585047, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9657927751541138, "global_step": 585048, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9829597473144531, "global_step": 585049, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0189051628112793, "global_step": 585050, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9631284475326538, "global_step": 585051, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.914182424545288, "global_step": 585052, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1097395420074463, "global_step": 585053, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9425405263900757, "global_step": 585054, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9899958372116089, "global_step": 585055, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9680882692337036, "global_step": 585056, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9688310623168945, "global_step": 585057, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.063375473022461, "global_step": 585058, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9772891998291016, "global_step": 585059, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0233941078186035, "global_step": 585060, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0037829875946045, "global_step": 585061, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.998451828956604, "global_step": 585062, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0259783267974854, "global_step": 585063, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.088456869125366, "global_step": 585064, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9248239994049072, "global_step": 585065, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9852242469787598, "global_step": 585066, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.069330930709839, "global_step": 585067, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0591483116149902, "global_step": 585068, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0068085193634033, "global_step": 585069, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0586555004119873, "global_step": 585070, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9465177059173584, "global_step": 585071, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0917229652404785, "global_step": 585072, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.013875722885132, "global_step": 585073, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.040224552154541, "global_step": 585074, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9973273277282715, "global_step": 585075, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0153932571411133, "global_step": 585076, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.016894817352295, "global_step": 585077, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0548250675201416, "global_step": 585078, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0147292613983154, "global_step": 585079, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9017138481140137, "global_step": 585080, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0082128047943115, "global_step": 585081, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9658722877502441, "global_step": 585082, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9508758783340454, "global_step": 585083, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.060500383377075, "global_step": 585084, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.03643536567688, "global_step": 585085, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0707449913024902, "global_step": 585086, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0083425045013428, "global_step": 585087, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.005565643310547, "global_step": 585088, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.086759328842163, "global_step": 585089, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0759150981903076, "global_step": 585090, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9726388454437256, "global_step": 585091, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0643248558044434, "global_step": 585092, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0228095054626465, "global_step": 585093, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.000325918197632, "global_step": 585094, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0140907764434814, "global_step": 585095, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0847361087799072, "global_step": 585096, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.109687328338623, "global_step": 585097, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.063150405883789, "global_step": 585098, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0134575366973877, "global_step": 585099, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0261783599853516, "global_step": 585100, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.072709560394287, "global_step": 585101, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.007537364959717, "global_step": 585102, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.959150791168213, "global_step": 585103, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9624521732330322, "global_step": 585104, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.023752212524414, "global_step": 585105, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.01820707321167, "global_step": 585106, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0958189964294434, "global_step": 585107, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.072427749633789, "global_step": 585108, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9529861211776733, "global_step": 585109, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.068699359893799, "global_step": 585110, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.033848524093628, "global_step": 585111, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9810454845428467, "global_step": 585112, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.063164472579956, "global_step": 585113, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0080065727233887, "global_step": 585114, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.009106397628784, "global_step": 585115, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.023024320602417, "global_step": 585116, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.976046085357666, "global_step": 585117, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9755942821502686, "global_step": 585118, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9242459535598755, "global_step": 585119, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9735321998596191, "global_step": 585120, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0002310276031494, "global_step": 585121, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.935794472694397, "global_step": 585122, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.059330940246582, "global_step": 585123, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.015348196029663, "global_step": 585124, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0456480979919434, "global_step": 585125, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9767886400222778, "global_step": 585126, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0611824989318848, "global_step": 585127, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0594851970672607, "global_step": 585128, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9699122905731201, "global_step": 585129, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0551583766937256, "global_step": 585130, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.001862049102783, "global_step": 585131, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.06205153465271, "global_step": 585132, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9898470640182495, "global_step": 585133, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.046027421951294, "global_step": 585134, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.006474494934082, "global_step": 585135, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.035404920578003, "global_step": 585136, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0319247245788574, "global_step": 585137, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9766836166381836, "global_step": 585138, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9788874387741089, "global_step": 585139, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.012943744659424, "global_step": 585140, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9803225994110107, "global_step": 585141, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0058703422546387, "global_step": 585142, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0060040950775146, "global_step": 585143, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0284910202026367, "global_step": 585144, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0501933097839355, "global_step": 585145, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9553701877593994, "global_step": 585146, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1022908687591553, "global_step": 585147, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0313894748687744, "global_step": 585148, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.973473310470581, "global_step": 585149, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0234267711639404, "global_step": 585150, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.035949468612671, "global_step": 585151, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.010380268096924, "global_step": 585152, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9515904188156128, "global_step": 585153, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.030780553817749, "global_step": 585154, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0375216007232666, "global_step": 585155, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9138245582580566, "global_step": 585156, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9861806631088257, "global_step": 585157, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9789097309112549, "global_step": 585158, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.064401626586914, "global_step": 585159, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.059235095977783, "global_step": 585160, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.018467664718628, "global_step": 585161, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9333878755569458, "global_step": 585162, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.958534598350525, "global_step": 585163, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0256080627441406, "global_step": 585164, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.04605770111084, "global_step": 585165, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.030945301055908, "global_step": 585166, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9970086812973022, "global_step": 585167, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.034287929534912, "global_step": 585168, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9717401266098022, "global_step": 585169, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.037597417831421, "global_step": 585170, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9534289836883545, "global_step": 585171, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.018803358078003, "global_step": 585172, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9514658451080322, "global_step": 585173, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0204150676727295, "global_step": 585174, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9961209297180176, "global_step": 585175, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1423587799072266, "global_step": 585176, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0726380348205566, "global_step": 585177, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9661401510238647, "global_step": 585178, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0162317752838135, "global_step": 585179, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9164178371429443, "global_step": 585180, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0469915866851807, "global_step": 585181, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0000460147857666, "global_step": 585182, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9518041610717773, "global_step": 585183, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.056103229522705, "global_step": 585184, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.030627489089966, "global_step": 585185, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0403010845184326, "global_step": 585186, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.933131456375122, "global_step": 585187, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0357413291931152, "global_step": 585188, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0554988384246826, "global_step": 585189, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9758837223052979, "global_step": 585190, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.986387014389038, "global_step": 585191, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0581541061401367, "global_step": 585192, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9774885177612305, "global_step": 585193, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0556681156158447, "global_step": 585194, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0502426624298096, "global_step": 585195, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0217771530151367, "global_step": 585196, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.892899751663208, "global_step": 585197, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.987673044204712, "global_step": 585198, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0484509468078613, "global_step": 585199, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0142743587493896, "global_step": 585200, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0283477306365967, "global_step": 585201, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0421290397644043, "global_step": 585202, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.015045404434204, "global_step": 585203, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9506984949111938, "global_step": 585204, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.005406141281128, "global_step": 585205, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.080909013748169, "global_step": 585206, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9578171968460083, "global_step": 585207, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9464919567108154, "global_step": 585208, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1165895462036133, "global_step": 585209, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0431365966796875, "global_step": 585210, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9317420721054077, "global_step": 585211, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.020235538482666, "global_step": 585212, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9975831508636475, "global_step": 585213, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0550284385681152, "global_step": 585214, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0088696479797363, "global_step": 585215, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0196316242218018, "global_step": 585216, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9875379800796509, "global_step": 585217, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0424704551696777, "global_step": 585218, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.079775094985962, "global_step": 585219, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1027700901031494, "global_step": 585220, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.001429557800293, "global_step": 585221, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9617608785629272, "global_step": 585222, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.069183349609375, "global_step": 585223, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9833664894104004, "global_step": 585224, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0645899772644043, "global_step": 585225, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.046180009841919, "global_step": 585226, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.100475311279297, "global_step": 585227, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.008727788925171, "global_step": 585228, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.984154224395752, "global_step": 585229, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.025514602661133, "global_step": 585230, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0635595321655273, "global_step": 585231, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0404391288757324, "global_step": 585232, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9739681482315063, "global_step": 585233, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.088524341583252, "global_step": 585234, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0378901958465576, "global_step": 585235, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.969140887260437, "global_step": 585236, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9523006677627563, "global_step": 585237, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.066758632659912, "global_step": 585238, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.031619071960449, "global_step": 585239, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0119030475616455, "global_step": 585240, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9832810163497925, "global_step": 585241, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0306100845336914, "global_step": 585242, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9304530620574951, "global_step": 585243, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.009021759033203, "global_step": 585244, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0465786457061768, "global_step": 585245, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.034186363220215, "global_step": 585246, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0688488483428955, "global_step": 585247, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.932962417602539, "global_step": 585248, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0158896446228027, "global_step": 585249, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0165581703186035, "global_step": 585250, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.069312572479248, "global_step": 585251, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.970971941947937, "global_step": 585252, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.963696837425232, "global_step": 585253, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0043907165527344, "global_step": 585254, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0216007232666016, "global_step": 585255, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.022812843322754, "global_step": 585256, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1008341312408447, "global_step": 585257, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.022357702255249, "global_step": 585258, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9911746978759766, "global_step": 585259, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0096070766448975, "global_step": 585260, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.016946315765381, "global_step": 585261, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.018298387527466, "global_step": 585262, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.04600191116333, "global_step": 585263, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0001611709594727, "global_step": 585264, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.020411968231201, "global_step": 585265, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.072986364364624, "global_step": 585266, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0066378116607666, "global_step": 585267, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0864973068237305, "global_step": 585268, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.014439105987549, "global_step": 585269, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9784808158874512, "global_step": 585270, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9950335025787354, "global_step": 585271, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0615954399108887, "global_step": 585272, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9916558265686035, "global_step": 585273, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.055476427078247, "global_step": 585274, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9961886405944824, "global_step": 585275, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0130667686462402, "global_step": 585276, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0384652614593506, "global_step": 585277, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9952449798583984, "global_step": 585278, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0799412727355957, "global_step": 585279, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0434768199920654, "global_step": 585280, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0058228969573975, "global_step": 585281, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.015685796737671, "global_step": 585282, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0060067176818848, "global_step": 585283, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.968984842300415, "global_step": 585284, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0418169498443604, "global_step": 585285, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0330610275268555, "global_step": 585286, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0303051471710205, "global_step": 585287, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0510449409484863, "global_step": 585288, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.981623888015747, "global_step": 585289, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0088107585906982, "global_step": 585290, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9901654720306396, "global_step": 585291, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.069646120071411, "global_step": 585292, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0092782974243164, "global_step": 585293, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9865025281906128, "global_step": 585294, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.050492763519287, "global_step": 585295, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9754184484481812, "global_step": 585296, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.023772716522217, "global_step": 585297, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0445058345794678, "global_step": 585298, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9511712789535522, "global_step": 585299, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9492950439453125, "global_step": 585300, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0077664852142334, "global_step": 585301, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.103288412094116, "global_step": 585302, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0680277347564697, "global_step": 585303, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.966645359992981, "global_step": 585304, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.086385488510132, "global_step": 585305, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9592411518096924, "global_step": 585306, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0388197898864746, "global_step": 585307, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9746028184890747, "global_step": 585308, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9645349979400635, "global_step": 585309, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0527753829956055, "global_step": 585310, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.008842706680298, "global_step": 585311, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0461015701293945, "global_step": 585312, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0231170654296875, "global_step": 585313, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0521292686462402, "global_step": 585314, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0224695205688477, "global_step": 585315, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9950603246688843, "global_step": 585316, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.076458215713501, "global_step": 585317, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0511553287506104, "global_step": 585318, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9622471332550049, "global_step": 585319, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.018266439437866, "global_step": 585320, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.956864833831787, "global_step": 585321, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0537455081939697, "global_step": 585322, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.986746072769165, "global_step": 585323, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.997597336769104, "global_step": 585324, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0538175106048584, "global_step": 585325, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.077803373336792, "global_step": 585326, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0740442276000977, "global_step": 585327, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.991335391998291, "global_step": 585328, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9293665885925293, "global_step": 585329, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9968534708023071, "global_step": 585330, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.074040174484253, "global_step": 585331, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9631222486495972, "global_step": 585332, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0943825244903564, "global_step": 585333, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9651832580566406, "global_step": 585334, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9946212768554688, "global_step": 585335, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.034390687942505, "global_step": 585336, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0644025802612305, "global_step": 585337, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9832100868225098, "global_step": 585338, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9850860834121704, "global_step": 585339, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.064236640930176, "global_step": 585340, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0245609283447266, "global_step": 585341, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.071016788482666, "global_step": 585342, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.001417636871338, "global_step": 585343, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.021876811981201, "global_step": 585344, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9997081756591797, "global_step": 585345, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0447804927825928, "global_step": 585346, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0101382732391357, "global_step": 585347, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0449304580688477, "global_step": 585348, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9833334684371948, "global_step": 585349, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0401792526245117, "global_step": 585350, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0386149883270264, "global_step": 585351, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0155372619628906, "global_step": 585352, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0233778953552246, "global_step": 585353, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.000998020172119, "global_step": 585354, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0009353160858154, "global_step": 585355, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0052006244659424, "global_step": 585356, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0434045791625977, "global_step": 585357, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0723228454589844, "global_step": 585358, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.067862033843994, "global_step": 585359, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0110857486724854, "global_step": 585360, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9831569194793701, "global_step": 585361, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0706350803375244, "global_step": 585362, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9036242961883545, "global_step": 585363, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0329363346099854, "global_step": 585364, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.013531446456909, "global_step": 585365, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.943327784538269, "global_step": 585366, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1750388145446777, "global_step": 585367, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.974359154701233, "global_step": 585368, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9929428100585938, "global_step": 585369, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0955848693847656, "global_step": 585370, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.946812629699707, "global_step": 585371, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1012210845947266, "global_step": 585372, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.001066207885742, "global_step": 585373, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.079442262649536, "global_step": 585374, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.024806499481201, "global_step": 585375, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.057344675064087, "global_step": 585376, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0983357429504395, "global_step": 585377, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0431535243988037, "global_step": 585378, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.040182113647461, "global_step": 585379, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0161335468292236, "global_step": 585380, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0512123107910156, "global_step": 585381, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0102527141571045, "global_step": 585382, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0152876377105713, "global_step": 585383, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.043137311935425, "global_step": 585384, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9986270666122437, "global_step": 585385, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9865527153015137, "global_step": 585386, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.071200370788574, "global_step": 585387, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.039536952972412, "global_step": 585388, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.990304946899414, "global_step": 585389, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0163300037384033, "global_step": 585390, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.1165943145751953, "global_step": 585391, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0241613388061523, "global_step": 585392, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0337014198303223, "global_step": 585393, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.05307674407959, "global_step": 585394, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9726899862289429, "global_step": 585395, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0478999614715576, "global_step": 585396, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0860328674316406, "global_step": 585397, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9713696241378784, "global_step": 585398, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.050194263458252, "global_step": 585399, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0184288024902344, "global_step": 585400, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.992646336555481, "global_step": 585401, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0048508644104004, "global_step": 585402, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0442771911621094, "global_step": 585403, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0510900020599365, "global_step": 585404, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0321762561798096, "global_step": 585405, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.103776216506958, "global_step": 585406, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9761334657669067, "global_step": 585407, "epoch": 953, "lr": 5e-05}
{"train_loss": 2.0173685550689697, "global_step": 585408, "epoch": 953, "lr": 5e-05}
{"train_loss": 1.9924229383468628, "global_step": 585409, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0580015182495117, "global_step": 585410, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.971694827079773, "global_step": 585411, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.029848098754883, "global_step": 585412, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.029812812805176, "global_step": 585413, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0545201301574707, "global_step": 585414, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9681955575942993, "global_step": 585415, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9952282905578613, "global_step": 585416, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0188701152801514, "global_step": 585417, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.09063720703125, "global_step": 585418, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.994511365890503, "global_step": 585419, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.076655387878418, "global_step": 585420, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.903329610824585, "global_step": 585421, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.035527467727661, "global_step": 585422, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.961191177368164, "global_step": 585423, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.006354331970215, "global_step": 585424, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9936447143554688, "global_step": 585425, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.071155071258545, "global_step": 585426, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.973446249961853, "global_step": 585427, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.987328052520752, "global_step": 585428, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.047297477722168, "global_step": 585429, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.028534412384033, "global_step": 585430, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.070575714111328, "global_step": 585431, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.983782172203064, "global_step": 585432, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0295073986053467, "global_step": 585433, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9775201082229614, "global_step": 585434, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9047983884811401, "global_step": 585435, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0670974254608154, "global_step": 585436, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.079000234603882, "global_step": 585437, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.956527590751648, "global_step": 585438, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9939228296279907, "global_step": 585439, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.021352767944336, "global_step": 585440, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0194098949432373, "global_step": 585441, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9575097560882568, "global_step": 585442, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.934215784072876, "global_step": 585443, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9998695850372314, "global_step": 585444, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.068282127380371, "global_step": 585445, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0079548358917236, "global_step": 585446, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9726026058197021, "global_step": 585447, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.076286792755127, "global_step": 585448, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9103970527648926, "global_step": 585449, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0557918548583984, "global_step": 585450, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9845774173736572, "global_step": 585451, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9948970079421997, "global_step": 585452, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.992242693901062, "global_step": 585453, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0082263946533203, "global_step": 585454, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0489439964294434, "global_step": 585455, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9706330299377441, "global_step": 585456, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0619113445281982, "global_step": 585457, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9954617023468018, "global_step": 585458, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9038407802581787, "global_step": 585459, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9965178966522217, "global_step": 585460, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9295989274978638, "global_step": 585461, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.020771026611328, "global_step": 585462, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.059370756149292, "global_step": 585463, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.983834147453308, "global_step": 585464, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9647475481033325, "global_step": 585465, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.121159791946411, "global_step": 585466, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0077433586120605, "global_step": 585467, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.932568073272705, "global_step": 585468, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0638647079467773, "global_step": 585469, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.082923173904419, "global_step": 585470, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.999848484992981, "global_step": 585471, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.044671058654785, "global_step": 585472, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.081669569015503, "global_step": 585473, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.990382432937622, "global_step": 585474, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9766311645507812, "global_step": 585475, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0601840019226074, "global_step": 585476, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.984312891960144, "global_step": 585477, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.05441951751709, "global_step": 585478, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.031099557876587, "global_step": 585479, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0620548725128174, "global_step": 585480, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0197222232818604, "global_step": 585481, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.006584882736206, "global_step": 585482, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.015624523162842, "global_step": 585483, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0149073600769043, "global_step": 585484, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0303053855895996, "global_step": 585485, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0086045265197754, "global_step": 585486, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.936892032623291, "global_step": 585487, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.107255458831787, "global_step": 585488, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.004913806915283, "global_step": 585489, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9786680936813354, "global_step": 585490, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.019552230834961, "global_step": 585491, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.061009168624878, "global_step": 585492, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.944604754447937, "global_step": 585493, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.094740629196167, "global_step": 585494, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0277507305145264, "global_step": 585495, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.097158670425415, "global_step": 585496, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0216286182403564, "global_step": 585497, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.993553638458252, "global_step": 585498, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9448904991149902, "global_step": 585499, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0671632289886475, "global_step": 585500, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9932924509048462, "global_step": 585501, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9602183103561401, "global_step": 585502, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0128939151763916, "global_step": 585503, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.993747591972351, "global_step": 585504, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0939056873321533, "global_step": 585505, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.975109338760376, "global_step": 585506, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0318565368652344, "global_step": 585507, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0646750926971436, "global_step": 585508, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0141119956970215, "global_step": 585509, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.8879437446594238, "global_step": 585510, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0712549686431885, "global_step": 585511, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.044292688369751, "global_step": 585512, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9276995658874512, "global_step": 585513, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0003278255462646, "global_step": 585514, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9641284942626953, "global_step": 585515, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9858527183532715, "global_step": 585516, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0645761489868164, "global_step": 585517, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9585269689559937, "global_step": 585518, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.938431978225708, "global_step": 585519, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.94562566280365, "global_step": 585520, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9657682180404663, "global_step": 585521, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0426688194274902, "global_step": 585522, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.8938223123550415, "global_step": 585523, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0143837928771973, "global_step": 585524, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.004878520965576, "global_step": 585525, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.096985101699829, "global_step": 585526, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9479930400848389, "global_step": 585527, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.026578426361084, "global_step": 585528, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1149001121520996, "global_step": 585529, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9587931632995605, "global_step": 585530, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9630323648452759, "global_step": 585531, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.028170585632324, "global_step": 585532, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9494210481643677, "global_step": 585533, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0105690956115723, "global_step": 585534, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0458714962005615, "global_step": 585535, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.036292552947998, "global_step": 585536, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9949513673782349, "global_step": 585537, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9747394323349, "global_step": 585538, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0577316284179688, "global_step": 585539, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.986682653427124, "global_step": 585540, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0914058685302734, "global_step": 585541, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0284581184387207, "global_step": 585542, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.932296633720398, "global_step": 585543, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9918166399002075, "global_step": 585544, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0422544479370117, "global_step": 585545, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9648454189300537, "global_step": 585546, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9205012321472168, "global_step": 585547, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9405124187469482, "global_step": 585548, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.045344829559326, "global_step": 585549, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.035689115524292, "global_step": 585550, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0966615676879883, "global_step": 585551, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.8910472393035889, "global_step": 585552, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.938546895980835, "global_step": 585553, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0702645778656006, "global_step": 585554, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0171875953674316, "global_step": 585555, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9822760820388794, "global_step": 585556, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9905500411987305, "global_step": 585557, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9688842296600342, "global_step": 585558, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.067643642425537, "global_step": 585559, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9590985774993896, "global_step": 585560, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.994608998298645, "global_step": 585561, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9611586332321167, "global_step": 585562, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.029604196548462, "global_step": 585563, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0281262397766113, "global_step": 585564, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.969849944114685, "global_step": 585565, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9662138223648071, "global_step": 585566, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.014529228210449, "global_step": 585567, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0393714904785156, "global_step": 585568, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9963513612747192, "global_step": 585569, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0048696994781494, "global_step": 585570, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9639889001846313, "global_step": 585571, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9793874025344849, "global_step": 585572, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.93206787109375, "global_step": 585573, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9960572719573975, "global_step": 585574, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0037407875061035, "global_step": 585575, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0432090759277344, "global_step": 585576, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.018066644668579, "global_step": 585577, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9803986549377441, "global_step": 585578, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9770355224609375, "global_step": 585579, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9982105493545532, "global_step": 585580, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0223400592803955, "global_step": 585581, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0308480262756348, "global_step": 585582, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.935038685798645, "global_step": 585583, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0064826011657715, "global_step": 585584, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9920743703842163, "global_step": 585585, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9450503587722778, "global_step": 585586, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.996977686882019, "global_step": 585587, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0010650157928467, "global_step": 585588, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0272626876831055, "global_step": 585589, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0065832138061523, "global_step": 585590, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0905911922454834, "global_step": 585591, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.992475152015686, "global_step": 585592, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.07716965675354, "global_step": 585593, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.022630214691162, "global_step": 585594, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.08632230758667, "global_step": 585595, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9927400350570679, "global_step": 585596, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9783538579940796, "global_step": 585597, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.014190912246704, "global_step": 585598, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0230352878570557, "global_step": 585599, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.023226737976074, "global_step": 585600, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0082223415374756, "global_step": 585601, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.056999444961548, "global_step": 585602, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9664286375045776, "global_step": 585603, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0316948890686035, "global_step": 585604, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0257177352905273, "global_step": 585605, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0268049240112305, "global_step": 585606, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.019209146499634, "global_step": 585607, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9594777822494507, "global_step": 585608, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.016695022583008, "global_step": 585609, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9971060752868652, "global_step": 585610, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9417201280593872, "global_step": 585611, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0179197788238525, "global_step": 585612, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9184882640838623, "global_step": 585613, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9979506731033325, "global_step": 585614, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.12815523147583, "global_step": 585615, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.986954689025879, "global_step": 585616, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0296790599823, "global_step": 585617, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0040807723999023, "global_step": 585618, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0101399421691895, "global_step": 585619, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.032961368560791, "global_step": 585620, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0008976459503174, "global_step": 585621, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1277358531951904, "global_step": 585622, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0500433444976807, "global_step": 585623, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.020148515701294, "global_step": 585624, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0547618865966797, "global_step": 585625, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9951978921890259, "global_step": 585626, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.013577699661255, "global_step": 585627, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0970630645751953, "global_step": 585628, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.03037691116333, "global_step": 585629, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9941099882125854, "global_step": 585630, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9627474546432495, "global_step": 585631, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0040457248687744, "global_step": 585632, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0423598289489746, "global_step": 585633, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0564937591552734, "global_step": 585634, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.069446086883545, "global_step": 585635, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.018627166748047, "global_step": 585636, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.02344012260437, "global_step": 585637, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0499165058135986, "global_step": 585638, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.952785849571228, "global_step": 585639, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9700285196304321, "global_step": 585640, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0634026527404785, "global_step": 585641, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.057079792022705, "global_step": 585642, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9719719886779785, "global_step": 585643, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.045103073120117, "global_step": 585644, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0819358825683594, "global_step": 585645, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0773706436157227, "global_step": 585646, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0815505981445312, "global_step": 585647, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9718326330184937, "global_step": 585648, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.982617735862732, "global_step": 585649, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0239105224609375, "global_step": 585650, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.006247043609619, "global_step": 585651, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0291008949279785, "global_step": 585652, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0280370712280273, "global_step": 585653, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9525806903839111, "global_step": 585654, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0317978858947754, "global_step": 585655, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.020280599594116, "global_step": 585656, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0257978439331055, "global_step": 585657, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0417518615722656, "global_step": 585658, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.026975631713867, "global_step": 585659, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0300214290618896, "global_step": 585660, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.012007713317871, "global_step": 585661, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9674115180969238, "global_step": 585662, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.088533639907837, "global_step": 585663, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.107093095779419, "global_step": 585664, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9216861724853516, "global_step": 585665, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0071699619293213, "global_step": 585666, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.056974172592163, "global_step": 585667, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.083524465560913, "global_step": 585668, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.967239499092102, "global_step": 585669, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0325887203216553, "global_step": 585670, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.022130012512207, "global_step": 585671, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.984331727027893, "global_step": 585672, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0652568340301514, "global_step": 585673, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.981998085975647, "global_step": 585674, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.014484405517578, "global_step": 585675, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0343596935272217, "global_step": 585676, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.053022861480713, "global_step": 585677, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9783430099487305, "global_step": 585678, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9505304098129272, "global_step": 585679, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0611979961395264, "global_step": 585680, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0521233081817627, "global_step": 585681, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.012639045715332, "global_step": 585682, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9806678295135498, "global_step": 585683, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0014395713806152, "global_step": 585684, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0087287425994873, "global_step": 585685, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.990782380104065, "global_step": 585686, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.023362874984741, "global_step": 585687, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0449671745300293, "global_step": 585688, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.025618553161621, "global_step": 585689, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9855334758758545, "global_step": 585690, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0965747833251953, "global_step": 585691, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0183777809143066, "global_step": 585692, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9615561962127686, "global_step": 585693, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.021902561187744, "global_step": 585694, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.058485507965088, "global_step": 585695, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0434281826019287, "global_step": 585696, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0166094303131104, "global_step": 585697, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.019183397293091, "global_step": 585698, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0653843879699707, "global_step": 585699, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9171253442764282, "global_step": 585700, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9867007732391357, "global_step": 585701, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9939663410186768, "global_step": 585702, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0011117458343506, "global_step": 585703, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9512659311294556, "global_step": 585704, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9835591316223145, "global_step": 585705, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.102074146270752, "global_step": 585706, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.972043752670288, "global_step": 585707, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0129661560058594, "global_step": 585708, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1001129150390625, "global_step": 585709, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.118910789489746, "global_step": 585710, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.066028594970703, "global_step": 585711, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.048964262008667, "global_step": 585712, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0214710235595703, "global_step": 585713, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9587594270706177, "global_step": 585714, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0510523319244385, "global_step": 585715, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.012510061264038, "global_step": 585716, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0391016006469727, "global_step": 585717, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.025221109390259, "global_step": 585718, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9951872825622559, "global_step": 585719, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.935804009437561, "global_step": 585720, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0888009071350098, "global_step": 585721, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9819005727767944, "global_step": 585722, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0195531845092773, "global_step": 585723, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.036435842514038, "global_step": 585724, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.009330987930298, "global_step": 585725, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0487780570983887, "global_step": 585726, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.004542350769043, "global_step": 585727, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.019003391265869, "global_step": 585728, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.033090114593506, "global_step": 585729, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9308264255523682, "global_step": 585730, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0409631729125977, "global_step": 585731, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0206491947174072, "global_step": 585732, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9775958061218262, "global_step": 585733, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0018372535705566, "global_step": 585734, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9263771772384644, "global_step": 585735, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.017580270767212, "global_step": 585736, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9758261442184448, "global_step": 585737, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0603694915771484, "global_step": 585738, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9891403913497925, "global_step": 585739, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9742255210876465, "global_step": 585740, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9893096685409546, "global_step": 585741, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0357284545898438, "global_step": 585742, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.964142918586731, "global_step": 585743, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1396689414978027, "global_step": 585744, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.061042308807373, "global_step": 585745, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0812337398529053, "global_step": 585746, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9982119798660278, "global_step": 585747, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9723801612854004, "global_step": 585748, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.086616039276123, "global_step": 585749, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9696588516235352, "global_step": 585750, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9720736742019653, "global_step": 585751, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0290582180023193, "global_step": 585752, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9685137271881104, "global_step": 585753, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.095393419265747, "global_step": 585754, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0898475646972656, "global_step": 585755, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.099733829498291, "global_step": 585756, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.05737566947937, "global_step": 585757, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.016319751739502, "global_step": 585758, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.036067485809326, "global_step": 585759, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9932169914245605, "global_step": 585760, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0491201877593994, "global_step": 585761, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9458770751953125, "global_step": 585762, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9473563432693481, "global_step": 585763, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0403358936309814, "global_step": 585764, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.990635871887207, "global_step": 585765, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.981589436531067, "global_step": 585766, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.8974307775497437, "global_step": 585767, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.086876630783081, "global_step": 585768, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.061800479888916, "global_step": 585769, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0232672691345215, "global_step": 585770, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9672973155975342, "global_step": 585771, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.032916784286499, "global_step": 585772, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9845329523086548, "global_step": 585773, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.092294216156006, "global_step": 585774, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9814256429672241, "global_step": 585775, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0936782360076904, "global_step": 585776, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0193629264831543, "global_step": 585777, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9219375848770142, "global_step": 585778, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0105011463165283, "global_step": 585779, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0714781284332275, "global_step": 585780, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0066754817962646, "global_step": 585781, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9985079765319824, "global_step": 585782, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0212137699127197, "global_step": 585783, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.099196434020996, "global_step": 585784, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0151665210723877, "global_step": 585785, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0730535984039307, "global_step": 585786, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9916905164718628, "global_step": 585787, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.059511184692383, "global_step": 585788, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.067185401916504, "global_step": 585789, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1218180656433105, "global_step": 585790, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.036778688430786, "global_step": 585791, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9432594776153564, "global_step": 585792, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0055887699127197, "global_step": 585793, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.04272198677063, "global_step": 585794, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9365242719650269, "global_step": 585795, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0536179542541504, "global_step": 585796, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9765172004699707, "global_step": 585797, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.051795244216919, "global_step": 585798, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0672333240509033, "global_step": 585799, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.117342948913574, "global_step": 585800, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0472819805145264, "global_step": 585801, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0414071083068848, "global_step": 585802, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0617687702178955, "global_step": 585803, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0305118560791016, "global_step": 585804, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.000732183456421, "global_step": 585805, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0050315856933594, "global_step": 585806, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.022732973098755, "global_step": 585807, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0233054161071777, "global_step": 585808, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0081562995910645, "global_step": 585809, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0054712295532227, "global_step": 585810, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.037322521209717, "global_step": 585811, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1146795749664307, "global_step": 585812, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0707297325134277, "global_step": 585813, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0417022705078125, "global_step": 585814, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.000319480895996, "global_step": 585815, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9806982278823853, "global_step": 585816, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0176260471343994, "global_step": 585817, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0671005249023438, "global_step": 585818, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9717700481414795, "global_step": 585819, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.001147985458374, "global_step": 585820, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9395153522491455, "global_step": 585821, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0284066200256348, "global_step": 585822, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0834341049194336, "global_step": 585823, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0062878131866455, "global_step": 585824, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0686886310577393, "global_step": 585825, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0416088104248047, "global_step": 585826, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0534465312957764, "global_step": 585827, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9642784595489502, "global_step": 585828, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.05538010597229, "global_step": 585829, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.006500482559204, "global_step": 585830, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9545390605926514, "global_step": 585831, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.08131742477417, "global_step": 585832, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0100200176239014, "global_step": 585833, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9276636838912964, "global_step": 585834, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.00709867477417, "global_step": 585835, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.975835919380188, "global_step": 585836, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0489823818206787, "global_step": 585837, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0620861053466797, "global_step": 585838, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.964909553527832, "global_step": 585839, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0303921699523926, "global_step": 585840, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0085933208465576, "global_step": 585841, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0389084815979004, "global_step": 585842, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.00392746925354, "global_step": 585843, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9967880249023438, "global_step": 585844, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0005972385406494, "global_step": 585845, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9864853620529175, "global_step": 585846, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.009575605392456, "global_step": 585847, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0559818744659424, "global_step": 585848, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9937808513641357, "global_step": 585849, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0759525299072266, "global_step": 585850, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0559916496276855, "global_step": 585851, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0410473346710205, "global_step": 585852, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0290687084198, "global_step": 585853, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9241759777069092, "global_step": 585854, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0329208374023438, "global_step": 585855, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.005828380584717, "global_step": 585856, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0635101795196533, "global_step": 585857, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0069453716278076, "global_step": 585858, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.058830499649048, "global_step": 585859, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.035689115524292, "global_step": 585860, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.963425874710083, "global_step": 585861, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9990499019622803, "global_step": 585862, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0713233947753906, "global_step": 585863, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9242844581604004, "global_step": 585864, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0284717082977295, "global_step": 585865, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.017200469970703, "global_step": 585866, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9451502561569214, "global_step": 585867, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9914028644561768, "global_step": 585868, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0514109134674072, "global_step": 585869, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1111061573028564, "global_step": 585870, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9778169393539429, "global_step": 585871, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0115737915039062, "global_step": 585872, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.016695261001587, "global_step": 585873, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.999062418937683, "global_step": 585874, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.027010917663574, "global_step": 585875, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0025341510772705, "global_step": 585876, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.053870916366577, "global_step": 585877, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9594749212265015, "global_step": 585878, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1210124492645264, "global_step": 585879, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.051975727081299, "global_step": 585880, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.950589656829834, "global_step": 585881, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9721850156784058, "global_step": 585882, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.992344856262207, "global_step": 585883, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.106938600540161, "global_step": 585884, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9739984273910522, "global_step": 585885, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9548559188842773, "global_step": 585886, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.002744436264038, "global_step": 585887, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9412927627563477, "global_step": 585888, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0489816665649414, "global_step": 585889, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9929243326187134, "global_step": 585890, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9115478992462158, "global_step": 585891, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9353971481323242, "global_step": 585892, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.97178053855896, "global_step": 585893, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.989031434059143, "global_step": 585894, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0120441913604736, "global_step": 585895, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.029061794281006, "global_step": 585896, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.058387279510498, "global_step": 585897, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.019479274749756, "global_step": 585898, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0275392532348633, "global_step": 585899, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0157227516174316, "global_step": 585900, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9852793216705322, "global_step": 585901, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0930702686309814, "global_step": 585902, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.027280330657959, "global_step": 585903, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.924249291419983, "global_step": 585904, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0107192993164062, "global_step": 585905, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.038769483566284, "global_step": 585906, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.066291332244873, "global_step": 585907, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9731242656707764, "global_step": 585908, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.933968424797058, "global_step": 585909, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0775763988494873, "global_step": 585910, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.8952453136444092, "global_step": 585911, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.029763698577881, "global_step": 585912, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.014078378677368, "global_step": 585913, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.105816125869751, "global_step": 585914, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.058393716812134, "global_step": 585915, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9771769046783447, "global_step": 585916, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0546562671661377, "global_step": 585917, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0262253284454346, "global_step": 585918, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.026129722595215, "global_step": 585919, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.969128966331482, "global_step": 585920, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.027799129486084, "global_step": 585921, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.986158013343811, "global_step": 585922, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9580113887786865, "global_step": 585923, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0239131450653076, "global_step": 585924, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.049514055252075, "global_step": 585925, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0331380367279053, "global_step": 585926, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.091888189315796, "global_step": 585927, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9622814655303955, "global_step": 585928, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.091743230819702, "global_step": 585929, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9116100072860718, "global_step": 585930, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9477620124816895, "global_step": 585931, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.996443271636963, "global_step": 585932, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.037832498550415, "global_step": 585933, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0105230808258057, "global_step": 585934, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0739641189575195, "global_step": 585935, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0169601440429688, "global_step": 585936, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.058878183364868, "global_step": 585937, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0034046173095703, "global_step": 585938, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.8993000984191895, "global_step": 585939, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0019023418426514, "global_step": 585940, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.011192560195923, "global_step": 585941, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9442449808120728, "global_step": 585942, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0749454498291016, "global_step": 585943, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.98466157913208, "global_step": 585944, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.037346363067627, "global_step": 585945, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9970734119415283, "global_step": 585946, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0051488876342773, "global_step": 585947, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0390453338623047, "global_step": 585948, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.131363868713379, "global_step": 585949, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.044735908508301, "global_step": 585950, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0338258743286133, "global_step": 585951, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1069841384887695, "global_step": 585952, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0575673580169678, "global_step": 585953, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0329430103302, "global_step": 585954, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9591774940490723, "global_step": 585955, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.047213077545166, "global_step": 585956, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0822842121124268, "global_step": 585957, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.980024814605713, "global_step": 585958, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0601518154144287, "global_step": 585959, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.01237416267395, "global_step": 585960, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9410943984985352, "global_step": 585961, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9989484548568726, "global_step": 585962, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.01430082321167, "global_step": 585963, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.054206132888794, "global_step": 585964, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9968150854110718, "global_step": 585965, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9979220628738403, "global_step": 585966, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0045180320739746, "global_step": 585967, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.933326005935669, "global_step": 585968, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9783951044082642, "global_step": 585969, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.042443037033081, "global_step": 585970, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.001791000366211, "global_step": 585971, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0272045135498047, "global_step": 585972, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.042475700378418, "global_step": 585973, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9519145488739014, "global_step": 585974, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9743562936782837, "global_step": 585975, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0703330039978027, "global_step": 585976, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0569612979888916, "global_step": 585977, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0219318866729736, "global_step": 585978, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0182197093963623, "global_step": 585979, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0666005611419678, "global_step": 585980, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9883365631103516, "global_step": 585981, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.006617784500122, "global_step": 585982, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.044983148574829, "global_step": 585983, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9161450862884521, "global_step": 585984, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.005162239074707, "global_step": 585985, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.055529832839966, "global_step": 585986, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.034066677093506, "global_step": 585987, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0578219890594482, "global_step": 585988, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0724196434020996, "global_step": 585989, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9956333637237549, "global_step": 585990, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0647644996643066, "global_step": 585991, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9779947996139526, "global_step": 585992, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9848815202713013, "global_step": 585993, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9980225563049316, "global_step": 585994, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.061861515045166, "global_step": 585995, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9963065385818481, "global_step": 585996, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0230553150177, "global_step": 585997, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.053635597229004, "global_step": 585998, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.07074236869812, "global_step": 585999, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0012550354003906, "global_step": 586000, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9952844381332397, "global_step": 586001, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0415210723876953, "global_step": 586002, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.007711887359619, "global_step": 586003, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0663535594940186, "global_step": 586004, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0474135875701904, "global_step": 586005, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.047096014022827, "global_step": 586006, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.063107490539551, "global_step": 586007, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.079920530319214, "global_step": 586008, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9911515712738037, "global_step": 586009, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.00221586227417, "global_step": 586010, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.05599045753479, "global_step": 586011, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9845685958862305, "global_step": 586012, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9895461797714233, "global_step": 586013, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0563855171203613, "global_step": 586014, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.970785140991211, "global_step": 586015, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0246329307556152, "global_step": 586016, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0842127799987793, "global_step": 586017, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0215258598327637, "global_step": 586018, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0836148262023926, "global_step": 586019, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.073150157928467, "global_step": 586020, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0393576622009277, "global_step": 586021, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9542992115020752, "global_step": 586022, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.99360990524292, "global_step": 586023, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9764846563339233, "global_step": 586024, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.070019245147705, "global_step": 586025, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.143756151199341, "global_step": 586026, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.047555685043335, "global_step": 586027, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.998380184173584, "global_step": 586028, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.015998363494873, "global_step": 586029, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.8908690214157104, "global_step": 586030, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9680176973342896, "global_step": 586031, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0541467666625977, "global_step": 586032, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.01352596282959, "global_step": 586033, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0919618606567383, "global_step": 586034, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.970454216003418, "global_step": 586035, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0569159984588623, "global_step": 586036, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0051779747009277, "global_step": 586037, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.994360089302063, "global_step": 586038, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.069854736328125, "global_step": 586039, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.94157874584198, "global_step": 586040, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.058699369430542, "global_step": 586041, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0967626571655273, "global_step": 586042, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0416064262390137, "global_step": 586043, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0230700969696045, "global_step": 586044, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0003280639648438, "global_step": 586045, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1333396434783936, "global_step": 586046, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0626473426818848, "global_step": 586047, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.088200569152832, "global_step": 586048, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9964979887008667, "global_step": 586049, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9079374074935913, "global_step": 586050, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0050668716430664, "global_step": 586051, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1160264015197754, "global_step": 586052, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0726804733276367, "global_step": 586053, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.084031820297241, "global_step": 586054, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0041260719299316, "global_step": 586055, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1062772274017334, "global_step": 586056, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9650216102600098, "global_step": 586057, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9859811067581177, "global_step": 586058, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9812558889389038, "global_step": 586059, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0030505657196045, "global_step": 586060, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0920069217681885, "global_step": 586061, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.036153793334961, "global_step": 586062, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.965543270111084, "global_step": 586063, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0500075817108154, "global_step": 586064, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9552018642425537, "global_step": 586065, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.007997989654541, "global_step": 586066, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1493122577667236, "global_step": 586067, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9885424375534058, "global_step": 586068, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.101759672164917, "global_step": 586069, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0174803733825684, "global_step": 586070, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0456278324127197, "global_step": 586071, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1011838912963867, "global_step": 586072, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0029728412628174, "global_step": 586073, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0489096641540527, "global_step": 586074, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0206871032714844, "global_step": 586075, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.029437303543091, "global_step": 586076, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9847612380981445, "global_step": 586077, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.025247812271118, "global_step": 586078, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0962576866149902, "global_step": 586079, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.044105291366577, "global_step": 586080, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9729108810424805, "global_step": 586081, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.017627716064453, "global_step": 586082, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0198702812194824, "global_step": 586083, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.998872995376587, "global_step": 586084, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.99371337890625, "global_step": 586085, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0215916633605957, "global_step": 586086, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0152711868286133, "global_step": 586087, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9991576671600342, "global_step": 586088, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0488121509552, "global_step": 586089, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9483442306518555, "global_step": 586090, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0407238006591797, "global_step": 586091, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0536911487579346, "global_step": 586092, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9883290529251099, "global_step": 586093, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9654765129089355, "global_step": 586094, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0232317447662354, "global_step": 586095, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9806833267211914, "global_step": 586096, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9923607110977173, "global_step": 586097, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.952136516571045, "global_step": 586098, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0312135219573975, "global_step": 586099, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0383048057556152, "global_step": 586100, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9778929948806763, "global_step": 586101, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0037906169891357, "global_step": 586102, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0694165229797363, "global_step": 586103, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0292770862579346, "global_step": 586104, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.00156831741333, "global_step": 586105, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.043836832046509, "global_step": 586106, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9994782209396362, "global_step": 586107, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0031237602233887, "global_step": 586108, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.052358627319336, "global_step": 586109, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0173113346099854, "global_step": 586110, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0655579566955566, "global_step": 586111, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.022488832473755, "global_step": 586112, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0311245918273926, "global_step": 586113, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0148074626922607, "global_step": 586114, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0189497470855713, "global_step": 586115, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0521702766418457, "global_step": 586116, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0745863914489746, "global_step": 586117, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0228044986724854, "global_step": 586118, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.036041259765625, "global_step": 586119, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0149688720703125, "global_step": 586120, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9894899129867554, "global_step": 586121, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9756622314453125, "global_step": 586122, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.109731674194336, "global_step": 586123, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9623562097549438, "global_step": 586124, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0255722999572754, "global_step": 586125, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.03074312210083, "global_step": 586126, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.064934015274048, "global_step": 586127, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0888421535491943, "global_step": 586128, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0223968029022217, "global_step": 586129, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9820016622543335, "global_step": 586130, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0502054691314697, "global_step": 586131, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9871995449066162, "global_step": 586132, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9463764429092407, "global_step": 586133, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0432796478271484, "global_step": 586134, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0164620876312256, "global_step": 586135, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0027425289154053, "global_step": 586136, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0147314071655273, "global_step": 586137, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0441300868988037, "global_step": 586138, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9929205179214478, "global_step": 586139, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.026674509048462, "global_step": 586140, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.078742265701294, "global_step": 586141, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0287587642669678, "global_step": 586142, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.130140542984009, "global_step": 586143, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.929396152496338, "global_step": 586144, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.030978202819824, "global_step": 586145, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0466558933258057, "global_step": 586146, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9638371467590332, "global_step": 586147, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0010483264923096, "global_step": 586148, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0192065238952637, "global_step": 586149, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0175251960754395, "global_step": 586150, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9899879693984985, "global_step": 586151, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.11924409866333, "global_step": 586152, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0139172077178955, "global_step": 586153, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0012636184692383, "global_step": 586154, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0140879154205322, "global_step": 586155, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0242679119110107, "global_step": 586156, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.028397560119629, "global_step": 586157, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.937580943107605, "global_step": 586158, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9406976699829102, "global_step": 586159, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.033515691757202, "global_step": 586160, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.050471544265747, "global_step": 586161, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9894267320632935, "global_step": 586162, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0773870944976807, "global_step": 586163, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0178375244140625, "global_step": 586164, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9427311420440674, "global_step": 586165, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.946864128112793, "global_step": 586166, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0466418266296387, "global_step": 586167, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9292010068893433, "global_step": 586168, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.993138313293457, "global_step": 586169, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.078444480895996, "global_step": 586170, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0137016773223877, "global_step": 586171, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0442428588867188, "global_step": 586172, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0767734050750732, "global_step": 586173, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.08575177192688, "global_step": 586174, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0270700454711914, "global_step": 586175, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.117926836013794, "global_step": 586176, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.042738437652588, "global_step": 586177, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0144903659820557, "global_step": 586178, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.061082601547241, "global_step": 586179, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0170674324035645, "global_step": 586180, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9883089065551758, "global_step": 586181, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.052626132965088, "global_step": 586182, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0506772994995117, "global_step": 586183, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0254809856414795, "global_step": 586184, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9889891147613525, "global_step": 586185, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.014998197555542, "global_step": 586186, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0103790760040283, "global_step": 586187, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.968326449394226, "global_step": 586188, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9995043277740479, "global_step": 586189, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0131845474243164, "global_step": 586190, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0330867767333984, "global_step": 586191, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9339488744735718, "global_step": 586192, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.027902364730835, "global_step": 586193, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0630173683166504, "global_step": 586194, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9709628820419312, "global_step": 586195, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.021052598953247, "global_step": 586196, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9969865083694458, "global_step": 586197, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.099259614944458, "global_step": 586198, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0008955001831055, "global_step": 586199, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1253092288970947, "global_step": 586200, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9615213871002197, "global_step": 586201, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9657200574874878, "global_step": 586202, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.047994613647461, "global_step": 586203, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.007546901702881, "global_step": 586204, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0159826278686523, "global_step": 586205, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0587825775146484, "global_step": 586206, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0036439895629883, "global_step": 586207, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.048238754272461, "global_step": 586208, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.003584146499634, "global_step": 586209, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.021873712539673, "global_step": 586210, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0226032733917236, "global_step": 586211, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0593831539154053, "global_step": 586212, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.107990264892578, "global_step": 586213, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9476948976516724, "global_step": 586214, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9849005937576294, "global_step": 586215, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.006035089492798, "global_step": 586216, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9903241395950317, "global_step": 586217, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9841561317443848, "global_step": 586218, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.077861785888672, "global_step": 586219, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.080857276916504, "global_step": 586220, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.059114694595337, "global_step": 586221, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.005237579345703, "global_step": 586222, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.005812644958496, "global_step": 586223, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9146174192428589, "global_step": 586224, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.992929458618164, "global_step": 586225, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.036118268966675, "global_step": 586226, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0151267051696777, "global_step": 586227, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0758230686187744, "global_step": 586228, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1308960914611816, "global_step": 586229, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9802839756011963, "global_step": 586230, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.101214647293091, "global_step": 586231, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.014284372329712, "global_step": 586232, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.053114175796509, "global_step": 586233, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0783138275146484, "global_step": 586234, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9934370517730713, "global_step": 586235, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0270564556121826, "global_step": 586236, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0149412155151367, "global_step": 586237, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.039212226867676, "global_step": 586238, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0486533641815186, "global_step": 586239, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9918862581253052, "global_step": 586240, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.053990364074707, "global_step": 586241, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0901880264282227, "global_step": 586242, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0171029567718506, "global_step": 586243, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.128385543823242, "global_step": 586244, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0672004222869873, "global_step": 586245, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.057222366333008, "global_step": 586246, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9579445123672485, "global_step": 586247, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.031334400177002, "global_step": 586248, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0247597694396973, "global_step": 586249, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.949799656867981, "global_step": 586250, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.146851062774658, "global_step": 586251, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0139198303222656, "global_step": 586252, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9889991283416748, "global_step": 586253, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.006849527359009, "global_step": 586254, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9945188760757446, "global_step": 586255, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.055464744567871, "global_step": 586256, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.000588893890381, "global_step": 586257, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0354933738708496, "global_step": 586258, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.003925323486328, "global_step": 586259, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1423330307006836, "global_step": 586260, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0173540115356445, "global_step": 586261, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.089735746383667, "global_step": 586262, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.037318706512451, "global_step": 586263, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.021087169647217, "global_step": 586264, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1445133686065674, "global_step": 586265, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0256378650665283, "global_step": 586266, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.924545168876648, "global_step": 586267, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.089799642562866, "global_step": 586268, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0166633129119873, "global_step": 586269, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.028230667114258, "global_step": 586270, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9445751905441284, "global_step": 586271, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.07267427444458, "global_step": 586272, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.000913619995117, "global_step": 586273, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9267468452453613, "global_step": 586274, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9161733388900757, "global_step": 586275, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9873839616775513, "global_step": 586276, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.095339775085449, "global_step": 586277, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.046302556991577, "global_step": 586278, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0359156131744385, "global_step": 586279, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0898666381835938, "global_step": 586280, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9791520833969116, "global_step": 586281, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.083237886428833, "global_step": 586282, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0220584869384766, "global_step": 586283, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1155731678009033, "global_step": 586284, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.011815071105957, "global_step": 586285, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9403284788131714, "global_step": 586286, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0006823539733887, "global_step": 586287, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.035194158554077, "global_step": 586288, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0311214923858643, "global_step": 586289, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.978665828704834, "global_step": 586290, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.135193347930908, "global_step": 586291, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.062406063079834, "global_step": 586292, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0204403400421143, "global_step": 586293, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0053770542144775, "global_step": 586294, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0561985969543457, "global_step": 586295, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.052253007888794, "global_step": 586296, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0002896785736084, "global_step": 586297, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9681531190872192, "global_step": 586298, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0257205963134766, "global_step": 586299, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0469019412994385, "global_step": 586300, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0509893894195557, "global_step": 586301, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0143561363220215, "global_step": 586302, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.962302803993225, "global_step": 586303, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9174120426177979, "global_step": 586304, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.034165859222412, "global_step": 586305, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.003554105758667, "global_step": 586306, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9654098749160767, "global_step": 586307, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0064244270324707, "global_step": 586308, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.944918155670166, "global_step": 586309, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.019948959350586, "global_step": 586310, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.99427330493927, "global_step": 586311, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9552640914916992, "global_step": 586312, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0137107372283936, "global_step": 586313, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.072115659713745, "global_step": 586314, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0014328956604004, "global_step": 586315, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9643841981887817, "global_step": 586316, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9564907550811768, "global_step": 586317, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.011030673980713, "global_step": 586318, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.028381824493408, "global_step": 586319, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.000213623046875, "global_step": 586320, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.059894323348999, "global_step": 586321, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.967262864112854, "global_step": 586322, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0524373054504395, "global_step": 586323, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.979968547821045, "global_step": 586324, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.099733352661133, "global_step": 586325, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.975685715675354, "global_step": 586326, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9804637432098389, "global_step": 586327, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9660505056381226, "global_step": 586328, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.009157419204712, "global_step": 586329, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.052412748336792, "global_step": 586330, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.096980333328247, "global_step": 586331, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.048043727874756, "global_step": 586332, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0404624938964844, "global_step": 586333, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.944292426109314, "global_step": 586334, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9744231700897217, "global_step": 586335, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0269839763641357, "global_step": 586336, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0936050415039062, "global_step": 586337, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9765065908432007, "global_step": 586338, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.028891086578369, "global_step": 586339, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9123928546905518, "global_step": 586340, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.040257215499878, "global_step": 586341, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9878953695297241, "global_step": 586342, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0112621784210205, "global_step": 586343, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.039120674133301, "global_step": 586344, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9581043720245361, "global_step": 586345, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0219616889953613, "global_step": 586346, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0192947387695312, "global_step": 586347, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9815431833267212, "global_step": 586348, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9872502088546753, "global_step": 586349, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.101285696029663, "global_step": 586350, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9961216449737549, "global_step": 586351, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9566096067428589, "global_step": 586352, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9299622774124146, "global_step": 586353, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.01291823387146, "global_step": 586354, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0413708686828613, "global_step": 586355, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0329132080078125, "global_step": 586356, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0705535411834717, "global_step": 586357, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9290688037872314, "global_step": 586358, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.059080123901367, "global_step": 586359, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0207552909851074, "global_step": 586360, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9111629724502563, "global_step": 586361, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0770766735076904, "global_step": 586362, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9767043590545654, "global_step": 586363, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9881224632263184, "global_step": 586364, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.046191692352295, "global_step": 586365, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.993841528892517, "global_step": 586366, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0134222507476807, "global_step": 586367, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.02819561958313, "global_step": 586368, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9769617319107056, "global_step": 586369, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0710341930389404, "global_step": 586370, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9804530143737793, "global_step": 586371, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.1017115116119385, "global_step": 586372, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.016291856765747, "global_step": 586373, "epoch": 954, "lr": 5e-05}
{"train_loss": 1.9805781841278076, "global_step": 586374, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0282232761383057, "global_step": 586375, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.0785181522369385, "global_step": 586376, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.01755952835083, "global_step": 586377, "epoch": 954, "lr": 5e-05}
{"train_loss": 2.044977903366089, "global_step": 586378, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9426108598709106, "global_step": 586379, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9753235578536987, "global_step": 586380, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0359039306640625, "global_step": 586381, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0236241817474365, "global_step": 586382, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.016066312789917, "global_step": 586383, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.03794264793396, "global_step": 586384, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9714909791946411, "global_step": 586385, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.000181198120117, "global_step": 586386, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9502203464508057, "global_step": 586387, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1375081539154053, "global_step": 586388, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9801242351531982, "global_step": 586389, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9779880046844482, "global_step": 586390, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.912969946861267, "global_step": 586391, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0423924922943115, "global_step": 586392, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9642904996871948, "global_step": 586393, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.979992151260376, "global_step": 586394, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0260379314422607, "global_step": 586395, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0433433055877686, "global_step": 586396, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.968445062637329, "global_step": 586397, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0350382328033447, "global_step": 586398, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0908186435699463, "global_step": 586399, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.00002121925354, "global_step": 586400, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.023036479949951, "global_step": 586401, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9942773580551147, "global_step": 586402, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.064394474029541, "global_step": 586403, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9334068298339844, "global_step": 586404, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0016071796417236, "global_step": 586405, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.89883291721344, "global_step": 586406, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0383553504943848, "global_step": 586407, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.093590259552002, "global_step": 586408, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9686068296432495, "global_step": 586409, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.164020299911499, "global_step": 586410, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0808420181274414, "global_step": 586411, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0412063598632812, "global_step": 586412, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9713538885116577, "global_step": 586413, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9178495407104492, "global_step": 586414, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0599920749664307, "global_step": 586415, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0399868488311768, "global_step": 586416, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9872785806655884, "global_step": 586417, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.033115863800049, "global_step": 586418, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0599734783172607, "global_step": 586419, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9585697650909424, "global_step": 586420, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9793486595153809, "global_step": 586421, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9862301349639893, "global_step": 586422, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.8511675596237183, "global_step": 586423, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9853386878967285, "global_step": 586424, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9167336225509644, "global_step": 586425, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9974439144134521, "global_step": 586426, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.991445541381836, "global_step": 586427, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9965518712997437, "global_step": 586428, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0333242416381836, "global_step": 586429, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9750335216522217, "global_step": 586430, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9370330572128296, "global_step": 586431, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0496304035186768, "global_step": 586432, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0397400856018066, "global_step": 586433, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1436681747436523, "global_step": 586434, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9997533559799194, "global_step": 586435, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9137178659439087, "global_step": 586436, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0211617946624756, "global_step": 586437, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.012028932571411, "global_step": 586438, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.048591136932373, "global_step": 586439, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9923144578933716, "global_step": 586440, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9701881408691406, "global_step": 586441, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1530954837799072, "global_step": 586442, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0907304286956787, "global_step": 586443, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.025726079940796, "global_step": 586444, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0070552825927734, "global_step": 586445, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9887322187423706, "global_step": 586446, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9441829919815063, "global_step": 586447, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0310559272766113, "global_step": 586448, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9891010522842407, "global_step": 586449, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9960960149765015, "global_step": 586450, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.117809772491455, "global_step": 586451, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.044293165206909, "global_step": 586452, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9575742483139038, "global_step": 586453, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.935518741607666, "global_step": 586454, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.045760154724121, "global_step": 586455, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.900175929069519, "global_step": 586456, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0109245777130127, "global_step": 586457, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0643179416656494, "global_step": 586458, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9528777599334717, "global_step": 586459, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.033766746520996, "global_step": 586460, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0184152126312256, "global_step": 586461, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9387686252593994, "global_step": 586462, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9493224620819092, "global_step": 586463, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9464105367660522, "global_step": 586464, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0363433361053467, "global_step": 586465, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0311286449432373, "global_step": 586466, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.92191481590271, "global_step": 586467, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9844088554382324, "global_step": 586468, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0810959339141846, "global_step": 586469, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.032365560531616, "global_step": 586470, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9523475170135498, "global_step": 586471, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.967120885848999, "global_step": 586472, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9479526281356812, "global_step": 586473, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0891528129577637, "global_step": 586474, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0660183429718018, "global_step": 586475, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9630303382873535, "global_step": 586476, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9851398468017578, "global_step": 586477, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.059011220932007, "global_step": 586478, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.040297746658325, "global_step": 586479, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9812802076339722, "global_step": 586480, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9805978536605835, "global_step": 586481, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0303828716278076, "global_step": 586482, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1243581771850586, "global_step": 586483, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0470762252807617, "global_step": 586484, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.93625807762146, "global_step": 586485, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0325608253479004, "global_step": 586486, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.8873471021652222, "global_step": 586487, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9683430194854736, "global_step": 586488, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0529842376708984, "global_step": 586489, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.014392137527466, "global_step": 586490, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0425522327423096, "global_step": 586491, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0294411182403564, "global_step": 586492, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.03117036819458, "global_step": 586493, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.953454613685608, "global_step": 586494, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.054309129714966, "global_step": 586495, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9295423030853271, "global_step": 586496, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9340705871582031, "global_step": 586497, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0264551639556885, "global_step": 586498, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0138773918151855, "global_step": 586499, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1206820011138916, "global_step": 586500, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0016732215881348, "global_step": 586501, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0011229515075684, "global_step": 586502, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0204453468322754, "global_step": 586503, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.032754898071289, "global_step": 586504, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9251489639282227, "global_step": 586505, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.996438980102539, "global_step": 586506, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.024216413497925, "global_step": 586507, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9426708221435547, "global_step": 586508, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.006429672241211, "global_step": 586509, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.916495442390442, "global_step": 586510, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1174111366271973, "global_step": 586511, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9163097143173218, "global_step": 586512, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.122676372528076, "global_step": 586513, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.050710678100586, "global_step": 586514, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9413706064224243, "global_step": 586515, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.955802321434021, "global_step": 586516, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.088629961013794, "global_step": 586517, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0561623573303223, "global_step": 586518, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0526793003082275, "global_step": 586519, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0068233013153076, "global_step": 586520, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.074673652648926, "global_step": 586521, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0121514797210693, "global_step": 586522, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0330052375793457, "global_step": 586523, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.007988929748535, "global_step": 586524, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.042510747909546, "global_step": 586525, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9998486042022705, "global_step": 586526, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0120654106140137, "global_step": 586527, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.018120765686035, "global_step": 586528, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0386719703674316, "global_step": 586529, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9124412536621094, "global_step": 586530, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.891677737236023, "global_step": 586531, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9744056463241577, "global_step": 586532, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0939693450927734, "global_step": 586533, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9881705045700073, "global_step": 586534, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0284805297851562, "global_step": 586535, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9334603548049927, "global_step": 586536, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0211563110351562, "global_step": 586537, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.026862144470215, "global_step": 586538, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9200260639190674, "global_step": 586539, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0862817764282227, "global_step": 586540, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0387625694274902, "global_step": 586541, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0470621585845947, "global_step": 586542, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0821666717529297, "global_step": 586543, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9526840448379517, "global_step": 586544, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9697810411453247, "global_step": 586545, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0549049377441406, "global_step": 586546, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9750324487686157, "global_step": 586547, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.983925223350525, "global_step": 586548, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.079653739929199, "global_step": 586549, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9733309745788574, "global_step": 586550, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9814159870147705, "global_step": 586551, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0051519870758057, "global_step": 586552, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9813275337219238, "global_step": 586553, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9675501585006714, "global_step": 586554, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9968526363372803, "global_step": 586555, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0261058807373047, "global_step": 586556, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.988660216331482, "global_step": 586557, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.944230079650879, "global_step": 586558, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0073254108428955, "global_step": 586559, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0561013221740723, "global_step": 586560, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.049544095993042, "global_step": 586561, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.006211280822754, "global_step": 586562, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9466965198516846, "global_step": 586563, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.038614511489868, "global_step": 586564, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0506110191345215, "global_step": 586565, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9432885646820068, "global_step": 586566, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.074550151824951, "global_step": 586567, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0679476261138916, "global_step": 586568, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9969805479049683, "global_step": 586569, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9704387187957764, "global_step": 586570, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9414734840393066, "global_step": 586571, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0678157806396484, "global_step": 586572, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.002743721008301, "global_step": 586573, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.967864990234375, "global_step": 586574, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0131537914276123, "global_step": 586575, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9989410638809204, "global_step": 586576, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0464560985565186, "global_step": 586577, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0136990547180176, "global_step": 586578, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9797725677490234, "global_step": 586579, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0197043418884277, "global_step": 586580, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9215384721755981, "global_step": 586581, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0973658561706543, "global_step": 586582, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0404562950134277, "global_step": 586583, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9823533296585083, "global_step": 586584, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.965606451034546, "global_step": 586585, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.03035306930542, "global_step": 586586, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.988409161567688, "global_step": 586587, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9857697486877441, "global_step": 586588, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9693692922592163, "global_step": 586589, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.967261552810669, "global_step": 586590, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9772536754608154, "global_step": 586591, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9324383735656738, "global_step": 586592, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9787228107452393, "global_step": 586593, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0616376399993896, "global_step": 586594, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.001446008682251, "global_step": 586595, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9349397420883179, "global_step": 586596, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.031663656234741, "global_step": 586597, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.98017156124115, "global_step": 586598, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.086682081222534, "global_step": 586599, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0557403564453125, "global_step": 586600, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.07723069190979, "global_step": 586601, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.002734422683716, "global_step": 586602, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9777581691741943, "global_step": 586603, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9644124507904053, "global_step": 586604, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.003885507583618, "global_step": 586605, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0400490760803223, "global_step": 586606, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0454821586608887, "global_step": 586607, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0285696983337402, "global_step": 586608, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9983704090118408, "global_step": 586609, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.86822509765625, "global_step": 586610, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9806593656539917, "global_step": 586611, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0104923248291016, "global_step": 586612, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0214321613311768, "global_step": 586613, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.031863212585449, "global_step": 586614, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0733797550201416, "global_step": 586615, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.056962490081787, "global_step": 586616, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9895097017288208, "global_step": 586617, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9494776725769043, "global_step": 586618, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.072683811187744, "global_step": 586619, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9586243629455566, "global_step": 586620, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.967904806137085, "global_step": 586621, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9952093362808228, "global_step": 586622, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0044138431549072, "global_step": 586623, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9965429306030273, "global_step": 586624, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0731399059295654, "global_step": 586625, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9564789533615112, "global_step": 586626, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0292272567749023, "global_step": 586627, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0140645503997803, "global_step": 586628, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0290403366088867, "global_step": 586629, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9915602207183838, "global_step": 586630, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0254759788513184, "global_step": 586631, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.031158208847046, "global_step": 586632, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0730934143066406, "global_step": 586633, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.036271810531616, "global_step": 586634, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9917454719543457, "global_step": 586635, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9814395904541016, "global_step": 586636, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.018887519836426, "global_step": 586637, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0388729572296143, "global_step": 586638, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.000173807144165, "global_step": 586639, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0491340160369873, "global_step": 586640, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.056769609451294, "global_step": 586641, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9750345945358276, "global_step": 586642, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9420528411865234, "global_step": 586643, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0221853256225586, "global_step": 586644, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9765187501907349, "global_step": 586645, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0937583446502686, "global_step": 586646, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.014028310775757, "global_step": 586647, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.946036696434021, "global_step": 586648, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9657752513885498, "global_step": 586649, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.032881498336792, "global_step": 586650, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9775081872940063, "global_step": 586651, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0067598819732666, "global_step": 586652, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9238072633743286, "global_step": 586653, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0134520530700684, "global_step": 586654, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0107028484344482, "global_step": 586655, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.008491039276123, "global_step": 586656, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9183603525161743, "global_step": 586657, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.045973777770996, "global_step": 586658, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0005321502685547, "global_step": 586659, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9350008964538574, "global_step": 586660, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0016839504241943, "global_step": 586661, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.102571487426758, "global_step": 586662, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.026388168334961, "global_step": 586663, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.070603370666504, "global_step": 586664, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0796425342559814, "global_step": 586665, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.047680616378784, "global_step": 586666, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0602216720581055, "global_step": 586667, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.053274631500244, "global_step": 586668, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.020301103591919, "global_step": 586669, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1242969036102295, "global_step": 586670, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.039957284927368, "global_step": 586671, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.049543857574463, "global_step": 586672, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.06162166595459, "global_step": 586673, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9885668754577637, "global_step": 586674, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.092683792114258, "global_step": 586675, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0428054332733154, "global_step": 586676, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0478503704071045, "global_step": 586677, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.048558473587036, "global_step": 586678, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9193226099014282, "global_step": 586679, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.05332088470459, "global_step": 586680, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9938957691192627, "global_step": 586681, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0292484760284424, "global_step": 586682, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.996010422706604, "global_step": 586683, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.968859314918518, "global_step": 586684, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0177111625671387, "global_step": 586685, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.10649037361145, "global_step": 586686, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9560366868972778, "global_step": 586687, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0920915603637695, "global_step": 586688, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9411550760269165, "global_step": 586689, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0502586364746094, "global_step": 586690, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9793251752853394, "global_step": 586691, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1011455059051514, "global_step": 586692, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.055042266845703, "global_step": 586693, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.995598316192627, "global_step": 586694, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9110418558120728, "global_step": 586695, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9909347295761108, "global_step": 586696, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.986720085144043, "global_step": 586697, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0797524452209473, "global_step": 586698, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.012561559677124, "global_step": 586699, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.973203182220459, "global_step": 586700, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1291661262512207, "global_step": 586701, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9952363967895508, "global_step": 586702, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0605311393737793, "global_step": 586703, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0343849658966064, "global_step": 586704, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.949310541152954, "global_step": 586705, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0091500282287598, "global_step": 586706, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0864880084991455, "global_step": 586707, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9014475345611572, "global_step": 586708, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.926513910293579, "global_step": 586709, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0309035778045654, "global_step": 586710, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.109367609024048, "global_step": 586711, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9565365314483643, "global_step": 586712, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.019806385040283, "global_step": 586713, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.02066969871521, "global_step": 586714, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.994442105293274, "global_step": 586715, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0598878860473633, "global_step": 586716, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.955835223197937, "global_step": 586717, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0558245182037354, "global_step": 586718, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9816490411758423, "global_step": 586719, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9216281175613403, "global_step": 586720, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0230472087860107, "global_step": 586721, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9321399927139282, "global_step": 586722, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.01529860496521, "global_step": 586723, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.035451889038086, "global_step": 586724, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9940904378890991, "global_step": 586725, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0156402587890625, "global_step": 586726, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.003495216369629, "global_step": 586727, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9668248891830444, "global_step": 586728, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9413574934005737, "global_step": 586729, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.933241844177246, "global_step": 586730, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.995258092880249, "global_step": 586731, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0002365112304688, "global_step": 586732, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0473976135253906, "global_step": 586733, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9841986894607544, "global_step": 586734, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0135695934295654, "global_step": 586735, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1069867610931396, "global_step": 586736, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9591087102890015, "global_step": 586737, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0653514862060547, "global_step": 586738, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.01214861869812, "global_step": 586739, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0638465881347656, "global_step": 586740, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9683626890182495, "global_step": 586741, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1060078144073486, "global_step": 586742, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9285072088241577, "global_step": 586743, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9602386951446533, "global_step": 586744, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.024564027786255, "global_step": 586745, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.00888729095459, "global_step": 586746, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0645065307617188, "global_step": 586747, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.988971471786499, "global_step": 586748, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0226173400878906, "global_step": 586749, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.011413812637329, "global_step": 586750, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9001686573028564, "global_step": 586751, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9911543130874634, "global_step": 586752, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.005162239074707, "global_step": 586753, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0433335304260254, "global_step": 586754, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.047337532043457, "global_step": 586755, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.093357801437378, "global_step": 586756, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.027570962905884, "global_step": 586757, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9397165775299072, "global_step": 586758, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9938243627548218, "global_step": 586759, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0481579303741455, "global_step": 586760, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9924771785736084, "global_step": 586761, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.050236225128174, "global_step": 586762, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.03438138961792, "global_step": 586763, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9573752880096436, "global_step": 586764, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.00949764251709, "global_step": 586765, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.040112018585205, "global_step": 586766, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9751094579696655, "global_step": 586767, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.002843141555786, "global_step": 586768, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9445754289627075, "global_step": 586769, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.061539888381958, "global_step": 586770, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0559005737304688, "global_step": 586771, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9557979106903076, "global_step": 586772, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9896376132965088, "global_step": 586773, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0678622722625732, "global_step": 586774, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0071868896484375, "global_step": 586775, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.03401780128479, "global_step": 586776, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0417051315307617, "global_step": 586777, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0554263591766357, "global_step": 586778, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.918969750404358, "global_step": 586779, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9574192762374878, "global_step": 586780, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0364766120910645, "global_step": 586781, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9930894374847412, "global_step": 586782, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.039839744567871, "global_step": 586783, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.068134307861328, "global_step": 586784, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1282050609588623, "global_step": 586785, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9881891012191772, "global_step": 586786, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.037309408187866, "global_step": 586787, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.948638677597046, "global_step": 586788, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9821945428848267, "global_step": 586789, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.984063982963562, "global_step": 586790, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0200133323669434, "global_step": 586791, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.978203535079956, "global_step": 586792, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0485100746154785, "global_step": 586793, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.085953712463379, "global_step": 586794, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9857196807861328, "global_step": 586795, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9330852031707764, "global_step": 586796, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.014876127243042, "global_step": 586797, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9703787565231323, "global_step": 586798, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0286409854888916, "global_step": 586799, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.013704299926758, "global_step": 586800, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.117600440979004, "global_step": 586801, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9662983417510986, "global_step": 586802, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0389018058776855, "global_step": 586803, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9799797534942627, "global_step": 586804, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9764035940170288, "global_step": 586805, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0013468265533447, "global_step": 586806, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.011751174926758, "global_step": 586807, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9996116161346436, "global_step": 586808, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.969383955001831, "global_step": 586809, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0182301998138428, "global_step": 586810, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9827187061309814, "global_step": 586811, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0302224159240723, "global_step": 586812, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.899596095085144, "global_step": 586813, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9843281507492065, "global_step": 586814, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0372042655944824, "global_step": 586815, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0534415245056152, "global_step": 586816, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9927462339401245, "global_step": 586817, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9697632789611816, "global_step": 586818, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.049351453781128, "global_step": 586819, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0005829334259033, "global_step": 586820, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9357746839523315, "global_step": 586821, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.120328903198242, "global_step": 586822, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0644643306732178, "global_step": 586823, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0282304286956787, "global_step": 586824, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1074812412261963, "global_step": 586825, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.004484176635742, "global_step": 586826, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0682263374328613, "global_step": 586827, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9707492589950562, "global_step": 586828, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0508413314819336, "global_step": 586829, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.954421043395996, "global_step": 586830, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0611703395843506, "global_step": 586831, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0779850482940674, "global_step": 586832, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0448622703552246, "global_step": 586833, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1194517612457275, "global_step": 586834, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.025146961212158, "global_step": 586835, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9510879516601562, "global_step": 586836, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0095107555389404, "global_step": 586837, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0331568717956543, "global_step": 586838, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9800530672073364, "global_step": 586839, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1449291706085205, "global_step": 586840, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0433738231658936, "global_step": 586841, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0578513145446777, "global_step": 586842, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9734233617782593, "global_step": 586843, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.029891014099121, "global_step": 586844, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0527539253234863, "global_step": 586845, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0437631607055664, "global_step": 586846, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.132750988006592, "global_step": 586847, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.114692449569702, "global_step": 586848, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.037973165512085, "global_step": 586849, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9968019723892212, "global_step": 586850, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.084324836730957, "global_step": 586851, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9747772216796875, "global_step": 586852, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.007392644882202, "global_step": 586853, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9752477407455444, "global_step": 586854, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9666866064071655, "global_step": 586855, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.052093982696533, "global_step": 586856, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.959584355354309, "global_step": 586857, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.8926070928573608, "global_step": 586858, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0176823139190674, "global_step": 586859, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.084900140762329, "global_step": 586860, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9899920225143433, "global_step": 586861, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0361080169677734, "global_step": 586862, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0345547199249268, "global_step": 586863, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0893988609313965, "global_step": 586864, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0801918506622314, "global_step": 586865, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0178768634796143, "global_step": 586866, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0226056575775146, "global_step": 586867, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9486057758331299, "global_step": 586868, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.018228054046631, "global_step": 586869, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0167250633239746, "global_step": 586870, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1518874168395996, "global_step": 586871, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9802913665771484, "global_step": 586872, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9499542713165283, "global_step": 586873, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0383596420288086, "global_step": 586874, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9278348684310913, "global_step": 586875, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9524738788604736, "global_step": 586876, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9971814155578613, "global_step": 586877, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.950453281402588, "global_step": 586878, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.031184196472168, "global_step": 586879, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9007585048675537, "global_step": 586880, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1597321033477783, "global_step": 586881, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.042811632156372, "global_step": 586882, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9406214952468872, "global_step": 586883, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0436627864837646, "global_step": 586884, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.057539463043213, "global_step": 586885, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9764071702957153, "global_step": 586886, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9869513511657715, "global_step": 586887, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0258963108062744, "global_step": 586888, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.947357416152954, "global_step": 586889, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0114593505859375, "global_step": 586890, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.016826629638672, "global_step": 586891, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.034135580062866, "global_step": 586892, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0940041542053223, "global_step": 586893, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0810654163360596, "global_step": 586894, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.066934585571289, "global_step": 586895, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.08536696434021, "global_step": 586896, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.128680467605591, "global_step": 586897, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.071221113204956, "global_step": 586898, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0287327766418457, "global_step": 586899, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.980545997619629, "global_step": 586900, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0433058738708496, "global_step": 586901, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9100457429885864, "global_step": 586902, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0630269050598145, "global_step": 586903, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.034475326538086, "global_step": 586904, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.964051604270935, "global_step": 586905, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0291435718536377, "global_step": 586906, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0325393676757812, "global_step": 586907, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.024428606033325, "global_step": 586908, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0346527099609375, "global_step": 586909, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9874327182769775, "global_step": 586910, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9811437129974365, "global_step": 586911, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0095348358154297, "global_step": 586912, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9291446208953857, "global_step": 586913, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.02921462059021, "global_step": 586914, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.048574686050415, "global_step": 586915, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0120866298675537, "global_step": 586916, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9951486587524414, "global_step": 586917, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0527350902557373, "global_step": 586918, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9460598230361938, "global_step": 586919, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9927408695220947, "global_step": 586920, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9963825941085815, "global_step": 586921, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.952964425086975, "global_step": 586922, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0642035007476807, "global_step": 586923, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.06803560256958, "global_step": 586924, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9301097393035889, "global_step": 586925, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0365471839904785, "global_step": 586926, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9614989757537842, "global_step": 586927, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9578771591186523, "global_step": 586928, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0782179832458496, "global_step": 586929, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0579092502593994, "global_step": 586930, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1029443740844727, "global_step": 586931, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.039820432662964, "global_step": 586932, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.984395146369934, "global_step": 586933, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9892799854278564, "global_step": 586934, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0268805027008057, "global_step": 586935, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0139498710632324, "global_step": 586936, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9389123916625977, "global_step": 586937, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0097463130950928, "global_step": 586938, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.972337007522583, "global_step": 586939, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0275278091430664, "global_step": 586940, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0742735862731934, "global_step": 586941, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.017568349838257, "global_step": 586942, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.983528971672058, "global_step": 586943, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.00093936920166, "global_step": 586944, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9636931419372559, "global_step": 586945, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.068478584289551, "global_step": 586946, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0140316486358643, "global_step": 586947, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.955437421798706, "global_step": 586948, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0329277515411377, "global_step": 586949, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.045496940612793, "global_step": 586950, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0096848011016846, "global_step": 586951, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0185134410858154, "global_step": 586952, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0508596897125244, "global_step": 586953, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0492990016937256, "global_step": 586954, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.037461042404175, "global_step": 586955, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.004539966583252, "global_step": 586956, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9545081853866577, "global_step": 586957, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0536015033721924, "global_step": 586958, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0279226303100586, "global_step": 586959, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.985023856163025, "global_step": 586960, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1114673614501953, "global_step": 586961, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.037666082382202, "global_step": 586962, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9598125219345093, "global_step": 586963, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0769760608673096, "global_step": 586964, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9689899682998657, "global_step": 586965, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9964858293533325, "global_step": 586966, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.960547924041748, "global_step": 586967, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.029832601547241, "global_step": 586968, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0664262771606445, "global_step": 586969, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0059256553649902, "global_step": 586970, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0185582637786865, "global_step": 586971, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.023716926574707, "global_step": 586972, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0017080307006836, "global_step": 586973, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9806458950042725, "global_step": 586974, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.042638063430786, "global_step": 586975, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9635604619979858, "global_step": 586976, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.109168529510498, "global_step": 586977, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.050158977508545, "global_step": 586978, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0648140907287598, "global_step": 586979, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.028428792953491, "global_step": 586980, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.039381265640259, "global_step": 586981, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0374059677124023, "global_step": 586982, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0595669746398926, "global_step": 586983, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9834566116333008, "global_step": 586984, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9311140775680542, "global_step": 586985, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0031301975250244, "global_step": 586986, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9751131534576416, "global_step": 586987, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0292177200317383, "global_step": 586988, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9768081903457642, "global_step": 586989, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.079159736633301, "global_step": 586990, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0157182216644287, "global_step": 586991, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9670225381851196, "global_step": 586992, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9648873805999756, "global_step": 586993, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9830224514007568, "global_step": 586994, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0208940505981445, "global_step": 586995, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9778013229370117, "global_step": 586996, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9946680068969727, "global_step": 586997, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.003012180328369, "global_step": 586998, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.092707872390747, "global_step": 586999, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.030608654022217, "global_step": 587000, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.968295693397522, "global_step": 587001, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9311026334762573, "global_step": 587002, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9394205808639526, "global_step": 587003, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0624170303344727, "global_step": 587004, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9706470966339111, "global_step": 587005, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.086963653564453, "global_step": 587006, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0263946056365967, "global_step": 587007, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0324721336364746, "global_step": 587008, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0333361625671387, "global_step": 587009, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0272605419158936, "global_step": 587010, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0172605514526367, "global_step": 587011, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.04988169670105, "global_step": 587012, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9882891178131104, "global_step": 587013, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0579285621643066, "global_step": 587014, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0267913341522217, "global_step": 587015, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.096219301223755, "global_step": 587016, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0267066955566406, "global_step": 587017, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.057438850402832, "global_step": 587018, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0062782764434814, "global_step": 587019, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0405471324920654, "global_step": 587020, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0466384887695312, "global_step": 587021, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9749454259872437, "global_step": 587022, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0504648685455322, "global_step": 587023, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.082655668258667, "global_step": 587024, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9920397996902466, "global_step": 587025, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9686022996902466, "global_step": 587026, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.025801420211792, "global_step": 587027, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0427803993225098, "global_step": 587028, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.050034523010254, "global_step": 587029, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.079874277114868, "global_step": 587030, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.019864559173584, "global_step": 587031, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0341625213623047, "global_step": 587032, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.014620065689087, "global_step": 587033, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.064446210861206, "global_step": 587034, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.057098627090454, "global_step": 587035, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0421056747436523, "global_step": 587036, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9769572019577026, "global_step": 587037, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9506454467773438, "global_step": 587038, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.951339602470398, "global_step": 587039, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.033318042755127, "global_step": 587040, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0239861011505127, "global_step": 587041, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.046586513519287, "global_step": 587042, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.055856227874756, "global_step": 587043, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.064053535461426, "global_step": 587044, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.000227928161621, "global_step": 587045, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0630338191986084, "global_step": 587046, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.997512936592102, "global_step": 587047, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0937318801879883, "global_step": 587048, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0716962814331055, "global_step": 587049, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0101006031036377, "global_step": 587050, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9838627576828003, "global_step": 587051, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9722083806991577, "global_step": 587052, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.935610055923462, "global_step": 587053, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0872509479522705, "global_step": 587054, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9537506103515625, "global_step": 587055, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.031445264816284, "global_step": 587056, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9862382411956787, "global_step": 587057, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9831634759902954, "global_step": 587058, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9537973403930664, "global_step": 587059, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9975495338439941, "global_step": 587060, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0959813594818115, "global_step": 587061, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9308501482009888, "global_step": 587062, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.00390625, "global_step": 587063, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9663383960723877, "global_step": 587064, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.009796619415283, "global_step": 587065, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.952702522277832, "global_step": 587066, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.024456024169922, "global_step": 587067, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.957675576210022, "global_step": 587068, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.041370153427124, "global_step": 587069, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1354329586029053, "global_step": 587070, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9984607696533203, "global_step": 587071, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9910101890563965, "global_step": 587072, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.986013412475586, "global_step": 587073, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9926789999008179, "global_step": 587074, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.08083438873291, "global_step": 587075, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0243849754333496, "global_step": 587076, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.09993052482605, "global_step": 587077, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1123085021972656, "global_step": 587078, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.051105260848999, "global_step": 587079, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9735703468322754, "global_step": 587080, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0488531589508057, "global_step": 587081, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.038698673248291, "global_step": 587082, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0234241485595703, "global_step": 587083, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9681835174560547, "global_step": 587084, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.087806463241577, "global_step": 587085, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.041769504547119, "global_step": 587086, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.920809268951416, "global_step": 587087, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.039820432662964, "global_step": 587088, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.003568649291992, "global_step": 587089, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9754853248596191, "global_step": 587090, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.034790515899658, "global_step": 587091, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.075537919998169, "global_step": 587092, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0513060092926025, "global_step": 587093, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0598161220550537, "global_step": 587094, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9153459072113037, "global_step": 587095, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9457168579101562, "global_step": 587096, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.998045563697815, "global_step": 587097, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0868186950683594, "global_step": 587098, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.8982524871826172, "global_step": 587099, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9869714975357056, "global_step": 587100, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.047428846359253, "global_step": 587101, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9893141984939575, "global_step": 587102, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1050498485565186, "global_step": 587103, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0405514240264893, "global_step": 587104, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0248420238494873, "global_step": 587105, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9793823957443237, "global_step": 587106, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.931563138961792, "global_step": 587107, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9800113439559937, "global_step": 587108, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9957724809646606, "global_step": 587109, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.091970205307007, "global_step": 587110, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9444386959075928, "global_step": 587111, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0010600090026855, "global_step": 587112, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.045938014984131, "global_step": 587113, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.021186113357544, "global_step": 587114, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9864909648895264, "global_step": 587115, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0501301288604736, "global_step": 587116, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.027003049850464, "global_step": 587117, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0402791500091553, "global_step": 587118, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0025391578674316, "global_step": 587119, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.002164840698242, "global_step": 587120, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0363082885742188, "global_step": 587121, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.07487416267395, "global_step": 587122, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0172109603881836, "global_step": 587123, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.057983875274658, "global_step": 587124, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.050985097885132, "global_step": 587125, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0464296340942383, "global_step": 587126, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1197259426116943, "global_step": 587127, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0586588382720947, "global_step": 587128, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.950303316116333, "global_step": 587129, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0085361003875732, "global_step": 587130, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9394608736038208, "global_step": 587131, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.087790012359619, "global_step": 587132, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9792606830596924, "global_step": 587133, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0214571952819824, "global_step": 587134, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.062898874282837, "global_step": 587135, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0112290382385254, "global_step": 587136, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.036309242248535, "global_step": 587137, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0052547454833984, "global_step": 587138, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0022847652435303, "global_step": 587139, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.01400089263916, "global_step": 587140, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0539498329162598, "global_step": 587141, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9874558448791504, "global_step": 587142, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.104804039001465, "global_step": 587143, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9752812385559082, "global_step": 587144, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0619187355041504, "global_step": 587145, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0007264614105225, "global_step": 587146, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0621066093444824, "global_step": 587147, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9945447444915771, "global_step": 587148, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9352141618728638, "global_step": 587149, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0528016090393066, "global_step": 587150, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0734760761260986, "global_step": 587151, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9919002056121826, "global_step": 587152, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0949130058288574, "global_step": 587153, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9689342975616455, "global_step": 587154, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9883424043655396, "global_step": 587155, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.049103260040283, "global_step": 587156, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.032269239425659, "global_step": 587157, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9628649950027466, "global_step": 587158, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0176892280578613, "global_step": 587159, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9747767448425293, "global_step": 587160, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0263049602508545, "global_step": 587161, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0088870525360107, "global_step": 587162, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.060426712036133, "global_step": 587163, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0176124572753906, "global_step": 587164, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.003268003463745, "global_step": 587165, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0277137756347656, "global_step": 587166, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.950478434562683, "global_step": 587167, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0267176628112793, "global_step": 587168, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.03499174118042, "global_step": 587169, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.095926284790039, "global_step": 587170, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.082981824874878, "global_step": 587171, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0098249912261963, "global_step": 587172, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0617682933807373, "global_step": 587173, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.110759735107422, "global_step": 587174, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9459710121154785, "global_step": 587175, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9855127334594727, "global_step": 587176, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.8915599584579468, "global_step": 587177, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9950225353240967, "global_step": 587178, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0692689418792725, "global_step": 587179, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.047403335571289, "global_step": 587180, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0284018516540527, "global_step": 587181, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0154099464416504, "global_step": 587182, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0729918479919434, "global_step": 587183, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.045931100845337, "global_step": 587184, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1199703216552734, "global_step": 587185, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9579046964645386, "global_step": 587186, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9554156064987183, "global_step": 587187, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.008774518966675, "global_step": 587188, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0255534648895264, "global_step": 587189, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0004937648773193, "global_step": 587190, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0065701007843018, "global_step": 587191, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9711259603500366, "global_step": 587192, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.073838472366333, "global_step": 587193, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9811956882476807, "global_step": 587194, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9366090297698975, "global_step": 587195, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0187766551971436, "global_step": 587196, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9527033567428589, "global_step": 587197, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0120463371276855, "global_step": 587198, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9889339208602905, "global_step": 587199, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0094802379608154, "global_step": 587200, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.107654333114624, "global_step": 587201, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9179036617279053, "global_step": 587202, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9410921335220337, "global_step": 587203, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.03747296333313, "global_step": 587204, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.069244384765625, "global_step": 587205, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.087172508239746, "global_step": 587206, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.990562915802002, "global_step": 587207, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0338144302368164, "global_step": 587208, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.00388765335083, "global_step": 587209, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.996203064918518, "global_step": 587210, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0122482776641846, "global_step": 587211, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.081671953201294, "global_step": 587212, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0357019901275635, "global_step": 587213, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9488370418548584, "global_step": 587214, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9799140691757202, "global_step": 587215, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0676004886627197, "global_step": 587216, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0470924377441406, "global_step": 587217, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.029050588607788, "global_step": 587218, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.022320508956909, "global_step": 587219, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.046823740005493, "global_step": 587220, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.982521891593933, "global_step": 587221, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0923664569854736, "global_step": 587222, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0089962482452393, "global_step": 587223, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.01381516456604, "global_step": 587224, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9810622930526733, "global_step": 587225, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9777549505233765, "global_step": 587226, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.029667615890503, "global_step": 587227, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9999144077301025, "global_step": 587228, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0313634872436523, "global_step": 587229, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9741284847259521, "global_step": 587230, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.983054757118225, "global_step": 587231, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9979119300842285, "global_step": 587232, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0234363079071045, "global_step": 587233, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0360400676727295, "global_step": 587234, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9669419527053833, "global_step": 587235, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9963260889053345, "global_step": 587236, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.035153865814209, "global_step": 587237, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.002833843231201, "global_step": 587238, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0674190521240234, "global_step": 587239, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.998293161392212, "global_step": 587240, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9600943326950073, "global_step": 587241, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.976122260093689, "global_step": 587242, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0827999114990234, "global_step": 587243, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0306496620178223, "global_step": 587244, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9845162630081177, "global_step": 587245, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9878082275390625, "global_step": 587246, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0015480518341064, "global_step": 587247, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.084792375564575, "global_step": 587248, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0383927822113037, "global_step": 587249, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9780335426330566, "global_step": 587250, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1227104663848877, "global_step": 587251, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0519750118255615, "global_step": 587252, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.951002836227417, "global_step": 587253, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9909625053405762, "global_step": 587254, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.921010136604309, "global_step": 587255, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.045422315597534, "global_step": 587256, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0599365234375, "global_step": 587257, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.064340353012085, "global_step": 587258, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0626423358917236, "global_step": 587259, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9830586910247803, "global_step": 587260, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0578951835632324, "global_step": 587261, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.03639817237854, "global_step": 587262, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.008223533630371, "global_step": 587263, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1073927879333496, "global_step": 587264, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.950255274772644, "global_step": 587265, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9996421337127686, "global_step": 587266, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0833020210266113, "global_step": 587267, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9497246742248535, "global_step": 587268, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.993048071861267, "global_step": 587269, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.021425485610962, "global_step": 587270, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.016461133956909, "global_step": 587271, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.017824411392212, "global_step": 587272, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.10414981842041, "global_step": 587273, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.029670476913452, "global_step": 587274, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9807261228561401, "global_step": 587275, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0068418979644775, "global_step": 587276, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.075188398361206, "global_step": 587277, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0592875480651855, "global_step": 587278, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0251524448394775, "global_step": 587279, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9294577836990356, "global_step": 587280, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0347256660461426, "global_step": 587281, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9545100927352905, "global_step": 587282, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.938724160194397, "global_step": 587283, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0148911476135254, "global_step": 587284, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9729372262954712, "global_step": 587285, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9942941665649414, "global_step": 587286, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0118465423583984, "global_step": 587287, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0104823112487793, "global_step": 587288, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9690372943878174, "global_step": 587289, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.961606502532959, "global_step": 587290, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0387985706329346, "global_step": 587291, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.976659893989563, "global_step": 587292, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.050579786300659, "global_step": 587293, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.047926425933838, "global_step": 587294, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0238640308380127, "global_step": 587295, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.142242670059204, "global_step": 587296, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0286130905151367, "global_step": 587297, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0977063179016113, "global_step": 587298, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.026470422744751, "global_step": 587299, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.033292055130005, "global_step": 587300, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.056007146835327, "global_step": 587301, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.079005718231201, "global_step": 587302, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0589535236358643, "global_step": 587303, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.947433590888977, "global_step": 587304, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.073629856109619, "global_step": 587305, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9771243333816528, "global_step": 587306, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9769015312194824, "global_step": 587307, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0368075370788574, "global_step": 587308, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0554702281951904, "global_step": 587309, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.1634464263916016, "global_step": 587310, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9455276727676392, "global_step": 587311, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.011018753051758, "global_step": 587312, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9804638624191284, "global_step": 587313, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0398924350738525, "global_step": 587314, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9901854991912842, "global_step": 587315, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0159478187561035, "global_step": 587316, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0674870014190674, "global_step": 587317, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0322141647338867, "global_step": 587318, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9798896312713623, "global_step": 587319, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0319056510925293, "global_step": 587320, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0190820693969727, "global_step": 587321, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0218915939331055, "global_step": 587322, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9928795099258423, "global_step": 587323, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0549561977386475, "global_step": 587324, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.092952013015747, "global_step": 587325, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0483272075653076, "global_step": 587326, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9833409786224365, "global_step": 587327, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9993335008621216, "global_step": 587328, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0026588439941406, "global_step": 587329, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9523262977600098, "global_step": 587330, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.120079278945923, "global_step": 587331, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0280606746673584, "global_step": 587332, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9681583642959595, "global_step": 587333, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.041701555252075, "global_step": 587334, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.95240318775177, "global_step": 587335, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.99396812915802, "global_step": 587336, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.114497661590576, "global_step": 587337, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9439818859100342, "global_step": 587338, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.02681303024292, "global_step": 587339, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9914319515228271, "global_step": 587340, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9656790494918823, "global_step": 587341, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.031552791595459, "global_step": 587342, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0489511489868164, "global_step": 587343, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.003293514251709, "global_step": 587344, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0798404216766357, "global_step": 587345, "epoch": 955, "lr": 5e-05}
{"train_loss": 2.0143544673919678, "global_step": 587346, "epoch": 955, "lr": 5e-05}
{"train_loss": 1.9018045663833618, "global_step": 587347, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0017881393432617, "global_step": 587348, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.056962490081787, "global_step": 587349, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0128159523010254, "global_step": 587350, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9939919710159302, "global_step": 587351, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0264289379119873, "global_step": 587352, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0773587226867676, "global_step": 587353, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.05971622467041, "global_step": 587354, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9806644916534424, "global_step": 587355, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.056028366088867, "global_step": 587356, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0038394927978516, "global_step": 587357, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0371692180633545, "global_step": 587358, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.961045742034912, "global_step": 587359, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.039630174636841, "global_step": 587360, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0038139820098877, "global_step": 587361, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9812520742416382, "global_step": 587362, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.976495623588562, "global_step": 587363, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9555585384368896, "global_step": 587364, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.975476861000061, "global_step": 587365, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9887075424194336, "global_step": 587366, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0063607692718506, "global_step": 587367, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0302677154541016, "global_step": 587368, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0671026706695557, "global_step": 587369, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.8786587715148926, "global_step": 587370, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.011260747909546, "global_step": 587371, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9954843521118164, "global_step": 587372, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9952499866485596, "global_step": 587373, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0107533931732178, "global_step": 587374, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.956855058670044, "global_step": 587375, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0687222480773926, "global_step": 587376, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9745237827301025, "global_step": 587377, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.984634280204773, "global_step": 587378, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9938337802886963, "global_step": 587379, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.020155191421509, "global_step": 587380, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9027855396270752, "global_step": 587381, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9716802835464478, "global_step": 587382, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.100172519683838, "global_step": 587383, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.8897809982299805, "global_step": 587384, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.961997389793396, "global_step": 587385, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.000612497329712, "global_step": 587386, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.978190302848816, "global_step": 587387, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.006066083908081, "global_step": 587388, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0832207202911377, "global_step": 587389, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.062953233718872, "global_step": 587390, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.081806182861328, "global_step": 587391, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9918001890182495, "global_step": 587392, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0489394664764404, "global_step": 587393, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.8853791952133179, "global_step": 587394, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0266618728637695, "global_step": 587395, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0694408416748047, "global_step": 587396, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.963639497756958, "global_step": 587397, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9407588243484497, "global_step": 587398, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9953750371932983, "global_step": 587399, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9660757780075073, "global_step": 587400, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0430192947387695, "global_step": 587401, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9760369062423706, "global_step": 587402, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.043170213699341, "global_step": 587403, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.036245822906494, "global_step": 587404, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9937915802001953, "global_step": 587405, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.041517972946167, "global_step": 587406, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0070276260375977, "global_step": 587407, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0663514137268066, "global_step": 587408, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0361204147338867, "global_step": 587409, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0373728275299072, "global_step": 587410, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0264430046081543, "global_step": 587411, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9870061874389648, "global_step": 587412, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.8942617177963257, "global_step": 587413, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9947340488433838, "global_step": 587414, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9671275615692139, "global_step": 587415, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9986672401428223, "global_step": 587416, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.063718795776367, "global_step": 587417, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0288941860198975, "global_step": 587418, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9699299335479736, "global_step": 587419, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.004518508911133, "global_step": 587420, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.032042980194092, "global_step": 587421, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0125181674957275, "global_step": 587422, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9673206806182861, "global_step": 587423, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.032644033432007, "global_step": 587424, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9598491191864014, "global_step": 587425, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.013699531555176, "global_step": 587426, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.045689344406128, "global_step": 587427, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.033273696899414, "global_step": 587428, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9797022342681885, "global_step": 587429, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9303172826766968, "global_step": 587430, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0453426837921143, "global_step": 587431, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0022225379943848, "global_step": 587432, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.1287434101104736, "global_step": 587433, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0471646785736084, "global_step": 587434, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0240464210510254, "global_step": 587435, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.044867753982544, "global_step": 587436, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9576846361160278, "global_step": 587437, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0308997631073, "global_step": 587438, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0153772830963135, "global_step": 587439, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0989022254943848, "global_step": 587440, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9250712394714355, "global_step": 587441, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.003980875015259, "global_step": 587442, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0654399394989014, "global_step": 587443, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0363423824310303, "global_step": 587444, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0323503017425537, "global_step": 587445, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9146286249160767, "global_step": 587446, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0583667755126953, "global_step": 587447, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.969397783279419, "global_step": 587448, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9818998575210571, "global_step": 587449, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0618841648101807, "global_step": 587450, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.048764228820801, "global_step": 587451, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9877943992614746, "global_step": 587452, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9780651330947876, "global_step": 587453, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9984157085418701, "global_step": 587454, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0737390518188477, "global_step": 587455, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.076265335083008, "global_step": 587456, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9712351560592651, "global_step": 587457, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0431649684906006, "global_step": 587458, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0366063117980957, "global_step": 587459, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9883363246917725, "global_step": 587460, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.013400077819824, "global_step": 587461, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9923536777496338, "global_step": 587462, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9717923402786255, "global_step": 587463, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0701615810394287, "global_step": 587464, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9256401062011719, "global_step": 587465, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9547966718673706, "global_step": 587466, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.095473289489746, "global_step": 587467, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0334415435791016, "global_step": 587468, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.084667205810547, "global_step": 587469, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.002930164337158, "global_step": 587470, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0417988300323486, "global_step": 587471, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.081367254257202, "global_step": 587472, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.025993585586548, "global_step": 587473, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0529260635375977, "global_step": 587474, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0088002681732178, "global_step": 587475, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9416959285736084, "global_step": 587476, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9469845294952393, "global_step": 587477, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0098516941070557, "global_step": 587478, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9925131797790527, "global_step": 587479, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.8905789852142334, "global_step": 587480, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.997429609298706, "global_step": 587481, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0623972415924072, "global_step": 587482, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9509450197219849, "global_step": 587483, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9955053329467773, "global_step": 587484, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9919599294662476, "global_step": 587485, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9267677068710327, "global_step": 587486, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.984101414680481, "global_step": 587487, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9745591878890991, "global_step": 587488, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.005248785018921, "global_step": 587489, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.946959137916565, "global_step": 587490, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0193119049072266, "global_step": 587491, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.014238119125366, "global_step": 587492, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.045891284942627, "global_step": 587493, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0248796939849854, "global_step": 587494, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9284840822219849, "global_step": 587495, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9699294567108154, "global_step": 587496, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9738531112670898, "global_step": 587497, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9758650064468384, "global_step": 587498, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9931472539901733, "global_step": 587499, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0729188919067383, "global_step": 587500, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.065711259841919, "global_step": 587501, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.020364999771118, "global_step": 587502, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.016824245452881, "global_step": 587503, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9973156452178955, "global_step": 587504, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0148086547851562, "global_step": 587505, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0028738975524902, "global_step": 587506, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0014610290527344, "global_step": 587507, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0102312564849854, "global_step": 587508, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0271339416503906, "global_step": 587509, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9915287494659424, "global_step": 587510, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0616743564605713, "global_step": 587511, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0207247734069824, "global_step": 587512, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9660876989364624, "global_step": 587513, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0079848766326904, "global_step": 587514, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0657296180725098, "global_step": 587515, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0449068546295166, "global_step": 587516, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9558173418045044, "global_step": 587517, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.946427345275879, "global_step": 587518, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0304782390594482, "global_step": 587519, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0264575481414795, "global_step": 587520, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0095760822296143, "global_step": 587521, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.941596269607544, "global_step": 587522, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.963813066482544, "global_step": 587523, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9543285369873047, "global_step": 587524, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.966636061668396, "global_step": 587525, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0250024795532227, "global_step": 587526, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0670313835144043, "global_step": 587527, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0425686836242676, "global_step": 587528, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.075470447540283, "global_step": 587529, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9693106412887573, "global_step": 587530, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.008862018585205, "global_step": 587531, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0242953300476074, "global_step": 587532, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.1545934677124023, "global_step": 587533, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0568954944610596, "global_step": 587534, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.961483359336853, "global_step": 587535, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0219461917877197, "global_step": 587536, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9583027362823486, "global_step": 587537, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0325875282287598, "global_step": 587538, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.940460443496704, "global_step": 587539, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0740773677825928, "global_step": 587540, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0511419773101807, "global_step": 587541, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.934529423713684, "global_step": 587542, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.03783917427063, "global_step": 587543, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9527016878128052, "global_step": 587544, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9920893907546997, "global_step": 587545, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9548720121383667, "global_step": 587546, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0037503242492676, "global_step": 587547, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9692597389221191, "global_step": 587548, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0522654056549072, "global_step": 587549, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9282053709030151, "global_step": 587550, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0105085372924805, "global_step": 587551, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9123133420944214, "global_step": 587552, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0254740715026855, "global_step": 587553, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9299365282058716, "global_step": 587554, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0067298412323, "global_step": 587555, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.98651921749115, "global_step": 587556, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.99720299243927, "global_step": 587557, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9914453029632568, "global_step": 587558, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0170273780822754, "global_step": 587559, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.1349873542785645, "global_step": 587560, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0296401977539062, "global_step": 587561, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.952850580215454, "global_step": 587562, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9897924661636353, "global_step": 587563, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9768264293670654, "global_step": 587564, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0336573123931885, "global_step": 587565, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9422308206558228, "global_step": 587566, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.054779052734375, "global_step": 587567, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.989206075668335, "global_step": 587568, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.964951753616333, "global_step": 587569, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9691200256347656, "global_step": 587570, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.017958879470825, "global_step": 587571, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9967961311340332, "global_step": 587572, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.092923641204834, "global_step": 587573, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.034818410873413, "global_step": 587574, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.020704984664917, "global_step": 587575, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9885368347167969, "global_step": 587576, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0655887126922607, "global_step": 587577, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0128419399261475, "global_step": 587578, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.914797067642212, "global_step": 587579, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0567147731781006, "global_step": 587580, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9369312524795532, "global_step": 587581, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0350797176361084, "global_step": 587582, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.017338752746582, "global_step": 587583, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9345331192016602, "global_step": 587584, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.053483247756958, "global_step": 587585, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.031815767288208, "global_step": 587586, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0999786853790283, "global_step": 587587, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0096664428710938, "global_step": 587588, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9699993133544922, "global_step": 587589, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.041170597076416, "global_step": 587590, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.048214912414551, "global_step": 587591, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0198044776916504, "global_step": 587592, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0368812084198, "global_step": 587593, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0438520908355713, "global_step": 587594, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0019190311431885, "global_step": 587595, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9239274263381958, "global_step": 587596, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9716120958328247, "global_step": 587597, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0087554454803467, "global_step": 587598, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.104795455932617, "global_step": 587599, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.057189702987671, "global_step": 587600, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.978933572769165, "global_step": 587601, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0545284748077393, "global_step": 587602, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9798258543014526, "global_step": 587603, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0833468437194824, "global_step": 587604, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0177760124206543, "global_step": 587605, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9765362739562988, "global_step": 587606, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0610573291778564, "global_step": 587607, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.004145860671997, "global_step": 587608, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9087245464324951, "global_step": 587609, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0772640705108643, "global_step": 587610, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0049996376037598, "global_step": 587611, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0881803035736084, "global_step": 587612, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0428860187530518, "global_step": 587613, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9596678018569946, "global_step": 587614, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0394845008850098, "global_step": 587615, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9781548976898193, "global_step": 587616, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0350892543792725, "global_step": 587617, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9791654348373413, "global_step": 587618, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.991702914237976, "global_step": 587619, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9965770244598389, "global_step": 587620, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0033371448516846, "global_step": 587621, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.077239990234375, "global_step": 587622, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.909598469734192, "global_step": 587623, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9605202674865723, "global_step": 587624, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0436925888061523, "global_step": 587625, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9661530256271362, "global_step": 587626, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.075054407119751, "global_step": 587627, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9907034635543823, "global_step": 587628, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9943829774856567, "global_step": 587629, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0655930042266846, "global_step": 587630, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9509197473526, "global_step": 587631, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.033174991607666, "global_step": 587632, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9530255794525146, "global_step": 587633, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9843803644180298, "global_step": 587634, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9140018224716187, "global_step": 587635, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9698032140731812, "global_step": 587636, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9111636877059937, "global_step": 587637, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.004425048828125, "global_step": 587638, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.008312940597534, "global_step": 587639, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.018254518508911, "global_step": 587640, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.10660982131958, "global_step": 587641, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0248987674713135, "global_step": 587642, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0351452827453613, "global_step": 587643, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.004962205886841, "global_step": 587644, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0646462440490723, "global_step": 587645, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.050236701965332, "global_step": 587646, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.090582847595215, "global_step": 587647, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0456702709198, "global_step": 587648, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9791499376296997, "global_step": 587649, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0176985263824463, "global_step": 587650, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0104429721832275, "global_step": 587651, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.037672758102417, "global_step": 587652, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0290236473083496, "global_step": 587653, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9860334396362305, "global_step": 587654, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9930124282836914, "global_step": 587655, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0781922340393066, "global_step": 587656, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.012258291244507, "global_step": 587657, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.887656331062317, "global_step": 587658, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9860122203826904, "global_step": 587659, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0500762462615967, "global_step": 587660, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9749250411987305, "global_step": 587661, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9539743661880493, "global_step": 587662, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0133755207061768, "global_step": 587663, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0442183017730713, "global_step": 587664, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9700342416763306, "global_step": 587665, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.002779245376587, "global_step": 587666, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.1348230838775635, "global_step": 587667, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.04809308052063, "global_step": 587668, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0736804008483887, "global_step": 587669, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0104331970214844, "global_step": 587670, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9634654521942139, "global_step": 587671, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0279595851898193, "global_step": 587672, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9864784479141235, "global_step": 587673, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0514190196990967, "global_step": 587674, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9619624614715576, "global_step": 587675, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.1567814350128174, "global_step": 587676, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9884001016616821, "global_step": 587677, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0926673412323, "global_step": 587678, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.010045051574707, "global_step": 587679, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0805318355560303, "global_step": 587680, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.081756114959717, "global_step": 587681, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9793426990509033, "global_step": 587682, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.960803508758545, "global_step": 587683, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9958913326263428, "global_step": 587684, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9417163133621216, "global_step": 587685, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.024057626724243, "global_step": 587686, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0417137145996094, "global_step": 587687, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9850950241088867, "global_step": 587688, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9993479251861572, "global_step": 587689, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0207302570343018, "global_step": 587690, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.93179452419281, "global_step": 587691, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0517234802246094, "global_step": 587692, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9695719480514526, "global_step": 587693, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0677530765533447, "global_step": 587694, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.093949556350708, "global_step": 587695, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0404791831970215, "global_step": 587696, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9239970445632935, "global_step": 587697, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.8795558214187622, "global_step": 587698, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.947975516319275, "global_step": 587699, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.1100172996520996, "global_step": 587700, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.043672561645508, "global_step": 587701, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9782812595367432, "global_step": 587702, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9679548740386963, "global_step": 587703, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9485670328140259, "global_step": 587704, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0506114959716797, "global_step": 587705, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9575546979904175, "global_step": 587706, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0228757858276367, "global_step": 587707, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9632596969604492, "global_step": 587708, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.1097397804260254, "global_step": 587709, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9025157690048218, "global_step": 587710, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.000946521759033, "global_step": 587711, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0551421642303467, "global_step": 587712, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.968144178390503, "global_step": 587713, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9907712936401367, "global_step": 587714, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0829837322235107, "global_step": 587715, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.071747064590454, "global_step": 587716, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.018198013305664, "global_step": 587717, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.048384428024292, "global_step": 587718, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.090365171432495, "global_step": 587719, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0641164779663086, "global_step": 587720, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.056117057800293, "global_step": 587721, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.1306614875793457, "global_step": 587722, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9942095279693604, "global_step": 587723, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.050731658935547, "global_step": 587724, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.041950225830078, "global_step": 587725, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.983356237411499, "global_step": 587726, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0235579013824463, "global_step": 587727, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.086165428161621, "global_step": 587728, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0053908824920654, "global_step": 587729, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0656275749206543, "global_step": 587730, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.009934425354004, "global_step": 587731, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9909791946411133, "global_step": 587732, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0890657901763916, "global_step": 587733, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.990444540977478, "global_step": 587734, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0971078872680664, "global_step": 587735, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9483370780944824, "global_step": 587736, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9746328592300415, "global_step": 587737, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0638678073883057, "global_step": 587738, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0383005142211914, "global_step": 587739, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0557570457458496, "global_step": 587740, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0153615474700928, "global_step": 587741, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0512211322784424, "global_step": 587742, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0415186882019043, "global_step": 587743, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0595765113830566, "global_step": 587744, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.8824326992034912, "global_step": 587745, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9887388944625854, "global_step": 587746, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.064265489578247, "global_step": 587747, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0325214862823486, "global_step": 587748, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.000459909439087, "global_step": 587749, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.155015707015991, "global_step": 587750, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9412989616394043, "global_step": 587751, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.099968671798706, "global_step": 587752, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9460982084274292, "global_step": 587753, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0035207271575928, "global_step": 587754, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.042680501937866, "global_step": 587755, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0446858406066895, "global_step": 587756, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.045619249343872, "global_step": 587757, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.914651870727539, "global_step": 587758, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.01737904548645, "global_step": 587759, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9044908285140991, "global_step": 587760, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0552358627319336, "global_step": 587761, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.963010311126709, "global_step": 587762, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.946476697921753, "global_step": 587763, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.981172800064087, "global_step": 587764, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9931796789169312, "global_step": 587765, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0161824226379395, "global_step": 587766, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9787230491638184, "global_step": 587767, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.938279151916504, "global_step": 587768, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0782296657562256, "global_step": 587769, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.986783742904663, "global_step": 587770, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.983099341392517, "global_step": 587771, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0392985343933105, "global_step": 587772, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9771063327789307, "global_step": 587773, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0047640800476074, "global_step": 587774, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.070026397705078, "global_step": 587775, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0339596271514893, "global_step": 587776, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.1064846515655518, "global_step": 587777, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9677250385284424, "global_step": 587778, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.981147289276123, "global_step": 587779, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0549185276031494, "global_step": 587780, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.052337646484375, "global_step": 587781, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0541300773620605, "global_step": 587782, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0252020359039307, "global_step": 587783, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9933764934539795, "global_step": 587784, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.046937942504883, "global_step": 587785, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.941782832145691, "global_step": 587786, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0718915462493896, "global_step": 587787, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9478775262832642, "global_step": 587788, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9974616765975952, "global_step": 587789, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.90513014793396, "global_step": 587790, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.961438536643982, "global_step": 587791, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.034377336502075, "global_step": 587792, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0064213275909424, "global_step": 587793, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.972531795501709, "global_step": 587794, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9688564538955688, "global_step": 587795, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9817787408828735, "global_step": 587796, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.003628730773926, "global_step": 587797, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.067370653152466, "global_step": 587798, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.8494179248809814, "global_step": 587799, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9873087406158447, "global_step": 587800, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.07894229888916, "global_step": 587801, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9899990558624268, "global_step": 587802, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.013507604598999, "global_step": 587803, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.953561782836914, "global_step": 587804, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.104901075363159, "global_step": 587805, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9157555103302002, "global_step": 587806, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.057215929031372, "global_step": 587807, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.080188274383545, "global_step": 587808, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.130857229232788, "global_step": 587809, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.95911705493927, "global_step": 587810, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.005091667175293, "global_step": 587811, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.064105749130249, "global_step": 587812, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9839962720870972, "global_step": 587813, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.026311159133911, "global_step": 587814, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.030956506729126, "global_step": 587815, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.008127212524414, "global_step": 587816, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.037281036376953, "global_step": 587817, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.028449535369873, "global_step": 587818, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0131447315216064, "global_step": 587819, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.005444049835205, "global_step": 587820, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0399088859558105, "global_step": 587821, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.071688175201416, "global_step": 587822, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.019226551055908, "global_step": 587823, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.075017213821411, "global_step": 587824, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0096817016601562, "global_step": 587825, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.017810821533203, "global_step": 587826, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0145716667175293, "global_step": 587827, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.038940668106079, "global_step": 587828, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.03556227684021, "global_step": 587829, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9492456912994385, "global_step": 587830, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9945508241653442, "global_step": 587831, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0548253059387207, "global_step": 587832, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0061254501342773, "global_step": 587833, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.059723377227783, "global_step": 587834, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0361886024475098, "global_step": 587835, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.029715061187744, "global_step": 587836, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.094160795211792, "global_step": 587837, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9730746746063232, "global_step": 587838, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.017176389694214, "global_step": 587839, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9710829257965088, "global_step": 587840, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0386836528778076, "global_step": 587841, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9515485763549805, "global_step": 587842, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.044076681137085, "global_step": 587843, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.007629871368408, "global_step": 587844, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0528204441070557, "global_step": 587845, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9286631345748901, "global_step": 587846, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0189177989959717, "global_step": 587847, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0631980895996094, "global_step": 587848, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9705228805541992, "global_step": 587849, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0384695529937744, "global_step": 587850, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0230205059051514, "global_step": 587851, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.072662115097046, "global_step": 587852, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9736813306808472, "global_step": 587853, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9994200468063354, "global_step": 587854, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0307159423828125, "global_step": 587855, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.083173990249634, "global_step": 587856, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0286145210266113, "global_step": 587857, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9112554788589478, "global_step": 587858, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0813746452331543, "global_step": 587859, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9211505651474, "global_step": 587860, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9622865915298462, "global_step": 587861, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0523626804351807, "global_step": 587862, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.030027389526367, "global_step": 587863, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9481468200683594, "global_step": 587864, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9560036659240723, "global_step": 587865, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.077259063720703, "global_step": 587866, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9255754947662354, "global_step": 587867, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.007587432861328, "global_step": 587868, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.1074471473693848, "global_step": 587869, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9985347986221313, "global_step": 587870, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0304057598114014, "global_step": 587871, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9152723550796509, "global_step": 587872, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0082130432128906, "global_step": 587873, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9873523712158203, "global_step": 587874, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9549013376235962, "global_step": 587875, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9232581853866577, "global_step": 587876, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.02030348777771, "global_step": 587877, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.014899730682373, "global_step": 587878, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9986177682876587, "global_step": 587879, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.084096908569336, "global_step": 587880, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0857956409454346, "global_step": 587881, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0333590507507324, "global_step": 587882, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0563158988952637, "global_step": 587883, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9483846426010132, "global_step": 587884, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0320122241973877, "global_step": 587885, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9796432256698608, "global_step": 587886, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.071643352508545, "global_step": 587887, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.958154320716858, "global_step": 587888, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.952412724494934, "global_step": 587889, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0280988216400146, "global_step": 587890, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.943448781967163, "global_step": 587891, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.012847423553467, "global_step": 587892, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.980049729347229, "global_step": 587893, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.935954213142395, "global_step": 587894, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.039860248565674, "global_step": 587895, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.1039538383483887, "global_step": 587896, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.973423957824707, "global_step": 587897, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0378012657165527, "global_step": 587898, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.00342059135437, "global_step": 587899, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0258593559265137, "global_step": 587900, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9980015754699707, "global_step": 587901, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0032005310058594, "global_step": 587902, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0103752613067627, "global_step": 587903, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0640130043029785, "global_step": 587904, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.08652925491333, "global_step": 587905, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9915534257888794, "global_step": 587906, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0045557022094727, "global_step": 587907, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.036773920059204, "global_step": 587908, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0236012935638428, "global_step": 587909, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.975464940071106, "global_step": 587910, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9846035242080688, "global_step": 587911, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0610923767089844, "global_step": 587912, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0579581260681152, "global_step": 587913, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.066603660583496, "global_step": 587914, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.031419515609741, "global_step": 587915, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0958445072174072, "global_step": 587916, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0174667835235596, "global_step": 587917, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.01802659034729, "global_step": 587918, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.028181791305542, "global_step": 587919, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9554455280303955, "global_step": 587920, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.087475538253784, "global_step": 587921, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.015782356262207, "global_step": 587922, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.091298818588257, "global_step": 587923, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0646495819091797, "global_step": 587924, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.065864324569702, "global_step": 587925, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0761659145355225, "global_step": 587926, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9553526639938354, "global_step": 587927, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9550100564956665, "global_step": 587928, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.008645534515381, "global_step": 587929, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.031423330307007, "global_step": 587930, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.998854160308838, "global_step": 587931, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0818989276885986, "global_step": 587932, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9512782096862793, "global_step": 587933, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.050854444503784, "global_step": 587934, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9665559530258179, "global_step": 587935, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9834617376327515, "global_step": 587936, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0495173931121826, "global_step": 587937, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.023494243621826, "global_step": 587938, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0499560832977295, "global_step": 587939, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.02850079536438, "global_step": 587940, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0388529300689697, "global_step": 587941, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.130079746246338, "global_step": 587942, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9463608264923096, "global_step": 587943, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.995147943496704, "global_step": 587944, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0204334259033203, "global_step": 587945, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9579888582229614, "global_step": 587946, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0380544662475586, "global_step": 587947, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.014702320098877, "global_step": 587948, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.04974365234375, "global_step": 587949, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0624260902404785, "global_step": 587950, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0604329109191895, "global_step": 587951, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.944698691368103, "global_step": 587952, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9943645000457764, "global_step": 587953, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0102577209472656, "global_step": 587954, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.055461883544922, "global_step": 587955, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0241310596466064, "global_step": 587956, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0571744441986084, "global_step": 587957, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0966076850891113, "global_step": 587958, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.982953429222107, "global_step": 587959, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0175728797912598, "global_step": 587960, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9925425052642822, "global_step": 587961, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9749807119369507, "global_step": 587962, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.096400260925293, "global_step": 587963, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.992073655128479, "global_step": 587964, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.019423484802246, "global_step": 587965, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.008897066116333, "global_step": 587966, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0691030025482178, "global_step": 587967, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.048424243927002, "global_step": 587968, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0417771339416504, "global_step": 587969, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0751209259033203, "global_step": 587970, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.896643042564392, "global_step": 587971, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0999603271484375, "global_step": 587972, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0091745853424072, "global_step": 587973, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0383505821228027, "global_step": 587974, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.926858901977539, "global_step": 587975, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.011686086654663, "global_step": 587976, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.019045829772949, "global_step": 587977, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0024185180664062, "global_step": 587978, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9720391035079956, "global_step": 587979, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0739963054656982, "global_step": 587980, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.138981819152832, "global_step": 587981, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9496959447860718, "global_step": 587982, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.124606132507324, "global_step": 587983, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.01444673538208, "global_step": 587984, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.025200366973877, "global_step": 587985, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9988206624984741, "global_step": 587986, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.014418125152588, "global_step": 587987, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.1021037101745605, "global_step": 587988, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.092177391052246, "global_step": 587989, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0611259937286377, "global_step": 587990, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.009279251098633, "global_step": 587991, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.034238576889038, "global_step": 587992, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0202527046203613, "global_step": 587993, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.019024133682251, "global_step": 587994, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.973491907119751, "global_step": 587995, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.086890459060669, "global_step": 587996, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9964035749435425, "global_step": 587997, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0045487880706787, "global_step": 587998, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.1238315105438232, "global_step": 587999, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.1298749446868896, "global_step": 588000, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9872111082077026, "global_step": 588001, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0573532581329346, "global_step": 588002, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.038026809692383, "global_step": 588003, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.020301580429077, "global_step": 588004, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.027177095413208, "global_step": 588005, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.031639575958252, "global_step": 588006, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0211181640625, "global_step": 588007, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9905498027801514, "global_step": 588008, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0097503662109375, "global_step": 588009, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0674731731414795, "global_step": 588010, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9813774824142456, "global_step": 588011, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.014796495437622, "global_step": 588012, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9814252853393555, "global_step": 588013, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0521233081817627, "global_step": 588014, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.953884243965149, "global_step": 588015, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0523312091827393, "global_step": 588016, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.047670602798462, "global_step": 588017, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.016538381576538, "global_step": 588018, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.071207046508789, "global_step": 588019, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9616929292678833, "global_step": 588020, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0115458965301514, "global_step": 588021, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9940388202667236, "global_step": 588022, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.014972686767578, "global_step": 588023, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0177199840545654, "global_step": 588024, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0434558391571045, "global_step": 588025, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0767595767974854, "global_step": 588026, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0351345539093018, "global_step": 588027, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.049146890640259, "global_step": 588028, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0864291191101074, "global_step": 588029, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0826447010040283, "global_step": 588030, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.046346664428711, "global_step": 588031, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0252084732055664, "global_step": 588032, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.021275520324707, "global_step": 588033, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9594353437423706, "global_step": 588034, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0712087154388428, "global_step": 588035, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0406699180603027, "global_step": 588036, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.113619804382324, "global_step": 588037, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9862074851989746, "global_step": 588038, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.042720079421997, "global_step": 588039, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0825421810150146, "global_step": 588040, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9965654611587524, "global_step": 588041, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.033811092376709, "global_step": 588042, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9797309637069702, "global_step": 588043, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.030900716781616, "global_step": 588044, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.068366527557373, "global_step": 588045, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0400757789611816, "global_step": 588046, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.017855405807495, "global_step": 588047, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.064466714859009, "global_step": 588048, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9742780923843384, "global_step": 588049, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.017578363418579, "global_step": 588050, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.1687204837799072, "global_step": 588051, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.966344952583313, "global_step": 588052, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.944222092628479, "global_step": 588053, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.053549289703369, "global_step": 588054, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.001164197921753, "global_step": 588055, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0574700832366943, "global_step": 588056, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9871379137039185, "global_step": 588057, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9498902559280396, "global_step": 588058, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0342557430267334, "global_step": 588059, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0028598308563232, "global_step": 588060, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.036576986312866, "global_step": 588061, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9792418479919434, "global_step": 588062, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.060011863708496, "global_step": 588063, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.034585952758789, "global_step": 588064, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0122969150543213, "global_step": 588065, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0590269565582275, "global_step": 588066, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9957622289657593, "global_step": 588067, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0544486045837402, "global_step": 588068, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.988946557044983, "global_step": 588069, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.003952980041504, "global_step": 588070, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.015350341796875, "global_step": 588071, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.001582622528076, "global_step": 588072, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9655609130859375, "global_step": 588073, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0367698669433594, "global_step": 588074, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0157968997955322, "global_step": 588075, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.07363224029541, "global_step": 588076, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.05295991897583, "global_step": 588077, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0356218814849854, "global_step": 588078, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0191357135772705, "global_step": 588079, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.8916295766830444, "global_step": 588080, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9599825143814087, "global_step": 588081, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.030174970626831, "global_step": 588082, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9828397035598755, "global_step": 588083, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0971453189849854, "global_step": 588084, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.931159496307373, "global_step": 588085, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0694353580474854, "global_step": 588086, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0638222694396973, "global_step": 588087, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9836516380310059, "global_step": 588088, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.057440996170044, "global_step": 588089, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9812614917755127, "global_step": 588090, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.095705509185791, "global_step": 588091, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9987680912017822, "global_step": 588092, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.027573585510254, "global_step": 588093, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0686280727386475, "global_step": 588094, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0438218116760254, "global_step": 588095, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9864532947540283, "global_step": 588096, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0724010467529297, "global_step": 588097, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0335159301757812, "global_step": 588098, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.090111255645752, "global_step": 588099, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0461692810058594, "global_step": 588100, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0406315326690674, "global_step": 588101, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0422046184539795, "global_step": 588102, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0737485885620117, "global_step": 588103, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0402588844299316, "global_step": 588104, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0424773693084717, "global_step": 588105, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0158321857452393, "global_step": 588106, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.030578851699829, "global_step": 588107, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.084908962249756, "global_step": 588108, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.003188133239746, "global_step": 588109, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.019118547439575, "global_step": 588110, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9955791234970093, "global_step": 588111, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9821587800979614, "global_step": 588112, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.006373167037964, "global_step": 588113, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.054025173187256, "global_step": 588114, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9365651607513428, "global_step": 588115, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9437203407287598, "global_step": 588116, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0320816040039062, "global_step": 588117, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9731378555297852, "global_step": 588118, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9835246801376343, "global_step": 588119, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9464038610458374, "global_step": 588120, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9652774333953857, "global_step": 588121, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.066380262374878, "global_step": 588122, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0176327228546143, "global_step": 588123, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.056246757507324, "global_step": 588124, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.065998077392578, "global_step": 588125, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0396111011505127, "global_step": 588126, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.087618827819824, "global_step": 588127, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9954860210418701, "global_step": 588128, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0143344402313232, "global_step": 588129, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.075024366378784, "global_step": 588130, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0212438106536865, "global_step": 588131, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9888521432876587, "global_step": 588132, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0406477451324463, "global_step": 588133, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.090480089187622, "global_step": 588134, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0322940349578857, "global_step": 588135, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.106146812438965, "global_step": 588136, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.076805830001831, "global_step": 588137, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0140271186828613, "global_step": 588138, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.974303960800171, "global_step": 588139, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0838375091552734, "global_step": 588140, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0125997066497803, "global_step": 588141, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9756988286972046, "global_step": 588142, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.016386032104492, "global_step": 588143, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0867578983306885, "global_step": 588144, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9335881471633911, "global_step": 588145, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0971574783325195, "global_step": 588146, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0526764392852783, "global_step": 588147, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0483133792877197, "global_step": 588148, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9995521306991577, "global_step": 588149, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0524861812591553, "global_step": 588150, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.010565996170044, "global_step": 588151, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.014824867248535, "global_step": 588152, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9811517000198364, "global_step": 588153, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9998908042907715, "global_step": 588154, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9967201948165894, "global_step": 588155, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9700915813446045, "global_step": 588156, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.109863042831421, "global_step": 588157, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0530998706817627, "global_step": 588158, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.036022186279297, "global_step": 588159, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.985477089881897, "global_step": 588160, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9819434881210327, "global_step": 588161, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9648257493972778, "global_step": 588162, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.923844337463379, "global_step": 588163, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9375370740890503, "global_step": 588164, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.029865026473999, "global_step": 588165, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0104987621307373, "global_step": 588166, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0397849082946777, "global_step": 588167, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0506904125213623, "global_step": 588168, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.062283515930176, "global_step": 588169, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0981602668762207, "global_step": 588170, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.054138422012329, "global_step": 588171, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.053042411804199, "global_step": 588172, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0433385372161865, "global_step": 588173, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.1040561199188232, "global_step": 588174, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0144753456115723, "global_step": 588175, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9605345726013184, "global_step": 588176, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0544497966766357, "global_step": 588177, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0631332397460938, "global_step": 588178, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0116913318634033, "global_step": 588179, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9897644519805908, "global_step": 588180, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9786546230316162, "global_step": 588181, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0699269771575928, "global_step": 588182, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.967272400856018, "global_step": 588183, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.08209228515625, "global_step": 588184, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9748491048812866, "global_step": 588185, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0354082584381104, "global_step": 588186, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.1218528747558594, "global_step": 588187, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.1226284503936768, "global_step": 588188, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.058345317840576, "global_step": 588189, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0384180545806885, "global_step": 588190, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0430283546447754, "global_step": 588191, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0309550762176514, "global_step": 588192, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9762916564941406, "global_step": 588193, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9042993783950806, "global_step": 588194, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0236711502075195, "global_step": 588195, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0424203872680664, "global_step": 588196, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0476958751678467, "global_step": 588197, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9902540445327759, "global_step": 588198, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9914448261260986, "global_step": 588199, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.007791757583618, "global_step": 588200, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0984530448913574, "global_step": 588201, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.070774793624878, "global_step": 588202, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0036041736602783, "global_step": 588203, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9359115362167358, "global_step": 588204, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0224380493164062, "global_step": 588205, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0578773021698, "global_step": 588206, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.110431671142578, "global_step": 588207, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0952422618865967, "global_step": 588208, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0211658477783203, "global_step": 588209, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.040144920349121, "global_step": 588210, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.091336727142334, "global_step": 588211, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9283071756362915, "global_step": 588212, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0109121799468994, "global_step": 588213, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9465436935424805, "global_step": 588214, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0339672565460205, "global_step": 588215, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.019181489944458, "global_step": 588216, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.014510154724121, "global_step": 588217, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9716947078704834, "global_step": 588218, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0253748893737793, "global_step": 588219, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9660450220108032, "global_step": 588220, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.027048110961914, "global_step": 588221, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9875531196594238, "global_step": 588222, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0017449855804443, "global_step": 588223, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.955820083618164, "global_step": 588224, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0583133697509766, "global_step": 588225, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.962092399597168, "global_step": 588226, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0411124229431152, "global_step": 588227, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9500691890716553, "global_step": 588228, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9864373207092285, "global_step": 588229, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0265860557556152, "global_step": 588230, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0967414379119873, "global_step": 588231, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0241057872772217, "global_step": 588232, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.003131866455078, "global_step": 588233, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.964463472366333, "global_step": 588234, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.031343460083008, "global_step": 588235, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.056931257247925, "global_step": 588236, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.118220806121826, "global_step": 588237, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.017463207244873, "global_step": 588238, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0364456176757812, "global_step": 588239, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0786848068237305, "global_step": 588240, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9868781566619873, "global_step": 588241, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0873067378997803, "global_step": 588242, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9381582736968994, "global_step": 588243, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9902232885360718, "global_step": 588244, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0486669540405273, "global_step": 588245, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0982673168182373, "global_step": 588246, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0900001525878906, "global_step": 588247, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.015687942504883, "global_step": 588248, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9981328248977661, "global_step": 588249, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0862202644348145, "global_step": 588250, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.037033796310425, "global_step": 588251, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.014449119567871, "global_step": 588252, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.066655158996582, "global_step": 588253, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.009711980819702, "global_step": 588254, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9720498323440552, "global_step": 588255, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0721402168273926, "global_step": 588256, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0341641902923584, "global_step": 588257, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0806214809417725, "global_step": 588258, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.067687511444092, "global_step": 588259, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9665606021881104, "global_step": 588260, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.072380542755127, "global_step": 588261, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9642791748046875, "global_step": 588262, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0421032905578613, "global_step": 588263, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.955389142036438, "global_step": 588264, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.963310956954956, "global_step": 588265, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.01348876953125, "global_step": 588266, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0081233978271484, "global_step": 588267, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0217342376708984, "global_step": 588268, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.018305540084839, "global_step": 588269, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0138089656829834, "global_step": 588270, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9943528175354004, "global_step": 588271, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9735585451126099, "global_step": 588272, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0519280433654785, "global_step": 588273, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9643142223358154, "global_step": 588274, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0309386253356934, "global_step": 588275, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.033557891845703, "global_step": 588276, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0110321044921875, "global_step": 588277, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9701091051101685, "global_step": 588278, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9998477697372437, "global_step": 588279, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9942657947540283, "global_step": 588280, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0506067276000977, "global_step": 588281, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.029581069946289, "global_step": 588282, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0586776733398438, "global_step": 588283, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.072340488433838, "global_step": 588284, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0386857986450195, "global_step": 588285, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0232632160186768, "global_step": 588286, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.998618721961975, "global_step": 588287, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.90086829662323, "global_step": 588288, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9135866165161133, "global_step": 588289, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9531855583190918, "global_step": 588290, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0223746299743652, "global_step": 588291, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9514250755310059, "global_step": 588292, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0482442378997803, "global_step": 588293, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.064162254333496, "global_step": 588294, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0047872066497803, "global_step": 588295, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.032010316848755, "global_step": 588296, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9093354940414429, "global_step": 588297, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9634530544281006, "global_step": 588298, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0213074684143066, "global_step": 588299, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.967810869216919, "global_step": 588300, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0121803283691406, "global_step": 588301, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0601840019226074, "global_step": 588302, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.006645917892456, "global_step": 588303, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.07546329498291, "global_step": 588304, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9539850950241089, "global_step": 588305, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0157077312469482, "global_step": 588306, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0458123683929443, "global_step": 588307, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.091688394546509, "global_step": 588308, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0929291248321533, "global_step": 588309, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.081879138946533, "global_step": 588310, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.9836618900299072, "global_step": 588311, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0047380924224854, "global_step": 588312, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0490214824676514, "global_step": 588313, "epoch": 956, "lr": 5e-05}
{"train_loss": 1.928088903427124, "global_step": 588314, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.016045331954956, "global_step": 588315, "epoch": 956, "lr": 5e-05}
{"train_loss": 2.0411717891693115, "global_step": 588316, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1663167476654053, "global_step": 588317, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9819996356964111, "global_step": 588318, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9267730712890625, "global_step": 588319, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.087545394897461, "global_step": 588320, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9128819704055786, "global_step": 588321, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9876277446746826, "global_step": 588322, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.947729468345642, "global_step": 588323, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9664794206619263, "global_step": 588324, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0228524208068848, "global_step": 588325, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9968199729919434, "global_step": 588326, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0247182846069336, "global_step": 588327, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0194952487945557, "global_step": 588328, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.045588254928589, "global_step": 588329, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0608394145965576, "global_step": 588330, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.026054620742798, "global_step": 588331, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.058889865875244, "global_step": 588332, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9605118036270142, "global_step": 588333, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0774800777435303, "global_step": 588334, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9369252920150757, "global_step": 588335, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9859416484832764, "global_step": 588336, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0928378105163574, "global_step": 588337, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0149528980255127, "global_step": 588338, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.026139497756958, "global_step": 588339, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0110154151916504, "global_step": 588340, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.040928602218628, "global_step": 588341, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0095109939575195, "global_step": 588342, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9218947887420654, "global_step": 588343, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9403514862060547, "global_step": 588344, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.959667682647705, "global_step": 588345, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.043194055557251, "global_step": 588346, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0198144912719727, "global_step": 588347, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9632861614227295, "global_step": 588348, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.889954686164856, "global_step": 588349, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.973060131072998, "global_step": 588350, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9941611289978027, "global_step": 588351, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9356240034103394, "global_step": 588352, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9945008754730225, "global_step": 588353, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.065636157989502, "global_step": 588354, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9424426555633545, "global_step": 588355, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0357038974761963, "global_step": 588356, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0169975757598877, "global_step": 588357, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.993444800376892, "global_step": 588358, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.007535934448242, "global_step": 588359, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9583081007003784, "global_step": 588360, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0145719051361084, "global_step": 588361, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.037959098815918, "global_step": 588362, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0031309127807617, "global_step": 588363, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.020644426345825, "global_step": 588364, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0782604217529297, "global_step": 588365, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9631973505020142, "global_step": 588366, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9852659702301025, "global_step": 588367, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9776933193206787, "global_step": 588368, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.023930788040161, "global_step": 588369, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1018362045288086, "global_step": 588370, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9805113077163696, "global_step": 588371, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0468087196350098, "global_step": 588372, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.989389181137085, "global_step": 588373, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0417726039886475, "global_step": 588374, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.941649079322815, "global_step": 588375, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.064439535140991, "global_step": 588376, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.041666269302368, "global_step": 588377, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9917314052581787, "global_step": 588378, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0121774673461914, "global_step": 588379, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.042283296585083, "global_step": 588380, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1073265075683594, "global_step": 588381, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.018402099609375, "global_step": 588382, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.8995944261550903, "global_step": 588383, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.01285719871521, "global_step": 588384, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0037596225738525, "global_step": 588385, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.010145664215088, "global_step": 588386, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9947909116744995, "global_step": 588387, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.998936414718628, "global_step": 588388, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9883475303649902, "global_step": 588389, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0437817573547363, "global_step": 588390, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.8796218633651733, "global_step": 588391, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9971805810928345, "global_step": 588392, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.004762649536133, "global_step": 588393, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.071228265762329, "global_step": 588394, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0256736278533936, "global_step": 588395, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.989593505859375, "global_step": 588396, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0501389503479004, "global_step": 588397, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9994921684265137, "global_step": 588398, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9944040775299072, "global_step": 588399, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0609259605407715, "global_step": 588400, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.042752742767334, "global_step": 588401, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9913090467453003, "global_step": 588402, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.021570920944214, "global_step": 588403, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.036987781524658, "global_step": 588404, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9992613792419434, "global_step": 588405, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.035546064376831, "global_step": 588406, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0315511226654053, "global_step": 588407, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.028641700744629, "global_step": 588408, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9983657598495483, "global_step": 588409, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0782816410064697, "global_step": 588410, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.8960009813308716, "global_step": 588411, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9434471130371094, "global_step": 588412, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9781720638275146, "global_step": 588413, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0455243587493896, "global_step": 588414, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.05880069732666, "global_step": 588415, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.8758593797683716, "global_step": 588416, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9937233924865723, "global_step": 588417, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0113768577575684, "global_step": 588418, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9493502378463745, "global_step": 588419, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.02882719039917, "global_step": 588420, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9747792482376099, "global_step": 588421, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0793285369873047, "global_step": 588422, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.977282166481018, "global_step": 588423, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.988062858581543, "global_step": 588424, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9566951990127563, "global_step": 588425, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9666540622711182, "global_step": 588426, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.040217638015747, "global_step": 588427, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.981287956237793, "global_step": 588428, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0319876670837402, "global_step": 588429, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9895497560501099, "global_step": 588430, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9567289352416992, "global_step": 588431, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9610515832901, "global_step": 588432, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0149037837982178, "global_step": 588433, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.031888961791992, "global_step": 588434, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0585827827453613, "global_step": 588435, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.049135208129883, "global_step": 588436, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0979719161987305, "global_step": 588437, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.97390878200531, "global_step": 588438, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.095698833465576, "global_step": 588439, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.005312919616699, "global_step": 588440, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9724668264389038, "global_step": 588441, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9959293603897095, "global_step": 588442, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0224592685699463, "global_step": 588443, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.038254499435425, "global_step": 588444, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.080515146255493, "global_step": 588445, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9607263803482056, "global_step": 588446, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0248584747314453, "global_step": 588447, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9681520462036133, "global_step": 588448, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.955327033996582, "global_step": 588449, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1083414554595947, "global_step": 588450, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.008294105529785, "global_step": 588451, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.982709527015686, "global_step": 588452, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.058781385421753, "global_step": 588453, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0068929195404053, "global_step": 588454, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.8993452787399292, "global_step": 588455, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9974039793014526, "global_step": 588456, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0232062339782715, "global_step": 588457, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.956282138824463, "global_step": 588458, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.024775505065918, "global_step": 588459, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0449864864349365, "global_step": 588460, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0241222381591797, "global_step": 588461, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9792389869689941, "global_step": 588462, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9550771713256836, "global_step": 588463, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0668721199035645, "global_step": 588464, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.072744131088257, "global_step": 588465, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.946765422821045, "global_step": 588466, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9831961393356323, "global_step": 588467, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.8996062278747559, "global_step": 588468, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0208935737609863, "global_step": 588469, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1226253509521484, "global_step": 588470, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.8665826320648193, "global_step": 588471, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.968937635421753, "global_step": 588472, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9654580354690552, "global_step": 588473, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9955682754516602, "global_step": 588474, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.058955430984497, "global_step": 588475, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.950639009475708, "global_step": 588476, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.033773183822632, "global_step": 588477, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.062140703201294, "global_step": 588478, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.011942148208618, "global_step": 588479, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.97603178024292, "global_step": 588480, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.017186164855957, "global_step": 588481, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9703197479248047, "global_step": 588482, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9851652383804321, "global_step": 588483, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0353009700775146, "global_step": 588484, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.06789493560791, "global_step": 588485, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.006676435470581, "global_step": 588486, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0340518951416016, "global_step": 588487, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9836609363555908, "global_step": 588488, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.000075578689575, "global_step": 588489, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.073913812637329, "global_step": 588490, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0284204483032227, "global_step": 588491, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.067363977432251, "global_step": 588492, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0292742252349854, "global_step": 588493, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0615572929382324, "global_step": 588494, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9805468320846558, "global_step": 588495, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9946993589401245, "global_step": 588496, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.004847288131714, "global_step": 588497, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.000121593475342, "global_step": 588498, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9474208354949951, "global_step": 588499, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.007701873779297, "global_step": 588500, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9975601434707642, "global_step": 588501, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9685654640197754, "global_step": 588502, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1026360988616943, "global_step": 588503, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0288946628570557, "global_step": 588504, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.05527663230896, "global_step": 588505, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.056313991546631, "global_step": 588506, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.065592050552368, "global_step": 588507, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0070676803588867, "global_step": 588508, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9417651891708374, "global_step": 588509, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.003591537475586, "global_step": 588510, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.083409547805786, "global_step": 588511, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9526399374008179, "global_step": 588512, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0194950103759766, "global_step": 588513, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9617607593536377, "global_step": 588514, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9879286289215088, "global_step": 588515, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.016054153442383, "global_step": 588516, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9963018894195557, "global_step": 588517, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.059126853942871, "global_step": 588518, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0218186378479004, "global_step": 588519, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9982630014419556, "global_step": 588520, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.01061749458313, "global_step": 588521, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9926124811172485, "global_step": 588522, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9680061340332031, "global_step": 588523, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.065387487411499, "global_step": 588524, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.061591148376465, "global_step": 588525, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0474815368652344, "global_step": 588526, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0452682971954346, "global_step": 588527, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.003289222717285, "global_step": 588528, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9469587802886963, "global_step": 588529, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0279288291931152, "global_step": 588530, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.03684401512146, "global_step": 588531, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.98973548412323, "global_step": 588532, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.085763692855835, "global_step": 588533, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9644392728805542, "global_step": 588534, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.009860038757324, "global_step": 588535, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9985893964767456, "global_step": 588536, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.003152847290039, "global_step": 588537, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.006824254989624, "global_step": 588538, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0562641620635986, "global_step": 588539, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.092499256134033, "global_step": 588540, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.049625873565674, "global_step": 588541, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.997312307357788, "global_step": 588542, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1499722003936768, "global_step": 588543, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0119004249572754, "global_step": 588544, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.007897138595581, "global_step": 588545, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0241663455963135, "global_step": 588546, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0325279235839844, "global_step": 588547, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0330758094787598, "global_step": 588548, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0509707927703857, "global_step": 588549, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9437518119812012, "global_step": 588550, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0458717346191406, "global_step": 588551, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.008347749710083, "global_step": 588552, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.011286735534668, "global_step": 588553, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9285634756088257, "global_step": 588554, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.984437346458435, "global_step": 588555, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.011523485183716, "global_step": 588556, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0013113021850586, "global_step": 588557, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0838723182678223, "global_step": 588558, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0155060291290283, "global_step": 588559, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.958591341972351, "global_step": 588560, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.052837610244751, "global_step": 588561, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.042616605758667, "global_step": 588562, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.011716842651367, "global_step": 588563, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0355565547943115, "global_step": 588564, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0292904376983643, "global_step": 588565, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.977584958076477, "global_step": 588566, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9293888807296753, "global_step": 588567, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.031916618347168, "global_step": 588568, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0870697498321533, "global_step": 588569, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9947057962417603, "global_step": 588570, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0430562496185303, "global_step": 588571, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.041996717453003, "global_step": 588572, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.070019006729126, "global_step": 588573, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0190718173980713, "global_step": 588574, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9877853393554688, "global_step": 588575, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0385000705718994, "global_step": 588576, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9974920749664307, "global_step": 588577, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9817429780960083, "global_step": 588578, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0298852920532227, "global_step": 588579, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9959152936935425, "global_step": 588580, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.037266492843628, "global_step": 588581, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.998199701309204, "global_step": 588582, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9605669975280762, "global_step": 588583, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0963332653045654, "global_step": 588584, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0220816135406494, "global_step": 588585, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0235915184020996, "global_step": 588586, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.997289776802063, "global_step": 588587, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.019408702850342, "global_step": 588588, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0203750133514404, "global_step": 588589, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.004945755004883, "global_step": 588590, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.052140712738037, "global_step": 588591, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.077674627304077, "global_step": 588592, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9892815351486206, "global_step": 588593, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9378103017807007, "global_step": 588594, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0490739345550537, "global_step": 588595, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0502941608428955, "global_step": 588596, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0337796211242676, "global_step": 588597, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9788615703582764, "global_step": 588598, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.037442207336426, "global_step": 588599, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0929200649261475, "global_step": 588600, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0279314517974854, "global_step": 588601, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0513412952423096, "global_step": 588602, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.075544595718384, "global_step": 588603, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.028717517852783, "global_step": 588604, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0632081031799316, "global_step": 588605, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.004547119140625, "global_step": 588606, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0625298023223877, "global_step": 588607, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9939830303192139, "global_step": 588608, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9684135913848877, "global_step": 588609, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9882733821868896, "global_step": 588610, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9767142534255981, "global_step": 588611, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9669286012649536, "global_step": 588612, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.017241954803467, "global_step": 588613, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9799001216888428, "global_step": 588614, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9962873458862305, "global_step": 588615, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0609333515167236, "global_step": 588616, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.964959740638733, "global_step": 588617, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.986061692237854, "global_step": 588618, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0301873683929443, "global_step": 588619, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9665783643722534, "global_step": 588620, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.039625406265259, "global_step": 588621, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9792531728744507, "global_step": 588622, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.132089376449585, "global_step": 588623, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9729779958724976, "global_step": 588624, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.961529016494751, "global_step": 588625, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9585926532745361, "global_step": 588626, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0328609943389893, "global_step": 588627, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0327751636505127, "global_step": 588628, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9993314743041992, "global_step": 588629, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.01718807220459, "global_step": 588630, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.072885274887085, "global_step": 588631, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.014202117919922, "global_step": 588632, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.044283151626587, "global_step": 588633, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.034994602203369, "global_step": 588634, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0016355514526367, "global_step": 588635, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.058634042739868, "global_step": 588636, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0458648204803467, "global_step": 588637, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0658390522003174, "global_step": 588638, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9790582656860352, "global_step": 588639, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0349013805389404, "global_step": 588640, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.074615716934204, "global_step": 588641, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0587589740753174, "global_step": 588642, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0238616466522217, "global_step": 588643, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9883694648742676, "global_step": 588644, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0564355850219727, "global_step": 588645, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.037997007369995, "global_step": 588646, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0070390701293945, "global_step": 588647, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.075195074081421, "global_step": 588648, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.041105031967163, "global_step": 588649, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.042092800140381, "global_step": 588650, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0198915004730225, "global_step": 588651, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9848319292068481, "global_step": 588652, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.020228862762451, "global_step": 588653, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.015131950378418, "global_step": 588654, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0997607707977295, "global_step": 588655, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0251097679138184, "global_step": 588656, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0016016960144043, "global_step": 588657, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0685226917266846, "global_step": 588658, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0926241874694824, "global_step": 588659, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0636696815490723, "global_step": 588660, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9290801286697388, "global_step": 588661, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.025313138961792, "global_step": 588662, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.023794174194336, "global_step": 588663, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.077587127685547, "global_step": 588664, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0095951557159424, "global_step": 588665, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0565638542175293, "global_step": 588666, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1018269062042236, "global_step": 588667, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0642426013946533, "global_step": 588668, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9976041316986084, "global_step": 588669, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0101780891418457, "global_step": 588670, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0579800605773926, "global_step": 588671, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.035609245300293, "global_step": 588672, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0027122497558594, "global_step": 588673, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9795020818710327, "global_step": 588674, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1173083782196045, "global_step": 588675, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0180599689483643, "global_step": 588676, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9954015016555786, "global_step": 588677, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.978067398071289, "global_step": 588678, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9742271900177002, "global_step": 588679, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9814761877059937, "global_step": 588680, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1035549640655518, "global_step": 588681, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0662593841552734, "global_step": 588682, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.092233180999756, "global_step": 588683, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0320804119110107, "global_step": 588684, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.049577474594116, "global_step": 588685, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9384269714355469, "global_step": 588686, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0175533294677734, "global_step": 588687, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0211939811706543, "global_step": 588688, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.8799699544906616, "global_step": 588689, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0743680000305176, "global_step": 588690, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0318076610565186, "global_step": 588691, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.049798011779785, "global_step": 588692, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9727284908294678, "global_step": 588693, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0696356296539307, "global_step": 588694, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9599791765213013, "global_step": 588695, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9921064376831055, "global_step": 588696, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0510122776031494, "global_step": 588697, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0333597660064697, "global_step": 588698, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9590915441513062, "global_step": 588699, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9813570976257324, "global_step": 588700, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9766042232513428, "global_step": 588701, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9763203859329224, "global_step": 588702, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0329692363739014, "global_step": 588703, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0234453678131104, "global_step": 588704, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.055647850036621, "global_step": 588705, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.035186529159546, "global_step": 588706, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.147477149963379, "global_step": 588707, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0513789653778076, "global_step": 588708, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.004225492477417, "global_step": 588709, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9728974103927612, "global_step": 588710, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9940769672393799, "global_step": 588711, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1193840503692627, "global_step": 588712, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9459974765777588, "global_step": 588713, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.041222333908081, "global_step": 588714, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.007673978805542, "global_step": 588715, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0793046951293945, "global_step": 588716, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.017573356628418, "global_step": 588717, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.034029722213745, "global_step": 588718, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0446152687072754, "global_step": 588719, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.016798973083496, "global_step": 588720, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0158631801605225, "global_step": 588721, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1594791412353516, "global_step": 588722, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0183846950531006, "global_step": 588723, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9692223072052002, "global_step": 588724, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9034454822540283, "global_step": 588725, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.003819465637207, "global_step": 588726, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0000030994415283, "global_step": 588727, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0803844928741455, "global_step": 588728, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0508885383605957, "global_step": 588729, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.019563674926758, "global_step": 588730, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.020794630050659, "global_step": 588731, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0570263862609863, "global_step": 588732, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9832756519317627, "global_step": 588733, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.030466318130493, "global_step": 588734, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9818527698516846, "global_step": 588735, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9757779836654663, "global_step": 588736, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.046544313430786, "global_step": 588737, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0502634048461914, "global_step": 588738, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9579777717590332, "global_step": 588739, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.944109320640564, "global_step": 588740, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.011167049407959, "global_step": 588741, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.002805709838867, "global_step": 588742, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9854700565338135, "global_step": 588743, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9682780504226685, "global_step": 588744, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9605358839035034, "global_step": 588745, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0832223892211914, "global_step": 588746, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9681826829910278, "global_step": 588747, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.993665099143982, "global_step": 588748, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.008134365081787, "global_step": 588749, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0409553050994873, "global_step": 588750, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9721436500549316, "global_step": 588751, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.974043369293213, "global_step": 588752, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.025810718536377, "global_step": 588753, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9954931735992432, "global_step": 588754, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9557182788848877, "global_step": 588755, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9621896743774414, "global_step": 588756, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0462424755096436, "global_step": 588757, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0176384449005127, "global_step": 588758, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.969556450843811, "global_step": 588759, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.029151201248169, "global_step": 588760, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0557072162628174, "global_step": 588761, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0034878253936768, "global_step": 588762, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.035275459289551, "global_step": 588763, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0392212867736816, "global_step": 588764, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0101242065429688, "global_step": 588765, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.992812991142273, "global_step": 588766, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.977439045906067, "global_step": 588767, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.048706531524658, "global_step": 588768, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9733860492706299, "global_step": 588769, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9211825132369995, "global_step": 588770, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9431121349334717, "global_step": 588771, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0462565422058105, "global_step": 588772, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9602206945419312, "global_step": 588773, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0369725227355957, "global_step": 588774, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0022454261779785, "global_step": 588775, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0137693881988525, "global_step": 588776, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9852683544158936, "global_step": 588777, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.054741859436035, "global_step": 588778, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.035175323486328, "global_step": 588779, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.129725933074951, "global_step": 588780, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.067704439163208, "global_step": 588781, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9763145446777344, "global_step": 588782, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.020936965942383, "global_step": 588783, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0153589248657227, "global_step": 588784, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.037466526031494, "global_step": 588785, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0419700145721436, "global_step": 588786, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.957694172859192, "global_step": 588787, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9743903875350952, "global_step": 588788, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.100588083267212, "global_step": 588789, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0443248748779297, "global_step": 588790, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.029055118560791, "global_step": 588791, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9903539419174194, "global_step": 588792, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9999969005584717, "global_step": 588793, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9956145286560059, "global_step": 588794, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.099548101425171, "global_step": 588795, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.969282627105713, "global_step": 588796, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.044187545776367, "global_step": 588797, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.999550461769104, "global_step": 588798, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0281198024749756, "global_step": 588799, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9912405014038086, "global_step": 588800, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0312681198120117, "global_step": 588801, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.062105417251587, "global_step": 588802, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.098855495452881, "global_step": 588803, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0987086296081543, "global_step": 588804, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0326666831970215, "global_step": 588805, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9960135221481323, "global_step": 588806, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.016296863555908, "global_step": 588807, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0266075134277344, "global_step": 588808, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9691340923309326, "global_step": 588809, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.06880259513855, "global_step": 588810, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9647011756896973, "global_step": 588811, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.006305694580078, "global_step": 588812, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0933268070220947, "global_step": 588813, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0559558868408203, "global_step": 588814, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0554215908050537, "global_step": 588815, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0893936157226562, "global_step": 588816, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9684250354766846, "global_step": 588817, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9863262176513672, "global_step": 588818, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.009490728378296, "global_step": 588819, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9760055541992188, "global_step": 588820, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0721046924591064, "global_step": 588821, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0527596473693848, "global_step": 588822, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.965714931488037, "global_step": 588823, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.996259093284607, "global_step": 588824, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9608885049819946, "global_step": 588825, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0891852378845215, "global_step": 588826, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.045837163925171, "global_step": 588827, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9797557592391968, "global_step": 588828, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0566976070404053, "global_step": 588829, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9774408340454102, "global_step": 588830, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0773305892944336, "global_step": 588831, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.083998203277588, "global_step": 588832, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.041696786880493, "global_step": 588833, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.020905017852783, "global_step": 588834, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9711700677871704, "global_step": 588835, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.07948899269104, "global_step": 588836, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9907375574111938, "global_step": 588837, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.055760145187378, "global_step": 588838, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9770816564559937, "global_step": 588839, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.024780035018921, "global_step": 588840, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.996883749961853, "global_step": 588841, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9720470905303955, "global_step": 588842, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1192538738250732, "global_step": 588843, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.010080337524414, "global_step": 588844, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9923450946807861, "global_step": 588845, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.955992341041565, "global_step": 588846, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.993324637413025, "global_step": 588847, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.015068531036377, "global_step": 588848, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0903513431549072, "global_step": 588849, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.012428045272827, "global_step": 588850, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9482431411743164, "global_step": 588851, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9975117444992065, "global_step": 588852, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9735480546951294, "global_step": 588853, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.066828727722168, "global_step": 588854, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.07401704788208, "global_step": 588855, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.029212713241577, "global_step": 588856, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.071934938430786, "global_step": 588857, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0747854709625244, "global_step": 588858, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0115437507629395, "global_step": 588859, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.008925676345825, "global_step": 588860, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.021651268005371, "global_step": 588861, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.035546064376831, "global_step": 588862, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0158278942108154, "global_step": 588863, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.959691047668457, "global_step": 588864, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.985270619392395, "global_step": 588865, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.991557002067566, "global_step": 588866, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0031979084014893, "global_step": 588867, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.063321113586426, "global_step": 588868, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.029207944869995, "global_step": 588869, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.037006378173828, "global_step": 588870, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0018858909606934, "global_step": 588871, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9893344640731812, "global_step": 588872, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0311098098754883, "global_step": 588873, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.03788423538208, "global_step": 588874, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9766203165054321, "global_step": 588875, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0255320072174072, "global_step": 588876, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0441741943359375, "global_step": 588877, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.039977550506592, "global_step": 588878, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9622911214828491, "global_step": 588879, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0367395877838135, "global_step": 588880, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0137248039245605, "global_step": 588881, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9815183877944946, "global_step": 588882, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.031680107116699, "global_step": 588883, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.113198757171631, "global_step": 588884, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9534486532211304, "global_step": 588885, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9765660762786865, "global_step": 588886, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.022592544555664, "global_step": 588887, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.956313133239746, "global_step": 588888, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1049675941467285, "global_step": 588889, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9849722385406494, "global_step": 588890, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0815248489379883, "global_step": 588891, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.017362594604492, "global_step": 588892, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0815420150756836, "global_step": 588893, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9875059127807617, "global_step": 588894, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0580427646636963, "global_step": 588895, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.045135259628296, "global_step": 588896, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.099092960357666, "global_step": 588897, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0015358924865723, "global_step": 588898, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0200037956237793, "global_step": 588899, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.045515537261963, "global_step": 588900, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9924170970916748, "global_step": 588901, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.028369903564453, "global_step": 588902, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0253448486328125, "global_step": 588903, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0272057056427, "global_step": 588904, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.030381441116333, "global_step": 588905, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.061129093170166, "global_step": 588906, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9682486057281494, "global_step": 588907, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0047786235809326, "global_step": 588908, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.008354663848877, "global_step": 588909, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0320329666137695, "global_step": 588910, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.003061294555664, "global_step": 588911, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9282358884811401, "global_step": 588912, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9686667919158936, "global_step": 588913, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0207204818725586, "global_step": 588914, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9729903936386108, "global_step": 588915, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0227530002593994, "global_step": 588916, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.041290044784546, "global_step": 588917, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.099506139755249, "global_step": 588918, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1180624961853027, "global_step": 588919, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0245964527130127, "global_step": 588920, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0111467838287354, "global_step": 588921, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9354997873306274, "global_step": 588922, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.007798433303833, "global_step": 588923, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.067162036895752, "global_step": 588924, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.983574390411377, "global_step": 588925, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.038862943649292, "global_step": 588926, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0319697856903076, "global_step": 588927, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.983484148979187, "global_step": 588928, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0394296646118164, "global_step": 588929, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.000980854034424, "global_step": 588930, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0438449382781982, "global_step": 588931, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.125576972961426, "global_step": 588932, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0671393871307373, "global_step": 588933, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.004002094268799, "global_step": 588934, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.047996759414673, "global_step": 588935, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0483548641204834, "global_step": 588936, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.949432373046875, "global_step": 588937, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9944037199020386, "global_step": 588938, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9440057277679443, "global_step": 588939, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9986498355865479, "global_step": 588940, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1159331798553467, "global_step": 588941, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.057790994644165, "global_step": 588942, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9798243045806885, "global_step": 588943, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.060396194458008, "global_step": 588944, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.013899326324463, "global_step": 588945, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.026695489883423, "global_step": 588946, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1064417362213135, "global_step": 588947, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0594236850738525, "global_step": 588948, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.004849910736084, "global_step": 588949, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9519826173782349, "global_step": 588950, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9552305936813354, "global_step": 588951, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.024078130722046, "global_step": 588952, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0864741802215576, "global_step": 588953, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9973235130310059, "global_step": 588954, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0747530460357666, "global_step": 588955, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9539059400558472, "global_step": 588956, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.044302225112915, "global_step": 588957, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0333151817321777, "global_step": 588958, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9941678047180176, "global_step": 588959, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.018418788909912, "global_step": 588960, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0969791412353516, "global_step": 588961, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0760157108306885, "global_step": 588962, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.942647933959961, "global_step": 588963, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.02742862701416, "global_step": 588964, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.942515254020691, "global_step": 588965, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9635131359100342, "global_step": 588966, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.019200563430786, "global_step": 588967, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9781192541122437, "global_step": 588968, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.046741008758545, "global_step": 588969, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.01985764503479, "global_step": 588970, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.019143581390381, "global_step": 588971, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9478142261505127, "global_step": 588972, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0520265102386475, "global_step": 588973, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.005697011947632, "global_step": 588974, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9968678951263428, "global_step": 588975, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.033032178878784, "global_step": 588976, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9925061464309692, "global_step": 588977, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.009687662124634, "global_step": 588978, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.053401470184326, "global_step": 588979, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0753321647644043, "global_step": 588980, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.8830536603927612, "global_step": 588981, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.938671588897705, "global_step": 588982, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0175533294677734, "global_step": 588983, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0077908039093018, "global_step": 588984, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.016101360321045, "global_step": 588985, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0030133724212646, "global_step": 588986, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9968045949935913, "global_step": 588987, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.002934455871582, "global_step": 588988, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.033287763595581, "global_step": 588989, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9662253856658936, "global_step": 588990, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9947526454925537, "global_step": 588991, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0611863136291504, "global_step": 588992, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9711897373199463, "global_step": 588993, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0118541717529297, "global_step": 588994, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1035664081573486, "global_step": 588995, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.029755115509033, "global_step": 588996, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9906432628631592, "global_step": 588997, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9916709661483765, "global_step": 588998, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.056795120239258, "global_step": 588999, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.024054527282715, "global_step": 589000, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0767414569854736, "global_step": 589001, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.048778772354126, "global_step": 589002, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9952818155288696, "global_step": 589003, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.01942777633667, "global_step": 589004, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.047459363937378, "global_step": 589005, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0527164936065674, "global_step": 589006, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0152268409729004, "global_step": 589007, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0521512031555176, "global_step": 589008, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0270659923553467, "global_step": 589009, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.078390598297119, "global_step": 589010, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9791492223739624, "global_step": 589011, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9968187808990479, "global_step": 589012, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9025412797927856, "global_step": 589013, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.033311367034912, "global_step": 589014, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1021833419799805, "global_step": 589015, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0366733074188232, "global_step": 589016, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0265252590179443, "global_step": 589017, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9986155033111572, "global_step": 589018, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0642454624176025, "global_step": 589019, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0498087406158447, "global_step": 589020, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.985816240310669, "global_step": 589021, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.000962018966675, "global_step": 589022, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0830087661743164, "global_step": 589023, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0294198989868164, "global_step": 589024, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.029627561569214, "global_step": 589025, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.010671377182007, "global_step": 589026, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.07725191116333, "global_step": 589027, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0173614025115967, "global_step": 589028, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9580599069595337, "global_step": 589029, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.984086513519287, "global_step": 589030, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0608317852020264, "global_step": 589031, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.034224510192871, "global_step": 589032, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.000789165496826, "global_step": 589033, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.015068531036377, "global_step": 589034, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0801711082458496, "global_step": 589035, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0287017822265625, "global_step": 589036, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0974605083465576, "global_step": 589037, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0980818271636963, "global_step": 589038, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.993348240852356, "global_step": 589039, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0378618240356445, "global_step": 589040, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0131478309631348, "global_step": 589041, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0521507263183594, "global_step": 589042, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9591807126998901, "global_step": 589043, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.050546884536743, "global_step": 589044, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.040487289428711, "global_step": 589045, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.06364369392395, "global_step": 589046, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9155184030532837, "global_step": 589047, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.991650104522705, "global_step": 589048, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0270588397979736, "global_step": 589049, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.009507179260254, "global_step": 589050, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0220112800598145, "global_step": 589051, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0068154335021973, "global_step": 589052, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.046627998352051, "global_step": 589053, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.057793140411377, "global_step": 589054, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9776055812835693, "global_step": 589055, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.975130558013916, "global_step": 589056, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0050606727600098, "global_step": 589057, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0611937046051025, "global_step": 589058, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0571513175964355, "global_step": 589059, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0033833980560303, "global_step": 589060, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1143198013305664, "global_step": 589061, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0837879180908203, "global_step": 589062, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9963889122009277, "global_step": 589063, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0659141540527344, "global_step": 589064, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9249533414840698, "global_step": 589065, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0304455757141113, "global_step": 589066, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9996356964111328, "global_step": 589067, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.052062511444092, "global_step": 589068, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0495615005493164, "global_step": 589069, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.055213212966919, "global_step": 589070, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0625152587890625, "global_step": 589071, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9693586826324463, "global_step": 589072, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9907619953155518, "global_step": 589073, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.054133176803589, "global_step": 589074, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9993191957473755, "global_step": 589075, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9883522987365723, "global_step": 589076, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9932491779327393, "global_step": 589077, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9639301300048828, "global_step": 589078, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9848867654800415, "global_step": 589079, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.005223512649536, "global_step": 589080, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.00866436958313, "global_step": 589081, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0958304405212402, "global_step": 589082, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.955152988433838, "global_step": 589083, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9521843194961548, "global_step": 589084, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.132491111755371, "global_step": 589085, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9770177602767944, "global_step": 589086, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0316293239593506, "global_step": 589087, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.097050666809082, "global_step": 589088, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.072194814682007, "global_step": 589089, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0236051082611084, "global_step": 589090, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.061265707015991, "global_step": 589091, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.96453857421875, "global_step": 589092, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0499250888824463, "global_step": 589093, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9716298580169678, "global_step": 589094, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0596022605895996, "global_step": 589095, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9784454107284546, "global_step": 589096, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.003150224685669, "global_step": 589097, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0640528202056885, "global_step": 589098, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0899839401245117, "global_step": 589099, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.02630615234375, "global_step": 589100, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0135724544525146, "global_step": 589101, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.012786626815796, "global_step": 589102, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.017157793045044, "global_step": 589103, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.015376329421997, "global_step": 589104, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.106586456298828, "global_step": 589105, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0559632778167725, "global_step": 589106, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.019158124923706, "global_step": 589107, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0448830127716064, "global_step": 589108, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9157339334487915, "global_step": 589109, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9822205305099487, "global_step": 589110, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.028001308441162, "global_step": 589111, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0123322010040283, "global_step": 589112, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9905086755752563, "global_step": 589113, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0726819038391113, "global_step": 589114, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0345258712768555, "global_step": 589115, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0356788635253906, "global_step": 589116, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.027462959289551, "global_step": 589117, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.077075481414795, "global_step": 589118, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0475783348083496, "global_step": 589119, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9937714338302612, "global_step": 589120, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.006110191345215, "global_step": 589121, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0910327434539795, "global_step": 589122, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0702898502349854, "global_step": 589123, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0349807739257812, "global_step": 589124, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1307146549224854, "global_step": 589125, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0444865226745605, "global_step": 589126, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1086065769195557, "global_step": 589127, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0259313583374023, "global_step": 589128, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0303523540496826, "global_step": 589129, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0880589485168457, "global_step": 589130, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.07773756980896, "global_step": 589131, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.961089849472046, "global_step": 589132, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0650973320007324, "global_step": 589133, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.071312427520752, "global_step": 589134, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1013827323913574, "global_step": 589135, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9342392683029175, "global_step": 589136, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.016535520553589, "global_step": 589137, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.021456480026245, "global_step": 589138, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.044823169708252, "global_step": 589139, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9833284616470337, "global_step": 589140, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9899059534072876, "global_step": 589141, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0226798057556152, "global_step": 589142, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9799867868423462, "global_step": 589143, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9914724826812744, "global_step": 589144, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9807220697402954, "global_step": 589145, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.005850076675415, "global_step": 589146, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0281925201416016, "global_step": 589147, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.037663698196411, "global_step": 589148, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0783255100250244, "global_step": 589149, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.049903154373169, "global_step": 589150, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.053783416748047, "global_step": 589151, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.044100761413574, "global_step": 589152, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1151158809661865, "global_step": 589153, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9501209259033203, "global_step": 589154, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.006329298019409, "global_step": 589155, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.03109073638916, "global_step": 589156, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.045349359512329, "global_step": 589157, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0148918628692627, "global_step": 589158, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9768259525299072, "global_step": 589159, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0459043979644775, "global_step": 589160, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0823137760162354, "global_step": 589161, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0545003414154053, "global_step": 589162, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9573054313659668, "global_step": 589163, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1856913566589355, "global_step": 589164, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.092244863510132, "global_step": 589165, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.007458448410034, "global_step": 589166, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.107905387878418, "global_step": 589167, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9688024520874023, "global_step": 589168, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.04598069190979, "global_step": 589169, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0116188526153564, "global_step": 589170, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0612969398498535, "global_step": 589171, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0191237926483154, "global_step": 589172, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0548322200775146, "global_step": 589173, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0793373584747314, "global_step": 589174, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.068730115890503, "global_step": 589175, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0160679817199707, "global_step": 589176, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9581798315048218, "global_step": 589177, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9795933961868286, "global_step": 589178, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.980642557144165, "global_step": 589179, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.026770830154419, "global_step": 589180, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0484156608581543, "global_step": 589181, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.056118965148926, "global_step": 589182, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0984315872192383, "global_step": 589183, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0590012073516846, "global_step": 589184, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0228159427642822, "global_step": 589185, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.060753345489502, "global_step": 589186, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.044327974319458, "global_step": 589187, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0019278526306152, "global_step": 589188, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.997090220451355, "global_step": 589189, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0371861457824707, "global_step": 589190, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0255508422851562, "global_step": 589191, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.073124408721924, "global_step": 589192, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0267624855041504, "global_step": 589193, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0163846015930176, "global_step": 589194, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0439603328704834, "global_step": 589195, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0272905826568604, "global_step": 589196, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0540976524353027, "global_step": 589197, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9948973655700684, "global_step": 589198, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.038045883178711, "global_step": 589199, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.017566680908203, "global_step": 589200, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.000386953353882, "global_step": 589201, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9235361814498901, "global_step": 589202, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.121263265609741, "global_step": 589203, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9538604021072388, "global_step": 589204, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0858781337738037, "global_step": 589205, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.044039726257324, "global_step": 589206, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0397515296936035, "global_step": 589207, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9685121774673462, "global_step": 589208, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9887269735336304, "global_step": 589209, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.999144196510315, "global_step": 589210, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.908856749534607, "global_step": 589211, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.072300910949707, "global_step": 589212, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9902936220169067, "global_step": 589213, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.943715214729309, "global_step": 589214, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0371246337890625, "global_step": 589215, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.059263229370117, "global_step": 589216, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.97934091091156, "global_step": 589217, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0876989364624023, "global_step": 589218, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0553619861602783, "global_step": 589219, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9732290506362915, "global_step": 589220, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9991343021392822, "global_step": 589221, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0530078411102295, "global_step": 589222, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9952747821807861, "global_step": 589223, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9638161659240723, "global_step": 589224, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.053518772125244, "global_step": 589225, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0182156562805176, "global_step": 589226, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0880348682403564, "global_step": 589227, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.001079797744751, "global_step": 589228, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.982704520225525, "global_step": 589229, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.051684856414795, "global_step": 589230, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9780609607696533, "global_step": 589231, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.040271282196045, "global_step": 589232, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.082075834274292, "global_step": 589233, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0218775272369385, "global_step": 589234, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0126259326934814, "global_step": 589235, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0589070320129395, "global_step": 589236, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.955336093902588, "global_step": 589237, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.915458083152771, "global_step": 589238, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.161309242248535, "global_step": 589239, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.01979660987854, "global_step": 589240, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0114784240722656, "global_step": 589241, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.051724433898926, "global_step": 589242, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9245089292526245, "global_step": 589243, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9932664632797241, "global_step": 589244, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.026878833770752, "global_step": 589245, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.054187774658203, "global_step": 589246, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9820358753204346, "global_step": 589247, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0182011127471924, "global_step": 589248, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9283907413482666, "global_step": 589249, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9686533212661743, "global_step": 589250, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0386624336242676, "global_step": 589251, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.031829833984375, "global_step": 589252, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0199460983276367, "global_step": 589253, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0829977989196777, "global_step": 589254, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9387280941009521, "global_step": 589255, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9887148141860962, "global_step": 589256, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.03057861328125, "global_step": 589257, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9994254112243652, "global_step": 589258, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0398905277252197, "global_step": 589259, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9676990509033203, "global_step": 589260, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9743564128875732, "global_step": 589261, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0631601810455322, "global_step": 589262, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.1465744972229004, "global_step": 589263, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.055694341659546, "global_step": 589264, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.061424493789673, "global_step": 589265, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0491409301757812, "global_step": 589266, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9416040182113647, "global_step": 589267, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.023022174835205, "global_step": 589268, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9889642000198364, "global_step": 589269, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.079342842102051, "global_step": 589270, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9762685298919678, "global_step": 589271, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0109593868255615, "global_step": 589272, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9552651643753052, "global_step": 589273, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9728909730911255, "global_step": 589274, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0243637561798096, "global_step": 589275, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.08981990814209, "global_step": 589276, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.018921136856079, "global_step": 589277, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0264694690704346, "global_step": 589278, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9886164665222168, "global_step": 589279, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9410120248794556, "global_step": 589280, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.069257974624634, "global_step": 589281, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.019057512283325, "global_step": 589282, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9786430597305298, "global_step": 589283, "epoch": 957, "lr": 5e-05}
{"train_loss": 2.0188112258911133, "global_step": 589284, "epoch": 957, "lr": 5e-05}
{"train_loss": 1.9853214025497437, "global_step": 589285, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0750300884246826, "global_step": 589286, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.035998821258545, "global_step": 589287, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0134801864624023, "global_step": 589288, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0205600261688232, "global_step": 589289, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.098506450653076, "global_step": 589290, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0848240852355957, "global_step": 589291, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0223188400268555, "global_step": 589292, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.995964765548706, "global_step": 589293, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0470664501190186, "global_step": 589294, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9919134378433228, "global_step": 589295, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.013383626937866, "global_step": 589296, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.006389856338501, "global_step": 589297, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.055445671081543, "global_step": 589298, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.8210666179656982, "global_step": 589299, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9771625995635986, "global_step": 589300, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0433366298675537, "global_step": 589301, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.980939269065857, "global_step": 589302, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.02097487449646, "global_step": 589303, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.05033540725708, "global_step": 589304, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9730041027069092, "global_step": 589305, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0356101989746094, "global_step": 589306, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0254743099212646, "global_step": 589307, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.014594554901123, "global_step": 589308, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.984332799911499, "global_step": 589309, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9220373630523682, "global_step": 589310, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0685534477233887, "global_step": 589311, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0768685340881348, "global_step": 589312, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.016836404800415, "global_step": 589313, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.036421775817871, "global_step": 589314, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0540738105773926, "global_step": 589315, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0101983547210693, "global_step": 589316, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.066765785217285, "global_step": 589317, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1331276893615723, "global_step": 589318, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0117740631103516, "global_step": 589319, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.003539562225342, "global_step": 589320, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.02007794380188, "global_step": 589321, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0799169540405273, "global_step": 589322, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.059743881225586, "global_step": 589323, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0004587173461914, "global_step": 589324, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.051250457763672, "global_step": 589325, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0578322410583496, "global_step": 589326, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.962214469909668, "global_step": 589327, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0484018325805664, "global_step": 589328, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.953210711479187, "global_step": 589329, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9680886268615723, "global_step": 589330, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9095157384872437, "global_step": 589331, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0313398838043213, "global_step": 589332, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9919763803482056, "global_step": 589333, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9648786783218384, "global_step": 589334, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9675675630569458, "global_step": 589335, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0568556785583496, "global_step": 589336, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0302836894989014, "global_step": 589337, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9920278787612915, "global_step": 589338, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0050952434539795, "global_step": 589339, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.992401361465454, "global_step": 589340, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.053727626800537, "global_step": 589341, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.037381172180176, "global_step": 589342, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0519368648529053, "global_step": 589343, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0355608463287354, "global_step": 589344, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.049705743789673, "global_step": 589345, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0621562004089355, "global_step": 589346, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9190893173217773, "global_step": 589347, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0860848426818848, "global_step": 589348, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.993150234222412, "global_step": 589349, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9879114627838135, "global_step": 589350, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9606825113296509, "global_step": 589351, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9846761226654053, "global_step": 589352, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9850773811340332, "global_step": 589353, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0066914558410645, "global_step": 589354, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9433505535125732, "global_step": 589355, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.022439479827881, "global_step": 589356, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0928001403808594, "global_step": 589357, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9941850900650024, "global_step": 589358, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0354321002960205, "global_step": 589359, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1072182655334473, "global_step": 589360, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.041947603225708, "global_step": 589361, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.052063465118408, "global_step": 589362, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.028797149658203, "global_step": 589363, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.027395248413086, "global_step": 589364, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9642157554626465, "global_step": 589365, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.019472599029541, "global_step": 589366, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.00097393989563, "global_step": 589367, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0000922679901123, "global_step": 589368, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9502601623535156, "global_step": 589369, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9304252862930298, "global_step": 589370, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1235663890838623, "global_step": 589371, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9704740047454834, "global_step": 589372, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.931416630744934, "global_step": 589373, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9624518156051636, "global_step": 589374, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9849704504013062, "global_step": 589375, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9790241718292236, "global_step": 589376, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0676748752593994, "global_step": 589377, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.075636148452759, "global_step": 589378, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.915417194366455, "global_step": 589379, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9763157367706299, "global_step": 589380, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.954911470413208, "global_step": 589381, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0012073516845703, "global_step": 589382, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0386786460876465, "global_step": 589383, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.017448663711548, "global_step": 589384, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9853627681732178, "global_step": 589385, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9566376209259033, "global_step": 589386, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9997797012329102, "global_step": 589387, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0223164558410645, "global_step": 589388, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0158448219299316, "global_step": 589389, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9970510005950928, "global_step": 589390, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0202410221099854, "global_step": 589391, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9585436582565308, "global_step": 589392, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.080793619155884, "global_step": 589393, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0368733406066895, "global_step": 589394, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9144346714019775, "global_step": 589395, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.077761173248291, "global_step": 589396, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.060213565826416, "global_step": 589397, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0256423950195312, "global_step": 589398, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.114901542663574, "global_step": 589399, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9279041290283203, "global_step": 589400, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.008859872817993, "global_step": 589401, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.009859085083008, "global_step": 589402, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9944592714309692, "global_step": 589403, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9579225778579712, "global_step": 589404, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.94596529006958, "global_step": 589405, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0933799743652344, "global_step": 589406, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9932692050933838, "global_step": 589407, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.056459426879883, "global_step": 589408, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.064926862716675, "global_step": 589409, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.991346001625061, "global_step": 589410, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.03794264793396, "global_step": 589411, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0383729934692383, "global_step": 589412, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1268727779388428, "global_step": 589413, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9941684007644653, "global_step": 589414, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9697381258010864, "global_step": 589415, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9873257875442505, "global_step": 589416, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9357250928878784, "global_step": 589417, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.939754605293274, "global_step": 589418, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0229976177215576, "global_step": 589419, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0436058044433594, "global_step": 589420, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.032604455947876, "global_step": 589421, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.039935350418091, "global_step": 589422, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.010932683944702, "global_step": 589423, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.011394739151001, "global_step": 589424, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.027186155319214, "global_step": 589425, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.073045492172241, "global_step": 589426, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9903312921524048, "global_step": 589427, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.066096544265747, "global_step": 589428, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.099614381790161, "global_step": 589429, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9902015924453735, "global_step": 589430, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.989467978477478, "global_step": 589431, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1094932556152344, "global_step": 589432, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9573458433151245, "global_step": 589433, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9552466869354248, "global_step": 589434, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.036017656326294, "global_step": 589435, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.049604654312134, "global_step": 589436, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0889062881469727, "global_step": 589437, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9951874017715454, "global_step": 589438, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0083091259002686, "global_step": 589439, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9824118614196777, "global_step": 589440, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.913070559501648, "global_step": 589441, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9165984392166138, "global_step": 589442, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9877525568008423, "global_step": 589443, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.032965898513794, "global_step": 589444, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.067103147506714, "global_step": 589445, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.019221782684326, "global_step": 589446, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9840569496154785, "global_step": 589447, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9814605712890625, "global_step": 589448, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0602095127105713, "global_step": 589449, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.056161403656006, "global_step": 589450, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9915273189544678, "global_step": 589451, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0756049156188965, "global_step": 589452, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.148240327835083, "global_step": 589453, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9773975610733032, "global_step": 589454, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0083160400390625, "global_step": 589455, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9790691137313843, "global_step": 589456, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.051938772201538, "global_step": 589457, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9647216796875, "global_step": 589458, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.972439169883728, "global_step": 589459, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.033841133117676, "global_step": 589460, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0746190547943115, "global_step": 589461, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9577341079711914, "global_step": 589462, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9874234199523926, "global_step": 589463, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9767142534255981, "global_step": 589464, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9782079458236694, "global_step": 589465, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.966336727142334, "global_step": 589466, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9770184755325317, "global_step": 589467, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.089439630508423, "global_step": 589468, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9953328371047974, "global_step": 589469, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.018474578857422, "global_step": 589470, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9468103647232056, "global_step": 589471, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0159809589385986, "global_step": 589472, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9567915201187134, "global_step": 589473, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9554979801177979, "global_step": 589474, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0198631286621094, "global_step": 589475, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.020806074142456, "global_step": 589476, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.027820587158203, "global_step": 589477, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9348033666610718, "global_step": 589478, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9717390537261963, "global_step": 589479, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0129106044769287, "global_step": 589480, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9851821660995483, "global_step": 589481, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9981606006622314, "global_step": 589482, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.999707818031311, "global_step": 589483, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.074880361557007, "global_step": 589484, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0460164546966553, "global_step": 589485, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0478429794311523, "global_step": 589486, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9830552339553833, "global_step": 589487, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.01562237739563, "global_step": 589488, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.017411708831787, "global_step": 589489, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9356520175933838, "global_step": 589490, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.027006149291992, "global_step": 589491, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9737921953201294, "global_step": 589492, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0277581214904785, "global_step": 589493, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.057673215866089, "global_step": 589494, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.025475263595581, "global_step": 589495, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0338830947875977, "global_step": 589496, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9949796199798584, "global_step": 589497, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0706188678741455, "global_step": 589498, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9974884986877441, "global_step": 589499, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.036341428756714, "global_step": 589500, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.009371042251587, "global_step": 589501, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.031576633453369, "global_step": 589502, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0036046504974365, "global_step": 589503, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.031942367553711, "global_step": 589504, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.05481219291687, "global_step": 589505, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0627737045288086, "global_step": 589506, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9573155641555786, "global_step": 589507, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.097059726715088, "global_step": 589508, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0273847579956055, "global_step": 589509, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0549206733703613, "global_step": 589510, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9589838981628418, "global_step": 589511, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0464072227478027, "global_step": 589512, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0908234119415283, "global_step": 589513, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.039738893508911, "global_step": 589514, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0314383506774902, "global_step": 589515, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9915533065795898, "global_step": 589516, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0181055068969727, "global_step": 589517, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9352589845657349, "global_step": 589518, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9731959104537964, "global_step": 589519, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0018017292022705, "global_step": 589520, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0359489917755127, "global_step": 589521, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.951674461364746, "global_step": 589522, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0595927238464355, "global_step": 589523, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.052941083908081, "global_step": 589524, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0719964504241943, "global_step": 589525, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9932137727737427, "global_step": 589526, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.078169345855713, "global_step": 589527, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9889953136444092, "global_step": 589528, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.023664712905884, "global_step": 589529, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0061330795288086, "global_step": 589530, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0465269088745117, "global_step": 589531, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9521715641021729, "global_step": 589532, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9340730905532837, "global_step": 589533, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.081794500350952, "global_step": 589534, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.000430107116699, "global_step": 589535, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0345053672790527, "global_step": 589536, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9879000186920166, "global_step": 589537, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0641956329345703, "global_step": 589538, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9960473775863647, "global_step": 589539, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9838182926177979, "global_step": 589540, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0173633098602295, "global_step": 589541, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9993432760238647, "global_step": 589542, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9786951541900635, "global_step": 589543, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0506834983825684, "global_step": 589544, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.017526149749756, "global_step": 589545, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.046889543533325, "global_step": 589546, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.93837308883667, "global_step": 589547, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9756444692611694, "global_step": 589548, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9934505224227905, "global_step": 589549, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9790090322494507, "global_step": 589550, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.064018487930298, "global_step": 589551, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1152360439300537, "global_step": 589552, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9785511493682861, "global_step": 589553, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0573570728302, "global_step": 589554, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.022388458251953, "global_step": 589555, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9611084461212158, "global_step": 589556, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9685472249984741, "global_step": 589557, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0166690349578857, "global_step": 589558, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0250377655029297, "global_step": 589559, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9468283653259277, "global_step": 589560, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.017552137374878, "global_step": 589561, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.059746742248535, "global_step": 589562, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9828671216964722, "global_step": 589563, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.088823080062866, "global_step": 589564, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.012603759765625, "global_step": 589565, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.009010076522827, "global_step": 589566, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9949698448181152, "global_step": 589567, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.988699197769165, "global_step": 589568, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9287121295928955, "global_step": 589569, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.049569606781006, "global_step": 589570, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0621039867401123, "global_step": 589571, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0404794216156006, "global_step": 589572, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.047194480895996, "global_step": 589573, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0467593669891357, "global_step": 589574, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.997416615486145, "global_step": 589575, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0004220008850098, "global_step": 589576, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.982697606086731, "global_step": 589577, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.148625612258911, "global_step": 589578, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9726390838623047, "global_step": 589579, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.055671215057373, "global_step": 589580, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0617728233337402, "global_step": 589581, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.04071307182312, "global_step": 589582, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.041226387023926, "global_step": 589583, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.049452543258667, "global_step": 589584, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9853771924972534, "global_step": 589585, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.022787570953369, "global_step": 589586, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0347495079040527, "global_step": 589587, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.034374952316284, "global_step": 589588, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0710067749023438, "global_step": 589589, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.039869546890259, "global_step": 589590, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.064065456390381, "global_step": 589591, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.018040180206299, "global_step": 589592, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9513269662857056, "global_step": 589593, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.030303478240967, "global_step": 589594, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0653274059295654, "global_step": 589595, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9442822933197021, "global_step": 589596, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.8926838636398315, "global_step": 589597, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9938312768936157, "global_step": 589598, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.003793478012085, "global_step": 589599, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.018683671951294, "global_step": 589600, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.03229022026062, "global_step": 589601, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0342955589294434, "global_step": 589602, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.051305055618286, "global_step": 589603, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.058626413345337, "global_step": 589604, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0706493854522705, "global_step": 589605, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9812111854553223, "global_step": 589606, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9885817766189575, "global_step": 589607, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0293145179748535, "global_step": 589608, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0775997638702393, "global_step": 589609, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.012186288833618, "global_step": 589610, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0057685375213623, "global_step": 589611, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0665295124053955, "global_step": 589612, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.026015520095825, "global_step": 589613, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9681119918823242, "global_step": 589614, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9837045669555664, "global_step": 589615, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0029678344726562, "global_step": 589616, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0342860221862793, "global_step": 589617, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0153331756591797, "global_step": 589618, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0653584003448486, "global_step": 589619, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.94662344455719, "global_step": 589620, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9792991876602173, "global_step": 589621, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9871392250061035, "global_step": 589622, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.988296389579773, "global_step": 589623, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0589029788970947, "global_step": 589624, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.958380103111267, "global_step": 589625, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.024810314178467, "global_step": 589626, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0359699726104736, "global_step": 589627, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.018829107284546, "global_step": 589628, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0858967304229736, "global_step": 589629, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.021618127822876, "global_step": 589630, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.942202091217041, "global_step": 589631, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.034057855606079, "global_step": 589632, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0559215545654297, "global_step": 589633, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9715054035186768, "global_step": 589634, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0493621826171875, "global_step": 589635, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.123126268386841, "global_step": 589636, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.028630018234253, "global_step": 589637, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.008598566055298, "global_step": 589638, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0228617191314697, "global_step": 589639, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9907615184783936, "global_step": 589640, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0294418334960938, "global_step": 589641, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.004326343536377, "global_step": 589642, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1100168228149414, "global_step": 589643, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0286271572113037, "global_step": 589644, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.981398105621338, "global_step": 589645, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.076263189315796, "global_step": 589646, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1358132362365723, "global_step": 589647, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.14715576171875, "global_step": 589648, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0203301906585693, "global_step": 589649, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9686698913574219, "global_step": 589650, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0109405517578125, "global_step": 589651, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.080535411834717, "global_step": 589652, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1127982139587402, "global_step": 589653, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0680997371673584, "global_step": 589654, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9590587615966797, "global_step": 589655, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9346575736999512, "global_step": 589656, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9666980504989624, "global_step": 589657, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9688137769699097, "global_step": 589658, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0232839584350586, "global_step": 589659, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1065852642059326, "global_step": 589660, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.009615421295166, "global_step": 589661, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0404677391052246, "global_step": 589662, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9574177265167236, "global_step": 589663, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0745368003845215, "global_step": 589664, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0432839393615723, "global_step": 589665, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9836859703063965, "global_step": 589666, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.044842004776001, "global_step": 589667, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0040640830993652, "global_step": 589668, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9967963695526123, "global_step": 589669, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9933335781097412, "global_step": 589670, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0061211585998535, "global_step": 589671, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.94733726978302, "global_step": 589672, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0478155612945557, "global_step": 589673, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0212435722351074, "global_step": 589674, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.028167486190796, "global_step": 589675, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.05411696434021, "global_step": 589676, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0327887535095215, "global_step": 589677, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1088149547576904, "global_step": 589678, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0512962341308594, "global_step": 589679, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9518955945968628, "global_step": 589680, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9823873043060303, "global_step": 589681, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9894442558288574, "global_step": 589682, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.102095603942871, "global_step": 589683, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0581443309783936, "global_step": 589684, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0042595863342285, "global_step": 589685, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9812389612197876, "global_step": 589686, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0140531063079834, "global_step": 589687, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9429527521133423, "global_step": 589688, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.017561674118042, "global_step": 589689, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9966042041778564, "global_step": 589690, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0458004474639893, "global_step": 589691, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.982892394065857, "global_step": 589692, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.998569130897522, "global_step": 589693, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0941245555877686, "global_step": 589694, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0893032550811768, "global_step": 589695, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.031018018722534, "global_step": 589696, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0853850841522217, "global_step": 589697, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.104182481765747, "global_step": 589698, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9673718214035034, "global_step": 589699, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.049442768096924, "global_step": 589700, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0247409343719482, "global_step": 589701, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.055494546890259, "global_step": 589702, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.8963062763214111, "global_step": 589703, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0232415199279785, "global_step": 589704, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1141645908355713, "global_step": 589705, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0423550605773926, "global_step": 589706, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0326499938964844, "global_step": 589707, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0030272006988525, "global_step": 589708, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9962830543518066, "global_step": 589709, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0097460746765137, "global_step": 589710, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0255067348480225, "global_step": 589711, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0933127403259277, "global_step": 589712, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9884331226348877, "global_step": 589713, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0112991333007812, "global_step": 589714, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9595433473587036, "global_step": 589715, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0426127910614014, "global_step": 589716, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0249404907226562, "global_step": 589717, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9837990999221802, "global_step": 589718, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0137269496917725, "global_step": 589719, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9654849767684937, "global_step": 589720, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9750961065292358, "global_step": 589721, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9897775650024414, "global_step": 589722, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9559746980667114, "global_step": 589723, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0196382999420166, "global_step": 589724, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.03391432762146, "global_step": 589725, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9658699035644531, "global_step": 589726, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.079315423965454, "global_step": 589727, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0006701946258545, "global_step": 589728, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0422091484069824, "global_step": 589729, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.998020052909851, "global_step": 589730, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.054352283477783, "global_step": 589731, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.057347059249878, "global_step": 589732, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0531599521636963, "global_step": 589733, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0552003383636475, "global_step": 589734, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.8843852281570435, "global_step": 589735, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.020098924636841, "global_step": 589736, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.012493133544922, "global_step": 589737, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.059720039367676, "global_step": 589738, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0104572772979736, "global_step": 589739, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.013460397720337, "global_step": 589740, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9941116571426392, "global_step": 589741, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.058676242828369, "global_step": 589742, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9530158042907715, "global_step": 589743, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0582473278045654, "global_step": 589744, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0900635719299316, "global_step": 589745, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.014263391494751, "global_step": 589746, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0263636112213135, "global_step": 589747, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9798706769943237, "global_step": 589748, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0602047443389893, "global_step": 589749, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.083961248397827, "global_step": 589750, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9482028484344482, "global_step": 589751, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.026020050048828, "global_step": 589752, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9664335250854492, "global_step": 589753, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0305516719818115, "global_step": 589754, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9670383930206299, "global_step": 589755, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.994322657585144, "global_step": 589756, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0288538932800293, "global_step": 589757, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.009732246398926, "global_step": 589758, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.973029375076294, "global_step": 589759, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0370090007781982, "global_step": 589760, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9725579023361206, "global_step": 589761, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.094707489013672, "global_step": 589762, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9522919654846191, "global_step": 589763, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.038250207901001, "global_step": 589764, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.033564567565918, "global_step": 589765, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0394160747528076, "global_step": 589766, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0111069679260254, "global_step": 589767, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.022451877593994, "global_step": 589768, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9269235134124756, "global_step": 589769, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.024980306625366, "global_step": 589770, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0160577297210693, "global_step": 589771, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.104522943496704, "global_step": 589772, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0713682174682617, "global_step": 589773, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9776499271392822, "global_step": 589774, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0126712322235107, "global_step": 589775, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.946466326713562, "global_step": 589776, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.999720811843872, "global_step": 589777, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9628779888153076, "global_step": 589778, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.975435733795166, "global_step": 589779, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9670876264572144, "global_step": 589780, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0290277004241943, "global_step": 589781, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.062915802001953, "global_step": 589782, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.977229356765747, "global_step": 589783, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0895164012908936, "global_step": 589784, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9967495203018188, "global_step": 589785, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.010286331176758, "global_step": 589786, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.037529945373535, "global_step": 589787, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.079908847808838, "global_step": 589788, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0754148960113525, "global_step": 589789, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.059899091720581, "global_step": 589790, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9686042070388794, "global_step": 589791, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.030597686767578, "global_step": 589792, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.078655958175659, "global_step": 589793, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9303040504455566, "global_step": 589794, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.031250238418579, "global_step": 589795, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0613350868225098, "global_step": 589796, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0013678073883057, "global_step": 589797, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0140228271484375, "global_step": 589798, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9720737934112549, "global_step": 589799, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.036334753036499, "global_step": 589800, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0527596473693848, "global_step": 589801, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0682597160339355, "global_step": 589802, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9264100790023804, "global_step": 589803, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9228769540786743, "global_step": 589804, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0885393619537354, "global_step": 589805, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0011446475982666, "global_step": 589806, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0919547080993652, "global_step": 589807, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.017380714416504, "global_step": 589808, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.00899076461792, "global_step": 589809, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0945234298706055, "global_step": 589810, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0578129291534424, "global_step": 589811, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.999830722808838, "global_step": 589812, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.007474422454834, "global_step": 589813, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9780274629592896, "global_step": 589814, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9522539377212524, "global_step": 589815, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9561505317687988, "global_step": 589816, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.987747311592102, "global_step": 589817, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0750348567962646, "global_step": 589818, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9812883138656616, "global_step": 589819, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9932559728622437, "global_step": 589820, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9893535375595093, "global_step": 589821, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.048757553100586, "global_step": 589822, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9910963773727417, "global_step": 589823, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0212278366088867, "global_step": 589824, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9723793268203735, "global_step": 589825, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.077892780303955, "global_step": 589826, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9733251333236694, "global_step": 589827, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9228920936584473, "global_step": 589828, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.014564275741577, "global_step": 589829, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9731285572052002, "global_step": 589830, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.946879506111145, "global_step": 589831, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0450518131256104, "global_step": 589832, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9874376058578491, "global_step": 589833, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9950993061065674, "global_step": 589834, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9749517440795898, "global_step": 589835, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.036005973815918, "global_step": 589836, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9407283067703247, "global_step": 589837, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0330727100372314, "global_step": 589838, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.041576862335205, "global_step": 589839, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0779805183410645, "global_step": 589840, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.050441265106201, "global_step": 589841, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0627810955047607, "global_step": 589842, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.992990255355835, "global_step": 589843, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.012665271759033, "global_step": 589844, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0281810760498047, "global_step": 589845, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0122222900390625, "global_step": 589846, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0615530014038086, "global_step": 589847, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9916433095932007, "global_step": 589848, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9677060842514038, "global_step": 589849, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.056514263153076, "global_step": 589850, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0483996868133545, "global_step": 589851, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9953978061676025, "global_step": 589852, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.01196551322937, "global_step": 589853, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9989407062530518, "global_step": 589854, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0463244915008545, "global_step": 589855, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0016047954559326, "global_step": 589856, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9809541702270508, "global_step": 589857, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0582802295684814, "global_step": 589858, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.026989698410034, "global_step": 589859, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9790929555892944, "global_step": 589860, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1175243854522705, "global_step": 589861, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9629336595535278, "global_step": 589862, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0797903537750244, "global_step": 589863, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.047858476638794, "global_step": 589864, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0453898906707764, "global_step": 589865, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9161683320999146, "global_step": 589866, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9968817234039307, "global_step": 589867, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0885796546936035, "global_step": 589868, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.030447006225586, "global_step": 589869, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9830302000045776, "global_step": 589870, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.062145233154297, "global_step": 589871, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9759713411331177, "global_step": 589872, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9867093563079834, "global_step": 589873, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0543482303619385, "global_step": 589874, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0015525817871094, "global_step": 589875, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9399060010910034, "global_step": 589876, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9768410921096802, "global_step": 589877, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.060492992401123, "global_step": 589878, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9743359088897705, "global_step": 589879, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.042125940322876, "global_step": 589880, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1149587631225586, "global_step": 589881, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1280524730682373, "global_step": 589882, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0098044872283936, "global_step": 589883, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.095273494720459, "global_step": 589884, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.066434860229492, "global_step": 589885, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.046416759490967, "global_step": 589886, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0156219005584717, "global_step": 589887, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.017735004425049, "global_step": 589888, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.043623447418213, "global_step": 589889, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.020106077194214, "global_step": 589890, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9934706687927246, "global_step": 589891, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0474629402160645, "global_step": 589892, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9784866571426392, "global_step": 589893, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9980965852737427, "global_step": 589894, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9630753993988037, "global_step": 589895, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0421786308288574, "global_step": 589896, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9971981048583984, "global_step": 589897, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0033457279205322, "global_step": 589898, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0346522331237793, "global_step": 589899, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9592334032058716, "global_step": 589900, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.013777017593384, "global_step": 589901, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0151236057281494, "global_step": 589902, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.028723955154419, "global_step": 589903, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0119881629943848, "global_step": 589904, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0289692878723145, "global_step": 589905, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.09774112701416, "global_step": 589906, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1191482543945312, "global_step": 589907, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0231034755706787, "global_step": 589908, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0329675674438477, "global_step": 589909, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.106269121170044, "global_step": 589910, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.101919651031494, "global_step": 589911, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9573285579681396, "global_step": 589912, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0497233867645264, "global_step": 589913, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9453948736190796, "global_step": 589914, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9886244535446167, "global_step": 589915, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.036898374557495, "global_step": 589916, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.940995454788208, "global_step": 589917, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9525930881500244, "global_step": 589918, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9800341129302979, "global_step": 589919, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9809021949768066, "global_step": 589920, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9762533903121948, "global_step": 589921, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9478951692581177, "global_step": 589922, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9748473167419434, "global_step": 589923, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.097660779953003, "global_step": 589924, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.092747211456299, "global_step": 589925, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.006288528442383, "global_step": 589926, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0803892612457275, "global_step": 589927, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.988824725151062, "global_step": 589928, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.980790615081787, "global_step": 589929, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9786497354507446, "global_step": 589930, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0331878662109375, "global_step": 589931, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0178866386413574, "global_step": 589932, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.022198438644409, "global_step": 589933, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9384876489639282, "global_step": 589934, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.030205726623535, "global_step": 589935, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0647592544555664, "global_step": 589936, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9918230772018433, "global_step": 589937, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.994030475616455, "global_step": 589938, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9683029651641846, "global_step": 589939, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0556201934814453, "global_step": 589940, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9700772762298584, "global_step": 589941, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.096379518508911, "global_step": 589942, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9881742000579834, "global_step": 589943, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0081918239593506, "global_step": 589944, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1494452953338623, "global_step": 589945, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0963454246520996, "global_step": 589946, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0540874004364014, "global_step": 589947, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0131728649139404, "global_step": 589948, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0450048446655273, "global_step": 589949, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0898778438568115, "global_step": 589950, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9771660566329956, "global_step": 589951, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9869462251663208, "global_step": 589952, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.03206729888916, "global_step": 589953, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9000729322433472, "global_step": 589954, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0386433601379395, "global_step": 589955, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.968876838684082, "global_step": 589956, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.087911367416382, "global_step": 589957, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0681753158569336, "global_step": 589958, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0051257610321045, "global_step": 589959, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0237603187561035, "global_step": 589960, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9951014518737793, "global_step": 589961, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0077197551727295, "global_step": 589962, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.006802797317505, "global_step": 589963, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9559614658355713, "global_step": 589964, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0817904472351074, "global_step": 589965, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0608584880828857, "global_step": 589966, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0743954181671143, "global_step": 589967, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9803619384765625, "global_step": 589968, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0236024856567383, "global_step": 589969, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1475799083709717, "global_step": 589970, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0056958198547363, "global_step": 589971, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.019937753677368, "global_step": 589972, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0403590202331543, "global_step": 589973, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9938225746154785, "global_step": 589974, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.984717845916748, "global_step": 589975, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.045546531677246, "global_step": 589976, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.03328800201416, "global_step": 589977, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.976654052734375, "global_step": 589978, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.071730136871338, "global_step": 589979, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9243659973144531, "global_step": 589980, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9567192792892456, "global_step": 589981, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.085573673248291, "global_step": 589982, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9630837440490723, "global_step": 589983, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.095521926879883, "global_step": 589984, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0458555221557617, "global_step": 589985, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0369348526000977, "global_step": 589986, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0735366344451904, "global_step": 589987, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.006312608718872, "global_step": 589988, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0083506107330322, "global_step": 589989, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0570247173309326, "global_step": 589990, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.979042410850525, "global_step": 589991, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.094905376434326, "global_step": 589992, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.065767288208008, "global_step": 589993, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.117800235748291, "global_step": 589994, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0944430828094482, "global_step": 589995, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.004563570022583, "global_step": 589996, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9674493074417114, "global_step": 589997, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.961224913597107, "global_step": 589998, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0772604942321777, "global_step": 589999, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9361217021942139, "global_step": 590000, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0142126083374023, "global_step": 590001, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0296056270599365, "global_step": 590002, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.004612445831299, "global_step": 590003, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0140254497528076, "global_step": 590004, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9877781867980957, "global_step": 590005, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.942673921585083, "global_step": 590006, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9710909128189087, "global_step": 590007, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.949971318244934, "global_step": 590008, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.019843101501465, "global_step": 590009, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.06567120552063, "global_step": 590010, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0211880207061768, "global_step": 590011, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0486764907836914, "global_step": 590012, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0534749031066895, "global_step": 590013, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9811718463897705, "global_step": 590014, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.027831792831421, "global_step": 590015, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.976864218711853, "global_step": 590016, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0630428791046143, "global_step": 590017, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.055372953414917, "global_step": 590018, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.029893636703491, "global_step": 590019, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.049295425415039, "global_step": 590020, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0702462196350098, "global_step": 590021, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.042819023132324, "global_step": 590022, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.06813907623291, "global_step": 590023, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.982328176498413, "global_step": 590024, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0678904056549072, "global_step": 590025, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.013906240463257, "global_step": 590026, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0923912525177, "global_step": 590027, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9521509408950806, "global_step": 590028, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9941450357437134, "global_step": 590029, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0442988872528076, "global_step": 590030, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.041248083114624, "global_step": 590031, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.03997802734375, "global_step": 590032, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.965935468673706, "global_step": 590033, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.026540756225586, "global_step": 590034, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0277583599090576, "global_step": 590035, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9798855781555176, "global_step": 590036, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.024341583251953, "global_step": 590037, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0340824127197266, "global_step": 590038, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9887769222259521, "global_step": 590039, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0252368450164795, "global_step": 590040, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.090380907058716, "global_step": 590041, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.019402265548706, "global_step": 590042, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.03993821144104, "global_step": 590043, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.041466236114502, "global_step": 590044, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.032597541809082, "global_step": 590045, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.016993522644043, "global_step": 590046, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.038360118865967, "global_step": 590047, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0254251956939697, "global_step": 590048, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.932551383972168, "global_step": 590049, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9816874265670776, "global_step": 590050, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9824262857437134, "global_step": 590051, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.080388307571411, "global_step": 590052, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0634560585021973, "global_step": 590053, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0277786254882812, "global_step": 590054, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9915114641189575, "global_step": 590055, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.072667121887207, "global_step": 590056, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9433714151382446, "global_step": 590057, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9649291038513184, "global_step": 590058, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.019115924835205, "global_step": 590059, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0263280868530273, "global_step": 590060, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9141178131103516, "global_step": 590061, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0254313945770264, "global_step": 590062, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0842177867889404, "global_step": 590063, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0284042358398438, "global_step": 590064, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.043792963027954, "global_step": 590065, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0604207515716553, "global_step": 590066, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0258383750915527, "global_step": 590067, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.052966833114624, "global_step": 590068, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0620954036712646, "global_step": 590069, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.972870945930481, "global_step": 590070, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9972137212753296, "global_step": 590071, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.023139238357544, "global_step": 590072, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0540244579315186, "global_step": 590073, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9192599058151245, "global_step": 590074, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9974945783615112, "global_step": 590075, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0485856533050537, "global_step": 590076, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9675803184509277, "global_step": 590077, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0256741046905518, "global_step": 590078, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9680942296981812, "global_step": 590079, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9871070384979248, "global_step": 590080, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0162482261657715, "global_step": 590081, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9872974157333374, "global_step": 590082, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9801117181777954, "global_step": 590083, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.983157992362976, "global_step": 590084, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0292789936065674, "global_step": 590085, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.051738977432251, "global_step": 590086, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0060842037200928, "global_step": 590087, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0601418018341064, "global_step": 590088, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9215211868286133, "global_step": 590089, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0553178787231445, "global_step": 590090, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9926198720932007, "global_step": 590091, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0789122581481934, "global_step": 590092, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.001737594604492, "global_step": 590093, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.003286123275757, "global_step": 590094, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9967670440673828, "global_step": 590095, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.047024965286255, "global_step": 590096, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.037228584289551, "global_step": 590097, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.040282726287842, "global_step": 590098, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.032224655151367, "global_step": 590099, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0170395374298096, "global_step": 590100, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.030313491821289, "global_step": 590101, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.130404472351074, "global_step": 590102, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1036221981048584, "global_step": 590103, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9134976863861084, "global_step": 590104, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9417730569839478, "global_step": 590105, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0106425285339355, "global_step": 590106, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.8891395330429077, "global_step": 590107, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.005772590637207, "global_step": 590108, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.104809522628784, "global_step": 590109, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0157225131988525, "global_step": 590110, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.032090663909912, "global_step": 590111, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9480431079864502, "global_step": 590112, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0212035179138184, "global_step": 590113, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.003849506378174, "global_step": 590114, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.034795045852661, "global_step": 590115, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.003171682357788, "global_step": 590116, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9901387691497803, "global_step": 590117, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0876011848449707, "global_step": 590118, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0056726932525635, "global_step": 590119, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9949942827224731, "global_step": 590120, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.14762020111084, "global_step": 590121, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0970098972320557, "global_step": 590122, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9204338788986206, "global_step": 590123, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0830228328704834, "global_step": 590124, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.087455987930298, "global_step": 590125, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0923187732696533, "global_step": 590126, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.053971290588379, "global_step": 590127, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0059688091278076, "global_step": 590128, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.998687744140625, "global_step": 590129, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0347740650177, "global_step": 590130, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0422325134277344, "global_step": 590131, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9782650470733643, "global_step": 590132, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.068547487258911, "global_step": 590133, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.027416467666626, "global_step": 590134, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.8902353048324585, "global_step": 590135, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0367002487182617, "global_step": 590136, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9675794839859009, "global_step": 590137, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.147305488586426, "global_step": 590138, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.008317708969116, "global_step": 590139, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.064138174057007, "global_step": 590140, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0264089107513428, "global_step": 590141, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0038015842437744, "global_step": 590142, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9551960229873657, "global_step": 590143, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9692134857177734, "global_step": 590144, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9866538047790527, "global_step": 590145, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0746970176696777, "global_step": 590146, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9369279146194458, "global_step": 590147, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.000370502471924, "global_step": 590148, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0409975051879883, "global_step": 590149, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9466784000396729, "global_step": 590150, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9966003894805908, "global_step": 590151, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.003933906555176, "global_step": 590152, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.067707061767578, "global_step": 590153, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.061414957046509, "global_step": 590154, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.004225492477417, "global_step": 590155, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.993262529373169, "global_step": 590156, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.040949821472168, "global_step": 590157, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.975823998451233, "global_step": 590158, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1138415336608887, "global_step": 590159, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0345258712768555, "global_step": 590160, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0565648078918457, "global_step": 590161, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0654547214508057, "global_step": 590162, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0329887866973877, "global_step": 590163, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0670292377471924, "global_step": 590164, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9754747152328491, "global_step": 590165, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.065931797027588, "global_step": 590166, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0106253623962402, "global_step": 590167, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0005412101745605, "global_step": 590168, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0276331901550293, "global_step": 590169, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0716586112976074, "global_step": 590170, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.060962438583374, "global_step": 590171, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0248923301696777, "global_step": 590172, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0351812839508057, "global_step": 590173, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.945906639099121, "global_step": 590174, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.031130075454712, "global_step": 590175, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0863656997680664, "global_step": 590176, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.8428447246551514, "global_step": 590177, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0491926670074463, "global_step": 590178, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9992984533309937, "global_step": 590179, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.052302598953247, "global_step": 590180, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0597496032714844, "global_step": 590181, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9870216846466064, "global_step": 590182, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0475223064422607, "global_step": 590183, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0228068828582764, "global_step": 590184, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9423545598983765, "global_step": 590185, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.037741184234619, "global_step": 590186, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9614678621292114, "global_step": 590187, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9945933818817139, "global_step": 590188, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.033129930496216, "global_step": 590189, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0437653064727783, "global_step": 590190, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0761210918426514, "global_step": 590191, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9397783279418945, "global_step": 590192, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.037376880645752, "global_step": 590193, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.071789503097534, "global_step": 590194, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.03049635887146, "global_step": 590195, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9691119194030762, "global_step": 590196, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9867311716079712, "global_step": 590197, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9360839128494263, "global_step": 590198, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0564584732055664, "global_step": 590199, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9876042604446411, "global_step": 590200, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.008352279663086, "global_step": 590201, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0726892948150635, "global_step": 590202, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0205538272857666, "global_step": 590203, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.019324541091919, "global_step": 590204, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0029759407043457, "global_step": 590205, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9967557191848755, "global_step": 590206, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.999770998954773, "global_step": 590207, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0210041999816895, "global_step": 590208, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1064229011535645, "global_step": 590209, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0058205127716064, "global_step": 590210, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.015774726867676, "global_step": 590211, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9401150941848755, "global_step": 590212, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.054171085357666, "global_step": 590213, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.037416458129883, "global_step": 590214, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9579942226409912, "global_step": 590215, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9790887832641602, "global_step": 590216, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9968116283416748, "global_step": 590217, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9908758401870728, "global_step": 590218, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0071358680725098, "global_step": 590219, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0088796615600586, "global_step": 590220, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.043454885482788, "global_step": 590221, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0670459270477295, "global_step": 590222, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0802042484283447, "global_step": 590223, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.027216672897339, "global_step": 590224, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9420170783996582, "global_step": 590225, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9962043762207031, "global_step": 590226, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0303759574890137, "global_step": 590227, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0748841762542725, "global_step": 590228, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0246174335479736, "global_step": 590229, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0205469131469727, "global_step": 590230, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9628430604934692, "global_step": 590231, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9413930177688599, "global_step": 590232, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0069282054901123, "global_step": 590233, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9983344078063965, "global_step": 590234, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0104169845581055, "global_step": 590235, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1067302227020264, "global_step": 590236, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9773272275924683, "global_step": 590237, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0246992111206055, "global_step": 590238, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0369949340820312, "global_step": 590239, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.1504387855529785, "global_step": 590240, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.044633388519287, "global_step": 590241, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.03279972076416, "global_step": 590242, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0023651123046875, "global_step": 590243, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9507368803024292, "global_step": 590244, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0355894565582275, "global_step": 590245, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0243008136749268, "global_step": 590246, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.021937608718872, "global_step": 590247, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9903417825698853, "global_step": 590248, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0095884799957275, "global_step": 590249, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.088097095489502, "global_step": 590250, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.081897020339966, "global_step": 590251, "epoch": 958, "lr": 5e-05}
{"train_loss": 1.9920711517333984, "global_step": 590252, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.017815351486206, "global_step": 590253, "epoch": 958, "lr": 5e-05}
{"train_loss": 2.0289857387542725, "global_step": 590254, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0518405437469482, "global_step": 590255, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9174208641052246, "global_step": 590256, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9460604190826416, "global_step": 590257, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0107266902923584, "global_step": 590258, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0021181106567383, "global_step": 590259, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0027835369110107, "global_step": 590260, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.999051809310913, "global_step": 590261, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9508419036865234, "global_step": 590262, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9953317642211914, "global_step": 590263, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0061872005462646, "global_step": 590264, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.055356740951538, "global_step": 590265, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0607192516326904, "global_step": 590266, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9412438869476318, "global_step": 590267, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.037788152694702, "global_step": 590268, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.014408588409424, "global_step": 590269, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.040060043334961, "global_step": 590270, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9735524654388428, "global_step": 590271, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9763973951339722, "global_step": 590272, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.974875807762146, "global_step": 590273, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0498154163360596, "global_step": 590274, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.934830665588379, "global_step": 590275, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0162506103515625, "global_step": 590276, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.990832805633545, "global_step": 590277, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0235695838928223, "global_step": 590278, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.989140272140503, "global_step": 590279, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.001957654953003, "global_step": 590280, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9267634153366089, "global_step": 590281, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0293962955474854, "global_step": 590282, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.083667516708374, "global_step": 590283, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.976906657218933, "global_step": 590284, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.046100378036499, "global_step": 590285, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.040292263031006, "global_step": 590286, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9889075756072998, "global_step": 590287, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.8885750770568848, "global_step": 590288, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9714910984039307, "global_step": 590289, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9536460638046265, "global_step": 590290, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.8957353830337524, "global_step": 590291, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9747270345687866, "global_step": 590292, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.004013776779175, "global_step": 590293, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9967541694641113, "global_step": 590294, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9599120616912842, "global_step": 590295, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0784544944763184, "global_step": 590296, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9697848558425903, "global_step": 590297, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9802944660186768, "global_step": 590298, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9573397636413574, "global_step": 590299, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0198192596435547, "global_step": 590300, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9984759092330933, "global_step": 590301, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0186915397644043, "global_step": 590302, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0667061805725098, "global_step": 590303, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.087657928466797, "global_step": 590304, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1086390018463135, "global_step": 590305, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9899612665176392, "global_step": 590306, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0352866649627686, "global_step": 590307, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0317413806915283, "global_step": 590308, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.10863995552063, "global_step": 590309, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9789584875106812, "global_step": 590310, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9902689456939697, "global_step": 590311, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.021589994430542, "global_step": 590312, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0723817348480225, "global_step": 590313, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.011146306991577, "global_step": 590314, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.020202875137329, "global_step": 590315, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.00705885887146, "global_step": 590316, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9947081804275513, "global_step": 590317, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.04882550239563, "global_step": 590318, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9231568574905396, "global_step": 590319, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9098612070083618, "global_step": 590320, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0202548503875732, "global_step": 590321, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.014751434326172, "global_step": 590322, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0299246311187744, "global_step": 590323, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9662975072860718, "global_step": 590324, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.019629955291748, "global_step": 590325, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0286192893981934, "global_step": 590326, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9934271574020386, "global_step": 590327, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9879491329193115, "global_step": 590328, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.989905595779419, "global_step": 590329, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9920045137405396, "global_step": 590330, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0435874462127686, "global_step": 590331, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9807323217391968, "global_step": 590332, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.03129243850708, "global_step": 590333, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0297913551330566, "global_step": 590334, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9726982116699219, "global_step": 590335, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0566060543060303, "global_step": 590336, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9519261121749878, "global_step": 590337, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.011164426803589, "global_step": 590338, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.024101495742798, "global_step": 590339, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9851970672607422, "global_step": 590340, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0052685737609863, "global_step": 590341, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.003922939300537, "global_step": 590342, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.973239541053772, "global_step": 590343, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.036050319671631, "global_step": 590344, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9790724515914917, "global_step": 590345, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0560691356658936, "global_step": 590346, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0762128829956055, "global_step": 590347, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9939889907836914, "global_step": 590348, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0538058280944824, "global_step": 590349, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.061558246612549, "global_step": 590350, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0705924034118652, "global_step": 590351, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0769429206848145, "global_step": 590352, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9950577020645142, "global_step": 590353, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.044971466064453, "global_step": 590354, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0443994998931885, "global_step": 590355, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0375053882598877, "global_step": 590356, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.010268211364746, "global_step": 590357, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0024988651275635, "global_step": 590358, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0574326515197754, "global_step": 590359, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9813588857650757, "global_step": 590360, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9603737592697144, "global_step": 590361, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9821503162384033, "global_step": 590362, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.022329092025757, "global_step": 590363, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0220534801483154, "global_step": 590364, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.092416286468506, "global_step": 590365, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.03367280960083, "global_step": 590366, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.101168632507324, "global_step": 590367, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.986930251121521, "global_step": 590368, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.020312547683716, "global_step": 590369, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0602550506591797, "global_step": 590370, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0141708850860596, "global_step": 590371, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9400758743286133, "global_step": 590372, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.998188853263855, "global_step": 590373, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0966014862060547, "global_step": 590374, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9885181188583374, "global_step": 590375, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9882704019546509, "global_step": 590376, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.036837100982666, "global_step": 590377, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.033425807952881, "global_step": 590378, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0141372680664062, "global_step": 590379, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9661577939987183, "global_step": 590380, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.012240171432495, "global_step": 590381, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0619430541992188, "global_step": 590382, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0057690143585205, "global_step": 590383, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9934192895889282, "global_step": 590384, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1497061252593994, "global_step": 590385, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9772719144821167, "global_step": 590386, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0924863815307617, "global_step": 590387, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.009044647216797, "global_step": 590388, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.042573928833008, "global_step": 590389, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0423080921173096, "global_step": 590390, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.063218116760254, "global_step": 590391, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.074453353881836, "global_step": 590392, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0484182834625244, "global_step": 590393, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9205641746520996, "global_step": 590394, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0535709857940674, "global_step": 590395, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9938478469848633, "global_step": 590396, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9685747623443604, "global_step": 590397, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9481347799301147, "global_step": 590398, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9223370552062988, "global_step": 590399, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0649383068084717, "global_step": 590400, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9699301719665527, "global_step": 590401, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0361266136169434, "global_step": 590402, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0189273357391357, "global_step": 590403, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9846980571746826, "global_step": 590404, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0097246170043945, "global_step": 590405, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9486991167068481, "global_step": 590406, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0713846683502197, "global_step": 590407, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.074760913848877, "global_step": 590408, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.962767243385315, "global_step": 590409, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.964021921157837, "global_step": 590410, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0357165336608887, "global_step": 590411, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9940826892852783, "global_step": 590412, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9776182174682617, "global_step": 590413, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9660587310791016, "global_step": 590414, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9816150665283203, "global_step": 590415, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1349575519561768, "global_step": 590416, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0075836181640625, "global_step": 590417, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0498404502868652, "global_step": 590418, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0825514793395996, "global_step": 590419, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0259079933166504, "global_step": 590420, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.968644618988037, "global_step": 590421, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0235562324523926, "global_step": 590422, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.003209114074707, "global_step": 590423, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9886908531188965, "global_step": 590424, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.013310670852661, "global_step": 590425, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9680472612380981, "global_step": 590426, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9464726448059082, "global_step": 590427, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0246872901916504, "global_step": 590428, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.009861707687378, "global_step": 590429, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0047125816345215, "global_step": 590430, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0297303199768066, "global_step": 590431, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0274882316589355, "global_step": 590432, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.046444892883301, "global_step": 590433, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0355021953582764, "global_step": 590434, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9552136659622192, "global_step": 590435, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.005884885787964, "global_step": 590436, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9754323959350586, "global_step": 590437, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9138540029525757, "global_step": 590438, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9335178136825562, "global_step": 590439, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.988071084022522, "global_step": 590440, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.052424430847168, "global_step": 590441, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.04960560798645, "global_step": 590442, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9570211172103882, "global_step": 590443, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.030749559402466, "global_step": 590444, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.009855270385742, "global_step": 590445, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.05234432220459, "global_step": 590446, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.01469349861145, "global_step": 590447, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0445120334625244, "global_step": 590448, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0835232734680176, "global_step": 590449, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.06939959526062, "global_step": 590450, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0596461296081543, "global_step": 590451, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0509166717529297, "global_step": 590452, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.034628391265869, "global_step": 590453, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0813992023468018, "global_step": 590454, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0566177368164062, "global_step": 590455, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0288212299346924, "global_step": 590456, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.023761510848999, "global_step": 590457, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0245370864868164, "global_step": 590458, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0115854740142822, "global_step": 590459, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.082685708999634, "global_step": 590460, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0919058322906494, "global_step": 590461, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.01188325881958, "global_step": 590462, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0614302158355713, "global_step": 590463, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0655181407928467, "global_step": 590464, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9828009605407715, "global_step": 590465, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0149762630462646, "global_step": 590466, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9966378211975098, "global_step": 590467, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.033592700958252, "global_step": 590468, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9746023416519165, "global_step": 590469, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0369200706481934, "global_step": 590470, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.112177848815918, "global_step": 590471, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0673327445983887, "global_step": 590472, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.899348258972168, "global_step": 590473, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9965239763259888, "global_step": 590474, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.947217345237732, "global_step": 590475, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.100583076477051, "global_step": 590476, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.069460868835449, "global_step": 590477, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9893085956573486, "global_step": 590478, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.938615083694458, "global_step": 590479, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9269760847091675, "global_step": 590480, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9607300758361816, "global_step": 590481, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9972615242004395, "global_step": 590482, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9804571866989136, "global_step": 590483, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.991599678993225, "global_step": 590484, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9236606359481812, "global_step": 590485, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9844145774841309, "global_step": 590486, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9795968532562256, "global_step": 590487, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0168943405151367, "global_step": 590488, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9327869415283203, "global_step": 590489, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0748496055603027, "global_step": 590490, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.067366361618042, "global_step": 590491, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0406670570373535, "global_step": 590492, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9911378622055054, "global_step": 590493, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0005109310150146, "global_step": 590494, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.015897035598755, "global_step": 590495, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0635933876037598, "global_step": 590496, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.029350757598877, "global_step": 590497, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9831712245941162, "global_step": 590498, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0922975540161133, "global_step": 590499, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9913947582244873, "global_step": 590500, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0873653888702393, "global_step": 590501, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9196968078613281, "global_step": 590502, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.031172275543213, "global_step": 590503, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0450549125671387, "global_step": 590504, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.090538740158081, "global_step": 590505, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1161065101623535, "global_step": 590506, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.018392324447632, "global_step": 590507, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9995453357696533, "global_step": 590508, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9932245016098022, "global_step": 590509, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9485383033752441, "global_step": 590510, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.022024393081665, "global_step": 590511, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9719338417053223, "global_step": 590512, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0114669799804688, "global_step": 590513, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9890341758728027, "global_step": 590514, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.997194766998291, "global_step": 590515, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.972925066947937, "global_step": 590516, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9426580667495728, "global_step": 590517, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9957541227340698, "global_step": 590518, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9969193935394287, "global_step": 590519, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9916026592254639, "global_step": 590520, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0456488132476807, "global_step": 590521, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0354726314544678, "global_step": 590522, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9868346452713013, "global_step": 590523, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.023913860321045, "global_step": 590524, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9720048904418945, "global_step": 590525, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.053114891052246, "global_step": 590526, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0002689361572266, "global_step": 590527, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0560286045074463, "global_step": 590528, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9578831195831299, "global_step": 590529, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.004181146621704, "global_step": 590530, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0457746982574463, "global_step": 590531, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9394268989562988, "global_step": 590532, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0146121978759766, "global_step": 590533, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0077052116394043, "global_step": 590534, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.909533977508545, "global_step": 590535, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.075639486312866, "global_step": 590536, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9400898218154907, "global_step": 590537, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9907081127166748, "global_step": 590538, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.958074927330017, "global_step": 590539, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.042743682861328, "global_step": 590540, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9486737251281738, "global_step": 590541, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.025141477584839, "global_step": 590542, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.038703203201294, "global_step": 590543, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.056006908416748, "global_step": 590544, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9359456300735474, "global_step": 590545, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0275728702545166, "global_step": 590546, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.015897274017334, "global_step": 590547, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.977042317390442, "global_step": 590548, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.109384775161743, "global_step": 590549, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0089917182922363, "global_step": 590550, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0781683921813965, "global_step": 590551, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0150177478790283, "global_step": 590552, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9985400438308716, "global_step": 590553, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0530903339385986, "global_step": 590554, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9812620878219604, "global_step": 590555, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9903644323349, "global_step": 590556, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0334765911102295, "global_step": 590557, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.130350112915039, "global_step": 590558, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9981988668441772, "global_step": 590559, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0487754344940186, "global_step": 590560, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9977781772613525, "global_step": 590561, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.028310775756836, "global_step": 590562, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9420801401138306, "global_step": 590563, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.042461633682251, "global_step": 590564, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0557124614715576, "global_step": 590565, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.037386655807495, "global_step": 590566, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0464656352996826, "global_step": 590567, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0399813652038574, "global_step": 590568, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9448310136795044, "global_step": 590569, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9412139654159546, "global_step": 590570, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0035929679870605, "global_step": 590571, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9882116317749023, "global_step": 590572, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0672049522399902, "global_step": 590573, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.018502712249756, "global_step": 590574, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9177320003509521, "global_step": 590575, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0443625450134277, "global_step": 590576, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.955443263053894, "global_step": 590577, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.96198570728302, "global_step": 590578, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9330577850341797, "global_step": 590579, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9709489345550537, "global_step": 590580, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0368547439575195, "global_step": 590581, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.8718211650848389, "global_step": 590582, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9830107688903809, "global_step": 590583, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9893625974655151, "global_step": 590584, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.936994194984436, "global_step": 590585, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.08839750289917, "global_step": 590586, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.023101806640625, "global_step": 590587, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9879294633865356, "global_step": 590588, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0453832149505615, "global_step": 590589, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0920519828796387, "global_step": 590590, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.023662567138672, "global_step": 590591, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.035618305206299, "global_step": 590592, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9858195781707764, "global_step": 590593, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0338964462280273, "global_step": 590594, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.937106966972351, "global_step": 590595, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9905189275741577, "global_step": 590596, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.027254819869995, "global_step": 590597, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0252737998962402, "global_step": 590598, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0092568397521973, "global_step": 590599, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9527547359466553, "global_step": 590600, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9948004484176636, "global_step": 590601, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0173096656799316, "global_step": 590602, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.8955062627792358, "global_step": 590603, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.001258373260498, "global_step": 590604, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9707181453704834, "global_step": 590605, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.938667893409729, "global_step": 590606, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9907666444778442, "global_step": 590607, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1488304138183594, "global_step": 590608, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0065951347351074, "global_step": 590609, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0010650157928467, "global_step": 590610, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.024348020553589, "global_step": 590611, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.117176055908203, "global_step": 590612, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9922462701797485, "global_step": 590613, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.059713840484619, "global_step": 590614, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0211124420166016, "global_step": 590615, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9836747646331787, "global_step": 590616, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9393763542175293, "global_step": 590617, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9591082334518433, "global_step": 590618, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0676584243774414, "global_step": 590619, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9902057647705078, "global_step": 590620, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9645836353302002, "global_step": 590621, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9690226316452026, "global_step": 590622, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9921274185180664, "global_step": 590623, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0831329822540283, "global_step": 590624, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.017791509628296, "global_step": 590625, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.074463367462158, "global_step": 590626, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0384700298309326, "global_step": 590627, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0246100425720215, "global_step": 590628, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.060486078262329, "global_step": 590629, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0595808029174805, "global_step": 590630, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.968056559562683, "global_step": 590631, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0348289012908936, "global_step": 590632, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9896470308303833, "global_step": 590633, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.053509473800659, "global_step": 590634, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9458372592926025, "global_step": 590635, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0388033390045166, "global_step": 590636, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0452582836151123, "global_step": 590637, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.994902491569519, "global_step": 590638, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0317282676696777, "global_step": 590639, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0510311126708984, "global_step": 590640, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0560009479522705, "global_step": 590641, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9865732192993164, "global_step": 590642, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.020587682723999, "global_step": 590643, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9932867288589478, "global_step": 590644, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.058055877685547, "global_step": 590645, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9398972988128662, "global_step": 590646, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9626230001449585, "global_step": 590647, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9630794525146484, "global_step": 590648, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9934221506118774, "global_step": 590649, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.088665246963501, "global_step": 590650, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.041172742843628, "global_step": 590651, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.046478748321533, "global_step": 590652, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.958303689956665, "global_step": 590653, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0285003185272217, "global_step": 590654, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0360424518585205, "global_step": 590655, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9642173051834106, "global_step": 590656, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.038278102874756, "global_step": 590657, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0306265354156494, "global_step": 590658, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0149998664855957, "global_step": 590659, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0569441318511963, "global_step": 590660, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.066812515258789, "global_step": 590661, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9690955877304077, "global_step": 590662, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9987348318099976, "global_step": 590663, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0205774307250977, "global_step": 590664, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.089503288269043, "global_step": 590665, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0384280681610107, "global_step": 590666, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9942158460617065, "global_step": 590667, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0017669200897217, "global_step": 590668, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0153310298919678, "global_step": 590669, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0176167488098145, "global_step": 590670, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.063621759414673, "global_step": 590671, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9953798055648804, "global_step": 590672, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0007741451263428, "global_step": 590673, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.038222312927246, "global_step": 590674, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0509896278381348, "global_step": 590675, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0133209228515625, "global_step": 590676, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0168991088867188, "global_step": 590677, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9515326023101807, "global_step": 590678, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9805078506469727, "global_step": 590679, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.011442184448242, "global_step": 590680, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.017270565032959, "global_step": 590681, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0461156368255615, "global_step": 590682, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0180583000183105, "global_step": 590683, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0712552070617676, "global_step": 590684, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0415732860565186, "global_step": 590685, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.010193347930908, "global_step": 590686, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.031780958175659, "global_step": 590687, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0903232097625732, "global_step": 590688, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.984861135482788, "global_step": 590689, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.986312985420227, "global_step": 590690, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.013720989227295, "global_step": 590691, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.022592782974243, "global_step": 590692, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0456836223602295, "global_step": 590693, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9989255666732788, "global_step": 590694, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9801262617111206, "global_step": 590695, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.082909345626831, "global_step": 590696, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.978874921798706, "global_step": 590697, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.004807233810425, "global_step": 590698, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9561502933502197, "global_step": 590699, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.009275436401367, "global_step": 590700, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0421860218048096, "global_step": 590701, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.960829257965088, "global_step": 590702, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9968243837356567, "global_step": 590703, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.03511905670166, "global_step": 590704, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.004337787628174, "global_step": 590705, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0853822231292725, "global_step": 590706, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0134758949279785, "global_step": 590707, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0945849418640137, "global_step": 590708, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0435335636138916, "global_step": 590709, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0438332557678223, "global_step": 590710, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.006377935409546, "global_step": 590711, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9701894521713257, "global_step": 590712, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9850691556930542, "global_step": 590713, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.088369607925415, "global_step": 590714, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0398783683776855, "global_step": 590715, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9596868753433228, "global_step": 590716, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0415091514587402, "global_step": 590717, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9749654531478882, "global_step": 590718, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0261733531951904, "global_step": 590719, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9799386262893677, "global_step": 590720, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1062753200531006, "global_step": 590721, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.018300771713257, "global_step": 590722, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0380728244781494, "global_step": 590723, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.102785110473633, "global_step": 590724, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0227742195129395, "global_step": 590725, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.965065598487854, "global_step": 590726, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.06640887260437, "global_step": 590727, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.020012378692627, "global_step": 590728, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0559639930725098, "global_step": 590729, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.060145139694214, "global_step": 590730, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9140383005142212, "global_step": 590731, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9938410520553589, "global_step": 590732, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.080543279647827, "global_step": 590733, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0707578659057617, "global_step": 590734, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.071988344192505, "global_step": 590735, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.032392978668213, "global_step": 590736, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0534849166870117, "global_step": 590737, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.037480115890503, "global_step": 590738, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9086883068084717, "global_step": 590739, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0044069290161133, "global_step": 590740, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.92897629737854, "global_step": 590741, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0165131092071533, "global_step": 590742, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.039194107055664, "global_step": 590743, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9720227718353271, "global_step": 590744, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9437413215637207, "global_step": 590745, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.944071650505066, "global_step": 590746, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.008533477783203, "global_step": 590747, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.011972188949585, "global_step": 590748, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9853729009628296, "global_step": 590749, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.008713960647583, "global_step": 590750, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0458059310913086, "global_step": 590751, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9847416877746582, "global_step": 590752, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9847506284713745, "global_step": 590753, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0600287914276123, "global_step": 590754, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.997973918914795, "global_step": 590755, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0611603260040283, "global_step": 590756, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.050978660583496, "global_step": 590757, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0046417713165283, "global_step": 590758, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9843776226043701, "global_step": 590759, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0377440452575684, "global_step": 590760, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.004575729370117, "global_step": 590761, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9837638139724731, "global_step": 590762, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0029993057250977, "global_step": 590763, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.961601972579956, "global_step": 590764, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.084832191467285, "global_step": 590765, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.994999647140503, "global_step": 590766, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0128462314605713, "global_step": 590767, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0340423583984375, "global_step": 590768, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.002800941467285, "global_step": 590769, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0437569618225098, "global_step": 590770, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.089082717895508, "global_step": 590771, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9406616687774658, "global_step": 590772, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0242555141448975, "global_step": 590773, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.894363522529602, "global_step": 590774, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.005399227142334, "global_step": 590775, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0440328121185303, "global_step": 590776, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.04449462890625, "global_step": 590777, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9174110889434814, "global_step": 590778, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.062370777130127, "global_step": 590779, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0017426013946533, "global_step": 590780, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9700829982757568, "global_step": 590781, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9765138626098633, "global_step": 590782, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0536091327667236, "global_step": 590783, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.112295627593994, "global_step": 590784, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.055237054824829, "global_step": 590785, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.003934383392334, "global_step": 590786, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0247867107391357, "global_step": 590787, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.088200330734253, "global_step": 590788, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0527098178863525, "global_step": 590789, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9782851934432983, "global_step": 590790, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0177650451660156, "global_step": 590791, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0769145488739014, "global_step": 590792, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0131566524505615, "global_step": 590793, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9919321537017822, "global_step": 590794, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.009765386581421, "global_step": 590795, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.024503707885742, "global_step": 590796, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9978893995285034, "global_step": 590797, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0097849369049072, "global_step": 590798, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0331146717071533, "global_step": 590799, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0824966430664062, "global_step": 590800, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0236868858337402, "global_step": 590801, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0614027976989746, "global_step": 590802, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0032730102539062, "global_step": 590803, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.01316237449646, "global_step": 590804, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0276219844818115, "global_step": 590805, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.042919635772705, "global_step": 590806, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1159515380859375, "global_step": 590807, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9337360858917236, "global_step": 590808, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.047583818435669, "global_step": 590809, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0086891651153564, "global_step": 590810, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.025372266769409, "global_step": 590811, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9966745376586914, "global_step": 590812, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9869433641433716, "global_step": 590813, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9201215505599976, "global_step": 590814, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9764267206192017, "global_step": 590815, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0601885318756104, "global_step": 590816, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.051323175430298, "global_step": 590817, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0472357273101807, "global_step": 590818, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.041252851486206, "global_step": 590819, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9836596250534058, "global_step": 590820, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0155415534973145, "global_step": 590821, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0747339725494385, "global_step": 590822, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9587606191635132, "global_step": 590823, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.046139717102051, "global_step": 590824, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0258586406707764, "global_step": 590825, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.980912685394287, "global_step": 590826, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.021906852722168, "global_step": 590827, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.056607723236084, "global_step": 590828, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1070103645324707, "global_step": 590829, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.05352783203125, "global_step": 590830, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0800304412841797, "global_step": 590831, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0358195304870605, "global_step": 590832, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0237598419189453, "global_step": 590833, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9755244255065918, "global_step": 590834, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.033900022506714, "global_step": 590835, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.009438991546631, "global_step": 590836, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9511849880218506, "global_step": 590837, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0489602088928223, "global_step": 590838, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1087229251861572, "global_step": 590839, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0080649852752686, "global_step": 590840, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.932977318763733, "global_step": 590841, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0095155239105225, "global_step": 590842, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0520222187042236, "global_step": 590843, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0452229976654053, "global_step": 590844, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.075753927230835, "global_step": 590845, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9639064073562622, "global_step": 590846, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9924827814102173, "global_step": 590847, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0495877265930176, "global_step": 590848, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0379931926727295, "global_step": 590849, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9756337404251099, "global_step": 590850, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.019773006439209, "global_step": 590851, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0410807132720947, "global_step": 590852, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9964208602905273, "global_step": 590853, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9550178050994873, "global_step": 590854, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.066847085952759, "global_step": 590855, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0287718772888184, "global_step": 590856, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9684336185455322, "global_step": 590857, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.000972270965576, "global_step": 590858, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9846904277801514, "global_step": 590859, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.090482234954834, "global_step": 590860, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0229692459106445, "global_step": 590861, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.056265354156494, "global_step": 590862, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.99544095993042, "global_step": 590863, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.077179193496704, "global_step": 590864, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0470898151397705, "global_step": 590865, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.044804573059082, "global_step": 590866, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0765397548675537, "global_step": 590867, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.003450870513916, "global_step": 590868, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.952642798423767, "global_step": 590869, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.088595390319824, "global_step": 590870, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0129380226135254, "global_step": 590871, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9291796684265137, "global_step": 590872, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1192898750305176, "global_step": 590873, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0831966400146484, "global_step": 590874, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0256433486938477, "global_step": 590875, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0456299781799316, "global_step": 590876, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.029545545578003, "global_step": 590877, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9454132318496704, "global_step": 590878, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.049128293991089, "global_step": 590879, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0782365798950195, "global_step": 590880, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.991284966468811, "global_step": 590881, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9845553636550903, "global_step": 590882, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.981369972229004, "global_step": 590883, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.019611120223999, "global_step": 590884, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0858566761016846, "global_step": 590885, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0220513343811035, "global_step": 590886, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0479445457458496, "global_step": 590887, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0040440559387207, "global_step": 590888, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.999624490737915, "global_step": 590889, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.045166015625, "global_step": 590890, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.989403486251831, "global_step": 590891, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.994300127029419, "global_step": 590892, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0092666149139404, "global_step": 590893, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0692079067230225, "global_step": 590894, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0689046382904053, "global_step": 590895, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.997939109802246, "global_step": 590896, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9555153846740723, "global_step": 590897, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1070852279663086, "global_step": 590898, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.040163040161133, "global_step": 590899, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9432541131973267, "global_step": 590900, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.8999180793762207, "global_step": 590901, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.000323534011841, "global_step": 590902, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9646975994110107, "global_step": 590903, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0578486919403076, "global_step": 590904, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9827702045440674, "global_step": 590905, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.063260078430176, "global_step": 590906, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9916828870773315, "global_step": 590907, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0785415172576904, "global_step": 590908, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0011579990386963, "global_step": 590909, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9890127182006836, "global_step": 590910, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0483107566833496, "global_step": 590911, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.007904291152954, "global_step": 590912, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0738344192504883, "global_step": 590913, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9782426357269287, "global_step": 590914, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.012960910797119, "global_step": 590915, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9451454877853394, "global_step": 590916, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1510910987854004, "global_step": 590917, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9655749797821045, "global_step": 590918, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.042123317718506, "global_step": 590919, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9512919187545776, "global_step": 590920, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0492985248565674, "global_step": 590921, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.065162181854248, "global_step": 590922, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0166468620300293, "global_step": 590923, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.02897310256958, "global_step": 590924, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0578465461730957, "global_step": 590925, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.032768726348877, "global_step": 590926, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0729892253875732, "global_step": 590927, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0526509284973145, "global_step": 590928, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.997524619102478, "global_step": 590929, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0391123294830322, "global_step": 590930, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.040771245956421, "global_step": 590931, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.045409917831421, "global_step": 590932, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.069314479827881, "global_step": 590933, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0710511207580566, "global_step": 590934, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9734323024749756, "global_step": 590935, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1195735931396484, "global_step": 590936, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.066056489944458, "global_step": 590937, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0578553676605225, "global_step": 590938, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.929057240486145, "global_step": 590939, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.978316307067871, "global_step": 590940, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.007829189300537, "global_step": 590941, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9868783950805664, "global_step": 590942, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9492236375808716, "global_step": 590943, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.064401388168335, "global_step": 590944, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0667591094970703, "global_step": 590945, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.036921262741089, "global_step": 590946, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9627702236175537, "global_step": 590947, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1041200160980225, "global_step": 590948, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0197463035583496, "global_step": 590949, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.011824607849121, "global_step": 590950, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0230724811553955, "global_step": 590951, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.135568141937256, "global_step": 590952, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9886746406555176, "global_step": 590953, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.038801431655884, "global_step": 590954, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.017122268676758, "global_step": 590955, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9692264795303345, "global_step": 590956, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.997664451599121, "global_step": 590957, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9614973068237305, "global_step": 590958, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.064708948135376, "global_step": 590959, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0836641788482666, "global_step": 590960, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0123424530029297, "global_step": 590961, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0393588542938232, "global_step": 590962, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1071555614471436, "global_step": 590963, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0358479022979736, "global_step": 590964, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.012833833694458, "global_step": 590965, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0027945041656494, "global_step": 590966, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9883733987808228, "global_step": 590967, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.026841402053833, "global_step": 590968, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.002387523651123, "global_step": 590969, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0936691761016846, "global_step": 590970, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.042062520980835, "global_step": 590971, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0617053508758545, "global_step": 590972, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.94327974319458, "global_step": 590973, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0096945762634277, "global_step": 590974, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9950505495071411, "global_step": 590975, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.065748929977417, "global_step": 590976, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.018548011779785, "global_step": 590977, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.048888683319092, "global_step": 590978, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9928803443908691, "global_step": 590979, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0447494983673096, "global_step": 590980, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0045740604400635, "global_step": 590981, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.089674949645996, "global_step": 590982, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0939760208129883, "global_step": 590983, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.072783946990967, "global_step": 590984, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9906220436096191, "global_step": 590985, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.013857126235962, "global_step": 590986, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.006472587585449, "global_step": 590987, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.954361915588379, "global_step": 590988, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9391555786132812, "global_step": 590989, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9926501512527466, "global_step": 590990, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9784834384918213, "global_step": 590991, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0995118618011475, "global_step": 590992, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.095686435699463, "global_step": 590993, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0987861156463623, "global_step": 590994, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9603960514068604, "global_step": 590995, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0383358001708984, "global_step": 590996, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.022495985031128, "global_step": 590997, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.04160475730896, "global_step": 590998, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0565459728240967, "global_step": 590999, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.016091823577881, "global_step": 591000, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0203495025634766, "global_step": 591001, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0223119258880615, "global_step": 591002, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0435478687286377, "global_step": 591003, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0121841430664062, "global_step": 591004, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9770029783248901, "global_step": 591005, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9576412439346313, "global_step": 591006, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0131285190582275, "global_step": 591007, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9606903791427612, "global_step": 591008, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.919836163520813, "global_step": 591009, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0257186889648438, "global_step": 591010, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.021960973739624, "global_step": 591011, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0267016887664795, "global_step": 591012, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0559310913085938, "global_step": 591013, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0128891468048096, "global_step": 591014, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0635344982147217, "global_step": 591015, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.030820846557617, "global_step": 591016, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.071753740310669, "global_step": 591017, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.06234073638916, "global_step": 591018, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.011579751968384, "global_step": 591019, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.002993106842041, "global_step": 591020, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.041351556777954, "global_step": 591021, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0493874549865723, "global_step": 591022, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.005018949508667, "global_step": 591023, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9679194688796997, "global_step": 591024, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9864574670791626, "global_step": 591025, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0063366889953613, "global_step": 591026, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.048293113708496, "global_step": 591027, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.082627773284912, "global_step": 591028, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0021069049835205, "global_step": 591029, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.134927988052368, "global_step": 591030, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.082141637802124, "global_step": 591031, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1525895595550537, "global_step": 591032, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0421595573425293, "global_step": 591033, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.979092001914978, "global_step": 591034, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9874335527420044, "global_step": 591035, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0624096393585205, "global_step": 591036, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9732675552368164, "global_step": 591037, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9175068140029907, "global_step": 591038, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9947887659072876, "global_step": 591039, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.04618763923645, "global_step": 591040, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.970380425453186, "global_step": 591041, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0621843338012695, "global_step": 591042, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.953278660774231, "global_step": 591043, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0109782218933105, "global_step": 591044, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0407919883728027, "global_step": 591045, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9789915084838867, "global_step": 591046, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0360779762268066, "global_step": 591047, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0010721683502197, "global_step": 591048, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9153283834457397, "global_step": 591049, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9817485809326172, "global_step": 591050, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.045193910598755, "global_step": 591051, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9659875631332397, "global_step": 591052, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9509509801864624, "global_step": 591053, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.028937339782715, "global_step": 591054, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0031042098999023, "global_step": 591055, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.040008306503296, "global_step": 591056, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0312066078186035, "global_step": 591057, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9703713655471802, "global_step": 591058, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.02249813079834, "global_step": 591059, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0401997566223145, "global_step": 591060, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0186476707458496, "global_step": 591061, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.002075672149658, "global_step": 591062, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.016284227371216, "global_step": 591063, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.987059235572815, "global_step": 591064, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0200467109680176, "global_step": 591065, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.085357427597046, "global_step": 591066, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1004483699798584, "global_step": 591067, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.035796642303467, "global_step": 591068, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9500640630722046, "global_step": 591069, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9919800758361816, "global_step": 591070, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9825693368911743, "global_step": 591071, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9196490049362183, "global_step": 591072, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.061497211456299, "global_step": 591073, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.998178243637085, "global_step": 591074, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0546298027038574, "global_step": 591075, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9470659494400024, "global_step": 591076, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0354602336883545, "global_step": 591077, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9510767459869385, "global_step": 591078, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.983903408050537, "global_step": 591079, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9990711212158203, "global_step": 591080, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9798535108566284, "global_step": 591081, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0025172233581543, "global_step": 591082, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.946426272392273, "global_step": 591083, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0061137676239014, "global_step": 591084, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9734090566635132, "global_step": 591085, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9992353916168213, "global_step": 591086, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.067237615585327, "global_step": 591087, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.102400541305542, "global_step": 591088, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9322667121887207, "global_step": 591089, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0656158924102783, "global_step": 591090, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0738816261291504, "global_step": 591091, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9722789525985718, "global_step": 591092, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9753217697143555, "global_step": 591093, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9858568906784058, "global_step": 591094, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9662047624588013, "global_step": 591095, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.032991409301758, "global_step": 591096, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.003868341445923, "global_step": 591097, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9469709396362305, "global_step": 591098, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.993554711341858, "global_step": 591099, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.01875638961792, "global_step": 591100, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.980265498161316, "global_step": 591101, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9919227361679077, "global_step": 591102, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0088846683502197, "global_step": 591103, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0556015968322754, "global_step": 591104, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9787769317626953, "global_step": 591105, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.050835609436035, "global_step": 591106, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.019162893295288, "global_step": 591107, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.044997453689575, "global_step": 591108, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0086541175842285, "global_step": 591109, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0467641353607178, "global_step": 591110, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.008683919906616, "global_step": 591111, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9977091550827026, "global_step": 591112, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0051424503326416, "global_step": 591113, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.951038122177124, "global_step": 591114, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0566365718841553, "global_step": 591115, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0062241554260254, "global_step": 591116, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.991093397140503, "global_step": 591117, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0404632091522217, "global_step": 591118, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9759838581085205, "global_step": 591119, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9859479665756226, "global_step": 591120, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0676581859588623, "global_step": 591121, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.028557538986206, "global_step": 591122, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0265371799468994, "global_step": 591123, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.982625126838684, "global_step": 591124, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.006842613220215, "global_step": 591125, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0153534412384033, "global_step": 591126, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9873837232589722, "global_step": 591127, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0364346504211426, "global_step": 591128, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0938785076141357, "global_step": 591129, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1019418239593506, "global_step": 591130, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9826908111572266, "global_step": 591131, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.020059823989868, "global_step": 591132, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0392889976501465, "global_step": 591133, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0405521392822266, "global_step": 591134, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0139517784118652, "global_step": 591135, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0940804481506348, "global_step": 591136, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.026034355163574, "global_step": 591137, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.096534013748169, "global_step": 591138, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9342893362045288, "global_step": 591139, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1101837158203125, "global_step": 591140, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.005608320236206, "global_step": 591141, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.051410436630249, "global_step": 591142, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1080355644226074, "global_step": 591143, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0311198234558105, "global_step": 591144, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9820435047149658, "global_step": 591145, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0191221237182617, "global_step": 591146, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9643784761428833, "global_step": 591147, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0140013694763184, "global_step": 591148, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.084678888320923, "global_step": 591149, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.995117425918579, "global_step": 591150, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.037384510040283, "global_step": 591151, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0721781253814697, "global_step": 591152, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0296242237091064, "global_step": 591153, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.900941014289856, "global_step": 591154, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.05822491645813, "global_step": 591155, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9420578479766846, "global_step": 591156, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9663783311843872, "global_step": 591157, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.010586738586426, "global_step": 591158, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.044987678527832, "global_step": 591159, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9809938669204712, "global_step": 591160, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.072165012359619, "global_step": 591161, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.011977434158325, "global_step": 591162, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.021859645843506, "global_step": 591163, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0304954051971436, "global_step": 591164, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0183112621307373, "global_step": 591165, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0658020973205566, "global_step": 591166, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0217466354370117, "global_step": 591167, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9910836219787598, "global_step": 591168, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9779685735702515, "global_step": 591169, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.033454179763794, "global_step": 591170, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9929450750350952, "global_step": 591171, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.014270782470703, "global_step": 591172, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.091817617416382, "global_step": 591173, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0521342754364014, "global_step": 591174, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.8739190101623535, "global_step": 591175, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.010695457458496, "global_step": 591176, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0507843494415283, "global_step": 591177, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9562703371047974, "global_step": 591178, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0128591060638428, "global_step": 591179, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.046684741973877, "global_step": 591180, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0587241649627686, "global_step": 591181, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9945652484893799, "global_step": 591182, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0003342628479004, "global_step": 591183, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0353755950927734, "global_step": 591184, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0229110717773438, "global_step": 591185, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9892526865005493, "global_step": 591186, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.079956293106079, "global_step": 591187, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.061293125152588, "global_step": 591188, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0597071647644043, "global_step": 591189, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9552451372146606, "global_step": 591190, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.058412551879883, "global_step": 591191, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9639372825622559, "global_step": 591192, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.088120937347412, "global_step": 591193, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9968222379684448, "global_step": 591194, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0135512351989746, "global_step": 591195, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0452497005462646, "global_step": 591196, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.093836784362793, "global_step": 591197, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.1146934032440186, "global_step": 591198, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0181779861450195, "global_step": 591199, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.979877233505249, "global_step": 591200, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9697580337524414, "global_step": 591201, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.029606580734253, "global_step": 591202, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0209548473358154, "global_step": 591203, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0286059379577637, "global_step": 591204, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0382888317108154, "global_step": 591205, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0399858951568604, "global_step": 591206, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9838461875915527, "global_step": 591207, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0618515014648438, "global_step": 591208, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9944660663604736, "global_step": 591209, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9819552898406982, "global_step": 591210, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9967570304870605, "global_step": 591211, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.045093297958374, "global_step": 591212, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.993225336074829, "global_step": 591213, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.000822067260742, "global_step": 591214, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9607343673706055, "global_step": 591215, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9727723598480225, "global_step": 591216, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.135438919067383, "global_step": 591217, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9919884204864502, "global_step": 591218, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.007596254348755, "global_step": 591219, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.8958940505981445, "global_step": 591220, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.0792057514190674, "global_step": 591221, "epoch": 959, "lr": 5e-05}
{"train_loss": 2.016007423400879, "global_step": 591222, "epoch": 959, "lr": 5e-05}
{"train_loss": 1.9954242706298828, "global_step": 591223, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9825681447982788, "global_step": 591224, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9964563846588135, "global_step": 591225, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.008066177368164, "global_step": 591226, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9467108249664307, "global_step": 591227, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0793631076812744, "global_step": 591228, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9760109186172485, "global_step": 591229, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0324509143829346, "global_step": 591230, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.023047924041748, "global_step": 591231, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1257450580596924, "global_step": 591232, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.019540548324585, "global_step": 591233, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9964981079101562, "global_step": 591234, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.997605323791504, "global_step": 591235, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0137081146240234, "global_step": 591236, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.968528151512146, "global_step": 591237, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0450127124786377, "global_step": 591238, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0541787147521973, "global_step": 591239, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.037644624710083, "global_step": 591240, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9962069988250732, "global_step": 591241, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0195815563201904, "global_step": 591242, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0637075901031494, "global_step": 591243, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9362363815307617, "global_step": 591244, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.09558367729187, "global_step": 591245, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0003411769866943, "global_step": 591246, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9570318460464478, "global_step": 591247, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9752593040466309, "global_step": 591248, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0701420307159424, "global_step": 591249, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.034834146499634, "global_step": 591250, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.043483257293701, "global_step": 591251, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0280117988586426, "global_step": 591252, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.024038076400757, "global_step": 591253, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9915825128555298, "global_step": 591254, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.00252103805542, "global_step": 591255, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0825769901275635, "global_step": 591256, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0620217323303223, "global_step": 591257, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.8644168376922607, "global_step": 591258, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.035064697265625, "global_step": 591259, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0806446075439453, "global_step": 591260, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9851956367492676, "global_step": 591261, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9876019954681396, "global_step": 591262, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9714692831039429, "global_step": 591263, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.997022271156311, "global_step": 591264, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0216763019561768, "global_step": 591265, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0760507583618164, "global_step": 591266, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.102095127105713, "global_step": 591267, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0149073600769043, "global_step": 591268, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0575509071350098, "global_step": 591269, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0197255611419678, "global_step": 591270, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.013225793838501, "global_step": 591271, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9475849866867065, "global_step": 591272, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9811712503433228, "global_step": 591273, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0623421669006348, "global_step": 591274, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9986037015914917, "global_step": 591275, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.988964557647705, "global_step": 591276, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.006195545196533, "global_step": 591277, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9633886814117432, "global_step": 591278, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0249791145324707, "global_step": 591279, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.990653157234192, "global_step": 591280, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9585754871368408, "global_step": 591281, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1136481761932373, "global_step": 591282, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0479328632354736, "global_step": 591283, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9557316303253174, "global_step": 591284, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0146684646606445, "global_step": 591285, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.00146222114563, "global_step": 591286, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0049424171447754, "global_step": 591287, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0425539016723633, "global_step": 591288, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.063350200653076, "global_step": 591289, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9336156845092773, "global_step": 591290, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.948652744293213, "global_step": 591291, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.005506753921509, "global_step": 591292, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0026350021362305, "global_step": 591293, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9887323379516602, "global_step": 591294, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.875503659248352, "global_step": 591295, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9949884414672852, "global_step": 591296, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0776126384735107, "global_step": 591297, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9358404874801636, "global_step": 591298, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.93520188331604, "global_step": 591299, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.045933485031128, "global_step": 591300, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0702714920043945, "global_step": 591301, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.874144434928894, "global_step": 591302, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.976919412612915, "global_step": 591303, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9338078498840332, "global_step": 591304, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.022646427154541, "global_step": 591305, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.011542558670044, "global_step": 591306, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9750151634216309, "global_step": 591307, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9850364923477173, "global_step": 591308, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.076597213745117, "global_step": 591309, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0554943084716797, "global_step": 591310, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9335670471191406, "global_step": 591311, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9962612390518188, "global_step": 591312, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9960052967071533, "global_step": 591313, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.011930227279663, "global_step": 591314, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.05275559425354, "global_step": 591315, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9289016723632812, "global_step": 591316, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.009927988052368, "global_step": 591317, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0507736206054688, "global_step": 591318, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.022202491760254, "global_step": 591319, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0301287174224854, "global_step": 591320, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9703935384750366, "global_step": 591321, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.8784233331680298, "global_step": 591322, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9575707912445068, "global_step": 591323, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.962059497833252, "global_step": 591324, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9620403051376343, "global_step": 591325, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9987993240356445, "global_step": 591326, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9976086616516113, "global_step": 591327, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0057010650634766, "global_step": 591328, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.043457508087158, "global_step": 591329, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0372214317321777, "global_step": 591330, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9876151084899902, "global_step": 591331, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.016899824142456, "global_step": 591332, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0606284141540527, "global_step": 591333, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.055830240249634, "global_step": 591334, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9541581869125366, "global_step": 591335, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0237059593200684, "global_step": 591336, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.968117356300354, "global_step": 591337, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0228848457336426, "global_step": 591338, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9239850044250488, "global_step": 591339, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9839202165603638, "global_step": 591340, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0105578899383545, "global_step": 591341, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.907668113708496, "global_step": 591342, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.068009853363037, "global_step": 591343, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9588719606399536, "global_step": 591344, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0436947345733643, "global_step": 591345, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.038930654525757, "global_step": 591346, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9633783102035522, "global_step": 591347, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0197250843048096, "global_step": 591348, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1212611198425293, "global_step": 591349, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9668649435043335, "global_step": 591350, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9943373203277588, "global_step": 591351, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9745627641677856, "global_step": 591352, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.022526741027832, "global_step": 591353, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9842829704284668, "global_step": 591354, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.957603931427002, "global_step": 591355, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9519689083099365, "global_step": 591356, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9956343173980713, "global_step": 591357, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0048131942749023, "global_step": 591358, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0725746154785156, "global_step": 591359, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0029642581939697, "global_step": 591360, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9843934774398804, "global_step": 591361, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9835437536239624, "global_step": 591362, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.07938551902771, "global_step": 591363, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.001715660095215, "global_step": 591364, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9878113269805908, "global_step": 591365, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9889333248138428, "global_step": 591366, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9795063734054565, "global_step": 591367, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9461897611618042, "global_step": 591368, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.000134229660034, "global_step": 591369, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.965576410293579, "global_step": 591370, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9432556629180908, "global_step": 591371, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.024036407470703, "global_step": 591372, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0499396324157715, "global_step": 591373, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9663029909133911, "global_step": 591374, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9810882806777954, "global_step": 591375, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.091959238052368, "global_step": 591376, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.993007779121399, "global_step": 591377, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0030908584594727, "global_step": 591378, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9725525379180908, "global_step": 591379, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9875428676605225, "global_step": 591380, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0751290321350098, "global_step": 591381, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0696370601654053, "global_step": 591382, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9835673570632935, "global_step": 591383, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0015451908111572, "global_step": 591384, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9916346073150635, "global_step": 591385, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.078270673751831, "global_step": 591386, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9474265575408936, "global_step": 591387, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.055023193359375, "global_step": 591388, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0359740257263184, "global_step": 591389, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.015979051589966, "global_step": 591390, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.057283401489258, "global_step": 591391, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0301735401153564, "global_step": 591392, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9756275415420532, "global_step": 591393, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9956262111663818, "global_step": 591394, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9848383665084839, "global_step": 591395, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.045870304107666, "global_step": 591396, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0338571071624756, "global_step": 591397, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9875231981277466, "global_step": 591398, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.013751268386841, "global_step": 591399, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9516870975494385, "global_step": 591400, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0869033336639404, "global_step": 591401, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.014866352081299, "global_step": 591402, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0514187812805176, "global_step": 591403, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0017945766448975, "global_step": 591404, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9977794885635376, "global_step": 591405, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.01812744140625, "global_step": 591406, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9715182781219482, "global_step": 591407, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0699636936187744, "global_step": 591408, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.042133331298828, "global_step": 591409, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0432584285736084, "global_step": 591410, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0038819313049316, "global_step": 591411, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9538815021514893, "global_step": 591412, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.045691728591919, "global_step": 591413, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.999476671218872, "global_step": 591414, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9929383993148804, "global_step": 591415, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9685558080673218, "global_step": 591416, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0157833099365234, "global_step": 591417, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9473453760147095, "global_step": 591418, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.052006721496582, "global_step": 591419, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9671608209609985, "global_step": 591420, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0436553955078125, "global_step": 591421, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0304675102233887, "global_step": 591422, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.964357852935791, "global_step": 591423, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0546233654022217, "global_step": 591424, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.015089750289917, "global_step": 591425, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.030102252960205, "global_step": 591426, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.061349391937256, "global_step": 591427, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1476528644561768, "global_step": 591428, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.130147695541382, "global_step": 591429, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9541679620742798, "global_step": 591430, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0556087493896484, "global_step": 591431, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9484905004501343, "global_step": 591432, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9753625392913818, "global_step": 591433, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.980643630027771, "global_step": 591434, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.959800124168396, "global_step": 591435, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.025437831878662, "global_step": 591436, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0024092197418213, "global_step": 591437, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.04583740234375, "global_step": 591438, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.981123447418213, "global_step": 591439, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9743014574050903, "global_step": 591440, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.05088472366333, "global_step": 591441, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.022406578063965, "global_step": 591442, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.937850832939148, "global_step": 591443, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0647053718566895, "global_step": 591444, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0061023235321045, "global_step": 591445, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.057142972946167, "global_step": 591446, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.124497890472412, "global_step": 591447, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.038411855697632, "global_step": 591448, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9249440431594849, "global_step": 591449, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.997113823890686, "global_step": 591450, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.083077907562256, "global_step": 591451, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9591248035430908, "global_step": 591452, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.014711380004883, "global_step": 591453, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0093576908111572, "global_step": 591454, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9300470352172852, "global_step": 591455, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.923417568206787, "global_step": 591456, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.026789903640747, "global_step": 591457, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0050559043884277, "global_step": 591458, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1028218269348145, "global_step": 591459, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.03692364692688, "global_step": 591460, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.077190399169922, "global_step": 591461, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9546611309051514, "global_step": 591462, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0658013820648193, "global_step": 591463, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0243513584136963, "global_step": 591464, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.04378080368042, "global_step": 591465, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.021378993988037, "global_step": 591466, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9858018159866333, "global_step": 591467, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.074162483215332, "global_step": 591468, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.052962303161621, "global_step": 591469, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9650912284851074, "global_step": 591470, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.017456293106079, "global_step": 591471, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0127077102661133, "global_step": 591472, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9700860977172852, "global_step": 591473, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.068877696990967, "global_step": 591474, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0151355266571045, "global_step": 591475, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.04555082321167, "global_step": 591476, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9592289924621582, "global_step": 591477, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.069047451019287, "global_step": 591478, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0304105281829834, "global_step": 591479, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0039377212524414, "global_step": 591480, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.026777744293213, "global_step": 591481, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9227938652038574, "global_step": 591482, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9860819578170776, "global_step": 591483, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9700994491577148, "global_step": 591484, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0082406997680664, "global_step": 591485, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0020041465759277, "global_step": 591486, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9780628681182861, "global_step": 591487, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.005333185195923, "global_step": 591488, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0221898555755615, "global_step": 591489, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0149452686309814, "global_step": 591490, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0100786685943604, "global_step": 591491, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0614981651306152, "global_step": 591492, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.973779559135437, "global_step": 591493, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0150527954101562, "global_step": 591494, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9153869152069092, "global_step": 591495, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9956260919570923, "global_step": 591496, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0341992378234863, "global_step": 591497, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1560568809509277, "global_step": 591498, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0004405975341797, "global_step": 591499, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9184633493423462, "global_step": 591500, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9502832889556885, "global_step": 591501, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.03460431098938, "global_step": 591502, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9611543416976929, "global_step": 591503, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9608696699142456, "global_step": 591504, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0943222045898438, "global_step": 591505, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9992884397506714, "global_step": 591506, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9954631328582764, "global_step": 591507, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.090708017349243, "global_step": 591508, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.939623236656189, "global_step": 591509, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9014852046966553, "global_step": 591510, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0503311157226562, "global_step": 591511, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9488898515701294, "global_step": 591512, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.062694549560547, "global_step": 591513, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9280201196670532, "global_step": 591514, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.053931951522827, "global_step": 591515, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0620596408843994, "global_step": 591516, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9834001064300537, "global_step": 591517, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0850932598114014, "global_step": 591518, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.063807249069214, "global_step": 591519, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9714796543121338, "global_step": 591520, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0486299991607666, "global_step": 591521, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9744040966033936, "global_step": 591522, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9928779602050781, "global_step": 591523, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0672831535339355, "global_step": 591524, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.042635679244995, "global_step": 591525, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0406992435455322, "global_step": 591526, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0581095218658447, "global_step": 591527, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9497922658920288, "global_step": 591528, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.031036376953125, "global_step": 591529, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1032965183258057, "global_step": 591530, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.067823648452759, "global_step": 591531, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.007242202758789, "global_step": 591532, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9995778799057007, "global_step": 591533, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9288139343261719, "global_step": 591534, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9982293844223022, "global_step": 591535, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.103872537612915, "global_step": 591536, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.084662675857544, "global_step": 591537, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9515495300292969, "global_step": 591538, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0422091484069824, "global_step": 591539, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0822837352752686, "global_step": 591540, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0301575660705566, "global_step": 591541, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1279659271240234, "global_step": 591542, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9801703691482544, "global_step": 591543, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.983474612236023, "global_step": 591544, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9342421293258667, "global_step": 591545, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9782601594924927, "global_step": 591546, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0176191329956055, "global_step": 591547, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.020569324493408, "global_step": 591548, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9994858503341675, "global_step": 591549, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.01898455619812, "global_step": 591550, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9529765844345093, "global_step": 591551, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0177202224731445, "global_step": 591552, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.019183874130249, "global_step": 591553, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.031431198120117, "global_step": 591554, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.999656319618225, "global_step": 591555, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0342702865600586, "global_step": 591556, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.018455982208252, "global_step": 591557, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.051903247833252, "global_step": 591558, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9547662734985352, "global_step": 591559, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.982736587524414, "global_step": 591560, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0254406929016113, "global_step": 591561, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9821233749389648, "global_step": 591562, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0531766414642334, "global_step": 591563, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1341118812561035, "global_step": 591564, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.076387405395508, "global_step": 591565, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9934543371200562, "global_step": 591566, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.052004814147949, "global_step": 591567, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.057249069213867, "global_step": 591568, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0086259841918945, "global_step": 591569, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9427592754364014, "global_step": 591570, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9943106174468994, "global_step": 591571, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9846746921539307, "global_step": 591572, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.081064462661743, "global_step": 591573, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.028223752975464, "global_step": 591574, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.043914794921875, "global_step": 591575, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.969664216041565, "global_step": 591576, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0360119342803955, "global_step": 591577, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.98471999168396, "global_step": 591578, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.8916796445846558, "global_step": 591579, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0275778770446777, "global_step": 591580, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.003795623779297, "global_step": 591581, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9997543096542358, "global_step": 591582, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.010744094848633, "global_step": 591583, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9917442798614502, "global_step": 591584, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.06412935256958, "global_step": 591585, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0542232990264893, "global_step": 591586, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9240673780441284, "global_step": 591587, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.02713680267334, "global_step": 591588, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0015838146209717, "global_step": 591589, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.000020980834961, "global_step": 591590, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0099234580993652, "global_step": 591591, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0618345737457275, "global_step": 591592, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.997222900390625, "global_step": 591593, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.060331106185913, "global_step": 591594, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.084390640258789, "global_step": 591595, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9418644905090332, "global_step": 591596, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0189554691314697, "global_step": 591597, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0925281047821045, "global_step": 591598, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0162246227264404, "global_step": 591599, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9951426982879639, "global_step": 591600, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0971412658691406, "global_step": 591601, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.985849142074585, "global_step": 591602, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9815278053283691, "global_step": 591603, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.055385112762451, "global_step": 591604, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.973689317703247, "global_step": 591605, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9689693450927734, "global_step": 591606, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0083847045898438, "global_step": 591607, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9474263191223145, "global_step": 591608, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.952266812324524, "global_step": 591609, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0507733821868896, "global_step": 591610, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0354881286621094, "global_step": 591611, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9210737943649292, "global_step": 591612, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.083951950073242, "global_step": 591613, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0053396224975586, "global_step": 591614, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.998767375946045, "global_step": 591615, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.028120756149292, "global_step": 591616, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.025092124938965, "global_step": 591617, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1795685291290283, "global_step": 591618, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9656437635421753, "global_step": 591619, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0215091705322266, "global_step": 591620, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9846422672271729, "global_step": 591621, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.972763180732727, "global_step": 591622, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0266876220703125, "global_step": 591623, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9927030801773071, "global_step": 591624, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.029869794845581, "global_step": 591625, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9905980825424194, "global_step": 591626, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.062044143676758, "global_step": 591627, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9602446556091309, "global_step": 591628, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9744068384170532, "global_step": 591629, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.993194580078125, "global_step": 591630, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0043811798095703, "global_step": 591631, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.96500563621521, "global_step": 591632, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.042785167694092, "global_step": 591633, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.022209882736206, "global_step": 591634, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0079305171966553, "global_step": 591635, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0713813304901123, "global_step": 591636, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0620765686035156, "global_step": 591637, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9420113563537598, "global_step": 591638, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.993138074874878, "global_step": 591639, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0717570781707764, "global_step": 591640, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9705637693405151, "global_step": 591641, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0410232543945312, "global_step": 591642, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0569663047790527, "global_step": 591643, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0646700859069824, "global_step": 591644, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1006362438201904, "global_step": 591645, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0005102157592773, "global_step": 591646, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9210940599441528, "global_step": 591647, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9361765384674072, "global_step": 591648, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.007185220718384, "global_step": 591649, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0751395225524902, "global_step": 591650, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.996447205543518, "global_step": 591651, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.061375141143799, "global_step": 591652, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9800530672073364, "global_step": 591653, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0106141567230225, "global_step": 591654, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.122854709625244, "global_step": 591655, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.009552001953125, "global_step": 591656, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0161542892456055, "global_step": 591657, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.070972442626953, "global_step": 591658, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.903403401374817, "global_step": 591659, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.035834312438965, "global_step": 591660, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9957587718963623, "global_step": 591661, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0545053482055664, "global_step": 591662, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.005398988723755, "global_step": 591663, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.071150541305542, "global_step": 591664, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0515565872192383, "global_step": 591665, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0319881439208984, "global_step": 591666, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.044196128845215, "global_step": 591667, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9180803298950195, "global_step": 591668, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9861235618591309, "global_step": 591669, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0620923042297363, "global_step": 591670, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0002853870391846, "global_step": 591671, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.007310628890991, "global_step": 591672, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0696685314178467, "global_step": 591673, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.011155843734741, "global_step": 591674, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0708699226379395, "global_step": 591675, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0816304683685303, "global_step": 591676, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.076211452484131, "global_step": 591677, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1426985263824463, "global_step": 591678, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.02156925201416, "global_step": 591679, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.104969024658203, "global_step": 591680, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0411338806152344, "global_step": 591681, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0013952255249023, "global_step": 591682, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0719430446624756, "global_step": 591683, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.049298048019409, "global_step": 591684, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0532429218292236, "global_step": 591685, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0044472217559814, "global_step": 591686, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9846322536468506, "global_step": 591687, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0846710205078125, "global_step": 591688, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.891287088394165, "global_step": 591689, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0121657848358154, "global_step": 591690, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9523484706878662, "global_step": 591691, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.100707530975342, "global_step": 591692, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0432488918304443, "global_step": 591693, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0684611797332764, "global_step": 591694, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.000523567199707, "global_step": 591695, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9572516679763794, "global_step": 591696, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9985358715057373, "global_step": 591697, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.026869297027588, "global_step": 591698, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9935461282730103, "global_step": 591699, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0059666633605957, "global_step": 591700, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9700137376785278, "global_step": 591701, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.078508138656616, "global_step": 591702, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0391907691955566, "global_step": 591703, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9398860931396484, "global_step": 591704, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0337884426116943, "global_step": 591705, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.008028030395508, "global_step": 591706, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.01413631439209, "global_step": 591707, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0496675968170166, "global_step": 591708, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.083813190460205, "global_step": 591709, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0448503494262695, "global_step": 591710, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0013113021850586, "global_step": 591711, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.02516508102417, "global_step": 591712, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9905949831008911, "global_step": 591713, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.027827501296997, "global_step": 591714, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0185108184814453, "global_step": 591715, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.067539691925049, "global_step": 591716, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9881130456924438, "global_step": 591717, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9831123352050781, "global_step": 591718, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.020643711090088, "global_step": 591719, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.042259454727173, "global_step": 591720, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9857630729675293, "global_step": 591721, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0829861164093018, "global_step": 591722, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9826490879058838, "global_step": 591723, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0103349685668945, "global_step": 591724, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.013723611831665, "global_step": 591725, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9730502367019653, "global_step": 591726, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0086114406585693, "global_step": 591727, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9803234338760376, "global_step": 591728, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9494664669036865, "global_step": 591729, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.967461347579956, "global_step": 591730, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9174145460128784, "global_step": 591731, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9451168775558472, "global_step": 591732, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9769207239151, "global_step": 591733, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0070385932922363, "global_step": 591734, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.01282000541687, "global_step": 591735, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0780067443847656, "global_step": 591736, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0179991722106934, "global_step": 591737, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.966291904449463, "global_step": 591738, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.059738874435425, "global_step": 591739, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0738418102264404, "global_step": 591740, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0395708084106445, "global_step": 591741, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.001427173614502, "global_step": 591742, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9777582883834839, "global_step": 591743, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.044095277786255, "global_step": 591744, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.993106484413147, "global_step": 591745, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0298478603363037, "global_step": 591746, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0058655738830566, "global_step": 591747, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.021378517150879, "global_step": 591748, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0899717807769775, "global_step": 591749, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9929254055023193, "global_step": 591750, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0327706336975098, "global_step": 591751, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.021526336669922, "global_step": 591752, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0199785232543945, "global_step": 591753, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0675811767578125, "global_step": 591754, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0168724060058594, "global_step": 591755, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9447224140167236, "global_step": 591756, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.993464469909668, "global_step": 591757, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9815789461135864, "global_step": 591758, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9679540395736694, "global_step": 591759, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0706329345703125, "global_step": 591760, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0374321937561035, "global_step": 591761, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0079309940338135, "global_step": 591762, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.003920555114746, "global_step": 591763, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.021926164627075, "global_step": 591764, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0105702877044678, "global_step": 591765, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0385007858276367, "global_step": 591766, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9796569347381592, "global_step": 591767, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9379243850708008, "global_step": 591768, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0556769371032715, "global_step": 591769, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9868605136871338, "global_step": 591770, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.986457347869873, "global_step": 591771, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9917917251586914, "global_step": 591772, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0031676292419434, "global_step": 591773, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1072304248809814, "global_step": 591774, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.987076997756958, "global_step": 591775, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.058300733566284, "global_step": 591776, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9902446269989014, "global_step": 591777, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0958571434020996, "global_step": 591778, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0808024406433105, "global_step": 591779, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9972443580627441, "global_step": 591780, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.012255907058716, "global_step": 591781, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0056865215301514, "global_step": 591782, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0404298305511475, "global_step": 591783, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.087095022201538, "global_step": 591784, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.065744161605835, "global_step": 591785, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.005776882171631, "global_step": 591786, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9898515939712524, "global_step": 591787, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0622341632843018, "global_step": 591788, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9124157428741455, "global_step": 591789, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9635213613510132, "global_step": 591790, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9884158372879028, "global_step": 591791, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0334506034851074, "global_step": 591792, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0085537433624268, "global_step": 591793, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0285515785217285, "global_step": 591794, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.100717067718506, "global_step": 591795, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.932943344116211, "global_step": 591796, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0782554149627686, "global_step": 591797, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0632474422454834, "global_step": 591798, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9383165836334229, "global_step": 591799, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.035278558731079, "global_step": 591800, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9726907014846802, "global_step": 591801, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9868043661117554, "global_step": 591802, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.032057762145996, "global_step": 591803, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9542003870010376, "global_step": 591804, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.07987904548645, "global_step": 591805, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0672528743743896, "global_step": 591806, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9814633131027222, "global_step": 591807, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9936364889144897, "global_step": 591808, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9610910415649414, "global_step": 591809, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.050422191619873, "global_step": 591810, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.072420358657837, "global_step": 591811, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.023961305618286, "global_step": 591812, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.103243827819824, "global_step": 591813, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9998712539672852, "global_step": 591814, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0694544315338135, "global_step": 591815, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.029297351837158, "global_step": 591816, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0094478130340576, "global_step": 591817, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.020968198776245, "global_step": 591818, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0632781982421875, "global_step": 591819, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0013301372528076, "global_step": 591820, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0480499267578125, "global_step": 591821, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1068010330200195, "global_step": 591822, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.058626890182495, "global_step": 591823, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.010756254196167, "global_step": 591824, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.030663251876831, "global_step": 591825, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.931129813194275, "global_step": 591826, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9860607385635376, "global_step": 591827, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0483787059783936, "global_step": 591828, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.047351360321045, "global_step": 591829, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.057877779006958, "global_step": 591830, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0353658199310303, "global_step": 591831, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.099249839782715, "global_step": 591832, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0506820678710938, "global_step": 591833, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.066129207611084, "global_step": 591834, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0040032863616943, "global_step": 591835, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1356441974639893, "global_step": 591836, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.977959156036377, "global_step": 591837, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.103463888168335, "global_step": 591838, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9986504316329956, "global_step": 591839, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9549559354782104, "global_step": 591840, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0111677646636963, "global_step": 591841, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.967045545578003, "global_step": 591842, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.91890287399292, "global_step": 591843, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0769169330596924, "global_step": 591844, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9978464841842651, "global_step": 591845, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.082613945007324, "global_step": 591846, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.023380994796753, "global_step": 591847, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0534133911132812, "global_step": 591848, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.03995943069458, "global_step": 591849, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.956167221069336, "global_step": 591850, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9561536312103271, "global_step": 591851, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9769160747528076, "global_step": 591852, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9864026308059692, "global_step": 591853, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9710546731948853, "global_step": 591854, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.009868621826172, "global_step": 591855, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9839236736297607, "global_step": 591856, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0243561267852783, "global_step": 591857, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0600063800811768, "global_step": 591858, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0236942768096924, "global_step": 591859, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.015233039855957, "global_step": 591860, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9914743900299072, "global_step": 591861, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0690362453460693, "global_step": 591862, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.026932716369629, "global_step": 591863, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0373036861419678, "global_step": 591864, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9985114336013794, "global_step": 591865, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9710850715637207, "global_step": 591866, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9981622695922852, "global_step": 591867, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.031769037246704, "global_step": 591868, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0293898582458496, "global_step": 591869, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.020986795425415, "global_step": 591870, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9566535949707031, "global_step": 591871, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9776538610458374, "global_step": 591872, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9488390684127808, "global_step": 591873, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.045840263366699, "global_step": 591874, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9675929546356201, "global_step": 591875, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.967999815940857, "global_step": 591876, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0604875087738037, "global_step": 591877, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9937416315078735, "global_step": 591878, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9603946208953857, "global_step": 591879, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9768030643463135, "global_step": 591880, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.015925407409668, "global_step": 591881, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.031343460083008, "global_step": 591882, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9632564783096313, "global_step": 591883, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0132365226745605, "global_step": 591884, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.03806734085083, "global_step": 591885, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0494561195373535, "global_step": 591886, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0029385089874268, "global_step": 591887, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0332610607147217, "global_step": 591888, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0002613067626953, "global_step": 591889, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.97567617893219, "global_step": 591890, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.061967611312866, "global_step": 591891, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.008662462234497, "global_step": 591892, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.955524206161499, "global_step": 591893, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0916411876678467, "global_step": 591894, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9531173706054688, "global_step": 591895, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0296823978424072, "global_step": 591896, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0002517700195312, "global_step": 591897, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.040611743927002, "global_step": 591898, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0732269287109375, "global_step": 591899, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.082099676132202, "global_step": 591900, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.023804187774658, "global_step": 591901, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.038334608078003, "global_step": 591902, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9839282035827637, "global_step": 591903, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.025212526321411, "global_step": 591904, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.029878854751587, "global_step": 591905, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9965922832489014, "global_step": 591906, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.8930959701538086, "global_step": 591907, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0640950202941895, "global_step": 591908, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0076003074645996, "global_step": 591909, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9490233659744263, "global_step": 591910, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0113439559936523, "global_step": 591911, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0220913887023926, "global_step": 591912, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.997967004776001, "global_step": 591913, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1266229152679443, "global_step": 591914, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9693089723587036, "global_step": 591915, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.974928855895996, "global_step": 591916, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.069873094558716, "global_step": 591917, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0043416023254395, "global_step": 591918, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9225404262542725, "global_step": 591919, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0069868564605713, "global_step": 591920, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.044477939605713, "global_step": 591921, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.080692768096924, "global_step": 591922, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.065189838409424, "global_step": 591923, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.093580484390259, "global_step": 591924, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.8926386833190918, "global_step": 591925, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0897953510284424, "global_step": 591926, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.965144395828247, "global_step": 591927, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0444283485412598, "global_step": 591928, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0012502670288086, "global_step": 591929, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.000103712081909, "global_step": 591930, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0059831142425537, "global_step": 591931, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.02618670463562, "global_step": 591932, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.019075632095337, "global_step": 591933, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.023298740386963, "global_step": 591934, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.958363652229309, "global_step": 591935, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9907463788986206, "global_step": 591936, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0055105686187744, "global_step": 591937, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9826686382293701, "global_step": 591938, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9920406341552734, "global_step": 591939, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.037550687789917, "global_step": 591940, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1678085327148438, "global_step": 591941, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0395724773406982, "global_step": 591942, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.082617998123169, "global_step": 591943, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.005406141281128, "global_step": 591944, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9888454675674438, "global_step": 591945, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.041712760925293, "global_step": 591946, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9655653238296509, "global_step": 591947, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9683479070663452, "global_step": 591948, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9962239265441895, "global_step": 591949, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9476231336593628, "global_step": 591950, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0028128623962402, "global_step": 591951, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.993981122970581, "global_step": 591952, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0647311210632324, "global_step": 591953, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.033806324005127, "global_step": 591954, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0092785358428955, "global_step": 591955, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.014357566833496, "global_step": 591956, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.024892807006836, "global_step": 591957, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1252999305725098, "global_step": 591958, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.059285879135132, "global_step": 591959, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.025228261947632, "global_step": 591960, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9973483085632324, "global_step": 591961, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9064931869506836, "global_step": 591962, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9791502952575684, "global_step": 591963, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0138657093048096, "global_step": 591964, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0939998626708984, "global_step": 591965, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9504883289337158, "global_step": 591966, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9719150066375732, "global_step": 591967, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0855090618133545, "global_step": 591968, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.159226179122925, "global_step": 591969, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9610036611557007, "global_step": 591970, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9935033321380615, "global_step": 591971, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0531978607177734, "global_step": 591972, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.070383310317993, "global_step": 591973, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9878636598587036, "global_step": 591974, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9660875797271729, "global_step": 591975, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.052205801010132, "global_step": 591976, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9494919776916504, "global_step": 591977, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.932300329208374, "global_step": 591978, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9332647323608398, "global_step": 591979, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.095160722732544, "global_step": 591980, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0452327728271484, "global_step": 591981, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0444374084472656, "global_step": 591982, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.01067852973938, "global_step": 591983, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9892562627792358, "global_step": 591984, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9981069564819336, "global_step": 591985, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0467922687530518, "global_step": 591986, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.972083568572998, "global_step": 591987, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0416762828826904, "global_step": 591988, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0537283420562744, "global_step": 591989, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0681638717651367, "global_step": 591990, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.058378219604492, "global_step": 591991, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.076949119567871, "global_step": 591992, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9287660121917725, "global_step": 591993, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9814417362213135, "global_step": 591994, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.975534439086914, "global_step": 591995, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.8667453527450562, "global_step": 591996, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0542824268341064, "global_step": 591997, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.047015905380249, "global_step": 591998, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0043909549713135, "global_step": 591999, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.954857587814331, "global_step": 592000, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0254433155059814, "global_step": 592001, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.048273801803589, "global_step": 592002, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9880645275115967, "global_step": 592003, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1378915309906006, "global_step": 592004, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.040348529815674, "global_step": 592005, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1232032775878906, "global_step": 592006, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.042217493057251, "global_step": 592007, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0132200717926025, "global_step": 592008, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.030627965927124, "global_step": 592009, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0573201179504395, "global_step": 592010, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.965240478515625, "global_step": 592011, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9672858715057373, "global_step": 592012, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9481606483459473, "global_step": 592013, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0204806327819824, "global_step": 592014, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.089542865753174, "global_step": 592015, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9908281564712524, "global_step": 592016, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0294976234436035, "global_step": 592017, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.056020975112915, "global_step": 592018, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9822829961776733, "global_step": 592019, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.009678363800049, "global_step": 592020, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9286372661590576, "global_step": 592021, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.039855480194092, "global_step": 592022, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.991685152053833, "global_step": 592023, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0298194885253906, "global_step": 592024, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.113739490509033, "global_step": 592025, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.054023027420044, "global_step": 592026, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.943472146987915, "global_step": 592027, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.082650899887085, "global_step": 592028, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0313539505004883, "global_step": 592029, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0141496658325195, "global_step": 592030, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.050480604171753, "global_step": 592031, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0431272983551025, "global_step": 592032, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.022252321243286, "global_step": 592033, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9280587434768677, "global_step": 592034, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.054199695587158, "global_step": 592035, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.091116189956665, "global_step": 592036, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9920824766159058, "global_step": 592037, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0283730030059814, "global_step": 592038, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.941851258277893, "global_step": 592039, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9551447629928589, "global_step": 592040, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.986948013305664, "global_step": 592041, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9458210468292236, "global_step": 592042, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9877676963806152, "global_step": 592043, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0027096271514893, "global_step": 592044, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0119876861572266, "global_step": 592045, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0387284755706787, "global_step": 592046, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0202927589416504, "global_step": 592047, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0255303382873535, "global_step": 592048, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0536229610443115, "global_step": 592049, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9910534620285034, "global_step": 592050, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.997696042060852, "global_step": 592051, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.054121732711792, "global_step": 592052, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.959015130996704, "global_step": 592053, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0580697059631348, "global_step": 592054, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.042154312133789, "global_step": 592055, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9491010904312134, "global_step": 592056, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9474875926971436, "global_step": 592057, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0416476726531982, "global_step": 592058, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9220951795578003, "global_step": 592059, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.006953001022339, "global_step": 592060, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0330750942230225, "global_step": 592061, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9283851385116577, "global_step": 592062, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0159008502960205, "global_step": 592063, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9666969776153564, "global_step": 592064, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0615105628967285, "global_step": 592065, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.043761968612671, "global_step": 592066, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.045252561569214, "global_step": 592067, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.055790424346924, "global_step": 592068, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0831706523895264, "global_step": 592069, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0808749198913574, "global_step": 592070, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9747319221496582, "global_step": 592071, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.999091625213623, "global_step": 592072, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0388193130493164, "global_step": 592073, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.00581693649292, "global_step": 592074, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0076723098754883, "global_step": 592075, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.077019214630127, "global_step": 592076, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.031294584274292, "global_step": 592077, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.121793031692505, "global_step": 592078, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9614540338516235, "global_step": 592079, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.000439167022705, "global_step": 592080, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0443520545959473, "global_step": 592081, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9637346267700195, "global_step": 592082, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0147550106048584, "global_step": 592083, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9905202388763428, "global_step": 592084, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.995902180671692, "global_step": 592085, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0441083908081055, "global_step": 592086, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.014113426208496, "global_step": 592087, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9162901639938354, "global_step": 592088, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9593256711959839, "global_step": 592089, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0417048931121826, "global_step": 592090, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0316410064697266, "global_step": 592091, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0183615684509277, "global_step": 592092, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.115708112716675, "global_step": 592093, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0022387504577637, "global_step": 592094, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.012843608856201, "global_step": 592095, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0844786167144775, "global_step": 592096, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1328179836273193, "global_step": 592097, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.013298273086548, "global_step": 592098, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.017622470855713, "global_step": 592099, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.059295177459717, "global_step": 592100, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9959574937820435, "global_step": 592101, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9939780235290527, "global_step": 592102, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0801963806152344, "global_step": 592103, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0643057823181152, "global_step": 592104, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9876182079315186, "global_step": 592105, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0229434967041016, "global_step": 592106, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9968205690383911, "global_step": 592107, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.038543224334717, "global_step": 592108, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0367064476013184, "global_step": 592109, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9759891033172607, "global_step": 592110, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.090869903564453, "global_step": 592111, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9739936590194702, "global_step": 592112, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0209503173828125, "global_step": 592113, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1076607704162598, "global_step": 592114, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0191354751586914, "global_step": 592115, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0637521743774414, "global_step": 592116, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.027045726776123, "global_step": 592117, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1104798316955566, "global_step": 592118, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0653979778289795, "global_step": 592119, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0625228881835938, "global_step": 592120, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9474111795425415, "global_step": 592121, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.014268159866333, "global_step": 592122, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9301843643188477, "global_step": 592123, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.021120548248291, "global_step": 592124, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.099865674972534, "global_step": 592125, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0528433322906494, "global_step": 592126, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0031659603118896, "global_step": 592127, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.032574415206909, "global_step": 592128, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9990482330322266, "global_step": 592129, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0112829208374023, "global_step": 592130, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0238161087036133, "global_step": 592131, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0774333477020264, "global_step": 592132, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.140683889389038, "global_step": 592133, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0741331577301025, "global_step": 592134, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.044257640838623, "global_step": 592135, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1102373600006104, "global_step": 592136, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0369651317596436, "global_step": 592137, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.000079870223999, "global_step": 592138, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0174951553344727, "global_step": 592139, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.131580114364624, "global_step": 592140, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.03352689743042, "global_step": 592141, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.023050308227539, "global_step": 592142, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.007026195526123, "global_step": 592143, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0461506843566895, "global_step": 592144, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.08782696723938, "global_step": 592145, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0041770935058594, "global_step": 592146, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1638224124908447, "global_step": 592147, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0324807167053223, "global_step": 592148, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0472147464752197, "global_step": 592149, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.133507490158081, "global_step": 592150, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0431017875671387, "global_step": 592151, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9920094013214111, "global_step": 592152, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1111907958984375, "global_step": 592153, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0495247840881348, "global_step": 592154, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1259305477142334, "global_step": 592155, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.01716685295105, "global_step": 592156, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1006338596343994, "global_step": 592157, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9907838106155396, "global_step": 592158, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0507237911224365, "global_step": 592159, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0416982173919678, "global_step": 592160, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0598928928375244, "global_step": 592161, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.042158603668213, "global_step": 592162, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.1067492961883545, "global_step": 592163, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.979324221611023, "global_step": 592164, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.016935110092163, "global_step": 592165, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.954613447189331, "global_step": 592166, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.06315541267395, "global_step": 592167, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0119359493255615, "global_step": 592168, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0113742351531982, "global_step": 592169, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9003502130508423, "global_step": 592170, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.110128879547119, "global_step": 592171, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.084883451461792, "global_step": 592172, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0422449111938477, "global_step": 592173, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9496136903762817, "global_step": 592174, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.03647518157959, "global_step": 592175, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0469722747802734, "global_step": 592176, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.070066213607788, "global_step": 592177, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.091872215270996, "global_step": 592178, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.060188055038452, "global_step": 592179, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.929879069328308, "global_step": 592180, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.056737184524536, "global_step": 592181, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.013356924057007, "global_step": 592182, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.112762689590454, "global_step": 592183, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.124737501144409, "global_step": 592184, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0715763568878174, "global_step": 592185, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9632824659347534, "global_step": 592186, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.002816677093506, "global_step": 592187, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0558602809906006, "global_step": 592188, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.9923349618911743, "global_step": 592189, "epoch": 960, "lr": 5e-05}
{"train_loss": 1.8934352397918701, "global_step": 592190, "epoch": 960, "lr": 5e-05}
{"train_loss": 2.0165483951568604, "global_step": 592191, "epoch": 960, "lr": 5e-05, "val_loss": 5.793044567108154, "test_reconst_mse": 0.07376902550458908}
{"train_loss": 2.0317084789276123, "global_step": 592192, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0533998012542725, "global_step": 592193, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9747304916381836, "global_step": 592194, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.040239095687866, "global_step": 592195, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.018092632293701, "global_step": 592196, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0296988487243652, "global_step": 592197, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0648438930511475, "global_step": 592198, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.154067039489746, "global_step": 592199, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0110301971435547, "global_step": 592200, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9775323867797852, "global_step": 592201, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9504162073135376, "global_step": 592202, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9938026666641235, "global_step": 592203, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0824058055877686, "global_step": 592204, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9615970849990845, "global_step": 592205, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0462985038757324, "global_step": 592206, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.034625768661499, "global_step": 592207, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9689902067184448, "global_step": 592208, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9031308889389038, "global_step": 592209, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.988722801208496, "global_step": 592210, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9431915283203125, "global_step": 592211, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0594191551208496, "global_step": 592212, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0541577339172363, "global_step": 592213, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.05051589012146, "global_step": 592214, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0626108646392822, "global_step": 592215, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9587589502334595, "global_step": 592216, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9060101509094238, "global_step": 592217, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.017435312271118, "global_step": 592218, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9554741382598877, "global_step": 592219, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0599138736724854, "global_step": 592220, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9351109266281128, "global_step": 592221, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.006793260574341, "global_step": 592222, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.004751205444336, "global_step": 592223, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9562255144119263, "global_step": 592224, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0343594551086426, "global_step": 592225, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9742087125778198, "global_step": 592226, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0071845054626465, "global_step": 592227, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9616212844848633, "global_step": 592228, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9719501733779907, "global_step": 592229, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9973363876342773, "global_step": 592230, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.050427198410034, "global_step": 592231, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9642906188964844, "global_step": 592232, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.032745122909546, "global_step": 592233, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.116969347000122, "global_step": 592234, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9986815452575684, "global_step": 592235, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9594613313674927, "global_step": 592236, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9933942556381226, "global_step": 592237, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9552069902420044, "global_step": 592238, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.024683713912964, "global_step": 592239, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.097207546234131, "global_step": 592240, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0494635105133057, "global_step": 592241, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9075942039489746, "global_step": 592242, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.1034274101257324, "global_step": 592243, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.138357162475586, "global_step": 592244, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9693806171417236, "global_step": 592245, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0261220932006836, "global_step": 592246, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9979350566864014, "global_step": 592247, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.081063747406006, "global_step": 592248, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.947782039642334, "global_step": 592249, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.025613784790039, "global_step": 592250, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0751686096191406, "global_step": 592251, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0162079334259033, "global_step": 592252, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9587515592575073, "global_step": 592253, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0304315090179443, "global_step": 592254, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.006059408187866, "global_step": 592255, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0710628032684326, "global_step": 592256, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0192301273345947, "global_step": 592257, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9879097938537598, "global_step": 592258, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0418214797973633, "global_step": 592259, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9395177364349365, "global_step": 592260, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.033959150314331, "global_step": 592261, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9355669021606445, "global_step": 592262, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9986408948898315, "global_step": 592263, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0132899284362793, "global_step": 592264, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0653154850006104, "global_step": 592265, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.912205696105957, "global_step": 592266, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.1143877506256104, "global_step": 592267, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0684046745300293, "global_step": 592268, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0554423332214355, "global_step": 592269, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.046816349029541, "global_step": 592270, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.021937608718872, "global_step": 592271, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.028306722640991, "global_step": 592272, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9670031070709229, "global_step": 592273, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9455238580703735, "global_step": 592274, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.952778697013855, "global_step": 592275, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9733058214187622, "global_step": 592276, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0359997749328613, "global_step": 592277, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.096017837524414, "global_step": 592278, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.02825927734375, "global_step": 592279, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9283376932144165, "global_step": 592280, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.069037914276123, "global_step": 592281, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0227713584899902, "global_step": 592282, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.953426718711853, "global_step": 592283, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.047236919403076, "global_step": 592284, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9850826263427734, "global_step": 592285, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0069591999053955, "global_step": 592286, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9895250797271729, "global_step": 592287, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0183358192443848, "global_step": 592288, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.051497220993042, "global_step": 592289, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9787368774414062, "global_step": 592290, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.047065496444702, "global_step": 592291, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.055549144744873, "global_step": 592292, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9363631010055542, "global_step": 592293, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9601085186004639, "global_step": 592294, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.009807586669922, "global_step": 592295, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0652737617492676, "global_step": 592296, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0154001712799072, "global_step": 592297, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.11789870262146, "global_step": 592298, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.95233154296875, "global_step": 592299, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.987717628479004, "global_step": 592300, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0430591106414795, "global_step": 592301, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0290627479553223, "global_step": 592302, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.014890432357788, "global_step": 592303, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0272252559661865, "global_step": 592304, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.003133535385132, "global_step": 592305, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0323638916015625, "global_step": 592306, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0237107276916504, "global_step": 592307, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.990381121635437, "global_step": 592308, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.100403070449829, "global_step": 592309, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9888709783554077, "global_step": 592310, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0675272941589355, "global_step": 592311, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0361268520355225, "global_step": 592312, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.95701003074646, "global_step": 592313, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9870595932006836, "global_step": 592314, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9156279563903809, "global_step": 592315, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9782536029815674, "global_step": 592316, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0258283615112305, "global_step": 592317, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.93488609790802, "global_step": 592318, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0472092628479004, "global_step": 592319, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0375099182128906, "global_step": 592320, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.044847249984741, "global_step": 592321, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.069000482559204, "global_step": 592322, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.033520221710205, "global_step": 592323, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9714676141738892, "global_step": 592324, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.003154993057251, "global_step": 592325, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9033637046813965, "global_step": 592326, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0099213123321533, "global_step": 592327, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.973662257194519, "global_step": 592328, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9624371528625488, "global_step": 592329, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.967584252357483, "global_step": 592330, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9762235879898071, "global_step": 592331, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0536577701568604, "global_step": 592332, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9386144876480103, "global_step": 592333, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0724360942840576, "global_step": 592334, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.086946725845337, "global_step": 592335, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0028533935546875, "global_step": 592336, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.028796672821045, "global_step": 592337, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0506200790405273, "global_step": 592338, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0306756496429443, "global_step": 592339, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0350894927978516, "global_step": 592340, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.073265314102173, "global_step": 592341, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9823877811431885, "global_step": 592342, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0312094688415527, "global_step": 592343, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.988879680633545, "global_step": 592344, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.04193377494812, "global_step": 592345, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.918006181716919, "global_step": 592346, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.954342007637024, "global_step": 592347, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.014251470565796, "global_step": 592348, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.015321731567383, "global_step": 592349, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.013343334197998, "global_step": 592350, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.985054850578308, "global_step": 592351, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.989197015762329, "global_step": 592352, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9949970245361328, "global_step": 592353, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0054421424865723, "global_step": 592354, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.987452745437622, "global_step": 592355, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.012444496154785, "global_step": 592356, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0139577388763428, "global_step": 592357, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.034837245941162, "global_step": 592358, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.046691656112671, "global_step": 592359, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.02140736579895, "global_step": 592360, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0262346267700195, "global_step": 592361, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0155723094940186, "global_step": 592362, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0597052574157715, "global_step": 592363, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0386064052581787, "global_step": 592364, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0146920680999756, "global_step": 592365, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9443169832229614, "global_step": 592366, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.114158868789673, "global_step": 592367, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9828892946243286, "global_step": 592368, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9972894191741943, "global_step": 592369, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9749457836151123, "global_step": 592370, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9758219718933105, "global_step": 592371, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.100080966949463, "global_step": 592372, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.057781457901001, "global_step": 592373, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9571603536605835, "global_step": 592374, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0447466373443604, "global_step": 592375, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0490305423736572, "global_step": 592376, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9771997928619385, "global_step": 592377, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9305543899536133, "global_step": 592378, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0471439361572266, "global_step": 592379, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9804667234420776, "global_step": 592380, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.066359758377075, "global_step": 592381, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.1086716651916504, "global_step": 592382, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.078387498855591, "global_step": 592383, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.029033899307251, "global_step": 592384, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.004718780517578, "global_step": 592385, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0740737915039062, "global_step": 592386, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.973044514656067, "global_step": 592387, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.033433675765991, "global_step": 592388, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.015312433242798, "global_step": 592389, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9543797969818115, "global_step": 592390, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.064256191253662, "global_step": 592391, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9961351156234741, "global_step": 592392, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0522959232330322, "global_step": 592393, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.084912061691284, "global_step": 592394, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.078352451324463, "global_step": 592395, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9644522666931152, "global_step": 592396, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9856269359588623, "global_step": 592397, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.006398916244507, "global_step": 592398, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0238037109375, "global_step": 592399, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.005941867828369, "global_step": 592400, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0066616535186768, "global_step": 592401, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.069070339202881, "global_step": 592402, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.000040292739868, "global_step": 592403, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0301499366760254, "global_step": 592404, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9942773580551147, "global_step": 592405, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0058484077453613, "global_step": 592406, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.925406575202942, "global_step": 592407, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0000288486480713, "global_step": 592408, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.063063859939575, "global_step": 592409, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0351321697235107, "global_step": 592410, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0243587493896484, "global_step": 592411, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0813074111938477, "global_step": 592412, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0523197650909424, "global_step": 592413, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.983522653579712, "global_step": 592414, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.016975164413452, "global_step": 592415, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9715845584869385, "global_step": 592416, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.02909255027771, "global_step": 592417, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.014292001724243, "global_step": 592418, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9711058139801025, "global_step": 592419, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9441248178482056, "global_step": 592420, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.036001443862915, "global_step": 592421, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.972694993019104, "global_step": 592422, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9372470378875732, "global_step": 592423, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0370285511016846, "global_step": 592424, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9654752016067505, "global_step": 592425, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9968916177749634, "global_step": 592426, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0180840492248535, "global_step": 592427, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0506980419158936, "global_step": 592428, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.008399724960327, "global_step": 592429, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0273075103759766, "global_step": 592430, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.1004300117492676, "global_step": 592431, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0302207469940186, "global_step": 592432, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9822365045547485, "global_step": 592433, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.027693510055542, "global_step": 592434, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0184383392333984, "global_step": 592435, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9956947565078735, "global_step": 592436, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9272682666778564, "global_step": 592437, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0526819229125977, "global_step": 592438, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0067954063415527, "global_step": 592439, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9911702871322632, "global_step": 592440, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9646434783935547, "global_step": 592441, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9732041358947754, "global_step": 592442, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.071636438369751, "global_step": 592443, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0702805519104004, "global_step": 592444, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9565082788467407, "global_step": 592445, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0561225414276123, "global_step": 592446, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0017504692077637, "global_step": 592447, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.014371156692505, "global_step": 592448, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0427989959716797, "global_step": 592449, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0634708404541016, "global_step": 592450, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0792348384857178, "global_step": 592451, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.988182544708252, "global_step": 592452, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0517425537109375, "global_step": 592453, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9544668197631836, "global_step": 592454, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.041609287261963, "global_step": 592455, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.089327335357666, "global_step": 592456, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9772392511367798, "global_step": 592457, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.937776803970337, "global_step": 592458, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.014500856399536, "global_step": 592459, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.080702781677246, "global_step": 592460, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.072026252746582, "global_step": 592461, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.047152519226074, "global_step": 592462, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0495352745056152, "global_step": 592463, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9721759557724, "global_step": 592464, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9707458019256592, "global_step": 592465, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9367632865905762, "global_step": 592466, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.115638256072998, "global_step": 592467, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9597911834716797, "global_step": 592468, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0701870918273926, "global_step": 592469, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9042941331863403, "global_step": 592470, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.095707893371582, "global_step": 592471, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.1101672649383545, "global_step": 592472, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.035734176635742, "global_step": 592473, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0094101428985596, "global_step": 592474, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9197666645050049, "global_step": 592475, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0657100677490234, "global_step": 592476, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9499419927597046, "global_step": 592477, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0417277812957764, "global_step": 592478, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0241353511810303, "global_step": 592479, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0080461502075195, "global_step": 592480, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.064260482788086, "global_step": 592481, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.015000343322754, "global_step": 592482, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0431721210479736, "global_step": 592483, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0384926795959473, "global_step": 592484, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0354959964752197, "global_step": 592485, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0093278884887695, "global_step": 592486, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.054182291030884, "global_step": 592487, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9396260976791382, "global_step": 592488, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0155346393585205, "global_step": 592489, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9004820585250854, "global_step": 592490, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9836628437042236, "global_step": 592491, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.928720474243164, "global_step": 592492, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9622563123703003, "global_step": 592493, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0521366596221924, "global_step": 592494, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.968472957611084, "global_step": 592495, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0128486156463623, "global_step": 592496, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0661213397979736, "global_step": 592497, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9963881969451904, "global_step": 592498, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9725292921066284, "global_step": 592499, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.022838830947876, "global_step": 592500, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0037851333618164, "global_step": 592501, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.072993040084839, "global_step": 592502, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0207934379577637, "global_step": 592503, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0368802547454834, "global_step": 592504, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9660555124282837, "global_step": 592505, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.045783758163452, "global_step": 592506, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0322482585906982, "global_step": 592507, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0487184524536133, "global_step": 592508, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0293800830841064, "global_step": 592509, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9762746095657349, "global_step": 592510, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0219855308532715, "global_step": 592511, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.077979326248169, "global_step": 592512, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0092296600341797, "global_step": 592513, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.975145936012268, "global_step": 592514, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0917394161224365, "global_step": 592515, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.150909662246704, "global_step": 592516, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0346667766571045, "global_step": 592517, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.014319896697998, "global_step": 592518, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0153207778930664, "global_step": 592519, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0993590354919434, "global_step": 592520, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9741530418395996, "global_step": 592521, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.105746269226074, "global_step": 592522, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.063910722732544, "global_step": 592523, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.970828652381897, "global_step": 592524, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9442589282989502, "global_step": 592525, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9181523323059082, "global_step": 592526, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.000607967376709, "global_step": 592527, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.050541877746582, "global_step": 592528, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9266700744628906, "global_step": 592529, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0161819458007812, "global_step": 592530, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9659290313720703, "global_step": 592531, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9992414712905884, "global_step": 592532, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.038389205932617, "global_step": 592533, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0661401748657227, "global_step": 592534, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0976946353912354, "global_step": 592535, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9527384042739868, "global_step": 592536, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0505895614624023, "global_step": 592537, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9463914632797241, "global_step": 592538, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9261609315872192, "global_step": 592539, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.924964189529419, "global_step": 592540, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0025248527526855, "global_step": 592541, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9429723024368286, "global_step": 592542, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9995671510696411, "global_step": 592543, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.00112247467041, "global_step": 592544, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.065061569213867, "global_step": 592545, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0039732456207275, "global_step": 592546, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0384085178375244, "global_step": 592547, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.050264596939087, "global_step": 592548, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.040930986404419, "global_step": 592549, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.032388210296631, "global_step": 592550, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9731535911560059, "global_step": 592551, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.016072988510132, "global_step": 592552, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0942533016204834, "global_step": 592553, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.997828483581543, "global_step": 592554, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0671966075897217, "global_step": 592555, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0539228916168213, "global_step": 592556, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0039682388305664, "global_step": 592557, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.996260166168213, "global_step": 592558, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.035991907119751, "global_step": 592559, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0459144115448, "global_step": 592560, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.037144184112549, "global_step": 592561, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0584940910339355, "global_step": 592562, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.013385772705078, "global_step": 592563, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.062396287918091, "global_step": 592564, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.020681381225586, "global_step": 592565, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9736005067825317, "global_step": 592566, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9188233613967896, "global_step": 592567, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0732614994049072, "global_step": 592568, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.059802293777466, "global_step": 592569, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0644748210906982, "global_step": 592570, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.1133384704589844, "global_step": 592571, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0621044635772705, "global_step": 592572, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.023909568786621, "global_step": 592573, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9420676231384277, "global_step": 592574, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0625288486480713, "global_step": 592575, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9745608568191528, "global_step": 592576, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9996509552001953, "global_step": 592577, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.989683985710144, "global_step": 592578, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9878796339035034, "global_step": 592579, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9239933490753174, "global_step": 592580, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.05287504196167, "global_step": 592581, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9624571800231934, "global_step": 592582, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.994978904724121, "global_step": 592583, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0703225135803223, "global_step": 592584, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0598628520965576, "global_step": 592585, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9567636251449585, "global_step": 592586, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9904403686523438, "global_step": 592587, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.978035569190979, "global_step": 592588, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.038477897644043, "global_step": 592589, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0700042247772217, "global_step": 592590, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0029561519622803, "global_step": 592591, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.066103935241699, "global_step": 592592, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9641011953353882, "global_step": 592593, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.995251178741455, "global_step": 592594, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.040877342224121, "global_step": 592595, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0635340213775635, "global_step": 592596, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0663633346557617, "global_step": 592597, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0394420623779297, "global_step": 592598, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.117298126220703, "global_step": 592599, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.053990364074707, "global_step": 592600, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.037489652633667, "global_step": 592601, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9593801498413086, "global_step": 592602, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9938526153564453, "global_step": 592603, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0462582111358643, "global_step": 592604, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0022664070129395, "global_step": 592605, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.063565254211426, "global_step": 592606, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0112671852111816, "global_step": 592607, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0097930431365967, "global_step": 592608, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0102322101593018, "global_step": 592609, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.1002681255340576, "global_step": 592610, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9313024282455444, "global_step": 592611, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9396730661392212, "global_step": 592612, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9987130165100098, "global_step": 592613, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9679477214813232, "global_step": 592614, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.007829189300537, "global_step": 592615, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.981020212173462, "global_step": 592616, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0208349227905273, "global_step": 592617, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0740292072296143, "global_step": 592618, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.026840925216675, "global_step": 592619, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0120954513549805, "global_step": 592620, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0843613147735596, "global_step": 592621, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0162672996520996, "global_step": 592622, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.991597056388855, "global_step": 592623, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9063385725021362, "global_step": 592624, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0870964527130127, "global_step": 592625, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0541582107543945, "global_step": 592626, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.991833209991455, "global_step": 592627, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0076818466186523, "global_step": 592628, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9886091947555542, "global_step": 592629, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.035173177719116, "global_step": 592630, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.998488426208496, "global_step": 592631, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.049832344055176, "global_step": 592632, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9307293891906738, "global_step": 592633, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.100205898284912, "global_step": 592634, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0370664596557617, "global_step": 592635, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.083468437194824, "global_step": 592636, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.017409563064575, "global_step": 592637, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.002647638320923, "global_step": 592638, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9493205547332764, "global_step": 592639, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0649683475494385, "global_step": 592640, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.005784034729004, "global_step": 592641, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.093958854675293, "global_step": 592642, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.048328161239624, "global_step": 592643, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.096662998199463, "global_step": 592644, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.984263300895691, "global_step": 592645, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.050459623336792, "global_step": 592646, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9725489616394043, "global_step": 592647, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0112245082855225, "global_step": 592648, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0392844676971436, "global_step": 592649, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.069279670715332, "global_step": 592650, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0090060234069824, "global_step": 592651, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0332283973693848, "global_step": 592652, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9944287538528442, "global_step": 592653, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.063901424407959, "global_step": 592654, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.01926851272583, "global_step": 592655, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9708693027496338, "global_step": 592656, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.003833055496216, "global_step": 592657, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0470120906829834, "global_step": 592658, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.91517972946167, "global_step": 592659, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.02713942527771, "global_step": 592660, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0005667209625244, "global_step": 592661, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.002279758453369, "global_step": 592662, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.1205081939697266, "global_step": 592663, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0557398796081543, "global_step": 592664, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.051923990249634, "global_step": 592665, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.085242986679077, "global_step": 592666, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0150327682495117, "global_step": 592667, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.1392316818237305, "global_step": 592668, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.112696409225464, "global_step": 592669, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9376609325408936, "global_step": 592670, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9998623132705688, "global_step": 592671, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.1106855869293213, "global_step": 592672, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0204319953918457, "global_step": 592673, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9776558876037598, "global_step": 592674, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.006772518157959, "global_step": 592675, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.007270336151123, "global_step": 592676, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0548088550567627, "global_step": 592677, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0325517654418945, "global_step": 592678, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0286812782287598, "global_step": 592679, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9710984230041504, "global_step": 592680, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.095308542251587, "global_step": 592681, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.978035569190979, "global_step": 592682, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0700974464416504, "global_step": 592683, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9731277227401733, "global_step": 592684, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0325822830200195, "global_step": 592685, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.984604835510254, "global_step": 592686, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.101696014404297, "global_step": 592687, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9265661239624023, "global_step": 592688, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0552940368652344, "global_step": 592689, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9661126136779785, "global_step": 592690, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9860631227493286, "global_step": 592691, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.048985481262207, "global_step": 592692, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9849770069122314, "global_step": 592693, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9451887607574463, "global_step": 592694, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0337700843811035, "global_step": 592695, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.042121648788452, "global_step": 592696, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.006657361984253, "global_step": 592697, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9738694429397583, "global_step": 592698, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.029531717300415, "global_step": 592699, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0514025688171387, "global_step": 592700, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0384597778320312, "global_step": 592701, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.037745237350464, "global_step": 592702, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0270919799804688, "global_step": 592703, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.113870859146118, "global_step": 592704, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.051295280456543, "global_step": 592705, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9828494787216187, "global_step": 592706, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9615271091461182, "global_step": 592707, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.970820665359497, "global_step": 592708, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0896944999694824, "global_step": 592709, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9960709810256958, "global_step": 592710, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9939073324203491, "global_step": 592711, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9643844366073608, "global_step": 592712, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.043006658554077, "global_step": 592713, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0081279277801514, "global_step": 592714, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0241241455078125, "global_step": 592715, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9907585382461548, "global_step": 592716, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.021454095840454, "global_step": 592717, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.969970464706421, "global_step": 592718, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.058318853378296, "global_step": 592719, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0694100856781006, "global_step": 592720, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0854315757751465, "global_step": 592721, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.004077911376953, "global_step": 592722, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.056361436843872, "global_step": 592723, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0041913986206055, "global_step": 592724, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.034062623977661, "global_step": 592725, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9469581842422485, "global_step": 592726, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.969383955001831, "global_step": 592727, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9658222198486328, "global_step": 592728, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.077132225036621, "global_step": 592729, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0393221378326416, "global_step": 592730, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.984799861907959, "global_step": 592731, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.984626054763794, "global_step": 592732, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.1003286838531494, "global_step": 592733, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9831898212432861, "global_step": 592734, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9607616662979126, "global_step": 592735, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.067335605621338, "global_step": 592736, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.012521743774414, "global_step": 592737, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9622974395751953, "global_step": 592738, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.078108072280884, "global_step": 592739, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9908757209777832, "global_step": 592740, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.016247034072876, "global_step": 592741, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0716187953948975, "global_step": 592742, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0817980766296387, "global_step": 592743, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.108238697052002, "global_step": 592744, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9334722757339478, "global_step": 592745, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.035649538040161, "global_step": 592746, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.050581216812134, "global_step": 592747, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0091655254364014, "global_step": 592748, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.019379138946533, "global_step": 592749, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0246565341949463, "global_step": 592750, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9967434406280518, "global_step": 592751, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0039374828338623, "global_step": 592752, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0613865852355957, "global_step": 592753, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.023702383041382, "global_step": 592754, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0839922428131104, "global_step": 592755, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0700020790100098, "global_step": 592756, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.060964584350586, "global_step": 592757, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9300076961517334, "global_step": 592758, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.023296356201172, "global_step": 592759, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.983786940574646, "global_step": 592760, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9543442726135254, "global_step": 592761, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9690051078796387, "global_step": 592762, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9813954830169678, "global_step": 592763, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9956562519073486, "global_step": 592764, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0069947242736816, "global_step": 592765, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0000596046447754, "global_step": 592766, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.027038097381592, "global_step": 592767, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0686817169189453, "global_step": 592768, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0229547023773193, "global_step": 592769, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0535202026367188, "global_step": 592770, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9969333410263062, "global_step": 592771, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9529826641082764, "global_step": 592772, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0723423957824707, "global_step": 592773, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9460569620132446, "global_step": 592774, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.057175636291504, "global_step": 592775, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9722872972488403, "global_step": 592776, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.020596742630005, "global_step": 592777, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.971997618675232, "global_step": 592778, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9330389499664307, "global_step": 592779, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.037161350250244, "global_step": 592780, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.027487277984619, "global_step": 592781, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0778346061706543, "global_step": 592782, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9925018548965454, "global_step": 592783, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9938709735870361, "global_step": 592784, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.070282220840454, "global_step": 592785, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.026341199874878, "global_step": 592786, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0632245540618896, "global_step": 592787, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9695717096328735, "global_step": 592788, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0963432788848877, "global_step": 592789, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.076772451400757, "global_step": 592790, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.011911630630493, "global_step": 592791, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0133373737335205, "global_step": 592792, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.122649908065796, "global_step": 592793, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.055922269821167, "global_step": 592794, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9322644472122192, "global_step": 592795, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0348052978515625, "global_step": 592796, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0369081497192383, "global_step": 592797, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9326632022857666, "global_step": 592798, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0537426471710205, "global_step": 592799, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0907375812530518, "global_step": 592800, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.089749336242676, "global_step": 592801, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0528159141540527, "global_step": 592802, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.01120662689209, "global_step": 592803, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0140621662139893, "global_step": 592804, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.074601173400879, "global_step": 592805, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0812737941741943, "global_step": 592806, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9631520509719849, "global_step": 592807, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0111820697784424, "global_step": 592808, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0652873516082764, "global_step": 592809, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.980832576751709, "global_step": 592810, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.016526460647583, "global_step": 592811, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9755815267562866, "global_step": 592812, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9834977388381958, "global_step": 592813, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9926060438156128, "global_step": 592814, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0290582180023193, "global_step": 592815, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.06364369392395, "global_step": 592816, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.059602975845337, "global_step": 592817, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.089124917984009, "global_step": 592818, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.041311740875244, "global_step": 592819, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.018737316131592, "global_step": 592820, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0015814304351807, "global_step": 592821, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.057158946990967, "global_step": 592822, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9706482887268066, "global_step": 592823, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.012173891067505, "global_step": 592824, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0056371688842773, "global_step": 592825, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.018744468688965, "global_step": 592826, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.954333782196045, "global_step": 592827, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.031559944152832, "global_step": 592828, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9629862308502197, "global_step": 592829, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.002657175064087, "global_step": 592830, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9892971515655518, "global_step": 592831, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0435292720794678, "global_step": 592832, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.121717929840088, "global_step": 592833, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.018709659576416, "global_step": 592834, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.983723759651184, "global_step": 592835, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.1078553199768066, "global_step": 592836, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.04679274559021, "global_step": 592837, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0358290672302246, "global_step": 592838, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0321710109710693, "global_step": 592839, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9759521484375, "global_step": 592840, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.069664239883423, "global_step": 592841, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9919264316558838, "global_step": 592842, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0328774452209473, "global_step": 592843, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9795260429382324, "global_step": 592844, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0425033569335938, "global_step": 592845, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.076117515563965, "global_step": 592846, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9845330715179443, "global_step": 592847, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0145678520202637, "global_step": 592848, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.06683087348938, "global_step": 592849, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9878783226013184, "global_step": 592850, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.000467300415039, "global_step": 592851, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0878713130950928, "global_step": 592852, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0641555786132812, "global_step": 592853, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9956210851669312, "global_step": 592854, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.008592367172241, "global_step": 592855, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0878427028656006, "global_step": 592856, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0771989822387695, "global_step": 592857, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9903008937835693, "global_step": 592858, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.990296721458435, "global_step": 592859, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.022822618484497, "global_step": 592860, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9801939725875854, "global_step": 592861, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.950634479522705, "global_step": 592862, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9630964994430542, "global_step": 592863, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9775594472885132, "global_step": 592864, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9875315427780151, "global_step": 592865, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0126001834869385, "global_step": 592866, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.026703119277954, "global_step": 592867, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.918789029121399, "global_step": 592868, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0511252880096436, "global_step": 592869, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0808746814727783, "global_step": 592870, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9851239919662476, "global_step": 592871, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9752882719039917, "global_step": 592872, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9397050142288208, "global_step": 592873, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0914835929870605, "global_step": 592874, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9763009548187256, "global_step": 592875, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.00464129447937, "global_step": 592876, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.8885588645935059, "global_step": 592877, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.05517578125, "global_step": 592878, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0159833431243896, "global_step": 592879, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.983566164970398, "global_step": 592880, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.029947280883789, "global_step": 592881, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.046186923980713, "global_step": 592882, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0496554374694824, "global_step": 592883, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.065403938293457, "global_step": 592884, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9789153337478638, "global_step": 592885, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0150439739227295, "global_step": 592886, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0370917320251465, "global_step": 592887, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.016767978668213, "global_step": 592888, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.069571018218994, "global_step": 592889, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.996579885482788, "global_step": 592890, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9414814710617065, "global_step": 592891, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.008012533187866, "global_step": 592892, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.044009208679199, "global_step": 592893, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.112887144088745, "global_step": 592894, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.070814847946167, "global_step": 592895, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0293235778808594, "global_step": 592896, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9599206447601318, "global_step": 592897, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9775474071502686, "global_step": 592898, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0354886054992676, "global_step": 592899, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0342743396759033, "global_step": 592900, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0491645336151123, "global_step": 592901, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.993077039718628, "global_step": 592902, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.995221495628357, "global_step": 592903, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.96040678024292, "global_step": 592904, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.973564624786377, "global_step": 592905, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9628188610076904, "global_step": 592906, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.018761157989502, "global_step": 592907, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0436739921569824, "global_step": 592908, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0285165309906006, "global_step": 592909, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0383880138397217, "global_step": 592910, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9881610870361328, "global_step": 592911, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0693743228912354, "global_step": 592912, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0088768005371094, "global_step": 592913, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9408349990844727, "global_step": 592914, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.070559024810791, "global_step": 592915, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9286494255065918, "global_step": 592916, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9382530450820923, "global_step": 592917, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9975777864456177, "global_step": 592918, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9982786178588867, "global_step": 592919, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.087721109390259, "global_step": 592920, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.061748743057251, "global_step": 592921, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9297281503677368, "global_step": 592922, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0314130783081055, "global_step": 592923, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.122098922729492, "global_step": 592924, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0016915798187256, "global_step": 592925, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9597413539886475, "global_step": 592926, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0559909343719482, "global_step": 592927, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.046273946762085, "global_step": 592928, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.966105580329895, "global_step": 592929, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9616297483444214, "global_step": 592930, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9453835487365723, "global_step": 592931, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9884949922561646, "global_step": 592932, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.093080520629883, "global_step": 592933, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.996121883392334, "global_step": 592934, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0939152240753174, "global_step": 592935, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.010998249053955, "global_step": 592936, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.008634567260742, "global_step": 592937, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9252026081085205, "global_step": 592938, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.979553461074829, "global_step": 592939, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.014631509780884, "global_step": 592940, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0157968997955322, "global_step": 592941, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.061091184616089, "global_step": 592942, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.1077418327331543, "global_step": 592943, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0133614540100098, "global_step": 592944, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0292463302612305, "global_step": 592945, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.998395323753357, "global_step": 592946, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9906467199325562, "global_step": 592947, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.000844955444336, "global_step": 592948, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0852770805358887, "global_step": 592949, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0113863945007324, "global_step": 592950, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9502829313278198, "global_step": 592951, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.031520128250122, "global_step": 592952, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0605781078338623, "global_step": 592953, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9953479766845703, "global_step": 592954, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.064133405685425, "global_step": 592955, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0162575244903564, "global_step": 592956, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.018378734588623, "global_step": 592957, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0437991619110107, "global_step": 592958, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.07588267326355, "global_step": 592959, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0383472442626953, "global_step": 592960, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9682003259658813, "global_step": 592961, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9903435707092285, "global_step": 592962, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0886223316192627, "global_step": 592963, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0651040077209473, "global_step": 592964, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0499234199523926, "global_step": 592965, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.116689920425415, "global_step": 592966, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0953290462493896, "global_step": 592967, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9723676443099976, "global_step": 592968, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0575881004333496, "global_step": 592969, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.025561571121216, "global_step": 592970, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9570034742355347, "global_step": 592971, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9965388774871826, "global_step": 592972, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.06130051612854, "global_step": 592973, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.989065408706665, "global_step": 592974, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.021442413330078, "global_step": 592975, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.039222002029419, "global_step": 592976, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.021124839782715, "global_step": 592977, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.032803773880005, "global_step": 592978, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.072469472885132, "global_step": 592979, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0170881748199463, "global_step": 592980, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0746562480926514, "global_step": 592981, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0716631412506104, "global_step": 592982, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.000790596008301, "global_step": 592983, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.027940511703491, "global_step": 592984, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0100152492523193, "global_step": 592985, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0230188369750977, "global_step": 592986, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0235965251922607, "global_step": 592987, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.984323263168335, "global_step": 592988, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9385573863983154, "global_step": 592989, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.970644474029541, "global_step": 592990, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0923376083374023, "global_step": 592991, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.042059898376465, "global_step": 592992, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9638478755950928, "global_step": 592993, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0037901401519775, "global_step": 592994, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.007408857345581, "global_step": 592995, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9691581726074219, "global_step": 592996, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9511620998382568, "global_step": 592997, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9808772802352905, "global_step": 592998, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0021116733551025, "global_step": 592999, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.006300449371338, "global_step": 593000, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0232629776000977, "global_step": 593001, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9524606466293335, "global_step": 593002, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0798935890197754, "global_step": 593003, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0188353061676025, "global_step": 593004, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9912763833999634, "global_step": 593005, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.01579213142395, "global_step": 593006, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.1017274856567383, "global_step": 593007, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0780534744262695, "global_step": 593008, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.055271625518799, "global_step": 593009, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0466301441192627, "global_step": 593010, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9687302112579346, "global_step": 593011, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.025113105773926, "global_step": 593012, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0631513595581055, "global_step": 593013, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.080979585647583, "global_step": 593014, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.043548583984375, "global_step": 593015, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0176613330841064, "global_step": 593016, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0170695781707764, "global_step": 593017, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0571181774139404, "global_step": 593018, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0690863132476807, "global_step": 593019, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.061492681503296, "global_step": 593020, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.084899663925171, "global_step": 593021, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.1155595779418945, "global_step": 593022, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0584027767181396, "global_step": 593023, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9648401737213135, "global_step": 593024, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9909964799880981, "global_step": 593025, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.03385329246521, "global_step": 593026, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0515475273132324, "global_step": 593027, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.052614450454712, "global_step": 593028, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9775758981704712, "global_step": 593029, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9490083456039429, "global_step": 593030, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.04990553855896, "global_step": 593031, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.1241683959960938, "global_step": 593032, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.983652949333191, "global_step": 593033, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9277235269546509, "global_step": 593034, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0241146087646484, "global_step": 593035, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0224292278289795, "global_step": 593036, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.028784990310669, "global_step": 593037, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0515100955963135, "global_step": 593038, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0103161334991455, "global_step": 593039, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.057945489883423, "global_step": 593040, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9941362142562866, "global_step": 593041, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0280063152313232, "global_step": 593042, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.8983699083328247, "global_step": 593043, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9587934017181396, "global_step": 593044, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9936590194702148, "global_step": 593045, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.011883497238159, "global_step": 593046, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.076345205307007, "global_step": 593047, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.094560384750366, "global_step": 593048, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.095564126968384, "global_step": 593049, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.063286304473877, "global_step": 593050, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0528218746185303, "global_step": 593051, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.075988531112671, "global_step": 593052, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.110062599182129, "global_step": 593053, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.951635479927063, "global_step": 593054, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9932748079299927, "global_step": 593055, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9905983209609985, "global_step": 593056, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.066739797592163, "global_step": 593057, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0234060287475586, "global_step": 593058, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.051276922225952, "global_step": 593059, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.089043140411377, "global_step": 593060, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0913186073303223, "global_step": 593061, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.02958607673645, "global_step": 593062, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0462071895599365, "global_step": 593063, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9436006546020508, "global_step": 593064, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.947640061378479, "global_step": 593065, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.1348602771759033, "global_step": 593066, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9827303886413574, "global_step": 593067, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9374573230743408, "global_step": 593068, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.976955533027649, "global_step": 593069, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0430045127868652, "global_step": 593070, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.04634952545166, "global_step": 593071, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0066440105438232, "global_step": 593072, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.02828311920166, "global_step": 593073, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9934443235397339, "global_step": 593074, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0498557090759277, "global_step": 593075, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.979798674583435, "global_step": 593076, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.01414155960083, "global_step": 593077, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0338289737701416, "global_step": 593078, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.072340726852417, "global_step": 593079, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0328173637390137, "global_step": 593080, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9447709321975708, "global_step": 593081, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0652620792388916, "global_step": 593082, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9645490646362305, "global_step": 593083, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0683658123016357, "global_step": 593084, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.942920207977295, "global_step": 593085, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9834823608398438, "global_step": 593086, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.014829158782959, "global_step": 593087, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9282047748565674, "global_step": 593088, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0541255474090576, "global_step": 593089, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9449824094772339, "global_step": 593090, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.008397340774536, "global_step": 593091, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.001408338546753, "global_step": 593092, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.032536029815674, "global_step": 593093, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0190842151641846, "global_step": 593094, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0094780921936035, "global_step": 593095, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.01528000831604, "global_step": 593096, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.119734525680542, "global_step": 593097, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0523195266723633, "global_step": 593098, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9699962139129639, "global_step": 593099, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0414936542510986, "global_step": 593100, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.940955638885498, "global_step": 593101, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9427744150161743, "global_step": 593102, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.076688051223755, "global_step": 593103, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0130603313446045, "global_step": 593104, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0179948806762695, "global_step": 593105, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9840095043182373, "global_step": 593106, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.082256555557251, "global_step": 593107, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.039780616760254, "global_step": 593108, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.098644495010376, "global_step": 593109, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9763747453689575, "global_step": 593110, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.125890016555786, "global_step": 593111, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0080342292785645, "global_step": 593112, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.057633399963379, "global_step": 593113, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.111417531967163, "global_step": 593114, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.097304105758667, "global_step": 593115, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0143632888793945, "global_step": 593116, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.051910638809204, "global_step": 593117, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9681591987609863, "global_step": 593118, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9963371753692627, "global_step": 593119, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0390241146087646, "global_step": 593120, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.079319715499878, "global_step": 593121, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0146467685699463, "global_step": 593122, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0547642707824707, "global_step": 593123, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9573872089385986, "global_step": 593124, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0256497859954834, "global_step": 593125, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.004232406616211, "global_step": 593126, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.006946325302124, "global_step": 593127, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.042867422103882, "global_step": 593128, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.963742733001709, "global_step": 593129, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.96211576461792, "global_step": 593130, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0703656673431396, "global_step": 593131, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.944977045059204, "global_step": 593132, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.110854148864746, "global_step": 593133, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0070724487304688, "global_step": 593134, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9928536415100098, "global_step": 593135, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0789754390716553, "global_step": 593136, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0641560554504395, "global_step": 593137, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.017108201980591, "global_step": 593138, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0441713333129883, "global_step": 593139, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.018785238265991, "global_step": 593140, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9895460605621338, "global_step": 593141, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0315914154052734, "global_step": 593142, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0467257499694824, "global_step": 593143, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0928666591644287, "global_step": 593144, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0036544799804688, "global_step": 593145, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.1102654933929443, "global_step": 593146, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0509727001190186, "global_step": 593147, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9935460090637207, "global_step": 593148, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9397203922271729, "global_step": 593149, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.029137134552002, "global_step": 593150, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0580270290374756, "global_step": 593151, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.006422281265259, "global_step": 593152, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.023336172103882, "global_step": 593153, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0099823474884033, "global_step": 593154, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.071373462677002, "global_step": 593155, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0176870822906494, "global_step": 593156, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9996616840362549, "global_step": 593157, "epoch": 961, "lr": 5e-05}
{"train_loss": 1.9117577075958252, "global_step": 593158, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0506834983825684, "global_step": 593159, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0184543132781982, "global_step": 593160, "epoch": 961, "lr": 5e-05}
{"train_loss": 2.0319085121154785, "global_step": 593161, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.033759593963623, "global_step": 593162, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.981252670288086, "global_step": 593163, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.011042833328247, "global_step": 593164, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0388405323028564, "global_step": 593165, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.008179187774658, "global_step": 593166, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.058356523513794, "global_step": 593167, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0069901943206787, "global_step": 593168, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0185654163360596, "global_step": 593169, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.06378436088562, "global_step": 593170, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9477794170379639, "global_step": 593171, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9881446361541748, "global_step": 593172, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9752178192138672, "global_step": 593173, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.027078151702881, "global_step": 593174, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0561256408691406, "global_step": 593175, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9905885457992554, "global_step": 593176, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9810117483139038, "global_step": 593177, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0475292205810547, "global_step": 593178, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.983763337135315, "global_step": 593179, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.007812023162842, "global_step": 593180, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0489468574523926, "global_step": 593181, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0351247787475586, "global_step": 593182, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.021599054336548, "global_step": 593183, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9985095262527466, "global_step": 593184, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9962559938430786, "global_step": 593185, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9413527250289917, "global_step": 593186, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9697867631912231, "global_step": 593187, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0389506816864014, "global_step": 593188, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0845324993133545, "global_step": 593189, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9562050104141235, "global_step": 593190, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0633034706115723, "global_step": 593191, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.012873411178589, "global_step": 593192, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9117120504379272, "global_step": 593193, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0474233627319336, "global_step": 593194, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9884620904922485, "global_step": 593195, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9880874156951904, "global_step": 593196, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0447919368743896, "global_step": 593197, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.031529426574707, "global_step": 593198, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.050765037536621, "global_step": 593199, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9691009521484375, "global_step": 593200, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0453946590423584, "global_step": 593201, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9905961751937866, "global_step": 593202, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0174214839935303, "global_step": 593203, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0048539638519287, "global_step": 593204, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.96990966796875, "global_step": 593205, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0733909606933594, "global_step": 593206, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.044313669204712, "global_step": 593207, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0377514362335205, "global_step": 593208, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0271763801574707, "global_step": 593209, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.020001173019409, "global_step": 593210, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9894840717315674, "global_step": 593211, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0331223011016846, "global_step": 593212, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.973858118057251, "global_step": 593213, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0269694328308105, "global_step": 593214, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.992430329322815, "global_step": 593215, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9836225509643555, "global_step": 593216, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.005995988845825, "global_step": 593217, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9524282217025757, "global_step": 593218, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.04575514793396, "global_step": 593219, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.010613441467285, "global_step": 593220, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.061345100402832, "global_step": 593221, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.95058012008667, "global_step": 593222, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.016885757446289, "global_step": 593223, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9873974323272705, "global_step": 593224, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9815212488174438, "global_step": 593225, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0272412300109863, "global_step": 593226, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9429607391357422, "global_step": 593227, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9719809293746948, "global_step": 593228, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.068321704864502, "global_step": 593229, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0764968395233154, "global_step": 593230, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9240288734436035, "global_step": 593231, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.005908727645874, "global_step": 593232, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.036163568496704, "global_step": 593233, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9815195798873901, "global_step": 593234, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0155482292175293, "global_step": 593235, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.007185459136963, "global_step": 593236, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0496511459350586, "global_step": 593237, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.022068977355957, "global_step": 593238, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9429837465286255, "global_step": 593239, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9534153938293457, "global_step": 593240, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.02022647857666, "global_step": 593241, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.02302885055542, "global_step": 593242, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.938204288482666, "global_step": 593243, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9865121841430664, "global_step": 593244, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.026064395904541, "global_step": 593245, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9506733417510986, "global_step": 593246, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0295650959014893, "global_step": 593247, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.979069471359253, "global_step": 593248, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.972528100013733, "global_step": 593249, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9576619863510132, "global_step": 593250, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.012498140335083, "global_step": 593251, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.04174542427063, "global_step": 593252, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0200090408325195, "global_step": 593253, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.944083571434021, "global_step": 593254, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.058415174484253, "global_step": 593255, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9561803340911865, "global_step": 593256, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.028865098953247, "global_step": 593257, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.091839075088501, "global_step": 593258, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0767343044281006, "global_step": 593259, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0732827186584473, "global_step": 593260, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.063552141189575, "global_step": 593261, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0783278942108154, "global_step": 593262, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.992934226989746, "global_step": 593263, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9516245126724243, "global_step": 593264, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.058771848678589, "global_step": 593265, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9448204040527344, "global_step": 593266, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0502991676330566, "global_step": 593267, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.1138088703155518, "global_step": 593268, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.011687755584717, "global_step": 593269, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.086043119430542, "global_step": 593270, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9613063335418701, "global_step": 593271, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.040515422821045, "global_step": 593272, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0911762714385986, "global_step": 593273, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0089690685272217, "global_step": 593274, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9205317497253418, "global_step": 593275, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.025533676147461, "global_step": 593276, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0329253673553467, "global_step": 593277, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0479824542999268, "global_step": 593278, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.974921464920044, "global_step": 593279, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9943963289260864, "global_step": 593280, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9097309112548828, "global_step": 593281, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0545222759246826, "global_step": 593282, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9769209623336792, "global_step": 593283, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.941304326057434, "global_step": 593284, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9851843118667603, "global_step": 593285, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9333789348602295, "global_step": 593286, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9374085664749146, "global_step": 593287, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.006296396255493, "global_step": 593288, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0566153526306152, "global_step": 593289, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0204012393951416, "global_step": 593290, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9924460649490356, "global_step": 593291, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9533319473266602, "global_step": 593292, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.900175929069519, "global_step": 593293, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9835255146026611, "global_step": 593294, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9194542169570923, "global_step": 593295, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.967573881149292, "global_step": 593296, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9503686428070068, "global_step": 593297, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.070619583129883, "global_step": 593298, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9823263883590698, "global_step": 593299, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9464010000228882, "global_step": 593300, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.018829822540283, "global_step": 593301, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0155253410339355, "global_step": 593302, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9605401754379272, "global_step": 593303, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0224461555480957, "global_step": 593304, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0282092094421387, "global_step": 593305, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.052434206008911, "global_step": 593306, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.009572744369507, "global_step": 593307, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.981937050819397, "global_step": 593308, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.94479238986969, "global_step": 593309, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.06579327583313, "global_step": 593310, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.038574695587158, "global_step": 593311, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9544860124588013, "global_step": 593312, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0002176761627197, "global_step": 593313, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9291789531707764, "global_step": 593314, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0787808895111084, "global_step": 593315, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9291350841522217, "global_step": 593316, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9611077308654785, "global_step": 593317, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.048323631286621, "global_step": 593318, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.073228120803833, "global_step": 593319, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9586572647094727, "global_step": 593320, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0170767307281494, "global_step": 593321, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0199973583221436, "global_step": 593322, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9828135967254639, "global_step": 593323, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.968056082725525, "global_step": 593324, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.975283145904541, "global_step": 593325, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9404358863830566, "global_step": 593326, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9965139627456665, "global_step": 593327, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0073604583740234, "global_step": 593328, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.019822835922241, "global_step": 593329, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0063679218292236, "global_step": 593330, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0025930404663086, "global_step": 593331, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9801665544509888, "global_step": 593332, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0458767414093018, "global_step": 593333, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9632192850112915, "global_step": 593334, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.061903715133667, "global_step": 593335, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9323190450668335, "global_step": 593336, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0044748783111572, "global_step": 593337, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.976521372795105, "global_step": 593338, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.084615468978882, "global_step": 593339, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.047867774963379, "global_step": 593340, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9496842622756958, "global_step": 593341, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9282009601593018, "global_step": 593342, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9456539154052734, "global_step": 593343, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9949291944503784, "global_step": 593344, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.071707010269165, "global_step": 593345, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0304532051086426, "global_step": 593346, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9636896848678589, "global_step": 593347, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.043783664703369, "global_step": 593348, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.110757350921631, "global_step": 593349, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0744688510894775, "global_step": 593350, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9951118230819702, "global_step": 593351, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.069016695022583, "global_step": 593352, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0175859928131104, "global_step": 593353, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9817073345184326, "global_step": 593354, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.068133592605591, "global_step": 593355, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0158634185791016, "global_step": 593356, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.989639163017273, "global_step": 593357, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.103180170059204, "global_step": 593358, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.068268299102783, "global_step": 593359, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9822038412094116, "global_step": 593360, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.8988537788391113, "global_step": 593361, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0241668224334717, "global_step": 593362, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.990365982055664, "global_step": 593363, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0225255489349365, "global_step": 593364, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0000100135803223, "global_step": 593365, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9647184610366821, "global_step": 593366, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.041325092315674, "global_step": 593367, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9629005193710327, "global_step": 593368, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.008347272872925, "global_step": 593369, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0066211223602295, "global_step": 593370, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9380099773406982, "global_step": 593371, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.050508499145508, "global_step": 593372, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0142312049865723, "global_step": 593373, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9725512266159058, "global_step": 593374, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0138018131256104, "global_step": 593375, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9399478435516357, "global_step": 593376, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9172565937042236, "global_step": 593377, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0180633068084717, "global_step": 593378, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0160953998565674, "global_step": 593379, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0328519344329834, "global_step": 593380, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0023996829986572, "global_step": 593381, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9547784328460693, "global_step": 593382, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0047364234924316, "global_step": 593383, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.107882261276245, "global_step": 593384, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0766499042510986, "global_step": 593385, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.03836989402771, "global_step": 593386, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.917938232421875, "global_step": 593387, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.966973066329956, "global_step": 593388, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.993658185005188, "global_step": 593389, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.963569164276123, "global_step": 593390, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.020418882369995, "global_step": 593391, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9878674745559692, "global_step": 593392, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.077594757080078, "global_step": 593393, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9819601774215698, "global_step": 593394, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0765631198883057, "global_step": 593395, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.047391891479492, "global_step": 593396, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0243136882781982, "global_step": 593397, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0477793216705322, "global_step": 593398, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.961046576499939, "global_step": 593399, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.009591579437256, "global_step": 593400, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.970953345298767, "global_step": 593401, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.032564640045166, "global_step": 593402, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0012900829315186, "global_step": 593403, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.028740406036377, "global_step": 593404, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9289385080337524, "global_step": 593405, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.059656858444214, "global_step": 593406, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0907490253448486, "global_step": 593407, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.040541887283325, "global_step": 593408, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.8934929370880127, "global_step": 593409, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0401065349578857, "global_step": 593410, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0211968421936035, "global_step": 593411, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0930886268615723, "global_step": 593412, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0183749198913574, "global_step": 593413, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.035784959793091, "global_step": 593414, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.02087140083313, "global_step": 593415, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.927782654762268, "global_step": 593416, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.891160488128662, "global_step": 593417, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.910644769668579, "global_step": 593418, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0704500675201416, "global_step": 593419, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9899104833602905, "global_step": 593420, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0606143474578857, "global_step": 593421, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.110661506652832, "global_step": 593422, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9582899808883667, "global_step": 593423, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.038485527038574, "global_step": 593424, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0374341011047363, "global_step": 593425, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9377577304840088, "global_step": 593426, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9510184526443481, "global_step": 593427, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0252957344055176, "global_step": 593428, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9951705932617188, "global_step": 593429, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9706823825836182, "global_step": 593430, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.028182029724121, "global_step": 593431, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.01013445854187, "global_step": 593432, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9775652885437012, "global_step": 593433, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.044649839401245, "global_step": 593434, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0835459232330322, "global_step": 593435, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9194984436035156, "global_step": 593436, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9507678747177124, "global_step": 593437, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.025912046432495, "global_step": 593438, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0570998191833496, "global_step": 593439, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.065721035003662, "global_step": 593440, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9616066217422485, "global_step": 593441, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.964944839477539, "global_step": 593442, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9508055448532104, "global_step": 593443, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.026592969894409, "global_step": 593444, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.969275712966919, "global_step": 593445, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9531112909317017, "global_step": 593446, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.078441619873047, "global_step": 593447, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.021376609802246, "global_step": 593448, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.015718460083008, "global_step": 593449, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9844934940338135, "global_step": 593450, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.027797222137451, "global_step": 593451, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.008138656616211, "global_step": 593452, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.097963333129883, "global_step": 593453, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.058614730834961, "global_step": 593454, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.004274368286133, "global_step": 593455, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0779123306274414, "global_step": 593456, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9240601062774658, "global_step": 593457, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.053847551345825, "global_step": 593458, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9408258199691772, "global_step": 593459, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9462518692016602, "global_step": 593460, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.983044981956482, "global_step": 593461, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.001387596130371, "global_step": 593462, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0844178199768066, "global_step": 593463, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9664267301559448, "global_step": 593464, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.004798412322998, "global_step": 593465, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9639267921447754, "global_step": 593466, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0280797481536865, "global_step": 593467, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0750222206115723, "global_step": 593468, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.024625539779663, "global_step": 593469, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9365698099136353, "global_step": 593470, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9884191751480103, "global_step": 593471, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9829092025756836, "global_step": 593472, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9550102949142456, "global_step": 593473, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9947690963745117, "global_step": 593474, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0332653522491455, "global_step": 593475, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0446953773498535, "global_step": 593476, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.033189535140991, "global_step": 593477, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0906074047088623, "global_step": 593478, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.020392894744873, "global_step": 593479, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0065786838531494, "global_step": 593480, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.007023334503174, "global_step": 593481, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0700602531433105, "global_step": 593482, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0300631523132324, "global_step": 593483, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0092051029205322, "global_step": 593484, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.027616262435913, "global_step": 593485, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9243241548538208, "global_step": 593486, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0774409770965576, "global_step": 593487, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0264792442321777, "global_step": 593488, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0322391986846924, "global_step": 593489, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9766234159469604, "global_step": 593490, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.007347583770752, "global_step": 593491, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.1079421043395996, "global_step": 593492, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.966127872467041, "global_step": 593493, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0169754028320312, "global_step": 593494, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9958641529083252, "global_step": 593495, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9783270359039307, "global_step": 593496, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.026564121246338, "global_step": 593497, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.942029595375061, "global_step": 593498, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9926211833953857, "global_step": 593499, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.1099486351013184, "global_step": 593500, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9635088443756104, "global_step": 593501, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9580429792404175, "global_step": 593502, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9694114923477173, "global_step": 593503, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.045064687728882, "global_step": 593504, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9708609580993652, "global_step": 593505, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9528868198394775, "global_step": 593506, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9692403078079224, "global_step": 593507, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0579683780670166, "global_step": 593508, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0315933227539062, "global_step": 593509, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.073460817337036, "global_step": 593510, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9246164560317993, "global_step": 593511, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.021526336669922, "global_step": 593512, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9518978595733643, "global_step": 593513, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9618260860443115, "global_step": 593514, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0314695835113525, "global_step": 593515, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0313305854797363, "global_step": 593516, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.074765920639038, "global_step": 593517, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9247883558273315, "global_step": 593518, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.963220238685608, "global_step": 593519, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9733028411865234, "global_step": 593520, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.113849401473999, "global_step": 593521, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.002943992614746, "global_step": 593522, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0656533241271973, "global_step": 593523, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.009986400604248, "global_step": 593524, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0265254974365234, "global_step": 593525, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.024338960647583, "global_step": 593526, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0103628635406494, "global_step": 593527, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9826438426971436, "global_step": 593528, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0525894165039062, "global_step": 593529, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0074872970581055, "global_step": 593530, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9206653833389282, "global_step": 593531, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0302610397338867, "global_step": 593532, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0239405632019043, "global_step": 593533, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9822190999984741, "global_step": 593534, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.011735200881958, "global_step": 593535, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9618406295776367, "global_step": 593536, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9737979173660278, "global_step": 593537, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9608994722366333, "global_step": 593538, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0481770038604736, "global_step": 593539, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0705950260162354, "global_step": 593540, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9215983152389526, "global_step": 593541, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.061772584915161, "global_step": 593542, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0146515369415283, "global_step": 593543, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9483741521835327, "global_step": 593544, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0014729499816895, "global_step": 593545, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.033080577850342, "global_step": 593546, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0215725898742676, "global_step": 593547, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9975732564926147, "global_step": 593548, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9967360496520996, "global_step": 593549, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.059581995010376, "global_step": 593550, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.085278034210205, "global_step": 593551, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.930794358253479, "global_step": 593552, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.961555004119873, "global_step": 593553, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9946749210357666, "global_step": 593554, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0136189460754395, "global_step": 593555, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.072572946548462, "global_step": 593556, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.020498037338257, "global_step": 593557, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0859036445617676, "global_step": 593558, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0638763904571533, "global_step": 593559, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.976791501045227, "global_step": 593560, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9555569887161255, "global_step": 593561, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0407910346984863, "global_step": 593562, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0326247215270996, "global_step": 593563, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0202958583831787, "global_step": 593564, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.950492024421692, "global_step": 593565, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.027078151702881, "global_step": 593566, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0118062496185303, "global_step": 593567, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.102644443511963, "global_step": 593568, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9375905990600586, "global_step": 593569, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9766396284103394, "global_step": 593570, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0194625854492188, "global_step": 593571, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.06166934967041, "global_step": 593572, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.046379566192627, "global_step": 593573, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.105318784713745, "global_step": 593574, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.959517240524292, "global_step": 593575, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0297622680664062, "global_step": 593576, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0551834106445312, "global_step": 593577, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.009442090988159, "global_step": 593578, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.015732526779175, "global_step": 593579, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.052870035171509, "global_step": 593580, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0208828449249268, "global_step": 593581, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.010859727859497, "global_step": 593582, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0481503009796143, "global_step": 593583, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0815131664276123, "global_step": 593584, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.061580181121826, "global_step": 593585, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.1256091594696045, "global_step": 593586, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.089698076248169, "global_step": 593587, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9931838512420654, "global_step": 593588, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.982464075088501, "global_step": 593589, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9800357818603516, "global_step": 593590, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9133844375610352, "global_step": 593591, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0781967639923096, "global_step": 593592, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.057589530944824, "global_step": 593593, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.021043539047241, "global_step": 593594, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.008866310119629, "global_step": 593595, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9866454601287842, "global_step": 593596, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0681991577148438, "global_step": 593597, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9579976797103882, "global_step": 593598, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.062319278717041, "global_step": 593599, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9941245317459106, "global_step": 593600, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9998950958251953, "global_step": 593601, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0966243743896484, "global_step": 593602, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9941991567611694, "global_step": 593603, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0135550498962402, "global_step": 593604, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9664342403411865, "global_step": 593605, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.000176429748535, "global_step": 593606, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.098375082015991, "global_step": 593607, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.979712963104248, "global_step": 593608, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.083608627319336, "global_step": 593609, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0215983390808105, "global_step": 593610, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0342857837677, "global_step": 593611, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.008291244506836, "global_step": 593612, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0594801902770996, "global_step": 593613, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0594592094421387, "global_step": 593614, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9963330030441284, "global_step": 593615, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0206828117370605, "global_step": 593616, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.997612476348877, "global_step": 593617, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.1450440883636475, "global_step": 593618, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9634548425674438, "global_step": 593619, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.037656545639038, "global_step": 593620, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9694374799728394, "global_step": 593621, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0241901874542236, "global_step": 593622, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0100200176239014, "global_step": 593623, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.028665542602539, "global_step": 593624, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0770208835601807, "global_step": 593625, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.962033748626709, "global_step": 593626, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0786292552948, "global_step": 593627, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0755743980407715, "global_step": 593628, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.062793493270874, "global_step": 593629, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.014882802963257, "global_step": 593630, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.082754611968994, "global_step": 593631, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.02579927444458, "global_step": 593632, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.1595096588134766, "global_step": 593633, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.04870343208313, "global_step": 593634, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.014660120010376, "global_step": 593635, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.001314640045166, "global_step": 593636, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.046250343322754, "global_step": 593637, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9826164245605469, "global_step": 593638, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9444658756256104, "global_step": 593639, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0744974613189697, "global_step": 593640, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.98478364944458, "global_step": 593641, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.03110933303833, "global_step": 593642, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9759892225265503, "global_step": 593643, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.073859691619873, "global_step": 593644, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.023707866668701, "global_step": 593645, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.100396156311035, "global_step": 593646, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.059234857559204, "global_step": 593647, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9901893138885498, "global_step": 593648, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.025524377822876, "global_step": 593649, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.110612630844116, "global_step": 593650, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0158112049102783, "global_step": 593651, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9881718158721924, "global_step": 593652, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9484546184539795, "global_step": 593653, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9718849658966064, "global_step": 593654, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.030367851257324, "global_step": 593655, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9222315549850464, "global_step": 593656, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9845728874206543, "global_step": 593657, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0488522052764893, "global_step": 593658, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.034221887588501, "global_step": 593659, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9314545392990112, "global_step": 593660, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.010662078857422, "global_step": 593661, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.02594256401062, "global_step": 593662, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.064666748046875, "global_step": 593663, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0018649101257324, "global_step": 593664, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9280260801315308, "global_step": 593665, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0007121562957764, "global_step": 593666, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0076236724853516, "global_step": 593667, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0511841773986816, "global_step": 593668, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0314247608184814, "global_step": 593669, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9996025562286377, "global_step": 593670, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9823455810546875, "global_step": 593671, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0389182567596436, "global_step": 593672, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.039468288421631, "global_step": 593673, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0508599281311035, "global_step": 593674, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.052980661392212, "global_step": 593675, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9945156574249268, "global_step": 593676, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9994324445724487, "global_step": 593677, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0727615356445312, "global_step": 593678, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0049068927764893, "global_step": 593679, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9899694919586182, "global_step": 593680, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.95767080783844, "global_step": 593681, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0008745193481445, "global_step": 593682, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9906268119812012, "global_step": 593683, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9977067708969116, "global_step": 593684, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0512382984161377, "global_step": 593685, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0212392807006836, "global_step": 593686, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9963253736495972, "global_step": 593687, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0600931644439697, "global_step": 593688, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.056586503982544, "global_step": 593689, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.006402015686035, "global_step": 593690, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9347615242004395, "global_step": 593691, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9931825399398804, "global_step": 593692, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.141937732696533, "global_step": 593693, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.090968370437622, "global_step": 593694, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.042128562927246, "global_step": 593695, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.969712257385254, "global_step": 593696, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.087136745452881, "global_step": 593697, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0055530071258545, "global_step": 593698, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.032088041305542, "global_step": 593699, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0295028686523438, "global_step": 593700, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.082923650741577, "global_step": 593701, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0413925647735596, "global_step": 593702, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.042041063308716, "global_step": 593703, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0460357666015625, "global_step": 593704, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9987983703613281, "global_step": 593705, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9794386625289917, "global_step": 593706, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.1519570350646973, "global_step": 593707, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0230634212493896, "global_step": 593708, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.02401065826416, "global_step": 593709, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9668493270874023, "global_step": 593710, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.020688772201538, "global_step": 593711, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0873515605926514, "global_step": 593712, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9385170936584473, "global_step": 593713, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.125725030899048, "global_step": 593714, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.036067247390747, "global_step": 593715, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0213277339935303, "global_step": 593716, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.053170680999756, "global_step": 593717, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0042967796325684, "global_step": 593718, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0717194080352783, "global_step": 593719, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.978018879890442, "global_step": 593720, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.020611524581909, "global_step": 593721, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9679514169692993, "global_step": 593722, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.095975637435913, "global_step": 593723, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.021759510040283, "global_step": 593724, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9712601900100708, "global_step": 593725, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0005738735198975, "global_step": 593726, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9830989837646484, "global_step": 593727, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.962803840637207, "global_step": 593728, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0262980461120605, "global_step": 593729, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0391600131988525, "global_step": 593730, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9759137630462646, "global_step": 593731, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.948535680770874, "global_step": 593732, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9974641799926758, "global_step": 593733, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.982519268989563, "global_step": 593734, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.110949754714966, "global_step": 593735, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.994312047958374, "global_step": 593736, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9818525314331055, "global_step": 593737, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9976238012313843, "global_step": 593738, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9833564758300781, "global_step": 593739, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.074036121368408, "global_step": 593740, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0319559574127197, "global_step": 593741, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0110790729522705, "global_step": 593742, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9733457565307617, "global_step": 593743, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0335869789123535, "global_step": 593744, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0988659858703613, "global_step": 593745, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.051138162612915, "global_step": 593746, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0395092964172363, "global_step": 593747, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.995768666267395, "global_step": 593748, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0377614498138428, "global_step": 593749, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0179383754730225, "global_step": 593750, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0013926029205322, "global_step": 593751, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0064537525177, "global_step": 593752, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9531967639923096, "global_step": 593753, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.019439935684204, "global_step": 593754, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9876893758773804, "global_step": 593755, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0601487159729004, "global_step": 593756, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.015004873275757, "global_step": 593757, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9904882907867432, "global_step": 593758, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.022490978240967, "global_step": 593759, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.028035879135132, "global_step": 593760, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9371991157531738, "global_step": 593761, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.944430947303772, "global_step": 593762, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.1538233757019043, "global_step": 593763, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0516998767852783, "global_step": 593764, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9966561794281006, "global_step": 593765, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0685927867889404, "global_step": 593766, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0152504444122314, "global_step": 593767, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.062192678451538, "global_step": 593768, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0549914836883545, "global_step": 593769, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0241141319274902, "global_step": 593770, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0079843997955322, "global_step": 593771, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0496931076049805, "global_step": 593772, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.983052134513855, "global_step": 593773, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9240573644638062, "global_step": 593774, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.026860237121582, "global_step": 593775, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9856082201004028, "global_step": 593776, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0338029861450195, "global_step": 593777, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9983086585998535, "global_step": 593778, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0050275325775146, "global_step": 593779, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.988822340965271, "global_step": 593780, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0435268878936768, "global_step": 593781, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9947901964187622, "global_step": 593782, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.070848226547241, "global_step": 593783, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0003161430358887, "global_step": 593784, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9376837015151978, "global_step": 593785, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9941328763961792, "global_step": 593786, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.013032913208008, "global_step": 593787, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9928009510040283, "global_step": 593788, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.977431058883667, "global_step": 593789, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.955528736114502, "global_step": 593790, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.978664755821228, "global_step": 593791, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.051896572113037, "global_step": 593792, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.017597198486328, "global_step": 593793, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9993215799331665, "global_step": 593794, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9791929721832275, "global_step": 593795, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.033609628677368, "global_step": 593796, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9964505434036255, "global_step": 593797, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.001471757888794, "global_step": 593798, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0770926475524902, "global_step": 593799, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.028639316558838, "global_step": 593800, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0003252029418945, "global_step": 593801, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.017610549926758, "global_step": 593802, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0050816535949707, "global_step": 593803, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0511460304260254, "global_step": 593804, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9698952436447144, "global_step": 593805, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.07344651222229, "global_step": 593806, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0013961791992188, "global_step": 593807, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0264108180999756, "global_step": 593808, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.008268356323242, "global_step": 593809, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0123989582061768, "global_step": 593810, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.983649730682373, "global_step": 593811, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0610461235046387, "global_step": 593812, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.054030418395996, "global_step": 593813, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.088890790939331, "global_step": 593814, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9987647533416748, "global_step": 593815, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.019239902496338, "global_step": 593816, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9836535453796387, "global_step": 593817, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0623316764831543, "global_step": 593818, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0831522941589355, "global_step": 593819, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.006714105606079, "global_step": 593820, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.001380205154419, "global_step": 593821, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9978082180023193, "global_step": 593822, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0674071311950684, "global_step": 593823, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0604588985443115, "global_step": 593824, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0303969383239746, "global_step": 593825, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9917490482330322, "global_step": 593826, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0267138481140137, "global_step": 593827, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.068488836288452, "global_step": 593828, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.004960536956787, "global_step": 593829, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9684607982635498, "global_step": 593830, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.04435396194458, "global_step": 593831, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.031069278717041, "global_step": 593832, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.014110565185547, "global_step": 593833, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.035259962081909, "global_step": 593834, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.001861572265625, "global_step": 593835, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0965123176574707, "global_step": 593836, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9720630645751953, "global_step": 593837, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.991506576538086, "global_step": 593838, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9865038394927979, "global_step": 593839, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.013166666030884, "global_step": 593840, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9943290948867798, "global_step": 593841, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0161216259002686, "global_step": 593842, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.041386842727661, "global_step": 593843, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0726981163024902, "global_step": 593844, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.011828899383545, "global_step": 593845, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9772969484329224, "global_step": 593846, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.018437623977661, "global_step": 593847, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9826887845993042, "global_step": 593848, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.016775608062744, "global_step": 593849, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9987620115280151, "global_step": 593850, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.025996446609497, "global_step": 593851, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0608205795288086, "global_step": 593852, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.037079334259033, "global_step": 593853, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.079521656036377, "global_step": 593854, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0036637783050537, "global_step": 593855, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.002916097640991, "global_step": 593856, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9850685596466064, "global_step": 593857, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0157718658447266, "global_step": 593858, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.951986312866211, "global_step": 593859, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.085106372833252, "global_step": 593860, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0260088443756104, "global_step": 593861, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9799060821533203, "global_step": 593862, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.063121795654297, "global_step": 593863, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0529541969299316, "global_step": 593864, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0173163414001465, "global_step": 593865, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.068833589553833, "global_step": 593866, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.040985345840454, "global_step": 593867, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9565876722335815, "global_step": 593868, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9836097955703735, "global_step": 593869, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9702374935150146, "global_step": 593870, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.067373752593994, "global_step": 593871, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.976232886314392, "global_step": 593872, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9894877672195435, "global_step": 593873, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0384364128112793, "global_step": 593874, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0794379711151123, "global_step": 593875, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.049874782562256, "global_step": 593876, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0174238681793213, "global_step": 593877, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.025362491607666, "global_step": 593878, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0518734455108643, "global_step": 593879, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0538270473480225, "global_step": 593880, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9984463453292847, "global_step": 593881, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.995786190032959, "global_step": 593882, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0179460048675537, "global_step": 593883, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9843257665634155, "global_step": 593884, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.086435317993164, "global_step": 593885, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9930236339569092, "global_step": 593886, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.1410906314849854, "global_step": 593887, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.099515438079834, "global_step": 593888, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0004401206970215, "global_step": 593889, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.002164363861084, "global_step": 593890, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.015815496444702, "global_step": 593891, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.964828610420227, "global_step": 593892, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9634349346160889, "global_step": 593893, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9705240726470947, "global_step": 593894, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0102436542510986, "global_step": 593895, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.053277015686035, "global_step": 593896, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.067296266555786, "global_step": 593897, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.144970655441284, "global_step": 593898, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0137288570404053, "global_step": 593899, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9674433469772339, "global_step": 593900, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.022308111190796, "global_step": 593901, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.034130573272705, "global_step": 593902, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.988035798072815, "global_step": 593903, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9877792596817017, "global_step": 593904, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9738032817840576, "global_step": 593905, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.1245977878570557, "global_step": 593906, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9322668313980103, "global_step": 593907, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0349156856536865, "global_step": 593908, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9907472133636475, "global_step": 593909, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9583665132522583, "global_step": 593910, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.001507520675659, "global_step": 593911, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0031299591064453, "global_step": 593912, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9807021617889404, "global_step": 593913, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.061694622039795, "global_step": 593914, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0365819931030273, "global_step": 593915, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.022482395172119, "global_step": 593916, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9572062492370605, "global_step": 593917, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0782217979431152, "global_step": 593918, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9800403118133545, "global_step": 593919, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0428755283355713, "global_step": 593920, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.1164088249206543, "global_step": 593921, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0357906818389893, "global_step": 593922, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.1066994667053223, "global_step": 593923, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0412099361419678, "global_step": 593924, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0615875720977783, "global_step": 593925, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0324227809906006, "global_step": 593926, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9486720561981201, "global_step": 593927, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0424280166625977, "global_step": 593928, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.029132604598999, "global_step": 593929, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9942195415496826, "global_step": 593930, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0024516582489014, "global_step": 593931, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.035555124282837, "global_step": 593932, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.065016984939575, "global_step": 593933, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9323917627334595, "global_step": 593934, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0569193363189697, "global_step": 593935, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0529842376708984, "global_step": 593936, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9819214344024658, "global_step": 593937, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0424418449401855, "global_step": 593938, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0680630207061768, "global_step": 593939, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9357820749282837, "global_step": 593940, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.065742254257202, "global_step": 593941, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.144920825958252, "global_step": 593942, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9660004377365112, "global_step": 593943, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0682849884033203, "global_step": 593944, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.883029580116272, "global_step": 593945, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9608721733093262, "global_step": 593946, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9836912155151367, "global_step": 593947, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0527007579803467, "global_step": 593948, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9591245651245117, "global_step": 593949, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.030205011367798, "global_step": 593950, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9514087438583374, "global_step": 593951, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0601658821105957, "global_step": 593952, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.055432081222534, "global_step": 593953, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9667490720748901, "global_step": 593954, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0088493824005127, "global_step": 593955, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0924744606018066, "global_step": 593956, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0354599952697754, "global_step": 593957, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.059051275253296, "global_step": 593958, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.003141164779663, "global_step": 593959, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9119471311569214, "global_step": 593960, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.027836799621582, "global_step": 593961, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9476985931396484, "global_step": 593962, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9973901510238647, "global_step": 593963, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.000854969024658, "global_step": 593964, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9501363039016724, "global_step": 593965, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.998827576637268, "global_step": 593966, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.008812427520752, "global_step": 593967, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.048840045928955, "global_step": 593968, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9918797016143799, "global_step": 593969, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9034503698349, "global_step": 593970, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.994962215423584, "global_step": 593971, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9847235679626465, "global_step": 593972, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.972872257232666, "global_step": 593973, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9981046915054321, "global_step": 593974, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.024340867996216, "global_step": 593975, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0818958282470703, "global_step": 593976, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9642924070358276, "global_step": 593977, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0546796321868896, "global_step": 593978, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.099653720855713, "global_step": 593979, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.086071252822876, "global_step": 593980, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0302460193634033, "global_step": 593981, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9931451082229614, "global_step": 593982, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0814359188079834, "global_step": 593983, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0709452629089355, "global_step": 593984, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0321919918060303, "global_step": 593985, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.071444511413574, "global_step": 593986, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.99373197555542, "global_step": 593987, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9867734909057617, "global_step": 593988, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.015594244003296, "global_step": 593989, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9329068660736084, "global_step": 593990, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0334601402282715, "global_step": 593991, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0306878089904785, "global_step": 593992, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.962011456489563, "global_step": 593993, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9491044282913208, "global_step": 593994, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.966266393661499, "global_step": 593995, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.994995355606079, "global_step": 593996, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.10459303855896, "global_step": 593997, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.060926675796509, "global_step": 593998, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9651561975479126, "global_step": 593999, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.109257698059082, "global_step": 594000, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.021892786026001, "global_step": 594001, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9946677684783936, "global_step": 594002, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0381689071655273, "global_step": 594003, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0405964851379395, "global_step": 594004, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.081939697265625, "global_step": 594005, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.040426731109619, "global_step": 594006, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9977844953536987, "global_step": 594007, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.040346622467041, "global_step": 594008, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.043928861618042, "global_step": 594009, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0467445850372314, "global_step": 594010, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0192582607269287, "global_step": 594011, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.99168062210083, "global_step": 594012, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0949363708496094, "global_step": 594013, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9960765838623047, "global_step": 594014, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9662610292434692, "global_step": 594015, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0168824195861816, "global_step": 594016, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9921518564224243, "global_step": 594017, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.046588897705078, "global_step": 594018, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9594085216522217, "global_step": 594019, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.043632984161377, "global_step": 594020, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.991605281829834, "global_step": 594021, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9929391145706177, "global_step": 594022, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0000362396240234, "global_step": 594023, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.066770076751709, "global_step": 594024, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.016495943069458, "global_step": 594025, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.1076505184173584, "global_step": 594026, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9815969467163086, "global_step": 594027, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.040818214416504, "global_step": 594028, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0055172443389893, "global_step": 594029, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.055227279663086, "global_step": 594030, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0046815872192383, "global_step": 594031, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0291974544525146, "global_step": 594032, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0184926986694336, "global_step": 594033, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.984336256980896, "global_step": 594034, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0760533809661865, "global_step": 594035, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9689275026321411, "global_step": 594036, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.914401650428772, "global_step": 594037, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0676300525665283, "global_step": 594038, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9714471101760864, "global_step": 594039, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.061458110809326, "global_step": 594040, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0446460247039795, "global_step": 594041, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.04233455657959, "global_step": 594042, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0479068756103516, "global_step": 594043, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.990347146987915, "global_step": 594044, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.08091139793396, "global_step": 594045, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.044029712677002, "global_step": 594046, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9908093214035034, "global_step": 594047, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0051732063293457, "global_step": 594048, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0389277935028076, "global_step": 594049, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.011507034301758, "global_step": 594050, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9129576683044434, "global_step": 594051, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.1022121906280518, "global_step": 594052, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9895437955856323, "global_step": 594053, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.1049692630767822, "global_step": 594054, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.022179365158081, "global_step": 594055, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0014286041259766, "global_step": 594056, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0446176528930664, "global_step": 594057, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0950472354888916, "global_step": 594058, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0343844890594482, "global_step": 594059, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9851210117340088, "global_step": 594060, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0026497840881348, "global_step": 594061, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.1686737537384033, "global_step": 594062, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9832054376602173, "global_step": 594063, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.03541898727417, "global_step": 594064, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9616076946258545, "global_step": 594065, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9941797256469727, "global_step": 594066, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0291104316711426, "global_step": 594067, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0120773315429688, "global_step": 594068, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9415442943572998, "global_step": 594069, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0221996307373047, "global_step": 594070, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0195648670196533, "global_step": 594071, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9613410234451294, "global_step": 594072, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.975711464881897, "global_step": 594073, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.015428066253662, "global_step": 594074, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.03855037689209, "global_step": 594075, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.059373378753662, "global_step": 594076, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0169506072998047, "global_step": 594077, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0153486728668213, "global_step": 594078, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0799269676208496, "global_step": 594079, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9757747650146484, "global_step": 594080, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0175094604492188, "global_step": 594081, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.039742946624756, "global_step": 594082, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.029893159866333, "global_step": 594083, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0425000190734863, "global_step": 594084, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0518136024475098, "global_step": 594085, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0384535789489746, "global_step": 594086, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.020472288131714, "global_step": 594087, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9991803169250488, "global_step": 594088, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9933090209960938, "global_step": 594089, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.006363868713379, "global_step": 594090, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0123865604400635, "global_step": 594091, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0582828521728516, "global_step": 594092, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.020474910736084, "global_step": 594093, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0442187786102295, "global_step": 594094, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0632424354553223, "global_step": 594095, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9600770473480225, "global_step": 594096, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.038355827331543, "global_step": 594097, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.054403066635132, "global_step": 594098, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.112708330154419, "global_step": 594099, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.040415048599243, "global_step": 594100, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.122860908508301, "global_step": 594101, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.031782388687134, "global_step": 594102, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9817198514938354, "global_step": 594103, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0050387382507324, "global_step": 594104, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.040006637573242, "global_step": 594105, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9815608263015747, "global_step": 594106, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9956482648849487, "global_step": 594107, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0146286487579346, "global_step": 594108, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.921581745147705, "global_step": 594109, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9743492603302002, "global_step": 594110, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9991756677627563, "global_step": 594111, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0548129081726074, "global_step": 594112, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.06520414352417, "global_step": 594113, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.124143600463867, "global_step": 594114, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0396149158477783, "global_step": 594115, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9782636165618896, "global_step": 594116, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0625410079956055, "global_step": 594117, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.1154065132141113, "global_step": 594118, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.020312547683716, "global_step": 594119, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9757318496704102, "global_step": 594120, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.035503387451172, "global_step": 594121, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.989001989364624, "global_step": 594122, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0542845726013184, "global_step": 594123, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0916929244995117, "global_step": 594124, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0392143726348877, "global_step": 594125, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.083935499191284, "global_step": 594126, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.0101099014282227, "global_step": 594127, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9571892023086548, "global_step": 594128, "epoch": 962, "lr": 5e-05}
{"train_loss": 2.015198230743408, "global_step": 594129, "epoch": 962, "lr": 5e-05}
{"train_loss": 1.9519062042236328, "global_step": 594130, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.019595146179199, "global_step": 594131, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.023897171020508, "global_step": 594132, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9845579862594604, "global_step": 594133, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0319857597351074, "global_step": 594134, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.029834032058716, "global_step": 594135, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.946006417274475, "global_step": 594136, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9449738264083862, "global_step": 594137, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.029064178466797, "global_step": 594138, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.062288522720337, "global_step": 594139, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9406262636184692, "global_step": 594140, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9550427198410034, "global_step": 594141, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9254812002182007, "global_step": 594142, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.081989049911499, "global_step": 594143, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9903327226638794, "global_step": 594144, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0116310119628906, "global_step": 594145, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.012373685836792, "global_step": 594146, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9793788194656372, "global_step": 594147, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.033505916595459, "global_step": 594148, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9923771619796753, "global_step": 594149, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0598998069763184, "global_step": 594150, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.013254165649414, "global_step": 594151, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0462307929992676, "global_step": 594152, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9986010789871216, "global_step": 594153, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9783738851547241, "global_step": 594154, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9934585094451904, "global_step": 594155, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.018808126449585, "global_step": 594156, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0134596824645996, "global_step": 594157, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.072406530380249, "global_step": 594158, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9876047372817993, "global_step": 594159, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.969147801399231, "global_step": 594160, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0752151012420654, "global_step": 594161, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9981279373168945, "global_step": 594162, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0358474254608154, "global_step": 594163, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0090880393981934, "global_step": 594164, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9725065231323242, "global_step": 594165, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0508432388305664, "global_step": 594166, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9816060066223145, "global_step": 594167, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.01362681388855, "global_step": 594168, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.054091215133667, "global_step": 594169, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0454459190368652, "global_step": 594170, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9931339025497437, "global_step": 594171, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0576906204223633, "global_step": 594172, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0037875175476074, "global_step": 594173, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9457844495773315, "global_step": 594174, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9973835945129395, "global_step": 594175, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9690220355987549, "global_step": 594176, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.110041618347168, "global_step": 594177, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.007503032684326, "global_step": 594178, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.033881187438965, "global_step": 594179, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9680603742599487, "global_step": 594180, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9646203517913818, "global_step": 594181, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0089550018310547, "global_step": 594182, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9878618717193604, "global_step": 594183, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.010061740875244, "global_step": 594184, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.006199598312378, "global_step": 594185, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.027238368988037, "global_step": 594186, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0136771202087402, "global_step": 594187, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9533854722976685, "global_step": 594188, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9263471364974976, "global_step": 594189, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9925360679626465, "global_step": 594190, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0220398902893066, "global_step": 594191, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.927449107170105, "global_step": 594192, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9708435535430908, "global_step": 594193, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9580434560775757, "global_step": 594194, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9876947402954102, "global_step": 594195, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9768868684768677, "global_step": 594196, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.110344171524048, "global_step": 594197, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.019451379776001, "global_step": 594198, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0964066982269287, "global_step": 594199, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9358561038970947, "global_step": 594200, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9636693000793457, "global_step": 594201, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9861568212509155, "global_step": 594202, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0988929271698, "global_step": 594203, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9509681463241577, "global_step": 594204, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0189409255981445, "global_step": 594205, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.049924612045288, "global_step": 594206, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9487690925598145, "global_step": 594207, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9690700769424438, "global_step": 594208, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9045490026474, "global_step": 594209, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9841289520263672, "global_step": 594210, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.8940479755401611, "global_step": 594211, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9977705478668213, "global_step": 594212, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.001084804534912, "global_step": 594213, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9482619762420654, "global_step": 594214, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.8807541131973267, "global_step": 594215, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.014765977859497, "global_step": 594216, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9904435873031616, "global_step": 594217, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0168442726135254, "global_step": 594218, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.051395893096924, "global_step": 594219, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.023749589920044, "global_step": 594220, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.098299026489258, "global_step": 594221, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9432264566421509, "global_step": 594222, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0360231399536133, "global_step": 594223, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9910157918930054, "global_step": 594224, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.10799241065979, "global_step": 594225, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9854778051376343, "global_step": 594226, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.071465492248535, "global_step": 594227, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9865268468856812, "global_step": 594228, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.004746913909912, "global_step": 594229, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.1521189212799072, "global_step": 594230, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.1167399883270264, "global_step": 594231, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9544692039489746, "global_step": 594232, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0059642791748047, "global_step": 594233, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9997708797454834, "global_step": 594234, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9516384601593018, "global_step": 594235, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0634725093841553, "global_step": 594236, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9605110883712769, "global_step": 594237, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.057406425476074, "global_step": 594238, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0661873817443848, "global_step": 594239, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0191500186920166, "global_step": 594240, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0259485244750977, "global_step": 594241, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.93076753616333, "global_step": 594242, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0604777336120605, "global_step": 594243, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0842502117156982, "global_step": 594244, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9415501356124878, "global_step": 594245, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9902373552322388, "global_step": 594246, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0591745376586914, "global_step": 594247, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0220212936401367, "global_step": 594248, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.06416654586792, "global_step": 594249, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.994728446006775, "global_step": 594250, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0639703273773193, "global_step": 594251, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0595831871032715, "global_step": 594252, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.052243947982788, "global_step": 594253, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0435338020324707, "global_step": 594254, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9751696586608887, "global_step": 594255, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9244805574417114, "global_step": 594256, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9517717361450195, "global_step": 594257, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.994261622428894, "global_step": 594258, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.970828652381897, "global_step": 594259, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.036571979522705, "global_step": 594260, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.047192335128784, "global_step": 594261, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9447487592697144, "global_step": 594262, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9831368923187256, "global_step": 594263, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9727520942687988, "global_step": 594264, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9955559968948364, "global_step": 594265, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9835892915725708, "global_step": 594266, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9848164319992065, "global_step": 594267, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9646711349487305, "global_step": 594268, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0219244956970215, "global_step": 594269, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.009321928024292, "global_step": 594270, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9605937004089355, "global_step": 594271, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.1314404010772705, "global_step": 594272, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0708343982696533, "global_step": 594273, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0663585662841797, "global_step": 594274, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.092130661010742, "global_step": 594275, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.012946367263794, "global_step": 594276, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0868349075317383, "global_step": 594277, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9783717393875122, "global_step": 594278, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.901232361793518, "global_step": 594279, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.045628547668457, "global_step": 594280, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.002364158630371, "global_step": 594281, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.8882070779800415, "global_step": 594282, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9837367534637451, "global_step": 594283, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.993660807609558, "global_step": 594284, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.080139398574829, "global_step": 594285, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9918200969696045, "global_step": 594286, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9214141368865967, "global_step": 594287, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9711706638336182, "global_step": 594288, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0354955196380615, "global_step": 594289, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0695416927337646, "global_step": 594290, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9832593202590942, "global_step": 594291, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9398053884506226, "global_step": 594292, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9399455785751343, "global_step": 594293, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.111140251159668, "global_step": 594294, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0194356441497803, "global_step": 594295, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9810352325439453, "global_step": 594296, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9645344018936157, "global_step": 594297, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.048928737640381, "global_step": 594298, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9465254545211792, "global_step": 594299, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9300764799118042, "global_step": 594300, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0427286624908447, "global_step": 594301, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.029768228530884, "global_step": 594302, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.040243625640869, "global_step": 594303, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9793500900268555, "global_step": 594304, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9695745706558228, "global_step": 594305, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.056509256362915, "global_step": 594306, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.004256248474121, "global_step": 594307, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.078373432159424, "global_step": 594308, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9463409185409546, "global_step": 594309, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0536484718322754, "global_step": 594310, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0496251583099365, "global_step": 594311, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9364352226257324, "global_step": 594312, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0180492401123047, "global_step": 594313, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9803764820098877, "global_step": 594314, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0008039474487305, "global_step": 594315, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.1139917373657227, "global_step": 594316, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.084726572036743, "global_step": 594317, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9756754636764526, "global_step": 594318, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9999529123306274, "global_step": 594319, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9859304428100586, "global_step": 594320, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.027329206466675, "global_step": 594321, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.014850616455078, "global_step": 594322, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0111100673675537, "global_step": 594323, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9923750162124634, "global_step": 594324, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0423293113708496, "global_step": 594325, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0677263736724854, "global_step": 594326, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0590178966522217, "global_step": 594327, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.053874969482422, "global_step": 594328, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9870113134384155, "global_step": 594329, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9873374700546265, "global_step": 594330, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.055814504623413, "global_step": 594331, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.021132230758667, "global_step": 594332, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0335562229156494, "global_step": 594333, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.05134654045105, "global_step": 594334, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.084486246109009, "global_step": 594335, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.001695156097412, "global_step": 594336, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0337870121002197, "global_step": 594337, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9930135011672974, "global_step": 594338, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0057759284973145, "global_step": 594339, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.057833433151245, "global_step": 594340, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0435492992401123, "global_step": 594341, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9880427122116089, "global_step": 594342, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.97853684425354, "global_step": 594343, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9869145154953003, "global_step": 594344, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0239884853363037, "global_step": 594345, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.030524253845215, "global_step": 594346, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0525169372558594, "global_step": 594347, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0229873657226562, "global_step": 594348, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0612881183624268, "global_step": 594349, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0190773010253906, "global_step": 594350, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9501830339431763, "global_step": 594351, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.005481719970703, "global_step": 594352, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.052682399749756, "global_step": 594353, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.997231125831604, "global_step": 594354, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9460147619247437, "global_step": 594355, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9384244680404663, "global_step": 594356, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.038090229034424, "global_step": 594357, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.035428047180176, "global_step": 594358, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9937233924865723, "global_step": 594359, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9469735622406006, "global_step": 594360, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.031904935836792, "global_step": 594361, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0607292652130127, "global_step": 594362, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0489718914031982, "global_step": 594363, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9664039611816406, "global_step": 594364, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0561935901641846, "global_step": 594365, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9865306615829468, "global_step": 594366, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9940321445465088, "global_step": 594367, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.999704360961914, "global_step": 594368, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.092407703399658, "global_step": 594369, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9607850313186646, "global_step": 594370, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.973171591758728, "global_step": 594371, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0273404121398926, "global_step": 594372, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0199077129364014, "global_step": 594373, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9839282035827637, "global_step": 594374, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9859154224395752, "global_step": 594375, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0973591804504395, "global_step": 594376, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9693634510040283, "global_step": 594377, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9737598896026611, "global_step": 594378, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0464601516723633, "global_step": 594379, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9928821325302124, "global_step": 594380, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9235306978225708, "global_step": 594381, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.061816930770874, "global_step": 594382, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0835518836975098, "global_step": 594383, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9822909832000732, "global_step": 594384, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9444763660430908, "global_step": 594385, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0821382999420166, "global_step": 594386, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0400116443634033, "global_step": 594387, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9163585901260376, "global_step": 594388, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.951506495475769, "global_step": 594389, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9995720386505127, "global_step": 594390, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0352489948272705, "global_step": 594391, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.068222761154175, "global_step": 594392, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0101728439331055, "global_step": 594393, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.114717960357666, "global_step": 594394, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9890385866165161, "global_step": 594395, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0350303649902344, "global_step": 594396, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0852224826812744, "global_step": 594397, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.1018474102020264, "global_step": 594398, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0301456451416016, "global_step": 594399, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.013007879257202, "global_step": 594400, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9795230627059937, "global_step": 594401, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.013160228729248, "global_step": 594402, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.044590950012207, "global_step": 594403, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.027615785598755, "global_step": 594404, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0075013637542725, "global_step": 594405, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0249407291412354, "global_step": 594406, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.926497459411621, "global_step": 594407, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.8950650691986084, "global_step": 594408, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9136378765106201, "global_step": 594409, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9787236452102661, "global_step": 594410, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0274410247802734, "global_step": 594411, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.029999256134033, "global_step": 594412, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.052027702331543, "global_step": 594413, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0127735137939453, "global_step": 594414, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.046811103820801, "global_step": 594415, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0781736373901367, "global_step": 594416, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0329418182373047, "global_step": 594417, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.071807384490967, "global_step": 594418, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.033228635787964, "global_step": 594419, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0481040477752686, "global_step": 594420, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9501359462738037, "global_step": 594421, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.98586106300354, "global_step": 594422, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9314063787460327, "global_step": 594423, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9628962278366089, "global_step": 594424, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0719785690307617, "global_step": 594425, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.056145668029785, "global_step": 594426, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9934906959533691, "global_step": 594427, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.063183307647705, "global_step": 594428, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9984592199325562, "global_step": 594429, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.080096960067749, "global_step": 594430, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.010608673095703, "global_step": 594431, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.010125160217285, "global_step": 594432, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.081423044204712, "global_step": 594433, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0495975017547607, "global_step": 594434, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0013504028320312, "global_step": 594435, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.053713321685791, "global_step": 594436, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9834710359573364, "global_step": 594437, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.02775502204895, "global_step": 594438, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.031787872314453, "global_step": 594439, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9542092084884644, "global_step": 594440, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0540714263916016, "global_step": 594441, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.03336238861084, "global_step": 594442, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0137064456939697, "global_step": 594443, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9889596700668335, "global_step": 594444, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.027968168258667, "global_step": 594445, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.019732713699341, "global_step": 594446, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9420349597930908, "global_step": 594447, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0662732124328613, "global_step": 594448, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9179213047027588, "global_step": 594449, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9859607219696045, "global_step": 594450, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.014453411102295, "global_step": 594451, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.060762643814087, "global_step": 594452, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0447323322296143, "global_step": 594453, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9336141347885132, "global_step": 594454, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9972317218780518, "global_step": 594455, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9994349479675293, "global_step": 594456, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.071794033050537, "global_step": 594457, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.038233757019043, "global_step": 594458, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.964428186416626, "global_step": 594459, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.064310312271118, "global_step": 594460, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9994268417358398, "global_step": 594461, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0284841060638428, "global_step": 594462, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.144623041152954, "global_step": 594463, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0640323162078857, "global_step": 594464, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.042479991912842, "global_step": 594465, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9796056747436523, "global_step": 594466, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9132441282272339, "global_step": 594467, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.02963924407959, "global_step": 594468, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.948100209236145, "global_step": 594469, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.063199996948242, "global_step": 594470, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9556684494018555, "global_step": 594471, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9713367223739624, "global_step": 594472, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0261309146881104, "global_step": 594473, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9997239112854004, "global_step": 594474, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.031400442123413, "global_step": 594475, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.084357261657715, "global_step": 594476, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0621554851531982, "global_step": 594477, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.014242172241211, "global_step": 594478, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9721651077270508, "global_step": 594479, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.059805393218994, "global_step": 594480, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.094727039337158, "global_step": 594481, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9367001056671143, "global_step": 594482, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0047388076782227, "global_step": 594483, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0191810131073, "global_step": 594484, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9387385845184326, "global_step": 594485, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0926146507263184, "global_step": 594486, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0970499515533447, "global_step": 594487, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0489413738250732, "global_step": 594488, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0268003940582275, "global_step": 594489, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0462124347686768, "global_step": 594490, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.917567491531372, "global_step": 594491, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.003758192062378, "global_step": 594492, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0897817611694336, "global_step": 594493, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9239873886108398, "global_step": 594494, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0220773220062256, "global_step": 594495, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0684690475463867, "global_step": 594496, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0923051834106445, "global_step": 594497, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9134047031402588, "global_step": 594498, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0069355964660645, "global_step": 594499, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.984229564666748, "global_step": 594500, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.005826950073242, "global_step": 594501, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0539445877075195, "global_step": 594502, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0127389430999756, "global_step": 594503, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9167203903198242, "global_step": 594504, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0391547679901123, "global_step": 594505, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9761645793914795, "global_step": 594506, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.959735631942749, "global_step": 594507, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0548086166381836, "global_step": 594508, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9979861974716187, "global_step": 594509, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0718472003936768, "global_step": 594510, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9828990697860718, "global_step": 594511, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0668859481811523, "global_step": 594512, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0015931129455566, "global_step": 594513, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9452372789382935, "global_step": 594514, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.02925968170166, "global_step": 594515, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9797534942626953, "global_step": 594516, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0381650924682617, "global_step": 594517, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.006740093231201, "global_step": 594518, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9326432943344116, "global_step": 594519, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.1042802333831787, "global_step": 594520, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9187308549880981, "global_step": 594521, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0334644317626953, "global_step": 594522, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.017174005508423, "global_step": 594523, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.1243391036987305, "global_step": 594524, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0714118480682373, "global_step": 594525, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0191357135772705, "global_step": 594526, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0256142616271973, "global_step": 594527, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9696544408798218, "global_step": 594528, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.960666537284851, "global_step": 594529, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.078032970428467, "global_step": 594530, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9986662864685059, "global_step": 594531, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9374417066574097, "global_step": 594532, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.965608835220337, "global_step": 594533, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0762388706207275, "global_step": 594534, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9560476541519165, "global_step": 594535, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.934442162513733, "global_step": 594536, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9491374492645264, "global_step": 594537, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9131402969360352, "global_step": 594538, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.972528338432312, "global_step": 594539, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9824979305267334, "global_step": 594540, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0405044555664062, "global_step": 594541, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9271717071533203, "global_step": 594542, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.041123628616333, "global_step": 594543, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.994558572769165, "global_step": 594544, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.043208122253418, "global_step": 594545, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.013315439224243, "global_step": 594546, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9696354866027832, "global_step": 594547, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0173091888427734, "global_step": 594548, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.019488573074341, "global_step": 594549, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0163345336914062, "global_step": 594550, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9831916093826294, "global_step": 594551, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9813121557235718, "global_step": 594552, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.063819646835327, "global_step": 594553, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0169167518615723, "global_step": 594554, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.032471179962158, "global_step": 594555, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9276081323623657, "global_step": 594556, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9847379922866821, "global_step": 594557, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.04583740234375, "global_step": 594558, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.022393226623535, "global_step": 594559, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.077491283416748, "global_step": 594560, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.005816698074341, "global_step": 594561, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.01371169090271, "global_step": 594562, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0717031955718994, "global_step": 594563, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9928548336029053, "global_step": 594564, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.931494116783142, "global_step": 594565, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0127217769622803, "global_step": 594566, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0641043186187744, "global_step": 594567, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0414843559265137, "global_step": 594568, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0462138652801514, "global_step": 594569, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.02156925201416, "global_step": 594570, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0864551067352295, "global_step": 594571, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9398155212402344, "global_step": 594572, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.012801170349121, "global_step": 594573, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0137288570404053, "global_step": 594574, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0358359813690186, "global_step": 594575, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.083160877227783, "global_step": 594576, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.045285701751709, "global_step": 594577, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.1131134033203125, "global_step": 594578, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.018268585205078, "global_step": 594579, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9359992742538452, "global_step": 594580, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9921092987060547, "global_step": 594581, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9796431064605713, "global_step": 594582, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.031292676925659, "global_step": 594583, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.016047716140747, "global_step": 594584, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9706676006317139, "global_step": 594585, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.990401268005371, "global_step": 594586, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0626370906829834, "global_step": 594587, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.035668134689331, "global_step": 594588, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0728721618652344, "global_step": 594589, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.103811025619507, "global_step": 594590, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.015328884124756, "global_step": 594591, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.023115634918213, "global_step": 594592, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.984015703201294, "global_step": 594593, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0415329933166504, "global_step": 594594, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9208316802978516, "global_step": 594595, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.025198221206665, "global_step": 594596, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.050682306289673, "global_step": 594597, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.943236231803894, "global_step": 594598, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0162923336029053, "global_step": 594599, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.997678279876709, "global_step": 594600, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.129021406173706, "global_step": 594601, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.098104238510132, "global_step": 594602, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0815269947052, "global_step": 594603, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9747627973556519, "global_step": 594604, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.019653797149658, "global_step": 594605, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.004521131515503, "global_step": 594606, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.009989023208618, "global_step": 594607, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9902921915054321, "global_step": 594608, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0508580207824707, "global_step": 594609, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9909807443618774, "global_step": 594610, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.031656265258789, "global_step": 594611, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0282251834869385, "global_step": 594612, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9970746040344238, "global_step": 594613, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0151801109313965, "global_step": 594614, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.05682110786438, "global_step": 594615, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.075181722640991, "global_step": 594616, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0122947692871094, "global_step": 594617, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0522327423095703, "global_step": 594618, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0830442905426025, "global_step": 594619, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0466175079345703, "global_step": 594620, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.022170066833496, "global_step": 594621, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9422025680541992, "global_step": 594622, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0401997566223145, "global_step": 594623, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9491984844207764, "global_step": 594624, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0164620876312256, "global_step": 594625, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.029078960418701, "global_step": 594626, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.054694890975952, "global_step": 594627, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0842132568359375, "global_step": 594628, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.955453872680664, "global_step": 594629, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0009686946868896, "global_step": 594630, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9966161251068115, "global_step": 594631, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.976071834564209, "global_step": 594632, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9551094770431519, "global_step": 594633, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0816264152526855, "global_step": 594634, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0213377475738525, "global_step": 594635, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.01249361038208, "global_step": 594636, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9745104312896729, "global_step": 594637, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.042820453643799, "global_step": 594638, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0231175422668457, "global_step": 594639, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0982041358947754, "global_step": 594640, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9628069400787354, "global_step": 594641, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.888438105583191, "global_step": 594642, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0296669006347656, "global_step": 594643, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0299761295318604, "global_step": 594644, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.917854905128479, "global_step": 594645, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9359087944030762, "global_step": 594646, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0029397010803223, "global_step": 594647, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0043275356292725, "global_step": 594648, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.1404693126678467, "global_step": 594649, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.036783218383789, "global_step": 594650, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.03578782081604, "global_step": 594651, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9406111240386963, "global_step": 594652, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0427708625793457, "global_step": 594653, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9937885999679565, "global_step": 594654, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9888584613800049, "global_step": 594655, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9878019094467163, "global_step": 594656, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9398707151412964, "global_step": 594657, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.00679087638855, "global_step": 594658, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0814220905303955, "global_step": 594659, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9791864156723022, "global_step": 594660, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.018450975418091, "global_step": 594661, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0544381141662598, "global_step": 594662, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0492420196533203, "global_step": 594663, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9952514171600342, "global_step": 594664, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.07545804977417, "global_step": 594665, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0160067081451416, "global_step": 594666, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0333027839660645, "global_step": 594667, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0842838287353516, "global_step": 594668, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0445473194122314, "global_step": 594669, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0227246284484863, "global_step": 594670, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.02803111076355, "global_step": 594671, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.083604335784912, "global_step": 594672, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0123586654663086, "global_step": 594673, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9775527715682983, "global_step": 594674, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0435452461242676, "global_step": 594675, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.042642593383789, "global_step": 594676, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0687811374664307, "global_step": 594677, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.002863645553589, "global_step": 594678, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.991114854812622, "global_step": 594679, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0272867679595947, "global_step": 594680, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9774560928344727, "global_step": 594681, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.945334792137146, "global_step": 594682, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0275914669036865, "global_step": 594683, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.979797124862671, "global_step": 594684, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0647058486938477, "global_step": 594685, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0569801330566406, "global_step": 594686, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9783529043197632, "global_step": 594687, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.070411443710327, "global_step": 594688, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.1094982624053955, "global_step": 594689, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0338234901428223, "global_step": 594690, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9894179105758667, "global_step": 594691, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0263140201568604, "global_step": 594692, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.075956344604492, "global_step": 594693, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9124844074249268, "global_step": 594694, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.025078296661377, "global_step": 594695, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9678058624267578, "global_step": 594696, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.008145332336426, "global_step": 594697, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9571645259857178, "global_step": 594698, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0169031620025635, "global_step": 594699, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9461545944213867, "global_step": 594700, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0567033290863037, "global_step": 594701, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0283172130584717, "global_step": 594702, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0560054779052734, "global_step": 594703, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0087807178497314, "global_step": 594704, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0467309951782227, "global_step": 594705, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9886571168899536, "global_step": 594706, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0555403232574463, "global_step": 594707, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9878809452056885, "global_step": 594708, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0953474044799805, "global_step": 594709, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.959477424621582, "global_step": 594710, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.094087839126587, "global_step": 594711, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.083583354949951, "global_step": 594712, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0246422290802, "global_step": 594713, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9887994527816772, "global_step": 594714, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9479541778564453, "global_step": 594715, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.062777519226074, "global_step": 594716, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0666871070861816, "global_step": 594717, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.056443214416504, "global_step": 594718, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9630513191223145, "global_step": 594719, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.954071283340454, "global_step": 594720, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0012307167053223, "global_step": 594721, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9800748825073242, "global_step": 594722, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.923575758934021, "global_step": 594723, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0094950199127197, "global_step": 594724, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0566627979278564, "global_step": 594725, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0378923416137695, "global_step": 594726, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0105185508728027, "global_step": 594727, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.976341724395752, "global_step": 594728, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9984050989151, "global_step": 594729, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9874321222305298, "global_step": 594730, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9188377857208252, "global_step": 594731, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.1088790893554688, "global_step": 594732, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.049037218093872, "global_step": 594733, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.082552433013916, "global_step": 594734, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9871512651443481, "global_step": 594735, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0988190174102783, "global_step": 594736, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9959931373596191, "global_step": 594737, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.972133755683899, "global_step": 594738, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0525383949279785, "global_step": 594739, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.09330677986145, "global_step": 594740, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.013669967651367, "global_step": 594741, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0504753589630127, "global_step": 594742, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0529980659484863, "global_step": 594743, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9333219528198242, "global_step": 594744, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.059870481491089, "global_step": 594745, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.120070219039917, "global_step": 594746, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9985520839691162, "global_step": 594747, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.009892225265503, "global_step": 594748, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9800077676773071, "global_step": 594749, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.033474922180176, "global_step": 594750, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9970550537109375, "global_step": 594751, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.973167061805725, "global_step": 594752, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9284478425979614, "global_step": 594753, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9936418533325195, "global_step": 594754, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9433948993682861, "global_step": 594755, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9887378215789795, "global_step": 594756, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9381130933761597, "global_step": 594757, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0444231033325195, "global_step": 594758, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.003432512283325, "global_step": 594759, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9826961755752563, "global_step": 594760, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.084181070327759, "global_step": 594761, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9985477924346924, "global_step": 594762, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0774104595184326, "global_step": 594763, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9376320838928223, "global_step": 594764, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0272011756896973, "global_step": 594765, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0360634326934814, "global_step": 594766, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9978760480880737, "global_step": 594767, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0619125366210938, "global_step": 594768, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0726544857025146, "global_step": 594769, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0425078868865967, "global_step": 594770, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0603439807891846, "global_step": 594771, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.036234140396118, "global_step": 594772, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.065276622772217, "global_step": 594773, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0584051609039307, "global_step": 594774, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0100784301757812, "global_step": 594775, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9175623655319214, "global_step": 594776, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0673303604125977, "global_step": 594777, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0015499591827393, "global_step": 594778, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0511057376861572, "global_step": 594779, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.007080554962158, "global_step": 594780, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.047485113143921, "global_step": 594781, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.03999662399292, "global_step": 594782, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.029047727584839, "global_step": 594783, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0727345943450928, "global_step": 594784, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9970391988754272, "global_step": 594785, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.923835277557373, "global_step": 594786, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0236213207244873, "global_step": 594787, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.01232647895813, "global_step": 594788, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.07552433013916, "global_step": 594789, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0525548458099365, "global_step": 594790, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9885412454605103, "global_step": 594791, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9765368700027466, "global_step": 594792, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.009122371673584, "global_step": 594793, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.043126106262207, "global_step": 594794, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0152957439422607, "global_step": 594795, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.960452914237976, "global_step": 594796, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9937244653701782, "global_step": 594797, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.8990540504455566, "global_step": 594798, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.033302068710327, "global_step": 594799, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9923733472824097, "global_step": 594800, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.006368637084961, "global_step": 594801, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.004737377166748, "global_step": 594802, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.070744514465332, "global_step": 594803, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.996232509613037, "global_step": 594804, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0237011909484863, "global_step": 594805, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0584189891815186, "global_step": 594806, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.001309871673584, "global_step": 594807, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9972184896469116, "global_step": 594808, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0902364253997803, "global_step": 594809, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0883638858795166, "global_step": 594810, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.012742280960083, "global_step": 594811, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.00693416595459, "global_step": 594812, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9709255695343018, "global_step": 594813, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9783812761306763, "global_step": 594814, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9720591306686401, "global_step": 594815, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9597042798995972, "global_step": 594816, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0016562938690186, "global_step": 594817, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.00470232963562, "global_step": 594818, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9932729005813599, "global_step": 594819, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0414204597473145, "global_step": 594820, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0151329040527344, "global_step": 594821, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9429855346679688, "global_step": 594822, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.007331371307373, "global_step": 594823, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0147082805633545, "global_step": 594824, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.022402763366699, "global_step": 594825, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.016122579574585, "global_step": 594826, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0483694076538086, "global_step": 594827, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0370664596557617, "global_step": 594828, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9387990236282349, "global_step": 594829, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0580337047576904, "global_step": 594830, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0895166397094727, "global_step": 594831, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.042492151260376, "global_step": 594832, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9663832187652588, "global_step": 594833, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0476033687591553, "global_step": 594834, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9677391052246094, "global_step": 594835, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0871927738189697, "global_step": 594836, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0275611877441406, "global_step": 594837, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0787153244018555, "global_step": 594838, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0365066528320312, "global_step": 594839, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9296720027923584, "global_step": 594840, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9916293621063232, "global_step": 594841, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.1450207233428955, "global_step": 594842, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.978494644165039, "global_step": 594843, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0215113162994385, "global_step": 594844, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.069159746170044, "global_step": 594845, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9746613502502441, "global_step": 594846, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9541438817977905, "global_step": 594847, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0012381076812744, "global_step": 594848, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0243475437164307, "global_step": 594849, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9673349857330322, "global_step": 594850, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9768162965774536, "global_step": 594851, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9308756589889526, "global_step": 594852, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.012625217437744, "global_step": 594853, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.034421682357788, "global_step": 594854, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.043572425842285, "global_step": 594855, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0294814109802246, "global_step": 594856, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9808523654937744, "global_step": 594857, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9278526306152344, "global_step": 594858, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9852474927902222, "global_step": 594859, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9611388444900513, "global_step": 594860, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.984757423400879, "global_step": 594861, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0091090202331543, "global_step": 594862, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.025881767272949, "global_step": 594863, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0250844955444336, "global_step": 594864, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.058763027191162, "global_step": 594865, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9996827840805054, "global_step": 594866, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.989119529724121, "global_step": 594867, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0708682537078857, "global_step": 594868, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9798117876052856, "global_step": 594869, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.095015525817871, "global_step": 594870, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.977424144744873, "global_step": 594871, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0137953758239746, "global_step": 594872, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.008378267288208, "global_step": 594873, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.962925910949707, "global_step": 594874, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9568109512329102, "global_step": 594875, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9873684644699097, "global_step": 594876, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9152964353561401, "global_step": 594877, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9681698083877563, "global_step": 594878, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.047991991043091, "global_step": 594879, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0042386054992676, "global_step": 594880, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.089723587036133, "global_step": 594881, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.015742778778076, "global_step": 594882, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.001889705657959, "global_step": 594883, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0295581817626953, "global_step": 594884, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0507187843322754, "global_step": 594885, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0586860179901123, "global_step": 594886, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.8858364820480347, "global_step": 594887, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.010033369064331, "global_step": 594888, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0405240058898926, "global_step": 594889, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.032602310180664, "global_step": 594890, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0540783405303955, "global_step": 594891, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.95832097530365, "global_step": 594892, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.901450753211975, "global_step": 594893, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9931261539459229, "global_step": 594894, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.074117422103882, "global_step": 594895, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0277888774871826, "global_step": 594896, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.021677255630493, "global_step": 594897, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.012735605239868, "global_step": 594898, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.975667953491211, "global_step": 594899, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.082551956176758, "global_step": 594900, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9725745916366577, "global_step": 594901, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.8716458082199097, "global_step": 594902, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.04954195022583, "global_step": 594903, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9831507205963135, "global_step": 594904, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.016035795211792, "global_step": 594905, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.030484199523926, "global_step": 594906, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0104682445526123, "global_step": 594907, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0515284538269043, "global_step": 594908, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0120489597320557, "global_step": 594909, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.022970676422119, "global_step": 594910, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0603253841400146, "global_step": 594911, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9836080074310303, "global_step": 594912, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0001604557037354, "global_step": 594913, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0748298168182373, "global_step": 594914, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.063612699508667, "global_step": 594915, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0817058086395264, "global_step": 594916, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0070149898529053, "global_step": 594917, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.008350372314453, "global_step": 594918, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9727686643600464, "global_step": 594919, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.938717246055603, "global_step": 594920, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.963409185409546, "global_step": 594921, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.8555634021759033, "global_step": 594922, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.069809913635254, "global_step": 594923, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.030211925506592, "global_step": 594924, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.013042688369751, "global_step": 594925, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.965871810913086, "global_step": 594926, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9652155637741089, "global_step": 594927, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0039732456207275, "global_step": 594928, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.024183511734009, "global_step": 594929, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.068979501724243, "global_step": 594930, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.014713764190674, "global_step": 594931, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.023754596710205, "global_step": 594932, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.991303563117981, "global_step": 594933, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.037613868713379, "global_step": 594934, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0262770652770996, "global_step": 594935, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.023200273513794, "global_step": 594936, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.046801805496216, "global_step": 594937, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.004232168197632, "global_step": 594938, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0645344257354736, "global_step": 594939, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0581908226013184, "global_step": 594940, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.961783528327942, "global_step": 594941, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0471198558807373, "global_step": 594942, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.008835792541504, "global_step": 594943, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0473339557647705, "global_step": 594944, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.031385660171509, "global_step": 594945, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.023617744445801, "global_step": 594946, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.036972999572754, "global_step": 594947, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0403802394866943, "global_step": 594948, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0257928371429443, "global_step": 594949, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.985133171081543, "global_step": 594950, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0681605339050293, "global_step": 594951, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0102591514587402, "global_step": 594952, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9217910766601562, "global_step": 594953, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9962517023086548, "global_step": 594954, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.023503065109253, "global_step": 594955, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.014725923538208, "global_step": 594956, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.111490488052368, "global_step": 594957, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.026923179626465, "global_step": 594958, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.104548215866089, "global_step": 594959, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9640549421310425, "global_step": 594960, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0059752464294434, "global_step": 594961, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0544538497924805, "global_step": 594962, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.012730360031128, "global_step": 594963, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0267984867095947, "global_step": 594964, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0956666469573975, "global_step": 594965, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0461041927337646, "global_step": 594966, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.020728588104248, "global_step": 594967, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0921554565429688, "global_step": 594968, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0186092853546143, "global_step": 594969, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.033686399459839, "global_step": 594970, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9745676517486572, "global_step": 594971, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9972223043441772, "global_step": 594972, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0448837280273438, "global_step": 594973, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9848101139068604, "global_step": 594974, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9813400506973267, "global_step": 594975, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.979308843612671, "global_step": 594976, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0969083309173584, "global_step": 594977, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0162861347198486, "global_step": 594978, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0442442893981934, "global_step": 594979, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.99034583568573, "global_step": 594980, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9644906520843506, "global_step": 594981, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0334911346435547, "global_step": 594982, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0239930152893066, "global_step": 594983, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.927141547203064, "global_step": 594984, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.035259485244751, "global_step": 594985, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0612599849700928, "global_step": 594986, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9735063314437866, "global_step": 594987, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.1417503356933594, "global_step": 594988, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.024831533432007, "global_step": 594989, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.038087844848633, "global_step": 594990, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0157480239868164, "global_step": 594991, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0246431827545166, "global_step": 594992, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9715731143951416, "global_step": 594993, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9770774841308594, "global_step": 594994, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0160861015319824, "global_step": 594995, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9916493892669678, "global_step": 594996, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0761027336120605, "global_step": 594997, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.020202398300171, "global_step": 594998, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.956210732460022, "global_step": 594999, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0185561180114746, "global_step": 595000, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.934577465057373, "global_step": 595001, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.079486608505249, "global_step": 595002, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.027743339538574, "global_step": 595003, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0246450901031494, "global_step": 595004, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9189965724945068, "global_step": 595005, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.969546914100647, "global_step": 595006, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9211207628250122, "global_step": 595007, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0285842418670654, "global_step": 595008, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.064605474472046, "global_step": 595009, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.084299325942993, "global_step": 595010, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9205467700958252, "global_step": 595011, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0724990367889404, "global_step": 595012, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.079063892364502, "global_step": 595013, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.039299249649048, "global_step": 595014, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0224688053131104, "global_step": 595015, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0370864868164062, "global_step": 595016, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0687146186828613, "global_step": 595017, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9198578596115112, "global_step": 595018, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.065314292907715, "global_step": 595019, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9875786304473877, "global_step": 595020, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0220134258270264, "global_step": 595021, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9529273509979248, "global_step": 595022, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.073143243789673, "global_step": 595023, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.939907431602478, "global_step": 595024, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.052306890487671, "global_step": 595025, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9786325693130493, "global_step": 595026, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0376996994018555, "global_step": 595027, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0645906925201416, "global_step": 595028, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.1362342834472656, "global_step": 595029, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9745007753372192, "global_step": 595030, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.033160448074341, "global_step": 595031, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.048050880432129, "global_step": 595032, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9791401624679565, "global_step": 595033, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0005757808685303, "global_step": 595034, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.96847665309906, "global_step": 595035, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9391297101974487, "global_step": 595036, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.02070951461792, "global_step": 595037, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.059065818786621, "global_step": 595038, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0843725204467773, "global_step": 595039, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0705137252807617, "global_step": 595040, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9513825178146362, "global_step": 595041, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0097992420196533, "global_step": 595042, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.996242642402649, "global_step": 595043, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9455503225326538, "global_step": 595044, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.005436658859253, "global_step": 595045, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0116055011749268, "global_step": 595046, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9819610118865967, "global_step": 595047, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0405588150024414, "global_step": 595048, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.061034917831421, "global_step": 595049, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0465011596679688, "global_step": 595050, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0343353748321533, "global_step": 595051, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9540408849716187, "global_step": 595052, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9955828189849854, "global_step": 595053, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0460774898529053, "global_step": 595054, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0892832279205322, "global_step": 595055, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.988312840461731, "global_step": 595056, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.178065299987793, "global_step": 595057, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0395429134368896, "global_step": 595058, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.02309250831604, "global_step": 595059, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.098299264907837, "global_step": 595060, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0504794120788574, "global_step": 595061, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.026386260986328, "global_step": 595062, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0388684272766113, "global_step": 595063, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.037390947341919, "global_step": 595064, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.002378463745117, "global_step": 595065, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0724711418151855, "global_step": 595066, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0546560287475586, "global_step": 595067, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0157949924468994, "global_step": 595068, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.053734064102173, "global_step": 595069, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.980179786682129, "global_step": 595070, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0119762420654297, "global_step": 595071, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.1004269123077393, "global_step": 595072, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0888326168060303, "global_step": 595073, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.036973714828491, "global_step": 595074, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.996946096420288, "global_step": 595075, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9959461688995361, "global_step": 595076, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9989179372787476, "global_step": 595077, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9303152561187744, "global_step": 595078, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.010735034942627, "global_step": 595079, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.07474684715271, "global_step": 595080, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.09036922454834, "global_step": 595081, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.081648588180542, "global_step": 595082, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.020814895629883, "global_step": 595083, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.059290647506714, "global_step": 595084, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.032223701477051, "global_step": 595085, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.04780912399292, "global_step": 595086, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.054986000061035, "global_step": 595087, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0193965435028076, "global_step": 595088, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.057673931121826, "global_step": 595089, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.061436176300049, "global_step": 595090, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.022322416305542, "global_step": 595091, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0631518363952637, "global_step": 595092, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.007547616958618, "global_step": 595093, "epoch": 963, "lr": 5e-05}
{"train_loss": 1.9900840520858765, "global_step": 595094, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0212950706481934, "global_step": 595095, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.00057315826416, "global_step": 595096, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.006204605102539, "global_step": 595097, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.014394760131836, "global_step": 595098, "epoch": 963, "lr": 5e-05}
{"train_loss": 2.0299925804138184, "global_step": 595099, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0826926231384277, "global_step": 595100, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.070841073989868, "global_step": 595101, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.021895170211792, "global_step": 595102, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0105764865875244, "global_step": 595103, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9844560623168945, "global_step": 595104, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0370113849639893, "global_step": 595105, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0108673572540283, "global_step": 595106, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.997956395149231, "global_step": 595107, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9955253601074219, "global_step": 595108, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0580573081970215, "global_step": 595109, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.994084119796753, "global_step": 595110, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0127744674682617, "global_step": 595111, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.128262758255005, "global_step": 595112, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9934216737747192, "global_step": 595113, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9329659938812256, "global_step": 595114, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.057389974594116, "global_step": 595115, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.059004545211792, "global_step": 595116, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.02691912651062, "global_step": 595117, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.930418610572815, "global_step": 595118, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.936001181602478, "global_step": 595119, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.017293691635132, "global_step": 595120, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0446810722351074, "global_step": 595121, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.975887417793274, "global_step": 595122, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.017195701599121, "global_step": 595123, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.8985844850540161, "global_step": 595124, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9723036289215088, "global_step": 595125, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0545570850372314, "global_step": 595126, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0269336700439453, "global_step": 595127, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.058995246887207, "global_step": 595128, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.062727928161621, "global_step": 595129, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.106348752975464, "global_step": 595130, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.077064275741577, "global_step": 595131, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.996256947517395, "global_step": 595132, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9651788473129272, "global_step": 595133, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0249807834625244, "global_step": 595134, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0517938137054443, "global_step": 595135, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0536515712738037, "global_step": 595136, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9044634103775024, "global_step": 595137, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9856033325195312, "global_step": 595138, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.993619441986084, "global_step": 595139, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9810395240783691, "global_step": 595140, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0337467193603516, "global_step": 595141, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9856798648834229, "global_step": 595142, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.1306099891662598, "global_step": 595143, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9839918613433838, "global_step": 595144, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0162620544433594, "global_step": 595145, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.044823408126831, "global_step": 595146, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0094380378723145, "global_step": 595147, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0769999027252197, "global_step": 595148, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9474916458129883, "global_step": 595149, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9235445261001587, "global_step": 595150, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9883171319961548, "global_step": 595151, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0020477771759033, "global_step": 595152, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.059467077255249, "global_step": 595153, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0044195652008057, "global_step": 595154, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9145232439041138, "global_step": 595155, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.00142240524292, "global_step": 595156, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9700617790222168, "global_step": 595157, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.04146671295166, "global_step": 595158, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9809786081314087, "global_step": 595159, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9433653354644775, "global_step": 595160, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0210659503936768, "global_step": 595161, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9870632886886597, "global_step": 595162, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.033252000808716, "global_step": 595163, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.969130039215088, "global_step": 595164, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9677623510360718, "global_step": 595165, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9374563694000244, "global_step": 595166, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0457565784454346, "global_step": 595167, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0740768909454346, "global_step": 595168, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0510730743408203, "global_step": 595169, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0163791179656982, "global_step": 595170, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9595402479171753, "global_step": 595171, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9959330558776855, "global_step": 595172, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9984817504882812, "global_step": 595173, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.023865222930908, "global_step": 595174, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9681310653686523, "global_step": 595175, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0450267791748047, "global_step": 595176, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9598394632339478, "global_step": 595177, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.017301321029663, "global_step": 595178, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.944833517074585, "global_step": 595179, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0283918380737305, "global_step": 595180, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0234086513519287, "global_step": 595181, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0168535709381104, "global_step": 595182, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9637035131454468, "global_step": 595183, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9912410974502563, "global_step": 595184, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0802669525146484, "global_step": 595185, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9832485914230347, "global_step": 595186, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9287877082824707, "global_step": 595187, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.022130012512207, "global_step": 595188, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.109149932861328, "global_step": 595189, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0570192337036133, "global_step": 595190, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9058332443237305, "global_step": 595191, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.00055193901062, "global_step": 595192, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.022853136062622, "global_step": 595193, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9839125871658325, "global_step": 595194, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0047969818115234, "global_step": 595195, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.038939952850342, "global_step": 595196, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0022428035736084, "global_step": 595197, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.1101326942443848, "global_step": 595198, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0511178970336914, "global_step": 595199, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.071964979171753, "global_step": 595200, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9387738704681396, "global_step": 595201, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9775958061218262, "global_step": 595202, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9727771282196045, "global_step": 595203, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.111570119857788, "global_step": 595204, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.05148983001709, "global_step": 595205, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9609285593032837, "global_step": 595206, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9958280324935913, "global_step": 595207, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.010694742202759, "global_step": 595208, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9900521039962769, "global_step": 595209, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0095303058624268, "global_step": 595210, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.002213954925537, "global_step": 595211, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.039304494857788, "global_step": 595212, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9722951650619507, "global_step": 595213, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0226240158081055, "global_step": 595214, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9632014036178589, "global_step": 595215, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0410256385803223, "global_step": 595216, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9896248579025269, "global_step": 595217, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0095362663269043, "global_step": 595218, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.8990482091903687, "global_step": 595219, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9567047357559204, "global_step": 595220, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9281357526779175, "global_step": 595221, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.047179937362671, "global_step": 595222, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0146775245666504, "global_step": 595223, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.055144786834717, "global_step": 595224, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.066969394683838, "global_step": 595225, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.00483775138855, "global_step": 595226, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.95335853099823, "global_step": 595227, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0754451751708984, "global_step": 595228, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0157506465911865, "global_step": 595229, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.8885645866394043, "global_step": 595230, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9933255910873413, "global_step": 595231, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9991151094436646, "global_step": 595232, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0267858505249023, "global_step": 595233, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.916713833808899, "global_step": 595234, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9431477785110474, "global_step": 595235, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.955901861190796, "global_step": 595236, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0257222652435303, "global_step": 595237, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9734041690826416, "global_step": 595238, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0259528160095215, "global_step": 595239, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.024176597595215, "global_step": 595240, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0871715545654297, "global_step": 595241, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0289254188537598, "global_step": 595242, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0362417697906494, "global_step": 595243, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.935563325881958, "global_step": 595244, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9894468784332275, "global_step": 595245, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0386016368865967, "global_step": 595246, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9490861892700195, "global_step": 595247, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9768764972686768, "global_step": 595248, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9668794870376587, "global_step": 595249, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.964156150817871, "global_step": 595250, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9418675899505615, "global_step": 595251, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0078275203704834, "global_step": 595252, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0521950721740723, "global_step": 595253, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9591326713562012, "global_step": 595254, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9180634021759033, "global_step": 595255, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0461509227752686, "global_step": 595256, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9624569416046143, "global_step": 595257, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0087573528289795, "global_step": 595258, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0349926948547363, "global_step": 595259, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.985382080078125, "global_step": 595260, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0051140785217285, "global_step": 595261, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9406167268753052, "global_step": 595262, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0562403202056885, "global_step": 595263, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.982081413269043, "global_step": 595264, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.082038164138794, "global_step": 595265, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9750545024871826, "global_step": 595266, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9720979928970337, "global_step": 595267, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9463216066360474, "global_step": 595268, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0613889694213867, "global_step": 595269, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.012162923812866, "global_step": 595270, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.999119520187378, "global_step": 595271, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.065277338027954, "global_step": 595272, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9902985095977783, "global_step": 595273, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9311819076538086, "global_step": 595274, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9877561330795288, "global_step": 595275, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.8922711610794067, "global_step": 595276, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.968397855758667, "global_step": 595277, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9893053770065308, "global_step": 595278, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9289686679840088, "global_step": 595279, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.059504985809326, "global_step": 595280, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9478987455368042, "global_step": 595281, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0460634231567383, "global_step": 595282, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9378944635391235, "global_step": 595283, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0540249347686768, "global_step": 595284, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.073805809020996, "global_step": 595285, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.025514602661133, "global_step": 595286, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.109560489654541, "global_step": 595287, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9254493713378906, "global_step": 595288, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.938697099685669, "global_step": 595289, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0926477909088135, "global_step": 595290, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0409841537475586, "global_step": 595291, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9835906028747559, "global_step": 595292, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9919019937515259, "global_step": 595293, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9579174518585205, "global_step": 595294, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0450034141540527, "global_step": 595295, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0847511291503906, "global_step": 595296, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0376033782958984, "global_step": 595297, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0764079093933105, "global_step": 595298, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0608530044555664, "global_step": 595299, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0131821632385254, "global_step": 595300, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.972643494606018, "global_step": 595301, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0630078315734863, "global_step": 595302, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9760210514068604, "global_step": 595303, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9734913110733032, "global_step": 595304, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.034268617630005, "global_step": 595305, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.999552845954895, "global_step": 595306, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9115855693817139, "global_step": 595307, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9833052158355713, "global_step": 595308, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9908825159072876, "global_step": 595309, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9619150161743164, "global_step": 595310, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.946736216545105, "global_step": 595311, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.036087989807129, "global_step": 595312, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9646915197372437, "global_step": 595313, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0237598419189453, "global_step": 595314, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0344011783599854, "global_step": 595315, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.091991424560547, "global_step": 595316, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0021326541900635, "global_step": 595317, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.99736750125885, "global_step": 595318, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9830753803253174, "global_step": 595319, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9966931343078613, "global_step": 595320, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.009963274002075, "global_step": 595321, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.028355360031128, "global_step": 595322, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.038347005844116, "global_step": 595323, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9775155782699585, "global_step": 595324, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.993753433227539, "global_step": 595325, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0689451694488525, "global_step": 595326, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9825738668441772, "global_step": 595327, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9170283079147339, "global_step": 595328, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9271749258041382, "global_step": 595329, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.945249080657959, "global_step": 595330, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9849975109100342, "global_step": 595331, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9664446115493774, "global_step": 595332, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.981116533279419, "global_step": 595333, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.932288646697998, "global_step": 595334, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.003971815109253, "global_step": 595335, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.009859800338745, "global_step": 595336, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.032747983932495, "global_step": 595337, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.00067400932312, "global_step": 595338, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0246968269348145, "global_step": 595339, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9895243644714355, "global_step": 595340, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9917901754379272, "global_step": 595341, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9808646440505981, "global_step": 595342, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.008418083190918, "global_step": 595343, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9672435522079468, "global_step": 595344, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9171987771987915, "global_step": 595345, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0366432666778564, "global_step": 595346, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.053809642791748, "global_step": 595347, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.073582649230957, "global_step": 595348, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.003535270690918, "global_step": 595349, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9540061950683594, "global_step": 595350, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0764973163604736, "global_step": 595351, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.982797384262085, "global_step": 595352, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.968475103378296, "global_step": 595353, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.980460286140442, "global_step": 595354, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.960050344467163, "global_step": 595355, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9596331119537354, "global_step": 595356, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0025384426116943, "global_step": 595357, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0387072563171387, "global_step": 595358, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.02734112739563, "global_step": 595359, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0775420665740967, "global_step": 595360, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9741102457046509, "global_step": 595361, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.023083209991455, "global_step": 595362, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.086444139480591, "global_step": 595363, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0340821743011475, "global_step": 595364, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9919620752334595, "global_step": 595365, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0732529163360596, "global_step": 595366, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9271882772445679, "global_step": 595367, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0535645484924316, "global_step": 595368, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9812726974487305, "global_step": 595369, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0099782943725586, "global_step": 595370, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9646426439285278, "global_step": 595371, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.076223134994507, "global_step": 595372, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9831342697143555, "global_step": 595373, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0011141300201416, "global_step": 595374, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9912488460540771, "global_step": 595375, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.165416717529297, "global_step": 595376, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.008425712585449, "global_step": 595377, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0542454719543457, "global_step": 595378, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.00199031829834, "global_step": 595379, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9820502996444702, "global_step": 595380, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9823862314224243, "global_step": 595381, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.967878818511963, "global_step": 595382, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.034478187561035, "global_step": 595383, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0091724395751953, "global_step": 595384, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9987928867340088, "global_step": 595385, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.012192964553833, "global_step": 595386, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0701465606689453, "global_step": 595387, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0144894123077393, "global_step": 595388, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.049642562866211, "global_step": 595389, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9387091398239136, "global_step": 595390, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0181493759155273, "global_step": 595391, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0495238304138184, "global_step": 595392, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.066848039627075, "global_step": 595393, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.108609914779663, "global_step": 595394, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.019524097442627, "global_step": 595395, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9986451864242554, "global_step": 595396, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9378613233566284, "global_step": 595397, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.976319432258606, "global_step": 595398, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.023249626159668, "global_step": 595399, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.064859628677368, "global_step": 595400, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.081693410873413, "global_step": 595401, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9495980739593506, "global_step": 595402, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.969420313835144, "global_step": 595403, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9205650091171265, "global_step": 595404, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.077530860900879, "global_step": 595405, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0182676315307617, "global_step": 595406, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.047598123550415, "global_step": 595407, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.096430540084839, "global_step": 595408, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.946293592453003, "global_step": 595409, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9634149074554443, "global_step": 595410, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.936846137046814, "global_step": 595411, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.073812484741211, "global_step": 595412, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9948394298553467, "global_step": 595413, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0577313899993896, "global_step": 595414, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0817840099334717, "global_step": 595415, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9573304653167725, "global_step": 595416, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.016258478164673, "global_step": 595417, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.042555332183838, "global_step": 595418, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9945437908172607, "global_step": 595419, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.070878744125366, "global_step": 595420, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.062166690826416, "global_step": 595421, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0536019802093506, "global_step": 595422, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9617284536361694, "global_step": 595423, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0683557987213135, "global_step": 595424, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9833210706710815, "global_step": 595425, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.975234031677246, "global_step": 595426, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9925711154937744, "global_step": 595427, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0314137935638428, "global_step": 595428, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0311882495880127, "global_step": 595429, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0707876682281494, "global_step": 595430, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.8942689895629883, "global_step": 595431, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0220768451690674, "global_step": 595432, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.087721109390259, "global_step": 595433, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.997564435005188, "global_step": 595434, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0820868015289307, "global_step": 595435, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9509421586990356, "global_step": 595436, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9668922424316406, "global_step": 595437, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9829813241958618, "global_step": 595438, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9401909112930298, "global_step": 595439, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0466179847717285, "global_step": 595440, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0072786808013916, "global_step": 595441, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0103797912597656, "global_step": 595442, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9268525838851929, "global_step": 595443, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.1055941581726074, "global_step": 595444, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9937891960144043, "global_step": 595445, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0702126026153564, "global_step": 595446, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0024118423461914, "global_step": 595447, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0645205974578857, "global_step": 595448, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0293383598327637, "global_step": 595449, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.1241817474365234, "global_step": 595450, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.050234317779541, "global_step": 595451, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.054687976837158, "global_step": 595452, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0607573986053467, "global_step": 595453, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9563559293746948, "global_step": 595454, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.01393723487854, "global_step": 595455, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9702953100204468, "global_step": 595456, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.944681167602539, "global_step": 595457, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9853202104568481, "global_step": 595458, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0400800704956055, "global_step": 595459, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0735533237457275, "global_step": 595460, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9694082736968994, "global_step": 595461, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0125272274017334, "global_step": 595462, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9440447092056274, "global_step": 595463, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9841586351394653, "global_step": 595464, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.975001335144043, "global_step": 595465, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.01833438873291, "global_step": 595466, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.062539577484131, "global_step": 595467, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9974727630615234, "global_step": 595468, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.973490595817566, "global_step": 595469, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9913597106933594, "global_step": 595470, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.011131525039673, "global_step": 595471, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.019474983215332, "global_step": 595472, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.8977923393249512, "global_step": 595473, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.025317430496216, "global_step": 595474, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0222063064575195, "global_step": 595475, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9532617330551147, "global_step": 595476, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0089383125305176, "global_step": 595477, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9319475889205933, "global_step": 595478, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.1009912490844727, "global_step": 595479, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.959465503692627, "global_step": 595480, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9961152076721191, "global_step": 595481, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0974574089050293, "global_step": 595482, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.018543004989624, "global_step": 595483, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9714205265045166, "global_step": 595484, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9947329759597778, "global_step": 595485, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.962730884552002, "global_step": 595486, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9673353433609009, "global_step": 595487, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.022878408432007, "global_step": 595488, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.021355390548706, "global_step": 595489, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.1024622917175293, "global_step": 595490, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9249603748321533, "global_step": 595491, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0652847290039062, "global_step": 595492, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0080809593200684, "global_step": 595493, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.1075756549835205, "global_step": 595494, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.053274154663086, "global_step": 595495, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9567652940750122, "global_step": 595496, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9769296646118164, "global_step": 595497, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0333144664764404, "global_step": 595498, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.00992488861084, "global_step": 595499, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9923627376556396, "global_step": 595500, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0245249271392822, "global_step": 595501, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9307091236114502, "global_step": 595502, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0407731533050537, "global_step": 595503, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.07369327545166, "global_step": 595504, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9806126356124878, "global_step": 595505, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0400381088256836, "global_step": 595506, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.918183445930481, "global_step": 595507, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9998462200164795, "global_step": 595508, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.1185667514801025, "global_step": 595509, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.00738787651062, "global_step": 595510, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0307374000549316, "global_step": 595511, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0224828720092773, "global_step": 595512, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.03179669380188, "global_step": 595513, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.009632110595703, "global_step": 595514, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0345346927642822, "global_step": 595515, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.901556134223938, "global_step": 595516, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.8783313035964966, "global_step": 595517, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0368449687957764, "global_step": 595518, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0562098026275635, "global_step": 595519, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.031604766845703, "global_step": 595520, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.073173999786377, "global_step": 595521, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0508859157562256, "global_step": 595522, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9928946495056152, "global_step": 595523, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0510432720184326, "global_step": 595524, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0657267570495605, "global_step": 595525, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0006062984466553, "global_step": 595526, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.02811861038208, "global_step": 595527, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9724493026733398, "global_step": 595528, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0375282764434814, "global_step": 595529, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0136661529541016, "global_step": 595530, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.022946834564209, "global_step": 595531, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.955400824546814, "global_step": 595532, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.1109516620635986, "global_step": 595533, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0159072875976562, "global_step": 595534, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.1062710285186768, "global_step": 595535, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.075061082839966, "global_step": 595536, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.111492872238159, "global_step": 595537, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.991615891456604, "global_step": 595538, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9721730947494507, "global_step": 595539, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.033228874206543, "global_step": 595540, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0248303413391113, "global_step": 595541, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0135209560394287, "global_step": 595542, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.024026393890381, "global_step": 595543, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0261287689208984, "global_step": 595544, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.962010145187378, "global_step": 595545, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.033722400665283, "global_step": 595546, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.029637575149536, "global_step": 595547, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.071430206298828, "global_step": 595548, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0256807804107666, "global_step": 595549, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0782155990600586, "global_step": 595550, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9995793104171753, "global_step": 595551, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0623443126678467, "global_step": 595552, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0857770442962646, "global_step": 595553, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9939044713974, "global_step": 595554, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0484440326690674, "global_step": 595555, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0512659549713135, "global_step": 595556, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0027618408203125, "global_step": 595557, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9760164022445679, "global_step": 595558, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9855374097824097, "global_step": 595559, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.964189887046814, "global_step": 595560, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.036635398864746, "global_step": 595561, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9567630290985107, "global_step": 595562, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.039067029953003, "global_step": 595563, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9970948696136475, "global_step": 595564, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0230720043182373, "global_step": 595565, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.024596691131592, "global_step": 595566, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.029141664505005, "global_step": 595567, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9147433042526245, "global_step": 595568, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.032001256942749, "global_step": 595569, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9018751382827759, "global_step": 595570, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9367823600769043, "global_step": 595571, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0381715297698975, "global_step": 595572, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0388448238372803, "global_step": 595573, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.037709951400757, "global_step": 595574, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.973515272140503, "global_step": 595575, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.004589319229126, "global_step": 595576, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9818246364593506, "global_step": 595577, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.034797430038452, "global_step": 595578, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.007331609725952, "global_step": 595579, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9835867881774902, "global_step": 595580, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.070683240890503, "global_step": 595581, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.039124011993408, "global_step": 595582, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0076794624328613, "global_step": 595583, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0416057109832764, "global_step": 595584, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0564870834350586, "global_step": 595585, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0739171504974365, "global_step": 595586, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.038454294204712, "global_step": 595587, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.997395634651184, "global_step": 595588, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9248212575912476, "global_step": 595589, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0016636848449707, "global_step": 595590, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0149223804473877, "global_step": 595591, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0255229473114014, "global_step": 595592, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9431852102279663, "global_step": 595593, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0227441787719727, "global_step": 595594, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0662171840667725, "global_step": 595595, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0104496479034424, "global_step": 595596, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.048908233642578, "global_step": 595597, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9574370384216309, "global_step": 595598, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0022952556610107, "global_step": 595599, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9888386726379395, "global_step": 595600, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.092055320739746, "global_step": 595601, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9583122730255127, "global_step": 595602, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0160083770751953, "global_step": 595603, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.02097749710083, "global_step": 595604, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9904359579086304, "global_step": 595605, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.05314302444458, "global_step": 595606, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9395147562026978, "global_step": 595607, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.049431324005127, "global_step": 595608, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0095958709716797, "global_step": 595609, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.053208589553833, "global_step": 595610, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0180182456970215, "global_step": 595611, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.085453510284424, "global_step": 595612, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0939440727233887, "global_step": 595613, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0733742713928223, "global_step": 595614, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.049156665802002, "global_step": 595615, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0706005096435547, "global_step": 595616, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0107486248016357, "global_step": 595617, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9860917329788208, "global_step": 595618, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9666314125061035, "global_step": 595619, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0596251487731934, "global_step": 595620, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9796589612960815, "global_step": 595621, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9998841285705566, "global_step": 595622, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.1193654537200928, "global_step": 595623, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9592013359069824, "global_step": 595624, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0912392139434814, "global_step": 595625, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0294485092163086, "global_step": 595626, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9812015295028687, "global_step": 595627, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9503475427627563, "global_step": 595628, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0346813201904297, "global_step": 595629, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.060586929321289, "global_step": 595630, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.942151427268982, "global_step": 595631, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9846932888031006, "global_step": 595632, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.939112901687622, "global_step": 595633, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9624193906784058, "global_step": 595634, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0461666584014893, "global_step": 595635, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0185556411743164, "global_step": 595636, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0458319187164307, "global_step": 595637, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0181665420532227, "global_step": 595638, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.948256492614746, "global_step": 595639, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.024822950363159, "global_step": 595640, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0289647579193115, "global_step": 595641, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0604352951049805, "global_step": 595642, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9965094327926636, "global_step": 595643, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9820266962051392, "global_step": 595644, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.1037466526031494, "global_step": 595645, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.062835454940796, "global_step": 595646, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0150938034057617, "global_step": 595647, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0361275672912598, "global_step": 595648, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.000629425048828, "global_step": 595649, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.023493528366089, "global_step": 595650, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.046607255935669, "global_step": 595651, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0013251304626465, "global_step": 595652, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.013578414916992, "global_step": 595653, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9752311706542969, "global_step": 595654, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0452675819396973, "global_step": 595655, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.969347357749939, "global_step": 595656, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.94695246219635, "global_step": 595657, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.07598614692688, "global_step": 595658, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.067317247390747, "global_step": 595659, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9377700090408325, "global_step": 595660, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.974467396736145, "global_step": 595661, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.009690523147583, "global_step": 595662, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.994178056716919, "global_step": 595663, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0601024627685547, "global_step": 595664, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.025210380554199, "global_step": 595665, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0591928958892822, "global_step": 595666, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9941102266311646, "global_step": 595667, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.036593437194824, "global_step": 595668, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0331573486328125, "global_step": 595669, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.007915496826172, "global_step": 595670, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9396700859069824, "global_step": 595671, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0387208461761475, "global_step": 595672, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9529509544372559, "global_step": 595673, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9800095558166504, "global_step": 595674, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9608498811721802, "global_step": 595675, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.022991418838501, "global_step": 595676, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9750115871429443, "global_step": 595677, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0012564659118652, "global_step": 595678, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0958948135375977, "global_step": 595679, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9890648126602173, "global_step": 595680, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0621302127838135, "global_step": 595681, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0426411628723145, "global_step": 595682, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9746373891830444, "global_step": 595683, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9920488595962524, "global_step": 595684, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9925649166107178, "global_step": 595685, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9691270589828491, "global_step": 595686, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9748047590255737, "global_step": 595687, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.005401849746704, "global_step": 595688, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.8712069988250732, "global_step": 595689, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.084864616394043, "global_step": 595690, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9484317302703857, "global_step": 595691, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9938734769821167, "global_step": 595692, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.003347396850586, "global_step": 595693, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0178325176239014, "global_step": 595694, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.012441635131836, "global_step": 595695, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0295236110687256, "global_step": 595696, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9440149068832397, "global_step": 595697, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0939621925354004, "global_step": 595698, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0036263465881348, "global_step": 595699, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.014904737472534, "global_step": 595700, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0115439891815186, "global_step": 595701, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.947214126586914, "global_step": 595702, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0007073879241943, "global_step": 595703, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0068447589874268, "global_step": 595704, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.8842241764068604, "global_step": 595705, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0743908882141113, "global_step": 595706, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9717411994934082, "global_step": 595707, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.063213586807251, "global_step": 595708, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9945883750915527, "global_step": 595709, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.978737711906433, "global_step": 595710, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0246896743774414, "global_step": 595711, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.978542685508728, "global_step": 595712, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.983304500579834, "global_step": 595713, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0495922565460205, "global_step": 595714, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.016871929168701, "global_step": 595715, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.963990569114685, "global_step": 595716, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9964280128479004, "global_step": 595717, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9658981561660767, "global_step": 595718, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0130815505981445, "global_step": 595719, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0026519298553467, "global_step": 595720, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9343328475952148, "global_step": 595721, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9959502220153809, "global_step": 595722, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.996418833732605, "global_step": 595723, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.04400372505188, "global_step": 595724, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9656404256820679, "global_step": 595725, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0809428691864014, "global_step": 595726, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9632081985473633, "global_step": 595727, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0597665309906006, "global_step": 595728, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9215993881225586, "global_step": 595729, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9421602487564087, "global_step": 595730, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9909075498580933, "global_step": 595731, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9546699523925781, "global_step": 595732, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.066267967224121, "global_step": 595733, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.018742799758911, "global_step": 595734, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9337533712387085, "global_step": 595735, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0481271743774414, "global_step": 595736, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9759197235107422, "global_step": 595737, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.1176609992980957, "global_step": 595738, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9964977502822876, "global_step": 595739, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0256519317626953, "global_step": 595740, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.879805088043213, "global_step": 595741, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0155832767486572, "global_step": 595742, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0469188690185547, "global_step": 595743, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0472257137298584, "global_step": 595744, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0176877975463867, "global_step": 595745, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.066631317138672, "global_step": 595746, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0174806118011475, "global_step": 595747, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0231053829193115, "global_step": 595748, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0457303524017334, "global_step": 595749, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0399558544158936, "global_step": 595750, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0178983211517334, "global_step": 595751, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.937848448753357, "global_step": 595752, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9867666959762573, "global_step": 595753, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.1197078227996826, "global_step": 595754, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0021986961364746, "global_step": 595755, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0080554485321045, "global_step": 595756, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0143938064575195, "global_step": 595757, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9301072359085083, "global_step": 595758, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.967599868774414, "global_step": 595759, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.079662799835205, "global_step": 595760, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9529250860214233, "global_step": 595761, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0412817001342773, "global_step": 595762, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.02113676071167, "global_step": 595763, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0210964679718018, "global_step": 595764, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9991875886917114, "global_step": 595765, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9650530815124512, "global_step": 595766, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0571722984313965, "global_step": 595767, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0669078826904297, "global_step": 595768, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.052098035812378, "global_step": 595769, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0220305919647217, "global_step": 595770, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9553492069244385, "global_step": 595771, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0380730628967285, "global_step": 595772, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.080223560333252, "global_step": 595773, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0963964462280273, "global_step": 595774, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.101731777191162, "global_step": 595775, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9950019121170044, "global_step": 595776, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.933290958404541, "global_step": 595777, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9713242053985596, "global_step": 595778, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0602521896362305, "global_step": 595779, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.987593412399292, "global_step": 595780, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0350427627563477, "global_step": 595781, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9699490070343018, "global_step": 595782, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.115835189819336, "global_step": 595783, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.046398162841797, "global_step": 595784, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.049945592880249, "global_step": 595785, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.030846118927002, "global_step": 595786, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.053025007247925, "global_step": 595787, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9500914812088013, "global_step": 595788, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0677199363708496, "global_step": 595789, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0606460571289062, "global_step": 595790, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0775420665740967, "global_step": 595791, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.008432388305664, "global_step": 595792, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0261459350585938, "global_step": 595793, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0254769325256348, "global_step": 595794, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.116617441177368, "global_step": 595795, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9825968742370605, "global_step": 595796, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.093407154083252, "global_step": 595797, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.055924415588379, "global_step": 595798, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0838897228240967, "global_step": 595799, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.984574556350708, "global_step": 595800, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0279974937438965, "global_step": 595801, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0700278282165527, "global_step": 595802, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.122551202774048, "global_step": 595803, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0914955139160156, "global_step": 595804, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9951363801956177, "global_step": 595805, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9686675071716309, "global_step": 595806, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0017552375793457, "global_step": 595807, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9914687871932983, "global_step": 595808, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0835089683532715, "global_step": 595809, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.025751829147339, "global_step": 595810, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9784092903137207, "global_step": 595811, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.019216299057007, "global_step": 595812, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9588056802749634, "global_step": 595813, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9546080827713013, "global_step": 595814, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9991074800491333, "global_step": 595815, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.045426368713379, "global_step": 595816, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.985587477684021, "global_step": 595817, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.046032667160034, "global_step": 595818, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.072506904602051, "global_step": 595819, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0667362213134766, "global_step": 595820, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.009812116622925, "global_step": 595821, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0369646549224854, "global_step": 595822, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.013803005218506, "global_step": 595823, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.155230760574341, "global_step": 595824, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0454483032226562, "global_step": 595825, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9682337045669556, "global_step": 595826, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0466339588165283, "global_step": 595827, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.014169931411743, "global_step": 595828, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0732061862945557, "global_step": 595829, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9808844327926636, "global_step": 595830, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.971989393234253, "global_step": 595831, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0466551780700684, "global_step": 595832, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9790394306182861, "global_step": 595833, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0339388847351074, "global_step": 595834, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.008997678756714, "global_step": 595835, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0162997245788574, "global_step": 595836, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.003575086593628, "global_step": 595837, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.036808490753174, "global_step": 595838, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9783536195755005, "global_step": 595839, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0210142135620117, "global_step": 595840, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9610496759414673, "global_step": 595841, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0069220066070557, "global_step": 595842, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.060615301132202, "global_step": 595843, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.031686544418335, "global_step": 595844, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.135830879211426, "global_step": 595845, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0372369289398193, "global_step": 595846, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.084097385406494, "global_step": 595847, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9870226383209229, "global_step": 595848, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.043977737426758, "global_step": 595849, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0573582649230957, "global_step": 595850, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.070286512374878, "global_step": 595851, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.082500457763672, "global_step": 595852, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.999006748199463, "global_step": 595853, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0746231079101562, "global_step": 595854, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0015623569488525, "global_step": 595855, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0587844848632812, "global_step": 595856, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0166828632354736, "global_step": 595857, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9749834537506104, "global_step": 595858, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9687774181365967, "global_step": 595859, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0344507694244385, "global_step": 595860, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0273823738098145, "global_step": 595861, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0402843952178955, "global_step": 595862, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.072486162185669, "global_step": 595863, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.951934814453125, "global_step": 595864, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.1177258491516113, "global_step": 595865, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0810418128967285, "global_step": 595866, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0236804485321045, "global_step": 595867, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0226902961730957, "global_step": 595868, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0334999561309814, "global_step": 595869, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.042263984680176, "global_step": 595870, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.009209156036377, "global_step": 595871, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.974733591079712, "global_step": 595872, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0168473720550537, "global_step": 595873, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0538923740386963, "global_step": 595874, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.036292552947998, "global_step": 595875, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0098397731781006, "global_step": 595876, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0303311347961426, "global_step": 595877, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9903475046157837, "global_step": 595878, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9980207681655884, "global_step": 595879, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0667591094970703, "global_step": 595880, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0958821773529053, "global_step": 595881, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0308878421783447, "global_step": 595882, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.1185309886932373, "global_step": 595883, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9957951307296753, "global_step": 595884, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0352704524993896, "global_step": 595885, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.96989905834198, "global_step": 595886, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.060246706008911, "global_step": 595887, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0647988319396973, "global_step": 595888, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9415254592895508, "global_step": 595889, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.060032844543457, "global_step": 595890, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.1622467041015625, "global_step": 595891, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.003199577331543, "global_step": 595892, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0283923149108887, "global_step": 595893, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9616920948028564, "global_step": 595894, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.016979694366455, "global_step": 595895, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9439324140548706, "global_step": 595896, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9753881692886353, "global_step": 595897, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0387773513793945, "global_step": 595898, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9372270107269287, "global_step": 595899, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0222299098968506, "global_step": 595900, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.044703483581543, "global_step": 595901, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.958913803100586, "global_step": 595902, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0218734741210938, "global_step": 595903, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9534263610839844, "global_step": 595904, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.929693579673767, "global_step": 595905, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9978071451187134, "global_step": 595906, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9761853218078613, "global_step": 595907, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0636978149414062, "global_step": 595908, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9503475427627563, "global_step": 595909, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.922101616859436, "global_step": 595910, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0161798000335693, "global_step": 595911, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.010242462158203, "global_step": 595912, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0260071754455566, "global_step": 595913, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0447733402252197, "global_step": 595914, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0598442554473877, "global_step": 595915, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.017113447189331, "global_step": 595916, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0578320026397705, "global_step": 595917, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0382986068725586, "global_step": 595918, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.029486656188965, "global_step": 595919, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0035252571105957, "global_step": 595920, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.041022539138794, "global_step": 595921, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.1147234439849854, "global_step": 595922, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9606220722198486, "global_step": 595923, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.041140079498291, "global_step": 595924, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0607492923736572, "global_step": 595925, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.01835036277771, "global_step": 595926, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.043663501739502, "global_step": 595927, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0202581882476807, "global_step": 595928, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9926373958587646, "global_step": 595929, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0502243041992188, "global_step": 595930, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0538899898529053, "global_step": 595931, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.025160312652588, "global_step": 595932, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0591893196105957, "global_step": 595933, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0093963146209717, "global_step": 595934, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0354721546173096, "global_step": 595935, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.025160789489746, "global_step": 595936, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.032463312149048, "global_step": 595937, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.003514051437378, "global_step": 595938, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.002753257751465, "global_step": 595939, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9700285196304321, "global_step": 595940, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.093778610229492, "global_step": 595941, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.052295207977295, "global_step": 595942, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.946839451789856, "global_step": 595943, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.014476776123047, "global_step": 595944, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9961788654327393, "global_step": 595945, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.987600564956665, "global_step": 595946, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9552894830703735, "global_step": 595947, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9570921659469604, "global_step": 595948, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0456299781799316, "global_step": 595949, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9850825071334839, "global_step": 595950, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.050788402557373, "global_step": 595951, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9663249254226685, "global_step": 595952, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0184099674224854, "global_step": 595953, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.030621290206909, "global_step": 595954, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.050306797027588, "global_step": 595955, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9829399585723877, "global_step": 595956, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9664560556411743, "global_step": 595957, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0061399936676025, "global_step": 595958, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0127525329589844, "global_step": 595959, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.047006607055664, "global_step": 595960, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9460221529006958, "global_step": 595961, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0591964721679688, "global_step": 595962, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9185028076171875, "global_step": 595963, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.925376534461975, "global_step": 595964, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.8959887027740479, "global_step": 595965, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0531156063079834, "global_step": 595966, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.008927583694458, "global_step": 595967, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0013654232025146, "global_step": 595968, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9827609062194824, "global_step": 595969, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0967676639556885, "global_step": 595970, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.959787368774414, "global_step": 595971, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9648430347442627, "global_step": 595972, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.049257278442383, "global_step": 595973, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9622080326080322, "global_step": 595974, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.047086000442505, "global_step": 595975, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9249447584152222, "global_step": 595976, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.014357089996338, "global_step": 595977, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0639171600341797, "global_step": 595978, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.057678461074829, "global_step": 595979, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9504518508911133, "global_step": 595980, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0139219760894775, "global_step": 595981, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.995768666267395, "global_step": 595982, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9933770895004272, "global_step": 595983, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9861669540405273, "global_step": 595984, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0042319297790527, "global_step": 595985, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0446341037750244, "global_step": 595986, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0401461124420166, "global_step": 595987, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9881353378295898, "global_step": 595988, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.068751096725464, "global_step": 595989, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.052779197692871, "global_step": 595990, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9889016151428223, "global_step": 595991, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9895226955413818, "global_step": 595992, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0300934314727783, "global_step": 595993, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0329368114471436, "global_step": 595994, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.034694194793701, "global_step": 595995, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0046234130859375, "global_step": 595996, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0352094173431396, "global_step": 595997, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0183188915252686, "global_step": 595998, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0843007564544678, "global_step": 595999, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.969980001449585, "global_step": 596000, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.006683349609375, "global_step": 596001, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.037313938140869, "global_step": 596002, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0161876678466797, "global_step": 596003, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9921387434005737, "global_step": 596004, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9995207786560059, "global_step": 596005, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0085232257843018, "global_step": 596006, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0057437419891357, "global_step": 596007, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.048398733139038, "global_step": 596008, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9809821844100952, "global_step": 596009, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.072094202041626, "global_step": 596010, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0493736267089844, "global_step": 596011, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0182747840881348, "global_step": 596012, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.022829294204712, "global_step": 596013, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.151052713394165, "global_step": 596014, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0288641452789307, "global_step": 596015, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0326197147369385, "global_step": 596016, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.914414644241333, "global_step": 596017, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.059772491455078, "global_step": 596018, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.057512044906616, "global_step": 596019, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.046828508377075, "global_step": 596020, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0190513134002686, "global_step": 596021, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.004896640777588, "global_step": 596022, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9918068647384644, "global_step": 596023, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.029921531677246, "global_step": 596024, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9731980562210083, "global_step": 596025, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.075732469558716, "global_step": 596026, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.999220371246338, "global_step": 596027, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9764777421951294, "global_step": 596028, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.016317367553711, "global_step": 596029, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9830431938171387, "global_step": 596030, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.019472122192383, "global_step": 596031, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.046480178833008, "global_step": 596032, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.112898826599121, "global_step": 596033, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0878803730010986, "global_step": 596034, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0682692527770996, "global_step": 596035, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.048713445663452, "global_step": 596036, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0303966999053955, "global_step": 596037, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9537421464920044, "global_step": 596038, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0488600730895996, "global_step": 596039, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0539259910583496, "global_step": 596040, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9530539512634277, "global_step": 596041, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0319199562072754, "global_step": 596042, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.087716817855835, "global_step": 596043, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0293312072753906, "global_step": 596044, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0384480953216553, "global_step": 596045, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0601580142974854, "global_step": 596046, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.031181573867798, "global_step": 596047, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.949699878692627, "global_step": 596048, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0685267448425293, "global_step": 596049, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9396944046020508, "global_step": 596050, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0268688201904297, "global_step": 596051, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.058910846710205, "global_step": 596052, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0281286239624023, "global_step": 596053, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9764347076416016, "global_step": 596054, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9834256172180176, "global_step": 596055, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0658912658691406, "global_step": 596056, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0247843265533447, "global_step": 596057, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9677577018737793, "global_step": 596058, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0210041999816895, "global_step": 596059, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9921519756317139, "global_step": 596060, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0071332454681396, "global_step": 596061, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9937912225723267, "global_step": 596062, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9253580570220947, "global_step": 596063, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0001344680786133, "global_step": 596064, "epoch": 964, "lr": 5e-05}
{"train_loss": 1.9969099760055542, "global_step": 596065, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.020200729370117, "global_step": 596066, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.0127995014190674, "global_step": 596067, "epoch": 964, "lr": 5e-05}
{"train_loss": 2.00940203666687, "global_step": 596068, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9604920148849487, "global_step": 596069, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0001978874206543, "global_step": 596070, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9931178092956543, "global_step": 596071, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0648980140686035, "global_step": 596072, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.064547300338745, "global_step": 596073, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0220894813537598, "global_step": 596074, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.054415702819824, "global_step": 596075, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.008942127227783, "global_step": 596076, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.1010401248931885, "global_step": 596077, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9469947814941406, "global_step": 596078, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0289764404296875, "global_step": 596079, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9960030317306519, "global_step": 596080, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0328965187072754, "global_step": 596081, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9606003761291504, "global_step": 596082, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9696325063705444, "global_step": 596083, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9902522563934326, "global_step": 596084, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.004403829574585, "global_step": 596085, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9608575105667114, "global_step": 596086, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9999991655349731, "global_step": 596087, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9744333028793335, "global_step": 596088, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0920019149780273, "global_step": 596089, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.990020751953125, "global_step": 596090, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9949127435684204, "global_step": 596091, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9550271034240723, "global_step": 596092, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0162160396575928, "global_step": 596093, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9611464738845825, "global_step": 596094, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.072721481323242, "global_step": 596095, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0086135864257812, "global_step": 596096, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.018986701965332, "global_step": 596097, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9848130941390991, "global_step": 596098, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.013031244277954, "global_step": 596099, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.022258996963501, "global_step": 596100, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.099817991256714, "global_step": 596101, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9113374948501587, "global_step": 596102, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9236103296279907, "global_step": 596103, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9033517837524414, "global_step": 596104, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0246918201446533, "global_step": 596105, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0529959201812744, "global_step": 596106, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.005239963531494, "global_step": 596107, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.008139133453369, "global_step": 596108, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9969676733016968, "global_step": 596109, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9357510805130005, "global_step": 596110, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0441510677337646, "global_step": 596111, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0407097339630127, "global_step": 596112, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.019942283630371, "global_step": 596113, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0316145420074463, "global_step": 596114, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.055953025817871, "global_step": 596115, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.013615608215332, "global_step": 596116, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9337763786315918, "global_step": 596117, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9332550764083862, "global_step": 596118, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.950823426246643, "global_step": 596119, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0559909343719482, "global_step": 596120, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.957460880279541, "global_step": 596121, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0025761127471924, "global_step": 596122, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0747649669647217, "global_step": 596123, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.065542221069336, "global_step": 596124, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.8915581703186035, "global_step": 596125, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.092371702194214, "global_step": 596126, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.012347459793091, "global_step": 596127, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9752339124679565, "global_step": 596128, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.023874282836914, "global_step": 596129, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0207619667053223, "global_step": 596130, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9894661903381348, "global_step": 596131, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0325918197631836, "global_step": 596132, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0710830688476562, "global_step": 596133, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.011766195297241, "global_step": 596134, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9333477020263672, "global_step": 596135, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.982548475265503, "global_step": 596136, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.917148470878601, "global_step": 596137, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9466023445129395, "global_step": 596138, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.031188726425171, "global_step": 596139, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.957808017730713, "global_step": 596140, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.988850474357605, "global_step": 596141, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.012465238571167, "global_step": 596142, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0497212409973145, "global_step": 596143, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0285041332244873, "global_step": 596144, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9799174070358276, "global_step": 596145, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0340914726257324, "global_step": 596146, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.01945161819458, "global_step": 596147, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0487992763519287, "global_step": 596148, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.062756061553955, "global_step": 596149, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0105040073394775, "global_step": 596150, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.057462215423584, "global_step": 596151, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.947150468826294, "global_step": 596152, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.072646141052246, "global_step": 596153, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.950478196144104, "global_step": 596154, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0116846561431885, "global_step": 596155, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9214518070220947, "global_step": 596156, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0892975330352783, "global_step": 596157, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.123319387435913, "global_step": 596158, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9804604053497314, "global_step": 596159, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9670803546905518, "global_step": 596160, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.01078200340271, "global_step": 596161, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9127744436264038, "global_step": 596162, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.103499174118042, "global_step": 596163, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0511794090270996, "global_step": 596164, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9708929061889648, "global_step": 596165, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9187628030776978, "global_step": 596166, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0487475395202637, "global_step": 596167, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.040031671524048, "global_step": 596168, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9815539121627808, "global_step": 596169, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9999077320098877, "global_step": 596170, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9901586771011353, "global_step": 596171, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9604896306991577, "global_step": 596172, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0744504928588867, "global_step": 596173, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.070263624191284, "global_step": 596174, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0211620330810547, "global_step": 596175, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9936960935592651, "global_step": 596176, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9829789400100708, "global_step": 596177, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.973586082458496, "global_step": 596178, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9736846685409546, "global_step": 596179, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9543510675430298, "global_step": 596180, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.028688669204712, "global_step": 596181, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9621456861495972, "global_step": 596182, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0324981212615967, "global_step": 596183, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9510287046432495, "global_step": 596184, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9837236404418945, "global_step": 596185, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9927111864089966, "global_step": 596186, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.014230251312256, "global_step": 596187, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0167276859283447, "global_step": 596188, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.046759843826294, "global_step": 596189, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.032043933868408, "global_step": 596190, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9848695993423462, "global_step": 596191, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0416572093963623, "global_step": 596192, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.057297706604004, "global_step": 596193, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9493420124053955, "global_step": 596194, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.988773226737976, "global_step": 596195, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9596705436706543, "global_step": 596196, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.099137306213379, "global_step": 596197, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9756717681884766, "global_step": 596198, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9720945358276367, "global_step": 596199, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.950183391571045, "global_step": 596200, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0514988899230957, "global_step": 596201, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.986919641494751, "global_step": 596202, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.038459300994873, "global_step": 596203, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.040229558944702, "global_step": 596204, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.980600118637085, "global_step": 596205, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9489848613739014, "global_step": 596206, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.04225754737854, "global_step": 596207, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0068585872650146, "global_step": 596208, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.048348903656006, "global_step": 596209, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0073940753936768, "global_step": 596210, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0735538005828857, "global_step": 596211, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9715722799301147, "global_step": 596212, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9897794723510742, "global_step": 596213, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0611352920532227, "global_step": 596214, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0082333087921143, "global_step": 596215, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0331690311431885, "global_step": 596216, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9935574531555176, "global_step": 596217, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0400211811065674, "global_step": 596218, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.042100667953491, "global_step": 596219, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.062302350997925, "global_step": 596220, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9749691486358643, "global_step": 596221, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9950292110443115, "global_step": 596222, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0380396842956543, "global_step": 596223, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0235679149627686, "global_step": 596224, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0935513973236084, "global_step": 596225, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0136878490448, "global_step": 596226, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.99064040184021, "global_step": 596227, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.055269241333008, "global_step": 596228, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9166786670684814, "global_step": 596229, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.04693865776062, "global_step": 596230, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9600675106048584, "global_step": 596231, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.1526594161987305, "global_step": 596232, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9670372009277344, "global_step": 596233, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9596954584121704, "global_step": 596234, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.038771152496338, "global_step": 596235, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.009523868560791, "global_step": 596236, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9388055801391602, "global_step": 596237, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9680147171020508, "global_step": 596238, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0025839805603027, "global_step": 596239, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.008122682571411, "global_step": 596240, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9309262037277222, "global_step": 596241, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0665817260742188, "global_step": 596242, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9984663724899292, "global_step": 596243, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.005610227584839, "global_step": 596244, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.072014570236206, "global_step": 596245, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.081193685531616, "global_step": 596246, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.955254316329956, "global_step": 596247, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.043311834335327, "global_step": 596248, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.986344575881958, "global_step": 596249, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9980674982070923, "global_step": 596250, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9840031862258911, "global_step": 596251, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0826187133789062, "global_step": 596252, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.982089877128601, "global_step": 596253, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0134177207946777, "global_step": 596254, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9829819202423096, "global_step": 596255, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9754914045333862, "global_step": 596256, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.004354238510132, "global_step": 596257, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0532798767089844, "global_step": 596258, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0440170764923096, "global_step": 596259, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0048742294311523, "global_step": 596260, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.004798173904419, "global_step": 596261, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9422402381896973, "global_step": 596262, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.074000120162964, "global_step": 596263, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.928626537322998, "global_step": 596264, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0916123390197754, "global_step": 596265, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.062863349914551, "global_step": 596266, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.068950653076172, "global_step": 596267, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.99897038936615, "global_step": 596268, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9623863697052002, "global_step": 596269, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.947415828704834, "global_step": 596270, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.044736623764038, "global_step": 596271, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9887703657150269, "global_step": 596272, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0242087841033936, "global_step": 596273, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9534225463867188, "global_step": 596274, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.041487455368042, "global_step": 596275, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.005547285079956, "global_step": 596276, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0255699157714844, "global_step": 596277, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.036947250366211, "global_step": 596278, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0140624046325684, "global_step": 596279, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0875608921051025, "global_step": 596280, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0241990089416504, "global_step": 596281, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9812484979629517, "global_step": 596282, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.009506940841675, "global_step": 596283, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.943947196006775, "global_step": 596284, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9718570709228516, "global_step": 596285, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.133152484893799, "global_step": 596286, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.982715129852295, "global_step": 596287, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0872960090637207, "global_step": 596288, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9617611169815063, "global_step": 596289, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0216872692108154, "global_step": 596290, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.98551344871521, "global_step": 596291, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9345959424972534, "global_step": 596292, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.931868314743042, "global_step": 596293, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0449440479278564, "global_step": 596294, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9444828033447266, "global_step": 596295, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0913889408111572, "global_step": 596296, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.004652261734009, "global_step": 596297, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.14143967628479, "global_step": 596298, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.985499382019043, "global_step": 596299, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9270883798599243, "global_step": 596300, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.990712285041809, "global_step": 596301, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9426356554031372, "global_step": 596302, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0418589115142822, "global_step": 596303, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.051527976989746, "global_step": 596304, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.020624876022339, "global_step": 596305, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.003190517425537, "global_step": 596306, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0560357570648193, "global_step": 596307, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0760154724121094, "global_step": 596308, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.035325050354004, "global_step": 596309, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0454044342041016, "global_step": 596310, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.02579665184021, "global_step": 596311, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9594993591308594, "global_step": 596312, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9783920049667358, "global_step": 596313, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0364651679992676, "global_step": 596314, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.032879590988159, "global_step": 596315, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9647692441940308, "global_step": 596316, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9693448543548584, "global_step": 596317, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0016067028045654, "global_step": 596318, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0475711822509766, "global_step": 596319, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.994907259941101, "global_step": 596320, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.034418821334839, "global_step": 596321, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.918975830078125, "global_step": 596322, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9679298400878906, "global_step": 596323, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.079240322113037, "global_step": 596324, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0946836471557617, "global_step": 596325, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9246541261672974, "global_step": 596326, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.027601480484009, "global_step": 596327, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.987892985343933, "global_step": 596328, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0341897010803223, "global_step": 596329, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9924073219299316, "global_step": 596330, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.013751745223999, "global_step": 596331, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0223193168640137, "global_step": 596332, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0225436687469482, "global_step": 596333, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.056807518005371, "global_step": 596334, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9203547239303589, "global_step": 596335, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.92569899559021, "global_step": 596336, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.001009941101074, "global_step": 596337, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.033632278442383, "global_step": 596338, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.977745532989502, "global_step": 596339, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0029990673065186, "global_step": 596340, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9982116222381592, "global_step": 596341, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0122361183166504, "global_step": 596342, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.023885488510132, "global_step": 596343, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.002317428588867, "global_step": 596344, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0166714191436768, "global_step": 596345, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.108828544616699, "global_step": 596346, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0724668502807617, "global_step": 596347, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9921588897705078, "global_step": 596348, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9957703351974487, "global_step": 596349, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9571473598480225, "global_step": 596350, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.070796012878418, "global_step": 596351, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.135500907897949, "global_step": 596352, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0337371826171875, "global_step": 596353, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0110220909118652, "global_step": 596354, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.042245626449585, "global_step": 596355, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0458486080169678, "global_step": 596356, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9543943405151367, "global_step": 596357, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.896064043045044, "global_step": 596358, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0199272632598877, "global_step": 596359, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.06927752494812, "global_step": 596360, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.930919885635376, "global_step": 596361, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.054790496826172, "global_step": 596362, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9811584949493408, "global_step": 596363, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.063253879547119, "global_step": 596364, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0032143592834473, "global_step": 596365, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9794856309890747, "global_step": 596366, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9278279542922974, "global_step": 596367, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.014547824859619, "global_step": 596368, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.003021717071533, "global_step": 596369, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0130889415740967, "global_step": 596370, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.07853102684021, "global_step": 596371, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0228540897369385, "global_step": 596372, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0744738578796387, "global_step": 596373, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0550479888916016, "global_step": 596374, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.905846357345581, "global_step": 596375, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.007596015930176, "global_step": 596376, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.047611713409424, "global_step": 596377, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9716392755508423, "global_step": 596378, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.99950110912323, "global_step": 596379, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.979799747467041, "global_step": 596380, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0049901008605957, "global_step": 596381, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.889117956161499, "global_step": 596382, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.01420259475708, "global_step": 596383, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.985002040863037, "global_step": 596384, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9790422916412354, "global_step": 596385, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.050482988357544, "global_step": 596386, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0788021087646484, "global_step": 596387, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0324041843414307, "global_step": 596388, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.8623578548431396, "global_step": 596389, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.031731605529785, "global_step": 596390, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9928849935531616, "global_step": 596391, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9707924127578735, "global_step": 596392, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9777473211288452, "global_step": 596393, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9977760314941406, "global_step": 596394, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.993735432624817, "global_step": 596395, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.033613443374634, "global_step": 596396, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.048494577407837, "global_step": 596397, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9115289449691772, "global_step": 596398, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9927725791931152, "global_step": 596399, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9518485069274902, "global_step": 596400, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0675699710845947, "global_step": 596401, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0387890338897705, "global_step": 596402, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.003660202026367, "global_step": 596403, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.007120132446289, "global_step": 596404, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.03735613822937, "global_step": 596405, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9062970876693726, "global_step": 596406, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.053541898727417, "global_step": 596407, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.1030869483947754, "global_step": 596408, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.016969919204712, "global_step": 596409, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.095681667327881, "global_step": 596410, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0093772411346436, "global_step": 596411, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0943288803100586, "global_step": 596412, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.027129650115967, "global_step": 596413, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.030956745147705, "global_step": 596414, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0416884422302246, "global_step": 596415, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9991838932037354, "global_step": 596416, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.03830885887146, "global_step": 596417, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9702032804489136, "global_step": 596418, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.038092851638794, "global_step": 596419, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0142428874969482, "global_step": 596420, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0510735511779785, "global_step": 596421, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0065953731536865, "global_step": 596422, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0177173614501953, "global_step": 596423, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0705440044403076, "global_step": 596424, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0474905967712402, "global_step": 596425, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.046452760696411, "global_step": 596426, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0661463737487793, "global_step": 596427, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9977346658706665, "global_step": 596428, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0203890800476074, "global_step": 596429, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9722877740859985, "global_step": 596430, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.972227692604065, "global_step": 596431, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.064481019973755, "global_step": 596432, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9346787929534912, "global_step": 596433, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.1130056381225586, "global_step": 596434, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.008925199508667, "global_step": 596435, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9268391132354736, "global_step": 596436, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9590669870376587, "global_step": 596437, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.031208038330078, "global_step": 596438, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9651767015457153, "global_step": 596439, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.012150764465332, "global_step": 596440, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0654728412628174, "global_step": 596441, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0573506355285645, "global_step": 596442, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0726420879364014, "global_step": 596443, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.984057903289795, "global_step": 596444, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.047258138656616, "global_step": 596445, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9533300399780273, "global_step": 596446, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0156795978546143, "global_step": 596447, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.030052661895752, "global_step": 596448, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.010883092880249, "global_step": 596449, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0025858879089355, "global_step": 596450, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0707314014434814, "global_step": 596451, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.091757297515869, "global_step": 596452, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.13287091255188, "global_step": 596453, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.082385540008545, "global_step": 596454, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9892324209213257, "global_step": 596455, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0398614406585693, "global_step": 596456, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9967108964920044, "global_step": 596457, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.051682233810425, "global_step": 596458, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.009456157684326, "global_step": 596459, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.039069652557373, "global_step": 596460, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.103663921356201, "global_step": 596461, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.073556900024414, "global_step": 596462, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0335919857025146, "global_step": 596463, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0343520641326904, "global_step": 596464, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.975184679031372, "global_step": 596465, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.060974359512329, "global_step": 596466, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.040485143661499, "global_step": 596467, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.010514497756958, "global_step": 596468, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.033120632171631, "global_step": 596469, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0947818756103516, "global_step": 596470, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0945301055908203, "global_step": 596471, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.991313099861145, "global_step": 596472, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.050886869430542, "global_step": 596473, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9699323177337646, "global_step": 596474, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.020249366760254, "global_step": 596475, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9550009965896606, "global_step": 596476, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0703999996185303, "global_step": 596477, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.1418349742889404, "global_step": 596478, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0233733654022217, "global_step": 596479, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9357810020446777, "global_step": 596480, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0333824157714844, "global_step": 596481, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.022341012954712, "global_step": 596482, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9620145559310913, "global_step": 596483, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.056204319000244, "global_step": 596484, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.972485899925232, "global_step": 596485, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0105409622192383, "global_step": 596486, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0893607139587402, "global_step": 596487, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.046327829360962, "global_step": 596488, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9829622507095337, "global_step": 596489, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0523135662078857, "global_step": 596490, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9300504922866821, "global_step": 596491, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9683544635772705, "global_step": 596492, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0300095081329346, "global_step": 596493, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9519025087356567, "global_step": 596494, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.1024537086486816, "global_step": 596495, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9546310901641846, "global_step": 596496, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0014560222625732, "global_step": 596497, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9400399923324585, "global_step": 596498, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0340092182159424, "global_step": 596499, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.978351354598999, "global_step": 596500, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0304155349731445, "global_step": 596501, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9852420091629028, "global_step": 596502, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9713717699050903, "global_step": 596503, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.024536609649658, "global_step": 596504, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.999727487564087, "global_step": 596505, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.025256633758545, "global_step": 596506, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.035634756088257, "global_step": 596507, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9690990447998047, "global_step": 596508, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9981502294540405, "global_step": 596509, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9671305418014526, "global_step": 596510, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0711052417755127, "global_step": 596511, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.05574107170105, "global_step": 596512, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0109992027282715, "global_step": 596513, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0159151554107666, "global_step": 596514, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0178709030151367, "global_step": 596515, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.064851760864258, "global_step": 596516, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9835902452468872, "global_step": 596517, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.083578109741211, "global_step": 596518, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.969001293182373, "global_step": 596519, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0012383460998535, "global_step": 596520, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0638368129730225, "global_step": 596521, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0132036209106445, "global_step": 596522, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0380678176879883, "global_step": 596523, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.025198221206665, "global_step": 596524, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0915298461914062, "global_step": 596525, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.019901990890503, "global_step": 596526, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.002673387527466, "global_step": 596527, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0312459468841553, "global_step": 596528, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.097158670425415, "global_step": 596529, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.080493688583374, "global_step": 596530, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.037635326385498, "global_step": 596531, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.074850559234619, "global_step": 596532, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0945980548858643, "global_step": 596533, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9431703090667725, "global_step": 596534, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0316202640533447, "global_step": 596535, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0463104248046875, "global_step": 596536, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0250627994537354, "global_step": 596537, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0828893184661865, "global_step": 596538, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.011240243911743, "global_step": 596539, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9943759441375732, "global_step": 596540, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.041632652282715, "global_step": 596541, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0503334999084473, "global_step": 596542, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.049168825149536, "global_step": 596543, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9955641031265259, "global_step": 596544, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.979606032371521, "global_step": 596545, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.072275400161743, "global_step": 596546, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9601624011993408, "global_step": 596547, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.056985855102539, "global_step": 596548, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.039264678955078, "global_step": 596549, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0330934524536133, "global_step": 596550, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9471784830093384, "global_step": 596551, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9236230850219727, "global_step": 596552, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.057722330093384, "global_step": 596553, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.004760503768921, "global_step": 596554, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9732097387313843, "global_step": 596555, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9746769666671753, "global_step": 596556, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.045335054397583, "global_step": 596557, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.079956531524658, "global_step": 596558, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.104264497756958, "global_step": 596559, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0184900760650635, "global_step": 596560, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9926973581314087, "global_step": 596561, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9940437078475952, "global_step": 596562, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.032731294631958, "global_step": 596563, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.936902642250061, "global_step": 596564, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0467395782470703, "global_step": 596565, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0454556941986084, "global_step": 596566, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0134239196777344, "global_step": 596567, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0274696350097656, "global_step": 596568, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9923691749572754, "global_step": 596569, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0072338581085205, "global_step": 596570, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9555810689926147, "global_step": 596571, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.027021884918213, "global_step": 596572, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.935752511024475, "global_step": 596573, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.061382293701172, "global_step": 596574, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0663139820098877, "global_step": 596575, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.001878499984741, "global_step": 596576, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.103147029876709, "global_step": 596577, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.024351119995117, "global_step": 596578, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0353236198425293, "global_step": 596579, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0333070755004883, "global_step": 596580, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0144076347351074, "global_step": 596581, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.999626636505127, "global_step": 596582, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0476949214935303, "global_step": 596583, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0204644203186035, "global_step": 596584, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.000108242034912, "global_step": 596585, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0823237895965576, "global_step": 596586, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9322913885116577, "global_step": 596587, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0181171894073486, "global_step": 596588, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.060330629348755, "global_step": 596589, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0608911514282227, "global_step": 596590, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.05830979347229, "global_step": 596591, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0567638874053955, "global_step": 596592, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.112332344055176, "global_step": 596593, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.043606758117676, "global_step": 596594, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.069450616836548, "global_step": 596595, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.958126187324524, "global_step": 596596, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9194809198379517, "global_step": 596597, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9795057773590088, "global_step": 596598, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0009145736694336, "global_step": 596599, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9839599132537842, "global_step": 596600, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9955404996871948, "global_step": 596601, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.032161235809326, "global_step": 596602, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.064584732055664, "global_step": 596603, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.936636209487915, "global_step": 596604, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.037928819656372, "global_step": 596605, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9889304637908936, "global_step": 596606, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0119001865386963, "global_step": 596607, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.042407989501953, "global_step": 596608, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.016953945159912, "global_step": 596609, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9591797590255737, "global_step": 596610, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0860891342163086, "global_step": 596611, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0083398818969727, "global_step": 596612, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9907058477401733, "global_step": 596613, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9993040561676025, "global_step": 596614, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0309553146362305, "global_step": 596615, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0734503269195557, "global_step": 596616, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9210727214813232, "global_step": 596617, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0390074253082275, "global_step": 596618, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9861063957214355, "global_step": 596619, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.096832752227783, "global_step": 596620, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9905587434768677, "global_step": 596621, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0345654487609863, "global_step": 596622, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.030158042907715, "global_step": 596623, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0432357788085938, "global_step": 596624, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0146477222442627, "global_step": 596625, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0605056285858154, "global_step": 596626, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0378172397613525, "global_step": 596627, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9695754051208496, "global_step": 596628, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0016987323760986, "global_step": 596629, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.982532262802124, "global_step": 596630, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9428699016571045, "global_step": 596631, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9925475120544434, "global_step": 596632, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9434680938720703, "global_step": 596633, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0186610221862793, "global_step": 596634, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0524396896362305, "global_step": 596635, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0148606300354004, "global_step": 596636, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0675923824310303, "global_step": 596637, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9633198976516724, "global_step": 596638, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0589442253112793, "global_step": 596639, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9856207370758057, "global_step": 596640, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0220131874084473, "global_step": 596641, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.027224063873291, "global_step": 596642, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.8731838464736938, "global_step": 596643, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0969252586364746, "global_step": 596644, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0012714862823486, "global_step": 596645, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9872426986694336, "global_step": 596646, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0014126300811768, "global_step": 596647, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0470550060272217, "global_step": 596648, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9797568321228027, "global_step": 596649, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9490594863891602, "global_step": 596650, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.1365668773651123, "global_step": 596651, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9909487962722778, "global_step": 596652, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0070345401763916, "global_step": 596653, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0773074626922607, "global_step": 596654, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0850026607513428, "global_step": 596655, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.063671588897705, "global_step": 596656, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.042942762374878, "global_step": 596657, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9641793966293335, "global_step": 596658, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0213699340820312, "global_step": 596659, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.045983076095581, "global_step": 596660, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9775099754333496, "global_step": 596661, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.079791784286499, "global_step": 596662, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0861945152282715, "global_step": 596663, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9402515888214111, "global_step": 596664, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.002317428588867, "global_step": 596665, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.000523567199707, "global_step": 596666, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.094374895095825, "global_step": 596667, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0614542961120605, "global_step": 596668, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.064185380935669, "global_step": 596669, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.985954761505127, "global_step": 596670, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0217416286468506, "global_step": 596671, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.028688907623291, "global_step": 596672, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.039125919342041, "global_step": 596673, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0216948986053467, "global_step": 596674, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0323522090911865, "global_step": 596675, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.970262050628662, "global_step": 596676, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.939971923828125, "global_step": 596677, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9749939441680908, "global_step": 596678, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0065200328826904, "global_step": 596679, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9667257070541382, "global_step": 596680, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.114055633544922, "global_step": 596681, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0368659496307373, "global_step": 596682, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9877281188964844, "global_step": 596683, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0321624279022217, "global_step": 596684, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0464694499969482, "global_step": 596685, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.024998903274536, "global_step": 596686, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.995474100112915, "global_step": 596687, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9988552331924438, "global_step": 596688, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.1324167251586914, "global_step": 596689, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0485408306121826, "global_step": 596690, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0474278926849365, "global_step": 596691, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.083523988723755, "global_step": 596692, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9844176769256592, "global_step": 596693, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9663218259811401, "global_step": 596694, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9694851636886597, "global_step": 596695, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.969862699508667, "global_step": 596696, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.054917812347412, "global_step": 596697, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0117218494415283, "global_step": 596698, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9873275756835938, "global_step": 596699, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.974905252456665, "global_step": 596700, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0271482467651367, "global_step": 596701, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0561306476593018, "global_step": 596702, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.96882963180542, "global_step": 596703, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9623075723648071, "global_step": 596704, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9611577987670898, "global_step": 596705, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0257742404937744, "global_step": 596706, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.954799771308899, "global_step": 596707, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0474021434783936, "global_step": 596708, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.015272617340088, "global_step": 596709, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9623334407806396, "global_step": 596710, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9669617414474487, "global_step": 596711, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.023193836212158, "global_step": 596712, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0094330310821533, "global_step": 596713, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0998246669769287, "global_step": 596714, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0076711177825928, "global_step": 596715, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0356154441833496, "global_step": 596716, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0054118633270264, "global_step": 596717, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0388143062591553, "global_step": 596718, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.005089282989502, "global_step": 596719, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.005887746810913, "global_step": 596720, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.063906192779541, "global_step": 596721, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9475573301315308, "global_step": 596722, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9560011625289917, "global_step": 596723, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.002058267593384, "global_step": 596724, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.05325984954834, "global_step": 596725, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0630128383636475, "global_step": 596726, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.017982244491577, "global_step": 596727, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0048656463623047, "global_step": 596728, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.046438694000244, "global_step": 596729, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.089841365814209, "global_step": 596730, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0181641578674316, "global_step": 596731, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9742255210876465, "global_step": 596732, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9493874311447144, "global_step": 596733, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9296330213546753, "global_step": 596734, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9622677564620972, "global_step": 596735, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.075235366821289, "global_step": 596736, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.127840995788574, "global_step": 596737, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9842307567596436, "global_step": 596738, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.088709831237793, "global_step": 596739, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.96745765209198, "global_step": 596740, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.030754327774048, "global_step": 596741, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0355162620544434, "global_step": 596742, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0001163482666016, "global_step": 596743, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0086584091186523, "global_step": 596744, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.99245023727417, "global_step": 596745, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0593504905700684, "global_step": 596746, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9636969566345215, "global_step": 596747, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0122873783111572, "global_step": 596748, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0180299282073975, "global_step": 596749, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.003493070602417, "global_step": 596750, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9961556196212769, "global_step": 596751, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0288150310516357, "global_step": 596752, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.933724045753479, "global_step": 596753, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.98714280128479, "global_step": 596754, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.1037731170654297, "global_step": 596755, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9784938097000122, "global_step": 596756, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0787272453308105, "global_step": 596757, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9975006580352783, "global_step": 596758, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0008254051208496, "global_step": 596759, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.034926652908325, "global_step": 596760, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0403201580047607, "global_step": 596761, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9669013023376465, "global_step": 596762, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0025112628936768, "global_step": 596763, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.011037588119507, "global_step": 596764, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.035865306854248, "global_step": 596765, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0290486812591553, "global_step": 596766, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9649009704589844, "global_step": 596767, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0367953777313232, "global_step": 596768, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9871373176574707, "global_step": 596769, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0795717239379883, "global_step": 596770, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0945355892181396, "global_step": 596771, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.062836170196533, "global_step": 596772, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.002143144607544, "global_step": 596773, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.998415470123291, "global_step": 596774, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0918562412261963, "global_step": 596775, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.996617317199707, "global_step": 596776, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9894421100616455, "global_step": 596777, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.109179973602295, "global_step": 596778, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0433101654052734, "global_step": 596779, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0244240760803223, "global_step": 596780, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.066385269165039, "global_step": 596781, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.004624605178833, "global_step": 596782, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.00417160987854, "global_step": 596783, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.055777072906494, "global_step": 596784, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9850215911865234, "global_step": 596785, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.087679386138916, "global_step": 596786, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9966720342636108, "global_step": 596787, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.032989501953125, "global_step": 596788, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0429022312164307, "global_step": 596789, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.075345039367676, "global_step": 596790, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9855927228927612, "global_step": 596791, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.071835517883301, "global_step": 596792, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9815540313720703, "global_step": 596793, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9859185218811035, "global_step": 596794, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0282726287841797, "global_step": 596795, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9989458322525024, "global_step": 596796, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0518646240234375, "global_step": 596797, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9861481189727783, "global_step": 596798, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.046182870864868, "global_step": 596799, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9506549835205078, "global_step": 596800, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.024716854095459, "global_step": 596801, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.004847526550293, "global_step": 596802, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9566404819488525, "global_step": 596803, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9764347076416016, "global_step": 596804, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0718815326690674, "global_step": 596805, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0766961574554443, "global_step": 596806, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9750381708145142, "global_step": 596807, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.932918667793274, "global_step": 596808, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0465502738952637, "global_step": 596809, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.083798885345459, "global_step": 596810, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.015697717666626, "global_step": 596811, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.1101040840148926, "global_step": 596812, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9936548471450806, "global_step": 596813, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9517005681991577, "global_step": 596814, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0405685901641846, "global_step": 596815, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.948758840560913, "global_step": 596816, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.033512830734253, "global_step": 596817, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.034785509109497, "global_step": 596818, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0153393745422363, "global_step": 596819, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0357797145843506, "global_step": 596820, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.949857234954834, "global_step": 596821, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.010202169418335, "global_step": 596822, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.8947222232818604, "global_step": 596823, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.098144054412842, "global_step": 596824, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0635263919830322, "global_step": 596825, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0615572929382324, "global_step": 596826, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.97727370262146, "global_step": 596827, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9557301998138428, "global_step": 596828, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0613338947296143, "global_step": 596829, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.083786725997925, "global_step": 596830, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9761227369308472, "global_step": 596831, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0311732292175293, "global_step": 596832, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9709128141403198, "global_step": 596833, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9843289852142334, "global_step": 596834, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0201680660247803, "global_step": 596835, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0585014820098877, "global_step": 596836, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.045457124710083, "global_step": 596837, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.01072359085083, "global_step": 596838, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.058926582336426, "global_step": 596839, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.044687271118164, "global_step": 596840, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0502007007598877, "global_step": 596841, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0670313835144043, "global_step": 596842, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.007765769958496, "global_step": 596843, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0427401065826416, "global_step": 596844, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9786128997802734, "global_step": 596845, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9971208572387695, "global_step": 596846, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9925134181976318, "global_step": 596847, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0239920616149902, "global_step": 596848, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9601035118103027, "global_step": 596849, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9650723934173584, "global_step": 596850, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9707319736480713, "global_step": 596851, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.962464451789856, "global_step": 596852, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0586330890655518, "global_step": 596853, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.02250337600708, "global_step": 596854, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0396242141723633, "global_step": 596855, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9032434225082397, "global_step": 596856, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0336461067199707, "global_step": 596857, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0206141471862793, "global_step": 596858, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9914065599441528, "global_step": 596859, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0826687812805176, "global_step": 596860, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0559186935424805, "global_step": 596861, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.093123197555542, "global_step": 596862, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9621092081069946, "global_step": 596863, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0181922912597656, "global_step": 596864, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0768027305603027, "global_step": 596865, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9902608394622803, "global_step": 596866, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9901375770568848, "global_step": 596867, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9870606660842896, "global_step": 596868, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0584726333618164, "global_step": 596869, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.026836633682251, "global_step": 596870, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0031304359436035, "global_step": 596871, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.006544351577759, "global_step": 596872, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0322258472442627, "global_step": 596873, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.019925832748413, "global_step": 596874, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.103506326675415, "global_step": 596875, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.950920581817627, "global_step": 596876, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.076340675354004, "global_step": 596877, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9665031433105469, "global_step": 596878, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0420923233032227, "global_step": 596879, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9726448059082031, "global_step": 596880, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0552895069122314, "global_step": 596881, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9883686304092407, "global_step": 596882, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9934858083724976, "global_step": 596883, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9714555740356445, "global_step": 596884, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0279018878936768, "global_step": 596885, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9438350200653076, "global_step": 596886, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0429697036743164, "global_step": 596887, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.041628122329712, "global_step": 596888, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0719082355499268, "global_step": 596889, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.082610845565796, "global_step": 596890, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0807137489318848, "global_step": 596891, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.003337860107422, "global_step": 596892, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9895646572113037, "global_step": 596893, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0751585960388184, "global_step": 596894, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.012387752532959, "global_step": 596895, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.009117364883423, "global_step": 596896, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0458905696868896, "global_step": 596897, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0371737480163574, "global_step": 596898, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0394816398620605, "global_step": 596899, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0402166843414307, "global_step": 596900, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0348024368286133, "global_step": 596901, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.082146167755127, "global_step": 596902, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.047748565673828, "global_step": 596903, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9992492198944092, "global_step": 596904, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0204665660858154, "global_step": 596905, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0367910861968994, "global_step": 596906, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.004364252090454, "global_step": 596907, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9840128421783447, "global_step": 596908, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9794931411743164, "global_step": 596909, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0521600246429443, "global_step": 596910, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9706038236618042, "global_step": 596911, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0320374965667725, "global_step": 596912, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9502501487731934, "global_step": 596913, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0199761390686035, "global_step": 596914, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9503036737442017, "global_step": 596915, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.094508171081543, "global_step": 596916, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0194084644317627, "global_step": 596917, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.112086534500122, "global_step": 596918, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0576953887939453, "global_step": 596919, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9338773488998413, "global_step": 596920, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.031029224395752, "global_step": 596921, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9867757558822632, "global_step": 596922, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0196170806884766, "global_step": 596923, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9837982654571533, "global_step": 596924, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0332417488098145, "global_step": 596925, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0667362213134766, "global_step": 596926, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9854216575622559, "global_step": 596927, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9447646141052246, "global_step": 596928, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.970827341079712, "global_step": 596929, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0658504962921143, "global_step": 596930, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0085184574127197, "global_step": 596931, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0138118267059326, "global_step": 596932, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0331099033355713, "global_step": 596933, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.089083194732666, "global_step": 596934, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.011793851852417, "global_step": 596935, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0609359741210938, "global_step": 596936, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9671844244003296, "global_step": 596937, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.057492733001709, "global_step": 596938, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0279769897460938, "global_step": 596939, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9575605392456055, "global_step": 596940, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0076143741607666, "global_step": 596941, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.114712953567505, "global_step": 596942, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9439172744750977, "global_step": 596943, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.1568074226379395, "global_step": 596944, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.042471408843994, "global_step": 596945, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.955465316772461, "global_step": 596946, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0478570461273193, "global_step": 596947, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9520014524459839, "global_step": 596948, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.1153600215911865, "global_step": 596949, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0657529830932617, "global_step": 596950, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.103318452835083, "global_step": 596951, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.958951711654663, "global_step": 596952, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.068148374557495, "global_step": 596953, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.971367597579956, "global_step": 596954, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0149316787719727, "global_step": 596955, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.982167363166809, "global_step": 596956, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9767050743103027, "global_step": 596957, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0409743785858154, "global_step": 596958, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0856456756591797, "global_step": 596959, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0301055908203125, "global_step": 596960, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0442168712615967, "global_step": 596961, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0062906742095947, "global_step": 596962, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0634377002716064, "global_step": 596963, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9804050922393799, "global_step": 596964, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9696005582809448, "global_step": 596965, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.04081654548645, "global_step": 596966, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9824645519256592, "global_step": 596967, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.097344160079956, "global_step": 596968, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.958203911781311, "global_step": 596969, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0017054080963135, "global_step": 596970, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9993278980255127, "global_step": 596971, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.013087749481201, "global_step": 596972, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0657434463500977, "global_step": 596973, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9484727382659912, "global_step": 596974, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9909673929214478, "global_step": 596975, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.987622857093811, "global_step": 596976, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9571086168289185, "global_step": 596977, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9980801343917847, "global_step": 596978, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0125412940979004, "global_step": 596979, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0542006492614746, "global_step": 596980, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0493109226226807, "global_step": 596981, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.137352705001831, "global_step": 596982, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.1337292194366455, "global_step": 596983, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0299720764160156, "global_step": 596984, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9358675479888916, "global_step": 596985, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.002697706222534, "global_step": 596986, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0961265563964844, "global_step": 596987, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0765810012817383, "global_step": 596988, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.97333824634552, "global_step": 596989, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.066277027130127, "global_step": 596990, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9522117376327515, "global_step": 596991, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.014796495437622, "global_step": 596992, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.096924304962158, "global_step": 596993, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.046116590499878, "global_step": 596994, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0228147506713867, "global_step": 596995, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0084400177001953, "global_step": 596996, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0043084621429443, "global_step": 596997, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.000401496887207, "global_step": 596998, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0436720848083496, "global_step": 596999, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0419750213623047, "global_step": 597000, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.8993498086929321, "global_step": 597001, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.047764539718628, "global_step": 597002, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9749692678451538, "global_step": 597003, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0116333961486816, "global_step": 597004, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0868966579437256, "global_step": 597005, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0538623332977295, "global_step": 597006, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9688116312026978, "global_step": 597007, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9751232862472534, "global_step": 597008, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9991194009780884, "global_step": 597009, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0697550773620605, "global_step": 597010, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.987397313117981, "global_step": 597011, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.1307826042175293, "global_step": 597012, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.134732484817505, "global_step": 597013, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9721579551696777, "global_step": 597014, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9910846948623657, "global_step": 597015, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.054666757583618, "global_step": 597016, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9949287176132202, "global_step": 597017, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9632186889648438, "global_step": 597018, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0589816570281982, "global_step": 597019, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0768685340881348, "global_step": 597020, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0480525493621826, "global_step": 597021, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9822874069213867, "global_step": 597022, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.002610683441162, "global_step": 597023, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.0473687648773193, "global_step": 597024, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.035881757736206, "global_step": 597025, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9758599996566772, "global_step": 597026, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9250028133392334, "global_step": 597027, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9147682189941406, "global_step": 597028, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.01223087310791, "global_step": 597029, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9523189067840576, "global_step": 597030, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.1303417682647705, "global_step": 597031, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9725408554077148, "global_step": 597032, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.04852032661438, "global_step": 597033, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.083496570587158, "global_step": 597034, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9952210187911987, "global_step": 597035, "epoch": 965, "lr": 5e-05}
{"train_loss": 2.015942335128784, "global_step": 597036, "epoch": 965, "lr": 5e-05}
{"train_loss": 1.9320142269134521, "global_step": 597037, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.048485040664673, "global_step": 597038, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0106570720672607, "global_step": 597039, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0215559005737305, "global_step": 597040, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0634381771087646, "global_step": 597041, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9541667699813843, "global_step": 597042, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0089659690856934, "global_step": 597043, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.08949613571167, "global_step": 597044, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0248780250549316, "global_step": 597045, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.924220323562622, "global_step": 597046, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9749358892440796, "global_step": 597047, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0543079376220703, "global_step": 597048, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9342997074127197, "global_step": 597049, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.025973081588745, "global_step": 597050, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0467169284820557, "global_step": 597051, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.040478467941284, "global_step": 597052, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9587106704711914, "global_step": 597053, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.067659616470337, "global_step": 597054, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9617983102798462, "global_step": 597055, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.073119640350342, "global_step": 597056, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.965552806854248, "global_step": 597057, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.974127173423767, "global_step": 597058, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.030179738998413, "global_step": 597059, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0015921592712402, "global_step": 597060, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.976118803024292, "global_step": 597061, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.903955101966858, "global_step": 597062, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.012521505355835, "global_step": 597063, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.042175769805908, "global_step": 597064, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9482641220092773, "global_step": 597065, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9609036445617676, "global_step": 597066, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.031658411026001, "global_step": 597067, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.000974416732788, "global_step": 597068, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.983974575996399, "global_step": 597069, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0376040935516357, "global_step": 597070, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.028193950653076, "global_step": 597071, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.917129635810852, "global_step": 597072, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.021812915802002, "global_step": 597073, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.00015926361084, "global_step": 597074, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.039602041244507, "global_step": 597075, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9701769351959229, "global_step": 597076, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9545308351516724, "global_step": 597077, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9932385683059692, "global_step": 597078, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0752673149108887, "global_step": 597079, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0719902515411377, "global_step": 597080, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0852997303009033, "global_step": 597081, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.009347438812256, "global_step": 597082, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9932117462158203, "global_step": 597083, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9586641788482666, "global_step": 597084, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9936763048171997, "global_step": 597085, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.030174970626831, "global_step": 597086, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.030893564224243, "global_step": 597087, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9821877479553223, "global_step": 597088, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9801390171051025, "global_step": 597089, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.01352596282959, "global_step": 597090, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0185458660125732, "global_step": 597091, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9292083978652954, "global_step": 597092, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9836313724517822, "global_step": 597093, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9634195566177368, "global_step": 597094, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0481791496276855, "global_step": 597095, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.939268946647644, "global_step": 597096, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0055601596832275, "global_step": 597097, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9220671653747559, "global_step": 597098, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9712786674499512, "global_step": 597099, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9618726968765259, "global_step": 597100, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0584776401519775, "global_step": 597101, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.076725482940674, "global_step": 597102, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9577735662460327, "global_step": 597103, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9664649963378906, "global_step": 597104, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.00273060798645, "global_step": 597105, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0039303302764893, "global_step": 597106, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0387675762176514, "global_step": 597107, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.990997314453125, "global_step": 597108, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9637584686279297, "global_step": 597109, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0492613315582275, "global_step": 597110, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9569835662841797, "global_step": 597111, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.035097360610962, "global_step": 597112, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9780713319778442, "global_step": 597113, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9660862684249878, "global_step": 597114, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9902621507644653, "global_step": 597115, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0062761306762695, "global_step": 597116, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.991783857345581, "global_step": 597117, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.999588131904602, "global_step": 597118, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9856137037277222, "global_step": 597119, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0542960166931152, "global_step": 597120, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9816217422485352, "global_step": 597121, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9729949235916138, "global_step": 597122, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0912528038024902, "global_step": 597123, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.105545997619629, "global_step": 597124, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0445146560668945, "global_step": 597125, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9804035425186157, "global_step": 597126, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.03395676612854, "global_step": 597127, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9744791984558105, "global_step": 597128, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0560708045959473, "global_step": 597129, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.028665065765381, "global_step": 597130, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0385608673095703, "global_step": 597131, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9306886196136475, "global_step": 597132, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.042259931564331, "global_step": 597133, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0196402072906494, "global_step": 597134, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0930581092834473, "global_step": 597135, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.12262225151062, "global_step": 597136, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.037741184234619, "global_step": 597137, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9887510538101196, "global_step": 597138, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9406951665878296, "global_step": 597139, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0786795616149902, "global_step": 597140, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0124194622039795, "global_step": 597141, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9788806438446045, "global_step": 597142, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.056145429611206, "global_step": 597143, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0115578174591064, "global_step": 597144, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.025351047515869, "global_step": 597145, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.008152484893799, "global_step": 597146, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9744038581848145, "global_step": 597147, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.008479118347168, "global_step": 597148, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0214552879333496, "global_step": 597149, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9330012798309326, "global_step": 597150, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.071787118911743, "global_step": 597151, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9091613292694092, "global_step": 597152, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9773517847061157, "global_step": 597153, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.984339714050293, "global_step": 597154, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.051457166671753, "global_step": 597155, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0137722492218018, "global_step": 597156, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.009779214859009, "global_step": 597157, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0613367557525635, "global_step": 597158, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9487886428833008, "global_step": 597159, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0720250606536865, "global_step": 597160, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9905409812927246, "global_step": 597161, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.018076181411743, "global_step": 597162, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.082493305206299, "global_step": 597163, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.029848337173462, "global_step": 597164, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9690660238265991, "global_step": 597165, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0057778358459473, "global_step": 597166, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.982762336730957, "global_step": 597167, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.078603744506836, "global_step": 597168, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0070650577545166, "global_step": 597169, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0528674125671387, "global_step": 597170, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0063910484313965, "global_step": 597171, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.111849784851074, "global_step": 597172, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0009586811065674, "global_step": 597173, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.031182289123535, "global_step": 597174, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9711294174194336, "global_step": 597175, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9598705768585205, "global_step": 597176, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.994307041168213, "global_step": 597177, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.046377658843994, "global_step": 597178, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9875212907791138, "global_step": 597179, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.983487606048584, "global_step": 597180, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9213236570358276, "global_step": 597181, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.936885118484497, "global_step": 597182, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9635297060012817, "global_step": 597183, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9516631364822388, "global_step": 597184, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9957492351531982, "global_step": 597185, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9559763669967651, "global_step": 597186, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.994835615158081, "global_step": 597187, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0031840801239014, "global_step": 597188, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0560574531555176, "global_step": 597189, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9923676252365112, "global_step": 597190, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0577993392944336, "global_step": 597191, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.082787036895752, "global_step": 597192, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9806346893310547, "global_step": 597193, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0411784648895264, "global_step": 597194, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.000502586364746, "global_step": 597195, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9263540506362915, "global_step": 597196, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.005103588104248, "global_step": 597197, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9909520149230957, "global_step": 597198, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0222997665405273, "global_step": 597199, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.053734302520752, "global_step": 597200, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.012115478515625, "global_step": 597201, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.004697322845459, "global_step": 597202, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0073788166046143, "global_step": 597203, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.982780933380127, "global_step": 597204, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0545763969421387, "global_step": 597205, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0982580184936523, "global_step": 597206, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0466856956481934, "global_step": 597207, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0098917484283447, "global_step": 597208, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.975653052330017, "global_step": 597209, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.881003499031067, "global_step": 597210, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0446979999542236, "global_step": 597211, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9461052417755127, "global_step": 597212, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9231998920440674, "global_step": 597213, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9918687343597412, "global_step": 597214, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9977200031280518, "global_step": 597215, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0004453659057617, "global_step": 597216, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9178929328918457, "global_step": 597217, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.021853446960449, "global_step": 597218, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.015810966491699, "global_step": 597219, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.061208486557007, "global_step": 597220, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9240655899047852, "global_step": 597221, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.037599563598633, "global_step": 597222, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.032193660736084, "global_step": 597223, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9630428552627563, "global_step": 597224, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9858076572418213, "global_step": 597225, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9697822332382202, "global_step": 597226, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0501599311828613, "global_step": 597227, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9552643299102783, "global_step": 597228, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.022704601287842, "global_step": 597229, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9876925945281982, "global_step": 597230, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9719725847244263, "global_step": 597231, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9025218486785889, "global_step": 597232, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9479286670684814, "global_step": 597233, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9397680759429932, "global_step": 597234, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9854949712753296, "global_step": 597235, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0454511642456055, "global_step": 597236, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0422163009643555, "global_step": 597237, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0175068378448486, "global_step": 597238, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9971104860305786, "global_step": 597239, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9919970035552979, "global_step": 597240, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9622453451156616, "global_step": 597241, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.070647954940796, "global_step": 597242, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9936763048171997, "global_step": 597243, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.1458356380462646, "global_step": 597244, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0309622287750244, "global_step": 597245, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9667348861694336, "global_step": 597246, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9827980995178223, "global_step": 597247, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0371460914611816, "global_step": 597248, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9113255739212036, "global_step": 597249, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0248942375183105, "global_step": 597250, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0493860244750977, "global_step": 597251, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.093994617462158, "global_step": 597252, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.009798049926758, "global_step": 597253, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0072619915008545, "global_step": 597254, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.123666286468506, "global_step": 597255, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9867594242095947, "global_step": 597256, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0210280418395996, "global_step": 597257, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9614429473876953, "global_step": 597258, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0260603427886963, "global_step": 597259, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0181663036346436, "global_step": 597260, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.020691394805908, "global_step": 597261, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.056622266769409, "global_step": 597262, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.985824465751648, "global_step": 597263, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.073697090148926, "global_step": 597264, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9755346775054932, "global_step": 597265, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.097541570663452, "global_step": 597266, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9497127532958984, "global_step": 597267, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9762052297592163, "global_step": 597268, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.980359435081482, "global_step": 597269, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0856738090515137, "global_step": 597270, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.992143988609314, "global_step": 597271, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0533864498138428, "global_step": 597272, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.998779296875, "global_step": 597273, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0172910690307617, "global_step": 597274, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9863463640213013, "global_step": 597275, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.014770269393921, "global_step": 597276, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9353410005569458, "global_step": 597277, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9948140382766724, "global_step": 597278, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0049831867218018, "global_step": 597279, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0075058937072754, "global_step": 597280, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9065585136413574, "global_step": 597281, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0701053142547607, "global_step": 597282, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9465359449386597, "global_step": 597283, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0233402252197266, "global_step": 597284, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0199434757232666, "global_step": 597285, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0007307529449463, "global_step": 597286, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9421653747558594, "global_step": 597287, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.966422438621521, "global_step": 597288, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.075854778289795, "global_step": 597289, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9270949363708496, "global_step": 597290, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0287599563598633, "global_step": 597291, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.003175973892212, "global_step": 597292, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0665576457977295, "global_step": 597293, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.032500743865967, "global_step": 597294, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.067779779434204, "global_step": 597295, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.054649829864502, "global_step": 597296, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.08180570602417, "global_step": 597297, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.083775043487549, "global_step": 597298, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.113677978515625, "global_step": 597299, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.026735544204712, "global_step": 597300, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9757035970687866, "global_step": 597301, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.078641176223755, "global_step": 597302, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0595197677612305, "global_step": 597303, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.087984323501587, "global_step": 597304, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0349459648132324, "global_step": 597305, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9782977104187012, "global_step": 597306, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9845813512802124, "global_step": 597307, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0012412071228027, "global_step": 597308, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.100043535232544, "global_step": 597309, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9934096336364746, "global_step": 597310, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9332424402236938, "global_step": 597311, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.8943501710891724, "global_step": 597312, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9850802421569824, "global_step": 597313, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9810725450515747, "global_step": 597314, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0054566860198975, "global_step": 597315, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.088466167449951, "global_step": 597316, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.015744686126709, "global_step": 597317, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0806567668914795, "global_step": 597318, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.969652533531189, "global_step": 597319, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9859979152679443, "global_step": 597320, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9695132970809937, "global_step": 597321, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9849711656570435, "global_step": 597322, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.039682388305664, "global_step": 597323, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0409626960754395, "global_step": 597324, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9550442695617676, "global_step": 597325, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.031454086303711, "global_step": 597326, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0165109634399414, "global_step": 597327, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0273256301879883, "global_step": 597328, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9802485704421997, "global_step": 597329, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.933059573173523, "global_step": 597330, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.063997268676758, "global_step": 597331, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.063147783279419, "global_step": 597332, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9530396461486816, "global_step": 597333, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9957512617111206, "global_step": 597334, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.015066146850586, "global_step": 597335, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.116880178451538, "global_step": 597336, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.039240837097168, "global_step": 597337, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0091748237609863, "global_step": 597338, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0219247341156006, "global_step": 597339, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0253238677978516, "global_step": 597340, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9554781913757324, "global_step": 597341, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0459113121032715, "global_step": 597342, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.037644863128662, "global_step": 597343, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0688066482543945, "global_step": 597344, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.024670362472534, "global_step": 597345, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9872167110443115, "global_step": 597346, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.961790680885315, "global_step": 597347, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.056870698928833, "global_step": 597348, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9537442922592163, "global_step": 597349, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0387961864471436, "global_step": 597350, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9711322784423828, "global_step": 597351, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9586280584335327, "global_step": 597352, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9801037311553955, "global_step": 597353, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.98408043384552, "global_step": 597354, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9906920194625854, "global_step": 597355, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.141792058944702, "global_step": 597356, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9290494918823242, "global_step": 597357, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.036473274230957, "global_step": 597358, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9826560020446777, "global_step": 597359, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0405430793762207, "global_step": 597360, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9704844951629639, "global_step": 597361, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0854246616363525, "global_step": 597362, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.924747109413147, "global_step": 597363, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0455665588378906, "global_step": 597364, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9732682704925537, "global_step": 597365, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9611380100250244, "global_step": 597366, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.891610860824585, "global_step": 597367, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0382261276245117, "global_step": 597368, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9538462162017822, "global_step": 597369, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9825093746185303, "global_step": 597370, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9538626670837402, "global_step": 597371, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.037385940551758, "global_step": 597372, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.8991024494171143, "global_step": 597373, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.8979402780532837, "global_step": 597374, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0095326900482178, "global_step": 597375, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.993175983428955, "global_step": 597376, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0724565982818604, "global_step": 597377, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0228867530822754, "global_step": 597378, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.922425627708435, "global_step": 597379, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.8987435102462769, "global_step": 597380, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9779400825500488, "global_step": 597381, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0176005363464355, "global_step": 597382, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0180697441101074, "global_step": 597383, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.016927480697632, "global_step": 597384, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.069239854812622, "global_step": 597385, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.959951639175415, "global_step": 597386, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0185465812683105, "global_step": 597387, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.052713394165039, "global_step": 597388, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.980894684791565, "global_step": 597389, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.029062271118164, "global_step": 597390, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9826090335845947, "global_step": 597391, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0786073207855225, "global_step": 597392, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0322439670562744, "global_step": 597393, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.022789716720581, "global_step": 597394, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.045752763748169, "global_step": 597395, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0014636516571045, "global_step": 597396, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0289084911346436, "global_step": 597397, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.00380277633667, "global_step": 597398, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0228500366210938, "global_step": 597399, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.065568685531616, "global_step": 597400, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9996509552001953, "global_step": 597401, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0232434272766113, "global_step": 597402, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0347678661346436, "global_step": 597403, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9866544008255005, "global_step": 597404, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.083996295928955, "global_step": 597405, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0502071380615234, "global_step": 597406, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.058396816253662, "global_step": 597407, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9476882219314575, "global_step": 597408, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9913146495819092, "global_step": 597409, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9967924356460571, "global_step": 597410, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9691121578216553, "global_step": 597411, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0577478408813477, "global_step": 597412, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9229735136032104, "global_step": 597413, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.933288335800171, "global_step": 597414, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0772786140441895, "global_step": 597415, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.045548677444458, "global_step": 597416, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9603177309036255, "global_step": 597417, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9702342748641968, "global_step": 597418, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.010404348373413, "global_step": 597419, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0540771484375, "global_step": 597420, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9795950651168823, "global_step": 597421, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9402462244033813, "global_step": 597422, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0074000358581543, "global_step": 597423, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.018247127532959, "global_step": 597424, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.06760835647583, "global_step": 597425, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9547770023345947, "global_step": 597426, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9779231548309326, "global_step": 597427, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.071181535720825, "global_step": 597428, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0143136978149414, "global_step": 597429, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0637059211730957, "global_step": 597430, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.01084041595459, "global_step": 597431, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.963577389717102, "global_step": 597432, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0534820556640625, "global_step": 597433, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9959897994995117, "global_step": 597434, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0249149799346924, "global_step": 597435, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0712156295776367, "global_step": 597436, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.00905704498291, "global_step": 597437, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9695017337799072, "global_step": 597438, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.033998966217041, "global_step": 597439, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9983491897583008, "global_step": 597440, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.89166259765625, "global_step": 597441, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0486316680908203, "global_step": 597442, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9821535348892212, "global_step": 597443, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.949924349784851, "global_step": 597444, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9649890661239624, "global_step": 597445, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9243195056915283, "global_step": 597446, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.055809259414673, "global_step": 597447, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.000044822692871, "global_step": 597448, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.020615816116333, "global_step": 597449, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0670177936553955, "global_step": 597450, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.1103298664093018, "global_step": 597451, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0765085220336914, "global_step": 597452, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9742873907089233, "global_step": 597453, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0969691276550293, "global_step": 597454, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0238566398620605, "global_step": 597455, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0273237228393555, "global_step": 597456, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0030031204223633, "global_step": 597457, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9791290760040283, "global_step": 597458, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.09919810295105, "global_step": 597459, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.01179838180542, "global_step": 597460, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.8952269554138184, "global_step": 597461, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.06044340133667, "global_step": 597462, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0057969093322754, "global_step": 597463, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.057072401046753, "global_step": 597464, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.1152515411376953, "global_step": 597465, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.002248764038086, "global_step": 597466, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.017768621444702, "global_step": 597467, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9989372491836548, "global_step": 597468, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0591931343078613, "global_step": 597469, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.056313991546631, "global_step": 597470, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9749858379364014, "global_step": 597471, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9750903844833374, "global_step": 597472, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.013544797897339, "global_step": 597473, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.04073166847229, "global_step": 597474, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.000046968460083, "global_step": 597475, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.023550271987915, "global_step": 597476, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.08455753326416, "global_step": 597477, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9819092750549316, "global_step": 597478, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0460269451141357, "global_step": 597479, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.037851572036743, "global_step": 597480, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.041227340698242, "global_step": 597481, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0420982837677, "global_step": 597482, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0437557697296143, "global_step": 597483, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0680489540100098, "global_step": 597484, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.039454936981201, "global_step": 597485, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0086469650268555, "global_step": 597486, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9620622396469116, "global_step": 597487, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9871768951416016, "global_step": 597488, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9395102262496948, "global_step": 597489, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9644991159439087, "global_step": 597490, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0587756633758545, "global_step": 597491, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9414827823638916, "global_step": 597492, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.940402865409851, "global_step": 597493, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.013031244277954, "global_step": 597494, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9615222215652466, "global_step": 597495, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.906302809715271, "global_step": 597496, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.101229429244995, "global_step": 597497, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.087498426437378, "global_step": 597498, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.954219937324524, "global_step": 597499, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.1052775382995605, "global_step": 597500, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9656943082809448, "global_step": 597501, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.056096076965332, "global_step": 597502, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9747159481048584, "global_step": 597503, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9448997974395752, "global_step": 597504, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9490727186203003, "global_step": 597505, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.898363709449768, "global_step": 597506, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0191752910614014, "global_step": 597507, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.108926296234131, "global_step": 597508, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.963055968284607, "global_step": 597509, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0505287647247314, "global_step": 597510, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9789894819259644, "global_step": 597511, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0378804206848145, "global_step": 597512, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0216054916381836, "global_step": 597513, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.021432876586914, "global_step": 597514, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.044994592666626, "global_step": 597515, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9633415937423706, "global_step": 597516, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0402698516845703, "global_step": 597517, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.1574277877807617, "global_step": 597518, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0128443241119385, "global_step": 597519, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.017507791519165, "global_step": 597520, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9937134981155396, "global_step": 597521, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.93422269821167, "global_step": 597522, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0049757957458496, "global_step": 597523, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9670342206954956, "global_step": 597524, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0380704402923584, "global_step": 597525, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9749634265899658, "global_step": 597526, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.024933099746704, "global_step": 597527, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9907084703445435, "global_step": 597528, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.019556760787964, "global_step": 597529, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9909025430679321, "global_step": 597530, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9345693588256836, "global_step": 597531, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9448620080947876, "global_step": 597532, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.075493097305298, "global_step": 597533, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9872914552688599, "global_step": 597534, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.072789430618286, "global_step": 597535, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9691376686096191, "global_step": 597536, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.1075475215911865, "global_step": 597537, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0393354892730713, "global_step": 597538, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0483529567718506, "global_step": 597539, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.005718946456909, "global_step": 597540, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9705498218536377, "global_step": 597541, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0160903930664062, "global_step": 597542, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.003904104232788, "global_step": 597543, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.042003870010376, "global_step": 597544, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.000332832336426, "global_step": 597545, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0440526008605957, "global_step": 597546, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.049238920211792, "global_step": 597547, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9870336055755615, "global_step": 597548, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0045366287231445, "global_step": 597549, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9978481531143188, "global_step": 597550, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0071544647216797, "global_step": 597551, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.020620822906494, "global_step": 597552, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9892520904541016, "global_step": 597553, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0446197986602783, "global_step": 597554, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0299668312072754, "global_step": 597555, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9792929887771606, "global_step": 597556, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9844781160354614, "global_step": 597557, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0264828205108643, "global_step": 597558, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9376778602600098, "global_step": 597559, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.995323657989502, "global_step": 597560, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.1145927906036377, "global_step": 597561, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.994777798652649, "global_step": 597562, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0092973709106445, "global_step": 597563, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9628888368606567, "global_step": 597564, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0396971702575684, "global_step": 597565, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9976831674575806, "global_step": 597566, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.983022928237915, "global_step": 597567, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9655967950820923, "global_step": 597568, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.077436685562134, "global_step": 597569, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9139477014541626, "global_step": 597570, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9605504274368286, "global_step": 597571, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0000224113464355, "global_step": 597572, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9409664869308472, "global_step": 597573, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0246670246124268, "global_step": 597574, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0648086071014404, "global_step": 597575, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.027233839035034, "global_step": 597576, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.054298162460327, "global_step": 597577, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0268948078155518, "global_step": 597578, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.074554204940796, "global_step": 597579, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0130889415740967, "global_step": 597580, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0268468856811523, "global_step": 597581, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.043370246887207, "global_step": 597582, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.078165292739868, "global_step": 597583, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0394744873046875, "global_step": 597584, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.023339033126831, "global_step": 597585, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0426461696624756, "global_step": 597586, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0699448585510254, "global_step": 597587, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9906251430511475, "global_step": 597588, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.001506805419922, "global_step": 597589, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9789941310882568, "global_step": 597590, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.051276445388794, "global_step": 597591, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.044250011444092, "global_step": 597592, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9653346538543701, "global_step": 597593, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0407543182373047, "global_step": 597594, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.051002025604248, "global_step": 597595, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.10868501663208, "global_step": 597596, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9788001775741577, "global_step": 597597, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.037670373916626, "global_step": 597598, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.8457690477371216, "global_step": 597599, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0777130126953125, "global_step": 597600, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9940288066864014, "global_step": 597601, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9655779600143433, "global_step": 597602, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.997599720954895, "global_step": 597603, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9947960376739502, "global_step": 597604, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.054112434387207, "global_step": 597605, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.045366048812866, "global_step": 597606, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0045859813690186, "global_step": 597607, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9168957471847534, "global_step": 597608, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9437808990478516, "global_step": 597609, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9656866788864136, "global_step": 597610, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.094697952270508, "global_step": 597611, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9695444107055664, "global_step": 597612, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.024482011795044, "global_step": 597613, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0423905849456787, "global_step": 597614, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0097970962524414, "global_step": 597615, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.00313401222229, "global_step": 597616, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.126359462738037, "global_step": 597617, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9873119592666626, "global_step": 597618, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.010288715362549, "global_step": 597619, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.009012222290039, "global_step": 597620, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9711352586746216, "global_step": 597621, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0071330070495605, "global_step": 597622, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9744817018508911, "global_step": 597623, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.003948450088501, "global_step": 597624, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0164854526519775, "global_step": 597625, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0312750339508057, "global_step": 597626, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.009225368499756, "global_step": 597627, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9351814985275269, "global_step": 597628, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.935707926750183, "global_step": 597629, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0125019550323486, "global_step": 597630, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9900511503219604, "global_step": 597631, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0082662105560303, "global_step": 597632, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.025458812713623, "global_step": 597633, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0684056282043457, "global_step": 597634, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9796199798583984, "global_step": 597635, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.077709436416626, "global_step": 597636, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0635123252868652, "global_step": 597637, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.001025676727295, "global_step": 597638, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.046391725540161, "global_step": 597639, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9860283136367798, "global_step": 597640, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9974843263626099, "global_step": 597641, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9961782693862915, "global_step": 597642, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0929033756256104, "global_step": 597643, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0187196731567383, "global_step": 597644, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9417248964309692, "global_step": 597645, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0217161178588867, "global_step": 597646, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0519843101501465, "global_step": 597647, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.044977903366089, "global_step": 597648, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9869887828826904, "global_step": 597649, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0474703311920166, "global_step": 597650, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.011418104171753, "global_step": 597651, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.076385259628296, "global_step": 597652, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.03126859664917, "global_step": 597653, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0092644691467285, "global_step": 597654, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0728278160095215, "global_step": 597655, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9732784032821655, "global_step": 597656, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0310778617858887, "global_step": 597657, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9527190923690796, "global_step": 597658, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.036848306655884, "global_step": 597659, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9762957096099854, "global_step": 597660, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.024768114089966, "global_step": 597661, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9275773763656616, "global_step": 597662, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0057828426361084, "global_step": 597663, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.041452407836914, "global_step": 597664, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.019604444503784, "global_step": 597665, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9597934484481812, "global_step": 597666, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0360236167907715, "global_step": 597667, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9854412078857422, "global_step": 597668, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0407814979553223, "global_step": 597669, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9996849298477173, "global_step": 597670, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0724661350250244, "global_step": 597671, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0438215732574463, "global_step": 597672, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.935451865196228, "global_step": 597673, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0011422634124756, "global_step": 597674, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.04754638671875, "global_step": 597675, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9503475427627563, "global_step": 597676, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.043055295944214, "global_step": 597677, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.032487630844116, "global_step": 597678, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.044975519180298, "global_step": 597679, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.115981340408325, "global_step": 597680, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.062070369720459, "global_step": 597681, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9281996488571167, "global_step": 597682, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.1110479831695557, "global_step": 597683, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9400590658187866, "global_step": 597684, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0117149353027344, "global_step": 597685, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0309736728668213, "global_step": 597686, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9324071407318115, "global_step": 597687, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.121286630630493, "global_step": 597688, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.018183708190918, "global_step": 597689, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.005084753036499, "global_step": 597690, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0182719230651855, "global_step": 597691, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0503780841827393, "global_step": 597692, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.967494010925293, "global_step": 597693, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0606791973114014, "global_step": 597694, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9419654607772827, "global_step": 597695, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0177714824676514, "global_step": 597696, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.042140483856201, "global_step": 597697, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.001434803009033, "global_step": 597698, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.988477110862732, "global_step": 597699, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0199272632598877, "global_step": 597700, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.1013989448547363, "global_step": 597701, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.017239809036255, "global_step": 597702, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0520224571228027, "global_step": 597703, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9997375011444092, "global_step": 597704, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9200173616409302, "global_step": 597705, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9815518856048584, "global_step": 597706, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.069840669631958, "global_step": 597707, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0206267833709717, "global_step": 597708, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9905600547790527, "global_step": 597709, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9481894969940186, "global_step": 597710, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0519001483917236, "global_step": 597711, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0159895420074463, "global_step": 597712, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.106096029281616, "global_step": 597713, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.07770037651062, "global_step": 597714, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.038713216781616, "global_step": 597715, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9780800342559814, "global_step": 597716, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0731394290924072, "global_step": 597717, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.030100107192993, "global_step": 597718, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9904162883758545, "global_step": 597719, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0973496437072754, "global_step": 597720, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0126991271972656, "global_step": 597721, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9622836112976074, "global_step": 597722, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.8797937631607056, "global_step": 597723, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.028856039047241, "global_step": 597724, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.004542112350464, "global_step": 597725, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0628325939178467, "global_step": 597726, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.077601194381714, "global_step": 597727, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.983764410018921, "global_step": 597728, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9367692470550537, "global_step": 597729, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0489420890808105, "global_step": 597730, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0446560382843018, "global_step": 597731, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0521912574768066, "global_step": 597732, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0327718257904053, "global_step": 597733, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9970086812973022, "global_step": 597734, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9992940425872803, "global_step": 597735, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9774283170700073, "global_step": 597736, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.932021975517273, "global_step": 597737, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.057025194168091, "global_step": 597738, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0065762996673584, "global_step": 597739, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.059243679046631, "global_step": 597740, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9735873937606812, "global_step": 597741, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.970131754875183, "global_step": 597742, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.063959836959839, "global_step": 597743, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.95268714427948, "global_step": 597744, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.054255723953247, "global_step": 597745, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9786325693130493, "global_step": 597746, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.077561855316162, "global_step": 597747, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.976623773574829, "global_step": 597748, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.003270149230957, "global_step": 597749, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.032557249069214, "global_step": 597750, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.973462462425232, "global_step": 597751, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0015790462493896, "global_step": 597752, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9760733842849731, "global_step": 597753, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.00225830078125, "global_step": 597754, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0043935775756836, "global_step": 597755, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9918289184570312, "global_step": 597756, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0103037357330322, "global_step": 597757, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.004530429840088, "global_step": 597758, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0204577445983887, "global_step": 597759, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9760724306106567, "global_step": 597760, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9677824974060059, "global_step": 597761, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0627360343933105, "global_step": 597762, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9602811336517334, "global_step": 597763, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.073586940765381, "global_step": 597764, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.040175676345825, "global_step": 597765, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.060927629470825, "global_step": 597766, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.031876564025879, "global_step": 597767, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.1415629386901855, "global_step": 597768, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9643490314483643, "global_step": 597769, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.010017156600952, "global_step": 597770, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.030244827270508, "global_step": 597771, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.936091661453247, "global_step": 597772, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9668654203414917, "global_step": 597773, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0796916484832764, "global_step": 597774, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.975803017616272, "global_step": 597775, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0458290576934814, "global_step": 597776, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0059940814971924, "global_step": 597777, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9627737998962402, "global_step": 597778, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.069624900817871, "global_step": 597779, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0565459728240967, "global_step": 597780, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.049664258956909, "global_step": 597781, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9742504358291626, "global_step": 597782, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0099260807037354, "global_step": 597783, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.894165277481079, "global_step": 597784, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.00764799118042, "global_step": 597785, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.008220672607422, "global_step": 597786, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0335183143615723, "global_step": 597787, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0436744689941406, "global_step": 597788, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9571435451507568, "global_step": 597789, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0027761459350586, "global_step": 597790, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.944155216217041, "global_step": 597791, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.959522008895874, "global_step": 597792, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.080409288406372, "global_step": 597793, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0196735858917236, "global_step": 597794, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9416437149047852, "global_step": 597795, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.064058542251587, "global_step": 597796, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.038421392440796, "global_step": 597797, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9711910486221313, "global_step": 597798, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.102951765060425, "global_step": 597799, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9515997171401978, "global_step": 597800, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.025728940963745, "global_step": 597801, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0989787578582764, "global_step": 597802, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.018676996231079, "global_step": 597803, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0398128032684326, "global_step": 597804, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0651731491088867, "global_step": 597805, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.1166422367095947, "global_step": 597806, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.00978422164917, "global_step": 597807, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0553760528564453, "global_step": 597808, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0169272422790527, "global_step": 597809, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0559239387512207, "global_step": 597810, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.015933036804199, "global_step": 597811, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0349111557006836, "global_step": 597812, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.044846296310425, "global_step": 597813, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9322508573532104, "global_step": 597814, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9414981603622437, "global_step": 597815, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0479414463043213, "global_step": 597816, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.953871726989746, "global_step": 597817, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.051237106323242, "global_step": 597818, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.96768319606781, "global_step": 597819, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9820636510849, "global_step": 597820, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.063979148864746, "global_step": 597821, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.08852219581604, "global_step": 597822, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9892417192459106, "global_step": 597823, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9955350160598755, "global_step": 597824, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0148158073425293, "global_step": 597825, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.136902332305908, "global_step": 597826, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.050431251525879, "global_step": 597827, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.051241397857666, "global_step": 597828, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0326128005981445, "global_step": 597829, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.024634838104248, "global_step": 597830, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9860472679138184, "global_step": 597831, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0921900272369385, "global_step": 597832, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9853065013885498, "global_step": 597833, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.004112720489502, "global_step": 597834, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0443339347839355, "global_step": 597835, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0785574913024902, "global_step": 597836, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0677852630615234, "global_step": 597837, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0142133235931396, "global_step": 597838, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0300276279449463, "global_step": 597839, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9966543912887573, "global_step": 597840, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0566205978393555, "global_step": 597841, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.014031410217285, "global_step": 597842, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.033996105194092, "global_step": 597843, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.997990369796753, "global_step": 597844, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9788089990615845, "global_step": 597845, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.8995840549468994, "global_step": 597846, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.05012583732605, "global_step": 597847, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0554375648498535, "global_step": 597848, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0491549968719482, "global_step": 597849, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.966692328453064, "global_step": 597850, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.973578691482544, "global_step": 597851, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.992433786392212, "global_step": 597852, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.8924330472946167, "global_step": 597853, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9650977849960327, "global_step": 597854, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9996354579925537, "global_step": 597855, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.1370136737823486, "global_step": 597856, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.983410358428955, "global_step": 597857, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0480573177337646, "global_step": 597858, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.007518768310547, "global_step": 597859, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.037383556365967, "global_step": 597860, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0177507400512695, "global_step": 597861, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.044114351272583, "global_step": 597862, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.057215452194214, "global_step": 597863, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0352940559387207, "global_step": 597864, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.020751476287842, "global_step": 597865, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0149786472320557, "global_step": 597866, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9843084812164307, "global_step": 597867, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9878196716308594, "global_step": 597868, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0102245807647705, "global_step": 597869, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.995510458946228, "global_step": 597870, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0768463611602783, "global_step": 597871, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9622870683670044, "global_step": 597872, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9853432178497314, "global_step": 597873, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0592267513275146, "global_step": 597874, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.943900227546692, "global_step": 597875, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0855677127838135, "global_step": 597876, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9441534280776978, "global_step": 597877, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9541596174240112, "global_step": 597878, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.994150996208191, "global_step": 597879, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.154572010040283, "global_step": 597880, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0241401195526123, "global_step": 597881, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9220231771469116, "global_step": 597882, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9642255306243896, "global_step": 597883, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0847864151000977, "global_step": 597884, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0110414028167725, "global_step": 597885, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0268900394439697, "global_step": 597886, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.018576145172119, "global_step": 597887, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.017704486846924, "global_step": 597888, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0844223499298096, "global_step": 597889, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.984264850616455, "global_step": 597890, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0509543418884277, "global_step": 597891, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9071705341339111, "global_step": 597892, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0123045444488525, "global_step": 597893, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9594056606292725, "global_step": 597894, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9564014673233032, "global_step": 597895, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0569725036621094, "global_step": 597896, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.1572086811065674, "global_step": 597897, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9625486135482788, "global_step": 597898, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.070997953414917, "global_step": 597899, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0729331970214844, "global_step": 597900, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.049419641494751, "global_step": 597901, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0860445499420166, "global_step": 597902, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0658059120178223, "global_step": 597903, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.036140203475952, "global_step": 597904, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0127317905426025, "global_step": 597905, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0837631225585938, "global_step": 597906, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.014064073562622, "global_step": 597907, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.952126383781433, "global_step": 597908, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.984318494796753, "global_step": 597909, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9734196662902832, "global_step": 597910, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.048771381378174, "global_step": 597911, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.048766613006592, "global_step": 597912, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0213706493377686, "global_step": 597913, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.988767147064209, "global_step": 597914, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9980367422103882, "global_step": 597915, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.012073040008545, "global_step": 597916, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9307188987731934, "global_step": 597917, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0260839462280273, "global_step": 597918, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.054631233215332, "global_step": 597919, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0303564071655273, "global_step": 597920, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0885109901428223, "global_step": 597921, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.087991952896118, "global_step": 597922, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0848891735076904, "global_step": 597923, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0088069438934326, "global_step": 597924, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9856164455413818, "global_step": 597925, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9989029169082642, "global_step": 597926, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.086211681365967, "global_step": 597927, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9416030645370483, "global_step": 597928, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.071913003921509, "global_step": 597929, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9451450109481812, "global_step": 597930, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9699829816818237, "global_step": 597931, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0691580772399902, "global_step": 597932, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9643023014068604, "global_step": 597933, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.059664011001587, "global_step": 597934, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.864861249923706, "global_step": 597935, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.997462511062622, "global_step": 597936, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.042478084564209, "global_step": 597937, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.021810531616211, "global_step": 597938, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0197839736938477, "global_step": 597939, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0059847831726074, "global_step": 597940, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9664559364318848, "global_step": 597941, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0475611686706543, "global_step": 597942, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0228757858276367, "global_step": 597943, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0353543758392334, "global_step": 597944, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0906403064727783, "global_step": 597945, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9601490497589111, "global_step": 597946, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.970869541168213, "global_step": 597947, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.012451171875, "global_step": 597948, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.023545026779175, "global_step": 597949, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9970510005950928, "global_step": 597950, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.007566452026367, "global_step": 597951, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0985212326049805, "global_step": 597952, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0098562240600586, "global_step": 597953, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.946394681930542, "global_step": 597954, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0046699047088623, "global_step": 597955, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9277949333190918, "global_step": 597956, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.129794120788574, "global_step": 597957, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.895321011543274, "global_step": 597958, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0430564880371094, "global_step": 597959, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0012295246124268, "global_step": 597960, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.089566707611084, "global_step": 597961, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.066941499710083, "global_step": 597962, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9507931470870972, "global_step": 597963, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9496420621871948, "global_step": 597964, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9952964782714844, "global_step": 597965, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9942967891693115, "global_step": 597966, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.02112078666687, "global_step": 597967, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0089311599731445, "global_step": 597968, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.004751443862915, "global_step": 597969, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9689078330993652, "global_step": 597970, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9571774005889893, "global_step": 597971, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.032747268676758, "global_step": 597972, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.064923048019409, "global_step": 597973, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0940587520599365, "global_step": 597974, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.070180892944336, "global_step": 597975, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0810489654541016, "global_step": 597976, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.059521436691284, "global_step": 597977, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0400021076202393, "global_step": 597978, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0015957355499268, "global_step": 597979, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.161421298980713, "global_step": 597980, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.069509506225586, "global_step": 597981, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.010671377182007, "global_step": 597982, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.015281915664673, "global_step": 597983, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0148565769195557, "global_step": 597984, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0152835845947266, "global_step": 597985, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.081157684326172, "global_step": 597986, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9665141105651855, "global_step": 597987, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0836946964263916, "global_step": 597988, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9865076541900635, "global_step": 597989, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9604345560073853, "global_step": 597990, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.045167922973633, "global_step": 597991, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.05226469039917, "global_step": 597992, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9918863773345947, "global_step": 597993, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.010267734527588, "global_step": 597994, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.068510055541992, "global_step": 597995, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0486080646514893, "global_step": 597996, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0278677940368652, "global_step": 597997, "epoch": 966, "lr": 5e-05}
{"train_loss": 1.9774832725524902, "global_step": 597998, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.091594934463501, "global_step": 597999, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0809502601623535, "global_step": 598000, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.094250440597534, "global_step": 598001, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0538406372070312, "global_step": 598002, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0261011123657227, "global_step": 598003, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0073094367980957, "global_step": 598004, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.012338876724243, "global_step": 598005, "epoch": 966, "lr": 5e-05}
{"train_loss": 2.0523996353149414, "global_step": 598006, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0304176807403564, "global_step": 598007, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9674431085586548, "global_step": 598008, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9626317024230957, "global_step": 598009, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.022892713546753, "global_step": 598010, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9993280172348022, "global_step": 598011, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0554628372192383, "global_step": 598012, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.991286277770996, "global_step": 598013, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0091001987457275, "global_step": 598014, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0578930377960205, "global_step": 598015, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.089366912841797, "global_step": 598016, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9402424097061157, "global_step": 598017, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0191681385040283, "global_step": 598018, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.91531503200531, "global_step": 598019, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9549920558929443, "global_step": 598020, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.03983736038208, "global_step": 598021, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9223886728286743, "global_step": 598022, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9581156969070435, "global_step": 598023, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0057144165039062, "global_step": 598024, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.017589807510376, "global_step": 598025, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0236542224884033, "global_step": 598026, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.115220069885254, "global_step": 598027, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0977282524108887, "global_step": 598028, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.010488510131836, "global_step": 598029, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0371146202087402, "global_step": 598030, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.002157211303711, "global_step": 598031, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0514707565307617, "global_step": 598032, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.1043736934661865, "global_step": 598033, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.977219820022583, "global_step": 598034, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9793453216552734, "global_step": 598035, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9535267353057861, "global_step": 598036, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.011152982711792, "global_step": 598037, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.908047080039978, "global_step": 598038, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0029873847961426, "global_step": 598039, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0257136821746826, "global_step": 598040, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.014989137649536, "global_step": 598041, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.994829535484314, "global_step": 598042, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0842533111572266, "global_step": 598043, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.006967306137085, "global_step": 598044, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.003992795944214, "global_step": 598045, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0491769313812256, "global_step": 598046, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0564260482788086, "global_step": 598047, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0185437202453613, "global_step": 598048, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9545913934707642, "global_step": 598049, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.987628698348999, "global_step": 598050, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0909314155578613, "global_step": 598051, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9069788455963135, "global_step": 598052, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9572300910949707, "global_step": 598053, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.962671160697937, "global_step": 598054, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.004352331161499, "global_step": 598055, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.004196882247925, "global_step": 598056, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0064940452575684, "global_step": 598057, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9946537017822266, "global_step": 598058, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0268073081970215, "global_step": 598059, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.991065502166748, "global_step": 598060, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0156350135803223, "global_step": 598061, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9646408557891846, "global_step": 598062, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.098597288131714, "global_step": 598063, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0218706130981445, "global_step": 598064, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.039729356765747, "global_step": 598065, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.089630603790283, "global_step": 598066, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.977909803390503, "global_step": 598067, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.062387704849243, "global_step": 598068, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.025913715362549, "global_step": 598069, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.024670362472534, "global_step": 598070, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9798210859298706, "global_step": 598071, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.984466791152954, "global_step": 598072, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0495059490203857, "global_step": 598073, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.98146390914917, "global_step": 598074, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9543251991271973, "global_step": 598075, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0001258850097656, "global_step": 598076, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0415358543395996, "global_step": 598077, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.1160640716552734, "global_step": 598078, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.992370843887329, "global_step": 598079, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9532983303070068, "global_step": 598080, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9490771293640137, "global_step": 598081, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9956467151641846, "global_step": 598082, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0038580894470215, "global_step": 598083, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9624390602111816, "global_step": 598084, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9900128841400146, "global_step": 598085, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.010613441467285, "global_step": 598086, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0284712314605713, "global_step": 598087, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0322425365448, "global_step": 598088, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.010233163833618, "global_step": 598089, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9980913400650024, "global_step": 598090, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9914511442184448, "global_step": 598091, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.007298231124878, "global_step": 598092, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0572705268859863, "global_step": 598093, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0069570541381836, "global_step": 598094, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9211872816085815, "global_step": 598095, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0247483253479004, "global_step": 598096, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9932560920715332, "global_step": 598097, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9894410371780396, "global_step": 598098, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9655038118362427, "global_step": 598099, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.009025812149048, "global_step": 598100, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.01554274559021, "global_step": 598101, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9695708751678467, "global_step": 598102, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0250439643859863, "global_step": 598103, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.026567220687866, "global_step": 598104, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9697788953781128, "global_step": 598105, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0356857776641846, "global_step": 598106, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0625252723693848, "global_step": 598107, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9903485774993896, "global_step": 598108, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9653468132019043, "global_step": 598109, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0180509090423584, "global_step": 598110, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9176747798919678, "global_step": 598111, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0465989112854004, "global_step": 598112, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0445730686187744, "global_step": 598113, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9147415161132812, "global_step": 598114, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0698719024658203, "global_step": 598115, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.028322458267212, "global_step": 598116, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9520083665847778, "global_step": 598117, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9045805931091309, "global_step": 598118, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.104794979095459, "global_step": 598119, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0699548721313477, "global_step": 598120, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.979137659072876, "global_step": 598121, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9937055110931396, "global_step": 598122, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9795247316360474, "global_step": 598123, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.934860110282898, "global_step": 598124, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.00124192237854, "global_step": 598125, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0091607570648193, "global_step": 598126, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.037367343902588, "global_step": 598127, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.926745891571045, "global_step": 598128, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9763383865356445, "global_step": 598129, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9461885690689087, "global_step": 598130, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9132353067398071, "global_step": 598131, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0083632469177246, "global_step": 598132, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.025729179382324, "global_step": 598133, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0511233806610107, "global_step": 598134, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.051656484603882, "global_step": 598135, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9913372993469238, "global_step": 598136, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9481346607208252, "global_step": 598137, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.059016704559326, "global_step": 598138, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.930552363395691, "global_step": 598139, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.074916362762451, "global_step": 598140, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.895246148109436, "global_step": 598141, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9907488822937012, "global_step": 598142, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9890137910842896, "global_step": 598143, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9459749460220337, "global_step": 598144, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0271222591400146, "global_step": 598145, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.98267662525177, "global_step": 598146, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0625545978546143, "global_step": 598147, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.965590238571167, "global_step": 598148, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0869393348693848, "global_step": 598149, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.957338571548462, "global_step": 598150, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.01534366607666, "global_step": 598151, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9824811220169067, "global_step": 598152, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.930635690689087, "global_step": 598153, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.030268430709839, "global_step": 598154, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9212994575500488, "global_step": 598155, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9729655981063843, "global_step": 598156, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9449173212051392, "global_step": 598157, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.007117748260498, "global_step": 598158, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.051523447036743, "global_step": 598159, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9440877437591553, "global_step": 598160, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9757503271102905, "global_step": 598161, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9737968444824219, "global_step": 598162, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.064392566680908, "global_step": 598163, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.8945800065994263, "global_step": 598164, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0090324878692627, "global_step": 598165, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9852112531661987, "global_step": 598166, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0473270416259766, "global_step": 598167, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.980525255203247, "global_step": 598168, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9699047803878784, "global_step": 598169, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9950824975967407, "global_step": 598170, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.092742443084717, "global_step": 598171, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.008030414581299, "global_step": 598172, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.026616096496582, "global_step": 598173, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.170825719833374, "global_step": 598174, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.058666706085205, "global_step": 598175, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0819177627563477, "global_step": 598176, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0074708461761475, "global_step": 598177, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.010143995285034, "global_step": 598178, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.005476236343384, "global_step": 598179, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9403536319732666, "global_step": 598180, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9916738271713257, "global_step": 598181, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0461783409118652, "global_step": 598182, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0245888233184814, "global_step": 598183, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.042065143585205, "global_step": 598184, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9939701557159424, "global_step": 598185, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9922956228256226, "global_step": 598186, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9396123886108398, "global_step": 598187, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9405289888381958, "global_step": 598188, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0467336177825928, "global_step": 598189, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.000225067138672, "global_step": 598190, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9899739027023315, "global_step": 598191, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.992124080657959, "global_step": 598192, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0639162063598633, "global_step": 598193, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.013420343399048, "global_step": 598194, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9359771013259888, "global_step": 598195, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9747004508972168, "global_step": 598196, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0513508319854736, "global_step": 598197, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.003046989440918, "global_step": 598198, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0207231044769287, "global_step": 598199, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9739253520965576, "global_step": 598200, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9902598857879639, "global_step": 598201, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9335798025131226, "global_step": 598202, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9711949825286865, "global_step": 598203, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.005676031112671, "global_step": 598204, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.049506425857544, "global_step": 598205, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9630396366119385, "global_step": 598206, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0113959312438965, "global_step": 598207, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0108983516693115, "global_step": 598208, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9947707653045654, "global_step": 598209, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9911218881607056, "global_step": 598210, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.978919267654419, "global_step": 598211, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0831096172332764, "global_step": 598212, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9681586027145386, "global_step": 598213, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0600085258483887, "global_step": 598214, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9204018115997314, "global_step": 598215, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0376179218292236, "global_step": 598216, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9905505180358887, "global_step": 598217, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9997601509094238, "global_step": 598218, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9808698892593384, "global_step": 598219, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9675086736679077, "global_step": 598220, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9508602619171143, "global_step": 598221, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9904844760894775, "global_step": 598222, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9809828996658325, "global_step": 598223, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0304195880889893, "global_step": 598224, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0143654346466064, "global_step": 598225, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.8972535133361816, "global_step": 598226, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0818357467651367, "global_step": 598227, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.05733323097229, "global_step": 598228, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9625285863876343, "global_step": 598229, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0591137409210205, "global_step": 598230, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9721102714538574, "global_step": 598231, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0296926498413086, "global_step": 598232, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.988969087600708, "global_step": 598233, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.035026788711548, "global_step": 598234, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9913833141326904, "global_step": 598235, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0029733180999756, "global_step": 598236, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.010068655014038, "global_step": 598237, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0422141551971436, "global_step": 598238, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.013490915298462, "global_step": 598239, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0268361568450928, "global_step": 598240, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9970382452011108, "global_step": 598241, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9531835317611694, "global_step": 598242, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9760222434997559, "global_step": 598243, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.066181182861328, "global_step": 598244, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9406850337982178, "global_step": 598245, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9896901845932007, "global_step": 598246, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9472918510437012, "global_step": 598247, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0318827629089355, "global_step": 598248, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.930115818977356, "global_step": 598249, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.036393165588379, "global_step": 598250, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0174124240875244, "global_step": 598251, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9454736709594727, "global_step": 598252, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.000136613845825, "global_step": 598253, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9599708318710327, "global_step": 598254, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9813077449798584, "global_step": 598255, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.026646614074707, "global_step": 598256, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0063881874084473, "global_step": 598257, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.931707501411438, "global_step": 598258, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9775676727294922, "global_step": 598259, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.96710205078125, "global_step": 598260, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.081538200378418, "global_step": 598261, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9900095462799072, "global_step": 598262, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.1017954349517822, "global_step": 598263, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.081000804901123, "global_step": 598264, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.020681381225586, "global_step": 598265, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9891318082809448, "global_step": 598266, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9988946914672852, "global_step": 598267, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.951343059539795, "global_step": 598268, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0263419151306152, "global_step": 598269, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.057084321975708, "global_step": 598270, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0373005867004395, "global_step": 598271, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0362699031829834, "global_step": 598272, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9567272663116455, "global_step": 598273, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9848648309707642, "global_step": 598274, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0550429821014404, "global_step": 598275, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0271754264831543, "global_step": 598276, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0645968914031982, "global_step": 598277, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0236012935638428, "global_step": 598278, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.054243803024292, "global_step": 598279, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.112959623336792, "global_step": 598280, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.085771322250366, "global_step": 598281, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0226798057556152, "global_step": 598282, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0062029361724854, "global_step": 598283, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9445558786392212, "global_step": 598284, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9943441152572632, "global_step": 598285, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.054877519607544, "global_step": 598286, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0251450538635254, "global_step": 598287, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.040985584259033, "global_step": 598288, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9972120523452759, "global_step": 598289, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0336997509002686, "global_step": 598290, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9762531518936157, "global_step": 598291, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9775986671447754, "global_step": 598292, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9989103078842163, "global_step": 598293, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.980210781097412, "global_step": 598294, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9911595582962036, "global_step": 598295, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9590842723846436, "global_step": 598296, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9726536273956299, "global_step": 598297, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0545167922973633, "global_step": 598298, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0325047969818115, "global_step": 598299, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.1100053787231445, "global_step": 598300, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.03535795211792, "global_step": 598301, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0172154903411865, "global_step": 598302, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.047207832336426, "global_step": 598303, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9775925874710083, "global_step": 598304, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0223517417907715, "global_step": 598305, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9860055446624756, "global_step": 598306, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0206093788146973, "global_step": 598307, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0183231830596924, "global_step": 598308, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0162768363952637, "global_step": 598309, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0178775787353516, "global_step": 598310, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9608248472213745, "global_step": 598311, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.982158899307251, "global_step": 598312, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9749058485031128, "global_step": 598313, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.1208274364471436, "global_step": 598314, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9912993907928467, "global_step": 598315, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9552319049835205, "global_step": 598316, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.018887519836426, "global_step": 598317, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.088654041290283, "global_step": 598318, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0739402770996094, "global_step": 598319, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0332179069519043, "global_step": 598320, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0249598026275635, "global_step": 598321, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9694973230361938, "global_step": 598322, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.016892194747925, "global_step": 598323, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.03023624420166, "global_step": 598324, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0561609268188477, "global_step": 598325, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9880785942077637, "global_step": 598326, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9940515756607056, "global_step": 598327, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9624817371368408, "global_step": 598328, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.937753677368164, "global_step": 598329, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0072755813598633, "global_step": 598330, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0524508953094482, "global_step": 598331, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.026890516281128, "global_step": 598332, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9986470937728882, "global_step": 598333, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9786911010742188, "global_step": 598334, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0154106616973877, "global_step": 598335, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.079442262649536, "global_step": 598336, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0300354957580566, "global_step": 598337, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9637471437454224, "global_step": 598338, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9626179933547974, "global_step": 598339, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9822579622268677, "global_step": 598340, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.086946964263916, "global_step": 598341, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9670305252075195, "global_step": 598342, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.008911371231079, "global_step": 598343, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0029380321502686, "global_step": 598344, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9566826820373535, "global_step": 598345, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0087902545928955, "global_step": 598346, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.036830425262451, "global_step": 598347, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0486953258514404, "global_step": 598348, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.065443992614746, "global_step": 598349, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.048776149749756, "global_step": 598350, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.023881673812866, "global_step": 598351, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0496389865875244, "global_step": 598352, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9221656322479248, "global_step": 598353, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9880387783050537, "global_step": 598354, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.041093587875366, "global_step": 598355, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9646004438400269, "global_step": 598356, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0089523792266846, "global_step": 598357, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9138377904891968, "global_step": 598358, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.974843978881836, "global_step": 598359, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9840294122695923, "global_step": 598360, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9881459474563599, "global_step": 598361, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0325396060943604, "global_step": 598362, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9844021797180176, "global_step": 598363, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.058095693588257, "global_step": 598364, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.01094388961792, "global_step": 598365, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.028120279312134, "global_step": 598366, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0160789489746094, "global_step": 598367, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0367026329040527, "global_step": 598368, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9712656736373901, "global_step": 598369, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.947784423828125, "global_step": 598370, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0020811557769775, "global_step": 598371, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9433585405349731, "global_step": 598372, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0005910396575928, "global_step": 598373, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9787278175354004, "global_step": 598374, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0353057384490967, "global_step": 598375, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.081016778945923, "global_step": 598376, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9224305152893066, "global_step": 598377, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0934231281280518, "global_step": 598378, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0343291759490967, "global_step": 598379, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9695565700531006, "global_step": 598380, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.022139072418213, "global_step": 598381, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9696615934371948, "global_step": 598382, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0035862922668457, "global_step": 598383, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9790130853652954, "global_step": 598384, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.00225830078125, "global_step": 598385, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9552558660507202, "global_step": 598386, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9619656801223755, "global_step": 598387, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9985233545303345, "global_step": 598388, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0259311199188232, "global_step": 598389, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9713116884231567, "global_step": 598390, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9911701679229736, "global_step": 598391, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.020975112915039, "global_step": 598392, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0739998817443848, "global_step": 598393, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9938956499099731, "global_step": 598394, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9944299459457397, "global_step": 598395, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.974994421005249, "global_step": 598396, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.1102137565612793, "global_step": 598397, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9640806913375854, "global_step": 598398, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9863312244415283, "global_step": 598399, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9934015274047852, "global_step": 598400, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0114054679870605, "global_step": 598401, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.936151385307312, "global_step": 598402, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9767242670059204, "global_step": 598403, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0300469398498535, "global_step": 598404, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.122014045715332, "global_step": 598405, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0573909282684326, "global_step": 598406, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.006603956222534, "global_step": 598407, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.958601951599121, "global_step": 598408, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.10992431640625, "global_step": 598409, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0339834690093994, "global_step": 598410, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.928236484527588, "global_step": 598411, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.116863489151001, "global_step": 598412, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.089016914367676, "global_step": 598413, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.05098295211792, "global_step": 598414, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9987890720367432, "global_step": 598415, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.078545331954956, "global_step": 598416, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.945038914680481, "global_step": 598417, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9919103384017944, "global_step": 598418, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.010220527648926, "global_step": 598419, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9516093730926514, "global_step": 598420, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.06048846244812, "global_step": 598421, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.095782995223999, "global_step": 598422, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.984763503074646, "global_step": 598423, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.004643440246582, "global_step": 598424, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9008437395095825, "global_step": 598425, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0029330253601074, "global_step": 598426, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0162620544433594, "global_step": 598427, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.035079002380371, "global_step": 598428, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9243013858795166, "global_step": 598429, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0100314617156982, "global_step": 598430, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0076444149017334, "global_step": 598431, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0243868827819824, "global_step": 598432, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0410478115081787, "global_step": 598433, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9979033470153809, "global_step": 598434, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9902074337005615, "global_step": 598435, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9610142707824707, "global_step": 598436, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9134904146194458, "global_step": 598437, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0812418460845947, "global_step": 598438, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.095576763153076, "global_step": 598439, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0352983474731445, "global_step": 598440, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9995611906051636, "global_step": 598441, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.1313302516937256, "global_step": 598442, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0057616233825684, "global_step": 598443, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0158472061157227, "global_step": 598444, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0759427547454834, "global_step": 598445, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0246429443359375, "global_step": 598446, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.047800302505493, "global_step": 598447, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9900001287460327, "global_step": 598448, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.997440218925476, "global_step": 598449, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.077942371368408, "global_step": 598450, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9510209560394287, "global_step": 598451, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.012423276901245, "global_step": 598452, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.004808187484741, "global_step": 598453, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.940656304359436, "global_step": 598454, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.011085033416748, "global_step": 598455, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9478956460952759, "global_step": 598456, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0661096572875977, "global_step": 598457, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.047910213470459, "global_step": 598458, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0122976303100586, "global_step": 598459, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0617003440856934, "global_step": 598460, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0154824256896973, "global_step": 598461, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9581917524337769, "global_step": 598462, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.126429319381714, "global_step": 598463, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9868170022964478, "global_step": 598464, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0886361598968506, "global_step": 598465, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.005117893218994, "global_step": 598466, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0110251903533936, "global_step": 598467, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9973499774932861, "global_step": 598468, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0146820545196533, "global_step": 598469, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9791101217269897, "global_step": 598470, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0042266845703125, "global_step": 598471, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.085380792617798, "global_step": 598472, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0487279891967773, "global_step": 598473, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0209429264068604, "global_step": 598474, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.056553840637207, "global_step": 598475, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9949841499328613, "global_step": 598476, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0125043392181396, "global_step": 598477, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9901783466339111, "global_step": 598478, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0742692947387695, "global_step": 598479, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.009399652481079, "global_step": 598480, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9905270338058472, "global_step": 598481, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9800225496292114, "global_step": 598482, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0204715728759766, "global_step": 598483, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0663983821868896, "global_step": 598484, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0468251705169678, "global_step": 598485, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0926403999328613, "global_step": 598486, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9673551321029663, "global_step": 598487, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0440402030944824, "global_step": 598488, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.006796360015869, "global_step": 598489, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9528530836105347, "global_step": 598490, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9639174938201904, "global_step": 598491, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.065971851348877, "global_step": 598492, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.965409517288208, "global_step": 598493, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9627134799957275, "global_step": 598494, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0898704528808594, "global_step": 598495, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9684504270553589, "global_step": 598496, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0422675609588623, "global_step": 598497, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9840805530548096, "global_step": 598498, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.054985761642456, "global_step": 598499, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0147602558135986, "global_step": 598500, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.099787473678589, "global_step": 598501, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.147681474685669, "global_step": 598502, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.952345371246338, "global_step": 598503, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.038079261779785, "global_step": 598504, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9999829530715942, "global_step": 598505, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.048914909362793, "global_step": 598506, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9931695461273193, "global_step": 598507, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0312206745147705, "global_step": 598508, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.079899549484253, "global_step": 598509, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.003098487854004, "global_step": 598510, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9203256368637085, "global_step": 598511, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.035543441772461, "global_step": 598512, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.052936315536499, "global_step": 598513, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0469753742218018, "global_step": 598514, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0433411598205566, "global_step": 598515, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.92397141456604, "global_step": 598516, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.937513828277588, "global_step": 598517, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0578482151031494, "global_step": 598518, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9322575330734253, "global_step": 598519, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.926337718963623, "global_step": 598520, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0113372802734375, "global_step": 598521, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.004124164581299, "global_step": 598522, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.111560106277466, "global_step": 598523, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.001915454864502, "global_step": 598524, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.948459506034851, "global_step": 598525, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0770320892333984, "global_step": 598526, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0530192852020264, "global_step": 598527, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9566521644592285, "global_step": 598528, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9481024742126465, "global_step": 598529, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.03610897064209, "global_step": 598530, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9848201274871826, "global_step": 598531, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9659345149993896, "global_step": 598532, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9715412855148315, "global_step": 598533, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9440443515777588, "global_step": 598534, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.043067693710327, "global_step": 598535, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9382351636886597, "global_step": 598536, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.1172022819519043, "global_step": 598537, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.022481918334961, "global_step": 598538, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0235869884490967, "global_step": 598539, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0743541717529297, "global_step": 598540, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.013258934020996, "global_step": 598541, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.034841537475586, "global_step": 598542, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.020937442779541, "global_step": 598543, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0505311489105225, "global_step": 598544, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.034322500228882, "global_step": 598545, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9399429559707642, "global_step": 598546, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.062389373779297, "global_step": 598547, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9859342575073242, "global_step": 598548, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9858779907226562, "global_step": 598549, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0727267265319824, "global_step": 598550, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0190088748931885, "global_step": 598551, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9941766262054443, "global_step": 598552, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0283286571502686, "global_step": 598553, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0234780311584473, "global_step": 598554, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9847047328948975, "global_step": 598555, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.990319013595581, "global_step": 598556, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9885189533233643, "global_step": 598557, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.042850971221924, "global_step": 598558, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.947784185409546, "global_step": 598559, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.037799835205078, "global_step": 598560, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0246238708496094, "global_step": 598561, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0526535511016846, "global_step": 598562, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9928754568099976, "global_step": 598563, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9889049530029297, "global_step": 598564, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.011657238006592, "global_step": 598565, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.061020612716675, "global_step": 598566, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9538424015045166, "global_step": 598567, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0334339141845703, "global_step": 598568, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0098624229431152, "global_step": 598569, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9527111053466797, "global_step": 598570, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9990495443344116, "global_step": 598571, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.94020676612854, "global_step": 598572, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0026512145996094, "global_step": 598573, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0598227977752686, "global_step": 598574, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.027276039123535, "global_step": 598575, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0436861515045166, "global_step": 598576, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9956170320510864, "global_step": 598577, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9469897747039795, "global_step": 598578, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0615506172180176, "global_step": 598579, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0668492317199707, "global_step": 598580, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0399372577667236, "global_step": 598581, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0214951038360596, "global_step": 598582, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.022768974304199, "global_step": 598583, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9910638332366943, "global_step": 598584, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.065765619277954, "global_step": 598585, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9442455768585205, "global_step": 598586, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9949696063995361, "global_step": 598587, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0417089462280273, "global_step": 598588, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.043217658996582, "global_step": 598589, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.049570083618164, "global_step": 598590, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.990466594696045, "global_step": 598591, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.965675950050354, "global_step": 598592, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.046379804611206, "global_step": 598593, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0495855808258057, "global_step": 598594, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.939723014831543, "global_step": 598595, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9713743925094604, "global_step": 598596, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.028663396835327, "global_step": 598597, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9709523916244507, "global_step": 598598, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.026359796524048, "global_step": 598599, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.037774085998535, "global_step": 598600, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9577962160110474, "global_step": 598601, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.011387825012207, "global_step": 598602, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0708160400390625, "global_step": 598603, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.978395700454712, "global_step": 598604, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9743493795394897, "global_step": 598605, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9995627403259277, "global_step": 598606, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.037231206893921, "global_step": 598607, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9831594228744507, "global_step": 598608, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.944826364517212, "global_step": 598609, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0012154579162598, "global_step": 598610, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9897371530532837, "global_step": 598611, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9852221012115479, "global_step": 598612, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9875118732452393, "global_step": 598613, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.957458734512329, "global_step": 598614, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.013129711151123, "global_step": 598615, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.077045440673828, "global_step": 598616, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0362048149108887, "global_step": 598617, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0933258533477783, "global_step": 598618, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9555925130844116, "global_step": 598619, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.1543033123016357, "global_step": 598620, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.010849714279175, "global_step": 598621, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9561917781829834, "global_step": 598622, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.007859468460083, "global_step": 598623, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9762877225875854, "global_step": 598624, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.004037380218506, "global_step": 598625, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.1088874340057373, "global_step": 598626, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.006924629211426, "global_step": 598627, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0653231143951416, "global_step": 598628, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9206091165542603, "global_step": 598629, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0939221382141113, "global_step": 598630, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0371456146240234, "global_step": 598631, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9934890270233154, "global_step": 598632, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0975072383880615, "global_step": 598633, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9806650876998901, "global_step": 598634, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.011556386947632, "global_step": 598635, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.05312442779541, "global_step": 598636, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0628821849823, "global_step": 598637, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.996802806854248, "global_step": 598638, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.988950252532959, "global_step": 598639, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0229086875915527, "global_step": 598640, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0191543102264404, "global_step": 598641, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.015594482421875, "global_step": 598642, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0285592079162598, "global_step": 598643, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.984151005744934, "global_step": 598644, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0273940563201904, "global_step": 598645, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.095041513442993, "global_step": 598646, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9559447765350342, "global_step": 598647, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0519611835479736, "global_step": 598648, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.917973279953003, "global_step": 598649, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0709452629089355, "global_step": 598650, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.10459041595459, "global_step": 598651, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.966313362121582, "global_step": 598652, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.066277265548706, "global_step": 598653, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0827863216400146, "global_step": 598654, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0186901092529297, "global_step": 598655, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9614522457122803, "global_step": 598656, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0217208862304688, "global_step": 598657, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.037398338317871, "global_step": 598658, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.040226936340332, "global_step": 598659, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.141672134399414, "global_step": 598660, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0295767784118652, "global_step": 598661, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0644586086273193, "global_step": 598662, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0355441570281982, "global_step": 598663, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.039628505706787, "global_step": 598664, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.012669324874878, "global_step": 598665, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.001056671142578, "global_step": 598666, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.043191432952881, "global_step": 598667, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9658952951431274, "global_step": 598668, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.089508295059204, "global_step": 598669, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0479204654693604, "global_step": 598670, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0027847290039062, "global_step": 598671, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.933646321296692, "global_step": 598672, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9713366031646729, "global_step": 598673, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.950347900390625, "global_step": 598674, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.985336422920227, "global_step": 598675, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9866515398025513, "global_step": 598676, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.080979108810425, "global_step": 598677, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.016789674758911, "global_step": 598678, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9361882209777832, "global_step": 598679, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0328497886657715, "global_step": 598680, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.032135248184204, "global_step": 598681, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9770159721374512, "global_step": 598682, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0895533561706543, "global_step": 598683, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0404016971588135, "global_step": 598684, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0203404426574707, "global_step": 598685, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0362682342529297, "global_step": 598686, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.031644821166992, "global_step": 598687, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.932472586631775, "global_step": 598688, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.97075617313385, "global_step": 598689, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.022850275039673, "global_step": 598690, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0347800254821777, "global_step": 598691, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0391898155212402, "global_step": 598692, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0619781017303467, "global_step": 598693, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0143511295318604, "global_step": 598694, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0140373706817627, "global_step": 598695, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9934394359588623, "global_step": 598696, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0463438034057617, "global_step": 598697, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.078123092651367, "global_step": 598698, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0196354389190674, "global_step": 598699, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.02242374420166, "global_step": 598700, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9960741996765137, "global_step": 598701, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9859615564346313, "global_step": 598702, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0553014278411865, "global_step": 598703, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9533052444458008, "global_step": 598704, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0283381938934326, "global_step": 598705, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9015483856201172, "global_step": 598706, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0578880310058594, "global_step": 598707, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.034189462661743, "global_step": 598708, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.000758171081543, "global_step": 598709, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9808869361877441, "global_step": 598710, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.05124831199646, "global_step": 598711, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.976590633392334, "global_step": 598712, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.1398839950561523, "global_step": 598713, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9971308708190918, "global_step": 598714, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9228177070617676, "global_step": 598715, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9894896745681763, "global_step": 598716, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.006155252456665, "global_step": 598717, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9918066263198853, "global_step": 598718, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9779810905456543, "global_step": 598719, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9972436428070068, "global_step": 598720, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0722875595092773, "global_step": 598721, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0507631301879883, "global_step": 598722, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0458931922912598, "global_step": 598723, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.026373863220215, "global_step": 598724, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0432369709014893, "global_step": 598725, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.006843328475952, "global_step": 598726, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9023829698562622, "global_step": 598727, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.01874041557312, "global_step": 598728, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0283470153808594, "global_step": 598729, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9911580085754395, "global_step": 598730, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.069413185119629, "global_step": 598731, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9963611364364624, "global_step": 598732, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.045346260070801, "global_step": 598733, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.058634042739868, "global_step": 598734, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.983587384223938, "global_step": 598735, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.117152214050293, "global_step": 598736, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.054269552230835, "global_step": 598737, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0458579063415527, "global_step": 598738, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.053690195083618, "global_step": 598739, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9972962141036987, "global_step": 598740, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9991670846939087, "global_step": 598741, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0813448429107666, "global_step": 598742, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9602327346801758, "global_step": 598743, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.041449546813965, "global_step": 598744, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0009994506835938, "global_step": 598745, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.008404493331909, "global_step": 598746, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.97475266456604, "global_step": 598747, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9618401527404785, "global_step": 598748, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9382457733154297, "global_step": 598749, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0060501098632812, "global_step": 598750, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9382177591323853, "global_step": 598751, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0136826038360596, "global_step": 598752, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0161304473876953, "global_step": 598753, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.1244935989379883, "global_step": 598754, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0618791580200195, "global_step": 598755, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9754341840744019, "global_step": 598756, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9571764469146729, "global_step": 598757, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.961681842803955, "global_step": 598758, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.061109781265259, "global_step": 598759, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.1107122898101807, "global_step": 598760, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9703935384750366, "global_step": 598761, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9873770475387573, "global_step": 598762, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0361392498016357, "global_step": 598763, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9966230392456055, "global_step": 598764, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.026902198791504, "global_step": 598765, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0321691036224365, "global_step": 598766, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9847040176391602, "global_step": 598767, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9949721097946167, "global_step": 598768, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.093583583831787, "global_step": 598769, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.007805824279785, "global_step": 598770, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0800695419311523, "global_step": 598771, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.01682448387146, "global_step": 598772, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9656593799591064, "global_step": 598773, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9516631364822388, "global_step": 598774, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.957101821899414, "global_step": 598775, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0150320529937744, "global_step": 598776, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9973127841949463, "global_step": 598777, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0158843994140625, "global_step": 598778, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.001826286315918, "global_step": 598779, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0343565940856934, "global_step": 598780, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9737906455993652, "global_step": 598781, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.037013530731201, "global_step": 598782, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.034461498260498, "global_step": 598783, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9856606721878052, "global_step": 598784, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0173003673553467, "global_step": 598785, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9855057001113892, "global_step": 598786, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.044193983078003, "global_step": 598787, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.002262592315674, "global_step": 598788, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0753753185272217, "global_step": 598789, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0631892681121826, "global_step": 598790, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9994219541549683, "global_step": 598791, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9804712533950806, "global_step": 598792, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.105294942855835, "global_step": 598793, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0380051136016846, "global_step": 598794, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9809666872024536, "global_step": 598795, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0290331840515137, "global_step": 598796, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0637454986572266, "global_step": 598797, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.953208327293396, "global_step": 598798, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.089953899383545, "global_step": 598799, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.000882387161255, "global_step": 598800, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9844374656677246, "global_step": 598801, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.01983904838562, "global_step": 598802, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0518627166748047, "global_step": 598803, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0797903537750244, "global_step": 598804, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.069236993789673, "global_step": 598805, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.025928497314453, "global_step": 598806, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.071946144104004, "global_step": 598807, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0292980670928955, "global_step": 598808, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0190269947052, "global_step": 598809, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9865927696228027, "global_step": 598810, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.028529644012451, "global_step": 598811, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.002453327178955, "global_step": 598812, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0122385025024414, "global_step": 598813, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.983363389968872, "global_step": 598814, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9776357412338257, "global_step": 598815, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9721304178237915, "global_step": 598816, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9781569242477417, "global_step": 598817, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.010133743286133, "global_step": 598818, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9527487754821777, "global_step": 598819, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.054109811782837, "global_step": 598820, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.969484806060791, "global_step": 598821, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0390465259552, "global_step": 598822, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.1183555126190186, "global_step": 598823, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9912683963775635, "global_step": 598824, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.116445779800415, "global_step": 598825, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9707027673721313, "global_step": 598826, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.005885124206543, "global_step": 598827, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.022254467010498, "global_step": 598828, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.036055088043213, "global_step": 598829, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0213735103607178, "global_step": 598830, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9680628776550293, "global_step": 598831, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9896509647369385, "global_step": 598832, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.1315927505493164, "global_step": 598833, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0381863117218018, "global_step": 598834, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0560407638549805, "global_step": 598835, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.046593189239502, "global_step": 598836, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0491480827331543, "global_step": 598837, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.975391149520874, "global_step": 598838, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.016063690185547, "global_step": 598839, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9782071113586426, "global_step": 598840, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0357346534729004, "global_step": 598841, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.020611047744751, "global_step": 598842, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9539153575897217, "global_step": 598843, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.983919620513916, "global_step": 598844, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9669888019561768, "global_step": 598845, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.046090841293335, "global_step": 598846, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9888136386871338, "global_step": 598847, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0117545127868652, "global_step": 598848, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0355045795440674, "global_step": 598849, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9400469064712524, "global_step": 598850, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0075197219848633, "global_step": 598851, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.05025577545166, "global_step": 598852, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9946200847625732, "global_step": 598853, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9616401195526123, "global_step": 598854, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.1014256477355957, "global_step": 598855, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9904955625534058, "global_step": 598856, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.075047731399536, "global_step": 598857, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0024218559265137, "global_step": 598858, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.011507511138916, "global_step": 598859, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.051152467727661, "global_step": 598860, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9110499620437622, "global_step": 598861, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.042532444000244, "global_step": 598862, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9996463060379028, "global_step": 598863, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9375423192977905, "global_step": 598864, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.086317777633667, "global_step": 598865, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.004566192626953, "global_step": 598866, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0612711906433105, "global_step": 598867, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.074202299118042, "global_step": 598868, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9854059219360352, "global_step": 598869, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0006017684936523, "global_step": 598870, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0721170902252197, "global_step": 598871, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0495970249176025, "global_step": 598872, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9619861841201782, "global_step": 598873, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0887207984924316, "global_step": 598874, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.013333320617676, "global_step": 598875, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.942348837852478, "global_step": 598876, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9222028255462646, "global_step": 598877, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0113980770111084, "global_step": 598878, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9772005081176758, "global_step": 598879, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0890259742736816, "global_step": 598880, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0853450298309326, "global_step": 598881, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9743893146514893, "global_step": 598882, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9965258836746216, "global_step": 598883, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.006359338760376, "global_step": 598884, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0765445232391357, "global_step": 598885, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9964295625686646, "global_step": 598886, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0355517864227295, "global_step": 598887, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.057173013687134, "global_step": 598888, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0309712886810303, "global_step": 598889, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.018322229385376, "global_step": 598890, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0318870544433594, "global_step": 598891, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.070863723754883, "global_step": 598892, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.022031784057617, "global_step": 598893, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.976872205734253, "global_step": 598894, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0145010948181152, "global_step": 598895, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0353715419769287, "global_step": 598896, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9432902336120605, "global_step": 598897, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0781166553497314, "global_step": 598898, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9712474346160889, "global_step": 598899, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.057110071182251, "global_step": 598900, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.014742851257324, "global_step": 598901, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9767329692840576, "global_step": 598902, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0502467155456543, "global_step": 598903, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9896801710128784, "global_step": 598904, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0639028549194336, "global_step": 598905, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9819221496582031, "global_step": 598906, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0285983085632324, "global_step": 598907, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0669050216674805, "global_step": 598908, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0110814571380615, "global_step": 598909, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0577869415283203, "global_step": 598910, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0141336917877197, "global_step": 598911, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0436229705810547, "global_step": 598912, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0571513175964355, "global_step": 598913, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.003070592880249, "global_step": 598914, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.961870789527893, "global_step": 598915, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9589977264404297, "global_step": 598916, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.000267267227173, "global_step": 598917, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9670765399932861, "global_step": 598918, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.071993350982666, "global_step": 598919, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0119853019714355, "global_step": 598920, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.113389015197754, "global_step": 598921, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0560362339019775, "global_step": 598922, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.980762004852295, "global_step": 598923, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.971526861190796, "global_step": 598924, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.038231134414673, "global_step": 598925, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0755186080932617, "global_step": 598926, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.002666711807251, "global_step": 598927, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9671474695205688, "global_step": 598928, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9410699605941772, "global_step": 598929, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9452210664749146, "global_step": 598930, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.03985857963562, "global_step": 598931, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.043250799179077, "global_step": 598932, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9871108531951904, "global_step": 598933, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9611941576004028, "global_step": 598934, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.027832269668579, "global_step": 598935, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.053601026535034, "global_step": 598936, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0913593769073486, "global_step": 598937, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.942209005355835, "global_step": 598938, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.001465082168579, "global_step": 598939, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0193185806274414, "global_step": 598940, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.081728935241699, "global_step": 598941, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0349783897399902, "global_step": 598942, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0498619079589844, "global_step": 598943, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.006776809692383, "global_step": 598944, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0342679023742676, "global_step": 598945, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9970229864120483, "global_step": 598946, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.065164804458618, "global_step": 598947, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9104225635528564, "global_step": 598948, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9697325229644775, "global_step": 598949, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0155978202819824, "global_step": 598950, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0471322536468506, "global_step": 598951, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.065882921218872, "global_step": 598952, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.01491379737854, "global_step": 598953, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0223276615142822, "global_step": 598954, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0815305709838867, "global_step": 598955, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9853205680847168, "global_step": 598956, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.021477222442627, "global_step": 598957, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9650607109069824, "global_step": 598958, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0062203407287598, "global_step": 598959, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9549652338027954, "global_step": 598960, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0549709796905518, "global_step": 598961, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.016845464706421, "global_step": 598962, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0512030124664307, "global_step": 598963, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9717061519622803, "global_step": 598964, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.038980007171631, "global_step": 598965, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9618711471557617, "global_step": 598966, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0460987091064453, "global_step": 598967, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0176427364349365, "global_step": 598968, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9717895984649658, "global_step": 598969, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.012564182281494, "global_step": 598970, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0165812969207764, "global_step": 598971, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0240530967712402, "global_step": 598972, "epoch": 967, "lr": 5e-05}
{"train_loss": 1.9815889596939087, "global_step": 598973, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0117125511169434, "global_step": 598974, "epoch": 967, "lr": 5e-05}
{"train_loss": 2.0379011631011963, "global_step": 598975, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9551407098770142, "global_step": 598976, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9975682497024536, "global_step": 598977, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.00307035446167, "global_step": 598978, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.981616735458374, "global_step": 598979, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0672099590301514, "global_step": 598980, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9075201749801636, "global_step": 598981, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9353017807006836, "global_step": 598982, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9622881412506104, "global_step": 598983, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.053241014480591, "global_step": 598984, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.995944619178772, "global_step": 598985, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9955592155456543, "global_step": 598986, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9657665491104126, "global_step": 598987, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9670583009719849, "global_step": 598988, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9729621410369873, "global_step": 598989, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9561266899108887, "global_step": 598990, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0085959434509277, "global_step": 598991, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9111346006393433, "global_step": 598992, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9998968839645386, "global_step": 598993, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.029219150543213, "global_step": 598994, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9899041652679443, "global_step": 598995, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9923110008239746, "global_step": 598996, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9751782417297363, "global_step": 598997, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.039564847946167, "global_step": 598998, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0807301998138428, "global_step": 598999, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.005305767059326, "global_step": 599000, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9681659936904907, "global_step": 599001, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9624829292297363, "global_step": 599002, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0165493488311768, "global_step": 599003, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.94675612449646, "global_step": 599004, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9553123712539673, "global_step": 599005, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.992986798286438, "global_step": 599006, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9961639642715454, "global_step": 599007, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.8963669538497925, "global_step": 599008, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9697946310043335, "global_step": 599009, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.014474868774414, "global_step": 599010, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.964328408241272, "global_step": 599011, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9836145639419556, "global_step": 599012, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.987168550491333, "global_step": 599013, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.024502992630005, "global_step": 599014, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.964004397392273, "global_step": 599015, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9795262813568115, "global_step": 599016, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9794600009918213, "global_step": 599017, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9941825866699219, "global_step": 599018, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9752137660980225, "global_step": 599019, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9902386665344238, "global_step": 599020, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0711491107940674, "global_step": 599021, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0146358013153076, "global_step": 599022, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0314316749572754, "global_step": 599023, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1160786151885986, "global_step": 599024, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9984709024429321, "global_step": 599025, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9895333051681519, "global_step": 599026, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0793564319610596, "global_step": 599027, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0474936962127686, "global_step": 599028, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.991414189338684, "global_step": 599029, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9334856271743774, "global_step": 599030, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0060646533966064, "global_step": 599031, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.063322067260742, "global_step": 599032, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.927240014076233, "global_step": 599033, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9933528900146484, "global_step": 599034, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.032588005065918, "global_step": 599035, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.954196572303772, "global_step": 599036, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0244035720825195, "global_step": 599037, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9614726305007935, "global_step": 599038, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9611672163009644, "global_step": 599039, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9911144971847534, "global_step": 599040, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9710274934768677, "global_step": 599041, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.951676845550537, "global_step": 599042, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.05456280708313, "global_step": 599043, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0106873512268066, "global_step": 599044, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.004199981689453, "global_step": 599045, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.987389087677002, "global_step": 599046, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9992343187332153, "global_step": 599047, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9483532905578613, "global_step": 599048, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9034565687179565, "global_step": 599049, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.925515055656433, "global_step": 599050, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.966727614402771, "global_step": 599051, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9133380651474, "global_step": 599052, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1012661457061768, "global_step": 599053, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0075817108154297, "global_step": 599054, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.947023630142212, "global_step": 599055, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0320851802825928, "global_step": 599056, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9651905298233032, "global_step": 599057, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9214506149291992, "global_step": 599058, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9829574823379517, "global_step": 599059, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1028666496276855, "global_step": 599060, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.045154571533203, "global_step": 599061, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.056145668029785, "global_step": 599062, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9937697649002075, "global_step": 599063, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0368828773498535, "global_step": 599064, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.057950258255005, "global_step": 599065, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.933289885520935, "global_step": 599066, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.067767858505249, "global_step": 599067, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.009721040725708, "global_step": 599068, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.044610023498535, "global_step": 599069, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9788633584976196, "global_step": 599070, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0089406967163086, "global_step": 599071, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0172996520996094, "global_step": 599072, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0226030349731445, "global_step": 599073, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9941940307617188, "global_step": 599074, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0774242877960205, "global_step": 599075, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0028419494628906, "global_step": 599076, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9671350717544556, "global_step": 599077, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0553317070007324, "global_step": 599078, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0250766277313232, "global_step": 599079, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9847441911697388, "global_step": 599080, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.995376467704773, "global_step": 599081, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0157630443573, "global_step": 599082, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0068371295928955, "global_step": 599083, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.041105270385742, "global_step": 599084, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0597052574157715, "global_step": 599085, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.044182300567627, "global_step": 599086, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9433326721191406, "global_step": 599087, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9406623840332031, "global_step": 599088, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9273618459701538, "global_step": 599089, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9489363431930542, "global_step": 599090, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0108394622802734, "global_step": 599091, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0384137630462646, "global_step": 599092, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.026374340057373, "global_step": 599093, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9466354846954346, "global_step": 599094, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0159504413604736, "global_step": 599095, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9762026071548462, "global_step": 599096, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.022982597351074, "global_step": 599097, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.028201103210449, "global_step": 599098, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.017709493637085, "global_step": 599099, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9649282693862915, "global_step": 599100, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9682013988494873, "global_step": 599101, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0194079875946045, "global_step": 599102, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.961646318435669, "global_step": 599103, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9952822923660278, "global_step": 599104, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9657784700393677, "global_step": 599105, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0029971599578857, "global_step": 599106, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0430307388305664, "global_step": 599107, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9875255823135376, "global_step": 599108, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9950522184371948, "global_step": 599109, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0105245113372803, "global_step": 599110, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.082404375076294, "global_step": 599111, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9934712648391724, "global_step": 599112, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9991534948349, "global_step": 599113, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9279067516326904, "global_step": 599114, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.987550139427185, "global_step": 599115, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9381086826324463, "global_step": 599116, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9847395420074463, "global_step": 599117, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.052311420440674, "global_step": 599118, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0121936798095703, "global_step": 599119, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0116772651672363, "global_step": 599120, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9337784051895142, "global_step": 599121, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.075352430343628, "global_step": 599122, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9842331409454346, "global_step": 599123, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9917429685592651, "global_step": 599124, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0198802947998047, "global_step": 599125, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.030731439590454, "global_step": 599126, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9494869709014893, "global_step": 599127, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9843683242797852, "global_step": 599128, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9000605344772339, "global_step": 599129, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0485215187072754, "global_step": 599130, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0221707820892334, "global_step": 599131, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9938551187515259, "global_step": 599132, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9998759031295776, "global_step": 599133, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9975535869598389, "global_step": 599134, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9196109771728516, "global_step": 599135, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0064291954040527, "global_step": 599136, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0312740802764893, "global_step": 599137, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9998888969421387, "global_step": 599138, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0694973468780518, "global_step": 599139, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0508370399475098, "global_step": 599140, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.031642198562622, "global_step": 599141, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.029881000518799, "global_step": 599142, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9690183401107788, "global_step": 599143, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.011040687561035, "global_step": 599144, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.068117380142212, "global_step": 599145, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.060180187225342, "global_step": 599146, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9306526184082031, "global_step": 599147, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9819504022598267, "global_step": 599148, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.027381181716919, "global_step": 599149, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0420570373535156, "global_step": 599150, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.981247901916504, "global_step": 599151, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.012782096862793, "global_step": 599152, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0054314136505127, "global_step": 599153, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0607457160949707, "global_step": 599154, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9918646812438965, "global_step": 599155, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.995935082435608, "global_step": 599156, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.024359703063965, "global_step": 599157, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9693188667297363, "global_step": 599158, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.034280776977539, "global_step": 599159, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9790830612182617, "global_step": 599160, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0228607654571533, "global_step": 599161, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9951021671295166, "global_step": 599162, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9946855306625366, "global_step": 599163, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9481611251831055, "global_step": 599164, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.008007526397705, "global_step": 599165, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.01680850982666, "global_step": 599166, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0886006355285645, "global_step": 599167, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9959731101989746, "global_step": 599168, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9501771926879883, "global_step": 599169, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9927382469177246, "global_step": 599170, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0443806648254395, "global_step": 599171, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.13321590423584, "global_step": 599172, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.965243935585022, "global_step": 599173, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.013890504837036, "global_step": 599174, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9948674440383911, "global_step": 599175, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.029722213745117, "global_step": 599176, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0378646850585938, "global_step": 599177, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9880377054214478, "global_step": 599178, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9587194919586182, "global_step": 599179, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9280750751495361, "global_step": 599180, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0293285846710205, "global_step": 599181, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.072261095046997, "global_step": 599182, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.017810583114624, "global_step": 599183, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9321722984313965, "global_step": 599184, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0227808952331543, "global_step": 599185, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9241704940795898, "global_step": 599186, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.09143328666687, "global_step": 599187, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9788812398910522, "global_step": 599188, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.008615732192993, "global_step": 599189, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9783334732055664, "global_step": 599190, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.065849542617798, "global_step": 599191, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0573973655700684, "global_step": 599192, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.084934949874878, "global_step": 599193, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0001277923583984, "global_step": 599194, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.022547960281372, "global_step": 599195, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9620404243469238, "global_step": 599196, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9323481321334839, "global_step": 599197, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0075833797454834, "global_step": 599198, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.972546100616455, "global_step": 599199, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0123376846313477, "global_step": 599200, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9900635480880737, "global_step": 599201, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.009704351425171, "global_step": 599202, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.986492395401001, "global_step": 599203, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0321900844573975, "global_step": 599204, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0166614055633545, "global_step": 599205, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.019019365310669, "global_step": 599206, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9760266542434692, "global_step": 599207, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0337331295013428, "global_step": 599208, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0239107608795166, "global_step": 599209, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0260307788848877, "global_step": 599210, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9885034561157227, "global_step": 599211, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.032961845397949, "global_step": 599212, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.04429030418396, "global_step": 599213, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9590977430343628, "global_step": 599214, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.985001564025879, "global_step": 599215, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9696121215820312, "global_step": 599216, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0423431396484375, "global_step": 599217, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0621604919433594, "global_step": 599218, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9038854837417603, "global_step": 599219, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.00246524810791, "global_step": 599220, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.07991623878479, "global_step": 599221, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0051639080047607, "global_step": 599222, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0261964797973633, "global_step": 599223, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9867929220199585, "global_step": 599224, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9581892490386963, "global_step": 599225, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.06095027923584, "global_step": 599226, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1320457458496094, "global_step": 599227, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.013277530670166, "global_step": 599228, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.967326283454895, "global_step": 599229, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.106792449951172, "global_step": 599230, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.048309326171875, "global_step": 599231, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9548261165618896, "global_step": 599232, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.985253930091858, "global_step": 599233, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9257735013961792, "global_step": 599234, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9743001461029053, "global_step": 599235, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.071549892425537, "global_step": 599236, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9430148601531982, "global_step": 599237, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9563679695129395, "global_step": 599238, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9714229106903076, "global_step": 599239, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.952871322631836, "global_step": 599240, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0523242950439453, "global_step": 599241, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0908632278442383, "global_step": 599242, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0902745723724365, "global_step": 599243, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9475488662719727, "global_step": 599244, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.958575963973999, "global_step": 599245, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.986814022064209, "global_step": 599246, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.061260461807251, "global_step": 599247, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0111143589019775, "global_step": 599248, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9850877523422241, "global_step": 599249, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0270142555236816, "global_step": 599250, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9743688106536865, "global_step": 599251, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9321165084838867, "global_step": 599252, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0318052768707275, "global_step": 599253, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.960665225982666, "global_step": 599254, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.998842477798462, "global_step": 599255, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0569868087768555, "global_step": 599256, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9757826328277588, "global_step": 599257, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0465645790100098, "global_step": 599258, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9846562147140503, "global_step": 599259, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.07041597366333, "global_step": 599260, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.068652391433716, "global_step": 599261, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0465283393859863, "global_step": 599262, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.013766050338745, "global_step": 599263, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.040515661239624, "global_step": 599264, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.000929117202759, "global_step": 599265, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9708325862884521, "global_step": 599266, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9775974750518799, "global_step": 599267, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.8739972114562988, "global_step": 599268, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9748338460922241, "global_step": 599269, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9787832498550415, "global_step": 599270, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9895869493484497, "global_step": 599271, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.055712938308716, "global_step": 599272, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9974430799484253, "global_step": 599273, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.024364471435547, "global_step": 599274, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9996817111968994, "global_step": 599275, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.976792573928833, "global_step": 599276, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9517762660980225, "global_step": 599277, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0453720092773438, "global_step": 599278, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9679582118988037, "global_step": 599279, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.06667160987854, "global_step": 599280, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.052427053451538, "global_step": 599281, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.081620454788208, "global_step": 599282, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0688440799713135, "global_step": 599283, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.004300355911255, "global_step": 599284, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0072021484375, "global_step": 599285, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.102919578552246, "global_step": 599286, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0412814617156982, "global_step": 599287, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.970558762550354, "global_step": 599288, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9396700859069824, "global_step": 599289, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0282535552978516, "global_step": 599290, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1470305919647217, "global_step": 599291, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9816293716430664, "global_step": 599292, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9829246997833252, "global_step": 599293, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.018218517303467, "global_step": 599294, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9802649021148682, "global_step": 599295, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.076509952545166, "global_step": 599296, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9422365427017212, "global_step": 599297, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.047495126724243, "global_step": 599298, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0658962726593018, "global_step": 599299, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.984884262084961, "global_step": 599300, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0157976150512695, "global_step": 599301, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0324740409851074, "global_step": 599302, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9845930337905884, "global_step": 599303, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0415775775909424, "global_step": 599304, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1032166481018066, "global_step": 599305, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0186948776245117, "global_step": 599306, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9550126791000366, "global_step": 599307, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9243032932281494, "global_step": 599308, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0356810092926025, "global_step": 599309, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.082458019256592, "global_step": 599310, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9452714920043945, "global_step": 599311, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0596060752868652, "global_step": 599312, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.021280288696289, "global_step": 599313, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9875770807266235, "global_step": 599314, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.038816213607788, "global_step": 599315, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.957359790802002, "global_step": 599316, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0139882564544678, "global_step": 599317, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9617047309875488, "global_step": 599318, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0531482696533203, "global_step": 599319, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.036296844482422, "global_step": 599320, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.003777265548706, "global_step": 599321, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9380919933319092, "global_step": 599322, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9652645587921143, "global_step": 599323, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9808872938156128, "global_step": 599324, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.8906642198562622, "global_step": 599325, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0216007232666016, "global_step": 599326, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9916473627090454, "global_step": 599327, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0206472873687744, "global_step": 599328, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9962786436080933, "global_step": 599329, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9770681858062744, "global_step": 599330, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.018277406692505, "global_step": 599331, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.963926076889038, "global_step": 599332, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0037286281585693, "global_step": 599333, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9432052373886108, "global_step": 599334, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.075608968734741, "global_step": 599335, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0418128967285156, "global_step": 599336, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0164031982421875, "global_step": 599337, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0248656272888184, "global_step": 599338, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.015937328338623, "global_step": 599339, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.001173734664917, "global_step": 599340, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0090458393096924, "global_step": 599341, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.053779363632202, "global_step": 599342, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0160021781921387, "global_step": 599343, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0385220050811768, "global_step": 599344, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9850025177001953, "global_step": 599345, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0126969814300537, "global_step": 599346, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.010989189147949, "global_step": 599347, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.032020092010498, "global_step": 599348, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0311667919158936, "global_step": 599349, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.017242193222046, "global_step": 599350, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0559046268463135, "global_step": 599351, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.086784839630127, "global_step": 599352, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.047872543334961, "global_step": 599353, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0176496505737305, "global_step": 599354, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9984256029129028, "global_step": 599355, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9609029293060303, "global_step": 599356, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0148518085479736, "global_step": 599357, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0642600059509277, "global_step": 599358, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0160093307495117, "global_step": 599359, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9895355701446533, "global_step": 599360, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9521939754486084, "global_step": 599361, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9299992322921753, "global_step": 599362, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0048272609710693, "global_step": 599363, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.985823154449463, "global_step": 599364, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0238890647888184, "global_step": 599365, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0368807315826416, "global_step": 599366, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9744114875793457, "global_step": 599367, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.018442392349243, "global_step": 599368, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0492095947265625, "global_step": 599369, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.033332586288452, "global_step": 599370, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.039602756500244, "global_step": 599371, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0011847019195557, "global_step": 599372, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.057396411895752, "global_step": 599373, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9882744550704956, "global_step": 599374, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0383636951446533, "global_step": 599375, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0185890197753906, "global_step": 599376, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0177195072174072, "global_step": 599377, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0381088256835938, "global_step": 599378, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9762506484985352, "global_step": 599379, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.002225160598755, "global_step": 599380, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0195090770721436, "global_step": 599381, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0710737705230713, "global_step": 599382, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.866426706314087, "global_step": 599383, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9304401874542236, "global_step": 599384, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0974040031433105, "global_step": 599385, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.060436964035034, "global_step": 599386, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0420114994049072, "global_step": 599387, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1508564949035645, "global_step": 599388, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9868327379226685, "global_step": 599389, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9607354402542114, "global_step": 599390, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9729570150375366, "global_step": 599391, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9940611124038696, "global_step": 599392, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.939522624015808, "global_step": 599393, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.046377182006836, "global_step": 599394, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0135796070098877, "global_step": 599395, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.993949294090271, "global_step": 599396, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9872615337371826, "global_step": 599397, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.006877899169922, "global_step": 599398, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9498339891433716, "global_step": 599399, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.033311367034912, "global_step": 599400, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.015023946762085, "global_step": 599401, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9901403188705444, "global_step": 599402, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.965271234512329, "global_step": 599403, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.021073818206787, "global_step": 599404, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9769468307495117, "global_step": 599405, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.966715693473816, "global_step": 599406, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9353269338607788, "global_step": 599407, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9449598789215088, "global_step": 599408, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0572805404663086, "global_step": 599409, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0279974937438965, "global_step": 599410, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.039651393890381, "global_step": 599411, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0130856037139893, "global_step": 599412, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.008904457092285, "global_step": 599413, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0876245498657227, "global_step": 599414, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.010868549346924, "global_step": 599415, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0352959632873535, "global_step": 599416, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.991232991218567, "global_step": 599417, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0508930683135986, "global_step": 599418, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0041465759277344, "global_step": 599419, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9874162673950195, "global_step": 599420, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0413007736206055, "global_step": 599421, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9743404388427734, "global_step": 599422, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.074146032333374, "global_step": 599423, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.032729387283325, "global_step": 599424, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9651912450790405, "global_step": 599425, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.001647472381592, "global_step": 599426, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9881625175476074, "global_step": 599427, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0236127376556396, "global_step": 599428, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.999969244003296, "global_step": 599429, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9594069719314575, "global_step": 599430, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0040078163146973, "global_step": 599431, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.020711660385132, "global_step": 599432, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9895236492156982, "global_step": 599433, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9943757057189941, "global_step": 599434, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0125186443328857, "global_step": 599435, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9789342880249023, "global_step": 599436, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9985367059707642, "global_step": 599437, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0765180587768555, "global_step": 599438, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.959706425666809, "global_step": 599439, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9197087287902832, "global_step": 599440, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0418384075164795, "global_step": 599441, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9927928447723389, "global_step": 599442, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.082038402557373, "global_step": 599443, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9521238803863525, "global_step": 599444, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9948686361312866, "global_step": 599445, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0542099475860596, "global_step": 599446, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.023554801940918, "global_step": 599447, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0834174156188965, "global_step": 599448, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0065577030181885, "global_step": 599449, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.047914981842041, "global_step": 599450, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0274429321289062, "global_step": 599451, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0385689735412598, "global_step": 599452, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1329407691955566, "global_step": 599453, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9724551439285278, "global_step": 599454, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0371758937835693, "global_step": 599455, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9263739585876465, "global_step": 599456, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9978996515274048, "global_step": 599457, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.000056028366089, "global_step": 599458, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0542051792144775, "global_step": 599459, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9572051763534546, "global_step": 599460, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0108723640441895, "global_step": 599461, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.975919246673584, "global_step": 599462, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9959185123443604, "global_step": 599463, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0000925064086914, "global_step": 599464, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0494704246520996, "global_step": 599465, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1031229496002197, "global_step": 599466, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9847843647003174, "global_step": 599467, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.023221492767334, "global_step": 599468, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0242481231689453, "global_step": 599469, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.008176326751709, "global_step": 599470, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.02937650680542, "global_step": 599471, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.028439998626709, "global_step": 599472, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0125887393951416, "global_step": 599473, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.029473066329956, "global_step": 599474, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9960469007492065, "global_step": 599475, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9683834314346313, "global_step": 599476, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9705573320388794, "global_step": 599477, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.071927070617676, "global_step": 599478, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.11324405670166, "global_step": 599479, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.01134991645813, "global_step": 599480, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.076523542404175, "global_step": 599481, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.011554718017578, "global_step": 599482, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.978066325187683, "global_step": 599483, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.996133804321289, "global_step": 599484, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.003918409347534, "global_step": 599485, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9628163576126099, "global_step": 599486, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.051229953765869, "global_step": 599487, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9506700038909912, "global_step": 599488, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0188724994659424, "global_step": 599489, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9675240516662598, "global_step": 599490, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.059361219406128, "global_step": 599491, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9937716722488403, "global_step": 599492, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.005012273788452, "global_step": 599493, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0275180339813232, "global_step": 599494, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.017876148223877, "global_step": 599495, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.976311206817627, "global_step": 599496, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.954180121421814, "global_step": 599497, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.015319585800171, "global_step": 599498, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.053068161010742, "global_step": 599499, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9273452758789062, "global_step": 599500, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.009943962097168, "global_step": 599501, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9772316217422485, "global_step": 599502, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9901931285858154, "global_step": 599503, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0337440967559814, "global_step": 599504, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0764341354370117, "global_step": 599505, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0952987670898438, "global_step": 599506, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.092200994491577, "global_step": 599507, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9980806112289429, "global_step": 599508, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0787506103515625, "global_step": 599509, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.003826141357422, "global_step": 599510, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9197189807891846, "global_step": 599511, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9919769763946533, "global_step": 599512, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9731817245483398, "global_step": 599513, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9518511295318604, "global_step": 599514, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9651930332183838, "global_step": 599515, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.942673921585083, "global_step": 599516, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.961409568786621, "global_step": 599517, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0018813610076904, "global_step": 599518, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.007035732269287, "global_step": 599519, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0122954845428467, "global_step": 599520, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9431380033493042, "global_step": 599521, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.058370590209961, "global_step": 599522, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0255849361419678, "global_step": 599523, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0145537853240967, "global_step": 599524, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9858553409576416, "global_step": 599525, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0212483406066895, "global_step": 599526, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.964073896408081, "global_step": 599527, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.965635895729065, "global_step": 599528, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.020853042602539, "global_step": 599529, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0710394382476807, "global_step": 599530, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9646234512329102, "global_step": 599531, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.998898983001709, "global_step": 599532, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0469908714294434, "global_step": 599533, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0143749713897705, "global_step": 599534, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0205841064453125, "global_step": 599535, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.047696113586426, "global_step": 599536, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.942380428314209, "global_step": 599537, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9179573059082031, "global_step": 599538, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.018462657928467, "global_step": 599539, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9465057849884033, "global_step": 599540, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9694606065750122, "global_step": 599541, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0170536041259766, "global_step": 599542, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.037227153778076, "global_step": 599543, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0269999504089355, "global_step": 599544, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0563559532165527, "global_step": 599545, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0036463737487793, "global_step": 599546, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9983670711517334, "global_step": 599547, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9970729351043701, "global_step": 599548, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0477914810180664, "global_step": 599549, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.04400897026062, "global_step": 599550, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0894291400909424, "global_step": 599551, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9940446615219116, "global_step": 599552, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9964638948440552, "global_step": 599553, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9697997570037842, "global_step": 599554, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9707791805267334, "global_step": 599555, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0988879203796387, "global_step": 599556, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9422354698181152, "global_step": 599557, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.089277505874634, "global_step": 599558, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9896509647369385, "global_step": 599559, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0672454833984375, "global_step": 599560, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9560397863388062, "global_step": 599561, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9919114112854004, "global_step": 599562, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9567087888717651, "global_step": 599563, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.000187873840332, "global_step": 599564, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9783716201782227, "global_step": 599565, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1055781841278076, "global_step": 599566, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.031031847000122, "global_step": 599567, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9603761434555054, "global_step": 599568, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.8821914196014404, "global_step": 599569, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0239813327789307, "global_step": 599570, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.079629898071289, "global_step": 599571, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.042341709136963, "global_step": 599572, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.010707378387451, "global_step": 599573, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.977308750152588, "global_step": 599574, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0069477558135986, "global_step": 599575, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.052727460861206, "global_step": 599576, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.960951566696167, "global_step": 599577, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0939719676971436, "global_step": 599578, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0126588344573975, "global_step": 599579, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.007634401321411, "global_step": 599580, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0604681968688965, "global_step": 599581, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.013352632522583, "global_step": 599582, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9805186986923218, "global_step": 599583, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.8880234956741333, "global_step": 599584, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0420665740966797, "global_step": 599585, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.021616220474243, "global_step": 599586, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9331207275390625, "global_step": 599587, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0505712032318115, "global_step": 599588, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.059591770172119, "global_step": 599589, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0129449367523193, "global_step": 599590, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.029186725616455, "global_step": 599591, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0375211238861084, "global_step": 599592, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.089426040649414, "global_step": 599593, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9934501647949219, "global_step": 599594, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0688235759735107, "global_step": 599595, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9884216785430908, "global_step": 599596, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0680935382843018, "global_step": 599597, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0250372886657715, "global_step": 599598, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.045527935028076, "global_step": 599599, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.008127450942993, "global_step": 599600, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.073784351348877, "global_step": 599601, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9973828792572021, "global_step": 599602, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0006866455078125, "global_step": 599603, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0304598808288574, "global_step": 599604, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0447700023651123, "global_step": 599605, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.008650541305542, "global_step": 599606, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0316078662872314, "global_step": 599607, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.943880319595337, "global_step": 599608, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.10467791557312, "global_step": 599609, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0659613609313965, "global_step": 599610, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0710396766662598, "global_step": 599611, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0171401500701904, "global_step": 599612, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0624053478240967, "global_step": 599613, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.948608636856079, "global_step": 599614, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9938300848007202, "global_step": 599615, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0142064094543457, "global_step": 599616, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0578882694244385, "global_step": 599617, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9765580892562866, "global_step": 599618, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9800667762756348, "global_step": 599619, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0102479457855225, "global_step": 599620, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.872215747833252, "global_step": 599621, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.956850290298462, "global_step": 599622, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0149765014648438, "global_step": 599623, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9080826044082642, "global_step": 599624, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0082528591156006, "global_step": 599625, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9419755935668945, "global_step": 599626, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0810952186584473, "global_step": 599627, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.066349506378174, "global_step": 599628, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.018582582473755, "global_step": 599629, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0164151191711426, "global_step": 599630, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.8897508382797241, "global_step": 599631, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0759406089782715, "global_step": 599632, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.036546468734741, "global_step": 599633, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.037061929702759, "global_step": 599634, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9851499795913696, "global_step": 599635, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9740833044052124, "global_step": 599636, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9943336248397827, "global_step": 599637, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1003551483154297, "global_step": 599638, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0427708625793457, "global_step": 599639, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.8919707536697388, "global_step": 599640, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.993452787399292, "global_step": 599641, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0364792346954346, "global_step": 599642, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.024153709411621, "global_step": 599643, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.053051710128784, "global_step": 599644, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.006775140762329, "global_step": 599645, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0924317836761475, "global_step": 599646, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.047313928604126, "global_step": 599647, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9476107358932495, "global_step": 599648, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0053091049194336, "global_step": 599649, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9293478727340698, "global_step": 599650, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1095457077026367, "global_step": 599651, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0276756286621094, "global_step": 599652, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0558619499206543, "global_step": 599653, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0722341537475586, "global_step": 599654, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0517077445983887, "global_step": 599655, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9995484352111816, "global_step": 599656, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.079192876815796, "global_step": 599657, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0325241088867188, "global_step": 599658, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0330464839935303, "global_step": 599659, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.966736912727356, "global_step": 599660, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.008061647415161, "global_step": 599661, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9633320569992065, "global_step": 599662, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.033508539199829, "global_step": 599663, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0558297634124756, "global_step": 599664, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.00740385055542, "global_step": 599665, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0262136459350586, "global_step": 599666, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9602041244506836, "global_step": 599667, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0215346813201904, "global_step": 599668, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.056340456008911, "global_step": 599669, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.093550205230713, "global_step": 599670, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.145387649536133, "global_step": 599671, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0330214500427246, "global_step": 599672, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.010439872741699, "global_step": 599673, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.088988780975342, "global_step": 599674, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0021398067474365, "global_step": 599675, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0977940559387207, "global_step": 599676, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.011874198913574, "global_step": 599677, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0456645488739014, "global_step": 599678, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0677711963653564, "global_step": 599679, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0336883068084717, "global_step": 599680, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9577696323394775, "global_step": 599681, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0296552181243896, "global_step": 599682, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0895044803619385, "global_step": 599683, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0469939708709717, "global_step": 599684, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9567880630493164, "global_step": 599685, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9766381978988647, "global_step": 599686, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0320279598236084, "global_step": 599687, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0087196826934814, "global_step": 599688, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0280330181121826, "global_step": 599689, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9938620328903198, "global_step": 599690, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0290565490722656, "global_step": 599691, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.121568441390991, "global_step": 599692, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9898842573165894, "global_step": 599693, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0133025646209717, "global_step": 599694, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0522751808166504, "global_step": 599695, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0419087409973145, "global_step": 599696, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9174387454986572, "global_step": 599697, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0103371143341064, "global_step": 599698, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.041384696960449, "global_step": 599699, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0446481704711914, "global_step": 599700, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.053071975708008, "global_step": 599701, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.028902769088745, "global_step": 599702, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0044853687286377, "global_step": 599703, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0372846126556396, "global_step": 599704, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0047290325164795, "global_step": 599705, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9772257804870605, "global_step": 599706, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.055363178253174, "global_step": 599707, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9755892753601074, "global_step": 599708, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9354808330535889, "global_step": 599709, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0451500415802, "global_step": 599710, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1050283908843994, "global_step": 599711, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0353896617889404, "global_step": 599712, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.032724618911743, "global_step": 599713, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9884642362594604, "global_step": 599714, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.042276382446289, "global_step": 599715, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.053018569946289, "global_step": 599716, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.8918952941894531, "global_step": 599717, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0045952796936035, "global_step": 599718, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0307137966156006, "global_step": 599719, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1173291206359863, "global_step": 599720, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9577744007110596, "global_step": 599721, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0770673751831055, "global_step": 599722, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0269291400909424, "global_step": 599723, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0751121044158936, "global_step": 599724, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.006162405014038, "global_step": 599725, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.017944574356079, "global_step": 599726, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.000199317932129, "global_step": 599727, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.096895456314087, "global_step": 599728, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9773213863372803, "global_step": 599729, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.03127121925354, "global_step": 599730, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9237176179885864, "global_step": 599731, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.987307071685791, "global_step": 599732, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9980055093765259, "global_step": 599733, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.994392991065979, "global_step": 599734, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.094987630844116, "global_step": 599735, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.049297571182251, "global_step": 599736, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0081262588500977, "global_step": 599737, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.103130578994751, "global_step": 599738, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9705923795700073, "global_step": 599739, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.051239252090454, "global_step": 599740, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0399839878082275, "global_step": 599741, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0470094680786133, "global_step": 599742, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0629935264587402, "global_step": 599743, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0797669887542725, "global_step": 599744, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9552665948867798, "global_step": 599745, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0009894371032715, "global_step": 599746, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.043696880340576, "global_step": 599747, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.041879653930664, "global_step": 599748, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.026628255844116, "global_step": 599749, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9446439743041992, "global_step": 599750, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.01115083694458, "global_step": 599751, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.029794692993164, "global_step": 599752, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.019052028656006, "global_step": 599753, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9670028686523438, "global_step": 599754, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.133601188659668, "global_step": 599755, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9616371393203735, "global_step": 599756, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0682408809661865, "global_step": 599757, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0626068115234375, "global_step": 599758, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.034283399581909, "global_step": 599759, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.050996780395508, "global_step": 599760, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0304880142211914, "global_step": 599761, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.013253688812256, "global_step": 599762, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0923423767089844, "global_step": 599763, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1220734119415283, "global_step": 599764, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0360116958618164, "global_step": 599765, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9487643241882324, "global_step": 599766, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9871928691864014, "global_step": 599767, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0548384189605713, "global_step": 599768, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9954952001571655, "global_step": 599769, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0583035945892334, "global_step": 599770, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0471203327178955, "global_step": 599771, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.005876302719116, "global_step": 599772, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.05743408203125, "global_step": 599773, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0101099014282227, "global_step": 599774, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0190839767456055, "global_step": 599775, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.011403799057007, "global_step": 599776, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0506091117858887, "global_step": 599777, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0401740074157715, "global_step": 599778, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.001692533493042, "global_step": 599779, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0060322284698486, "global_step": 599780, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0521318912506104, "global_step": 599781, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0640976428985596, "global_step": 599782, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0889203548431396, "global_step": 599783, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.015106439590454, "global_step": 599784, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.974609613418579, "global_step": 599785, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.946507215499878, "global_step": 599786, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9926445484161377, "global_step": 599787, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0502851009368896, "global_step": 599788, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9829444885253906, "global_step": 599789, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.045708656311035, "global_step": 599790, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9958933591842651, "global_step": 599791, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.968377709388733, "global_step": 599792, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.001265525817871, "global_step": 599793, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9213018417358398, "global_step": 599794, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0510494709014893, "global_step": 599795, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0829572677612305, "global_step": 599796, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0655124187469482, "global_step": 599797, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9999783039093018, "global_step": 599798, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.004706621170044, "global_step": 599799, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.003472089767456, "global_step": 599800, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.000932455062866, "global_step": 599801, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9981250762939453, "global_step": 599802, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.124833345413208, "global_step": 599803, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0862667560577393, "global_step": 599804, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.948560118675232, "global_step": 599805, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0862557888031006, "global_step": 599806, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.004408121109009, "global_step": 599807, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9946037530899048, "global_step": 599808, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0427398681640625, "global_step": 599809, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0771849155426025, "global_step": 599810, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.061568021774292, "global_step": 599811, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.991121530532837, "global_step": 599812, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.996431589126587, "global_step": 599813, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.025017023086548, "global_step": 599814, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9913291931152344, "global_step": 599815, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0760443210601807, "global_step": 599816, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9673024415969849, "global_step": 599817, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0395212173461914, "global_step": 599818, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0158610343933105, "global_step": 599819, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.987013816833496, "global_step": 599820, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0177435874938965, "global_step": 599821, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9758801460266113, "global_step": 599822, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1413888931274414, "global_step": 599823, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9985482692718506, "global_step": 599824, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.031466484069824, "global_step": 599825, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9994757175445557, "global_step": 599826, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9109727144241333, "global_step": 599827, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.112140655517578, "global_step": 599828, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0402634143829346, "global_step": 599829, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.03178071975708, "global_step": 599830, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.015472412109375, "global_step": 599831, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9947506189346313, "global_step": 599832, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9484081268310547, "global_step": 599833, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9572993516921997, "global_step": 599834, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9743729829788208, "global_step": 599835, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9486157894134521, "global_step": 599836, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9379353523254395, "global_step": 599837, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.984595775604248, "global_step": 599838, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0722951889038086, "global_step": 599839, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0316007137298584, "global_step": 599840, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.048900604248047, "global_step": 599841, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9441173076629639, "global_step": 599842, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9723594188690186, "global_step": 599843, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9174891710281372, "global_step": 599844, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0531809329986572, "global_step": 599845, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.015190362930298, "global_step": 599846, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1527888774871826, "global_step": 599847, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9825397729873657, "global_step": 599848, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.023899555206299, "global_step": 599849, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0445663928985596, "global_step": 599850, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.046339273452759, "global_step": 599851, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9809832572937012, "global_step": 599852, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.010505437850952, "global_step": 599853, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0340216159820557, "global_step": 599854, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.05611515045166, "global_step": 599855, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.029487133026123, "global_step": 599856, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.015012741088867, "global_step": 599857, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.003458023071289, "global_step": 599858, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9684299230575562, "global_step": 599859, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.00935435295105, "global_step": 599860, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.111811399459839, "global_step": 599861, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9974775314331055, "global_step": 599862, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.043480396270752, "global_step": 599863, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.002157211303711, "global_step": 599864, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.956654667854309, "global_step": 599865, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.034240961074829, "global_step": 599866, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9967155456542969, "global_step": 599867, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9811019897460938, "global_step": 599868, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0702383518218994, "global_step": 599869, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.974713683128357, "global_step": 599870, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9777028560638428, "global_step": 599871, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.04199481010437, "global_step": 599872, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9886884689331055, "global_step": 599873, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.072329521179199, "global_step": 599874, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0787973403930664, "global_step": 599875, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1212525367736816, "global_step": 599876, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9915510416030884, "global_step": 599877, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0071053504943848, "global_step": 599878, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0028178691864014, "global_step": 599879, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.087829351425171, "global_step": 599880, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.049081802368164, "global_step": 599881, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9791232347488403, "global_step": 599882, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.862868070602417, "global_step": 599883, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0536704063415527, "global_step": 599884, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9940365552902222, "global_step": 599885, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.096816062927246, "global_step": 599886, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9447919130325317, "global_step": 599887, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1171679496765137, "global_step": 599888, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.972477912902832, "global_step": 599889, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0414819717407227, "global_step": 599890, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.06689453125, "global_step": 599891, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9591182470321655, "global_step": 599892, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.026276111602783, "global_step": 599893, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.003801107406616, "global_step": 599894, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.054072618484497, "global_step": 599895, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.014883041381836, "global_step": 599896, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0031609535217285, "global_step": 599897, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0839829444885254, "global_step": 599898, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0888671875, "global_step": 599899, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.992870807647705, "global_step": 599900, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9961563348770142, "global_step": 599901, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9183263778686523, "global_step": 599902, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1396162509918213, "global_step": 599903, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9915913343429565, "global_step": 599904, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0307133197784424, "global_step": 599905, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0327141284942627, "global_step": 599906, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1318156719207764, "global_step": 599907, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0346384048461914, "global_step": 599908, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.115756034851074, "global_step": 599909, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9183478355407715, "global_step": 599910, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0023279190063477, "global_step": 599911, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.994821310043335, "global_step": 599912, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0188510417938232, "global_step": 599913, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0063138008117676, "global_step": 599914, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0193848609924316, "global_step": 599915, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.028712511062622, "global_step": 599916, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.000706434249878, "global_step": 599917, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9935067892074585, "global_step": 599918, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0075011253356934, "global_step": 599919, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.086344003677368, "global_step": 599920, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0115251541137695, "global_step": 599921, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0668981075286865, "global_step": 599922, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9417072534561157, "global_step": 599923, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0567500591278076, "global_step": 599924, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.077521324157715, "global_step": 599925, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1176085472106934, "global_step": 599926, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.1455492973327637, "global_step": 599927, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0035388469696045, "global_step": 599928, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0101852416992188, "global_step": 599929, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9492605924606323, "global_step": 599930, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.017194986343384, "global_step": 599931, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.036228895187378, "global_step": 599932, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.07668399810791, "global_step": 599933, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.078648567199707, "global_step": 599934, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9670034646987915, "global_step": 599935, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.034391403198242, "global_step": 599936, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9896507263183594, "global_step": 599937, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0360262393951416, "global_step": 599938, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.072948694229126, "global_step": 599939, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.119645357131958, "global_step": 599940, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.122932195663452, "global_step": 599941, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.0513076782226562, "global_step": 599942, "epoch": 968, "lr": 5e-05}
{"train_loss": 2.012284755706787, "global_step": 599943, "epoch": 968, "lr": 5e-05}
{"train_loss": 1.9636691808700562, "global_step": 599944, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0636537075042725, "global_step": 599945, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9621398448944092, "global_step": 599946, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0398623943328857, "global_step": 599947, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9658071994781494, "global_step": 599948, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.034947633743286, "global_step": 599949, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9873580932617188, "global_step": 599950, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9816381931304932, "global_step": 599951, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9360250234603882, "global_step": 599952, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.023359537124634, "global_step": 599953, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9676228761672974, "global_step": 599954, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.030863046646118, "global_step": 599955, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9942963123321533, "global_step": 599956, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.1073532104492188, "global_step": 599957, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.91867196559906, "global_step": 599958, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9426772594451904, "global_step": 599959, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.08669376373291, "global_step": 599960, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9125027656555176, "global_step": 599961, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9188059568405151, "global_step": 599962, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.005094528198242, "global_step": 599963, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9613914489746094, "global_step": 599964, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9694123268127441, "global_step": 599965, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0369632244110107, "global_step": 599966, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.066006660461426, "global_step": 599967, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.015517473220825, "global_step": 599968, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.103214740753174, "global_step": 599969, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9388396739959717, "global_step": 599970, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0543065071105957, "global_step": 599971, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0347228050231934, "global_step": 599972, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9642584323883057, "global_step": 599973, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9592063426971436, "global_step": 599974, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9573514461517334, "global_step": 599975, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.005749464035034, "global_step": 599976, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0111725330352783, "global_step": 599977, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0578012466430664, "global_step": 599978, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9179962873458862, "global_step": 599979, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0186197757720947, "global_step": 599980, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9711940288543701, "global_step": 599981, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.026500940322876, "global_step": 599982, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.043079376220703, "global_step": 599983, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.006228446960449, "global_step": 599984, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.962450623512268, "global_step": 599985, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.015157699584961, "global_step": 599986, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0139245986938477, "global_step": 599987, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0021474361419678, "global_step": 599988, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0978851318359375, "global_step": 599989, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9816768169403076, "global_step": 599990, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9790747165679932, "global_step": 599991, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9956660270690918, "global_step": 599992, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.009904623031616, "global_step": 599993, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0021233558654785, "global_step": 599994, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.03883957862854, "global_step": 599995, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9925391674041748, "global_step": 599996, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0917508602142334, "global_step": 599997, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.01826548576355, "global_step": 599998, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.056750774383545, "global_step": 599999, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0136406421661377, "global_step": 600000, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.020399808883667, "global_step": 600001, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0253729820251465, "global_step": 600002, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9626660346984863, "global_step": 600003, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9819328784942627, "global_step": 600004, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9485132694244385, "global_step": 600005, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.047072172164917, "global_step": 600006, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9887917041778564, "global_step": 600007, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.049032688140869, "global_step": 600008, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9744539260864258, "global_step": 600009, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9395900964736938, "global_step": 600010, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9883925914764404, "global_step": 600011, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0433430671691895, "global_step": 600012, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9726734161376953, "global_step": 600013, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9717063903808594, "global_step": 600014, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.994069218635559, "global_step": 600015, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9840672016143799, "global_step": 600016, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.035348653793335, "global_step": 600017, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.023242712020874, "global_step": 600018, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9732798337936401, "global_step": 600019, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9849804639816284, "global_step": 600020, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9935357570648193, "global_step": 600021, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9929689168930054, "global_step": 600022, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9960248470306396, "global_step": 600023, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0041513442993164, "global_step": 600024, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.994839072227478, "global_step": 600025, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9967563152313232, "global_step": 600026, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0084776878356934, "global_step": 600027, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9768168926239014, "global_step": 600028, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9543991088867188, "global_step": 600029, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9379866123199463, "global_step": 600030, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.953792929649353, "global_step": 600031, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0228371620178223, "global_step": 600032, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.922746181488037, "global_step": 600033, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.977617859840393, "global_step": 600034, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9485762119293213, "global_step": 600035, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.995951771736145, "global_step": 600036, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.05635142326355, "global_step": 600037, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.998653769493103, "global_step": 600038, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0228323936462402, "global_step": 600039, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9777278900146484, "global_step": 600040, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0275471210479736, "global_step": 600041, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.967798113822937, "global_step": 600042, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.043442964553833, "global_step": 600043, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0723378658294678, "global_step": 600044, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.050905227661133, "global_step": 600045, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9717117547988892, "global_step": 600046, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.031024694442749, "global_step": 600047, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.041769504547119, "global_step": 600048, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0251002311706543, "global_step": 600049, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.001487970352173, "global_step": 600050, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.077084541320801, "global_step": 600051, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.068326473236084, "global_step": 600052, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9980401992797852, "global_step": 600053, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9984103441238403, "global_step": 600054, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9803084135055542, "global_step": 600055, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9817726612091064, "global_step": 600056, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.071051836013794, "global_step": 600057, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.028301954269409, "global_step": 600058, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.966213345527649, "global_step": 600059, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9514559507369995, "global_step": 600060, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0768914222717285, "global_step": 600061, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9889583587646484, "global_step": 600062, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9770399332046509, "global_step": 600063, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0037057399749756, "global_step": 600064, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0271811485290527, "global_step": 600065, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.019721746444702, "global_step": 600066, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9690454006195068, "global_step": 600067, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.022836923599243, "global_step": 600068, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0195248126983643, "global_step": 600069, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9265551567077637, "global_step": 600070, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9788591861724854, "global_step": 600071, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9957116842269897, "global_step": 600072, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0132107734680176, "global_step": 600073, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.042545795440674, "global_step": 600074, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.034425735473633, "global_step": 600075, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.031812906265259, "global_step": 600076, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.038203716278076, "global_step": 600077, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0371177196502686, "global_step": 600078, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9849116802215576, "global_step": 600079, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.017728328704834, "global_step": 600080, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9694634675979614, "global_step": 600081, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.021893262863159, "global_step": 600082, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.008183240890503, "global_step": 600083, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.047731637954712, "global_step": 600084, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.031177520751953, "global_step": 600085, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9704464673995972, "global_step": 600086, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.941943645477295, "global_step": 600087, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0189568996429443, "global_step": 600088, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0176854133605957, "global_step": 600089, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0010411739349365, "global_step": 600090, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9701541662216187, "global_step": 600091, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9859896898269653, "global_step": 600092, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0230319499969482, "global_step": 600093, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9607073068618774, "global_step": 600094, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9727914333343506, "global_step": 600095, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0506436824798584, "global_step": 600096, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0362539291381836, "global_step": 600097, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.001723527908325, "global_step": 600098, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0145263671875, "global_step": 600099, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.029078722000122, "global_step": 600100, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9086370468139648, "global_step": 600101, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0368709564208984, "global_step": 600102, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9751678705215454, "global_step": 600103, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.003674268722534, "global_step": 600104, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9162081480026245, "global_step": 600105, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0024564266204834, "global_step": 600106, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0103771686553955, "global_step": 600107, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.033388137817383, "global_step": 600108, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0534677505493164, "global_step": 600109, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9892604351043701, "global_step": 600110, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0045173168182373, "global_step": 600111, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.989406704902649, "global_step": 600112, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0908203125, "global_step": 600113, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.032191753387451, "global_step": 600114, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9903273582458496, "global_step": 600115, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.067819118499756, "global_step": 600116, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.092588186264038, "global_step": 600117, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9690710306167603, "global_step": 600118, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0265450477600098, "global_step": 600119, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.1091737747192383, "global_step": 600120, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.048189878463745, "global_step": 600121, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.088536262512207, "global_step": 600122, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.066206455230713, "global_step": 600123, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.123542308807373, "global_step": 600124, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9671337604522705, "global_step": 600125, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.008652448654175, "global_step": 600126, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0191123485565186, "global_step": 600127, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.016493320465088, "global_step": 600128, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0277419090270996, "global_step": 600129, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.042393207550049, "global_step": 600130, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9815855026245117, "global_step": 600131, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.071566343307495, "global_step": 600132, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9616289138793945, "global_step": 600133, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.04731822013855, "global_step": 600134, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.003784656524658, "global_step": 600135, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.005268096923828, "global_step": 600136, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.003559112548828, "global_step": 600137, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9657827615737915, "global_step": 600138, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9655917882919312, "global_step": 600139, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0584495067596436, "global_step": 600140, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0488672256469727, "global_step": 600141, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9815375804901123, "global_step": 600142, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9530346393585205, "global_step": 600143, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9751412868499756, "global_step": 600144, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0143656730651855, "global_step": 600145, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.983845591545105, "global_step": 600146, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9086414575576782, "global_step": 600147, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9605878591537476, "global_step": 600148, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9964745044708252, "global_step": 600149, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9471330642700195, "global_step": 600150, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0033628940582275, "global_step": 600151, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9706768989562988, "global_step": 600152, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0343704223632812, "global_step": 600153, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0314505100250244, "global_step": 600154, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.997922420501709, "global_step": 600155, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.072925090789795, "global_step": 600156, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9754109382629395, "global_step": 600157, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9861904382705688, "global_step": 600158, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9251606464385986, "global_step": 600159, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.06673526763916, "global_step": 600160, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.021562337875366, "global_step": 600161, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0062546730041504, "global_step": 600162, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9865316152572632, "global_step": 600163, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.964316725730896, "global_step": 600164, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.121764659881592, "global_step": 600165, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9865186214447021, "global_step": 600166, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.000492572784424, "global_step": 600167, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9713143110275269, "global_step": 600168, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0370593070983887, "global_step": 600169, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.005591869354248, "global_step": 600170, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.099717140197754, "global_step": 600171, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0253632068634033, "global_step": 600172, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0476298332214355, "global_step": 600173, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9609465599060059, "global_step": 600174, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9511182308197021, "global_step": 600175, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9600675106048584, "global_step": 600176, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9910646677017212, "global_step": 600177, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.980425238609314, "global_step": 600178, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9677386283874512, "global_step": 600179, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0412776470184326, "global_step": 600180, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0514075756073, "global_step": 600181, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0408928394317627, "global_step": 600182, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0101349353790283, "global_step": 600183, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9773494005203247, "global_step": 600184, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.960680603981018, "global_step": 600185, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.1025614738464355, "global_step": 600186, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.077117443084717, "global_step": 600187, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0289976596832275, "global_step": 600188, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.009284257888794, "global_step": 600189, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.027064323425293, "global_step": 600190, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0736727714538574, "global_step": 600191, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9695247411727905, "global_step": 600192, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0126712322235107, "global_step": 600193, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0580737590789795, "global_step": 600194, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9738717079162598, "global_step": 600195, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.026684284210205, "global_step": 600196, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.008668899536133, "global_step": 600197, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.011295795440674, "global_step": 600198, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0165672302246094, "global_step": 600199, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.082490921020508, "global_step": 600200, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9519288539886475, "global_step": 600201, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0543692111968994, "global_step": 600202, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.068840503692627, "global_step": 600203, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0097713470458984, "global_step": 600204, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9665082693099976, "global_step": 600205, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9538614749908447, "global_step": 600206, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.960842251777649, "global_step": 600207, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.073399305343628, "global_step": 600208, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.037235975265503, "global_step": 600209, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0343356132507324, "global_step": 600210, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9869369268417358, "global_step": 600211, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.027132511138916, "global_step": 600212, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9869983196258545, "global_step": 600213, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.048085927963257, "global_step": 600214, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.922688364982605, "global_step": 600215, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.028730630874634, "global_step": 600216, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.031245470046997, "global_step": 600217, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0398318767547607, "global_step": 600218, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0110626220703125, "global_step": 600219, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.087515354156494, "global_step": 600220, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9934254884719849, "global_step": 600221, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9971950054168701, "global_step": 600222, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.976784586906433, "global_step": 600223, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9393876791000366, "global_step": 600224, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.022082567214966, "global_step": 600225, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0374717712402344, "global_step": 600226, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.035080671310425, "global_step": 600227, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.983929991722107, "global_step": 600228, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9290317296981812, "global_step": 600229, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9555522203445435, "global_step": 600230, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0645225048065186, "global_step": 600231, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0212321281433105, "global_step": 600232, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9784101247787476, "global_step": 600233, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0091373920440674, "global_step": 600234, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.081270456314087, "global_step": 600235, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.015187978744507, "global_step": 600236, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0109386444091797, "global_step": 600237, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0570430755615234, "global_step": 600238, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9641177654266357, "global_step": 600239, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0689830780029297, "global_step": 600240, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.006863594055176, "global_step": 600241, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9515968561172485, "global_step": 600242, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0213000774383545, "global_step": 600243, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.011474132537842, "global_step": 600244, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.968744158744812, "global_step": 600245, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.971232533454895, "global_step": 600246, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.04080867767334, "global_step": 600247, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.8896405696868896, "global_step": 600248, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.1492340564727783, "global_step": 600249, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.035137891769409, "global_step": 600250, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9588154554367065, "global_step": 600251, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9971662759780884, "global_step": 600252, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9947515726089478, "global_step": 600253, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.046398878097534, "global_step": 600254, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.008744955062866, "global_step": 600255, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.052945852279663, "global_step": 600256, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9927856922149658, "global_step": 600257, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.027636766433716, "global_step": 600258, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.015514373779297, "global_step": 600259, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9992749691009521, "global_step": 600260, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0219838619232178, "global_step": 600261, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.025956153869629, "global_step": 600262, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9930691719055176, "global_step": 600263, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9822444915771484, "global_step": 600264, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0111544132232666, "global_step": 600265, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0166075229644775, "global_step": 600266, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9911983013153076, "global_step": 600267, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0819270610809326, "global_step": 600268, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.985520601272583, "global_step": 600269, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.022545576095581, "global_step": 600270, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0746755599975586, "global_step": 600271, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9905864000320435, "global_step": 600272, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9487709999084473, "global_step": 600273, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0027246475219727, "global_step": 600274, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.017977714538574, "global_step": 600275, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0058000087738037, "global_step": 600276, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.935759425163269, "global_step": 600277, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.940228819847107, "global_step": 600278, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0002970695495605, "global_step": 600279, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0046863555908203, "global_step": 600280, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.011941432952881, "global_step": 600281, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.044473648071289, "global_step": 600282, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0033254623413086, "global_step": 600283, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.049098014831543, "global_step": 600284, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.12483549118042, "global_step": 600285, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0492401123046875, "global_step": 600286, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9533361196517944, "global_step": 600287, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.028090476989746, "global_step": 600288, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.010906934738159, "global_step": 600289, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.920833945274353, "global_step": 600290, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.011260747909546, "global_step": 600291, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.069204568862915, "global_step": 600292, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0316498279571533, "global_step": 600293, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.045415163040161, "global_step": 600294, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0024826526641846, "global_step": 600295, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0173420906066895, "global_step": 600296, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.118896245956421, "global_step": 600297, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.032378673553467, "global_step": 600298, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0012667179107666, "global_step": 600299, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.022766590118408, "global_step": 600300, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.017630100250244, "global_step": 600301, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9833199977874756, "global_step": 600302, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9731324911117554, "global_step": 600303, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.026384115219116, "global_step": 600304, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0245418548583984, "global_step": 600305, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9825294017791748, "global_step": 600306, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0102224349975586, "global_step": 600307, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9811071157455444, "global_step": 600308, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9910175800323486, "global_step": 600309, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9955317974090576, "global_step": 600310, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9097230434417725, "global_step": 600311, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0561468601226807, "global_step": 600312, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9658043384552002, "global_step": 600313, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.051529884338379, "global_step": 600314, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.102957248687744, "global_step": 600315, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.002335786819458, "global_step": 600316, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9925248622894287, "global_step": 600317, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.003298044204712, "global_step": 600318, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9786293506622314, "global_step": 600319, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0874714851379395, "global_step": 600320, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.034217357635498, "global_step": 600321, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0743660926818848, "global_step": 600322, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.067676305770874, "global_step": 600323, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0147972106933594, "global_step": 600324, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0166516304016113, "global_step": 600325, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.005253553390503, "global_step": 600326, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9969539642333984, "global_step": 600327, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.04642391204834, "global_step": 600328, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.1182241439819336, "global_step": 600329, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0536441802978516, "global_step": 600330, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0363428592681885, "global_step": 600331, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0479307174682617, "global_step": 600332, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9992066621780396, "global_step": 600333, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9725784063339233, "global_step": 600334, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.010253667831421, "global_step": 600335, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9452080726623535, "global_step": 600336, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.026752471923828, "global_step": 600337, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9915876388549805, "global_step": 600338, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.068627119064331, "global_step": 600339, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.1077518463134766, "global_step": 600340, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0145151615142822, "global_step": 600341, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.023606300354004, "global_step": 600342, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9728831052780151, "global_step": 600343, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9635071754455566, "global_step": 600344, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.021327257156372, "global_step": 600345, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9915746450424194, "global_step": 600346, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9693539142608643, "global_step": 600347, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0096285343170166, "global_step": 600348, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.072895050048828, "global_step": 600349, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.964070200920105, "global_step": 600350, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.066683769226074, "global_step": 600351, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.012815475463867, "global_step": 600352, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0426762104034424, "global_step": 600353, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9806185960769653, "global_step": 600354, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9537214040756226, "global_step": 600355, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0480873584747314, "global_step": 600356, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0308165550231934, "global_step": 600357, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9816536903381348, "global_step": 600358, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9742709398269653, "global_step": 600359, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.003573417663574, "global_step": 600360, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0134763717651367, "global_step": 600361, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0057716369628906, "global_step": 600362, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9053114652633667, "global_step": 600363, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0089011192321777, "global_step": 600364, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.145761013031006, "global_step": 600365, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9517827033996582, "global_step": 600366, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0042331218719482, "global_step": 600367, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.975555658340454, "global_step": 600368, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0671443939208984, "global_step": 600369, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9868899583816528, "global_step": 600370, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.017540693283081, "global_step": 600371, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0147602558135986, "global_step": 600372, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9471186399459839, "global_step": 600373, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.042653799057007, "global_step": 600374, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0280981063842773, "global_step": 600375, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0221517086029053, "global_step": 600376, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.023451805114746, "global_step": 600377, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0047662258148193, "global_step": 600378, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.111844062805176, "global_step": 600379, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.025475025177002, "global_step": 600380, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.947189450263977, "global_step": 600381, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.901888132095337, "global_step": 600382, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.983777642250061, "global_step": 600383, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9519047737121582, "global_step": 600384, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9979506731033325, "global_step": 600385, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.006924629211426, "global_step": 600386, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0578479766845703, "global_step": 600387, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.039303779602051, "global_step": 600388, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.034306764602661, "global_step": 600389, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.997402548789978, "global_step": 600390, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.006631851196289, "global_step": 600391, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0153379440307617, "global_step": 600392, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.069967746734619, "global_step": 600393, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9881415367126465, "global_step": 600394, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.062436103820801, "global_step": 600395, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.00677227973938, "global_step": 600396, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.959625244140625, "global_step": 600397, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0667247772216797, "global_step": 600398, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9508668184280396, "global_step": 600399, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0640857219696045, "global_step": 600400, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9862480163574219, "global_step": 600401, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.050632953643799, "global_step": 600402, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.95350980758667, "global_step": 600403, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.060171127319336, "global_step": 600404, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0070338249206543, "global_step": 600405, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.049516201019287, "global_step": 600406, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9847079515457153, "global_step": 600407, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0145788192749023, "global_step": 600408, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9779938459396362, "global_step": 600409, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9853776693344116, "global_step": 600410, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.030496835708618, "global_step": 600411, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9232808351516724, "global_step": 600412, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0337917804718018, "global_step": 600413, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9894633293151855, "global_step": 600414, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9999892711639404, "global_step": 600415, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9312870502471924, "global_step": 600416, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9631932973861694, "global_step": 600417, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.024092435836792, "global_step": 600418, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0137972831726074, "global_step": 600419, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9762002229690552, "global_step": 600420, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0153756141662598, "global_step": 600421, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0385732650756836, "global_step": 600422, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9898006916046143, "global_step": 600423, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.854278564453125, "global_step": 600424, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.070403814315796, "global_step": 600425, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.029232978820801, "global_step": 600426, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9868723154067993, "global_step": 600427, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0388500690460205, "global_step": 600428, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0093657970428467, "global_step": 600429, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.1054117679595947, "global_step": 600430, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0460429191589355, "global_step": 600431, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0101144313812256, "global_step": 600432, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9987596273422241, "global_step": 600433, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.996567726135254, "global_step": 600434, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.012176513671875, "global_step": 600435, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.025388717651367, "global_step": 600436, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.151200532913208, "global_step": 600437, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9471017122268677, "global_step": 600438, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9909625053405762, "global_step": 600439, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0008420944213867, "global_step": 600440, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.044138193130493, "global_step": 600441, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.018855571746826, "global_step": 600442, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9686459302902222, "global_step": 600443, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0429816246032715, "global_step": 600444, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.053689479827881, "global_step": 600445, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0683999061584473, "global_step": 600446, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9854230880737305, "global_step": 600447, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0444116592407227, "global_step": 600448, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9237433671951294, "global_step": 600449, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0195629596710205, "global_step": 600450, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.004594087600708, "global_step": 600451, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9567283391952515, "global_step": 600452, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.06343412399292, "global_step": 600453, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.019010305404663, "global_step": 600454, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.904911756515503, "global_step": 600455, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9899002313613892, "global_step": 600456, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.012786388397217, "global_step": 600457, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0231118202209473, "global_step": 600458, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0519614219665527, "global_step": 600459, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9604684114456177, "global_step": 600460, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.987168312072754, "global_step": 600461, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9770907163619995, "global_step": 600462, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9802385568618774, "global_step": 600463, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.954094409942627, "global_step": 600464, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.008906841278076, "global_step": 600465, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.034222364425659, "global_step": 600466, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9955273866653442, "global_step": 600467, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.970914602279663, "global_step": 600468, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9811537265777588, "global_step": 600469, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0173914432525635, "global_step": 600470, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0168237686157227, "global_step": 600471, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.021026611328125, "global_step": 600472, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9724761247634888, "global_step": 600473, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0843982696533203, "global_step": 600474, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9873504638671875, "global_step": 600475, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.8809285163879395, "global_step": 600476, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9812533855438232, "global_step": 600477, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0303404331207275, "global_step": 600478, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9981874227523804, "global_step": 600479, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.017512321472168, "global_step": 600480, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9834377765655518, "global_step": 600481, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9523212909698486, "global_step": 600482, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.993878722190857, "global_step": 600483, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0167348384857178, "global_step": 600484, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9621471166610718, "global_step": 600485, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.05210542678833, "global_step": 600486, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.979001522064209, "global_step": 600487, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.1256442070007324, "global_step": 600488, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9536867141723633, "global_step": 600489, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9812159538269043, "global_step": 600490, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0715785026550293, "global_step": 600491, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9569114446640015, "global_step": 600492, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9278064966201782, "global_step": 600493, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.985559344291687, "global_step": 600494, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.994093656539917, "global_step": 600495, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0212419033050537, "global_step": 600496, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.091357707977295, "global_step": 600497, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9792343378067017, "global_step": 600498, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0244874954223633, "global_step": 600499, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0145232677459717, "global_step": 600500, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0528202056884766, "global_step": 600501, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9607577323913574, "global_step": 600502, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.107640266418457, "global_step": 600503, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0409305095672607, "global_step": 600504, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0854129791259766, "global_step": 600505, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0041370391845703, "global_step": 600506, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9881439208984375, "global_step": 600507, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0252530574798584, "global_step": 600508, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9565799236297607, "global_step": 600509, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0981695652008057, "global_step": 600510, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0430209636688232, "global_step": 600511, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.020479917526245, "global_step": 600512, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9631330966949463, "global_step": 600513, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0106797218322754, "global_step": 600514, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0531182289123535, "global_step": 600515, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9830288887023926, "global_step": 600516, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0394134521484375, "global_step": 600517, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9565023183822632, "global_step": 600518, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.1386988162994385, "global_step": 600519, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0427253246307373, "global_step": 600520, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0054194927215576, "global_step": 600521, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.1046299934387207, "global_step": 600522, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9398173093795776, "global_step": 600523, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9760022163391113, "global_step": 600524, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0809082984924316, "global_step": 600525, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0929765701293945, "global_step": 600526, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.028409242630005, "global_step": 600527, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.011622428894043, "global_step": 600528, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.950836420059204, "global_step": 600529, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.006735324859619, "global_step": 600530, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.995941400527954, "global_step": 600531, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0387473106384277, "global_step": 600532, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9682163000106812, "global_step": 600533, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9574888944625854, "global_step": 600534, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0144050121307373, "global_step": 600535, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9797313213348389, "global_step": 600536, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.966505765914917, "global_step": 600537, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.030372142791748, "global_step": 600538, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0557525157928467, "global_step": 600539, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0346007347106934, "global_step": 600540, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.000192642211914, "global_step": 600541, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.046895742416382, "global_step": 600542, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9692941904067993, "global_step": 600543, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0463669300079346, "global_step": 600544, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.074213743209839, "global_step": 600545, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.993782877922058, "global_step": 600546, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0978775024414062, "global_step": 600547, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.017385244369507, "global_step": 600548, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.084496259689331, "global_step": 600549, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0428717136383057, "global_step": 600550, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9551856517791748, "global_step": 600551, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0609052181243896, "global_step": 600552, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9928388595581055, "global_step": 600553, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0008583068847656, "global_step": 600554, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9753813743591309, "global_step": 600555, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9357625246047974, "global_step": 600556, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0195722579956055, "global_step": 600557, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.1232779026031494, "global_step": 600558, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0330326557159424, "global_step": 600559, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9565200805664062, "global_step": 600560, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9846632480621338, "global_step": 600561, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9965243339538574, "global_step": 600562, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.015537738800049, "global_step": 600563, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0351815223693848, "global_step": 600564, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9842554330825806, "global_step": 600565, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0504040718078613, "global_step": 600566, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.00587797164917, "global_step": 600567, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.045764446258545, "global_step": 600568, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0795135498046875, "global_step": 600569, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0868256092071533, "global_step": 600570, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0088043212890625, "global_step": 600571, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9792572259902954, "global_step": 600572, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0344367027282715, "global_step": 600573, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.993281602859497, "global_step": 600574, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9868162870407104, "global_step": 600575, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9424889087677002, "global_step": 600576, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9856626987457275, "global_step": 600577, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.082319974899292, "global_step": 600578, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.019509792327881, "global_step": 600579, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.096684694290161, "global_step": 600580, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0109920501708984, "global_step": 600581, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.017690658569336, "global_step": 600582, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.060309648513794, "global_step": 600583, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0455217361450195, "global_step": 600584, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.028367519378662, "global_step": 600585, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0725300312042236, "global_step": 600586, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.026014804840088, "global_step": 600587, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9879810810089111, "global_step": 600588, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0175909996032715, "global_step": 600589, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.054537296295166, "global_step": 600590, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9778982400894165, "global_step": 600591, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0914573669433594, "global_step": 600592, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9925333261489868, "global_step": 600593, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0141804218292236, "global_step": 600594, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9885752201080322, "global_step": 600595, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0028164386749268, "global_step": 600596, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9555346965789795, "global_step": 600597, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.040731430053711, "global_step": 600598, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.014676570892334, "global_step": 600599, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0159530639648438, "global_step": 600600, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.960517406463623, "global_step": 600601, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0241401195526123, "global_step": 600602, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0611584186553955, "global_step": 600603, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.007164716720581, "global_step": 600604, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9422699213027954, "global_step": 600605, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0445990562438965, "global_step": 600606, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.058328628540039, "global_step": 600607, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9881864786148071, "global_step": 600608, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.033986806869507, "global_step": 600609, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9879761934280396, "global_step": 600610, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0531742572784424, "global_step": 600611, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0020241737365723, "global_step": 600612, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0123839378356934, "global_step": 600613, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.030500888824463, "global_step": 600614, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0774011611938477, "global_step": 600615, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.1262500286102295, "global_step": 600616, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.013200044631958, "global_step": 600617, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.085303783416748, "global_step": 600618, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0227317810058594, "global_step": 600619, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0918784141540527, "global_step": 600620, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.067380905151367, "global_step": 600621, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.959080457687378, "global_step": 600622, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.1276278495788574, "global_step": 600623, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9294977188110352, "global_step": 600624, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0173275470733643, "global_step": 600625, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0608160495758057, "global_step": 600626, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0082948207855225, "global_step": 600627, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9414501190185547, "global_step": 600628, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.002467393875122, "global_step": 600629, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0694711208343506, "global_step": 600630, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0119025707244873, "global_step": 600631, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.011258125305176, "global_step": 600632, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9472427368164062, "global_step": 600633, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0756332874298096, "global_step": 600634, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9589732885360718, "global_step": 600635, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.995085597038269, "global_step": 600636, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9541038274765015, "global_step": 600637, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0087203979492188, "global_step": 600638, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.103121757507324, "global_step": 600639, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.044733762741089, "global_step": 600640, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9802182912826538, "global_step": 600641, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.989046573638916, "global_step": 600642, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0011961460113525, "global_step": 600643, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.03529691696167, "global_step": 600644, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0157577991485596, "global_step": 600645, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.03275465965271, "global_step": 600646, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.098497152328491, "global_step": 600647, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9269427061080933, "global_step": 600648, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0179927349090576, "global_step": 600649, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.977097988128662, "global_step": 600650, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9737370014190674, "global_step": 600651, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0562353134155273, "global_step": 600652, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0274455547332764, "global_step": 600653, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.00282883644104, "global_step": 600654, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0415444374084473, "global_step": 600655, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.055877447128296, "global_step": 600656, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0587329864501953, "global_step": 600657, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9999243021011353, "global_step": 600658, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9908820390701294, "global_step": 600659, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9496960639953613, "global_step": 600660, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.011350393295288, "global_step": 600661, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0578174591064453, "global_step": 600662, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.163886547088623, "global_step": 600663, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0906646251678467, "global_step": 600664, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9414291381835938, "global_step": 600665, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0208377838134766, "global_step": 600666, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0027546882629395, "global_step": 600667, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9842383861541748, "global_step": 600668, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.115112543106079, "global_step": 600669, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0503222942352295, "global_step": 600670, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.8607292175292969, "global_step": 600671, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0310637950897217, "global_step": 600672, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.019860029220581, "global_step": 600673, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.012751579284668, "global_step": 600674, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9937995672225952, "global_step": 600675, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0820257663726807, "global_step": 600676, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9784119129180908, "global_step": 600677, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.070521831512451, "global_step": 600678, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9794847965240479, "global_step": 600679, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0577750205993652, "global_step": 600680, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.008641481399536, "global_step": 600681, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0403993129730225, "global_step": 600682, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9335681200027466, "global_step": 600683, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9363703727722168, "global_step": 600684, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.022695302963257, "global_step": 600685, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0648446083068848, "global_step": 600686, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.943900227546692, "global_step": 600687, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9324487447738647, "global_step": 600688, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9885607957839966, "global_step": 600689, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9909337759017944, "global_step": 600690, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0765583515167236, "global_step": 600691, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0467677116394043, "global_step": 600692, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.957256555557251, "global_step": 600693, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.058229923248291, "global_step": 600694, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9996378421783447, "global_step": 600695, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.052490472793579, "global_step": 600696, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9215346574783325, "global_step": 600697, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.044234037399292, "global_step": 600698, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9651259183883667, "global_step": 600699, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0560455322265625, "global_step": 600700, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.059602737426758, "global_step": 600701, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0707106590270996, "global_step": 600702, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9980584383010864, "global_step": 600703, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.088911533355713, "global_step": 600704, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.039388418197632, "global_step": 600705, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9678151607513428, "global_step": 600706, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9962000846862793, "global_step": 600707, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.973653793334961, "global_step": 600708, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9801955223083496, "global_step": 600709, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.045588254928589, "global_step": 600710, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.025712013244629, "global_step": 600711, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0227391719818115, "global_step": 600712, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.981329083442688, "global_step": 600713, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9951705932617188, "global_step": 600714, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0413124561309814, "global_step": 600715, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9895284175872803, "global_step": 600716, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.036961078643799, "global_step": 600717, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.011786460876465, "global_step": 600718, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.044377326965332, "global_step": 600719, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.074044704437256, "global_step": 600720, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.1224851608276367, "global_step": 600721, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9630022048950195, "global_step": 600722, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.027479887008667, "global_step": 600723, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9455714225769043, "global_step": 600724, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.995843529701233, "global_step": 600725, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.021949052810669, "global_step": 600726, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9872993230819702, "global_step": 600727, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9969751834869385, "global_step": 600728, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0439505577087402, "global_step": 600729, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.040302276611328, "global_step": 600730, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0577170848846436, "global_step": 600731, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0162353515625, "global_step": 600732, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0426039695739746, "global_step": 600733, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0248351097106934, "global_step": 600734, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0742321014404297, "global_step": 600735, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.062976360321045, "global_step": 600736, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.090196132659912, "global_step": 600737, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0328688621520996, "global_step": 600738, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0042996406555176, "global_step": 600739, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.032301664352417, "global_step": 600740, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0340819358825684, "global_step": 600741, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0357885360717773, "global_step": 600742, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.122774124145508, "global_step": 600743, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.096358299255371, "global_step": 600744, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0502302646636963, "global_step": 600745, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0524892807006836, "global_step": 600746, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9759137630462646, "global_step": 600747, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.042181968688965, "global_step": 600748, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9922406673431396, "global_step": 600749, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9854228496551514, "global_step": 600750, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.021791458129883, "global_step": 600751, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9489219188690186, "global_step": 600752, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9847551584243774, "global_step": 600753, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.007169723510742, "global_step": 600754, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.03450345993042, "global_step": 600755, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.041656970977783, "global_step": 600756, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9016304016113281, "global_step": 600757, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.049694061279297, "global_step": 600758, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9702640771865845, "global_step": 600759, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0755674839019775, "global_step": 600760, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9825981855392456, "global_step": 600761, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0447700023651123, "global_step": 600762, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.010249137878418, "global_step": 600763, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.024523973464966, "global_step": 600764, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.012781858444214, "global_step": 600765, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0077919960021973, "global_step": 600766, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9865185022354126, "global_step": 600767, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9291105270385742, "global_step": 600768, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9758511781692505, "global_step": 600769, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9844247102737427, "global_step": 600770, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.1160354614257812, "global_step": 600771, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0055034160614014, "global_step": 600772, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9922281503677368, "global_step": 600773, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.019132614135742, "global_step": 600774, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0641679763793945, "global_step": 600775, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0307211875915527, "global_step": 600776, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9751423597335815, "global_step": 600777, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0712339878082275, "global_step": 600778, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.053260326385498, "global_step": 600779, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0015530586242676, "global_step": 600780, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0635292530059814, "global_step": 600781, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9749349355697632, "global_step": 600782, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.099668502807617, "global_step": 600783, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.030240297317505, "global_step": 600784, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9447461366653442, "global_step": 600785, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9367051124572754, "global_step": 600786, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0368423461914062, "global_step": 600787, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0741994380950928, "global_step": 600788, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.116246461868286, "global_step": 600789, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.088407278060913, "global_step": 600790, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9710527658462524, "global_step": 600791, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.009058952331543, "global_step": 600792, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0749032497406006, "global_step": 600793, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.013817071914673, "global_step": 600794, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.041442394256592, "global_step": 600795, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0428109169006348, "global_step": 600796, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0456480979919434, "global_step": 600797, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9872325658798218, "global_step": 600798, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0233073234558105, "global_step": 600799, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9818576574325562, "global_step": 600800, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0174903869628906, "global_step": 600801, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.001999616622925, "global_step": 600802, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9501359462738037, "global_step": 600803, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0137956142425537, "global_step": 600804, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9978786706924438, "global_step": 600805, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9284707307815552, "global_step": 600806, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9759197235107422, "global_step": 600807, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.06874942779541, "global_step": 600808, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9576756954193115, "global_step": 600809, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0084550380706787, "global_step": 600810, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.053995370864868, "global_step": 600811, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.114386796951294, "global_step": 600812, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0651865005493164, "global_step": 600813, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0619895458221436, "global_step": 600814, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0593230724334717, "global_step": 600815, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.973339557647705, "global_step": 600816, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9973375797271729, "global_step": 600817, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9824388027191162, "global_step": 600818, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9982576370239258, "global_step": 600819, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0005853176116943, "global_step": 600820, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.94889497756958, "global_step": 600821, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9915285110473633, "global_step": 600822, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9754518270492554, "global_step": 600823, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.027830123901367, "global_step": 600824, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0100722312927246, "global_step": 600825, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.040964126586914, "global_step": 600826, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.095067262649536, "global_step": 600827, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9230915307998657, "global_step": 600828, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0950560569763184, "global_step": 600829, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.039231061935425, "global_step": 600830, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.94736647605896, "global_step": 600831, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0169928073883057, "global_step": 600832, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.100593090057373, "global_step": 600833, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.1060268878936768, "global_step": 600834, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.042912006378174, "global_step": 600835, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0232632160186768, "global_step": 600836, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.1076974868774414, "global_step": 600837, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.983110785484314, "global_step": 600838, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.114417314529419, "global_step": 600839, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0768072605133057, "global_step": 600840, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9781936407089233, "global_step": 600841, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.014585494995117, "global_step": 600842, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.964322805404663, "global_step": 600843, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9674489498138428, "global_step": 600844, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9155609607696533, "global_step": 600845, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0431296825408936, "global_step": 600846, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.989250898361206, "global_step": 600847, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0033273696899414, "global_step": 600848, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9950077533721924, "global_step": 600849, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.958659052848816, "global_step": 600850, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0495970249176025, "global_step": 600851, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.00601863861084, "global_step": 600852, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0322890281677246, "global_step": 600853, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.06791353225708, "global_step": 600854, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9906760454177856, "global_step": 600855, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0015621185302734, "global_step": 600856, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9915523529052734, "global_step": 600857, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9670788049697876, "global_step": 600858, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.020472288131714, "global_step": 600859, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9537104368209839, "global_step": 600860, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.028968095779419, "global_step": 600861, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0379152297973633, "global_step": 600862, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0589420795440674, "global_step": 600863, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9677878618240356, "global_step": 600864, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.933638095855713, "global_step": 600865, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.019010543823242, "global_step": 600866, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.186971664428711, "global_step": 600867, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.1189346313476562, "global_step": 600868, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0315310955047607, "global_step": 600869, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9855010509490967, "global_step": 600870, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9911929368972778, "global_step": 600871, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0323801040649414, "global_step": 600872, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0168533325195312, "global_step": 600873, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0118513107299805, "global_step": 600874, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0483574867248535, "global_step": 600875, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0302786827087402, "global_step": 600876, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9660580158233643, "global_step": 600877, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.112020254135132, "global_step": 600878, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0023279190063477, "global_step": 600879, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9920109510421753, "global_step": 600880, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0577995777130127, "global_step": 600881, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0260369777679443, "global_step": 600882, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9962937831878662, "global_step": 600883, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9808900356292725, "global_step": 600884, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.05023455619812, "global_step": 600885, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0022988319396973, "global_step": 600886, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.096844434738159, "global_step": 600887, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.063295602798462, "global_step": 600888, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.077118158340454, "global_step": 600889, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.136234760284424, "global_step": 600890, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0331811904907227, "global_step": 600891, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.075627565383911, "global_step": 600892, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0382776260375977, "global_step": 600893, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0445749759674072, "global_step": 600894, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0082030296325684, "global_step": 600895, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.8822696208953857, "global_step": 600896, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9763984680175781, "global_step": 600897, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0536317825317383, "global_step": 600898, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9805623292922974, "global_step": 600899, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0539743900299072, "global_step": 600900, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.102527141571045, "global_step": 600901, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0580432415008545, "global_step": 600902, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.1097898483276367, "global_step": 600903, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9759591817855835, "global_step": 600904, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.028836250305176, "global_step": 600905, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.057499647140503, "global_step": 600906, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0208394527435303, "global_step": 600907, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0362417697906494, "global_step": 600908, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0472376346588135, "global_step": 600909, "epoch": 969, "lr": 5e-05}
{"train_loss": 1.9578814506530762, "global_step": 600910, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0827858448028564, "global_step": 600911, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.013672113418579, "global_step": 600912, "epoch": 969, "lr": 5e-05}
{"train_loss": 2.0154316425323486, "global_step": 600913, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0053188800811768, "global_step": 600914, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.001681327819824, "global_step": 600915, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0420618057250977, "global_step": 600916, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9328970909118652, "global_step": 600917, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0201194286346436, "global_step": 600918, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1337318420410156, "global_step": 600919, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0039591789245605, "global_step": 600920, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9909816980361938, "global_step": 600921, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.014747381210327, "global_step": 600922, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0279417037963867, "global_step": 600923, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.962244987487793, "global_step": 600924, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0623867511749268, "global_step": 600925, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0158846378326416, "global_step": 600926, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0260353088378906, "global_step": 600927, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9240490198135376, "global_step": 600928, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9992494583129883, "global_step": 600929, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.008606195449829, "global_step": 600930, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.957990050315857, "global_step": 600931, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0866756439208984, "global_step": 600932, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0165414810180664, "global_step": 600933, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0438766479492188, "global_step": 600934, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9914189577102661, "global_step": 600935, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9574229717254639, "global_step": 600936, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.060760498046875, "global_step": 600937, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0112075805664062, "global_step": 600938, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.001018762588501, "global_step": 600939, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9817973375320435, "global_step": 600940, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0480034351348877, "global_step": 600941, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0801141262054443, "global_step": 600942, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9587193727493286, "global_step": 600943, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9787969589233398, "global_step": 600944, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.996998906135559, "global_step": 600945, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0110366344451904, "global_step": 600946, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.08064866065979, "global_step": 600947, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9352561235427856, "global_step": 600948, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.977185606956482, "global_step": 600949, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.986158013343811, "global_step": 600950, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9469542503356934, "global_step": 600951, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9677273035049438, "global_step": 600952, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.994676947593689, "global_step": 600953, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.998515248298645, "global_step": 600954, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0524392127990723, "global_step": 600955, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9404046535491943, "global_step": 600956, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.002380609512329, "global_step": 600957, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0835583209991455, "global_step": 600958, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.05495023727417, "global_step": 600959, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0171656608581543, "global_step": 600960, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9879767894744873, "global_step": 600961, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.021881103515625, "global_step": 600962, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9111616611480713, "global_step": 600963, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9985988140106201, "global_step": 600964, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.002516746520996, "global_step": 600965, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0059964656829834, "global_step": 600966, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0360360145568848, "global_step": 600967, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.046441078186035, "global_step": 600968, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9722208976745605, "global_step": 600969, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0971035957336426, "global_step": 600970, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0171639919281006, "global_step": 600971, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9857697486877441, "global_step": 600972, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0004618167877197, "global_step": 600973, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.123321294784546, "global_step": 600974, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.032438278198242, "global_step": 600975, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9891504049301147, "global_step": 600976, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9978736639022827, "global_step": 600977, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0042600631713867, "global_step": 600978, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9969909191131592, "global_step": 600979, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9870588779449463, "global_step": 600980, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.039698362350464, "global_step": 600981, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0110650062561035, "global_step": 600982, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9762403964996338, "global_step": 600983, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.977170705795288, "global_step": 600984, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.031308650970459, "global_step": 600985, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.02618145942688, "global_step": 600986, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.002666473388672, "global_step": 600987, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.990932822227478, "global_step": 600988, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.924354076385498, "global_step": 600989, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9797866344451904, "global_step": 600990, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.007376194000244, "global_step": 600991, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.00649094581604, "global_step": 600992, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.064549207687378, "global_step": 600993, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.028357982635498, "global_step": 600994, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.944298505783081, "global_step": 600995, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0500175952911377, "global_step": 600996, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.006033420562744, "global_step": 600997, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9830577373504639, "global_step": 600998, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.961634635925293, "global_step": 600999, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.029456853866577, "global_step": 601000, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.036545515060425, "global_step": 601001, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9894318580627441, "global_step": 601002, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9844709634780884, "global_step": 601003, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.013192653656006, "global_step": 601004, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9443151950836182, "global_step": 601005, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9664454460144043, "global_step": 601006, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.053189754486084, "global_step": 601007, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9529489278793335, "global_step": 601008, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9788228273391724, "global_step": 601009, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.068840265274048, "global_step": 601010, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0103468894958496, "global_step": 601011, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.039149284362793, "global_step": 601012, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0363895893096924, "global_step": 601013, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9881150722503662, "global_step": 601014, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.035501480102539, "global_step": 601015, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.978729009628296, "global_step": 601016, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0961790084838867, "global_step": 601017, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.067354917526245, "global_step": 601018, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9714105129241943, "global_step": 601019, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0185317993164062, "global_step": 601020, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9761439561843872, "global_step": 601021, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.066434860229492, "global_step": 601022, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9895461797714233, "global_step": 601023, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0164105892181396, "global_step": 601024, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9766494035720825, "global_step": 601025, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9323590993881226, "global_step": 601026, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0663771629333496, "global_step": 601027, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0371196269989014, "global_step": 601028, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.084340810775757, "global_step": 601029, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0169928073883057, "global_step": 601030, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9804352521896362, "global_step": 601031, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0313339233398438, "global_step": 601032, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9635443687438965, "global_step": 601033, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1101596355438232, "global_step": 601034, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0383265018463135, "global_step": 601035, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0154824256896973, "global_step": 601036, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0936944484710693, "global_step": 601037, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.055015802383423, "global_step": 601038, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9129213094711304, "global_step": 601039, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9810588359832764, "global_step": 601040, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.025818109512329, "global_step": 601041, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.012765884399414, "global_step": 601042, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0153629779815674, "global_step": 601043, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.944414496421814, "global_step": 601044, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9764353036880493, "global_step": 601045, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0485641956329346, "global_step": 601046, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9581633806228638, "global_step": 601047, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.112025499343872, "global_step": 601048, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.056044340133667, "global_step": 601049, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1094133853912354, "global_step": 601050, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.006694793701172, "global_step": 601051, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.988928198814392, "global_step": 601052, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.038362741470337, "global_step": 601053, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.946327805519104, "global_step": 601054, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9476670026779175, "global_step": 601055, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.004666566848755, "global_step": 601056, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9391489028930664, "global_step": 601057, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9875352382659912, "global_step": 601058, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0018889904022217, "global_step": 601059, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.101341962814331, "global_step": 601060, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.042574405670166, "global_step": 601061, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0717339515686035, "global_step": 601062, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9666744470596313, "global_step": 601063, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0270910263061523, "global_step": 601064, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9542087316513062, "global_step": 601065, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.015120267868042, "global_step": 601066, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.961293339729309, "global_step": 601067, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.055155038833618, "global_step": 601068, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9355393648147583, "global_step": 601069, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0303268432617188, "global_step": 601070, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9566103219985962, "global_step": 601071, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0049948692321777, "global_step": 601072, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9720275402069092, "global_step": 601073, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9494315385818481, "global_step": 601074, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9997261762619019, "global_step": 601075, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.04121994972229, "global_step": 601076, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.083585262298584, "global_step": 601077, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.041853666305542, "global_step": 601078, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0436301231384277, "global_step": 601079, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0115835666656494, "global_step": 601080, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9519798755645752, "global_step": 601081, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.946306824684143, "global_step": 601082, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.105973482131958, "global_step": 601083, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.082751512527466, "global_step": 601084, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9390971660614014, "global_step": 601085, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0238447189331055, "global_step": 601086, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0258431434631348, "global_step": 601087, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9450297355651855, "global_step": 601088, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.987236499786377, "global_step": 601089, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0056495666503906, "global_step": 601090, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9449069499969482, "global_step": 601091, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.079983949661255, "global_step": 601092, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0337204933166504, "global_step": 601093, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9717075824737549, "global_step": 601094, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0578694343566895, "global_step": 601095, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.026186466217041, "global_step": 601096, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9937800168991089, "global_step": 601097, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.960316777229309, "global_step": 601098, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9878116846084595, "global_step": 601099, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0329174995422363, "global_step": 601100, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0140626430511475, "global_step": 601101, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.940330147743225, "global_step": 601102, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.8963731527328491, "global_step": 601103, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0417778491973877, "global_step": 601104, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9456673860549927, "global_step": 601105, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.995229721069336, "global_step": 601106, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.02335262298584, "global_step": 601107, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.076503038406372, "global_step": 601108, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.984171986579895, "global_step": 601109, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9972933530807495, "global_step": 601110, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.07033371925354, "global_step": 601111, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0494885444641113, "global_step": 601112, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9714648723602295, "global_step": 601113, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.029285192489624, "global_step": 601114, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9735808372497559, "global_step": 601115, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.989997148513794, "global_step": 601116, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.984476089477539, "global_step": 601117, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0424540042877197, "global_step": 601118, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9252992868423462, "global_step": 601119, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.009519338607788, "global_step": 601120, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.066316604614258, "global_step": 601121, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9699430465698242, "global_step": 601122, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0044052600860596, "global_step": 601123, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.993206262588501, "global_step": 601124, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0404279232025146, "global_step": 601125, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0233964920043945, "global_step": 601126, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.006509304046631, "global_step": 601127, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.960759162902832, "global_step": 601128, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0008413791656494, "global_step": 601129, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9870580434799194, "global_step": 601130, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9997137784957886, "global_step": 601131, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9977082014083862, "global_step": 601132, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9761594533920288, "global_step": 601133, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9376851320266724, "global_step": 601134, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.048436403274536, "global_step": 601135, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.048901319503784, "global_step": 601136, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.003697156906128, "global_step": 601137, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.945557713508606, "global_step": 601138, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.001800060272217, "global_step": 601139, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0765247344970703, "global_step": 601140, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9103384017944336, "global_step": 601141, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0677950382232666, "global_step": 601142, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9752827882766724, "global_step": 601143, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.102236747741699, "global_step": 601144, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0654876232147217, "global_step": 601145, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0710339546203613, "global_step": 601146, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.044541358947754, "global_step": 601147, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.996875286102295, "global_step": 601148, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9919544458389282, "global_step": 601149, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0396156311035156, "global_step": 601150, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.06290340423584, "global_step": 601151, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.01102352142334, "global_step": 601152, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.000077247619629, "global_step": 601153, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0343754291534424, "global_step": 601154, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.020812511444092, "global_step": 601155, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.959646463394165, "global_step": 601156, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1076295375823975, "global_step": 601157, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0723211765289307, "global_step": 601158, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9839012622833252, "global_step": 601159, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0317697525024414, "global_step": 601160, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.932851791381836, "global_step": 601161, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9849677085876465, "global_step": 601162, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0568392276763916, "global_step": 601163, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.063241481781006, "global_step": 601164, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.08575701713562, "global_step": 601165, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0421411991119385, "global_step": 601166, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9505858421325684, "global_step": 601167, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9271876811981201, "global_step": 601168, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.006488084793091, "global_step": 601169, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9898381233215332, "global_step": 601170, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.047483205795288, "global_step": 601171, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.972077488899231, "global_step": 601172, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9731396436691284, "global_step": 601173, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.006697177886963, "global_step": 601174, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.018308639526367, "global_step": 601175, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.021212577819824, "global_step": 601176, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9232975244522095, "global_step": 601177, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9954808950424194, "global_step": 601178, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1104254722595215, "global_step": 601179, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0521230697631836, "global_step": 601180, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0164551734924316, "global_step": 601181, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.084388256072998, "global_step": 601182, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9730726480484009, "global_step": 601183, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9136457443237305, "global_step": 601184, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.066892623901367, "global_step": 601185, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.078425645828247, "global_step": 601186, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0807058811187744, "global_step": 601187, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.981549859046936, "global_step": 601188, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9217857122421265, "global_step": 601189, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0465452671051025, "global_step": 601190, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0482380390167236, "global_step": 601191, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0561110973358154, "global_step": 601192, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.018453598022461, "global_step": 601193, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9840502738952637, "global_step": 601194, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9512068033218384, "global_step": 601195, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9947155714035034, "global_step": 601196, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.04109525680542, "global_step": 601197, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9728221893310547, "global_step": 601198, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9967985153198242, "global_step": 601199, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0139431953430176, "global_step": 601200, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9968132972717285, "global_step": 601201, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0631000995635986, "global_step": 601202, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9910469055175781, "global_step": 601203, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0069122314453125, "global_step": 601204, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.023158073425293, "global_step": 601205, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9296733140945435, "global_step": 601206, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.967474102973938, "global_step": 601207, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.952981948852539, "global_step": 601208, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9799087047576904, "global_step": 601209, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.011957883834839, "global_step": 601210, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9948863983154297, "global_step": 601211, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9849853515625, "global_step": 601212, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0359349250793457, "global_step": 601213, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9902241230010986, "global_step": 601214, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.075162887573242, "global_step": 601215, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.060579538345337, "global_step": 601216, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9601513147354126, "global_step": 601217, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.953247308731079, "global_step": 601218, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9508922100067139, "global_step": 601219, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.996171236038208, "global_step": 601220, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.98163902759552, "global_step": 601221, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.041210174560547, "global_step": 601222, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.013124942779541, "global_step": 601223, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9737132787704468, "global_step": 601224, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0813827514648438, "global_step": 601225, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9712320566177368, "global_step": 601226, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0448784828186035, "global_step": 601227, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.988551139831543, "global_step": 601228, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9964650869369507, "global_step": 601229, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0110857486724854, "global_step": 601230, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0713555812835693, "global_step": 601231, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0752508640289307, "global_step": 601232, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.967982292175293, "global_step": 601233, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0360937118530273, "global_step": 601234, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9282342195510864, "global_step": 601235, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.013413429260254, "global_step": 601236, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9594407081604004, "global_step": 601237, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9981539249420166, "global_step": 601238, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9847445487976074, "global_step": 601239, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.005324602127075, "global_step": 601240, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.00117826461792, "global_step": 601241, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.024489402770996, "global_step": 601242, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.938712239265442, "global_step": 601243, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.972973346710205, "global_step": 601244, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1067864894866943, "global_step": 601245, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9986943006515503, "global_step": 601246, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9665954113006592, "global_step": 601247, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.046156167984009, "global_step": 601248, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9365744590759277, "global_step": 601249, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9860187768936157, "global_step": 601250, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0401620864868164, "global_step": 601251, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0600783824920654, "global_step": 601252, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.011519432067871, "global_step": 601253, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9647743701934814, "global_step": 601254, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9840199947357178, "global_step": 601255, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0297048091888428, "global_step": 601256, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9724818468093872, "global_step": 601257, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.967089056968689, "global_step": 601258, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9949359893798828, "global_step": 601259, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.971199631690979, "global_step": 601260, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.022855281829834, "global_step": 601261, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9808440208435059, "global_step": 601262, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.013575792312622, "global_step": 601263, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.038057327270508, "global_step": 601264, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9972234964370728, "global_step": 601265, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0270259380340576, "global_step": 601266, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.949002981185913, "global_step": 601267, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9735376834869385, "global_step": 601268, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0234804153442383, "global_step": 601269, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0407142639160156, "global_step": 601270, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9958326816558838, "global_step": 601271, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9967138767242432, "global_step": 601272, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9816415309906006, "global_step": 601273, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.8787893056869507, "global_step": 601274, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9936147928237915, "global_step": 601275, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0639405250549316, "global_step": 601276, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.056753158569336, "global_step": 601277, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.094940185546875, "global_step": 601278, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0082361698150635, "global_step": 601279, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9171385765075684, "global_step": 601280, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0186712741851807, "global_step": 601281, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.023336410522461, "global_step": 601282, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.024421453475952, "global_step": 601283, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9891927242279053, "global_step": 601284, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.028963088989258, "global_step": 601285, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0505154132843018, "global_step": 601286, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0589466094970703, "global_step": 601287, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.03895902633667, "global_step": 601288, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.957777976989746, "global_step": 601289, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9265319108963013, "global_step": 601290, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9747971296310425, "global_step": 601291, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9582515954971313, "global_step": 601292, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1024913787841797, "global_step": 601293, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0218262672424316, "global_step": 601294, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9576150178909302, "global_step": 601295, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0034358501434326, "global_step": 601296, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0042097568511963, "global_step": 601297, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.982263207435608, "global_step": 601298, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9883133172988892, "global_step": 601299, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.039635419845581, "global_step": 601300, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9116348028182983, "global_step": 601301, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0392661094665527, "global_step": 601302, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9820995330810547, "global_step": 601303, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9324833154678345, "global_step": 601304, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.029759645462036, "global_step": 601305, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9889987707138062, "global_step": 601306, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0250251293182373, "global_step": 601307, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.039931058883667, "global_step": 601308, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.034006118774414, "global_step": 601309, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0129783153533936, "global_step": 601310, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0516486167907715, "global_step": 601311, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0624186992645264, "global_step": 601312, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0437002182006836, "global_step": 601313, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9291380643844604, "global_step": 601314, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.8998682498931885, "global_step": 601315, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9486796855926514, "global_step": 601316, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.034235954284668, "global_step": 601317, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9613004922866821, "global_step": 601318, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0396008491516113, "global_step": 601319, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.065268039703369, "global_step": 601320, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0365707874298096, "global_step": 601321, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.959375023841858, "global_step": 601322, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0451972484588623, "global_step": 601323, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.026524305343628, "global_step": 601324, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0272250175476074, "global_step": 601325, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9946720600128174, "global_step": 601326, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9805805683135986, "global_step": 601327, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0472490787506104, "global_step": 601328, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.998896598815918, "global_step": 601329, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.937180519104004, "global_step": 601330, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9995765686035156, "global_step": 601331, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9452030658721924, "global_step": 601332, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0401434898376465, "global_step": 601333, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9374847412109375, "global_step": 601334, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.955773115158081, "global_step": 601335, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9524048566818237, "global_step": 601336, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0798468589782715, "global_step": 601337, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9834576845169067, "global_step": 601338, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0185482501983643, "global_step": 601339, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0781044960021973, "global_step": 601340, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0701372623443604, "global_step": 601341, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.002074956893921, "global_step": 601342, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9832451343536377, "global_step": 601343, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.045116662979126, "global_step": 601344, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.970679759979248, "global_step": 601345, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.006622314453125, "global_step": 601346, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0696051120758057, "global_step": 601347, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9810981750488281, "global_step": 601348, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9481185674667358, "global_step": 601349, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0976734161376953, "global_step": 601350, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0166099071502686, "global_step": 601351, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0231821537017822, "global_step": 601352, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.025777578353882, "global_step": 601353, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0215280055999756, "global_step": 601354, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9425472021102905, "global_step": 601355, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0442652702331543, "global_step": 601356, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0268476009368896, "global_step": 601357, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.986387848854065, "global_step": 601358, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0446112155914307, "global_step": 601359, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0110867023468018, "global_step": 601360, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.024937868118286, "global_step": 601361, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9989734888076782, "global_step": 601362, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0188512802124023, "global_step": 601363, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.047532796859741, "global_step": 601364, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9841870069503784, "global_step": 601365, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.037302017211914, "global_step": 601366, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0362396240234375, "global_step": 601367, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.038069725036621, "global_step": 601368, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0977537631988525, "global_step": 601369, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0062291622161865, "global_step": 601370, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0026047229766846, "global_step": 601371, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.063958168029785, "global_step": 601372, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0063045024871826, "global_step": 601373, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.020756959915161, "global_step": 601374, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0459251403808594, "global_step": 601375, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0472829341888428, "global_step": 601376, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0154125690460205, "global_step": 601377, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0229580402374268, "global_step": 601378, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0921566486358643, "global_step": 601379, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0228872299194336, "global_step": 601380, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9844926595687866, "global_step": 601381, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9627188444137573, "global_step": 601382, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9666484594345093, "global_step": 601383, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9970076084136963, "global_step": 601384, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9576613903045654, "global_step": 601385, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.022902488708496, "global_step": 601386, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0059714317321777, "global_step": 601387, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9759273529052734, "global_step": 601388, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9953041076660156, "global_step": 601389, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0565240383148193, "global_step": 601390, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.092984199523926, "global_step": 601391, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0476434230804443, "global_step": 601392, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0600221157073975, "global_step": 601393, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9970074892044067, "global_step": 601394, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0682904720306396, "global_step": 601395, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0556833744049072, "global_step": 601396, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.022000551223755, "global_step": 601397, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0822436809539795, "global_step": 601398, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.043915033340454, "global_step": 601399, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1051392555236816, "global_step": 601400, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.8845958709716797, "global_step": 601401, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9021896123886108, "global_step": 601402, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0510976314544678, "global_step": 601403, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0799503326416016, "global_step": 601404, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0440738201141357, "global_step": 601405, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0205349922180176, "global_step": 601406, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.080631971359253, "global_step": 601407, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9838799238204956, "global_step": 601408, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.996207356452942, "global_step": 601409, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1364784240722656, "global_step": 601410, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9710607528686523, "global_step": 601411, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.089048147201538, "global_step": 601412, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0632107257843018, "global_step": 601413, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.993346929550171, "global_step": 601414, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9294875860214233, "global_step": 601415, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.012333631515503, "global_step": 601416, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.060231924057007, "global_step": 601417, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0250933170318604, "global_step": 601418, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.053683280944824, "global_step": 601419, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.050584316253662, "global_step": 601420, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.011904239654541, "global_step": 601421, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9712542295455933, "global_step": 601422, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9445825815200806, "global_step": 601423, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0533909797668457, "global_step": 601424, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0411875247955322, "global_step": 601425, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.012901544570923, "global_step": 601426, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9638001918792725, "global_step": 601427, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.8830667734146118, "global_step": 601428, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.046621799468994, "global_step": 601429, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1268582344055176, "global_step": 601430, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9248912334442139, "global_step": 601431, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.050147294998169, "global_step": 601432, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.006742238998413, "global_step": 601433, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.014214515686035, "global_step": 601434, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1371190547943115, "global_step": 601435, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0567305088043213, "global_step": 601436, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9626132249832153, "global_step": 601437, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0644946098327637, "global_step": 601438, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9940067529678345, "global_step": 601439, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.079881191253662, "global_step": 601440, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.135291576385498, "global_step": 601441, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0035226345062256, "global_step": 601442, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0392167568206787, "global_step": 601443, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.081090211868286, "global_step": 601444, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0227317810058594, "global_step": 601445, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1029467582702637, "global_step": 601446, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.024796485900879, "global_step": 601447, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.044595718383789, "global_step": 601448, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.052793502807617, "global_step": 601449, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.922314167022705, "global_step": 601450, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9627869129180908, "global_step": 601451, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.064129114151001, "global_step": 601452, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.005955934524536, "global_step": 601453, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.00502347946167, "global_step": 601454, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9459365606307983, "global_step": 601455, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0799875259399414, "global_step": 601456, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.053386926651001, "global_step": 601457, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0249521732330322, "global_step": 601458, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.994784951210022, "global_step": 601459, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9942376613616943, "global_step": 601460, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.103300094604492, "global_step": 601461, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0391764640808105, "global_step": 601462, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.972898244857788, "global_step": 601463, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.997958779335022, "global_step": 601464, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0891659259796143, "global_step": 601465, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0181188583374023, "global_step": 601466, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.033342123031616, "global_step": 601467, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0585620403289795, "global_step": 601468, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0342984199523926, "global_step": 601469, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.062692165374756, "global_step": 601470, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9491729736328125, "global_step": 601471, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9950731992721558, "global_step": 601472, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0312650203704834, "global_step": 601473, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.064154863357544, "global_step": 601474, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.005169153213501, "global_step": 601475, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9898217916488647, "global_step": 601476, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.084092140197754, "global_step": 601477, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9757869243621826, "global_step": 601478, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9956750869750977, "global_step": 601479, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.082859754562378, "global_step": 601480, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0005762577056885, "global_step": 601481, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0727033615112305, "global_step": 601482, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0190188884735107, "global_step": 601483, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0819506645202637, "global_step": 601484, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.956319808959961, "global_step": 601485, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.99527907371521, "global_step": 601486, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0019142627716064, "global_step": 601487, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9621468782424927, "global_step": 601488, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.019113540649414, "global_step": 601489, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9924811124801636, "global_step": 601490, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.048784017562866, "global_step": 601491, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.071829080581665, "global_step": 601492, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.019242286682129, "global_step": 601493, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9898959398269653, "global_step": 601494, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.956728219985962, "global_step": 601495, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0665371417999268, "global_step": 601496, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.964903712272644, "global_step": 601497, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9326860904693604, "global_step": 601498, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.078918695449829, "global_step": 601499, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0129806995391846, "global_step": 601500, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0460848808288574, "global_step": 601501, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0217974185943604, "global_step": 601502, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9652950763702393, "global_step": 601503, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0701353549957275, "global_step": 601504, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.995251178741455, "global_step": 601505, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.038318157196045, "global_step": 601506, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.029674768447876, "global_step": 601507, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1041738986968994, "global_step": 601508, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.996504783630371, "global_step": 601509, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9766379594802856, "global_step": 601510, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9252389669418335, "global_step": 601511, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0360798835754395, "global_step": 601512, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9828077554702759, "global_step": 601513, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.035970687866211, "global_step": 601514, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9253391027450562, "global_step": 601515, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.970603585243225, "global_step": 601516, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9596763849258423, "global_step": 601517, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0066492557525635, "global_step": 601518, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.016413450241089, "global_step": 601519, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.142328977584839, "global_step": 601520, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.054189682006836, "global_step": 601521, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0258595943450928, "global_step": 601522, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.062535524368286, "global_step": 601523, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.925681471824646, "global_step": 601524, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.969534158706665, "global_step": 601525, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.043825149536133, "global_step": 601526, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0559029579162598, "global_step": 601527, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9925495386123657, "global_step": 601528, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0656697750091553, "global_step": 601529, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.099916934967041, "global_step": 601530, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9807829856872559, "global_step": 601531, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0601770877838135, "global_step": 601532, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.003232002258301, "global_step": 601533, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.002927541732788, "global_step": 601534, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.020902395248413, "global_step": 601535, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.2134461402893066, "global_step": 601536, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0610556602478027, "global_step": 601537, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.930045485496521, "global_step": 601538, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.973037600517273, "global_step": 601539, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0862138271331787, "global_step": 601540, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9974796772003174, "global_step": 601541, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.023937702178955, "global_step": 601542, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0543832778930664, "global_step": 601543, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.02718186378479, "global_step": 601544, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.019538402557373, "global_step": 601545, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9526950120925903, "global_step": 601546, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0275442600250244, "global_step": 601547, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.04353404045105, "global_step": 601548, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.971481442451477, "global_step": 601549, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9870073795318604, "global_step": 601550, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.012671947479248, "global_step": 601551, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9923781156539917, "global_step": 601552, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.075859308242798, "global_step": 601553, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.956348180770874, "global_step": 601554, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.061873435974121, "global_step": 601555, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9889912605285645, "global_step": 601556, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.944461703300476, "global_step": 601557, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.046381950378418, "global_step": 601558, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.984514594078064, "global_step": 601559, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9544261693954468, "global_step": 601560, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.945662498474121, "global_step": 601561, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9673120975494385, "global_step": 601562, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9513044357299805, "global_step": 601563, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9255311489105225, "global_step": 601564, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9908149242401123, "global_step": 601565, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9920403957366943, "global_step": 601566, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.042194366455078, "global_step": 601567, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.11458683013916, "global_step": 601568, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9774365425109863, "global_step": 601569, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0034499168395996, "global_step": 601570, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9451788663864136, "global_step": 601571, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.073333263397217, "global_step": 601572, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9954960346221924, "global_step": 601573, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.056612730026245, "global_step": 601574, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.065782070159912, "global_step": 601575, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1089839935302734, "global_step": 601576, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0647473335266113, "global_step": 601577, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.038804292678833, "global_step": 601578, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9268242120742798, "global_step": 601579, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.022162437438965, "global_step": 601580, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0772032737731934, "global_step": 601581, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9827916622161865, "global_step": 601582, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0764353275299072, "global_step": 601583, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0260987281799316, "global_step": 601584, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0027997493743896, "global_step": 601585, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.005775213241577, "global_step": 601586, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9915674924850464, "global_step": 601587, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0114152431488037, "global_step": 601588, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0348899364471436, "global_step": 601589, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.021834135055542, "global_step": 601590, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0619826316833496, "global_step": 601591, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9978066682815552, "global_step": 601592, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0336923599243164, "global_step": 601593, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0386037826538086, "global_step": 601594, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.033343553543091, "global_step": 601595, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9961092472076416, "global_step": 601596, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.04144549369812, "global_step": 601597, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9455066919326782, "global_step": 601598, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0179896354675293, "global_step": 601599, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9704899787902832, "global_step": 601600, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.008504629135132, "global_step": 601601, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.061075210571289, "global_step": 601602, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0747921466827393, "global_step": 601603, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9624550342559814, "global_step": 601604, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9720596075057983, "global_step": 601605, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0024476051330566, "global_step": 601606, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9402117729187012, "global_step": 601607, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.038224220275879, "global_step": 601608, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0227768421173096, "global_step": 601609, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.138357400894165, "global_step": 601610, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9474235773086548, "global_step": 601611, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9714611768722534, "global_step": 601612, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9909141063690186, "global_step": 601613, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0379836559295654, "global_step": 601614, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9360120296478271, "global_step": 601615, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0148301124572754, "global_step": 601616, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0109825134277344, "global_step": 601617, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0412180423736572, "global_step": 601618, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9552370309829712, "global_step": 601619, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0306084156036377, "global_step": 601620, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9754269123077393, "global_step": 601621, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.070154905319214, "global_step": 601622, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.97335946559906, "global_step": 601623, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0327658653259277, "global_step": 601624, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.975878119468689, "global_step": 601625, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9645400047302246, "global_step": 601626, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0357863903045654, "global_step": 601627, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0507540702819824, "global_step": 601628, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.015976905822754, "global_step": 601629, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0097146034240723, "global_step": 601630, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9715919494628906, "global_step": 601631, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.958892583847046, "global_step": 601632, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.030238151550293, "global_step": 601633, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9878050088882446, "global_step": 601634, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.037506341934204, "global_step": 601635, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0250072479248047, "global_step": 601636, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0002601146698, "global_step": 601637, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.121683359146118, "global_step": 601638, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.064202070236206, "global_step": 601639, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.160780906677246, "global_step": 601640, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9633562564849854, "global_step": 601641, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0525219440460205, "global_step": 601642, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0309932231903076, "global_step": 601643, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0328528881073, "global_step": 601644, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0238232612609863, "global_step": 601645, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9868534803390503, "global_step": 601646, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.021158456802368, "global_step": 601647, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0577549934387207, "global_step": 601648, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9944179058074951, "global_step": 601649, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9277331829071045, "global_step": 601650, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0441510677337646, "global_step": 601651, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0049657821655273, "global_step": 601652, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.958589792251587, "global_step": 601653, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0999557971954346, "global_step": 601654, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0510122776031494, "global_step": 601655, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9744313955307007, "global_step": 601656, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0187795162200928, "global_step": 601657, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.011045455932617, "global_step": 601658, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.013786792755127, "global_step": 601659, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9709558486938477, "global_step": 601660, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0008199214935303, "global_step": 601661, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9688955545425415, "global_step": 601662, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9751179218292236, "global_step": 601663, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.031633138656616, "global_step": 601664, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.009706497192383, "global_step": 601665, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9631998538970947, "global_step": 601666, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1567628383636475, "global_step": 601667, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9845867156982422, "global_step": 601668, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0135083198547363, "global_step": 601669, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0714528560638428, "global_step": 601670, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.04372239112854, "global_step": 601671, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.059602975845337, "global_step": 601672, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.000560760498047, "global_step": 601673, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0006771087646484, "global_step": 601674, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0236752033233643, "global_step": 601675, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9838827848434448, "global_step": 601676, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1345090866088867, "global_step": 601677, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1059155464172363, "global_step": 601678, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.912577509880066, "global_step": 601679, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9613959789276123, "global_step": 601680, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0266668796539307, "global_step": 601681, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0406527519226074, "global_step": 601682, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9651771783828735, "global_step": 601683, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9416323900222778, "global_step": 601684, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.09946870803833, "global_step": 601685, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.970049500465393, "global_step": 601686, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0954885482788086, "global_step": 601687, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0236778259277344, "global_step": 601688, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0473825931549072, "global_step": 601689, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9714001417160034, "global_step": 601690, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0532374382019043, "global_step": 601691, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0080068111419678, "global_step": 601692, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0468530654907227, "global_step": 601693, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9904561042785645, "global_step": 601694, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9424623250961304, "global_step": 601695, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0384533405303955, "global_step": 601696, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.011559009552002, "global_step": 601697, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0695433616638184, "global_step": 601698, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.992154836654663, "global_step": 601699, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.086935520172119, "global_step": 601700, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.085099935531616, "global_step": 601701, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9540029764175415, "global_step": 601702, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0943593978881836, "global_step": 601703, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9548202753067017, "global_step": 601704, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.074758529663086, "global_step": 601705, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9763747453689575, "global_step": 601706, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0744149684906006, "global_step": 601707, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9349781274795532, "global_step": 601708, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.063302516937256, "global_step": 601709, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.046332836151123, "global_step": 601710, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9907751083374023, "global_step": 601711, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9724102020263672, "global_step": 601712, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0641071796417236, "global_step": 601713, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9856219291687012, "global_step": 601714, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9961479902267456, "global_step": 601715, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0454938411712646, "global_step": 601716, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9561346769332886, "global_step": 601717, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9952834844589233, "global_step": 601718, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.004842758178711, "global_step": 601719, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0015857219696045, "global_step": 601720, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0167946815490723, "global_step": 601721, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.018228530883789, "global_step": 601722, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.072420120239258, "global_step": 601723, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.035479784011841, "global_step": 601724, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0236170291900635, "global_step": 601725, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0127551555633545, "global_step": 601726, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0343620777130127, "global_step": 601727, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9678308963775635, "global_step": 601728, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0318334102630615, "global_step": 601729, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.02535343170166, "global_step": 601730, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.076061248779297, "global_step": 601731, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0241472721099854, "global_step": 601732, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0489068031311035, "global_step": 601733, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.109956979751587, "global_step": 601734, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0040371417999268, "global_step": 601735, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0704402923583984, "global_step": 601736, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9980909824371338, "global_step": 601737, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0596635341644287, "global_step": 601738, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1215503215789795, "global_step": 601739, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9367190599441528, "global_step": 601740, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0941989421844482, "global_step": 601741, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0013420581817627, "global_step": 601742, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0608487129211426, "global_step": 601743, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.038518190383911, "global_step": 601744, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.950244665145874, "global_step": 601745, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.969484567642212, "global_step": 601746, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9579163789749146, "global_step": 601747, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9423472881317139, "global_step": 601748, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9938056468963623, "global_step": 601749, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.959060549736023, "global_step": 601750, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9768891334533691, "global_step": 601751, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9889662265777588, "global_step": 601752, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.028817892074585, "global_step": 601753, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0145716667175293, "global_step": 601754, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1148791313171387, "global_step": 601755, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.963350772857666, "global_step": 601756, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.053611993789673, "global_step": 601757, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.01242733001709, "global_step": 601758, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.033350706100464, "global_step": 601759, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0633938312530518, "global_step": 601760, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0278031826019287, "global_step": 601761, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.003190517425537, "global_step": 601762, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0383846759796143, "global_step": 601763, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9868614673614502, "global_step": 601764, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9729821681976318, "global_step": 601765, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1402766704559326, "global_step": 601766, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0232841968536377, "global_step": 601767, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0061123371124268, "global_step": 601768, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.040703773498535, "global_step": 601769, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9883394241333008, "global_step": 601770, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9654077291488647, "global_step": 601771, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9728500843048096, "global_step": 601772, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9659066200256348, "global_step": 601773, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.952569842338562, "global_step": 601774, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.037707805633545, "global_step": 601775, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9970170259475708, "global_step": 601776, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.112842559814453, "global_step": 601777, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9941738843917847, "global_step": 601778, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0307798385620117, "global_step": 601779, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0406765937805176, "global_step": 601780, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.029027223587036, "global_step": 601781, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.041146993637085, "global_step": 601782, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.018688678741455, "global_step": 601783, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0289158821105957, "global_step": 601784, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9933873414993286, "global_step": 601785, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0145044326782227, "global_step": 601786, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0256574153900146, "global_step": 601787, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.005758285522461, "global_step": 601788, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9962191581726074, "global_step": 601789, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9917916059494019, "global_step": 601790, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.984684944152832, "global_step": 601791, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.028236150741577, "global_step": 601792, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0289220809936523, "global_step": 601793, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0506701469421387, "global_step": 601794, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0800414085388184, "global_step": 601795, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.026658058166504, "global_step": 601796, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9874792098999023, "global_step": 601797, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9991095066070557, "global_step": 601798, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0278890132904053, "global_step": 601799, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.911067247390747, "global_step": 601800, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.000784397125244, "global_step": 601801, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.965660572052002, "global_step": 601802, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.06778883934021, "global_step": 601803, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.032881259918213, "global_step": 601804, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9938524961471558, "global_step": 601805, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.014615058898926, "global_step": 601806, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0133392810821533, "global_step": 601807, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.112460136413574, "global_step": 601808, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9726877212524414, "global_step": 601809, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0887420177459717, "global_step": 601810, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0001490116119385, "global_step": 601811, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.994638204574585, "global_step": 601812, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9426599740982056, "global_step": 601813, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9968278408050537, "global_step": 601814, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.971604347229004, "global_step": 601815, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.975049614906311, "global_step": 601816, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1492655277252197, "global_step": 601817, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.908851981163025, "global_step": 601818, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1472229957580566, "global_step": 601819, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.989131212234497, "global_step": 601820, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9893784523010254, "global_step": 601821, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0020744800567627, "global_step": 601822, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9506826400756836, "global_step": 601823, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0155410766601562, "global_step": 601824, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0082414150238037, "global_step": 601825, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.015336513519287, "global_step": 601826, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0542821884155273, "global_step": 601827, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0587682723999023, "global_step": 601828, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.061758518218994, "global_step": 601829, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.080333948135376, "global_step": 601830, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0536997318267822, "global_step": 601831, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9887759685516357, "global_step": 601832, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.084573984146118, "global_step": 601833, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0453338623046875, "global_step": 601834, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.987953782081604, "global_step": 601835, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9993573427200317, "global_step": 601836, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0213544368743896, "global_step": 601837, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9082459211349487, "global_step": 601838, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0610742568969727, "global_step": 601839, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.045501708984375, "global_step": 601840, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.953301191329956, "global_step": 601841, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.01053786277771, "global_step": 601842, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9840296506881714, "global_step": 601843, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0400521755218506, "global_step": 601844, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.006009817123413, "global_step": 601845, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.033442974090576, "global_step": 601846, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0466513633728027, "global_step": 601847, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.080702304840088, "global_step": 601848, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0134973526000977, "global_step": 601849, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0456249713897705, "global_step": 601850, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9711674451828003, "global_step": 601851, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0190141201019287, "global_step": 601852, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9603627920150757, "global_step": 601853, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0487465858459473, "global_step": 601854, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0146231651306152, "global_step": 601855, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9861674308776855, "global_step": 601856, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.1040446758270264, "global_step": 601857, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0319292545318604, "global_step": 601858, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0006375312805176, "global_step": 601859, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9819655418395996, "global_step": 601860, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9662803411483765, "global_step": 601861, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9803962707519531, "global_step": 601862, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0093040466308594, "global_step": 601863, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9810973405838013, "global_step": 601864, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9653923511505127, "global_step": 601865, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.015955686569214, "global_step": 601866, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9761322736740112, "global_step": 601867, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9536279439926147, "global_step": 601868, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9675486087799072, "global_step": 601869, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9921499490737915, "global_step": 601870, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.991214394569397, "global_step": 601871, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9985787868499756, "global_step": 601872, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.975406289100647, "global_step": 601873, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0192465782165527, "global_step": 601874, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.080657720565796, "global_step": 601875, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.976055383682251, "global_step": 601876, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9988408088684082, "global_step": 601877, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.013338088989258, "global_step": 601878, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9872311353683472, "global_step": 601879, "epoch": 970, "lr": 5e-05}
{"train_loss": 1.9803379774093628, "global_step": 601880, "epoch": 970, "lr": 5e-05}
{"train_loss": 2.0130321979522705, "global_step": 601881, "epoch": 970, "lr": 5e-05, "val_loss": 5.797432899475098, "test_reconst_mse": 0.07371663302183151}
{"train_loss": 2.057203769683838, "global_step": 601882, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0660810470581055, "global_step": 601883, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.053136110305786, "global_step": 601884, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9575344324111938, "global_step": 601885, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0530853271484375, "global_step": 601886, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9886088371276855, "global_step": 601887, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.086341381072998, "global_step": 601888, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0609469413757324, "global_step": 601889, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0303261280059814, "global_step": 601890, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.988200306892395, "global_step": 601891, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.057363271713257, "global_step": 601892, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.046443462371826, "global_step": 601893, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.946775197982788, "global_step": 601894, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9724407196044922, "global_step": 601895, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.012298583984375, "global_step": 601896, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.036850929260254, "global_step": 601897, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0695250034332275, "global_step": 601898, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0082411766052246, "global_step": 601899, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9774384498596191, "global_step": 601900, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9716224670410156, "global_step": 601901, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9821994304656982, "global_step": 601902, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.064199686050415, "global_step": 601903, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9869682788848877, "global_step": 601904, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9897572994232178, "global_step": 601905, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9961609840393066, "global_step": 601906, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9986741542816162, "global_step": 601907, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0868570804595947, "global_step": 601908, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.010974884033203, "global_step": 601909, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9959375858306885, "global_step": 601910, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0263452529907227, "global_step": 601911, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.064235210418701, "global_step": 601912, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9664463996887207, "global_step": 601913, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9013736248016357, "global_step": 601914, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0327539443969727, "global_step": 601915, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9538192749023438, "global_step": 601916, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0771145820617676, "global_step": 601917, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9902477264404297, "global_step": 601918, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0249860286712646, "global_step": 601919, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.035626173019409, "global_step": 601920, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9914414882659912, "global_step": 601921, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9822725057601929, "global_step": 601922, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.950547218322754, "global_step": 601923, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9775420427322388, "global_step": 601924, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9761583805084229, "global_step": 601925, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9995909929275513, "global_step": 601926, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0254671573638916, "global_step": 601927, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.020524024963379, "global_step": 601928, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.8833001852035522, "global_step": 601929, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.1006672382354736, "global_step": 601930, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.956382393836975, "global_step": 601931, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0143539905548096, "global_step": 601932, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0609750747680664, "global_step": 601933, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.026397466659546, "global_step": 601934, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.040922164916992, "global_step": 601935, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9953579902648926, "global_step": 601936, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9933416843414307, "global_step": 601937, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.010909080505371, "global_step": 601938, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.126875400543213, "global_step": 601939, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.061540365219116, "global_step": 601940, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.98737370967865, "global_step": 601941, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0159432888031006, "global_step": 601942, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9123889207839966, "global_step": 601943, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.017019033432007, "global_step": 601944, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9742999076843262, "global_step": 601945, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0301499366760254, "global_step": 601946, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0052709579467773, "global_step": 601947, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9911584854125977, "global_step": 601948, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.042226791381836, "global_step": 601949, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0139102935791016, "global_step": 601950, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9981179237365723, "global_step": 601951, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9836962223052979, "global_step": 601952, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0028233528137207, "global_step": 601953, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0598220825195312, "global_step": 601954, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.914856195449829, "global_step": 601955, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9739747047424316, "global_step": 601956, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0114781856536865, "global_step": 601957, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9608261585235596, "global_step": 601958, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0464470386505127, "global_step": 601959, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9148491621017456, "global_step": 601960, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0212628841400146, "global_step": 601961, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.096700429916382, "global_step": 601962, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.081700325012207, "global_step": 601963, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.036085605621338, "global_step": 601964, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.112903594970703, "global_step": 601965, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9532623291015625, "global_step": 601966, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0158631801605225, "global_step": 601967, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.05904483795166, "global_step": 601968, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.011110305786133, "global_step": 601969, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9318420886993408, "global_step": 601970, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.968424916267395, "global_step": 601971, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9841408729553223, "global_step": 601972, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.94590425491333, "global_step": 601973, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0626132488250732, "global_step": 601974, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0942275524139404, "global_step": 601975, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.06071138381958, "global_step": 601976, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9530389308929443, "global_step": 601977, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.017800807952881, "global_step": 601978, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9332749843597412, "global_step": 601979, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9127575159072876, "global_step": 601980, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9769234657287598, "global_step": 601981, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9754979610443115, "global_step": 601982, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9575812816619873, "global_step": 601983, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0130505561828613, "global_step": 601984, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.008509635925293, "global_step": 601985, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9243084192276, "global_step": 601986, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9702602624893188, "global_step": 601987, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.048111915588379, "global_step": 601988, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0619688034057617, "global_step": 601989, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.999018669128418, "global_step": 601990, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0188868045806885, "global_step": 601991, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0510354042053223, "global_step": 601992, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0259315967559814, "global_step": 601993, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.967968225479126, "global_step": 601994, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.033052444458008, "global_step": 601995, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0194716453552246, "global_step": 601996, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9965574741363525, "global_step": 601997, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9978053569793701, "global_step": 601998, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9879109859466553, "global_step": 601999, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0087995529174805, "global_step": 602000, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9596247673034668, "global_step": 602001, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0382583141326904, "global_step": 602002, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.020615816116333, "global_step": 602003, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9654916524887085, "global_step": 602004, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9191620349884033, "global_step": 602005, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0680909156799316, "global_step": 602006, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0421483516693115, "global_step": 602007, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.055729866027832, "global_step": 602008, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9894342422485352, "global_step": 602009, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0485215187072754, "global_step": 602010, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.054309606552124, "global_step": 602011, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9360294342041016, "global_step": 602012, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0525543689727783, "global_step": 602013, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9564095735549927, "global_step": 602014, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0411791801452637, "global_step": 602015, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.015266180038452, "global_step": 602016, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9551663398742676, "global_step": 602017, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9880201816558838, "global_step": 602018, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9387032985687256, "global_step": 602019, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.980833649635315, "global_step": 602020, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.052807569503784, "global_step": 602021, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9508270025253296, "global_step": 602022, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9896893501281738, "global_step": 602023, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.052354335784912, "global_step": 602024, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.996672511100769, "global_step": 602025, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.939335584640503, "global_step": 602026, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9961681365966797, "global_step": 602027, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0346767902374268, "global_step": 602028, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9899177551269531, "global_step": 602029, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9821125268936157, "global_step": 602030, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9695507287979126, "global_step": 602031, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.021937847137451, "global_step": 602032, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.021394968032837, "global_step": 602033, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9316773414611816, "global_step": 602034, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0373575687408447, "global_step": 602035, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.042158365249634, "global_step": 602036, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.012683629989624, "global_step": 602037, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.989933729171753, "global_step": 602038, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0245718955993652, "global_step": 602039, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.059351921081543, "global_step": 602040, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9729268550872803, "global_step": 602041, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.090319871902466, "global_step": 602042, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9262361526489258, "global_step": 602043, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9788873195648193, "global_step": 602044, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.013885736465454, "global_step": 602045, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0731732845306396, "global_step": 602046, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0142858028411865, "global_step": 602047, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9875370264053345, "global_step": 602048, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.00264310836792, "global_step": 602049, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.979834794998169, "global_step": 602050, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0426440238952637, "global_step": 602051, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.968534231185913, "global_step": 602052, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.053525686264038, "global_step": 602053, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9613313674926758, "global_step": 602054, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9488310813903809, "global_step": 602055, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.013120651245117, "global_step": 602056, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0418286323547363, "global_step": 602057, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.050766944885254, "global_step": 602058, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.938609004020691, "global_step": 602059, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.018191337585449, "global_step": 602060, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.033092975616455, "global_step": 602061, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0564422607421875, "global_step": 602062, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.983209252357483, "global_step": 602063, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0744853019714355, "global_step": 602064, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0383358001708984, "global_step": 602065, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.990720272064209, "global_step": 602066, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0523056983947754, "global_step": 602067, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.035414457321167, "global_step": 602068, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0895304679870605, "global_step": 602069, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9384429454803467, "global_step": 602070, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0143396854400635, "global_step": 602071, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.036386489868164, "global_step": 602072, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9373083114624023, "global_step": 602073, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9760146141052246, "global_step": 602074, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9573725461959839, "global_step": 602075, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0411555767059326, "global_step": 602076, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9261975288391113, "global_step": 602077, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9257416725158691, "global_step": 602078, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0129637718200684, "global_step": 602079, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0133402347564697, "global_step": 602080, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.075875759124756, "global_step": 602081, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0349321365356445, "global_step": 602082, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9468660354614258, "global_step": 602083, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0315794944763184, "global_step": 602084, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.970710277557373, "global_step": 602085, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.972602128982544, "global_step": 602086, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0440847873687744, "global_step": 602087, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9930434226989746, "global_step": 602088, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.014225959777832, "global_step": 602089, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.028266668319702, "global_step": 602090, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9570753574371338, "global_step": 602091, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.057339668273926, "global_step": 602092, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0855138301849365, "global_step": 602093, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.000663995742798, "global_step": 602094, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0499141216278076, "global_step": 602095, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.959026575088501, "global_step": 602096, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9689137935638428, "global_step": 602097, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.965242624282837, "global_step": 602098, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0514230728149414, "global_step": 602099, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9667590856552124, "global_step": 602100, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.013908624649048, "global_step": 602101, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.021354913711548, "global_step": 602102, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9576070308685303, "global_step": 602103, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0238311290740967, "global_step": 602104, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9803062677383423, "global_step": 602105, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.038591146469116, "global_step": 602106, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.984283447265625, "global_step": 602107, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.037569522857666, "global_step": 602108, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9883383512496948, "global_step": 602109, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.061042070388794, "global_step": 602110, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.002769708633423, "global_step": 602111, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0221219062805176, "global_step": 602112, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.044050931930542, "global_step": 602113, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0268666744232178, "global_step": 602114, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9386223554611206, "global_step": 602115, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9907305240631104, "global_step": 602116, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9855822324752808, "global_step": 602117, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.035750389099121, "global_step": 602118, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.065744161605835, "global_step": 602119, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9571998119354248, "global_step": 602120, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.086674213409424, "global_step": 602121, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9729833602905273, "global_step": 602122, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.080103635787964, "global_step": 602123, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9669337272644043, "global_step": 602124, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0347368717193604, "global_step": 602125, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9420979022979736, "global_step": 602126, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0368525981903076, "global_step": 602127, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9331525564193726, "global_step": 602128, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9998699426651, "global_step": 602129, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9675525426864624, "global_step": 602130, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.1081249713897705, "global_step": 602131, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0103654861450195, "global_step": 602132, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0186803340911865, "global_step": 602133, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0378365516662598, "global_step": 602134, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.087412118911743, "global_step": 602135, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0466268062591553, "global_step": 602136, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9611377716064453, "global_step": 602137, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.001394033432007, "global_step": 602138, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0679681301116943, "global_step": 602139, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.975369930267334, "global_step": 602140, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0426743030548096, "global_step": 602141, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9733284711837769, "global_step": 602142, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9725985527038574, "global_step": 602143, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9936497211456299, "global_step": 602144, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.995404601097107, "global_step": 602145, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.056623935699463, "global_step": 602146, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0095293521881104, "global_step": 602147, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0604238510131836, "global_step": 602148, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9163203239440918, "global_step": 602149, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.1090621948242188, "global_step": 602150, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.1325294971466064, "global_step": 602151, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0001189708709717, "global_step": 602152, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.021169424057007, "global_step": 602153, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0269815921783447, "global_step": 602154, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0120458602905273, "global_step": 602155, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.020461320877075, "global_step": 602156, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0538761615753174, "global_step": 602157, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.046194076538086, "global_step": 602158, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0115275382995605, "global_step": 602159, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0004119873046875, "global_step": 602160, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9595670700073242, "global_step": 602161, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0201961994171143, "global_step": 602162, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9574934244155884, "global_step": 602163, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.006298780441284, "global_step": 602164, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0507383346557617, "global_step": 602165, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.064772605895996, "global_step": 602166, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9686124324798584, "global_step": 602167, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0388035774230957, "global_step": 602168, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.040893316268921, "global_step": 602169, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.1124069690704346, "global_step": 602170, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.98861563205719, "global_step": 602171, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0274205207824707, "global_step": 602172, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.1146795749664307, "global_step": 602173, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0595908164978027, "global_step": 602174, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9969687461853027, "global_step": 602175, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0454261302948, "global_step": 602176, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.944260597229004, "global_step": 602177, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9977903366088867, "global_step": 602178, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9760806560516357, "global_step": 602179, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0249645709991455, "global_step": 602180, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0432591438293457, "global_step": 602181, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.059448719024658, "global_step": 602182, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.036626100540161, "global_step": 602183, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0795466899871826, "global_step": 602184, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0164811611175537, "global_step": 602185, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.138098955154419, "global_step": 602186, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9982414245605469, "global_step": 602187, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9356696605682373, "global_step": 602188, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0599498748779297, "global_step": 602189, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9670064449310303, "global_step": 602190, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.022205352783203, "global_step": 602191, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.998936414718628, "global_step": 602192, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0573344230651855, "global_step": 602193, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9636999368667603, "global_step": 602194, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0710322856903076, "global_step": 602195, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.8552470207214355, "global_step": 602196, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.008409261703491, "global_step": 602197, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.011120080947876, "global_step": 602198, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.028785228729248, "global_step": 602199, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9947211742401123, "global_step": 602200, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.089906930923462, "global_step": 602201, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0537912845611572, "global_step": 602202, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9611326456069946, "global_step": 602203, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9956172704696655, "global_step": 602204, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9536776542663574, "global_step": 602205, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0352399349212646, "global_step": 602206, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0230913162231445, "global_step": 602207, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.995666742324829, "global_step": 602208, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.1276190280914307, "global_step": 602209, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9599546194076538, "global_step": 602210, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.035695791244507, "global_step": 602211, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0320725440979004, "global_step": 602212, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9626058340072632, "global_step": 602213, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0469443798065186, "global_step": 602214, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9913979768753052, "global_step": 602215, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0231523513793945, "global_step": 602216, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.108790159225464, "global_step": 602217, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.053680419921875, "global_step": 602218, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0091030597686768, "global_step": 602219, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.000760078430176, "global_step": 602220, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9175068140029907, "global_step": 602221, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0019383430480957, "global_step": 602222, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.032578945159912, "global_step": 602223, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9633009433746338, "global_step": 602224, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0452070236206055, "global_step": 602225, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.972715139389038, "global_step": 602226, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0366899967193604, "global_step": 602227, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9132522344589233, "global_step": 602228, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9786680936813354, "global_step": 602229, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0745315551757812, "global_step": 602230, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9592931270599365, "global_step": 602231, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.034649133682251, "global_step": 602232, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0045809745788574, "global_step": 602233, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.025550603866577, "global_step": 602234, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9962074756622314, "global_step": 602235, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0111515522003174, "global_step": 602236, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9434657096862793, "global_step": 602237, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0657992362976074, "global_step": 602238, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9602601528167725, "global_step": 602239, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0376946926116943, "global_step": 602240, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9821640253067017, "global_step": 602241, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9644603729248047, "global_step": 602242, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.040278434753418, "global_step": 602243, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0073397159576416, "global_step": 602244, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0137150287628174, "global_step": 602245, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0854952335357666, "global_step": 602246, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.968044638633728, "global_step": 602247, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9697237014770508, "global_step": 602248, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.088557243347168, "global_step": 602249, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0271151065826416, "global_step": 602250, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9734705686569214, "global_step": 602251, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.006028175354004, "global_step": 602252, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9546761512756348, "global_step": 602253, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.052931785583496, "global_step": 602254, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.994356393814087, "global_step": 602255, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9680029153823853, "global_step": 602256, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.066662073135376, "global_step": 602257, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0411648750305176, "global_step": 602258, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9301483631134033, "global_step": 602259, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.957614779472351, "global_step": 602260, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9766100645065308, "global_step": 602261, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9615803956985474, "global_step": 602262, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.072035789489746, "global_step": 602263, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.018613815307617, "global_step": 602264, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.040921688079834, "global_step": 602265, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.002284526824951, "global_step": 602266, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9776277542114258, "global_step": 602267, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.139394521713257, "global_step": 602268, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.024515151977539, "global_step": 602269, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.00193190574646, "global_step": 602270, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9085108041763306, "global_step": 602271, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0225019454956055, "global_step": 602272, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0273935794830322, "global_step": 602273, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.000851631164551, "global_step": 602274, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.075434923171997, "global_step": 602275, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9303582906723022, "global_step": 602276, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9808681011199951, "global_step": 602277, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.038566827774048, "global_step": 602278, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0155420303344727, "global_step": 602279, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9610323905944824, "global_step": 602280, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.08903431892395, "global_step": 602281, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9714961051940918, "global_step": 602282, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9232451915740967, "global_step": 602283, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0039212703704834, "global_step": 602284, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.030721664428711, "global_step": 602285, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0353925228118896, "global_step": 602286, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0345189571380615, "global_step": 602287, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0565731525421143, "global_step": 602288, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0314996242523193, "global_step": 602289, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0671157836914062, "global_step": 602290, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.045423746109009, "global_step": 602291, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.036203145980835, "global_step": 602292, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.922682523727417, "global_step": 602293, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9721168279647827, "global_step": 602294, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9045813083648682, "global_step": 602295, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.923938274383545, "global_step": 602296, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.976676344871521, "global_step": 602297, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.8929535150527954, "global_step": 602298, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.077343463897705, "global_step": 602299, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.101383686065674, "global_step": 602300, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9840701818466187, "global_step": 602301, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.1712121963500977, "global_step": 602302, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9775974750518799, "global_step": 602303, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9617716073989868, "global_step": 602304, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0444276332855225, "global_step": 602305, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.031961441040039, "global_step": 602306, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.071110486984253, "global_step": 602307, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.081941604614258, "global_step": 602308, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9128605127334595, "global_step": 602309, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9649100303649902, "global_step": 602310, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9288034439086914, "global_step": 602311, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.042376756668091, "global_step": 602312, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0228326320648193, "global_step": 602313, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9998809099197388, "global_step": 602314, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0187413692474365, "global_step": 602315, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0630805492401123, "global_step": 602316, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0575830936431885, "global_step": 602317, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.001690626144409, "global_step": 602318, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0336198806762695, "global_step": 602319, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9792346954345703, "global_step": 602320, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0490403175354004, "global_step": 602321, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.1152966022491455, "global_step": 602322, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9805707931518555, "global_step": 602323, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.908482313156128, "global_step": 602324, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9103131294250488, "global_step": 602325, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.982804775238037, "global_step": 602326, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9218568801879883, "global_step": 602327, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9806318283081055, "global_step": 602328, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9520398378372192, "global_step": 602329, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0290439128875732, "global_step": 602330, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.944092869758606, "global_step": 602331, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9625517129898071, "global_step": 602332, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0266246795654297, "global_step": 602333, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.054669141769409, "global_step": 602334, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9744046926498413, "global_step": 602335, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0162501335144043, "global_step": 602336, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.045128107070923, "global_step": 602337, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.007477283477783, "global_step": 602338, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.035983085632324, "global_step": 602339, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.959578514099121, "global_step": 602340, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9818451404571533, "global_step": 602341, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0168235301971436, "global_step": 602342, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.063616991043091, "global_step": 602343, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0282962322235107, "global_step": 602344, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0940139293670654, "global_step": 602345, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.039304494857788, "global_step": 602346, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9918389320373535, "global_step": 602347, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.974423885345459, "global_step": 602348, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9574655294418335, "global_step": 602349, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9683518409729004, "global_step": 602350, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0192222595214844, "global_step": 602351, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.073624849319458, "global_step": 602352, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0509066581726074, "global_step": 602353, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.974051833152771, "global_step": 602354, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0357515811920166, "global_step": 602355, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.066873550415039, "global_step": 602356, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.076397657394409, "global_step": 602357, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0422654151916504, "global_step": 602358, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0373377799987793, "global_step": 602359, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9884978532791138, "global_step": 602360, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9719568490982056, "global_step": 602361, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.057711362838745, "global_step": 602362, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0414371490478516, "global_step": 602363, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.021235466003418, "global_step": 602364, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.964343786239624, "global_step": 602365, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0344526767730713, "global_step": 602366, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9480369091033936, "global_step": 602367, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9654924869537354, "global_step": 602368, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9765470027923584, "global_step": 602369, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0075647830963135, "global_step": 602370, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.027163028717041, "global_step": 602371, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.030770778656006, "global_step": 602372, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.060950517654419, "global_step": 602373, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9810665845870972, "global_step": 602374, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0026955604553223, "global_step": 602375, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9743698835372925, "global_step": 602376, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0148189067840576, "global_step": 602377, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.044771194458008, "global_step": 602378, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.161954879760742, "global_step": 602379, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0409607887268066, "global_step": 602380, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.066789150238037, "global_step": 602381, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9456093311309814, "global_step": 602382, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9756457805633545, "global_step": 602383, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.937173843383789, "global_step": 602384, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.06048846244812, "global_step": 602385, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9872838258743286, "global_step": 602386, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.00610089302063, "global_step": 602387, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.960519790649414, "global_step": 602388, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9999477863311768, "global_step": 602389, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.053006649017334, "global_step": 602390, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.037616491317749, "global_step": 602391, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.1002230644226074, "global_step": 602392, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.050086736679077, "global_step": 602393, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.986604928970337, "global_step": 602394, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0749258995056152, "global_step": 602395, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0101799964904785, "global_step": 602396, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0206034183502197, "global_step": 602397, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.03289532661438, "global_step": 602398, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.986418604850769, "global_step": 602399, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0567281246185303, "global_step": 602400, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.114530324935913, "global_step": 602401, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0446252822875977, "global_step": 602402, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0414834022521973, "global_step": 602403, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.01896333694458, "global_step": 602404, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0120768547058105, "global_step": 602405, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9932761192321777, "global_step": 602406, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.02710223197937, "global_step": 602407, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.097153902053833, "global_step": 602408, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.070995330810547, "global_step": 602409, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9363771677017212, "global_step": 602410, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9916203022003174, "global_step": 602411, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.946816325187683, "global_step": 602412, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9959954023361206, "global_step": 602413, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.005797863006592, "global_step": 602414, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.039215087890625, "global_step": 602415, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9935393333435059, "global_step": 602416, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.97879958152771, "global_step": 602417, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.123699188232422, "global_step": 602418, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.036684513092041, "global_step": 602419, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0847456455230713, "global_step": 602420, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.002695322036743, "global_step": 602421, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9410483837127686, "global_step": 602422, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0656657218933105, "global_step": 602423, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.056504011154175, "global_step": 602424, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.031092882156372, "global_step": 602425, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9904497861862183, "global_step": 602426, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9801652431488037, "global_step": 602427, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9637830257415771, "global_step": 602428, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.044154405593872, "global_step": 602429, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.024655818939209, "global_step": 602430, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9875767230987549, "global_step": 602431, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9586853981018066, "global_step": 602432, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0271027088165283, "global_step": 602433, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0506434440612793, "global_step": 602434, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9374984502792358, "global_step": 602435, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0058236122131348, "global_step": 602436, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0051708221435547, "global_step": 602437, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.027477979660034, "global_step": 602438, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0511467456817627, "global_step": 602439, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0715129375457764, "global_step": 602440, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.1359591484069824, "global_step": 602441, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.974175214767456, "global_step": 602442, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0090830326080322, "global_step": 602443, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.969988226890564, "global_step": 602444, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9773480892181396, "global_step": 602445, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9705171585083008, "global_step": 602446, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0436460971832275, "global_step": 602447, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9991227388381958, "global_step": 602448, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.945936918258667, "global_step": 602449, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.067129611968994, "global_step": 602450, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9386582374572754, "global_step": 602451, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0093398094177246, "global_step": 602452, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.93070387840271, "global_step": 602453, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.061131715774536, "global_step": 602454, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0642688274383545, "global_step": 602455, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0596396923065186, "global_step": 602456, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0232508182525635, "global_step": 602457, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9971750974655151, "global_step": 602458, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9924852848052979, "global_step": 602459, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0398964881896973, "global_step": 602460, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9855607748031616, "global_step": 602461, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0545310974121094, "global_step": 602462, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.093996286392212, "global_step": 602463, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.973657488822937, "global_step": 602464, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0458080768585205, "global_step": 602465, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9575389623641968, "global_step": 602466, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9681671857833862, "global_step": 602467, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0314931869506836, "global_step": 602468, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0709309577941895, "global_step": 602469, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0076053142547607, "global_step": 602470, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0516855716705322, "global_step": 602471, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9682458639144897, "global_step": 602472, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9925137758255005, "global_step": 602473, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.997045636177063, "global_step": 602474, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9598994255065918, "global_step": 602475, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.1095130443573, "global_step": 602476, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0684995651245117, "global_step": 602477, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9793949127197266, "global_step": 602478, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.126384973526001, "global_step": 602479, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.091456174850464, "global_step": 602480, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.03568434715271, "global_step": 602481, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9756642580032349, "global_step": 602482, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9964810609817505, "global_step": 602483, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0386788845062256, "global_step": 602484, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.00921893119812, "global_step": 602485, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9920762777328491, "global_step": 602486, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9895257949829102, "global_step": 602487, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.025580406188965, "global_step": 602488, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0996391773223877, "global_step": 602489, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0276525020599365, "global_step": 602490, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.055791139602661, "global_step": 602491, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.989614486694336, "global_step": 602492, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0003573894500732, "global_step": 602493, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0886967182159424, "global_step": 602494, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9415018558502197, "global_step": 602495, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0005905628204346, "global_step": 602496, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.015714645385742, "global_step": 602497, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.003901958465576, "global_step": 602498, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9687625169754028, "global_step": 602499, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.952954888343811, "global_step": 602500, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0431573390960693, "global_step": 602501, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.109877109527588, "global_step": 602502, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.013706922531128, "global_step": 602503, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.104966402053833, "global_step": 602504, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9946765899658203, "global_step": 602505, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9290300607681274, "global_step": 602506, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0366241931915283, "global_step": 602507, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.010225772857666, "global_step": 602508, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0173141956329346, "global_step": 602509, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.031191349029541, "global_step": 602510, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.029022216796875, "global_step": 602511, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.996286153793335, "global_step": 602512, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.036245346069336, "global_step": 602513, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9890984296798706, "global_step": 602514, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0649254322052, "global_step": 602515, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9468531608581543, "global_step": 602516, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9775679111480713, "global_step": 602517, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.021724224090576, "global_step": 602518, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.014472484588623, "global_step": 602519, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9255571365356445, "global_step": 602520, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9713298082351685, "global_step": 602521, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.8873960971832275, "global_step": 602522, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0731799602508545, "global_step": 602523, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9811265468597412, "global_step": 602524, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0217559337615967, "global_step": 602525, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9738845825195312, "global_step": 602526, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.998085618019104, "global_step": 602527, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.048100233078003, "global_step": 602528, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.079181671142578, "global_step": 602529, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.983974575996399, "global_step": 602530, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9668172597885132, "global_step": 602531, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.015631675720215, "global_step": 602532, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.996134877204895, "global_step": 602533, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9496561288833618, "global_step": 602534, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9463976621627808, "global_step": 602535, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0059425830841064, "global_step": 602536, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0727078914642334, "global_step": 602537, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.99257493019104, "global_step": 602538, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.995385766029358, "global_step": 602539, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.045358419418335, "global_step": 602540, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.015885353088379, "global_step": 602541, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0922954082489014, "global_step": 602542, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.01657772064209, "global_step": 602543, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9984360933303833, "global_step": 602544, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9843517541885376, "global_step": 602545, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.049137830734253, "global_step": 602546, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0632681846618652, "global_step": 602547, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0563066005706787, "global_step": 602548, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9940173625946045, "global_step": 602549, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0453734397888184, "global_step": 602550, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.008885145187378, "global_step": 602551, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0837018489837646, "global_step": 602552, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0062382221221924, "global_step": 602553, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.044050931930542, "global_step": 602554, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.058631658554077, "global_step": 602555, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9214893579483032, "global_step": 602556, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0469565391540527, "global_step": 602557, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.030775308609009, "global_step": 602558, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0541844367980957, "global_step": 602559, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9905940294265747, "global_step": 602560, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.945992350578308, "global_step": 602561, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0821845531463623, "global_step": 602562, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9896252155303955, "global_step": 602563, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.1078319549560547, "global_step": 602564, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0313456058502197, "global_step": 602565, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.1014270782470703, "global_step": 602566, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.031179189682007, "global_step": 602567, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9858168363571167, "global_step": 602568, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.016083240509033, "global_step": 602569, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0617666244506836, "global_step": 602570, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9416476488113403, "global_step": 602571, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9508143663406372, "global_step": 602572, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0234880447387695, "global_step": 602573, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9624407291412354, "global_step": 602574, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.049516439437866, "global_step": 602575, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9825491905212402, "global_step": 602576, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.910142183303833, "global_step": 602577, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0000996589660645, "global_step": 602578, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0323703289031982, "global_step": 602579, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.037870407104492, "global_step": 602580, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0383193492889404, "global_step": 602581, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9954757690429688, "global_step": 602582, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.970813274383545, "global_step": 602583, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.026005983352661, "global_step": 602584, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9635734558105469, "global_step": 602585, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.053657293319702, "global_step": 602586, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0558366775512695, "global_step": 602587, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.008876323699951, "global_step": 602588, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.8794236183166504, "global_step": 602589, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.000793695449829, "global_step": 602590, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.95735502243042, "global_step": 602591, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.07167911529541, "global_step": 602592, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.089298963546753, "global_step": 602593, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.005932331085205, "global_step": 602594, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.111680030822754, "global_step": 602595, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0854592323303223, "global_step": 602596, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.907570242881775, "global_step": 602597, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.1700704097747803, "global_step": 602598, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0232934951782227, "global_step": 602599, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9654659032821655, "global_step": 602600, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0277559757232666, "global_step": 602601, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0568385124206543, "global_step": 602602, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9522536993026733, "global_step": 602603, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.048285722732544, "global_step": 602604, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.024244546890259, "global_step": 602605, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9980709552764893, "global_step": 602606, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.019810676574707, "global_step": 602607, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0350847244262695, "global_step": 602608, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0037553310394287, "global_step": 602609, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0456631183624268, "global_step": 602610, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.960294485092163, "global_step": 602611, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0316054821014404, "global_step": 602612, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9842575788497925, "global_step": 602613, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0184741020202637, "global_step": 602614, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.010607957839966, "global_step": 602615, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9444305896759033, "global_step": 602616, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9666152000427246, "global_step": 602617, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.995050311088562, "global_step": 602618, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.995229959487915, "global_step": 602619, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0691285133361816, "global_step": 602620, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.03794002532959, "global_step": 602621, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9553838968276978, "global_step": 602622, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9586204290390015, "global_step": 602623, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9692718982696533, "global_step": 602624, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.993981122970581, "global_step": 602625, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9979352951049805, "global_step": 602626, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0279738903045654, "global_step": 602627, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0876662731170654, "global_step": 602628, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0434751510620117, "global_step": 602629, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0513200759887695, "global_step": 602630, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.072395086288452, "global_step": 602631, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.028031826019287, "global_step": 602632, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9136412143707275, "global_step": 602633, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9766777753829956, "global_step": 602634, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.989704966545105, "global_step": 602635, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0091183185577393, "global_step": 602636, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0012269020080566, "global_step": 602637, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.053947687149048, "global_step": 602638, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0560381412506104, "global_step": 602639, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.952606201171875, "global_step": 602640, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0298643112182617, "global_step": 602641, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0585591793060303, "global_step": 602642, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.041081428527832, "global_step": 602643, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0850367546081543, "global_step": 602644, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0511388778686523, "global_step": 602645, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0185844898223877, "global_step": 602646, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0798122882843018, "global_step": 602647, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9402254819869995, "global_step": 602648, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0674428939819336, "global_step": 602649, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9898004531860352, "global_step": 602650, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.974949598312378, "global_step": 602651, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9937541484832764, "global_step": 602652, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.018308162689209, "global_step": 602653, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.005790948867798, "global_step": 602654, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9895387887954712, "global_step": 602655, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.065702438354492, "global_step": 602656, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9629408121109009, "global_step": 602657, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.027033567428589, "global_step": 602658, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.011143684387207, "global_step": 602659, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9989923238754272, "global_step": 602660, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0131988525390625, "global_step": 602661, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0516271591186523, "global_step": 602662, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9476962089538574, "global_step": 602663, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0069029331207275, "global_step": 602664, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9990944862365723, "global_step": 602665, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.087585210800171, "global_step": 602666, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9825305938720703, "global_step": 602667, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9637651443481445, "global_step": 602668, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.93905508518219, "global_step": 602669, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0350534915924072, "global_step": 602670, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0326077938079834, "global_step": 602671, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9606544971466064, "global_step": 602672, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0401113033294678, "global_step": 602673, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0163919925689697, "global_step": 602674, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0359463691711426, "global_step": 602675, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.049089193344116, "global_step": 602676, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.063967704772949, "global_step": 602677, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9353272914886475, "global_step": 602678, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.96675705909729, "global_step": 602679, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0552101135253906, "global_step": 602680, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.977217674255371, "global_step": 602681, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.025747299194336, "global_step": 602682, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.074720621109009, "global_step": 602683, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9923957586288452, "global_step": 602684, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.012556552886963, "global_step": 602685, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0328917503356934, "global_step": 602686, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9592803716659546, "global_step": 602687, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.1059155464172363, "global_step": 602688, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0145533084869385, "global_step": 602689, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0617587566375732, "global_step": 602690, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9034227132797241, "global_step": 602691, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0347232818603516, "global_step": 602692, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0134055614471436, "global_step": 602693, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.995993733406067, "global_step": 602694, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9248164892196655, "global_step": 602695, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0018723011016846, "global_step": 602696, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0139591693878174, "global_step": 602697, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9585734605789185, "global_step": 602698, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.103325366973877, "global_step": 602699, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0067594051361084, "global_step": 602700, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0624771118164062, "global_step": 602701, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.983323574066162, "global_step": 602702, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.963198184967041, "global_step": 602703, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.8997575044631958, "global_step": 602704, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0578174591064453, "global_step": 602705, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0307538509368896, "global_step": 602706, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0238494873046875, "global_step": 602707, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.084075927734375, "global_step": 602708, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0328245162963867, "global_step": 602709, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.981420874595642, "global_step": 602710, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.056936502456665, "global_step": 602711, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.13674259185791, "global_step": 602712, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9797911643981934, "global_step": 602713, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0574538707733154, "global_step": 602714, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9583901166915894, "global_step": 602715, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9472272396087646, "global_step": 602716, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.032944440841675, "global_step": 602717, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.958834171295166, "global_step": 602718, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.005467414855957, "global_step": 602719, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9694234132766724, "global_step": 602720, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9822522401809692, "global_step": 602721, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0139920711517334, "global_step": 602722, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9557955265045166, "global_step": 602723, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0280964374542236, "global_step": 602724, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0444653034210205, "global_step": 602725, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0764002799987793, "global_step": 602726, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0476181507110596, "global_step": 602727, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0089852809906006, "global_step": 602728, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9868416786193848, "global_step": 602729, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0753490924835205, "global_step": 602730, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.00024676322937, "global_step": 602731, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9625259637832642, "global_step": 602732, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.000080108642578, "global_step": 602733, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9744863510131836, "global_step": 602734, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.8755282163619995, "global_step": 602735, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.02913498878479, "global_step": 602736, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.079981565475464, "global_step": 602737, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.017894983291626, "global_step": 602738, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0058236122131348, "global_step": 602739, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9624069929122925, "global_step": 602740, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0310862064361572, "global_step": 602741, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0331389904022217, "global_step": 602742, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9948632717132568, "global_step": 602743, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0073764324188232, "global_step": 602744, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.066096067428589, "global_step": 602745, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9876459836959839, "global_step": 602746, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.030078411102295, "global_step": 602747, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.000934362411499, "global_step": 602748, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.081552505493164, "global_step": 602749, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.076897382736206, "global_step": 602750, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0725433826446533, "global_step": 602751, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0120503902435303, "global_step": 602752, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0015666484832764, "global_step": 602753, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9441828727722168, "global_step": 602754, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.08034348487854, "global_step": 602755, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0798628330230713, "global_step": 602756, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.8367661237716675, "global_step": 602757, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.028334617614746, "global_step": 602758, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.026650905609131, "global_step": 602759, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0482282638549805, "global_step": 602760, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9972583055496216, "global_step": 602761, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0606839656829834, "global_step": 602762, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.086560010910034, "global_step": 602763, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0103955268859863, "global_step": 602764, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0199806690216064, "global_step": 602765, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.13832426071167, "global_step": 602766, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.006073474884033, "global_step": 602767, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.8961501121520996, "global_step": 602768, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9949079751968384, "global_step": 602769, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0315122604370117, "global_step": 602770, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0674331188201904, "global_step": 602771, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0414693355560303, "global_step": 602772, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9993234872817993, "global_step": 602773, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9978249073028564, "global_step": 602774, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.041595935821533, "global_step": 602775, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.126633882522583, "global_step": 602776, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9880256652832031, "global_step": 602777, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0250563621520996, "global_step": 602778, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0179688930511475, "global_step": 602779, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.015951156616211, "global_step": 602780, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0693609714508057, "global_step": 602781, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9716334342956543, "global_step": 602782, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0244901180267334, "global_step": 602783, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0028891563415527, "global_step": 602784, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0524821281433105, "global_step": 602785, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9699918031692505, "global_step": 602786, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9883391857147217, "global_step": 602787, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.067943572998047, "global_step": 602788, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9398484230041504, "global_step": 602789, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.022662878036499, "global_step": 602790, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9396687746047974, "global_step": 602791, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9714925289154053, "global_step": 602792, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.868032455444336, "global_step": 602793, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0205564498901367, "global_step": 602794, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9480646848678589, "global_step": 602795, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.002040386199951, "global_step": 602796, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.135608673095703, "global_step": 602797, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.002758026123047, "global_step": 602798, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0160951614379883, "global_step": 602799, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0400428771972656, "global_step": 602800, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9897091388702393, "global_step": 602801, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9441267251968384, "global_step": 602802, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9848284721374512, "global_step": 602803, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0248982906341553, "global_step": 602804, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0425362586975098, "global_step": 602805, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.021071195602417, "global_step": 602806, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0255813598632812, "global_step": 602807, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.964921236038208, "global_step": 602808, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.043532609939575, "global_step": 602809, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.079777479171753, "global_step": 602810, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0255849361419678, "global_step": 602811, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.993374228477478, "global_step": 602812, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9961495399475098, "global_step": 602813, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.983060359954834, "global_step": 602814, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0152575969696045, "global_step": 602815, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0591330528259277, "global_step": 602816, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.026124954223633, "global_step": 602817, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0207884311676025, "global_step": 602818, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9258642196655273, "global_step": 602819, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9737510681152344, "global_step": 602820, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.007758140563965, "global_step": 602821, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.1059279441833496, "global_step": 602822, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9038342237472534, "global_step": 602823, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.088393211364746, "global_step": 602824, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9325460195541382, "global_step": 602825, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0291244983673096, "global_step": 602826, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0171947479248047, "global_step": 602827, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9777289628982544, "global_step": 602828, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.048898696899414, "global_step": 602829, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0177764892578125, "global_step": 602830, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.8925881385803223, "global_step": 602831, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0050809383392334, "global_step": 602832, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9240405559539795, "global_step": 602833, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0809335708618164, "global_step": 602834, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.103877544403076, "global_step": 602835, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0075321197509766, "global_step": 602836, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.072554111480713, "global_step": 602837, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9273008108139038, "global_step": 602838, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.8928353786468506, "global_step": 602839, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0373644828796387, "global_step": 602840, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.030000925064087, "global_step": 602841, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0358030796051025, "global_step": 602842, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.076826810836792, "global_step": 602843, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0732522010803223, "global_step": 602844, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9831382036209106, "global_step": 602845, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.069890022277832, "global_step": 602846, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.036206007003784, "global_step": 602847, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.0006141662597656, "global_step": 602848, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9459998607635498, "global_step": 602849, "epoch": 971, "lr": 5e-05}
{"train_loss": 2.011925458908081, "global_step": 602850, "epoch": 971, "lr": 5e-05}
{"train_loss": 1.9680835008621216, "global_step": 602851, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0990896224975586, "global_step": 602852, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.021369218826294, "global_step": 602853, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9128097295761108, "global_step": 602854, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9559437036514282, "global_step": 602855, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.040494441986084, "global_step": 602856, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9425021409988403, "global_step": 602857, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0382463932037354, "global_step": 602858, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9146052598953247, "global_step": 602859, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0244462490081787, "global_step": 602860, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.96848726272583, "global_step": 602861, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.994925618171692, "global_step": 602862, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.8795498609542847, "global_step": 602863, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0434787273406982, "global_step": 602864, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0672194957733154, "global_step": 602865, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0921974182128906, "global_step": 602866, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0212013721466064, "global_step": 602867, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9294708967208862, "global_step": 602868, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.042140483856201, "global_step": 602869, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9376862049102783, "global_step": 602870, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.979875087738037, "global_step": 602871, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9496327638626099, "global_step": 602872, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0611512660980225, "global_step": 602873, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.949831247329712, "global_step": 602874, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.037709951400757, "global_step": 602875, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.056533098220825, "global_step": 602876, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9734009504318237, "global_step": 602877, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.988086462020874, "global_step": 602878, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.00553035736084, "global_step": 602879, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.061863660812378, "global_step": 602880, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0122945308685303, "global_step": 602881, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9880397319793701, "global_step": 602882, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9887012243270874, "global_step": 602883, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0090818405151367, "global_step": 602884, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.8837859630584717, "global_step": 602885, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.992322564125061, "global_step": 602886, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.057978630065918, "global_step": 602887, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.996880292892456, "global_step": 602888, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.8809542655944824, "global_step": 602889, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0214693546295166, "global_step": 602890, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.8994756937026978, "global_step": 602891, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9711127281188965, "global_step": 602892, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.991167426109314, "global_step": 602893, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.035384178161621, "global_step": 602894, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.027918577194214, "global_step": 602895, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.006080150604248, "global_step": 602896, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0457658767700195, "global_step": 602897, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.054863214492798, "global_step": 602898, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9855672121047974, "global_step": 602899, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0260531902313232, "global_step": 602900, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.074044704437256, "global_step": 602901, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.041378974914551, "global_step": 602902, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0175671577453613, "global_step": 602903, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9518322944641113, "global_step": 602904, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.092073917388916, "global_step": 602905, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.985116958618164, "global_step": 602906, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9913623332977295, "global_step": 602907, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0147013664245605, "global_step": 602908, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.017033815383911, "global_step": 602909, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0476527214050293, "global_step": 602910, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9894517660140991, "global_step": 602911, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9954144954681396, "global_step": 602912, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9377174377441406, "global_step": 602913, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.959464192390442, "global_step": 602914, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0796444416046143, "global_step": 602915, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0178253650665283, "global_step": 602916, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0284385681152344, "global_step": 602917, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0249645709991455, "global_step": 602918, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9871299266815186, "global_step": 602919, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.024059534072876, "global_step": 602920, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.8817981481552124, "global_step": 602921, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0064070224761963, "global_step": 602922, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.03369402885437, "global_step": 602923, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.02070951461792, "global_step": 602924, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.126682758331299, "global_step": 602925, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0950539112091064, "global_step": 602926, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1030445098876953, "global_step": 602927, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.060302495956421, "global_step": 602928, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.023160696029663, "global_step": 602929, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0397632122039795, "global_step": 602930, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0127995014190674, "global_step": 602931, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0526397228240967, "global_step": 602932, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0813939571380615, "global_step": 602933, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0460782051086426, "global_step": 602934, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.963277816772461, "global_step": 602935, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9928535223007202, "global_step": 602936, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0928871631622314, "global_step": 602937, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9313644170761108, "global_step": 602938, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9950354099273682, "global_step": 602939, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9865902662277222, "global_step": 602940, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9915486574172974, "global_step": 602941, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9860085248947144, "global_step": 602942, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.99622642993927, "global_step": 602943, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9784088134765625, "global_step": 602944, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9905580282211304, "global_step": 602945, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9426895380020142, "global_step": 602946, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9328268766403198, "global_step": 602947, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0127601623535156, "global_step": 602948, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9898632764816284, "global_step": 602949, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0152792930603027, "global_step": 602950, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0571415424346924, "global_step": 602951, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.034752130508423, "global_step": 602952, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9606786966323853, "global_step": 602953, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0702054500579834, "global_step": 602954, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.070042848587036, "global_step": 602955, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9797896146774292, "global_step": 602956, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.000763177871704, "global_step": 602957, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0584304332733154, "global_step": 602958, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.056568145751953, "global_step": 602959, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0042335987091064, "global_step": 602960, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.070560932159424, "global_step": 602961, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9259917736053467, "global_step": 602962, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.96331787109375, "global_step": 602963, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.005500316619873, "global_step": 602964, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.931780219078064, "global_step": 602965, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.001835584640503, "global_step": 602966, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0652642250061035, "global_step": 602967, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.017263650894165, "global_step": 602968, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1048102378845215, "global_step": 602969, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.97703218460083, "global_step": 602970, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.993618130683899, "global_step": 602971, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0059103965759277, "global_step": 602972, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9501893520355225, "global_step": 602973, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.011183977127075, "global_step": 602974, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0058908462524414, "global_step": 602975, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9473354816436768, "global_step": 602976, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9966267347335815, "global_step": 602977, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.984166145324707, "global_step": 602978, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9992976188659668, "global_step": 602979, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.8954559564590454, "global_step": 602980, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.058626651763916, "global_step": 602981, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.050415515899658, "global_step": 602982, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0936710834503174, "global_step": 602983, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.002639055252075, "global_step": 602984, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9916634559631348, "global_step": 602985, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9475154876708984, "global_step": 602986, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9952846765518188, "global_step": 602987, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9722652435302734, "global_step": 602988, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0075650215148926, "global_step": 602989, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9829590320587158, "global_step": 602990, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.996785283088684, "global_step": 602991, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1080241203308105, "global_step": 602992, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9820939302444458, "global_step": 602993, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0538501739501953, "global_step": 602994, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9683489799499512, "global_step": 602995, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.981115698814392, "global_step": 602996, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9398032426834106, "global_step": 602997, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.089081048965454, "global_step": 602998, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9853395223617554, "global_step": 602999, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0589427947998047, "global_step": 603000, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0000627040863037, "global_step": 603001, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9809494018554688, "global_step": 603002, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9611879587173462, "global_step": 603003, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9392986297607422, "global_step": 603004, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.031466007232666, "global_step": 603005, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9965229034423828, "global_step": 603006, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1136536598205566, "global_step": 603007, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9899243116378784, "global_step": 603008, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0823559761047363, "global_step": 603009, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.033489942550659, "global_step": 603010, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0520541667938232, "global_step": 603011, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9452691078186035, "global_step": 603012, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.03456974029541, "global_step": 603013, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0240561962127686, "global_step": 603014, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.071855306625366, "global_step": 603015, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9618431329727173, "global_step": 603016, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.011756181716919, "global_step": 603017, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0416102409362793, "global_step": 603018, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0209336280822754, "global_step": 603019, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.048755168914795, "global_step": 603020, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.979788899421692, "global_step": 603021, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0769152641296387, "global_step": 603022, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0032124519348145, "global_step": 603023, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0124528408050537, "global_step": 603024, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9881807565689087, "global_step": 603025, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.03070330619812, "global_step": 603026, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9679068326950073, "global_step": 603027, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.019298791885376, "global_step": 603028, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9766600131988525, "global_step": 603029, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.070709705352783, "global_step": 603030, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.057170867919922, "global_step": 603031, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.044462203979492, "global_step": 603032, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0591890811920166, "global_step": 603033, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.054100275039673, "global_step": 603034, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.99019193649292, "global_step": 603035, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0634379386901855, "global_step": 603036, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0694143772125244, "global_step": 603037, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0008299350738525, "global_step": 603038, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.980646014213562, "global_step": 603039, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.01031756401062, "global_step": 603040, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0420637130737305, "global_step": 603041, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1387946605682373, "global_step": 603042, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.049316167831421, "global_step": 603043, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0587759017944336, "global_step": 603044, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9364628791809082, "global_step": 603045, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0168893337249756, "global_step": 603046, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.96311354637146, "global_step": 603047, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9273340702056885, "global_step": 603048, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0859100818634033, "global_step": 603049, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.105560064315796, "global_step": 603050, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9665719270706177, "global_step": 603051, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0126307010650635, "global_step": 603052, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0254509449005127, "global_step": 603053, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0816164016723633, "global_step": 603054, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9638969898223877, "global_step": 603055, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.057276725769043, "global_step": 603056, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9561480283737183, "global_step": 603057, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0796151161193848, "global_step": 603058, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.070321798324585, "global_step": 603059, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9697294235229492, "global_step": 603060, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0230069160461426, "global_step": 603061, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9739192724227905, "global_step": 603062, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9917501211166382, "global_step": 603063, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0564498901367188, "global_step": 603064, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0452940464019775, "global_step": 603065, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9480443000793457, "global_step": 603066, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.981949806213379, "global_step": 603067, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.971587896347046, "global_step": 603068, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0204710960388184, "global_step": 603069, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.980954885482788, "global_step": 603070, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.037066698074341, "global_step": 603071, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0436038970947266, "global_step": 603072, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9243502616882324, "global_step": 603073, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9576231241226196, "global_step": 603074, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9722543954849243, "global_step": 603075, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.023192882537842, "global_step": 603076, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.932360291481018, "global_step": 603077, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.003810405731201, "global_step": 603078, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.967236876487732, "global_step": 603079, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9610214233398438, "global_step": 603080, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0717694759368896, "global_step": 603081, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.012514352798462, "global_step": 603082, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.020923614501953, "global_step": 603083, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9867768287658691, "global_step": 603084, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0567092895507812, "global_step": 603085, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.954245924949646, "global_step": 603086, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.012425422668457, "global_step": 603087, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.978751301765442, "global_step": 603088, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.094027519226074, "global_step": 603089, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.019643545150757, "global_step": 603090, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0056843757629395, "global_step": 603091, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0514044761657715, "global_step": 603092, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9787639379501343, "global_step": 603093, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1395983695983887, "global_step": 603094, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0265138149261475, "global_step": 603095, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1043484210968018, "global_step": 603096, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9899157285690308, "global_step": 603097, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.048532009124756, "global_step": 603098, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9969533681869507, "global_step": 603099, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9958598613739014, "global_step": 603100, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0473194122314453, "global_step": 603101, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9961165189743042, "global_step": 603102, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9401429891586304, "global_step": 603103, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0433542728424072, "global_step": 603104, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.01242733001709, "global_step": 603105, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0332722663879395, "global_step": 603106, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9890819787979126, "global_step": 603107, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0015347003936768, "global_step": 603108, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.028622627258301, "global_step": 603109, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0166115760803223, "global_step": 603110, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0570313930511475, "global_step": 603111, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9842370748519897, "global_step": 603112, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9600192308425903, "global_step": 603113, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.980088233947754, "global_step": 603114, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0215256214141846, "global_step": 603115, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0132625102996826, "global_step": 603116, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0155322551727295, "global_step": 603117, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9812856912612915, "global_step": 603118, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9390519857406616, "global_step": 603119, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.025923728942871, "global_step": 603120, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0693132877349854, "global_step": 603121, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9602932929992676, "global_step": 603122, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9980976581573486, "global_step": 603123, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0161287784576416, "global_step": 603124, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.996799349784851, "global_step": 603125, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9459211826324463, "global_step": 603126, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9549251794815063, "global_step": 603127, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.066108465194702, "global_step": 603128, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.009089708328247, "global_step": 603129, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0507214069366455, "global_step": 603130, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.000469446182251, "global_step": 603131, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.05926251411438, "global_step": 603132, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9846880435943604, "global_step": 603133, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0545811653137207, "global_step": 603134, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9846830368041992, "global_step": 603135, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.00616717338562, "global_step": 603136, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9796520471572876, "global_step": 603137, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0294270515441895, "global_step": 603138, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0829033851623535, "global_step": 603139, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9931137561798096, "global_step": 603140, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9905288219451904, "global_step": 603141, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9885152578353882, "global_step": 603142, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0545623302459717, "global_step": 603143, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9980803728103638, "global_step": 603144, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.005275011062622, "global_step": 603145, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9889414310455322, "global_step": 603146, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0446746349334717, "global_step": 603147, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9640499353408813, "global_step": 603148, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1343467235565186, "global_step": 603149, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9994925260543823, "global_step": 603150, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.073286533355713, "global_step": 603151, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.093668222427368, "global_step": 603152, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.966398000717163, "global_step": 603153, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9792802333831787, "global_step": 603154, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9839905500411987, "global_step": 603155, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9745426177978516, "global_step": 603156, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.046647310256958, "global_step": 603157, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0163865089416504, "global_step": 603158, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0404982566833496, "global_step": 603159, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.027980089187622, "global_step": 603160, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.030689239501953, "global_step": 603161, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.00823974609375, "global_step": 603162, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.071662425994873, "global_step": 603163, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0514209270477295, "global_step": 603164, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.008101463317871, "global_step": 603165, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0171327590942383, "global_step": 603166, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9467015266418457, "global_step": 603167, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9727500677108765, "global_step": 603168, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9324852228164673, "global_step": 603169, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.000091552734375, "global_step": 603170, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9957331418991089, "global_step": 603171, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9884099960327148, "global_step": 603172, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9375909566879272, "global_step": 603173, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9658869504928589, "global_step": 603174, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.01682186126709, "global_step": 603175, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.993955135345459, "global_step": 603176, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9348549842834473, "global_step": 603177, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.002902030944824, "global_step": 603178, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9887622594833374, "global_step": 603179, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.966315507888794, "global_step": 603180, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.095179557800293, "global_step": 603181, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0869414806365967, "global_step": 603182, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9736218452453613, "global_step": 603183, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.006622314453125, "global_step": 603184, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.020944118499756, "global_step": 603185, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9792017936706543, "global_step": 603186, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9868006706237793, "global_step": 603187, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9634120464324951, "global_step": 603188, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.01334810256958, "global_step": 603189, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9895732402801514, "global_step": 603190, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.046630382537842, "global_step": 603191, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9902185201644897, "global_step": 603192, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0589704513549805, "global_step": 603193, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.029233455657959, "global_step": 603194, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0304336547851562, "global_step": 603195, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.021404266357422, "global_step": 603196, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9569562673568726, "global_step": 603197, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9644798040390015, "global_step": 603198, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9750572443008423, "global_step": 603199, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9141408205032349, "global_step": 603200, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0715420246124268, "global_step": 603201, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1179208755493164, "global_step": 603202, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9868425130844116, "global_step": 603203, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0361170768737793, "global_step": 603204, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.961783766746521, "global_step": 603205, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.060276508331299, "global_step": 603206, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.009016513824463, "global_step": 603207, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.963938593864441, "global_step": 603208, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0664784908294678, "global_step": 603209, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1002633571624756, "global_step": 603210, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9945652484893799, "global_step": 603211, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0780560970306396, "global_step": 603212, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9874436855316162, "global_step": 603213, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0390377044677734, "global_step": 603214, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0152344703674316, "global_step": 603215, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9389691352844238, "global_step": 603216, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.948846459388733, "global_step": 603217, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9539424180984497, "global_step": 603218, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.027028799057007, "global_step": 603219, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9570156335830688, "global_step": 603220, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.037569999694824, "global_step": 603221, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9932804107666016, "global_step": 603222, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.122968912124634, "global_step": 603223, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9866092205047607, "global_step": 603224, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0189154148101807, "global_step": 603225, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9630240201950073, "global_step": 603226, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9414801597595215, "global_step": 603227, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0378546714782715, "global_step": 603228, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.081296682357788, "global_step": 603229, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9777066707611084, "global_step": 603230, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0624279975891113, "global_step": 603231, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.033376455307007, "global_step": 603232, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9934992790222168, "global_step": 603233, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0491578578948975, "global_step": 603234, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0424015522003174, "global_step": 603235, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.054318904876709, "global_step": 603236, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0661349296569824, "global_step": 603237, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0191640853881836, "global_step": 603238, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0171284675598145, "global_step": 603239, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0091776847839355, "global_step": 603240, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0594892501831055, "global_step": 603241, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1127562522888184, "global_step": 603242, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.051767349243164, "global_step": 603243, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9673441648483276, "global_step": 603244, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.056215763092041, "global_step": 603245, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0483486652374268, "global_step": 603246, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.895098090171814, "global_step": 603247, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0927557945251465, "global_step": 603248, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9990646839141846, "global_step": 603249, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0542423725128174, "global_step": 603250, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0659053325653076, "global_step": 603251, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.000441789627075, "global_step": 603252, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.030930995941162, "global_step": 603253, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0901942253112793, "global_step": 603254, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0228464603424072, "global_step": 603255, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9746469259262085, "global_step": 603256, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0075600147247314, "global_step": 603257, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9817454814910889, "global_step": 603258, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.037809133529663, "global_step": 603259, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9639906883239746, "global_step": 603260, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9678409099578857, "global_step": 603261, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9387328624725342, "global_step": 603262, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9745749235153198, "global_step": 603263, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0911977291107178, "global_step": 603264, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.981124997138977, "global_step": 603265, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9786549806594849, "global_step": 603266, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0596725940704346, "global_step": 603267, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9663513898849487, "global_step": 603268, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9545284509658813, "global_step": 603269, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0048258304595947, "global_step": 603270, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.8970786333084106, "global_step": 603271, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9815753698349, "global_step": 603272, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1156005859375, "global_step": 603273, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0338685512542725, "global_step": 603274, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.149282932281494, "global_step": 603275, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9836467504501343, "global_step": 603276, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0352702140808105, "global_step": 603277, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0152316093444824, "global_step": 603278, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.077558755874634, "global_step": 603279, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0633349418640137, "global_step": 603280, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.046396255493164, "global_step": 603281, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9634885787963867, "global_step": 603282, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0524561405181885, "global_step": 603283, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0175211429595947, "global_step": 603284, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.064002275466919, "global_step": 603285, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0630974769592285, "global_step": 603286, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9593851566314697, "global_step": 603287, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9501116275787354, "global_step": 603288, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9847358465194702, "global_step": 603289, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.974430799484253, "global_step": 603290, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.070594549179077, "global_step": 603291, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0662119388580322, "global_step": 603292, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0224921703338623, "global_step": 603293, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0137484073638916, "global_step": 603294, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0194356441497803, "global_step": 603295, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.018519878387451, "global_step": 603296, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.040553569793701, "global_step": 603297, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.021573543548584, "global_step": 603298, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9664220809936523, "global_step": 603299, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.963787317276001, "global_step": 603300, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9913649559020996, "global_step": 603301, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0980823040008545, "global_step": 603302, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.063431739807129, "global_step": 603303, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.045274496078491, "global_step": 603304, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.055986166000366, "global_step": 603305, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0313286781311035, "global_step": 603306, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.920031189918518, "global_step": 603307, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1046175956726074, "global_step": 603308, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0677502155303955, "global_step": 603309, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9706484079360962, "global_step": 603310, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0377204418182373, "global_step": 603311, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.971274495124817, "global_step": 603312, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.986435890197754, "global_step": 603313, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.082301378250122, "global_step": 603314, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.04841947555542, "global_step": 603315, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.03629207611084, "global_step": 603316, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1039998531341553, "global_step": 603317, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0543720722198486, "global_step": 603318, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0153040885925293, "global_step": 603319, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0005509853363037, "global_step": 603320, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0478689670562744, "global_step": 603321, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9711215496063232, "global_step": 603322, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.011279344558716, "global_step": 603323, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9564310312271118, "global_step": 603324, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9120670557022095, "global_step": 603325, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0141963958740234, "global_step": 603326, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.982739806175232, "global_step": 603327, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0090742111206055, "global_step": 603328, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.987646460533142, "global_step": 603329, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1201653480529785, "global_step": 603330, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0230352878570557, "global_step": 603331, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.036964178085327, "global_step": 603332, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0749926567077637, "global_step": 603333, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9376219511032104, "global_step": 603334, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.037075996398926, "global_step": 603335, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0539848804473877, "global_step": 603336, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.974069595336914, "global_step": 603337, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9811509847640991, "global_step": 603338, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0148518085479736, "global_step": 603339, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.058392286300659, "global_step": 603340, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9824577569961548, "global_step": 603341, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0185887813568115, "global_step": 603342, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1249077320098877, "global_step": 603343, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0143611431121826, "global_step": 603344, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.013254404067993, "global_step": 603345, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9046521186828613, "global_step": 603346, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.032370090484619, "global_step": 603347, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.042840003967285, "global_step": 603348, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.140900135040283, "global_step": 603349, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9640214443206787, "global_step": 603350, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9402836561203003, "global_step": 603351, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.020787000656128, "global_step": 603352, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0037190914154053, "global_step": 603353, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9586522579193115, "global_step": 603354, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9854387044906616, "global_step": 603355, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.982362151145935, "global_step": 603356, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9883421659469604, "global_step": 603357, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9538394212722778, "global_step": 603358, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.930105209350586, "global_step": 603359, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0451276302337646, "global_step": 603360, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9774147272109985, "global_step": 603361, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1164205074310303, "global_step": 603362, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.012859582901001, "global_step": 603363, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9855620861053467, "global_step": 603364, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.010148048400879, "global_step": 603365, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.963012933731079, "global_step": 603366, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.035012722015381, "global_step": 603367, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0017380714416504, "global_step": 603368, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9466856718063354, "global_step": 603369, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.091552972793579, "global_step": 603370, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.053471088409424, "global_step": 603371, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0957770347595215, "global_step": 603372, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.035963773727417, "global_step": 603373, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9874053001403809, "global_step": 603374, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9806458950042725, "global_step": 603375, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.05413818359375, "global_step": 603376, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.080904006958008, "global_step": 603377, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0190491676330566, "global_step": 603378, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9544554948806763, "global_step": 603379, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.983220100402832, "global_step": 603380, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0621695518493652, "global_step": 603381, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.022916078567505, "global_step": 603382, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.004711151123047, "global_step": 603383, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9551905393600464, "global_step": 603384, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.034654140472412, "global_step": 603385, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.989362359046936, "global_step": 603386, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0155715942382812, "global_step": 603387, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9588931798934937, "global_step": 603388, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9715330600738525, "global_step": 603389, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0457937717437744, "global_step": 603390, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0407052040100098, "global_step": 603391, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9764344692230225, "global_step": 603392, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0581419467926025, "global_step": 603393, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0253748893737793, "global_step": 603394, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.056461811065674, "global_step": 603395, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.001438856124878, "global_step": 603396, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0012619495391846, "global_step": 603397, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.090019941329956, "global_step": 603398, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.955128788948059, "global_step": 603399, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.926993727684021, "global_step": 603400, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.007842779159546, "global_step": 603401, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9998211860656738, "global_step": 603402, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9434870481491089, "global_step": 603403, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.061176300048828, "global_step": 603404, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0293049812316895, "global_step": 603405, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9759883880615234, "global_step": 603406, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0503861904144287, "global_step": 603407, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9628535509109497, "global_step": 603408, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9926356077194214, "global_step": 603409, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.130523681640625, "global_step": 603410, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9154783487319946, "global_step": 603411, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0368564128875732, "global_step": 603412, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.019695997238159, "global_step": 603413, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9319316148757935, "global_step": 603414, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.00981068611145, "global_step": 603415, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0258944034576416, "global_step": 603416, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0556764602661133, "global_step": 603417, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0527422428131104, "global_step": 603418, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.989087462425232, "global_step": 603419, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.949062705039978, "global_step": 603420, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.040192127227783, "global_step": 603421, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.003709077835083, "global_step": 603422, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9473140239715576, "global_step": 603423, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9667786359786987, "global_step": 603424, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0121591091156006, "global_step": 603425, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0465002059936523, "global_step": 603426, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.073066234588623, "global_step": 603427, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0052146911621094, "global_step": 603428, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.026756525039673, "global_step": 603429, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0480668544769287, "global_step": 603430, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9885969161987305, "global_step": 603431, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.042677402496338, "global_step": 603432, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.023642063140869, "global_step": 603433, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0500378608703613, "global_step": 603434, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9394656419754028, "global_step": 603435, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.060368061065674, "global_step": 603436, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.065218925476074, "global_step": 603437, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0735161304473877, "global_step": 603438, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9998220205307007, "global_step": 603439, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0329906940460205, "global_step": 603440, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9927117824554443, "global_step": 603441, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9936997890472412, "global_step": 603442, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9956884384155273, "global_step": 603443, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.026031017303467, "global_step": 603444, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0201807022094727, "global_step": 603445, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0573062896728516, "global_step": 603446, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.056546449661255, "global_step": 603447, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.032594680786133, "global_step": 603448, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0095410346984863, "global_step": 603449, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.008443593978882, "global_step": 603450, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0042824745178223, "global_step": 603451, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.028313398361206, "global_step": 603452, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9899202585220337, "global_step": 603453, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0102553367614746, "global_step": 603454, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.987514615058899, "global_step": 603455, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9826221466064453, "global_step": 603456, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9712387323379517, "global_step": 603457, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.042948007583618, "global_step": 603458, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.030611038208008, "global_step": 603459, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.072111129760742, "global_step": 603460, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.009359359741211, "global_step": 603461, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.021477460861206, "global_step": 603462, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9865772724151611, "global_step": 603463, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0141375064849854, "global_step": 603464, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.938163161277771, "global_step": 603465, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9604605436325073, "global_step": 603466, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9433835744857788, "global_step": 603467, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0119102001190186, "global_step": 603468, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0418214797973633, "global_step": 603469, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0516631603240967, "global_step": 603470, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.047861099243164, "global_step": 603471, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0217838287353516, "global_step": 603472, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9548510313034058, "global_step": 603473, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.052137851715088, "global_step": 603474, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9699727296829224, "global_step": 603475, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.980261206626892, "global_step": 603476, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.012380599975586, "global_step": 603477, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.01764178276062, "global_step": 603478, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.114692211151123, "global_step": 603479, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.021216869354248, "global_step": 603480, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0003662109375, "global_step": 603481, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9480926990509033, "global_step": 603482, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.051541566848755, "global_step": 603483, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9803588390350342, "global_step": 603484, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.011267900466919, "global_step": 603485, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.062818765640259, "global_step": 603486, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0531504154205322, "global_step": 603487, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0465850830078125, "global_step": 603488, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.985735535621643, "global_step": 603489, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9511228799819946, "global_step": 603490, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9655821323394775, "global_step": 603491, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9913444519042969, "global_step": 603492, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.952571988105774, "global_step": 603493, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.003156900405884, "global_step": 603494, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9691015481948853, "global_step": 603495, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.002840995788574, "global_step": 603496, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9799213409423828, "global_step": 603497, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9564611911773682, "global_step": 603498, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0479512214660645, "global_step": 603499, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.8750046491622925, "global_step": 603500, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0159270763397217, "global_step": 603501, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9661670923233032, "global_step": 603502, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0326762199401855, "global_step": 603503, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.966565489768982, "global_step": 603504, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9991501569747925, "global_step": 603505, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9601476192474365, "global_step": 603506, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.012495517730713, "global_step": 603507, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9970382452011108, "global_step": 603508, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9617522954940796, "global_step": 603509, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0225369930267334, "global_step": 603510, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.099682569503784, "global_step": 603511, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.979851245880127, "global_step": 603512, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9262580871582031, "global_step": 603513, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9995877742767334, "global_step": 603514, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9403785467147827, "global_step": 603515, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9734200239181519, "global_step": 603516, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.059597969055176, "global_step": 603517, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9943675994873047, "global_step": 603518, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0107665061950684, "global_step": 603519, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.067584753036499, "global_step": 603520, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.051417589187622, "global_step": 603521, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.028982400894165, "global_step": 603522, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0150668621063232, "global_step": 603523, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0067780017852783, "global_step": 603524, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9994027614593506, "global_step": 603525, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.109962224960327, "global_step": 603526, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9813573360443115, "global_step": 603527, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9615108966827393, "global_step": 603528, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.020318031311035, "global_step": 603529, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0124316215515137, "global_step": 603530, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9915345907211304, "global_step": 603531, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0043065547943115, "global_step": 603532, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.995335340499878, "global_step": 603533, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.979792594909668, "global_step": 603534, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9942013025283813, "global_step": 603535, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.005763530731201, "global_step": 603536, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0087227821350098, "global_step": 603537, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.01751971244812, "global_step": 603538, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.026275634765625, "global_step": 603539, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9390686750411987, "global_step": 603540, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0340559482574463, "global_step": 603541, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0503175258636475, "global_step": 603542, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9832825660705566, "global_step": 603543, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.007904529571533, "global_step": 603544, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0570425987243652, "global_step": 603545, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9912612438201904, "global_step": 603546, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9815913438796997, "global_step": 603547, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9669585227966309, "global_step": 603548, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.976893424987793, "global_step": 603549, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.046804428100586, "global_step": 603550, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.060014009475708, "global_step": 603551, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0115387439727783, "global_step": 603552, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9279975891113281, "global_step": 603553, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9527177810668945, "global_step": 603554, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.950404167175293, "global_step": 603555, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.04109787940979, "global_step": 603556, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9486740827560425, "global_step": 603557, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0362589359283447, "global_step": 603558, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.955758810043335, "global_step": 603559, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0430049896240234, "global_step": 603560, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0713865756988525, "global_step": 603561, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.961287021636963, "global_step": 603562, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.995496392250061, "global_step": 603563, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9858896732330322, "global_step": 603564, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0436482429504395, "global_step": 603565, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9884692430496216, "global_step": 603566, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0160868167877197, "global_step": 603567, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.094740152359009, "global_step": 603568, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.999287486076355, "global_step": 603569, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9862147569656372, "global_step": 603570, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9686279296875, "global_step": 603571, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0232672691345215, "global_step": 603572, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.026514768600464, "global_step": 603573, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0564610958099365, "global_step": 603574, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9542622566223145, "global_step": 603575, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9987906217575073, "global_step": 603576, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9898759126663208, "global_step": 603577, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9613966941833496, "global_step": 603578, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.015157699584961, "global_step": 603579, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1041038036346436, "global_step": 603580, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9723972082138062, "global_step": 603581, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9861496686935425, "global_step": 603582, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9368641376495361, "global_step": 603583, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9790140390396118, "global_step": 603584, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0338664054870605, "global_step": 603585, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.022813081741333, "global_step": 603586, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0396487712860107, "global_step": 603587, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9750112295150757, "global_step": 603588, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0331695079803467, "global_step": 603589, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0010554790496826, "global_step": 603590, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9695361852645874, "global_step": 603591, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9846917390823364, "global_step": 603592, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0162839889526367, "global_step": 603593, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0069329738616943, "global_step": 603594, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.063039541244507, "global_step": 603595, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.098978042602539, "global_step": 603596, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0804405212402344, "global_step": 603597, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1079490184783936, "global_step": 603598, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0631232261657715, "global_step": 603599, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.020009756088257, "global_step": 603600, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.976096272468567, "global_step": 603601, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0280590057373047, "global_step": 603602, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0080642700195312, "global_step": 603603, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.10107684135437, "global_step": 603604, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0448389053344727, "global_step": 603605, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.016808032989502, "global_step": 603606, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.043349266052246, "global_step": 603607, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9429789781570435, "global_step": 603608, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9612072706222534, "global_step": 603609, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0022525787353516, "global_step": 603610, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.019322156906128, "global_step": 603611, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0671238899230957, "global_step": 603612, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9905825853347778, "global_step": 603613, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9741061925888062, "global_step": 603614, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.078360080718994, "global_step": 603615, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.935561180114746, "global_step": 603616, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9111024141311646, "global_step": 603617, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.014674186706543, "global_step": 603618, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9523942470550537, "global_step": 603619, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.944999098777771, "global_step": 603620, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0551609992980957, "global_step": 603621, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0597922801971436, "global_step": 603622, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.048402786254883, "global_step": 603623, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.016660213470459, "global_step": 603624, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.040353298187256, "global_step": 603625, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.022379159927368, "global_step": 603626, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0094778537750244, "global_step": 603627, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0526223182678223, "global_step": 603628, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0036561489105225, "global_step": 603629, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.987997055053711, "global_step": 603630, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0272324085235596, "global_step": 603631, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9817123413085938, "global_step": 603632, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.033614158630371, "global_step": 603633, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.942091941833496, "global_step": 603634, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9849268198013306, "global_step": 603635, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9373321533203125, "global_step": 603636, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.09637188911438, "global_step": 603637, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.946615219116211, "global_step": 603638, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9436930418014526, "global_step": 603639, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0559186935424805, "global_step": 603640, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0426061153411865, "global_step": 603641, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0220329761505127, "global_step": 603642, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.988633155822754, "global_step": 603643, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.040130376815796, "global_step": 603644, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0052895545959473, "global_step": 603645, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.987305760383606, "global_step": 603646, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0896992683410645, "global_step": 603647, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9700888395309448, "global_step": 603648, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.047173261642456, "global_step": 603649, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.010514497756958, "global_step": 603650, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.004577875137329, "global_step": 603651, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9991862773895264, "global_step": 603652, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9830468893051147, "global_step": 603653, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0528829097747803, "global_step": 603654, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.981346607208252, "global_step": 603655, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.044753074645996, "global_step": 603656, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9671704769134521, "global_step": 603657, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0508406162261963, "global_step": 603658, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0350403785705566, "global_step": 603659, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9460095167160034, "global_step": 603660, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9147708415985107, "global_step": 603661, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.063863515853882, "global_step": 603662, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.051811695098877, "global_step": 603663, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0472869873046875, "global_step": 603664, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.040334939956665, "global_step": 603665, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0188145637512207, "global_step": 603666, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0352842807769775, "global_step": 603667, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.033738851547241, "global_step": 603668, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0595004558563232, "global_step": 603669, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.006682872772217, "global_step": 603670, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9933966398239136, "global_step": 603671, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.039364814758301, "global_step": 603672, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9972714185714722, "global_step": 603673, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.036090850830078, "global_step": 603674, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9421621561050415, "global_step": 603675, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9949005842208862, "global_step": 603676, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9889041185379028, "global_step": 603677, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0544750690460205, "global_step": 603678, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0056350231170654, "global_step": 603679, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.025346279144287, "global_step": 603680, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9890464544296265, "global_step": 603681, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.053494453430176, "global_step": 603682, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.065178394317627, "global_step": 603683, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.014354705810547, "global_step": 603684, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.035520315170288, "global_step": 603685, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0179388523101807, "global_step": 603686, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0412185192108154, "global_step": 603687, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0805037021636963, "global_step": 603688, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.038590669631958, "global_step": 603689, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.999537467956543, "global_step": 603690, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1229233741760254, "global_step": 603691, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.970076084136963, "global_step": 603692, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0468645095825195, "global_step": 603693, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.016909122467041, "global_step": 603694, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.018111228942871, "global_step": 603695, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9614357948303223, "global_step": 603696, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.047914505004883, "global_step": 603697, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9753739833831787, "global_step": 603698, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0489468574523926, "global_step": 603699, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9761556386947632, "global_step": 603700, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9795246124267578, "global_step": 603701, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0067479610443115, "global_step": 603702, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.08709716796875, "global_step": 603703, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9723436832427979, "global_step": 603704, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.992879033088684, "global_step": 603705, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9765164852142334, "global_step": 603706, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0777955055236816, "global_step": 603707, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0183935165405273, "global_step": 603708, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.029287338256836, "global_step": 603709, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0424232482910156, "global_step": 603710, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0226638317108154, "global_step": 603711, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.950901746749878, "global_step": 603712, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0408692359924316, "global_step": 603713, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.976645827293396, "global_step": 603714, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.042607307434082, "global_step": 603715, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.006923198699951, "global_step": 603716, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9814053773880005, "global_step": 603717, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0286865234375, "global_step": 603718, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0122053623199463, "global_step": 603719, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0663437843322754, "global_step": 603720, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9739559888839722, "global_step": 603721, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0095677375793457, "global_step": 603722, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.079108238220215, "global_step": 603723, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.084484338760376, "global_step": 603724, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9737192392349243, "global_step": 603725, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.962628722190857, "global_step": 603726, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.014735221862793, "global_step": 603727, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0405073165893555, "global_step": 603728, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.097290515899658, "global_step": 603729, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.094510316848755, "global_step": 603730, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9874401092529297, "global_step": 603731, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0003647804260254, "global_step": 603732, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.035996437072754, "global_step": 603733, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9730304479599, "global_step": 603734, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9213670492172241, "global_step": 603735, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.037747859954834, "global_step": 603736, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0178892612457275, "global_step": 603737, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0869498252868652, "global_step": 603738, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0268633365631104, "global_step": 603739, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.031481981277466, "global_step": 603740, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0745913982391357, "global_step": 603741, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.105520248413086, "global_step": 603742, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0586063861846924, "global_step": 603743, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.129067897796631, "global_step": 603744, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0388500690460205, "global_step": 603745, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.993431568145752, "global_step": 603746, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0406439304351807, "global_step": 603747, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0570521354675293, "global_step": 603748, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9781588315963745, "global_step": 603749, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9885481595993042, "global_step": 603750, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.094754695892334, "global_step": 603751, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0212454795837402, "global_step": 603752, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0505876541137695, "global_step": 603753, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.928989291191101, "global_step": 603754, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9680782556533813, "global_step": 603755, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9590932130813599, "global_step": 603756, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9441779851913452, "global_step": 603757, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9702796936035156, "global_step": 603758, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9520775079727173, "global_step": 603759, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0295262336730957, "global_step": 603760, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9312138557434082, "global_step": 603761, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.02728271484375, "global_step": 603762, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9885749816894531, "global_step": 603763, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0314714908599854, "global_step": 603764, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.974906086921692, "global_step": 603765, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0392439365386963, "global_step": 603766, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9845826625823975, "global_step": 603767, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.014580488204956, "global_step": 603768, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.009052276611328, "global_step": 603769, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.918729543685913, "global_step": 603770, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9794038534164429, "global_step": 603771, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.976357340812683, "global_step": 603772, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.966825008392334, "global_step": 603773, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0713672637939453, "global_step": 603774, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0374512672424316, "global_step": 603775, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9745672941207886, "global_step": 603776, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0626089572906494, "global_step": 603777, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9577656984329224, "global_step": 603778, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9873666763305664, "global_step": 603779, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0162129402160645, "global_step": 603780, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1143033504486084, "global_step": 603781, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.955578088760376, "global_step": 603782, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.98029625415802, "global_step": 603783, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1472716331481934, "global_step": 603784, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.081048011779785, "global_step": 603785, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0799825191497803, "global_step": 603786, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0545480251312256, "global_step": 603787, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.1102545261383057, "global_step": 603788, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0194733142852783, "global_step": 603789, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9923940896987915, "global_step": 603790, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0049989223480225, "global_step": 603791, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.10005521774292, "global_step": 603792, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.028900384902954, "global_step": 603793, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0185141563415527, "global_step": 603794, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0359277725219727, "global_step": 603795, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0817816257476807, "global_step": 603796, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.994943380355835, "global_step": 603797, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0030155181884766, "global_step": 603798, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0707478523254395, "global_step": 603799, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.040353536605835, "global_step": 603800, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9850658178329468, "global_step": 603801, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.044316053390503, "global_step": 603802, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.069859743118286, "global_step": 603803, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.996716856956482, "global_step": 603804, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.020592212677002, "global_step": 603805, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.922957181930542, "global_step": 603806, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9229921102523804, "global_step": 603807, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.09958815574646, "global_step": 603808, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0213027000427246, "global_step": 603809, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9244786500930786, "global_step": 603810, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0887341499328613, "global_step": 603811, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0421998500823975, "global_step": 603812, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.994878888130188, "global_step": 603813, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.018799066543579, "global_step": 603814, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.01702880859375, "global_step": 603815, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0371904373168945, "global_step": 603816, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9502960443496704, "global_step": 603817, "epoch": 972, "lr": 5e-05}
{"train_loss": 1.9570188522338867, "global_step": 603818, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.0120904445648193, "global_step": 603819, "epoch": 972, "lr": 5e-05}
{"train_loss": 2.121396780014038, "global_step": 603820, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.990545392036438, "global_step": 603821, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9412935972213745, "global_step": 603822, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.006091833114624, "global_step": 603823, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9387770891189575, "global_step": 603824, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0765678882598877, "global_step": 603825, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9279954433441162, "global_step": 603826, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9743281602859497, "global_step": 603827, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.017122268676758, "global_step": 603828, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0019803047180176, "global_step": 603829, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.066689968109131, "global_step": 603830, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9441760778427124, "global_step": 603831, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9652057886123657, "global_step": 603832, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0681040287017822, "global_step": 603833, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9916691780090332, "global_step": 603834, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9350535869598389, "global_step": 603835, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9802711009979248, "global_step": 603836, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9742307662963867, "global_step": 603837, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.973227858543396, "global_step": 603838, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9539200067520142, "global_step": 603839, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9861986637115479, "global_step": 603840, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0285565853118896, "global_step": 603841, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9383891820907593, "global_step": 603842, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9932302236557007, "global_step": 603843, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9460840225219727, "global_step": 603844, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.960546612739563, "global_step": 603845, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9545295238494873, "global_step": 603846, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.043463945388794, "global_step": 603847, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0282137393951416, "global_step": 603848, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0247349739074707, "global_step": 603849, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9705032110214233, "global_step": 603850, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0370941162109375, "global_step": 603851, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0596275329589844, "global_step": 603852, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.088095188140869, "global_step": 603853, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9993263483047485, "global_step": 603854, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9715368747711182, "global_step": 603855, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.002054452896118, "global_step": 603856, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9623825550079346, "global_step": 603857, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0757768154144287, "global_step": 603858, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0387637615203857, "global_step": 603859, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.974497675895691, "global_step": 603860, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0684235095977783, "global_step": 603861, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0281403064727783, "global_step": 603862, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.999006986618042, "global_step": 603863, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.1055712699890137, "global_step": 603864, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9954272508621216, "global_step": 603865, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9897807836532593, "global_step": 603866, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0293831825256348, "global_step": 603867, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9762872457504272, "global_step": 603868, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.027322292327881, "global_step": 603869, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9987261295318604, "global_step": 603870, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.064243793487549, "global_step": 603871, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0998339653015137, "global_step": 603872, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0280563831329346, "global_step": 603873, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9567642211914062, "global_step": 603874, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.1034018993377686, "global_step": 603875, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0078601837158203, "global_step": 603876, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0297775268554688, "global_step": 603877, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9014233350753784, "global_step": 603878, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0042145252227783, "global_step": 603879, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0581705570220947, "global_step": 603880, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0196480751037598, "global_step": 603881, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9729863405227661, "global_step": 603882, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.009737014770508, "global_step": 603883, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0227372646331787, "global_step": 603884, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9608433246612549, "global_step": 603885, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9740147590637207, "global_step": 603886, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.047837018966675, "global_step": 603887, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0128843784332275, "global_step": 603888, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0457684993743896, "global_step": 603889, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0453193187713623, "global_step": 603890, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.029566764831543, "global_step": 603891, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0066866874694824, "global_step": 603892, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9747028350830078, "global_step": 603893, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0311594009399414, "global_step": 603894, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.075110673904419, "global_step": 603895, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9740071296691895, "global_step": 603896, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9395438432693481, "global_step": 603897, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9786595106124878, "global_step": 603898, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.013888120651245, "global_step": 603899, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.091449022293091, "global_step": 603900, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0666956901550293, "global_step": 603901, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9420080184936523, "global_step": 603902, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0213823318481445, "global_step": 603903, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0416719913482666, "global_step": 603904, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0383896827697754, "global_step": 603905, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.01991868019104, "global_step": 603906, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0343213081359863, "global_step": 603907, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.061389207839966, "global_step": 603908, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9643595218658447, "global_step": 603909, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.024799346923828, "global_step": 603910, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9187641143798828, "global_step": 603911, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9460264444351196, "global_step": 603912, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9332334995269775, "global_step": 603913, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9899041652679443, "global_step": 603914, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.018775463104248, "global_step": 603915, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9254848957061768, "global_step": 603916, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0443878173828125, "global_step": 603917, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.029102325439453, "global_step": 603918, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9610443115234375, "global_step": 603919, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9752084016799927, "global_step": 603920, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.008730888366699, "global_step": 603921, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9883668422698975, "global_step": 603922, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9719696044921875, "global_step": 603923, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.975378155708313, "global_step": 603924, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.028778553009033, "global_step": 603925, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9527958631515503, "global_step": 603926, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9467970132827759, "global_step": 603927, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.042184352874756, "global_step": 603928, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9627313613891602, "global_step": 603929, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.98926842212677, "global_step": 603930, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.00382924079895, "global_step": 603931, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.00262188911438, "global_step": 603932, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.013277053833008, "global_step": 603933, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9894591569900513, "global_step": 603934, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9269806146621704, "global_step": 603935, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0359513759613037, "global_step": 603936, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.023787260055542, "global_step": 603937, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0188169479370117, "global_step": 603938, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.002871513366699, "global_step": 603939, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0078201293945312, "global_step": 603940, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.052938938140869, "global_step": 603941, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9371386766433716, "global_step": 603942, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9030524492263794, "global_step": 603943, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.985771894454956, "global_step": 603944, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.8971474170684814, "global_step": 603945, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.083374500274658, "global_step": 603946, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0442655086517334, "global_step": 603947, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0157785415649414, "global_step": 603948, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9755027294158936, "global_step": 603949, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9384088516235352, "global_step": 603950, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9241373538970947, "global_step": 603951, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9571024179458618, "global_step": 603952, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9312375783920288, "global_step": 603953, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.926349401473999, "global_step": 603954, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0597777366638184, "global_step": 603955, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0014266967773438, "global_step": 603956, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9207649230957031, "global_step": 603957, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9911338090896606, "global_step": 603958, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.998368263244629, "global_step": 603959, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9864206314086914, "global_step": 603960, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0284459590911865, "global_step": 603961, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9610404968261719, "global_step": 603962, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.965190052986145, "global_step": 603963, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0218656063079834, "global_step": 603964, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.038238525390625, "global_step": 603965, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.12009859085083, "global_step": 603966, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9980467557907104, "global_step": 603967, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0283496379852295, "global_step": 603968, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.961185336112976, "global_step": 603969, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0597243309020996, "global_step": 603970, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.04677152633667, "global_step": 603971, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0369222164154053, "global_step": 603972, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9659109115600586, "global_step": 603973, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.041384220123291, "global_step": 603974, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0148441791534424, "global_step": 603975, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9906377792358398, "global_step": 603976, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.078418254852295, "global_step": 603977, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.030297040939331, "global_step": 603978, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0330045223236084, "global_step": 603979, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0372772216796875, "global_step": 603980, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.129150867462158, "global_step": 603981, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0317697525024414, "global_step": 603982, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0494236946105957, "global_step": 603983, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9607629776000977, "global_step": 603984, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.987252950668335, "global_step": 603985, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.05531644821167, "global_step": 603986, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9332170486450195, "global_step": 603987, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0638926029205322, "global_step": 603988, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0275051593780518, "global_step": 603989, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9174089431762695, "global_step": 603990, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.970231294631958, "global_step": 603991, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.931347131729126, "global_step": 603992, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.081753730773926, "global_step": 603993, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9399464130401611, "global_step": 603994, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.909530520439148, "global_step": 603995, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.077556610107422, "global_step": 603996, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9531501531600952, "global_step": 603997, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0291192531585693, "global_step": 603998, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9903640747070312, "global_step": 603999, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9958734512329102, "global_step": 604000, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9927351474761963, "global_step": 604001, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.057034730911255, "global_step": 604002, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9514176845550537, "global_step": 604003, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0700604915618896, "global_step": 604004, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.057802438735962, "global_step": 604005, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0058557987213135, "global_step": 604006, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9913763999938965, "global_step": 604007, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.975590705871582, "global_step": 604008, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0059773921966553, "global_step": 604009, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.8754537105560303, "global_step": 604010, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9839686155319214, "global_step": 604011, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9872161149978638, "global_step": 604012, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9679914712905884, "global_step": 604013, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9972567558288574, "global_step": 604014, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0470478534698486, "global_step": 604015, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9959522485733032, "global_step": 604016, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0003583431243896, "global_step": 604017, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9504543542861938, "global_step": 604018, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0080559253692627, "global_step": 604019, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0582919120788574, "global_step": 604020, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.8785290718078613, "global_step": 604021, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0754449367523193, "global_step": 604022, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9436296224594116, "global_step": 604023, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0771517753601074, "global_step": 604024, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9348751306533813, "global_step": 604025, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9436533451080322, "global_step": 604026, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0044217109680176, "global_step": 604027, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.970895528793335, "global_step": 604028, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9969958066940308, "global_step": 604029, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9723597764968872, "global_step": 604030, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.063775062561035, "global_step": 604031, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9628955125808716, "global_step": 604032, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9592232704162598, "global_step": 604033, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.1477246284484863, "global_step": 604034, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9857743978500366, "global_step": 604035, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9408241510391235, "global_step": 604036, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9280067682266235, "global_step": 604037, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.011946439743042, "global_step": 604038, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.051685094833374, "global_step": 604039, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9760419130325317, "global_step": 604040, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.008629322052002, "global_step": 604041, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.040492296218872, "global_step": 604042, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.044398307800293, "global_step": 604043, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0268821716308594, "global_step": 604044, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.87430739402771, "global_step": 604045, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0666134357452393, "global_step": 604046, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0140538215637207, "global_step": 604047, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.103440284729004, "global_step": 604048, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9639630317687988, "global_step": 604049, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0148563385009766, "global_step": 604050, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.1181392669677734, "global_step": 604051, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9879512786865234, "global_step": 604052, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0172927379608154, "global_step": 604053, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0037994384765625, "global_step": 604054, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.1090781688690186, "global_step": 604055, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9903485774993896, "global_step": 604056, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0031957626342773, "global_step": 604057, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.95575749874115, "global_step": 604058, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.997207522392273, "global_step": 604059, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.030229330062866, "global_step": 604060, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.994870901107788, "global_step": 604061, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0203142166137695, "global_step": 604062, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0503733158111572, "global_step": 604063, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9640007019042969, "global_step": 604064, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9559942483901978, "global_step": 604065, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0256636142730713, "global_step": 604066, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.006917715072632, "global_step": 604067, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0565602779388428, "global_step": 604068, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.008366823196411, "global_step": 604069, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9567594528198242, "global_step": 604070, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.024524688720703, "global_step": 604071, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0396084785461426, "global_step": 604072, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0118155479431152, "global_step": 604073, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0273444652557373, "global_step": 604074, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0592753887176514, "global_step": 604075, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9331761598587036, "global_step": 604076, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0215420722961426, "global_step": 604077, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0006954669952393, "global_step": 604078, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9541000127792358, "global_step": 604079, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.024226188659668, "global_step": 604080, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0612072944641113, "global_step": 604081, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.041086196899414, "global_step": 604082, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0488462448120117, "global_step": 604083, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.079829454421997, "global_step": 604084, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.033996105194092, "global_step": 604085, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9676049947738647, "global_step": 604086, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.8680369853973389, "global_step": 604087, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.067798614501953, "global_step": 604088, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9780958890914917, "global_step": 604089, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.044459581375122, "global_step": 604090, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9967352151870728, "global_step": 604091, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.1284661293029785, "global_step": 604092, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0403249263763428, "global_step": 604093, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9585297107696533, "global_step": 604094, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0142722129821777, "global_step": 604095, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.967565894126892, "global_step": 604096, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.004246473312378, "global_step": 604097, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.009204387664795, "global_step": 604098, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0058159828186035, "global_step": 604099, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.067063093185425, "global_step": 604100, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.989816427230835, "global_step": 604101, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0531628131866455, "global_step": 604102, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0392801761627197, "global_step": 604103, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9198774099349976, "global_step": 604104, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0573954582214355, "global_step": 604105, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0322630405426025, "global_step": 604106, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0788943767547607, "global_step": 604107, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0104422569274902, "global_step": 604108, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9753711223602295, "global_step": 604109, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.989251971244812, "global_step": 604110, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.022329330444336, "global_step": 604111, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0202078819274902, "global_step": 604112, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9610629081726074, "global_step": 604113, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9510440826416016, "global_step": 604114, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0171799659729004, "global_step": 604115, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0363078117370605, "global_step": 604116, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9893221855163574, "global_step": 604117, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.069859743118286, "global_step": 604118, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.8842140436172485, "global_step": 604119, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9774781465530396, "global_step": 604120, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0240700244903564, "global_step": 604121, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0198512077331543, "global_step": 604122, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.02119517326355, "global_step": 604123, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9507566690444946, "global_step": 604124, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9945905208587646, "global_step": 604125, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9538617134094238, "global_step": 604126, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.989221215248108, "global_step": 604127, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.104402542114258, "global_step": 604128, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.008354663848877, "global_step": 604129, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9497169256210327, "global_step": 604130, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.05437970161438, "global_step": 604131, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0778660774230957, "global_step": 604132, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.1079483032226562, "global_step": 604133, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.8804858922958374, "global_step": 604134, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9333741664886475, "global_step": 604135, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0161139965057373, "global_step": 604136, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.001690149307251, "global_step": 604137, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.042069435119629, "global_step": 604138, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.029998540878296, "global_step": 604139, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.051563024520874, "global_step": 604140, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.080704689025879, "global_step": 604141, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9660005569458008, "global_step": 604142, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0818417072296143, "global_step": 604143, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.004088878631592, "global_step": 604144, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0674328804016113, "global_step": 604145, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0895137786865234, "global_step": 604146, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0067474842071533, "global_step": 604147, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0398712158203125, "global_step": 604148, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9271758794784546, "global_step": 604149, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9901752471923828, "global_step": 604150, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9845490455627441, "global_step": 604151, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.1345269680023193, "global_step": 604152, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.081371307373047, "global_step": 604153, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.006242275238037, "global_step": 604154, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.003628969192505, "global_step": 604155, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0711748600006104, "global_step": 604156, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0269675254821777, "global_step": 604157, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0372228622436523, "global_step": 604158, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0083391666412354, "global_step": 604159, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9917985200881958, "global_step": 604160, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0062098503112793, "global_step": 604161, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0483946800231934, "global_step": 604162, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0094051361083984, "global_step": 604163, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9436771869659424, "global_step": 604164, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.074680805206299, "global_step": 604165, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0199992656707764, "global_step": 604166, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.926426887512207, "global_step": 604167, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9876796007156372, "global_step": 604168, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.1092915534973145, "global_step": 604169, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9129399061203003, "global_step": 604170, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0127906799316406, "global_step": 604171, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0728585720062256, "global_step": 604172, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.1060967445373535, "global_step": 604173, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0278356075286865, "global_step": 604174, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9832913875579834, "global_step": 604175, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9808454513549805, "global_step": 604176, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.079155921936035, "global_step": 604177, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9835946559906006, "global_step": 604178, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0401742458343506, "global_step": 604179, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0094852447509766, "global_step": 604180, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.03446102142334, "global_step": 604181, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9720064401626587, "global_step": 604182, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.029942512512207, "global_step": 604183, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.089010238647461, "global_step": 604184, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0677592754364014, "global_step": 604185, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.8960036039352417, "global_step": 604186, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0673394203186035, "global_step": 604187, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0871593952178955, "global_step": 604188, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.8839470148086548, "global_step": 604189, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0470831394195557, "global_step": 604190, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0442748069763184, "global_step": 604191, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.148102283477783, "global_step": 604192, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.99698805809021, "global_step": 604193, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0280070304870605, "global_step": 604194, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9907892942428589, "global_step": 604195, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9860605001449585, "global_step": 604196, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0035552978515625, "global_step": 604197, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.1175663471221924, "global_step": 604198, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.967573642730713, "global_step": 604199, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.980118989944458, "global_step": 604200, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9888578653335571, "global_step": 604201, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.096919059753418, "global_step": 604202, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0517842769622803, "global_step": 604203, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9808399677276611, "global_step": 604204, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.035735607147217, "global_step": 604205, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0517313480377197, "global_step": 604206, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0191562175750732, "global_step": 604207, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.048677682876587, "global_step": 604208, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0153698921203613, "global_step": 604209, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.060364007949829, "global_step": 604210, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9426443576812744, "global_step": 604211, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0400962829589844, "global_step": 604212, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.02524471282959, "global_step": 604213, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.996621012687683, "global_step": 604214, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0235517024993896, "global_step": 604215, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.019245147705078, "global_step": 604216, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0548713207244873, "global_step": 604217, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9875476360321045, "global_step": 604218, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.024287700653076, "global_step": 604219, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0075693130493164, "global_step": 604220, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0096120834350586, "global_step": 604221, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0117123126983643, "global_step": 604222, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9728087186813354, "global_step": 604223, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0665574073791504, "global_step": 604224, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.014155387878418, "global_step": 604225, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9432519674301147, "global_step": 604226, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9845775365829468, "global_step": 604227, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.036264419555664, "global_step": 604228, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9535472393035889, "global_step": 604229, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9857653379440308, "global_step": 604230, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9966152906417847, "global_step": 604231, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9983315467834473, "global_step": 604232, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.056748151779175, "global_step": 604233, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0448036193847656, "global_step": 604234, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0168683528900146, "global_step": 604235, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9314630031585693, "global_step": 604236, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.971112608909607, "global_step": 604237, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9793955087661743, "global_step": 604238, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.035846710205078, "global_step": 604239, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.040792942047119, "global_step": 604240, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.064946174621582, "global_step": 604241, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.018127679824829, "global_step": 604242, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.07322096824646, "global_step": 604243, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0238709449768066, "global_step": 604244, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.944008708000183, "global_step": 604245, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.985653281211853, "global_step": 604246, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9738610982894897, "global_step": 604247, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0296740531921387, "global_step": 604248, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9787424802780151, "global_step": 604249, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9820085763931274, "global_step": 604250, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.011963129043579, "global_step": 604251, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9631645679473877, "global_step": 604252, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9244939088821411, "global_step": 604253, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0179286003112793, "global_step": 604254, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.016733169555664, "global_step": 604255, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0028936862945557, "global_step": 604256, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.148270845413208, "global_step": 604257, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.041815757751465, "global_step": 604258, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0468761920928955, "global_step": 604259, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9491809606552124, "global_step": 604260, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.000366687774658, "global_step": 604261, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.064918279647827, "global_step": 604262, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.1171822547912598, "global_step": 604263, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.077481746673584, "global_step": 604264, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0590879917144775, "global_step": 604265, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.013381004333496, "global_step": 604266, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9809340238571167, "global_step": 604267, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9826231002807617, "global_step": 604268, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.051431655883789, "global_step": 604269, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0640218257904053, "global_step": 604270, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.986082911491394, "global_step": 604271, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0152556896209717, "global_step": 604272, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.988492488861084, "global_step": 604273, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9441803693771362, "global_step": 604274, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.01070237159729, "global_step": 604275, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.022829055786133, "global_step": 604276, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.061511278152466, "global_step": 604277, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0844480991363525, "global_step": 604278, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0511178970336914, "global_step": 604279, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0469582080841064, "global_step": 604280, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0373082160949707, "global_step": 604281, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9931721687316895, "global_step": 604282, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.009899377822876, "global_step": 604283, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9698176383972168, "global_step": 604284, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9984548091888428, "global_step": 604285, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9908440113067627, "global_step": 604286, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9929370880126953, "global_step": 604287, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0084357261657715, "global_step": 604288, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.015305995941162, "global_step": 604289, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.054169178009033, "global_step": 604290, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9246044158935547, "global_step": 604291, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.090083122253418, "global_step": 604292, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.075859546661377, "global_step": 604293, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0349531173706055, "global_step": 604294, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0394704341888428, "global_step": 604295, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.031818389892578, "global_step": 604296, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0151586532592773, "global_step": 604297, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9315838813781738, "global_step": 604298, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9822255373001099, "global_step": 604299, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9843635559082031, "global_step": 604300, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0099494457244873, "global_step": 604301, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9948400259017944, "global_step": 604302, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9686397314071655, "global_step": 604303, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9732450246810913, "global_step": 604304, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0279440879821777, "global_step": 604305, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9508962631225586, "global_step": 604306, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9962928295135498, "global_step": 604307, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.120271682739258, "global_step": 604308, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.912964105606079, "global_step": 604309, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0443599224090576, "global_step": 604310, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.084660053253174, "global_step": 604311, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.041027545928955, "global_step": 604312, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.021486282348633, "global_step": 604313, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.004317045211792, "global_step": 604314, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0184683799743652, "global_step": 604315, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9920752048492432, "global_step": 604316, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9139313697814941, "global_step": 604317, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0080981254577637, "global_step": 604318, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9078376293182373, "global_step": 604319, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.021169424057007, "global_step": 604320, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9532074928283691, "global_step": 604321, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.044555425643921, "global_step": 604322, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.063325881958008, "global_step": 604323, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9723622798919678, "global_step": 604324, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0985898971557617, "global_step": 604325, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9509682655334473, "global_step": 604326, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0513601303100586, "global_step": 604327, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9041537046432495, "global_step": 604328, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0451066493988037, "global_step": 604329, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.993203043937683, "global_step": 604330, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9279868602752686, "global_step": 604331, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9758728742599487, "global_step": 604332, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.079280376434326, "global_step": 604333, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9833236932754517, "global_step": 604334, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0468924045562744, "global_step": 604335, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9861984252929688, "global_step": 604336, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0570178031921387, "global_step": 604337, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9697271585464478, "global_step": 604338, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0221779346466064, "global_step": 604339, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9973429441452026, "global_step": 604340, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.058772087097168, "global_step": 604341, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.042489767074585, "global_step": 604342, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0053470134735107, "global_step": 604343, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9770358800888062, "global_step": 604344, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9729373455047607, "global_step": 604345, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.064420223236084, "global_step": 604346, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0155701637268066, "global_step": 604347, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9871902465820312, "global_step": 604348, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9871317148208618, "global_step": 604349, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0461270809173584, "global_step": 604350, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9377293586730957, "global_step": 604351, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0027942657470703, "global_step": 604352, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9759315252304077, "global_step": 604353, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9982584714889526, "global_step": 604354, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.8987915515899658, "global_step": 604355, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9424949884414673, "global_step": 604356, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9821678400039673, "global_step": 604357, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0089192390441895, "global_step": 604358, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.009763240814209, "global_step": 604359, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9834213256835938, "global_step": 604360, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.067732572555542, "global_step": 604361, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.959545612335205, "global_step": 604362, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9768377542495728, "global_step": 604363, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.1077144145965576, "global_step": 604364, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.057432174682617, "global_step": 604365, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0505056381225586, "global_step": 604366, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0060603618621826, "global_step": 604367, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.8747469186782837, "global_step": 604368, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9890782833099365, "global_step": 604369, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0106184482574463, "global_step": 604370, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9748834371566772, "global_step": 604371, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0832479000091553, "global_step": 604372, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9833675622940063, "global_step": 604373, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.016873836517334, "global_step": 604374, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0810770988464355, "global_step": 604375, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.011754035949707, "global_step": 604376, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9589738845825195, "global_step": 604377, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9622567892074585, "global_step": 604378, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9899170398712158, "global_step": 604379, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9826687574386597, "global_step": 604380, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.033099889755249, "global_step": 604381, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9697952270507812, "global_step": 604382, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.106253147125244, "global_step": 604383, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9900946617126465, "global_step": 604384, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9580827951431274, "global_step": 604385, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9709804058074951, "global_step": 604386, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.009394645690918, "global_step": 604387, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.009953260421753, "global_step": 604388, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.959446907043457, "global_step": 604389, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0579020977020264, "global_step": 604390, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9893174171447754, "global_step": 604391, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.07177996635437, "global_step": 604392, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9845397472381592, "global_step": 604393, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0404462814331055, "global_step": 604394, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.975487470626831, "global_step": 604395, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.034764289855957, "global_step": 604396, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9632071256637573, "global_step": 604397, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.958551287651062, "global_step": 604398, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.987525463104248, "global_step": 604399, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.042522668838501, "global_step": 604400, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.006028175354004, "global_step": 604401, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0082521438598633, "global_step": 604402, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9343384504318237, "global_step": 604403, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9550666809082031, "global_step": 604404, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9684430360794067, "global_step": 604405, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.07436466217041, "global_step": 604406, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0764307975769043, "global_step": 604407, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.971625804901123, "global_step": 604408, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9958122968673706, "global_step": 604409, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0669057369232178, "global_step": 604410, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0379726886749268, "global_step": 604411, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0693888664245605, "global_step": 604412, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.049795627593994, "global_step": 604413, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9849711656570435, "global_step": 604414, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9954842329025269, "global_step": 604415, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9982376098632812, "global_step": 604416, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9283440113067627, "global_step": 604417, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.985977292060852, "global_step": 604418, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.066830635070801, "global_step": 604419, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0229451656341553, "global_step": 604420, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0422604084014893, "global_step": 604421, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0542917251586914, "global_step": 604422, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0203309059143066, "global_step": 604423, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0398547649383545, "global_step": 604424, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0039100646972656, "global_step": 604425, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.03501558303833, "global_step": 604426, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9693914651870728, "global_step": 604427, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0114846229553223, "global_step": 604428, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.97265625, "global_step": 604429, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0553781986236572, "global_step": 604430, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.988775372505188, "global_step": 604431, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.993035078048706, "global_step": 604432, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0114521980285645, "global_step": 604433, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.065551280975342, "global_step": 604434, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0341506004333496, "global_step": 604435, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.044041156768799, "global_step": 604436, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.088595151901245, "global_step": 604437, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.096351385116577, "global_step": 604438, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9233657121658325, "global_step": 604439, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0298869609832764, "global_step": 604440, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.8381621837615967, "global_step": 604441, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.089268445968628, "global_step": 604442, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9854272603988647, "global_step": 604443, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9598685503005981, "global_step": 604444, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0621793270111084, "global_step": 604445, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9965384006500244, "global_step": 604446, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.034332752227783, "global_step": 604447, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9371395111083984, "global_step": 604448, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0136263370513916, "global_step": 604449, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0048670768737793, "global_step": 604450, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0498955249786377, "global_step": 604451, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0715129375457764, "global_step": 604452, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9777474403381348, "global_step": 604453, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9382133483886719, "global_step": 604454, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9940147399902344, "global_step": 604455, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9556790590286255, "global_step": 604456, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.020914077758789, "global_step": 604457, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0184552669525146, "global_step": 604458, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0187830924987793, "global_step": 604459, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0288188457489014, "global_step": 604460, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.013636350631714, "global_step": 604461, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0879926681518555, "global_step": 604462, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0495269298553467, "global_step": 604463, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.061999559402466, "global_step": 604464, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0101330280303955, "global_step": 604465, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0039920806884766, "global_step": 604466, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0263826847076416, "global_step": 604467, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9463343620300293, "global_step": 604468, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.981143593788147, "global_step": 604469, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0578835010528564, "global_step": 604470, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9513635635375977, "global_step": 604471, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.990127682685852, "global_step": 604472, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.988800287246704, "global_step": 604473, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0098366737365723, "global_step": 604474, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9152147769927979, "global_step": 604475, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.047563076019287, "global_step": 604476, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.020697832107544, "global_step": 604477, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9793272018432617, "global_step": 604478, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.977495789527893, "global_step": 604479, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0122575759887695, "global_step": 604480, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.941311240196228, "global_step": 604481, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0500776767730713, "global_step": 604482, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0652527809143066, "global_step": 604483, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.00120210647583, "global_step": 604484, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0330121517181396, "global_step": 604485, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.114027738571167, "global_step": 604486, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0509533882141113, "global_step": 604487, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.016090154647827, "global_step": 604488, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9887933731079102, "global_step": 604489, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9539519548416138, "global_step": 604490, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9600518941879272, "global_step": 604491, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.031804323196411, "global_step": 604492, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9676507711410522, "global_step": 604493, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0097615718841553, "global_step": 604494, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0376508235931396, "global_step": 604495, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0314621925354004, "global_step": 604496, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9785246849060059, "global_step": 604497, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.132014036178589, "global_step": 604498, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.016897201538086, "global_step": 604499, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9867442846298218, "global_step": 604500, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.096414804458618, "global_step": 604501, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9425976276397705, "global_step": 604502, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.004620313644409, "global_step": 604503, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0200932025909424, "global_step": 604504, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.981014609336853, "global_step": 604505, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.1028778553009033, "global_step": 604506, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9744678735733032, "global_step": 604507, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0117545127868652, "global_step": 604508, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.010103225708008, "global_step": 604509, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.932092547416687, "global_step": 604510, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0145328044891357, "global_step": 604511, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0329477787017822, "global_step": 604512, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0866801738739014, "global_step": 604513, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9671261310577393, "global_step": 604514, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.959615707397461, "global_step": 604515, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0547616481781006, "global_step": 604516, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9831377267837524, "global_step": 604517, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0597681999206543, "global_step": 604518, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.097486734390259, "global_step": 604519, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.062974214553833, "global_step": 604520, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.065436601638794, "global_step": 604521, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.064762592315674, "global_step": 604522, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0042550563812256, "global_step": 604523, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.060739517211914, "global_step": 604524, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0157856941223145, "global_step": 604525, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.024259567260742, "global_step": 604526, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0664820671081543, "global_step": 604527, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9623082876205444, "global_step": 604528, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9833952188491821, "global_step": 604529, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.024845838546753, "global_step": 604530, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.014265775680542, "global_step": 604531, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0041067600250244, "global_step": 604532, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.040393352508545, "global_step": 604533, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0354175567626953, "global_step": 604534, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0592472553253174, "global_step": 604535, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9505634307861328, "global_step": 604536, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0014352798461914, "global_step": 604537, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9524635076522827, "global_step": 604538, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.02203106880188, "global_step": 604539, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0606741905212402, "global_step": 604540, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.010464906692505, "global_step": 604541, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.883569598197937, "global_step": 604542, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.963537335395813, "global_step": 604543, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.8944299221038818, "global_step": 604544, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9571211338043213, "global_step": 604545, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.042975425720215, "global_step": 604546, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9772855043411255, "global_step": 604547, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.006364345550537, "global_step": 604548, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9511916637420654, "global_step": 604549, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.017110824584961, "global_step": 604550, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0535261631011963, "global_step": 604551, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0173935890197754, "global_step": 604552, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9836070537567139, "global_step": 604553, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.073805332183838, "global_step": 604554, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9805041551589966, "global_step": 604555, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0174551010131836, "global_step": 604556, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.048293113708496, "global_step": 604557, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9725937843322754, "global_step": 604558, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0189616680145264, "global_step": 604559, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9335695505142212, "global_step": 604560, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.016947031021118, "global_step": 604561, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9753837585449219, "global_step": 604562, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9622303247451782, "global_step": 604563, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.999721646308899, "global_step": 604564, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0225236415863037, "global_step": 604565, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9283701181411743, "global_step": 604566, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.067274332046509, "global_step": 604567, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.970489501953125, "global_step": 604568, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9768753051757812, "global_step": 604569, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.022442579269409, "global_step": 604570, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9565824270248413, "global_step": 604571, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.014918327331543, "global_step": 604572, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9489874839782715, "global_step": 604573, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.019824743270874, "global_step": 604574, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0640852451324463, "global_step": 604575, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9614810943603516, "global_step": 604576, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.942528486251831, "global_step": 604577, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9942529201507568, "global_step": 604578, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.031987190246582, "global_step": 604579, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.048285961151123, "global_step": 604580, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9777907133102417, "global_step": 604581, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0303330421447754, "global_step": 604582, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9673941135406494, "global_step": 604583, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.962165117263794, "global_step": 604584, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9530421495437622, "global_step": 604585, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9803714752197266, "global_step": 604586, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9767451286315918, "global_step": 604587, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9779131412506104, "global_step": 604588, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.078176975250244, "global_step": 604589, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0849063396453857, "global_step": 604590, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0204434394836426, "global_step": 604591, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0201642513275146, "global_step": 604592, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9791346788406372, "global_step": 604593, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.052034378051758, "global_step": 604594, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.009870767593384, "global_step": 604595, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9683897495269775, "global_step": 604596, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.056567668914795, "global_step": 604597, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9785232543945312, "global_step": 604598, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9895204305648804, "global_step": 604599, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0286147594451904, "global_step": 604600, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.839050531387329, "global_step": 604601, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.030466079711914, "global_step": 604602, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.122642993927002, "global_step": 604603, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9803584814071655, "global_step": 604604, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.037905693054199, "global_step": 604605, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.023346424102783, "global_step": 604606, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.087639093399048, "global_step": 604607, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9990510940551758, "global_step": 604608, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.973153829574585, "global_step": 604609, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9201526641845703, "global_step": 604610, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9906338453292847, "global_step": 604611, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.8909242153167725, "global_step": 604612, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0479705333709717, "global_step": 604613, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.038796901702881, "global_step": 604614, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.021815776824951, "global_step": 604615, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9370157718658447, "global_step": 604616, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0589871406555176, "global_step": 604617, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0239505767822266, "global_step": 604618, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.036618947982788, "global_step": 604619, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.029562473297119, "global_step": 604620, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.1017987728118896, "global_step": 604621, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.043616533279419, "global_step": 604622, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0261898040771484, "global_step": 604623, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.059528112411499, "global_step": 604624, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9687294960021973, "global_step": 604625, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0143208503723145, "global_step": 604626, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0246942043304443, "global_step": 604627, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.017913341522217, "global_step": 604628, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.025317430496216, "global_step": 604629, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0590853691101074, "global_step": 604630, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.005911350250244, "global_step": 604631, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0734355449676514, "global_step": 604632, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0474278926849365, "global_step": 604633, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.031252384185791, "global_step": 604634, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0627307891845703, "global_step": 604635, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0277152061462402, "global_step": 604636, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9318487644195557, "global_step": 604637, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0859036445617676, "global_step": 604638, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0093233585357666, "global_step": 604639, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.002291202545166, "global_step": 604640, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9934601783752441, "global_step": 604641, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.045590400695801, "global_step": 604642, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0125222206115723, "global_step": 604643, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.016042470932007, "global_step": 604644, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.068751335144043, "global_step": 604645, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.072970390319824, "global_step": 604646, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.925502896308899, "global_step": 604647, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.021688938140869, "global_step": 604648, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9928556680679321, "global_step": 604649, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.031623363494873, "global_step": 604650, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0344595909118652, "global_step": 604651, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9197168350219727, "global_step": 604652, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0042333602905273, "global_step": 604653, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.009113311767578, "global_step": 604654, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0564944744110107, "global_step": 604655, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.973659873008728, "global_step": 604656, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9234747886657715, "global_step": 604657, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9979221820831299, "global_step": 604658, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.992018461227417, "global_step": 604659, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.013862371444702, "global_step": 604660, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0616250038146973, "global_step": 604661, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0149710178375244, "global_step": 604662, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.115410327911377, "global_step": 604663, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.036374807357788, "global_step": 604664, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9898570775985718, "global_step": 604665, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0807480812072754, "global_step": 604666, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.026021718978882, "global_step": 604667, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0286099910736084, "global_step": 604668, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.1309397220611572, "global_step": 604669, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.034942150115967, "global_step": 604670, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.047769784927368, "global_step": 604671, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9847087860107422, "global_step": 604672, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0339033603668213, "global_step": 604673, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.001641035079956, "global_step": 604674, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.995344877243042, "global_step": 604675, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0555343627929688, "global_step": 604676, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0331618785858154, "global_step": 604677, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.021129608154297, "global_step": 604678, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.078907012939453, "global_step": 604679, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9775938987731934, "global_step": 604680, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9825087785720825, "global_step": 604681, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0311152935028076, "global_step": 604682, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.075679063796997, "global_step": 604683, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9265161752700806, "global_step": 604684, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0277202129364014, "global_step": 604685, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.998504400253296, "global_step": 604686, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0133554935455322, "global_step": 604687, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0109951496124268, "global_step": 604688, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9737790822982788, "global_step": 604689, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.959253191947937, "global_step": 604690, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0148777961730957, "global_step": 604691, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.983269453048706, "global_step": 604692, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9642270803451538, "global_step": 604693, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0572478771209717, "global_step": 604694, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0673885345458984, "global_step": 604695, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9800045490264893, "global_step": 604696, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.004743814468384, "global_step": 604697, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0155253410339355, "global_step": 604698, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0122714042663574, "global_step": 604699, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9541215896606445, "global_step": 604700, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9596771001815796, "global_step": 604701, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0663623809814453, "global_step": 604702, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0452537536621094, "global_step": 604703, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9992316961288452, "global_step": 604704, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.140467643737793, "global_step": 604705, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9980894327163696, "global_step": 604706, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9354636669158936, "global_step": 604707, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9830832481384277, "global_step": 604708, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0291519165039062, "global_step": 604709, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0158751010894775, "global_step": 604710, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.08766508102417, "global_step": 604711, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9393144845962524, "global_step": 604712, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9992518424987793, "global_step": 604713, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.99561607837677, "global_step": 604714, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.037175178527832, "global_step": 604715, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0809576511383057, "global_step": 604716, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0158822536468506, "global_step": 604717, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9661285877227783, "global_step": 604718, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0499186515808105, "global_step": 604719, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9826838970184326, "global_step": 604720, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9820669889450073, "global_step": 604721, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0060231685638428, "global_step": 604722, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.060750961303711, "global_step": 604723, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.01448392868042, "global_step": 604724, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.124131202697754, "global_step": 604725, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0850493907928467, "global_step": 604726, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.071941375732422, "global_step": 604727, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.074315309524536, "global_step": 604728, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9602173566818237, "global_step": 604729, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9754918813705444, "global_step": 604730, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.04426646232605, "global_step": 604731, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9525690078735352, "global_step": 604732, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0518276691436768, "global_step": 604733, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0378506183624268, "global_step": 604734, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.100131034851074, "global_step": 604735, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0408637523651123, "global_step": 604736, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.08225679397583, "global_step": 604737, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0851082801818848, "global_step": 604738, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9764131307601929, "global_step": 604739, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9715163707733154, "global_step": 604740, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.058032989501953, "global_step": 604741, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.005575180053711, "global_step": 604742, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0217952728271484, "global_step": 604743, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.019867420196533, "global_step": 604744, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.095618963241577, "global_step": 604745, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.006146192550659, "global_step": 604746, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9563993215560913, "global_step": 604747, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0400147438049316, "global_step": 604748, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0276589393615723, "global_step": 604749, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.016878604888916, "global_step": 604750, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0606186389923096, "global_step": 604751, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9919575452804565, "global_step": 604752, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.080434799194336, "global_step": 604753, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.06421160697937, "global_step": 604754, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0276355743408203, "global_step": 604755, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0712661743164062, "global_step": 604756, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0700652599334717, "global_step": 604757, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0605390071868896, "global_step": 604758, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9747645854949951, "global_step": 604759, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.024448871612549, "global_step": 604760, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0383377075195312, "global_step": 604761, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.034067153930664, "global_step": 604762, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9198920726776123, "global_step": 604763, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0453834533691406, "global_step": 604764, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0282139778137207, "global_step": 604765, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9829193353652954, "global_step": 604766, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9548757076263428, "global_step": 604767, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0389516353607178, "global_step": 604768, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.014223575592041, "global_step": 604769, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.957697868347168, "global_step": 604770, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0283071994781494, "global_step": 604771, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9863420724868774, "global_step": 604772, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9940756559371948, "global_step": 604773, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0104479789733887, "global_step": 604774, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9835875034332275, "global_step": 604775, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9854660034179688, "global_step": 604776, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0750653743743896, "global_step": 604777, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0633716583251953, "global_step": 604778, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.008122205734253, "global_step": 604779, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9623533487319946, "global_step": 604780, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.063047409057617, "global_step": 604781, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.9632129669189453, "global_step": 604782, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.06180739402771, "global_step": 604783, "epoch": 973, "lr": 5e-05}
{"train_loss": 1.983018159866333, "global_step": 604784, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0246245861053467, "global_step": 604785, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.012693405151367, "global_step": 604786, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0409293174743652, "global_step": 604787, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.010456085205078, "global_step": 604788, "epoch": 973, "lr": 5e-05}
{"train_loss": 2.0189647674560547, "global_step": 604789, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0037221908569336, "global_step": 604790, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0710842609405518, "global_step": 604791, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0645675659179688, "global_step": 604792, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0629966259002686, "global_step": 604793, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9609816074371338, "global_step": 604794, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.017650842666626, "global_step": 604795, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0326590538024902, "global_step": 604796, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.030968189239502, "global_step": 604797, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0559895038604736, "global_step": 604798, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9221751689910889, "global_step": 604799, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0399322509765625, "global_step": 604800, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0124738216400146, "global_step": 604801, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.031437635421753, "global_step": 604802, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.003166913986206, "global_step": 604803, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0200717449188232, "global_step": 604804, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0498814582824707, "global_step": 604805, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.974822759628296, "global_step": 604806, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0297861099243164, "global_step": 604807, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9446460008621216, "global_step": 604808, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9970886707305908, "global_step": 604809, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9571210145950317, "global_step": 604810, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9350714683532715, "global_step": 604811, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9877206087112427, "global_step": 604812, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9441125392913818, "global_step": 604813, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0276846885681152, "global_step": 604814, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0377399921417236, "global_step": 604815, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.986472249031067, "global_step": 604816, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9786360263824463, "global_step": 604817, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0464847087860107, "global_step": 604818, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0305838584899902, "global_step": 604819, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9018597602844238, "global_step": 604820, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9910955429077148, "global_step": 604821, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9817968606948853, "global_step": 604822, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.026624917984009, "global_step": 604823, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.050354242324829, "global_step": 604824, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9889382123947144, "global_step": 604825, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.01422119140625, "global_step": 604826, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.92208731174469, "global_step": 604827, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0363588333129883, "global_step": 604828, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.068514585494995, "global_step": 604829, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9827263355255127, "global_step": 604830, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.957721471786499, "global_step": 604831, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9922460317611694, "global_step": 604832, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.8961204290390015, "global_step": 604833, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.912034273147583, "global_step": 604834, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0303125381469727, "global_step": 604835, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.026277542114258, "global_step": 604836, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.8822016716003418, "global_step": 604837, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0398902893066406, "global_step": 604838, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9773932695388794, "global_step": 604839, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9438978433609009, "global_step": 604840, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0280301570892334, "global_step": 604841, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0131781101226807, "global_step": 604842, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.979883074760437, "global_step": 604843, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0320956707000732, "global_step": 604844, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9810137748718262, "global_step": 604845, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9678585529327393, "global_step": 604846, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.967504620552063, "global_step": 604847, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0232276916503906, "global_step": 604848, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.8942049741744995, "global_step": 604849, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0960333347320557, "global_step": 604850, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0004613399505615, "global_step": 604851, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9520264863967896, "global_step": 604852, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0648255348205566, "global_step": 604853, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9435662031173706, "global_step": 604854, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9454426765441895, "global_step": 604855, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0349836349487305, "global_step": 604856, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0322117805480957, "global_step": 604857, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9860870838165283, "global_step": 604858, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0640974044799805, "global_step": 604859, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.031339406967163, "global_step": 604860, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9639748334884644, "global_step": 604861, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0491154193878174, "global_step": 604862, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.055319309234619, "global_step": 604863, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9470398426055908, "global_step": 604864, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9283087253570557, "global_step": 604865, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0226528644561768, "global_step": 604866, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9770593643188477, "global_step": 604867, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.99602472782135, "global_step": 604868, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0162854194641113, "global_step": 604869, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0194361209869385, "global_step": 604870, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9444915056228638, "global_step": 604871, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9830517768859863, "global_step": 604872, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.02927303314209, "global_step": 604873, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9587675333023071, "global_step": 604874, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9570306539535522, "global_step": 604875, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9842661619186401, "global_step": 604876, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.997482419013977, "global_step": 604877, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9955235719680786, "global_step": 604878, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.003912925720215, "global_step": 604879, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0022470951080322, "global_step": 604880, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.007185935974121, "global_step": 604881, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.934536099433899, "global_step": 604882, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0524284839630127, "global_step": 604883, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0172221660614014, "global_step": 604884, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0666556358337402, "global_step": 604885, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.020873546600342, "global_step": 604886, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.033859968185425, "global_step": 604887, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9963152408599854, "global_step": 604888, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.064486026763916, "global_step": 604889, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.030092716217041, "global_step": 604890, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9709508419036865, "global_step": 604891, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.023703098297119, "global_step": 604892, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9679192304611206, "global_step": 604893, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0003156661987305, "global_step": 604894, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9834791421890259, "global_step": 604895, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0131614208221436, "global_step": 604896, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9648569822311401, "global_step": 604897, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9938238859176636, "global_step": 604898, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9651237726211548, "global_step": 604899, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0260250568389893, "global_step": 604900, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0826256275177, "global_step": 604901, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0220224857330322, "global_step": 604902, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.983323097229004, "global_step": 604903, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9559720754623413, "global_step": 604904, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.995126485824585, "global_step": 604905, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.034074306488037, "global_step": 604906, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0151143074035645, "global_step": 604907, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9615368843078613, "global_step": 604908, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9704123735427856, "global_step": 604909, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.8925237655639648, "global_step": 604910, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9219169616699219, "global_step": 604911, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9963603019714355, "global_step": 604912, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.994288682937622, "global_step": 604913, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.005037546157837, "global_step": 604914, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9524400234222412, "global_step": 604915, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0029425621032715, "global_step": 604916, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.035902976989746, "global_step": 604917, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9798600673675537, "global_step": 604918, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9982635974884033, "global_step": 604919, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0794620513916016, "global_step": 604920, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9808695316314697, "global_step": 604921, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9304983615875244, "global_step": 604922, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.931594729423523, "global_step": 604923, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.990246295928955, "global_step": 604924, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0299675464630127, "global_step": 604925, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9833049774169922, "global_step": 604926, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.986409068107605, "global_step": 604927, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0479555130004883, "global_step": 604928, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9555565118789673, "global_step": 604929, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9246090650558472, "global_step": 604930, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9805653095245361, "global_step": 604931, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9349398612976074, "global_step": 604932, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9354711771011353, "global_step": 604933, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.968685269355774, "global_step": 604934, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9682493209838867, "global_step": 604935, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.032991647720337, "global_step": 604936, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0508675575256348, "global_step": 604937, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9991401433944702, "global_step": 604938, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9372050762176514, "global_step": 604939, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.94150710105896, "global_step": 604940, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.112196445465088, "global_step": 604941, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0639941692352295, "global_step": 604942, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.970819115638733, "global_step": 604943, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.039421558380127, "global_step": 604944, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9609696865081787, "global_step": 604945, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0097076892852783, "global_step": 604946, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0563583374023438, "global_step": 604947, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0059492588043213, "global_step": 604948, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.088691473007202, "global_step": 604949, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0243289470672607, "global_step": 604950, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0164480209350586, "global_step": 604951, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0224578380584717, "global_step": 604952, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9961259365081787, "global_step": 604953, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0006039142608643, "global_step": 604954, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.969351887702942, "global_step": 604955, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9322705268859863, "global_step": 604956, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9528825283050537, "global_step": 604957, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.081315755844116, "global_step": 604958, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0320348739624023, "global_step": 604959, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9709577560424805, "global_step": 604960, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0325183868408203, "global_step": 604961, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0167434215545654, "global_step": 604962, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.105350971221924, "global_step": 604963, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9544340372085571, "global_step": 604964, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0130422115325928, "global_step": 604965, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.018673896789551, "global_step": 604966, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.007791757583618, "global_step": 604967, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.01952862739563, "global_step": 604968, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9436166286468506, "global_step": 604969, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0084877014160156, "global_step": 604970, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0247840881347656, "global_step": 604971, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9996126890182495, "global_step": 604972, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.057608127593994, "global_step": 604973, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9712873697280884, "global_step": 604974, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9169371128082275, "global_step": 604975, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.006596088409424, "global_step": 604976, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9905792474746704, "global_step": 604977, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0047779083251953, "global_step": 604978, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.987973690032959, "global_step": 604979, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0465168952941895, "global_step": 604980, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9293807744979858, "global_step": 604981, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.017702579498291, "global_step": 604982, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0816006660461426, "global_step": 604983, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9628435373306274, "global_step": 604984, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.965340256690979, "global_step": 604985, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.094877243041992, "global_step": 604986, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9806973934173584, "global_step": 604987, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0098891258239746, "global_step": 604988, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0732669830322266, "global_step": 604989, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9803342819213867, "global_step": 604990, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0020642280578613, "global_step": 604991, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0335922241210938, "global_step": 604992, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.024717330932617, "global_step": 604993, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0653839111328125, "global_step": 604994, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9679529666900635, "global_step": 604995, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.052666664123535, "global_step": 604996, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9717227220535278, "global_step": 604997, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9652032852172852, "global_step": 604998, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9701961278915405, "global_step": 604999, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.090718984603882, "global_step": 605000, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0160768032073975, "global_step": 605001, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0287506580352783, "global_step": 605002, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9869260787963867, "global_step": 605003, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.01692533493042, "global_step": 605004, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9961761236190796, "global_step": 605005, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0285983085632324, "global_step": 605006, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9916678667068481, "global_step": 605007, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0163707733154297, "global_step": 605008, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.042783260345459, "global_step": 605009, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0405619144439697, "global_step": 605010, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.043240547180176, "global_step": 605011, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9478302001953125, "global_step": 605012, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.046680212020874, "global_step": 605013, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.057365894317627, "global_step": 605014, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.000453233718872, "global_step": 605015, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9647701978683472, "global_step": 605016, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.030543565750122, "global_step": 605017, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9932129383087158, "global_step": 605018, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.037113666534424, "global_step": 605019, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0356385707855225, "global_step": 605020, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9940930604934692, "global_step": 605021, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0796568393707275, "global_step": 605022, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0444791316986084, "global_step": 605023, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0180740356445312, "global_step": 605024, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9762980937957764, "global_step": 605025, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9792640209197998, "global_step": 605026, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0839500427246094, "global_step": 605027, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0342085361480713, "global_step": 605028, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.03053617477417, "global_step": 605029, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9448162317276, "global_step": 605030, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9610575437545776, "global_step": 605031, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9758327007293701, "global_step": 605032, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0135738849639893, "global_step": 605033, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9536939859390259, "global_step": 605034, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0062263011932373, "global_step": 605035, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0050251483917236, "global_step": 605036, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.927914023399353, "global_step": 605037, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.978737235069275, "global_step": 605038, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.974947214126587, "global_step": 605039, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0157992839813232, "global_step": 605040, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9087131023406982, "global_step": 605041, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0899014472961426, "global_step": 605042, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.998002290725708, "global_step": 605043, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9788093566894531, "global_step": 605044, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.085287094116211, "global_step": 605045, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0411157608032227, "global_step": 605046, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.039027690887451, "global_step": 605047, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0244717597961426, "global_step": 605048, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9241291284561157, "global_step": 605049, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9552879333496094, "global_step": 605050, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.967491865158081, "global_step": 605051, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.957268476486206, "global_step": 605052, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.060096502304077, "global_step": 605053, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.009770631790161, "global_step": 605054, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.004871129989624, "global_step": 605055, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9489638805389404, "global_step": 605056, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9385071992874146, "global_step": 605057, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.046548843383789, "global_step": 605058, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9968701601028442, "global_step": 605059, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0100409984588623, "global_step": 605060, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.013235330581665, "global_step": 605061, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.974613070487976, "global_step": 605062, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9226056337356567, "global_step": 605063, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.966722846031189, "global_step": 605064, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.1113250255584717, "global_step": 605065, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9792002439498901, "global_step": 605066, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0322792530059814, "global_step": 605067, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9790116548538208, "global_step": 605068, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9414758682250977, "global_step": 605069, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.014983892440796, "global_step": 605070, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0512442588806152, "global_step": 605071, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9549453258514404, "global_step": 605072, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9338806867599487, "global_step": 605073, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0570626258850098, "global_step": 605074, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0273447036743164, "global_step": 605075, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0801098346710205, "global_step": 605076, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9772777557373047, "global_step": 605077, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.010091781616211, "global_step": 605078, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9644224643707275, "global_step": 605079, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9943193197250366, "global_step": 605080, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.034595251083374, "global_step": 605081, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9824038743972778, "global_step": 605082, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.032695770263672, "global_step": 605083, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0068933963775635, "global_step": 605084, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.010455846786499, "global_step": 605085, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.032625675201416, "global_step": 605086, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.99039626121521, "global_step": 605087, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9309446811676025, "global_step": 605088, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0180163383483887, "global_step": 605089, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0123131275177, "global_step": 605090, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.968215823173523, "global_step": 605091, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.973875641822815, "global_step": 605092, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.1165566444396973, "global_step": 605093, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0290403366088867, "global_step": 605094, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.018036365509033, "global_step": 605095, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0334620475769043, "global_step": 605096, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.029250144958496, "global_step": 605097, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0105185508728027, "global_step": 605098, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.082942008972168, "global_step": 605099, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0479178428649902, "global_step": 605100, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0028579235076904, "global_step": 605101, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.082092046737671, "global_step": 605102, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0468084812164307, "global_step": 605103, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9480359554290771, "global_step": 605104, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0533061027526855, "global_step": 605105, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9791803359985352, "global_step": 605106, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.989508867263794, "global_step": 605107, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0039401054382324, "global_step": 605108, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9226257801055908, "global_step": 605109, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.009229898452759, "global_step": 605110, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9491459131240845, "global_step": 605111, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0363614559173584, "global_step": 605112, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.000065803527832, "global_step": 605113, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0050482749938965, "global_step": 605114, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9843071699142456, "global_step": 605115, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9777462482452393, "global_step": 605116, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.027231216430664, "global_step": 605117, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9980878829956055, "global_step": 605118, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0569770336151123, "global_step": 605119, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0747311115264893, "global_step": 605120, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0123586654663086, "global_step": 605121, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9886165857315063, "global_step": 605122, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9802684783935547, "global_step": 605123, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9821302890777588, "global_step": 605124, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9497411251068115, "global_step": 605125, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9835395812988281, "global_step": 605126, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9805546998977661, "global_step": 605127, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9957422018051147, "global_step": 605128, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9677971601486206, "global_step": 605129, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0895867347717285, "global_step": 605130, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.014740467071533, "global_step": 605131, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.046415090560913, "global_step": 605132, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9243608713150024, "global_step": 605133, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0125298500061035, "global_step": 605134, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0765860080718994, "global_step": 605135, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.8938000202178955, "global_step": 605136, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.962524175643921, "global_step": 605137, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9864532947540283, "global_step": 605138, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9331674575805664, "global_step": 605139, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0681004524230957, "global_step": 605140, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0233304500579834, "global_step": 605141, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.010694980621338, "global_step": 605142, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0417237281799316, "global_step": 605143, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0073020458221436, "global_step": 605144, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0074520111083984, "global_step": 605145, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0055088996887207, "global_step": 605146, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.019922971725464, "global_step": 605147, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0712788105010986, "global_step": 605148, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9741226434707642, "global_step": 605149, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0526468753814697, "global_step": 605150, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9745410680770874, "global_step": 605151, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.033304452896118, "global_step": 605152, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.054941415786743, "global_step": 605153, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9548150300979614, "global_step": 605154, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.033594846725464, "global_step": 605155, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0827789306640625, "global_step": 605156, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.017857313156128, "global_step": 605157, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.029153347015381, "global_step": 605158, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0687808990478516, "global_step": 605159, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.012202262878418, "global_step": 605160, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9869343042373657, "global_step": 605161, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0080995559692383, "global_step": 605162, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9869089126586914, "global_step": 605163, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9617327451705933, "global_step": 605164, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0404703617095947, "global_step": 605165, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0130250453948975, "global_step": 605166, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.022115468978882, "global_step": 605167, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9979352951049805, "global_step": 605168, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0739572048187256, "global_step": 605169, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.047227382659912, "global_step": 605170, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.017040967941284, "global_step": 605171, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0322883129119873, "global_step": 605172, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.01477313041687, "global_step": 605173, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0701591968536377, "global_step": 605174, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.065148115158081, "global_step": 605175, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0061163902282715, "global_step": 605176, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.034102201461792, "global_step": 605177, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9412907361984253, "global_step": 605178, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.055258274078369, "global_step": 605179, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.063770055770874, "global_step": 605180, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0256869792938232, "global_step": 605181, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9872548580169678, "global_step": 605182, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0780720710754395, "global_step": 605183, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.028135061264038, "global_step": 605184, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.018841505050659, "global_step": 605185, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0375876426696777, "global_step": 605186, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.007094621658325, "global_step": 605187, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.989108920097351, "global_step": 605188, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.034162759780884, "global_step": 605189, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9862996339797974, "global_step": 605190, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0287961959838867, "global_step": 605191, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.057722806930542, "global_step": 605192, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.011711597442627, "global_step": 605193, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.03059458732605, "global_step": 605194, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9901585578918457, "global_step": 605195, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.978992223739624, "global_step": 605196, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9688230752944946, "global_step": 605197, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.972381591796875, "global_step": 605198, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.070103406906128, "global_step": 605199, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.105170249938965, "global_step": 605200, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.056442975997925, "global_step": 605201, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9740867614746094, "global_step": 605202, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.016657829284668, "global_step": 605203, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.977928638458252, "global_step": 605204, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0331997871398926, "global_step": 605205, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9936730861663818, "global_step": 605206, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0648698806762695, "global_step": 605207, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0327236652374268, "global_step": 605208, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.123918294906616, "global_step": 605209, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.055804491043091, "global_step": 605210, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.946173071861267, "global_step": 605211, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0515658855438232, "global_step": 605212, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.980151653289795, "global_step": 605213, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0334064960479736, "global_step": 605214, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9548146724700928, "global_step": 605215, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.00172758102417, "global_step": 605216, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9480725526809692, "global_step": 605217, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0270330905914307, "global_step": 605218, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0168118476867676, "global_step": 605219, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.015648603439331, "global_step": 605220, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.949257254600525, "global_step": 605221, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0603225231170654, "global_step": 605222, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9641836881637573, "global_step": 605223, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9811762571334839, "global_step": 605224, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.996776819229126, "global_step": 605225, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.03635835647583, "global_step": 605226, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9424511194229126, "global_step": 605227, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9391261339187622, "global_step": 605228, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.00622296333313, "global_step": 605229, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9985287189483643, "global_step": 605230, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9695409536361694, "global_step": 605231, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0127198696136475, "global_step": 605232, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9581531286239624, "global_step": 605233, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9976613521575928, "global_step": 605234, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9338150024414062, "global_step": 605235, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.919067621231079, "global_step": 605236, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0416765213012695, "global_step": 605237, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.036105155944824, "global_step": 605238, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9896316528320312, "global_step": 605239, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0946269035339355, "global_step": 605240, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0043282508850098, "global_step": 605241, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0746607780456543, "global_step": 605242, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9633209705352783, "global_step": 605243, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0200600624084473, "global_step": 605244, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.015855312347412, "global_step": 605245, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.018024444580078, "global_step": 605246, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.057621955871582, "global_step": 605247, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.033592939376831, "global_step": 605248, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9545161724090576, "global_step": 605249, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9643232822418213, "global_step": 605250, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0279436111450195, "global_step": 605251, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.026329517364502, "global_step": 605252, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9740238189697266, "global_step": 605253, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9871594905853271, "global_step": 605254, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0487875938415527, "global_step": 605255, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9976025819778442, "global_step": 605256, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0470378398895264, "global_step": 605257, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9576640129089355, "global_step": 605258, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0112102031707764, "global_step": 605259, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9959311485290527, "global_step": 605260, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.99593985080719, "global_step": 605261, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.025235891342163, "global_step": 605262, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0093674659729004, "global_step": 605263, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0934648513793945, "global_step": 605264, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9507910013198853, "global_step": 605265, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.01345157623291, "global_step": 605266, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.044715642929077, "global_step": 605267, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0052919387817383, "global_step": 605268, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0480170249938965, "global_step": 605269, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.038529872894287, "global_step": 605270, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0164661407470703, "global_step": 605271, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9850661754608154, "global_step": 605272, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0327210426330566, "global_step": 605273, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0662052631378174, "global_step": 605274, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.065502405166626, "global_step": 605275, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0464000701904297, "global_step": 605276, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.137289047241211, "global_step": 605277, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0803236961364746, "global_step": 605278, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.037890911102295, "global_step": 605279, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9877514839172363, "global_step": 605280, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.069427967071533, "global_step": 605281, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.012051582336426, "global_step": 605282, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.028022289276123, "global_step": 605283, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9350718259811401, "global_step": 605284, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9839674234390259, "global_step": 605285, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.884472131729126, "global_step": 605286, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9797419309616089, "global_step": 605287, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.010291576385498, "global_step": 605288, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0053248405456543, "global_step": 605289, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9840301275253296, "global_step": 605290, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0949654579162598, "global_step": 605291, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9910264015197754, "global_step": 605292, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0283021926879883, "global_step": 605293, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0793235301971436, "global_step": 605294, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0519814491271973, "global_step": 605295, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0041940212249756, "global_step": 605296, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0836029052734375, "global_step": 605297, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0329368114471436, "global_step": 605298, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0574302673339844, "global_step": 605299, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.954518437385559, "global_step": 605300, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0346577167510986, "global_step": 605301, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0518076419830322, "global_step": 605302, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0275485515594482, "global_step": 605303, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.000805139541626, "global_step": 605304, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9362945556640625, "global_step": 605305, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0294618606567383, "global_step": 605306, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0945119857788086, "global_step": 605307, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0209946632385254, "global_step": 605308, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.009526014328003, "global_step": 605309, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0339338779449463, "global_step": 605310, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.956710696220398, "global_step": 605311, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.067399263381958, "global_step": 605312, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9637107849121094, "global_step": 605313, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.1006038188934326, "global_step": 605314, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.8962035179138184, "global_step": 605315, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9939996004104614, "global_step": 605316, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0751712322235107, "global_step": 605317, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9961076974868774, "global_step": 605318, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0215225219726562, "global_step": 605319, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.028609037399292, "global_step": 605320, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.999804973602295, "global_step": 605321, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0218472480773926, "global_step": 605322, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.043382167816162, "global_step": 605323, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.988223910331726, "global_step": 605324, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.1114373207092285, "global_step": 605325, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9821407794952393, "global_step": 605326, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0223844051361084, "global_step": 605327, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.044337749481201, "global_step": 605328, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0430214405059814, "global_step": 605329, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0405006408691406, "global_step": 605330, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9729558229446411, "global_step": 605331, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.00388503074646, "global_step": 605332, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9282009601593018, "global_step": 605333, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9221714735031128, "global_step": 605334, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.027127742767334, "global_step": 605335, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0666391849517822, "global_step": 605336, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.053725242614746, "global_step": 605337, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.1014232635498047, "global_step": 605338, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9770944118499756, "global_step": 605339, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0538442134857178, "global_step": 605340, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9555588960647583, "global_step": 605341, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9756934642791748, "global_step": 605342, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.965300440788269, "global_step": 605343, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0678470134735107, "global_step": 605344, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.021955728530884, "global_step": 605345, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.019794225692749, "global_step": 605346, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0675249099731445, "global_step": 605347, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0368237495422363, "global_step": 605348, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0449891090393066, "global_step": 605349, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9376318454742432, "global_step": 605350, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0171525478363037, "global_step": 605351, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.929736852645874, "global_step": 605352, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9942224025726318, "global_step": 605353, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.038945436477661, "global_step": 605354, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9795671701431274, "global_step": 605355, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.038945198059082, "global_step": 605356, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0461885929107666, "global_step": 605357, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0094025135040283, "global_step": 605358, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.065099000930786, "global_step": 605359, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.949983835220337, "global_step": 605360, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9941813945770264, "global_step": 605361, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.057040214538574, "global_step": 605362, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0583512783050537, "global_step": 605363, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9790751934051514, "global_step": 605364, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.000868797302246, "global_step": 605365, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9511984586715698, "global_step": 605366, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.057208299636841, "global_step": 605367, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9024267196655273, "global_step": 605368, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0549569129943848, "global_step": 605369, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.97299063205719, "global_step": 605370, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.981934666633606, "global_step": 605371, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0038909912109375, "global_step": 605372, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0514066219329834, "global_step": 605373, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.035623073577881, "global_step": 605374, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9822964668273926, "global_step": 605375, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0482213497161865, "global_step": 605376, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0921497344970703, "global_step": 605377, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9594169855117798, "global_step": 605378, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9938157796859741, "global_step": 605379, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9614781141281128, "global_step": 605380, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.036932945251465, "global_step": 605381, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.014846086502075, "global_step": 605382, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.073312520980835, "global_step": 605383, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.90579354763031, "global_step": 605384, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0578439235687256, "global_step": 605385, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9643324613571167, "global_step": 605386, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9694042205810547, "global_step": 605387, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9236671924591064, "global_step": 605388, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9715516567230225, "global_step": 605389, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0299477577209473, "global_step": 605390, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9719089269638062, "global_step": 605391, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0449249744415283, "global_step": 605392, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0389294624328613, "global_step": 605393, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0750293731689453, "global_step": 605394, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.050713062286377, "global_step": 605395, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9818480014801025, "global_step": 605396, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.971948504447937, "global_step": 605397, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.042280435562134, "global_step": 605398, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.005448818206787, "global_step": 605399, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.029245138168335, "global_step": 605400, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0017549991607666, "global_step": 605401, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0568816661834717, "global_step": 605402, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.962414264678955, "global_step": 605403, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9718821048736572, "global_step": 605404, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.002807140350342, "global_step": 605405, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0100114345550537, "global_step": 605406, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0163536071777344, "global_step": 605407, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.051910638809204, "global_step": 605408, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9277971982955933, "global_step": 605409, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.986276626586914, "global_step": 605410, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9818835258483887, "global_step": 605411, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0319833755493164, "global_step": 605412, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9618762731552124, "global_step": 605413, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.005505323410034, "global_step": 605414, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0106706619262695, "global_step": 605415, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.071240186691284, "global_step": 605416, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0800230503082275, "global_step": 605417, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0476410388946533, "global_step": 605418, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.005819320678711, "global_step": 605419, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9527432918548584, "global_step": 605420, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0211410522460938, "global_step": 605421, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0557799339294434, "global_step": 605422, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.1193935871124268, "global_step": 605423, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0468802452087402, "global_step": 605424, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.003471851348877, "global_step": 605425, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.072437286376953, "global_step": 605426, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9664639234542847, "global_step": 605427, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9732526540756226, "global_step": 605428, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9997565746307373, "global_step": 605429, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9006690979003906, "global_step": 605430, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0048539638519287, "global_step": 605431, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9789713621139526, "global_step": 605432, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0455281734466553, "global_step": 605433, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.051917791366577, "global_step": 605434, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0983972549438477, "global_step": 605435, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9887970685958862, "global_step": 605436, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9835267066955566, "global_step": 605437, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.129267692565918, "global_step": 605438, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0378549098968506, "global_step": 605439, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9881621599197388, "global_step": 605440, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0171947479248047, "global_step": 605441, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0142526626586914, "global_step": 605442, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9341858625411987, "global_step": 605443, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0039563179016113, "global_step": 605444, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0691304206848145, "global_step": 605445, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.979346752166748, "global_step": 605446, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.922865867614746, "global_step": 605447, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9500693082809448, "global_step": 605448, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.01070499420166, "global_step": 605449, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9647281169891357, "global_step": 605450, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0069282054901123, "global_step": 605451, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0764734745025635, "global_step": 605452, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0064451694488525, "global_step": 605453, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9922481775283813, "global_step": 605454, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0732421875, "global_step": 605455, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.017241954803467, "global_step": 605456, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0370373725891113, "global_step": 605457, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.045720338821411, "global_step": 605458, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.010582447052002, "global_step": 605459, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9975254535675049, "global_step": 605460, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9524961709976196, "global_step": 605461, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9816720485687256, "global_step": 605462, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.022221088409424, "global_step": 605463, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.002798557281494, "global_step": 605464, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9829448461532593, "global_step": 605465, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0271568298339844, "global_step": 605466, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.996869444847107, "global_step": 605467, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9990694522857666, "global_step": 605468, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9947320222854614, "global_step": 605469, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0205838680267334, "global_step": 605470, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0728566646575928, "global_step": 605471, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.031477212905884, "global_step": 605472, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0320303440093994, "global_step": 605473, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9328879117965698, "global_step": 605474, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9540905952453613, "global_step": 605475, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9486781358718872, "global_step": 605476, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9931589365005493, "global_step": 605477, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.089205503463745, "global_step": 605478, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9542142152786255, "global_step": 605479, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.011434555053711, "global_step": 605480, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.017632007598877, "global_step": 605481, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0774331092834473, "global_step": 605482, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0239524841308594, "global_step": 605483, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9717704057693481, "global_step": 605484, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0521976947784424, "global_step": 605485, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.044940710067749, "global_step": 605486, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0817530155181885, "global_step": 605487, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0228829383850098, "global_step": 605488, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.022674083709717, "global_step": 605489, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0143909454345703, "global_step": 605490, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0984764099121094, "global_step": 605491, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9949532747268677, "global_step": 605492, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0352249145507812, "global_step": 605493, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.127192497253418, "global_step": 605494, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0542891025543213, "global_step": 605495, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0332043170928955, "global_step": 605496, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.1187708377838135, "global_step": 605497, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9268951416015625, "global_step": 605498, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.8332034349441528, "global_step": 605499, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.064483165740967, "global_step": 605500, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0196805000305176, "global_step": 605501, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0432002544403076, "global_step": 605502, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9482325315475464, "global_step": 605503, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.088881492614746, "global_step": 605504, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9706385135650635, "global_step": 605505, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.990257740020752, "global_step": 605506, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.989469051361084, "global_step": 605507, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.004582166671753, "global_step": 605508, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9927870035171509, "global_step": 605509, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.081881284713745, "global_step": 605510, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.021402597427368, "global_step": 605511, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.088609218597412, "global_step": 605512, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9285329580307007, "global_step": 605513, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0484864711761475, "global_step": 605514, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9862569570541382, "global_step": 605515, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0788209438323975, "global_step": 605516, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0058183670043945, "global_step": 605517, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.059394359588623, "global_step": 605518, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.897032618522644, "global_step": 605519, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9302176237106323, "global_step": 605520, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.007901906967163, "global_step": 605521, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0550196170806885, "global_step": 605522, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0469772815704346, "global_step": 605523, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0458617210388184, "global_step": 605524, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0194082260131836, "global_step": 605525, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0048274993896484, "global_step": 605526, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.978908896446228, "global_step": 605527, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.034794807434082, "global_step": 605528, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0647132396698, "global_step": 605529, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0597383975982666, "global_step": 605530, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0000839233398438, "global_step": 605531, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0058341026306152, "global_step": 605532, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0933778285980225, "global_step": 605533, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9784221649169922, "global_step": 605534, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9999759197235107, "global_step": 605535, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9761008024215698, "global_step": 605536, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.1106009483337402, "global_step": 605537, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.07346773147583, "global_step": 605538, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0451760292053223, "global_step": 605539, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9987696409225464, "global_step": 605540, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.005765199661255, "global_step": 605541, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0226709842681885, "global_step": 605542, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0137126445770264, "global_step": 605543, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0673627853393555, "global_step": 605544, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.04944109916687, "global_step": 605545, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.946961522102356, "global_step": 605546, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.037743330001831, "global_step": 605547, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.003899335861206, "global_step": 605548, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.054980754852295, "global_step": 605549, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.090053081512451, "global_step": 605550, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.005075216293335, "global_step": 605551, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0550622940063477, "global_step": 605552, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9530317783355713, "global_step": 605553, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0240895748138428, "global_step": 605554, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.889460802078247, "global_step": 605555, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9958536624908447, "global_step": 605556, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.022519111633301, "global_step": 605557, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.042393207550049, "global_step": 605558, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.959464192390442, "global_step": 605559, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0913279056549072, "global_step": 605560, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.034329414367676, "global_step": 605561, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9214894771575928, "global_step": 605562, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0312657356262207, "global_step": 605563, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9830127954483032, "global_step": 605564, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.017683982849121, "global_step": 605565, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.994104266166687, "global_step": 605566, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9971681833267212, "global_step": 605567, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.063321352005005, "global_step": 605568, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.015918254852295, "global_step": 605569, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.011045455932617, "global_step": 605570, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9230828285217285, "global_step": 605571, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9929192066192627, "global_step": 605572, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0083224773406982, "global_step": 605573, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.039395570755005, "global_step": 605574, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9935585260391235, "global_step": 605575, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9843285083770752, "global_step": 605576, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9626227617263794, "global_step": 605577, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0788893699645996, "global_step": 605578, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9921513795852661, "global_step": 605579, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.007383346557617, "global_step": 605580, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9809175729751587, "global_step": 605581, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9787918329238892, "global_step": 605582, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0303285121917725, "global_step": 605583, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.999870777130127, "global_step": 605584, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9654369354248047, "global_step": 605585, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0503571033477783, "global_step": 605586, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9947409629821777, "global_step": 605587, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0578548908233643, "global_step": 605588, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.011629581451416, "global_step": 605589, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.100557804107666, "global_step": 605590, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.012465715408325, "global_step": 605591, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.958078384399414, "global_step": 605592, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9628283977508545, "global_step": 605593, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0223636627197266, "global_step": 605594, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.967942476272583, "global_step": 605595, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0190701484680176, "global_step": 605596, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0276010036468506, "global_step": 605597, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9558192491531372, "global_step": 605598, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9692840576171875, "global_step": 605599, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.040339708328247, "global_step": 605600, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9885300397872925, "global_step": 605601, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.029414176940918, "global_step": 605602, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0043039321899414, "global_step": 605603, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0806081295013428, "global_step": 605604, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.004369020462036, "global_step": 605605, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0384624004364014, "global_step": 605606, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.981337547302246, "global_step": 605607, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9558628797531128, "global_step": 605608, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.004121780395508, "global_step": 605609, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.005634307861328, "global_step": 605610, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9630634784698486, "global_step": 605611, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9530647993087769, "global_step": 605612, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0298843383789062, "global_step": 605613, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0346195697784424, "global_step": 605614, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.019575357437134, "global_step": 605615, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9932035207748413, "global_step": 605616, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.068134307861328, "global_step": 605617, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.033513069152832, "global_step": 605618, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.988516926765442, "global_step": 605619, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0063109397888184, "global_step": 605620, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0305240154266357, "global_step": 605621, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.006434440612793, "global_step": 605622, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.121248483657837, "global_step": 605623, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.03381609916687, "global_step": 605624, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.034240245819092, "global_step": 605625, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9982516765594482, "global_step": 605626, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0142343044281006, "global_step": 605627, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.988519310951233, "global_step": 605628, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9805876016616821, "global_step": 605629, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0716731548309326, "global_step": 605630, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9507980346679688, "global_step": 605631, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.089233875274658, "global_step": 605632, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.078965663909912, "global_step": 605633, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.092482805252075, "global_step": 605634, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.145869255065918, "global_step": 605635, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.042875289916992, "global_step": 605636, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9768781661987305, "global_step": 605637, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9918460845947266, "global_step": 605638, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.010035276412964, "global_step": 605639, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9813623428344727, "global_step": 605640, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.02883243560791, "global_step": 605641, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0331928730010986, "global_step": 605642, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.04431414604187, "global_step": 605643, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9433093070983887, "global_step": 605644, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.049393653869629, "global_step": 605645, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0263640880584717, "global_step": 605646, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0426061153411865, "global_step": 605647, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0082602500915527, "global_step": 605648, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0845887660980225, "global_step": 605649, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0256996154785156, "global_step": 605650, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9928804636001587, "global_step": 605651, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9969844818115234, "global_step": 605652, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0158562660217285, "global_step": 605653, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.023437738418579, "global_step": 605654, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.042330026626587, "global_step": 605655, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0391130447387695, "global_step": 605656, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9605462551116943, "global_step": 605657, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9752509593963623, "global_step": 605658, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0038414001464844, "global_step": 605659, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0399160385131836, "global_step": 605660, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.064288377761841, "global_step": 605661, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.061464309692383, "global_step": 605662, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9301592111587524, "global_step": 605663, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0761771202087402, "global_step": 605664, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0008857250213623, "global_step": 605665, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0426251888275146, "global_step": 605666, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0231099128723145, "global_step": 605667, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9590075016021729, "global_step": 605668, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9929687976837158, "global_step": 605669, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0861291885375977, "global_step": 605670, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.010481119155884, "global_step": 605671, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9666322469711304, "global_step": 605672, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.038912057876587, "global_step": 605673, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0899105072021484, "global_step": 605674, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.1168179512023926, "global_step": 605675, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0026450157165527, "global_step": 605676, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9882985353469849, "global_step": 605677, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.958367109298706, "global_step": 605678, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0030782222747803, "global_step": 605679, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.99624502658844, "global_step": 605680, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9812703132629395, "global_step": 605681, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9596961736679077, "global_step": 605682, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9577716588974, "global_step": 605683, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9815853834152222, "global_step": 605684, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9735678434371948, "global_step": 605685, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.033327579498291, "global_step": 605686, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0700364112854004, "global_step": 605687, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0467984676361084, "global_step": 605688, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.040759325027466, "global_step": 605689, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0738861560821533, "global_step": 605690, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9916021823883057, "global_step": 605691, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.103013753890991, "global_step": 605692, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.944054126739502, "global_step": 605693, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0328259468078613, "global_step": 605694, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9422613382339478, "global_step": 605695, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.07063889503479, "global_step": 605696, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.049236297607422, "global_step": 605697, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9151506423950195, "global_step": 605698, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0850679874420166, "global_step": 605699, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9818761348724365, "global_step": 605700, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0183568000793457, "global_step": 605701, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0077881813049316, "global_step": 605702, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9744312763214111, "global_step": 605703, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0579230785369873, "global_step": 605704, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0555615425109863, "global_step": 605705, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9677685499191284, "global_step": 605706, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0138609409332275, "global_step": 605707, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.028172492980957, "global_step": 605708, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.06040096282959, "global_step": 605709, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9507395029067993, "global_step": 605710, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9705957174301147, "global_step": 605711, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9897722005844116, "global_step": 605712, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9969699382781982, "global_step": 605713, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9686764478683472, "global_step": 605714, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9782636165618896, "global_step": 605715, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.041323661804199, "global_step": 605716, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9389516115188599, "global_step": 605717, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9847689867019653, "global_step": 605718, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.039396047592163, "global_step": 605719, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0458266735076904, "global_step": 605720, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9843947887420654, "global_step": 605721, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0057389736175537, "global_step": 605722, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0280001163482666, "global_step": 605723, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.027275323867798, "global_step": 605724, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.016704559326172, "global_step": 605725, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9252983331680298, "global_step": 605726, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9942306280136108, "global_step": 605727, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.016896963119507, "global_step": 605728, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9389660358428955, "global_step": 605729, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9530160427093506, "global_step": 605730, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.088080883026123, "global_step": 605731, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.044304609298706, "global_step": 605732, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9663459062576294, "global_step": 605733, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0276825428009033, "global_step": 605734, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.1276090145111084, "global_step": 605735, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9270521402359009, "global_step": 605736, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0553197860717773, "global_step": 605737, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0168614387512207, "global_step": 605738, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9977209568023682, "global_step": 605739, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.018317222595215, "global_step": 605740, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.021674633026123, "global_step": 605741, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0304510593414307, "global_step": 605742, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0143401622772217, "global_step": 605743, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9390549659729004, "global_step": 605744, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0014591217041016, "global_step": 605745, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9814949035644531, "global_step": 605746, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0599687099456787, "global_step": 605747, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9847923517227173, "global_step": 605748, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9565162658691406, "global_step": 605749, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0126423835754395, "global_step": 605750, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9337990283966064, "global_step": 605751, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.028594732284546, "global_step": 605752, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.00590181350708, "global_step": 605753, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9984434843063354, "global_step": 605754, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9683674573898315, "global_step": 605755, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0337138175964355, "global_step": 605756, "epoch": 974, "lr": 5e-05}
{"train_loss": 2.0092384815216064, "global_step": 605757, "epoch": 974, "lr": 5e-05}
{"train_loss": 1.9357935190200806, "global_step": 605758, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9233540296554565, "global_step": 605759, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9920481443405151, "global_step": 605760, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.028937578201294, "global_step": 605761, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9680745601654053, "global_step": 605762, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9932875633239746, "global_step": 605763, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0456862449645996, "global_step": 605764, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9018816947937012, "global_step": 605765, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0204203128814697, "global_step": 605766, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9660544395446777, "global_step": 605767, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.962300181388855, "global_step": 605768, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0342535972595215, "global_step": 605769, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0231146812438965, "global_step": 605770, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.953747034072876, "global_step": 605771, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0144529342651367, "global_step": 605772, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9494671821594238, "global_step": 605773, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0475101470947266, "global_step": 605774, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0273663997650146, "global_step": 605775, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.059833288192749, "global_step": 605776, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9144511222839355, "global_step": 605777, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9997951984405518, "global_step": 605778, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9658043384552002, "global_step": 605779, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9864758253097534, "global_step": 605780, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0209624767303467, "global_step": 605781, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9669911861419678, "global_step": 605782, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.994963526725769, "global_step": 605783, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9695042371749878, "global_step": 605784, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1032416820526123, "global_step": 605785, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9656567573547363, "global_step": 605786, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9769923686981201, "global_step": 605787, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9918158054351807, "global_step": 605788, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.972955346107483, "global_step": 605789, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0882465839385986, "global_step": 605790, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.017197847366333, "global_step": 605791, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0234854221343994, "global_step": 605792, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0045671463012695, "global_step": 605793, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1239755153656006, "global_step": 605794, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.068270683288574, "global_step": 605795, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9741299152374268, "global_step": 605796, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9959604740142822, "global_step": 605797, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0517616271972656, "global_step": 605798, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.957654595375061, "global_step": 605799, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.8860900402069092, "global_step": 605800, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.017352342605591, "global_step": 605801, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.014857053756714, "global_step": 605802, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0233004093170166, "global_step": 605803, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.014847993850708, "global_step": 605804, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0206544399261475, "global_step": 605805, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.982089877128601, "global_step": 605806, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0979959964752197, "global_step": 605807, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0871469974517822, "global_step": 605808, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0441386699676514, "global_step": 605809, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0154342651367188, "global_step": 605810, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.021268844604492, "global_step": 605811, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0107157230377197, "global_step": 605812, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9502822160720825, "global_step": 605813, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0994081497192383, "global_step": 605814, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9676613807678223, "global_step": 605815, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.974457859992981, "global_step": 605816, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.055804967880249, "global_step": 605817, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0211732387542725, "global_step": 605818, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0051050186157227, "global_step": 605819, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0039618015289307, "global_step": 605820, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9805526733398438, "global_step": 605821, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9835538864135742, "global_step": 605822, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.057884931564331, "global_step": 605823, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0814530849456787, "global_step": 605824, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.036958932876587, "global_step": 605825, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0042757987976074, "global_step": 605826, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0294551849365234, "global_step": 605827, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9756793975830078, "global_step": 605828, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0974502563476562, "global_step": 605829, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0658328533172607, "global_step": 605830, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0016915798187256, "global_step": 605831, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.028125524520874, "global_step": 605832, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.913438081741333, "global_step": 605833, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0286877155303955, "global_step": 605834, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9294583797454834, "global_step": 605835, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9390547275543213, "global_step": 605836, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.992104172706604, "global_step": 605837, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9616304636001587, "global_step": 605838, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0340189933776855, "global_step": 605839, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.047220230102539, "global_step": 605840, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.090289354324341, "global_step": 605841, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.990761160850525, "global_step": 605842, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0513763427734375, "global_step": 605843, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9823600053787231, "global_step": 605844, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9779118299484253, "global_step": 605845, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.040923595428467, "global_step": 605846, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.015577554702759, "global_step": 605847, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9694079160690308, "global_step": 605848, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0907461643218994, "global_step": 605849, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0272140502929688, "global_step": 605850, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9633859395980835, "global_step": 605851, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.097806215286255, "global_step": 605852, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.970294713973999, "global_step": 605853, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.096498966217041, "global_step": 605854, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0489766597747803, "global_step": 605855, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0568273067474365, "global_step": 605856, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.050595283508301, "global_step": 605857, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0357308387756348, "global_step": 605858, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.868283748626709, "global_step": 605859, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0077064037323, "global_step": 605860, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9805303812026978, "global_step": 605861, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9653202295303345, "global_step": 605862, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9795180559158325, "global_step": 605863, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0118441581726074, "global_step": 605864, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9610545635223389, "global_step": 605865, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0085995197296143, "global_step": 605866, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9891060590744019, "global_step": 605867, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0157406330108643, "global_step": 605868, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9854772090911865, "global_step": 605869, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.008117914199829, "global_step": 605870, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0185179710388184, "global_step": 605871, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.02323055267334, "global_step": 605872, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0136845111846924, "global_step": 605873, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9409421682357788, "global_step": 605874, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9893946647644043, "global_step": 605875, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0018973350524902, "global_step": 605876, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0848934650421143, "global_step": 605877, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9667530059814453, "global_step": 605878, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.059187889099121, "global_step": 605879, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.067567825317383, "global_step": 605880, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.8962737321853638, "global_step": 605881, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.02563214302063, "global_step": 605882, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.003298044204712, "global_step": 605883, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9580076932907104, "global_step": 605884, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0755362510681152, "global_step": 605885, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9260454177856445, "global_step": 605886, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9906600713729858, "global_step": 605887, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9125771522521973, "global_step": 605888, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9902143478393555, "global_step": 605889, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9689011573791504, "global_step": 605890, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.060157537460327, "global_step": 605891, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9173808097839355, "global_step": 605892, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.977446436882019, "global_step": 605893, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0503058433532715, "global_step": 605894, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.112377882003784, "global_step": 605895, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0449423789978027, "global_step": 605896, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9321528673171997, "global_step": 605897, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.007195234298706, "global_step": 605898, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0207083225250244, "global_step": 605899, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0685927867889404, "global_step": 605900, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0006463527679443, "global_step": 605901, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9511137008666992, "global_step": 605902, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9078301191329956, "global_step": 605903, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9942426681518555, "global_step": 605904, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9074829816818237, "global_step": 605905, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.992034673690796, "global_step": 605906, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.991248607635498, "global_step": 605907, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9935400485992432, "global_step": 605908, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9997620582580566, "global_step": 605909, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0176401138305664, "global_step": 605910, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.006737470626831, "global_step": 605911, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0147085189819336, "global_step": 605912, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1048824787139893, "global_step": 605913, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.986380696296692, "global_step": 605914, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9538555145263672, "global_step": 605915, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9977607727050781, "global_step": 605916, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9975330829620361, "global_step": 605917, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.042893886566162, "global_step": 605918, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9582668542861938, "global_step": 605919, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0025768280029297, "global_step": 605920, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9668428897857666, "global_step": 605921, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9439194202423096, "global_step": 605922, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9210647344589233, "global_step": 605923, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.015199899673462, "global_step": 605924, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.097140312194824, "global_step": 605925, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9792777299880981, "global_step": 605926, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0005154609680176, "global_step": 605927, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0087602138519287, "global_step": 605928, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9131351709365845, "global_step": 605929, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9581953287124634, "global_step": 605930, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0276525020599365, "global_step": 605931, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9708713293075562, "global_step": 605932, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0719943046569824, "global_step": 605933, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.8929845094680786, "global_step": 605934, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0790224075317383, "global_step": 605935, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0357232093811035, "global_step": 605936, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9964584112167358, "global_step": 605937, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0746445655822754, "global_step": 605938, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9773818254470825, "global_step": 605939, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0285799503326416, "global_step": 605940, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0533382892608643, "global_step": 605941, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.915183186531067, "global_step": 605942, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0209522247314453, "global_step": 605943, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0104856491088867, "global_step": 605944, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.908622145652771, "global_step": 605945, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0968055725097656, "global_step": 605946, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9968544244766235, "global_step": 605947, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0281484127044678, "global_step": 605948, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9691041707992554, "global_step": 605949, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9807722568511963, "global_step": 605950, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9888302087783813, "global_step": 605951, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0332953929901123, "global_step": 605952, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.06016206741333, "global_step": 605953, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9468063116073608, "global_step": 605954, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9724597930908203, "global_step": 605955, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.045243263244629, "global_step": 605956, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.016317129135132, "global_step": 605957, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9863274097442627, "global_step": 605958, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.046851634979248, "global_step": 605959, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.98983633518219, "global_step": 605960, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9990050792694092, "global_step": 605961, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0290794372558594, "global_step": 605962, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9789602756500244, "global_step": 605963, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0216493606567383, "global_step": 605964, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9942585229873657, "global_step": 605965, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9937257766723633, "global_step": 605966, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9101966619491577, "global_step": 605967, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0639808177948, "global_step": 605968, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.937019944190979, "global_step": 605969, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0093250274658203, "global_step": 605970, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9570097923278809, "global_step": 605971, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9667425155639648, "global_step": 605972, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0353565216064453, "global_step": 605973, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0133140087127686, "global_step": 605974, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9992542266845703, "global_step": 605975, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.001690626144409, "global_step": 605976, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9871004819869995, "global_step": 605977, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9561591148376465, "global_step": 605978, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0862295627593994, "global_step": 605979, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.07116961479187, "global_step": 605980, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0489108562469482, "global_step": 605981, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0059895515441895, "global_step": 605982, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.114682674407959, "global_step": 605983, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1341686248779297, "global_step": 605984, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9662139415740967, "global_step": 605985, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9773879051208496, "global_step": 605986, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9780588150024414, "global_step": 605987, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0176780223846436, "global_step": 605988, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.040048837661743, "global_step": 605989, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0176093578338623, "global_step": 605990, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.992077112197876, "global_step": 605991, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9593186378479004, "global_step": 605992, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9183995723724365, "global_step": 605993, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0210676193237305, "global_step": 605994, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0024161338806152, "global_step": 605995, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0767626762390137, "global_step": 605996, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.067657709121704, "global_step": 605997, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9035820960998535, "global_step": 605998, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9608725309371948, "global_step": 605999, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9764699935913086, "global_step": 606000, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.942018747329712, "global_step": 606001, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9923295974731445, "global_step": 606002, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9202499389648438, "global_step": 606003, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0071234703063965, "global_step": 606004, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9402216672897339, "global_step": 606005, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9610952138900757, "global_step": 606006, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0556795597076416, "global_step": 606007, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9436298608779907, "global_step": 606008, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.046649217605591, "global_step": 606009, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.071855306625366, "global_step": 606010, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9419621229171753, "global_step": 606011, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9367377758026123, "global_step": 606012, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0627028942108154, "global_step": 606013, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0574395656585693, "global_step": 606014, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1371700763702393, "global_step": 606015, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9661937952041626, "global_step": 606016, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9373865127563477, "global_step": 606017, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.015840768814087, "global_step": 606018, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.036715507507324, "global_step": 606019, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9960472583770752, "global_step": 606020, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.048941135406494, "global_step": 606021, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.983276128768921, "global_step": 606022, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9547605514526367, "global_step": 606023, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0474233627319336, "global_step": 606024, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0490293502807617, "global_step": 606025, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.006373167037964, "global_step": 606026, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0285484790802, "global_step": 606027, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9802802801132202, "global_step": 606028, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.888718843460083, "global_step": 606029, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0487446784973145, "global_step": 606030, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1251912117004395, "global_step": 606031, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.066335439682007, "global_step": 606032, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9333727359771729, "global_step": 606033, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.026198387145996, "global_step": 606034, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.038163661956787, "global_step": 606035, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0401248931884766, "global_step": 606036, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0161232948303223, "global_step": 606037, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0342698097229004, "global_step": 606038, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0807530879974365, "global_step": 606039, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.948243498802185, "global_step": 606040, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0319008827209473, "global_step": 606041, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9094626903533936, "global_step": 606042, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0107390880584717, "global_step": 606043, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.041365146636963, "global_step": 606044, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9546451568603516, "global_step": 606045, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9579657316207886, "global_step": 606046, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.024955987930298, "global_step": 606047, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9730249643325806, "global_step": 606048, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9962968826293945, "global_step": 606049, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9496958255767822, "global_step": 606050, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9953584671020508, "global_step": 606051, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.993783950805664, "global_step": 606052, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.942011833190918, "global_step": 606053, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9400346279144287, "global_step": 606054, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9235479831695557, "global_step": 606055, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9496535062789917, "global_step": 606056, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9644231796264648, "global_step": 606057, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9495929479599, "global_step": 606058, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9433802366256714, "global_step": 606059, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.028873920440674, "global_step": 606060, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.942857027053833, "global_step": 606061, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0281598567962646, "global_step": 606062, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.03045392036438, "global_step": 606063, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0407886505126953, "global_step": 606064, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9997341632843018, "global_step": 606065, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.047400951385498, "global_step": 606066, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0813093185424805, "global_step": 606067, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0027496814727783, "global_step": 606068, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.009652614593506, "global_step": 606069, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9735405445098877, "global_step": 606070, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0755093097686768, "global_step": 606071, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.902672290802002, "global_step": 606072, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.083277463912964, "global_step": 606073, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0097882747650146, "global_step": 606074, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9638158082962036, "global_step": 606075, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9814348220825195, "global_step": 606076, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9646064043045044, "global_step": 606077, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9979805946350098, "global_step": 606078, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.046926498413086, "global_step": 606079, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.993942379951477, "global_step": 606080, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9795494079589844, "global_step": 606081, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.957291841506958, "global_step": 606082, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.001833438873291, "global_step": 606083, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9638413190841675, "global_step": 606084, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9848395586013794, "global_step": 606085, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9780967235565186, "global_step": 606086, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9548356533050537, "global_step": 606087, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9224574565887451, "global_step": 606088, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0031094551086426, "global_step": 606089, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.011951446533203, "global_step": 606090, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9639875888824463, "global_step": 606091, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.975999116897583, "global_step": 606092, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9523565769195557, "global_step": 606093, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9770451784133911, "global_step": 606094, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0633671283721924, "global_step": 606095, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.061157464981079, "global_step": 606096, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0023157596588135, "global_step": 606097, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.992124080657959, "global_step": 606098, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9491432905197144, "global_step": 606099, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9235217571258545, "global_step": 606100, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.99985671043396, "global_step": 606101, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9994218349456787, "global_step": 606102, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.077554941177368, "global_step": 606103, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9548715353012085, "global_step": 606104, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0142195224761963, "global_step": 606105, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0350112915039062, "global_step": 606106, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0033323764801025, "global_step": 606107, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9689302444458008, "global_step": 606108, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0761139392852783, "global_step": 606109, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9343256950378418, "global_step": 606110, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.040684938430786, "global_step": 606111, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9989025592803955, "global_step": 606112, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0000691413879395, "global_step": 606113, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.01216721534729, "global_step": 606114, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0196847915649414, "global_step": 606115, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0536062717437744, "global_step": 606116, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.8751813173294067, "global_step": 606117, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9868693351745605, "global_step": 606118, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.080519199371338, "global_step": 606119, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0422818660736084, "global_step": 606120, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.062574863433838, "global_step": 606121, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.061213493347168, "global_step": 606122, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.03835391998291, "global_step": 606123, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0123956203460693, "global_step": 606124, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.022087335586548, "global_step": 606125, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.089388370513916, "global_step": 606126, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.00566029548645, "global_step": 606127, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9702924489974976, "global_step": 606128, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0297505855560303, "global_step": 606129, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.001905679702759, "global_step": 606130, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.961300015449524, "global_step": 606131, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.8959091901779175, "global_step": 606132, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0317084789276123, "global_step": 606133, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.960089087486267, "global_step": 606134, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0042896270751953, "global_step": 606135, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.020836114883423, "global_step": 606136, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9934148788452148, "global_step": 606137, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9872909784317017, "global_step": 606138, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0453245639801025, "global_step": 606139, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.004817247390747, "global_step": 606140, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0652730464935303, "global_step": 606141, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0416412353515625, "global_step": 606142, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.01613187789917, "global_step": 606143, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0938782691955566, "global_step": 606144, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.039242744445801, "global_step": 606145, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9726897478103638, "global_step": 606146, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9726248979568481, "global_step": 606147, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0187196731567383, "global_step": 606148, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0911293029785156, "global_step": 606149, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0089378356933594, "global_step": 606150, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0824508666992188, "global_step": 606151, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0262069702148438, "global_step": 606152, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0424423217773438, "global_step": 606153, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9579709768295288, "global_step": 606154, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9613302946090698, "global_step": 606155, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0385758876800537, "global_step": 606156, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.000965118408203, "global_step": 606157, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9774501323699951, "global_step": 606158, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9768056869506836, "global_step": 606159, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9988819360733032, "global_step": 606160, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.042036533355713, "global_step": 606161, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.00475811958313, "global_step": 606162, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.011810064315796, "global_step": 606163, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.044893503189087, "global_step": 606164, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0558388233184814, "global_step": 606165, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9924157857894897, "global_step": 606166, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.8976136445999146, "global_step": 606167, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1173393726348877, "global_step": 606168, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.077864170074463, "global_step": 606169, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9552030563354492, "global_step": 606170, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9036307334899902, "global_step": 606171, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.039466142654419, "global_step": 606172, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.048454761505127, "global_step": 606173, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9714195728302002, "global_step": 606174, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0413126945495605, "global_step": 606175, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0275261402130127, "global_step": 606176, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9243230819702148, "global_step": 606177, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0428757667541504, "global_step": 606178, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.084742784500122, "global_step": 606179, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.073133707046509, "global_step": 606180, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.06640625, "global_step": 606181, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.020642042160034, "global_step": 606182, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0272090435028076, "global_step": 606183, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.009432077407837, "global_step": 606184, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0663371086120605, "global_step": 606185, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.03788423538208, "global_step": 606186, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0724422931671143, "global_step": 606187, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0229527950286865, "global_step": 606188, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0966124534606934, "global_step": 606189, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9877113103866577, "global_step": 606190, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.070218563079834, "global_step": 606191, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.054593801498413, "global_step": 606192, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.002577781677246, "global_step": 606193, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9893687963485718, "global_step": 606194, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0432987213134766, "global_step": 606195, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.8411588668823242, "global_step": 606196, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.986112356185913, "global_step": 606197, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0139694213867188, "global_step": 606198, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.003998041152954, "global_step": 606199, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0571975708007812, "global_step": 606200, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.017402410507202, "global_step": 606201, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.998128056526184, "global_step": 606202, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9958901405334473, "global_step": 606203, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9553781747817993, "global_step": 606204, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0732221603393555, "global_step": 606205, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.972532033920288, "global_step": 606206, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9604872465133667, "global_step": 606207, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.106400728225708, "global_step": 606208, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.972396731376648, "global_step": 606209, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.95516037940979, "global_step": 606210, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0525240898132324, "global_step": 606211, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.017775774002075, "global_step": 606212, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.01471209526062, "global_step": 606213, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.902516484260559, "global_step": 606214, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0373494625091553, "global_step": 606215, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0501058101654053, "global_step": 606216, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.8706231117248535, "global_step": 606217, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0812830924987793, "global_step": 606218, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9915474653244019, "global_step": 606219, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.05631947517395, "global_step": 606220, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0737431049346924, "global_step": 606221, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9338655471801758, "global_step": 606222, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.963107943534851, "global_step": 606223, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.082750082015991, "global_step": 606224, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9860055446624756, "global_step": 606225, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.98478364944458, "global_step": 606226, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.973122000694275, "global_step": 606227, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0078237056732178, "global_step": 606228, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.02962064743042, "global_step": 606229, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.068817377090454, "global_step": 606230, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9357157945632935, "global_step": 606231, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9699808359146118, "global_step": 606232, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9466850757598877, "global_step": 606233, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9659409523010254, "global_step": 606234, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.978096842765808, "global_step": 606235, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9517183303833008, "global_step": 606236, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0352025032043457, "global_step": 606237, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.897077202796936, "global_step": 606238, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.079315423965454, "global_step": 606239, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.023710012435913, "global_step": 606240, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.952968716621399, "global_step": 606241, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.028911590576172, "global_step": 606242, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0326364040374756, "global_step": 606243, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.125190019607544, "global_step": 606244, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9702833890914917, "global_step": 606245, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1170084476470947, "global_step": 606246, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.980603814125061, "global_step": 606247, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9828591346740723, "global_step": 606248, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.8708184957504272, "global_step": 606249, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0083096027374268, "global_step": 606250, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0240414142608643, "global_step": 606251, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9870524406433105, "global_step": 606252, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0590806007385254, "global_step": 606253, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.04491925239563, "global_step": 606254, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9725769758224487, "global_step": 606255, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.029337167739868, "global_step": 606256, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.128657341003418, "global_step": 606257, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0027761459350586, "global_step": 606258, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.008784532546997, "global_step": 606259, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0529685020446777, "global_step": 606260, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9822580814361572, "global_step": 606261, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.932012915611267, "global_step": 606262, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0013763904571533, "global_step": 606263, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0219600200653076, "global_step": 606264, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.05255126953125, "global_step": 606265, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.974026083946228, "global_step": 606266, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.049053907394409, "global_step": 606267, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.046985387802124, "global_step": 606268, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.931368350982666, "global_step": 606269, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.002115488052368, "global_step": 606270, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0024373531341553, "global_step": 606271, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9830156564712524, "global_step": 606272, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.025674819946289, "global_step": 606273, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0087151527404785, "global_step": 606274, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.047922134399414, "global_step": 606275, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0756211280822754, "global_step": 606276, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.005384922027588, "global_step": 606277, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0154597759246826, "global_step": 606278, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0823781490325928, "global_step": 606279, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0240092277526855, "global_step": 606280, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.95880126953125, "global_step": 606281, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0462610721588135, "global_step": 606282, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9841868877410889, "global_step": 606283, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0309481620788574, "global_step": 606284, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0854365825653076, "global_step": 606285, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0812296867370605, "global_step": 606286, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0297744274139404, "global_step": 606287, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9981342554092407, "global_step": 606288, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9898850917816162, "global_step": 606289, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.020827293395996, "global_step": 606290, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9810004234313965, "global_step": 606291, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0493242740631104, "global_step": 606292, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0191025733947754, "global_step": 606293, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9316143989562988, "global_step": 606294, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0042831897735596, "global_step": 606295, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0159902572631836, "global_step": 606296, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0479278564453125, "global_step": 606297, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.020721197128296, "global_step": 606298, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0763392448425293, "global_step": 606299, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.017324924468994, "global_step": 606300, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.025852680206299, "global_step": 606301, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0521860122680664, "global_step": 606302, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9900130033493042, "global_step": 606303, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0108089447021484, "global_step": 606304, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0714876651763916, "global_step": 606305, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0356884002685547, "global_step": 606306, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9495266675949097, "global_step": 606307, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9874975681304932, "global_step": 606308, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0805957317352295, "global_step": 606309, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0011162757873535, "global_step": 606310, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.017749547958374, "global_step": 606311, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.062324047088623, "global_step": 606312, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.086716651916504, "global_step": 606313, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.084839105606079, "global_step": 606314, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0797390937805176, "global_step": 606315, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9759280681610107, "global_step": 606316, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9383207559585571, "global_step": 606317, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.014012575149536, "global_step": 606318, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1007080078125, "global_step": 606319, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0909643173217773, "global_step": 606320, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1155378818511963, "global_step": 606321, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.011559009552002, "global_step": 606322, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9494647979736328, "global_step": 606323, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.077204465866089, "global_step": 606324, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.045950412750244, "global_step": 606325, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9241409301757812, "global_step": 606326, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.066304922103882, "global_step": 606327, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0799505710601807, "global_step": 606328, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0586540699005127, "global_step": 606329, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9327434301376343, "global_step": 606330, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0829315185546875, "global_step": 606331, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0457661151885986, "global_step": 606332, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9831950664520264, "global_step": 606333, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9802175760269165, "global_step": 606334, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.005197525024414, "global_step": 606335, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.063382148742676, "global_step": 606336, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0042295455932617, "global_step": 606337, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0602238178253174, "global_step": 606338, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9823012351989746, "global_step": 606339, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.019155263900757, "global_step": 606340, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9648559093475342, "global_step": 606341, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9866887331008911, "global_step": 606342, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9169875383377075, "global_step": 606343, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.993260383605957, "global_step": 606344, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.009469509124756, "global_step": 606345, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9499478340148926, "global_step": 606346, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.033123254776001, "global_step": 606347, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.03102970123291, "global_step": 606348, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.047245740890503, "global_step": 606349, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0476338863372803, "global_step": 606350, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0227468013763428, "global_step": 606351, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.069471597671509, "global_step": 606352, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0392422676086426, "global_step": 606353, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0000648498535156, "global_step": 606354, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.043882369995117, "global_step": 606355, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9863286018371582, "global_step": 606356, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9857537746429443, "global_step": 606357, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9055508375167847, "global_step": 606358, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9098976850509644, "global_step": 606359, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0201332569122314, "global_step": 606360, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9387500286102295, "global_step": 606361, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0195255279541016, "global_step": 606362, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.031369924545288, "global_step": 606363, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1185178756713867, "global_step": 606364, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9683811664581299, "global_step": 606365, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.932424545288086, "global_step": 606366, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.965829610824585, "global_step": 606367, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9540963172912598, "global_step": 606368, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.060523748397827, "global_step": 606369, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9812090396881104, "global_step": 606370, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0180423259735107, "global_step": 606371, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0142524242401123, "global_step": 606372, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0834710597991943, "global_step": 606373, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.10744571685791, "global_step": 606374, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.15336537361145, "global_step": 606375, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0343196392059326, "global_step": 606376, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.034433126449585, "global_step": 606377, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0283243656158447, "global_step": 606378, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.044269561767578, "global_step": 606379, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0796995162963867, "global_step": 606380, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0043137073516846, "global_step": 606381, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.027557611465454, "global_step": 606382, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.019822597503662, "global_step": 606383, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9546340703964233, "global_step": 606384, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9398013353347778, "global_step": 606385, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9844670295715332, "global_step": 606386, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0015206336975098, "global_step": 606387, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9816838502883911, "global_step": 606388, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.058427572250366, "global_step": 606389, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.008399248123169, "global_step": 606390, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0228569507598877, "global_step": 606391, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0112714767456055, "global_step": 606392, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9711984395980835, "global_step": 606393, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9966405630111694, "global_step": 606394, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9715080261230469, "global_step": 606395, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.012324333190918, "global_step": 606396, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9659298658370972, "global_step": 606397, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0198333263397217, "global_step": 606398, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0588159561157227, "global_step": 606399, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9483954906463623, "global_step": 606400, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0565133094787598, "global_step": 606401, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.031684160232544, "global_step": 606402, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.049295663833618, "global_step": 606403, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.026808500289917, "global_step": 606404, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0360183715820312, "global_step": 606405, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0414183139801025, "global_step": 606406, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.994704246520996, "global_step": 606407, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9645121097564697, "global_step": 606408, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.017362356185913, "global_step": 606409, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.926162838935852, "global_step": 606410, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.040397882461548, "global_step": 606411, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9767444133758545, "global_step": 606412, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0072126388549805, "global_step": 606413, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.008014678955078, "global_step": 606414, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.8417456150054932, "global_step": 606415, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0170071125030518, "global_step": 606416, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9205857515335083, "global_step": 606417, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.927271842956543, "global_step": 606418, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0448288917541504, "global_step": 606419, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9856315851211548, "global_step": 606420, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.033676862716675, "global_step": 606421, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0580332279205322, "global_step": 606422, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9807143211364746, "global_step": 606423, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.02402400970459, "global_step": 606424, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0833072662353516, "global_step": 606425, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0196895599365234, "global_step": 606426, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.050934314727783, "global_step": 606427, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.061807155609131, "global_step": 606428, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0068628787994385, "global_step": 606429, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9489163160324097, "global_step": 606430, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0448381900787354, "global_step": 606431, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0301287174224854, "global_step": 606432, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0168464183807373, "global_step": 606433, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9280849695205688, "global_step": 606434, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9840129613876343, "global_step": 606435, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9496138095855713, "global_step": 606436, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.096925735473633, "global_step": 606437, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9850298166275024, "global_step": 606438, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9554734230041504, "global_step": 606439, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.889722466468811, "global_step": 606440, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9592626094818115, "global_step": 606441, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9880824089050293, "global_step": 606442, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.977715015411377, "global_step": 606443, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.008035182952881, "global_step": 606444, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0477542877197266, "global_step": 606445, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.983359456062317, "global_step": 606446, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1085574626922607, "global_step": 606447, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.069533109664917, "global_step": 606448, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.061020851135254, "global_step": 606449, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.8919317722320557, "global_step": 606450, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.001366138458252, "global_step": 606451, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9936333894729614, "global_step": 606452, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0124351978302, "global_step": 606453, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.8726779222488403, "global_step": 606454, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0414798259735107, "global_step": 606455, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0169625282287598, "global_step": 606456, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9666944742202759, "global_step": 606457, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9928815364837646, "global_step": 606458, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9983805418014526, "global_step": 606459, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0290677547454834, "global_step": 606460, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9764467477798462, "global_step": 606461, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9660179615020752, "global_step": 606462, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0483357906341553, "global_step": 606463, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0665857791900635, "global_step": 606464, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0683205127716064, "global_step": 606465, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9369982481002808, "global_step": 606466, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9358171224594116, "global_step": 606467, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0118911266326904, "global_step": 606468, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1021957397460938, "global_step": 606469, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0770537853240967, "global_step": 606470, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9993400573730469, "global_step": 606471, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.033446788787842, "global_step": 606472, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9397180080413818, "global_step": 606473, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0127146244049072, "global_step": 606474, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9902983903884888, "global_step": 606475, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.019102096557617, "global_step": 606476, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9297459125518799, "global_step": 606477, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.022962808609009, "global_step": 606478, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.030217170715332, "global_step": 606479, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0509870052337646, "global_step": 606480, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.983831763267517, "global_step": 606481, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9954463243484497, "global_step": 606482, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1135687828063965, "global_step": 606483, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1165614128112793, "global_step": 606484, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.026601552963257, "global_step": 606485, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.030374765396118, "global_step": 606486, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9148964881896973, "global_step": 606487, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.951213002204895, "global_step": 606488, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.968779444694519, "global_step": 606489, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.001648426055908, "global_step": 606490, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.001051425933838, "global_step": 606491, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.083784341812134, "global_step": 606492, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0583808422088623, "global_step": 606493, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9995518922805786, "global_step": 606494, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.022684335708618, "global_step": 606495, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.074582576751709, "global_step": 606496, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9814127683639526, "global_step": 606497, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.112215042114258, "global_step": 606498, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0156192779541016, "global_step": 606499, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0134074687957764, "global_step": 606500, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0510661602020264, "global_step": 606501, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0863189697265625, "global_step": 606502, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0378518104553223, "global_step": 606503, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9853228330612183, "global_step": 606504, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.044235944747925, "global_step": 606505, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9055488109588623, "global_step": 606506, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.168792724609375, "global_step": 606507, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0204129219055176, "global_step": 606508, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.036846399307251, "global_step": 606509, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.033360004425049, "global_step": 606510, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.989579677581787, "global_step": 606511, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0358150005340576, "global_step": 606512, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0393409729003906, "global_step": 606513, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.089185953140259, "global_step": 606514, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0102522373199463, "global_step": 606515, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0298640727996826, "global_step": 606516, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9927120208740234, "global_step": 606517, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.917696475982666, "global_step": 606518, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.038470983505249, "global_step": 606519, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9677377939224243, "global_step": 606520, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1524300575256348, "global_step": 606521, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.022756576538086, "global_step": 606522, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.046522617340088, "global_step": 606523, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.086883544921875, "global_step": 606524, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.008791923522949, "global_step": 606525, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9793555736541748, "global_step": 606526, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0477945804595947, "global_step": 606527, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0450141429901123, "global_step": 606528, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.020810604095459, "global_step": 606529, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9823371171951294, "global_step": 606530, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9696823358535767, "global_step": 606531, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.021554946899414, "global_step": 606532, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0133819580078125, "global_step": 606533, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.004817485809326, "global_step": 606534, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0166079998016357, "global_step": 606535, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.056425094604492, "global_step": 606536, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.965744137763977, "global_step": 606537, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9808841943740845, "global_step": 606538, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.967085361480713, "global_step": 606539, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9791878461837769, "global_step": 606540, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.041701555252075, "global_step": 606541, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.011909008026123, "global_step": 606542, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0250906944274902, "global_step": 606543, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9937045574188232, "global_step": 606544, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0070884227752686, "global_step": 606545, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9645776748657227, "global_step": 606546, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0333001613616943, "global_step": 606547, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9632586240768433, "global_step": 606548, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9073452949523926, "global_step": 606549, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.10133695602417, "global_step": 606550, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0165488719940186, "global_step": 606551, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0332963466644287, "global_step": 606552, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9522943496704102, "global_step": 606553, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0022850036621094, "global_step": 606554, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0195748805999756, "global_step": 606555, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9172488451004028, "global_step": 606556, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.040226459503174, "global_step": 606557, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.973297119140625, "global_step": 606558, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.021723747253418, "global_step": 606559, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0365374088287354, "global_step": 606560, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0447850227355957, "global_step": 606561, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0488529205322266, "global_step": 606562, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.993774652481079, "global_step": 606563, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0275731086730957, "global_step": 606564, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1049842834472656, "global_step": 606565, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9560760259628296, "global_step": 606566, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.044015884399414, "global_step": 606567, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0878143310546875, "global_step": 606568, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9169081449508667, "global_step": 606569, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0524821281433105, "global_step": 606570, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9935818910598755, "global_step": 606571, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9672907590866089, "global_step": 606572, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.049966335296631, "global_step": 606573, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9910175800323486, "global_step": 606574, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.094170570373535, "global_step": 606575, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0434587001800537, "global_step": 606576, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.062059164047241, "global_step": 606577, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0071146488189697, "global_step": 606578, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0415966510772705, "global_step": 606579, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.8886078596115112, "global_step": 606580, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0649280548095703, "global_step": 606581, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0237889289855957, "global_step": 606582, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9801679849624634, "global_step": 606583, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9507720470428467, "global_step": 606584, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9955487251281738, "global_step": 606585, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9490865468978882, "global_step": 606586, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9369868040084839, "global_step": 606587, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9498871564865112, "global_step": 606588, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.023437261581421, "global_step": 606589, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.006011724472046, "global_step": 606590, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0426623821258545, "global_step": 606591, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9764448404312134, "global_step": 606592, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.97780442237854, "global_step": 606593, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9527192115783691, "global_step": 606594, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.101835250854492, "global_step": 606595, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9989838600158691, "global_step": 606596, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.054591178894043, "global_step": 606597, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9700891971588135, "global_step": 606598, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0254735946655273, "global_step": 606599, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.019364595413208, "global_step": 606600, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0029375553131104, "global_step": 606601, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.984789490699768, "global_step": 606602, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9965877532958984, "global_step": 606603, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.009540557861328, "global_step": 606604, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.168419599533081, "global_step": 606605, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.989578127861023, "global_step": 606606, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.036078691482544, "global_step": 606607, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.939318060874939, "global_step": 606608, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.007416248321533, "global_step": 606609, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.001577377319336, "global_step": 606610, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9604650735855103, "global_step": 606611, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.019949436187744, "global_step": 606612, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.005941152572632, "global_step": 606613, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.01501727104187, "global_step": 606614, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0457818508148193, "global_step": 606615, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.987083911895752, "global_step": 606616, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.039177656173706, "global_step": 606617, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.013364553451538, "global_step": 606618, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.014531373977661, "global_step": 606619, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0347962379455566, "global_step": 606620, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.011248826980591, "global_step": 606621, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9431120157241821, "global_step": 606622, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9646766185760498, "global_step": 606623, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.987510085105896, "global_step": 606624, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9327367544174194, "global_step": 606625, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0591490268707275, "global_step": 606626, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.174311637878418, "global_step": 606627, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.030121326446533, "global_step": 606628, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1120612621307373, "global_step": 606629, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.014651298522949, "global_step": 606630, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.998619794845581, "global_step": 606631, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0422048568725586, "global_step": 606632, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.008206844329834, "global_step": 606633, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9781570434570312, "global_step": 606634, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0515260696411133, "global_step": 606635, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9969063997268677, "global_step": 606636, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0067498683929443, "global_step": 606637, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0006046295166016, "global_step": 606638, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0769715309143066, "global_step": 606639, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.02652907371521, "global_step": 606640, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9910598993301392, "global_step": 606641, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.124192714691162, "global_step": 606642, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.000643730163574, "global_step": 606643, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0782480239868164, "global_step": 606644, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1017067432403564, "global_step": 606645, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.036024808883667, "global_step": 606646, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9588472843170166, "global_step": 606647, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9918663501739502, "global_step": 606648, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.059457540512085, "global_step": 606649, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0230908393859863, "global_step": 606650, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9851740598678589, "global_step": 606651, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9879652261734009, "global_step": 606652, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9999115467071533, "global_step": 606653, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0648300647735596, "global_step": 606654, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9360289573669434, "global_step": 606655, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1298580169677734, "global_step": 606656, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0010414123535156, "global_step": 606657, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.073566436767578, "global_step": 606658, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.097425699234009, "global_step": 606659, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.075334072113037, "global_step": 606660, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0437042713165283, "global_step": 606661, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.941439151763916, "global_step": 606662, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0351712703704834, "global_step": 606663, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9249857664108276, "global_step": 606664, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.1184706687927246, "global_step": 606665, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9882869720458984, "global_step": 606666, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0114681720733643, "global_step": 606667, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.050166130065918, "global_step": 606668, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0189905166625977, "global_step": 606669, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0493268966674805, "global_step": 606670, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9711642265319824, "global_step": 606671, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0892956256866455, "global_step": 606672, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.016982078552246, "global_step": 606673, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.006277084350586, "global_step": 606674, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.018359899520874, "global_step": 606675, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.005459785461426, "global_step": 606676, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.931352972984314, "global_step": 606677, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0399582386016846, "global_step": 606678, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.01249361038208, "global_step": 606679, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0961155891418457, "global_step": 606680, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0915679931640625, "global_step": 606681, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.8712849617004395, "global_step": 606682, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9950159788131714, "global_step": 606683, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0232436656951904, "global_step": 606684, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.029811143875122, "global_step": 606685, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.037705659866333, "global_step": 606686, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0875132083892822, "global_step": 606687, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.064781427383423, "global_step": 606688, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9559581279754639, "global_step": 606689, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.039475679397583, "global_step": 606690, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0947318077087402, "global_step": 606691, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.007883071899414, "global_step": 606692, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.065477132797241, "global_step": 606693, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0453920364379883, "global_step": 606694, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0282015800476074, "global_step": 606695, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.034101963043213, "global_step": 606696, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9872479438781738, "global_step": 606697, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.034182071685791, "global_step": 606698, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.991355299949646, "global_step": 606699, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0046677589416504, "global_step": 606700, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9543633460998535, "global_step": 606701, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.859456181526184, "global_step": 606702, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9924508333206177, "global_step": 606703, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0734188556671143, "global_step": 606704, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9823957681655884, "global_step": 606705, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.045870780944824, "global_step": 606706, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9611998796463013, "global_step": 606707, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9786052703857422, "global_step": 606708, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.999877691268921, "global_step": 606709, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0267341136932373, "global_step": 606710, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0526413917541504, "global_step": 606711, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.083897352218628, "global_step": 606712, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9636125564575195, "global_step": 606713, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.00419545173645, "global_step": 606714, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.02893328666687, "global_step": 606715, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0106401443481445, "global_step": 606716, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.975238561630249, "global_step": 606717, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.031341314315796, "global_step": 606718, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0459365844726562, "global_step": 606719, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.172224283218384, "global_step": 606720, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0357918739318848, "global_step": 606721, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0311920642852783, "global_step": 606722, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0560097694396973, "global_step": 606723, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.002978801727295, "global_step": 606724, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.00001859664917, "global_step": 606725, "epoch": 975, "lr": 5e-05}
{"train_loss": 2.0098330974578857, "global_step": 606726, "epoch": 975, "lr": 5e-05}
{"train_loss": 1.9446706771850586, "global_step": 606727, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.001525640487671, "global_step": 606728, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0529072284698486, "global_step": 606729, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.994957685470581, "global_step": 606730, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9705218076705933, "global_step": 606731, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9313868284225464, "global_step": 606732, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0354137420654297, "global_step": 606733, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9339674711227417, "global_step": 606734, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0963892936706543, "global_step": 606735, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0302655696868896, "global_step": 606736, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.1259047985076904, "global_step": 606737, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.058936357498169, "global_step": 606738, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.912430763244629, "global_step": 606739, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0618560314178467, "global_step": 606740, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9880942106246948, "global_step": 606741, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.100752115249634, "global_step": 606742, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0127151012420654, "global_step": 606743, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0310702323913574, "global_step": 606744, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9667274951934814, "global_step": 606745, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9492268562316895, "global_step": 606746, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.981469988822937, "global_step": 606747, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.958171010017395, "global_step": 606748, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9941562414169312, "global_step": 606749, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9037435054779053, "global_step": 606750, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.994651436805725, "global_step": 606751, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.006350040435791, "global_step": 606752, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9778209924697876, "global_step": 606753, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9687957763671875, "global_step": 606754, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9614747762680054, "global_step": 606755, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0096824169158936, "global_step": 606756, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.007505178451538, "global_step": 606757, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.050525426864624, "global_step": 606758, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.061342716217041, "global_step": 606759, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9817148447036743, "global_step": 606760, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9920933246612549, "global_step": 606761, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0123863220214844, "global_step": 606762, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9623057842254639, "global_step": 606763, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0086612701416016, "global_step": 606764, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.937839388847351, "global_step": 606765, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9706190824508667, "global_step": 606766, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0044500827789307, "global_step": 606767, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.006895065307617, "global_step": 606768, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.1074624061584473, "global_step": 606769, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0341315269470215, "global_step": 606770, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.03558087348938, "global_step": 606771, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9771287441253662, "global_step": 606772, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0332648754119873, "global_step": 606773, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0404982566833496, "global_step": 606774, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9806281328201294, "global_step": 606775, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9926470518112183, "global_step": 606776, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.969910740852356, "global_step": 606777, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9296302795410156, "global_step": 606778, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.987747311592102, "global_step": 606779, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9789602756500244, "global_step": 606780, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.013154983520508, "global_step": 606781, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.067974090576172, "global_step": 606782, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0038394927978516, "global_step": 606783, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.1271610260009766, "global_step": 606784, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9873687028884888, "global_step": 606785, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.946696162223816, "global_step": 606786, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0008368492126465, "global_step": 606787, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.942619800567627, "global_step": 606788, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.015303134918213, "global_step": 606789, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0062220096588135, "global_step": 606790, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.8900617361068726, "global_step": 606791, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9930366277694702, "global_step": 606792, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9819332361221313, "global_step": 606793, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9768065214157104, "global_step": 606794, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9979933500289917, "global_step": 606795, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0369346141815186, "global_step": 606796, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.033524513244629, "global_step": 606797, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9656386375427246, "global_step": 606798, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9849494695663452, "global_step": 606799, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0463240146636963, "global_step": 606800, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9423396587371826, "global_step": 606801, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.01821231842041, "global_step": 606802, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9639934301376343, "global_step": 606803, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.037724256515503, "global_step": 606804, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.8992420434951782, "global_step": 606805, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.999280571937561, "global_step": 606806, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9563437700271606, "global_step": 606807, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9484773874282837, "global_step": 606808, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0158331394195557, "global_step": 606809, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.005056858062744, "global_step": 606810, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.98402738571167, "global_step": 606811, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9532973766326904, "global_step": 606812, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0794248580932617, "global_step": 606813, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.03544282913208, "global_step": 606814, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0089588165283203, "global_step": 606815, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0016233921051025, "global_step": 606816, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.980470061302185, "global_step": 606817, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.981909990310669, "global_step": 606818, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9994735717773438, "global_step": 606819, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9693467617034912, "global_step": 606820, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.122326612472534, "global_step": 606821, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9687561988830566, "global_step": 606822, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.039743185043335, "global_step": 606823, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9861747026443481, "global_step": 606824, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.041623592376709, "global_step": 606825, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9906975030899048, "global_step": 606826, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.990200161933899, "global_step": 606827, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9226270914077759, "global_step": 606828, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.086052179336548, "global_step": 606829, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.934952974319458, "global_step": 606830, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.05643892288208, "global_step": 606831, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.986817479133606, "global_step": 606832, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0358734130859375, "global_step": 606833, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.8886855840682983, "global_step": 606834, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.978757381439209, "global_step": 606835, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.065704822540283, "global_step": 606836, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9528698921203613, "global_step": 606837, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.983476161956787, "global_step": 606838, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.00935697555542, "global_step": 606839, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.956694483757019, "global_step": 606840, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9918547868728638, "global_step": 606841, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0134241580963135, "global_step": 606842, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.040994167327881, "global_step": 606843, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0284171104431152, "global_step": 606844, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9800294637680054, "global_step": 606845, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9791041612625122, "global_step": 606846, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0523457527160645, "global_step": 606847, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0422682762145996, "global_step": 606848, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0241286754608154, "global_step": 606849, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.164379835128784, "global_step": 606850, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0121853351593018, "global_step": 606851, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9303234815597534, "global_step": 606852, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9853196144104004, "global_step": 606853, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.8993724584579468, "global_step": 606854, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9824557304382324, "global_step": 606855, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0002310276031494, "global_step": 606856, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9411849975585938, "global_step": 606857, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.02901291847229, "global_step": 606858, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.009575605392456, "global_step": 606859, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9748811721801758, "global_step": 606860, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.011042594909668, "global_step": 606861, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.038039207458496, "global_step": 606862, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0870461463928223, "global_step": 606863, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9712177515029907, "global_step": 606864, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.990725040435791, "global_step": 606865, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9530158042907715, "global_step": 606866, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.001950263977051, "global_step": 606867, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9717730283737183, "global_step": 606868, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0893661975860596, "global_step": 606869, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0161945819854736, "global_step": 606870, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9588706493377686, "global_step": 606871, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.028684616088867, "global_step": 606872, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9851373434066772, "global_step": 606873, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9953041076660156, "global_step": 606874, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.059330701828003, "global_step": 606875, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9795116186141968, "global_step": 606876, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9828685522079468, "global_step": 606877, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9585881233215332, "global_step": 606878, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.037261962890625, "global_step": 606879, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.935513973236084, "global_step": 606880, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9780263900756836, "global_step": 606881, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9614498615264893, "global_step": 606882, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.1035168170928955, "global_step": 606883, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0266242027282715, "global_step": 606884, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9436649084091187, "global_step": 606885, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9933042526245117, "global_step": 606886, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.043849468231201, "global_step": 606887, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.070012092590332, "global_step": 606888, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9494258165359497, "global_step": 606889, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.059635639190674, "global_step": 606890, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0182008743286133, "global_step": 606891, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9632488489151, "global_step": 606892, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0374879837036133, "global_step": 606893, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0081310272216797, "global_step": 606894, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0018513202667236, "global_step": 606895, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.035665988922119, "global_step": 606896, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0316309928894043, "global_step": 606897, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.021700859069824, "global_step": 606898, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9655390977859497, "global_step": 606899, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9747227430343628, "global_step": 606900, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0569021701812744, "global_step": 606901, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.031940460205078, "global_step": 606902, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0137743949890137, "global_step": 606903, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9879465103149414, "global_step": 606904, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9581173658370972, "global_step": 606905, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0406334400177, "global_step": 606906, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9825292825698853, "global_step": 606907, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.069889783859253, "global_step": 606908, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9686977863311768, "global_step": 606909, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0035674571990967, "global_step": 606910, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9590717554092407, "global_step": 606911, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0183799266815186, "global_step": 606912, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9928600788116455, "global_step": 606913, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0123519897460938, "global_step": 606914, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.067375659942627, "global_step": 606915, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0923409461975098, "global_step": 606916, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0557305812835693, "global_step": 606917, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0111186504364014, "global_step": 606918, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.970832109451294, "global_step": 606919, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.964083194732666, "global_step": 606920, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.1193718910217285, "global_step": 606921, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0558202266693115, "global_step": 606922, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0000088214874268, "global_step": 606923, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0344996452331543, "global_step": 606924, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9548834562301636, "global_step": 606925, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9924769401550293, "global_step": 606926, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0062432289123535, "global_step": 606927, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9512180089950562, "global_step": 606928, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.04675555229187, "global_step": 606929, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0166399478912354, "global_step": 606930, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.013803720474243, "global_step": 606931, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9717772006988525, "global_step": 606932, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0098752975463867, "global_step": 606933, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.007855176925659, "global_step": 606934, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.006540298461914, "global_step": 606935, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0196731090545654, "global_step": 606936, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9870359897613525, "global_step": 606937, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.8774441480636597, "global_step": 606938, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0002987384796143, "global_step": 606939, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.003951072692871, "global_step": 606940, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9108933210372925, "global_step": 606941, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0517358779907227, "global_step": 606942, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0177500247955322, "global_step": 606943, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.995397925376892, "global_step": 606944, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9552730321884155, "global_step": 606945, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.008971691131592, "global_step": 606946, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0339651107788086, "global_step": 606947, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0861127376556396, "global_step": 606948, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.076781988143921, "global_step": 606949, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.027695417404175, "global_step": 606950, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.031785011291504, "global_step": 606951, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.019986391067505, "global_step": 606952, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9727343320846558, "global_step": 606953, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0117483139038086, "global_step": 606954, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.95845627784729, "global_step": 606955, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9329419136047363, "global_step": 606956, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0263655185699463, "global_step": 606957, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0712413787841797, "global_step": 606958, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0821149349212646, "global_step": 606959, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9493680000305176, "global_step": 606960, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9752389192581177, "global_step": 606961, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9402644634246826, "global_step": 606962, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0082948207855225, "global_step": 606963, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0907480716705322, "global_step": 606964, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.00795841217041, "global_step": 606965, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9240171909332275, "global_step": 606966, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.093989849090576, "global_step": 606967, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9777487516403198, "global_step": 606968, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9670647382736206, "global_step": 606969, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.971846103668213, "global_step": 606970, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0127193927764893, "global_step": 606971, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.022038698196411, "global_step": 606972, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9652777910232544, "global_step": 606973, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0597918033599854, "global_step": 606974, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9859766960144043, "global_step": 606975, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9953030347824097, "global_step": 606976, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.016507625579834, "global_step": 606977, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.066580295562744, "global_step": 606978, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.179853916168213, "global_step": 606979, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0056700706481934, "global_step": 606980, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9538592100143433, "global_step": 606981, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9754369258880615, "global_step": 606982, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.099372625350952, "global_step": 606983, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.067659378051758, "global_step": 606984, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.947948694229126, "global_step": 606985, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9857022762298584, "global_step": 606986, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0564801692962646, "global_step": 606987, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9065521955490112, "global_step": 606988, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0595810413360596, "global_step": 606989, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0288851261138916, "global_step": 606990, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9926307201385498, "global_step": 606991, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.01348876953125, "global_step": 606992, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9938901662826538, "global_step": 606993, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9376579523086548, "global_step": 606994, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.026458978652954, "global_step": 606995, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9564052820205688, "global_step": 606996, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.119476318359375, "global_step": 606997, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.001728057861328, "global_step": 606998, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9609366655349731, "global_step": 606999, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9808369874954224, "global_step": 607000, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0123839378356934, "global_step": 607001, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9535578489303589, "global_step": 607002, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0309386253356934, "global_step": 607003, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.1362338066101074, "global_step": 607004, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0371291637420654, "global_step": 607005, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.8423748016357422, "global_step": 607006, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.971311092376709, "global_step": 607007, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.001962423324585, "global_step": 607008, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0089311599731445, "global_step": 607009, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0850377082824707, "global_step": 607010, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.022996425628662, "global_step": 607011, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9771554470062256, "global_step": 607012, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0186927318573, "global_step": 607013, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.106761932373047, "global_step": 607014, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9362449645996094, "global_step": 607015, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9809446334838867, "global_step": 607016, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.991723656654358, "global_step": 607017, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.012958526611328, "global_step": 607018, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9428986310958862, "global_step": 607019, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.04822039604187, "global_step": 607020, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.000133991241455, "global_step": 607021, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0146844387054443, "global_step": 607022, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.017373561859131, "global_step": 607023, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.02174711227417, "global_step": 607024, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9696279764175415, "global_step": 607025, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.045750141143799, "global_step": 607026, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9999178647994995, "global_step": 607027, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0252344608306885, "global_step": 607028, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.034353256225586, "global_step": 607029, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0199265480041504, "global_step": 607030, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0018503665924072, "global_step": 607031, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0091700553894043, "global_step": 607032, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0157601833343506, "global_step": 607033, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0328595638275146, "global_step": 607034, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0449578762054443, "global_step": 607035, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.041195869445801, "global_step": 607036, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.021963596343994, "global_step": 607037, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9324750900268555, "global_step": 607038, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.016261577606201, "global_step": 607039, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9679303169250488, "global_step": 607040, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9801437854766846, "global_step": 607041, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9155898094177246, "global_step": 607042, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0169596672058105, "global_step": 607043, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.985851764678955, "global_step": 607044, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9099313020706177, "global_step": 607045, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0572962760925293, "global_step": 607046, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9714008569717407, "global_step": 607047, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.087764024734497, "global_step": 607048, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.045015335083008, "global_step": 607049, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0559046268463135, "global_step": 607050, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.059955596923828, "global_step": 607051, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.990592122077942, "global_step": 607052, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0368919372558594, "global_step": 607053, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0101099014282227, "global_step": 607054, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.943230152130127, "global_step": 607055, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9661810398101807, "global_step": 607056, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.948305368423462, "global_step": 607057, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9721369743347168, "global_step": 607058, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9800434112548828, "global_step": 607059, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.034641742706299, "global_step": 607060, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0680019855499268, "global_step": 607061, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.952445149421692, "global_step": 607062, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0264556407928467, "global_step": 607063, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9304041862487793, "global_step": 607064, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0448966026306152, "global_step": 607065, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9743952751159668, "global_step": 607066, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0633130073547363, "global_step": 607067, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.96017324924469, "global_step": 607068, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.024395227432251, "global_step": 607069, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9938247203826904, "global_step": 607070, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9605599641799927, "global_step": 607071, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.065145254135132, "global_step": 607072, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0700931549072266, "global_step": 607073, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9825273752212524, "global_step": 607074, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.964237928390503, "global_step": 607075, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0445194244384766, "global_step": 607076, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.019437789916992, "global_step": 607077, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9832336902618408, "global_step": 607078, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9819897413253784, "global_step": 607079, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.038020610809326, "global_step": 607080, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9760931730270386, "global_step": 607081, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.017836332321167, "global_step": 607082, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9987664222717285, "global_step": 607083, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9546297788619995, "global_step": 607084, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9798030853271484, "global_step": 607085, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9054102897644043, "global_step": 607086, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.973345160484314, "global_step": 607087, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.064922571182251, "global_step": 607088, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9471389055252075, "global_step": 607089, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.935924768447876, "global_step": 607090, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0208632946014404, "global_step": 607091, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.95263671875, "global_step": 607092, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9159284830093384, "global_step": 607093, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.963575839996338, "global_step": 607094, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.032500982284546, "global_step": 607095, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.03489351272583, "global_step": 607096, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0184900760650635, "global_step": 607097, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.013852834701538, "global_step": 607098, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9540200233459473, "global_step": 607099, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.014011859893799, "global_step": 607100, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.010617733001709, "global_step": 607101, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0916056632995605, "global_step": 607102, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.935006022453308, "global_step": 607103, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.004497766494751, "global_step": 607104, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.012286901473999, "global_step": 607105, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0041141510009766, "global_step": 607106, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.077174186706543, "global_step": 607107, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9683376550674438, "global_step": 607108, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.993897795677185, "global_step": 607109, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9936643838882446, "global_step": 607110, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.941696047782898, "global_step": 607111, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.06201434135437, "global_step": 607112, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0133869647979736, "global_step": 607113, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9945236444473267, "global_step": 607114, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.020796537399292, "global_step": 607115, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.022705078125, "global_step": 607116, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9769351482391357, "global_step": 607117, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0712509155273438, "global_step": 607118, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.923790693283081, "global_step": 607119, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9913997650146484, "global_step": 607120, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0382163524627686, "global_step": 607121, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.049245834350586, "global_step": 607122, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9555401802062988, "global_step": 607123, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9609671831130981, "global_step": 607124, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9484742879867554, "global_step": 607125, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.02767014503479, "global_step": 607126, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.00376033782959, "global_step": 607127, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9172072410583496, "global_step": 607128, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0099117755889893, "global_step": 607129, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0052576065063477, "global_step": 607130, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0296878814697266, "global_step": 607131, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9904038906097412, "global_step": 607132, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0141420364379883, "global_step": 607133, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9956942796707153, "global_step": 607134, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9766329526901245, "global_step": 607135, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.01031756401062, "global_step": 607136, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9778203964233398, "global_step": 607137, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.998232126235962, "global_step": 607138, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9596129655838013, "global_step": 607139, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9257200956344604, "global_step": 607140, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0157132148742676, "global_step": 607141, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.989927887916565, "global_step": 607142, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.975460410118103, "global_step": 607143, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9652730226516724, "global_step": 607144, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0453855991363525, "global_step": 607145, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0783190727233887, "global_step": 607146, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.028446912765503, "global_step": 607147, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0397322177886963, "global_step": 607148, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.082937717437744, "global_step": 607149, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0115528106689453, "global_step": 607150, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.018160343170166, "global_step": 607151, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0459768772125244, "global_step": 607152, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0045177936553955, "global_step": 607153, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.015885591506958, "global_step": 607154, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.039670467376709, "global_step": 607155, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0418150424957275, "global_step": 607156, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9229590892791748, "global_step": 607157, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9663392305374146, "global_step": 607158, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0127387046813965, "global_step": 607159, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0053939819335938, "global_step": 607160, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0422306060791016, "global_step": 607161, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.06291127204895, "global_step": 607162, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.055321455001831, "global_step": 607163, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9926135540008545, "global_step": 607164, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.043276309967041, "global_step": 607165, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9625425338745117, "global_step": 607166, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9262844324111938, "global_step": 607167, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.904716968536377, "global_step": 607168, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0529768466949463, "global_step": 607169, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9934778213500977, "global_step": 607170, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.068355083465576, "global_step": 607171, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9784042835235596, "global_step": 607172, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9213932752609253, "global_step": 607173, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0081515312194824, "global_step": 607174, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.028790235519409, "global_step": 607175, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9873499870300293, "global_step": 607176, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.956079125404358, "global_step": 607177, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.056332588195801, "global_step": 607178, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9529670476913452, "global_step": 607179, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.007575511932373, "global_step": 607180, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0348143577575684, "global_step": 607181, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0401268005371094, "global_step": 607182, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9632923603057861, "global_step": 607183, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0909883975982666, "global_step": 607184, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.008756399154663, "global_step": 607185, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9516057968139648, "global_step": 607186, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9184784889221191, "global_step": 607187, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.000821113586426, "global_step": 607188, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.1006929874420166, "global_step": 607189, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0996556282043457, "global_step": 607190, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9907184839248657, "global_step": 607191, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9637552499771118, "global_step": 607192, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9241570234298706, "global_step": 607193, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.985917568206787, "global_step": 607194, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0040135383605957, "global_step": 607195, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9432284832000732, "global_step": 607196, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0812933444976807, "global_step": 607197, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9947926998138428, "global_step": 607198, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0557196140289307, "global_step": 607199, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.990727424621582, "global_step": 607200, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0438499450683594, "global_step": 607201, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9868559837341309, "global_step": 607202, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.951639175415039, "global_step": 607203, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9840517044067383, "global_step": 607204, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.062340259552002, "global_step": 607205, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0184648036956787, "global_step": 607206, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0361196994781494, "global_step": 607207, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.906944990158081, "global_step": 607208, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9716321229934692, "global_step": 607209, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9410912990570068, "global_step": 607210, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9648957252502441, "global_step": 607211, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9750466346740723, "global_step": 607212, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0671398639678955, "global_step": 607213, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9572244882583618, "global_step": 607214, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0820982456207275, "global_step": 607215, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0371530055999756, "global_step": 607216, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0513827800750732, "global_step": 607217, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0454134941101074, "global_step": 607218, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9867537021636963, "global_step": 607219, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.001403570175171, "global_step": 607220, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.006211996078491, "global_step": 607221, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0236270427703857, "global_step": 607222, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9769201278686523, "global_step": 607223, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.1148884296417236, "global_step": 607224, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0542714595794678, "global_step": 607225, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.013651132583618, "global_step": 607226, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0076842308044434, "global_step": 607227, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0103871822357178, "global_step": 607228, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9432272911071777, "global_step": 607229, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0252468585968018, "global_step": 607230, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9699783325195312, "global_step": 607231, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.961090087890625, "global_step": 607232, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9892094135284424, "global_step": 607233, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.040127992630005, "global_step": 607234, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9898799657821655, "global_step": 607235, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9624648094177246, "global_step": 607236, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.068237781524658, "global_step": 607237, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.038712501525879, "global_step": 607238, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9963740110397339, "global_step": 607239, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.045262575149536, "global_step": 607240, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.996518850326538, "global_step": 607241, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0598130226135254, "global_step": 607242, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.1025772094726562, "global_step": 607243, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.019657611846924, "global_step": 607244, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9281121492385864, "global_step": 607245, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0646371841430664, "global_step": 607246, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.938125491142273, "global_step": 607247, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.1080291271209717, "global_step": 607248, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9802906513214111, "global_step": 607249, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9342149496078491, "global_step": 607250, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.012585163116455, "global_step": 607251, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9979913234710693, "global_step": 607252, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0748467445373535, "global_step": 607253, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0366058349609375, "global_step": 607254, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0341074466705322, "global_step": 607255, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9872276782989502, "global_step": 607256, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0160365104675293, "global_step": 607257, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.08160662651062, "global_step": 607258, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0841081142425537, "global_step": 607259, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.05126690864563, "global_step": 607260, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9376436471939087, "global_step": 607261, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.8639830350875854, "global_step": 607262, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0386643409729004, "global_step": 607263, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0066428184509277, "global_step": 607264, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9065290689468384, "global_step": 607265, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0297467708587646, "global_step": 607266, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.078077793121338, "global_step": 607267, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.067678928375244, "global_step": 607268, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0323269367218018, "global_step": 607269, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.961275577545166, "global_step": 607270, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.003011703491211, "global_step": 607271, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.977969765663147, "global_step": 607272, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9739564657211304, "global_step": 607273, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9886616468429565, "global_step": 607274, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0605390071868896, "global_step": 607275, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9213744401931763, "global_step": 607276, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0582833290100098, "global_step": 607277, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9976530075073242, "global_step": 607278, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0193569660186768, "global_step": 607279, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.923226237297058, "global_step": 607280, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.017662286758423, "global_step": 607281, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0622966289520264, "global_step": 607282, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.995855689048767, "global_step": 607283, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.036210060119629, "global_step": 607284, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.1070728302001953, "global_step": 607285, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9113342761993408, "global_step": 607286, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9895583391189575, "global_step": 607287, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0883734226226807, "global_step": 607288, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.011500358581543, "global_step": 607289, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.023244619369507, "global_step": 607290, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.002692461013794, "global_step": 607291, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0824153423309326, "global_step": 607292, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.062263011932373, "global_step": 607293, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9400354623794556, "global_step": 607294, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0063061714172363, "global_step": 607295, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9970500469207764, "global_step": 607296, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9401532411575317, "global_step": 607297, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.978852391242981, "global_step": 607298, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0319998264312744, "global_step": 607299, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9856864213943481, "global_step": 607300, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0720176696777344, "global_step": 607301, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0168027877807617, "global_step": 607302, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0897533893585205, "global_step": 607303, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0616605281829834, "global_step": 607304, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.051624298095703, "global_step": 607305, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.023235559463501, "global_step": 607306, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9456285238265991, "global_step": 607307, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9688524007797241, "global_step": 607308, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.160569667816162, "global_step": 607309, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0193722248077393, "global_step": 607310, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.125542402267456, "global_step": 607311, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0969746112823486, "global_step": 607312, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0292279720306396, "global_step": 607313, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9586150646209717, "global_step": 607314, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.002166271209717, "global_step": 607315, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0418701171875, "global_step": 607316, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9854151010513306, "global_step": 607317, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.007329225540161, "global_step": 607318, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9604523181915283, "global_step": 607319, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9749577045440674, "global_step": 607320, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0276055335998535, "global_step": 607321, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9079357385635376, "global_step": 607322, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9689401388168335, "global_step": 607323, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0272104740142822, "global_step": 607324, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.062458038330078, "global_step": 607325, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9534395933151245, "global_step": 607326, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9629930257797241, "global_step": 607327, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9910167455673218, "global_step": 607328, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.096595048904419, "global_step": 607329, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9797247648239136, "global_step": 607330, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9886600971221924, "global_step": 607331, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9287643432617188, "global_step": 607332, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0479819774627686, "global_step": 607333, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9877272844314575, "global_step": 607334, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9849363565444946, "global_step": 607335, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0045008659362793, "global_step": 607336, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0490565299987793, "global_step": 607337, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.028822660446167, "global_step": 607338, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9896413087844849, "global_step": 607339, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.029228687286377, "global_step": 607340, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.011709451675415, "global_step": 607341, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0339198112487793, "global_step": 607342, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.032424211502075, "global_step": 607343, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0526845455169678, "global_step": 607344, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0790398120880127, "global_step": 607345, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0948634147644043, "global_step": 607346, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9561338424682617, "global_step": 607347, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9938918352127075, "global_step": 607348, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9704666137695312, "global_step": 607349, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.976549506187439, "global_step": 607350, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.936790108680725, "global_step": 607351, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0193142890930176, "global_step": 607352, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.010218858718872, "global_step": 607353, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0692570209503174, "global_step": 607354, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.052807569503784, "global_step": 607355, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0170092582702637, "global_step": 607356, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9757506847381592, "global_step": 607357, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9434865713119507, "global_step": 607358, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.971536636352539, "global_step": 607359, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9494942426681519, "global_step": 607360, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9655911922454834, "global_step": 607361, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0243990421295166, "global_step": 607362, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.049752712249756, "global_step": 607363, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9800026416778564, "global_step": 607364, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.1256089210510254, "global_step": 607365, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.004349946975708, "global_step": 607366, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0777788162231445, "global_step": 607367, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9808018207550049, "global_step": 607368, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0683035850524902, "global_step": 607369, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9691412448883057, "global_step": 607370, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.105890989303589, "global_step": 607371, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9923986196517944, "global_step": 607372, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9619896411895752, "global_step": 607373, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.017216205596924, "global_step": 607374, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0849037170410156, "global_step": 607375, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9591739177703857, "global_step": 607376, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9745975732803345, "global_step": 607377, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.051853656768799, "global_step": 607378, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0087778568267822, "global_step": 607379, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.052218437194824, "global_step": 607380, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.02175235748291, "global_step": 607381, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.1153039932250977, "global_step": 607382, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.972962737083435, "global_step": 607383, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.028035879135132, "global_step": 607384, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0671942234039307, "global_step": 607385, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0122599601745605, "global_step": 607386, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0188002586364746, "global_step": 607387, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.973305583000183, "global_step": 607388, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9402880668640137, "global_step": 607389, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.951745867729187, "global_step": 607390, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9991432428359985, "global_step": 607391, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.072533130645752, "global_step": 607392, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.8419820070266724, "global_step": 607393, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.007617950439453, "global_step": 607394, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0084779262542725, "global_step": 607395, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9890040159225464, "global_step": 607396, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0391533374786377, "global_step": 607397, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.934422254562378, "global_step": 607398, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.056978702545166, "global_step": 607399, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0366108417510986, "global_step": 607400, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9738969802856445, "global_step": 607401, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.065606117248535, "global_step": 607402, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.079975128173828, "global_step": 607403, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.026491165161133, "global_step": 607404, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9657907485961914, "global_step": 607405, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0869898796081543, "global_step": 607406, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.02616810798645, "global_step": 607407, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9379085302352905, "global_step": 607408, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9727733135223389, "global_step": 607409, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0057413578033447, "global_step": 607410, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0196022987365723, "global_step": 607411, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.046462297439575, "global_step": 607412, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.060300827026367, "global_step": 607413, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.988417148590088, "global_step": 607414, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0344722270965576, "global_step": 607415, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.038888931274414, "global_step": 607416, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0648491382598877, "global_step": 607417, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.086298942565918, "global_step": 607418, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.045400857925415, "global_step": 607419, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9469953775405884, "global_step": 607420, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0011637210845947, "global_step": 607421, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9404394626617432, "global_step": 607422, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0848958492279053, "global_step": 607423, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.000345468521118, "global_step": 607424, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0081491470336914, "global_step": 607425, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.974631667137146, "global_step": 607426, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0671632289886475, "global_step": 607427, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.005223035812378, "global_step": 607428, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9916417598724365, "global_step": 607429, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0771584510803223, "global_step": 607430, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.005472421646118, "global_step": 607431, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.031956434249878, "global_step": 607432, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0222039222717285, "global_step": 607433, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.103785991668701, "global_step": 607434, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0271289348602295, "global_step": 607435, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0429372787475586, "global_step": 607436, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.976840615272522, "global_step": 607437, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0177762508392334, "global_step": 607438, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9947497844696045, "global_step": 607439, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.04333233833313, "global_step": 607440, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9500452280044556, "global_step": 607441, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9634838104248047, "global_step": 607442, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0206122398376465, "global_step": 607443, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0142810344696045, "global_step": 607444, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0493407249450684, "global_step": 607445, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0996265411376953, "global_step": 607446, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.928848385810852, "global_step": 607447, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.046917676925659, "global_step": 607448, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0658986568450928, "global_step": 607449, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9934909343719482, "global_step": 607450, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0486509799957275, "global_step": 607451, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.050288677215576, "global_step": 607452, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.095061779022217, "global_step": 607453, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0719614028930664, "global_step": 607454, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9845154285430908, "global_step": 607455, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9607305526733398, "global_step": 607456, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.006014347076416, "global_step": 607457, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9665300846099854, "global_step": 607458, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.911432147026062, "global_step": 607459, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.058058023452759, "global_step": 607460, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9954197406768799, "global_step": 607461, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.016278028488159, "global_step": 607462, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.03129243850708, "global_step": 607463, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0820915699005127, "global_step": 607464, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.034470558166504, "global_step": 607465, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.024548053741455, "global_step": 607466, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9845353364944458, "global_step": 607467, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.052685022354126, "global_step": 607468, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0384647846221924, "global_step": 607469, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.006077766418457, "global_step": 607470, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0817465782165527, "global_step": 607471, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.090721368789673, "global_step": 607472, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.077199697494507, "global_step": 607473, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0764660835266113, "global_step": 607474, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.021613836288452, "global_step": 607475, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9780887365341187, "global_step": 607476, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0820670127868652, "global_step": 607477, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0529041290283203, "global_step": 607478, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9449650049209595, "global_step": 607479, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.052924871444702, "global_step": 607480, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9648962020874023, "global_step": 607481, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9693763256072998, "global_step": 607482, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.977529525756836, "global_step": 607483, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0314252376556396, "global_step": 607484, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0077860355377197, "global_step": 607485, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9860376119613647, "global_step": 607486, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0486695766448975, "global_step": 607487, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0231454372406006, "global_step": 607488, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0562901496887207, "global_step": 607489, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9747788906097412, "global_step": 607490, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0603864192962646, "global_step": 607491, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9314310550689697, "global_step": 607492, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0390634536743164, "global_step": 607493, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0775086879730225, "global_step": 607494, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.022446632385254, "global_step": 607495, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.065537452697754, "global_step": 607496, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9608761072158813, "global_step": 607497, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0589678287506104, "global_step": 607498, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0374443531036377, "global_step": 607499, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9908642768859863, "global_step": 607500, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0646886825561523, "global_step": 607501, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.98505437374115, "global_step": 607502, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0411689281463623, "global_step": 607503, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0308053493499756, "global_step": 607504, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.000276565551758, "global_step": 607505, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9840753078460693, "global_step": 607506, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9458469152450562, "global_step": 607507, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0482089519500732, "global_step": 607508, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.000044584274292, "global_step": 607509, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.987601637840271, "global_step": 607510, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.062528610229492, "global_step": 607511, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.8651535511016846, "global_step": 607512, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.028168201446533, "global_step": 607513, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0654542446136475, "global_step": 607514, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.003202199935913, "global_step": 607515, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0220017433166504, "global_step": 607516, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0271081924438477, "global_step": 607517, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9637973308563232, "global_step": 607518, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.930285930633545, "global_step": 607519, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9791483879089355, "global_step": 607520, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.967383861541748, "global_step": 607521, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9741113185882568, "global_step": 607522, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.060401439666748, "global_step": 607523, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0981929302215576, "global_step": 607524, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0583889484405518, "global_step": 607525, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9698736667633057, "global_step": 607526, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0337159633636475, "global_step": 607527, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9607970714569092, "global_step": 607528, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0535671710968018, "global_step": 607529, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9538342952728271, "global_step": 607530, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9240148067474365, "global_step": 607531, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9818121194839478, "global_step": 607532, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.024024248123169, "global_step": 607533, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.040194034576416, "global_step": 607534, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0084779262542725, "global_step": 607535, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9857841730117798, "global_step": 607536, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9658641815185547, "global_step": 607537, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9965559244155884, "global_step": 607538, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.004549503326416, "global_step": 607539, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.060861110687256, "global_step": 607540, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0355541706085205, "global_step": 607541, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.076960802078247, "global_step": 607542, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.070711374282837, "global_step": 607543, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0997424125671387, "global_step": 607544, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9742227792739868, "global_step": 607545, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.060734510421753, "global_step": 607546, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0959365367889404, "global_step": 607547, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9774997234344482, "global_step": 607548, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9703787565231323, "global_step": 607549, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.039080858230591, "global_step": 607550, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0504894256591797, "global_step": 607551, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.023907423019409, "global_step": 607552, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.014580249786377, "global_step": 607553, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0627686977386475, "global_step": 607554, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.040384292602539, "global_step": 607555, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9631481170654297, "global_step": 607556, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.015488386154175, "global_step": 607557, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.044981002807617, "global_step": 607558, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.032355785369873, "global_step": 607559, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.025628089904785, "global_step": 607560, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9840763807296753, "global_step": 607561, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.00065016746521, "global_step": 607562, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0063226222991943, "global_step": 607563, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.025682210922241, "global_step": 607564, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9380114078521729, "global_step": 607565, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.966993808746338, "global_step": 607566, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0098817348480225, "global_step": 607567, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.997654914855957, "global_step": 607568, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9970344305038452, "global_step": 607569, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.00286865234375, "global_step": 607570, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9596631526947021, "global_step": 607571, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9733617305755615, "global_step": 607572, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.996507167816162, "global_step": 607573, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0278515815734863, "global_step": 607574, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.047149181365967, "global_step": 607575, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.006030559539795, "global_step": 607576, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.127614974975586, "global_step": 607577, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.048628330230713, "global_step": 607578, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.026549816131592, "global_step": 607579, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.038831949234009, "global_step": 607580, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0038678646087646, "global_step": 607581, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.06616473197937, "global_step": 607582, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0013091564178467, "global_step": 607583, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0681254863739014, "global_step": 607584, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9723855257034302, "global_step": 607585, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0448102951049805, "global_step": 607586, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0436716079711914, "global_step": 607587, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.8902909755706787, "global_step": 607588, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0565733909606934, "global_step": 607589, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9775102138519287, "global_step": 607590, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.8930565118789673, "global_step": 607591, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.038200616836548, "global_step": 607592, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9864039421081543, "global_step": 607593, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0432209968566895, "global_step": 607594, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.97819983959198, "global_step": 607595, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.051379680633545, "global_step": 607596, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0588457584381104, "global_step": 607597, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0475499629974365, "global_step": 607598, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0901405811309814, "global_step": 607599, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9696296453475952, "global_step": 607600, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.000844717025757, "global_step": 607601, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0520858764648438, "global_step": 607602, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0377166271209717, "global_step": 607603, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.012216806411743, "global_step": 607604, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0190012454986572, "global_step": 607605, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0445282459259033, "global_step": 607606, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9527682065963745, "global_step": 607607, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9370278120040894, "global_step": 607608, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.991119384765625, "global_step": 607609, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9345364570617676, "global_step": 607610, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.009611129760742, "global_step": 607611, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0753602981567383, "global_step": 607612, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0257184505462646, "global_step": 607613, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0356712341308594, "global_step": 607614, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9979275465011597, "global_step": 607615, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0284433364868164, "global_step": 607616, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9665050506591797, "global_step": 607617, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.01181697845459, "global_step": 607618, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9691270589828491, "global_step": 607619, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0208773612976074, "global_step": 607620, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0747230052948, "global_step": 607621, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.022432327270508, "global_step": 607622, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9641697406768799, "global_step": 607623, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0097131729125977, "global_step": 607624, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.998887538909912, "global_step": 607625, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0467965602874756, "global_step": 607626, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9782285690307617, "global_step": 607627, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.016005277633667, "global_step": 607628, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9995678663253784, "global_step": 607629, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.924165964126587, "global_step": 607630, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.016754388809204, "global_step": 607631, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9912152290344238, "global_step": 607632, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.979528784751892, "global_step": 607633, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.990139365196228, "global_step": 607634, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0115585327148438, "global_step": 607635, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.076310157775879, "global_step": 607636, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9797183275222778, "global_step": 607637, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.014977216720581, "global_step": 607638, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9816977977752686, "global_step": 607639, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9903974533081055, "global_step": 607640, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9957807064056396, "global_step": 607641, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.151529550552368, "global_step": 607642, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9496560096740723, "global_step": 607643, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.014873743057251, "global_step": 607644, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0285909175872803, "global_step": 607645, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0234391689300537, "global_step": 607646, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9712343215942383, "global_step": 607647, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0444154739379883, "global_step": 607648, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.993991732597351, "global_step": 607649, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9867252111434937, "global_step": 607650, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.050804615020752, "global_step": 607651, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.020664930343628, "global_step": 607652, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.042536735534668, "global_step": 607653, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0397706031799316, "global_step": 607654, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0221502780914307, "global_step": 607655, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.005573272705078, "global_step": 607656, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.008937358856201, "global_step": 607657, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.00539231300354, "global_step": 607658, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0655627250671387, "global_step": 607659, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0263946056365967, "global_step": 607660, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.042909860610962, "global_step": 607661, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9730103015899658, "global_step": 607662, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0217299461364746, "global_step": 607663, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0027294158935547, "global_step": 607664, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0027928352355957, "global_step": 607665, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0737552642822266, "global_step": 607666, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9772735834121704, "global_step": 607667, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.988692045211792, "global_step": 607668, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0225284099578857, "global_step": 607669, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.987765908241272, "global_step": 607670, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9936439990997314, "global_step": 607671, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9779971837997437, "global_step": 607672, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0273399353027344, "global_step": 607673, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.028176784515381, "global_step": 607674, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.037435293197632, "global_step": 607675, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0668535232543945, "global_step": 607676, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0055034160614014, "global_step": 607677, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9652578830718994, "global_step": 607678, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9553700685501099, "global_step": 607679, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.111675977706909, "global_step": 607680, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9195756912231445, "global_step": 607681, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.096240520477295, "global_step": 607682, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9904388189315796, "global_step": 607683, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.038299083709717, "global_step": 607684, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0166568756103516, "global_step": 607685, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0183658599853516, "global_step": 607686, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.006469964981079, "global_step": 607687, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.028625965118408, "global_step": 607688, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.003448724746704, "global_step": 607689, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.021094560623169, "global_step": 607690, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9960236549377441, "global_step": 607691, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.966230034828186, "global_step": 607692, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0039093494415283, "global_step": 607693, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.002599000930786, "global_step": 607694, "epoch": 976, "lr": 5e-05}
{"train_loss": 2.0085525512695312, "global_step": 607695, "epoch": 976, "lr": 5e-05}
{"train_loss": 1.9894455671310425, "global_step": 607696, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0393168926239014, "global_step": 607697, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0384764671325684, "global_step": 607698, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9288041591644287, "global_step": 607699, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9817934036254883, "global_step": 607700, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.995375394821167, "global_step": 607701, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0728096961975098, "global_step": 607702, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.035905599594116, "global_step": 607703, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0019989013671875, "global_step": 607704, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0369362831115723, "global_step": 607705, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9894200563430786, "global_step": 607706, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9589612483978271, "global_step": 607707, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.050933361053467, "global_step": 607708, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0136749744415283, "global_step": 607709, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9446498155593872, "global_step": 607710, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0940089225769043, "global_step": 607711, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.036017894744873, "global_step": 607712, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9852042198181152, "global_step": 607713, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.100294589996338, "global_step": 607714, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0424766540527344, "global_step": 607715, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9998905658721924, "global_step": 607716, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0307254791259766, "global_step": 607717, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0766489505767822, "global_step": 607718, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0193192958831787, "global_step": 607719, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9783084392547607, "global_step": 607720, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9306825399398804, "global_step": 607721, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9818241596221924, "global_step": 607722, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9897525310516357, "global_step": 607723, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9676730632781982, "global_step": 607724, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9775172472000122, "global_step": 607725, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9255919456481934, "global_step": 607726, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.988295078277588, "global_step": 607727, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0730228424072266, "global_step": 607728, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.034475564956665, "global_step": 607729, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.957139015197754, "global_step": 607730, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9752191305160522, "global_step": 607731, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9298945665359497, "global_step": 607732, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.083176374435425, "global_step": 607733, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9409199953079224, "global_step": 607734, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.006850004196167, "global_step": 607735, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.917479157447815, "global_step": 607736, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9613959789276123, "global_step": 607737, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9156397581100464, "global_step": 607738, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.986325979232788, "global_step": 607739, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.951595664024353, "global_step": 607740, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9655650854110718, "global_step": 607741, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.024085760116577, "global_step": 607742, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9420121908187866, "global_step": 607743, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9715328216552734, "global_step": 607744, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0132694244384766, "global_step": 607745, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.918587327003479, "global_step": 607746, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0444576740264893, "global_step": 607747, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0915372371673584, "global_step": 607748, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.964482069015503, "global_step": 607749, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9895000457763672, "global_step": 607750, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.039720058441162, "global_step": 607751, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.085066795349121, "global_step": 607752, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.930186152458191, "global_step": 607753, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0366878509521484, "global_step": 607754, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9844930171966553, "global_step": 607755, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9780833721160889, "global_step": 607756, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9152427911758423, "global_step": 607757, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9508106708526611, "global_step": 607758, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.993701696395874, "global_step": 607759, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.013580083847046, "global_step": 607760, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.057321310043335, "global_step": 607761, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0666613578796387, "global_step": 607762, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0518240928649902, "global_step": 607763, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0202646255493164, "global_step": 607764, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9691920280456543, "global_step": 607765, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9332574605941772, "global_step": 607766, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9386982917785645, "global_step": 607767, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9938420057296753, "global_step": 607768, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9477193355560303, "global_step": 607769, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.004349708557129, "global_step": 607770, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.053748369216919, "global_step": 607771, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.047315835952759, "global_step": 607772, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9967368841171265, "global_step": 607773, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9715477228164673, "global_step": 607774, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9128727912902832, "global_step": 607775, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.122199058532715, "global_step": 607776, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.068918466567993, "global_step": 607777, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.048426628112793, "global_step": 607778, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.007477045059204, "global_step": 607779, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0477797985076904, "global_step": 607780, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9003338813781738, "global_step": 607781, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.948980450630188, "global_step": 607782, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.8935147523880005, "global_step": 607783, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.965267300605774, "global_step": 607784, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.07804799079895, "global_step": 607785, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.1491432189941406, "global_step": 607786, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.952986717224121, "global_step": 607787, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9929996728897095, "global_step": 607788, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.024109125137329, "global_step": 607789, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9438551664352417, "global_step": 607790, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0243570804595947, "global_step": 607791, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9519761800765991, "global_step": 607792, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.011756181716919, "global_step": 607793, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9480345249176025, "global_step": 607794, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0047976970672607, "global_step": 607795, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.94718599319458, "global_step": 607796, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.051575183868408, "global_step": 607797, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.884479284286499, "global_step": 607798, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9558279514312744, "global_step": 607799, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9238593578338623, "global_step": 607800, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.041071891784668, "global_step": 607801, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0717718601226807, "global_step": 607802, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0237317085266113, "global_step": 607803, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.98493230342865, "global_step": 607804, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9361484050750732, "global_step": 607805, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.987207293510437, "global_step": 607806, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.975895881652832, "global_step": 607807, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9798740148544312, "global_step": 607808, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.020284414291382, "global_step": 607809, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9739621877670288, "global_step": 607810, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.045626640319824, "global_step": 607811, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0747385025024414, "global_step": 607812, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0154190063476562, "global_step": 607813, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.003763198852539, "global_step": 607814, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0357611179351807, "global_step": 607815, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9583148956298828, "global_step": 607816, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.1434853076934814, "global_step": 607817, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.00360107421875, "global_step": 607818, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.002169609069824, "global_step": 607819, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9656016826629639, "global_step": 607820, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9551242589950562, "global_step": 607821, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.983579397201538, "global_step": 607822, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0261738300323486, "global_step": 607823, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0072405338287354, "global_step": 607824, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.098656415939331, "global_step": 607825, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0417659282684326, "global_step": 607826, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.063734531402588, "global_step": 607827, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9699088335037231, "global_step": 607828, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.989620327949524, "global_step": 607829, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9763253927230835, "global_step": 607830, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9436473846435547, "global_step": 607831, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0021419525146484, "global_step": 607832, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.046015739440918, "global_step": 607833, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0468244552612305, "global_step": 607834, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0060970783233643, "global_step": 607835, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0004172325134277, "global_step": 607836, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9471917152404785, "global_step": 607837, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0129995346069336, "global_step": 607838, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9742740392684937, "global_step": 607839, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.028930187225342, "global_step": 607840, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.89249587059021, "global_step": 607841, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9630396366119385, "global_step": 607842, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9932767152786255, "global_step": 607843, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0050013065338135, "global_step": 607844, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0255610942840576, "global_step": 607845, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.074540138244629, "global_step": 607846, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9298064708709717, "global_step": 607847, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9649444818496704, "global_step": 607848, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0401549339294434, "global_step": 607849, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9628770351409912, "global_step": 607850, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.086972236633301, "global_step": 607851, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.098602771759033, "global_step": 607852, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9888858795166016, "global_step": 607853, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0948500633239746, "global_step": 607854, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9482479095458984, "global_step": 607855, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0545814037323, "global_step": 607856, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.055856227874756, "global_step": 607857, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.041696786880493, "global_step": 607858, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0104637145996094, "global_step": 607859, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.984640121459961, "global_step": 607860, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.035611391067505, "global_step": 607861, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0077462196350098, "global_step": 607862, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.004913330078125, "global_step": 607863, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.972933053970337, "global_step": 607864, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9422836303710938, "global_step": 607865, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9117648601531982, "global_step": 607866, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.955539345741272, "global_step": 607867, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.022498369216919, "global_step": 607868, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.005197048187256, "global_step": 607869, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.059075355529785, "global_step": 607870, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9202847480773926, "global_step": 607871, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.067413568496704, "global_step": 607872, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0260720252990723, "global_step": 607873, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9915425777435303, "global_step": 607874, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.010932683944702, "global_step": 607875, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.033311128616333, "global_step": 607876, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0224685668945312, "global_step": 607877, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0431416034698486, "global_step": 607878, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0390658378601074, "global_step": 607879, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.066498041152954, "global_step": 607880, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0499918460845947, "global_step": 607881, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9240392446517944, "global_step": 607882, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0356943607330322, "global_step": 607883, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9403928518295288, "global_step": 607884, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0637857913970947, "global_step": 607885, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.011892557144165, "global_step": 607886, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.002880573272705, "global_step": 607887, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.060410261154175, "global_step": 607888, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9580447673797607, "global_step": 607889, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0302886962890625, "global_step": 607890, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.967970848083496, "global_step": 607891, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.8631082773208618, "global_step": 607892, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9451804161071777, "global_step": 607893, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0077641010284424, "global_step": 607894, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.088658571243286, "global_step": 607895, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9859782457351685, "global_step": 607896, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0854239463806152, "global_step": 607897, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9798414707183838, "global_step": 607898, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0191705226898193, "global_step": 607899, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.010852813720703, "global_step": 607900, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9794820547103882, "global_step": 607901, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9603419303894043, "global_step": 607902, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0400378704071045, "global_step": 607903, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.027791976928711, "global_step": 607904, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.035189151763916, "global_step": 607905, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0627288818359375, "global_step": 607906, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.064439058303833, "global_step": 607907, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0810744762420654, "global_step": 607908, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9019871950149536, "global_step": 607909, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9297939538955688, "global_step": 607910, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0257797241210938, "global_step": 607911, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.019092559814453, "global_step": 607912, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.048262357711792, "global_step": 607913, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0458426475524902, "global_step": 607914, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.044456958770752, "global_step": 607915, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9913064241409302, "global_step": 607916, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0618441104888916, "global_step": 607917, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0476512908935547, "global_step": 607918, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9339852333068848, "global_step": 607919, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9727061986923218, "global_step": 607920, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9399999380111694, "global_step": 607921, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0092902183532715, "global_step": 607922, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0006890296936035, "global_step": 607923, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9818648099899292, "global_step": 607924, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0252535343170166, "global_step": 607925, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9804551601409912, "global_step": 607926, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9437763690948486, "global_step": 607927, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.023710012435913, "global_step": 607928, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.006211042404175, "global_step": 607929, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0561699867248535, "global_step": 607930, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0585837364196777, "global_step": 607931, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.059474468231201, "global_step": 607932, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.057584285736084, "global_step": 607933, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.863516926765442, "global_step": 607934, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0335490703582764, "global_step": 607935, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9976887702941895, "global_step": 607936, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9070982933044434, "global_step": 607937, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9205224514007568, "global_step": 607938, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9836289882659912, "global_step": 607939, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0447962284088135, "global_step": 607940, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.038635492324829, "global_step": 607941, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.021352767944336, "global_step": 607942, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.013314723968506, "global_step": 607943, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.047311305999756, "global_step": 607944, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.936445951461792, "global_step": 607945, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.8972104787826538, "global_step": 607946, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0823817253112793, "global_step": 607947, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0171523094177246, "global_step": 607948, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0089733600616455, "global_step": 607949, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9704971313476562, "global_step": 607950, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0272154808044434, "global_step": 607951, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9417158365249634, "global_step": 607952, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9900801181793213, "global_step": 607953, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9480454921722412, "global_step": 607954, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0965495109558105, "global_step": 607955, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9893629550933838, "global_step": 607956, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.005171537399292, "global_step": 607957, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0644173622131348, "global_step": 607958, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0307483673095703, "global_step": 607959, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0307185649871826, "global_step": 607960, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.1059861183166504, "global_step": 607961, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.053999185562134, "global_step": 607962, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0198147296905518, "global_step": 607963, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9392473697662354, "global_step": 607964, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.002810001373291, "global_step": 607965, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9606772661209106, "global_step": 607966, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0359854698181152, "global_step": 607967, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0252256393432617, "global_step": 607968, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.068800210952759, "global_step": 607969, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.062415838241577, "global_step": 607970, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9529181718826294, "global_step": 607971, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9270986318588257, "global_step": 607972, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9991530179977417, "global_step": 607973, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.041299819946289, "global_step": 607974, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0124902725219727, "global_step": 607975, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0285301208496094, "global_step": 607976, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0284202098846436, "global_step": 607977, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0250513553619385, "global_step": 607978, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.930411458015442, "global_step": 607979, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9893633127212524, "global_step": 607980, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.023165702819824, "global_step": 607981, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.974572777748108, "global_step": 607982, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.882469654083252, "global_step": 607983, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.995476245880127, "global_step": 607984, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.968318223953247, "global_step": 607985, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0869178771972656, "global_step": 607986, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9389630556106567, "global_step": 607987, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0927772521972656, "global_step": 607988, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0566699504852295, "global_step": 607989, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.092864513397217, "global_step": 607990, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9958293437957764, "global_step": 607991, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9879915714263916, "global_step": 607992, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.049795150756836, "global_step": 607993, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9998326301574707, "global_step": 607994, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.091660261154175, "global_step": 607995, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0846264362335205, "global_step": 607996, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9803290367126465, "global_step": 607997, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.004534959793091, "global_step": 607998, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.990825891494751, "global_step": 607999, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9503238201141357, "global_step": 608000, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9446041584014893, "global_step": 608001, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9851462841033936, "global_step": 608002, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9734294414520264, "global_step": 608003, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9430469274520874, "global_step": 608004, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.060690402984619, "global_step": 608005, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0234487056732178, "global_step": 608006, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.004220485687256, "global_step": 608007, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9539072513580322, "global_step": 608008, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.023963451385498, "global_step": 608009, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9157341718673706, "global_step": 608010, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0660524368286133, "global_step": 608011, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9704868793487549, "global_step": 608012, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9816687107086182, "global_step": 608013, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9960992336273193, "global_step": 608014, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.99454665184021, "global_step": 608015, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9714833498001099, "global_step": 608016, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9948713779449463, "global_step": 608017, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9797221422195435, "global_step": 608018, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9822288751602173, "global_step": 608019, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.973473072052002, "global_step": 608020, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.097712993621826, "global_step": 608021, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9635934829711914, "global_step": 608022, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0333094596862793, "global_step": 608023, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9582024812698364, "global_step": 608024, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.967699646949768, "global_step": 608025, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0031282901763916, "global_step": 608026, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.045233964920044, "global_step": 608027, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.969617247581482, "global_step": 608028, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9897949695587158, "global_step": 608029, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.8953099250793457, "global_step": 608030, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.021167755126953, "global_step": 608031, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9768966436386108, "global_step": 608032, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0399434566497803, "global_step": 608033, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.1189587116241455, "global_step": 608034, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.05539608001709, "global_step": 608035, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0122992992401123, "global_step": 608036, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.049788475036621, "global_step": 608037, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.026062250137329, "global_step": 608038, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.069420099258423, "global_step": 608039, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9768391847610474, "global_step": 608040, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0747790336608887, "global_step": 608041, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0170154571533203, "global_step": 608042, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.8743678331375122, "global_step": 608043, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.036877393722534, "global_step": 608044, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9982935190200806, "global_step": 608045, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0406570434570312, "global_step": 608046, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.000082015991211, "global_step": 608047, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0568206310272217, "global_step": 608048, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9923629760742188, "global_step": 608049, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.992599606513977, "global_step": 608050, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0720314979553223, "global_step": 608051, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.976051926612854, "global_step": 608052, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.944493293762207, "global_step": 608053, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.002707004547119, "global_step": 608054, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0479283332824707, "global_step": 608055, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.94479501247406, "global_step": 608056, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.003627300262451, "global_step": 608057, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9102258682250977, "global_step": 608058, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9504255056381226, "global_step": 608059, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.013293504714966, "global_step": 608060, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.029331922531128, "global_step": 608061, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9513522386550903, "global_step": 608062, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.990572452545166, "global_step": 608063, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.972929835319519, "global_step": 608064, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9497568607330322, "global_step": 608065, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9822760820388794, "global_step": 608066, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.05051851272583, "global_step": 608067, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9344797134399414, "global_step": 608068, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0092365741729736, "global_step": 608069, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9630998373031616, "global_step": 608070, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.015841007232666, "global_step": 608071, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9218140840530396, "global_step": 608072, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.971725344657898, "global_step": 608073, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0733866691589355, "global_step": 608074, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9423975944519043, "global_step": 608075, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0220274925231934, "global_step": 608076, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9098906517028809, "global_step": 608077, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.029224157333374, "global_step": 608078, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0069189071655273, "global_step": 608079, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0117759704589844, "global_step": 608080, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.059302806854248, "global_step": 608081, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9964959621429443, "global_step": 608082, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9628703594207764, "global_step": 608083, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9527519941329956, "global_step": 608084, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.982507348060608, "global_step": 608085, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.010831117630005, "global_step": 608086, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.043286085128784, "global_step": 608087, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9206349849700928, "global_step": 608088, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9324607849121094, "global_step": 608089, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9376285076141357, "global_step": 608090, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9035797119140625, "global_step": 608091, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0152394771575928, "global_step": 608092, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0520083904266357, "global_step": 608093, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9595266580581665, "global_step": 608094, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.991165041923523, "global_step": 608095, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9426909685134888, "global_step": 608096, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.992430329322815, "global_step": 608097, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0236544609069824, "global_step": 608098, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.078786849975586, "global_step": 608099, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.00345516204834, "global_step": 608100, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9955657720565796, "global_step": 608101, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.933680772781372, "global_step": 608102, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.067805290222168, "global_step": 608103, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0996406078338623, "global_step": 608104, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9563190937042236, "global_step": 608105, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.1147267818450928, "global_step": 608106, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.014291286468506, "global_step": 608107, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.935604214668274, "global_step": 608108, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.060616970062256, "global_step": 608109, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9509609937667847, "global_step": 608110, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9574615955352783, "global_step": 608111, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.055854082107544, "global_step": 608112, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.022804021835327, "global_step": 608113, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9722212553024292, "global_step": 608114, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0258162021636963, "global_step": 608115, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.092881917953491, "global_step": 608116, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.991762399673462, "global_step": 608117, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0159950256347656, "global_step": 608118, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0774998664855957, "global_step": 608119, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.018561363220215, "global_step": 608120, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.026435136795044, "global_step": 608121, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9869091510772705, "global_step": 608122, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0871458053588867, "global_step": 608123, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.044095039367676, "global_step": 608124, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0213310718536377, "global_step": 608125, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0865955352783203, "global_step": 608126, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.040560722351074, "global_step": 608127, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.986039638519287, "global_step": 608128, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0506162643432617, "global_step": 608129, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.057462453842163, "global_step": 608130, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0453503131866455, "global_step": 608131, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.048689365386963, "global_step": 608132, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.1276164054870605, "global_step": 608133, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.965325951576233, "global_step": 608134, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0428481101989746, "global_step": 608135, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.056084632873535, "global_step": 608136, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9034863710403442, "global_step": 608137, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9982622861862183, "global_step": 608138, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.934403657913208, "global_step": 608139, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.090440273284912, "global_step": 608140, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0077104568481445, "global_step": 608141, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9995408058166504, "global_step": 608142, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0154645442962646, "global_step": 608143, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0188663005828857, "global_step": 608144, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9487183094024658, "global_step": 608145, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9892915487289429, "global_step": 608146, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0059914588928223, "global_step": 608147, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0003533363342285, "global_step": 608148, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.081861734390259, "global_step": 608149, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9846408367156982, "global_step": 608150, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.945710301399231, "global_step": 608151, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0323619842529297, "global_step": 608152, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.029128074645996, "global_step": 608153, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9482566118240356, "global_step": 608154, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9963783025741577, "global_step": 608155, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0116472244262695, "global_step": 608156, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9570094347000122, "global_step": 608157, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.086493730545044, "global_step": 608158, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9778740406036377, "global_step": 608159, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9595927000045776, "global_step": 608160, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0438334941864014, "global_step": 608161, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9897910356521606, "global_step": 608162, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0167219638824463, "global_step": 608163, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.06020188331604, "global_step": 608164, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.953123688697815, "global_step": 608165, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9702413082122803, "global_step": 608166, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9477038383483887, "global_step": 608167, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0224900245666504, "global_step": 608168, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9891413450241089, "global_step": 608169, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.1245274543762207, "global_step": 608170, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.957000970840454, "global_step": 608171, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9914727210998535, "global_step": 608172, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9837067127227783, "global_step": 608173, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.008248805999756, "global_step": 608174, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.026190996170044, "global_step": 608175, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9461870193481445, "global_step": 608176, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.038219451904297, "global_step": 608177, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.042346954345703, "global_step": 608178, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.017202138900757, "global_step": 608179, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0128090381622314, "global_step": 608180, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0572500228881836, "global_step": 608181, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9501112699508667, "global_step": 608182, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.068051338195801, "global_step": 608183, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9581903219223022, "global_step": 608184, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.032864809036255, "global_step": 608185, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0348329544067383, "global_step": 608186, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.077227830886841, "global_step": 608187, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0036206245422363, "global_step": 608188, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9881223440170288, "global_step": 608189, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9423930644989014, "global_step": 608190, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.983718991279602, "global_step": 608191, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0910751819610596, "global_step": 608192, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9888676404953003, "global_step": 608193, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.013707160949707, "global_step": 608194, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.998106598854065, "global_step": 608195, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9989715814590454, "global_step": 608196, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.071596622467041, "global_step": 608197, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9975249767303467, "global_step": 608198, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.005073308944702, "global_step": 608199, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9623613357543945, "global_step": 608200, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.058866500854492, "global_step": 608201, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.01566219329834, "global_step": 608202, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.973217248916626, "global_step": 608203, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9262733459472656, "global_step": 608204, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9102925062179565, "global_step": 608205, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.938705563545227, "global_step": 608206, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9801751375198364, "global_step": 608207, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.097510576248169, "global_step": 608208, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0394668579101562, "global_step": 608209, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.060779571533203, "global_step": 608210, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.029639482498169, "global_step": 608211, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.030691146850586, "global_step": 608212, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.018842935562134, "global_step": 608213, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9358460903167725, "global_step": 608214, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9249260425567627, "global_step": 608215, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9634051322937012, "global_step": 608216, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0173468589782715, "global_step": 608217, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.990685224533081, "global_step": 608218, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0195930004119873, "global_step": 608219, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9608566761016846, "global_step": 608220, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9666428565979004, "global_step": 608221, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9715341329574585, "global_step": 608222, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.064682960510254, "global_step": 608223, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9974346160888672, "global_step": 608224, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.023139476776123, "global_step": 608225, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.005183696746826, "global_step": 608226, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.977181077003479, "global_step": 608227, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9855471849441528, "global_step": 608228, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0218727588653564, "global_step": 608229, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.062854528427124, "global_step": 608230, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.049410820007324, "global_step": 608231, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9783810377120972, "global_step": 608232, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.070495843887329, "global_step": 608233, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0001814365386963, "global_step": 608234, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9965474605560303, "global_step": 608235, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.966956377029419, "global_step": 608236, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0062830448150635, "global_step": 608237, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9492158889770508, "global_step": 608238, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0195322036743164, "global_step": 608239, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9876130819320679, "global_step": 608240, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.012101650238037, "global_step": 608241, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9637757539749146, "global_step": 608242, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.953375220298767, "global_step": 608243, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9208621978759766, "global_step": 608244, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.1558125019073486, "global_step": 608245, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0510292053222656, "global_step": 608246, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9847707748413086, "global_step": 608247, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9518613815307617, "global_step": 608248, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0385334491729736, "global_step": 608249, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.986000418663025, "global_step": 608250, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.1222376823425293, "global_step": 608251, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.083357572555542, "global_step": 608252, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9127790927886963, "global_step": 608253, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.989599347114563, "global_step": 608254, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0257487297058105, "global_step": 608255, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9729334115982056, "global_step": 608256, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0449023246765137, "global_step": 608257, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0611538887023926, "global_step": 608258, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0301363468170166, "global_step": 608259, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9691470861434937, "global_step": 608260, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0056724548339844, "global_step": 608261, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0523018836975098, "global_step": 608262, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0536694526672363, "global_step": 608263, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0070526599884033, "global_step": 608264, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0639102458953857, "global_step": 608265, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0836148262023926, "global_step": 608266, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9784249067306519, "global_step": 608267, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0279321670532227, "global_step": 608268, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9878956079483032, "global_step": 608269, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9896094799041748, "global_step": 608270, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9956634044647217, "global_step": 608271, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9742296934127808, "global_step": 608272, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0094494819641113, "global_step": 608273, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9283665418624878, "global_step": 608274, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.962050437927246, "global_step": 608275, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0409178733825684, "global_step": 608276, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.033473014831543, "global_step": 608277, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9621891975402832, "global_step": 608278, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.957600712776184, "global_step": 608279, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9669222831726074, "global_step": 608280, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9914230108261108, "global_step": 608281, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0041439533233643, "global_step": 608282, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9672926664352417, "global_step": 608283, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.033689498901367, "global_step": 608284, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.037766218185425, "global_step": 608285, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.007795572280884, "global_step": 608286, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.052855968475342, "global_step": 608287, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.009234666824341, "global_step": 608288, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.010784387588501, "global_step": 608289, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.001837968826294, "global_step": 608290, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0103189945220947, "global_step": 608291, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.083233594894409, "global_step": 608292, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0026485919952393, "global_step": 608293, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0324904918670654, "global_step": 608294, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0433349609375, "global_step": 608295, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9058938026428223, "global_step": 608296, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9604547023773193, "global_step": 608297, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.974751591682434, "global_step": 608298, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.019777774810791, "global_step": 608299, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.058602809906006, "global_step": 608300, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9745186567306519, "global_step": 608301, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9726674556732178, "global_step": 608302, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9117194414138794, "global_step": 608303, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.990868330001831, "global_step": 608304, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9051339626312256, "global_step": 608305, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0365872383117676, "global_step": 608306, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.032116413116455, "global_step": 608307, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.022179365158081, "global_step": 608308, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.010890007019043, "global_step": 608309, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9684184789657593, "global_step": 608310, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9387127161026, "global_step": 608311, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0378928184509277, "global_step": 608312, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9869797229766846, "global_step": 608313, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.020907163619995, "global_step": 608314, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9397209882736206, "global_step": 608315, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0817160606384277, "global_step": 608316, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0161476135253906, "global_step": 608317, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0099635124206543, "global_step": 608318, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.009998083114624, "global_step": 608319, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0032036304473877, "global_step": 608320, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.014798879623413, "global_step": 608321, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0134992599487305, "global_step": 608322, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9477444887161255, "global_step": 608323, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.030496120452881, "global_step": 608324, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.951488733291626, "global_step": 608325, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0452075004577637, "global_step": 608326, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0835201740264893, "global_step": 608327, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9683282375335693, "global_step": 608328, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0308468341827393, "global_step": 608329, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.014385938644409, "global_step": 608330, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0847842693328857, "global_step": 608331, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.087754487991333, "global_step": 608332, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.941386342048645, "global_step": 608333, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.990090012550354, "global_step": 608334, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0235257148742676, "global_step": 608335, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.1084587574005127, "global_step": 608336, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9532971382141113, "global_step": 608337, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.03647518157959, "global_step": 608338, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9589823484420776, "global_step": 608339, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9787395000457764, "global_step": 608340, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9621798992156982, "global_step": 608341, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.1096887588500977, "global_step": 608342, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9627174139022827, "global_step": 608343, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.012484312057495, "global_step": 608344, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.033571720123291, "global_step": 608345, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.024610996246338, "global_step": 608346, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.037562608718872, "global_step": 608347, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9889957904815674, "global_step": 608348, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.045396327972412, "global_step": 608349, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0706369876861572, "global_step": 608350, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0630173683166504, "global_step": 608351, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0105984210968018, "global_step": 608352, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9983882904052734, "global_step": 608353, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9832035303115845, "global_step": 608354, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.1273858547210693, "global_step": 608355, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0575757026672363, "global_step": 608356, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0465269088745117, "global_step": 608357, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0107364654541016, "global_step": 608358, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.989176630973816, "global_step": 608359, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9678571224212646, "global_step": 608360, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0337469577789307, "global_step": 608361, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0064244270324707, "global_step": 608362, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0603270530700684, "global_step": 608363, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.007554054260254, "global_step": 608364, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0650031566619873, "global_step": 608365, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0393073558807373, "global_step": 608366, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0840609073638916, "global_step": 608367, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.02211594581604, "global_step": 608368, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.017982244491577, "global_step": 608369, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0293781757354736, "global_step": 608370, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0120835304260254, "global_step": 608371, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.983831763267517, "global_step": 608372, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9286649227142334, "global_step": 608373, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0012245178222656, "global_step": 608374, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9767205715179443, "global_step": 608375, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0737006664276123, "global_step": 608376, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.017091989517212, "global_step": 608377, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.092289447784424, "global_step": 608378, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0809662342071533, "global_step": 608379, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0505826473236084, "global_step": 608380, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9797766208648682, "global_step": 608381, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.025160312652588, "global_step": 608382, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9853270053863525, "global_step": 608383, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0623342990875244, "global_step": 608384, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.02001690864563, "global_step": 608385, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.1544437408447266, "global_step": 608386, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0929741859436035, "global_step": 608387, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.036156415939331, "global_step": 608388, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0312976837158203, "global_step": 608389, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.990049123764038, "global_step": 608390, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9659743309020996, "global_step": 608391, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.043328285217285, "global_step": 608392, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.113233804702759, "global_step": 608393, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.022883653640747, "global_step": 608394, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.045638084411621, "global_step": 608395, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9812201261520386, "global_step": 608396, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.965416431427002, "global_step": 608397, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.013209581375122, "global_step": 608398, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0655643939971924, "global_step": 608399, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.061638355255127, "global_step": 608400, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0373334884643555, "global_step": 608401, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0071988105773926, "global_step": 608402, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.099966049194336, "global_step": 608403, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0240843296051025, "global_step": 608404, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9824144840240479, "global_step": 608405, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.050485610961914, "global_step": 608406, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.031604528427124, "global_step": 608407, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9942673444747925, "global_step": 608408, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0630087852478027, "global_step": 608409, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.059391975402832, "global_step": 608410, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0258917808532715, "global_step": 608411, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.981763243675232, "global_step": 608412, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9711170196533203, "global_step": 608413, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9884474277496338, "global_step": 608414, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0309910774230957, "global_step": 608415, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.98997962474823, "global_step": 608416, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9172261953353882, "global_step": 608417, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.061030626296997, "global_step": 608418, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.956605315208435, "global_step": 608419, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9579113721847534, "global_step": 608420, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.085601568222046, "global_step": 608421, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0418527126312256, "global_step": 608422, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.994671106338501, "global_step": 608423, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.991780161857605, "global_step": 608424, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9555836915969849, "global_step": 608425, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.00195574760437, "global_step": 608426, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9580798149108887, "global_step": 608427, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0273733139038086, "global_step": 608428, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9459869861602783, "global_step": 608429, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.003232717514038, "global_step": 608430, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9965463876724243, "global_step": 608431, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9854795932769775, "global_step": 608432, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0143306255340576, "global_step": 608433, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.02912974357605, "global_step": 608434, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.113187551498413, "global_step": 608435, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0497472286224365, "global_step": 608436, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0548412799835205, "global_step": 608437, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9787073135375977, "global_step": 608438, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9752371311187744, "global_step": 608439, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0052056312561035, "global_step": 608440, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.028432607650757, "global_step": 608441, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9932444095611572, "global_step": 608442, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9757874011993408, "global_step": 608443, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.017310619354248, "global_step": 608444, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0795023441314697, "global_step": 608445, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9665753841400146, "global_step": 608446, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.1148929595947266, "global_step": 608447, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9964842796325684, "global_step": 608448, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0651957988739014, "global_step": 608449, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0305535793304443, "global_step": 608450, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.041206121444702, "global_step": 608451, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0010826587677, "global_step": 608452, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9672900438308716, "global_step": 608453, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0010337829589844, "global_step": 608454, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9685238599777222, "global_step": 608455, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.048765182495117, "global_step": 608456, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9259263277053833, "global_step": 608457, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9861828088760376, "global_step": 608458, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.999526023864746, "global_step": 608459, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0238687992095947, "global_step": 608460, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0884175300598145, "global_step": 608461, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9562140703201294, "global_step": 608462, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0055718421936035, "global_step": 608463, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.098656415939331, "global_step": 608464, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.08524489402771, "global_step": 608465, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0019094944000244, "global_step": 608466, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.030832529067993, "global_step": 608467, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9020965099334717, "global_step": 608468, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0425963401794434, "global_step": 608469, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0503835678100586, "global_step": 608470, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.1483559608459473, "global_step": 608471, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0506908893585205, "global_step": 608472, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0622525215148926, "global_step": 608473, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.972684621810913, "global_step": 608474, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0434913635253906, "global_step": 608475, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0339584350585938, "global_step": 608476, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0824034214019775, "global_step": 608477, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.943402886390686, "global_step": 608478, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.061825752258301, "global_step": 608479, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.082514762878418, "global_step": 608480, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.060744285583496, "global_step": 608481, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.051778793334961, "global_step": 608482, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9597374200820923, "global_step": 608483, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0798592567443848, "global_step": 608484, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9596211910247803, "global_step": 608485, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.009589195251465, "global_step": 608486, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9761167764663696, "global_step": 608487, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.932239294052124, "global_step": 608488, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9956958293914795, "global_step": 608489, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9995900392532349, "global_step": 608490, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9167520999908447, "global_step": 608491, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0503273010253906, "global_step": 608492, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.972756266593933, "global_step": 608493, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.998603105545044, "global_step": 608494, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0217397212982178, "global_step": 608495, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9748128652572632, "global_step": 608496, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0835187435150146, "global_step": 608497, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.061293601989746, "global_step": 608498, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9626625776290894, "global_step": 608499, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0909805297851562, "global_step": 608500, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.996565818786621, "global_step": 608501, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9650769233703613, "global_step": 608502, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.051250696182251, "global_step": 608503, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.002079963684082, "global_step": 608504, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9670346975326538, "global_step": 608505, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0173792839050293, "global_step": 608506, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9640697240829468, "global_step": 608507, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0728745460510254, "global_step": 608508, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.998354196548462, "global_step": 608509, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.932310700416565, "global_step": 608510, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0452303886413574, "global_step": 608511, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.065189838409424, "global_step": 608512, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9841208457946777, "global_step": 608513, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0264153480529785, "global_step": 608514, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.988642930984497, "global_step": 608515, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9202958345413208, "global_step": 608516, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9837919473648071, "global_step": 608517, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9516173601150513, "global_step": 608518, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0744948387145996, "global_step": 608519, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9624673128128052, "global_step": 608520, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.97602117061615, "global_step": 608521, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9905325174331665, "global_step": 608522, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0528125762939453, "global_step": 608523, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0035762786865234, "global_step": 608524, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9584696292877197, "global_step": 608525, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0123207569122314, "global_step": 608526, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0206377506256104, "global_step": 608527, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9598796367645264, "global_step": 608528, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.018162250518799, "global_step": 608529, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.016930341720581, "global_step": 608530, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9992371797561646, "global_step": 608531, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0240535736083984, "global_step": 608532, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.97028386592865, "global_step": 608533, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9753355979919434, "global_step": 608534, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.034440517425537, "global_step": 608535, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9254246950149536, "global_step": 608536, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0851943492889404, "global_step": 608537, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9951632022857666, "global_step": 608538, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.058243751525879, "global_step": 608539, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0418319702148438, "global_step": 608540, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9391109943389893, "global_step": 608541, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0202672481536865, "global_step": 608542, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.994887351989746, "global_step": 608543, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9994726181030273, "global_step": 608544, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9456549882888794, "global_step": 608545, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0361149311065674, "global_step": 608546, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.042642831802368, "global_step": 608547, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.988398551940918, "global_step": 608548, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0101938247680664, "global_step": 608549, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.023428440093994, "global_step": 608550, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9856871366500854, "global_step": 608551, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.068594455718994, "global_step": 608552, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9818637371063232, "global_step": 608553, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.987483024597168, "global_step": 608554, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0173537731170654, "global_step": 608555, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.990146517753601, "global_step": 608556, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0262765884399414, "global_step": 608557, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0237181186676025, "global_step": 608558, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.023122549057007, "global_step": 608559, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.039515733718872, "global_step": 608560, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.091912031173706, "global_step": 608561, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0090465545654297, "global_step": 608562, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9924678802490234, "global_step": 608563, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0411548614501953, "global_step": 608564, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.976825475692749, "global_step": 608565, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0166711807250977, "global_step": 608566, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0545811653137207, "global_step": 608567, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.000075101852417, "global_step": 608568, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.998616099357605, "global_step": 608569, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.99891197681427, "global_step": 608570, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.003225803375244, "global_step": 608571, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0518758296966553, "global_step": 608572, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9843556880950928, "global_step": 608573, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.021366834640503, "global_step": 608574, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.053079843521118, "global_step": 608575, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.075284004211426, "global_step": 608576, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9731947183609009, "global_step": 608577, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0406830310821533, "global_step": 608578, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0639407634735107, "global_step": 608579, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9825841188430786, "global_step": 608580, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0225014686584473, "global_step": 608581, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0493216514587402, "global_step": 608582, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.096752643585205, "global_step": 608583, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.026092290878296, "global_step": 608584, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0607669353485107, "global_step": 608585, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9777836799621582, "global_step": 608586, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.057140588760376, "global_step": 608587, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9856775999069214, "global_step": 608588, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.030553102493286, "global_step": 608589, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0815768241882324, "global_step": 608590, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9687515497207642, "global_step": 608591, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.990925669670105, "global_step": 608592, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.959479808807373, "global_step": 608593, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.003848075866699, "global_step": 608594, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9801347255706787, "global_step": 608595, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.086848497390747, "global_step": 608596, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.02133846282959, "global_step": 608597, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.023951768875122, "global_step": 608598, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0217254161834717, "global_step": 608599, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.069305419921875, "global_step": 608600, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.1244003772735596, "global_step": 608601, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9880977869033813, "global_step": 608602, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9212725162506104, "global_step": 608603, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.991024136543274, "global_step": 608604, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9852010011672974, "global_step": 608605, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0726475715637207, "global_step": 608606, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0033392906188965, "global_step": 608607, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.964887022972107, "global_step": 608608, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0241763591766357, "global_step": 608609, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.926039457321167, "global_step": 608610, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9910621643066406, "global_step": 608611, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.995120644569397, "global_step": 608612, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0498909950256348, "global_step": 608613, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9727964401245117, "global_step": 608614, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0484964847564697, "global_step": 608615, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9043952226638794, "global_step": 608616, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.03202223777771, "global_step": 608617, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0373642444610596, "global_step": 608618, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0640146732330322, "global_step": 608619, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.046269416809082, "global_step": 608620, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0389041900634766, "global_step": 608621, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0577542781829834, "global_step": 608622, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.997213363647461, "global_step": 608623, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.035191774368286, "global_step": 608624, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.036041021347046, "global_step": 608625, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9784269332885742, "global_step": 608626, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0060367584228516, "global_step": 608627, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9181129932403564, "global_step": 608628, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9835983514785767, "global_step": 608629, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0516598224639893, "global_step": 608630, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9962598085403442, "global_step": 608631, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.055691719055176, "global_step": 608632, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0318312644958496, "global_step": 608633, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9820067882537842, "global_step": 608634, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0806562900543213, "global_step": 608635, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0365946292877197, "global_step": 608636, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.075575113296509, "global_step": 608637, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9694520235061646, "global_step": 608638, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0086121559143066, "global_step": 608639, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0094776153564453, "global_step": 608640, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9946329593658447, "global_step": 608641, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.011162519454956, "global_step": 608642, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9981516599655151, "global_step": 608643, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9467118978500366, "global_step": 608644, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.1191277503967285, "global_step": 608645, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.071549654006958, "global_step": 608646, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9687855243682861, "global_step": 608647, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9817966222763062, "global_step": 608648, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.027977466583252, "global_step": 608649, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0240883827209473, "global_step": 608650, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.958564281463623, "global_step": 608651, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0563206672668457, "global_step": 608652, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9073686599731445, "global_step": 608653, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.028625965118408, "global_step": 608654, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0238656997680664, "global_step": 608655, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0161309242248535, "global_step": 608656, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.092667818069458, "global_step": 608657, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0403525829315186, "global_step": 608658, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0198822021484375, "global_step": 608659, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.0269229412078857, "global_step": 608660, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.047222375869751, "global_step": 608661, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9763014316558838, "global_step": 608662, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.036681890487671, "global_step": 608663, "epoch": 977, "lr": 5e-05}
{"train_loss": 2.008183717727661, "global_step": 608664, "epoch": 977, "lr": 5e-05}
{"train_loss": 1.9775192737579346, "global_step": 608665, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.013010025024414, "global_step": 608666, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9686061143875122, "global_step": 608667, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9915629625320435, "global_step": 608668, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9859511852264404, "global_step": 608669, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9397151470184326, "global_step": 608670, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.001150369644165, "global_step": 608671, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9560803174972534, "global_step": 608672, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.944096565246582, "global_step": 608673, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.007739782333374, "global_step": 608674, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.918468713760376, "global_step": 608675, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.953633189201355, "global_step": 608676, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.042405843734741, "global_step": 608677, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9928393363952637, "global_step": 608678, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0298190116882324, "global_step": 608679, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0368828773498535, "global_step": 608680, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.972344994544983, "global_step": 608681, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0066473484039307, "global_step": 608682, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9124327898025513, "global_step": 608683, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9269517660140991, "global_step": 608684, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.953199863433838, "global_step": 608685, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0120606422424316, "global_step": 608686, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0649001598358154, "global_step": 608687, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.108070135116577, "global_step": 608688, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.942644476890564, "global_step": 608689, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9964194297790527, "global_step": 608690, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.967742681503296, "global_step": 608691, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.026981830596924, "global_step": 608692, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9670493602752686, "global_step": 608693, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9396135807037354, "global_step": 608694, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.001269578933716, "global_step": 608695, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.000164747238159, "global_step": 608696, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0130615234375, "global_step": 608697, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9300813674926758, "global_step": 608698, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.023066759109497, "global_step": 608699, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9847536087036133, "global_step": 608700, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0386648178100586, "global_step": 608701, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.992794156074524, "global_step": 608702, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9929890632629395, "global_step": 608703, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0828471183776855, "global_step": 608704, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0569820404052734, "global_step": 608705, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.8911411762237549, "global_step": 608706, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.002281904220581, "global_step": 608707, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9833439588546753, "global_step": 608708, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.085249662399292, "global_step": 608709, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.982500433921814, "global_step": 608710, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0296101570129395, "global_step": 608711, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0686302185058594, "global_step": 608712, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.981113314628601, "global_step": 608713, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.087186813354492, "global_step": 608714, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.038123846054077, "global_step": 608715, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9548225402832031, "global_step": 608716, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.964127779006958, "global_step": 608717, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9589084386825562, "global_step": 608718, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0040199756622314, "global_step": 608719, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9578256607055664, "global_step": 608720, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9780808687210083, "global_step": 608721, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9102935791015625, "global_step": 608722, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9323370456695557, "global_step": 608723, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9492876529693604, "global_step": 608724, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9989467859268188, "global_step": 608725, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9333231449127197, "global_step": 608726, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9801815748214722, "global_step": 608727, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9980106353759766, "global_step": 608728, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0860185623168945, "global_step": 608729, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.979850172996521, "global_step": 608730, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0161399841308594, "global_step": 608731, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.042574167251587, "global_step": 608732, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0282654762268066, "global_step": 608733, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0504238605499268, "global_step": 608734, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.035057783126831, "global_step": 608735, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9872002601623535, "global_step": 608736, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9639616012573242, "global_step": 608737, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.041931629180908, "global_step": 608738, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9632256031036377, "global_step": 608739, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9094067811965942, "global_step": 608740, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9413458108901978, "global_step": 608741, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.017282009124756, "global_step": 608742, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9980864524841309, "global_step": 608743, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9637348651885986, "global_step": 608744, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9563612937927246, "global_step": 608745, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.978285789489746, "global_step": 608746, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.024575710296631, "global_step": 608747, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0099644660949707, "global_step": 608748, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9765560626983643, "global_step": 608749, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9816386699676514, "global_step": 608750, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.961712121963501, "global_step": 608751, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9971084594726562, "global_step": 608752, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.05856990814209, "global_step": 608753, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.008864164352417, "global_step": 608754, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0422773361206055, "global_step": 608755, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9425112009048462, "global_step": 608756, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0562729835510254, "global_step": 608757, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.957693099975586, "global_step": 608758, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9568109512329102, "global_step": 608759, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.035061836242676, "global_step": 608760, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9891549348831177, "global_step": 608761, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9986482858657837, "global_step": 608762, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9701868295669556, "global_step": 608763, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.936051607131958, "global_step": 608764, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9829366207122803, "global_step": 608765, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0111234188079834, "global_step": 608766, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9264981746673584, "global_step": 608767, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.025942087173462, "global_step": 608768, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9025729894638062, "global_step": 608769, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.950788974761963, "global_step": 608770, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.062034845352173, "global_step": 608771, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0177392959594727, "global_step": 608772, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9530210494995117, "global_step": 608773, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9724700450897217, "global_step": 608774, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0588791370391846, "global_step": 608775, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0800082683563232, "global_step": 608776, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.972934365272522, "global_step": 608777, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9723796844482422, "global_step": 608778, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.046987533569336, "global_step": 608779, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0162930488586426, "global_step": 608780, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.001455783843994, "global_step": 608781, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.093991994857788, "global_step": 608782, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.975205421447754, "global_step": 608783, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0972607135772705, "global_step": 608784, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0409202575683594, "global_step": 608785, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9238916635513306, "global_step": 608786, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0095012187957764, "global_step": 608787, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0020370483398438, "global_step": 608788, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0222225189208984, "global_step": 608789, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9721907377243042, "global_step": 608790, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9224363565444946, "global_step": 608791, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9986248016357422, "global_step": 608792, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0277674198150635, "global_step": 608793, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9971017837524414, "global_step": 608794, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0875186920166016, "global_step": 608795, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0558924674987793, "global_step": 608796, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9465545415878296, "global_step": 608797, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.045172691345215, "global_step": 608798, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0352678298950195, "global_step": 608799, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.045083999633789, "global_step": 608800, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.042353391647339, "global_step": 608801, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9534602165222168, "global_step": 608802, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0479514598846436, "global_step": 608803, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0458407402038574, "global_step": 608804, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0219643115997314, "global_step": 608805, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0516772270202637, "global_step": 608806, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.996912956237793, "global_step": 608807, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.916878342628479, "global_step": 608808, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0339207649230957, "global_step": 608809, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0208873748779297, "global_step": 608810, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0328269004821777, "global_step": 608811, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0664851665496826, "global_step": 608812, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.010852098464966, "global_step": 608813, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.046854019165039, "global_step": 608814, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9842151403427124, "global_step": 608815, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0731019973754883, "global_step": 608816, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.971244215965271, "global_step": 608817, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.951829433441162, "global_step": 608818, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.049483299255371, "global_step": 608819, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.017301321029663, "global_step": 608820, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.994017243385315, "global_step": 608821, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9501972198486328, "global_step": 608822, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9723271131515503, "global_step": 608823, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0065460205078125, "global_step": 608824, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0026512145996094, "global_step": 608825, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.033764600753784, "global_step": 608826, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0237905979156494, "global_step": 608827, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.1263601779937744, "global_step": 608828, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0072226524353027, "global_step": 608829, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.046572685241699, "global_step": 608830, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9639930725097656, "global_step": 608831, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9667068719863892, "global_step": 608832, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0298898220062256, "global_step": 608833, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.069101333618164, "global_step": 608834, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0135934352874756, "global_step": 608835, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9871129989624023, "global_step": 608836, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9927583932876587, "global_step": 608837, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9526420831680298, "global_step": 608838, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.018791675567627, "global_step": 608839, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.065680980682373, "global_step": 608840, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0245301723480225, "global_step": 608841, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9365055561065674, "global_step": 608842, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0634615421295166, "global_step": 608843, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9632617235183716, "global_step": 608844, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9810987710952759, "global_step": 608845, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.004887104034424, "global_step": 608846, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0125699043273926, "global_step": 608847, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.98234224319458, "global_step": 608848, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.970623254776001, "global_step": 608849, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0284476280212402, "global_step": 608850, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9781384468078613, "global_step": 608851, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9988420009613037, "global_step": 608852, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9507850408554077, "global_step": 608853, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9470189809799194, "global_step": 608854, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.041428804397583, "global_step": 608855, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9722265005111694, "global_step": 608856, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.1363770961761475, "global_step": 608857, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9819608926773071, "global_step": 608858, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9517154693603516, "global_step": 608859, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9700336456298828, "global_step": 608860, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0073981285095215, "global_step": 608861, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0095887184143066, "global_step": 608862, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9794750213623047, "global_step": 608863, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0449447631835938, "global_step": 608864, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.961513638496399, "global_step": 608865, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.081040859222412, "global_step": 608866, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9823211431503296, "global_step": 608867, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0320210456848145, "global_step": 608868, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.002657175064087, "global_step": 608869, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0228865146636963, "global_step": 608870, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.008840799331665, "global_step": 608871, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9986505508422852, "global_step": 608872, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0738043785095215, "global_step": 608873, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.013925790786743, "global_step": 608874, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0103626251220703, "global_step": 608875, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9758532047271729, "global_step": 608876, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9397227764129639, "global_step": 608877, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0097341537475586, "global_step": 608878, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9644763469696045, "global_step": 608879, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9599913358688354, "global_step": 608880, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9819824695587158, "global_step": 608881, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9971731901168823, "global_step": 608882, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.043724775314331, "global_step": 608883, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0484635829925537, "global_step": 608884, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9377467632293701, "global_step": 608885, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.010791301727295, "global_step": 608886, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.974315881729126, "global_step": 608887, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9779446125030518, "global_step": 608888, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.017897844314575, "global_step": 608889, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0111618041992188, "global_step": 608890, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0203118324279785, "global_step": 608891, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0704431533813477, "global_step": 608892, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.076219081878662, "global_step": 608893, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.065836191177368, "global_step": 608894, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.087947130203247, "global_step": 608895, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.013935089111328, "global_step": 608896, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0941221714019775, "global_step": 608897, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9958109855651855, "global_step": 608898, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9632444381713867, "global_step": 608899, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0348246097564697, "global_step": 608900, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0141258239746094, "global_step": 608901, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9467500448226929, "global_step": 608902, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.06942081451416, "global_step": 608903, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.8979265689849854, "global_step": 608904, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9965842962265015, "global_step": 608905, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0513458251953125, "global_step": 608906, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9715068340301514, "global_step": 608907, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.024502992630005, "global_step": 608908, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0067012310028076, "global_step": 608909, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.013617753982544, "global_step": 608910, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.034832239151001, "global_step": 608911, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9914406538009644, "global_step": 608912, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.018372058868408, "global_step": 608913, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0407466888427734, "global_step": 608914, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.006821393966675, "global_step": 608915, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.95280122756958, "global_step": 608916, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9653534889221191, "global_step": 608917, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9798930883407593, "global_step": 608918, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0619845390319824, "global_step": 608919, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9920825958251953, "global_step": 608920, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0562305450439453, "global_step": 608921, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9644042253494263, "global_step": 608922, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.049351215362549, "global_step": 608923, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.052363157272339, "global_step": 608924, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9646726846694946, "global_step": 608925, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0685272216796875, "global_step": 608926, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0385050773620605, "global_step": 608927, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9721356630325317, "global_step": 608928, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0535032749176025, "global_step": 608929, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.03782057762146, "global_step": 608930, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.985418677330017, "global_step": 608931, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9324356317520142, "global_step": 608932, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9215227365493774, "global_step": 608933, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.066579818725586, "global_step": 608934, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9477992057800293, "global_step": 608935, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9427803754806519, "global_step": 608936, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0254464149475098, "global_step": 608937, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9114917516708374, "global_step": 608938, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9981458187103271, "global_step": 608939, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9868800640106201, "global_step": 608940, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9544252157211304, "global_step": 608941, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.978929042816162, "global_step": 608942, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9973914623260498, "global_step": 608943, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9779213666915894, "global_step": 608944, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.078648805618286, "global_step": 608945, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0629453659057617, "global_step": 608946, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.011352777481079, "global_step": 608947, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9734582901000977, "global_step": 608948, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.968442440032959, "global_step": 608949, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.045633554458618, "global_step": 608950, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0280256271362305, "global_step": 608951, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.018717050552368, "global_step": 608952, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0353286266326904, "global_step": 608953, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9853005409240723, "global_step": 608954, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.017132043838501, "global_step": 608955, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9648807048797607, "global_step": 608956, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.998237133026123, "global_step": 608957, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.106985330581665, "global_step": 608958, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0533416271209717, "global_step": 608959, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9590245485305786, "global_step": 608960, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0362091064453125, "global_step": 608961, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.012406349182129, "global_step": 608962, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.099724531173706, "global_step": 608963, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9893819093704224, "global_step": 608964, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.015559196472168, "global_step": 608965, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0175652503967285, "global_step": 608966, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9868894815444946, "global_step": 608967, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9762752056121826, "global_step": 608968, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0866034030914307, "global_step": 608969, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.107581615447998, "global_step": 608970, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.116406202316284, "global_step": 608971, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9246091842651367, "global_step": 608972, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0266036987304688, "global_step": 608973, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0692286491394043, "global_step": 608974, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.963524341583252, "global_step": 608975, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0041861534118652, "global_step": 608976, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0394325256347656, "global_step": 608977, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.00628924369812, "global_step": 608978, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.020653247833252, "global_step": 608979, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9827460050582886, "global_step": 608980, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0063934326171875, "global_step": 608981, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9963603019714355, "global_step": 608982, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9969562292099, "global_step": 608983, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9675767421722412, "global_step": 608984, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0176079273223877, "global_step": 608985, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0546858310699463, "global_step": 608986, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9576504230499268, "global_step": 608987, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9876134395599365, "global_step": 608988, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.065020799636841, "global_step": 608989, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9104511737823486, "global_step": 608990, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.015127658843994, "global_step": 608991, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0180490016937256, "global_step": 608992, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.045238733291626, "global_step": 608993, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0304317474365234, "global_step": 608994, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9651192426681519, "global_step": 608995, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9731560945510864, "global_step": 608996, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0708441734313965, "global_step": 608997, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9800713062286377, "global_step": 608998, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9863574504852295, "global_step": 608999, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.02598237991333, "global_step": 609000, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0769505500793457, "global_step": 609001, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9983036518096924, "global_step": 609002, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.978178858757019, "global_step": 609003, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9692422151565552, "global_step": 609004, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.1553733348846436, "global_step": 609005, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9644941091537476, "global_step": 609006, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.928892731666565, "global_step": 609007, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9516674280166626, "global_step": 609008, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9815871715545654, "global_step": 609009, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0125746726989746, "global_step": 609010, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.007582426071167, "global_step": 609011, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0060713291168213, "global_step": 609012, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.056023597717285, "global_step": 609013, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.041177988052368, "global_step": 609014, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.03075909614563, "global_step": 609015, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0175890922546387, "global_step": 609016, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.960863471031189, "global_step": 609017, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0357134342193604, "global_step": 609018, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9629151821136475, "global_step": 609019, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.057546854019165, "global_step": 609020, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.039346694946289, "global_step": 609021, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0369930267333984, "global_step": 609022, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0090761184692383, "global_step": 609023, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.062992811203003, "global_step": 609024, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9664928913116455, "global_step": 609025, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9792492389678955, "global_step": 609026, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.078382968902588, "global_step": 609027, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.983710765838623, "global_step": 609028, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0334343910217285, "global_step": 609029, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0417680740356445, "global_step": 609030, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0002853870391846, "global_step": 609031, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9607113599777222, "global_step": 609032, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0495102405548096, "global_step": 609033, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.986951231956482, "global_step": 609034, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9766557216644287, "global_step": 609035, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.039552927017212, "global_step": 609036, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.991585373878479, "global_step": 609037, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9739456176757812, "global_step": 609038, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.027182102203369, "global_step": 609039, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.010643482208252, "global_step": 609040, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9659302234649658, "global_step": 609041, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9959311485290527, "global_step": 609042, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0477499961853027, "global_step": 609043, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0619418621063232, "global_step": 609044, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9840209484100342, "global_step": 609045, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.920910120010376, "global_step": 609046, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.874944806098938, "global_step": 609047, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.01904034614563, "global_step": 609048, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0655157566070557, "global_step": 609049, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.968024492263794, "global_step": 609050, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0026466846466064, "global_step": 609051, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.035970449447632, "global_step": 609052, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0442845821380615, "global_step": 609053, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.995564341545105, "global_step": 609054, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9601061344146729, "global_step": 609055, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0582501888275146, "global_step": 609056, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0123496055603027, "global_step": 609057, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.071413040161133, "global_step": 609058, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.072350025177002, "global_step": 609059, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0551791191101074, "global_step": 609060, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9577960968017578, "global_step": 609061, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0681421756744385, "global_step": 609062, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0541815757751465, "global_step": 609063, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9806594848632812, "global_step": 609064, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.048152208328247, "global_step": 609065, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.028181791305542, "global_step": 609066, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9569289684295654, "global_step": 609067, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0237932205200195, "global_step": 609068, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.026455879211426, "global_step": 609069, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.023463249206543, "global_step": 609070, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9823391437530518, "global_step": 609071, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0121243000030518, "global_step": 609072, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9273970127105713, "global_step": 609073, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.02107310295105, "global_step": 609074, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.038917303085327, "global_step": 609075, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0060174465179443, "global_step": 609076, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.000227928161621, "global_step": 609077, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.085031270980835, "global_step": 609078, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0197834968566895, "global_step": 609079, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.003880023956299, "global_step": 609080, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9968855381011963, "global_step": 609081, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0371155738830566, "global_step": 609082, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.8852330446243286, "global_step": 609083, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9413604736328125, "global_step": 609084, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.101954221725464, "global_step": 609085, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.948676347732544, "global_step": 609086, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.010261297225952, "global_step": 609087, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9810317754745483, "global_step": 609088, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.007289171218872, "global_step": 609089, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.019184112548828, "global_step": 609090, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0197958946228027, "global_step": 609091, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.980959415435791, "global_step": 609092, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0067176818847656, "global_step": 609093, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.029092788696289, "global_step": 609094, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9897167682647705, "global_step": 609095, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9633510112762451, "global_step": 609096, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0089569091796875, "global_step": 609097, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.089176654815674, "global_step": 609098, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0090978145599365, "global_step": 609099, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.017879009246826, "global_step": 609100, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9968031644821167, "global_step": 609101, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9388254880905151, "global_step": 609102, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.959921956062317, "global_step": 609103, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.022268295288086, "global_step": 609104, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0926997661590576, "global_step": 609105, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9829689264297485, "global_step": 609106, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0088469982147217, "global_step": 609107, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9156345129013062, "global_step": 609108, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0561466217041016, "global_step": 609109, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9658098220825195, "global_step": 609110, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0492353439331055, "global_step": 609111, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0692529678344727, "global_step": 609112, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.969578742980957, "global_step": 609113, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.064070224761963, "global_step": 609114, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0774078369140625, "global_step": 609115, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.967901587486267, "global_step": 609116, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.05789852142334, "global_step": 609117, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.029101848602295, "global_step": 609118, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.036468744277954, "global_step": 609119, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0710740089416504, "global_step": 609120, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.046081066131592, "global_step": 609121, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.977874755859375, "global_step": 609122, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.096876859664917, "global_step": 609123, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0889766216278076, "global_step": 609124, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9881058931350708, "global_step": 609125, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0214059352874756, "global_step": 609126, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0114150047302246, "global_step": 609127, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.010453462600708, "global_step": 609128, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.950666904449463, "global_step": 609129, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0665318965911865, "global_step": 609130, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.043872594833374, "global_step": 609131, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9618470668792725, "global_step": 609132, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9374226331710815, "global_step": 609133, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0129358768463135, "global_step": 609134, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0480329990386963, "global_step": 609135, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.964819312095642, "global_step": 609136, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.965586543083191, "global_step": 609137, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0401453971862793, "global_step": 609138, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9461809396743774, "global_step": 609139, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9461590051651, "global_step": 609140, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.997593879699707, "global_step": 609141, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.079662561416626, "global_step": 609142, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0174124240875244, "global_step": 609143, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.003425359725952, "global_step": 609144, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.943010926246643, "global_step": 609145, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.005960702896118, "global_step": 609146, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0133137702941895, "global_step": 609147, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0183563232421875, "global_step": 609148, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0336270332336426, "global_step": 609149, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.045355796813965, "global_step": 609150, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.050546169281006, "global_step": 609151, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9343198537826538, "global_step": 609152, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.096343517303467, "global_step": 609153, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.8840994834899902, "global_step": 609154, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.063858985900879, "global_step": 609155, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0864064693450928, "global_step": 609156, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.987525224685669, "global_step": 609157, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9472661018371582, "global_step": 609158, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9122059345245361, "global_step": 609159, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0237226486206055, "global_step": 609160, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9645919799804688, "global_step": 609161, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0451323986053467, "global_step": 609162, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9900654554367065, "global_step": 609163, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0527572631835938, "global_step": 609164, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0630903244018555, "global_step": 609165, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0704283714294434, "global_step": 609166, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9786763191223145, "global_step": 609167, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0298619270324707, "global_step": 609168, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0421035289764404, "global_step": 609169, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.95961594581604, "global_step": 609170, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9792299270629883, "global_step": 609171, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9625096321105957, "global_step": 609172, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.976703405380249, "global_step": 609173, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0026118755340576, "global_step": 609174, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.01779842376709, "global_step": 609175, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.978347897529602, "global_step": 609176, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0443549156188965, "global_step": 609177, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.010969638824463, "global_step": 609178, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.981633186340332, "global_step": 609179, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0058791637420654, "global_step": 609180, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9716652631759644, "global_step": 609181, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.972309947013855, "global_step": 609182, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.104611873626709, "global_step": 609183, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9767869710922241, "global_step": 609184, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.99684739112854, "global_step": 609185, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9479900598526, "global_step": 609186, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0106701850891113, "global_step": 609187, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0414109230041504, "global_step": 609188, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9899569749832153, "global_step": 609189, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0725841522216797, "global_step": 609190, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0221927165985107, "global_step": 609191, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.03912091255188, "global_step": 609192, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.933092474937439, "global_step": 609193, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.997838020324707, "global_step": 609194, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9662775993347168, "global_step": 609195, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9990193843841553, "global_step": 609196, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.017474889755249, "global_step": 609197, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0846540927886963, "global_step": 609198, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0134341716766357, "global_step": 609199, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0697383880615234, "global_step": 609200, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0558695793151855, "global_step": 609201, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.950758934020996, "global_step": 609202, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9947211742401123, "global_step": 609203, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0088934898376465, "global_step": 609204, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9374711513519287, "global_step": 609205, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0190460681915283, "global_step": 609206, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9894932508468628, "global_step": 609207, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9680893421173096, "global_step": 609208, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9409860372543335, "global_step": 609209, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9597253799438477, "global_step": 609210, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.994397521018982, "global_step": 609211, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.036536931991577, "global_step": 609212, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0577871799468994, "global_step": 609213, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0259106159210205, "global_step": 609214, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.045323133468628, "global_step": 609215, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.030647039413452, "global_step": 609216, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9549331665039062, "global_step": 609217, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9966596364974976, "global_step": 609218, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.054391384124756, "global_step": 609219, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0273358821868896, "global_step": 609220, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0707409381866455, "global_step": 609221, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9893118143081665, "global_step": 609222, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.035296678543091, "global_step": 609223, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0859603881835938, "global_step": 609224, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.026538372039795, "global_step": 609225, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9922406673431396, "global_step": 609226, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.023797035217285, "global_step": 609227, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.031554698944092, "global_step": 609228, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9345324039459229, "global_step": 609229, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9928475618362427, "global_step": 609230, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0493946075439453, "global_step": 609231, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9725996255874634, "global_step": 609232, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9638261795043945, "global_step": 609233, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0331923961639404, "global_step": 609234, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.1080374717712402, "global_step": 609235, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9583702087402344, "global_step": 609236, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0617835521698, "global_step": 609237, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.014427900314331, "global_step": 609238, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0471200942993164, "global_step": 609239, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.059607982635498, "global_step": 609240, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.136575222015381, "global_step": 609241, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0866613388061523, "global_step": 609242, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9770268201828003, "global_step": 609243, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.063418388366699, "global_step": 609244, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0324060916900635, "global_step": 609245, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9679707288742065, "global_step": 609246, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.979032278060913, "global_step": 609247, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.035994291305542, "global_step": 609248, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9769030809402466, "global_step": 609249, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9478439092636108, "global_step": 609250, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9800515174865723, "global_step": 609251, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0711259841918945, "global_step": 609252, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0238003730773926, "global_step": 609253, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9550622701644897, "global_step": 609254, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0868947505950928, "global_step": 609255, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0699307918548584, "global_step": 609256, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0119078159332275, "global_step": 609257, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.021810293197632, "global_step": 609258, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0082592964172363, "global_step": 609259, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9456483125686646, "global_step": 609260, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.002420663833618, "global_step": 609261, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.034684896469116, "global_step": 609262, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.068577289581299, "global_step": 609263, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9858860969543457, "global_step": 609264, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9630569219589233, "global_step": 609265, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9944024085998535, "global_step": 609266, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0986616611480713, "global_step": 609267, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0565831661224365, "global_step": 609268, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0516762733459473, "global_step": 609269, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9786221981048584, "global_step": 609270, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9976006746292114, "global_step": 609271, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0066893100738525, "global_step": 609272, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0030715465545654, "global_step": 609273, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.004976987838745, "global_step": 609274, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0335147380828857, "global_step": 609275, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0089316368103027, "global_step": 609276, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.049245595932007, "global_step": 609277, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.041776180267334, "global_step": 609278, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0566680431365967, "global_step": 609279, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0115389823913574, "global_step": 609280, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.052666425704956, "global_step": 609281, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.049208402633667, "global_step": 609282, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9943172931671143, "global_step": 609283, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0656802654266357, "global_step": 609284, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9282300472259521, "global_step": 609285, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9627931118011475, "global_step": 609286, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9400224685668945, "global_step": 609287, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9875032901763916, "global_step": 609288, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0141546726226807, "global_step": 609289, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.012803554534912, "global_step": 609290, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.1135149002075195, "global_step": 609291, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0042548179626465, "global_step": 609292, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9325706958770752, "global_step": 609293, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.063626289367676, "global_step": 609294, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.049041271209717, "global_step": 609295, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9751428365707397, "global_step": 609296, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.096975088119507, "global_step": 609297, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.084934711456299, "global_step": 609298, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0323991775512695, "global_step": 609299, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0039944648742676, "global_step": 609300, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9760645627975464, "global_step": 609301, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9308720827102661, "global_step": 609302, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9902387857437134, "global_step": 609303, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0032355785369873, "global_step": 609304, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.914986491203308, "global_step": 609305, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.047173023223877, "global_step": 609306, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0182220935821533, "global_step": 609307, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.014094829559326, "global_step": 609308, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.080287456512451, "global_step": 609309, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.912351131439209, "global_step": 609310, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9603296518325806, "global_step": 609311, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.030503749847412, "global_step": 609312, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0051212310791016, "global_step": 609313, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.974730372428894, "global_step": 609314, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.1098554134368896, "global_step": 609315, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9962505102157593, "global_step": 609316, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.064087152481079, "global_step": 609317, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0394480228424072, "global_step": 609318, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9914404153823853, "global_step": 609319, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0415377616882324, "global_step": 609320, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0112879276275635, "global_step": 609321, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.031249523162842, "global_step": 609322, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0176258087158203, "global_step": 609323, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.1124417781829834, "global_step": 609324, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9429242610931396, "global_step": 609325, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.932766079902649, "global_step": 609326, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9953161478042603, "global_step": 609327, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9904091358184814, "global_step": 609328, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0833401679992676, "global_step": 609329, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9797214269638062, "global_step": 609330, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0298867225646973, "global_step": 609331, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0813143253326416, "global_step": 609332, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.8862159252166748, "global_step": 609333, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.041919708251953, "global_step": 609334, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9612226486206055, "global_step": 609335, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9735450744628906, "global_step": 609336, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9771960973739624, "global_step": 609337, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.947325348854065, "global_step": 609338, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0470378398895264, "global_step": 609339, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9611870050430298, "global_step": 609340, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9906976222991943, "global_step": 609341, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.042131185531616, "global_step": 609342, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9296438694000244, "global_step": 609343, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0107581615448, "global_step": 609344, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9977930784225464, "global_step": 609345, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.001809597015381, "global_step": 609346, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9800114631652832, "global_step": 609347, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9685146808624268, "global_step": 609348, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.07283353805542, "global_step": 609349, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9874764680862427, "global_step": 609350, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.043185234069824, "global_step": 609351, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.068509340286255, "global_step": 609352, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9979677200317383, "global_step": 609353, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9980568885803223, "global_step": 609354, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.017763376235962, "global_step": 609355, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0139756202697754, "global_step": 609356, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9933592081069946, "global_step": 609357, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.068697214126587, "global_step": 609358, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0316073894500732, "global_step": 609359, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9798424243927002, "global_step": 609360, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9877943992614746, "global_step": 609361, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.047142744064331, "global_step": 609362, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0055718421936035, "global_step": 609363, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.121770143508911, "global_step": 609364, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.013620615005493, "global_step": 609365, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9548594951629639, "global_step": 609366, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0063529014587402, "global_step": 609367, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.001725435256958, "global_step": 609368, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0298335552215576, "global_step": 609369, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.99150812625885, "global_step": 609370, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.031768321990967, "global_step": 609371, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0365190505981445, "global_step": 609372, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9760689735412598, "global_step": 609373, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9551610946655273, "global_step": 609374, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9342461824417114, "global_step": 609375, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.063474655151367, "global_step": 609376, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.1014668941497803, "global_step": 609377, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0246071815490723, "global_step": 609378, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.975556492805481, "global_step": 609379, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9281556606292725, "global_step": 609380, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0912091732025146, "global_step": 609381, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9366973638534546, "global_step": 609382, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0003905296325684, "global_step": 609383, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.029998540878296, "global_step": 609384, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9471462965011597, "global_step": 609385, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9828503131866455, "global_step": 609386, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0193982124328613, "global_step": 609387, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0713438987731934, "global_step": 609388, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.024623155593872, "global_step": 609389, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0959322452545166, "global_step": 609390, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0438008308410645, "global_step": 609391, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9492384195327759, "global_step": 609392, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.002504825592041, "global_step": 609393, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9505661725997925, "global_step": 609394, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9479451179504395, "global_step": 609395, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9540973901748657, "global_step": 609396, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0928895473480225, "global_step": 609397, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0138978958129883, "global_step": 609398, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9703212976455688, "global_step": 609399, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9819307327270508, "global_step": 609400, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.039249897003174, "global_step": 609401, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9706040620803833, "global_step": 609402, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.01969051361084, "global_step": 609403, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0140750408172607, "global_step": 609404, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.868749976158142, "global_step": 609405, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9896621704101562, "global_step": 609406, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9399383068084717, "global_step": 609407, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.050210475921631, "global_step": 609408, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9651890993118286, "global_step": 609409, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.013683557510376, "global_step": 609410, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9989993572235107, "global_step": 609411, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.997476577758789, "global_step": 609412, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0184152126312256, "global_step": 609413, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9936599731445312, "global_step": 609414, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.013833999633789, "global_step": 609415, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.052208185195923, "global_step": 609416, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.060781955718994, "global_step": 609417, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9873799085617065, "global_step": 609418, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.057098388671875, "global_step": 609419, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.022125720977783, "global_step": 609420, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.035278558731079, "global_step": 609421, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.1238901615142822, "global_step": 609422, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9968034029006958, "global_step": 609423, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.026761770248413, "global_step": 609424, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9819233417510986, "global_step": 609425, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0074708461761475, "global_step": 609426, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.023026466369629, "global_step": 609427, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.1137773990631104, "global_step": 609428, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.1146106719970703, "global_step": 609429, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0389721393585205, "global_step": 609430, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.034437894821167, "global_step": 609431, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.983557105064392, "global_step": 609432, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0300934314727783, "global_step": 609433, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9791477918624878, "global_step": 609434, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.017636775970459, "global_step": 609435, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0323970317840576, "global_step": 609436, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.984904170036316, "global_step": 609437, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9713897705078125, "global_step": 609438, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.092440128326416, "global_step": 609439, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9875189065933228, "global_step": 609440, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.924273133277893, "global_step": 609441, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9862146377563477, "global_step": 609442, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0502848625183105, "global_step": 609443, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0344181060791016, "global_step": 609444, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.017915964126587, "global_step": 609445, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.991571307182312, "global_step": 609446, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.023707866668701, "global_step": 609447, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9578722715377808, "global_step": 609448, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0054681301116943, "global_step": 609449, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0272226333618164, "global_step": 609450, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.01990008354187, "global_step": 609451, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0440361499786377, "global_step": 609452, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.039891481399536, "global_step": 609453, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.993067741394043, "global_step": 609454, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.031067132949829, "global_step": 609455, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0527703762054443, "global_step": 609456, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9967275857925415, "global_step": 609457, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.004990816116333, "global_step": 609458, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0572445392608643, "global_step": 609459, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.001957416534424, "global_step": 609460, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0067882537841797, "global_step": 609461, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0478436946868896, "global_step": 609462, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.042574644088745, "global_step": 609463, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0194592475891113, "global_step": 609464, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0425772666931152, "global_step": 609465, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.020010471343994, "global_step": 609466, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.017141103744507, "global_step": 609467, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9866280555725098, "global_step": 609468, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0759565830230713, "global_step": 609469, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.943925380706787, "global_step": 609470, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9369983673095703, "global_step": 609471, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.104642629623413, "global_step": 609472, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.009164571762085, "global_step": 609473, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.994267225265503, "global_step": 609474, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9653149843215942, "global_step": 609475, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0376174449920654, "global_step": 609476, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0391602516174316, "global_step": 609477, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0318214893341064, "global_step": 609478, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0807247161865234, "global_step": 609479, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9061708450317383, "global_step": 609480, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.140913963317871, "global_step": 609481, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9927409887313843, "global_step": 609482, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.056551456451416, "global_step": 609483, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.97736656665802, "global_step": 609484, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.036186695098877, "global_step": 609485, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0590546131134033, "global_step": 609486, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0337250232696533, "global_step": 609487, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.979611873626709, "global_step": 609488, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.963658094406128, "global_step": 609489, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9826672077178955, "global_step": 609490, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0499072074890137, "global_step": 609491, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0402579307556152, "global_step": 609492, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.955854892730713, "global_step": 609493, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.043954372406006, "global_step": 609494, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.1230204105377197, "global_step": 609495, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9643827676773071, "global_step": 609496, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.96343195438385, "global_step": 609497, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9614115953445435, "global_step": 609498, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.119910955429077, "global_step": 609499, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0170645713806152, "global_step": 609500, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0404562950134277, "global_step": 609501, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.039062023162842, "global_step": 609502, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.046414613723755, "global_step": 609503, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.054748296737671, "global_step": 609504, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.992607831954956, "global_step": 609505, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.065922260284424, "global_step": 609506, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0807528495788574, "global_step": 609507, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.005096673965454, "global_step": 609508, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0164272785186768, "global_step": 609509, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.1044716835021973, "global_step": 609510, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.8786565065383911, "global_step": 609511, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9633253812789917, "global_step": 609512, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0299484729766846, "global_step": 609513, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.1098721027374268, "global_step": 609514, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9401317834854126, "global_step": 609515, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0025806427001953, "global_step": 609516, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.030524730682373, "global_step": 609517, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.991337537765503, "global_step": 609518, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9639198780059814, "global_step": 609519, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9778163433074951, "global_step": 609520, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.945224642753601, "global_step": 609521, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.027625799179077, "global_step": 609522, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0429887771606445, "global_step": 609523, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0559566020965576, "global_step": 609524, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.028407096862793, "global_step": 609525, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0172483921051025, "global_step": 609526, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.976235270500183, "global_step": 609527, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.1710939407348633, "global_step": 609528, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9695242643356323, "global_step": 609529, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.129471778869629, "global_step": 609530, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.1130051612854004, "global_step": 609531, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9431631565093994, "global_step": 609532, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.993697166442871, "global_step": 609533, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9707131385803223, "global_step": 609534, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.03851056098938, "global_step": 609535, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0119364261627197, "global_step": 609536, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0620851516723633, "global_step": 609537, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.133131265640259, "global_step": 609538, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9866477251052856, "global_step": 609539, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.040517568588257, "global_step": 609540, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0113601684570312, "global_step": 609541, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0107812881469727, "global_step": 609542, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0562825202941895, "global_step": 609543, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.065044403076172, "global_step": 609544, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9653364419937134, "global_step": 609545, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0601089000701904, "global_step": 609546, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9628698825836182, "global_step": 609547, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0291249752044678, "global_step": 609548, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9485427141189575, "global_step": 609549, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0973920822143555, "global_step": 609550, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9983484745025635, "global_step": 609551, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.976485252380371, "global_step": 609552, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.109407901763916, "global_step": 609553, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.994733214378357, "global_step": 609554, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.990456223487854, "global_step": 609555, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.037649631500244, "global_step": 609556, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.930806279182434, "global_step": 609557, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.956045389175415, "global_step": 609558, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.983988881111145, "global_step": 609559, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0749282836914062, "global_step": 609560, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.011662721633911, "global_step": 609561, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.03075909614563, "global_step": 609562, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.041630506515503, "global_step": 609563, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.090778112411499, "global_step": 609564, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0465948581695557, "global_step": 609565, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.026459217071533, "global_step": 609566, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0528507232666016, "global_step": 609567, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9822918176651, "global_step": 609568, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0106265544891357, "global_step": 609569, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9875131845474243, "global_step": 609570, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0899479389190674, "global_step": 609571, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0560765266418457, "global_step": 609572, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0628488063812256, "global_step": 609573, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.008197546005249, "global_step": 609574, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.966536283493042, "global_step": 609575, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0543134212493896, "global_step": 609576, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9619872570037842, "global_step": 609577, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0484790802001953, "global_step": 609578, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.013120174407959, "global_step": 609579, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.091707229614258, "global_step": 609580, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9278203248977661, "global_step": 609581, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.037332773208618, "global_step": 609582, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9683259725570679, "global_step": 609583, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0238242149353027, "global_step": 609584, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0208969116210938, "global_step": 609585, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9885683059692383, "global_step": 609586, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9601175785064697, "global_step": 609587, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9369488954544067, "global_step": 609588, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9883543252944946, "global_step": 609589, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.028237819671631, "global_step": 609590, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9724551439285278, "global_step": 609591, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0083298683166504, "global_step": 609592, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.054974317550659, "global_step": 609593, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9913183450698853, "global_step": 609594, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0205953121185303, "global_step": 609595, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0324041843414307, "global_step": 609596, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.988348126411438, "global_step": 609597, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9903080463409424, "global_step": 609598, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0709002017974854, "global_step": 609599, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0614447593688965, "global_step": 609600, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.023251533508301, "global_step": 609601, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.044445753097534, "global_step": 609602, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.002833843231201, "global_step": 609603, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.063528060913086, "global_step": 609604, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0172910690307617, "global_step": 609605, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9889203310012817, "global_step": 609606, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9876084327697754, "global_step": 609607, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.959220290184021, "global_step": 609608, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.060668468475342, "global_step": 609609, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0189061164855957, "global_step": 609610, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.046687126159668, "global_step": 609611, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9673397541046143, "global_step": 609612, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9016869068145752, "global_step": 609613, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9342586994171143, "global_step": 609614, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0586328506469727, "global_step": 609615, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0459749698638916, "global_step": 609616, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0259220600128174, "global_step": 609617, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9646868705749512, "global_step": 609618, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0329434871673584, "global_step": 609619, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9666664600372314, "global_step": 609620, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.048861265182495, "global_step": 609621, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0251126289367676, "global_step": 609622, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0469045639038086, "global_step": 609623, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.938572883605957, "global_step": 609624, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.986986517906189, "global_step": 609625, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0540928840637207, "global_step": 609626, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9838017225265503, "global_step": 609627, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.001471519470215, "global_step": 609628, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0971555709838867, "global_step": 609629, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.9858006238937378, "global_step": 609630, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.0436418056488037, "global_step": 609631, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.045034408569336, "global_step": 609632, "epoch": 978, "lr": 5e-05}
{"train_loss": 2.00981068611145, "global_step": 609633, "epoch": 978, "lr": 5e-05}
{"train_loss": 1.997522234916687, "global_step": 609634, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9319241046905518, "global_step": 609635, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9998341798782349, "global_step": 609636, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0282511711120605, "global_step": 609637, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.980915904045105, "global_step": 609638, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.954581618309021, "global_step": 609639, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9648181200027466, "global_step": 609640, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0441603660583496, "global_step": 609641, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.1220033168792725, "global_step": 609642, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0001220703125, "global_step": 609643, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0261738300323486, "global_step": 609644, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.048464059829712, "global_step": 609645, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9484660625457764, "global_step": 609646, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0741984844207764, "global_step": 609647, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9837487936019897, "global_step": 609648, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0248215198516846, "global_step": 609649, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0055015087127686, "global_step": 609650, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0261456966400146, "global_step": 609651, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9910097122192383, "global_step": 609652, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9356576204299927, "global_step": 609653, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0084431171417236, "global_step": 609654, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.986883282661438, "global_step": 609655, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0629758834838867, "global_step": 609656, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9888287782669067, "global_step": 609657, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9079705476760864, "global_step": 609658, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0573720932006836, "global_step": 609659, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.926774501800537, "global_step": 609660, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0199472904205322, "global_step": 609661, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9534547328948975, "global_step": 609662, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9701087474822998, "global_step": 609663, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0152533054351807, "global_step": 609664, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9742909669876099, "global_step": 609665, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9903087615966797, "global_step": 609666, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9907950162887573, "global_step": 609667, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9526854753494263, "global_step": 609668, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0955259799957275, "global_step": 609669, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0174453258514404, "global_step": 609670, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.020285129547119, "global_step": 609671, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.035975694656372, "global_step": 609672, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9919737577438354, "global_step": 609673, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9013234376907349, "global_step": 609674, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9847439527511597, "global_step": 609675, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.078371524810791, "global_step": 609676, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9965640306472778, "global_step": 609677, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.007249116897583, "global_step": 609678, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9919745922088623, "global_step": 609679, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0826375484466553, "global_step": 609680, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.019779920578003, "global_step": 609681, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.042241334915161, "global_step": 609682, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9986437559127808, "global_step": 609683, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0967094898223877, "global_step": 609684, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9397268295288086, "global_step": 609685, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9644666910171509, "global_step": 609686, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0224950313568115, "global_step": 609687, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.027662992477417, "global_step": 609688, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9442039728164673, "global_step": 609689, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.010852813720703, "global_step": 609690, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9700185060501099, "global_step": 609691, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.018733263015747, "global_step": 609692, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9595293998718262, "global_step": 609693, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9444327354431152, "global_step": 609694, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9368531703948975, "global_step": 609695, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0646560192108154, "global_step": 609696, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0508668422698975, "global_step": 609697, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0459718704223633, "global_step": 609698, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9928678274154663, "global_step": 609699, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0215108394622803, "global_step": 609700, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9512794017791748, "global_step": 609701, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9945377111434937, "global_step": 609702, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0633597373962402, "global_step": 609703, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0555837154388428, "global_step": 609704, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.01989483833313, "global_step": 609705, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0662896633148193, "global_step": 609706, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9927873611450195, "global_step": 609707, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.015418767929077, "global_step": 609708, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0667855739593506, "global_step": 609709, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0557491779327393, "global_step": 609710, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.952323079109192, "global_step": 609711, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0488839149475098, "global_step": 609712, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9907739162445068, "global_step": 609713, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9795434474945068, "global_step": 609714, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9889931678771973, "global_step": 609715, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0442452430725098, "global_step": 609716, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0303893089294434, "global_step": 609717, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.8895987272262573, "global_step": 609718, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0639495849609375, "global_step": 609719, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9773330688476562, "global_step": 609720, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9971898794174194, "global_step": 609721, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0537095069885254, "global_step": 609722, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9983993768692017, "global_step": 609723, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9627737998962402, "global_step": 609724, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9719873666763306, "global_step": 609725, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.967323899269104, "global_step": 609726, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0301663875579834, "global_step": 609727, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9685308933258057, "global_step": 609728, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9879471063613892, "global_step": 609729, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0261385440826416, "global_step": 609730, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.048966407775879, "global_step": 609731, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9418033361434937, "global_step": 609732, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0024337768554688, "global_step": 609733, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9952800273895264, "global_step": 609734, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.08992862701416, "global_step": 609735, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0439751148223877, "global_step": 609736, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0306217670440674, "global_step": 609737, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9949069023132324, "global_step": 609738, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.994565725326538, "global_step": 609739, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.053868532180786, "global_step": 609740, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0115368366241455, "global_step": 609741, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.990797758102417, "global_step": 609742, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.027848243713379, "global_step": 609743, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0179548263549805, "global_step": 609744, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0232975482940674, "global_step": 609745, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.958005666732788, "global_step": 609746, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9717731475830078, "global_step": 609747, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9922890663146973, "global_step": 609748, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9487807750701904, "global_step": 609749, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.958261489868164, "global_step": 609750, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9039603471755981, "global_step": 609751, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.02146053314209, "global_step": 609752, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0405209064483643, "global_step": 609753, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.8927931785583496, "global_step": 609754, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0514416694641113, "global_step": 609755, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0943915843963623, "global_step": 609756, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.003830671310425, "global_step": 609757, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.025632381439209, "global_step": 609758, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0266876220703125, "global_step": 609759, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9671813249588013, "global_step": 609760, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9600181579589844, "global_step": 609761, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9183801412582397, "global_step": 609762, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9832888841629028, "global_step": 609763, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.997283697128296, "global_step": 609764, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0777385234832764, "global_step": 609765, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9514960050582886, "global_step": 609766, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9513887166976929, "global_step": 609767, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9824023246765137, "global_step": 609768, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0774357318878174, "global_step": 609769, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0398597717285156, "global_step": 609770, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.016294240951538, "global_step": 609771, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.948820948600769, "global_step": 609772, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9386268854141235, "global_step": 609773, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9642205238342285, "global_step": 609774, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.002046823501587, "global_step": 609775, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0472121238708496, "global_step": 609776, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.016315221786499, "global_step": 609777, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9532155990600586, "global_step": 609778, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9808088541030884, "global_step": 609779, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.967609167098999, "global_step": 609780, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9884765148162842, "global_step": 609781, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.983191967010498, "global_step": 609782, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.8960466384887695, "global_step": 609783, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0101218223571777, "global_step": 609784, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.041548013687134, "global_step": 609785, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9980413913726807, "global_step": 609786, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9276059865951538, "global_step": 609787, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0500261783599854, "global_step": 609788, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0092105865478516, "global_step": 609789, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.042552947998047, "global_step": 609790, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.00230073928833, "global_step": 609791, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9245189428329468, "global_step": 609792, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.010483503341675, "global_step": 609793, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.957891821861267, "global_step": 609794, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0581822395324707, "global_step": 609795, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9822049140930176, "global_step": 609796, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0443191528320312, "global_step": 609797, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9982659816741943, "global_step": 609798, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.026918649673462, "global_step": 609799, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0544097423553467, "global_step": 609800, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9688297510147095, "global_step": 609801, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.004643440246582, "global_step": 609802, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.036684989929199, "global_step": 609803, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.949496865272522, "global_step": 609804, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9913065433502197, "global_step": 609805, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0013673305511475, "global_step": 609806, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0536372661590576, "global_step": 609807, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.082287549972534, "global_step": 609808, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.1229519844055176, "global_step": 609809, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.998631238937378, "global_step": 609810, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.974647879600525, "global_step": 609811, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0957984924316406, "global_step": 609812, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0402562618255615, "global_step": 609813, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.022190570831299, "global_step": 609814, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9525487422943115, "global_step": 609815, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9757834672927856, "global_step": 609816, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0470099449157715, "global_step": 609817, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.033501386642456, "global_step": 609818, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0196645259857178, "global_step": 609819, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9660918712615967, "global_step": 609820, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9634190797805786, "global_step": 609821, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9593735933303833, "global_step": 609822, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0707805156707764, "global_step": 609823, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.025759220123291, "global_step": 609824, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9922767877578735, "global_step": 609825, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9722199440002441, "global_step": 609826, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.004686117172241, "global_step": 609827, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0495083332061768, "global_step": 609828, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.010544776916504, "global_step": 609829, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.01051664352417, "global_step": 609830, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.012105703353882, "global_step": 609831, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0575079917907715, "global_step": 609832, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.1073312759399414, "global_step": 609833, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0369842052459717, "global_step": 609834, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0820984840393066, "global_step": 609835, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.920525074005127, "global_step": 609836, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9692176580429077, "global_step": 609837, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.977640151977539, "global_step": 609838, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9881168603897095, "global_step": 609839, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0135350227355957, "global_step": 609840, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0811924934387207, "global_step": 609841, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.108111619949341, "global_step": 609842, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9896684885025024, "global_step": 609843, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0079352855682373, "global_step": 609844, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0398824214935303, "global_step": 609845, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9412331581115723, "global_step": 609846, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.007392406463623, "global_step": 609847, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9933958053588867, "global_step": 609848, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9758445024490356, "global_step": 609849, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0677037239074707, "global_step": 609850, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0251517295837402, "global_step": 609851, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.026906967163086, "global_step": 609852, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0254271030426025, "global_step": 609853, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9255549907684326, "global_step": 609854, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0878825187683105, "global_step": 609855, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9158958196640015, "global_step": 609856, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.980055332183838, "global_step": 609857, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9890363216400146, "global_step": 609858, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.958206057548523, "global_step": 609859, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0025620460510254, "global_step": 609860, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.919001579284668, "global_step": 609861, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9396870136260986, "global_step": 609862, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.01408052444458, "global_step": 609863, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0040454864501953, "global_step": 609864, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.038367986679077, "global_step": 609865, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0482239723205566, "global_step": 609866, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.04490327835083, "global_step": 609867, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9881576299667358, "global_step": 609868, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.08445405960083, "global_step": 609869, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.000129222869873, "global_step": 609870, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0804078578948975, "global_step": 609871, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.007507562637329, "global_step": 609872, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.00553297996521, "global_step": 609873, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0706779956817627, "global_step": 609874, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9737449884414673, "global_step": 609875, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9325309991836548, "global_step": 609876, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9619576930999756, "global_step": 609877, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0066580772399902, "global_step": 609878, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.979219913482666, "global_step": 609879, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.000446319580078, "global_step": 609880, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0910940170288086, "global_step": 609881, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9351352453231812, "global_step": 609882, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0310025215148926, "global_step": 609883, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0393683910369873, "global_step": 609884, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9957313537597656, "global_step": 609885, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.001981735229492, "global_step": 609886, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.056112766265869, "global_step": 609887, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.892309546470642, "global_step": 609888, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9083770513534546, "global_step": 609889, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0708954334259033, "global_step": 609890, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9562550783157349, "global_step": 609891, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.05991268157959, "global_step": 609892, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9965887069702148, "global_step": 609893, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0455822944641113, "global_step": 609894, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.90666663646698, "global_step": 609895, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.98406183719635, "global_step": 609896, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.044220209121704, "global_step": 609897, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.964263916015625, "global_step": 609898, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.059591293334961, "global_step": 609899, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9953513145446777, "global_step": 609900, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.968430757522583, "global_step": 609901, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9944018125534058, "global_step": 609902, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.097860097885132, "global_step": 609903, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.985049843788147, "global_step": 609904, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0333337783813477, "global_step": 609905, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0738656520843506, "global_step": 609906, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0568315982818604, "global_step": 609907, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.880571722984314, "global_step": 609908, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.004432439804077, "global_step": 609909, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.8948562145233154, "global_step": 609910, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9901888370513916, "global_step": 609911, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.033036231994629, "global_step": 609912, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.009047031402588, "global_step": 609913, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.025377035140991, "global_step": 609914, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0447258949279785, "global_step": 609915, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0513269901275635, "global_step": 609916, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.092402219772339, "global_step": 609917, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.020240306854248, "global_step": 609918, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.964233160018921, "global_step": 609919, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9642083644866943, "global_step": 609920, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0687506198883057, "global_step": 609921, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.930933952331543, "global_step": 609922, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.031385660171509, "global_step": 609923, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9758397340774536, "global_step": 609924, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0276243686676025, "global_step": 609925, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9444208145141602, "global_step": 609926, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0937535762786865, "global_step": 609927, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9645893573760986, "global_step": 609928, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0265932083129883, "global_step": 609929, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0326802730560303, "global_step": 609930, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0238728523254395, "global_step": 609931, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9223910570144653, "global_step": 609932, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0034608840942383, "global_step": 609933, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9434887170791626, "global_step": 609934, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9993168115615845, "global_step": 609935, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0498952865600586, "global_step": 609936, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9968695640563965, "global_step": 609937, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0322840213775635, "global_step": 609938, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.066084861755371, "global_step": 609939, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9837826490402222, "global_step": 609940, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.004362106323242, "global_step": 609941, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.000568389892578, "global_step": 609942, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0111336708068848, "global_step": 609943, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.1674184799194336, "global_step": 609944, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0554749965667725, "global_step": 609945, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.081434488296509, "global_step": 609946, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0045101642608643, "global_step": 609947, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9726489782333374, "global_step": 609948, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.1163086891174316, "global_step": 609949, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9595059156417847, "global_step": 609950, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0203237533569336, "global_step": 609951, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9473875761032104, "global_step": 609952, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.021965503692627, "global_step": 609953, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0069730281829834, "global_step": 609954, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9408601522445679, "global_step": 609955, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0867416858673096, "global_step": 609956, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.092320442199707, "global_step": 609957, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0225350856781006, "global_step": 609958, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9875553846359253, "global_step": 609959, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0022366046905518, "global_step": 609960, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9938071966171265, "global_step": 609961, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.913529396057129, "global_step": 609962, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0551843643188477, "global_step": 609963, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.02470064163208, "global_step": 609964, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0725574493408203, "global_step": 609965, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0373787879943848, "global_step": 609966, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.998946189880371, "global_step": 609967, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9568105936050415, "global_step": 609968, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0079948902130127, "global_step": 609969, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9997012615203857, "global_step": 609970, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9938355684280396, "global_step": 609971, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.1186752319335938, "global_step": 609972, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9429686069488525, "global_step": 609973, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9646819829940796, "global_step": 609974, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.973978877067566, "global_step": 609975, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9251885414123535, "global_step": 609976, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0246386528015137, "global_step": 609977, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9528981447219849, "global_step": 609978, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0949347019195557, "global_step": 609979, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.062206983566284, "global_step": 609980, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9995023012161255, "global_step": 609981, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.004629135131836, "global_step": 609982, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9480029344558716, "global_step": 609983, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.023873805999756, "global_step": 609984, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9571532011032104, "global_step": 609985, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.065748453140259, "global_step": 609986, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0348329544067383, "global_step": 609987, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9770240783691406, "global_step": 609988, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.1024463176727295, "global_step": 609989, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.02587628364563, "global_step": 609990, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0952351093292236, "global_step": 609991, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.1360232830047607, "global_step": 609992, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0458953380584717, "global_step": 609993, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0358362197875977, "global_step": 609994, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.951364278793335, "global_step": 609995, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.009763240814209, "global_step": 609996, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.003227949142456, "global_step": 609997, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0349156856536865, "global_step": 609998, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0309112071990967, "global_step": 609999, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0993993282318115, "global_step": 610000, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.970633625984192, "global_step": 610001, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9857558012008667, "global_step": 610002, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9662108421325684, "global_step": 610003, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.938154697418213, "global_step": 610004, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0903706550598145, "global_step": 610005, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.048558235168457, "global_step": 610006, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0288639068603516, "global_step": 610007, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9530972242355347, "global_step": 610008, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.051774740219116, "global_step": 610009, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0265603065490723, "global_step": 610010, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.070958137512207, "global_step": 610011, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9822125434875488, "global_step": 610012, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9838908910751343, "global_step": 610013, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9257192611694336, "global_step": 610014, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.032097578048706, "global_step": 610015, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0218117237091064, "global_step": 610016, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.007002592086792, "global_step": 610017, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9874722957611084, "global_step": 610018, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.997933268547058, "global_step": 610019, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.905293583869934, "global_step": 610020, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9998670816421509, "global_step": 610021, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9855873584747314, "global_step": 610022, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.055825710296631, "global_step": 610023, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0147862434387207, "global_step": 610024, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9884223937988281, "global_step": 610025, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9733368158340454, "global_step": 610026, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9682097434997559, "global_step": 610027, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0020370483398438, "global_step": 610028, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0056169033050537, "global_step": 610029, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0364487171173096, "global_step": 610030, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.030858039855957, "global_step": 610031, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.996889352798462, "global_step": 610032, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.002230405807495, "global_step": 610033, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0283591747283936, "global_step": 610034, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0137503147125244, "global_step": 610035, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.090857744216919, "global_step": 610036, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.008725166320801, "global_step": 610037, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.008668899536133, "global_step": 610038, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.067777633666992, "global_step": 610039, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.03151798248291, "global_step": 610040, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0622878074645996, "global_step": 610041, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9044681787490845, "global_step": 610042, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0636117458343506, "global_step": 610043, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.08477520942688, "global_step": 610044, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0302443504333496, "global_step": 610045, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0284059047698975, "global_step": 610046, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9347330331802368, "global_step": 610047, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.052703619003296, "global_step": 610048, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0057790279388428, "global_step": 610049, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.025041341781616, "global_step": 610050, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9872417449951172, "global_step": 610051, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.04891037940979, "global_step": 610052, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0365283489227295, "global_step": 610053, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9470378160476685, "global_step": 610054, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9873957633972168, "global_step": 610055, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0508882999420166, "global_step": 610056, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.027498483657837, "global_step": 610057, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.016643762588501, "global_step": 610058, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0024185180664062, "global_step": 610059, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9614815711975098, "global_step": 610060, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9593580961227417, "global_step": 610061, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.980832576751709, "global_step": 610062, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.972643494606018, "global_step": 610063, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9360620975494385, "global_step": 610064, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.033299446105957, "global_step": 610065, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9650949239730835, "global_step": 610066, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0573911666870117, "global_step": 610067, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9923545122146606, "global_step": 610068, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9478883743286133, "global_step": 610069, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.011995553970337, "global_step": 610070, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.891847014427185, "global_step": 610071, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9931014776229858, "global_step": 610072, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.977568507194519, "global_step": 610073, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.005533456802368, "global_step": 610074, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9871251583099365, "global_step": 610075, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9832680225372314, "global_step": 610076, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9842315912246704, "global_step": 610077, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9957045316696167, "global_step": 610078, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9902526140213013, "global_step": 610079, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9754507541656494, "global_step": 610080, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.011110544204712, "global_step": 610081, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0757012367248535, "global_step": 610082, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.1025824546813965, "global_step": 610083, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0660033226013184, "global_step": 610084, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9269613027572632, "global_step": 610085, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0005054473876953, "global_step": 610086, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.086747646331787, "global_step": 610087, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0801258087158203, "global_step": 610088, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.016876697540283, "global_step": 610089, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9954273700714111, "global_step": 610090, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.1120219230651855, "global_step": 610091, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9143298864364624, "global_step": 610092, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.05755615234375, "global_step": 610093, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9431308507919312, "global_step": 610094, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0569117069244385, "global_step": 610095, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9763981103897095, "global_step": 610096, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9137566089630127, "global_step": 610097, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.029860019683838, "global_step": 610098, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.060722827911377, "global_step": 610099, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.933841586112976, "global_step": 610100, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.1320178508758545, "global_step": 610101, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.010716676712036, "global_step": 610102, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0494542121887207, "global_step": 610103, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9583605527877808, "global_step": 610104, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.004948139190674, "global_step": 610105, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.039505958557129, "global_step": 610106, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.975459098815918, "global_step": 610107, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0445268154144287, "global_step": 610108, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0237362384796143, "global_step": 610109, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9672483205795288, "global_step": 610110, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9752492904663086, "global_step": 610111, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0665111541748047, "global_step": 610112, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.988936424255371, "global_step": 610113, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.016817331314087, "global_step": 610114, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.026323080062866, "global_step": 610115, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.005659341812134, "global_step": 610116, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.987679362297058, "global_step": 610117, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.989024043083191, "global_step": 610118, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0202016830444336, "global_step": 610119, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9926979541778564, "global_step": 610120, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9982242584228516, "global_step": 610121, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.029207229614258, "global_step": 610122, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9893231391906738, "global_step": 610123, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.948400616645813, "global_step": 610124, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.018320322036743, "global_step": 610125, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9066165685653687, "global_step": 610126, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0524535179138184, "global_step": 610127, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.001221179962158, "global_step": 610128, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0428340435028076, "global_step": 610129, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0191731452941895, "global_step": 610130, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.078557014465332, "global_step": 610131, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9539587497711182, "global_step": 610132, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0079386234283447, "global_step": 610133, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0194177627563477, "global_step": 610134, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9747804403305054, "global_step": 610135, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0450849533081055, "global_step": 610136, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9429333209991455, "global_step": 610137, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0345423221588135, "global_step": 610138, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.00675368309021, "global_step": 610139, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.029843807220459, "global_step": 610140, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.926252007484436, "global_step": 610141, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.043649435043335, "global_step": 610142, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.1122562885284424, "global_step": 610143, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.023440361022949, "global_step": 610144, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0322515964508057, "global_step": 610145, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.038020610809326, "global_step": 610146, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9920138120651245, "global_step": 610147, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.970620036125183, "global_step": 610148, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.020972728729248, "global_step": 610149, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9934020042419434, "global_step": 610150, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9266564846038818, "global_step": 610151, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.007585287094116, "global_step": 610152, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9747751951217651, "global_step": 610153, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0436203479766846, "global_step": 610154, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.964085340499878, "global_step": 610155, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.949629545211792, "global_step": 610156, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0153605937957764, "global_step": 610157, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9357776641845703, "global_step": 610158, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9843425750732422, "global_step": 610159, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0328588485717773, "global_step": 610160, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0786614418029785, "global_step": 610161, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.054058790206909, "global_step": 610162, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.1050758361816406, "global_step": 610163, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9695016145706177, "global_step": 610164, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.010627031326294, "global_step": 610165, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.917397141456604, "global_step": 610166, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9806594848632812, "global_step": 610167, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.107968330383301, "global_step": 610168, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0206844806671143, "global_step": 610169, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.058013916015625, "global_step": 610170, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.962519645690918, "global_step": 610171, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.096604824066162, "global_step": 610172, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9862515926361084, "global_step": 610173, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0711913108825684, "global_step": 610174, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9716471433639526, "global_step": 610175, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9587150812149048, "global_step": 610176, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9717597961425781, "global_step": 610177, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9344818592071533, "global_step": 610178, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.034876585006714, "global_step": 610179, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.071479320526123, "global_step": 610180, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0840797424316406, "global_step": 610181, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.057466745376587, "global_step": 610182, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.1029138565063477, "global_step": 610183, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.043142080307007, "global_step": 610184, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.047830581665039, "global_step": 610185, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9508702754974365, "global_step": 610186, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.024531126022339, "global_step": 610187, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0677194595336914, "global_step": 610188, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9883122444152832, "global_step": 610189, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9919424057006836, "global_step": 610190, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.993030309677124, "global_step": 610191, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9760950803756714, "global_step": 610192, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0112013816833496, "global_step": 610193, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0591368675231934, "global_step": 610194, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0327630043029785, "global_step": 610195, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.034609079360962, "global_step": 610196, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9821585416793823, "global_step": 610197, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0378096103668213, "global_step": 610198, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.988368034362793, "global_step": 610199, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0088274478912354, "global_step": 610200, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0288660526275635, "global_step": 610201, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9589548110961914, "global_step": 610202, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0561769008636475, "global_step": 610203, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9175935983657837, "global_step": 610204, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0489439964294434, "global_step": 610205, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.011482000350952, "global_step": 610206, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9514940977096558, "global_step": 610207, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9853017330169678, "global_step": 610208, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.066495895385742, "global_step": 610209, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.1438405513763428, "global_step": 610210, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9602227210998535, "global_step": 610211, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.092913866043091, "global_step": 610212, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0888612270355225, "global_step": 610213, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9347717761993408, "global_step": 610214, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.99362313747406, "global_step": 610215, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9850819110870361, "global_step": 610216, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9787150621414185, "global_step": 610217, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.035461187362671, "global_step": 610218, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9871842861175537, "global_step": 610219, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9694275856018066, "global_step": 610220, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0295629501342773, "global_step": 610221, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.926358699798584, "global_step": 610222, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0618577003479004, "global_step": 610223, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.002736806869507, "global_step": 610224, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.035068988800049, "global_step": 610225, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0053467750549316, "global_step": 610226, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0317602157592773, "global_step": 610227, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9746965169906616, "global_step": 610228, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0927796363830566, "global_step": 610229, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0540523529052734, "global_step": 610230, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9931949377059937, "global_step": 610231, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0341172218322754, "global_step": 610232, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9299067258834839, "global_step": 610233, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9395614862442017, "global_step": 610234, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9920451641082764, "global_step": 610235, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9460294246673584, "global_step": 610236, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.081353187561035, "global_step": 610237, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.013138771057129, "global_step": 610238, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9515150785446167, "global_step": 610239, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.020627975463867, "global_step": 610240, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0110621452331543, "global_step": 610241, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0498435497283936, "global_step": 610242, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.016024351119995, "global_step": 610243, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9609746932983398, "global_step": 610244, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9156205654144287, "global_step": 610245, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9775477647781372, "global_step": 610246, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.031118154525757, "global_step": 610247, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0710699558258057, "global_step": 610248, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9444069862365723, "global_step": 610249, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0071535110473633, "global_step": 610250, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9341886043548584, "global_step": 610251, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.896598219871521, "global_step": 610252, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.002742290496826, "global_step": 610253, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.981882929801941, "global_step": 610254, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.977074146270752, "global_step": 610255, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9832847118377686, "global_step": 610256, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9773061275482178, "global_step": 610257, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.964049220085144, "global_step": 610258, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9560601711273193, "global_step": 610259, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0034823417663574, "global_step": 610260, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9647551774978638, "global_step": 610261, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0360052585601807, "global_step": 610262, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0334813594818115, "global_step": 610263, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9696217775344849, "global_step": 610264, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.049438714981079, "global_step": 610265, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.088223934173584, "global_step": 610266, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0232362747192383, "global_step": 610267, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0761542320251465, "global_step": 610268, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0699410438537598, "global_step": 610269, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0863723754882812, "global_step": 610270, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9962159395217896, "global_step": 610271, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9854562282562256, "global_step": 610272, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9779610633850098, "global_step": 610273, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.028392791748047, "global_step": 610274, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0496294498443604, "global_step": 610275, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.040177822113037, "global_step": 610276, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9925847053527832, "global_step": 610277, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9851744174957275, "global_step": 610278, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0035414695739746, "global_step": 610279, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0732882022857666, "global_step": 610280, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0283021926879883, "global_step": 610281, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9908297061920166, "global_step": 610282, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.031471014022827, "global_step": 610283, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0040969848632812, "global_step": 610284, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9653680324554443, "global_step": 610285, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0848231315612793, "global_step": 610286, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0193536281585693, "global_step": 610287, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0198934078216553, "global_step": 610288, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.096188545227051, "global_step": 610289, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9245394468307495, "global_step": 610290, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9300869703292847, "global_step": 610291, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9388701915740967, "global_step": 610292, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.058163642883301, "global_step": 610293, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.023980140686035, "global_step": 610294, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0230319499969482, "global_step": 610295, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9674808979034424, "global_step": 610296, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0008299350738525, "global_step": 610297, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0568606853485107, "global_step": 610298, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.016645908355713, "global_step": 610299, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9494655132293701, "global_step": 610300, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.931490182876587, "global_step": 610301, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9753074645996094, "global_step": 610302, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9409565925598145, "global_step": 610303, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9899847507476807, "global_step": 610304, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.024031400680542, "global_step": 610305, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.975387454032898, "global_step": 610306, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9748281240463257, "global_step": 610307, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9684360027313232, "global_step": 610308, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9973883628845215, "global_step": 610309, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.047262668609619, "global_step": 610310, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.098609209060669, "global_step": 610311, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0345911979675293, "global_step": 610312, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9571715593338013, "global_step": 610313, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.022519588470459, "global_step": 610314, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0152804851531982, "global_step": 610315, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9814609289169312, "global_step": 610316, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.092985153198242, "global_step": 610317, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0289559364318848, "global_step": 610318, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9102345705032349, "global_step": 610319, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.052321434020996, "global_step": 610320, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9436259269714355, "global_step": 610321, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0452640056610107, "global_step": 610322, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0255398750305176, "global_step": 610323, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.004852771759033, "global_step": 610324, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.095689296722412, "global_step": 610325, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0329344272613525, "global_step": 610326, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0492591857910156, "global_step": 610327, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.054347515106201, "global_step": 610328, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0453758239746094, "global_step": 610329, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0695722103118896, "global_step": 610330, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9316658973693848, "global_step": 610331, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9318405389785767, "global_step": 610332, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.990875005722046, "global_step": 610333, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.954062581062317, "global_step": 610334, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.977038025856018, "global_step": 610335, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.057067394256592, "global_step": 610336, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.982855200767517, "global_step": 610337, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.972090721130371, "global_step": 610338, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9468802213668823, "global_step": 610339, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9325003623962402, "global_step": 610340, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9812543392181396, "global_step": 610341, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9581153392791748, "global_step": 610342, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0214409828186035, "global_step": 610343, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.976685881614685, "global_step": 610344, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9777023792266846, "global_step": 610345, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0635714530944824, "global_step": 610346, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.982036828994751, "global_step": 610347, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9936965703964233, "global_step": 610348, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9890451431274414, "global_step": 610349, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0688319206237793, "global_step": 610350, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.948469638824463, "global_step": 610351, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.034968852996826, "global_step": 610352, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.982349157333374, "global_step": 610353, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0117316246032715, "global_step": 610354, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.104296922683716, "global_step": 610355, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0028722286224365, "global_step": 610356, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.973109483718872, "global_step": 610357, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.019817590713501, "global_step": 610358, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0982909202575684, "global_step": 610359, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.052957534790039, "global_step": 610360, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9887871742248535, "global_step": 610361, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9562392234802246, "global_step": 610362, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.017368793487549, "global_step": 610363, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.011370897293091, "global_step": 610364, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.043593168258667, "global_step": 610365, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9530677795410156, "global_step": 610366, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9773552417755127, "global_step": 610367, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.013005495071411, "global_step": 610368, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0044260025024414, "global_step": 610369, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0056424140930176, "global_step": 610370, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0351736545562744, "global_step": 610371, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.041522979736328, "global_step": 610372, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.067941427230835, "global_step": 610373, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0218536853790283, "global_step": 610374, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9375531673431396, "global_step": 610375, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.995406985282898, "global_step": 610376, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0459985733032227, "global_step": 610377, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.034376621246338, "global_step": 610378, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9944636821746826, "global_step": 610379, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0307798385620117, "global_step": 610380, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.060321092605591, "global_step": 610381, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.072239398956299, "global_step": 610382, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.015805244445801, "global_step": 610383, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9660018682479858, "global_step": 610384, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.016063928604126, "global_step": 610385, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9571985006332397, "global_step": 610386, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.021435022354126, "global_step": 610387, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9958785772323608, "global_step": 610388, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.025980234146118, "global_step": 610389, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0435826778411865, "global_step": 610390, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0153911113739014, "global_step": 610391, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9912161827087402, "global_step": 610392, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9764140844345093, "global_step": 610393, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0264649391174316, "global_step": 610394, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0045719146728516, "global_step": 610395, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0590641498565674, "global_step": 610396, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0370285511016846, "global_step": 610397, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9963899850845337, "global_step": 610398, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9868680238723755, "global_step": 610399, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9658677577972412, "global_step": 610400, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0786757469177246, "global_step": 610401, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0786633491516113, "global_step": 610402, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.007315158843994, "global_step": 610403, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9799585342407227, "global_step": 610404, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9965187311172485, "global_step": 610405, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9693288803100586, "global_step": 610406, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9500529766082764, "global_step": 610407, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.059746503829956, "global_step": 610408, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9753531217575073, "global_step": 610409, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0529944896698, "global_step": 610410, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0308191776275635, "global_step": 610411, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0257887840270996, "global_step": 610412, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.120861291885376, "global_step": 610413, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.949963927268982, "global_step": 610414, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0008633136749268, "global_step": 610415, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.029611110687256, "global_step": 610416, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9225846529006958, "global_step": 610417, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9847238063812256, "global_step": 610418, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9797581434249878, "global_step": 610419, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.974414348602295, "global_step": 610420, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.00076961517334, "global_step": 610421, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9921663999557495, "global_step": 610422, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.8541314601898193, "global_step": 610423, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.1321425437927246, "global_step": 610424, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0286431312561035, "global_step": 610425, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0251781940460205, "global_step": 610426, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.092992067337036, "global_step": 610427, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.043893575668335, "global_step": 610428, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9763306379318237, "global_step": 610429, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0249757766723633, "global_step": 610430, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.047731637954712, "global_step": 610431, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.975475549697876, "global_step": 610432, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.046217918395996, "global_step": 610433, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.041945457458496, "global_step": 610434, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.044304609298706, "global_step": 610435, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0246334075927734, "global_step": 610436, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9671212434768677, "global_step": 610437, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0116772651672363, "global_step": 610438, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0689802169799805, "global_step": 610439, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0687406063079834, "global_step": 610440, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9808059930801392, "global_step": 610441, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.029963254928589, "global_step": 610442, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0149662494659424, "global_step": 610443, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.8900688886642456, "global_step": 610444, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.041898727416992, "global_step": 610445, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9902011156082153, "global_step": 610446, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.1037425994873047, "global_step": 610447, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0320498943328857, "global_step": 610448, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.963059663772583, "global_step": 610449, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9749677181243896, "global_step": 610450, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9106035232543945, "global_step": 610451, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9702521562576294, "global_step": 610452, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9852439165115356, "global_step": 610453, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0237245559692383, "global_step": 610454, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9988981485366821, "global_step": 610455, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0239837169647217, "global_step": 610456, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0164835453033447, "global_step": 610457, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0391695499420166, "global_step": 610458, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0489673614501953, "global_step": 610459, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.1590576171875, "global_step": 610460, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9822731018066406, "global_step": 610461, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.049149513244629, "global_step": 610462, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.054612398147583, "global_step": 610463, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0267186164855957, "global_step": 610464, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0292792320251465, "global_step": 610465, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0753424167633057, "global_step": 610466, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9665453433990479, "global_step": 610467, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.008181571960449, "global_step": 610468, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.8797721862792969, "global_step": 610469, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.08897066116333, "global_step": 610470, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.899631142616272, "global_step": 610471, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.025904893875122, "global_step": 610472, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.004513740539551, "global_step": 610473, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.954968810081482, "global_step": 610474, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.108822822570801, "global_step": 610475, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9596527814865112, "global_step": 610476, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9968246221542358, "global_step": 610477, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0215508937835693, "global_step": 610478, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.040724039077759, "global_step": 610479, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9954180717468262, "global_step": 610480, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0732438564300537, "global_step": 610481, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0589892864227295, "global_step": 610482, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0332674980163574, "global_step": 610483, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9434763193130493, "global_step": 610484, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.029110908508301, "global_step": 610485, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9738558530807495, "global_step": 610486, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0439064502716064, "global_step": 610487, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.034456491470337, "global_step": 610488, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0800631046295166, "global_step": 610489, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0680246353149414, "global_step": 610490, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9614895582199097, "global_step": 610491, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9258736371994019, "global_step": 610492, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9834375381469727, "global_step": 610493, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9192200899124146, "global_step": 610494, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9590264558792114, "global_step": 610495, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9735827445983887, "global_step": 610496, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9419969320297241, "global_step": 610497, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0298027992248535, "global_step": 610498, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0068345069885254, "global_step": 610499, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.996856451034546, "global_step": 610500, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9877700805664062, "global_step": 610501, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.005708694458008, "global_step": 610502, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0291576385498047, "global_step": 610503, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.006270170211792, "global_step": 610504, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.093858242034912, "global_step": 610505, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9844274520874023, "global_step": 610506, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.07435941696167, "global_step": 610507, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.012470006942749, "global_step": 610508, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0241847038269043, "global_step": 610509, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.992906093597412, "global_step": 610510, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0716028213500977, "global_step": 610511, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.015075206756592, "global_step": 610512, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0538346767425537, "global_step": 610513, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9176647663116455, "global_step": 610514, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9319188594818115, "global_step": 610515, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9431313276290894, "global_step": 610516, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9440921545028687, "global_step": 610517, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9573495388031006, "global_step": 610518, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.000594139099121, "global_step": 610519, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9774397611618042, "global_step": 610520, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9486336708068848, "global_step": 610521, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0059714317321777, "global_step": 610522, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.972280502319336, "global_step": 610523, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0087947845458984, "global_step": 610524, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9906251430511475, "global_step": 610525, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0372610092163086, "global_step": 610526, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.081263780593872, "global_step": 610527, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0712690353393555, "global_step": 610528, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0639829635620117, "global_step": 610529, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.054921865463257, "global_step": 610530, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.036471128463745, "global_step": 610531, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.004096746444702, "global_step": 610532, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9745601415634155, "global_step": 610533, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0014493465423584, "global_step": 610534, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.922899842262268, "global_step": 610535, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9721577167510986, "global_step": 610536, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0171451568603516, "global_step": 610537, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9886096715927124, "global_step": 610538, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.997087001800537, "global_step": 610539, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.044421911239624, "global_step": 610540, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.988319754600525, "global_step": 610541, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.020296573638916, "global_step": 610542, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.036947250366211, "global_step": 610543, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.989230990409851, "global_step": 610544, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9809609651565552, "global_step": 610545, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0047507286071777, "global_step": 610546, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.921973705291748, "global_step": 610547, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.006490468978882, "global_step": 610548, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9904587268829346, "global_step": 610549, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9486134052276611, "global_step": 610550, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0126614570617676, "global_step": 610551, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9503724575042725, "global_step": 610552, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9488424062728882, "global_step": 610553, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.010678291320801, "global_step": 610554, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9917960166931152, "global_step": 610555, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.085756301879883, "global_step": 610556, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9661742448806763, "global_step": 610557, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9677873849868774, "global_step": 610558, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.919901967048645, "global_step": 610559, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.942224383354187, "global_step": 610560, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.056328058242798, "global_step": 610561, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.009300947189331, "global_step": 610562, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9522424936294556, "global_step": 610563, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.041280746459961, "global_step": 610564, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9970341920852661, "global_step": 610565, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.024188280105591, "global_step": 610566, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9517818689346313, "global_step": 610567, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9702104330062866, "global_step": 610568, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9453098773956299, "global_step": 610569, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0089125633239746, "global_step": 610570, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9646925926208496, "global_step": 610571, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9286378622055054, "global_step": 610572, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0246036052703857, "global_step": 610573, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.94692862033844, "global_step": 610574, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9790555238723755, "global_step": 610575, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9932857751846313, "global_step": 610576, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.009073257446289, "global_step": 610577, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0535054206848145, "global_step": 610578, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0244693756103516, "global_step": 610579, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.052424430847168, "global_step": 610580, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0032575130462646, "global_step": 610581, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9589283466339111, "global_step": 610582, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9857642650604248, "global_step": 610583, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9597337245941162, "global_step": 610584, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0275120735168457, "global_step": 610585, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0127689838409424, "global_step": 610586, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9688071012496948, "global_step": 610587, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0193541049957275, "global_step": 610588, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0369060039520264, "global_step": 610589, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.043822765350342, "global_step": 610590, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0468010902404785, "global_step": 610591, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0626280307769775, "global_step": 610592, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0611400604248047, "global_step": 610593, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.05098819732666, "global_step": 610594, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.029573917388916, "global_step": 610595, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9892114400863647, "global_step": 610596, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0189743041992188, "global_step": 610597, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9840493202209473, "global_step": 610598, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0018131732940674, "global_step": 610599, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0591273307800293, "global_step": 610600, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0023128986358643, "global_step": 610601, "epoch": 979, "lr": 5e-05}
{"train_loss": 2.0071322917938232, "global_step": 610602, "epoch": 979, "lr": 5e-05}
{"train_loss": 1.9910203218460083, "global_step": 610603, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0573925971984863, "global_step": 610604, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.981710433959961, "global_step": 610605, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.032137870788574, "global_step": 610606, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0890886783599854, "global_step": 610607, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9742424488067627, "global_step": 610608, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0463171005249023, "global_step": 610609, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0742993354797363, "global_step": 610610, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0599558353424072, "global_step": 610611, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9559416770935059, "global_step": 610612, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0019004344940186, "global_step": 610613, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.013180732727051, "global_step": 610614, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0608713626861572, "global_step": 610615, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9843379259109497, "global_step": 610616, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9571365118026733, "global_step": 610617, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.008814573287964, "global_step": 610618, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.055647134780884, "global_step": 610619, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.929159164428711, "global_step": 610620, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0616536140441895, "global_step": 610621, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9166080951690674, "global_step": 610622, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9248301982879639, "global_step": 610623, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9607808589935303, "global_step": 610624, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9639769792556763, "global_step": 610625, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9401171207427979, "global_step": 610626, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0049898624420166, "global_step": 610627, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.966303825378418, "global_step": 610628, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.05954909324646, "global_step": 610629, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9581191539764404, "global_step": 610630, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9415197372436523, "global_step": 610631, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9898368120193481, "global_step": 610632, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0009469985961914, "global_step": 610633, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.017866611480713, "global_step": 610634, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.006208658218384, "global_step": 610635, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9548392295837402, "global_step": 610636, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0608296394348145, "global_step": 610637, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.05857515335083, "global_step": 610638, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9070743322372437, "global_step": 610639, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9703865051269531, "global_step": 610640, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9911352396011353, "global_step": 610641, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9708822965621948, "global_step": 610642, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.11710524559021, "global_step": 610643, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.048815965652466, "global_step": 610644, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0076417922973633, "global_step": 610645, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0278797149658203, "global_step": 610646, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9946080446243286, "global_step": 610647, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.008819341659546, "global_step": 610648, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9540135860443115, "global_step": 610649, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.965888500213623, "global_step": 610650, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9807355403900146, "global_step": 610651, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9336154460906982, "global_step": 610652, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9479725360870361, "global_step": 610653, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.98250412940979, "global_step": 610654, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9705452919006348, "global_step": 610655, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.8786557912826538, "global_step": 610656, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0160443782806396, "global_step": 610657, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9913350343704224, "global_step": 610658, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9629539251327515, "global_step": 610659, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.073441743850708, "global_step": 610660, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0273427963256836, "global_step": 610661, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9874018430709839, "global_step": 610662, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0014805793762207, "global_step": 610663, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9518452882766724, "global_step": 610664, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.915024757385254, "global_step": 610665, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0149385929107666, "global_step": 610666, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9832046031951904, "global_step": 610667, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9433696269989014, "global_step": 610668, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0422070026397705, "global_step": 610669, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.940760612487793, "global_step": 610670, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.038308620452881, "global_step": 610671, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9471876621246338, "global_step": 610672, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0604372024536133, "global_step": 610673, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0252490043640137, "global_step": 610674, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.027157783508301, "global_step": 610675, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0055322647094727, "global_step": 610676, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9935479164123535, "global_step": 610677, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.992734670639038, "global_step": 610678, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9889694452285767, "global_step": 610679, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9512604475021362, "global_step": 610680, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9976807832717896, "global_step": 610681, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.091543674468994, "global_step": 610682, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9538884162902832, "global_step": 610683, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.953800082206726, "global_step": 610684, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.005305528640747, "global_step": 610685, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9467829465866089, "global_step": 610686, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.048757791519165, "global_step": 610687, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0320117473602295, "global_step": 610688, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.006864309310913, "global_step": 610689, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.989188551902771, "global_step": 610690, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.1179120540618896, "global_step": 610691, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9749016761779785, "global_step": 610692, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.010754108428955, "global_step": 610693, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9759407043457031, "global_step": 610694, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9798928499221802, "global_step": 610695, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9879097938537598, "global_step": 610696, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9743380546569824, "global_step": 610697, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0675876140594482, "global_step": 610698, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.934777021408081, "global_step": 610699, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9356852769851685, "global_step": 610700, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0753672122955322, "global_step": 610701, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9910612106323242, "global_step": 610702, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.017707347869873, "global_step": 610703, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9489142894744873, "global_step": 610704, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.026560068130493, "global_step": 610705, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9926142692565918, "global_step": 610706, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9654814004898071, "global_step": 610707, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0018928050994873, "global_step": 610708, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0296504497528076, "global_step": 610709, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0160772800445557, "global_step": 610710, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9554535150527954, "global_step": 610711, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0226480960845947, "global_step": 610712, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9347944259643555, "global_step": 610713, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9906412363052368, "global_step": 610714, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0018086433410645, "global_step": 610715, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0308146476745605, "global_step": 610716, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.01043701171875, "global_step": 610717, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.02714467048645, "global_step": 610718, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9852333068847656, "global_step": 610719, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0331850051879883, "global_step": 610720, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9273481369018555, "global_step": 610721, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9808772802352905, "global_step": 610722, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0271544456481934, "global_step": 610723, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9259992837905884, "global_step": 610724, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9877383708953857, "global_step": 610725, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.040739059448242, "global_step": 610726, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0356082916259766, "global_step": 610727, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9848551750183105, "global_step": 610728, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9673266410827637, "global_step": 610729, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.900761365890503, "global_step": 610730, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.008443832397461, "global_step": 610731, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0396952629089355, "global_step": 610732, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0309231281280518, "global_step": 610733, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9639273881912231, "global_step": 610734, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9911412000656128, "global_step": 610735, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0636253356933594, "global_step": 610736, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0255966186523438, "global_step": 610737, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.004594087600708, "global_step": 610738, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9965347051620483, "global_step": 610739, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.035471200942993, "global_step": 610740, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.1354727745056152, "global_step": 610741, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9750155210494995, "global_step": 610742, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.015761137008667, "global_step": 610743, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.02691650390625, "global_step": 610744, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9637706279754639, "global_step": 610745, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.125044345855713, "global_step": 610746, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9869447946548462, "global_step": 610747, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0758180618286133, "global_step": 610748, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9403713941574097, "global_step": 610749, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9286222457885742, "global_step": 610750, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.015202045440674, "global_step": 610751, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0241496562957764, "global_step": 610752, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9876153469085693, "global_step": 610753, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.040788173675537, "global_step": 610754, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.012892723083496, "global_step": 610755, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9781830310821533, "global_step": 610756, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9320027828216553, "global_step": 610757, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0202596187591553, "global_step": 610758, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9628708362579346, "global_step": 610759, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9979981184005737, "global_step": 610760, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9155213832855225, "global_step": 610761, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0166091918945312, "global_step": 610762, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9990235567092896, "global_step": 610763, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0457985401153564, "global_step": 610764, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.016192674636841, "global_step": 610765, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.021885871887207, "global_step": 610766, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0257434844970703, "global_step": 610767, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.934831142425537, "global_step": 610768, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9725966453552246, "global_step": 610769, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9826955795288086, "global_step": 610770, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9914233684539795, "global_step": 610771, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.021082878112793, "global_step": 610772, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0163872241973877, "global_step": 610773, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9874882698059082, "global_step": 610774, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9168585538864136, "global_step": 610775, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.996012568473816, "global_step": 610776, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9716264009475708, "global_step": 610777, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0363526344299316, "global_step": 610778, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9823148250579834, "global_step": 610779, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0777370929718018, "global_step": 610780, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9517269134521484, "global_step": 610781, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9100593328475952, "global_step": 610782, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.8843075037002563, "global_step": 610783, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0597965717315674, "global_step": 610784, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.980351209640503, "global_step": 610785, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0422494411468506, "global_step": 610786, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9391493797302246, "global_step": 610787, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0417110919952393, "global_step": 610788, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9366774559020996, "global_step": 610789, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0331125259399414, "global_step": 610790, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.8881758451461792, "global_step": 610791, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9922544956207275, "global_step": 610792, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.014098882675171, "global_step": 610793, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.014932155609131, "global_step": 610794, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.005303382873535, "global_step": 610795, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9071704149246216, "global_step": 610796, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0401418209075928, "global_step": 610797, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9892714023590088, "global_step": 610798, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9610674381256104, "global_step": 610799, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9658533334732056, "global_step": 610800, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.051034927368164, "global_step": 610801, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0196468830108643, "global_step": 610802, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0364410877227783, "global_step": 610803, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9589728116989136, "global_step": 610804, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.014540195465088, "global_step": 610805, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.969968557357788, "global_step": 610806, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.051973342895508, "global_step": 610807, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9360699653625488, "global_step": 610808, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9669164419174194, "global_step": 610809, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9916549921035767, "global_step": 610810, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.027768850326538, "global_step": 610811, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9423649311065674, "global_step": 610812, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9196909666061401, "global_step": 610813, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9592117071151733, "global_step": 610814, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.026017189025879, "global_step": 610815, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9882615804672241, "global_step": 610816, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0921101570129395, "global_step": 610817, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9365980625152588, "global_step": 610818, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0444798469543457, "global_step": 610819, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.984783411026001, "global_step": 610820, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0508577823638916, "global_step": 610821, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0348758697509766, "global_step": 610822, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0697906017303467, "global_step": 610823, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.929610013961792, "global_step": 610824, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0326719284057617, "global_step": 610825, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9524471759796143, "global_step": 610826, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.898821473121643, "global_step": 610827, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.934053659439087, "global_step": 610828, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0774521827697754, "global_step": 610829, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.059131145477295, "global_step": 610830, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.064671516418457, "global_step": 610831, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0127577781677246, "global_step": 610832, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0183093547821045, "global_step": 610833, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9895823001861572, "global_step": 610834, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0963385105133057, "global_step": 610835, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9283289909362793, "global_step": 610836, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9927550554275513, "global_step": 610837, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0631680488586426, "global_step": 610838, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9787566661834717, "global_step": 610839, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.011915922164917, "global_step": 610840, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.954475998878479, "global_step": 610841, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0142245292663574, "global_step": 610842, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.010820150375366, "global_step": 610843, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.906250238418579, "global_step": 610844, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9670010805130005, "global_step": 610845, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9725055694580078, "global_step": 610846, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0808305740356445, "global_step": 610847, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.1086466312408447, "global_step": 610848, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0624847412109375, "global_step": 610849, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.98026704788208, "global_step": 610850, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.918426513671875, "global_step": 610851, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.085582733154297, "global_step": 610852, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9893019199371338, "global_step": 610853, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9506607055664062, "global_step": 610854, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0113461017608643, "global_step": 610855, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9744635820388794, "global_step": 610856, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.8832287788391113, "global_step": 610857, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9933769702911377, "global_step": 610858, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9850739240646362, "global_step": 610859, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0114378929138184, "global_step": 610860, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.009328842163086, "global_step": 610861, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.989325761795044, "global_step": 610862, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9279181957244873, "global_step": 610863, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9743398427963257, "global_step": 610864, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.027973175048828, "global_step": 610865, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.002890110015869, "global_step": 610866, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9800373315811157, "global_step": 610867, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.059809446334839, "global_step": 610868, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0265936851501465, "global_step": 610869, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9371105432510376, "global_step": 610870, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9259545803070068, "global_step": 610871, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0097830295562744, "global_step": 610872, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9304770231246948, "global_step": 610873, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0281636714935303, "global_step": 610874, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9686325788497925, "global_step": 610875, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.003074884414673, "global_step": 610876, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.009361505508423, "global_step": 610877, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9971641302108765, "global_step": 610878, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.06666898727417, "global_step": 610879, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9722144603729248, "global_step": 610880, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0650506019592285, "global_step": 610881, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0560128688812256, "global_step": 610882, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.066828727722168, "global_step": 610883, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.030261993408203, "global_step": 610884, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.038381338119507, "global_step": 610885, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0022687911987305, "global_step": 610886, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.021238327026367, "global_step": 610887, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0678513050079346, "global_step": 610888, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0122835636138916, "global_step": 610889, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0303268432617188, "global_step": 610890, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9622527360916138, "global_step": 610891, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0491063594818115, "global_step": 610892, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0473504066467285, "global_step": 610893, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9741673469543457, "global_step": 610894, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9781783819198608, "global_step": 610895, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9990627765655518, "global_step": 610896, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9798290729522705, "global_step": 610897, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9757832288742065, "global_step": 610898, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0275182723999023, "global_step": 610899, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.968559741973877, "global_step": 610900, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.055825710296631, "global_step": 610901, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.07072377204895, "global_step": 610902, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9211782217025757, "global_step": 610903, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9750665426254272, "global_step": 610904, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.038198232650757, "global_step": 610905, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0042059421539307, "global_step": 610906, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0253288745880127, "global_step": 610907, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.015872001647949, "global_step": 610908, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0774526596069336, "global_step": 610909, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.032135486602783, "global_step": 610910, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.072143077850342, "global_step": 610911, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0176172256469727, "global_step": 610912, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9220865964889526, "global_step": 610913, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.960770606994629, "global_step": 610914, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9394497871398926, "global_step": 610915, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.036665916442871, "global_step": 610916, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.1122827529907227, "global_step": 610917, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9704828262329102, "global_step": 610918, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0020549297332764, "global_step": 610919, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.021550178527832, "global_step": 610920, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9344165325164795, "global_step": 610921, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.056694269180298, "global_step": 610922, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.015650749206543, "global_step": 610923, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.040705680847168, "global_step": 610924, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.94941246509552, "global_step": 610925, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9536799192428589, "global_step": 610926, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9907031059265137, "global_step": 610927, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.132915496826172, "global_step": 610928, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.073631525039673, "global_step": 610929, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.997087001800537, "global_step": 610930, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0354957580566406, "global_step": 610931, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.017125129699707, "global_step": 610932, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.060732126235962, "global_step": 610933, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9785399436950684, "global_step": 610934, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.014192581176758, "global_step": 610935, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0778379440307617, "global_step": 610936, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.003894805908203, "global_step": 610937, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0561764240264893, "global_step": 610938, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0348005294799805, "global_step": 610939, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0438005924224854, "global_step": 610940, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0267810821533203, "global_step": 610941, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.04707407951355, "global_step": 610942, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.1058080196380615, "global_step": 610943, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0709378719329834, "global_step": 610944, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0418777465820312, "global_step": 610945, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.96016526222229, "global_step": 610946, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0146305561065674, "global_step": 610947, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0786118507385254, "global_step": 610948, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9319418668746948, "global_step": 610949, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.019266128540039, "global_step": 610950, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9904601573944092, "global_step": 610951, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.929491400718689, "global_step": 610952, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9950571060180664, "global_step": 610953, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0365262031555176, "global_step": 610954, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9648224115371704, "global_step": 610955, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.949209213256836, "global_step": 610956, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0565364360809326, "global_step": 610957, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9078372716903687, "global_step": 610958, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.108935832977295, "global_step": 610959, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9502894878387451, "global_step": 610960, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.981501579284668, "global_step": 610961, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.059943199157715, "global_step": 610962, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0658724308013916, "global_step": 610963, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9889545440673828, "global_step": 610964, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0301032066345215, "global_step": 610965, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0316834449768066, "global_step": 610966, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0417282581329346, "global_step": 610967, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.030167579650879, "global_step": 610968, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0535194873809814, "global_step": 610969, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0303304195404053, "global_step": 610970, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0519258975982666, "global_step": 610971, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.017550230026245, "global_step": 610972, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.02382230758667, "global_step": 610973, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0611376762390137, "global_step": 610974, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9908559322357178, "global_step": 610975, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9985584020614624, "global_step": 610976, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.050766944885254, "global_step": 610977, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9610240459442139, "global_step": 610978, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9630144834518433, "global_step": 610979, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9606523513793945, "global_step": 610980, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.046377182006836, "global_step": 610981, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0048511028289795, "global_step": 610982, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.932078242301941, "global_step": 610983, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9551074504852295, "global_step": 610984, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0358307361602783, "global_step": 610985, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.018313407897949, "global_step": 610986, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9652622938156128, "global_step": 610987, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9691722393035889, "global_step": 610988, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0141608715057373, "global_step": 610989, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9500627517700195, "global_step": 610990, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.084453821182251, "global_step": 610991, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.019918441772461, "global_step": 610992, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.922625184059143, "global_step": 610993, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9637295007705688, "global_step": 610994, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0009214878082275, "global_step": 610995, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9823824167251587, "global_step": 610996, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9904775619506836, "global_step": 610997, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0138747692108154, "global_step": 610998, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0342390537261963, "global_step": 610999, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.92270028591156, "global_step": 611000, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.030965566635132, "global_step": 611001, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.975834608078003, "global_step": 611002, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0034067630767822, "global_step": 611003, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0496835708618164, "global_step": 611004, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.048952579498291, "global_step": 611005, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0226051807403564, "global_step": 611006, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0357818603515625, "global_step": 611007, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.079822540283203, "global_step": 611008, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.091129779815674, "global_step": 611009, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.01822829246521, "global_step": 611010, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.034557819366455, "global_step": 611011, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9389036893844604, "global_step": 611012, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.006047487258911, "global_step": 611013, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0003252029418945, "global_step": 611014, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.8870129585266113, "global_step": 611015, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.001530170440674, "global_step": 611016, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9791324138641357, "global_step": 611017, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.029843330383301, "global_step": 611018, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9920724630355835, "global_step": 611019, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.01314115524292, "global_step": 611020, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9760364294052124, "global_step": 611021, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.004931688308716, "global_step": 611022, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.017327308654785, "global_step": 611023, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9897291660308838, "global_step": 611024, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0636065006256104, "global_step": 611025, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.038376569747925, "global_step": 611026, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9678951501846313, "global_step": 611027, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9818284511566162, "global_step": 611028, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.080702543258667, "global_step": 611029, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.03143048286438, "global_step": 611030, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.026785135269165, "global_step": 611031, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9952400922775269, "global_step": 611032, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0360450744628906, "global_step": 611033, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.993170976638794, "global_step": 611034, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.02028489112854, "global_step": 611035, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0946877002716064, "global_step": 611036, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0039854049682617, "global_step": 611037, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.056563138961792, "global_step": 611038, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9920846223831177, "global_step": 611039, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0604543685913086, "global_step": 611040, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.01006817817688, "global_step": 611041, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.8905797004699707, "global_step": 611042, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9790230989456177, "global_step": 611043, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0436928272247314, "global_step": 611044, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.08465576171875, "global_step": 611045, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0784237384796143, "global_step": 611046, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0389835834503174, "global_step": 611047, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0181448459625244, "global_step": 611048, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.1035003662109375, "global_step": 611049, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0481348037719727, "global_step": 611050, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.075390100479126, "global_step": 611051, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9571129083633423, "global_step": 611052, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9860620498657227, "global_step": 611053, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.013319969177246, "global_step": 611054, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.934006929397583, "global_step": 611055, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.036931037902832, "global_step": 611056, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0671050548553467, "global_step": 611057, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.104121208190918, "global_step": 611058, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0997209548950195, "global_step": 611059, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9839494228363037, "global_step": 611060, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.067707061767578, "global_step": 611061, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9785983562469482, "global_step": 611062, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9777960777282715, "global_step": 611063, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9330408573150635, "global_step": 611064, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.028240919113159, "global_step": 611065, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0429062843322754, "global_step": 611066, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0595216751098633, "global_step": 611067, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9650729894638062, "global_step": 611068, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9936803579330444, "global_step": 611069, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0432016849517822, "global_step": 611070, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9979897737503052, "global_step": 611071, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.989019751548767, "global_step": 611072, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.1350810527801514, "global_step": 611073, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9202890396118164, "global_step": 611074, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.044032096862793, "global_step": 611075, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.145704984664917, "global_step": 611076, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.032599925994873, "global_step": 611077, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.949242115020752, "global_step": 611078, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9555658102035522, "global_step": 611079, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9950542449951172, "global_step": 611080, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9984080791473389, "global_step": 611081, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.047881603240967, "global_step": 611082, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.045642614364624, "global_step": 611083, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9972087144851685, "global_step": 611084, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9637330770492554, "global_step": 611085, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.036308765411377, "global_step": 611086, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0541350841522217, "global_step": 611087, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.003632068634033, "global_step": 611088, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0302846431732178, "global_step": 611089, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9664183855056763, "global_step": 611090, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.994844675064087, "global_step": 611091, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0161867141723633, "global_step": 611092, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.099424362182617, "global_step": 611093, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0270259380340576, "global_step": 611094, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9436967372894287, "global_step": 611095, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9981987476348877, "global_step": 611096, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0478134155273438, "global_step": 611097, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0725183486938477, "global_step": 611098, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.926163911819458, "global_step": 611099, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9874881505966187, "global_step": 611100, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.1089999675750732, "global_step": 611101, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9762873649597168, "global_step": 611102, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.994823694229126, "global_step": 611103, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9924919605255127, "global_step": 611104, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9882022142410278, "global_step": 611105, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9622678756713867, "global_step": 611106, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0611724853515625, "global_step": 611107, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.054001569747925, "global_step": 611108, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0549509525299072, "global_step": 611109, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0187151432037354, "global_step": 611110, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.072039842605591, "global_step": 611111, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0627567768096924, "global_step": 611112, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0095722675323486, "global_step": 611113, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0202691555023193, "global_step": 611114, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0117204189300537, "global_step": 611115, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9565092325210571, "global_step": 611116, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0413291454315186, "global_step": 611117, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.07590913772583, "global_step": 611118, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0330395698547363, "global_step": 611119, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9270095825195312, "global_step": 611120, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9826241731643677, "global_step": 611121, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9572632312774658, "global_step": 611122, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.031949043273926, "global_step": 611123, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0318455696105957, "global_step": 611124, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.053391695022583, "global_step": 611125, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.110513687133789, "global_step": 611126, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.970618486404419, "global_step": 611127, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9942636489868164, "global_step": 611128, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.066343069076538, "global_step": 611129, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9981623888015747, "global_step": 611130, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9919523000717163, "global_step": 611131, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9006510972976685, "global_step": 611132, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.959789752960205, "global_step": 611133, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0546061992645264, "global_step": 611134, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.023286819458008, "global_step": 611135, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.047245740890503, "global_step": 611136, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0122780799865723, "global_step": 611137, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.986274003982544, "global_step": 611138, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.03096604347229, "global_step": 611139, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.984578013420105, "global_step": 611140, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9754388332366943, "global_step": 611141, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9994012117385864, "global_step": 611142, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0302975177764893, "global_step": 611143, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.912832498550415, "global_step": 611144, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.932880163192749, "global_step": 611145, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9527851343154907, "global_step": 611146, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9664876461029053, "global_step": 611147, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9687732458114624, "global_step": 611148, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0147533416748047, "global_step": 611149, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0658068656921387, "global_step": 611150, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0179500579833984, "global_step": 611151, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9434664249420166, "global_step": 611152, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.1062564849853516, "global_step": 611153, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.983640193939209, "global_step": 611154, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9753972291946411, "global_step": 611155, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9605718851089478, "global_step": 611156, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9747819900512695, "global_step": 611157, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0418930053710938, "global_step": 611158, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0682756900787354, "global_step": 611159, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9608514308929443, "global_step": 611160, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0909671783447266, "global_step": 611161, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0132246017456055, "global_step": 611162, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9999897480010986, "global_step": 611163, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.052586317062378, "global_step": 611164, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0065979957580566, "global_step": 611165, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9349220991134644, "global_step": 611166, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.045572519302368, "global_step": 611167, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0265564918518066, "global_step": 611168, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.973179817199707, "global_step": 611169, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0244808197021484, "global_step": 611170, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0381217002868652, "global_step": 611171, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9650546312332153, "global_step": 611172, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9991376399993896, "global_step": 611173, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.071749687194824, "global_step": 611174, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9146777391433716, "global_step": 611175, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9993807077407837, "global_step": 611176, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0325536727905273, "global_step": 611177, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9308584928512573, "global_step": 611178, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.023451089859009, "global_step": 611179, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9941147565841675, "global_step": 611180, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0697989463806152, "global_step": 611181, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0039315223693848, "global_step": 611182, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0143489837646484, "global_step": 611183, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0692317485809326, "global_step": 611184, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.943697452545166, "global_step": 611185, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.060979127883911, "global_step": 611186, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.999956727027893, "global_step": 611187, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9529337882995605, "global_step": 611188, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9914500713348389, "global_step": 611189, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9270039796829224, "global_step": 611190, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0444071292877197, "global_step": 611191, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9972126483917236, "global_step": 611192, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0371201038360596, "global_step": 611193, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.034836530685425, "global_step": 611194, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9436938762664795, "global_step": 611195, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9964194297790527, "global_step": 611196, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9635452032089233, "global_step": 611197, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0679707527160645, "global_step": 611198, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0651466846466064, "global_step": 611199, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9865351915359497, "global_step": 611200, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.011500120162964, "global_step": 611201, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9466575384140015, "global_step": 611202, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.009063720703125, "global_step": 611203, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.990272879600525, "global_step": 611204, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.039806365966797, "global_step": 611205, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9491983652114868, "global_step": 611206, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.036083459854126, "global_step": 611207, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9882302284240723, "global_step": 611208, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9784733057022095, "global_step": 611209, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9752637147903442, "global_step": 611210, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9487420320510864, "global_step": 611211, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.919152021408081, "global_step": 611212, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0208027362823486, "global_step": 611213, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9605224132537842, "global_step": 611214, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9862966537475586, "global_step": 611215, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9364124536514282, "global_step": 611216, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9112365245819092, "global_step": 611217, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9376094341278076, "global_step": 611218, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9861948490142822, "global_step": 611219, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.999080777168274, "global_step": 611220, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9844372272491455, "global_step": 611221, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0382652282714844, "global_step": 611222, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9967734813690186, "global_step": 611223, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9301923513412476, "global_step": 611224, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.062647819519043, "global_step": 611225, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0305633544921875, "global_step": 611226, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9837738275527954, "global_step": 611227, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.079894781112671, "global_step": 611228, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9938898086547852, "global_step": 611229, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.035414695739746, "global_step": 611230, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9525771141052246, "global_step": 611231, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0430853366851807, "global_step": 611232, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.035710573196411, "global_step": 611233, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0256433486938477, "global_step": 611234, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9580674171447754, "global_step": 611235, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0476973056793213, "global_step": 611236, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.054780960083008, "global_step": 611237, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0269813537597656, "global_step": 611238, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9536833763122559, "global_step": 611239, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9703372716903687, "global_step": 611240, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.055769920349121, "global_step": 611241, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.935819149017334, "global_step": 611242, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9911998510360718, "global_step": 611243, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.1314456462860107, "global_step": 611244, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.999914526939392, "global_step": 611245, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0144240856170654, "global_step": 611246, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0954384803771973, "global_step": 611247, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9766160249710083, "global_step": 611248, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.963477611541748, "global_step": 611249, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0416996479034424, "global_step": 611250, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.930708408355713, "global_step": 611251, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9705283641815186, "global_step": 611252, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.1178619861602783, "global_step": 611253, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9590119123458862, "global_step": 611254, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9310128688812256, "global_step": 611255, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0856969356536865, "global_step": 611256, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.039454221725464, "global_step": 611257, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.990885615348816, "global_step": 611258, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9278326034545898, "global_step": 611259, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.944485068321228, "global_step": 611260, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0849835872650146, "global_step": 611261, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.020765542984009, "global_step": 611262, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.001323938369751, "global_step": 611263, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9924430847167969, "global_step": 611264, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0294747352600098, "global_step": 611265, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9316446781158447, "global_step": 611266, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.089107036590576, "global_step": 611267, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.027588367462158, "global_step": 611268, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.917077898979187, "global_step": 611269, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0593762397766113, "global_step": 611270, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.073575258255005, "global_step": 611271, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0563008785247803, "global_step": 611272, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0984132289886475, "global_step": 611273, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9941149950027466, "global_step": 611274, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.949247121810913, "global_step": 611275, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0168302059173584, "global_step": 611276, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.065498113632202, "global_step": 611277, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0422749519348145, "global_step": 611278, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.081749677658081, "global_step": 611279, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9682388305664062, "global_step": 611280, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0101165771484375, "global_step": 611281, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9551713466644287, "global_step": 611282, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.000397205352783, "global_step": 611283, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.054741382598877, "global_step": 611284, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.003045082092285, "global_step": 611285, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9834916591644287, "global_step": 611286, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0407357215881348, "global_step": 611287, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9423837661743164, "global_step": 611288, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9106944799423218, "global_step": 611289, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0741610527038574, "global_step": 611290, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9329746961593628, "global_step": 611291, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.061753273010254, "global_step": 611292, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.004244327545166, "global_step": 611293, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.012822389602661, "global_step": 611294, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9967612028121948, "global_step": 611295, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.941508412361145, "global_step": 611296, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.026456832885742, "global_step": 611297, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.008819818496704, "global_step": 611298, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9182218313217163, "global_step": 611299, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.094111442565918, "global_step": 611300, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9463287591934204, "global_step": 611301, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.027708053588867, "global_step": 611302, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9671775102615356, "global_step": 611303, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0380566120147705, "global_step": 611304, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9215917587280273, "global_step": 611305, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9671427011489868, "global_step": 611306, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.070775270462036, "global_step": 611307, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9663035869598389, "global_step": 611308, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.015803813934326, "global_step": 611309, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0049190521240234, "global_step": 611310, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9866833686828613, "global_step": 611311, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9780361652374268, "global_step": 611312, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0651695728302, "global_step": 611313, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.048143148422241, "global_step": 611314, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0358855724334717, "global_step": 611315, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9469094276428223, "global_step": 611316, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0288596153259277, "global_step": 611317, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0813937187194824, "global_step": 611318, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.004533529281616, "global_step": 611319, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0061991214752197, "global_step": 611320, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0203652381896973, "global_step": 611321, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.960378646850586, "global_step": 611322, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9478051662445068, "global_step": 611323, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9319519996643066, "global_step": 611324, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.023601770401001, "global_step": 611325, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0365679264068604, "global_step": 611326, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0525548458099365, "global_step": 611327, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0762391090393066, "global_step": 611328, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9454530477523804, "global_step": 611329, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0545156002044678, "global_step": 611330, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9566465616226196, "global_step": 611331, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.8966448307037354, "global_step": 611332, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0797317028045654, "global_step": 611333, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0150351524353027, "global_step": 611334, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.049084424972534, "global_step": 611335, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9360026121139526, "global_step": 611336, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9589298963546753, "global_step": 611337, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0292391777038574, "global_step": 611338, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.06973934173584, "global_step": 611339, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.085814952850342, "global_step": 611340, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.001634359359741, "global_step": 611341, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.086893081665039, "global_step": 611342, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9792126417160034, "global_step": 611343, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9343945980072021, "global_step": 611344, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9908860921859741, "global_step": 611345, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.059748888015747, "global_step": 611346, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.970961093902588, "global_step": 611347, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9919525384902954, "global_step": 611348, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9840492010116577, "global_step": 611349, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9925683736801147, "global_step": 611350, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.990186095237732, "global_step": 611351, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9644267559051514, "global_step": 611352, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0687761306762695, "global_step": 611353, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9061229228973389, "global_step": 611354, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0744283199310303, "global_step": 611355, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9822266101837158, "global_step": 611356, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.040945053100586, "global_step": 611357, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0651519298553467, "global_step": 611358, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0325489044189453, "global_step": 611359, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9974969625473022, "global_step": 611360, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9184459447860718, "global_step": 611361, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.1139256954193115, "global_step": 611362, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0413742065429688, "global_step": 611363, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9480512142181396, "global_step": 611364, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.004366159439087, "global_step": 611365, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0175843238830566, "global_step": 611366, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9711214303970337, "global_step": 611367, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.008232593536377, "global_step": 611368, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0874927043914795, "global_step": 611369, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.022725820541382, "global_step": 611370, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.018691062927246, "global_step": 611371, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9240450859069824, "global_step": 611372, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.035499095916748, "global_step": 611373, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.010956048965454, "global_step": 611374, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9499447345733643, "global_step": 611375, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9850527048110962, "global_step": 611376, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0437543392181396, "global_step": 611377, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0296554565429688, "global_step": 611378, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9836753606796265, "global_step": 611379, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.081395387649536, "global_step": 611380, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0050816535949707, "global_step": 611381, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9943960905075073, "global_step": 611382, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0673916339874268, "global_step": 611383, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0953402519226074, "global_step": 611384, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9392814636230469, "global_step": 611385, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0288124084472656, "global_step": 611386, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9862430095672607, "global_step": 611387, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.108527421951294, "global_step": 611388, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.1023733615875244, "global_step": 611389, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9188276529312134, "global_step": 611390, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9968479871749878, "global_step": 611391, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.994271993637085, "global_step": 611392, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9953607320785522, "global_step": 611393, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.998784065246582, "global_step": 611394, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0085158348083496, "global_step": 611395, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9865186214447021, "global_step": 611396, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0373332500457764, "global_step": 611397, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0001890659332275, "global_step": 611398, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0306551456451416, "global_step": 611399, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.035118818283081, "global_step": 611400, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9676628112792969, "global_step": 611401, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.977726697921753, "global_step": 611402, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9729832410812378, "global_step": 611403, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.937916874885559, "global_step": 611404, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0630605220794678, "global_step": 611405, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.024852991104126, "global_step": 611406, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.972703218460083, "global_step": 611407, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.004035711288452, "global_step": 611408, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.8695911169052124, "global_step": 611409, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.990095853805542, "global_step": 611410, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9846702814102173, "global_step": 611411, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0264062881469727, "global_step": 611412, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.952546238899231, "global_step": 611413, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0693013668060303, "global_step": 611414, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0857512950897217, "global_step": 611415, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0094921588897705, "global_step": 611416, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.912047028541565, "global_step": 611417, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.015028238296509, "global_step": 611418, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.006948709487915, "global_step": 611419, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9926769733428955, "global_step": 611420, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.045534133911133, "global_step": 611421, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9956473112106323, "global_step": 611422, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.977360486984253, "global_step": 611423, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9404281377792358, "global_step": 611424, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9752418994903564, "global_step": 611425, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0372848510742188, "global_step": 611426, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.029569387435913, "global_step": 611427, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0063962936401367, "global_step": 611428, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0855376720428467, "global_step": 611429, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0514698028564453, "global_step": 611430, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0161101818084717, "global_step": 611431, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9633315801620483, "global_step": 611432, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.051549196243286, "global_step": 611433, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.977513074874878, "global_step": 611434, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.029592275619507, "global_step": 611435, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9489034414291382, "global_step": 611436, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0040698051452637, "global_step": 611437, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.971941351890564, "global_step": 611438, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.032975673675537, "global_step": 611439, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9283854961395264, "global_step": 611440, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9476507902145386, "global_step": 611441, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.098370313644409, "global_step": 611442, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0383214950561523, "global_step": 611443, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0031580924987793, "global_step": 611444, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.028823137283325, "global_step": 611445, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0004091262817383, "global_step": 611446, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0003204345703125, "global_step": 611447, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.024998664855957, "global_step": 611448, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0753769874572754, "global_step": 611449, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9871633052825928, "global_step": 611450, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0894293785095215, "global_step": 611451, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.972456932067871, "global_step": 611452, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.055666208267212, "global_step": 611453, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9355545043945312, "global_step": 611454, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0357978343963623, "global_step": 611455, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0878283977508545, "global_step": 611456, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0334315299987793, "global_step": 611457, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9823607206344604, "global_step": 611458, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9125312566757202, "global_step": 611459, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0328333377838135, "global_step": 611460, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0401523113250732, "global_step": 611461, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9960118532180786, "global_step": 611462, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.964644432067871, "global_step": 611463, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.929782748222351, "global_step": 611464, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.034255266189575, "global_step": 611465, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9902174472808838, "global_step": 611466, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9500722885131836, "global_step": 611467, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.098661184310913, "global_step": 611468, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9764609336853027, "global_step": 611469, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9498087167739868, "global_step": 611470, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0703415870666504, "global_step": 611471, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.021821975708008, "global_step": 611472, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.953829050064087, "global_step": 611473, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.086393117904663, "global_step": 611474, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0748178958892822, "global_step": 611475, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.985979437828064, "global_step": 611476, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.1237194538116455, "global_step": 611477, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.012059450149536, "global_step": 611478, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0278730392456055, "global_step": 611479, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9892237186431885, "global_step": 611480, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9760382175445557, "global_step": 611481, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0303030014038086, "global_step": 611482, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.99593985080719, "global_step": 611483, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9405783414840698, "global_step": 611484, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9498599767684937, "global_step": 611485, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0372817516326904, "global_step": 611486, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.1212575435638428, "global_step": 611487, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9748173952102661, "global_step": 611488, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.966362714767456, "global_step": 611489, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0471508502960205, "global_step": 611490, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.057101011276245, "global_step": 611491, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.029658317565918, "global_step": 611492, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9889039993286133, "global_step": 611493, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9977341890335083, "global_step": 611494, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.057354688644409, "global_step": 611495, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0670204162597656, "global_step": 611496, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.041975259780884, "global_step": 611497, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0919365882873535, "global_step": 611498, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0209500789642334, "global_step": 611499, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9603831768035889, "global_step": 611500, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0376720428466797, "global_step": 611501, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9720784425735474, "global_step": 611502, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.007514715194702, "global_step": 611503, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.007190704345703, "global_step": 611504, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0897250175476074, "global_step": 611505, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.8999676704406738, "global_step": 611506, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.952717900276184, "global_step": 611507, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0348901748657227, "global_step": 611508, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.096432685852051, "global_step": 611509, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0213253498077393, "global_step": 611510, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.01688551902771, "global_step": 611511, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9630786180496216, "global_step": 611512, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.057033061981201, "global_step": 611513, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.1174211502075195, "global_step": 611514, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.164630889892578, "global_step": 611515, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9368449449539185, "global_step": 611516, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0733442306518555, "global_step": 611517, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9958044290542603, "global_step": 611518, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0191173553466797, "global_step": 611519, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9951180219650269, "global_step": 611520, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0747671127319336, "global_step": 611521, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9693771600723267, "global_step": 611522, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0164742469787598, "global_step": 611523, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0076780319213867, "global_step": 611524, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0305874347686768, "global_step": 611525, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.051584482192993, "global_step": 611526, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.017024040222168, "global_step": 611527, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.017272710800171, "global_step": 611528, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0417678356170654, "global_step": 611529, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.068516254425049, "global_step": 611530, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.003842830657959, "global_step": 611531, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0217971801757812, "global_step": 611532, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9371165037155151, "global_step": 611533, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9435932636260986, "global_step": 611534, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9732508659362793, "global_step": 611535, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0108840465545654, "global_step": 611536, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9329756498336792, "global_step": 611537, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.063960075378418, "global_step": 611538, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0480775833129883, "global_step": 611539, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0437517166137695, "global_step": 611540, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0386533737182617, "global_step": 611541, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0150461196899414, "global_step": 611542, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.030468702316284, "global_step": 611543, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0037455558776855, "global_step": 611544, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0273239612579346, "global_step": 611545, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9679571390151978, "global_step": 611546, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9660825729370117, "global_step": 611547, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.071878433227539, "global_step": 611548, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9640411138534546, "global_step": 611549, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.060345411300659, "global_step": 611550, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.08463191986084, "global_step": 611551, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9987390041351318, "global_step": 611552, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.936075210571289, "global_step": 611553, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9674996137619019, "global_step": 611554, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.005868911743164, "global_step": 611555, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.99490225315094, "global_step": 611556, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9838162660598755, "global_step": 611557, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9434040784835815, "global_step": 611558, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9915781021118164, "global_step": 611559, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.032485008239746, "global_step": 611560, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.034999370574951, "global_step": 611561, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0636916160583496, "global_step": 611562, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0477826595306396, "global_step": 611563, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.000730037689209, "global_step": 611564, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9780142307281494, "global_step": 611565, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0346298217773438, "global_step": 611566, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9459441900253296, "global_step": 611567, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.055781841278076, "global_step": 611568, "epoch": 980, "lr": 5e-05}
{"train_loss": 1.9585570096969604, "global_step": 611569, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0277280807495117, "global_step": 611570, "epoch": 980, "lr": 5e-05}
{"train_loss": 2.0061564445495605, "global_step": 611571, "epoch": 980, "lr": 5e-05, "val_loss": 5.808138847351074, "test_reconst_mse": 0.07379033416509628}
{"train_loss": 2.074272394180298, "global_step": 611572, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.97018563747406, "global_step": 611573, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0994839668273926, "global_step": 611574, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.029484748840332, "global_step": 611575, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0062310695648193, "global_step": 611576, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0456244945526123, "global_step": 611577, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0082650184631348, "global_step": 611578, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.914027452468872, "global_step": 611579, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0250213146209717, "global_step": 611580, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0324432849884033, "global_step": 611581, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.00498366355896, "global_step": 611582, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9206231832504272, "global_step": 611583, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.948328971862793, "global_step": 611584, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9560776948928833, "global_step": 611585, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9358415603637695, "global_step": 611586, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0730903148651123, "global_step": 611587, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9382485151290894, "global_step": 611588, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9607700109481812, "global_step": 611589, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9435292482376099, "global_step": 611590, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9584300518035889, "global_step": 611591, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9666390419006348, "global_step": 611592, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.15045428276062, "global_step": 611593, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9507099390029907, "global_step": 611594, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9957084655761719, "global_step": 611595, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.025857448577881, "global_step": 611596, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0387918949127197, "global_step": 611597, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0141255855560303, "global_step": 611598, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.058043956756592, "global_step": 611599, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9767403602600098, "global_step": 611600, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0421900749206543, "global_step": 611601, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9835201501846313, "global_step": 611602, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9555928707122803, "global_step": 611603, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0738017559051514, "global_step": 611604, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.1127490997314453, "global_step": 611605, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.958709955215454, "global_step": 611606, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9411851167678833, "global_step": 611607, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.023181676864624, "global_step": 611608, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0003933906555176, "global_step": 611609, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9121702909469604, "global_step": 611610, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0433037281036377, "global_step": 611611, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9962539672851562, "global_step": 611612, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.026951313018799, "global_step": 611613, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9690358638763428, "global_step": 611614, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9514753818511963, "global_step": 611615, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0018277168273926, "global_step": 611616, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9865391254425049, "global_step": 611617, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9626705646514893, "global_step": 611618, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0592358112335205, "global_step": 611619, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.018725872039795, "global_step": 611620, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0119102001190186, "global_step": 611621, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9478398561477661, "global_step": 611622, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.045772075653076, "global_step": 611623, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0914647579193115, "global_step": 611624, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.942821741104126, "global_step": 611625, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.996815800666809, "global_step": 611626, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0682647228240967, "global_step": 611627, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0312118530273438, "global_step": 611628, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.015989303588867, "global_step": 611629, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.01301646232605, "global_step": 611630, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0372135639190674, "global_step": 611631, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0480635166168213, "global_step": 611632, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0262813568115234, "global_step": 611633, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.99623703956604, "global_step": 611634, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9464055299758911, "global_step": 611635, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0835390090942383, "global_step": 611636, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9707189798355103, "global_step": 611637, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.105344533920288, "global_step": 611638, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9901676177978516, "global_step": 611639, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.004133462905884, "global_step": 611640, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0200297832489014, "global_step": 611641, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9705390930175781, "global_step": 611642, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0670642852783203, "global_step": 611643, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0773203372955322, "global_step": 611644, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9527373313903809, "global_step": 611645, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.1164138317108154, "global_step": 611646, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.00927472114563, "global_step": 611647, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.033879041671753, "global_step": 611648, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9730933904647827, "global_step": 611649, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9950824975967407, "global_step": 611650, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9395906925201416, "global_step": 611651, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9521790742874146, "global_step": 611652, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9999206066131592, "global_step": 611653, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0757710933685303, "global_step": 611654, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.000560760498047, "global_step": 611655, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.988188624382019, "global_step": 611656, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.049808979034424, "global_step": 611657, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0779359340667725, "global_step": 611658, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0698065757751465, "global_step": 611659, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.991096019744873, "global_step": 611660, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0019454956054688, "global_step": 611661, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9614651203155518, "global_step": 611662, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0183889865875244, "global_step": 611663, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9539238214492798, "global_step": 611664, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0055272579193115, "global_step": 611665, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9687727689743042, "global_step": 611666, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9637454748153687, "global_step": 611667, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9644643068313599, "global_step": 611668, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0089828968048096, "global_step": 611669, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0397756099700928, "global_step": 611670, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.993834137916565, "global_step": 611671, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9879326820373535, "global_step": 611672, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0351955890655518, "global_step": 611673, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9634430408477783, "global_step": 611674, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.024280309677124, "global_step": 611675, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9672982692718506, "global_step": 611676, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.973435878753662, "global_step": 611677, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9677246809005737, "global_step": 611678, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.042987823486328, "global_step": 611679, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.012944221496582, "global_step": 611680, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9858031272888184, "global_step": 611681, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.025749921798706, "global_step": 611682, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0530874729156494, "global_step": 611683, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.04036808013916, "global_step": 611684, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.986605167388916, "global_step": 611685, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.015516996383667, "global_step": 611686, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9328325986862183, "global_step": 611687, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.963671088218689, "global_step": 611688, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.053182363510132, "global_step": 611689, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0054008960723877, "global_step": 611690, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.97052001953125, "global_step": 611691, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.010779619216919, "global_step": 611692, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.961155652999878, "global_step": 611693, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.030799388885498, "global_step": 611694, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0266542434692383, "global_step": 611695, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0274412631988525, "global_step": 611696, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.011935234069824, "global_step": 611697, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0085055828094482, "global_step": 611698, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9530692100524902, "global_step": 611699, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9999775886535645, "global_step": 611700, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9636150598526, "global_step": 611701, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9518731832504272, "global_step": 611702, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0906734466552734, "global_step": 611703, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0809805393218994, "global_step": 611704, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9912331104278564, "global_step": 611705, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0200328826904297, "global_step": 611706, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0237789154052734, "global_step": 611707, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.036268472671509, "global_step": 611708, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9384011030197144, "global_step": 611709, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9825327396392822, "global_step": 611710, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9294097423553467, "global_step": 611711, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.024629592895508, "global_step": 611712, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0251986980438232, "global_step": 611713, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0016655921936035, "global_step": 611714, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.038342237472534, "global_step": 611715, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0573651790618896, "global_step": 611716, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.016815185546875, "global_step": 611717, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9051905870437622, "global_step": 611718, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0163333415985107, "global_step": 611719, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9248638153076172, "global_step": 611720, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.050995349884033, "global_step": 611721, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0513947010040283, "global_step": 611722, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0933308601379395, "global_step": 611723, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0115058422088623, "global_step": 611724, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9905807971954346, "global_step": 611725, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9560779333114624, "global_step": 611726, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9655389785766602, "global_step": 611727, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.043224334716797, "global_step": 611728, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9684555530548096, "global_step": 611729, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.017489433288574, "global_step": 611730, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9546353816986084, "global_step": 611731, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.013381242752075, "global_step": 611732, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0475239753723145, "global_step": 611733, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9719282388687134, "global_step": 611734, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0342981815338135, "global_step": 611735, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9471685886383057, "global_step": 611736, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9563345909118652, "global_step": 611737, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9693379402160645, "global_step": 611738, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0331966876983643, "global_step": 611739, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9745917320251465, "global_step": 611740, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9923807382583618, "global_step": 611741, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9832267761230469, "global_step": 611742, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9432613849639893, "global_step": 611743, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0296804904937744, "global_step": 611744, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0063345432281494, "global_step": 611745, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0378594398498535, "global_step": 611746, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9170178174972534, "global_step": 611747, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.965307593345642, "global_step": 611748, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.022611141204834, "global_step": 611749, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.039642333984375, "global_step": 611750, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.009134531021118, "global_step": 611751, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0624964237213135, "global_step": 611752, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.918472170829773, "global_step": 611753, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9807064533233643, "global_step": 611754, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9728401899337769, "global_step": 611755, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0706355571746826, "global_step": 611756, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.081331968307495, "global_step": 611757, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9921581745147705, "global_step": 611758, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9466862678527832, "global_step": 611759, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.031686782836914, "global_step": 611760, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.010097026824951, "global_step": 611761, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.985530138015747, "global_step": 611762, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9817008972167969, "global_step": 611763, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.053208589553833, "global_step": 611764, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.965409278869629, "global_step": 611765, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0258045196533203, "global_step": 611766, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9295364618301392, "global_step": 611767, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.005307674407959, "global_step": 611768, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.983786702156067, "global_step": 611769, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0459694862365723, "global_step": 611770, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.02750301361084, "global_step": 611771, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0129292011260986, "global_step": 611772, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9922044277191162, "global_step": 611773, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9333491325378418, "global_step": 611774, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9696261882781982, "global_step": 611775, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0531625747680664, "global_step": 611776, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9467353820800781, "global_step": 611777, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9558072090148926, "global_step": 611778, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.039973020553589, "global_step": 611779, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.053837299346924, "global_step": 611780, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0176889896392822, "global_step": 611781, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9323844909667969, "global_step": 611782, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.997012734413147, "global_step": 611783, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0086567401885986, "global_step": 611784, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9073868989944458, "global_step": 611785, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.013026714324951, "global_step": 611786, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.1018104553222656, "global_step": 611787, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0577738285064697, "global_step": 611788, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0354669094085693, "global_step": 611789, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9733760356903076, "global_step": 611790, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9679369926452637, "global_step": 611791, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.990499496459961, "global_step": 611792, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.028439998626709, "global_step": 611793, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.049008369445801, "global_step": 611794, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9887542724609375, "global_step": 611795, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9090406894683838, "global_step": 611796, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9989622831344604, "global_step": 611797, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9945461750030518, "global_step": 611798, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0108485221862793, "global_step": 611799, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0412747859954834, "global_step": 611800, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0392746925354004, "global_step": 611801, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9756290912628174, "global_step": 611802, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.93965744972229, "global_step": 611803, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0987610816955566, "global_step": 611804, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9965784549713135, "global_step": 611805, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.036811590194702, "global_step": 611806, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9156831502914429, "global_step": 611807, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0420291423797607, "global_step": 611808, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.078096389770508, "global_step": 611809, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9538638591766357, "global_step": 611810, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.887377381324768, "global_step": 611811, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9771299362182617, "global_step": 611812, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.004945755004883, "global_step": 611813, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.002676486968994, "global_step": 611814, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.039839506149292, "global_step": 611815, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9808624982833862, "global_step": 611816, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.1100454330444336, "global_step": 611817, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.025254249572754, "global_step": 611818, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0259878635406494, "global_step": 611819, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.058119297027588, "global_step": 611820, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0321102142333984, "global_step": 611821, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.091053009033203, "global_step": 611822, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.99652099609375, "global_step": 611823, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9274033308029175, "global_step": 611824, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0065622329711914, "global_step": 611825, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9262940883636475, "global_step": 611826, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0153210163116455, "global_step": 611827, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0865190029144287, "global_step": 611828, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0374948978424072, "global_step": 611829, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0162758827209473, "global_step": 611830, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9991950988769531, "global_step": 611831, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.069369316101074, "global_step": 611832, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0462679862976074, "global_step": 611833, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9759390354156494, "global_step": 611834, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.09220027923584, "global_step": 611835, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.939102053642273, "global_step": 611836, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9671940803527832, "global_step": 611837, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9641244411468506, "global_step": 611838, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9834175109863281, "global_step": 611839, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0354573726654053, "global_step": 611840, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9680590629577637, "global_step": 611841, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.993179440498352, "global_step": 611842, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.073507070541382, "global_step": 611843, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9554539918899536, "global_step": 611844, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9588249921798706, "global_step": 611845, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9337105751037598, "global_step": 611846, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0259816646575928, "global_step": 611847, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.034959077835083, "global_step": 611848, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.000898599624634, "global_step": 611849, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9767001867294312, "global_step": 611850, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.117030620574951, "global_step": 611851, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0313332080841064, "global_step": 611852, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0041821002960205, "global_step": 611853, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0271668434143066, "global_step": 611854, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9822787046432495, "global_step": 611855, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.037299156188965, "global_step": 611856, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0133867263793945, "global_step": 611857, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.981980800628662, "global_step": 611858, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9690686464309692, "global_step": 611859, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9871450662612915, "global_step": 611860, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.035701274871826, "global_step": 611861, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9740906953811646, "global_step": 611862, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0677225589752197, "global_step": 611863, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0002708435058594, "global_step": 611864, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0288267135620117, "global_step": 611865, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9746280908584595, "global_step": 611866, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.026740550994873, "global_step": 611867, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0229177474975586, "global_step": 611868, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.041804313659668, "global_step": 611869, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0225701332092285, "global_step": 611870, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0201613903045654, "global_step": 611871, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9432145357131958, "global_step": 611872, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9863876104354858, "global_step": 611873, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0236401557922363, "global_step": 611874, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0480198860168457, "global_step": 611875, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.008249044418335, "global_step": 611876, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9873621463775635, "global_step": 611877, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0337207317352295, "global_step": 611878, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9529403448104858, "global_step": 611879, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0492475032806396, "global_step": 611880, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9924225807189941, "global_step": 611881, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9450204372406006, "global_step": 611882, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9859405755996704, "global_step": 611883, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0864107608795166, "global_step": 611884, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9247961044311523, "global_step": 611885, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.891807198524475, "global_step": 611886, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9371240139007568, "global_step": 611887, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.910465955734253, "global_step": 611888, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.009723424911499, "global_step": 611889, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.979835033416748, "global_step": 611890, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9891949892044067, "global_step": 611891, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.97211754322052, "global_step": 611892, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9684048891067505, "global_step": 611893, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.004518508911133, "global_step": 611894, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0426132678985596, "global_step": 611895, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.030782461166382, "global_step": 611896, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9131525754928589, "global_step": 611897, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9881901741027832, "global_step": 611898, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0597429275512695, "global_step": 611899, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9454410076141357, "global_step": 611900, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9341042041778564, "global_step": 611901, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9744281768798828, "global_step": 611902, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0449957847595215, "global_step": 611903, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.00115704536438, "global_step": 611904, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.05175518989563, "global_step": 611905, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.021867513656616, "global_step": 611906, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0170211791992188, "global_step": 611907, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9601753950119019, "global_step": 611908, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0585856437683105, "global_step": 611909, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9566144943237305, "global_step": 611910, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0428404808044434, "global_step": 611911, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9246957302093506, "global_step": 611912, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.96335768699646, "global_step": 611913, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0377931594848633, "global_step": 611914, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0581138134002686, "global_step": 611915, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.081073760986328, "global_step": 611916, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.044546127319336, "global_step": 611917, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0046658515930176, "global_step": 611918, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0473670959472656, "global_step": 611919, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9891473054885864, "global_step": 611920, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0079092979431152, "global_step": 611921, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9413602352142334, "global_step": 611922, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.025789260864258, "global_step": 611923, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0491461753845215, "global_step": 611924, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0543906688690186, "global_step": 611925, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9410772323608398, "global_step": 611926, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9528517723083496, "global_step": 611927, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9476011991500854, "global_step": 611928, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.034166097640991, "global_step": 611929, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9815642833709717, "global_step": 611930, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.040710210800171, "global_step": 611931, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9858113527297974, "global_step": 611932, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9444448947906494, "global_step": 611933, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9793686866760254, "global_step": 611934, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9592829942703247, "global_step": 611935, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0069057941436768, "global_step": 611936, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9730981588363647, "global_step": 611937, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.944805383682251, "global_step": 611938, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0238397121429443, "global_step": 611939, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0510895252227783, "global_step": 611940, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.052405834197998, "global_step": 611941, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.95428466796875, "global_step": 611942, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.016435384750366, "global_step": 611943, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9888205528259277, "global_step": 611944, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.958113193511963, "global_step": 611945, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0002341270446777, "global_step": 611946, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.052802801132202, "global_step": 611947, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.010232448577881, "global_step": 611948, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9785716533660889, "global_step": 611949, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0168113708496094, "global_step": 611950, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0191822052001953, "global_step": 611951, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.003979206085205, "global_step": 611952, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9762176275253296, "global_step": 611953, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.049283027648926, "global_step": 611954, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9801185131072998, "global_step": 611955, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9552499055862427, "global_step": 611956, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0149648189544678, "global_step": 611957, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0231263637542725, "global_step": 611958, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0625572204589844, "global_step": 611959, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9552267789840698, "global_step": 611960, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9789029359817505, "global_step": 611961, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.035001516342163, "global_step": 611962, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.933455467224121, "global_step": 611963, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0161471366882324, "global_step": 611964, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9533958435058594, "global_step": 611965, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9822598695755005, "global_step": 611966, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9508576393127441, "global_step": 611967, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9044263362884521, "global_step": 611968, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9721622467041016, "global_step": 611969, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.041593551635742, "global_step": 611970, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9410572052001953, "global_step": 611971, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9376553297042847, "global_step": 611972, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9875596761703491, "global_step": 611973, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0018584728240967, "global_step": 611974, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.051330804824829, "global_step": 611975, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0492539405822754, "global_step": 611976, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0247538089752197, "global_step": 611977, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.922947645187378, "global_step": 611978, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9801887273788452, "global_step": 611979, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.086811065673828, "global_step": 611980, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.017824411392212, "global_step": 611981, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0115699768066406, "global_step": 611982, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9736993312835693, "global_step": 611983, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9963260889053345, "global_step": 611984, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.987705945968628, "global_step": 611985, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0931103229522705, "global_step": 611986, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.095663070678711, "global_step": 611987, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0336782932281494, "global_step": 611988, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9984309673309326, "global_step": 611989, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9658032655715942, "global_step": 611990, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0058836936950684, "global_step": 611991, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.029341697692871, "global_step": 611992, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.942739725112915, "global_step": 611993, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0090250968933105, "global_step": 611994, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0086662769317627, "global_step": 611995, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.965981364250183, "global_step": 611996, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.086674451828003, "global_step": 611997, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.039144277572632, "global_step": 611998, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0213589668273926, "global_step": 611999, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0079784393310547, "global_step": 612000, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0479042530059814, "global_step": 612001, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.060335397720337, "global_step": 612002, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9657405614852905, "global_step": 612003, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.8902243375778198, "global_step": 612004, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.988578200340271, "global_step": 612005, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.000868797302246, "global_step": 612006, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9641613960266113, "global_step": 612007, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9504785537719727, "global_step": 612008, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.064223051071167, "global_step": 612009, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0466530323028564, "global_step": 612010, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0634472370147705, "global_step": 612011, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9679381847381592, "global_step": 612012, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.957031011581421, "global_step": 612013, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0239508152008057, "global_step": 612014, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0914273262023926, "global_step": 612015, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0064496994018555, "global_step": 612016, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0553524494171143, "global_step": 612017, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0545127391815186, "global_step": 612018, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9470573663711548, "global_step": 612019, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9899885654449463, "global_step": 612020, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9905223846435547, "global_step": 612021, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.012218952178955, "global_step": 612022, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0632972717285156, "global_step": 612023, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.027550220489502, "global_step": 612024, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.017921209335327, "global_step": 612025, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9970371723175049, "global_step": 612026, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9836946725845337, "global_step": 612027, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9256733655929565, "global_step": 612028, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.978305697441101, "global_step": 612029, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.02803111076355, "global_step": 612030, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9901015758514404, "global_step": 612031, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0121963024139404, "global_step": 612032, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0591840744018555, "global_step": 612033, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.935153603553772, "global_step": 612034, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9660165309906006, "global_step": 612035, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0359272956848145, "global_step": 612036, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0281808376312256, "global_step": 612037, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9888672828674316, "global_step": 612038, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9710803031921387, "global_step": 612039, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.073460340499878, "global_step": 612040, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.048870801925659, "global_step": 612041, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0269381999969482, "global_step": 612042, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9612764120101929, "global_step": 612043, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9674172401428223, "global_step": 612044, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9724037647247314, "global_step": 612045, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0926308631896973, "global_step": 612046, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.165468215942383, "global_step": 612047, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.957067847251892, "global_step": 612048, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.017998695373535, "global_step": 612049, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0228374004364014, "global_step": 612050, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9773690700531006, "global_step": 612051, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.030425786972046, "global_step": 612052, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.030674457550049, "global_step": 612053, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0125882625579834, "global_step": 612054, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.006246566772461, "global_step": 612055, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0942063331604004, "global_step": 612056, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.016589879989624, "global_step": 612057, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0441677570343018, "global_step": 612058, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0686635971069336, "global_step": 612059, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.074981689453125, "global_step": 612060, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9447776079177856, "global_step": 612061, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0075442790985107, "global_step": 612062, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.1013221740722656, "global_step": 612063, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0317270755767822, "global_step": 612064, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.012737989425659, "global_step": 612065, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.013561725616455, "global_step": 612066, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.039600133895874, "global_step": 612067, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0132226943969727, "global_step": 612068, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9980815649032593, "global_step": 612069, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9975305795669556, "global_step": 612070, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9439362287521362, "global_step": 612071, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9798979759216309, "global_step": 612072, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.8737984895706177, "global_step": 612073, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.016806125640869, "global_step": 612074, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9913861751556396, "global_step": 612075, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9864294528961182, "global_step": 612076, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.043182849884033, "global_step": 612077, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0371739864349365, "global_step": 612078, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.950642704963684, "global_step": 612079, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0266497135162354, "global_step": 612080, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0636448860168457, "global_step": 612081, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.082157611846924, "global_step": 612082, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0515570640563965, "global_step": 612083, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0254998207092285, "global_step": 612084, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.014901638031006, "global_step": 612085, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.065659284591675, "global_step": 612086, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0948314666748047, "global_step": 612087, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.951362133026123, "global_step": 612088, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9888211488723755, "global_step": 612089, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.97384512424469, "global_step": 612090, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.052717685699463, "global_step": 612091, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0751397609710693, "global_step": 612092, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9147474765777588, "global_step": 612093, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0810625553131104, "global_step": 612094, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.011564254760742, "global_step": 612095, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9784971475601196, "global_step": 612096, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0002951622009277, "global_step": 612097, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0522594451904297, "global_step": 612098, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9303306341171265, "global_step": 612099, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9924958944320679, "global_step": 612100, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9682841300964355, "global_step": 612101, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.037846803665161, "global_step": 612102, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0303165912628174, "global_step": 612103, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9757529497146606, "global_step": 612104, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9456508159637451, "global_step": 612105, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9840078353881836, "global_step": 612106, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.075917959213257, "global_step": 612107, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0345046520233154, "global_step": 612108, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0506482124328613, "global_step": 612109, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0823705196380615, "global_step": 612110, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0194661617279053, "global_step": 612111, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.97800874710083, "global_step": 612112, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.056959629058838, "global_step": 612113, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0585200786590576, "global_step": 612114, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.058591365814209, "global_step": 612115, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9943057298660278, "global_step": 612116, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0467517375946045, "global_step": 612117, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.059765577316284, "global_step": 612118, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9907687902450562, "global_step": 612119, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.13832426071167, "global_step": 612120, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9605716466903687, "global_step": 612121, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9837777614593506, "global_step": 612122, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0423481464385986, "global_step": 612123, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.039457082748413, "global_step": 612124, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0784780979156494, "global_step": 612125, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9379866123199463, "global_step": 612126, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.1337597370147705, "global_step": 612127, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.93994140625, "global_step": 612128, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9933186769485474, "global_step": 612129, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.048102855682373, "global_step": 612130, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0522923469543457, "global_step": 612131, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0188839435577393, "global_step": 612132, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9821487665176392, "global_step": 612133, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.023786783218384, "global_step": 612134, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0548434257507324, "global_step": 612135, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0106940269470215, "global_step": 612136, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.98219633102417, "global_step": 612137, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0932164192199707, "global_step": 612138, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0072009563446045, "global_step": 612139, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0378594398498535, "global_step": 612140, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9974874258041382, "global_step": 612141, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.987932801246643, "global_step": 612142, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.00924015045166, "global_step": 612143, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9557808637619019, "global_step": 612144, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.059566020965576, "global_step": 612145, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.951281189918518, "global_step": 612146, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.04616641998291, "global_step": 612147, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9466941356658936, "global_step": 612148, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0988175868988037, "global_step": 612149, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.001100540161133, "global_step": 612150, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0117080211639404, "global_step": 612151, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9846224784851074, "global_step": 612152, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9794948101043701, "global_step": 612153, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9919019937515259, "global_step": 612154, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9738967418670654, "global_step": 612155, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.006148338317871, "global_step": 612156, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.031001091003418, "global_step": 612157, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9721770286560059, "global_step": 612158, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0816359519958496, "global_step": 612159, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.963725209236145, "global_step": 612160, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0069420337677, "global_step": 612161, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9571279287338257, "global_step": 612162, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.914993405342102, "global_step": 612163, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9872633218765259, "global_step": 612164, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9247663021087646, "global_step": 612165, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.1128249168395996, "global_step": 612166, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.05751633644104, "global_step": 612167, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0161263942718506, "global_step": 612168, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.022390365600586, "global_step": 612169, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.982978105545044, "global_step": 612170, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0367279052734375, "global_step": 612171, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9827251434326172, "global_step": 612172, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9926660060882568, "global_step": 612173, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9983367919921875, "global_step": 612174, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.040257692337036, "global_step": 612175, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9837582111358643, "global_step": 612176, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.024683952331543, "global_step": 612177, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.030580997467041, "global_step": 612178, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.067492723464966, "global_step": 612179, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.026326894760132, "global_step": 612180, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.1547060012817383, "global_step": 612181, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9710118770599365, "global_step": 612182, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.054847240447998, "global_step": 612183, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.037710428237915, "global_step": 612184, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9400581121444702, "global_step": 612185, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.969626784324646, "global_step": 612186, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.992436408996582, "global_step": 612187, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0414578914642334, "global_step": 612188, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9405367374420166, "global_step": 612189, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0015530586242676, "global_step": 612190, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0783205032348633, "global_step": 612191, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.000542402267456, "global_step": 612192, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9947261810302734, "global_step": 612193, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.015202522277832, "global_step": 612194, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.046905040740967, "global_step": 612195, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0307412147521973, "global_step": 612196, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.025859832763672, "global_step": 612197, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.091198444366455, "global_step": 612198, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9499467611312866, "global_step": 612199, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0258073806762695, "global_step": 612200, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0096518993377686, "global_step": 612201, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.056628942489624, "global_step": 612202, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.049031972885132, "global_step": 612203, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.965119481086731, "global_step": 612204, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9425969123840332, "global_step": 612205, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9672104120254517, "global_step": 612206, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9146168231964111, "global_step": 612207, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.10686993598938, "global_step": 612208, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.992958903312683, "global_step": 612209, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.015331506729126, "global_step": 612210, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0370266437530518, "global_step": 612211, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0860795974731445, "global_step": 612212, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0304489135742188, "global_step": 612213, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.10028076171875, "global_step": 612214, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.028557300567627, "global_step": 612215, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.084109306335449, "global_step": 612216, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9602738618850708, "global_step": 612217, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.030524492263794, "global_step": 612218, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9564313888549805, "global_step": 612219, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0253469944000244, "global_step": 612220, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0537192821502686, "global_step": 612221, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0643937587738037, "global_step": 612222, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0403473377227783, "global_step": 612223, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.064746618270874, "global_step": 612224, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.087080717086792, "global_step": 612225, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.039119005203247, "global_step": 612226, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0476975440979004, "global_step": 612227, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.022620916366577, "global_step": 612228, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.934169054031372, "global_step": 612229, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.077763557434082, "global_step": 612230, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.008601665496826, "global_step": 612231, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.007584571838379, "global_step": 612232, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0159988403320312, "global_step": 612233, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0458996295928955, "global_step": 612234, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.970363974571228, "global_step": 612235, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.977422833442688, "global_step": 612236, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9817019701004028, "global_step": 612237, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0569968223571777, "global_step": 612238, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.084503650665283, "global_step": 612239, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0704572200775146, "global_step": 612240, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.051882028579712, "global_step": 612241, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0288631916046143, "global_step": 612242, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9662895202636719, "global_step": 612243, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.019822359085083, "global_step": 612244, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9635965824127197, "global_step": 612245, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0538339614868164, "global_step": 612246, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.979367733001709, "global_step": 612247, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0492265224456787, "global_step": 612248, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0147593021392822, "global_step": 612249, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9515315294265747, "global_step": 612250, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0165748596191406, "global_step": 612251, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9286046028137207, "global_step": 612252, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.083885431289673, "global_step": 612253, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.988452672958374, "global_step": 612254, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9845683574676514, "global_step": 612255, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.946041464805603, "global_step": 612256, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.001875877380371, "global_step": 612257, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.126762628555298, "global_step": 612258, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9850322008132935, "global_step": 612259, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.084454298019409, "global_step": 612260, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9830878973007202, "global_step": 612261, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.059948444366455, "global_step": 612262, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0391616821289062, "global_step": 612263, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9914897680282593, "global_step": 612264, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.071611166000366, "global_step": 612265, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9542899131774902, "global_step": 612266, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0105834007263184, "global_step": 612267, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9581509828567505, "global_step": 612268, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9430593252182007, "global_step": 612269, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.094763994216919, "global_step": 612270, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0367040634155273, "global_step": 612271, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.042078971862793, "global_step": 612272, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.006019115447998, "global_step": 612273, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.99562668800354, "global_step": 612274, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.8839881420135498, "global_step": 612275, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0265939235687256, "global_step": 612276, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.085815906524658, "global_step": 612277, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9664194583892822, "global_step": 612278, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0868780612945557, "global_step": 612279, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9629080295562744, "global_step": 612280, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.056044340133667, "global_step": 612281, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9881104230880737, "global_step": 612282, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0316405296325684, "global_step": 612283, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.129377841949463, "global_step": 612284, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9839383363723755, "global_step": 612285, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9713943004608154, "global_step": 612286, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0064549446105957, "global_step": 612287, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.015155076980591, "global_step": 612288, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9832137823104858, "global_step": 612289, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9631301164627075, "global_step": 612290, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.070842742919922, "global_step": 612291, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0007762908935547, "global_step": 612292, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.990222692489624, "global_step": 612293, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9985615015029907, "global_step": 612294, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0076019763946533, "global_step": 612295, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0441582202911377, "global_step": 612296, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.8952089548110962, "global_step": 612297, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9555952548980713, "global_step": 612298, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0126993656158447, "global_step": 612299, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9419225454330444, "global_step": 612300, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9844701290130615, "global_step": 612301, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.024305820465088, "global_step": 612302, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0702457427978516, "global_step": 612303, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.030590057373047, "global_step": 612304, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9329975843429565, "global_step": 612305, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.051780939102173, "global_step": 612306, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9292315244674683, "global_step": 612307, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0490801334381104, "global_step": 612308, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.005582094192505, "global_step": 612309, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9988120794296265, "global_step": 612310, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.065850257873535, "global_step": 612311, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9313828945159912, "global_step": 612312, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9746730327606201, "global_step": 612313, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0405781269073486, "global_step": 612314, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.081897497177124, "global_step": 612315, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9701370000839233, "global_step": 612316, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0324766635894775, "global_step": 612317, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.066605567932129, "global_step": 612318, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.986689567565918, "global_step": 612319, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9873942136764526, "global_step": 612320, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.92930269241333, "global_step": 612321, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.029188871383667, "global_step": 612322, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.1061148643493652, "global_step": 612323, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0040242671966553, "global_step": 612324, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9761725664138794, "global_step": 612325, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9693962335586548, "global_step": 612326, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9554476737976074, "global_step": 612327, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.1025266647338867, "global_step": 612328, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0948736667633057, "global_step": 612329, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.023386240005493, "global_step": 612330, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0057029724121094, "global_step": 612331, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.044715642929077, "global_step": 612332, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.032472848892212, "global_step": 612333, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.086366653442383, "global_step": 612334, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.060610294342041, "global_step": 612335, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.935659646987915, "global_step": 612336, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9528318643569946, "global_step": 612337, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9767190217971802, "global_step": 612338, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9899249076843262, "global_step": 612339, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9929720163345337, "global_step": 612340, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0531294345855713, "global_step": 612341, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.07315993309021, "global_step": 612342, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.965478539466858, "global_step": 612343, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.940504550933838, "global_step": 612344, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0365631580352783, "global_step": 612345, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0777032375335693, "global_step": 612346, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0162198543548584, "global_step": 612347, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.055922031402588, "global_step": 612348, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9819326400756836, "global_step": 612349, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.140303611755371, "global_step": 612350, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9863468408584595, "global_step": 612351, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.979292631149292, "global_step": 612352, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.966751217842102, "global_step": 612353, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.1117475032806396, "global_step": 612354, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0158891677856445, "global_step": 612355, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0734009742736816, "global_step": 612356, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.002753734588623, "global_step": 612357, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.078699827194214, "global_step": 612358, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.133831262588501, "global_step": 612359, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0039138793945312, "global_step": 612360, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0481789112091064, "global_step": 612361, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.067765712738037, "global_step": 612362, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.057955265045166, "global_step": 612363, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.065964460372925, "global_step": 612364, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9494481086730957, "global_step": 612365, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9560143947601318, "global_step": 612366, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9691293239593506, "global_step": 612367, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9143863916397095, "global_step": 612368, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9409033060073853, "global_step": 612369, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0128283500671387, "global_step": 612370, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0110678672790527, "global_step": 612371, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.071181297302246, "global_step": 612372, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9737850427627563, "global_step": 612373, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9821522235870361, "global_step": 612374, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9652843475341797, "global_step": 612375, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.8964967727661133, "global_step": 612376, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0319786071777344, "global_step": 612377, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0180211067199707, "global_step": 612378, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9761277437210083, "global_step": 612379, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0173168182373047, "global_step": 612380, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0576376914978027, "global_step": 612381, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0268478393554688, "global_step": 612382, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.00736665725708, "global_step": 612383, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.008646249771118, "global_step": 612384, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0150513648986816, "global_step": 612385, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9543304443359375, "global_step": 612386, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9541383981704712, "global_step": 612387, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.984279751777649, "global_step": 612388, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9914512634277344, "global_step": 612389, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0198726654052734, "global_step": 612390, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.949689269065857, "global_step": 612391, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9141676425933838, "global_step": 612392, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0644984245300293, "global_step": 612393, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.038032054901123, "global_step": 612394, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9972420930862427, "global_step": 612395, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0249292850494385, "global_step": 612396, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9458075761795044, "global_step": 612397, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0331873893737793, "global_step": 612398, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.094116687774658, "global_step": 612399, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0804078578948975, "global_step": 612400, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0612878799438477, "global_step": 612401, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.064708948135376, "global_step": 612402, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0206594467163086, "global_step": 612403, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.058084011077881, "global_step": 612404, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9523018598556519, "global_step": 612405, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0395359992980957, "global_step": 612406, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.090514659881592, "global_step": 612407, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9920498132705688, "global_step": 612408, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.026545763015747, "global_step": 612409, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0217342376708984, "global_step": 612410, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9486773014068604, "global_step": 612411, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0125346183776855, "global_step": 612412, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9427571296691895, "global_step": 612413, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0311777591705322, "global_step": 612414, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.009697437286377, "global_step": 612415, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0070841312408447, "global_step": 612416, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0882608890533447, "global_step": 612417, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0233240127563477, "global_step": 612418, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9571783542633057, "global_step": 612419, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.980028510093689, "global_step": 612420, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.018244743347168, "global_step": 612421, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9718091487884521, "global_step": 612422, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.095278024673462, "global_step": 612423, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0342607498168945, "global_step": 612424, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0205745697021484, "global_step": 612425, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0764005184173584, "global_step": 612426, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.1150643825531006, "global_step": 612427, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9839012622833252, "global_step": 612428, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9577441215515137, "global_step": 612429, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0132789611816406, "global_step": 612430, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9362518787384033, "global_step": 612431, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.014956474304199, "global_step": 612432, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0140433311462402, "global_step": 612433, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9896730184555054, "global_step": 612434, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0039377212524414, "global_step": 612435, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0096352100372314, "global_step": 612436, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9964179992675781, "global_step": 612437, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0587570667266846, "global_step": 612438, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.010499954223633, "global_step": 612439, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9662907123565674, "global_step": 612440, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0372626781463623, "global_step": 612441, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.093330144882202, "global_step": 612442, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0095701217651367, "global_step": 612443, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.017629861831665, "global_step": 612444, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9609521627426147, "global_step": 612445, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9385589361190796, "global_step": 612446, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9769129753112793, "global_step": 612447, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.057859182357788, "global_step": 612448, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.024620771408081, "global_step": 612449, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9942941665649414, "global_step": 612450, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0117478370666504, "global_step": 612451, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.008763074874878, "global_step": 612452, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0138792991638184, "global_step": 612453, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0350382328033447, "global_step": 612454, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9535608291625977, "global_step": 612455, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0686705112457275, "global_step": 612456, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9226726293563843, "global_step": 612457, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0513429641723633, "global_step": 612458, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0229992866516113, "global_step": 612459, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.990309238433838, "global_step": 612460, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9790970087051392, "global_step": 612461, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9502888917922974, "global_step": 612462, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0226900577545166, "global_step": 612463, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0622854232788086, "global_step": 612464, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.01151442527771, "global_step": 612465, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.034968376159668, "global_step": 612466, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9718371629714966, "global_step": 612467, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.044424533843994, "global_step": 612468, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0874276161193848, "global_step": 612469, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9683947563171387, "global_step": 612470, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0125744342803955, "global_step": 612471, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0880417823791504, "global_step": 612472, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9120051860809326, "global_step": 612473, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.089042901992798, "global_step": 612474, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0175111293792725, "global_step": 612475, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9042209386825562, "global_step": 612476, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9980322122573853, "global_step": 612477, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9689831733703613, "global_step": 612478, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0288095474243164, "global_step": 612479, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9566929340362549, "global_step": 612480, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0277674198150635, "global_step": 612481, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9970571994781494, "global_step": 612482, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0861003398895264, "global_step": 612483, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.003282308578491, "global_step": 612484, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0483782291412354, "global_step": 612485, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0360231399536133, "global_step": 612486, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0047342777252197, "global_step": 612487, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9401781558990479, "global_step": 612488, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0883610248565674, "global_step": 612489, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.005704879760742, "global_step": 612490, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9938219785690308, "global_step": 612491, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.067216157913208, "global_step": 612492, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.021448850631714, "global_step": 612493, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9992882013320923, "global_step": 612494, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.010610342025757, "global_step": 612495, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.039641857147217, "global_step": 612496, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.040351152420044, "global_step": 612497, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9206607341766357, "global_step": 612498, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9726966619491577, "global_step": 612499, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.067589521408081, "global_step": 612500, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.020528793334961, "global_step": 612501, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0534703731536865, "global_step": 612502, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0072221755981445, "global_step": 612503, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0611319541931152, "global_step": 612504, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.06181263923645, "global_step": 612505, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9950051307678223, "global_step": 612506, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0562584400177, "global_step": 612507, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.1076102256774902, "global_step": 612508, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.921583890914917, "global_step": 612509, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.994835615158081, "global_step": 612510, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.932321548461914, "global_step": 612511, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.015096426010132, "global_step": 612512, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.029493570327759, "global_step": 612513, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0539636611938477, "global_step": 612514, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.040621042251587, "global_step": 612515, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.039306163787842, "global_step": 612516, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.962188959121704, "global_step": 612517, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9122021198272705, "global_step": 612518, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.019759178161621, "global_step": 612519, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0398995876312256, "global_step": 612520, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0407700538635254, "global_step": 612521, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.060403347015381, "global_step": 612522, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0480191707611084, "global_step": 612523, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9702259302139282, "global_step": 612524, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0269718170166016, "global_step": 612525, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.010033369064331, "global_step": 612526, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.084711790084839, "global_step": 612527, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.981015682220459, "global_step": 612528, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.978428840637207, "global_step": 612529, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0001542568206787, "global_step": 612530, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.1233632564544678, "global_step": 612531, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9863413572311401, "global_step": 612532, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.101367950439453, "global_step": 612533, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.005948543548584, "global_step": 612534, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9870407581329346, "global_step": 612535, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.0112860202789307, "global_step": 612536, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9595942497253418, "global_step": 612537, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9577267169952393, "global_step": 612538, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9343801736831665, "global_step": 612539, "epoch": 981, "lr": 5e-05}
{"train_loss": 2.009047746658325, "global_step": 612540, "epoch": 981, "lr": 5e-05}
{"train_loss": 1.9945496320724487, "global_step": 612541, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1030073165893555, "global_step": 612542, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9502700567245483, "global_step": 612543, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0040621757507324, "global_step": 612544, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9796435832977295, "global_step": 612545, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.997800588607788, "global_step": 612546, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9933240413665771, "global_step": 612547, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0021045207977295, "global_step": 612548, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.014522075653076, "global_step": 612549, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9645284414291382, "global_step": 612550, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0051066875457764, "global_step": 612551, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9224343299865723, "global_step": 612552, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9933464527130127, "global_step": 612553, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.062572717666626, "global_step": 612554, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.023102045059204, "global_step": 612555, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9475573301315308, "global_step": 612556, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.054382085800171, "global_step": 612557, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0059447288513184, "global_step": 612558, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.008927583694458, "global_step": 612559, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.916263461112976, "global_step": 612560, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0123848915100098, "global_step": 612561, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9343609809875488, "global_step": 612562, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.065281629562378, "global_step": 612563, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.028395652770996, "global_step": 612564, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0179903507232666, "global_step": 612565, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.993045687675476, "global_step": 612566, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0391006469726562, "global_step": 612567, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9984763860702515, "global_step": 612568, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9730324745178223, "global_step": 612569, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9721829891204834, "global_step": 612570, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0387253761291504, "global_step": 612571, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9527384042739868, "global_step": 612572, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.009239435195923, "global_step": 612573, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.004263162612915, "global_step": 612574, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9923607110977173, "global_step": 612575, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.077077865600586, "global_step": 612576, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9019832611083984, "global_step": 612577, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.018497943878174, "global_step": 612578, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9829919338226318, "global_step": 612579, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9164760112762451, "global_step": 612580, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.032914876937866, "global_step": 612581, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0426454544067383, "global_step": 612582, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0237133502960205, "global_step": 612583, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.973901391029358, "global_step": 612584, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9806544780731201, "global_step": 612585, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0863640308380127, "global_step": 612586, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9573249816894531, "global_step": 612587, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.02823805809021, "global_step": 612588, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9854755401611328, "global_step": 612589, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0879406929016113, "global_step": 612590, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.977018117904663, "global_step": 612591, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9652197360992432, "global_step": 612592, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.032458782196045, "global_step": 612593, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9220523834228516, "global_step": 612594, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0507915019989014, "global_step": 612595, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9772210121154785, "global_step": 612596, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0557944774627686, "global_step": 612597, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0243868827819824, "global_step": 612598, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.04499888420105, "global_step": 612599, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.990412950515747, "global_step": 612600, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.8974498510360718, "global_step": 612601, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0116348266601562, "global_step": 612602, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.985303521156311, "global_step": 612603, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.015068531036377, "global_step": 612604, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9727882146835327, "global_step": 612605, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9916439056396484, "global_step": 612606, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9606399536132812, "global_step": 612607, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.000861167907715, "global_step": 612608, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.879726767539978, "global_step": 612609, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0593767166137695, "global_step": 612610, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9254766702651978, "global_step": 612611, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.005404472351074, "global_step": 612612, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9984204769134521, "global_step": 612613, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9780346155166626, "global_step": 612614, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0240516662597656, "global_step": 612615, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1511318683624268, "global_step": 612616, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.939643144607544, "global_step": 612617, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9054709672927856, "global_step": 612618, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.990437626838684, "global_step": 612619, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9574286937713623, "global_step": 612620, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9726754426956177, "global_step": 612621, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9964767694473267, "global_step": 612622, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9872835874557495, "global_step": 612623, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.048521041870117, "global_step": 612624, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.023829936981201, "global_step": 612625, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.016580104827881, "global_step": 612626, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0389244556427, "global_step": 612627, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.036884069442749, "global_step": 612628, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9236643314361572, "global_step": 612629, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0353546142578125, "global_step": 612630, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.081280469894409, "global_step": 612631, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.045549154281616, "global_step": 612632, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9601283073425293, "global_step": 612633, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9899998903274536, "global_step": 612634, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.000295877456665, "global_step": 612635, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.074129343032837, "global_step": 612636, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9355504512786865, "global_step": 612637, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9159716367721558, "global_step": 612638, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.935410976409912, "global_step": 612639, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0453789234161377, "global_step": 612640, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.038494348526001, "global_step": 612641, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1134302616119385, "global_step": 612642, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.996558427810669, "global_step": 612643, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9489779472351074, "global_step": 612644, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.902500867843628, "global_step": 612645, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0006213188171387, "global_step": 612646, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9577726125717163, "global_step": 612647, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.005005359649658, "global_step": 612648, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9940171241760254, "global_step": 612649, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.977034330368042, "global_step": 612650, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.998114824295044, "global_step": 612651, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9592763185501099, "global_step": 612652, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9702410697937012, "global_step": 612653, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.032196521759033, "global_step": 612654, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.048583984375, "global_step": 612655, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0076305866241455, "global_step": 612656, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.957642912864685, "global_step": 612657, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9322623014450073, "global_step": 612658, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.009002923965454, "global_step": 612659, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.015174388885498, "global_step": 612660, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9333555698394775, "global_step": 612661, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.966058611869812, "global_step": 612662, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0458104610443115, "global_step": 612663, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9887362718582153, "global_step": 612664, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9789150953292847, "global_step": 612665, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9480528831481934, "global_step": 612666, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.040106773376465, "global_step": 612667, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9626030921936035, "global_step": 612668, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0544028282165527, "global_step": 612669, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0711512565612793, "global_step": 612670, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.069647789001465, "global_step": 612671, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9734240770339966, "global_step": 612672, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.966758370399475, "global_step": 612673, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.024970769882202, "global_step": 612674, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9469549655914307, "global_step": 612675, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9343764781951904, "global_step": 612676, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0362982749938965, "global_step": 612677, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.096341371536255, "global_step": 612678, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9617310762405396, "global_step": 612679, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.019197940826416, "global_step": 612680, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0351741313934326, "global_step": 612681, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.986581563949585, "global_step": 612682, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.084953546524048, "global_step": 612683, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.016249895095825, "global_step": 612684, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9103354215621948, "global_step": 612685, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9691071510314941, "global_step": 612686, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.055962324142456, "global_step": 612687, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9688072204589844, "global_step": 612688, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.8954490423202515, "global_step": 612689, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.999409556388855, "global_step": 612690, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.027157783508301, "global_step": 612691, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0566463470458984, "global_step": 612692, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9814757108688354, "global_step": 612693, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.970461368560791, "global_step": 612694, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9944294691085815, "global_step": 612695, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.035539388656616, "global_step": 612696, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.023872137069702, "global_step": 612697, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0095722675323486, "global_step": 612698, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0197017192840576, "global_step": 612699, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1063942909240723, "global_step": 612700, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.007539987564087, "global_step": 612701, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9968456029891968, "global_step": 612702, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0590832233428955, "global_step": 612703, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9900299310684204, "global_step": 612704, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9448059797286987, "global_step": 612705, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9877012968063354, "global_step": 612706, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0456364154815674, "global_step": 612707, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.02968692779541, "global_step": 612708, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0336830615997314, "global_step": 612709, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9647427797317505, "global_step": 612710, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9856148958206177, "global_step": 612711, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.008307933807373, "global_step": 612712, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.992065191268921, "global_step": 612713, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.046145439147949, "global_step": 612714, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.994080662727356, "global_step": 612715, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9647034406661987, "global_step": 612716, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1442813873291016, "global_step": 612717, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9645718336105347, "global_step": 612718, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9590154886245728, "global_step": 612719, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.014746904373169, "global_step": 612720, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.995539903640747, "global_step": 612721, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9507979154586792, "global_step": 612722, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9678986072540283, "global_step": 612723, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.037879228591919, "global_step": 612724, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9973474740982056, "global_step": 612725, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9870043992996216, "global_step": 612726, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9697692394256592, "global_step": 612727, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0421180725097656, "global_step": 612728, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.936992883682251, "global_step": 612729, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.006917715072632, "global_step": 612730, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0178802013397217, "global_step": 612731, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.008632183074951, "global_step": 612732, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9761754274368286, "global_step": 612733, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.026054859161377, "global_step": 612734, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.910788655281067, "global_step": 612735, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.013749837875366, "global_step": 612736, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0055646896362305, "global_step": 612737, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.945504069328308, "global_step": 612738, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9848676919937134, "global_step": 612739, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0316598415374756, "global_step": 612740, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0765888690948486, "global_step": 612741, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.101773500442505, "global_step": 612742, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0275959968566895, "global_step": 612743, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0402169227600098, "global_step": 612744, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9883804321289062, "global_step": 612745, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9484447240829468, "global_step": 612746, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9921272993087769, "global_step": 612747, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9890172481536865, "global_step": 612748, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.005589246749878, "global_step": 612749, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0231773853302, "global_step": 612750, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9812928438186646, "global_step": 612751, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9891613721847534, "global_step": 612752, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0930230617523193, "global_step": 612753, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9965955018997192, "global_step": 612754, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0522382259368896, "global_step": 612755, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.083592653274536, "global_step": 612756, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0774857997894287, "global_step": 612757, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.047193765640259, "global_step": 612758, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9624555110931396, "global_step": 612759, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0687026977539062, "global_step": 612760, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.090365171432495, "global_step": 612761, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.064627170562744, "global_step": 612762, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.062349796295166, "global_step": 612763, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9896880388259888, "global_step": 612764, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9925694465637207, "global_step": 612765, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9030250310897827, "global_step": 612766, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0632574558258057, "global_step": 612767, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9763532876968384, "global_step": 612768, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9515494108200073, "global_step": 612769, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0482845306396484, "global_step": 612770, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.019413709640503, "global_step": 612771, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.8866750001907349, "global_step": 612772, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.016079902648926, "global_step": 612773, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1370809078216553, "global_step": 612774, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9867982864379883, "global_step": 612775, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0105841159820557, "global_step": 612776, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9710729122161865, "global_step": 612777, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0351648330688477, "global_step": 612778, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.142549514770508, "global_step": 612779, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.010091543197632, "global_step": 612780, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.975396990776062, "global_step": 612781, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9668664932250977, "global_step": 612782, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0320987701416016, "global_step": 612783, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.999664306640625, "global_step": 612784, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.8977128267288208, "global_step": 612785, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9403303861618042, "global_step": 612786, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0987935066223145, "global_step": 612787, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.036102056503296, "global_step": 612788, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0147805213928223, "global_step": 612789, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9711759090423584, "global_step": 612790, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.036086082458496, "global_step": 612791, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9921637773513794, "global_step": 612792, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.038727283477783, "global_step": 612793, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0401666164398193, "global_step": 612794, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9735989570617676, "global_step": 612795, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9723989963531494, "global_step": 612796, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9399774074554443, "global_step": 612797, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9615073204040527, "global_step": 612798, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.00656795501709, "global_step": 612799, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.031665086746216, "global_step": 612800, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.004178047180176, "global_step": 612801, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0342509746551514, "global_step": 612802, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9588592052459717, "global_step": 612803, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9963924884796143, "global_step": 612804, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.005028247833252, "global_step": 612805, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9927116632461548, "global_step": 612806, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0844385623931885, "global_step": 612807, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.024775266647339, "global_step": 612808, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0085604190826416, "global_step": 612809, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0526928901672363, "global_step": 612810, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.075540542602539, "global_step": 612811, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9697359800338745, "global_step": 612812, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.87679922580719, "global_step": 612813, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9622949361801147, "global_step": 612814, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9291160106658936, "global_step": 612815, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.891647458076477, "global_step": 612816, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0978527069091797, "global_step": 612817, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9904907941818237, "global_step": 612818, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.970655083656311, "global_step": 612819, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0117170810699463, "global_step": 612820, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.017160177230835, "global_step": 612821, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0798001289367676, "global_step": 612822, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9817463159561157, "global_step": 612823, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0647268295288086, "global_step": 612824, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.981174349784851, "global_step": 612825, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0371804237365723, "global_step": 612826, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.067887783050537, "global_step": 612827, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0288126468658447, "global_step": 612828, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9698201417922974, "global_step": 612829, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.944115161895752, "global_step": 612830, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.8999006748199463, "global_step": 612831, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9532690048217773, "global_step": 612832, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9731545448303223, "global_step": 612833, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9836324453353882, "global_step": 612834, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.045604705810547, "global_step": 612835, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0272128582000732, "global_step": 612836, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0035512447357178, "global_step": 612837, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0863099098205566, "global_step": 612838, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9841487407684326, "global_step": 612839, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0393807888031006, "global_step": 612840, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9913727045059204, "global_step": 612841, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.987791657447815, "global_step": 612842, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0125765800476074, "global_step": 612843, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9609888792037964, "global_step": 612844, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9763835668563843, "global_step": 612845, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0133557319641113, "global_step": 612846, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.031017780303955, "global_step": 612847, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.980791449546814, "global_step": 612848, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9664838314056396, "global_step": 612849, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9461426734924316, "global_step": 612850, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.054713487625122, "global_step": 612851, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.996601939201355, "global_step": 612852, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.99547278881073, "global_step": 612853, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0042781829833984, "global_step": 612854, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.942441463470459, "global_step": 612855, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9514682292938232, "global_step": 612856, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.988762617111206, "global_step": 612857, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9262028932571411, "global_step": 612858, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9661978483200073, "global_step": 612859, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.003859043121338, "global_step": 612860, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9782720804214478, "global_step": 612861, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9850845336914062, "global_step": 612862, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9583240747451782, "global_step": 612863, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0158419609069824, "global_step": 612864, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9404388666152954, "global_step": 612865, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.003615617752075, "global_step": 612866, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9873857498168945, "global_step": 612867, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0296530723571777, "global_step": 612868, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9852896928787231, "global_step": 612869, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.074383497238159, "global_step": 612870, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0285887718200684, "global_step": 612871, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9901564121246338, "global_step": 612872, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.053734540939331, "global_step": 612873, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9842969179153442, "global_step": 612874, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.985816240310669, "global_step": 612875, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0419342517852783, "global_step": 612876, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0371932983398438, "global_step": 612877, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.014500617980957, "global_step": 612878, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.950592041015625, "global_step": 612879, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0047049522399902, "global_step": 612880, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0187535285949707, "global_step": 612881, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0864357948303223, "global_step": 612882, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.97635018825531, "global_step": 612883, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.8947199583053589, "global_step": 612884, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0773258209228516, "global_step": 612885, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1021456718444824, "global_step": 612886, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0205225944519043, "global_step": 612887, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0034079551696777, "global_step": 612888, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9873920679092407, "global_step": 612889, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.048995018005371, "global_step": 612890, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0511667728424072, "global_step": 612891, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.8837522268295288, "global_step": 612892, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9570679664611816, "global_step": 612893, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9728223085403442, "global_step": 612894, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0154569149017334, "global_step": 612895, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.989705204963684, "global_step": 612896, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9775962829589844, "global_step": 612897, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9641685485839844, "global_step": 612898, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9603111743927002, "global_step": 612899, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9568365812301636, "global_step": 612900, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9983000755310059, "global_step": 612901, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9648510217666626, "global_step": 612902, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0304527282714844, "global_step": 612903, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0331616401672363, "global_step": 612904, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.008457899093628, "global_step": 612905, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0002524852752686, "global_step": 612906, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.943834662437439, "global_step": 612907, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9445327520370483, "global_step": 612908, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9835050106048584, "global_step": 612909, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.069938898086548, "global_step": 612910, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.023002862930298, "global_step": 612911, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.037419080734253, "global_step": 612912, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9363198280334473, "global_step": 612913, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.024779796600342, "global_step": 612914, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9759966135025024, "global_step": 612915, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.100527763366699, "global_step": 612916, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.8744983673095703, "global_step": 612917, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9614274501800537, "global_step": 612918, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9806939363479614, "global_step": 612919, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9471040964126587, "global_step": 612920, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9794225692749023, "global_step": 612921, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0787038803100586, "global_step": 612922, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0085678100585938, "global_step": 612923, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9958524703979492, "global_step": 612924, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0051050186157227, "global_step": 612925, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.08790922164917, "global_step": 612926, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.987760305404663, "global_step": 612927, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9627190828323364, "global_step": 612928, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9933154582977295, "global_step": 612929, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9284312725067139, "global_step": 612930, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9418245553970337, "global_step": 612931, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9571034908294678, "global_step": 612932, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.957493543624878, "global_step": 612933, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0986881256103516, "global_step": 612934, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0963165760040283, "global_step": 612935, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.062117338180542, "global_step": 612936, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.137632131576538, "global_step": 612937, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9812278747558594, "global_step": 612938, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9937869310379028, "global_step": 612939, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.047423839569092, "global_step": 612940, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9903600215911865, "global_step": 612941, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0031001567840576, "global_step": 612942, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.01564621925354, "global_step": 612943, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0027577877044678, "global_step": 612944, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0460619926452637, "global_step": 612945, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.00943660736084, "global_step": 612946, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.031792640686035, "global_step": 612947, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0187766551971436, "global_step": 612948, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9849812984466553, "global_step": 612949, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.01924729347229, "global_step": 612950, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.03763484954834, "global_step": 612951, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.057426691055298, "global_step": 612952, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0987963676452637, "global_step": 612953, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.996482491493225, "global_step": 612954, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9648075103759766, "global_step": 612955, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.023287773132324, "global_step": 612956, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0157835483551025, "global_step": 612957, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.038449287414551, "global_step": 612958, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0038375854492188, "global_step": 612959, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9808871746063232, "global_step": 612960, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.999128818511963, "global_step": 612961, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.002479076385498, "global_step": 612962, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0542285442352295, "global_step": 612963, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0674517154693604, "global_step": 612964, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9707449674606323, "global_step": 612965, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.068941116333008, "global_step": 612966, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.024746894836426, "global_step": 612967, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9683960676193237, "global_step": 612968, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9303494691848755, "global_step": 612969, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9588364362716675, "global_step": 612970, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.981554627418518, "global_step": 612971, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9844788312911987, "global_step": 612972, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0112807750701904, "global_step": 612973, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9688224792480469, "global_step": 612974, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9621837139129639, "global_step": 612975, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9976991415023804, "global_step": 612976, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.984095573425293, "global_step": 612977, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9438222646713257, "global_step": 612978, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0461816787719727, "global_step": 612979, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0542614459991455, "global_step": 612980, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9736729860305786, "global_step": 612981, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0111284255981445, "global_step": 612982, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9764277935028076, "global_step": 612983, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9508001804351807, "global_step": 612984, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0701851844787598, "global_step": 612985, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9272133111953735, "global_step": 612986, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.996632695198059, "global_step": 612987, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9915404319763184, "global_step": 612988, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.035651445388794, "global_step": 612989, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9278688430786133, "global_step": 612990, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9848988056182861, "global_step": 612991, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0988616943359375, "global_step": 612992, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9173389673233032, "global_step": 612993, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1214656829833984, "global_step": 612994, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9747421741485596, "global_step": 612995, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0240046977996826, "global_step": 612996, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.087242841720581, "global_step": 612997, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0047214031219482, "global_step": 612998, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.964713454246521, "global_step": 612999, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.059434175491333, "global_step": 613000, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.027982473373413, "global_step": 613001, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.031803846359253, "global_step": 613002, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.061810255050659, "global_step": 613003, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.032607078552246, "global_step": 613004, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.077414035797119, "global_step": 613005, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0520427227020264, "global_step": 613006, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.036940813064575, "global_step": 613007, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0421628952026367, "global_step": 613008, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0406618118286133, "global_step": 613009, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9790066480636597, "global_step": 613010, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0099940299987793, "global_step": 613011, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9922833442687988, "global_step": 613012, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.028230905532837, "global_step": 613013, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0301876068115234, "global_step": 613014, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9949138164520264, "global_step": 613015, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0252742767333984, "global_step": 613016, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0262811183929443, "global_step": 613017, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.011359691619873, "global_step": 613018, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.010317325592041, "global_step": 613019, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0498085021972656, "global_step": 613020, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9681063890457153, "global_step": 613021, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9704203605651855, "global_step": 613022, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.035595655441284, "global_step": 613023, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0886330604553223, "global_step": 613024, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.976412296295166, "global_step": 613025, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9520128965377808, "global_step": 613026, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9875999689102173, "global_step": 613027, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0001578330993652, "global_step": 613028, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.003868579864502, "global_step": 613029, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9816452264785767, "global_step": 613030, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0481905937194824, "global_step": 613031, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.000201940536499, "global_step": 613032, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0908968448638916, "global_step": 613033, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9866838455200195, "global_step": 613034, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0328361988067627, "global_step": 613035, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0241239070892334, "global_step": 613036, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0428214073181152, "global_step": 613037, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9860308170318604, "global_step": 613038, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.029076099395752, "global_step": 613039, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.03591251373291, "global_step": 613040, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9984421730041504, "global_step": 613041, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9460663795471191, "global_step": 613042, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0315496921539307, "global_step": 613043, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9889277219772339, "global_step": 613044, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1300151348114014, "global_step": 613045, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0576095581054688, "global_step": 613046, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.064234733581543, "global_step": 613047, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0216071605682373, "global_step": 613048, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0692429542541504, "global_step": 613049, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9636319875717163, "global_step": 613050, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.026766538619995, "global_step": 613051, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0143113136291504, "global_step": 613052, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.03890323638916, "global_step": 613053, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.012906551361084, "global_step": 613054, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9954043626785278, "global_step": 613055, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0728206634521484, "global_step": 613056, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0001332759857178, "global_step": 613057, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.065528154373169, "global_step": 613058, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9634228944778442, "global_step": 613059, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1324987411499023, "global_step": 613060, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9597066640853882, "global_step": 613061, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9891413450241089, "global_step": 613062, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.991294026374817, "global_step": 613063, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9252979755401611, "global_step": 613064, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9982178211212158, "global_step": 613065, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.014176607131958, "global_step": 613066, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9849797487258911, "global_step": 613067, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.042550563812256, "global_step": 613068, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.098569631576538, "global_step": 613069, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9414931535720825, "global_step": 613070, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9781854152679443, "global_step": 613071, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9689027070999146, "global_step": 613072, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0747463703155518, "global_step": 613073, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.010594606399536, "global_step": 613074, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0032639503479004, "global_step": 613075, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1149370670318604, "global_step": 613076, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.08970046043396, "global_step": 613077, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0389771461486816, "global_step": 613078, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0482943058013916, "global_step": 613079, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9696986675262451, "global_step": 613080, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0769200325012207, "global_step": 613081, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9302723407745361, "global_step": 613082, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9626132249832153, "global_step": 613083, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.992685079574585, "global_step": 613084, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.003178119659424, "global_step": 613085, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.062929630279541, "global_step": 613086, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9962623119354248, "global_step": 613087, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9747802019119263, "global_step": 613088, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.050747871398926, "global_step": 613089, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9008853435516357, "global_step": 613090, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0568184852600098, "global_step": 613091, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.00272274017334, "global_step": 613092, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.934445858001709, "global_step": 613093, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.02321457862854, "global_step": 613094, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9534484148025513, "global_step": 613095, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0370664596557617, "global_step": 613096, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9941494464874268, "global_step": 613097, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0135979652404785, "global_step": 613098, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0284841060638428, "global_step": 613099, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.926496148109436, "global_step": 613100, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9948594570159912, "global_step": 613101, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0170035362243652, "global_step": 613102, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.8909858465194702, "global_step": 613103, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.08986496925354, "global_step": 613104, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.964141845703125, "global_step": 613105, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9848371744155884, "global_step": 613106, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9868595600128174, "global_step": 613107, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9336878061294556, "global_step": 613108, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9719196557998657, "global_step": 613109, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.025873899459839, "global_step": 613110, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9593007564544678, "global_step": 613111, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9760242700576782, "global_step": 613112, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.043455123901367, "global_step": 613113, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0573716163635254, "global_step": 613114, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.124239444732666, "global_step": 613115, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0219695568084717, "global_step": 613116, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.018575429916382, "global_step": 613117, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9612951278686523, "global_step": 613118, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.05623197555542, "global_step": 613119, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9489524364471436, "global_step": 613120, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0424277782440186, "global_step": 613121, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.043865442276001, "global_step": 613122, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9096816778182983, "global_step": 613123, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.014514446258545, "global_step": 613124, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.012056827545166, "global_step": 613125, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1117873191833496, "global_step": 613126, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.015441656112671, "global_step": 613127, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9109978675842285, "global_step": 613128, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0490145683288574, "global_step": 613129, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.003239154815674, "global_step": 613130, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9324208498001099, "global_step": 613131, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.05600905418396, "global_step": 613132, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.96986985206604, "global_step": 613133, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0396933555603027, "global_step": 613134, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.95036780834198, "global_step": 613135, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0745980739593506, "global_step": 613136, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0786943435668945, "global_step": 613137, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.087087392807007, "global_step": 613138, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0067882537841797, "global_step": 613139, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9827666282653809, "global_step": 613140, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0666165351867676, "global_step": 613141, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.001896619796753, "global_step": 613142, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.024815797805786, "global_step": 613143, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.110968828201294, "global_step": 613144, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9512412548065186, "global_step": 613145, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0411856174468994, "global_step": 613146, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0231330394744873, "global_step": 613147, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.021014451980591, "global_step": 613148, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.087808132171631, "global_step": 613149, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0014121532440186, "global_step": 613150, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0345020294189453, "global_step": 613151, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9568989276885986, "global_step": 613152, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9474034309387207, "global_step": 613153, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9438858032226562, "global_step": 613154, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0263571739196777, "global_step": 613155, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.068701982498169, "global_step": 613156, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.980654001235962, "global_step": 613157, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9027239084243774, "global_step": 613158, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.927034854888916, "global_step": 613159, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.071612596511841, "global_step": 613160, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1472694873809814, "global_step": 613161, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.016840934753418, "global_step": 613162, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9624460935592651, "global_step": 613163, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.025421380996704, "global_step": 613164, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9465793371200562, "global_step": 613165, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9969204664230347, "global_step": 613166, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0257396697998047, "global_step": 613167, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0204920768737793, "global_step": 613168, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.082796096801758, "global_step": 613169, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.04225754737854, "global_step": 613170, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.979725956916809, "global_step": 613171, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.018937349319458, "global_step": 613172, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.960070013999939, "global_step": 613173, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9918891191482544, "global_step": 613174, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9616326093673706, "global_step": 613175, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0425965785980225, "global_step": 613176, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0119240283966064, "global_step": 613177, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.023228883743286, "global_step": 613178, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.005734920501709, "global_step": 613179, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0387401580810547, "global_step": 613180, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0699760913848877, "global_step": 613181, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0079004764556885, "global_step": 613182, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0290603637695312, "global_step": 613183, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.972139835357666, "global_step": 613184, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.075080156326294, "global_step": 613185, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9824539422988892, "global_step": 613186, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9805184602737427, "global_step": 613187, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.100257396697998, "global_step": 613188, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.974579095840454, "global_step": 613189, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9295603036880493, "global_step": 613190, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9694985151290894, "global_step": 613191, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9618098735809326, "global_step": 613192, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9850969314575195, "global_step": 613193, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.063659906387329, "global_step": 613194, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.084827423095703, "global_step": 613195, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.993525505065918, "global_step": 613196, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0125350952148438, "global_step": 613197, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9774138927459717, "global_step": 613198, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0622851848602295, "global_step": 613199, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.049736261367798, "global_step": 613200, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0953800678253174, "global_step": 613201, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9954699277877808, "global_step": 613202, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0173404216766357, "global_step": 613203, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0233678817749023, "global_step": 613204, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9482271671295166, "global_step": 613205, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9542211294174194, "global_step": 613206, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1401917934417725, "global_step": 613207, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.987433910369873, "global_step": 613208, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0459492206573486, "global_step": 613209, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.953705906867981, "global_step": 613210, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9706273078918457, "global_step": 613211, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0653977394104004, "global_step": 613212, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.995986819267273, "global_step": 613213, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0018157958984375, "global_step": 613214, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9867552518844604, "global_step": 613215, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9991897344589233, "global_step": 613216, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9497649669647217, "global_step": 613217, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.032467842102051, "global_step": 613218, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9757380485534668, "global_step": 613219, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9447650909423828, "global_step": 613220, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9018187522888184, "global_step": 613221, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.917527198791504, "global_step": 613222, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.001120090484619, "global_step": 613223, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.082306385040283, "global_step": 613224, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.091163158416748, "global_step": 613225, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.927270531654358, "global_step": 613226, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9713513851165771, "global_step": 613227, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9351924657821655, "global_step": 613228, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.01308274269104, "global_step": 613229, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.011815309524536, "global_step": 613230, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9393084049224854, "global_step": 613231, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9679806232452393, "global_step": 613232, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0429651737213135, "global_step": 613233, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.993618369102478, "global_step": 613234, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.027841806411743, "global_step": 613235, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.06962513923645, "global_step": 613236, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.043833017349243, "global_step": 613237, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0284786224365234, "global_step": 613238, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0298421382904053, "global_step": 613239, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0256032943725586, "global_step": 613240, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.064570665359497, "global_step": 613241, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9807713031768799, "global_step": 613242, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9843573570251465, "global_step": 613243, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9845311641693115, "global_step": 613244, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0435190200805664, "global_step": 613245, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0388102531433105, "global_step": 613246, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9719823598861694, "global_step": 613247, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0075817108154297, "global_step": 613248, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0114638805389404, "global_step": 613249, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0649373531341553, "global_step": 613250, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.963857889175415, "global_step": 613251, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0203311443328857, "global_step": 613252, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9583014249801636, "global_step": 613253, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9509481191635132, "global_step": 613254, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0392227172851562, "global_step": 613255, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0711417198181152, "global_step": 613256, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0341684818267822, "global_step": 613257, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.072570562362671, "global_step": 613258, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9544267654418945, "global_step": 613259, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9741740226745605, "global_step": 613260, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9989583492279053, "global_step": 613261, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1063835620880127, "global_step": 613262, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9637075662612915, "global_step": 613263, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.016860246658325, "global_step": 613264, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.063598155975342, "global_step": 613265, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0314698219299316, "global_step": 613266, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.010685920715332, "global_step": 613267, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9691134691238403, "global_step": 613268, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9872478246688843, "global_step": 613269, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.987517237663269, "global_step": 613270, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.031290054321289, "global_step": 613271, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0080060958862305, "global_step": 613272, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9759341478347778, "global_step": 613273, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.009939432144165, "global_step": 613274, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9914491176605225, "global_step": 613275, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9679145812988281, "global_step": 613276, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0237326622009277, "global_step": 613277, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0246288776397705, "global_step": 613278, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1191043853759766, "global_step": 613279, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9426180124282837, "global_step": 613280, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9933295249938965, "global_step": 613281, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9564927816390991, "global_step": 613282, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9771572351455688, "global_step": 613283, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9535421133041382, "global_step": 613284, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9519524574279785, "global_step": 613285, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.03676438331604, "global_step": 613286, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0023372173309326, "global_step": 613287, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.962881088256836, "global_step": 613288, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9691839218139648, "global_step": 613289, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.017955780029297, "global_step": 613290, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.04892635345459, "global_step": 613291, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9326715469360352, "global_step": 613292, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.055605888366699, "global_step": 613293, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1068410873413086, "global_step": 613294, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.048415422439575, "global_step": 613295, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.050311326980591, "global_step": 613296, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.01033091545105, "global_step": 613297, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9997762441635132, "global_step": 613298, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0057373046875, "global_step": 613299, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9701616764068604, "global_step": 613300, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0783512592315674, "global_step": 613301, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9162898063659668, "global_step": 613302, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9447546005249023, "global_step": 613303, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9637439250946045, "global_step": 613304, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0505592823028564, "global_step": 613305, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9711222648620605, "global_step": 613306, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.08671498298645, "global_step": 613307, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.002490997314453, "global_step": 613308, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9620612859725952, "global_step": 613309, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0061330795288086, "global_step": 613310, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9635841846466064, "global_step": 613311, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0775444507598877, "global_step": 613312, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0151987075805664, "global_step": 613313, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.042198657989502, "global_step": 613314, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9952092170715332, "global_step": 613315, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0381977558135986, "global_step": 613316, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.025179862976074, "global_step": 613317, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1077985763549805, "global_step": 613318, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0098559856414795, "global_step": 613319, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0375940799713135, "global_step": 613320, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.902567982673645, "global_step": 613321, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0108284950256348, "global_step": 613322, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1232800483703613, "global_step": 613323, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0718796253204346, "global_step": 613324, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9952677488327026, "global_step": 613325, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9325227737426758, "global_step": 613326, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0306403636932373, "global_step": 613327, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.028061628341675, "global_step": 613328, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0764570236206055, "global_step": 613329, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0866870880126953, "global_step": 613330, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0503194332122803, "global_step": 613331, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9586358070373535, "global_step": 613332, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9710144996643066, "global_step": 613333, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9939097166061401, "global_step": 613334, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.058539867401123, "global_step": 613335, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0012943744659424, "global_step": 613336, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9275157451629639, "global_step": 613337, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.053330898284912, "global_step": 613338, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.030210256576538, "global_step": 613339, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0381741523742676, "global_step": 613340, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0825486183166504, "global_step": 613341, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.094835042953491, "global_step": 613342, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0901458263397217, "global_step": 613343, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9794039726257324, "global_step": 613344, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9320812225341797, "global_step": 613345, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.055203676223755, "global_step": 613346, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9838354587554932, "global_step": 613347, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9393672943115234, "global_step": 613348, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9384596347808838, "global_step": 613349, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0522820949554443, "global_step": 613350, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9530599117279053, "global_step": 613351, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0062248706817627, "global_step": 613352, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.992106318473816, "global_step": 613353, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9705469608306885, "global_step": 613354, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0842361450195312, "global_step": 613355, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9788835048675537, "global_step": 613356, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9628777503967285, "global_step": 613357, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.007437229156494, "global_step": 613358, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.081191301345825, "global_step": 613359, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9413492679595947, "global_step": 613360, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0416977405548096, "global_step": 613361, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.078946113586426, "global_step": 613362, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0134878158569336, "global_step": 613363, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9654828310012817, "global_step": 613364, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0627341270446777, "global_step": 613365, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.022998332977295, "global_step": 613366, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9627788066864014, "global_step": 613367, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9996325969696045, "global_step": 613368, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0832176208496094, "global_step": 613369, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0945868492126465, "global_step": 613370, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.013580560684204, "global_step": 613371, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0068647861480713, "global_step": 613372, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9685401916503906, "global_step": 613373, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9889447689056396, "global_step": 613374, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.033061981201172, "global_step": 613375, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9373983144760132, "global_step": 613376, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0127151012420654, "global_step": 613377, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0289361476898193, "global_step": 613378, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1223175525665283, "global_step": 613379, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0256869792938232, "global_step": 613380, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0429036617279053, "global_step": 613381, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0150325298309326, "global_step": 613382, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.035656213760376, "global_step": 613383, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0271694660186768, "global_step": 613384, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0346319675445557, "global_step": 613385, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.045522689819336, "global_step": 613386, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1134326457977295, "global_step": 613387, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.006895065307617, "global_step": 613388, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9846280813217163, "global_step": 613389, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9430930614471436, "global_step": 613390, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1034514904022217, "global_step": 613391, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.050442695617676, "global_step": 613392, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.105724573135376, "global_step": 613393, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.08976149559021, "global_step": 613394, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.010176658630371, "global_step": 613395, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0347888469696045, "global_step": 613396, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0713765621185303, "global_step": 613397, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9324854612350464, "global_step": 613398, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.99931800365448, "global_step": 613399, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9946662187576294, "global_step": 613400, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9849690198898315, "global_step": 613401, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9464308023452759, "global_step": 613402, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0188558101654053, "global_step": 613403, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.8930119276046753, "global_step": 613404, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9464802742004395, "global_step": 613405, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9641573429107666, "global_step": 613406, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9095211029052734, "global_step": 613407, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9674968719482422, "global_step": 613408, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9795573949813843, "global_step": 613409, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9892240762710571, "global_step": 613410, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9948372840881348, "global_step": 613411, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9932488203048706, "global_step": 613412, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.968004822731018, "global_step": 613413, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.005530595779419, "global_step": 613414, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0051794052124023, "global_step": 613415, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0634591579437256, "global_step": 613416, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0531880855560303, "global_step": 613417, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9656805992126465, "global_step": 613418, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0474908351898193, "global_step": 613419, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9459967613220215, "global_step": 613420, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9875980615615845, "global_step": 613421, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.03149676322937, "global_step": 613422, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.055981159210205, "global_step": 613423, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9752655029296875, "global_step": 613424, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.01243257522583, "global_step": 613425, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9560716152191162, "global_step": 613426, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.009251594543457, "global_step": 613427, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.046353340148926, "global_step": 613428, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0098257064819336, "global_step": 613429, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.111765146255493, "global_step": 613430, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.030395269393921, "global_step": 613431, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.030141830444336, "global_step": 613432, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1870369911193848, "global_step": 613433, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0436573028564453, "global_step": 613434, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.064295530319214, "global_step": 613435, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9368896484375, "global_step": 613436, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9759175777435303, "global_step": 613437, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0226857662200928, "global_step": 613438, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0297605991363525, "global_step": 613439, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.13883900642395, "global_step": 613440, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.999660611152649, "global_step": 613441, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0504403114318848, "global_step": 613442, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0614233016967773, "global_step": 613443, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0185706615448, "global_step": 613444, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0587215423583984, "global_step": 613445, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0418155193328857, "global_step": 613446, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.014852523803711, "global_step": 613447, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0596609115600586, "global_step": 613448, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0194733142852783, "global_step": 613449, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.043964147567749, "global_step": 613450, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.041128635406494, "global_step": 613451, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9846539497375488, "global_step": 613452, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.020047664642334, "global_step": 613453, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.974195957183838, "global_step": 613454, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.036600112915039, "global_step": 613455, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0297346115112305, "global_step": 613456, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0355653762817383, "global_step": 613457, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9595491886138916, "global_step": 613458, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.986126184463501, "global_step": 613459, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0782463550567627, "global_step": 613460, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9352712631225586, "global_step": 613461, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9633386135101318, "global_step": 613462, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.022850275039673, "global_step": 613463, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.059502601623535, "global_step": 613464, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9701342582702637, "global_step": 613465, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9959849119186401, "global_step": 613466, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0625295639038086, "global_step": 613467, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1232705116271973, "global_step": 613468, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.052276849746704, "global_step": 613469, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.176332473754883, "global_step": 613470, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9643163681030273, "global_step": 613471, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0226430892944336, "global_step": 613472, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.038606882095337, "global_step": 613473, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.044717311859131, "global_step": 613474, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.998213768005371, "global_step": 613475, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.080263376235962, "global_step": 613476, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.022714138031006, "global_step": 613477, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9635272026062012, "global_step": 613478, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.985297441482544, "global_step": 613479, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9852299690246582, "global_step": 613480, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9972634315490723, "global_step": 613481, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.1326465606689453, "global_step": 613482, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9565337896347046, "global_step": 613483, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.027629852294922, "global_step": 613484, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0305063724517822, "global_step": 613485, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9932502508163452, "global_step": 613486, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0685935020446777, "global_step": 613487, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0546109676361084, "global_step": 613488, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.06013822555542, "global_step": 613489, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9980003833770752, "global_step": 613490, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9311132431030273, "global_step": 613491, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0521085262298584, "global_step": 613492, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0218403339385986, "global_step": 613493, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9727810621261597, "global_step": 613494, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.986486554145813, "global_step": 613495, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.060041666030884, "global_step": 613496, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9271411895751953, "global_step": 613497, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0629630088806152, "global_step": 613498, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0447871685028076, "global_step": 613499, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9794422388076782, "global_step": 613500, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.991330623626709, "global_step": 613501, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.003420114517212, "global_step": 613502, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.99375581741333, "global_step": 613503, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0021538734436035, "global_step": 613504, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.0791242122650146, "global_step": 613505, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.980295181274414, "global_step": 613506, "epoch": 982, "lr": 5e-05}
{"train_loss": 1.9888051748275757, "global_step": 613507, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.080958127975464, "global_step": 613508, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.008134603500366, "global_step": 613509, "epoch": 982, "lr": 5e-05}
{"train_loss": 2.02152681350708, "global_step": 613510, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0271291732788086, "global_step": 613511, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0022940635681152, "global_step": 613512, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.057532548904419, "global_step": 613513, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9583264589309692, "global_step": 613514, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9254200458526611, "global_step": 613515, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0378222465515137, "global_step": 613516, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0104892253875732, "global_step": 613517, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0115561485290527, "global_step": 613518, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9793658256530762, "global_step": 613519, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.938975214958191, "global_step": 613520, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.007676839828491, "global_step": 613521, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9524779319763184, "global_step": 613522, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.052405834197998, "global_step": 613523, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9609078168869019, "global_step": 613524, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0295000076293945, "global_step": 613525, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0086302757263184, "global_step": 613526, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9878815412521362, "global_step": 613527, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0587167739868164, "global_step": 613528, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0048441886901855, "global_step": 613529, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.007966995239258, "global_step": 613530, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.020315170288086, "global_step": 613531, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0014476776123047, "global_step": 613532, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.08626651763916, "global_step": 613533, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.057814598083496, "global_step": 613534, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.911245584487915, "global_step": 613535, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0363149642944336, "global_step": 613536, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9545084238052368, "global_step": 613537, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0493199825286865, "global_step": 613538, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0199649333953857, "global_step": 613539, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.97922682762146, "global_step": 613540, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9407304525375366, "global_step": 613541, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9216123819351196, "global_step": 613542, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9974346160888672, "global_step": 613543, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.988006830215454, "global_step": 613544, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9848086833953857, "global_step": 613545, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9140950441360474, "global_step": 613546, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0969038009643555, "global_step": 613547, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9328309297561646, "global_step": 613548, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.012693405151367, "global_step": 613549, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.054379940032959, "global_step": 613550, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9534339904785156, "global_step": 613551, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9871145486831665, "global_step": 613552, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9948127269744873, "global_step": 613553, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.999480962753296, "global_step": 613554, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0056283473968506, "global_step": 613555, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.046022653579712, "global_step": 613556, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.1096901893615723, "global_step": 613557, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.954628825187683, "global_step": 613558, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0457587242126465, "global_step": 613559, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.981200098991394, "global_step": 613560, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.970079779624939, "global_step": 613561, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.970664620399475, "global_step": 613562, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0395421981811523, "global_step": 613563, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0254099369049072, "global_step": 613564, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9483740329742432, "global_step": 613565, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.1676933765411377, "global_step": 613566, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.052102565765381, "global_step": 613567, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0624890327453613, "global_step": 613568, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9572232961654663, "global_step": 613569, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.034449577331543, "global_step": 613570, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9882320165634155, "global_step": 613571, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.019345283508301, "global_step": 613572, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.943766713142395, "global_step": 613573, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0615527629852295, "global_step": 613574, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9972712993621826, "global_step": 613575, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9627087116241455, "global_step": 613576, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9350956678390503, "global_step": 613577, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.055264711380005, "global_step": 613578, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9573613405227661, "global_step": 613579, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.1077847480773926, "global_step": 613580, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.014817476272583, "global_step": 613581, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9603105783462524, "global_step": 613582, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.968273401260376, "global_step": 613583, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0696802139282227, "global_step": 613584, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.00722599029541, "global_step": 613585, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.073699474334717, "global_step": 613586, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.938967227935791, "global_step": 613587, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9801075458526611, "global_step": 613588, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0652401447296143, "global_step": 613589, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9848400354385376, "global_step": 613590, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.026026487350464, "global_step": 613591, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9901189804077148, "global_step": 613592, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9965146780014038, "global_step": 613593, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9650996923446655, "global_step": 613594, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0010664463043213, "global_step": 613595, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9739797115325928, "global_step": 613596, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0644185543060303, "global_step": 613597, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9688584804534912, "global_step": 613598, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9417699575424194, "global_step": 613599, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.018228769302368, "global_step": 613600, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.115654468536377, "global_step": 613601, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.019510507583618, "global_step": 613602, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.04162335395813, "global_step": 613603, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9344937801361084, "global_step": 613604, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9517838954925537, "global_step": 613605, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.085279941558838, "global_step": 613606, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.025315284729004, "global_step": 613607, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9260997772216797, "global_step": 613608, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0259125232696533, "global_step": 613609, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.05047345161438, "global_step": 613610, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.056751012802124, "global_step": 613611, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0515592098236084, "global_step": 613612, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9713804721832275, "global_step": 613613, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0086662769317627, "global_step": 613614, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0221445560455322, "global_step": 613615, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9507050514221191, "global_step": 613616, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.007143497467041, "global_step": 613617, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9591141939163208, "global_step": 613618, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9962742328643799, "global_step": 613619, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9362539052963257, "global_step": 613620, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.991145133972168, "global_step": 613621, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0093629360198975, "global_step": 613622, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9356467723846436, "global_step": 613623, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9786512851715088, "global_step": 613624, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.069154739379883, "global_step": 613625, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0575125217437744, "global_step": 613626, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.008787155151367, "global_step": 613627, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.992490291595459, "global_step": 613628, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.1481709480285645, "global_step": 613629, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.068638324737549, "global_step": 613630, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.011317253112793, "global_step": 613631, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.965688705444336, "global_step": 613632, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9964570999145508, "global_step": 613633, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.018395185470581, "global_step": 613634, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9988045692443848, "global_step": 613635, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.038611650466919, "global_step": 613636, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9572033882141113, "global_step": 613637, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.056866407394409, "global_step": 613638, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9881911277770996, "global_step": 613639, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.928976058959961, "global_step": 613640, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0808019638061523, "global_step": 613641, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.045060157775879, "global_step": 613642, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0832631587982178, "global_step": 613643, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.945103645324707, "global_step": 613644, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.021773099899292, "global_step": 613645, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.040574073791504, "global_step": 613646, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.078660488128662, "global_step": 613647, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9959142208099365, "global_step": 613648, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9847936630249023, "global_step": 613649, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9901587963104248, "global_step": 613650, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9143704175949097, "global_step": 613651, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9705597162246704, "global_step": 613652, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.975161075592041, "global_step": 613653, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9837154150009155, "global_step": 613654, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0654375553131104, "global_step": 613655, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.011850595474243, "global_step": 613656, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9285829067230225, "global_step": 613657, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9682536125183105, "global_step": 613658, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.018285036087036, "global_step": 613659, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0628340244293213, "global_step": 613660, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0644547939300537, "global_step": 613661, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9384093284606934, "global_step": 613662, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0853309631347656, "global_step": 613663, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9767215251922607, "global_step": 613664, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.002140522003174, "global_step": 613665, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9590330123901367, "global_step": 613666, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9263145923614502, "global_step": 613667, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0177571773529053, "global_step": 613668, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9785270690917969, "global_step": 613669, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9986218214035034, "global_step": 613670, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9205952882766724, "global_step": 613671, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0338118076324463, "global_step": 613672, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.96826171875, "global_step": 613673, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.012915849685669, "global_step": 613674, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9919111728668213, "global_step": 613675, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.974304437637329, "global_step": 613676, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9894967079162598, "global_step": 613677, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.976793646812439, "global_step": 613678, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9546921253204346, "global_step": 613679, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.070817708969116, "global_step": 613680, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.982498049736023, "global_step": 613681, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0364573001861572, "global_step": 613682, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0028417110443115, "global_step": 613683, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.023019790649414, "global_step": 613684, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9366990327835083, "global_step": 613685, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.968796968460083, "global_step": 613686, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9780538082122803, "global_step": 613687, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.978925108909607, "global_step": 613688, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0374257564544678, "global_step": 613689, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.983521580696106, "global_step": 613690, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.009037733078003, "global_step": 613691, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9614222049713135, "global_step": 613692, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.96366286277771, "global_step": 613693, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.020153284072876, "global_step": 613694, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.913985013961792, "global_step": 613695, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9876041412353516, "global_step": 613696, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9702309370040894, "global_step": 613697, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9584722518920898, "global_step": 613698, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9938853979110718, "global_step": 613699, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9610819816589355, "global_step": 613700, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0033957958221436, "global_step": 613701, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0661165714263916, "global_step": 613702, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.045548439025879, "global_step": 613703, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9886287450790405, "global_step": 613704, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0009002685546875, "global_step": 613705, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0231199264526367, "global_step": 613706, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.956695318222046, "global_step": 613707, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9411213397979736, "global_step": 613708, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9761985540390015, "global_step": 613709, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9730212688446045, "global_step": 613710, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9383691549301147, "global_step": 613711, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9604971408843994, "global_step": 613712, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0184924602508545, "global_step": 613713, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9904487133026123, "global_step": 613714, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9844739437103271, "global_step": 613715, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9829175472259521, "global_step": 613716, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.942635178565979, "global_step": 613717, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9914036989212036, "global_step": 613718, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9482847452163696, "global_step": 613719, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9730660915374756, "global_step": 613720, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9835126399993896, "global_step": 613721, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.1029717922210693, "global_step": 613722, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9759601354599, "global_step": 613723, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0391292572021484, "global_step": 613724, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.000398635864258, "global_step": 613725, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0064690113067627, "global_step": 613726, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9426509141921997, "global_step": 613727, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9448925256729126, "global_step": 613728, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0137135982513428, "global_step": 613729, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9695268869400024, "global_step": 613730, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9759256839752197, "global_step": 613731, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9579229354858398, "global_step": 613732, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0502705574035645, "global_step": 613733, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0294559001922607, "global_step": 613734, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9275016784667969, "global_step": 613735, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9184931516647339, "global_step": 613736, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0118842124938965, "global_step": 613737, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9695546627044678, "global_step": 613738, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0058436393737793, "global_step": 613739, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9984898567199707, "global_step": 613740, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.8995387554168701, "global_step": 613741, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9923380613327026, "global_step": 613742, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0801641941070557, "global_step": 613743, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.012077808380127, "global_step": 613744, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.020986557006836, "global_step": 613745, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.962744951248169, "global_step": 613746, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0319106578826904, "global_step": 613747, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0434422492980957, "global_step": 613748, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.058175563812256, "global_step": 613749, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9800363779067993, "global_step": 613750, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9378843307495117, "global_step": 613751, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9353845119476318, "global_step": 613752, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.07625412940979, "global_step": 613753, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.044459819793701, "global_step": 613754, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0129215717315674, "global_step": 613755, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.8856340646743774, "global_step": 613756, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9788213968276978, "global_step": 613757, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9106063842773438, "global_step": 613758, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0109684467315674, "global_step": 613759, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.025959014892578, "global_step": 613760, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0445494651794434, "global_step": 613761, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0124518871307373, "global_step": 613762, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0504183769226074, "global_step": 613763, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0305724143981934, "global_step": 613764, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.007096290588379, "global_step": 613765, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.075345993041992, "global_step": 613766, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.000060558319092, "global_step": 613767, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0506160259246826, "global_step": 613768, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0227818489074707, "global_step": 613769, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9835180044174194, "global_step": 613770, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0627501010894775, "global_step": 613771, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.049142837524414, "global_step": 613772, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0241591930389404, "global_step": 613773, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9059466123580933, "global_step": 613774, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.059251070022583, "global_step": 613775, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0246992111206055, "global_step": 613776, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9999455213546753, "global_step": 613777, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0863633155822754, "global_step": 613778, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.006208896636963, "global_step": 613779, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.063271999359131, "global_step": 613780, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.98005211353302, "global_step": 613781, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.94264817237854, "global_step": 613782, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9118423461914062, "global_step": 613783, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.070693254470825, "global_step": 613784, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0245277881622314, "global_step": 613785, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0245940685272217, "global_step": 613786, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0105080604553223, "global_step": 613787, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9374911785125732, "global_step": 613788, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9618562459945679, "global_step": 613789, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0581986904144287, "global_step": 613790, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9388742446899414, "global_step": 613791, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0845515727996826, "global_step": 613792, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9955244064331055, "global_step": 613793, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9664764404296875, "global_step": 613794, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0343410968780518, "global_step": 613795, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0281243324279785, "global_step": 613796, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.058755874633789, "global_step": 613797, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9637254476547241, "global_step": 613798, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9638848304748535, "global_step": 613799, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9069119691848755, "global_step": 613800, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0545642375946045, "global_step": 613801, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.038067579269409, "global_step": 613802, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9630533456802368, "global_step": 613803, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9356729984283447, "global_step": 613804, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9363932609558105, "global_step": 613805, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.031696319580078, "global_step": 613806, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0167064666748047, "global_step": 613807, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.979642629623413, "global_step": 613808, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.043488025665283, "global_step": 613809, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0518014430999756, "global_step": 613810, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9647948741912842, "global_step": 613811, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.025847911834717, "global_step": 613812, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9286900758743286, "global_step": 613813, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.089076280593872, "global_step": 613814, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9796456098556519, "global_step": 613815, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0265700817108154, "global_step": 613816, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.046154499053955, "global_step": 613817, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9846419095993042, "global_step": 613818, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0211808681488037, "global_step": 613819, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0287277698516846, "global_step": 613820, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9336271286010742, "global_step": 613821, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.1187069416046143, "global_step": 613822, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0452260971069336, "global_step": 613823, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.014681339263916, "global_step": 613824, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.998258113861084, "global_step": 613825, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0685784816741943, "global_step": 613826, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.007807493209839, "global_step": 613827, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.908922791481018, "global_step": 613828, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9727715253829956, "global_step": 613829, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0375893115997314, "global_step": 613830, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.983652949333191, "global_step": 613831, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9947946071624756, "global_step": 613832, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9953792095184326, "global_step": 613833, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9769558906555176, "global_step": 613834, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9996384382247925, "global_step": 613835, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.033565044403076, "global_step": 613836, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0297930240631104, "global_step": 613837, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0014071464538574, "global_step": 613838, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9795597791671753, "global_step": 613839, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9533110857009888, "global_step": 613840, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0141687393188477, "global_step": 613841, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.928318977355957, "global_step": 613842, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.913057804107666, "global_step": 613843, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9692500829696655, "global_step": 613844, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.092670202255249, "global_step": 613845, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9762187004089355, "global_step": 613846, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.002753496170044, "global_step": 613847, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.038839340209961, "global_step": 613848, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.038726806640625, "global_step": 613849, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.951027512550354, "global_step": 613850, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9418035745620728, "global_step": 613851, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9810653924942017, "global_step": 613852, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0362634658813477, "global_step": 613853, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9959983825683594, "global_step": 613854, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.000866174697876, "global_step": 613855, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9662625789642334, "global_step": 613856, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9736348390579224, "global_step": 613857, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9141466617584229, "global_step": 613858, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9872791767120361, "global_step": 613859, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9177453517913818, "global_step": 613860, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9986860752105713, "global_step": 613861, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0060653686523438, "global_step": 613862, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0099222660064697, "global_step": 613863, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9762095212936401, "global_step": 613864, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.973262071609497, "global_step": 613865, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.950486660003662, "global_step": 613866, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.1242260932922363, "global_step": 613867, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0350794792175293, "global_step": 613868, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.028665781021118, "global_step": 613869, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.944907307624817, "global_step": 613870, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.049877405166626, "global_step": 613871, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0460169315338135, "global_step": 613872, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0122509002685547, "global_step": 613873, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.00081729888916, "global_step": 613874, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0905604362487793, "global_step": 613875, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.066249132156372, "global_step": 613876, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0473499298095703, "global_step": 613877, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.999180555343628, "global_step": 613878, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.957732081413269, "global_step": 613879, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.011093854904175, "global_step": 613880, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9658900499343872, "global_step": 613881, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.007195234298706, "global_step": 613882, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9932384490966797, "global_step": 613883, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0947163105010986, "global_step": 613884, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9925751686096191, "global_step": 613885, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.021526336669922, "global_step": 613886, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.919348955154419, "global_step": 613887, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.077936887741089, "global_step": 613888, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9273831844329834, "global_step": 613889, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9806146621704102, "global_step": 613890, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.024303674697876, "global_step": 613891, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9875166416168213, "global_step": 613892, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9971104860305786, "global_step": 613893, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.050126552581787, "global_step": 613894, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.95937979221344, "global_step": 613895, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9021590948104858, "global_step": 613896, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0237877368927, "global_step": 613897, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9209917783737183, "global_step": 613898, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9951058626174927, "global_step": 613899, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.011970281600952, "global_step": 613900, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.054861068725586, "global_step": 613901, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.975869059562683, "global_step": 613902, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9657089710235596, "global_step": 613903, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0888900756835938, "global_step": 613904, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.001143217086792, "global_step": 613905, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9441814422607422, "global_step": 613906, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0179102420806885, "global_step": 613907, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9802379608154297, "global_step": 613908, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.029074192047119, "global_step": 613909, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9428519010543823, "global_step": 613910, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.020371913909912, "global_step": 613911, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.932137131690979, "global_step": 613912, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.939598798751831, "global_step": 613913, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0251588821411133, "global_step": 613914, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9798855781555176, "global_step": 613915, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.979555368423462, "global_step": 613916, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9942995309829712, "global_step": 613917, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.013658046722412, "global_step": 613918, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9854322671890259, "global_step": 613919, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.031691551208496, "global_step": 613920, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.028007984161377, "global_step": 613921, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9346764087677002, "global_step": 613922, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.985201358795166, "global_step": 613923, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.097585439682007, "global_step": 613924, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.00146746635437, "global_step": 613925, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9311645030975342, "global_step": 613926, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0277419090270996, "global_step": 613927, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.062577724456787, "global_step": 613928, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.040195941925049, "global_step": 613929, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9923685789108276, "global_step": 613930, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0102314949035645, "global_step": 613931, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9859422445297241, "global_step": 613932, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.056724786758423, "global_step": 613933, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9271574020385742, "global_step": 613934, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.928140640258789, "global_step": 613935, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0630950927734375, "global_step": 613936, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0185940265655518, "global_step": 613937, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0390679836273193, "global_step": 613938, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.021291971206665, "global_step": 613939, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.037212371826172, "global_step": 613940, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9989955425262451, "global_step": 613941, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0237269401550293, "global_step": 613942, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9909731149673462, "global_step": 613943, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.96746027469635, "global_step": 613944, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0648841857910156, "global_step": 613945, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9716920852661133, "global_step": 613946, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9818333387374878, "global_step": 613947, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.009739637374878, "global_step": 613948, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.018758535385132, "global_step": 613949, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9784934520721436, "global_step": 613950, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0365889072418213, "global_step": 613951, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0688531398773193, "global_step": 613952, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.959964394569397, "global_step": 613953, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0858407020568848, "global_step": 613954, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9658499956130981, "global_step": 613955, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0429532527923584, "global_step": 613956, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9818743467330933, "global_step": 613957, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.102114200592041, "global_step": 613958, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.042990207672119, "global_step": 613959, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.082843780517578, "global_step": 613960, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.975921630859375, "global_step": 613961, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0250649452209473, "global_step": 613962, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.92184579372406, "global_step": 613963, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0176217555999756, "global_step": 613964, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.025604724884033, "global_step": 613965, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0100529193878174, "global_step": 613966, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0734522342681885, "global_step": 613967, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.029771327972412, "global_step": 613968, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9676306247711182, "global_step": 613969, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.013601779937744, "global_step": 613970, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0124969482421875, "global_step": 613971, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.013578414916992, "global_step": 613972, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9730030298233032, "global_step": 613973, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.051116704940796, "global_step": 613974, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.967590093612671, "global_step": 613975, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9510927200317383, "global_step": 613976, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.008434295654297, "global_step": 613977, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.022068500518799, "global_step": 613978, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0380125045776367, "global_step": 613979, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.041228771209717, "global_step": 613980, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0249013900756836, "global_step": 613981, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.037611246109009, "global_step": 613982, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9715158939361572, "global_step": 613983, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.061582326889038, "global_step": 613984, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.965526819229126, "global_step": 613985, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9805326461791992, "global_step": 613986, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9824225902557373, "global_step": 613987, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9951374530792236, "global_step": 613988, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.021531343460083, "global_step": 613989, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9878307580947876, "global_step": 613990, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0015487670898438, "global_step": 613991, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9937962293624878, "global_step": 613992, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.018791437149048, "global_step": 613993, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.982177734375, "global_step": 613994, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0729451179504395, "global_step": 613995, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0197412967681885, "global_step": 613996, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0066680908203125, "global_step": 613997, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9524829387664795, "global_step": 613998, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0203969478607178, "global_step": 613999, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.001032829284668, "global_step": 614000, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9667710065841675, "global_step": 614001, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.091848850250244, "global_step": 614002, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.972774863243103, "global_step": 614003, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0399770736694336, "global_step": 614004, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9446057081222534, "global_step": 614005, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9139024019241333, "global_step": 614006, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0671322345733643, "global_step": 614007, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.060615301132202, "global_step": 614008, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9773985147476196, "global_step": 614009, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.001042366027832, "global_step": 614010, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9980401992797852, "global_step": 614011, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.039116382598877, "global_step": 614012, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0316526889801025, "global_step": 614013, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.039363384246826, "global_step": 614014, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0645742416381836, "global_step": 614015, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.072600841522217, "global_step": 614016, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0042660236358643, "global_step": 614017, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.1107916831970215, "global_step": 614018, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9976866245269775, "global_step": 614019, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9754265546798706, "global_step": 614020, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.039151906967163, "global_step": 614021, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0405826568603516, "global_step": 614022, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0782597064971924, "global_step": 614023, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.026780366897583, "global_step": 614024, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.021688938140869, "global_step": 614025, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9475499391555786, "global_step": 614026, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9507602453231812, "global_step": 614027, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.077173948287964, "global_step": 614028, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.967288613319397, "global_step": 614029, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0362706184387207, "global_step": 614030, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0274555683135986, "global_step": 614031, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0665032863616943, "global_step": 614032, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0462684631347656, "global_step": 614033, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0729520320892334, "global_step": 614034, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.1064674854278564, "global_step": 614035, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0645971298217773, "global_step": 614036, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9634755849838257, "global_step": 614037, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.010096311569214, "global_step": 614038, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9614583253860474, "global_step": 614039, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.995782494544983, "global_step": 614040, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9990431070327759, "global_step": 614041, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.029107093811035, "global_step": 614042, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9989643096923828, "global_step": 614043, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.004077196121216, "global_step": 614044, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.01365065574646, "global_step": 614045, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.996628761291504, "global_step": 614046, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.023711681365967, "global_step": 614047, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9949634075164795, "global_step": 614048, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.004094362258911, "global_step": 614049, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0709190368652344, "global_step": 614050, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0231690406799316, "global_step": 614051, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.060267448425293, "global_step": 614052, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9971270561218262, "global_step": 614053, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9630080461502075, "global_step": 614054, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0511271953582764, "global_step": 614055, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.109556198120117, "global_step": 614056, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9989609718322754, "global_step": 614057, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.025923252105713, "global_step": 614058, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.013517379760742, "global_step": 614059, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.088021755218506, "global_step": 614060, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.056097984313965, "global_step": 614061, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0209786891937256, "global_step": 614062, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0012638568878174, "global_step": 614063, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.030071973800659, "global_step": 614064, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.047825574874878, "global_step": 614065, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.151245355606079, "global_step": 614066, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.968410849571228, "global_step": 614067, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9783600568771362, "global_step": 614068, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9784272909164429, "global_step": 614069, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.913166880607605, "global_step": 614070, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0529208183288574, "global_step": 614071, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.044616937637329, "global_step": 614072, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9926501512527466, "global_step": 614073, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.009143352508545, "global_step": 614074, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0622611045837402, "global_step": 614075, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.009410858154297, "global_step": 614076, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9792131185531616, "global_step": 614077, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0233795642852783, "global_step": 614078, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9307574033737183, "global_step": 614079, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0580503940582275, "global_step": 614080, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9399172067642212, "global_step": 614081, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0624313354492188, "global_step": 614082, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9459737539291382, "global_step": 614083, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.045941114425659, "global_step": 614084, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.138174295425415, "global_step": 614085, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.094204902648926, "global_step": 614086, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0286452770233154, "global_step": 614087, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0182180404663086, "global_step": 614088, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.99411141872406, "global_step": 614089, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.954514503479004, "global_step": 614090, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0374464988708496, "global_step": 614091, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0200960636138916, "global_step": 614092, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9548182487487793, "global_step": 614093, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.013986110687256, "global_step": 614094, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0293314456939697, "global_step": 614095, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9782508611679077, "global_step": 614096, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.041663646697998, "global_step": 614097, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.015073299407959, "global_step": 614098, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9150354862213135, "global_step": 614099, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9587255716323853, "global_step": 614100, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0078938007354736, "global_step": 614101, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.00752854347229, "global_step": 614102, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.034506320953369, "global_step": 614103, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.040374994277954, "global_step": 614104, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0315375328063965, "global_step": 614105, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0191726684570312, "global_step": 614106, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.023395538330078, "global_step": 614107, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9976941347122192, "global_step": 614108, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9838677644729614, "global_step": 614109, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.017805576324463, "global_step": 614110, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.037982940673828, "global_step": 614111, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9929572343826294, "global_step": 614112, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.080232620239258, "global_step": 614113, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9554985761642456, "global_step": 614114, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9827989339828491, "global_step": 614115, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.060917377471924, "global_step": 614116, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0693864822387695, "global_step": 614117, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9827539920806885, "global_step": 614118, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9799495935440063, "global_step": 614119, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0385568141937256, "global_step": 614120, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9886962175369263, "global_step": 614121, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.049802303314209, "global_step": 614122, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0669643878936768, "global_step": 614123, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0336403846740723, "global_step": 614124, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9665625095367432, "global_step": 614125, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.057105541229248, "global_step": 614126, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9783567190170288, "global_step": 614127, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0744125843048096, "global_step": 614128, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0196022987365723, "global_step": 614129, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9391138553619385, "global_step": 614130, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0580921173095703, "global_step": 614131, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0347299575805664, "global_step": 614132, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9931455850601196, "global_step": 614133, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0394675731658936, "global_step": 614134, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9388145208358765, "global_step": 614135, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9667521715164185, "global_step": 614136, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.039921283721924, "global_step": 614137, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9683376550674438, "global_step": 614138, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0134716033935547, "global_step": 614139, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9508816003799438, "global_step": 614140, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.005953073501587, "global_step": 614141, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.050374984741211, "global_step": 614142, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9746019840240479, "global_step": 614143, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0856266021728516, "global_step": 614144, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.057497501373291, "global_step": 614145, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.03721022605896, "global_step": 614146, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.947134017944336, "global_step": 614147, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0380971431732178, "global_step": 614148, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9431450366973877, "global_step": 614149, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0822856426239014, "global_step": 614150, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9925603866577148, "global_step": 614151, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0287375450134277, "global_step": 614152, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0665316581726074, "global_step": 614153, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.005911111831665, "global_step": 614154, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.02139949798584, "global_step": 614155, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.029024362564087, "global_step": 614156, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.941170334815979, "global_step": 614157, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0159153938293457, "global_step": 614158, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.980736255645752, "global_step": 614159, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0555508136749268, "global_step": 614160, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0133655071258545, "global_step": 614161, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9651846885681152, "global_step": 614162, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.031949996948242, "global_step": 614163, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.066509485244751, "global_step": 614164, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.145644426345825, "global_step": 614165, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9504032135009766, "global_step": 614166, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9605276584625244, "global_step": 614167, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.029451847076416, "global_step": 614168, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.00624418258667, "global_step": 614169, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9789905548095703, "global_step": 614170, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9264094829559326, "global_step": 614171, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0237605571746826, "global_step": 614172, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9920344352722168, "global_step": 614173, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9804768562316895, "global_step": 614174, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9867115020751953, "global_step": 614175, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.044999361038208, "global_step": 614176, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.1256752014160156, "global_step": 614177, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9483468532562256, "global_step": 614178, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9746309518814087, "global_step": 614179, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.064554452896118, "global_step": 614180, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0267903804779053, "global_step": 614181, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9903054237365723, "global_step": 614182, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0149474143981934, "global_step": 614183, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.008096933364868, "global_step": 614184, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.992305040359497, "global_step": 614185, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9988899230957031, "global_step": 614186, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0424392223358154, "global_step": 614187, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.053621530532837, "global_step": 614188, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0312838554382324, "global_step": 614189, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.996696949005127, "global_step": 614190, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0741524696350098, "global_step": 614191, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0986545085906982, "global_step": 614192, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0130231380462646, "global_step": 614193, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9506572484970093, "global_step": 614194, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0108959674835205, "global_step": 614195, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.979406714439392, "global_step": 614196, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0074992179870605, "global_step": 614197, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0217514038085938, "global_step": 614198, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.03505802154541, "global_step": 614199, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.018030881881714, "global_step": 614200, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9879710674285889, "global_step": 614201, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9708294868469238, "global_step": 614202, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.995714783668518, "global_step": 614203, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9841203689575195, "global_step": 614204, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0861330032348633, "global_step": 614205, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0130856037139893, "global_step": 614206, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.012906074523926, "global_step": 614207, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.024070978164673, "global_step": 614208, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9830102920532227, "global_step": 614209, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9318170547485352, "global_step": 614210, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0070056915283203, "global_step": 614211, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.131798267364502, "global_step": 614212, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.997037410736084, "global_step": 614213, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0064260959625244, "global_step": 614214, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9784789085388184, "global_step": 614215, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0188233852386475, "global_step": 614216, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.052744150161743, "global_step": 614217, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9869279861450195, "global_step": 614218, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9709023237228394, "global_step": 614219, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9267191886901855, "global_step": 614220, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.05281925201416, "global_step": 614221, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9574604034423828, "global_step": 614222, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9023606777191162, "global_step": 614223, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.091721534729004, "global_step": 614224, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.024951934814453, "global_step": 614225, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.111409902572632, "global_step": 614226, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9993494749069214, "global_step": 614227, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.009571075439453, "global_step": 614228, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.965228796005249, "global_step": 614229, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9991881847381592, "global_step": 614230, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.074954032897949, "global_step": 614231, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0150511264801025, "global_step": 614232, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.054110288619995, "global_step": 614233, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0314764976501465, "global_step": 614234, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.034027576446533, "global_step": 614235, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9660162925720215, "global_step": 614236, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.972425103187561, "global_step": 614237, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.000654458999634, "global_step": 614238, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0000674724578857, "global_step": 614239, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0664684772491455, "global_step": 614240, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9083516597747803, "global_step": 614241, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.014451026916504, "global_step": 614242, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.136052131652832, "global_step": 614243, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0498995780944824, "global_step": 614244, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9456186294555664, "global_step": 614245, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0043091773986816, "global_step": 614246, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0299432277679443, "global_step": 614247, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.048758029937744, "global_step": 614248, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0045900344848633, "global_step": 614249, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.957226037979126, "global_step": 614250, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9487158060073853, "global_step": 614251, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0192580223083496, "global_step": 614252, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9232829809188843, "global_step": 614253, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.976809024810791, "global_step": 614254, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.022718667984009, "global_step": 614255, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.98869788646698, "global_step": 614256, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9830424785614014, "global_step": 614257, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9796721935272217, "global_step": 614258, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9811851978302002, "global_step": 614259, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.037456750869751, "global_step": 614260, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9780038595199585, "global_step": 614261, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0638864040374756, "global_step": 614262, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0797410011291504, "global_step": 614263, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0104570388793945, "global_step": 614264, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9420241117477417, "global_step": 614265, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0120019912719727, "global_step": 614266, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0049731731414795, "global_step": 614267, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9963881969451904, "global_step": 614268, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.019735813140869, "global_step": 614269, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0034985542297363, "global_step": 614270, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.064401626586914, "global_step": 614271, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.114868402481079, "global_step": 614272, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.017139196395874, "global_step": 614273, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.031334400177002, "global_step": 614274, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.938163161277771, "global_step": 614275, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9613362550735474, "global_step": 614276, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.064018487930298, "global_step": 614277, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0386083126068115, "global_step": 614278, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0493171215057373, "global_step": 614279, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0239124298095703, "global_step": 614280, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9834963083267212, "global_step": 614281, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.042198896408081, "global_step": 614282, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.019331216812134, "global_step": 614283, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0223217010498047, "global_step": 614284, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9654126167297363, "global_step": 614285, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0446550846099854, "global_step": 614286, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0021119117736816, "global_step": 614287, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0930209159851074, "global_step": 614288, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.985924243927002, "global_step": 614289, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9948906898498535, "global_step": 614290, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9880691766738892, "global_step": 614291, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0854897499084473, "global_step": 614292, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.13236141204834, "global_step": 614293, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9785385131835938, "global_step": 614294, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.8971363306045532, "global_step": 614295, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9787203073501587, "global_step": 614296, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.055487632751465, "global_step": 614297, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9685235023498535, "global_step": 614298, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9603201150894165, "global_step": 614299, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.982662558555603, "global_step": 614300, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0825061798095703, "global_step": 614301, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0550363063812256, "global_step": 614302, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9672982692718506, "global_step": 614303, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0809884071350098, "global_step": 614304, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.037841796875, "global_step": 614305, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.052790880203247, "global_step": 614306, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0146701335906982, "global_step": 614307, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0319182872772217, "global_step": 614308, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9827598333358765, "global_step": 614309, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0545568466186523, "global_step": 614310, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0049469470977783, "global_step": 614311, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9611210823059082, "global_step": 614312, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.079577922821045, "global_step": 614313, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.078427791595459, "global_step": 614314, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.991824984550476, "global_step": 614315, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9198535680770874, "global_step": 614316, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0522172451019287, "global_step": 614317, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0364251136779785, "global_step": 614318, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9693471193313599, "global_step": 614319, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.032148838043213, "global_step": 614320, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0520596504211426, "global_step": 614321, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0602493286132812, "global_step": 614322, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0813279151916504, "global_step": 614323, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0688016414642334, "global_step": 614324, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0244665145874023, "global_step": 614325, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.092730760574341, "global_step": 614326, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9737991094589233, "global_step": 614327, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9776915311813354, "global_step": 614328, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0282061100006104, "global_step": 614329, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0819544792175293, "global_step": 614330, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9275634288787842, "global_step": 614331, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0730998516082764, "global_step": 614332, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.010136365890503, "global_step": 614333, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0206050872802734, "global_step": 614334, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0336689949035645, "global_step": 614335, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9991447925567627, "global_step": 614336, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.1373605728149414, "global_step": 614337, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9971920251846313, "global_step": 614338, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0030324459075928, "global_step": 614339, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9603241682052612, "global_step": 614340, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9499295949935913, "global_step": 614341, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9474488496780396, "global_step": 614342, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0052473545074463, "global_step": 614343, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.008769989013672, "global_step": 614344, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9493932723999023, "global_step": 614345, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.048354387283325, "global_step": 614346, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9969817399978638, "global_step": 614347, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0280394554138184, "global_step": 614348, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9088903665542603, "global_step": 614349, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0075690746307373, "global_step": 614350, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.983954668045044, "global_step": 614351, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.05521559715271, "global_step": 614352, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.024045944213867, "global_step": 614353, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.051966905593872, "global_step": 614354, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.991525411605835, "global_step": 614355, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.011789321899414, "global_step": 614356, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.032170057296753, "global_step": 614357, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9279308319091797, "global_step": 614358, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.031968355178833, "global_step": 614359, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.03529953956604, "global_step": 614360, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0478291511535645, "global_step": 614361, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.013139009475708, "global_step": 614362, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.013578176498413, "global_step": 614363, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0359227657318115, "global_step": 614364, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9029827117919922, "global_step": 614365, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9684784412384033, "global_step": 614366, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0064992904663086, "global_step": 614367, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0054845809936523, "global_step": 614368, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0677490234375, "global_step": 614369, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9849148988723755, "global_step": 614370, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9989057779312134, "global_step": 614371, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.048431873321533, "global_step": 614372, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.1069939136505127, "global_step": 614373, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.045093059539795, "global_step": 614374, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9839911460876465, "global_step": 614375, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0255990028381348, "global_step": 614376, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.02333927154541, "global_step": 614377, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9061051607131958, "global_step": 614378, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9707111120224, "global_step": 614379, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.065039873123169, "global_step": 614380, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9547181129455566, "global_step": 614381, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9645425081253052, "global_step": 614382, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0626156330108643, "global_step": 614383, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9594701528549194, "global_step": 614384, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.004654884338379, "global_step": 614385, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9304190874099731, "global_step": 614386, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9865987300872803, "global_step": 614387, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.014786720275879, "global_step": 614388, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.924131989479065, "global_step": 614389, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0069265365600586, "global_step": 614390, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.991288185119629, "global_step": 614391, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9272537231445312, "global_step": 614392, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.036895275115967, "global_step": 614393, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0141427516937256, "global_step": 614394, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9679847955703735, "global_step": 614395, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.937619686126709, "global_step": 614396, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.047745943069458, "global_step": 614397, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0540552139282227, "global_step": 614398, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9497697353363037, "global_step": 614399, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0052618980407715, "global_step": 614400, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.947990894317627, "global_step": 614401, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9875447750091553, "global_step": 614402, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0464231967926025, "global_step": 614403, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9501311779022217, "global_step": 614404, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.995963215827942, "global_step": 614405, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9094865322113037, "global_step": 614406, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9809000492095947, "global_step": 614407, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.001361608505249, "global_step": 614408, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0991687774658203, "global_step": 614409, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9920064210891724, "global_step": 614410, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9895049333572388, "global_step": 614411, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9988285303115845, "global_step": 614412, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0338168144226074, "global_step": 614413, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.019158124923706, "global_step": 614414, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0324344635009766, "global_step": 614415, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.003892183303833, "global_step": 614416, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9884874820709229, "global_step": 614417, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0223586559295654, "global_step": 614418, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.1327786445617676, "global_step": 614419, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.971791386604309, "global_step": 614420, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0889267921447754, "global_step": 614421, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9767162799835205, "global_step": 614422, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9925262928009033, "global_step": 614423, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.059685707092285, "global_step": 614424, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0535593032836914, "global_step": 614425, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.02254319190979, "global_step": 614426, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0214834213256836, "global_step": 614427, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.958311915397644, "global_step": 614428, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0519497394561768, "global_step": 614429, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.074791431427002, "global_step": 614430, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9284051656723022, "global_step": 614431, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.042029619216919, "global_step": 614432, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0482513904571533, "global_step": 614433, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9687148332595825, "global_step": 614434, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9713490009307861, "global_step": 614435, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.971657156944275, "global_step": 614436, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.015347957611084, "global_step": 614437, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0598576068878174, "global_step": 614438, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.8976036310195923, "global_step": 614439, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0475125312805176, "global_step": 614440, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.084212064743042, "global_step": 614441, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0323166847229004, "global_step": 614442, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.061767816543579, "global_step": 614443, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0102415084838867, "global_step": 614444, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.006514310836792, "global_step": 614445, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.1155331134796143, "global_step": 614446, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9834257364273071, "global_step": 614447, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0194547176361084, "global_step": 614448, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0317981243133545, "global_step": 614449, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.002948045730591, "global_step": 614450, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9691572189331055, "global_step": 614451, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.025836229324341, "global_step": 614452, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9308292865753174, "global_step": 614453, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.132563829421997, "global_step": 614454, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9772334098815918, "global_step": 614455, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.94758939743042, "global_step": 614456, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.975441575050354, "global_step": 614457, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.090280294418335, "global_step": 614458, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0359833240509033, "global_step": 614459, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9953901767730713, "global_step": 614460, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.075753688812256, "global_step": 614461, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0285818576812744, "global_step": 614462, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9691073894500732, "global_step": 614463, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9968632459640503, "global_step": 614464, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0016441345214844, "global_step": 614465, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0594756603240967, "global_step": 614466, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.041445732116699, "global_step": 614467, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.1161789894104004, "global_step": 614468, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.050321340560913, "global_step": 614469, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.976635456085205, "global_step": 614470, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.027843952178955, "global_step": 614471, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9673237800598145, "global_step": 614472, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9383645057678223, "global_step": 614473, "epoch": 983, "lr": 5e-05}
{"train_loss": 1.9720194339752197, "global_step": 614474, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.019246816635132, "global_step": 614475, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.072202444076538, "global_step": 614476, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.097250461578369, "global_step": 614477, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.0077524185180664, "global_step": 614478, "epoch": 983, "lr": 5e-05}
{"train_loss": 2.1168980598449707, "global_step": 614479, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.000338315963745, "global_step": 614480, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0445947647094727, "global_step": 614481, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0352749824523926, "global_step": 614482, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.901484727859497, "global_step": 614483, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.914754033088684, "global_step": 614484, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0143370628356934, "global_step": 614485, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9528698921203613, "global_step": 614486, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9926612377166748, "global_step": 614487, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.001741647720337, "global_step": 614488, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0294454097747803, "global_step": 614489, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.027413845062256, "global_step": 614490, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.055208444595337, "global_step": 614491, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.063260555267334, "global_step": 614492, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0446813106536865, "global_step": 614493, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.006568670272827, "global_step": 614494, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9661524295806885, "global_step": 614495, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.8504575490951538, "global_step": 614496, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9158869981765747, "global_step": 614497, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9749786853790283, "global_step": 614498, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9905884265899658, "global_step": 614499, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9938452243804932, "global_step": 614500, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.940940260887146, "global_step": 614501, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9921015501022339, "global_step": 614502, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.079482316970825, "global_step": 614503, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0593063831329346, "global_step": 614504, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9486472606658936, "global_step": 614505, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9413325786590576, "global_step": 614506, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9383454322814941, "global_step": 614507, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.984701156616211, "global_step": 614508, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0671865940093994, "global_step": 614509, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9339300394058228, "global_step": 614510, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0036394596099854, "global_step": 614511, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.955575704574585, "global_step": 614512, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0290749073028564, "global_step": 614513, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.083158493041992, "global_step": 614514, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.043128252029419, "global_step": 614515, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.001444101333618, "global_step": 614516, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9921492338180542, "global_step": 614517, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.029918670654297, "global_step": 614518, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9449684619903564, "global_step": 614519, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.981138825416565, "global_step": 614520, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.052967071533203, "global_step": 614521, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0582613945007324, "global_step": 614522, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9469126462936401, "global_step": 614523, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9767341613769531, "global_step": 614524, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.989662766456604, "global_step": 614525, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0600485801696777, "global_step": 614526, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9879357814788818, "global_step": 614527, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.026639223098755, "global_step": 614528, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9974898099899292, "global_step": 614529, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.987837791442871, "global_step": 614530, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0456795692443848, "global_step": 614531, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.973339557647705, "global_step": 614532, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9429042339324951, "global_step": 614533, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0040225982666016, "global_step": 614534, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.020827054977417, "global_step": 614535, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.069486379623413, "global_step": 614536, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9471343755722046, "global_step": 614537, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.911449670791626, "global_step": 614538, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.057664155960083, "global_step": 614539, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9674575328826904, "global_step": 614540, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0605387687683105, "global_step": 614541, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9571324586868286, "global_step": 614542, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0177741050720215, "global_step": 614543, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.025357723236084, "global_step": 614544, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0936765670776367, "global_step": 614545, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9997272491455078, "global_step": 614546, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0239222049713135, "global_step": 614547, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9927679300308228, "global_step": 614548, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9152554273605347, "global_step": 614549, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.93352472782135, "global_step": 614550, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1219160556793213, "global_step": 614551, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9233850240707397, "global_step": 614552, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0373897552490234, "global_step": 614553, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0612294673919678, "global_step": 614554, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0509848594665527, "global_step": 614555, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.015472173690796, "global_step": 614556, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0168862342834473, "global_step": 614557, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9704636335372925, "global_step": 614558, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0239012241363525, "global_step": 614559, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9529826641082764, "global_step": 614560, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0282859802246094, "global_step": 614561, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9763612747192383, "global_step": 614562, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9175617694854736, "global_step": 614563, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9615081548690796, "global_step": 614564, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.95608389377594, "global_step": 614565, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.037992238998413, "global_step": 614566, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.032926082611084, "global_step": 614567, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9400466680526733, "global_step": 614568, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9978646039962769, "global_step": 614569, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0330607891082764, "global_step": 614570, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0668680667877197, "global_step": 614571, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.997200608253479, "global_step": 614572, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9960380792617798, "global_step": 614573, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0082712173461914, "global_step": 614574, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9188896417617798, "global_step": 614575, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.118582248687744, "global_step": 614576, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.965670108795166, "global_step": 614577, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0334665775299072, "global_step": 614578, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9523282051086426, "global_step": 614579, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9396257400512695, "global_step": 614580, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0114314556121826, "global_step": 614581, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1356594562530518, "global_step": 614582, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0522046089172363, "global_step": 614583, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0948266983032227, "global_step": 614584, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.974989891052246, "global_step": 614585, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0014631748199463, "global_step": 614586, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0482945442199707, "global_step": 614587, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.043501138687134, "global_step": 614588, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.001801013946533, "global_step": 614589, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9828131198883057, "global_step": 614590, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9614518880844116, "global_step": 614591, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0095624923706055, "global_step": 614592, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.092031240463257, "global_step": 614593, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0106048583984375, "global_step": 614594, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9569392204284668, "global_step": 614595, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9592223167419434, "global_step": 614596, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.038435220718384, "global_step": 614597, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9350616931915283, "global_step": 614598, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.978779673576355, "global_step": 614599, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.026264190673828, "global_step": 614600, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.8865456581115723, "global_step": 614601, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0106661319732666, "global_step": 614602, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0501708984375, "global_step": 614603, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9407252073287964, "global_step": 614604, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0409669876098633, "global_step": 614605, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9944514036178589, "global_step": 614606, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0509157180786133, "global_step": 614607, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9821288585662842, "global_step": 614608, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0080034732818604, "global_step": 614609, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9866420030593872, "global_step": 614610, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0712640285491943, "global_step": 614611, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.018261432647705, "global_step": 614612, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9471795558929443, "global_step": 614613, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9688249826431274, "global_step": 614614, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.098336935043335, "global_step": 614615, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0240488052368164, "global_step": 614616, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9695820808410645, "global_step": 614617, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9654507637023926, "global_step": 614618, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.932645559310913, "global_step": 614619, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0354347229003906, "global_step": 614620, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9837896823883057, "global_step": 614621, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.041227102279663, "global_step": 614622, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.965406060218811, "global_step": 614623, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9955027103424072, "global_step": 614624, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0449063777923584, "global_step": 614625, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9291248321533203, "global_step": 614626, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.011782169342041, "global_step": 614627, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0973143577575684, "global_step": 614628, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9610503911972046, "global_step": 614629, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.105173349380493, "global_step": 614630, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9673476219177246, "global_step": 614631, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0531418323516846, "global_step": 614632, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0593762397766113, "global_step": 614633, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9911999702453613, "global_step": 614634, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.025557279586792, "global_step": 614635, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9822195768356323, "global_step": 614636, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.01328706741333, "global_step": 614637, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0228302478790283, "global_step": 614638, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.946591854095459, "global_step": 614639, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0150790214538574, "global_step": 614640, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1047403812408447, "global_step": 614641, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0143954753875732, "global_step": 614642, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.953826904296875, "global_step": 614643, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0191454887390137, "global_step": 614644, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0560965538024902, "global_step": 614645, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0919458866119385, "global_step": 614646, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9665377140045166, "global_step": 614647, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.001842975616455, "global_step": 614648, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9989746809005737, "global_step": 614649, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9871981143951416, "global_step": 614650, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.004727840423584, "global_step": 614651, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9789583683013916, "global_step": 614652, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.972415566444397, "global_step": 614653, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0304932594299316, "global_step": 614654, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9879121780395508, "global_step": 614655, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.017936944961548, "global_step": 614656, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.028744697570801, "global_step": 614657, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9339776039123535, "global_step": 614658, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.068046808242798, "global_step": 614659, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0638113021850586, "global_step": 614660, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.923414707183838, "global_step": 614661, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.940100073814392, "global_step": 614662, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9950015544891357, "global_step": 614663, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.933487892150879, "global_step": 614664, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.047253131866455, "global_step": 614665, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0022048950195312, "global_step": 614666, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0290377140045166, "global_step": 614667, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9212430715560913, "global_step": 614668, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.975066900253296, "global_step": 614669, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9907031059265137, "global_step": 614670, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9550626277923584, "global_step": 614671, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.039229154586792, "global_step": 614672, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.055354118347168, "global_step": 614673, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.944495677947998, "global_step": 614674, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.019836664199829, "global_step": 614675, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0924174785614014, "global_step": 614676, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0537734031677246, "global_step": 614677, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9798457622528076, "global_step": 614678, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0006158351898193, "global_step": 614679, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9634826183319092, "global_step": 614680, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0252373218536377, "global_step": 614681, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0705678462982178, "global_step": 614682, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9631648063659668, "global_step": 614683, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0108158588409424, "global_step": 614684, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0989363193511963, "global_step": 614685, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9686172008514404, "global_step": 614686, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0283725261688232, "global_step": 614687, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9844567775726318, "global_step": 614688, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.8837718963623047, "global_step": 614689, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.034095287322998, "global_step": 614690, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.011214256286621, "global_step": 614691, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.8810843229293823, "global_step": 614692, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0327610969543457, "global_step": 614693, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.024480104446411, "global_step": 614694, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0159542560577393, "global_step": 614695, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.981812834739685, "global_step": 614696, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0845892429351807, "global_step": 614697, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0148143768310547, "global_step": 614698, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0622477531433105, "global_step": 614699, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9709663391113281, "global_step": 614700, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.021115303039551, "global_step": 614701, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0178487300872803, "global_step": 614702, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.8764431476593018, "global_step": 614703, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.96503484249115, "global_step": 614704, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.01228928565979, "global_step": 614705, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.919403076171875, "global_step": 614706, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.979099154472351, "global_step": 614707, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.026413679122925, "global_step": 614708, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.082070827484131, "global_step": 614709, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.937943696975708, "global_step": 614710, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.039064407348633, "global_step": 614711, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9238919019699097, "global_step": 614712, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.027308702468872, "global_step": 614713, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.8717752695083618, "global_step": 614714, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1265180110931396, "global_step": 614715, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0365660190582275, "global_step": 614716, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.059584379196167, "global_step": 614717, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.964377999305725, "global_step": 614718, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0090463161468506, "global_step": 614719, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9227548837661743, "global_step": 614720, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0429413318634033, "global_step": 614721, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9313442707061768, "global_step": 614722, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.018279552459717, "global_step": 614723, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9643642902374268, "global_step": 614724, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9795637130737305, "global_step": 614725, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.001188278198242, "global_step": 614726, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0478549003601074, "global_step": 614727, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.98082435131073, "global_step": 614728, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9237751960754395, "global_step": 614729, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.992121696472168, "global_step": 614730, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.049546718597412, "global_step": 614731, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.026869773864746, "global_step": 614732, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.900463342666626, "global_step": 614733, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.014634370803833, "global_step": 614734, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9338605403900146, "global_step": 614735, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.988706350326538, "global_step": 614736, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0462160110473633, "global_step": 614737, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.025188684463501, "global_step": 614738, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.023683547973633, "global_step": 614739, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0366573333740234, "global_step": 614740, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0132784843444824, "global_step": 614741, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9614256620407104, "global_step": 614742, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9740241765975952, "global_step": 614743, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0426361560821533, "global_step": 614744, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0427072048187256, "global_step": 614745, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9589388370513916, "global_step": 614746, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9622160196304321, "global_step": 614747, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9987677335739136, "global_step": 614748, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.017902135848999, "global_step": 614749, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.915292739868164, "global_step": 614750, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1301324367523193, "global_step": 614751, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.998557209968567, "global_step": 614752, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0548152923583984, "global_step": 614753, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.011425256729126, "global_step": 614754, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9508388042449951, "global_step": 614755, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.033801555633545, "global_step": 614756, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9612796306610107, "global_step": 614757, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.044217109680176, "global_step": 614758, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0265908241271973, "global_step": 614759, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.936385989189148, "global_step": 614760, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.024601697921753, "global_step": 614761, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.96084725856781, "global_step": 614762, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.011981725692749, "global_step": 614763, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.019287347793579, "global_step": 614764, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0267934799194336, "global_step": 614765, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9600473642349243, "global_step": 614766, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.8723750114440918, "global_step": 614767, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9992419481277466, "global_step": 614768, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.015148162841797, "global_step": 614769, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0303196907043457, "global_step": 614770, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9342412948608398, "global_step": 614771, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.054931402206421, "global_step": 614772, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.08927059173584, "global_step": 614773, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9515395164489746, "global_step": 614774, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9857819080352783, "global_step": 614775, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9609286785125732, "global_step": 614776, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0176963806152344, "global_step": 614777, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1179757118225098, "global_step": 614778, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0656938552856445, "global_step": 614779, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.999396562576294, "global_step": 614780, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0090479850769043, "global_step": 614781, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0078768730163574, "global_step": 614782, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.070840835571289, "global_step": 614783, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0530381202697754, "global_step": 614784, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9962563514709473, "global_step": 614785, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0242416858673096, "global_step": 614786, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0118257999420166, "global_step": 614787, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.8803515434265137, "global_step": 614788, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.986310601234436, "global_step": 614789, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0285046100616455, "global_step": 614790, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0640664100646973, "global_step": 614791, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0014095306396484, "global_step": 614792, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.997765302658081, "global_step": 614793, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9885053634643555, "global_step": 614794, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9983566999435425, "global_step": 614795, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0546810626983643, "global_step": 614796, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.018296957015991, "global_step": 614797, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0333011150360107, "global_step": 614798, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.006877899169922, "global_step": 614799, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9778962135314941, "global_step": 614800, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0261056423187256, "global_step": 614801, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.079667329788208, "global_step": 614802, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9792107343673706, "global_step": 614803, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9630136489868164, "global_step": 614804, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9368253946304321, "global_step": 614805, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.059433698654175, "global_step": 614806, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.894071102142334, "global_step": 614807, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.8915832042694092, "global_step": 614808, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0952043533325195, "global_step": 614809, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0040621757507324, "global_step": 614810, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0487709045410156, "global_step": 614811, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9751806259155273, "global_step": 614812, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0059571266174316, "global_step": 614813, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9717614650726318, "global_step": 614814, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0520689487457275, "global_step": 614815, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0194180011749268, "global_step": 614816, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.937650442123413, "global_step": 614817, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9475401639938354, "global_step": 614818, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9338347911834717, "global_step": 614819, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0328280925750732, "global_step": 614820, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.068747043609619, "global_step": 614821, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0458106994628906, "global_step": 614822, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0569443702697754, "global_step": 614823, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9925434589385986, "global_step": 614824, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0894110202789307, "global_step": 614825, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9899767637252808, "global_step": 614826, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9589252471923828, "global_step": 614827, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9952729940414429, "global_step": 614828, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9851820468902588, "global_step": 614829, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9232428073883057, "global_step": 614830, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9725565910339355, "global_step": 614831, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9446886777877808, "global_step": 614832, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.058654546737671, "global_step": 614833, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9452646970748901, "global_step": 614834, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.003028631210327, "global_step": 614835, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0376408100128174, "global_step": 614836, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9856793880462646, "global_step": 614837, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.034212350845337, "global_step": 614838, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9741575717926025, "global_step": 614839, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.980366826057434, "global_step": 614840, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.076240062713623, "global_step": 614841, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9513450860977173, "global_step": 614842, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0770339965820312, "global_step": 614843, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.030616044998169, "global_step": 614844, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0206427574157715, "global_step": 614845, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0384018421173096, "global_step": 614846, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0685858726501465, "global_step": 614847, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.942935585975647, "global_step": 614848, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0312647819519043, "global_step": 614849, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9721802473068237, "global_step": 614850, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.963287591934204, "global_step": 614851, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.005753993988037, "global_step": 614852, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0232367515563965, "global_step": 614853, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.002391815185547, "global_step": 614854, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9433221817016602, "global_step": 614855, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9190889596939087, "global_step": 614856, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9307618141174316, "global_step": 614857, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9263668060302734, "global_step": 614858, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0062334537506104, "global_step": 614859, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0156922340393066, "global_step": 614860, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0386898517608643, "global_step": 614861, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9763965606689453, "global_step": 614862, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9803736209869385, "global_step": 614863, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9705349206924438, "global_step": 614864, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0031347274780273, "global_step": 614865, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0244252681732178, "global_step": 614866, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9846664667129517, "global_step": 614867, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9849210977554321, "global_step": 614868, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.099386215209961, "global_step": 614869, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.07392954826355, "global_step": 614870, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9825795888900757, "global_step": 614871, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9673731327056885, "global_step": 614872, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.011838912963867, "global_step": 614873, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.086019515991211, "global_step": 614874, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0225980281829834, "global_step": 614875, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9788720607757568, "global_step": 614876, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9391964673995972, "global_step": 614877, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9230608940124512, "global_step": 614878, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.062347173690796, "global_step": 614879, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.025371789932251, "global_step": 614880, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9708796739578247, "global_step": 614881, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9844304323196411, "global_step": 614882, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9594827890396118, "global_step": 614883, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9191420078277588, "global_step": 614884, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0278913974761963, "global_step": 614885, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.03855562210083, "global_step": 614886, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.009998083114624, "global_step": 614887, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9908052682876587, "global_step": 614888, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.006751537322998, "global_step": 614889, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0401840209960938, "global_step": 614890, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9865056276321411, "global_step": 614891, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0577120780944824, "global_step": 614892, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1441996097564697, "global_step": 614893, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.986216425895691, "global_step": 614894, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9372804164886475, "global_step": 614895, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.894366979598999, "global_step": 614896, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9938576221466064, "global_step": 614897, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0487842559814453, "global_step": 614898, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9777336120605469, "global_step": 614899, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9433997869491577, "global_step": 614900, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.002040386199951, "global_step": 614901, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.053025960922241, "global_step": 614902, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0120887756347656, "global_step": 614903, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9326509237289429, "global_step": 614904, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9905139207839966, "global_step": 614905, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9664782285690308, "global_step": 614906, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.048178195953369, "global_step": 614907, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9789396524429321, "global_step": 614908, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.019545555114746, "global_step": 614909, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9707574844360352, "global_step": 614910, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0375709533691406, "global_step": 614911, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0472898483276367, "global_step": 614912, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0067028999328613, "global_step": 614913, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0221126079559326, "global_step": 614914, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9948569536209106, "global_step": 614915, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0078022480010986, "global_step": 614916, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.017671823501587, "global_step": 614917, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0136797428131104, "global_step": 614918, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9131768941879272, "global_step": 614919, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.005129814147949, "global_step": 614920, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0578908920288086, "global_step": 614921, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9656342267990112, "global_step": 614922, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.938292384147644, "global_step": 614923, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9611773490905762, "global_step": 614924, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.081021547317505, "global_step": 614925, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.003679037094116, "global_step": 614926, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9336211681365967, "global_step": 614927, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0306432247161865, "global_step": 614928, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9667354822158813, "global_step": 614929, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0338125228881836, "global_step": 614930, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9690632820129395, "global_step": 614931, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.035456657409668, "global_step": 614932, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0310897827148438, "global_step": 614933, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.966022253036499, "global_step": 614934, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0304620265960693, "global_step": 614935, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.976883053779602, "global_step": 614936, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.002695322036743, "global_step": 614937, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.936928391456604, "global_step": 614938, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9489825963974, "global_step": 614939, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9547781944274902, "global_step": 614940, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0438644886016846, "global_step": 614941, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.10103702545166, "global_step": 614942, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9475504159927368, "global_step": 614943, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9597759246826172, "global_step": 614944, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9689269065856934, "global_step": 614945, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.037735939025879, "global_step": 614946, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0027921199798584, "global_step": 614947, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9582115411758423, "global_step": 614948, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.027226209640503, "global_step": 614949, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9404997825622559, "global_step": 614950, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.002903699874878, "global_step": 614951, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9369335174560547, "global_step": 614952, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1543662548065186, "global_step": 614953, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.024109363555908, "global_step": 614954, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.970403790473938, "global_step": 614955, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0489768981933594, "global_step": 614956, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0220069885253906, "global_step": 614957, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9894499778747559, "global_step": 614958, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9653315544128418, "global_step": 614959, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0468015670776367, "global_step": 614960, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.993574857711792, "global_step": 614961, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9735853672027588, "global_step": 614962, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0401737689971924, "global_step": 614963, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0407888889312744, "global_step": 614964, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9505717754364014, "global_step": 614965, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.024836540222168, "global_step": 614966, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.001508951187134, "global_step": 614967, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.022891044616699, "global_step": 614968, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.012289524078369, "global_step": 614969, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9954795837402344, "global_step": 614970, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9559297561645508, "global_step": 614971, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.045109987258911, "global_step": 614972, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0173513889312744, "global_step": 614973, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9983493089675903, "global_step": 614974, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0700204372406006, "global_step": 614975, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.010110378265381, "global_step": 614976, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0083189010620117, "global_step": 614977, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.916027545928955, "global_step": 614978, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.948248267173767, "global_step": 614979, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.8443297147750854, "global_step": 614980, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0036559104919434, "global_step": 614981, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.037085771560669, "global_step": 614982, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0369231700897217, "global_step": 614983, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0095152854919434, "global_step": 614984, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.902695894241333, "global_step": 614985, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.97404146194458, "global_step": 614986, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.026211977005005, "global_step": 614987, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0787768363952637, "global_step": 614988, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0364878177642822, "global_step": 614989, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9026275873184204, "global_step": 614990, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.100537061691284, "global_step": 614991, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0793673992156982, "global_step": 614992, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0487003326416016, "global_step": 614993, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0476152896881104, "global_step": 614994, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9739818572998047, "global_step": 614995, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0643885135650635, "global_step": 614996, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.005099058151245, "global_step": 614997, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0403153896331787, "global_step": 614998, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9852805137634277, "global_step": 614999, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.925158143043518, "global_step": 615000, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9649291038513184, "global_step": 615001, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.014399528503418, "global_step": 615002, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9650685787200928, "global_step": 615003, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.981600284576416, "global_step": 615004, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.004612445831299, "global_step": 615005, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0768346786499023, "global_step": 615006, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9242241382598877, "global_step": 615007, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.032407522201538, "global_step": 615008, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9457566738128662, "global_step": 615009, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.943482756614685, "global_step": 615010, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.033663272857666, "global_step": 615011, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9399510622024536, "global_step": 615012, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0200343132019043, "global_step": 615013, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9706499576568604, "global_step": 615014, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9711939096450806, "global_step": 615015, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.181030511856079, "global_step": 615016, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0435450077056885, "global_step": 615017, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.996622085571289, "global_step": 615018, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9623643159866333, "global_step": 615019, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.99761164188385, "global_step": 615020, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.998213291168213, "global_step": 615021, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9665005207061768, "global_step": 615022, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.8969926834106445, "global_step": 615023, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0156450271606445, "global_step": 615024, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.969292163848877, "global_step": 615025, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9863998889923096, "global_step": 615026, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.980881690979004, "global_step": 615027, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0166380405426025, "global_step": 615028, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9701958894729614, "global_step": 615029, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.993664264678955, "global_step": 615030, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0060935020446777, "global_step": 615031, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0122265815734863, "global_step": 615032, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.01098895072937, "global_step": 615033, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0099098682403564, "global_step": 615034, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.061595916748047, "global_step": 615035, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.095336437225342, "global_step": 615036, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0797276496887207, "global_step": 615037, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0014214515686035, "global_step": 615038, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.955464243888855, "global_step": 615039, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0119333267211914, "global_step": 615040, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0402305126190186, "global_step": 615041, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1100475788116455, "global_step": 615042, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0089457035064697, "global_step": 615043, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9999439716339111, "global_step": 615044, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9784432649612427, "global_step": 615045, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9550409317016602, "global_step": 615046, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9736297130584717, "global_step": 615047, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9493460655212402, "global_step": 615048, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9607926607131958, "global_step": 615049, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0508053302764893, "global_step": 615050, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.056931972503662, "global_step": 615051, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.06337308883667, "global_step": 615052, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.989089846611023, "global_step": 615053, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.006801128387451, "global_step": 615054, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9421240091323853, "global_step": 615055, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0683107376098633, "global_step": 615056, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9988478422164917, "global_step": 615057, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9994182586669922, "global_step": 615058, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0081961154937744, "global_step": 615059, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.995681881904602, "global_step": 615060, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.029423236846924, "global_step": 615061, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9546077251434326, "global_step": 615062, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0054452419281006, "global_step": 615063, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0001814365386963, "global_step": 615064, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.018117904663086, "global_step": 615065, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.122710704803467, "global_step": 615066, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0491600036621094, "global_step": 615067, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.013622760772705, "global_step": 615068, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.08009934425354, "global_step": 615069, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0517091751098633, "global_step": 615070, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.972242832183838, "global_step": 615071, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.957478404045105, "global_step": 615072, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.05338978767395, "global_step": 615073, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9974416494369507, "global_step": 615074, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.084559202194214, "global_step": 615075, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.031705617904663, "global_step": 615076, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.994431495666504, "global_step": 615077, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.975090503692627, "global_step": 615078, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.018988609313965, "global_step": 615079, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0488483905792236, "global_step": 615080, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.049999237060547, "global_step": 615081, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9574098587036133, "global_step": 615082, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9173552989959717, "global_step": 615083, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.003343105316162, "global_step": 615084, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0527453422546387, "global_step": 615085, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9074047803878784, "global_step": 615086, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0369086265563965, "global_step": 615087, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.035062313079834, "global_step": 615088, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.13045597076416, "global_step": 615089, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.107819080352783, "global_step": 615090, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.040459394454956, "global_step": 615091, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.974530816078186, "global_step": 615092, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0673139095306396, "global_step": 615093, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0069262981414795, "global_step": 615094, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0991714000701904, "global_step": 615095, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.14286470413208, "global_step": 615096, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.009488821029663, "global_step": 615097, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9807828664779663, "global_step": 615098, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9689275026321411, "global_step": 615099, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0405375957489014, "global_step": 615100, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0294694900512695, "global_step": 615101, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.057676076889038, "global_step": 615102, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0281364917755127, "global_step": 615103, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0906729698181152, "global_step": 615104, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.022348165512085, "global_step": 615105, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.039182424545288, "global_step": 615106, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1113951206207275, "global_step": 615107, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0049455165863037, "global_step": 615108, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0811073780059814, "global_step": 615109, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9893819093704224, "global_step": 615110, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0196778774261475, "global_step": 615111, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1040866374969482, "global_step": 615112, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.024972915649414, "global_step": 615113, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9694221019744873, "global_step": 615114, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.109740734100342, "global_step": 615115, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0307228565216064, "global_step": 615116, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9837955236434937, "global_step": 615117, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.009312152862549, "global_step": 615118, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9821765422821045, "global_step": 615119, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.019305944442749, "global_step": 615120, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9468021392822266, "global_step": 615121, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.040278434753418, "global_step": 615122, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.088646173477173, "global_step": 615123, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.025998830795288, "global_step": 615124, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.055479049682617, "global_step": 615125, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9471113681793213, "global_step": 615126, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.024684429168701, "global_step": 615127, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.003549098968506, "global_step": 615128, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0402326583862305, "global_step": 615129, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.044930934906006, "global_step": 615130, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0256006717681885, "global_step": 615131, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9745874404907227, "global_step": 615132, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0475192070007324, "global_step": 615133, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.000553607940674, "global_step": 615134, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0271122455596924, "global_step": 615135, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9597506523132324, "global_step": 615136, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.026675224304199, "global_step": 615137, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.992470145225525, "global_step": 615138, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.050187826156616, "global_step": 615139, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0657877922058105, "global_step": 615140, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.029797077178955, "global_step": 615141, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.134079694747925, "global_step": 615142, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0367658138275146, "global_step": 615143, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.964667797088623, "global_step": 615144, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.901066780090332, "global_step": 615145, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0164530277252197, "global_step": 615146, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.034815788269043, "global_step": 615147, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0437347888946533, "global_step": 615148, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.050602436065674, "global_step": 615149, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9908391237258911, "global_step": 615150, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0363614559173584, "global_step": 615151, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.063251495361328, "global_step": 615152, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0251047611236572, "global_step": 615153, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9778269529342651, "global_step": 615154, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9986519813537598, "global_step": 615155, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9381593465805054, "global_step": 615156, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.097898244857788, "global_step": 615157, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9822486639022827, "global_step": 615158, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9574917554855347, "global_step": 615159, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0069448947906494, "global_step": 615160, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0473248958587646, "global_step": 615161, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.980311632156372, "global_step": 615162, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9535704851150513, "global_step": 615163, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.983962893486023, "global_step": 615164, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.068716526031494, "global_step": 615165, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9879121780395508, "global_step": 615166, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.028367519378662, "global_step": 615167, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.00543475151062, "global_step": 615168, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9252396821975708, "global_step": 615169, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.002290725708008, "global_step": 615170, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0537281036376953, "global_step": 615171, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9650665521621704, "global_step": 615172, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0081655979156494, "global_step": 615173, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1209378242492676, "global_step": 615174, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9168034791946411, "global_step": 615175, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0001866817474365, "global_step": 615176, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.003934383392334, "global_step": 615177, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.000688076019287, "global_step": 615178, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.047541618347168, "global_step": 615179, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.026686668395996, "global_step": 615180, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.005840539932251, "global_step": 615181, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9515612125396729, "global_step": 615182, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.045388698577881, "global_step": 615183, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0044260025024414, "global_step": 615184, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9382030963897705, "global_step": 615185, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9494524002075195, "global_step": 615186, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.003594398498535, "global_step": 615187, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9907052516937256, "global_step": 615188, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9617940187454224, "global_step": 615189, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0389158725738525, "global_step": 615190, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9798332452774048, "global_step": 615191, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9752154350280762, "global_step": 615192, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0624427795410156, "global_step": 615193, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.056582450866699, "global_step": 615194, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0435783863067627, "global_step": 615195, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.969455599784851, "global_step": 615196, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0540945529937744, "global_step": 615197, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0258355140686035, "global_step": 615198, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.055203676223755, "global_step": 615199, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.8989553451538086, "global_step": 615200, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9837703704833984, "global_step": 615201, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9747329950332642, "global_step": 615202, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.044965982437134, "global_step": 615203, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9925651550292969, "global_step": 615204, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0337491035461426, "global_step": 615205, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0593159198760986, "global_step": 615206, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0641191005706787, "global_step": 615207, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9341256618499756, "global_step": 615208, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.033964157104492, "global_step": 615209, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9630874395370483, "global_step": 615210, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.898709774017334, "global_step": 615211, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9877163171768188, "global_step": 615212, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.012298822402954, "global_step": 615213, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.055860996246338, "global_step": 615214, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.04927134513855, "global_step": 615215, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0694985389709473, "global_step": 615216, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0165371894836426, "global_step": 615217, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.950720191001892, "global_step": 615218, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9855170249938965, "global_step": 615219, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0981600284576416, "global_step": 615220, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9881311655044556, "global_step": 615221, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.041612148284912, "global_step": 615222, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9462963342666626, "global_step": 615223, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0573530197143555, "global_step": 615224, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9989813566207886, "global_step": 615225, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9933253526687622, "global_step": 615226, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0365376472473145, "global_step": 615227, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9975417852401733, "global_step": 615228, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0777575969696045, "global_step": 615229, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.031132698059082, "global_step": 615230, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0597665309906006, "global_step": 615231, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0162570476531982, "global_step": 615232, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.984855055809021, "global_step": 615233, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.959693193435669, "global_step": 615234, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1203453540802, "global_step": 615235, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.009861707687378, "global_step": 615236, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0063209533691406, "global_step": 615237, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0035414695739746, "global_step": 615238, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0204129219055176, "global_step": 615239, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0087313652038574, "global_step": 615240, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0237061977386475, "global_step": 615241, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.043905019760132, "global_step": 615242, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0576419830322266, "global_step": 615243, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9775795936584473, "global_step": 615244, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0578465461730957, "global_step": 615245, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9872267246246338, "global_step": 615246, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.974564790725708, "global_step": 615247, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9758964776992798, "global_step": 615248, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.013214111328125, "global_step": 615249, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9904823303222656, "global_step": 615250, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0628445148468018, "global_step": 615251, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9282549619674683, "global_step": 615252, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9937782287597656, "global_step": 615253, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0788488388061523, "global_step": 615254, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.133540391921997, "global_step": 615255, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0112287998199463, "global_step": 615256, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.064998149871826, "global_step": 615257, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1045358180999756, "global_step": 615258, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.07015061378479, "global_step": 615259, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0274486541748047, "global_step": 615260, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0900635719299316, "global_step": 615261, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.071599006652832, "global_step": 615262, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.031576633453369, "global_step": 615263, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9592163562774658, "global_step": 615264, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9845625162124634, "global_step": 615265, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9708935022354126, "global_step": 615266, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.024787664413452, "global_step": 615267, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1097018718719482, "global_step": 615268, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.063577651977539, "global_step": 615269, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0967321395874023, "global_step": 615270, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0180749893188477, "global_step": 615271, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.968052864074707, "global_step": 615272, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0223405361175537, "global_step": 615273, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0244927406311035, "global_step": 615274, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9741383790969849, "global_step": 615275, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.00406813621521, "global_step": 615276, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0683956146240234, "global_step": 615277, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9407256841659546, "global_step": 615278, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.962667465209961, "global_step": 615279, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.045931816101074, "global_step": 615280, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9995533227920532, "global_step": 615281, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0196948051452637, "global_step": 615282, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9778496026992798, "global_step": 615283, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1198089122772217, "global_step": 615284, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0552124977111816, "global_step": 615285, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.000612497329712, "global_step": 615286, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.051927328109741, "global_step": 615287, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.027909994125366, "global_step": 615288, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.049485445022583, "global_step": 615289, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.019223213195801, "global_step": 615290, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0583255290985107, "global_step": 615291, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0321152210235596, "global_step": 615292, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0222244262695312, "global_step": 615293, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9946298599243164, "global_step": 615294, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.997627854347229, "global_step": 615295, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.060743808746338, "global_step": 615296, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9242874383926392, "global_step": 615297, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.997771143913269, "global_step": 615298, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9878965616226196, "global_step": 615299, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.049777030944824, "global_step": 615300, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.968714714050293, "global_step": 615301, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.008476972579956, "global_step": 615302, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9726802110671997, "global_step": 615303, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9649262428283691, "global_step": 615304, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.012568950653076, "global_step": 615305, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9746884107589722, "global_step": 615306, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.021895170211792, "global_step": 615307, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.02193546295166, "global_step": 615308, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9996024370193481, "global_step": 615309, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9652782678604126, "global_step": 615310, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.035620927810669, "global_step": 615311, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0178027153015137, "global_step": 615312, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0156357288360596, "global_step": 615313, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9515702724456787, "global_step": 615314, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9665082693099976, "global_step": 615315, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9792845249176025, "global_step": 615316, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.001861095428467, "global_step": 615317, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9878453016281128, "global_step": 615318, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.026463270187378, "global_step": 615319, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0313808917999268, "global_step": 615320, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.054611921310425, "global_step": 615321, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9698867797851562, "global_step": 615322, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0441675186157227, "global_step": 615323, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0242269039154053, "global_step": 615324, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9732028245925903, "global_step": 615325, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0233240127563477, "global_step": 615326, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0173938274383545, "global_step": 615327, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.020186185836792, "global_step": 615328, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9492353200912476, "global_step": 615329, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9800056219100952, "global_step": 615330, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9137012958526611, "global_step": 615331, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9754438400268555, "global_step": 615332, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.031212091445923, "global_step": 615333, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9955642223358154, "global_step": 615334, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.011441707611084, "global_step": 615335, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0413978099823, "global_step": 615336, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.941250205039978, "global_step": 615337, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9988843202590942, "global_step": 615338, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0338923931121826, "global_step": 615339, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0474088191986084, "global_step": 615340, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.022212266921997, "global_step": 615341, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9448649883270264, "global_step": 615342, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.96598219871521, "global_step": 615343, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9847949743270874, "global_step": 615344, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.990798830986023, "global_step": 615345, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.064951181411743, "global_step": 615346, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9983735084533691, "global_step": 615347, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0107743740081787, "global_step": 615348, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9581470489501953, "global_step": 615349, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.945279598236084, "global_step": 615350, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9558902978897095, "global_step": 615351, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0564334392547607, "global_step": 615352, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.943606972694397, "global_step": 615353, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9729841947555542, "global_step": 615354, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.072169303894043, "global_step": 615355, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9957371950149536, "global_step": 615356, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9834637641906738, "global_step": 615357, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9842860698699951, "global_step": 615358, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9001383781433105, "global_step": 615359, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0571439266204834, "global_step": 615360, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0372958183288574, "global_step": 615361, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0614144802093506, "global_step": 615362, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.8826743364334106, "global_step": 615363, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0214040279388428, "global_step": 615364, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.006291151046753, "global_step": 615365, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.055522918701172, "global_step": 615366, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.076791763305664, "global_step": 615367, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.034280300140381, "global_step": 615368, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.029247522354126, "global_step": 615369, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0350899696350098, "global_step": 615370, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0257067680358887, "global_step": 615371, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9771546125411987, "global_step": 615372, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1103007793426514, "global_step": 615373, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0342624187469482, "global_step": 615374, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0417277812957764, "global_step": 615375, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.045001983642578, "global_step": 615376, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.042895793914795, "global_step": 615377, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9638363122940063, "global_step": 615378, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0482659339904785, "global_step": 615379, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.901540756225586, "global_step": 615380, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9654273986816406, "global_step": 615381, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.033120632171631, "global_step": 615382, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0505645275115967, "global_step": 615383, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.990006685256958, "global_step": 615384, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.981104850769043, "global_step": 615385, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9553669691085815, "global_step": 615386, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9617825746536255, "global_step": 615387, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.049941062927246, "global_step": 615388, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9701449871063232, "global_step": 615389, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0044593811035156, "global_step": 615390, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.04215145111084, "global_step": 615391, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0016860961914062, "global_step": 615392, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.035271406173706, "global_step": 615393, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.056674003601074, "global_step": 615394, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.043905735015869, "global_step": 615395, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0167148113250732, "global_step": 615396, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9177134037017822, "global_step": 615397, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.000110387802124, "global_step": 615398, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0433945655822754, "global_step": 615399, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1074492931365967, "global_step": 615400, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0577056407928467, "global_step": 615401, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9267882108688354, "global_step": 615402, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0157155990600586, "global_step": 615403, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9919288158416748, "global_step": 615404, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9211667776107788, "global_step": 615405, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9830964803695679, "global_step": 615406, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.8964929580688477, "global_step": 615407, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.028437852859497, "global_step": 615408, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0738751888275146, "global_step": 615409, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1022157669067383, "global_step": 615410, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9507691860198975, "global_step": 615411, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.058410406112671, "global_step": 615412, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.956586241722107, "global_step": 615413, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.045958995819092, "global_step": 615414, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9549440145492554, "global_step": 615415, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.99931800365448, "global_step": 615416, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0051231384277344, "global_step": 615417, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0504748821258545, "global_step": 615418, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0507655143737793, "global_step": 615419, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.052933931350708, "global_step": 615420, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.080744743347168, "global_step": 615421, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0513882637023926, "global_step": 615422, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.059816360473633, "global_step": 615423, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.004509687423706, "global_step": 615424, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.048051595687866, "global_step": 615425, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0494420528411865, "global_step": 615426, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9880105257034302, "global_step": 615427, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0230047702789307, "global_step": 615428, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0604822635650635, "global_step": 615429, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9540654420852661, "global_step": 615430, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1310060024261475, "global_step": 615431, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.983392596244812, "global_step": 615432, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.092884063720703, "global_step": 615433, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9992594718933105, "global_step": 615434, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.1289074420928955, "global_step": 615435, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0714454650878906, "global_step": 615436, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0390536785125732, "global_step": 615437, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0347652435302734, "global_step": 615438, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0406646728515625, "global_step": 615439, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9943397045135498, "global_step": 615440, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.8831712007522583, "global_step": 615441, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0357635021209717, "global_step": 615442, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.962760329246521, "global_step": 615443, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.9238172769546509, "global_step": 615444, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.090421438217163, "global_step": 615445, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0209884643554688, "global_step": 615446, "epoch": 984, "lr": 5e-05}
{"train_loss": 2.0070621967315674, "global_step": 615447, "epoch": 984, "lr": 5e-05}
{"train_loss": 1.966590404510498, "global_step": 615448, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9369102716445923, "global_step": 615449, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0070948600769043, "global_step": 615450, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9907276630401611, "global_step": 615451, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9954315423965454, "global_step": 615452, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.8938171863555908, "global_step": 615453, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9412469863891602, "global_step": 615454, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9314630031585693, "global_step": 615455, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9857401847839355, "global_step": 615456, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.909125566482544, "global_step": 615457, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.8779982328414917, "global_step": 615458, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.8809592723846436, "global_step": 615459, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.992438793182373, "global_step": 615460, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9959871768951416, "global_step": 615461, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.973071813583374, "global_step": 615462, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9603453874588013, "global_step": 615463, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.951258659362793, "global_step": 615464, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9059722423553467, "global_step": 615465, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9308676719665527, "global_step": 615466, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.995121717453003, "global_step": 615467, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9728502035140991, "global_step": 615468, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9883321523666382, "global_step": 615469, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0040502548217773, "global_step": 615470, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9943408966064453, "global_step": 615471, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9635388851165771, "global_step": 615472, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9974806308746338, "global_step": 615473, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.965433120727539, "global_step": 615474, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.96409273147583, "global_step": 615475, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0402302742004395, "global_step": 615476, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.1075820922851562, "global_step": 615477, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9408762454986572, "global_step": 615478, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9224398136138916, "global_step": 615479, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0939993858337402, "global_step": 615480, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.102940320968628, "global_step": 615481, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.023993492126465, "global_step": 615482, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9703766107559204, "global_step": 615483, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0241949558258057, "global_step": 615484, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9296432733535767, "global_step": 615485, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.004774808883667, "global_step": 615486, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9939935207366943, "global_step": 615487, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0022075176239014, "global_step": 615488, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9802184104919434, "global_step": 615489, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.026759386062622, "global_step": 615490, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.911062240600586, "global_step": 615491, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9391610622406006, "global_step": 615492, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9639567136764526, "global_step": 615493, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9038351774215698, "global_step": 615494, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.8973479270935059, "global_step": 615495, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9399079084396362, "global_step": 615496, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9823963642120361, "global_step": 615497, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0404605865478516, "global_step": 615498, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0185556411743164, "global_step": 615499, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0187902450561523, "global_step": 615500, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.976304292678833, "global_step": 615501, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0483834743499756, "global_step": 615502, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.945417046546936, "global_step": 615503, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9861098527908325, "global_step": 615504, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.916500449180603, "global_step": 615505, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9948137998580933, "global_step": 615506, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0200226306915283, "global_step": 615507, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0005228519439697, "global_step": 615508, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9015092849731445, "global_step": 615509, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.95224130153656, "global_step": 615510, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.018272876739502, "global_step": 615511, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9632127285003662, "global_step": 615512, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0450658798217773, "global_step": 615513, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0385076999664307, "global_step": 615514, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.096144437789917, "global_step": 615515, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.975638747215271, "global_step": 615516, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.029397964477539, "global_step": 615517, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9908936023712158, "global_step": 615518, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.028383255004883, "global_step": 615519, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9796510934829712, "global_step": 615520, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.021617889404297, "global_step": 615521, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9143413305282593, "global_step": 615522, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9426203966140747, "global_step": 615523, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0769379138946533, "global_step": 615524, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9994802474975586, "global_step": 615525, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.997814655303955, "global_step": 615526, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.009587287902832, "global_step": 615527, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.062227249145508, "global_step": 615528, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9179610013961792, "global_step": 615529, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.939253568649292, "global_step": 615530, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9274849891662598, "global_step": 615531, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9349493980407715, "global_step": 615532, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9547269344329834, "global_step": 615533, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.00563907623291, "global_step": 615534, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0676705837249756, "global_step": 615535, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.027305841445923, "global_step": 615536, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.010199785232544, "global_step": 615537, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9878134727478027, "global_step": 615538, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9266360998153687, "global_step": 615539, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.039109945297241, "global_step": 615540, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9797818660736084, "global_step": 615541, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.948613166809082, "global_step": 615542, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9511843919754028, "global_step": 615543, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.027310371398926, "global_step": 615544, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.021005630493164, "global_step": 615545, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.024921417236328, "global_step": 615546, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0763182640075684, "global_step": 615547, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9105474948883057, "global_step": 615548, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9383256435394287, "global_step": 615549, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9790470600128174, "global_step": 615550, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.075986862182617, "global_step": 615551, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0057313442230225, "global_step": 615552, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0483486652374268, "global_step": 615553, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9462273120880127, "global_step": 615554, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9669359922409058, "global_step": 615555, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.1081342697143555, "global_step": 615556, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0033557415008545, "global_step": 615557, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.009134531021118, "global_step": 615558, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0372555255889893, "global_step": 615559, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9614813327789307, "global_step": 615560, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.968164086341858, "global_step": 615561, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.963606834411621, "global_step": 615562, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9752501249313354, "global_step": 615563, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9454594850540161, "global_step": 615564, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9795992374420166, "global_step": 615565, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9852931499481201, "global_step": 615566, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9081106185913086, "global_step": 615567, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9166138172149658, "global_step": 615568, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0064215660095215, "global_step": 615569, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0256807804107666, "global_step": 615570, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9962698221206665, "global_step": 615571, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0208868980407715, "global_step": 615572, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9641635417938232, "global_step": 615573, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9969947338104248, "global_step": 615574, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.099217414855957, "global_step": 615575, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9576315879821777, "global_step": 615576, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0998692512512207, "global_step": 615577, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9645490646362305, "global_step": 615578, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0755035877227783, "global_step": 615579, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9392048120498657, "global_step": 615580, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0810132026672363, "global_step": 615581, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.922687292098999, "global_step": 615582, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0269973278045654, "global_step": 615583, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0317585468292236, "global_step": 615584, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0456526279449463, "global_step": 615585, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0815844535827637, "global_step": 615586, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0515105724334717, "global_step": 615587, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.005575656890869, "global_step": 615588, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.040337085723877, "global_step": 615589, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9660273790359497, "global_step": 615590, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9797004461288452, "global_step": 615591, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.059084177017212, "global_step": 615592, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9929512739181519, "global_step": 615593, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.070955514907837, "global_step": 615594, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0419998168945312, "global_step": 615595, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.002542734146118, "global_step": 615596, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0039100646972656, "global_step": 615597, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0183980464935303, "global_step": 615598, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9731988906860352, "global_step": 615599, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.02406907081604, "global_step": 615600, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.993924617767334, "global_step": 615601, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.077810525894165, "global_step": 615602, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.981786847114563, "global_step": 615603, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.05161190032959, "global_step": 615604, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0105419158935547, "global_step": 615605, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.991321325302124, "global_step": 615606, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9887301921844482, "global_step": 615607, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9715328216552734, "global_step": 615608, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.1121394634246826, "global_step": 615609, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0193538665771484, "global_step": 615610, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0407700538635254, "global_step": 615611, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.939293384552002, "global_step": 615612, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9624028205871582, "global_step": 615613, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.054884195327759, "global_step": 615614, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0520825386047363, "global_step": 615615, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9924310445785522, "global_step": 615616, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0196120738983154, "global_step": 615617, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.005622386932373, "global_step": 615618, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9836628437042236, "global_step": 615619, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0166420936584473, "global_step": 615620, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9622256755828857, "global_step": 615621, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.045468807220459, "global_step": 615622, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9598604440689087, "global_step": 615623, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9429190158843994, "global_step": 615624, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9940133094787598, "global_step": 615625, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0282723903656006, "global_step": 615626, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9123098850250244, "global_step": 615627, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.106736183166504, "global_step": 615628, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9169279336929321, "global_step": 615629, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0641727447509766, "global_step": 615630, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9940102100372314, "global_step": 615631, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.029047727584839, "global_step": 615632, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9586517810821533, "global_step": 615633, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.945950984954834, "global_step": 615634, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.023946762084961, "global_step": 615635, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9533342123031616, "global_step": 615636, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.057147979736328, "global_step": 615637, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.000509023666382, "global_step": 615638, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0083296298980713, "global_step": 615639, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.92514967918396, "global_step": 615640, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.067331314086914, "global_step": 615641, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9310210943222046, "global_step": 615642, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0079989433288574, "global_step": 615643, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9203684329986572, "global_step": 615644, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0185840129852295, "global_step": 615645, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.962623119354248, "global_step": 615646, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.8995587825775146, "global_step": 615647, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9636316299438477, "global_step": 615648, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0131208896636963, "global_step": 615649, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9924362897872925, "global_step": 615650, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.977856993675232, "global_step": 615651, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0121638774871826, "global_step": 615652, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.042363166809082, "global_step": 615653, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9365653991699219, "global_step": 615654, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9848164319992065, "global_step": 615655, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0615310668945312, "global_step": 615656, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0265183448791504, "global_step": 615657, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0697591304779053, "global_step": 615658, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9737313985824585, "global_step": 615659, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0706348419189453, "global_step": 615660, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0581579208374023, "global_step": 615661, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9442473649978638, "global_step": 615662, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9839032888412476, "global_step": 615663, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9654489755630493, "global_step": 615664, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0332651138305664, "global_step": 615665, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9531638622283936, "global_step": 615666, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9555248022079468, "global_step": 615667, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.062854290008545, "global_step": 615668, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9738305807113647, "global_step": 615669, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9561572074890137, "global_step": 615670, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.952169418334961, "global_step": 615671, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.03816819190979, "global_step": 615672, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9625641107559204, "global_step": 615673, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0231056213378906, "global_step": 615674, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9951419830322266, "global_step": 615675, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9685169458389282, "global_step": 615676, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.019742488861084, "global_step": 615677, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9848641157150269, "global_step": 615678, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0166006088256836, "global_step": 615679, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9151638746261597, "global_step": 615680, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9880149364471436, "global_step": 615681, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.004215955734253, "global_step": 615682, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0308656692504883, "global_step": 615683, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.91361665725708, "global_step": 615684, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9909039735794067, "global_step": 615685, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.982102870941162, "global_step": 615686, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9571813344955444, "global_step": 615687, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0493483543395996, "global_step": 615688, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.924833059310913, "global_step": 615689, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9989913702011108, "global_step": 615690, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.031656503677368, "global_step": 615691, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.022080898284912, "global_step": 615692, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.990478277206421, "global_step": 615693, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9733537435531616, "global_step": 615694, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0387191772460938, "global_step": 615695, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9532651901245117, "global_step": 615696, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.091364860534668, "global_step": 615697, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0023691654205322, "global_step": 615698, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9906023740768433, "global_step": 615699, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9967806339263916, "global_step": 615700, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0267765522003174, "global_step": 615701, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9996105432510376, "global_step": 615702, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0437307357788086, "global_step": 615703, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0359718799591064, "global_step": 615704, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0109291076660156, "global_step": 615705, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.988464117050171, "global_step": 615706, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.992408275604248, "global_step": 615707, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0301032066345215, "global_step": 615708, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.942238450050354, "global_step": 615709, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.012993812561035, "global_step": 615710, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.06701922416687, "global_step": 615711, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9787862300872803, "global_step": 615712, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9599422216415405, "global_step": 615713, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9503560066223145, "global_step": 615714, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.052452325820923, "global_step": 615715, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0897011756896973, "global_step": 615716, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.007479190826416, "global_step": 615717, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9911733865737915, "global_step": 615718, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9449293613433838, "global_step": 615719, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0300426483154297, "global_step": 615720, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0654280185699463, "global_step": 615721, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.054077625274658, "global_step": 615722, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.019380807876587, "global_step": 615723, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9677330255508423, "global_step": 615724, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0756311416625977, "global_step": 615725, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0775585174560547, "global_step": 615726, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.887345790863037, "global_step": 615727, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0170023441314697, "global_step": 615728, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.023561954498291, "global_step": 615729, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9758484363555908, "global_step": 615730, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9459567070007324, "global_step": 615731, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0438053607940674, "global_step": 615732, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.935280203819275, "global_step": 615733, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0115206241607666, "global_step": 615734, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9474589824676514, "global_step": 615735, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.062817096710205, "global_step": 615736, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0118048191070557, "global_step": 615737, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0097544193267822, "global_step": 615738, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.033949851989746, "global_step": 615739, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.00887393951416, "global_step": 615740, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9218908548355103, "global_step": 615741, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.972907543182373, "global_step": 615742, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.968788981437683, "global_step": 615743, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9465364217758179, "global_step": 615744, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9865715503692627, "global_step": 615745, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.046879529953003, "global_step": 615746, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.089822292327881, "global_step": 615747, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9885945320129395, "global_step": 615748, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9676190614700317, "global_step": 615749, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.036273956298828, "global_step": 615750, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9053388833999634, "global_step": 615751, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9602303504943848, "global_step": 615752, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.997178077697754, "global_step": 615753, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9971168041229248, "global_step": 615754, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0281317234039307, "global_step": 615755, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0399742126464844, "global_step": 615756, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.046738386154175, "global_step": 615757, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.011331796646118, "global_step": 615758, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.045271873474121, "global_step": 615759, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9986352920532227, "global_step": 615760, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0056803226470947, "global_step": 615761, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9534590244293213, "global_step": 615762, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.007831335067749, "global_step": 615763, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.005382537841797, "global_step": 615764, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0277137756347656, "global_step": 615765, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.033966302871704, "global_step": 615766, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9664570093154907, "global_step": 615767, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9387993812561035, "global_step": 615768, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0437300205230713, "global_step": 615769, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.000589609146118, "global_step": 615770, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9761724472045898, "global_step": 615771, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0189003944396973, "global_step": 615772, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0283868312835693, "global_step": 615773, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.1018283367156982, "global_step": 615774, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.987423300743103, "global_step": 615775, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0107057094573975, "global_step": 615776, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.022296667098999, "global_step": 615777, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9419844150543213, "global_step": 615778, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.036473274230957, "global_step": 615779, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0051488876342773, "global_step": 615780, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.001415252685547, "global_step": 615781, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9875574111938477, "global_step": 615782, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0325112342834473, "global_step": 615783, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9804412126541138, "global_step": 615784, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.956772804260254, "global_step": 615785, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9591295719146729, "global_step": 615786, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.8947416543960571, "global_step": 615787, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0078396797180176, "global_step": 615788, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9720540046691895, "global_step": 615789, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0030300617218018, "global_step": 615790, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0286619663238525, "global_step": 615791, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.021550178527832, "global_step": 615792, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9544131755828857, "global_step": 615793, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9804103374481201, "global_step": 615794, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.06646728515625, "global_step": 615795, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9818973541259766, "global_step": 615796, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0757522583007812, "global_step": 615797, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.932300329208374, "global_step": 615798, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0660009384155273, "global_step": 615799, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0967612266540527, "global_step": 615800, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.005552053451538, "global_step": 615801, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9520808458328247, "global_step": 615802, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.03361439704895, "global_step": 615803, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.031982183456421, "global_step": 615804, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9743258953094482, "global_step": 615805, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.030445098876953, "global_step": 615806, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9855660200119019, "global_step": 615807, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.065082550048828, "global_step": 615808, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0507283210754395, "global_step": 615809, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0480196475982666, "global_step": 615810, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.055790901184082, "global_step": 615811, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0308785438537598, "global_step": 615812, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9374510049819946, "global_step": 615813, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.94771409034729, "global_step": 615814, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.00175404548645, "global_step": 615815, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.99265718460083, "global_step": 615816, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.08545184135437, "global_step": 615817, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.070981025695801, "global_step": 615818, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.978471040725708, "global_step": 615819, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.957951545715332, "global_step": 615820, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9746475219726562, "global_step": 615821, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.010125160217285, "global_step": 615822, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9993095397949219, "global_step": 615823, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0255227088928223, "global_step": 615824, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9477354288101196, "global_step": 615825, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9709433317184448, "global_step": 615826, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.063070297241211, "global_step": 615827, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.080427646636963, "global_step": 615828, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.012409210205078, "global_step": 615829, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.018141746520996, "global_step": 615830, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9594526290893555, "global_step": 615831, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0164272785186768, "global_step": 615832, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.05914044380188, "global_step": 615833, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9384331703186035, "global_step": 615834, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9944676160812378, "global_step": 615835, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9721518754959106, "global_step": 615836, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9148821830749512, "global_step": 615837, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9276036024093628, "global_step": 615838, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.077125310897827, "global_step": 615839, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0158016681671143, "global_step": 615840, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0474259853363037, "global_step": 615841, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.013721227645874, "global_step": 615842, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.049738883972168, "global_step": 615843, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9689006805419922, "global_step": 615844, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0553505420684814, "global_step": 615845, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9644577503204346, "global_step": 615846, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9735652208328247, "global_step": 615847, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9683531522750854, "global_step": 615848, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0329408645629883, "global_step": 615849, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9853358268737793, "global_step": 615850, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9735972881317139, "global_step": 615851, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9563108682632446, "global_step": 615852, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9991658926010132, "global_step": 615853, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0066773891448975, "global_step": 615854, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.021602153778076, "global_step": 615855, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.031303644180298, "global_step": 615856, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.02583909034729, "global_step": 615857, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.007864236831665, "global_step": 615858, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9787696599960327, "global_step": 615859, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.942030668258667, "global_step": 615860, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.017308235168457, "global_step": 615861, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9434518814086914, "global_step": 615862, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0281777381896973, "global_step": 615863, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9069839715957642, "global_step": 615864, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9890650510787964, "global_step": 615865, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0347769260406494, "global_step": 615866, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9980868101119995, "global_step": 615867, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0408191680908203, "global_step": 615868, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9876042604446411, "global_step": 615869, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.014387845993042, "global_step": 615870, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0239717960357666, "global_step": 615871, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0560286045074463, "global_step": 615872, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0000267028808594, "global_step": 615873, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0571088790893555, "global_step": 615874, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.037757396697998, "global_step": 615875, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0171351432800293, "global_step": 615876, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0219995975494385, "global_step": 615877, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0400772094726562, "global_step": 615878, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9971362352371216, "global_step": 615879, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.018894910812378, "global_step": 615880, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.023871898651123, "global_step": 615881, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0599002838134766, "global_step": 615882, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9841198921203613, "global_step": 615883, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9661520719528198, "global_step": 615884, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.088183879852295, "global_step": 615885, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.019143581390381, "global_step": 615886, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.993037223815918, "global_step": 615887, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.019625186920166, "global_step": 615888, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0264811515808105, "global_step": 615889, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.002495527267456, "global_step": 615890, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0018551349639893, "global_step": 615891, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0222790241241455, "global_step": 615892, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9409494400024414, "global_step": 615893, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.995818018913269, "global_step": 615894, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.032078504562378, "global_step": 615895, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9951887130737305, "global_step": 615896, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9801632165908813, "global_step": 615897, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9665942192077637, "global_step": 615898, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9579185247421265, "global_step": 615899, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9920181035995483, "global_step": 615900, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.044914484024048, "global_step": 615901, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9880000352859497, "global_step": 615902, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9776554107666016, "global_step": 615903, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.055107593536377, "global_step": 615904, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.8839112520217896, "global_step": 615905, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.952699899673462, "global_step": 615906, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0002503395080566, "global_step": 615907, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.048920154571533, "global_step": 615908, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.040599822998047, "global_step": 615909, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9308174848556519, "global_step": 615910, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.978076696395874, "global_step": 615911, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0779948234558105, "global_step": 615912, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.048283100128174, "global_step": 615913, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0463194847106934, "global_step": 615914, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.03763747215271, "global_step": 615915, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.071320056915283, "global_step": 615916, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.988779902458191, "global_step": 615917, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9611618518829346, "global_step": 615918, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.940041184425354, "global_step": 615919, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.1224677562713623, "global_step": 615920, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9937074184417725, "global_step": 615921, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9632177352905273, "global_step": 615922, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0335028171539307, "global_step": 615923, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0545995235443115, "global_step": 615924, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9741947650909424, "global_step": 615925, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.066525459289551, "global_step": 615926, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0044376850128174, "global_step": 615927, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9527134895324707, "global_step": 615928, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9929484128952026, "global_step": 615929, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0725362300872803, "global_step": 615930, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9878045320510864, "global_step": 615931, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9337286949157715, "global_step": 615932, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0085878372192383, "global_step": 615933, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.06170392036438, "global_step": 615934, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.969343662261963, "global_step": 615935, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0006394386291504, "global_step": 615936, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9844610691070557, "global_step": 615937, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0346157550811768, "global_step": 615938, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.006399393081665, "global_step": 615939, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9624875783920288, "global_step": 615940, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9612737894058228, "global_step": 615941, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0013234615325928, "global_step": 615942, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0096726417541504, "global_step": 615943, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9573765993118286, "global_step": 615944, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9894545078277588, "global_step": 615945, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0379574298858643, "global_step": 615946, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.880745768547058, "global_step": 615947, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.044543743133545, "global_step": 615948, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.020775079727173, "global_step": 615949, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9274603128433228, "global_step": 615950, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.016066789627075, "global_step": 615951, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9879761934280396, "global_step": 615952, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0372304916381836, "global_step": 615953, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.989358901977539, "global_step": 615954, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0914804935455322, "global_step": 615955, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.032109260559082, "global_step": 615956, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0402612686157227, "global_step": 615957, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.981492519378662, "global_step": 615958, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9565953016281128, "global_step": 615959, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.952981948852539, "global_step": 615960, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9014828205108643, "global_step": 615961, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0778305530548096, "global_step": 615962, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.011436700820923, "global_step": 615963, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9406403303146362, "global_step": 615964, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0753014087677, "global_step": 615965, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.938629388809204, "global_step": 615966, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.1578023433685303, "global_step": 615967, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9498751163482666, "global_step": 615968, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.923465609550476, "global_step": 615969, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9946974515914917, "global_step": 615970, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0660808086395264, "global_step": 615971, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9456593990325928, "global_step": 615972, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0733935832977295, "global_step": 615973, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.031078577041626, "global_step": 615974, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.8956540822982788, "global_step": 615975, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0490329265594482, "global_step": 615976, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.065762996673584, "global_step": 615977, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9821377992630005, "global_step": 615978, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0135059356689453, "global_step": 615979, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.019005298614502, "global_step": 615980, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0046072006225586, "global_step": 615981, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9969359636306763, "global_step": 615982, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0504496097564697, "global_step": 615983, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0131731033325195, "global_step": 615984, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9951728582382202, "global_step": 615985, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0006513595581055, "global_step": 615986, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9706177711486816, "global_step": 615987, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0088846683502197, "global_step": 615988, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.1139700412750244, "global_step": 615989, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0133004188537598, "global_step": 615990, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.8842591047286987, "global_step": 615991, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9989651441574097, "global_step": 615992, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.985942006111145, "global_step": 615993, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0156116485595703, "global_step": 615994, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.037419319152832, "global_step": 615995, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9947091341018677, "global_step": 615996, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0464842319488525, "global_step": 615997, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0841190814971924, "global_step": 615998, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.000596046447754, "global_step": 615999, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.051328420639038, "global_step": 616000, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9425736665725708, "global_step": 616001, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9726033210754395, "global_step": 616002, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0855791568756104, "global_step": 616003, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.957107663154602, "global_step": 616004, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.02388072013855, "global_step": 616005, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.060218572616577, "global_step": 616006, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0782787799835205, "global_step": 616007, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9424114227294922, "global_step": 616008, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9318602085113525, "global_step": 616009, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.011464834213257, "global_step": 616010, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0398311614990234, "global_step": 616011, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.098583459854126, "global_step": 616012, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9980357885360718, "global_step": 616013, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0371103286743164, "global_step": 616014, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.019958734512329, "global_step": 616015, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.057682514190674, "global_step": 616016, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.944352626800537, "global_step": 616017, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0187456607818604, "global_step": 616018, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9420506954193115, "global_step": 616019, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0137486457824707, "global_step": 616020, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9530290365219116, "global_step": 616021, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9867708683013916, "global_step": 616022, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9946280717849731, "global_step": 616023, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9680894613265991, "global_step": 616024, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.073239326477051, "global_step": 616025, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9972999095916748, "global_step": 616026, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.016077995300293, "global_step": 616027, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9916175603866577, "global_step": 616028, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9919288158416748, "global_step": 616029, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.016676664352417, "global_step": 616030, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9159886837005615, "global_step": 616031, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9796160459518433, "global_step": 616032, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.952417254447937, "global_step": 616033, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9210461378097534, "global_step": 616034, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9776630401611328, "global_step": 616035, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0399551391601562, "global_step": 616036, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9304958581924438, "global_step": 616037, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.011125087738037, "global_step": 616038, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.045511484146118, "global_step": 616039, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0758771896362305, "global_step": 616040, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.977791428565979, "global_step": 616041, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.933270812034607, "global_step": 616042, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0426526069641113, "global_step": 616043, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9913418292999268, "global_step": 616044, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.1249353885650635, "global_step": 616045, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9739375114440918, "global_step": 616046, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.094226360321045, "global_step": 616047, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9924523830413818, "global_step": 616048, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.060777425765991, "global_step": 616049, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0703816413879395, "global_step": 616050, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.019000291824341, "global_step": 616051, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0517401695251465, "global_step": 616052, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0919387340545654, "global_step": 616053, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9932024478912354, "global_step": 616054, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.99827241897583, "global_step": 616055, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.032543420791626, "global_step": 616056, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.983663558959961, "global_step": 616057, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.064425468444824, "global_step": 616058, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.013448476791382, "global_step": 616059, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9821165800094604, "global_step": 616060, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.037210464477539, "global_step": 616061, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.063699245452881, "global_step": 616062, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9932926893234253, "global_step": 616063, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9294685125350952, "global_step": 616064, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.1001670360565186, "global_step": 616065, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.031113624572754, "global_step": 616066, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.063369035720825, "global_step": 616067, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9709004163742065, "global_step": 616068, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9193394184112549, "global_step": 616069, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9944431781768799, "global_step": 616070, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9680432081222534, "global_step": 616071, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.005803108215332, "global_step": 616072, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0348353385925293, "global_step": 616073, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9317295551300049, "global_step": 616074, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.031022787094116, "global_step": 616075, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0441970825195312, "global_step": 616076, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9443974494934082, "global_step": 616077, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9987752437591553, "global_step": 616078, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.040245771408081, "global_step": 616079, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0296547412872314, "global_step": 616080, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0225443840026855, "global_step": 616081, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9331610202789307, "global_step": 616082, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9304677248001099, "global_step": 616083, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0265941619873047, "global_step": 616084, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.102330207824707, "global_step": 616085, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9650133848190308, "global_step": 616086, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0509727001190186, "global_step": 616087, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9095892906188965, "global_step": 616088, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9931886196136475, "global_step": 616089, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0363268852233887, "global_step": 616090, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9461967945098877, "global_step": 616091, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.957817554473877, "global_step": 616092, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9675095081329346, "global_step": 616093, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9549064636230469, "global_step": 616094, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0516719818115234, "global_step": 616095, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0082945823669434, "global_step": 616096, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9441664218902588, "global_step": 616097, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9808378219604492, "global_step": 616098, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.041752338409424, "global_step": 616099, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9908387660980225, "global_step": 616100, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0325655937194824, "global_step": 616101, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9907872676849365, "global_step": 616102, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9568017721176147, "global_step": 616103, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.024651527404785, "global_step": 616104, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.039935350418091, "global_step": 616105, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.005331039428711, "global_step": 616106, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9699183702468872, "global_step": 616107, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.002747058868408, "global_step": 616108, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.024205207824707, "global_step": 616109, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9953539371490479, "global_step": 616110, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0176000595092773, "global_step": 616111, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0530099868774414, "global_step": 616112, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9805703163146973, "global_step": 616113, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.003908634185791, "global_step": 616114, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9876952171325684, "global_step": 616115, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.044193983078003, "global_step": 616116, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9403369426727295, "global_step": 616117, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9898593425750732, "global_step": 616118, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.000288724899292, "global_step": 616119, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9580737352371216, "global_step": 616120, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0500328540802, "global_step": 616121, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9321552515029907, "global_step": 616122, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0320184230804443, "global_step": 616123, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.021303176879883, "global_step": 616124, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0555903911590576, "global_step": 616125, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.044088840484619, "global_step": 616126, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9772472381591797, "global_step": 616127, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.081888198852539, "global_step": 616128, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0311942100524902, "global_step": 616129, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9584596157073975, "global_step": 616130, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.025702953338623, "global_step": 616131, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9544403553009033, "global_step": 616132, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.061307907104492, "global_step": 616133, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9630669355392456, "global_step": 616134, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.01057767868042, "global_step": 616135, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.001755714416504, "global_step": 616136, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.989927053451538, "global_step": 616137, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0887198448181152, "global_step": 616138, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.995857834815979, "global_step": 616139, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.949392557144165, "global_step": 616140, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.928369164466858, "global_step": 616141, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.951586365699768, "global_step": 616142, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9182037115097046, "global_step": 616143, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.044606924057007, "global_step": 616144, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.013200521469116, "global_step": 616145, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.1186394691467285, "global_step": 616146, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9935065507888794, "global_step": 616147, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0143890380859375, "global_step": 616148, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0444343090057373, "global_step": 616149, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9166266918182373, "global_step": 616150, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.113159418106079, "global_step": 616151, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.93021559715271, "global_step": 616152, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0534169673919678, "global_step": 616153, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0431723594665527, "global_step": 616154, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.097261667251587, "global_step": 616155, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.053806781768799, "global_step": 616156, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0581846237182617, "global_step": 616157, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9498697519302368, "global_step": 616158, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9183303117752075, "global_step": 616159, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.027146816253662, "global_step": 616160, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0005102157592773, "global_step": 616161, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0211174488067627, "global_step": 616162, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0884125232696533, "global_step": 616163, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.068464994430542, "global_step": 616164, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0655441284179688, "global_step": 616165, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0601165294647217, "global_step": 616166, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0143144130706787, "global_step": 616167, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.03151798248291, "global_step": 616168, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.993739128112793, "global_step": 616169, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0681679248809814, "global_step": 616170, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9903826713562012, "global_step": 616171, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.983528733253479, "global_step": 616172, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9964267015457153, "global_step": 616173, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9913911819458008, "global_step": 616174, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0705771446228027, "global_step": 616175, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9868484735488892, "global_step": 616176, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9641001224517822, "global_step": 616177, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0156493186950684, "global_step": 616178, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.163262367248535, "global_step": 616179, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0561447143554688, "global_step": 616180, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9399254322052002, "global_step": 616181, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0006749629974365, "global_step": 616182, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0468966960906982, "global_step": 616183, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.110182762145996, "global_step": 616184, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0698020458221436, "global_step": 616185, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9890185594558716, "global_step": 616186, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0010271072387695, "global_step": 616187, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0372812747955322, "global_step": 616188, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0075185298919678, "global_step": 616189, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0378711223602295, "global_step": 616190, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0000877380371094, "global_step": 616191, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0160129070281982, "global_step": 616192, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0639262199401855, "global_step": 616193, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9086503982543945, "global_step": 616194, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9807556867599487, "global_step": 616195, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9829285144805908, "global_step": 616196, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9528650045394897, "global_step": 616197, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.999490737915039, "global_step": 616198, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0324394702911377, "global_step": 616199, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9803396463394165, "global_step": 616200, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0432493686676025, "global_step": 616201, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0318970680236816, "global_step": 616202, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9707856178283691, "global_step": 616203, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.039458751678467, "global_step": 616204, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.993912696838379, "global_step": 616205, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0040910243988037, "global_step": 616206, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9810513257980347, "global_step": 616207, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9874573945999146, "global_step": 616208, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0000686645507812, "global_step": 616209, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9948298931121826, "global_step": 616210, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0344319343566895, "global_step": 616211, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.021242380142212, "global_step": 616212, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0222671031951904, "global_step": 616213, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9289677143096924, "global_step": 616214, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9721879959106445, "global_step": 616215, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.011746883392334, "global_step": 616216, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.962571620941162, "global_step": 616217, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9554011821746826, "global_step": 616218, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9941730499267578, "global_step": 616219, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9561443328857422, "global_step": 616220, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9828788042068481, "global_step": 616221, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0663697719573975, "global_step": 616222, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9324325323104858, "global_step": 616223, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0387158393859863, "global_step": 616224, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.011474370956421, "global_step": 616225, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0084762573242188, "global_step": 616226, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9895505905151367, "global_step": 616227, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9871569871902466, "global_step": 616228, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9063512086868286, "global_step": 616229, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0137290954589844, "global_step": 616230, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.011357307434082, "global_step": 616231, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9985157251358032, "global_step": 616232, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.055760383605957, "global_step": 616233, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9852803945541382, "global_step": 616234, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9464430809020996, "global_step": 616235, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9944076538085938, "global_step": 616236, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9821230173110962, "global_step": 616237, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0281782150268555, "global_step": 616238, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.003567695617676, "global_step": 616239, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.102949380874634, "global_step": 616240, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9511140584945679, "global_step": 616241, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0094709396362305, "global_step": 616242, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0297484397888184, "global_step": 616243, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9924718141555786, "global_step": 616244, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0502805709838867, "global_step": 616245, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0532314777374268, "global_step": 616246, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9870126247406006, "global_step": 616247, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0064432621002197, "global_step": 616248, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.006294012069702, "global_step": 616249, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.038817882537842, "global_step": 616250, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9763094186782837, "global_step": 616251, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9378361701965332, "global_step": 616252, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.07383394241333, "global_step": 616253, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9957606792449951, "global_step": 616254, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0494892597198486, "global_step": 616255, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0501747131347656, "global_step": 616256, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.091714859008789, "global_step": 616257, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0074100494384766, "global_step": 616258, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.036271810531616, "global_step": 616259, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0178334712982178, "global_step": 616260, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0554938316345215, "global_step": 616261, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9854129552841187, "global_step": 616262, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9898059368133545, "global_step": 616263, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.109616279602051, "global_step": 616264, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0055289268493652, "global_step": 616265, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9680843353271484, "global_step": 616266, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.019395351409912, "global_step": 616267, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.160191297531128, "global_step": 616268, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9901472330093384, "global_step": 616269, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0045382976531982, "global_step": 616270, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0424721240997314, "global_step": 616271, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.001296043395996, "global_step": 616272, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0572781562805176, "global_step": 616273, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.945338487625122, "global_step": 616274, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0860488414764404, "global_step": 616275, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.076610803604126, "global_step": 616276, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.051825523376465, "global_step": 616277, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9979344606399536, "global_step": 616278, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.019582509994507, "global_step": 616279, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.060506582260132, "global_step": 616280, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9459861516952515, "global_step": 616281, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9942281246185303, "global_step": 616282, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.026825189590454, "global_step": 616283, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.018336534500122, "global_step": 616284, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.035008192062378, "global_step": 616285, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9253778457641602, "global_step": 616286, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0593924522399902, "global_step": 616287, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0590569972991943, "global_step": 616288, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.007777452468872, "global_step": 616289, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9740593433380127, "global_step": 616290, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9957411289215088, "global_step": 616291, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9281952381134033, "global_step": 616292, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9789543151855469, "global_step": 616293, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9676916599273682, "global_step": 616294, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9941134452819824, "global_step": 616295, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9756072759628296, "global_step": 616296, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9641287326812744, "global_step": 616297, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.8995224237442017, "global_step": 616298, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.063387870788574, "global_step": 616299, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9940919876098633, "global_step": 616300, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0558950901031494, "global_step": 616301, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9734042882919312, "global_step": 616302, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9962365627288818, "global_step": 616303, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9358495473861694, "global_step": 616304, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.047630548477173, "global_step": 616305, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0204970836639404, "global_step": 616306, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0016825199127197, "global_step": 616307, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0785651206970215, "global_step": 616308, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0206620693206787, "global_step": 616309, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9642599821090698, "global_step": 616310, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9489933252334595, "global_step": 616311, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9933674335479736, "global_step": 616312, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.00935959815979, "global_step": 616313, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0463149547576904, "global_step": 616314, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.083768606185913, "global_step": 616315, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9667280912399292, "global_step": 616316, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0162785053253174, "global_step": 616317, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.050901174545288, "global_step": 616318, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0169906616210938, "global_step": 616319, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0203185081481934, "global_step": 616320, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0852267742156982, "global_step": 616321, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.000789165496826, "global_step": 616322, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.045142889022827, "global_step": 616323, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0794856548309326, "global_step": 616324, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.026042938232422, "global_step": 616325, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9837719202041626, "global_step": 616326, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0370213985443115, "global_step": 616327, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.072862386703491, "global_step": 616328, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0580039024353027, "global_step": 616329, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.1891117095947266, "global_step": 616330, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9643644094467163, "global_step": 616331, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9186649322509766, "global_step": 616332, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.989611029624939, "global_step": 616333, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9761037826538086, "global_step": 616334, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9710071086883545, "global_step": 616335, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.035538673400879, "global_step": 616336, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9539843797683716, "global_step": 616337, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9524123668670654, "global_step": 616338, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0687713623046875, "global_step": 616339, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.064114570617676, "global_step": 616340, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9984219074249268, "global_step": 616341, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.011016368865967, "global_step": 616342, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9688445329666138, "global_step": 616343, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9559873342514038, "global_step": 616344, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.010418176651001, "global_step": 616345, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.015904188156128, "global_step": 616346, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.042997121810913, "global_step": 616347, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.095820903778076, "global_step": 616348, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9719386100769043, "global_step": 616349, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.045886993408203, "global_step": 616350, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.024702548980713, "global_step": 616351, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9667901992797852, "global_step": 616352, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.033761978149414, "global_step": 616353, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.007110357284546, "global_step": 616354, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.901059865951538, "global_step": 616355, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9802064895629883, "global_step": 616356, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.992905855178833, "global_step": 616357, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.009458065032959, "global_step": 616358, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.1073200702667236, "global_step": 616359, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0437326431274414, "global_step": 616360, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9995791912078857, "global_step": 616361, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0020384788513184, "global_step": 616362, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.004795789718628, "global_step": 616363, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.8972026109695435, "global_step": 616364, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0299859046936035, "global_step": 616365, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9510420560836792, "global_step": 616366, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.032726526260376, "global_step": 616367, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9552969932556152, "global_step": 616368, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9784544706344604, "global_step": 616369, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0114569664001465, "global_step": 616370, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9504520893096924, "global_step": 616371, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0111281871795654, "global_step": 616372, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9824309349060059, "global_step": 616373, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.076488971710205, "global_step": 616374, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.040586233139038, "global_step": 616375, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.06339168548584, "global_step": 616376, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9481055736541748, "global_step": 616377, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9953330755233765, "global_step": 616378, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.116248369216919, "global_step": 616379, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.041973114013672, "global_step": 616380, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9656670093536377, "global_step": 616381, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0008747577667236, "global_step": 616382, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0538558959960938, "global_step": 616383, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9410077333450317, "global_step": 616384, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0703701972961426, "global_step": 616385, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.049147129058838, "global_step": 616386, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.077165126800537, "global_step": 616387, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9540112018585205, "global_step": 616388, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.043670415878296, "global_step": 616389, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9345122575759888, "global_step": 616390, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9997243881225586, "global_step": 616391, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.068293571472168, "global_step": 616392, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.052921772003174, "global_step": 616393, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.8957161903381348, "global_step": 616394, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.010338068008423, "global_step": 616395, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0936477184295654, "global_step": 616396, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0871834754943848, "global_step": 616397, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.074017286300659, "global_step": 616398, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.007488250732422, "global_step": 616399, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9829297065734863, "global_step": 616400, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9830297231674194, "global_step": 616401, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.043195962905884, "global_step": 616402, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.012368679046631, "global_step": 616403, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0233585834503174, "global_step": 616404, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.864751935005188, "global_step": 616405, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.07301664352417, "global_step": 616406, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.051488161087036, "global_step": 616407, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0360355377197266, "global_step": 616408, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.98211669921875, "global_step": 616409, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.048909902572632, "global_step": 616410, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9705878496170044, "global_step": 616411, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.053577423095703, "global_step": 616412, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.0525050163269043, "global_step": 616413, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.053405523300171, "global_step": 616414, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.9895334243774414, "global_step": 616415, "epoch": 985, "lr": 5e-05}
{"train_loss": 2.003890037536621, "global_step": 616416, "epoch": 985, "lr": 5e-05}
{"train_loss": 1.941928744316101, "global_step": 616417, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9847991466522217, "global_step": 616418, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0133893489837646, "global_step": 616419, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9787074327468872, "global_step": 616420, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0398013591766357, "global_step": 616421, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.010037899017334, "global_step": 616422, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0275778770446777, "global_step": 616423, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.019906997680664, "global_step": 616424, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.060511827468872, "global_step": 616425, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9410873651504517, "global_step": 616426, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9883828163146973, "global_step": 616427, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.954256534576416, "global_step": 616428, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9508416652679443, "global_step": 616429, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9079538583755493, "global_step": 616430, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0321526527404785, "global_step": 616431, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.008805990219116, "global_step": 616432, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.095911979675293, "global_step": 616433, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.005836248397827, "global_step": 616434, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.031585454940796, "global_step": 616435, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9551218748092651, "global_step": 616436, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9751228094100952, "global_step": 616437, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9991084337234497, "global_step": 616438, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.002943277359009, "global_step": 616439, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.879230260848999, "global_step": 616440, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9067835807800293, "global_step": 616441, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9968857765197754, "global_step": 616442, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9311773777008057, "global_step": 616443, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.93582022190094, "global_step": 616444, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0242421627044678, "global_step": 616445, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9229921102523804, "global_step": 616446, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0314996242523193, "global_step": 616447, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0037803649902344, "global_step": 616448, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.889775276184082, "global_step": 616449, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.067633867263794, "global_step": 616450, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.054105758666992, "global_step": 616451, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9909992218017578, "global_step": 616452, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0245134830474854, "global_step": 616453, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.008565664291382, "global_step": 616454, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0113959312438965, "global_step": 616455, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9730417728424072, "global_step": 616456, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.931700587272644, "global_step": 616457, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9816858768463135, "global_step": 616458, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.8946927785873413, "global_step": 616459, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9830322265625, "global_step": 616460, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9500033855438232, "global_step": 616461, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0414113998413086, "global_step": 616462, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0590569972991943, "global_step": 616463, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9586970806121826, "global_step": 616464, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9032025337219238, "global_step": 616465, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9384633302688599, "global_step": 616466, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9435696601867676, "global_step": 616467, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.029524564743042, "global_step": 616468, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.054962635040283, "global_step": 616469, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.943920612335205, "global_step": 616470, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9766584634780884, "global_step": 616471, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0528645515441895, "global_step": 616472, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.936943769454956, "global_step": 616473, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.009575128555298, "global_step": 616474, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.058861494064331, "global_step": 616475, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9945706129074097, "global_step": 616476, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9848707914352417, "global_step": 616477, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9575095176696777, "global_step": 616478, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9898693561553955, "global_step": 616479, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9490621089935303, "global_step": 616480, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9436542987823486, "global_step": 616481, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.8793296813964844, "global_step": 616482, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9891685247421265, "global_step": 616483, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9301211833953857, "global_step": 616484, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9830913543701172, "global_step": 616485, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9947493076324463, "global_step": 616486, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.023198127746582, "global_step": 616487, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0022265911102295, "global_step": 616488, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9655672311782837, "global_step": 616489, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.062518358230591, "global_step": 616490, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.962356686592102, "global_step": 616491, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9218642711639404, "global_step": 616492, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0025532245635986, "global_step": 616493, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0293526649475098, "global_step": 616494, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.004265308380127, "global_step": 616495, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.136845111846924, "global_step": 616496, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0310845375061035, "global_step": 616497, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.035717010498047, "global_step": 616498, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0227549076080322, "global_step": 616499, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.031219482421875, "global_step": 616500, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0123188495635986, "global_step": 616501, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.036529541015625, "global_step": 616502, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.042781114578247, "global_step": 616503, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9210244417190552, "global_step": 616504, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0003879070281982, "global_step": 616505, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9670424461364746, "global_step": 616506, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.041356086730957, "global_step": 616507, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.041050672531128, "global_step": 616508, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9556623697280884, "global_step": 616509, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9471200704574585, "global_step": 616510, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9104080200195312, "global_step": 616511, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.986822247505188, "global_step": 616512, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.934281349182129, "global_step": 616513, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9907548427581787, "global_step": 616514, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9608310461044312, "global_step": 616515, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9705396890640259, "global_step": 616516, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9392266273498535, "global_step": 616517, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.007205009460449, "global_step": 616518, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0158259868621826, "global_step": 616519, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.011512517929077, "global_step": 616520, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0508525371551514, "global_step": 616521, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9984127283096313, "global_step": 616522, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9759048223495483, "global_step": 616523, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.045459747314453, "global_step": 616524, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0076828002929688, "global_step": 616525, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.98569917678833, "global_step": 616526, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.030477523803711, "global_step": 616527, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0162036418914795, "global_step": 616528, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0164008140563965, "global_step": 616529, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9802483320236206, "global_step": 616530, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9744747877120972, "global_step": 616531, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9721781015396118, "global_step": 616532, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9561678171157837, "global_step": 616533, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.993232011795044, "global_step": 616534, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9937018156051636, "global_step": 616535, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9513529539108276, "global_step": 616536, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0474815368652344, "global_step": 616537, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9869475364685059, "global_step": 616538, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9352405071258545, "global_step": 616539, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9700969457626343, "global_step": 616540, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.046772003173828, "global_step": 616541, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0185892581939697, "global_step": 616542, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9315993785858154, "global_step": 616543, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.034668445587158, "global_step": 616544, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.065981388092041, "global_step": 616545, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.997155785560608, "global_step": 616546, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0606894493103027, "global_step": 616547, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9462100267410278, "global_step": 616548, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0084691047668457, "global_step": 616549, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0009918212890625, "global_step": 616550, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0380098819732666, "global_step": 616551, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.941109299659729, "global_step": 616552, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.941368579864502, "global_step": 616553, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.988437533378601, "global_step": 616554, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0665011405944824, "global_step": 616555, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0110557079315186, "global_step": 616556, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9862942695617676, "global_step": 616557, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0123913288116455, "global_step": 616558, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9736624956130981, "global_step": 616559, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9585459232330322, "global_step": 616560, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9638153314590454, "global_step": 616561, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0998005867004395, "global_step": 616562, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9575340747833252, "global_step": 616563, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.010128974914551, "global_step": 616564, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9191348552703857, "global_step": 616565, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9518001079559326, "global_step": 616566, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.91636323928833, "global_step": 616567, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.024890184402466, "global_step": 616568, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9855763912200928, "global_step": 616569, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.012420415878296, "global_step": 616570, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0118844509124756, "global_step": 616571, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.002789258956909, "global_step": 616572, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.063559055328369, "global_step": 616573, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9714181423187256, "global_step": 616574, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9650652408599854, "global_step": 616575, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.953458309173584, "global_step": 616576, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.076120615005493, "global_step": 616577, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9000279903411865, "global_step": 616578, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0010602474212646, "global_step": 616579, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.8368744850158691, "global_step": 616580, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9421465396881104, "global_step": 616581, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0232367515563965, "global_step": 616582, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0138962268829346, "global_step": 616583, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9800195693969727, "global_step": 616584, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.963389277458191, "global_step": 616585, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9404329061508179, "global_step": 616586, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9781666994094849, "global_step": 616587, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9592680931091309, "global_step": 616588, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.034558057785034, "global_step": 616589, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9514260292053223, "global_step": 616590, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.946468710899353, "global_step": 616591, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.010774612426758, "global_step": 616592, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.948615550994873, "global_step": 616593, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.8839620351791382, "global_step": 616594, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0333220958709717, "global_step": 616595, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9735443592071533, "global_step": 616596, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0418782234191895, "global_step": 616597, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9765063524246216, "global_step": 616598, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.075859785079956, "global_step": 616599, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9901866912841797, "global_step": 616600, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9453257322311401, "global_step": 616601, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0416452884674072, "global_step": 616602, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0049989223480225, "global_step": 616603, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.062959909439087, "global_step": 616604, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.035153388977051, "global_step": 616605, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9735708236694336, "global_step": 616606, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.8908265829086304, "global_step": 616607, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9956883192062378, "global_step": 616608, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.913636565208435, "global_step": 616609, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9424854516983032, "global_step": 616610, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.91646409034729, "global_step": 616611, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9559361934661865, "global_step": 616612, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0744686126708984, "global_step": 616613, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9687340259552002, "global_step": 616614, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.112795352935791, "global_step": 616615, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0266051292419434, "global_step": 616616, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9895596504211426, "global_step": 616617, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9866007566452026, "global_step": 616618, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9223098754882812, "global_step": 616619, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9157012701034546, "global_step": 616620, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.012428045272827, "global_step": 616621, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9930918216705322, "global_step": 616622, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.029686212539673, "global_step": 616623, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9815329313278198, "global_step": 616624, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0016376972198486, "global_step": 616625, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9620997905731201, "global_step": 616626, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0664916038513184, "global_step": 616627, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0250725746154785, "global_step": 616628, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0042474269866943, "global_step": 616629, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.008949041366577, "global_step": 616630, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.880588173866272, "global_step": 616631, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0531163215637207, "global_step": 616632, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9906340837478638, "global_step": 616633, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0018582344055176, "global_step": 616634, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0917298793792725, "global_step": 616635, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0354769229888916, "global_step": 616636, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9592821598052979, "global_step": 616637, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9536759853363037, "global_step": 616638, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.016697406768799, "global_step": 616639, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.014726400375366, "global_step": 616640, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0035088062286377, "global_step": 616641, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.001641273498535, "global_step": 616642, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9661781787872314, "global_step": 616643, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.065298557281494, "global_step": 616644, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9091472625732422, "global_step": 616645, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9819279909133911, "global_step": 616646, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9539690017700195, "global_step": 616647, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9146037101745605, "global_step": 616648, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0322489738464355, "global_step": 616649, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0326173305511475, "global_step": 616650, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.019397258758545, "global_step": 616651, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9619923830032349, "global_step": 616652, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9649908542633057, "global_step": 616653, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9817034006118774, "global_step": 616654, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.988813042640686, "global_step": 616655, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9656120538711548, "global_step": 616656, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9295527935028076, "global_step": 616657, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9596264362335205, "global_step": 616658, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9970747232437134, "global_step": 616659, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9967896938323975, "global_step": 616660, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0126681327819824, "global_step": 616661, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9879066944122314, "global_step": 616662, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9556251764297485, "global_step": 616663, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.985540509223938, "global_step": 616664, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.982314109802246, "global_step": 616665, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9667783975601196, "global_step": 616666, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0307908058166504, "global_step": 616667, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.023498058319092, "global_step": 616668, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.077735662460327, "global_step": 616669, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0669240951538086, "global_step": 616670, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0592081546783447, "global_step": 616671, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0855166912078857, "global_step": 616672, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0683000087738037, "global_step": 616673, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9662672281265259, "global_step": 616674, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9929931163787842, "global_step": 616675, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9526153802871704, "global_step": 616676, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0499424934387207, "global_step": 616677, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9296401739120483, "global_step": 616678, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0147933959960938, "global_step": 616679, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9676120281219482, "global_step": 616680, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9771534204483032, "global_step": 616681, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9809740781784058, "global_step": 616682, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0563817024230957, "global_step": 616683, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.05688214302063, "global_step": 616684, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9527171850204468, "global_step": 616685, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9700524806976318, "global_step": 616686, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9987003803253174, "global_step": 616687, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.942853331565857, "global_step": 616688, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0217535495758057, "global_step": 616689, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9321616888046265, "global_step": 616690, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9734042882919312, "global_step": 616691, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.939574956893921, "global_step": 616692, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9798083305358887, "global_step": 616693, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0147712230682373, "global_step": 616694, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.003993511199951, "global_step": 616695, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0251426696777344, "global_step": 616696, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.057844877243042, "global_step": 616697, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.008521795272827, "global_step": 616698, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.009453058242798, "global_step": 616699, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.102607250213623, "global_step": 616700, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0081870555877686, "global_step": 616701, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.075161933898926, "global_step": 616702, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.026850461959839, "global_step": 616703, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9648144245147705, "global_step": 616704, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.048130512237549, "global_step": 616705, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.012843132019043, "global_step": 616706, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9795773029327393, "global_step": 616707, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.015690565109253, "global_step": 616708, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0345022678375244, "global_step": 616709, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.014739990234375, "global_step": 616710, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0791306495666504, "global_step": 616711, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9891321659088135, "global_step": 616712, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.004748821258545, "global_step": 616713, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.979367971420288, "global_step": 616714, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0360333919525146, "global_step": 616715, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.000181198120117, "global_step": 616716, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9414843320846558, "global_step": 616717, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.004574775695801, "global_step": 616718, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0429158210754395, "global_step": 616719, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9335572719573975, "global_step": 616720, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.924748420715332, "global_step": 616721, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.030728340148926, "global_step": 616722, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9795831441879272, "global_step": 616723, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9972803592681885, "global_step": 616724, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.082975149154663, "global_step": 616725, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0196499824523926, "global_step": 616726, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0529396533966064, "global_step": 616727, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0331263542175293, "global_step": 616728, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0875678062438965, "global_step": 616729, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.046217679977417, "global_step": 616730, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0355939865112305, "global_step": 616731, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0269994735717773, "global_step": 616732, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9580886363983154, "global_step": 616733, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0474853515625, "global_step": 616734, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9782042503356934, "global_step": 616735, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.005772113800049, "global_step": 616736, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9730918407440186, "global_step": 616737, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9212465286254883, "global_step": 616738, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0091137886047363, "global_step": 616739, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.043783187866211, "global_step": 616740, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0524628162384033, "global_step": 616741, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9929025173187256, "global_step": 616742, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0135445594787598, "global_step": 616743, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.000009059906006, "global_step": 616744, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.8923451900482178, "global_step": 616745, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9585517644882202, "global_step": 616746, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0576558113098145, "global_step": 616747, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9994622468948364, "global_step": 616748, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.004434823989868, "global_step": 616749, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.971341609954834, "global_step": 616750, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.00378680229187, "global_step": 616751, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9501882791519165, "global_step": 616752, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0852444171905518, "global_step": 616753, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.041006088256836, "global_step": 616754, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9566453695297241, "global_step": 616755, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.049760580062866, "global_step": 616756, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0879507064819336, "global_step": 616757, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9464564323425293, "global_step": 616758, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9807649850845337, "global_step": 616759, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.99026358127594, "global_step": 616760, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.951683521270752, "global_step": 616761, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9464459419250488, "global_step": 616762, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.009683609008789, "global_step": 616763, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9560500383377075, "global_step": 616764, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.136359453201294, "global_step": 616765, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0044589042663574, "global_step": 616766, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0068044662475586, "global_step": 616767, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0152945518493652, "global_step": 616768, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.094564914703369, "global_step": 616769, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9977902173995972, "global_step": 616770, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0111050605773926, "global_step": 616771, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9659528732299805, "global_step": 616772, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.013813018798828, "global_step": 616773, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0235037803649902, "global_step": 616774, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9368846416473389, "global_step": 616775, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9543144702911377, "global_step": 616776, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0560622215270996, "global_step": 616777, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0172231197357178, "global_step": 616778, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0208182334899902, "global_step": 616779, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0888028144836426, "global_step": 616780, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9516574144363403, "global_step": 616781, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9657717943191528, "global_step": 616782, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9468681812286377, "global_step": 616783, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9251148700714111, "global_step": 616784, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9965513944625854, "global_step": 616785, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9816137552261353, "global_step": 616786, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9460722208023071, "global_step": 616787, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0694313049316406, "global_step": 616788, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9598817825317383, "global_step": 616789, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0409183502197266, "global_step": 616790, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0218629837036133, "global_step": 616791, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0246644020080566, "global_step": 616792, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9845340251922607, "global_step": 616793, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9534003734588623, "global_step": 616794, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9963122606277466, "global_step": 616795, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.983256220817566, "global_step": 616796, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9808290004730225, "global_step": 616797, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9232151508331299, "global_step": 616798, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.011280059814453, "global_step": 616799, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9987976551055908, "global_step": 616800, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.027564287185669, "global_step": 616801, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9673748016357422, "global_step": 616802, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9866389036178589, "global_step": 616803, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9829670190811157, "global_step": 616804, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0424704551696777, "global_step": 616805, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9648152589797974, "global_step": 616806, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9573270082473755, "global_step": 616807, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.002617597579956, "global_step": 616808, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0249907970428467, "global_step": 616809, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.008100748062134, "global_step": 616810, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0504491329193115, "global_step": 616811, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0117790699005127, "global_step": 616812, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.992347240447998, "global_step": 616813, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0141100883483887, "global_step": 616814, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.911617398262024, "global_step": 616815, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9258232116699219, "global_step": 616816, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9479992389678955, "global_step": 616817, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.050964117050171, "global_step": 616818, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0082998275756836, "global_step": 616819, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0757596492767334, "global_step": 616820, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9954404830932617, "global_step": 616821, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9728024005889893, "global_step": 616822, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9980298280715942, "global_step": 616823, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0750997066497803, "global_step": 616824, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0335426330566406, "global_step": 616825, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.8918763399124146, "global_step": 616826, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0007095336914062, "global_step": 616827, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9051671028137207, "global_step": 616828, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9763250350952148, "global_step": 616829, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.069065570831299, "global_step": 616830, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0320374965667725, "global_step": 616831, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.990020990371704, "global_step": 616832, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0004916191101074, "global_step": 616833, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.057941436767578, "global_step": 616834, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0275535583496094, "global_step": 616835, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0440590381622314, "global_step": 616836, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.004391670227051, "global_step": 616837, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.969814658164978, "global_step": 616838, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0611958503723145, "global_step": 616839, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9962456226348877, "global_step": 616840, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0336623191833496, "global_step": 616841, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0579147338867188, "global_step": 616842, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0083858966827393, "global_step": 616843, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0077943801879883, "global_step": 616844, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.1114261150360107, "global_step": 616845, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.019939661026001, "global_step": 616846, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0487232208251953, "global_step": 616847, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0742347240448, "global_step": 616848, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.984205722808838, "global_step": 616849, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9951075315475464, "global_step": 616850, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9454128742218018, "global_step": 616851, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.982133388519287, "global_step": 616852, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9644041061401367, "global_step": 616853, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0622994899749756, "global_step": 616854, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.974090337753296, "global_step": 616855, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0071542263031006, "global_step": 616856, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9483845233917236, "global_step": 616857, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9712412357330322, "global_step": 616858, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0231471061706543, "global_step": 616859, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.051535129547119, "global_step": 616860, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.038987636566162, "global_step": 616861, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0177505016326904, "global_step": 616862, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0240325927734375, "global_step": 616863, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9882676601409912, "global_step": 616864, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9836368560791016, "global_step": 616865, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.015503406524658, "global_step": 616866, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9990777969360352, "global_step": 616867, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9752962589263916, "global_step": 616868, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.008843183517456, "global_step": 616869, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9876344203948975, "global_step": 616870, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.016411304473877, "global_step": 616871, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.047553539276123, "global_step": 616872, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9589654207229614, "global_step": 616873, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.1100809574127197, "global_step": 616874, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.000051736831665, "global_step": 616875, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9859287738800049, "global_step": 616876, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0637521743774414, "global_step": 616877, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9984664916992188, "global_step": 616878, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0637407302856445, "global_step": 616879, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0064539909362793, "global_step": 616880, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.111675500869751, "global_step": 616881, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.000373125076294, "global_step": 616882, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.988627314567566, "global_step": 616883, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.030576705932617, "global_step": 616884, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.056462049484253, "global_step": 616885, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0291571617126465, "global_step": 616886, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.009039878845215, "global_step": 616887, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.978702425956726, "global_step": 616888, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.930484652519226, "global_step": 616889, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9846044778823853, "global_step": 616890, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9609675407409668, "global_step": 616891, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.1051011085510254, "global_step": 616892, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.022745132446289, "global_step": 616893, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9693328142166138, "global_step": 616894, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.001986503601074, "global_step": 616895, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.969305157661438, "global_step": 616896, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0522844791412354, "global_step": 616897, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0303986072540283, "global_step": 616898, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0207386016845703, "global_step": 616899, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.012953996658325, "global_step": 616900, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0079729557037354, "global_step": 616901, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9381232261657715, "global_step": 616902, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0640358924865723, "global_step": 616903, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.009662628173828, "global_step": 616904, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0028586387634277, "global_step": 616905, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0228729248046875, "global_step": 616906, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9754300117492676, "global_step": 616907, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0769572257995605, "global_step": 616908, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0064966678619385, "global_step": 616909, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.047689437866211, "global_step": 616910, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9896667003631592, "global_step": 616911, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.999272108078003, "global_step": 616912, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.04787015914917, "global_step": 616913, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0058274269104004, "global_step": 616914, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0852441787719727, "global_step": 616915, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9713730812072754, "global_step": 616916, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0845208168029785, "global_step": 616917, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.979832649230957, "global_step": 616918, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9321061372756958, "global_step": 616919, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9700361490249634, "global_step": 616920, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0947728157043457, "global_step": 616921, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9635285139083862, "global_step": 616922, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0647075176239014, "global_step": 616923, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9775577783584595, "global_step": 616924, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.994749665260315, "global_step": 616925, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0464913845062256, "global_step": 616926, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9730582237243652, "global_step": 616927, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0498666763305664, "global_step": 616928, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0179848670959473, "global_step": 616929, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0647687911987305, "global_step": 616930, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0073435306549072, "global_step": 616931, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.900627851486206, "global_step": 616932, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0294432640075684, "global_step": 616933, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9404675960540771, "global_step": 616934, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0068905353546143, "global_step": 616935, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9285681247711182, "global_step": 616936, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9983747005462646, "global_step": 616937, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.019883155822754, "global_step": 616938, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9443690776824951, "global_step": 616939, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.065197467803955, "global_step": 616940, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.071023464202881, "global_step": 616941, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.106184720993042, "global_step": 616942, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9997758865356445, "global_step": 616943, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9016896486282349, "global_step": 616944, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9594411849975586, "global_step": 616945, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.960979700088501, "global_step": 616946, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.006051778793335, "global_step": 616947, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0070815086364746, "global_step": 616948, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.000657558441162, "global_step": 616949, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.012528896331787, "global_step": 616950, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0889456272125244, "global_step": 616951, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9848359823226929, "global_step": 616952, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9737961292266846, "global_step": 616953, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.021963596343994, "global_step": 616954, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.024038314819336, "global_step": 616955, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0451133251190186, "global_step": 616956, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.1369802951812744, "global_step": 616957, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.98842191696167, "global_step": 616958, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0493597984313965, "global_step": 616959, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.009916067123413, "global_step": 616960, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.030381679534912, "global_step": 616961, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0532429218292236, "global_step": 616962, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0903897285461426, "global_step": 616963, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9412468671798706, "global_step": 616964, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9801636934280396, "global_step": 616965, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0539965629577637, "global_step": 616966, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.969111442565918, "global_step": 616967, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9370157718658447, "global_step": 616968, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9847495555877686, "global_step": 616969, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.064542770385742, "global_step": 616970, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9300264120101929, "global_step": 616971, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.989937663078308, "global_step": 616972, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.044772148132324, "global_step": 616973, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.952731728553772, "global_step": 616974, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9218428134918213, "global_step": 616975, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9855420589447021, "global_step": 616976, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9576855897903442, "global_step": 616977, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.959977149963379, "global_step": 616978, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9331631660461426, "global_step": 616979, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9600335359573364, "global_step": 616980, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0340936183929443, "global_step": 616981, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9195964336395264, "global_step": 616982, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.022925853729248, "global_step": 616983, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9684256315231323, "global_step": 616984, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.027003049850464, "global_step": 616985, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9701186418533325, "global_step": 616986, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9177032709121704, "global_step": 616987, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.035148859024048, "global_step": 616988, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.922379493713379, "global_step": 616989, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9808322191238403, "global_step": 616990, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.04940128326416, "global_step": 616991, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0557119846343994, "global_step": 616992, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.924566388130188, "global_step": 616993, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9857089519500732, "global_step": 616994, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0599653720855713, "global_step": 616995, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0115694999694824, "global_step": 616996, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9421002864837646, "global_step": 616997, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9653292894363403, "global_step": 616998, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9919806718826294, "global_step": 616999, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9932301044464111, "global_step": 617000, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.000687837600708, "global_step": 617001, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0227608680725098, "global_step": 617002, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0143344402313232, "global_step": 617003, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9751348495483398, "global_step": 617004, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9610874652862549, "global_step": 617005, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9772125482559204, "global_step": 617006, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.022733449935913, "global_step": 617007, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0000436305999756, "global_step": 617008, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.044793128967285, "global_step": 617009, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.036571741104126, "global_step": 617010, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.007760524749756, "global_step": 617011, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9199398756027222, "global_step": 617012, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.050443410873413, "global_step": 617013, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.015528440475464, "global_step": 617014, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.037137985229492, "global_step": 617015, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.00488543510437, "global_step": 617016, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.109872579574585, "global_step": 617017, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9100688695907593, "global_step": 617018, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.011035680770874, "global_step": 617019, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0022873878479004, "global_step": 617020, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9575767517089844, "global_step": 617021, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.004159927368164, "global_step": 617022, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9997061491012573, "global_step": 617023, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0641520023345947, "global_step": 617024, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.009925127029419, "global_step": 617025, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9538320302963257, "global_step": 617026, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.07336688041687, "global_step": 617027, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.073437452316284, "global_step": 617028, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9762327671051025, "global_step": 617029, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.964708685874939, "global_step": 617030, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0304787158966064, "global_step": 617031, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9851853847503662, "global_step": 617032, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.97910737991333, "global_step": 617033, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.003248929977417, "global_step": 617034, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.082752227783203, "global_step": 617035, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9140896797180176, "global_step": 617036, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.036170721054077, "global_step": 617037, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.065223455429077, "global_step": 617038, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.971623182296753, "global_step": 617039, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.054931402206421, "global_step": 617040, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.003582239151001, "global_step": 617041, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9729549884796143, "global_step": 617042, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9686744213104248, "global_step": 617043, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9386996030807495, "global_step": 617044, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9848356246948242, "global_step": 617045, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.027111768722534, "global_step": 617046, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.073434829711914, "global_step": 617047, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.07407808303833, "global_step": 617048, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9848262071609497, "global_step": 617049, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9754478931427002, "global_step": 617050, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.000675678253174, "global_step": 617051, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.027529239654541, "global_step": 617052, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0514354705810547, "global_step": 617053, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9733476638793945, "global_step": 617054, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0325448513031006, "global_step": 617055, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0610625743865967, "global_step": 617056, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.00635027885437, "global_step": 617057, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.851184606552124, "global_step": 617058, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0323686599731445, "global_step": 617059, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9317561388015747, "global_step": 617060, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9854439496994019, "global_step": 617061, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.988256812095642, "global_step": 617062, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0595905780792236, "global_step": 617063, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.018585443496704, "global_step": 617064, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.956941843032837, "global_step": 617065, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0563509464263916, "global_step": 617066, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9235285520553589, "global_step": 617067, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0020878314971924, "global_step": 617068, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.053328037261963, "global_step": 617069, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.985655665397644, "global_step": 617070, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9939275979995728, "global_step": 617071, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.011152744293213, "global_step": 617072, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0335521697998047, "global_step": 617073, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0019192695617676, "global_step": 617074, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.007225751876831, "global_step": 617075, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.010355234146118, "global_step": 617076, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.075817584991455, "global_step": 617077, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.979102611541748, "global_step": 617078, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0131800174713135, "global_step": 617079, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9995946884155273, "global_step": 617080, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0739731788635254, "global_step": 617081, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.022639036178589, "global_step": 617082, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0052638053894043, "global_step": 617083, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0633363723754883, "global_step": 617084, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0305185317993164, "global_step": 617085, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.930445909500122, "global_step": 617086, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.076911687850952, "global_step": 617087, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.027867555618286, "global_step": 617088, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9314019680023193, "global_step": 617089, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0914900302886963, "global_step": 617090, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9907331466674805, "global_step": 617091, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9781537055969238, "global_step": 617092, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0325918197631836, "global_step": 617093, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.029503107070923, "global_step": 617094, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.029046058654785, "global_step": 617095, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.079218864440918, "global_step": 617096, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9980419874191284, "global_step": 617097, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0302531719207764, "global_step": 617098, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.021627187728882, "global_step": 617099, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9511979818344116, "global_step": 617100, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0069282054901123, "global_step": 617101, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.022930860519409, "global_step": 617102, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.036119222640991, "global_step": 617103, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.048105239868164, "global_step": 617104, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9919077157974243, "global_step": 617105, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9954286813735962, "global_step": 617106, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9152284860610962, "global_step": 617107, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0161263942718506, "global_step": 617108, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0583560466766357, "global_step": 617109, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9486370086669922, "global_step": 617110, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.045517921447754, "global_step": 617111, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.961119532585144, "global_step": 617112, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.970543384552002, "global_step": 617113, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9574158191680908, "global_step": 617114, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.992793321609497, "global_step": 617115, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9953590631484985, "global_step": 617116, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.063967227935791, "global_step": 617117, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0208823680877686, "global_step": 617118, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9963290691375732, "global_step": 617119, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9954750537872314, "global_step": 617120, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.100940227508545, "global_step": 617121, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9797618389129639, "global_step": 617122, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.015455722808838, "global_step": 617123, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0001020431518555, "global_step": 617124, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9864509105682373, "global_step": 617125, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.040968179702759, "global_step": 617126, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.1205191612243652, "global_step": 617127, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.061099052429199, "global_step": 617128, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.047328233718872, "global_step": 617129, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.941422462463379, "global_step": 617130, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.924088954925537, "global_step": 617131, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.947022557258606, "global_step": 617132, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.043752670288086, "global_step": 617133, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9620568752288818, "global_step": 617134, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9336851835250854, "global_step": 617135, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0266621112823486, "global_step": 617136, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9500236511230469, "global_step": 617137, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.114330530166626, "global_step": 617138, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9728068113327026, "global_step": 617139, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9736692905426025, "global_step": 617140, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.029256582260132, "global_step": 617141, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0146613121032715, "global_step": 617142, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0207455158233643, "global_step": 617143, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9565725326538086, "global_step": 617144, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.040290355682373, "global_step": 617145, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9561612606048584, "global_step": 617146, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0416948795318604, "global_step": 617147, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9616775512695312, "global_step": 617148, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0757784843444824, "global_step": 617149, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0570895671844482, "global_step": 617150, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0140199661254883, "global_step": 617151, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0191147327423096, "global_step": 617152, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9901113510131836, "global_step": 617153, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.021824359893799, "global_step": 617154, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.004779577255249, "global_step": 617155, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0977895259857178, "global_step": 617156, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0413408279418945, "global_step": 617157, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9643173217773438, "global_step": 617158, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.008171319961548, "global_step": 617159, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0350539684295654, "global_step": 617160, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.08532977104187, "global_step": 617161, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.031160831451416, "global_step": 617162, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0166378021240234, "global_step": 617163, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9038010835647583, "global_step": 617164, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9930180311203003, "global_step": 617165, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.071615219116211, "global_step": 617166, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0743651390075684, "global_step": 617167, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9341238737106323, "global_step": 617168, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.061067581176758, "global_step": 617169, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0435850620269775, "global_step": 617170, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.928848147392273, "global_step": 617171, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.1018519401550293, "global_step": 617172, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9724451303482056, "global_step": 617173, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9705780744552612, "global_step": 617174, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9964128732681274, "global_step": 617175, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0359878540039062, "global_step": 617176, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.036763906478882, "global_step": 617177, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0479490756988525, "global_step": 617178, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.019420623779297, "global_step": 617179, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0797877311706543, "global_step": 617180, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0417416095733643, "global_step": 617181, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0280327796936035, "global_step": 617182, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0199971199035645, "global_step": 617183, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.007256507873535, "global_step": 617184, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9104208946228027, "global_step": 617185, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.086326837539673, "global_step": 617186, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.051222562789917, "global_step": 617187, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9488492012023926, "global_step": 617188, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0477359294891357, "global_step": 617189, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9714733362197876, "global_step": 617190, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9875798225402832, "global_step": 617191, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0110230445861816, "global_step": 617192, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9925180673599243, "global_step": 617193, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9643185138702393, "global_step": 617194, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9195095300674438, "global_step": 617195, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.03828501701355, "global_step": 617196, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.012660026550293, "global_step": 617197, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0632128715515137, "global_step": 617198, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.011265993118286, "global_step": 617199, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0072131156921387, "global_step": 617200, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.001729726791382, "global_step": 617201, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.013906955718994, "global_step": 617202, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9858700037002563, "global_step": 617203, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9845349788665771, "global_step": 617204, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0802736282348633, "global_step": 617205, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0463814735412598, "global_step": 617206, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0088999271392822, "global_step": 617207, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.083937883377075, "global_step": 617208, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.076702833175659, "global_step": 617209, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9687913656234741, "global_step": 617210, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.064969778060913, "global_step": 617211, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0393776893615723, "global_step": 617212, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.024662733078003, "global_step": 617213, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0446035861968994, "global_step": 617214, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9917738437652588, "global_step": 617215, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9465281963348389, "global_step": 617216, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.013054609298706, "global_step": 617217, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0170910358428955, "global_step": 617218, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.058743715286255, "global_step": 617219, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0052268505096436, "global_step": 617220, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.989615797996521, "global_step": 617221, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9921703338623047, "global_step": 617222, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0701510906219482, "global_step": 617223, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0123684406280518, "global_step": 617224, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0554466247558594, "global_step": 617225, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0395734310150146, "global_step": 617226, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0353012084960938, "global_step": 617227, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0066657066345215, "global_step": 617228, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0089917182922363, "global_step": 617229, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.98842453956604, "global_step": 617230, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0157968997955322, "global_step": 617231, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0551130771636963, "global_step": 617232, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9955590963363647, "global_step": 617233, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.972291350364685, "global_step": 617234, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0845839977264404, "global_step": 617235, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9732856750488281, "global_step": 617236, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0073866844177246, "global_step": 617237, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9656431674957275, "global_step": 617238, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.013767957687378, "global_step": 617239, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0401222705841064, "global_step": 617240, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.076242446899414, "global_step": 617241, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0538647174835205, "global_step": 617242, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0655860900878906, "global_step": 617243, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0699968338012695, "global_step": 617244, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.019101619720459, "global_step": 617245, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0152523517608643, "global_step": 617246, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0528042316436768, "global_step": 617247, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9978994131088257, "global_step": 617248, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9258276224136353, "global_step": 617249, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.020115375518799, "global_step": 617250, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0001494884490967, "global_step": 617251, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9898110628128052, "global_step": 617252, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.114741325378418, "global_step": 617253, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.005427837371826, "global_step": 617254, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0479133129119873, "global_step": 617255, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9761881828308105, "global_step": 617256, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0190680027008057, "global_step": 617257, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0416812896728516, "global_step": 617258, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9594873189926147, "global_step": 617259, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9780312776565552, "global_step": 617260, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9742915630340576, "global_step": 617261, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.026559352874756, "global_step": 617262, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.079134702682495, "global_step": 617263, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0664968490600586, "global_step": 617264, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0392041206359863, "global_step": 617265, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9270002841949463, "global_step": 617266, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.024132013320923, "global_step": 617267, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9831491708755493, "global_step": 617268, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9838509559631348, "global_step": 617269, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0942296981811523, "global_step": 617270, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0381245613098145, "global_step": 617271, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9324915409088135, "global_step": 617272, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9663361310958862, "global_step": 617273, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9528167247772217, "global_step": 617274, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9612301588058472, "global_step": 617275, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9871724843978882, "global_step": 617276, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0768983364105225, "global_step": 617277, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.029752254486084, "global_step": 617278, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0042433738708496, "global_step": 617279, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0932705402374268, "global_step": 617280, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.024657726287842, "global_step": 617281, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9823167324066162, "global_step": 617282, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9609137773513794, "global_step": 617283, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.975534439086914, "global_step": 617284, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.048123598098755, "global_step": 617285, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.005530834197998, "global_step": 617286, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0269689559936523, "global_step": 617287, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.995395541191101, "global_step": 617288, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0189905166625977, "global_step": 617289, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0856261253356934, "global_step": 617290, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9750440120697021, "global_step": 617291, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9685454368591309, "global_step": 617292, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0247411727905273, "global_step": 617293, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9310460090637207, "global_step": 617294, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0134947299957275, "global_step": 617295, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0516626834869385, "global_step": 617296, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0370140075683594, "global_step": 617297, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0153322219848633, "global_step": 617298, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0200955867767334, "global_step": 617299, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9427257776260376, "global_step": 617300, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.065192461013794, "global_step": 617301, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0358774662017822, "global_step": 617302, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9061232805252075, "global_step": 617303, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9977366924285889, "global_step": 617304, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0906622409820557, "global_step": 617305, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0211124420166016, "global_step": 617306, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9610682725906372, "global_step": 617307, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0470476150512695, "global_step": 617308, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0243735313415527, "global_step": 617309, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.058896541595459, "global_step": 617310, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.990229845046997, "global_step": 617311, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9915071725845337, "global_step": 617312, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.034818410873413, "global_step": 617313, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0273289680480957, "global_step": 617314, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.964156985282898, "global_step": 617315, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0058915615081787, "global_step": 617316, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.8999048471450806, "global_step": 617317, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.983431339263916, "global_step": 617318, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.033088207244873, "global_step": 617319, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.005213737487793, "global_step": 617320, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.915937900543213, "global_step": 617321, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9593122005462646, "global_step": 617322, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9862034320831299, "global_step": 617323, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.921618938446045, "global_step": 617324, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0970187187194824, "global_step": 617325, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.084836721420288, "global_step": 617326, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.076709270477295, "global_step": 617327, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9426794052124023, "global_step": 617328, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.040825843811035, "global_step": 617329, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0396876335144043, "global_step": 617330, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9353196620941162, "global_step": 617331, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0669240951538086, "global_step": 617332, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0222110748291016, "global_step": 617333, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.921052098274231, "global_step": 617334, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9841541051864624, "global_step": 617335, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0716609954833984, "global_step": 617336, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.060309886932373, "global_step": 617337, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.079288959503174, "global_step": 617338, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0648794174194336, "global_step": 617339, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.1030092239379883, "global_step": 617340, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0599617958068848, "global_step": 617341, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.068715810775757, "global_step": 617342, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.010002613067627, "global_step": 617343, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0726616382598877, "global_step": 617344, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.086225748062134, "global_step": 617345, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0142722129821777, "global_step": 617346, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.932953953742981, "global_step": 617347, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9228497743606567, "global_step": 617348, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0067548751831055, "global_step": 617349, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9807225465774536, "global_step": 617350, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0235671997070312, "global_step": 617351, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0216097831726074, "global_step": 617352, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.016357421875, "global_step": 617353, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.009345531463623, "global_step": 617354, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.060736894607544, "global_step": 617355, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9764807224273682, "global_step": 617356, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.998860478401184, "global_step": 617357, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.011324167251587, "global_step": 617358, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.02980637550354, "global_step": 617359, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9779276847839355, "global_step": 617360, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.1005561351776123, "global_step": 617361, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.026613235473633, "global_step": 617362, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0580382347106934, "global_step": 617363, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0226118564605713, "global_step": 617364, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9653834104537964, "global_step": 617365, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0435585975646973, "global_step": 617366, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9258670806884766, "global_step": 617367, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.017864227294922, "global_step": 617368, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0599334239959717, "global_step": 617369, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9943344593048096, "global_step": 617370, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0144424438476562, "global_step": 617371, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.966180682182312, "global_step": 617372, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9402945041656494, "global_step": 617373, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.067354679107666, "global_step": 617374, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.06854248046875, "global_step": 617375, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0458388328552246, "global_step": 617376, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.0067152976989746, "global_step": 617377, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.940659761428833, "global_step": 617378, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9478282928466797, "global_step": 617379, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.972346544265747, "global_step": 617380, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9881705045700073, "global_step": 617381, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9806883335113525, "global_step": 617382, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9811538457870483, "global_step": 617383, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9906331300735474, "global_step": 617384, "epoch": 986, "lr": 5e-05}
{"train_loss": 2.003441095352173, "global_step": 617385, "epoch": 986, "lr": 5e-05}
{"train_loss": 1.9544278383255005, "global_step": 617386, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0494916439056396, "global_step": 617387, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9415662288665771, "global_step": 617388, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9922252893447876, "global_step": 617389, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0455095767974854, "global_step": 617390, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9921191930770874, "global_step": 617391, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9800077676773071, "global_step": 617392, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9811214208602905, "global_step": 617393, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.998424768447876, "global_step": 617394, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9746952056884766, "global_step": 617395, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.953578233718872, "global_step": 617396, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9854892492294312, "global_step": 617397, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.984784483909607, "global_step": 617398, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.026618242263794, "global_step": 617399, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0245721340179443, "global_step": 617400, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0287513732910156, "global_step": 617401, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.005617618560791, "global_step": 617402, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0325827598571777, "global_step": 617403, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.94839346408844, "global_step": 617404, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0004849433898926, "global_step": 617405, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0197179317474365, "global_step": 617406, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0720393657684326, "global_step": 617407, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9816830158233643, "global_step": 617408, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9528065919876099, "global_step": 617409, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0607404708862305, "global_step": 617410, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0676939487457275, "global_step": 617411, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.021493673324585, "global_step": 617412, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9591670036315918, "global_step": 617413, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9469294548034668, "global_step": 617414, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.965208888053894, "global_step": 617415, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9900200366973877, "global_step": 617416, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.050157308578491, "global_step": 617417, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.030581474304199, "global_step": 617418, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.051135301589966, "global_step": 617419, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.935010552406311, "global_step": 617420, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.112600326538086, "global_step": 617421, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0349459648132324, "global_step": 617422, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.003279685974121, "global_step": 617423, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9684319496154785, "global_step": 617424, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9466447830200195, "global_step": 617425, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9783028364181519, "global_step": 617426, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9591407775878906, "global_step": 617427, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.131880760192871, "global_step": 617428, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.969120979309082, "global_step": 617429, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.982753038406372, "global_step": 617430, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0214247703552246, "global_step": 617431, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.012937545776367, "global_step": 617432, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.009392738342285, "global_step": 617433, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.977491855621338, "global_step": 617434, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.991273045539856, "global_step": 617435, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0075619220733643, "global_step": 617436, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9841899871826172, "global_step": 617437, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9955692291259766, "global_step": 617438, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.009687662124634, "global_step": 617439, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0827889442443848, "global_step": 617440, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0246095657348633, "global_step": 617441, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0865113735198975, "global_step": 617442, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9769741296768188, "global_step": 617443, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9663511514663696, "global_step": 617444, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0006487369537354, "global_step": 617445, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9107093811035156, "global_step": 617446, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0088253021240234, "global_step": 617447, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0258398056030273, "global_step": 617448, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.035306692123413, "global_step": 617449, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9877917766571045, "global_step": 617450, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0202531814575195, "global_step": 617451, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.932277798652649, "global_step": 617452, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9491163492202759, "global_step": 617453, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0134918689727783, "global_step": 617454, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0712404251098633, "global_step": 617455, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.969564437866211, "global_step": 617456, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9981549978256226, "global_step": 617457, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.02766489982605, "global_step": 617458, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9660316705703735, "global_step": 617459, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.061164379119873, "global_step": 617460, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9207723140716553, "global_step": 617461, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9979984760284424, "global_step": 617462, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0292179584503174, "global_step": 617463, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.039306402206421, "global_step": 617464, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9635539054870605, "global_step": 617465, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9954992532730103, "global_step": 617466, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.019395351409912, "global_step": 617467, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.02785587310791, "global_step": 617468, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9975067377090454, "global_step": 617469, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0290822982788086, "global_step": 617470, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.930678129196167, "global_step": 617471, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9587825536727905, "global_step": 617472, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9852672815322876, "global_step": 617473, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.991890788078308, "global_step": 617474, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9866976737976074, "global_step": 617475, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9557746648788452, "global_step": 617476, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0277419090270996, "global_step": 617477, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0609405040740967, "global_step": 617478, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.019163131713867, "global_step": 617479, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9668515920639038, "global_step": 617480, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9886878728866577, "global_step": 617481, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.028953790664673, "global_step": 617482, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.934617280960083, "global_step": 617483, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9947905540466309, "global_step": 617484, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9967964887619019, "global_step": 617485, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9534636735916138, "global_step": 617486, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9747560024261475, "global_step": 617487, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9595246315002441, "global_step": 617488, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0159242153167725, "global_step": 617489, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.074890375137329, "global_step": 617490, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.036635398864746, "global_step": 617491, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9446905851364136, "global_step": 617492, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.962021827697754, "global_step": 617493, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9430088996887207, "global_step": 617494, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9830902814865112, "global_step": 617495, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0167112350463867, "global_step": 617496, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.007517099380493, "global_step": 617497, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0499086380004883, "global_step": 617498, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.010352611541748, "global_step": 617499, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9773911237716675, "global_step": 617500, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.027235984802246, "global_step": 617501, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.945708155632019, "global_step": 617502, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9906507730484009, "global_step": 617503, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.956215739250183, "global_step": 617504, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9991708993911743, "global_step": 617505, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.963387370109558, "global_step": 617506, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9219211339950562, "global_step": 617507, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.061859607696533, "global_step": 617508, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0202903747558594, "global_step": 617509, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9675583839416504, "global_step": 617510, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9819883108139038, "global_step": 617511, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.970388412475586, "global_step": 617512, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.044179916381836, "global_step": 617513, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9806129932403564, "global_step": 617514, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0317201614379883, "global_step": 617515, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.8838164806365967, "global_step": 617516, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9531974792480469, "global_step": 617517, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.030492067337036, "global_step": 617518, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9803824424743652, "global_step": 617519, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0500566959381104, "global_step": 617520, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.039134979248047, "global_step": 617521, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9780032634735107, "global_step": 617522, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9771904945373535, "global_step": 617523, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.005751609802246, "global_step": 617524, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0424063205718994, "global_step": 617525, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9909570217132568, "global_step": 617526, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9902254343032837, "global_step": 617527, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9225860834121704, "global_step": 617528, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0460264682769775, "global_step": 617529, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9744863510131836, "global_step": 617530, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9868415594100952, "global_step": 617531, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.032865524291992, "global_step": 617532, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9258897304534912, "global_step": 617533, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0815227031707764, "global_step": 617534, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0809154510498047, "global_step": 617535, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.015395164489746, "global_step": 617536, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9726648330688477, "global_step": 617537, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9491530656814575, "global_step": 617538, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9614976644515991, "global_step": 617539, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0111260414123535, "global_step": 617540, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0085227489471436, "global_step": 617541, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.937598466873169, "global_step": 617542, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0485124588012695, "global_step": 617543, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0338523387908936, "global_step": 617544, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9631890058517456, "global_step": 617545, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.984017252922058, "global_step": 617546, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9594628810882568, "global_step": 617547, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0400071144104004, "global_step": 617548, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.8629921674728394, "global_step": 617549, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0948195457458496, "global_step": 617550, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.8868687152862549, "global_step": 617551, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0074446201324463, "global_step": 617552, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9744504690170288, "global_step": 617553, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.025951623916626, "global_step": 617554, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9972344636917114, "global_step": 617555, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.899131417274475, "global_step": 617556, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0112316608428955, "global_step": 617557, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.992272973060608, "global_step": 617558, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.042930841445923, "global_step": 617559, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.970015287399292, "global_step": 617560, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0074124336242676, "global_step": 617561, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0538203716278076, "global_step": 617562, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0592329502105713, "global_step": 617563, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9919770956039429, "global_step": 617564, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9615808725357056, "global_step": 617565, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9149706363677979, "global_step": 617566, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9576274156570435, "global_step": 617567, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.059891700744629, "global_step": 617568, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9547709226608276, "global_step": 617569, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.938358187675476, "global_step": 617570, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0101144313812256, "global_step": 617571, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0566608905792236, "global_step": 617572, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9536839723587036, "global_step": 617573, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0088095664978027, "global_step": 617574, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9600273370742798, "global_step": 617575, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9890172481536865, "global_step": 617576, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.063671350479126, "global_step": 617577, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0361552238464355, "global_step": 617578, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9838762283325195, "global_step": 617579, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0265398025512695, "global_step": 617580, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9762319326400757, "global_step": 617581, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0506739616394043, "global_step": 617582, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9419022798538208, "global_step": 617583, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9809595346450806, "global_step": 617584, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.976953148841858, "global_step": 617585, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0302915573120117, "global_step": 617586, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.042776107788086, "global_step": 617587, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0211265087127686, "global_step": 617588, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.001497268676758, "global_step": 617589, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.001215934753418, "global_step": 617590, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9616835117340088, "global_step": 617591, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9735552072525024, "global_step": 617592, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9888864755630493, "global_step": 617593, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0155014991760254, "global_step": 617594, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.002791166305542, "global_step": 617595, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.971591830253601, "global_step": 617596, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.084869623184204, "global_step": 617597, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9993544816970825, "global_step": 617598, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0258162021636963, "global_step": 617599, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9593528509140015, "global_step": 617600, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.025672674179077, "global_step": 617601, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9951690435409546, "global_step": 617602, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.040708303451538, "global_step": 617603, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9899872541427612, "global_step": 617604, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0324857234954834, "global_step": 617605, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.1093859672546387, "global_step": 617606, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0209240913391113, "global_step": 617607, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9432532787322998, "global_step": 617608, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9955228567123413, "global_step": 617609, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.028001546859741, "global_step": 617610, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.974373459815979, "global_step": 617611, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.023981809616089, "global_step": 617612, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9538265466690063, "global_step": 617613, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.050784111022949, "global_step": 617614, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9277254343032837, "global_step": 617615, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9621167182922363, "global_step": 617616, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9561039209365845, "global_step": 617617, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.035034418106079, "global_step": 617618, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0246708393096924, "global_step": 617619, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0120339393615723, "global_step": 617620, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.950699806213379, "global_step": 617621, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0386345386505127, "global_step": 617622, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9949861764907837, "global_step": 617623, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.019707679748535, "global_step": 617624, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0124034881591797, "global_step": 617625, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9708561897277832, "global_step": 617626, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.1056289672851562, "global_step": 617627, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.087752103805542, "global_step": 617628, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9602913856506348, "global_step": 617629, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0001795291900635, "global_step": 617630, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0333781242370605, "global_step": 617631, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9923486709594727, "global_step": 617632, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0406100749969482, "global_step": 617633, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9593052864074707, "global_step": 617634, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9451202154159546, "global_step": 617635, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.022890567779541, "global_step": 617636, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0196287631988525, "global_step": 617637, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9751513004302979, "global_step": 617638, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0805540084838867, "global_step": 617639, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9636880159378052, "global_step": 617640, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.030465841293335, "global_step": 617641, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0303890705108643, "global_step": 617642, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9844636917114258, "global_step": 617643, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9393287897109985, "global_step": 617644, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0311126708984375, "global_step": 617645, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.035400152206421, "global_step": 617646, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0869147777557373, "global_step": 617647, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.065856456756592, "global_step": 617648, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.087315320968628, "global_step": 617649, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0266005992889404, "global_step": 617650, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9975329637527466, "global_step": 617651, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9935671091079712, "global_step": 617652, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0182597637176514, "global_step": 617653, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9340863227844238, "global_step": 617654, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.041598081588745, "global_step": 617655, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9874879121780396, "global_step": 617656, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9751969575881958, "global_step": 617657, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9362472295761108, "global_step": 617658, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0581016540527344, "global_step": 617659, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0261104106903076, "global_step": 617660, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.026285409927368, "global_step": 617661, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9274553060531616, "global_step": 617662, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.944555401802063, "global_step": 617663, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0480797290802, "global_step": 617664, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0634925365448, "global_step": 617665, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9818894863128662, "global_step": 617666, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.043775796890259, "global_step": 617667, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9993484020233154, "global_step": 617668, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9557807445526123, "global_step": 617669, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9982991218566895, "global_step": 617670, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.914023756980896, "global_step": 617671, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0006747245788574, "global_step": 617672, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.008864641189575, "global_step": 617673, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9688539505004883, "global_step": 617674, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.009938955307007, "global_step": 617675, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.013570547103882, "global_step": 617676, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.066936492919922, "global_step": 617677, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9228118658065796, "global_step": 617678, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.063363552093506, "global_step": 617679, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9895505905151367, "global_step": 617680, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9821611642837524, "global_step": 617681, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0983290672302246, "global_step": 617682, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.024661064147949, "global_step": 617683, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0408313274383545, "global_step": 617684, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9688022136688232, "global_step": 617685, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.051748037338257, "global_step": 617686, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.021243095397949, "global_step": 617687, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.952299952507019, "global_step": 617688, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0282907485961914, "global_step": 617689, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9869767427444458, "global_step": 617690, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9983335733413696, "global_step": 617691, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9963464736938477, "global_step": 617692, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0265259742736816, "global_step": 617693, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0295801162719727, "global_step": 617694, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0562984943389893, "global_step": 617695, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9684276580810547, "global_step": 617696, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.064338207244873, "global_step": 617697, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0151829719543457, "global_step": 617698, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.025205135345459, "global_step": 617699, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9679635763168335, "global_step": 617700, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9753873348236084, "global_step": 617701, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0081980228424072, "global_step": 617702, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.081395149230957, "global_step": 617703, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0632622241973877, "global_step": 617704, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.050994634628296, "global_step": 617705, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0625205039978027, "global_step": 617706, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0024096965789795, "global_step": 617707, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9513556957244873, "global_step": 617708, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9685840606689453, "global_step": 617709, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0342719554901123, "global_step": 617710, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9866427183151245, "global_step": 617711, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0688059329986572, "global_step": 617712, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0082738399505615, "global_step": 617713, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0774810314178467, "global_step": 617714, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.09224009513855, "global_step": 617715, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9238682985305786, "global_step": 617716, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.016143560409546, "global_step": 617717, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9913380146026611, "global_step": 617718, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0397260189056396, "global_step": 617719, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.085164785385132, "global_step": 617720, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.099618434906006, "global_step": 617721, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.974355697631836, "global_step": 617722, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.038526773452759, "global_step": 617723, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9469635486602783, "global_step": 617724, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9850844144821167, "global_step": 617725, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9926379919052124, "global_step": 617726, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0100343227386475, "global_step": 617727, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9134948253631592, "global_step": 617728, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.985990285873413, "global_step": 617729, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0557801723480225, "global_step": 617730, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9864898920059204, "global_step": 617731, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.024569511413574, "global_step": 617732, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9113162755966187, "global_step": 617733, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0110421180725098, "global_step": 617734, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0552303791046143, "global_step": 617735, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.919512391090393, "global_step": 617736, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0211970806121826, "global_step": 617737, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9719576835632324, "global_step": 617738, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0993592739105225, "global_step": 617739, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9514654874801636, "global_step": 617740, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9575835466384888, "global_step": 617741, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0398788452148438, "global_step": 617742, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9391049146652222, "global_step": 617743, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.085081100463867, "global_step": 617744, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0069339275360107, "global_step": 617745, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0130374431610107, "global_step": 617746, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9622453451156616, "global_step": 617747, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.068863868713379, "global_step": 617748, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0156748294830322, "global_step": 617749, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9855626821517944, "global_step": 617750, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.051548480987549, "global_step": 617751, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.98835027217865, "global_step": 617752, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0323214530944824, "global_step": 617753, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.058122396469116, "global_step": 617754, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.044912815093994, "global_step": 617755, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0499258041381836, "global_step": 617756, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9663143157958984, "global_step": 617757, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9825749397277832, "global_step": 617758, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.039862632751465, "global_step": 617759, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0109245777130127, "global_step": 617760, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9798715114593506, "global_step": 617761, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9998838901519775, "global_step": 617762, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.056279182434082, "global_step": 617763, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.950584053993225, "global_step": 617764, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0021164417266846, "global_step": 617765, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0249111652374268, "global_step": 617766, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.978236436843872, "global_step": 617767, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9499861001968384, "global_step": 617768, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.085036516189575, "global_step": 617769, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9725483655929565, "global_step": 617770, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9953924417495728, "global_step": 617771, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.079577922821045, "global_step": 617772, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9921554327011108, "global_step": 617773, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9045298099517822, "global_step": 617774, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.001110792160034, "global_step": 617775, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9205241203308105, "global_step": 617776, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9617811441421509, "global_step": 617777, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0649447441101074, "global_step": 617778, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.064884901046753, "global_step": 617779, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.033555746078491, "global_step": 617780, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0146424770355225, "global_step": 617781, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0105392932891846, "global_step": 617782, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.031920909881592, "global_step": 617783, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0110888481140137, "global_step": 617784, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9894590377807617, "global_step": 617785, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.049909830093384, "global_step": 617786, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.082120418548584, "global_step": 617787, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0103073120117188, "global_step": 617788, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0157909393310547, "global_step": 617789, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9584141969680786, "global_step": 617790, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9749475717544556, "global_step": 617791, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0043957233428955, "global_step": 617792, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0386195182800293, "global_step": 617793, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0166635513305664, "global_step": 617794, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.036593437194824, "global_step": 617795, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9799067974090576, "global_step": 617796, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.042754650115967, "global_step": 617797, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9440668821334839, "global_step": 617798, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.93446946144104, "global_step": 617799, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.976724624633789, "global_step": 617800, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.025397777557373, "global_step": 617801, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9865403175354004, "global_step": 617802, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.065203905105591, "global_step": 617803, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.022887945175171, "global_step": 617804, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9720274209976196, "global_step": 617805, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9970494508743286, "global_step": 617806, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0100908279418945, "global_step": 617807, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.100064754486084, "global_step": 617808, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.008547306060791, "global_step": 617809, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0442543029785156, "global_step": 617810, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.034332275390625, "global_step": 617811, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0980494022369385, "global_step": 617812, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0066473484039307, "global_step": 617813, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.002142906188965, "global_step": 617814, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9898991584777832, "global_step": 617815, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9942686557769775, "global_step": 617816, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.047766923904419, "global_step": 617817, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.113384246826172, "global_step": 617818, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9651634693145752, "global_step": 617819, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9846792221069336, "global_step": 617820, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9915509223937988, "global_step": 617821, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0246541500091553, "global_step": 617822, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0665531158447266, "global_step": 617823, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0525705814361572, "global_step": 617824, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.973907470703125, "global_step": 617825, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9332284927368164, "global_step": 617826, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9769965410232544, "global_step": 617827, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0003888607025146, "global_step": 617828, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.039024591445923, "global_step": 617829, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.01120924949646, "global_step": 617830, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9131947755813599, "global_step": 617831, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.105018377304077, "global_step": 617832, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.084117889404297, "global_step": 617833, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.911552906036377, "global_step": 617834, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9206488132476807, "global_step": 617835, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.022503614425659, "global_step": 617836, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9794498682022095, "global_step": 617837, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9993667602539062, "global_step": 617838, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.991913914680481, "global_step": 617839, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.091738224029541, "global_step": 617840, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0229616165161133, "global_step": 617841, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.980879545211792, "global_step": 617842, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.1385457515716553, "global_step": 617843, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.044761896133423, "global_step": 617844, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.051725387573242, "global_step": 617845, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.1056833267211914, "global_step": 617846, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9869436025619507, "global_step": 617847, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.037868022918701, "global_step": 617848, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9649062156677246, "global_step": 617849, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0421998500823975, "global_step": 617850, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.1019704341888428, "global_step": 617851, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.047145366668701, "global_step": 617852, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9465222358703613, "global_step": 617853, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.134373426437378, "global_step": 617854, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0400099754333496, "global_step": 617855, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9578943252563477, "global_step": 617856, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.980261206626892, "global_step": 617857, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.036691427230835, "global_step": 617858, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.1022684574127197, "global_step": 617859, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.032670259475708, "global_step": 617860, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9494318962097168, "global_step": 617861, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9636427164077759, "global_step": 617862, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0061488151550293, "global_step": 617863, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9287983179092407, "global_step": 617864, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.036701202392578, "global_step": 617865, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9141805171966553, "global_step": 617866, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.072976589202881, "global_step": 617867, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0601487159729004, "global_step": 617868, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9752320051193237, "global_step": 617869, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9532543420791626, "global_step": 617870, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.062894582748413, "global_step": 617871, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.980501651763916, "global_step": 617872, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9801174402236938, "global_step": 617873, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0432167053222656, "global_step": 617874, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9897682666778564, "global_step": 617875, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.983846664428711, "global_step": 617876, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9545317888259888, "global_step": 617877, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9933698177337646, "global_step": 617878, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9704005718231201, "global_step": 617879, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9614638090133667, "global_step": 617880, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9972827434539795, "global_step": 617881, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.999177098274231, "global_step": 617882, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9520570039749146, "global_step": 617883, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.044792413711548, "global_step": 617884, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9922904968261719, "global_step": 617885, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9885873794555664, "global_step": 617886, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0871541500091553, "global_step": 617887, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0453107357025146, "global_step": 617888, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.059110403060913, "global_step": 617889, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0265185832977295, "global_step": 617890, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9468040466308594, "global_step": 617891, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0402095317840576, "global_step": 617892, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.041372776031494, "global_step": 617893, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0338118076324463, "global_step": 617894, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9548864364624023, "global_step": 617895, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0318515300750732, "global_step": 617896, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9831331968307495, "global_step": 617897, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0275118350982666, "global_step": 617898, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.885892629623413, "global_step": 617899, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9905152320861816, "global_step": 617900, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9649646282196045, "global_step": 617901, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.110309362411499, "global_step": 617902, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.004812479019165, "global_step": 617903, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9941685199737549, "global_step": 617904, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9992191791534424, "global_step": 617905, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0535850524902344, "global_step": 617906, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9854350090026855, "global_step": 617907, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9447376728057861, "global_step": 617908, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9900856018066406, "global_step": 617909, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0554909706115723, "global_step": 617910, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0427675247192383, "global_step": 617911, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0218749046325684, "global_step": 617912, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9714864492416382, "global_step": 617913, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0065314769744873, "global_step": 617914, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9927175045013428, "global_step": 617915, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.016197919845581, "global_step": 617916, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9800931215286255, "global_step": 617917, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9800565242767334, "global_step": 617918, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.02816104888916, "global_step": 617919, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.087578058242798, "global_step": 617920, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0169878005981445, "global_step": 617921, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9334375858306885, "global_step": 617922, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9181054830551147, "global_step": 617923, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9674060344696045, "global_step": 617924, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0665950775146484, "global_step": 617925, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0387260913848877, "global_step": 617926, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9826250076293945, "global_step": 617927, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.065924882888794, "global_step": 617928, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9213573932647705, "global_step": 617929, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9050313234329224, "global_step": 617930, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9322420358657837, "global_step": 617931, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.967162847518921, "global_step": 617932, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9574744701385498, "global_step": 617933, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9824994802474976, "global_step": 617934, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9946788549423218, "global_step": 617935, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9779046773910522, "global_step": 617936, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9903838634490967, "global_step": 617937, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.950352430343628, "global_step": 617938, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.977853775024414, "global_step": 617939, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9748610258102417, "global_step": 617940, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.952789545059204, "global_step": 617941, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9842584133148193, "global_step": 617942, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.020249843597412, "global_step": 617943, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.039674758911133, "global_step": 617944, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0283288955688477, "global_step": 617945, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0169451236724854, "global_step": 617946, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0367627143859863, "global_step": 617947, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.054870128631592, "global_step": 617948, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0307822227478027, "global_step": 617949, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.8813977241516113, "global_step": 617950, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0564515590667725, "global_step": 617951, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.062434196472168, "global_step": 617952, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9346940517425537, "global_step": 617953, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0171401500701904, "global_step": 617954, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.1089844703674316, "global_step": 617955, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9808975458145142, "global_step": 617956, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.049976110458374, "global_step": 617957, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.005671262741089, "global_step": 617958, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.931960105895996, "global_step": 617959, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.007781982421875, "global_step": 617960, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.025110960006714, "global_step": 617961, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9340702295303345, "global_step": 617962, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.042248010635376, "global_step": 617963, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0043299198150635, "global_step": 617964, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0216052532196045, "global_step": 617965, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0013022422790527, "global_step": 617966, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.091029405593872, "global_step": 617967, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.059053659439087, "global_step": 617968, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.00701904296875, "global_step": 617969, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0277416706085205, "global_step": 617970, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.026536703109741, "global_step": 617971, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9493452310562134, "global_step": 617972, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9786255359649658, "global_step": 617973, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0242488384246826, "global_step": 617974, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9683341979980469, "global_step": 617975, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0347938537597656, "global_step": 617976, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0289158821105957, "global_step": 617977, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.916841745376587, "global_step": 617978, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.011364459991455, "global_step": 617979, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9680300951004028, "global_step": 617980, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0324137210845947, "global_step": 617981, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9510747194290161, "global_step": 617982, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.009906053543091, "global_step": 617983, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0671169757843018, "global_step": 617984, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9570591449737549, "global_step": 617985, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.040236234664917, "global_step": 617986, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0364956855773926, "global_step": 617987, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0814688205718994, "global_step": 617988, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9332636594772339, "global_step": 617989, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.957126498222351, "global_step": 617990, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9648140668869019, "global_step": 617991, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0580198764801025, "global_step": 617992, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0382940769195557, "global_step": 617993, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9655208587646484, "global_step": 617994, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9694950580596924, "global_step": 617995, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.002946615219116, "global_step": 617996, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0362043380737305, "global_step": 617997, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.043715476989746, "global_step": 617998, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0996193885803223, "global_step": 617999, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0213451385498047, "global_step": 618000, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.022066354751587, "global_step": 618001, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9834672212600708, "global_step": 618002, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0875442028045654, "global_step": 618003, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9517323970794678, "global_step": 618004, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.016754388809204, "global_step": 618005, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0055911540985107, "global_step": 618006, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.883118987083435, "global_step": 618007, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.1103975772857666, "global_step": 618008, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0139427185058594, "global_step": 618009, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9270060062408447, "global_step": 618010, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9520469903945923, "global_step": 618011, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.059990406036377, "global_step": 618012, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.064775228500366, "global_step": 618013, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0763297080993652, "global_step": 618014, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0040717124938965, "global_step": 618015, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9826016426086426, "global_step": 618016, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0320231914520264, "global_step": 618017, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0219831466674805, "global_step": 618018, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.054030179977417, "global_step": 618019, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9756556749343872, "global_step": 618020, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0865445137023926, "global_step": 618021, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9485833644866943, "global_step": 618022, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9947141408920288, "global_step": 618023, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0197694301605225, "global_step": 618024, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9739413261413574, "global_step": 618025, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0258922576904297, "global_step": 618026, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.004889488220215, "global_step": 618027, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9678738117218018, "global_step": 618028, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0316483974456787, "global_step": 618029, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9098522663116455, "global_step": 618030, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9901480674743652, "global_step": 618031, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.884936809539795, "global_step": 618032, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9785534143447876, "global_step": 618033, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.8869457244873047, "global_step": 618034, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9829394817352295, "global_step": 618035, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.982485294342041, "global_step": 618036, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.94060218334198, "global_step": 618037, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9992073774337769, "global_step": 618038, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.014284372329712, "global_step": 618039, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0161519050598145, "global_step": 618040, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.093756914138794, "global_step": 618041, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0151712894439697, "global_step": 618042, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.070483684539795, "global_step": 618043, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.075707197189331, "global_step": 618044, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9195290803909302, "global_step": 618045, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.086557388305664, "global_step": 618046, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.067519187927246, "global_step": 618047, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9642887115478516, "global_step": 618048, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.109978199005127, "global_step": 618049, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0770957469940186, "global_step": 618050, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9819669723510742, "global_step": 618051, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9969029426574707, "global_step": 618052, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.031409740447998, "global_step": 618053, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.015812635421753, "global_step": 618054, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.078258991241455, "global_step": 618055, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0740551948547363, "global_step": 618056, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.989174246788025, "global_step": 618057, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.043823480606079, "global_step": 618058, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9850434064865112, "global_step": 618059, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9828133583068848, "global_step": 618060, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.047192335128784, "global_step": 618061, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.033806800842285, "global_step": 618062, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0819482803344727, "global_step": 618063, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.062318801879883, "global_step": 618064, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.045112371444702, "global_step": 618065, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9863309860229492, "global_step": 618066, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.036043643951416, "global_step": 618067, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.01552414894104, "global_step": 618068, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9775444269180298, "global_step": 618069, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.10298752784729, "global_step": 618070, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.949505090713501, "global_step": 618071, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9960381984710693, "global_step": 618072, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.015523910522461, "global_step": 618073, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.016238212585449, "global_step": 618074, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.967147707939148, "global_step": 618075, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9465041160583496, "global_step": 618076, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9928529262542725, "global_step": 618077, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.022376775741577, "global_step": 618078, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9611836671829224, "global_step": 618079, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.020787477493286, "global_step": 618080, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0351128578186035, "global_step": 618081, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.070993661880493, "global_step": 618082, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.074892997741699, "global_step": 618083, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.046998977661133, "global_step": 618084, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9329497814178467, "global_step": 618085, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.001434803009033, "global_step": 618086, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.973938226699829, "global_step": 618087, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.91700279712677, "global_step": 618088, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9590787887573242, "global_step": 618089, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.011042833328247, "global_step": 618090, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.02351450920105, "global_step": 618091, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0598509311676025, "global_step": 618092, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.121396064758301, "global_step": 618093, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9942235946655273, "global_step": 618094, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.039421319961548, "global_step": 618095, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9901564121246338, "global_step": 618096, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9628238677978516, "global_step": 618097, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.058340072631836, "global_step": 618098, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.013857126235962, "global_step": 618099, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.055591583251953, "global_step": 618100, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.970143437385559, "global_step": 618101, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0101871490478516, "global_step": 618102, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9874250888824463, "global_step": 618103, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.984300971031189, "global_step": 618104, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.031402826309204, "global_step": 618105, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9927905797958374, "global_step": 618106, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9708888530731201, "global_step": 618107, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0322318077087402, "global_step": 618108, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9587098360061646, "global_step": 618109, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.065260410308838, "global_step": 618110, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.004892110824585, "global_step": 618111, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.900597095489502, "global_step": 618112, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0104928016662598, "global_step": 618113, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9580732583999634, "global_step": 618114, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9580669403076172, "global_step": 618115, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9866074323654175, "global_step": 618116, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0299291610717773, "global_step": 618117, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9881654977798462, "global_step": 618118, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.039909839630127, "global_step": 618119, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.009361743927002, "global_step": 618120, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9338648319244385, "global_step": 618121, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9410529136657715, "global_step": 618122, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.045562744140625, "global_step": 618123, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.019969940185547, "global_step": 618124, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9720613956451416, "global_step": 618125, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0006420612335205, "global_step": 618126, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0854735374450684, "global_step": 618127, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0418286323547363, "global_step": 618128, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.002352237701416, "global_step": 618129, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.113882541656494, "global_step": 618130, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9621062278747559, "global_step": 618131, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.950682282447815, "global_step": 618132, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.033695697784424, "global_step": 618133, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.020618438720703, "global_step": 618134, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.047928810119629, "global_step": 618135, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9263367652893066, "global_step": 618136, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0677359104156494, "global_step": 618137, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.977641224861145, "global_step": 618138, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.002652883529663, "global_step": 618139, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9953919649124146, "global_step": 618140, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.003624439239502, "global_step": 618141, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0238757133483887, "global_step": 618142, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.996489405632019, "global_step": 618143, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0120770931243896, "global_step": 618144, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9860590696334839, "global_step": 618145, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9964592456817627, "global_step": 618146, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.005392551422119, "global_step": 618147, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.052844762802124, "global_step": 618148, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.011634588241577, "global_step": 618149, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9692790508270264, "global_step": 618150, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9780430793762207, "global_step": 618151, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0319628715515137, "global_step": 618152, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.070251703262329, "global_step": 618153, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.042232036590576, "global_step": 618154, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.1238017082214355, "global_step": 618155, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9606112241744995, "global_step": 618156, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9828803539276123, "global_step": 618157, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.927632212638855, "global_step": 618158, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.938218116760254, "global_step": 618159, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.009540319442749, "global_step": 618160, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0199809074401855, "global_step": 618161, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.051650285720825, "global_step": 618162, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.061619520187378, "global_step": 618163, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0381627082824707, "global_step": 618164, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.016775131225586, "global_step": 618165, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.172240734100342, "global_step": 618166, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0403029918670654, "global_step": 618167, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.000086545944214, "global_step": 618168, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.054839611053467, "global_step": 618169, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.054276466369629, "global_step": 618170, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.081439971923828, "global_step": 618171, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0191051959991455, "global_step": 618172, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0209126472473145, "global_step": 618173, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0500848293304443, "global_step": 618174, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.003444194793701, "global_step": 618175, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.989635705947876, "global_step": 618176, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.013355255126953, "global_step": 618177, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.028475046157837, "global_step": 618178, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0565080642700195, "global_step": 618179, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0304605960845947, "global_step": 618180, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0212481021881104, "global_step": 618181, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9192746877670288, "global_step": 618182, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0030856132507324, "global_step": 618183, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0358777046203613, "global_step": 618184, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0053257942199707, "global_step": 618185, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.019174337387085, "global_step": 618186, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9322168827056885, "global_step": 618187, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0243823528289795, "global_step": 618188, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.032569169998169, "global_step": 618189, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.071659803390503, "global_step": 618190, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0543570518493652, "global_step": 618191, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9734889268875122, "global_step": 618192, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9665135145187378, "global_step": 618193, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9392417669296265, "global_step": 618194, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.909861445426941, "global_step": 618195, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.039027690887451, "global_step": 618196, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.038395404815674, "global_step": 618197, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.00358247756958, "global_step": 618198, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.000528573989868, "global_step": 618199, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9161056280136108, "global_step": 618200, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0025877952575684, "global_step": 618201, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9742121696472168, "global_step": 618202, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0075485706329346, "global_step": 618203, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0330512523651123, "global_step": 618204, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9899436235427856, "global_step": 618205, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.931301236152649, "global_step": 618206, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.064016819000244, "global_step": 618207, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.040729522705078, "global_step": 618208, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.975533366203308, "global_step": 618209, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9687163829803467, "global_step": 618210, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.951460361480713, "global_step": 618211, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9079848527908325, "global_step": 618212, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0179622173309326, "global_step": 618213, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0726888179779053, "global_step": 618214, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.992965817451477, "global_step": 618215, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.1021318435668945, "global_step": 618216, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.99223792552948, "global_step": 618217, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.918489933013916, "global_step": 618218, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9763034582138062, "global_step": 618219, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.024263620376587, "global_step": 618220, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0561306476593018, "global_step": 618221, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.025320291519165, "global_step": 618222, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9947319030761719, "global_step": 618223, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.874849796295166, "global_step": 618224, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0272843837738037, "global_step": 618225, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0261502265930176, "global_step": 618226, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0937936305999756, "global_step": 618227, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.939453363418579, "global_step": 618228, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9707953929901123, "global_step": 618229, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.062507152557373, "global_step": 618230, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9428883790969849, "global_step": 618231, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0233206748962402, "global_step": 618232, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.101881980895996, "global_step": 618233, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0634987354278564, "global_step": 618234, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0255331993103027, "global_step": 618235, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9928064346313477, "global_step": 618236, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0412721633911133, "global_step": 618237, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0532660484313965, "global_step": 618238, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9852683544158936, "global_step": 618239, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0693917274475098, "global_step": 618240, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.019483804702759, "global_step": 618241, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9226065874099731, "global_step": 618242, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.07139253616333, "global_step": 618243, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.033224105834961, "global_step": 618244, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9926087856292725, "global_step": 618245, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.076413869857788, "global_step": 618246, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0396728515625, "global_step": 618247, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.041165351867676, "global_step": 618248, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.011471748352051, "global_step": 618249, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.021001100540161, "global_step": 618250, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9857593774795532, "global_step": 618251, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0178449153900146, "global_step": 618252, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9373881816864014, "global_step": 618253, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.986579179763794, "global_step": 618254, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0173542499542236, "global_step": 618255, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9967526197433472, "global_step": 618256, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.096080780029297, "global_step": 618257, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0111806392669678, "global_step": 618258, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0634329319000244, "global_step": 618259, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.022493362426758, "global_step": 618260, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.1060245037078857, "global_step": 618261, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9678877592086792, "global_step": 618262, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.053497791290283, "global_step": 618263, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.875939965248108, "global_step": 618264, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9246524572372437, "global_step": 618265, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0658600330352783, "global_step": 618266, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9995671510696411, "global_step": 618267, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.024937152862549, "global_step": 618268, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.097611427307129, "global_step": 618269, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9615267515182495, "global_step": 618270, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9976108074188232, "global_step": 618271, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.089134454727173, "global_step": 618272, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0326292514801025, "global_step": 618273, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0328145027160645, "global_step": 618274, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9859789609909058, "global_step": 618275, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.01381516456604, "global_step": 618276, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.1046130657196045, "global_step": 618277, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9785760641098022, "global_step": 618278, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0060813426971436, "global_step": 618279, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.02520489692688, "global_step": 618280, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.019824743270874, "global_step": 618281, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0101943016052246, "global_step": 618282, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.992362380027771, "global_step": 618283, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.00467848777771, "global_step": 618284, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9685254096984863, "global_step": 618285, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0339808464050293, "global_step": 618286, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9489017724990845, "global_step": 618287, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9204165935516357, "global_step": 618288, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0834803581237793, "global_step": 618289, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.031729221343994, "global_step": 618290, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.8853775262832642, "global_step": 618291, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9732474088668823, "global_step": 618292, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9615471363067627, "global_step": 618293, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9847681522369385, "global_step": 618294, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0706515312194824, "global_step": 618295, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9782254695892334, "global_step": 618296, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.026792526245117, "global_step": 618297, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.007966995239258, "global_step": 618298, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9825172424316406, "global_step": 618299, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.004685401916504, "global_step": 618300, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.048707962036133, "global_step": 618301, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9861209392547607, "global_step": 618302, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0014851093292236, "global_step": 618303, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0627081394195557, "global_step": 618304, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0000991821289062, "global_step": 618305, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9684518575668335, "global_step": 618306, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0425238609313965, "global_step": 618307, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9742335081100464, "global_step": 618308, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0353927612304688, "global_step": 618309, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0038046836853027, "global_step": 618310, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9761581420898438, "global_step": 618311, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9856585264205933, "global_step": 618312, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9857094287872314, "global_step": 618313, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9834280014038086, "global_step": 618314, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9226386547088623, "global_step": 618315, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9395867586135864, "global_step": 618316, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0589051246643066, "global_step": 618317, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9931762218475342, "global_step": 618318, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0066089630126953, "global_step": 618319, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0007286071777344, "global_step": 618320, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9587314128875732, "global_step": 618321, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9648898839950562, "global_step": 618322, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0147624015808105, "global_step": 618323, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.945071816444397, "global_step": 618324, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.024824380874634, "global_step": 618325, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0085856914520264, "global_step": 618326, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9599213600158691, "global_step": 618327, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9996757507324219, "global_step": 618328, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9979932308197021, "global_step": 618329, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9215394258499146, "global_step": 618330, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0501468181610107, "global_step": 618331, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0046017169952393, "global_step": 618332, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.970271110534668, "global_step": 618333, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.934003472328186, "global_step": 618334, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.039018392562866, "global_step": 618335, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0065150260925293, "global_step": 618336, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.053792715072632, "global_step": 618337, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0198447704315186, "global_step": 618338, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9830048084259033, "global_step": 618339, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0675206184387207, "global_step": 618340, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.039668083190918, "global_step": 618341, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.009519577026367, "global_step": 618342, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.1046223640441895, "global_step": 618343, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0475447177886963, "global_step": 618344, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0624170303344727, "global_step": 618345, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0010998249053955, "global_step": 618346, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9891033172607422, "global_step": 618347, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0486717224121094, "global_step": 618348, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.061192512512207, "global_step": 618349, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9428471326828003, "global_step": 618350, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.068129301071167, "global_step": 618351, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0266036987304688, "global_step": 618352, "epoch": 987, "lr": 5e-05}
{"train_loss": 1.9292328357696533, "global_step": 618353, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0061705112457275, "global_step": 618354, "epoch": 987, "lr": 5e-05}
{"train_loss": 2.0357229709625244, "global_step": 618355, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0359442234039307, "global_step": 618356, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.017359495162964, "global_step": 618357, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.043302536010742, "global_step": 618358, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9675509929656982, "global_step": 618359, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9842064380645752, "global_step": 618360, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9888238906860352, "global_step": 618361, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0584332942962646, "global_step": 618362, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9778465032577515, "global_step": 618363, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.944021224975586, "global_step": 618364, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0477097034454346, "global_step": 618365, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9884147644042969, "global_step": 618366, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0776660442352295, "global_step": 618367, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9541676044464111, "global_step": 618368, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.043821334838867, "global_step": 618369, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.021956205368042, "global_step": 618370, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.036857843399048, "global_step": 618371, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0310564041137695, "global_step": 618372, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.070394992828369, "global_step": 618373, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.071403980255127, "global_step": 618374, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.8891774415969849, "global_step": 618375, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9501785039901733, "global_step": 618376, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.019338846206665, "global_step": 618377, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9827908277511597, "global_step": 618378, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.011622428894043, "global_step": 618379, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0771548748016357, "global_step": 618380, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0813686847686768, "global_step": 618381, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0109760761260986, "global_step": 618382, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9762669801712036, "global_step": 618383, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.964192271232605, "global_step": 618384, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9681236743927002, "global_step": 618385, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9704923629760742, "global_step": 618386, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9748778343200684, "global_step": 618387, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.037120819091797, "global_step": 618388, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9472789764404297, "global_step": 618389, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.040712833404541, "global_step": 618390, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.03706693649292, "global_step": 618391, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.99578058719635, "global_step": 618392, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.075352430343628, "global_step": 618393, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.057882070541382, "global_step": 618394, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9139381647109985, "global_step": 618395, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0589561462402344, "global_step": 618396, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9658492803573608, "global_step": 618397, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9548927545547485, "global_step": 618398, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0452828407287598, "global_step": 618399, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.110703468322754, "global_step": 618400, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9344316720962524, "global_step": 618401, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0049445629119873, "global_step": 618402, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0087685585021973, "global_step": 618403, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0510740280151367, "global_step": 618404, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0473833084106445, "global_step": 618405, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.021521806716919, "global_step": 618406, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9387266635894775, "global_step": 618407, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.100787401199341, "global_step": 618408, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9431687593460083, "global_step": 618409, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9835566282272339, "global_step": 618410, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.04626727104187, "global_step": 618411, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9962077140808105, "global_step": 618412, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9026525020599365, "global_step": 618413, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9223438501358032, "global_step": 618414, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0299360752105713, "global_step": 618415, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9189307689666748, "global_step": 618416, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.05121111869812, "global_step": 618417, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.027395009994507, "global_step": 618418, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0090434551239014, "global_step": 618419, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9658582210540771, "global_step": 618420, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.045700788497925, "global_step": 618421, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9592065811157227, "global_step": 618422, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.963149070739746, "global_step": 618423, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0253729820251465, "global_step": 618424, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9679181575775146, "global_step": 618425, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.014620304107666, "global_step": 618426, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9504752159118652, "global_step": 618427, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9691698551177979, "global_step": 618428, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0166854858398438, "global_step": 618429, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.068344831466675, "global_step": 618430, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9646477699279785, "global_step": 618431, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9404367208480835, "global_step": 618432, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9770467281341553, "global_step": 618433, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.952949047088623, "global_step": 618434, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.053135395050049, "global_step": 618435, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9621398448944092, "global_step": 618436, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9819529056549072, "global_step": 618437, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0239686965942383, "global_step": 618438, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.029958963394165, "global_step": 618439, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0213046073913574, "global_step": 618440, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9518054723739624, "global_step": 618441, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9908908605575562, "global_step": 618442, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9966996908187866, "global_step": 618443, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9814953804016113, "global_step": 618444, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.01374888420105, "global_step": 618445, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.011629819869995, "global_step": 618446, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.97536301612854, "global_step": 618447, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9871079921722412, "global_step": 618448, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0070455074310303, "global_step": 618449, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0319881439208984, "global_step": 618450, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9635300636291504, "global_step": 618451, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.953831672668457, "global_step": 618452, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0061192512512207, "global_step": 618453, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9490851163864136, "global_step": 618454, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9775400161743164, "global_step": 618455, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.973083734512329, "global_step": 618456, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9125171899795532, "global_step": 618457, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0457704067230225, "global_step": 618458, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9384363889694214, "global_step": 618459, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9513314962387085, "global_step": 618460, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.121523857116699, "global_step": 618461, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9206358194351196, "global_step": 618462, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9789612293243408, "global_step": 618463, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.029639482498169, "global_step": 618464, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0044608116149902, "global_step": 618465, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.031100273132324, "global_step": 618466, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.94171941280365, "global_step": 618467, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.946155071258545, "global_step": 618468, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9665496349334717, "global_step": 618469, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.030449628829956, "global_step": 618470, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.021960496902466, "global_step": 618471, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.036871910095215, "global_step": 618472, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.989260196685791, "global_step": 618473, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9712872505187988, "global_step": 618474, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9687330722808838, "global_step": 618475, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.039348602294922, "global_step": 618476, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9733412265777588, "global_step": 618477, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0495471954345703, "global_step": 618478, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9239885807037354, "global_step": 618479, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.017637014389038, "global_step": 618480, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.994012713432312, "global_step": 618481, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9763739109039307, "global_step": 618482, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0460574626922607, "global_step": 618483, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.039872169494629, "global_step": 618484, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0302624702453613, "global_step": 618485, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.007566213607788, "global_step": 618486, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9723304510116577, "global_step": 618487, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.003546714782715, "global_step": 618488, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.005399227142334, "global_step": 618489, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9877533912658691, "global_step": 618490, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.8887351751327515, "global_step": 618491, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.11185359954834, "global_step": 618492, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9926316738128662, "global_step": 618493, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9482728242874146, "global_step": 618494, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.995872974395752, "global_step": 618495, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0097098350524902, "global_step": 618496, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9469318389892578, "global_step": 618497, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9790395498275757, "global_step": 618498, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.037619113922119, "global_step": 618499, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.02651309967041, "global_step": 618500, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.045884609222412, "global_step": 618501, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9927736520767212, "global_step": 618502, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0791380405426025, "global_step": 618503, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.10145902633667, "global_step": 618504, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9680317640304565, "global_step": 618505, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.061257839202881, "global_step": 618506, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.99324369430542, "global_step": 618507, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0755112171173096, "global_step": 618508, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0050084590911865, "global_step": 618509, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9832497835159302, "global_step": 618510, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.036297559738159, "global_step": 618511, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9912641048431396, "global_step": 618512, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0052270889282227, "global_step": 618513, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0605037212371826, "global_step": 618514, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9405925273895264, "global_step": 618515, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9993399381637573, "global_step": 618516, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.024155616760254, "global_step": 618517, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0032596588134766, "global_step": 618518, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0311427116394043, "global_step": 618519, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.003885269165039, "global_step": 618520, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.020480155944824, "global_step": 618521, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.004183053970337, "global_step": 618522, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9758259057998657, "global_step": 618523, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9401721954345703, "global_step": 618524, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9988200664520264, "global_step": 618525, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9525299072265625, "global_step": 618526, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9851865768432617, "global_step": 618527, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9052577018737793, "global_step": 618528, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.957033634185791, "global_step": 618529, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9760067462921143, "global_step": 618530, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9292601346969604, "global_step": 618531, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.985952615737915, "global_step": 618532, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9718239307403564, "global_step": 618533, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.02449369430542, "global_step": 618534, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.988974928855896, "global_step": 618535, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9239447116851807, "global_step": 618536, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.020740032196045, "global_step": 618537, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9782058000564575, "global_step": 618538, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9695966243743896, "global_step": 618539, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9742095470428467, "global_step": 618540, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.04219388961792, "global_step": 618541, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.93584406375885, "global_step": 618542, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.004476308822632, "global_step": 618543, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9684605598449707, "global_step": 618544, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9949183464050293, "global_step": 618545, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.946441650390625, "global_step": 618546, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0418403148651123, "global_step": 618547, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9876152276992798, "global_step": 618548, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0226216316223145, "global_step": 618549, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9760103225708008, "global_step": 618550, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9690368175506592, "global_step": 618551, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9477550983428955, "global_step": 618552, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.039828062057495, "global_step": 618553, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9908390045166016, "global_step": 618554, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.058488130569458, "global_step": 618555, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.044686794281006, "global_step": 618556, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.002838134765625, "global_step": 618557, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9954167604446411, "global_step": 618558, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0678749084472656, "global_step": 618559, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0559780597686768, "global_step": 618560, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9752379655838013, "global_step": 618561, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9341697692871094, "global_step": 618562, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9781039953231812, "global_step": 618563, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.074676513671875, "global_step": 618564, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0041141510009766, "global_step": 618565, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9538419246673584, "global_step": 618566, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.004525661468506, "global_step": 618567, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9763134717941284, "global_step": 618568, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.006378650665283, "global_step": 618569, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9108877182006836, "global_step": 618570, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.017606019973755, "global_step": 618571, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9727262258529663, "global_step": 618572, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9332752227783203, "global_step": 618573, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.039736747741699, "global_step": 618574, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9395067691802979, "global_step": 618575, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.030843496322632, "global_step": 618576, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.004753828048706, "global_step": 618577, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.05948543548584, "global_step": 618578, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0199036598205566, "global_step": 618579, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.034726619720459, "global_step": 618580, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9830223321914673, "global_step": 618581, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0956032276153564, "global_step": 618582, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9780734777450562, "global_step": 618583, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9114576578140259, "global_step": 618584, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.989796757698059, "global_step": 618585, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9000627994537354, "global_step": 618586, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9062131643295288, "global_step": 618587, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.008033037185669, "global_step": 618588, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0434679985046387, "global_step": 618589, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.8922024965286255, "global_step": 618590, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9581457376480103, "global_step": 618591, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0560317039489746, "global_step": 618592, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9852124452590942, "global_step": 618593, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0225014686584473, "global_step": 618594, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0305256843566895, "global_step": 618595, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0446290969848633, "global_step": 618596, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9954688549041748, "global_step": 618597, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9466099739074707, "global_step": 618598, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9482163190841675, "global_step": 618599, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.031928300857544, "global_step": 618600, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9939470291137695, "global_step": 618601, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.043916940689087, "global_step": 618602, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0787692070007324, "global_step": 618603, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.963929295539856, "global_step": 618604, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0207314491271973, "global_step": 618605, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.996714472770691, "global_step": 618606, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9703890085220337, "global_step": 618607, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.03277587890625, "global_step": 618608, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9928860664367676, "global_step": 618609, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.020490884780884, "global_step": 618610, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0159239768981934, "global_step": 618611, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9530936479568481, "global_step": 618612, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9641257524490356, "global_step": 618613, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0098819732666016, "global_step": 618614, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0130374431610107, "global_step": 618615, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.028400421142578, "global_step": 618616, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0481739044189453, "global_step": 618617, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9682362079620361, "global_step": 618618, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.008927822113037, "global_step": 618619, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0233163833618164, "global_step": 618620, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0171759128570557, "global_step": 618621, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9942491054534912, "global_step": 618622, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.037147045135498, "global_step": 618623, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9712038040161133, "global_step": 618624, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.946777105331421, "global_step": 618625, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0137670040130615, "global_step": 618626, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9614882469177246, "global_step": 618627, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.954062819480896, "global_step": 618628, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.028759002685547, "global_step": 618629, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9625732898712158, "global_step": 618630, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9772372245788574, "global_step": 618631, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0249247550964355, "global_step": 618632, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.102731227874756, "global_step": 618633, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9310084581375122, "global_step": 618634, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9841045141220093, "global_step": 618635, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.110302686691284, "global_step": 618636, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.969757080078125, "global_step": 618637, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.068155527114868, "global_step": 618638, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.944718599319458, "global_step": 618639, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0523946285247803, "global_step": 618640, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.1108319759368896, "global_step": 618641, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.90558922290802, "global_step": 618642, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.977525234222412, "global_step": 618643, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0837252140045166, "global_step": 618644, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0298781394958496, "global_step": 618645, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0310537815093994, "global_step": 618646, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9627562761306763, "global_step": 618647, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9681428670883179, "global_step": 618648, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9978255033493042, "global_step": 618649, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0591256618499756, "global_step": 618650, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.03352952003479, "global_step": 618651, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9770238399505615, "global_step": 618652, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.924360990524292, "global_step": 618653, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.026310682296753, "global_step": 618654, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.005042314529419, "global_step": 618655, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.961490511894226, "global_step": 618656, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9846857786178589, "global_step": 618657, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0178091526031494, "global_step": 618658, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9456111192703247, "global_step": 618659, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9700069427490234, "global_step": 618660, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9796574115753174, "global_step": 618661, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.029210090637207, "global_step": 618662, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0068883895874023, "global_step": 618663, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9329911470413208, "global_step": 618664, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.992136001586914, "global_step": 618665, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9631010293960571, "global_step": 618666, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.989846110343933, "global_step": 618667, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9157837629318237, "global_step": 618668, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9509077072143555, "global_step": 618669, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9720511436462402, "global_step": 618670, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.005502700805664, "global_step": 618671, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0207743644714355, "global_step": 618672, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9875534772872925, "global_step": 618673, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.068341016769409, "global_step": 618674, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9251792430877686, "global_step": 618675, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0181398391723633, "global_step": 618676, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9047081470489502, "global_step": 618677, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.975635051727295, "global_step": 618678, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.990606427192688, "global_step": 618679, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0226643085479736, "global_step": 618680, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9860451221466064, "global_step": 618681, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9909875392913818, "global_step": 618682, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.972982406616211, "global_step": 618683, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.058340311050415, "global_step": 618684, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.965996503829956, "global_step": 618685, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9857072830200195, "global_step": 618686, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.00504469871521, "global_step": 618687, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.00827693939209, "global_step": 618688, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9969850778579712, "global_step": 618689, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.992514967918396, "global_step": 618690, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9270942211151123, "global_step": 618691, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9708465337753296, "global_step": 618692, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.065448045730591, "global_step": 618693, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.021925687789917, "global_step": 618694, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.99655020236969, "global_step": 618695, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9011549949645996, "global_step": 618696, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9820581674575806, "global_step": 618697, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9870436191558838, "global_step": 618698, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9639722108840942, "global_step": 618699, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9498199224472046, "global_step": 618700, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.089388370513916, "global_step": 618701, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9449615478515625, "global_step": 618702, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.885256052017212, "global_step": 618703, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.009291410446167, "global_step": 618704, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0090150833129883, "global_step": 618705, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.1101906299591064, "global_step": 618706, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9981584548950195, "global_step": 618707, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9838043451309204, "global_step": 618708, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0172953605651855, "global_step": 618709, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0432446002960205, "global_step": 618710, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.020879030227661, "global_step": 618711, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.99240243434906, "global_step": 618712, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.047677755355835, "global_step": 618713, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9435888528823853, "global_step": 618714, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0455541610717773, "global_step": 618715, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9500118494033813, "global_step": 618716, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9699833393096924, "global_step": 618717, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.007378339767456, "global_step": 618718, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0163321495056152, "global_step": 618719, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.992473840713501, "global_step": 618720, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.1555402278900146, "global_step": 618721, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9447139501571655, "global_step": 618722, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0179245471954346, "global_step": 618723, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0098533630371094, "global_step": 618724, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0039167404174805, "global_step": 618725, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.012531042098999, "global_step": 618726, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.982122540473938, "global_step": 618727, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.038680076599121, "global_step": 618728, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.036918878555298, "global_step": 618729, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0087926387786865, "global_step": 618730, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9758405685424805, "global_step": 618731, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.064666271209717, "global_step": 618732, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.069873571395874, "global_step": 618733, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9981149435043335, "global_step": 618734, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0085794925689697, "global_step": 618735, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0263004302978516, "global_step": 618736, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0456461906433105, "global_step": 618737, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.015747547149658, "global_step": 618738, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.073728322982788, "global_step": 618739, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9313009977340698, "global_step": 618740, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.048985242843628, "global_step": 618741, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9187990427017212, "global_step": 618742, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9113576412200928, "global_step": 618743, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9805548191070557, "global_step": 618744, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.034140110015869, "global_step": 618745, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.01552677154541, "global_step": 618746, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9743566513061523, "global_step": 618747, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.8657686710357666, "global_step": 618748, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0934946537017822, "global_step": 618749, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.001073122024536, "global_step": 618750, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9956401586532593, "global_step": 618751, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9936175346374512, "global_step": 618752, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9754321575164795, "global_step": 618753, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0001962184906006, "global_step": 618754, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0149478912353516, "global_step": 618755, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.087270736694336, "global_step": 618756, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.03125262260437, "global_step": 618757, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9348019361495972, "global_step": 618758, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0410284996032715, "global_step": 618759, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.063107490539551, "global_step": 618760, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0092649459838867, "global_step": 618761, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.119539260864258, "global_step": 618762, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.027294397354126, "global_step": 618763, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.112130641937256, "global_step": 618764, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.021461009979248, "global_step": 618765, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.022123336791992, "global_step": 618766, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0517101287841797, "global_step": 618767, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0304038524627686, "global_step": 618768, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0169575214385986, "global_step": 618769, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.910189151763916, "global_step": 618770, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.920854091644287, "global_step": 618771, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.081906795501709, "global_step": 618772, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0426106452941895, "global_step": 618773, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0121421813964844, "global_step": 618774, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.048654079437256, "global_step": 618775, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9775986671447754, "global_step": 618776, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9853160381317139, "global_step": 618777, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9444549083709717, "global_step": 618778, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.951861023902893, "global_step": 618779, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.93044114112854, "global_step": 618780, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.037548303604126, "global_step": 618781, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0081300735473633, "global_step": 618782, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.033576011657715, "global_step": 618783, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9410600662231445, "global_step": 618784, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0956454277038574, "global_step": 618785, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.046996831893921, "global_step": 618786, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0494637489318848, "global_step": 618787, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.1050174236297607, "global_step": 618788, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0126936435699463, "global_step": 618789, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0069711208343506, "global_step": 618790, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.000898838043213, "global_step": 618791, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9840409755706787, "global_step": 618792, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.009950876235962, "global_step": 618793, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9728347063064575, "global_step": 618794, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.988139033317566, "global_step": 618795, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.8923605680465698, "global_step": 618796, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9503653049468994, "global_step": 618797, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9561405181884766, "global_step": 618798, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9883166551589966, "global_step": 618799, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.940043330192566, "global_step": 618800, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0702905654907227, "global_step": 618801, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.065180778503418, "global_step": 618802, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9051309823989868, "global_step": 618803, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.987792730331421, "global_step": 618804, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.033207654953003, "global_step": 618805, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.92070734500885, "global_step": 618806, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0212833881378174, "global_step": 618807, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.965793251991272, "global_step": 618808, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0308642387390137, "global_step": 618809, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.020406723022461, "global_step": 618810, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0034239292144775, "global_step": 618811, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.8924974203109741, "global_step": 618812, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.037370204925537, "global_step": 618813, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9445149898529053, "global_step": 618814, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0528690814971924, "global_step": 618815, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9619550704956055, "global_step": 618816, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.935987949371338, "global_step": 618817, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0734214782714844, "global_step": 618818, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0499520301818848, "global_step": 618819, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.94576895236969, "global_step": 618820, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9622867107391357, "global_step": 618821, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9483377933502197, "global_step": 618822, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0349340438842773, "global_step": 618823, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0548582077026367, "global_step": 618824, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9879443645477295, "global_step": 618825, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.00838041305542, "global_step": 618826, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9869725704193115, "global_step": 618827, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.031327486038208, "global_step": 618828, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9300140142440796, "global_step": 618829, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.98203444480896, "global_step": 618830, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.102992057800293, "global_step": 618831, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0170679092407227, "global_step": 618832, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.89625084400177, "global_step": 618833, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0562491416931152, "global_step": 618834, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.994218349456787, "global_step": 618835, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0337166786193848, "global_step": 618836, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9277862310409546, "global_step": 618837, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0268664360046387, "global_step": 618838, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9703459739685059, "global_step": 618839, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9680076837539673, "global_step": 618840, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.012576103210449, "global_step": 618841, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0299417972564697, "global_step": 618842, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.042084217071533, "global_step": 618843, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.111950635910034, "global_step": 618844, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0288028717041016, "global_step": 618845, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9966795444488525, "global_step": 618846, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0943892002105713, "global_step": 618847, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9164947271347046, "global_step": 618848, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.1220285892486572, "global_step": 618849, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.073774576187134, "global_step": 618850, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0113255977630615, "global_step": 618851, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0577940940856934, "global_step": 618852, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9238218069076538, "global_step": 618853, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9346426725387573, "global_step": 618854, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.927639126777649, "global_step": 618855, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9752839803695679, "global_step": 618856, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0633974075317383, "global_step": 618857, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.958367109298706, "global_step": 618858, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0310261249542236, "global_step": 618859, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9699095487594604, "global_step": 618860, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0331788063049316, "global_step": 618861, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9774482250213623, "global_step": 618862, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9857921600341797, "global_step": 618863, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9566067457199097, "global_step": 618864, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.017141819000244, "global_step": 618865, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9392420053482056, "global_step": 618866, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0065743923187256, "global_step": 618867, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.115967035293579, "global_step": 618868, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.982109785079956, "global_step": 618869, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.048429489135742, "global_step": 618870, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9577442407608032, "global_step": 618871, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.97038733959198, "global_step": 618872, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.022231340408325, "global_step": 618873, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.049905776977539, "global_step": 618874, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9953114986419678, "global_step": 618875, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0732743740081787, "global_step": 618876, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9395638704299927, "global_step": 618877, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.014249801635742, "global_step": 618878, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0931713581085205, "global_step": 618879, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.127889394760132, "global_step": 618880, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.049793004989624, "global_step": 618881, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0704915523529053, "global_step": 618882, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9757342338562012, "global_step": 618883, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.117208957672119, "global_step": 618884, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0462453365325928, "global_step": 618885, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.954919457435608, "global_step": 618886, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0218639373779297, "global_step": 618887, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.008664846420288, "global_step": 618888, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.069249153137207, "global_step": 618889, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9212671518325806, "global_step": 618890, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9898617267608643, "global_step": 618891, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0417964458465576, "global_step": 618892, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9806793928146362, "global_step": 618893, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.91920006275177, "global_step": 618894, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0374200344085693, "global_step": 618895, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0377821922302246, "global_step": 618896, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9847264289855957, "global_step": 618897, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9769550561904907, "global_step": 618898, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9960790872573853, "global_step": 618899, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9566954374313354, "global_step": 618900, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.057990074157715, "global_step": 618901, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9797065258026123, "global_step": 618902, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9691182374954224, "global_step": 618903, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.911090612411499, "global_step": 618904, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.065185546875, "global_step": 618905, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.038971185684204, "global_step": 618906, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9905130863189697, "global_step": 618907, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.011369466781616, "global_step": 618908, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9929932355880737, "global_step": 618909, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0389339923858643, "global_step": 618910, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9989668130874634, "global_step": 618911, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9895987510681152, "global_step": 618912, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9397037029266357, "global_step": 618913, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.056070566177368, "global_step": 618914, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0275089740753174, "global_step": 618915, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9388738870620728, "global_step": 618916, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.076599597930908, "global_step": 618917, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.1028153896331787, "global_step": 618918, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0272743701934814, "global_step": 618919, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.8754044771194458, "global_step": 618920, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9752182960510254, "global_step": 618921, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0027096271514893, "global_step": 618922, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9958415031433105, "global_step": 618923, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9605178833007812, "global_step": 618924, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0287458896636963, "global_step": 618925, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.041670322418213, "global_step": 618926, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0049262046813965, "global_step": 618927, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.01145076751709, "global_step": 618928, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9910818338394165, "global_step": 618929, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9729597568511963, "global_step": 618930, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0211126804351807, "global_step": 618931, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9966824054718018, "global_step": 618932, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9974215030670166, "global_step": 618933, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.05476975440979, "global_step": 618934, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.055410385131836, "global_step": 618935, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.95624840259552, "global_step": 618936, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9454634189605713, "global_step": 618937, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0202577114105225, "global_step": 618938, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9436250925064087, "global_step": 618939, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0027108192443848, "global_step": 618940, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.01625394821167, "global_step": 618941, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9421863555908203, "global_step": 618942, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.987194299697876, "global_step": 618943, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9945265054702759, "global_step": 618944, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0059590339660645, "global_step": 618945, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9924730062484741, "global_step": 618946, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0391616821289062, "global_step": 618947, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.8711259365081787, "global_step": 618948, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9801708459854126, "global_step": 618949, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9546730518341064, "global_step": 618950, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.016291856765747, "global_step": 618951, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.009131669998169, "global_step": 618952, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.065605878829956, "global_step": 618953, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0056207180023193, "global_step": 618954, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0208096504211426, "global_step": 618955, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9930752515792847, "global_step": 618956, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0305635929107666, "global_step": 618957, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9934206008911133, "global_step": 618958, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9837929010391235, "global_step": 618959, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9968624114990234, "global_step": 618960, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.946666955947876, "global_step": 618961, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.011822462081909, "global_step": 618962, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.983216643333435, "global_step": 618963, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.042249917984009, "global_step": 618964, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.047636032104492, "global_step": 618965, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.056225061416626, "global_step": 618966, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.070343017578125, "global_step": 618967, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9081703424453735, "global_step": 618968, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.921824336051941, "global_step": 618969, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9761667251586914, "global_step": 618970, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9677282571792603, "global_step": 618971, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9971661567687988, "global_step": 618972, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0688390731811523, "global_step": 618973, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9170914888381958, "global_step": 618974, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0215532779693604, "global_step": 618975, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.98888099193573, "global_step": 618976, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0560038089752197, "global_step": 618977, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.013167381286621, "global_step": 618978, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.050806999206543, "global_step": 618979, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.034075975418091, "global_step": 618980, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.974984884262085, "global_step": 618981, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0918960571289062, "global_step": 618982, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.928256630897522, "global_step": 618983, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0172829627990723, "global_step": 618984, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9488226175308228, "global_step": 618985, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.961511254310608, "global_step": 618986, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0189478397369385, "global_step": 618987, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.932856559753418, "global_step": 618988, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9628721475601196, "global_step": 618989, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9987504482269287, "global_step": 618990, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.049600124359131, "global_step": 618991, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.025631904602051, "global_step": 618992, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9958871603012085, "global_step": 618993, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0713088512420654, "global_step": 618994, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.948207139968872, "global_step": 618995, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.1115808486938477, "global_step": 618996, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0792744159698486, "global_step": 618997, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0035414695739746, "global_step": 618998, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9369337558746338, "global_step": 618999, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.030075788497925, "global_step": 619000, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.067545175552368, "global_step": 619001, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.046010732650757, "global_step": 619002, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9704519510269165, "global_step": 619003, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0383167266845703, "global_step": 619004, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.042872667312622, "global_step": 619005, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9045151472091675, "global_step": 619006, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.957663893699646, "global_step": 619007, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9895511865615845, "global_step": 619008, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.053107261657715, "global_step": 619009, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9537934064865112, "global_step": 619010, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9964392185211182, "global_step": 619011, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9826446771621704, "global_step": 619012, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0584967136383057, "global_step": 619013, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0315520763397217, "global_step": 619014, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9854881763458252, "global_step": 619015, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9009886980056763, "global_step": 619016, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.8985852003097534, "global_step": 619017, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.951979637145996, "global_step": 619018, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.91904878616333, "global_step": 619019, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9866714477539062, "global_step": 619020, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9817427396774292, "global_step": 619021, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.002136707305908, "global_step": 619022, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0326998233795166, "global_step": 619023, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.051246404647827, "global_step": 619024, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.019665241241455, "global_step": 619025, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9280030727386475, "global_step": 619026, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9577786922454834, "global_step": 619027, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.082827091217041, "global_step": 619028, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9843873977661133, "global_step": 619029, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0120668411254883, "global_step": 619030, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0907175540924072, "global_step": 619031, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0924017429351807, "global_step": 619032, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9554661512374878, "global_step": 619033, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.017693281173706, "global_step": 619034, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.857119083404541, "global_step": 619035, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.941424012184143, "global_step": 619036, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.950307846069336, "global_step": 619037, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0946121215820312, "global_step": 619038, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0630879402160645, "global_step": 619039, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9433152675628662, "global_step": 619040, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0236518383026123, "global_step": 619041, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.1026206016540527, "global_step": 619042, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9921743869781494, "global_step": 619043, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9722297191619873, "global_step": 619044, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0009634494781494, "global_step": 619045, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.028134822845459, "global_step": 619046, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9975968599319458, "global_step": 619047, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.082143783569336, "global_step": 619048, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0398881435394287, "global_step": 619049, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0592329502105713, "global_step": 619050, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.002068042755127, "global_step": 619051, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0069122314453125, "global_step": 619052, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0245723724365234, "global_step": 619053, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0549561977386475, "global_step": 619054, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.006037950515747, "global_step": 619055, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9945520162582397, "global_step": 619056, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.066843271255493, "global_step": 619057, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0627310276031494, "global_step": 619058, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9925978183746338, "global_step": 619059, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9596301317214966, "global_step": 619060, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0483429431915283, "global_step": 619061, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.984139323234558, "global_step": 619062, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.002685785293579, "global_step": 619063, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9224549531936646, "global_step": 619064, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.010540246963501, "global_step": 619065, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.003398895263672, "global_step": 619066, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9892760515213013, "global_step": 619067, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9961141347885132, "global_step": 619068, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.038923978805542, "global_step": 619069, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.946988582611084, "global_step": 619070, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9833327531814575, "global_step": 619071, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.1720523834228516, "global_step": 619072, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0060341358184814, "global_step": 619073, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.1081836223602295, "global_step": 619074, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9895073175430298, "global_step": 619075, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.8996105194091797, "global_step": 619076, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.044448137283325, "global_step": 619077, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.005368709564209, "global_step": 619078, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0306544303894043, "global_step": 619079, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9627939462661743, "global_step": 619080, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0232908725738525, "global_step": 619081, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9543436765670776, "global_step": 619082, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9972368478775024, "global_step": 619083, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.965598464012146, "global_step": 619084, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9791721105575562, "global_step": 619085, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.926674246788025, "global_step": 619086, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9438581466674805, "global_step": 619087, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0000040531158447, "global_step": 619088, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.050628185272217, "global_step": 619089, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9306467771530151, "global_step": 619090, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.028329849243164, "global_step": 619091, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9588289260864258, "global_step": 619092, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.016822338104248, "global_step": 619093, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9820325374603271, "global_step": 619094, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.012258291244507, "global_step": 619095, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9944466352462769, "global_step": 619096, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0513556003570557, "global_step": 619097, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0286200046539307, "global_step": 619098, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.068223237991333, "global_step": 619099, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9292150735855103, "global_step": 619100, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9883737564086914, "global_step": 619101, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9967800378799438, "global_step": 619102, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.043755054473877, "global_step": 619103, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.049889326095581, "global_step": 619104, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9943548440933228, "global_step": 619105, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9886388778686523, "global_step": 619106, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9310181140899658, "global_step": 619107, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9610114097595215, "global_step": 619108, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0121755599975586, "global_step": 619109, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.070169687271118, "global_step": 619110, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0149946212768555, "global_step": 619111, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9848437309265137, "global_step": 619112, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9922043085098267, "global_step": 619113, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0846757888793945, "global_step": 619114, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0566470623016357, "global_step": 619115, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.014191150665283, "global_step": 619116, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9824308156967163, "global_step": 619117, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0000252723693848, "global_step": 619118, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9670835733413696, "global_step": 619119, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9837381839752197, "global_step": 619120, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0516655445098877, "global_step": 619121, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.003159761428833, "global_step": 619122, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.1009812355041504, "global_step": 619123, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.032724380493164, "global_step": 619124, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0231051445007324, "global_step": 619125, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9436423778533936, "global_step": 619126, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0504400730133057, "global_step": 619127, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0310139656066895, "global_step": 619128, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9683399200439453, "global_step": 619129, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0162758827209473, "global_step": 619130, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9535528421401978, "global_step": 619131, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.044215679168701, "global_step": 619132, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.01564621925354, "global_step": 619133, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0409064292907715, "global_step": 619134, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.053518772125244, "global_step": 619135, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9135822057724, "global_step": 619136, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.115567922592163, "global_step": 619137, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.1248481273651123, "global_step": 619138, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.024585247039795, "global_step": 619139, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.048928737640381, "global_step": 619140, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9527963399887085, "global_step": 619141, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9836829900741577, "global_step": 619142, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.051206588745117, "global_step": 619143, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.019909620285034, "global_step": 619144, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9767160415649414, "global_step": 619145, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.999096393585205, "global_step": 619146, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.009082555770874, "global_step": 619147, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9837887287139893, "global_step": 619148, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.050684928894043, "global_step": 619149, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.006160020828247, "global_step": 619150, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.963411569595337, "global_step": 619151, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0252037048339844, "global_step": 619152, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0616910457611084, "global_step": 619153, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9763307571411133, "global_step": 619154, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9506239891052246, "global_step": 619155, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0841739177703857, "global_step": 619156, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.946197509765625, "global_step": 619157, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0726609230041504, "global_step": 619158, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.918758749961853, "global_step": 619159, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9885072708129883, "global_step": 619160, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0413966178894043, "global_step": 619161, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9831702709197998, "global_step": 619162, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.092961549758911, "global_step": 619163, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9352810382843018, "global_step": 619164, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0360186100006104, "global_step": 619165, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.993095874786377, "global_step": 619166, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.058140277862549, "global_step": 619167, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9403955936431885, "global_step": 619168, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.946670651435852, "global_step": 619169, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.047990560531616, "global_step": 619170, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9691722393035889, "global_step": 619171, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.026726484298706, "global_step": 619172, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0330135822296143, "global_step": 619173, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.000441074371338, "global_step": 619174, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9963200092315674, "global_step": 619175, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0081253051757812, "global_step": 619176, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0064537525177, "global_step": 619177, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.025264024734497, "global_step": 619178, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0526790618896484, "global_step": 619179, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9758739471435547, "global_step": 619180, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0070557594299316, "global_step": 619181, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.06601619720459, "global_step": 619182, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9939346313476562, "global_step": 619183, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9718952178955078, "global_step": 619184, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.017481803894043, "global_step": 619185, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0346615314483643, "global_step": 619186, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0814192295074463, "global_step": 619187, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.158517360687256, "global_step": 619188, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.041534185409546, "global_step": 619189, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0781967639923096, "global_step": 619190, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9936180114746094, "global_step": 619191, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0728185176849365, "global_step": 619192, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.1032307147979736, "global_step": 619193, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9805058240890503, "global_step": 619194, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.08170747756958, "global_step": 619195, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.13485050201416, "global_step": 619196, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.00201416015625, "global_step": 619197, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9901821613311768, "global_step": 619198, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.048707962036133, "global_step": 619199, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9937679767608643, "global_step": 619200, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9938076734542847, "global_step": 619201, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0251355171203613, "global_step": 619202, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0462193489074707, "global_step": 619203, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0262138843536377, "global_step": 619204, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.1294946670532227, "global_step": 619205, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.963153600692749, "global_step": 619206, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.039788007736206, "global_step": 619207, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9841545820236206, "global_step": 619208, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9821237325668335, "global_step": 619209, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.009485960006714, "global_step": 619210, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.946099042892456, "global_step": 619211, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.040036916732788, "global_step": 619212, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9841814041137695, "global_step": 619213, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0065054893493652, "global_step": 619214, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0165467262268066, "global_step": 619215, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9259412288665771, "global_step": 619216, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.037990093231201, "global_step": 619217, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0519747734069824, "global_step": 619218, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.062633991241455, "global_step": 619219, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.97250497341156, "global_step": 619220, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0547702312469482, "global_step": 619221, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9863580465316772, "global_step": 619222, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9767308235168457, "global_step": 619223, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9893999099731445, "global_step": 619224, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.986831545829773, "global_step": 619225, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9918239116668701, "global_step": 619226, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9431980848312378, "global_step": 619227, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0439794063568115, "global_step": 619228, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0489501953125, "global_step": 619229, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9204643964767456, "global_step": 619230, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9938768148422241, "global_step": 619231, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0331082344055176, "global_step": 619232, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0028512477874756, "global_step": 619233, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.075291872024536, "global_step": 619234, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9813659191131592, "global_step": 619235, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.064647912979126, "global_step": 619236, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0363035202026367, "global_step": 619237, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0082569122314453, "global_step": 619238, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9696741104125977, "global_step": 619239, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0200116634368896, "global_step": 619240, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.029024600982666, "global_step": 619241, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0041117668151855, "global_step": 619242, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.070234775543213, "global_step": 619243, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0404562950134277, "global_step": 619244, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0484371185302734, "global_step": 619245, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9213696718215942, "global_step": 619246, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0076820850372314, "global_step": 619247, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0286672115325928, "global_step": 619248, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0264666080474854, "global_step": 619249, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.990350365638733, "global_step": 619250, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0398001670837402, "global_step": 619251, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.98799467086792, "global_step": 619252, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.94677734375, "global_step": 619253, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0697526931762695, "global_step": 619254, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9895262718200684, "global_step": 619255, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9687583446502686, "global_step": 619256, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.010746479034424, "global_step": 619257, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0492444038391113, "global_step": 619258, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.980997920036316, "global_step": 619259, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0553112030029297, "global_step": 619260, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.043534517288208, "global_step": 619261, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0375356674194336, "global_step": 619262, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.1054911613464355, "global_step": 619263, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9991785287857056, "global_step": 619264, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.061851978302002, "global_step": 619265, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9516243934631348, "global_step": 619266, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0098743438720703, "global_step": 619267, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0164928436279297, "global_step": 619268, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9423197507858276, "global_step": 619269, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0072014331817627, "global_step": 619270, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.028249502182007, "global_step": 619271, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9650359153747559, "global_step": 619272, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0237386226654053, "global_step": 619273, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0723628997802734, "global_step": 619274, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.980094313621521, "global_step": 619275, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9665436744689941, "global_step": 619276, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.027806282043457, "global_step": 619277, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9372973442077637, "global_step": 619278, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.128168821334839, "global_step": 619279, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9978913068771362, "global_step": 619280, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.1440773010253906, "global_step": 619281, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.010169744491577, "global_step": 619282, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.058121681213379, "global_step": 619283, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9682559967041016, "global_step": 619284, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0370032787323, "global_step": 619285, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9910365343093872, "global_step": 619286, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9951096773147583, "global_step": 619287, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0101609230041504, "global_step": 619288, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9563630819320679, "global_step": 619289, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9704126119613647, "global_step": 619290, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.018141746520996, "global_step": 619291, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.029360055923462, "global_step": 619292, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0622963905334473, "global_step": 619293, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.8968616724014282, "global_step": 619294, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.034019947052002, "global_step": 619295, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0116424560546875, "global_step": 619296, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9308704137802124, "global_step": 619297, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0438148975372314, "global_step": 619298, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0306947231292725, "global_step": 619299, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.00244140625, "global_step": 619300, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.010986328125, "global_step": 619301, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0364789962768555, "global_step": 619302, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9946670532226562, "global_step": 619303, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.05267596244812, "global_step": 619304, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9597103595733643, "global_step": 619305, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0935027599334717, "global_step": 619306, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.8832175731658936, "global_step": 619307, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.9857627153396606, "global_step": 619308, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.026597738265991, "global_step": 619309, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.985446810722351, "global_step": 619310, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.165050983428955, "global_step": 619311, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.014859676361084, "global_step": 619312, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.028155565261841, "global_step": 619313, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.924785852432251, "global_step": 619314, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.035083055496216, "global_step": 619315, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0997719764709473, "global_step": 619316, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.8904809951782227, "global_step": 619317, "epoch": 988, "lr": 5e-05}
{"train_loss": 1.95436429977417, "global_step": 619318, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0344817638397217, "global_step": 619319, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0131454467773438, "global_step": 619320, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0406832695007324, "global_step": 619321, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.028719902038574, "global_step": 619322, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0039243698120117, "global_step": 619323, "epoch": 988, "lr": 5e-05}
{"train_loss": 2.0034515857696533, "global_step": 619324, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.8862253427505493, "global_step": 619325, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9721876382827759, "global_step": 619326, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.023401975631714, "global_step": 619327, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9664467573165894, "global_step": 619328, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0410571098327637, "global_step": 619329, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9537273645401, "global_step": 619330, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9637677669525146, "global_step": 619331, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9943879842758179, "global_step": 619332, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9660130739212036, "global_step": 619333, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9063869714736938, "global_step": 619334, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.044126510620117, "global_step": 619335, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9649251699447632, "global_step": 619336, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.033947229385376, "global_step": 619337, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9455596208572388, "global_step": 619338, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.94558846950531, "global_step": 619339, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9930882453918457, "global_step": 619340, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0087430477142334, "global_step": 619341, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.955260992050171, "global_step": 619342, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.033161163330078, "global_step": 619343, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0613343715667725, "global_step": 619344, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9819482564926147, "global_step": 619345, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.924544095993042, "global_step": 619346, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.011885643005371, "global_step": 619347, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9738786220550537, "global_step": 619348, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.107787847518921, "global_step": 619349, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.96682608127594, "global_step": 619350, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.988703727722168, "global_step": 619351, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9628021717071533, "global_step": 619352, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9473035335540771, "global_step": 619353, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.8980950117111206, "global_step": 619354, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.117220878601074, "global_step": 619355, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0140926837921143, "global_step": 619356, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0145769119262695, "global_step": 619357, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0298752784729004, "global_step": 619358, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0120511054992676, "global_step": 619359, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9381693601608276, "global_step": 619360, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.007652521133423, "global_step": 619361, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9837599992752075, "global_step": 619362, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.047778844833374, "global_step": 619363, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.041865110397339, "global_step": 619364, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9715688228607178, "global_step": 619365, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9761322736740112, "global_step": 619366, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.002525806427002, "global_step": 619367, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.028249740600586, "global_step": 619368, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0763189792633057, "global_step": 619369, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.052203893661499, "global_step": 619370, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9727216958999634, "global_step": 619371, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0528197288513184, "global_step": 619372, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9174901247024536, "global_step": 619373, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.984766960144043, "global_step": 619374, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9828077554702759, "global_step": 619375, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9441249370574951, "global_step": 619376, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.026759624481201, "global_step": 619377, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.027442455291748, "global_step": 619378, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9911540746688843, "global_step": 619379, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.043482542037964, "global_step": 619380, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.074420213699341, "global_step": 619381, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.968369960784912, "global_step": 619382, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0240542888641357, "global_step": 619383, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.960166335105896, "global_step": 619384, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9517983198165894, "global_step": 619385, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9902132749557495, "global_step": 619386, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0076045989990234, "global_step": 619387, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9864906072616577, "global_step": 619388, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0579686164855957, "global_step": 619389, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0888006687164307, "global_step": 619390, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0605576038360596, "global_step": 619391, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9734561443328857, "global_step": 619392, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9793674945831299, "global_step": 619393, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0009984970092773, "global_step": 619394, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.1179141998291016, "global_step": 619395, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9211516380310059, "global_step": 619396, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.028968334197998, "global_step": 619397, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0322518348693848, "global_step": 619398, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9247790575027466, "global_step": 619399, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.061306953430176, "global_step": 619400, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.000060558319092, "global_step": 619401, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0754640102386475, "global_step": 619402, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.958450198173523, "global_step": 619403, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9885787963867188, "global_step": 619404, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0367558002471924, "global_step": 619405, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0311946868896484, "global_step": 619406, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.998168706893921, "global_step": 619407, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9716696739196777, "global_step": 619408, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9681928157806396, "global_step": 619409, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.995083212852478, "global_step": 619410, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0028371810913086, "global_step": 619411, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.985228180885315, "global_step": 619412, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9721832275390625, "global_step": 619413, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.085184097290039, "global_step": 619414, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9936037063598633, "global_step": 619415, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.939424753189087, "global_step": 619416, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9908740520477295, "global_step": 619417, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0388741493225098, "global_step": 619418, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.1349849700927734, "global_step": 619419, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9730839729309082, "global_step": 619420, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.000751495361328, "global_step": 619421, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.996894121170044, "global_step": 619422, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0198378562927246, "global_step": 619423, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0116355419158936, "global_step": 619424, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0192365646362305, "global_step": 619425, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0017056465148926, "global_step": 619426, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0216829776763916, "global_step": 619427, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9702805280685425, "global_step": 619428, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9102507829666138, "global_step": 619429, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.021249532699585, "global_step": 619430, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9563214778900146, "global_step": 619431, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.882666826248169, "global_step": 619432, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9509220123291016, "global_step": 619433, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0469539165496826, "global_step": 619434, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9942092895507812, "global_step": 619435, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.007007598876953, "global_step": 619436, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.098249912261963, "global_step": 619437, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.006915330886841, "global_step": 619438, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.159006357192993, "global_step": 619439, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.027266025543213, "global_step": 619440, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9935157299041748, "global_step": 619441, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9354777336120605, "global_step": 619442, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0135087966918945, "global_step": 619443, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0068979263305664, "global_step": 619444, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9455385208129883, "global_step": 619445, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.942513108253479, "global_step": 619446, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.028285503387451, "global_step": 619447, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0031726360321045, "global_step": 619448, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0095841884613037, "global_step": 619449, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9985090494155884, "global_step": 619450, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9779084920883179, "global_step": 619451, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.982169270515442, "global_step": 619452, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9650497436523438, "global_step": 619453, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9410167932510376, "global_step": 619454, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.058407783508301, "global_step": 619455, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0169835090637207, "global_step": 619456, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9990705251693726, "global_step": 619457, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9867907762527466, "global_step": 619458, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.999342679977417, "global_step": 619459, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0392770767211914, "global_step": 619460, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.001559257507324, "global_step": 619461, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9486244916915894, "global_step": 619462, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.059300184249878, "global_step": 619463, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9932528734207153, "global_step": 619464, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0126256942749023, "global_step": 619465, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9963761568069458, "global_step": 619466, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9811363220214844, "global_step": 619467, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.034822463989258, "global_step": 619468, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0123143196105957, "global_step": 619469, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9323588609695435, "global_step": 619470, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9635506868362427, "global_step": 619471, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9082598686218262, "global_step": 619472, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9575086832046509, "global_step": 619473, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9616492986679077, "global_step": 619474, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.00925874710083, "global_step": 619475, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9460813999176025, "global_step": 619476, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.982520580291748, "global_step": 619477, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9845985174179077, "global_step": 619478, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0335299968719482, "global_step": 619479, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9384592771530151, "global_step": 619480, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0144848823547363, "global_step": 619481, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9774256944656372, "global_step": 619482, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0327911376953125, "global_step": 619483, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9929229021072388, "global_step": 619484, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9718025922775269, "global_step": 619485, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.002971649169922, "global_step": 619486, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.036438226699829, "global_step": 619487, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9506196975708008, "global_step": 619488, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9433385133743286, "global_step": 619489, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9244693517684937, "global_step": 619490, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9207950830459595, "global_step": 619491, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.983014702796936, "global_step": 619492, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9965076446533203, "global_step": 619493, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9831852912902832, "global_step": 619494, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9617927074432373, "global_step": 619495, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0158870220184326, "global_step": 619496, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0019824504852295, "global_step": 619497, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9010798931121826, "global_step": 619498, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9515185356140137, "global_step": 619499, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0248422622680664, "global_step": 619500, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9512667655944824, "global_step": 619501, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9611735343933105, "global_step": 619502, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.029688596725464, "global_step": 619503, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.933894395828247, "global_step": 619504, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.011423110961914, "global_step": 619505, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0369977951049805, "global_step": 619506, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.011441469192505, "global_step": 619507, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0018656253814697, "global_step": 619508, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9590140581130981, "global_step": 619509, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.992629051208496, "global_step": 619510, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.025148868560791, "global_step": 619511, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9770596027374268, "global_step": 619512, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9308925867080688, "global_step": 619513, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.001011610031128, "global_step": 619514, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.007127285003662, "global_step": 619515, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9750155210494995, "global_step": 619516, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.099720001220703, "global_step": 619517, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.02053165435791, "global_step": 619518, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9449915885925293, "global_step": 619519, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.074805736541748, "global_step": 619520, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0520968437194824, "global_step": 619521, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9154937267303467, "global_step": 619522, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.114443302154541, "global_step": 619523, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.029771089553833, "global_step": 619524, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9674023389816284, "global_step": 619525, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0114588737487793, "global_step": 619526, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.949526309967041, "global_step": 619527, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9678736925125122, "global_step": 619528, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0586254596710205, "global_step": 619529, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0655226707458496, "global_step": 619530, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9160633087158203, "global_step": 619531, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0059516429901123, "global_step": 619532, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0578677654266357, "global_step": 619533, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0643489360809326, "global_step": 619534, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.053661346435547, "global_step": 619535, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.919438362121582, "global_step": 619536, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0472774505615234, "global_step": 619537, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0732674598693848, "global_step": 619538, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.94033682346344, "global_step": 619539, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9114060401916504, "global_step": 619540, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.026684284210205, "global_step": 619541, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9723325967788696, "global_step": 619542, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0168559551239014, "global_step": 619543, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9619553089141846, "global_step": 619544, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0429904460906982, "global_step": 619545, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0140912532806396, "global_step": 619546, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9282221794128418, "global_step": 619547, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0307869911193848, "global_step": 619548, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0095107555389404, "global_step": 619549, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9160298109054565, "global_step": 619550, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.062443971633911, "global_step": 619551, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9679642915725708, "global_step": 619552, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.054614543914795, "global_step": 619553, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.022433280944824, "global_step": 619554, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0469398498535156, "global_step": 619555, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0994279384613037, "global_step": 619556, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.050321102142334, "global_step": 619557, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.040673017501831, "global_step": 619558, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0259013175964355, "global_step": 619559, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.919865369796753, "global_step": 619560, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.015113353729248, "global_step": 619561, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.047369956970215, "global_step": 619562, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0688421726226807, "global_step": 619563, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0265891551971436, "global_step": 619564, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.974290370941162, "global_step": 619565, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9524970054626465, "global_step": 619566, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.975915551185608, "global_step": 619567, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.040437698364258, "global_step": 619568, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.955269455909729, "global_step": 619569, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.961020588874817, "global_step": 619570, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9181314706802368, "global_step": 619571, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9951263666152954, "global_step": 619572, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9366724491119385, "global_step": 619573, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.016848087310791, "global_step": 619574, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.993992567062378, "global_step": 619575, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.057723045349121, "global_step": 619576, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0292317867279053, "global_step": 619577, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.014699697494507, "global_step": 619578, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.979232907295227, "global_step": 619579, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.065943717956543, "global_step": 619580, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9570770263671875, "global_step": 619581, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.022278070449829, "global_step": 619582, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0273211002349854, "global_step": 619583, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9638608694076538, "global_step": 619584, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.03519606590271, "global_step": 619585, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.1136703491210938, "global_step": 619586, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9424580335617065, "global_step": 619587, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9763355255126953, "global_step": 619588, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0625829696655273, "global_step": 619589, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.8810826539993286, "global_step": 619590, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0091750621795654, "global_step": 619591, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.950391173362732, "global_step": 619592, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0046041011810303, "global_step": 619593, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0113742351531982, "global_step": 619594, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9577233791351318, "global_step": 619595, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9913567304611206, "global_step": 619596, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9423978328704834, "global_step": 619597, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0175774097442627, "global_step": 619598, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.001424789428711, "global_step": 619599, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.04400897026062, "global_step": 619600, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9169725179672241, "global_step": 619601, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0805718898773193, "global_step": 619602, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.947222113609314, "global_step": 619603, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9987543821334839, "global_step": 619604, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9810572862625122, "global_step": 619605, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9632130861282349, "global_step": 619606, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.016429901123047, "global_step": 619607, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9857312440872192, "global_step": 619608, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0269386768341064, "global_step": 619609, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9677594900131226, "global_step": 619610, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9702363014221191, "global_step": 619611, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9484789371490479, "global_step": 619612, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.95709228515625, "global_step": 619613, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.041280746459961, "global_step": 619614, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0640246868133545, "global_step": 619615, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.026496171951294, "global_step": 619616, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9801454544067383, "global_step": 619617, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0152158737182617, "global_step": 619618, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0266144275665283, "global_step": 619619, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9080172777175903, "global_step": 619620, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0335917472839355, "global_step": 619621, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0205485820770264, "global_step": 619622, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9876025915145874, "global_step": 619623, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.039491653442383, "global_step": 619624, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0533084869384766, "global_step": 619625, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9799213409423828, "global_step": 619626, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.975069284439087, "global_step": 619627, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0043680667877197, "global_step": 619628, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0394601821899414, "global_step": 619629, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9927279949188232, "global_step": 619630, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9305193424224854, "global_step": 619631, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0026681423187256, "global_step": 619632, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9701834917068481, "global_step": 619633, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.93418550491333, "global_step": 619634, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.982667326927185, "global_step": 619635, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0320699214935303, "global_step": 619636, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0138204097747803, "global_step": 619637, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0059003829956055, "global_step": 619638, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.080841064453125, "global_step": 619639, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9818724393844604, "global_step": 619640, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0195295810699463, "global_step": 619641, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.050549030303955, "global_step": 619642, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9829597473144531, "global_step": 619643, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9449937343597412, "global_step": 619644, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.973538875579834, "global_step": 619645, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0948739051818848, "global_step": 619646, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9829353094100952, "global_step": 619647, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0564932823181152, "global_step": 619648, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9935206174850464, "global_step": 619649, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0076215267181396, "global_step": 619650, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9471631050109863, "global_step": 619651, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9882280826568604, "global_step": 619652, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.032041072845459, "global_step": 619653, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0075833797454834, "global_step": 619654, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9797062873840332, "global_step": 619655, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9554802179336548, "global_step": 619656, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9948137998580933, "global_step": 619657, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0324649810791016, "global_step": 619658, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.017721176147461, "global_step": 619659, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.095808267593384, "global_step": 619660, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9538334608078003, "global_step": 619661, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.04213547706604, "global_step": 619662, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9690719842910767, "global_step": 619663, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9962624311447144, "global_step": 619664, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9814332723617554, "global_step": 619665, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.961043357849121, "global_step": 619666, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9694342613220215, "global_step": 619667, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0249998569488525, "global_step": 619668, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9581726789474487, "global_step": 619669, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.952491283416748, "global_step": 619670, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.010822296142578, "global_step": 619671, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0147910118103027, "global_step": 619672, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9751231670379639, "global_step": 619673, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9855008125305176, "global_step": 619674, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0115914344787598, "global_step": 619675, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0095317363739014, "global_step": 619676, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.13051176071167, "global_step": 619677, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0126893520355225, "global_step": 619678, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.059675931930542, "global_step": 619679, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.991532325744629, "global_step": 619680, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.978442907333374, "global_step": 619681, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0801339149475098, "global_step": 619682, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.992775559425354, "global_step": 619683, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9619688987731934, "global_step": 619684, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9906952381134033, "global_step": 619685, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.103052854537964, "global_step": 619686, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9786440134048462, "global_step": 619687, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.093240976333618, "global_step": 619688, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9235544204711914, "global_step": 619689, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.030977964401245, "global_step": 619690, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.125469207763672, "global_step": 619691, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9818187952041626, "global_step": 619692, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.035184144973755, "global_step": 619693, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.963512659072876, "global_step": 619694, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9116063117980957, "global_step": 619695, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.045461416244507, "global_step": 619696, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.938069224357605, "global_step": 619697, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.021603584289551, "global_step": 619698, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0419673919677734, "global_step": 619699, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.031754970550537, "global_step": 619700, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.077338695526123, "global_step": 619701, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.916460633277893, "global_step": 619702, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.005112409591675, "global_step": 619703, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9110006093978882, "global_step": 619704, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.999893307685852, "global_step": 619705, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.025764226913452, "global_step": 619706, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.079376697540283, "global_step": 619707, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0437779426574707, "global_step": 619708, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.004945993423462, "global_step": 619709, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.892224907875061, "global_step": 619710, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0421230792999268, "global_step": 619711, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.021005392074585, "global_step": 619712, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.004547357559204, "global_step": 619713, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0056490898132324, "global_step": 619714, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9647700786590576, "global_step": 619715, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9670521020889282, "global_step": 619716, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9096823930740356, "global_step": 619717, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9703283309936523, "global_step": 619718, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9769455194473267, "global_step": 619719, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9227222204208374, "global_step": 619720, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0553598403930664, "global_step": 619721, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9864710569381714, "global_step": 619722, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.030158758163452, "global_step": 619723, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.923890233039856, "global_step": 619724, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9629219770431519, "global_step": 619725, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.048856735229492, "global_step": 619726, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0284059047698975, "global_step": 619727, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.079970598220825, "global_step": 619728, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.060663938522339, "global_step": 619729, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0127580165863037, "global_step": 619730, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9362105131149292, "global_step": 619731, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.980838656425476, "global_step": 619732, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.001293182373047, "global_step": 619733, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9712812900543213, "global_step": 619734, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0464534759521484, "global_step": 619735, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9598615169525146, "global_step": 619736, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9663110971450806, "global_step": 619737, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9908729791641235, "global_step": 619738, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9956721067428589, "global_step": 619739, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.041645050048828, "global_step": 619740, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9484082460403442, "global_step": 619741, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9690147638320923, "global_step": 619742, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0456199645996094, "global_step": 619743, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.024327039718628, "global_step": 619744, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.016541004180908, "global_step": 619745, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.021010160446167, "global_step": 619746, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0062122344970703, "global_step": 619747, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9453092813491821, "global_step": 619748, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.082277774810791, "global_step": 619749, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0280256271362305, "global_step": 619750, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9889811277389526, "global_step": 619751, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.86734938621521, "global_step": 619752, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0038442611694336, "global_step": 619753, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0389862060546875, "global_step": 619754, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.970777153968811, "global_step": 619755, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0161778926849365, "global_step": 619756, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9165239334106445, "global_step": 619757, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.050994634628296, "global_step": 619758, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9838356971740723, "global_step": 619759, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0530431270599365, "global_step": 619760, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0012857913970947, "global_step": 619761, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9751733541488647, "global_step": 619762, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9957667589187622, "global_step": 619763, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.044973611831665, "global_step": 619764, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9757797718048096, "global_step": 619765, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0429179668426514, "global_step": 619766, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.023956775665283, "global_step": 619767, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0897347927093506, "global_step": 619768, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.1295108795166016, "global_step": 619769, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.017418384552002, "global_step": 619770, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9953250885009766, "global_step": 619771, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9471784830093384, "global_step": 619772, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0126595497131348, "global_step": 619773, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9961689710617065, "global_step": 619774, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.97171950340271, "global_step": 619775, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9816499948501587, "global_step": 619776, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9260069131851196, "global_step": 619777, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0082030296325684, "global_step": 619778, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.019866704940796, "global_step": 619779, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9977831840515137, "global_step": 619780, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9374548196792603, "global_step": 619781, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.1009202003479004, "global_step": 619782, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.111891508102417, "global_step": 619783, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9985010623931885, "global_step": 619784, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.072237491607666, "global_step": 619785, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0240471363067627, "global_step": 619786, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0175087451934814, "global_step": 619787, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.053581714630127, "global_step": 619788, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.109978437423706, "global_step": 619789, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0269927978515625, "global_step": 619790, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0526907444000244, "global_step": 619791, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9840078353881836, "global_step": 619792, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.975730061531067, "global_step": 619793, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9877564907073975, "global_step": 619794, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.994249701499939, "global_step": 619795, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.992304801940918, "global_step": 619796, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9800920486450195, "global_step": 619797, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0415515899658203, "global_step": 619798, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9927146434783936, "global_step": 619799, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.003586769104004, "global_step": 619800, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9940690994262695, "global_step": 619801, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9250798225402832, "global_step": 619802, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0149316787719727, "global_step": 619803, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.016477108001709, "global_step": 619804, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9927040338516235, "global_step": 619805, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0226566791534424, "global_step": 619806, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.016171932220459, "global_step": 619807, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9581128358840942, "global_step": 619808, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0543694496154785, "global_step": 619809, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9709519147872925, "global_step": 619810, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.018897771835327, "global_step": 619811, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.027634620666504, "global_step": 619812, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0049242973327637, "global_step": 619813, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.013237476348877, "global_step": 619814, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0127696990966797, "global_step": 619815, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.068922758102417, "global_step": 619816, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9040818214416504, "global_step": 619817, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9960520267486572, "global_step": 619818, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9557826519012451, "global_step": 619819, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0124990940093994, "global_step": 619820, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.049406051635742, "global_step": 619821, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.056749105453491, "global_step": 619822, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0296425819396973, "global_step": 619823, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9917423725128174, "global_step": 619824, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9943448305130005, "global_step": 619825, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.1011171340942383, "global_step": 619826, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9671164751052856, "global_step": 619827, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0467543601989746, "global_step": 619828, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9565420150756836, "global_step": 619829, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.021378755569458, "global_step": 619830, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9982852935791016, "global_step": 619831, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9088523387908936, "global_step": 619832, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9800218343734741, "global_step": 619833, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9955974817276, "global_step": 619834, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0677945613861084, "global_step": 619835, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9782729148864746, "global_step": 619836, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.02306866645813, "global_step": 619837, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0340442657470703, "global_step": 619838, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0123403072357178, "global_step": 619839, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.044814348220825, "global_step": 619840, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.8983843326568604, "global_step": 619841, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0731682777404785, "global_step": 619842, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.974212884902954, "global_step": 619843, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9323853254318237, "global_step": 619844, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9974653720855713, "global_step": 619845, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9486316442489624, "global_step": 619846, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0098676681518555, "global_step": 619847, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.036083221435547, "global_step": 619848, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0042691230773926, "global_step": 619849, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9887163639068604, "global_step": 619850, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9575122594833374, "global_step": 619851, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9508056640625, "global_step": 619852, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.002169370651245, "global_step": 619853, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9726792573928833, "global_step": 619854, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.055241584777832, "global_step": 619855, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0363965034484863, "global_step": 619856, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.015733480453491, "global_step": 619857, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.952268362045288, "global_step": 619858, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.043684720993042, "global_step": 619859, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.942756175994873, "global_step": 619860, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.030601978302002, "global_step": 619861, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9170565605163574, "global_step": 619862, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.083505153656006, "global_step": 619863, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9925599098205566, "global_step": 619864, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0328330993652344, "global_step": 619865, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0880727767944336, "global_step": 619866, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.860097050666809, "global_step": 619867, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9455100297927856, "global_step": 619868, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0451200008392334, "global_step": 619869, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.97773015499115, "global_step": 619870, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9964566230773926, "global_step": 619871, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9785369634628296, "global_step": 619872, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9666074514389038, "global_step": 619873, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0675010681152344, "global_step": 619874, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.002897024154663, "global_step": 619875, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9292606115341187, "global_step": 619876, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9382624626159668, "global_step": 619877, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9954619407653809, "global_step": 619878, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.012848377227783, "global_step": 619879, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9531458616256714, "global_step": 619880, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0563974380493164, "global_step": 619881, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.044302225112915, "global_step": 619882, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.013479709625244, "global_step": 619883, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.031416654586792, "global_step": 619884, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.038329601287842, "global_step": 619885, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9637322425842285, "global_step": 619886, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.024468421936035, "global_step": 619887, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0447280406951904, "global_step": 619888, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.962308645248413, "global_step": 619889, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0311596393585205, "global_step": 619890, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.8890925645828247, "global_step": 619891, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0891053676605225, "global_step": 619892, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9915488958358765, "global_step": 619893, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0642290115356445, "global_step": 619894, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.932053565979004, "global_step": 619895, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9390474557876587, "global_step": 619896, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.151024341583252, "global_step": 619897, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9383447170257568, "global_step": 619898, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.952623963356018, "global_step": 619899, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9829530715942383, "global_step": 619900, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0479822158813477, "global_step": 619901, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0804922580718994, "global_step": 619902, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0196306705474854, "global_step": 619903, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9412994384765625, "global_step": 619904, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9663019180297852, "global_step": 619905, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9744359254837036, "global_step": 619906, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9993774890899658, "global_step": 619907, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9546513557434082, "global_step": 619908, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.031052350997925, "global_step": 619909, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.997818946838379, "global_step": 619910, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9980818033218384, "global_step": 619911, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.959165096282959, "global_step": 619912, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9783765077590942, "global_step": 619913, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9863436222076416, "global_step": 619914, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.016771078109741, "global_step": 619915, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0217483043670654, "global_step": 619916, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.030059576034546, "global_step": 619917, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9818578958511353, "global_step": 619918, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0087759494781494, "global_step": 619919, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0107855796813965, "global_step": 619920, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0196266174316406, "global_step": 619921, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.033395528793335, "global_step": 619922, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0273025035858154, "global_step": 619923, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9892698526382446, "global_step": 619924, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.8875759840011597, "global_step": 619925, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9894983768463135, "global_step": 619926, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0733957290649414, "global_step": 619927, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0441040992736816, "global_step": 619928, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0379626750946045, "global_step": 619929, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9699050188064575, "global_step": 619930, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.008937358856201, "global_step": 619931, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.020334482192993, "global_step": 619932, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0106089115142822, "global_step": 619933, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9794552326202393, "global_step": 619934, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9993199110031128, "global_step": 619935, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.010673999786377, "global_step": 619936, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.033496856689453, "global_step": 619937, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0419185161590576, "global_step": 619938, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9636454582214355, "global_step": 619939, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9949711561203003, "global_step": 619940, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9853793382644653, "global_step": 619941, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9712837934494019, "global_step": 619942, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0175728797912598, "global_step": 619943, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.024690866470337, "global_step": 619944, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.988896131515503, "global_step": 619945, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9842572212219238, "global_step": 619946, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0118813514709473, "global_step": 619947, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0137226581573486, "global_step": 619948, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.072200298309326, "global_step": 619949, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0838937759399414, "global_step": 619950, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9045617580413818, "global_step": 619951, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0108730792999268, "global_step": 619952, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0113749504089355, "global_step": 619953, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.024082660675049, "global_step": 619954, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0395467281341553, "global_step": 619955, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9926815032958984, "global_step": 619956, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.859236717224121, "global_step": 619957, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.043734312057495, "global_step": 619958, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.020503520965576, "global_step": 619959, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9168416261672974, "global_step": 619960, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.01534104347229, "global_step": 619961, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9884800910949707, "global_step": 619962, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9299595355987549, "global_step": 619963, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.004817485809326, "global_step": 619964, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0549120903015137, "global_step": 619965, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.008103370666504, "global_step": 619966, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.989820122718811, "global_step": 619967, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0147545337677, "global_step": 619968, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0111544132232666, "global_step": 619969, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.005206346511841, "global_step": 619970, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.028038501739502, "global_step": 619971, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0534396171569824, "global_step": 619972, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0713326930999756, "global_step": 619973, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.965527892112732, "global_step": 619974, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.936889410018921, "global_step": 619975, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.1285831928253174, "global_step": 619976, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9667786359786987, "global_step": 619977, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.043804407119751, "global_step": 619978, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.1518752574920654, "global_step": 619979, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0638587474823, "global_step": 619980, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9248348474502563, "global_step": 619981, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9911701679229736, "global_step": 619982, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9824901819229126, "global_step": 619983, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9350945949554443, "global_step": 619984, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.966684341430664, "global_step": 619985, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0222549438476562, "global_step": 619986, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.014112949371338, "global_step": 619987, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0687243938446045, "global_step": 619988, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0393450260162354, "global_step": 619989, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9389592409133911, "global_step": 619990, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.043884515762329, "global_step": 619991, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.006865978240967, "global_step": 619992, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0719451904296875, "global_step": 619993, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.012460947036743, "global_step": 619994, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.8950364589691162, "global_step": 619995, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0084028244018555, "global_step": 619996, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0055594444274902, "global_step": 619997, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.986034631729126, "global_step": 619998, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0539560317993164, "global_step": 619999, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9407680034637451, "global_step": 620000, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0267817974090576, "global_step": 620001, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9853242635726929, "global_step": 620002, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9507524967193604, "global_step": 620003, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9988497495651245, "global_step": 620004, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.982029676437378, "global_step": 620005, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9989185333251953, "global_step": 620006, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0023632049560547, "global_step": 620007, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9799984693527222, "global_step": 620008, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9950045347213745, "global_step": 620009, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9752737283706665, "global_step": 620010, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.063577175140381, "global_step": 620011, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.056932210922241, "global_step": 620012, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.001117706298828, "global_step": 620013, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.028566360473633, "global_step": 620014, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9335867166519165, "global_step": 620015, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9929977655410767, "global_step": 620016, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9261744022369385, "global_step": 620017, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.033097743988037, "global_step": 620018, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.048349142074585, "global_step": 620019, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9637176990509033, "global_step": 620020, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.001821994781494, "global_step": 620021, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0296120643615723, "global_step": 620022, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.940273404121399, "global_step": 620023, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.095075845718384, "global_step": 620024, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0459794998168945, "global_step": 620025, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9782737493515015, "global_step": 620026, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0760276317596436, "global_step": 620027, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0330498218536377, "global_step": 620028, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9902199506759644, "global_step": 620029, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9146788120269775, "global_step": 620030, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0042824745178223, "global_step": 620031, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9727733135223389, "global_step": 620032, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0408835411071777, "global_step": 620033, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9680237770080566, "global_step": 620034, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0377893447875977, "global_step": 620035, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0498287677764893, "global_step": 620036, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.028202772140503, "global_step": 620037, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9477685689926147, "global_step": 620038, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9930524826049805, "global_step": 620039, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.085096836090088, "global_step": 620040, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0323140621185303, "global_step": 620041, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.953484058380127, "global_step": 620042, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.002290725708008, "global_step": 620043, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0269269943237305, "global_step": 620044, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.051037073135376, "global_step": 620045, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9630497694015503, "global_step": 620046, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0379748344421387, "global_step": 620047, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0008506774902344, "global_step": 620048, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0755245685577393, "global_step": 620049, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9962158203125, "global_step": 620050, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0245134830474854, "global_step": 620051, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.045844793319702, "global_step": 620052, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.05642032623291, "global_step": 620053, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.043147563934326, "global_step": 620054, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0582637786865234, "global_step": 620055, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0180091857910156, "global_step": 620056, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0490713119506836, "global_step": 620057, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9668291807174683, "global_step": 620058, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.018733263015747, "global_step": 620059, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0263497829437256, "global_step": 620060, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0266406536102295, "global_step": 620061, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0193216800689697, "global_step": 620062, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0217394828796387, "global_step": 620063, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0223636627197266, "global_step": 620064, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.000316619873047, "global_step": 620065, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.063084125518799, "global_step": 620066, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9859330654144287, "global_step": 620067, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.01355242729187, "global_step": 620068, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0258729457855225, "global_step": 620069, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0156044960021973, "global_step": 620070, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0409302711486816, "global_step": 620071, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9381203651428223, "global_step": 620072, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9901008605957031, "global_step": 620073, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.021993398666382, "global_step": 620074, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0567867755889893, "global_step": 620075, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9757875204086304, "global_step": 620076, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0600943565368652, "global_step": 620077, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9778406620025635, "global_step": 620078, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9271600246429443, "global_step": 620079, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0282673835754395, "global_step": 620080, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9926278591156006, "global_step": 620081, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.030214786529541, "global_step": 620082, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9630275964736938, "global_step": 620083, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9811514616012573, "global_step": 620084, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0051307678222656, "global_step": 620085, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9696719646453857, "global_step": 620086, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.082214593887329, "global_step": 620087, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0033938884735107, "global_step": 620088, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9805705547332764, "global_step": 620089, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0725672245025635, "global_step": 620090, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9810842275619507, "global_step": 620091, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0292906761169434, "global_step": 620092, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.991869330406189, "global_step": 620093, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0419435501098633, "global_step": 620094, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.026578187942505, "global_step": 620095, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9477604627609253, "global_step": 620096, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0335171222686768, "global_step": 620097, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.994033694267273, "global_step": 620098, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0947372913360596, "global_step": 620099, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.019747734069824, "global_step": 620100, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.950866937637329, "global_step": 620101, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0800516605377197, "global_step": 620102, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.030975341796875, "global_step": 620103, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0505809783935547, "global_step": 620104, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.989424705505371, "global_step": 620105, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.038893699645996, "global_step": 620106, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.017000436782837, "global_step": 620107, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.081791639328003, "global_step": 620108, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9318010807037354, "global_step": 620109, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0359694957733154, "global_step": 620110, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.017172336578369, "global_step": 620111, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0318994522094727, "global_step": 620112, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.044041395187378, "global_step": 620113, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0275278091430664, "global_step": 620114, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.00881028175354, "global_step": 620115, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.076704502105713, "global_step": 620116, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9861817359924316, "global_step": 620117, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.03644061088562, "global_step": 620118, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.047830820083618, "global_step": 620119, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.048534870147705, "global_step": 620120, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0063068866729736, "global_step": 620121, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9971061944961548, "global_step": 620122, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9414176940917969, "global_step": 620123, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.994929313659668, "global_step": 620124, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.071699619293213, "global_step": 620125, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.1220765113830566, "global_step": 620126, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0555646419525146, "global_step": 620127, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0747861862182617, "global_step": 620128, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0671069622039795, "global_step": 620129, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.048032760620117, "global_step": 620130, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9927177429199219, "global_step": 620131, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9733283519744873, "global_step": 620132, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9680347442626953, "global_step": 620133, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9812372922897339, "global_step": 620134, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.081878185272217, "global_step": 620135, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9637694358825684, "global_step": 620136, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9920909404754639, "global_step": 620137, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.963513731956482, "global_step": 620138, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9574788808822632, "global_step": 620139, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.014272928237915, "global_step": 620140, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.023728132247925, "global_step": 620141, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.030531883239746, "global_step": 620142, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9816408157348633, "global_step": 620143, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.005507469177246, "global_step": 620144, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.014024257659912, "global_step": 620145, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9979256391525269, "global_step": 620146, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9422423839569092, "global_step": 620147, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.013467788696289, "global_step": 620148, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.928106665611267, "global_step": 620149, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0181784629821777, "global_step": 620150, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9745813608169556, "global_step": 620151, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0061452388763428, "global_step": 620152, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0052497386932373, "global_step": 620153, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.003958225250244, "global_step": 620154, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9697978496551514, "global_step": 620155, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.1382923126220703, "global_step": 620156, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.014942169189453, "global_step": 620157, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0412938594818115, "global_step": 620158, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.073634624481201, "global_step": 620159, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.1000053882598877, "global_step": 620160, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.044840097427368, "global_step": 620161, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.05540132522583, "global_step": 620162, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9979302883148193, "global_step": 620163, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.996436595916748, "global_step": 620164, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9952137470245361, "global_step": 620165, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.045508623123169, "global_step": 620166, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.083043336868286, "global_step": 620167, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0041391849517822, "global_step": 620168, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.03690242767334, "global_step": 620169, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.961639404296875, "global_step": 620170, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9743092060089111, "global_step": 620171, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.009148597717285, "global_step": 620172, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9823577404022217, "global_step": 620173, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9562240839004517, "global_step": 620174, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9334230422973633, "global_step": 620175, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.081024169921875, "global_step": 620176, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.030510663986206, "global_step": 620177, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0510387420654297, "global_step": 620178, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0192747116088867, "global_step": 620179, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9656879901885986, "global_step": 620180, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.976811408996582, "global_step": 620181, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0012576580047607, "global_step": 620182, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9623807668685913, "global_step": 620183, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.025204658508301, "global_step": 620184, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9826877117156982, "global_step": 620185, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.977332353591919, "global_step": 620186, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.024434804916382, "global_step": 620187, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.960567593574524, "global_step": 620188, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9990094900131226, "global_step": 620189, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9780277013778687, "global_step": 620190, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0214571952819824, "global_step": 620191, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0055992603302, "global_step": 620192, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9843125343322754, "global_step": 620193, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9752024412155151, "global_step": 620194, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.964147925376892, "global_step": 620195, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0415759086608887, "global_step": 620196, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9604839086532593, "global_step": 620197, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9746133089065552, "global_step": 620198, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9433099031448364, "global_step": 620199, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9985508918762207, "global_step": 620200, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0515122413635254, "global_step": 620201, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0091991424560547, "global_step": 620202, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.03438663482666, "global_step": 620203, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0259344577789307, "global_step": 620204, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0755040645599365, "global_step": 620205, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9896091222763062, "global_step": 620206, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.1068942546844482, "global_step": 620207, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.023747205734253, "global_step": 620208, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.011004686355591, "global_step": 620209, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9778532981872559, "global_step": 620210, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0138161182403564, "global_step": 620211, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.064925193786621, "global_step": 620212, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0300307273864746, "global_step": 620213, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0060577392578125, "global_step": 620214, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9658408164978027, "global_step": 620215, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0661396980285645, "global_step": 620216, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.003445625305176, "global_step": 620217, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.981323003768921, "global_step": 620218, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.057124137878418, "global_step": 620219, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9881566762924194, "global_step": 620220, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0014967918395996, "global_step": 620221, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.984972357749939, "global_step": 620222, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0039405822753906, "global_step": 620223, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9981704950332642, "global_step": 620224, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0049140453338623, "global_step": 620225, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.1148736476898193, "global_step": 620226, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0014233589172363, "global_step": 620227, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9886664152145386, "global_step": 620228, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0170397758483887, "global_step": 620229, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.001873254776001, "global_step": 620230, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9825105667114258, "global_step": 620231, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.059154987335205, "global_step": 620232, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9586654901504517, "global_step": 620233, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0003092288970947, "global_step": 620234, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0162947177886963, "global_step": 620235, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.071492910385132, "global_step": 620236, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.042512893676758, "global_step": 620237, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9652764797210693, "global_step": 620238, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.045726776123047, "global_step": 620239, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.985971450805664, "global_step": 620240, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9561187028884888, "global_step": 620241, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0469603538513184, "global_step": 620242, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.953614592552185, "global_step": 620243, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.036986827850342, "global_step": 620244, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.969886064529419, "global_step": 620245, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.01263427734375, "global_step": 620246, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.021721363067627, "global_step": 620247, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9867907762527466, "global_step": 620248, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.073679208755493, "global_step": 620249, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9660592079162598, "global_step": 620250, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.078584671020508, "global_step": 620251, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.077167510986328, "global_step": 620252, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9902541637420654, "global_step": 620253, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9761368036270142, "global_step": 620254, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0911800861358643, "global_step": 620255, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9588168859481812, "global_step": 620256, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.984366536140442, "global_step": 620257, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0193114280700684, "global_step": 620258, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0156121253967285, "global_step": 620259, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0365419387817383, "global_step": 620260, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0626637935638428, "global_step": 620261, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.1067850589752197, "global_step": 620262, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0279364585876465, "global_step": 620263, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0059521198272705, "global_step": 620264, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9829579591751099, "global_step": 620265, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9854366779327393, "global_step": 620266, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0243282318115234, "global_step": 620267, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.979806661605835, "global_step": 620268, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.065927267074585, "global_step": 620269, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0723142623901367, "global_step": 620270, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.08174729347229, "global_step": 620271, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9664342403411865, "global_step": 620272, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9715582132339478, "global_step": 620273, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9974086284637451, "global_step": 620274, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.01519775390625, "global_step": 620275, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.011897087097168, "global_step": 620276, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0083744525909424, "global_step": 620277, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9767663478851318, "global_step": 620278, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0471127033233643, "global_step": 620279, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.939369559288025, "global_step": 620280, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0665762424468994, "global_step": 620281, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9843320846557617, "global_step": 620282, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.1145246028900146, "global_step": 620283, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9986861944198608, "global_step": 620284, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9986897706985474, "global_step": 620285, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9662160873413086, "global_step": 620286, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.062431812286377, "global_step": 620287, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9726065397262573, "global_step": 620288, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.00909423828125, "global_step": 620289, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0431644916534424, "global_step": 620290, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.0484352111816406, "global_step": 620291, "epoch": 989, "lr": 5e-05}
{"train_loss": 2.004464864730835, "global_step": 620292, "epoch": 989, "lr": 5e-05}
{"train_loss": 1.9658915996551514, "global_step": 620293, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0400712490081787, "global_step": 620294, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0535905361175537, "global_step": 620295, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9725611209869385, "global_step": 620296, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9788708686828613, "global_step": 620297, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0755133628845215, "global_step": 620298, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.016935110092163, "global_step": 620299, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9807010889053345, "global_step": 620300, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.044497013092041, "global_step": 620301, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9526793956756592, "global_step": 620302, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.947481632232666, "global_step": 620303, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9767441749572754, "global_step": 620304, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9083068370819092, "global_step": 620305, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0349955558776855, "global_step": 620306, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.120953321456909, "global_step": 620307, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0315511226654053, "global_step": 620308, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9836477041244507, "global_step": 620309, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.965135097503662, "global_step": 620310, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0265414714813232, "global_step": 620311, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9210102558135986, "global_step": 620312, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9764524698257446, "global_step": 620313, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.916438341140747, "global_step": 620314, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.087942600250244, "global_step": 620315, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9410709142684937, "global_step": 620316, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9006742238998413, "global_step": 620317, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9308483600616455, "global_step": 620318, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9649138450622559, "global_step": 620319, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.026015520095825, "global_step": 620320, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0333709716796875, "global_step": 620321, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9612563848495483, "global_step": 620322, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0096495151519775, "global_step": 620323, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9645800590515137, "global_step": 620324, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9487292766571045, "global_step": 620325, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9610588550567627, "global_step": 620326, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.013760805130005, "global_step": 620327, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9599665403366089, "global_step": 620328, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0064449310302734, "global_step": 620329, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.951904058456421, "global_step": 620330, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0001745223999023, "global_step": 620331, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.056741714477539, "global_step": 620332, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.079730272293091, "global_step": 620333, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0213754177093506, "global_step": 620334, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.969614028930664, "global_step": 620335, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.031897783279419, "global_step": 620336, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.054983139038086, "global_step": 620337, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0041332244873047, "global_step": 620338, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0285940170288086, "global_step": 620339, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.035430908203125, "global_step": 620340, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0632805824279785, "global_step": 620341, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9751484394073486, "global_step": 620342, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9344396591186523, "global_step": 620343, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8789100646972656, "global_step": 620344, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9544750452041626, "global_step": 620345, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9806666374206543, "global_step": 620346, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9793334007263184, "global_step": 620347, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0677850246429443, "global_step": 620348, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.016301155090332, "global_step": 620349, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9995193481445312, "global_step": 620350, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9698375463485718, "global_step": 620351, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.025120735168457, "global_step": 620352, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.919722557067871, "global_step": 620353, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9670149087905884, "global_step": 620354, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9740195274353027, "global_step": 620355, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9340602159500122, "global_step": 620356, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0863661766052246, "global_step": 620357, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8698307275772095, "global_step": 620358, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9697532653808594, "global_step": 620359, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9165040254592896, "global_step": 620360, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.068939447402954, "global_step": 620361, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.007128953933716, "global_step": 620362, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.007704496383667, "global_step": 620363, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9638863801956177, "global_step": 620364, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.986657977104187, "global_step": 620365, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1327972412109375, "global_step": 620366, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.938355565071106, "global_step": 620367, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.023458957672119, "global_step": 620368, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9998687505722046, "global_step": 620369, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.00575852394104, "global_step": 620370, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.90720534324646, "global_step": 620371, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.888656735420227, "global_step": 620372, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9833139181137085, "global_step": 620373, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0554261207580566, "global_step": 620374, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9650905132293701, "global_step": 620375, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.981605052947998, "global_step": 620376, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.989975929260254, "global_step": 620377, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9734646081924438, "global_step": 620378, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0706684589385986, "global_step": 620379, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.963104009628296, "global_step": 620380, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.003526210784912, "global_step": 620381, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9079203605651855, "global_step": 620382, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.026435375213623, "global_step": 620383, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9971035718917847, "global_step": 620384, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.070427894592285, "global_step": 620385, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0673720836639404, "global_step": 620386, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9563438892364502, "global_step": 620387, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0200035572052, "global_step": 620388, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9358043670654297, "global_step": 620389, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9895403385162354, "global_step": 620390, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.077519416809082, "global_step": 620391, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.030221700668335, "global_step": 620392, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.956470012664795, "global_step": 620393, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9777884483337402, "global_step": 620394, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0447285175323486, "global_step": 620395, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.007826805114746, "global_step": 620396, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9963041543960571, "global_step": 620397, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.026019811630249, "global_step": 620398, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0729897022247314, "global_step": 620399, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9529190063476562, "global_step": 620400, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0712709426879883, "global_step": 620401, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0252492427825928, "global_step": 620402, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9543780088424683, "global_step": 620403, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9508845806121826, "global_step": 620404, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9877700805664062, "global_step": 620405, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.033799648284912, "global_step": 620406, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.010026216506958, "global_step": 620407, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9884555339813232, "global_step": 620408, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.008868455886841, "global_step": 620409, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9837387800216675, "global_step": 620410, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.004655122756958, "global_step": 620411, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9767183065414429, "global_step": 620412, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0296804904937744, "global_step": 620413, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.047706127166748, "global_step": 620414, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.049504041671753, "global_step": 620415, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.011575698852539, "global_step": 620416, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.018012523651123, "global_step": 620417, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.030212163925171, "global_step": 620418, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9802913665771484, "global_step": 620419, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0796666145324707, "global_step": 620420, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9704270362854004, "global_step": 620421, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1003215312957764, "global_step": 620422, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0780768394470215, "global_step": 620423, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0778567790985107, "global_step": 620424, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9259775876998901, "global_step": 620425, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.958587646484375, "global_step": 620426, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.994682788848877, "global_step": 620427, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.98746657371521, "global_step": 620428, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.031785488128662, "global_step": 620429, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0533607006073, "global_step": 620430, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0893938541412354, "global_step": 620431, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9400988817214966, "global_step": 620432, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0326623916625977, "global_step": 620433, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.017252206802368, "global_step": 620434, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8768281936645508, "global_step": 620435, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0501976013183594, "global_step": 620436, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9731754064559937, "global_step": 620437, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.017714500427246, "global_step": 620438, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9444737434387207, "global_step": 620439, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9668411016464233, "global_step": 620440, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.05558705329895, "global_step": 620441, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.144634962081909, "global_step": 620442, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0152344703674316, "global_step": 620443, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9156473875045776, "global_step": 620444, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.041839599609375, "global_step": 620445, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9619777202606201, "global_step": 620446, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9863070249557495, "global_step": 620447, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.956605076789856, "global_step": 620448, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0273916721343994, "global_step": 620449, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.012468099594116, "global_step": 620450, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.992688536643982, "global_step": 620451, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.044740915298462, "global_step": 620452, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.060795783996582, "global_step": 620453, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0246548652648926, "global_step": 620454, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0266942977905273, "global_step": 620455, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0132100582122803, "global_step": 620456, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.998665452003479, "global_step": 620457, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0417397022247314, "global_step": 620458, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.075376510620117, "global_step": 620459, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0577378273010254, "global_step": 620460, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.94756281375885, "global_step": 620461, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9959769248962402, "global_step": 620462, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0116000175476074, "global_step": 620463, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9534072875976562, "global_step": 620464, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.039642572402954, "global_step": 620465, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.000746726989746, "global_step": 620466, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9614102840423584, "global_step": 620467, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9968615770339966, "global_step": 620468, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9377844333648682, "global_step": 620469, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.986587405204773, "global_step": 620470, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.017134666442871, "global_step": 620471, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9347867965698242, "global_step": 620472, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0309066772460938, "global_step": 620473, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9405879974365234, "global_step": 620474, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.026010513305664, "global_step": 620475, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9864884614944458, "global_step": 620476, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0041158199310303, "global_step": 620477, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0296361446380615, "global_step": 620478, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9352527856826782, "global_step": 620479, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.981759786605835, "global_step": 620480, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0029850006103516, "global_step": 620481, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0756022930145264, "global_step": 620482, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9842828512191772, "global_step": 620483, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9263755083084106, "global_step": 620484, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.032252073287964, "global_step": 620485, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.079413890838623, "global_step": 620486, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.093306064605713, "global_step": 620487, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.13751220703125, "global_step": 620488, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9441429376602173, "global_step": 620489, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0254690647125244, "global_step": 620490, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0540552139282227, "global_step": 620491, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9689881801605225, "global_step": 620492, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.051656723022461, "global_step": 620493, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9723478555679321, "global_step": 620494, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0705504417419434, "global_step": 620495, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1366918087005615, "global_step": 620496, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0270755290985107, "global_step": 620497, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9267362356185913, "global_step": 620498, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9716366529464722, "global_step": 620499, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9579041004180908, "global_step": 620500, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9884263277053833, "global_step": 620501, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.040395736694336, "global_step": 620502, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.02484393119812, "global_step": 620503, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0014359951019287, "global_step": 620504, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9782683849334717, "global_step": 620505, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.984129786491394, "global_step": 620506, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0421252250671387, "global_step": 620507, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.048095464706421, "global_step": 620508, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9833186864852905, "global_step": 620509, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9614585638046265, "global_step": 620510, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9825656414031982, "global_step": 620511, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9908864498138428, "global_step": 620512, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0525317192077637, "global_step": 620513, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9346791505813599, "global_step": 620514, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.957566499710083, "global_step": 620515, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.000598430633545, "global_step": 620516, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0392184257507324, "global_step": 620517, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0599188804626465, "global_step": 620518, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9408704042434692, "global_step": 620519, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0150527954101562, "global_step": 620520, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9591491222381592, "global_step": 620521, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.025285005569458, "global_step": 620522, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9559028148651123, "global_step": 620523, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.097154140472412, "global_step": 620524, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9337575435638428, "global_step": 620525, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0123229026794434, "global_step": 620526, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8969322443008423, "global_step": 620527, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.025829553604126, "global_step": 620528, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9735298156738281, "global_step": 620529, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0736396312713623, "global_step": 620530, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.055168867111206, "global_step": 620531, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9388115406036377, "global_step": 620532, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.005335569381714, "global_step": 620533, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.002697229385376, "global_step": 620534, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0573971271514893, "global_step": 620535, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0181033611297607, "global_step": 620536, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9951601028442383, "global_step": 620537, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0882070064544678, "global_step": 620538, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.932668924331665, "global_step": 620539, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.039207935333252, "global_step": 620540, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0265660285949707, "global_step": 620541, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9951496124267578, "global_step": 620542, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0373713970184326, "global_step": 620543, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9864630699157715, "global_step": 620544, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9883817434310913, "global_step": 620545, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.976690649986267, "global_step": 620546, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0541672706604004, "global_step": 620547, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.019052743911743, "global_step": 620548, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9247158765792847, "global_step": 620549, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0805673599243164, "global_step": 620550, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.941449522972107, "global_step": 620551, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.991591453552246, "global_step": 620552, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.007960796356201, "global_step": 620553, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0813498497009277, "global_step": 620554, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9810370206832886, "global_step": 620555, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9518142938613892, "global_step": 620556, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0495195388793945, "global_step": 620557, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0194263458251953, "global_step": 620558, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9511535167694092, "global_step": 620559, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.990201473236084, "global_step": 620560, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.029484748840332, "global_step": 620561, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0761117935180664, "global_step": 620562, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.931809663772583, "global_step": 620563, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.063302516937256, "global_step": 620564, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9754326343536377, "global_step": 620565, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.007248878479004, "global_step": 620566, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9307150840759277, "global_step": 620567, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.076990842819214, "global_step": 620568, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9814821481704712, "global_step": 620569, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1131412982940674, "global_step": 620570, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9307690858840942, "global_step": 620571, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.01944637298584, "global_step": 620572, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0264694690704346, "global_step": 620573, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0520968437194824, "global_step": 620574, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9974775314331055, "global_step": 620575, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.963725209236145, "global_step": 620576, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.025981903076172, "global_step": 620577, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0914969444274902, "global_step": 620578, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.048997163772583, "global_step": 620579, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.042198896408081, "global_step": 620580, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.079219102859497, "global_step": 620581, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0526890754699707, "global_step": 620582, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9341039657592773, "global_step": 620583, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9584269523620605, "global_step": 620584, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0046911239624023, "global_step": 620585, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9125257730484009, "global_step": 620586, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.104024887084961, "global_step": 620587, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0310614109039307, "global_step": 620588, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1117122173309326, "global_step": 620589, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.983998417854309, "global_step": 620590, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9358487129211426, "global_step": 620591, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0270655155181885, "global_step": 620592, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.015606641769409, "global_step": 620593, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0334362983703613, "global_step": 620594, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9971975088119507, "global_step": 620595, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.99502432346344, "global_step": 620596, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.963494062423706, "global_step": 620597, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.12618350982666, "global_step": 620598, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0443954467773438, "global_step": 620599, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.001833200454712, "global_step": 620600, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9701318740844727, "global_step": 620601, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.93792724609375, "global_step": 620602, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.982954740524292, "global_step": 620603, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0738940238952637, "global_step": 620604, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.013369083404541, "global_step": 620605, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0244698524475098, "global_step": 620606, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0252532958984375, "global_step": 620607, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.927000641822815, "global_step": 620608, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0979745388031006, "global_step": 620609, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.984980583190918, "global_step": 620610, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0294692516326904, "global_step": 620611, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.046018123626709, "global_step": 620612, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.94619882106781, "global_step": 620613, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.969840407371521, "global_step": 620614, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9579648971557617, "global_step": 620615, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9611071348190308, "global_step": 620616, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.974442958831787, "global_step": 620617, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9911243915557861, "global_step": 620618, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.007176160812378, "global_step": 620619, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.044008493423462, "global_step": 620620, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.036834716796875, "global_step": 620621, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0477499961853027, "global_step": 620622, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9766509532928467, "global_step": 620623, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0088260173797607, "global_step": 620624, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9976310729980469, "global_step": 620625, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.999794602394104, "global_step": 620626, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.023575782775879, "global_step": 620627, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9495912790298462, "global_step": 620628, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9321118593215942, "global_step": 620629, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9289275407791138, "global_step": 620630, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.029935359954834, "global_step": 620631, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9121618270874023, "global_step": 620632, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9993064403533936, "global_step": 620633, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.954637050628662, "global_step": 620634, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0030360221862793, "global_step": 620635, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0278847217559814, "global_step": 620636, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.892501711845398, "global_step": 620637, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.030839681625366, "global_step": 620638, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0018930435180664, "global_step": 620639, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9720885753631592, "global_step": 620640, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9347773790359497, "global_step": 620641, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8971459865570068, "global_step": 620642, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9858648777008057, "global_step": 620643, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.953836441040039, "global_step": 620644, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9994804859161377, "global_step": 620645, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9973353147506714, "global_step": 620646, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9915565252304077, "global_step": 620647, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0787839889526367, "global_step": 620648, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.003249406814575, "global_step": 620649, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.923616886138916, "global_step": 620650, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0473268032073975, "global_step": 620651, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9858685731887817, "global_step": 620652, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0128867626190186, "global_step": 620653, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0611789226531982, "global_step": 620654, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9107410907745361, "global_step": 620655, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0002589225769043, "global_step": 620656, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0306687355041504, "global_step": 620657, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.026717185974121, "global_step": 620658, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9216797351837158, "global_step": 620659, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0157630443573, "global_step": 620660, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0030267238616943, "global_step": 620661, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9862993955612183, "global_step": 620662, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9640001058578491, "global_step": 620663, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.936989188194275, "global_step": 620664, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0058250427246094, "global_step": 620665, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.004138946533203, "global_step": 620666, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.032597064971924, "global_step": 620667, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0288920402526855, "global_step": 620668, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.019892930984497, "global_step": 620669, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9752531051635742, "global_step": 620670, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0649921894073486, "global_step": 620671, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0404298305511475, "global_step": 620672, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0006260871887207, "global_step": 620673, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9840904474258423, "global_step": 620674, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0149664878845215, "global_step": 620675, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9666268825531006, "global_step": 620676, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0503292083740234, "global_step": 620677, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9599800109863281, "global_step": 620678, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0002806186676025, "global_step": 620679, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.059354543685913, "global_step": 620680, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0383856296539307, "global_step": 620681, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0145070552825928, "global_step": 620682, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0265450477600098, "global_step": 620683, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0348424911499023, "global_step": 620684, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.978906512260437, "global_step": 620685, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.045914649963379, "global_step": 620686, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0083720684051514, "global_step": 620687, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0158581733703613, "global_step": 620688, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9915201663970947, "global_step": 620689, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0097718238830566, "global_step": 620690, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9617977142333984, "global_step": 620691, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.06270694732666, "global_step": 620692, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1206700801849365, "global_step": 620693, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.041682004928589, "global_step": 620694, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9278236627578735, "global_step": 620695, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9764338731765747, "global_step": 620696, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.974545955657959, "global_step": 620697, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.934178352355957, "global_step": 620698, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.088068962097168, "global_step": 620699, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9151920080184937, "global_step": 620700, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0288567543029785, "global_step": 620701, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9928910732269287, "global_step": 620702, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0190298557281494, "global_step": 620703, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9661109447479248, "global_step": 620704, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.969212532043457, "global_step": 620705, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0563557147979736, "global_step": 620706, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.057377338409424, "global_step": 620707, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.030985116958618, "global_step": 620708, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9373098611831665, "global_step": 620709, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.980623483657837, "global_step": 620710, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.014482021331787, "global_step": 620711, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.071841239929199, "global_step": 620712, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9995230436325073, "global_step": 620713, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0427756309509277, "global_step": 620714, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.062633752822876, "global_step": 620715, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9543050527572632, "global_step": 620716, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.026158094406128, "global_step": 620717, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9875019788742065, "global_step": 620718, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0221896171569824, "global_step": 620719, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.985794186592102, "global_step": 620720, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0827348232269287, "global_step": 620721, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9763789176940918, "global_step": 620722, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.045413017272949, "global_step": 620723, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9501811265945435, "global_step": 620724, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.011523485183716, "global_step": 620725, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9894816875457764, "global_step": 620726, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1255102157592773, "global_step": 620727, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.058790683746338, "global_step": 620728, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9227005243301392, "global_step": 620729, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9927645921707153, "global_step": 620730, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.931810736656189, "global_step": 620731, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.037095069885254, "global_step": 620732, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.013002395629883, "global_step": 620733, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.956589698791504, "global_step": 620734, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9903013706207275, "global_step": 620735, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.010511636734009, "global_step": 620736, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.982229471206665, "global_step": 620737, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9836211204528809, "global_step": 620738, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9811663627624512, "global_step": 620739, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.091261148452759, "global_step": 620740, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.03647780418396, "global_step": 620741, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0128657817840576, "global_step": 620742, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0214929580688477, "global_step": 620743, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0217978954315186, "global_step": 620744, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.021740674972534, "global_step": 620745, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9242748022079468, "global_step": 620746, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9685330390930176, "global_step": 620747, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0179460048675537, "global_step": 620748, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9660474061965942, "global_step": 620749, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.036062240600586, "global_step": 620750, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9899942874908447, "global_step": 620751, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.03849458694458, "global_step": 620752, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9375925064086914, "global_step": 620753, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0844502449035645, "global_step": 620754, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9666354656219482, "global_step": 620755, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9981029033660889, "global_step": 620756, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0653812885284424, "global_step": 620757, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0207011699676514, "global_step": 620758, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.010336399078369, "global_step": 620759, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0139591693878174, "global_step": 620760, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.021409273147583, "global_step": 620761, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0870847702026367, "global_step": 620762, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9860087633132935, "global_step": 620763, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.019963264465332, "global_step": 620764, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.033350944519043, "global_step": 620765, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0122971534729004, "global_step": 620766, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0983901023864746, "global_step": 620767, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0517120361328125, "global_step": 620768, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9188261032104492, "global_step": 620769, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9898422956466675, "global_step": 620770, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0392706394195557, "global_step": 620771, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9566787481307983, "global_step": 620772, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.977277398109436, "global_step": 620773, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9692689180374146, "global_step": 620774, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.003847360610962, "global_step": 620775, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.992346167564392, "global_step": 620776, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.98422110080719, "global_step": 620777, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0140743255615234, "global_step": 620778, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9731953144073486, "global_step": 620779, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0241732597351074, "global_step": 620780, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0453011989593506, "global_step": 620781, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9344465732574463, "global_step": 620782, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9224108457565308, "global_step": 620783, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.011051893234253, "global_step": 620784, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.971284031867981, "global_step": 620785, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0225987434387207, "global_step": 620786, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9830538034439087, "global_step": 620787, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9927903413772583, "global_step": 620788, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.014813184738159, "global_step": 620789, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0839884281158447, "global_step": 620790, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9532109498977661, "global_step": 620791, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9457374811172485, "global_step": 620792, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0136711597442627, "global_step": 620793, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.005728006362915, "global_step": 620794, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.137648344039917, "global_step": 620795, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.977893352508545, "global_step": 620796, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9961451292037964, "global_step": 620797, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.009978771209717, "global_step": 620798, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0290000438690186, "global_step": 620799, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.027005195617676, "global_step": 620800, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.002708673477173, "global_step": 620801, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0532047748565674, "global_step": 620802, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9490411281585693, "global_step": 620803, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9909719228744507, "global_step": 620804, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9638235569000244, "global_step": 620805, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9107859134674072, "global_step": 620806, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9353450536727905, "global_step": 620807, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.91650390625, "global_step": 620808, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.080054521560669, "global_step": 620809, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9529353380203247, "global_step": 620810, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0189874172210693, "global_step": 620811, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9694411754608154, "global_step": 620812, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9954711198806763, "global_step": 620813, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0070645809173584, "global_step": 620814, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0371322631835938, "global_step": 620815, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1194379329681396, "global_step": 620816, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.057795524597168, "global_step": 620817, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0109684467315674, "global_step": 620818, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0715701580047607, "global_step": 620819, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.024775743484497, "global_step": 620820, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.03664231300354, "global_step": 620821, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0165212154388428, "global_step": 620822, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.024364471435547, "global_step": 620823, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0193798542022705, "global_step": 620824, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9946568012237549, "global_step": 620825, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0743861198425293, "global_step": 620826, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0108253955841064, "global_step": 620827, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9640161991119385, "global_step": 620828, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0228333473205566, "global_step": 620829, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.99994957447052, "global_step": 620830, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.046868085861206, "global_step": 620831, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9442403316497803, "global_step": 620832, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9869120121002197, "global_step": 620833, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.044660806655884, "global_step": 620834, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.995617389678955, "global_step": 620835, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0152690410614014, "global_step": 620836, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9627214670181274, "global_step": 620837, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9969778060913086, "global_step": 620838, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0651748180389404, "global_step": 620839, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9450719356536865, "global_step": 620840, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.009655475616455, "global_step": 620841, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9772989749908447, "global_step": 620842, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0225279331207275, "global_step": 620843, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.122945547103882, "global_step": 620844, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.029426336288452, "global_step": 620845, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.00606369972229, "global_step": 620846, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9562708139419556, "global_step": 620847, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.11816143989563, "global_step": 620848, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9931526184082031, "global_step": 620849, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9842374324798584, "global_step": 620850, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0451819896698, "global_step": 620851, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9997230768203735, "global_step": 620852, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9991289377212524, "global_step": 620853, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.084634304046631, "global_step": 620854, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0021731853485107, "global_step": 620855, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9852805137634277, "global_step": 620856, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.071105718612671, "global_step": 620857, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0279929637908936, "global_step": 620858, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9734448194503784, "global_step": 620859, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9556571245193481, "global_step": 620860, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9860416650772095, "global_step": 620861, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0329668521881104, "global_step": 620862, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.070216655731201, "global_step": 620863, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9979928731918335, "global_step": 620864, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9971935749053955, "global_step": 620865, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.036121129989624, "global_step": 620866, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9705842733383179, "global_step": 620867, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.038848400115967, "global_step": 620868, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9990556240081787, "global_step": 620869, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0267117023468018, "global_step": 620870, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.994642972946167, "global_step": 620871, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.999968409538269, "global_step": 620872, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0560109615325928, "global_step": 620873, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0250210762023926, "global_step": 620874, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.952652931213379, "global_step": 620875, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0392673015594482, "global_step": 620876, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.009016752243042, "global_step": 620877, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9884672164916992, "global_step": 620878, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9789268970489502, "global_step": 620879, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0885708332061768, "global_step": 620880, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9665757417678833, "global_step": 620881, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9264246225357056, "global_step": 620882, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.001354932785034, "global_step": 620883, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.051661491394043, "global_step": 620884, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9631654024124146, "global_step": 620885, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0285487174987793, "global_step": 620886, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0019681453704834, "global_step": 620887, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9641319513320923, "global_step": 620888, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.110724449157715, "global_step": 620889, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9955018758773804, "global_step": 620890, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.016289234161377, "global_step": 620891, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.02500319480896, "global_step": 620892, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.063257932662964, "global_step": 620893, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9973959922790527, "global_step": 620894, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9493224620819092, "global_step": 620895, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.018400192260742, "global_step": 620896, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9993733167648315, "global_step": 620897, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9884076118469238, "global_step": 620898, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.017949342727661, "global_step": 620899, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0662734508514404, "global_step": 620900, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9438326358795166, "global_step": 620901, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9124150276184082, "global_step": 620902, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0241453647613525, "global_step": 620903, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9735809564590454, "global_step": 620904, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9935636520385742, "global_step": 620905, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9672528505325317, "global_step": 620906, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.983989953994751, "global_step": 620907, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9432193040847778, "global_step": 620908, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.065598964691162, "global_step": 620909, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0661516189575195, "global_step": 620910, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0215060710906982, "global_step": 620911, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0065715312957764, "global_step": 620912, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.007192611694336, "global_step": 620913, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.024188995361328, "global_step": 620914, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.989916205406189, "global_step": 620915, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9460867643356323, "global_step": 620916, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9692864418029785, "global_step": 620917, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9530001878738403, "global_step": 620918, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9524469375610352, "global_step": 620919, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0587048530578613, "global_step": 620920, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0375397205352783, "global_step": 620921, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0372390747070312, "global_step": 620922, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.067915678024292, "global_step": 620923, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.007808208465576, "global_step": 620924, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0392892360687256, "global_step": 620925, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1063709259033203, "global_step": 620926, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.027932643890381, "global_step": 620927, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1411917209625244, "global_step": 620928, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0293538570404053, "global_step": 620929, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0576279163360596, "global_step": 620930, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9776663780212402, "global_step": 620931, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.028808116912842, "global_step": 620932, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9848995208740234, "global_step": 620933, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0926592350006104, "global_step": 620934, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.049790859222412, "global_step": 620935, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9803993701934814, "global_step": 620936, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9518641233444214, "global_step": 620937, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9387177228927612, "global_step": 620938, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.023946523666382, "global_step": 620939, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.016746997833252, "global_step": 620940, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.079263687133789, "global_step": 620941, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.030722141265869, "global_step": 620942, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9771844148635864, "global_step": 620943, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9793857336044312, "global_step": 620944, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9555535316467285, "global_step": 620945, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9933464527130127, "global_step": 620946, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9908490180969238, "global_step": 620947, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9630463123321533, "global_step": 620948, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9977110624313354, "global_step": 620949, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0377957820892334, "global_step": 620950, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9891761541366577, "global_step": 620951, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.046461820602417, "global_step": 620952, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.013648271560669, "global_step": 620953, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0310440063476562, "global_step": 620954, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0439555644989014, "global_step": 620955, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.07146954536438, "global_step": 620956, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.997090458869934, "global_step": 620957, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0035252571105957, "global_step": 620958, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0330286026000977, "global_step": 620959, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.07841420173645, "global_step": 620960, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.039930820465088, "global_step": 620961, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9907963275909424, "global_step": 620962, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0717179775238037, "global_step": 620963, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.016758441925049, "global_step": 620964, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.987052321434021, "global_step": 620965, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1018807888031006, "global_step": 620966, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0560877323150635, "global_step": 620967, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.931030511856079, "global_step": 620968, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.023313522338867, "global_step": 620969, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0644924640655518, "global_step": 620970, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9958114624023438, "global_step": 620971, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9946472644805908, "global_step": 620972, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.007810115814209, "global_step": 620973, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0606682300567627, "global_step": 620974, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9541343450546265, "global_step": 620975, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9350600242614746, "global_step": 620976, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0738468170166016, "global_step": 620977, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0673117637634277, "global_step": 620978, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0588855743408203, "global_step": 620979, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.033013105392456, "global_step": 620980, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9453953504562378, "global_step": 620981, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0324201583862305, "global_step": 620982, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9610310792922974, "global_step": 620983, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1123781204223633, "global_step": 620984, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0279054641723633, "global_step": 620985, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.020681381225586, "global_step": 620986, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.934576153755188, "global_step": 620987, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8905057907104492, "global_step": 620988, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9621726274490356, "global_step": 620989, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0629818439483643, "global_step": 620990, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9850103855133057, "global_step": 620991, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0448250770568848, "global_step": 620992, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0574536323547363, "global_step": 620993, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9028136730194092, "global_step": 620994, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.047224760055542, "global_step": 620995, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.079177141189575, "global_step": 620996, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.003187417984009, "global_step": 620997, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.101633071899414, "global_step": 620998, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0422513484954834, "global_step": 620999, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.060241460800171, "global_step": 621000, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.004845380783081, "global_step": 621001, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0258195400238037, "global_step": 621002, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.094573974609375, "global_step": 621003, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9865663051605225, "global_step": 621004, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0628557205200195, "global_step": 621005, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.09922194480896, "global_step": 621006, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0207791328430176, "global_step": 621007, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9943679571151733, "global_step": 621008, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9236561059951782, "global_step": 621009, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0361216068267822, "global_step": 621010, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.057812213897705, "global_step": 621011, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0067522525787354, "global_step": 621012, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9392576217651367, "global_step": 621013, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0534331798553467, "global_step": 621014, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.034705400466919, "global_step": 621015, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.944665551185608, "global_step": 621016, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.027665853500366, "global_step": 621017, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0780234336853027, "global_step": 621018, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0303664207458496, "global_step": 621019, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9843487739562988, "global_step": 621020, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9913008213043213, "global_step": 621021, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.07151198387146, "global_step": 621022, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0745813846588135, "global_step": 621023, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.998094916343689, "global_step": 621024, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0820181369781494, "global_step": 621025, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.968708872795105, "global_step": 621026, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9629228115081787, "global_step": 621027, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9916430711746216, "global_step": 621028, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0520408153533936, "global_step": 621029, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.009915351867676, "global_step": 621030, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9575494527816772, "global_step": 621031, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.025930881500244, "global_step": 621032, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0025413036346436, "global_step": 621033, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.054964065551758, "global_step": 621034, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0015575885772705, "global_step": 621035, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0738682746887207, "global_step": 621036, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1273486614227295, "global_step": 621037, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.003519058227539, "global_step": 621038, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9183499813079834, "global_step": 621039, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.964215874671936, "global_step": 621040, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9133151769638062, "global_step": 621041, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9756351709365845, "global_step": 621042, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9647148847579956, "global_step": 621043, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9809409379959106, "global_step": 621044, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.106239080429077, "global_step": 621045, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0184736251831055, "global_step": 621046, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.988222360610962, "global_step": 621047, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9673503637313843, "global_step": 621048, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0439789295196533, "global_step": 621049, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.040329933166504, "global_step": 621050, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0291080474853516, "global_step": 621051, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.973846673965454, "global_step": 621052, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.982444405555725, "global_step": 621053, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.985095500946045, "global_step": 621054, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.018056631088257, "global_step": 621055, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.914724588394165, "global_step": 621056, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9886656999588013, "global_step": 621057, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0696542263031006, "global_step": 621058, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9088979959487915, "global_step": 621059, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.915066123008728, "global_step": 621060, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9929968118667603, "global_step": 621061, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0316362380981445, "global_step": 621062, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9904558658599854, "global_step": 621063, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9835710525512695, "global_step": 621064, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9980493783950806, "global_step": 621065, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0222957134246826, "global_step": 621066, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.975010871887207, "global_step": 621067, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9779956340789795, "global_step": 621068, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9641854763031006, "global_step": 621069, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9629266262054443, "global_step": 621070, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.041595697402954, "global_step": 621071, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.036473274230957, "global_step": 621072, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.946516513824463, "global_step": 621073, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0378925800323486, "global_step": 621074, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9528223276138306, "global_step": 621075, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.987200379371643, "global_step": 621076, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9891942739486694, "global_step": 621077, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9705804586410522, "global_step": 621078, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9391592741012573, "global_step": 621079, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9993840456008911, "global_step": 621080, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9686717987060547, "global_step": 621081, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9471330642700195, "global_step": 621082, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9942717552185059, "global_step": 621083, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9837456941604614, "global_step": 621084, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9356971979141235, "global_step": 621085, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9348517656326294, "global_step": 621086, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1293532848358154, "global_step": 621087, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9743214845657349, "global_step": 621088, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.074228286743164, "global_step": 621089, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0053632259368896, "global_step": 621090, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9745588302612305, "global_step": 621091, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9706588983535767, "global_step": 621092, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9907667636871338, "global_step": 621093, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9878795146942139, "global_step": 621094, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0613765716552734, "global_step": 621095, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0189099311828613, "global_step": 621096, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0445337295532227, "global_step": 621097, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9903314113616943, "global_step": 621098, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9940682649612427, "global_step": 621099, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0025413036346436, "global_step": 621100, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9630687236785889, "global_step": 621101, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9792646169662476, "global_step": 621102, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9859782457351685, "global_step": 621103, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9694100618362427, "global_step": 621104, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.976854920387268, "global_step": 621105, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.026110887527466, "global_step": 621106, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9531413316726685, "global_step": 621107, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0136518478393555, "global_step": 621108, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9826154708862305, "global_step": 621109, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.993196964263916, "global_step": 621110, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.907952904701233, "global_step": 621111, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0763344764709473, "global_step": 621112, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9903066158294678, "global_step": 621113, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0581953525543213, "global_step": 621114, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9767502546310425, "global_step": 621115, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.016256332397461, "global_step": 621116, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9208046197891235, "global_step": 621117, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0256662368774414, "global_step": 621118, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.970538854598999, "global_step": 621119, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0503857135772705, "global_step": 621120, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0599405765533447, "global_step": 621121, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9811294078826904, "global_step": 621122, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0135293006896973, "global_step": 621123, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.968576431274414, "global_step": 621124, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9348224401474, "global_step": 621125, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.952599287033081, "global_step": 621126, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0320241451263428, "global_step": 621127, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9530689716339111, "global_step": 621128, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0345938205718994, "global_step": 621129, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9706528186798096, "global_step": 621130, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9717674255371094, "global_step": 621131, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.13959002494812, "global_step": 621132, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.972103476524353, "global_step": 621133, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.113633155822754, "global_step": 621134, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9966598749160767, "global_step": 621135, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.009262800216675, "global_step": 621136, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.027383327484131, "global_step": 621137, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.950385332107544, "global_step": 621138, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1016669273376465, "global_step": 621139, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9726474285125732, "global_step": 621140, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0116565227508545, "global_step": 621141, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0453648567199707, "global_step": 621142, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9342714548110962, "global_step": 621143, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9152683019638062, "global_step": 621144, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.056148052215576, "global_step": 621145, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8922559022903442, "global_step": 621146, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0050344467163086, "global_step": 621147, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9917254447937012, "global_step": 621148, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9386590719223022, "global_step": 621149, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0268561840057373, "global_step": 621150, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.042926073074341, "global_step": 621151, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9772216081619263, "global_step": 621152, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.960297703742981, "global_step": 621153, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.037475347518921, "global_step": 621154, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.92112135887146, "global_step": 621155, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.084425210952759, "global_step": 621156, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1294302940368652, "global_step": 621157, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0700137615203857, "global_step": 621158, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.144752025604248, "global_step": 621159, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.006948947906494, "global_step": 621160, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9923920631408691, "global_step": 621161, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.013664722442627, "global_step": 621162, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9966620206832886, "global_step": 621163, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.926997423171997, "global_step": 621164, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9974101781845093, "global_step": 621165, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.064704418182373, "global_step": 621166, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0215320587158203, "global_step": 621167, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.031534433364868, "global_step": 621168, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9919357299804688, "global_step": 621169, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.049656867980957, "global_step": 621170, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0247297286987305, "global_step": 621171, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.078185796737671, "global_step": 621172, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9710772037506104, "global_step": 621173, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.046898126602173, "global_step": 621174, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9993925094604492, "global_step": 621175, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1187994480133057, "global_step": 621176, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9921694993972778, "global_step": 621177, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0639634132385254, "global_step": 621178, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0597376823425293, "global_step": 621179, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9493904113769531, "global_step": 621180, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0778896808624268, "global_step": 621181, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0696537494659424, "global_step": 621182, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.090291738510132, "global_step": 621183, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0186431407928467, "global_step": 621184, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9914007186889648, "global_step": 621185, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9778848886489868, "global_step": 621186, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.998023509979248, "global_step": 621187, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0637927055358887, "global_step": 621188, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9859936237335205, "global_step": 621189, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9373835325241089, "global_step": 621190, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0483572483062744, "global_step": 621191, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9984482526779175, "global_step": 621192, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9908215999603271, "global_step": 621193, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9662861824035645, "global_step": 621194, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9277057647705078, "global_step": 621195, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.055206537246704, "global_step": 621196, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9802720546722412, "global_step": 621197, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.023010730743408, "global_step": 621198, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0047738552093506, "global_step": 621199, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0167665481567383, "global_step": 621200, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0168142318725586, "global_step": 621201, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.09749174118042, "global_step": 621202, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9878442287445068, "global_step": 621203, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0595312118530273, "global_step": 621204, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0437729358673096, "global_step": 621205, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9757190942764282, "global_step": 621206, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.975427508354187, "global_step": 621207, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.086658000946045, "global_step": 621208, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0010290145874023, "global_step": 621209, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9144448041915894, "global_step": 621210, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.046701192855835, "global_step": 621211, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.083117961883545, "global_step": 621212, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.944136619567871, "global_step": 621213, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0024516582489014, "global_step": 621214, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.007922410964966, "global_step": 621215, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.011143922805786, "global_step": 621216, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0172362327575684, "global_step": 621217, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1141908168792725, "global_step": 621218, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.058865547180176, "global_step": 621219, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9378021955490112, "global_step": 621220, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.012101411819458, "global_step": 621221, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0111658573150635, "global_step": 621222, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.027503252029419, "global_step": 621223, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.948061227798462, "global_step": 621224, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0483336448669434, "global_step": 621225, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.069460868835449, "global_step": 621226, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.955618977546692, "global_step": 621227, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1389355659484863, "global_step": 621228, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.044036865234375, "global_step": 621229, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9460132122039795, "global_step": 621230, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.998855471611023, "global_step": 621231, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.005368709564209, "global_step": 621232, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9810630083084106, "global_step": 621233, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9764000177383423, "global_step": 621234, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9668269157409668, "global_step": 621235, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0752744674682617, "global_step": 621236, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9654817581176758, "global_step": 621237, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.985778570175171, "global_step": 621238, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.01257586479187, "global_step": 621239, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.029789924621582, "global_step": 621240, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0152151584625244, "global_step": 621241, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9477366209030151, "global_step": 621242, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.028137683868408, "global_step": 621243, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1052932739257812, "global_step": 621244, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0362648963928223, "global_step": 621245, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9937264919281006, "global_step": 621246, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.001021146774292, "global_step": 621247, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0506317615509033, "global_step": 621248, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9549325704574585, "global_step": 621249, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0016732215881348, "global_step": 621250, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0132670402526855, "global_step": 621251, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9886682033538818, "global_step": 621252, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0592124462127686, "global_step": 621253, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.029052257537842, "global_step": 621254, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8945250511169434, "global_step": 621255, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9493114948272705, "global_step": 621256, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9603809118270874, "global_step": 621257, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0801594257354736, "global_step": 621258, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9655485153198242, "global_step": 621259, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.017411708831787, "global_step": 621260, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.006110668182373, "global_step": 621261, "epoch": 990, "lr": 5e-05, "val_loss": 5.815815448760986, "test_reconst_mse": 0.07303875684738159}
{"train_loss": 1.9916887283325195, "global_step": 621262, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.019731283187866, "global_step": 621263, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9910463094711304, "global_step": 621264, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9997957944869995, "global_step": 621265, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.022301197052002, "global_step": 621266, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1043763160705566, "global_step": 621267, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9841519594192505, "global_step": 621268, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9846142530441284, "global_step": 621269, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9830635786056519, "global_step": 621270, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9902626276016235, "global_step": 621271, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.029041290283203, "global_step": 621272, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9599858522415161, "global_step": 621273, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9657783508300781, "global_step": 621274, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0056071281433105, "global_step": 621275, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.995270848274231, "global_step": 621276, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9672281742095947, "global_step": 621277, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9905441999435425, "global_step": 621278, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9918190240859985, "global_step": 621279, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0533905029296875, "global_step": 621280, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9242398738861084, "global_step": 621281, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9129730463027954, "global_step": 621282, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0388996601104736, "global_step": 621283, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0798017978668213, "global_step": 621284, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9241622686386108, "global_step": 621285, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9925042390823364, "global_step": 621286, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9063615798950195, "global_step": 621287, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.028762102127075, "global_step": 621288, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.033449649810791, "global_step": 621289, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0569682121276855, "global_step": 621290, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9710992574691772, "global_step": 621291, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9387153387069702, "global_step": 621292, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9886127710342407, "global_step": 621293, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9368377923965454, "global_step": 621294, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0817058086395264, "global_step": 621295, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.024418592453003, "global_step": 621296, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.080232620239258, "global_step": 621297, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.024350643157959, "global_step": 621298, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.982250690460205, "global_step": 621299, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.003610372543335, "global_step": 621300, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0016705989837646, "global_step": 621301, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.019378900527954, "global_step": 621302, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9659693241119385, "global_step": 621303, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9705344438552856, "global_step": 621304, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.995391607284546, "global_step": 621305, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.047550678253174, "global_step": 621306, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0083773136138916, "global_step": 621307, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.00183367729187, "global_step": 621308, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0650274753570557, "global_step": 621309, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0555055141448975, "global_step": 621310, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9923810958862305, "global_step": 621311, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9584732055664062, "global_step": 621312, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9895163774490356, "global_step": 621313, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.053701877593994, "global_step": 621314, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0107977390289307, "global_step": 621315, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.985551118850708, "global_step": 621316, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0411810874938965, "global_step": 621317, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9874255657196045, "global_step": 621318, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9221467971801758, "global_step": 621319, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0515995025634766, "global_step": 621320, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.026031494140625, "global_step": 621321, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9759992361068726, "global_step": 621322, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9973609447479248, "global_step": 621323, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9766229391098022, "global_step": 621324, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9575645923614502, "global_step": 621325, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9723531007766724, "global_step": 621326, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0352771282196045, "global_step": 621327, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9661586284637451, "global_step": 621328, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0106148719787598, "global_step": 621329, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9900870323181152, "global_step": 621330, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9268264770507812, "global_step": 621331, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.051652669906616, "global_step": 621332, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9849923849105835, "global_step": 621333, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1012156009674072, "global_step": 621334, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9545338153839111, "global_step": 621335, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0099658966064453, "global_step": 621336, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0482962131500244, "global_step": 621337, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.965844988822937, "global_step": 621338, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9773954153060913, "global_step": 621339, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.024174213409424, "global_step": 621340, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.007567882537842, "global_step": 621341, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.926102638244629, "global_step": 621342, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.960425853729248, "global_step": 621343, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0740857124328613, "global_step": 621344, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.015138626098633, "global_step": 621345, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9124033451080322, "global_step": 621346, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9210368394851685, "global_step": 621347, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9924741983413696, "global_step": 621348, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.087371349334717, "global_step": 621349, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.003514528274536, "global_step": 621350, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9383089542388916, "global_step": 621351, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0228898525238037, "global_step": 621352, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0644192695617676, "global_step": 621353, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.996767282485962, "global_step": 621354, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9463402032852173, "global_step": 621355, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.98490309715271, "global_step": 621356, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0369746685028076, "global_step": 621357, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0580098628997803, "global_step": 621358, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9382760524749756, "global_step": 621359, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9050074815750122, "global_step": 621360, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9770209789276123, "global_step": 621361, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9852986335754395, "global_step": 621362, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0183403491973877, "global_step": 621363, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.902913212776184, "global_step": 621364, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0105016231536865, "global_step": 621365, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9808775186538696, "global_step": 621366, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.054647207260132, "global_step": 621367, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0474300384521484, "global_step": 621368, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0163912773132324, "global_step": 621369, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.009605884552002, "global_step": 621370, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0320160388946533, "global_step": 621371, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0571744441986084, "global_step": 621372, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.047959327697754, "global_step": 621373, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.055267095565796, "global_step": 621374, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9662106037139893, "global_step": 621375, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.917084813117981, "global_step": 621376, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9821799993515015, "global_step": 621377, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0601911544799805, "global_step": 621378, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9429880380630493, "global_step": 621379, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9794288873672485, "global_step": 621380, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.048720359802246, "global_step": 621381, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9152216911315918, "global_step": 621382, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9911874532699585, "global_step": 621383, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9895001649856567, "global_step": 621384, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.012979507446289, "global_step": 621385, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9278349876403809, "global_step": 621386, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.016050100326538, "global_step": 621387, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.013932704925537, "global_step": 621388, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9681423902511597, "global_step": 621389, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.011448621749878, "global_step": 621390, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9772560596466064, "global_step": 621391, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0012800693511963, "global_step": 621392, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.988301157951355, "global_step": 621393, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0259687900543213, "global_step": 621394, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.077519178390503, "global_step": 621395, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9798529148101807, "global_step": 621396, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9231486320495605, "global_step": 621397, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.038344144821167, "global_step": 621398, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9392646551132202, "global_step": 621399, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9687258005142212, "global_step": 621400, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0979764461517334, "global_step": 621401, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0301361083984375, "global_step": 621402, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0448930263519287, "global_step": 621403, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9479862451553345, "global_step": 621404, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.032806873321533, "global_step": 621405, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.058479070663452, "global_step": 621406, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0125889778137207, "global_step": 621407, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.986829400062561, "global_step": 621408, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0029947757720947, "global_step": 621409, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9768980741500854, "global_step": 621410, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9571337699890137, "global_step": 621411, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.996146559715271, "global_step": 621412, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8900948762893677, "global_step": 621413, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0286333560943604, "global_step": 621414, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.942899465560913, "global_step": 621415, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9345206022262573, "global_step": 621416, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9878618717193604, "global_step": 621417, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9652740955352783, "global_step": 621418, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0741772651672363, "global_step": 621419, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9772614240646362, "global_step": 621420, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0617949962615967, "global_step": 621421, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9686222076416016, "global_step": 621422, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9974607229232788, "global_step": 621423, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9485392570495605, "global_step": 621424, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9495506286621094, "global_step": 621425, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9309190511703491, "global_step": 621426, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9601006507873535, "global_step": 621427, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9642388820648193, "global_step": 621428, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9999715089797974, "global_step": 621429, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9954068660736084, "global_step": 621430, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.046273946762085, "global_step": 621431, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9990503787994385, "global_step": 621432, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.980981707572937, "global_step": 621433, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1040685176849365, "global_step": 621434, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.982684850692749, "global_step": 621435, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0207972526550293, "global_step": 621436, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.035087823867798, "global_step": 621437, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.075928211212158, "global_step": 621438, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.008815050125122, "global_step": 621439, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0002152919769287, "global_step": 621440, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.150057077407837, "global_step": 621441, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0493392944335938, "global_step": 621442, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9476886987686157, "global_step": 621443, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.058845043182373, "global_step": 621444, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0801851749420166, "global_step": 621445, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0305094718933105, "global_step": 621446, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.044778823852539, "global_step": 621447, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9008662700653076, "global_step": 621448, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0107202529907227, "global_step": 621449, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0396063327789307, "global_step": 621450, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.965747356414795, "global_step": 621451, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9903755187988281, "global_step": 621452, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9977790117263794, "global_step": 621453, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9475622177124023, "global_step": 621454, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.020770788192749, "global_step": 621455, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0512545108795166, "global_step": 621456, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.011136293411255, "global_step": 621457, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9231044054031372, "global_step": 621458, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.015646457672119, "global_step": 621459, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9343154430389404, "global_step": 621460, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.041318416595459, "global_step": 621461, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0038273334503174, "global_step": 621462, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9440009593963623, "global_step": 621463, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9609863758087158, "global_step": 621464, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9758694171905518, "global_step": 621465, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.006359100341797, "global_step": 621466, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9625444412231445, "global_step": 621467, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.023874282836914, "global_step": 621468, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9409584999084473, "global_step": 621469, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9540191888809204, "global_step": 621470, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9591097831726074, "global_step": 621471, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0781564712524414, "global_step": 621472, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0045650005340576, "global_step": 621473, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9658076763153076, "global_step": 621474, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0351219177246094, "global_step": 621475, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0981175899505615, "global_step": 621476, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0311663150787354, "global_step": 621477, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.957202434539795, "global_step": 621478, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0015511512756348, "global_step": 621479, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9662346839904785, "global_step": 621480, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.01450777053833, "global_step": 621481, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0086638927459717, "global_step": 621482, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9400643110275269, "global_step": 621483, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9387571811676025, "global_step": 621484, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0643012523651123, "global_step": 621485, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9771900177001953, "global_step": 621486, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0620779991149902, "global_step": 621487, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9797276258468628, "global_step": 621488, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8862334489822388, "global_step": 621489, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0808005332946777, "global_step": 621490, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.970676064491272, "global_step": 621491, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9440028667449951, "global_step": 621492, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9921495914459229, "global_step": 621493, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0939383506774902, "global_step": 621494, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.062281370162964, "global_step": 621495, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9044675827026367, "global_step": 621496, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0103628635406494, "global_step": 621497, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0191335678100586, "global_step": 621498, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.110053300857544, "global_step": 621499, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.018733263015747, "global_step": 621500, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9427978992462158, "global_step": 621501, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9842071533203125, "global_step": 621502, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.977733850479126, "global_step": 621503, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.015394687652588, "global_step": 621504, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0979702472686768, "global_step": 621505, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9545954465866089, "global_step": 621506, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.016843795776367, "global_step": 621507, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0675411224365234, "global_step": 621508, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.099341869354248, "global_step": 621509, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9637142419815063, "global_step": 621510, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9897944927215576, "global_step": 621511, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.001084089279175, "global_step": 621512, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9595798254013062, "global_step": 621513, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0848441123962402, "global_step": 621514, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0184030532836914, "global_step": 621515, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9625357389450073, "global_step": 621516, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9485586881637573, "global_step": 621517, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.056135654449463, "global_step": 621518, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9922609329223633, "global_step": 621519, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.035477638244629, "global_step": 621520, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.044431686401367, "global_step": 621521, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9847190380096436, "global_step": 621522, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8992570638656616, "global_step": 621523, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.035332441329956, "global_step": 621524, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0595524311065674, "global_step": 621525, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0155205726623535, "global_step": 621526, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9826054573059082, "global_step": 621527, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.125678062438965, "global_step": 621528, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0403971672058105, "global_step": 621529, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0101022720336914, "global_step": 621530, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.982347011566162, "global_step": 621531, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9183701276779175, "global_step": 621532, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8573726415634155, "global_step": 621533, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9925353527069092, "global_step": 621534, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9913175106048584, "global_step": 621535, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9754860401153564, "global_step": 621536, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.045780897140503, "global_step": 621537, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.975845217704773, "global_step": 621538, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9573423862457275, "global_step": 621539, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9757312536239624, "global_step": 621540, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9704837799072266, "global_step": 621541, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9981393814086914, "global_step": 621542, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0295116901397705, "global_step": 621543, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9707229137420654, "global_step": 621544, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9895710945129395, "global_step": 621545, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.019266128540039, "global_step": 621546, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.970531940460205, "global_step": 621547, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9709219932556152, "global_step": 621548, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9732933044433594, "global_step": 621549, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.972570776939392, "global_step": 621550, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.035989761352539, "global_step": 621551, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0695135593414307, "global_step": 621552, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0090105533599854, "global_step": 621553, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0155084133148193, "global_step": 621554, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0017175674438477, "global_step": 621555, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.954176664352417, "global_step": 621556, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9860484600067139, "global_step": 621557, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0708603858947754, "global_step": 621558, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.051072359085083, "global_step": 621559, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9209595918655396, "global_step": 621560, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.159816265106201, "global_step": 621561, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0349409580230713, "global_step": 621562, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.033226251602173, "global_step": 621563, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0306386947631836, "global_step": 621564, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.915897250175476, "global_step": 621565, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0049221515655518, "global_step": 621566, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0797853469848633, "global_step": 621567, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9661033153533936, "global_step": 621568, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9301092624664307, "global_step": 621569, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0329694747924805, "global_step": 621570, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0369205474853516, "global_step": 621571, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.048434019088745, "global_step": 621572, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.028085947036743, "global_step": 621573, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9885097742080688, "global_step": 621574, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0187182426452637, "global_step": 621575, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9699960947036743, "global_step": 621576, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.985693335533142, "global_step": 621577, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0799875259399414, "global_step": 621578, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.071333408355713, "global_step": 621579, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0430026054382324, "global_step": 621580, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9882971048355103, "global_step": 621581, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0297789573669434, "global_step": 621582, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0209832191467285, "global_step": 621583, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0083415508270264, "global_step": 621584, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9736562967300415, "global_step": 621585, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0414881706237793, "global_step": 621586, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9288597106933594, "global_step": 621587, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9544758796691895, "global_step": 621588, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.018941640853882, "global_step": 621589, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0101168155670166, "global_step": 621590, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9524381160736084, "global_step": 621591, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.995465636253357, "global_step": 621592, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.972132682800293, "global_step": 621593, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9898185729980469, "global_step": 621594, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9342687129974365, "global_step": 621595, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0658020973205566, "global_step": 621596, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9169217348098755, "global_step": 621597, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0666394233703613, "global_step": 621598, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9741315841674805, "global_step": 621599, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9761910438537598, "global_step": 621600, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0160586833953857, "global_step": 621601, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9974156618118286, "global_step": 621602, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.049346446990967, "global_step": 621603, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9336479902267456, "global_step": 621604, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9447957277297974, "global_step": 621605, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9243510961532593, "global_step": 621606, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0443882942199707, "global_step": 621607, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.001243829727173, "global_step": 621608, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0420730113983154, "global_step": 621609, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.985079050064087, "global_step": 621610, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.949415922164917, "global_step": 621611, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.001922130584717, "global_step": 621612, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.017854690551758, "global_step": 621613, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0144190788269043, "global_step": 621614, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9979075193405151, "global_step": 621615, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0121047496795654, "global_step": 621616, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0017056465148926, "global_step": 621617, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.052231788635254, "global_step": 621618, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9988497495651245, "global_step": 621619, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0117030143737793, "global_step": 621620, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.00521183013916, "global_step": 621621, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.964779257774353, "global_step": 621622, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0855014324188232, "global_step": 621623, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9876173734664917, "global_step": 621624, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.027906656265259, "global_step": 621625, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.070363998413086, "global_step": 621626, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9625025987625122, "global_step": 621627, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0669264793395996, "global_step": 621628, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.029582977294922, "global_step": 621629, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.046060800552368, "global_step": 621630, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.02163028717041, "global_step": 621631, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9776719808578491, "global_step": 621632, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0404117107391357, "global_step": 621633, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.068635940551758, "global_step": 621634, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.986727237701416, "global_step": 621635, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9735159873962402, "global_step": 621636, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.017291307449341, "global_step": 621637, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9570506811141968, "global_step": 621638, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0065670013427734, "global_step": 621639, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0443062782287598, "global_step": 621640, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9883991479873657, "global_step": 621641, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9585883617401123, "global_step": 621642, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9515739679336548, "global_step": 621643, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.005145311355591, "global_step": 621644, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.018404245376587, "global_step": 621645, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9503493309020996, "global_step": 621646, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0030956268310547, "global_step": 621647, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0216281414031982, "global_step": 621648, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.049938201904297, "global_step": 621649, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9946036338806152, "global_step": 621650, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9678997993469238, "global_step": 621651, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0511364936828613, "global_step": 621652, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9115246534347534, "global_step": 621653, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.000850200653076, "global_step": 621654, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0323071479797363, "global_step": 621655, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0111613273620605, "global_step": 621656, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9636532068252563, "global_step": 621657, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.030665636062622, "global_step": 621658, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9288097620010376, "global_step": 621659, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0690503120422363, "global_step": 621660, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9185791015625, "global_step": 621661, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.079700469970703, "global_step": 621662, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9735193252563477, "global_step": 621663, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9821009635925293, "global_step": 621664, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.978366732597351, "global_step": 621665, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.026991844177246, "global_step": 621666, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0481045246124268, "global_step": 621667, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9052541255950928, "global_step": 621668, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9994715452194214, "global_step": 621669, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9554275274276733, "global_step": 621670, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0004122257232666, "global_step": 621671, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9956231117248535, "global_step": 621672, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0161380767822266, "global_step": 621673, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0391480922698975, "global_step": 621674, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.950378179550171, "global_step": 621675, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9658424854278564, "global_step": 621676, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9416656494140625, "global_step": 621677, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9993882179260254, "global_step": 621678, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.071868896484375, "global_step": 621679, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.928819179534912, "global_step": 621680, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.027168035507202, "global_step": 621681, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.074514150619507, "global_step": 621682, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.01594877243042, "global_step": 621683, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0621731281280518, "global_step": 621684, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9405337572097778, "global_step": 621685, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9778144359588623, "global_step": 621686, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0147829055786133, "global_step": 621687, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0135068893432617, "global_step": 621688, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.006038188934326, "global_step": 621689, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0234203338623047, "global_step": 621690, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0319206714630127, "global_step": 621691, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.020098924636841, "global_step": 621692, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9851043224334717, "global_step": 621693, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.035238265991211, "global_step": 621694, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.032024621963501, "global_step": 621695, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0256543159484863, "global_step": 621696, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0297374725341797, "global_step": 621697, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9674321413040161, "global_step": 621698, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.049624443054199, "global_step": 621699, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0628011226654053, "global_step": 621700, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9462392330169678, "global_step": 621701, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1334922313690186, "global_step": 621702, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9438467025756836, "global_step": 621703, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9506280422210693, "global_step": 621704, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.066399097442627, "global_step": 621705, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0106327533721924, "global_step": 621706, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9793848991394043, "global_step": 621707, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9461246728897095, "global_step": 621708, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.042245626449585, "global_step": 621709, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0095672607421875, "global_step": 621710, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9506261348724365, "global_step": 621711, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9982088804244995, "global_step": 621712, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0612809658050537, "global_step": 621713, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0035717487335205, "global_step": 621714, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1141250133514404, "global_step": 621715, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9743585586547852, "global_step": 621716, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.950451135635376, "global_step": 621717, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0178678035736084, "global_step": 621718, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9745686054229736, "global_step": 621719, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0060806274414062, "global_step": 621720, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9402949810028076, "global_step": 621721, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9424070119857788, "global_step": 621722, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.024120330810547, "global_step": 621723, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1150245666503906, "global_step": 621724, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9843169450759888, "global_step": 621725, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9802632331848145, "global_step": 621726, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.085665464401245, "global_step": 621727, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9630630016326904, "global_step": 621728, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0341262817382812, "global_step": 621729, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9062626361846924, "global_step": 621730, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.062770128250122, "global_step": 621731, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9238722324371338, "global_step": 621732, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0156025886535645, "global_step": 621733, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9571882486343384, "global_step": 621734, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9462131261825562, "global_step": 621735, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0644984245300293, "global_step": 621736, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.032257318496704, "global_step": 621737, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9952337741851807, "global_step": 621738, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0148472785949707, "global_step": 621739, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9656014442443848, "global_step": 621740, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.045259475708008, "global_step": 621741, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9539388418197632, "global_step": 621742, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.906403660774231, "global_step": 621743, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0527350902557373, "global_step": 621744, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.048290491104126, "global_step": 621745, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.955691933631897, "global_step": 621746, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0073134899139404, "global_step": 621747, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9731855392456055, "global_step": 621748, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0553507804870605, "global_step": 621749, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0207509994506836, "global_step": 621750, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.052856922149658, "global_step": 621751, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9530119895935059, "global_step": 621752, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.022674560546875, "global_step": 621753, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0086371898651123, "global_step": 621754, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0028090476989746, "global_step": 621755, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0803818702697754, "global_step": 621756, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9936293363571167, "global_step": 621757, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.059835433959961, "global_step": 621758, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.126476526260376, "global_step": 621759, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.992002248764038, "global_step": 621760, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.056372880935669, "global_step": 621761, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0427238941192627, "global_step": 621762, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.068179130554199, "global_step": 621763, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.000181198120117, "global_step": 621764, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0431947708129883, "global_step": 621765, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9334301948547363, "global_step": 621766, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.053070306777954, "global_step": 621767, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0201828479766846, "global_step": 621768, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9728775024414062, "global_step": 621769, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0284879207611084, "global_step": 621770, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.030094623565674, "global_step": 621771, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9483698606491089, "global_step": 621772, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9982341527938843, "global_step": 621773, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0555806159973145, "global_step": 621774, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.072153329849243, "global_step": 621775, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9254937171936035, "global_step": 621776, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9470471143722534, "global_step": 621777, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.017252206802368, "global_step": 621778, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9996528625488281, "global_step": 621779, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0490963459014893, "global_step": 621780, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0540854930877686, "global_step": 621781, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0783274173736572, "global_step": 621782, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.95699143409729, "global_step": 621783, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9062533378601074, "global_step": 621784, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9984352588653564, "global_step": 621785, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9449265003204346, "global_step": 621786, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9903723001480103, "global_step": 621787, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0453271865844727, "global_step": 621788, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0192952156066895, "global_step": 621789, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9426581859588623, "global_step": 621790, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.005268096923828, "global_step": 621791, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8919744491577148, "global_step": 621792, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.014624834060669, "global_step": 621793, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.952297568321228, "global_step": 621794, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0491068363189697, "global_step": 621795, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0122668743133545, "global_step": 621796, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0089035034179688, "global_step": 621797, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.034132957458496, "global_step": 621798, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.032177448272705, "global_step": 621799, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.082488775253296, "global_step": 621800, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9707770347595215, "global_step": 621801, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0663909912109375, "global_step": 621802, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9748806953430176, "global_step": 621803, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.995803713798523, "global_step": 621804, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.005887031555176, "global_step": 621805, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.048205852508545, "global_step": 621806, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0400474071502686, "global_step": 621807, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9950388669967651, "global_step": 621808, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.013176918029785, "global_step": 621809, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.003309965133667, "global_step": 621810, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0087368488311768, "global_step": 621811, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0070302486419678, "global_step": 621812, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9757477045059204, "global_step": 621813, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9537243843078613, "global_step": 621814, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0302960872650146, "global_step": 621815, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.012342929840088, "global_step": 621816, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9962447881698608, "global_step": 621817, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.979390263557434, "global_step": 621818, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.059497356414795, "global_step": 621819, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9961014986038208, "global_step": 621820, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1271421909332275, "global_step": 621821, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.973395586013794, "global_step": 621822, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9954243898391724, "global_step": 621823, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0453274250030518, "global_step": 621824, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9895154237747192, "global_step": 621825, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0837526321411133, "global_step": 621826, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9932847023010254, "global_step": 621827, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0661282539367676, "global_step": 621828, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0381100177764893, "global_step": 621829, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1084673404693604, "global_step": 621830, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9920073747634888, "global_step": 621831, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.886013150215149, "global_step": 621832, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0171875953674316, "global_step": 621833, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9494974613189697, "global_step": 621834, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0507242679595947, "global_step": 621835, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.975105881690979, "global_step": 621836, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0469937324523926, "global_step": 621837, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9902338981628418, "global_step": 621838, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0043230056762695, "global_step": 621839, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9609516859054565, "global_step": 621840, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0157811641693115, "global_step": 621841, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0806679725646973, "global_step": 621842, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9967734813690186, "global_step": 621843, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0318689346313477, "global_step": 621844, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9799370765686035, "global_step": 621845, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.991983413696289, "global_step": 621846, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9933345317840576, "global_step": 621847, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0559756755828857, "global_step": 621848, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0459558963775635, "global_step": 621849, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0909159183502197, "global_step": 621850, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9647477865219116, "global_step": 621851, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9379055500030518, "global_step": 621852, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1919455528259277, "global_step": 621853, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9975030422210693, "global_step": 621854, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.005662202835083, "global_step": 621855, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9672784805297852, "global_step": 621856, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0418105125427246, "global_step": 621857, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0008132457733154, "global_step": 621858, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0632731914520264, "global_step": 621859, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0105655193328857, "global_step": 621860, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.087750196456909, "global_step": 621861, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.059709310531616, "global_step": 621862, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0065364837646484, "global_step": 621863, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.043984889984131, "global_step": 621864, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.058864116668701, "global_step": 621865, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0590226650238037, "global_step": 621866, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9440077543258667, "global_step": 621867, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0463266372680664, "global_step": 621868, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9345440864562988, "global_step": 621869, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9933291673660278, "global_step": 621870, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9559996128082275, "global_step": 621871, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0381901264190674, "global_step": 621872, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.005225896835327, "global_step": 621873, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9684840440750122, "global_step": 621874, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.012216567993164, "global_step": 621875, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8975054025650024, "global_step": 621876, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9848262071609497, "global_step": 621877, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.040377616882324, "global_step": 621878, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.977341890335083, "global_step": 621879, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0076944828033447, "global_step": 621880, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.022991180419922, "global_step": 621881, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1268017292022705, "global_step": 621882, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9786914587020874, "global_step": 621883, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0207643508911133, "global_step": 621884, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9708456993103027, "global_step": 621885, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9619090557098389, "global_step": 621886, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9622219800949097, "global_step": 621887, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0852906703948975, "global_step": 621888, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.932602882385254, "global_step": 621889, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9998670816421509, "global_step": 621890, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.035139560699463, "global_step": 621891, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.046705484390259, "global_step": 621892, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.027587890625, "global_step": 621893, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0124852657318115, "global_step": 621894, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0673446655273438, "global_step": 621895, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9655330181121826, "global_step": 621896, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8933502435684204, "global_step": 621897, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.064281940460205, "global_step": 621898, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8930425643920898, "global_step": 621899, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0575497150421143, "global_step": 621900, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.051603078842163, "global_step": 621901, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9832957983016968, "global_step": 621902, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.925360083580017, "global_step": 621903, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0999293327331543, "global_step": 621904, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.012800931930542, "global_step": 621905, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9448391199111938, "global_step": 621906, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.023527145385742, "global_step": 621907, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9658600091934204, "global_step": 621908, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.029521942138672, "global_step": 621909, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.05342173576355, "global_step": 621910, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0160906314849854, "global_step": 621911, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0742952823638916, "global_step": 621912, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0413410663604736, "global_step": 621913, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.032080888748169, "global_step": 621914, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0895934104919434, "global_step": 621915, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.078946113586426, "global_step": 621916, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.009320020675659, "global_step": 621917, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0073444843292236, "global_step": 621918, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9893295764923096, "global_step": 621919, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1413397789001465, "global_step": 621920, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9490118026733398, "global_step": 621921, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1050422191619873, "global_step": 621922, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0500166416168213, "global_step": 621923, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9045566320419312, "global_step": 621924, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0577197074890137, "global_step": 621925, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.03591251373291, "global_step": 621926, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9818679094314575, "global_step": 621927, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.084282875061035, "global_step": 621928, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0260539054870605, "global_step": 621929, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9567815065383911, "global_step": 621930, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.008479595184326, "global_step": 621931, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.972928524017334, "global_step": 621932, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9908497333526611, "global_step": 621933, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9769697189331055, "global_step": 621934, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0646891593933105, "global_step": 621935, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.001152276992798, "global_step": 621936, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.000931978225708, "global_step": 621937, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0562028884887695, "global_step": 621938, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.921860933303833, "global_step": 621939, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.996811032295227, "global_step": 621940, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0897231101989746, "global_step": 621941, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9890501499176025, "global_step": 621942, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0159451961517334, "global_step": 621943, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9092674255371094, "global_step": 621944, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.002566337585449, "global_step": 621945, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0191426277160645, "global_step": 621946, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9748389720916748, "global_step": 621947, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0001096725463867, "global_step": 621948, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.007791519165039, "global_step": 621949, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.053758382797241, "global_step": 621950, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.014397382736206, "global_step": 621951, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.959944725036621, "global_step": 621952, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.059422016143799, "global_step": 621953, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.100836753845215, "global_step": 621954, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9912667274475098, "global_step": 621955, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9929440021514893, "global_step": 621956, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0023796558380127, "global_step": 621957, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9369184970855713, "global_step": 621958, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.060744047164917, "global_step": 621959, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9733502864837646, "global_step": 621960, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.915407657623291, "global_step": 621961, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0953123569488525, "global_step": 621962, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0439908504486084, "global_step": 621963, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.009411334991455, "global_step": 621964, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9605810642242432, "global_step": 621965, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9793939590454102, "global_step": 621966, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0103914737701416, "global_step": 621967, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1044156551361084, "global_step": 621968, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.029083728790283, "global_step": 621969, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.028839111328125, "global_step": 621970, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.005324602127075, "global_step": 621971, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.964977502822876, "global_step": 621972, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9653171300888062, "global_step": 621973, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0020370483398438, "global_step": 621974, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0101680755615234, "global_step": 621975, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9355124235153198, "global_step": 621976, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0173795223236084, "global_step": 621977, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0898125171661377, "global_step": 621978, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.021484375, "global_step": 621979, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0660595893859863, "global_step": 621980, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.042773723602295, "global_step": 621981, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.020148754119873, "global_step": 621982, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0448081493377686, "global_step": 621983, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0360500812530518, "global_step": 621984, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.007335901260376, "global_step": 621985, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9876365661621094, "global_step": 621986, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.020728349685669, "global_step": 621987, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0172736644744873, "global_step": 621988, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8977227210998535, "global_step": 621989, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.097726583480835, "global_step": 621990, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9878878593444824, "global_step": 621991, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.025294303894043, "global_step": 621992, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.017141580581665, "global_step": 621993, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.918580412864685, "global_step": 621994, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.082153558731079, "global_step": 621995, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9042086601257324, "global_step": 621996, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.047329902648926, "global_step": 621997, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.005699872970581, "global_step": 621998, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0101265907287598, "global_step": 621999, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0852386951446533, "global_step": 622000, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9973640441894531, "global_step": 622001, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0195629596710205, "global_step": 622002, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.94915771484375, "global_step": 622003, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0468358993530273, "global_step": 622004, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0925145149230957, "global_step": 622005, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.949175238609314, "global_step": 622006, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.102010726928711, "global_step": 622007, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.073991298675537, "global_step": 622008, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0475971698760986, "global_step": 622009, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0549042224884033, "global_step": 622010, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0115435123443604, "global_step": 622011, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.032750368118286, "global_step": 622012, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.012148380279541, "global_step": 622013, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9810415506362915, "global_step": 622014, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0009047985076904, "global_step": 622015, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0554192066192627, "global_step": 622016, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9686665534973145, "global_step": 622017, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9180140495300293, "global_step": 622018, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0023534297943115, "global_step": 622019, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.025282621383667, "global_step": 622020, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.941757082939148, "global_step": 622021, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1019208431243896, "global_step": 622022, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.008007287979126, "global_step": 622023, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0080275535583496, "global_step": 622024, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0406551361083984, "global_step": 622025, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.000439405441284, "global_step": 622026, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8922107219696045, "global_step": 622027, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.036531448364258, "global_step": 622028, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.067201614379883, "global_step": 622029, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0372848510742188, "global_step": 622030, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9942268133163452, "global_step": 622031, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0221331119537354, "global_step": 622032, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9876153469085693, "global_step": 622033, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9756559133529663, "global_step": 622034, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.035618543624878, "global_step": 622035, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.988757610321045, "global_step": 622036, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0526764392852783, "global_step": 622037, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.044403314590454, "global_step": 622038, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.993359088897705, "global_step": 622039, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0650722980499268, "global_step": 622040, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0583205223083496, "global_step": 622041, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9981141090393066, "global_step": 622042, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.070270299911499, "global_step": 622043, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0046463012695312, "global_step": 622044, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9990105628967285, "global_step": 622045, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9449729919433594, "global_step": 622046, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0367391109466553, "global_step": 622047, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9393500089645386, "global_step": 622048, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0025546550750732, "global_step": 622049, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.105376958847046, "global_step": 622050, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.992431879043579, "global_step": 622051, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.120920181274414, "global_step": 622052, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.958540439605713, "global_step": 622053, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0374810695648193, "global_step": 622054, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0180108547210693, "global_step": 622055, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9524047374725342, "global_step": 622056, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0522043704986572, "global_step": 622057, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9764426946640015, "global_step": 622058, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0229995250701904, "global_step": 622059, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9948625564575195, "global_step": 622060, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9507383108139038, "global_step": 622061, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1280951499938965, "global_step": 622062, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0366106033325195, "global_step": 622063, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.041400909423828, "global_step": 622064, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9895670413970947, "global_step": 622065, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0650784969329834, "global_step": 622066, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9788318872451782, "global_step": 622067, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.073716640472412, "global_step": 622068, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.018320083618164, "global_step": 622069, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.110255241394043, "global_step": 622070, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0035645961761475, "global_step": 622071, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.078662157058716, "global_step": 622072, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0323495864868164, "global_step": 622073, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0205695629119873, "global_step": 622074, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9797505140304565, "global_step": 622075, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.082958698272705, "global_step": 622076, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.060741901397705, "global_step": 622077, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.079575777053833, "global_step": 622078, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0283188819885254, "global_step": 622079, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0190823078155518, "global_step": 622080, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.043564558029175, "global_step": 622081, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9748601913452148, "global_step": 622082, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.03096866607666, "global_step": 622083, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.00827956199646, "global_step": 622084, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9908413887023926, "global_step": 622085, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9960192441940308, "global_step": 622086, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0178720951080322, "global_step": 622087, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.94138765335083, "global_step": 622088, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.891902208328247, "global_step": 622089, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.037980794906616, "global_step": 622090, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.053325891494751, "global_step": 622091, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9886679649353027, "global_step": 622092, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.00488018989563, "global_step": 622093, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0074403285980225, "global_step": 622094, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.959797978401184, "global_step": 622095, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.070150375366211, "global_step": 622096, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9956647157669067, "global_step": 622097, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1257691383361816, "global_step": 622098, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9451665878295898, "global_step": 622099, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.048553466796875, "global_step": 622100, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.091311454772949, "global_step": 622101, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.003310441970825, "global_step": 622102, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0908093452453613, "global_step": 622103, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0344841480255127, "global_step": 622104, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9690910577774048, "global_step": 622105, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9356558322906494, "global_step": 622106, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0357608795166016, "global_step": 622107, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0722782611846924, "global_step": 622108, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.993795394897461, "global_step": 622109, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0367658138275146, "global_step": 622110, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9630916118621826, "global_step": 622111, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0590381622314453, "global_step": 622112, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1652989387512207, "global_step": 622113, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9567954540252686, "global_step": 622114, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0554497241973877, "global_step": 622115, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.020249843597412, "global_step": 622116, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9964619874954224, "global_step": 622117, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.96486496925354, "global_step": 622118, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9539742469787598, "global_step": 622119, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9839168787002563, "global_step": 622120, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0895025730133057, "global_step": 622121, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1026296615600586, "global_step": 622122, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0180420875549316, "global_step": 622123, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.041769027709961, "global_step": 622124, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.022952079772949, "global_step": 622125, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9763274192810059, "global_step": 622126, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9973751306533813, "global_step": 622127, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0978541374206543, "global_step": 622128, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.066601514816284, "global_step": 622129, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8666210174560547, "global_step": 622130, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.982685923576355, "global_step": 622131, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.92975652217865, "global_step": 622132, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.060255765914917, "global_step": 622133, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.983352541923523, "global_step": 622134, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0115861892700195, "global_step": 622135, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9823884963989258, "global_step": 622136, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0028998851776123, "global_step": 622137, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9789905548095703, "global_step": 622138, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.956843376159668, "global_step": 622139, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0371556282043457, "global_step": 622140, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0634605884552, "global_step": 622141, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.959936499595642, "global_step": 622142, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9214798212051392, "global_step": 622143, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9085314273834229, "global_step": 622144, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0477070808410645, "global_step": 622145, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.027022361755371, "global_step": 622146, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9917593002319336, "global_step": 622147, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0450985431671143, "global_step": 622148, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.005763530731201, "global_step": 622149, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.068687915802002, "global_step": 622150, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.956665277481079, "global_step": 622151, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0279242992401123, "global_step": 622152, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0661661624908447, "global_step": 622153, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.034778594970703, "global_step": 622154, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.022399663925171, "global_step": 622155, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9925470352172852, "global_step": 622156, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1388461589813232, "global_step": 622157, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.030128240585327, "global_step": 622158, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9280107021331787, "global_step": 622159, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0056285858154297, "global_step": 622160, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0013298988342285, "global_step": 622161, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9694905281066895, "global_step": 622162, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.042181968688965, "global_step": 622163, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0063424110412598, "global_step": 622164, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0664920806884766, "global_step": 622165, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9721264839172363, "global_step": 622166, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.057246446609497, "global_step": 622167, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0133979320526123, "global_step": 622168, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9480255842208862, "global_step": 622169, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0157368183135986, "global_step": 622170, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9593580961227417, "global_step": 622171, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9723680019378662, "global_step": 622172, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1370787620544434, "global_step": 622173, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.961357831954956, "global_step": 622174, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.015273332595825, "global_step": 622175, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9438756704330444, "global_step": 622176, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0027546882629395, "global_step": 622177, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0759081840515137, "global_step": 622178, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.093519926071167, "global_step": 622179, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9116692543029785, "global_step": 622180, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0149199962615967, "global_step": 622181, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1117260456085205, "global_step": 622182, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9516494274139404, "global_step": 622183, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.138033628463745, "global_step": 622184, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.032127857208252, "global_step": 622185, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.956239104270935, "global_step": 622186, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9905083179473877, "global_step": 622187, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.01901912689209, "global_step": 622188, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.954944372177124, "global_step": 622189, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9641635417938232, "global_step": 622190, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.009047508239746, "global_step": 622191, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9583438634872437, "global_step": 622192, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.986074447631836, "global_step": 622193, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9903044700622559, "global_step": 622194, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.081977605819702, "global_step": 622195, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0024220943450928, "global_step": 622196, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0268378257751465, "global_step": 622197, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.02567458152771, "global_step": 622198, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.050180435180664, "global_step": 622199, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0865516662597656, "global_step": 622200, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0251879692077637, "global_step": 622201, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.047776699066162, "global_step": 622202, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0451149940490723, "global_step": 622203, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8879928588867188, "global_step": 622204, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.055277109146118, "global_step": 622205, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9961196184158325, "global_step": 622206, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0085644721984863, "global_step": 622207, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.055135726928711, "global_step": 622208, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.014411449432373, "global_step": 622209, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9859243631362915, "global_step": 622210, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.014230728149414, "global_step": 622211, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9599529504776, "global_step": 622212, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.969563603401184, "global_step": 622213, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9886142015457153, "global_step": 622214, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.051571846008301, "global_step": 622215, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.029876232147217, "global_step": 622216, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0638315677642822, "global_step": 622217, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.054454803466797, "global_step": 622218, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.00471830368042, "global_step": 622219, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9861910343170166, "global_step": 622220, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0111947059631348, "global_step": 622221, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9534693956375122, "global_step": 622222, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.908661127090454, "global_step": 622223, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.030992269515991, "global_step": 622224, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0177619457244873, "global_step": 622225, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.005948543548584, "global_step": 622226, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0011935234069824, "global_step": 622227, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9711841344833374, "global_step": 622228, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.024563789367676, "global_step": 622229, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0073611736297607, "global_step": 622230, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.006525754928589, "global_step": 622231, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.935675024986267, "global_step": 622232, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0633368492126465, "global_step": 622233, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9654603004455566, "global_step": 622234, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9589966535568237, "global_step": 622235, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9410020112991333, "global_step": 622236, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9821540117263794, "global_step": 622237, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9257677793502808, "global_step": 622238, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.03515362739563, "global_step": 622239, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9428715705871582, "global_step": 622240, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.986557960510254, "global_step": 622241, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9879097938537598, "global_step": 622242, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.041642427444458, "global_step": 622243, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9208976030349731, "global_step": 622244, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9912117719650269, "global_step": 622245, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1146299839019775, "global_step": 622246, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9636266231536865, "global_step": 622247, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0297486782073975, "global_step": 622248, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.997032880783081, "global_step": 622249, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.967888593673706, "global_step": 622250, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.069319009780884, "global_step": 622251, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9770351648330688, "global_step": 622252, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0672287940979004, "global_step": 622253, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9594924449920654, "global_step": 622254, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9559319019317627, "global_step": 622255, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9526373147964478, "global_step": 622256, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.944547176361084, "global_step": 622257, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.990429401397705, "global_step": 622258, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9923133850097656, "global_step": 622259, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9187898635864258, "global_step": 622260, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9507607221603394, "global_step": 622261, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0181491374969482, "global_step": 622262, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9280909299850464, "global_step": 622263, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9296597242355347, "global_step": 622264, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.02150559425354, "global_step": 622265, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0717597007751465, "global_step": 622266, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0390498638153076, "global_step": 622267, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0548691749572754, "global_step": 622268, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0080602169036865, "global_step": 622269, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.961853265762329, "global_step": 622270, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.028153419494629, "global_step": 622271, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0533242225646973, "global_step": 622272, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.01467227935791, "global_step": 622273, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0346086025238037, "global_step": 622274, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9761896133422852, "global_step": 622275, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0460658073425293, "global_step": 622276, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0014891624450684, "global_step": 622277, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0192906856536865, "global_step": 622278, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9740805625915527, "global_step": 622279, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.01424241065979, "global_step": 622280, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0326638221740723, "global_step": 622281, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9612385034561157, "global_step": 622282, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0167083740234375, "global_step": 622283, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.892991304397583, "global_step": 622284, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9263659715652466, "global_step": 622285, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9309422969818115, "global_step": 622286, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9885716438293457, "global_step": 622287, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9472367763519287, "global_step": 622288, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9351803064346313, "global_step": 622289, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9654518365859985, "global_step": 622290, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9277398586273193, "global_step": 622291, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9685735702514648, "global_step": 622292, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.032125234603882, "global_step": 622293, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9930342435836792, "global_step": 622294, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.98780357837677, "global_step": 622295, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9804033041000366, "global_step": 622296, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9532393217086792, "global_step": 622297, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.950637936592102, "global_step": 622298, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.010755777359009, "global_step": 622299, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.000657320022583, "global_step": 622300, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0058369636535645, "global_step": 622301, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0256519317626953, "global_step": 622302, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9514496326446533, "global_step": 622303, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.979521632194519, "global_step": 622304, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9278827905654907, "global_step": 622305, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9154831171035767, "global_step": 622306, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.010655641555786, "global_step": 622307, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.039379835128784, "global_step": 622308, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0432956218719482, "global_step": 622309, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9914579391479492, "global_step": 622310, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9548293352127075, "global_step": 622311, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0268094539642334, "global_step": 622312, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0154190063476562, "global_step": 622313, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0488994121551514, "global_step": 622314, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0405330657958984, "global_step": 622315, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0574138164520264, "global_step": 622316, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9848979711532593, "global_step": 622317, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0236058235168457, "global_step": 622318, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0461034774780273, "global_step": 622319, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0057523250579834, "global_step": 622320, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9751312732696533, "global_step": 622321, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.076496124267578, "global_step": 622322, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.968742847442627, "global_step": 622323, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0361149311065674, "global_step": 622324, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0753798484802246, "global_step": 622325, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.912480354309082, "global_step": 622326, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9888086318969727, "global_step": 622327, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9843180179595947, "global_step": 622328, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.8942307233810425, "global_step": 622329, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.035687208175659, "global_step": 622330, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.021303176879883, "global_step": 622331, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9968961477279663, "global_step": 622332, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.136842966079712, "global_step": 622333, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.081871747970581, "global_step": 622334, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.995322346687317, "global_step": 622335, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9856582880020142, "global_step": 622336, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.017212152481079, "global_step": 622337, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.019246816635132, "global_step": 622338, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9196724891662598, "global_step": 622339, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9688353538513184, "global_step": 622340, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0039470195770264, "global_step": 622341, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9653878211975098, "global_step": 622342, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9959373474121094, "global_step": 622343, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0162580013275146, "global_step": 622344, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9688892364501953, "global_step": 622345, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9799273014068604, "global_step": 622346, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9586291313171387, "global_step": 622347, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9778326749801636, "global_step": 622348, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9665014743804932, "global_step": 622349, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9886407852172852, "global_step": 622350, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0435752868652344, "global_step": 622351, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.073690414428711, "global_step": 622352, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9779043197631836, "global_step": 622353, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.040658950805664, "global_step": 622354, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.043741226196289, "global_step": 622355, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.8577909469604492, "global_step": 622356, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.027582883834839, "global_step": 622357, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.038428544998169, "global_step": 622358, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9202992916107178, "global_step": 622359, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0194647312164307, "global_step": 622360, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9447355270385742, "global_step": 622361, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.056109666824341, "global_step": 622362, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0593760013580322, "global_step": 622363, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.958333134651184, "global_step": 622364, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.969394326210022, "global_step": 622365, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0006306171417236, "global_step": 622366, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0348265171051025, "global_step": 622367, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9607250690460205, "global_step": 622368, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0725674629211426, "global_step": 622369, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9626741409301758, "global_step": 622370, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9488019943237305, "global_step": 622371, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0533559322357178, "global_step": 622372, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.992027997970581, "global_step": 622373, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0459301471710205, "global_step": 622374, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.956106424331665, "global_step": 622375, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9656991958618164, "global_step": 622376, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0745768547058105, "global_step": 622377, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0257325172424316, "global_step": 622378, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9059711694717407, "global_step": 622379, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9639073610305786, "global_step": 622380, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9865005016326904, "global_step": 622381, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9899349212646484, "global_step": 622382, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.953710675239563, "global_step": 622383, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9602200984954834, "global_step": 622384, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.967995285987854, "global_step": 622385, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9911412000656128, "global_step": 622386, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.00687837600708, "global_step": 622387, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.024381399154663, "global_step": 622388, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0626792907714844, "global_step": 622389, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.8485687971115112, "global_step": 622390, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9644752740859985, "global_step": 622391, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.000577926635742, "global_step": 622392, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.057880401611328, "global_step": 622393, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0696163177490234, "global_step": 622394, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0150668621063232, "global_step": 622395, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9770910739898682, "global_step": 622396, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9540942907333374, "global_step": 622397, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.026649236679077, "global_step": 622398, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9865132570266724, "global_step": 622399, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0316121578216553, "global_step": 622400, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9845125675201416, "global_step": 622401, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0266060829162598, "global_step": 622402, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9582997560501099, "global_step": 622403, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9739274978637695, "global_step": 622404, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.012284755706787, "global_step": 622405, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.900067925453186, "global_step": 622406, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.017807722091675, "global_step": 622407, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0650880336761475, "global_step": 622408, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.985556721687317, "global_step": 622409, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.975898265838623, "global_step": 622410, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9802075624465942, "global_step": 622411, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9720546007156372, "global_step": 622412, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0277833938598633, "global_step": 622413, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9429632425308228, "global_step": 622414, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9447664022445679, "global_step": 622415, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.11081862449646, "global_step": 622416, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.016392230987549, "global_step": 622417, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0930497646331787, "global_step": 622418, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.995743989944458, "global_step": 622419, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.05456805229187, "global_step": 622420, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0091989040374756, "global_step": 622421, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.030085325241089, "global_step": 622422, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0399489402770996, "global_step": 622423, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9858840703964233, "global_step": 622424, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9329715967178345, "global_step": 622425, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.958741307258606, "global_step": 622426, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0343353748321533, "global_step": 622427, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9436063766479492, "global_step": 622428, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.000901699066162, "global_step": 622429, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9705415964126587, "global_step": 622430, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.03012752532959, "global_step": 622431, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9776318073272705, "global_step": 622432, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.998071551322937, "global_step": 622433, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.991807460784912, "global_step": 622434, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9846450090408325, "global_step": 622435, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0123636722564697, "global_step": 622436, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.987868070602417, "global_step": 622437, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0471506118774414, "global_step": 622438, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9051966667175293, "global_step": 622439, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0235400199890137, "global_step": 622440, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.993560791015625, "global_step": 622441, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9493645429611206, "global_step": 622442, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9586331844329834, "global_step": 622443, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9852272272109985, "global_step": 622444, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0686724185943604, "global_step": 622445, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9101885557174683, "global_step": 622446, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9474235773086548, "global_step": 622447, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1162562370300293, "global_step": 622448, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.992022156715393, "global_step": 622449, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9254539012908936, "global_step": 622450, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0674006938934326, "global_step": 622451, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0038774013519287, "global_step": 622452, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.994245171546936, "global_step": 622453, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0056185722351074, "global_step": 622454, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0958807468414307, "global_step": 622455, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0973715782165527, "global_step": 622456, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.054257869720459, "global_step": 622457, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9450322389602661, "global_step": 622458, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.048576831817627, "global_step": 622459, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9881190061569214, "global_step": 622460, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0736145973205566, "global_step": 622461, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9718701839447021, "global_step": 622462, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0402495861053467, "global_step": 622463, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9811755418777466, "global_step": 622464, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.97870671749115, "global_step": 622465, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0052132606506348, "global_step": 622466, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.020139455795288, "global_step": 622467, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0720155239105225, "global_step": 622468, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.00455641746521, "global_step": 622469, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9681886434555054, "global_step": 622470, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9844261407852173, "global_step": 622471, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0309839248657227, "global_step": 622472, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0484018325805664, "global_step": 622473, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.023204803466797, "global_step": 622474, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9595234394073486, "global_step": 622475, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0180888175964355, "global_step": 622476, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9830044507980347, "global_step": 622477, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0408577919006348, "global_step": 622478, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0650110244750977, "global_step": 622479, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0279176235198975, "global_step": 622480, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9270098209381104, "global_step": 622481, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9200040102005005, "global_step": 622482, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0019614696502686, "global_step": 622483, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.018341541290283, "global_step": 622484, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0620415210723877, "global_step": 622485, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.092863082885742, "global_step": 622486, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0555777549743652, "global_step": 622487, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0525095462799072, "global_step": 622488, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9906446933746338, "global_step": 622489, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.04620361328125, "global_step": 622490, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9976452589035034, "global_step": 622491, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9310302734375, "global_step": 622492, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.977690577507019, "global_step": 622493, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.966339349746704, "global_step": 622494, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.945464849472046, "global_step": 622495, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0395445823669434, "global_step": 622496, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.961931586265564, "global_step": 622497, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0458970069885254, "global_step": 622498, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.069430351257324, "global_step": 622499, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9952526092529297, "global_step": 622500, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.027904510498047, "global_step": 622501, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0309338569641113, "global_step": 622502, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9739855527877808, "global_step": 622503, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9508576393127441, "global_step": 622504, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.923316240310669, "global_step": 622505, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.069570302963257, "global_step": 622506, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9200223684310913, "global_step": 622507, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9706273078918457, "global_step": 622508, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9207897186279297, "global_step": 622509, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9779889583587646, "global_step": 622510, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0148491859436035, "global_step": 622511, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9165737628936768, "global_step": 622512, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9927256107330322, "global_step": 622513, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9496604204177856, "global_step": 622514, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.968509554862976, "global_step": 622515, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9892873764038086, "global_step": 622516, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0152530670166016, "global_step": 622517, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0326693058013916, "global_step": 622518, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.967804193496704, "global_step": 622519, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0065765380859375, "global_step": 622520, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0304205417633057, "global_step": 622521, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9713681936264038, "global_step": 622522, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.025524139404297, "global_step": 622523, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9648582935333252, "global_step": 622524, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9207955598831177, "global_step": 622525, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9773340225219727, "global_step": 622526, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9443508386611938, "global_step": 622527, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9085768461227417, "global_step": 622528, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0767791271209717, "global_step": 622529, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0161550045013428, "global_step": 622530, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0047216415405273, "global_step": 622531, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9825637340545654, "global_step": 622532, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0614748001098633, "global_step": 622533, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.940892219543457, "global_step": 622534, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9077767133712769, "global_step": 622535, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.056055784225464, "global_step": 622536, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0080459117889404, "global_step": 622537, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0017244815826416, "global_step": 622538, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9748493432998657, "global_step": 622539, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9777965545654297, "global_step": 622540, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.018956422805786, "global_step": 622541, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.051689624786377, "global_step": 622542, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.058480978012085, "global_step": 622543, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.055781602859497, "global_step": 622544, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0155270099639893, "global_step": 622545, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9960410594940186, "global_step": 622546, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9864797592163086, "global_step": 622547, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.022658586502075, "global_step": 622548, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9480924606323242, "global_step": 622549, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9887428283691406, "global_step": 622550, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0482797622680664, "global_step": 622551, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.025169610977173, "global_step": 622552, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9385337829589844, "global_step": 622553, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0537452697753906, "global_step": 622554, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0377357006073, "global_step": 622555, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.060354709625244, "global_step": 622556, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9291759729385376, "global_step": 622557, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9670933485031128, "global_step": 622558, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9270384311676025, "global_step": 622559, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0215628147125244, "global_step": 622560, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.041788339614868, "global_step": 622561, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9817038774490356, "global_step": 622562, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0055761337280273, "global_step": 622563, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.032731533050537, "global_step": 622564, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9629161357879639, "global_step": 622565, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9823473691940308, "global_step": 622566, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0784199237823486, "global_step": 622567, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9950547218322754, "global_step": 622568, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9600855112075806, "global_step": 622569, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0584545135498047, "global_step": 622570, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0087890625, "global_step": 622571, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0788660049438477, "global_step": 622572, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9901429414749146, "global_step": 622573, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.02213978767395, "global_step": 622574, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9981751441955566, "global_step": 622575, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.02878737449646, "global_step": 622576, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9774854183197021, "global_step": 622577, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0407602787017822, "global_step": 622578, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0433566570281982, "global_step": 622579, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9274086952209473, "global_step": 622580, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9387067556381226, "global_step": 622581, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.079124689102173, "global_step": 622582, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0154504776000977, "global_step": 622583, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0390141010284424, "global_step": 622584, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9953012466430664, "global_step": 622585, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9504168033599854, "global_step": 622586, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9986008405685425, "global_step": 622587, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9319437742233276, "global_step": 622588, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0293021202087402, "global_step": 622589, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0591044425964355, "global_step": 622590, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.107464551925659, "global_step": 622591, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0500900745391846, "global_step": 622592, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9082543849945068, "global_step": 622593, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.017298936843872, "global_step": 622594, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0820908546447754, "global_step": 622595, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.971510887145996, "global_step": 622596, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0836994647979736, "global_step": 622597, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0328006744384766, "global_step": 622598, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.128225326538086, "global_step": 622599, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.080838203430176, "global_step": 622600, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0187411308288574, "global_step": 622601, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.015793800354004, "global_step": 622602, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.895536184310913, "global_step": 622603, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9879355430603027, "global_step": 622604, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.949231743812561, "global_step": 622605, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.058527708053589, "global_step": 622606, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0030336380004883, "global_step": 622607, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.969559907913208, "global_step": 622608, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0055315494537354, "global_step": 622609, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0096161365509033, "global_step": 622610, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9831469058990479, "global_step": 622611, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.014324903488159, "global_step": 622612, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9412951469421387, "global_step": 622613, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0053048133850098, "global_step": 622614, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.015019178390503, "global_step": 622615, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9814693927764893, "global_step": 622616, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9285584688186646, "global_step": 622617, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.962166666984558, "global_step": 622618, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9530704021453857, "global_step": 622619, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0432674884796143, "global_step": 622620, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.012122392654419, "global_step": 622621, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.037787914276123, "global_step": 622622, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9551236629486084, "global_step": 622623, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0985145568847656, "global_step": 622624, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.961484432220459, "global_step": 622625, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.048999309539795, "global_step": 622626, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0011420249938965, "global_step": 622627, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.022855520248413, "global_step": 622628, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.000971794128418, "global_step": 622629, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9600410461425781, "global_step": 622630, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0821993350982666, "global_step": 622631, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.132896900177002, "global_step": 622632, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.949597954750061, "global_step": 622633, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.027606964111328, "global_step": 622634, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9836788177490234, "global_step": 622635, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0421864986419678, "global_step": 622636, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9968364238739014, "global_step": 622637, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9366317987442017, "global_step": 622638, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9764891862869263, "global_step": 622639, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.022397041320801, "global_step": 622640, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9649385213851929, "global_step": 622641, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9658149480819702, "global_step": 622642, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9709577560424805, "global_step": 622643, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.027599573135376, "global_step": 622644, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.033435106277466, "global_step": 622645, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9548219442367554, "global_step": 622646, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0896215438842773, "global_step": 622647, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9548499584197998, "global_step": 622648, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.989987850189209, "global_step": 622649, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0917794704437256, "global_step": 622650, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.958726167678833, "global_step": 622651, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0922646522521973, "global_step": 622652, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9419933557510376, "global_step": 622653, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.011636734008789, "global_step": 622654, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9489656686782837, "global_step": 622655, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.021792411804199, "global_step": 622656, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0447683334350586, "global_step": 622657, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.070688009262085, "global_step": 622658, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9539769887924194, "global_step": 622659, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.057673215866089, "global_step": 622660, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9528311491012573, "global_step": 622661, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0458457469940186, "global_step": 622662, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.905990719795227, "global_step": 622663, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0068016052246094, "global_step": 622664, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9847841262817383, "global_step": 622665, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9724912643432617, "global_step": 622666, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0028820037841797, "global_step": 622667, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.032853126525879, "global_step": 622668, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.004051446914673, "global_step": 622669, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.062483310699463, "global_step": 622670, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.075815200805664, "global_step": 622671, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0065858364105225, "global_step": 622672, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9161345958709717, "global_step": 622673, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0706560611724854, "global_step": 622674, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.017261505126953, "global_step": 622675, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0537917613983154, "global_step": 622676, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0306670665740967, "global_step": 622677, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.084995746612549, "global_step": 622678, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0056207180023193, "global_step": 622679, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0546977519989014, "global_step": 622680, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9872835874557495, "global_step": 622681, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0393970012664795, "global_step": 622682, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9840092658996582, "global_step": 622683, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9768186807632446, "global_step": 622684, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9802968502044678, "global_step": 622685, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.942514181137085, "global_step": 622686, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.026806354522705, "global_step": 622687, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.994415521621704, "global_step": 622688, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9678173065185547, "global_step": 622689, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.025214433670044, "global_step": 622690, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.969957947731018, "global_step": 622691, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.028377056121826, "global_step": 622692, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0413525104522705, "global_step": 622693, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9981659650802612, "global_step": 622694, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9916030168533325, "global_step": 622695, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9907290935516357, "global_step": 622696, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.05647873878479, "global_step": 622697, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9710644483566284, "global_step": 622698, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.039519786834717, "global_step": 622699, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9762284755706787, "global_step": 622700, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9746372699737549, "global_step": 622701, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0138721466064453, "global_step": 622702, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0201942920684814, "global_step": 622703, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1109068393707275, "global_step": 622704, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.994506597518921, "global_step": 622705, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0200083255767822, "global_step": 622706, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.977688193321228, "global_step": 622707, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0094404220581055, "global_step": 622708, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.012831926345825, "global_step": 622709, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0026299953460693, "global_step": 622710, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9892029762268066, "global_step": 622711, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9733800888061523, "global_step": 622712, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.00667142868042, "global_step": 622713, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.058051586151123, "global_step": 622714, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.058854341506958, "global_step": 622715, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0469930171966553, "global_step": 622716, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0840327739715576, "global_step": 622717, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9160587787628174, "global_step": 622718, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9833574295043945, "global_step": 622719, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0530905723571777, "global_step": 622720, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9940764904022217, "global_step": 622721, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9975154399871826, "global_step": 622722, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9065147638320923, "global_step": 622723, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.032233476638794, "global_step": 622724, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0176408290863037, "global_step": 622725, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9480327367782593, "global_step": 622726, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0856847763061523, "global_step": 622727, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9700053930282593, "global_step": 622728, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9289506673812866, "global_step": 622729, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0045359134674072, "global_step": 622730, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0342929363250732, "global_step": 622731, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.010448932647705, "global_step": 622732, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.007650852203369, "global_step": 622733, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0004587173461914, "global_step": 622734, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0281660556793213, "global_step": 622735, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.071720838546753, "global_step": 622736, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.993099570274353, "global_step": 622737, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9931347370147705, "global_step": 622738, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0466091632843018, "global_step": 622739, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.009349822998047, "global_step": 622740, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.03786301612854, "global_step": 622741, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.053697109222412, "global_step": 622742, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0758702754974365, "global_step": 622743, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0017309188842773, "global_step": 622744, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.971191167831421, "global_step": 622745, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0751633644104004, "global_step": 622746, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.055844783782959, "global_step": 622747, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9446996450424194, "global_step": 622748, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9988539218902588, "global_step": 622749, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0766568183898926, "global_step": 622750, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9695063829421997, "global_step": 622751, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9932053089141846, "global_step": 622752, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0494558811187744, "global_step": 622753, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0753583908081055, "global_step": 622754, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0736260414123535, "global_step": 622755, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1268470287323, "global_step": 622756, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9817678928375244, "global_step": 622757, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.027388095855713, "global_step": 622758, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.094998359680176, "global_step": 622759, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9418169260025024, "global_step": 622760, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9738689661026, "global_step": 622761, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.993478775024414, "global_step": 622762, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0955071449279785, "global_step": 622763, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0702803134918213, "global_step": 622764, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0096821784973145, "global_step": 622765, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.059159517288208, "global_step": 622766, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.003080368041992, "global_step": 622767, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9538031816482544, "global_step": 622768, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.100128412246704, "global_step": 622769, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0195882320404053, "global_step": 622770, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9507694244384766, "global_step": 622771, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9562355279922485, "global_step": 622772, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9510140419006348, "global_step": 622773, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.039550542831421, "global_step": 622774, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0116236209869385, "global_step": 622775, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0251245498657227, "global_step": 622776, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0111899375915527, "global_step": 622777, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9719529151916504, "global_step": 622778, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0220186710357666, "global_step": 622779, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9890190362930298, "global_step": 622780, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9673850536346436, "global_step": 622781, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.104623794555664, "global_step": 622782, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9901090860366821, "global_step": 622783, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.08101487159729, "global_step": 622784, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0064077377319336, "global_step": 622785, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.964638113975525, "global_step": 622786, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.081204891204834, "global_step": 622787, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9569590091705322, "global_step": 622788, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9458026885986328, "global_step": 622789, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0169529914855957, "global_step": 622790, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9615123271942139, "global_step": 622791, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9355167150497437, "global_step": 622792, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.090789794921875, "global_step": 622793, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0485663414001465, "global_step": 622794, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0210886001586914, "global_step": 622795, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.110159158706665, "global_step": 622796, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9601693153381348, "global_step": 622797, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0155649185180664, "global_step": 622798, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.02246356010437, "global_step": 622799, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9769251346588135, "global_step": 622800, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9889991283416748, "global_step": 622801, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.035781145095825, "global_step": 622802, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.035644054412842, "global_step": 622803, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0188324451446533, "global_step": 622804, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.043016195297241, "global_step": 622805, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0219390392303467, "global_step": 622806, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9889122247695923, "global_step": 622807, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0762689113616943, "global_step": 622808, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9474107027053833, "global_step": 622809, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9762405157089233, "global_step": 622810, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0298428535461426, "global_step": 622811, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9907187223434448, "global_step": 622812, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9703645706176758, "global_step": 622813, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0321102142333984, "global_step": 622814, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.992370843887329, "global_step": 622815, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9817146062850952, "global_step": 622816, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.008913993835449, "global_step": 622817, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0376524925231934, "global_step": 622818, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0421016216278076, "global_step": 622819, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9839376211166382, "global_step": 622820, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1452903747558594, "global_step": 622821, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9641393423080444, "global_step": 622822, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0123796463012695, "global_step": 622823, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.013408660888672, "global_step": 622824, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.985208511352539, "global_step": 622825, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.096757173538208, "global_step": 622826, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9176695346832275, "global_step": 622827, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9523193836212158, "global_step": 622828, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9668760299682617, "global_step": 622829, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9592010974884033, "global_step": 622830, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1097214221954346, "global_step": 622831, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0190114974975586, "global_step": 622832, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.114755630493164, "global_step": 622833, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9893304109573364, "global_step": 622834, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.99934983253479, "global_step": 622835, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.078421115875244, "global_step": 622836, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9990577697753906, "global_step": 622837, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9945894479751587, "global_step": 622838, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.019436836242676, "global_step": 622839, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.017275333404541, "global_step": 622840, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9960931539535522, "global_step": 622841, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.005692958831787, "global_step": 622842, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9808807373046875, "global_step": 622843, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.028235912322998, "global_step": 622844, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9987046718597412, "global_step": 622845, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9766852855682373, "global_step": 622846, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.053210735321045, "global_step": 622847, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9599120616912842, "global_step": 622848, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9304542541503906, "global_step": 622849, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9494707584381104, "global_step": 622850, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0522713661193848, "global_step": 622851, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0729281902313232, "global_step": 622852, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.036822557449341, "global_step": 622853, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0470409393310547, "global_step": 622854, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0061211585998535, "global_step": 622855, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0046732425689697, "global_step": 622856, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9867079257965088, "global_step": 622857, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9999316930770874, "global_step": 622858, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9550772905349731, "global_step": 622859, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.023019552230835, "global_step": 622860, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9851436614990234, "global_step": 622861, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0391416549682617, "global_step": 622862, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0227842330932617, "global_step": 622863, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0245022773742676, "global_step": 622864, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9907114505767822, "global_step": 622865, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.990895390510559, "global_step": 622866, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.939033031463623, "global_step": 622867, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9606263637542725, "global_step": 622868, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0561392307281494, "global_step": 622869, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9534635543823242, "global_step": 622870, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.98605215549469, "global_step": 622871, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9514470100402832, "global_step": 622872, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0370266437530518, "global_step": 622873, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0355873107910156, "global_step": 622874, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.952000379562378, "global_step": 622875, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.997829794883728, "global_step": 622876, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0293092727661133, "global_step": 622877, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.8877573013305664, "global_step": 622878, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9098148345947266, "global_step": 622879, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.8957542181015015, "global_step": 622880, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.014759063720703, "global_step": 622881, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9931293725967407, "global_step": 622882, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0531575679779053, "global_step": 622883, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0949580669403076, "global_step": 622884, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.978770136833191, "global_step": 622885, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.8901515007019043, "global_step": 622886, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9615004062652588, "global_step": 622887, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.00359845161438, "global_step": 622888, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0367255210876465, "global_step": 622889, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0036673545837402, "global_step": 622890, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.017702102661133, "global_step": 622891, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0683345794677734, "global_step": 622892, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9233556985855103, "global_step": 622893, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.02211594581604, "global_step": 622894, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.020233392715454, "global_step": 622895, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1104376316070557, "global_step": 622896, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0615570545196533, "global_step": 622897, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.024015426635742, "global_step": 622898, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0169999599456787, "global_step": 622899, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0070481300354004, "global_step": 622900, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.8940097093582153, "global_step": 622901, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.93612539768219, "global_step": 622902, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9510825872421265, "global_step": 622903, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.003568410873413, "global_step": 622904, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.013573408126831, "global_step": 622905, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.068812370300293, "global_step": 622906, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.027419328689575, "global_step": 622907, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9257441759109497, "global_step": 622908, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.097137451171875, "global_step": 622909, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9924900531768799, "global_step": 622910, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.013046979904175, "global_step": 622911, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.052947521209717, "global_step": 622912, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0438010692596436, "global_step": 622913, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.047421455383301, "global_step": 622914, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9398808479309082, "global_step": 622915, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.014359474182129, "global_step": 622916, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9488842487335205, "global_step": 622917, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0253498554229736, "global_step": 622918, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0198473930358887, "global_step": 622919, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0246334075927734, "global_step": 622920, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.047452449798584, "global_step": 622921, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0252175331115723, "global_step": 622922, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9285013675689697, "global_step": 622923, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9859305620193481, "global_step": 622924, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9877738952636719, "global_step": 622925, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0459070205688477, "global_step": 622926, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9942671060562134, "global_step": 622927, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.010906457901001, "global_step": 622928, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0375442504882812, "global_step": 622929, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0430030822753906, "global_step": 622930, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0424869060516357, "global_step": 622931, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0931918621063232, "global_step": 622932, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0022528171539307, "global_step": 622933, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9627859592437744, "global_step": 622934, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9259166717529297, "global_step": 622935, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9689209461212158, "global_step": 622936, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.00838565826416, "global_step": 622937, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9605365991592407, "global_step": 622938, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0841944217681885, "global_step": 622939, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0250473022460938, "global_step": 622940, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9654359817504883, "global_step": 622941, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9867464303970337, "global_step": 622942, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.010195255279541, "global_step": 622943, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0155527591705322, "global_step": 622944, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9555740356445312, "global_step": 622945, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9165949821472168, "global_step": 622946, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.958519697189331, "global_step": 622947, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.923114538192749, "global_step": 622948, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9741851091384888, "global_step": 622949, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.030486583709717, "global_step": 622950, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.989966869354248, "global_step": 622951, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0335805416107178, "global_step": 622952, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.024155855178833, "global_step": 622953, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.098130464553833, "global_step": 622954, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9702204465866089, "global_step": 622955, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0156357288360596, "global_step": 622956, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.00874924659729, "global_step": 622957, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9889051914215088, "global_step": 622958, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0461533069610596, "global_step": 622959, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9744110107421875, "global_step": 622960, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9590961933135986, "global_step": 622961, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0751025676727295, "global_step": 622962, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9470340013504028, "global_step": 622963, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1304397583007812, "global_step": 622964, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9854720830917358, "global_step": 622965, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9496572017669678, "global_step": 622966, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9613703489303589, "global_step": 622967, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0644688606262207, "global_step": 622968, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0163731575012207, "global_step": 622969, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0864486694335938, "global_step": 622970, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0142784118652344, "global_step": 622971, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.040544271469116, "global_step": 622972, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9027124643325806, "global_step": 622973, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9977262020111084, "global_step": 622974, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0165700912475586, "global_step": 622975, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.051206588745117, "global_step": 622976, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.047405242919922, "global_step": 622977, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0106871128082275, "global_step": 622978, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0523905754089355, "global_step": 622979, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0749945640563965, "global_step": 622980, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.031677722930908, "global_step": 622981, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9733787775039673, "global_step": 622982, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9585038423538208, "global_step": 622983, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0257091522216797, "global_step": 622984, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.921999216079712, "global_step": 622985, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9523431062698364, "global_step": 622986, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1584279537200928, "global_step": 622987, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.939785122871399, "global_step": 622988, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0083625316619873, "global_step": 622989, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9999827146530151, "global_step": 622990, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.8959561586380005, "global_step": 622991, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0351638793945312, "global_step": 622992, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.018766164779663, "global_step": 622993, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9124361276626587, "global_step": 622994, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.029029369354248, "global_step": 622995, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.04419207572937, "global_step": 622996, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.92454195022583, "global_step": 622997, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9921350479125977, "global_step": 622998, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9439903497695923, "global_step": 622999, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9452776908874512, "global_step": 623000, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0258612632751465, "global_step": 623001, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.04219651222229, "global_step": 623002, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0188350677490234, "global_step": 623003, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9598312377929688, "global_step": 623004, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0140535831451416, "global_step": 623005, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9683855772018433, "global_step": 623006, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9848469495773315, "global_step": 623007, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1046879291534424, "global_step": 623008, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1025917530059814, "global_step": 623009, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0111212730407715, "global_step": 623010, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9586381912231445, "global_step": 623011, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0276334285736084, "global_step": 623012, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9332716464996338, "global_step": 623013, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0087063312530518, "global_step": 623014, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9839866161346436, "global_step": 623015, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9687449932098389, "global_step": 623016, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.980061411857605, "global_step": 623017, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9466665983200073, "global_step": 623018, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9470783472061157, "global_step": 623019, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9686795473098755, "global_step": 623020, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9858585596084595, "global_step": 623021, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.053269386291504, "global_step": 623022, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.982587218284607, "global_step": 623023, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9925005435943604, "global_step": 623024, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.010999917984009, "global_step": 623025, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9306018352508545, "global_step": 623026, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.008153200149536, "global_step": 623027, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.021857738494873, "global_step": 623028, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.035275459289551, "global_step": 623029, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0083718299865723, "global_step": 623030, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9366960525512695, "global_step": 623031, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0174269676208496, "global_step": 623032, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9491527080535889, "global_step": 623033, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.001732349395752, "global_step": 623034, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0103158950805664, "global_step": 623035, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0500712394714355, "global_step": 623036, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9500515460968018, "global_step": 623037, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.985775113105774, "global_step": 623038, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0053322315216064, "global_step": 623039, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9975053071975708, "global_step": 623040, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1297476291656494, "global_step": 623041, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.003498077392578, "global_step": 623042, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.999015212059021, "global_step": 623043, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9878466129302979, "global_step": 623044, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.971769094467163, "global_step": 623045, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9450117349624634, "global_step": 623046, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.921701192855835, "global_step": 623047, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.109013795852661, "global_step": 623048, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9897910356521606, "global_step": 623049, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0396668910980225, "global_step": 623050, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.005173683166504, "global_step": 623051, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.030219793319702, "global_step": 623052, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9350261688232422, "global_step": 623053, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.032433032989502, "global_step": 623054, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0415902137756348, "global_step": 623055, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9633222818374634, "global_step": 623056, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9956120252609253, "global_step": 623057, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9580695629119873, "global_step": 623058, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9258196353912354, "global_step": 623059, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9873714447021484, "global_step": 623060, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9802563190460205, "global_step": 623061, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.996970534324646, "global_step": 623062, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.143188238143921, "global_step": 623063, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0046334266662598, "global_step": 623064, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1185572147369385, "global_step": 623065, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.00485897064209, "global_step": 623066, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0746374130249023, "global_step": 623067, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9629318714141846, "global_step": 623068, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.040534257888794, "global_step": 623069, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.061936855316162, "global_step": 623070, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9970436096191406, "global_step": 623071, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0361053943634033, "global_step": 623072, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9295450448989868, "global_step": 623073, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.061505079269409, "global_step": 623074, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.8655190467834473, "global_step": 623075, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0215587615966797, "global_step": 623076, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9866353273391724, "global_step": 623077, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0578386783599854, "global_step": 623078, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0066096782684326, "global_step": 623079, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1051981449127197, "global_step": 623080, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9439367055892944, "global_step": 623081, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.963592529296875, "global_step": 623082, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.966839075088501, "global_step": 623083, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.8643269538879395, "global_step": 623084, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.944197654724121, "global_step": 623085, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.013658285140991, "global_step": 623086, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0776548385620117, "global_step": 623087, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9822067022323608, "global_step": 623088, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0182483196258545, "global_step": 623089, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0179624557495117, "global_step": 623090, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.027865171432495, "global_step": 623091, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9729915857315063, "global_step": 623092, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0068037509918213, "global_step": 623093, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.99821138381958, "global_step": 623094, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9683278799057007, "global_step": 623095, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.026463747024536, "global_step": 623096, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9818240404129028, "global_step": 623097, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9815953969955444, "global_step": 623098, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9611003398895264, "global_step": 623099, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9674283266067505, "global_step": 623100, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.051365375518799, "global_step": 623101, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.001204252243042, "global_step": 623102, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0518198013305664, "global_step": 623103, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9374327659606934, "global_step": 623104, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0158426761627197, "global_step": 623105, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0307817459106445, "global_step": 623106, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9861186742782593, "global_step": 623107, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0138025283813477, "global_step": 623108, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9865708351135254, "global_step": 623109, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0215647220611572, "global_step": 623110, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0091660022735596, "global_step": 623111, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.029890537261963, "global_step": 623112, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9651544094085693, "global_step": 623113, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9928652048110962, "global_step": 623114, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.986491322517395, "global_step": 623115, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.085477828979492, "global_step": 623116, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9985148906707764, "global_step": 623117, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0462069511413574, "global_step": 623118, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.959284782409668, "global_step": 623119, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0261378288269043, "global_step": 623120, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0953447818756104, "global_step": 623121, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9843528270721436, "global_step": 623122, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.037446975708008, "global_step": 623123, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9640377759933472, "global_step": 623124, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.028837203979492, "global_step": 623125, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0412774085998535, "global_step": 623126, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9662269353866577, "global_step": 623127, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.013251781463623, "global_step": 623128, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0369091033935547, "global_step": 623129, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.101935625076294, "global_step": 623130, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0041792392730713, "global_step": 623131, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0531578063964844, "global_step": 623132, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.067422866821289, "global_step": 623133, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.046849012374878, "global_step": 623134, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0985307693481445, "global_step": 623135, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.055344820022583, "global_step": 623136, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.026134967803955, "global_step": 623137, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1080074310302734, "global_step": 623138, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9805939197540283, "global_step": 623139, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9863197803497314, "global_step": 623140, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0058462619781494, "global_step": 623141, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9844046831130981, "global_step": 623142, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9305741786956787, "global_step": 623143, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9708645343780518, "global_step": 623144, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.992841362953186, "global_step": 623145, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.147542953491211, "global_step": 623146, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.008265495300293, "global_step": 623147, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0665459632873535, "global_step": 623148, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0348808765411377, "global_step": 623149, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.048079013824463, "global_step": 623150, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.025329351425171, "global_step": 623151, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.989379644393921, "global_step": 623152, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.963877558708191, "global_step": 623153, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0283286571502686, "global_step": 623154, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.007246732711792, "global_step": 623155, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9510924816131592, "global_step": 623156, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0405118465423584, "global_step": 623157, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0292234420776367, "global_step": 623158, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.027987241744995, "global_step": 623159, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0404040813446045, "global_step": 623160, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0216987133026123, "global_step": 623161, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.024000644683838, "global_step": 623162, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.968820333480835, "global_step": 623163, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9309264421463013, "global_step": 623164, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.072171449661255, "global_step": 623165, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.01725435256958, "global_step": 623166, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0200297832489014, "global_step": 623167, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0069141387939453, "global_step": 623168, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.050654411315918, "global_step": 623169, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9630874395370483, "global_step": 623170, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0318233966827393, "global_step": 623171, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.01861572265625, "global_step": 623172, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0045995712280273, "global_step": 623173, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9860420227050781, "global_step": 623174, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9909220933914185, "global_step": 623175, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0235252380371094, "global_step": 623176, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9448604583740234, "global_step": 623177, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9939498901367188, "global_step": 623178, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.053105354309082, "global_step": 623179, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.067042827606201, "global_step": 623180, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0539371967315674, "global_step": 623181, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.950706958770752, "global_step": 623182, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.05325984954834, "global_step": 623183, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9958348274230957, "global_step": 623184, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9868696928024292, "global_step": 623185, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.056814432144165, "global_step": 623186, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9655108451843262, "global_step": 623187, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9961094856262207, "global_step": 623188, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0109896659851074, "global_step": 623189, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9748375415802002, "global_step": 623190, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.03005313873291, "global_step": 623191, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9956440925598145, "global_step": 623192, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0692412853240967, "global_step": 623193, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9966704845428467, "global_step": 623194, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.043105125427246, "global_step": 623195, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.029745578765869, "global_step": 623196, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.041146993637085, "global_step": 623197, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.028795003890991, "global_step": 623198, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0042123794555664, "global_step": 623199, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.001340389251709, "global_step": 623200, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.998740315437317, "global_step": 623201, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9836697578430176, "global_step": 623202, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.912756323814392, "global_step": 623203, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0041515827178955, "global_step": 623204, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9948960542678833, "global_step": 623205, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0598247051239014, "global_step": 623206, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0746426582336426, "global_step": 623207, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.022361993789673, "global_step": 623208, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.918535828590393, "global_step": 623209, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0829765796661377, "global_step": 623210, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.05458927154541, "global_step": 623211, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.016469955444336, "global_step": 623212, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.061875581741333, "global_step": 623213, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9796578884124756, "global_step": 623214, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9957455396652222, "global_step": 623215, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.042210102081299, "global_step": 623216, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9429181814193726, "global_step": 623217, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9940015077590942, "global_step": 623218, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9736692905426025, "global_step": 623219, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9657284021377563, "global_step": 623220, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0052490234375, "global_step": 623221, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.972100019454956, "global_step": 623222, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.019418954849243, "global_step": 623223, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0580546855926514, "global_step": 623224, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9658256769180298, "global_step": 623225, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9781028032302856, "global_step": 623226, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9595004320144653, "global_step": 623227, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9611737728118896, "global_step": 623228, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.038287878036499, "global_step": 623229, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8949363231658936, "global_step": 623230, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.980987548828125, "global_step": 623231, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0131709575653076, "global_step": 623232, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.06294584274292, "global_step": 623233, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1115169525146484, "global_step": 623234, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9919835329055786, "global_step": 623235, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9546197652816772, "global_step": 623236, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.007096290588379, "global_step": 623237, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1134209632873535, "global_step": 623238, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9969704151153564, "global_step": 623239, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9652106761932373, "global_step": 623240, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.992431402206421, "global_step": 623241, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9402326345443726, "global_step": 623242, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9086607694625854, "global_step": 623243, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9282455444335938, "global_step": 623244, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0229833126068115, "global_step": 623245, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.005934715270996, "global_step": 623246, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9615119695663452, "global_step": 623247, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0448505878448486, "global_step": 623248, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0009124279022217, "global_step": 623249, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9698495864868164, "global_step": 623250, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9926635026931763, "global_step": 623251, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.999916672706604, "global_step": 623252, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9884248971939087, "global_step": 623253, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9703584909439087, "global_step": 623254, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0094971656799316, "global_step": 623255, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.999091625213623, "global_step": 623256, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9536067247390747, "global_step": 623257, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9625200033187866, "global_step": 623258, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.934964656829834, "global_step": 623259, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0047976970672607, "global_step": 623260, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9980885982513428, "global_step": 623261, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8848097324371338, "global_step": 623262, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.902554988861084, "global_step": 623263, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9359724521636963, "global_step": 623264, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.035726547241211, "global_step": 623265, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9972809553146362, "global_step": 623266, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0147624015808105, "global_step": 623267, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.050151824951172, "global_step": 623268, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0088865756988525, "global_step": 623269, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.058338165283203, "global_step": 623270, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.904415249824524, "global_step": 623271, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9980887174606323, "global_step": 623272, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9517788887023926, "global_step": 623273, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9627678394317627, "global_step": 623274, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0301601886749268, "global_step": 623275, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0205116271972656, "global_step": 623276, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9721962213516235, "global_step": 623277, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9773485660552979, "global_step": 623278, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0572726726531982, "global_step": 623279, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9856858253479004, "global_step": 623280, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9947617053985596, "global_step": 623281, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0044450759887695, "global_step": 623282, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9562941789627075, "global_step": 623283, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8850116729736328, "global_step": 623284, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9691966772079468, "global_step": 623285, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.965584397315979, "global_step": 623286, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9394948482513428, "global_step": 623287, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9261974096298218, "global_step": 623288, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0345418453216553, "global_step": 623289, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0375707149505615, "global_step": 623290, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0217626094818115, "global_step": 623291, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9636317491531372, "global_step": 623292, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0245361328125, "global_step": 623293, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9928008317947388, "global_step": 623294, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0243029594421387, "global_step": 623295, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9711463451385498, "global_step": 623296, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0289809703826904, "global_step": 623297, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9924366474151611, "global_step": 623298, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0144379138946533, "global_step": 623299, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9885435104370117, "global_step": 623300, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0353827476501465, "global_step": 623301, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0088367462158203, "global_step": 623302, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.987012267112732, "global_step": 623303, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.988122820854187, "global_step": 623304, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.025888442993164, "global_step": 623305, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9443870782852173, "global_step": 623306, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0349440574645996, "global_step": 623307, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.993516206741333, "global_step": 623308, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.98683500289917, "global_step": 623309, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9879040718078613, "global_step": 623310, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.982290267944336, "global_step": 623311, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0261151790618896, "global_step": 623312, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9804214239120483, "global_step": 623313, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9829665422439575, "global_step": 623314, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0196659564971924, "global_step": 623315, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0049917697906494, "global_step": 623316, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9837186336517334, "global_step": 623317, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9247955083847046, "global_step": 623318, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0322937965393066, "global_step": 623319, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9947113990783691, "global_step": 623320, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.898447871208191, "global_step": 623321, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.028434991836548, "global_step": 623322, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0338563919067383, "global_step": 623323, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9604741334915161, "global_step": 623324, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9833191633224487, "global_step": 623325, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9793825149536133, "global_step": 623326, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0400993824005127, "global_step": 623327, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8775581121444702, "global_step": 623328, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9979788064956665, "global_step": 623329, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0313713550567627, "global_step": 623330, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9782358407974243, "global_step": 623331, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.964426040649414, "global_step": 623332, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.916054129600525, "global_step": 623333, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.101574420928955, "global_step": 623334, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.055148124694824, "global_step": 623335, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.980161190032959, "global_step": 623336, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9847650527954102, "global_step": 623337, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9492270946502686, "global_step": 623338, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9925780296325684, "global_step": 623339, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9652316570281982, "global_step": 623340, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0440268516540527, "global_step": 623341, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.926875352859497, "global_step": 623342, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9692273139953613, "global_step": 623343, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.02372670173645, "global_step": 623344, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.011340856552124, "global_step": 623345, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0509421825408936, "global_step": 623346, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9779561758041382, "global_step": 623347, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9972983598709106, "global_step": 623348, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9877458810806274, "global_step": 623349, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0555975437164307, "global_step": 623350, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9776314496994019, "global_step": 623351, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9313466548919678, "global_step": 623352, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9305273294448853, "global_step": 623353, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.049466609954834, "global_step": 623354, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9971485137939453, "global_step": 623355, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9048703908920288, "global_step": 623356, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.944433569908142, "global_step": 623357, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9859997034072876, "global_step": 623358, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9746915102005005, "global_step": 623359, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0634827613830566, "global_step": 623360, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.025658130645752, "global_step": 623361, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0385684967041016, "global_step": 623362, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1092844009399414, "global_step": 623363, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9587723016738892, "global_step": 623364, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9893286228179932, "global_step": 623365, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9261780977249146, "global_step": 623366, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9871037006378174, "global_step": 623367, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0041520595550537, "global_step": 623368, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.002795457839966, "global_step": 623369, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.981970191001892, "global_step": 623370, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9311989545822144, "global_step": 623371, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0083277225494385, "global_step": 623372, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.97291898727417, "global_step": 623373, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9906432628631592, "global_step": 623374, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0009214878082275, "global_step": 623375, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.072669744491577, "global_step": 623376, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0776190757751465, "global_step": 623377, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0278711318969727, "global_step": 623378, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.957942008972168, "global_step": 623379, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.976208209991455, "global_step": 623380, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.071380138397217, "global_step": 623381, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9312260150909424, "global_step": 623382, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.025341510772705, "global_step": 623383, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.958351731300354, "global_step": 623384, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9653024673461914, "global_step": 623385, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9792112112045288, "global_step": 623386, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.000731945037842, "global_step": 623387, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.06121563911438, "global_step": 623388, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9800496101379395, "global_step": 623389, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9660266637802124, "global_step": 623390, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0913524627685547, "global_step": 623391, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0163650512695312, "global_step": 623392, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8956832885742188, "global_step": 623393, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9207299947738647, "global_step": 623394, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.033886432647705, "global_step": 623395, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0332834720611572, "global_step": 623396, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9456225633621216, "global_step": 623397, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9527486562728882, "global_step": 623398, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0703768730163574, "global_step": 623399, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.00170636177063, "global_step": 623400, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9423344135284424, "global_step": 623401, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0614418983459473, "global_step": 623402, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0563995838165283, "global_step": 623403, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9621155261993408, "global_step": 623404, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9765493869781494, "global_step": 623405, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.073586940765381, "global_step": 623406, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0610387325286865, "global_step": 623407, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9166580438613892, "global_step": 623408, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9959886074066162, "global_step": 623409, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.959324598312378, "global_step": 623410, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.02407169342041, "global_step": 623411, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9654299020767212, "global_step": 623412, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9905040264129639, "global_step": 623413, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.008615255355835, "global_step": 623414, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.004585027694702, "global_step": 623415, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9417277574539185, "global_step": 623416, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0636656284332275, "global_step": 623417, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0339818000793457, "global_step": 623418, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.009528636932373, "global_step": 623419, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9258793592453003, "global_step": 623420, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.866357684135437, "global_step": 623421, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9907513856887817, "global_step": 623422, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9837801456451416, "global_step": 623423, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0187885761260986, "global_step": 623424, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.972891092300415, "global_step": 623425, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9558359384536743, "global_step": 623426, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0275003910064697, "global_step": 623427, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9868730306625366, "global_step": 623428, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.040707588195801, "global_step": 623429, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9794951677322388, "global_step": 623430, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0254757404327393, "global_step": 623431, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9498857259750366, "global_step": 623432, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9926637411117554, "global_step": 623433, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9756022691726685, "global_step": 623434, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8771828413009644, "global_step": 623435, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0415842533111572, "global_step": 623436, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.103860855102539, "global_step": 623437, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9402031898498535, "global_step": 623438, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.07261061668396, "global_step": 623439, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.978119134902954, "global_step": 623440, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.036968946456909, "global_step": 623441, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9746556282043457, "global_step": 623442, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9943246841430664, "global_step": 623443, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9801915884017944, "global_step": 623444, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0647847652435303, "global_step": 623445, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.017353057861328, "global_step": 623446, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0054140090942383, "global_step": 623447, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0410828590393066, "global_step": 623448, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9441713094711304, "global_step": 623449, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.029268741607666, "global_step": 623450, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.021712303161621, "global_step": 623451, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.013307571411133, "global_step": 623452, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.00130558013916, "global_step": 623453, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9822165966033936, "global_step": 623454, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.01672101020813, "global_step": 623455, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.022726058959961, "global_step": 623456, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0420470237731934, "global_step": 623457, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9963994026184082, "global_step": 623458, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9913053512573242, "global_step": 623459, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9624860286712646, "global_step": 623460, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9513330459594727, "global_step": 623461, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9653642177581787, "global_step": 623462, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9416122436523438, "global_step": 623463, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0201706886291504, "global_step": 623464, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9998527765274048, "global_step": 623465, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9733387231826782, "global_step": 623466, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.962362289428711, "global_step": 623467, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.001544952392578, "global_step": 623468, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.058680772781372, "global_step": 623469, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0149893760681152, "global_step": 623470, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.089271306991577, "global_step": 623471, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9760124683380127, "global_step": 623472, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.983989953994751, "global_step": 623473, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.986512541770935, "global_step": 623474, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9912188053131104, "global_step": 623475, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.042618989944458, "global_step": 623476, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.099742889404297, "global_step": 623477, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.02720046043396, "global_step": 623478, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9346396923065186, "global_step": 623479, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0149855613708496, "global_step": 623480, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9832807779312134, "global_step": 623481, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9211517572402954, "global_step": 623482, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.025017261505127, "global_step": 623483, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0017690658569336, "global_step": 623484, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9509813785552979, "global_step": 623485, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0016136169433594, "global_step": 623486, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0423543453216553, "global_step": 623487, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.117079734802246, "global_step": 623488, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0767128467559814, "global_step": 623489, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0422332286834717, "global_step": 623490, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9888797998428345, "global_step": 623491, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0158071517944336, "global_step": 623492, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.004039764404297, "global_step": 623493, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9562515020370483, "global_step": 623494, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.006091833114624, "global_step": 623495, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9930391311645508, "global_step": 623496, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0490775108337402, "global_step": 623497, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.085263967514038, "global_step": 623498, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9312471151351929, "global_step": 623499, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0091347694396973, "global_step": 623500, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9654721021652222, "global_step": 623501, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9758440256118774, "global_step": 623502, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.020087242126465, "global_step": 623503, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.004646062850952, "global_step": 623504, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9666424989700317, "global_step": 623505, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.046549081802368, "global_step": 623506, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9615591764450073, "global_step": 623507, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8820831775665283, "global_step": 623508, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9870891571044922, "global_step": 623509, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.011514902114868, "global_step": 623510, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9155175685882568, "global_step": 623511, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0637428760528564, "global_step": 623512, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1002402305603027, "global_step": 623513, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.055778741836548, "global_step": 623514, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0022497177124023, "global_step": 623515, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9338150024414062, "global_step": 623516, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0168635845184326, "global_step": 623517, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0623257160186768, "global_step": 623518, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9883854389190674, "global_step": 623519, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0821480751037598, "global_step": 623520, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9719593524932861, "global_step": 623521, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9938035011291504, "global_step": 623522, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.029203176498413, "global_step": 623523, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0555062294006348, "global_step": 623524, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.018263339996338, "global_step": 623525, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9602380990982056, "global_step": 623526, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.005042552947998, "global_step": 623527, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.042489767074585, "global_step": 623528, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9241334199905396, "global_step": 623529, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0601749420166016, "global_step": 623530, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0226869583129883, "global_step": 623531, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0281145572662354, "global_step": 623532, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.997318148612976, "global_step": 623533, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.013932466506958, "global_step": 623534, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9968451261520386, "global_step": 623535, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8944897651672363, "global_step": 623536, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0047478675842285, "global_step": 623537, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.033137083053589, "global_step": 623538, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.031557321548462, "global_step": 623539, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0838403701782227, "global_step": 623540, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0046162605285645, "global_step": 623541, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8859411478042603, "global_step": 623542, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9489644765853882, "global_step": 623543, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.008854627609253, "global_step": 623544, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0001273155212402, "global_step": 623545, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.938449740409851, "global_step": 623546, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9786312580108643, "global_step": 623547, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0618109703063965, "global_step": 623548, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.995229721069336, "global_step": 623549, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0128374099731445, "global_step": 623550, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.078357458114624, "global_step": 623551, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9968148469924927, "global_step": 623552, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.014343023300171, "global_step": 623553, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9990105628967285, "global_step": 623554, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.003937005996704, "global_step": 623555, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.078122854232788, "global_step": 623556, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.080112934112549, "global_step": 623557, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.018418550491333, "global_step": 623558, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.052626371383667, "global_step": 623559, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9925124645233154, "global_step": 623560, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.06436824798584, "global_step": 623561, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9681010246276855, "global_step": 623562, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.101998805999756, "global_step": 623563, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0010454654693604, "global_step": 623564, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9497278928756714, "global_step": 623565, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9659477472305298, "global_step": 623566, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.005279541015625, "global_step": 623567, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.032675266265869, "global_step": 623568, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1010563373565674, "global_step": 623569, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.030275344848633, "global_step": 623570, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9781010150909424, "global_step": 623571, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9967458248138428, "global_step": 623572, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.930083155632019, "global_step": 623573, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9320381879806519, "global_step": 623574, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9811477661132812, "global_step": 623575, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.052011489868164, "global_step": 623576, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.993668794631958, "global_step": 623577, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.923539400100708, "global_step": 623578, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.171760320663452, "global_step": 623579, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0238728523254395, "global_step": 623580, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9465603828430176, "global_step": 623581, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.081103563308716, "global_step": 623582, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9675370454788208, "global_step": 623583, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0425641536712646, "global_step": 623584, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.956547737121582, "global_step": 623585, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.068272829055786, "global_step": 623586, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.981661081314087, "global_step": 623587, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0314390659332275, "global_step": 623588, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9915916919708252, "global_step": 623589, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.079749345779419, "global_step": 623590, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9830868244171143, "global_step": 623591, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9985716342926025, "global_step": 623592, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0676498413085938, "global_step": 623593, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1089911460876465, "global_step": 623594, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.041231393814087, "global_step": 623595, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9510393142700195, "global_step": 623596, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9791408777236938, "global_step": 623597, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.026812791824341, "global_step": 623598, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.02418851852417, "global_step": 623599, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0271782875061035, "global_step": 623600, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9406306743621826, "global_step": 623601, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.013404607772827, "global_step": 623602, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.088104486465454, "global_step": 623603, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.96683669090271, "global_step": 623604, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.031081438064575, "global_step": 623605, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9742469787597656, "global_step": 623606, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.010246753692627, "global_step": 623607, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9939385652542114, "global_step": 623608, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.009938955307007, "global_step": 623609, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0173346996307373, "global_step": 623610, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.049177408218384, "global_step": 623611, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.019524097442627, "global_step": 623612, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0307326316833496, "global_step": 623613, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9811934232711792, "global_step": 623614, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9070755243301392, "global_step": 623615, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.983805775642395, "global_step": 623616, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0113468170166016, "global_step": 623617, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.013704538345337, "global_step": 623618, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8710112571716309, "global_step": 623619, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.003485679626465, "global_step": 623620, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.085705280303955, "global_step": 623621, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0000131130218506, "global_step": 623622, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.022080421447754, "global_step": 623623, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0762100219726562, "global_step": 623624, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9959635734558105, "global_step": 623625, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.99198579788208, "global_step": 623626, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9267271757125854, "global_step": 623627, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.049257516860962, "global_step": 623628, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9853811264038086, "global_step": 623629, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0772812366485596, "global_step": 623630, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.040085554122925, "global_step": 623631, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0523838996887207, "global_step": 623632, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.046538829803467, "global_step": 623633, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.94512140750885, "global_step": 623634, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0396740436553955, "global_step": 623635, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9583483934402466, "global_step": 623636, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.038508892059326, "global_step": 623637, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0322177410125732, "global_step": 623638, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0059380531311035, "global_step": 623639, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9510529041290283, "global_step": 623640, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0488648414611816, "global_step": 623641, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9144787788391113, "global_step": 623642, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9790806770324707, "global_step": 623643, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.986667513847351, "global_step": 623644, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.018923759460449, "global_step": 623645, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9918090105056763, "global_step": 623646, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9718166589736938, "global_step": 623647, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9629491567611694, "global_step": 623648, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0218088626861572, "global_step": 623649, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.914096713066101, "global_step": 623650, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.005005359649658, "global_step": 623651, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.999419927597046, "global_step": 623652, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.083167552947998, "global_step": 623653, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0167768001556396, "global_step": 623654, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0594630241394043, "global_step": 623655, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.97165846824646, "global_step": 623656, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9702205657958984, "global_step": 623657, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0198471546173096, "global_step": 623658, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9422770738601685, "global_step": 623659, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9830125570297241, "global_step": 623660, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9253287315368652, "global_step": 623661, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0237371921539307, "global_step": 623662, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.008573532104492, "global_step": 623663, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0137600898742676, "global_step": 623664, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.088773250579834, "global_step": 623665, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9697080850601196, "global_step": 623666, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.025460720062256, "global_step": 623667, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9361763000488281, "global_step": 623668, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9435365200042725, "global_step": 623669, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9964065551757812, "global_step": 623670, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9791024923324585, "global_step": 623671, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0266897678375244, "global_step": 623672, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.029367446899414, "global_step": 623673, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9845335483551025, "global_step": 623674, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9645310640335083, "global_step": 623675, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9913077354431152, "global_step": 623676, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.016890525817871, "global_step": 623677, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.870538592338562, "global_step": 623678, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9534252882003784, "global_step": 623679, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9622684717178345, "global_step": 623680, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0043416023254395, "global_step": 623681, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0246236324310303, "global_step": 623682, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.967560052871704, "global_step": 623683, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0261878967285156, "global_step": 623684, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9415550231933594, "global_step": 623685, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9332059621810913, "global_step": 623686, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9426143169403076, "global_step": 623687, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.993327021598816, "global_step": 623688, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9552381038665771, "global_step": 623689, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9985898733139038, "global_step": 623690, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9874438047409058, "global_step": 623691, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9765061140060425, "global_step": 623692, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.04435396194458, "global_step": 623693, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9728260040283203, "global_step": 623694, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9521507024765015, "global_step": 623695, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9389091730117798, "global_step": 623696, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.00020694732666, "global_step": 623697, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9414814710617065, "global_step": 623698, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9791544675827026, "global_step": 623699, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.052954912185669, "global_step": 623700, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9494017362594604, "global_step": 623701, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0175695419311523, "global_step": 623702, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8950365781784058, "global_step": 623703, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9646376371383667, "global_step": 623704, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.083164691925049, "global_step": 623705, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9824546575546265, "global_step": 623706, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0300452709198, "global_step": 623707, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9763000011444092, "global_step": 623708, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9536160230636597, "global_step": 623709, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9278483390808105, "global_step": 623710, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0432159900665283, "global_step": 623711, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0000503063201904, "global_step": 623712, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.047093152999878, "global_step": 623713, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9897618293762207, "global_step": 623714, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.024510622024536, "global_step": 623715, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.01043963432312, "global_step": 623716, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0378940105438232, "global_step": 623717, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.044391393661499, "global_step": 623718, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9428300857543945, "global_step": 623719, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9798436164855957, "global_step": 623720, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9570516347885132, "global_step": 623721, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.00962233543396, "global_step": 623722, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.020627021789551, "global_step": 623723, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9926644563674927, "global_step": 623724, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0191712379455566, "global_step": 623725, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.068711757659912, "global_step": 623726, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.066169500350952, "global_step": 623727, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.059608221054077, "global_step": 623728, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0453922748565674, "global_step": 623729, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0059351921081543, "global_step": 623730, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.053189277648926, "global_step": 623731, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0184731483459473, "global_step": 623732, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1112139225006104, "global_step": 623733, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0395002365112305, "global_step": 623734, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.022798776626587, "global_step": 623735, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.007047176361084, "global_step": 623736, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9613282680511475, "global_step": 623737, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9942270517349243, "global_step": 623738, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.008476495742798, "global_step": 623739, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.013278007507324, "global_step": 623740, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9813858270645142, "global_step": 623741, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.081082582473755, "global_step": 623742, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9687623977661133, "global_step": 623743, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.994381070137024, "global_step": 623744, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0081777572631836, "global_step": 623745, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.002260684967041, "global_step": 623746, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.96769118309021, "global_step": 623747, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.04500412940979, "global_step": 623748, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0240869522094727, "global_step": 623749, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0601768493652344, "global_step": 623750, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.057215929031372, "global_step": 623751, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9804977178573608, "global_step": 623752, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9481536149978638, "global_step": 623753, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.077803134918213, "global_step": 623754, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.068676710128784, "global_step": 623755, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.030674457550049, "global_step": 623756, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.000112533569336, "global_step": 623757, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9309378862380981, "global_step": 623758, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9504649639129639, "global_step": 623759, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0646262168884277, "global_step": 623760, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.008291721343994, "global_step": 623761, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0784547328948975, "global_step": 623762, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.091588020324707, "global_step": 623763, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0456440448760986, "global_step": 623764, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.89108145236969, "global_step": 623765, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.040720224380493, "global_step": 623766, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9559558629989624, "global_step": 623767, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0062148571014404, "global_step": 623768, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9519150257110596, "global_step": 623769, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0256693363189697, "global_step": 623770, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0316061973571777, "global_step": 623771, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0034115314483643, "global_step": 623772, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.069434881210327, "global_step": 623773, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9088422060012817, "global_step": 623774, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.981259822845459, "global_step": 623775, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9660592079162598, "global_step": 623776, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.94027578830719, "global_step": 623777, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9576038122177124, "global_step": 623778, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.930875539779663, "global_step": 623779, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0564334392547607, "global_step": 623780, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0051372051239014, "global_step": 623781, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.017085552215576, "global_step": 623782, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9808677434921265, "global_step": 623783, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0410635471343994, "global_step": 623784, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9682815074920654, "global_step": 623785, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.960164189338684, "global_step": 623786, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9953174591064453, "global_step": 623787, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9950436353683472, "global_step": 623788, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.932041049003601, "global_step": 623789, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0339643955230713, "global_step": 623790, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9573396444320679, "global_step": 623791, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0124356746673584, "global_step": 623792, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9905829429626465, "global_step": 623793, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.009695529937744, "global_step": 623794, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0108253955841064, "global_step": 623795, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0253102779388428, "global_step": 623796, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.029827356338501, "global_step": 623797, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9889637231826782, "global_step": 623798, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9535400867462158, "global_step": 623799, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0101964473724365, "global_step": 623800, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0357673168182373, "global_step": 623801, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.96731436252594, "global_step": 623802, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9778183698654175, "global_step": 623803, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9601258039474487, "global_step": 623804, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0294785499572754, "global_step": 623805, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.009819984436035, "global_step": 623806, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0113821029663086, "global_step": 623807, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.921555519104004, "global_step": 623808, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.052391290664673, "global_step": 623809, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.060398578643799, "global_step": 623810, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.076533794403076, "global_step": 623811, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0654122829437256, "global_step": 623812, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.004093885421753, "global_step": 623813, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9662567377090454, "global_step": 623814, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0161876678466797, "global_step": 623815, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0043375492095947, "global_step": 623816, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0711605548858643, "global_step": 623817, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0063130855560303, "global_step": 623818, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9968918561935425, "global_step": 623819, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9973901510238647, "global_step": 623820, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0144078731536865, "global_step": 623821, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.069331645965576, "global_step": 623822, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.96180260181427, "global_step": 623823, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9491467475891113, "global_step": 623824, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.015273094177246, "global_step": 623825, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.001845121383667, "global_step": 623826, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0273473262786865, "global_step": 623827, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0481936931610107, "global_step": 623828, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.016474723815918, "global_step": 623829, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9127380847930908, "global_step": 623830, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0034072399139404, "global_step": 623831, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9489859342575073, "global_step": 623832, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.93833589553833, "global_step": 623833, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0218212604522705, "global_step": 623834, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9722578525543213, "global_step": 623835, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9484961032867432, "global_step": 623836, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0578672885894775, "global_step": 623837, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9956597089767456, "global_step": 623838, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9346948862075806, "global_step": 623839, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.010822296142578, "global_step": 623840, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0242843627929688, "global_step": 623841, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0087766647338867, "global_step": 623842, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.018937349319458, "global_step": 623843, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.074460506439209, "global_step": 623844, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0328798294067383, "global_step": 623845, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0571346282958984, "global_step": 623846, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0652341842651367, "global_step": 623847, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.047037363052368, "global_step": 623848, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0360028743743896, "global_step": 623849, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0136423110961914, "global_step": 623850, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.95613694190979, "global_step": 623851, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9834468364715576, "global_step": 623852, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.036494731903076, "global_step": 623853, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0342519283294678, "global_step": 623854, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0239808559417725, "global_step": 623855, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.019198179244995, "global_step": 623856, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0506229400634766, "global_step": 623857, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.041262626647949, "global_step": 623858, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9909018278121948, "global_step": 623859, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0715975761413574, "global_step": 623860, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0360634326934814, "global_step": 623861, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9984432458877563, "global_step": 623862, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.028228998184204, "global_step": 623863, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.932496428489685, "global_step": 623864, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0549635887145996, "global_step": 623865, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9658790826797485, "global_step": 623866, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0547800064086914, "global_step": 623867, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.971777081489563, "global_step": 623868, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0362389087677, "global_step": 623869, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.966981291770935, "global_step": 623870, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.103498697280884, "global_step": 623871, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0769622325897217, "global_step": 623872, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8978030681610107, "global_step": 623873, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.13565731048584, "global_step": 623874, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.990706205368042, "global_step": 623875, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9643447399139404, "global_step": 623876, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0243914127349854, "global_step": 623877, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9482884407043457, "global_step": 623878, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.997484803199768, "global_step": 623879, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0469861030578613, "global_step": 623880, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.049495220184326, "global_step": 623881, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9945849180221558, "global_step": 623882, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9557318687438965, "global_step": 623883, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.004415512084961, "global_step": 623884, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0268819332122803, "global_step": 623885, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.010948657989502, "global_step": 623886, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.961508870124817, "global_step": 623887, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.088073253631592, "global_step": 623888, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9076781272888184, "global_step": 623889, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9131762981414795, "global_step": 623890, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9877586364746094, "global_step": 623891, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0690414905548096, "global_step": 623892, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9883984327316284, "global_step": 623893, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9685581922531128, "global_step": 623894, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9899436235427856, "global_step": 623895, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9611872434616089, "global_step": 623896, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0585081577301025, "global_step": 623897, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.000847101211548, "global_step": 623898, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.991828203201294, "global_step": 623899, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.071371555328369, "global_step": 623900, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.009416103363037, "global_step": 623901, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9475446939468384, "global_step": 623902, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9974251985549927, "global_step": 623903, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.004483222961426, "global_step": 623904, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9150421619415283, "global_step": 623905, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9854661226272583, "global_step": 623906, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0179927349090576, "global_step": 623907, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0819590091705322, "global_step": 623908, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9649994373321533, "global_step": 623909, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.960638403892517, "global_step": 623910, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.028503656387329, "global_step": 623911, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0120046138763428, "global_step": 623912, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0410001277923584, "global_step": 623913, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0249156951904297, "global_step": 623914, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9563331604003906, "global_step": 623915, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0260324478149414, "global_step": 623916, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.035663604736328, "global_step": 623917, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.057880163192749, "global_step": 623918, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9839677810668945, "global_step": 623919, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9844123125076294, "global_step": 623920, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.036893844604492, "global_step": 623921, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9117867946624756, "global_step": 623922, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9994479417800903, "global_step": 623923, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9326339960098267, "global_step": 623924, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9829457998275757, "global_step": 623925, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.008875608444214, "global_step": 623926, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0201497077941895, "global_step": 623927, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.020139217376709, "global_step": 623928, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9060808420181274, "global_step": 623929, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9730415344238281, "global_step": 623930, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1257998943328857, "global_step": 623931, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9998726844787598, "global_step": 623932, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9613722562789917, "global_step": 623933, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1052207946777344, "global_step": 623934, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.991173505783081, "global_step": 623935, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0289063453674316, "global_step": 623936, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9806020259857178, "global_step": 623937, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0598878860473633, "global_step": 623938, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0273427963256836, "global_step": 623939, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0192596912384033, "global_step": 623940, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9495646953582764, "global_step": 623941, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9737237691879272, "global_step": 623942, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0373027324676514, "global_step": 623943, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.024451732635498, "global_step": 623944, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.000983238220215, "global_step": 623945, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0615439414978027, "global_step": 623946, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0627963542938232, "global_step": 623947, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1116323471069336, "global_step": 623948, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9808100461959839, "global_step": 623949, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9962111711502075, "global_step": 623950, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0185511112213135, "global_step": 623951, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9180467128753662, "global_step": 623952, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9447673559188843, "global_step": 623953, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0209953784942627, "global_step": 623954, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0301668643951416, "global_step": 623955, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0704400539398193, "global_step": 623956, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9970662593841553, "global_step": 623957, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0304102897644043, "global_step": 623958, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0530359745025635, "global_step": 623959, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9597833156585693, "global_step": 623960, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0126402378082275, "global_step": 623961, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.996987223625183, "global_step": 623962, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9448034763336182, "global_step": 623963, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.040785789489746, "global_step": 623964, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.008394479751587, "global_step": 623965, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9863746166229248, "global_step": 623966, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9544272422790527, "global_step": 623967, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0479583740234375, "global_step": 623968, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.971288800239563, "global_step": 623969, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9872252941131592, "global_step": 623970, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8974556922912598, "global_step": 623971, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9408341646194458, "global_step": 623972, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9911950826644897, "global_step": 623973, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9920802116394043, "global_step": 623974, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.002687454223633, "global_step": 623975, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.048835515975952, "global_step": 623976, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.001293420791626, "global_step": 623977, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0554707050323486, "global_step": 623978, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.10614275932312, "global_step": 623979, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9399869441986084, "global_step": 623980, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.031158208847046, "global_step": 623981, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9200907945632935, "global_step": 623982, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.043147087097168, "global_step": 623983, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.050518274307251, "global_step": 623984, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0829899311065674, "global_step": 623985, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9455986022949219, "global_step": 623986, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0378408432006836, "global_step": 623987, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.126406192779541, "global_step": 623988, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.960254192352295, "global_step": 623989, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0621838569641113, "global_step": 623990, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9322137832641602, "global_step": 623991, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9919427633285522, "global_step": 623992, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9845702648162842, "global_step": 623993, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9528391361236572, "global_step": 623994, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.093395233154297, "global_step": 623995, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9071099758148193, "global_step": 623996, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1018784046173096, "global_step": 623997, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.099177122116089, "global_step": 623998, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0189809799194336, "global_step": 623999, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0224881172180176, "global_step": 624000, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.989956021308899, "global_step": 624001, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0015382766723633, "global_step": 624002, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9535242319107056, "global_step": 624003, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9915343523025513, "global_step": 624004, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.020491123199463, "global_step": 624005, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0429818630218506, "global_step": 624006, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9870284795761108, "global_step": 624007, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.101651430130005, "global_step": 624008, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0668528079986572, "global_step": 624009, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0385425090789795, "global_step": 624010, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0141401290893555, "global_step": 624011, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.03517484664917, "global_step": 624012, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.987528920173645, "global_step": 624013, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0356340408325195, "global_step": 624014, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.955626130104065, "global_step": 624015, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9945076704025269, "global_step": 624016, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0128066539764404, "global_step": 624017, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.052079916000366, "global_step": 624018, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9924970865249634, "global_step": 624019, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9848843812942505, "global_step": 624020, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.078869342803955, "global_step": 624021, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.078078269958496, "global_step": 624022, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.027808427810669, "global_step": 624023, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.076798439025879, "global_step": 624024, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.101680278778076, "global_step": 624025, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0075905323028564, "global_step": 624026, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.993743658065796, "global_step": 624027, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.982001781463623, "global_step": 624028, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9764719009399414, "global_step": 624029, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9882506132125854, "global_step": 624030, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.985579252243042, "global_step": 624031, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.930422067642212, "global_step": 624032, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0852749347686768, "global_step": 624033, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0552892684936523, "global_step": 624034, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9555323123931885, "global_step": 624035, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9108549356460571, "global_step": 624036, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9845640659332275, "global_step": 624037, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.039893388748169, "global_step": 624038, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0121798515319824, "global_step": 624039, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9735157489776611, "global_step": 624040, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0475668907165527, "global_step": 624041, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.060523271560669, "global_step": 624042, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.965330958366394, "global_step": 624043, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0547523498535156, "global_step": 624044, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0106005668640137, "global_step": 624045, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0012149810791016, "global_step": 624046, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.015683889389038, "global_step": 624047, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9881134033203125, "global_step": 624048, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.953049659729004, "global_step": 624049, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.046818256378174, "global_step": 624050, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.010159969329834, "global_step": 624051, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.985141634941101, "global_step": 624052, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.007127523422241, "global_step": 624053, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9788451194763184, "global_step": 624054, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.15588116645813, "global_step": 624055, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9511826038360596, "global_step": 624056, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.993486762046814, "global_step": 624057, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0226542949676514, "global_step": 624058, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.001229763031006, "global_step": 624059, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9428521394729614, "global_step": 624060, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0181570053100586, "global_step": 624061, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0515024662017822, "global_step": 624062, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.98265540599823, "global_step": 624063, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0589404106140137, "global_step": 624064, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.089151382446289, "global_step": 624065, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9809863567352295, "global_step": 624066, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.02099609375, "global_step": 624067, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0319724082946777, "global_step": 624068, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9650321006774902, "global_step": 624069, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0512402057647705, "global_step": 624070, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.959981083869934, "global_step": 624071, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9597902297973633, "global_step": 624072, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0644397735595703, "global_step": 624073, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0604875087738037, "global_step": 624074, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8857855796813965, "global_step": 624075, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.050138235092163, "global_step": 624076, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0193898677825928, "global_step": 624077, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9772913455963135, "global_step": 624078, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0128610134124756, "global_step": 624079, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0532071590423584, "global_step": 624080, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.066429615020752, "global_step": 624081, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0531718730926514, "global_step": 624082, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9883240461349487, "global_step": 624083, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0496344566345215, "global_step": 624084, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.041477680206299, "global_step": 624085, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9274498224258423, "global_step": 624086, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.974280834197998, "global_step": 624087, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.106647253036499, "global_step": 624088, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.035352945327759, "global_step": 624089, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0629794597625732, "global_step": 624090, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9425455331802368, "global_step": 624091, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0453617572784424, "global_step": 624092, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.04532790184021, "global_step": 624093, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0033938884735107, "global_step": 624094, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9641720056533813, "global_step": 624095, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.007307291030884, "global_step": 624096, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.046880006790161, "global_step": 624097, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0073509216308594, "global_step": 624098, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.004988431930542, "global_step": 624099, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.011708974838257, "global_step": 624100, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.033879280090332, "global_step": 624101, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0482990741729736, "global_step": 624102, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9799622297286987, "global_step": 624103, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.031224250793457, "global_step": 624104, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0221073627471924, "global_step": 624105, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0169174671173096, "global_step": 624106, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9799785614013672, "global_step": 624107, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0685009956359863, "global_step": 624108, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.973928689956665, "global_step": 624109, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.016547679901123, "global_step": 624110, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0256125926971436, "global_step": 624111, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.048757553100586, "global_step": 624112, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9573476314544678, "global_step": 624113, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9758800268173218, "global_step": 624114, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.014817714691162, "global_step": 624115, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9693397283554077, "global_step": 624116, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9790306091308594, "global_step": 624117, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.929965615272522, "global_step": 624118, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9877045154571533, "global_step": 624119, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.056166172027588, "global_step": 624120, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.029794692993164, "global_step": 624121, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0663812160491943, "global_step": 624122, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9769411087036133, "global_step": 624123, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9931055307388306, "global_step": 624124, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0618090629577637, "global_step": 624125, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9365290403366089, "global_step": 624126, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.021315574645996, "global_step": 624127, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9881221055984497, "global_step": 624128, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.952802300453186, "global_step": 624129, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0316622257232666, "global_step": 624130, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0364229679107666, "global_step": 624131, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.011695384979248, "global_step": 624132, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.999432921409607, "global_step": 624133, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9380369186401367, "global_step": 624134, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.049908399581909, "global_step": 624135, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0093090534210205, "global_step": 624136, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9510371685028076, "global_step": 624137, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.015699863433838, "global_step": 624138, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0167789459228516, "global_step": 624139, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9544028043746948, "global_step": 624140, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0329055786132812, "global_step": 624141, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.005819082260132, "global_step": 624142, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0499260425567627, "global_step": 624143, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0100958347320557, "global_step": 624144, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0003714561462402, "global_step": 624145, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0011062622070312, "global_step": 624146, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.007122039794922, "global_step": 624147, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9592881202697754, "global_step": 624148, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.061502695083618, "global_step": 624149, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9442511796951294, "global_step": 624150, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9433977603912354, "global_step": 624151, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0345726013183594, "global_step": 624152, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0372204780578613, "global_step": 624153, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0900230407714844, "global_step": 624154, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.006143808364868, "global_step": 624155, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0097312927246094, "global_step": 624156, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0112388134002686, "global_step": 624157, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.024552822113037, "global_step": 624158, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0014028549194336, "global_step": 624159, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0344362258911133, "global_step": 624160, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9543790817260742, "global_step": 624161, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.032930612564087, "global_step": 624162, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9767670631408691, "global_step": 624163, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.032686233520508, "global_step": 624164, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9737812280654907, "global_step": 624165, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.937916874885559, "global_step": 624166, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9799188375473022, "global_step": 624167, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0028738975524902, "global_step": 624168, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9735298156738281, "global_step": 624169, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0399062633514404, "global_step": 624170, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.060303211212158, "global_step": 624171, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.004720449447632, "global_step": 624172, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.010171413421631, "global_step": 624173, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.03229022026062, "global_step": 624174, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.022449493408203, "global_step": 624175, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.02736496925354, "global_step": 624176, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0804905891418457, "global_step": 624177, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9873583316802979, "global_step": 624178, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9903879165649414, "global_step": 624179, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0486555099487305, "global_step": 624180, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0822789669036865, "global_step": 624181, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0963823795318604, "global_step": 624182, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.987290382385254, "global_step": 624183, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9832359552383423, "global_step": 624184, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9923564195632935, "global_step": 624185, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9870526790618896, "global_step": 624186, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0461087226867676, "global_step": 624187, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0640146732330322, "global_step": 624188, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.984188437461853, "global_step": 624189, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0194458961486816, "global_step": 624190, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9854724407196045, "global_step": 624191, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9460277557373047, "global_step": 624192, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9609460830688477, "global_step": 624193, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9283515214920044, "global_step": 624194, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.028641939163208, "global_step": 624195, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.989490032196045, "global_step": 624196, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0134358406066895, "global_step": 624197, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9675049781799316, "global_step": 624198, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0173141956329346, "global_step": 624199, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0087461471557617, "global_step": 624200, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.064314603805542, "global_step": 624201, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9586284160614014, "global_step": 624202, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0507476329803467, "global_step": 624203, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.014228105545044, "global_step": 624204, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9893321990966797, "global_step": 624205, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0373435020446777, "global_step": 624206, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0015976428985596, "global_step": 624207, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0173022747039795, "global_step": 624208, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9542577266693115, "global_step": 624209, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0076160430908203, "global_step": 624210, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.026270866394043, "global_step": 624211, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9869564771652222, "global_step": 624212, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9454524517059326, "global_step": 624213, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0396816730499268, "global_step": 624214, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.949270248413086, "global_step": 624215, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.995803713798523, "global_step": 624216, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9669501781463623, "global_step": 624217, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0213465690612793, "global_step": 624218, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.941221833229065, "global_step": 624219, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.904762625694275, "global_step": 624220, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.007934331893921, "global_step": 624221, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0929558277130127, "global_step": 624222, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.152024507522583, "global_step": 624223, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9908521175384521, "global_step": 624224, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0516154766082764, "global_step": 624225, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9875415563583374, "global_step": 624226, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.013143301010132, "global_step": 624227, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9705767631530762, "global_step": 624228, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9944032430648804, "global_step": 624229, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9751811027526855, "global_step": 624230, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.942481517791748, "global_step": 624231, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.962514042854309, "global_step": 624232, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9674327373504639, "global_step": 624233, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.063896656036377, "global_step": 624234, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0298855304718018, "global_step": 624235, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.036729097366333, "global_step": 624236, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.959113597869873, "global_step": 624237, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0525031089782715, "global_step": 624238, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.953994631767273, "global_step": 624239, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9776270389556885, "global_step": 624240, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9563761949539185, "global_step": 624241, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0891494750976562, "global_step": 624242, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0437004566192627, "global_step": 624243, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.909890055656433, "global_step": 624244, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9625625610351562, "global_step": 624245, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9119493961334229, "global_step": 624246, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9597618579864502, "global_step": 624247, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.992472767829895, "global_step": 624248, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.933140516281128, "global_step": 624249, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.093705415725708, "global_step": 624250, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.009495735168457, "global_step": 624251, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.037632465362549, "global_step": 624252, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.948012113571167, "global_step": 624253, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9276137351989746, "global_step": 624254, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.8709335327148438, "global_step": 624255, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0001285076141357, "global_step": 624256, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0828161239624023, "global_step": 624257, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9826147556304932, "global_step": 624258, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.002291679382324, "global_step": 624259, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.058283805847168, "global_step": 624260, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0331532955169678, "global_step": 624261, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9894641637802124, "global_step": 624262, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0298731327056885, "global_step": 624263, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.076221227645874, "global_step": 624264, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9688446521759033, "global_step": 624265, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0840256214141846, "global_step": 624266, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0296857357025146, "global_step": 624267, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9597638845443726, "global_step": 624268, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.944296956062317, "global_step": 624269, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.004859209060669, "global_step": 624270, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.003037214279175, "global_step": 624271, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.934653401374817, "global_step": 624272, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.021454095840454, "global_step": 624273, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.969719648361206, "global_step": 624274, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9713056087493896, "global_step": 624275, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0361721515655518, "global_step": 624276, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9281460046768188, "global_step": 624277, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.09123158454895, "global_step": 624278, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.022714376449585, "global_step": 624279, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.051647663116455, "global_step": 624280, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9974757432937622, "global_step": 624281, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9723976850509644, "global_step": 624282, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9833974838256836, "global_step": 624283, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9604116678237915, "global_step": 624284, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9694687128067017, "global_step": 624285, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0178558826446533, "global_step": 624286, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9105803966522217, "global_step": 624287, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9844328165054321, "global_step": 624288, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0418291091918945, "global_step": 624289, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.947008490562439, "global_step": 624290, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.982158899307251, "global_step": 624291, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0001983642578125, "global_step": 624292, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.991809368133545, "global_step": 624293, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.037304162979126, "global_step": 624294, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.054731845855713, "global_step": 624295, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.070983648300171, "global_step": 624296, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0018749237060547, "global_step": 624297, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0066335201263428, "global_step": 624298, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0246477127075195, "global_step": 624299, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1223413944244385, "global_step": 624300, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.886440634727478, "global_step": 624301, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.99170982837677, "global_step": 624302, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9748302698135376, "global_step": 624303, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9939273595809937, "global_step": 624304, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.982056736946106, "global_step": 624305, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9964107275009155, "global_step": 624306, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9238405227661133, "global_step": 624307, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9842066764831543, "global_step": 624308, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0154120922088623, "global_step": 624309, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0415055751800537, "global_step": 624310, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9970808029174805, "global_step": 624311, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9472488164901733, "global_step": 624312, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9184967279434204, "global_step": 624313, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.013324022293091, "global_step": 624314, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0346527099609375, "global_step": 624315, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9673223495483398, "global_step": 624316, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0400583744049072, "global_step": 624317, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9938205480575562, "global_step": 624318, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9280835390090942, "global_step": 624319, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.988191843032837, "global_step": 624320, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9262897968292236, "global_step": 624321, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9643504619598389, "global_step": 624322, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0744175910949707, "global_step": 624323, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9693635702133179, "global_step": 624324, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0082414150238037, "global_step": 624325, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9321843385696411, "global_step": 624326, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0523486137390137, "global_step": 624327, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0171170234680176, "global_step": 624328, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0167977809906006, "global_step": 624329, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9044181108474731, "global_step": 624330, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0239109992980957, "global_step": 624331, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9982954263687134, "global_step": 624332, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1128156185150146, "global_step": 624333, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.012108087539673, "global_step": 624334, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.056199312210083, "global_step": 624335, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9974957704544067, "global_step": 624336, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9567584991455078, "global_step": 624337, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0383803844451904, "global_step": 624338, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0657527446746826, "global_step": 624339, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9593689441680908, "global_step": 624340, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0762288570404053, "global_step": 624341, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.991584300994873, "global_step": 624342, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.047727108001709, "global_step": 624343, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.8894273042678833, "global_step": 624344, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.01315975189209, "global_step": 624345, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.041780471801758, "global_step": 624346, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.018496513366699, "global_step": 624347, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9819753170013428, "global_step": 624348, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.010162115097046, "global_step": 624349, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9578876495361328, "global_step": 624350, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.051525354385376, "global_step": 624351, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.076976776123047, "global_step": 624352, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9361622333526611, "global_step": 624353, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9971486330032349, "global_step": 624354, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9606564044952393, "global_step": 624355, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9677445888519287, "global_step": 624356, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0487561225891113, "global_step": 624357, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.021907329559326, "global_step": 624358, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9883321523666382, "global_step": 624359, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0321218967437744, "global_step": 624360, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0407402515411377, "global_step": 624361, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0293684005737305, "global_step": 624362, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.010892629623413, "global_step": 624363, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.038921594619751, "global_step": 624364, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9975608587265015, "global_step": 624365, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0025389194488525, "global_step": 624366, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.991670846939087, "global_step": 624367, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9853527545928955, "global_step": 624368, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9983820915222168, "global_step": 624369, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9885989427566528, "global_step": 624370, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.004338264465332, "global_step": 624371, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9366064071655273, "global_step": 624372, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.931376338005066, "global_step": 624373, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.032822847366333, "global_step": 624374, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.949802041053772, "global_step": 624375, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0246448516845703, "global_step": 624376, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9898217916488647, "global_step": 624377, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9465476274490356, "global_step": 624378, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.96392023563385, "global_step": 624379, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9816545248031616, "global_step": 624380, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1222763061523438, "global_step": 624381, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0421481132507324, "global_step": 624382, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.084169626235962, "global_step": 624383, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9195835590362549, "global_step": 624384, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0606560707092285, "global_step": 624385, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9609590768814087, "global_step": 624386, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9839253425598145, "global_step": 624387, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9504709243774414, "global_step": 624388, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9280920028686523, "global_step": 624389, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9614158868789673, "global_step": 624390, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.978304386138916, "global_step": 624391, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.924315094947815, "global_step": 624392, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9568225145339966, "global_step": 624393, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0123863220214844, "global_step": 624394, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0123138427734375, "global_step": 624395, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.8749821186065674, "global_step": 624396, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.056368112564087, "global_step": 624397, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0169520378112793, "global_step": 624398, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0009655952453613, "global_step": 624399, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.102158546447754, "global_step": 624400, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9152648448944092, "global_step": 624401, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9361622333526611, "global_step": 624402, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9926941394805908, "global_step": 624403, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0561718940734863, "global_step": 624404, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0591800212860107, "global_step": 624405, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9629297256469727, "global_step": 624406, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.913708209991455, "global_step": 624407, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9604042768478394, "global_step": 624408, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9769134521484375, "global_step": 624409, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9946035146713257, "global_step": 624410, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.022947311401367, "global_step": 624411, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.003737449645996, "global_step": 624412, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0206708908081055, "global_step": 624413, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9783117771148682, "global_step": 624414, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9639641046524048, "global_step": 624415, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9265151023864746, "global_step": 624416, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.001253128051758, "global_step": 624417, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.068326711654663, "global_step": 624418, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0129635334014893, "global_step": 624419, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.95546293258667, "global_step": 624420, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0044734477996826, "global_step": 624421, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0304970741271973, "global_step": 624422, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.046968460083008, "global_step": 624423, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9402683973312378, "global_step": 624424, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.055262804031372, "global_step": 624425, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0025758743286133, "global_step": 624426, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0360898971557617, "global_step": 624427, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9841835498809814, "global_step": 624428, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0330893993377686, "global_step": 624429, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9635796546936035, "global_step": 624430, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.991216778755188, "global_step": 624431, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.010511636734009, "global_step": 624432, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.003775119781494, "global_step": 624433, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.909787654876709, "global_step": 624434, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0370712280273438, "global_step": 624435, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9820308685302734, "global_step": 624436, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0551247596740723, "global_step": 624437, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0063114166259766, "global_step": 624438, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.946782112121582, "global_step": 624439, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0298104286193848, "global_step": 624440, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0734472274780273, "global_step": 624441, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.041496515274048, "global_step": 624442, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.954542875289917, "global_step": 624443, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9555059671401978, "global_step": 624444, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9768623113632202, "global_step": 624445, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.999632477760315, "global_step": 624446, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0270979404449463, "global_step": 624447, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.01785945892334, "global_step": 624448, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9913294315338135, "global_step": 624449, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0854222774505615, "global_step": 624450, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0074219703674316, "global_step": 624451, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.008948802947998, "global_step": 624452, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9604493379592896, "global_step": 624453, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9514356851577759, "global_step": 624454, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0219459533691406, "global_step": 624455, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9505858421325684, "global_step": 624456, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9254257678985596, "global_step": 624457, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0352625846862793, "global_step": 624458, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.970246434211731, "global_step": 624459, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0009233951568604, "global_step": 624460, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9493184089660645, "global_step": 624461, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9594966173171997, "global_step": 624462, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0341415405273438, "global_step": 624463, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.935535192489624, "global_step": 624464, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9498213529586792, "global_step": 624465, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9671906232833862, "global_step": 624466, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0623528957366943, "global_step": 624467, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.049992799758911, "global_step": 624468, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.023149013519287, "global_step": 624469, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9995344877243042, "global_step": 624470, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0375845432281494, "global_step": 624471, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0495657920837402, "global_step": 624472, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0107858180999756, "global_step": 624473, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.999694585800171, "global_step": 624474, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.014875650405884, "global_step": 624475, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.017371892929077, "global_step": 624476, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9969173669815063, "global_step": 624477, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9711394309997559, "global_step": 624478, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.031010866165161, "global_step": 624479, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9633408784866333, "global_step": 624480, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9762845039367676, "global_step": 624481, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0121877193450928, "global_step": 624482, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.047945261001587, "global_step": 624483, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.037691831588745, "global_step": 624484, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0697269439697266, "global_step": 624485, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.858377456665039, "global_step": 624486, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9730632305145264, "global_step": 624487, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.029721736907959, "global_step": 624488, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9967061281204224, "global_step": 624489, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.975451111793518, "global_step": 624490, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9408899545669556, "global_step": 624491, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.042243242263794, "global_step": 624492, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9735772609710693, "global_step": 624493, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.006258487701416, "global_step": 624494, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.035130739212036, "global_step": 624495, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.987247109413147, "global_step": 624496, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0746848583221436, "global_step": 624497, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.936517357826233, "global_step": 624498, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.054252862930298, "global_step": 624499, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.8972558975219727, "global_step": 624500, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9381953477859497, "global_step": 624501, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.055450201034546, "global_step": 624502, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9764506816864014, "global_step": 624503, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0168886184692383, "global_step": 624504, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.00140643119812, "global_step": 624505, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.013913154602051, "global_step": 624506, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0438685417175293, "global_step": 624507, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0628912448883057, "global_step": 624508, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.07073974609375, "global_step": 624509, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0358705520629883, "global_step": 624510, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0014278888702393, "global_step": 624511, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.009887456893921, "global_step": 624512, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0658602714538574, "global_step": 624513, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0364058017730713, "global_step": 624514, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9786717891693115, "global_step": 624515, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9001950025558472, "global_step": 624516, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0223610401153564, "global_step": 624517, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0097954273223877, "global_step": 624518, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.004725933074951, "global_step": 624519, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9372187852859497, "global_step": 624520, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9963501691818237, "global_step": 624521, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0136945247650146, "global_step": 624522, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9572315216064453, "global_step": 624523, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0177793502807617, "global_step": 624524, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9708532094955444, "global_step": 624525, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0197081565856934, "global_step": 624526, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.061868190765381, "global_step": 624527, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0406229496002197, "global_step": 624528, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.033881902694702, "global_step": 624529, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9856858253479004, "global_step": 624530, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9749224185943604, "global_step": 624531, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.029189348220825, "global_step": 624532, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.944179892539978, "global_step": 624533, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0212244987487793, "global_step": 624534, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0338311195373535, "global_step": 624535, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9726006984710693, "global_step": 624536, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.01711106300354, "global_step": 624537, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1521027088165283, "global_step": 624538, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9379593133926392, "global_step": 624539, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.976456642150879, "global_step": 624540, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9590345621109009, "global_step": 624541, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0566182136535645, "global_step": 624542, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0008161067962646, "global_step": 624543, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0157012939453125, "global_step": 624544, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9432214498519897, "global_step": 624545, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9627203941345215, "global_step": 624546, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9797182083129883, "global_step": 624547, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0280070304870605, "global_step": 624548, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0307297706604004, "global_step": 624549, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0862741470336914, "global_step": 624550, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.022853374481201, "global_step": 624551, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0117979049682617, "global_step": 624552, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.075664758682251, "global_step": 624553, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9529329538345337, "global_step": 624554, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9834407567977905, "global_step": 624555, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9918981790542603, "global_step": 624556, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9783732891082764, "global_step": 624557, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0001518726348877, "global_step": 624558, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9833571910858154, "global_step": 624559, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0183236598968506, "global_step": 624560, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.006577730178833, "global_step": 624561, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.018927812576294, "global_step": 624562, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0848166942596436, "global_step": 624563, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0127265453338623, "global_step": 624564, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0693371295928955, "global_step": 624565, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0583670139312744, "global_step": 624566, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.045637607574463, "global_step": 624567, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9285846948623657, "global_step": 624568, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0441322326660156, "global_step": 624569, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0082626342773438, "global_step": 624570, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.097212553024292, "global_step": 624571, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9594249725341797, "global_step": 624572, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.033018112182617, "global_step": 624573, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.865272045135498, "global_step": 624574, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0728917121887207, "global_step": 624575, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9856314659118652, "global_step": 624576, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9069149494171143, "global_step": 624577, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9860706329345703, "global_step": 624578, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.020488739013672, "global_step": 624579, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9383772611618042, "global_step": 624580, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0246567726135254, "global_step": 624581, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0162954330444336, "global_step": 624582, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0935802459716797, "global_step": 624583, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9473497867584229, "global_step": 624584, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.060673475265503, "global_step": 624585, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.962510585784912, "global_step": 624586, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9731762409210205, "global_step": 624587, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9975305795669556, "global_step": 624588, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9502832889556885, "global_step": 624589, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.957120418548584, "global_step": 624590, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9602141380310059, "global_step": 624591, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9930025339126587, "global_step": 624592, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0599727630615234, "global_step": 624593, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.970729947090149, "global_step": 624594, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9011656045913696, "global_step": 624595, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0100576877593994, "global_step": 624596, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9720051288604736, "global_step": 624597, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9040344953536987, "global_step": 624598, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.97013258934021, "global_step": 624599, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0020134449005127, "global_step": 624600, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9589643478393555, "global_step": 624601, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.993356704711914, "global_step": 624602, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9765969514846802, "global_step": 624603, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.013634443283081, "global_step": 624604, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9616738557815552, "global_step": 624605, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.051396608352661, "global_step": 624606, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9574544429779053, "global_step": 624607, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.027557849884033, "global_step": 624608, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9974284172058105, "global_step": 624609, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.993912935256958, "global_step": 624610, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0071723461151123, "global_step": 624611, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.999430537223816, "global_step": 624612, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.972915768623352, "global_step": 624613, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.964180827140808, "global_step": 624614, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9565496444702148, "global_step": 624615, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0729286670684814, "global_step": 624616, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9855308532714844, "global_step": 624617, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0035293102264404, "global_step": 624618, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9786440134048462, "global_step": 624619, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9789999723434448, "global_step": 624620, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.090067148208618, "global_step": 624621, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9995980262756348, "global_step": 624622, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.030977249145508, "global_step": 624623, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9514700174331665, "global_step": 624624, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0843584537506104, "global_step": 624625, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.043109893798828, "global_step": 624626, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9513777494430542, "global_step": 624627, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1065728664398193, "global_step": 624628, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0430076122283936, "global_step": 624629, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.992677927017212, "global_step": 624630, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0533816814422607, "global_step": 624631, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9684021472930908, "global_step": 624632, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9384615421295166, "global_step": 624633, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0324628353118896, "global_step": 624634, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.024958848953247, "global_step": 624635, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.103963851928711, "global_step": 624636, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9962923526763916, "global_step": 624637, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.052837371826172, "global_step": 624638, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0736114978790283, "global_step": 624639, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0066165924072266, "global_step": 624640, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9959101676940918, "global_step": 624641, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0262417793273926, "global_step": 624642, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.061666250228882, "global_step": 624643, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9654524326324463, "global_step": 624644, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0131938457489014, "global_step": 624645, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0212035179138184, "global_step": 624646, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.002889394760132, "global_step": 624647, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9785568714141846, "global_step": 624648, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9763625860214233, "global_step": 624649, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.952778697013855, "global_step": 624650, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0373644828796387, "global_step": 624651, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.986973762512207, "global_step": 624652, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9716079235076904, "global_step": 624653, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.007683277130127, "global_step": 624654, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9693313837051392, "global_step": 624655, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0886361598968506, "global_step": 624656, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.043369770050049, "global_step": 624657, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9457414150238037, "global_step": 624658, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9535202980041504, "global_step": 624659, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.072948455810547, "global_step": 624660, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0106990337371826, "global_step": 624661, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9953386783599854, "global_step": 624662, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0403926372528076, "global_step": 624663, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.075136184692383, "global_step": 624664, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9571330547332764, "global_step": 624665, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9629944562911987, "global_step": 624666, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.955528736114502, "global_step": 624667, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9797598123550415, "global_step": 624668, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9818705320358276, "global_step": 624669, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0153615474700928, "global_step": 624670, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0320940017700195, "global_step": 624671, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9960789680480957, "global_step": 624672, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.928545594215393, "global_step": 624673, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.008455514907837, "global_step": 624674, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9771859645843506, "global_step": 624675, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9788107872009277, "global_step": 624676, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.032087564468384, "global_step": 624677, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0248208045959473, "global_step": 624678, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.012826919555664, "global_step": 624679, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0093979835510254, "global_step": 624680, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.974320888519287, "global_step": 624681, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9935582876205444, "global_step": 624682, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9686992168426514, "global_step": 624683, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.002981662750244, "global_step": 624684, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9788472652435303, "global_step": 624685, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.015801191329956, "global_step": 624686, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0160748958587646, "global_step": 624687, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.917549967765808, "global_step": 624688, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9681446552276611, "global_step": 624689, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9781510829925537, "global_step": 624690, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.010657787322998, "global_step": 624691, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.033561944961548, "global_step": 624692, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9506003856658936, "global_step": 624693, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0682759284973145, "global_step": 624694, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9874364137649536, "global_step": 624695, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0811851024627686, "global_step": 624696, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9758508205413818, "global_step": 624697, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.049178123474121, "global_step": 624698, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9379723072052002, "global_step": 624699, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.025864601135254, "global_step": 624700, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9779341220855713, "global_step": 624701, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.033651828765869, "global_step": 624702, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9956618547439575, "global_step": 624703, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.070284605026245, "global_step": 624704, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9969146251678467, "global_step": 624705, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9631952047348022, "global_step": 624706, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9963606595993042, "global_step": 624707, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0600028038024902, "global_step": 624708, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0092051029205322, "global_step": 624709, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0255794525146484, "global_step": 624710, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.003671407699585, "global_step": 624711, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0344996452331543, "global_step": 624712, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0448451042175293, "global_step": 624713, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0245392322540283, "global_step": 624714, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.017045497894287, "global_step": 624715, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.048593521118164, "global_step": 624716, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0106866359710693, "global_step": 624717, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9948859214782715, "global_step": 624718, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0377683639526367, "global_step": 624719, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.983467936515808, "global_step": 624720, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9377235174179077, "global_step": 624721, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0701510906219482, "global_step": 624722, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0147855281829834, "global_step": 624723, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9913536310195923, "global_step": 624724, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.977026104927063, "global_step": 624725, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9750878810882568, "global_step": 624726, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0523080825805664, "global_step": 624727, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.97823166847229, "global_step": 624728, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0425007343292236, "global_step": 624729, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.024531126022339, "global_step": 624730, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.012068033218384, "global_step": 624731, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.010615825653076, "global_step": 624732, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0163328647613525, "global_step": 624733, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.964430570602417, "global_step": 624734, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.957725167274475, "global_step": 624735, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.019534111022949, "global_step": 624736, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0572400093078613, "global_step": 624737, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9867963790893555, "global_step": 624738, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0154974460601807, "global_step": 624739, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.065911054611206, "global_step": 624740, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9590740203857422, "global_step": 624741, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0664217472076416, "global_step": 624742, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.075772285461426, "global_step": 624743, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.041997194290161, "global_step": 624744, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9694044589996338, "global_step": 624745, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9437298774719238, "global_step": 624746, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.014986038208008, "global_step": 624747, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.005685806274414, "global_step": 624748, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0618112087249756, "global_step": 624749, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.015554666519165, "global_step": 624750, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9823592901229858, "global_step": 624751, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9719905853271484, "global_step": 624752, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0363481044769287, "global_step": 624753, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.055126905441284, "global_step": 624754, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9950053691864014, "global_step": 624755, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1135010719299316, "global_step": 624756, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0517287254333496, "global_step": 624757, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.956775426864624, "global_step": 624758, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.028505802154541, "global_step": 624759, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9906376600265503, "global_step": 624760, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9650148153305054, "global_step": 624761, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9911906719207764, "global_step": 624762, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9845895767211914, "global_step": 624763, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.031761884689331, "global_step": 624764, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9840660095214844, "global_step": 624765, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0061936378479004, "global_step": 624766, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0186386108398438, "global_step": 624767, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0672502517700195, "global_step": 624768, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.024714708328247, "global_step": 624769, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.017611265182495, "global_step": 624770, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0033130645751953, "global_step": 624771, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0063090324401855, "global_step": 624772, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.969283103942871, "global_step": 624773, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0339748859405518, "global_step": 624774, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9645107984542847, "global_step": 624775, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9360939264297485, "global_step": 624776, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.001661539077759, "global_step": 624777, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0974276065826416, "global_step": 624778, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.007370710372925, "global_step": 624779, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0114359855651855, "global_step": 624780, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.01892352104187, "global_step": 624781, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0346617698669434, "global_step": 624782, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9440041780471802, "global_step": 624783, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.004870653152466, "global_step": 624784, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.989236831665039, "global_step": 624785, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0178115367889404, "global_step": 624786, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0271570682525635, "global_step": 624787, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9699500799179077, "global_step": 624788, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9469060897827148, "global_step": 624789, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0507285594940186, "global_step": 624790, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9850492477416992, "global_step": 624791, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.085700273513794, "global_step": 624792, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.984048843383789, "global_step": 624793, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9944936037063599, "global_step": 624794, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0315983295440674, "global_step": 624795, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9812721014022827, "global_step": 624796, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9319099187850952, "global_step": 624797, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.015183687210083, "global_step": 624798, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9599967002868652, "global_step": 624799, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0455946922302246, "global_step": 624800, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9659464359283447, "global_step": 624801, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.000023126602173, "global_step": 624802, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9644581079483032, "global_step": 624803, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.02468204498291, "global_step": 624804, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.948678731918335, "global_step": 624805, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0423977375030518, "global_step": 624806, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.8492852449417114, "global_step": 624807, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9896154403686523, "global_step": 624808, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0140795707702637, "global_step": 624809, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9894990921020508, "global_step": 624810, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.8997085094451904, "global_step": 624811, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0289034843444824, "global_step": 624812, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0077502727508545, "global_step": 624813, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9650161266326904, "global_step": 624814, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1061465740203857, "global_step": 624815, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0951008796691895, "global_step": 624816, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0107734203338623, "global_step": 624817, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9719277620315552, "global_step": 624818, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9392184019088745, "global_step": 624819, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9978985786437988, "global_step": 624820, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.025783061981201, "global_step": 624821, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.004835367202759, "global_step": 624822, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.8678499460220337, "global_step": 624823, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.013353109359741, "global_step": 624824, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.102336883544922, "global_step": 624825, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9290227890014648, "global_step": 624826, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.978329062461853, "global_step": 624827, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.000612497329712, "global_step": 624828, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0041651725769043, "global_step": 624829, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.01090931892395, "global_step": 624830, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.059870958328247, "global_step": 624831, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.033083915710449, "global_step": 624832, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0058839321136475, "global_step": 624833, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9487048387527466, "global_step": 624834, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9529688358306885, "global_step": 624835, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9993994235992432, "global_step": 624836, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.039328098297119, "global_step": 624837, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9881209135055542, "global_step": 624838, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9071581363677979, "global_step": 624839, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9455032348632812, "global_step": 624840, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0691187381744385, "global_step": 624841, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.969236969947815, "global_step": 624842, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0360617637634277, "global_step": 624843, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0292084217071533, "global_step": 624844, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.00370192527771, "global_step": 624845, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0195844173431396, "global_step": 624846, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0232508182525635, "global_step": 624847, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.016779899597168, "global_step": 624848, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.031773328781128, "global_step": 624849, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.8660110235214233, "global_step": 624850, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0437560081481934, "global_step": 624851, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9716169834136963, "global_step": 624852, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0277321338653564, "global_step": 624853, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0156021118164062, "global_step": 624854, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9930000305175781, "global_step": 624855, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9634275436401367, "global_step": 624856, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.009718179702759, "global_step": 624857, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.098115921020508, "global_step": 624858, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9717470407485962, "global_step": 624859, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9831675291061401, "global_step": 624860, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.966125726699829, "global_step": 624861, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.000028371810913, "global_step": 624862, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9700677394866943, "global_step": 624863, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.046252965927124, "global_step": 624864, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9709941148757935, "global_step": 624865, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.004237174987793, "global_step": 624866, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9757148027420044, "global_step": 624867, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0418097972869873, "global_step": 624868, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.02811861038208, "global_step": 624869, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.047327995300293, "global_step": 624870, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9849307537078857, "global_step": 624871, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.073807954788208, "global_step": 624872, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9828583002090454, "global_step": 624873, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.022639036178589, "global_step": 624874, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0762200355529785, "global_step": 624875, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.042173147201538, "global_step": 624876, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0015978813171387, "global_step": 624877, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.945482850074768, "global_step": 624878, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9676278829574585, "global_step": 624879, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0004494190216064, "global_step": 624880, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.8878326416015625, "global_step": 624881, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0267603397369385, "global_step": 624882, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9244377613067627, "global_step": 624883, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9822971820831299, "global_step": 624884, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0201802253723145, "global_step": 624885, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.078509569168091, "global_step": 624886, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0110182762145996, "global_step": 624887, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9193183183670044, "global_step": 624888, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.014045476913452, "global_step": 624889, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9547817707061768, "global_step": 624890, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1216423511505127, "global_step": 624891, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.075565814971924, "global_step": 624892, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.051542043685913, "global_step": 624893, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9633322954177856, "global_step": 624894, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9549263715744019, "global_step": 624895, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9848922491073608, "global_step": 624896, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9968273639678955, "global_step": 624897, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9428225755691528, "global_step": 624898, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.969016671180725, "global_step": 624899, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9392035007476807, "global_step": 624900, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0495059490203857, "global_step": 624901, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.022237777709961, "global_step": 624902, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.043487787246704, "global_step": 624903, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0877652168273926, "global_step": 624904, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9620792865753174, "global_step": 624905, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9797624349594116, "global_step": 624906, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0028741359710693, "global_step": 624907, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.044417142868042, "global_step": 624908, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9727444648742676, "global_step": 624909, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0120575428009033, "global_step": 624910, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.011870861053467, "global_step": 624911, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9856626987457275, "global_step": 624912, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9898678064346313, "global_step": 624913, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0215954780578613, "global_step": 624914, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.004422903060913, "global_step": 624915, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9853016138076782, "global_step": 624916, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0031161308288574, "global_step": 624917, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9889930486679077, "global_step": 624918, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.037752866744995, "global_step": 624919, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.986511468887329, "global_step": 624920, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9954843521118164, "global_step": 624921, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9916226863861084, "global_step": 624922, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.034165859222412, "global_step": 624923, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.922251582145691, "global_step": 624924, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9585243463516235, "global_step": 624925, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0212507247924805, "global_step": 624926, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.040024518966675, "global_step": 624927, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9613182544708252, "global_step": 624928, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0628201961517334, "global_step": 624929, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9758570194244385, "global_step": 624930, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0287342071533203, "global_step": 624931, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.044719934463501, "global_step": 624932, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0216073989868164, "global_step": 624933, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0028953552246094, "global_step": 624934, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0413448810577393, "global_step": 624935, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9572125673294067, "global_step": 624936, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.11848521232605, "global_step": 624937, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.009927988052368, "global_step": 624938, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0555543899536133, "global_step": 624939, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.005275249481201, "global_step": 624940, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0056886672973633, "global_step": 624941, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0218729972839355, "global_step": 624942, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0158607959747314, "global_step": 624943, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1016364097595215, "global_step": 624944, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9723389148712158, "global_step": 624945, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.069774627685547, "global_step": 624946, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.060272693634033, "global_step": 624947, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.078244686126709, "global_step": 624948, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9984080791473389, "global_step": 624949, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9394792318344116, "global_step": 624950, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9771053791046143, "global_step": 624951, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0293831825256348, "global_step": 624952, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9489165544509888, "global_step": 624953, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9807889461517334, "global_step": 624954, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.02349853515625, "global_step": 624955, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.019759178161621, "global_step": 624956, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0821127891540527, "global_step": 624957, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0031330585479736, "global_step": 624958, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0309813022613525, "global_step": 624959, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9657249450683594, "global_step": 624960, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.14418363571167, "global_step": 624961, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.034135103225708, "global_step": 624962, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.949885606765747, "global_step": 624963, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0088326930999756, "global_step": 624964, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0276973247528076, "global_step": 624965, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0768990516662598, "global_step": 624966, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.030195713043213, "global_step": 624967, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.038825035095215, "global_step": 624968, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0146520137786865, "global_step": 624969, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9692734479904175, "global_step": 624970, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.039417266845703, "global_step": 624971, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0336809158325195, "global_step": 624972, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9255350828170776, "global_step": 624973, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9957445859909058, "global_step": 624974, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0059027671813965, "global_step": 624975, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9886544942855835, "global_step": 624976, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.039555549621582, "global_step": 624977, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.031832218170166, "global_step": 624978, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.032874584197998, "global_step": 624979, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.979440689086914, "global_step": 624980, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9428598880767822, "global_step": 624981, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.053091526031494, "global_step": 624982, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.976151466369629, "global_step": 624983, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.006413459777832, "global_step": 624984, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0214028358459473, "global_step": 624985, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9242795705795288, "global_step": 624986, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.054445505142212, "global_step": 624987, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0743019580841064, "global_step": 624988, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.918200135231018, "global_step": 624989, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.992285132408142, "global_step": 624990, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9653937816619873, "global_step": 624991, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.105851411819458, "global_step": 624992, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0515925884246826, "global_step": 624993, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0370495319366455, "global_step": 624994, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0577850341796875, "global_step": 624995, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.013507604598999, "global_step": 624996, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0548038482666016, "global_step": 624997, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.005934715270996, "global_step": 624998, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0671746730804443, "global_step": 624999, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9494102001190186, "global_step": 625000, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.095306873321533, "global_step": 625001, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.037440299987793, "global_step": 625002, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.924145221710205, "global_step": 625003, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9900583028793335, "global_step": 625004, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0401809215545654, "global_step": 625005, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0594570636749268, "global_step": 625006, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.046987533569336, "global_step": 625007, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0341827869415283, "global_step": 625008, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9740239381790161, "global_step": 625009, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0082950592041016, "global_step": 625010, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9897136688232422, "global_step": 625011, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9337222576141357, "global_step": 625012, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0613298416137695, "global_step": 625013, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.990833044052124, "global_step": 625014, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.977290153503418, "global_step": 625015, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.00016188621521, "global_step": 625016, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0067296028137207, "global_step": 625017, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0191309452056885, "global_step": 625018, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.028958559036255, "global_step": 625019, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9742940664291382, "global_step": 625020, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0036308765411377, "global_step": 625021, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0978338718414307, "global_step": 625022, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.91799795627594, "global_step": 625023, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0710535049438477, "global_step": 625024, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0140788555145264, "global_step": 625025, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1044156551361084, "global_step": 625026, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9503222703933716, "global_step": 625027, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9826829433441162, "global_step": 625028, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9957042932510376, "global_step": 625029, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0067760944366455, "global_step": 625030, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.038429021835327, "global_step": 625031, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0738472938537598, "global_step": 625032, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0199179649353027, "global_step": 625033, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0344274044036865, "global_step": 625034, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.01397442817688, "global_step": 625035, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.95750093460083, "global_step": 625036, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.060410737991333, "global_step": 625037, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.039191722869873, "global_step": 625038, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0446407794952393, "global_step": 625039, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0623607635498047, "global_step": 625040, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9890882968902588, "global_step": 625041, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9374613761901855, "global_step": 625042, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0021212100982666, "global_step": 625043, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9192172288894653, "global_step": 625044, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0256125926971436, "global_step": 625045, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0239129066467285, "global_step": 625046, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.952050805091858, "global_step": 625047, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.980449914932251, "global_step": 625048, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9753698110580444, "global_step": 625049, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0231704711914062, "global_step": 625050, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9595463275909424, "global_step": 625051, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0239827632904053, "global_step": 625052, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.055593967437744, "global_step": 625053, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9988406896591187, "global_step": 625054, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9510719776153564, "global_step": 625055, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9800851345062256, "global_step": 625056, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.011169910430908, "global_step": 625057, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9927150011062622, "global_step": 625058, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0372865200042725, "global_step": 625059, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9790136814117432, "global_step": 625060, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9537029266357422, "global_step": 625061, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9622552394866943, "global_step": 625062, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0860097408294678, "global_step": 625063, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9864145517349243, "global_step": 625064, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.038388252258301, "global_step": 625065, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.006509304046631, "global_step": 625066, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.082606077194214, "global_step": 625067, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0592851638793945, "global_step": 625068, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0181143283843994, "global_step": 625069, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.004194736480713, "global_step": 625070, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9334399700164795, "global_step": 625071, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9385168552398682, "global_step": 625072, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.048304557800293, "global_step": 625073, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.047405242919922, "global_step": 625074, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.037940502166748, "global_step": 625075, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0823872089385986, "global_step": 625076, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.982646107673645, "global_step": 625077, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9777212142944336, "global_step": 625078, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.938044548034668, "global_step": 625079, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.061552047729492, "global_step": 625080, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0304768085479736, "global_step": 625081, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.999237060546875, "global_step": 625082, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9737067222595215, "global_step": 625083, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.095416307449341, "global_step": 625084, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9742462635040283, "global_step": 625085, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0180466175079346, "global_step": 625086, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9856820106506348, "global_step": 625087, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.013331174850464, "global_step": 625088, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.979743242263794, "global_step": 625089, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9516875743865967, "global_step": 625090, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.007402181625366, "global_step": 625091, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9626599550247192, "global_step": 625092, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9898254871368408, "global_step": 625093, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.998502254486084, "global_step": 625094, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.123007297515869, "global_step": 625095, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.969438910484314, "global_step": 625096, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9136401414871216, "global_step": 625097, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.987520694732666, "global_step": 625098, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0483710765838623, "global_step": 625099, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.02227783203125, "global_step": 625100, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9949339628219604, "global_step": 625101, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.950812816619873, "global_step": 625102, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0501742362976074, "global_step": 625103, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1064324378967285, "global_step": 625104, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.959438443183899, "global_step": 625105, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9762598276138306, "global_step": 625106, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.988641619682312, "global_step": 625107, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0215539932250977, "global_step": 625108, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9432404041290283, "global_step": 625109, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.032710075378418, "global_step": 625110, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0601062774658203, "global_step": 625111, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0116844177246094, "global_step": 625112, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.053946018218994, "global_step": 625113, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.026834487915039, "global_step": 625114, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9172989130020142, "global_step": 625115, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.004378080368042, "global_step": 625116, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9753572940826416, "global_step": 625117, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0032052993774414, "global_step": 625118, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9840527772903442, "global_step": 625119, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9748263359069824, "global_step": 625120, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.948994755744934, "global_step": 625121, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9361741542816162, "global_step": 625122, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9558025598526, "global_step": 625123, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.952598214149475, "global_step": 625124, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0942928791046143, "global_step": 625125, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.071376323699951, "global_step": 625126, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0217537879943848, "global_step": 625127, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9520366191864014, "global_step": 625128, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.049391269683838, "global_step": 625129, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9749714136123657, "global_step": 625130, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.054049253463745, "global_step": 625131, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9441226720809937, "global_step": 625132, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9945355653762817, "global_step": 625133, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0633370876312256, "global_step": 625134, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.931777834892273, "global_step": 625135, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9106500148773193, "global_step": 625136, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.003356456756592, "global_step": 625137, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.926801323890686, "global_step": 625138, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9400800466537476, "global_step": 625139, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8765101432800293, "global_step": 625140, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8931219577789307, "global_step": 625141, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.000549077987671, "global_step": 625142, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.042496681213379, "global_step": 625143, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9907931089401245, "global_step": 625144, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9746061563491821, "global_step": 625145, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9343990087509155, "global_step": 625146, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.975488305091858, "global_step": 625147, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9663676023483276, "global_step": 625148, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0916080474853516, "global_step": 625149, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0012741088867188, "global_step": 625150, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9709136486053467, "global_step": 625151, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9855616092681885, "global_step": 625152, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0607523918151855, "global_step": 625153, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9494026899337769, "global_step": 625154, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8627924919128418, "global_step": 625155, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.000843048095703, "global_step": 625156, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9515963792800903, "global_step": 625157, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0402021408081055, "global_step": 625158, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9200316667556763, "global_step": 625159, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0228159427642822, "global_step": 625160, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.06704044342041, "global_step": 625161, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9156107902526855, "global_step": 625162, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0602784156799316, "global_step": 625163, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8854169845581055, "global_step": 625164, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.007133960723877, "global_step": 625165, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9363056421279907, "global_step": 625166, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.987874984741211, "global_step": 625167, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.959625005722046, "global_step": 625168, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.968347191810608, "global_step": 625169, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.042503595352173, "global_step": 625170, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9780313968658447, "global_step": 625171, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.989864468574524, "global_step": 625172, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1271989345550537, "global_step": 625173, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9088332653045654, "global_step": 625174, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0165462493896484, "global_step": 625175, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9473423957824707, "global_step": 625176, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.013963460922241, "global_step": 625177, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9811204671859741, "global_step": 625178, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.956830382347107, "global_step": 625179, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8678816556930542, "global_step": 625180, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9873310327529907, "global_step": 625181, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8687022924423218, "global_step": 625182, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9891210794448853, "global_step": 625183, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0164735317230225, "global_step": 625184, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0484371185302734, "global_step": 625185, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9622807502746582, "global_step": 625186, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9073283672332764, "global_step": 625187, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9766196012496948, "global_step": 625188, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9382981061935425, "global_step": 625189, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9652421474456787, "global_step": 625190, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.034332513809204, "global_step": 625191, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9231120347976685, "global_step": 625192, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.006038188934326, "global_step": 625193, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0160019397735596, "global_step": 625194, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0445711612701416, "global_step": 625195, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9861990213394165, "global_step": 625196, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.037109613418579, "global_step": 625197, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.05930233001709, "global_step": 625198, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.983708381652832, "global_step": 625199, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9680663347244263, "global_step": 625200, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0187008380889893, "global_step": 625201, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0167365074157715, "global_step": 625202, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0594592094421387, "global_step": 625203, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0557737350463867, "global_step": 625204, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.976462483406067, "global_step": 625205, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.99160897731781, "global_step": 625206, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8955578804016113, "global_step": 625207, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0181047916412354, "global_step": 625208, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9346745014190674, "global_step": 625209, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0063493251800537, "global_step": 625210, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9741361141204834, "global_step": 625211, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0487592220306396, "global_step": 625212, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9739047288894653, "global_step": 625213, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9101500511169434, "global_step": 625214, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9492567777633667, "global_step": 625215, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9365981817245483, "global_step": 625216, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9828039407730103, "global_step": 625217, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9436503648757935, "global_step": 625218, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0543220043182373, "global_step": 625219, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9867522716522217, "global_step": 625220, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.984420895576477, "global_step": 625221, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0022401809692383, "global_step": 625222, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.006232500076294, "global_step": 625223, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0024688243865967, "global_step": 625224, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9758446216583252, "global_step": 625225, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0580172538757324, "global_step": 625226, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0029990673065186, "global_step": 625227, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0429461002349854, "global_step": 625228, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.013522148132324, "global_step": 625229, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0451009273529053, "global_step": 625230, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0594398975372314, "global_step": 625231, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9808484315872192, "global_step": 625232, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.012887477874756, "global_step": 625233, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9873157739639282, "global_step": 625234, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.909024715423584, "global_step": 625235, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0408132076263428, "global_step": 625236, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0200440883636475, "global_step": 625237, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.019986629486084, "global_step": 625238, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0004303455352783, "global_step": 625239, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9484994411468506, "global_step": 625240, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.990679144859314, "global_step": 625241, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.022341012954712, "global_step": 625242, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9524872303009033, "global_step": 625243, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9754841327667236, "global_step": 625244, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0408031940460205, "global_step": 625245, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9147337675094604, "global_step": 625246, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.058382987976074, "global_step": 625247, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.984217882156372, "global_step": 625248, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.987838864326477, "global_step": 625249, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.013007640838623, "global_step": 625250, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9786911010742188, "global_step": 625251, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.043219566345215, "global_step": 625252, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.000889301300049, "global_step": 625253, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.073690891265869, "global_step": 625254, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0218403339385986, "global_step": 625255, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9892150163650513, "global_step": 625256, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9612208604812622, "global_step": 625257, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.028655767440796, "global_step": 625258, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9888277053833008, "global_step": 625259, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0370194911956787, "global_step": 625260, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.972003698348999, "global_step": 625261, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.018132448196411, "global_step": 625262, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.972100853919983, "global_step": 625263, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9972275495529175, "global_step": 625264, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9537363052368164, "global_step": 625265, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0279428958892822, "global_step": 625266, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0118682384490967, "global_step": 625267, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0307793617248535, "global_step": 625268, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0696465969085693, "global_step": 625269, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9895672798156738, "global_step": 625270, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9676686525344849, "global_step": 625271, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.947095513343811, "global_step": 625272, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.993173360824585, "global_step": 625273, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8870421648025513, "global_step": 625274, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.960329294204712, "global_step": 625275, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.986474633216858, "global_step": 625276, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9641352891921997, "global_step": 625277, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9518605470657349, "global_step": 625278, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0847203731536865, "global_step": 625279, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9396378993988037, "global_step": 625280, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9792978763580322, "global_step": 625281, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.050137758255005, "global_step": 625282, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9812297821044922, "global_step": 625283, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9589383602142334, "global_step": 625284, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.033172607421875, "global_step": 625285, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9694377183914185, "global_step": 625286, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.006091594696045, "global_step": 625287, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0286507606506348, "global_step": 625288, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9101588726043701, "global_step": 625289, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0418701171875, "global_step": 625290, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9061925411224365, "global_step": 625291, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0065202713012695, "global_step": 625292, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0066118240356445, "global_step": 625293, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.988560676574707, "global_step": 625294, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0425326824188232, "global_step": 625295, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.993493914604187, "global_step": 625296, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.003247022628784, "global_step": 625297, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0337698459625244, "global_step": 625298, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9990298748016357, "global_step": 625299, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0363574028015137, "global_step": 625300, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1115615367889404, "global_step": 625301, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0075786113739014, "global_step": 625302, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.10187029838562, "global_step": 625303, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.104797601699829, "global_step": 625304, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9546889066696167, "global_step": 625305, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9728729724884033, "global_step": 625306, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.06699538230896, "global_step": 625307, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9521586894989014, "global_step": 625308, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.908238172531128, "global_step": 625309, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9791291952133179, "global_step": 625310, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0743608474731445, "global_step": 625311, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0152747631073, "global_step": 625312, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.083566188812256, "global_step": 625313, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9996061325073242, "global_step": 625314, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9451031684875488, "global_step": 625315, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9863677024841309, "global_step": 625316, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0897629261016846, "global_step": 625317, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.043987274169922, "global_step": 625318, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0101897716522217, "global_step": 625319, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.04732084274292, "global_step": 625320, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.022155523300171, "global_step": 625321, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9378689527511597, "global_step": 625322, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9331790208816528, "global_step": 625323, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9305555820465088, "global_step": 625324, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9975364208221436, "global_step": 625325, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.004060983657837, "global_step": 625326, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0548462867736816, "global_step": 625327, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.050429344177246, "global_step": 625328, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9598946571350098, "global_step": 625329, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9949908256530762, "global_step": 625330, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.946512222290039, "global_step": 625331, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0511980056762695, "global_step": 625332, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0112318992614746, "global_step": 625333, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9183223247528076, "global_step": 625334, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9882451295852661, "global_step": 625335, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.959022879600525, "global_step": 625336, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9569698572158813, "global_step": 625337, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.001605749130249, "global_step": 625338, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9722390174865723, "global_step": 625339, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0679802894592285, "global_step": 625340, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.917168140411377, "global_step": 625341, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.00791072845459, "global_step": 625342, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9192770719528198, "global_step": 625343, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.099741220474243, "global_step": 625344, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.110985279083252, "global_step": 625345, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.972130537033081, "global_step": 625346, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.058041572570801, "global_step": 625347, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9588749408721924, "global_step": 625348, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8262277841567993, "global_step": 625349, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.062901020050049, "global_step": 625350, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.000836133956909, "global_step": 625351, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9651446342468262, "global_step": 625352, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0163166522979736, "global_step": 625353, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9905506372451782, "global_step": 625354, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0111119747161865, "global_step": 625355, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.005326271057129, "global_step": 625356, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9800755977630615, "global_step": 625357, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.006588935852051, "global_step": 625358, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9408400058746338, "global_step": 625359, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9908263683319092, "global_step": 625360, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1096465587615967, "global_step": 625361, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9478627443313599, "global_step": 625362, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.068507194519043, "global_step": 625363, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9722011089324951, "global_step": 625364, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.008047580718994, "global_step": 625365, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.009740114212036, "global_step": 625366, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0685372352600098, "global_step": 625367, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.023987054824829, "global_step": 625368, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.956799030303955, "global_step": 625369, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0920958518981934, "global_step": 625370, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.057699680328369, "global_step": 625371, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0289199352264404, "global_step": 625372, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1105692386627197, "global_step": 625373, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0525705814361572, "global_step": 625374, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9775433540344238, "global_step": 625375, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.965294599533081, "global_step": 625376, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9624555110931396, "global_step": 625377, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.021916151046753, "global_step": 625378, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.989939570426941, "global_step": 625379, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0784263610839844, "global_step": 625380, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9676120281219482, "global_step": 625381, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9690628051757812, "global_step": 625382, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9474818706512451, "global_step": 625383, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.057421922683716, "global_step": 625384, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0306360721588135, "global_step": 625385, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.050020694732666, "global_step": 625386, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0182204246520996, "global_step": 625387, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.001234769821167, "global_step": 625388, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0509164333343506, "global_step": 625389, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0363080501556396, "global_step": 625390, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.085547924041748, "global_step": 625391, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0650227069854736, "global_step": 625392, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0443456172943115, "global_step": 625393, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9822443723678589, "global_step": 625394, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9962044954299927, "global_step": 625395, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.056171417236328, "global_step": 625396, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9780737161636353, "global_step": 625397, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.97038996219635, "global_step": 625398, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9633148908615112, "global_step": 625399, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.07387375831604, "global_step": 625400, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.950201153755188, "global_step": 625401, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.00170636177063, "global_step": 625402, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0228238105773926, "global_step": 625403, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0022695064544678, "global_step": 625404, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9954825639724731, "global_step": 625405, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.987768292427063, "global_step": 625406, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0122053623199463, "global_step": 625407, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9606159925460815, "global_step": 625408, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.96728515625, "global_step": 625409, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9758074283599854, "global_step": 625410, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9408458471298218, "global_step": 625411, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0023646354675293, "global_step": 625412, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.06280255317688, "global_step": 625413, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0247817039489746, "global_step": 625414, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9967541694641113, "global_step": 625415, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.936369776725769, "global_step": 625416, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0644545555114746, "global_step": 625417, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.002039670944214, "global_step": 625418, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.923155426979065, "global_step": 625419, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9315513372421265, "global_step": 625420, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.926185131072998, "global_step": 625421, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0149104595184326, "global_step": 625422, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.959678292274475, "global_step": 625423, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9911779165267944, "global_step": 625424, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0621325969696045, "global_step": 625425, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.081157922744751, "global_step": 625426, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9915502071380615, "global_step": 625427, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9305481910705566, "global_step": 625428, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9948763847351074, "global_step": 625429, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9429869651794434, "global_step": 625430, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0454747676849365, "global_step": 625431, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.015042543411255, "global_step": 625432, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.032989501953125, "global_step": 625433, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0215415954589844, "global_step": 625434, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.057196855545044, "global_step": 625435, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9801198244094849, "global_step": 625436, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0365474224090576, "global_step": 625437, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9837127923965454, "global_step": 625438, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9464812278747559, "global_step": 625439, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0388872623443604, "global_step": 625440, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.982933759689331, "global_step": 625441, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9861369132995605, "global_step": 625442, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9192276000976562, "global_step": 625443, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9747986793518066, "global_step": 625444, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.99607253074646, "global_step": 625445, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0813190937042236, "global_step": 625446, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9655426740646362, "global_step": 625447, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.023198366165161, "global_step": 625448, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.022589683532715, "global_step": 625449, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0442147254943848, "global_step": 625450, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.990923523902893, "global_step": 625451, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0048022270202637, "global_step": 625452, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0382072925567627, "global_step": 625453, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.962403416633606, "global_step": 625454, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0773799419403076, "global_step": 625455, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.935331106185913, "global_step": 625456, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9683266878128052, "global_step": 625457, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9881486892700195, "global_step": 625458, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0183141231536865, "global_step": 625459, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9843355417251587, "global_step": 625460, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.004192352294922, "global_step": 625461, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9689693450927734, "global_step": 625462, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.83230721950531, "global_step": 625463, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0606207847595215, "global_step": 625464, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0448458194732666, "global_step": 625465, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.046962261199951, "global_step": 625466, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.035202741622925, "global_step": 625467, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9634383916854858, "global_step": 625468, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9667187929153442, "global_step": 625469, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.99461030960083, "global_step": 625470, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9197102785110474, "global_step": 625471, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9886776208877563, "global_step": 625472, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9426021575927734, "global_step": 625473, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9461071491241455, "global_step": 625474, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0310754776000977, "global_step": 625475, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0219013690948486, "global_step": 625476, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0299277305603027, "global_step": 625477, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9742331504821777, "global_step": 625478, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.007685422897339, "global_step": 625479, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.032290458679199, "global_step": 625480, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0775675773620605, "global_step": 625481, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9993318319320679, "global_step": 625482, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9255998134613037, "global_step": 625483, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9609163999557495, "global_step": 625484, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.928602933883667, "global_step": 625485, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0532565116882324, "global_step": 625486, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9956811666488647, "global_step": 625487, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9638675451278687, "global_step": 625488, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9079138040542603, "global_step": 625489, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9922866821289062, "global_step": 625490, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.054295301437378, "global_step": 625491, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9655927419662476, "global_step": 625492, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9866775274276733, "global_step": 625493, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0360546112060547, "global_step": 625494, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9683207273483276, "global_step": 625495, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.966490387916565, "global_step": 625496, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9943609237670898, "global_step": 625497, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.993548035621643, "global_step": 625498, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0597753524780273, "global_step": 625499, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9999643564224243, "global_step": 625500, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9738848209381104, "global_step": 625501, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0615382194519043, "global_step": 625502, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9850106239318848, "global_step": 625503, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9854605197906494, "global_step": 625504, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.029202699661255, "global_step": 625505, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0136568546295166, "global_step": 625506, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9153616428375244, "global_step": 625507, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.007364511489868, "global_step": 625508, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.040283203125, "global_step": 625509, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.028618097305298, "global_step": 625510, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.072547674179077, "global_step": 625511, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9621044397354126, "global_step": 625512, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.980346918106079, "global_step": 625513, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0175161361694336, "global_step": 625514, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9760879278182983, "global_step": 625515, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.950348973274231, "global_step": 625516, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9885132312774658, "global_step": 625517, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9285621643066406, "global_step": 625518, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.032350540161133, "global_step": 625519, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0275936126708984, "global_step": 625520, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9143143892288208, "global_step": 625521, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9594920873641968, "global_step": 625522, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9308949708938599, "global_step": 625523, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9467415809631348, "global_step": 625524, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0113837718963623, "global_step": 625525, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9956315755844116, "global_step": 625526, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8999016284942627, "global_step": 625527, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.925183892250061, "global_step": 625528, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0042941570281982, "global_step": 625529, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9228672981262207, "global_step": 625530, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0519039630889893, "global_step": 625531, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0859649181365967, "global_step": 625532, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.85163152217865, "global_step": 625533, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9991028308868408, "global_step": 625534, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9752833843231201, "global_step": 625535, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.000800609588623, "global_step": 625536, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9574763774871826, "global_step": 625537, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9835585355758667, "global_step": 625538, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9422796964645386, "global_step": 625539, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9721171855926514, "global_step": 625540, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.118229627609253, "global_step": 625541, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9910651445388794, "global_step": 625542, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0357909202575684, "global_step": 625543, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.101836681365967, "global_step": 625544, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9987976551055908, "global_step": 625545, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9922869205474854, "global_step": 625546, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9180376529693604, "global_step": 625547, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9940208196640015, "global_step": 625548, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9326231479644775, "global_step": 625549, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0499517917633057, "global_step": 625550, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9608888626098633, "global_step": 625551, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.009861469268799, "global_step": 625552, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.047913074493408, "global_step": 625553, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0730462074279785, "global_step": 625554, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0238587856292725, "global_step": 625555, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9898616075515747, "global_step": 625556, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9075313806533813, "global_step": 625557, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0672576427459717, "global_step": 625558, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.072362184524536, "global_step": 625559, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.009679079055786, "global_step": 625560, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.039008378982544, "global_step": 625561, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9487395286560059, "global_step": 625562, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9903934001922607, "global_step": 625563, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.96249520778656, "global_step": 625564, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.990878939628601, "global_step": 625565, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9734703302383423, "global_step": 625566, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9961761236190796, "global_step": 625567, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9566376209259033, "global_step": 625568, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9052493572235107, "global_step": 625569, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9778026342391968, "global_step": 625570, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9470175504684448, "global_step": 625571, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0542924404144287, "global_step": 625572, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.94032883644104, "global_step": 625573, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0097031593322754, "global_step": 625574, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0137641429901123, "global_step": 625575, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9828534126281738, "global_step": 625576, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.029531478881836, "global_step": 625577, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9844557046890259, "global_step": 625578, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9811218976974487, "global_step": 625579, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0315041542053223, "global_step": 625580, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1032748222351074, "global_step": 625581, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9631437063217163, "global_step": 625582, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0228679180145264, "global_step": 625583, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0055179595947266, "global_step": 625584, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0009098052978516, "global_step": 625585, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9245765209197998, "global_step": 625586, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.089181900024414, "global_step": 625587, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9669203758239746, "global_step": 625588, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.965403437614441, "global_step": 625589, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0237460136413574, "global_step": 625590, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9526734352111816, "global_step": 625591, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.060241222381592, "global_step": 625592, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.035269260406494, "global_step": 625593, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9714951515197754, "global_step": 625594, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9507981538772583, "global_step": 625595, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.969704270362854, "global_step": 625596, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0347416400909424, "global_step": 625597, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.03729510307312, "global_step": 625598, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.007749080657959, "global_step": 625599, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9867839813232422, "global_step": 625600, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9956274032592773, "global_step": 625601, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0919787883758545, "global_step": 625602, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0095996856689453, "global_step": 625603, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0051684379577637, "global_step": 625604, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0003926753997803, "global_step": 625605, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9916930198669434, "global_step": 625606, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9658128023147583, "global_step": 625607, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.057361602783203, "global_step": 625608, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9742809534072876, "global_step": 625609, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0675158500671387, "global_step": 625610, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.021099805831909, "global_step": 625611, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0313186645507812, "global_step": 625612, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.005915641784668, "global_step": 625613, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0296504497528076, "global_step": 625614, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9385603666305542, "global_step": 625615, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9911863803863525, "global_step": 625616, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9440444707870483, "global_step": 625617, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9490554332733154, "global_step": 625618, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0271875858306885, "global_step": 625619, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0225229263305664, "global_step": 625620, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1602680683135986, "global_step": 625621, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0144522190093994, "global_step": 625622, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9677737951278687, "global_step": 625623, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.037592887878418, "global_step": 625624, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0603041648864746, "global_step": 625625, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.084019899368286, "global_step": 625626, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0944900512695312, "global_step": 625627, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9440644979476929, "global_step": 625628, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0646491050720215, "global_step": 625629, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.00996994972229, "global_step": 625630, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.065054416656494, "global_step": 625631, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.049492120742798, "global_step": 625632, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0885725021362305, "global_step": 625633, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.950995922088623, "global_step": 625634, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.072627067565918, "global_step": 625635, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.001448392868042, "global_step": 625636, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.036198139190674, "global_step": 625637, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.007530450820923, "global_step": 625638, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.984697937965393, "global_step": 625639, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.861458420753479, "global_step": 625640, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.040524482727051, "global_step": 625641, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9779542684555054, "global_step": 625642, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0135793685913086, "global_step": 625643, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.041712999343872, "global_step": 625644, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.066387891769409, "global_step": 625645, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9891552925109863, "global_step": 625646, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9909178018569946, "global_step": 625647, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.020753860473633, "global_step": 625648, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9571372270584106, "global_step": 625649, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0655672550201416, "global_step": 625650, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0397284030914307, "global_step": 625651, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1169512271881104, "global_step": 625652, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.034135103225708, "global_step": 625653, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9592912197113037, "global_step": 625654, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0084328651428223, "global_step": 625655, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9829398393630981, "global_step": 625656, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.04955792427063, "global_step": 625657, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9127000570297241, "global_step": 625658, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.011699914932251, "global_step": 625659, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0488362312316895, "global_step": 625660, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.01767635345459, "global_step": 625661, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.974143147468567, "global_step": 625662, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9676580429077148, "global_step": 625663, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0374255180358887, "global_step": 625664, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.028794050216675, "global_step": 625665, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0152430534362793, "global_step": 625666, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.034719705581665, "global_step": 625667, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.041308879852295, "global_step": 625668, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9535512924194336, "global_step": 625669, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0676112174987793, "global_step": 625670, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9695218801498413, "global_step": 625671, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8987727165222168, "global_step": 625672, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.007280111312866, "global_step": 625673, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0368289947509766, "global_step": 625674, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9578882455825806, "global_step": 625675, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0201611518859863, "global_step": 625676, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9481066465377808, "global_step": 625677, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9696459770202637, "global_step": 625678, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.958152413368225, "global_step": 625679, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.993888258934021, "global_step": 625680, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9793530702590942, "global_step": 625681, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9691219329833984, "global_step": 625682, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9276666641235352, "global_step": 625683, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0885136127471924, "global_step": 625684, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0343966484069824, "global_step": 625685, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0247459411621094, "global_step": 625686, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9589099884033203, "global_step": 625687, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0988833904266357, "global_step": 625688, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9948207139968872, "global_step": 625689, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.051920175552368, "global_step": 625690, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.072763681411743, "global_step": 625691, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9872747659683228, "global_step": 625692, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0255684852600098, "global_step": 625693, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.017333984375, "global_step": 625694, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.093341112136841, "global_step": 625695, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9732692241668701, "global_step": 625696, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0765979290008545, "global_step": 625697, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9843744039535522, "global_step": 625698, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.029496669769287, "global_step": 625699, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9579716920852661, "global_step": 625700, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8937432765960693, "global_step": 625701, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9815219640731812, "global_step": 625702, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.061692953109741, "global_step": 625703, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.054086923599243, "global_step": 625704, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.961928367614746, "global_step": 625705, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0142769813537598, "global_step": 625706, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9340773820877075, "global_step": 625707, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0037569999694824, "global_step": 625708, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.96174156665802, "global_step": 625709, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0117971897125244, "global_step": 625710, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.072046995162964, "global_step": 625711, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0807840824127197, "global_step": 625712, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.030008554458618, "global_step": 625713, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.039494276046753, "global_step": 625714, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.008044719696045, "global_step": 625715, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.910759449005127, "global_step": 625716, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.01962947845459, "global_step": 625717, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0127718448638916, "global_step": 625718, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.049605369567871, "global_step": 625719, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.926080346107483, "global_step": 625720, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.052032709121704, "global_step": 625721, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9743380546569824, "global_step": 625722, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9929237365722656, "global_step": 625723, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.016174793243408, "global_step": 625724, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9667115211486816, "global_step": 625725, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0135085582733154, "global_step": 625726, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0149707794189453, "global_step": 625727, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.011464834213257, "global_step": 625728, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9995920658111572, "global_step": 625729, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9539921283721924, "global_step": 625730, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9799681901931763, "global_step": 625731, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.025357484817505, "global_step": 625732, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.927830457687378, "global_step": 625733, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9974290132522583, "global_step": 625734, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9289246797561646, "global_step": 625735, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.016641139984131, "global_step": 625736, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.991187572479248, "global_step": 625737, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9763411283493042, "global_step": 625738, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9827057123184204, "global_step": 625739, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.031311273574829, "global_step": 625740, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.034843683242798, "global_step": 625741, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.008821487426758, "global_step": 625742, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.002871036529541, "global_step": 625743, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.008692741394043, "global_step": 625744, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9714875221252441, "global_step": 625745, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.03826904296875, "global_step": 625746, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.071582078933716, "global_step": 625747, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0237605571746826, "global_step": 625748, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0257675647735596, "global_step": 625749, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9774707555770874, "global_step": 625750, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0011837482452393, "global_step": 625751, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9569047689437866, "global_step": 625752, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0561420917510986, "global_step": 625753, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.031744956970215, "global_step": 625754, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.057000160217285, "global_step": 625755, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9744102954864502, "global_step": 625756, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0493762493133545, "global_step": 625757, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0798447132110596, "global_step": 625758, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0846939086914062, "global_step": 625759, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.058563709259033, "global_step": 625760, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9552134275436401, "global_step": 625761, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0379996299743652, "global_step": 625762, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0095736980438232, "global_step": 625763, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.995969295501709, "global_step": 625764, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0027339458465576, "global_step": 625765, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9463118314743042, "global_step": 625766, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0265376567840576, "global_step": 625767, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.062781572341919, "global_step": 625768, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9565242528915405, "global_step": 625769, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0358903408050537, "global_step": 625770, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9974409341812134, "global_step": 625771, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9705390930175781, "global_step": 625772, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9961589574813843, "global_step": 625773, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9818627834320068, "global_step": 625774, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.985371470451355, "global_step": 625775, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.008413314819336, "global_step": 625776, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0250349044799805, "global_step": 625777, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.056539535522461, "global_step": 625778, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.080540895462036, "global_step": 625779, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9506840705871582, "global_step": 625780, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9896494150161743, "global_step": 625781, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9043397903442383, "global_step": 625782, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.086243152618408, "global_step": 625783, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.077575445175171, "global_step": 625784, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9372857809066772, "global_step": 625785, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.021829843521118, "global_step": 625786, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0629372596740723, "global_step": 625787, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.05755877494812, "global_step": 625788, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9340400695800781, "global_step": 625789, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9529449939727783, "global_step": 625790, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9735324382781982, "global_step": 625791, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.040297031402588, "global_step": 625792, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0727665424346924, "global_step": 625793, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0200448036193848, "global_step": 625794, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.024078369140625, "global_step": 625795, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.020358085632324, "global_step": 625796, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0939581394195557, "global_step": 625797, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9970492124557495, "global_step": 625798, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9992173910140991, "global_step": 625799, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0354483127593994, "global_step": 625800, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.948941707611084, "global_step": 625801, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.997593641281128, "global_step": 625802, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9925990104675293, "global_step": 625803, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.031224489212036, "global_step": 625804, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.027904748916626, "global_step": 625805, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9558217525482178, "global_step": 625806, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0626211166381836, "global_step": 625807, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0579280853271484, "global_step": 625808, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9369345903396606, "global_step": 625809, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9455069303512573, "global_step": 625810, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9800951480865479, "global_step": 625811, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9669232368469238, "global_step": 625812, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.050297498703003, "global_step": 625813, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.076680898666382, "global_step": 625814, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.000365972518921, "global_step": 625815, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.056556463241577, "global_step": 625816, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.040935754776001, "global_step": 625817, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.034773349761963, "global_step": 625818, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.034389019012451, "global_step": 625819, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.043170690536499, "global_step": 625820, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.023134469985962, "global_step": 625821, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0299172401428223, "global_step": 625822, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9861962795257568, "global_step": 625823, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9631991386413574, "global_step": 625824, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1079187393188477, "global_step": 625825, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.984958529472351, "global_step": 625826, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0311169624328613, "global_step": 625827, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.063106060028076, "global_step": 625828, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8827667236328125, "global_step": 625829, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.027390956878662, "global_step": 625830, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0341458320617676, "global_step": 625831, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9758552312850952, "global_step": 625832, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0838046073913574, "global_step": 625833, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9737508296966553, "global_step": 625834, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.037536859512329, "global_step": 625835, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9901237487792969, "global_step": 625836, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9532806873321533, "global_step": 625837, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9508037567138672, "global_step": 625838, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9508858919143677, "global_step": 625839, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.032565116882324, "global_step": 625840, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0148074626922607, "global_step": 625841, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.013301134109497, "global_step": 625842, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.043653726577759, "global_step": 625843, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9486260414123535, "global_step": 625844, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0101656913757324, "global_step": 625845, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0479538440704346, "global_step": 625846, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.043856143951416, "global_step": 625847, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9910136461257935, "global_step": 625848, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.064054489135742, "global_step": 625849, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.979414701461792, "global_step": 625850, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0515854358673096, "global_step": 625851, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.036391019821167, "global_step": 625852, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0160183906555176, "global_step": 625853, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8984931707382202, "global_step": 625854, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0728447437286377, "global_step": 625855, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9134178161621094, "global_step": 625856, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0839784145355225, "global_step": 625857, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9918620586395264, "global_step": 625858, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.017979383468628, "global_step": 625859, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.045367479324341, "global_step": 625860, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9188710451126099, "global_step": 625861, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0483241081237793, "global_step": 625862, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0105080604553223, "global_step": 625863, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9819656610488892, "global_step": 625864, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9830008745193481, "global_step": 625865, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9568675756454468, "global_step": 625866, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0096945762634277, "global_step": 625867, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0341968536376953, "global_step": 625868, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.056088924407959, "global_step": 625869, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9695916175842285, "global_step": 625870, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.032693386077881, "global_step": 625871, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0401816368103027, "global_step": 625872, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9977437257766724, "global_step": 625873, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9708173274993896, "global_step": 625874, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.942290186882019, "global_step": 625875, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9763325452804565, "global_step": 625876, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0661227703094482, "global_step": 625877, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0762574672698975, "global_step": 625878, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9248830080032349, "global_step": 625879, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.03716778755188, "global_step": 625880, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.020724058151245, "global_step": 625881, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9554190635681152, "global_step": 625882, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.031188488006592, "global_step": 625883, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0088391304016113, "global_step": 625884, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9693143367767334, "global_step": 625885, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.991400122642517, "global_step": 625886, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9885830879211426, "global_step": 625887, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0795295238494873, "global_step": 625888, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.087507724761963, "global_step": 625889, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9758960008621216, "global_step": 625890, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.091477155685425, "global_step": 625891, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.027172803878784, "global_step": 625892, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.059723138809204, "global_step": 625893, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.008333921432495, "global_step": 625894, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.066242218017578, "global_step": 625895, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.025512456893921, "global_step": 625896, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9558165073394775, "global_step": 625897, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.995003342628479, "global_step": 625898, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0456230640411377, "global_step": 625899, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.918868064880371, "global_step": 625900, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9690974950790405, "global_step": 625901, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.054680109024048, "global_step": 625902, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.992106318473816, "global_step": 625903, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.020641326904297, "global_step": 625904, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0284101963043213, "global_step": 625905, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.011915683746338, "global_step": 625906, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.03666353225708, "global_step": 625907, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9170374870300293, "global_step": 625908, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9798115491867065, "global_step": 625909, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9814822673797607, "global_step": 625910, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.025259017944336, "global_step": 625911, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0071005821228027, "global_step": 625912, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0014402866363525, "global_step": 625913, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9736720323562622, "global_step": 625914, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.062382459640503, "global_step": 625915, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1062488555908203, "global_step": 625916, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0026440620422363, "global_step": 625917, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.999600887298584, "global_step": 625918, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0014748573303223, "global_step": 625919, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9678837060928345, "global_step": 625920, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9696534872055054, "global_step": 625921, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9594048261642456, "global_step": 625922, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0381662845611572, "global_step": 625923, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.990615963935852, "global_step": 625924, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0895187854766846, "global_step": 625925, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0126707553863525, "global_step": 625926, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9790641069412231, "global_step": 625927, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.077378034591675, "global_step": 625928, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.024012804031372, "global_step": 625929, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.012669563293457, "global_step": 625930, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9664047956466675, "global_step": 625931, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0521492958068848, "global_step": 625932, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.047417402267456, "global_step": 625933, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9962158203125, "global_step": 625934, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.019761323928833, "global_step": 625935, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0269172191619873, "global_step": 625936, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9593570232391357, "global_step": 625937, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.017237424850464, "global_step": 625938, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9854485988616943, "global_step": 625939, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0379626750946045, "global_step": 625940, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0350699424743652, "global_step": 625941, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0317628383636475, "global_step": 625942, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.986112117767334, "global_step": 625943, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9824602603912354, "global_step": 625944, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0100064277648926, "global_step": 625945, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9472577571868896, "global_step": 625946, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9843719005584717, "global_step": 625947, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9767956733703613, "global_step": 625948, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.000650644302368, "global_step": 625949, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.067493438720703, "global_step": 625950, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.984689712524414, "global_step": 625951, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0114076137542725, "global_step": 625952, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.082634687423706, "global_step": 625953, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.017807960510254, "global_step": 625954, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0210821628570557, "global_step": 625955, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9710795879364014, "global_step": 625956, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0039963722229004, "global_step": 625957, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9869755506515503, "global_step": 625958, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.973533272743225, "global_step": 625959, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9736714363098145, "global_step": 625960, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9779530763626099, "global_step": 625961, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.033740282058716, "global_step": 625962, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.01863431930542, "global_step": 625963, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.104595899581909, "global_step": 625964, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9071099758148193, "global_step": 625965, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.99833345413208, "global_step": 625966, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9159290790557861, "global_step": 625967, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.13435959815979, "global_step": 625968, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.959862470626831, "global_step": 625969, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9327844381332397, "global_step": 625970, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9979579448699951, "global_step": 625971, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0444860458374023, "global_step": 625972, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0057990550994873, "global_step": 625973, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0998473167419434, "global_step": 625974, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9844152927398682, "global_step": 625975, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9235070943832397, "global_step": 625976, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.00795316696167, "global_step": 625977, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0147571563720703, "global_step": 625978, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0616955757141113, "global_step": 625979, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.092050075531006, "global_step": 625980, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.009875535964966, "global_step": 625981, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0974526405334473, "global_step": 625982, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0281822681427, "global_step": 625983, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.022522449493408, "global_step": 625984, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0834157466888428, "global_step": 625985, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.049980640411377, "global_step": 625986, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0476789474487305, "global_step": 625987, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0492141246795654, "global_step": 625988, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.990914225578308, "global_step": 625989, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0404505729675293, "global_step": 625990, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.010899305343628, "global_step": 625991, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.064340353012085, "global_step": 625992, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9778335094451904, "global_step": 625993, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0334134101867676, "global_step": 625994, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9530242681503296, "global_step": 625995, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0078513622283936, "global_step": 625996, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.953497290611267, "global_step": 625997, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.976123332977295, "global_step": 625998, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9884072542190552, "global_step": 625999, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9974968433380127, "global_step": 626000, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9493436813354492, "global_step": 626001, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9295721054077148, "global_step": 626002, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0206847190856934, "global_step": 626003, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0834550857543945, "global_step": 626004, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.976455569267273, "global_step": 626005, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.965667963027954, "global_step": 626006, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.040947198867798, "global_step": 626007, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.077326774597168, "global_step": 626008, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.940049648284912, "global_step": 626009, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9663338661193848, "global_step": 626010, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.017099142074585, "global_step": 626011, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1016650199890137, "global_step": 626012, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0270276069641113, "global_step": 626013, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0526862144470215, "global_step": 626014, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.941819190979004, "global_step": 626015, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.042800188064575, "global_step": 626016, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.023327589035034, "global_step": 626017, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.915023922920227, "global_step": 626018, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0079100131988525, "global_step": 626019, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8989150524139404, "global_step": 626020, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.028188705444336, "global_step": 626021, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.042367935180664, "global_step": 626022, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9542555809020996, "global_step": 626023, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9540231227874756, "global_step": 626024, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.01934552192688, "global_step": 626025, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9733577966690063, "global_step": 626026, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0365893840789795, "global_step": 626027, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0188374519348145, "global_step": 626028, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0886361598968506, "global_step": 626029, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9947656393051147, "global_step": 626030, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9315319061279297, "global_step": 626031, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.033384084701538, "global_step": 626032, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0244743824005127, "global_step": 626033, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0067508220672607, "global_step": 626034, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.990138292312622, "global_step": 626035, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0766615867614746, "global_step": 626036, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.029597520828247, "global_step": 626037, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0393781661987305, "global_step": 626038, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9910316467285156, "global_step": 626039, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0353050231933594, "global_step": 626040, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0384023189544678, "global_step": 626041, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9783121347427368, "global_step": 626042, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.081129789352417, "global_step": 626043, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9821900129318237, "global_step": 626044, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.980937123298645, "global_step": 626045, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0291550159454346, "global_step": 626046, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0713090896606445, "global_step": 626047, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.96580970287323, "global_step": 626048, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9751412868499756, "global_step": 626049, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8874186277389526, "global_step": 626050, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.991239309310913, "global_step": 626051, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8799924850463867, "global_step": 626052, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.03933048248291, "global_step": 626053, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0169897079467773, "global_step": 626054, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0316500663757324, "global_step": 626055, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.979380488395691, "global_step": 626056, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0533571243286133, "global_step": 626057, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.998469352722168, "global_step": 626058, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9831087589263916, "global_step": 626059, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9772417545318604, "global_step": 626060, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0460610389709473, "global_step": 626061, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0496182441711426, "global_step": 626062, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9075158834457397, "global_step": 626063, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0054309368133545, "global_step": 626064, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.027210235595703, "global_step": 626065, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9771771430969238, "global_step": 626066, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9525781869888306, "global_step": 626067, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.018256425857544, "global_step": 626068, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.078603744506836, "global_step": 626069, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.02099347114563, "global_step": 626070, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.025489091873169, "global_step": 626071, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0028305053710938, "global_step": 626072, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1082682609558105, "global_step": 626073, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9968910217285156, "global_step": 626074, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.031937837600708, "global_step": 626075, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.992646336555481, "global_step": 626076, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9663527011871338, "global_step": 626077, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0118978023529053, "global_step": 626078, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.98101007938385, "global_step": 626079, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.057401418685913, "global_step": 626080, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9814866781234741, "global_step": 626081, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9839717149734497, "global_step": 626082, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9515798091888428, "global_step": 626083, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.983754277229309, "global_step": 626084, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0742321014404297, "global_step": 626085, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.022764205932617, "global_step": 626086, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0829389095306396, "global_step": 626087, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.922590732574463, "global_step": 626088, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.983894944190979, "global_step": 626089, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0129528045654297, "global_step": 626090, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.036212921142578, "global_step": 626091, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.020299196243286, "global_step": 626092, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0072996616363525, "global_step": 626093, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0084950923919678, "global_step": 626094, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0142128467559814, "global_step": 626095, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9922187328338623, "global_step": 626096, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9110404253005981, "global_step": 626097, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9828760623931885, "global_step": 626098, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.077474355697632, "global_step": 626099, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.057072162628174, "global_step": 626100, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0388667583465576, "global_step": 626101, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9751025438308716, "global_step": 626102, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0980772972106934, "global_step": 626103, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0277512073516846, "global_step": 626104, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9850540161132812, "global_step": 626105, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0027620792388916, "global_step": 626106, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.017592668533325, "global_step": 626107, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.992061972618103, "global_step": 626108, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9267444610595703, "global_step": 626109, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.974813461303711, "global_step": 626110, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9569506645202637, "global_step": 626111, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.003929615020752, "global_step": 626112, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0555057525634766, "global_step": 626113, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0827252864837646, "global_step": 626114, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.021376848220825, "global_step": 626115, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.939197301864624, "global_step": 626116, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9921797513961792, "global_step": 626117, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0928878784179688, "global_step": 626118, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.965912938117981, "global_step": 626119, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.007080316543579, "global_step": 626120, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.072528600692749, "global_step": 626121, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9717738628387451, "global_step": 626122, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9218450784683228, "global_step": 626123, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.963390827178955, "global_step": 626124, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9867843389511108, "global_step": 626125, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9069371223449707, "global_step": 626126, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.029189348220825, "global_step": 626127, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.008509874343872, "global_step": 626128, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0871949195861816, "global_step": 626129, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.946268916130066, "global_step": 626130, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9227877855300903, "global_step": 626131, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9861154556274414, "global_step": 626132, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9342446327209473, "global_step": 626133, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0111045837402344, "global_step": 626134, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9725990295410156, "global_step": 626135, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.920493245124817, "global_step": 626136, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9631567001342773, "global_step": 626137, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9992551803588867, "global_step": 626138, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0585203170776367, "global_step": 626139, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9758895635604858, "global_step": 626140, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9907442331314087, "global_step": 626141, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.001708507537842, "global_step": 626142, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.023561954498291, "global_step": 626143, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9904950857162476, "global_step": 626144, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9220240116119385, "global_step": 626145, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9761918783187866, "global_step": 626146, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9289573431015015, "global_step": 626147, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.963323950767517, "global_step": 626148, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0732171535491943, "global_step": 626149, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0281686782836914, "global_step": 626150, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9804894924163818, "global_step": 626151, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0059962272644043, "global_step": 626152, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9537205696105957, "global_step": 626153, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0309255123138428, "global_step": 626154, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9166513681411743, "global_step": 626155, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9447575807571411, "global_step": 626156, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9571894407272339, "global_step": 626157, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0540335178375244, "global_step": 626158, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.951042890548706, "global_step": 626159, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0167784690856934, "global_step": 626160, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.05281925201416, "global_step": 626161, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.004523992538452, "global_step": 626162, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9760942459106445, "global_step": 626163, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9256922006607056, "global_step": 626164, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.039656639099121, "global_step": 626165, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9908190965652466, "global_step": 626166, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0895962715148926, "global_step": 626167, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0067617893218994, "global_step": 626168, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9416391849517822, "global_step": 626169, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.108513355255127, "global_step": 626170, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8669148683547974, "global_step": 626171, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9794089794158936, "global_step": 626172, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0807149410247803, "global_step": 626173, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9052026271820068, "global_step": 626174, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.939501404762268, "global_step": 626175, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9814515113830566, "global_step": 626176, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.010246515274048, "global_step": 626177, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9447249174118042, "global_step": 626178, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0337555408477783, "global_step": 626179, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.058716297149658, "global_step": 626180, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0256946086883545, "global_step": 626181, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9988722801208496, "global_step": 626182, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9250895977020264, "global_step": 626183, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.066903829574585, "global_step": 626184, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9817405939102173, "global_step": 626185, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.936783790588379, "global_step": 626186, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.00103759765625, "global_step": 626187, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.042118549346924, "global_step": 626188, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9018892049789429, "global_step": 626189, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0720808506011963, "global_step": 626190, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0039560794830322, "global_step": 626191, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.058251142501831, "global_step": 626192, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9954864978790283, "global_step": 626193, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9507546424865723, "global_step": 626194, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0325469970703125, "global_step": 626195, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9945454597473145, "global_step": 626196, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8903534412384033, "global_step": 626197, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.962841272354126, "global_step": 626198, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.037790536880493, "global_step": 626199, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0628790855407715, "global_step": 626200, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.00642728805542, "global_step": 626201, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9417794942855835, "global_step": 626202, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0087502002716064, "global_step": 626203, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.949418306350708, "global_step": 626204, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0748274326324463, "global_step": 626205, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8857777118682861, "global_step": 626206, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9601794481277466, "global_step": 626207, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9681366682052612, "global_step": 626208, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9800115823745728, "global_step": 626209, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9951996803283691, "global_step": 626210, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.948323130607605, "global_step": 626211, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0858585834503174, "global_step": 626212, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.003666400909424, "global_step": 626213, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9511115550994873, "global_step": 626214, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.039461374282837, "global_step": 626215, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9702507257461548, "global_step": 626216, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0955214500427246, "global_step": 626217, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0916249752044678, "global_step": 626218, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9573814868927002, "global_step": 626219, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0043954849243164, "global_step": 626220, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.922686219215393, "global_step": 626221, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.06546950340271, "global_step": 626222, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0701632499694824, "global_step": 626223, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9959769248962402, "global_step": 626224, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.976269006729126, "global_step": 626225, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9175560474395752, "global_step": 626226, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9813774824142456, "global_step": 626227, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9127452373504639, "global_step": 626228, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9239192008972168, "global_step": 626229, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9692656993865967, "global_step": 626230, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.956699252128601, "global_step": 626231, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9703551530838013, "global_step": 626232, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9906620979309082, "global_step": 626233, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0452780723571777, "global_step": 626234, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0849952697753906, "global_step": 626235, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9096416234970093, "global_step": 626236, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9536632299423218, "global_step": 626237, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9724206924438477, "global_step": 626238, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9738258123397827, "global_step": 626239, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9470081329345703, "global_step": 626240, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9655640125274658, "global_step": 626241, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9608583450317383, "global_step": 626242, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0259313583374023, "global_step": 626243, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9284021854400635, "global_step": 626244, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.96722412109375, "global_step": 626245, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.057403326034546, "global_step": 626246, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.034640312194824, "global_step": 626247, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9777076244354248, "global_step": 626248, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9561694860458374, "global_step": 626249, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.95577871799469, "global_step": 626250, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0218939781188965, "global_step": 626251, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.014057159423828, "global_step": 626252, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.007154703140259, "global_step": 626253, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0555191040039062, "global_step": 626254, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0230088233947754, "global_step": 626255, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.959598183631897, "global_step": 626256, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0510385036468506, "global_step": 626257, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9694031476974487, "global_step": 626258, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9661402702331543, "global_step": 626259, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0722439289093018, "global_step": 626260, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9574756622314453, "global_step": 626261, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0022294521331787, "global_step": 626262, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9684230089187622, "global_step": 626263, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0835399627685547, "global_step": 626264, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.029069662094116, "global_step": 626265, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9752544164657593, "global_step": 626266, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8855607509613037, "global_step": 626267, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.036795139312744, "global_step": 626268, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0093579292297363, "global_step": 626269, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0055429935455322, "global_step": 626270, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.166348695755005, "global_step": 626271, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0221474170684814, "global_step": 626272, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9489877223968506, "global_step": 626273, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.072211742401123, "global_step": 626274, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0308356285095215, "global_step": 626275, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9802407026290894, "global_step": 626276, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9531887769699097, "global_step": 626277, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.002171516418457, "global_step": 626278, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9569356441497803, "global_step": 626279, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.05557918548584, "global_step": 626280, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9738388061523438, "global_step": 626281, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0271456241607666, "global_step": 626282, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0022592544555664, "global_step": 626283, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9633862972259521, "global_step": 626284, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9694935083389282, "global_step": 626285, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0672054290771484, "global_step": 626286, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0223007202148438, "global_step": 626287, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.045797109603882, "global_step": 626288, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.028505563735962, "global_step": 626289, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9544492959976196, "global_step": 626290, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9177517890930176, "global_step": 626291, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.019662618637085, "global_step": 626292, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9693187475204468, "global_step": 626293, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9694492816925049, "global_step": 626294, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.015737533569336, "global_step": 626295, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.907225489616394, "global_step": 626296, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0105082988739014, "global_step": 626297, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.011878252029419, "global_step": 626298, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0693459510803223, "global_step": 626299, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.990272045135498, "global_step": 626300, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0160973072052, "global_step": 626301, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0213773250579834, "global_step": 626302, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.027677059173584, "global_step": 626303, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0615527629852295, "global_step": 626304, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.025310516357422, "global_step": 626305, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9688196182250977, "global_step": 626306, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0438616275787354, "global_step": 626307, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.055248260498047, "global_step": 626308, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0573267936706543, "global_step": 626309, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9924737215042114, "global_step": 626310, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9988101720809937, "global_step": 626311, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9821897745132446, "global_step": 626312, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9792593717575073, "global_step": 626313, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9961340427398682, "global_step": 626314, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0826256275177, "global_step": 626315, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.014401912689209, "global_step": 626316, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1036152839660645, "global_step": 626317, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.99539053440094, "global_step": 626318, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.065294027328491, "global_step": 626319, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9332057237625122, "global_step": 626320, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.044032096862793, "global_step": 626321, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9287012815475464, "global_step": 626322, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9793784618377686, "global_step": 626323, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9798651933670044, "global_step": 626324, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.035905599594116, "global_step": 626325, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.029951333999634, "global_step": 626326, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9451698064804077, "global_step": 626327, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0611865520477295, "global_step": 626328, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.039733409881592, "global_step": 626329, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.036663055419922, "global_step": 626330, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.079746961593628, "global_step": 626331, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0075106620788574, "global_step": 626332, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9776978492736816, "global_step": 626333, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9580353498458862, "global_step": 626334, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1005446910858154, "global_step": 626335, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9528995752334595, "global_step": 626336, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.997950553894043, "global_step": 626337, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9848984479904175, "global_step": 626338, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9081405401229858, "global_step": 626339, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.962518334388733, "global_step": 626340, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9887261390686035, "global_step": 626341, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9542839527130127, "global_step": 626342, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0354979038238525, "global_step": 626343, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9510433673858643, "global_step": 626344, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.016359567642212, "global_step": 626345, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.06215238571167, "global_step": 626346, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0108225345611572, "global_step": 626347, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0014572143554688, "global_step": 626348, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9773062467575073, "global_step": 626349, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0132415294647217, "global_step": 626350, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0281431674957275, "global_step": 626351, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0872716903686523, "global_step": 626352, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9955676794052124, "global_step": 626353, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9983997344970703, "global_step": 626354, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0533323287963867, "global_step": 626355, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0273630619049072, "global_step": 626356, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9234991073608398, "global_step": 626357, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1002562046051025, "global_step": 626358, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9790188074111938, "global_step": 626359, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.958498239517212, "global_step": 626360, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9769248962402344, "global_step": 626361, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.057771921157837, "global_step": 626362, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.021289587020874, "global_step": 626363, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9792366027832031, "global_step": 626364, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.991439938545227, "global_step": 626365, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.97915518283844, "global_step": 626366, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9651256799697876, "global_step": 626367, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.102539539337158, "global_step": 626368, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9924046993255615, "global_step": 626369, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.061891794204712, "global_step": 626370, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9590684175491333, "global_step": 626371, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9717586040496826, "global_step": 626372, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9326821565628052, "global_step": 626373, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.088020086288452, "global_step": 626374, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9881154298782349, "global_step": 626375, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.951752781867981, "global_step": 626376, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0215935707092285, "global_step": 626377, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0146939754486084, "global_step": 626378, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0087316036224365, "global_step": 626379, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9630529880523682, "global_step": 626380, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.911049485206604, "global_step": 626381, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.993013620376587, "global_step": 626382, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9799150228500366, "global_step": 626383, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0031449794769287, "global_step": 626384, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.023263931274414, "global_step": 626385, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0015175342559814, "global_step": 626386, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.014673948287964, "global_step": 626387, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9799028635025024, "global_step": 626388, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8778687715530396, "global_step": 626389, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9846558570861816, "global_step": 626390, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.042022228240967, "global_step": 626391, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9856760501861572, "global_step": 626392, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9778348207473755, "global_step": 626393, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0037524700164795, "global_step": 626394, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.043048858642578, "global_step": 626395, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9965230226516724, "global_step": 626396, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9006671905517578, "global_step": 626397, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9664080142974854, "global_step": 626398, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9961373805999756, "global_step": 626399, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.989516019821167, "global_step": 626400, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.971354603767395, "global_step": 626401, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.994294285774231, "global_step": 626402, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0473358631134033, "global_step": 626403, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0209765434265137, "global_step": 626404, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0535008907318115, "global_step": 626405, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0512797832489014, "global_step": 626406, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0744738578796387, "global_step": 626407, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0160584449768066, "global_step": 626408, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0248916149139404, "global_step": 626409, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9371768236160278, "global_step": 626410, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9823904037475586, "global_step": 626411, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9947080612182617, "global_step": 626412, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.030989170074463, "global_step": 626413, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9443879127502441, "global_step": 626414, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9686660766601562, "global_step": 626415, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0308094024658203, "global_step": 626416, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0210578441619873, "global_step": 626417, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9629814624786377, "global_step": 626418, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.975181221961975, "global_step": 626419, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.94927978515625, "global_step": 626420, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9744830131530762, "global_step": 626421, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9848854541778564, "global_step": 626422, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0256502628326416, "global_step": 626423, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8735036849975586, "global_step": 626424, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0268828868865967, "global_step": 626425, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9237340688705444, "global_step": 626426, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0190391540527344, "global_step": 626427, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.94285249710083, "global_step": 626428, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9375534057617188, "global_step": 626429, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9882701635360718, "global_step": 626430, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1229562759399414, "global_step": 626431, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0164852142333984, "global_step": 626432, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0124378204345703, "global_step": 626433, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9785407781600952, "global_step": 626434, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0117101669311523, "global_step": 626435, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.932244896888733, "global_step": 626436, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.048635959625244, "global_step": 626437, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.056849479675293, "global_step": 626438, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9512407779693604, "global_step": 626439, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9814941883087158, "global_step": 626440, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.064847469329834, "global_step": 626441, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.020460367202759, "global_step": 626442, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0095324516296387, "global_step": 626443, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.050053834915161, "global_step": 626444, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.984277367591858, "global_step": 626445, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.024350166320801, "global_step": 626446, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.027467727661133, "global_step": 626447, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9211925268173218, "global_step": 626448, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9914257526397705, "global_step": 626449, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0027756690979004, "global_step": 626450, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9404969215393066, "global_step": 626451, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9612921476364136, "global_step": 626452, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0268561840057373, "global_step": 626453, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.991438865661621, "global_step": 626454, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9091070890426636, "global_step": 626455, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9221335649490356, "global_step": 626456, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0092673301696777, "global_step": 626457, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.94640052318573, "global_step": 626458, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0737791061401367, "global_step": 626459, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0313503742218018, "global_step": 626460, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.012267589569092, "global_step": 626461, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1108760833740234, "global_step": 626462, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9132781028747559, "global_step": 626463, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0142934322357178, "global_step": 626464, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9801101684570312, "global_step": 626465, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9173835515975952, "global_step": 626466, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.992766261100769, "global_step": 626467, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.016242504119873, "global_step": 626468, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9479365348815918, "global_step": 626469, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.058485507965088, "global_step": 626470, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9911608695983887, "global_step": 626471, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0086870193481445, "global_step": 626472, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.014169454574585, "global_step": 626473, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.032541275024414, "global_step": 626474, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.074392080307007, "global_step": 626475, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0044162273406982, "global_step": 626476, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9628214836120605, "global_step": 626477, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0259108543395996, "global_step": 626478, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9801855087280273, "global_step": 626479, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9787040948867798, "global_step": 626480, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.04514479637146, "global_step": 626481, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9550325870513916, "global_step": 626482, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.067689895629883, "global_step": 626483, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8426563739776611, "global_step": 626484, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0592849254608154, "global_step": 626485, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9056801795959473, "global_step": 626486, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0412232875823975, "global_step": 626487, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0048909187316895, "global_step": 626488, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9566468000411987, "global_step": 626489, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.038311243057251, "global_step": 626490, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9878796339035034, "global_step": 626491, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0038652420043945, "global_step": 626492, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0025198459625244, "global_step": 626493, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9444724321365356, "global_step": 626494, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0069737434387207, "global_step": 626495, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9913547039031982, "global_step": 626496, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.023587465286255, "global_step": 626497, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9912784099578857, "global_step": 626498, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.998454213142395, "global_step": 626499, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0048828125, "global_step": 626500, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0329701900482178, "global_step": 626501, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9822266101837158, "global_step": 626502, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0331480503082275, "global_step": 626503, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8918079137802124, "global_step": 626504, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9676246643066406, "global_step": 626505, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0108535289764404, "global_step": 626506, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.034397602081299, "global_step": 626507, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0250210762023926, "global_step": 626508, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.04540753364563, "global_step": 626509, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.078003406524658, "global_step": 626510, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.032531976699829, "global_step": 626511, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0722544193267822, "global_step": 626512, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0257108211517334, "global_step": 626513, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0564253330230713, "global_step": 626514, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0091874599456787, "global_step": 626515, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0777108669281006, "global_step": 626516, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9624871015548706, "global_step": 626517, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1173863410949707, "global_step": 626518, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.058143138885498, "global_step": 626519, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0191168785095215, "global_step": 626520, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0294225215911865, "global_step": 626521, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.970062494277954, "global_step": 626522, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.020669937133789, "global_step": 626523, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0626332759857178, "global_step": 626524, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9330192804336548, "global_step": 626525, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.945244550704956, "global_step": 626526, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.117405891418457, "global_step": 626527, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0762569904327393, "global_step": 626528, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.016364336013794, "global_step": 626529, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0039095878601074, "global_step": 626530, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.95723295211792, "global_step": 626531, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0128161907196045, "global_step": 626532, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9778989553451538, "global_step": 626533, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.04217791557312, "global_step": 626534, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.944616675376892, "global_step": 626535, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0330581665039062, "global_step": 626536, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.984430193901062, "global_step": 626537, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9938814640045166, "global_step": 626538, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9756337404251099, "global_step": 626539, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9806832075119019, "global_step": 626540, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9761685132980347, "global_step": 626541, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.044506549835205, "global_step": 626542, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9960289001464844, "global_step": 626543, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0098798274993896, "global_step": 626544, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9793155193328857, "global_step": 626545, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.073432207107544, "global_step": 626546, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9929753541946411, "global_step": 626547, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0221564769744873, "global_step": 626548, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9670090675354004, "global_step": 626549, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8973764181137085, "global_step": 626550, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.022263288497925, "global_step": 626551, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.993389368057251, "global_step": 626552, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0572476387023926, "global_step": 626553, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9374076128005981, "global_step": 626554, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9043986797332764, "global_step": 626555, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9326845407485962, "global_step": 626556, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9943739175796509, "global_step": 626557, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0837090015411377, "global_step": 626558, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0811243057250977, "global_step": 626559, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0353403091430664, "global_step": 626560, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9701313972473145, "global_step": 626561, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9525476694107056, "global_step": 626562, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9690165519714355, "global_step": 626563, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.094175338745117, "global_step": 626564, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9622145891189575, "global_step": 626565, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.92144775390625, "global_step": 626566, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9575666189193726, "global_step": 626567, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9760043621063232, "global_step": 626568, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9468156099319458, "global_step": 626569, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0286526679992676, "global_step": 626570, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9553879499435425, "global_step": 626571, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.971084713935852, "global_step": 626572, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0096123218536377, "global_step": 626573, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9683905839920044, "global_step": 626574, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9826507568359375, "global_step": 626575, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0243213176727295, "global_step": 626576, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.047894239425659, "global_step": 626577, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.014511823654175, "global_step": 626578, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.974348545074463, "global_step": 626579, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.101964235305786, "global_step": 626580, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.038735866546631, "global_step": 626581, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9181162118911743, "global_step": 626582, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0317258834838867, "global_step": 626583, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9831790924072266, "global_step": 626584, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9773873090744019, "global_step": 626585, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9946099519729614, "global_step": 626586, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0560379028320312, "global_step": 626587, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0673649311065674, "global_step": 626588, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9956415891647339, "global_step": 626589, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0433223247528076, "global_step": 626590, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.06320858001709, "global_step": 626591, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.081223487854004, "global_step": 626592, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9903846979141235, "global_step": 626593, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.141411066055298, "global_step": 626594, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.097931385040283, "global_step": 626595, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0147945880889893, "global_step": 626596, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9746819734573364, "global_step": 626597, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.070693254470825, "global_step": 626598, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.06565260887146, "global_step": 626599, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8822435140609741, "global_step": 626600, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9518587589263916, "global_step": 626601, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0039596557617188, "global_step": 626602, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0123517513275146, "global_step": 626603, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9628537893295288, "global_step": 626604, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0191023349761963, "global_step": 626605, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.122143507003784, "global_step": 626606, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.043987989425659, "global_step": 626607, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.011096477508545, "global_step": 626608, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9554616212844849, "global_step": 626609, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.003322124481201, "global_step": 626610, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9620381593704224, "global_step": 626611, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9308109283447266, "global_step": 626612, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9589660167694092, "global_step": 626613, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.026639938354492, "global_step": 626614, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9537580013275146, "global_step": 626615, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9561495780944824, "global_step": 626616, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.056260347366333, "global_step": 626617, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.065701723098755, "global_step": 626618, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.002209186553955, "global_step": 626619, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0651185512542725, "global_step": 626620, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0364959239959717, "global_step": 626621, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9738067388534546, "global_step": 626622, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0440618991851807, "global_step": 626623, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9968419075012207, "global_step": 626624, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0510661602020264, "global_step": 626625, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9471073150634766, "global_step": 626626, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9351173639297485, "global_step": 626627, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.023390293121338, "global_step": 626628, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9581010341644287, "global_step": 626629, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.098963975906372, "global_step": 626630, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.96097993850708, "global_step": 626631, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0591161251068115, "global_step": 626632, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9863746166229248, "global_step": 626633, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0366122722625732, "global_step": 626634, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9665868282318115, "global_step": 626635, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9827467203140259, "global_step": 626636, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0505430698394775, "global_step": 626637, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.011476993560791, "global_step": 626638, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0307252407073975, "global_step": 626639, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.046912908554077, "global_step": 626640, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1260879039764404, "global_step": 626641, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0221495628356934, "global_step": 626642, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.094958782196045, "global_step": 626643, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.992862343788147, "global_step": 626644, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9976245164871216, "global_step": 626645, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9484831094741821, "global_step": 626646, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0137155055999756, "global_step": 626647, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0324697494506836, "global_step": 626648, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0072758197784424, "global_step": 626649, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.988572597503662, "global_step": 626650, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9240082502365112, "global_step": 626651, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9880326986312866, "global_step": 626652, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9830034971237183, "global_step": 626653, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.116769313812256, "global_step": 626654, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0653536319732666, "global_step": 626655, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.028319835662842, "global_step": 626656, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0185701847076416, "global_step": 626657, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0514237880706787, "global_step": 626658, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9626022577285767, "global_step": 626659, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.03192138671875, "global_step": 626660, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9778671264648438, "global_step": 626661, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.084805965423584, "global_step": 626662, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9748226404190063, "global_step": 626663, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9573253393173218, "global_step": 626664, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0103394985198975, "global_step": 626665, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0635769367218018, "global_step": 626666, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.013479709625244, "global_step": 626667, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0733046531677246, "global_step": 626668, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9904513359069824, "global_step": 626669, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0166265964508057, "global_step": 626670, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9718173742294312, "global_step": 626671, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0707175731658936, "global_step": 626672, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0667593479156494, "global_step": 626673, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9692260026931763, "global_step": 626674, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1276865005493164, "global_step": 626675, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9556998014450073, "global_step": 626676, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9636006355285645, "global_step": 626677, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9922796487808228, "global_step": 626678, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.009366273880005, "global_step": 626679, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.064650297164917, "global_step": 626680, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.021352529525757, "global_step": 626681, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0595197677612305, "global_step": 626682, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9768885374069214, "global_step": 626683, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.997112512588501, "global_step": 626684, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9252924919128418, "global_step": 626685, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9934040307998657, "global_step": 626686, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0557634830474854, "global_step": 626687, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.06268048286438, "global_step": 626688, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9563515186309814, "global_step": 626689, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9766865968704224, "global_step": 626690, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9564712047576904, "global_step": 626691, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.044365882873535, "global_step": 626692, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0014407634735107, "global_step": 626693, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9904495477676392, "global_step": 626694, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0691964626312256, "global_step": 626695, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9515130519866943, "global_step": 626696, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.973876953125, "global_step": 626697, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9916369915008545, "global_step": 626698, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.932028889656067, "global_step": 626699, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.955176830291748, "global_step": 626700, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.005101203918457, "global_step": 626701, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0550711154937744, "global_step": 626702, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9641170501708984, "global_step": 626703, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.984753966331482, "global_step": 626704, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0275795459747314, "global_step": 626705, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.964673638343811, "global_step": 626706, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9811238050460815, "global_step": 626707, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9642324447631836, "global_step": 626708, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9960200786590576, "global_step": 626709, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.037482976913452, "global_step": 626710, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0614566802978516, "global_step": 626711, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0409095287323, "global_step": 626712, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9582099914550781, "global_step": 626713, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.978865623474121, "global_step": 626714, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.027536630630493, "global_step": 626715, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9909586906433105, "global_step": 626716, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9397916793823242, "global_step": 626717, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.989176869392395, "global_step": 626718, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9757556915283203, "global_step": 626719, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9761312007904053, "global_step": 626720, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.024292469024658, "global_step": 626721, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.057856559753418, "global_step": 626722, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8893228769302368, "global_step": 626723, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9653843641281128, "global_step": 626724, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9309941530227661, "global_step": 626725, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9829154014587402, "global_step": 626726, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9988269805908203, "global_step": 626727, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9537593126296997, "global_step": 626728, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0330448150634766, "global_step": 626729, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9967286586761475, "global_step": 626730, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9622677564620972, "global_step": 626731, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0580596923828125, "global_step": 626732, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1258742809295654, "global_step": 626733, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9940299987792969, "global_step": 626734, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0332257747650146, "global_step": 626735, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9143930673599243, "global_step": 626736, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9807268381118774, "global_step": 626737, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1082377433776855, "global_step": 626738, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.009655475616455, "global_step": 626739, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.952176809310913, "global_step": 626740, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9756748676300049, "global_step": 626741, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.068787097930908, "global_step": 626742, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0179288387298584, "global_step": 626743, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0313425064086914, "global_step": 626744, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.974596381187439, "global_step": 626745, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9860910177230835, "global_step": 626746, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.011014461517334, "global_step": 626747, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0049235820770264, "global_step": 626748, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.013714551925659, "global_step": 626749, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9858109951019287, "global_step": 626750, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0234615802764893, "global_step": 626751, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9981651306152344, "global_step": 626752, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9668474197387695, "global_step": 626753, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.004955768585205, "global_step": 626754, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0300662517547607, "global_step": 626755, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9856295585632324, "global_step": 626756, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0052366256713867, "global_step": 626757, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9446442127227783, "global_step": 626758, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0361649990081787, "global_step": 626759, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.039245128631592, "global_step": 626760, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9347286224365234, "global_step": 626761, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9950543642044067, "global_step": 626762, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.036004066467285, "global_step": 626763, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.044731855392456, "global_step": 626764, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.018780469894409, "global_step": 626765, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1251590251922607, "global_step": 626766, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.042403221130371, "global_step": 626767, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.976693034172058, "global_step": 626768, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.09001088142395, "global_step": 626769, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.994710922241211, "global_step": 626770, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9718115329742432, "global_step": 626771, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9289754629135132, "global_step": 626772, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0051231384277344, "global_step": 626773, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.089111566543579, "global_step": 626774, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.028491258621216, "global_step": 626775, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.982670783996582, "global_step": 626776, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9575453996658325, "global_step": 626777, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9548990726470947, "global_step": 626778, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9950107336044312, "global_step": 626779, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0508534908294678, "global_step": 626780, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0848820209503174, "global_step": 626781, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0567245483398438, "global_step": 626782, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.007490634918213, "global_step": 626783, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9298056364059448, "global_step": 626784, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9848458766937256, "global_step": 626785, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0117690563201904, "global_step": 626786, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0305593013763428, "global_step": 626787, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.934766411781311, "global_step": 626788, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0806729793548584, "global_step": 626789, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.922160267829895, "global_step": 626790, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0495731830596924, "global_step": 626791, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.030517339706421, "global_step": 626792, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1023669242858887, "global_step": 626793, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9734917879104614, "global_step": 626794, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.023831844329834, "global_step": 626795, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9911494255065918, "global_step": 626796, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9759725332260132, "global_step": 626797, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.06323504447937, "global_step": 626798, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.998018503189087, "global_step": 626799, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9588921070098877, "global_step": 626800, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9950867891311646, "global_step": 626801, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.105640411376953, "global_step": 626802, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0021004676818848, "global_step": 626803, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0074310302734375, "global_step": 626804, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.00273060798645, "global_step": 626805, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9787991046905518, "global_step": 626806, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.971225619316101, "global_step": 626807, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0112338066101074, "global_step": 626808, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.070079803466797, "global_step": 626809, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0368168354034424, "global_step": 626810, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0957398414611816, "global_step": 626811, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9279422760009766, "global_step": 626812, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.961563229560852, "global_step": 626813, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0054657459259033, "global_step": 626814, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.952453851699829, "global_step": 626815, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9887593984603882, "global_step": 626816, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9364489316940308, "global_step": 626817, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9704760313034058, "global_step": 626818, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.973966121673584, "global_step": 626819, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9870176315307617, "global_step": 626820, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9770888090133667, "global_step": 626821, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0776267051696777, "global_step": 626822, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0435781478881836, "global_step": 626823, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.967367172241211, "global_step": 626824, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0686497688293457, "global_step": 626825, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.052757740020752, "global_step": 626826, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9522732496261597, "global_step": 626827, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.999340534210205, "global_step": 626828, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.032351493835449, "global_step": 626829, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0509352684020996, "global_step": 626830, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0067121982574463, "global_step": 626831, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0929322242736816, "global_step": 626832, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.011206865310669, "global_step": 626833, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9474037885665894, "global_step": 626834, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9773294925689697, "global_step": 626835, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1076722145080566, "global_step": 626836, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0143160820007324, "global_step": 626837, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9892065525054932, "global_step": 626838, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9843645095825195, "global_step": 626839, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9441204071044922, "global_step": 626840, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0485923290252686, "global_step": 626841, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0170366764068604, "global_step": 626842, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0784432888031006, "global_step": 626843, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0310404300689697, "global_step": 626844, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0070550441741943, "global_step": 626845, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0429818630218506, "global_step": 626846, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9459339380264282, "global_step": 626847, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9525336027145386, "global_step": 626848, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9439939260482788, "global_step": 626849, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9909788370132446, "global_step": 626850, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9888581037521362, "global_step": 626851, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.012672185897827, "global_step": 626852, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0982606410980225, "global_step": 626853, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.032979965209961, "global_step": 626854, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0286436080932617, "global_step": 626855, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9722492694854736, "global_step": 626856, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.098926067352295, "global_step": 626857, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8993147611618042, "global_step": 626858, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.049166202545166, "global_step": 626859, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.991087794303894, "global_step": 626860, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9145827293395996, "global_step": 626861, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0084145069122314, "global_step": 626862, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.049804210662842, "global_step": 626863, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9579784870147705, "global_step": 626864, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9601540565490723, "global_step": 626865, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9558790922164917, "global_step": 626866, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0766868591308594, "global_step": 626867, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.021291732788086, "global_step": 626868, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0518085956573486, "global_step": 626869, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9592827558517456, "global_step": 626870, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0050582885742188, "global_step": 626871, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8827329874038696, "global_step": 626872, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9005640745162964, "global_step": 626873, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.103072166442871, "global_step": 626874, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9611001014709473, "global_step": 626875, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9853739738464355, "global_step": 626876, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0233154296875, "global_step": 626877, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.944161057472229, "global_step": 626878, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0182950496673584, "global_step": 626879, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.069929838180542, "global_step": 626880, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9300223588943481, "global_step": 626881, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.025836944580078, "global_step": 626882, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0701518058776855, "global_step": 626883, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9772580862045288, "global_step": 626884, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.967617154121399, "global_step": 626885, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.009732961654663, "global_step": 626886, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.010136604309082, "global_step": 626887, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0042638778686523, "global_step": 626888, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0022168159484863, "global_step": 626889, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9352548122406006, "global_step": 626890, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.049314498901367, "global_step": 626891, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.938984751701355, "global_step": 626892, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.10250186920166, "global_step": 626893, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.992736577987671, "global_step": 626894, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.041818380355835, "global_step": 626895, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9499882459640503, "global_step": 626896, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1177444458007812, "global_step": 626897, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9914575815200806, "global_step": 626898, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9933515787124634, "global_step": 626899, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.984397530555725, "global_step": 626900, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.026313066482544, "global_step": 626901, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.02647066116333, "global_step": 626902, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.987903118133545, "global_step": 626903, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.008395195007324, "global_step": 626904, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9781779050827026, "global_step": 626905, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9972823858261108, "global_step": 626906, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9484864473342896, "global_step": 626907, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9378461837768555, "global_step": 626908, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0585875511169434, "global_step": 626909, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9600110054016113, "global_step": 626910, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9377329349517822, "global_step": 626911, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0063235759735107, "global_step": 626912, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9287724494934082, "global_step": 626913, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.002626419067383, "global_step": 626914, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0389480590820312, "global_step": 626915, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0025923252105713, "global_step": 626916, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0461955070495605, "global_step": 626917, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9533588886260986, "global_step": 626918, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.972971796989441, "global_step": 626919, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0687475204467773, "global_step": 626920, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9673103094100952, "global_step": 626921, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.015152931213379, "global_step": 626922, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.99192214012146, "global_step": 626923, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9399604797363281, "global_step": 626924, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9858858585357666, "global_step": 626925, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.049804925918579, "global_step": 626926, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0484423637390137, "global_step": 626927, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9847038984298706, "global_step": 626928, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.95639169216156, "global_step": 626929, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.008212089538574, "global_step": 626930, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9927905797958374, "global_step": 626931, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0079424381256104, "global_step": 626932, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0092499256134033, "global_step": 626933, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9403082132339478, "global_step": 626934, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0230281352996826, "global_step": 626935, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9852418899536133, "global_step": 626936, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0182366371154785, "global_step": 626937, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9390476942062378, "global_step": 626938, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0041964054107666, "global_step": 626939, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.017376184463501, "global_step": 626940, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0064871311187744, "global_step": 626941, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0604169368743896, "global_step": 626942, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9348307847976685, "global_step": 626943, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.019533157348633, "global_step": 626944, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9756299257278442, "global_step": 626945, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.043907403945923, "global_step": 626946, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9833877086639404, "global_step": 626947, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0146217346191406, "global_step": 626948, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9685410261154175, "global_step": 626949, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9758694171905518, "global_step": 626950, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.000492811203003, "global_step": 626951, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0224575996398926, "global_step": 626952, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9927042722702026, "global_step": 626953, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9954742193222046, "global_step": 626954, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.027289628982544, "global_step": 626955, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0054025650024414, "global_step": 626956, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0433173179626465, "global_step": 626957, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9698386192321777, "global_step": 626958, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.97226083278656, "global_step": 626959, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9088919162750244, "global_step": 626960, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0621793270111084, "global_step": 626961, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9494798183441162, "global_step": 626962, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.027308702468872, "global_step": 626963, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.015460252761841, "global_step": 626964, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0490267276763916, "global_step": 626965, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9859720468521118, "global_step": 626966, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.027005910873413, "global_step": 626967, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9512248039245605, "global_step": 626968, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.036763906478882, "global_step": 626969, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9187769889831543, "global_step": 626970, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9364243745803833, "global_step": 626971, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0055224895477295, "global_step": 626972, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9437278509140015, "global_step": 626973, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.954159140586853, "global_step": 626974, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.989938497543335, "global_step": 626975, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.981630802154541, "global_step": 626976, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0455398559570312, "global_step": 626977, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.052762985229492, "global_step": 626978, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0164449214935303, "global_step": 626979, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.089442253112793, "global_step": 626980, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.094740152359009, "global_step": 626981, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0302579402923584, "global_step": 626982, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.981382131576538, "global_step": 626983, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9819316864013672, "global_step": 626984, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0313901901245117, "global_step": 626985, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0609469413757324, "global_step": 626986, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9618096351623535, "global_step": 626987, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0443270206451416, "global_step": 626988, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9711419343948364, "global_step": 626989, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0334322452545166, "global_step": 626990, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0256564617156982, "global_step": 626991, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0760929584503174, "global_step": 626992, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9982389211654663, "global_step": 626993, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0576024055480957, "global_step": 626994, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.058523416519165, "global_step": 626995, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.013376235961914, "global_step": 626996, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9562015533447266, "global_step": 626997, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.00304913520813, "global_step": 626998, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0043270587921143, "global_step": 626999, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.051989793777466, "global_step": 627000, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1153457164764404, "global_step": 627001, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0558183193206787, "global_step": 627002, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9848220348358154, "global_step": 627003, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0102391242980957, "global_step": 627004, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9707225561141968, "global_step": 627005, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9560154676437378, "global_step": 627006, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9718031883239746, "global_step": 627007, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0053231716156006, "global_step": 627008, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9787323474884033, "global_step": 627009, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.965151309967041, "global_step": 627010, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.101573944091797, "global_step": 627011, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.032426118850708, "global_step": 627012, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.99293053150177, "global_step": 627013, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0329055786132812, "global_step": 627014, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0138516426086426, "global_step": 627015, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9726471900939941, "global_step": 627016, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0247628688812256, "global_step": 627017, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.999114990234375, "global_step": 627018, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8889402151107788, "global_step": 627019, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.964961051940918, "global_step": 627020, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9869177341461182, "global_step": 627021, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.892875075340271, "global_step": 627022, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.100508451461792, "global_step": 627023, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9938173294067383, "global_step": 627024, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.015225887298584, "global_step": 627025, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0452964305877686, "global_step": 627026, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9578230381011963, "global_step": 627027, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0105724334716797, "global_step": 627028, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1119964122772217, "global_step": 627029, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0006604194641113, "global_step": 627030, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9903024435043335, "global_step": 627031, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0137529373168945, "global_step": 627032, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.02184796333313, "global_step": 627033, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9773504734039307, "global_step": 627034, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9545766115188599, "global_step": 627035, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0012354850769043, "global_step": 627036, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.033193349838257, "global_step": 627037, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9781486988067627, "global_step": 627038, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0778703689575195, "global_step": 627039, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.052544355392456, "global_step": 627040, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0068466663360596, "global_step": 627041, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9131897687911987, "global_step": 627042, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0800857543945312, "global_step": 627043, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9669573307037354, "global_step": 627044, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0146727561950684, "global_step": 627045, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.033107042312622, "global_step": 627046, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.069498062133789, "global_step": 627047, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0624072551727295, "global_step": 627048, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.015719413757324, "global_step": 627049, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9140610694885254, "global_step": 627050, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.04616117477417, "global_step": 627051, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9469830989837646, "global_step": 627052, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.108778238296509, "global_step": 627053, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9920806884765625, "global_step": 627054, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.086442232131958, "global_step": 627055, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0527896881103516, "global_step": 627056, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0381219387054443, "global_step": 627057, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9354171752929688, "global_step": 627058, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9240111112594604, "global_step": 627059, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.022503614425659, "global_step": 627060, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.045734167098999, "global_step": 627061, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0187647342681885, "global_step": 627062, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1132404804229736, "global_step": 627063, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.015956163406372, "global_step": 627064, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0502817630767822, "global_step": 627065, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9603294134140015, "global_step": 627066, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9875686168670654, "global_step": 627067, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0809719562530518, "global_step": 627068, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9993293285369873, "global_step": 627069, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.941504716873169, "global_step": 627070, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.023805856704712, "global_step": 627071, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.003739356994629, "global_step": 627072, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.029433250427246, "global_step": 627073, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0396804809570312, "global_step": 627074, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0025527477264404, "global_step": 627075, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9753646850585938, "global_step": 627076, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1023313999176025, "global_step": 627077, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0449469089508057, "global_step": 627078, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9632164239883423, "global_step": 627079, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.988302230834961, "global_step": 627080, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9230709075927734, "global_step": 627081, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9922676086425781, "global_step": 627082, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.962392807006836, "global_step": 627083, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.944437026977539, "global_step": 627084, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9074773788452148, "global_step": 627085, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9440556764602661, "global_step": 627086, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0608787536621094, "global_step": 627087, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9415324926376343, "global_step": 627088, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.100054979324341, "global_step": 627089, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9958263635635376, "global_step": 627090, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0299739837646484, "global_step": 627091, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.970335841178894, "global_step": 627092, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9295721054077148, "global_step": 627093, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9978729486465454, "global_step": 627094, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.005417585372925, "global_step": 627095, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8874871730804443, "global_step": 627096, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0581560134887695, "global_step": 627097, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9542521238327026, "global_step": 627098, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9663770198822021, "global_step": 627099, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9337127208709717, "global_step": 627100, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.001601219177246, "global_step": 627101, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.959896445274353, "global_step": 627102, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0490033626556396, "global_step": 627103, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9511430263519287, "global_step": 627104, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9872571229934692, "global_step": 627105, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.01700758934021, "global_step": 627106, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.002790927886963, "global_step": 627107, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9261411428451538, "global_step": 627108, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9999279975891113, "global_step": 627109, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0580904483795166, "global_step": 627110, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0706629753112793, "global_step": 627111, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1096608638763428, "global_step": 627112, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9255036115646362, "global_step": 627113, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9957726001739502, "global_step": 627114, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.119556188583374, "global_step": 627115, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0062448978424072, "global_step": 627116, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9698057174682617, "global_step": 627117, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.052762508392334, "global_step": 627118, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0436999797821045, "global_step": 627119, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9960976839065552, "global_step": 627120, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9889652729034424, "global_step": 627121, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.056863307952881, "global_step": 627122, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9851760864257812, "global_step": 627123, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0004851818084717, "global_step": 627124, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.984230875968933, "global_step": 627125, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.006072521209717, "global_step": 627126, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0215694904327393, "global_step": 627127, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0063388347625732, "global_step": 627128, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9085544347763062, "global_step": 627129, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.02116322517395, "global_step": 627130, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.972313404083252, "global_step": 627131, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.922140121459961, "global_step": 627132, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.985840082168579, "global_step": 627133, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9943890571594238, "global_step": 627134, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0409560203552246, "global_step": 627135, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9746553897857666, "global_step": 627136, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0165483951568604, "global_step": 627137, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.004110097885132, "global_step": 627138, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9409799575805664, "global_step": 627139, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0024478435516357, "global_step": 627140, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.056370735168457, "global_step": 627141, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9996719360351562, "global_step": 627142, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9065552949905396, "global_step": 627143, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1234261989593506, "global_step": 627144, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9595553874969482, "global_step": 627145, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9069832563400269, "global_step": 627146, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.005409002304077, "global_step": 627147, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.019554376602173, "global_step": 627148, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9941675662994385, "global_step": 627149, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9039005041122437, "global_step": 627150, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9993029832839966, "global_step": 627151, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.051861047744751, "global_step": 627152, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.005777359008789, "global_step": 627153, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9815435409545898, "global_step": 627154, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9649243354797363, "global_step": 627155, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9415611028671265, "global_step": 627156, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9346905946731567, "global_step": 627157, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9387292861938477, "global_step": 627158, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.037257432937622, "global_step": 627159, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9940440654754639, "global_step": 627160, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.008338212966919, "global_step": 627161, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0242671966552734, "global_step": 627162, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0037875175476074, "global_step": 627163, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9794756174087524, "global_step": 627164, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9839811325073242, "global_step": 627165, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9986310005187988, "global_step": 627166, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9945249557495117, "global_step": 627167, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.021014928817749, "global_step": 627168, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.00034499168396, "global_step": 627169, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.045682191848755, "global_step": 627170, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9876394271850586, "global_step": 627171, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.013314723968506, "global_step": 627172, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0223777294158936, "global_step": 627173, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.003693103790283, "global_step": 627174, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.981616497039795, "global_step": 627175, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9149119853973389, "global_step": 627176, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9530504941940308, "global_step": 627177, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9812930822372437, "global_step": 627178, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9896810054779053, "global_step": 627179, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0625476837158203, "global_step": 627180, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.986167550086975, "global_step": 627181, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.975932240486145, "global_step": 627182, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.047565460205078, "global_step": 627183, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9469172954559326, "global_step": 627184, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.013411521911621, "global_step": 627185, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0482544898986816, "global_step": 627186, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9971611499786377, "global_step": 627187, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9530869722366333, "global_step": 627188, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9704668521881104, "global_step": 627189, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9633901119232178, "global_step": 627190, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9999910593032837, "global_step": 627191, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9632463455200195, "global_step": 627192, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0373387336730957, "global_step": 627193, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1036179065704346, "global_step": 627194, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.933565616607666, "global_step": 627195, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9872695207595825, "global_step": 627196, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9864524602890015, "global_step": 627197, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0263543128967285, "global_step": 627198, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9312058687210083, "global_step": 627199, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.981873869895935, "global_step": 627200, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0257644653320312, "global_step": 627201, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.013843536376953, "global_step": 627202, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9491965770721436, "global_step": 627203, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9635109901428223, "global_step": 627204, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0185012817382812, "global_step": 627205, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0651021003723145, "global_step": 627206, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8620319366455078, "global_step": 627207, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9135757684707642, "global_step": 627208, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.021637439727783, "global_step": 627209, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9887241125106812, "global_step": 627210, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9944705963134766, "global_step": 627211, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9938383102416992, "global_step": 627212, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9749393463134766, "global_step": 627213, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0091614723205566, "global_step": 627214, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8859671354293823, "global_step": 627215, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9731965065002441, "global_step": 627216, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.963446855545044, "global_step": 627217, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.956229567527771, "global_step": 627218, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9394913911819458, "global_step": 627219, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.077723264694214, "global_step": 627220, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9516189098358154, "global_step": 627221, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9541525840759277, "global_step": 627222, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0148439407348633, "global_step": 627223, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9694477319717407, "global_step": 627224, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0394504070281982, "global_step": 627225, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9733260869979858, "global_step": 627226, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9752386808395386, "global_step": 627227, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.028179883956909, "global_step": 627228, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.967779517173767, "global_step": 627229, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0318493843078613, "global_step": 627230, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.973118782043457, "global_step": 627231, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0999579429626465, "global_step": 627232, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.015265464782715, "global_step": 627233, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.043647289276123, "global_step": 627234, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9492956399917603, "global_step": 627235, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9584975242614746, "global_step": 627236, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9752488136291504, "global_step": 627237, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9401259422302246, "global_step": 627238, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9638844728469849, "global_step": 627239, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0024640560150146, "global_step": 627240, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0440707206726074, "global_step": 627241, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.056969165802002, "global_step": 627242, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1696720123291016, "global_step": 627243, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9606999158859253, "global_step": 627244, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9966250658035278, "global_step": 627245, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9899605512619019, "global_step": 627246, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.095951557159424, "global_step": 627247, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1096396446228027, "global_step": 627248, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9198942184448242, "global_step": 627249, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0001657009124756, "global_step": 627250, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.059647798538208, "global_step": 627251, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0657453536987305, "global_step": 627252, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.12269926071167, "global_step": 627253, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.988169550895691, "global_step": 627254, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.008989095687866, "global_step": 627255, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9077056646347046, "global_step": 627256, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.03176212310791, "global_step": 627257, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.003795862197876, "global_step": 627258, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.023528575897217, "global_step": 627259, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9917070865631104, "global_step": 627260, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.935300588607788, "global_step": 627261, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.047572135925293, "global_step": 627262, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0619349479675293, "global_step": 627263, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0309391021728516, "global_step": 627264, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.054705858230591, "global_step": 627265, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.051710367202759, "global_step": 627266, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0141687393188477, "global_step": 627267, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9420607089996338, "global_step": 627268, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0040407180786133, "global_step": 627269, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0280301570892334, "global_step": 627270, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.991060495376587, "global_step": 627271, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.949354648590088, "global_step": 627272, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9861235618591309, "global_step": 627273, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0680055618286133, "global_step": 627274, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0303869247436523, "global_step": 627275, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.982115626335144, "global_step": 627276, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0354726314544678, "global_step": 627277, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0381085872650146, "global_step": 627278, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9969674348831177, "global_step": 627279, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.055006504058838, "global_step": 627280, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0098814964294434, "global_step": 627281, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0399656295776367, "global_step": 627282, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.025472640991211, "global_step": 627283, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9955508708953857, "global_step": 627284, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.973986029624939, "global_step": 627285, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.065197467803955, "global_step": 627286, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.006397008895874, "global_step": 627287, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9928879737854004, "global_step": 627288, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0271084308624268, "global_step": 627289, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9996522665023804, "global_step": 627290, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9867901802062988, "global_step": 627291, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9084436893463135, "global_step": 627292, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9261703491210938, "global_step": 627293, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9434263706207275, "global_step": 627294, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.003284215927124, "global_step": 627295, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9236656427383423, "global_step": 627296, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0658018589019775, "global_step": 627297, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9496071338653564, "global_step": 627298, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.014164924621582, "global_step": 627299, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.928457260131836, "global_step": 627300, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9529006481170654, "global_step": 627301, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9347035884857178, "global_step": 627302, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0179831981658936, "global_step": 627303, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9729773998260498, "global_step": 627304, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9297728538513184, "global_step": 627305, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.014885902404785, "global_step": 627306, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9459218978881836, "global_step": 627307, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9345759153366089, "global_step": 627308, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.005769729614258, "global_step": 627309, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.01676082611084, "global_step": 627310, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9854440689086914, "global_step": 627311, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9777814149856567, "global_step": 627312, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.116035223007202, "global_step": 627313, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9391056299209595, "global_step": 627314, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9637278318405151, "global_step": 627315, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9594171047210693, "global_step": 627316, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.099590539932251, "global_step": 627317, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0148892402648926, "global_step": 627318, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.940308928489685, "global_step": 627319, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.066059112548828, "global_step": 627320, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0314037799835205, "global_step": 627321, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.014280319213867, "global_step": 627322, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.050816059112549, "global_step": 627323, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.997632384300232, "global_step": 627324, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9101921319961548, "global_step": 627325, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.016974925994873, "global_step": 627326, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9339464902877808, "global_step": 627327, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9776160717010498, "global_step": 627328, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9980754852294922, "global_step": 627329, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9469051361083984, "global_step": 627330, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.985363483428955, "global_step": 627331, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9887739419937134, "global_step": 627332, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0066728591918945, "global_step": 627333, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9669033288955688, "global_step": 627334, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9479389190673828, "global_step": 627335, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0465152263641357, "global_step": 627336, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.004197597503662, "global_step": 627337, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0444040298461914, "global_step": 627338, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.021087408065796, "global_step": 627339, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0501742362976074, "global_step": 627340, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.089526414871216, "global_step": 627341, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0628504753112793, "global_step": 627342, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9581758975982666, "global_step": 627343, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9822733402252197, "global_step": 627344, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9831364154815674, "global_step": 627345, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9390949010849, "global_step": 627346, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9708892107009888, "global_step": 627347, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9141260385513306, "global_step": 627348, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.091618776321411, "global_step": 627349, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0444796085357666, "global_step": 627350, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9521565437316895, "global_step": 627351, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0553886890411377, "global_step": 627352, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9219138622283936, "global_step": 627353, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.025001049041748, "global_step": 627354, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.056509494781494, "global_step": 627355, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9443365335464478, "global_step": 627356, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0514087677001953, "global_step": 627357, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.952449083328247, "global_step": 627358, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9125031232833862, "global_step": 627359, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.977051019668579, "global_step": 627360, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9706425666809082, "global_step": 627361, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1357998847961426, "global_step": 627362, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9017494916915894, "global_step": 627363, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9499480724334717, "global_step": 627364, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0580763816833496, "global_step": 627365, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9907220602035522, "global_step": 627366, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0311574935913086, "global_step": 627367, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.057760238647461, "global_step": 627368, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.005789041519165, "global_step": 627369, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0816874504089355, "global_step": 627370, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0012853145599365, "global_step": 627371, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8779889345169067, "global_step": 627372, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0045337677001953, "global_step": 627373, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0178873538970947, "global_step": 627374, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0455639362335205, "global_step": 627375, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9726924896240234, "global_step": 627376, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9959784746170044, "global_step": 627377, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.102520227432251, "global_step": 627378, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0498809814453125, "global_step": 627379, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.920442819595337, "global_step": 627380, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0734987258911133, "global_step": 627381, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0095863342285156, "global_step": 627382, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0226078033447266, "global_step": 627383, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.014543294906616, "global_step": 627384, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0848450660705566, "global_step": 627385, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.97774338722229, "global_step": 627386, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.007861375808716, "global_step": 627387, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.122236967086792, "global_step": 627388, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.00808048248291, "global_step": 627389, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.971199870109558, "global_step": 627390, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.006294012069702, "global_step": 627391, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9570435285568237, "global_step": 627392, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0058815479278564, "global_step": 627393, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9580575227737427, "global_step": 627394, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0346083641052246, "global_step": 627395, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0619759559631348, "global_step": 627396, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.066716194152832, "global_step": 627397, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9368873834609985, "global_step": 627398, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0425918102264404, "global_step": 627399, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9167927503585815, "global_step": 627400, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9630695581436157, "global_step": 627401, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9302548170089722, "global_step": 627402, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.056955099105835, "global_step": 627403, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9668017625808716, "global_step": 627404, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0368130207061768, "global_step": 627405, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0515074729919434, "global_step": 627406, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0053510665893555, "global_step": 627407, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9767827987670898, "global_step": 627408, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9632223844528198, "global_step": 627409, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9839531183242798, "global_step": 627410, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.043896436691284, "global_step": 627411, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.021472930908203, "global_step": 627412, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.014472246170044, "global_step": 627413, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.051136016845703, "global_step": 627414, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0268540382385254, "global_step": 627415, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.070394277572632, "global_step": 627416, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9584996700286865, "global_step": 627417, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9480738639831543, "global_step": 627418, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0094025135040283, "global_step": 627419, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.027801036834717, "global_step": 627420, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9804803133010864, "global_step": 627421, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.923805832862854, "global_step": 627422, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0570998191833496, "global_step": 627423, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9620239734649658, "global_step": 627424, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.065232038497925, "global_step": 627425, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9800530672073364, "global_step": 627426, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.05599045753479, "global_step": 627427, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.96073317527771, "global_step": 627428, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.094191789627075, "global_step": 627429, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8909715414047241, "global_step": 627430, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9882299900054932, "global_step": 627431, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9889711141586304, "global_step": 627432, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9468778371810913, "global_step": 627433, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9946370124816895, "global_step": 627434, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9554208517074585, "global_step": 627435, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9348456859588623, "global_step": 627436, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.998128890991211, "global_step": 627437, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.943015217781067, "global_step": 627438, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0131797790527344, "global_step": 627439, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9918389320373535, "global_step": 627440, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.958305835723877, "global_step": 627441, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9169230461120605, "global_step": 627442, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0505590438842773, "global_step": 627443, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9730678796768188, "global_step": 627444, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9443262815475464, "global_step": 627445, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0310232639312744, "global_step": 627446, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.071418523788452, "global_step": 627447, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0962445735931396, "global_step": 627448, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.031867742538452, "global_step": 627449, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.954026699066162, "global_step": 627450, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0679433345794678, "global_step": 627451, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9856048822402954, "global_step": 627452, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.018742084503174, "global_step": 627453, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.041255474090576, "global_step": 627454, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9574624300003052, "global_step": 627455, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0049736499786377, "global_step": 627456, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9973618984222412, "global_step": 627457, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.042987108230591, "global_step": 627458, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0270402431488037, "global_step": 627459, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.93976628780365, "global_step": 627460, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9456897974014282, "global_step": 627461, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.044250965118408, "global_step": 627462, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0227630138397217, "global_step": 627463, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9449007511138916, "global_step": 627464, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9322550296783447, "global_step": 627465, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.832105278968811, "global_step": 627466, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1144185066223145, "global_step": 627467, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0017144680023193, "global_step": 627468, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9267933368682861, "global_step": 627469, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.957653522491455, "global_step": 627470, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9440839290618896, "global_step": 627471, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.995249629020691, "global_step": 627472, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.964534044265747, "global_step": 627473, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9360166788101196, "global_step": 627474, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9650137424468994, "global_step": 627475, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.956580638885498, "global_step": 627476, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9932295083999634, "global_step": 627477, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9548704624176025, "global_step": 627478, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9361186027526855, "global_step": 627479, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9391628503799438, "global_step": 627480, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0280590057373047, "global_step": 627481, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.011209011077881, "global_step": 627482, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9031256437301636, "global_step": 627483, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.961620807647705, "global_step": 627484, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9525724649429321, "global_step": 627485, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0886051654815674, "global_step": 627486, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0490853786468506, "global_step": 627487, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.949575662612915, "global_step": 627488, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.048536777496338, "global_step": 627489, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9746184349060059, "global_step": 627490, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9719897508621216, "global_step": 627491, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.061558246612549, "global_step": 627492, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9818105697631836, "global_step": 627493, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.983905553817749, "global_step": 627494, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9809740781784058, "global_step": 627495, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.010185718536377, "global_step": 627496, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0389866828918457, "global_step": 627497, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.937533974647522, "global_step": 627498, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9635809659957886, "global_step": 627499, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9395352602005005, "global_step": 627500, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0360968112945557, "global_step": 627501, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9180935621261597, "global_step": 627502, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.906441569328308, "global_step": 627503, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0030789375305176, "global_step": 627504, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9743731021881104, "global_step": 627505, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0070278644561768, "global_step": 627506, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9306548833847046, "global_step": 627507, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.068957567214966, "global_step": 627508, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0164639949798584, "global_step": 627509, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0183701515197754, "global_step": 627510, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.064138412475586, "global_step": 627511, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.04018497467041, "global_step": 627512, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9943090677261353, "global_step": 627513, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.007756471633911, "global_step": 627514, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0227484703063965, "global_step": 627515, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9965356588363647, "global_step": 627516, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0163214206695557, "global_step": 627517, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0188522338867188, "global_step": 627518, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0469088554382324, "global_step": 627519, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.025857925415039, "global_step": 627520, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.948204755783081, "global_step": 627521, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9621480703353882, "global_step": 627522, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.017160177230835, "global_step": 627523, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0951216220855713, "global_step": 627524, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0242087841033936, "global_step": 627525, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0422422885894775, "global_step": 627526, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9798791408538818, "global_step": 627527, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0164101123809814, "global_step": 627528, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.063563108444214, "global_step": 627529, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0912439823150635, "global_step": 627530, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9762599468231201, "global_step": 627531, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9926296472549438, "global_step": 627532, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9895586967468262, "global_step": 627533, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.013472557067871, "global_step": 627534, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.113055467605591, "global_step": 627535, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8446999788284302, "global_step": 627536, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8836990594863892, "global_step": 627537, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9766043424606323, "global_step": 627538, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.056891441345215, "global_step": 627539, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0617613792419434, "global_step": 627540, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.048602342605591, "global_step": 627541, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9392231702804565, "global_step": 627542, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1189076900482178, "global_step": 627543, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.066419839859009, "global_step": 627544, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9551483392715454, "global_step": 627545, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.016118049621582, "global_step": 627546, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9620431661605835, "global_step": 627547, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9582016468048096, "global_step": 627548, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0078392028808594, "global_step": 627549, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0678980350494385, "global_step": 627550, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9841246604919434, "global_step": 627551, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0504400730133057, "global_step": 627552, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.015266180038452, "global_step": 627553, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.043914318084717, "global_step": 627554, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9973037242889404, "global_step": 627555, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.00413179397583, "global_step": 627556, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0038177967071533, "global_step": 627557, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.067737579345703, "global_step": 627558, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9855338335037231, "global_step": 627559, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.019115924835205, "global_step": 627560, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0177061557769775, "global_step": 627561, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9975736141204834, "global_step": 627562, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.962960958480835, "global_step": 627563, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0232861042022705, "global_step": 627564, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0324461460113525, "global_step": 627565, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0148215293884277, "global_step": 627566, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.004646062850952, "global_step": 627567, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9938572645187378, "global_step": 627568, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0011649131774902, "global_step": 627569, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8922566175460815, "global_step": 627570, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.065052032470703, "global_step": 627571, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9592605829238892, "global_step": 627572, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9765644073486328, "global_step": 627573, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0401880741119385, "global_step": 627574, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.948600172996521, "global_step": 627575, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9681881666183472, "global_step": 627576, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0404434204101562, "global_step": 627577, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9639290571212769, "global_step": 627578, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9466438293457031, "global_step": 627579, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.881737232208252, "global_step": 627580, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0207293033599854, "global_step": 627581, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.015315532684326, "global_step": 627582, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0030224323272705, "global_step": 627583, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0112433433532715, "global_step": 627584, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.041635274887085, "global_step": 627585, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9542416334152222, "global_step": 627586, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.006718397140503, "global_step": 627587, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0099945068359375, "global_step": 627588, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.912423014640808, "global_step": 627589, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.045476198196411, "global_step": 627590, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0287411212921143, "global_step": 627591, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.938815712928772, "global_step": 627592, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.920813798904419, "global_step": 627593, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9199990034103394, "global_step": 627594, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0092947483062744, "global_step": 627595, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9955039024353027, "global_step": 627596, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8996144533157349, "global_step": 627597, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.036031484603882, "global_step": 627598, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.000900983810425, "global_step": 627599, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9802072048187256, "global_step": 627600, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.043041467666626, "global_step": 627601, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9834718704223633, "global_step": 627602, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9048267602920532, "global_step": 627603, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9771028757095337, "global_step": 627604, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0374112129211426, "global_step": 627605, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9806902408599854, "global_step": 627606, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.978015661239624, "global_step": 627607, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9125834703445435, "global_step": 627608, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0468997955322266, "global_step": 627609, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.024052143096924, "global_step": 627610, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0426483154296875, "global_step": 627611, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9301966428756714, "global_step": 627612, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0450210571289062, "global_step": 627613, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0249383449554443, "global_step": 627614, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.060516834259033, "global_step": 627615, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.005384922027588, "global_step": 627616, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9953768253326416, "global_step": 627617, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9978374242782593, "global_step": 627618, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9399489164352417, "global_step": 627619, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.974494457244873, "global_step": 627620, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.99418044090271, "global_step": 627621, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0215654373168945, "global_step": 627622, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.987502098083496, "global_step": 627623, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.10640549659729, "global_step": 627624, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9842289686203003, "global_step": 627625, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.030229091644287, "global_step": 627626, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9736583232879639, "global_step": 627627, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9012044668197632, "global_step": 627628, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9943079948425293, "global_step": 627629, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.98939049243927, "global_step": 627630, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9151837825775146, "global_step": 627631, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.010500431060791, "global_step": 627632, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9409520626068115, "global_step": 627633, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0210177898406982, "global_step": 627634, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.967578411102295, "global_step": 627635, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.991065263748169, "global_step": 627636, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0656983852386475, "global_step": 627637, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.016716241836548, "global_step": 627638, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9755126237869263, "global_step": 627639, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0669894218444824, "global_step": 627640, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.018432855606079, "global_step": 627641, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.004997730255127, "global_step": 627642, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0670418739318848, "global_step": 627643, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9958666563034058, "global_step": 627644, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9774689674377441, "global_step": 627645, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0271027088165283, "global_step": 627646, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9974862337112427, "global_step": 627647, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0298566818237305, "global_step": 627648, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.043616771697998, "global_step": 627649, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9829877614974976, "global_step": 627650, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9367990493774414, "global_step": 627651, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9934927225112915, "global_step": 627652, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9713282585144043, "global_step": 627653, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0327656269073486, "global_step": 627654, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.055004835128784, "global_step": 627655, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9993877410888672, "global_step": 627656, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.963747501373291, "global_step": 627657, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0345349311828613, "global_step": 627658, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0144002437591553, "global_step": 627659, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9338867664337158, "global_step": 627660, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0207138061523438, "global_step": 627661, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.931394100189209, "global_step": 627662, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.07169771194458, "global_step": 627663, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.073326349258423, "global_step": 627664, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0158889293670654, "global_step": 627665, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.072239875793457, "global_step": 627666, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1370794773101807, "global_step": 627667, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9601861238479614, "global_step": 627668, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.063528299331665, "global_step": 627669, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0531365871429443, "global_step": 627670, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9951497316360474, "global_step": 627671, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0303285121917725, "global_step": 627672, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0780155658721924, "global_step": 627673, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9417171478271484, "global_step": 627674, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9258873462677002, "global_step": 627675, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9474351406097412, "global_step": 627676, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0394961833953857, "global_step": 627677, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9988691806793213, "global_step": 627678, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1728341579437256, "global_step": 627679, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0758063793182373, "global_step": 627680, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.016329526901245, "global_step": 627681, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0159409046173096, "global_step": 627682, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0226573944091797, "global_step": 627683, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8971527814865112, "global_step": 627684, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0181663036346436, "global_step": 627685, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.930589199066162, "global_step": 627686, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0588555335998535, "global_step": 627687, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0609850883483887, "global_step": 627688, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.026540756225586, "global_step": 627689, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0119094848632812, "global_step": 627690, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.081451654434204, "global_step": 627691, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0227949619293213, "global_step": 627692, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0536911487579346, "global_step": 627693, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.038388252258301, "global_step": 627694, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9490336179733276, "global_step": 627695, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9227023124694824, "global_step": 627696, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9564456939697266, "global_step": 627697, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.055225372314453, "global_step": 627698, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9921505451202393, "global_step": 627699, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.072995185852051, "global_step": 627700, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9558206796646118, "global_step": 627701, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.995853304862976, "global_step": 627702, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0322892665863037, "global_step": 627703, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9945948123931885, "global_step": 627704, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0884997844696045, "global_step": 627705, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9871392250061035, "global_step": 627706, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9955698251724243, "global_step": 627707, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0088772773742676, "global_step": 627708, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.061159133911133, "global_step": 627709, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9699532985687256, "global_step": 627710, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9720655679702759, "global_step": 627711, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9871634244918823, "global_step": 627712, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9910869598388672, "global_step": 627713, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.003509044647217, "global_step": 627714, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0028493404388428, "global_step": 627715, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.003188371658325, "global_step": 627716, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.068441390991211, "global_step": 627717, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.998302936553955, "global_step": 627718, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8953596353530884, "global_step": 627719, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.97960364818573, "global_step": 627720, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.021374225616455, "global_step": 627721, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.986863613128662, "global_step": 627722, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0616350173950195, "global_step": 627723, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.96833074092865, "global_step": 627724, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.020087718963623, "global_step": 627725, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9642852544784546, "global_step": 627726, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0066962242126465, "global_step": 627727, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9759825468063354, "global_step": 627728, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0169472694396973, "global_step": 627729, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9995064735412598, "global_step": 627730, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.066990852355957, "global_step": 627731, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9352837800979614, "global_step": 627732, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9216517210006714, "global_step": 627733, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9619204998016357, "global_step": 627734, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0229694843292236, "global_step": 627735, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0161831378936768, "global_step": 627736, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9556037187576294, "global_step": 627737, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9895234107971191, "global_step": 627738, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9745943546295166, "global_step": 627739, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9865368604660034, "global_step": 627740, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9693496227264404, "global_step": 627741, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9761085510253906, "global_step": 627742, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0487172603607178, "global_step": 627743, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0162909030914307, "global_step": 627744, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9892137050628662, "global_step": 627745, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0082547664642334, "global_step": 627746, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.026520013809204, "global_step": 627747, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0248701572418213, "global_step": 627748, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9268219470977783, "global_step": 627749, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9786018133163452, "global_step": 627750, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9840792417526245, "global_step": 627751, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9547477960586548, "global_step": 627752, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9440959692001343, "global_step": 627753, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0050206184387207, "global_step": 627754, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9480860233306885, "global_step": 627755, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9485870599746704, "global_step": 627756, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.040663719177246, "global_step": 627757, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9175684452056885, "global_step": 627758, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9546639919281006, "global_step": 627759, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0427980422973633, "global_step": 627760, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0162227153778076, "global_step": 627761, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9818683862686157, "global_step": 627762, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0445988178253174, "global_step": 627763, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9798557758331299, "global_step": 627764, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9926776885986328, "global_step": 627765, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.000624656677246, "global_step": 627766, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0294604301452637, "global_step": 627767, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.022118330001831, "global_step": 627768, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0970590114593506, "global_step": 627769, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.014411449432373, "global_step": 627770, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0044057369232178, "global_step": 627771, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.945960283279419, "global_step": 627772, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0088703632354736, "global_step": 627773, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.000370979309082, "global_step": 627774, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0253679752349854, "global_step": 627775, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0778610706329346, "global_step": 627776, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9503357410430908, "global_step": 627777, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.984822154045105, "global_step": 627778, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9920036792755127, "global_step": 627779, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.004162073135376, "global_step": 627780, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9900164604187012, "global_step": 627781, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.035078287124634, "global_step": 627782, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0161781311035156, "global_step": 627783, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9979733228683472, "global_step": 627784, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.096444845199585, "global_step": 627785, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.958849549293518, "global_step": 627786, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.01900053024292, "global_step": 627787, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0564675331115723, "global_step": 627788, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.088852882385254, "global_step": 627789, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.058505058288574, "global_step": 627790, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9692597389221191, "global_step": 627791, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9672530889511108, "global_step": 627792, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.063570976257324, "global_step": 627793, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0051026344299316, "global_step": 627794, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0477826595306396, "global_step": 627795, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0018746852874756, "global_step": 627796, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0492770671844482, "global_step": 627797, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9531285762786865, "global_step": 627798, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0181095600128174, "global_step": 627799, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0150234699249268, "global_step": 627800, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0801994800567627, "global_step": 627801, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0137510299682617, "global_step": 627802, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.016730308532715, "global_step": 627803, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9689326286315918, "global_step": 627804, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.921639323234558, "global_step": 627805, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9469215869903564, "global_step": 627806, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.021017074584961, "global_step": 627807, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.088266134262085, "global_step": 627808, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.026315927505493, "global_step": 627809, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0108745098114014, "global_step": 627810, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.909618854522705, "global_step": 627811, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.089995861053467, "global_step": 627812, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0888328552246094, "global_step": 627813, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.069384813308716, "global_step": 627814, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0120325088500977, "global_step": 627815, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.002908229827881, "global_step": 627816, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9178187847137451, "global_step": 627817, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.105839729309082, "global_step": 627818, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9772480726242065, "global_step": 627819, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0002968311309814, "global_step": 627820, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9299577474594116, "global_step": 627821, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9373899698257446, "global_step": 627822, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.091151475906372, "global_step": 627823, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.927159309387207, "global_step": 627824, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.005331516265869, "global_step": 627825, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0365209579467773, "global_step": 627826, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9646095037460327, "global_step": 627827, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9597158432006836, "global_step": 627828, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0228445529937744, "global_step": 627829, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0264739990234375, "global_step": 627830, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9453604221343994, "global_step": 627831, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9958583116531372, "global_step": 627832, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.02872633934021, "global_step": 627833, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9618784189224243, "global_step": 627834, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.01332688331604, "global_step": 627835, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.007875442504883, "global_step": 627836, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0239546298980713, "global_step": 627837, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9775110483169556, "global_step": 627838, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9816410541534424, "global_step": 627839, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0189948081970215, "global_step": 627840, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0776476860046387, "global_step": 627841, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0367677211761475, "global_step": 627842, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.941697359085083, "global_step": 627843, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0304391384124756, "global_step": 627844, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.053957462310791, "global_step": 627845, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1370596885681152, "global_step": 627846, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0068140029907227, "global_step": 627847, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9942582845687866, "global_step": 627848, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9241362810134888, "global_step": 627849, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9618291854858398, "global_step": 627850, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.973067045211792, "global_step": 627851, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0384163856506348, "global_step": 627852, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0182316303253174, "global_step": 627853, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9671497344970703, "global_step": 627854, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.126176357269287, "global_step": 627855, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.059753894805908, "global_step": 627856, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9260504245758057, "global_step": 627857, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9947792291641235, "global_step": 627858, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9779126644134521, "global_step": 627859, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0872890949249268, "global_step": 627860, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.088151693344116, "global_step": 627861, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9423680305480957, "global_step": 627862, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.040350914001465, "global_step": 627863, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0721635818481445, "global_step": 627864, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.992669939994812, "global_step": 627865, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0681557655334473, "global_step": 627866, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.039310932159424, "global_step": 627867, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.979400873184204, "global_step": 627868, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.098280906677246, "global_step": 627869, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.956146001815796, "global_step": 627870, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9033067226409912, "global_step": 627871, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0530433654785156, "global_step": 627872, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0685813426971436, "global_step": 627873, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.944616436958313, "global_step": 627874, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9471056461334229, "global_step": 627875, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0033528804779053, "global_step": 627876, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.034449338912964, "global_step": 627877, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.009669303894043, "global_step": 627878, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.977873682975769, "global_step": 627879, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.022292137145996, "global_step": 627880, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0488040447235107, "global_step": 627881, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0265352725982666, "global_step": 627882, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0210800170898438, "global_step": 627883, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9811369180679321, "global_step": 627884, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.048762798309326, "global_step": 627885, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.990388035774231, "global_step": 627886, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0798964500427246, "global_step": 627887, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.913494348526001, "global_step": 627888, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0032246112823486, "global_step": 627889, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0777366161346436, "global_step": 627890, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0438835620880127, "global_step": 627891, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1093289852142334, "global_step": 627892, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.986019492149353, "global_step": 627893, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9266607761383057, "global_step": 627894, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.01277232170105, "global_step": 627895, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1172683238983154, "global_step": 627896, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9766428470611572, "global_step": 627897, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.033020496368408, "global_step": 627898, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9933675527572632, "global_step": 627899, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.035733938217163, "global_step": 627900, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0614519119262695, "global_step": 627901, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0106561183929443, "global_step": 627902, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9848625659942627, "global_step": 627903, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9999593496322632, "global_step": 627904, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9963819980621338, "global_step": 627905, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0410995483398438, "global_step": 627906, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0367202758789062, "global_step": 627907, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1060678958892822, "global_step": 627908, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9938312768936157, "global_step": 627909, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.032766103744507, "global_step": 627910, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0521159172058105, "global_step": 627911, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9158530235290527, "global_step": 627912, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9662355184555054, "global_step": 627913, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9695429801940918, "global_step": 627914, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9415652751922607, "global_step": 627915, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9379138946533203, "global_step": 627916, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9922760725021362, "global_step": 627917, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9419432878494263, "global_step": 627918, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.032546281814575, "global_step": 627919, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0238237380981445, "global_step": 627920, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.107337236404419, "global_step": 627921, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9454725980758667, "global_step": 627922, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.05344557762146, "global_step": 627923, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9851280450820923, "global_step": 627924, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9969674348831177, "global_step": 627925, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0460379123687744, "global_step": 627926, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9794057607650757, "global_step": 627927, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.951686143875122, "global_step": 627928, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9725371599197388, "global_step": 627929, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0856869220733643, "global_step": 627930, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9635182619094849, "global_step": 627931, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9756476879119873, "global_step": 627932, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.031130790710449, "global_step": 627933, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.017693042755127, "global_step": 627934, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.01131534576416, "global_step": 627935, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0090227127075195, "global_step": 627936, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9750380516052246, "global_step": 627937, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.957339882850647, "global_step": 627938, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9555143117904663, "global_step": 627939, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.032728910446167, "global_step": 627940, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0625762939453125, "global_step": 627941, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0018253326416016, "global_step": 627942, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.022502899169922, "global_step": 627943, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.956903338432312, "global_step": 627944, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.969486117362976, "global_step": 627945, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.98319411277771, "global_step": 627946, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0405099391937256, "global_step": 627947, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.971752643585205, "global_step": 627948, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0616819858551025, "global_step": 627949, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.051002264022827, "global_step": 627950, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.078770399093628, "global_step": 627951, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9280064105987549, "global_step": 627952, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0717592239379883, "global_step": 627953, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.048276901245117, "global_step": 627954, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1085383892059326, "global_step": 627955, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.010235071182251, "global_step": 627956, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0130422115325928, "global_step": 627957, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.006892204284668, "global_step": 627958, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0445830821990967, "global_step": 627959, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9244177341461182, "global_step": 627960, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9695795774459839, "global_step": 627961, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9964261054992676, "global_step": 627962, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.084972858428955, "global_step": 627963, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0196704864501953, "global_step": 627964, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.941956639289856, "global_step": 627965, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9981383085250854, "global_step": 627966, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1162073612213135, "global_step": 627967, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.028392791748047, "global_step": 627968, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.051985740661621, "global_step": 627969, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.029071807861328, "global_step": 627970, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0005271434783936, "global_step": 627971, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.979404091835022, "global_step": 627972, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.950534462928772, "global_step": 627973, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.992217779159546, "global_step": 627974, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9607999324798584, "global_step": 627975, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9774222373962402, "global_step": 627976, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.001110076904297, "global_step": 627977, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.961479663848877, "global_step": 627978, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.017359972000122, "global_step": 627979, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9672431945800781, "global_step": 627980, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0217812061309814, "global_step": 627981, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0884463787078857, "global_step": 627982, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9923813343048096, "global_step": 627983, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9611003398895264, "global_step": 627984, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9910070896148682, "global_step": 627985, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9439504146575928, "global_step": 627986, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0150866508483887, "global_step": 627987, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.933362603187561, "global_step": 627988, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0729897022247314, "global_step": 627989, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9764063358306885, "global_step": 627990, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.011090040206909, "global_step": 627991, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.053713798522949, "global_step": 627992, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.03488826751709, "global_step": 627993, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9915599822998047, "global_step": 627994, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9993418455123901, "global_step": 627995, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.037332534790039, "global_step": 627996, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.061675786972046, "global_step": 627997, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.970293641090393, "global_step": 627998, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0370125770568848, "global_step": 627999, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.028031826019287, "global_step": 628000, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9417296648025513, "global_step": 628001, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.995235562324524, "global_step": 628002, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.01823353767395, "global_step": 628003, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.020427703857422, "global_step": 628004, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9971495866775513, "global_step": 628005, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.040985584259033, "global_step": 628006, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9692797660827637, "global_step": 628007, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.003357410430908, "global_step": 628008, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9624896049499512, "global_step": 628009, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9230449199676514, "global_step": 628010, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0469744205474854, "global_step": 628011, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0063188076019287, "global_step": 628012, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9605841636657715, "global_step": 628013, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9780675172805786, "global_step": 628014, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0079057216644287, "global_step": 628015, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0241379737854004, "global_step": 628016, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1770951747894287, "global_step": 628017, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0161118507385254, "global_step": 628018, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0611965656280518, "global_step": 628019, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9184683561325073, "global_step": 628020, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1436381340026855, "global_step": 628021, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0548853874206543, "global_step": 628022, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.029015302658081, "global_step": 628023, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0142290592193604, "global_step": 628024, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0489864349365234, "global_step": 628025, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.00933837890625, "global_step": 628026, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9366984367370605, "global_step": 628027, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.018707752227783, "global_step": 628028, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0044658184051514, "global_step": 628029, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9700219631195068, "global_step": 628030, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9636783599853516, "global_step": 628031, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9915883541107178, "global_step": 628032, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9761533737182617, "global_step": 628033, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9962064027786255, "global_step": 628034, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8860223293304443, "global_step": 628035, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.029008150100708, "global_step": 628036, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.099881410598755, "global_step": 628037, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9699745178222656, "global_step": 628038, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9747933149337769, "global_step": 628039, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0315065383911133, "global_step": 628040, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.002220630645752, "global_step": 628041, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9867478609085083, "global_step": 628042, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9852322340011597, "global_step": 628043, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.001465320587158, "global_step": 628044, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0293850898742676, "global_step": 628045, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0430219173431396, "global_step": 628046, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9925756454467773, "global_step": 628047, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9951319694519043, "global_step": 628048, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.979672908782959, "global_step": 628049, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.028804063796997, "global_step": 628050, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9260761737823486, "global_step": 628051, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.017946243286133, "global_step": 628052, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0312232971191406, "global_step": 628053, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9982175827026367, "global_step": 628054, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9401531219482422, "global_step": 628055, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0077624320983887, "global_step": 628056, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9646342992782593, "global_step": 628057, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.068899154663086, "global_step": 628058, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0211167335510254, "global_step": 628059, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0083093643188477, "global_step": 628060, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0084643363952637, "global_step": 628061, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0126750469207764, "global_step": 628062, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9370718002319336, "global_step": 628063, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0707836151123047, "global_step": 628064, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9503697156906128, "global_step": 628065, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0285050868988037, "global_step": 628066, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9526571035385132, "global_step": 628067, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0234413146972656, "global_step": 628068, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9168318510055542, "global_step": 628069, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9401289224624634, "global_step": 628070, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.081847906112671, "global_step": 628071, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0611000061035156, "global_step": 628072, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.018497943878174, "global_step": 628073, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.899492859840393, "global_step": 628074, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9804985523223877, "global_step": 628075, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.946516752243042, "global_step": 628076, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.078033447265625, "global_step": 628077, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.029444694519043, "global_step": 628078, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9876991510391235, "global_step": 628079, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9762192964553833, "global_step": 628080, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9524589776992798, "global_step": 628081, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9473237991333008, "global_step": 628082, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9786732196807861, "global_step": 628083, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0584239959716797, "global_step": 628084, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9341721534729004, "global_step": 628085, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0144946575164795, "global_step": 628086, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9780319929122925, "global_step": 628087, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9179565906524658, "global_step": 628088, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9643172025680542, "global_step": 628089, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9860717058181763, "global_step": 628090, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0420567989349365, "global_step": 628091, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0333104133605957, "global_step": 628092, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9910733699798584, "global_step": 628093, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.92255437374115, "global_step": 628094, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.086927652359009, "global_step": 628095, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.031736373901367, "global_step": 628096, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.993606448173523, "global_step": 628097, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.063140630722046, "global_step": 628098, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9596624374389648, "global_step": 628099, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9845330715179443, "global_step": 628100, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0667781829833984, "global_step": 628101, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0052437782287598, "global_step": 628102, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0236587524414062, "global_step": 628103, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9752898216247559, "global_step": 628104, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.979823350906372, "global_step": 628105, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8802714347839355, "global_step": 628106, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9886358976364136, "global_step": 628107, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.034595012664795, "global_step": 628108, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9956474304199219, "global_step": 628109, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0104246139526367, "global_step": 628110, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9465075731277466, "global_step": 628111, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9155235290527344, "global_step": 628112, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.019987106323242, "global_step": 628113, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0270307064056396, "global_step": 628114, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9268893003463745, "global_step": 628115, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0476508140563965, "global_step": 628116, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.047408103942871, "global_step": 628117, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0343971252441406, "global_step": 628118, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0669031143188477, "global_step": 628119, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0571460723876953, "global_step": 628120, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9790031909942627, "global_step": 628121, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0534613132476807, "global_step": 628122, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9256551265716553, "global_step": 628123, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9771147966384888, "global_step": 628124, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.010093927383423, "global_step": 628125, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0378358364105225, "global_step": 628126, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0434610843658447, "global_step": 628127, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.057244062423706, "global_step": 628128, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9604034423828125, "global_step": 628129, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0384480953216553, "global_step": 628130, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0254154205322266, "global_step": 628131, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0013363361358643, "global_step": 628132, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.986862063407898, "global_step": 628133, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.974378228187561, "global_step": 628134, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9980002641677856, "global_step": 628135, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.929697036743164, "global_step": 628136, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0386383533477783, "global_step": 628137, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9559351205825806, "global_step": 628138, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0477476119995117, "global_step": 628139, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9837123155593872, "global_step": 628140, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.008777379989624, "global_step": 628141, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.008030652999878, "global_step": 628142, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.963979721069336, "global_step": 628143, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.976529598236084, "global_step": 628144, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0024240016937256, "global_step": 628145, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0671346187591553, "global_step": 628146, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.993991732597351, "global_step": 628147, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.941733956336975, "global_step": 628148, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9791017770767212, "global_step": 628149, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.935662865638733, "global_step": 628150, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0082693099975586, "global_step": 628151, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0775251388549805, "global_step": 628152, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0568649768829346, "global_step": 628153, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0322492122650146, "global_step": 628154, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9971054792404175, "global_step": 628155, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9632023572921753, "global_step": 628156, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9272539615631104, "global_step": 628157, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0229153633117676, "global_step": 628158, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.939793586730957, "global_step": 628159, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9888434410095215, "global_step": 628160, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9899791479110718, "global_step": 628161, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0177547931671143, "global_step": 628162, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0849320888519287, "global_step": 628163, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.001236915588379, "global_step": 628164, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9740073680877686, "global_step": 628165, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9704982042312622, "global_step": 628166, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0263595581054688, "global_step": 628167, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0729212760925293, "global_step": 628168, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.014678478240967, "global_step": 628169, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0112850666046143, "global_step": 628170, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9518311023712158, "global_step": 628171, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8992667198181152, "global_step": 628172, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9743305444717407, "global_step": 628173, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.92444908618927, "global_step": 628174, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.976879596710205, "global_step": 628175, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9675179719924927, "global_step": 628176, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.985517144203186, "global_step": 628177, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9116297960281372, "global_step": 628178, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9322822093963623, "global_step": 628179, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.033233165740967, "global_step": 628180, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.108717203140259, "global_step": 628181, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.003002166748047, "global_step": 628182, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.923539161682129, "global_step": 628183, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.038933277130127, "global_step": 628184, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9996236562728882, "global_step": 628185, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1104516983032227, "global_step": 628186, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1257522106170654, "global_step": 628187, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0472376346588135, "global_step": 628188, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9999486207962036, "global_step": 628189, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0342743396759033, "global_step": 628190, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9819633960723877, "global_step": 628191, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9876420497894287, "global_step": 628192, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9839369058609009, "global_step": 628193, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1236534118652344, "global_step": 628194, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9757765531539917, "global_step": 628195, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.042602062225342, "global_step": 628196, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9942911863327026, "global_step": 628197, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0317952632904053, "global_step": 628198, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.043395519256592, "global_step": 628199, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0181190967559814, "global_step": 628200, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9914814233779907, "global_step": 628201, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9838087558746338, "global_step": 628202, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0080549716949463, "global_step": 628203, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0257368087768555, "global_step": 628204, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0196340084075928, "global_step": 628205, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0350966453552246, "global_step": 628206, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0530893802642822, "global_step": 628207, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.983526349067688, "global_step": 628208, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9853250980377197, "global_step": 628209, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.906690001487732, "global_step": 628210, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0040271282196045, "global_step": 628211, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9695446491241455, "global_step": 628212, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9862326383590698, "global_step": 628213, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9143294095993042, "global_step": 628214, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.002279043197632, "global_step": 628215, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0340826511383057, "global_step": 628216, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9879026412963867, "global_step": 628217, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9451913833618164, "global_step": 628218, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0379862785339355, "global_step": 628219, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9486056566238403, "global_step": 628220, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9672753810882568, "global_step": 628221, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9546440839767456, "global_step": 628222, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.059995651245117, "global_step": 628223, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.045391082763672, "global_step": 628224, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9272876977920532, "global_step": 628225, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0058891773223877, "global_step": 628226, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0677950382232666, "global_step": 628227, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.954920768737793, "global_step": 628228, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9964755773544312, "global_step": 628229, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9686821699142456, "global_step": 628230, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.024456024169922, "global_step": 628231, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9913952350616455, "global_step": 628232, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9999363422393799, "global_step": 628233, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.016871690750122, "global_step": 628234, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9624472856521606, "global_step": 628235, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.00101637840271, "global_step": 628236, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.002392053604126, "global_step": 628237, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0670242309570312, "global_step": 628238, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9259687662124634, "global_step": 628239, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.121142625808716, "global_step": 628240, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.048110008239746, "global_step": 628241, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9480111598968506, "global_step": 628242, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.028891086578369, "global_step": 628243, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.947910189628601, "global_step": 628244, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.063528060913086, "global_step": 628245, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.029740571975708, "global_step": 628246, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.038303852081299, "global_step": 628247, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.987670660018921, "global_step": 628248, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.023200273513794, "global_step": 628249, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.025996685028076, "global_step": 628250, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.027029037475586, "global_step": 628251, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.006667375564575, "global_step": 628252, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9232314825057983, "global_step": 628253, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9575121402740479, "global_step": 628254, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9797303676605225, "global_step": 628255, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9937877655029297, "global_step": 628256, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9562101364135742, "global_step": 628257, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9166696071624756, "global_step": 628258, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0236876010894775, "global_step": 628259, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0246291160583496, "global_step": 628260, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.060478687286377, "global_step": 628261, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0140931606292725, "global_step": 628262, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.977718710899353, "global_step": 628263, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0509727001190186, "global_step": 628264, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9814633131027222, "global_step": 628265, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0226521492004395, "global_step": 628266, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9622886180877686, "global_step": 628267, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0807998180389404, "global_step": 628268, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9698940515518188, "global_step": 628269, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.969106912612915, "global_step": 628270, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0672128200531006, "global_step": 628271, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.004265546798706, "global_step": 628272, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0030417442321777, "global_step": 628273, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.009894371032715, "global_step": 628274, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9930996894836426, "global_step": 628275, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0559213161468506, "global_step": 628276, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9761619567871094, "global_step": 628277, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0098073482513428, "global_step": 628278, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9256805181503296, "global_step": 628279, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0028250217437744, "global_step": 628280, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9123797416687012, "global_step": 628281, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0233943462371826, "global_step": 628282, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.014577865600586, "global_step": 628283, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0266776084899902, "global_step": 628284, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.991194486618042, "global_step": 628285, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9001649618148804, "global_step": 628286, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.040454864501953, "global_step": 628287, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.028756856918335, "global_step": 628288, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9718719720840454, "global_step": 628289, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0199975967407227, "global_step": 628290, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0181052684783936, "global_step": 628291, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9050462245941162, "global_step": 628292, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9784013032913208, "global_step": 628293, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9657050371170044, "global_step": 628294, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9968225955963135, "global_step": 628295, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.021972417831421, "global_step": 628296, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0138587951660156, "global_step": 628297, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.035879135131836, "global_step": 628298, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9488128423690796, "global_step": 628299, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.030829906463623, "global_step": 628300, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0039002895355225, "global_step": 628301, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9982746839523315, "global_step": 628302, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9966646432876587, "global_step": 628303, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9556427001953125, "global_step": 628304, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.019930601119995, "global_step": 628305, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9899592399597168, "global_step": 628306, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.07407546043396, "global_step": 628307, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9633361101150513, "global_step": 628308, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.00644588470459, "global_step": 628309, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9763964414596558, "global_step": 628310, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.975665807723999, "global_step": 628311, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9310345649719238, "global_step": 628312, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.063485622406006, "global_step": 628313, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9240742921829224, "global_step": 628314, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9929076433181763, "global_step": 628315, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.991068959236145, "global_step": 628316, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9835890531539917, "global_step": 628317, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0210158824920654, "global_step": 628318, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0443227291107178, "global_step": 628319, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9219801425933838, "global_step": 628320, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0078935623168945, "global_step": 628321, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.001647710800171, "global_step": 628322, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9663232564926147, "global_step": 628323, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0707497596740723, "global_step": 628324, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0104856491088867, "global_step": 628325, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.936089038848877, "global_step": 628326, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0218708515167236, "global_step": 628327, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0329272747039795, "global_step": 628328, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9691613912582397, "global_step": 628329, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1036720275878906, "global_step": 628330, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9813392162322998, "global_step": 628331, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9449377059936523, "global_step": 628332, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0012435913085938, "global_step": 628333, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9718680381774902, "global_step": 628334, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.020646810531616, "global_step": 628335, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.069368839263916, "global_step": 628336, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9335808753967285, "global_step": 628337, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.085688591003418, "global_step": 628338, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0182113647460938, "global_step": 628339, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9500484466552734, "global_step": 628340, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9842255115509033, "global_step": 628341, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9793111085891724, "global_step": 628342, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0130200386047363, "global_step": 628343, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0054256916046143, "global_step": 628344, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9484940767288208, "global_step": 628345, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9527760744094849, "global_step": 628346, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8702797889709473, "global_step": 628347, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.08205246925354, "global_step": 628348, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.068525552749634, "global_step": 628349, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.120455503463745, "global_step": 628350, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.017148971557617, "global_step": 628351, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0458803176879883, "global_step": 628352, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9949052333831787, "global_step": 628353, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9733576774597168, "global_step": 628354, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.997544288635254, "global_step": 628355, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.006868362426758, "global_step": 628356, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9684158563613892, "global_step": 628357, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.011282205581665, "global_step": 628358, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9921619892120361, "global_step": 628359, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9408702850341797, "global_step": 628360, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.029991388320923, "global_step": 628361, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.005459785461426, "global_step": 628362, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9507420063018799, "global_step": 628363, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9564893245697021, "global_step": 628364, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.968722939491272, "global_step": 628365, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0541160106658936, "global_step": 628366, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0702579021453857, "global_step": 628367, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0556280612945557, "global_step": 628368, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0189404487609863, "global_step": 628369, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8966108560562134, "global_step": 628370, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9975920915603638, "global_step": 628371, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9247502088546753, "global_step": 628372, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9557753801345825, "global_step": 628373, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9545879364013672, "global_step": 628374, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0175654888153076, "global_step": 628375, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0109810829162598, "global_step": 628376, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9346234798431396, "global_step": 628377, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0418267250061035, "global_step": 628378, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9192125797271729, "global_step": 628379, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.047910213470459, "global_step": 628380, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8977712392807007, "global_step": 628381, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9798932075500488, "global_step": 628382, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.002889633178711, "global_step": 628383, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9345073699951172, "global_step": 628384, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.998489499092102, "global_step": 628385, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.029205799102783, "global_step": 628386, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0585849285125732, "global_step": 628387, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0559539794921875, "global_step": 628388, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.000765085220337, "global_step": 628389, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.037198543548584, "global_step": 628390, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9443084001541138, "global_step": 628391, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.033149003982544, "global_step": 628392, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.035860300064087, "global_step": 628393, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0389890670776367, "global_step": 628394, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.997933268547058, "global_step": 628395, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9982482194900513, "global_step": 628396, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.987511157989502, "global_step": 628397, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9651806354522705, "global_step": 628398, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9518479108810425, "global_step": 628399, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0722134113311768, "global_step": 628400, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0361902713775635, "global_step": 628401, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0097179412841797, "global_step": 628402, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.077214479446411, "global_step": 628403, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.024091958999634, "global_step": 628404, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0090184211730957, "global_step": 628405, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.965986728668213, "global_step": 628406, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.991210699081421, "global_step": 628407, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0258474349975586, "global_step": 628408, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0675673484802246, "global_step": 628409, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.050219774246216, "global_step": 628410, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9725446701049805, "global_step": 628411, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.068479299545288, "global_step": 628412, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.004073143005371, "global_step": 628413, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9822900295257568, "global_step": 628414, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9449236392974854, "global_step": 628415, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.037689685821533, "global_step": 628416, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9683599472045898, "global_step": 628417, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.971473217010498, "global_step": 628418, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9815220832824707, "global_step": 628419, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9042731523513794, "global_step": 628420, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0108113288879395, "global_step": 628421, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0339412689208984, "global_step": 628422, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0499534606933594, "global_step": 628423, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0575647354125977, "global_step": 628424, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0098178386688232, "global_step": 628425, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9565341472625732, "global_step": 628426, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0177576541900635, "global_step": 628427, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.999894142150879, "global_step": 628428, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.085615634918213, "global_step": 628429, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9714106321334839, "global_step": 628430, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0312278270721436, "global_step": 628431, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.021214723587036, "global_step": 628432, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0714035034179688, "global_step": 628433, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9413609504699707, "global_step": 628434, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.987117052078247, "global_step": 628435, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.027439594268799, "global_step": 628436, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0608291625976562, "global_step": 628437, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.04134464263916, "global_step": 628438, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.051679849624634, "global_step": 628439, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.063737630844116, "global_step": 628440, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9701818227767944, "global_step": 628441, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0273683071136475, "global_step": 628442, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9661184549331665, "global_step": 628443, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0852444171905518, "global_step": 628444, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.871335506439209, "global_step": 628445, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9941507577896118, "global_step": 628446, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9631435871124268, "global_step": 628447, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9798341989517212, "global_step": 628448, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0517663955688477, "global_step": 628449, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9513742923736572, "global_step": 628450, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9985237121582031, "global_step": 628451, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9780126810073853, "global_step": 628452, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.024657964706421, "global_step": 628453, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.071091890335083, "global_step": 628454, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.985992670059204, "global_step": 628455, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.008735179901123, "global_step": 628456, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9819221496582031, "global_step": 628457, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0629398822784424, "global_step": 628458, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0171732902526855, "global_step": 628459, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0852105617523193, "global_step": 628460, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.979273796081543, "global_step": 628461, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9763027429580688, "global_step": 628462, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.002228260040283, "global_step": 628463, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9422913789749146, "global_step": 628464, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0205254554748535, "global_step": 628465, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0186753273010254, "global_step": 628466, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.088031530380249, "global_step": 628467, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.901711344718933, "global_step": 628468, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9991402626037598, "global_step": 628469, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.018148899078369, "global_step": 628470, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9670249223709106, "global_step": 628471, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.112495183944702, "global_step": 628472, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9531681537628174, "global_step": 628473, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9726676940917969, "global_step": 628474, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.04763126373291, "global_step": 628475, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9537360668182373, "global_step": 628476, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1292762756347656, "global_step": 628477, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.970567226409912, "global_step": 628478, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9428664445877075, "global_step": 628479, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.018399238586426, "global_step": 628480, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0036697387695312, "global_step": 628481, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.010883331298828, "global_step": 628482, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9835036993026733, "global_step": 628483, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0550973415374756, "global_step": 628484, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.004595994949341, "global_step": 628485, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9304254055023193, "global_step": 628486, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.941993236541748, "global_step": 628487, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.043584108352661, "global_step": 628488, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.02128267288208, "global_step": 628489, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9260258674621582, "global_step": 628490, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.060980796813965, "global_step": 628491, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0138566493988037, "global_step": 628492, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9884164333343506, "global_step": 628493, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8512719869613647, "global_step": 628494, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8931684494018555, "global_step": 628495, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.112452268600464, "global_step": 628496, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0180039405822754, "global_step": 628497, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.043900728225708, "global_step": 628498, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.002467393875122, "global_step": 628499, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0155820846557617, "global_step": 628500, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.993451476097107, "global_step": 628501, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9493591785430908, "global_step": 628502, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9997057914733887, "global_step": 628503, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9536930322647095, "global_step": 628504, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9997586011886597, "global_step": 628505, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9840118885040283, "global_step": 628506, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.959713101387024, "global_step": 628507, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9532105922698975, "global_step": 628508, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.021779775619507, "global_step": 628509, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9604684114456177, "global_step": 628510, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0529139041900635, "global_step": 628511, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.039361000061035, "global_step": 628512, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9575283527374268, "global_step": 628513, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0329411029815674, "global_step": 628514, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9900543689727783, "global_step": 628515, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0398080348968506, "global_step": 628516, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0291950702667236, "global_step": 628517, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0397441387176514, "global_step": 628518, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.009793758392334, "global_step": 628519, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.000195264816284, "global_step": 628520, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0330471992492676, "global_step": 628521, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9853872060775757, "global_step": 628522, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0318756103515625, "global_step": 628523, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.016986608505249, "global_step": 628524, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9711260795593262, "global_step": 628525, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9888637065887451, "global_step": 628526, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0821080207824707, "global_step": 628527, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9956684112548828, "global_step": 628528, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9702798128128052, "global_step": 628529, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.068901777267456, "global_step": 628530, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.073216676712036, "global_step": 628531, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9716557264328003, "global_step": 628532, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0071113109588623, "global_step": 628533, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9507958889007568, "global_step": 628534, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0738439559936523, "global_step": 628535, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9632173776626587, "global_step": 628536, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.945108413696289, "global_step": 628537, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.96889066696167, "global_step": 628538, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0695271492004395, "global_step": 628539, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.989051342010498, "global_step": 628540, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.967079997062683, "global_step": 628541, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.102543830871582, "global_step": 628542, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0355324745178223, "global_step": 628543, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9623931646347046, "global_step": 628544, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0019445419311523, "global_step": 628545, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9677066802978516, "global_step": 628546, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9433013200759888, "global_step": 628547, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.030311346054077, "global_step": 628548, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.020122528076172, "global_step": 628549, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.009873390197754, "global_step": 628550, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.996424674987793, "global_step": 628551, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9201931953430176, "global_step": 628552, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9713717699050903, "global_step": 628553, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.031440258026123, "global_step": 628554, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0912301540374756, "global_step": 628555, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.049196720123291, "global_step": 628556, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.037834882736206, "global_step": 628557, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0253145694732666, "global_step": 628558, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9814165830612183, "global_step": 628559, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9671427011489868, "global_step": 628560, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0948009490966797, "global_step": 628561, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.002479076385498, "global_step": 628562, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9692906141281128, "global_step": 628563, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0103135108947754, "global_step": 628564, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9702540636062622, "global_step": 628565, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9782449007034302, "global_step": 628566, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0207395553588867, "global_step": 628567, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0161266326904297, "global_step": 628568, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.009807825088501, "global_step": 628569, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9181092977523804, "global_step": 628570, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9664990901947021, "global_step": 628571, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.029472589492798, "global_step": 628572, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9736056327819824, "global_step": 628573, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9955954551696777, "global_step": 628574, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0522286891937256, "global_step": 628575, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9600917100906372, "global_step": 628576, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9804401397705078, "global_step": 628577, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.020759344100952, "global_step": 628578, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.964294195175171, "global_step": 628579, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.000424385070801, "global_step": 628580, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0658302307128906, "global_step": 628581, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0327584743499756, "global_step": 628582, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0365588665008545, "global_step": 628583, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.006624937057495, "global_step": 628584, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9944790601730347, "global_step": 628585, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.050844669342041, "global_step": 628586, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.061380624771118, "global_step": 628587, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.026205062866211, "global_step": 628588, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0136160850524902, "global_step": 628589, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.900235891342163, "global_step": 628590, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.948047399520874, "global_step": 628591, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0642597675323486, "global_step": 628592, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9749982357025146, "global_step": 628593, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0149991512298584, "global_step": 628594, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.998785138130188, "global_step": 628595, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9710358381271362, "global_step": 628596, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0049445629119873, "global_step": 628597, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.953770399093628, "global_step": 628598, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9795054197311401, "global_step": 628599, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9757063388824463, "global_step": 628600, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.959917426109314, "global_step": 628601, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0171515941619873, "global_step": 628602, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9489511251449585, "global_step": 628603, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0488853454589844, "global_step": 628604, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9675118923187256, "global_step": 628605, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.010788679122925, "global_step": 628606, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.044168710708618, "global_step": 628607, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.005394458770752, "global_step": 628608, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9424527883529663, "global_step": 628609, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9630790948867798, "global_step": 628610, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0953638553619385, "global_step": 628611, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0032873153686523, "global_step": 628612, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0529158115386963, "global_step": 628613, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.099484443664551, "global_step": 628614, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0005571842193604, "global_step": 628615, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9964733123779297, "global_step": 628616, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0712971687316895, "global_step": 628617, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9992636442184448, "global_step": 628618, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0895133018493652, "global_step": 628619, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9255125522613525, "global_step": 628620, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9664591550827026, "global_step": 628621, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.049208641052246, "global_step": 628622, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9030197858810425, "global_step": 628623, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0179603099823, "global_step": 628624, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0523877143859863, "global_step": 628625, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9268254041671753, "global_step": 628626, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.072193145751953, "global_step": 628627, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0795483589172363, "global_step": 628628, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9821581840515137, "global_step": 628629, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9257287979125977, "global_step": 628630, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1054975986480713, "global_step": 628631, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9664641618728638, "global_step": 628632, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9265718460083008, "global_step": 628633, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9616588354110718, "global_step": 628634, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9897500276565552, "global_step": 628635, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9526017904281616, "global_step": 628636, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0466485023498535, "global_step": 628637, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9952776432037354, "global_step": 628638, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9665518999099731, "global_step": 628639, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0165975093841553, "global_step": 628640, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9858564138412476, "global_step": 628641, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.914088487625122, "global_step": 628642, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9845209121704102, "global_step": 628643, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9637950658798218, "global_step": 628644, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9855232238769531, "global_step": 628645, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9990895986557007, "global_step": 628646, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.937294602394104, "global_step": 628647, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9632325172424316, "global_step": 628648, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.983765959739685, "global_step": 628649, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0508086681365967, "global_step": 628650, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.066688299179077, "global_step": 628651, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0282561779022217, "global_step": 628652, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.964860439300537, "global_step": 628653, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.991625189781189, "global_step": 628654, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.982556939125061, "global_step": 628655, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0075700283050537, "global_step": 628656, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9184738397598267, "global_step": 628657, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.000336170196533, "global_step": 628658, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.926613688468933, "global_step": 628659, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.054503917694092, "global_step": 628660, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0694117546081543, "global_step": 628661, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0538225173950195, "global_step": 628662, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0151758193969727, "global_step": 628663, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9560322761535645, "global_step": 628664, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9990501403808594, "global_step": 628665, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0234127044677734, "global_step": 628666, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9828228950500488, "global_step": 628667, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9706652164459229, "global_step": 628668, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.993740439414978, "global_step": 628669, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0088279247283936, "global_step": 628670, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9324136972427368, "global_step": 628671, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9845197200775146, "global_step": 628672, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.045013904571533, "global_step": 628673, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9169021844863892, "global_step": 628674, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.096613645553589, "global_step": 628675, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.975763201713562, "global_step": 628676, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.052381753921509, "global_step": 628677, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0460660457611084, "global_step": 628678, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0963611602783203, "global_step": 628679, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9809876680374146, "global_step": 628680, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.099351167678833, "global_step": 628681, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.996180772781372, "global_step": 628682, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.059412956237793, "global_step": 628683, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0445942878723145, "global_step": 628684, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8954592943191528, "global_step": 628685, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.007772445678711, "global_step": 628686, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0374813079833984, "global_step": 628687, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.015207052230835, "global_step": 628688, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9752776622772217, "global_step": 628689, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.058633327484131, "global_step": 628690, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9816043376922607, "global_step": 628691, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.057380199432373, "global_step": 628692, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0111377239227295, "global_step": 628693, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9708937406539917, "global_step": 628694, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.015774965286255, "global_step": 628695, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.055058479309082, "global_step": 628696, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.012061595916748, "global_step": 628697, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9937191009521484, "global_step": 628698, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.086090564727783, "global_step": 628699, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.002864360809326, "global_step": 628700, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.054152727127075, "global_step": 628701, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9565731287002563, "global_step": 628702, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9671008586883545, "global_step": 628703, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9496513605117798, "global_step": 628704, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0612127780914307, "global_step": 628705, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.010770320892334, "global_step": 628706, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0627408027648926, "global_step": 628707, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.008883476257324, "global_step": 628708, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.014279365539551, "global_step": 628709, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9999470710754395, "global_step": 628710, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9323639869689941, "global_step": 628711, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0284276008605957, "global_step": 628712, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.039670467376709, "global_step": 628713, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9950790405273438, "global_step": 628714, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.016728162765503, "global_step": 628715, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0300378799438477, "global_step": 628716, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0235822200775146, "global_step": 628717, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.030259132385254, "global_step": 628718, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9547587633132935, "global_step": 628719, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9570361375808716, "global_step": 628720, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.988646388053894, "global_step": 628721, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9603748321533203, "global_step": 628722, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9164479970932007, "global_step": 628723, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0235085487365723, "global_step": 628724, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0107200145721436, "global_step": 628725, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0097901821136475, "global_step": 628726, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9739384651184082, "global_step": 628727, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.006276845932007, "global_step": 628728, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0231995582580566, "global_step": 628729, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9868754148483276, "global_step": 628730, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9340815544128418, "global_step": 628731, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0139107704162598, "global_step": 628732, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.028855562210083, "global_step": 628733, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.053614377975464, "global_step": 628734, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.068429946899414, "global_step": 628735, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0172295570373535, "global_step": 628736, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.022247076034546, "global_step": 628737, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0157220363616943, "global_step": 628738, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.06599760055542, "global_step": 628739, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.04792857170105, "global_step": 628740, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.983798623085022, "global_step": 628741, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9075839519500732, "global_step": 628742, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.028562545776367, "global_step": 628743, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.985087275505066, "global_step": 628744, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0391409397125244, "global_step": 628745, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0049166679382324, "global_step": 628746, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.007570266723633, "global_step": 628747, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.058662176132202, "global_step": 628748, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.048647880554199, "global_step": 628749, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9683464765548706, "global_step": 628750, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0098378658294678, "global_step": 628751, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9264717102050781, "global_step": 628752, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.010446786880493, "global_step": 628753, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.014155387878418, "global_step": 628754, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9539077281951904, "global_step": 628755, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.028545618057251, "global_step": 628756, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9372814893722534, "global_step": 628757, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0201141834259033, "global_step": 628758, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0131471157073975, "global_step": 628759, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9733860492706299, "global_step": 628760, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9130531549453735, "global_step": 628761, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9796781539916992, "global_step": 628762, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9612741470336914, "global_step": 628763, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.976169228553772, "global_step": 628764, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1109354496002197, "global_step": 628765, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9319199323654175, "global_step": 628766, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0564374923706055, "global_step": 628767, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9549731016159058, "global_step": 628768, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9687590599060059, "global_step": 628769, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.97134268283844, "global_step": 628770, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0533206462860107, "global_step": 628771, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0120785236358643, "global_step": 628772, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0626330375671387, "global_step": 628773, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9868429899215698, "global_step": 628774, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.939137578010559, "global_step": 628775, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9737242460250854, "global_step": 628776, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.004013776779175, "global_step": 628777, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.971653699874878, "global_step": 628778, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9378539323806763, "global_step": 628779, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0266129970550537, "global_step": 628780, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0601766109466553, "global_step": 628781, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0042343139648438, "global_step": 628782, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9951640367507935, "global_step": 628783, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0428080558776855, "global_step": 628784, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.050753355026245, "global_step": 628785, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9951368570327759, "global_step": 628786, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0503249168395996, "global_step": 628787, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0406579971313477, "global_step": 628788, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.127362012863159, "global_step": 628789, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.028404474258423, "global_step": 628790, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.062479019165039, "global_step": 628791, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.062141180038452, "global_step": 628792, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0617899894714355, "global_step": 628793, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.016345500946045, "global_step": 628794, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9959900379180908, "global_step": 628795, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.031881332397461, "global_step": 628796, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0075795650482178, "global_step": 628797, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9959536790847778, "global_step": 628798, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.055914878845215, "global_step": 628799, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9683451652526855, "global_step": 628800, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0761139392852783, "global_step": 628801, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9753855466842651, "global_step": 628802, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9918406009674072, "global_step": 628803, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0277748107910156, "global_step": 628804, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9997576475143433, "global_step": 628805, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0046353340148926, "global_step": 628806, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9847147464752197, "global_step": 628807, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.030623197555542, "global_step": 628808, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9504120349884033, "global_step": 628809, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0144309997558594, "global_step": 628810, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.935055136680603, "global_step": 628811, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.011230707168579, "global_step": 628812, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9816137552261353, "global_step": 628813, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9420851469039917, "global_step": 628814, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0603396892547607, "global_step": 628815, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.147695779800415, "global_step": 628816, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0951130390167236, "global_step": 628817, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0989761352539062, "global_step": 628818, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.045314311981201, "global_step": 628819, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.990384578704834, "global_step": 628820, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0000483989715576, "global_step": 628821, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.99793541431427, "global_step": 628822, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0037434101104736, "global_step": 628823, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9768332242965698, "global_step": 628824, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0191469192504883, "global_step": 628825, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.963067889213562, "global_step": 628826, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1332180500030518, "global_step": 628827, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0328619480133057, "global_step": 628828, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0433919429779053, "global_step": 628829, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0180912017822266, "global_step": 628830, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9508079290390015, "global_step": 628831, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0217957496643066, "global_step": 628832, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0115625858306885, "global_step": 628833, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9593815803527832, "global_step": 628834, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0206518173217773, "global_step": 628835, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0029709339141846, "global_step": 628836, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9941258430480957, "global_step": 628837, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9998515844345093, "global_step": 628838, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0157084465026855, "global_step": 628839, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9653582572937012, "global_step": 628840, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0153720378875732, "global_step": 628841, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9838615655899048, "global_step": 628842, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0132510662078857, "global_step": 628843, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.106718063354492, "global_step": 628844, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0065202713012695, "global_step": 628845, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9711214303970337, "global_step": 628846, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0208778381347656, "global_step": 628847, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.985228180885315, "global_step": 628848, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.014235258102417, "global_step": 628849, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.041752576828003, "global_step": 628850, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0740914344787598, "global_step": 628851, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0604734420776367, "global_step": 628852, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9965434074401855, "global_step": 628853, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0461082458496094, "global_step": 628854, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9059971570968628, "global_step": 628855, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9409475326538086, "global_step": 628856, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1019604206085205, "global_step": 628857, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9593737125396729, "global_step": 628858, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8993065357208252, "global_step": 628859, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9912824630737305, "global_step": 628860, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.005270004272461, "global_step": 628861, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9926397800445557, "global_step": 628862, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.967535376548767, "global_step": 628863, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.015354871749878, "global_step": 628864, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.003859281539917, "global_step": 628865, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9190237522125244, "global_step": 628866, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9297981262207031, "global_step": 628867, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.062615156173706, "global_step": 628868, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.980209231376648, "global_step": 628869, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.068089008331299, "global_step": 628870, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.028583526611328, "global_step": 628871, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.029362916946411, "global_step": 628872, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0504353046417236, "global_step": 628873, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9612114429473877, "global_step": 628874, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.944962739944458, "global_step": 628875, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9873785972595215, "global_step": 628876, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.060385227203369, "global_step": 628877, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.013329267501831, "global_step": 628878, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0496773719787598, "global_step": 628879, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.002976655960083, "global_step": 628880, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.067169666290283, "global_step": 628881, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.01228928565979, "global_step": 628882, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0744338035583496, "global_step": 628883, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0009803771972656, "global_step": 628884, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1001298427581787, "global_step": 628885, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.03238844871521, "global_step": 628886, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.071119785308838, "global_step": 628887, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9783177375793457, "global_step": 628888, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9505552053451538, "global_step": 628889, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.004687786102295, "global_step": 628890, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9925767183303833, "global_step": 628891, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9417182207107544, "global_step": 628892, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.032893657684326, "global_step": 628893, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.989420771598816, "global_step": 628894, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.037475824356079, "global_step": 628895, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.990416169166565, "global_step": 628896, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9804728031158447, "global_step": 628897, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.009683132171631, "global_step": 628898, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.094421625137329, "global_step": 628899, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9798098802566528, "global_step": 628900, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9875010251998901, "global_step": 628901, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.008535146713257, "global_step": 628902, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9820085763931274, "global_step": 628903, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0043110847473145, "global_step": 628904, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0200462341308594, "global_step": 628905, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.947756052017212, "global_step": 628906, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.057154655456543, "global_step": 628907, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.044879913330078, "global_step": 628908, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.044909954071045, "global_step": 628909, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0062360763549805, "global_step": 628910, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.073822021484375, "global_step": 628911, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0032012462615967, "global_step": 628912, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0075294971466064, "global_step": 628913, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.946577787399292, "global_step": 628914, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.042598247528076, "global_step": 628915, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0442798137664795, "global_step": 628916, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.036177635192871, "global_step": 628917, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.951632022857666, "global_step": 628918, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0047860145568848, "global_step": 628919, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0002989768981934, "global_step": 628920, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0522148609161377, "global_step": 628921, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.980144739151001, "global_step": 628922, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1231679916381836, "global_step": 628923, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9912524223327637, "global_step": 628924, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.005244016647339, "global_step": 628925, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9625895023345947, "global_step": 628926, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0092055797576904, "global_step": 628927, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9928532838821411, "global_step": 628928, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.00836443901062, "global_step": 628929, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.989790916442871, "global_step": 628930, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.974764108657837, "global_step": 628931, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.032123327255249, "global_step": 628932, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9643601179122925, "global_step": 628933, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0625088214874268, "global_step": 628934, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0594210624694824, "global_step": 628935, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8989485502243042, "global_step": 628936, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0476009845733643, "global_step": 628937, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9442362785339355, "global_step": 628938, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.005401611328125, "global_step": 628939, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.043409824371338, "global_step": 628940, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0812184810638428, "global_step": 628941, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0027408599853516, "global_step": 628942, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0110085010528564, "global_step": 628943, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9965766668319702, "global_step": 628944, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9886126518249512, "global_step": 628945, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0278031826019287, "global_step": 628946, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.944257378578186, "global_step": 628947, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0713207721710205, "global_step": 628948, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.996494174003601, "global_step": 628949, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9508285522460938, "global_step": 628950, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.05527400970459, "global_step": 628951, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9716190099716187, "global_step": 628952, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0010108947753906, "global_step": 628953, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0396387577056885, "global_step": 628954, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0072765350341797, "global_step": 628955, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9549000263214111, "global_step": 628956, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0026168823242188, "global_step": 628957, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.026738405227661, "global_step": 628958, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0194764137268066, "global_step": 628959, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9979522228240967, "global_step": 628960, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0572781562805176, "global_step": 628961, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.007927179336548, "global_step": 628962, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0690560340881348, "global_step": 628963, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0253713130950928, "global_step": 628964, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.017434597015381, "global_step": 628965, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8905853033065796, "global_step": 628966, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9304912090301514, "global_step": 628967, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9519755840301514, "global_step": 628968, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9060287475585938, "global_step": 628969, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.009937047958374, "global_step": 628970, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0392205715179443, "global_step": 628971, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0006203651428223, "global_step": 628972, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.082321882247925, "global_step": 628973, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0068066120147705, "global_step": 628974, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.018542528152466, "global_step": 628975, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9839401245117188, "global_step": 628976, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9743406772613525, "global_step": 628977, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9562315940856934, "global_step": 628978, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.919132113456726, "global_step": 628979, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.081138849258423, "global_step": 628980, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0487756729125977, "global_step": 628981, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.065113067626953, "global_step": 628982, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0209455490112305, "global_step": 628983, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9677666425704956, "global_step": 628984, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0507729053497314, "global_step": 628985, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.023557186126709, "global_step": 628986, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.03257417678833, "global_step": 628987, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0549814701080322, "global_step": 628988, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.045821189880371, "global_step": 628989, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.913325548171997, "global_step": 628990, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.016333818435669, "global_step": 628991, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9244500398635864, "global_step": 628992, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.017625093460083, "global_step": 628993, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0074777603149414, "global_step": 628994, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0155253410339355, "global_step": 628995, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9809792041778564, "global_step": 628996, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9770960807800293, "global_step": 628997, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.013139486312866, "global_step": 628998, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.020665168762207, "global_step": 628999, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1180708408355713, "global_step": 629000, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.001931667327881, "global_step": 629001, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0380804538726807, "global_step": 629002, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9758977890014648, "global_step": 629003, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.006680488586426, "global_step": 629004, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9952707290649414, "global_step": 629005, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.011486053466797, "global_step": 629006, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0219337940216064, "global_step": 629007, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0032715797424316, "global_step": 629008, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9704018831253052, "global_step": 629009, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.128469228744507, "global_step": 629010, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0493829250335693, "global_step": 629011, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9513368606567383, "global_step": 629012, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0036182403564453, "global_step": 629013, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9079900979995728, "global_step": 629014, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.065062999725342, "global_step": 629015, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9247359037399292, "global_step": 629016, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0242226123809814, "global_step": 629017, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0283186435699463, "global_step": 629018, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9482172727584839, "global_step": 629019, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.047788619995117, "global_step": 629020, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9904139041900635, "global_step": 629021, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0635290145874023, "global_step": 629022, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9633712768554688, "global_step": 629023, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9993596076965332, "global_step": 629024, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.010906457901001, "global_step": 629025, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9633136987686157, "global_step": 629026, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9970959424972534, "global_step": 629027, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0018420219421387, "global_step": 629028, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0252268314361572, "global_step": 629029, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.054629325866699, "global_step": 629030, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9930298328399658, "global_step": 629031, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0517663955688477, "global_step": 629032, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.014725923538208, "global_step": 629033, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0678369998931885, "global_step": 629034, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.080547332763672, "global_step": 629035, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0030643939971924, "global_step": 629036, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.97393798828125, "global_step": 629037, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.925916075706482, "global_step": 629038, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.975237250328064, "global_step": 629039, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9935446977615356, "global_step": 629040, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9828301668167114, "global_step": 629041, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0227675437927246, "global_step": 629042, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.057708501815796, "global_step": 629043, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0984745025634766, "global_step": 629044, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.018350601196289, "global_step": 629045, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.053539991378784, "global_step": 629046, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0143308639526367, "global_step": 629047, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0131888389587402, "global_step": 629048, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.1112332344055176, "global_step": 629049, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0145113468170166, "global_step": 629050, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0553605556488037, "global_step": 629051, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9674547910690308, "global_step": 629052, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9605090618133545, "global_step": 629053, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0373146533966064, "global_step": 629054, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9337787628173828, "global_step": 629055, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9809165000915527, "global_step": 629056, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0376522541046143, "global_step": 629057, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9678142070770264, "global_step": 629058, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9463335275650024, "global_step": 629059, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.956902027130127, "global_step": 629060, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9711148738861084, "global_step": 629061, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.926910638809204, "global_step": 629062, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9710782766342163, "global_step": 629063, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9531782865524292, "global_step": 629064, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9628645181655884, "global_step": 629065, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9461491107940674, "global_step": 629066, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0332627296447754, "global_step": 629067, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0065224170684814, "global_step": 629068, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.925691843032837, "global_step": 629069, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.893460988998413, "global_step": 629070, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0098929405212402, "global_step": 629071, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.975612759590149, "global_step": 629072, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0293407440185547, "global_step": 629073, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.019217014312744, "global_step": 629074, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0070040225982666, "global_step": 629075, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.060234785079956, "global_step": 629076, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0065972805023193, "global_step": 629077, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9745807647705078, "global_step": 629078, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0161194801330566, "global_step": 629079, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.04498028755188, "global_step": 629080, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0392913818359375, "global_step": 629081, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0675411224365234, "global_step": 629082, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.044074058532715, "global_step": 629083, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9464870691299438, "global_step": 629084, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9908300638198853, "global_step": 629085, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0562326908111572, "global_step": 629086, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.03957462310791, "global_step": 629087, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0196776390075684, "global_step": 629088, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0524234771728516, "global_step": 629089, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0074446201324463, "global_step": 629090, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.035325288772583, "global_step": 629091, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.049213409423828, "global_step": 629092, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9458670616149902, "global_step": 629093, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.004559278488159, "global_step": 629094, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9583415985107422, "global_step": 629095, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9767781496047974, "global_step": 629096, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.010427474975586, "global_step": 629097, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0050816535949707, "global_step": 629098, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0169548988342285, "global_step": 629099, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9429768323898315, "global_step": 629100, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9069838523864746, "global_step": 629101, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0591561794281006, "global_step": 629102, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.015089273452759, "global_step": 629103, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0712413787841797, "global_step": 629104, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9933162927627563, "global_step": 629105, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9549567699432373, "global_step": 629106, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9979777336120605, "global_step": 629107, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9262069463729858, "global_step": 629108, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0239813327789307, "global_step": 629109, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0121190547943115, "global_step": 629110, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0021793842315674, "global_step": 629111, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9205509424209595, "global_step": 629112, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9024602174758911, "global_step": 629113, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.014730215072632, "global_step": 629114, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9222524166107178, "global_step": 629115, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9505428075790405, "global_step": 629116, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9866740703582764, "global_step": 629117, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9890748262405396, "global_step": 629118, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0406765937805176, "global_step": 629119, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0443811416625977, "global_step": 629120, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9752163887023926, "global_step": 629121, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9389541149139404, "global_step": 629122, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.995381474494934, "global_step": 629123, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9805067777633667, "global_step": 629124, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9746545553207397, "global_step": 629125, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9180855751037598, "global_step": 629126, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9329684972763062, "global_step": 629127, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0086848735809326, "global_step": 629128, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9343328475952148, "global_step": 629129, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9955263137817383, "global_step": 629130, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0056231021881104, "global_step": 629131, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9743707180023193, "global_step": 629132, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.074462652206421, "global_step": 629133, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0975072383880615, "global_step": 629134, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.062880754470825, "global_step": 629135, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9293360710144043, "global_step": 629136, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.043459177017212, "global_step": 629137, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.065617084503174, "global_step": 629138, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0454463958740234, "global_step": 629139, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0190024375915527, "global_step": 629140, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0021064281463623, "global_step": 629141, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0364062786102295, "global_step": 629142, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0056540966033936, "global_step": 629143, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9499752521514893, "global_step": 629144, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0343270301818848, "global_step": 629145, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0265657901763916, "global_step": 629146, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9275166988372803, "global_step": 629147, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9824579954147339, "global_step": 629148, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0095365047454834, "global_step": 629149, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.004385471343994, "global_step": 629150, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9859881401062012, "global_step": 629151, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.061488389968872, "global_step": 629152, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9497466087341309, "global_step": 629153, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9525489807128906, "global_step": 629154, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0444440841674805, "global_step": 629155, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.059936285018921, "global_step": 629156, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.988731026649475, "global_step": 629157, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9478691816329956, "global_step": 629158, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9968297481536865, "global_step": 629159, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9021095037460327, "global_step": 629160, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9931862354278564, "global_step": 629161, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.031019449234009, "global_step": 629162, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9721145629882812, "global_step": 629163, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0106635093688965, "global_step": 629164, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9571185111999512, "global_step": 629165, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9084059000015259, "global_step": 629166, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.004232168197632, "global_step": 629167, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.961368441581726, "global_step": 629168, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.960215449333191, "global_step": 629169, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.12960147857666, "global_step": 629170, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0630483627319336, "global_step": 629171, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9028667211532593, "global_step": 629172, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.907036542892456, "global_step": 629173, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0145535469055176, "global_step": 629174, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9803824424743652, "global_step": 629175, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.049933910369873, "global_step": 629176, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0621070861816406, "global_step": 629177, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9827886819839478, "global_step": 629178, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.018594980239868, "global_step": 629179, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9520081281661987, "global_step": 629180, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9314011335372925, "global_step": 629181, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.025623321533203, "global_step": 629182, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9764909744262695, "global_step": 629183, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.125701904296875, "global_step": 629184, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.089641809463501, "global_step": 629185, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0354390144348145, "global_step": 629186, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.071002960205078, "global_step": 629187, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9964756965637207, "global_step": 629188, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0345051288604736, "global_step": 629189, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9422823190689087, "global_step": 629190, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0215156078338623, "global_step": 629191, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.040647506713867, "global_step": 629192, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9850839376449585, "global_step": 629193, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9608005285263062, "global_step": 629194, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9698476791381836, "global_step": 629195, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0563790798187256, "global_step": 629196, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.1132071018218994, "global_step": 629197, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9346730709075928, "global_step": 629198, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9787886142730713, "global_step": 629199, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.029543876647949, "global_step": 629200, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.030385971069336, "global_step": 629201, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9816008806228638, "global_step": 629202, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9689358472824097, "global_step": 629203, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.08581805229187, "global_step": 629204, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9886552095413208, "global_step": 629205, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9690265655517578, "global_step": 629206, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9182828664779663, "global_step": 629207, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0488815307617188, "global_step": 629208, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.055736780166626, "global_step": 629209, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0266966819763184, "global_step": 629210, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9911773204803467, "global_step": 629211, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9539302587509155, "global_step": 629212, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.936866283416748, "global_step": 629213, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0033774375915527, "global_step": 629214, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.013833522796631, "global_step": 629215, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0300133228302, "global_step": 629216, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.026960611343384, "global_step": 629217, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9809114933013916, "global_step": 629218, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9479349851608276, "global_step": 629219, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9094239473342896, "global_step": 629220, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0218393802642822, "global_step": 629221, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0352110862731934, "global_step": 629222, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9645365476608276, "global_step": 629223, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9111313819885254, "global_step": 629224, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.945561170578003, "global_step": 629225, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.910186529159546, "global_step": 629226, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0429818630218506, "global_step": 629227, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9800680875778198, "global_step": 629228, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9980549812316895, "global_step": 629229, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8674252033233643, "global_step": 629230, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9240105152130127, "global_step": 629231, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0629143714904785, "global_step": 629232, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.111229419708252, "global_step": 629233, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9148190021514893, "global_step": 629234, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.052436113357544, "global_step": 629235, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0143797397613525, "global_step": 629236, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9786025285720825, "global_step": 629237, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.957714557647705, "global_step": 629238, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.875089406967163, "global_step": 629239, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.060952663421631, "global_step": 629240, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0073113441467285, "global_step": 629241, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.001455068588257, "global_step": 629242, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9724352359771729, "global_step": 629243, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0128719806671143, "global_step": 629244, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.05720853805542, "global_step": 629245, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.036461591720581, "global_step": 629246, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.052947521209717, "global_step": 629247, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0459697246551514, "global_step": 629248, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.948904037475586, "global_step": 629249, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.014183521270752, "global_step": 629250, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8582472801208496, "global_step": 629251, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0238327980041504, "global_step": 629252, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0577640533447266, "global_step": 629253, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9843189716339111, "global_step": 629254, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0075109004974365, "global_step": 629255, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9340803623199463, "global_step": 629256, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9293453693389893, "global_step": 629257, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9566943645477295, "global_step": 629258, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0023224353790283, "global_step": 629259, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9726297855377197, "global_step": 629260, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0494868755340576, "global_step": 629261, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0773603916168213, "global_step": 629262, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9733421802520752, "global_step": 629263, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9972823858261108, "global_step": 629264, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0672240257263184, "global_step": 629265, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9159870147705078, "global_step": 629266, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0217998027801514, "global_step": 629267, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0079281330108643, "global_step": 629268, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.018688440322876, "global_step": 629269, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.064148426055908, "global_step": 629270, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9231165647506714, "global_step": 629271, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9533708095550537, "global_step": 629272, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9332689046859741, "global_step": 629273, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0203804969787598, "global_step": 629274, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9828553199768066, "global_step": 629275, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0495989322662354, "global_step": 629276, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0187838077545166, "global_step": 629277, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0073187351226807, "global_step": 629278, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0379855632781982, "global_step": 629279, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0774834156036377, "global_step": 629280, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0103800296783447, "global_step": 629281, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9840692281723022, "global_step": 629282, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.939950942993164, "global_step": 629283, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0105440616607666, "global_step": 629284, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9837006330490112, "global_step": 629285, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9642655849456787, "global_step": 629286, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0840861797332764, "global_step": 629287, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9615939855575562, "global_step": 629288, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9520938396453857, "global_step": 629289, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9700103998184204, "global_step": 629290, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9892019033432007, "global_step": 629291, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0051400661468506, "global_step": 629292, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.998161792755127, "global_step": 629293, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.064357280731201, "global_step": 629294, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9415888786315918, "global_step": 629295, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.907217025756836, "global_step": 629296, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9930115938186646, "global_step": 629297, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9800524711608887, "global_step": 629298, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9883205890655518, "global_step": 629299, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9640271663665771, "global_step": 629300, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9364476203918457, "global_step": 629301, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9475765228271484, "global_step": 629302, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9927808046340942, "global_step": 629303, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9560619592666626, "global_step": 629304, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9500789642333984, "global_step": 629305, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9775573015213013, "global_step": 629306, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0034735202789307, "global_step": 629307, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.023010730743408, "global_step": 629308, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0011332035064697, "global_step": 629309, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9961475133895874, "global_step": 629310, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0081818103790283, "global_step": 629311, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.000633478164673, "global_step": 629312, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0629959106445312, "global_step": 629313, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8956199884414673, "global_step": 629314, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0171568393707275, "global_step": 629315, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9796303510665894, "global_step": 629316, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9760606288909912, "global_step": 629317, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0530545711517334, "global_step": 629318, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9841911792755127, "global_step": 629319, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.004636287689209, "global_step": 629320, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9819762706756592, "global_step": 629321, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0120623111724854, "global_step": 629322, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0447800159454346, "global_step": 629323, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9359649419784546, "global_step": 629324, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0131120681762695, "global_step": 629325, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9986621141433716, "global_step": 629326, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0317678451538086, "global_step": 629327, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.946765422821045, "global_step": 629328, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9826085567474365, "global_step": 629329, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9398585557937622, "global_step": 629330, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.016941547393799, "global_step": 629331, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.946528434753418, "global_step": 629332, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9712799787521362, "global_step": 629333, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0008544921875, "global_step": 629334, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.047961473464966, "global_step": 629335, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0879905223846436, "global_step": 629336, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.994418740272522, "global_step": 629337, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0683491230010986, "global_step": 629338, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0150017738342285, "global_step": 629339, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9728466272354126, "global_step": 629340, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9837446212768555, "global_step": 629341, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.030856132507324, "global_step": 629342, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9316374063491821, "global_step": 629343, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9218281507492065, "global_step": 629344, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0690975189208984, "global_step": 629345, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0513997077941895, "global_step": 629346, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9066252708435059, "global_step": 629347, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.084219455718994, "global_step": 629348, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.061460018157959, "global_step": 629349, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9008442163467407, "global_step": 629350, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.025456428527832, "global_step": 629351, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0596137046813965, "global_step": 629352, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.983052134513855, "global_step": 629353, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.955325722694397, "global_step": 629354, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0132429599761963, "global_step": 629355, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.004077911376953, "global_step": 629356, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9420651197433472, "global_step": 629357, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9975098371505737, "global_step": 629358, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9756652116775513, "global_step": 629359, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.020921230316162, "global_step": 629360, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.056222438812256, "global_step": 629361, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0310134887695312, "global_step": 629362, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9852592945098877, "global_step": 629363, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9367611408233643, "global_step": 629364, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.049055814743042, "global_step": 629365, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8936127424240112, "global_step": 629366, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0832109451293945, "global_step": 629367, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.938429355621338, "global_step": 629368, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0149362087249756, "global_step": 629369, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.057511329650879, "global_step": 629370, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.043320655822754, "global_step": 629371, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9219310283660889, "global_step": 629372, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.948302149772644, "global_step": 629373, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.050588846206665, "global_step": 629374, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0785560607910156, "global_step": 629375, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.016017198562622, "global_step": 629376, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.926827073097229, "global_step": 629377, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9689874649047852, "global_step": 629378, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.001375436782837, "global_step": 629379, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9749553203582764, "global_step": 629380, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0182130336761475, "global_step": 629381, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.057720422744751, "global_step": 629382, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9348434209823608, "global_step": 629383, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9399969577789307, "global_step": 629384, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9883108139038086, "global_step": 629385, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0312557220458984, "global_step": 629386, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.975436806678772, "global_step": 629387, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9571622610092163, "global_step": 629388, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.007117509841919, "global_step": 629389, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8504459857940674, "global_step": 629390, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9561578035354614, "global_step": 629391, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.112389326095581, "global_step": 629392, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.039865732192993, "global_step": 629393, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9075278043746948, "global_step": 629394, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9234850406646729, "global_step": 629395, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9220142364501953, "global_step": 629396, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.021744728088379, "global_step": 629397, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.049509286880493, "global_step": 629398, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9270542860031128, "global_step": 629399, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.02465558052063, "global_step": 629400, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.992865800857544, "global_step": 629401, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9790400266647339, "global_step": 629402, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9539138078689575, "global_step": 629403, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.081439733505249, "global_step": 629404, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9255348443984985, "global_step": 629405, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0173916816711426, "global_step": 629406, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0648880004882812, "global_step": 629407, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8837401866912842, "global_step": 629408, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0585789680480957, "global_step": 629409, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.042548179626465, "global_step": 629410, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.051995277404785, "global_step": 629411, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0878872871398926, "global_step": 629412, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0157055854797363, "global_step": 629413, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0640666484832764, "global_step": 629414, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0132036209106445, "global_step": 629415, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.061502695083618, "global_step": 629416, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9978832006454468, "global_step": 629417, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0246942043304443, "global_step": 629418, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.009939670562744, "global_step": 629419, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0429980754852295, "global_step": 629420, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.026552200317383, "global_step": 629421, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0477144718170166, "global_step": 629422, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9695947170257568, "global_step": 629423, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.074214220046997, "global_step": 629424, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9874892234802246, "global_step": 629425, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0452425479888916, "global_step": 629426, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0542349815368652, "global_step": 629427, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9990861415863037, "global_step": 629428, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.034214735031128, "global_step": 629429, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.029597043991089, "global_step": 629430, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9699504375457764, "global_step": 629431, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9739983081817627, "global_step": 629432, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.955083966255188, "global_step": 629433, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0045533180236816, "global_step": 629434, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.1197009086608887, "global_step": 629435, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0619313716888428, "global_step": 629436, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9238817691802979, "global_step": 629437, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9147260189056396, "global_step": 629438, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0049076080322266, "global_step": 629439, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9155874252319336, "global_step": 629440, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.989215612411499, "global_step": 629441, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9789142608642578, "global_step": 629442, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0223357677459717, "global_step": 629443, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8895304203033447, "global_step": 629444, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9787296056747437, "global_step": 629445, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0440564155578613, "global_step": 629446, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0515694618225098, "global_step": 629447, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0925402641296387, "global_step": 629448, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.020925283432007, "global_step": 629449, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9504098892211914, "global_step": 629450, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0152933597564697, "global_step": 629451, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0343451499938965, "global_step": 629452, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.064384698867798, "global_step": 629453, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.998099684715271, "global_step": 629454, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.97459077835083, "global_step": 629455, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.954047441482544, "global_step": 629456, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.035933256149292, "global_step": 629457, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9289121627807617, "global_step": 629458, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.025688409805298, "global_step": 629459, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0028257369995117, "global_step": 629460, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9526654481887817, "global_step": 629461, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0331802368164062, "global_step": 629462, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9673322439193726, "global_step": 629463, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9912132024765015, "global_step": 629464, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9812800884246826, "global_step": 629465, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0248923301696777, "global_step": 629466, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9961562156677246, "global_step": 629467, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0535595417022705, "global_step": 629468, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.923458456993103, "global_step": 629469, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.064270496368408, "global_step": 629470, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9241172075271606, "global_step": 629471, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9094899892807007, "global_step": 629472, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.06954026222229, "global_step": 629473, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9678025245666504, "global_step": 629474, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.071610450744629, "global_step": 629475, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9334938526153564, "global_step": 629476, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8916099071502686, "global_step": 629477, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9629780054092407, "global_step": 629478, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0315959453582764, "global_step": 629479, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.984745740890503, "global_step": 629480, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9271516799926758, "global_step": 629481, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8798807859420776, "global_step": 629482, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9658787250518799, "global_step": 629483, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9151983261108398, "global_step": 629484, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.017681360244751, "global_step": 629485, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9937515258789062, "global_step": 629486, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.058889389038086, "global_step": 629487, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9688589572906494, "global_step": 629488, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9675514698028564, "global_step": 629489, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9826931953430176, "global_step": 629490, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0433919429779053, "global_step": 629491, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.059748888015747, "global_step": 629492, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0024454593658447, "global_step": 629493, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.00719952583313, "global_step": 629494, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9430058002471924, "global_step": 629495, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9589678049087524, "global_step": 629496, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9958661794662476, "global_step": 629497, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9928399324417114, "global_step": 629498, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0050313472747803, "global_step": 629499, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9822027683258057, "global_step": 629500, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.998711109161377, "global_step": 629501, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9908798933029175, "global_step": 629502, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.019345760345459, "global_step": 629503, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0861289501190186, "global_step": 629504, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9971247911453247, "global_step": 629505, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.021167755126953, "global_step": 629506, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0644001960754395, "global_step": 629507, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9971511363983154, "global_step": 629508, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.996171474456787, "global_step": 629509, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9943604469299316, "global_step": 629510, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9872372150421143, "global_step": 629511, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.87213134765625, "global_step": 629512, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9675592184066772, "global_step": 629513, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9724143743515015, "global_step": 629514, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.950924277305603, "global_step": 629515, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9841501712799072, "global_step": 629516, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0344791412353516, "global_step": 629517, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.987418293952942, "global_step": 629518, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0926356315612793, "global_step": 629519, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9630699157714844, "global_step": 629520, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.988358736038208, "global_step": 629521, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9887332916259766, "global_step": 629522, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.037656307220459, "global_step": 629523, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9706615209579468, "global_step": 629524, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9244484901428223, "global_step": 629525, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9722708463668823, "global_step": 629526, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.000347137451172, "global_step": 629527, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9678351879119873, "global_step": 629528, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.032711982727051, "global_step": 629529, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.948106050491333, "global_step": 629530, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.959861159324646, "global_step": 629531, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0135130882263184, "global_step": 629532, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.044553756713867, "global_step": 629533, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0295639038085938, "global_step": 629534, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9804050922393799, "global_step": 629535, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.004992723464966, "global_step": 629536, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.009218692779541, "global_step": 629537, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.026073694229126, "global_step": 629538, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0265932083129883, "global_step": 629539, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9766292572021484, "global_step": 629540, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0451200008392334, "global_step": 629541, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.1737358570098877, "global_step": 629542, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.005049228668213, "global_step": 629543, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.995215654373169, "global_step": 629544, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0131826400756836, "global_step": 629545, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9334840774536133, "global_step": 629546, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.032888650894165, "global_step": 629547, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0344324111938477, "global_step": 629548, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0221951007843018, "global_step": 629549, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9903019666671753, "global_step": 629550, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0340731143951416, "global_step": 629551, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9837639331817627, "global_step": 629552, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.89407479763031, "global_step": 629553, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9934005737304688, "global_step": 629554, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9847261905670166, "global_step": 629555, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8894338607788086, "global_step": 629556, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.002908229827881, "global_step": 629557, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.992564082145691, "global_step": 629558, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0059103965759277, "global_step": 629559, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.027024984359741, "global_step": 629560, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.02477765083313, "global_step": 629561, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9999390840530396, "global_step": 629562, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9125442504882812, "global_step": 629563, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9839882850646973, "global_step": 629564, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9299957752227783, "global_step": 629565, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.976434350013733, "global_step": 629566, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9958053827285767, "global_step": 629567, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0768420696258545, "global_step": 629568, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9529995918273926, "global_step": 629569, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0309770107269287, "global_step": 629570, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9383000135421753, "global_step": 629571, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9756920337677002, "global_step": 629572, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.1225619316101074, "global_step": 629573, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0069069862365723, "global_step": 629574, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0635337829589844, "global_step": 629575, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9863319396972656, "global_step": 629576, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9934749603271484, "global_step": 629577, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.1116786003112793, "global_step": 629578, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0630288124084473, "global_step": 629579, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.022150754928589, "global_step": 629580, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9902129173278809, "global_step": 629581, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.972177267074585, "global_step": 629582, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.011962652206421, "global_step": 629583, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.019683599472046, "global_step": 629584, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0103366374969482, "global_step": 629585, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9796286821365356, "global_step": 629586, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9987751245498657, "global_step": 629587, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0761497020721436, "global_step": 629588, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.04671049118042, "global_step": 629589, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9635121822357178, "global_step": 629590, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9869529008865356, "global_step": 629591, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9929804801940918, "global_step": 629592, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0663352012634277, "global_step": 629593, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.968419075012207, "global_step": 629594, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.016432762145996, "global_step": 629595, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0688815116882324, "global_step": 629596, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9970048666000366, "global_step": 629597, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.019437074661255, "global_step": 629598, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.026486873626709, "global_step": 629599, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0740010738372803, "global_step": 629600, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0554609298706055, "global_step": 629601, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.987395167350769, "global_step": 629602, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.083277463912964, "global_step": 629603, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.014134645462036, "global_step": 629604, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0404253005981445, "global_step": 629605, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0264296531677246, "global_step": 629606, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0371811389923096, "global_step": 629607, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.017895221710205, "global_step": 629608, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.091068983078003, "global_step": 629609, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0233538150787354, "global_step": 629610, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.062882900238037, "global_step": 629611, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9759806394577026, "global_step": 629612, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0040221214294434, "global_step": 629613, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0031490325927734, "global_step": 629614, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0426993370056152, "global_step": 629615, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.114489793777466, "global_step": 629616, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0636465549468994, "global_step": 629617, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9973506927490234, "global_step": 629618, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0739638805389404, "global_step": 629619, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.961763858795166, "global_step": 629620, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0193424224853516, "global_step": 629621, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9930394887924194, "global_step": 629622, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0220868587493896, "global_step": 629623, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.00348162651062, "global_step": 629624, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.080700635910034, "global_step": 629625, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.067692756652832, "global_step": 629626, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9547560214996338, "global_step": 629627, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.004359006881714, "global_step": 629628, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0083611011505127, "global_step": 629629, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.038917303085327, "global_step": 629630, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.994219422340393, "global_step": 629631, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0320770740509033, "global_step": 629632, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0119690895080566, "global_step": 629633, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9687702655792236, "global_step": 629634, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.04049015045166, "global_step": 629635, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.027137041091919, "global_step": 629636, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0519156455993652, "global_step": 629637, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0999016761779785, "global_step": 629638, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0751733779907227, "global_step": 629639, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9974313974380493, "global_step": 629640, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0232155323028564, "global_step": 629641, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9012815952301025, "global_step": 629642, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0001251697540283, "global_step": 629643, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9296925067901611, "global_step": 629644, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9414196014404297, "global_step": 629645, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8934991359710693, "global_step": 629646, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.082326650619507, "global_step": 629647, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0058352947235107, "global_step": 629648, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9389797449111938, "global_step": 629649, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0641627311706543, "global_step": 629650, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.06685733795166, "global_step": 629651, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.028719186782837, "global_step": 629652, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9592331647872925, "global_step": 629653, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9587503671646118, "global_step": 629654, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9130748510360718, "global_step": 629655, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9859541654586792, "global_step": 629656, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9499980211257935, "global_step": 629657, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0006558895111084, "global_step": 629658, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0779531002044678, "global_step": 629659, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.11232852935791, "global_step": 629660, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9369348287582397, "global_step": 629661, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.898180603981018, "global_step": 629662, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9725244045257568, "global_step": 629663, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.038982629776001, "global_step": 629664, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9678374528884888, "global_step": 629665, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9561054706573486, "global_step": 629666, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.019522190093994, "global_step": 629667, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.986670732498169, "global_step": 629668, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9592199325561523, "global_step": 629669, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0288524627685547, "global_step": 629670, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.039058208465576, "global_step": 629671, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9874401092529297, "global_step": 629672, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9553755521774292, "global_step": 629673, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.978379726409912, "global_step": 629674, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0037147998809814, "global_step": 629675, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9646176099777222, "global_step": 629676, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9560691118240356, "global_step": 629677, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9799540042877197, "global_step": 629678, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9398987293243408, "global_step": 629679, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0095086097717285, "global_step": 629680, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.952609896659851, "global_step": 629681, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9688223600387573, "global_step": 629682, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0855159759521484, "global_step": 629683, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9703705310821533, "global_step": 629684, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.104811906814575, "global_step": 629685, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.986615777015686, "global_step": 629686, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0659232139587402, "global_step": 629687, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0138092041015625, "global_step": 629688, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.011812686920166, "global_step": 629689, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.998713731765747, "global_step": 629690, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9596097469329834, "global_step": 629691, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0723159313201904, "global_step": 629692, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9884474277496338, "global_step": 629693, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9580789804458618, "global_step": 629694, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9850143194198608, "global_step": 629695, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.044537305831909, "global_step": 629696, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9877738952636719, "global_step": 629697, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.977000117301941, "global_step": 629698, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9974122047424316, "global_step": 629699, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.931767225265503, "global_step": 629700, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.972571849822998, "global_step": 629701, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.017706871032715, "global_step": 629702, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0512797832489014, "global_step": 629703, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0710349082946777, "global_step": 629704, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.008920669555664, "global_step": 629705, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9408642053604126, "global_step": 629706, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.985228419303894, "global_step": 629707, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0433387756347656, "global_step": 629708, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.1014974117279053, "global_step": 629709, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0911154747009277, "global_step": 629710, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9885709285736084, "global_step": 629711, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9818611145019531, "global_step": 629712, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0285348892211914, "global_step": 629713, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.024864435195923, "global_step": 629714, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9712488651275635, "global_step": 629715, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0454676151275635, "global_step": 629716, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.883123755455017, "global_step": 629717, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.023923635482788, "global_step": 629718, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.036839485168457, "global_step": 629719, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.065763235092163, "global_step": 629720, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0599312782287598, "global_step": 629721, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9900918006896973, "global_step": 629722, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9513825178146362, "global_step": 629723, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9880048036575317, "global_step": 629724, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.030421018600464, "global_step": 629725, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9711332321166992, "global_step": 629726, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9682697057724, "global_step": 629727, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9623955488204956, "global_step": 629728, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.038982629776001, "global_step": 629729, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0459139347076416, "global_step": 629730, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9699310064315796, "global_step": 629731, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0300676822662354, "global_step": 629732, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.025475025177002, "global_step": 629733, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0017147064208984, "global_step": 629734, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9688003063201904, "global_step": 629735, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0458953380584717, "global_step": 629736, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.970502495765686, "global_step": 629737, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9785430431365967, "global_step": 629738, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.010284423828125, "global_step": 629739, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9859068393707275, "global_step": 629740, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.010806083679199, "global_step": 629741, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0489988327026367, "global_step": 629742, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9729888439178467, "global_step": 629743, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.993817687034607, "global_step": 629744, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9592190980911255, "global_step": 629745, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9565585851669312, "global_step": 629746, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0748302936553955, "global_step": 629747, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.953680396080017, "global_step": 629748, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.940103530883789, "global_step": 629749, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9807920455932617, "global_step": 629750, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8539639711380005, "global_step": 629751, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0165517330169678, "global_step": 629752, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9895395040512085, "global_step": 629753, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.071260929107666, "global_step": 629754, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.036060333251953, "global_step": 629755, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0607521533966064, "global_step": 629756, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9966051578521729, "global_step": 629757, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9920110702514648, "global_step": 629758, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.000450372695923, "global_step": 629759, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.017749071121216, "global_step": 629760, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9966856241226196, "global_step": 629761, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0042574405670166, "global_step": 629762, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0365893840789795, "global_step": 629763, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0130417346954346, "global_step": 629764, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9959571361541748, "global_step": 629765, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.034625768661499, "global_step": 629766, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9983397722244263, "global_step": 629767, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.967016339302063, "global_step": 629768, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.023470401763916, "global_step": 629769, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.060774564743042, "global_step": 629770, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0254499912261963, "global_step": 629771, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9811955690383911, "global_step": 629772, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.049781322479248, "global_step": 629773, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0440831184387207, "global_step": 629774, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.03364896774292, "global_step": 629775, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9502198696136475, "global_step": 629776, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0224721431732178, "global_step": 629777, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.025556802749634, "global_step": 629778, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9524803161621094, "global_step": 629779, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9330039024353027, "global_step": 629780, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9816666841506958, "global_step": 629781, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0100152492523193, "global_step": 629782, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9937621355056763, "global_step": 629783, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0304768085479736, "global_step": 629784, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.010190010070801, "global_step": 629785, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.013206720352173, "global_step": 629786, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9653006792068481, "global_step": 629787, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.070629596710205, "global_step": 629788, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0074713230133057, "global_step": 629789, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9211044311523438, "global_step": 629790, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9473141431808472, "global_step": 629791, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.064462661743164, "global_step": 629792, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.093562364578247, "global_step": 629793, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9731409549713135, "global_step": 629794, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0309183597564697, "global_step": 629795, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0679190158843994, "global_step": 629796, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.015847682952881, "global_step": 629797, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.086843729019165, "global_step": 629798, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.948677659034729, "global_step": 629799, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0363099575042725, "global_step": 629800, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0007171630859375, "global_step": 629801, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0316567420959473, "global_step": 629802, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9647427797317505, "global_step": 629803, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.022592067718506, "global_step": 629804, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0409584045410156, "global_step": 629805, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9108916521072388, "global_step": 629806, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9822288751602173, "global_step": 629807, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9638738632202148, "global_step": 629808, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.953115463256836, "global_step": 629809, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0539519786834717, "global_step": 629810, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.005575180053711, "global_step": 629811, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.022440195083618, "global_step": 629812, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.017436981201172, "global_step": 629813, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0755133628845215, "global_step": 629814, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9935109615325928, "global_step": 629815, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0470311641693115, "global_step": 629816, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0234017372131348, "global_step": 629817, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.025468587875366, "global_step": 629818, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0771772861480713, "global_step": 629819, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9783753156661987, "global_step": 629820, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9545462131500244, "global_step": 629821, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.034209966659546, "global_step": 629822, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0369489192962646, "global_step": 629823, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0120856761932373, "global_step": 629824, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9941682815551758, "global_step": 629825, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.947399616241455, "global_step": 629826, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0500149726867676, "global_step": 629827, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0394673347473145, "global_step": 629828, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9261822700500488, "global_step": 629829, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9605132341384888, "global_step": 629830, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9893598556518555, "global_step": 629831, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.010745048522949, "global_step": 629832, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.938841462135315, "global_step": 629833, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9537558555603027, "global_step": 629834, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.031942367553711, "global_step": 629835, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.007903814315796, "global_step": 629836, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.981289029121399, "global_step": 629837, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9300155639648438, "global_step": 629838, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9845818281173706, "global_step": 629839, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.000889778137207, "global_step": 629840, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0775043964385986, "global_step": 629841, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0959460735321045, "global_step": 629842, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0037343502044678, "global_step": 629843, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9637665748596191, "global_step": 629844, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.018738269805908, "global_step": 629845, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.038874864578247, "global_step": 629846, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9667048454284668, "global_step": 629847, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0152111053466797, "global_step": 629848, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.059175491333008, "global_step": 629849, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0095503330230713, "global_step": 629850, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9576877355575562, "global_step": 629851, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.995288610458374, "global_step": 629852, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0982489585876465, "global_step": 629853, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0681676864624023, "global_step": 629854, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.01090145111084, "global_step": 629855, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9812049865722656, "global_step": 629856, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.007850408554077, "global_step": 629857, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9719054698944092, "global_step": 629858, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9983580112457275, "global_step": 629859, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0369584560394287, "global_step": 629860, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0260894298553467, "global_step": 629861, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.1043782234191895, "global_step": 629862, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.036414861679077, "global_step": 629863, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0397770404815674, "global_step": 629864, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0957415103912354, "global_step": 629865, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.960856556892395, "global_step": 629866, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0212924480438232, "global_step": 629867, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0010385513305664, "global_step": 629868, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.00406813621521, "global_step": 629869, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9670065641403198, "global_step": 629870, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9955819845199585, "global_step": 629871, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9684467315673828, "global_step": 629872, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.072115659713745, "global_step": 629873, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9479742050170898, "global_step": 629874, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.921111822128296, "global_step": 629875, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0240354537963867, "global_step": 629876, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.025080680847168, "global_step": 629877, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0208778381347656, "global_step": 629878, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.036100149154663, "global_step": 629879, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0274617671966553, "global_step": 629880, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.068208694458008, "global_step": 629881, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0059750080108643, "global_step": 629882, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.019592523574829, "global_step": 629883, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9321227073669434, "global_step": 629884, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9932504892349243, "global_step": 629885, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.050644874572754, "global_step": 629886, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.070482015609741, "global_step": 629887, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8577592372894287, "global_step": 629888, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.079285144805908, "global_step": 629889, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0782833099365234, "global_step": 629890, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9435744285583496, "global_step": 629891, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.002910614013672, "global_step": 629892, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9810274839401245, "global_step": 629893, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0250093936920166, "global_step": 629894, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.989819049835205, "global_step": 629895, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0448098182678223, "global_step": 629896, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0147945880889893, "global_step": 629897, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.010554552078247, "global_step": 629898, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.94600510597229, "global_step": 629899, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.087519407272339, "global_step": 629900, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.016000747680664, "global_step": 629901, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0268540382385254, "global_step": 629902, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0358352661132812, "global_step": 629903, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0666589736938477, "global_step": 629904, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.009307384490967, "global_step": 629905, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.902220606803894, "global_step": 629906, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.939089298248291, "global_step": 629907, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9518450498580933, "global_step": 629908, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0008952617645264, "global_step": 629909, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9348541498184204, "global_step": 629910, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.021127462387085, "global_step": 629911, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.10383939743042, "global_step": 629912, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.964959979057312, "global_step": 629913, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.921317219734192, "global_step": 629914, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0451555252075195, "global_step": 629915, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0560686588287354, "global_step": 629916, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.010762929916382, "global_step": 629917, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0672948360443115, "global_step": 629918, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0089526176452637, "global_step": 629919, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9456322193145752, "global_step": 629920, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0272974967956543, "global_step": 629921, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9411725997924805, "global_step": 629922, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.053701400756836, "global_step": 629923, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.080005168914795, "global_step": 629924, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.011481285095215, "global_step": 629925, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0166797637939453, "global_step": 629926, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.033233165740967, "global_step": 629927, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.98800790309906, "global_step": 629928, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9574638605117798, "global_step": 629929, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0555453300476074, "global_step": 629930, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.985823392868042, "global_step": 629931, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.020580530166626, "global_step": 629932, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9952614307403564, "global_step": 629933, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0082662105560303, "global_step": 629934, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9424512386322021, "global_step": 629935, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.936022400856018, "global_step": 629936, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9839894771575928, "global_step": 629937, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0563018321990967, "global_step": 629938, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9749376773834229, "global_step": 629939, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.039175271987915, "global_step": 629940, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9996083974838257, "global_step": 629941, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0101184844970703, "global_step": 629942, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0003409385681152, "global_step": 629943, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.062473773956299, "global_step": 629944, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0656986236572266, "global_step": 629945, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.959433674812317, "global_step": 629946, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.018435001373291, "global_step": 629947, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9685256481170654, "global_step": 629948, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0185556411743164, "global_step": 629949, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9994518756866455, "global_step": 629950, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.004629611968994, "global_step": 629951, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0424604415893555, "global_step": 629952, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9821557998657227, "global_step": 629953, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8448817729949951, "global_step": 629954, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0224013328552246, "global_step": 629955, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9801844358444214, "global_step": 629956, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.009295701980591, "global_step": 629957, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.079270124435425, "global_step": 629958, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.017906427383423, "global_step": 629959, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.990024209022522, "global_step": 629960, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.036295175552368, "global_step": 629961, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9868342876434326, "global_step": 629962, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.030395030975342, "global_step": 629963, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0358097553253174, "global_step": 629964, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9929622411727905, "global_step": 629965, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.001652717590332, "global_step": 629966, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9230256080627441, "global_step": 629967, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0293962955474854, "global_step": 629968, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9980806112289429, "global_step": 629969, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.099055290222168, "global_step": 629970, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9794379472732544, "global_step": 629971, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9658945798873901, "global_step": 629972, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0646793842315674, "global_step": 629973, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0293853282928467, "global_step": 629974, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0260910987854004, "global_step": 629975, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9421546459197998, "global_step": 629976, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9788075685501099, "global_step": 629977, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.996153473854065, "global_step": 629978, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.032527208328247, "global_step": 629979, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0474021434783936, "global_step": 629980, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.054771900177002, "global_step": 629981, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0015814304351807, "global_step": 629982, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0065107345581055, "global_step": 621261, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9341868162155151, "global_step": 621262, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.051309108734131, "global_step": 621263, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9785575866699219, "global_step": 621264, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0667331218719482, "global_step": 621265, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8907363414764404, "global_step": 621266, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9383549690246582, "global_step": 621267, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.00215482711792, "global_step": 621268, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9813872575759888, "global_step": 621269, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.007305383682251, "global_step": 621270, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.062700033187866, "global_step": 621271, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9396458864212036, "global_step": 621272, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0870518684387207, "global_step": 621273, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.997115135192871, "global_step": 621274, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9733262062072754, "global_step": 621275, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9488399028778076, "global_step": 621276, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8887524604797363, "global_step": 621277, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9910366535186768, "global_step": 621278, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0027313232421875, "global_step": 621279, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9338423013687134, "global_step": 621280, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9789049625396729, "global_step": 621281, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0038228034973145, "global_step": 621282, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0493197441101074, "global_step": 621283, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.046787977218628, "global_step": 621284, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9377187490463257, "global_step": 621285, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9805912971496582, "global_step": 621286, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9886894226074219, "global_step": 621287, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.960233211517334, "global_step": 621288, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9687175750732422, "global_step": 621289, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9989850521087646, "global_step": 621290, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9556888341903687, "global_step": 621291, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9988007545471191, "global_step": 621292, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0299232006073, "global_step": 621293, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.012349843978882, "global_step": 621294, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.041663646697998, "global_step": 621295, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9890567064285278, "global_step": 621296, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.937661051750183, "global_step": 621297, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.937739610671997, "global_step": 621298, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.019927740097046, "global_step": 621299, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.980079174041748, "global_step": 621300, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9483648538589478, "global_step": 621301, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9712939262390137, "global_step": 621302, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1023499965667725, "global_step": 621303, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.101816177368164, "global_step": 621304, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9870377779006958, "global_step": 621305, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9990514516830444, "global_step": 621306, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9289153814315796, "global_step": 621307, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0339324474334717, "global_step": 621308, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0076897144317627, "global_step": 621309, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9890655279159546, "global_step": 621310, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9933035373687744, "global_step": 621311, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.099710702896118, "global_step": 621312, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.004277229309082, "global_step": 621313, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8879817724227905, "global_step": 621314, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.982169508934021, "global_step": 621315, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.120011806488037, "global_step": 621316, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.013920307159424, "global_step": 621317, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.035952091217041, "global_step": 621318, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0256123542785645, "global_step": 621319, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9557769298553467, "global_step": 621320, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0485823154449463, "global_step": 621321, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0262207984924316, "global_step": 621322, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.979374885559082, "global_step": 621323, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.991464376449585, "global_step": 621324, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9598679542541504, "global_step": 621325, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9178248643875122, "global_step": 621326, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.016522169113159, "global_step": 621327, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.982668161392212, "global_step": 621328, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.001329183578491, "global_step": 621329, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.978771686553955, "global_step": 621330, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9696711301803589, "global_step": 621331, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0389318466186523, "global_step": 621332, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9962674379348755, "global_step": 621333, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.029569625854492, "global_step": 621334, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9624305963516235, "global_step": 621335, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9672410488128662, "global_step": 621336, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9687999486923218, "global_step": 621337, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0144765377044678, "global_step": 621338, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9172327518463135, "global_step": 621339, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0081887245178223, "global_step": 621340, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.936651587486267, "global_step": 621341, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9839385747909546, "global_step": 621342, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9930778741836548, "global_step": 621343, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.972900390625, "global_step": 621344, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0435211658477783, "global_step": 621345, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.953532338142395, "global_step": 621346, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9539680480957031, "global_step": 621347, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.998507022857666, "global_step": 621348, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9407200813293457, "global_step": 621349, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0252270698547363, "global_step": 621350, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.068696975708008, "global_step": 621351, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9480186700820923, "global_step": 621352, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.040987253189087, "global_step": 621353, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9530678987503052, "global_step": 621354, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9473477602005005, "global_step": 621355, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0756988525390625, "global_step": 621356, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1304972171783447, "global_step": 621357, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9505622386932373, "global_step": 621358, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8909519910812378, "global_step": 621359, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0386312007904053, "global_step": 621360, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.911001205444336, "global_step": 621361, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.93922758102417, "global_step": 621362, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.98223078250885, "global_step": 621363, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9990862607955933, "global_step": 621364, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.975611686706543, "global_step": 621365, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0037765502929688, "global_step": 621366, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.036632776260376, "global_step": 621367, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0489237308502197, "global_step": 621368, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9527850151062012, "global_step": 621369, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0024452209472656, "global_step": 621370, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9877965450286865, "global_step": 621371, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0185611248016357, "global_step": 621372, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9575705528259277, "global_step": 621373, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9351263046264648, "global_step": 621374, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.019390106201172, "global_step": 621375, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1197173595428467, "global_step": 621376, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0769214630126953, "global_step": 621377, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.985364556312561, "global_step": 621378, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9859793186187744, "global_step": 621379, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0760209560394287, "global_step": 621380, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.029940128326416, "global_step": 621381, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.05322003364563, "global_step": 621382, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0672285556793213, "global_step": 621383, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.938361406326294, "global_step": 621384, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.045830726623535, "global_step": 621385, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9832799434661865, "global_step": 621386, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9591504335403442, "global_step": 621387, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9694225788116455, "global_step": 621388, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9178866147994995, "global_step": 621389, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9692293405532837, "global_step": 621390, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.994246482849121, "global_step": 621391, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.042081832885742, "global_step": 621392, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0275111198425293, "global_step": 621393, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9601874351501465, "global_step": 621394, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.963620901107788, "global_step": 621395, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9732965230941772, "global_step": 621396, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.952041506767273, "global_step": 621397, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9736638069152832, "global_step": 621398, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.972975730895996, "global_step": 621399, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9806129932403564, "global_step": 621400, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.994673252105713, "global_step": 621401, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9398446083068848, "global_step": 621402, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0060555934906006, "global_step": 621403, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.047376871109009, "global_step": 621404, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.028909683227539, "global_step": 621405, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9378252029418945, "global_step": 621406, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.026434898376465, "global_step": 621407, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.009761095046997, "global_step": 621408, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.037182569503784, "global_step": 621409, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.084613561630249, "global_step": 621410, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9664329290390015, "global_step": 621411, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.032723903656006, "global_step": 621412, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0552432537078857, "global_step": 621413, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9674040079116821, "global_step": 621414, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.006110191345215, "global_step": 621415, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.057544469833374, "global_step": 621416, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0257341861724854, "global_step": 621417, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.065971612930298, "global_step": 621418, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9696968793869019, "global_step": 621419, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.949875831604004, "global_step": 621420, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.054737091064453, "global_step": 621421, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9110748767852783, "global_step": 621422, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9486631155014038, "global_step": 621423, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0139617919921875, "global_step": 621424, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9419431686401367, "global_step": 621425, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9682618379592896, "global_step": 621426, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0339715480804443, "global_step": 621427, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0057733058929443, "global_step": 621428, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0013864040374756, "global_step": 621429, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9867430925369263, "global_step": 621430, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.014630079269409, "global_step": 621431, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9244095087051392, "global_step": 621432, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.940416932106018, "global_step": 621433, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0263307094573975, "global_step": 621434, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9390662908554077, "global_step": 621435, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.954793930053711, "global_step": 621436, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.978168249130249, "global_step": 621437, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.93075430393219, "global_step": 621438, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0225822925567627, "global_step": 621439, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9341140985488892, "global_step": 621440, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.97159743309021, "global_step": 621441, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9735591411590576, "global_step": 621442, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9858949184417725, "global_step": 621443, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9741711616516113, "global_step": 621444, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.00512957572937, "global_step": 621445, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9784834384918213, "global_step": 621446, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0055840015411377, "global_step": 621447, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.016313314437866, "global_step": 621448, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9946789741516113, "global_step": 621449, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9616663455963135, "global_step": 621450, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1167895793914795, "global_step": 621451, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8971507549285889, "global_step": 621452, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0613644123077393, "global_step": 621453, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.011096954345703, "global_step": 621454, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0864875316619873, "global_step": 621455, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9771513938903809, "global_step": 621456, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.029428005218506, "global_step": 621457, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9738967418670654, "global_step": 621458, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.04695200920105, "global_step": 621459, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9389090538024902, "global_step": 621460, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9633690118789673, "global_step": 621461, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9679759740829468, "global_step": 621462, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9269111156463623, "global_step": 621463, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.852376937866211, "global_step": 621464, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9710395336151123, "global_step": 621465, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9647538661956787, "global_step": 621466, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9420245885849, "global_step": 621467, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9876803159713745, "global_step": 621468, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9919966459274292, "global_step": 621469, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9306938648223877, "global_step": 621470, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.889487624168396, "global_step": 621471, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1313023567199707, "global_step": 621472, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.022080898284912, "global_step": 621473, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0807952880859375, "global_step": 621474, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9772670269012451, "global_step": 621475, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0078818798065186, "global_step": 621476, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0314693450927734, "global_step": 621477, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9508308172225952, "global_step": 621478, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9883733987808228, "global_step": 621479, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.970149278640747, "global_step": 621480, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0299041271209717, "global_step": 621481, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9845731258392334, "global_step": 621482, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9881529808044434, "global_step": 621483, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.005918025970459, "global_step": 621484, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.034313678741455, "global_step": 621485, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.008533000946045, "global_step": 621486, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0387396812438965, "global_step": 621487, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9985432624816895, "global_step": 621488, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.044370412826538, "global_step": 621489, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0358290672302246, "global_step": 621490, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0077638626098633, "global_step": 621491, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0816450119018555, "global_step": 621492, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.982720971107483, "global_step": 621493, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.985607624053955, "global_step": 621494, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9866440296173096, "global_step": 621495, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.976417064666748, "global_step": 621496, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9326285123825073, "global_step": 621497, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0520341396331787, "global_step": 621498, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9928724765777588, "global_step": 621499, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.951558232307434, "global_step": 621500, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9935563802719116, "global_step": 621501, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9492210149765015, "global_step": 621502, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.036768913269043, "global_step": 621503, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.958056926727295, "global_step": 621504, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.035592794418335, "global_step": 621505, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0403661727905273, "global_step": 621506, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0067832469940186, "global_step": 621507, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.99126398563385, "global_step": 621508, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9214916229248047, "global_step": 621509, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0469863414764404, "global_step": 621510, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.008484125137329, "global_step": 621511, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9688726663589478, "global_step": 621512, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0245583057403564, "global_step": 621513, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0676982402801514, "global_step": 621514, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9937382936477661, "global_step": 621515, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.060145854949951, "global_step": 621516, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9880605936050415, "global_step": 621517, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.030566453933716, "global_step": 621518, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9848803281784058, "global_step": 621519, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.057964563369751, "global_step": 621520, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9555447101593018, "global_step": 621521, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9567680358886719, "global_step": 621522, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.999126672744751, "global_step": 621523, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8949470520019531, "global_step": 621524, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0164434909820557, "global_step": 621525, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9746915102005005, "global_step": 621526, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0195488929748535, "global_step": 621527, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0737926959991455, "global_step": 621528, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9939568042755127, "global_step": 621529, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9041593074798584, "global_step": 621530, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9327305555343628, "global_step": 621531, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.026726245880127, "global_step": 621532, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.983687400817871, "global_step": 621533, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9588143825531006, "global_step": 621534, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9420429468154907, "global_step": 621535, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9885859489440918, "global_step": 621536, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9646013975143433, "global_step": 621537, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.942474365234375, "global_step": 621538, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9658448696136475, "global_step": 621539, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0188724994659424, "global_step": 621540, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.051790475845337, "global_step": 621541, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.016150712966919, "global_step": 621542, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.006507635116577, "global_step": 621543, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0553700923919678, "global_step": 621544, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.993586778640747, "global_step": 621545, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.919224739074707, "global_step": 621546, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0377347469329834, "global_step": 621547, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.050899028778076, "global_step": 621548, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0362353324890137, "global_step": 621549, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0168731212615967, "global_step": 621550, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9631320238113403, "global_step": 621551, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.047105073928833, "global_step": 621552, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.087369680404663, "global_step": 621553, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9152218103408813, "global_step": 621554, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0070722103118896, "global_step": 621555, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8940402269363403, "global_step": 621556, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9300123453140259, "global_step": 621557, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9717304706573486, "global_step": 621558, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.003913640975952, "global_step": 621559, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9806265830993652, "global_step": 621560, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0616376399993896, "global_step": 621561, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0179474353790283, "global_step": 621562, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.902813196182251, "global_step": 621563, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0695669651031494, "global_step": 621564, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0154170989990234, "global_step": 621565, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9911375045776367, "global_step": 621566, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.042682647705078, "global_step": 621567, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9453659057617188, "global_step": 621568, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9726518392562866, "global_step": 621569, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9703829288482666, "global_step": 621570, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.01115083694458, "global_step": 621571, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9808963537216187, "global_step": 621572, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9610732793807983, "global_step": 621573, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9432575702667236, "global_step": 621574, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0148813724517822, "global_step": 621575, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9961178302764893, "global_step": 621576, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9088902473449707, "global_step": 621577, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9786736965179443, "global_step": 621578, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.034862756729126, "global_step": 621579, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0658297538757324, "global_step": 621580, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9527287483215332, "global_step": 621581, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.043118476867676, "global_step": 621582, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9017935991287231, "global_step": 621583, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0032386779785156, "global_step": 621584, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.941895604133606, "global_step": 621585, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0086498260498047, "global_step": 621586, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9856164455413818, "global_step": 621587, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.011683225631714, "global_step": 621588, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9598280191421509, "global_step": 621589, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9812021255493164, "global_step": 621590, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.975308895111084, "global_step": 621591, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9782243967056274, "global_step": 621592, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9617815017700195, "global_step": 621593, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0046308040618896, "global_step": 621594, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.077697992324829, "global_step": 621595, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.958086609840393, "global_step": 621596, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.947811245918274, "global_step": 621597, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.007958173751831, "global_step": 621598, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9988025426864624, "global_step": 621599, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9340258836746216, "global_step": 621600, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.002653121948242, "global_step": 621601, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0165727138519287, "global_step": 621602, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9746415615081787, "global_step": 621603, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.054832696914673, "global_step": 621604, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.036468505859375, "global_step": 621605, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.035635471343994, "global_step": 621606, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.023197650909424, "global_step": 621607, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0262451171875, "global_step": 621608, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0396437644958496, "global_step": 621609, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0875964164733887, "global_step": 621610, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.968552827835083, "global_step": 621611, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9988175630569458, "global_step": 621612, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0284268856048584, "global_step": 621613, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.049415111541748, "global_step": 621614, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0240304470062256, "global_step": 621615, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9353885650634766, "global_step": 621616, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.957302451133728, "global_step": 621617, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.013326406478882, "global_step": 621618, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.04687237739563, "global_step": 621619, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.887635588645935, "global_step": 621620, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0243427753448486, "global_step": 621621, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9756675958633423, "global_step": 621622, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.091143846511841, "global_step": 621623, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.044095516204834, "global_step": 621624, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.040902853012085, "global_step": 621625, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9970738887786865, "global_step": 621626, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.042879819869995, "global_step": 621627, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.997816562652588, "global_step": 621628, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0272018909454346, "global_step": 621629, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9172688722610474, "global_step": 621630, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9499679803848267, "global_step": 621631, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.981234073638916, "global_step": 621632, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9803133010864258, "global_step": 621633, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.010296583175659, "global_step": 621634, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8921297788619995, "global_step": 621635, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0412700176239014, "global_step": 621636, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9107892513275146, "global_step": 621637, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.003056287765503, "global_step": 621638, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9671926498413086, "global_step": 621639, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.003786087036133, "global_step": 621640, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.001187562942505, "global_step": 621641, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9437803030014038, "global_step": 621642, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.994362711906433, "global_step": 621643, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9788577556610107, "global_step": 621644, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.025705575942993, "global_step": 621645, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0712764263153076, "global_step": 621646, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.077556848526001, "global_step": 621647, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9650431871414185, "global_step": 621648, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9438453912734985, "global_step": 621649, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0370748043060303, "global_step": 621650, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.057079315185547, "global_step": 621651, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.023575782775879, "global_step": 621652, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.078460216522217, "global_step": 621653, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9871422052383423, "global_step": 621654, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0014078617095947, "global_step": 621655, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.926571011543274, "global_step": 621656, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9628204107284546, "global_step": 621657, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.008516311645508, "global_step": 621658, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.072329044342041, "global_step": 621659, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9685523509979248, "global_step": 621660, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9909306764602661, "global_step": 621661, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9965746402740479, "global_step": 621662, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0384607315063477, "global_step": 621663, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0150461196899414, "global_step": 621664, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0725059509277344, "global_step": 621665, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.973572850227356, "global_step": 621666, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9622514247894287, "global_step": 621667, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.999163269996643, "global_step": 621668, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0266497135162354, "global_step": 621669, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1102089881896973, "global_step": 621670, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0063323974609375, "global_step": 621671, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.05281925201416, "global_step": 621672, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.90663480758667, "global_step": 621673, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9786478281021118, "global_step": 621674, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.031913995742798, "global_step": 621675, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0444529056549072, "global_step": 621676, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9617685079574585, "global_step": 621677, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.022247076034546, "global_step": 621678, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9255142211914062, "global_step": 621679, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9693031311035156, "global_step": 621680, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0131726264953613, "global_step": 621681, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.950930118560791, "global_step": 621682, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9733455181121826, "global_step": 621683, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.006561040878296, "global_step": 621684, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9977686405181885, "global_step": 621685, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0826971530914307, "global_step": 621686, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.974995732307434, "global_step": 621687, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9915885925292969, "global_step": 621688, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9847205877304077, "global_step": 621689, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9863440990447998, "global_step": 621690, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9815256595611572, "global_step": 621691, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8437906503677368, "global_step": 621692, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.973130226135254, "global_step": 621693, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0530619621276855, "global_step": 621694, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9486984014511108, "global_step": 621695, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.000366687774658, "global_step": 621696, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.001664638519287, "global_step": 621697, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9945800304412842, "global_step": 621698, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0705833435058594, "global_step": 621699, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9553735256195068, "global_step": 621700, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9984711408615112, "global_step": 621701, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0205066204071045, "global_step": 621702, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0792341232299805, "global_step": 621703, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0488016605377197, "global_step": 621704, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.961185097694397, "global_step": 621705, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9214012622833252, "global_step": 621706, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.013540029525757, "global_step": 621707, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9774881601333618, "global_step": 621708, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9593487977981567, "global_step": 621709, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0803022384643555, "global_step": 621710, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9451918601989746, "global_step": 621711, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.960882544517517, "global_step": 621712, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.989475131034851, "global_step": 621713, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0279834270477295, "global_step": 621714, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.977904200553894, "global_step": 621715, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.943097710609436, "global_step": 621716, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9999158382415771, "global_step": 621717, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0406506061553955, "global_step": 621718, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.012235164642334, "global_step": 621719, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.057344675064087, "global_step": 621720, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9386053085327148, "global_step": 621721, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.010486364364624, "global_step": 621722, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0983471870422363, "global_step": 621723, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0190982818603516, "global_step": 621724, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.059634208679199, "global_step": 621725, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.917505145072937, "global_step": 621726, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9190728664398193, "global_step": 621727, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9826929569244385, "global_step": 621728, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.070674419403076, "global_step": 621729, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0626375675201416, "global_step": 621730, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0180187225341797, "global_step": 621731, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0463969707489014, "global_step": 621732, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9591022729873657, "global_step": 621733, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9205814599990845, "global_step": 621734, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9644463062286377, "global_step": 621735, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0103256702423096, "global_step": 621736, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.878096580505371, "global_step": 621737, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.055795431137085, "global_step": 621738, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.927495002746582, "global_step": 621739, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9942079782485962, "global_step": 621740, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.976094126701355, "global_step": 621741, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0132336616516113, "global_step": 621742, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9613243341445923, "global_step": 621743, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.909358024597168, "global_step": 621744, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9477429389953613, "global_step": 621745, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9544990062713623, "global_step": 621746, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0800650119781494, "global_step": 621747, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9934552907943726, "global_step": 621748, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.026453733444214, "global_step": 621749, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0391135215759277, "global_step": 621750, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0359725952148438, "global_step": 621751, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.048081874847412, "global_step": 621752, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0150363445281982, "global_step": 621753, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0816009044647217, "global_step": 621754, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.974144458770752, "global_step": 621755, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.045907735824585, "global_step": 621756, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9932769536972046, "global_step": 621757, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0627338886260986, "global_step": 621758, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.951897382736206, "global_step": 621759, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9361599683761597, "global_step": 621760, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9596915245056152, "global_step": 621761, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0220439434051514, "global_step": 621762, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.009209156036377, "global_step": 621763, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9662196636199951, "global_step": 621764, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0525052547454834, "global_step": 621765, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.005141019821167, "global_step": 621766, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0739994049072266, "global_step": 621767, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9795478582382202, "global_step": 621768, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9390416145324707, "global_step": 621769, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.941921591758728, "global_step": 621770, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.051004409790039, "global_step": 621771, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0144295692443848, "global_step": 621772, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9934431314468384, "global_step": 621773, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0902442932128906, "global_step": 621774, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0103235244750977, "global_step": 621775, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.013000249862671, "global_step": 621776, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9707852602005005, "global_step": 621777, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9480918645858765, "global_step": 621778, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9881469011306763, "global_step": 621779, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.010956287384033, "global_step": 621780, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9900377988815308, "global_step": 621781, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0505447387695312, "global_step": 621782, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.009575366973877, "global_step": 621783, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.979617714881897, "global_step": 621784, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9627925157546997, "global_step": 621785, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0582051277160645, "global_step": 621786, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9090991020202637, "global_step": 621787, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.005441904067993, "global_step": 621788, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8934237957000732, "global_step": 621789, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9614592790603638, "global_step": 621790, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0030040740966797, "global_step": 621791, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9587717056274414, "global_step": 621792, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0400965213775635, "global_step": 621793, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9839444160461426, "global_step": 621794, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0864410400390625, "global_step": 621795, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9586893320083618, "global_step": 621796, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.945388913154602, "global_step": 621797, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9931470155715942, "global_step": 621798, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9806575775146484, "global_step": 621799, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8857721090316772, "global_step": 621800, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0683953762054443, "global_step": 621801, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0264320373535156, "global_step": 621802, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9182382822036743, "global_step": 621803, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0387537479400635, "global_step": 621804, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0338058471679688, "global_step": 621805, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0500638484954834, "global_step": 621806, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.003096342086792, "global_step": 621807, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.058220148086548, "global_step": 621808, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.985180139541626, "global_step": 621809, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0560367107391357, "global_step": 621810, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8920279741287231, "global_step": 621811, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.083475112915039, "global_step": 621812, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.052474021911621, "global_step": 621813, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9871028661727905, "global_step": 621814, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9490056037902832, "global_step": 621815, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0649068355560303, "global_step": 621816, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9059994220733643, "global_step": 621817, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0584843158721924, "global_step": 621818, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9494863748550415, "global_step": 621819, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.946858286857605, "global_step": 621820, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8888541460037231, "global_step": 621821, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9656147956848145, "global_step": 621822, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9988644123077393, "global_step": 621823, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.037506341934204, "global_step": 621824, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0273187160491943, "global_step": 621825, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9143414497375488, "global_step": 621826, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.03068470954895, "global_step": 621827, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.026369571685791, "global_step": 621828, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9196568727493286, "global_step": 621829, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9944864511489868, "global_step": 621830, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.006182909011841, "global_step": 621831, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.038079023361206, "global_step": 621832, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.033250093460083, "global_step": 621833, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9977277517318726, "global_step": 621834, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9841201305389404, "global_step": 621835, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9158660173416138, "global_step": 621836, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0440287590026855, "global_step": 621837, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0111441612243652, "global_step": 621838, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9503352642059326, "global_step": 621839, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0041239261627197, "global_step": 621840, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.01668119430542, "global_step": 621841, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9670673608779907, "global_step": 621842, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.921296238899231, "global_step": 621843, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.00091552734375, "global_step": 621844, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9972320795059204, "global_step": 621845, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9794706106185913, "global_step": 621846, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9983724355697632, "global_step": 621847, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.982975959777832, "global_step": 621848, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.957054853439331, "global_step": 621849, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9820507764816284, "global_step": 621850, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.024986982345581, "global_step": 621851, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.00993013381958, "global_step": 621852, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9818861484527588, "global_step": 621853, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.99463951587677, "global_step": 621854, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8591980934143066, "global_step": 621855, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.022472381591797, "global_step": 621856, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0250775814056396, "global_step": 621857, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9272620677947998, "global_step": 621858, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8626283407211304, "global_step": 621859, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9782828092575073, "global_step": 621860, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.012352466583252, "global_step": 621861, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.004128932952881, "global_step": 621862, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.080752372741699, "global_step": 621863, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9790589809417725, "global_step": 621864, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9791560173034668, "global_step": 621865, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0923635959625244, "global_step": 621866, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0030083656311035, "global_step": 621867, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9588056802749634, "global_step": 621868, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.993072748184204, "global_step": 621869, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.965646743774414, "global_step": 621870, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.019731044769287, "global_step": 621871, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0366315841674805, "global_step": 621872, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9659429788589478, "global_step": 621873, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.027040719985962, "global_step": 621874, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9674900770187378, "global_step": 621875, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9541456699371338, "global_step": 621876, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0784249305725098, "global_step": 621877, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0629332065582275, "global_step": 621878, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.060850143432617, "global_step": 621879, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0059895515441895, "global_step": 621880, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0473268032073975, "global_step": 621881, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0965678691864014, "global_step": 621882, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0178587436676025, "global_step": 621883, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9826607704162598, "global_step": 621884, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9540244340896606, "global_step": 621885, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.000114679336548, "global_step": 621886, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.026897668838501, "global_step": 621887, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9936821460723877, "global_step": 621888, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.022601366043091, "global_step": 621889, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9059648513793945, "global_step": 621890, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9410288333892822, "global_step": 621891, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0212810039520264, "global_step": 621892, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9387925863265991, "global_step": 621893, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0017611980438232, "global_step": 621894, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0579233169555664, "global_step": 621895, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9777121543884277, "global_step": 621896, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9534553289413452, "global_step": 621897, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0482373237609863, "global_step": 621898, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.973970651626587, "global_step": 621899, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0478389263153076, "global_step": 621900, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.992915153503418, "global_step": 621901, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0203208923339844, "global_step": 621902, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0240931510925293, "global_step": 621903, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.023059129714966, "global_step": 621904, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0440475940704346, "global_step": 621905, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.044436454772949, "global_step": 621906, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.976972222328186, "global_step": 621907, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9993373155593872, "global_step": 621908, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0842084884643555, "global_step": 621909, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9839560985565186, "global_step": 621910, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0138001441955566, "global_step": 621911, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.13879656791687, "global_step": 621912, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9941877126693726, "global_step": 621913, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9683126211166382, "global_step": 621914, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9571681022644043, "global_step": 621915, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9680936336517334, "global_step": 621916, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0259344577789307, "global_step": 621917, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0378990173339844, "global_step": 621918, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0507376194000244, "global_step": 621919, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9944679737091064, "global_step": 621920, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0537538528442383, "global_step": 621921, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9989736080169678, "global_step": 621922, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9496407508850098, "global_step": 621923, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9939855337142944, "global_step": 621924, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.013101816177368, "global_step": 621925, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.032615900039673, "global_step": 621926, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0329201221466064, "global_step": 621927, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0925705432891846, "global_step": 621928, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9742985963821411, "global_step": 621929, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.011436939239502, "global_step": 621930, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9950000047683716, "global_step": 621931, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0138068199157715, "global_step": 621932, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9978301525115967, "global_step": 621933, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.071605682373047, "global_step": 621934, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9997336864471436, "global_step": 621935, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.020110607147217, "global_step": 621936, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.043801784515381, "global_step": 621937, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.022854804992676, "global_step": 621938, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0830368995666504, "global_step": 621939, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0013933181762695, "global_step": 621940, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0580663681030273, "global_step": 621941, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8698478937149048, "global_step": 621942, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.909895420074463, "global_step": 621943, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0019588470458984, "global_step": 621944, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9695724248886108, "global_step": 621945, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.043341636657715, "global_step": 621946, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0027008056640625, "global_step": 621947, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.086158514022827, "global_step": 621948, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0086488723754883, "global_step": 621949, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.981269359588623, "global_step": 621950, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9770643711090088, "global_step": 621951, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9860680103302002, "global_step": 621952, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.011025905609131, "global_step": 621953, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9938112497329712, "global_step": 621954, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.052886962890625, "global_step": 621955, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.086416721343994, "global_step": 621956, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0152549743652344, "global_step": 621957, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9704030752182007, "global_step": 621958, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9750747680664062, "global_step": 621959, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.084590196609497, "global_step": 621960, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0604732036590576, "global_step": 621961, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.034644365310669, "global_step": 621962, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.934836983680725, "global_step": 621963, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9709237813949585, "global_step": 621964, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.033912181854248, "global_step": 621965, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9119874238967896, "global_step": 621966, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.950565218925476, "global_step": 621967, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.018871545791626, "global_step": 621968, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.968229055404663, "global_step": 621969, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9835000038146973, "global_step": 621970, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0444815158843994, "global_step": 621971, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.043299436569214, "global_step": 621972, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.968590259552002, "global_step": 621973, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1021945476531982, "global_step": 621974, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9756481647491455, "global_step": 621975, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9212076663970947, "global_step": 621976, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.044253349304199, "global_step": 621977, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0021767616271973, "global_step": 621978, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.01737380027771, "global_step": 621979, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9883581399917603, "global_step": 621980, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9870930910110474, "global_step": 621981, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9373316764831543, "global_step": 621982, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.983325481414795, "global_step": 621983, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.022675037384033, "global_step": 621984, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.069492816925049, "global_step": 621985, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.011061906814575, "global_step": 621986, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9248158931732178, "global_step": 621987, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0124404430389404, "global_step": 621988, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9732519388198853, "global_step": 621989, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0240366458892822, "global_step": 621990, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.964728593826294, "global_step": 621991, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0782546997070312, "global_step": 621992, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9746352434158325, "global_step": 621993, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9365490674972534, "global_step": 621994, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0340394973754883, "global_step": 621995, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.083167791366577, "global_step": 621996, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.000786542892456, "global_step": 621997, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9989519119262695, "global_step": 621998, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0155491828918457, "global_step": 621999, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9172475337982178, "global_step": 622000, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9923717975616455, "global_step": 622001, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.974753975868225, "global_step": 622002, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.008512258529663, "global_step": 622003, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9810400009155273, "global_step": 622004, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9336365461349487, "global_step": 622005, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9995743036270142, "global_step": 622006, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0871455669403076, "global_step": 622007, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0081899166107178, "global_step": 622008, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9356127977371216, "global_step": 622009, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.967071294784546, "global_step": 622010, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.019796848297119, "global_step": 622011, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0315606594085693, "global_step": 622012, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0172951221466064, "global_step": 622013, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9661988019943237, "global_step": 622014, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9744081497192383, "global_step": 622015, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0897216796875, "global_step": 622016, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.948253870010376, "global_step": 622017, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.983506441116333, "global_step": 622018, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9940266609191895, "global_step": 622019, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.042945384979248, "global_step": 622020, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.996341347694397, "global_step": 622021, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9522268772125244, "global_step": 622022, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0310184955596924, "global_step": 622023, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0414350032806396, "global_step": 622024, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0181870460510254, "global_step": 622025, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0470502376556396, "global_step": 622026, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.006838083267212, "global_step": 622027, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8651708364486694, "global_step": 622028, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9542961120605469, "global_step": 622029, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.089177370071411, "global_step": 622030, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.002124309539795, "global_step": 622031, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9992585182189941, "global_step": 622032, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.992483377456665, "global_step": 622033, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.987627625465393, "global_step": 622034, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0716865062713623, "global_step": 622035, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.029703378677368, "global_step": 622036, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0196666717529297, "global_step": 622037, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.992214560508728, "global_step": 622038, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.950344443321228, "global_step": 622039, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.05021071434021, "global_step": 622040, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9888660907745361, "global_step": 622041, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0525989532470703, "global_step": 622042, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9020193815231323, "global_step": 622043, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.998990774154663, "global_step": 622044, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0429441928863525, "global_step": 622045, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.061337471008301, "global_step": 622046, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.117151975631714, "global_step": 622047, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9476673603057861, "global_step": 622048, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9760985374450684, "global_step": 622049, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.010939836502075, "global_step": 622050, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.016278028488159, "global_step": 622051, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0245068073272705, "global_step": 622052, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.058969020843506, "global_step": 622053, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9395842552185059, "global_step": 622054, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.988035798072815, "global_step": 622055, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.96046781539917, "global_step": 622056, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.026078939437866, "global_step": 622057, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0247669219970703, "global_step": 622058, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0294933319091797, "global_step": 622059, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.026564121246338, "global_step": 622060, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.992661952972412, "global_step": 622061, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9927504062652588, "global_step": 622062, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0119504928588867, "global_step": 622063, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9939566850662231, "global_step": 622064, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0431008338928223, "global_step": 622065, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0572705268859863, "global_step": 622066, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9711227416992188, "global_step": 622067, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9804742336273193, "global_step": 622068, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9820821285247803, "global_step": 622069, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9698114395141602, "global_step": 622070, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9222365617752075, "global_step": 622071, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0677454471588135, "global_step": 622072, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0762975215911865, "global_step": 622073, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9083553552627563, "global_step": 622074, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.062258005142212, "global_step": 622075, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.014653205871582, "global_step": 622076, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.993937373161316, "global_step": 622077, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.980940341949463, "global_step": 622078, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.106891632080078, "global_step": 622079, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1288363933563232, "global_step": 622080, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.012894630432129, "global_step": 622081, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9809424877166748, "global_step": 622082, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.032430410385132, "global_step": 622083, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.065119981765747, "global_step": 622084, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9685468673706055, "global_step": 622085, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.971366286277771, "global_step": 622086, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9295669794082642, "global_step": 622087, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9625645875930786, "global_step": 622088, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9663009643554688, "global_step": 622089, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9286867380142212, "global_step": 622090, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0060696601867676, "global_step": 622091, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9982938766479492, "global_step": 622092, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9592043161392212, "global_step": 622093, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9866232872009277, "global_step": 622094, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.023534059524536, "global_step": 622095, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.084554672241211, "global_step": 622096, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.044710159301758, "global_step": 622097, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9902695417404175, "global_step": 622098, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0078492164611816, "global_step": 622099, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1230483055114746, "global_step": 622100, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0314371585845947, "global_step": 622101, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9405215978622437, "global_step": 622102, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0235695838928223, "global_step": 622103, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0009653568267822, "global_step": 622104, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.077211856842041, "global_step": 622105, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9836786985397339, "global_step": 622106, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0120153427124023, "global_step": 622107, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9731069803237915, "global_step": 622108, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0136313438415527, "global_step": 622109, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0738909244537354, "global_step": 622110, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0367181301116943, "global_step": 622111, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0194320678710938, "global_step": 622112, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.074124336242676, "global_step": 622113, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0518319606781006, "global_step": 622114, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0447235107421875, "global_step": 622115, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0648112297058105, "global_step": 622116, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9730339050292969, "global_step": 622117, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9694243669509888, "global_step": 622118, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.966223120689392, "global_step": 622119, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9985698461532593, "global_step": 622120, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.961239218711853, "global_step": 622121, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0352978706359863, "global_step": 622122, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9501014947891235, "global_step": 622123, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9772462844848633, "global_step": 622124, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.02512264251709, "global_step": 622125, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0662145614624023, "global_step": 622126, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0271878242492676, "global_step": 622127, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9950984716415405, "global_step": 622128, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0456247329711914, "global_step": 622129, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0397777557373047, "global_step": 622130, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9849534034729004, "global_step": 622131, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9954092502593994, "global_step": 622132, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0673749446868896, "global_step": 622133, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0542192459106445, "global_step": 622134, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9980038404464722, "global_step": 622135, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.035959005355835, "global_step": 622136, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.994086503982544, "global_step": 622137, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0096216201782227, "global_step": 622138, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0272696018218994, "global_step": 622139, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0396153926849365, "global_step": 622140, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.001631498336792, "global_step": 622141, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.007758378982544, "global_step": 622142, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.957648754119873, "global_step": 622143, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.055838108062744, "global_step": 622144, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0574090480804443, "global_step": 622145, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.002408027648926, "global_step": 622146, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8928204774856567, "global_step": 622147, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9923145771026611, "global_step": 622148, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9686495065689087, "global_step": 622149, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.943300724029541, "global_step": 622150, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.058023452758789, "global_step": 622151, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0157041549682617, "global_step": 622152, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0753331184387207, "global_step": 622153, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8852514028549194, "global_step": 622154, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.104379177093506, "global_step": 622155, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0306451320648193, "global_step": 622156, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.981471300125122, "global_step": 622157, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9605947732925415, "global_step": 622158, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9916495084762573, "global_step": 622159, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9694359302520752, "global_step": 622160, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0153138637542725, "global_step": 622161, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0776944160461426, "global_step": 622162, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1032509803771973, "global_step": 622163, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.8790075778961182, "global_step": 622164, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0102829933166504, "global_step": 622165, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.1230509281158447, "global_step": 622166, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0880837440490723, "global_step": 622167, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0237269401550293, "global_step": 622168, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.064070224761963, "global_step": 622169, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.043720006942749, "global_step": 622170, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.022831439971924, "global_step": 622171, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9589344263076782, "global_step": 622172, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9377834796905518, "global_step": 622173, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0336244106292725, "global_step": 622174, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9708129167556763, "global_step": 622175, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0043468475341797, "global_step": 622176, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9338867664337158, "global_step": 622177, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9817951917648315, "global_step": 622178, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9538558721542358, "global_step": 622179, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0887608528137207, "global_step": 622180, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.039092540740967, "global_step": 622181, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9150151014328003, "global_step": 622182, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0706779956817627, "global_step": 622183, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0259368419647217, "global_step": 622184, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.005293369293213, "global_step": 622185, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9878548383712769, "global_step": 622186, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9430564641952515, "global_step": 622187, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0175771713256836, "global_step": 622188, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9867287874221802, "global_step": 622189, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9897634983062744, "global_step": 622190, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.010636329650879, "global_step": 622191, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0500173568725586, "global_step": 622192, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.075089931488037, "global_step": 622193, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0636558532714844, "global_step": 622194, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9963245391845703, "global_step": 622195, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.091305732727051, "global_step": 622196, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9970784187316895, "global_step": 622197, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9779258966445923, "global_step": 622198, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0834081172943115, "global_step": 622199, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.026902437210083, "global_step": 622200, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9881175756454468, "global_step": 622201, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9772686958312988, "global_step": 622202, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9771625995635986, "global_step": 622203, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9341378211975098, "global_step": 622204, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0622801780700684, "global_step": 622205, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.003563642501831, "global_step": 622206, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0027358531951904, "global_step": 622207, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0621421337127686, "global_step": 622208, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9673993587493896, "global_step": 622209, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.026250123977661, "global_step": 622210, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0379438400268555, "global_step": 622211, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.99924898147583, "global_step": 622212, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0433313846588135, "global_step": 622213, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.129977226257324, "global_step": 622214, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0675480365753174, "global_step": 622215, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0169694423675537, "global_step": 622216, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.046541452407837, "global_step": 622217, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9571647644042969, "global_step": 622218, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.991413950920105, "global_step": 622219, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.042052984237671, "global_step": 622220, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9324655532836914, "global_step": 622221, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9271557331085205, "global_step": 622222, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9663362503051758, "global_step": 622223, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.984292984008789, "global_step": 622224, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.097153902053833, "global_step": 622225, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.9514950513839722, "global_step": 622226, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0355634689331055, "global_step": 622227, "epoch": 990, "lr": 5e-05}
{"train_loss": 2.0546088218688965, "global_step": 622228, "epoch": 990, "lr": 5e-05}
{"train_loss": 1.999935507774353, "global_step": 622229, "epoch": 990, "lr": 5e-05, "val_loss": 5.865447521209717, "test_reconst_mse": 0.07360617071390152}
{"train_loss": 1.952012538909912, "global_step": 622230, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9673266410827637, "global_step": 622231, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9243049621582031, "global_step": 622232, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9347679615020752, "global_step": 622233, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9500421285629272, "global_step": 622234, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.983401894569397, "global_step": 622235, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.94969642162323, "global_step": 622236, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0119848251342773, "global_step": 622237, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9705860614776611, "global_step": 622238, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.957526683807373, "global_step": 622239, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0271518230438232, "global_step": 622240, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9996410608291626, "global_step": 622241, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9930953979492188, "global_step": 622242, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9662238359451294, "global_step": 622243, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.99893319606781, "global_step": 622244, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0275609493255615, "global_step": 622245, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0019705295562744, "global_step": 622246, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9324626922607422, "global_step": 622247, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9710196256637573, "global_step": 622248, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0968198776245117, "global_step": 622249, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9712177515029907, "global_step": 622250, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.951910376548767, "global_step": 622251, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8928745985031128, "global_step": 622252, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.942431926727295, "global_step": 622253, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9499539136886597, "global_step": 622254, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9702911376953125, "global_step": 622255, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0891597270965576, "global_step": 622256, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9875850677490234, "global_step": 622257, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.962923288345337, "global_step": 622258, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0343177318573, "global_step": 622259, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9206708669662476, "global_step": 622260, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0036041736602783, "global_step": 622261, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9170136451721191, "global_step": 622262, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0543429851531982, "global_step": 622263, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.023350238800049, "global_step": 622264, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9117095470428467, "global_step": 622265, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.008951187133789, "global_step": 622266, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.988512396812439, "global_step": 622267, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9855185747146606, "global_step": 622268, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9749491214752197, "global_step": 622269, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9216560125350952, "global_step": 622270, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9414396286010742, "global_step": 622271, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0259432792663574, "global_step": 622272, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9303858280181885, "global_step": 622273, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9536254405975342, "global_step": 622274, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9493175745010376, "global_step": 622275, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0092575550079346, "global_step": 622276, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9539999961853027, "global_step": 622277, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9956897497177124, "global_step": 622278, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9552526473999023, "global_step": 622279, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9796620607376099, "global_step": 622280, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.034574270248413, "global_step": 622281, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.002027750015259, "global_step": 622282, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.045660972595215, "global_step": 622283, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.024960994720459, "global_step": 622284, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9962635040283203, "global_step": 622285, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0143990516662598, "global_step": 622286, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9611350297927856, "global_step": 622287, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0553009510040283, "global_step": 622288, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.989545464515686, "global_step": 622289, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0237648487091064, "global_step": 622290, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0722086429595947, "global_step": 622291, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.918562412261963, "global_step": 622292, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9202029705047607, "global_step": 622293, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1044905185699463, "global_step": 622294, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.00158953666687, "global_step": 622295, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.043466806411743, "global_step": 622296, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.051861047744751, "global_step": 622297, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9806684255599976, "global_step": 622298, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.046475887298584, "global_step": 622299, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.034527063369751, "global_step": 622300, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9964663982391357, "global_step": 622301, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0907962322235107, "global_step": 622302, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.047145366668701, "global_step": 622303, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9646756649017334, "global_step": 622304, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9940276145935059, "global_step": 622305, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.054647207260132, "global_step": 622306, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9708150625228882, "global_step": 622307, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9766119718551636, "global_step": 622308, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0289385318756104, "global_step": 622309, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9243167638778687, "global_step": 622310, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9741482734680176, "global_step": 622311, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.901031732559204, "global_step": 622312, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0415875911712646, "global_step": 622313, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9940632581710815, "global_step": 622314, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.041621208190918, "global_step": 622315, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.995500922203064, "global_step": 622316, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9905500411987305, "global_step": 622317, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9970877170562744, "global_step": 622318, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.061769962310791, "global_step": 622319, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0541043281555176, "global_step": 622320, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9949493408203125, "global_step": 622321, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0221004486083984, "global_step": 622322, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.024728536605835, "global_step": 622323, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9568493366241455, "global_step": 622324, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0611050128936768, "global_step": 622325, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9714641571044922, "global_step": 622326, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.036067008972168, "global_step": 622327, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.937718152999878, "global_step": 622328, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.05134654045105, "global_step": 622329, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9646621942520142, "global_step": 622330, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9278918504714966, "global_step": 622331, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9588193893432617, "global_step": 622332, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0052878856658936, "global_step": 622333, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.031620979309082, "global_step": 622334, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9569919109344482, "global_step": 622335, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0048677921295166, "global_step": 622336, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.046827793121338, "global_step": 622337, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9999935626983643, "global_step": 622338, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9858523607254028, "global_step": 622339, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1297404766082764, "global_step": 622340, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.046038866043091, "global_step": 622341, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9929814338684082, "global_step": 622342, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0657293796539307, "global_step": 622343, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.015880584716797, "global_step": 622344, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0208380222320557, "global_step": 622345, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.954063892364502, "global_step": 622346, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.958868145942688, "global_step": 622347, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9767181873321533, "global_step": 622348, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9772388935089111, "global_step": 622349, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0265860557556152, "global_step": 622350, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9357960224151611, "global_step": 622351, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.024313449859619, "global_step": 622352, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9595704078674316, "global_step": 622353, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0890705585479736, "global_step": 622354, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.013760566711426, "global_step": 622355, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9574902057647705, "global_step": 622356, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9440890550613403, "global_step": 622357, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0409653186798096, "global_step": 622358, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0297229290008545, "global_step": 622359, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9869868755340576, "global_step": 622360, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9660344123840332, "global_step": 622361, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0433475971221924, "global_step": 622362, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.073735475540161, "global_step": 622363, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.051081418991089, "global_step": 622364, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0048165321350098, "global_step": 622365, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9985588788986206, "global_step": 622366, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9425395727157593, "global_step": 622367, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0015313625335693, "global_step": 622368, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.073821544647217, "global_step": 622369, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.018467664718628, "global_step": 622370, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0538060665130615, "global_step": 622371, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.037432909011841, "global_step": 622372, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.057492256164551, "global_step": 622373, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9398642778396606, "global_step": 622374, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0304362773895264, "global_step": 622375, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9606930017471313, "global_step": 622376, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9173495769500732, "global_step": 622377, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.975138783454895, "global_step": 622378, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.078794240951538, "global_step": 622379, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0039219856262207, "global_step": 622380, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.022581100463867, "global_step": 622381, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.03652286529541, "global_step": 622382, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.023282289505005, "global_step": 622383, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.937586784362793, "global_step": 622384, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.936402678489685, "global_step": 622385, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0451056957244873, "global_step": 622386, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0102105140686035, "global_step": 622387, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0258970260620117, "global_step": 622388, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.035511016845703, "global_step": 622389, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.038482189178467, "global_step": 622390, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9288848638534546, "global_step": 622391, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9553700685501099, "global_step": 622392, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.044721841812134, "global_step": 622393, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.052393913269043, "global_step": 622394, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.097017765045166, "global_step": 622395, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.067789316177368, "global_step": 622396, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.937052607536316, "global_step": 622397, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.041827440261841, "global_step": 622398, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9628442525863647, "global_step": 622399, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0098588466644287, "global_step": 622400, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9631190299987793, "global_step": 622401, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9323011636734009, "global_step": 622402, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0246591567993164, "global_step": 622403, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.95576012134552, "global_step": 622404, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0609898567199707, "global_step": 622405, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0273187160491943, "global_step": 622406, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9511659145355225, "global_step": 622407, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.040172815322876, "global_step": 622408, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9831708669662476, "global_step": 622409, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9782226085662842, "global_step": 622410, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.030890941619873, "global_step": 622411, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.035888671875, "global_step": 622412, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9618580341339111, "global_step": 622413, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.023319959640503, "global_step": 622414, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.048086166381836, "global_step": 622415, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9236372709274292, "global_step": 622416, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0698673725128174, "global_step": 622417, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0754802227020264, "global_step": 622418, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0580813884735107, "global_step": 622419, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9960525035858154, "global_step": 622420, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0323972702026367, "global_step": 622421, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.018235921859741, "global_step": 622422, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.950657844543457, "global_step": 622423, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9985630512237549, "global_step": 622424, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9657179117202759, "global_step": 622425, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.997553825378418, "global_step": 622426, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0406899452209473, "global_step": 622427, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9875482320785522, "global_step": 622428, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9427452087402344, "global_step": 622429, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9850071668624878, "global_step": 622430, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0178160667419434, "global_step": 622431, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.938937783241272, "global_step": 622432, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0693557262420654, "global_step": 622433, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.022599220275879, "global_step": 622434, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9963412284851074, "global_step": 622435, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0312161445617676, "global_step": 622436, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.046872138977051, "global_step": 622437, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9519636631011963, "global_step": 622438, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9157850742340088, "global_step": 622439, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9969117641448975, "global_step": 622440, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.088008165359497, "global_step": 622441, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.985836386680603, "global_step": 622442, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9892573356628418, "global_step": 622443, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.074838161468506, "global_step": 622444, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.02211332321167, "global_step": 622445, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0676074028015137, "global_step": 622446, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9486932754516602, "global_step": 622447, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9803314208984375, "global_step": 622448, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9921588897705078, "global_step": 622449, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0072097778320312, "global_step": 622450, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.061936140060425, "global_step": 622451, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.943174958229065, "global_step": 622452, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0967698097229004, "global_step": 622453, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0118978023529053, "global_step": 622454, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.00068736076355, "global_step": 622455, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0562946796417236, "global_step": 622456, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0211892127990723, "global_step": 622457, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.007819414138794, "global_step": 622458, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.027644395828247, "global_step": 622459, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.970265507698059, "global_step": 622460, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9867908954620361, "global_step": 622461, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.080932855606079, "global_step": 622462, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9777098894119263, "global_step": 622463, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9600082635879517, "global_step": 622464, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.99966561794281, "global_step": 622465, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0059773921966553, "global_step": 622466, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9494094848632812, "global_step": 622467, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9643609523773193, "global_step": 622468, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9531654119491577, "global_step": 622469, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9005186557769775, "global_step": 622470, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0458314418792725, "global_step": 622471, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9863662719726562, "global_step": 622472, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0087502002716064, "global_step": 622473, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.959144115447998, "global_step": 622474, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9762946367263794, "global_step": 622475, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.022709846496582, "global_step": 622476, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.012913703918457, "global_step": 622477, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.031345844268799, "global_step": 622478, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0329785346984863, "global_step": 622479, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9659144878387451, "global_step": 622480, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.946984887123108, "global_step": 622481, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9490138292312622, "global_step": 622482, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.035724639892578, "global_step": 622483, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.961412787437439, "global_step": 622484, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.013753890991211, "global_step": 622485, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0609025955200195, "global_step": 622486, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.045098066329956, "global_step": 622487, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0457398891448975, "global_step": 622488, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9980806112289429, "global_step": 622489, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.07694673538208, "global_step": 622490, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0504159927368164, "global_step": 622491, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9798967838287354, "global_step": 622492, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9272876977920532, "global_step": 622493, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9393447637557983, "global_step": 622494, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0360288619995117, "global_step": 622495, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.01694393157959, "global_step": 622496, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.034844160079956, "global_step": 622497, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.007847309112549, "global_step": 622498, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.104764461517334, "global_step": 622499, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0318236351013184, "global_step": 622500, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.028559446334839, "global_step": 622501, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0325098037719727, "global_step": 622502, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9849029779434204, "global_step": 622503, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.032855749130249, "global_step": 622504, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0504307746887207, "global_step": 622505, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9843629598617554, "global_step": 622506, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9760969877243042, "global_step": 622507, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9665217399597168, "global_step": 622508, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9479657411575317, "global_step": 622509, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9983305931091309, "global_step": 622510, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0471744537353516, "global_step": 622511, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.998927116394043, "global_step": 622512, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0705032348632812, "global_step": 622513, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9473081827163696, "global_step": 622514, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.001890182495117, "global_step": 622515, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0667693614959717, "global_step": 622516, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.978206992149353, "global_step": 622517, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9848040342330933, "global_step": 622518, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9682658910751343, "global_step": 622519, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0245275497436523, "global_step": 622520, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9737129211425781, "global_step": 622521, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1003448963165283, "global_step": 622522, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0022685527801514, "global_step": 622523, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.057281017303467, "global_step": 622524, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9931443929672241, "global_step": 622525, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.082432985305786, "global_step": 622526, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9731663465499878, "global_step": 622527, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0645737648010254, "global_step": 622528, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9822651147842407, "global_step": 622529, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.050950765609741, "global_step": 622530, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0324230194091797, "global_step": 622531, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.002030611038208, "global_step": 622532, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9553555250167847, "global_step": 622533, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0240607261657715, "global_step": 622534, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8907759189605713, "global_step": 622535, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.010861873626709, "global_step": 622536, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9984148740768433, "global_step": 622537, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0507566928863525, "global_step": 622538, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9986119270324707, "global_step": 622539, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.034327983856201, "global_step": 622540, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.97171151638031, "global_step": 622541, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.908313512802124, "global_step": 622542, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0910415649414062, "global_step": 622543, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9993436336517334, "global_step": 622544, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9782896041870117, "global_step": 622545, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0459587574005127, "global_step": 622546, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9731136560440063, "global_step": 622547, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0556743144989014, "global_step": 622548, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0359532833099365, "global_step": 622549, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.057898759841919, "global_step": 622550, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9927235841751099, "global_step": 622551, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0057172775268555, "global_step": 622552, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0735487937927246, "global_step": 622553, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.015897512435913, "global_step": 622554, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0092320442199707, "global_step": 622555, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9998772144317627, "global_step": 622556, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.012457847595215, "global_step": 622557, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9925274848937988, "global_step": 622558, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9929133653640747, "global_step": 622559, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9896762371063232, "global_step": 622560, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0541627407073975, "global_step": 622561, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.024167060852051, "global_step": 622562, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9654825925827026, "global_step": 622563, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9528794288635254, "global_step": 622564, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9941354990005493, "global_step": 622565, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9597492218017578, "global_step": 622566, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9928048849105835, "global_step": 622567, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0192015171051025, "global_step": 622568, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.921501636505127, "global_step": 622569, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.101590633392334, "global_step": 622570, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.976794719696045, "global_step": 622571, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.951502799987793, "global_step": 622572, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9970401525497437, "global_step": 622573, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9767909049987793, "global_step": 622574, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9516726732254028, "global_step": 622575, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.039649724960327, "global_step": 622576, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.01062273979187, "global_step": 622577, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9979029893875122, "global_step": 622578, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9802080392837524, "global_step": 622579, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.995589017868042, "global_step": 622580, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.059513568878174, "global_step": 622581, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1014647483825684, "global_step": 622582, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.065438747406006, "global_step": 622583, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9594470262527466, "global_step": 622584, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.091102123260498, "global_step": 622585, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0859508514404297, "global_step": 622586, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0307583808898926, "global_step": 622587, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0515244007110596, "global_step": 622588, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9541176557540894, "global_step": 622589, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0065455436706543, "global_step": 622590, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.051166296005249, "global_step": 622591, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.056962490081787, "global_step": 622592, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.013031005859375, "global_step": 622593, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0633327960968018, "global_step": 622594, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9852278232574463, "global_step": 622595, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.02402663230896, "global_step": 622596, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9184236526489258, "global_step": 622597, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.998887300491333, "global_step": 622598, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9585410356521606, "global_step": 622599, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0400807857513428, "global_step": 622600, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.027956247329712, "global_step": 622601, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9761786460876465, "global_step": 622602, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9985530376434326, "global_step": 622603, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.938004493713379, "global_step": 622604, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9792675971984863, "global_step": 622605, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.995532512664795, "global_step": 622606, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0195834636688232, "global_step": 622607, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9427968263626099, "global_step": 622608, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.067333698272705, "global_step": 622609, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0737452507019043, "global_step": 622610, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.091520309448242, "global_step": 622611, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.990047812461853, "global_step": 622612, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9875930547714233, "global_step": 622613, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.068849563598633, "global_step": 622614, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.957960844039917, "global_step": 622615, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9613959789276123, "global_step": 622616, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9333839416503906, "global_step": 622617, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9837796688079834, "global_step": 622618, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8890234231948853, "global_step": 622619, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0323140621185303, "global_step": 622620, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9611817598342896, "global_step": 622621, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9891245365142822, "global_step": 622622, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.996666669845581, "global_step": 622623, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0652127265930176, "global_step": 622624, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9884368181228638, "global_step": 622625, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9492017030715942, "global_step": 622626, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.083411931991577, "global_step": 622627, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0131824016571045, "global_step": 622628, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9806365966796875, "global_step": 622629, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0190205574035645, "global_step": 622630, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0681052207946777, "global_step": 622631, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1039884090423584, "global_step": 622632, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9769117832183838, "global_step": 622633, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9539434909820557, "global_step": 622634, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.082935333251953, "global_step": 622635, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9566749334335327, "global_step": 622636, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0515997409820557, "global_step": 622637, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9889614582061768, "global_step": 622638, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9844343662261963, "global_step": 622639, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.069927930831909, "global_step": 622640, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9111381769180298, "global_step": 622641, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9947664737701416, "global_step": 622642, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9998728036880493, "global_step": 622643, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0585525035858154, "global_step": 622644, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9547945261001587, "global_step": 622645, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.040318727493286, "global_step": 622646, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9834635257720947, "global_step": 622647, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9578996896743774, "global_step": 622648, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9576104879379272, "global_step": 622649, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9897249937057495, "global_step": 622650, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0141429901123047, "global_step": 622651, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.054206609725952, "global_step": 622652, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9972045421600342, "global_step": 622653, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0070881843566895, "global_step": 622654, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0017712116241455, "global_step": 622655, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0065431594848633, "global_step": 622656, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.067141056060791, "global_step": 622657, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9769151210784912, "global_step": 622658, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0704243183135986, "global_step": 622659, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0488204956054688, "global_step": 622660, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0326406955718994, "global_step": 622661, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.051297426223755, "global_step": 622662, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9905670881271362, "global_step": 622663, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9386391639709473, "global_step": 622664, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.013813018798828, "global_step": 622665, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0532023906707764, "global_step": 622666, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9822160005569458, "global_step": 622667, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9031860828399658, "global_step": 622668, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9981579780578613, "global_step": 622669, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.020639181137085, "global_step": 622670, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9446638822555542, "global_step": 622671, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0782980918884277, "global_step": 622672, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1255199909210205, "global_step": 622673, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.963867425918579, "global_step": 622674, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.991230845451355, "global_step": 622675, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9929115772247314, "global_step": 622676, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.020503520965576, "global_step": 622677, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.025825023651123, "global_step": 622678, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9212058782577515, "global_step": 622679, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.016787528991699, "global_step": 622680, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.958783745765686, "global_step": 622681, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.054264545440674, "global_step": 622682, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.999096155166626, "global_step": 622683, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9590321779251099, "global_step": 622684, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0705411434173584, "global_step": 622685, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9441787004470825, "global_step": 622686, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0304436683654785, "global_step": 622687, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.020533561706543, "global_step": 622688, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9299718141555786, "global_step": 622689, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9313819408416748, "global_step": 622690, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9860730171203613, "global_step": 622691, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0291805267333984, "global_step": 622692, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0507891178131104, "global_step": 622693, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9667576551437378, "global_step": 622694, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9992055892944336, "global_step": 622695, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9726948738098145, "global_step": 622696, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9443621635437012, "global_step": 622697, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9628841876983643, "global_step": 622698, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9746884107589722, "global_step": 622699, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1061108112335205, "global_step": 622700, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.005936861038208, "global_step": 622701, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9966151714324951, "global_step": 622702, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.981652021408081, "global_step": 622703, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9940013885498047, "global_step": 622704, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0240345001220703, "global_step": 622705, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.030799150466919, "global_step": 622706, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9586635828018188, "global_step": 622707, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.016956090927124, "global_step": 622708, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9586743116378784, "global_step": 622709, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0216145515441895, "global_step": 622710, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9320740699768066, "global_step": 622711, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0051701068878174, "global_step": 622712, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0289084911346436, "global_step": 622713, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9805083274841309, "global_step": 622714, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.997374415397644, "global_step": 622715, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9832136631011963, "global_step": 622716, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9444106817245483, "global_step": 622717, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9971208572387695, "global_step": 622718, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9701036214828491, "global_step": 622719, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9907687902450562, "global_step": 622720, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.074923515319824, "global_step": 622721, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.968650460243225, "global_step": 622722, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0667037963867188, "global_step": 622723, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0646116733551025, "global_step": 622724, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0292956829071045, "global_step": 622725, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0314085483551025, "global_step": 622726, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.001760959625244, "global_step": 622727, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9257556200027466, "global_step": 622728, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9531614780426025, "global_step": 622729, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0247044563293457, "global_step": 622730, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.031665325164795, "global_step": 622731, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.98398756980896, "global_step": 622732, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.984758734703064, "global_step": 622733, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.904676914215088, "global_step": 622734, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8984436988830566, "global_step": 622735, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0319747924804688, "global_step": 622736, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.059189796447754, "global_step": 622737, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.02394962310791, "global_step": 622738, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0621681213378906, "global_step": 622739, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9582668542861938, "global_step": 622740, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0573999881744385, "global_step": 622741, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.033168077468872, "global_step": 622742, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9523506164550781, "global_step": 622743, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9498621225357056, "global_step": 622744, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9973682165145874, "global_step": 622745, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9870178699493408, "global_step": 622746, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.065049409866333, "global_step": 622747, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9464069604873657, "global_step": 622748, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0189666748046875, "global_step": 622749, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9424464702606201, "global_step": 622750, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9881439208984375, "global_step": 622751, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1257669925689697, "global_step": 622752, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.982285976409912, "global_step": 622753, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1094582080841064, "global_step": 622754, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0551209449768066, "global_step": 622755, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.96537446975708, "global_step": 622756, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.916843295097351, "global_step": 622757, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.065161943435669, "global_step": 622758, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0411341190338135, "global_step": 622759, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9915449619293213, "global_step": 622760, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9674532413482666, "global_step": 622761, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.019322633743286, "global_step": 622762, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.988742470741272, "global_step": 622763, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9605034589767456, "global_step": 622764, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9470609426498413, "global_step": 622765, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9243367910385132, "global_step": 622766, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9227615594863892, "global_step": 622767, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0646486282348633, "global_step": 622768, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0500967502593994, "global_step": 622769, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0145583152770996, "global_step": 622770, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9722254276275635, "global_step": 622771, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9928257465362549, "global_step": 622772, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9998172521591187, "global_step": 622773, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9475263357162476, "global_step": 622774, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.991778016090393, "global_step": 622775, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.006779432296753, "global_step": 622776, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.05395245552063, "global_step": 622777, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9380438327789307, "global_step": 622778, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0506937503814697, "global_step": 622779, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.061267614364624, "global_step": 622780, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9810717105865479, "global_step": 622781, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0649662017822266, "global_step": 622782, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.056661605834961, "global_step": 622783, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0236313343048096, "global_step": 622784, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9264252185821533, "global_step": 622785, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9845043420791626, "global_step": 622786, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.994181752204895, "global_step": 622787, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0501582622528076, "global_step": 622788, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.981363296508789, "global_step": 622789, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.083622694015503, "global_step": 622790, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.022913932800293, "global_step": 622791, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.058431625366211, "global_step": 622792, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9994524717330933, "global_step": 622793, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9883588552474976, "global_step": 622794, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.101752519607544, "global_step": 622795, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.093782424926758, "global_step": 622796, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9166028499603271, "global_step": 622797, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9510419368743896, "global_step": 622798, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9650410413742065, "global_step": 622799, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9329373836517334, "global_step": 622800, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9577497243881226, "global_step": 622801, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.036438465118408, "global_step": 622802, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.02744722366333, "global_step": 622803, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9738967418670654, "global_step": 622804, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9779771566390991, "global_step": 622805, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0620510578155518, "global_step": 622806, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0350890159606934, "global_step": 622807, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.017124891281128, "global_step": 622808, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.053088665008545, "global_step": 622809, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0933713912963867, "global_step": 622810, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9544051885604858, "global_step": 622811, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.066478729248047, "global_step": 622812, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0965113639831543, "global_step": 622813, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9916571378707886, "global_step": 622814, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0172886848449707, "global_step": 622815, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0384726524353027, "global_step": 622816, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0440030097961426, "global_step": 622817, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.045264720916748, "global_step": 622818, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.07778263092041, "global_step": 622819, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9906094074249268, "global_step": 622820, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0665013790130615, "global_step": 622821, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9936575889587402, "global_step": 622822, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9985285997390747, "global_step": 622823, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9602466821670532, "global_step": 622824, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9929734468460083, "global_step": 622825, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0041096210479736, "global_step": 622826, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.001002550125122, "global_step": 622827, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.993337869644165, "global_step": 622828, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9712233543395996, "global_step": 622829, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0636110305786133, "global_step": 622830, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9878532886505127, "global_step": 622831, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9657477140426636, "global_step": 622832, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.017953395843506, "global_step": 622833, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9567447900772095, "global_step": 622834, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.95125150680542, "global_step": 622835, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9477020502090454, "global_step": 622836, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0470032691955566, "global_step": 622837, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9577274322509766, "global_step": 622838, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0437686443328857, "global_step": 622839, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.065408229827881, "global_step": 622840, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9975990056991577, "global_step": 622841, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9918886423110962, "global_step": 622842, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.01350474357605, "global_step": 622843, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9837092161178589, "global_step": 622844, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.036550760269165, "global_step": 622845, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.982985258102417, "global_step": 622846, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9923068284988403, "global_step": 622847, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9222220182418823, "global_step": 622848, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.912961483001709, "global_step": 622849, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.019817352294922, "global_step": 622850, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9969393014907837, "global_step": 622851, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9711493253707886, "global_step": 622852, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0096263885498047, "global_step": 622853, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.037203311920166, "global_step": 622854, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.970940351486206, "global_step": 622855, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.96364164352417, "global_step": 622856, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0526676177978516, "global_step": 622857, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.015713930130005, "global_step": 622858, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0228450298309326, "global_step": 622859, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0387187004089355, "global_step": 622860, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9945813417434692, "global_step": 622861, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0229649543762207, "global_step": 622862, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9519141912460327, "global_step": 622863, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0507864952087402, "global_step": 622864, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9555015563964844, "global_step": 622865, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0370967388153076, "global_step": 622866, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.102842092514038, "global_step": 622867, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9774689674377441, "global_step": 622868, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0540096759796143, "global_step": 622869, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.019536018371582, "global_step": 622870, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0592525005340576, "global_step": 622871, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9198938608169556, "global_step": 622872, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0689308643341064, "global_step": 622873, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9809889793395996, "global_step": 622874, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9619148969650269, "global_step": 622875, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0325403213500977, "global_step": 622876, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9406111240386963, "global_step": 622877, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.068168878555298, "global_step": 622878, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9941827058792114, "global_step": 622879, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.037302255630493, "global_step": 622880, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.001319169998169, "global_step": 622881, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0642905235290527, "global_step": 622882, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0188169479370117, "global_step": 622883, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9310067892074585, "global_step": 622884, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9545724391937256, "global_step": 622885, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.054008722305298, "global_step": 622886, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.066145658493042, "global_step": 622887, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.957883358001709, "global_step": 622888, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0320279598236084, "global_step": 622889, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9554654359817505, "global_step": 622890, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0265235900878906, "global_step": 622891, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9229214191436768, "global_step": 622892, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9661433696746826, "global_step": 622893, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.01328706741333, "global_step": 622894, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0080227851867676, "global_step": 622895, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.08650803565979, "global_step": 622896, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0621306896209717, "global_step": 622897, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0108554363250732, "global_step": 622898, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.031703472137451, "global_step": 622899, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1636805534362793, "global_step": 622900, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.133005380630493, "global_step": 622901, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.038987874984741, "global_step": 622902, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0149669647216797, "global_step": 622903, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.014106273651123, "global_step": 622904, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8879084587097168, "global_step": 622905, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.985249638557434, "global_step": 622906, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0613648891448975, "global_step": 622907, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.965092420578003, "global_step": 622908, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0071496963500977, "global_step": 622909, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.041985034942627, "global_step": 622910, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9249348640441895, "global_step": 622911, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.972181797027588, "global_step": 622912, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.087549924850464, "global_step": 622913, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9931584596633911, "global_step": 622914, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.004244327545166, "global_step": 622915, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9868088960647583, "global_step": 622916, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0149645805358887, "global_step": 622917, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.000169515609741, "global_step": 622918, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9907174110412598, "global_step": 622919, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9947293996810913, "global_step": 622920, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9758784770965576, "global_step": 622921, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.031175374984741, "global_step": 622922, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9697779417037964, "global_step": 622923, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.877042531967163, "global_step": 622924, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.056345224380493, "global_step": 622925, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9777846336364746, "global_step": 622926, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.011821985244751, "global_step": 622927, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.926133394241333, "global_step": 622928, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.016209602355957, "global_step": 622929, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0178802013397217, "global_step": 622930, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.024644613265991, "global_step": 622931, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9468166828155518, "global_step": 622932, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.003972053527832, "global_step": 622933, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9229466915130615, "global_step": 622934, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9703562259674072, "global_step": 622935, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0481326580047607, "global_step": 622936, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9603697061538696, "global_step": 622937, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9447659254074097, "global_step": 622938, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0170788764953613, "global_step": 622939, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9666035175323486, "global_step": 622940, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9805817604064941, "global_step": 622941, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.094816207885742, "global_step": 622942, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9996424913406372, "global_step": 622943, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0315394401550293, "global_step": 622944, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.04559326171875, "global_step": 622945, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9719974994659424, "global_step": 622946, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0177419185638428, "global_step": 622947, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.023684024810791, "global_step": 622948, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.99339759349823, "global_step": 622949, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.000910997390747, "global_step": 622950, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9960801601409912, "global_step": 622951, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9604789018630981, "global_step": 622952, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8632582426071167, "global_step": 622953, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9688386917114258, "global_step": 622954, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9939519166946411, "global_step": 622955, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9686278104782104, "global_step": 622956, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9592366218566895, "global_step": 622957, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0077500343322754, "global_step": 622958, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0836868286132812, "global_step": 622959, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9156721830368042, "global_step": 622960, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0756449699401855, "global_step": 622961, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9642995595932007, "global_step": 622962, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9534618854522705, "global_step": 622963, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.000704050064087, "global_step": 622964, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9373196363449097, "global_step": 622965, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0164942741394043, "global_step": 622966, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0975875854492188, "global_step": 622967, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0255463123321533, "global_step": 622968, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.075859546661377, "global_step": 622969, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9812164306640625, "global_step": 622970, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9989478588104248, "global_step": 622971, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.019232988357544, "global_step": 622972, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.955047369003296, "global_step": 622973, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0676541328430176, "global_step": 622974, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.026606321334839, "global_step": 622975, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8990343809127808, "global_step": 622976, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0581915378570557, "global_step": 622977, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.961538553237915, "global_step": 622978, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0389461517333984, "global_step": 622979, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.941554069519043, "global_step": 622980, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9929454326629639, "global_step": 622981, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9952102899551392, "global_step": 622982, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0355494022369385, "global_step": 622983, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.054790735244751, "global_step": 622984, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9524587392807007, "global_step": 622985, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.018134117126465, "global_step": 622986, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9953192472457886, "global_step": 622987, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0687267780303955, "global_step": 622988, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0156078338623047, "global_step": 622989, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9954872131347656, "global_step": 622990, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0288007259368896, "global_step": 622991, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.026339054107666, "global_step": 622992, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.92434561252594, "global_step": 622993, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.053311347961426, "global_step": 622994, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0352015495300293, "global_step": 622995, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0181689262390137, "global_step": 622996, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.036452531814575, "global_step": 622997, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0048561096191406, "global_step": 622998, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9957269430160522, "global_step": 622999, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0292747020721436, "global_step": 623000, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0223844051361084, "global_step": 623001, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.031104564666748, "global_step": 623002, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.012749671936035, "global_step": 623003, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9572439193725586, "global_step": 623004, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9758135080337524, "global_step": 623005, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0155696868896484, "global_step": 623006, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.12174391746521, "global_step": 623007, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.975868821144104, "global_step": 623008, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9807496070861816, "global_step": 623009, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.072758197784424, "global_step": 623010, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1087679862976074, "global_step": 623011, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.966691255569458, "global_step": 623012, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.112501621246338, "global_step": 623013, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0181617736816406, "global_step": 623014, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9576021432876587, "global_step": 623015, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0025575160980225, "global_step": 623016, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0089635848999023, "global_step": 623017, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8986225128173828, "global_step": 623018, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0523908138275146, "global_step": 623019, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9920750856399536, "global_step": 623020, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0403852462768555, "global_step": 623021, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0338823795318604, "global_step": 623022, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9846636056900024, "global_step": 623023, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.019779920578003, "global_step": 623024, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0208985805511475, "global_step": 623025, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0376522541046143, "global_step": 623026, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0672008991241455, "global_step": 623027, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9266585111618042, "global_step": 623028, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.006537914276123, "global_step": 623029, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0204031467437744, "global_step": 623030, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0154781341552734, "global_step": 623031, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.041109561920166, "global_step": 623032, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0062613487243652, "global_step": 623033, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.973280906677246, "global_step": 623034, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9991825819015503, "global_step": 623035, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0256807804107666, "global_step": 623036, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9676320552825928, "global_step": 623037, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9961133003234863, "global_step": 623038, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.004279613494873, "global_step": 623039, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9928096532821655, "global_step": 623040, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9617722034454346, "global_step": 623041, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.115595579147339, "global_step": 623042, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9720946550369263, "global_step": 623043, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0156567096710205, "global_step": 623044, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.015467882156372, "global_step": 623045, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.988588809967041, "global_step": 623046, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.033768892288208, "global_step": 623047, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.059624433517456, "global_step": 623048, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.015047550201416, "global_step": 623049, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.040543556213379, "global_step": 623050, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.007941246032715, "global_step": 623051, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.021458148956299, "global_step": 623052, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.023576498031616, "global_step": 623053, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.008474826812744, "global_step": 623054, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9398655891418457, "global_step": 623055, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9282411336898804, "global_step": 623056, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.982546091079712, "global_step": 623057, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9582383632659912, "global_step": 623058, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9516304731369019, "global_step": 623059, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.075831651687622, "global_step": 623060, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9663445949554443, "global_step": 623061, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.989362359046936, "global_step": 623062, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9879744052886963, "global_step": 623063, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9503662586212158, "global_step": 623064, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9841952323913574, "global_step": 623065, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.949723482131958, "global_step": 623066, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.999898910522461, "global_step": 623067, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9341661930084229, "global_step": 623068, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0233380794525146, "global_step": 623069, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0626373291015625, "global_step": 623070, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0096490383148193, "global_step": 623071, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9928522109985352, "global_step": 623072, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9876773357391357, "global_step": 623073, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0899641513824463, "global_step": 623074, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.038581371307373, "global_step": 623075, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9800584316253662, "global_step": 623076, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.023407459259033, "global_step": 623077, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9152913093566895, "global_step": 623078, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.969681739807129, "global_step": 623079, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9456701278686523, "global_step": 623080, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0304348468780518, "global_step": 623081, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0273306369781494, "global_step": 623082, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.002511501312256, "global_step": 623083, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0157196521759033, "global_step": 623084, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9832193851470947, "global_step": 623085, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.070167303085327, "global_step": 623086, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9483035802841187, "global_step": 623087, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9667097330093384, "global_step": 623088, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0312745571136475, "global_step": 623089, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0530548095703125, "global_step": 623090, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9589511156082153, "global_step": 623091, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1045122146606445, "global_step": 623092, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.007126569747925, "global_step": 623093, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.010204553604126, "global_step": 623094, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9614349603652954, "global_step": 623095, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9291270971298218, "global_step": 623096, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.007232904434204, "global_step": 623097, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9499088525772095, "global_step": 623098, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.097050189971924, "global_step": 623099, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0172176361083984, "global_step": 623100, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.970706582069397, "global_step": 623101, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.999864101409912, "global_step": 623102, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.057260751724243, "global_step": 623103, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0097296237945557, "global_step": 623104, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.968849778175354, "global_step": 623105, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0272159576416016, "global_step": 623106, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9997222423553467, "global_step": 623107, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0821597576141357, "global_step": 623108, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9421378374099731, "global_step": 623109, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.027923583984375, "global_step": 623110, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9157065153121948, "global_step": 623111, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.923050880432129, "global_step": 623112, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9995570182800293, "global_step": 623113, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0299627780914307, "global_step": 623114, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0033364295959473, "global_step": 623115, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.925705909729004, "global_step": 623116, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0167787075042725, "global_step": 623117, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.074394702911377, "global_step": 623118, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0772390365600586, "global_step": 623119, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9992666244506836, "global_step": 623120, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0446200370788574, "global_step": 623121, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9299250841140747, "global_step": 623122, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9902846813201904, "global_step": 623123, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0352284908294678, "global_step": 623124, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9426130056381226, "global_step": 623125, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0628607273101807, "global_step": 623126, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9399446249008179, "global_step": 623127, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0046768188476562, "global_step": 623128, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0046799182891846, "global_step": 623129, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.080247640609741, "global_step": 623130, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.994706153869629, "global_step": 623131, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0380566120147705, "global_step": 623132, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9239914417266846, "global_step": 623133, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0548908710479736, "global_step": 623134, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9917168617248535, "global_step": 623135, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9446648359298706, "global_step": 623136, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9868935346603394, "global_step": 623137, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0456430912017822, "global_step": 623138, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0517055988311768, "global_step": 623139, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.977019190788269, "global_step": 623140, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0608808994293213, "global_step": 623141, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0340449810028076, "global_step": 623142, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0206384658813477, "global_step": 623143, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9888466596603394, "global_step": 623144, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0275261402130127, "global_step": 623145, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9684032201766968, "global_step": 623146, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9882005453109741, "global_step": 623147, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.010812997817993, "global_step": 623148, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9985156059265137, "global_step": 623149, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9662208557128906, "global_step": 623150, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0054826736450195, "global_step": 623151, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0650830268859863, "global_step": 623152, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.000108003616333, "global_step": 623153, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0087950229644775, "global_step": 623154, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9412288665771484, "global_step": 623155, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9595677852630615, "global_step": 623156, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9689545631408691, "global_step": 623157, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9374501705169678, "global_step": 623158, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9830760955810547, "global_step": 623159, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.030689239501953, "global_step": 623160, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0671019554138184, "global_step": 623161, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0254099369049072, "global_step": 623162, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.002268075942993, "global_step": 623163, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.089470148086548, "global_step": 623164, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.027982234954834, "global_step": 623165, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.1063990592956543, "global_step": 623166, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.063845634460449, "global_step": 623167, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9624202251434326, "global_step": 623168, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0237715244293213, "global_step": 623169, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9711414575576782, "global_step": 623170, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.066974639892578, "global_step": 623171, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.987951636314392, "global_step": 623172, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0229430198669434, "global_step": 623173, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9846845865249634, "global_step": 623174, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9985638856887817, "global_step": 623175, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.978453516960144, "global_step": 623176, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.004894733428955, "global_step": 623177, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9701199531555176, "global_step": 623178, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9645915031433105, "global_step": 623179, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0214662551879883, "global_step": 623180, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9865916967391968, "global_step": 623181, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.053356409072876, "global_step": 623182, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0047829151153564, "global_step": 623183, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9524421691894531, "global_step": 623184, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9504693746566772, "global_step": 623185, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0013504028320312, "global_step": 623186, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0943210124969482, "global_step": 623187, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0269100666046143, "global_step": 623188, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.048307180404663, "global_step": 623189, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.15769624710083, "global_step": 623190, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.036371946334839, "global_step": 623191, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.8908488750457764, "global_step": 623192, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.986752986907959, "global_step": 623193, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0454018115997314, "global_step": 623194, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0061469078063965, "global_step": 623195, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.0462329387664795, "global_step": 623196, "epoch": 991, "lr": 5e-05}
{"train_loss": 1.9955148696899414, "global_step": 623197, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.003986120223999, "global_step": 623198, "epoch": 991, "lr": 5e-05}
{"train_loss": 2.033257246017456, "global_step": 623199, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9445148706436157, "global_step": 623200, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9701712131500244, "global_step": 623201, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.00964093208313, "global_step": 623202, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9434796571731567, "global_step": 623203, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9507689476013184, "global_step": 623204, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9937238693237305, "global_step": 623205, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9129189252853394, "global_step": 623206, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9634889364242554, "global_step": 623207, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.938124179840088, "global_step": 623208, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.929231882095337, "global_step": 623209, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0313408374786377, "global_step": 623210, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0261037349700928, "global_step": 623211, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.971779465675354, "global_step": 623212, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.990465521812439, "global_step": 623213, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0352084636688232, "global_step": 623214, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9367812871932983, "global_step": 623215, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9428379535675049, "global_step": 623216, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.058180332183838, "global_step": 623217, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0102598667144775, "global_step": 623218, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0347414016723633, "global_step": 623219, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0236129760742188, "global_step": 623220, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.070009231567383, "global_step": 623221, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.003054618835449, "global_step": 623222, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.030611038208008, "global_step": 623223, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9891374111175537, "global_step": 623224, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9885691404342651, "global_step": 623225, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9845486879348755, "global_step": 623226, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9639267921447754, "global_step": 623227, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.027182102203369, "global_step": 623228, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9315154552459717, "global_step": 623229, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0043468475341797, "global_step": 623230, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0099294185638428, "global_step": 623231, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.051772356033325, "global_step": 623232, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9375572204589844, "global_step": 623233, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0347671508789062, "global_step": 623234, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9395703077316284, "global_step": 623235, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.050798177719116, "global_step": 623236, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9854036569595337, "global_step": 623237, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9664368629455566, "global_step": 623238, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9288583993911743, "global_step": 623239, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9763801097869873, "global_step": 623240, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0584540367126465, "global_step": 623241, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0466561317443848, "global_step": 623242, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9051475524902344, "global_step": 623243, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9798945188522339, "global_step": 623244, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.995236873626709, "global_step": 623245, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.056366443634033, "global_step": 623246, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9847207069396973, "global_step": 623247, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.934662103652954, "global_step": 623248, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0497772693634033, "global_step": 623249, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.936931848526001, "global_step": 623250, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.033586025238037, "global_step": 623251, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.009796619415283, "global_step": 623252, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0558202266693115, "global_step": 623253, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.931139349937439, "global_step": 623254, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9318957328796387, "global_step": 623255, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.005267381668091, "global_step": 623256, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9397224187850952, "global_step": 623257, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9613584280014038, "global_step": 623258, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9912595748901367, "global_step": 623259, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.927965760231018, "global_step": 623260, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9168850183486938, "global_step": 623261, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.001434087753296, "global_step": 623262, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9397494792938232, "global_step": 623263, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9794546365737915, "global_step": 623264, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9736100435256958, "global_step": 623265, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9993075132369995, "global_step": 623266, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0800442695617676, "global_step": 623267, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.024399518966675, "global_step": 623268, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9827806949615479, "global_step": 623269, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.921156406402588, "global_step": 623270, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9821137189865112, "global_step": 623271, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9932467937469482, "global_step": 623272, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.051508665084839, "global_step": 623273, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.006289482116699, "global_step": 623274, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.088576555252075, "global_step": 623275, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9804213047027588, "global_step": 623276, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.022514581680298, "global_step": 623277, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9666354656219482, "global_step": 623278, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0619964599609375, "global_step": 623279, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0306684970855713, "global_step": 623280, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9404150247573853, "global_step": 623281, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1251168251037598, "global_step": 623282, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9561811685562134, "global_step": 623283, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9874179363250732, "global_step": 623284, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0358755588531494, "global_step": 623285, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9168232679367065, "global_step": 623286, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9988093376159668, "global_step": 623287, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9518001079559326, "global_step": 623288, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9539490938186646, "global_step": 623289, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9242607355117798, "global_step": 623290, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9973461627960205, "global_step": 623291, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9928652048110962, "global_step": 623292, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9519906044006348, "global_step": 623293, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.006895065307617, "global_step": 623294, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9524352550506592, "global_step": 623295, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.044847011566162, "global_step": 623296, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9616281986236572, "global_step": 623297, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0105772018432617, "global_step": 623298, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.078831672668457, "global_step": 623299, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.931691288948059, "global_step": 623300, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9680464267730713, "global_step": 623301, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0155692100524902, "global_step": 623302, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.114116907119751, "global_step": 623303, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9594178199768066, "global_step": 623304, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.8999496698379517, "global_step": 623305, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.002687454223633, "global_step": 623306, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0066959857940674, "global_step": 623307, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0357513427734375, "global_step": 623308, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0064291954040527, "global_step": 623309, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9936368465423584, "global_step": 623310, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9908947944641113, "global_step": 623311, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9276763200759888, "global_step": 623312, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9777107238769531, "global_step": 623313, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9875669479370117, "global_step": 623314, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.060082197189331, "global_step": 623315, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0318667888641357, "global_step": 623316, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0902647972106934, "global_step": 623317, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9924017190933228, "global_step": 623318, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9880813360214233, "global_step": 623319, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9374816417694092, "global_step": 623320, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.8801746368408203, "global_step": 623321, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.984951138496399, "global_step": 623322, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9930592775344849, "global_step": 623323, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0273983478546143, "global_step": 623324, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9868817329406738, "global_step": 623325, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9438579082489014, "global_step": 623326, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9966461658477783, "global_step": 623327, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0106706619262695, "global_step": 623328, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9307986497879028, "global_step": 623329, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0350658893585205, "global_step": 623330, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9618890285491943, "global_step": 623331, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9648725986480713, "global_step": 623332, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0068583488464355, "global_step": 623333, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0271551609039307, "global_step": 623334, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9983255863189697, "global_step": 623335, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0513901710510254, "global_step": 623336, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9653620719909668, "global_step": 623337, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.046036958694458, "global_step": 623338, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9106764793395996, "global_step": 623339, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0722875595092773, "global_step": 623340, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.009061813354492, "global_step": 623341, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9611738920211792, "global_step": 623342, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0420713424682617, "global_step": 623343, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9328142404556274, "global_step": 623344, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.016774892807007, "global_step": 623345, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.017183780670166, "global_step": 623346, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9926223754882812, "global_step": 623347, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0223326683044434, "global_step": 623348, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9808003902435303, "global_step": 623349, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.017911434173584, "global_step": 623350, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.945046067237854, "global_step": 623351, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9994747638702393, "global_step": 623352, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.015986442565918, "global_step": 623353, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.000908136367798, "global_step": 623354, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.017390251159668, "global_step": 623355, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9405819177627563, "global_step": 623356, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9674580097198486, "global_step": 623357, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9697438478469849, "global_step": 623358, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9763683080673218, "global_step": 623359, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.058180809020996, "global_step": 623360, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9576640129089355, "global_step": 623361, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9994769096374512, "global_step": 623362, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9385255575180054, "global_step": 623363, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0011374950408936, "global_step": 623364, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9798691272735596, "global_step": 623365, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.941105842590332, "global_step": 623366, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9449738264083862, "global_step": 623367, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.999549150466919, "global_step": 623368, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9882838726043701, "global_step": 623369, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.049553155899048, "global_step": 623370, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.961785912513733, "global_step": 623371, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0276060104370117, "global_step": 623372, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9865244626998901, "global_step": 623373, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9599273204803467, "global_step": 623374, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.067131757736206, "global_step": 623375, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.00835919380188, "global_step": 623376, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.916380763053894, "global_step": 623377, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0651962757110596, "global_step": 623378, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9697402715682983, "global_step": 623379, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0560121536254883, "global_step": 623380, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9982715845108032, "global_step": 623381, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.028632640838623, "global_step": 623382, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0012314319610596, "global_step": 623383, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.912010908126831, "global_step": 623384, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9968870878219604, "global_step": 623385, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.947245478630066, "global_step": 623386, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0616543292999268, "global_step": 623387, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.943184733390808, "global_step": 623388, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.021739959716797, "global_step": 623389, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.925182819366455, "global_step": 623390, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.006007194519043, "global_step": 623391, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9638421535491943, "global_step": 623392, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9155700206756592, "global_step": 623393, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.004136323928833, "global_step": 623394, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9026983976364136, "global_step": 623395, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0208182334899902, "global_step": 623396, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.946852684020996, "global_step": 623397, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0208678245544434, "global_step": 623398, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.058243989944458, "global_step": 623399, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.090885639190674, "global_step": 623400, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.065298557281494, "global_step": 623401, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.029352903366089, "global_step": 623402, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0265097618103027, "global_step": 623403, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0130484104156494, "global_step": 623404, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0119001865386963, "global_step": 623405, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0033912658691406, "global_step": 623406, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0168163776397705, "global_step": 623407, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9334259033203125, "global_step": 623408, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.022136688232422, "global_step": 623409, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0314865112304688, "global_step": 623410, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0029783248901367, "global_step": 623411, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9731193780899048, "global_step": 623412, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9822196960449219, "global_step": 623413, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9493707418441772, "global_step": 623414, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.043888568878174, "global_step": 623415, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9923005104064941, "global_step": 623416, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.953839659690857, "global_step": 623417, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0084586143493652, "global_step": 623418, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0016989707946777, "global_step": 623419, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.111727476119995, "global_step": 623420, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0481350421905518, "global_step": 623421, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0346198081970215, "global_step": 623422, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9853389263153076, "global_step": 623423, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.001838207244873, "global_step": 623424, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9337098598480225, "global_step": 623425, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.891969919204712, "global_step": 623426, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9935574531555176, "global_step": 623427, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0386862754821777, "global_step": 623428, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.998337745666504, "global_step": 623429, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.062978982925415, "global_step": 623430, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0082874298095703, "global_step": 623431, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.005319118499756, "global_step": 623432, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9285361766815186, "global_step": 623433, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0380496978759766, "global_step": 623434, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0025007724761963, "global_step": 623435, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0199358463287354, "global_step": 623436, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0069642066955566, "global_step": 623437, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.022254705429077, "global_step": 623438, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0010464191436768, "global_step": 623439, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.00687837600708, "global_step": 623440, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9375048875808716, "global_step": 623441, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0429446697235107, "global_step": 623442, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0925140380859375, "global_step": 623443, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9935060739517212, "global_step": 623444, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9354968070983887, "global_step": 623445, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.045565128326416, "global_step": 623446, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.057539939880371, "global_step": 623447, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0081698894500732, "global_step": 623448, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.035440444946289, "global_step": 623449, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.092233657836914, "global_step": 623450, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.872175931930542, "global_step": 623451, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.10616397857666, "global_step": 623452, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9381762742996216, "global_step": 623453, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0288407802581787, "global_step": 623454, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.962275743484497, "global_step": 623455, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.023528575897217, "global_step": 623456, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.036712169647217, "global_step": 623457, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9349024295806885, "global_step": 623458, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9611163139343262, "global_step": 623459, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.043517827987671, "global_step": 623460, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.122126817703247, "global_step": 623461, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9522361755371094, "global_step": 623462, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.05855131149292, "global_step": 623463, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9660942554473877, "global_step": 623464, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.954525351524353, "global_step": 623465, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.936166763305664, "global_step": 623466, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0074191093444824, "global_step": 623467, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9918948411941528, "global_step": 623468, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.989702582359314, "global_step": 623469, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.951999545097351, "global_step": 623470, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0519933700561523, "global_step": 623471, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.111402750015259, "global_step": 623472, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0624327659606934, "global_step": 623473, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9207268953323364, "global_step": 623474, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9956231117248535, "global_step": 623475, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9970753192901611, "global_step": 623476, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0910980701446533, "global_step": 623477, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.996704339981079, "global_step": 623478, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.989130973815918, "global_step": 623479, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1076364517211914, "global_step": 623480, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.896007776260376, "global_step": 623481, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0067460536956787, "global_step": 623482, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0169870853424072, "global_step": 623483, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.143160820007324, "global_step": 623484, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.015019416809082, "global_step": 623485, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9618691205978394, "global_step": 623486, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9301726818084717, "global_step": 623487, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.947203516960144, "global_step": 623488, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.075369358062744, "global_step": 623489, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.955039143562317, "global_step": 623490, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0513429641723633, "global_step": 623491, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9877468347549438, "global_step": 623492, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.8988237380981445, "global_step": 623493, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0294265747070312, "global_step": 623494, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9968986511230469, "global_step": 623495, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9758790731430054, "global_step": 623496, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9770563840866089, "global_step": 623497, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.06705641746521, "global_step": 623498, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9490373134613037, "global_step": 623499, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.021784782409668, "global_step": 623500, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9265943765640259, "global_step": 623501, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9961981773376465, "global_step": 623502, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0170772075653076, "global_step": 623503, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0522420406341553, "global_step": 623504, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.980771780014038, "global_step": 623505, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.032989263534546, "global_step": 623506, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0239553451538086, "global_step": 623507, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.975711464881897, "global_step": 623508, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9784516096115112, "global_step": 623509, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9706369638442993, "global_step": 623510, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.970760464668274, "global_step": 623511, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0013177394866943, "global_step": 623512, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9428033828735352, "global_step": 623513, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0383143424987793, "global_step": 623514, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.069753885269165, "global_step": 623515, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.017456293106079, "global_step": 623516, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0236215591430664, "global_step": 623517, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9820060729980469, "global_step": 623518, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.005406618118286, "global_step": 623519, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0317282676696777, "global_step": 623520, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.933480143547058, "global_step": 623521, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.047427177429199, "global_step": 623522, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0057122707366943, "global_step": 623523, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9119114875793457, "global_step": 623524, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9706413745880127, "global_step": 623525, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9560095071792603, "global_step": 623526, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9765939712524414, "global_step": 623527, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9994598627090454, "global_step": 623528, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9470328092575073, "global_step": 623529, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0754339694976807, "global_step": 623530, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0318846702575684, "global_step": 623531, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9390215873718262, "global_step": 623532, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0175933837890625, "global_step": 623533, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0214414596557617, "global_step": 623534, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.935155987739563, "global_step": 623535, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0258712768554688, "global_step": 623536, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.022582769393921, "global_step": 623537, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.141249895095825, "global_step": 623538, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9313753843307495, "global_step": 623539, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9561213254928589, "global_step": 623540, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.016723871231079, "global_step": 623541, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.039407730102539, "global_step": 623542, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9727598428726196, "global_step": 623543, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.008507490158081, "global_step": 623544, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0001637935638428, "global_step": 623545, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0103766918182373, "global_step": 623546, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0487139225006104, "global_step": 623547, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0605990886688232, "global_step": 623548, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9743890762329102, "global_step": 623549, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.018141031265259, "global_step": 623550, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0016589164733887, "global_step": 623551, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0776796340942383, "global_step": 623552, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9690754413604736, "global_step": 623553, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9877811670303345, "global_step": 623554, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0574119091033936, "global_step": 623555, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9693562984466553, "global_step": 623556, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.030351161956787, "global_step": 623557, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0556423664093018, "global_step": 623558, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9598760604858398, "global_step": 623559, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9696266651153564, "global_step": 623560, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9859641790390015, "global_step": 623561, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9746372699737549, "global_step": 623562, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9198994636535645, "global_step": 623563, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9421820640563965, "global_step": 623564, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.026743173599243, "global_step": 623565, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0666427612304688, "global_step": 623566, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0554075241088867, "global_step": 623567, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0487475395202637, "global_step": 623568, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9639531373977661, "global_step": 623569, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0041980743408203, "global_step": 623570, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0477209091186523, "global_step": 623571, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9445098638534546, "global_step": 623572, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9890273809432983, "global_step": 623573, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.918552041053772, "global_step": 623574, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0414905548095703, "global_step": 623575, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.022764205932617, "global_step": 623576, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.086672067642212, "global_step": 623577, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9666433334350586, "global_step": 623578, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9761050939559937, "global_step": 623579, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0080063343048096, "global_step": 623580, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.918715476989746, "global_step": 623581, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.014897108078003, "global_step": 623582, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.986595630645752, "global_step": 623583, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0266544818878174, "global_step": 623584, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9866610765457153, "global_step": 623585, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9413214921951294, "global_step": 623586, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0362823009490967, "global_step": 623587, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.102696180343628, "global_step": 623588, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0552165508270264, "global_step": 623589, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0092103481292725, "global_step": 623590, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0760269165039062, "global_step": 623591, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.995068073272705, "global_step": 623592, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0252957344055176, "global_step": 623593, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9745365381240845, "global_step": 623594, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.026308059692383, "global_step": 623595, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0939652919769287, "global_step": 623596, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9240126609802246, "global_step": 623597, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9152692556381226, "global_step": 623598, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9032704830169678, "global_step": 623599, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9967302083969116, "global_step": 623600, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9870003461837769, "global_step": 623601, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.030923843383789, "global_step": 623602, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0139429569244385, "global_step": 623603, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9550683498382568, "global_step": 623604, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.911058783531189, "global_step": 623605, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0665290355682373, "global_step": 623606, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0218684673309326, "global_step": 623607, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9730457067489624, "global_step": 623608, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9476755857467651, "global_step": 623609, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0299601554870605, "global_step": 623610, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.146857500076294, "global_step": 623611, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9876457452774048, "global_step": 623612, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9581403732299805, "global_step": 623613, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9810230731964111, "global_step": 623614, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0188040733337402, "global_step": 623615, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0155577659606934, "global_step": 623616, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0263824462890625, "global_step": 623617, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9805279970169067, "global_step": 623618, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0129971504211426, "global_step": 623619, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9726874828338623, "global_step": 623620, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9668805599212646, "global_step": 623621, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.015244960784912, "global_step": 623622, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0282695293426514, "global_step": 623623, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0405943393707275, "global_step": 623624, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.938939094543457, "global_step": 623625, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.023799180984497, "global_step": 623626, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0185484886169434, "global_step": 623627, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9937093257904053, "global_step": 623628, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.998258113861084, "global_step": 623629, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0239057540893555, "global_step": 623630, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9259953498840332, "global_step": 623631, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0096561908721924, "global_step": 623632, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.938050627708435, "global_step": 623633, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.059399127960205, "global_step": 623634, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9927198886871338, "global_step": 623635, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0739431381225586, "global_step": 623636, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.004122018814087, "global_step": 623637, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0253758430480957, "global_step": 623638, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0893473625183105, "global_step": 623639, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9795002937316895, "global_step": 623640, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0656211376190186, "global_step": 623641, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.993350863456726, "global_step": 623642, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0066211223602295, "global_step": 623643, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.020075798034668, "global_step": 623644, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0026917457580566, "global_step": 623645, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0763938426971436, "global_step": 623646, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9740383625030518, "global_step": 623647, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.034752368927002, "global_step": 623648, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.998819351196289, "global_step": 623649, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.040093421936035, "global_step": 623650, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.079742670059204, "global_step": 623651, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.93082857131958, "global_step": 623652, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.914607286453247, "global_step": 623653, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9700533151626587, "global_step": 623654, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.023742437362671, "global_step": 623655, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0548784732818604, "global_step": 623656, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9433060884475708, "global_step": 623657, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0754809379577637, "global_step": 623658, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0235965251922607, "global_step": 623659, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0087668895721436, "global_step": 623660, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9780428409576416, "global_step": 623661, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9472877979278564, "global_step": 623662, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.012014627456665, "global_step": 623663, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0637457370758057, "global_step": 623664, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.974198818206787, "global_step": 623665, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9983330965042114, "global_step": 623666, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9708137512207031, "global_step": 623667, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9933403730392456, "global_step": 623668, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9872846603393555, "global_step": 623669, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.034529685974121, "global_step": 623670, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0618016719818115, "global_step": 623671, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0626089572906494, "global_step": 623672, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.02762770652771, "global_step": 623673, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9644721746444702, "global_step": 623674, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9458116292953491, "global_step": 623675, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0809645652770996, "global_step": 623676, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9893876314163208, "global_step": 623677, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.050961494445801, "global_step": 623678, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9736888408660889, "global_step": 623679, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0523619651794434, "global_step": 623680, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.065354108810425, "global_step": 623681, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9651294946670532, "global_step": 623682, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.990847110748291, "global_step": 623683, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1260974407196045, "global_step": 623684, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9463908672332764, "global_step": 623685, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9356684684753418, "global_step": 623686, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0027785301208496, "global_step": 623687, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.038027048110962, "global_step": 623688, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.068495273590088, "global_step": 623689, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9790793657302856, "global_step": 623690, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0688652992248535, "global_step": 623691, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0280232429504395, "global_step": 623692, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.005067825317383, "global_step": 623693, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.883223295211792, "global_step": 623694, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0226681232452393, "global_step": 623695, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9499620199203491, "global_step": 623696, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9473682641983032, "global_step": 623697, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0038628578186035, "global_step": 623698, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.060210943222046, "global_step": 623699, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0303478240966797, "global_step": 623700, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.98517644405365, "global_step": 623701, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1222121715545654, "global_step": 623702, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.03920841217041, "global_step": 623703, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0274200439453125, "global_step": 623704, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9771454334259033, "global_step": 623705, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9497172832489014, "global_step": 623706, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.074183702468872, "global_step": 623707, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.054488182067871, "global_step": 623708, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.079641103744507, "global_step": 623709, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.100848913192749, "global_step": 623710, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0636136531829834, "global_step": 623711, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9683798551559448, "global_step": 623712, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.987638235092163, "global_step": 623713, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.982559323310852, "global_step": 623714, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.949516773223877, "global_step": 623715, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.067016839981079, "global_step": 623716, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0093982219696045, "global_step": 623717, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9455803632736206, "global_step": 623718, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9514068365097046, "global_step": 623719, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0388669967651367, "global_step": 623720, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9886844158172607, "global_step": 623721, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0240631103515625, "global_step": 623722, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.934267282485962, "global_step": 623723, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0501461029052734, "global_step": 623724, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9666959047317505, "global_step": 623725, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.035496234893799, "global_step": 623726, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0171918869018555, "global_step": 623727, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.050471067428589, "global_step": 623728, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9215773344039917, "global_step": 623729, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0257322788238525, "global_step": 623730, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9491792917251587, "global_step": 623731, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.038090944290161, "global_step": 623732, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0127243995666504, "global_step": 623733, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.010854482650757, "global_step": 623734, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.051943302154541, "global_step": 623735, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9675068855285645, "global_step": 623736, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9458308219909668, "global_step": 623737, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9575748443603516, "global_step": 623738, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9184411764144897, "global_step": 623739, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1784555912017822, "global_step": 623740, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9883874654769897, "global_step": 623741, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0112648010253906, "global_step": 623742, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9898715019226074, "global_step": 623743, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0018653869628906, "global_step": 623744, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0127031803131104, "global_step": 623745, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0246376991271973, "global_step": 623746, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9676358699798584, "global_step": 623747, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9798600673675537, "global_step": 623748, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9893673658370972, "global_step": 623749, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.959861159324646, "global_step": 623750, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9938746690750122, "global_step": 623751, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.005786418914795, "global_step": 623752, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0500662326812744, "global_step": 623753, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.063722848892212, "global_step": 623754, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9746233224868774, "global_step": 623755, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0384738445281982, "global_step": 623756, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.935180902481079, "global_step": 623757, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9882216453552246, "global_step": 623758, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.007176637649536, "global_step": 623759, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0909030437469482, "global_step": 623760, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9914257526397705, "global_step": 623761, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0263595581054688, "global_step": 623762, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.966886281967163, "global_step": 623763, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0016348361968994, "global_step": 623764, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9899098873138428, "global_step": 623765, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0305776596069336, "global_step": 623766, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.920821189880371, "global_step": 623767, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.963939905166626, "global_step": 623768, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.001185417175293, "global_step": 623769, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.015606641769409, "global_step": 623770, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9865736961364746, "global_step": 623771, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9754126071929932, "global_step": 623772, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9719816446304321, "global_step": 623773, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9809023141860962, "global_step": 623774, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.976063847541809, "global_step": 623775, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9850291013717651, "global_step": 623776, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.020986318588257, "global_step": 623777, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0833194255828857, "global_step": 623778, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0144989490509033, "global_step": 623779, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0762569904327393, "global_step": 623780, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0216000080108643, "global_step": 623781, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9287883043289185, "global_step": 623782, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0036168098449707, "global_step": 623783, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.060382604598999, "global_step": 623784, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0141828060150146, "global_step": 623785, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0824010372161865, "global_step": 623786, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.071852922439575, "global_step": 623787, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0063395500183105, "global_step": 623788, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.032437562942505, "global_step": 623789, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9372056722640991, "global_step": 623790, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9908626079559326, "global_step": 623791, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9992847442626953, "global_step": 623792, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.064049005508423, "global_step": 623793, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9838488101959229, "global_step": 623794, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0142853260040283, "global_step": 623795, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0587613582611084, "global_step": 623796, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9723044633865356, "global_step": 623797, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9939465522766113, "global_step": 623798, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9556198120117188, "global_step": 623799, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0121803283691406, "global_step": 623800, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0436511039733887, "global_step": 623801, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.010671854019165, "global_step": 623802, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0226330757141113, "global_step": 623803, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9301666021347046, "global_step": 623804, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0041744709014893, "global_step": 623805, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0380680561065674, "global_step": 623806, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0766594409942627, "global_step": 623807, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.090506076812744, "global_step": 623808, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9915473461151123, "global_step": 623809, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0506062507629395, "global_step": 623810, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9125202894210815, "global_step": 623811, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0204365253448486, "global_step": 623812, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9715173244476318, "global_step": 623813, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.056300640106201, "global_step": 623814, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9369890689849854, "global_step": 623815, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0630111694335938, "global_step": 623816, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9628404378890991, "global_step": 623817, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.057354688644409, "global_step": 623818, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9570642709732056, "global_step": 623819, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0244622230529785, "global_step": 623820, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9579946994781494, "global_step": 623821, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0514841079711914, "global_step": 623822, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.011551856994629, "global_step": 623823, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.119022846221924, "global_step": 623824, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9544117450714111, "global_step": 623825, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0333731174468994, "global_step": 623826, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9656453132629395, "global_step": 623827, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9967403411865234, "global_step": 623828, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.992246389389038, "global_step": 623829, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9643384218215942, "global_step": 623830, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0925984382629395, "global_step": 623831, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9287843704223633, "global_step": 623832, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0215024948120117, "global_step": 623833, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.029489040374756, "global_step": 623834, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0380938053131104, "global_step": 623835, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0302810668945312, "global_step": 623836, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.058748960494995, "global_step": 623837, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.926192283630371, "global_step": 623838, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0715906620025635, "global_step": 623839, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9956943988800049, "global_step": 623840, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9859765768051147, "global_step": 623841, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0946671962738037, "global_step": 623842, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0139057636260986, "global_step": 623843, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.049908399581909, "global_step": 623844, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0318737030029297, "global_step": 623845, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.013270616531372, "global_step": 623846, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.00860857963562, "global_step": 623847, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0079002380371094, "global_step": 623848, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9580888748168945, "global_step": 623849, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.064678907394409, "global_step": 623850, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9672179222106934, "global_step": 623851, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0056300163269043, "global_step": 623852, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9774805307388306, "global_step": 623853, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0328643321990967, "global_step": 623854, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9238159656524658, "global_step": 623855, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0416312217712402, "global_step": 623856, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0182883739471436, "global_step": 623857, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9632213115692139, "global_step": 623858, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9595082998275757, "global_step": 623859, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9903433322906494, "global_step": 623860, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.023786783218384, "global_step": 623861, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0293984413146973, "global_step": 623862, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.970129132270813, "global_step": 623863, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.053251028060913, "global_step": 623864, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.032754898071289, "global_step": 623865, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.003427267074585, "global_step": 623866, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0049242973327637, "global_step": 623867, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0401341915130615, "global_step": 623868, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9228405952453613, "global_step": 623869, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.045034646987915, "global_step": 623870, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.056825637817383, "global_step": 623871, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.025580883026123, "global_step": 623872, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9523084163665771, "global_step": 623873, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.983276605606079, "global_step": 623874, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9356051683425903, "global_step": 623875, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9679276943206787, "global_step": 623876, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9026435613632202, "global_step": 623877, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0868868827819824, "global_step": 623878, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.986114740371704, "global_step": 623879, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9717966318130493, "global_step": 623880, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9635493755340576, "global_step": 623881, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.984411358833313, "global_step": 623882, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0398130416870117, "global_step": 623883, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9577888250350952, "global_step": 623884, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0119552612304688, "global_step": 623885, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.010047435760498, "global_step": 623886, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.008108615875244, "global_step": 623887, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.004471778869629, "global_step": 623888, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9514977931976318, "global_step": 623889, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.951507568359375, "global_step": 623890, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.045151472091675, "global_step": 623891, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9680595397949219, "global_step": 623892, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9675827026367188, "global_step": 623893, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0137076377868652, "global_step": 623894, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9864717721939087, "global_step": 623895, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.084390640258789, "global_step": 623896, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9884693622589111, "global_step": 623897, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9217188358306885, "global_step": 623898, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9916965961456299, "global_step": 623899, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.013495445251465, "global_step": 623900, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.075399398803711, "global_step": 623901, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9380005598068237, "global_step": 623902, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0012240409851074, "global_step": 623903, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9877361059188843, "global_step": 623904, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.023040533065796, "global_step": 623905, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0488665103912354, "global_step": 623906, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.110746383666992, "global_step": 623907, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.04889178276062, "global_step": 623908, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9993672370910645, "global_step": 623909, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.09550142288208, "global_step": 623910, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.026197910308838, "global_step": 623911, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.027926206588745, "global_step": 623912, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9829663038253784, "global_step": 623913, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0392682552337646, "global_step": 623914, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0339534282684326, "global_step": 623915, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0552423000335693, "global_step": 623916, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0334696769714355, "global_step": 623917, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.02113676071167, "global_step": 623918, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.013974905014038, "global_step": 623919, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9533637762069702, "global_step": 623920, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9606304168701172, "global_step": 623921, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.996255874633789, "global_step": 623922, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.938850998878479, "global_step": 623923, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9382292032241821, "global_step": 623924, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.128815174102783, "global_step": 623925, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0090506076812744, "global_step": 623926, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0105481147766113, "global_step": 623927, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9699753522872925, "global_step": 623928, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0179073810577393, "global_step": 623929, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0553839206695557, "global_step": 623930, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9585554599761963, "global_step": 623931, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9751214981079102, "global_step": 623932, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9904001951217651, "global_step": 623933, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0084633827209473, "global_step": 623934, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.065791368484497, "global_step": 623935, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.040900945663452, "global_step": 623936, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.065736770629883, "global_step": 623937, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1781091690063477, "global_step": 623938, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0122361183166504, "global_step": 623939, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0034780502319336, "global_step": 623940, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9436578750610352, "global_step": 623941, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9949634075164795, "global_step": 623942, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9858778715133667, "global_step": 623943, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0077695846557617, "global_step": 623944, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0153181552886963, "global_step": 623945, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9671062231063843, "global_step": 623946, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.124372720718384, "global_step": 623947, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9497485160827637, "global_step": 623948, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9656108617782593, "global_step": 623949, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9411815404891968, "global_step": 623950, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.033634662628174, "global_step": 623951, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0444884300231934, "global_step": 623952, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.103116273880005, "global_step": 623953, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0143327713012695, "global_step": 623954, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9778214693069458, "global_step": 623955, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0831618309020996, "global_step": 623956, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.002596139907837, "global_step": 623957, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9250251054763794, "global_step": 623958, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.982356071472168, "global_step": 623959, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0748515129089355, "global_step": 623960, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9742568731307983, "global_step": 623961, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0509650707244873, "global_step": 623962, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.000305414199829, "global_step": 623963, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.979704737663269, "global_step": 623964, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9843063354492188, "global_step": 623965, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9785823822021484, "global_step": 623966, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.005695104598999, "global_step": 623967, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.048236846923828, "global_step": 623968, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0105948448181152, "global_step": 623969, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0023629665374756, "global_step": 623970, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.949363350868225, "global_step": 623971, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9314022064208984, "global_step": 623972, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0709307193756104, "global_step": 623973, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0702719688415527, "global_step": 623974, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.094325065612793, "global_step": 623975, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.975836992263794, "global_step": 623976, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1092851161956787, "global_step": 623977, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0634877681732178, "global_step": 623978, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.969679355621338, "global_step": 623979, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0251336097717285, "global_step": 623980, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0358238220214844, "global_step": 623981, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.965224027633667, "global_step": 623982, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9475394487380981, "global_step": 623983, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0370357036590576, "global_step": 623984, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9511483907699585, "global_step": 623985, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.976204514503479, "global_step": 623986, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9772979021072388, "global_step": 623987, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.994889497756958, "global_step": 623988, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9922306537628174, "global_step": 623989, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.016145706176758, "global_step": 623990, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.028658628463745, "global_step": 623991, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0275259017944336, "global_step": 623992, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.073434829711914, "global_step": 623993, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.954693078994751, "global_step": 623994, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.004502773284912, "global_step": 623995, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9626044034957886, "global_step": 623996, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0386924743652344, "global_step": 623997, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0133306980133057, "global_step": 623998, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.052464485168457, "global_step": 623999, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0622916221618652, "global_step": 624000, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9068814516067505, "global_step": 624001, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9699455499649048, "global_step": 624002, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9558900594711304, "global_step": 624003, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.101170063018799, "global_step": 624004, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.036181688308716, "global_step": 624005, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1256749629974365, "global_step": 624006, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0034139156341553, "global_step": 624007, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.961326241493225, "global_step": 624008, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0284152030944824, "global_step": 624009, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9749270677566528, "global_step": 624010, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9809998273849487, "global_step": 624011, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0442054271698, "global_step": 624012, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9899311065673828, "global_step": 624013, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9664347171783447, "global_step": 624014, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.980656385421753, "global_step": 624015, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.103372812271118, "global_step": 624016, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.019272804260254, "global_step": 624017, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.074718952178955, "global_step": 624018, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9523353576660156, "global_step": 624019, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0092175006866455, "global_step": 624020, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0235533714294434, "global_step": 624021, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.063063144683838, "global_step": 624022, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9624103307724, "global_step": 624023, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9273093938827515, "global_step": 624024, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.894314169883728, "global_step": 624025, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9893888235092163, "global_step": 624026, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.965651273727417, "global_step": 624027, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0183866024017334, "global_step": 624028, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1038286685943604, "global_step": 624029, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0298051834106445, "global_step": 624030, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.039703369140625, "global_step": 624031, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0736217498779297, "global_step": 624032, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.029448986053467, "global_step": 624033, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9882690906524658, "global_step": 624034, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0709309577941895, "global_step": 624035, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9965211153030396, "global_step": 624036, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1198081970214844, "global_step": 624037, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0194907188415527, "global_step": 624038, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.055912733078003, "global_step": 624039, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9225950241088867, "global_step": 624040, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.066643238067627, "global_step": 624041, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.016300678253174, "global_step": 624042, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0923385620117188, "global_step": 624043, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9935953617095947, "global_step": 624044, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9535318613052368, "global_step": 624045, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9385708570480347, "global_step": 624046, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9951157569885254, "global_step": 624047, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9317494630813599, "global_step": 624048, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0470046997070312, "global_step": 624049, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.007359266281128, "global_step": 624050, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9999510049819946, "global_step": 624051, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0887060165405273, "global_step": 624052, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9867500066757202, "global_step": 624053, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.984621286392212, "global_step": 624054, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.970896601676941, "global_step": 624055, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.002511501312256, "global_step": 624056, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0530030727386475, "global_step": 624057, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.961991548538208, "global_step": 624058, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1052443981170654, "global_step": 624059, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0190436840057373, "global_step": 624060, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9862571954727173, "global_step": 624061, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9886778593063354, "global_step": 624062, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.056997537612915, "global_step": 624063, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0347988605499268, "global_step": 624064, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9660743474960327, "global_step": 624065, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.072147846221924, "global_step": 624066, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0219810009002686, "global_step": 624067, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0103869438171387, "global_step": 624068, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0297536849975586, "global_step": 624069, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.060777425765991, "global_step": 624070, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1099512577056885, "global_step": 624071, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0864500999450684, "global_step": 624072, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0160138607025146, "global_step": 624073, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9760111570358276, "global_step": 624074, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9688541889190674, "global_step": 624075, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.053809642791748, "global_step": 624076, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.007709264755249, "global_step": 624077, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.906148076057434, "global_step": 624078, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0227999687194824, "global_step": 624079, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9716850519180298, "global_step": 624080, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9060033559799194, "global_step": 624081, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9950839281082153, "global_step": 624082, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0778632164001465, "global_step": 624083, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.928892731666565, "global_step": 624084, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9789562225341797, "global_step": 624085, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0347208976745605, "global_step": 624086, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.983401894569397, "global_step": 624087, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.024784803390503, "global_step": 624088, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9727271795272827, "global_step": 624089, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.026289701461792, "global_step": 624090, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.021900177001953, "global_step": 624091, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0201385021209717, "global_step": 624092, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1394264698028564, "global_step": 624093, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.966534972190857, "global_step": 624094, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.054373264312744, "global_step": 624095, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.092993974685669, "global_step": 624096, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.022031545639038, "global_step": 624097, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0010862350463867, "global_step": 624098, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9725453853607178, "global_step": 624099, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0030205249786377, "global_step": 624100, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0621769428253174, "global_step": 624101, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9285130500793457, "global_step": 624102, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.962105393409729, "global_step": 624103, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.985519528388977, "global_step": 624104, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.042734146118164, "global_step": 624105, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9979861974716187, "global_step": 624106, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0306801795959473, "global_step": 624107, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9701632261276245, "global_step": 624108, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9657832384109497, "global_step": 624109, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9679549932479858, "global_step": 624110, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9714785814285278, "global_step": 624111, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.024578809738159, "global_step": 624112, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.035248041152954, "global_step": 624113, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0529377460479736, "global_step": 624114, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9548335075378418, "global_step": 624115, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9792165756225586, "global_step": 624116, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.000251531600952, "global_step": 624117, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0025603771209717, "global_step": 624118, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9343197345733643, "global_step": 624119, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9895915985107422, "global_step": 624120, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9896376132965088, "global_step": 624121, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.075834035873413, "global_step": 624122, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0122034549713135, "global_step": 624123, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9995408058166504, "global_step": 624124, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9621753692626953, "global_step": 624125, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0480098724365234, "global_step": 624126, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9974496364593506, "global_step": 624127, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.013542652130127, "global_step": 624128, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0150039196014404, "global_step": 624129, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.022585153579712, "global_step": 624130, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1370439529418945, "global_step": 624131, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9831143617630005, "global_step": 624132, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0501391887664795, "global_step": 624133, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0389606952667236, "global_step": 624134, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9630409479141235, "global_step": 624135, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.011439561843872, "global_step": 624136, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9956912994384766, "global_step": 624137, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.071427345275879, "global_step": 624138, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9407095909118652, "global_step": 624139, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9587128162384033, "global_step": 624140, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0069921016693115, "global_step": 624141, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.067763090133667, "global_step": 624142, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.030806064605713, "global_step": 624143, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0438761711120605, "global_step": 624144, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.03497314453125, "global_step": 624145, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0043063163757324, "global_step": 624146, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0331532955169678, "global_step": 624147, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0777976512908936, "global_step": 624148, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.054927110671997, "global_step": 624149, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0248613357543945, "global_step": 624150, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9964077472686768, "global_step": 624151, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.021184206008911, "global_step": 624152, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1089797019958496, "global_step": 624153, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9927177429199219, "global_step": 624154, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.1578266620635986, "global_step": 624155, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0602054595947266, "global_step": 624156, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.034898519515991, "global_step": 624157, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9200470447540283, "global_step": 624158, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9654735326766968, "global_step": 624159, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0738234519958496, "global_step": 624160, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.8910006284713745, "global_step": 624161, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.947787880897522, "global_step": 624162, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9232869148254395, "global_step": 624163, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9740569591522217, "global_step": 624164, "epoch": 992, "lr": 5e-05}
{"train_loss": 1.9119935035705566, "global_step": 624165, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.062947988510132, "global_step": 624166, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.0039596557617188, "global_step": 624167, "epoch": 992, "lr": 5e-05}
{"train_loss": 2.021116018295288, "global_step": 624168, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9261997938156128, "global_step": 624169, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9670798778533936, "global_step": 624170, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9785652160644531, "global_step": 624171, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8857144117355347, "global_step": 624172, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9652330875396729, "global_step": 624173, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9563945531845093, "global_step": 624174, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.032148838043213, "global_step": 624175, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9409642219543457, "global_step": 624176, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0362181663513184, "global_step": 624177, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9720402956008911, "global_step": 624178, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9557820558547974, "global_step": 624179, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.977828860282898, "global_step": 624180, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1042232513427734, "global_step": 624181, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.074824810028076, "global_step": 624182, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.021453380584717, "global_step": 624183, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.019075632095337, "global_step": 624184, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9353786706924438, "global_step": 624185, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.986473560333252, "global_step": 624186, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9749302864074707, "global_step": 624187, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9737374782562256, "global_step": 624188, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9362205266952515, "global_step": 624189, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0441017150878906, "global_step": 624190, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8107035160064697, "global_step": 624191, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9095712900161743, "global_step": 624192, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.033010482788086, "global_step": 624193, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0483126640319824, "global_step": 624194, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9808642864227295, "global_step": 624195, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9820080995559692, "global_step": 624196, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8986127376556396, "global_step": 624197, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9757620096206665, "global_step": 624198, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9755786657333374, "global_step": 624199, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0553441047668457, "global_step": 624200, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.032170295715332, "global_step": 624201, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9687364101409912, "global_step": 624202, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.046513080596924, "global_step": 624203, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0576274394989014, "global_step": 624204, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9493685960769653, "global_step": 624205, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.993596076965332, "global_step": 624206, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9929012060165405, "global_step": 624207, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.006385564804077, "global_step": 624208, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.024397850036621, "global_step": 624209, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0476810932159424, "global_step": 624210, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.015462875366211, "global_step": 624211, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9975159168243408, "global_step": 624212, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9873179197311401, "global_step": 624213, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9532055854797363, "global_step": 624214, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9990586042404175, "global_step": 624215, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.905813217163086, "global_step": 624216, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9184257984161377, "global_step": 624217, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.001765012741089, "global_step": 624218, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.018071174621582, "global_step": 624219, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9474425315856934, "global_step": 624220, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9996196031570435, "global_step": 624221, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0117008686065674, "global_step": 624222, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9987164735794067, "global_step": 624223, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0134682655334473, "global_step": 624224, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9811885356903076, "global_step": 624225, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.955936074256897, "global_step": 624226, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9282324314117432, "global_step": 624227, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9703385829925537, "global_step": 624228, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0087833404541016, "global_step": 624229, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9565014839172363, "global_step": 624230, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0324015617370605, "global_step": 624231, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9930649995803833, "global_step": 624232, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.014915943145752, "global_step": 624233, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.046560049057007, "global_step": 624234, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.049382209777832, "global_step": 624235, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0579261779785156, "global_step": 624236, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9717440605163574, "global_step": 624237, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9441046714782715, "global_step": 624238, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.075727939605713, "global_step": 624239, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9285011291503906, "global_step": 624240, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0379278659820557, "global_step": 624241, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0065417289733887, "global_step": 624242, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9621483087539673, "global_step": 624243, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.051590919494629, "global_step": 624244, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8604576587677002, "global_step": 624245, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0174427032470703, "global_step": 624246, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9699175357818604, "global_step": 624247, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1087968349456787, "global_step": 624248, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.884889841079712, "global_step": 624249, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9940814971923828, "global_step": 624250, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.021890640258789, "global_step": 624251, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.970691204071045, "global_step": 624252, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0025556087493896, "global_step": 624253, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.981468915939331, "global_step": 624254, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0625927448272705, "global_step": 624255, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.015469551086426, "global_step": 624256, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9937833547592163, "global_step": 624257, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9936176538467407, "global_step": 624258, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9754307270050049, "global_step": 624259, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9659223556518555, "global_step": 624260, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.955428123474121, "global_step": 624261, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9463056325912476, "global_step": 624262, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9900059700012207, "global_step": 624263, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0190446376800537, "global_step": 624264, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.055187940597534, "global_step": 624265, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0365993976593018, "global_step": 624266, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.003000497817993, "global_step": 624267, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0335066318511963, "global_step": 624268, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9549351930618286, "global_step": 624269, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9539159536361694, "global_step": 624270, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9893560409545898, "global_step": 624271, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.077690601348877, "global_step": 624272, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0295779705047607, "global_step": 624273, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9249796867370605, "global_step": 624274, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0483100414276123, "global_step": 624275, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0414087772369385, "global_step": 624276, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.039428472518921, "global_step": 624277, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0507404804229736, "global_step": 624278, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9760515689849854, "global_step": 624279, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.056741237640381, "global_step": 624280, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9808948040008545, "global_step": 624281, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9734148979187012, "global_step": 624282, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9995301961898804, "global_step": 624283, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9546394348144531, "global_step": 624284, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9901291131973267, "global_step": 624285, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.023041009902954, "global_step": 624286, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0211164951324463, "global_step": 624287, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9762978553771973, "global_step": 624288, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0501298904418945, "global_step": 624289, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9661879539489746, "global_step": 624290, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9863309860229492, "global_step": 624291, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9270968437194824, "global_step": 624292, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0193655490875244, "global_step": 624293, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9437255859375, "global_step": 624294, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9222816228866577, "global_step": 624295, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.02254056930542, "global_step": 624296, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0853638648986816, "global_step": 624297, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0229077339172363, "global_step": 624298, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.970462679862976, "global_step": 624299, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9788912534713745, "global_step": 624300, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0214743614196777, "global_step": 624301, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0156593322753906, "global_step": 624302, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9561734199523926, "global_step": 624303, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9915821552276611, "global_step": 624304, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9340591430664062, "global_step": 624305, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9730762243270874, "global_step": 624306, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.00168776512146, "global_step": 624307, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.066805601119995, "global_step": 624308, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9542310237884521, "global_step": 624309, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0714638233184814, "global_step": 624310, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9750866889953613, "global_step": 624311, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.004725694656372, "global_step": 624312, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.013504981994629, "global_step": 624313, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9785622358322144, "global_step": 624314, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1213629245758057, "global_step": 624315, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.057008743286133, "global_step": 624316, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9882793426513672, "global_step": 624317, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.050856351852417, "global_step": 624318, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.062411069869995, "global_step": 624319, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0030572414398193, "global_step": 624320, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.042275905609131, "global_step": 624321, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0651211738586426, "global_step": 624322, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0468928813934326, "global_step": 624323, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.99651300907135, "global_step": 624324, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.966099500656128, "global_step": 624325, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0387935638427734, "global_step": 624326, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9943405389785767, "global_step": 624327, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9306095838546753, "global_step": 624328, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9467766284942627, "global_step": 624329, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.997274398803711, "global_step": 624330, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.030034303665161, "global_step": 624331, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0035324096679688, "global_step": 624332, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.974391222000122, "global_step": 624333, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.015551805496216, "global_step": 624334, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9395668506622314, "global_step": 624335, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9662362337112427, "global_step": 624336, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0128915309906006, "global_step": 624337, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0160162448883057, "global_step": 624338, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0310616493225098, "global_step": 624339, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9966391324996948, "global_step": 624340, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.002718448638916, "global_step": 624341, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0229740142822266, "global_step": 624342, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0225563049316406, "global_step": 624343, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.952310562133789, "global_step": 624344, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.077808380126953, "global_step": 624345, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0467379093170166, "global_step": 624346, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.006195068359375, "global_step": 624347, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9901647567749023, "global_step": 624348, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9574480056762695, "global_step": 624349, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0065629482269287, "global_step": 624350, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9841663837432861, "global_step": 624351, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9561786651611328, "global_step": 624352, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9067786931991577, "global_step": 624353, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.014981508255005, "global_step": 624354, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0271553993225098, "global_step": 624355, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0376479625701904, "global_step": 624356, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0176877975463867, "global_step": 624357, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0159552097320557, "global_step": 624358, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.04307222366333, "global_step": 624359, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9843952655792236, "global_step": 624360, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.007410764694214, "global_step": 624361, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9779499769210815, "global_step": 624362, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.982377052307129, "global_step": 624363, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0156455039978027, "global_step": 624364, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9714363813400269, "global_step": 624365, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.01228666305542, "global_step": 624366, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0726723670959473, "global_step": 624367, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9799548387527466, "global_step": 624368, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.982340931892395, "global_step": 624369, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0331923961639404, "global_step": 624370, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0983619689941406, "global_step": 624371, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.045140266418457, "global_step": 624372, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.986897349357605, "global_step": 624373, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9332327842712402, "global_step": 624374, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.027989149093628, "global_step": 624375, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9970388412475586, "global_step": 624376, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0584945678710938, "global_step": 624377, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0472934246063232, "global_step": 624378, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9493234157562256, "global_step": 624379, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9816913604736328, "global_step": 624380, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9880573749542236, "global_step": 624381, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9369903802871704, "global_step": 624382, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.918525218963623, "global_step": 624383, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.976048469543457, "global_step": 624384, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.056079149246216, "global_step": 624385, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8679900169372559, "global_step": 624386, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9924439191818237, "global_step": 624387, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9935383796691895, "global_step": 624388, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.008190155029297, "global_step": 624389, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.097249984741211, "global_step": 624390, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.036107063293457, "global_step": 624391, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9131901264190674, "global_step": 624392, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9533612728118896, "global_step": 624393, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9407929182052612, "global_step": 624394, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0119259357452393, "global_step": 624395, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9323580265045166, "global_step": 624396, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9658222198486328, "global_step": 624397, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0197715759277344, "global_step": 624398, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.93354332447052, "global_step": 624399, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0270779132843018, "global_step": 624400, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0285470485687256, "global_step": 624401, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9950007200241089, "global_step": 624402, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9994022846221924, "global_step": 624403, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.016056776046753, "global_step": 624404, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0422260761260986, "global_step": 624405, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.04510235786438, "global_step": 624406, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9196444749832153, "global_step": 624407, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9805541038513184, "global_step": 624408, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.050018548965454, "global_step": 624409, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9965511560440063, "global_step": 624410, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.950914740562439, "global_step": 624411, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0151121616363525, "global_step": 624412, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8911631107330322, "global_step": 624413, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.017338275909424, "global_step": 624414, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9365041255950928, "global_step": 624415, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0057811737060547, "global_step": 624416, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9254374504089355, "global_step": 624417, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9914653301239014, "global_step": 624418, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0513360500335693, "global_step": 624419, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9463311433792114, "global_step": 624420, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.947961688041687, "global_step": 624421, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9403443336486816, "global_step": 624422, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1042802333831787, "global_step": 624423, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.026520013809204, "global_step": 624424, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.007871627807617, "global_step": 624425, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.036837100982666, "global_step": 624426, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9544486999511719, "global_step": 624427, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0262234210968018, "global_step": 624428, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0762805938720703, "global_step": 624429, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0755248069763184, "global_step": 624430, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.068848133087158, "global_step": 624431, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9865723848342896, "global_step": 624432, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0485310554504395, "global_step": 624433, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9928405284881592, "global_step": 624434, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.032658576965332, "global_step": 624435, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.032336950302124, "global_step": 624436, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.051147699356079, "global_step": 624437, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9647259712219238, "global_step": 624438, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.040864944458008, "global_step": 624439, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.037515163421631, "global_step": 624440, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9719423055648804, "global_step": 624441, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.969529151916504, "global_step": 624442, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9783755540847778, "global_step": 624443, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0440852642059326, "global_step": 624444, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.061706304550171, "global_step": 624445, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9903796911239624, "global_step": 624446, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9362176656723022, "global_step": 624447, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.02716064453125, "global_step": 624448, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9631493091583252, "global_step": 624449, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.027724504470825, "global_step": 624450, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.044090747833252, "global_step": 624451, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.039893388748169, "global_step": 624452, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0405516624450684, "global_step": 624453, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9287747144699097, "global_step": 624454, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0381765365600586, "global_step": 624455, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.024991989135742, "global_step": 624456, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.995232105255127, "global_step": 624457, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0365121364593506, "global_step": 624458, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9946588277816772, "global_step": 624459, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9871729612350464, "global_step": 624460, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9642502069473267, "global_step": 624461, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9934710264205933, "global_step": 624462, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0773918628692627, "global_step": 624463, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9619579315185547, "global_step": 624464, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9279696941375732, "global_step": 624465, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9675469398498535, "global_step": 624466, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.075941801071167, "global_step": 624467, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.965649962425232, "global_step": 624468, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9856810569763184, "global_step": 624469, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9661089181900024, "global_step": 624470, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9884692430496216, "global_step": 624471, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9193596839904785, "global_step": 624472, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0569236278533936, "global_step": 624473, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.041999578475952, "global_step": 624474, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0069050788879395, "global_step": 624475, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.981241226196289, "global_step": 624476, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.928917407989502, "global_step": 624477, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9971295595169067, "global_step": 624478, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9098553657531738, "global_step": 624479, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0622329711914062, "global_step": 624480, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9410278797149658, "global_step": 624481, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.021904230117798, "global_step": 624482, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0137181282043457, "global_step": 624483, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9722285270690918, "global_step": 624484, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.064770460128784, "global_step": 624485, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9930753707885742, "global_step": 624486, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0743253231048584, "global_step": 624487, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.994614601135254, "global_step": 624488, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8919193744659424, "global_step": 624489, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0403497219085693, "global_step": 624490, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9827485084533691, "global_step": 624491, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9301100969314575, "global_step": 624492, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9101122617721558, "global_step": 624493, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.979846477508545, "global_step": 624494, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9986680746078491, "global_step": 624495, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0278103351593018, "global_step": 624496, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8919974565505981, "global_step": 624497, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.993100643157959, "global_step": 624498, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9390653371810913, "global_step": 624499, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9866522550582886, "global_step": 624500, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.02691650390625, "global_step": 624501, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.994097113609314, "global_step": 624502, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0034666061401367, "global_step": 624503, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9590022563934326, "global_step": 624504, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9774824380874634, "global_step": 624505, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.054701805114746, "global_step": 624506, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9741648435592651, "global_step": 624507, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9340800046920776, "global_step": 624508, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9430054426193237, "global_step": 624509, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9500846862792969, "global_step": 624510, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9396568536758423, "global_step": 624511, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.998626708984375, "global_step": 624512, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9910264015197754, "global_step": 624513, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9333620071411133, "global_step": 624514, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9816299676895142, "global_step": 624515, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9880021810531616, "global_step": 624516, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.998598337173462, "global_step": 624517, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.058349370956421, "global_step": 624518, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0289559364318848, "global_step": 624519, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0130655765533447, "global_step": 624520, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9518413543701172, "global_step": 624521, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0369136333465576, "global_step": 624522, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.971548080444336, "global_step": 624523, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9918107986450195, "global_step": 624524, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.035446882247925, "global_step": 624525, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9930524826049805, "global_step": 624526, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0521368980407715, "global_step": 624527, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.006249189376831, "global_step": 624528, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9944151639938354, "global_step": 624529, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.972077488899231, "global_step": 624530, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9095628261566162, "global_step": 624531, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9740891456604004, "global_step": 624532, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0741608142852783, "global_step": 624533, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.050187110900879, "global_step": 624534, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9320650100708008, "global_step": 624535, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.96390700340271, "global_step": 624536, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.128551483154297, "global_step": 624537, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0846118927001953, "global_step": 624538, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9374606609344482, "global_step": 624539, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0229928493499756, "global_step": 624540, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.982464075088501, "global_step": 624541, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.99405837059021, "global_step": 624542, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.984878659248352, "global_step": 624543, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0480904579162598, "global_step": 624544, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9697593450546265, "global_step": 624545, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9312735795974731, "global_step": 624546, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9694346189498901, "global_step": 624547, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0963871479034424, "global_step": 624548, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.049163341522217, "global_step": 624549, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.977921724319458, "global_step": 624550, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0679986476898193, "global_step": 624551, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.011490821838379, "global_step": 624552, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9822510480880737, "global_step": 624553, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0482611656188965, "global_step": 624554, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0165693759918213, "global_step": 624555, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9172749519348145, "global_step": 624556, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.958146095275879, "global_step": 624557, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9894447326660156, "global_step": 624558, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9278062582015991, "global_step": 624559, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.005338668823242, "global_step": 624560, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9216879606246948, "global_step": 624561, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0318000316619873, "global_step": 624562, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9590972661972046, "global_step": 624563, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.007425546646118, "global_step": 624564, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.09196400642395, "global_step": 624565, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.025722026824951, "global_step": 624566, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9827972650527954, "global_step": 624567, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.017390727996826, "global_step": 624568, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.004758596420288, "global_step": 624569, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0258123874664307, "global_step": 624570, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0000991821289062, "global_step": 624571, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.091714859008789, "global_step": 624572, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0725667476654053, "global_step": 624573, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0232131481170654, "global_step": 624574, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9931913614273071, "global_step": 624575, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0429646968841553, "global_step": 624576, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.086286783218384, "global_step": 624577, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.958726167678833, "global_step": 624578, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0205063819885254, "global_step": 624579, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0097081661224365, "global_step": 624580, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9718327522277832, "global_step": 624581, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9789602756500244, "global_step": 624582, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.048759698867798, "global_step": 624583, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.042727470397949, "global_step": 624584, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8838119506835938, "global_step": 624585, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.916483998298645, "global_step": 624586, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9954876899719238, "global_step": 624587, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9788002967834473, "global_step": 624588, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.034205436706543, "global_step": 624589, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9345916509628296, "global_step": 624590, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9465702772140503, "global_step": 624591, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9350481033325195, "global_step": 624592, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1081864833831787, "global_step": 624593, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9466131925582886, "global_step": 624594, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9985296726226807, "global_step": 624595, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0437538623809814, "global_step": 624596, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0236175060272217, "global_step": 624597, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9522134065628052, "global_step": 624598, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0052239894866943, "global_step": 624599, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.978330135345459, "global_step": 624600, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0222229957580566, "global_step": 624601, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0678136348724365, "global_step": 624602, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.068416118621826, "global_step": 624603, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0869665145874023, "global_step": 624604, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9655898809432983, "global_step": 624605, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.017770528793335, "global_step": 624606, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9109634160995483, "global_step": 624607, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.024717330932617, "global_step": 624608, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9213320016860962, "global_step": 624609, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0375607013702393, "global_step": 624610, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.005613088607788, "global_step": 624611, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.07879900932312, "global_step": 624612, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9556113481521606, "global_step": 624613, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.019669532775879, "global_step": 624614, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.971398115158081, "global_step": 624615, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9291400909423828, "global_step": 624616, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.063075304031372, "global_step": 624617, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0376689434051514, "global_step": 624618, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0191879272460938, "global_step": 624619, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0429086685180664, "global_step": 624620, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0109524726867676, "global_step": 624621, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9973547458648682, "global_step": 624622, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0280959606170654, "global_step": 624623, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0656139850616455, "global_step": 624624, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.021526336669922, "global_step": 624625, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9682124853134155, "global_step": 624626, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0564146041870117, "global_step": 624627, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9641071557998657, "global_step": 624628, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9304230213165283, "global_step": 624629, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.064607620239258, "global_step": 624630, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.044748306274414, "global_step": 624631, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0004873275756836, "global_step": 624632, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.048663377761841, "global_step": 624633, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.987916350364685, "global_step": 624634, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9755834341049194, "global_step": 624635, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.013620615005493, "global_step": 624636, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0102787017822266, "global_step": 624637, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9919798374176025, "global_step": 624638, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0454657077789307, "global_step": 624639, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9857383966445923, "global_step": 624640, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9911258220672607, "global_step": 624641, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0613536834716797, "global_step": 624642, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9019898176193237, "global_step": 624643, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0432920455932617, "global_step": 624644, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9864299297332764, "global_step": 624645, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.99772310256958, "global_step": 624646, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.080084800720215, "global_step": 624647, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8973784446716309, "global_step": 624648, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0353827476501465, "global_step": 624649, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.922515630722046, "global_step": 624650, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9727766513824463, "global_step": 624651, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0498876571655273, "global_step": 624652, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.958174467086792, "global_step": 624653, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9115478992462158, "global_step": 624654, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9662336111068726, "global_step": 624655, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0687670707702637, "global_step": 624656, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0444769859313965, "global_step": 624657, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9767948389053345, "global_step": 624658, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.009823799133301, "global_step": 624659, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.084010124206543, "global_step": 624660, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0196382999420166, "global_step": 624661, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0274367332458496, "global_step": 624662, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9975330829620361, "global_step": 624663, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9988863468170166, "global_step": 624664, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0311591625213623, "global_step": 624665, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.006633996963501, "global_step": 624666, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.063260316848755, "global_step": 624667, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9415910243988037, "global_step": 624668, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.018878698348999, "global_step": 624669, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0203123092651367, "global_step": 624670, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9562057256698608, "global_step": 624671, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9879751205444336, "global_step": 624672, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0051770210266113, "global_step": 624673, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9695202112197876, "global_step": 624674, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.031158685684204, "global_step": 624675, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9549636840820312, "global_step": 624676, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0760202407836914, "global_step": 624677, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0250113010406494, "global_step": 624678, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0502710342407227, "global_step": 624679, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9099270105361938, "global_step": 624680, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0406203269958496, "global_step": 624681, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0246312618255615, "global_step": 624682, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0169074535369873, "global_step": 624683, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.068636655807495, "global_step": 624684, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0550129413604736, "global_step": 624685, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.003857135772705, "global_step": 624686, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9775216579437256, "global_step": 624687, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9800938367843628, "global_step": 624688, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1052584648132324, "global_step": 624689, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.020207405090332, "global_step": 624690, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0537660121917725, "global_step": 624691, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.973398208618164, "global_step": 624692, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9558836221694946, "global_step": 624693, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0173139572143555, "global_step": 624694, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0532612800598145, "global_step": 624695, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9987266063690186, "global_step": 624696, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9856990575790405, "global_step": 624697, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.044891357421875, "global_step": 624698, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0121114253997803, "global_step": 624699, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.032045602798462, "global_step": 624700, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0435054302215576, "global_step": 624701, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9688019752502441, "global_step": 624702, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.941793441772461, "global_step": 624703, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.002469778060913, "global_step": 624704, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.946335792541504, "global_step": 624705, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9680144786834717, "global_step": 624706, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0041580200195312, "global_step": 624707, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9187978506088257, "global_step": 624708, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0204110145568848, "global_step": 624709, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9491528272628784, "global_step": 624710, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0058321952819824, "global_step": 624711, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9983351230621338, "global_step": 624712, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9954890012741089, "global_step": 624713, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.012134552001953, "global_step": 624714, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.014873504638672, "global_step": 624715, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9897619485855103, "global_step": 624716, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9794846773147583, "global_step": 624717, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0069527626037598, "global_step": 624718, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0237863063812256, "global_step": 624719, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9169615507125854, "global_step": 624720, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.021116256713867, "global_step": 624721, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.02333927154541, "global_step": 624722, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9519206285476685, "global_step": 624723, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.003469228744507, "global_step": 624724, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.021190881729126, "global_step": 624725, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9811813831329346, "global_step": 624726, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.101377487182617, "global_step": 624727, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.998735785484314, "global_step": 624728, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.992061734199524, "global_step": 624729, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9730640649795532, "global_step": 624730, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.969448447227478, "global_step": 624731, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0197112560272217, "global_step": 624732, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8361221551895142, "global_step": 624733, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.009060859680176, "global_step": 624734, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0059127807617188, "global_step": 624735, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0218899250030518, "global_step": 624736, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1149911880493164, "global_step": 624737, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9658455848693848, "global_step": 624738, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9667842388153076, "global_step": 624739, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9717944860458374, "global_step": 624740, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9874294996261597, "global_step": 624741, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.041759490966797, "global_step": 624742, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0907959938049316, "global_step": 624743, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.022423505783081, "global_step": 624744, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.920890212059021, "global_step": 624745, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.972617268562317, "global_step": 624746, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0770981311798096, "global_step": 624747, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9221012592315674, "global_step": 624748, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0814907550811768, "global_step": 624749, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9851014614105225, "global_step": 624750, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9537432193756104, "global_step": 624751, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0181896686553955, "global_step": 624752, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.054269313812256, "global_step": 624753, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9292060136795044, "global_step": 624754, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0529608726501465, "global_step": 624755, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9925462007522583, "global_step": 624756, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.050844192504883, "global_step": 624757, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9090774059295654, "global_step": 624758, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.986786127090454, "global_step": 624759, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.102262258529663, "global_step": 624760, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0431370735168457, "global_step": 624761, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9906508922576904, "global_step": 624762, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0595571994781494, "global_step": 624763, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0597143173217773, "global_step": 624764, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.009686231613159, "global_step": 624765, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.118417739868164, "global_step": 624766, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0691182613372803, "global_step": 624767, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9723583459854126, "global_step": 624768, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0695483684539795, "global_step": 624769, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0288102626800537, "global_step": 624770, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.963787317276001, "global_step": 624771, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0012972354888916, "global_step": 624772, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.991621732711792, "global_step": 624773, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9648411273956299, "global_step": 624774, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9548044204711914, "global_step": 624775, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9177364110946655, "global_step": 624776, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0201222896575928, "global_step": 624777, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9437997341156006, "global_step": 624778, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9945883750915527, "global_step": 624779, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.095675230026245, "global_step": 624780, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.035670518875122, "global_step": 624781, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9956530332565308, "global_step": 624782, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0494418144226074, "global_step": 624783, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.013622999191284, "global_step": 624784, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0036487579345703, "global_step": 624785, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0687990188598633, "global_step": 624786, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9745880365371704, "global_step": 624787, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9893040657043457, "global_step": 624788, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9875611066818237, "global_step": 624789, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0712811946868896, "global_step": 624790, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0334012508392334, "global_step": 624791, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.054564952850342, "global_step": 624792, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.005387544631958, "global_step": 624793, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0274064540863037, "global_step": 624794, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.001229763031006, "global_step": 624795, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.062734603881836, "global_step": 624796, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9591370820999146, "global_step": 624797, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.979140043258667, "global_step": 624798, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.059122323989868, "global_step": 624799, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9588673114776611, "global_step": 624800, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1024208068847656, "global_step": 624801, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.997248649597168, "global_step": 624802, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.047168731689453, "global_step": 624803, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9879454374313354, "global_step": 624804, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0406787395477295, "global_step": 624805, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0586142539978027, "global_step": 624806, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.037386655807495, "global_step": 624807, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0320045948028564, "global_step": 624808, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0170226097106934, "global_step": 624809, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9888657331466675, "global_step": 624810, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.992443561553955, "global_step": 624811, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9271252155303955, "global_step": 624812, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.005621910095215, "global_step": 624813, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9948691129684448, "global_step": 624814, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0682008266448975, "global_step": 624815, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.961055040359497, "global_step": 624816, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9731764793395996, "global_step": 624817, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.000800609588623, "global_step": 624818, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8807578086853027, "global_step": 624819, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9975165128707886, "global_step": 624820, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0020601749420166, "global_step": 624821, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9749053716659546, "global_step": 624822, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.063788414001465, "global_step": 624823, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9150526523590088, "global_step": 624824, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.989994764328003, "global_step": 624825, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0184218883514404, "global_step": 624826, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9695734977722168, "global_step": 624827, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9828511476516724, "global_step": 624828, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0355751514434814, "global_step": 624829, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0262458324432373, "global_step": 624830, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9809730052947998, "global_step": 624831, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0956685543060303, "global_step": 624832, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0116770267486572, "global_step": 624833, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0534827709198, "global_step": 624834, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0192949771881104, "global_step": 624835, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.941589593887329, "global_step": 624836, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0161468982696533, "global_step": 624837, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9898288249969482, "global_step": 624838, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9590712785720825, "global_step": 624839, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9495353698730469, "global_step": 624840, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9306262731552124, "global_step": 624841, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9865795373916626, "global_step": 624842, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0294508934020996, "global_step": 624843, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9817296266555786, "global_step": 624844, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.040864944458008, "global_step": 624845, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.048070192337036, "global_step": 624846, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.057342767715454, "global_step": 624847, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0139312744140625, "global_step": 624848, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0168755054473877, "global_step": 624849, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0406339168548584, "global_step": 624850, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0012898445129395, "global_step": 624851, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9988932609558105, "global_step": 624852, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.040060043334961, "global_step": 624853, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9141894578933716, "global_step": 624854, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0231246948242188, "global_step": 624855, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.947121262550354, "global_step": 624856, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9817509651184082, "global_step": 624857, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.976499319076538, "global_step": 624858, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.007740020751953, "global_step": 624859, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0738556385040283, "global_step": 624860, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.976574420928955, "global_step": 624861, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.037156105041504, "global_step": 624862, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0254645347595215, "global_step": 624863, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0661838054656982, "global_step": 624864, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0641720294952393, "global_step": 624865, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.959061861038208, "global_step": 624866, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.993699073791504, "global_step": 624867, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0236172676086426, "global_step": 624868, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9936089515686035, "global_step": 624869, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.020488977432251, "global_step": 624870, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.039306879043579, "global_step": 624871, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9693138599395752, "global_step": 624872, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.055689573287964, "global_step": 624873, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.014880895614624, "global_step": 624874, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.950663685798645, "global_step": 624875, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0245680809020996, "global_step": 624876, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9416685104370117, "global_step": 624877, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9699602127075195, "global_step": 624878, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0720715522766113, "global_step": 624879, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.002969980239868, "global_step": 624880, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1094419956207275, "global_step": 624881, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.047348976135254, "global_step": 624882, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.045745611190796, "global_step": 624883, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0320682525634766, "global_step": 624884, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0093038082122803, "global_step": 624885, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9462591409683228, "global_step": 624886, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.014665126800537, "global_step": 624887, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.052791118621826, "global_step": 624888, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0177688598632812, "global_step": 624889, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.014338254928589, "global_step": 624890, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.951284646987915, "global_step": 624891, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9491870403289795, "global_step": 624892, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0172362327575684, "global_step": 624893, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0077109336853027, "global_step": 624894, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1047797203063965, "global_step": 624895, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9813408851623535, "global_step": 624896, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9810774326324463, "global_step": 624897, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0785388946533203, "global_step": 624898, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.02290678024292, "global_step": 624899, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.021547317504883, "global_step": 624900, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.026988983154297, "global_step": 624901, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.995074987411499, "global_step": 624902, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9764409065246582, "global_step": 624903, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.030073642730713, "global_step": 624904, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0753376483917236, "global_step": 624905, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9651997089385986, "global_step": 624906, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1221065521240234, "global_step": 624907, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0769846439361572, "global_step": 624908, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0623557567596436, "global_step": 624909, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0889089107513428, "global_step": 624910, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.071113109588623, "global_step": 624911, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.951282024383545, "global_step": 624912, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0619187355041504, "global_step": 624913, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.011888027191162, "global_step": 624914, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1081430912017822, "global_step": 624915, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0504050254821777, "global_step": 624916, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0395359992980957, "global_step": 624917, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9303643703460693, "global_step": 624918, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9866677522659302, "global_step": 624919, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9875659942626953, "global_step": 624920, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.976570963859558, "global_step": 624921, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0164358615875244, "global_step": 624922, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9968478679656982, "global_step": 624923, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9139043092727661, "global_step": 624924, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8949661254882812, "global_step": 624925, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9696269035339355, "global_step": 624926, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0455291271209717, "global_step": 624927, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9680155515670776, "global_step": 624928, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9955614805221558, "global_step": 624929, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9789066314697266, "global_step": 624930, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9889957904815674, "global_step": 624931, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9303160905838013, "global_step": 624932, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9961199760437012, "global_step": 624933, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0039420127868652, "global_step": 624934, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.015259265899658, "global_step": 624935, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0473992824554443, "global_step": 624936, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.009460926055908, "global_step": 624937, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9185676574707031, "global_step": 624938, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1024582386016846, "global_step": 624939, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.047797918319702, "global_step": 624940, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0246245861053467, "global_step": 624941, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9708577394485474, "global_step": 624942, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0894668102264404, "global_step": 624943, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9612274169921875, "global_step": 624944, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9640580415725708, "global_step": 624945, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0129759311676025, "global_step": 624946, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0568690299987793, "global_step": 624947, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.959028720855713, "global_step": 624948, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0600132942199707, "global_step": 624949, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.010776996612549, "global_step": 624950, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9742450714111328, "global_step": 624951, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0285935401916504, "global_step": 624952, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0860352516174316, "global_step": 624953, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.028221845626831, "global_step": 624954, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9801976680755615, "global_step": 624955, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.004755735397339, "global_step": 624956, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9726271629333496, "global_step": 624957, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9918460845947266, "global_step": 624958, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.916032314300537, "global_step": 624959, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9528322219848633, "global_step": 624960, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.002729654312134, "global_step": 624961, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0373666286468506, "global_step": 624962, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.102238655090332, "global_step": 624963, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.022754430770874, "global_step": 624964, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.00801944732666, "global_step": 624965, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.047987222671509, "global_step": 624966, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.07378888130188, "global_step": 624967, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.025975465774536, "global_step": 624968, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0155317783355713, "global_step": 624969, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0217795372009277, "global_step": 624970, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.068653106689453, "global_step": 624971, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.921181321144104, "global_step": 624972, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0427119731903076, "global_step": 624973, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0846238136291504, "global_step": 624974, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9225939512252808, "global_step": 624975, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.058690309524536, "global_step": 624976, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.973683476448059, "global_step": 624977, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9724587202072144, "global_step": 624978, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.044703245162964, "global_step": 624979, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9731508493423462, "global_step": 624980, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9651329517364502, "global_step": 624981, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9982879161834717, "global_step": 624982, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0104267597198486, "global_step": 624983, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9945123195648193, "global_step": 624984, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.045058488845825, "global_step": 624985, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1424148082733154, "global_step": 624986, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0096046924591064, "global_step": 624987, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.922818899154663, "global_step": 624988, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1100094318389893, "global_step": 624989, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0035762786865234, "global_step": 624990, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0323331356048584, "global_step": 624991, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9700303077697754, "global_step": 624992, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0012221336364746, "global_step": 624993, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.058903932571411, "global_step": 624994, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0197887420654297, "global_step": 624995, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0461697578430176, "global_step": 624996, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0268256664276123, "global_step": 624997, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.00185489654541, "global_step": 624998, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9578653573989868, "global_step": 624999, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0209877490997314, "global_step": 625000, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1073760986328125, "global_step": 625001, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9771676063537598, "global_step": 625002, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9702993631362915, "global_step": 625003, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0888993740081787, "global_step": 625004, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0474846363067627, "global_step": 625005, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.085899829864502, "global_step": 625006, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9763411283493042, "global_step": 625007, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0980942249298096, "global_step": 625008, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9524633884429932, "global_step": 625009, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9618815183639526, "global_step": 625010, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0144712924957275, "global_step": 625011, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.076167345046997, "global_step": 625012, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9834669828414917, "global_step": 625013, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.041869640350342, "global_step": 625014, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.051403284072876, "global_step": 625015, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9806448221206665, "global_step": 625016, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0515329837799072, "global_step": 625017, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0288710594177246, "global_step": 625018, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9902106523513794, "global_step": 625019, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0559470653533936, "global_step": 625020, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9988089799880981, "global_step": 625021, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0489349365234375, "global_step": 625022, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0206477642059326, "global_step": 625023, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.117126703262329, "global_step": 625024, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.019073963165283, "global_step": 625025, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9524413347244263, "global_step": 625026, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9455145597457886, "global_step": 625027, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.959097981452942, "global_step": 625028, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0784895420074463, "global_step": 625029, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.035039186477661, "global_step": 625030, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.006497621536255, "global_step": 625031, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9975265264511108, "global_step": 625032, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.004711866378784, "global_step": 625033, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.04685378074646, "global_step": 625034, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.050302505493164, "global_step": 625035, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.92832612991333, "global_step": 625036, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0412919521331787, "global_step": 625037, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9254732131958008, "global_step": 625038, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0414962768554688, "global_step": 625039, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.998131275177002, "global_step": 625040, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9904416799545288, "global_step": 625041, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.026752471923828, "global_step": 625042, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9448866844177246, "global_step": 625043, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0611259937286377, "global_step": 625044, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.103921413421631, "global_step": 625045, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9827945232391357, "global_step": 625046, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.902626633644104, "global_step": 625047, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9907821416854858, "global_step": 625048, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0938732624053955, "global_step": 625049, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.025007724761963, "global_step": 625050, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9473655223846436, "global_step": 625051, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0068647861480713, "global_step": 625052, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0362961292266846, "global_step": 625053, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.042951822280884, "global_step": 625054, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.001959800720215, "global_step": 625055, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0046536922454834, "global_step": 625056, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.002687692642212, "global_step": 625057, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.059471368789673, "global_step": 625058, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.085879325866699, "global_step": 625059, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9895020723342896, "global_step": 625060, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0018136501312256, "global_step": 625061, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0566647052764893, "global_step": 625062, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.10622501373291, "global_step": 625063, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9825187921524048, "global_step": 625064, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0174355506896973, "global_step": 625065, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.045602560043335, "global_step": 625066, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9738991260528564, "global_step": 625067, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9719526767730713, "global_step": 625068, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9622722864151, "global_step": 625069, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.027730941772461, "global_step": 625070, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.007345199584961, "global_step": 625071, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.00439453125, "global_step": 625072, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9505209922790527, "global_step": 625073, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.018402338027954, "global_step": 625074, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9821209907531738, "global_step": 625075, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9114539623260498, "global_step": 625076, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9598174095153809, "global_step": 625077, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9863967895507812, "global_step": 625078, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.019508123397827, "global_step": 625079, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.042018175125122, "global_step": 625080, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0191166400909424, "global_step": 625081, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.952991247177124, "global_step": 625082, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0343191623687744, "global_step": 625083, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.086319923400879, "global_step": 625084, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.119671106338501, "global_step": 625085, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.035166025161743, "global_step": 625086, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0231316089630127, "global_step": 625087, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0514068603515625, "global_step": 625088, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9450064897537231, "global_step": 625089, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0323824882507324, "global_step": 625090, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.060718536376953, "global_step": 625091, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9753191471099854, "global_step": 625092, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.018320083618164, "global_step": 625093, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0157296657562256, "global_step": 625094, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9416756629943848, "global_step": 625095, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0533459186553955, "global_step": 625096, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0008606910705566, "global_step": 625097, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1174509525299072, "global_step": 625098, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0600759983062744, "global_step": 625099, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0792410373687744, "global_step": 625100, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9423956871032715, "global_step": 625101, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.994943618774414, "global_step": 625102, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9810718297958374, "global_step": 625103, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0762720108032227, "global_step": 625104, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.082136869430542, "global_step": 625105, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.8991081714630127, "global_step": 625106, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.047074794769287, "global_step": 625107, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.1284446716308594, "global_step": 625108, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9413204193115234, "global_step": 625109, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9982483386993408, "global_step": 625110, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9908806085586548, "global_step": 625111, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9438530206680298, "global_step": 625112, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.087998867034912, "global_step": 625113, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0941593647003174, "global_step": 625114, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9300713539123535, "global_step": 625115, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.035292863845825, "global_step": 625116, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0207719802856445, "global_step": 625117, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0317320823669434, "global_step": 625118, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9874385595321655, "global_step": 625119, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0112693309783936, "global_step": 625120, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0325098037719727, "global_step": 625121, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9603369235992432, "global_step": 625122, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9823838472366333, "global_step": 625123, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9856077432632446, "global_step": 625124, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0149526596069336, "global_step": 625125, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.975040316581726, "global_step": 625126, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0258283615112305, "global_step": 625127, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0078487396240234, "global_step": 625128, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9609923362731934, "global_step": 625129, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9610854387283325, "global_step": 625130, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9662171602249146, "global_step": 625131, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9567569494247437, "global_step": 625132, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0389490127563477, "global_step": 625133, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.090900182723999, "global_step": 625134, "epoch": 993, "lr": 5e-05}
{"train_loss": 1.9310719966888428, "global_step": 625135, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0042099952697754, "global_step": 625136, "epoch": 993, "lr": 5e-05}
{"train_loss": 2.0046257972717285, "global_step": 625137, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.99037504196167, "global_step": 625138, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.030027389526367, "global_step": 625139, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9268019199371338, "global_step": 625140, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.929766297340393, "global_step": 625141, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.042224407196045, "global_step": 625142, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0298964977264404, "global_step": 625143, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9602330923080444, "global_step": 625144, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0269570350646973, "global_step": 625145, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.006937265396118, "global_step": 625146, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9654966592788696, "global_step": 625147, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.948508381843567, "global_step": 625148, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0795557498931885, "global_step": 625149, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.136106491088867, "global_step": 625150, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9041658639907837, "global_step": 625151, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.004342794418335, "global_step": 625152, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9339710474014282, "global_step": 625153, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9917616844177246, "global_step": 625154, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.033198356628418, "global_step": 625155, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0149855613708496, "global_step": 625156, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.95646333694458, "global_step": 625157, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0023984909057617, "global_step": 625158, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0592126846313477, "global_step": 625159, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9672857522964478, "global_step": 625160, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9122611284255981, "global_step": 625161, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9435458183288574, "global_step": 625162, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.982972264289856, "global_step": 625163, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9613889455795288, "global_step": 625164, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9273372888565063, "global_step": 625165, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0262036323547363, "global_step": 625166, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0113096237182617, "global_step": 625167, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9893038272857666, "global_step": 625168, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9647248983383179, "global_step": 625169, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.948372721672058, "global_step": 625170, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9073015451431274, "global_step": 625171, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9886428117752075, "global_step": 625172, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9952352046966553, "global_step": 625173, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9837002754211426, "global_step": 625174, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9952664375305176, "global_step": 625175, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0033388137817383, "global_step": 625176, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0493671894073486, "global_step": 625177, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9576663970947266, "global_step": 625178, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9055538177490234, "global_step": 625179, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9868282079696655, "global_step": 625180, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.991054654121399, "global_step": 625181, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0112898349761963, "global_step": 625182, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.049365282058716, "global_step": 625183, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.007909059524536, "global_step": 625184, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9412215948104858, "global_step": 625185, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0566067695617676, "global_step": 625186, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9998167753219604, "global_step": 625187, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.965716004371643, "global_step": 625188, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0495386123657227, "global_step": 625189, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9363632202148438, "global_step": 625190, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9278292655944824, "global_step": 625191, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0431089401245117, "global_step": 625192, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9634844064712524, "global_step": 625193, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9848586320877075, "global_step": 625194, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.951385498046875, "global_step": 625195, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.968564510345459, "global_step": 625196, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0065994262695312, "global_step": 625197, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.080629825592041, "global_step": 625198, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.977356195449829, "global_step": 625199, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.062889337539673, "global_step": 625200, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9690049886703491, "global_step": 625201, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9926166534423828, "global_step": 625202, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.081634521484375, "global_step": 625203, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.033024787902832, "global_step": 625204, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9600894451141357, "global_step": 625205, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.909532904624939, "global_step": 625206, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9113112688064575, "global_step": 625207, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.045083999633789, "global_step": 625208, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0428073406219482, "global_step": 625209, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9812114238739014, "global_step": 625210, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9996492862701416, "global_step": 625211, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9849648475646973, "global_step": 625212, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9630941152572632, "global_step": 625213, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0911741256713867, "global_step": 625214, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.006255865097046, "global_step": 625215, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.031808853149414, "global_step": 625216, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9194974899291992, "global_step": 625217, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.064939022064209, "global_step": 625218, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9420932531356812, "global_step": 625219, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0248184204101562, "global_step": 625220, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.034193754196167, "global_step": 625221, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0686607360839844, "global_step": 625222, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9534322023391724, "global_step": 625223, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0472686290740967, "global_step": 625224, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.974368929862976, "global_step": 625225, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9415374994277954, "global_step": 625226, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0523838996887207, "global_step": 625227, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0270087718963623, "global_step": 625228, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9506902694702148, "global_step": 625229, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.01900053024292, "global_step": 625230, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9872328042984009, "global_step": 625231, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0666615962982178, "global_step": 625232, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.970649003982544, "global_step": 625233, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0139756202697754, "global_step": 625234, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.015923023223877, "global_step": 625235, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.052119493484497, "global_step": 625236, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9536925554275513, "global_step": 625237, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0026681423187256, "global_step": 625238, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9633082151412964, "global_step": 625239, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9808050394058228, "global_step": 625240, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0024898052215576, "global_step": 625241, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.017014265060425, "global_step": 625242, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.028672218322754, "global_step": 625243, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9499526023864746, "global_step": 625244, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0196800231933594, "global_step": 625245, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.8931442499160767, "global_step": 625246, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.982180118560791, "global_step": 625247, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.022130012512207, "global_step": 625248, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.055039167404175, "global_step": 625249, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.03732967376709, "global_step": 625250, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0679140090942383, "global_step": 625251, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1153581142425537, "global_step": 625252, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9894551038742065, "global_step": 625253, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.993256688117981, "global_step": 625254, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.099510908126831, "global_step": 625255, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.019602060317993, "global_step": 625256, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.8849987983703613, "global_step": 625257, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9523814916610718, "global_step": 625258, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0143911838531494, "global_step": 625259, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9823334217071533, "global_step": 625260, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.04547381401062, "global_step": 625261, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.045841932296753, "global_step": 625262, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0254628658294678, "global_step": 625263, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.97731614112854, "global_step": 625264, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.07021164894104, "global_step": 625265, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0332703590393066, "global_step": 625266, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9208606481552124, "global_step": 625267, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.8977551460266113, "global_step": 625268, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9525587558746338, "global_step": 625269, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.922450304031372, "global_step": 625270, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9985333681106567, "global_step": 625271, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9764748811721802, "global_step": 625272, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.083310842514038, "global_step": 625273, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9336521625518799, "global_step": 625274, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0211706161499023, "global_step": 625275, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9958269596099854, "global_step": 625276, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.958306074142456, "global_step": 625277, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.930564522743225, "global_step": 625278, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9738683700561523, "global_step": 625279, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9218604564666748, "global_step": 625280, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.980332851409912, "global_step": 625281, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9275254011154175, "global_step": 625282, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.05192494392395, "global_step": 625283, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9954619407653809, "global_step": 625284, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9559001922607422, "global_step": 625285, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.003352403640747, "global_step": 625286, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0403659343719482, "global_step": 625287, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.008293390274048, "global_step": 625288, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9867193698883057, "global_step": 625289, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9955986738204956, "global_step": 625290, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9712022542953491, "global_step": 625291, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.039140224456787, "global_step": 625292, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9974515438079834, "global_step": 625293, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.022448778152466, "global_step": 625294, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0524773597717285, "global_step": 625295, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9512232542037964, "global_step": 625296, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0678446292877197, "global_step": 625297, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.948287844657898, "global_step": 625298, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0034737586975098, "global_step": 625299, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0316994190216064, "global_step": 625300, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9748212099075317, "global_step": 625301, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0555529594421387, "global_step": 625302, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.018965005874634, "global_step": 625303, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9658269882202148, "global_step": 625304, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.932997465133667, "global_step": 625305, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9789789915084839, "global_step": 625306, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.953843116760254, "global_step": 625307, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.097489833831787, "global_step": 625308, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9236336946487427, "global_step": 625309, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9738082885742188, "global_step": 625310, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9922921657562256, "global_step": 625311, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0058047771453857, "global_step": 625312, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0769224166870117, "global_step": 625313, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9924216270446777, "global_step": 625314, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9714027643203735, "global_step": 625315, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.980432391166687, "global_step": 625316, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0178921222686768, "global_step": 625317, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0033891201019287, "global_step": 625318, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0343716144561768, "global_step": 625319, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9968358278274536, "global_step": 625320, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.031496047973633, "global_step": 625321, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.978062391281128, "global_step": 625322, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.982830286026001, "global_step": 625323, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.027007579803467, "global_step": 625324, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.882234811782837, "global_step": 625325, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9661122560501099, "global_step": 625326, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9952080249786377, "global_step": 625327, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9589093923568726, "global_step": 625328, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0201666355133057, "global_step": 625329, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.02176570892334, "global_step": 625330, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9811334609985352, "global_step": 625331, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0107812881469727, "global_step": 625332, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.058797836303711, "global_step": 625333, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9439589977264404, "global_step": 625334, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.022728443145752, "global_step": 625335, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.975843071937561, "global_step": 625336, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.013719320297241, "global_step": 625337, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0748727321624756, "global_step": 625338, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0993080139160156, "global_step": 625339, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.027808427810669, "global_step": 625340, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0518505573272705, "global_step": 625341, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.023442029953003, "global_step": 625342, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9502449035644531, "global_step": 625343, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9699846506118774, "global_step": 625344, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.979470133781433, "global_step": 625345, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9624216556549072, "global_step": 625346, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9368278980255127, "global_step": 625347, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.029550552368164, "global_step": 625348, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0431771278381348, "global_step": 625349, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.8949247598648071, "global_step": 625350, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.024217128753662, "global_step": 625351, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9386069774627686, "global_step": 625352, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0076842308044434, "global_step": 625353, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.005202293395996, "global_step": 625354, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0055994987487793, "global_step": 625355, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9904993772506714, "global_step": 625356, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9988285303115845, "global_step": 625357, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.087657928466797, "global_step": 625358, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.923748254776001, "global_step": 625359, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0281765460968018, "global_step": 625360, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9915015697479248, "global_step": 625361, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9650777578353882, "global_step": 625362, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0363330841064453, "global_step": 625363, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.015218734741211, "global_step": 625364, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9870758056640625, "global_step": 625365, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.98505699634552, "global_step": 625366, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.935284972190857, "global_step": 625367, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9124714136123657, "global_step": 625368, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9613004922866821, "global_step": 625369, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.088932991027832, "global_step": 625370, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0035622119903564, "global_step": 625371, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9496651887893677, "global_step": 625372, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.070533514022827, "global_step": 625373, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9165453910827637, "global_step": 625374, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0448460578918457, "global_step": 625375, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.060499668121338, "global_step": 625376, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0877609252929688, "global_step": 625377, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9559036493301392, "global_step": 625378, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0136988162994385, "global_step": 625379, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9525225162506104, "global_step": 625380, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0103185176849365, "global_step": 625381, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0055062770843506, "global_step": 625382, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9093536138534546, "global_step": 625383, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9537452459335327, "global_step": 625384, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9959638118743896, "global_step": 625385, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9999077320098877, "global_step": 625386, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9549585580825806, "global_step": 625387, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0678091049194336, "global_step": 625388, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0194602012634277, "global_step": 625389, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9823873043060303, "global_step": 625390, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.021634578704834, "global_step": 625391, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0545318126678467, "global_step": 625392, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9748605489730835, "global_step": 625393, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9550358057022095, "global_step": 625394, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9863977432250977, "global_step": 625395, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0065536499023438, "global_step": 625396, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9956063032150269, "global_step": 625397, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9880045652389526, "global_step": 625398, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9490219354629517, "global_step": 625399, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0783069133758545, "global_step": 625400, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9823755025863647, "global_step": 625401, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.058199644088745, "global_step": 625402, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.988926887512207, "global_step": 625403, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0411906242370605, "global_step": 625404, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9396419525146484, "global_step": 625405, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1215415000915527, "global_step": 625406, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0083436965942383, "global_step": 625407, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9655463695526123, "global_step": 625408, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0031514167785645, "global_step": 625409, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.069767713546753, "global_step": 625410, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9890260696411133, "global_step": 625411, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0128068923950195, "global_step": 625412, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0479578971862793, "global_step": 625413, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.999651551246643, "global_step": 625414, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.009816884994507, "global_step": 625415, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9521442651748657, "global_step": 625416, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.078218936920166, "global_step": 625417, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.081916332244873, "global_step": 625418, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.998980164527893, "global_step": 625419, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.107137441635132, "global_step": 625420, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9975956678390503, "global_step": 625421, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.905617594718933, "global_step": 625422, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.007446527481079, "global_step": 625423, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9837806224822998, "global_step": 625424, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.965081810951233, "global_step": 625425, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9826090335845947, "global_step": 625426, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0321261882781982, "global_step": 625427, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.010256290435791, "global_step": 625428, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9765299558639526, "global_step": 625429, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0839202404022217, "global_step": 625430, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.953033208847046, "global_step": 625431, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.978635311126709, "global_step": 625432, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9841943979263306, "global_step": 625433, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.956367015838623, "global_step": 625434, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9219918251037598, "global_step": 625435, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.027130126953125, "global_step": 625436, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9997658729553223, "global_step": 625437, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.071577548980713, "global_step": 625438, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0297019481658936, "global_step": 625439, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0315606594085693, "global_step": 625440, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0879271030426025, "global_step": 625441, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.95481538772583, "global_step": 625442, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0211567878723145, "global_step": 625443, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0088858604431152, "global_step": 625444, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.062023878097534, "global_step": 625445, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9746534824371338, "global_step": 625446, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9961248636245728, "global_step": 625447, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9348347187042236, "global_step": 625448, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0396597385406494, "global_step": 625449, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9613242149353027, "global_step": 625450, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0042386054992676, "global_step": 625451, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.015800714492798, "global_step": 625452, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9979586601257324, "global_step": 625453, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0146546363830566, "global_step": 625454, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.948524832725525, "global_step": 625455, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9741312265396118, "global_step": 625456, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0055558681488037, "global_step": 625457, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9567146301269531, "global_step": 625458, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.072573661804199, "global_step": 625459, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9876203536987305, "global_step": 625460, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9640772342681885, "global_step": 625461, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0370144844055176, "global_step": 625462, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0161373615264893, "global_step": 625463, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0064172744750977, "global_step": 625464, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.012125015258789, "global_step": 625465, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9840562343597412, "global_step": 625466, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.970325231552124, "global_step": 625467, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9379794597625732, "global_step": 625468, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.182262420654297, "global_step": 625469, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0073211193084717, "global_step": 625470, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9000985622406006, "global_step": 625471, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9933538436889648, "global_step": 625472, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.04962158203125, "global_step": 625473, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0429718494415283, "global_step": 625474, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0226337909698486, "global_step": 625475, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0342864990234375, "global_step": 625476, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.029681444168091, "global_step": 625477, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9732578992843628, "global_step": 625478, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9538850784301758, "global_step": 625479, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0014052391052246, "global_step": 625480, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.007112741470337, "global_step": 625481, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9364064931869507, "global_step": 625482, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.043948173522949, "global_step": 625483, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.922497272491455, "global_step": 625484, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.010915517807007, "global_step": 625485, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0343315601348877, "global_step": 625486, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9258992671966553, "global_step": 625487, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9836004972457886, "global_step": 625488, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9732069969177246, "global_step": 625489, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9444026947021484, "global_step": 625490, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9992589950561523, "global_step": 625491, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0223491191864014, "global_step": 625492, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.082399606704712, "global_step": 625493, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0684826374053955, "global_step": 625494, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.984002947807312, "global_step": 625495, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9945069551467896, "global_step": 625496, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.005589723587036, "global_step": 625497, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.054978370666504, "global_step": 625498, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9739693403244019, "global_step": 625499, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.961912751197815, "global_step": 625500, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9747213125228882, "global_step": 625501, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9920756816864014, "global_step": 625502, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0885183811187744, "global_step": 625503, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0480217933654785, "global_step": 625504, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0140719413757324, "global_step": 625505, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9830427169799805, "global_step": 625506, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.060678243637085, "global_step": 625507, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0033047199249268, "global_step": 625508, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0050902366638184, "global_step": 625509, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9874467849731445, "global_step": 625510, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9484845399856567, "global_step": 625511, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.012481451034546, "global_step": 625512, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1215720176696777, "global_step": 625513, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9514487981796265, "global_step": 625514, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0999176502227783, "global_step": 625515, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0637550354003906, "global_step": 625516, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0384464263916016, "global_step": 625517, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.003415584564209, "global_step": 625518, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0063934326171875, "global_step": 625519, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9265919923782349, "global_step": 625520, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9812889099121094, "global_step": 625521, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9186922311782837, "global_step": 625522, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.965463399887085, "global_step": 625523, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9268403053283691, "global_step": 625524, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9911777973175049, "global_step": 625525, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9007304906845093, "global_step": 625526, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0715928077697754, "global_step": 625527, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.034470319747925, "global_step": 625528, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.991106629371643, "global_step": 625529, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0282719135284424, "global_step": 625530, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0580170154571533, "global_step": 625531, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0751662254333496, "global_step": 625532, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.060246706008911, "global_step": 625533, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.043302059173584, "global_step": 625534, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.031904697418213, "global_step": 625535, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9815075397491455, "global_step": 625536, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0054962635040283, "global_step": 625537, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9510200023651123, "global_step": 625538, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.002117156982422, "global_step": 625539, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9668245315551758, "global_step": 625540, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.974971890449524, "global_step": 625541, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9337739944458008, "global_step": 625542, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9360123872756958, "global_step": 625543, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9804993867874146, "global_step": 625544, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9797999858856201, "global_step": 625545, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.004211902618408, "global_step": 625546, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9628307819366455, "global_step": 625547, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0434021949768066, "global_step": 625548, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9513434171676636, "global_step": 625549, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9865829944610596, "global_step": 625550, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0432329177856445, "global_step": 625551, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9955850839614868, "global_step": 625552, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9443703889846802, "global_step": 625553, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0634074211120605, "global_step": 625554, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9310222864151, "global_step": 625555, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.035287618637085, "global_step": 625556, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.917574405670166, "global_step": 625557, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9963191747665405, "global_step": 625558, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0784802436828613, "global_step": 625559, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9946850538253784, "global_step": 625560, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0445642471313477, "global_step": 625561, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0065665245056152, "global_step": 625562, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0524747371673584, "global_step": 625563, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9358937740325928, "global_step": 625564, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.004365921020508, "global_step": 625565, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0533485412597656, "global_step": 625566, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9623198509216309, "global_step": 625567, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.064352512359619, "global_step": 625568, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.8871476650238037, "global_step": 625569, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9567193984985352, "global_step": 625570, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.969454288482666, "global_step": 625571, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.935163140296936, "global_step": 625572, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0753371715545654, "global_step": 625573, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9912296533584595, "global_step": 625574, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0341577529907227, "global_step": 625575, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9038643836975098, "global_step": 625576, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9411073923110962, "global_step": 625577, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.027426242828369, "global_step": 625578, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0156378746032715, "global_step": 625579, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.084256649017334, "global_step": 625580, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9334312677383423, "global_step": 625581, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9216032028198242, "global_step": 625582, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.057816743850708, "global_step": 625583, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9366495609283447, "global_step": 625584, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9762018918991089, "global_step": 625585, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0718436241149902, "global_step": 625586, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0132625102996826, "global_step": 625587, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0471293926239014, "global_step": 625588, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0107710361480713, "global_step": 625589, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.030071973800659, "global_step": 625590, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9246175289154053, "global_step": 625591, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9983803033828735, "global_step": 625592, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9836558103561401, "global_step": 625593, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9958586692810059, "global_step": 625594, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0401220321655273, "global_step": 625595, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9437572956085205, "global_step": 625596, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9935003519058228, "global_step": 625597, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0715019702911377, "global_step": 625598, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0254833698272705, "global_step": 625599, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9910197257995605, "global_step": 625600, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.939017415046692, "global_step": 625601, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.93513023853302, "global_step": 625602, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9122037887573242, "global_step": 625603, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9580175876617432, "global_step": 625604, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.036897659301758, "global_step": 625605, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9582664966583252, "global_step": 625606, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.990351676940918, "global_step": 625607, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0906872749328613, "global_step": 625608, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9604623317718506, "global_step": 625609, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9699409008026123, "global_step": 625610, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0353240966796875, "global_step": 625611, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9814871549606323, "global_step": 625612, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0002267360687256, "global_step": 625613, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9712908267974854, "global_step": 625614, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0457258224487305, "global_step": 625615, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9815762042999268, "global_step": 625616, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.144639492034912, "global_step": 625617, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9646732807159424, "global_step": 625618, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.934298038482666, "global_step": 625619, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.092780113220215, "global_step": 625620, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9103119373321533, "global_step": 625621, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9949924945831299, "global_step": 625622, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.8429597616195679, "global_step": 625623, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0779523849487305, "global_step": 625624, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.051025152206421, "global_step": 625625, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.040029525756836, "global_step": 625626, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9164700508117676, "global_step": 625627, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9332637786865234, "global_step": 625628, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9948161840438843, "global_step": 625629, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.050898790359497, "global_step": 625630, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9742180109024048, "global_step": 625631, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9968111515045166, "global_step": 625632, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0234744548797607, "global_step": 625633, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0036072731018066, "global_step": 625634, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.985729455947876, "global_step": 625635, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1015560626983643, "global_step": 625636, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9616392850875854, "global_step": 625637, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0022404193878174, "global_step": 625638, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.040860176086426, "global_step": 625639, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9885239601135254, "global_step": 625640, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9532387256622314, "global_step": 625641, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.025864601135254, "global_step": 625642, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.001695156097412, "global_step": 625643, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0188565254211426, "global_step": 625644, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0064380168914795, "global_step": 625645, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.003373384475708, "global_step": 625646, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9628303050994873, "global_step": 625647, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0256288051605225, "global_step": 625648, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0132927894592285, "global_step": 625649, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9235968589782715, "global_step": 625650, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0178661346435547, "global_step": 625651, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.016603946685791, "global_step": 625652, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9674931764602661, "global_step": 625653, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0098717212677, "global_step": 625654, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0039567947387695, "global_step": 625655, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.98441743850708, "global_step": 625656, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0003793239593506, "global_step": 625657, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0362672805786133, "global_step": 625658, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0037693977355957, "global_step": 625659, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0538992881774902, "global_step": 625660, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0526840686798096, "global_step": 625661, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0117290019989014, "global_step": 625662, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.036100387573242, "global_step": 625663, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.070542335510254, "global_step": 625664, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0286812782287598, "global_step": 625665, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9731365442276, "global_step": 625666, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.027029275894165, "global_step": 625667, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.046260356903076, "global_step": 625668, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9857697486877441, "global_step": 625669, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.019988775253296, "global_step": 625670, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0560851097106934, "global_step": 625671, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9565410614013672, "global_step": 625672, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9530359506607056, "global_step": 625673, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9960417747497559, "global_step": 625674, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0092461109161377, "global_step": 625675, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9107913970947266, "global_step": 625676, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0134875774383545, "global_step": 625677, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.926450252532959, "global_step": 625678, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9936020374298096, "global_step": 625679, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.053433895111084, "global_step": 625680, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.030144453048706, "global_step": 625681, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9844213724136353, "global_step": 625682, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9850869178771973, "global_step": 625683, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9979861974716187, "global_step": 625684, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.000706434249878, "global_step": 625685, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.984717845916748, "global_step": 625686, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.029923439025879, "global_step": 625687, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9933233261108398, "global_step": 625688, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0254135131835938, "global_step": 625689, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0896522998809814, "global_step": 625690, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.976902961730957, "global_step": 625691, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.025869131088257, "global_step": 625692, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.969411015510559, "global_step": 625693, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0209553241729736, "global_step": 625694, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0549838542938232, "global_step": 625695, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9847368001937866, "global_step": 625696, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0051982402801514, "global_step": 625697, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0885121822357178, "global_step": 625698, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0805740356445312, "global_step": 625699, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.009104013442993, "global_step": 625700, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.040724515914917, "global_step": 625701, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0550696849823, "global_step": 625702, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9892375469207764, "global_step": 625703, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.049909830093384, "global_step": 625704, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9775631427764893, "global_step": 625705, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0128486156463623, "global_step": 625706, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0789954662323, "global_step": 625707, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.995269536972046, "global_step": 625708, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.020362615585327, "global_step": 625709, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.997841238975525, "global_step": 625710, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0263235569000244, "global_step": 625711, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.003253936767578, "global_step": 625712, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0097594261169434, "global_step": 625713, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.138335704803467, "global_step": 625714, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.958685040473938, "global_step": 625715, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.026801109313965, "global_step": 625716, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9098951816558838, "global_step": 625717, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9209150075912476, "global_step": 625718, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.058871269226074, "global_step": 625719, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0323684215545654, "global_step": 625720, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.937165379524231, "global_step": 625721, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.036672830581665, "global_step": 625722, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9937037229537964, "global_step": 625723, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.02323842048645, "global_step": 625724, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0113625526428223, "global_step": 625725, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.998833417892456, "global_step": 625726, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0245418548583984, "global_step": 625727, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9887826442718506, "global_step": 625728, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.013275146484375, "global_step": 625729, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9608895778656006, "global_step": 625730, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0563340187072754, "global_step": 625731, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9757730960845947, "global_step": 625732, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9737277030944824, "global_step": 625733, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.051177740097046, "global_step": 625734, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.051079034805298, "global_step": 625735, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0385243892669678, "global_step": 625736, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0352582931518555, "global_step": 625737, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9951081275939941, "global_step": 625738, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9298325777053833, "global_step": 625739, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.063347101211548, "global_step": 625740, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.011788845062256, "global_step": 625741, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9329249858856201, "global_step": 625742, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0670764446258545, "global_step": 625743, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.07539701461792, "global_step": 625744, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9707268476486206, "global_step": 625745, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9812157154083252, "global_step": 625746, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0107860565185547, "global_step": 625747, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.100168228149414, "global_step": 625748, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9656858444213867, "global_step": 625749, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0100390911102295, "global_step": 625750, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0754642486572266, "global_step": 625751, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9111379384994507, "global_step": 625752, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0036277770996094, "global_step": 625753, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0273382663726807, "global_step": 625754, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9786179065704346, "global_step": 625755, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9907653331756592, "global_step": 625756, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0974743366241455, "global_step": 625757, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9567325115203857, "global_step": 625758, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.052877902984619, "global_step": 625759, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0508227348327637, "global_step": 625760, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9861414432525635, "global_step": 625761, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9492146968841553, "global_step": 625762, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9440253973007202, "global_step": 625763, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9657927751541138, "global_step": 625764, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0018162727355957, "global_step": 625765, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.006295680999756, "global_step": 625766, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9909451007843018, "global_step": 625767, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0260581970214844, "global_step": 625768, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.056405544281006, "global_step": 625769, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.061326503753662, "global_step": 625770, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9235185384750366, "global_step": 625771, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9885846376419067, "global_step": 625772, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.04182767868042, "global_step": 625773, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1323277950286865, "global_step": 625774, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.964400053024292, "global_step": 625775, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.053107976913452, "global_step": 625776, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0308995246887207, "global_step": 625777, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9627639055252075, "global_step": 625778, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.974194049835205, "global_step": 625779, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.025696039199829, "global_step": 625780, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0040082931518555, "global_step": 625781, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9778341054916382, "global_step": 625782, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.025209903717041, "global_step": 625783, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0656580924987793, "global_step": 625784, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9958442449569702, "global_step": 625785, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9429574012756348, "global_step": 625786, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0656638145446777, "global_step": 625787, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0347230434417725, "global_step": 625788, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0168263912200928, "global_step": 625789, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9960393905639648, "global_step": 625790, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9948062896728516, "global_step": 625791, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.051290512084961, "global_step": 625792, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0034172534942627, "global_step": 625793, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9714820384979248, "global_step": 625794, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9541041851043701, "global_step": 625795, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0189201831817627, "global_step": 625796, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0042152404785156, "global_step": 625797, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0158255100250244, "global_step": 625798, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.919400691986084, "global_step": 625799, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0180861949920654, "global_step": 625800, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.008699893951416, "global_step": 625801, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0428810119628906, "global_step": 625802, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.056056499481201, "global_step": 625803, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0024662017822266, "global_step": 625804, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9910616874694824, "global_step": 625805, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9945166110992432, "global_step": 625806, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9872626066207886, "global_step": 625807, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0062177181243896, "global_step": 625808, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0143840312957764, "global_step": 625809, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.031851053237915, "global_step": 625810, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.03129243850708, "global_step": 625811, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9997811317443848, "global_step": 625812, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.005190134048462, "global_step": 625813, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.060126304626465, "global_step": 625814, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9974703788757324, "global_step": 625815, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9550623893737793, "global_step": 625816, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.944638729095459, "global_step": 625817, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9449248313903809, "global_step": 625818, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0033791065216064, "global_step": 625819, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.034440040588379, "global_step": 625820, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.978424072265625, "global_step": 625821, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9797109365463257, "global_step": 625822, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.8966689109802246, "global_step": 625823, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.999060869216919, "global_step": 625824, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.042537212371826, "global_step": 625825, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9665262699127197, "global_step": 625826, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0092790126800537, "global_step": 625827, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0540103912353516, "global_step": 625828, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9389090538024902, "global_step": 625829, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9569460153579712, "global_step": 625830, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.049058675765991, "global_step": 625831, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0165915489196777, "global_step": 625832, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0566062927246094, "global_step": 625833, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.916399359703064, "global_step": 625834, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.953155517578125, "global_step": 625835, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9198888540267944, "global_step": 625836, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9672824144363403, "global_step": 625837, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.055321216583252, "global_step": 625838, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0070395469665527, "global_step": 625839, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0110723972320557, "global_step": 625840, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.063267946243286, "global_step": 625841, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.044497013092041, "global_step": 625842, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9983603954315186, "global_step": 625843, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0490236282348633, "global_step": 625844, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.942602276802063, "global_step": 625845, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0663740634918213, "global_step": 625846, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.006861925125122, "global_step": 625847, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.101550340652466, "global_step": 625848, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.972863793373108, "global_step": 625849, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0198588371276855, "global_step": 625850, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.933690071105957, "global_step": 625851, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.961277961730957, "global_step": 625852, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0653390884399414, "global_step": 625853, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.992098093032837, "global_step": 625854, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9700487852096558, "global_step": 625855, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0046744346618652, "global_step": 625856, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0950028896331787, "global_step": 625857, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.016364336013794, "global_step": 625858, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9766721725463867, "global_step": 625859, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9850889444351196, "global_step": 625860, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0543923377990723, "global_step": 625861, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0539581775665283, "global_step": 625862, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.014802932739258, "global_step": 625863, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0352396965026855, "global_step": 625864, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.047816276550293, "global_step": 625865, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1460158824920654, "global_step": 625866, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9433674812316895, "global_step": 625867, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0212082862854004, "global_step": 625868, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0362794399261475, "global_step": 625869, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.015064001083374, "global_step": 625870, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.019619941711426, "global_step": 625871, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9978663921356201, "global_step": 625872, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.954382300376892, "global_step": 625873, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0934479236602783, "global_step": 625874, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0493364334106445, "global_step": 625875, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9254883527755737, "global_step": 625876, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.990768313407898, "global_step": 625877, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.088331460952759, "global_step": 625878, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0026469230651855, "global_step": 625879, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9805212020874023, "global_step": 625880, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.022454261779785, "global_step": 625881, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0272927284240723, "global_step": 625882, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0032050609588623, "global_step": 625883, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0087943077087402, "global_step": 625884, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0009000301361084, "global_step": 625885, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.087616205215454, "global_step": 625886, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0085928440093994, "global_step": 625887, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.964463472366333, "global_step": 625888, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0520317554473877, "global_step": 625889, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.094212770462036, "global_step": 625890, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9037201404571533, "global_step": 625891, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.94312584400177, "global_step": 625892, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.054360866546631, "global_step": 625893, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0465340614318848, "global_step": 625894, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9958853721618652, "global_step": 625895, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0175423622131348, "global_step": 625896, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9586106538772583, "global_step": 625897, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0455167293548584, "global_step": 625898, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9272524118423462, "global_step": 625899, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.974194884300232, "global_step": 625900, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.027517795562744, "global_step": 625901, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9728282690048218, "global_step": 625902, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.041740894317627, "global_step": 625903, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.087003469467163, "global_step": 625904, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0187621116638184, "global_step": 625905, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9935214519500732, "global_step": 625906, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0637705326080322, "global_step": 625907, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9575169086456299, "global_step": 625908, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.038442373275757, "global_step": 625909, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0264551639556885, "global_step": 625910, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.013218402862549, "global_step": 625911, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9727336168289185, "global_step": 625912, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.031435012817383, "global_step": 625913, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.100619077682495, "global_step": 625914, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9037672281265259, "global_step": 625915, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0180044174194336, "global_step": 625916, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9964120388031006, "global_step": 625917, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.061265468597412, "global_step": 625918, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.051534652709961, "global_step": 625919, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0382230281829834, "global_step": 625920, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.024144411087036, "global_step": 625921, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9864543676376343, "global_step": 625922, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.8639304637908936, "global_step": 625923, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.035675525665283, "global_step": 625924, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0335335731506348, "global_step": 625925, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.986257791519165, "global_step": 625926, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9682350158691406, "global_step": 625927, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9957530498504639, "global_step": 625928, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.034398078918457, "global_step": 625929, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0515122413635254, "global_step": 625930, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0590224266052246, "global_step": 625931, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9950430393218994, "global_step": 625932, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0647799968719482, "global_step": 625933, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9511034488677979, "global_step": 625934, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9374690055847168, "global_step": 625935, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.981046199798584, "global_step": 625936, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.978520393371582, "global_step": 625937, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.940871000289917, "global_step": 625938, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9811807870864868, "global_step": 625939, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.024974822998047, "global_step": 625940, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0246284008026123, "global_step": 625941, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0197806358337402, "global_step": 625942, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0403778553009033, "global_step": 625943, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9529953002929688, "global_step": 625944, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.007136583328247, "global_step": 625945, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9495372772216797, "global_step": 625946, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9837852716445923, "global_step": 625947, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.028745412826538, "global_step": 625948, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9969247579574585, "global_step": 625949, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0646042823791504, "global_step": 625950, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.999747633934021, "global_step": 625951, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0444459915161133, "global_step": 625952, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0583600997924805, "global_step": 625953, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9539790153503418, "global_step": 625954, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.039578676223755, "global_step": 625955, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0454304218292236, "global_step": 625956, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9817988872528076, "global_step": 625957, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0279481410980225, "global_step": 625958, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.002271890640259, "global_step": 625959, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0470423698425293, "global_step": 625960, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0308263301849365, "global_step": 625961, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.041816473007202, "global_step": 625962, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.963641881942749, "global_step": 625963, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9919856786727905, "global_step": 625964, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.084890842437744, "global_step": 625965, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.924087405204773, "global_step": 625966, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0087392330169678, "global_step": 625967, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.005099058151245, "global_step": 625968, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.886439323425293, "global_step": 625969, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9605425596237183, "global_step": 625970, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0396106243133545, "global_step": 625971, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0571610927581787, "global_step": 625972, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9996240139007568, "global_step": 625973, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9580780267715454, "global_step": 625974, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0266029834747314, "global_step": 625975, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.940281629562378, "global_step": 625976, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9629433155059814, "global_step": 625977, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0145957469940186, "global_step": 625978, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9934312105178833, "global_step": 625979, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0044775009155273, "global_step": 625980, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.996217966079712, "global_step": 625981, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.055896043777466, "global_step": 625982, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.972154140472412, "global_step": 625983, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.979434847831726, "global_step": 625984, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9310013055801392, "global_step": 625985, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0938785076141357, "global_step": 625986, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0134167671203613, "global_step": 625987, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.045123338699341, "global_step": 625988, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9720187187194824, "global_step": 625989, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0884647369384766, "global_step": 625990, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1104884147644043, "global_step": 625991, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9870789051055908, "global_step": 625992, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9300891160964966, "global_step": 625993, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.00498104095459, "global_step": 625994, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.020995616912842, "global_step": 625995, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0620861053466797, "global_step": 625996, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9683640003204346, "global_step": 625997, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.882109522819519, "global_step": 625998, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0101492404937744, "global_step": 625999, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9864915609359741, "global_step": 626000, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.050173282623291, "global_step": 626001, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9226534366607666, "global_step": 626002, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0221850872039795, "global_step": 626003, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9594351053237915, "global_step": 626004, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9641664028167725, "global_step": 626005, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0875697135925293, "global_step": 626006, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0699312686920166, "global_step": 626007, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.050398588180542, "global_step": 626008, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.042207717895508, "global_step": 626009, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.990335464477539, "global_step": 626010, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0301897525787354, "global_step": 626011, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.004091501235962, "global_step": 626012, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0164148807525635, "global_step": 626013, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0070338249206543, "global_step": 626014, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9737637042999268, "global_step": 626015, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9788818359375, "global_step": 626016, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.06646466255188, "global_step": 626017, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0807266235351562, "global_step": 626018, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.095508575439453, "global_step": 626019, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.073878288269043, "global_step": 626020, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0464353561401367, "global_step": 626021, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.989851474761963, "global_step": 626022, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0056803226470947, "global_step": 626023, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.984215497970581, "global_step": 626024, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9603644609451294, "global_step": 626025, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.040114402770996, "global_step": 626026, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9905462265014648, "global_step": 626027, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.061032772064209, "global_step": 626028, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9922689199447632, "global_step": 626029, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9706013202667236, "global_step": 626030, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.006641149520874, "global_step": 626031, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0836880207061768, "global_step": 626032, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0228183269500732, "global_step": 626033, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0219643115997314, "global_step": 626034, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0295658111572266, "global_step": 626035, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0302093029022217, "global_step": 626036, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.970159649848938, "global_step": 626037, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9731258153915405, "global_step": 626038, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.030465602874756, "global_step": 626039, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.930962085723877, "global_step": 626040, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0018248558044434, "global_step": 626041, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.015305519104004, "global_step": 626042, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0716700553894043, "global_step": 626043, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.051957368850708, "global_step": 626044, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9993505477905273, "global_step": 626045, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9985443353652954, "global_step": 626046, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.003129482269287, "global_step": 626047, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0339794158935547, "global_step": 626048, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0423269271850586, "global_step": 626049, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0736196041107178, "global_step": 626050, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.998133659362793, "global_step": 626051, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0081117153167725, "global_step": 626052, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0468595027923584, "global_step": 626053, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9909193515777588, "global_step": 626054, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9546762704849243, "global_step": 626055, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.980426549911499, "global_step": 626056, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0748214721679688, "global_step": 626057, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.025235652923584, "global_step": 626058, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0816445350646973, "global_step": 626059, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9879649877548218, "global_step": 626060, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0152361392974854, "global_step": 626061, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9263173341751099, "global_step": 626062, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.002683162689209, "global_step": 626063, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9734678268432617, "global_step": 626064, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.997458815574646, "global_step": 626065, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.001971483230591, "global_step": 626066, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0267815589904785, "global_step": 626067, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9987421035766602, "global_step": 626068, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.064330816268921, "global_step": 626069, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.977959394454956, "global_step": 626070, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9826771020889282, "global_step": 626071, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9724727869033813, "global_step": 626072, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0253937244415283, "global_step": 626073, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0044500827789307, "global_step": 626074, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.03006911277771, "global_step": 626075, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.041746139526367, "global_step": 626076, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9933704137802124, "global_step": 626077, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.968603253364563, "global_step": 626078, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9542443752288818, "global_step": 626079, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0376691818237305, "global_step": 626080, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9825892448425293, "global_step": 626081, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9005461931228638, "global_step": 626082, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9731676578521729, "global_step": 626083, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1303701400756836, "global_step": 626084, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0321426391601562, "global_step": 626085, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.064073324203491, "global_step": 626086, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1312642097473145, "global_step": 626087, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9903342723846436, "global_step": 626088, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.054500102996826, "global_step": 626089, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9502193927764893, "global_step": 626090, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9327342510223389, "global_step": 626091, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0122263431549072, "global_step": 626092, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9952588081359863, "global_step": 626093, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0244507789611816, "global_step": 626094, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.005319833755493, "global_step": 626095, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0470423698425293, "global_step": 626096, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0730152130126953, "global_step": 626097, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.1089911460876465, "global_step": 626098, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9894108772277832, "global_step": 626099, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.9967613220214844, "global_step": 626100, "epoch": 994, "lr": 5e-05}
{"train_loss": 1.981203556060791, "global_step": 626101, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.023087501525879, "global_step": 626102, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0152535438537598, "global_step": 626103, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0176796913146973, "global_step": 626104, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.0035102367401123, "global_step": 626105, "epoch": 994, "lr": 5e-05}
{"train_loss": 2.039706230163574, "global_step": 626106, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9898791313171387, "global_step": 626107, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.046298027038574, "global_step": 626108, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.082843542098999, "global_step": 626109, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0373098850250244, "global_step": 626110, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.065264940261841, "global_step": 626111, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9508434534072876, "global_step": 626112, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9498164653778076, "global_step": 626113, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8742363452911377, "global_step": 626114, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.994476556777954, "global_step": 626115, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9746167659759521, "global_step": 626116, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9823009967803955, "global_step": 626117, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0283560752868652, "global_step": 626118, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9065381288528442, "global_step": 626119, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.965399980545044, "global_step": 626120, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9130772352218628, "global_step": 626121, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.98665452003479, "global_step": 626122, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9108086824417114, "global_step": 626123, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.00770902633667, "global_step": 626124, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.973616123199463, "global_step": 626125, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0544466972351074, "global_step": 626126, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9785102605819702, "global_step": 626127, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.972450852394104, "global_step": 626128, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.065418004989624, "global_step": 626129, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0058741569519043, "global_step": 626130, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0719292163848877, "global_step": 626131, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.95607328414917, "global_step": 626132, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9525315761566162, "global_step": 626133, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.016967296600342, "global_step": 626134, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9998881816864014, "global_step": 626135, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9115498065948486, "global_step": 626136, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9788827896118164, "global_step": 626137, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9319679737091064, "global_step": 626138, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9585777521133423, "global_step": 626139, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0643670558929443, "global_step": 626140, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9766936302185059, "global_step": 626141, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.005880355834961, "global_step": 626142, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0497519969940186, "global_step": 626143, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9524590969085693, "global_step": 626144, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9149645566940308, "global_step": 626145, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9303985834121704, "global_step": 626146, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.983933925628662, "global_step": 626147, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0199134349823, "global_step": 626148, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0118255615234375, "global_step": 626149, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9401640892028809, "global_step": 626150, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.013092517852783, "global_step": 626151, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9225713014602661, "global_step": 626152, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.949534296989441, "global_step": 626153, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0338046550750732, "global_step": 626154, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9970364570617676, "global_step": 626155, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0033817291259766, "global_step": 626156, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0038764476776123, "global_step": 626157, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9368467330932617, "global_step": 626158, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.048151731491089, "global_step": 626159, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9787625074386597, "global_step": 626160, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9956134557724, "global_step": 626161, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9744999408721924, "global_step": 626162, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9056622982025146, "global_step": 626163, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0058999061584473, "global_step": 626164, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9821853637695312, "global_step": 626165, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0311272144317627, "global_step": 626166, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9917747974395752, "global_step": 626167, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0019073486328125, "global_step": 626168, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.06146240234375, "global_step": 626169, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0416982173919678, "global_step": 626170, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0167367458343506, "global_step": 626171, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0985805988311768, "global_step": 626172, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0346291065216064, "global_step": 626173, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.004019021987915, "global_step": 626174, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0376052856445312, "global_step": 626175, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0552124977111816, "global_step": 626176, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9756876230239868, "global_step": 626177, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9801489114761353, "global_step": 626178, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0374338626861572, "global_step": 626179, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.07241153717041, "global_step": 626180, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.059128522872925, "global_step": 626181, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.025575876235962, "global_step": 626182, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0012614727020264, "global_step": 626183, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0116546154022217, "global_step": 626184, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9434758424758911, "global_step": 626185, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9543009996414185, "global_step": 626186, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0170609951019287, "global_step": 626187, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9009634256362915, "global_step": 626188, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9649995565414429, "global_step": 626189, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0215413570404053, "global_step": 626190, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9769465923309326, "global_step": 626191, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9808757305145264, "global_step": 626192, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0502588748931885, "global_step": 626193, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0078682899475098, "global_step": 626194, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.003095865249634, "global_step": 626195, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.971362829208374, "global_step": 626196, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9461350440979004, "global_step": 626197, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.040187120437622, "global_step": 626198, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.011593818664551, "global_step": 626199, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.018531322479248, "global_step": 626200, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9670531749725342, "global_step": 626201, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.963810920715332, "global_step": 626202, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0160672664642334, "global_step": 626203, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.032108783721924, "global_step": 626204, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.005125045776367, "global_step": 626205, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9589606523513794, "global_step": 626206, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8754547834396362, "global_step": 626207, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9284855127334595, "global_step": 626208, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.032364845275879, "global_step": 626209, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.006241798400879, "global_step": 626210, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.069894313812256, "global_step": 626211, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9688833951950073, "global_step": 626212, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.036640167236328, "global_step": 626213, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.001008987426758, "global_step": 626214, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.036895751953125, "global_step": 626215, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.953154444694519, "global_step": 626216, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.035292148590088, "global_step": 626217, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.023707866668701, "global_step": 626218, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.043339967727661, "global_step": 626219, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0847997665405273, "global_step": 626220, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0064609050750732, "global_step": 626221, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.066290855407715, "global_step": 626222, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9352837800979614, "global_step": 626223, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9724352359771729, "global_step": 626224, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9998267889022827, "global_step": 626225, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.933310627937317, "global_step": 626226, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.053356409072876, "global_step": 626227, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9574319124221802, "global_step": 626228, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0505597591400146, "global_step": 626229, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.969107747077942, "global_step": 626230, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.012010335922241, "global_step": 626231, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9594473838806152, "global_step": 626232, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0317165851593018, "global_step": 626233, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9728050231933594, "global_step": 626234, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9752813577651978, "global_step": 626235, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0518887042999268, "global_step": 626236, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.042503833770752, "global_step": 626237, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1053578853607178, "global_step": 626238, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0030014514923096, "global_step": 626239, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9514867067337036, "global_step": 626240, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.956888198852539, "global_step": 626241, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0356862545013428, "global_step": 626242, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9490092992782593, "global_step": 626243, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.015749931335449, "global_step": 626244, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0450539588928223, "global_step": 626245, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9941685199737549, "global_step": 626246, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.949438452720642, "global_step": 626247, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.033933401107788, "global_step": 626248, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0244312286376953, "global_step": 626249, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9957315921783447, "global_step": 626250, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9510622024536133, "global_step": 626251, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0070056915283203, "global_step": 626252, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0330965518951416, "global_step": 626253, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9843212366104126, "global_step": 626254, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.015094041824341, "global_step": 626255, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8870515823364258, "global_step": 626256, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.025815010070801, "global_step": 626257, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0354936122894287, "global_step": 626258, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0051634311676025, "global_step": 626259, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.991737723350525, "global_step": 626260, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9785317182540894, "global_step": 626261, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9786361455917358, "global_step": 626262, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.019498586654663, "global_step": 626263, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.930294156074524, "global_step": 626264, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.051581859588623, "global_step": 626265, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9725804328918457, "global_step": 626266, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9412493705749512, "global_step": 626267, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.033447742462158, "global_step": 626268, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9474834203720093, "global_step": 626269, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.002570629119873, "global_step": 626270, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.996897578239441, "global_step": 626271, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9824562072753906, "global_step": 626272, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0411500930786133, "global_step": 626273, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.983231544494629, "global_step": 626274, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9461593627929688, "global_step": 626275, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0323710441589355, "global_step": 626276, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9604129791259766, "global_step": 626277, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9935299158096313, "global_step": 626278, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.941551923751831, "global_step": 626279, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0346145629882812, "global_step": 626280, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0292468070983887, "global_step": 626281, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0242865085601807, "global_step": 626282, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9694322347640991, "global_step": 626283, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.01423978805542, "global_step": 626284, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9601445198059082, "global_step": 626285, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.057800769805908, "global_step": 626286, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.000606060028076, "global_step": 626287, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.017371416091919, "global_step": 626288, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9583766460418701, "global_step": 626289, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9350099563598633, "global_step": 626290, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.059907913208008, "global_step": 626291, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.068243980407715, "global_step": 626292, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.058434247970581, "global_step": 626293, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0099589824676514, "global_step": 626294, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0811259746551514, "global_step": 626295, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9374206066131592, "global_step": 626296, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9849849939346313, "global_step": 626297, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.023641586303711, "global_step": 626298, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0148801803588867, "global_step": 626299, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0477688312530518, "global_step": 626300, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.06547212600708, "global_step": 626301, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9379900693893433, "global_step": 626302, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1029512882232666, "global_step": 626303, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.031073808670044, "global_step": 626304, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9545334577560425, "global_step": 626305, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9905399084091187, "global_step": 626306, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9966201782226562, "global_step": 626307, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9506207704544067, "global_step": 626308, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9818289279937744, "global_step": 626309, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9642235040664673, "global_step": 626310, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9602525234222412, "global_step": 626311, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9914957284927368, "global_step": 626312, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9801716804504395, "global_step": 626313, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.051391363143921, "global_step": 626314, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9423426389694214, "global_step": 626315, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9645357131958008, "global_step": 626316, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9708515405654907, "global_step": 626317, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9448322057724, "global_step": 626318, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9953889846801758, "global_step": 626319, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9532233476638794, "global_step": 626320, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.01666259765625, "global_step": 626321, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9733599424362183, "global_step": 626322, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0709049701690674, "global_step": 626323, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9533321857452393, "global_step": 626324, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9103366136550903, "global_step": 626325, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9909489154815674, "global_step": 626326, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0150513648986816, "global_step": 626327, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0982818603515625, "global_step": 626328, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.061021089553833, "global_step": 626329, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9983868598937988, "global_step": 626330, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.066286325454712, "global_step": 626331, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9553234577178955, "global_step": 626332, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9899100065231323, "global_step": 626333, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.986746907234192, "global_step": 626334, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9243026971817017, "global_step": 626335, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.957972764968872, "global_step": 626336, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.937964677810669, "global_step": 626337, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.96989905834198, "global_step": 626338, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0433766841888428, "global_step": 626339, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.010397434234619, "global_step": 626340, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0489909648895264, "global_step": 626341, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.020531177520752, "global_step": 626342, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.000872850418091, "global_step": 626343, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.069762945175171, "global_step": 626344, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0302131175994873, "global_step": 626345, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.009005308151245, "global_step": 626346, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.963413119316101, "global_step": 626347, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9870851039886475, "global_step": 626348, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9732656478881836, "global_step": 626349, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9995685815811157, "global_step": 626350, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9518102407455444, "global_step": 626351, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.095285654067993, "global_step": 626352, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9407246112823486, "global_step": 626353, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.029773235321045, "global_step": 626354, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9710218906402588, "global_step": 626355, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9879894256591797, "global_step": 626356, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.949904203414917, "global_step": 626357, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9828122854232788, "global_step": 626358, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9668995141983032, "global_step": 626359, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9737379550933838, "global_step": 626360, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9627912044525146, "global_step": 626361, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.034580707550049, "global_step": 626362, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.982290267944336, "global_step": 626363, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9268603324890137, "global_step": 626364, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9350478649139404, "global_step": 626365, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.991075038909912, "global_step": 626366, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9614440202713013, "global_step": 626367, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0520455837249756, "global_step": 626368, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9571222066879272, "global_step": 626369, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9826278686523438, "global_step": 626370, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.051348924636841, "global_step": 626371, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0270960330963135, "global_step": 626372, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.001324415206909, "global_step": 626373, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0539751052856445, "global_step": 626374, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0636394023895264, "global_step": 626375, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9993351697921753, "global_step": 626376, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.021333932876587, "global_step": 626377, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9882183074951172, "global_step": 626378, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.019298791885376, "global_step": 626379, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.040802240371704, "global_step": 626380, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0411319732666016, "global_step": 626381, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.043283700942993, "global_step": 626382, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9787660837173462, "global_step": 626383, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.036775827407837, "global_step": 626384, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.988765835762024, "global_step": 626385, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9190269708633423, "global_step": 626386, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9496517181396484, "global_step": 626387, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9559394121170044, "global_step": 626388, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9931281805038452, "global_step": 626389, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0134787559509277, "global_step": 626390, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9779595136642456, "global_step": 626391, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9896502494812012, "global_step": 626392, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0358834266662598, "global_step": 626393, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.982314944267273, "global_step": 626394, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.049119710922241, "global_step": 626395, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0337026119232178, "global_step": 626396, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.986374020576477, "global_step": 626397, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1192312240600586, "global_step": 626398, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9847947359085083, "global_step": 626399, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0001094341278076, "global_step": 626400, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0361826419830322, "global_step": 626401, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0270509719848633, "global_step": 626402, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8984839916229248, "global_step": 626403, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9932221174240112, "global_step": 626404, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9865599870681763, "global_step": 626405, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.031710147857666, "global_step": 626406, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.934720516204834, "global_step": 626407, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9433475732803345, "global_step": 626408, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8939327001571655, "global_step": 626409, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.989134430885315, "global_step": 626410, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.056973457336426, "global_step": 626411, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.978161096572876, "global_step": 626412, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.066990852355957, "global_step": 626413, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.939910650253296, "global_step": 626414, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0336241722106934, "global_step": 626415, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.982846975326538, "global_step": 626416, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.896934986114502, "global_step": 626417, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9664647579193115, "global_step": 626418, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0029492378234863, "global_step": 626419, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9739477634429932, "global_step": 626420, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0253865718841553, "global_step": 626421, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9395828247070312, "global_step": 626422, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.942586064338684, "global_step": 626423, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0914604663848877, "global_step": 626424, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9302489757537842, "global_step": 626425, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9207121133804321, "global_step": 626426, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0751302242279053, "global_step": 626427, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8602476119995117, "global_step": 626428, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9069957733154297, "global_step": 626429, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.007856607437134, "global_step": 626430, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0465283393859863, "global_step": 626431, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9539384841918945, "global_step": 626432, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9824799299240112, "global_step": 626433, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9410884380340576, "global_step": 626434, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9190340042114258, "global_step": 626435, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9734622240066528, "global_step": 626436, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.062037467956543, "global_step": 626437, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.97641122341156, "global_step": 626438, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0728254318237305, "global_step": 626439, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9201117753982544, "global_step": 626440, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.065835475921631, "global_step": 626441, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.02636981010437, "global_step": 626442, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9243303537368774, "global_step": 626443, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.038517475128174, "global_step": 626444, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.081754684448242, "global_step": 626445, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.003584861755371, "global_step": 626446, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.046107769012451, "global_step": 626447, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9920881986618042, "global_step": 626448, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0350863933563232, "global_step": 626449, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.093557119369507, "global_step": 626450, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9259281158447266, "global_step": 626451, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.942468523979187, "global_step": 626452, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.074198007583618, "global_step": 626453, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1042370796203613, "global_step": 626454, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9681035280227661, "global_step": 626455, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0175118446350098, "global_step": 626456, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9970418214797974, "global_step": 626457, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9865481853485107, "global_step": 626458, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0656840801239014, "global_step": 626459, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0055365562438965, "global_step": 626460, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0559465885162354, "global_step": 626461, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9895035028457642, "global_step": 626462, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9985393285751343, "global_step": 626463, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0376365184783936, "global_step": 626464, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0117273330688477, "global_step": 626465, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9847371578216553, "global_step": 626466, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0718750953674316, "global_step": 626467, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9674851894378662, "global_step": 626468, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9822845458984375, "global_step": 626469, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9940159320831299, "global_step": 626470, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.094562530517578, "global_step": 626471, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9121555089950562, "global_step": 626472, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0776686668395996, "global_step": 626473, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0654776096343994, "global_step": 626474, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9445995092391968, "global_step": 626475, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9229769706726074, "global_step": 626476, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.071674108505249, "global_step": 626477, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9147340059280396, "global_step": 626478, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9401485919952393, "global_step": 626479, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0528836250305176, "global_step": 626480, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.999376893043518, "global_step": 626481, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9556242227554321, "global_step": 626482, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9617317914962769, "global_step": 626483, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.075802803039551, "global_step": 626484, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0840232372283936, "global_step": 626485, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0343194007873535, "global_step": 626486, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9849066734313965, "global_step": 626487, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.951876163482666, "global_step": 626488, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0597307682037354, "global_step": 626489, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9288325309753418, "global_step": 626490, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.024671792984009, "global_step": 626491, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0727384090423584, "global_step": 626492, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9935975074768066, "global_step": 626493, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9511700868606567, "global_step": 626494, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9410532712936401, "global_step": 626495, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9910147190093994, "global_step": 626496, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.942160964012146, "global_step": 626497, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0047860145568848, "global_step": 626498, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.065673351287842, "global_step": 626499, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.084716320037842, "global_step": 626500, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.994287371635437, "global_step": 626501, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0490708351135254, "global_step": 626502, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0837223529815674, "global_step": 626503, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9620366096496582, "global_step": 626504, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.028032064437866, "global_step": 626505, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9957785606384277, "global_step": 626506, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0315914154052734, "global_step": 626507, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0815956592559814, "global_step": 626508, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9927334785461426, "global_step": 626509, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.040595054626465, "global_step": 626510, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0029714107513428, "global_step": 626511, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0173685550689697, "global_step": 626512, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.030315399169922, "global_step": 626513, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0527584552764893, "global_step": 626514, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9648596048355103, "global_step": 626515, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9987804889678955, "global_step": 626516, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.964066982269287, "global_step": 626517, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0812795162200928, "global_step": 626518, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0053868293762207, "global_step": 626519, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.004185676574707, "global_step": 626520, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9572415351867676, "global_step": 626521, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9956475496292114, "global_step": 626522, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9775676727294922, "global_step": 626523, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0067691802978516, "global_step": 626524, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0166122913360596, "global_step": 626525, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9635361433029175, "global_step": 626526, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.007267475128174, "global_step": 626527, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.971732497215271, "global_step": 626528, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0552401542663574, "global_step": 626529, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9955852031707764, "global_step": 626530, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9574068784713745, "global_step": 626531, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0201029777526855, "global_step": 626532, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.982500433921814, "global_step": 626533, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9968024492263794, "global_step": 626534, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9243199825286865, "global_step": 626535, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9725536108016968, "global_step": 626536, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9756271839141846, "global_step": 626537, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0127179622650146, "global_step": 626538, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.075127601623535, "global_step": 626539, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0445308685302734, "global_step": 626540, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9631805419921875, "global_step": 626541, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0227620601654053, "global_step": 626542, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0407068729400635, "global_step": 626543, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9747849702835083, "global_step": 626544, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.927010178565979, "global_step": 626545, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9579600095748901, "global_step": 626546, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.007812261581421, "global_step": 626547, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0124425888061523, "global_step": 626548, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.975608229637146, "global_step": 626549, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0056302547454834, "global_step": 626550, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.967147707939148, "global_step": 626551, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.963961124420166, "global_step": 626552, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9723222255706787, "global_step": 626553, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.083444118499756, "global_step": 626554, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0640251636505127, "global_step": 626555, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.026501178741455, "global_step": 626556, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9931820631027222, "global_step": 626557, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9896830320358276, "global_step": 626558, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.949004888534546, "global_step": 626559, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.078453302383423, "global_step": 626560, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8974292278289795, "global_step": 626561, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8968654870986938, "global_step": 626562, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.929045557975769, "global_step": 626563, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9203928709030151, "global_step": 626564, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0017035007476807, "global_step": 626565, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.945520043373108, "global_step": 626566, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9860183000564575, "global_step": 626567, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9939405918121338, "global_step": 626568, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9193050861358643, "global_step": 626569, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0190670490264893, "global_step": 626570, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9674913883209229, "global_step": 626571, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.030629873275757, "global_step": 626572, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9879206418991089, "global_step": 626573, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0882387161254883, "global_step": 626574, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.010981321334839, "global_step": 626575, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.021644115447998, "global_step": 626576, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9213539361953735, "global_step": 626577, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0249669551849365, "global_step": 626578, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0008351802825928, "global_step": 626579, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0342929363250732, "global_step": 626580, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0240185260772705, "global_step": 626581, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0144729614257812, "global_step": 626582, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0557572841644287, "global_step": 626583, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9564963579177856, "global_step": 626584, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0010814666748047, "global_step": 626585, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.006791114807129, "global_step": 626586, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.009300947189331, "global_step": 626587, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0546576976776123, "global_step": 626588, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9935154914855957, "global_step": 626589, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0483288764953613, "global_step": 626590, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.912461280822754, "global_step": 626591, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.055896759033203, "global_step": 626592, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0391483306884766, "global_step": 626593, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.037381172180176, "global_step": 626594, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9642480611801147, "global_step": 626595, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0224523544311523, "global_step": 626596, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.019335985183716, "global_step": 626597, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0125045776367188, "global_step": 626598, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9573253393173218, "global_step": 626599, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9848542213439941, "global_step": 626600, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0733718872070312, "global_step": 626601, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.039945363998413, "global_step": 626602, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.08624267578125, "global_step": 626603, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.105210781097412, "global_step": 626604, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.965240478515625, "global_step": 626605, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0257022380828857, "global_step": 626606, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9806960821151733, "global_step": 626607, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.04390287399292, "global_step": 626608, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9336185455322266, "global_step": 626609, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.981731653213501, "global_step": 626610, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.98821222782135, "global_step": 626611, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.067099094390869, "global_step": 626612, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9803391695022583, "global_step": 626613, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1334245204925537, "global_step": 626614, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0238654613494873, "global_step": 626615, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.015366315841675, "global_step": 626616, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0275447368621826, "global_step": 626617, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0515403747558594, "global_step": 626618, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.032885789871216, "global_step": 626619, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.036123037338257, "global_step": 626620, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.965521216392517, "global_step": 626621, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0609636306762695, "global_step": 626622, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.008681297302246, "global_step": 626623, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0286617279052734, "global_step": 626624, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9984979629516602, "global_step": 626625, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0180575847625732, "global_step": 626626, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.986928105354309, "global_step": 626627, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.986149787902832, "global_step": 626628, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9877252578735352, "global_step": 626629, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.00797176361084, "global_step": 626630, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9983726739883423, "global_step": 626631, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.016803503036499, "global_step": 626632, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0235533714294434, "global_step": 626633, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9812294244766235, "global_step": 626634, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9870762825012207, "global_step": 626635, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.945847749710083, "global_step": 626636, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0527989864349365, "global_step": 626637, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.085728406906128, "global_step": 626638, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.118151903152466, "global_step": 626639, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.022916555404663, "global_step": 626640, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.016103744506836, "global_step": 626641, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.088496446609497, "global_step": 626642, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9476470947265625, "global_step": 626643, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.066622734069824, "global_step": 626644, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0044689178466797, "global_step": 626645, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9926972389221191, "global_step": 626646, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0486209392547607, "global_step": 626647, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9618748426437378, "global_step": 626648, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1695384979248047, "global_step": 626649, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.01052188873291, "global_step": 626650, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.017192840576172, "global_step": 626651, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0377113819122314, "global_step": 626652, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.990365743637085, "global_step": 626653, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.060262680053711, "global_step": 626654, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0167934894561768, "global_step": 626655, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1569371223449707, "global_step": 626656, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0596461296081543, "global_step": 626657, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9566093683242798, "global_step": 626658, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9879049062728882, "global_step": 626659, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9624075889587402, "global_step": 626660, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9996801614761353, "global_step": 626661, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0232887268066406, "global_step": 626662, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9832136631011963, "global_step": 626663, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9080407619476318, "global_step": 626664, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9627747535705566, "global_step": 626665, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.00390887260437, "global_step": 626666, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0286853313446045, "global_step": 626667, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.033071756362915, "global_step": 626668, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.019603729248047, "global_step": 626669, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.000077247619629, "global_step": 626670, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9910306930541992, "global_step": 626671, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0018692016601562, "global_step": 626672, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8981889486312866, "global_step": 626673, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.050339460372925, "global_step": 626674, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9572741985321045, "global_step": 626675, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.022104501724243, "global_step": 626676, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.006953239440918, "global_step": 626677, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1238021850585938, "global_step": 626678, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9843101501464844, "global_step": 626679, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.007478713989258, "global_step": 626680, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9731104373931885, "global_step": 626681, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.082634210586548, "global_step": 626682, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0232770442962646, "global_step": 626683, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.013019323348999, "global_step": 626684, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9547216892242432, "global_step": 626685, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0255346298217773, "global_step": 626686, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9070217609405518, "global_step": 626687, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9792084693908691, "global_step": 626688, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9647303819656372, "global_step": 626689, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9875050783157349, "global_step": 626690, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0881025791168213, "global_step": 626691, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9602798223495483, "global_step": 626692, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0657124519348145, "global_step": 626693, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0177173614501953, "global_step": 626694, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9505175352096558, "global_step": 626695, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8541146516799927, "global_step": 626696, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9731463193893433, "global_step": 626697, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0005569458007812, "global_step": 626698, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.01381778717041, "global_step": 626699, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.052699565887451, "global_step": 626700, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9774385690689087, "global_step": 626701, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9936320781707764, "global_step": 626702, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.053711175918579, "global_step": 626703, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9915238618850708, "global_step": 626704, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0670430660247803, "global_step": 626705, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9913640022277832, "global_step": 626706, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9962581396102905, "global_step": 626707, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9585797786712646, "global_step": 626708, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9949076175689697, "global_step": 626709, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0601606369018555, "global_step": 626710, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.063600540161133, "global_step": 626711, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9578030109405518, "global_step": 626712, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9791042804718018, "global_step": 626713, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9772679805755615, "global_step": 626714, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.962376356124878, "global_step": 626715, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.940451741218567, "global_step": 626716, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9674941301345825, "global_step": 626717, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9713594913482666, "global_step": 626718, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.992102861404419, "global_step": 626719, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0501339435577393, "global_step": 626720, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.945724606513977, "global_step": 626721, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.066462993621826, "global_step": 626722, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9996092319488525, "global_step": 626723, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9984468221664429, "global_step": 626724, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9507243633270264, "global_step": 626725, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.007514238357544, "global_step": 626726, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.040405035018921, "global_step": 626727, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0297603607177734, "global_step": 626728, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0516231060028076, "global_step": 626729, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.075197458267212, "global_step": 626730, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0135552883148193, "global_step": 626731, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.040083885192871, "global_step": 626732, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.051905393600464, "global_step": 626733, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9854148626327515, "global_step": 626734, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9360445737838745, "global_step": 626735, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0764782428741455, "global_step": 626736, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0366389751434326, "global_step": 626737, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9540942907333374, "global_step": 626738, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.063542366027832, "global_step": 626739, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9408196210861206, "global_step": 626740, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9543917179107666, "global_step": 626741, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0274860858917236, "global_step": 626742, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0602245330810547, "global_step": 626743, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0065112113952637, "global_step": 626744, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0153043270111084, "global_step": 626745, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0004730224609375, "global_step": 626746, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0093770027160645, "global_step": 626747, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9785170555114746, "global_step": 626748, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.028376817703247, "global_step": 626749, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9983131885528564, "global_step": 626750, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9782634973526, "global_step": 626751, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.060189723968506, "global_step": 626752, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8957624435424805, "global_step": 626753, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0920886993408203, "global_step": 626754, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0393929481506348, "global_step": 626755, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.051858425140381, "global_step": 626756, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0736899375915527, "global_step": 626757, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1039395332336426, "global_step": 626758, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0239124298095703, "global_step": 626759, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0690321922302246, "global_step": 626760, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0755839347839355, "global_step": 626761, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9274029731750488, "global_step": 626762, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9681113958358765, "global_step": 626763, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0566775798797607, "global_step": 626764, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9983800649642944, "global_step": 626765, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1176414489746094, "global_step": 626766, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9852150678634644, "global_step": 626767, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9362940788269043, "global_step": 626768, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.031155824661255, "global_step": 626769, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.999279260635376, "global_step": 626770, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.020148515701294, "global_step": 626771, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0418484210968018, "global_step": 626772, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0010554790496826, "global_step": 626773, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9627363681793213, "global_step": 626774, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0596728324890137, "global_step": 626775, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0074899196624756, "global_step": 626776, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9529850482940674, "global_step": 626777, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.074810743331909, "global_step": 626778, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.944210410118103, "global_step": 626779, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0518276691436768, "global_step": 626780, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9668569564819336, "global_step": 626781, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9422191381454468, "global_step": 626782, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0182762145996094, "global_step": 626783, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.115553140640259, "global_step": 626784, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.084400177001953, "global_step": 626785, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0330052375793457, "global_step": 626786, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9333239793777466, "global_step": 626787, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.003582000732422, "global_step": 626788, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.026324510574341, "global_step": 626789, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.031527519226074, "global_step": 626790, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9587090015411377, "global_step": 626791, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.068773031234741, "global_step": 626792, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9666643142700195, "global_step": 626793, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9973551034927368, "global_step": 626794, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9940906763076782, "global_step": 626795, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.943832278251648, "global_step": 626796, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9897751808166504, "global_step": 626797, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.035093307495117, "global_step": 626798, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.057832717895508, "global_step": 626799, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.971070408821106, "global_step": 626800, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0945663452148438, "global_step": 626801, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0296730995178223, "global_step": 626802, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1025071144104004, "global_step": 626803, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.000051975250244, "global_step": 626804, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.078866481781006, "global_step": 626805, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.015263319015503, "global_step": 626806, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0168368816375732, "global_step": 626807, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9203097820281982, "global_step": 626808, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9731136560440063, "global_step": 626809, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.023674964904785, "global_step": 626810, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.039350748062134, "global_step": 626811, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9828062057495117, "global_step": 626812, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9625428915023804, "global_step": 626813, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9303605556488037, "global_step": 626814, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.019392967224121, "global_step": 626815, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.998569130897522, "global_step": 626816, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.959261417388916, "global_step": 626817, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9283727407455444, "global_step": 626818, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0207741260528564, "global_step": 626819, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.016059160232544, "global_step": 626820, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.016838312149048, "global_step": 626821, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9449526071548462, "global_step": 626822, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9860036373138428, "global_step": 626823, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0471549034118652, "global_step": 626824, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0483672618865967, "global_step": 626825, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9697396755218506, "global_step": 626826, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.942231297492981, "global_step": 626827, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9188975095748901, "global_step": 626828, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.035399913787842, "global_step": 626829, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.014030933380127, "global_step": 626830, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0183112621307373, "global_step": 626831, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9712820053100586, "global_step": 626832, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.981361746788025, "global_step": 626833, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0987510681152344, "global_step": 626834, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.965063214302063, "global_step": 626835, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9449442625045776, "global_step": 626836, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0378036499023438, "global_step": 626837, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0453286170959473, "global_step": 626838, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.896955966949463, "global_step": 626839, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.013002872467041, "global_step": 626840, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9515951871871948, "global_step": 626841, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0101537704467773, "global_step": 626842, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0256056785583496, "global_step": 626843, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9994730949401855, "global_step": 626844, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9709490537643433, "global_step": 626845, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9442251920700073, "global_step": 626846, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.063255548477173, "global_step": 626847, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9973350763320923, "global_step": 626848, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9946396350860596, "global_step": 626849, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9910459518432617, "global_step": 626850, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9137015342712402, "global_step": 626851, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0537586212158203, "global_step": 626852, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0627973079681396, "global_step": 626853, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.073263645172119, "global_step": 626854, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9894453287124634, "global_step": 626855, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.005343198776245, "global_step": 626856, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0285563468933105, "global_step": 626857, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0139224529266357, "global_step": 626858, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.081718921661377, "global_step": 626859, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9423291683197021, "global_step": 626860, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0788044929504395, "global_step": 626861, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9861629009246826, "global_step": 626862, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.039863348007202, "global_step": 626863, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1160945892333984, "global_step": 626864, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0090670585632324, "global_step": 626865, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.984905481338501, "global_step": 626866, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.999413251876831, "global_step": 626867, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9512864351272583, "global_step": 626868, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0117857456207275, "global_step": 626869, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.069124937057495, "global_step": 626870, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0118749141693115, "global_step": 626871, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.912920594215393, "global_step": 626872, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9998631477355957, "global_step": 626873, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.079314947128296, "global_step": 626874, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0476877689361572, "global_step": 626875, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9146506786346436, "global_step": 626876, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0143380165100098, "global_step": 626877, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0772016048431396, "global_step": 626878, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0323281288146973, "global_step": 626879, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9202133417129517, "global_step": 626880, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.997628927230835, "global_step": 626881, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9715858697891235, "global_step": 626882, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9571774005889893, "global_step": 626883, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9438295364379883, "global_step": 626884, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9662717580795288, "global_step": 626885, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.885164499282837, "global_step": 626886, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.01572847366333, "global_step": 626887, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0890653133392334, "global_step": 626888, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.052968740463257, "global_step": 626889, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.00830340385437, "global_step": 626890, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9711217880249023, "global_step": 626891, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9810357093811035, "global_step": 626892, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9183591604232788, "global_step": 626893, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0152642726898193, "global_step": 626894, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.967416524887085, "global_step": 626895, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0311145782470703, "global_step": 626896, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9288725852966309, "global_step": 626897, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9310263395309448, "global_step": 626898, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.906630516052246, "global_step": 626899, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9667479991912842, "global_step": 626900, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0064587593078613, "global_step": 626901, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0042128562927246, "global_step": 626902, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9736714363098145, "global_step": 626903, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0619964599609375, "global_step": 626904, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1028177738189697, "global_step": 626905, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.017144203186035, "global_step": 626906, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0260162353515625, "global_step": 626907, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0087268352508545, "global_step": 626908, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0283167362213135, "global_step": 626909, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9571592807769775, "global_step": 626910, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9818470478057861, "global_step": 626911, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.041597604751587, "global_step": 626912, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0741915702819824, "global_step": 626913, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0304019451141357, "global_step": 626914, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0030596256256104, "global_step": 626915, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9517052173614502, "global_step": 626916, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9872599840164185, "global_step": 626917, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.125955104827881, "global_step": 626918, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.130967855453491, "global_step": 626919, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0405049324035645, "global_step": 626920, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0136048793792725, "global_step": 626921, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9944844245910645, "global_step": 626922, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0556929111480713, "global_step": 626923, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.063359022140503, "global_step": 626924, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0359981060028076, "global_step": 626925, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0078201293945312, "global_step": 626926, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.8666338920593262, "global_step": 626927, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0748331546783447, "global_step": 626928, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0524497032165527, "global_step": 626929, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9986293315887451, "global_step": 626930, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0570266246795654, "global_step": 626931, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0267131328582764, "global_step": 626932, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0024466514587402, "global_step": 626933, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0638153553009033, "global_step": 626934, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.984316349029541, "global_step": 626935, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0194714069366455, "global_step": 626936, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.979814887046814, "global_step": 626937, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.017360210418701, "global_step": 626938, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.060408592224121, "global_step": 626939, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9875563383102417, "global_step": 626940, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.072497844696045, "global_step": 626941, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.924208164215088, "global_step": 626942, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.003237724304199, "global_step": 626943, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0265188217163086, "global_step": 626944, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.955284833908081, "global_step": 626945, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0262858867645264, "global_step": 626946, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9569193124771118, "global_step": 626947, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0124289989471436, "global_step": 626948, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.007138729095459, "global_step": 626949, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9826688766479492, "global_step": 626950, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9711591005325317, "global_step": 626951, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.051513195037842, "global_step": 626952, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0383236408233643, "global_step": 626953, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0637972354888916, "global_step": 626954, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0205838680267334, "global_step": 626955, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.047813892364502, "global_step": 626956, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0547587871551514, "global_step": 626957, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9685289859771729, "global_step": 626958, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9890871047973633, "global_step": 626959, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.013420820236206, "global_step": 626960, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.994802713394165, "global_step": 626961, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9338802099227905, "global_step": 626962, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9826123714447021, "global_step": 626963, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.117802858352661, "global_step": 626964, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.922872543334961, "global_step": 626965, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9995886087417603, "global_step": 626966, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0131783485412598, "global_step": 626967, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.022167444229126, "global_step": 626968, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9858039617538452, "global_step": 626969, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0071327686309814, "global_step": 626970, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.027285099029541, "global_step": 626971, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0444746017456055, "global_step": 626972, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0200443267822266, "global_step": 626973, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0330469608306885, "global_step": 626974, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9798471927642822, "global_step": 626975, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.035223960876465, "global_step": 626976, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9773274660110474, "global_step": 626977, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9761065244674683, "global_step": 626978, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0000834465026855, "global_step": 626979, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0005719661712646, "global_step": 626980, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.016171455383301, "global_step": 626981, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0448968410491943, "global_step": 626982, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9681342840194702, "global_step": 626983, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.977587342262268, "global_step": 626984, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0292880535125732, "global_step": 626985, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.025357246398926, "global_step": 626986, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9422423839569092, "global_step": 626987, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0365774631500244, "global_step": 626988, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9562320709228516, "global_step": 626989, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.971983790397644, "global_step": 626990, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.986616849899292, "global_step": 626991, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.996630311012268, "global_step": 626992, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0155110359191895, "global_step": 626993, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0001370906829834, "global_step": 626994, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1460893154144287, "global_step": 626995, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0473508834838867, "global_step": 626996, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9846163988113403, "global_step": 626997, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9142358303070068, "global_step": 626998, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.001838207244873, "global_step": 626999, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9937286376953125, "global_step": 627000, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0350186824798584, "global_step": 627001, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9562214612960815, "global_step": 627002, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9695062637329102, "global_step": 627003, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9277684688568115, "global_step": 627004, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0225908756256104, "global_step": 627005, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.1175479888916016, "global_step": 627006, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.025919198989868, "global_step": 627007, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9565938711166382, "global_step": 627008, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9630528688430786, "global_step": 627009, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9778755903244019, "global_step": 627010, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.056014060974121, "global_step": 627011, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.934973955154419, "global_step": 627012, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.982790470123291, "global_step": 627013, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.990415096282959, "global_step": 627014, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0510706901550293, "global_step": 627015, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.03564190864563, "global_step": 627016, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.974592924118042, "global_step": 627017, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9541077613830566, "global_step": 627018, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0116701126098633, "global_step": 627019, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9393677711486816, "global_step": 627020, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.043760061264038, "global_step": 627021, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0851314067840576, "global_step": 627022, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9917961359024048, "global_step": 627023, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0551202297210693, "global_step": 627024, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.036099672317505, "global_step": 627025, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9381169080734253, "global_step": 627026, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0501549243927, "global_step": 627027, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0342772006988525, "global_step": 627028, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9548286199569702, "global_step": 627029, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0153560638427734, "global_step": 627030, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9792349338531494, "global_step": 627031, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.2416534423828125, "global_step": 627032, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0165274143218994, "global_step": 627033, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0297417640686035, "global_step": 627034, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0103020668029785, "global_step": 627035, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0078368186950684, "global_step": 627036, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9503624439239502, "global_step": 627037, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.029085159301758, "global_step": 627038, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9468363523483276, "global_step": 627039, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0256004333496094, "global_step": 627040, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9643912315368652, "global_step": 627041, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.033517360687256, "global_step": 627042, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.004925489425659, "global_step": 627043, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.078587770462036, "global_step": 627044, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0317845344543457, "global_step": 627045, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0476484298706055, "global_step": 627046, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0569310188293457, "global_step": 627047, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0276870727539062, "global_step": 627048, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.022968053817749, "global_step": 627049, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9652976989746094, "global_step": 627050, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.083080768585205, "global_step": 627051, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.042379379272461, "global_step": 627052, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9014471769332886, "global_step": 627053, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.01031756401062, "global_step": 627054, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.0760159492492676, "global_step": 627055, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9855135679244995, "global_step": 627056, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.002049446105957, "global_step": 627057, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.967113971710205, "global_step": 627058, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9891282320022583, "global_step": 627059, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9896559715270996, "global_step": 627060, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.004178762435913, "global_step": 627061, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.01961088180542, "global_step": 627062, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9687565565109253, "global_step": 627063, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.980847716331482, "global_step": 627064, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9554336071014404, "global_step": 627065, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.016273021697998, "global_step": 627066, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9602882862091064, "global_step": 627067, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9722676277160645, "global_step": 627068, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.044513463973999, "global_step": 627069, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9428982734680176, "global_step": 627070, "epoch": 995, "lr": 5e-05}
{"train_loss": 1.9625113010406494, "global_step": 627071, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.041297197341919, "global_step": 627072, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.004103422164917, "global_step": 627073, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.003145933151245, "global_step": 627074, "epoch": 995, "lr": 5e-05}
{"train_loss": 2.008251905441284, "global_step": 627075, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.000927209854126, "global_step": 627076, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.973185658454895, "global_step": 627077, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9553587436676025, "global_step": 627078, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9805612564086914, "global_step": 627079, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1108081340789795, "global_step": 627080, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0822224617004395, "global_step": 627081, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0475077629089355, "global_step": 627082, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9874320030212402, "global_step": 627083, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9858617782592773, "global_step": 627084, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0140161514282227, "global_step": 627085, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9309697151184082, "global_step": 627086, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0797557830810547, "global_step": 627087, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9235975742340088, "global_step": 627088, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0464107990264893, "global_step": 627089, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0546841621398926, "global_step": 627090, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9759573936462402, "global_step": 627091, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.023456335067749, "global_step": 627092, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.004319667816162, "global_step": 627093, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0010228157043457, "global_step": 627094, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9982430934906006, "global_step": 627095, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.067451238632202, "global_step": 627096, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.024787664413452, "global_step": 627097, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.016845464706421, "global_step": 627098, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.01517653465271, "global_step": 627099, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.001187324523926, "global_step": 627100, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0251262187957764, "global_step": 627101, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9741277694702148, "global_step": 627102, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0036396980285645, "global_step": 627103, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.987061619758606, "global_step": 627104, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.018458366394043, "global_step": 627105, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9710872173309326, "global_step": 627106, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9893181324005127, "global_step": 627107, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.006023406982422, "global_step": 627108, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0188305377960205, "global_step": 627109, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9529310464859009, "global_step": 627110, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.025543212890625, "global_step": 627111, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9053212404251099, "global_step": 627112, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0025317668914795, "global_step": 627113, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.026154041290283, "global_step": 627114, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.999758243560791, "global_step": 627115, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0309696197509766, "global_step": 627116, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.007672071456909, "global_step": 627117, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.976530909538269, "global_step": 627118, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.127155065536499, "global_step": 627119, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0056214332580566, "global_step": 627120, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.009166955947876, "global_step": 627121, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9713783264160156, "global_step": 627122, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0719735622406006, "global_step": 627123, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9747930765151978, "global_step": 627124, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9528162479400635, "global_step": 627125, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.959513783454895, "global_step": 627126, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.02510666847229, "global_step": 627127, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.936937689781189, "global_step": 627128, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9288588762283325, "global_step": 627129, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0176663398742676, "global_step": 627130, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.033193349838257, "global_step": 627131, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9436068534851074, "global_step": 627132, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9789173603057861, "global_step": 627133, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9725641012191772, "global_step": 627134, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9857826232910156, "global_step": 627135, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0634138584136963, "global_step": 627136, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.057158946990967, "global_step": 627137, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9486284255981445, "global_step": 627138, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0250675678253174, "global_step": 627139, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.981099247932434, "global_step": 627140, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9923001527786255, "global_step": 627141, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9387236833572388, "global_step": 627142, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9388879537582397, "global_step": 627143, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0225212574005127, "global_step": 627144, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.022038459777832, "global_step": 627145, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0598959922790527, "global_step": 627146, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9825975894927979, "global_step": 627147, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9479724168777466, "global_step": 627148, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0160210132598877, "global_step": 627149, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.931614637374878, "global_step": 627150, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0496392250061035, "global_step": 627151, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9809496402740479, "global_step": 627152, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0444986820220947, "global_step": 627153, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.027660846710205, "global_step": 627154, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9082804918289185, "global_step": 627155, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0304386615753174, "global_step": 627156, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0211451053619385, "global_step": 627157, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0130364894866943, "global_step": 627158, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0657851696014404, "global_step": 627159, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9575042724609375, "global_step": 627160, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0963058471679688, "global_step": 627161, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0596606731414795, "global_step": 627162, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0403051376342773, "global_step": 627163, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9775563478469849, "global_step": 627164, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0280730724334717, "global_step": 627165, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.049654006958008, "global_step": 627166, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0118322372436523, "global_step": 627167, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9953340291976929, "global_step": 627168, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8942232131958008, "global_step": 627169, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9586617946624756, "global_step": 627170, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0242772102355957, "global_step": 627171, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9984570741653442, "global_step": 627172, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0150420665740967, "global_step": 627173, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.985248327255249, "global_step": 627174, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9537047147750854, "global_step": 627175, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.029348850250244, "global_step": 627176, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9779666662216187, "global_step": 627177, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9373975992202759, "global_step": 627178, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9987088441848755, "global_step": 627179, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0026278495788574, "global_step": 627180, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.00988507270813, "global_step": 627181, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.942640781402588, "global_step": 627182, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9200705289840698, "global_step": 627183, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0267741680145264, "global_step": 627184, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0260918140411377, "global_step": 627185, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9937231540679932, "global_step": 627186, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9895833730697632, "global_step": 627187, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.033292293548584, "global_step": 627188, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9272938966751099, "global_step": 627189, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0586564540863037, "global_step": 627190, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9225002527236938, "global_step": 627191, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.963204264640808, "global_step": 627192, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0059597492218018, "global_step": 627193, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0142602920532227, "global_step": 627194, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0307202339172363, "global_step": 627195, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9783662557601929, "global_step": 627196, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.036153793334961, "global_step": 627197, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.972281575202942, "global_step": 627198, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0147151947021484, "global_step": 627199, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9326379299163818, "global_step": 627200, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.016000747680664, "global_step": 627201, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.026855945587158, "global_step": 627202, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9922244548797607, "global_step": 627203, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.045238971710205, "global_step": 627204, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.070791482925415, "global_step": 627205, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.04984712600708, "global_step": 627206, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9883368015289307, "global_step": 627207, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.014355421066284, "global_step": 627208, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9770880937576294, "global_step": 627209, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9501909017562866, "global_step": 627210, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.017580270767212, "global_step": 627211, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.051414966583252, "global_step": 627212, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8991823196411133, "global_step": 627213, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0640032291412354, "global_step": 627214, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.976905107498169, "global_step": 627215, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.953813910484314, "global_step": 627216, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.09245228767395, "global_step": 627217, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.044555425643921, "global_step": 627218, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0391829013824463, "global_step": 627219, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.038304328918457, "global_step": 627220, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0180413722991943, "global_step": 627221, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0149412155151367, "global_step": 627222, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.102600574493408, "global_step": 627223, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9946125745773315, "global_step": 627224, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.027987003326416, "global_step": 627225, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0491151809692383, "global_step": 627226, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.015004873275757, "global_step": 627227, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9894306659698486, "global_step": 627228, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.028341770172119, "global_step": 627229, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9421366453170776, "global_step": 627230, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9822505712509155, "global_step": 627231, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0101826190948486, "global_step": 627232, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.025545358657837, "global_step": 627233, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9904781579971313, "global_step": 627234, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9609407186508179, "global_step": 627235, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9752960205078125, "global_step": 627236, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.03177547454834, "global_step": 627237, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0583488941192627, "global_step": 627238, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.016752243041992, "global_step": 627239, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9429173469543457, "global_step": 627240, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0329675674438477, "global_step": 627241, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9509145021438599, "global_step": 627242, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9611518383026123, "global_step": 627243, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.993247151374817, "global_step": 627244, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0290958881378174, "global_step": 627245, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0595483779907227, "global_step": 627246, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.000612258911133, "global_step": 627247, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9835433959960938, "global_step": 627248, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9341766834259033, "global_step": 627249, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.022326707839966, "global_step": 627250, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.960473656654358, "global_step": 627251, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0252926349639893, "global_step": 627252, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.071627616882324, "global_step": 627253, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9569798707962036, "global_step": 627254, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.019461154937744, "global_step": 627255, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.008647918701172, "global_step": 627256, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9984651803970337, "global_step": 627257, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0101895332336426, "global_step": 627258, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0607199668884277, "global_step": 627259, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.973273515701294, "global_step": 627260, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0758256912231445, "global_step": 627261, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.017235040664673, "global_step": 627262, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0919487476348877, "global_step": 627263, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.027930498123169, "global_step": 627264, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0499038696289062, "global_step": 627265, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.955019474029541, "global_step": 627266, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0342085361480713, "global_step": 627267, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.991999864578247, "global_step": 627268, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0257792472839355, "global_step": 627269, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9663983583450317, "global_step": 627270, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.005324125289917, "global_step": 627271, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.966576337814331, "global_step": 627272, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.900808572769165, "global_step": 627273, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.12147855758667, "global_step": 627274, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9004175662994385, "global_step": 627275, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.03529691696167, "global_step": 627276, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.926440954208374, "global_step": 627277, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0242316722869873, "global_step": 627278, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.01000714302063, "global_step": 627279, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.011603593826294, "global_step": 627280, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9007203578948975, "global_step": 627281, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0200865268707275, "global_step": 627282, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.993465542793274, "global_step": 627283, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.029311418533325, "global_step": 627284, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.008683443069458, "global_step": 627285, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.001194953918457, "global_step": 627286, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.013399124145508, "global_step": 627287, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0154471397399902, "global_step": 627288, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.956514835357666, "global_step": 627289, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9816452264785767, "global_step": 627290, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0455799102783203, "global_step": 627291, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9681499004364014, "global_step": 627292, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9908533096313477, "global_step": 627293, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0457763671875, "global_step": 627294, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9799981117248535, "global_step": 627295, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9802640676498413, "global_step": 627296, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9406028985977173, "global_step": 627297, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9911218881607056, "global_step": 627298, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0222747325897217, "global_step": 627299, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.001697063446045, "global_step": 627300, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1056485176086426, "global_step": 627301, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.947379231452942, "global_step": 627302, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.010596990585327, "global_step": 627303, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9745302200317383, "global_step": 627304, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9833638668060303, "global_step": 627305, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9930720329284668, "global_step": 627306, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.977658987045288, "global_step": 627307, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.002798318862915, "global_step": 627308, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9479572772979736, "global_step": 627309, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9987425804138184, "global_step": 627310, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9592268466949463, "global_step": 627311, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0561115741729736, "global_step": 627312, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.002912998199463, "global_step": 627313, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0297484397888184, "global_step": 627314, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9694539308547974, "global_step": 627315, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8811198472976685, "global_step": 627316, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0810108184814453, "global_step": 627317, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9772104024887085, "global_step": 627318, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.982949137687683, "global_step": 627319, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9070237874984741, "global_step": 627320, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0521392822265625, "global_step": 627321, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9448622465133667, "global_step": 627322, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9946895837783813, "global_step": 627323, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.964172124862671, "global_step": 627324, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0450439453125, "global_step": 627325, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.982568383216858, "global_step": 627326, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0194180011749268, "global_step": 627327, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9605505466461182, "global_step": 627328, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.996079921722412, "global_step": 627329, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9839168787002563, "global_step": 627330, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.010455846786499, "global_step": 627331, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9827601909637451, "global_step": 627332, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.96590256690979, "global_step": 627333, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9841675758361816, "global_step": 627334, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.072383165359497, "global_step": 627335, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.889869213104248, "global_step": 627336, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.034576892852783, "global_step": 627337, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9885329008102417, "global_step": 627338, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9840199947357178, "global_step": 627339, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.896417498588562, "global_step": 627340, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0464513301849365, "global_step": 627341, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9134916067123413, "global_step": 627342, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9579027891159058, "global_step": 627343, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.990435004234314, "global_step": 627344, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.971856951713562, "global_step": 627345, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9633415937423706, "global_step": 627346, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.965921401977539, "global_step": 627347, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9251774549484253, "global_step": 627348, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8842952251434326, "global_step": 627349, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9594675302505493, "global_step": 627350, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0032289028167725, "global_step": 627351, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9670344591140747, "global_step": 627352, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0508298873901367, "global_step": 627353, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9684444665908813, "global_step": 627354, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.023942232131958, "global_step": 627355, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.001650094985962, "global_step": 627356, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0410306453704834, "global_step": 627357, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9780569076538086, "global_step": 627358, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0415821075439453, "global_step": 627359, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.030386447906494, "global_step": 627360, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9294710159301758, "global_step": 627361, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.045224666595459, "global_step": 627362, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.972034215927124, "global_step": 627363, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0113487243652344, "global_step": 627364, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0690412521362305, "global_step": 627365, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9613316059112549, "global_step": 627366, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9493663311004639, "global_step": 627367, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.976565957069397, "global_step": 627368, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.008678436279297, "global_step": 627369, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.958276629447937, "global_step": 627370, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9462400674819946, "global_step": 627371, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.970571756362915, "global_step": 627372, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.049220323562622, "global_step": 627373, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.020393133163452, "global_step": 627374, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0723814964294434, "global_step": 627375, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.013632297515869, "global_step": 627376, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8547427654266357, "global_step": 627377, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.005798578262329, "global_step": 627378, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.970625638961792, "global_step": 627379, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0584280490875244, "global_step": 627380, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.079676628112793, "global_step": 627381, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.923302412033081, "global_step": 627382, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.019845962524414, "global_step": 627383, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9520511627197266, "global_step": 627384, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9504566192626953, "global_step": 627385, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.025988817214966, "global_step": 627386, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9213193655014038, "global_step": 627387, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.019775629043579, "global_step": 627388, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9895614385604858, "global_step": 627389, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.024012327194214, "global_step": 627390, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0337512493133545, "global_step": 627391, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0137763023376465, "global_step": 627392, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.022428274154663, "global_step": 627393, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.962611198425293, "global_step": 627394, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9883700609207153, "global_step": 627395, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9797430038452148, "global_step": 627396, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0568270683288574, "global_step": 627397, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0092852115631104, "global_step": 627398, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.989607572555542, "global_step": 627399, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9347219467163086, "global_step": 627400, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0258615016937256, "global_step": 627401, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0348830223083496, "global_step": 627402, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9809972047805786, "global_step": 627403, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.021679639816284, "global_step": 627404, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9992038011550903, "global_step": 627405, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.035841703414917, "global_step": 627406, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9417908191680908, "global_step": 627407, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8781546354293823, "global_step": 627408, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0073087215423584, "global_step": 627409, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.083983898162842, "global_step": 627410, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1096761226654053, "global_step": 627411, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0341742038726807, "global_step": 627412, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9281878471374512, "global_step": 627413, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0138590335845947, "global_step": 627414, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0750887393951416, "global_step": 627415, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9802148342132568, "global_step": 627416, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.017529010772705, "global_step": 627417, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.958497405052185, "global_step": 627418, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.947885274887085, "global_step": 627419, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0083303451538086, "global_step": 627420, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9731045961380005, "global_step": 627421, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0256428718566895, "global_step": 627422, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0256338119506836, "global_step": 627423, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0537171363830566, "global_step": 627424, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9889432191848755, "global_step": 627425, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8824012279510498, "global_step": 627426, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.015080451965332, "global_step": 627427, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9628708362579346, "global_step": 627428, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.037285089492798, "global_step": 627429, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.033829689025879, "global_step": 627430, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9965044260025024, "global_step": 627431, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.069133996963501, "global_step": 627432, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9954402446746826, "global_step": 627433, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.024264097213745, "global_step": 627434, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9160135984420776, "global_step": 627435, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0128605365753174, "global_step": 627436, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9838286638259888, "global_step": 627437, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9313733577728271, "global_step": 627438, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9708220958709717, "global_step": 627439, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.039581060409546, "global_step": 627440, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0722246170043945, "global_step": 627441, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0307135581970215, "global_step": 627442, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9835419654846191, "global_step": 627443, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9753800630569458, "global_step": 627444, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9861215353012085, "global_step": 627445, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0210039615631104, "global_step": 627446, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.962545394897461, "global_step": 627447, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.058344841003418, "global_step": 627448, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.023263931274414, "global_step": 627449, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.961382269859314, "global_step": 627450, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.968442678451538, "global_step": 627451, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0131287574768066, "global_step": 627452, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.033405065536499, "global_step": 627453, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.125230312347412, "global_step": 627454, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9922040700912476, "global_step": 627455, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8822321891784668, "global_step": 627456, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.11779522895813, "global_step": 627457, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9809030294418335, "global_step": 627458, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.055818557739258, "global_step": 627459, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9983876943588257, "global_step": 627460, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0015876293182373, "global_step": 627461, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.062384843826294, "global_step": 627462, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9443445205688477, "global_step": 627463, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.038231134414673, "global_step": 627464, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9776777029037476, "global_step": 627465, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.967145562171936, "global_step": 627466, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.994679570198059, "global_step": 627467, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0533151626586914, "global_step": 627468, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0176143646240234, "global_step": 627469, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.025125741958618, "global_step": 627470, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9878501892089844, "global_step": 627471, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.095533847808838, "global_step": 627472, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9418997764587402, "global_step": 627473, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9822943210601807, "global_step": 627474, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0287561416625977, "global_step": 627475, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.040085554122925, "global_step": 627476, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.998328685760498, "global_step": 627477, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0096216201782227, "global_step": 627478, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9086291790008545, "global_step": 627479, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.019739866256714, "global_step": 627480, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9843848943710327, "global_step": 627481, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9316082000732422, "global_step": 627482, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9642066955566406, "global_step": 627483, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9252204895019531, "global_step": 627484, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9295344352722168, "global_step": 627485, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.971301555633545, "global_step": 627486, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0356569290161133, "global_step": 627487, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.998130440711975, "global_step": 627488, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.144313097000122, "global_step": 627489, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.064375400543213, "global_step": 627490, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0508103370666504, "global_step": 627491, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.989095687866211, "global_step": 627492, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.050898551940918, "global_step": 627493, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9331157207489014, "global_step": 627494, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.991789698600769, "global_step": 627495, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0027706623077393, "global_step": 627496, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0468742847442627, "global_step": 627497, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0341341495513916, "global_step": 627498, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0589792728424072, "global_step": 627499, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9811573028564453, "global_step": 627500, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0099236965179443, "global_step": 627501, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.078028678894043, "global_step": 627502, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.951702356338501, "global_step": 627503, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.043131113052368, "global_step": 627504, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0215671062469482, "global_step": 627505, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.035792112350464, "global_step": 627506, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9561793804168701, "global_step": 627507, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.985572338104248, "global_step": 627508, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.100733518600464, "global_step": 627509, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0322608947753906, "global_step": 627510, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0781025886535645, "global_step": 627511, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9064993858337402, "global_step": 627512, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.005409002304077, "global_step": 627513, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.024702310562134, "global_step": 627514, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9441100358963013, "global_step": 627515, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9613745212554932, "global_step": 627516, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9853363037109375, "global_step": 627517, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.042593240737915, "global_step": 627518, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.99053156375885, "global_step": 627519, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.024218797683716, "global_step": 627520, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0179362297058105, "global_step": 627521, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9885751008987427, "global_step": 627522, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0924668312072754, "global_step": 627523, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0587778091430664, "global_step": 627524, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9896410703659058, "global_step": 627525, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0295534133911133, "global_step": 627526, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0545425415039062, "global_step": 627527, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.009073495864868, "global_step": 627528, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9036868810653687, "global_step": 627529, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.028170347213745, "global_step": 627530, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9246010780334473, "global_step": 627531, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.946378469467163, "global_step": 627532, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0058717727661133, "global_step": 627533, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0045437812805176, "global_step": 627534, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9463084936141968, "global_step": 627535, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0734503269195557, "global_step": 627536, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0878419876098633, "global_step": 627537, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0113351345062256, "global_step": 627538, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9738214015960693, "global_step": 627539, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9869341850280762, "global_step": 627540, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.981201410293579, "global_step": 627541, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.940476894378662, "global_step": 627542, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.058777093887329, "global_step": 627543, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0003678798675537, "global_step": 627544, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9192832708358765, "global_step": 627545, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.013162851333618, "global_step": 627546, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9846395254135132, "global_step": 627547, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0185062885284424, "global_step": 627548, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.009167432785034, "global_step": 627549, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.081732988357544, "global_step": 627550, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.014545440673828, "global_step": 627551, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0665409564971924, "global_step": 627552, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.012542963027954, "global_step": 627553, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0120208263397217, "global_step": 627554, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.038304328918457, "global_step": 627555, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9676146507263184, "global_step": 627556, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.995552897453308, "global_step": 627557, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9966169595718384, "global_step": 627558, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.034979820251465, "global_step": 627559, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0280044078826904, "global_step": 627560, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9341228008270264, "global_step": 627561, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9198263883590698, "global_step": 627562, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9825804233551025, "global_step": 627563, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9810506105422974, "global_step": 627564, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9516338109970093, "global_step": 627565, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.057093620300293, "global_step": 627566, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1171131134033203, "global_step": 627567, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9748690128326416, "global_step": 627568, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.917722225189209, "global_step": 627569, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.111316680908203, "global_step": 627570, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.02095890045166, "global_step": 627571, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9663400650024414, "global_step": 627572, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0687623023986816, "global_step": 627573, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0036258697509766, "global_step": 627574, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9583461284637451, "global_step": 627575, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.041043996810913, "global_step": 627576, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9898396730422974, "global_step": 627577, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.903511643409729, "global_step": 627578, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.995099663734436, "global_step": 627579, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9816184043884277, "global_step": 627580, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.004859209060669, "global_step": 627581, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0068907737731934, "global_step": 627582, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0598697662353516, "global_step": 627583, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0248494148254395, "global_step": 627584, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9249659776687622, "global_step": 627585, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.923909068107605, "global_step": 627586, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0199615955352783, "global_step": 627587, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.952746033668518, "global_step": 627588, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9763211011886597, "global_step": 627589, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9775512218475342, "global_step": 627590, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0660390853881836, "global_step": 627591, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0631213188171387, "global_step": 627592, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9921003580093384, "global_step": 627593, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0779170989990234, "global_step": 627594, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0014588832855225, "global_step": 627595, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.971847414970398, "global_step": 627596, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.924545168876648, "global_step": 627597, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9294195175170898, "global_step": 627598, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9453281164169312, "global_step": 627599, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.011218547821045, "global_step": 627600, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.934842586517334, "global_step": 627601, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0806219577789307, "global_step": 627602, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9931634664535522, "global_step": 627603, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0699124336242676, "global_step": 627604, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0218892097473145, "global_step": 627605, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0627939701080322, "global_step": 627606, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9992012977600098, "global_step": 627607, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0177524089813232, "global_step": 627608, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0070481300354004, "global_step": 627609, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9699656963348389, "global_step": 627610, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.007364273071289, "global_step": 627611, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9751635789871216, "global_step": 627612, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0917038917541504, "global_step": 627613, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0002284049987793, "global_step": 627614, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.034168004989624, "global_step": 627615, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9907318353652954, "global_step": 627616, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9750758409500122, "global_step": 627617, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.062023162841797, "global_step": 627618, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9777628183364868, "global_step": 627619, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9349027872085571, "global_step": 627620, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.007342576980591, "global_step": 627621, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.019745349884033, "global_step": 627622, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.050546407699585, "global_step": 627623, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.045302152633667, "global_step": 627624, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0771727561950684, "global_step": 627625, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0145833492279053, "global_step": 627626, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0197901725769043, "global_step": 627627, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0015721321105957, "global_step": 627628, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0367977619171143, "global_step": 627629, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9767837524414062, "global_step": 627630, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.032365560531616, "global_step": 627631, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.990876317024231, "global_step": 627632, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0148277282714844, "global_step": 627633, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.14605450630188, "global_step": 627634, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9509996175765991, "global_step": 627635, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0602505207061768, "global_step": 627636, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0403695106506348, "global_step": 627637, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0661563873291016, "global_step": 627638, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9558639526367188, "global_step": 627639, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0569827556610107, "global_step": 627640, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0336520671844482, "global_step": 627641, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.981204867362976, "global_step": 627642, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.035752058029175, "global_step": 627643, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9900668859481812, "global_step": 627644, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.058396577835083, "global_step": 627645, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0502257347106934, "global_step": 627646, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0861012935638428, "global_step": 627647, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9664981365203857, "global_step": 627648, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.054677724838257, "global_step": 627649, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9293675422668457, "global_step": 627650, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0222971439361572, "global_step": 627651, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0025784969329834, "global_step": 627652, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9262841939926147, "global_step": 627653, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9695876836776733, "global_step": 627654, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.96962571144104, "global_step": 627655, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9688749313354492, "global_step": 627656, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9974327087402344, "global_step": 627657, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.037048101425171, "global_step": 627658, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9389214515686035, "global_step": 627659, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.03198504447937, "global_step": 627660, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0389480590820312, "global_step": 627661, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0608530044555664, "global_step": 627662, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9843560457229614, "global_step": 627663, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.05576753616333, "global_step": 627664, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9069021940231323, "global_step": 627665, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0341532230377197, "global_step": 627666, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0385708808898926, "global_step": 627667, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0243141651153564, "global_step": 627668, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9827966690063477, "global_step": 627669, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.990842342376709, "global_step": 627670, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9690696001052856, "global_step": 627671, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0113325119018555, "global_step": 627672, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9652125835418701, "global_step": 627673, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.01265549659729, "global_step": 627674, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9953092336654663, "global_step": 627675, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9566457271575928, "global_step": 627676, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.983067512512207, "global_step": 627677, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9902690649032593, "global_step": 627678, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9409980773925781, "global_step": 627679, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.070028305053711, "global_step": 627680, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0558154582977295, "global_step": 627681, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9547072649002075, "global_step": 627682, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.003369092941284, "global_step": 627683, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.023097276687622, "global_step": 627684, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.065840005874634, "global_step": 627685, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.022942066192627, "global_step": 627686, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0368123054504395, "global_step": 627687, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.044393539428711, "global_step": 627688, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.001945972442627, "global_step": 627689, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.083808660507202, "global_step": 627690, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0519979000091553, "global_step": 627691, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9314751625061035, "global_step": 627692, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0790822505950928, "global_step": 627693, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9998600482940674, "global_step": 627694, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0039689540863037, "global_step": 627695, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.07430362701416, "global_step": 627696, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.041172742843628, "global_step": 627697, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.990814447402954, "global_step": 627698, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.005763530731201, "global_step": 627699, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9776943922042847, "global_step": 627700, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.120002269744873, "global_step": 627701, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9468146562576294, "global_step": 627702, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.056535005569458, "global_step": 627703, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9652396440505981, "global_step": 627704, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0131871700286865, "global_step": 627705, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.943284273147583, "global_step": 627706, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9873334169387817, "global_step": 627707, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9562110900878906, "global_step": 627708, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.057067632675171, "global_step": 627709, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9999432563781738, "global_step": 627710, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.031419038772583, "global_step": 627711, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.951872706413269, "global_step": 627712, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9968888759613037, "global_step": 627713, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0276424884796143, "global_step": 627714, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.00960636138916, "global_step": 627715, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.994086503982544, "global_step": 627716, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0485355854034424, "global_step": 627717, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9835549592971802, "global_step": 627718, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0005691051483154, "global_step": 627719, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9090733528137207, "global_step": 627720, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0521702766418457, "global_step": 627721, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.055464506149292, "global_step": 627722, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9419653415679932, "global_step": 627723, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9725053310394287, "global_step": 627724, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0159974098205566, "global_step": 627725, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9527992010116577, "global_step": 627726, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9508945941925049, "global_step": 627727, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.939937710762024, "global_step": 627728, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9128168821334839, "global_step": 627729, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0628113746643066, "global_step": 627730, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.972853183746338, "global_step": 627731, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0236568450927734, "global_step": 627732, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0153398513793945, "global_step": 627733, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9996564388275146, "global_step": 627734, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0384511947631836, "global_step": 627735, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0025992393493652, "global_step": 627736, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.030046224594116, "global_step": 627737, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9924064874649048, "global_step": 627738, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.080735683441162, "global_step": 627739, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9096871614456177, "global_step": 627740, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0783591270446777, "global_step": 627741, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9768264293670654, "global_step": 627742, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0273959636688232, "global_step": 627743, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0504815578460693, "global_step": 627744, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0313823223114014, "global_step": 627745, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.964154839515686, "global_step": 627746, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.044708490371704, "global_step": 627747, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.992448329925537, "global_step": 627748, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.022099018096924, "global_step": 627749, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.070000410079956, "global_step": 627750, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.953324556350708, "global_step": 627751, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9510762691497803, "global_step": 627752, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.03946590423584, "global_step": 627753, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.967484951019287, "global_step": 627754, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0279247760772705, "global_step": 627755, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9480772018432617, "global_step": 627756, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.00924015045166, "global_step": 627757, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0467116832733154, "global_step": 627758, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9775022268295288, "global_step": 627759, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.012791395187378, "global_step": 627760, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9710403680801392, "global_step": 627761, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.02388596534729, "global_step": 627762, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9974623918533325, "global_step": 627763, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0368807315826416, "global_step": 627764, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9845746755599976, "global_step": 627765, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9267604351043701, "global_step": 627766, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9809460639953613, "global_step": 627767, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.00435209274292, "global_step": 627768, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.003929376602173, "global_step": 627769, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.006950855255127, "global_step": 627770, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.992519497871399, "global_step": 627771, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9689574241638184, "global_step": 627772, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0415091514587402, "global_step": 627773, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.054396629333496, "global_step": 627774, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.024609088897705, "global_step": 627775, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9748162031173706, "global_step": 627776, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0189731121063232, "global_step": 627777, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1022210121154785, "global_step": 627778, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.028348207473755, "global_step": 627779, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0148191452026367, "global_step": 627780, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9209465980529785, "global_step": 627781, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.086585760116577, "global_step": 627782, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.011953115463257, "global_step": 627783, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9672071933746338, "global_step": 627784, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0555226802825928, "global_step": 627785, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9943788051605225, "global_step": 627786, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.06758189201355, "global_step": 627787, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0873281955718994, "global_step": 627788, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0349676609039307, "global_step": 627789, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9745066165924072, "global_step": 627790, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9820815324783325, "global_step": 627791, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9743390083312988, "global_step": 627792, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0326883792877197, "global_step": 627793, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9550029039382935, "global_step": 627794, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9924399852752686, "global_step": 627795, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0289180278778076, "global_step": 627796, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.050690174102783, "global_step": 627797, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9761461019515991, "global_step": 627798, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9752388000488281, "global_step": 627799, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.977630376815796, "global_step": 627800, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9720945358276367, "global_step": 627801, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9979863166809082, "global_step": 627802, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.938071608543396, "global_step": 627803, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9371496438980103, "global_step": 627804, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.071831226348877, "global_step": 627805, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.007124662399292, "global_step": 627806, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9334025382995605, "global_step": 627807, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.969793438911438, "global_step": 627808, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.898128628730774, "global_step": 627809, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.020986318588257, "global_step": 627810, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.018399715423584, "global_step": 627811, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0130326747894287, "global_step": 627812, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0396649837493896, "global_step": 627813, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0129237174987793, "global_step": 627814, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.043410539627075, "global_step": 627815, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.052091360092163, "global_step": 627816, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.033416509628296, "global_step": 627817, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.034914970397949, "global_step": 627818, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0527684688568115, "global_step": 627819, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0202548503875732, "global_step": 627820, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0511059761047363, "global_step": 627821, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0477819442749023, "global_step": 627822, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.03603196144104, "global_step": 627823, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9934664964675903, "global_step": 627824, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9979133605957031, "global_step": 627825, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.000572681427002, "global_step": 627826, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.967604160308838, "global_step": 627827, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0927069187164307, "global_step": 627828, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9587289094924927, "global_step": 627829, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.01955246925354, "global_step": 627830, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.8803826570510864, "global_step": 627831, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9765013456344604, "global_step": 627832, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9750096797943115, "global_step": 627833, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0639796257019043, "global_step": 627834, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.009586811065674, "global_step": 627835, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9448972940444946, "global_step": 627836, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9583711624145508, "global_step": 627837, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9645049571990967, "global_step": 627838, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.032142162322998, "global_step": 627839, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9696059226989746, "global_step": 627840, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.076411485671997, "global_step": 627841, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0150349140167236, "global_step": 627842, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9868916273117065, "global_step": 627843, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.077746629714966, "global_step": 627844, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9557875394821167, "global_step": 627845, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9917232990264893, "global_step": 627846, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9993066787719727, "global_step": 627847, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0083858966827393, "global_step": 627848, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9728094339370728, "global_step": 627849, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.009916067123413, "global_step": 627850, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.039780378341675, "global_step": 627851, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.899505615234375, "global_step": 627852, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9016342163085938, "global_step": 627853, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.049365997314453, "global_step": 627854, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.044194459915161, "global_step": 627855, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.08709716796875, "global_step": 627856, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0510666370391846, "global_step": 627857, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9610646963119507, "global_step": 627858, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.027188777923584, "global_step": 627859, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0263733863830566, "global_step": 627860, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0362658500671387, "global_step": 627861, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0514395236968994, "global_step": 627862, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9726409912109375, "global_step": 627863, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9042222499847412, "global_step": 627864, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.994138240814209, "global_step": 627865, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0613911151885986, "global_step": 627866, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9914703369140625, "global_step": 627867, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9375710487365723, "global_step": 627868, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9745824337005615, "global_step": 627869, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.928335189819336, "global_step": 627870, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1082708835601807, "global_step": 627871, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0769169330596924, "global_step": 627872, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9831163883209229, "global_step": 627873, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9187806844711304, "global_step": 627874, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0004563331604004, "global_step": 627875, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0116281509399414, "global_step": 627876, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9092144966125488, "global_step": 627877, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0490171909332275, "global_step": 627878, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.035764694213867, "global_step": 627879, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.022020101547241, "global_step": 627880, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.997344732284546, "global_step": 627881, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0058953762054443, "global_step": 627882, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.014206886291504, "global_step": 627883, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9247584342956543, "global_step": 627884, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.029900550842285, "global_step": 627885, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0103659629821777, "global_step": 627886, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9776848554611206, "global_step": 627887, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.02154541015625, "global_step": 627888, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0066168308258057, "global_step": 627889, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0229530334472656, "global_step": 627890, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9819508790969849, "global_step": 627891, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0399186611175537, "global_step": 627892, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0431971549987793, "global_step": 627893, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0162248611450195, "global_step": 627894, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0386545658111572, "global_step": 627895, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0261199474334717, "global_step": 627896, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0299532413482666, "global_step": 627897, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0436456203460693, "global_step": 627898, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.035123825073242, "global_step": 627899, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.021042585372925, "global_step": 627900, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9200993776321411, "global_step": 627901, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0484769344329834, "global_step": 627902, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.031585693359375, "global_step": 627903, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9151450395584106, "global_step": 627904, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9998401403427124, "global_step": 627905, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9734594821929932, "global_step": 627906, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.022294759750366, "global_step": 627907, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.043581247329712, "global_step": 627908, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.021854877471924, "global_step": 627909, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9881114959716797, "global_step": 627910, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9964405298233032, "global_step": 627911, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.001340389251709, "global_step": 627912, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0067293643951416, "global_step": 627913, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0336830615997314, "global_step": 627914, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.06169056892395, "global_step": 627915, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.059234142303467, "global_step": 627916, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0112972259521484, "global_step": 627917, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.984997272491455, "global_step": 627918, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.016068935394287, "global_step": 627919, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9913994073867798, "global_step": 627920, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.046790838241577, "global_step": 627921, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9525153636932373, "global_step": 627922, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9144421815872192, "global_step": 627923, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0438122749328613, "global_step": 627924, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0279316902160645, "global_step": 627925, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.983251690864563, "global_step": 627926, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0186479091644287, "global_step": 627927, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9740915298461914, "global_step": 627928, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9689204692840576, "global_step": 627929, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.050661325454712, "global_step": 627930, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.016223907470703, "global_step": 627931, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9635100364685059, "global_step": 627932, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.957995057106018, "global_step": 627933, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9287694692611694, "global_step": 627934, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.991363286972046, "global_step": 627935, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9770183563232422, "global_step": 627936, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0534865856170654, "global_step": 627937, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9795395135879517, "global_step": 627938, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.034776449203491, "global_step": 627939, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.060296058654785, "global_step": 627940, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9639309644699097, "global_step": 627941, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9962323904037476, "global_step": 627942, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1150546073913574, "global_step": 627943, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0680699348449707, "global_step": 627944, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0317625999450684, "global_step": 627945, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.998206615447998, "global_step": 627946, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0205130577087402, "global_step": 627947, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0007388591766357, "global_step": 627948, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.990919589996338, "global_step": 627949, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0323379039764404, "global_step": 627950, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9563074111938477, "global_step": 627951, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0557265281677246, "global_step": 627952, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0111050605773926, "global_step": 627953, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9560596942901611, "global_step": 627954, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0250542163848877, "global_step": 627955, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0003774166107178, "global_step": 627956, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.069953441619873, "global_step": 627957, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0952892303466797, "global_step": 627958, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.057344436645508, "global_step": 627959, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.962984323501587, "global_step": 627960, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0230565071105957, "global_step": 627961, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0905208587646484, "global_step": 627962, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9659478664398193, "global_step": 627963, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.991661548614502, "global_step": 627964, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9717105627059937, "global_step": 627965, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1062378883361816, "global_step": 627966, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0482177734375, "global_step": 627967, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0168964862823486, "global_step": 627968, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9947967529296875, "global_step": 627969, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.079179286956787, "global_step": 627970, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.998974323272705, "global_step": 627971, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.093057632446289, "global_step": 627972, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0131988525390625, "global_step": 627973, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0160105228424072, "global_step": 627974, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.994700312614441, "global_step": 627975, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0035548210144043, "global_step": 627976, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0846078395843506, "global_step": 627977, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9692094326019287, "global_step": 627978, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0023915767669678, "global_step": 627979, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0414834022521973, "global_step": 627980, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.072861909866333, "global_step": 627981, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0781686305999756, "global_step": 627982, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0369555950164795, "global_step": 627983, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0046544075012207, "global_step": 627984, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9836872816085815, "global_step": 627985, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0474507808685303, "global_step": 627986, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0968964099884033, "global_step": 627987, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9743353128433228, "global_step": 627988, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9606014490127563, "global_step": 627989, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0697500705718994, "global_step": 627990, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0101189613342285, "global_step": 627991, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0135178565979004, "global_step": 627992, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0849032402038574, "global_step": 627993, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.969843864440918, "global_step": 627994, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.012164354324341, "global_step": 627995, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9827523231506348, "global_step": 627996, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0083260536193848, "global_step": 627997, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0807902812957764, "global_step": 627998, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0693182945251465, "global_step": 627999, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0049033164978027, "global_step": 628000, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0227391719818115, "global_step": 628001, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0231425762176514, "global_step": 628002, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.062699556350708, "global_step": 628003, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.075474262237549, "global_step": 628004, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9459360837936401, "global_step": 628005, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0142242908477783, "global_step": 628006, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1100246906280518, "global_step": 628007, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9711103439331055, "global_step": 628008, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0879154205322266, "global_step": 628009, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9781138896942139, "global_step": 628010, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.065056800842285, "global_step": 628011, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.1253676414489746, "global_step": 628012, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0497491359710693, "global_step": 628013, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.056985855102539, "global_step": 628014, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9495161771774292, "global_step": 628015, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9701282978057861, "global_step": 628016, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9409422874450684, "global_step": 628017, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9171189069747925, "global_step": 628018, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9368306398391724, "global_step": 628019, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0571985244750977, "global_step": 628020, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0198426246643066, "global_step": 628021, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9908686876296997, "global_step": 628022, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9777004718780518, "global_step": 628023, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0789949893951416, "global_step": 628024, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.042043447494507, "global_step": 628025, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9653170108795166, "global_step": 628026, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9973900318145752, "global_step": 628027, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.892634391784668, "global_step": 628028, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9280084371566772, "global_step": 628029, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9870022535324097, "global_step": 628030, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9933338165283203, "global_step": 628031, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0392282009124756, "global_step": 628032, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9325181245803833, "global_step": 628033, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.048511028289795, "global_step": 628034, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9982796907424927, "global_step": 628035, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0571014881134033, "global_step": 628036, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.067094326019287, "global_step": 628037, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.023181915283203, "global_step": 628038, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.069345235824585, "global_step": 628039, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9744468927383423, "global_step": 628040, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.9470914602279663, "global_step": 628041, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.046578884124756, "global_step": 628042, "epoch": 996, "lr": 5e-05}
{"train_loss": 2.0043606758117676, "global_step": 628043, "epoch": 996, "lr": 5e-05}
{"train_loss": 1.971929669380188, "global_step": 628044, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9048265218734741, "global_step": 628045, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9481785297393799, "global_step": 628046, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0876095294952393, "global_step": 628047, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.967962384223938, "global_step": 628048, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0542287826538086, "global_step": 628049, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0302746295928955, "global_step": 628050, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0118560791015625, "global_step": 628051, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.020442247390747, "global_step": 628052, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0660669803619385, "global_step": 628053, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9623245000839233, "global_step": 628054, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0325913429260254, "global_step": 628055, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9639827013015747, "global_step": 628056, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9985864162445068, "global_step": 628057, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0132007598876953, "global_step": 628058, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8599739074707031, "global_step": 628059, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9485198259353638, "global_step": 628060, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9919986724853516, "global_step": 628061, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9288383722305298, "global_step": 628062, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9900538921356201, "global_step": 628063, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0322651863098145, "global_step": 628064, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.046138048171997, "global_step": 628065, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9815672636032104, "global_step": 628066, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0081381797790527, "global_step": 628067, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9451428651809692, "global_step": 628068, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9989233016967773, "global_step": 628069, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0538337230682373, "global_step": 628070, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.971326231956482, "global_step": 628071, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9972126483917236, "global_step": 628072, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9190821647644043, "global_step": 628073, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.980238914489746, "global_step": 628074, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9686535596847534, "global_step": 628075, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9669177532196045, "global_step": 628076, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.017693042755127, "global_step": 628077, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9320517778396606, "global_step": 628078, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.939019799232483, "global_step": 628079, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.024085760116577, "global_step": 628080, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9162572622299194, "global_step": 628081, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9536672830581665, "global_step": 628082, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9877896308898926, "global_step": 628083, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9312876462936401, "global_step": 628084, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9513238668441772, "global_step": 628085, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0289270877838135, "global_step": 628086, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9958152770996094, "global_step": 628087, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.061541795730591, "global_step": 628088, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0775043964385986, "global_step": 628089, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9768587350845337, "global_step": 628090, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9916318655014038, "global_step": 628091, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.035384178161621, "global_step": 628092, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0000851154327393, "global_step": 628093, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9624940156936646, "global_step": 628094, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.038698434829712, "global_step": 628095, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9790083169937134, "global_step": 628096, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9502371549606323, "global_step": 628097, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0478148460388184, "global_step": 628098, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9706746339797974, "global_step": 628099, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.983430027961731, "global_step": 628100, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8833179473876953, "global_step": 628101, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.980891227722168, "global_step": 628102, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9457218647003174, "global_step": 628103, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.006962537765503, "global_step": 628104, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.896486520767212, "global_step": 628105, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9518423080444336, "global_step": 628106, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.955671787261963, "global_step": 628107, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.956274151802063, "global_step": 628108, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.080409049987793, "global_step": 628109, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9521000385284424, "global_step": 628110, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0011918544769287, "global_step": 628111, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9600437879562378, "global_step": 628112, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.068622350692749, "global_step": 628113, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9946982860565186, "global_step": 628114, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9788366556167603, "global_step": 628115, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0606560707092285, "global_step": 628116, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.966604471206665, "global_step": 628117, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0538992881774902, "global_step": 628118, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9457509517669678, "global_step": 628119, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.051758050918579, "global_step": 628120, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0479934215545654, "global_step": 628121, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0860087871551514, "global_step": 628122, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8831325769424438, "global_step": 628123, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9897862672805786, "global_step": 628124, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9728435277938843, "global_step": 628125, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0628468990325928, "global_step": 628126, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9561927318572998, "global_step": 628127, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9888501167297363, "global_step": 628128, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9965548515319824, "global_step": 628129, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.983435869216919, "global_step": 628130, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9728093147277832, "global_step": 628131, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9926443099975586, "global_step": 628132, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.004852533340454, "global_step": 628133, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.973433494567871, "global_step": 628134, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.006910562515259, "global_step": 628135, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9418166875839233, "global_step": 628136, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9359530210494995, "global_step": 628137, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0406055450439453, "global_step": 628138, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9689364433288574, "global_step": 628139, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.042597532272339, "global_step": 628140, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.970152497291565, "global_step": 628141, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9560619592666626, "global_step": 628142, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9842089414596558, "global_step": 628143, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9662041664123535, "global_step": 628144, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0052943229675293, "global_step": 628145, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.981567621231079, "global_step": 628146, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.934160828590393, "global_step": 628147, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9489433765411377, "global_step": 628148, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0572564601898193, "global_step": 628149, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9874976873397827, "global_step": 628150, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9277095794677734, "global_step": 628151, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0837342739105225, "global_step": 628152, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0289671421051025, "global_step": 628153, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.971009612083435, "global_step": 628154, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.051201343536377, "global_step": 628155, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9598863124847412, "global_step": 628156, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0474894046783447, "global_step": 628157, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.019841432571411, "global_step": 628158, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.96396803855896, "global_step": 628159, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9154317378997803, "global_step": 628160, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9231250286102295, "global_step": 628161, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0009281635284424, "global_step": 628162, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9461606740951538, "global_step": 628163, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9430793523788452, "global_step": 628164, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.000154733657837, "global_step": 628165, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.021590232849121, "global_step": 628166, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9111576080322266, "global_step": 628167, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9456801414489746, "global_step": 628168, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9762778282165527, "global_step": 628169, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9940184354782104, "global_step": 628170, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9917305707931519, "global_step": 628171, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0090646743774414, "global_step": 628172, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0171849727630615, "global_step": 628173, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0442893505096436, "global_step": 628174, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9221526384353638, "global_step": 628175, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.05155348777771, "global_step": 628176, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0244245529174805, "global_step": 628177, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9774106740951538, "global_step": 628178, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9483428001403809, "global_step": 628179, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.017023801803589, "global_step": 628180, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9269707202911377, "global_step": 628181, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9451836347579956, "global_step": 628182, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0050806999206543, "global_step": 628183, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0116608142852783, "global_step": 628184, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9731781482696533, "global_step": 628185, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9740036725997925, "global_step": 628186, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.05892014503479, "global_step": 628187, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0995988845825195, "global_step": 628188, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9734039306640625, "global_step": 628189, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.007758140563965, "global_step": 628190, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9863860607147217, "global_step": 628191, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9936935901641846, "global_step": 628192, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9697345495224, "global_step": 628193, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.015373945236206, "global_step": 628194, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0252645015716553, "global_step": 628195, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0545125007629395, "global_step": 628196, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.953920602798462, "global_step": 628197, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.099443197250366, "global_step": 628198, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9709135293960571, "global_step": 628199, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9787969589233398, "global_step": 628200, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.979810357093811, "global_step": 628201, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9323245286941528, "global_step": 628202, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0199525356292725, "global_step": 628203, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9507044553756714, "global_step": 628204, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0626327991485596, "global_step": 628205, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.936016321182251, "global_step": 628206, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8924024105072021, "global_step": 628207, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9930435419082642, "global_step": 628208, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0412893295288086, "global_step": 628209, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.047419786453247, "global_step": 628210, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0125012397766113, "global_step": 628211, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9364137649536133, "global_step": 628212, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0458028316497803, "global_step": 628213, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.046184778213501, "global_step": 628214, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.988330364227295, "global_step": 628215, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.037594795227051, "global_step": 628216, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8740251064300537, "global_step": 628217, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9514198303222656, "global_step": 628218, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0153074264526367, "global_step": 628219, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9438139200210571, "global_step": 628220, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0696961879730225, "global_step": 628221, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0655789375305176, "global_step": 628222, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0188984870910645, "global_step": 628223, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9652351140975952, "global_step": 628224, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.003262519836426, "global_step": 628225, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0153114795684814, "global_step": 628226, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0154590606689453, "global_step": 628227, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.013862133026123, "global_step": 628228, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.015573263168335, "global_step": 628229, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9931524991989136, "global_step": 628230, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.020571708679199, "global_step": 628231, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.010852098464966, "global_step": 628232, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9888997077941895, "global_step": 628233, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9830856323242188, "global_step": 628234, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9040322303771973, "global_step": 628235, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9585124254226685, "global_step": 628236, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.05098032951355, "global_step": 628237, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.033259868621826, "global_step": 628238, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9922524690628052, "global_step": 628239, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.971618890762329, "global_step": 628240, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.029998302459717, "global_step": 628241, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8969677686691284, "global_step": 628242, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9934931993484497, "global_step": 628243, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.101867198944092, "global_step": 628244, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0509748458862305, "global_step": 628245, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.026405096054077, "global_step": 628246, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9720659255981445, "global_step": 628247, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0576629638671875, "global_step": 628248, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9755929708480835, "global_step": 628249, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.020909547805786, "global_step": 628250, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0358052253723145, "global_step": 628251, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.060671091079712, "global_step": 628252, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.000617504119873, "global_step": 628253, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0402872562408447, "global_step": 628254, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0007517337799072, "global_step": 628255, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1227705478668213, "global_step": 628256, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9733965396881104, "global_step": 628257, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0544233322143555, "global_step": 628258, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.000678062438965, "global_step": 628259, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.074774742126465, "global_step": 628260, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0624656677246094, "global_step": 628261, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0093374252319336, "global_step": 628262, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.049957752227783, "global_step": 628263, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9394217729568481, "global_step": 628264, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.961477279663086, "global_step": 628265, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9758660793304443, "global_step": 628266, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0087525844573975, "global_step": 628267, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9531888961791992, "global_step": 628268, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0190751552581787, "global_step": 628269, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9606194496154785, "global_step": 628270, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9644149541854858, "global_step": 628271, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9856044054031372, "global_step": 628272, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9730297327041626, "global_step": 628273, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.937691330909729, "global_step": 628274, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9858555793762207, "global_step": 628275, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0163233280181885, "global_step": 628276, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0311431884765625, "global_step": 628277, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9825100898742676, "global_step": 628278, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.031158447265625, "global_step": 628279, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9878345727920532, "global_step": 628280, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9566411972045898, "global_step": 628281, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9391508102416992, "global_step": 628282, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0028533935546875, "global_step": 628283, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0357961654663086, "global_step": 628284, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0755584239959717, "global_step": 628285, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.997498631477356, "global_step": 628286, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.004132032394409, "global_step": 628287, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9542200565338135, "global_step": 628288, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0910491943359375, "global_step": 628289, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0240156650543213, "global_step": 628290, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8673744201660156, "global_step": 628291, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.06278920173645, "global_step": 628292, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.047748565673828, "global_step": 628293, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9865397214889526, "global_step": 628294, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9733250141143799, "global_step": 628295, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.012281894683838, "global_step": 628296, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9830482006072998, "global_step": 628297, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9946482181549072, "global_step": 628298, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0357015132904053, "global_step": 628299, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.044243097305298, "global_step": 628300, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9724962711334229, "global_step": 628301, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0622684955596924, "global_step": 628302, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.946387529373169, "global_step": 628303, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0220727920532227, "global_step": 628304, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9893525838851929, "global_step": 628305, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9615166187286377, "global_step": 628306, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.053152084350586, "global_step": 628307, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0054404735565186, "global_step": 628308, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0563931465148926, "global_step": 628309, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0000224113464355, "global_step": 628310, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9866681098937988, "global_step": 628311, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0170369148254395, "global_step": 628312, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0355148315429688, "global_step": 628313, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0717670917510986, "global_step": 628314, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8992832899093628, "global_step": 628315, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.024487018585205, "global_step": 628316, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.040250301361084, "global_step": 628317, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9908974170684814, "global_step": 628318, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9040006399154663, "global_step": 628319, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9595528841018677, "global_step": 628320, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0129003524780273, "global_step": 628321, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9810962677001953, "global_step": 628322, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9907938241958618, "global_step": 628323, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.949059009552002, "global_step": 628324, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0850555896759033, "global_step": 628325, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9511656761169434, "global_step": 628326, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9824379682540894, "global_step": 628327, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.057504177093506, "global_step": 628328, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.005388021469116, "global_step": 628329, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.02400541305542, "global_step": 628330, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0970606803894043, "global_step": 628331, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0177621841430664, "global_step": 628332, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9890239238739014, "global_step": 628333, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.919935703277588, "global_step": 628334, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9575424194335938, "global_step": 628335, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0585572719573975, "global_step": 628336, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.020266532897949, "global_step": 628337, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.98777174949646, "global_step": 628338, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.014606237411499, "global_step": 628339, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0438075065612793, "global_step": 628340, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9467283487319946, "global_step": 628341, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9845163822174072, "global_step": 628342, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.981910228729248, "global_step": 628343, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8984800577163696, "global_step": 628344, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9698796272277832, "global_step": 628345, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.949364423751831, "global_step": 628346, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.017076015472412, "global_step": 628347, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.03204607963562, "global_step": 628348, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9960683584213257, "global_step": 628349, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0471346378326416, "global_step": 628350, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.957217812538147, "global_step": 628351, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.928053617477417, "global_step": 628352, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9722707271575928, "global_step": 628353, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9215434789657593, "global_step": 628354, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0387136936187744, "global_step": 628355, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0423858165740967, "global_step": 628356, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0750367641448975, "global_step": 628357, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.017719030380249, "global_step": 628358, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1249985694885254, "global_step": 628359, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9924761056900024, "global_step": 628360, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0014991760253906, "global_step": 628361, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9731086492538452, "global_step": 628362, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0614421367645264, "global_step": 628363, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8783375024795532, "global_step": 628364, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.04211163520813, "global_step": 628365, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.937657117843628, "global_step": 628366, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9751046895980835, "global_step": 628367, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.012315273284912, "global_step": 628368, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0277259349823, "global_step": 628369, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0596091747283936, "global_step": 628370, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9906589984893799, "global_step": 628371, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0022881031036377, "global_step": 628372, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9421663284301758, "global_step": 628373, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.028075933456421, "global_step": 628374, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0187506675720215, "global_step": 628375, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1504805088043213, "global_step": 628376, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9168397188186646, "global_step": 628377, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0181164741516113, "global_step": 628378, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9451311826705933, "global_step": 628379, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9997341632843018, "global_step": 628380, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.005904197692871, "global_step": 628381, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.951377272605896, "global_step": 628382, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0417428016662598, "global_step": 628383, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.984346628189087, "global_step": 628384, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0447516441345215, "global_step": 628385, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9388185739517212, "global_step": 628386, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.039886951446533, "global_step": 628387, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9655866622924805, "global_step": 628388, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0607032775878906, "global_step": 628389, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0480716228485107, "global_step": 628390, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0877184867858887, "global_step": 628391, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0091392993927, "global_step": 628392, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.902890920639038, "global_step": 628393, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.950588583946228, "global_step": 628394, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0969748497009277, "global_step": 628395, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0175726413726807, "global_step": 628396, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0003225803375244, "global_step": 628397, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0071794986724854, "global_step": 628398, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9917399883270264, "global_step": 628399, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9976764917373657, "global_step": 628400, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0333704948425293, "global_step": 628401, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.006727457046509, "global_step": 628402, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9530967473983765, "global_step": 628403, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0049736499786377, "global_step": 628404, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9938528537750244, "global_step": 628405, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0476701259613037, "global_step": 628406, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9495073556900024, "global_step": 628407, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.021599054336548, "global_step": 628408, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.02728271484375, "global_step": 628409, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9960660934448242, "global_step": 628410, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9255160093307495, "global_step": 628411, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.057551145553589, "global_step": 628412, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.96171236038208, "global_step": 628413, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.091221809387207, "global_step": 628414, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0374484062194824, "global_step": 628415, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0463240146636963, "global_step": 628416, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9621893167495728, "global_step": 628417, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.102884292602539, "global_step": 628418, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9522922039031982, "global_step": 628419, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.034843683242798, "global_step": 628420, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.090041160583496, "global_step": 628421, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9445255994796753, "global_step": 628422, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.921831727027893, "global_step": 628423, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9942089319229126, "global_step": 628424, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.02862811088562, "global_step": 628425, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9567066431045532, "global_step": 628426, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.984704852104187, "global_step": 628427, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0697755813598633, "global_step": 628428, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.016381025314331, "global_step": 628429, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.962789535522461, "global_step": 628430, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9263590574264526, "global_step": 628431, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.032443046569824, "global_step": 628432, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0181031227111816, "global_step": 628433, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9813635349273682, "global_step": 628434, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.051086664199829, "global_step": 628435, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9715043306350708, "global_step": 628436, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0418460369110107, "global_step": 628437, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.992549180984497, "global_step": 628438, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9943419694900513, "global_step": 628439, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.050032615661621, "global_step": 628440, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0329928398132324, "global_step": 628441, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.04718279838562, "global_step": 628442, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9437543153762817, "global_step": 628443, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9604012966156006, "global_step": 628444, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0857346057891846, "global_step": 628445, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.029834747314453, "global_step": 628446, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0495870113372803, "global_step": 628447, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.969421625137329, "global_step": 628448, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0031051635742188, "global_step": 628449, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.096712827682495, "global_step": 628450, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9656522274017334, "global_step": 628451, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.016735315322876, "global_step": 628452, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0188491344451904, "global_step": 628453, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9952750205993652, "global_step": 628454, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.011491298675537, "global_step": 628455, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.063117742538452, "global_step": 628456, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.122319459915161, "global_step": 628457, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9806843996047974, "global_step": 628458, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.932560682296753, "global_step": 628459, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.957064151763916, "global_step": 628460, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.047308921813965, "global_step": 628461, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9210867881774902, "global_step": 628462, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9038876295089722, "global_step": 628463, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.010502338409424, "global_step": 628464, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0683212280273438, "global_step": 628465, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.04471492767334, "global_step": 628466, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.998270034790039, "global_step": 628467, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9676967859268188, "global_step": 628468, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9893581867218018, "global_step": 628469, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9434714317321777, "global_step": 628470, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.054250955581665, "global_step": 628471, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0139236450195312, "global_step": 628472, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9519511461257935, "global_step": 628473, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8712050914764404, "global_step": 628474, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9441041946411133, "global_step": 628475, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9399648904800415, "global_step": 628476, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.024722099304199, "global_step": 628477, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0462820529937744, "global_step": 628478, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9329125881195068, "global_step": 628479, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0777158737182617, "global_step": 628480, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.092689037322998, "global_step": 628481, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0418548583984375, "global_step": 628482, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.051544189453125, "global_step": 628483, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0425562858581543, "global_step": 628484, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0236904621124268, "global_step": 628485, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0414886474609375, "global_step": 628486, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9853955507278442, "global_step": 628487, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.977662444114685, "global_step": 628488, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0092129707336426, "global_step": 628489, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9137251377105713, "global_step": 628490, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9794652462005615, "global_step": 628491, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.983158826828003, "global_step": 628492, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0660624504089355, "global_step": 628493, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.020010232925415, "global_step": 628494, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9827154874801636, "global_step": 628495, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9655722379684448, "global_step": 628496, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9464799165725708, "global_step": 628497, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.030972480773926, "global_step": 628498, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9866788387298584, "global_step": 628499, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9562114477157593, "global_step": 628500, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.02209734916687, "global_step": 628501, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.082273244857788, "global_step": 628502, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.986448049545288, "global_step": 628503, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1286652088165283, "global_step": 628504, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9717344045639038, "global_step": 628505, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9739711284637451, "global_step": 628506, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0007143020629883, "global_step": 628507, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9707212448120117, "global_step": 628508, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9801170825958252, "global_step": 628509, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9647252559661865, "global_step": 628510, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0124521255493164, "global_step": 628511, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9546688795089722, "global_step": 628512, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9242972135543823, "global_step": 628513, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9844844341278076, "global_step": 628514, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9798663854599, "global_step": 628515, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0529847145080566, "global_step": 628516, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.00870418548584, "global_step": 628517, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9944493770599365, "global_step": 628518, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9272575378417969, "global_step": 628519, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0155560970306396, "global_step": 628520, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9887964725494385, "global_step": 628521, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9223215579986572, "global_step": 628522, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9196609258651733, "global_step": 628523, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0527656078338623, "global_step": 628524, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9167147874832153, "global_step": 628525, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9513137340545654, "global_step": 628526, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.001737356185913, "global_step": 628527, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0322961807250977, "global_step": 628528, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9327987432479858, "global_step": 628529, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.086385488510132, "global_step": 628530, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0481057167053223, "global_step": 628531, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0086522102355957, "global_step": 628532, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0671730041503906, "global_step": 628533, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.031863212585449, "global_step": 628534, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.08522891998291, "global_step": 628535, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0357184410095215, "global_step": 628536, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.005275011062622, "global_step": 628537, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.954869031906128, "global_step": 628538, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0347864627838135, "global_step": 628539, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.09647536277771, "global_step": 628540, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9034371376037598, "global_step": 628541, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.010134220123291, "global_step": 628542, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9482632875442505, "global_step": 628543, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.952408790588379, "global_step": 628544, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0729379653930664, "global_step": 628545, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9972877502441406, "global_step": 628546, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0146586894989014, "global_step": 628547, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9756653308868408, "global_step": 628548, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9403722286224365, "global_step": 628549, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9613579511642456, "global_step": 628550, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9269487857818604, "global_step": 628551, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.060667037963867, "global_step": 628552, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.046992063522339, "global_step": 628553, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.032963514328003, "global_step": 628554, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.026981830596924, "global_step": 628555, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.049551248550415, "global_step": 628556, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9564099311828613, "global_step": 628557, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.047642230987549, "global_step": 628558, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.036771535873413, "global_step": 628559, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0082576274871826, "global_step": 628560, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9907537698745728, "global_step": 628561, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.037712335586548, "global_step": 628562, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.00242280960083, "global_step": 628563, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9234918355941772, "global_step": 628564, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9706181287765503, "global_step": 628565, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0558104515075684, "global_step": 628566, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0469014644622803, "global_step": 628567, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8928629159927368, "global_step": 628568, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.041287660598755, "global_step": 628569, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0418601036071777, "global_step": 628570, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.952692985534668, "global_step": 628571, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.981484055519104, "global_step": 628572, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0560479164123535, "global_step": 628573, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0719780921936035, "global_step": 628574, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.039030075073242, "global_step": 628575, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9652845859527588, "global_step": 628576, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0465574264526367, "global_step": 628577, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9928123950958252, "global_step": 628578, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9338316917419434, "global_step": 628579, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.066209554672241, "global_step": 628580, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0255093574523926, "global_step": 628581, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8997786045074463, "global_step": 628582, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0099289417266846, "global_step": 628583, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9397276639938354, "global_step": 628584, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.972510576248169, "global_step": 628585, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0241963863372803, "global_step": 628586, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.043752431869507, "global_step": 628587, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.095881938934326, "global_step": 628588, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9979453086853027, "global_step": 628589, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0118582248687744, "global_step": 628590, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9569826126098633, "global_step": 628591, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.020050525665283, "global_step": 628592, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.895424246788025, "global_step": 628593, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.082615852355957, "global_step": 628594, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.014512538909912, "global_step": 628595, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9998347759246826, "global_step": 628596, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9268001317977905, "global_step": 628597, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.007612943649292, "global_step": 628598, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9501729011535645, "global_step": 628599, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9684531688690186, "global_step": 628600, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9265714883804321, "global_step": 628601, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.001676321029663, "global_step": 628602, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.972695231437683, "global_step": 628603, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1070303916931152, "global_step": 628604, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.010531187057495, "global_step": 628605, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0129036903381348, "global_step": 628606, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9738608598709106, "global_step": 628607, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9398916959762573, "global_step": 628608, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.038722276687622, "global_step": 628609, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.019371509552002, "global_step": 628610, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9709975719451904, "global_step": 628611, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1093850135803223, "global_step": 628612, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.071850061416626, "global_step": 628613, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9855620861053467, "global_step": 628614, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0556788444519043, "global_step": 628615, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.975683331489563, "global_step": 628616, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9849094152450562, "global_step": 628617, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.110866069793701, "global_step": 628618, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0220847129821777, "global_step": 628619, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.050856590270996, "global_step": 628620, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9252400398254395, "global_step": 628621, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.001617431640625, "global_step": 628622, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.045144557952881, "global_step": 628623, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0725507736206055, "global_step": 628624, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0508651733398438, "global_step": 628625, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.076970338821411, "global_step": 628626, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9651215076446533, "global_step": 628627, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9834837913513184, "global_step": 628628, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0594582557678223, "global_step": 628629, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.062244176864624, "global_step": 628630, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9841182231903076, "global_step": 628631, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8902168273925781, "global_step": 628632, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0428478717803955, "global_step": 628633, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9743322134017944, "global_step": 628634, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9135267734527588, "global_step": 628635, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0452380180358887, "global_step": 628636, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0170509815216064, "global_step": 628637, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0689289569854736, "global_step": 628638, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9100871086120605, "global_step": 628639, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0163304805755615, "global_step": 628640, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.082134485244751, "global_step": 628641, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0443694591522217, "global_step": 628642, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9802558422088623, "global_step": 628643, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8952590227127075, "global_step": 628644, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9753159284591675, "global_step": 628645, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9693307876586914, "global_step": 628646, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0303096771240234, "global_step": 628647, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9805538654327393, "global_step": 628648, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.985251545906067, "global_step": 628649, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0442049503326416, "global_step": 628650, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0058822631835938, "global_step": 628651, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.078662157058716, "global_step": 628652, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.023922920227051, "global_step": 628653, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9686996936798096, "global_step": 628654, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.030586004257202, "global_step": 628655, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.976894497871399, "global_step": 628656, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0632078647613525, "global_step": 628657, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.979566216468811, "global_step": 628658, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.924052119255066, "global_step": 628659, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.039102077484131, "global_step": 628660, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0096943378448486, "global_step": 628661, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0210020542144775, "global_step": 628662, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9866317510604858, "global_step": 628663, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.029294013977051, "global_step": 628664, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9903534650802612, "global_step": 628665, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0715384483337402, "global_step": 628666, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.005415201187134, "global_step": 628667, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.993709921836853, "global_step": 628668, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0452334880828857, "global_step": 628669, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0142226219177246, "global_step": 628670, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0516152381896973, "global_step": 628671, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.02032208442688, "global_step": 628672, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9985265731811523, "global_step": 628673, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0639567375183105, "global_step": 628674, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.050788640975952, "global_step": 628675, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.039492607116699, "global_step": 628676, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.034442901611328, "global_step": 628677, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9477205276489258, "global_step": 628678, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0440313816070557, "global_step": 628679, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.054270029067993, "global_step": 628680, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.069514513015747, "global_step": 628681, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.015684127807617, "global_step": 628682, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.996931791305542, "global_step": 628683, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.985180377960205, "global_step": 628684, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9711683988571167, "global_step": 628685, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9728200435638428, "global_step": 628686, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0993144512176514, "global_step": 628687, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.032212734222412, "global_step": 628688, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0336437225341797, "global_step": 628689, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9331490993499756, "global_step": 628690, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0413246154785156, "global_step": 628691, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.914669394493103, "global_step": 628692, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.010876417160034, "global_step": 628693, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0233967304229736, "global_step": 628694, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9724018573760986, "global_step": 628695, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.023465394973755, "global_step": 628696, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0326907634735107, "global_step": 628697, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9961105585098267, "global_step": 628698, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0447635650634766, "global_step": 628699, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.024783134460449, "global_step": 628700, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9451916217803955, "global_step": 628701, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.030496835708618, "global_step": 628702, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.977087378501892, "global_step": 628703, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1321423053741455, "global_step": 628704, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9904310703277588, "global_step": 628705, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.007934093475342, "global_step": 628706, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.929660677909851, "global_step": 628707, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.949157953262329, "global_step": 628708, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.992207407951355, "global_step": 628709, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.990450143814087, "global_step": 628710, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9466291666030884, "global_step": 628711, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9918724298477173, "global_step": 628712, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0588486194610596, "global_step": 628713, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9605942964553833, "global_step": 628714, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0114946365356445, "global_step": 628715, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9984383583068848, "global_step": 628716, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9270685911178589, "global_step": 628717, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0853214263916016, "global_step": 628718, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0364925861358643, "global_step": 628719, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.048635959625244, "global_step": 628720, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.050967216491699, "global_step": 628721, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0793514251708984, "global_step": 628722, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9682046175003052, "global_step": 628723, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.957669734954834, "global_step": 628724, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0671796798706055, "global_step": 628725, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0627808570861816, "global_step": 628726, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9573131799697876, "global_step": 628727, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.074753761291504, "global_step": 628728, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.068790912628174, "global_step": 628729, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.836037516593933, "global_step": 628730, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9839322566986084, "global_step": 628731, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8887101411819458, "global_step": 628732, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0338501930236816, "global_step": 628733, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.031649351119995, "global_step": 628734, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9599711894989014, "global_step": 628735, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9684191942214966, "global_step": 628736, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.969667673110962, "global_step": 628737, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9887933731079102, "global_step": 628738, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9444005489349365, "global_step": 628739, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.064488172531128, "global_step": 628740, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0478267669677734, "global_step": 628741, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.991959571838379, "global_step": 628742, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0774478912353516, "global_step": 628743, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.090062141418457, "global_step": 628744, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9630647897720337, "global_step": 628745, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9732792377471924, "global_step": 628746, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9549423456192017, "global_step": 628747, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9822568893432617, "global_step": 628748, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9860419034957886, "global_step": 628749, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0658020973205566, "global_step": 628750, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0947444438934326, "global_step": 628751, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0918595790863037, "global_step": 628752, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9283572435379028, "global_step": 628753, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0325474739074707, "global_step": 628754, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9930185079574585, "global_step": 628755, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.939497947692871, "global_step": 628756, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.033489942550659, "global_step": 628757, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9512443542480469, "global_step": 628758, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0140650272369385, "global_step": 628759, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0098376274108887, "global_step": 628760, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.004350423812866, "global_step": 628761, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9767426252365112, "global_step": 628762, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.001046657562256, "global_step": 628763, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0461132526397705, "global_step": 628764, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9927561283111572, "global_step": 628765, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9620805978775024, "global_step": 628766, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.061640501022339, "global_step": 628767, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.060469627380371, "global_step": 628768, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0105297565460205, "global_step": 628769, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.012646436691284, "global_step": 628770, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0101070404052734, "global_step": 628771, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0089290142059326, "global_step": 628772, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0318000316619873, "global_step": 628773, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0196478366851807, "global_step": 628774, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.970157265663147, "global_step": 628775, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9716477394104004, "global_step": 628776, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.070099115371704, "global_step": 628777, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.977066993713379, "global_step": 628778, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0168588161468506, "global_step": 628779, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.046111822128296, "global_step": 628780, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9223988056182861, "global_step": 628781, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.000068426132202, "global_step": 628782, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0721120834350586, "global_step": 628783, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0232460498809814, "global_step": 628784, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.979257583618164, "global_step": 628785, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9237021207809448, "global_step": 628786, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0198607444763184, "global_step": 628787, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9544543027877808, "global_step": 628788, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0325276851654053, "global_step": 628789, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.976866364479065, "global_step": 628790, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0466244220733643, "global_step": 628791, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9643608331680298, "global_step": 628792, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.021892786026001, "global_step": 628793, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.058157205581665, "global_step": 628794, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1028547286987305, "global_step": 628795, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.042797803878784, "global_step": 628796, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.996495008468628, "global_step": 628797, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0116944313049316, "global_step": 628798, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0474865436553955, "global_step": 628799, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9946231842041016, "global_step": 628800, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9931628704071045, "global_step": 628801, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9914981126785278, "global_step": 628802, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.992011308670044, "global_step": 628803, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.939305305480957, "global_step": 628804, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0909485816955566, "global_step": 628805, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9551186561584473, "global_step": 628806, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9809410572052002, "global_step": 628807, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9763611555099487, "global_step": 628808, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.968353509902954, "global_step": 628809, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.980202317237854, "global_step": 628810, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0219640731811523, "global_step": 628811, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0606954097747803, "global_step": 628812, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9978121519088745, "global_step": 628813, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.034060478210449, "global_step": 628814, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0324487686157227, "global_step": 628815, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9922418594360352, "global_step": 628816, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.061521053314209, "global_step": 628817, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.000347375869751, "global_step": 628818, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.05267596244812, "global_step": 628819, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9809387922286987, "global_step": 628820, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.055889844894409, "global_step": 628821, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9275431632995605, "global_step": 628822, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0574586391448975, "global_step": 628823, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0018692016601562, "global_step": 628824, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9923080205917358, "global_step": 628825, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9892634153366089, "global_step": 628826, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.005692958831787, "global_step": 628827, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9571679830551147, "global_step": 628828, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9906249046325684, "global_step": 628829, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.102996349334717, "global_step": 628830, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9754157066345215, "global_step": 628831, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0090458393096924, "global_step": 628832, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0662834644317627, "global_step": 628833, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.055264949798584, "global_step": 628834, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.008908987045288, "global_step": 628835, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.069385051727295, "global_step": 628836, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.053619623184204, "global_step": 628837, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.058324098587036, "global_step": 628838, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1444602012634277, "global_step": 628839, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0635759830474854, "global_step": 628840, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9191465377807617, "global_step": 628841, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.99429190158844, "global_step": 628842, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9690262079238892, "global_step": 628843, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9796760082244873, "global_step": 628844, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.082761287689209, "global_step": 628845, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9673492908477783, "global_step": 628846, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.013613700866699, "global_step": 628847, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9379538297653198, "global_step": 628848, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.043846607208252, "global_step": 628849, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9950565099716187, "global_step": 628850, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9953745603561401, "global_step": 628851, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.07236385345459, "global_step": 628852, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9522385597229004, "global_step": 628853, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.055428981781006, "global_step": 628854, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.02549147605896, "global_step": 628855, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9708733558654785, "global_step": 628856, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9848836660385132, "global_step": 628857, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9911481142044067, "global_step": 628858, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9682235717773438, "global_step": 628859, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.111409902572632, "global_step": 628860, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0722763538360596, "global_step": 628861, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.082695484161377, "global_step": 628862, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.91921067237854, "global_step": 628863, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.046466588973999, "global_step": 628864, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0182085037231445, "global_step": 628865, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9347904920578003, "global_step": 628866, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0763320922851562, "global_step": 628867, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.034374237060547, "global_step": 628868, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.99497652053833, "global_step": 628869, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0679218769073486, "global_step": 628870, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0838050842285156, "global_step": 628871, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0107994079589844, "global_step": 628872, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.034956693649292, "global_step": 628873, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0693063735961914, "global_step": 628874, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0538055896759033, "global_step": 628875, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0171704292297363, "global_step": 628876, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9690781831741333, "global_step": 628877, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0337138175964355, "global_step": 628878, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9449176788330078, "global_step": 628879, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0866689682006836, "global_step": 628880, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0296356678009033, "global_step": 628881, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.059117078781128, "global_step": 628882, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.001668930053711, "global_step": 628883, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9398388862609863, "global_step": 628884, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0428240299224854, "global_step": 628885, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0355255603790283, "global_step": 628886, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0465357303619385, "global_step": 628887, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9856419563293457, "global_step": 628888, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9755092859268188, "global_step": 628889, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.016294002532959, "global_step": 628890, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8728828430175781, "global_step": 628891, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0391857624053955, "global_step": 628892, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9906330108642578, "global_step": 628893, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.040393352508545, "global_step": 628894, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9046339988708496, "global_step": 628895, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9523786306381226, "global_step": 628896, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1047377586364746, "global_step": 628897, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0447771549224854, "global_step": 628898, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9774320125579834, "global_step": 628899, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9844610691070557, "global_step": 628900, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.11043119430542, "global_step": 628901, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0963003635406494, "global_step": 628902, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.976913571357727, "global_step": 628903, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0235061645507812, "global_step": 628904, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9350636005401611, "global_step": 628905, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.993248462677002, "global_step": 628906, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0987823009490967, "global_step": 628907, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9463582038879395, "global_step": 628908, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.028615713119507, "global_step": 628909, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0320920944213867, "global_step": 628910, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0243892669677734, "global_step": 628911, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9916398525238037, "global_step": 628912, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.018476963043213, "global_step": 628913, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9831047058105469, "global_step": 628914, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.012587308883667, "global_step": 628915, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.042998790740967, "global_step": 628916, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0447304248809814, "global_step": 628917, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0065932273864746, "global_step": 628918, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0545713901519775, "global_step": 628919, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.015000343322754, "global_step": 628920, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9651896953582764, "global_step": 628921, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.055868148803711, "global_step": 628922, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.989882230758667, "global_step": 628923, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9536020755767822, "global_step": 628924, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.028261184692383, "global_step": 628925, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.990728735923767, "global_step": 628926, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.016879081726074, "global_step": 628927, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9459807872772217, "global_step": 628928, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0481536388397217, "global_step": 628929, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9776241779327393, "global_step": 628930, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0645570755004883, "global_step": 628931, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.020456552505493, "global_step": 628932, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.051957130432129, "global_step": 628933, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9795780181884766, "global_step": 628934, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9836013317108154, "global_step": 628935, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9814205169677734, "global_step": 628936, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.051436185836792, "global_step": 628937, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9773063659667969, "global_step": 628938, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0089006423950195, "global_step": 628939, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9961490631103516, "global_step": 628940, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9625133275985718, "global_step": 628941, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.001523971557617, "global_step": 628942, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.020261764526367, "global_step": 628943, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.087944269180298, "global_step": 628944, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9574930667877197, "global_step": 628945, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.039738178253174, "global_step": 628946, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0189244747161865, "global_step": 628947, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.007122039794922, "global_step": 628948, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0437653064727783, "global_step": 628949, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0001747608184814, "global_step": 628950, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9581152200698853, "global_step": 628951, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9833680391311646, "global_step": 628952, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.983277440071106, "global_step": 628953, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.905890941619873, "global_step": 628954, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0829455852508545, "global_step": 628955, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0060951709747314, "global_step": 628956, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0367751121520996, "global_step": 628957, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9108186960220337, "global_step": 628958, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.038494825363159, "global_step": 628959, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9558014869689941, "global_step": 628960, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9776355028152466, "global_step": 628961, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9483730792999268, "global_step": 628962, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0373172760009766, "global_step": 628963, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.017042636871338, "global_step": 628964, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9545104503631592, "global_step": 628965, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.126509428024292, "global_step": 628966, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.019381523132324, "global_step": 628967, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0864033699035645, "global_step": 628968, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0196261405944824, "global_step": 628969, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.019387722015381, "global_step": 628970, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.092823028564453, "global_step": 628971, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9935146570205688, "global_step": 628972, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9684240818023682, "global_step": 628973, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.960030436515808, "global_step": 628974, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9900789260864258, "global_step": 628975, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.974892497062683, "global_step": 628976, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.010385513305664, "global_step": 628977, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9874284267425537, "global_step": 628978, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.8990647792816162, "global_step": 628979, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9731667041778564, "global_step": 628980, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9932243824005127, "global_step": 628981, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.1401004791259766, "global_step": 628982, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0258402824401855, "global_step": 628983, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0559589862823486, "global_step": 628984, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.930087685585022, "global_step": 628985, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.985668420791626, "global_step": 628986, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.085149049758911, "global_step": 628987, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.122938632965088, "global_step": 628988, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9370471239089966, "global_step": 628989, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9829199314117432, "global_step": 628990, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0440621376037598, "global_step": 628991, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9701611995697021, "global_step": 628992, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0038750171661377, "global_step": 628993, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9675270318984985, "global_step": 628994, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.990700364112854, "global_step": 628995, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.0244669914245605, "global_step": 628996, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.020120620727539, "global_step": 628997, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.987687349319458, "global_step": 628998, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9409399032592773, "global_step": 628999, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.04634428024292, "global_step": 629000, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.000338077545166, "global_step": 629001, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.003770351409912, "global_step": 629002, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9899979829788208, "global_step": 629003, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9664723873138428, "global_step": 629004, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.017765760421753, "global_step": 629005, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9991804361343384, "global_step": 629006, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9260224103927612, "global_step": 629007, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9548978805541992, "global_step": 629008, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.035801887512207, "global_step": 629009, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9305046796798706, "global_step": 629010, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.007244825363159, "global_step": 629011, "epoch": 997, "lr": 5e-05}
{"train_loss": 2.002953052520752, "global_step": 629012, "epoch": 997, "lr": 5e-05}
{"train_loss": 1.9775511026382446, "global_step": 629013, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0319533348083496, "global_step": 629014, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9739091396331787, "global_step": 629015, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9709116220474243, "global_step": 629016, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9241009950637817, "global_step": 629017, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9036972522735596, "global_step": 629018, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0119144916534424, "global_step": 629019, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.012446165084839, "global_step": 629020, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9904567003250122, "global_step": 629021, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8675291538238525, "global_step": 629022, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9683634042739868, "global_step": 629023, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0016939640045166, "global_step": 629024, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.012742757797241, "global_step": 629025, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.988163948059082, "global_step": 629026, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9803978204727173, "global_step": 629027, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0369443893432617, "global_step": 629028, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.978176474571228, "global_step": 629029, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.068237781524658, "global_step": 629030, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1046504974365234, "global_step": 629031, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9212712049484253, "global_step": 629032, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9314230680465698, "global_step": 629033, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9767934083938599, "global_step": 629034, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9875774383544922, "global_step": 629035, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9698253870010376, "global_step": 629036, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9490039348602295, "global_step": 629037, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.006974458694458, "global_step": 629038, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0909759998321533, "global_step": 629039, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9416844844818115, "global_step": 629040, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0398178100585938, "global_step": 629041, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9498653411865234, "global_step": 629042, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.978337049484253, "global_step": 629043, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8892624378204346, "global_step": 629044, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.017374038696289, "global_step": 629045, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9628421068191528, "global_step": 629046, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9688762426376343, "global_step": 629047, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9722713232040405, "global_step": 629048, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9937525987625122, "global_step": 629049, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9412941932678223, "global_step": 629050, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0786116123199463, "global_step": 629051, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.000429391860962, "global_step": 629052, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9318077564239502, "global_step": 629053, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9600917100906372, "global_step": 629054, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9654322862625122, "global_step": 629055, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0728631019592285, "global_step": 629056, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0077996253967285, "global_step": 629057, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0590624809265137, "global_step": 629058, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0458219051361084, "global_step": 629059, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0213053226470947, "global_step": 629060, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.945533037185669, "global_step": 629061, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0305540561676025, "global_step": 629062, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9398338794708252, "global_step": 629063, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9809954166412354, "global_step": 629064, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9321861267089844, "global_step": 629065, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9409959316253662, "global_step": 629066, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9525030851364136, "global_step": 629067, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9794076681137085, "global_step": 629068, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0132689476013184, "global_step": 629069, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9874083995819092, "global_step": 629070, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9959022998809814, "global_step": 629071, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9913288354873657, "global_step": 629072, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0456862449645996, "global_step": 629073, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9806009531021118, "global_step": 629074, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9741578102111816, "global_step": 629075, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0136525630950928, "global_step": 629076, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.936176061630249, "global_step": 629077, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0043551921844482, "global_step": 629078, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.041922092437744, "global_step": 629079, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.013383388519287, "global_step": 629080, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.015549898147583, "global_step": 629081, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9742482900619507, "global_step": 629082, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9652460813522339, "global_step": 629083, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9319249391555786, "global_step": 629084, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9757447242736816, "global_step": 629085, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9983065128326416, "global_step": 629086, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.036867380142212, "global_step": 629087, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.020923376083374, "global_step": 629088, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9156032800674438, "global_step": 629089, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0261154174804688, "global_step": 629090, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0536227226257324, "global_step": 629091, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0445685386657715, "global_step": 629092, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.979047417640686, "global_step": 629093, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.000293254852295, "global_step": 629094, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.033757209777832, "global_step": 629095, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.024005651473999, "global_step": 629096, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9992022514343262, "global_step": 629097, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9374092817306519, "global_step": 629098, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.003079652786255, "global_step": 629099, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0292720794677734, "global_step": 629100, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9884873628616333, "global_step": 629101, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.027724504470825, "global_step": 629102, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8586273193359375, "global_step": 629103, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0682525634765625, "global_step": 629104, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.018988609313965, "global_step": 629105, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0103180408477783, "global_step": 629106, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9669760465621948, "global_step": 629107, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.975826621055603, "global_step": 629108, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9787797927856445, "global_step": 629109, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.982360601425171, "global_step": 629110, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9240570068359375, "global_step": 629111, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.888260006904602, "global_step": 629112, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9775053262710571, "global_step": 629113, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0081419944763184, "global_step": 629114, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.053988218307495, "global_step": 629115, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9516212940216064, "global_step": 629116, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.050353765487671, "global_step": 629117, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9961040019989014, "global_step": 629118, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0147433280944824, "global_step": 629119, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.011566638946533, "global_step": 629120, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9335150718688965, "global_step": 629121, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9598627090454102, "global_step": 629122, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0279266834259033, "global_step": 629123, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.084549903869629, "global_step": 629124, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.077035665512085, "global_step": 629125, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.998523473739624, "global_step": 629126, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9428943395614624, "global_step": 629127, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.955698013305664, "global_step": 629128, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8741755485534668, "global_step": 629129, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0151286125183105, "global_step": 629130, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0010948181152344, "global_step": 629131, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9560067653656006, "global_step": 629132, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9903101921081543, "global_step": 629133, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9621604681015015, "global_step": 629134, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9835035800933838, "global_step": 629135, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.973838210105896, "global_step": 629136, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0478477478027344, "global_step": 629137, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9011545181274414, "global_step": 629138, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9417426586151123, "global_step": 629139, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.969031810760498, "global_step": 629140, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0073904991149902, "global_step": 629141, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.049804449081421, "global_step": 629142, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.09600567817688, "global_step": 629143, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.03302001953125, "global_step": 629144, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.093742609024048, "global_step": 629145, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9375090599060059, "global_step": 629146, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.018249273300171, "global_step": 629147, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9162957668304443, "global_step": 629148, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.992950677871704, "global_step": 629149, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9776484966278076, "global_step": 629150, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.941983938217163, "global_step": 629151, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9374958276748657, "global_step": 629152, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9060534238815308, "global_step": 629153, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.019803762435913, "global_step": 629154, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9781039953231812, "global_step": 629155, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0228347778320312, "global_step": 629156, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0023837089538574, "global_step": 629157, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0191967487335205, "global_step": 629158, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0377862453460693, "global_step": 629159, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1020257472991943, "global_step": 629160, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0530807971954346, "global_step": 629161, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.989354133605957, "global_step": 629162, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9956932067871094, "global_step": 629163, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0865464210510254, "global_step": 629164, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9631420373916626, "global_step": 629165, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9817861318588257, "global_step": 629166, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0004305839538574, "global_step": 629167, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9348779916763306, "global_step": 629168, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.042339563369751, "global_step": 629169, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0137088298797607, "global_step": 629170, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0065488815307617, "global_step": 629171, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9304816722869873, "global_step": 629172, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.002591848373413, "global_step": 629173, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9152318239212036, "global_step": 629174, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0107786655426025, "global_step": 629175, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.074267625808716, "global_step": 629176, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9934277534484863, "global_step": 629177, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.921891212463379, "global_step": 629178, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.012576103210449, "global_step": 629179, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0214767456054688, "global_step": 629180, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1076786518096924, "global_step": 629181, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9801331758499146, "global_step": 629182, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.105792284011841, "global_step": 629183, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.058540105819702, "global_step": 629184, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8821617364883423, "global_step": 629185, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.005425453186035, "global_step": 629186, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9989677667617798, "global_step": 629187, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9897838830947876, "global_step": 629188, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0195491313934326, "global_step": 629189, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1055891513824463, "global_step": 629190, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9746723175048828, "global_step": 629191, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9159578084945679, "global_step": 629192, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9628123044967651, "global_step": 629193, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9747170209884644, "global_step": 629194, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.060774803161621, "global_step": 629195, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0344042778015137, "global_step": 629196, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0236852169036865, "global_step": 629197, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.969405174255371, "global_step": 629198, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0200817584991455, "global_step": 629199, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0014758110046387, "global_step": 629200, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.941301941871643, "global_step": 629201, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9327948093414307, "global_step": 629202, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.006078004837036, "global_step": 629203, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.047759532928467, "global_step": 629204, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.03185772895813, "global_step": 629205, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9521679878234863, "global_step": 629206, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0183265209198, "global_step": 629207, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9508916139602661, "global_step": 629208, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9175198078155518, "global_step": 629209, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.928276777267456, "global_step": 629210, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0352652072906494, "global_step": 629211, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.061508893966675, "global_step": 629212, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0133910179138184, "global_step": 629213, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0468602180480957, "global_step": 629214, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.098094940185547, "global_step": 629215, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9605921506881714, "global_step": 629216, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0039138793945312, "global_step": 629217, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9686470031738281, "global_step": 629218, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0323615074157715, "global_step": 629219, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0537264347076416, "global_step": 629220, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.047229290008545, "global_step": 629221, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0839529037475586, "global_step": 629222, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.960761308670044, "global_step": 629223, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.975690245628357, "global_step": 629224, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.045886278152466, "global_step": 629225, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9091010093688965, "global_step": 629226, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.005220890045166, "global_step": 629227, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.969185709953308, "global_step": 629228, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.034702777862549, "global_step": 629229, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.889028787612915, "global_step": 629230, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0594844818115234, "global_step": 629231, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0602831840515137, "global_step": 629232, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9214102029800415, "global_step": 629233, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.982817530632019, "global_step": 629234, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.001803398132324, "global_step": 629235, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9805611371994019, "global_step": 629236, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9676750898361206, "global_step": 629237, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9805407524108887, "global_step": 629238, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8938543796539307, "global_step": 629239, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0455522537231445, "global_step": 629240, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0441973209381104, "global_step": 629241, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0728132724761963, "global_step": 629242, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9573938846588135, "global_step": 629243, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9733422994613647, "global_step": 629244, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9717134237289429, "global_step": 629245, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.029550552368164, "global_step": 629246, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.025261163711548, "global_step": 629247, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9021186828613281, "global_step": 629248, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.012268304824829, "global_step": 629249, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.001648426055908, "global_step": 629250, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.034846544265747, "global_step": 629251, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0079479217529297, "global_step": 629252, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9565995931625366, "global_step": 629253, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0337657928466797, "global_step": 629254, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9017488956451416, "global_step": 629255, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.952134609222412, "global_step": 629256, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.071474075317383, "global_step": 629257, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1093602180480957, "global_step": 629258, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.046370267868042, "global_step": 629259, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.997567892074585, "global_step": 629260, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.944405198097229, "global_step": 629261, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.043384075164795, "global_step": 629262, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1181604862213135, "global_step": 629263, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.016169309616089, "global_step": 629264, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9391893148422241, "global_step": 629265, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.088576078414917, "global_step": 629266, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9474399089813232, "global_step": 629267, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.005143165588379, "global_step": 629268, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9371460676193237, "global_step": 629269, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9401510953903198, "global_step": 629270, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0674965381622314, "global_step": 629271, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0215957164764404, "global_step": 629272, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.939833164215088, "global_step": 629273, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.959720253944397, "global_step": 629274, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0676190853118896, "global_step": 629275, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.02988862991333, "global_step": 629276, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9566469192504883, "global_step": 629277, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9720087051391602, "global_step": 629278, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9903006553649902, "global_step": 629279, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0298779010772705, "global_step": 629280, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9928054809570312, "global_step": 629281, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0238471031188965, "global_step": 629282, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.954940915107727, "global_step": 629283, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0487914085388184, "global_step": 629284, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9986605644226074, "global_step": 629285, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9512468576431274, "global_step": 629286, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9271177053451538, "global_step": 629287, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.087907314300537, "global_step": 629288, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0030453205108643, "global_step": 629289, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.032672166824341, "global_step": 629290, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9836163520812988, "global_step": 629291, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.035301923751831, "global_step": 629292, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0355491638183594, "global_step": 629293, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.002133846282959, "global_step": 629294, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9815444946289062, "global_step": 629295, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0028717517852783, "global_step": 629296, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9114747047424316, "global_step": 629297, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.987403392791748, "global_step": 629298, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0518062114715576, "global_step": 629299, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.923967719078064, "global_step": 629300, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9100971221923828, "global_step": 629301, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0045578479766846, "global_step": 629302, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9422852993011475, "global_step": 629303, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9414644241333008, "global_step": 629304, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9512697458267212, "global_step": 629305, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9919605255126953, "global_step": 629306, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9554736614227295, "global_step": 629307, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.993011713027954, "global_step": 629308, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9664263725280762, "global_step": 629309, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0545833110809326, "global_step": 629310, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0309503078460693, "global_step": 629311, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.04929780960083, "global_step": 629312, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.039872884750366, "global_step": 629313, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0677428245544434, "global_step": 629314, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9887572526931763, "global_step": 629315, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0060064792633057, "global_step": 629316, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.940577745437622, "global_step": 629317, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9374828338623047, "global_step": 629318, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0175940990448, "global_step": 629319, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.00093936920166, "global_step": 629320, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0756478309631348, "global_step": 629321, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9916893243789673, "global_step": 629322, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9393409490585327, "global_step": 629323, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.029043197631836, "global_step": 629324, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0214831829071045, "global_step": 629325, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0305404663085938, "global_step": 629326, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.930078148841858, "global_step": 629327, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0021657943725586, "global_step": 629328, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0976028442382812, "global_step": 629329, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.068073272705078, "global_step": 629330, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9253355264663696, "global_step": 629331, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0049915313720703, "global_step": 629332, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.004945755004883, "global_step": 629333, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9579226970672607, "global_step": 629334, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0334584712982178, "global_step": 629335, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0095267295837402, "global_step": 629336, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9620332717895508, "global_step": 629337, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9840402603149414, "global_step": 629338, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9989721775054932, "global_step": 629339, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.96755051612854, "global_step": 629340, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0522377490997314, "global_step": 629341, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9894680976867676, "global_step": 629342, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.931552767753601, "global_step": 629343, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0117194652557373, "global_step": 629344, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9542794227600098, "global_step": 629345, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0333468914031982, "global_step": 629346, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9959913492202759, "global_step": 629347, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0244240760803223, "global_step": 629348, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9908406734466553, "global_step": 629349, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9617946147918701, "global_step": 629350, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9855289459228516, "global_step": 629351, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0097904205322266, "global_step": 629352, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.042677879333496, "global_step": 629353, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.004561185836792, "global_step": 629354, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.077252149581909, "global_step": 629355, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9881988763809204, "global_step": 629356, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9695351123809814, "global_step": 629357, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0169763565063477, "global_step": 629358, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.059140682220459, "global_step": 629359, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.988304853439331, "global_step": 629360, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.017158031463623, "global_step": 629361, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.031261444091797, "global_step": 629362, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.017104387283325, "global_step": 629363, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.961013913154602, "global_step": 629364, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9662905931472778, "global_step": 629365, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9860889911651611, "global_step": 629366, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9058245420455933, "global_step": 629367, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.007903575897217, "global_step": 629368, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0406432151794434, "global_step": 629369, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0168418884277344, "global_step": 629370, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9466131925582886, "global_step": 629371, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9824590682983398, "global_step": 629372, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0139002799987793, "global_step": 629373, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0466883182525635, "global_step": 629374, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9745569229125977, "global_step": 629375, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.036376953125, "global_step": 629376, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9962942600250244, "global_step": 629377, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9208279848098755, "global_step": 629378, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9536924362182617, "global_step": 629379, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.09912371635437, "global_step": 629380, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.024186611175537, "global_step": 629381, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.967859148979187, "global_step": 629382, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.037360668182373, "global_step": 629383, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0363051891326904, "global_step": 629384, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9976842403411865, "global_step": 629385, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9745144844055176, "global_step": 629386, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9941970109939575, "global_step": 629387, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9985651969909668, "global_step": 629388, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0203096866607666, "global_step": 629389, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0445446968078613, "global_step": 629390, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.957414150238037, "global_step": 629391, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9753628969192505, "global_step": 629392, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.070117473602295, "global_step": 629393, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9979248046875, "global_step": 629394, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9503811597824097, "global_step": 629395, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9957904815673828, "global_step": 629396, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0103909969329834, "global_step": 629397, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9747405052185059, "global_step": 629398, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9687165021896362, "global_step": 629399, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0407702922821045, "global_step": 629400, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8897382020950317, "global_step": 629401, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.028568983078003, "global_step": 629402, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0789904594421387, "global_step": 629403, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0079617500305176, "global_step": 629404, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0176825523376465, "global_step": 629405, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9140915870666504, "global_step": 629406, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0549559593200684, "global_step": 629407, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9489085674285889, "global_step": 629408, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9502458572387695, "global_step": 629409, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.029183864593506, "global_step": 629410, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.009751558303833, "global_step": 629411, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9953659772872925, "global_step": 629412, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.061504602432251, "global_step": 629413, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9917718172073364, "global_step": 629414, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.038921594619751, "global_step": 629415, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.975988507270813, "global_step": 629416, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9396414756774902, "global_step": 629417, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.050586223602295, "global_step": 629418, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.010185718536377, "global_step": 629419, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.99587881565094, "global_step": 629420, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9410150051116943, "global_step": 629421, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.064436912536621, "global_step": 629422, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0271313190460205, "global_step": 629423, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0363693237304688, "global_step": 629424, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0363028049468994, "global_step": 629425, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9862356185913086, "global_step": 629426, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9933860301971436, "global_step": 629427, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9354459047317505, "global_step": 629428, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9816538095474243, "global_step": 629429, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.991429090499878, "global_step": 629430, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9821388721466064, "global_step": 629431, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9827053546905518, "global_step": 629432, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9902005195617676, "global_step": 629433, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.985251784324646, "global_step": 629434, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9976911544799805, "global_step": 629435, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.981357455253601, "global_step": 629436, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.995896339416504, "global_step": 629437, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.015429973602295, "global_step": 629438, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0664350986480713, "global_step": 629439, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.001282215118408, "global_step": 629440, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9741580486297607, "global_step": 629441, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0548596382141113, "global_step": 629442, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.029707431793213, "global_step": 629443, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.952583909034729, "global_step": 629444, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9623141288757324, "global_step": 629445, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0435125827789307, "global_step": 629446, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.14250111579895, "global_step": 629447, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.083345651626587, "global_step": 629448, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.025012969970703, "global_step": 629449, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.028979539871216, "global_step": 629450, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.026129722595215, "global_step": 629451, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0133378505706787, "global_step": 629452, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.020111322402954, "global_step": 629453, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.936043381690979, "global_step": 629454, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0744988918304443, "global_step": 629455, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9625495672225952, "global_step": 629456, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9898509979248047, "global_step": 629457, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.033203601837158, "global_step": 629458, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0953798294067383, "global_step": 629459, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0218632221221924, "global_step": 629460, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.078965187072754, "global_step": 629461, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.013331890106201, "global_step": 629462, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0025036334991455, "global_step": 629463, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0519912242889404, "global_step": 629464, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0145223140716553, "global_step": 629465, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9555063247680664, "global_step": 629466, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9724516868591309, "global_step": 629467, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9869019985198975, "global_step": 629468, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9772257804870605, "global_step": 629469, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9947789907455444, "global_step": 629470, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0122103691101074, "global_step": 629471, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9948692321777344, "global_step": 629472, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.91812002658844, "global_step": 629473, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.962912678718567, "global_step": 629474, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.02642822265625, "global_step": 629475, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.042412281036377, "global_step": 629476, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0060949325561523, "global_step": 629477, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0100862979888916, "global_step": 629478, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9773327112197876, "global_step": 629479, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0450868606567383, "global_step": 629480, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9613240957260132, "global_step": 629481, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.951767921447754, "global_step": 629482, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9976847171783447, "global_step": 629483, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.078075647354126, "global_step": 629484, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0606651306152344, "global_step": 629485, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.958201289176941, "global_step": 629486, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.990091323852539, "global_step": 629487, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.91883385181427, "global_step": 629488, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0856943130493164, "global_step": 629489, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0367960929870605, "global_step": 629490, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0279381275177, "global_step": 629491, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.015310049057007, "global_step": 629492, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9419294595718384, "global_step": 629493, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9989840984344482, "global_step": 629494, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0092601776123047, "global_step": 629495, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.051765203475952, "global_step": 629496, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9624165296554565, "global_step": 629497, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9618209600448608, "global_step": 629498, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9291247129440308, "global_step": 629499, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.035525321960449, "global_step": 629500, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9316320419311523, "global_step": 629501, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9730907678604126, "global_step": 629502, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9943039417266846, "global_step": 629503, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.004499673843384, "global_step": 629504, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9970879554748535, "global_step": 629505, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0143744945526123, "global_step": 629506, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0120632648468018, "global_step": 629507, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9895027875900269, "global_step": 629508, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8838741779327393, "global_step": 629509, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9915014505386353, "global_step": 629510, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.950890302658081, "global_step": 629511, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.001276731491089, "global_step": 629512, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.986367106437683, "global_step": 629513, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9251999855041504, "global_step": 629514, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.000417709350586, "global_step": 629515, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.046297311782837, "global_step": 629516, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9023213386535645, "global_step": 629517, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9705443382263184, "global_step": 629518, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9592056274414062, "global_step": 629519, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.112117052078247, "global_step": 629520, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.099362373352051, "global_step": 629521, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9995572566986084, "global_step": 629522, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9993858337402344, "global_step": 629523, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.005115032196045, "global_step": 629524, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.062994956970215, "global_step": 629525, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9780374765396118, "global_step": 629526, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.09023380279541, "global_step": 629527, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0231735706329346, "global_step": 629528, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0023508071899414, "global_step": 629529, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.029176950454712, "global_step": 629530, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9042001962661743, "global_step": 629531, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1197595596313477, "global_step": 629532, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9628673791885376, "global_step": 629533, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0680840015411377, "global_step": 629534, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.024470090866089, "global_step": 629535, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9689910411834717, "global_step": 629536, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0002312660217285, "global_step": 629537, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.007995128631592, "global_step": 629538, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9302958250045776, "global_step": 629539, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.08758807182312, "global_step": 629540, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9569635391235352, "global_step": 629541, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0633809566497803, "global_step": 629542, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.004807233810425, "global_step": 629543, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9756368398666382, "global_step": 629544, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.939794659614563, "global_step": 629545, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0045363903045654, "global_step": 629546, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.040656566619873, "global_step": 629547, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.026350975036621, "global_step": 629548, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9620298147201538, "global_step": 629549, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.027559995651245, "global_step": 629550, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9297789335250854, "global_step": 629551, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9341765642166138, "global_step": 629552, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9827430248260498, "global_step": 629553, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0134289264678955, "global_step": 629554, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.878894329071045, "global_step": 629555, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9976147413253784, "global_step": 629556, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0826058387756348, "global_step": 629557, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.023791551589966, "global_step": 629558, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0281059741973877, "global_step": 629559, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.975490689277649, "global_step": 629560, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.105496644973755, "global_step": 629561, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9978232383728027, "global_step": 629562, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9410896301269531, "global_step": 629563, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.047273635864258, "global_step": 629564, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.960206389427185, "global_step": 629565, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.002000331878662, "global_step": 629566, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.962149739265442, "global_step": 629567, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0110578536987305, "global_step": 629568, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.09897780418396, "global_step": 629569, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9568392038345337, "global_step": 629570, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.962680459022522, "global_step": 629571, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0457630157470703, "global_step": 629572, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.02209734916687, "global_step": 629573, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9788711071014404, "global_step": 629574, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9501073360443115, "global_step": 629575, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9889488220214844, "global_step": 629576, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.03961181640625, "global_step": 629577, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0308239459991455, "global_step": 629578, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.05074143409729, "global_step": 629579, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0232765674591064, "global_step": 629580, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.103743553161621, "global_step": 629581, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9970448017120361, "global_step": 629582, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0233154296875, "global_step": 629583, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0621609687805176, "global_step": 629584, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9936915636062622, "global_step": 629585, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.966422438621521, "global_step": 629586, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.975547194480896, "global_step": 629587, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.063628911972046, "global_step": 629588, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9573006629943848, "global_step": 629589, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.915558099746704, "global_step": 629590, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.040064573287964, "global_step": 629591, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.932151198387146, "global_step": 629592, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.919119119644165, "global_step": 629593, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9255685806274414, "global_step": 629594, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9071321487426758, "global_step": 629595, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.014336109161377, "global_step": 629596, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0272321701049805, "global_step": 629597, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9760310649871826, "global_step": 629598, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.106557846069336, "global_step": 629599, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.006608009338379, "global_step": 629600, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9971437454223633, "global_step": 629601, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9614979028701782, "global_step": 629602, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9853103160858154, "global_step": 629603, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.001638889312744, "global_step": 629604, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9790362119674683, "global_step": 629605, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9717432260513306, "global_step": 629606, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.084291458129883, "global_step": 629607, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.043837547302246, "global_step": 629608, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.020144462585449, "global_step": 629609, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.000552177429199, "global_step": 629610, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.990400791168213, "global_step": 629611, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9727388620376587, "global_step": 629612, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0316779613494873, "global_step": 629613, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.892411470413208, "global_step": 629614, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.114868640899658, "global_step": 629615, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.942521572113037, "global_step": 629616, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.05635929107666, "global_step": 629617, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9732718467712402, "global_step": 629618, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0459835529327393, "global_step": 629619, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.069502830505371, "global_step": 629620, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.117779493331909, "global_step": 629621, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9821977615356445, "global_step": 629622, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0258898735046387, "global_step": 629623, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9887421131134033, "global_step": 629624, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.030529737472534, "global_step": 629625, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0312602519989014, "global_step": 629626, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.010201930999756, "global_step": 629627, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9098535776138306, "global_step": 629628, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.089219331741333, "global_step": 629629, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9841368198394775, "global_step": 629630, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9369014501571655, "global_step": 629631, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9787615537643433, "global_step": 629632, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0145950317382812, "global_step": 629633, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9837353229522705, "global_step": 629634, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.007014274597168, "global_step": 629635, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9478695392608643, "global_step": 629636, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8859658241271973, "global_step": 629637, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0173099040985107, "global_step": 629638, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.992940902709961, "global_step": 629639, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1581225395202637, "global_step": 629640, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9700520038604736, "global_step": 629641, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.069807529449463, "global_step": 629642, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9419326782226562, "global_step": 629643, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0353477001190186, "global_step": 629644, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9358283281326294, "global_step": 629645, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9711806774139404, "global_step": 629646, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9823589324951172, "global_step": 629647, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.946649432182312, "global_step": 629648, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.11592960357666, "global_step": 629649, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0428268909454346, "global_step": 629650, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0216445922851562, "global_step": 629651, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.965523600578308, "global_step": 629652, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.952730655670166, "global_step": 629653, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9523097276687622, "global_step": 629654, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.046444892883301, "global_step": 629655, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.949697732925415, "global_step": 629656, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0607242584228516, "global_step": 629657, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.043649435043335, "global_step": 629658, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.060415029525757, "global_step": 629659, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9514219760894775, "global_step": 629660, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0373432636260986, "global_step": 629661, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9203784465789795, "global_step": 629662, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9261479377746582, "global_step": 629663, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9640541076660156, "global_step": 629664, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9550765752792358, "global_step": 629665, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9585167169570923, "global_step": 629666, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.04443621635437, "global_step": 629667, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.948919653892517, "global_step": 629668, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9923352003097534, "global_step": 629669, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.069244861602783, "global_step": 629670, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.985410213470459, "global_step": 629671, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.108588218688965, "global_step": 629672, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.015568971633911, "global_step": 629673, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9977223873138428, "global_step": 629674, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.000471591949463, "global_step": 629675, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9792038202285767, "global_step": 629676, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0886013507843018, "global_step": 629677, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.060906171798706, "global_step": 629678, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.972872018814087, "global_step": 629679, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0299501419067383, "global_step": 629680, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.026233673095703, "global_step": 629681, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9750727415084839, "global_step": 629682, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0101654529571533, "global_step": 629683, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0228888988494873, "global_step": 629684, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0211966037750244, "global_step": 629685, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9845213890075684, "global_step": 629686, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9764043092727661, "global_step": 629687, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9712555408477783, "global_step": 629688, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.974924087524414, "global_step": 629689, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9856194257736206, "global_step": 629690, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.02878999710083, "global_step": 629691, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9847499132156372, "global_step": 629692, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0718536376953125, "global_step": 629693, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0344583988189697, "global_step": 629694, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0068774223327637, "global_step": 629695, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8790342807769775, "global_step": 629696, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0871312618255615, "global_step": 629697, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.054109573364258, "global_step": 629698, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.972486138343811, "global_step": 629699, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9684655666351318, "global_step": 629700, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0106680393218994, "global_step": 629701, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.957315444946289, "global_step": 629702, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1063296794891357, "global_step": 629703, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0487396717071533, "global_step": 629704, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0062856674194336, "global_step": 629705, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.02945613861084, "global_step": 629706, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.077697277069092, "global_step": 629707, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.958396077156067, "global_step": 629708, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0524702072143555, "global_step": 629709, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.998745083808899, "global_step": 629710, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.015209674835205, "global_step": 629711, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.980526328086853, "global_step": 629712, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.03996205329895, "global_step": 629713, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0590081214904785, "global_step": 629714, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.032464027404785, "global_step": 629715, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.068737030029297, "global_step": 629716, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0365304946899414, "global_step": 629717, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9897363185882568, "global_step": 629718, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1048643589019775, "global_step": 629719, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0175681114196777, "global_step": 629720, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9456348419189453, "global_step": 629721, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9444987773895264, "global_step": 629722, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.014382839202881, "global_step": 629723, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9939852952957153, "global_step": 629724, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.115083932876587, "global_step": 629725, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.970162034034729, "global_step": 629726, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9850573539733887, "global_step": 629727, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0132968425750732, "global_step": 629728, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.048415184020996, "global_step": 629729, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.026704788208008, "global_step": 629730, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0182652473449707, "global_step": 629731, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0536510944366455, "global_step": 629732, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0094709396362305, "global_step": 629733, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0265183448791504, "global_step": 629734, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9893364906311035, "global_step": 629735, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.019320487976074, "global_step": 629736, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1143105030059814, "global_step": 629737, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.891445279121399, "global_step": 629738, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.965467095375061, "global_step": 629739, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0259897708892822, "global_step": 629740, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.008161783218384, "global_step": 629741, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9900190830230713, "global_step": 629742, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0107510089874268, "global_step": 629743, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.014793634414673, "global_step": 629744, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9207022190093994, "global_step": 629745, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0406033992767334, "global_step": 629746, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9983429908752441, "global_step": 629747, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0546412467956543, "global_step": 629748, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0064425468444824, "global_step": 629749, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9885327816009521, "global_step": 629750, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.93442702293396, "global_step": 629751, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.001098394393921, "global_step": 629752, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0433945655822754, "global_step": 629753, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.034444570541382, "global_step": 629754, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0783119201660156, "global_step": 629755, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0511178970336914, "global_step": 629756, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.947609543800354, "global_step": 629757, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0168981552124023, "global_step": 629758, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.008718967437744, "global_step": 629759, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.08298659324646, "global_step": 629760, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9546284675598145, "global_step": 629761, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9911770820617676, "global_step": 629762, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9957958459854126, "global_step": 629763, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0480830669403076, "global_step": 629764, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.003331422805786, "global_step": 629765, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.955125093460083, "global_step": 629766, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.080397605895996, "global_step": 629767, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0329434871673584, "global_step": 629768, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9797173738479614, "global_step": 629769, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0079500675201416, "global_step": 629770, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9503552913665771, "global_step": 629771, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9640997648239136, "global_step": 629772, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0372447967529297, "global_step": 629773, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.933893084526062, "global_step": 629774, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9773755073547363, "global_step": 629775, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0262742042541504, "global_step": 629776, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.976783037185669, "global_step": 629777, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9597175121307373, "global_step": 629778, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.02986478805542, "global_step": 629779, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.917786717414856, "global_step": 629780, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9915058612823486, "global_step": 629781, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.024275302886963, "global_step": 629782, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0249111652374268, "global_step": 629783, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0123307704925537, "global_step": 629784, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.087930202484131, "global_step": 629785, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.038604259490967, "global_step": 629786, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.956501841545105, "global_step": 629787, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0309391021728516, "global_step": 629788, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9779702425003052, "global_step": 629789, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0617153644561768, "global_step": 629790, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9252634048461914, "global_step": 629791, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9875340461730957, "global_step": 629792, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.029538631439209, "global_step": 629793, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.002439498901367, "global_step": 629794, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.037706136703491, "global_step": 629795, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9958170652389526, "global_step": 629796, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.987212896347046, "global_step": 629797, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9477516412734985, "global_step": 629798, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9071896076202393, "global_step": 629799, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.006232976913452, "global_step": 629800, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.992864966392517, "global_step": 629801, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.1124188899993896, "global_step": 629802, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.028442859649658, "global_step": 629803, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0579166412353516, "global_step": 629804, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9937142133712769, "global_step": 629805, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.989825963973999, "global_step": 629806, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0497891902923584, "global_step": 629807, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.08015513420105, "global_step": 629808, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0103235244750977, "global_step": 629809, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0205845832824707, "global_step": 629810, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0732100009918213, "global_step": 629811, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0131633281707764, "global_step": 629812, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0377931594848633, "global_step": 629813, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.077104330062866, "global_step": 629814, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0109152793884277, "global_step": 629815, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.992197871208191, "global_step": 629816, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.999277949333191, "global_step": 629817, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0261878967285156, "global_step": 629818, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0190465450286865, "global_step": 629819, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.013004779815674, "global_step": 629820, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9470542669296265, "global_step": 629821, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.018301486968994, "global_step": 629822, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9570237398147583, "global_step": 629823, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.042785406112671, "global_step": 629824, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9829825162887573, "global_step": 629825, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9613686800003052, "global_step": 629826, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.011678695678711, "global_step": 629827, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.054349899291992, "global_step": 629828, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0022807121276855, "global_step": 629829, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.017024517059326, "global_step": 629830, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.003913640975952, "global_step": 629831, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9690196514129639, "global_step": 629832, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.018037796020508, "global_step": 629833, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9998059272766113, "global_step": 629834, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0140178203582764, "global_step": 629835, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0146799087524414, "global_step": 629836, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0074403285980225, "global_step": 629837, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9951015710830688, "global_step": 629838, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.009606122970581, "global_step": 629839, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.017747402191162, "global_step": 629840, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9440997838974, "global_step": 629841, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0226340293884277, "global_step": 629842, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.052243232727051, "global_step": 629843, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9733233451843262, "global_step": 629844, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9917117357254028, "global_step": 629845, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9471327066421509, "global_step": 629846, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0116701126098633, "global_step": 629847, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.038665294647217, "global_step": 629848, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0719316005706787, "global_step": 629849, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.935985803604126, "global_step": 629850, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.050616502761841, "global_step": 629851, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9848992824554443, "global_step": 629852, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0483500957489014, "global_step": 629853, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0306336879730225, "global_step": 629854, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.023289203643799, "global_step": 629855, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.020233154296875, "global_step": 629856, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.026364803314209, "global_step": 629857, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9968119859695435, "global_step": 629858, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.115466356277466, "global_step": 629859, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.932436466217041, "global_step": 629860, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9466829299926758, "global_step": 629861, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0581412315368652, "global_step": 629862, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0167369842529297, "global_step": 629863, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9715358018875122, "global_step": 629864, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.909369945526123, "global_step": 629865, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0042412281036377, "global_step": 629866, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.031865119934082, "global_step": 629867, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.966972827911377, "global_step": 629868, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9679458141326904, "global_step": 629869, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.036386251449585, "global_step": 629870, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0027265548706055, "global_step": 629871, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8842333555221558, "global_step": 629872, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8936693668365479, "global_step": 629873, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9722963571548462, "global_step": 629874, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.993465542793274, "global_step": 629875, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0863707065582275, "global_step": 629876, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9625136852264404, "global_step": 629877, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9768738746643066, "global_step": 629878, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0090370178222656, "global_step": 629879, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8682000637054443, "global_step": 629880, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9479928016662598, "global_step": 629881, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9979759454727173, "global_step": 629882, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0477895736694336, "global_step": 629883, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9923717975616455, "global_step": 629884, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.019604444503784, "global_step": 629885, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.015911817550659, "global_step": 629886, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9510210752487183, "global_step": 629887, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9952900409698486, "global_step": 629888, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0426063537597656, "global_step": 629889, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0181424617767334, "global_step": 629890, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0642874240875244, "global_step": 629891, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9771755933761597, "global_step": 629892, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9900339841842651, "global_step": 629893, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9809154272079468, "global_step": 629894, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.965149998664856, "global_step": 629895, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9998939037322998, "global_step": 629896, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.984903335571289, "global_step": 629897, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9413261413574219, "global_step": 629898, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9338663816452026, "global_step": 629899, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.073601245880127, "global_step": 629900, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.104691982269287, "global_step": 629901, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0202126502990723, "global_step": 629902, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.021960973739624, "global_step": 629903, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9409481287002563, "global_step": 629904, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9995031356811523, "global_step": 629905, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.990307092666626, "global_step": 629906, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0227160453796387, "global_step": 629907, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9914615154266357, "global_step": 629908, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0220842361450195, "global_step": 629909, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.06168794631958, "global_step": 629910, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9913499355316162, "global_step": 629911, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0644896030426025, "global_step": 629912, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0780177116394043, "global_step": 629913, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9965794086456299, "global_step": 629914, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.049211263656616, "global_step": 629915, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.8962687253952026, "global_step": 629916, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9627445936203003, "global_step": 629917, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0301313400268555, "global_step": 629918, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9539657831192017, "global_step": 629919, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.025111436843872, "global_step": 629920, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0300323963165283, "global_step": 629921, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9874154329299927, "global_step": 629922, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9841030836105347, "global_step": 629923, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.974174976348877, "global_step": 629924, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0805318355560303, "global_step": 629925, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.955344796180725, "global_step": 629926, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0109786987304688, "global_step": 629927, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.010025978088379, "global_step": 629928, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.969650387763977, "global_step": 629929, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0040903091430664, "global_step": 629930, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9571454524993896, "global_step": 629931, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0672309398651123, "global_step": 629932, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.097316265106201, "global_step": 629933, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.025129556655884, "global_step": 629934, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.973089337348938, "global_step": 629935, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.038867235183716, "global_step": 629936, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9860763549804688, "global_step": 629937, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9627408981323242, "global_step": 629938, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.958430290222168, "global_step": 629939, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9881459474563599, "global_step": 629940, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9609572887420654, "global_step": 629941, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9819624423980713, "global_step": 629942, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9977365732192993, "global_step": 629943, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.025277614593506, "global_step": 629944, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.048926591873169, "global_step": 629945, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0322177410125732, "global_step": 629946, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.983133316040039, "global_step": 629947, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0086171627044678, "global_step": 629948, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0170679092407227, "global_step": 629949, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.024730682373047, "global_step": 629950, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9933668375015259, "global_step": 629951, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9253807067871094, "global_step": 629952, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9051162004470825, "global_step": 629953, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.054739236831665, "global_step": 629954, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9752726554870605, "global_step": 629955, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9581775665283203, "global_step": 629956, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.990422010421753, "global_step": 629957, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0107147693634033, "global_step": 629958, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.015349864959717, "global_step": 629959, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0141220092773438, "global_step": 629960, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0563879013061523, "global_step": 629961, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0248184204101562, "global_step": 629962, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9967516660690308, "global_step": 629963, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.965630292892456, "global_step": 629964, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0334060192108154, "global_step": 629965, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.052144765853882, "global_step": 629966, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9375628232955933, "global_step": 629967, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0465850830078125, "global_step": 629968, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0423543453216553, "global_step": 629969, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0185296535491943, "global_step": 629970, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0228271484375, "global_step": 629971, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9934495687484741, "global_step": 629972, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9588137865066528, "global_step": 629973, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0157790184020996, "global_step": 629974, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.061105728149414, "global_step": 629975, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.069450616836548, "global_step": 629976, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0299530029296875, "global_step": 629977, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9044551849365234, "global_step": 629978, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9353936910629272, "global_step": 629979, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0153648853302, "global_step": 629980, "epoch": 998, "lr": 5e-05}
{"train_loss": 2.0007596015930176, "global_step": 629981, "epoch": 998, "lr": 5e-05}
{"train_loss": 1.9441903829574585, "global_step": 629982, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9440863132476807, "global_step": 629983, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9581868648529053, "global_step": 629984, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.019260883331299, "global_step": 629985, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0602941513061523, "global_step": 629986, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0716869831085205, "global_step": 629987, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9367948770523071, "global_step": 629988, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9082268476486206, "global_step": 629989, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.931695818901062, "global_step": 629990, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.949782133102417, "global_step": 629991, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.024043083190918, "global_step": 629992, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.076594591140747, "global_step": 629993, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.89406156539917, "global_step": 629994, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.010401487350464, "global_step": 629995, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0574450492858887, "global_step": 629996, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9050753116607666, "global_step": 629997, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9905699491500854, "global_step": 629998, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.988267183303833, "global_step": 629999, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0107970237731934, "global_step": 630000, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9974696636199951, "global_step": 630001, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9406987428665161, "global_step": 630002, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9090993404388428, "global_step": 630003, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9585554599761963, "global_step": 630004, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9461655616760254, "global_step": 630005, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.982757329940796, "global_step": 630006, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9890247583389282, "global_step": 630007, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.02866530418396, "global_step": 630008, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0283169746398926, "global_step": 630009, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0251872539520264, "global_step": 630010, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.022413969039917, "global_step": 630011, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.034296989440918, "global_step": 630012, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0474579334259033, "global_step": 630013, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9790517091751099, "global_step": 630014, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9940972328186035, "global_step": 630015, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9963057041168213, "global_step": 630016, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0063741207122803, "global_step": 630017, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9721063375473022, "global_step": 630018, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.012847423553467, "global_step": 630019, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0311245918273926, "global_step": 630020, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.007389545440674, "global_step": 630021, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9725494384765625, "global_step": 630022, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.008669137954712, "global_step": 630023, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9846802949905396, "global_step": 630024, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.1108531951904297, "global_step": 630025, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0369603633880615, "global_step": 630026, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9238243103027344, "global_step": 630027, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9200283288955688, "global_step": 630028, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.995486855506897, "global_step": 630029, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.020040512084961, "global_step": 630030, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.992448329925537, "global_step": 630031, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9689178466796875, "global_step": 630032, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.001899003982544, "global_step": 630033, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.910078525543213, "global_step": 630034, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.001408576965332, "global_step": 630035, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9269713163375854, "global_step": 630036, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9324928522109985, "global_step": 630037, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0029730796813965, "global_step": 630038, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.026482582092285, "global_step": 630039, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.12477707862854, "global_step": 630040, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9971858263015747, "global_step": 630041, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.963785171508789, "global_step": 630042, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9941272735595703, "global_step": 630043, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.99643075466156, "global_step": 630044, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.003319025039673, "global_step": 630045, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9056861400604248, "global_step": 630046, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.005028009414673, "global_step": 630047, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9125055074691772, "global_step": 630048, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.057231903076172, "global_step": 630049, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.001730442047119, "global_step": 630050, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.983843207359314, "global_step": 630051, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.041358470916748, "global_step": 630052, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.037738084793091, "global_step": 630053, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0174076557159424, "global_step": 630054, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0036141872406006, "global_step": 630055, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9742774963378906, "global_step": 630056, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.010770082473755, "global_step": 630057, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.084449291229248, "global_step": 630058, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.01175856590271, "global_step": 630059, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9631315469741821, "global_step": 630060, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9308772087097168, "global_step": 630061, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.019559383392334, "global_step": 630062, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9585765600204468, "global_step": 630063, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0060606002807617, "global_step": 630064, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0029690265655518, "global_step": 630065, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9431610107421875, "global_step": 630066, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0002694129943848, "global_step": 630067, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0070080757141113, "global_step": 630068, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.027021646499634, "global_step": 630069, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9248096942901611, "global_step": 630070, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9563393592834473, "global_step": 630071, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.94758939743042, "global_step": 630072, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9555823802947998, "global_step": 630073, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8787353038787842, "global_step": 630074, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9660698175430298, "global_step": 630075, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9106066226959229, "global_step": 630076, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0542593002319336, "global_step": 630077, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.042113780975342, "global_step": 630078, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.025031805038452, "global_step": 630079, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9723140001296997, "global_step": 630080, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.939892292022705, "global_step": 630081, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.025965929031372, "global_step": 630082, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.036705255508423, "global_step": 630083, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.94499933719635, "global_step": 630084, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9368836879730225, "global_step": 630085, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.053257703781128, "global_step": 630086, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9637771844863892, "global_step": 630087, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.969329595565796, "global_step": 630088, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.070960760116577, "global_step": 630089, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.997255802154541, "global_step": 630090, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9779070615768433, "global_step": 630091, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.1135616302490234, "global_step": 630092, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9797502756118774, "global_step": 630093, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.071397304534912, "global_step": 630094, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0538299083709717, "global_step": 630095, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9394361972808838, "global_step": 630096, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.069305896759033, "global_step": 630097, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9507745504379272, "global_step": 630098, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.09578537940979, "global_step": 630099, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9789252281188965, "global_step": 630100, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9832251071929932, "global_step": 630101, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.063249349594116, "global_step": 630102, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.940676212310791, "global_step": 630103, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9721328020095825, "global_step": 630104, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.90146803855896, "global_step": 630105, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9982595443725586, "global_step": 630106, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.086850166320801, "global_step": 630107, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0000061988830566, "global_step": 630108, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0732851028442383, "global_step": 630109, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9225318431854248, "global_step": 630110, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0095391273498535, "global_step": 630111, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9573116302490234, "global_step": 630112, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9596741199493408, "global_step": 630113, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.1289961338043213, "global_step": 630114, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.998093843460083, "global_step": 630115, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.043278455734253, "global_step": 630116, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.946678876876831, "global_step": 630117, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9830591678619385, "global_step": 630118, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0083675384521484, "global_step": 630119, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9847420454025269, "global_step": 630120, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.061692953109741, "global_step": 630121, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.00089693069458, "global_step": 630122, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.040240526199341, "global_step": 630123, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9893666505813599, "global_step": 630124, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9658352136611938, "global_step": 630125, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.93415105342865, "global_step": 630126, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0237112045288086, "global_step": 630127, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9986085891723633, "global_step": 630128, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9480477571487427, "global_step": 630129, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0350146293640137, "global_step": 630130, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.005782127380371, "global_step": 630131, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9490959644317627, "global_step": 630132, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9494205713272095, "global_step": 630133, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.064824342727661, "global_step": 630134, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.071458578109741, "global_step": 630135, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.890906810760498, "global_step": 630136, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9755451679229736, "global_step": 630137, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9910141229629517, "global_step": 630138, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0504038333892822, "global_step": 630139, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.011232614517212, "global_step": 630140, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.038691997528076, "global_step": 630141, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.958233118057251, "global_step": 630142, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0070884227752686, "global_step": 630143, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9860998392105103, "global_step": 630144, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9803789854049683, "global_step": 630145, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.006812572479248, "global_step": 630146, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.98903489112854, "global_step": 630147, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0205395221710205, "global_step": 630148, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9155348539352417, "global_step": 630149, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0224123001098633, "global_step": 630150, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.031799793243408, "global_step": 630151, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8672635555267334, "global_step": 630152, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9418195486068726, "global_step": 630153, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9506661891937256, "global_step": 630154, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8539198637008667, "global_step": 630155, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9698904752731323, "global_step": 630156, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9650121927261353, "global_step": 630157, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9048963785171509, "global_step": 630158, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9678194522857666, "global_step": 630159, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0448176860809326, "global_step": 630160, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.997696042060852, "global_step": 630161, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9365819692611694, "global_step": 630162, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.032423973083496, "global_step": 630163, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8779881000518799, "global_step": 630164, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.088778018951416, "global_step": 630165, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.043184518814087, "global_step": 630166, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8856698274612427, "global_step": 630167, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9802577495574951, "global_step": 630168, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9886760711669922, "global_step": 630169, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9800645112991333, "global_step": 630170, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.998499870300293, "global_step": 630171, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9924547672271729, "global_step": 630172, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0055289268493652, "global_step": 630173, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0389256477355957, "global_step": 630174, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.079561471939087, "global_step": 630175, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.995111107826233, "global_step": 630176, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.967209815979004, "global_step": 630177, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.037980318069458, "global_step": 630178, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0369036197662354, "global_step": 630179, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9821068048477173, "global_step": 630180, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0174124240875244, "global_step": 630181, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9729243516921997, "global_step": 630182, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9601908922195435, "global_step": 630183, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9577140808105469, "global_step": 630184, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.1028833389282227, "global_step": 630185, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.966767430305481, "global_step": 630186, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.007632255554199, "global_step": 630187, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9152355194091797, "global_step": 630188, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0120160579681396, "global_step": 630189, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0629384517669678, "global_step": 630190, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.050076484680176, "global_step": 630191, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9852445125579834, "global_step": 630192, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.038989305496216, "global_step": 630193, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0291740894317627, "global_step": 630194, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.01499342918396, "global_step": 630195, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.007768154144287, "global_step": 630196, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0587847232818604, "global_step": 630197, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.05340838432312, "global_step": 630198, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0552978515625, "global_step": 630199, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9532549381256104, "global_step": 630200, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.980698823928833, "global_step": 630201, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9832887649536133, "global_step": 630202, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9941844940185547, "global_step": 630203, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.025455951690674, "global_step": 630204, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.978751540184021, "global_step": 630205, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9482837915420532, "global_step": 630206, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9887139797210693, "global_step": 630207, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.140434741973877, "global_step": 630208, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.020620107650757, "global_step": 630209, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0239157676696777, "global_step": 630210, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9869529008865356, "global_step": 630211, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9376109838485718, "global_step": 630212, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9944233894348145, "global_step": 630213, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9922529458999634, "global_step": 630214, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0887882709503174, "global_step": 630215, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9324835538864136, "global_step": 630216, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0655694007873535, "global_step": 630217, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.027174472808838, "global_step": 630218, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9834277629852295, "global_step": 630219, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.027677059173584, "global_step": 630220, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9732125997543335, "global_step": 630221, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.932888388633728, "global_step": 630222, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.945911169052124, "global_step": 630223, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9307559728622437, "global_step": 630224, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.953197717666626, "global_step": 630225, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.904887080192566, "global_step": 630226, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0635786056518555, "global_step": 630227, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9159163236618042, "global_step": 630228, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0238020420074463, "global_step": 630229, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.025848388671875, "global_step": 630230, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9448939561843872, "global_step": 630231, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0196707248687744, "global_step": 630232, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9679070711135864, "global_step": 630233, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0510857105255127, "global_step": 630234, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9544717073440552, "global_step": 630235, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9737573862075806, "global_step": 630236, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0037405490875244, "global_step": 630237, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.90036141872406, "global_step": 630238, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0206446647644043, "global_step": 630239, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9036134481430054, "global_step": 630240, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9488683938980103, "global_step": 630241, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9486002922058105, "global_step": 630242, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0423178672790527, "global_step": 630243, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0333640575408936, "global_step": 630244, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.000471830368042, "global_step": 630245, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.072748899459839, "global_step": 630246, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.989371657371521, "global_step": 630247, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0819475650787354, "global_step": 630248, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9946175813674927, "global_step": 630249, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.906782865524292, "global_step": 630250, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0588693618774414, "global_step": 630251, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.079271078109741, "global_step": 630252, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9894840717315674, "global_step": 630253, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0672342777252197, "global_step": 630254, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.080049514770508, "global_step": 630255, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9646910429000854, "global_step": 630256, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.040853261947632, "global_step": 630257, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0590591430664062, "global_step": 630258, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.082404136657715, "global_step": 630259, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0414202213287354, "global_step": 630260, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0122225284576416, "global_step": 630261, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9954748153686523, "global_step": 630262, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.058659553527832, "global_step": 630263, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9845471382141113, "global_step": 630264, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.01678466796875, "global_step": 630265, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.994315505027771, "global_step": 630266, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9799561500549316, "global_step": 630267, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.096653461456299, "global_step": 630268, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.018995761871338, "global_step": 630269, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0098862648010254, "global_step": 630270, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.07316517829895, "global_step": 630271, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9941949844360352, "global_step": 630272, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9909909963607788, "global_step": 630273, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9916990995407104, "global_step": 630274, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9690566062927246, "global_step": 630275, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.913133144378662, "global_step": 630276, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.955786108970642, "global_step": 630277, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9236921072006226, "global_step": 630278, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.049236297607422, "global_step": 630279, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0352935791015625, "global_step": 630280, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.961419939994812, "global_step": 630281, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.028639554977417, "global_step": 630282, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9164214134216309, "global_step": 630283, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.009552478790283, "global_step": 630284, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.963075876235962, "global_step": 630285, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0035831928253174, "global_step": 630286, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9204223155975342, "global_step": 630287, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9657080173492432, "global_step": 630288, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0148327350616455, "global_step": 630289, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.93119478225708, "global_step": 630290, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9903974533081055, "global_step": 630291, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9446139335632324, "global_step": 630292, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9640470743179321, "global_step": 630293, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0150794982910156, "global_step": 630294, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0959231853485107, "global_step": 630295, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9990801811218262, "global_step": 630296, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.039658784866333, "global_step": 630297, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0165445804595947, "global_step": 630298, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9984428882598877, "global_step": 630299, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9909427165985107, "global_step": 630300, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9542661905288696, "global_step": 630301, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.031576156616211, "global_step": 630302, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9215201139450073, "global_step": 630303, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0058083534240723, "global_step": 630304, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9773088693618774, "global_step": 630305, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0449295043945312, "global_step": 630306, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9643068313598633, "global_step": 630307, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.005462646484375, "global_step": 630308, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9858838319778442, "global_step": 630309, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.055530309677124, "global_step": 630310, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9490888118743896, "global_step": 630311, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.075709819793701, "global_step": 630312, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9428479671478271, "global_step": 630313, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.961484670639038, "global_step": 630314, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.084548234939575, "global_step": 630315, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9546468257904053, "global_step": 630316, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9140324592590332, "global_step": 630317, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.052603244781494, "global_step": 630318, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0436277389526367, "global_step": 630319, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.098681926727295, "global_step": 630320, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0762887001037598, "global_step": 630321, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0637216567993164, "global_step": 630322, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9864774942398071, "global_step": 630323, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0633087158203125, "global_step": 630324, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9970009326934814, "global_step": 630325, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.027549982070923, "global_step": 630326, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9058887958526611, "global_step": 630327, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.938330054283142, "global_step": 630328, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0262231826782227, "global_step": 630329, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.057276487350464, "global_step": 630330, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0735957622528076, "global_step": 630331, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.034777879714966, "global_step": 630332, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0160770416259766, "global_step": 630333, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9574413299560547, "global_step": 630334, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9684250354766846, "global_step": 630335, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9999656677246094, "global_step": 630336, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9364415407180786, "global_step": 630337, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.031993865966797, "global_step": 630338, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9918670654296875, "global_step": 630339, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9851410388946533, "global_step": 630340, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9979292154312134, "global_step": 630341, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9988490343093872, "global_step": 630342, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9808874130249023, "global_step": 630343, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9683842658996582, "global_step": 630344, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.972564935684204, "global_step": 630345, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.936381459236145, "global_step": 630346, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0382378101348877, "global_step": 630347, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.020007371902466, "global_step": 630348, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9350671768188477, "global_step": 630349, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9136983156204224, "global_step": 630350, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0217323303222656, "global_step": 630351, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9276635646820068, "global_step": 630352, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0939459800720215, "global_step": 630353, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0127270221710205, "global_step": 630354, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9318336248397827, "global_step": 630355, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0730443000793457, "global_step": 630356, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.989284634590149, "global_step": 630357, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.009901762008667, "global_step": 630358, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0165326595306396, "global_step": 630359, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0286028385162354, "global_step": 630360, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9980190992355347, "global_step": 630361, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9674335718154907, "global_step": 630362, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.105009078979492, "global_step": 630363, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9928663969039917, "global_step": 630364, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0259690284729004, "global_step": 630365, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9167925119400024, "global_step": 630366, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0395421981811523, "global_step": 630367, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.037001371383667, "global_step": 630368, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.958914041519165, "global_step": 630369, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0139849185943604, "global_step": 630370, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.982304573059082, "global_step": 630371, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.988178014755249, "global_step": 630372, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0292041301727295, "global_step": 630373, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0006542205810547, "global_step": 630374, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9796794652938843, "global_step": 630375, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9816738367080688, "global_step": 630376, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9737796783447266, "global_step": 630377, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.976396918296814, "global_step": 630378, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.966536283493042, "global_step": 630379, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0075464248657227, "global_step": 630380, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9794237613677979, "global_step": 630381, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0445542335510254, "global_step": 630382, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.078113555908203, "global_step": 630383, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.987902283668518, "global_step": 630384, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.1483874320983887, "global_step": 630385, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0307319164276123, "global_step": 630386, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.002953052520752, "global_step": 630387, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9536467790603638, "global_step": 630388, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0541954040527344, "global_step": 630389, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.027395009994507, "global_step": 630390, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0851962566375732, "global_step": 630391, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9778326749801636, "global_step": 630392, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.987083911895752, "global_step": 630393, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0837349891662598, "global_step": 630394, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9994826316833496, "global_step": 630395, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9185411930084229, "global_step": 630396, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0411038398742676, "global_step": 630397, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9648927450180054, "global_step": 630398, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0202527046203613, "global_step": 630399, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0561459064483643, "global_step": 630400, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0162851810455322, "global_step": 630401, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0465197563171387, "global_step": 630402, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.020897388458252, "global_step": 630403, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9526317119598389, "global_step": 630404, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9367278814315796, "global_step": 630405, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9159685373306274, "global_step": 630406, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9272644519805908, "global_step": 630407, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.045757532119751, "global_step": 630408, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9218945503234863, "global_step": 630409, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.1004185676574707, "global_step": 630410, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.044058322906494, "global_step": 630411, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9920380115509033, "global_step": 630412, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9558160305023193, "global_step": 630413, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9335334300994873, "global_step": 630414, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0958938598632812, "global_step": 630415, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9535914659500122, "global_step": 630416, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.986006736755371, "global_step": 630417, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.002544403076172, "global_step": 630418, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0077812671661377, "global_step": 630419, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9930301904678345, "global_step": 630420, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9655778408050537, "global_step": 630421, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9781895875930786, "global_step": 630422, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0287628173828125, "global_step": 630423, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0515706539154053, "global_step": 630424, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9602922201156616, "global_step": 630425, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.037630319595337, "global_step": 630426, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0109663009643555, "global_step": 630427, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9699406623840332, "global_step": 630428, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9891244173049927, "global_step": 630429, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9342429637908936, "global_step": 630430, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0670835971832275, "global_step": 630431, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9903634786605835, "global_step": 630432, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.027702808380127, "global_step": 630433, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9658504724502563, "global_step": 630434, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0106847286224365, "global_step": 630435, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9388195276260376, "global_step": 630436, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0237021446228027, "global_step": 630437, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0080339908599854, "global_step": 630438, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.960155963897705, "global_step": 630439, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0128371715545654, "global_step": 630440, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9937896728515625, "global_step": 630441, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9748718738555908, "global_step": 630442, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0238943099975586, "global_step": 630443, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0226402282714844, "global_step": 630444, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.053171157836914, "global_step": 630445, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.038865327835083, "global_step": 630446, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.069566011428833, "global_step": 630447, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.026233673095703, "global_step": 630448, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.868253469467163, "global_step": 630449, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0509047508239746, "global_step": 630450, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0849826335906982, "global_step": 630451, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0533745288848877, "global_step": 630452, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0642900466918945, "global_step": 630453, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9773308038711548, "global_step": 630454, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.994565486907959, "global_step": 630455, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9666918516159058, "global_step": 630456, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.988143801689148, "global_step": 630457, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0025975704193115, "global_step": 630458, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9683787822723389, "global_step": 630459, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.890153169631958, "global_step": 630460, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.99675714969635, "global_step": 630461, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.044826030731201, "global_step": 630462, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0064926147460938, "global_step": 630463, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9957748651504517, "global_step": 630464, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.007572650909424, "global_step": 630465, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9928895235061646, "global_step": 630466, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.009235143661499, "global_step": 630467, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9395068883895874, "global_step": 630468, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.049070358276367, "global_step": 630469, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9788119792938232, "global_step": 630470, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.1029911041259766, "global_step": 630471, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9550766944885254, "global_step": 630472, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9260066747665405, "global_step": 630473, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.985644817352295, "global_step": 630474, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.042332410812378, "global_step": 630475, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9916770458221436, "global_step": 630476, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9909782409667969, "global_step": 630477, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0033068656921387, "global_step": 630478, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8910726308822632, "global_step": 630479, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0492300987243652, "global_step": 630480, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0945396423339844, "global_step": 630481, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9925508499145508, "global_step": 630482, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.025986671447754, "global_step": 630483, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.069258213043213, "global_step": 630484, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.988440752029419, "global_step": 630485, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9550122022628784, "global_step": 630486, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0071587562561035, "global_step": 630487, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0473473072052, "global_step": 630488, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9713855981826782, "global_step": 630489, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.037447452545166, "global_step": 630490, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0484464168548584, "global_step": 630491, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.119267463684082, "global_step": 630492, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0146260261535645, "global_step": 630493, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9790472984313965, "global_step": 630494, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9614115953445435, "global_step": 630495, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9234691858291626, "global_step": 630496, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0078251361846924, "global_step": 630497, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0240092277526855, "global_step": 630498, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9894658327102661, "global_step": 630499, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9929568767547607, "global_step": 630500, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9115946292877197, "global_step": 630501, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9053081274032593, "global_step": 630502, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9941682815551758, "global_step": 630503, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9910540580749512, "global_step": 630504, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0291805267333984, "global_step": 630505, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0262649059295654, "global_step": 630506, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.074120044708252, "global_step": 630507, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9151087999343872, "global_step": 630508, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0673439502716064, "global_step": 630509, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0438995361328125, "global_step": 630510, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0030910968780518, "global_step": 630511, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.074176073074341, "global_step": 630512, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.008452892303467, "global_step": 630513, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.972151517868042, "global_step": 630514, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9280836582183838, "global_step": 630515, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0359408855438232, "global_step": 630516, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0673797130584717, "global_step": 630517, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.986715316772461, "global_step": 630518, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.020852565765381, "global_step": 630519, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.003124475479126, "global_step": 630520, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.977230429649353, "global_step": 630521, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.001331090927124, "global_step": 630522, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9338172674179077, "global_step": 630523, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9416818618774414, "global_step": 630524, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0164694786071777, "global_step": 630525, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.037848949432373, "global_step": 630526, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0984997749328613, "global_step": 630527, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0189616680145264, "global_step": 630528, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0405476093292236, "global_step": 630529, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.948215126991272, "global_step": 630530, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9941914081573486, "global_step": 630531, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.993460774421692, "global_step": 630532, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0127384662628174, "global_step": 630533, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.1059138774871826, "global_step": 630534, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9728096723556519, "global_step": 630535, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0169684886932373, "global_step": 630536, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.993022084236145, "global_step": 630537, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9764182567596436, "global_step": 630538, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9703090190887451, "global_step": 630539, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9661853313446045, "global_step": 630540, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9680095911026, "global_step": 630541, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.95183527469635, "global_step": 630542, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9778435230255127, "global_step": 630543, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.064375400543213, "global_step": 630544, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.1152565479278564, "global_step": 630545, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.008770704269409, "global_step": 630546, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.065877676010132, "global_step": 630547, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.114548444747925, "global_step": 630548, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9737459421157837, "global_step": 630549, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.976900577545166, "global_step": 630550, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0670928955078125, "global_step": 630551, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9721075296401978, "global_step": 630552, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0353739261627197, "global_step": 630553, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.020695686340332, "global_step": 630554, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9616103172302246, "global_step": 630555, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0399508476257324, "global_step": 630556, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9737948179244995, "global_step": 630557, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9996243715286255, "global_step": 630558, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.030395984649658, "global_step": 630559, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.009763240814209, "global_step": 630560, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9862446784973145, "global_step": 630561, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.1023976802825928, "global_step": 630562, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.959032654762268, "global_step": 630563, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9791176319122314, "global_step": 630564, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0328564643859863, "global_step": 630565, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9859600067138672, "global_step": 630566, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0434012413024902, "global_step": 630567, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.971733808517456, "global_step": 630568, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9590555429458618, "global_step": 630569, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0402581691741943, "global_step": 630570, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0062906742095947, "global_step": 630571, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0883798599243164, "global_step": 630572, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.973600149154663, "global_step": 630573, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8731145858764648, "global_step": 630574, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0123329162597656, "global_step": 630575, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9996583461761475, "global_step": 630576, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9778211116790771, "global_step": 630577, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.959592342376709, "global_step": 630578, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9911028146743774, "global_step": 630579, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0561418533325195, "global_step": 630580, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0461859703063965, "global_step": 630581, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9571834802627563, "global_step": 630582, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0279922485351562, "global_step": 630583, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0322978496551514, "global_step": 630584, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9897807836532593, "global_step": 630585, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.014951705932617, "global_step": 630586, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0072858333587646, "global_step": 630587, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.992612361907959, "global_step": 630588, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0255541801452637, "global_step": 630589, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.095686435699463, "global_step": 630590, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9940274953842163, "global_step": 630591, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.059093713760376, "global_step": 630592, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.996612548828125, "global_step": 630593, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.048450469970703, "global_step": 630594, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0283751487731934, "global_step": 630595, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0562000274658203, "global_step": 630596, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0136899948120117, "global_step": 630597, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.052079677581787, "global_step": 630598, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.030259132385254, "global_step": 630599, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0122244358062744, "global_step": 630600, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9088878631591797, "global_step": 630601, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.99940824508667, "global_step": 630602, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.120147466659546, "global_step": 630603, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9632809162139893, "global_step": 630604, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0343661308288574, "global_step": 630605, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0283427238464355, "global_step": 630606, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9818289279937744, "global_step": 630607, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9370096921920776, "global_step": 630608, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9542109966278076, "global_step": 630609, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9367105960845947, "global_step": 630610, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0286223888397217, "global_step": 630611, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.073152780532837, "global_step": 630612, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.020982503890991, "global_step": 630613, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.052885055541992, "global_step": 630614, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9983686208724976, "global_step": 630615, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.090768575668335, "global_step": 630616, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0427331924438477, "global_step": 630617, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.966016173362732, "global_step": 630618, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.026256799697876, "global_step": 630619, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9602584838867188, "global_step": 630620, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9354501962661743, "global_step": 630621, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9201781749725342, "global_step": 630622, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.033531427383423, "global_step": 630623, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.003087282180786, "global_step": 630624, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9851224422454834, "global_step": 630625, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.024996757507324, "global_step": 630626, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9668519496917725, "global_step": 630627, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.004455089569092, "global_step": 630628, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9900407791137695, "global_step": 630629, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9924659729003906, "global_step": 630630, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0089144706726074, "global_step": 630631, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9736162424087524, "global_step": 630632, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.983189582824707, "global_step": 630633, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.095689058303833, "global_step": 630634, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.03279447555542, "global_step": 630635, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9956315755844116, "global_step": 630636, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9822500944137573, "global_step": 630637, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.008643627166748, "global_step": 630638, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9234495162963867, "global_step": 630639, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9724607467651367, "global_step": 630640, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0272772312164307, "global_step": 630641, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.017037868499756, "global_step": 630642, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0629231929779053, "global_step": 630643, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9059900045394897, "global_step": 630644, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9823148250579834, "global_step": 630645, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.015334129333496, "global_step": 630646, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.065321207046509, "global_step": 630647, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.027224063873291, "global_step": 630648, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9629261493682861, "global_step": 630649, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.946540355682373, "global_step": 630650, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9939202070236206, "global_step": 630651, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0096328258514404, "global_step": 630652, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.037386655807495, "global_step": 630653, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9612425565719604, "global_step": 630654, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9443655014038086, "global_step": 630655, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.010371208190918, "global_step": 630656, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9622299671173096, "global_step": 630657, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.015324115753174, "global_step": 630658, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9842674732208252, "global_step": 630659, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0590388774871826, "global_step": 630660, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9749518632888794, "global_step": 630661, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0118932723999023, "global_step": 630662, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.046654462814331, "global_step": 630663, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.038142204284668, "global_step": 630664, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9868882894515991, "global_step": 630665, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9511321783065796, "global_step": 630666, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0124948024749756, "global_step": 630667, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0249810218811035, "global_step": 630668, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9942944049835205, "global_step": 630669, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9898866415023804, "global_step": 630670, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9615463018417358, "global_step": 630671, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.106140613555908, "global_step": 630672, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9634239673614502, "global_step": 630673, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0349621772766113, "global_step": 630674, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.006866931915283, "global_step": 630675, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.015907049179077, "global_step": 630676, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.047194242477417, "global_step": 630677, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.037809371948242, "global_step": 630678, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9634556770324707, "global_step": 630679, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9710882902145386, "global_step": 630680, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9666365385055542, "global_step": 630681, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.057590961456299, "global_step": 630682, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.967738389968872, "global_step": 630683, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.994125247001648, "global_step": 630684, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9969768524169922, "global_step": 630685, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0677435398101807, "global_step": 630686, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9863814115524292, "global_step": 630687, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0160586833953857, "global_step": 630688, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.061103105545044, "global_step": 630689, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9326624870300293, "global_step": 630690, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9998185634613037, "global_step": 630691, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.026890516281128, "global_step": 630692, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.067305088043213, "global_step": 630693, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.045473337173462, "global_step": 630694, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.080660343170166, "global_step": 630695, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9455680847167969, "global_step": 630696, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9081231355667114, "global_step": 630697, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0235648155212402, "global_step": 630698, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0856149196624756, "global_step": 630699, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0925610065460205, "global_step": 630700, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9027515649795532, "global_step": 630701, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9887139797210693, "global_step": 630702, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9846267700195312, "global_step": 630703, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9767411947250366, "global_step": 630704, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.065260887145996, "global_step": 630705, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9740177392959595, "global_step": 630706, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.92216157913208, "global_step": 630707, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.995682954788208, "global_step": 630708, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9548110961914062, "global_step": 630709, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.091054916381836, "global_step": 630710, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.004509687423706, "global_step": 630711, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.952902913093567, "global_step": 630712, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0611886978149414, "global_step": 630713, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.046379804611206, "global_step": 630714, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9649778604507446, "global_step": 630715, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0850167274475098, "global_step": 630716, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.053130865097046, "global_step": 630717, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0249016284942627, "global_step": 630718, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.91921067237854, "global_step": 630719, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0285935401916504, "global_step": 630720, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9964733123779297, "global_step": 630721, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9307868480682373, "global_step": 630722, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9537521600723267, "global_step": 630723, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9708242416381836, "global_step": 630724, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.01847767829895, "global_step": 630725, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9812577962875366, "global_step": 630726, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9834136962890625, "global_step": 630727, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0308425426483154, "global_step": 630728, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9819444417953491, "global_step": 630729, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9929802417755127, "global_step": 630730, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.995841383934021, "global_step": 630731, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9312236309051514, "global_step": 630732, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.022989273071289, "global_step": 630733, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.024790048599243, "global_step": 630734, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9873300790786743, "global_step": 630735, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.030148506164551, "global_step": 630736, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0055477619171143, "global_step": 630737, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9937999248504639, "global_step": 630738, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8979687690734863, "global_step": 630739, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0610568523406982, "global_step": 630740, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8969694375991821, "global_step": 630741, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.016587018966675, "global_step": 630742, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0194413661956787, "global_step": 630743, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.014357805252075, "global_step": 630744, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.991531491279602, "global_step": 630745, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.100830316543579, "global_step": 630746, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.020975351333618, "global_step": 630747, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0283501148223877, "global_step": 630748, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9566222429275513, "global_step": 630749, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0447072982788086, "global_step": 630750, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0694990158081055, "global_step": 630751, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.023793935775757, "global_step": 630752, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.011991262435913, "global_step": 630753, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0128273963928223, "global_step": 630754, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0274274349212646, "global_step": 630755, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0629758834838867, "global_step": 630756, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0034403800964355, "global_step": 630757, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9537054300308228, "global_step": 630758, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8485393524169922, "global_step": 630759, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0248565673828125, "global_step": 630760, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.967739462852478, "global_step": 630761, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.066937208175659, "global_step": 630762, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9781900644302368, "global_step": 630763, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9555243253707886, "global_step": 630764, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0032782554626465, "global_step": 630765, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0457568168640137, "global_step": 630766, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.986009120941162, "global_step": 630767, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9607361555099487, "global_step": 630768, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9793701171875, "global_step": 630769, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0438108444213867, "global_step": 630770, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9998397827148438, "global_step": 630771, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9665676355361938, "global_step": 630772, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0133538246154785, "global_step": 630773, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9754180908203125, "global_step": 630774, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0774028301239014, "global_step": 630775, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8835790157318115, "global_step": 630776, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.00605845451355, "global_step": 630777, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0087714195251465, "global_step": 630778, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.016324520111084, "global_step": 630779, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.00418758392334, "global_step": 630780, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.917716383934021, "global_step": 630781, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9686262607574463, "global_step": 630782, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0268712043762207, "global_step": 630783, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.100867748260498, "global_step": 630784, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0115649700164795, "global_step": 630785, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9684613943099976, "global_step": 630786, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.028310537338257, "global_step": 630787, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9760284423828125, "global_step": 630788, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0036027431488037, "global_step": 630789, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0257492065429688, "global_step": 630790, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.078165054321289, "global_step": 630791, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.952292799949646, "global_step": 630792, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9917795658111572, "global_step": 630793, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9858139753341675, "global_step": 630794, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0871615409851074, "global_step": 630795, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0249547958374023, "global_step": 630796, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.992807149887085, "global_step": 630797, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0547449588775635, "global_step": 630798, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0545520782470703, "global_step": 630799, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.080042839050293, "global_step": 630800, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0609607696533203, "global_step": 630801, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9986634254455566, "global_step": 630802, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.052349805831909, "global_step": 630803, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9922404289245605, "global_step": 630804, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0191490650177, "global_step": 630805, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9455652236938477, "global_step": 630806, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.028468608856201, "global_step": 630807, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9822120666503906, "global_step": 630808, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.056257963180542, "global_step": 630809, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.971930980682373, "global_step": 630810, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.000195026397705, "global_step": 630811, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0301976203918457, "global_step": 630812, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.053224802017212, "global_step": 630813, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9310660362243652, "global_step": 630814, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.963050127029419, "global_step": 630815, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.987244963645935, "global_step": 630816, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9615046977996826, "global_step": 630817, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9530370235443115, "global_step": 630818, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9625109434127808, "global_step": 630819, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0320873260498047, "global_step": 630820, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9106730222702026, "global_step": 630821, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0532312393188477, "global_step": 630822, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.045365571975708, "global_step": 630823, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.049832820892334, "global_step": 630824, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.000218391418457, "global_step": 630825, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.030517578125, "global_step": 630826, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0176827907562256, "global_step": 630827, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9553872346878052, "global_step": 630828, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.08328914642334, "global_step": 630829, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.004351854324341, "global_step": 630830, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9789049625396729, "global_step": 630831, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9652082920074463, "global_step": 630832, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0148916244506836, "global_step": 630833, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.062498092651367, "global_step": 630834, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9810411930084229, "global_step": 630835, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9530538320541382, "global_step": 630836, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9524024724960327, "global_step": 630837, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9510332345962524, "global_step": 630838, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.98287034034729, "global_step": 630839, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0052120685577393, "global_step": 630840, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9784845113754272, "global_step": 630841, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0063955783843994, "global_step": 630842, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9398692846298218, "global_step": 630843, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9932782649993896, "global_step": 630844, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9349499940872192, "global_step": 630845, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0372860431671143, "global_step": 630846, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.00294828414917, "global_step": 630847, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9776805639266968, "global_step": 630848, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9056239128112793, "global_step": 630849, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.978053331375122, "global_step": 630850, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0656611919403076, "global_step": 630851, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0780298709869385, "global_step": 630852, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9384961128234863, "global_step": 630853, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.086047887802124, "global_step": 630854, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.992829442024231, "global_step": 630855, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.036128520965576, "global_step": 630856, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9568488597869873, "global_step": 630857, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9916311502456665, "global_step": 630858, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.1195993423461914, "global_step": 630859, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0833749771118164, "global_step": 630860, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.036046028137207, "global_step": 630861, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.00834321975708, "global_step": 630862, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.071727752685547, "global_step": 630863, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.074220895767212, "global_step": 630864, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9754841327667236, "global_step": 630865, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0340192317962646, "global_step": 630866, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.938212275505066, "global_step": 630867, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.979266881942749, "global_step": 630868, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9447342157363892, "global_step": 630869, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9880629777908325, "global_step": 630870, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.994530439376831, "global_step": 630871, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0139050483703613, "global_step": 630872, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9985851049423218, "global_step": 630873, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8884124755859375, "global_step": 630874, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0088255405426025, "global_step": 630875, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0530569553375244, "global_step": 630876, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0209426879882812, "global_step": 630877, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0736379623413086, "global_step": 630878, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0432891845703125, "global_step": 630879, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.944198727607727, "global_step": 630880, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0077426433563232, "global_step": 630881, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9648504257202148, "global_step": 630882, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.059753894805908, "global_step": 630883, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8962786197662354, "global_step": 630884, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.059814929962158, "global_step": 630885, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0284900665283203, "global_step": 630886, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.995066523551941, "global_step": 630887, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9701271057128906, "global_step": 630888, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9678354263305664, "global_step": 630889, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.033708333969116, "global_step": 630890, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9858617782592773, "global_step": 630891, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9952279329299927, "global_step": 630892, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9989326000213623, "global_step": 630893, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.980830192565918, "global_step": 630894, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9154607057571411, "global_step": 630895, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9755666255950928, "global_step": 630896, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9766652584075928, "global_step": 630897, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0000696182250977, "global_step": 630898, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9301049709320068, "global_step": 630899, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9390491247177124, "global_step": 630900, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9788413047790527, "global_step": 630901, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0012383460998535, "global_step": 630902, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9696383476257324, "global_step": 630903, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9705764055252075, "global_step": 630904, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0199763774871826, "global_step": 630905, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9928276538848877, "global_step": 630906, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9653900861740112, "global_step": 630907, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0320932865142822, "global_step": 630908, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9325066804885864, "global_step": 630909, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9987363815307617, "global_step": 630910, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0313451290130615, "global_step": 630911, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9434001445770264, "global_step": 630912, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.084958553314209, "global_step": 630913, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9451998472213745, "global_step": 630914, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0885798931121826, "global_step": 630915, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9854438304901123, "global_step": 630916, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9589357376098633, "global_step": 630917, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9811789989471436, "global_step": 630918, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9238395690917969, "global_step": 630919, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9958760738372803, "global_step": 630920, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0072145462036133, "global_step": 630921, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.99855375289917, "global_step": 630922, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9824646711349487, "global_step": 630923, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.070640802383423, "global_step": 630924, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9679925441741943, "global_step": 630925, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0603902339935303, "global_step": 630926, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0170626640319824, "global_step": 630927, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9621812105178833, "global_step": 630928, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9804569482803345, "global_step": 630929, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.973611831665039, "global_step": 630930, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0311777591705322, "global_step": 630931, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.171292781829834, "global_step": 630932, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.00569224357605, "global_step": 630933, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9451353549957275, "global_step": 630934, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.8893612623214722, "global_step": 630935, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0483927726745605, "global_step": 630936, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9918133020401, "global_step": 630937, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0749447345733643, "global_step": 630938, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9730974435806274, "global_step": 630939, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0376482009887695, "global_step": 630940, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0240511894226074, "global_step": 630941, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9801381826400757, "global_step": 630942, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9434144496917725, "global_step": 630943, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.109898090362549, "global_step": 630944, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0339932441711426, "global_step": 630945, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9526374340057373, "global_step": 630946, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9233328104019165, "global_step": 630947, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9159117937088013, "global_step": 630948, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9465997219085693, "global_step": 630949, "epoch": 999, "lr": 5e-05}
{"train_loss": 2.0001795291900635, "global_step": 630950, "epoch": 999, "lr": 5e-05}
{"train_loss": 1.9817994832992554, "global_step": 630951, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0505735874176025, "global_step": 630952, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.8673181533813477, "global_step": 630953, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9937244653701782, "global_step": 630954, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9828362464904785, "global_step": 630955, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0046050548553467, "global_step": 630956, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.993575930595398, "global_step": 630957, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9719957113265991, "global_step": 630958, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.007528781890869, "global_step": 630959, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0090794563293457, "global_step": 630960, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9267114400863647, "global_step": 630961, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9677932262420654, "global_step": 630962, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0007126331329346, "global_step": 630963, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0050199031829834, "global_step": 630964, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9404293298721313, "global_step": 630965, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9354772567749023, "global_step": 630966, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0206663608551025, "global_step": 630967, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9958823919296265, "global_step": 630968, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0085031986236572, "global_step": 630969, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9522653818130493, "global_step": 630970, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.014817476272583, "global_step": 630971, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0266120433807373, "global_step": 630972, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9508681297302246, "global_step": 630973, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0025415420532227, "global_step": 630974, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.022907257080078, "global_step": 630975, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9974644184112549, "global_step": 630976, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9766435623168945, "global_step": 630977, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9561434984207153, "global_step": 630978, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0684871673583984, "global_step": 630979, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9671924114227295, "global_step": 630980, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9347440004348755, "global_step": 630981, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9402252435684204, "global_step": 630982, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.020780086517334, "global_step": 630983, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9712822437286377, "global_step": 630984, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.906798243522644, "global_step": 630985, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.016733407974243, "global_step": 630986, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.001617193222046, "global_step": 630987, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.003190040588379, "global_step": 630988, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9162484407424927, "global_step": 630989, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.933721899986267, "global_step": 630990, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9549975395202637, "global_step": 630991, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.065495014190674, "global_step": 630992, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.022477149963379, "global_step": 630993, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9979169368743896, "global_step": 630994, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9153481721878052, "global_step": 630995, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9222396612167358, "global_step": 630996, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9837493896484375, "global_step": 630997, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0154430866241455, "global_step": 630998, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9102392196655273, "global_step": 630999, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0423216819763184, "global_step": 631000, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.965476155281067, "global_step": 631001, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0574164390563965, "global_step": 631002, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9866005182266235, "global_step": 631003, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9667694568634033, "global_step": 631004, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.956251621246338, "global_step": 631005, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0487141609191895, "global_step": 631006, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0049784183502197, "global_step": 631007, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9456051588058472, "global_step": 631008, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0814340114593506, "global_step": 631009, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9473330974578857, "global_step": 631010, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0940375328063965, "global_step": 631011, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.998937964439392, "global_step": 631012, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.941657543182373, "global_step": 631013, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9174538850784302, "global_step": 631014, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9603567123413086, "global_step": 631015, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0317933559417725, "global_step": 631016, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0604629516601562, "global_step": 631017, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9500105381011963, "global_step": 631018, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9067753553390503, "global_step": 631019, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0283312797546387, "global_step": 631020, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0173611640930176, "global_step": 631021, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9652055501937866, "global_step": 631022, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.036820650100708, "global_step": 631023, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.997221827507019, "global_step": 631024, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.1079986095428467, "global_step": 631025, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9704004526138306, "global_step": 631026, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9775980710983276, "global_step": 631027, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9542269706726074, "global_step": 631028, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.053370952606201, "global_step": 631029, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.988281488418579, "global_step": 631030, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9902900457382202, "global_step": 631031, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0477139949798584, "global_step": 631032, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0114974975585938, "global_step": 631033, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.985336422920227, "global_step": 631034, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.021709680557251, "global_step": 631035, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9669420719146729, "global_step": 631036, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9752182960510254, "global_step": 631037, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0396885871887207, "global_step": 631038, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0469162464141846, "global_step": 631039, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9217292070388794, "global_step": 631040, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0702970027923584, "global_step": 631041, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9328806400299072, "global_step": 631042, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.051316261291504, "global_step": 631043, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9432965517044067, "global_step": 631044, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.05928373336792, "global_step": 631045, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0484232902526855, "global_step": 631046, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0517117977142334, "global_step": 631047, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.032686948776245, "global_step": 631048, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.007335662841797, "global_step": 631049, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9670847654342651, "global_step": 631050, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9733316898345947, "global_step": 631051, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9248650074005127, "global_step": 631052, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.969206690788269, "global_step": 631053, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0010530948638916, "global_step": 631054, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0085623264312744, "global_step": 631055, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0634353160858154, "global_step": 631056, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.021681308746338, "global_step": 631057, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9839893579483032, "global_step": 631058, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9909467697143555, "global_step": 631059, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.1052331924438477, "global_step": 631060, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0081534385681152, "global_step": 631061, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.045088291168213, "global_step": 631062, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0043106079101562, "global_step": 631063, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0188980102539062, "global_step": 631064, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9678196907043457, "global_step": 631065, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.986948013305664, "global_step": 631066, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.015406847000122, "global_step": 631067, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.059448719024658, "global_step": 631068, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9388173818588257, "global_step": 631069, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.063488006591797, "global_step": 631070, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9741265773773193, "global_step": 631071, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0242276191711426, "global_step": 631072, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9926233291625977, "global_step": 631073, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9175207614898682, "global_step": 631074, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0533359050750732, "global_step": 631075, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0731678009033203, "global_step": 631076, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.027742624282837, "global_step": 631077, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9777992963790894, "global_step": 631078, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.022435426712036, "global_step": 631079, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.977558970451355, "global_step": 631080, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0749495029449463, "global_step": 631081, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.034029483795166, "global_step": 631082, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.065147876739502, "global_step": 631083, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0492444038391113, "global_step": 631084, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9914971590042114, "global_step": 631085, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9223757982254028, "global_step": 631086, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9217419624328613, "global_step": 631087, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9980403184890747, "global_step": 631088, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.00628399848938, "global_step": 631089, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.004523515701294, "global_step": 631090, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9789108037948608, "global_step": 631091, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.962553858757019, "global_step": 631092, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9718194007873535, "global_step": 631093, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9629764556884766, "global_step": 631094, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.997483730316162, "global_step": 631095, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9870487451553345, "global_step": 631096, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0165045261383057, "global_step": 631097, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0139732360839844, "global_step": 631098, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9531049728393555, "global_step": 631099, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9364707469940186, "global_step": 631100, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0634641647338867, "global_step": 631101, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.002794027328491, "global_step": 631102, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.016674757003784, "global_step": 631103, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.013655662536621, "global_step": 631104, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9978327751159668, "global_step": 631105, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0502326488494873, "global_step": 631106, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0289816856384277, "global_step": 631107, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0189695358276367, "global_step": 631108, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9778940677642822, "global_step": 631109, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9971894025802612, "global_step": 631110, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0441553592681885, "global_step": 631111, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9633653163909912, "global_step": 631112, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.002971649169922, "global_step": 631113, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0534353256225586, "global_step": 631114, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9850388765335083, "global_step": 631115, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.027691602706909, "global_step": 631116, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9676662683486938, "global_step": 631117, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0954091548919678, "global_step": 631118, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9140814542770386, "global_step": 631119, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9888643026351929, "global_step": 631120, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.002082109451294, "global_step": 631121, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0070106983184814, "global_step": 631122, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.950858235359192, "global_step": 631123, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0064210891723633, "global_step": 631124, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.928251028060913, "global_step": 631125, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0097901821136475, "global_step": 631126, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9601244926452637, "global_step": 631127, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9818075895309448, "global_step": 631128, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9792506694793701, "global_step": 631129, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0051610469818115, "global_step": 631130, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.1180243492126465, "global_step": 631131, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9056943655014038, "global_step": 631132, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.1171038150787354, "global_step": 631133, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.964104175567627, "global_step": 631134, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.976852536201477, "global_step": 631135, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9828122854232788, "global_step": 631136, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9461748600006104, "global_step": 631137, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0172340869903564, "global_step": 631138, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9738216400146484, "global_step": 631139, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9948984384536743, "global_step": 631140, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9944734573364258, "global_step": 631141, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9369983673095703, "global_step": 631142, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.8979606628417969, "global_step": 631143, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9600523710250854, "global_step": 631144, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.996066927909851, "global_step": 631145, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0097196102142334, "global_step": 631146, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.059288263320923, "global_step": 631147, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.025393009185791, "global_step": 631148, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.8554552793502808, "global_step": 631149, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.974450707435608, "global_step": 631150, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9935837984085083, "global_step": 631151, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0311777591705322, "global_step": 631152, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9670449495315552, "global_step": 631153, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.027299165725708, "global_step": 631154, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.051494598388672, "global_step": 631155, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0009572505950928, "global_step": 631156, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9618254899978638, "global_step": 631157, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.026580810546875, "global_step": 631158, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9727543592453003, "global_step": 631159, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0336344242095947, "global_step": 631160, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0259270668029785, "global_step": 631161, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0626800060272217, "global_step": 631162, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0287015438079834, "global_step": 631163, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0136966705322266, "global_step": 631164, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0181355476379395, "global_step": 631165, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9773954153060913, "global_step": 631166, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0011682510375977, "global_step": 631167, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9667315483093262, "global_step": 631168, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.97031569480896, "global_step": 631169, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9703576564788818, "global_step": 631170, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9743075370788574, "global_step": 631171, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9929180145263672, "global_step": 631172, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9951903820037842, "global_step": 631173, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9202450513839722, "global_step": 631174, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.114685535430908, "global_step": 631175, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.01354718208313, "global_step": 631176, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9936217069625854, "global_step": 631177, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0894837379455566, "global_step": 631178, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9704749584197998, "global_step": 631179, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9905242919921875, "global_step": 631180, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0618858337402344, "global_step": 631181, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0229053497314453, "global_step": 631182, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9852590560913086, "global_step": 631183, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0192654132843018, "global_step": 631184, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0158321857452393, "global_step": 631185, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0591046810150146, "global_step": 631186, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.008777379989624, "global_step": 631187, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.026493549346924, "global_step": 631188, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.037841558456421, "global_step": 631189, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9835433959960938, "global_step": 631190, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9276660680770874, "global_step": 631191, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9560099840164185, "global_step": 631192, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.135380506515503, "global_step": 631193, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9868589639663696, "global_step": 631194, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.025617837905884, "global_step": 631195, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9331287145614624, "global_step": 631196, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9591305255889893, "global_step": 631197, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0164263248443604, "global_step": 631198, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0640997886657715, "global_step": 631199, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9991984367370605, "global_step": 631200, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0412840843200684, "global_step": 631201, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0742945671081543, "global_step": 631202, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9673947095870972, "global_step": 631203, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0161006450653076, "global_step": 631204, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9282457828521729, "global_step": 631205, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9916443824768066, "global_step": 631206, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.927743673324585, "global_step": 631207, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.996495246887207, "global_step": 631208, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9829092025756836, "global_step": 631209, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9425550699234009, "global_step": 631210, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0353498458862305, "global_step": 631211, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0423455238342285, "global_step": 631212, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0275943279266357, "global_step": 631213, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9899139404296875, "global_step": 631214, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.038282632827759, "global_step": 631215, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0346882343292236, "global_step": 631216, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0703470706939697, "global_step": 631217, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.934179425239563, "global_step": 631218, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.994266390800476, "global_step": 631219, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9809114933013916, "global_step": 631220, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9260450601577759, "global_step": 631221, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.956346035003662, "global_step": 631222, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.988165020942688, "global_step": 631223, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9400736093521118, "global_step": 631224, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9841638803482056, "global_step": 631225, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9939993619918823, "global_step": 631226, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9904705286026, "global_step": 631227, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9773695468902588, "global_step": 631228, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0253686904907227, "global_step": 631229, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9515583515167236, "global_step": 631230, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9758317470550537, "global_step": 631231, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0290896892547607, "global_step": 631232, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0071513652801514, "global_step": 631233, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9863249063491821, "global_step": 631234, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.946939468383789, "global_step": 631235, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9786193370819092, "global_step": 631236, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9658238887786865, "global_step": 631237, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.009195327758789, "global_step": 631238, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0002517700195312, "global_step": 631239, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9802289009094238, "global_step": 631240, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.015615463256836, "global_step": 631241, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9483686685562134, "global_step": 631242, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.027924060821533, "global_step": 631243, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.992616891860962, "global_step": 631244, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0242607593536377, "global_step": 631245, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0373916625976562, "global_step": 631246, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0153989791870117, "global_step": 631247, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.959536075592041, "global_step": 631248, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.079319953918457, "global_step": 631249, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0095081329345703, "global_step": 631250, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.038999557495117, "global_step": 631251, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0173184871673584, "global_step": 631252, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9820371866226196, "global_step": 631253, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9528517723083496, "global_step": 631254, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9854308366775513, "global_step": 631255, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9901540279388428, "global_step": 631256, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9826757907867432, "global_step": 631257, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0641963481903076, "global_step": 631258, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0383286476135254, "global_step": 631259, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.96904718875885, "global_step": 631260, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0422911643981934, "global_step": 631261, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.1087143421173096, "global_step": 631262, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9774796962738037, "global_step": 631263, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0227675437927246, "global_step": 631264, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9652619361877441, "global_step": 631265, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.047567844390869, "global_step": 631266, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0059282779693604, "global_step": 631267, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9932202100753784, "global_step": 631268, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9730459451675415, "global_step": 631269, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9843440055847168, "global_step": 631270, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0647594928741455, "global_step": 631271, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.999544620513916, "global_step": 631272, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0626370906829834, "global_step": 631273, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0537540912628174, "global_step": 631274, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9714106321334839, "global_step": 631275, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.966590404510498, "global_step": 631276, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.020425796508789, "global_step": 631277, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9670939445495605, "global_step": 631278, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.058000326156616, "global_step": 631279, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0377120971679688, "global_step": 631280, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9977525472640991, "global_step": 631281, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0531444549560547, "global_step": 631282, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.017961025238037, "global_step": 631283, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.025688886642456, "global_step": 631284, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9948827028274536, "global_step": 631285, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.111743927001953, "global_step": 631286, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9253520965576172, "global_step": 631287, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.948046326637268, "global_step": 631288, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9702073335647583, "global_step": 631289, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.996216058731079, "global_step": 631290, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.068955183029175, "global_step": 631291, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0377776622772217, "global_step": 631292, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.006371021270752, "global_step": 631293, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9856595993041992, "global_step": 631294, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9743572473526, "global_step": 631295, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.024096965789795, "global_step": 631296, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9551141262054443, "global_step": 631297, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9314875602722168, "global_step": 631298, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.003817319869995, "global_step": 631299, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0529403686523438, "global_step": 631300, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0554964542388916, "global_step": 631301, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9253922700881958, "global_step": 631302, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.075819730758667, "global_step": 631303, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9496581554412842, "global_step": 631304, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0474166870117188, "global_step": 631305, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.008124351501465, "global_step": 631306, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0253639221191406, "global_step": 631307, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0326080322265625, "global_step": 631308, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.008456230163574, "global_step": 631309, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0255391597747803, "global_step": 631310, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.1188559532165527, "global_step": 631311, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0866057872772217, "global_step": 631312, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.056962013244629, "global_step": 631313, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9679542779922485, "global_step": 631314, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0113024711608887, "global_step": 631315, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9825934171676636, "global_step": 631316, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0480268001556396, "global_step": 631317, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9565043449401855, "global_step": 631318, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0599939823150635, "global_step": 631319, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9625355005264282, "global_step": 631320, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9721475839614868, "global_step": 631321, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9873019456863403, "global_step": 631322, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.988968849182129, "global_step": 631323, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0069985389709473, "global_step": 631324, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.980616569519043, "global_step": 631325, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0319159030914307, "global_step": 631326, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9638895988464355, "global_step": 631327, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9996004104614258, "global_step": 631328, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.020815849304199, "global_step": 631329, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9831733703613281, "global_step": 631330, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9791762828826904, "global_step": 631331, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0037055015563965, "global_step": 631332, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.173673391342163, "global_step": 631333, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9337036609649658, "global_step": 631334, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0662970542907715, "global_step": 631335, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.99745774269104, "global_step": 631336, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.966658592224121, "global_step": 631337, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9737340211868286, "global_step": 631338, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0419533252716064, "global_step": 631339, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9887666702270508, "global_step": 631340, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9824646711349487, "global_step": 631341, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9762287139892578, "global_step": 631342, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.015514612197876, "global_step": 631343, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.994553804397583, "global_step": 631344, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9972039461135864, "global_step": 631345, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9749934673309326, "global_step": 631346, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0189101696014404, "global_step": 631347, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.975932002067566, "global_step": 631348, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0272018909454346, "global_step": 631349, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9766989946365356, "global_step": 631350, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0057506561279297, "global_step": 631351, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9443732500076294, "global_step": 631352, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.041499376296997, "global_step": 631353, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0366387367248535, "global_step": 631354, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9459178447723389, "global_step": 631355, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.000887632369995, "global_step": 631356, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.077158212661743, "global_step": 631357, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.045116901397705, "global_step": 631358, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.016031265258789, "global_step": 631359, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.034788131713867, "global_step": 631360, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.940227746963501, "global_step": 631361, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9931331872940063, "global_step": 631362, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9933863878250122, "global_step": 631363, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.073366403579712, "global_step": 631364, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.022822618484497, "global_step": 631365, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.056246280670166, "global_step": 631366, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.005510091781616, "global_step": 631367, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0401623249053955, "global_step": 631368, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9681822061538696, "global_step": 631369, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9254474639892578, "global_step": 631370, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.045208692550659, "global_step": 631371, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0549938678741455, "global_step": 631372, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9532372951507568, "global_step": 631373, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9749819040298462, "global_step": 631374, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.063504934310913, "global_step": 631375, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9934041500091553, "global_step": 631376, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0254428386688232, "global_step": 631377, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0352513790130615, "global_step": 631378, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9888436794281006, "global_step": 631379, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9172606468200684, "global_step": 631380, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0305638313293457, "global_step": 631381, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.082979202270508, "global_step": 631382, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.046077251434326, "global_step": 631383, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9923397302627563, "global_step": 631384, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.8681303262710571, "global_step": 631385, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0206491947174072, "global_step": 631386, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.002216339111328, "global_step": 631387, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9423068761825562, "global_step": 631388, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.019597291946411, "global_step": 631389, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9922230243682861, "global_step": 631390, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.001267194747925, "global_step": 631391, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.024827718734741, "global_step": 631392, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9960306882858276, "global_step": 631393, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.00838303565979, "global_step": 631394, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9165552854537964, "global_step": 631395, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0353598594665527, "global_step": 631396, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0184755325317383, "global_step": 631397, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9863146543502808, "global_step": 631398, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.049903631210327, "global_step": 631399, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0070667266845703, "global_step": 631400, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.99379563331604, "global_step": 631401, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.010225772857666, "global_step": 631402, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.048309803009033, "global_step": 631403, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9928920269012451, "global_step": 631404, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9335252046585083, "global_step": 631405, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0480668544769287, "global_step": 631406, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.1607372760772705, "global_step": 631407, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0266876220703125, "global_step": 631408, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.005645513534546, "global_step": 631409, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.005844831466675, "global_step": 631410, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.000322103500366, "global_step": 631411, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0131304264068604, "global_step": 631412, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9737423658370972, "global_step": 631413, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.956459879875183, "global_step": 631414, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0045433044433594, "global_step": 631415, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.036371946334839, "global_step": 631416, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9548555612564087, "global_step": 631417, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9898277521133423, "global_step": 631418, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9745796918869019, "global_step": 631419, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9963514804840088, "global_step": 631420, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.102379083633423, "global_step": 631421, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9550269842147827, "global_step": 631422, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.033736228942871, "global_step": 631423, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0200068950653076, "global_step": 631424, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.8982418775558472, "global_step": 631425, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0409348011016846, "global_step": 631426, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.013918399810791, "global_step": 631427, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.03132963180542, "global_step": 631428, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0114057064056396, "global_step": 631429, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0808863639831543, "global_step": 631430, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0692005157470703, "global_step": 631431, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0254693031311035, "global_step": 631432, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9888594150543213, "global_step": 631433, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9185800552368164, "global_step": 631434, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0041823387145996, "global_step": 631435, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9866862297058105, "global_step": 631436, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0413224697113037, "global_step": 631437, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0501766204833984, "global_step": 631438, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9448857307434082, "global_step": 631439, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.976641058921814, "global_step": 631440, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0362820625305176, "global_step": 631441, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9912129640579224, "global_step": 631442, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0272715091705322, "global_step": 631443, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0538110733032227, "global_step": 631444, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0352113246917725, "global_step": 631445, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.982513666152954, "global_step": 631446, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.995619773864746, "global_step": 631447, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.063307285308838, "global_step": 631448, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9789317846298218, "global_step": 631449, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9774329662322998, "global_step": 631450, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9877638816833496, "global_step": 631451, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9448150396347046, "global_step": 631452, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9738290309906006, "global_step": 631453, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9465032815933228, "global_step": 631454, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.054659128189087, "global_step": 631455, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0188732147216797, "global_step": 631456, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0410473346710205, "global_step": 631457, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0249598026275635, "global_step": 631458, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0021378993988037, "global_step": 631459, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9623194932937622, "global_step": 631460, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9592877626419067, "global_step": 631461, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0902276039123535, "global_step": 631462, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.032776355743408, "global_step": 631463, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9361131191253662, "global_step": 631464, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9987471103668213, "global_step": 631465, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9879769086837769, "global_step": 631466, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.02553391456604, "global_step": 631467, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9798866510391235, "global_step": 631468, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9434614181518555, "global_step": 631469, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0379669666290283, "global_step": 631470, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9661788940429688, "global_step": 631471, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0595338344573975, "global_step": 631472, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.045389413833618, "global_step": 631473, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9523950815200806, "global_step": 631474, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9701329469680786, "global_step": 631475, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9738264083862305, "global_step": 631476, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9823987483978271, "global_step": 631477, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0230605602264404, "global_step": 631478, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0255932807922363, "global_step": 631479, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.991255521774292, "global_step": 631480, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.073093891143799, "global_step": 631481, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9529500007629395, "global_step": 631482, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9902198314666748, "global_step": 631483, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9995362758636475, "global_step": 631484, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.932539463043213, "global_step": 631485, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9907000064849854, "global_step": 631486, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9822019338607788, "global_step": 631487, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0034258365631104, "global_step": 631488, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0914504528045654, "global_step": 631489, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.009138345718384, "global_step": 631490, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9833099842071533, "global_step": 631491, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.007528781890869, "global_step": 631492, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9895148277282715, "global_step": 631493, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9855282306671143, "global_step": 631494, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.007209062576294, "global_step": 631495, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.042004108428955, "global_step": 631496, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9264285564422607, "global_step": 631497, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9529286623001099, "global_step": 631498, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9404207468032837, "global_step": 631499, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0026590824127197, "global_step": 631500, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9735063314437866, "global_step": 631501, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.058594226837158, "global_step": 631502, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.921809196472168, "global_step": 631503, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9119211435317993, "global_step": 631504, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0467100143432617, "global_step": 631505, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.014134645462036, "global_step": 631506, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0864086151123047, "global_step": 631507, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0413949489593506, "global_step": 631508, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9844461679458618, "global_step": 631509, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.017758846282959, "global_step": 631510, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9825509786605835, "global_step": 631511, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9162975549697876, "global_step": 631512, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9880045652389526, "global_step": 631513, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9181822538375854, "global_step": 631514, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.01169753074646, "global_step": 631515, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.088576555252075, "global_step": 631516, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9900617599487305, "global_step": 631517, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9953330755233765, "global_step": 631518, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9801316261291504, "global_step": 631519, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.8900957107543945, "global_step": 631520, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9684845209121704, "global_step": 631521, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9864246845245361, "global_step": 631522, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0613391399383545, "global_step": 631523, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.987892508506775, "global_step": 631524, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0142405033111572, "global_step": 631525, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0542490482330322, "global_step": 631526, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.061927080154419, "global_step": 631527, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.950735330581665, "global_step": 631528, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0272748470306396, "global_step": 631529, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0194435119628906, "global_step": 631530, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.025679349899292, "global_step": 631531, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9896453619003296, "global_step": 631532, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0582985877990723, "global_step": 631533, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.024005651473999, "global_step": 631534, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0407190322875977, "global_step": 631535, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9820369482040405, "global_step": 631536, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9980878829956055, "global_step": 631537, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0105514526367188, "global_step": 631538, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0501792430877686, "global_step": 631539, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9932681322097778, "global_step": 631540, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.963688850402832, "global_step": 631541, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.064602851867676, "global_step": 631542, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9632935523986816, "global_step": 631543, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.046988010406494, "global_step": 631544, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.029329776763916, "global_step": 631545, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9575600624084473, "global_step": 631546, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0053799152374268, "global_step": 631547, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.003822088241577, "global_step": 631548, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9796243906021118, "global_step": 631549, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0098164081573486, "global_step": 631550, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0086987018585205, "global_step": 631551, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9204132556915283, "global_step": 631552, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9527546167373657, "global_step": 631553, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9965777397155762, "global_step": 631554, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9682209491729736, "global_step": 631555, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9482823610305786, "global_step": 631556, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.043114423751831, "global_step": 631557, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9679945707321167, "global_step": 631558, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9369115829467773, "global_step": 631559, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0059356689453125, "global_step": 631560, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.974008321762085, "global_step": 631561, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9535928964614868, "global_step": 631562, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.990734577178955, "global_step": 631563, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9933780431747437, "global_step": 631564, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.056368827819824, "global_step": 631565, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9350805282592773, "global_step": 631566, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9835302829742432, "global_step": 631567, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.033538579940796, "global_step": 631568, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.029777765274048, "global_step": 631569, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9477481842041016, "global_step": 631570, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.028895854949951, "global_step": 631571, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9839366674423218, "global_step": 631572, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9679034948349, "global_step": 631573, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.051581859588623, "global_step": 631574, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0027830600738525, "global_step": 631575, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.984963297843933, "global_step": 631576, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9602456092834473, "global_step": 631577, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.015277624130249, "global_step": 631578, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.976128339767456, "global_step": 631579, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9971798658370972, "global_step": 631580, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.023221015930176, "global_step": 631581, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9777441024780273, "global_step": 631582, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0483570098876953, "global_step": 631583, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.983789086341858, "global_step": 631584, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0077383518218994, "global_step": 631585, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.057065486907959, "global_step": 631586, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9486209154129028, "global_step": 631587, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9816832542419434, "global_step": 631588, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9520753622055054, "global_step": 631589, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9266053438186646, "global_step": 631590, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.971845030784607, "global_step": 631591, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9869858026504517, "global_step": 631592, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0002551078796387, "global_step": 631593, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.8929928541183472, "global_step": 631594, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.009934425354004, "global_step": 631595, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9318106174468994, "global_step": 631596, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0011937618255615, "global_step": 631597, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9801791906356812, "global_step": 631598, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.100477933883667, "global_step": 631599, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0137267112731934, "global_step": 631600, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9510728120803833, "global_step": 631601, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.043004274368286, "global_step": 631602, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.954957365989685, "global_step": 631603, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9901365041732788, "global_step": 631604, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.010939598083496, "global_step": 631605, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9930989742279053, "global_step": 631606, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.885725498199463, "global_step": 631607, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0204834938049316, "global_step": 631608, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0106945037841797, "global_step": 631609, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.033673048019409, "global_step": 631610, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0436034202575684, "global_step": 631611, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0541679859161377, "global_step": 631612, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9744412899017334, "global_step": 631613, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.997533917427063, "global_step": 631614, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.024399757385254, "global_step": 631615, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.020226240158081, "global_step": 631616, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9825350046157837, "global_step": 631617, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0661330223083496, "global_step": 631618, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.010221242904663, "global_step": 631619, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.014230251312256, "global_step": 631620, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0363683700561523, "global_step": 631621, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9995753765106201, "global_step": 631622, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0984325408935547, "global_step": 631623, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0227768421173096, "global_step": 631624, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9333723783493042, "global_step": 631625, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0611891746520996, "global_step": 631626, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9928933382034302, "global_step": 631627, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9346987009048462, "global_step": 631628, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9218801259994507, "global_step": 631629, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.913030982017517, "global_step": 631630, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9954379796981812, "global_step": 631631, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.090085983276367, "global_step": 631632, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.095191240310669, "global_step": 631633, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.007427453994751, "global_step": 631634, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.050851583480835, "global_step": 631635, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9836609363555908, "global_step": 631636, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9666409492492676, "global_step": 631637, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9212559461593628, "global_step": 631638, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9885138273239136, "global_step": 631639, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9414751529693604, "global_step": 631640, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9443316459655762, "global_step": 631641, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.01111102104187, "global_step": 631642, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.970210313796997, "global_step": 631643, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.058216094970703, "global_step": 631644, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9462792873382568, "global_step": 631645, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9727004766464233, "global_step": 631646, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.104275703430176, "global_step": 631647, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.930879831314087, "global_step": 631648, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.938806176185608, "global_step": 631649, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.974595546722412, "global_step": 631650, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9702026844024658, "global_step": 631651, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.060704231262207, "global_step": 631652, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9099451303482056, "global_step": 631653, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0383059978485107, "global_step": 631654, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9938905239105225, "global_step": 631655, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.067518472671509, "global_step": 631656, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.966957449913025, "global_step": 631657, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9974696636199951, "global_step": 631658, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0427536964416504, "global_step": 631659, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.002241849899292, "global_step": 631660, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0058865547180176, "global_step": 631661, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9919712543487549, "global_step": 631662, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9904261827468872, "global_step": 631663, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0091402530670166, "global_step": 631664, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9854592084884644, "global_step": 631665, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0493357181549072, "global_step": 631666, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.04353666305542, "global_step": 631667, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9596325159072876, "global_step": 631668, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.965829849243164, "global_step": 631669, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0143632888793945, "global_step": 631670, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.100039482116699, "global_step": 631671, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0236856937408447, "global_step": 631672, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.992866039276123, "global_step": 631673, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.008404493331909, "global_step": 631674, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9947700500488281, "global_step": 631675, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0904219150543213, "global_step": 631676, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.006061553955078, "global_step": 631677, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.927817940711975, "global_step": 631678, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0665383338928223, "global_step": 631679, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0420002937316895, "global_step": 631680, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.918675184249878, "global_step": 631681, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9950013160705566, "global_step": 631682, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.973280668258667, "global_step": 631683, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.973508596420288, "global_step": 631684, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9532665014266968, "global_step": 631685, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.025604724884033, "global_step": 631686, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9626935720443726, "global_step": 631687, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.056516170501709, "global_step": 631688, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.937329649925232, "global_step": 631689, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9259207248687744, "global_step": 631690, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0286102294921875, "global_step": 631691, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.1128547191619873, "global_step": 631692, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9951756000518799, "global_step": 631693, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.012779474258423, "global_step": 631694, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0275542736053467, "global_step": 631695, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9429116249084473, "global_step": 631696, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.021048069000244, "global_step": 631697, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9997478723526, "global_step": 631698, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9914470911026, "global_step": 631699, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0094714164733887, "global_step": 631700, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.003159523010254, "global_step": 631701, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9086095094680786, "global_step": 631702, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.006856679916382, "global_step": 631703, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0444655418395996, "global_step": 631704, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.00614595413208, "global_step": 631705, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0535409450531006, "global_step": 631706, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0085537433624268, "global_step": 631707, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9777402877807617, "global_step": 631708, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0440914630889893, "global_step": 631709, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0249574184417725, "global_step": 631710, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.08858323097229, "global_step": 631711, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0020854473114014, "global_step": 631712, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.935171365737915, "global_step": 631713, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.976953387260437, "global_step": 631714, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0096230506896973, "global_step": 631715, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9419188499450684, "global_step": 631716, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9968159198760986, "global_step": 631717, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9424035549163818, "global_step": 631718, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.082075834274292, "global_step": 631719, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.966425895690918, "global_step": 631720, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.021827220916748, "global_step": 631721, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0570595264434814, "global_step": 631722, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0566766262054443, "global_step": 631723, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.022068500518799, "global_step": 631724, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9532183408737183, "global_step": 631725, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.015507221221924, "global_step": 631726, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.018458843231201, "global_step": 631727, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0109357833862305, "global_step": 631728, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9422086477279663, "global_step": 631729, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.106001377105713, "global_step": 631730, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.977071762084961, "global_step": 631731, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.051023244857788, "global_step": 631732, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9230139255523682, "global_step": 631733, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0288214683532715, "global_step": 631734, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.981468915939331, "global_step": 631735, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0674192905426025, "global_step": 631736, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.033395290374756, "global_step": 631737, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0356287956237793, "global_step": 631738, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9950793981552124, "global_step": 631739, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0190677642822266, "global_step": 631740, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9323763847351074, "global_step": 631741, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.950984239578247, "global_step": 631742, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9533311128616333, "global_step": 631743, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9925563335418701, "global_step": 631744, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9000914096832275, "global_step": 631745, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.955375075340271, "global_step": 631746, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0181596279144287, "global_step": 631747, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.925046682357788, "global_step": 631748, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9866042137145996, "global_step": 631749, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.087632894515991, "global_step": 631750, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9480501413345337, "global_step": 631751, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0876710414886475, "global_step": 631752, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9983465671539307, "global_step": 631753, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.010165214538574, "global_step": 631754, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0488123893737793, "global_step": 631755, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.959380030632019, "global_step": 631756, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.009523630142212, "global_step": 631757, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9928590059280396, "global_step": 631758, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0282061100006104, "global_step": 631759, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9979350566864014, "global_step": 631760, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9817816019058228, "global_step": 631761, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9857782125473022, "global_step": 631762, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9936918020248413, "global_step": 631763, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.074328899383545, "global_step": 631764, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9938013553619385, "global_step": 631765, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.014976978302002, "global_step": 631766, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0159378051757812, "global_step": 631767, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0077133178710938, "global_step": 631768, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0313210487365723, "global_step": 631769, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9973360300064087, "global_step": 631770, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.050537586212158, "global_step": 631771, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.042015314102173, "global_step": 631772, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0483016967773438, "global_step": 631773, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9620943069458008, "global_step": 631774, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.040386438369751, "global_step": 631775, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0159811973571777, "global_step": 631776, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.083794593811035, "global_step": 631777, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.1107335090637207, "global_step": 631778, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9912813901901245, "global_step": 631779, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9979320764541626, "global_step": 631780, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0557050704956055, "global_step": 631781, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.04183292388916, "global_step": 631782, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9573699235916138, "global_step": 631783, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9970691204071045, "global_step": 631784, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9360147714614868, "global_step": 631785, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0936710834503174, "global_step": 631786, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9490255117416382, "global_step": 631787, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0224225521087646, "global_step": 631788, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.019047737121582, "global_step": 631789, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9863663911819458, "global_step": 631790, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.002246141433716, "global_step": 631791, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9425575733184814, "global_step": 631792, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0015156269073486, "global_step": 631793, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.015326976776123, "global_step": 631794, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.025040626525879, "global_step": 631795, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.033815383911133, "global_step": 631796, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9515396356582642, "global_step": 631797, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0422754287719727, "global_step": 631798, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.019702196121216, "global_step": 631799, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0304319858551025, "global_step": 631800, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.952510952949524, "global_step": 631801, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9664764404296875, "global_step": 631802, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.041189432144165, "global_step": 631803, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9483460187911987, "global_step": 631804, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9681055545806885, "global_step": 631805, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9690607786178589, "global_step": 631806, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0188639163970947, "global_step": 631807, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9776307344436646, "global_step": 631808, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.8754019737243652, "global_step": 631809, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.05350923538208, "global_step": 631810, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9807626008987427, "global_step": 631811, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9696378707885742, "global_step": 631812, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.964769721031189, "global_step": 631813, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9777095317840576, "global_step": 631814, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9714399576187134, "global_step": 631815, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.097191095352173, "global_step": 631816, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9091228246688843, "global_step": 631817, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9757890701293945, "global_step": 631818, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9922744035720825, "global_step": 631819, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.023439645767212, "global_step": 631820, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0022687911987305, "global_step": 631821, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0515666007995605, "global_step": 631822, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.126753091812134, "global_step": 631823, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0026655197143555, "global_step": 631824, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0013270378112793, "global_step": 631825, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.022451400756836, "global_step": 631826, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0304036140441895, "global_step": 631827, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.974176049232483, "global_step": 631828, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9588855504989624, "global_step": 631829, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.110060214996338, "global_step": 631830, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9808861017227173, "global_step": 631831, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.114541530609131, "global_step": 631832, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0113439559936523, "global_step": 631833, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9414650201797485, "global_step": 631834, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0078835487365723, "global_step": 631835, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0197649002075195, "global_step": 631836, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9645498991012573, "global_step": 631837, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9757792949676514, "global_step": 631838, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0031402111053467, "global_step": 631839, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.918739676475525, "global_step": 631840, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0317494869232178, "global_step": 631841, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.900688648223877, "global_step": 631842, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9752310514450073, "global_step": 631843, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0191073417663574, "global_step": 631844, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9725693464279175, "global_step": 631845, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.053814172744751, "global_step": 631846, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.973004937171936, "global_step": 631847, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0158169269561768, "global_step": 631848, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9778691530227661, "global_step": 631849, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0356483459472656, "global_step": 631850, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.040081262588501, "global_step": 631851, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0061745643615723, "global_step": 631852, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9404960870742798, "global_step": 631853, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0507681369781494, "global_step": 631854, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9537326097488403, "global_step": 631855, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9546979665756226, "global_step": 631856, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.977776288986206, "global_step": 631857, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9919201135635376, "global_step": 631858, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9024419784545898, "global_step": 631859, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.98891019821167, "global_step": 631860, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.021393060684204, "global_step": 631861, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.969366431236267, "global_step": 631862, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.994027018547058, "global_step": 631863, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9412842988967896, "global_step": 631864, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9032326936721802, "global_step": 631865, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.894147276878357, "global_step": 631866, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.016295909881592, "global_step": 631867, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.947774887084961, "global_step": 631868, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.008849620819092, "global_step": 631869, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9435902833938599, "global_step": 631870, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.101001739501953, "global_step": 631871, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9470473527908325, "global_step": 631872, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0266706943511963, "global_step": 631873, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.988233208656311, "global_step": 631874, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9832253456115723, "global_step": 631875, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.01545786857605, "global_step": 631876, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9695005416870117, "global_step": 631877, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0247113704681396, "global_step": 631878, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9636061191558838, "global_step": 631879, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.1278395652770996, "global_step": 631880, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9920170307159424, "global_step": 631881, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9916603565216064, "global_step": 631882, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.075528383255005, "global_step": 631883, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.937923550605774, "global_step": 631884, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.030553102493286, "global_step": 631885, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.085235595703125, "global_step": 631886, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9837725162506104, "global_step": 631887, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0088553428649902, "global_step": 631888, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9261471033096313, "global_step": 631889, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9979562759399414, "global_step": 631890, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9774372577667236, "global_step": 631891, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.972140908241272, "global_step": 631892, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0212514400482178, "global_step": 631893, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.001232862472534, "global_step": 631894, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0767953395843506, "global_step": 631895, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.951903223991394, "global_step": 631896, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9783847332000732, "global_step": 631897, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.053335666656494, "global_step": 631898, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9986965656280518, "global_step": 631899, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9777597188949585, "global_step": 631900, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9757190942764282, "global_step": 631901, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.034228563308716, "global_step": 631902, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.011801242828369, "global_step": 631903, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9839472770690918, "global_step": 631904, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0210068225860596, "global_step": 631905, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.057616949081421, "global_step": 631906, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9779287576675415, "global_step": 631907, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9878309965133667, "global_step": 631908, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.065049886703491, "global_step": 631909, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.001931667327881, "global_step": 631910, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9543715715408325, "global_step": 631911, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9785908460617065, "global_step": 631912, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0301320552825928, "global_step": 631913, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9811267852783203, "global_step": 631914, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9183399677276611, "global_step": 631915, "epoch": 1000, "lr": 5e-05}
{"train_loss": 1.9858283996582031, "global_step": 631916, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0016252994537354, "global_step": 631917, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.042268753051758, "global_step": 631918, "epoch": 1000, "lr": 5e-05}
{"train_loss": 2.0002641677856445, "global_step": 631919, "epoch": 1000, "lr": 5e-05, "KITCHEN_SCENE4_put_the_black_bowl_in_the_bottom_drawer_of_the_cabinet_and_close_it/mean_success_rate": 0.8333333333333334, "KITCHEN_SCENE8_put_both_moka_pots_on_the_stove/mean_success_rate": 0.13333333333333333, "LIVING_ROOM_SCENE2_put_both_the_alphabet_soup_and_the_tomato_sauce_in_the_basket/mean_success_rate": 0.03333333333333333, "KITCHEN_SCENE6_put_the_yellow_and_white_mug_in_the_microwave_and_close_it/mean_success_rate": 0.8666666666666667, "KITCHEN_SCENE3_turn_on_the_stove_and_put_the_moka_pot_on_it/mean_success_rate": 0.9333333333333333, "LIVING_ROOM_SCENE2_put_both_the_cream_cheese_box_and_the_butter_in_the_basket/mean_success_rate": 0.43333333333333335, "LIVING_ROOM_SCENE1_put_both_the_alphabet_soup_and_the_cream_cheese_box_in_the_basket/mean_success_rate": 0.0, "LIVING_ROOM_SCENE6_put_the_white_mug_on_the_plate_and_put_the_chocolate_pudding_to_the_right_of_the_plate/mean_success_rate": 0.4, "STUDY_SCENE1_pick_up_the_book_and_place_it_in_the_back_compartment_of_the_caddy/mean_success_rate": 0.5, "LIVING_ROOM_SCENE5_put_the_white_mug_on_the_left_plate_and_put_the_yellow_and_white_mug_on_the_right_plate/mean_success_rate": 0.5666666666666667, "mean_success_rate": 0.47, "val_loss": 5.849298477172852, "test_reconst_mse": 0.07339446246623993}
